From 7f2e104f2eebc2c3e15ae34740c7b05d0362040a Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 15 Jan 2025 20:17:49 +0300
Subject: [PATCH 0001/2753] wifi: ath9k: cleanup struct ath_tx_control and
 ath_tx_prepare()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After switching to mac80211 software queues, pointer to 'struct ath_node'
in 'struct ath_tx_control' is still assigned but not actually used. So drop
it and cleanup related things in 'ath_tx_prepare()'. Compile tested only.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20250115171750.259917-1-dmantipov@yandex.ru
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath9k/ath9k.h | 1 -
 drivers/net/wireless/ath/ath9k/xmit.c  | 9 ---------
 2 files changed, 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index a728cc0387df8..3a7164bf537a8 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -274,7 +274,6 @@ struct ath_node {
 
 struct ath_tx_control {
 	struct ath_txq *txq;
-	struct ath_node *an;
 	struct ieee80211_sta *sta;
 	u8 paprd;
 };
diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c
index db07ce6dbc080..0ac9212e42f75 100644
--- a/drivers/net/wireless/ath/ath9k/xmit.c
+++ b/drivers/net/wireless/ath/ath9k/xmit.c
@@ -2291,19 +2291,10 @@ static int ath_tx_prepare(struct ieee80211_hw *hw, struct sk_buff *skb,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_sta *sta = txctl->sta;
 	struct ieee80211_vif *vif = info->control.vif;
-	struct ath_vif *avp;
 	struct ath_softc *sc = hw->priv;
 	int frmlen = skb->len + FCS_LEN;
 	int padpos, padsize;
 
-	/* NOTE:  sta can be NULL according to net/mac80211.h */
-	if (sta)
-		txctl->an = (struct ath_node *)sta->drv_priv;
-	else if (vif && ieee80211_is_data(hdr->frame_control)) {
-		avp = (void *)vif->drv_priv;
-		txctl->an = &avp->mcast_node;
-	}
-
 	if (info->control.hw_key)
 		frmlen += info->control.hw_key->icv_len;
 

From 8fe64b0fedcb7348080529c46c71ae23f60c9d3e Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Wed, 15 Jan 2025 20:17:50 +0300
Subject: [PATCH 0002/2753] wifi: ath9k: use unsigned long for activity check
 timestamp
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since 'rx_active_check_time' of 'struct ath_softc' is in jiffies,
prefer 'unsigned long' over 'u32' to avoid possible truncation in
'ath_hw_rx_inactive_check()'. Found with clang's -Wshorten-64-to-32,
compile tested only.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20250115171750.259917-2-dmantipov@yandex.ru
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath9k/ath9k.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h
index 3a7164bf537a8..6e38aa7351e33 100644
--- a/drivers/net/wireless/ath/ath9k/ath9k.h
+++ b/drivers/net/wireless/ath/ath9k/ath9k.h
@@ -1017,7 +1017,7 @@ struct ath_softc {
 
 	u8 gtt_cnt;
 	u32 intrstatus;
-	u32 rx_active_check_time;
+	unsigned long rx_active_check_time;
 	u32 rx_active_count;
 	u16 ps_flags; /* PS_* */
 	bool ps_enabled;

From b238941e8e97c17380f6a6a2dc51520b1829c167 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 24 Dec 2024 20:06:11 +0530
Subject: [PATCH 0003/2753] wifi: ath12k: Refactor the monitor Rx parser
 handler argument

Currently, the monitor Rx parser handlers
ath12k_dp_mon_rx_parse_status_tlv() and ath12k_dp_mon_parse_rx_dest()
take the device handle from the caller. However, these handlers
functionality is technically pdev specific. Additionally, the device handle
can be retrieved from the pdev handle. Therefore, for better code
understanding, change the monitor Rx parser handlers argument from the
device handle to the pdev handle.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20241224143613.164921-2-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 5a21961cfd465..85ff89b91624b 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -563,11 +563,12 @@ static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *
 }
 
 static enum hal_rx_mon_status
-ath12k_dp_mon_rx_parse_status_tlv(struct ath12k_base *ab,
+ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
 				  u32 tlv_tag, const void *tlv_data,
 				  u32 userid)
 {
+	struct ath12k_base *ab = ar->ab;
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	u32 info[7];
 
@@ -1180,7 +1181,7 @@ static int ath12k_dp_mon_rx_deliver(struct ath12k *ar, u32 mac_id,
 }
 
 static enum hal_rx_mon_status
-ath12k_dp_mon_parse_rx_dest(struct ath12k_base *ab, struct ath12k_mon_data *pmon,
+ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 			    struct sk_buff *skb)
 {
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
@@ -1208,7 +1209,7 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k_base *ab, struct ath12k_mon_data *pmon
 		if (tlv_tag == HAL_RX_PPDU_END)
 			tlv_len = sizeof(struct hal_rx_rxpcu_classification_overview);
 
-		hal_status = ath12k_dp_mon_rx_parse_status_tlv(ab, pmon,
+		hal_status = ath12k_dp_mon_rx_parse_status_tlv(ar, pmon,
 							       tlv_tag, ptr, tlv_userid);
 		ptr += tlv_len;
 		ptr = PTR_ALIGN(ptr, HAL_TLV_64_ALIGN);
@@ -1228,14 +1229,13 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 				  struct sk_buff *skb,
 				  struct napi_struct *napi)
 {
-	struct ath12k_base *ab = ar->ab;
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	struct dp_mon_mpdu *tmp;
 	struct dp_mon_mpdu *mon_mpdu = pmon->mon_mpdu;
 	struct sk_buff *head_msdu, *tail_msdu;
 	enum hal_rx_mon_status hal_status = HAL_RX_MON_STATUS_BUF_DONE;
 
-	ath12k_dp_mon_parse_rx_dest(ab, pmon, skb);
+	ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
 
 	list_for_each_entry_safe(mon_mpdu, tmp, &pmon->dp_rx_mon_mpdu_list, list) {
 		list_del(&mon_mpdu->list);
@@ -2477,7 +2477,7 @@ int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id,
 
 		for (i = 0; i < dest_idx; i++) {
 			skb = pmon->dest_skb_q[i];
-			hal_status = ath12k_dp_mon_parse_rx_dest(ab, pmon, skb);
+			hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
 
 			if (ppdu_info->peer_id == HAL_INVALID_PEERID ||
 			    hal_status != HAL_RX_MON_STATUS_PPDU_DONE) {

From 844c256892e162e85db52ce2e1f3d14053ecd488 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 24 Dec 2024 20:06:12 +0530
Subject: [PATCH 0004/2753] wifi: ath12k: Refactor the monitor Tx/RX handler
 procedure arguments

Currently, the pdev handle is given along with the mac id to all the
monitor Tx/Rx handler procedure arguments. The mac id information is
derived from the pdev handle itself. Therefore, remove the unnecessary
mac id argument from the handler.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20241224143613.164921-3-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 29 ++++++++++++------------
 drivers/net/wireless/ath/ath12k/dp_mon.h |  7 +++---
 2 files changed, 17 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 85ff89b91624b..ae2f6847bc888 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -845,7 +845,7 @@ static void ath12k_dp_mon_rx_msdus_set_payload(struct ath12k *ar,
 }
 
 static struct sk_buff *
-ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar, u32 mac_id,
+ath12k_dp_mon_rx_merg_msdus(struct ath12k *ar,
 			    struct sk_buff *head_msdu, struct sk_buff *tail_msdu,
 			    struct ieee80211_rx_status *rxs, bool *fcs_err)
 {
@@ -1126,7 +1126,7 @@ static void ath12k_dp_mon_rx_deliver_msdu(struct ath12k *ar, struct napi_struct
 	ieee80211_rx_napi(ath12k_ar_to_hw(ar), pubsta, msdu, napi);
 }
 
-static int ath12k_dp_mon_rx_deliver(struct ath12k *ar, u32 mac_id,
+static int ath12k_dp_mon_rx_deliver(struct ath12k *ar,
 				    struct sk_buff *head_msdu, struct sk_buff *tail_msdu,
 				    struct hal_rx_mon_ppdu_info *ppduinfo,
 				    struct napi_struct *napi)
@@ -1136,7 +1136,7 @@ static int ath12k_dp_mon_rx_deliver(struct ath12k *ar, u32 mac_id,
 	struct ieee80211_rx_status *rxs = &dp->rx_status;
 	bool fcs_err = false;
 
-	mon_skb = ath12k_dp_mon_rx_merg_msdus(ar, mac_id,
+	mon_skb = ath12k_dp_mon_rx_merg_msdus(ar,
 					      head_msdu, tail_msdu,
 					      rxs, &fcs_err);
 	if (!mon_skb)
@@ -1225,7 +1225,6 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
-				  int mac_id,
 				  struct sk_buff *skb,
 				  struct napi_struct *napi)
 {
@@ -1243,7 +1242,7 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 		tail_msdu = mon_mpdu->tail;
 
 		if (head_msdu && tail_msdu) {
-			ath12k_dp_mon_rx_deliver(ar, mac_id, head_msdu,
+			ath12k_dp_mon_rx_deliver(ar, head_msdu,
 						 tail_msdu, ppdu_info, napi);
 		}
 
@@ -1924,7 +1923,7 @@ ath12k_dp_mon_tx_status_get_num_user(u16 tlv_tag,
 }
 
 static void
-ath12k_dp_mon_tx_process_ppdu_info(struct ath12k *ar, int mac_id,
+ath12k_dp_mon_tx_process_ppdu_info(struct ath12k *ar,
 				   struct napi_struct *napi,
 				   struct dp_mon_tx_ppdu_info *tx_ppdu_info)
 {
@@ -1938,7 +1937,7 @@ ath12k_dp_mon_tx_process_ppdu_info(struct ath12k *ar, int mac_id,
 		tail_msdu = mon_mpdu->tail;
 
 		if (head_msdu)
-			ath12k_dp_mon_rx_deliver(ar, mac_id, head_msdu, tail_msdu,
+			ath12k_dp_mon_rx_deliver(ar, head_msdu, tail_msdu,
 						 &tx_ppdu_info->rx_status, napi);
 
 		kfree(mon_mpdu);
@@ -1948,7 +1947,6 @@ ath12k_dp_mon_tx_process_ppdu_info(struct ath12k *ar, int mac_id,
 enum hal_rx_mon_status
 ath12k_dp_mon_tx_parse_mon_status(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
-				  int mac_id,
 				  struct sk_buff *skb,
 				  struct napi_struct *napi,
 				  u32 ppdu_id)
@@ -1995,13 +1993,13 @@ ath12k_dp_mon_tx_parse_mon_status(struct ath12k *ar,
 			break;
 	} while (tlv_status != DP_MON_TX_FES_STATUS_END);
 
-	ath12k_dp_mon_tx_process_ppdu_info(ar, mac_id, napi, tx_data_ppdu_info);
-	ath12k_dp_mon_tx_process_ppdu_info(ar, mac_id, napi, tx_prot_ppdu_info);
+	ath12k_dp_mon_tx_process_ppdu_info(ar, napi, tx_data_ppdu_info);
+	ath12k_dp_mon_tx_process_ppdu_info(ar, napi, tx_prot_ppdu_info);
 
 	return tlv_status;
 }
 
-int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
+int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 			       enum dp_monitor_mode monitor_mode,
 			       struct napi_struct *napi)
 {
@@ -2022,12 +2020,13 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
 	bool end_of_ppdu;
 	struct hal_rx_mon_ppdu_info *ppdu_info;
 	struct ath12k_peer *peer = NULL;
+	u8 pdev_idx = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, ar->pdev_idx);
 
 	ppdu_info = &pmon->mon_ppdu_info;
 	memset(ppdu_info, 0, sizeof(*ppdu_info));
 	ppdu_info->peer_id = HAL_INVALID_PEERID;
 
-	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, mac_id);
+	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, pdev_idx);
 
 	if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE) {
 		mon_dst_ring = &pdev_dp->rxdma_mon_dst_ring[srng_id];
@@ -2077,10 +2076,10 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id, int *budget,
 			skb = pmon->dest_skb_q[i];
 
 			if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE)
-				ath12k_dp_mon_rx_parse_mon_status(ar, pmon, mac_id,
+				ath12k_dp_mon_rx_parse_mon_status(ar, pmon,
 								  skb, napi);
 			else
-				ath12k_dp_mon_tx_parse_mon_status(ar, pmon, mac_id,
+				ath12k_dp_mon_tx_parse_mon_status(ar, pmon,
 								  skb, napi, ppdu_id);
 
 			peer = ath12k_peer_find_by_id(ab, ppdu_info->peer_id);
@@ -2538,7 +2537,7 @@ int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 	if (!ar->monitor_started)
 		ath12k_dp_mon_rx_process_stats(ar, mac_id, napi, &budget);
 	else
-		num_buffs_reaped = ath12k_dp_mon_srng_process(ar, mac_id, &budget,
+		num_buffs_reaped = ath12k_dp_mon_srng_process(ar, &budget,
 							      monitor_mode, napi);
 
 	return num_buffs_reaped;
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.h b/drivers/net/wireless/ath/ath12k/dp_mon.h
index fb9e9c176ce57..64c959c364599 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.h
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_MON_H
@@ -77,12 +77,12 @@ struct dp_mon_tx_ppdu_info {
 enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
-				  int mac_id, struct sk_buff *skb,
+				  struct sk_buff *skb,
 				  struct napi_struct *napi);
 int ath12k_dp_mon_buf_replenish(struct ath12k_base *ab,
 				struct dp_rxdma_mon_ring *buf_ring,
 				int req_entries);
-int ath12k_dp_mon_srng_process(struct ath12k *ar, int mac_id,
+int ath12k_dp_mon_srng_process(struct ath12k *ar,
 			       int *budget, enum dp_monitor_mode monitor_mode,
 			       struct napi_struct *napi);
 int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
@@ -96,7 +96,6 @@ ath12k_dp_mon_tx_status_get_num_user(u16 tlv_tag,
 enum hal_rx_mon_status
 ath12k_dp_mon_tx_parse_mon_status(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
-				  int mac_id,
 				  struct sk_buff *skb,
 				  struct napi_struct *napi,
 				  u32 ppdu_id);

From 1254580d4f831808462e719e00d43a46e4254631 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Tue, 24 Dec 2024 20:06:13 +0530
Subject: [PATCH 0005/2753] wifi: ath12k: Refactor Rx status TLV parsing
 procedure argument

Currently, ath12k_dp_mon_rx_parse_status_tlv() takes the TLV tag, TLV data
and TLV userid as separate arguments from the caller. In the future, the
TLV length will be needed for parsing the EHT TLV tag. Therefore, instead
of increasing the number of arguments, pass the TLV header and retrieve the
necessary fields from the TLV header itself.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20241224143613.164921-4-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index ae2f6847bc888..53f8e8f8959ad 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -565,12 +565,16 @@ static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *
 static enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
-				  u32 tlv_tag, const void *tlv_data,
-				  u32 userid)
+				  const struct hal_tlv_64_hdr *tlv)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
-	u32 info[7];
+	const void *tlv_data = tlv->value;
+	u32 info[7], userid;
+	u16 tlv_tag;
+
+	tlv_tag = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_TAG);
+	userid = le64_get_bits(tlv->tl, HAL_TLV_64_USR_ID);
 
 	switch (tlv_tag) {
 	case HAL_RX_PPDU_START: {
@@ -1187,7 +1191,6 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	struct hal_tlv_64_hdr *tlv;
 	enum hal_rx_mon_status hal_status;
-	u32 tlv_userid;
 	u16 tlv_tag, tlv_len;
 	u8 *ptr = skb->data;
 
@@ -1196,9 +1199,6 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 	do {
 		tlv = (struct hal_tlv_64_hdr *)ptr;
 		tlv_tag = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_TAG);
-		tlv_len = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_LEN);
-		tlv_userid = le64_get_bits(tlv->tl, HAL_TLV_64_USR_ID);
-		ptr += sizeof(*tlv);
 
 		/* The actual length of PPDU_END is the combined length of many PHY
 		 * TLVs that follow. Skip the TLV header and
@@ -1208,10 +1208,11 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 
 		if (tlv_tag == HAL_RX_PPDU_END)
 			tlv_len = sizeof(struct hal_rx_rxpcu_classification_overview);
+		else
+			tlv_len = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_LEN);
 
-		hal_status = ath12k_dp_mon_rx_parse_status_tlv(ar, pmon,
-							       tlv_tag, ptr, tlv_userid);
-		ptr += tlv_len;
+		hal_status = ath12k_dp_mon_rx_parse_status_tlv(ar, pmon, tlv);
+		ptr += sizeof(*tlv) + tlv_len;
 		ptr = PTR_ALIGN(ptr, HAL_TLV_64_ALIGN);
 
 		if ((ptr - skb->data) >= DP_RX_BUFFER_SIZE)

From 5251fd321684b591245a072b765d01a6c22a112c Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 10 Jan 2025 09:54:14 +0800
Subject: [PATCH 0006/2753] wifi: rtw89: coex: Add protect to avoid A2DP lag
 while Wi-Fi connecting

To get a well Wi-Fi RF quality, Wi-Fi need to do RF calibrations. While
Wi-Fi is doing RF calibrations, driver will pause the Bluetooth traffic
to make sure the RF calibration will not be interfered by Bluetooth.
However, if the RF calibrations take too much time, Bluetooth audio
will perform a lag sound. Add a function to make Bluetooth can do
traffic between the individual calibrations to avoid Bluetooth sound
lag. And patch related A2DP coexistence mechanism actions.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250110015416.10704-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c     | 90 +++++++++++--------
 drivers/net/wireless/realtek/rtw89/coex.h     |  2 +
 drivers/net/wireless/realtek/rtw89/core.h     |  3 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  6 ++
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  6 ++
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  6 ++
 .../net/wireless/realtek/rtw89/rtw8852bt.c    |  6 ++
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  6 ++
 8 files changed, 85 insertions(+), 40 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 68316d44b2043..d5b8091e7541d 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -4589,17 +4589,16 @@ static void _action_bt_a2dp(struct rtw89_dev *rtwdev)
 
 	_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
 
+	if (a2dp.vendor_id == 0x4c || dm->leak_ap || bt_linfo->slave_role)
+		dm->slot_dur[CXST_W1] = 20;
+	else
+		dm->slot_dur[CXST_W1] = 40;
+
+	dm->slot_dur[CXST_B1] = BTC_B1_MAX;
+
 	switch (btc->cx.state_map) {
 	case BTC_WBUSY_BNOSCAN: /* wl-busy + bt-A2DP */
-		if (a2dp.vendor_id == 0x4c || dm->leak_ap) {
-			dm->slot_dur[CXST_W1] = 40;
-			dm->slot_dur[CXST_B1] = 200;
-			_set_policy(rtwdev,
-				    BTC_CXP_PAUTO_TDW1B1, BTC_ACT_BT_A2DP);
-		} else {
-			_set_policy(rtwdev,
-				    BTC_CXP_PAUTO_TD50B1, BTC_ACT_BT_A2DP);
-		}
+		_set_policy(rtwdev, BTC_CXP_PAUTO_TDW1B1, BTC_ACT_BT_A2DP);
 		break;
 	case BTC_WBUSY_BSCAN: /* wl-busy + bt-inq + bt-A2DP */
 		_set_policy(rtwdev, BTC_CXP_PAUTO2_TD3050, BTC_ACT_BT_A2DP);
@@ -4609,15 +4608,10 @@ static void _action_bt_a2dp(struct rtw89_dev *rtwdev)
 		break;
 	case BTC_WSCAN_BNOSCAN: /* wl-scan + bt-A2DP */
 	case BTC_WLINKING: /* wl-connecting + bt-A2DP */
-		if (a2dp.vendor_id == 0x4c || dm->leak_ap) {
-			dm->slot_dur[CXST_W1] = 40;
-			dm->slot_dur[CXST_B1] = 200;
-			_set_policy(rtwdev, BTC_CXP_AUTO_TDW1B1,
-				    BTC_ACT_BT_A2DP);
-		} else {
-			_set_policy(rtwdev, BTC_CXP_AUTO_TD50B1,
-				    BTC_ACT_BT_A2DP);
-		}
+		if (btc->cx.wl.rfk_info.con_rfk)
+			_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_BT_A2DP);
+		else
+			_set_policy(rtwdev, BTC_CXP_AUTO_TDW1B1, BTC_ACT_BT_A2DP);
 		break;
 	case BTC_WIDLE:  /* wl-idle + bt-A2DP */
 		_set_policy(rtwdev, BTC_CXP_AUTO_TD20B1, BTC_ACT_BT_A2DP);
@@ -4645,7 +4639,10 @@ static void _action_bt_a2dpsink(struct rtw89_dev *rtwdev)
 		_set_policy(rtwdev, BTC_CXP_FIX_TD2060, BTC_ACT_BT_A2DPSINK);
 		break;
 	case BTC_WLINKING: /* wl-connecting + bt-A2dp_Sink */
-		_set_policy(rtwdev, BTC_CXP_FIX_TD3030, BTC_ACT_BT_A2DPSINK);
+		if (btc->cx.wl.rfk_info.con_rfk)
+			_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_BT_A2DPSINK);
+		else
+			_set_policy(rtwdev, BTC_CXP_FIX_TD3030, BTC_ACT_BT_A2DPSINK);
 		break;
 	case BTC_WIDLE: /* wl-idle + bt-A2dp_Sink */
 		_set_policy(rtwdev, BTC_CXP_FIX_TD2080, BTC_ACT_BT_A2DPSINK);
@@ -4699,21 +4696,20 @@ static void _action_bt_a2dp_hid(struct rtw89_dev *rtwdev)
 
 	_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
 
+	if (a2dp.vendor_id == 0x4c || dm->leak_ap || bt_linfo->slave_role)
+		dm->slot_dur[CXST_W1] = 20;
+	else
+		dm->slot_dur[CXST_W1] = 40;
+
+	dm->slot_dur[CXST_B1] = BTC_B1_MAX;
+
 	switch (btc->cx.state_map) {
 	case BTC_WBUSY_BNOSCAN: /* wl-busy + bt-A2DP+HID */
 	case BTC_WIDLE:  /* wl-idle + bt-A2DP */
-		if (a2dp.vendor_id == 0x4c || dm->leak_ap) {
-			dm->slot_dur[CXST_W1] = 40;
-			dm->slot_dur[CXST_B1] = 200;
-			_set_policy(rtwdev,
-				    BTC_CXP_PAUTO_TDW1B1, BTC_ACT_BT_A2DP_HID);
-		} else {
-			_set_policy(rtwdev,
-				    BTC_CXP_PAUTO_TD50B1, BTC_ACT_BT_A2DP_HID);
-		}
+		_set_policy(rtwdev, BTC_CXP_PAUTO_TDW1B1, BTC_ACT_BT_A2DP_HID);
 		break;
 	case BTC_WBUSY_BSCAN: /* wl-busy + bt-inq + bt-A2DP+HID */
-		_set_policy(rtwdev, BTC_CXP_PAUTO2_TD3050, BTC_ACT_BT_A2DP_HID);
+		_set_policy(rtwdev, BTC_CXP_PAUTO2_TD3070, BTC_ACT_BT_A2DP_HID);
 		break;
 
 	case BTC_WSCAN_BSCAN: /* wl-scan + bt-inq + bt-A2DP+HID */
@@ -4721,15 +4717,10 @@ static void _action_bt_a2dp_hid(struct rtw89_dev *rtwdev)
 		break;
 	case BTC_WSCAN_BNOSCAN: /* wl-scan + bt-A2DP+HID */
 	case BTC_WLINKING: /* wl-connecting + bt-A2DP+HID */
-		if (a2dp.vendor_id == 0x4c || dm->leak_ap) {
-			dm->slot_dur[CXST_W1] = 40;
-			dm->slot_dur[CXST_B1] = 200;
-			_set_policy(rtwdev, BTC_CXP_AUTO_TDW1B1,
-				    BTC_ACT_BT_A2DP_HID);
-		} else {
-			_set_policy(rtwdev, BTC_CXP_AUTO_TD50B1,
-				    BTC_ACT_BT_A2DP_HID);
-		}
+		if (btc->cx.wl.rfk_info.con_rfk)
+			_set_policy(rtwdev, BTC_CXP_OFF_BT, BTC_ACT_BT_A2DP_HID);
+		else
+			_set_policy(rtwdev, BTC_CXP_AUTO_TDW1B1, BTC_ACT_BT_A2DP_HID);
 		break;
 	}
 }
@@ -7002,7 +6993,7 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 		goto exit;
 	}
 
-	if (wl->status.val & btc_scanning_map.val) {
+	if (wl->status.val & btc_scanning_map.val && !wl->rfk_info.con_rfk) {
 		_action_wl_scan(rtwdev);
 		bt->scan_rx_low_pri = true;
 		goto exit;
@@ -11037,3 +11028,24 @@ void rtw89_coex_recognize_ver(struct rtw89_dev *rtwdev)
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC] use version def[%d] = 0x%08x\n",
 		    (int)(btc->ver - rtw89_btc_ver_defs), btc->ver->fw_ver_code);
 }
+
+void rtw89_btc_ntfy_preserve_bt_time(struct rtw89_dev *rtwdev, u32 ms)
+{
+	struct rtw89_btc_bt_link_info *bt_linfo = &rtwdev->btc.cx.bt.link_info;
+	struct rtw89_btc_bt_a2dp_desc a2dp = bt_linfo->a2dp_desc;
+
+	if (test_bit(RTW89_FLAG_SER_HANDLING, rtwdev->flags))
+		return;
+
+	if (!a2dp.exist)
+		return;
+
+	fsleep(ms * 1000);
+}
+EXPORT_SYMBOL(rtw89_btc_ntfy_preserve_bt_time);
+
+void rtw89_btc_ntfy_conn_rfk(struct rtw89_dev *rtwdev, bool state)
+{
+	rtwdev->btc.cx.wl.rfk_info.con_rfk = state;
+}
+EXPORT_SYMBOL(rtw89_btc_ntfy_conn_rfk);
diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index dbdb56e063ef0..757d03675cf4e 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -290,6 +290,8 @@ void rtw89_coex_power_on(struct rtw89_dev *rtwdev);
 void rtw89_btc_set_policy(struct rtw89_dev *rtwdev, u16 policy_type);
 void rtw89_btc_set_policy_v1(struct rtw89_dev *rtwdev, u16 policy_type);
 void rtw89_coex_recognize_ver(struct rtw89_dev *rtwdev);
+void rtw89_btc_ntfy_preserve_bt_time(struct rtw89_dev *rtwdev, u32 ms);
+void rtw89_btc_ntfy_conn_rfk(struct rtw89_dev *rtwdev, bool state);
 
 static inline u8 rtw89_btc_phymap(struct rtw89_dev *rtwdev,
 				  enum rtw89_phy_idx phy_idx,
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index ff4894c7fa8a5..0f2a46e36b042 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -1761,7 +1761,8 @@ struct rtw89_btc_wl_rfk_info {
 	u32 phy_map: 2;
 	u32 band: 2;
 	u32 type: 8;
-	u32 rsvd: 14;
+	u32 con_rfk: 1;
+	u32 rsvd: 13;
 
 	u32 start_time;
 	u32 proc_time;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index c56f70267882a..0487d1cbe6057 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -1596,10 +1596,16 @@ static void rtw8851b_rfk_channel(struct rtw89_dev *rtwdev,
 	enum rtw89_chanctx_idx chanctx_idx = rtwvif_link->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif_link->phy_idx;
 
+	rtw89_btc_ntfy_conn_rfk(rtwdev, true);
+
 	rtw8851b_rx_dck(rtwdev, phy_idx, chanctx_idx);
 	rtw8851b_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8851b_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8851b_dpk(rtwdev, phy_idx, chanctx_idx);
+
+	rtw89_btc_ntfy_conn_rfk(rtwdev, false);
 }
 
 static void rtw8851b_rfk_band_changed(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 9bd2842c27d50..8a9a5201b2ee6 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -1356,10 +1356,16 @@ static void rtw8852a_rfk_channel(struct rtw89_dev *rtwdev,
 	enum rtw89_chanctx_idx chanctx_idx = rtwvif_link->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif_link->phy_idx;
 
+	rtw89_btc_ntfy_conn_rfk(rtwdev, true);
+
 	rtw8852a_rx_dck(rtwdev, phy_idx, true, chanctx_idx);
 	rtw8852a_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852a_tssi(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852a_dpk(rtwdev, phy_idx, chanctx_idx);
+
+	rtw89_btc_ntfy_conn_rfk(rtwdev, false);
 }
 
 static void rtw8852a_rfk_band_changed(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index dfb2bf61b0b83..cbaf54f88af6f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -568,10 +568,16 @@ static void rtw8852b_rfk_channel(struct rtw89_dev *rtwdev,
 	enum rtw89_chanctx_idx chanctx_idx = rtwvif_link->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif_link->phy_idx;
 
+	rtw89_btc_ntfy_conn_rfk(rtwdev, true);
+
 	rtw8852b_rx_dck(rtwdev, phy_idx, chanctx_idx);
 	rtw8852b_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852b_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852b_dpk(rtwdev, phy_idx, chanctx_idx);
+
+	rtw89_btc_ntfy_conn_rfk(rtwdev, false);
 }
 
 static void rtw8852b_rfk_band_changed(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index bde3e1fb7ca62..c0ae5dca30492 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -541,10 +541,16 @@ static void rtw8852bt_rfk_channel(struct rtw89_dev *rtwdev,
 	enum rtw89_chanctx_idx chanctx_idx = rtwvif_link->chanctx_idx;
 	enum rtw89_phy_idx phy_idx = rtwvif_link->phy_idx;
 
+	rtw89_btc_ntfy_conn_rfk(rtwdev, true);
+
 	rtw8852bt_rx_dck(rtwdev, phy_idx, chanctx_idx);
 	rtw8852bt_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852bt_tssi(rtwdev, phy_idx, true, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852bt_dpk(rtwdev, phy_idx, chanctx_idx);
+
+	rtw89_btc_ntfy_conn_rfk(rtwdev, false);
 }
 
 static void rtw8852bt_rfk_band_changed(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index bc84b15e7826d..106df618bb588 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -1853,10 +1853,16 @@ static void rtw8852c_rfk_channel(struct rtw89_dev *rtwdev,
 	enum rtw89_phy_idx phy_idx = rtwvif_link->phy_idx;
 
 	rtw8852c_mcc_get_ch_info(rtwdev, phy_idx);
+	rtw89_btc_ntfy_conn_rfk(rtwdev, true);
+
 	rtw8852c_rx_dck(rtwdev, phy_idx, false);
 	rtw8852c_iqk(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852c_tssi(rtwdev, phy_idx, chanctx_idx);
+	rtw89_btc_ntfy_preserve_bt_time(rtwdev, 30);
 	rtw8852c_dpk(rtwdev, phy_idx, chanctx_idx);
+
+	rtw89_btc_ntfy_conn_rfk(rtwdev, false);
 	rtw89_fw_h2c_rf_ntfy_mcc(rtwdev);
 }
 

From 4a57346652154bb339c48b41166df9154cff33f5 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 10 Jan 2025 09:54:15 +0800
Subject: [PATCH 0007/2753] wifi: rtw89: coex: Separated Wi-Fi connecting event
 from Wi-Fi scan event

Wi-Fi connecting process don't need to assign to firmware slot control,
if assign firmware slot control for Wi-Fi connecting event, firmware will
not toggle slots because driver don't tell the slot schedule to firmware.
Wi-Fi connecting event end should also cancel the 4way handshake status.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250110015416.10704-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index d5b8091e7541d..cde65ee43bac4 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -5399,7 +5399,8 @@ static void _action_wl_scan(struct rtw89_dev *rtwdev)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
 
-	if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) {
+	if (btc->cx.state_map != BTC_WLINKING &&
+	    RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw)) {
 		_action_wl_25g_mcc(rtwdev);
 		rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], Scan offload!\n");
 	} else if (rtwdev->dbcc_en) {
@@ -7214,6 +7215,8 @@ void rtw89_btc_ntfy_scan_finish(struct rtw89_dev *rtwdev, u8 phy_idx)
 		_fw_set_drv_info(rtwdev, CXDRVINFO_DBCC);
 	}
 
+	btc->dm.tdma_instant_excute = 1;
+
 	_run_coex(rtwdev, BTC_RSN_NTFY_SCAN_FINISH);
 }
 
@@ -7662,7 +7665,8 @@ void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev,
 	else
 		wl->status.map.connecting = 0;
 
-	if (state == BTC_ROLE_MSTS_STA_DIS_CONN)
+	if (state == BTC_ROLE_MSTS_STA_DIS_CONN ||
+	    state == BTC_ROLE_MSTS_STA_CONN_END)
 		wl->status.map._4way = false;
 
 	_run_coex(rtwdev, BTC_RSN_NTFY_ROLE_INFO);

From dbb6a738f6cb55c542df286f028fb7d524f71077 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Fri, 10 Jan 2025 09:54:16 +0800
Subject: [PATCH 0008/2753] wifi: rtw89: coex: Update Wi-Fi/Bluetooth
 coexistence version to 7.0.2

With this version, fix Wi-Fi scan/connecting/RF calibration triggered A2DP
sound lag related issues.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250110015416.10704-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index cde65ee43bac4..7e43ba0c4098b 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -10,7 +10,7 @@
 #include "ps.h"
 #include "reg.h"
 
-#define RTW89_COEX_VERSION 0x07000113
+#define RTW89_COEX_VERSION 0x07000213
 #define FCXDEF_STEP 50 /* MUST <= FCXMAX_STEP and match with wl fw*/
 #define BTC_E2G_LIMIT_DEF 80
 

From 361cb056e2468be534f47c1a6745f96581a721e3 Mon Sep 17 00:00:00 2001
From: Liang Jie <liangjie@lixiang.com>
Date: Sun, 12 Jan 2025 18:51:44 +0800
Subject: [PATCH 0009/2753] wifi: rtw89: Correct immediate cfg_len calculation
 for scan_offload_be

Ensures the correct calculation of `cfg_len` prior to the allocation of
the skb in the `rtw89_fw_h2c_scan_offload_be` function, particularly when
the `SCAN_OFFLOAD_BE_V0` firmware feature is enabled. It addresses an
issue where an incorrect skb size might be allocated due to a delayed
setting of `cfg_len`, potentially leading to memory inefficiencies.

By moving the conditional check and assignment of `cfg_len` before skb
allocation, the patch guarantees that `len`, which depends on `cfg_len`,
is accurately computed, ensuring proper skb size and preventing any
unnecessary memory reservation for firmware operations not supporting
beyond the `w8` member of the command data structure.

This correction helps to optimize memory usage and maintain consistent
behavior across different firmware versions.

Fixes: 6ca6b918f280 ("wifi: rtw89: 8922a: Add new fields for scan offload H2C command")
Signed-off-by: Liang Jie <liangjie@lixiang.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250112105144.615474-1-buaajxlj@163.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 5d4ad23cc3bd4..5cc9ab78c09f7 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -5311,6 +5311,7 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 	u8 macc_role_size = sizeof(*macc_role) * option->num_macc_role;
 	u8 opch_size = sizeof(*opch) * option->num_opch;
 	u8 probe_id[NUM_NL80211_BANDS];
+	u8 scan_offload_ver = U8_MAX;
 	u8 cfg_len = sizeof(*h2c);
 	unsigned int cond;
 	u8 ver = U8_MAX;
@@ -5321,6 +5322,11 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 
 	rtw89_scan_get_6g_disabled_chan(rtwdev, option);
 
+	if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD_BE_V0, &rtwdev->fw)) {
+		cfg_len = offsetofend(typeof(*h2c), w8);
+		scan_offload_ver = 0;
+	}
+
 	len = cfg_len + macc_role_size + opch_size;
 	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
@@ -5392,10 +5398,8 @@ int rtw89_fw_h2c_scan_offload_be(struct rtw89_dev *rtwdev,
 					   RTW89_H2C_SCANOFLD_BE_W8_PROBE_RATE_6GHZ);
 	}
 
-	if (RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD_BE_V0, &rtwdev->fw)) {
-		cfg_len = offsetofend(typeof(*h2c), w8);
+	if (scan_offload_ver == 0)
 		goto flex_member;
-	}
 
 	h2c->w9 = le32_encode_bits(sizeof(*h2c) / sizeof(h2c->w0),
 				   RTW89_H2C_SCANOFLD_BE_W9_SIZE_CFG) |

From 1bcd20981834928ccc5d981aacb806bb523d8b29 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Sun, 19 Jan 2025 22:12:18 +0530
Subject: [PATCH 0010/2753] wifi: ath11k: Fix DMA buffer allocation to resolve
 SWIOTLB issues

Currently, the driver allocates cacheable DMA buffers for rings like
HAL_REO_DST and HAL_WBM2SW_RELEASE. The buffers for HAL_WBM2SW_RELEASE
are large (1024 KiB), exceeding the SWIOTLB slot size of 256 KiB. This
leads to "swiotlb buffer is full" error messages on systems without an
IOMMU that use SWIOTLB, causing driver initialization failures. The driver
calls dma_map_single() with these large buffers obtained from kzalloc(),
resulting in ring initialization errors on systems without an IOMMU that
use SWIOTLB.

To address these issues, replace the flawed buffer allocation mechanism
with the appropriate DMA API. Specifically, use dma_alloc_noncoherent()
for cacheable DMA buffers, ensuring proper freeing of buffers with
dma_free_noncoherent().

Error log:
[   10.194343] ath11k_pci 0000:04:00.0: swiotlb buffer is full (sz:1048583 bytes), total 32768 (slots), used 2529 (slots)
[   10.194406] ath11k_pci 0000:04:00.0: failed to set up tcl_comp ring (0) :-12
[   10.194781] ath11k_pci 0000:04:00.0: failed to init DP: -12

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Reported-by: Tim Harvey <tharvey@gateworks.com>
Closes: https://lore.kernel.org/all/20241210041133.GA17116@lst.de/
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Tested-by: Tim Harvey <tharvey@gateworks.com>
Link: https://patch.msgid.link/20250119164219.647059-2-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp.c | 35 +++++++++-------------------
 1 file changed, 11 insertions(+), 24 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp.c b/drivers/net/wireless/ath/ath11k/dp.c
index fbf666d0ecf1d..f124b7329e1ac 100644
--- a/drivers/net/wireless/ath/ath11k/dp.c
+++ b/drivers/net/wireless/ath/ath11k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
@@ -104,14 +104,12 @@ void ath11k_dp_srng_cleanup(struct ath11k_base *ab, struct dp_srng *ring)
 	if (!ring->vaddr_unaligned)
 		return;
 
-	if (ring->cached) {
-		dma_unmap_single(ab->dev, ring->paddr_unaligned, ring->size,
-				 DMA_FROM_DEVICE);
-		kfree(ring->vaddr_unaligned);
-	} else {
+	if (ring->cached)
+		dma_free_noncoherent(ab->dev, ring->size, ring->vaddr_unaligned,
+				     ring->paddr_unaligned, DMA_FROM_DEVICE);
+	else
 		dma_free_coherent(ab->dev, ring->size, ring->vaddr_unaligned,
 				  ring->paddr_unaligned);
-	}
 
 	ring->vaddr_unaligned = NULL;
 }
@@ -249,25 +247,14 @@ int ath11k_dp_srng_setup(struct ath11k_base *ab, struct dp_srng *ring,
 		default:
 			cached = false;
 		}
-
-		if (cached) {
-			ring->vaddr_unaligned = kzalloc(ring->size, GFP_KERNEL);
-			if (!ring->vaddr_unaligned)
-				return -ENOMEM;
-
-			ring->paddr_unaligned = dma_map_single(ab->dev,
-							       ring->vaddr_unaligned,
-							       ring->size,
-							       DMA_FROM_DEVICE);
-			if (dma_mapping_error(ab->dev, ring->paddr_unaligned)) {
-				kfree(ring->vaddr_unaligned);
-				ring->vaddr_unaligned = NULL;
-				return -ENOMEM;
-			}
-		}
 	}
 
-	if (!cached)
+	if (cached)
+		ring->vaddr_unaligned = dma_alloc_noncoherent(ab->dev, ring->size,
+							      &ring->paddr_unaligned,
+							      DMA_FROM_DEVICE,
+							      GFP_KERNEL);
+	else
 		ring->vaddr_unaligned = dma_alloc_coherent(ab->dev, ring->size,
 							   &ring->paddr_unaligned,
 							   GFP_KERNEL);

From eeadc6baf8b3dcd32787cc84f0473dc2a2850370 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Sun, 19 Jan 2025 22:12:19 +0530
Subject: [PATCH 0011/2753] wifi: ath11k: Use dma_alloc_noncoherent for rx_tid
 buffer allocation

Currently, the driver allocates cacheable DMA buffers for the rx_tid
structure using kzalloc() and dma_map_single(). These buffers are
long-lived and can persist for the lifetime of the peer, which is not
advisable. Instead of using kzalloc() and dma_map_single() for allocating
cacheable DMA buffers, utilize the dma_alloc_noncoherent() helper for the
allocation of long-lived cacheable DMA buffers, such as the peer's rx_tid.
Since dma_alloc_noncoherent() returns unaligned physical and virtual
addresses, align them internally before use within the driver. This
ensures proper allocation of non-coherent memory through the kernel
helper.

Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Tested-by: Tim Harvey <tharvey@gateworks.com>
Link: https://patch.msgid.link/20250119164219.647059-3-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp.h    |   6 +-
 drivers/net/wireless/ath/ath11k/dp_rx.c | 117 +++++++++++-------------
 2 files changed, 58 insertions(+), 65 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp.h b/drivers/net/wireless/ath/ath11k/dp.h
index f777314db8b36..7a55afd33be82 100644
--- a/drivers/net/wireless/ath/ath11k/dp.h
+++ b/drivers/net/wireless/ath/ath11k/dp.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2023, 2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_DP_H
@@ -20,7 +20,6 @@ struct ath11k_ext_irq_grp;
 
 struct dp_rx_tid {
 	u8 tid;
-	u32 *vaddr;
 	dma_addr_t paddr;
 	u32 size;
 	u32 ba_win_sz;
@@ -37,6 +36,9 @@ struct dp_rx_tid {
 	/* Timer info related to fragments */
 	struct timer_list frag_timer;
 	struct ath11k_base *ab;
+	u32 *vaddr_unaligned;
+	dma_addr_t paddr_unaligned;
+	u32 unaligned_size;
 };
 
 #define DP_REO_DESC_FREE_THRESHOLD  64
diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 029ecf51c9efd..5e71e5d9ecb78 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
@@ -675,11 +675,11 @@ void ath11k_dp_reo_cmd_list_cleanup(struct ath11k_base *ab)
 	list_for_each_entry_safe(cmd, tmp, &dp->reo_cmd_list, list) {
 		list_del(&cmd->list);
 		rx_tid = &cmd->data;
-		if (rx_tid->vaddr) {
-			dma_unmap_single(ab->dev, rx_tid->paddr,
-					 rx_tid->size, DMA_BIDIRECTIONAL);
-			kfree(rx_tid->vaddr);
-			rx_tid->vaddr = NULL;
+		if (rx_tid->vaddr_unaligned) {
+			dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+					     rx_tid->vaddr_unaligned,
+					     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+			rx_tid->vaddr_unaligned = NULL;
 		}
 		kfree(cmd);
 	}
@@ -689,11 +689,11 @@ void ath11k_dp_reo_cmd_list_cleanup(struct ath11k_base *ab)
 		list_del(&cmd_cache->list);
 		dp->reo_cmd_cache_flush_count--;
 		rx_tid = &cmd_cache->data;
-		if (rx_tid->vaddr) {
-			dma_unmap_single(ab->dev, rx_tid->paddr,
-					 rx_tid->size, DMA_BIDIRECTIONAL);
-			kfree(rx_tid->vaddr);
-			rx_tid->vaddr = NULL;
+		if (rx_tid->vaddr_unaligned) {
+			dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+					     rx_tid->vaddr_unaligned,
+					     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+			rx_tid->vaddr_unaligned = NULL;
 		}
 		kfree(cmd_cache);
 	}
@@ -708,11 +708,11 @@ static void ath11k_dp_reo_cmd_free(struct ath11k_dp *dp, void *ctx,
 	if (status != HAL_REO_CMD_SUCCESS)
 		ath11k_warn(dp->ab, "failed to flush rx tid hw desc, tid %d status %d\n",
 			    rx_tid->tid, status);
-	if (rx_tid->vaddr) {
-		dma_unmap_single(dp->ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+	if (rx_tid->vaddr_unaligned) {
+		dma_free_noncoherent(dp->ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 }
 
@@ -749,10 +749,10 @@ static void ath11k_dp_reo_cache_flush(struct ath11k_base *ab,
 	if (ret) {
 		ath11k_err(ab, "failed to send HAL_REO_CMD_FLUSH_CACHE cmd, tid %d (%d)\n",
 			   rx_tid->tid, ret);
-		dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 }
 
@@ -802,10 +802,10 @@ static void ath11k_dp_rx_tid_del_func(struct ath11k_dp *dp, void *ctx,
 
 	return;
 free_desc:
-	dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	dma_free_noncoherent(ab->dev, rx_tid->unaligned_size,
+			     rx_tid->vaddr_unaligned,
+			     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+	rx_tid->vaddr_unaligned = NULL;
 }
 
 void ath11k_peer_rx_tid_delete(struct ath11k *ar,
@@ -831,14 +831,16 @@ void ath11k_peer_rx_tid_delete(struct ath11k *ar,
 		if (ret != -ESHUTDOWN)
 			ath11k_err(ar->ab, "failed to send HAL_REO_CMD_UPDATE_RX_QUEUE cmd, tid %d (%d)\n",
 				   tid, ret);
-		dma_unmap_single(ar->ab->dev, rx_tid->paddr, rx_tid->size,
-				 DMA_BIDIRECTIONAL);
-		kfree(rx_tid->vaddr);
-		rx_tid->vaddr = NULL;
+		dma_free_noncoherent(ar->ab->dev, rx_tid->unaligned_size,
+				     rx_tid->vaddr_unaligned,
+				     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+		rx_tid->vaddr_unaligned = NULL;
 	}
 
 	rx_tid->paddr = 0;
+	rx_tid->paddr_unaligned = 0;
 	rx_tid->size = 0;
+	rx_tid->unaligned_size = 0;
 }
 
 static int ath11k_dp_rx_link_desc_return(struct ath11k_base *ab,
@@ -982,10 +984,9 @@ static void ath11k_dp_rx_tid_mem_free(struct ath11k_base *ab,
 	if (!rx_tid->active)
 		goto unlock_exit;
 
-	dma_unmap_single(ab->dev, rx_tid->paddr, rx_tid->size,
-			 DMA_BIDIRECTIONAL);
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
+	dma_free_noncoherent(ab->dev, rx_tid->unaligned_size, rx_tid->vaddr_unaligned,
+			     rx_tid->paddr_unaligned, DMA_BIDIRECTIONAL);
+	rx_tid->vaddr_unaligned = NULL;
 
 	rx_tid->active = false;
 
@@ -1000,9 +1001,8 @@ int ath11k_peer_rx_tid_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id,
 	struct ath11k_base *ab = ar->ab;
 	struct ath11k_peer *peer;
 	struct dp_rx_tid *rx_tid;
-	u32 hw_desc_sz;
-	u32 *addr_aligned;
-	void *vaddr;
+	u32 hw_desc_sz, *vaddr;
+	void *vaddr_unaligned;
 	dma_addr_t paddr;
 	int ret;
 
@@ -1050,49 +1050,40 @@ int ath11k_peer_rx_tid_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id,
 	else
 		hw_desc_sz = ath11k_hal_reo_qdesc_size(DP_BA_WIN_SZ_MAX, tid);
 
-	vaddr = kzalloc(hw_desc_sz + HAL_LINK_DESC_ALIGN - 1, GFP_ATOMIC);
-	if (!vaddr) {
+	rx_tid->unaligned_size = hw_desc_sz + HAL_LINK_DESC_ALIGN - 1;
+	vaddr_unaligned = dma_alloc_noncoherent(ab->dev, rx_tid->unaligned_size, &paddr,
+						DMA_BIDIRECTIONAL, GFP_ATOMIC);
+	if (!vaddr_unaligned) {
 		spin_unlock_bh(&ab->base_lock);
 		return -ENOMEM;
 	}
 
-	addr_aligned = PTR_ALIGN(vaddr, HAL_LINK_DESC_ALIGN);
-
-	ath11k_hal_reo_qdesc_setup(addr_aligned, tid, ba_win_sz,
-				   ssn, pn_type);
-
-	paddr = dma_map_single(ab->dev, addr_aligned, hw_desc_sz,
-			       DMA_BIDIRECTIONAL);
-
-	ret = dma_mapping_error(ab->dev, paddr);
-	if (ret) {
-		spin_unlock_bh(&ab->base_lock);
-		ath11k_warn(ab, "failed to setup dma map for peer %pM rx tid %d: %d\n",
-			    peer_mac, tid, ret);
-		goto err_mem_free;
-	}
-
-	rx_tid->vaddr = vaddr;
-	rx_tid->paddr = paddr;
+	rx_tid->vaddr_unaligned = vaddr_unaligned;
+	vaddr = PTR_ALIGN(vaddr_unaligned, HAL_LINK_DESC_ALIGN);
+	rx_tid->paddr_unaligned = paddr;
+	rx_tid->paddr = rx_tid->paddr_unaligned + ((unsigned long)vaddr -
+			(unsigned long)rx_tid->vaddr_unaligned);
+	ath11k_hal_reo_qdesc_setup(vaddr, tid, ba_win_sz, ssn, pn_type);
 	rx_tid->size = hw_desc_sz;
 	rx_tid->active = true;
 
+	/* After dma_alloc_noncoherent, vaddr is being modified for reo qdesc setup.
+	 * Since these changes are not reflected in the device, driver now needs to
+	 * explicitly call dma_sync_single_for_device.
+	 */
+	dma_sync_single_for_device(ab->dev, rx_tid->paddr,
+				   rx_tid->size,
+				   DMA_TO_DEVICE);
 	spin_unlock_bh(&ab->base_lock);
 
-	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac,
-						     paddr, tid, 1, ba_win_sz);
+	ret = ath11k_wmi_peer_rx_reorder_queue_setup(ar, vdev_id, peer_mac, rx_tid->paddr,
+						     tid, 1, ba_win_sz);
 	if (ret) {
 		ath11k_warn(ar->ab, "failed to setup rx reorder queue for peer %pM tid %d: %d\n",
 			    peer_mac, tid, ret);
 		ath11k_dp_rx_tid_mem_free(ab, peer_mac, vdev_id, tid);
 	}
 
-	return ret;
-
-err_mem_free:
-	kfree(rx_tid->vaddr);
-	rx_tid->vaddr = NULL;
-
 	return ret;
 }
 

From 6fabed4052176a18da9519fc14a18897ed4f820d Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Sun, 19 Jan 2025 14:06:54 +0530
Subject: [PATCH 0012/2753] wifi: ath: create common testmode_i.h file for ath
 drivers

User space application requires that the testmode interface
is exactly same between ath drivers. Move testmode_i.h file
in ath directory to ensure that all ath driver uses same testmode
interface instead of duplicating testmode_i.h for each ath drivers.

Tested-on: IPQ8074 hw2.0 AHB WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250119083657.1937557-2-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/testmode.c    | 80 +++++++++----------
 .../wireless/ath/{ath11k => }/testmode_i.h    | 54 ++++++-------
 2 files changed, 67 insertions(+), 67 deletions(-)
 rename drivers/net/wireless/ath/{ath11k => }/testmode_i.h (50%)

diff --git a/drivers/net/wireless/ath/ath11k/testmode.c b/drivers/net/wireless/ath/ath11k/testmode.c
index 302d66092b973..9be1cd742339c 100644
--- a/drivers/net/wireless/ath/ath11k/testmode.c
+++ b/drivers/net/wireless/ath/ath11k/testmode.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "testmode.h"
@@ -10,18 +10,18 @@
 #include "wmi.h"
 #include "hw.h"
 #include "core.h"
-#include "testmode_i.h"
+#include "../testmode_i.h"
 
 #define ATH11K_FTM_SEGHDR_CURRENT_SEQ		GENMASK(3, 0)
 #define ATH11K_FTM_SEGHDR_TOTAL_SEGMENTS	GENMASK(7, 4)
 
-static const struct nla_policy ath11k_tm_policy[ATH11K_TM_ATTR_MAX + 1] = {
-	[ATH11K_TM_ATTR_CMD]		= { .type = NLA_U32 },
-	[ATH11K_TM_ATTR_DATA]		= { .type = NLA_BINARY,
-					    .len = ATH11K_TM_DATA_MAX_LEN },
-	[ATH11K_TM_ATTR_WMI_CMDID]	= { .type = NLA_U32 },
-	[ATH11K_TM_ATTR_VERSION_MAJOR]	= { .type = NLA_U32 },
-	[ATH11K_TM_ATTR_VERSION_MINOR]	= { .type = NLA_U32 },
+static const struct nla_policy ath11k_tm_policy[ATH_TM_ATTR_MAX + 1] = {
+	[ATH_TM_ATTR_CMD]		= { .type = NLA_U32 },
+	[ATH_TM_ATTR_DATA]		= { .type = NLA_BINARY,
+					    .len = ATH_TM_DATA_MAX_LEN },
+	[ATH_TM_ATTR_WMI_CMDID]		= { .type = NLA_U32 },
+	[ATH_TM_ATTR_VERSION_MAJOR]	= { .type = NLA_U32 },
+	[ATH_TM_ATTR_VERSION_MINOR]	= { .type = NLA_U32 },
 };
 
 static struct ath11k *ath11k_tm_get_ar(struct ath11k_base *ab)
@@ -73,9 +73,9 @@ static void ath11k_tm_wmi_event_unsegmented(struct ath11k_base *ab, u32 cmd_id,
 		goto out;
 	}
 
-	if (nla_put_u32(nl_skb, ATH11K_TM_ATTR_CMD, ATH11K_TM_CMD_WMI) ||
-	    nla_put_u32(nl_skb, ATH11K_TM_ATTR_WMI_CMDID, cmd_id) ||
-	    nla_put(nl_skb, ATH11K_TM_ATTR_DATA, skb->len, skb->data)) {
+	if (nla_put_u32(nl_skb, ATH_TM_ATTR_CMD, ATH_TM_CMD_WMI) ||
+	    nla_put_u32(nl_skb, ATH_TM_ATTR_WMI_CMDID, cmd_id) ||
+	    nla_put(nl_skb, ATH_TM_ATTR_DATA, skb->len, skb->data)) {
 		ath11k_warn(ab, "failed to populate testmode unsegmented event\n");
 		kfree_skb(nl_skb);
 		goto out;
@@ -140,7 +140,7 @@ static int ath11k_tm_process_event(struct ath11k_base *ab, u32 cmd_id,
 
 	data_pos = ab->testmode.data_pos;
 
-	if ((data_pos + datalen) > ATH11K_FTM_EVENT_MAX_BUF_LENGTH) {
+	if ((data_pos + datalen) > ATH_FTM_EVENT_MAX_BUF_LENGTH) {
 		ath11k_warn(ab, "Invalid ftm event length at %d: %d\n",
 			    data_pos, datalen);
 		ret = -EINVAL;
@@ -172,10 +172,10 @@ static int ath11k_tm_process_event(struct ath11k_base *ab, u32 cmd_id,
 		goto out;
 	}
 
-	if (nla_put_u32(nl_skb, ATH11K_TM_ATTR_CMD,
-			ATH11K_TM_CMD_WMI_FTM) ||
-	    nla_put_u32(nl_skb, ATH11K_TM_ATTR_WMI_CMDID, cmd_id) ||
-	    nla_put(nl_skb, ATH11K_TM_ATTR_DATA, data_pos,
+	if (nla_put_u32(nl_skb, ATH_TM_ATTR_CMD,
+			ATH_TM_CMD_WMI_FTM) ||
+	    nla_put_u32(nl_skb, ATH_TM_ATTR_WMI_CMDID, cmd_id) ||
+	    nla_put(nl_skb, ATH_TM_ATTR_DATA, data_pos,
 		    &ab->testmode.eventdata[0])) {
 		ath11k_warn(ab, "failed to populate segmented testmode event");
 		kfree_skb(nl_skb);
@@ -235,23 +235,23 @@ static int ath11k_tm_cmd_get_version(struct ath11k *ar, struct nlattr *tb[])
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_TESTMODE,
 		   "cmd get version_major %d version_minor %d\n",
-		   ATH11K_TESTMODE_VERSION_MAJOR,
-		   ATH11K_TESTMODE_VERSION_MINOR);
+		   ATH_TESTMODE_VERSION_MAJOR,
+		   ATH_TESTMODE_VERSION_MINOR);
 
 	skb = cfg80211_testmode_alloc_reply_skb(ar->hw->wiphy,
 						nla_total_size(sizeof(u32)));
 	if (!skb)
 		return -ENOMEM;
 
-	ret = nla_put_u32(skb, ATH11K_TM_ATTR_VERSION_MAJOR,
-			  ATH11K_TESTMODE_VERSION_MAJOR);
+	ret = nla_put_u32(skb, ATH_TM_ATTR_VERSION_MAJOR,
+			  ATH_TESTMODE_VERSION_MAJOR);
 	if (ret) {
 		kfree_skb(skb);
 		return ret;
 	}
 
-	ret = nla_put_u32(skb, ATH11K_TM_ATTR_VERSION_MINOR,
-			  ATH11K_TESTMODE_VERSION_MINOR);
+	ret = nla_put_u32(skb, ATH_TM_ATTR_VERSION_MINOR,
+			  ATH_TESTMODE_VERSION_MINOR);
 	if (ret) {
 		kfree_skb(skb);
 		return ret;
@@ -277,7 +277,7 @@ static int ath11k_tm_cmd_testmode_start(struct ath11k *ar, struct nlattr *tb[])
 		goto err;
 	}
 
-	ar->ab->testmode.eventdata = kzalloc(ATH11K_FTM_EVENT_MAX_BUF_LENGTH,
+	ar->ab->testmode.eventdata = kzalloc(ATH_FTM_EVENT_MAX_BUF_LENGTH,
 					     GFP_KERNEL);
 	if (!ar->ab->testmode.eventdata) {
 		ret = -ENOMEM;
@@ -310,25 +310,25 @@ static int ath11k_tm_cmd_wmi(struct ath11k *ar, struct nlattr *tb[],
 
 	mutex_lock(&ar->conf_mutex);
 
-	if (!tb[ATH11K_TM_ATTR_DATA]) {
+	if (!tb[ATH_TM_ATTR_DATA]) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	if (!tb[ATH11K_TM_ATTR_WMI_CMDID]) {
+	if (!tb[ATH_TM_ATTR_WMI_CMDID]) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	buf = nla_data(tb[ATH11K_TM_ATTR_DATA]);
-	buf_len = nla_len(tb[ATH11K_TM_ATTR_DATA]);
+	buf = nla_data(tb[ATH_TM_ATTR_DATA]);
+	buf_len = nla_len(tb[ATH_TM_ATTR_DATA]);
 	if (!buf_len) {
 		ath11k_warn(ar->ab, "No data present in testmode wmi command\n");
 		ret = -EINVAL;
 		goto out;
 	}
 
-	cmd_id = nla_get_u32(tb[ATH11K_TM_ATTR_WMI_CMDID]);
+	cmd_id = nla_get_u32(tb[ATH_TM_ATTR_WMI_CMDID]);
 
 	/* Make sure that the buffer length is long enough to
 	 * hold TLV and pdev/vdev id.
@@ -409,13 +409,13 @@ static int ath11k_tm_cmd_wmi_ftm(struct ath11k *ar, struct nlattr *tb[])
 		goto out;
 	}
 
-	if (!tb[ATH11K_TM_ATTR_DATA]) {
+	if (!tb[ATH_TM_ATTR_DATA]) {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	buf = nla_data(tb[ATH11K_TM_ATTR_DATA]);
-	buf_len = nla_len(tb[ATH11K_TM_ATTR_DATA]);
+	buf = nla_data(tb[ATH_TM_ATTR_DATA]);
+	buf_len = nla_len(tb[ATH_TM_ATTR_DATA]);
 	cmd_id = WMI_PDEV_UTF_CMDID;
 
 	ath11k_dbg(ar->ab, ATH11K_DBG_TESTMODE,
@@ -476,25 +476,25 @@ int ath11k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		  void *data, int len)
 {
 	struct ath11k *ar = hw->priv;
-	struct nlattr *tb[ATH11K_TM_ATTR_MAX + 1];
+	struct nlattr *tb[ATH_TM_ATTR_MAX + 1];
 	int ret;
 
-	ret = nla_parse(tb, ATH11K_TM_ATTR_MAX, data, len, ath11k_tm_policy,
+	ret = nla_parse(tb, ATH_TM_ATTR_MAX, data, len, ath11k_tm_policy,
 			NULL);
 	if (ret)
 		return ret;
 
-	if (!tb[ATH11K_TM_ATTR_CMD])
+	if (!tb[ATH_TM_ATTR_CMD])
 		return -EINVAL;
 
-	switch (nla_get_u32(tb[ATH11K_TM_ATTR_CMD])) {
-	case ATH11K_TM_CMD_GET_VERSION:
+	switch (nla_get_u32(tb[ATH_TM_ATTR_CMD])) {
+	case ATH_TM_CMD_GET_VERSION:
 		return ath11k_tm_cmd_get_version(ar, tb);
-	case ATH11K_TM_CMD_WMI:
+	case ATH_TM_CMD_WMI:
 		return ath11k_tm_cmd_wmi(ar, tb, vif);
-	case ATH11K_TM_CMD_TESTMODE_START:
+	case ATH_TM_CMD_TESTMODE_START:
 		return ath11k_tm_cmd_testmode_start(ar, tb);
-	case ATH11K_TM_CMD_WMI_FTM:
+	case ATH_TM_CMD_WMI_FTM:
 		return ath11k_tm_cmd_wmi_ftm(ar, tb);
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/wireless/ath/ath11k/testmode_i.h b/drivers/net/wireless/ath/testmode_i.h
similarity index 50%
rename from drivers/net/wireless/ath/ath11k/testmode_i.h
rename to drivers/net/wireless/ath/testmode_i.h
index 91b83873d6608..980ef2f3f05f8 100644
--- a/drivers/net/wireless/ath/ath11k/testmode_i.h
+++ b/drivers/net/wireless/ath/testmode_i.h
@@ -1,59 +1,59 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
-/* "API" level of the ath11k testmode interface. Bump it after every
+/* "API" level of the ath testmode interface. Bump it after every
  * incompatible interface change.
  */
-#define ATH11K_TESTMODE_VERSION_MAJOR 1
+#define ATH_TESTMODE_VERSION_MAJOR 1
 
 /* Bump this after every _compatible_ interface change, for example
  * addition of a new command or an attribute.
  */
-#define ATH11K_TESTMODE_VERSION_MINOR 1
+#define ATH_TESTMODE_VERSION_MINOR 1
 
-#define ATH11K_TM_DATA_MAX_LEN		5000
-#define ATH11K_FTM_EVENT_MAX_BUF_LENGTH 2048
+#define ATH_TM_DATA_MAX_LEN		5000
+#define ATH_FTM_EVENT_MAX_BUF_LENGTH	2048
 
-enum ath11k_tm_attr {
-	__ATH11K_TM_ATTR_INVALID		= 0,
-	ATH11K_TM_ATTR_CMD			= 1,
-	ATH11K_TM_ATTR_DATA			= 2,
-	ATH11K_TM_ATTR_WMI_CMDID		= 3,
-	ATH11K_TM_ATTR_VERSION_MAJOR		= 4,
-	ATH11K_TM_ATTR_VERSION_MINOR		= 5,
-	ATH11K_TM_ATTR_WMI_OP_VERSION		= 6,
+enum ath_tm_attr {
+	__ATH_TM_ATTR_INVALID		= 0,
+	ATH_TM_ATTR_CMD			= 1,
+	ATH_TM_ATTR_DATA		= 2,
+	ATH_TM_ATTR_WMI_CMDID		= 3,
+	ATH_TM_ATTR_VERSION_MAJOR	= 4,
+	ATH_TM_ATTR_VERSION_MINOR	= 5,
+	ATH_TM_ATTR_WMI_OP_VERSION	= 6,
 
 	/* keep last */
-	__ATH11K_TM_ATTR_AFTER_LAST,
-	ATH11K_TM_ATTR_MAX		= __ATH11K_TM_ATTR_AFTER_LAST - 1,
+	__ATH_TM_ATTR_AFTER_LAST,
+	ATH_TM_ATTR_MAX			= __ATH_TM_ATTR_AFTER_LAST - 1,
 };
 
-/* All ath11k testmode interface commands specified in
- * ATH11K_TM_ATTR_CMD
+/* All ath testmode interface commands specified in
+ * ATH_TM_ATTR_CMD
  */
-enum ath11k_tm_cmd {
-	/* Returns the supported ath11k testmode interface version in
-	 * ATH11K_TM_ATTR_VERSION. Always guaranteed to work. User space
+enum ath_tm_cmd {
+	/* Returns the supported ath testmode interface version in
+	 * ATH_TM_ATTR_VERSION. Always guaranteed to work. User space
 	 * uses this to verify it's using the correct version of the
 	 * testmode interface
 	 */
-	ATH11K_TM_CMD_GET_VERSION = 0,
+	ATH_TM_CMD_GET_VERSION = 0,
 
 	/* The command used to transmit a WMI command to the firmware and
 	 * the event to receive WMI events from the firmware. Without
 	 * struct wmi_cmd_hdr header, only the WMI payload. Command id is
-	 * provided with ATH11K_TM_ATTR_WMI_CMDID and payload in
-	 * ATH11K_TM_ATTR_DATA.
+	 * provided with ATH_TM_ATTR_WMI_CMDID and payload in
+	 * ATH_TM_ATTR_DATA.
 	 */
-	ATH11K_TM_CMD_WMI = 1,
+	ATH_TM_CMD_WMI = 1,
 
 	/* Boots the UTF firmware, the netdev interface must be down at the
 	 * time.
 	 */
-	ATH11K_TM_CMD_TESTMODE_START = 2,
+	ATH_TM_CMD_TESTMODE_START = 2,
 
 	/* The command used to transmit a FTM WMI command to the firmware
 	 * and the event to receive WMI events from the firmware. The data
@@ -62,5 +62,5 @@ enum ath11k_tm_cmd {
 	 * The data payload size could be large and the driver needs to
 	 * send segmented data to firmware.
 	 */
-	ATH11K_TM_CMD_WMI_FTM = 3,
+	ATH_TM_CMD_WMI_FTM = 3,
 };

From 786d5258faba099779fe0d14d344893f9215d6be Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Sun, 19 Jan 2025 14:06:55 +0530
Subject: [PATCH 0013/2753] wifi: ath12k: export ath12k_wmi_tlv_hdr for
 testmode

Export ath12k_wmi_tlv_hdr() to further use in the testmode command
processing.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250119083657.1937557-3-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 4 ++--
 drivers/net/wireless/ath/ath12k/wmi.h | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 4dd6cdf84571d..246b8aab49a9a 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/skbuff.h>
 #include <linux/ctype.h>
@@ -173,7 +173,7 @@ static const struct ath12k_wmi_tlv_policy ath12k_wmi_tlv_policies[] = {
 		.min_len = sizeof(struct wmi_p2p_noa_event) },
 };
 
-static __le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len)
+__le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len)
 {
 	return le32_encode_bits(cmd, WMI_TLV_TAG) |
 		le32_encode_bits(len, WMI_TLV_LEN);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index b6a197389277b..00d024d4eb2cb 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_WMI_H
@@ -5754,6 +5754,7 @@ int ath12k_wmi_set_bios_cmd(struct ath12k_base *ab, u32 param_id,
 			    const u8 *buf, size_t buf_len);
 int ath12k_wmi_set_bios_sar_cmd(struct ath12k_base *ab, const u8 *psar_table);
 int ath12k_wmi_set_bios_geo_cmd(struct ath12k_base *ab, const u8 *pgeo_table);
+__le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len);
 
 static inline u32
 ath12k_wmi_caps_ext_get_pdev_id(const struct ath12k_wmi_caps_ext_params *param)

From 3bc374cbc49ec39891381d2e25d81a6f74fa3364 Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Sun, 19 Jan 2025 14:06:56 +0530
Subject: [PATCH 0014/2753] wifi: ath12k: add factory test mode support

Add support to process factory test mode commands(FTM) for calibration.
By default firmware start with MISSION mode and to process the FTM commands
firmware needs to be restarted in FTM mode using module parameter ftm_mode.
The pre-request is all the radios should be down before starting the test.

All ath12k test mode interface related commands specified in enum
ath_tm_cmd.

When start command ATH_TM_CMD_TESTMODE_START is received, ar state
is set to test Mode and FTM daemon sends test mode command to wifi
driver via cfg80211. Wifi driver sends these command to firmware as
wmi events. If it is segmented commands it will be broken down into
multiple segments and encoded with TLV header else it is sent to
firmware as it is.

Firmware response via UTF events, wifi driver creates skb and send
to cfg80211, cfg80211 sends firmware response to FTM daemon via
netlink message.

Command to boot in ftm mode
insmod ath12k ftm_mode=1

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250119083657.1937557-4-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/Makefile   |   1 +
 drivers/net/wireless/ath/ath12k/core.c     |  22 +-
 drivers/net/wireless/ath/ath12k/core.h     |  11 +
 drivers/net/wireless/ath/ath12k/debug.h    |   3 +-
 drivers/net/wireless/ath/ath12k/dp.c       |   5 +-
 drivers/net/wireless/ath/ath12k/mac.c      |  15 +-
 drivers/net/wireless/ath/ath12k/pci.c      |   3 +-
 drivers/net/wireless/ath/ath12k/testmode.c | 395 +++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/testmode.h |  40 +++
 drivers/net/wireless/ath/ath12k/wmi.c      |  37 +-
 drivers/net/wireless/ath/ath12k/wmi.h      |  20 ++
 drivers/net/wireless/ath/ath12k/wow.c      |   3 +-
 12 files changed, 543 insertions(+), 12 deletions(-)
 create mode 100644 drivers/net/wireless/ath/ath12k/testmode.c
 create mode 100644 drivers/net/wireless/ath/ath12k/testmode.h

diff --git a/drivers/net/wireless/ath/ath12k/Makefile b/drivers/net/wireless/ath/ath12k/Makefile
index b5bb3e2599cd0..4a7f5e87384c2 100644
--- a/drivers/net/wireless/ath/ath12k/Makefile
+++ b/drivers/net/wireless/ath/ath12k/Makefile
@@ -28,6 +28,7 @@ ath12k-$(CONFIG_ACPI) += acpi.o
 ath12k-$(CONFIG_ATH12K_TRACING) += trace.o
 ath12k-$(CONFIG_PM) += wow.o
 ath12k-$(CONFIG_ATH12K_COREDUMP) += coredump.o
+ath12k-$(CONFIG_NL80211_TESTMODE) += testmode.o
 
 # for tracing framework to find trace.h
 CFLAGS_trace.o := -I$(src)
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 0606116d6b9c4..20c8a7bed3db6 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -23,6 +23,10 @@ unsigned int ath12k_debug_mask;
 module_param_named(debug_mask, ath12k_debug_mask, uint, 0644);
 MODULE_PARM_DESC(debug_mask, "Debugging mask");
 
+bool ath12k_ftm_mode;
+module_param_named(ftm_mode, ath12k_ftm_mode, bool, 0444);
+MODULE_PARM_DESC(ftm_mode, "Boots up in factory test mode");
+
 /* protected with ath12k_hw_group_mutex */
 static struct list_head ath12k_hw_group_list = LIST_HEAD_INIT(ath12k_hw_group_list);
 
@@ -693,6 +697,11 @@ static int ath12k_core_soc_create(struct ath12k_base *ab)
 {
 	int ret;
 
+	if (ath12k_ftm_mode) {
+		ab->fw_mode = ATH12K_FIRMWARE_MODE_FTM;
+		ath12k_info(ab, "Booting in ftm mode\n");
+	}
+
 	ret = ath12k_qmi_init_service(ab);
 	if (ret) {
 		ath12k_err(ab, "failed to initialize qmi :%d\n", ret);
@@ -741,8 +750,7 @@ static void ath12k_core_pdev_destroy(struct ath12k_base *ab)
 	ath12k_dp_pdev_free(ab);
 }
 
-static int ath12k_core_start(struct ath12k_base *ab,
-			     enum ath12k_firmware_mode mode)
+static int ath12k_core_start(struct ath12k_base *ab)
 {
 	int ret;
 
@@ -1068,7 +1076,7 @@ int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab)
 	struct ath12k_hw_group *ag = ath12k_ab_to_ag(ab);
 	int ret, i;
 
-	ret = ath12k_core_start_firmware(ab, ATH12K_FIRMWARE_MODE_NORMAL);
+	ret = ath12k_core_start_firmware(ab, ab->fw_mode);
 	if (ret) {
 		ath12k_err(ab, "failed to start firmware: %d\n", ret);
 		return ret;
@@ -1089,7 +1097,7 @@ int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab)
 	mutex_lock(&ag->mutex);
 	mutex_lock(&ab->core_lock);
 
-	ret = ath12k_core_start(ab, ATH12K_FIRMWARE_MODE_NORMAL);
+	ret = ath12k_core_start(ab);
 	if (ret) {
 		ath12k_err(ab, "failed to start core: %d\n", ret);
 		goto err_dp_free;
@@ -1239,7 +1247,8 @@ static void ath12k_core_pre_reconfigure_recovery(struct ath12k_base *ab)
 
 	for (i = 0; i < ag->num_hw; i++) {
 		ah = ath12k_ag_to_ah(ag, i);
-		if (!ah || ah->state == ATH12K_HW_STATE_OFF)
+		if (!ah || ah->state == ATH12K_HW_STATE_OFF ||
+		    ah->state == ATH12K_HW_STATE_TM)
 			continue;
 
 		ieee80211_stop_queues(ah->hw);
@@ -1309,6 +1318,9 @@ static void ath12k_core_post_reconfigure_recovery(struct ath12k_base *ab)
 			ath12k_warn(ab,
 				    "device is wedged, will not restart hw %d\n", i);
 			break;
+		case ATH12K_HW_STATE_TM:
+			ath12k_warn(ab, "fw mode reset done radio %d\n", i);
+			break;
 		}
 
 		mutex_unlock(&ah->hw_mutex);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index ee595794a7aee..86a1eeec64a6e 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -235,6 +235,7 @@ enum ath12k_dev_flags {
 	ATH12K_FLAG_CE_IRQ_ENABLED,
 	ATH12K_FLAG_EXT_IRQ_ENABLED,
 	ATH12K_FLAG_QMI_FW_READY_COMPLETE,
+	ATH12K_FLAG_FTM_SEGMENTED,
 };
 
 struct ath12k_tx_conf {
@@ -534,12 +535,19 @@ enum ath12k_hw_state {
 	ATH12K_HW_STATE_RESTARTING,
 	ATH12K_HW_STATE_RESTARTED,
 	ATH12K_HW_STATE_WEDGED,
+	ATH12K_HW_STATE_TM,
 	/* Add other states as required */
 };
 
 /* Antenna noise floor */
 #define ATH12K_DEFAULT_NOISE_FLOOR -95
 
+struct ath12k_ftm_event_obj {
+	u32 data_pos;
+	u32 expected_seq;
+	u8 *eventdata;
+};
+
 struct ath12k_fw_stats {
 	u32 pdev_id;
 	u32 stats_id;
@@ -714,6 +722,7 @@ struct ath12k {
 
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;
+	u8 ftm_msgref;
 };
 
 struct ath12k_hw {
@@ -1052,6 +1061,8 @@ struct ath12k_base {
 
 	struct ath12k_hw_group *ag;
 	struct ath12k_wsi_info wsi_info;
+	enum ath12k_firmware_mode fw_mode;
+	struct ath12k_ftm_event_obj ftm_event_obj;
 
 	/* must be last */
 	u8 drv_priv[] __aligned(sizeof(void *));
diff --git a/drivers/net/wireless/ath/ath12k/debug.h b/drivers/net/wireless/ath/ath12k/debug.h
index 90e801136bc65..0aa7c8ccb14cc 100644
--- a/drivers/net/wireless/ath/ath12k/debug.h
+++ b/drivers/net/wireless/ath/ath12k/debug.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH12K_DEBUG_H_
@@ -37,6 +37,7 @@ __printf(2, 3) void __ath12k_warn(struct device *dev, const char *fmt, ...);
 #define ath12k_hw_warn(ah, fmt, ...) __ath12k_warn((ah)->dev, fmt, ##__VA_ARGS__)
 
 extern unsigned int ath12k_debug_mask;
+extern bool ath12k_ftm_mode;
 
 #ifdef CONFIG_ATH12K_DEBUG
 __printf(3, 4) void __ath12k_dbg(struct ath12k_base *ab,
diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
index 9e5a4e75f2f62..b1f27c3ac723e 100644
--- a/drivers/net/wireless/ath/ath12k/dp.c
+++ b/drivers/net/wireless/ath/ath12k/dp.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <crypto/hash.h>
@@ -1315,6 +1315,9 @@ void ath12k_dp_cc_config(struct ath12k_base *ab)
 	u32 wbm_base = HAL_SEQ_WCSS_UMAC_WBM_REG;
 	u32 val = 0;
 
+	if (ath12k_ftm_mode)
+		return;
+
 	ath12k_hif_write32(ab, reo_base + HAL_REO1_SW_COOKIE_CFG0(ab), cmem_base);
 
 	val |= u32_encode_bits(ATH12K_CMEM_ADDR_MSB,
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 2d062b5904a8e..329c050037219 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -15,6 +15,7 @@
 #include "hw.h"
 #include "dp_tx.h"
 #include "dp_rx.h"
+#include "testmode.h"
 #include "peer.h"
 #include "debugfs.h"
 #include "hif.h"
@@ -675,7 +676,10 @@ struct ath12k *ath12k_mac_get_ar_by_pdev_id(struct ath12k_base *ab, u32 pdev_id)
 		return NULL;
 
 	for (i = 0; i < ab->num_radios; i++) {
-		pdev = rcu_dereference(ab->pdevs_active[i]);
+		if (ab->fw_mode == ATH12K_FIRMWARE_MODE_FTM)
+			pdev = &ab->pdevs[i];
+		else
+			pdev = rcu_dereference(ab->pdevs_active[i]);
 
 		if (pdev && pdev->pdev_id == pdev_id)
 			return (pdev->ar ? pdev->ar : NULL);
@@ -7363,9 +7367,14 @@ static int ath12k_mac_start(struct ath12k *ar)
 
 static void ath12k_drain_tx(struct ath12k_hw *ah)
 {
-	struct ath12k *ar;
+	struct ath12k *ar = ah->radio;
 	int i;
 
+	if (ath12k_ftm_mode) {
+		ath12k_err(ar->ab, "fail to start mac operations in ftm mode\n");
+		return;
+	}
+
 	lockdep_assert_wiphy(ah->hw->wiphy);
 
 	for_each_ar(ah, ar, i)
@@ -7394,6 +7403,7 @@ static int ath12k_mac_op_start(struct ieee80211_hw *hw)
 	case ATH12K_HW_STATE_RESTARTED:
 	case ATH12K_HW_STATE_WEDGED:
 	case ATH12K_HW_STATE_ON:
+	case ATH12K_HW_STATE_TM:
 		ah->state = ATH12K_HW_STATE_OFF;
 
 		WARN_ON(1);
@@ -10299,6 +10309,7 @@ static const struct ieee80211_ops ath12k_ops = {
 	.resume				= ath12k_wow_op_resume,
 	.set_wakeup			= ath12k_wow_op_set_wakeup,
 #endif
+	CFG80211_TESTMODE_CMD(ath12k_tm_cmd)
 };
 
 static void ath12k_mac_update_ch_list(struct ath12k *ar,
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 06cff3849ab8d..4a50d7118b3ea 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -1561,6 +1561,7 @@ static int ath12k_pci_probe(struct pci_dev *pdev,
 	ab_pci->ab = ab;
 	ab_pci->pdev = pdev;
 	ab->hif.ops = &ath12k_pci_hif_ops;
+	ab->fw_mode = ATH12K_FIRMWARE_MODE_NORMAL;
 	pci_set_drvdata(pdev, ab);
 	spin_lock_init(&ab_pci->window_lock);
 
diff --git a/drivers/net/wireless/ath/ath12k/testmode.c b/drivers/net/wireless/ath/ath12k/testmode.c
new file mode 100644
index 0000000000000..18d56a976dc74
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/testmode.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: BSD-3-Clause-Clear
+/*
+ * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include "testmode.h"
+#include <net/netlink.h>
+#include "debug.h"
+#include "wmi.h"
+#include "hw.h"
+#include "core.h"
+#include "hif.h"
+#include "../testmode_i.h"
+
+#define ATH12K_FTM_SEGHDR_CURRENT_SEQ		GENMASK(3, 0)
+#define ATH12K_FTM_SEGHDR_TOTAL_SEGMENTS	GENMASK(7, 4)
+
+static const struct nla_policy ath12k_tm_policy[ATH_TM_ATTR_MAX + 1] = {
+	[ATH_TM_ATTR_CMD]		= { .type = NLA_U32 },
+	[ATH_TM_ATTR_DATA]		= { .type = NLA_BINARY,
+					    .len = ATH_TM_DATA_MAX_LEN },
+	[ATH_TM_ATTR_WMI_CMDID]		= { .type = NLA_U32 },
+	[ATH_TM_ATTR_VERSION_MAJOR]	= { .type = NLA_U32 },
+	[ATH_TM_ATTR_VERSION_MINOR]	= { .type = NLA_U32 },
+};
+
+static struct ath12k *ath12k_tm_get_ar(struct ath12k_base *ab)
+{
+	struct ath12k_pdev *pdev;
+	struct ath12k *ar;
+	int i;
+
+	for (i = 0; i < ab->num_radios; i++) {
+		pdev = &ab->pdevs[i];
+		ar = pdev->ar;
+
+		if (ar && ar->ah->state == ATH12K_HW_STATE_TM)
+			return ar;
+	}
+
+	return NULL;
+}
+
+void ath12k_tm_wmi_event_unsegmented(struct ath12k_base *ab, u32 cmd_id,
+				     struct sk_buff *skb)
+{
+	struct sk_buff *nl_skb;
+	struct ath12k *ar;
+
+	ath12k_dbg(ab, ATH12K_DBG_TESTMODE,
+		   "testmode event wmi cmd_id %d skb length %d\n",
+		   cmd_id, skb->len);
+
+	ath12k_dbg_dump(ab, ATH12K_DBG_TESTMODE, NULL, "", skb->data, skb->len);
+
+	ar = ath12k_tm_get_ar(ab);
+	if (!ar) {
+		ath12k_warn(ab, "testmode event not handled due to invalid pdev\n");
+		return;
+	}
+
+	spin_lock_bh(&ar->data_lock);
+
+	nl_skb = cfg80211_testmode_alloc_event_skb(ar->ah->hw->wiphy,
+						   2 * nla_total_size(sizeof(u32)) +
+						   nla_total_size(skb->len),
+						   GFP_ATOMIC);
+	spin_unlock_bh(&ar->data_lock);
+
+	if (!nl_skb) {
+		ath12k_warn(ab,
+			    "failed to allocate skb for unsegmented testmode wmi event\n");
+		return;
+	}
+
+	if (nla_put_u32(nl_skb, ATH_TM_ATTR_CMD, ATH_TM_CMD_WMI) ||
+	    nla_put_u32(nl_skb, ATH_TM_ATTR_WMI_CMDID, cmd_id) ||
+	    nla_put(nl_skb, ATH_TM_ATTR_DATA, skb->len, skb->data)) {
+		ath12k_warn(ab, "failed to populate testmode unsegmented event\n");
+		kfree_skb(nl_skb);
+		return;
+	}
+
+	cfg80211_testmode_event(nl_skb, GFP_ATOMIC);
+}
+
+void ath12k_tm_process_event(struct ath12k_base *ab, u32 cmd_id,
+			     const struct ath12k_wmi_ftm_event *ftm_msg,
+			     u16 length)
+{
+	struct sk_buff *nl_skb;
+	struct ath12k *ar;
+	u32 data_pos, pdev_id;
+	u16 datalen;
+	u8 total_segments, current_seq;
+	u8 const *buf_pos;
+
+	ath12k_dbg(ab, ATH12K_DBG_TESTMODE,
+		   "testmode event wmi cmd_id %d ftm event msg %pK datalen %d\n",
+		   cmd_id, ftm_msg, length);
+	ath12k_dbg_dump(ab, ATH12K_DBG_TESTMODE, NULL, "", ftm_msg, length);
+	pdev_id = DP_HW2SW_MACID(le32_to_cpu(ftm_msg->seg_hdr.pdev_id));
+
+	if (pdev_id >= ab->num_radios) {
+		ath12k_warn(ab, "testmode event not handled due to invalid pdev id\n");
+		return;
+	}
+
+	ar = ab->pdevs[pdev_id].ar;
+
+	if (!ar) {
+		ath12k_warn(ab, "testmode event not handled due to absence of pdev\n");
+		return;
+	}
+
+	current_seq = le32_get_bits(ftm_msg->seg_hdr.segmentinfo,
+				    ATH12K_FTM_SEGHDR_CURRENT_SEQ);
+	total_segments = le32_get_bits(ftm_msg->seg_hdr.segmentinfo,
+				       ATH12K_FTM_SEGHDR_TOTAL_SEGMENTS);
+	datalen = length - (sizeof(struct ath12k_wmi_ftm_seg_hdr_params));
+	buf_pos = ftm_msg->data;
+
+	if (current_seq == 0) {
+		ab->ftm_event_obj.expected_seq = 0;
+		ab->ftm_event_obj.data_pos = 0;
+	}
+
+	data_pos = ab->ftm_event_obj.data_pos;
+
+	if ((data_pos + datalen) > ATH_FTM_EVENT_MAX_BUF_LENGTH) {
+		ath12k_warn(ab,
+			    "Invalid event length date_pos[%d] datalen[%d]\n",
+			    data_pos, datalen);
+		return;
+	}
+
+	memcpy(&ab->ftm_event_obj.eventdata[data_pos], buf_pos, datalen);
+	data_pos += datalen;
+
+	if (++ab->ftm_event_obj.expected_seq != total_segments) {
+		ab->ftm_event_obj.data_pos = data_pos;
+		ath12k_dbg(ab, ATH12K_DBG_TESTMODE,
+			   "partial data received current_seq[%d], total_seg[%d]\n",
+			    current_seq, total_segments);
+		return;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_TESTMODE,
+		   "total data length[%d] = [%d]\n",
+		   data_pos, ftm_msg->seg_hdr.len);
+
+	spin_lock_bh(&ar->data_lock);
+	nl_skb = cfg80211_testmode_alloc_event_skb(ar->ah->hw->wiphy,
+						   2 * nla_total_size(sizeof(u32)) +
+						   nla_total_size(data_pos),
+						   GFP_ATOMIC);
+	spin_unlock_bh(&ar->data_lock);
+
+	if (!nl_skb) {
+		ath12k_warn(ab,
+			    "failed to allocate skb for testmode wmi event\n");
+		return;
+	}
+
+	if (nla_put_u32(nl_skb, ATH_TM_ATTR_CMD,
+			ATH_TM_CMD_WMI_FTM) ||
+	    nla_put_u32(nl_skb, ATH_TM_ATTR_WMI_CMDID, cmd_id) ||
+	    nla_put(nl_skb, ATH_TM_ATTR_DATA, data_pos,
+		    &ab->ftm_event_obj.eventdata[0])) {
+		ath12k_warn(ab, "failed to populate testmode event");
+		kfree_skb(nl_skb);
+		return;
+	}
+
+	cfg80211_testmode_event(nl_skb, GFP_ATOMIC);
+}
+
+static int ath12k_tm_cmd_get_version(struct ath12k *ar, struct nlattr *tb[])
+{
+	struct sk_buff *skb;
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_TESTMODE,
+		   "testmode cmd get version_major %d version_minor %d\n",
+		   ATH_TESTMODE_VERSION_MAJOR,
+		   ATH_TESTMODE_VERSION_MINOR);
+
+	spin_lock_bh(&ar->data_lock);
+	skb = cfg80211_testmode_alloc_reply_skb(ar->ah->hw->wiphy,
+						2 * nla_total_size(sizeof(u32)));
+	spin_unlock_bh(&ar->data_lock);
+
+	if (!skb)
+		return -ENOMEM;
+
+	if (nla_put_u32(skb, ATH_TM_ATTR_VERSION_MAJOR,
+			ATH_TESTMODE_VERSION_MAJOR) ||
+	    nla_put_u32(skb, ATH_TM_ATTR_VERSION_MINOR,
+			ATH_TESTMODE_VERSION_MINOR)) {
+		kfree_skb(skb);
+		return -ENOBUFS;
+	}
+
+	return cfg80211_testmode_reply(skb);
+}
+
+static int ath12k_tm_cmd_process_ftm(struct ath12k *ar, struct nlattr *tb[])
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct sk_buff *skb;
+	struct ath12k_wmi_ftm_cmd *ftm_cmd;
+	int ret = 0;
+	void *buf;
+	size_t aligned_len;
+	u32 cmd_id, buf_len;
+	u16 chunk_len, total_bytes, num_segments;
+	u8 segnumber = 0, *bufpos;
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_TESTMODE, "ah->state  %d\n", ar->ah->state);
+	if (ar->ah->state != ATH12K_HW_STATE_TM)
+		return -ENETDOWN;
+
+	if (!tb[ATH_TM_ATTR_DATA])
+		return -EINVAL;
+
+	buf = nla_data(tb[ATH_TM_ATTR_DATA]);
+	buf_len = nla_len(tb[ATH_TM_ATTR_DATA]);
+	cmd_id = WMI_PDEV_UTF_CMDID;
+	ath12k_dbg(ar->ab, ATH12K_DBG_TESTMODE,
+		   "testmode cmd wmi cmd_id %d buf %pK buf_len %d\n",
+		   cmd_id, buf, buf_len);
+	ath12k_dbg_dump(ar->ab, ATH12K_DBG_TESTMODE, NULL, "", buf, buf_len);
+	bufpos = buf;
+	total_bytes = buf_len;
+	num_segments = total_bytes / MAX_WMI_UTF_LEN;
+
+	if (buf_len - (num_segments * MAX_WMI_UTF_LEN))
+		num_segments++;
+
+	while (buf_len) {
+		if (buf_len > MAX_WMI_UTF_LEN)
+			chunk_len = MAX_WMI_UTF_LEN;    /* MAX message */
+		else
+			chunk_len = buf_len;
+
+		skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, (chunk_len +
+					sizeof(struct ath12k_wmi_ftm_cmd)));
+
+		if (!skb)
+			return -ENOMEM;
+
+		ftm_cmd = (struct ath12k_wmi_ftm_cmd *)skb->data;
+		aligned_len  = chunk_len + sizeof(struct ath12k_wmi_ftm_seg_hdr_params);
+		ftm_cmd->tlv_header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_BYTE, aligned_len);
+		ftm_cmd->seg_hdr.len = cpu_to_le32(total_bytes);
+		ftm_cmd->seg_hdr.msgref = cpu_to_le32(ar->ftm_msgref);
+		ftm_cmd->seg_hdr.segmentinfo =
+			le32_encode_bits(num_segments,
+					 ATH12K_FTM_SEGHDR_TOTAL_SEGMENTS) |
+			le32_encode_bits(segnumber,
+					 ATH12K_FTM_SEGHDR_CURRENT_SEQ);
+		ftm_cmd->seg_hdr.pdev_id = cpu_to_le32(ar->pdev->pdev_id);
+		segnumber++;
+		memcpy(&ftm_cmd->data, bufpos, chunk_len);
+		ret = ath12k_wmi_cmd_send(wmi, skb, cmd_id);
+
+		if (ret) {
+			ath12k_warn(ar->ab, "ftm wmi command fail: %d\n", ret);
+			kfree_skb(skb);
+			return ret;
+		}
+
+		buf_len -= chunk_len;
+		bufpos += chunk_len;
+	}
+
+	++ar->ftm_msgref;
+	return ret;
+}
+
+static int ath12k_tm_cmd_testmode_start(struct ath12k *ar, struct nlattr *tb[])
+{
+	if (ar->ah->state == ATH12K_HW_STATE_TM)
+		return -EALREADY;
+
+	if (ar->ah->state != ATH12K_HW_STATE_OFF)
+		return -EBUSY;
+
+	ar->ab->ftm_event_obj.eventdata = kzalloc(ATH_FTM_EVENT_MAX_BUF_LENGTH,
+						  GFP_KERNEL);
+
+	if (!ar->ab->ftm_event_obj.eventdata)
+		return -ENOMEM;
+
+	ar->ah->state = ATH12K_HW_STATE_TM;
+	ar->ftm_msgref = 0;
+	return 0;
+}
+
+static int ath12k_tm_cmd_wmi(struct ath12k *ar, struct nlattr *tb[])
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct sk_buff *skb;
+	struct wmi_pdev_set_param_cmd *cmd;
+	int ret = 0, tag;
+	void *buf;
+	u32 cmd_id, buf_len;
+
+	if (!tb[ATH_TM_ATTR_DATA])
+		return -EINVAL;
+
+	if (!tb[ATH_TM_ATTR_WMI_CMDID])
+		return -EINVAL;
+
+	buf = nla_data(tb[ATH_TM_ATTR_DATA]);
+	buf_len = nla_len(tb[ATH_TM_ATTR_DATA]);
+
+	if (!buf_len) {
+		ath12k_warn(ar->ab, "No data present in testmode command\n");
+		return -EINVAL;
+	}
+
+	cmd_id = nla_get_u32(tb[ATH_TM_ATTR_WMI_CMDID]);
+
+	cmd = buf;
+	tag = le32_get_bits(cmd->tlv_header, WMI_TLV_TAG);
+
+	if (tag == WMI_TAG_PDEV_SET_PARAM_CMD)
+		cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_TESTMODE,
+		   "testmode cmd wmi cmd_id %d  buf length %d\n",
+		   cmd_id, buf_len);
+
+	ath12k_dbg_dump(ar->ab, ATH12K_DBG_TESTMODE, NULL, "", buf, buf_len);
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, buf_len);
+
+	if (!skb)
+		return -ENOMEM;
+
+	memcpy(skb->data, buf, buf_len);
+
+	ret = ath12k_wmi_cmd_send(wmi, skb, cmd_id);
+	if (ret) {
+		dev_kfree_skb(skb);
+		ath12k_warn(ar->ab, "failed to transmit wmi command (testmode): %d\n",
+			    ret);
+	}
+
+	return ret;
+}
+
+int ath12k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  void *data, int len)
+{
+	struct ath12k_hw *ah = hw->priv;
+	struct ath12k *ar = NULL;
+	struct nlattr *tb[ATH_TM_ATTR_MAX + 1];
+	struct ath12k_base *ab;
+	struct wiphy *wiphy = hw->wiphy;
+	int ret;
+
+	lockdep_assert_held(&wiphy->mtx);
+
+	ret = nla_parse(tb, ATH_TM_ATTR_MAX, data, len, ath12k_tm_policy,
+			NULL);
+	if (ret)
+		return ret;
+
+	if (!tb[ATH_TM_ATTR_CMD])
+		return -EINVAL;
+
+	/* TODO: have to handle ar for MLO case */
+	if (ah->num_radio)
+		ar = ah->radio;
+
+	if (!ar)
+		return -EINVAL;
+
+	ab = ar->ab;
+	switch (nla_get_u32(tb[ATH_TM_ATTR_CMD])) {
+	case ATH_TM_CMD_WMI:
+		return ath12k_tm_cmd_wmi(ar, tb);
+	case ATH_TM_CMD_TESTMODE_START:
+		return ath12k_tm_cmd_testmode_start(ar, tb);
+	case ATH_TM_CMD_GET_VERSION:
+		return ath12k_tm_cmd_get_version(ar, tb);
+	case ATH_TM_CMD_WMI_FTM:
+		set_bit(ATH12K_FLAG_FTM_SEGMENTED, &ab->dev_flags);
+		return ath12k_tm_cmd_process_ftm(ar, tb);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
diff --git a/drivers/net/wireless/ath/ath12k/testmode.h b/drivers/net/wireless/ath/ath12k/testmode.h
new file mode 100644
index 0000000000000..ef6ab21d19b82
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/testmode.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include "core.h"
+#include "hif.h"
+
+#ifdef CONFIG_NL80211_TESTMODE
+
+void ath12k_tm_wmi_event_unsegmented(struct ath12k_base *ab, u32 cmd_id,
+				     struct sk_buff *skb);
+void ath12k_tm_process_event(struct ath12k_base *ab, u32 cmd_id,
+			     const struct ath12k_wmi_ftm_event *ftm_msg,
+			     u16 length);
+int ath12k_tm_cmd(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		  void *data, int len);
+
+#else
+
+static inline void ath12k_tm_wmi_event_unsegmented(struct ath12k_base *ab, u32 cmd_id,
+						   struct sk_buff *skb)
+{
+}
+
+static inline void ath12k_tm_process_event(struct ath12k_base *ab, u32 cmd_id,
+					   const struct ath12k_wmi_ftm_event *msg,
+					   u16 length)
+{
+}
+
+static inline int ath12k_tm_cmd(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif,
+				void *data, int len)
+{
+	return 0;
+}
+
+#endif
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 246b8aab49a9a..a7625a3d1a3a9 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -20,6 +20,7 @@
 #include "hw.h"
 #include "peer.h"
 #include "p2p.h"
+#include "testmode.h"
 
 struct ath12k_wmi_svc_ready_parse {
 	bool wmi_svc_bitmap_done;
@@ -6997,6 +6998,35 @@ ath12k_wmi_pdev_dfs_radar_detected_event(struct ath12k_base *ab, struct sk_buff
 	kfree(tb);
 }
 
+static void ath12k_tm_wmi_event_segmented(struct ath12k_base *ab, u32 cmd_id,
+					  struct sk_buff *skb)
+{
+	const struct ath12k_wmi_ftm_event *ev;
+	const void **tb;
+	int ret;
+	u16 length;
+
+	tb = ath12k_wmi_tlv_parse_alloc(ab, skb, GFP_ATOMIC);
+
+	if (IS_ERR(tb)) {
+		ret = PTR_ERR(tb);
+		ath12k_warn(ab, "failed to parse ftm event tlv: %d\n", ret);
+		return;
+	}
+
+	ev = tb[WMI_TAG_ARRAY_BYTE];
+	if (!ev) {
+		ath12k_warn(ab, "failed to fetch ftm msg\n");
+		kfree(tb);
+		return;
+	}
+
+	length = skb->len - TLV_HDR_SIZE;
+	ath12k_tm_process_event(ab, cmd_id, ev, length);
+	kfree(tb);
+	tb = NULL;
+}
+
 static void
 ath12k_wmi_pdev_temperature_event(struct ath12k_base *ab,
 				  struct sk_buff *skb)
@@ -7555,7 +7585,12 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb)
 	case WMI_OBSS_COLOR_COLLISION_DETECTION_EVENTID:
 		/* debug might flood hence silently ignore (no-op) */
 		break;
-	/* TODO: Add remaining events */
+	case WMI_PDEV_UTF_EVENTID:
+		if (test_bit(ATH12K_FLAG_FTM_SEGMENTED, &ab->dev_flags))
+			ath12k_tm_wmi_event_segmented(ab, id, skb);
+		else
+			ath12k_tm_wmi_event_unsegmented(ab, id, skb);
+		break;
 	default:
 		ath12k_dbg(ab, ATH12K_DBG_WMI, "Unknown eventid: 0x%x\n", id);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 00d024d4eb2cb..38aed18b99f42 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -3624,6 +3624,26 @@ struct ath12k_wmi_p2p_noa_info {
 	struct ath12k_wmi_p2p_noa_descriptor descriptors[WMI_P2P_MAX_NOA_DESCRIPTORS];
 } __packed;
 
+#define MAX_WMI_UTF_LEN 252
+
+struct ath12k_wmi_ftm_seg_hdr_params {
+	__le32 len;
+	__le32 msgref;
+	__le32 segmentinfo;
+	__le32 pdev_id;
+} __packed;
+
+struct ath12k_wmi_ftm_cmd {
+	__le32 tlv_header;
+	struct ath12k_wmi_ftm_seg_hdr_params seg_hdr;
+	u8 data[];
+} __packed;
+
+struct ath12k_wmi_ftm_event {
+	struct ath12k_wmi_ftm_seg_hdr_params seg_hdr;
+	u8 data[];
+} __packed;
+
 #define WMI_BEACON_TX_BUFFER_SIZE	512
 
 #define WMI_EMA_BEACON_CNT      GENMASK(7, 0)
diff --git a/drivers/net/wireless/ath/ath12k/wow.c b/drivers/net/wireless/ath/ath12k/wow.c
index 9e1c0bfd212f5..dce9bd0bcaefb 100644
--- a/drivers/net/wireless/ath/ath12k/wow.c
+++ b/drivers/net/wireless/ath/ath12k/wow.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/delay.h>
@@ -990,6 +990,7 @@ int ath12k_wow_op_resume(struct ieee80211_hw *hw)
 		case ATH12K_HW_STATE_RESTARTING:
 		case ATH12K_HW_STATE_RESTARTED:
 		case ATH12K_HW_STATE_WEDGED:
+		case ATH12K_HW_STATE_TM:
 			ath12k_warn(ar->ab, "encountered unexpected device state %d on resume, cannot recover\n",
 				    ah->state);
 			ret = -EIO;

From a93185b708f259ace63414b8529e9e15c6323b69 Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Sun, 19 Jan 2025 14:06:57 +0530
Subject: [PATCH 0015/2753] wifi: ath12k: Disable MLO in Factory Test Mode

Factory test mode(FTM) is supported only in non-MLO(multi-link operation)
mode. Therefore, disable MLO when driver boots in FTM mode.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250119083657.1937557-5-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 20c8a7bed3db6..2dd0666959cd4 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1614,6 +1614,9 @@ static struct ath12k_hw_group *ath12k_core_hw_group_assign(struct ath12k_base *a
 
 	lockdep_assert_held(&ath12k_hw_group_mutex);
 
+	if (ath12k_ftm_mode)
+		goto invalid_group;
+
 	/* The grouping of multiple devices will be done based on device tree file.
 	 * The platforms that do not have any valid group information would have
 	 * each device to be part of its own invalid group.
@@ -1801,6 +1804,9 @@ void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag)
 	struct ath12k_base *ab;
 	int i;
 
+	if (ath12k_ftm_mode)
+		return;
+
 	lockdep_assert_held(&ag->mutex);
 
 	/* If more than one devices are grouped, then inter MLO

From c8084a89bd91b05f51a36bff61f63a94c800b0d6 Mon Sep 17 00:00:00 2001
From: Yu-Chun Lin <eleanor15x@gmail.com>
Date: Sun, 19 Jan 2025 16:43:12 +0800
Subject: [PATCH 0016/2753] Input: wdt87xx_i2c - fix compiler warning

As reported by the kernel test robot, the following warning occur:

>> drivers/input/touchscreen/wdt87xx_i2c.c:1166:36: warning: 'wdt87xx_acpi_id' defined but not used [-Wunused-const-variable=]
    1166 | static const struct acpi_device_id wdt87xx_acpi_id[] = {
         |                                    ^~~~~~~~~~~~~~~

The 'wdt87xx_acpi_id' array is only used when CONFIG_ACPI is enabled.
Wrapping its definition and 'MODULE_DEVICE_TABLE' in '#ifdef CONFIG_ACPI'
prevents a compiler warning when ACPI is disabled.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501181549.uzdlBwuN-lkp@intel.com/
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Link: https://lore.kernel.org/r/20250119084312.1851486-1-eleanor15x@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/wdt87xx_i2c.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/touchscreen/wdt87xx_i2c.c b/drivers/input/touchscreen/wdt87xx_i2c.c
index 27941245e962f..88d376090e6e6 100644
--- a/drivers/input/touchscreen/wdt87xx_i2c.c
+++ b/drivers/input/touchscreen/wdt87xx_i2c.c
@@ -1153,11 +1153,13 @@ static const struct i2c_device_id wdt87xx_dev_id[] = {
 };
 MODULE_DEVICE_TABLE(i2c, wdt87xx_dev_id);
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id wdt87xx_acpi_id[] = {
 	{ "WDHT0001", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, wdt87xx_acpi_id);
+#endif
 
 static struct i2c_driver wdt87xx_driver = {
 	.probe		= wdt87xx_ts_probe,

From 28a9972e0f0693cd4d08f431c992fa6be39c788c Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Wed, 22 Jan 2025 17:01:12 +0100
Subject: [PATCH 0017/2753] wifi: ath12k: fix skb_ext_desc leak in
 ath12k_dp_tx() error path

When vlan support was added, we missed that when
ath12k_dp_prepare_htt_metadata() returns an error we also need to free
the skb holding the metadata before going on with the cleanup process.

Compile tested only.

Fixes: 26dd8ccdba4d ("wifi: ath12k: dynamic VLAN support")
Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250122160112.3234558-1-nico.escande@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index a8d341a6df01e..e0b85f959cd4a 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -398,6 +398,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
 			if (ret < 0) {
 				ath12k_dbg(ab, ATH12K_DBG_DP_TX,
 					   "Failed to add HTT meta data, dropping packet\n");
+				kfree_skb(skb_ext_desc);
 				goto fail_unmap_dma;
 			}
 		}

From 8a9c06b40882ebea45563059ddc5d57acdec9dda Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Wed, 15 Jan 2025 14:35:35 +0800
Subject: [PATCH 0018/2753] wifi: ath12k: report station mode transmit rate

Currently, the transmit rate of "iw dev xxx station dump" command
always show an invalid value.

To address this issue, ath12k parse the info of transmit complete
report from firmware and indicate the transmit rate to mac80211.

This patch affects the station mode of WCN7850 and QCN9274.

After that, "iw dev xxx station dump" show the correct transmit rate.
Such as:

Station 00:03:7f:12:03:03 (on wlo1)
        inactive time:  872 ms
        rx bytes:       219111
        rx packets:     1133
        tx bytes:       53767
        tx packets:     462
        tx retries:     51
        tx failed:      0
        beacon loss:    0
        beacon rx:      403
        rx drop misc:   74
        signal:         -95 dBm
        beacon signal avg:      -18 dBm
        tx bitrate:     1441.1 MBit/s 80MHz EHT-MCS 13 EHT-NSS 2 EHT-GI 0

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00214-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219715
Link: https://patch.msgid.link/20250115063537.35797-2-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h    |   2 +
 drivers/net/wireless/ath/ath12k/dp_rx.h   |   5 +-
 drivers/net/wireless/ath/ath12k/dp_tx.c   | 139 +++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/hal_rx.h  |   5 +-
 drivers/net/wireless/ath/ath12k/hal_tx.h  |  10 +-
 drivers/net/wireless/ath/ath12k/mac.c     |  79 ++++++++++++
 drivers/net/wireless/ath/ath12k/mac.h     |   5 +-
 drivers/net/wireless/ath/ath12k/rx_desc.h |   3 +-
 8 files changed, 238 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 86a1eeec64a6e..95c2ff6a9ae2b 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -87,6 +87,7 @@ enum wme_ac {
 #define ATH12K_HT_MCS_MAX	7
 #define ATH12K_VHT_MCS_MAX	9
 #define ATH12K_HE_MCS_MAX	11
+#define ATH12K_EHT_MCS_MAX	15
 
 enum ath12k_crypt_mode {
 	/* Only use hardware crypto engine */
@@ -501,6 +502,7 @@ struct ath12k_link_sta {
 	struct ath12k_rx_peer_stats *rx_stats;
 	struct ath12k_wbm_tx_stats *wbm_tx_stats;
 	u32 bw_prev;
+	u32 peer_nss;
 
 	/* For now the assoc link will be considered primary */
 	bool is_assoc_link;
diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h
index 1ce82088c9540..c0aa965f47e77 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_DP_RX_H
 #define ATH12K_DP_RX_H
@@ -79,6 +79,9 @@ static inline u32 ath12k_he_gi_to_nl80211_he_gi(u8 sgi)
 	case RX_MSDU_START_SGI_3_2_US:
 		ret = NL80211_RATE_INFO_HE_GI_3_2;
 		break;
+	default:
+		ret = NL80211_RATE_INFO_HE_GI_0_8;
+		break;
 	}
 
 	return ret;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index e0b85f959cd4a..de8bb9c1533e9 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -8,6 +8,8 @@
 #include "dp_tx.h"
 #include "debug.h"
 #include "hw.h"
+#include "peer.h"
+#include "mac.h"
 
 static enum hal_tcl_encap_type
 ath12k_dp_tx_get_encap_type(struct ath12k_link_vif *arvif, struct sk_buff *skb)
@@ -581,6 +583,124 @@ ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
 	}
 }
 
+static void ath12k_dp_tx_update_txcompl(struct ath12k *ar, struct hal_tx_status *ts)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_peer *peer;
+	struct ieee80211_sta *sta;
+	struct ath12k_sta *ahsta;
+	struct ath12k_link_sta *arsta;
+	struct rate_info txrate = {0};
+	u16 rate, ru_tones;
+	u8 rate_idx = 0;
+	int ret;
+
+	spin_lock_bh(&ab->base_lock);
+	peer = ath12k_peer_find_by_id(ab, ts->peer_id);
+	if (!peer || !peer->sta) {
+		ath12k_dbg(ab, ATH12K_DBG_DP_TX,
+			   "failed to find the peer by id %u\n", ts->peer_id);
+		spin_unlock_bh(&ab->base_lock);
+		return;
+	}
+	sta = peer->sta;
+	ahsta = ath12k_sta_to_ahsta(sta);
+	arsta = &ahsta->deflink;
+
+	/* This is to prefer choose the real NSS value arsta->last_txrate.nss,
+	 * if it is invalid, then choose the NSS value while assoc.
+	 */
+	if (arsta->last_txrate.nss)
+		txrate.nss = arsta->last_txrate.nss;
+	else
+		txrate.nss = arsta->peer_nss;
+	spin_unlock_bh(&ab->base_lock);
+
+	switch (ts->pkt_type) {
+	case HAL_TX_RATE_STATS_PKT_TYPE_11A:
+	case HAL_TX_RATE_STATS_PKT_TYPE_11B:
+		ret = ath12k_mac_hw_ratecode_to_legacy_rate(ts->mcs,
+							    ts->pkt_type,
+							    &rate_idx,
+							    &rate);
+		if (ret < 0) {
+			ath12k_warn(ab, "Invalid tx legacy rate %d\n", ret);
+			return;
+		}
+
+		txrate.legacy = rate;
+		break;
+	case HAL_TX_RATE_STATS_PKT_TYPE_11N:
+		if (ts->mcs > ATH12K_HT_MCS_MAX) {
+			ath12k_warn(ab, "Invalid HT mcs index %d\n", ts->mcs);
+			return;
+		}
+
+		if (txrate.nss != 0)
+			txrate.mcs = ts->mcs + 8 * (txrate.nss - 1);
+
+		txrate.flags = RATE_INFO_FLAGS_MCS;
+
+		if (ts->sgi)
+			txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
+		break;
+	case HAL_TX_RATE_STATS_PKT_TYPE_11AC:
+		if (ts->mcs > ATH12K_VHT_MCS_MAX) {
+			ath12k_warn(ab, "Invalid VHT mcs index %d\n", ts->mcs);
+			return;
+		}
+
+		txrate.mcs = ts->mcs;
+		txrate.flags = RATE_INFO_FLAGS_VHT_MCS;
+
+		if (ts->sgi)
+			txrate.flags |= RATE_INFO_FLAGS_SHORT_GI;
+		break;
+	case HAL_TX_RATE_STATS_PKT_TYPE_11AX:
+		if (ts->mcs > ATH12K_HE_MCS_MAX) {
+			ath12k_warn(ab, "Invalid HE mcs index %d\n", ts->mcs);
+			return;
+		}
+
+		txrate.mcs = ts->mcs;
+		txrate.flags = RATE_INFO_FLAGS_HE_MCS;
+		txrate.he_gi = ath12k_he_gi_to_nl80211_he_gi(ts->sgi);
+		break;
+	case HAL_TX_RATE_STATS_PKT_TYPE_11BE:
+		if (ts->mcs > ATH12K_EHT_MCS_MAX) {
+			ath12k_warn(ab, "Invalid EHT mcs index %d\n", ts->mcs);
+			return;
+		}
+
+		txrate.mcs = ts->mcs;
+		txrate.flags = RATE_INFO_FLAGS_EHT_MCS;
+		txrate.eht_gi = ath12k_mac_eht_gi_to_nl80211_eht_gi(ts->sgi);
+		break;
+	default:
+		ath12k_warn(ab, "Invalid tx pkt type: %d\n", ts->pkt_type);
+		return;
+	}
+
+	txrate.bw = ath12k_mac_bw_to_mac80211_bw(ts->bw);
+
+	if (ts->ofdma && ts->pkt_type == HAL_TX_RATE_STATS_PKT_TYPE_11AX) {
+		txrate.bw = RATE_INFO_BW_HE_RU;
+		ru_tones = ath12k_mac_he_convert_tones_to_ru_tones(ts->tones);
+		txrate.he_ru_alloc =
+			ath12k_he_ru_tones_to_nl80211_he_ru_alloc(ru_tones);
+	}
+
+	if (ts->ofdma && ts->pkt_type == HAL_TX_RATE_STATS_PKT_TYPE_11BE) {
+		txrate.bw = RATE_INFO_BW_EHT_RU;
+		txrate.eht_ru_alloc =
+			ath12k_mac_eht_ru_tones_to_nl80211_eht_ru_alloc(ts->tones);
+	}
+
+	spin_lock_bh(&ab->base_lock);
+	arsta->txrate = txrate;
+	spin_unlock_bh(&ab->base_lock);
+}
+
 static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 				       struct sk_buff *msdu,
 				       struct hal_tx_status *ts)
@@ -659,6 +779,8 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
 	 * Might end up reporting it out-of-band from HTT stats.
 	 */
 
+	ath12k_dp_tx_update_txcompl(ar, ts);
+
 	ieee80211_tx_status_skb(ath12k_ar_to_hw(ar), msdu);
 
 exit:
@@ -669,6 +791,8 @@ static void ath12k_dp_tx_status_parse(struct ath12k_base *ab,
 				      struct hal_wbm_completion_ring_tx *desc,
 				      struct hal_tx_status *ts)
 {
+	u32 info0 = le32_to_cpu(desc->rate_stats.info0);
+
 	ts->buf_rel_source =
 		le32_get_bits(desc->info0, HAL_WBM_COMPL_TX_INFO0_REL_SRC_MODULE);
 	if (ts->buf_rel_source != HAL_WBM_REL_SRC_MODULE_FW &&
@@ -683,10 +807,17 @@ static void ath12k_dp_tx_status_parse(struct ath12k_base *ab,
 
 	ts->ppdu_id = le32_get_bits(desc->info1,
 				    HAL_WBM_COMPL_TX_INFO1_TQM_STATUS_NUMBER);
-	if (le32_to_cpu(desc->rate_stats.info0) & HAL_TX_RATE_STATS_INFO0_VALID)
-		ts->rate_stats = le32_to_cpu(desc->rate_stats.info0);
-	else
-		ts->rate_stats = 0;
+
+	ts->peer_id = le32_get_bits(desc->info3, HAL_WBM_COMPL_TX_INFO3_PEER_ID);
+
+	if (info0 & HAL_TX_RATE_STATS_INFO0_VALID) {
+		ts->pkt_type = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_PKT_TYPE);
+		ts->mcs = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_MCS);
+		ts->sgi = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_SGI);
+		ts->bw = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_BW);
+		ts->tones = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_TONES_IN_RU);
+		ts->ofdma = u32_get_bits(info0, HAL_TX_RATE_STATS_INFO0_OFDMA_TX);
+	}
 }
 
 void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id)
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index b08aa2e79f411..04e9f5f8e83ab 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_HAL_RX_H
@@ -662,6 +662,9 @@ enum nl80211_he_ru_alloc ath12k_he_ru_tones_to_nl80211_he_ru_alloc(u16 ru_tones)
 	case RU_996:
 		ret = NL80211_RATE_INFO_HE_RU_ALLOC_996;
 		break;
+	case RU_2X996:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+		break;
 	case RU_26:
 		fallthrough;
 	default:
diff --git a/drivers/net/wireless/ath/ath12k/hal_tx.h b/drivers/net/wireless/ath/ath12k/hal_tx.h
index 3cf5973771d78..eb065a79f6c64 100644
--- a/drivers/net/wireless/ath/ath12k/hal_tx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_tx.h
@@ -1,7 +1,8 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc.
+ * All rights reserved.
  */
 
 #ifndef ATH12K_HAL_TX_H
@@ -63,7 +64,12 @@ struct hal_tx_status {
 	u8 try_cnt;
 	u8 tid;
 	u16 peer_id;
-	u32 rate_stats;
+	enum hal_tx_rate_stats_pkt_type pkt_type;
+	enum hal_tx_rate_stats_sgi sgi;
+	enum ath12k_supported_bw bw;
+	u8 mcs;
+	u16 tones;
+	u8 ofdma;
 };
 
 #define HAL_TX_PHY_DESC_INFO0_BF_TYPE		GENMASK(17, 16)
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 329c050037219..26c5b02844295 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -338,6 +338,82 @@ static const char *ath12k_mac_phymode_str(enum wmi_phy_mode mode)
 	return "<unknown>";
 }
 
+u16 ath12k_mac_he_convert_tones_to_ru_tones(u16 tones)
+{
+	switch (tones) {
+	case 26:
+		return RU_26;
+	case 52:
+		return RU_52;
+	case 106:
+		return RU_106;
+	case 242:
+		return RU_242;
+	case 484:
+		return RU_484;
+	case 996:
+		return RU_996;
+	case (996 * 2):
+		return RU_2X996;
+	default:
+		return RU_26;
+	}
+}
+
+enum nl80211_eht_gi ath12k_mac_eht_gi_to_nl80211_eht_gi(u8 sgi)
+{
+	switch (sgi) {
+	case RX_MSDU_START_SGI_0_8_US:
+		return NL80211_RATE_INFO_EHT_GI_0_8;
+	case RX_MSDU_START_SGI_1_6_US:
+		return NL80211_RATE_INFO_EHT_GI_1_6;
+	case RX_MSDU_START_SGI_3_2_US:
+		return NL80211_RATE_INFO_EHT_GI_3_2;
+	default:
+		return NL80211_RATE_INFO_EHT_GI_0_8;
+	}
+}
+
+enum nl80211_eht_ru_alloc ath12k_mac_eht_ru_tones_to_nl80211_eht_ru_alloc(u16 ru_tones)
+{
+	switch (ru_tones) {
+	case 26:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_26;
+	case 52:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_52;
+	case (52 + 26):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_52P26;
+	case 106:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_106;
+	case (106 + 26):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_106P26;
+	case 242:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_242;
+	case 484:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_484;
+	case (484 + 242):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_484P242;
+	case 996:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_996;
+	case (996 + 484):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_996P484;
+	case (996 + 484 + 242):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242;
+	case (2 * 996):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_2x996;
+	case (2 * 996 + 484):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484;
+	case (3 * 996):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_3x996;
+	case (3 * 996 + 484):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484;
+	case (4 * 996):
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_4x996;
+	default:
+		return NL80211_RATE_INFO_EHT_RU_ALLOC_26;
+	}
+}
+
 enum rate_info_bw
 ath12k_mac_bw_to_mac80211_bw(enum ath12k_supported_bw bw)
 {
@@ -3120,6 +3196,7 @@ static void ath12k_peer_assoc_prepare(struct ath12k *ar,
 	ath12k_peer_assoc_h_smps(arsta, arg);
 	ath12k_peer_assoc_h_mlo(arsta, arg);
 
+	arsta->peer_nss = arg->peer_nss;
 	/* TODO: amsdu_disable req? */
 }
 
@@ -10057,6 +10134,8 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->txrate.he_gi = arsta->txrate.he_gi;
 		sinfo->txrate.he_dcm = arsta->txrate.he_dcm;
 		sinfo->txrate.he_ru_alloc = arsta->txrate.he_ru_alloc;
+		sinfo->txrate.eht_gi = arsta->txrate.eht_gi;
+		sinfo->txrate.eht_ru_alloc = arsta->txrate.eht_ru_alloc;
 	}
 	sinfo->txrate.flags = arsta->txrate.flags;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index 3594729b63974..1acaf3f68292c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_MAC_H
@@ -108,5 +108,8 @@ int ath12k_mac_vdev_stop(struct ath12k_link_vif *arvif);
 void ath12k_mac_get_any_chanctx_conf_iter(struct ieee80211_hw *hw,
 					  struct ieee80211_chanctx_conf *conf,
 					  void *data);
+u16 ath12k_mac_he_convert_tones_to_ru_tones(u16 tones);
+enum nl80211_eht_ru_alloc ath12k_mac_eht_ru_tones_to_nl80211_eht_ru_alloc(u16 ru_tones);
+enum nl80211_eht_gi ath12k_mac_eht_gi_to_nl80211_eht_gi(u8 sgi);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/rx_desc.h b/drivers/net/wireless/ath/ath12k/rx_desc.h
index 10366bbe99999..777506a67d656 100644
--- a/drivers/net/wireless/ath/ath12k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath12k/rx_desc.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_RX_DESC_H
 #define ATH12K_RX_DESC_H
@@ -1546,5 +1546,6 @@ struct hal_rx_desc {
 #define RU_242 9
 #define RU_484 18
 #define RU_996 37
+#define RU_2X996 74
 
 #endif /* ATH12K_RX_DESC_H */

From 5e73276c814fc1a5a1bce6be743e1a07baa6d4bc Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Wed, 15 Jan 2025 14:35:36 +0800
Subject: [PATCH 0019/2753] wifi: ath12k: report station mode receive rate for
 IEEE 802.11be

Currently, the receive rate of EHT of "iw dev xxx station dump" command
always show an invalid value.

This is because ath12k does not pass information about the rx_status of EHT
to mac80211. So, mac80211 not calculate the receive rate.

To address this issue, add logic for handling rx_status of EHT to the
ath12k_dp_rx_h_rate() function.

After that, "iw dev xxx station dump" show the correct receive rate.
Such as:

Station 00:03:7f:12:03:03 (on wlo1)
        inactive time:  48 ms
        rx bytes:       59226
        rx packets:     320
        tx bytes:       26556
        tx packets:     191
        tx retries:     99
        tx failed:      0
        beacon loss:    0
        beacon rx:      79
        rx drop misc:   68
        signal:         -95 dBm
        beacon signal avg:      -20 dBm
        tx bitrate:     688.2 MBit/s 40MHz EHT-MCS 13 EHT-NSS 2 EHT-GI 0
        tx duration:    0 us
        rx bitrate:     619.5 MBit/s 40MHz EHT-MCS 8 EHT-NSS 3 EHT-GI 0

This patch affects the station mode of WCN7850 and QCN9274.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00214-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219715
Link: https://patch.msgid.link/20250115063537.35797-3-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_rx.c   | 22 ++++++++++++++++++++--
 drivers/net/wireless/ath/ath12k/rx_desc.h |  2 ++
 2 files changed, 22 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index dad35bfd83f62..09e35dd757e06 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/ieee80211.h>
@@ -2392,6 +2392,23 @@ static void ath12k_dp_rx_h_rate(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 		rx_status->he_gi = ath12k_he_gi_to_nl80211_he_gi(sgi);
 		rx_status->bw = ath12k_mac_bw_to_mac80211_bw(bw);
 		break;
+	case RX_MSDU_START_PKT_TYPE_11BE:
+		rx_status->rate_idx = rate_mcs;
+
+		if (rate_mcs > ATH12K_EHT_MCS_MAX) {
+			ath12k_warn(ar->ab,
+				    "Received with invalid mcs in EHT mode %d\n",
+				    rate_mcs);
+			break;
+		}
+
+		rx_status->encoding = RX_ENC_EHT;
+		rx_status->nss = nss;
+		rx_status->eht.gi = ath12k_mac_eht_gi_to_nl80211_eht_gi(sgi);
+		rx_status->bw = ath12k_mac_bw_to_mac80211_bw(bw);
+		break;
+	default:
+		break;
 	}
 }
 
@@ -2486,7 +2503,7 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	spin_unlock_bh(&ab->base_lock);
 
 	ath12k_dbg(ab, ATH12K_DBG_DATA,
-		   "rx skb %p len %u peer %pM %d %s sn %u %s%s%s%s%s%s%s%s%s rate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
+		   "rx skb %p len %u peer %pM %d %s sn %u %s%s%s%s%s%s%s%s%s%s rate_idx %u vht_nss %u freq %u band %u flag 0x%x fcs-err %i mic-err %i amsdu-more %i\n",
 		   msdu,
 		   msdu->len,
 		   peer ? peer->addr : NULL,
@@ -2497,6 +2514,7 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 		   (status->encoding == RX_ENC_HT) ? "ht" : "",
 		   (status->encoding == RX_ENC_VHT) ? "vht" : "",
 		   (status->encoding == RX_ENC_HE) ? "he" : "",
+		   (status->encoding == RX_ENC_EHT) ? "eht" : "",
 		   (status->bw == RATE_INFO_BW_40) ? "40" : "",
 		   (status->bw == RATE_INFO_BW_80) ? "80" : "",
 		   (status->bw == RATE_INFO_BW_160) ? "160" : "",
diff --git a/drivers/net/wireless/ath/ath12k/rx_desc.h b/drivers/net/wireless/ath/ath12k/rx_desc.h
index 777506a67d656..7367935ee68b3 100644
--- a/drivers/net/wireless/ath/ath12k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath12k/rx_desc.h
@@ -637,6 +637,8 @@ enum rx_msdu_start_pkt_type {
 	RX_MSDU_START_PKT_TYPE_11N,
 	RX_MSDU_START_PKT_TYPE_11AC,
 	RX_MSDU_START_PKT_TYPE_11AX,
+	RX_MSDU_START_PKT_TYPE_11BA,
+	RX_MSDU_START_PKT_TYPE_11BE,
 };
 
 enum rx_msdu_start_sgi {

From 79e7b04b5388c13290ae6d64f930b096c2f465c9 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Wed, 15 Jan 2025 14:35:37 +0800
Subject: [PATCH 0020/2753] wifi: ath12k: report station mode signal strength

Currently, the signal strength of "iw dev xxx station dump" always show an
invalid value.

This is because signal strength is only set in ath12k_mgmt_rx_event()
function, and not set for received data packet. So, change to get signal
from firmware and report to mac80211.

After that, "iw dev xxx station dump" show the correct signal strength.
Such as:

Station 00:03:7f:12:03:03 (on wlo1)
        inactive time:  36 ms
        rx bytes:       61571
        rx packets:     336
        tx bytes:       28204
        tx packets:     205
        tx retries:     49
        tx failed:      0
        beacon loss:    0
        beacon rx:      83
        rx drop misc:   66
        signal:         -24 dBm
        beacon signal avg:      -22 dBm

For WCN7850, the firmware supports db2dbm, so not need to add noise floor.
For QCN9274, the firmware not support db2dbm, so need to add noise floor.

This patch affects the station mode of WCN7850 and QCN9274.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00214-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Link: https://patch.msgid.link/20250115063537.35797-4-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h |   3 +
 drivers/net/wireless/ath/ath12k/mac.c  |  59 ++++++++++-
 drivers/net/wireless/ath/ath12k/wmi.c  | 132 +++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h  |  48 +++++++++
 4 files changed, 240 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 95c2ff6a9ae2b..e036f2e00eb7d 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -503,6 +503,7 @@ struct ath12k_link_sta {
 	struct ath12k_wbm_tx_stats *wbm_tx_stats;
 	u32 bw_prev;
 	u32 peer_nss;
+	s8 rssi_beacon;
 
 	/* For now the assoc link will be considered primary */
 	bool is_assoc_link;
@@ -722,6 +723,8 @@ struct ath12k {
 
 	bool nlo_enabled;
 
+	struct completion fw_stats_complete;
+
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;
 	u8 ftm_msgref;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 26c5b02844295..a245eb6293fbc 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -10104,6 +10104,40 @@ static int ath12k_mac_op_get_survey(struct ieee80211_hw *hw, int idx,
 	return 0;
 }
 
+static int ath12k_mac_get_fw_stats(struct ath12k *ar, u32 pdev_id,
+				   u32 vdev_id, u32 stats_id)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	unsigned long time_left;
+	int ret;
+
+	guard(mutex)(&ah->hw_mutex);
+
+	if (ah->state != ATH12K_HW_STATE_ON)
+		return -ENETDOWN;
+
+	reinit_completion(&ar->fw_stats_complete);
+
+	ret = ath12k_wmi_send_stats_request_cmd(ar, stats_id, vdev_id, pdev_id);
+
+	if (ret) {
+		ath12k_warn(ab, "failed to request fw stats: %d\n", ret);
+		return ret;
+	}
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "get fw stat pdev id %d vdev id %d stats id 0x%x\n",
+		   pdev_id, vdev_id, stats_id);
+
+	time_left = wait_for_completion_timeout(&ar->fw_stats_complete, 1 * HZ);
+
+	if (!time_left)
+		ath12k_warn(ab, "time out while waiting for get fw stats\n");
+
+	return ret;
+}
+
 static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 					 struct ieee80211_vif *vif,
 					 struct ieee80211_sta *sta,
@@ -10111,10 +10145,19 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 {
 	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(sta);
 	struct ath12k_link_sta *arsta;
+	struct ath12k *ar;
+	s8 signal;
+	bool db2dbm;
 
 	lockdep_assert_wiphy(hw->wiphy);
 
 	arsta = &ahsta->deflink;
+	ar = ath12k_get_ar_by_vif(hw, vif, arsta->link_id);
+	if (!ar)
+		return;
+
+	db2dbm = test_bit(WMI_TLV_SERVICE_HW_DB2DBM_CONVERSION_SUPPORT,
+			  ar->ab->wmi_ab.svc_map);
 
 	sinfo->rx_duration = arsta->rx_duration;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION);
@@ -10141,8 +10184,18 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
 	/* TODO: Use real NF instead of default one. */
-	sinfo->signal = arsta->rssi_comb + ATH12K_DEFAULT_NOISE_FLOOR;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
+	signal = arsta->rssi_comb;
+
+	if (!signal &&
+	    ahsta->ahvif->vdev_type == WMI_VDEV_TYPE_STA &&
+	    !(ath12k_mac_get_fw_stats(ar, ar->pdev->pdev_id, 0,
+				      WMI_REQUEST_VDEV_STAT)))
+		signal = arsta->rssi_beacon;
+
+	if (signal) {
+		sinfo->signal = db2dbm ? signal : signal + ATH12K_DEFAULT_NOISE_FLOOR;
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
+	}
 }
 
 static int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw,
@@ -11123,6 +11176,8 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 		ath12k_debugfs_register(ar);
 	}
 
+	init_completion(&ar->fw_stats_complete);
+
 	return 0;
 
 err_unregister_hw:
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index a7625a3d1a3a9..57132c269aad8 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -26,6 +26,10 @@ struct ath12k_wmi_svc_ready_parse {
 	bool wmi_svc_bitmap_done;
 };
 
+struct wmi_tlv_fw_stats_parse {
+	const struct wmi_stats_event *ev;
+};
+
 struct ath12k_wmi_dma_ring_caps_parse {
 	struct ath12k_wmi_dma_ring_caps_params *dma_ring_caps;
 	u32 n_dma_ring_caps;
@@ -815,6 +819,39 @@ int ath12k_wmi_mgmt_send(struct ath12k *ar, u32 vdev_id, u32 buf_id,
 	return ret;
 }
 
+int ath12k_wmi_send_stats_request_cmd(struct ath12k *ar, u32 stats_id,
+				      u32 vdev_id, u32 pdev_id)
+{
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct wmi_request_stats_cmd *cmd;
+	struct sk_buff *skb;
+	int ret;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, sizeof(*cmd));
+	if (!skb)
+		return -ENOMEM;
+
+	cmd = (struct wmi_request_stats_cmd *)skb->data;
+	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_REQUEST_STATS_CMD,
+						 sizeof(*cmd));
+
+	cmd->stats_id = cpu_to_le32(stats_id);
+	cmd->vdev_id = cpu_to_le32(vdev_id);
+	cmd->pdev_id = cpu_to_le32(pdev_id);
+
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_REQUEST_STATS_CMDID);
+	if (ret) {
+		ath12k_warn(ar->ab, "failed to send WMI_REQUEST_STATS cmd\n");
+		dev_kfree_skb(skb);
+	}
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+		   "WMI request stats 0x%x vdev id %d pdev id %d\n",
+		   stats_id, vdev_id, pdev_id);
+
+	return ret;
+}
+
 int ath12k_wmi_vdev_create(struct ath12k *ar, u8 *macaddr,
 			   struct ath12k_wmi_vdev_create_arg *args)
 {
@@ -6814,8 +6851,103 @@ static void ath12k_peer_assoc_conf_event(struct ath12k_base *ab, struct sk_buff
 	rcu_read_unlock();
 }
 
+static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
+					      struct wmi_tlv_fw_stats_parse *parse,
+					      const void *ptr,
+					      u16 len)
+{
+	const struct wmi_stats_event *ev = parse->ev;
+	struct ath12k *ar;
+	struct ath12k_link_vif *arvif;
+	struct ieee80211_sta *sta;
+	struct ath12k_sta *ahsta;
+	struct ath12k_link_sta *arsta;
+	int i, ret = 0;
+	const void *data = ptr;
+
+	if (!ev) {
+		ath12k_warn(ab, "failed to fetch update stats ev");
+		return -EPROTO;
+	}
+
+	rcu_read_lock();
+
+	ar = ath12k_mac_get_ar_by_pdev_id(ab, le32_to_cpu(ev->pdev_id));
+	if (!ar) {
+		ath12k_warn(ab, "invalid pdev id %d in update stats event\n",
+			    le32_to_cpu(ev->pdev_id));
+		ret = -EPROTO;
+		goto exit;
+	}
+
+	for (i = 0; i < le32_to_cpu(ev->num_vdev_stats); i++) {
+		const struct wmi_vdev_stats_params *src;
+
+		src = data;
+		if (len < sizeof(*src)) {
+			ret = -EPROTO;
+			goto exit;
+		}
+
+		arvif = ath12k_mac_get_arvif(ar, le32_to_cpu(src->vdev_id));
+		if (arvif) {
+			sta = ieee80211_find_sta_by_ifaddr(ath12k_ar_to_hw(ar),
+							   arvif->bssid,
+							   NULL);
+			if (sta) {
+				ahsta = ath12k_sta_to_ahsta(sta);
+				arsta = &ahsta->deflink;
+				arsta->rssi_beacon = le32_to_cpu(src->beacon_snr);
+				ath12k_dbg(ab, ATH12K_DBG_WMI,
+					   "wmi stats vdev id %d snr %d\n",
+					   src->vdev_id, src->beacon_snr);
+			} else {
+				ath12k_dbg(ab, ATH12K_DBG_WMI,
+					   "not found station bssid %pM for vdev stat\n",
+					   arvif->bssid);
+			}
+		}
+
+		data += sizeof(*src);
+		len -= sizeof(*src);
+	}
+
+	complete(&ar->fw_stats_complete);
+exit:
+	rcu_read_unlock();
+	return ret;
+}
+
+static int ath12k_wmi_tlv_fw_stats_parse(struct ath12k_base *ab,
+					 u16 tag, u16 len,
+					 const void *ptr, void *data)
+{
+	struct wmi_tlv_fw_stats_parse *parse = data;
+	int ret = 0;
+
+	switch (tag) {
+	case WMI_TAG_STATS_EVENT:
+		parse->ev = ptr;
+		break;
+	case WMI_TAG_ARRAY_BYTE:
+		ret = ath12k_wmi_tlv_fw_stats_data_parse(ab, parse, ptr, len);
+		break;
+	default:
+		break;
+	}
+	return ret;
+}
+
 static void ath12k_update_stats_event(struct ath12k_base *ab, struct sk_buff *skb)
 {
+	int ret;
+	struct wmi_tlv_fw_stats_parse parse = {};
+
+	ret = ath12k_wmi_tlv_iter(ab, skb->data, skb->len,
+				  ath12k_wmi_tlv_fw_stats_parse,
+				  &parse);
+	if (ret)
+		ath12k_warn(ab, "failed to parse fw stats %d\n", ret);
 }
 
 /* PDEV_CTL_FAILSAFE_CHECK_EVENT is received from FW when the frequency scanned
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 38aed18b99f42..54ac7ca019fda 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -5649,6 +5649,52 @@ enum wmi_sta_keepalive_method {
 #define WMI_STA_KEEPALIVE_INTERVAL_DEFAULT	30
 #define WMI_STA_KEEPALIVE_INTERVAL_DISABLE	0
 
+struct wmi_stats_event {
+	__le32 stats_id;
+	__le32 num_pdev_stats;
+	__le32 num_vdev_stats;
+	__le32 num_peer_stats;
+	__le32 num_bcnflt_stats;
+	__le32 num_chan_stats;
+	__le32 num_mib_stats;
+	__le32 pdev_id;
+	__le32 num_bcn_stats;
+	__le32 num_peer_extd_stats;
+	__le32 num_peer_extd2_stats;
+} __packed;
+
+enum wmi_stats_id {
+	WMI_REQUEST_VDEV_STAT	= BIT(3),
+};
+
+struct wmi_request_stats_cmd {
+	__le32 tlv_header;
+	__le32 stats_id;
+	__le32 vdev_id;
+	struct ath12k_wmi_mac_addr_params peer_macaddr;
+	__le32 pdev_id;
+} __packed;
+
+#define WLAN_MAX_AC 4
+#define MAX_TX_RATE_VALUES 10
+
+struct wmi_vdev_stats_params {
+	__le32 vdev_id;
+	__le32 beacon_snr;
+	__le32 data_snr;
+	__le32 num_tx_frames[WLAN_MAX_AC];
+	__le32 num_rx_frames;
+	__le32 num_tx_frames_retries[WLAN_MAX_AC];
+	__le32 num_tx_frames_failures[WLAN_MAX_AC];
+	__le32 num_rts_fail;
+	__le32 num_rts_success;
+	__le32 num_rx_err;
+	__le32 num_rx_discard;
+	__le32 num_tx_not_acked;
+	__le32 tx_rate_history[MAX_TX_RATE_VALUES];
+	__le32 beacon_rssi_history[MAX_TX_RATE_VALUES];
+} __packed;
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -5774,6 +5820,8 @@ int ath12k_wmi_set_bios_cmd(struct ath12k_base *ab, u32 param_id,
 			    const u8 *buf, size_t buf_len);
 int ath12k_wmi_set_bios_sar_cmd(struct ath12k_base *ab, const u8 *psar_table);
 int ath12k_wmi_set_bios_geo_cmd(struct ath12k_base *ab, const u8 *pgeo_table);
+int ath12k_wmi_send_stats_request_cmd(struct ath12k *ar, u32 stats_id,
+				      u32 vdev_id, u32 pdev_id);
 __le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len);
 
 static inline u32

From efb24b1f0d29537714dd3cc46fb335ac27855251 Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <quic_miaoqing@quicinc.com>
Date: Thu, 23 Jan 2025 16:49:48 +0800
Subject: [PATCH 0021/2753] wifi: ath11k: fix memory leak in
 ath11k_xxx_remove()

The firmware memory was allocated in ath11k_pci_probe() or
ath11k_ahb_probe(), but not freed in ath11k_xxx_remove() in case
ATH11K_FLAG_QMI_FAIL bit is set. So call ath11k_fw_destroy() to
free the memory.

Found while fixing the same problem in ath12k:
https://lore.kernel.org/linux-wireless/20240314012746.2729101-1-quic_miaoqing@quicinc.com

Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-04546-QCAHSPSWPL_V1_V2_SILICONZ_IOE-1

Signed-off-by: Miaoqing Pan <quic_miaoqing@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250123084948.1124357-1-quic_miaoqing@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/ahb.c  | 4 +++-
 drivers/net/wireless/ath/ath11k/core.c | 3 +--
 drivers/net/wireless/ath/ath11k/fw.c   | 3 ++-
 drivers/net/wireless/ath/ath11k/pci.c  | 3 ++-
 4 files changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
index f2fc04596d481..eedba3766ba24 100644
--- a/drivers/net/wireless/ath/ath11k/ahb.c
+++ b/drivers/net/wireless/ath/ath11k/ahb.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -1290,6 +1290,7 @@ static void ath11k_ahb_remove(struct platform_device *pdev)
 	ath11k_core_deinit(ab);
 
 qmi_fail:
+	ath11k_fw_destroy(ab);
 	ath11k_ahb_free_resources(ab);
 }
 
@@ -1309,6 +1310,7 @@ static void ath11k_ahb_shutdown(struct platform_device *pdev)
 	ath11k_core_deinit(ab);
 
 free_resources:
+	ath11k_fw_destroy(ab);
 	ath11k_ahb_free_resources(ab);
 }
 
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index c576bbba52bf1..85077247b0251 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -2346,7 +2346,6 @@ void ath11k_core_deinit(struct ath11k_base *ab)
 	ath11k_hif_power_down(ab);
 	ath11k_mac_destroy(ab);
 	ath11k_core_soc_destroy(ab);
-	ath11k_fw_destroy(ab);
 }
 EXPORT_SYMBOL(ath11k_core_deinit);
 
diff --git a/drivers/net/wireless/ath/ath11k/fw.c b/drivers/net/wireless/ath/ath11k/fw.c
index 4e36292a79db8..cbbd8e57119f2 100644
--- a/drivers/net/wireless/ath/ath11k/fw.c
+++ b/drivers/net/wireless/ath/ath11k/fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
- * Copyright (c) 2022-2023, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -166,3 +166,4 @@ void ath11k_fw_destroy(struct ath11k_base *ab)
 {
 	release_firmware(ab->fw.fw);
 }
+EXPORT_SYMBOL(ath11k_fw_destroy);
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index b93f04973ad79..f1121e3317194 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2020 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/module.h>
@@ -984,6 +984,7 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
 	ath11k_core_deinit(ab);
 
 qmi_fail:
+	ath11k_fw_destroy(ab);
 	ath11k_mhi_unregister(ab_pci);
 
 	ath11k_pcic_free_irq(ab);

From 07c34cad10ab0ac8b06ede8a7fbc55ecf2efa3e6 Mon Sep 17 00:00:00 2001
From: Sathishkumar Muruganandam <quic_murugana@quicinc.com>
Date: Tue, 7 Jan 2025 09:31:39 +0530
Subject: [PATCH 0022/2753] wifi: ath12k: encode max Tx power in scan channel
 list command

Currently, when sending the scan channel list command to the firmware, the
maximum Tx power is not encoded in the reg2 member. This omission causes
the firmware to be unaware of the host's maximum Tx power, leading to
incorrect Tx power derivation at firmware level.

To resolve this issue, encode the maximum Tx power in the scan channel list
command before sending it to firmware.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: d889913205cf ("wifi: ath12k: driver for Qualcomm Wi-Fi 7 devices")
Signed-off-by: Sathishkumar Muruganandam <quic_murugana@quicinc.com>
Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250107-add_max_reg_pwr_in_scan_ch_list_cmd-v1-1-70d9963a21e4@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 57132c269aad8..c7d128d41a922 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -2832,6 +2832,8 @@ int ath12k_wmi_send_scan_chan_list_cmd(struct ath12k *ar,
 						  WMI_CHAN_REG_INFO1_REG_CLS);
 			*reg2 |= le32_encode_bits(channel_arg->antennamax,
 						  WMI_CHAN_REG_INFO2_ANT_MAX);
+			*reg2 |= le32_encode_bits(channel_arg->maxregpower,
+						  WMI_CHAN_REG_INFO2_MAX_TX_PWR);
 
 			ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
 				   "WMI chan scan list chan[%d] = %u, chan_info->info %8x\n",

From 1b24394ed5c8a8d8f7b9e3aa9044c31495d46f2e Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <quic_miaoqing@quicinc.com>
Date: Thu, 23 Jan 2025 16:02:26 +0800
Subject: [PATCH 0023/2753] wifi: ath12k: fix memory leak in
 ath12k_pci_remove()

Kmemleak reported this error:

  unreferenced object 0xffff1c165cec3060 (size 32):
    comm "insmod", pid 560, jiffies 4296964570 (age 235.596s)
    backtrace:
      [<000000005434db68>] __kmem_cache_alloc_node+0x1f4/0x2c0
      [<000000001203b155>] kmalloc_trace+0x40/0x88
      [<0000000028adc9c8>] _request_firmware+0xb8/0x608
      [<00000000cad1aef7>] firmware_request_nowarn+0x50/0x80
      [<000000005011a682>] local_pci_probe+0x48/0xd0
      [<00000000077cd295>] pci_device_probe+0xb4/0x200
      [<0000000087184c94>] really_probe+0x150/0x2c0

The firmware memory was allocated in ath12k_pci_probe(), but not
freed in ath12k_pci_remove() in case ATH12K_FLAG_QMI_FAIL bit is
set. So call ath12k_fw_unmap() to free the memory.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.2.0-02280-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1

Signed-off-by: Miaoqing Pan <quic_miaoqing@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250123080226.1116479-1-quic_miaoqing@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 4a50d7118b3ea..6c6a3cabab326 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1735,9 +1735,9 @@ static void ath12k_pci_remove(struct pci_dev *pdev)
 	cancel_work_sync(&ab->reset_work);
 	cancel_work_sync(&ab->dump_work);
 	ath12k_core_deinit(ab);
-	ath12k_fw_unmap(ab);
 
 qmi_fail:
+	ath12k_fw_unmap(ab);
 	ath12k_mhi_unregister(ab_pci);
 
 	ath12k_pci_free_irq(ab);

From e367c924768b11d28727efbf2a6426c7aef66f0f Mon Sep 17 00:00:00 2001
From: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Date: Sat, 25 Jan 2025 00:23:28 +0530
Subject: [PATCH 0024/2753] wifi: ath12k: Request vdev stats from firmware

Add support to request and print vdev stats from firmware through WMI.

Sample output:
-------------
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/fw_stats/vdev_stats

             ath12k VDEV stats
             =================

                       VDEV ID 0
              VDEV MAC address 00:03:7f:6c:9c:1a
                    beacon snr 96
                      data snr 255
                 num rx frames 0
                  num rts fail 0
               num rts success 0
                    num rx err 0
                num rx discard 0
              num tx not acked 0
            num tx frames [00] 0
            num tx frames [01] 0
            num tx frames [02] 0
            num tx frames [03] 2
    num tx frames retries [00] 0
    num tx frames retries [01] 0
    num tx frames retries [02] 0
    num tx frames retries [03] 0
   num tx frames failures [00] 0
   num tx frames failures [01] 0
   num tx frames failures [02] 0
   num tx frames failures [03] 0
          tx rate history [00] 0x00000000
          tx rate history [01] 0x00000000
          tx rate history [02] 0x00000000
          tx rate history [03] 0x00000000
          tx rate history [04] 0x00000000
          tx rate history [05] 0x00000000
          tx rate history [06] 0x00000000
          tx rate history [07] 0x00000000
          tx rate history [08] 0x00000000
          tx rate history [09] 0x00000000
      beacon rssi history [00] 0
      beacon rssi history [01] 0
      beacon rssi history [02] 0
      beacon rssi history [03] 0
      beacon rssi history [04] 0
      beacon rssi history [05] 0
      beacon rssi history [06] 0
      beacon rssi history [07] 0
      beacon rssi history [08] 0
      beacon rssi history [09] 0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124185330.1244585-2-ramya.gnanasekar@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h    |  21 +++
 drivers/net/wireless/ath/ath12k/debugfs.c | 197 +++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/debugfs.h |  13 +-
 drivers/net/wireless/ath/ath12k/wmi.c     | 155 +++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h     |  10 ++
 5 files changed, 394 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index e036f2e00eb7d..97939ddb3cd7c 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -557,6 +557,7 @@ struct ath12k_fw_stats {
 	struct list_head pdevs;
 	struct list_head vdevs;
 	struct list_head bcn;
+	bool fw_stats_done;
 };
 
 struct ath12k_dbg_htt_stats {
@@ -728,6 +729,7 @@ struct ath12k {
 	struct completion mlo_setup_done;
 	u32 mlo_setup_status;
 	u8 ftm_msgref;
+	struct ath12k_fw_stats fw_stats;
 };
 
 struct ath12k_hw {
@@ -1078,6 +1080,25 @@ struct ath12k_pdev_map {
 	u8 pdev_idx;
 };
 
+struct ath12k_fw_stats_vdev {
+	struct list_head list;
+
+	u32 vdev_id;
+	u32 beacon_snr;
+	u32 data_snr;
+	u32 num_tx_frames[WLAN_MAX_AC];
+	u32 num_rx_frames;
+	u32 num_tx_frames_retries[WLAN_MAX_AC];
+	u32 num_tx_frames_failures[WLAN_MAX_AC];
+	u32 num_rts_fail;
+	u32 num_rts_success;
+	u32 num_rx_err;
+	u32 num_rx_discard;
+	u32 num_tx_not_acked;
+	u32 tx_rate_history[MAX_TX_RATE_VALUES];
+	u32 beacon_rssi_history[MAX_TX_RATE_VALUES];
+};
+
 int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab);
 int ath12k_core_pre_init(struct ath12k_base *ab);
 int ath12k_core_init(struct ath12k_base *ath12k);
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index d4b32d1a431c0..1ee9a3e00514f 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -1,10 +1,11 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
+#include "debug.h"
 #include "debugfs.h"
 #include "debugfs_htt_stats.h"
 
@@ -68,6 +69,199 @@ void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
 	 */
 }
 
+static void ath12k_fw_stats_vdevs_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_vdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
+void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
+{
+	spin_lock_bh(&ar->data_lock);
+	ar->fw_stats.fw_stats_done = false;
+	ath12k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+	spin_unlock_bh(&ar->data_lock);
+}
+
+static int ath12k_debugfs_fw_stats_request(struct ath12k *ar,
+					   struct ath12k_fw_stats_req_params *param)
+{
+	struct ath12k_base *ab = ar->ab;
+	unsigned long timeout, time_left;
+	int ret;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	/* FW stats can get split when exceeding the stats data buffer limit.
+	 * In that case, since there is no end marking for the back-to-back
+	 * received 'update stats' event, we keep a 3 seconds timeout in case,
+	 * fw_stats_done is not marked yet
+	 */
+	timeout = jiffies + msecs_to_jiffies(3 * 1000);
+
+	ath12k_debugfs_fw_stats_reset(ar);
+
+	reinit_completion(&ar->fw_stats_complete);
+
+	ret = ath12k_wmi_send_stats_request_cmd(ar, param->stats_id,
+						param->vdev_id, param->pdev_id);
+
+	if (ret) {
+		ath12k_warn(ab, "could not request fw stats (%d)\n",
+			    ret);
+		return ret;
+	}
+
+	time_left = wait_for_completion_timeout(&ar->fw_stats_complete,
+						1 * HZ);
+	/* If the wait timed out, return -ETIMEDOUT */
+	if (!time_left)
+		return -ETIMEDOUT;
+
+	/* Firmware sends WMI_UPDATE_STATS_EVENTID back-to-back
+	 * when stats data buffer limit is reached. fw_stats_complete
+	 * is completed once host receives first event from firmware, but
+	 * still end might not be marked in the TLV.
+	 * Below loop is to confirm that firmware completed sending all the event
+	 * and fw_stats_done is marked true when end is marked in the TLV
+	 */
+	for (;;) {
+		if (time_after(jiffies, timeout))
+			break;
+
+		spin_lock_bh(&ar->data_lock);
+		if (ar->fw_stats.fw_stats_done) {
+			spin_unlock_bh(&ar->data_lock);
+			break;
+		}
+		spin_unlock_bh(&ar->data_lock);
+	}
+	return 0;
+}
+
+void
+ath12k_debugfs_fw_stats_process(struct ath12k *ar,
+				struct ath12k_fw_stats *stats)
+{
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_pdev *pdev;
+	bool is_end;
+	static unsigned int num_vdev;
+	size_t total_vdevs_started = 0;
+	int i;
+
+	if (stats->stats_id == WMI_REQUEST_VDEV_STAT) {
+		if (list_empty(&stats->vdevs)) {
+			ath12k_warn(ab, "empty vdev stats");
+			return;
+		}
+		/* FW sends all the active VDEV stats irrespective of PDEV,
+		 * hence limit until the count of all VDEVs started
+		 */
+		rcu_read_lock();
+		for (i = 0; i < ab->num_radios; i++) {
+			pdev = rcu_dereference(ab->pdevs_active[i]);
+			if (pdev && pdev->ar)
+				total_vdevs_started += pdev->ar->num_started_vdevs;
+		}
+		rcu_read_unlock();
+
+		is_end = ((++num_vdev) == total_vdevs_started);
+
+		list_splice_tail_init(&stats->vdevs,
+				      &ar->fw_stats.vdevs);
+
+		if (is_end) {
+			ar->fw_stats.fw_stats_done = true;
+			num_vdev = 0;
+		}
+		return;
+	}
+}
+
+static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
+{
+	struct ath12k *ar = inode->i_private;
+	struct ath12k_fw_stats_req_params param;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	int ret;
+
+	guard(wiphy)(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (!ah)
+		return -ENETDOWN;
+
+	if (ah->state != ATH12K_HW_STATE_ON)
+		return -ENETDOWN;
+
+	void *buf __free(kfree) = kzalloc(ATH12K_FW_STATS_BUF_SIZE, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	param.pdev_id = ath12k_mac_get_target_pdev_id(ar);
+	/* VDEV stats is always sent for all active VDEVs from FW */
+	param.vdev_id = 0;
+	param.stats_id = WMI_REQUEST_VDEV_STAT;
+
+	ret = ath12k_debugfs_fw_stats_request(ar, &param);
+	if (ret) {
+		ath12k_warn(ar->ab, "failed to request fw vdev stats: %d\n", ret);
+		return ret;
+	}
+
+	ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id,
+				 buf);
+
+	file->private_data = no_free_ptr(buf);
+
+	return 0;
+}
+
+static int ath12k_release_vdev_stats(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath12k_read_vdev_stats(struct file *file,
+				      char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_vdev_stats = {
+	.open = ath12k_open_vdev_stats,
+	.release = ath12k_release_vdev_stats,
+	.read = ath12k_read_vdev_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static
+void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
+{
+	struct dentry *fwstats_dir = debugfs_create_dir("fw_stats",
+							ar->debug.debugfs_pdev);
+
+	/* all stats debugfs files created are under "fw_stats" directory
+	 * created per PDEV
+	 */
+	debugfs_create_file("vdev_stats", 0600, fwstats_dir, ar,
+			    &fops_vdev_stats);
+
+	INIT_LIST_HEAD(&ar->fw_stats.vdevs);
+	init_completion(&ar->fw_stats_complete);
+}
+
 void ath12k_debugfs_register(struct ath12k *ar)
 {
 	struct ath12k_base *ab = ar->ab;
@@ -92,6 +286,7 @@ void ath12k_debugfs_register(struct ath12k *ar)
 	}
 
 	ath12k_debugfs_htt_stats_register(ar);
+	ath12k_debugfs_fw_stats_register(ar);
 }
 
 void ath12k_debugfs_unregister(struct ath12k *ar)
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index 8d64ba03aa9ad..1c30745ee4153 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef _ATH12K_DEBUGFS_H_
@@ -12,6 +12,9 @@ void ath12k_debugfs_soc_create(struct ath12k_base *ab);
 void ath12k_debugfs_soc_destroy(struct ath12k_base *ab);
 void ath12k_debugfs_register(struct ath12k *ar);
 void ath12k_debugfs_unregister(struct ath12k *ar);
+void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
+				     struct ath12k_fw_stats *stats);
+void ath12k_debugfs_fw_stats_reset(struct ath12k *ar);
 #else
 static inline void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
@@ -29,6 +32,14 @@ static inline void ath12k_debugfs_unregister(struct ath12k *ar)
 {
 }
 
+static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
+						   struct ath12k_fw_stats *stats)
+{
+}
+
+static inline void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
+{
+}
 #endif /* CONFIG_ATH12K_DEBUGFS */
 
 #endif /* _ATH12K_DEBUGFS_H_ */
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index c7d128d41a922..8ffb215f7aba9 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -15,6 +15,7 @@
 #include <linux/time.h>
 #include <linux/of.h>
 #include "core.h"
+#include "debugfs.h"
 #include "debug.h"
 #include "mac.h"
 #include "hw.h"
@@ -6853,12 +6854,156 @@ static void ath12k_peer_assoc_conf_event(struct ath12k_base *ab, struct sk_buff
 	rcu_read_unlock();
 }
 
+static void
+ath12k_wmi_fw_vdev_stats_dump(struct ath12k *ar,
+			      struct ath12k_fw_stats *fw_stats,
+			      char *buf, u32 *length)
+{
+	const struct ath12k_fw_stats_vdev *vdev;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+	struct ath12k_link_vif *arvif;
+	u32 len = *length;
+	u8 *vif_macaddr;
+	int i;
+
+	len += scnprintf(buf + len, buf_len - len, "\n");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n",
+			 "ath12k VDEV stats");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+			 "=================");
+
+	list_for_each_entry(vdev, &fw_stats->vdevs, list) {
+		arvif = ath12k_mac_get_arvif(ar, vdev->vdev_id);
+		if (!arvif)
+			continue;
+		vif_macaddr = arvif->ahvif->vif->addr;
+
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "VDEV ID", vdev->vdev_id);
+		len += scnprintf(buf + len, buf_len - len, "%30s %pM\n",
+				 "VDEV MAC address", vif_macaddr);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "beacon snr", vdev->beacon_snr);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "data snr", vdev->data_snr);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num rx frames", vdev->num_rx_frames);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num rts fail", vdev->num_rts_fail);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num rts success", vdev->num_rts_success);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num rx err", vdev->num_rx_err);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num rx discard", vdev->num_rx_discard);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "num tx not acked", vdev->num_tx_not_acked);
+
+		for (i = 0 ; i < WLAN_MAX_AC; i++)
+			len += scnprintf(buf + len, buf_len - len,
+					"%25s [%02d] %u\n",
+					"num tx frames", i,
+					vdev->num_tx_frames[i]);
+
+		for (i = 0 ; i < WLAN_MAX_AC; i++)
+			len += scnprintf(buf + len, buf_len - len,
+					"%25s [%02d] %u\n",
+					"num tx frames retries", i,
+					vdev->num_tx_frames_retries[i]);
+
+		for (i = 0 ; i < WLAN_MAX_AC; i++)
+			len += scnprintf(buf + len, buf_len - len,
+					"%25s [%02d] %u\n",
+					"num tx frames failures", i,
+					vdev->num_tx_frames_failures[i]);
+
+		for (i = 0 ; i < MAX_TX_RATE_VALUES; i++)
+			len += scnprintf(buf + len, buf_len - len,
+					"%25s [%02d] 0x%08x\n",
+					"tx rate history", i,
+					vdev->tx_rate_history[i]);
+		for (i = 0 ; i < MAX_TX_RATE_VALUES; i++)
+			len += scnprintf(buf + len, buf_len - len,
+					"%25s [%02d] %u\n",
+					"beacon rssi history", i,
+					vdev->beacon_rssi_history[i]);
+
+		len += scnprintf(buf + len, buf_len - len, "\n");
+		*length = len;
+	}
+}
+
+void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
+			      struct ath12k_fw_stats *fw_stats,
+			      u32 stats_id, char *buf)
+{
+	u32 len = 0;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+
+	spin_lock_bh(&ar->data_lock);
+
+	switch (stats_id) {
+	case WMI_REQUEST_VDEV_STAT:
+		ath12k_wmi_fw_vdev_stats_dump(ar, fw_stats, buf, &len);
+		break;
+	default:
+		break;
+	}
+
+	spin_unlock_bh(&ar->data_lock);
+
+	if (len >= buf_len)
+		buf[len - 1] = 0;
+	else
+		buf[len] = 0;
+
+	ath12k_debugfs_fw_stats_reset(ar);
+}
+
+static void
+ath12k_wmi_pull_vdev_stats(const struct wmi_vdev_stats_params *src,
+			   struct ath12k_fw_stats_vdev *dst)
+{
+	int i;
+
+	dst->vdev_id = le32_to_cpu(src->vdev_id);
+	dst->beacon_snr = le32_to_cpu(src->beacon_snr);
+	dst->data_snr = le32_to_cpu(src->data_snr);
+	dst->num_rx_frames = le32_to_cpu(src->num_rx_frames);
+	dst->num_rts_fail = le32_to_cpu(src->num_rts_fail);
+	dst->num_rts_success = le32_to_cpu(src->num_rts_success);
+	dst->num_rx_err = le32_to_cpu(src->num_rx_err);
+	dst->num_rx_discard = le32_to_cpu(src->num_rx_discard);
+	dst->num_tx_not_acked = le32_to_cpu(src->num_tx_not_acked);
+
+	for (i = 0; i < WLAN_MAX_AC; i++)
+		dst->num_tx_frames[i] =
+			le32_to_cpu(src->num_tx_frames[i]);
+
+	for (i = 0; i < WLAN_MAX_AC; i++)
+		dst->num_tx_frames_retries[i] =
+			le32_to_cpu(src->num_tx_frames_retries[i]);
+
+	for (i = 0; i < WLAN_MAX_AC; i++)
+		dst->num_tx_frames_failures[i] =
+			le32_to_cpu(src->num_tx_frames_failures[i]);
+
+	for (i = 0; i < MAX_TX_RATE_VALUES; i++)
+		dst->tx_rate_history[i] =
+			le32_to_cpu(src->tx_rate_history[i]);
+
+	for (i = 0; i < MAX_TX_RATE_VALUES; i++)
+		dst->beacon_rssi_history[i] =
+			le32_to_cpu(src->beacon_rssi_history[i]);
+}
+
 static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 					      struct wmi_tlv_fw_stats_parse *parse,
 					      const void *ptr,
 					      u16 len)
 {
 	const struct wmi_stats_event *ev = parse->ev;
+	struct ath12k_fw_stats stats = {0};
 	struct ath12k *ar;
 	struct ath12k_link_vif *arvif;
 	struct ieee80211_sta *sta;
@@ -6867,6 +7012,8 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 	int i, ret = 0;
 	const void *data = ptr;
 
+	INIT_LIST_HEAD(&stats.vdevs);
+
 	if (!ev) {
 		ath12k_warn(ab, "failed to fetch update stats ev");
 		return -EPROTO;
@@ -6884,6 +7031,7 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 
 	for (i = 0; i < le32_to_cpu(ev->num_vdev_stats); i++) {
 		const struct wmi_vdev_stats_params *src;
+		struct ath12k_fw_stats_vdev *dst;
 
 		src = data;
 		if (len < sizeof(*src)) {
@@ -6912,9 +7060,16 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 
 		data += sizeof(*src);
 		len -= sizeof(*src);
+		dst = kzalloc(sizeof(*dst), GFP_ATOMIC);
+		if (!dst)
+			continue;
+		ath12k_wmi_pull_vdev_stats(src, dst);
+		stats.stats_id = WMI_REQUEST_VDEV_STAT;
+		list_add_tail(&dst->list, &stats.vdevs);
 	}
 
 	complete(&ar->fw_stats_complete);
+	ath12k_debugfs_fw_stats_process(ar, &stats);
 exit:
 	rcu_read_unlock();
 	return ret;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 54ac7ca019fda..13644dec50f92 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -25,6 +25,7 @@
 struct ath12k_base;
 struct ath12k;
 struct ath12k_link_vif;
+struct ath12k_fw_stats;
 
 /* There is no signed version of __le32, so for a temporary solution come
  * up with our own version. The idea is from fs/ntfs/endian.h.
@@ -5695,6 +5696,12 @@ struct wmi_vdev_stats_params {
 	__le32 beacon_rssi_history[MAX_TX_RATE_VALUES];
 } __packed;
 
+struct ath12k_fw_stats_req_params {
+	u32 stats_id;
+	u32 vdev_id;
+	u32 pdev_id;
+};
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -5876,5 +5883,8 @@ int ath12k_wmi_sta_keepalive(struct ath12k *ar,
 int ath12k_wmi_mlo_setup(struct ath12k *ar, struct wmi_mlo_setup_arg *mlo_params);
 int ath12k_wmi_mlo_ready(struct ath12k *ar);
 int ath12k_wmi_mlo_teardown(struct ath12k *ar);
+void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
+			      struct ath12k_fw_stats *fw_stats, u32 stats_id,
+			      char *buf);
 
 #endif

From 9fe4669ae9193b27d1d4add9a26c82dca9d59da0 Mon Sep 17 00:00:00 2001
From: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Date: Sat, 25 Jan 2025 00:23:29 +0530
Subject: [PATCH 0025/2753] wifi: ath12k: Request beacon stats from firmware

Add support to request and dump beacon statistics from firmware

Sample output:
-------------
cat /sys/kernel/debug/ath12k/pci-0000:06:00.0/mac0/fw_stats/beacon_stats

           ath12k Beacon stats (1)
           ===================

                       VDEV ID 0
              VDEV MAC address 00:03:7f:04:37:58
              ================

      Num of beacon tx success 20
     Num of beacon tx failures 0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124185330.1244585-3-ramya.gnanasekar@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h    |   8 ++
 drivers/net/wireless/ath/ath12k/debugfs.c | 106 +++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/wmi.c     |  71 +++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h     |   7 ++
 4 files changed, 191 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 97939ddb3cd7c..7159343113d6a 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1099,6 +1099,14 @@ struct ath12k_fw_stats_vdev {
 	u32 beacon_rssi_history[MAX_TX_RATE_VALUES];
 };
 
+struct ath12k_fw_stats_bcn {
+	struct list_head list;
+
+	u32 vdev_id;
+	u32 tx_bcn_succ_cnt;
+	u32 tx_bcn_outage_cnt;
+};
+
 int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab);
 int ath12k_core_pre_init(struct ath12k_base *ab);
 int ath12k_core_init(struct ath12k_base *ath12k);
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index 1ee9a3e00514f..3cb2bb9fa4240 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -69,6 +69,16 @@ void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
 	 */
 }
 
+static void ath12k_fw_stats_bcn_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_bcn *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
 static void ath12k_fw_stats_vdevs_free(struct list_head *head)
 {
 	struct ath12k_fw_stats_vdev *i, *tmp;
@@ -84,6 +94,7 @@ void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
 	spin_lock_bh(&ar->data_lock);
 	ar->fw_stats.fw_stats_done = false;
 	ath12k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
+	ath12k_fw_stats_bcn_free(&ar->fw_stats.bcn);
 	spin_unlock_bh(&ar->data_lock);
 }
 
@@ -150,7 +161,7 @@ ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_pdev *pdev;
 	bool is_end;
-	static unsigned int num_vdev;
+	static unsigned int num_vdev, num_bcn;
 	size_t total_vdevs_started = 0;
 	int i;
 
@@ -181,6 +192,24 @@ ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 		}
 		return;
 	}
+	if (stats->stats_id == WMI_REQUEST_BCN_STAT) {
+		if (list_empty(&stats->bcn)) {
+			ath12k_warn(ab, "empty beacon stats");
+			return;
+		}
+		/* Mark end until we reached the count of all started VDEVs
+		 * within the PDEV
+		 */
+		is_end = ((++num_bcn) == ar->num_started_vdevs);
+
+		list_splice_tail_init(&stats->bcn,
+				      &ar->fw_stats.bcn);
+
+		if (is_end) {
+			ar->fw_stats.fw_stats_done = true;
+			num_bcn = 0;
+		}
+	}
 }
 
 static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
@@ -246,6 +275,78 @@ static const struct file_operations fops_vdev_stats = {
 	.llseek = default_llseek,
 };
 
+static int ath12k_open_bcn_stats(struct inode *inode, struct file *file)
+{
+	struct ath12k *ar = inode->i_private;
+	struct ath12k_link_vif *arvif;
+	struct ath12k_fw_stats_req_params param;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	int ret;
+
+	guard(wiphy)(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (ah && ah->state != ATH12K_HW_STATE_ON)
+		return -ENETDOWN;
+
+	void *buf __free(kfree) = kzalloc(ATH12K_FW_STATS_BUF_SIZE, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	param.pdev_id = ath12k_mac_get_target_pdev_id(ar);
+	param.stats_id = WMI_REQUEST_BCN_STAT;
+
+	/* loop all active VDEVs for bcn stats */
+	list_for_each_entry(arvif, &ar->arvifs, list) {
+		if (!arvif->is_up)
+			continue;
+
+		param.vdev_id = arvif->vdev_id;
+		ret = ath12k_debugfs_fw_stats_request(ar, &param);
+		if (ret) {
+			ath12k_warn(ar->ab, "failed to request fw bcn stats: %d\n", ret);
+			return ret;
+		}
+	}
+
+	ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id,
+				 buf);
+	/* since beacon stats request is looped for all active VDEVs, saved fw
+	 * stats is not freed for each request until done for all active VDEVs
+	 */
+	spin_lock_bh(&ar->data_lock);
+	ath12k_fw_stats_bcn_free(&ar->fw_stats.bcn);
+	spin_unlock_bh(&ar->data_lock);
+
+	file->private_data = no_free_ptr(buf);
+
+	return 0;
+}
+
+static int ath12k_release_bcn_stats(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath12k_read_bcn_stats(struct file *file,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_bcn_stats = {
+	.open = ath12k_open_bcn_stats,
+	.release = ath12k_release_bcn_stats,
+	.read = ath12k_read_bcn_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 static
 void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
 {
@@ -257,8 +358,11 @@ void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
 	 */
 	debugfs_create_file("vdev_stats", 0600, fwstats_dir, ar,
 			    &fops_vdev_stats);
+	debugfs_create_file("beacon_stats", 0600, fwstats_dir, ar,
+			    &fops_bcn_stats);
 
 	INIT_LIST_HEAD(&ar->fw_stats.vdevs);
+	INIT_LIST_HEAD(&ar->fw_stats.bcn);
 	init_completion(&ar->fw_stats_complete);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 8ffb215f7aba9..c9a448492bf12 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -6933,6 +6933,45 @@ ath12k_wmi_fw_vdev_stats_dump(struct ath12k *ar,
 	}
 }
 
+static void
+ath12k_wmi_fw_bcn_stats_dump(struct ath12k *ar,
+			     struct ath12k_fw_stats *fw_stats,
+			     char *buf, u32 *length)
+{
+	const struct ath12k_fw_stats_bcn *bcn;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+	struct ath12k_link_vif *arvif;
+	u32 len = *length;
+	size_t num_bcn;
+
+	num_bcn = list_count_nodes(&fw_stats->bcn);
+
+	len += scnprintf(buf + len, buf_len - len, "\n");
+	len += scnprintf(buf + len, buf_len - len, "%30s (%zu)\n",
+			 "ath12k Beacon stats", num_bcn);
+	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+			 "===================");
+
+	list_for_each_entry(bcn, &fw_stats->bcn, list) {
+		arvif = ath12k_mac_get_arvif(ar, bcn->vdev_id);
+		if (!arvif)
+			continue;
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "VDEV ID", bcn->vdev_id);
+		len += scnprintf(buf + len, buf_len - len, "%30s %pM\n",
+				 "VDEV MAC address", arvif->ahvif->vif->addr);
+		len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+				 "================");
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "Num of beacon tx success", bcn->tx_bcn_succ_cnt);
+		len += scnprintf(buf + len, buf_len - len, "%30s %u\n",
+				 "Num of beacon tx failures", bcn->tx_bcn_outage_cnt);
+
+		len += scnprintf(buf + len, buf_len - len, "\n");
+		*length = len;
+	}
+}
+
 void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 			      struct ath12k_fw_stats *fw_stats,
 			      u32 stats_id, char *buf)
@@ -6946,6 +6985,9 @@ void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 	case WMI_REQUEST_VDEV_STAT:
 		ath12k_wmi_fw_vdev_stats_dump(ar, fw_stats, buf, &len);
 		break;
+	case WMI_REQUEST_BCN_STAT:
+		ath12k_wmi_fw_bcn_stats_dump(ar, fw_stats, buf, &len);
+		break;
 	default:
 		break;
 	}
@@ -6997,6 +7039,15 @@ ath12k_wmi_pull_vdev_stats(const struct wmi_vdev_stats_params *src,
 			le32_to_cpu(src->beacon_rssi_history[i]);
 }
 
+static void
+ath12k_wmi_pull_bcn_stats(const struct ath12k_wmi_bcn_stats_params *src,
+			  struct ath12k_fw_stats_bcn *dst)
+{
+	dst->vdev_id = le32_to_cpu(src->vdev_id);
+	dst->tx_bcn_succ_cnt = le32_to_cpu(src->tx_bcn_succ_cnt);
+	dst->tx_bcn_outage_cnt = le32_to_cpu(src->tx_bcn_outage_cnt);
+}
+
 static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 					      struct wmi_tlv_fw_stats_parse *parse,
 					      const void *ptr,
@@ -7013,6 +7064,7 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 	const void *data = ptr;
 
 	INIT_LIST_HEAD(&stats.vdevs);
+	INIT_LIST_HEAD(&stats.bcn);
 
 	if (!ev) {
 		ath12k_warn(ab, "failed to fetch update stats ev");
@@ -7067,6 +7119,25 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 		stats.stats_id = WMI_REQUEST_VDEV_STAT;
 		list_add_tail(&dst->list, &stats.vdevs);
 	}
+	for (i = 0; i < le32_to_cpu(ev->num_bcn_stats); i++) {
+		const struct ath12k_wmi_bcn_stats_params *src;
+		struct ath12k_fw_stats_bcn *dst;
+
+		src = data;
+		if (len < sizeof(*src)) {
+			ret = -EPROTO;
+			goto exit;
+		}
+
+		data += sizeof(*src);
+		len -= sizeof(*src);
+		dst = kzalloc(sizeof(*dst), GFP_ATOMIC);
+		if (!dst)
+			continue;
+		ath12k_wmi_pull_bcn_stats(src, dst);
+		stats.stats_id = WMI_REQUEST_BCN_STAT;
+		list_add_tail(&dst->list, &stats.bcn);
+	}
 
 	complete(&ar->fw_stats_complete);
 	ath12k_debugfs_fw_stats_process(ar, &stats);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 13644dec50f92..326e079c46c55 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -5666,6 +5666,7 @@ struct wmi_stats_event {
 
 enum wmi_stats_id {
 	WMI_REQUEST_VDEV_STAT	= BIT(3),
+	WMI_REQUEST_BCN_STAT	= BIT(11),
 };
 
 struct wmi_request_stats_cmd {
@@ -5696,6 +5697,12 @@ struct wmi_vdev_stats_params {
 	__le32 beacon_rssi_history[MAX_TX_RATE_VALUES];
 } __packed;
 
+struct ath12k_wmi_bcn_stats_params {
+	__le32 vdev_id;
+	__le32 tx_bcn_succ_cnt;
+	__le32 tx_bcn_outage_cnt;
+} __packed;
+
 struct ath12k_fw_stats_req_params {
 	u32 stats_id;
 	u32 vdev_id;

From b826ad94d89615e222a3682b02adcbe45ecbde0e Mon Sep 17 00:00:00 2001
From: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Date: Sat, 25 Jan 2025 00:23:30 +0530
Subject: [PATCH 0026/2753] wifi: ath12k: Request pdev stats from firmware

Add support to request pdev stats from firmware through WMI and
print the information

Sample Output:
-------------
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/fw_stats/pdev_stats

             ath12k PDEV stats
             =================

           Channel noise floor        -85
              Channel TX power        126
                TX frame count          0
                RX frame count       8637
                RX clear count      37424
                   Cycle count    4372024
               PHY error count          0
                soc drop count          0

          ath12k PDEV TX stats
          ====================

            HTT cookies queued          0
             HTT cookies disp.          0
                   MSDU queued          0
                   MPDU queued          0
                 MSDUs dropped          0
                  Local enqued          0
                   Local freed          0
                     HW queued          0
                  PPDUs reaped          0
                 Num underruns          0
                 PPDUs cleaned          0
                MPDUs requeued          0
             Excessive retries          0
                       HW rate          0
           Sched self triggers          0
     Dropped due to SW retries          0
       Illegal rate phy errors          0
        PDEV continuous xretry          0
                    TX timeout          9
                   PDEV resets          0
 Stateless TIDs alloc failures          0
                  PHY underrun          0
  MPDU is more than txop limit          0

          ath12k PDEV RX stats
          ====================

         Mid PPDU route change          0
       Tot. number of statuses          0
        Extra frags on rings 0          0
        Extra frags on rings 1          0
        Extra frags on rings 2          0
        Extra frags on rings 3          0
        MSDUs delivered to HTT          0
        MPDUs delivered to HTT          0
      MSDUs delivered to stack          0
      MPDUs delivered to stack          0
               Oversized AMSUs          0
                    PHY errors          0
              PHY errors drops          0
   MPDU errors (FCS, MIC, ENC)          0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Ramya Gnanasekar <ramya.gnanasekar@oss.qualcomm.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124185330.1244585-4-ramya.gnanasekar@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h    |  60 +++++
 drivers/net/wireless/ath/ath12k/debugfs.c |  79 +++++++
 drivers/net/wireless/ath/ath12k/wmi.c     | 256 ++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h     |  60 +++++
 4 files changed, 455 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 7159343113d6a..3d20a6b3b473a 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1107,6 +1107,66 @@ struct ath12k_fw_stats_bcn {
 	u32 tx_bcn_outage_cnt;
 };
 
+struct ath12k_fw_stats_pdev {
+	struct list_head list;
+
+	/* PDEV stats */
+	s32 ch_noise_floor;
+	u32 tx_frame_count;
+	u32 rx_frame_count;
+	u32 rx_clear_count;
+	u32 cycle_count;
+	u32 phy_err_count;
+	u32 chan_tx_power;
+	u32 ack_rx_bad;
+	u32 rts_bad;
+	u32 rts_good;
+	u32 fcs_bad;
+	u32 no_beacons;
+	u32 mib_int_count;
+
+	/* PDEV TX stats */
+	s32 comp_queued;
+	s32 comp_delivered;
+	s32 msdu_enqued;
+	s32 mpdu_enqued;
+	s32 wmm_drop;
+	s32 local_enqued;
+	s32 local_freed;
+	s32 hw_queued;
+	s32 hw_reaped;
+	s32 underrun;
+	s32 tx_abort;
+	s32 mpdus_requed;
+	u32 tx_ko;
+	u32 data_rc;
+	u32 self_triggers;
+	u32 sw_retry_failure;
+	u32 illgl_rate_phy_err;
+	u32 pdev_cont_xretry;
+	u32 pdev_tx_timeout;
+	u32 pdev_resets;
+	u32 stateless_tid_alloc_failure;
+	u32 phy_underrun;
+	u32 txop_ovf;
+
+	/* PDEV RX stats */
+	s32 mid_ppdu_route_change;
+	s32 status_rcvd;
+	s32 r0_frags;
+	s32 r1_frags;
+	s32 r2_frags;
+	s32 r3_frags;
+	s32 htt_msdus;
+	s32 htt_mpdus;
+	s32 loc_msdus;
+	s32 loc_mpdus;
+	s32 oversize_amsdu;
+	s32 phy_errs;
+	s32 phy_err_drop;
+	s32 mpdu_errs;
+};
+
 int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab);
 int ath12k_core_pre_init(struct ath12k_base *ab);
 int ath12k_core_init(struct ath12k_base *ath12k);
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index 3cb2bb9fa4240..6d6708486d142 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -69,6 +69,16 @@ void ath12k_debugfs_soc_destroy(struct ath12k_base *ab)
 	 */
 }
 
+static void ath12k_fw_stats_pdevs_free(struct list_head *head)
+{
+	struct ath12k_fw_stats_pdev *i, *tmp;
+
+	list_for_each_entry_safe(i, tmp, head, list) {
+		list_del(&i->list);
+		kfree(i);
+	}
+}
+
 static void ath12k_fw_stats_bcn_free(struct list_head *head)
 {
 	struct ath12k_fw_stats_bcn *i, *tmp;
@@ -95,6 +105,7 @@ void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
 	ar->fw_stats.fw_stats_done = false;
 	ath12k_fw_stats_vdevs_free(&ar->fw_stats.vdevs);
 	ath12k_fw_stats_bcn_free(&ar->fw_stats.bcn);
+	ath12k_fw_stats_pdevs_free(&ar->fw_stats.pdevs);
 	spin_unlock_bh(&ar->data_lock);
 }
 
@@ -210,6 +221,10 @@ ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 			num_bcn = 0;
 		}
 	}
+	if (stats->stats_id == WMI_REQUEST_PDEV_STAT) {
+		list_splice_tail_init(&stats->pdevs, &ar->fw_stats.pdevs);
+		ar->fw_stats.fw_stats_done = true;
+	}
 }
 
 static int ath12k_open_vdev_stats(struct inode *inode, struct file *file)
@@ -347,6 +362,66 @@ static const struct file_operations fops_bcn_stats = {
 	.llseek = default_llseek,
 };
 
+static int ath12k_open_pdev_stats(struct inode *inode, struct file *file)
+{
+	struct ath12k *ar = inode->i_private;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	struct ath12k_base *ab = ar->ab;
+	struct ath12k_fw_stats_req_params param;
+	int ret;
+
+	guard(wiphy)(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (ah && ah->state != ATH12K_HW_STATE_ON)
+		return -ENETDOWN;
+
+	void *buf __free(kfree) = kzalloc(ATH12K_FW_STATS_BUF_SIZE, GFP_ATOMIC);
+	if (!buf)
+		return -ENOMEM;
+
+	param.pdev_id = ath12k_mac_get_target_pdev_id(ar);
+	param.vdev_id = 0;
+	param.stats_id = WMI_REQUEST_PDEV_STAT;
+
+	ret = ath12k_debugfs_fw_stats_request(ar, &param);
+	if (ret) {
+		ath12k_warn(ab, "failed to request fw pdev stats: %d\n", ret);
+		return ret;
+	}
+
+	ath12k_wmi_fw_stats_dump(ar, &ar->fw_stats, param.stats_id,
+				 buf);
+
+	file->private_data = no_free_ptr(buf);
+
+	return 0;
+}
+
+static int ath12k_release_pdev_stats(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+
+	return 0;
+}
+
+static ssize_t ath12k_read_pdev_stats(struct file *file,
+				      char __user *user_buf,
+				      size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_pdev_stats = {
+	.open = ath12k_open_pdev_stats,
+	.release = ath12k_release_pdev_stats,
+	.read = ath12k_read_pdev_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 static
 void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
 {
@@ -360,9 +435,13 @@ void ath12k_debugfs_fw_stats_register(struct ath12k *ar)
 			    &fops_vdev_stats);
 	debugfs_create_file("beacon_stats", 0600, fwstats_dir, ar,
 			    &fops_bcn_stats);
+	debugfs_create_file("pdev_stats", 0600, fwstats_dir, ar,
+			    &fops_pdev_stats);
 
 	INIT_LIST_HEAD(&ar->fw_stats.vdevs);
 	INIT_LIST_HEAD(&ar->fw_stats.bcn);
+	INIT_LIST_HEAD(&ar->fw_stats.pdevs);
+
 	init_completion(&ar->fw_stats_complete);
 }
 
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index c9a448492bf12..ad29c4c99dc78 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -6972,6 +6972,170 @@ ath12k_wmi_fw_bcn_stats_dump(struct ath12k *ar,
 	}
 }
 
+static void
+ath12k_wmi_fw_pdev_base_stats_dump(const struct ath12k_fw_stats_pdev *pdev,
+				   char *buf, u32 *length, u64 fw_soc_drop_cnt)
+{
+	u32 len = *length;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+
+	len = scnprintf(buf + len, buf_len - len, "\n");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n",
+			"ath12k PDEV stats");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+			"=================");
+
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			"Channel noise floor", pdev->ch_noise_floor);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"Channel TX power", pdev->chan_tx_power);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"TX frame count", pdev->tx_frame_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"RX frame count", pdev->rx_frame_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"RX clear count", pdev->rx_clear_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"Cycle count", pdev->cycle_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			"PHY error count", pdev->phy_err_count);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10llu\n",
+			"soc drop count", fw_soc_drop_cnt);
+
+	*length = len;
+}
+
+static void
+ath12k_wmi_fw_pdev_tx_stats_dump(const struct ath12k_fw_stats_pdev *pdev,
+				 char *buf, u32 *length)
+{
+	u32 len = *length;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+
+	len += scnprintf(buf + len, buf_len - len, "\n%30s\n",
+			 "ath12k PDEV TX stats");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+			 "====================");
+
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "HTT cookies queued", pdev->comp_queued);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "HTT cookies disp.", pdev->comp_delivered);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MSDU queued", pdev->msdu_enqued);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MPDU queued", pdev->mpdu_enqued);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MSDUs dropped", pdev->wmm_drop);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Local enqued", pdev->local_enqued);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Local freed", pdev->local_freed);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "HW queued", pdev->hw_queued);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "PPDUs reaped", pdev->hw_reaped);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Num underruns", pdev->underrun);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "PPDUs cleaned", pdev->tx_abort);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MPDUs requeued", pdev->mpdus_requed);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "Excessive retries", pdev->tx_ko);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "HW rate", pdev->data_rc);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "Sched self triggers", pdev->self_triggers);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "Dropped due to SW retries",
+			 pdev->sw_retry_failure);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "Illegal rate phy errors",
+			 pdev->illgl_rate_phy_err);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "PDEV continuous xretry", pdev->pdev_cont_xretry);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "TX timeout", pdev->pdev_tx_timeout);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "PDEV resets", pdev->pdev_resets);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "Stateless TIDs alloc failures",
+			 pdev->stateless_tid_alloc_failure);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "PHY underrun", pdev->phy_underrun);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10u\n",
+			 "MPDU is more than txop limit", pdev->txop_ovf);
+	*length = len;
+}
+
+static void
+ath12k_wmi_fw_pdev_rx_stats_dump(const struct ath12k_fw_stats_pdev *pdev,
+				 char *buf, u32 *length)
+{
+	u32 len = *length;
+	u32 buf_len = ATH12K_FW_STATS_BUF_SIZE;
+
+	len += scnprintf(buf + len, buf_len - len, "\n%30s\n",
+			 "ath12k PDEV RX stats");
+	len += scnprintf(buf + len, buf_len - len, "%30s\n\n",
+			 "====================");
+
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Mid PPDU route change",
+			 pdev->mid_ppdu_route_change);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Tot. number of statuses", pdev->status_rcvd);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Extra frags on rings 0", pdev->r0_frags);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Extra frags on rings 1", pdev->r1_frags);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Extra frags on rings 2", pdev->r2_frags);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Extra frags on rings 3", pdev->r3_frags);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MSDUs delivered to HTT", pdev->htt_msdus);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MPDUs delivered to HTT", pdev->htt_mpdus);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MSDUs delivered to stack", pdev->loc_msdus);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MPDUs delivered to stack", pdev->loc_mpdus);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "Oversized AMSUs", pdev->oversize_amsdu);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "PHY errors", pdev->phy_errs);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "PHY errors drops", pdev->phy_err_drop);
+	len += scnprintf(buf + len, buf_len - len, "%30s %10d\n",
+			 "MPDU errors (FCS, MIC, ENC)", pdev->mpdu_errs);
+	*length = len;
+}
+
+static void
+ath12k_wmi_fw_pdev_stats_dump(struct ath12k *ar,
+			      struct ath12k_fw_stats *fw_stats,
+			      char *buf, u32 *length)
+{
+	const struct ath12k_fw_stats_pdev *pdev;
+	u32 len = *length;
+
+	pdev = list_first_entry_or_null(&fw_stats->pdevs,
+					struct ath12k_fw_stats_pdev, list);
+	if (!pdev) {
+		ath12k_warn(ar->ab, "failed to get pdev stats\n");
+		return;
+	}
+
+	ath12k_wmi_fw_pdev_base_stats_dump(pdev, buf, &len,
+					   ar->ab->fw_soc_drop_count);
+	ath12k_wmi_fw_pdev_tx_stats_dump(pdev, buf, &len);
+	ath12k_wmi_fw_pdev_rx_stats_dump(pdev, buf, &len);
+
+	*length = len;
+}
+
 void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 			      struct ath12k_fw_stats *fw_stats,
 			      u32 stats_id, char *buf)
@@ -6988,6 +7152,9 @@ void ath12k_wmi_fw_stats_dump(struct ath12k *ar,
 	case WMI_REQUEST_BCN_STAT:
 		ath12k_wmi_fw_bcn_stats_dump(ar, fw_stats, buf, &len);
 		break;
+	case WMI_REQUEST_PDEV_STAT:
+		ath12k_wmi_fw_pdev_stats_dump(ar, fw_stats, buf, &len);
+		break;
 	default:
 		break;
 	}
@@ -7048,6 +7215,70 @@ ath12k_wmi_pull_bcn_stats(const struct ath12k_wmi_bcn_stats_params *src,
 	dst->tx_bcn_outage_cnt = le32_to_cpu(src->tx_bcn_outage_cnt);
 }
 
+static void
+ath12k_wmi_pull_pdev_stats_base(const struct ath12k_wmi_pdev_base_stats_params *src,
+				struct ath12k_fw_stats_pdev *dst)
+{
+	dst->ch_noise_floor = a_sle32_to_cpu(src->chan_nf);
+	dst->tx_frame_count = __le32_to_cpu(src->tx_frame_count);
+	dst->rx_frame_count = __le32_to_cpu(src->rx_frame_count);
+	dst->rx_clear_count = __le32_to_cpu(src->rx_clear_count);
+	dst->cycle_count = __le32_to_cpu(src->cycle_count);
+	dst->phy_err_count = __le32_to_cpu(src->phy_err_count);
+	dst->chan_tx_power = __le32_to_cpu(src->chan_tx_pwr);
+}
+
+static void
+ath12k_wmi_pull_pdev_stats_tx(const struct ath12k_wmi_pdev_tx_stats_params *src,
+			      struct ath12k_fw_stats_pdev *dst)
+{
+	dst->comp_queued = a_sle32_to_cpu(src->comp_queued);
+	dst->comp_delivered = a_sle32_to_cpu(src->comp_delivered);
+	dst->msdu_enqued = a_sle32_to_cpu(src->msdu_enqued);
+	dst->mpdu_enqued = a_sle32_to_cpu(src->mpdu_enqued);
+	dst->wmm_drop = a_sle32_to_cpu(src->wmm_drop);
+	dst->local_enqued = a_sle32_to_cpu(src->local_enqued);
+	dst->local_freed = a_sle32_to_cpu(src->local_freed);
+	dst->hw_queued = a_sle32_to_cpu(src->hw_queued);
+	dst->hw_reaped = a_sle32_to_cpu(src->hw_reaped);
+	dst->underrun = a_sle32_to_cpu(src->underrun);
+	dst->tx_abort = a_sle32_to_cpu(src->tx_abort);
+	dst->mpdus_requed = a_sle32_to_cpu(src->mpdus_requed);
+	dst->tx_ko = __le32_to_cpu(src->tx_ko);
+	dst->data_rc = __le32_to_cpu(src->data_rc);
+	dst->self_triggers = __le32_to_cpu(src->self_triggers);
+	dst->sw_retry_failure = __le32_to_cpu(src->sw_retry_failure);
+	dst->illgl_rate_phy_err = __le32_to_cpu(src->illgl_rate_phy_err);
+	dst->pdev_cont_xretry = __le32_to_cpu(src->pdev_cont_xretry);
+	dst->pdev_tx_timeout = __le32_to_cpu(src->pdev_tx_timeout);
+	dst->pdev_resets = __le32_to_cpu(src->pdev_resets);
+	dst->stateless_tid_alloc_failure =
+		__le32_to_cpu(src->stateless_tid_alloc_failure);
+	dst->phy_underrun = __le32_to_cpu(src->phy_underrun);
+	dst->txop_ovf = __le32_to_cpu(src->txop_ovf);
+}
+
+static void
+ath12k_wmi_pull_pdev_stats_rx(const struct ath12k_wmi_pdev_rx_stats_params *src,
+			      struct ath12k_fw_stats_pdev *dst)
+{
+	dst->mid_ppdu_route_change =
+		a_sle32_to_cpu(src->mid_ppdu_route_change);
+	dst->status_rcvd = a_sle32_to_cpu(src->status_rcvd);
+	dst->r0_frags = a_sle32_to_cpu(src->r0_frags);
+	dst->r1_frags = a_sle32_to_cpu(src->r1_frags);
+	dst->r2_frags = a_sle32_to_cpu(src->r2_frags);
+	dst->r3_frags = a_sle32_to_cpu(src->r3_frags);
+	dst->htt_msdus = a_sle32_to_cpu(src->htt_msdus);
+	dst->htt_mpdus = a_sle32_to_cpu(src->htt_mpdus);
+	dst->loc_msdus = a_sle32_to_cpu(src->loc_msdus);
+	dst->loc_mpdus = a_sle32_to_cpu(src->loc_mpdus);
+	dst->oversize_amsdu = a_sle32_to_cpu(src->oversize_amsdu);
+	dst->phy_errs = a_sle32_to_cpu(src->phy_errs);
+	dst->phy_err_drop = a_sle32_to_cpu(src->phy_err_drop);
+	dst->mpdu_errs = a_sle32_to_cpu(src->mpdu_errs);
+}
+
 static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 					      struct wmi_tlv_fw_stats_parse *parse,
 					      const void *ptr,
@@ -7065,6 +7296,7 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 
 	INIT_LIST_HEAD(&stats.vdevs);
 	INIT_LIST_HEAD(&stats.bcn);
+	INIT_LIST_HEAD(&stats.pdevs);
 
 	if (!ev) {
 		ath12k_warn(ab, "failed to fetch update stats ev");
@@ -7138,6 +7370,30 @@ static int ath12k_wmi_tlv_fw_stats_data_parse(struct ath12k_base *ab,
 		stats.stats_id = WMI_REQUEST_BCN_STAT;
 		list_add_tail(&dst->list, &stats.bcn);
 	}
+	for (i = 0; i < le32_to_cpu(ev->num_pdev_stats); i++) {
+		const struct ath12k_wmi_pdev_stats_params *src;
+		struct ath12k_fw_stats_pdev *dst;
+
+		src = data;
+		if (len < sizeof(*src)) {
+			ret = -EPROTO;
+			goto exit;
+		}
+
+		stats.stats_id = WMI_REQUEST_PDEV_STAT;
+
+		data += sizeof(*src);
+		len -= sizeof(*src);
+
+		dst = kzalloc(sizeof(*dst), GFP_ATOMIC);
+		if (!dst)
+			continue;
+
+		ath12k_wmi_pull_pdev_stats_base(&src->base, dst);
+		ath12k_wmi_pull_pdev_stats_tx(&src->tx, dst);
+		ath12k_wmi_pull_pdev_stats_rx(&src->rx, dst);
+		list_add_tail(&dst->list, &stats.pdevs);
+	}
 
 	complete(&ar->fw_stats_complete);
 	ath12k_debugfs_fw_stats_process(ar, &stats);
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 326e079c46c55..bd069a81e4c61 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -5665,6 +5665,7 @@ struct wmi_stats_event {
 } __packed;
 
 enum wmi_stats_id {
+	WMI_REQUEST_PDEV_STAT	= BIT(2),
 	WMI_REQUEST_VDEV_STAT	= BIT(3),
 	WMI_REQUEST_BCN_STAT	= BIT(11),
 };
@@ -5703,6 +5704,65 @@ struct ath12k_wmi_bcn_stats_params {
 	__le32 tx_bcn_outage_cnt;
 } __packed;
 
+struct ath12k_wmi_pdev_base_stats_params {
+	a_sle32 chan_nf;
+	__le32 tx_frame_count; /* Cycles spent transmitting frames */
+	__le32 rx_frame_count; /* Cycles spent receiving frames */
+	__le32 rx_clear_count; /* Total channel busy time, evidently */
+	__le32 cycle_count; /* Total on-channel time */
+	__le32 phy_err_count;
+	__le32 chan_tx_pwr;
+} __packed;
+
+struct ath12k_wmi_pdev_tx_stats_params {
+	a_sle32 comp_queued;
+	a_sle32 comp_delivered;
+	a_sle32 msdu_enqued;
+	a_sle32 mpdu_enqued;
+	a_sle32 wmm_drop;
+	a_sle32 local_enqued;
+	a_sle32 local_freed;
+	a_sle32 hw_queued;
+	a_sle32 hw_reaped;
+	a_sle32 underrun;
+	a_sle32 tx_abort;
+	a_sle32 mpdus_requed;
+	__le32 tx_ko;
+	__le32 data_rc;
+	__le32 self_triggers;
+	__le32 sw_retry_failure;
+	__le32 illgl_rate_phy_err;
+	__le32 pdev_cont_xretry;
+	__le32 pdev_tx_timeout;
+	__le32 pdev_resets;
+	__le32 stateless_tid_alloc_failure;
+	__le32 phy_underrun;
+	__le32 txop_ovf;
+} __packed;
+
+struct ath12k_wmi_pdev_rx_stats_params {
+	a_sle32 mid_ppdu_route_change;
+	a_sle32 status_rcvd;
+	a_sle32 r0_frags;
+	a_sle32 r1_frags;
+	a_sle32 r2_frags;
+	a_sle32 r3_frags;
+	a_sle32 htt_msdus;
+	a_sle32 htt_mpdus;
+	a_sle32 loc_msdus;
+	a_sle32 loc_mpdus;
+	a_sle32 oversize_amsdu;
+	a_sle32 phy_errs;
+	a_sle32 phy_err_drop;
+	a_sle32 mpdu_errs;
+} __packed;
+
+struct ath12k_wmi_pdev_stats_params {
+	struct ath12k_wmi_pdev_base_stats_params base;
+	struct ath12k_wmi_pdev_tx_stats_params tx;
+	struct ath12k_wmi_pdev_rx_stats_params rx;
+} __packed;
+
 struct ath12k_fw_stats_req_params {
 	u32 stats_id;
 	u32 vdev_id;

From 4e635b81db9d69bbb836afae8cb402978ff966a4 Mon Sep 17 00:00:00 2001
From: Rameshkumar Sundaram <quic_ramess@quicinc.com>
Date: Thu, 2 Jan 2025 10:00:48 +0530
Subject: [PATCH 0027/2753] wifi: ath12k: Fix pdev lookup in WBM error
 processing

Currently in ath12k_dp_rx_process_wbm_err(), when processing packets
received on the WBM error ring, pdev validation is done based upon the
hw_link_id. But hw_link_id corresponds to link id of a given partner pdev
in a MLO hardware group, and is not the correct index to use to lookup a
pdev in an SoC(ab). As a result, pdev validation fails, and the reaped
packets are dropped instead of being processed.

The correct index to use is the pdev_id, which is already derived in the
function. So update the logic to validate the pdev based upon the pdev_id
instead of the hw_link_id. This matches the logic used in other Rx ring
processing functions.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Fixes: 1a73acb5fba4 ("wifi: ath12k: move to HW link id based receive handling")
Signed-off-by: Rameshkumar Sundaram <quic_ramess@quicinc.com>
Link: https://patch.msgid.link/20250102043048.2596791-1-quic_ramess@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 09e35dd757e06..95c9056642cfd 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -4050,7 +4050,7 @@ int ath12k_dp_rx_process_wbm_err(struct ath12k_base *ab,
 						      hw_links[hw_link_id].pdev_idx);
 		ar = partner_ab->pdevs[pdev_id].ar;
 
-		if (!ar || !rcu_dereference(ar->ab->pdevs_active[hw_link_id])) {
+		if (!ar || !rcu_dereference(ar->ab->pdevs_active[pdev_id])) {
 			dev_kfree_skb_any(msdu);
 			continue;
 		}

From dbb73909eea3e89437296d75675e84fcd76a418c Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:19 +0530
Subject: [PATCH 0028/2753] wifi: ath12k: Add HTT source ring ID for monitor
 rings

Add source buffer ring and destination buffer ring ID for monitor rings.
These IDs are used for ring configuration during initial ring setup.

Since monitor rings are enabled based on the rxdma1_enable flag, enable it
in the hardware param for the QCN9274 version 2 hardware and increase the
destination ring size to handle MSDU data buffers.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-2-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp.h    | 5 ++++-
 drivers/net/wireless/ath/ath12k/dp_tx.c | 4 ++--
 drivers/net/wireless/ath/ath12k/hw.c    | 2 +-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 7ac3143de0168..1099ec19260bb 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -176,7 +176,7 @@ struct ath12k_pdev_dp {
 #define DP_RXDMA_ERR_DST_RING_SIZE	1024
 #define DP_RXDMA_MON_STATUS_RING_SIZE	1024
 #define DP_RXDMA_MONITOR_BUF_RING_SIZE	4096
-#define DP_RXDMA_MONITOR_DST_RING_SIZE	2048
+#define DP_RXDMA_MONITOR_DST_RING_SIZE	8092
 #define DP_RXDMA_MONITOR_DESC_RING_SIZE	4096
 #define DP_TX_MONITOR_BUF_RING_SIZE	4096
 #define DP_TX_MONITOR_DEST_RING_SIZE	2048
@@ -434,8 +434,11 @@ enum htt_srng_ring_id {
 	HTT_HOST1_TO_FW_RXBUF_RING,
 	HTT_HOST2_TO_FW_RXBUF_RING,
 	HTT_RXDMA_NON_MONITOR_DEST_RING,
+	HTT_RXDMA_HOST_BUF_RING2,
 	HTT_TX_MON_HOST2MON_BUF_RING,
 	HTT_TX_MON_MON2HOST_DEST_RING,
+	HTT_RX_MON_HOST2MON_BUF_RING,
+	HTT_RX_MON_MON2HOST_DEST_RING,
 };
 
 /* host -> target  HTT_SRING_SETUP message
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index de8bb9c1533e9..133a496bebb97 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -946,7 +946,7 @@ ath12k_dp_tx_get_ring_id_type(struct ath12k_base *ab,
 		*htt_ring_type = HTT_HW_TO_SW_RING;
 		break;
 	case HAL_RXDMA_MONITOR_BUF:
-		*htt_ring_id = HTT_RXDMA_MONITOR_BUF_RING;
+		*htt_ring_id = HTT_RX_MON_HOST2MON_BUF_RING;
 		*htt_ring_type = HTT_SW_TO_HW_RING;
 		break;
 	case HAL_RXDMA_MONITOR_STATUS:
@@ -954,7 +954,7 @@ ath12k_dp_tx_get_ring_id_type(struct ath12k_base *ab,
 		*htt_ring_type = HTT_SW_TO_HW_RING;
 		break;
 	case HAL_RXDMA_MONITOR_DST:
-		*htt_ring_id = HTT_RXDMA_MONITOR_DEST_RING;
+		*htt_ring_id = HTT_RX_MON_MON2HOST_DEST_RING;
 		*htt_ring_type = HTT_HW_TO_SW_RING;
 		break;
 	case HAL_RXDMA_MONITOR_DESC:
diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index b7b583fadb5ac..14bbd446ad370 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -1035,7 +1035,7 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
 
 		.hal_params = &ath12k_hw_hal_params_qcn9274,
 
-		.rxdma1_enable = false,
+		.rxdma1_enable = true,
 		.num_rxdma_per_pdev = 1,
 		.num_rxdma_dst_ring = 0,
 		.rx_mac_buf_ring = false,

From 9b0d8fb3326b32a11981a3ac6fa4ddf97248b8a6 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:20 +0530
Subject: [PATCH 0029/2753] wifi: ath12k: Enable filter config for monitor
 destination ring

Add provision to configure monitor filter for the destination
ring. These filters are used for requesting statistics or monitor mode
through the monitor destination ring.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-3-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp.h    | 49 +++++++++++++++-
 drivers/net/wireless/ath/ath12k/dp_tx.c | 75 ++++++++++++++++++++-----
 2 files changed, 109 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 1099ec19260bb..6946fb4f5c25f 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -770,8 +770,22 @@ enum htt_stats_internal_ppdu_frametype {
 #define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_RING_ID	GENMASK(23, 16)
 #define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_SS		BIT(24)
 #define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_PS		BIT(25)
-#define HTT_RX_RING_SELECTION_CFG_CMD_INFO1_BUF_SIZE	GENMASK(15, 0)
-#define HTT_RX_RING_SELECTION_CFG_CMD_OFFSET_VALID      BIT(26)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_OFFSET_VALID	BIT(26)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_DROP_THRES_VAL	BIT(27)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO0_EN_RXMON		BIT(28)
+
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO1_BUF_SIZE		GENMASK(15, 0)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_MGMT	GENMASK(18, 16)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_CTRL	GENMASK(21, 19)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_DATA	GENMASK(24, 22)
+
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO2_DROP_THRESHOLD	GENMASK(9, 0)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_LOG_MGMT_TYPE	BIT(17)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_CTRL_TYPE	BIT(18)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_LOG_DATA_TYPE	BIT(19)
+
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO3_EN_TLV_PKT_OFFSET	BIT(0)
+#define HTT_RX_RING_SELECTION_CFG_CMD_INFO3_PKT_TLV_OFFSET	GENMASK(14, 1)
 
 #define HTT_RX_RING_SELECTION_CFG_RX_PACKET_OFFSET      GENMASK(15, 0)
 #define HTT_RX_RING_SELECTION_CFG_RX_HEADER_OFFSET      GENMASK(31, 16)
@@ -800,6 +814,7 @@ enum htt_rx_filter_tlv_flags {
 	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS	= BIT(10),
 	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT	= BIT(11),
 	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE	= BIT(12),
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_START_USER_INFO	= BIT(13),
 };
 
 enum htt_rx_mgmt_pkt_filter_tlv_flags0 {
@@ -1088,6 +1103,21 @@ enum htt_rx_data_pkt_filter_tlv_flasg3 {
 		HTT_RX_FILTER_TLV_FLAGS_PER_MSDU_HEADER | \
 		HTT_RX_FILTER_TLV_FLAGS_ATTENTION)
 
+#define HTT_RX_MON_FILTER_TLV_FLAGS_MON_DEST_RING \
+	(HTT_RX_FILTER_TLV_FLAGS_MPDU_START | \
+	HTT_RX_FILTER_TLV_FLAGS_MSDU_START | \
+	HTT_RX_FILTER_TLV_FLAGS_RX_PACKET | \
+	HTT_RX_FILTER_TLV_FLAGS_MSDU_END | \
+	HTT_RX_FILTER_TLV_FLAGS_MPDU_END | \
+	HTT_RX_FILTER_TLV_FLAGS_PACKET_HEADER | \
+	HTT_RX_FILTER_TLV_FLAGS_PER_MSDU_HEADER | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_START | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_END | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE | \
+	HTT_RX_FILTER_TLV_FLAGS_PPDU_START_USER_INFO)
+
 /* msdu start. mpdu end, attention, rx hdr tlv's are not subscribed */
 #define HTT_RX_TLV_FLAGS_RXDMA_RING \
 		(HTT_RX_FILTER_TLV_FLAGS_MPDU_START | \
@@ -1116,6 +1146,10 @@ struct htt_rx_ring_selection_cfg_cmd {
 	__le32 info3;
 } __packed;
 
+#define HTT_RX_RING_TLV_DROP_THRESHOLD_VALUE	32
+#define HTT_RX_RING_DEFAULT_DMA_LENGTH		0x7
+#define HTT_RX_RING_PKT_TLV_OFFSET		0x1
+
 struct htt_rx_ring_tlv_filter {
 	u32 rx_filter; /* see htt_rx_filter_tlv_flags */
 	u32 pkt_filter_flags0; /* MGMT */
@@ -1133,6 +1167,17 @@ struct htt_rx_ring_tlv_filter {
 	u16 rx_mpdu_start_wmask;
 	u16 rx_mpdu_end_wmask;
 	u32 rx_msdu_end_wmask;
+	u32 conf_len_ctrl;
+	u32 conf_len_mgmt;
+	u32 conf_len_data;
+	u16 rx_drop_threshold;
+	bool enable_log_mgmt_type;
+	bool enable_log_ctrl_type;
+	bool enable_log_data_type;
+	bool enable_rx_tlv_offset;
+	u16 rx_tlv_offset;
+	bool drop_threshold_valid;
+	bool rxmon_disable;
 };
 
 #define HTT_STATS_FRAME_CTRL_TYPE_MGMT  0x0
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 133a496bebb97..aa8058dd2da62 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -1209,15 +1209,46 @@ int ath12k_dp_tx_htt_rx_filter_setup(struct ath12k_base *ab, u32 ring_id,
 	cmd->info0 |= le32_encode_bits(!!(params.flags & HAL_SRNG_FLAGS_DATA_TLV_SWAP),
 				       HTT_RX_RING_SELECTION_CFG_CMD_INFO0_PS);
 	cmd->info0 |= le32_encode_bits(tlv_filter->offset_valid,
-				       HTT_RX_RING_SELECTION_CFG_CMD_OFFSET_VALID);
+				       HTT_RX_RING_SELECTION_CFG_CMD_INFO0_OFFSET_VALID);
+	cmd->info0 |=
+		le32_encode_bits(tlv_filter->drop_threshold_valid,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO0_DROP_THRES_VAL);
+	cmd->info0 |= le32_encode_bits(!tlv_filter->rxmon_disable,
+				       HTT_RX_RING_SELECTION_CFG_CMD_INFO0_EN_RXMON);
+
 	cmd->info1 = le32_encode_bits(rx_buf_size,
 				      HTT_RX_RING_SELECTION_CFG_CMD_INFO1_BUF_SIZE);
+	cmd->info1 |= le32_encode_bits(tlv_filter->conf_len_mgmt,
+				       HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_MGMT);
+	cmd->info1 |= le32_encode_bits(tlv_filter->conf_len_ctrl,
+				       HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_CTRL);
+	cmd->info1 |= le32_encode_bits(tlv_filter->conf_len_data,
+				       HTT_RX_RING_SELECTION_CFG_CMD_INFO1_CONF_LEN_DATA);
 	cmd->pkt_type_en_flags0 = cpu_to_le32(tlv_filter->pkt_filter_flags0);
 	cmd->pkt_type_en_flags1 = cpu_to_le32(tlv_filter->pkt_filter_flags1);
 	cmd->pkt_type_en_flags2 = cpu_to_le32(tlv_filter->pkt_filter_flags2);
 	cmd->pkt_type_en_flags3 = cpu_to_le32(tlv_filter->pkt_filter_flags3);
 	cmd->rx_filter_tlv = cpu_to_le32(tlv_filter->rx_filter);
 
+	cmd->info2 = le32_encode_bits(tlv_filter->rx_drop_threshold,
+				      HTT_RX_RING_SELECTION_CFG_CMD_INFO2_DROP_THRESHOLD);
+	cmd->info2 |=
+		le32_encode_bits(tlv_filter->enable_log_mgmt_type,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_LOG_MGMT_TYPE);
+	cmd->info2 |=
+		le32_encode_bits(tlv_filter->enable_log_ctrl_type,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_CTRL_TYPE);
+	cmd->info2 |=
+		le32_encode_bits(tlv_filter->enable_log_data_type,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO2_EN_LOG_DATA_TYPE);
+
+	cmd->info3 =
+		le32_encode_bits(tlv_filter->enable_rx_tlv_offset,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO3_EN_TLV_PKT_OFFSET);
+	cmd->info3 |=
+		le32_encode_bits(tlv_filter->rx_tlv_offset,
+				 HTT_RX_RING_SELECTION_CFG_CMD_INFO3_PKT_TLV_OFFSET);
+
 	if (tlv_filter->offset_valid) {
 		cmd->rx_packet_offset =
 			le32_encode_bits(tlv_filter->rx_packet_offset,
@@ -1342,15 +1373,28 @@ int ath12k_dp_tx_htt_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 int ath12k_dp_tx_htt_rx_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 {
 	struct ath12k_base *ab = ar->ab;
-	struct ath12k_dp *dp = &ab->dp;
 	struct htt_rx_ring_tlv_filter tlv_filter = {0};
-	int ret, ring_id;
+	int ret, ring_id, i;
 
-	ring_id = dp->rxdma_mon_buf_ring.refill_buf_ring.ring_id;
 	tlv_filter.offset_valid = false;
 
 	if (!reset) {
-		tlv_filter.rx_filter = HTT_RX_MON_FILTER_TLV_FLAGS_MON_BUF_RING;
+		tlv_filter.rx_filter = HTT_RX_MON_FILTER_TLV_FLAGS_MON_DEST_RING;
+
+		tlv_filter.drop_threshold_valid = true;
+		tlv_filter.rx_drop_threshold = HTT_RX_RING_TLV_DROP_THRESHOLD_VALUE;
+
+		tlv_filter.enable_log_mgmt_type = true;
+		tlv_filter.enable_log_ctrl_type = true;
+		tlv_filter.enable_log_data_type = true;
+
+		tlv_filter.conf_len_ctrl = HTT_RX_RING_DEFAULT_DMA_LENGTH;
+		tlv_filter.conf_len_mgmt = HTT_RX_RING_DEFAULT_DMA_LENGTH;
+		tlv_filter.conf_len_data = HTT_RX_RING_DEFAULT_DMA_LENGTH;
+
+		tlv_filter.enable_rx_tlv_offset = true;
+		tlv_filter.rx_tlv_offset = HTT_RX_RING_PKT_TLV_OFFSET;
+
 		tlv_filter.pkt_filter_flags0 =
 					HTT_RX_MON_FP_MGMT_FILTER_FLAGS0 |
 					HTT_RX_MON_MO_MGMT_FILTER_FLAGS0;
@@ -1368,14 +1412,19 @@ int ath12k_dp_tx_htt_rx_monitor_mode_ring_config(struct ath12k *ar, bool reset)
 	}
 
 	if (ab->hw_params->rxdma1_enable) {
-		ret = ath12k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, 0,
-						       HAL_RXDMA_MONITOR_BUF,
-						       DP_RXDMA_REFILL_RING_SIZE,
-						       &tlv_filter);
-		if (ret) {
-			ath12k_err(ab,
-				   "failed to setup filter for monitor buf %d\n", ret);
-			return ret;
+		for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+			ring_id = ar->dp.rxdma_mon_dst_ring[i].ring_id;
+			ret = ath12k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id,
+							       ar->dp.mac_id + i,
+							       HAL_RXDMA_MONITOR_DST,
+							       DP_RXDMA_REFILL_RING_SIZE,
+							       &tlv_filter);
+			if (ret) {
+				ath12k_err(ab,
+					   "failed to setup filter for monitor buf %d\n",
+					   ret);
+				return ret;
+			}
 		}
 	}
 

From 6e8c9ba7f0308ba2a88270cec6ce7e8ef621df1f Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:21 +0530
Subject: [PATCH 0030/2753] wifi: ath12k: Avoid multiple times configuring
 monitor filter

ath12k_mac_op_configure_filter() gets called multiple times during
interface bringup. Applying filter configuration from this function leads
to writing same filter configurations multiple times.

Resolve this issue by relocating the filter configuration to
ath12k_mac_config_mon_status_default(), which is invoked by both
ath12k_mac_op_start() and ath12k_mac_op_stop(). Additionally, set the
rxmon_disable flag to true when called from ath12k_mac_op_stop() to
disable the monitor destination ring.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-4-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 57 +++++++++++++++------------
 1 file changed, 31 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index a245eb6293fbc..4fb7e235be667 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7336,8 +7336,36 @@ void ath12k_mac_drain_tx(struct ath12k *ar)
 
 static int ath12k_mac_config_mon_status_default(struct ath12k *ar, bool enable)
 {
-	return -EOPNOTSUPP;
-	/* TODO: Need to support new monitor mode */
+	struct htt_rx_ring_tlv_filter tlv_filter = {};
+	struct ath12k_base *ab = ar->ab;
+	u32 ring_id, i;
+	int ret = 0;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (!ab->hw_params->rxdma1_enable)
+		return ret;
+
+	if (enable)
+		tlv_filter = ath12k_mac_mon_status_filter_default;
+	else
+		tlv_filter.rxmon_disable = true;
+
+	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
+		ring_id = ar->dp.rxdma_mon_dst_ring[i].ring_id;
+		ret = ath12k_dp_tx_htt_rx_filter_setup(ab, ring_id,
+						       ar->dp.mac_id + i,
+						       HAL_RXDMA_MONITOR_DST,
+						       DP_RXDMA_REFILL_RING_SIZE,
+						       &tlv_filter);
+		if (ret) {
+			ath12k_err(ab,
+				   "failed to setup filter for monitor buf %d\n",
+				   ret);
+		}
+	}
+
+	return ret;
 }
 
 static int ath12k_mac_start(struct ath12k *ar)
@@ -8468,29 +8496,6 @@ static void ath12k_mac_op_remove_interface(struct ieee80211_hw *hw,
 	FIF_PROBE_REQ |				\
 	FIF_FCSFAIL)
 
-static void ath12k_mac_configure_filter(struct ath12k *ar,
-					unsigned int total_flags)
-{
-	bool reset_flag;
-	int ret;
-
-	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
-
-	ar->filter_flags = total_flags;
-
-	/* For monitor mode */
-	reset_flag = !(ar->filter_flags & FIF_BCN_PRBRESP_PROMISC);
-
-	ret = ath12k_dp_tx_htt_monitor_mode_ring_config(ar, reset_flag);
-	if (ret)
-		ath12k_warn(ar->ab,
-			    "fail to set monitor filter: %d\n", ret);
-
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
-		   "total_flags:0x%x, reset_flag:%d\n",
-		   total_flags, reset_flag);
-}
-
 static void ath12k_mac_op_configure_filter(struct ieee80211_hw *hw,
 					   unsigned int changed_flags,
 					   unsigned int *total_flags,
@@ -8504,7 +8509,7 @@ static void ath12k_mac_op_configure_filter(struct ieee80211_hw *hw,
 	ar = ath12k_ah_to_ar(ah, 0);
 
 	*total_flags &= SUPPORTED_FILTERS;
-	ath12k_mac_configure_filter(ar, *total_flags);
+	ar->filter_flags = *total_flags;
 }
 
 static int ath12k_mac_op_get_antenna(struct ieee80211_hw *hw, u32 *tx_ant, u32 *rx_ant)

From 39f1d751d2ae7050ad9b88560fc2042515dc88d5 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:22 +0530
Subject: [PATCH 0031/2753] wifi: ath12k: Avoid code duplication in monitor
 ring processing

The current implementation processes the monitor destination ring using
two separate functions, ath12k_dp_mon_srng_process() for standalone
monitor mode and ath12k_dp_mon_rx_process_stats() for statistics.
However, both functions contain same code which performs monitor ring
reaping and skb data processing. To eliminate redundancy, remove the
duplicate code and use a single function to handle both the cases.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-5-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 126 ++---------------------
 drivers/net/wireless/ath/ath12k/dp_mon.h |   6 +-
 2 files changed, 9 insertions(+), 123 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 53f8e8f8959ad..08f92e74feded 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2000,116 +2000,6 @@ ath12k_dp_mon_tx_parse_mon_status(struct ath12k *ar,
 	return tlv_status;
 }
 
-int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
-			       enum dp_monitor_mode monitor_mode,
-			       struct napi_struct *napi)
-{
-	struct hal_mon_dest_desc *mon_dst_desc;
-	struct ath12k_pdev_dp *pdev_dp = &ar->dp;
-	struct ath12k_mon_data *pmon = (struct ath12k_mon_data *)&pdev_dp->mon_data;
-	struct ath12k_base *ab = ar->ab;
-	struct ath12k_dp *dp = &ab->dp;
-	struct sk_buff *skb;
-	struct ath12k_skb_rxcb *rxcb;
-	struct dp_srng *mon_dst_ring;
-	struct hal_srng *srng;
-	struct dp_rxdma_mon_ring *buf_ring;
-	u64 cookie;
-	u32 ppdu_id;
-	int num_buffs_reaped = 0, srng_id, buf_id;
-	u8 dest_idx = 0, i;
-	bool end_of_ppdu;
-	struct hal_rx_mon_ppdu_info *ppdu_info;
-	struct ath12k_peer *peer = NULL;
-	u8 pdev_idx = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, ar->pdev_idx);
-
-	ppdu_info = &pmon->mon_ppdu_info;
-	memset(ppdu_info, 0, sizeof(*ppdu_info));
-	ppdu_info->peer_id = HAL_INVALID_PEERID;
-
-	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, pdev_idx);
-
-	if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE) {
-		mon_dst_ring = &pdev_dp->rxdma_mon_dst_ring[srng_id];
-		buf_ring = &dp->rxdma_mon_buf_ring;
-	} else {
-		return 0;
-	}
-
-	srng = &ab->hal.srng_list[mon_dst_ring->ring_id];
-
-	spin_lock_bh(&srng->lock);
-	ath12k_hal_srng_access_begin(ab, srng);
-
-	while (likely(*budget)) {
-		*budget -= 1;
-		mon_dst_desc = ath12k_hal_srng_dst_peek(ab, srng);
-		if (unlikely(!mon_dst_desc))
-			break;
-
-		cookie = le32_to_cpu(mon_dst_desc->cookie);
-		buf_id = u32_get_bits(cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
-
-		spin_lock_bh(&buf_ring->idr_lock);
-		skb = idr_remove(&buf_ring->bufs_idr, buf_id);
-		spin_unlock_bh(&buf_ring->idr_lock);
-
-		if (unlikely(!skb)) {
-			ath12k_warn(ab, "monitor destination with invalid buf_id %d\n",
-				    buf_id);
-			goto move_next;
-		}
-
-		rxcb = ATH12K_SKB_RXCB(skb);
-		dma_unmap_single(ab->dev, rxcb->paddr,
-				 skb->len + skb_tailroom(skb),
-				 DMA_FROM_DEVICE);
-
-		pmon->dest_skb_q[dest_idx] = skb;
-		dest_idx++;
-		ppdu_id = le32_to_cpu(mon_dst_desc->ppdu_id);
-		end_of_ppdu = le32_get_bits(mon_dst_desc->info0,
-					    HAL_MON_DEST_INFO0_END_OF_PPDU);
-		if (!end_of_ppdu)
-			continue;
-
-		for (i = 0; i < dest_idx; i++) {
-			skb = pmon->dest_skb_q[i];
-
-			if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE)
-				ath12k_dp_mon_rx_parse_mon_status(ar, pmon,
-								  skb, napi);
-			else
-				ath12k_dp_mon_tx_parse_mon_status(ar, pmon,
-								  skb, napi, ppdu_id);
-
-			peer = ath12k_peer_find_by_id(ab, ppdu_info->peer_id);
-
-			if (!peer || !peer->sta) {
-				ath12k_dbg(ab, ATH12K_DBG_DATA,
-					   "failed to find the peer with peer_id %d\n",
-					   ppdu_info->peer_id);
-				dev_kfree_skb_any(skb);
-				continue;
-			}
-
-			dev_kfree_skb_any(skb);
-			pmon->dest_skb_q[i] = NULL;
-		}
-
-		dest_idx = 0;
-move_next:
-		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
-		ath12k_hal_srng_src_get_next_entry(ab, srng);
-		num_buffs_reaped++;
-	}
-
-	ath12k_hal_srng_access_end(ab, srng);
-	spin_unlock_bh(&srng->lock);
-
-	return num_buffs_reaped;
-}
-
 static void
 ath12k_dp_mon_rx_update_peer_rate_table_stats(struct ath12k_rx_peer_stats *rx_stats,
 					      struct hal_rx_mon_ppdu_info *ppdu_info,
@@ -2415,8 +2305,8 @@ ath12k_dp_mon_rx_update_peer_mu_stats(struct ath12k *ar,
 		ath12k_dp_mon_rx_update_user_stats(ar, ppdu_info, i);
 }
 
-int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id,
-				   struct napi_struct *napi, int *budget)
+int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
+			       struct napi_struct *napi)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_pdev_dp *pdev_dp = &ar->dp;
@@ -2437,8 +2327,9 @@ int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id,
 	u8 dest_idx = 0, i;
 	bool end_of_ppdu;
 	u32 hal_status;
+	u8 pdev_idx = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, ar->pdev_idx);
 
-	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, mac_id);
+	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, pdev_idx);
 	mon_dst_ring = &pdev_dp->rxdma_mon_dst_ring[srng_id];
 	buf_ring = &dp->rxdma_mon_buf_ring;
 
@@ -2535,11 +2426,10 @@ int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 	struct ath12k *ar = ath12k_ab_to_ar(ab, mac_id);
 	int num_buffs_reaped = 0;
 
-	if (!ar->monitor_started)
-		ath12k_dp_mon_rx_process_stats(ar, mac_id, napi, &budget);
-	else
-		num_buffs_reaped = ath12k_dp_mon_srng_process(ar, &budget,
-							      monitor_mode, napi);
+	if (ab->hw_params->rxdma1_enable) {
+		if (monitor_mode == ATH12K_DP_RX_MONITOR_MODE)
+			num_buffs_reaped = ath12k_dp_mon_srng_process(ar, &budget, napi);
+	}
 
 	return num_buffs_reaped;
 }
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.h b/drivers/net/wireless/ath/ath12k/dp_mon.h
index 64c959c364599..e4368eb42aca8 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.h
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.h
@@ -82,9 +82,6 @@ ath12k_dp_mon_rx_parse_mon_status(struct ath12k *ar,
 int ath12k_dp_mon_buf_replenish(struct ath12k_base *ab,
 				struct dp_rxdma_mon_ring *buf_ring,
 				int req_entries);
-int ath12k_dp_mon_srng_process(struct ath12k *ar,
-			       int *budget, enum dp_monitor_mode monitor_mode,
-			       struct napi_struct *napi);
 int ath12k_dp_mon_process_ring(struct ath12k_base *ab, int mac_id,
 			       struct napi_struct *napi, int budget,
 			       enum dp_monitor_mode monitor_mode);
@@ -100,6 +97,5 @@ ath12k_dp_mon_tx_parse_mon_status(struct ath12k *ar,
 				  struct napi_struct *napi,
 				  u32 ppdu_id);
 void ath12k_dp_mon_rx_process_ulofdma(struct hal_rx_mon_ppdu_info *ppdu_info);
-int ath12k_dp_mon_rx_process_stats(struct ath12k *ar, int mac_id,
-				   struct napi_struct *napi, int *budget);
+int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget, struct napi_struct *napi);
 #endif

From cf544270c7392af1dc3a3bf405b902f3b9d3f925 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:23 +0530
Subject: [PATCH 0032/2753] wifi: ath12k: Restructure the code for monitor ring
 processing

Currently, monitor ring reaping and processing occur in the same loop,
which requires holding ring locks until skb processing is complete.
However, only the ring reaping part requires the ring lock; the skb
processing part does not need it. This approach is problematic because it
unnecessarily extends the duration for which the ring locks are held,
leading to increased contention and potential backpressure issues.
Fix it by holding ring locks only during the reaping phase, as skb
processing does not require them. First, reap the monitor destination ring
with the ring lock and queue the skbs into an skb list. Then, process the
skbs in this list in a separate loop without holding the ring lock.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-6-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp.h     |   1 -
 drivers/net/wireless/ath/ath12k/dp_mon.c | 116 +++++++++++++----------
 2 files changed, 64 insertions(+), 53 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 6946fb4f5c25f..f68bb78d4a110 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -125,7 +125,6 @@ struct ath12k_mon_data {
 	struct sk_buff_head rx_status_q;
 	struct dp_mon_mpdu *mon_mpdu;
 	struct list_head dp_rx_mon_mpdu_list;
-	struct sk_buff *dest_skb_q[DP_MON_MAX_STATUS_BUF];
 	struct dp_mon_tx_ppdu_info *tx_prot_ppdu_info;
 	struct dp_mon_tx_ppdu_info *tx_data_ppdu_info;
 };
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 08f92e74feded..f9fd28ce801ad 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1188,14 +1188,11 @@ static enum hal_rx_mon_status
 ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 			    struct sk_buff *skb)
 {
-	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	struct hal_tlv_64_hdr *tlv;
 	enum hal_rx_mon_status hal_status;
 	u16 tlv_tag, tlv_len;
 	u8 *ptr = skb->data;
 
-	memset(ppdu_info, 0, sizeof(struct hal_rx_mon_ppdu_info));
-
 	do {
 		tlv = (struct hal_tlv_64_hdr *)ptr;
 		tlv_tag = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_TAG);
@@ -2305,6 +2302,13 @@ ath12k_dp_mon_rx_update_peer_mu_stats(struct ath12k *ar,
 		ath12k_dp_mon_rx_update_user_stats(ar, ppdu_info, i);
 }
 
+static void
+ath12k_dp_mon_rx_memset_ppdu_info(struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	memset(ppdu_info, 0, sizeof(*ppdu_info));
+	ppdu_info->peer_id = HAL_INVALID_PEERID;
+}
+
 int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 			       struct napi_struct *napi)
 {
@@ -2322,13 +2326,13 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 	struct ath12k_sta *ahsta = NULL;
 	struct ath12k_link_sta *arsta;
 	struct ath12k_peer *peer;
+	struct sk_buff_head skb_list;
 	u64 cookie;
 	int num_buffs_reaped = 0, srng_id, buf_id;
-	u8 dest_idx = 0, i;
-	bool end_of_ppdu;
-	u32 hal_status;
+	u32 hal_status, end_offset, info0;
 	u8 pdev_idx = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, ar->pdev_idx);
 
+	__skb_queue_head_init(&skb_list);
 	srng_id = ath12k_hw_mac_id_to_srng_id(ab->hw_params, pdev_idx);
 	mon_dst_ring = &pdev_dp->rxdma_mon_dst_ring[srng_id];
 	buf_ring = &dp->rxdma_mon_buf_ring;
@@ -2342,6 +2346,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 		mon_dst_desc = ath12k_hal_srng_dst_peek(ab, srng);
 		if (unlikely(!mon_dst_desc))
 			break;
+
 		cookie = le32_to_cpu(mon_dst_desc->cookie);
 		buf_id = u32_get_bits(cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
 
@@ -2359,55 +2364,19 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 		dma_unmap_single(ab->dev, rxcb->paddr,
 				 skb->len + skb_tailroom(skb),
 				 DMA_FROM_DEVICE);
-		pmon->dest_skb_q[dest_idx] = skb;
-		dest_idx++;
-		end_of_ppdu = le32_get_bits(mon_dst_desc->info0,
-					    HAL_MON_DEST_INFO0_END_OF_PPDU);
-		if (!end_of_ppdu)
-			continue;
-
-		for (i = 0; i < dest_idx; i++) {
-			skb = pmon->dest_skb_q[i];
-			hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
-
-			if (ppdu_info->peer_id == HAL_INVALID_PEERID ||
-			    hal_status != HAL_RX_MON_STATUS_PPDU_DONE) {
-				dev_kfree_skb_any(skb);
-				continue;
-			}
-
-			rcu_read_lock();
-			spin_lock_bh(&ab->base_lock);
-			peer = ath12k_peer_find_by_id(ab, ppdu_info->peer_id);
-			if (!peer || !peer->sta) {
-				ath12k_dbg(ab, ATH12K_DBG_DATA,
-					   "failed to find the peer with peer_id %d\n",
-					   ppdu_info->peer_id);
-				spin_unlock_bh(&ab->base_lock);
-				rcu_read_unlock();
-				dev_kfree_skb_any(skb);
-				continue;
-			}
-
-			if (ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_SU) {
-				ahsta = ath12k_sta_to_ahsta(peer->sta);
-				arsta = &ahsta->deflink;
-				ath12k_dp_mon_rx_update_peer_su_stats(ar, arsta,
-								      ppdu_info);
-			} else if ((ppdu_info->fc_valid) &&
-				   (ppdu_info->ast_index != HAL_AST_IDX_INVALID)) {
-				ath12k_dp_mon_rx_process_ulofdma(ppdu_info);
-				ath12k_dp_mon_rx_update_peer_mu_stats(ar, ppdu_info);
-			}
 
-			spin_unlock_bh(&ab->base_lock);
-			rcu_read_unlock();
-			dev_kfree_skb_any(skb);
-			memset(ppdu_info, 0, sizeof(*ppdu_info));
-			ppdu_info->peer_id = HAL_INVALID_PEERID;
+		end_offset = u32_get_bits(info0, HAL_MON_DEST_INFO0_END_OFFSET);
+		if (likely(end_offset <= DP_RX_BUFFER_SIZE)) {
+			skb_put(skb, end_offset);
+		} else {
+			ath12k_warn(ab,
+				    "invalid offset on mon stats destination %u\n",
+				    end_offset);
+			skb_put(skb, DP_RX_BUFFER_SIZE);
 		}
 
-		dest_idx = 0;
+		__skb_queue_tail(&skb_list, skb);
+
 move_next:
 		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
 		ath12k_hal_srng_src_get_next_entry(ab, srng);
@@ -2416,6 +2385,49 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 
 	ath12k_hal_srng_access_end(ab, srng);
 	spin_unlock_bh(&srng->lock);
+
+	if (!num_buffs_reaped)
+		return 0;
+
+	while ((skb = __skb_dequeue(&skb_list))) {
+		hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
+		if (hal_status != HAL_RX_MON_STATUS_PPDU_DONE) {
+			dev_kfree_skb_any(skb);
+			continue;
+		}
+
+		if (ppdu_info->peer_id == HAL_INVALID_PEERID)
+			goto free_skb;
+
+		rcu_read_lock();
+		spin_lock_bh(&ab->base_lock);
+		peer = ath12k_peer_find_by_id(ab, ppdu_info->peer_id);
+		if (!peer || !peer->sta) {
+			ath12k_dbg(ab, ATH12K_DBG_DATA,
+				   "failed to find the peer with monitor peer_id %d\n",
+				   ppdu_info->peer_id);
+			goto next_skb;
+		}
+
+		if (ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_SU) {
+			ahsta = ath12k_sta_to_ahsta(peer->sta);
+			arsta = &ahsta->deflink;
+			ath12k_dp_mon_rx_update_peer_su_stats(ar, arsta,
+							      ppdu_info);
+		} else if ((ppdu_info->fc_valid) &&
+			   (ppdu_info->ast_index != HAL_AST_IDX_INVALID)) {
+			ath12k_dp_mon_rx_process_ulofdma(ppdu_info);
+			ath12k_dp_mon_rx_update_peer_mu_stats(ar, ppdu_info);
+		}
+
+next_skb:
+		spin_unlock_bh(&ab->base_lock);
+		rcu_read_unlock();
+free_skb:
+		dev_kfree_skb_any(skb);
+		ath12k_dp_mon_rx_memset_ppdu_info(ppdu_info);
+	}
+
 	return num_buffs_reaped;
 }
 

From 63fdc4509bcf483e79548de6bc08bf3c8e504bb3 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:24 +0530
Subject: [PATCH 0033/2753] wifi: ath12k: Fix invalid entry fetch in
 ath12k_dp_mon_srng_process

Currently, ath12k_dp_mon_srng_process uses ath12k_hal_srng_src_get_next_entry
to fetch the next entry from the destination ring. This is incorrect because
ath12k_hal_srng_src_get_next_entry is intended for source rings, not destination
rings. This leads to invalid entry fetches, causing potential data corruption or
crashes due to accessing incorrect memory locations. This happens because the
source ring and destination ring have different handling mechanisms and using
the wrong function results in incorrect pointer arithmetic and ring management.

To fix this issue, replace the call to ath12k_hal_srng_src_get_next_entry with
ath12k_hal_srng_dst_get_next_entry in ath12k_dp_mon_srng_process. This ensures
that the correct function is used for fetching entries from the destination
ring, preventing invalid memory accesses.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-7-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index f9fd28ce801ad..236456b02198c 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2379,7 +2379,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 
 move_next:
 		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
-		ath12k_hal_srng_src_get_next_entry(ab, srng);
+		ath12k_hal_srng_dst_get_next_entry(ab, srng);
 		num_buffs_reaped++;
 	}
 

From 6788a666000d600bd8f2e9f991cad9cc805e7f01 Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:25 +0530
Subject: [PATCH 0034/2753] wifi: ath12k: Fix end offset bit definition in
 monitor ring descriptor

End offset for the monitor destination ring descriptor is defined as
16 bits, while the firmware definition specifies only 12 bits.
The remaining bits (bit 12 to bit 15) are reserved and may contain
junk values, leading to invalid information retrieval. Fix this issue
by updating the correct genmask values.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-8-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/hal_desc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index 7b0403d245e59..a102d27e5785f 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -2968,7 +2968,7 @@ struct hal_mon_buf_ring {
 
 #define HAL_MON_DEST_COOKIE_BUF_ID      GENMASK(17, 0)
 
-#define HAL_MON_DEST_INFO0_END_OFFSET		GENMASK(15, 0)
+#define HAL_MON_DEST_INFO0_END_OFFSET		GENMASK(11, 0)
 #define HAL_MON_DEST_INFO0_FLUSH_DETECTED	BIT(16)
 #define HAL_MON_DEST_INFO0_END_OF_PPDU		BIT(17)
 #define HAL_MON_DEST_INFO0_INITIATOR		BIT(18)

From 51ad34a47e9f261d03894b49a734174c170b326f Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:26 +0530
Subject: [PATCH 0035/2753] wifi: ath12k: Add drop descriptor handling for
 monitor ring

When monitor block in Hardware experiences internal backpressure, a ring
entry with the EMPTY_DESC reason is received in the monitor destination
ring descriptor. The cookie field for this corresponding entry is invalid.
Currently driver attempts to process this cookie resulting in invalid
buf_id warning logs flooding the console. To fix this, skip processing the
destination descriptor when the EMPTY_DESCRIPTOR bit is set to true in ring
descriptor, thereby avoiding the processing of junk cookies.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-9-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 236456b02198c..bf43ef2b6b39d 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2347,6 +2347,14 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 		if (unlikely(!mon_dst_desc))
 			break;
 
+		/* In case of empty descriptor, the cookie in the ring descriptor
+		 * is invalid. Therefore, this entry is skipped, and ring processing
+		 * continues.
+		 */
+		info0 = le32_to_cpu(mon_dst_desc->info0);
+		if (u32_get_bits(info0, HAL_MON_DEST_INFO0_EMPTY_DESC))
+			goto move_next;
+
 		cookie = le32_to_cpu(mon_dst_desc->cookie);
 		buf_id = u32_get_bits(cookie, DP_RXDMA_BUF_COOKIE_BUF_ID);
 

From 8520ba9bb8f43ce9d540d9be6a5711ceeb1651cf Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:27 +0530
Subject: [PATCH 0036/2753] wifi: ath12k: Handle end reason for the monitor
 destination ring

Currently, the monitor destination ring's descriptor includes a 2-bit
field for the end reason. Out of all the end reason values, hardware uses
HAL_MON_FLUSH_DETECTED and HAL_MON_PPDU_TRUNCATED to indicate buffers that
should not be processed due to system level errors. Driver should not
process entries with these end reasons, as they contain junk values.
However, the current code lacks end reason-specific checks for the monitor
destination ring, leading to the processing of invalid buffers.
Fix this by adding checks for these two end reasons during the reaping
phase. Free the skb if either HAL_MON_FLUSH_DETECTED or
HAL_MON_PPDU_TRUNCATED is detected, preventing the driver from processing
invalid entries.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-10-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c   | 17 ++++++++++++++++-
 drivers/net/wireless/ath/ath12k/hal_desc.h |  3 +--
 2 files changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index bf43ef2b6b39d..dbf5afd88ad53 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2329,7 +2329,7 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 	struct sk_buff_head skb_list;
 	u64 cookie;
 	int num_buffs_reaped = 0, srng_id, buf_id;
-	u32 hal_status, end_offset, info0;
+	u32 hal_status, end_offset, info0, end_reason;
 	u8 pdev_idx = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, ar->pdev_idx);
 
 	__skb_queue_head_init(&skb_list);
@@ -2373,6 +2373,21 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 				 skb->len + skb_tailroom(skb),
 				 DMA_FROM_DEVICE);
 
+		end_reason = u32_get_bits(info0, HAL_MON_DEST_INFO0_END_REASON);
+
+		/* HAL_MON_FLUSH_DETECTED implies that an rx flush received at the end of
+		 * rx PPDU and HAL_MON_PPDU_TRUNCATED implies that the PPDU got
+		 * truncated due to a system level error. In both the cases, buffer data
+		 * can be discarded
+		 */
+		if ((end_reason == HAL_MON_FLUSH_DETECTED) ||
+		    (end_reason == HAL_MON_PPDU_TRUNCATED)) {
+			ath12k_dbg(ab, ATH12K_DBG_DATA,
+				   "Monitor dest descriptor end reason %d", end_reason);
+			dev_kfree_skb_any(skb);
+			goto move_next;
+		}
+
 		end_offset = u32_get_bits(info0, HAL_MON_DEST_INFO0_END_OFFSET);
 		if (likely(end_offset <= DP_RX_BUFFER_SIZE)) {
 			skb_put(skb, end_offset);
diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
index a102d27e5785f..3e8983b85de86 100644
--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
+++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
@@ -2969,8 +2969,7 @@ struct hal_mon_buf_ring {
 #define HAL_MON_DEST_COOKIE_BUF_ID      GENMASK(17, 0)
 
 #define HAL_MON_DEST_INFO0_END_OFFSET		GENMASK(11, 0)
-#define HAL_MON_DEST_INFO0_FLUSH_DETECTED	BIT(16)
-#define HAL_MON_DEST_INFO0_END_OF_PPDU		BIT(17)
+#define HAL_MON_DEST_INFO0_END_REASON		GENMASK(17, 16)
 #define HAL_MON_DEST_INFO0_INITIATOR		BIT(18)
 #define HAL_MON_DEST_INFO0_EMPTY_DESC		BIT(19)
 #define HAL_MON_DEST_INFO0_RING_ID		GENMASK(27, 20)

From 394a3fa7c538060ee3cb134d52b4e9ec1f680cac Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:28 +0530
Subject: [PATCH 0037/2753] wifi: ath12k: Optimize NAPI budget by adjusting
 PPDU processing

In the current implementation, when PPDU spans multiple ring descriptors,
leading to inefficient use of the NAPI budget. The budget counter is
decremented for each ring descriptor, causing rapid depletion of the
budget even though the processing of a single PPDU might not be complete.

To address this issue, modify the code to decrement the budget counter
only when the driver receives HAL_MON_END_OF_PPDU as the end reason. This
change ensures that the budget is decremented only once per PPDU,
resulting in more efficient utilization of the NAPI budget and better
handling of monitor destination ring.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-11-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index dbf5afd88ad53..a11b39ae37745 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2388,6 +2388,13 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 			goto move_next;
 		}
 
+		/* Calculate the budget when the ring descriptor with the
+		 * HAL_MON_END_OF_PPDU to ensure that one PPDU worth of data is always
+		 * reaped. This helps to efficiently utilize the NAPI budget.
+		 */
+		if (end_reason == HAL_MON_END_OF_PPDU)
+			*budget -= 1;
+
 		end_offset = u32_get_bits(info0, HAL_MON_DEST_INFO0_END_OFFSET);
 		if (likely(end_offset <= DP_RX_BUFFER_SIZE)) {
 			skb_put(skb, end_offset);

From 67434640e52256efd14260cb8edbea41c1faef0b Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:29 +0530
Subject: [PATCH 0038/2753] wifi: ath12k: Handle PPDU spread across multiple
 buffers
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Each PPDU contains numerous TLV tags. HAL_RX_PPDU_START marks the start
of the PPDU, and HAL_RX_PPDU_END_STATUS_DONE marks the end. From the
monitor destination rings, the driver retrieves skb containing these
TLV tags and their corresponding data. Sometimes, one PPDU’s information
spreads across multiple skbs. The current parsing logic uses memset on
struct hal_rx_mon_ppdu_info after parsing each skb, leading to information
loss if a PPDU spans multiple skbs. Fix this by setting the
ppdu_continuation flag when the driver fails to get
HAL_RX_PPDU_END_STATUS_DONE, and do memset on struct
hal_rx_mon_ppdu_info only when the ppdu_continuation flag is not set.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-12-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 8 ++++++++
 drivers/net/wireless/ath/ath12k/hal_rx.h | 1 +
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index a11b39ae37745..4b35dfcbdfe18 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2419,9 +2419,17 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 	if (!num_buffs_reaped)
 		return 0;
 
+	/* In some cases, one PPDU worth of data can be spread across multiple NAPI
+	 * schedules, To avoid losing existing parsed ppdu_info information, skip
+	 * the memset of the ppdu_info structure and continue processing it.
+	 */
+	if (!ppdu_info->ppdu_continuation)
+		ath12k_dp_mon_rx_memset_ppdu_info(ppdu_info);
+
 	while ((skb = __skb_dequeue(&skb_list))) {
 		hal_status = ath12k_dp_mon_parse_rx_dest(ar, pmon, skb);
 		if (hal_status != HAL_RX_MON_STATUS_PPDU_DONE) {
+			ppdu_info->ppdu_continuation = true;
 			dev_kfree_skb_any(skb);
 			continue;
 		}
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 04e9f5f8e83ab..b60c172d131b8 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -231,6 +231,7 @@ struct hal_rx_mon_ppdu_info {
 	bool first_msdu_in_mpdu;
 	bool is_ampdu;
 	u8 medium_prot_type;
+	bool ppdu_continuation;
 };
 
 #define HAL_RX_PPDU_START_INFO0_PPDU_ID			GENMASK(15, 0)

From ecfc131389923405be8e7a6f4408fd9321e4d19b Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:30 +0530
Subject: [PATCH 0039/2753] wifi: ath12k: Avoid memory leak while enabling
 statistics

Driver uses monitor destination rings for extended statistics mode and
standalone monitor mode. In extended statistics mode, TLVs are parsed from
the buffer received from the monitor destination ring and assigned to the
ppdu_info structure to update per-packet statistics. In standalone monitor
mode, along with per-packet statistics, the packet data (payload) is
captured, and the driver updates per MSDU to mac80211.

When the AP interface is enabled, only extended statistics mode is
activated. As part of enabling monitor rings for collecting statistics,
the driver subscribes to HAL_RX_MPDU_START TLV in the filter
configuration. This TLV is received from the monitor destination ring, and
kzalloc for the mon_mpdu object occurs, which is not freed, leading to a
memory leak. The kzalloc for the mon_mpdu object is only required while
enabling the standalone monitor interface. This causes a memory leak while
enabling extended statistics mode in the driver.

Fix this memory leak by removing the kzalloc for the mon_mpdu object in
the HAL_RX_MPDU_START TLV handling. Additionally, remove the standalone
monitor mode handlings in the HAL_MON_BUF_ADDR and HAL_RX_MSDU_END TLVs.
These TLV tags will be handled properly when enabling standalone monitor
mode in the future.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-13-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 65 ++++--------------------
 drivers/net/wireless/ath/ath12k/hal_rx.h |  3 ++
 2 files changed, 12 insertions(+), 56 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 4b35dfcbdfe18..23b1a41c6fd2b 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -567,7 +567,6 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
 				  const struct hal_tlv_64_hdr *tlv)
 {
-	struct ath12k_base *ab = ar->ab;
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	const void *tlv_data = tlv->value;
 	u32 info[7], userid;
@@ -748,7 +747,6 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 	}
 	case HAL_RX_MPDU_START: {
 		const struct hal_rx_mpdu_start *mpdu_start = tlv_data;
-		struct dp_mon_mpdu *mon_mpdu = pmon->mon_mpdu;
 		u16 peer_id;
 
 		info[1] = __le32_to_cpu(mpdu_start->info1);
@@ -765,65 +763,17 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO1_PEERID);
 		}
 
-		mon_mpdu = kzalloc(sizeof(*mon_mpdu), GFP_ATOMIC);
-		if (!mon_mpdu)
-			return HAL_RX_MON_STATUS_PPDU_NOT_DONE;
-
 		break;
 	}
 	case HAL_RX_MSDU_START:
 		/* TODO: add msdu start parsing logic */
 		break;
-	case HAL_MON_BUF_ADDR: {
-		struct dp_rxdma_mon_ring *buf_ring = &ab->dp.rxdma_mon_buf_ring;
-		const struct dp_mon_packet_info *packet_info = tlv_data;
-		int buf_id = u32_get_bits(packet_info->cookie,
-					  DP_RXDMA_BUF_COOKIE_BUF_ID);
-		struct sk_buff *msdu;
-		struct dp_mon_mpdu *mon_mpdu = pmon->mon_mpdu;
-		struct ath12k_skb_rxcb *rxcb;
-
-		spin_lock_bh(&buf_ring->idr_lock);
-		msdu = idr_remove(&buf_ring->bufs_idr, buf_id);
-		spin_unlock_bh(&buf_ring->idr_lock);
-
-		if (unlikely(!msdu)) {
-			ath12k_warn(ab, "monitor destination with invalid buf_id %d\n",
-				    buf_id);
-			return HAL_RX_MON_STATUS_PPDU_NOT_DONE;
-		}
-
-		rxcb = ATH12K_SKB_RXCB(msdu);
-		dma_unmap_single(ab->dev, rxcb->paddr,
-				 msdu->len + skb_tailroom(msdu),
-				 DMA_FROM_DEVICE);
-
-		if (mon_mpdu->tail)
-			mon_mpdu->tail->next = msdu;
-		else
-			mon_mpdu->tail = msdu;
-
-		ath12k_dp_mon_buf_replenish(ab, buf_ring, 1);
-
-		break;
-	}
-	case HAL_RX_MSDU_END: {
-		const struct rx_msdu_end_qcn9274 *msdu_end = tlv_data;
-		bool is_first_msdu_in_mpdu;
-		u16 msdu_end_info;
-
-		msdu_end_info = __le16_to_cpu(msdu_end->info5);
-		is_first_msdu_in_mpdu = u32_get_bits(msdu_end_info,
-						     RX_MSDU_END_INFO5_FIRST_MSDU);
-		if (is_first_msdu_in_mpdu) {
-			pmon->mon_mpdu->head = pmon->mon_mpdu->tail;
-			pmon->mon_mpdu->tail = NULL;
-		}
-		break;
-	}
+	case HAL_MON_BUF_ADDR:
+		return HAL_RX_MON_STATUS_BUF_ADDR;
+	case HAL_RX_MSDU_END:
+		return HAL_RX_MON_STATUS_MSDU_END;
 	case HAL_RX_MPDU_END:
-		list_add_tail(&pmon->mon_mpdu->list, &pmon->dp_rx_mon_mpdu_list);
-		break;
+		return HAL_RX_MON_STATUS_MPDU_END;
 	case HAL_DUMMY:
 		return HAL_RX_MON_STATUS_BUF_DONE;
 	case HAL_RX_PPDU_END_STATUS_DONE:
@@ -1215,7 +1165,10 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 		if ((ptr - skb->data) >= DP_RX_BUFFER_SIZE)
 			break;
 
-	} while (hal_status == HAL_RX_MON_STATUS_PPDU_NOT_DONE);
+	} while ((hal_status == HAL_RX_MON_STATUS_PPDU_NOT_DONE) ||
+		 (hal_status == HAL_RX_MON_STATUS_BUF_ADDR) ||
+		 (hal_status == HAL_RX_MON_STATUS_MPDU_END) ||
+		 (hal_status == HAL_RX_MON_STATUS_MSDU_END));
 
 	return hal_status;
 }
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index b60c172d131b8..96954b2f7ca66 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -108,6 +108,9 @@ enum hal_rx_mon_status {
 	HAL_RX_MON_STATUS_PPDU_NOT_DONE,
 	HAL_RX_MON_STATUS_PPDU_DONE,
 	HAL_RX_MON_STATUS_BUF_DONE,
+	HAL_RX_MON_STATUS_BUF_ADDR,
+	HAL_RX_MON_STATUS_MPDU_END,
+	HAL_RX_MON_STATUS_MSDU_END,
 };
 
 #define HAL_RX_MAX_MPDU		256

From 3bcc4e830e05ed604bbba89c5415926df4ccabae Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:31 +0530
Subject: [PATCH 0040/2753] wifi: ath12k: Handle monitor drop TLVs scenario

During monitor destination ring back-pressure, hardware failed to send
HAL_RX_PPDU_END_STATUS_DONE TLV. But driver uses this TLV as a delimiter
to complete one PPDU worth of data parsing. This causes driver to overwrite
the existing PPDU information with the new PPDU information.

Fix it by recording the end reason which is provided under each buffer's
descriptor in skb->cb and uses it while parsing TLV tags to mark the PPDU
end delimiter.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-14-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h   | 1 +
 drivers/net/wireless/ath/ath12k/dp_mon.c | 9 ++++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 3d20a6b3b473a..28db100cfac06 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -142,6 +142,7 @@ struct ath12k_skb_rxcb {
 	u8 is_frag;
 	u8 tid;
 	u16 peer_id;
+	bool is_end_of_ppdu;
 };
 
 enum ath12k_hw_rev {
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 23b1a41c6fd2b..4e9a60181c067 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1139,6 +1139,7 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 			    struct sk_buff *skb)
 {
 	struct hal_tlv_64_hdr *tlv;
+	struct ath12k_skb_rxcb *rxcb;
 	enum hal_rx_mon_status hal_status;
 	u16 tlv_tag, tlv_len;
 	u8 *ptr = skb->data;
@@ -1170,6 +1171,10 @@ ath12k_dp_mon_parse_rx_dest(struct ath12k *ar, struct ath12k_mon_data *pmon,
 		 (hal_status == HAL_RX_MON_STATUS_MPDU_END) ||
 		 (hal_status == HAL_RX_MON_STATUS_MSDU_END));
 
+	rxcb = ATH12K_SKB_RXCB(skb);
+	if (rxcb->is_end_of_ppdu)
+		hal_status = HAL_RX_MON_STATUS_PPDU_DONE;
+
 	return hal_status;
 }
 
@@ -2345,8 +2350,10 @@ int ath12k_dp_mon_srng_process(struct ath12k *ar, int *budget,
 		 * HAL_MON_END_OF_PPDU to ensure that one PPDU worth of data is always
 		 * reaped. This helps to efficiently utilize the NAPI budget.
 		 */
-		if (end_reason == HAL_MON_END_OF_PPDU)
+		if (end_reason == HAL_MON_END_OF_PPDU) {
 			*budget -= 1;
+			rxcb->is_end_of_ppdu = true;
+		}
 
 		end_offset = u32_get_bits(info0, HAL_MON_DEST_INFO0_END_OFFSET);
 		if (likely(end_offset <= DP_RX_BUFFER_SIZE)) {

From 58b976e4f4b4d727eea27c0e40830853ef7ecf0e Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Mon, 23 Dec 2024 11:31:32 +0530
Subject: [PATCH 0041/2753] wifi: ath12k: Enable monitor ring mask for QCN9274

QCN9274's monitor related rings are initialized properly. Hence enabling
the corresponding ring mask in the hardware params.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Link: https://patch.msgid.link/20241223060132.3506372-15-quic_ppranees@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/hw.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
index 14bbd446ad370..a106ebed7870d 100644
--- a/drivers/net/wireless/ath/ath12k/hw.c
+++ b/drivers/net/wireless/ath/ath12k/hw.c
@@ -543,7 +543,11 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
 		ATH12K_TX_RING_MASK_3,
 	},
 	.rx_mon_dest = {
-		0, 0, 0,
+		0, 0, 0, 0,
+		0, 0, 0, 0,
+		ATH12K_RX_MON_RING_MASK_0,
+		ATH12K_RX_MON_RING_MASK_1,
+		ATH12K_RX_MON_RING_MASK_2,
 	},
 	.rx = {
 		0, 0, 0, 0,

From e50e30fa966e7f1ef407d5cdda22de629d64e82b Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sun, 19 Jan 2025 18:48:39 +0100
Subject: [PATCH 0042/2753] wifi: mwifiex: Constify struct mwifiex_if_ops

'struct mwifiex_if_ops' are not modified in these drivers.

Constifying these structures moves some data to a read-only section, so
increase overall security, especially when the structure holds some
function pointers.

On a x86_64, with allmodconfig, as an example:
Before:
======
   text	   data	    bss	    dec	    hex	filename
  61439	   4367	     32	  65838	  1012e	drivers/net/wireless/marvell/mwifiex/pcie.o

After:
=====
   text	   data	    bss	    dec	    hex	filename
  61699	   4127	     32	  65858	  10142	drivers/net/wireless/marvell/mwifiex/pcie.o

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/03d524b72f20a0302e4de5e0ebdc20ab69469dec.1737308889.git.christophe.jaillet@wanadoo.fr
---
 drivers/net/wireless/marvell/mwifiex/main.c | 4 ++--
 drivers/net/wireless/marvell/mwifiex/main.h | 2 +-
 drivers/net/wireless/marvell/mwifiex/pcie.c | 4 ++--
 drivers/net/wireless/marvell/mwifiex/sdio.c | 4 ++--
 drivers/net/wireless/marvell/mwifiex/usb.c  | 4 ++--
 5 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 855019fe54858..45eecb5f643b7 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -54,7 +54,7 @@ const u16 mwifiex_1d_to_wmm_queue[8] = { 1, 0, 0, 1, 2, 2, 3, 3 };
  * proper cleanup before exiting.
  */
 static int mwifiex_register(void *card, struct device *dev,
-			    struct mwifiex_if_ops *if_ops, void **padapter)
+			    const struct mwifiex_if_ops *if_ops, void **padapter)
 {
 	struct mwifiex_adapter *adapter;
 	int i;
@@ -1713,7 +1713,7 @@ static void mwifiex_probe_of(struct mwifiex_adapter *adapter)
  */
 int
 mwifiex_add_card(void *card, struct completion *fw_done,
-		 struct mwifiex_if_ops *if_ops, u8 iface_type,
+		 const struct mwifiex_if_ops *if_ops, u8 iface_type,
 		 struct device *dev)
 {
 	struct mwifiex_adapter *adapter;
diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index 0674dcf7a5374..fb15831201f74 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1470,7 +1470,7 @@ int mwifiex_init_shutdown_fw(struct mwifiex_private *priv,
 			     u32 func_init_shutdown);
 
 int mwifiex_add_card(void *card, struct completion *fw_done,
-		     struct mwifiex_if_ops *if_ops, u8 iface_type,
+		     const struct mwifiex_if_ops *if_ops, u8 iface_type,
 		     struct device *dev);
 int mwifiex_remove_card(struct mwifiex_adapter *adapter);
 
diff --git a/drivers/net/wireless/marvell/mwifiex/pcie.c b/drivers/net/wireless/marvell/mwifiex/pcie.c
index 5f997becdbaa2..e11458fd4d50f 100644
--- a/drivers/net/wireless/marvell/mwifiex/pcie.c
+++ b/drivers/net/wireless/marvell/mwifiex/pcie.c
@@ -21,7 +21,7 @@
 #define PCIE_VERSION	"1.0"
 #define DRV_NAME        "Marvell mwifiex PCIe"
 
-static struct mwifiex_if_ops pcie_ops;
+static const struct mwifiex_if_ops pcie_ops;
 
 static const struct mwifiex_pcie_card_reg mwifiex_reg_8766 = {
 	.cmd_addr_lo = PCIE_SCRATCH_0_REG,
@@ -3240,7 +3240,7 @@ static void mwifiex_pcie_down_dev(struct mwifiex_adapter *adapter)
 	mwifiex_pcie_free_buffers(adapter);
 }
 
-static struct mwifiex_if_ops pcie_ops = {
+static const struct mwifiex_if_ops pcie_ops = {
 	.init_if =			mwifiex_init_pcie,
 	.cleanup_if =			mwifiex_cleanup_pcie,
 	.check_fw_status =		mwifiex_check_fw_status,
diff --git a/drivers/net/wireless/marvell/mwifiex/sdio.c b/drivers/net/wireless/marvell/mwifiex/sdio.c
index 490ffd981164d..c1fe484488399 100644
--- a/drivers/net/wireless/marvell/mwifiex/sdio.c
+++ b/drivers/net/wireless/marvell/mwifiex/sdio.c
@@ -21,7 +21,7 @@
 
 static void mwifiex_sdio_work(struct work_struct *work);
 
-static struct mwifiex_if_ops sdio_ops;
+static const struct mwifiex_if_ops sdio_ops;
 
 static const struct mwifiex_sdio_card_reg mwifiex_reg_sd87xx = {
 	.start_rd_port = 1,
@@ -3167,7 +3167,7 @@ static void mwifiex_sdio_up_dev(struct mwifiex_adapter *adapter)
 		dev_err(&card->func->dev, "error enabling SDIO port\n");
 }
 
-static struct mwifiex_if_ops sdio_ops = {
+static const struct mwifiex_if_ops sdio_ops = {
 	.init_if = mwifiex_init_sdio,
 	.cleanup_if = mwifiex_cleanup_sdio,
 	.check_fw_status = mwifiex_check_fw_status,
diff --git a/drivers/net/wireless/marvell/mwifiex/usb.c b/drivers/net/wireless/marvell/mwifiex/usb.c
index 6085cd50970d4..3034c4405cb57 100644
--- a/drivers/net/wireless/marvell/mwifiex/usb.c
+++ b/drivers/net/wireless/marvell/mwifiex/usb.c
@@ -10,7 +10,7 @@
 
 #define USB_VERSION	"1.0"
 
-static struct mwifiex_if_ops usb_ops;
+static const struct mwifiex_if_ops usb_ops;
 
 static const struct usb_device_id mwifiex_usb_table[] = {
 	/* 8766 */
@@ -1585,7 +1585,7 @@ mwifiex_pm_wakeup_card_complete(struct mwifiex_adapter *adapter)
 	return 0;
 }
 
-static struct mwifiex_if_ops usb_ops = {
+static const struct mwifiex_if_ops usb_ops = {
 	.register_dev =		mwifiex_register_dev,
 	.unregister_dev =	mwifiex_unregister_dev,
 	.wakeup =		mwifiex_pm_wakeup_card,

From d5b66511fd35d3fd551b4e34ded103c83c3484d5 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 21 Jan 2025 01:32:58 +0000
Subject: [PATCH 0043/2753] wifi: libertas: main: remove unused functions

lbs_data_rate_to_fw_index(), lbs_enter_auto_deep_sleep() and
lbs_exit_auto_deep_sleep() last use was removed in 2010 by
commit e86dc1ca4676 ("Libertas: cfg80211 support").

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20250121013300.433538-2-linux@treblig.org
---
 drivers/net/wireless/marvell/libertas/decl.h |  4 --
 drivers/net/wireless/marvell/libertas/main.c | 40 --------------------
 2 files changed, 44 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/decl.h b/drivers/net/wireless/marvell/libertas/decl.h
index c1e0388ef01da..ea69007a29584 100644
--- a/drivers/net/wireless/marvell/libertas/decl.h
+++ b/drivers/net/wireless/marvell/libertas/decl.h
@@ -64,11 +64,7 @@ int lbs_resume(struct lbs_private *priv);
 void lbs_queue_event(struct lbs_private *priv, u32 event);
 void lbs_notify_command_response(struct lbs_private *priv, u8 resp_idx);
 
-int lbs_enter_auto_deep_sleep(struct lbs_private *priv);
-int lbs_exit_auto_deep_sleep(struct lbs_private *priv);
-
 u32 lbs_fw_index_to_data_rate(u8 index);
-u8 lbs_data_rate_to_fw_index(u32 rate);
 
 int lbs_get_firmware(struct device *dev, u32 card_model,
 			const struct lbs_fw_table *fw_table,
diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c
index 78e8b5aecec0e..e7fa27a7de816 100644
--- a/drivers/net/wireless/marvell/libertas/main.c
+++ b/drivers/net/wireless/marvell/libertas/main.c
@@ -79,26 +79,6 @@ u32 lbs_fw_index_to_data_rate(u8 idx)
 	return fw_data_rates[idx];
 }
 
-/**
- *  lbs_data_rate_to_fw_index - use rate to get the index
- *
- *  @rate:	data rate
- *  returns:	index or 0
- */
-u8 lbs_data_rate_to_fw_index(u32 rate)
-{
-	u8 i;
-
-	if (!rate)
-		return 0;
-
-	for (i = 0; i < sizeof(fw_data_rates); i++) {
-		if (rate == fw_data_rates[i])
-			return i;
-	}
-	return 0;
-}
-
 int lbs_set_iface_type(struct lbs_private *priv, enum nl80211_iftype type)
 {
 	int ret = 0;
@@ -802,26 +782,6 @@ static void auto_deepsleep_timer_fn(struct timer_list *t)
 				(priv->auto_deep_sleep_timeout * HZ)/1000);
 }
 
-int lbs_enter_auto_deep_sleep(struct lbs_private *priv)
-{
-	priv->is_auto_deep_sleep_enabled = 1;
-	if (priv->is_deep_sleep)
-		priv->wakeup_dev_required = 1;
-	mod_timer(&priv->auto_deepsleep_timer ,
-			jiffies + (priv->auto_deep_sleep_timeout * HZ)/1000);
-
-	return 0;
-}
-
-int lbs_exit_auto_deep_sleep(struct lbs_private *priv)
-{
-	priv->is_auto_deep_sleep_enabled = 0;
-	priv->auto_deep_sleep_timeout = 0;
-	del_timer(&priv->auto_deepsleep_timer);
-
-	return 0;
-}
-
 static int lbs_init_adapter(struct lbs_private *priv)
 {
 	int ret;

From 5a7148ba1806008cb9f99fb099b6259c80a0dce6 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 21 Jan 2025 01:32:59 +0000
Subject: [PATCH 0044/2753] wifi: libertas: cmd: remove unused functions

lbs_get_snmp_mib(), lbs_set_power_adapt_cfg(), lbs_set_tpc_cfg()
and lbs_set_tx_power() have been unused since 2010's
commit e86dc1ca4676 ("Libertas: cfg80211 support").

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20250121013300.433538-3-linux@treblig.org
---
 drivers/net/wireless/marvell/libertas/cmd.c | 129 --------------------
 drivers/net/wireless/marvell/libertas/cmd.h |  10 --
 2 files changed, 139 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/cmd.c b/drivers/net/wireless/marvell/libertas/cmd.c
index 5a525da434c28..4032bbd28acd0 100644
--- a/drivers/net/wireless/marvell/libertas/cmd.c
+++ b/drivers/net/wireless/marvell/libertas/cmd.c
@@ -452,46 +452,6 @@ int lbs_set_snmp_mib(struct lbs_private *priv, u32 oid, u16 val)
 	return ret;
 }
 
-/**
- *  lbs_get_snmp_mib - Get an SNMP MIB value
- *
- *  @priv:	A pointer to &struct lbs_private structure
- *  @oid:	The OID to retrieve from the firmware
- *  @out_val:	Location for the returned value
- *
- *  returns:	0 on success, error on failure
- */
-int lbs_get_snmp_mib(struct lbs_private *priv, u32 oid, u16 *out_val)
-{
-	struct cmd_ds_802_11_snmp_mib cmd;
-	int ret;
-
-	memset(&cmd, 0, sizeof (cmd));
-	cmd.hdr.size = cpu_to_le16(sizeof(cmd));
-	cmd.action = cpu_to_le16(CMD_ACT_GET);
-	cmd.oid = cpu_to_le16(oid);
-
-	ret = lbs_cmd_with_response(priv, CMD_802_11_SNMP_MIB, &cmd);
-	if (ret)
-		goto out;
-
-	switch (le16_to_cpu(cmd.bufsize)) {
-	case sizeof(u8):
-		*out_val = cmd.value[0];
-		break;
-	case sizeof(u16):
-		*out_val = le16_to_cpu(*((__le16 *)(&cmd.value)));
-		break;
-	default:
-		lbs_deb_cmd("SNMP_CMD: (get) unhandled OID 0x%x size %d\n",
-		            oid, le16_to_cpu(cmd.bufsize));
-		break;
-	}
-
-out:
-	return ret;
-}
-
 /**
  *  lbs_get_tx_power - Get the min, max, and current TX power
  *
@@ -524,31 +484,6 @@ int lbs_get_tx_power(struct lbs_private *priv, s16 *curlevel, s16 *minlevel,
 	return ret;
 }
 
-/**
- *  lbs_set_tx_power - Set the TX power
- *
- *  @priv:	A pointer to &struct lbs_private structure
- *  @dbm:	The desired power level in dBm
- *
- *  returns: 	   	0 on success, error on failure
- */
-int lbs_set_tx_power(struct lbs_private *priv, s16 dbm)
-{
-	struct cmd_ds_802_11_rf_tx_power cmd;
-	int ret;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.hdr.size = cpu_to_le16(sizeof(cmd));
-	cmd.action = cpu_to_le16(CMD_ACT_SET);
-	cmd.curlevel = cpu_to_le16(dbm);
-
-	lbs_deb_cmd("SET_RF_TX_POWER: %d dBm\n", dbm);
-
-	ret = lbs_cmd_with_response(priv, CMD_802_11_RF_TX_POWER, &cmd);
-
-	return ret;
-}
-
 /**
  *  lbs_set_monitor_mode - Enable or disable monitor mode
  *  (only implemented on OLPC usb8388 FW)
@@ -1440,70 +1375,6 @@ void lbs_ps_confirm_sleep(struct lbs_private *priv)
 }
 
 
-/**
- * lbs_set_tpc_cfg - Configures the transmission power control functionality
- *
- * @priv:	A pointer to &struct lbs_private structure
- * @enable:	Transmission power control enable
- * @p0:		Power level when link quality is good (dBm).
- * @p1:		Power level when link quality is fair (dBm).
- * @p2:		Power level when link quality is poor (dBm).
- * @usesnr:	Use Signal to Noise Ratio in TPC
- *
- * returns:	0 on success
- */
-int lbs_set_tpc_cfg(struct lbs_private *priv, int enable, int8_t p0, int8_t p1,
-		int8_t p2, int usesnr)
-{
-	struct cmd_ds_802_11_tpc_cfg cmd;
-	int ret;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.hdr.size = cpu_to_le16(sizeof(cmd));
-	cmd.action = cpu_to_le16(CMD_ACT_SET);
-	cmd.enable = !!enable;
-	cmd.usesnr = !!usesnr;
-	cmd.P0 = p0;
-	cmd.P1 = p1;
-	cmd.P2 = p2;
-
-	ret = lbs_cmd_with_response(priv, CMD_802_11_TPC_CFG, &cmd);
-
-	return ret;
-}
-
-/**
- * lbs_set_power_adapt_cfg - Configures the power adaptation settings
- *
- * @priv:	A pointer to &struct lbs_private structure
- * @enable:	Power adaptation enable
- * @p0:		Power level for 1, 2, 5.5 and 11 Mbps (dBm).
- * @p1:		Power level for 6, 9, 12, 18, 22, 24 and 36 Mbps (dBm).
- * @p2:		Power level for 48 and 54 Mbps (dBm).
- *
- * returns:	0 on Success
- */
-
-int lbs_set_power_adapt_cfg(struct lbs_private *priv, int enable, int8_t p0,
-		int8_t p1, int8_t p2)
-{
-	struct cmd_ds_802_11_pa_cfg cmd;
-	int ret;
-
-	memset(&cmd, 0, sizeof(cmd));
-	cmd.hdr.size = cpu_to_le16(sizeof(cmd));
-	cmd.action = cpu_to_le16(CMD_ACT_SET);
-	cmd.enable = !!enable;
-	cmd.P0 = p0;
-	cmd.P1 = p1;
-	cmd.P2 = p2;
-
-	ret = lbs_cmd_with_response(priv, CMD_802_11_PA_CFG , &cmd);
-
-	return ret;
-}
-
-
 struct cmd_ctrl_node *__lbs_cmd_async(struct lbs_private *priv,
 	uint16_t command, struct cmd_header *in_cmd, int in_cmd_size,
 	int (*callback)(struct lbs_private *, unsigned long, struct cmd_header *),
diff --git a/drivers/net/wireless/marvell/libertas/cmd.h b/drivers/net/wireless/marvell/libertas/cmd.h
index d7be232f57394..a95c2651e67f6 100644
--- a/drivers/net/wireless/marvell/libertas/cmd.h
+++ b/drivers/net/wireless/marvell/libertas/cmd.h
@@ -105,19 +105,9 @@ int lbs_get_tx_power(struct lbs_private *priv, s16 *curlevel, s16 *minlevel,
 
 int lbs_set_snmp_mib(struct lbs_private *priv, u32 oid, u16 val);
 
-int lbs_get_snmp_mib(struct lbs_private *priv, u32 oid, u16 *out_val);
-
 
 /* Commands only used in wext.c, assoc. and scan.c */
 
-int lbs_set_power_adapt_cfg(struct lbs_private *priv, int enable, int8_t p0,
-		int8_t p1, int8_t p2);
-
-int lbs_set_tpc_cfg(struct lbs_private *priv, int enable, int8_t p0, int8_t p1,
-		int8_t p2, int usesnr);
-
-int lbs_set_tx_power(struct lbs_private *priv, s16 dbm);
-
 int lbs_set_deep_sleep(struct lbs_private *priv, int deep_sleep);
 
 int lbs_set_host_sleep(struct lbs_private *priv, int host_sleep);

From 107c2be8ddf42e8eff2fba7ede76ef3f1771301e Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 21 Jan 2025 01:33:00 +0000
Subject: [PATCH 0045/2753] wifi: libertas: Remove unused auto deep sleep code

With the recent removal of the uncalled
  lbs_(enter|exit)_auto_deep_sleep()
functions, it's no longer possible to set
  priv->is_auto_deep_sleep_enabled
so we can remove all tests of it and the variable itself.

With that gone, priv->wakeup_dev_required also doesn't
get set, so we can remove any testing of it.

Now the timer itself, and the function it calls goes.
The timer used the apparently unset auto_deep_sleep_timeout
member, which can also go.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20250121013300.433538-4-linux@treblig.org
---
 drivers/net/wireless/marvell/libertas/cmd.c   | 14 ++----
 .../net/wireless/marvell/libertas/cmdresp.c   |  1 -
 drivers/net/wireless/marvell/libertas/dev.h   |  4 --
 drivers/net/wireless/marvell/libertas/main.c  | 48 +------------------
 4 files changed, 6 insertions(+), 61 deletions(-)

diff --git a/drivers/net/wireless/marvell/libertas/cmd.c b/drivers/net/wireless/marvell/libertas/cmd.c
index 4032bbd28acd0..21fde876bb0de 100644
--- a/drivers/net/wireless/marvell/libertas/cmd.c
+++ b/drivers/net/wireless/marvell/libertas/cmd.c
@@ -903,10 +903,6 @@ static void lbs_submit_command(struct lbs_private *priv,
 	}
 
 	if (command == CMD_802_11_DEEP_SLEEP) {
-		if (priv->is_auto_deep_sleep_enabled) {
-			priv->wakeup_dev_required = 1;
-			priv->dnld_sent = 0;
-		}
 		priv->is_deep_sleep = 1;
 		lbs_complete_command(priv, cmdnode, 0);
 	} else {
@@ -1391,12 +1387,10 @@ struct cmd_ctrl_node *__lbs_cmd_async(struct lbs_private *priv,
 	/* No commands are allowed in Deep Sleep until we toggle the GPIO
 	 * to wake up the card and it has signaled that it's ready.
 	 */
-	if (!priv->is_auto_deep_sleep_enabled) {
-		if (priv->is_deep_sleep) {
-			lbs_deb_cmd("command not allowed in deep sleep\n");
-			cmdnode = ERR_PTR(-EBUSY);
-			goto done;
-		}
+	if (priv->is_deep_sleep) {
+		lbs_deb_cmd("command not allowed in deep sleep\n");
+		cmdnode = ERR_PTR(-EBUSY);
+		goto done;
 	}
 
 	cmdnode = lbs_get_free_cmd_node(priv);
diff --git a/drivers/net/wireless/marvell/libertas/cmdresp.c b/drivers/net/wireless/marvell/libertas/cmdresp.c
index f2aa659e77148..8393f396eebee 100644
--- a/drivers/net/wireless/marvell/libertas/cmdresp.c
+++ b/drivers/net/wireless/marvell/libertas/cmdresp.c
@@ -279,7 +279,6 @@ void lbs_process_event(struct lbs_private *priv, u32 event)
 			priv->reset_deep_sleep_wakeup(priv);
 		lbs_deb_cmd("EVENT: ds awake\n");
 		priv->is_deep_sleep = 0;
-		priv->wakeup_dev_required = 0;
 		wake_up_interruptible(&priv->ds_awake_q);
 		break;
 
diff --git a/drivers/net/wireless/marvell/libertas/dev.h b/drivers/net/wireless/marvell/libertas/dev.h
index 4b6e05a8e5d54..c4708ce4eb835 100644
--- a/drivers/net/wireless/marvell/libertas/dev.h
+++ b/drivers/net/wireless/marvell/libertas/dev.h
@@ -83,12 +83,8 @@ struct lbs_private {
 	/* Deep sleep */
 	int is_deep_sleep;
 	int deep_sleep_required;
-	int is_auto_deep_sleep_enabled;
-	int wakeup_dev_required;
 	int is_activity_detected;
-	int auto_deep_sleep_timeout; /* in ms */
 	wait_queue_head_t ds_awake_q;
-	struct timer_list auto_deepsleep_timer;
 
 	/* Host sleep*/
 	int is_host_sleep_configured;
diff --git a/drivers/net/wireless/marvell/libertas/main.c b/drivers/net/wireless/marvell/libertas/main.c
index e7fa27a7de816..017e5c6bbade5 100644
--- a/drivers/net/wireless/marvell/libertas/main.c
+++ b/drivers/net/wireless/marvell/libertas/main.c
@@ -256,8 +256,7 @@ void lbs_host_to_card_done(struct lbs_private *priv)
 
 	/* Wake main thread if commands are pending */
 	if (!priv->cur_cmd || priv->tx_pending_len > 0) {
-		if (!priv->wakeup_dev_required)
-			wake_up(&priv->waitq);
+		wake_up(&priv->waitq);
 	}
 
 	spin_unlock_irqrestore(&priv->driver_lock, flags);
@@ -448,8 +447,7 @@ static int lbs_thread(void *data)
 			shouldsleep = 0;	/* We have a command response */
 		else if (priv->cur_cmd)
 			shouldsleep = 1;	/* Can't send a command; one already running */
-		else if (!list_empty(&priv->cmdpendingq) &&
-					!(priv->wakeup_dev_required))
+		else if (!list_empty(&priv->cmdpendingq))
 			shouldsleep = 0;	/* We have a command to send */
 		else if (kfifo_len(&priv->event_fifo))
 			shouldsleep = 0;	/* We have an event to process */
@@ -516,14 +514,6 @@ static int lbs_thread(void *data)
 		}
 		spin_unlock_irq(&priv->driver_lock);
 
-		if (priv->wakeup_dev_required) {
-			lbs_deb_thread("Waking up device...\n");
-			/* Wake up device */
-			if (priv->exit_deep_sleep(priv))
-				lbs_deb_thread("Wakeup device failed\n");
-			continue;
-		}
-
 		/* command timeout stuff */
 		if (priv->cmd_timed_out && priv->cur_cmd) {
 			struct cmd_ctrl_node *cmdnode = priv->cur_cmd;
@@ -606,7 +596,6 @@ static int lbs_thread(void *data)
 
 	del_timer(&priv->command_timer);
 	del_timer(&priv->tx_lockup_timer);
-	del_timer(&priv->auto_deepsleep_timer);
 
 	return 0;
 }
@@ -753,35 +742,6 @@ static void lbs_tx_lockup_handler(struct timer_list *t)
 	spin_unlock_irqrestore(&priv->driver_lock, flags);
 }
 
-/**
- * auto_deepsleep_timer_fn - put the device back to deep sleep mode when
- * timer expires and no activity (command, event, data etc.) is detected.
- * @t: Context from which to retrieve a &struct lbs_private pointer
- * returns:	N/A
- */
-static void auto_deepsleep_timer_fn(struct timer_list *t)
-{
-	struct lbs_private *priv = from_timer(priv, t, auto_deepsleep_timer);
-
-	if (priv->is_activity_detected) {
-		priv->is_activity_detected = 0;
-	} else {
-		if (priv->is_auto_deep_sleep_enabled &&
-		    (!priv->wakeup_dev_required) &&
-		    (priv->connect_status != LBS_CONNECTED)) {
-			struct cmd_header cmd;
-
-			lbs_deb_main("Entering auto deep sleep mode...\n");
-			memset(&cmd, 0, sizeof(cmd));
-			cmd.size = cpu_to_le16(sizeof(cmd));
-			lbs_cmd_async(priv, CMD_802_11_DEEP_SLEEP, &cmd,
-					sizeof(cmd));
-		}
-	}
-	mod_timer(&priv->auto_deepsleep_timer , jiffies +
-				(priv->auto_deep_sleep_timeout * HZ)/1000);
-}
-
 static int lbs_init_adapter(struct lbs_private *priv)
 {
 	int ret;
@@ -795,9 +755,7 @@ static int lbs_init_adapter(struct lbs_private *priv)
 	priv->psmode = LBS802_11POWERMODECAM;
 	priv->psstate = PS_STATE_FULL_POWER;
 	priv->is_deep_sleep = 0;
-	priv->is_auto_deep_sleep_enabled = 0;
 	priv->deep_sleep_required = 0;
-	priv->wakeup_dev_required = 0;
 	init_waitqueue_head(&priv->ds_awake_q);
 	init_waitqueue_head(&priv->scan_q);
 	priv->authtype_auto = 1;
@@ -809,7 +767,6 @@ static int lbs_init_adapter(struct lbs_private *priv)
 
 	timer_setup(&priv->command_timer, lbs_cmd_timeout_handler, 0);
 	timer_setup(&priv->tx_lockup_timer, lbs_tx_lockup_handler, 0);
-	timer_setup(&priv->auto_deepsleep_timer, auto_deepsleep_timer_fn, 0);
 
 	INIT_LIST_HEAD(&priv->cmdfreeq);
 	INIT_LIST_HEAD(&priv->cmdpendingq);
@@ -843,7 +800,6 @@ static void lbs_free_adapter(struct lbs_private *priv)
 	kfifo_free(&priv->event_fifo);
 	del_timer(&priv->command_timer);
 	del_timer(&priv->tx_lockup_timer);
-	del_timer(&priv->auto_deepsleep_timer);
 }
 
 static const struct net_device_ops lbs_netdev_ops = {

From 22f3551b60be7d126db9233998d262edfc577d0b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Wed, 22 Jan 2025 02:22:40 +0000
Subject: [PATCH 0046/2753] wifi: ipw2x00: Remove unused libipw_rx_any()

libipw_rx_any() was added in 2006 by commit 1a995b45a528 ("[PATCH]
ieee80211_rx_any: filter out packets, call ieee80211_rx or ieee80211_rx_mgt")
as ieee80211_rx_any but is currently unused and I can't find any sign it was
used under either name.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://patch.msgid.link/20250122022240.456198-1-linux@treblig.org
---
 drivers/net/wireless/intel/ipw2x00/libipw.h   |  2 -
 .../net/wireless/intel/ipw2x00/libipw_rx.c    | 91 -------------------
 2 files changed, 93 deletions(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/libipw.h b/drivers/net/wireless/intel/ipw2x00/libipw.h
index 3c20353e5a412..e031e8692ca64 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw.h
+++ b/drivers/net/wireless/intel/ipw2x00/libipw.h
@@ -1011,8 +1011,6 @@ netdev_tx_t libipw_xmit(struct sk_buff *skb, struct net_device *dev);
 void libipw_txb_free(struct libipw_txb *);
 
 /* libipw_rx.c */
-void libipw_rx_any(struct libipw_device *ieee, struct sk_buff *skb,
-		   struct libipw_rx_stats *stats);
 int libipw_rx(struct libipw_device *ieee, struct sk_buff *skb,
 	      struct libipw_rx_stats *rx_stats);
 /* make sure to set stats->len */
diff --git a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
index dc4e91f58bb4a..b7bc94f7abd8a 100644
--- a/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
+++ b/drivers/net/wireless/intel/ipw2x00/libipw_rx.c
@@ -823,96 +823,6 @@ int libipw_rx(struct libipw_device *ieee, struct sk_buff *skb,
 	return 0;
 }
 
-/* Filter out unrelated packets, call libipw_rx[_mgt]
- * This function takes over the skb, it should not be used again after calling
- * this function. */
-void libipw_rx_any(struct libipw_device *ieee,
-		     struct sk_buff *skb, struct libipw_rx_stats *stats)
-{
-	struct libipw_hdr_4addr *hdr;
-	int is_packet_for_us;
-	u16 fc;
-
-	if (ieee->iw_mode == IW_MODE_MONITOR) {
-		if (!libipw_rx(ieee, skb, stats))
-			dev_kfree_skb_irq(skb);
-		return;
-	}
-
-	if (skb->len < sizeof(struct ieee80211_hdr))
-		goto drop_free;
-
-	hdr = (struct libipw_hdr_4addr *)skb->data;
-	fc = le16_to_cpu(hdr->frame_ctl);
-
-	if ((fc & IEEE80211_FCTL_VERS) != 0)
-		goto drop_free;
-
-	switch (fc & IEEE80211_FCTL_FTYPE) {
-	case IEEE80211_FTYPE_MGMT:
-		if (skb->len < sizeof(struct libipw_hdr_3addr))
-			goto drop_free;
-		libipw_rx_mgt(ieee, hdr, stats);
-		dev_kfree_skb_irq(skb);
-		return;
-	case IEEE80211_FTYPE_DATA:
-		break;
-	case IEEE80211_FTYPE_CTL:
-		return;
-	default:
-		return;
-	}
-
-	is_packet_for_us = 0;
-	switch (ieee->iw_mode) {
-	case IW_MODE_ADHOC:
-		/* our BSS and not from/to DS */
-		if (ether_addr_equal(hdr->addr3, ieee->bssid) &&
-		    ((fc & (IEEE80211_FCTL_TODS + IEEE80211_FCTL_FROMDS)) == 0)) {
-			/* promisc: get all */
-			if (ieee->dev->flags & IFF_PROMISC)
-				is_packet_for_us = 1;
-			/* to us */
-			else if (ether_addr_equal(hdr->addr1, ieee->dev->dev_addr))
-				is_packet_for_us = 1;
-			/* mcast */
-			else if (is_multicast_ether_addr(hdr->addr1))
-				is_packet_for_us = 1;
-		}
-		break;
-	case IW_MODE_INFRA:
-		/* our BSS (== from our AP) and from DS */
-		if (ether_addr_equal(hdr->addr2, ieee->bssid) &&
-		    ((fc & (IEEE80211_FCTL_TODS + IEEE80211_FCTL_FROMDS)) == IEEE80211_FCTL_FROMDS)) {
-			/* promisc: get all */
-			if (ieee->dev->flags & IFF_PROMISC)
-				is_packet_for_us = 1;
-			/* to us */
-			else if (ether_addr_equal(hdr->addr1, ieee->dev->dev_addr))
-				is_packet_for_us = 1;
-			/* mcast */
-			else if (is_multicast_ether_addr(hdr->addr1)) {
-				/* not our own packet bcasted from AP */
-				if (!ether_addr_equal(hdr->addr3, ieee->dev->dev_addr))
-					is_packet_for_us = 1;
-			}
-		}
-		break;
-	default:
-		/* ? */
-		break;
-	}
-
-	if (is_packet_for_us)
-		if (!libipw_rx(ieee, skb, stats))
-			dev_kfree_skb_irq(skb);
-	return;
-
-drop_free:
-	dev_kfree_skb_irq(skb);
-	ieee->dev->stats.rx_dropped++;
-}
-
 #define MGMT_FRAME_FIXED_PART_LENGTH		0x24
 
 static u8 qos_oui[QOS_OUI_LEN] = { 0x00, 0x50, 0xF2 };
@@ -1729,6 +1639,5 @@ void libipw_rx_mgt(struct libipw_device *ieee,
 	}
 }
 
-EXPORT_SYMBOL_GPL(libipw_rx_any);
 EXPORT_SYMBOL(libipw_rx_mgt);
 EXPORT_SYMBOL(libipw_rx);

From b9a49520679e98700d3d89689cc91c08a1c88c1d Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Sun, 19 Jan 2025 00:55:32 +0100
Subject: [PATCH 0047/2753] rcuref: Plug slowpath race in rcuref_put()

Kernel test robot reported an "imbalanced put" in the rcuref_put() slow
path, which turned out to be a false positive. Consider the following race:

            ref  = 0 (via rcuref_init(ref, 1))
 T1                                      T2
 rcuref_put(ref)
 -> atomic_add_negative_release(-1, ref)                                         # ref -> 0xffffffff
 -> rcuref_put_slowpath(ref)
                                         rcuref_get(ref)
                                         -> atomic_add_negative_relaxed(1, &ref->refcnt)
                                           -> return true;                       # ref -> 0

                                         rcuref_put(ref)
                                         -> atomic_add_negative_release(-1, ref) # ref -> 0xffffffff
                                         -> rcuref_put_slowpath()

    -> cnt = atomic_read(&ref->refcnt);                                          # cnt -> 0xffffffff / RCUREF_NOREF
    -> atomic_try_cmpxchg_release(&ref->refcnt, &cnt, RCUREF_DEAD))              # ref -> 0xe0000000 / RCUREF_DEAD
       -> return true
                                           -> cnt = atomic_read(&ref->refcnt);   # cnt -> 0xe0000000 / RCUREF_DEAD
                                           -> if (cnt > RCUREF_RELEASED)         # 0xe0000000 > 0xc0000000
                                             -> WARN_ONCE(cnt >= RCUREF_RELEASED, "rcuref - imbalanced put()")

The problem is the additional read in the slow path (after it
decremented to RCUREF_NOREF) which can happen after the counter has been
marked RCUREF_DEAD.

Prevent this by reusing the return value of the decrement. Now every "final"
put uses RCUREF_NOREF in the slow path and attempts the final cmpxchg() to
RCUREF_DEAD.

[ bigeasy: Add changelog ]

Fixes: ee1ee6db07795 ("atomics: Provide rcuref - scalable reference counting")
Reported-by: kernel test robot <oliver.sang@intel.com>
Debugged-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: stable@vger.kernel.org
Closes: https://lore.kernel.org/oe-lkp/202412311453.9d7636a2-lkp@intel.com
---
 include/linux/rcuref.h | 9 ++++++---
 lib/rcuref.c           | 5 ++---
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/linux/rcuref.h b/include/linux/rcuref.h
index 2c8bfd0f1b6b3..6322d8c1c6b42 100644
--- a/include/linux/rcuref.h
+++ b/include/linux/rcuref.h
@@ -71,27 +71,30 @@ static inline __must_check bool rcuref_get(rcuref_t *ref)
 	return rcuref_get_slowpath(ref);
 }
 
-extern __must_check bool rcuref_put_slowpath(rcuref_t *ref);
+extern __must_check bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt);
 
 /*
  * Internal helper. Do not invoke directly.
  */
 static __always_inline __must_check bool __rcuref_put(rcuref_t *ref)
 {
+	int cnt;
+
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() && preemptible(),
 			 "suspicious rcuref_put_rcusafe() usage");
 	/*
 	 * Unconditionally decrease the reference count. The saturation and
 	 * dead zones provide enough tolerance for this.
 	 */
-	if (likely(!atomic_add_negative_release(-1, &ref->refcnt)))
+	cnt = atomic_sub_return_release(1, &ref->refcnt);
+	if (likely(cnt >= 0))
 		return false;
 
 	/*
 	 * Handle the last reference drop and cases inside the saturation
 	 * and dead zones.
 	 */
-	return rcuref_put_slowpath(ref);
+	return rcuref_put_slowpath(ref, cnt);
 }
 
 /**
diff --git a/lib/rcuref.c b/lib/rcuref.c
index 97f300eca927c..5bd726b71e393 100644
--- a/lib/rcuref.c
+++ b/lib/rcuref.c
@@ -220,6 +220,7 @@ EXPORT_SYMBOL_GPL(rcuref_get_slowpath);
 /**
  * rcuref_put_slowpath - Slowpath of __rcuref_put()
  * @ref:	Pointer to the reference count
+ * @cnt:	The resulting value of the fastpath decrement
  *
  * Invoked when the reference count is outside of the valid zone.
  *
@@ -233,10 +234,8 @@ EXPORT_SYMBOL_GPL(rcuref_get_slowpath);
  *	with a concurrent get()/put() pair. Caller is not allowed to
  *	deconstruct the protected object.
  */
-bool rcuref_put_slowpath(rcuref_t *ref)
+bool rcuref_put_slowpath(rcuref_t *ref, unsigned int cnt)
 {
-	unsigned int cnt = atomic_read(&ref->refcnt);
-
 	/* Did this drop the last reference? */
 	if (likely(cnt == RCUREF_NOREF)) {
 		/*

From 24f587572acf7509127dbdfcbf1b681ef84eeba0 Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Thu, 16 Jan 2025 08:58:35 +0530
Subject: [PATCH 0048/2753] wifi: ath12k: Fetch regdb.bin file from board-2.bin

Currently, ath12k_core_fetch_regdb() finds regdb.bin file through
board id's but in board-2.bin file regdb.bin file is present with
default board id because of which regdb.bin is not fetched.

Add support to fetch regdb.bin file from board-2.bin through
default board id.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250116032835.118397-1-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 2dd0666959cd4..60c077b016b40 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -177,7 +177,7 @@ EXPORT_SYMBOL(ath12k_core_resume);
 
 static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 					   size_t name_len, bool with_variant,
-					   bool bus_type_mode)
+					   bool bus_type_mode, bool with_default)
 {
 	/* strlen(',variant=') + strlen(ab->qmi.target.bdf_ext) */
 	char variant[9 + ATH12K_QMI_BDF_EXT_STR_LENGTH] = { 0 };
@@ -208,7 +208,9 @@ static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 			  "bus=%s,qmi-chip-id=%d,qmi-board-id=%d%s",
 			  ath12k_bus_str(ab->hif.bus),
 			  ab->qmi.target.chip_id,
-			  ab->qmi.target.board_id, variant);
+			  with_default ?
+			  ATH12K_BOARD_ID_DEFAULT : ab->qmi.target.board_id,
+			  variant);
 		break;
 	}
 
@@ -220,19 +222,19 @@ static int __ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 static int ath12k_core_create_board_name(struct ath12k_base *ab, char *name,
 					 size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, true, false);
+	return __ath12k_core_create_board_name(ab, name, name_len, true, false, false);
 }
 
 static int ath12k_core_create_fallback_board_name(struct ath12k_base *ab, char *name,
 						  size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, false, false);
+	return __ath12k_core_create_board_name(ab, name, name_len, false, false, true);
 }
 
 static int ath12k_core_create_bus_type_board_name(struct ath12k_base *ab, char *name,
 						  size_t name_len)
 {
-	return __ath12k_core_create_board_name(ab, name, name_len, false, true);
+	return __ath12k_core_create_board_name(ab, name, name_len, false, true, true);
 }
 
 const struct firmware *ath12k_core_firmware_request(struct ath12k_base *ab,

From dfffb317519f88534bb82797f055f0a2fd867e7b Mon Sep 17 00:00:00 2001
From: Rosen Penev <rosenp@gmail.com>
Date: Tue, 5 Nov 2024 14:23:26 -0800
Subject: [PATCH 0049/2753] wifi: ath9k: return by of_get_mac_address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When using nvmem, ath9k could potentially be loaded before nvmem, which
loads after mtd. This is an issue if DT contains an nvmem mac address.

If nvmem is not ready in time for ath9k, -EPROBE_DEFER is returned. Pass
it to _probe so that ath9k can properly grab a potentially present MAC
address.

Signed-off-by: Rosen Penev <rosenp@gmail.com>
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20241105222326.194417-1-rosenp@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath9k/init.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c
index f9e77c4624d99..01e0dffbf57ed 100644
--- a/drivers/net/wireless/ath/ath9k/init.c
+++ b/drivers/net/wireless/ath/ath9k/init.c
@@ -647,7 +647,9 @@ static int ath9k_of_init(struct ath_softc *sc)
 		ah->ah_flags |= AH_NO_EEP_SWAP;
 	}
 
-	of_get_mac_address(np, common->macaddr);
+	ret = of_get_mac_address(np, common->macaddr);
+	if (ret == -EPROBE_DEFER)
+		return ret;
 
 	return 0;
 }

From 0f2b59a98027a781eee1cbd48c7c8fdf87cb73f6 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 23 Jan 2025 17:10:58 +0300
Subject: [PATCH 0050/2753] wifi: ath9k: do not submit zero bytes to the
 entropy pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In 'ath_cmn_process_fft()', it doesn't make too much sense to
add zero bytes in attempt to improve randomness. So swap calls
to 'memset()' and 'add_device_randomness()' to feed the pool
with actual FFT results rather than zeroes. Compile tested only.

Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Fixes: 2aa56cca3571 ("ath9k: Mix the received FFT bins to the random pool")
Acked-by: Toke Høiland-Jørgensen <toke@toke.dk>
Link: https://patch.msgid.link/20250123141058.1696502-1-dmantipov@yandex.ru
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath9k/common-spectral.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath9k/common-spectral.c b/drivers/net/wireless/ath/ath9k/common-spectral.c
index 628eeec4b82fe..300d178830adf 100644
--- a/drivers/net/wireless/ath/ath9k/common-spectral.c
+++ b/drivers/net/wireless/ath/ath9k/common-spectral.c
@@ -628,12 +628,12 @@ int ath_cmn_process_fft(struct ath_spec_scan_priv *spec_priv, struct ieee80211_h
 				else
 					RX_STAT_INC(sc, rx_spectral_sample_err);
 
-				memset(sample_buf, 0, SPECTRAL_SAMPLE_MAX_LEN);
-
 				/* Mix the received bins to the /dev/random
 				 * pool
 				 */
 				add_device_randomness(sample_buf, num_bins);
+
+				memset(sample_buf, 0, SPECTRAL_SAMPLE_MAX_LEN);
 			}
 
 			/* Process a normal frame */

From bee577165a0a375a1d47d8ddef1c321e0f7dd6c8 Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Fri, 17 Jan 2025 19:19:53 +0100
Subject: [PATCH 0051/2753] wifi: ath11k: remove peer extra rssi update

Commit b205ce4c266c ("ath11k: support avg signal in station dump") added an
extra assignment of arsta->rssi_comb in ath11k_dp_rx_update_peer_stats()
when it added the average rssi support. So let's keep only one by removing
the legacy assignment so the two statements about rssi stay next to each
other. Compile tested only.

Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Reviewed-by: Vasanthakumar Thiagarajan <quic_vthiagar@quicinc.com>
Link: https://patch.msgid.link/20250117181953.3375273-1-nico.escande@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 5e71e5d9ecb78..640d617a585af 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -2822,8 +2822,6 @@ static void ath11k_dp_rx_update_peer_stats(struct ath11k_sta *arsta,
 	rx_stats->dcm_count += ppdu_info->dcm;
 	rx_stats->ru_alloc_cnt[ppdu_info->ru_alloc] += num_msdu;
 
-	arsta->rssi_comb = ppdu_info->rssi_comb;
-
 	BUILD_BUG_ON(ARRAY_SIZE(arsta->chain_signal) >
 			     ARRAY_SIZE(ppdu_info->rssi_chain_pri20));
 

From df11edfba49e5fb69f4c9e7cb76082b89c417f78 Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Mon, 27 Jan 2025 08:13:06 +0100
Subject: [PATCH 0052/2753] wifi: ath12k: fix
 ath12k_hal_tx_cmd_ext_desc_setup() info1 override

Since inception there is an obvious typo laying around in
ath12k_hal_tx_cmd_ext_desc_setup(). Instead of initializing + adding
flags to tcl_ext_cmd->info1, we initialize + override. This will be needed
in the future to make broadcast frames work with ethernet encapsulation.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250127071306.1454699-1-nico.escande@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index aa8058dd2da62..94310bcc620cb 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -119,7 +119,7 @@ static void ath12k_hal_tx_cmd_ext_desc_setup(struct ath12k_base *ab,
 			       le32_encode_bits(ti->data_len,
 						HAL_TX_MSDU_EXT_INFO1_BUF_LEN);
 
-	tcl_ext_cmd->info1 = le32_encode_bits(1, HAL_TX_MSDU_EXT_INFO1_EXTN_OVERRIDE) |
+	tcl_ext_cmd->info1 |= le32_encode_bits(1, HAL_TX_MSDU_EXT_INFO1_EXTN_OVERRIDE) |
 				le32_encode_bits(ti->encap_type,
 						 HAL_TX_MSDU_EXT_INFO1_ENCAP_TYPE) |
 				le32_encode_bits(ti->encrypt_type,

From 8a5ad319f2e6f0462dbcb1bd3a6ba5097f629a5b Mon Sep 17 00:00:00 2001
From: Remi Pommarel <repk@triplefau.lt>
Date: Wed, 29 Jan 2025 17:55:17 +0100
Subject: [PATCH 0053/2753] wifi: ath12k: remove return for empty tx bitrate in
 mac_op_sta_statistics

Currently in ath12k_mac_op_sta_statistics() there is the following
logic:

    if (!arsta->txrate.legacy && !arsta->txrate.nss)
        return;

Because ath12k_sta_statistics is used to report many info to iw wlan0 link,
if it return for empty legacy and nss of arsta->txrate, then the other
stats after it will not be set.

To address this issue remove the return and instead invert the logic to set
the txrate logic if (arsta->txrate.legacy || arsta->txrate.nss).

The same was done also in both ath10k with commit 1cd6ba8ae33e ("ath10k:
remove return for NL80211_STA_INFO_TX_BITRATE") and ath11k as well with
commit 1d795645e1ee ("ath11k: remove return for empty tx bitrate in
mac_op_sta_statistics").

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Remi Pommarel <repk@triplefau.lt>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/38c2a7c4f7eaf57b9306bb95a9e6c42b7d987e05.1738169458.git.repk@triplefau.lt
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 33 +++++++++++++--------------
 1 file changed, 16 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 4fb7e235be667..e9663c6ac72cd 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -10170,23 +10170,22 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 	sinfo->tx_duration = arsta->tx_duration;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION);
 
-	if (!arsta->txrate.legacy && !arsta->txrate.nss)
-		return;
-
-	if (arsta->txrate.legacy) {
-		sinfo->txrate.legacy = arsta->txrate.legacy;
-	} else {
-		sinfo->txrate.mcs = arsta->txrate.mcs;
-		sinfo->txrate.nss = arsta->txrate.nss;
-		sinfo->txrate.bw = arsta->txrate.bw;
-		sinfo->txrate.he_gi = arsta->txrate.he_gi;
-		sinfo->txrate.he_dcm = arsta->txrate.he_dcm;
-		sinfo->txrate.he_ru_alloc = arsta->txrate.he_ru_alloc;
-		sinfo->txrate.eht_gi = arsta->txrate.eht_gi;
-		sinfo->txrate.eht_ru_alloc = arsta->txrate.eht_ru_alloc;
-	}
-	sinfo->txrate.flags = arsta->txrate.flags;
-	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+	if (arsta->txrate.legacy || arsta->txrate.nss) {
+		if (arsta->txrate.legacy) {
+			sinfo->txrate.legacy = arsta->txrate.legacy;
+		} else {
+			sinfo->txrate.mcs = arsta->txrate.mcs;
+			sinfo->txrate.nss = arsta->txrate.nss;
+			sinfo->txrate.bw = arsta->txrate.bw;
+			sinfo->txrate.he_gi = arsta->txrate.he_gi;
+			sinfo->txrate.he_dcm = arsta->txrate.he_dcm;
+			sinfo->txrate.he_ru_alloc = arsta->txrate.he_ru_alloc;
+			sinfo->txrate.eht_gi = arsta->txrate.eht_gi;
+			sinfo->txrate.eht_ru_alloc = arsta->txrate.eht_ru_alloc;
+		}
+		sinfo->txrate.flags = arsta->txrate.flags;
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+	}
 
 	/* TODO: Use real NF instead of default one. */
 	signal = arsta->rssi_comb;

From f0dc53a7b77f900aa3d13309f84912b324ccca35 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:21 +0800
Subject: [PATCH 0054/2753] wifi: rtw89: phy: rename to RTW89_PHY_NUM as proper
 naming

The meaning is number of PHY, not maximum ID of PHY. Change to proper
naming.

No change logic at all.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c   | 38 ++++++++++-----------
 drivers/net/wireless/realtek/rtw89/core.c   |  4 +--
 drivers/net/wireless/realtek/rtw89/core.h   | 36 +++++++++----------
 drivers/net/wireless/realtek/rtw89/fw.h     | 14 ++++----
 drivers/net/wireless/realtek/rtw89/mac.c    |  2 +-
 drivers/net/wireless/realtek/rtw89/mac_be.c |  2 +-
 6 files changed, 48 insertions(+), 48 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 7e43ba0c4098b..755c157c815d4 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -1602,7 +1602,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			wl->ver_info.fw = le32_to_cpu(prpt->v4.wl_fw_info.fw_ver);
 			dm->wl_fw_cx_offload = !!le32_to_cpu(prpt->v4.wl_fw_info.cx_offload);
 
-			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+			for (i = RTW89_PHY_0; i < RTW89_PHY_NUM; i++)
 				memcpy(&dm->gnt.band[i], &prpt->v4.gnt_val[i],
 				       sizeof(dm->gnt.band[i]));
 
@@ -1634,7 +1634,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			wl->ver_info.fw = le32_to_cpu(prpt->v5.rpt_info.fw_ver);
 			dm->wl_fw_cx_offload = 0;
 
-			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+			for (i = RTW89_PHY_0; i < RTW89_PHY_NUM; i++)
 				memcpy(&dm->gnt.band[i], &prpt->v5.gnt_val[i][0],
 				       sizeof(dm->gnt.band[i]));
 
@@ -1661,7 +1661,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			wl->ver_info.fw = le32_to_cpu(prpt->v105.rpt_info.fw_ver);
 			dm->wl_fw_cx_offload = 0;
 
-			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+			for (i = RTW89_PHY_0; i < RTW89_PHY_NUM; i++)
 				memcpy(&dm->gnt.band[i], &prpt->v105.gnt_val[i][0],
 				       sizeof(dm->gnt.band[i]));
 
@@ -1687,7 +1687,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			wl->ver_info.fw_coex = le32_to_cpu(prpt->v7.rpt_info.cx_ver);
 			wl->ver_info.fw = le32_to_cpu(prpt->v7.rpt_info.fw_ver);
 
-			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+			for (i = RTW89_PHY_0; i < RTW89_PHY_NUM; i++)
 				memcpy(&dm->gnt.band[i], &prpt->v7.gnt_val[i][0],
 				       sizeof(dm->gnt.band[i]));
 
@@ -1719,7 +1719,7 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 			wl->ver_info.fw_coex = le32_to_cpu(prpt->v8.rpt_info.cx_ver);
 			wl->ver_info.fw = le32_to_cpu(prpt->v8.rpt_info.fw_ver);
 
-			for (i = RTW89_PHY_0; i < RTW89_PHY_MAX; i++)
+			for (i = RTW89_PHY_0; i < RTW89_PHY_NUM; i++)
 				memcpy(&dm->gnt.band[i], &prpt->v8.gnt_val[i][0],
 				       sizeof(dm->gnt.band[i]));
 
@@ -2706,7 +2706,7 @@ static void _set_gnt(struct rtw89_dev *rtwdev, u8 phy_map, u8 wl_state, u8 bt_st
 	if (phy_map > BTC_PHY_ALL)
 		return;
 
-	for (i = 0; i < RTW89_PHY_MAX; i++) {
+	for (i = 0; i < RTW89_PHY_NUM; i++) {
 		if (!(phy_map & BIT(i)))
 			continue;
 
@@ -2755,7 +2755,7 @@ static void _set_gnt_v1(struct rtw89_dev *rtwdev, u8 phy_map,
 	if (phy_map > BTC_PHY_ALL)
 		return;
 
-	for (i = 0; i < RTW89_PHY_MAX; i++) {
+	for (i = 0; i < RTW89_PHY_NUM; i++) {
 		if (!(phy_map & BIT(i)))
 			continue;
 
@@ -2955,7 +2955,7 @@ static void _set_rf_trx_para(struct rtw89_dev *rtwdev)
 
 	if (ver->fwlrole == 0) {
 		link_mode = wl->role_info.link_mode;
-		for (i = 0; i < RTW89_PHY_MAX; i++) {
+		for (i = 0; i < RTW89_PHY_NUM; i++) {
 			if (wl->dbcc_info.real_band[i] == RTW89_BAND_2G)
 				dbcc_2g_phy = i;
 		}
@@ -4240,7 +4240,7 @@ static void _set_ant_v0(struct rtw89_dev *rtwdev, bool force_exec,
 	case BTC_ANT_W2G:
 		rtw89_chip_cfg_ctrl_path(rtwdev, BTC_CTRL_BY_WL);
 		if (rtwdev->dbcc_en) {
-			for (i = 0; i < RTW89_PHY_MAX; i++) {
+			for (i = 0; i < RTW89_PHY_NUM; i++) {
 				b2g = (wl_dinfo->real_band[i] == RTW89_BAND_2G);
 
 				gnt_wl_ctrl = b2g ? BTC_GNT_HW : BTC_GNT_SW_HI;
@@ -4896,9 +4896,9 @@ static void _set_btg_ctrl(struct rtw89_dev *rtwdev)
 
 	if (rtwdev->dbcc_en) {
 		if (ver->fwlrole == 0) {
-			wl_rinfo.dbcc_2g_phy = RTW89_PHY_MAX;
+			wl_rinfo.dbcc_2g_phy = RTW89_PHY_NUM;
 
-			for (i = 0; i < RTW89_PHY_MAX; i++) {
+			for (i = 0; i < RTW89_PHY_NUM; i++) {
 				if (wl_dinfo->real_band[i] == RTW89_BAND_2G)
 					wl_rinfo.dbcc_2g_phy = i;
 			}
@@ -5790,7 +5790,7 @@ static void _update_wl_info(struct rtw89_dev *rtwdev)
 		phy = wl_linfo[i].phy;
 
 		/* check dbcc role */
-		if (rtwdev->dbcc_en && phy < RTW89_PHY_MAX) {
+		if (rtwdev->dbcc_en && phy < RTW89_PHY_NUM) {
 			wl_dinfo->role[phy] = wl_linfo[i].role;
 			wl_dinfo->op_band[phy] = wl_linfo[i].band;
 			_update_dbcc_band(rtwdev, phy);
@@ -5940,7 +5940,7 @@ static void _update_wl_info_v1(struct rtw89_dev *rtwdev)
 
 		phy = wl_linfo[i].phy;
 
-		if (rtwdev->dbcc_en && phy < RTW89_PHY_MAX) {
+		if (rtwdev->dbcc_en && phy < RTW89_PHY_NUM) {
 			wl_dinfo->role[phy] = wl_linfo[i].role;
 			wl_dinfo->op_band[phy] = wl_linfo[i].band;
 			_update_dbcc_band(rtwdev, phy);
@@ -6090,7 +6090,7 @@ static void _update_wl_info_v2(struct rtw89_dev *rtwdev)
 
 		phy = wl_linfo[i].phy;
 
-		if (rtwdev->dbcc_en && phy < RTW89_PHY_MAX) {
+		if (rtwdev->dbcc_en && phy < RTW89_PHY_NUM) {
 			wl_dinfo->role[phy] = wl_linfo[i].role;
 			wl_dinfo->op_band[phy] = wl_linfo[i].band;
 			_update_dbcc_band(rtwdev, phy);
@@ -6381,7 +6381,7 @@ static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid)
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
 	struct rtw89_btc_wl_link_info *wl_linfo = wl->link_info;
 	struct rtw89_btc_wl_active_role_v7 *act_role = NULL;
-	u8 i, mode, cnt = 0, cnt_2g = 0, cnt_5g = 0, phy_now = RTW89_PHY_MAX, phy_dbcc;
+	u8 i, mode, cnt = 0, cnt_2g = 0, cnt_5g = 0, phy_now = RTW89_PHY_NUM, phy_dbcc;
 	bool b2g = false, b5g = false, client_joined = false, client_inc_2g = false;
 	u8 client_cnt_last[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER] = {};
 	u8 cid_role[RTW89_BE_BTC_WL_MAX_ROLE_NUMBER] = {};
@@ -6392,7 +6392,7 @@ static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid)
 	memset(wl_rinfo, 0, sizeof(*wl_rinfo));
 
 	for (i = 0; i < RTW89_PORT_NUM; i++) {
-		if (!wl_linfo[i].active || wl_linfo[i].phy >= RTW89_PHY_MAX)
+		if (!wl_linfo[i].active || wl_linfo[i].phy >= RTW89_PHY_NUM)
 			continue;
 
 		act_role = &wl_rinfo->active_role[i];
@@ -6486,7 +6486,7 @@ static void _update_wl_info_v7(struct rtw89_dev *rtwdev, u8 rid)
 		mode = _chk_dbcc(rtwdev, cid_ch, cid_phy, cid_role, &dbcc_2g_phy);
 
 		/* correct 2G-located PHY band for gnt ctrl */
-		if (dbcc_2g_phy < RTW89_PHY_MAX)
+		if (dbcc_2g_phy < RTW89_PHY_NUM)
 			wl_dinfo->op_band[dbcc_2g_phy] = RTW89_BAND_2G;
 	} else if (b2g && b5g && cnt == 2) {
 		mode = BTC_WLINK_25G_MCC;
@@ -7179,7 +7179,7 @@ void rtw89_btc_ntfy_scan_start(struct rtw89_dev *rtwdev, u8 phy_idx, u8 band)
 		    "[BTC], %s(): phy_idx=%d, band=%d\n",
 		    __func__, phy_idx, band);
 
-	if (phy_idx >= RTW89_PHY_MAX)
+	if (phy_idx >= RTW89_PHY_NUM)
 		return;
 
 	btc->dm.cnt_notify[BTC_NCNT_SCAN_START]++;
@@ -7229,7 +7229,7 @@ void rtw89_btc_ntfy_switch_band(struct rtw89_dev *rtwdev, u8 phy_idx, u8 band)
 		    "[BTC], %s(): phy_idx=%d, band=%d\n",
 		    __func__, phy_idx, band);
 
-	if (phy_idx >= RTW89_PHY_MAX)
+	if (phy_idx >= RTW89_PHY_NUM)
 		return;
 
 	btc->dm.cnt_notify[BTC_NCNT_SWITCH_BAND]++;
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 85f739f1173d8..b7987c6b1cd52 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4432,9 +4432,9 @@ static void rtw89_core_ppdu_sts_init(struct rtw89_dev *rtwdev)
 {
 	int i;
 
-	for (i = 0; i < RTW89_PHY_MAX; i++)
+	for (i = 0; i < RTW89_PHY_NUM; i++)
 		skb_queue_head_init(&rtwdev->ppdu_sts.rx_queue[i]);
-	for (i = 0; i < RTW89_PHY_MAX; i++)
+	for (i = 0; i < RTW89_PHY_NUM; i++)
 		rtwdev->ppdu_sts.curr_rx_ppdu_cnt[i] = U8_MAX;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 0f2a46e36b042..4e5949516a758 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -826,7 +826,7 @@ enum rtw89_mac_idx {
 enum rtw89_phy_idx {
 	RTW89_PHY_0 = 0,
 	RTW89_PHY_1 = 1,
-	RTW89_PHY_MAX
+	RTW89_PHY_NUM,
 };
 
 #define __RTW89_MLD_MAX_LINK_NUM 2
@@ -1540,16 +1540,16 @@ struct rtw89_btc_u8_sta_chg {
 };
 
 struct rtw89_btc_wl_scan_info {
-	u8 band[RTW89_PHY_MAX];
+	u8 band[RTW89_PHY_NUM];
 	u8 phy_map;
 	u8 rsvd;
 };
 
 struct rtw89_btc_wl_dbcc_info {
-	u8 op_band[RTW89_PHY_MAX]; /* op band in each phy */
-	u8 scan_band[RTW89_PHY_MAX]; /* scan band in  each phy */
-	u8 real_band[RTW89_PHY_MAX];
-	u8 role[RTW89_PHY_MAX]; /* role in each phy */
+	u8 op_band[RTW89_PHY_NUM]; /* op band in each phy */
+	u8 scan_band[RTW89_PHY_NUM]; /* scan band in  each phy */
+	u8 real_band[RTW89_PHY_NUM];
+	u8 role[RTW89_PHY_NUM]; /* role in each phy */
 };
 
 struct rtw89_btc_wl_active_role {
@@ -1899,7 +1899,7 @@ struct rtw89_btc_wl_info {
 	u8 cn_report;
 	u8 coex_mode;
 	u8 pta_req_mac;
-	u8 bt_polut_type[RTW89_PHY_MAX]; /* BT polluted WL-Tx type for phy0/1  */
+	u8 bt_polut_type[RTW89_PHY_NUM]; /* BT polluted WL-Tx type for phy0/1  */
 
 	bool is_5g_hi_channel;
 	bool pta_reg_mac_chg;
@@ -2231,7 +2231,7 @@ struct rtw89_btc_fbtc_rpt_ctrl_v4 {
 	struct rtw89_btc_fbtc_rpt_ctrl_wl_fw_info wl_fw_info;
 	struct rtw89_btc_fbtc_rpt_ctrl_bt_mailbox bt_mbx_info;
 	__le32 bt_cnt[BTC_BCNT_STA_MAX];
-	struct rtw89_mac_ax_gnt gnt_val[RTW89_PHY_MAX];
+	struct rtw89_mac_ax_gnt gnt_val[RTW89_PHY_NUM];
 } __packed;
 
 struct rtw89_btc_fbtc_rpt_ctrl_v5 {
@@ -2239,7 +2239,7 @@ struct rtw89_btc_fbtc_rpt_ctrl_v5 {
 	u8 rsvd;
 	__le16 rsvd1;
 
-	u8 gnt_val[RTW89_PHY_MAX][4];
+	u8 gnt_val[RTW89_PHY_NUM][4];
 	__le16 bt_cnt[BTC_BCNT_STA_MAX];
 
 	struct rtw89_btc_fbtc_rpt_ctrl_info_v5 rpt_info;
@@ -2251,7 +2251,7 @@ struct rtw89_btc_fbtc_rpt_ctrl_v105 {
 	u8 rsvd;
 	__le16 rsvd1;
 
-	u8 gnt_val[RTW89_PHY_MAX][4];
+	u8 gnt_val[RTW89_PHY_NUM][4];
 	__le16 bt_cnt[BTC_BCNT_STA_MAX_V105];
 
 	struct rtw89_btc_fbtc_rpt_ctrl_info_v5 rpt_info;
@@ -2264,7 +2264,7 @@ struct rtw89_btc_fbtc_rpt_ctrl_v7 {
 	u8 rsvd1;
 	u8 rsvd2;
 
-	u8 gnt_val[RTW89_PHY_MAX][4];
+	u8 gnt_val[RTW89_PHY_NUM][4];
 	__le16 bt_cnt[BTC_BCNT_STA_MAX_V105];
 
 	struct rtw89_btc_fbtc_rpt_ctrl_info_v8 rpt_info;
@@ -2277,7 +2277,7 @@ struct rtw89_btc_fbtc_rpt_ctrl_v8 {
 	u8 rpt_len_max_l; /* BTC_RPT_MAX bit0~7 */
 	u8 rpt_len_max_h; /* BTC_RPT_MAX bit8~15 */
 
-	u8 gnt_val[RTW89_PHY_MAX][4];
+	u8 gnt_val[RTW89_PHY_NUM][4];
 	__le16 bt_cnt[BTC_BCNT_STA_MAX_V105];
 
 	struct rtw89_btc_fbtc_rpt_ctrl_info_v8 rpt_info;
@@ -4763,7 +4763,7 @@ struct rtw89_hal {
 	struct rtw89_chanctx chanctx[NUM_OF_RTW89_CHANCTX];
 	struct cfg80211_chan_def roc_chandef;
 
-	bool entity_active[RTW89_PHY_MAX];
+	bool entity_active[RTW89_PHY_NUM];
 	bool entity_pause;
 	enum rtw89_entity_mode entity_mode;
 	struct rtw89_entity_mgnt entity_mgnt;
@@ -4974,7 +4974,7 @@ struct rtw89_dpk_bkup_para {
 struct rtw89_dpk_info {
 	bool is_dpk_enable;
 	bool is_dpk_reload_en;
-	u8 dpk_gs[RTW89_PHY_MAX];
+	u8 dpk_gs[RTW89_PHY_NUM];
 	u16 dc_i[RTW89_DPK_RF_PATH][RTW89_DPK_BKUP_NUM];
 	u16 dc_q[RTW89_DPK_RF_PATH][RTW89_DPK_BKUP_NUM];
 	u8 corr_val[RTW89_DPK_RF_PATH][RTW89_DPK_BKUP_NUM];
@@ -5300,8 +5300,8 @@ struct rtw89_lps_parm {
 };
 
 struct rtw89_ppdu_sts_info {
-	struct sk_buff_head rx_queue[RTW89_PHY_MAX];
-	u8 curr_rx_ppdu_cnt[RTW89_PHY_MAX];
+	struct sk_buff_head rx_queue[RTW89_PHY_NUM];
+	u8 curr_rx_ppdu_cnt[RTW89_PHY_NUM];
 };
 
 struct rtw89_early_h2c {
@@ -5420,8 +5420,8 @@ struct rtw89_phy_efuse_gain {
 	bool offset_valid;
 	bool comp_valid;
 	s8 offset[RF_PATH_MAX][RTW89_GAIN_OFFSET_NR]; /* S(8, 0) */
-	s8 offset_base[RTW89_PHY_MAX]; /* S(8, 4) */
-	s8 rssi_base[RTW89_PHY_MAX]; /* S(8, 4) */
+	s8 offset_base[RTW89_PHY_NUM]; /* S(8, 4) */
+	s8 rssi_base[RTW89_PHY_NUM]; /* S(8, 4) */
 	s8 comp[RF_PATH_MAX][RTW89_SUBBAND_NR]; /* S(8, 0) */
 };
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 2026bc2fd2acd..3cc514de073ab 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -1803,14 +1803,14 @@ struct rtw89_h2c_lps_ml_cmn_info {
 	u8 fmt_id;
 	u8 rsvd0[3];
 	__le32 mlo_dbcc_mode;
-	u8 central_ch[RTW89_PHY_MAX];
-	u8 pri_ch[RTW89_PHY_MAX];
-	u8 bw[RTW89_PHY_MAX];
-	u8 band[RTW89_PHY_MAX];
-	u8 bcn_rate_type[RTW89_PHY_MAX];
+	u8 central_ch[RTW89_PHY_NUM];
+	u8 pri_ch[RTW89_PHY_NUM];
+	u8 bw[RTW89_PHY_NUM];
+	u8 band[RTW89_PHY_NUM];
+	u8 bcn_rate_type[RTW89_PHY_NUM];
 	u8 rsvd1[2];
-	__le16 tia_gain[RTW89_PHY_MAX][TIA_GAIN_NUM];
-	u8 lna_gain[RTW89_PHY_MAX][LNA_GAIN_NUM];
+	__le16 tia_gain[RTW89_PHY_NUM][TIA_GAIN_NUM];
+	u8 lna_gain[RTW89_PHY_NUM][LNA_GAIN_NUM];
 	u8 rsvd2[2];
 } __packed;
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index a37c6d525d6f0..f698807790ffc 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -6031,7 +6031,7 @@ int rtw89_mac_cfg_ctrl_path_v1(struct rtw89_dev *rtwdev, bool wl)
 	if (wl)
 		return 0;
 
-	for (i = 0; i < RTW89_PHY_MAX; i++) {
+	for (i = 0; i < RTW89_PHY_NUM; i++) {
 		g[i].gnt_bt_sw_en = 1;
 		g[i].gnt_bt = 1;
 		g[i].gnt_wl_sw_en = 1;
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index 2dbdeae904ade..16ee378c54187 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -1865,7 +1865,7 @@ int rtw89_mac_cfg_ctrl_path_v2(struct rtw89_dev *rtwdev, bool wl)
 	if (wl)
 		return 0;
 
-	for (i = 0; i < RTW89_PHY_MAX; i++) {
+	for (i = 0; i < RTW89_PHY_NUM; i++) {
 		g[i].gnt_bt_sw_en = 1;
 		g[i].gnt_bt = 1;
 		g[i].gnt_wl_sw_en = 1;

From 57a6cdf2feaf864903b88ae03fe9e0d56cdbd0ee Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:22 +0800
Subject: [PATCH 0055/2753] wifi: rtw89: phy: add PHY context array to support
 functions per PHY

To support MLO working on PHY 0 and PHY 1, extend existing PHY dynamic
mechanism from PHY 0 to PHY 0/1.

Implement a 2 elements array for two PHY instances, and pass pointer
of each element as argument to existing functions. Then existing algorithm
is kept, unchanged.

Also provide iterate and get function to access PHY context.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  3 ++
 drivers/net/wireless/realtek/rtw89/core.h | 46 +++++++++++++++++++++++
 2 files changed, 49 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index b7987c6b1cd52..42815a58a49a3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4867,6 +4867,9 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 		rtwdev->mlo_dbcc_mode = MLO_2_PLUS_0_1RF;
 	}
 
+	rtwdev->bbs[RTW89_PHY_0].phy_idx = RTW89_PHY_0;
+	rtwdev->bbs[RTW89_PHY_1].phy_idx = RTW89_PHY_1;
+
 	INIT_WORK(&btc->eapol_notify_work, rtw89_btc_ntfy_eapol_packet_work);
 	INIT_WORK(&btc->arp_notify_work, rtw89_btc_ntfy_arp_packet_work);
 	INIT_WORK(&btc->dhcp_notify_work, rtw89_btc_ntfy_dhcp_packet_work);
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 4e5949516a758..d15d8c4046c11 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5694,6 +5694,10 @@ struct rtw89_dev {
 	struct rtw89_phy_ul_tb_info ul_tb_info;
 	struct rtw89_antdiv_info antdiv;
 
+	struct rtw89_bb_ctx {
+		enum rtw89_phy_idx phy_idx;
+	} bbs[RTW89_PHY_NUM];
+
 	struct delayed_work track_work;
 	struct delayed_work chanctx_work;
 	struct delayed_work coex_act1_work;
@@ -6979,6 +6983,48 @@ static inline bool rtw89_is_mlo_1_1(struct rtw89_dev *rtwdev)
 	}
 }
 
+static inline u8 rtw89_get_active_phy_bitmap(struct rtw89_dev *rtwdev)
+{
+	if (!rtwdev->dbcc_en)
+		return BIT(RTW89_PHY_0);
+
+	switch (rtwdev->mlo_dbcc_mode) {
+	case MLO_0_PLUS_2_1RF:
+	case MLO_0_PLUS_2_2RF:
+		return BIT(RTW89_PHY_1);
+	case MLO_1_PLUS_1_1RF:
+	case MLO_1_PLUS_1_2RF:
+	case MLO_2_PLUS_2_2RF:
+	case DBCC_LEGACY:
+		return BIT(RTW89_PHY_0) | BIT(RTW89_PHY_1);
+	case MLO_2_PLUS_0_1RF:
+	case MLO_2_PLUS_0_2RF:
+	default:
+		return BIT(RTW89_PHY_0);
+	}
+}
+
+#define rtw89_for_each_active_bb(rtwdev, bb) \
+	for (u8 __active_bb_bitmap = rtw89_get_active_phy_bitmap(rtwdev), \
+	     __phy_idx = 0; __phy_idx < RTW89_PHY_NUM; __phy_idx++) \
+		if (__active_bb_bitmap & BIT(__phy_idx) && \
+		    (bb = &rtwdev->bbs[__phy_idx]))
+
+#define rtw89_for_each_capab_bb(rtwdev, bb) \
+	for (u8 __phy_idx_max = rtwdev->dbcc_en ? RTW89_PHY_1 : RTW89_PHY_0, \
+	     __phy_idx = 0; __phy_idx <= __phy_idx_max; __phy_idx++) \
+		if ((bb = &rtwdev->bbs[__phy_idx]))
+
+static inline
+struct rtw89_bb_ctx *rtw89_get_bb_ctx(struct rtw89_dev *rtwdev,
+				      enum rtw89_phy_idx phy_idx)
+{
+	if (phy_idx >= RTW89_PHY_NUM)
+		return &rtwdev->bbs[RTW89_PHY_0];
+
+	return &rtwdev->bbs[phy_idx];
+}
+
 static inline bool rtw89_is_rtl885xb(struct rtw89_dev *rtwdev)
 {
 	enum rtw89_core_chip_id chip_id = rtwdev->chip->chip_id;

From 11a625160a32243001b6c773a671dcacdd56c038 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:23 +0800
Subject: [PATCH 0056/2753] wifi: rtw89: phy: support env_monitor per PHY

The env_monitor is to collect information of current operating channel as
helper to make decision with better hardware parameters to adopt current
environment.

Use PHY context as argument to control PHY accordingly, and use
rtw89_phy_{write32,read32}_idx with phy_idx to access registers.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |   2 +-
 drivers/net/wireless/realtek/rtw89/phy.c  | 306 +++++++++++++---------
 drivers/net/wireless/realtek/rtw89/sar.c  |   3 +-
 3 files changed, 180 insertions(+), 131 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index d15d8c4046c11..2f1bb51f6a0c2 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5683,7 +5683,6 @@ struct rtw89_dev {
 	struct rtw89_power_trim_info pwr_trim;
 
 	struct rtw89_cfo_tracking_info cfo_tracking;
-	struct rtw89_env_monitor_info env_monitor;
 	struct rtw89_dig_info dig;
 	struct rtw89_phy_ch_info ch_info;
 	union {
@@ -5696,6 +5695,7 @@ struct rtw89_dev {
 
 	struct rtw89_bb_ctx {
 		enum rtw89_phy_idx phy_idx;
+		struct rtw89_env_monitor_info env_monitor;
 	} bbs[RTW89_PHY_NUM];
 
 	struct delayed_work track_work;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index c7c05f7fda1d5..e266ddae0c31b 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -5199,24 +5199,27 @@ void rtw89_phy_stat_track(struct rtw89_dev *rtwdev)
 	memset(&phystat->cur_pkt_stat, 0, sizeof(phystat->cur_pkt_stat));
 }
 
-static u16 rtw89_phy_ccx_us_to_idx(struct rtw89_dev *rtwdev, u32 time_us)
+static u16 rtw89_phy_ccx_us_to_idx(struct rtw89_dev *rtwdev,
+				   struct rtw89_bb_ctx *bb, u32 time_us)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 
 	return time_us >> (ilog2(CCX_US_BASE_RATIO) + env->ccx_unit_idx);
 }
 
-static u32 rtw89_phy_ccx_idx_to_us(struct rtw89_dev *rtwdev, u16 idx)
+static u32 rtw89_phy_ccx_idx_to_us(struct rtw89_dev *rtwdev,
+				   struct rtw89_bb_ctx *bb, u16 idx)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 
 	return idx << (ilog2(CCX_US_BASE_RATIO) + env->ccx_unit_idx);
 }
 
-static void rtw89_phy_ccx_top_setting_init(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ccx_top_setting_init(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
 
 	env->ccx_manual_ctrl = false;
@@ -5225,17 +5228,20 @@ static void rtw89_phy_ccx_top_setting_init(struct rtw89_dev *rtwdev)
 	env->ccx_period = 0;
 	env->ccx_unit_idx = RTW89_CCX_32_US;
 
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->en_mask, 1);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->trig_opt_mask, 1);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->edcca_opt_mask,
-			       RTW89_CCX_EDCCA_BW20_0);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->en_mask, 1, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->trig_opt_mask, 1,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->edcca_opt_mask,
+			      RTW89_CCX_EDCCA_BW20_0, bb->phy_idx);
 }
 
-static u16 rtw89_phy_ccx_get_report(struct rtw89_dev *rtwdev, u16 report,
-				    u16 score)
+static u16 rtw89_phy_ccx_get_report(struct rtw89_dev *rtwdev,
+				    struct rtw89_bb_ctx *bb,
+				    u16 report, u16 score)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	u32 numer = 0;
 	u16 ret = 0;
 
@@ -5275,9 +5281,10 @@ static void rtw89_phy_ccx_ms_to_period_unit(struct rtw89_dev *rtwdev,
 		    *period, *unit_idx);
 }
 
-static void rtw89_phy_ccx_racing_release(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ccx_racing_release(struct rtw89_dev *rtwdev,
+					 struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 
 	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 		    "lv:(%d)->(0)\n", env->ccx_rac_lv);
@@ -5288,9 +5295,10 @@ static void rtw89_phy_ccx_racing_release(struct rtw89_dev *rtwdev)
 }
 
 static bool rtw89_phy_ifs_clm_th_update_check(struct rtw89_dev *rtwdev,
+					      struct rtw89_bb_ctx *bb,
 					      struct rtw89_ccx_para_info *para)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	bool is_update = env->ifs_clm_app != para->ifs_clm_app;
 	u8 i = 0;
 	u16 *ifs_th_l = env->ifs_clm_th_l;
@@ -5325,12 +5333,12 @@ static bool rtw89_phy_ifs_clm_th_update_check(struct rtw89_dev *rtwdev,
 	 */
 	ifs_th_l[IFS_CLM_TH_START_IDX] = 0;
 	ifs_th_h_us[IFS_CLM_TH_START_IDX] = ifs_th0_us;
-	ifs_th_h[IFS_CLM_TH_START_IDX] = rtw89_phy_ccx_us_to_idx(rtwdev,
+	ifs_th_h[IFS_CLM_TH_START_IDX] = rtw89_phy_ccx_us_to_idx(rtwdev, bb,
 								 ifs_th0_us);
 	for (i = 1; i < RTW89_IFS_CLM_NUM; i++) {
 		ifs_th_l[i] = ifs_th_h[i - 1] + 1;
 		ifs_th_h_us[i] = ifs_th_h_us[i - 1] * ifs_th_times;
-		ifs_th_h[i] = rtw89_phy_ccx_us_to_idx(rtwdev, ifs_th_h_us[i]);
+		ifs_th_h[i] = rtw89_phy_ccx_us_to_idx(rtwdev, bb, ifs_th_h_us[i]);
 	}
 
 ifs_update_finished:
@@ -5341,30 +5349,31 @@ static bool rtw89_phy_ifs_clm_th_update_check(struct rtw89_dev *rtwdev,
 	return is_update;
 }
 
-static void rtw89_phy_ifs_clm_set_th_reg(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ifs_clm_set_th_reg(struct rtw89_dev *rtwdev,
+					 struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u8 i = 0;
 
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_l_mask,
-			       env->ifs_clm_th_l[0]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_l_mask,
-			       env->ifs_clm_th_l[1]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_l_mask,
-			       env->ifs_clm_th_l[2]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_l_mask,
-			       env->ifs_clm_th_l[3]);
-
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_h_mask,
-			       env->ifs_clm_th_h[0]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_h_mask,
-			       env->ifs_clm_th_h[1]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_h_mask,
-			       env->ifs_clm_th_h[2]);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_h_mask,
-			       env->ifs_clm_th_h[3]);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_l_mask,
+			      env->ifs_clm_th_l[0], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_l_mask,
+			      env->ifs_clm_th_l[1], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_l_mask,
+			      env->ifs_clm_th_l[2], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_l_mask,
+			      env->ifs_clm_th_l[3], bb->phy_idx);
+
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_th_h_mask,
+			      env->ifs_clm_th_h[0], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_th_h_mask,
+			      env->ifs_clm_th_h[1], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_th_h_mask,
+			      env->ifs_clm_th_h[2], bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_th_h_mask,
+			      env->ifs_clm_th_h[3], bb->phy_idx);
 
 	for (i = 0; i < RTW89_IFS_CLM_NUM; i++)
 		rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
@@ -5372,31 +5381,38 @@ static void rtw89_phy_ifs_clm_set_th_reg(struct rtw89_dev *rtwdev)
 			    i + 1, env->ifs_clm_th_l[i], env->ifs_clm_th_h[i]);
 }
 
-static void rtw89_phy_ifs_clm_setting_init(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ifs_clm_setting_init(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
-	struct rtw89_ccx_para_info para = {0};
+	struct rtw89_ccx_para_info para = {};
 
 	env->ifs_clm_app = RTW89_IFS_CLM_BACKGROUND;
 	env->ifs_clm_mntr_time = 0;
 
 	para.ifs_clm_app = RTW89_IFS_CLM_INIT;
-	if (rtw89_phy_ifs_clm_th_update_check(rtwdev, &para))
-		rtw89_phy_ifs_clm_set_th_reg(rtwdev);
+	if (rtw89_phy_ifs_clm_th_update_check(rtwdev, bb, &para))
+		rtw89_phy_ifs_clm_set_th_reg(rtwdev, bb);
 
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_collect_en_mask, true);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_en_mask, true);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_en_mask, true);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_en_mask, true);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_en_mask, true);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_collect_en_mask, true,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t1_addr, ccx->ifs_t1_en_mask, true,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t2_addr, ccx->ifs_t2_en_mask, true,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t3_addr, ccx->ifs_t3_en_mask, true,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_t4_addr, ccx->ifs_t4_en_mask, true,
+			      bb->phy_idx);
 }
 
 static int rtw89_phy_ccx_racing_ctrl(struct rtw89_dev *rtwdev,
+				     struct rtw89_bb_ctx *bb,
 				     enum rtw89_env_racing_lv level)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	int ret = 0;
 
 	if (level >= RTW89_RAC_MAX_NUM) {
@@ -5425,56 +5441,62 @@ static int rtw89_phy_ccx_racing_ctrl(struct rtw89_dev *rtwdev,
 	return ret;
 }
 
-static void rtw89_phy_ccx_trigger(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ccx_trigger(struct rtw89_dev *rtwdev,
+				  struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
 
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 0);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 0);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 1);
-	rtw89_phy_set_phy_regs(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 0,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 0,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->ifs_cnt_addr, ccx->ifs_clm_cnt_clear_mask, 1,
+			      bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, ccx->setting_addr, ccx->measurement_trig_mask, 1,
+			      bb->phy_idx);
 
 	env->ccx_ongoing = true;
 }
 
-static void rtw89_phy_ifs_clm_get_utility(struct rtw89_dev *rtwdev)
+static void rtw89_phy_ifs_clm_get_utility(struct rtw89_dev *rtwdev,
+					  struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	u8 i = 0;
 	u32 res = 0;
 
 	env->ifs_clm_tx_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_tx, PERCENT);
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_tx, PERCENT);
 	env->ifs_clm_edcca_excl_cca_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_edcca_excl_cca,
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_edcca_excl_cca,
 					 PERCENT);
 	env->ifs_clm_cck_fa_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_cckfa, PERCENT);
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_cckfa, PERCENT);
 	env->ifs_clm_ofdm_fa_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_ofdmfa, PERCENT);
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_ofdmfa, PERCENT);
 	env->ifs_clm_cck_cca_excl_fa_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_cckcca_excl_fa,
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_cckcca_excl_fa,
 					 PERCENT);
 	env->ifs_clm_ofdm_cca_excl_fa_ratio =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_ofdmcca_excl_fa,
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_ofdmcca_excl_fa,
 					 PERCENT);
 	env->ifs_clm_cck_fa_permil =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_cckfa, PERMIL);
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_cckfa, PERMIL);
 	env->ifs_clm_ofdm_fa_permil =
-		rtw89_phy_ccx_get_report(rtwdev, env->ifs_clm_ofdmfa, PERMIL);
+		rtw89_phy_ccx_get_report(rtwdev, bb, env->ifs_clm_ofdmfa, PERMIL);
 
 	for (i = 0; i < RTW89_IFS_CLM_NUM; i++) {
 		if (env->ifs_clm_his[i] > ENV_MNTR_IFSCLM_HIS_MAX) {
 			env->ifs_clm_ifs_avg[i] = ENV_MNTR_FAIL_DWORD;
 		} else {
 			env->ifs_clm_ifs_avg[i] =
-				rtw89_phy_ccx_idx_to_us(rtwdev,
+				rtw89_phy_ccx_idx_to_us(rtwdev, bb,
 							env->ifs_clm_avg[i]);
 		}
 
-		res = rtw89_phy_ccx_idx_to_us(rtwdev, env->ifs_clm_cca[i]);
+		res = rtw89_phy_ccx_idx_to_us(rtwdev, bb, env->ifs_clm_cca[i]);
 		res += env->ifs_clm_his[i] >> 1;
 		if (env->ifs_clm_his[i])
 			res /= env->ifs_clm_his[i];
@@ -5504,81 +5526,82 @@ static void rtw89_phy_ifs_clm_get_utility(struct rtw89_dev *rtwdev)
 			    env->ifs_clm_cca_avg[i]);
 }
 
-static bool rtw89_phy_ifs_clm_get_result(struct rtw89_dev *rtwdev)
+static bool rtw89_phy_ifs_clm_get_result(struct rtw89_dev *rtwdev,
+					 struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u8 i = 0;
 
-	if (rtw89_phy_read32_mask(rtwdev, ccx->ifs_total_addr,
-				  ccx->ifs_cnt_done_mask) == 0) {
+	if (rtw89_phy_read32_idx(rtwdev, ccx->ifs_total_addr,
+				 ccx->ifs_cnt_done_mask, bb->phy_idx) == 0) {
 		rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 			    "Get IFS_CLM report Fail\n");
 		return false;
 	}
 
 	env->ifs_clm_tx =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_tx_cnt_addr,
-				      ccx->ifs_clm_tx_cnt_msk);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_tx_cnt_addr,
+				     ccx->ifs_clm_tx_cnt_msk, bb->phy_idx);
 	env->ifs_clm_edcca_excl_cca =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_tx_cnt_addr,
-				      ccx->ifs_clm_edcca_excl_cca_fa_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_tx_cnt_addr,
+				     ccx->ifs_clm_edcca_excl_cca_fa_mask, bb->phy_idx);
 	env->ifs_clm_cckcca_excl_fa =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_cca_addr,
-				      ccx->ifs_clm_cckcca_excl_fa_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_cca_addr,
+				     ccx->ifs_clm_cckcca_excl_fa_mask, bb->phy_idx);
 	env->ifs_clm_ofdmcca_excl_fa =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_cca_addr,
-				      ccx->ifs_clm_ofdmcca_excl_fa_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_cca_addr,
+				     ccx->ifs_clm_ofdmcca_excl_fa_mask, bb->phy_idx);
 	env->ifs_clm_cckfa =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_fa_addr,
-				      ccx->ifs_clm_cck_fa_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_fa_addr,
+				     ccx->ifs_clm_cck_fa_mask, bb->phy_idx);
 	env->ifs_clm_ofdmfa =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_clm_fa_addr,
-				      ccx->ifs_clm_ofdm_fa_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_clm_fa_addr,
+				     ccx->ifs_clm_ofdm_fa_mask, bb->phy_idx);
 
 	env->ifs_clm_his[0] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
-				      ccx->ifs_t1_his_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_his_addr,
+				     ccx->ifs_t1_his_mask, bb->phy_idx);
 	env->ifs_clm_his[1] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
-				      ccx->ifs_t2_his_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_his_addr,
+				     ccx->ifs_t2_his_mask, bb->phy_idx);
 	env->ifs_clm_his[2] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
-				      ccx->ifs_t3_his_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_his_addr,
+				     ccx->ifs_t3_his_mask, bb->phy_idx);
 	env->ifs_clm_his[3] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_his_addr,
-				      ccx->ifs_t4_his_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_his_addr,
+				     ccx->ifs_t4_his_mask, bb->phy_idx);
 
 	env->ifs_clm_avg[0] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_l_addr,
-				      ccx->ifs_t1_avg_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_avg_l_addr,
+				     ccx->ifs_t1_avg_mask, bb->phy_idx);
 	env->ifs_clm_avg[1] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_l_addr,
-				      ccx->ifs_t2_avg_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_avg_l_addr,
+				     ccx->ifs_t2_avg_mask, bb->phy_idx);
 	env->ifs_clm_avg[2] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_h_addr,
-				      ccx->ifs_t3_avg_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_avg_h_addr,
+				     ccx->ifs_t3_avg_mask, bb->phy_idx);
 	env->ifs_clm_avg[3] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_avg_h_addr,
-				      ccx->ifs_t4_avg_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_avg_h_addr,
+				     ccx->ifs_t4_avg_mask, bb->phy_idx);
 
 	env->ifs_clm_cca[0] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_l_addr,
-				      ccx->ifs_t1_cca_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_cca_l_addr,
+				     ccx->ifs_t1_cca_mask, bb->phy_idx);
 	env->ifs_clm_cca[1] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_l_addr,
-				      ccx->ifs_t2_cca_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_cca_l_addr,
+				     ccx->ifs_t2_cca_mask, bb->phy_idx);
 	env->ifs_clm_cca[2] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_h_addr,
-				      ccx->ifs_t3_cca_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_cca_h_addr,
+				     ccx->ifs_t3_cca_mask, bb->phy_idx);
 	env->ifs_clm_cca[3] =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_cca_h_addr,
-				      ccx->ifs_t4_cca_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_cca_h_addr,
+				     ccx->ifs_t4_cca_mask, bb->phy_idx);
 
 	env->ifs_clm_total_ifs =
-		rtw89_phy_read32_mask(rtwdev, ccx->ifs_total_addr,
-				      ccx->ifs_total_mask);
+		rtw89_phy_read32_idx(rtwdev, ccx->ifs_total_addr,
+				     ccx->ifs_total_mask, bb->phy_idx);
 
 	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK, "IFS-CLM total_ifs = %d\n",
 		    env->ifs_clm_total_ifs);
@@ -5598,16 +5621,17 @@ static bool rtw89_phy_ifs_clm_get_result(struct rtw89_dev *rtwdev)
 			    "T%d:[%d, %d, %d]\n", i + 1, env->ifs_clm_his[i],
 			    env->ifs_clm_avg[i], env->ifs_clm_cca[i]);
 
-	rtw89_phy_ifs_clm_get_utility(rtwdev);
+	rtw89_phy_ifs_clm_get_utility(rtwdev, bb);
 
 	return true;
 }
 
 static int rtw89_phy_ifs_clm_set(struct rtw89_dev *rtwdev,
+				 struct rtw89_bb_ctx *bb,
 				 struct rtw89_ccx_para_info *para)
 {
 	const struct rtw89_phy_gen_def *phy = rtwdev->chip->phy_def;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const struct rtw89_ccx_regs *ccx = phy->ccx;
 	u32 period = 0;
 	u32 unit_idx = 0;
@@ -5618,17 +5642,17 @@ static int rtw89_phy_ifs_clm_set(struct rtw89_dev *rtwdev,
 		return -EINVAL;
 	}
 
-	if (rtw89_phy_ccx_racing_ctrl(rtwdev, para->rac_lv))
+	if (rtw89_phy_ccx_racing_ctrl(rtwdev, bb, para->rac_lv))
 		return -EINVAL;
 
 	if (para->mntr_time != env->ifs_clm_mntr_time) {
 		rtw89_phy_ccx_ms_to_period_unit(rtwdev, para->mntr_time,
 						&period, &unit_idx);
-		rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr,
-				       ccx->ifs_clm_period_mask, period);
-		rtw89_phy_set_phy_regs(rtwdev, ccx->ifs_cnt_addr,
-				       ccx->ifs_clm_cnt_unit_mask,
-				       unit_idx);
+		rtw89_phy_write32_idx(rtwdev, ccx->ifs_cnt_addr,
+				      ccx->ifs_clm_period_mask, period, bb->phy_idx);
+		rtw89_phy_write32_idx(rtwdev, ccx->ifs_cnt_addr,
+				      ccx->ifs_clm_cnt_unit_mask,
+				      unit_idx, bb->phy_idx);
 
 		rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 			    "Update IFS-CLM time ((%d)) -> ((%d))\n",
@@ -5639,18 +5663,19 @@ static int rtw89_phy_ifs_clm_set(struct rtw89_dev *rtwdev,
 		env->ccx_unit_idx = (u8)unit_idx;
 	}
 
-	if (rtw89_phy_ifs_clm_th_update_check(rtwdev, para)) {
+	if (rtw89_phy_ifs_clm_th_update_check(rtwdev, bb, para)) {
 		env->ifs_clm_app = para->ifs_clm_app;
-		rtw89_phy_ifs_clm_set_th_reg(rtwdev);
+		rtw89_phy_ifs_clm_set_th_reg(rtwdev, bb);
 	}
 
 	return 0;
 }
 
-void rtw89_phy_env_monitor_track(struct rtw89_dev *rtwdev)
+static void __rtw89_phy_env_monitor_track(struct rtw89_dev *rtwdev,
+					  struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
-	struct rtw89_ccx_para_info para = {0};
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
+	struct rtw89_ccx_para_info para = {};
 	u8 chk_result = RTW89_PHY_ENV_MON_CCX_FAIL;
 
 	env->ccx_watchdog_result = RTW89_PHY_ENV_MON_CCX_FAIL;
@@ -5660,25 +5685,36 @@ void rtw89_phy_env_monitor_track(struct rtw89_dev *rtwdev)
 		return;
 	}
 
+	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
+		    "BB-%d env_monitor track\n", bb->phy_idx);
+
 	/* only ifs_clm for now */
-	if (rtw89_phy_ifs_clm_get_result(rtwdev))
+	if (rtw89_phy_ifs_clm_get_result(rtwdev, bb))
 		env->ccx_watchdog_result |= RTW89_PHY_ENV_MON_IFS_CLM;
 
-	rtw89_phy_ccx_racing_release(rtwdev);
+	rtw89_phy_ccx_racing_release(rtwdev, bb);
 	para.mntr_time = 1900;
 	para.rac_lv = RTW89_RAC_LV_1;
 	para.ifs_clm_app = RTW89_IFS_CLM_BACKGROUND;
 
-	if (rtw89_phy_ifs_clm_set(rtwdev, &para) == 0)
+	if (rtw89_phy_ifs_clm_set(rtwdev, bb, &para) == 0)
 		chk_result |= RTW89_PHY_ENV_MON_IFS_CLM;
 	if (chk_result)
-		rtw89_phy_ccx_trigger(rtwdev);
+		rtw89_phy_ccx_trigger(rtwdev, bb);
 
 	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
 		    "get_result=0x%x, chk_result:0x%x\n",
 		    env->ccx_watchdog_result, chk_result);
 }
 
+void rtw89_phy_env_monitor_track(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_bb_ctx *bb;
+
+	rtw89_for_each_active_bb(rtwdev, bb)
+		__rtw89_phy_env_monitor_track(rtwdev, bb);
+}
+
 static bool rtw89_physts_ie_page_valid(enum rtw89_phy_status_bitmap *ie_page)
 {
 	if (*ie_page >= RTW89_PHYSTS_BITMAP_NUM ||
@@ -6020,7 +6056,7 @@ static void rtw89_phy_dig_gaincode_by_rssi(struct rtw89_dev *rtwdev, u8 rssi,
 static void rtw89_phy_dig_igi_offset_by_env(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_dig_info *dig = &rtwdev->dig;
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_env_monitor_info *env = &rtwdev->bbs[0].env_monitor;
 	enum rtw89_dig_noisy_level noisy_lv;
 	u8 igi_offset = dig->fa_rssi_ofst;
 	u16 fa_ratio = 0;
@@ -6486,10 +6522,22 @@ void rtw89_phy_antdiv_track(struct rtw89_dev *rtwdev)
 	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->antdiv_work, 0);
 }
 
+static void __rtw89_phy_env_monitor_init(struct rtw89_dev *rtwdev,
+					 struct rtw89_bb_ctx *bb)
+{
+	rtw89_debug(rtwdev, RTW89_DBG_PHY_TRACK,
+		    "BB-%d env_monitor init\n", bb->phy_idx);
+
+	rtw89_phy_ccx_top_setting_init(rtwdev, bb);
+	rtw89_phy_ifs_clm_setting_init(rtwdev, bb);
+}
+
 static void rtw89_phy_env_monitor_init(struct rtw89_dev *rtwdev)
 {
-	rtw89_phy_ccx_top_setting_init(rtwdev);
-	rtw89_phy_ifs_clm_setting_init(rtwdev);
+	struct rtw89_bb_ctx *bb;
+
+	rtw89_for_each_capab_bb(rtwdev, bb)
+		__rtw89_phy_env_monitor_init(rtwdev, bb);
 }
 
 static void rtw89_phy_edcca_init(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 871f45a6508ca..94db695e78e6f 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -411,7 +411,8 @@ static const struct rtw89_reg_def txpwr_regs[] = {
 
 void rtw89_tas_track(struct rtw89_dev *rtwdev)
 {
-	struct rtw89_env_monitor_info *env = &rtwdev->env_monitor;
+	struct rtw89_bb_ctx *bb = rtw89_get_bb_ctx(rtwdev, RTW89_PHY_0);
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	u8 max_nss_num = rtwdev->chip->rf_path_num;
 	struct rtw89_tas_info *tas = &rtwdev->tas;

From dc0ac60f2a92cc8a44636cbee3d6c32d0197cbe6 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:24 +0800
Subject: [PATCH 0057/2753] wifi: rtw89: phy: support DIG per PHY

DIG standing for dynamic initial gain is to define RX coverage. Adjust this
value dynamically to gain good RX performance.

Use PHY context to extend DIG algorithm to support two PHY.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |   4 +-
 drivers/net/wireless/realtek/rtw89/core.h |   2 +-
 drivers/net/wireless/realtek/rtw89/phy.c  | 224 +++++++++++++---------
 drivers/net/wireless/realtek/rtw89/phy.h  |   2 +-
 4 files changed, 136 insertions(+), 96 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 42815a58a49a3..e39fb696ac13c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4925,6 +4925,7 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 			      struct rtw89_vif_link *rtwvif_link, bool hw_scan)
 {
 	struct ieee80211_bss_conf *bss_conf;
+	struct rtw89_bb_ctx *bb;
 
 	if (!rtwvif_link)
 		return;
@@ -4943,7 +4944,8 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 	rtw89_phy_config_edcca(rtwdev, false);
 
 	rtwdev->scanning = false;
-	rtwdev->dig.bypass_dig = true;
+	rtw89_for_each_active_bb(rtwdev, bb)
+		bb->dig.bypass_dig = true;
 	if (hw_scan && (rtwdev->hw->conf.flags & IEEE80211_CONF_IDLE))
 		ieee80211_queue_work(rtwdev->hw, &rtwdev->ips_work);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 2f1bb51f6a0c2..42632d1c981fc 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5683,7 +5683,6 @@ struct rtw89_dev {
 	struct rtw89_power_trim_info pwr_trim;
 
 	struct rtw89_cfo_tracking_info cfo_tracking;
-	struct rtw89_dig_info dig;
 	struct rtw89_phy_ch_info ch_info;
 	union {
 		struct rtw89_phy_bb_gain_info ax;
@@ -5696,6 +5695,7 @@ struct rtw89_dev {
 	struct rtw89_bb_ctx {
 		enum rtw89_phy_idx phy_idx;
 		struct rtw89_env_monitor_info env_monitor;
+		struct rtw89_dig_info dig;
 	} bbs[RTW89_PHY_NUM];
 
 	struct delayed_work track_work;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index e266ddae0c31b..bae8d86434900 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -5835,11 +5835,12 @@ static void rtw89_physts_parsing_init(struct rtw89_dev *rtwdev)
 		__rtw89_physts_parsing_init(rtwdev, RTW89_PHY_1);
 }
 
-static void rtw89_phy_dig_read_gain_table(struct rtw89_dev *rtwdev, int type)
+static void rtw89_phy_dig_read_gain_table(struct rtw89_dev *rtwdev,
+					  struct rtw89_bb_ctx *bb, int type)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	struct rtw89_dig_info *dig = &rtwdev->dig;
 	const struct rtw89_phy_dig_gain_cfg *cfg;
+	struct rtw89_dig_info *dig = &bb->dig;
 	const char *msg;
 	u8 i;
 	s8 gain_base;
@@ -5876,8 +5877,8 @@ static void rtw89_phy_dig_read_gain_table(struct rtw89_dev *rtwdev, int type)
 	}
 
 	for (i = 0; i < cfg->size; i++) {
-		tmp = rtw89_phy_read32_mask(rtwdev, cfg->table[i].addr,
-					    cfg->table[i].mask);
+		tmp = rtw89_phy_read32_idx(rtwdev, cfg->table[i].addr,
+					   cfg->table[i].mask, bb->phy_idx);
 		tmp >>= DIG_GAIN_SHIFT;
 		gain_arr[i] = sign_extend32(tmp, U4_MAX_BIT) + gain_base;
 		gain_base += DIG_GAIN;
@@ -5887,25 +5888,26 @@ static void rtw89_phy_dig_read_gain_table(struct rtw89_dev *rtwdev, int type)
 	}
 }
 
-static void rtw89_phy_dig_update_gain_para(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_update_gain_para(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	u32 tmp;
 	u8 i;
 
 	if (!rtwdev->hal.support_igi)
 		return;
 
-	tmp = rtw89_phy_read32_mask(rtwdev, R_PATH0_IB_PKPW,
-				    B_PATH0_IB_PKPW_MSK);
+	tmp = rtw89_phy_read32_idx(rtwdev, R_PATH0_IB_PKPW,
+				   B_PATH0_IB_PKPW_MSK, bb->phy_idx);
 	dig->ib_pkpwr = sign_extend32(tmp >> DIG_GAIN_SHIFT, U8_MAX_BIT);
-	dig->ib_pbk = rtw89_phy_read32_mask(rtwdev, R_PATH0_IB_PBK,
-					    B_PATH0_IB_PBK_MSK);
+	dig->ib_pbk = rtw89_phy_read32_idx(rtwdev, R_PATH0_IB_PBK,
+					   B_PATH0_IB_PBK_MSK, bb->phy_idx);
 	rtw89_debug(rtwdev, RTW89_DBG_DIG, "ib_pkpwr=%d, ib_pbk=%d\n",
 		    dig->ib_pkpwr, dig->ib_pbk);
 
 	for (i = RTW89_DIG_GAIN_LNA_G; i < RTW89_DIG_GAIN_MAX; i++)
-		rtw89_phy_dig_read_gain_table(rtwdev, i);
+		rtw89_phy_dig_read_gain_table(rtwdev, bb, i);
 }
 
 static const u8 rssi_nolink = 22;
@@ -5914,10 +5916,11 @@ static const u16 fa_th_2g[FA_TH_NUM] = {22, 44, 66, 88};
 static const u16 fa_th_5g[FA_TH_NUM] = {4, 8, 12, 16};
 static const u16 fa_th_nolink[FA_TH_NUM] = {196, 352, 440, 528};
 
-static void rtw89_phy_dig_update_rssi_info(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_update_rssi_info(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb)
 {
 	struct rtw89_phy_ch_info *ch_info = &rtwdev->ch_info;
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 
 	if (is_linked) {
@@ -5928,10 +5931,11 @@ static void rtw89_phy_dig_update_rssi_info(struct rtw89_dev *rtwdev)
 	}
 }
 
-static void rtw89_phy_dig_update_para(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_update_para(struct rtw89_dev *rtwdev,
+				      struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_mgnt_chan_get(rtwdev, bb->phy_idx);
+	struct rtw89_dig_info *dig = &bb->dig;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 	const u16 *fa_th_src = NULL;
 
@@ -5960,9 +5964,10 @@ static const u8 pd_low_th_offset = 16, dynamic_igi_min = 0x20;
 static const u8 igi_max_performance_mode = 0x5a;
 static const u8 dynamic_pd_threshold_max;
 
-static void rtw89_phy_dig_para_reset(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_para_reset(struct rtw89_dev *rtwdev,
+				     struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 
 	dig->cur_gaincode.lna_idx = LNA_IDX_MAX;
 	dig->cur_gaincode.tia_idx = TIA_IDX_MAX;
@@ -5978,15 +5983,27 @@ static void rtw89_phy_dig_para_reset(struct rtw89_dev *rtwdev)
 	dig->is_linked_pre = false;
 }
 
+static void __rtw89_phy_dig_init(struct rtw89_dev *rtwdev,
+				 struct rtw89_bb_ctx *bb)
+{
+	rtw89_debug(rtwdev, RTW89_DBG_DIG, "BB-%d dig_init\n", bb->phy_idx);
+
+	rtw89_phy_dig_update_gain_para(rtwdev, bb);
+	rtw89_phy_dig_reset(rtwdev, bb);
+}
+
 static void rtw89_phy_dig_init(struct rtw89_dev *rtwdev)
 {
-	rtw89_phy_dig_update_gain_para(rtwdev);
-	rtw89_phy_dig_reset(rtwdev);
+	struct rtw89_bb_ctx *bb;
+
+	rtw89_for_each_capab_bb(rtwdev, bb)
+		__rtw89_phy_dig_init(rtwdev, bb);
 }
 
-static u8 rtw89_phy_dig_lna_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi)
+static u8 rtw89_phy_dig_lna_idx_by_rssi(struct rtw89_dev *rtwdev,
+					struct rtw89_bb_ctx *bb, u8 rssi)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	u8 lna_idx;
 
 	if (rssi < dig->igi_rssi_th[0])
@@ -6005,9 +6022,10 @@ static u8 rtw89_phy_dig_lna_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi)
 	return lna_idx;
 }
 
-static u8 rtw89_phy_dig_tia_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi)
+static u8 rtw89_phy_dig_tia_idx_by_rssi(struct rtw89_dev *rtwdev,
+					struct rtw89_bb_ctx *bb, u8 rssi)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	u8 tia_idx;
 
 	if (rssi < dig->igi_rssi_th[0])
@@ -6020,10 +6038,11 @@ static u8 rtw89_phy_dig_tia_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi)
 
 #define IB_PBK_BASE 110
 #define WB_RSSI_BASE 10
-static u8 rtw89_phy_dig_rxb_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi,
+static u8 rtw89_phy_dig_rxb_idx_by_rssi(struct rtw89_dev *rtwdev,
+					struct rtw89_bb_ctx *bb, u8 rssi,
 					struct rtw89_agc_gaincode_set *set)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	s8 lna_gain = dig->lna_gain[set->lna_idx];
 	s8 tia_gain = dig->tia_gain[set->tia_idx];
 	s32 wb_rssi = rssi + lna_gain + tia_gain;
@@ -6039,12 +6058,13 @@ static u8 rtw89_phy_dig_rxb_idx_by_rssi(struct rtw89_dev *rtwdev, u8 rssi,
 	return rxb_idx;
 }
 
-static void rtw89_phy_dig_gaincode_by_rssi(struct rtw89_dev *rtwdev, u8 rssi,
+static void rtw89_phy_dig_gaincode_by_rssi(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb, u8 rssi,
 					   struct rtw89_agc_gaincode_set *set)
 {
-	set->lna_idx = rtw89_phy_dig_lna_idx_by_rssi(rtwdev, rssi);
-	set->tia_idx = rtw89_phy_dig_tia_idx_by_rssi(rtwdev, rssi);
-	set->rxb_idx = rtw89_phy_dig_rxb_idx_by_rssi(rtwdev, rssi, set);
+	set->lna_idx = rtw89_phy_dig_lna_idx_by_rssi(rtwdev, bb, rssi);
+	set->tia_idx = rtw89_phy_dig_tia_idx_by_rssi(rtwdev, bb, rssi);
+	set->rxb_idx = rtw89_phy_dig_rxb_idx_by_rssi(rtwdev, bb, rssi, set);
 
 	rtw89_debug(rtwdev, RTW89_DBG_DIG,
 		    "final_rssi=%03d, (lna,tia,rab)=(%d,%d,%02d)\n",
@@ -6053,10 +6073,11 @@ static void rtw89_phy_dig_gaincode_by_rssi(struct rtw89_dev *rtwdev, u8 rssi,
 
 #define IGI_OFFSET_MAX 25
 #define IGI_OFFSET_MUL 2
-static void rtw89_phy_dig_igi_offset_by_env(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_igi_offset_by_env(struct rtw89_dev *rtwdev,
+					    struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
-	struct rtw89_env_monitor_info *env = &rtwdev->bbs[0].env_monitor;
+	struct rtw89_dig_info *dig = &bb->dig;
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
 	enum rtw89_dig_noisy_level noisy_lv;
 	u8 igi_offset = dig->fa_rssi_ofst;
 	u16 fa_ratio = 0;
@@ -6093,92 +6114,99 @@ static void rtw89_phy_dig_igi_offset_by_env(struct rtw89_dev *rtwdev)
 		    noisy_lv, igi_offset);
 }
 
-static void rtw89_phy_dig_set_lna_idx(struct rtw89_dev *rtwdev, u8 lna_idx)
+static void rtw89_phy_dig_set_lna_idx(struct rtw89_dev *rtwdev,
+				      struct rtw89_bb_ctx *bb, u8 lna_idx)
 {
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p0_lna_init.addr,
-			       dig_regs->p0_lna_init.mask, lna_idx);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p1_lna_init.addr,
-			       dig_regs->p1_lna_init.mask, lna_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p0_lna_init.addr,
+			      dig_regs->p0_lna_init.mask, lna_idx, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p1_lna_init.addr,
+			      dig_regs->p1_lna_init.mask, lna_idx, bb->phy_idx);
 }
 
-static void rtw89_phy_dig_set_tia_idx(struct rtw89_dev *rtwdev, u8 tia_idx)
+static void rtw89_phy_dig_set_tia_idx(struct rtw89_dev *rtwdev,
+				      struct rtw89_bb_ctx *bb, u8 tia_idx)
 {
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p0_tia_init.addr,
-			       dig_regs->p0_tia_init.mask, tia_idx);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p1_tia_init.addr,
-			       dig_regs->p1_tia_init.mask, tia_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p0_tia_init.addr,
+			      dig_regs->p0_tia_init.mask, tia_idx, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p1_tia_init.addr,
+			      dig_regs->p1_tia_init.mask, tia_idx, bb->phy_idx);
 }
 
-static void rtw89_phy_dig_set_rxb_idx(struct rtw89_dev *rtwdev, u8 rxb_idx)
+static void rtw89_phy_dig_set_rxb_idx(struct rtw89_dev *rtwdev,
+				      struct rtw89_bb_ctx *bb, u8 rxb_idx)
 {
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p0_rxb_init.addr,
-			       dig_regs->p0_rxb_init.mask, rxb_idx);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p1_rxb_init.addr,
-			       dig_regs->p1_rxb_init.mask, rxb_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p0_rxb_init.addr,
+			      dig_regs->p0_rxb_init.mask, rxb_idx, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p1_rxb_init.addr,
+			      dig_regs->p1_rxb_init.mask, rxb_idx, bb->phy_idx);
 }
 
 static void rtw89_phy_dig_set_igi_cr(struct rtw89_dev *rtwdev,
+				     struct rtw89_bb_ctx *bb,
 				     const struct rtw89_agc_gaincode_set set)
 {
 	if (!rtwdev->hal.support_igi)
 		return;
 
-	rtw89_phy_dig_set_lna_idx(rtwdev, set.lna_idx);
-	rtw89_phy_dig_set_tia_idx(rtwdev, set.tia_idx);
-	rtw89_phy_dig_set_rxb_idx(rtwdev, set.rxb_idx);
+	rtw89_phy_dig_set_lna_idx(rtwdev, bb, set.lna_idx);
+	rtw89_phy_dig_set_tia_idx(rtwdev, bb, set.tia_idx);
+	rtw89_phy_dig_set_rxb_idx(rtwdev, bb, set.rxb_idx);
 
 	rtw89_debug(rtwdev, RTW89_DBG_DIG, "Set (lna,tia,rxb)=((%d,%d,%02d))\n",
 		    set.lna_idx, set.tia_idx, set.rxb_idx);
 }
 
 static void rtw89_phy_dig_sdagc_follow_pagc_config(struct rtw89_dev *rtwdev,
+						   struct rtw89_bb_ctx *bb,
 						   bool enable)
 {
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p0_p20_pagcugc_en.addr,
-			       dig_regs->p0_p20_pagcugc_en.mask, enable);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p0_s20_pagcugc_en.addr,
-			       dig_regs->p0_s20_pagcugc_en.mask, enable);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p1_p20_pagcugc_en.addr,
-			       dig_regs->p1_p20_pagcugc_en.mask, enable);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->p1_s20_pagcugc_en.addr,
-			       dig_regs->p1_s20_pagcugc_en.mask, enable);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p0_p20_pagcugc_en.addr,
+			      dig_regs->p0_p20_pagcugc_en.mask, enable, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p0_s20_pagcugc_en.addr,
+			      dig_regs->p0_s20_pagcugc_en.mask, enable, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p1_p20_pagcugc_en.addr,
+			      dig_regs->p1_p20_pagcugc_en.mask, enable, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->p1_s20_pagcugc_en.addr,
+			      dig_regs->p1_s20_pagcugc_en.mask, enable, bb->phy_idx);
 
 	rtw89_debug(rtwdev, RTW89_DBG_DIG, "sdagc_follow_pagc=%d\n", enable);
 }
 
-static void rtw89_phy_dig_config_igi(struct rtw89_dev *rtwdev)
+static void rtw89_phy_dig_config_igi(struct rtw89_dev *rtwdev,
+				     struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 
 	if (!rtwdev->hal.support_igi)
 		return;
 
 	if (dig->force_gaincode_idx_en) {
-		rtw89_phy_dig_set_igi_cr(rtwdev, dig->force_gaincode);
+		rtw89_phy_dig_set_igi_cr(rtwdev, bb, dig->force_gaincode);
 		rtw89_debug(rtwdev, RTW89_DBG_DIG,
 			    "Force gaincode index enabled.\n");
 	} else {
-		rtw89_phy_dig_gaincode_by_rssi(rtwdev, dig->igi_fa_rssi,
+		rtw89_phy_dig_gaincode_by_rssi(rtwdev, bb, dig->igi_fa_rssi,
 					       &dig->cur_gaincode);
-		rtw89_phy_dig_set_igi_cr(rtwdev, dig->cur_gaincode);
+		rtw89_phy_dig_set_igi_cr(rtwdev, bb, dig->cur_gaincode);
 	}
 }
 
-static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi,
-				    bool enable)
+static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev,
+				    struct rtw89_bb_ctx *bb,
+				    u8 rssi, bool enable)
 {
-	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	const struct rtw89_chan *chan = rtw89_mgnt_chan_get(rtwdev, bb->phy_idx);
 	const struct rtw89_dig_regs *dig_regs = rtwdev->chip->dig_regs;
 	enum rtw89_bandwidth cbw = chan->band_width;
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	u8 final_rssi = 0, under_region = dig->pd_low_th_ofst;
 	u8 ofdm_cca_th;
 	s8 cck_cca_th;
@@ -6220,10 +6248,10 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi,
 			    "Dynamic PD th disabled, Set PD_low_bd=0\n");
 	}
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->seg0_pd_reg,
-			       dig_regs->pd_lower_bound_mask, pd_val);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->seg0_pd_reg,
-			       dig_regs->pd_spatial_reuse_en, enable);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->seg0_pd_reg,
+			      dig_regs->pd_lower_bound_mask, pd_val, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->seg0_pd_reg,
+			      dig_regs->pd_spatial_reuse_en, enable, bb->phy_idx);
 
 	if (!rtwdev->hal.support_cckpd)
 		return;
@@ -6235,29 +6263,29 @@ static void rtw89_phy_dig_dyn_pd_th(struct rtw89_dev *rtwdev, u8 rssi,
 		    "igi=%d, cck_ccaTH=%d, backoff=%d, cck_PD_low=((%d))dB\n",
 		    final_rssi, cck_cca_th, under_region, pd_val);
 
-	rtw89_phy_write32_mask(rtwdev, dig_regs->bmode_pd_reg,
-			       dig_regs->bmode_cca_rssi_limit_en, enable);
-	rtw89_phy_write32_mask(rtwdev, dig_regs->bmode_pd_lower_bound_reg,
-			       dig_regs->bmode_rssi_nocca_low_th_mask, pd_val);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->bmode_pd_reg,
+			      dig_regs->bmode_cca_rssi_limit_en, enable, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, dig_regs->bmode_pd_lower_bound_reg,
+			      dig_regs->bmode_rssi_nocca_low_th_mask, pd_val, bb->phy_idx);
 }
 
-void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev)
+void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 
 	dig->bypass_dig = false;
-	rtw89_phy_dig_para_reset(rtwdev);
-	rtw89_phy_dig_set_igi_cr(rtwdev, dig->force_gaincode);
-	rtw89_phy_dig_dyn_pd_th(rtwdev, rssi_nolink, false);
-	rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, false);
-	rtw89_phy_dig_update_para(rtwdev);
+	rtw89_phy_dig_para_reset(rtwdev, bb);
+	rtw89_phy_dig_set_igi_cr(rtwdev, bb, dig->force_gaincode);
+	rtw89_phy_dig_dyn_pd_th(rtwdev, bb, rssi_nolink, false);
+	rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, bb, false);
+	rtw89_phy_dig_update_para(rtwdev, bb);
 }
 
 #define IGI_RSSI_MIN 10
 #define ABS_IGI_MIN 0xc
-void rtw89_phy_dig(struct rtw89_dev *rtwdev)
+static void __rtw89_phy_dig(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_dig_info *dig = &rtwdev->dig;
+	struct rtw89_dig_info *dig = &bb->dig;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 	u8 igi_min;
 
@@ -6266,20 +6294,22 @@ void rtw89_phy_dig(struct rtw89_dev *rtwdev)
 		return;
 	}
 
-	rtw89_phy_dig_update_rssi_info(rtwdev);
+	rtw89_debug(rtwdev, RTW89_DBG_DIG, "BB-%d dig track\n", bb->phy_idx);
+
+	rtw89_phy_dig_update_rssi_info(rtwdev, bb);
 
 	if (!dig->is_linked_pre && is_linked) {
 		rtw89_debug(rtwdev, RTW89_DBG_DIG, "First connected\n");
-		rtw89_phy_dig_update_para(rtwdev);
+		rtw89_phy_dig_update_para(rtwdev, bb);
 		dig->igi_fa_rssi = dig->igi_rssi;
 	} else if (dig->is_linked_pre && !is_linked) {
 		rtw89_debug(rtwdev, RTW89_DBG_DIG, "First disconnected\n");
-		rtw89_phy_dig_update_para(rtwdev);
+		rtw89_phy_dig_update_para(rtwdev, bb);
 		dig->igi_fa_rssi = dig->igi_rssi;
 	}
 	dig->is_linked_pre = is_linked;
 
-	rtw89_phy_dig_igi_offset_by_env(rtwdev);
+	rtw89_phy_dig_igi_offset_by_env(rtwdev, bb);
 
 	igi_min = max_t(int, dig->igi_rssi - IGI_RSSI_MIN, 0);
 	dig->dyn_igi_max = min(igi_min + IGI_OFFSET_MAX, igi_max_performance_mode);
@@ -6298,14 +6328,22 @@ void rtw89_phy_dig(struct rtw89_dev *rtwdev)
 		    dig->igi_rssi, dig->dyn_igi_max, dig->dyn_igi_min,
 		    dig->igi_fa_rssi);
 
-	rtw89_phy_dig_config_igi(rtwdev);
+	rtw89_phy_dig_config_igi(rtwdev, bb);
 
-	rtw89_phy_dig_dyn_pd_th(rtwdev, dig->igi_fa_rssi, dig->dyn_pd_th_en);
+	rtw89_phy_dig_dyn_pd_th(rtwdev, bb, dig->igi_fa_rssi, dig->dyn_pd_th_en);
 
 	if (dig->dyn_pd_th_en && dig->igi_fa_rssi > dig->dyn_pd_th_max)
-		rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, true);
+		rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, bb, true);
 	else
-		rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, false);
+		rtw89_phy_dig_sdagc_follow_pagc_config(rtwdev, bb, false);
+}
+
+void rtw89_phy_dig(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_bb_ctx *bb;
+
+	rtw89_for_each_active_bb(rtwdev, bb)
+		__rtw89_phy_dig(rtwdev, bb);
 }
 
 static void __rtw89_phy_tx_path_div_sta_iter(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 08b635c93ac3e..db748c7453cd9 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -985,7 +985,7 @@ void rtw89_phy_stat_track(struct rtw89_dev *rtwdev);
 void rtw89_phy_env_monitor_track(struct rtw89_dev *rtwdev);
 void rtw89_phy_set_phy_regs(struct rtw89_dev *rtwdev, u32 addr, u32 mask,
 			    u32 val);
-void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev);
+void rtw89_phy_dig_reset(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb);
 void rtw89_phy_dig(struct rtw89_dev *rtwdev);
 void rtw89_phy_tx_path_div_track(struct rtw89_dev *rtwdev);
 void rtw89_phy_antdiv_parse(struct rtw89_dev *rtwdev,

From 786e485c61efaca1b986fc5b83b1d2132fe5b88b Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:25 +0800
Subject: [PATCH 0058/2753] wifi: rtw89: phy: support ch_info per PHY

The ch_info is to record current channel info such as minimum RSSI of
connected stations, and to assist in dynamic mechanisms of DIG and EDCCA.

Move the struct to PHY context, so the dynamic mechanisms can use the info
of the same PHY.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  1 +
 drivers/net/wireless/realtek/rtw89/phy.c  | 18 ++++++++++++------
 2 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 42632d1c981fc..ca2719957bbfb 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5696,6 +5696,7 @@ struct rtw89_dev {
 		enum rtw89_phy_idx phy_idx;
 		struct rtw89_env_monitor_info env_monitor;
 		struct rtw89_dig_info dig;
+		struct rtw89_phy_ch_info ch_info;
 	} bbs[RTW89_PHY_NUM];
 
 	struct delayed_work track_work;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index bae8d86434900..e07f874590d2c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -5115,7 +5115,6 @@ static void rtw89_phy_stat_thermal_update(struct rtw89_dev *rtwdev)
 
 struct rtw89_phy_iter_rssi_data {
 	struct rtw89_dev *rtwdev;
-	struct rtw89_phy_ch_info *ch_info;
 	bool rssi_changed;
 };
 
@@ -5123,10 +5122,15 @@ static
 void __rtw89_phy_stat_rssi_update_iter(struct rtw89_sta_link *rtwsta_link,
 				       struct rtw89_phy_iter_rssi_data *rssi_data)
 {
-	struct rtw89_phy_ch_info *ch_info = rssi_data->ch_info;
+	struct rtw89_vif_link *rtwvif_link = rtwsta_link->rtwvif_link;
+	struct rtw89_dev *rtwdev = rssi_data->rtwdev;
+	struct rtw89_phy_ch_info *ch_info;
+	struct rtw89_bb_ctx *bb;
 	unsigned long rssi_curr;
 
 	rssi_curr = ewma_rssi_read(&rtwsta_link->avg_rssi);
+	bb = rtw89_get_bb_ctx(rtwdev, rtwvif_link->phy_idx);
+	ch_info = &bb->ch_info;
 
 	if (rssi_curr < ch_info->rssi_min) {
 		ch_info->rssi_min = rssi_curr;
@@ -5157,11 +5161,13 @@ static void rtw89_phy_stat_rssi_update_iter(void *data,
 
 static void rtw89_phy_stat_rssi_update(struct rtw89_dev *rtwdev)
 {
-	struct rtw89_phy_iter_rssi_data rssi_data = {0};
+	struct rtw89_phy_iter_rssi_data rssi_data = {};
+	struct rtw89_bb_ctx *bb;
 
 	rssi_data.rtwdev = rtwdev;
-	rssi_data.ch_info = &rtwdev->ch_info;
-	rssi_data.ch_info->rssi_min = U8_MAX;
+	rtw89_for_each_active_bb(rtwdev, bb)
+		bb->ch_info.rssi_min = U8_MAX;
+
 	ieee80211_iterate_stations_atomic(rtwdev->hw,
 					  rtw89_phy_stat_rssi_update_iter,
 					  &rssi_data);
@@ -5919,7 +5925,7 @@ static const u16 fa_th_nolink[FA_TH_NUM] = {196, 352, 440, 528};
 static void rtw89_phy_dig_update_rssi_info(struct rtw89_dev *rtwdev,
 					   struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_phy_ch_info *ch_info = &rtwdev->ch_info;
+	struct rtw89_phy_ch_info *ch_info = &bb->ch_info;
 	struct rtw89_dig_info *dig = &bb->dig;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 

From af5fa884e22feae23643515bbeec53a021e06b84 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:26 +0800
Subject: [PATCH 0059/2753] wifi: rtw89: phy: support EDCCA per PHY

Dynamic mechanism EDCCA (Energy Detection Clear Channel Assessment) is to
dynamically adjusted to make EDCCA suitable for situations.

Use PHY context to support two PHY.

For the EDCCA log part, registers to report EDCCA for PHY 1 is not a
simple offset from PHY 0, so add them by separate patch.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |   6 +-
 drivers/net/wireless/realtek/rtw89/core.h |   3 +-
 drivers/net/wireless/realtek/rtw89/phy.c  | 107 +++++++++++++---------
 drivers/net/wireless/realtek/rtw89/phy.h  |   5 +-
 4 files changed, 73 insertions(+), 48 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index e39fb696ac13c..b730f70c82aa9 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4906,6 +4906,7 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 {
 	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev,
 						       rtwvif_link->chanctx_idx);
+	struct rtw89_bb_ctx *bb = rtw89_get_bb_ctx(rtwdev, rtwvif_link->phy_idx);
 
 	rtwdev->scanning = true;
 	rtw89_leave_lps(rtwdev);
@@ -4916,7 +4917,7 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 	rtw89_btc_ntfy_scan_start(rtwdev, rtwvif_link->phy_idx, chan->band_type);
 	rtw89_chip_rfk_scan(rtwdev, rtwvif_link, true);
 	rtw89_hci_recalc_int_mit(rtwdev);
-	rtw89_phy_config_edcca(rtwdev, true);
+	rtw89_phy_config_edcca(rtwdev, bb, true);
 
 	rtw89_fw_h2c_cam(rtwdev, rtwvif_link, NULL, mac_addr);
 }
@@ -4941,7 +4942,8 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 
 	rtw89_chip_rfk_scan(rtwdev, rtwvif_link, false);
 	rtw89_btc_ntfy_scan_finish(rtwdev, rtwvif_link->phy_idx);
-	rtw89_phy_config_edcca(rtwdev, false);
+	bb = rtw89_get_bb_ctx(rtwdev, rtwvif_link->phy_idx);
+	rtw89_phy_config_edcca(rtwdev, bb, false);
 
 	rtwdev->scanning = false;
 	rtw89_for_each_active_bb(rtwdev, bb)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index ca2719957bbfb..c8b4809c2f368 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4768,7 +4768,6 @@ struct rtw89_hal {
 	enum rtw89_entity_mode entity_mode;
 	struct rtw89_entity_mgnt entity_mgnt;
 
-	struct rtw89_edcca_bak edcca_bak;
 	u32 disabled_dm_bitmap; /* bitmap of enum rtw89_dm_type */
 
 	u8 thermal_prot_th;
@@ -5683,7 +5682,6 @@ struct rtw89_dev {
 	struct rtw89_power_trim_info pwr_trim;
 
 	struct rtw89_cfo_tracking_info cfo_tracking;
-	struct rtw89_phy_ch_info ch_info;
 	union {
 		struct rtw89_phy_bb_gain_info ax;
 		struct rtw89_phy_bb_gain_info_be be;
@@ -5697,6 +5695,7 @@ struct rtw89_dev {
 		struct rtw89_env_monitor_info env_monitor;
 		struct rtw89_dig_info dig;
 		struct rtw89_phy_ch_info ch_info;
+		struct rtw89_edcca_bak edcca_bak;
 	} bbs[RTW89_PHY_NUM];
 
 	struct delayed_work track_work;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index e07f874590d2c..f1029da4a78ea 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -6584,10 +6584,13 @@ static void rtw89_phy_env_monitor_init(struct rtw89_dev *rtwdev)
 		__rtw89_phy_env_monitor_init(rtwdev, bb);
 }
 
-static void rtw89_phy_edcca_init(struct rtw89_dev *rtwdev)
+static void __rtw89_phy_edcca_init(struct rtw89_dev *rtwdev,
+				   struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
-	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
+	struct rtw89_edcca_bak *edcca_bak = &bb->edcca_bak;
+
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA, "BB-%d edcca init\n", bb->phy_idx);
 
 	memset(edcca_bak, 0, sizeof(*edcca_bak));
 
@@ -6603,8 +6606,16 @@ static void rtw89_phy_edcca_init(struct rtw89_dev *rtwdev)
 		rtw89_phy_set_phy_regs(rtwdev, R_DFS_FFT_CG, B_DFS_FFT_EN, 1);
 	}
 
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->tx_collision_t2r_st,
-			       edcca_regs->tx_collision_t2r_st_mask, 0x29);
+	rtw89_phy_write32_idx(rtwdev, edcca_regs->tx_collision_t2r_st,
+			      edcca_regs->tx_collision_t2r_st_mask, 0x29, bb->phy_idx);
+}
+
+static void rtw89_phy_edcca_init(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_bb_ctx *bb;
+
+	rtw89_for_each_capab_bb(rtwdev, bb)
+		__rtw89_phy_edcca_init(rtwdev, bb);
 }
 
 void rtw89_phy_dm_init(struct rtw89_dev *rtwdev)
@@ -6967,42 +6978,43 @@ void rtw89_decode_chan_idx(struct rtw89_dev *rtwdev, u8 chan_idx,
 }
 EXPORT_SYMBOL(rtw89_decode_chan_idx);
 
-void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan)
+void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev,
+			    struct rtw89_bb_ctx *bb, bool scan)
 {
 	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
-	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
+	struct rtw89_edcca_bak *edcca_bak = &bb->edcca_bak;
 
 	if (scan) {
 		edcca_bak->a =
-			rtw89_phy_read32_mask(rtwdev, edcca_regs->edcca_level,
-					      edcca_regs->edcca_mask);
+			rtw89_phy_read32_idx(rtwdev, edcca_regs->edcca_level,
+					     edcca_regs->edcca_mask, bb->phy_idx);
 		edcca_bak->p =
-			rtw89_phy_read32_mask(rtwdev, edcca_regs->edcca_level,
-					      edcca_regs->edcca_p_mask);
+			rtw89_phy_read32_idx(rtwdev, edcca_regs->edcca_level,
+					     edcca_regs->edcca_p_mask, bb->phy_idx);
 		edcca_bak->ppdu =
-			rtw89_phy_read32_mask(rtwdev, edcca_regs->ppdu_level,
-					      edcca_regs->ppdu_mask);
-
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-				       edcca_regs->edcca_mask, EDCCA_MAX);
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-				       edcca_regs->edcca_p_mask, EDCCA_MAX);
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
-				       edcca_regs->ppdu_mask, EDCCA_MAX);
+			rtw89_phy_read32_idx(rtwdev, edcca_regs->ppdu_level,
+					     edcca_regs->ppdu_mask, bb->phy_idx);
+
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+				      edcca_regs->edcca_mask, EDCCA_MAX, bb->phy_idx);
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+				      edcca_regs->edcca_p_mask, EDCCA_MAX, bb->phy_idx);
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->ppdu_level,
+				      edcca_regs->ppdu_mask, EDCCA_MAX, bb->phy_idx);
 	} else {
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-				       edcca_regs->edcca_mask,
-				       edcca_bak->a);
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-				       edcca_regs->edcca_p_mask,
-				       edcca_bak->p);
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
-				       edcca_regs->ppdu_mask,
-				       edcca_bak->ppdu);
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+				      edcca_regs->edcca_mask,
+				      edcca_bak->a, bb->phy_idx);
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+				      edcca_regs->edcca_p_mask,
+				      edcca_bak->p, bb->phy_idx);
+		rtw89_phy_write32_idx(rtwdev, edcca_regs->ppdu_level,
+				      edcca_regs->ppdu_mask,
+				      edcca_bak->ppdu, bb->phy_idx);
 	}
 }
 
-static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev)
+static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
 	bool flag_fb, flag_p20, flag_s20, flag_s40, flag_s80;
@@ -7099,9 +7111,10 @@ static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev)
 		    pwdb_fb, pwdb_p20, pwdb_s20, pwdb_s40, pwdb_s80);
 }
 
-static u8 rtw89_phy_edcca_get_thre_by_rssi(struct rtw89_dev *rtwdev)
+static u8 rtw89_phy_edcca_get_thre_by_rssi(struct rtw89_dev *rtwdev,
+					   struct rtw89_bb_ctx *bb)
 {
-	struct rtw89_phy_ch_info *ch_info = &rtwdev->ch_info;
+	struct rtw89_phy_ch_info *ch_info = &bb->ch_info;
 	bool is_linked = rtwdev->total_sta_assoc > 0;
 	u8 rssi_min = ch_info->rssi_min >> 1;
 	u8 edcca_thre;
@@ -7117,13 +7130,13 @@ static u8 rtw89_phy_edcca_get_thre_by_rssi(struct rtw89_dev *rtwdev)
 	return edcca_thre;
 }
 
-void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev)
+void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
-	struct rtw89_edcca_bak *edcca_bak = &rtwdev->hal.edcca_bak;
+	struct rtw89_edcca_bak *edcca_bak = &bb->edcca_bak;
 	u8 th;
 
-	th = rtw89_phy_edcca_get_thre_by_rssi(rtwdev);
+	th = rtw89_phy_edcca_get_thre_by_rssi(rtwdev, bb);
 	if (th == edcca_bak->th_old)
 		return;
 
@@ -7132,23 +7145,33 @@ void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev)
 	rtw89_debug(rtwdev, RTW89_DBG_EDCCA,
 		    "[EDCCA]: Normal Mode, EDCCA_th = %d\n", th);
 
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-			       edcca_regs->edcca_mask, th);
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->edcca_level,
-			       edcca_regs->edcca_p_mask, th);
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->ppdu_level,
-			       edcca_regs->ppdu_mask, th);
+	rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+			      edcca_regs->edcca_mask, th, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, edcca_regs->edcca_level,
+			      edcca_regs->edcca_p_mask, th, bb->phy_idx);
+	rtw89_phy_write32_idx(rtwdev, edcca_regs->ppdu_level,
+			      edcca_regs->ppdu_mask, th, bb->phy_idx);
+}
+
+static
+void __rtw89_phy_edcca_track(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
+{
+	rtw89_debug(rtwdev, RTW89_DBG_EDCCA, "BB-%d edcca track\n", bb->phy_idx);
+
+	rtw89_phy_edcca_thre_calc(rtwdev, bb);
+	rtw89_phy_edcca_log(rtwdev, bb);
 }
 
 void rtw89_phy_edcca_track(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_hal *hal = &rtwdev->hal;
+	struct rtw89_bb_ctx *bb;
 
 	if (hal->disabled_dm_bitmap & BIT(RTW89_DM_DYNAMIC_EDCCA))
 		return;
 
-	rtw89_phy_edcca_thre_calc(rtwdev);
-	rtw89_phy_edcca_log(rtwdev);
+	rtw89_for_each_active_bb(rtwdev, bb)
+		__rtw89_phy_edcca_track(rtwdev, bb);
 }
 
 enum rtw89_rf_path_bit rtw89_phy_get_kpath(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index db748c7453cd9..33d466c519e3a 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -1002,9 +1002,10 @@ void rtw89_phy_ul_tb_ctrl_track(struct rtw89_dev *rtwdev);
 u8 rtw89_encode_chan_idx(struct rtw89_dev *rtwdev, u8 central_ch, u8 band);
 void rtw89_decode_chan_idx(struct rtw89_dev *rtwdev, u8 chan_idx,
 			   u8 *ch, enum nl80211_band *band);
-void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev, bool scan);
+void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev,
+			    struct rtw89_bb_ctx *bb, bool scan);
 void rtw89_phy_edcca_track(struct rtw89_dev *rtwdev);
-void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev);
+void rtw89_phy_edcca_thre_calc(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb);
 enum rtw89_rf_path_bit rtw89_phy_get_kpath(struct rtw89_dev *rtwdev,
 					   enum rtw89_phy_idx phy_idx);
 enum rtw89_rf_path rtw89_phy_get_syn_sel(struct rtw89_dev *rtwdev,

From 0a51f04a9afe98bf60dbfcef5ccf6a120398c356 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:27 +0800
Subject: [PATCH 0060/2753] wifi: rtw89: phy: support EDCCA log per PHY

The registers of EDCCA log for PHY 1 isn't a simple offset, so define
them accordingly. Then the function use register set to access reports
according to phy_idx.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     | 10 ++--
 drivers/net/wireless/realtek/rtw89/phy.c      | 48 +++++++++++--------
 drivers/net/wireless/realtek/rtw89/reg.h      |  5 ++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c | 15 ++++--
 drivers/net/wireless/realtek/rtw89/rtw8852a.c | 15 ++++--
 drivers/net/wireless/realtek/rtw89/rtw8852b.c | 15 ++++--
 .../net/wireless/realtek/rtw89/rtw8852bt.c    | 15 ++++--
 drivers/net/wireless/realtek/rtw89/rtw8852c.c | 15 ++++--
 drivers/net/wireless/realtek/rtw89/rtw8922a.c | 15 ++++--
 9 files changed, 104 insertions(+), 49 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index c8b4809c2f368..970730291e567 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4190,10 +4190,12 @@ struct rtw89_edcca_regs {
 	u32 edcca_p_mask;
 	u32 ppdu_level;
 	u32 ppdu_mask;
-	u32 rpt_a;
-	u32 rpt_b;
-	u32 rpt_sel;
-	u32 rpt_sel_mask;
+	struct rtw89_edcca_p_regs {
+		u32 rpt_a;
+		u32 rpt_b;
+		u32 rpt_sel;
+		u32 rpt_sel_mask;
+	} p[RTW89_PHY_NUM];
 	u32 rpt_sel_be;
 	u32 rpt_sel_be_mask;
 	u32 tx_collision_t2r_st;
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index f1029da4a78ea..a5299295b7774 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -7017,6 +7017,7 @@ void rtw89_phy_config_edcca(struct rtw89_dev *rtwdev,
 static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *bb)
 {
 	const struct rtw89_edcca_regs *edcca_regs = rtwdev->chip->edcca_regs;
+	const struct rtw89_edcca_p_regs *edcca_p_regs;
 	bool flag_fb, flag_p20, flag_s20, flag_s40, flag_s80;
 	s8 pwdb_fb, pwdb_p20, pwdb_s20, pwdb_s40, pwdb_s80;
 	u8 path, per20_bitmap;
@@ -7026,13 +7027,18 @@ static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *b
 	if (!rtw89_debug_is_enabled(rtwdev, RTW89_DBG_EDCCA))
 		return;
 
+	if (bb->phy_idx == RTW89_PHY_1)
+		edcca_p_regs = &edcca_regs->p[RTW89_PHY_1];
+	else
+		edcca_p_regs = &edcca_regs->p[RTW89_PHY_0];
+
 	if (rtwdev->chip->chip_id == RTL8922A)
 		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
 				       edcca_regs->rpt_sel_be_mask, 0);
 
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-			       edcca_regs->rpt_sel_mask, 0);
-	tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+	rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+			       edcca_p_regs->rpt_sel_mask, 0);
+	tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_b);
 	path = u32_get_bits(tmp, B_EDCCA_RPT_B_PATH_MASK);
 	flag_s80 = u32_get_bits(tmp, B_EDCCA_RPT_B_S80);
 	flag_s40 = u32_get_bits(tmp, B_EDCCA_RPT_B_S40);
@@ -7043,19 +7049,19 @@ static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *b
 	pwdb_p20 = u32_get_bits(tmp, MASKBYTE2);
 	pwdb_fb = u32_get_bits(tmp, MASKBYTE3);
 
-	rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-			       edcca_regs->rpt_sel_mask, 4);
-	tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+	rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+			       edcca_p_regs->rpt_sel_mask, 4);
+	tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_b);
 	pwdb_s80 = u32_get_bits(tmp, MASKBYTE1);
 	pwdb_s40 = u32_get_bits(tmp, MASKBYTE2);
 
-	per20_bitmap = rtw89_phy_read32_mask(rtwdev, edcca_regs->rpt_a,
+	per20_bitmap = rtw89_phy_read32_mask(rtwdev, edcca_p_regs->rpt_a,
 					     MASKBYTE0);
 
 	if (rtwdev->chip->chip_id == RTL8922A) {
 		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
 				       edcca_regs->rpt_sel_be_mask, 4);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_b);
 		pwdb[0] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[1] = u32_get_bits(tmp, MASKBYTE2);
 		pwdb[2] = u32_get_bits(tmp, MASKBYTE1);
@@ -7063,33 +7069,33 @@ static void rtw89_phy_edcca_log(struct rtw89_dev *rtwdev, struct rtw89_bb_ctx *b
 
 		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel_be,
 				       edcca_regs->rpt_sel_be_mask, 5);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_b);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_b);
 		pwdb[4] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[5] = u32_get_bits(tmp, MASKBYTE2);
 		pwdb[6] = u32_get_bits(tmp, MASKBYTE1);
 		pwdb[7] = u32_get_bits(tmp, MASKBYTE0);
 	} else {
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-				       edcca_regs->rpt_sel_mask, 0);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+				       edcca_p_regs->rpt_sel_mask, 0);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_a);
 		pwdb[0] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[1] = u32_get_bits(tmp, MASKBYTE2);
 
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-				       edcca_regs->rpt_sel_mask, 1);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+				       edcca_p_regs->rpt_sel_mask, 1);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_a);
 		pwdb[2] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[3] = u32_get_bits(tmp, MASKBYTE2);
 
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-				       edcca_regs->rpt_sel_mask, 2);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+				       edcca_p_regs->rpt_sel_mask, 2);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_a);
 		pwdb[4] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[5] = u32_get_bits(tmp, MASKBYTE2);
 
-		rtw89_phy_write32_mask(rtwdev, edcca_regs->rpt_sel,
-				       edcca_regs->rpt_sel_mask, 3);
-		tmp = rtw89_phy_read32(rtwdev, edcca_regs->rpt_a);
+		rtw89_phy_write32_mask(rtwdev, edcca_p_regs->rpt_sel,
+				       edcca_p_regs->rpt_sel_mask, 3);
+		tmp = rtw89_phy_read32(rtwdev, edcca_p_regs->rpt_a);
 		pwdb[6] = u32_get_bits(tmp, MASKBYTE3);
 		pwdb[7] = u32_get_bits(tmp, MASKBYTE2);
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 10d0efa7a58ef..c992835d4b63c 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -8157,6 +8157,8 @@
 #define B_EDCCA_RPT_B_S40 BIT(4)
 #define B_EDCCA_RPT_B_S80 BIT(3)
 #define B_EDCCA_RPT_B_PATH_MASK GENMASK(2, 1)
+#define R_EDCCA_RPT_P1_A 0x1740
+#define R_EDCCA_RPT_P1_B 0x1744
 #define R_SWSI_V1 0x174C
 #define B_SWSI_W_BUSY_V1 BIT(24)
 #define B_SWSI_R_BUSY_V1 BIT(25)
@@ -8222,6 +8224,7 @@
 #define B_TXCKEN_FORCE_ALL GENMASK(24, 0)
 #define R_EDCCA_RPT_SEL 0x20CC
 #define B_EDCCA_RPT_SEL_MSK GENMASK(2, 0)
+#define B_EDCCA_RPT_SEL_P1_MSK GENMASK(5, 3)
 #define R_ADC_FIFO 0x20fc
 #define B_ADC_FIFO_RST GENMASK(31, 24)
 #define B_ADC_FIFO_RXK GENMASK(31, 16)
@@ -8291,6 +8294,8 @@
 #define B_P1_EN_SOUND_WO_NDP BIT(1)
 #define R_EDCCA_RPT_A_BE 0x2E38
 #define R_EDCCA_RPT_B_BE 0x2E3C
+#define R_EDCCA_RPT_P1_A_BE 0x2E40
+#define R_EDCCA_RPT_P1_B_BE 0x2E44
 #define R_S1_HW_SI_DIS 0x3200
 #define B_S1_HW_SI_DIS_W_R_TRIG GENMASK(30, 28)
 #define R_P1_RXCK 0x32A0
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 0487d1cbe6057..82289dbad1f4d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -224,10 +224,17 @@ static const struct rtw89_edcca_regs rtw8851b_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
 	.ppdu_mask			= B_EDCCA_LVL_MSK3,
-	.rpt_a				= R_EDCCA_RPT_A,
-	.rpt_b				= R_EDCCA_RPT_B,
-	.rpt_sel			= R_EDCCA_RPT_SEL,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A,
+		.rpt_b			= R_EDCCA_RPT_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A,
+		.rpt_b			= R_EDCCA_RPT_P1_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
 	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 8a9a5201b2ee6..2046832d021fd 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -522,10 +522,17 @@ static const struct rtw89_edcca_regs rtw8852a_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_EDCCA_LVL,
 	.ppdu_mask			= B_EDCCA_LVL_MSK3,
-	.rpt_a				= R_EDCCA_RPT_A,
-	.rpt_b				= R_EDCCA_RPT_B,
-	.rpt_sel			= R_EDCCA_RPT_SEL,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A,
+		.rpt_b			= R_EDCCA_RPT_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A,
+		.rpt_b			= R_EDCCA_RPT_P1_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
 	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index cbaf54f88af6f..652914a362451 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -189,10 +189,17 @@ static const struct rtw89_edcca_regs rtw8852b_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
 	.ppdu_mask			= B_EDCCA_LVL_MSK3,
-	.rpt_a				= R_EDCCA_RPT_A,
-	.rpt_b				= R_EDCCA_RPT_B,
-	.rpt_sel			= R_EDCCA_RPT_SEL,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A,
+		.rpt_b			= R_EDCCA_RPT_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A,
+		.rpt_b			= R_EDCCA_RPT_P1_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
 	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index c0ae5dca30492..6f15245b2f749 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -187,10 +187,17 @@ static const struct rtw89_edcca_regs rtw8852bt_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_EDCCA_LVL_V1,
 	.ppdu_mask			= B_EDCCA_LVL_MSK3,
-	.rpt_a				= R_EDCCA_RPT_A,
-	.rpt_b				= R_EDCCA_RPT_B,
-	.rpt_sel			= R_EDCCA_RPT_SEL,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A,
+		.rpt_b			= R_EDCCA_RPT_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A,
+		.rpt_b			= R_EDCCA_RPT_P1_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
 	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 106df618bb588..ecc1ff3585831 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -186,10 +186,17 @@ static const struct rtw89_edcca_regs rtw8852c_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_EDCCA_LVL,
 	.ppdu_mask			= B_EDCCA_LVL_MSK3,
-	.rpt_a				= R_EDCCA_RPT_A,
-	.rpt_b				= R_EDCCA_RPT_B,
-	.rpt_sel			= R_EDCCA_RPT_SEL,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A,
+		.rpt_b			= R_EDCCA_RPT_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A,
+		.rpt_b			= R_EDCCA_RPT_P1_B,
+		.rpt_sel		= R_EDCCA_RPT_SEL,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST,
 	.tx_collision_t2r_st_mask	= B_TX_COLLISION_T2R_ST_M,
 };
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 11d66bfceb15f..898a65a721dc4 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -205,10 +205,17 @@ static const struct rtw89_edcca_regs rtw8922a_edcca_regs = {
 	.edcca_p_mask			= B_EDCCA_LVL_MSK1,
 	.ppdu_level			= R_SEG0R_PPDU_LVL_BE,
 	.ppdu_mask			= B_EDCCA_LVL_MSK1,
-	.rpt_a				= R_EDCCA_RPT_A_BE,
-	.rpt_b				= R_EDCCA_RPT_B_BE,
-	.rpt_sel			= R_EDCCA_RPT_SEL_BE,
-	.rpt_sel_mask			= B_EDCCA_RPT_SEL_MSK,
+	.p = {{
+		.rpt_a			= R_EDCCA_RPT_A_BE,
+		.rpt_b			= R_EDCCA_RPT_B_BE,
+		.rpt_sel		= R_EDCCA_RPT_SEL_BE,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_MSK,
+	}, {
+		.rpt_a			= R_EDCCA_RPT_P1_A_BE,
+		.rpt_b			= R_EDCCA_RPT_P1_B_BE,
+		.rpt_sel		= R_EDCCA_RPT_SEL_BE,
+		.rpt_sel_mask		= B_EDCCA_RPT_SEL_P1_MSK,
+	}},
 	.rpt_sel_be			= R_EDCCA_RPTREG_SEL_BE,
 	.rpt_sel_be_mask		= B_EDCCA_RPTREG_SEL_BE_MSK,
 	.tx_collision_t2r_st		= R_TX_COLLISION_T2R_ST_BE,

From 076652f56ed6c5eea2e2c05b1fc805094045c7b9 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Fri, 17 Jan 2025 15:28:28 +0800
Subject: [PATCH 0061/2753] wifi: rtw89: phy: disable CFO track when two PHY
 are working simultaneously

To have good performance, adjust hardware XTAL to track CFO (carrier
frequency offset). However, there is only one hardware XTAL, so it is not
possible to track on two PHY simultaneously. It also can't track on single
one PHY when two PHY are working, because the adjustment of XTAL will
affect all PHY. Thus, disable CFO track for this case.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250117072828.16728-9-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/phy.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index a5299295b7774..5b0cf8314fb2a 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -4600,7 +4600,7 @@ static void rtw89_phy_cfo_dm(struct rtw89_dev *rtwdev)
 	cfo->dcfo_avg = 0;
 	rtw89_debug(rtwdev, RTW89_DBG_CFO, "CFO:total_sta_assoc=%d\n",
 		    rtwdev->total_sta_assoc);
-	if (rtwdev->total_sta_assoc == 0) {
+	if (rtwdev->total_sta_assoc == 0 || rtw89_is_mlo_1_1(rtwdev)) {
 		rtw89_phy_cfo_reset(rtwdev);
 		return;
 	}

From e7196b32a43de0e230b29b5682ea7af83568b903 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 20 Jan 2025 11:27:21 +0800
Subject: [PATCH 0062/2753] wifi: rtw89: regd: support loading regd table from
 fw element

Regd table is a table that we use to describe how to map Realtek RF TX
power settings on different countries. Originally, a common regd table
for all chips is implemented in driver. However, in order to work on all
chips, the common regd table might have some trade-off. So now, there are
also an individual regd table for some chips. And, we support loading it
from FW element.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250120032723.19042-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 14 ++++
 drivers/net/wireless/realtek/rtw89/fw.c   | 86 +++++++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h   | 22 ++++++
 drivers/net/wireless/realtek/rtw89/regd.c | 66 +++++++++++------
 4 files changed, 166 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 970730291e567..680e80b06f014 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -22,6 +22,7 @@ struct rtw89_h2c_rf_tssi;
 struct rtw89_fw_txpwr_track_cfg;
 struct rtw89_phy_rfk_log_fmt;
 struct rtw89_debugfs;
+struct rtw89_regd_data;
 
 extern const struct ieee80211_ops rtw89_ops;
 
@@ -718,6 +719,7 @@ enum rtw89_ofdma_type {
 	RTW89_OFDMA_NUM,
 };
 
+/* neither insert new in the middle, nor change any given definition */
 enum rtw89_regulation_type {
 	RTW89_WW	= 0,
 	RTW89_ETSI	= 1,
@@ -4539,6 +4541,7 @@ struct rtw89_fw_elm_info {
 	struct rtw89_phy_table *rf_nctl;
 	struct rtw89_fw_txpwr_track_cfg *txpwr_trk;
 	struct rtw89_phy_rfk_log_fmt *rfk_log_fmt;
+	const struct rtw89_regd_data *regd;
 };
 
 enum rtw89_fw_mss_dev_type {
@@ -5153,11 +5156,22 @@ struct rtw89_regd {
 	u8 txpwr_regd[RTW89_BAND_NUM];
 };
 
+struct rtw89_regd_data {
+	unsigned int nr;
+	struct rtw89_regd map[] __counted_by(nr);
+};
+
+struct rtw89_regd_ctrl {
+	unsigned int nr;
+	const struct rtw89_regd *map;
+};
+
 #define RTW89_REGD_MAX_COUNTRY_NUM U8_MAX
 #define RTW89_5GHZ_UNII4_CHANNEL_NUM 3
 #define RTW89_5GHZ_UNII4_START_INDEX 25
 
 struct rtw89_regulatory_info {
+	struct rtw89_regd_ctrl ctrl;
 	const struct rtw89_regd *regd;
 	enum rtw89_reg_6ghz_power reg_6ghz_power;
 	struct rtw89_reg_6ghz_tpe reg_6ghz_tpe;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 5cc9ab78c09f7..7b7994b8e1aa9 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1056,6 +1056,89 @@ int rtw89_build_rfk_log_fmt_from_elm(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static bool rtw89_regd_entcpy(struct rtw89_regd *regd, const void *cursor,
+			      u8 cursor_size)
+{
+	/* fill default values if needed for backward compatibility */
+	struct rtw89_fw_regd_entry entry = {
+		.rule_2ghz = RTW89_NA,
+		.rule_5ghz = RTW89_NA,
+		.rule_6ghz = RTW89_NA,
+	};
+	u8 valid_size = min_t(u8, sizeof(entry), cursor_size);
+
+	memcpy(&entry, cursor, valid_size);
+	memset(regd, 0, sizeof(*regd));
+
+	regd->alpha2[0] = entry.alpha2_0;
+	regd->alpha2[1] = entry.alpha2_1;
+	regd->alpha2[2] = '\0';
+
+	/* also need to consider forward compatibility */
+	regd->txpwr_regd[RTW89_BAND_2G] = entry.rule_2ghz < RTW89_REGD_NUM ?
+					  entry.rule_2ghz : RTW89_NA;
+	regd->txpwr_regd[RTW89_BAND_5G] = entry.rule_5ghz < RTW89_REGD_NUM ?
+					  entry.rule_5ghz : RTW89_NA;
+	regd->txpwr_regd[RTW89_BAND_6G] = entry.rule_6ghz < RTW89_REGD_NUM ?
+					  entry.rule_6ghz : RTW89_NA;
+
+	return true;
+}
+
+#define rtw89_for_each_in_regd_element(regd, element) \
+	for (const void *cursor = (element)->content, \
+	     *end = (element)->content + \
+		    le32_to_cpu((element)->num_ents) * (element)->ent_sz; \
+	     cursor < end; cursor += (element)->ent_sz) \
+		if (rtw89_regd_entcpy(regd, cursor, (element)->ent_sz))
+
+static
+int rtw89_recognize_regd_from_elm(struct rtw89_dev *rtwdev,
+				  const struct rtw89_fw_element_hdr *elm,
+				  const union rtw89_fw_element_arg arg)
+{
+	const struct __rtw89_fw_regd_element *regd_elm = &elm->u.regd;
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	u32 num_ents = le32_to_cpu(regd_elm->num_ents);
+	struct rtw89_regd_data *p;
+	struct rtw89_regd regd;
+	u32 i = 0;
+
+	if (num_ents > RTW89_REGD_MAX_COUNTRY_NUM) {
+		rtw89_warn(rtwdev,
+			   "regd element ents (%d) are over max num (%d)\n",
+			   num_ents, RTW89_REGD_MAX_COUNTRY_NUM);
+		rtw89_warn(rtwdev,
+			   "regd element ignore and take another/common\n");
+		return 1;
+	}
+
+	if (elm_info->regd) {
+		rtw89_debug(rtwdev, RTW89_DBG_REGD,
+			    "regd element take the latter\n");
+		devm_kfree(rtwdev->dev, elm_info->regd);
+		elm_info->regd = NULL;
+	}
+
+	p = devm_kzalloc(rtwdev->dev, struct_size(p, map, num_ents), GFP_KERNEL);
+	if (!p)
+		return -ENOMEM;
+
+	p->nr = num_ents;
+	rtw89_for_each_in_regd_element(&regd, regd_elm)
+		p->map[i++] = regd;
+
+	if (i != num_ents) {
+		rtw89_err(rtwdev, "regd element has %d invalid ents\n",
+			  num_ents - i);
+		devm_kfree(rtwdev->dev, p);
+		return -EINVAL;
+	}
+
+	elm_info->regd = p;
+	return 0;
+}
+
 static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 	[RTW89_FW_ELEMENT_ID_BBMCU0] = {__rtw89_fw_recognize_from_elm,
 					{ .fw_type = RTW89_FW_BBMCU0 }, NULL},
@@ -1114,6 +1197,9 @@ static const struct rtw89_fw_element_handler __fw_element_handlers[] = {
 	[RTW89_FW_ELEMENT_ID_RFKLOG_FMT] = {
 		rtw89_build_rfk_log_fmt_from_elm, {}, NULL,
 	},
+	[RTW89_FW_ELEMENT_ID_REGD] = {
+		rtw89_recognize_regd_from_elm, {}, "REGD",
+	},
 };
 
 int rtw89_fw_recognize_elements(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 3cc514de073ab..b98da24e9af3e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -3882,6 +3882,7 @@ enum rtw89_fw_element_id {
 	RTW89_FW_ELEMENT_ID_TX_SHAPE_LMT_RU = 17,
 	RTW89_FW_ELEMENT_ID_TXPWR_TRK = 18,
 	RTW89_FW_ELEMENT_ID_RFKLOG_FMT = 19,
+	RTW89_FW_ELEMENT_ID_REGD = 20,
 
 	RTW89_FW_ELEMENT_ID_NUM,
 };
@@ -3925,6 +3926,15 @@ struct __rtw89_fw_txpwr_element {
 	u8 content[];
 } __packed;
 
+struct __rtw89_fw_regd_element {
+	u8 rsvd0;
+	u8 rsvd1;
+	u8 rsvd2;
+	u8 ent_sz;
+	__le32 num_ents;
+	u8 content[];
+} __packed;
+
 enum rtw89_fw_txpwr_trk_type {
 	__RTW89_FW_TXPWR_TRK_TYPE_6GHZ_START = 0,
 	RTW89_FW_TXPWR_TRK_TYPE_6GB_N = 0,
@@ -4016,6 +4026,7 @@ struct rtw89_fw_element_hdr {
 			__le16 offset[];
 		} __packed rfk_log_fmt;
 		struct __rtw89_fw_txpwr_element txpwr;
+		struct __rtw89_fw_regd_element regd;
 	} __packed u;
 } __packed;
 
@@ -4874,6 +4885,17 @@ int rtw89_chip_h2c_ba_cam(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta,
 	return 0;
 }
 
+/* Must consider compatibility; don't insert new in the mid.
+ * Fill each field's default value in rtw89_regd_entcpy().
+ */
+struct rtw89_fw_regd_entry {
+	u8 alpha2_0;
+	u8 alpha2_1;
+	u8 rule_2ghz;
+	u8 rule_5ghz;
+	u8 rule_6ghz;
+} __packed;
+
 /* must consider compatibility; don't insert new in the mid */
 struct rtw89_fw_txpwr_byrate_entry {
 	u8 band;
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 80b2f74589eb9..aea37dae8ef91 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -7,9 +7,12 @@
 #include "ps.h"
 #include "util.h"
 
-#define COUNTRY_REGD(_alpha2, _txpwr_regd...) \
-	{.alpha2 = (_alpha2), \
-	 .txpwr_regd = {_txpwr_regd}, \
+#define COUNTRY_REGD(_alpha2, _rule_2ghz, _rule_5ghz, _rule_6ghz) \
+	{							\
+		.alpha2 = _alpha2,				\
+		.txpwr_regd[RTW89_BAND_2G] = _rule_2ghz,	\
+		.txpwr_regd[RTW89_BAND_5G] = _rule_5ghz,	\
+		.txpwr_regd[RTW89_BAND_6G] = _rule_6ghz,	\
 	}
 
 static const struct rtw89_regd rtw89_ww_regd =
@@ -295,13 +298,16 @@ static const char rtw89_alpha2_list_eu[][3] = {
 	"RO",
 };
 
-static const struct rtw89_regd *rtw89_regd_find_reg_by_name(const char *alpha2)
+static const struct rtw89_regd *rtw89_regd_find_reg_by_name(struct rtw89_dev *rtwdev,
+							    const char *alpha2)
 {
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd_ctrl *regd_ctrl = &regulatory->ctrl;
 	u32 i;
 
-	for (i = 0; i < ARRAY_SIZE(rtw89_regd_map); i++) {
-		if (!memcmp(rtw89_regd_map[i].alpha2, alpha2, 2))
-			return &rtw89_regd_map[i];
+	for (i = 0; i < regd_ctrl->nr; i++) {
+		if (!memcmp(regd_ctrl->map[i].alpha2, alpha2, 2))
+			return &regd_ctrl->map[i];
 	}
 
 	return &rtw89_ww_regd;
@@ -312,22 +318,25 @@ static bool rtw89_regd_is_ww(const struct rtw89_regd *regd)
 	return regd == &rtw89_ww_regd;
 }
 
-static u8 rtw89_regd_get_index(const struct rtw89_regd *regd)
+static u8 rtw89_regd_get_index(struct rtw89_dev *rtwdev, const struct rtw89_regd *regd)
 {
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd_ctrl *regd_ctrl = &regulatory->ctrl;
+
 	BUILD_BUG_ON(ARRAY_SIZE(rtw89_regd_map) > RTW89_REGD_MAX_COUNTRY_NUM);
 
 	if (rtw89_regd_is_ww(regd))
 		return RTW89_REGD_MAX_COUNTRY_NUM;
 
-	return regd - rtw89_regd_map;
+	return regd - regd_ctrl->map;
 }
 
-static u8 rtw89_regd_get_index_by_name(const char *alpha2)
+static u8 rtw89_regd_get_index_by_name(struct rtw89_dev *rtwdev, const char *alpha2)
 {
 	const struct rtw89_regd *regd;
 
-	regd = rtw89_regd_find_reg_by_name(alpha2);
-	return rtw89_regd_get_index(regd);
+	regd = rtw89_regd_find_reg_by_name(rtwdev, alpha2);
+	return rtw89_regd_get_index(rtwdev, regd);
 }
 
 #define rtw89_debug_regd(_dev, _regd, _desc, _argv...) \
@@ -345,6 +354,7 @@ static void rtw89_regd_setup_unii4(struct rtw89_dev *rtwdev,
 				   struct wiphy *wiphy)
 {
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd_ctrl *regd_ctrl = &regulatory->ctrl;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct ieee80211_supported_band *sband;
 	struct rtw89_acpi_dsm_result res = {};
@@ -382,8 +392,8 @@ static void rtw89_regd_setup_unii4(struct rtw89_dev *rtwdev,
 		    "acpi: eval if allow unii-4: 0x%x\n", val);
 
 bottom:
-	for (i = 0; i < ARRAY_SIZE(rtw89_regd_map); i++) {
-		const struct rtw89_regd *regd = &rtw89_regd_map[i];
+	for (i = 0; i < regd_ctrl->nr; i++) {
+		const struct rtw89_regd *regd = &regd_ctrl->map[i];
 
 		switch (regd->txpwr_regd[RTW89_BAND_5G]) {
 		case RTW89_FCC:
@@ -406,7 +416,7 @@ static void __rtw89_regd_setup_policy_6ghz(struct rtw89_dev *rtwdev, bool block,
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	u8 index;
 
-	index = rtw89_regd_get_index_by_name(alpha2);
+	index = rtw89_regd_get_index_by_name(rtwdev, alpha2);
 	if (index == RTW89_REGD_MAX_COUNTRY_NUM) {
 		rtw89_debug(rtwdev, RTW89_DBG_REGD, "%s: unknown alpha2 %c%c\n",
 			    __func__, alpha2[0], alpha2[1]);
@@ -474,6 +484,7 @@ static void rtw89_regd_setup_policy_6ghz(struct rtw89_dev *rtwdev)
 static void rtw89_regd_setup_policy_6ghz_sp(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd_ctrl *regd_ctrl = &regulatory->ctrl;
 	const struct rtw89_acpi_policy_6ghz_sp *ptr;
 	struct rtw89_acpi_dsm_result res = {};
 	bool enable_by_us;
@@ -505,8 +516,8 @@ static void rtw89_regd_setup_policy_6ghz_sp(struct rtw89_dev *rtwdev)
 
 	enable_by_us = u8_get_bits(ptr->conf, RTW89_ACPI_CONF_6GHZ_SP_US);
 
-	for (i = 0; i < ARRAY_SIZE(rtw89_regd_map); i++) {
-		const struct rtw89_regd *tmp = &rtw89_regd_map[i];
+	for (i = 0; i < regd_ctrl->nr; i++) {
+		const struct rtw89_regd *tmp = &regd_ctrl->map[i];
 
 		if (enable_by_us && memcmp(tmp->alpha2, "US", 2) == 0)
 			clear_bit(i, regulatory->block_6ghz_sp);
@@ -573,8 +584,19 @@ static void rtw89_regd_setup_6ghz(struct rtw89_dev *rtwdev, struct wiphy *wiphy)
 
 int rtw89_regd_setup(struct rtw89_dev *rtwdev)
 {
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	struct rtw89_fw_elm_info *elm_info = &rtwdev->fw.elm_info;
+	const struct rtw89_regd_data *regd_data = elm_info->regd;
 	struct wiphy *wiphy = rtwdev->hw->wiphy;
 
+	if (regd_data) {
+		regulatory->ctrl.nr = regd_data->nr;
+		regulatory->ctrl.map = regd_data->map;
+	} else {
+		regulatory->ctrl.nr = ARRAY_SIZE(rtw89_regd_map);
+		regulatory->ctrl.map = rtw89_regd_map;
+	}
+
 	if (!wiphy)
 		return -EINVAL;
 
@@ -599,7 +621,7 @@ int rtw89_regd_init(struct rtw89_dev *rtwdev,
 	if (!wiphy)
 		return -EINVAL;
 
-	chip_regd = rtw89_regd_find_reg_by_name(rtwdev->efuse.country_code);
+	chip_regd = rtw89_regd_find_reg_by_name(rtwdev, rtwdev->efuse.country_code);
 	if (!rtw89_regd_is_ww(chip_regd)) {
 		rtwdev->regulatory.regd = chip_regd;
 		/* Ignore country ie if there is a country domain programmed in chip */
@@ -637,7 +659,7 @@ static void rtw89_regd_apply_policy_unii4(struct rtw89_dev *rtwdev,
 	if (!chip->support_unii4)
 		return;
 
-	index = rtw89_regd_get_index(regd);
+	index = rtw89_regd_get_index(rtwdev, regd);
 	if (index != RTW89_REGD_MAX_COUNTRY_NUM &&
 	    !test_bit(index, regulatory->block_unii4))
 		return;
@@ -655,7 +677,7 @@ static bool regd_is_6ghz_blocked(struct rtw89_dev *rtwdev)
 	const struct rtw89_regd *regd = regulatory->regd;
 	u8 index;
 
-	index = rtw89_regd_get_index(regd);
+	index = rtw89_regd_get_index(rtwdev, regd);
 	if (index != RTW89_REGD_MAX_COUNTRY_NUM &&
 	    !test_bit(index, regulatory->block_6ghz))
 		return false;
@@ -700,7 +722,7 @@ static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 				      struct wiphy *wiphy,
 				      struct regulatory_request *request)
 {
-	rtwdev->regulatory.regd = rtw89_regd_find_reg_by_name(request->alpha2);
+	rtwdev->regulatory.regd = rtw89_regd_find_reg_by_name(rtwdev, request->alpha2);
 	/* This notification might be set from the system of distros,
 	 * and it does not expect the regulatory will be modified by
 	 * connecting to an AP (i.e. country ie).
@@ -925,7 +947,7 @@ static bool __rtw89_reg_6ghz_power_recalc(struct rtw89_dev *rtwdev)
 		sel = RTW89_REG_6GHZ_POWER_DFLT;
 
 	if (sel == RTW89_REG_6GHZ_POWER_STD) {
-		index = rtw89_regd_get_index(regd);
+		index = rtw89_regd_get_index(rtwdev, regd);
 		if (index == RTW89_REGD_MAX_COUNTRY_NUM ||
 		    test_bit(index, regulatory->block_6ghz_sp)) {
 			rtw89_debug(rtwdev, RTW89_DBG_REGD,

From 79a36fc56beaeac31cb9b0ca10618b88f4ac31c8 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 20 Jan 2025 11:27:22 +0800
Subject: [PATCH 0063/2753] wifi: rtw89: regd: handle supported regulatory
 functions by country

There are two regulatory functions including TAS (Time Average SAR) and
DAG (Dynamic Antenna Gain) for now. They are used to improve RF behavior.
But, availability depends on country. Extend regd map to record the status
of whether a country allows to enable certain regulatory functions.

Also, extend the handling of loading regd map via FW element for this.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250120032723.19042-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |   8 +
 drivers/net/wireless/realtek/rtw89/fw.c   |  12 +
 drivers/net/wireless/realtek/rtw89/fw.h   |   1 +
 drivers/net/wireless/realtek/rtw89/regd.c | 489 +++++++++++-----------
 4 files changed, 266 insertions(+), 244 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 680e80b06f014..4328b3acca45f 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5151,9 +5151,17 @@ struct rtw89_power_trim_info {
 	u8 pad_bias_trim[RF_PATH_MAX];
 };
 
+enum rtw89_regd_func {
+	RTW89_REGD_FUNC_TAS = 0, /* TAS (Time Average SAR) */
+	RTW89_REGD_FUNC_DAG = 1, /* DAG (Dynamic Antenna Gain) */
+
+	NUM_OF_RTW89_REGD_FUNC,
+};
+
 struct rtw89_regd {
 	char alpha2[3];
 	u8 txpwr_regd[RTW89_BAND_NUM];
+	DECLARE_BITMAP(func_bitmap, NUM_OF_RTW89_REGD_FUNC);
 };
 
 struct rtw89_regd_data {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 7b7994b8e1aa9..cb5ccd9df364e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1064,8 +1064,11 @@ static bool rtw89_regd_entcpy(struct rtw89_regd *regd, const void *cursor,
 		.rule_2ghz = RTW89_NA,
 		.rule_5ghz = RTW89_NA,
 		.rule_6ghz = RTW89_NA,
+		.fmap = cpu_to_le32(0x0),
 	};
 	u8 valid_size = min_t(u8, sizeof(entry), cursor_size);
+	unsigned int i;
+	u32 fmap;
 
 	memcpy(&entry, cursor, valid_size);
 	memset(regd, 0, sizeof(*regd));
@@ -1082,6 +1085,15 @@ static bool rtw89_regd_entcpy(struct rtw89_regd *regd, const void *cursor,
 	regd->txpwr_regd[RTW89_BAND_6G] = entry.rule_6ghz < RTW89_REGD_NUM ?
 					  entry.rule_6ghz : RTW89_NA;
 
+	BUILD_BUG_ON(sizeof(fmap) != sizeof(entry.fmap));
+	BUILD_BUG_ON(sizeof(fmap) * 8 < NUM_OF_RTW89_REGD_FUNC);
+
+	fmap = le32_to_cpu(entry.fmap);
+	for (i = 0; i < NUM_OF_RTW89_REGD_FUNC; i++) {
+		if (fmap & BIT(i))
+			set_bit(i, regd->func_bitmap);
+	}
+
 	return true;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index b98da24e9af3e..c8faa2f29f5e8 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4894,6 +4894,7 @@ struct rtw89_fw_regd_entry {
 	u8 rule_2ghz;
 	u8 rule_5ghz;
 	u8 rule_6ghz;
+	__le32 fmap;
 } __packed;
 
 /* must consider compatibility; don't insert new in the mid */
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index aea37dae8ef91..50a7f6ff4b5bf 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -7,260 +7,261 @@
 #include "ps.h"
 #include "util.h"
 
-#define COUNTRY_REGD(_alpha2, _rule_2ghz, _rule_5ghz, _rule_6ghz) \
+#define COUNTRY_REGD(_alpha2, _rule_2ghz, _rule_5ghz, _rule_6ghz, _fmap) \
 	{							\
 		.alpha2 = _alpha2,				\
 		.txpwr_regd[RTW89_BAND_2G] = _rule_2ghz,	\
 		.txpwr_regd[RTW89_BAND_5G] = _rule_5ghz,	\
 		.txpwr_regd[RTW89_BAND_6G] = _rule_6ghz,	\
+		.func_bitmap = { BITMAP_FROM_U64(_fmap), },	\
 	}
 
 static const struct rtw89_regd rtw89_ww_regd =
-	COUNTRY_REGD("00", RTW89_WW, RTW89_WW, RTW89_WW);
+	COUNTRY_REGD("00", RTW89_WW, RTW89_WW, RTW89_WW, 0x0);
 
 static const struct rtw89_regd rtw89_regd_map[] = {
-	COUNTRY_REGD("AR", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC),
-	COUNTRY_REGD("BO", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("BR", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("CL", RTW89_CHILE, RTW89_CHILE, RTW89_CHILE),
-	COUNTRY_REGD("CO", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("CR", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("EC", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("SV", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("GT", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("HN", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("MX", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC),
-	COUNTRY_REGD("NI", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("PA", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("PY", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("PE", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("US", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("UY", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("VE", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("PR", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("DO", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("AT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("BE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("DK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("EE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("FI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("FR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("DE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("HU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("IS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("IE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("IT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LV", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MC", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("NL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("NO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("PL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("PT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("ES", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GB", RTW89_UK, RTW89_UK, RTW89_UK),
-	COUNTRY_REGD("AL", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("BH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("BA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("HR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("EG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("IQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("IL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("JO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("KZ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("KW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("KG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LB", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("NA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("OM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("QA", RTW89_QATAR, RTW89_QATAR, RTW89_QATAR),
-	COUNTRY_REGD("RO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("RU", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("RS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("ME", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ZA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("TR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("UA", RTW89_UKRAINE, RTW89_UKRAINE, RTW89_UKRAINE),
-	COUNTRY_REGD("AE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("YE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ZW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("BD", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KH", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("CN", RTW89_CN, RTW89_CN, RTW89_CN),
-	COUNTRY_REGD("HK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("IN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ID", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KR", RTW89_KCC, RTW89_KCC, RTW89_KCC),
-	COUNTRY_REGD("MY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("PK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("PH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_ETSI),
-	COUNTRY_REGD("TH", RTW89_THAILAND, RTW89_THAILAND, RTW89_THAILAND),
-	COUNTRY_REGD("VN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AU", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA),
-	COUNTRY_REGD("NZ", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA),
-	COUNTRY_REGD("PG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CA", RTW89_IC, RTW89_IC, RTW89_IC),
-	COUNTRY_REGD("JP", RTW89_MKK, RTW89_MKK, RTW89_MKK),
-	COUNTRY_REGD("JM", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("AN", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("TT", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("TN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("DZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("AS", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("AD", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("AQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("AG", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("AM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("AW", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("BS", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("BB", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("BY", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BZ", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("BJ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BM", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("BT", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("BV", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("IO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("VG", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("BN", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BF", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("BI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("CV", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KY", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("CF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CX", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("CC", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("KM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("CG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("CK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("CI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("DJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("DM", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("GQ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("ER", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ET", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("FK", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("FO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("FJ", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("GF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("PF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GL", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("GP", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("GG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("GW", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GY", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("HT", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("HM", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("VA", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("IM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("JE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KI", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("XK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("LY", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MW", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MV", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ML", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MH", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("MQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MR", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("MU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("YT", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("FM", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("MD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("MS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NR", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NP", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NC", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("NU", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("NF", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("MP", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("PW", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("RE", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("RW", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SH", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("KN", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("LC", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("MF", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("SX", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("PM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("VC", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("WS", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("SM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ST", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SC", RTW89_FCC, RTW89_FCC, RTW89_NA),
-	COUNTRY_REGD("SL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("SB", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("GS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SR", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("SJ", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("TJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("TZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("TG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("TK", RTW89_ACMA, RTW89_ACMA, RTW89_NA),
-	COUNTRY_REGD("TO", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TC", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("TV", RTW89_ETSI, RTW89_NA, RTW89_NA),
-	COUNTRY_REGD("UG", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("VI", RTW89_FCC, RTW89_FCC, RTW89_FCC),
-	COUNTRY_REGD("UZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI),
-	COUNTRY_REGD("VU", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("WF", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("EH", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("ZM", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("CU", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("IR", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("SY", RTW89_ETSI, RTW89_NA, RTW89_NA),
-	COUNTRY_REGD("SD", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
-	COUNTRY_REGD("PS", RTW89_ETSI, RTW89_ETSI, RTW89_NA),
+	COUNTRY_REGD("AR", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BO", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("BR", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("CL", RTW89_CHILE, RTW89_CHILE, RTW89_CHILE, 0x0),
+	COUNTRY_REGD("CO", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("CR", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("EC", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("SV", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("GT", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("HN", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("MX", RTW89_MEXICO, RTW89_MEXICO, RTW89_FCC, 0x0),
+	COUNTRY_REGD("NI", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("PA", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("PY", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("PE", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("US", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x1),
+	COUNTRY_REGD("UY", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("VE", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("PR", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("DO", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("AT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("BE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("CY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("CZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("DK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("EE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("FI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("FR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("DE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("GR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("HU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("IS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("IE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("IT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("LV", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("LI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("LT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("LU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("MT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("MC", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("NL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("NO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("PL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("PT", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("SK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("SI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("ES", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("SE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("CH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("GB", RTW89_UK, RTW89_UK, RTW89_UK, 0x0),
+	COUNTRY_REGD("AL", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("BH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("BA", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("HR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("EG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("GH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("IQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("IL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("JO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("KZ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("KW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("KG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LB", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MK", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("NA", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("OM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("QA", RTW89_QATAR, RTW89_QATAR, RTW89_QATAR, 0x0),
+	COUNTRY_REGD("RO", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x2),
+	COUNTRY_REGD("RU", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("SN", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("RS", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("ME", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ZA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("UA", RTW89_UKRAINE, RTW89_UKRAINE, RTW89_UKRAINE, 0x0),
+	COUNTRY_REGD("AE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("YE", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ZW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("BD", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KH", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("CN", RTW89_CN, RTW89_CN, RTW89_CN, 0x0),
+	COUNTRY_REGD("HK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("IN", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ID", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KR", RTW89_KCC, RTW89_KCC, RTW89_KCC, 0x1),
+	COUNTRY_REGD("MY", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("PK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("PH", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("SG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LK", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TW", RTW89_FCC, RTW89_FCC, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TH", RTW89_THAILAND, RTW89_THAILAND, RTW89_THAILAND, 0x0),
+	COUNTRY_REGD("VN", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AU", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA, 0x0),
+	COUNTRY_REGD("NZ", RTW89_ACMA, RTW89_ACMA, RTW89_ACMA, 0x0),
+	COUNTRY_REGD("PG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("CA", RTW89_IC, RTW89_IC, RTW89_IC, 0x1),
+	COUNTRY_REGD("JP", RTW89_MKK, RTW89_MKK, RTW89_MKK, 0x0),
+	COUNTRY_REGD("JM", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("AN", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("TT", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("TN", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("DZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("AS", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("AD", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("AQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("AG", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("AM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("AW", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BS", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BB", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BY", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BZ", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("BJ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BM", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BT", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BW", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("BV", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("IO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("VG", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("BN", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BF", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("BI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("CM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("CV", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KY", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("CF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("CX", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("CC", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("KM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("CG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("CD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("CK", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("CI", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("DJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("DM", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("GQ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("ER", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ET", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("FK", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("FO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("FJ", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("GF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("PF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GA", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GM", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("GE", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("GI", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("GL", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GD", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("GP", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GU", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("GG", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("GW", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GY", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("HT", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("HM", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("VA", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("IM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("JE", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KI", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("XK", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LA", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LR", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("LY", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MW", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MV", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ML", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MH", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("MQ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MR", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("MU", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("YT", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("FM", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("MD", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MN", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("MS", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NR", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NP", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NC", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NE", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("NU", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("NF", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("MP", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("PW", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("RE", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("RW", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SH", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("KN", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("LC", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("MF", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("SX", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("PM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("VC", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("WS", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("SM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ST", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SC", RTW89_FCC, RTW89_FCC, RTW89_NA, 0x0),
+	COUNTRY_REGD("SL", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("SB", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("GS", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SR", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("SJ", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TJ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TG", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("TK", RTW89_ACMA, RTW89_ACMA, RTW89_NA, 0x0),
+	COUNTRY_REGD("TO", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TC", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("TV", RTW89_ETSI, RTW89_NA, RTW89_NA, 0x0),
+	COUNTRY_REGD("UG", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("VI", RTW89_FCC, RTW89_FCC, RTW89_FCC, 0x0),
+	COUNTRY_REGD("UZ", RTW89_ETSI, RTW89_ETSI, RTW89_ETSI, 0x0),
+	COUNTRY_REGD("VU", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("WF", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("EH", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("ZM", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("CU", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("IR", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("SY", RTW89_ETSI, RTW89_NA, RTW89_NA, 0x0),
+	COUNTRY_REGD("SD", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
+	COUNTRY_REGD("PS", RTW89_ETSI, RTW89_ETSI, RTW89_NA, 0x0),
 };
 
 static const char rtw89_alpha2_list_eu[][3] = {

From b45acf245596d01cc9e2965695d2d1c428001f62 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 20 Jan 2025 11:27:23 +0800
Subject: [PATCH 0064/2753] wifi: rtw89: regd: refactor init/setup flow and
 prototype

The regulatory and wiphy setup should be done in rtw89_regd_setup(). And,
what rtw89_regd_init() should do is to initialize target regulatory domain
(regd), if and only if one is programmed in efuse. Since HW is registered
after rtw89_regd_setup() and before rtw89_regd_init(), do not fill fields
of regulatory in rtw89_regd_init(). So, move the regulatory->reg_6ghz_power
assignment into rtw89_regd_setup().

Besides, rtw89_regd_notifier is assigned in rtw89_regd_setup() instead of
rtw89_regd_init(). To reduce confusion, stop passing rtw89_regd_notifier to
rtw89_regd_init(). And, rename rtw89_regd_init() to rtw89_regd_init_hint().

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250120032723.19042-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  2 +-
 drivers/net/wireless/realtek/rtw89/core.h |  4 +---
 drivers/net/wireless/realtek/rtw89/regd.c | 13 +++++++------
 3 files changed, 9 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index b730f70c82aa9..37002cfe83259 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -5303,7 +5303,7 @@ static int rtw89_core_register_hw(struct rtw89_dev *rtwdev)
 		goto err_free_supported_band;
 	}
 
-	ret = rtw89_regd_init(rtwdev, rtw89_regd_notifier);
+	ret = rtw89_regd_init_hint(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to init regd\n");
 		goto err_unregister_hw;
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 4328b3acca45f..505a645e7a88e 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -7163,9 +7163,7 @@ void rtw89_chip_cfg_txpwr_ul_tb_offset(struct rtw89_dev *rtwdev,
 				       struct rtw89_vif_link *rtwvif_link);
 bool rtw89_ra_report_to_bitrate(struct rtw89_dev *rtwdev, u8 rpt_rate, u16 *bitrate);
 int rtw89_regd_setup(struct rtw89_dev *rtwdev);
-int rtw89_regd_init(struct rtw89_dev *rtwdev,
-		    void (*reg_notifier)(struct wiphy *wiphy, struct regulatory_request *request));
-void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request);
+int rtw89_regd_init_hint(struct rtw89_dev *rtwdev);
 void rtw89_traffic_stats_init(struct rtw89_dev *rtwdev,
 			      struct rtw89_traffic_stats *stats);
 int rtw89_wait_for_cond(struct rtw89_wait_info *wait, unsigned int cond);
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 50a7f6ff4b5bf..5b9d3b78c24e2 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -7,6 +7,9 @@
 #include "ps.h"
 #include "util.h"
 
+static
+void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request);
+
 #define COUNTRY_REGD(_alpha2, _rule_2ghz, _rule_5ghz, _rule_6ghz, _fmap) \
 	{							\
 		.alpha2 = _alpha2,				\
@@ -598,6 +601,8 @@ int rtw89_regd_setup(struct rtw89_dev *rtwdev)
 		regulatory->ctrl.map = rtw89_regd_map;
 	}
 
+	regulatory->reg_6ghz_power = RTW89_REG_6GHZ_POWER_DFLT;
+
 	if (!wiphy)
 		return -EINVAL;
 
@@ -608,17 +613,12 @@ int rtw89_regd_setup(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-int rtw89_regd_init(struct rtw89_dev *rtwdev,
-		    void (*reg_notifier)(struct wiphy *wiphy,
-					 struct regulatory_request *request))
+int rtw89_regd_init_hint(struct rtw89_dev *rtwdev)
 {
-	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	const struct rtw89_regd *chip_regd;
 	struct wiphy *wiphy = rtwdev->hw->wiphy;
 	int ret;
 
-	regulatory->reg_6ghz_power = RTW89_REG_6GHZ_POWER_DFLT;
-
 	if (!wiphy)
 		return -EINVAL;
 
@@ -738,6 +738,7 @@ static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 	rtw89_regd_apply_policy_6ghz(rtwdev, wiphy);
 }
 
+static
 void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 {
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);

From c281bdb8821461047d3e74206afbff190d1f7846 Mon Sep 17 00:00:00 2001
From: Zong-Zhe Yang <kevin_yang@realtek.com>
Date: Mon, 20 Jan 2025 11:40:04 +0800
Subject: [PATCH 0065/2753] wifi: rtw89: cleanup unused rtwdev::roc_work

The needed one was moved to rtwvif::roc_work. And, rtwdev::roc_work is
unused. So, remove it.

Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250120034004.21135-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 505a645e7a88e..9a44475a8be64 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5729,7 +5729,6 @@ struct rtw89_dev {
 	struct delayed_work coex_rfk_chk_work;
 	struct delayed_work cfo_track_work;
 	struct delayed_work forbid_ba_work;
-	struct delayed_work roc_work;
 	struct delayed_work antdiv_work;
 	struct rtw89_ppdu_sts_info ppdu_sts;
 	u8 total_sta_assoc;

From ebfc9199df05d37b67f4d1b7ee997193f3d2e7c8 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:01 +0800
Subject: [PATCH 0066/2753] wifi: rtw89: add wiphy_lock() to work that isn't
 held wiphy_lock() yet

To ensure where are protected by driver mutex can also be protected by
wiphy_lock(), so afterward we can remove driver mutex safely.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/regd.c | 2 ++
 drivers/net/wireless/realtek/rtw89/ser.c  | 4 ++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 5b9d3b78c24e2..46f5c7eb16830 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -744,6 +744,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
 	struct rtw89_dev *rtwdev = hw->priv;
 
+	wiphy_lock(wiphy);
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
 
@@ -761,6 +762,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 
 exit:
 	mutex_unlock(&rtwdev->mutex);
+	wiphy_unlock(wiphy);
 }
 
 /* Maximum Transmit Power field (@raw) can be EIRP or PSD.
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 26a944d3b6727..d0c8584308c06 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -156,9 +156,11 @@ static void ser_state_run(struct rtw89_ser *ser, u8 evt)
 	rtw89_debug(rtwdev, RTW89_DBG_SER, "ser: %s receive %s\n",
 		    ser_st_name(ser), ser_ev_name(ser, evt));
 
+	wiphy_lock(rtwdev->hw->wiphy);
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_lps(rtwdev);
 	mutex_unlock(&rtwdev->mutex);
+	wiphy_unlock(rtwdev->hw->wiphy);
 
 	ser->st_tbl[ser->state].st_func(ser, evt);
 }
@@ -708,9 +710,11 @@ static void ser_l2_reset_st_hdl(struct rtw89_ser *ser, u8 evt)
 
 	switch (evt) {
 	case SER_EV_STATE_IN:
+		wiphy_lock(rtwdev->hw->wiphy);
 		mutex_lock(&rtwdev->mutex);
 		ser_l2_reset_st_pre_hdl(ser);
 		mutex_unlock(&rtwdev->mutex);
+		wiphy_unlock(rtwdev->hw->wiphy);
 
 		ieee80211_restart_hw(rtwdev->hw);
 		ser_set_alarm(ser, SER_RECFG_TIMEOUT, SER_EV_L2_RECFG_TIMEOUT);

From 4afde17d266795eff3ebb94526c7b04ea876259d Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:02 +0800
Subject: [PATCH 0067/2753] wifi: rtw89: use wiphy_work() to replace
 ieee802111_work()

For certain works protected by driver mutex, use wiphy_work() directly
to have wiphy lock held naturally. Then every this kind of works is
protected by both wiphy lock and driver mutex.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c     |  6 +-
 drivers/net/wireless/realtek/rtw89/chan.h     |  2 +-
 drivers/net/wireless/realtek/rtw89/coex.c     | 38 ++++----
 drivers/net/wireless/realtek/rtw89/coex.h     | 14 +--
 drivers/net/wireless/realtek/rtw89/core.c     | 96 ++++++++++---------
 drivers/net/wireless/realtek/rtw89/core.h     | 36 +++----
 drivers/net/wireless/realtek/rtw89/fw.c       |  4 +-
 drivers/net/wireless/realtek/rtw89/fw.h       |  2 +-
 drivers/net/wireless/realtek/rtw89/mac80211.c | 21 ++--
 drivers/net/wireless/realtek/rtw89/phy.c      | 18 ++--
 drivers/net/wireless/realtek/rtw89/phy.h      |  4 +-
 drivers/net/wireless/realtek/rtw89/ser.c      |  9 +-
 12 files changed, 128 insertions(+), 122 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 4df4e04c3e67d..9858894dfc236 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -2390,7 +2390,7 @@ static void rtw89_mcc_update_limit(struct rtw89_dev *rtwdev)
 	rtw89_iterate_mcc_roles(rtwdev, rtw89_mcc_upd_lmt_iterator, NULL);
 }
 
-void rtw89_chanctx_work(struct work_struct *work)
+void rtw89_chanctx_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						chanctx_work.work);
@@ -2477,8 +2477,8 @@ void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev,
 	rtw89_debug(rtwdev, RTW89_DBG_CHAN,
 		    "queue chanctx work for mode %d with delay %d us\n",
 		    mode, delay);
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->chanctx_work,
-				     usecs_to_jiffies(delay));
+	wiphy_delayed_work_queue(rtwdev->hw->wiphy, &rtwdev->chanctx_work,
+				 usecs_to_jiffies(delay));
 }
 
 void rtw89_queue_chanctx_work(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/chan.h b/drivers/net/wireless/realtek/rtw89/chan.h
index 092a6f676894f..e6391f6f2aa78 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.h
+++ b/drivers/net/wireless/realtek/rtw89/chan.h
@@ -99,7 +99,7 @@ void rtw89_config_roc_chandef(struct rtw89_dev *rtwdev,
 			      const struct cfg80211_chan_def *chandef);
 void rtw89_entity_init(struct rtw89_dev *rtwdev);
 enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev);
-void rtw89_chanctx_work(struct work_struct *work);
+void rtw89_chanctx_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_queue_chanctx_work(struct rtw89_dev *rtwdev);
 void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev,
 				enum rtw89_chanctx_changes change);
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 755c157c815d4..c51c069099666 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -6712,7 +6712,7 @@ static void _update_wl_info_v8(struct rtw89_dev *rtwdev, u8 role_id, u8 rlink_id
 	_fw_set_drv_info(rtwdev, CXDRVINFO_ROLE);
 }
 
-void rtw89_coex_act1_work(struct work_struct *work)
+void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						coex_act1_work.work);
@@ -6733,7 +6733,7 @@ void rtw89_coex_act1_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-void rtw89_coex_bt_devinfo_work(struct work_struct *work)
+void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						coex_bt_devinfo_work.work);
@@ -6749,7 +6749,7 @@ void rtw89_coex_bt_devinfo_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-void rtw89_coex_rfk_chk_work(struct work_struct *work)
+void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						coex_rfk_chk_work.work);
@@ -7278,7 +7278,7 @@ void rtw89_btc_ntfy_specific_packet(struct rtw89_dev *rtwdev,
 			    "[BTC], %s(): EAPOL_End cnt=%d\n",
 			    __func__, cnt);
 		wl->status.map._4way = false;
-		cancel_delayed_work(&rtwdev->coex_act1_work);
+		wiphy_delayed_work_cancel(rtwdev->hw->wiphy, &rtwdev->coex_act1_work);
 		break;
 	case PACKET_ARP:
 		cnt = ++cx->cnt_wl[BTC_WCNT_ARP];
@@ -7297,16 +7297,16 @@ void rtw89_btc_ntfy_specific_packet(struct rtw89_dev *rtwdev,
 	}
 
 	if (delay_work) {
-		cancel_delayed_work(&rtwdev->coex_act1_work);
-		ieee80211_queue_delayed_work(rtwdev->hw,
-					     &rtwdev->coex_act1_work, delay);
+		wiphy_delayed_work_cancel(rtwdev->hw->wiphy, &rtwdev->coex_act1_work);
+		wiphy_delayed_work_queue(rtwdev->hw->wiphy,
+					 &rtwdev->coex_act1_work, delay);
 	}
 
 	btc->dm.cnt_notify[BTC_NCNT_SPECIAL_PACKET]++;
 	_run_coex(rtwdev, BTC_RSN_NTFY_SPECIFIC_PACKET);
 }
 
-void rtw89_btc_ntfy_eapol_packet_work(struct work_struct *work)
+void rtw89_btc_ntfy_eapol_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.eapol_notify_work);
@@ -7317,7 +7317,7 @@ void rtw89_btc_ntfy_eapol_packet_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-void rtw89_btc_ntfy_arp_packet_work(struct work_struct *work)
+void rtw89_btc_ntfy_arp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.arp_notify_work);
@@ -7327,7 +7327,7 @@ void rtw89_btc_ntfy_arp_packet_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-void rtw89_btc_ntfy_dhcp_packet_work(struct work_struct *work)
+void rtw89_btc_ntfy_dhcp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.dhcp_notify_work);
@@ -7338,7 +7338,7 @@ void rtw89_btc_ntfy_dhcp_packet_work(struct work_struct *work)
 	mutex_unlock(&rtwdev->mutex);
 }
 
-void rtw89_btc_ntfy_icmp_packet_work(struct work_struct *work)
+void rtw89_btc_ntfy_icmp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.icmp_notify_work);
@@ -7525,9 +7525,9 @@ static void _update_bt_info(struct rtw89_dev *rtwdev, u8 *buf, u32 len)
 		a2dp->vendor_id = 0;
 		a2dp->flush_time = 0;
 		a2dp->play_latency = 1;
-		ieee80211_queue_delayed_work(rtwdev->hw,
-					     &rtwdev->coex_bt_devinfo_work,
-					     RTW89_COEX_BT_DEVINFO_WORK_PERIOD);
+		wiphy_delayed_work_queue(rtwdev->hw->wiphy,
+					 &rtwdev->coex_bt_devinfo_work,
+					 RTW89_COEX_BT_DEVINFO_WORK_PERIOD);
 	}
 
 	_run_coex(rtwdev, BTC_RSN_UPDATE_BT_INFO);
@@ -7776,7 +7776,7 @@ static bool _ntfy_wl_rfk(struct rtw89_dev *rtwdev, u8 phy_path,
 		wl->rfk_info.state = BTC_WRFK_STOP;
 
 		_write_scbd(rtwdev, BTC_WSCB_WLRFK, false);
-		cancel_delayed_work(&rtwdev->coex_rfk_chk_work);
+		wiphy_delayed_work_cancel(rtwdev->hw->wiphy, &rtwdev->coex_rfk_chk_work);
 		break;
 	default:
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
@@ -7790,9 +7790,9 @@ static bool _ntfy_wl_rfk(struct rtw89_dev *rtwdev, u8 phy_path,
 			_run_coex(rtwdev, BTC_RSN_NTFY_WL_RFK);
 
 		if (wl->rfk_info.state == BTC_WRFK_START)
-			ieee80211_queue_delayed_work(rtwdev->hw,
-						     &rtwdev->coex_rfk_chk_work,
-						     RTW89_COEX_RFK_CHK_WORK_PERIOD);
+			wiphy_delayed_work_queue(rtwdev->hw->wiphy,
+						 &rtwdev->coex_rfk_chk_work,
+						 RTW89_COEX_RFK_CHK_WORK_PERIOD);
 	}
 
 	rtw89_debug(rtwdev, RTW89_DBG_BTC,
@@ -7810,6 +7810,8 @@ void rtw89_btc_ntfy_wl_rfk(struct rtw89_dev *rtwdev, u8 phy_map,
 	bool allow;
 	int ret;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	band = FIELD_GET(BTC_RFK_BAND_MAP, phy_map);
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index 757d03675cf4e..30134f58d5317 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -267,10 +267,10 @@ void rtw89_btc_ntfy_scan_finish(struct rtw89_dev *rtwdev, u8 phy_idx);
 void rtw89_btc_ntfy_switch_band(struct rtw89_dev *rtwdev, u8 phy_idx, u8 band);
 void rtw89_btc_ntfy_specific_packet(struct rtw89_dev *rtwdev,
 				    enum btc_pkt_type pkt_type);
-void rtw89_btc_ntfy_eapol_packet_work(struct work_struct *work);
-void rtw89_btc_ntfy_arp_packet_work(struct work_struct *work);
-void rtw89_btc_ntfy_dhcp_packet_work(struct work_struct *work);
-void rtw89_btc_ntfy_icmp_packet_work(struct work_struct *work);
+void rtw89_btc_ntfy_eapol_packet_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_btc_ntfy_arp_packet_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_btc_ntfy_dhcp_packet_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_btc_ntfy_icmp_packet_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_btc_ntfy_role_info(struct rtw89_dev *rtwdev,
 			      struct rtw89_vif_link *rtwvif_link,
 			      struct rtw89_sta_link *rtwsta_link,
@@ -283,9 +283,9 @@ void rtw89_btc_ntfy_wl_sta(struct rtw89_dev *rtwdev);
 void rtw89_btc_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			  u32 len, u8 class, u8 func);
 void rtw89_btc_dump_info(struct rtw89_dev *rtwdev, struct seq_file *m);
-void rtw89_coex_act1_work(struct work_struct *work);
-void rtw89_coex_bt_devinfo_work(struct work_struct *work);
-void rtw89_coex_rfk_chk_work(struct work_struct *work);
+void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_coex_power_on(struct rtw89_dev *rtwdev);
 void rtw89_btc_set_policy(struct rtw89_dev *rtwdev, u16 policy_type);
 void rtw89_btc_set_policy_v1(struct rtw89_dev *rtwdev, u16 policy_type);
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 37002cfe83259..330b23db4868b 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -913,16 +913,17 @@ static enum btc_pkt_type
 rtw89_core_tx_btc_spec_pkt_notify(struct rtw89_dev *rtwdev,
 				  struct rtw89_core_tx_request *tx_req)
 {
+	struct wiphy *wiphy = rtwdev->hw->wiphy;
 	struct sk_buff *skb = tx_req->skb;
 	struct udphdr *udphdr;
 
 	if (IEEE80211_SKB_CB(skb)->control.flags & IEEE80211_TX_CTRL_PORT_CTRL_PROTO) {
-		ieee80211_queue_work(rtwdev->hw, &rtwdev->btc.eapol_notify_work);
+		wiphy_work_queue(wiphy, &rtwdev->btc.eapol_notify_work);
 		return PACKET_EAPOL;
 	}
 
 	if (skb->protocol == htons(ETH_P_ARP)) {
-		ieee80211_queue_work(rtwdev->hw, &rtwdev->btc.arp_notify_work);
+		wiphy_work_queue(wiphy, &rtwdev->btc.arp_notify_work);
 		return PACKET_ARP;
 	}
 
@@ -932,14 +933,14 @@ rtw89_core_tx_btc_spec_pkt_notify(struct rtw89_dev *rtwdev,
 		if (((udphdr->source == htons(67) && udphdr->dest == htons(68)) ||
 		     (udphdr->source == htons(68) && udphdr->dest == htons(67))) &&
 		    skb->len > 282) {
-			ieee80211_queue_work(rtwdev->hw, &rtwdev->btc.dhcp_notify_work);
+			wiphy_work_queue(wiphy, &rtwdev->btc.dhcp_notify_work);
 			return PACKET_DHCP;
 		}
 	}
 
 	if (skb->protocol == htons(ETH_P_IP) &&
 	    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
-		ieee80211_queue_work(rtwdev->hw, &rtwdev->btc.icmp_notify_work);
+		wiphy_work_queue(wiphy, &rtwdev->btc.icmp_notify_work);
 		return PACKET_ICMP;
 	}
 
@@ -2071,7 +2072,7 @@ static void rtw89_stats_trigger_frame(struct rtw89_dev *rtwdev,
 	}
 }
 
-static void rtw89_cancel_6ghz_probe_work(struct work_struct *work)
+static void rtw89_cancel_6ghz_probe_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						cancel_6ghz_probe_work);
@@ -2131,7 +2132,7 @@ static void rtw89_core_cancel_6ghz_probe_tx(struct rtw89_dev *rtwdev,
 	}
 
 	if (queue_work)
-		ieee80211_queue_work(rtwdev->hw, &rtwdev->cancel_6ghz_probe_work);
+		wiphy_work_queue(rtwdev->hw->wiphy, &rtwdev->cancel_6ghz_probe_work);
 }
 
 static void rtw89_vif_sync_bcn_tsf(struct rtw89_vif_link *rtwvif_link,
@@ -3143,7 +3144,7 @@ static void rtw89_core_txq_schedule(struct rtw89_dev *rtwdev, u8 ac, bool *reinv
 	ieee80211_txq_schedule_end(hw, ac);
 }
 
-static void rtw89_ips_work(struct work_struct *work)
+static void rtw89_ips_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						ips_work);
@@ -3330,9 +3331,9 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	rtw89_write32_clr(rtwdev, reg, B_AX_A_UC_CAM_MATCH | B_AX_A_BC_CAM_MATCH);
 
 	ieee80211_ready_on_channel(hw);
-	cancel_delayed_work(&rtwvif->roc.roc_work);
-	ieee80211_queue_delayed_work(hw, &rtwvif->roc.roc_work,
-				     msecs_to_jiffies(rtwvif->roc.duration));
+	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
+	wiphy_delayed_work_queue(hw->wiphy, &rtwvif->roc.roc_work,
+				 msecs_to_jiffies(rtwvif->roc.duration));
 }
 
 void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
@@ -3377,11 +3378,11 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	queue_work(rtwdev->txq_wq, &rtwdev->txq_work);
 
 	if (hw->conf.flags & IEEE80211_CONF_IDLE)
-		ieee80211_queue_delayed_work(hw, &roc->roc_work,
-					     msecs_to_jiffies(RTW89_ROC_IDLE_TIMEOUT));
+		wiphy_delayed_work_queue(hw->wiphy, &roc->roc_work,
+					 msecs_to_jiffies(RTW89_ROC_IDLE_TIMEOUT));
 }
 
-void rtw89_roc_work(struct work_struct *work)
+void rtw89_roc_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_vif *rtwvif = container_of(work, struct rtw89_vif,
 						roc.roc_work.work);
@@ -3533,7 +3534,7 @@ void rtw89_traffic_stats_init(struct rtw89_dev *rtwdev,
 	ewma_tp_init(&stats->rx_ewma_tp);
 }
 
-static void rtw89_track_work(struct work_struct *work)
+static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						track_work.work);
@@ -3547,8 +3548,8 @@ static void rtw89_track_work(struct work_struct *work)
 	if (!test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
 		goto out;
 
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->track_work,
-				     RTW89_TRACK_WORK_PERIOD);
+	wiphy_delayed_work_queue(wiphy, &rtwdev->track_work,
+				 RTW89_TRACK_WORK_PERIOD);
 
 	tfc_changed = rtw89_traffic_stats_track(rtwdev);
 	if (rtwdev->scanning)
@@ -4438,7 +4439,7 @@ static void rtw89_core_ppdu_sts_init(struct rtw89_dev *rtwdev)
 		rtwdev->ppdu_sts.curr_rx_ppdu_cnt[i] = U8_MAX;
 }
 
-void rtw89_core_update_beacon_work(struct work_struct *work)
+void rtw89_core_update_beacon_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev;
 	struct rtw89_vif_link *rtwvif_link = container_of(work, struct rtw89_vif_link,
@@ -4568,8 +4569,8 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 		return ret;
 	}
 
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->track_work,
-				     RTW89_TRACK_WORK_PERIOD);
+	wiphy_delayed_work_queue(rtwdev->hw->wiphy, &rtwdev->track_work,
+				 RTW89_TRACK_WORK_PERIOD);
 
 	set_bit(RTW89_FLAG_RUNNING, rtwdev->flags);
 
@@ -4583,6 +4584,7 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 
 void rtw89_core_stop(struct rtw89_dev *rtwdev)
 {
+	struct wiphy *wiphy = rtwdev->hw->wiphy;
 	struct rtw89_btc *btc = &rtwdev->btc;
 
 	/* Prvent to stop twice; enter_ips and ops_stop */
@@ -4595,21 +4597,21 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 
 	mutex_unlock(&rtwdev->mutex);
 
-	cancel_work_sync(&rtwdev->c2h_work);
-	cancel_work_sync(&rtwdev->cancel_6ghz_probe_work);
-	cancel_work_sync(&btc->eapol_notify_work);
-	cancel_work_sync(&btc->arp_notify_work);
-	cancel_work_sync(&btc->dhcp_notify_work);
-	cancel_work_sync(&btc->icmp_notify_work);
+	wiphy_work_cancel(wiphy, &rtwdev->c2h_work);
+	wiphy_work_cancel(wiphy, &rtwdev->cancel_6ghz_probe_work);
+	wiphy_work_cancel(wiphy, &btc->eapol_notify_work);
+	wiphy_work_cancel(wiphy, &btc->arp_notify_work);
+	wiphy_work_cancel(wiphy, &btc->dhcp_notify_work);
+	wiphy_work_cancel(wiphy, &btc->icmp_notify_work);
 	cancel_delayed_work_sync(&rtwdev->txq_reinvoke_work);
-	cancel_delayed_work_sync(&rtwdev->track_work);
-	cancel_delayed_work_sync(&rtwdev->chanctx_work);
-	cancel_delayed_work_sync(&rtwdev->coex_act1_work);
-	cancel_delayed_work_sync(&rtwdev->coex_bt_devinfo_work);
-	cancel_delayed_work_sync(&rtwdev->coex_rfk_chk_work);
-	cancel_delayed_work_sync(&rtwdev->cfo_track_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->track_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->chanctx_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->coex_act1_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->coex_bt_devinfo_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->coex_rfk_chk_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->cfo_track_work);
 	cancel_delayed_work_sync(&rtwdev->forbid_ba_work);
-	cancel_delayed_work_sync(&rtwdev->antdiv_work);
+	wiphy_delayed_work_cancel(wiphy, &rtwdev->antdiv_work);
 
 	mutex_lock(&rtwdev->mutex);
 
@@ -4825,14 +4827,14 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	INIT_WORK(&rtwdev->ba_work, rtw89_core_ba_work);
 	INIT_WORK(&rtwdev->txq_work, rtw89_core_txq_work);
 	INIT_DELAYED_WORK(&rtwdev->txq_reinvoke_work, rtw89_core_txq_reinvoke_work);
-	INIT_DELAYED_WORK(&rtwdev->track_work, rtw89_track_work);
-	INIT_DELAYED_WORK(&rtwdev->chanctx_work, rtw89_chanctx_work);
-	INIT_DELAYED_WORK(&rtwdev->coex_act1_work, rtw89_coex_act1_work);
-	INIT_DELAYED_WORK(&rtwdev->coex_bt_devinfo_work, rtw89_coex_bt_devinfo_work);
-	INIT_DELAYED_WORK(&rtwdev->coex_rfk_chk_work, rtw89_coex_rfk_chk_work);
-	INIT_DELAYED_WORK(&rtwdev->cfo_track_work, rtw89_phy_cfo_track_work);
+	wiphy_delayed_work_init(&rtwdev->track_work, rtw89_track_work);
+	wiphy_delayed_work_init(&rtwdev->chanctx_work, rtw89_chanctx_work);
+	wiphy_delayed_work_init(&rtwdev->coex_act1_work, rtw89_coex_act1_work);
+	wiphy_delayed_work_init(&rtwdev->coex_bt_devinfo_work, rtw89_coex_bt_devinfo_work);
+	wiphy_delayed_work_init(&rtwdev->coex_rfk_chk_work, rtw89_coex_rfk_chk_work);
+	wiphy_delayed_work_init(&rtwdev->cfo_track_work, rtw89_phy_cfo_track_work);
 	INIT_DELAYED_WORK(&rtwdev->forbid_ba_work, rtw89_forbid_ba_work);
-	INIT_DELAYED_WORK(&rtwdev->antdiv_work, rtw89_phy_antdiv_work);
+	wiphy_delayed_work_init(&rtwdev->antdiv_work, rtw89_phy_antdiv_work);
 	rtwdev->txq_wq = alloc_workqueue("rtw89_tx_wq", WQ_UNBOUND | WQ_HIGHPRI, 0);
 	if (!rtwdev->txq_wq)
 		return -ENOMEM;
@@ -4847,10 +4849,10 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	rtw89_init_wait(&rtwdev->wow.wait);
 	rtw89_init_wait(&rtwdev->mac.ps_wait);
 
-	INIT_WORK(&rtwdev->c2h_work, rtw89_fw_c2h_work);
-	INIT_WORK(&rtwdev->ips_work, rtw89_ips_work);
+	wiphy_work_init(&rtwdev->c2h_work, rtw89_fw_c2h_work);
+	wiphy_work_init(&rtwdev->ips_work, rtw89_ips_work);
+	wiphy_work_init(&rtwdev->cancel_6ghz_probe_work, rtw89_cancel_6ghz_probe_work);
 	INIT_WORK(&rtwdev->load_firmware_work, rtw89_load_firmware_work);
-	INIT_WORK(&rtwdev->cancel_6ghz_probe_work, rtw89_cancel_6ghz_probe_work);
 
 	skb_queue_head_init(&rtwdev->c2h_queue);
 	rtw89_core_ppdu_sts_init(rtwdev);
@@ -4870,10 +4872,10 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 	rtwdev->bbs[RTW89_PHY_0].phy_idx = RTW89_PHY_0;
 	rtwdev->bbs[RTW89_PHY_1].phy_idx = RTW89_PHY_1;
 
-	INIT_WORK(&btc->eapol_notify_work, rtw89_btc_ntfy_eapol_packet_work);
-	INIT_WORK(&btc->arp_notify_work, rtw89_btc_ntfy_arp_packet_work);
-	INIT_WORK(&btc->dhcp_notify_work, rtw89_btc_ntfy_dhcp_packet_work);
-	INIT_WORK(&btc->icmp_notify_work, rtw89_btc_ntfy_icmp_packet_work);
+	wiphy_work_init(&btc->eapol_notify_work, rtw89_btc_ntfy_eapol_packet_work);
+	wiphy_work_init(&btc->arp_notify_work, rtw89_btc_ntfy_arp_packet_work);
+	wiphy_work_init(&btc->dhcp_notify_work, rtw89_btc_ntfy_dhcp_packet_work);
+	wiphy_work_init(&btc->icmp_notify_work, rtw89_btc_ntfy_icmp_packet_work);
 
 	init_completion(&rtwdev->fw.req.completion);
 	init_completion(&rtwdev->rfk_wait.completion);
@@ -4949,7 +4951,7 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 	rtw89_for_each_active_bb(rtwdev, bb)
 		bb->dig.bypass_dig = true;
 	if (hw_scan && (rtwdev->hw->conf.flags & IEEE80211_CONF_IDLE))
-		ieee80211_queue_work(rtwdev->hw, &rtwdev->ips_work);
+		wiphy_work_queue(rtwdev->hw->wiphy, &rtwdev->ips_work);
 }
 
 static void rtw89_read_chip_ver(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 9a44475a8be64..6970e4d4e73fa 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3177,10 +3177,10 @@ struct rtw89_btc {
 	struct rtw89_btc_btf_fwinfo fwinfo;
 	struct rtw89_btc_dbg dbg;
 
-	struct work_struct eapol_notify_work;
-	struct work_struct arp_notify_work;
-	struct work_struct dhcp_notify_work;
-	struct work_struct icmp_notify_work;
+	struct wiphy_work eapol_notify_work;
+	struct wiphy_work arp_notify_work;
+	struct wiphy_work dhcp_notify_work;
+	struct wiphy_work icmp_notify_work;
 
 	u32 bt_req_len;
 
@@ -3447,7 +3447,7 @@ enum rtw89_roc_state {
 
 struct rtw89_roc {
 	struct ieee80211_channel chan;
-	struct delayed_work roc_work;
+	struct wiphy_delayed_work roc_work;
 	enum ieee80211_roc_type type;
 	enum rtw89_roc_state state;
 	int duration;
@@ -3517,7 +3517,7 @@ struct rtw89_vif_link {
 	bool pre_pwr_diff_en;
 	bool pwr_diff_en;
 	u8 def_tri_idx;
-	struct work_struct update_beacon_work;
+	struct wiphy_work update_beacon_work;
 	struct rtw89_addr_cam_entry addr_cam;
 	struct rtw89_bssid_cam_entry bssid_cam;
 	struct ieee80211_tx_queue_params tx_params[IEEE80211_NUM_ACS];
@@ -5674,10 +5674,10 @@ struct rtw89_dev {
 	struct rtw89_cam_info cam_info;
 
 	struct sk_buff_head c2h_queue;
-	struct work_struct c2h_work;
-	struct work_struct ips_work;
+	struct wiphy_work c2h_work;
+	struct wiphy_work ips_work;
+	struct wiphy_work cancel_6ghz_probe_work;
 	struct work_struct load_firmware_work;
-	struct work_struct cancel_6ghz_probe_work;
 
 	struct list_head early_h2c_list;
 
@@ -5722,14 +5722,14 @@ struct rtw89_dev {
 		struct rtw89_edcca_bak edcca_bak;
 	} bbs[RTW89_PHY_NUM];
 
-	struct delayed_work track_work;
-	struct delayed_work chanctx_work;
-	struct delayed_work coex_act1_work;
-	struct delayed_work coex_bt_devinfo_work;
-	struct delayed_work coex_rfk_chk_work;
-	struct delayed_work cfo_track_work;
+	struct wiphy_delayed_work track_work;
+	struct wiphy_delayed_work chanctx_work;
+	struct wiphy_delayed_work coex_act1_work;
+	struct wiphy_delayed_work coex_bt_devinfo_work;
+	struct wiphy_delayed_work coex_rfk_chk_work;
+	struct wiphy_delayed_work cfo_track_work;
 	struct delayed_work forbid_ba_work;
-	struct delayed_work antdiv_work;
+	struct wiphy_delayed_work antdiv_work;
 	struct rtw89_ppdu_sts_info ppdu_sts;
 	u8 total_sta_assoc;
 	bool scanning;
@@ -7170,8 +7170,8 @@ void rtw89_complete_cond(struct rtw89_wait_info *wait, unsigned int cond,
 			 const struct rtw89_completion_data *data);
 int rtw89_core_start(struct rtw89_dev *rtwdev);
 void rtw89_core_stop(struct rtw89_dev *rtwdev);
-void rtw89_core_update_beacon_work(struct work_struct *work);
-void rtw89_roc_work(struct work_struct *work);
+void rtw89_core_update_beacon_work(struct wiphy *wiphy, struct wiphy_work *work);
+void rtw89_roc_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif);
 void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index cb5ccd9df364e..64c2895309c6e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6157,7 +6157,7 @@ void rtw89_fw_c2h_irqsafe(struct rtw89_dev *rtwdev, struct sk_buff *c2h)
 
 enqueue:
 	skb_queue_tail(&rtwdev->c2h_queue, c2h);
-	ieee80211_queue_work(rtwdev->hw, &rtwdev->c2h_work);
+	wiphy_work_queue(rtwdev->hw->wiphy, &rtwdev->c2h_work);
 }
 
 static void rtw89_fw_c2h_cmd_handle(struct rtw89_dev *rtwdev,
@@ -6195,7 +6195,7 @@ static void rtw89_fw_c2h_cmd_handle(struct rtw89_dev *rtwdev,
 		rtw89_hex_dump(rtwdev, RTW89_DBG_FW, "C2H: ", skb->data, skb->len);
 }
 
-void rtw89_fw_c2h_work(struct work_struct *work)
+void rtw89_fw_c2h_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						c2h_work);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index c8faa2f29f5e8..b621dbed2c615 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4599,7 +4599,7 @@ int rtw89_fw_h2c_dctl_sec_cam_v2(struct rtw89_dev *rtwdev,
 				 struct rtw89_vif_link *rtwvif_link,
 				 struct rtw89_sta_link *rtwsta_link);
 void rtw89_fw_c2h_irqsafe(struct rtw89_dev *rtwdev, struct sk_buff *c2h);
-void rtw89_fw_c2h_work(struct work_struct *work);
+void rtw89_fw_c2h_work(struct wiphy *wiphy, struct wiphy_work *work);
 int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev,
 			       struct rtw89_vif_link *rtwvif_link,
 			       struct rtw89_sta_link *rtwsta_link,
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index b3669e0074df9..7b3520e6389bb 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -80,7 +80,7 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	/* let previous ips work finish to ensure we don't leave ips twice */
-	cancel_work_sync(&rtwdev->ips_work);
+	wiphy_work_cancel(hw->wiphy, &rtwdev->ips_work);
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
@@ -115,7 +115,7 @@ static int __rtw89_ops_add_iface_link(struct rtw89_dev *rtwdev,
 
 	rtw89_vif_type_mapping(rtwvif_link, false);
 
-	INIT_WORK(&rtwvif_link->update_beacon_work, rtw89_core_update_beacon_work);
+	wiphy_work_init(&rtwvif_link->update_beacon_work, rtw89_core_update_beacon_work);
 	INIT_LIST_HEAD(&rtwvif_link->general_pkt_list);
 
 	rtwvif_link->hit_rule = 0;
@@ -143,7 +143,7 @@ static void __rtw89_ops_remove_iface_link(struct rtw89_dev *rtwdev,
 					  struct rtw89_vif_link *rtwvif_link)
 {
 	mutex_unlock(&rtwdev->mutex);
-	cancel_work_sync(&rtwvif_link->update_beacon_work);
+	wiphy_work_cancel(rtwdev->hw->wiphy, &rtwvif_link->update_beacon_work);
 	mutex_lock(&rtwdev->mutex);
 
 	rtw89_leave_ps_mode(rtwdev);
@@ -198,7 +198,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 
 	rtwvif->offchan = false;
 	rtwvif->roc.state = RTW89_ROC_IDLE;
-	INIT_DELAYED_WORK(&rtwvif->roc.roc_work, rtw89_roc_work);
+	wiphy_delayed_work_init(&rtwvif->roc.roc_work, rtw89_roc_work);
 
 	rtw89_traffic_stats_init(rtwdev, &rtwvif->stats);
 
@@ -242,7 +242,7 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw,
 	rtw89_debug(rtwdev, RTW89_DBG_STATE, "remove vif %pM type %d p2p %d\n",
 		    vif->addr, vif->type, vif->p2p);
 
-	cancel_delayed_work_sync(&rtwvif->roc.roc_work);
+	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
 	mutex_lock(&rtwdev->mutex);
 
@@ -853,14 +853,13 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 static int rtw89_ops_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
 			     bool set)
 {
-	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_vif *rtwvif = rtwsta->rtwvif;
 	struct rtw89_vif_link *rtwvif_link;
 	unsigned int link_id;
 
 	rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id)
-		ieee80211_queue_work(rtwdev->hw, &rtwvif_link->update_beacon_work);
+		wiphy_work_queue(hw->wiphy, &rtwvif_link->update_beacon_work);
 
 	return 0;
 }
@@ -1453,7 +1452,7 @@ static int rtw89_ops_cancel_remain_on_channel(struct ieee80211_hw *hw,
 	if (!rtwvif)
 		return -EINVAL;
 
-	cancel_delayed_work_sync(&rtwvif->roc.roc_work);
+	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_roc_end(rtwdev, rtwvif);
@@ -1751,7 +1750,7 @@ static int rtw89_ops_suspend(struct ieee80211_hw *hw,
 	int ret;
 
 	set_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
-	cancel_delayed_work_sync(&rtwdev->track_work);
+	wiphy_delayed_work_cancel(hw->wiphy, &rtwdev->track_work);
 
 	mutex_lock(&rtwdev->mutex);
 	ret = rtw89_wow_suspend(rtwdev, wowlan);
@@ -1778,8 +1777,8 @@ static int rtw89_ops_resume(struct ieee80211_hw *hw)
 	mutex_unlock(&rtwdev->mutex);
 
 	clear_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->track_work,
-				     RTW89_TRACK_WORK_PERIOD);
+	wiphy_delayed_work_queue(hw->wiphy, &rtwdev->track_work,
+				 RTW89_TRACK_WORK_PERIOD);
 
 	return ret ? 1 : 0;
 }
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 5b0cf8314fb2a..2f8694fe4bd1c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -4651,7 +4651,7 @@ static void rtw89_phy_cfo_dm(struct rtw89_dev *rtwdev)
 	rtw89_phy_cfo_statistics_reset(rtwdev);
 }
 
-void rtw89_phy_cfo_track_work(struct work_struct *work)
+void rtw89_phy_cfo_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						cfo_track_work.work);
@@ -4662,8 +4662,8 @@ void rtw89_phy_cfo_track_work(struct work_struct *work)
 		goto out;
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_phy_cfo_dm(rtwdev);
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->cfo_track_work,
-				     msecs_to_jiffies(cfo->cfo_timer_ms));
+	wiphy_delayed_work_queue(wiphy, &rtwdev->cfo_track_work,
+				 msecs_to_jiffies(cfo->cfo_timer_ms));
 out:
 	mutex_unlock(&rtwdev->mutex);
 }
@@ -4672,8 +4672,8 @@ static void rtw89_phy_cfo_start_work(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking;
 
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->cfo_track_work,
-				     msecs_to_jiffies(cfo->cfo_timer_ms));
+	wiphy_delayed_work_queue(rtwdev->hw->wiphy, &rtwdev->cfo_track_work,
+				 msecs_to_jiffies(cfo->cfo_timer_ms));
 }
 
 void rtw89_phy_cfo_track(struct rtw89_dev *rtwdev)
@@ -6523,11 +6523,11 @@ static void rtw89_phy_antdiv_training_state(struct rtw89_dev *rtwdev)
 	}
 
 	antdiv->training_count++;
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->antdiv_work,
-				     state_period);
+	wiphy_delayed_work_queue(rtwdev->hw->wiphy, &rtwdev->antdiv_work,
+				 state_period);
 }
 
-void rtw89_phy_antdiv_work(struct work_struct *work)
+void rtw89_phy_antdiv_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						antdiv_work.work);
@@ -6563,7 +6563,7 @@ void rtw89_phy_antdiv_track(struct rtw89_dev *rtwdev)
 		return;
 
 	antdiv->training_count = 0;
-	ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->antdiv_work, 0);
+	wiphy_delayed_work_queue(rtwdev->hw->wiphy, &rtwdev->antdiv_work, 0);
 }
 
 static void __rtw89_phy_env_monitor_init(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index 33d466c519e3a..cec165e222e7d 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -978,7 +978,7 @@ void rtw89_phy_rfk_tssi_fill_fwcmd_tmeter_tbl(struct rtw89_dev *rtwdev,
 					      const struct rtw89_chan *chan,
 					      struct rtw89_h2c_rf_tssi *h2c);
 void rtw89_phy_cfo_track(struct rtw89_dev *rtwdev);
-void rtw89_phy_cfo_track_work(struct work_struct *work);
+void rtw89_phy_cfo_track_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_phy_cfo_parse(struct rtw89_dev *rtwdev, s16 cfo_val,
 			 struct rtw89_rx_phy_ppdu *phy_ppdu);
 void rtw89_phy_stat_track(struct rtw89_dev *rtwdev);
@@ -991,7 +991,7 @@ void rtw89_phy_tx_path_div_track(struct rtw89_dev *rtwdev);
 void rtw89_phy_antdiv_parse(struct rtw89_dev *rtwdev,
 			    struct rtw89_rx_phy_ppdu *phy_ppdu);
 void rtw89_phy_antdiv_track(struct rtw89_dev *rtwdev);
-void rtw89_phy_antdiv_work(struct work_struct *work);
+void rtw89_phy_antdiv_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_phy_set_bss_color(struct rtw89_dev *rtwdev,
 			     struct rtw89_vif_link *rtwvif_link);
 void rtw89_phy_tssi_ctrl_set_bandedge_cfg(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index d0c8584308c06..9658672ad2744 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -485,10 +485,13 @@ static void ser_l1_reset_pre_st_hdl(struct rtw89_ser *ser, u8 evt)
 static void ser_reset_trx_st_hdl(struct rtw89_ser *ser, u8 evt)
 {
 	struct rtw89_dev *rtwdev = container_of(ser, struct rtw89_dev, ser);
+	struct wiphy *wiphy = rtwdev->hw->wiphy;
 
 	switch (evt) {
 	case SER_EV_STATE_IN:
-		cancel_delayed_work_sync(&rtwdev->track_work);
+		wiphy_lock(wiphy);
+		wiphy_delayed_work_cancel(wiphy, &rtwdev->track_work);
+		wiphy_unlock(wiphy);
 		drv_stop_tx(ser);
 
 		if (hal_stop_dma(ser)) {
@@ -519,8 +522,8 @@ static void ser_reset_trx_st_hdl(struct rtw89_ser *ser, u8 evt)
 		hal_enable_dma(ser);
 		drv_resume_rx(ser);
 		drv_resume_tx(ser);
-		ieee80211_queue_delayed_work(rtwdev->hw, &rtwdev->track_work,
-					     RTW89_TRACK_WORK_PERIOD);
+		wiphy_delayed_work_queue(wiphy, &rtwdev->track_work,
+					 RTW89_TRACK_WORK_PERIOD);
 		break;
 
 	default:

From 831cceed3baf498984add821d288ced95a4ec4cf Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:03 +0800
Subject: [PATCH 0068/2753] wifi: rtw89: debugfs: implement
 file_ops::read/write to replace seq_file

Since debugfs needs wiphy lock held, wiphy_locked_debugfs_{read,write}()
will be adopted, so implmenet file_ops::read/write along with their
arguments.

For reading part, it needs lots of changes because seq_file is not
suitable for wiphy_locked_debugfs_{read,write}(), so use spatch script
below to convert basically, and manually implement the functions.

  @ rule1 @
  identifier m;
  @@

  - seq_printf(m,
  + p += scnprintf(p, end - p,
    ...)

  @ rule2 @
  identifier m;
  @@

  - seq_puts(m,
  + p += scnprintf(p, end - p,
    ...)

For current version, only 4K buffer to output. To note ourselves, add
ellipsis symbol "..." to trailing if buffer is full. Later, add an option
to specify buffer size needed by a debugfs entry.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c  | 2737 +++++++++++---------
 drivers/net/wireless/realtek/rtw89/coex.h  |    2 +-
 drivers/net/wireless/realtek/rtw89/debug.c | 1917 ++++++++------
 drivers/net/wireless/realtek/rtw89/phy.c   |   16 +-
 drivers/net/wireless/realtek/rtw89/phy.h   |    4 +-
 drivers/net/wireless/realtek/rtw89/sar.c   |   40 +-
 drivers/net/wireless/realtek/rtw89/sar.h   |    5 +-
 drivers/net/wireless/realtek/rtw89/util.c  |   11 +
 drivers/net/wireless/realtek/rtw89/util.h  |    1 +
 9 files changed, 2584 insertions(+), 2149 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index c51c069099666..1065f610d80f1 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -8153,7 +8153,7 @@ void rtw89_btc_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 
 #define BTC_CX_FW_OFFLOAD 0
 
-static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_cx_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	union rtw89_btc_module_info *md = &rtwdev->btc.mdinfo;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
@@ -8165,40 +8165,43 @@ static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	u32 ver_main = 0, ver_sub = 0, ver_hotfix = 0, id_branch = 0;
 	u8 cv, rfe, iso, ant_num, ant_single_pos;
+	char *p = buf, *end = buf + bufsz;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_CX))
-		return;
+		return 0;
 
 	dm->cnt_notify[BTC_NCNT_SHOW_COEX_INFO]++;
 
-	seq_printf(m, "========== [BTC COEX INFO (%d)] ==========\n",
-		   chip->chip_id);
+	p += scnprintf(p, end - p,
+		       "========== [BTC COEX INFO (%d)] ==========\n",
+		       chip->chip_id);
 
 	ver_main = FIELD_GET(GENMASK(31, 24), RTW89_COEX_VERSION);
 	ver_sub = FIELD_GET(GENMASK(23, 16), RTW89_COEX_VERSION);
 	ver_hotfix = FIELD_GET(GENMASK(15, 8), RTW89_COEX_VERSION);
 	id_branch = FIELD_GET(GENMASK(7, 0), RTW89_COEX_VERSION);
-	seq_printf(m, " %-15s : Coex:%d.%d.%d(branch:%d), ",
-		   "[coex_version]", ver_main, ver_sub, ver_hotfix, id_branch);
+	p += scnprintf(p, end - p, " %-15s : Coex:%d.%d.%d(branch:%d), ",
+		       "[coex_version]", ver_main, ver_sub, ver_hotfix,
+		       id_branch);
 
 	ver_main = FIELD_GET(GENMASK(31, 24), wl->ver_info.fw_coex);
 	ver_sub = FIELD_GET(GENMASK(23, 16), wl->ver_info.fw_coex);
 	ver_hotfix = FIELD_GET(GENMASK(15, 8), wl->ver_info.fw_coex);
 	id_branch = FIELD_GET(GENMASK(7, 0), wl->ver_info.fw_coex);
-	seq_printf(m, "WL_FW_coex:%d.%d.%d(branch:%d)",
-		   ver_main, ver_sub, ver_hotfix, id_branch);
+	p += scnprintf(p, end - p, "WL_FW_coex:%d.%d.%d(branch:%d)",
+		       ver_main, ver_sub, ver_hotfix, id_branch);
 
 	ver_main = FIELD_GET(GENMASK(31, 24), chip->wlcx_desired);
 	ver_sub = FIELD_GET(GENMASK(23, 16), chip->wlcx_desired);
 	ver_hotfix = FIELD_GET(GENMASK(15, 8), chip->wlcx_desired);
-	seq_printf(m, "(%s, desired:%d.%d.%d), ",
-		   (wl->ver_info.fw_coex >= chip->wlcx_desired ?
-		   "Match" : "Mismatch"), ver_main, ver_sub, ver_hotfix);
+	p += scnprintf(p, end - p, "(%s, desired:%d.%d.%d), ",
+		       (wl->ver_info.fw_coex >= chip->wlcx_desired ?
+			"Match" : "Mismatch"), ver_main, ver_sub, ver_hotfix);
 
-	seq_printf(m, "BT_FW_coex:%d(%s, desired:%d)\n",
-		   bt->ver_info.fw_coex,
-		   (bt->ver_info.fw_coex >= chip->btcx_desired ?
-		   "Match" : "Mismatch"), chip->btcx_desired);
+	p += scnprintf(p, end - p, "BT_FW_coex:%d(%s, desired:%d)\n",
+		       bt->ver_info.fw_coex,
+		       (bt->ver_info.fw_coex >= chip->btcx_desired ?
+			"Match" : "Mismatch"), chip->btcx_desired);
 
 	if (bt->enable.now && bt->ver_info.fw == 0)
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_BT_VER_INFO, true);
@@ -8209,10 +8212,11 @@ static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	ver_sub = FIELD_GET(GENMASK(23, 16), wl->ver_info.fw);
 	ver_hotfix = FIELD_GET(GENMASK(15, 8), wl->ver_info.fw);
 	id_branch = FIELD_GET(GENMASK(7, 0), wl->ver_info.fw);
-	seq_printf(m, " %-15s : WL_FW:%d.%d.%d.%d, BT_FW:0x%x(%s)\n",
-		   "[sub_module]",
-		   ver_main, ver_sub, ver_hotfix, id_branch,
-		   bt->ver_info.fw, bt->run_patch_code ? "patch" : "ROM");
+	p += scnprintf(p, end - p,
+		       " %-15s : WL_FW:%d.%d.%d.%d, BT_FW:0x%x(%s)\n",
+		       "[sub_module]",
+		       ver_main, ver_sub, ver_hotfix, id_branch,
+		       bt->ver_info.fw, bt->run_patch_code ? "patch" : "ROM");
 
 	if (ver->fcxinit == 7) {
 		cv = md->md_v7.kt_ver;
@@ -8228,36 +8232,41 @@ static void _show_cx_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		ant_single_pos = md->md.ant.single_pos;
 	}
 
-	seq_printf(m, " %-15s : cv:%x, rfe_type:0x%x, ant_iso:%d, ant_pg:%d, %s",
-		   "[hw_info]", cv, rfe, iso, ant_num,
-		   ant_num > 1 ? "" :
-		   ant_single_pos ? "1Ant_Pos:S1, " : "1Ant_Pos:S0, ");
+	p += scnprintf(p, end - p,
+		       " %-15s : cv:%x, rfe_type:0x%x, ant_iso:%d, ant_pg:%d, %s",
+		       "[hw_info]", cv, rfe, iso, ant_num,
+		       ant_num > 1 ? "" :
+		       ant_single_pos ? "1Ant_Pos:S1, " : "1Ant_Pos:S0, ");
 
-	seq_printf(m, "3rd_coex:%d, dbcc:%d, tx_num:%d, rx_num:%d\n",
-		   btc->cx.other.type, rtwdev->dbcc_en, hal->tx_nss,
-		   hal->rx_nss);
+	p += scnprintf(p, end - p,
+		       "3rd_coex:%d, dbcc:%d, tx_num:%d, rx_num:%d\n",
+		       btc->cx.other.type, rtwdev->dbcc_en, hal->tx_nss,
+		       hal->rx_nss);
+
+	return p - buf;
 }
 
-static void _show_wl_role_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_wl_role_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_wl_link_info *plink = NULL;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_wl_dbcc_info *wl_dinfo = &wl->dbcc_info;
 	struct rtw89_traffic_stats *t;
+	char *p = buf, *end = buf + bufsz;
 	u8 i;
 
 	if (rtwdev->dbcc_en) {
-		seq_printf(m,
-			   " %-15s : PHY0_band(op:%d/scan:%d/real:%d), ",
-			   "[dbcc_info]", wl_dinfo->op_band[RTW89_PHY_0],
-			   wl_dinfo->scan_band[RTW89_PHY_0],
-			   wl_dinfo->real_band[RTW89_PHY_0]);
-		seq_printf(m,
-			   "PHY1_band(op:%d/scan:%d/real:%d)\n",
-			   wl_dinfo->op_band[RTW89_PHY_1],
-			   wl_dinfo->scan_band[RTW89_PHY_1],
-			   wl_dinfo->real_band[RTW89_PHY_1]);
+		p += scnprintf(p, end - p,
+			       " %-15s : PHY0_band(op:%d/scan:%d/real:%d), ",
+			       "[dbcc_info]", wl_dinfo->op_band[RTW89_PHY_0],
+			       wl_dinfo->scan_band[RTW89_PHY_0],
+			       wl_dinfo->real_band[RTW89_PHY_0]);
+		p += scnprintf(p, end - p,
+			       "PHY1_band(op:%d/scan:%d/real:%d)\n",
+			       wl_dinfo->op_band[RTW89_PHY_1],
+			       wl_dinfo->scan_band[RTW89_PHY_1],
+			       wl_dinfo->real_band[RTW89_PHY_1]);
 	}
 
 	for (i = 0; i < RTW89_PORT_NUM; i++) {
@@ -8269,38 +8278,41 @@ static void _show_wl_role_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		if (!plink->active)
 			continue;
 
-		seq_printf(m,
-			   " [port_%d]        : role=%d(phy-%d), connect=%d(client_cnt=%d), mode=%d, center_ch=%d, bw=%d",
-			   plink->pid, (u32)plink->role, plink->phy,
-			   (u32)plink->connected, plink->client_cnt - 1,
-			   (u32)plink->mode, plink->ch, (u32)plink->bw);
+		p += scnprintf(p, end - p,
+			       " [port_%d]        : role=%d(phy-%d), connect=%d(client_cnt=%d), mode=%d, center_ch=%d, bw=%d",
+			       plink->pid, (u32)plink->role, plink->phy,
+			       (u32)plink->connected, plink->client_cnt - 1,
+			       (u32)plink->mode, plink->ch, (u32)plink->bw);
 
 		if (plink->connected == MLME_NO_LINK)
 			continue;
 
-		seq_printf(m,
-			   ", mac_id=%d, max_tx_time=%dus, max_tx_retry=%d\n",
-			   plink->mac_id, plink->tx_time, plink->tx_retry);
+		p += scnprintf(p, end - p,
+			       ", mac_id=%d, max_tx_time=%dus, max_tx_retry=%d\n",
+			       plink->mac_id, plink->tx_time, plink->tx_retry);
 
-		seq_printf(m,
-			   " [port_%d]        : rssi=-%ddBm(%d), busy=%d, dir=%s, ",
-			   plink->pid, 110 - plink->stat.rssi,
-			   plink->stat.rssi, plink->busy,
-			   plink->dir == RTW89_TFC_UL ? "UL" : "DL");
+		p += scnprintf(p, end - p,
+			       " [port_%d]        : rssi=-%ddBm(%d), busy=%d, dir=%s, ",
+			       plink->pid, 110 - plink->stat.rssi,
+			       plink->stat.rssi, plink->busy,
+			       plink->dir == RTW89_TFC_UL ? "UL" : "DL");
 
 		t = &plink->stat.traffic;
 
-		seq_printf(m,
-			   "tx[rate:%d/busy_level:%d], ",
-			   (u32)t->tx_rate, t->tx_tfc_lv);
+		p += scnprintf(p, end - p,
+			       "tx[rate:%d/busy_level:%d], ",
+			       (u32)t->tx_rate, t->tx_tfc_lv);
 
-		seq_printf(m, "rx[rate:%d/busy_level:%d/drop:%d]\n",
-			   (u32)t->rx_rate,
-			   t->rx_tfc_lv, plink->rx_rate_drop_cnt);
+		p += scnprintf(p, end - p,
+			       "rx[rate:%d/busy_level:%d/drop:%d]\n",
+			       (u32)t->rx_rate,
+			       t->rx_tfc_lv, plink->rx_rate_drop_cnt);
 	}
+
+	return p - buf;
 }
 
-static void _show_wl_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_wl_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
@@ -8311,12 +8323,13 @@ static void _show_wl_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_role_info_v2 *wl_rinfo_v2 = &wl->role_info_v2;
 	struct rtw89_btc_wl_role_info_v7 *wl_rinfo_v7 = &wl->role_info_v7;
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
+	char *p = buf, *end = buf + bufsz;
 	u8 mode;
 
 	if (!(btc->dm.coex_info_map & BTC_COEX_INFO_WL))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [WL Status] ==========\n");
+	p += scnprintf(p, end - p, "========== [WL Status] ==========\n");
 
 	if (ver->fwlrole == 0)
 		mode = wl_rinfo->link_mode;
@@ -8329,24 +8342,28 @@ static void _show_wl_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	else if (ver->fwlrole == 8)
 		mode = wl_rinfo_v8->link_mode;
 	else
-		return;
+		goto out;
+
+	p += scnprintf(p, end - p, " %-15s : link_mode:%d, ", "[status]",
+		       mode);
 
-	seq_printf(m, " %-15s : link_mode:%d, ", "[status]", mode);
+	p += scnprintf(p, end - p,
+		       "rf_off:%d, power_save:%d, scan:%s(band:%d/phy_map:0x%x), ",
+		       wl->status.map.rf_off, wl->status.map.lps,
+		       wl->status.map.scan ? "Y" : "N",
+		       wl->scan_info.band[RTW89_PHY_0], wl->scan_info.phy_map);
 
-	seq_printf(m,
-		   "rf_off:%d, power_save:%d, scan:%s(band:%d/phy_map:0x%x), ",
-		   wl->status.map.rf_off, wl->status.map.lps,
-		   wl->status.map.scan ? "Y" : "N",
-		   wl->scan_info.band[RTW89_PHY_0], wl->scan_info.phy_map);
+	p += scnprintf(p, end - p,
+		       "connecting:%s, roam:%s, 4way:%s, init_ok:%s\n",
+		       wl->status.map.connecting ? "Y" : "N",
+		       wl->status.map.roaming ?  "Y" : "N",
+		       wl->status.map._4way ? "Y" : "N",
+		       wl->status.map.init_ok ? "Y" : "N");
 
-	seq_printf(m,
-		   "connecting:%s, roam:%s, 4way:%s, init_ok:%s\n",
-		   wl->status.map.connecting ? "Y" : "N",
-		   wl->status.map.roaming ?  "Y" : "N",
-		   wl->status.map._4way ? "Y" : "N",
-		   wl->status.map.init_ok ? "Y" : "N");
+	p += _show_wl_role_info(rtwdev, p, end - p);
 
-	_show_wl_role_info(rtwdev, m);
+out:
+	return p - buf;
 }
 
 enum btc_bt_a2dp_type {
@@ -8355,7 +8372,7 @@ enum btc_bt_a2dp_type {
 	BTC_A2DP_TWS_RELAY = 2,
 };
 
-static void _show_bt_profile_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_bt_profile_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_link_info *bt_linfo = &btc->cx.bt.link_info;
@@ -8363,50 +8380,55 @@ static void _show_bt_profile_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_bt_hid_desc hid = bt_linfo->hid_desc;
 	struct rtw89_btc_bt_a2dp_desc a2dp = bt_linfo->a2dp_desc;
 	struct rtw89_btc_bt_pan_desc pan = bt_linfo->pan_desc;
+	char *p = buf, *end = buf + bufsz;
 
 	if (hfp.exist) {
-		seq_printf(m, " %-15s : type:%s, sut_pwr:%d, golden-rx:%d",
-			   "[HFP]", (hfp.type == 0 ? "SCO" : "eSCO"),
-			   bt_linfo->sut_pwr_level[0],
-			   bt_linfo->golden_rx_shift[0]);
+		p += scnprintf(p, end - p,
+			       " %-15s : type:%s, sut_pwr:%d, golden-rx:%d",
+			       "[HFP]", (hfp.type == 0 ? "SCO" : "eSCO"),
+			       bt_linfo->sut_pwr_level[0],
+			       bt_linfo->golden_rx_shift[0]);
 	}
 
 	if (hid.exist) {
-		seq_printf(m,
-			   "\n\r %-15s : type:%s%s%s%s%s pair-cnt:%d, sut_pwr:%d, golden-rx:%d\n",
-			   "[HID]",
-			   hid.type & BTC_HID_218 ? "2/18," : "",
-			   hid.type & BTC_HID_418 ? "4/18," : "",
-			   hid.type & BTC_HID_BLE ? "BLE," : "",
-			   hid.type & BTC_HID_RCU ? "RCU," : "",
-			   hid.type & BTC_HID_RCU_VOICE ? "RCU-Voice," : "",
-			   hid.pair_cnt, bt_linfo->sut_pwr_level[1],
-			   bt_linfo->golden_rx_shift[1]);
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : type:%s%s%s%s%s pair-cnt:%d, sut_pwr:%d, golden-rx:%d\n",
+			       "[HID]",
+			       hid.type & BTC_HID_218 ? "2/18," : "",
+			       hid.type & BTC_HID_418 ? "4/18," : "",
+			       hid.type & BTC_HID_BLE ? "BLE," : "",
+			       hid.type & BTC_HID_RCU ? "RCU," : "",
+			       hid.type & BTC_HID_RCU_VOICE ? "RCU-Voice," : "",
+			       hid.pair_cnt, bt_linfo->sut_pwr_level[1],
+			       bt_linfo->golden_rx_shift[1]);
 	}
 
 	if (a2dp.exist) {
-		seq_printf(m,
-			   " %-15s : type:%s, bit-pool:%d, flush-time:%d, ",
-			   "[A2DP]",
-			   a2dp.type == BTC_A2DP_LEGACY ? "Legacy" : "TWS",
-			    a2dp.bitpool, a2dp.flush_time);
+		p += scnprintf(p, end - p,
+			       " %-15s : type:%s, bit-pool:%d, flush-time:%d, ",
+			       "[A2DP]",
+			       a2dp.type == BTC_A2DP_LEGACY ? "Legacy" : "TWS",
+			       a2dp.bitpool, a2dp.flush_time);
 
-		seq_printf(m,
-			   "vid:0x%x, Dev-name:0x%x, sut_pwr:%d, golden-rx:%d\n",
-			   a2dp.vendor_id, a2dp.device_name,
-			   bt_linfo->sut_pwr_level[2],
-			   bt_linfo->golden_rx_shift[2]);
+		p += scnprintf(p, end - p,
+			       "vid:0x%x, Dev-name:0x%x, sut_pwr:%d, golden-rx:%d\n",
+			       a2dp.vendor_id, a2dp.device_name,
+			       bt_linfo->sut_pwr_level[2],
+			       bt_linfo->golden_rx_shift[2]);
 	}
 
 	if (pan.exist) {
-		seq_printf(m, " %-15s : sut_pwr:%d, golden-rx:%d\n",
-			   "[PAN]",
-			   bt_linfo->sut_pwr_level[3],
-			   bt_linfo->golden_rx_shift[3]);
+		p += scnprintf(p, end - p,
+			       " %-15s : sut_pwr:%d, golden-rx:%d\n",
+			       "[PAN]",
+			       bt_linfo->sut_pwr_level[3],
+			       bt_linfo->golden_rx_shift[3]);
 	}
+
+	return p - buf;
 }
 
-static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_bt_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
@@ -8415,129 +8437,136 @@ static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	struct rtw89_btc_bt_link_info *bt_linfo = &bt->link_info;
 	union rtw89_btc_module_info *md = &btc->mdinfo;
+	char *p = buf, *end = buf + bufsz;
 	u8 *afh = bt_linfo->afh_map;
 	u8 *afh_le = bt_linfo->afh_map_le;
 	u8 bt_pos;
 
 	if (!(btc->dm.coex_info_map & BTC_COEX_INFO_BT))
-		return;
+		return 0;
 
 	if (ver->fcxinit == 7)
 		bt_pos = md->md_v7.bt_pos;
 	else
 		bt_pos = md->md.bt_pos;
 
-	seq_puts(m, "========== [BT Status] ==========\n");
-
-	seq_printf(m, " %-15s : enable:%s, btg:%s%s, connect:%s, ",
-		   "[status]", bt->enable.now ? "Y" : "N",
-		   bt->btg_type ? "Y" : "N",
-		   (bt->enable.now && (bt->btg_type != bt_pos) ?
-		   "(efuse-mismatch!!)" : ""),
-		   (bt_linfo->status.map.connect ? "Y" : "N"));
-
-	seq_printf(m, "igno_wl:%s, mailbox_avl:%s, rfk_state:0x%x\n",
-		   bt->igno_wl ? "Y" : "N",
-		   bt->mbx_avl ? "Y" : "N", bt->rfk_info.val);
-
-	seq_printf(m, " %-15s : profile:%s%s%s%s%s ",
-		   "[profile]",
-		   (bt_linfo->profile_cnt.now == 0) ? "None," : "",
-		   bt_linfo->hfp_desc.exist ? "HFP," : "",
-		   bt_linfo->hid_desc.exist ? "HID," : "",
-		   bt_linfo->a2dp_desc.exist ?
-		   (bt_linfo->a2dp_desc.sink ? "A2DP_sink," : "A2DP,") : "",
-		   bt_linfo->pan_desc.exist ? "PAN," : "");
-
-	seq_printf(m,
-		   "multi-link:%s, role:%s, ble-connect:%s, CQDDR:%s, A2DP_active:%s, PAN_active:%s\n",
-		   bt_linfo->multi_link.now ? "Y" : "N",
-		   bt_linfo->slave_role ? "Slave" : "Master",
-		   bt_linfo->status.map.ble_connect ? "Y" : "N",
-		   bt_linfo->cqddr ? "Y" : "N",
-		   bt_linfo->a2dp_desc.active ? "Y" : "N",
-		   bt_linfo->pan_desc.active ? "Y" : "N");
-
-	seq_printf(m,
-		   " %-15s : rssi:%ddBm(lvl:%d), tx_rate:%dM, %s%s%s",
-		   "[link]", bt_linfo->rssi - 100,
-		   bt->rssi_level,
-		   bt_linfo->tx_3m ? 3 : 2,
-		   bt_linfo->status.map.inq_pag ? " inq-page!!" : "",
-		   bt_linfo->status.map.acl_busy ? " acl_busy!!" : "",
-		   bt_linfo->status.map.mesh_busy ? " mesh_busy!!" : "");
-
-	seq_printf(m,
-		   "%s afh_map[%02x%02x_%02x%02x_%02x%02x_%02x%02x_%02x%02x], ",
-		   bt_linfo->relink.now ? " ReLink!!" : "",
-		   afh[0], afh[1], afh[2], afh[3], afh[4],
-		   afh[5], afh[6], afh[7], afh[8], afh[9]);
+	p += scnprintf(p, end - p, "========== [BT Status] ==========\n");
+
+	p += scnprintf(p, end - p,
+		       " %-15s : enable:%s, btg:%s%s, connect:%s, ",
+		       "[status]", bt->enable.now ? "Y" : "N",
+		       bt->btg_type ? "Y" : "N",
+		       (bt->enable.now && (bt->btg_type != bt_pos) ?
+			"(efuse-mismatch!!)" : ""),
+		       (bt_linfo->status.map.connect ? "Y" : "N"));
+
+	p += scnprintf(p, end - p,
+		       "igno_wl:%s, mailbox_avl:%s, rfk_state:0x%x\n",
+		       bt->igno_wl ? "Y" : "N",
+		       bt->mbx_avl ? "Y" : "N", bt->rfk_info.val);
+
+	p += scnprintf(p, end - p, " %-15s : profile:%s%s%s%s%s ",
+		       "[profile]",
+		       (bt_linfo->profile_cnt.now == 0) ? "None," : "",
+		       bt_linfo->hfp_desc.exist ? "HFP," : "",
+		       bt_linfo->hid_desc.exist ? "HID," : "",
+		       bt_linfo->a2dp_desc.exist ?
+		       (bt_linfo->a2dp_desc.sink ? "A2DP_sink," : "A2DP,") : "",
+		       bt_linfo->pan_desc.exist ? "PAN," : "");
+
+	p += scnprintf(p, end - p,
+		       "multi-link:%s, role:%s, ble-connect:%s, CQDDR:%s, A2DP_active:%s, PAN_active:%s\n",
+		       bt_linfo->multi_link.now ? "Y" : "N",
+		       bt_linfo->slave_role ? "Slave" : "Master",
+		       bt_linfo->status.map.ble_connect ? "Y" : "N",
+		       bt_linfo->cqddr ? "Y" : "N",
+		       bt_linfo->a2dp_desc.active ? "Y" : "N",
+		       bt_linfo->pan_desc.active ? "Y" : "N");
+
+	p += scnprintf(p, end - p,
+		       " %-15s : rssi:%ddBm(lvl:%d), tx_rate:%dM, %s%s%s",
+		       "[link]", bt_linfo->rssi - 100,
+		       bt->rssi_level,
+		       bt_linfo->tx_3m ? 3 : 2,
+		       bt_linfo->status.map.inq_pag ? " inq-page!!" : "",
+		       bt_linfo->status.map.acl_busy ? " acl_busy!!" : "",
+		       bt_linfo->status.map.mesh_busy ? " mesh_busy!!" : "");
+
+	p += scnprintf(p, end - p,
+		       "%s afh_map[%02x%02x_%02x%02x_%02x%02x_%02x%02x_%02x%02x], ",
+		       bt_linfo->relink.now ? " ReLink!!" : "",
+		       afh[0], afh[1], afh[2], afh[3], afh[4],
+		       afh[5], afh[6], afh[7], afh[8], afh[9]);
 
 	if (ver->fcxbtafh == 2 && bt_linfo->status.map.ble_connect)
-		seq_printf(m,
-			   "LE[%02x%02x_%02x_%02x%02x]",
-			   afh_le[0], afh_le[1], afh_le[2],
-			   afh_le[3], afh_le[4]);
-
-	seq_printf(m, "wl_ch_map[en:%d/ch:%d/bw:%d]\n",
-		   wl->afh_info.en, wl->afh_info.ch, wl->afh_info.bw);
-
-	seq_printf(m,
-		   " %-15s : retry:%d, relink:%d, rate_chg:%d, reinit:%d, reenable:%d, ",
-		   "[stat_cnt]", cx->cnt_bt[BTC_BCNT_RETRY],
-		   cx->cnt_bt[BTC_BCNT_RELINK], cx->cnt_bt[BTC_BCNT_RATECHG],
-		   cx->cnt_bt[BTC_BCNT_REINIT], cx->cnt_bt[BTC_BCNT_REENABLE]);
-
-	seq_printf(m,
-		   "role-switch:%d, afh:%d, inq_page:%d(inq:%d/page:%d), igno_wl:%d\n",
-		   cx->cnt_bt[BTC_BCNT_ROLESW], cx->cnt_bt[BTC_BCNT_AFH],
-		   cx->cnt_bt[BTC_BCNT_INQPAG], cx->cnt_bt[BTC_BCNT_INQ],
-		   cx->cnt_bt[BTC_BCNT_PAGE], cx->cnt_bt[BTC_BCNT_IGNOWL]);
-
-	_show_bt_profile_info(rtwdev, m);
-
-	seq_printf(m,
-		   " %-15s : raw_data[%02x %02x %02x %02x %02x %02x] (type:%s/cnt:%d/same:%d)\n",
-		   "[bt_info]", bt->raw_info[2], bt->raw_info[3],
-		   bt->raw_info[4], bt->raw_info[5], bt->raw_info[6],
-		   bt->raw_info[7],
-		   bt->raw_info[0] == BTC_BTINFO_AUTO ? "auto" : "reply",
-		   cx->cnt_bt[BTC_BCNT_INFOUPDATE],
-		   cx->cnt_bt[BTC_BCNT_INFOSAME]);
-
-	seq_printf(m,
-		   " %-15s : Hi-rx = %d, Hi-tx = %d, Lo-rx = %d, Lo-tx = %d (bt_polut_wl_tx = %d)",
-		   "[trx_req_cnt]", cx->cnt_bt[BTC_BCNT_HIPRI_RX],
-		   cx->cnt_bt[BTC_BCNT_HIPRI_TX], cx->cnt_bt[BTC_BCNT_LOPRI_RX],
-		   cx->cnt_bt[BTC_BCNT_LOPRI_TX], cx->cnt_bt[BTC_BCNT_POLUT]);
+		p += scnprintf(p, end - p,
+			       "LE[%02x%02x_%02x_%02x%02x]",
+			       afh_le[0], afh_le[1], afh_le[2],
+			       afh_le[3], afh_le[4]);
+
+	p += scnprintf(p, end - p, "wl_ch_map[en:%d/ch:%d/bw:%d]\n",
+		       wl->afh_info.en, wl->afh_info.ch, wl->afh_info.bw);
+
+	p += scnprintf(p, end - p,
+		       " %-15s : retry:%d, relink:%d, rate_chg:%d, reinit:%d, reenable:%d, ",
+		       "[stat_cnt]", cx->cnt_bt[BTC_BCNT_RETRY],
+		       cx->cnt_bt[BTC_BCNT_RELINK],
+		       cx->cnt_bt[BTC_BCNT_RATECHG],
+		       cx->cnt_bt[BTC_BCNT_REINIT],
+		       cx->cnt_bt[BTC_BCNT_REENABLE]);
+
+	p += scnprintf(p, end - p,
+		       "role-switch:%d, afh:%d, inq_page:%d(inq:%d/page:%d), igno_wl:%d\n",
+		       cx->cnt_bt[BTC_BCNT_ROLESW], cx->cnt_bt[BTC_BCNT_AFH],
+		       cx->cnt_bt[BTC_BCNT_INQPAG], cx->cnt_bt[BTC_BCNT_INQ],
+		       cx->cnt_bt[BTC_BCNT_PAGE], cx->cnt_bt[BTC_BCNT_IGNOWL]);
+
+	p += _show_bt_profile_info(rtwdev, p, end - p);
+
+	p += scnprintf(p, end - p,
+		       " %-15s : raw_data[%02x %02x %02x %02x %02x %02x] (type:%s/cnt:%d/same:%d)\n",
+		       "[bt_info]", bt->raw_info[2], bt->raw_info[3],
+		       bt->raw_info[4], bt->raw_info[5], bt->raw_info[6],
+		       bt->raw_info[7],
+		       bt->raw_info[0] == BTC_BTINFO_AUTO ? "auto" : "reply",
+		       cx->cnt_bt[BTC_BCNT_INFOUPDATE],
+		       cx->cnt_bt[BTC_BCNT_INFOSAME]);
+
+	p += scnprintf(p, end - p,
+		       " %-15s : Hi-rx = %d, Hi-tx = %d, Lo-rx = %d, Lo-tx = %d (bt_polut_wl_tx = %d)",
+		       "[trx_req_cnt]", cx->cnt_bt[BTC_BCNT_HIPRI_RX],
+		       cx->cnt_bt[BTC_BCNT_HIPRI_TX],
+		       cx->cnt_bt[BTC_BCNT_LOPRI_RX],
+		       cx->cnt_bt[BTC_BCNT_LOPRI_TX],
+		       cx->cnt_bt[BTC_BCNT_POLUT]);
 
 	if (!bt->scan_info_update) {
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_BT_SCAN_INFO, true);
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	} else {
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_BT_SCAN_INFO, false);
 		if (ver->fcxbtscan == 1) {
-			seq_printf(m,
-				   "(INQ:%d-%d/PAGE:%d-%d/LE:%d-%d/INIT:%d-%d)",
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INQ].win),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INQ].intvl),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_PAGE].win),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_PAGE].intvl),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_BLE].win),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_BLE].intvl),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INIT].win),
-				   le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INIT].intvl));
+			p += scnprintf(p, end - p,
+				       "(INQ:%d-%d/PAGE:%d-%d/LE:%d-%d/INIT:%d-%d)",
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INQ].win),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INQ].intvl),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_PAGE].win),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_PAGE].intvl),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_BLE].win),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_BLE].intvl),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INIT].win),
+				       le16_to_cpu(bt->scan_info_v1[BTC_SCAN_INIT].intvl));
 		} else if (ver->fcxbtscan == 2) {
-			seq_printf(m,
-				   "(BG:%d-%d/INIT:%d-%d/LE:%d-%d)",
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_BG].win),
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_BG].intvl),
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_INIT].win),
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_INIT].intvl),
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_LE].win),
-				   le16_to_cpu(bt->scan_info_v2[CXSCAN_LE].intvl));
+			p += scnprintf(p, end - p,
+				       "(BG:%d-%d/INIT:%d-%d/LE:%d-%d)",
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_BG].win),
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_BG].intvl),
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_INIT].win),
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_INIT].intvl),
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_LE].win),
+				       le16_to_cpu(bt->scan_info_v2[CXSCAN_LE].intvl));
 		}
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
 
 	if (bt_linfo->profile_cnt.now || bt_linfo->status.map.ble_connect)
@@ -8557,6 +8586,8 @@ static void _show_bt_info(struct rtw89_dev *rtwdev, struct seq_file *m)
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_BT_DEVICE_INFO, true);
 	else
 		rtw89_btc_fw_en_rpt(rtwdev, RPT_EN_BT_DEVICE_INFO, false);
+
+	return p - buf;
 }
 
 #define CASE_BTC_RSN_STR(e) case BTC_RSN_ ## e: return #e
@@ -8850,114 +8881,132 @@ static const char *id_to_ant(u32 id)
 }
 
 static
-void seq_print_segment(struct seq_file *m, const char *prefix, u16 *data,
-		       u8 len, u8 seg_len, u8 start_idx, u8 ring_len)
+int scnprintf_segment(char *buf, size_t bufsz, const char *prefix, const u16 *data,
+		      u8 len, u8 seg_len, u8 start_idx, u8 ring_len)
 {
-	u8 i;
+	char *p = buf, *end = buf + bufsz;
 	u8 cur_index;
+	u8 i;
 
 	for (i = 0; i < len ; i++) {
 		if ((i % seg_len) == 0)
-			seq_printf(m, " %-15s : ", prefix);
+			p += scnprintf(p, end - p, " %-15s : ", prefix);
 		cur_index = (start_idx + i) % ring_len;
 		if (i % 3 == 0)
-			seq_printf(m, "-> %-20s",
-				   steps_to_str(*(data + cur_index)));
+			p += scnprintf(p, end - p, "-> %-20s",
+				       steps_to_str(*(data + cur_index)));
 		else if (i % 3 == 1)
-			seq_printf(m, "-> %-15s",
-				   steps_to_str(*(data + cur_index)));
+			p += scnprintf(p, end - p, "-> %-15s",
+				       steps_to_str(*(data + cur_index)));
 		else
-			seq_printf(m, "-> %-13s",
-				   steps_to_str(*(data + cur_index)));
+			p += scnprintf(p, end - p, "-> %-13s",
+				       steps_to_str(*(data + cur_index)));
 		if (i == (len - 1) || (i % seg_len) == (seg_len - 1))
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
+
+	return p - buf;
 }
 
-static void _show_dm_step(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_dm_step(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_dm *dm = &btc->dm;
+	char *p = buf, *end = buf + bufsz;
 	u8 start_idx;
 	u8 len;
 
 	len = dm->dm_step.step_ov ? RTW89_BTC_DM_MAXSTEP : dm->dm_step.step_pos;
 	start_idx = dm->dm_step.step_ov ? dm->dm_step.step_pos : 0;
 
-	seq_print_segment(m, "[dm_steps]", dm->dm_step.step, len, 6, start_idx,
-			  ARRAY_SIZE(dm->dm_step.step));
+	p += scnprintf_segment(p, end - p, "[dm_steps]", dm->dm_step.step, len,
+			       6, start_idx, ARRAY_SIZE(dm->dm_step.step));
+
+	return p - buf;
 }
 
-static void _show_dm_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_dm_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_dm *dm = &btc->dm;
 	struct rtw89_btc_wl_info *wl = &btc->cx.wl;
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
+	char *p = buf, *end = buf + bufsz;
 	u8 igno_bt;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_DM))
-		return;
+		return 0;
 
-	seq_printf(m, "========== [Mechanism Status %s] ==========\n",
-		   (btc->manual_ctrl ? "(Manual)" : "(Auto)"));
+	p += scnprintf(p, end - p,
+		       "========== [Mechanism Status %s] ==========\n",
+		       (btc->manual_ctrl ? "(Manual)" : "(Auto)"));
 
-	seq_printf(m,
-		   " %-15s : type:%s, reason:%s(), action:%s(), ant_path:%s, init_mode:%s, run_cnt:%d\n",
-		   "[status]",
-		   btc->ant_type == BTC_ANT_SHARED ? "shared" : "dedicated",
-		   steps_to_str(dm->run_reason),
-		   steps_to_str(dm->run_action | BTC_ACT_EXT_BIT),
-		   id_to_ant(FIELD_GET(GENMASK(7, 0), dm->set_ant_path)),
-		   id_to_mode(wl->coex_mode),
-		   dm->cnt_dm[BTC_DCNT_RUN]);
+	p += scnprintf(p, end - p,
+		       " %-15s : type:%s, reason:%s(), action:%s(), ant_path:%s, init_mode:%s, run_cnt:%d\n",
+		       "[status]",
+		       btc->ant_type == BTC_ANT_SHARED ? "shared" : "dedicated",
+		       steps_to_str(dm->run_reason),
+		       steps_to_str(dm->run_action | BTC_ACT_EXT_BIT),
+		       id_to_ant(FIELD_GET(GENMASK(7, 0), dm->set_ant_path)),
+		       id_to_mode(wl->coex_mode),
+		       dm->cnt_dm[BTC_DCNT_RUN]);
 
-	_show_dm_step(rtwdev, m);
+	p += _show_dm_step(rtwdev, p, end - p);
 
 	if (ver->fcxctrl == 7)
 		igno_bt = btc->ctrl.ctrl_v7.igno_bt;
 	else
 		igno_bt = btc->ctrl.ctrl.igno_bt;
 
-	seq_printf(m, " %-15s : wl_only:%d, bt_only:%d, igno_bt:%d, free_run:%d, wl_ps_ctrl:%d, wl_mimo_ps:%d, ",
-		   "[dm_flag]", dm->wl_only, dm->bt_only, igno_bt,
-		   dm->freerun, btc->lps, dm->wl_mimo_ps);
+	p += scnprintf(p, end - p,
+		       " %-15s : wl_only:%d, bt_only:%d, igno_bt:%d, free_run:%d, wl_ps_ctrl:%d, wl_mimo_ps:%d, ",
+		       "[dm_flag]", dm->wl_only, dm->bt_only, igno_bt,
+		       dm->freerun, btc->lps, dm->wl_mimo_ps);
 
-	seq_printf(m, "leak_ap:%d, fw_offload:%s%s\n", dm->leak_ap,
-		   (BTC_CX_FW_OFFLOAD ? "Y" : "N"),
-		   (dm->wl_fw_cx_offload == BTC_CX_FW_OFFLOAD ?
-		    "" : "(Mismatch!!)"));
+	p += scnprintf(p, end - p, "leak_ap:%d, fw_offload:%s%s\n",
+		       dm->leak_ap,
+		       (BTC_CX_FW_OFFLOAD ? "Y" : "N"),
+		       (dm->wl_fw_cx_offload == BTC_CX_FW_OFFLOAD ?
+			"" : "(Mismatch!!)"));
 
 	if (dm->rf_trx_para.wl_tx_power == 0xff)
-		seq_printf(m,
-			   " %-15s : wl_rssi_lvl:%d, para_lvl:%d, wl_tx_pwr:orig, ",
-			   "[trx_ctrl]", wl->rssi_level, dm->trx_para_level);
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rssi_lvl:%d, para_lvl:%d, wl_tx_pwr:orig, ",
+			       "[trx_ctrl]", wl->rssi_level,
+			       dm->trx_para_level);
 
 	else
-		seq_printf(m,
-			   " %-15s : wl_rssi_lvl:%d, para_lvl:%d, wl_tx_pwr:%d, ",
-			   "[trx_ctrl]", wl->rssi_level, dm->trx_para_level,
-			   dm->rf_trx_para.wl_tx_power);
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rssi_lvl:%d, para_lvl:%d, wl_tx_pwr:%d, ",
+			       "[trx_ctrl]", wl->rssi_level,
+			       dm->trx_para_level,
+			       dm->rf_trx_para.wl_tx_power);
+
+	p += scnprintf(p, end - p,
+		       "wl_rx_lvl:%d, bt_tx_pwr_dec:%d, bt_rx_lna:%d(%s-tbl), wl_btg_rx:%d\n",
+		       dm->rf_trx_para.wl_rx_gain,
+		       dm->rf_trx_para.bt_tx_power,
+		       dm->rf_trx_para.bt_rx_gain,
+		       (bt->hi_lna_rx ? "Hi" : "Ori"), dm->wl_btg_rx);
 
-	seq_printf(m,
-		   "wl_rx_lvl:%d, bt_tx_pwr_dec:%d, bt_rx_lna:%d(%s-tbl), wl_btg_rx:%d\n",
-		   dm->rf_trx_para.wl_rx_gain, dm->rf_trx_para.bt_tx_power,
-		   dm->rf_trx_para.bt_rx_gain,
-		   (bt->hi_lna_rx ? "Hi" : "Ori"), dm->wl_btg_rx);
+	p += scnprintf(p, end - p,
+		       " %-15s : wl_tx_limit[en:%d/max_t:%dus/max_retry:%d], bt_slot_reg:%d-TU, bt_scan_rx_low_pri:%d\n",
+		       "[dm_ctrl]", dm->wl_tx_limit.enable,
+		       dm->wl_tx_limit.tx_time,
+		       dm->wl_tx_limit.tx_retry, btc->bt_req_len,
+		       bt->scan_rx_low_pri);
 
-	seq_printf(m,
-		   " %-15s : wl_tx_limit[en:%d/max_t:%dus/max_retry:%d], bt_slot_reg:%d-TU, bt_scan_rx_low_pri:%d\n",
-		   "[dm_ctrl]", dm->wl_tx_limit.enable, dm->wl_tx_limit.tx_time,
-		   dm->wl_tx_limit.tx_retry, btc->bt_req_len, bt->scan_rx_low_pri);
+	return p - buf;
 }
 
-static void _show_error(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_error(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
 	union rtw89_btc_fbtc_cysta_info *pcysta;
+	char *p = buf, *end = buf + bufsz;
 	u32 except_cnt, exception_map;
 
 	pcysta = &pfwinfo->rpt_fbtc_cysta.finfo;
@@ -8982,81 +9031,87 @@ static void _show_error(struct rtw89_dev *rtwdev, struct seq_file *m)
 		except_cnt = pcysta->v7.except_cnt;
 		exception_map = le32_to_cpu(pcysta->v7.except_map);
 	} else {
-		return;
+		return 0;
 	}
 
 	if (pfwinfo->event[BTF_EVNT_BUF_OVERFLOW] == 0 && except_cnt == 0 &&
 	    !pfwinfo->len_mismch && !pfwinfo->fver_mismch)
-		return;
+		return 0;
 
-	seq_printf(m, " %-15s : ", "[error]");
+	p += scnprintf(p, end - p, " %-15s : ", "[error]");
 
 	if (pfwinfo->event[BTF_EVNT_BUF_OVERFLOW]) {
-		seq_printf(m,
-			   "overflow-cnt: %d, ",
-			   pfwinfo->event[BTF_EVNT_BUF_OVERFLOW]);
+		p += scnprintf(p, end - p,
+			       "overflow-cnt: %d, ",
+			       pfwinfo->event[BTF_EVNT_BUF_OVERFLOW]);
 	}
 
 	if (pfwinfo->len_mismch) {
-		seq_printf(m,
-			   "len-mismatch: 0x%x, ",
-			   pfwinfo->len_mismch);
+		p += scnprintf(p, end - p,
+			       "len-mismatch: 0x%x, ",
+			       pfwinfo->len_mismch);
 	}
 
 	if (pfwinfo->fver_mismch) {
-		seq_printf(m,
-			   "fver-mismatch: 0x%x, ",
-			   pfwinfo->fver_mismch);
+		p += scnprintf(p, end - p,
+			       "fver-mismatch: 0x%x, ",
+			       pfwinfo->fver_mismch);
 	}
 
 	/* cycle statistics exceptions */
 	if (exception_map || except_cnt) {
-		seq_printf(m,
-			   "exception-type: 0x%x, exception-cnt = %d",
-			   exception_map, except_cnt);
+		p += scnprintf(p, end - p,
+			       "exception-type: 0x%x, exception-cnt = %d",
+			       exception_map, except_cnt);
 	}
-	seq_puts(m, "\n");
+	p += scnprintf(p, end - p, "\n");
+
+	return p - buf;
 }
 
-static void _show_fbtc_tdma(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_tdma(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
 	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
 	struct rtw89_btc_fbtc_tdma *t = NULL;
+	char *p = buf, *end = buf + bufsz;
 
 	pcinfo = &pfwinfo->rpt_fbtc_tdma.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	if (ver->fcxtdma == 1)
 		t = &pfwinfo->rpt_fbtc_tdma.finfo.v1;
 	else
 		t = &pfwinfo->rpt_fbtc_tdma.finfo.v3.tdma;
 
-	seq_printf(m,
-		   " %-15s : ", "[tdma_policy]");
-	seq_printf(m,
-		   "type:%d, rx_flow_ctrl:%d, tx_pause:%d, ",
-		   (u32)t->type,
-		   t->rxflctrl, t->txpause);
+	p += scnprintf(p, end - p,
+		       " %-15s : ", "[tdma_policy]");
+	p += scnprintf(p, end - p,
+		       "type:%d, rx_flow_ctrl:%d, tx_pause:%d, ",
+		       (u32)t->type,
+		       t->rxflctrl, t->txpause);
+
+	p += scnprintf(p, end - p,
+		       "wl_toggle_n:%d, leak_n:%d, ext_ctrl:%d, ",
+		       t->wtgle_n, t->leak_n, t->ext_ctrl);
 
-	seq_printf(m,
-		   "wl_toggle_n:%d, leak_n:%d, ext_ctrl:%d, ",
-		   t->wtgle_n, t->leak_n, t->ext_ctrl);
+	p += scnprintf(p, end - p,
+		       "policy_type:%d",
+		       (u32)btc->policy_type);
 
-	seq_printf(m,
-		   "policy_type:%d",
-		   (u32)btc->policy_type);
+	p += scnprintf(p, end - p, "\n");
 
-	seq_puts(m, "\n");
+	return p - buf;
 }
 
-static void _show_fbtc_slots(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_slots(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_dm *dm = &btc->dm;
+	char *p = buf, *end = buf + bufsz;
 	u16 dur, cxtype;
 	u32 tbl;
 	u8 i = 0;
@@ -9071,28 +9126,30 @@ static void _show_fbtc_slots(struct rtw89_dev *rtwdev, struct seq_file *m)
 			tbl = le32_to_cpu(dm->slot_now.v7[i].cxtbl);
 			cxtype = le16_to_cpu(dm->slot_now.v7[i].cxtype);
 		} else {
-			return;
+			return 0;
 		}
 
 		if (i % 5 == 0)
-			seq_printf(m,
-				   " %-15s : %5s[%03d/0x%x/%d]",
-				   "[slot_list]",
-				   id_to_slot((u32)i),
-				   dur, tbl, cxtype);
+			p += scnprintf(p, end - p,
+				       " %-15s : %5s[%03d/0x%x/%d]",
+				       "[slot_list]",
+				       id_to_slot((u32)i),
+				       dur, tbl, cxtype);
 		else
-			seq_printf(m,
-				   ", %5s[%03d/0x%x/%d]",
-				   id_to_slot((u32)i),
-				   dur, tbl, cxtype);
+			p += scnprintf(p, end - p,
+				       ", %5s[%03d/0x%x/%d]",
+				       id_to_slot((u32)i),
+				       dur, tbl, cxtype);
 
 		if (i % 5 == 4)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
-	seq_puts(m, "\n");
+	p += scnprintf(p, end - p, "\n");
+
+	return p - buf;
 }
 
-static void _show_fbtc_cysta_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_cysta_v2(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -9101,63 +9158,64 @@ static void _show_fbtc_cysta_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
 	struct rtw89_btc_fbtc_cysta_v2 *pcysta_le32 = NULL;
 	union rtw89_btc_fbtc_rxflct r;
-	u8 i, cnt = 0, slot_pair;
 	u16 cycle, c_begin, c_end, store_index;
+	char *p = buf, *end = buf + bufsz;
+	u8 i, cnt = 0, slot_pair;
 
 	pcinfo = &pfwinfo->rpt_fbtc_cysta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pcysta_le32 = &pfwinfo->rpt_fbtc_cysta.finfo.v2;
-	seq_printf(m,
-		   " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
-		   "[cycle_cnt]",
-		   le16_to_cpu(pcysta_le32->cycles),
-		   le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_ALL]),
-		   le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_ALL_OK]),
-		   le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_BT_SLOT]),
-		   le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_BT_OK]));
+	p += scnprintf(p, end - p,
+		       " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
+		       "[cycle_cnt]",
+		       le16_to_cpu(pcysta_le32->cycles),
+		       le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_ALL]),
+		       le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_ALL_OK]),
+		       le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_BT_SLOT]),
+		       le32_to_cpu(pcysta_le32->bcn_cnt[CXBCN_BT_OK]));
 
 	for (i = 0; i < CXST_MAX; i++) {
 		if (!le32_to_cpu(pcysta_le32->slot_cnt[i]))
 			continue;
-		seq_printf(m, ", %s:%d", id_to_slot((u32)i),
-			   le32_to_cpu(pcysta_le32->slot_cnt[i]));
+		p += scnprintf(p, end - p, ", %s:%d", id_to_slot((u32)i),
+			       le32_to_cpu(pcysta_le32->slot_cnt[i]));
 	}
 
 	if (dm->tdma_now.rxflctrl) {
-		seq_printf(m, ", leak_rx:%d",
-			   le32_to_cpu(pcysta_le32->leakrx_cnt));
+		p += scnprintf(p, end - p, ", leak_rx:%d",
+			       le32_to_cpu(pcysta_le32->leakrx_cnt));
 	}
 
 	if (le32_to_cpu(pcysta_le32->collision_cnt)) {
-		seq_printf(m, ", collision:%d",
-			   le32_to_cpu(pcysta_le32->collision_cnt));
+		p += scnprintf(p, end - p, ", collision:%d",
+			       le32_to_cpu(pcysta_le32->collision_cnt));
 	}
 
 	if (le32_to_cpu(pcysta_le32->skip_cnt)) {
-		seq_printf(m, ", skip:%d",
-			   le32_to_cpu(pcysta_le32->skip_cnt));
-	}
-	seq_puts(m, "\n");
-
-	seq_printf(m, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   "[cycle_time]",
-		   le16_to_cpu(pcysta_le32->tavg_cycle[CXT_WL]),
-		   le16_to_cpu(pcysta_le32->tavg_cycle[CXT_BT]),
-		   le16_to_cpu(pcysta_le32->tavg_lk) / 1000,
-		   le16_to_cpu(pcysta_le32->tavg_lk) % 1000);
-	seq_printf(m, ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   le16_to_cpu(pcysta_le32->tmax_cycle[CXT_WL]),
-		   le16_to_cpu(pcysta_le32->tmax_cycle[CXT_BT]),
-		   le16_to_cpu(pcysta_le32->tmax_lk) / 1000,
-		   le16_to_cpu(pcysta_le32->tmax_lk) % 1000);
-	seq_printf(m, ", maxdiff_t[wl:%d/bt:%d]\n",
-		   le16_to_cpu(pcysta_le32->tmaxdiff_cycle[CXT_WL]),
-		   le16_to_cpu(pcysta_le32->tmaxdiff_cycle[CXT_BT]));
+		p += scnprintf(p, end - p, ", skip:%d",
+			       le32_to_cpu(pcysta_le32->skip_cnt));
+	}
+	p += scnprintf(p, end - p, "\n");
+
+	p += scnprintf(p, end - p, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       "[cycle_time]",
+		       le16_to_cpu(pcysta_le32->tavg_cycle[CXT_WL]),
+		       le16_to_cpu(pcysta_le32->tavg_cycle[CXT_BT]),
+		       le16_to_cpu(pcysta_le32->tavg_lk) / 1000,
+		       le16_to_cpu(pcysta_le32->tavg_lk) % 1000);
+	p += scnprintf(p, end - p, ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       le16_to_cpu(pcysta_le32->tmax_cycle[CXT_WL]),
+		       le16_to_cpu(pcysta_le32->tmax_cycle[CXT_BT]),
+		       le16_to_cpu(pcysta_le32->tmax_lk) / 1000,
+		       le16_to_cpu(pcysta_le32->tmax_lk) % 1000);
+	p += scnprintf(p, end - p, ", maxdiff_t[wl:%d/bt:%d]\n",
+		       le16_to_cpu(pcysta_le32->tmaxdiff_cycle[CXT_WL]),
+		       le16_to_cpu(pcysta_le32->tmaxdiff_cycle[CXT_BT]));
 
 	if (le16_to_cpu(pcysta_le32->cycles) <= 1)
-		return;
+		goto out;
 
 	/* 1 cycle record 1 wl-slot and 1 bt-slot */
 	slot_pair = BTC_CYCLE_SLOT_MAX / 2;
@@ -9174,53 +9232,57 @@ static void _show_fbtc_cysta_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 		store_index = ((cycle - 1) % slot_pair) * 2;
 
 		if (cnt % (BTC_CYCLE_SLOT_MAX / 4) == 1)
-			seq_printf(m,
-				   " %-15s : ->b%02d->w%02d", "[cycle_step]",
-				   le16_to_cpu(pcysta_le32->tslot_cycle[store_index]),
-				   le16_to_cpu(pcysta_le32->tslot_cycle[store_index + 1]));
+			p += scnprintf(p, end - p,
+				       " %-15s : ->b%02d->w%02d",
+				       "[cycle_step]",
+				       le16_to_cpu(pcysta_le32->tslot_cycle[store_index]),
+				       le16_to_cpu(pcysta_le32->tslot_cycle[store_index + 1]));
 		else
-			seq_printf(m,
-				   "->b%02d->w%02d",
-				   le16_to_cpu(pcysta_le32->tslot_cycle[store_index]),
-				   le16_to_cpu(pcysta_le32->tslot_cycle[store_index + 1]));
+			p += scnprintf(p, end - p,
+				       "->b%02d->w%02d",
+				       le16_to_cpu(pcysta_le32->tslot_cycle[store_index]),
+				       le16_to_cpu(pcysta_le32->tslot_cycle[store_index + 1]));
 		if (cnt % (BTC_CYCLE_SLOT_MAX / 4) == 0 || cnt == c_end)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
 
 	if (a2dp->exist) {
-		seq_printf(m,
-			   " %-15s : a2dp_ept:%d, a2dp_late:%d",
-			   "[a2dp_t_sta]",
-			   le16_to_cpu(pcysta_le32->a2dpept),
-			   le16_to_cpu(pcysta_le32->a2dpeptto));
-
-		seq_printf(m,
-			   ", avg_t:%d, max_t:%d",
-			   le16_to_cpu(pcysta_le32->tavg_a2dpept),
-			   le16_to_cpu(pcysta_le32->tmax_a2dpept));
+		p += scnprintf(p, end - p,
+			       " %-15s : a2dp_ept:%d, a2dp_late:%d",
+			       "[a2dp_t_sta]",
+			       le16_to_cpu(pcysta_le32->a2dpept),
+			       le16_to_cpu(pcysta_le32->a2dpeptto));
+
+		p += scnprintf(p, end - p,
+			       ", avg_t:%d, max_t:%d",
+			       le16_to_cpu(pcysta_le32->tavg_a2dpept),
+			       le16_to_cpu(pcysta_le32->tmax_a2dpept));
 		r.val = dm->tdma_now.rxflctrl;
 
 		if (r.type && r.tgln_n) {
-			seq_printf(m,
-				   ", cycle[PSTDMA:%d/TDMA:%d], ",
-				   le16_to_cpu(pcysta_le32->cycles_a2dp[CXT_FLCTRL_ON]),
-				   le16_to_cpu(pcysta_le32->cycles_a2dp[CXT_FLCTRL_OFF]));
-
-			seq_printf(m,
-				   "avg_t[PSTDMA:%d/TDMA:%d], ",
-				   le16_to_cpu(pcysta_le32->tavg_a2dp[CXT_FLCTRL_ON]),
-				   le16_to_cpu(pcysta_le32->tavg_a2dp[CXT_FLCTRL_OFF]));
-
-			seq_printf(m,
-				   "max_t[PSTDMA:%d/TDMA:%d]",
-				   le16_to_cpu(pcysta_le32->tmax_a2dp[CXT_FLCTRL_ON]),
-				   le16_to_cpu(pcysta_le32->tmax_a2dp[CXT_FLCTRL_OFF]));
+			p += scnprintf(p, end - p,
+				       ", cycle[PSTDMA:%d/TDMA:%d], ",
+				       le16_to_cpu(pcysta_le32->cycles_a2dp[CXT_FLCTRL_ON]),
+				       le16_to_cpu(pcysta_le32->cycles_a2dp[CXT_FLCTRL_OFF]));
+
+			p += scnprintf(p, end - p,
+				       "avg_t[PSTDMA:%d/TDMA:%d], ",
+				       le16_to_cpu(pcysta_le32->tavg_a2dp[CXT_FLCTRL_ON]),
+				       le16_to_cpu(pcysta_le32->tavg_a2dp[CXT_FLCTRL_OFF]));
+
+			p += scnprintf(p, end - p,
+				       "max_t[PSTDMA:%d/TDMA:%d]",
+				       le16_to_cpu(pcysta_le32->tmax_a2dp[CXT_FLCTRL_ON]),
+				       le16_to_cpu(pcysta_le32->tmax_a2dp[CXT_FLCTRL_OFF]));
 		}
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_fbtc_cysta_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_cysta_v3(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &btc->cx.bt.link_info.a2dp_desc;
@@ -9231,60 +9293,64 @@ static void _show_fbtc_cysta_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
 	u8 i, cnt = 0, slot_pair, divide_cnt;
 	u16 cycle, c_begin, c_end, store_index;
+	char *p = buf, *end = buf + bufsz;
 
 	pcinfo = &pfwinfo->rpt_fbtc_cysta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pcysta = &pfwinfo->rpt_fbtc_cysta.finfo.v3;
-	seq_printf(m,
-		   " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
-		   "[cycle_cnt]",
-		   le16_to_cpu(pcysta->cycles),
-		   le32_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
-		   le32_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
-		   le32_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
-		   le32_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
+	p += scnprintf(p, end - p,
+		       " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
+		       "[cycle_cnt]",
+		       le16_to_cpu(pcysta->cycles),
+		       le32_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
+		       le32_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
+		       le32_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
+		       le32_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
 
 	for (i = 0; i < CXST_MAX; i++) {
 		if (!le32_to_cpu(pcysta->slot_cnt[i]))
 			continue;
 
-		seq_printf(m, ", %s:%d", id_to_slot(i),
-			   le32_to_cpu(pcysta->slot_cnt[i]));
+		p += scnprintf(p, end - p, ", %s:%d", id_to_slot(i),
+			       le32_to_cpu(pcysta->slot_cnt[i]));
 	}
 
 	if (dm->tdma_now.rxflctrl)
-		seq_printf(m, ", leak_rx:%d", le32_to_cpu(pcysta->leak_slot.cnt_rximr));
+		p += scnprintf(p, end - p, ", leak_rx:%d",
+			       le32_to_cpu(pcysta->leak_slot.cnt_rximr));
 
 	if (le32_to_cpu(pcysta->collision_cnt))
-		seq_printf(m, ", collision:%d", le32_to_cpu(pcysta->collision_cnt));
+		p += scnprintf(p, end - p, ", collision:%d",
+			       le32_to_cpu(pcysta->collision_cnt));
 
 	if (le32_to_cpu(pcysta->skip_cnt))
-		seq_printf(m, ", skip:%d", le32_to_cpu(pcysta->skip_cnt));
-
-	seq_puts(m, "\n");
-
-	seq_printf(m, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   "[cycle_time]",
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
-	seq_printf(m,
-		   ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
-	seq_printf(m,
-		   ", maxdiff_t[wl:%d/bt:%d]\n",
-		   le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_BT]));
+		p += scnprintf(p, end - p, ", skip:%d",
+			       le32_to_cpu(pcysta->skip_cnt));
+
+	p += scnprintf(p, end - p, "\n");
+
+	p += scnprintf(p, end - p, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       "[cycle_time]",
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
+	p += scnprintf(p, end - p,
+		       ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
+	p += scnprintf(p, end - p,
+		       ", maxdiff_t[wl:%d/bt:%d]\n",
+		       le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_BT]));
 
 	cycle = le16_to_cpu(pcysta->cycles);
 	if (cycle <= 1)
-		return;
+		goto out;
 
 	/* 1 cycle record 1 wl-slot and 1 bt-slot */
 	slot_pair = BTC_CYCLE_SLOT_MAX / 2;
@@ -9306,51 +9372,56 @@ static void _show_fbtc_cysta_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
 		store_index = ((cycle - 1) % slot_pair) * 2;
 
 		if (cnt % divide_cnt == 1)
-			seq_printf(m, " %-15s : ", "[cycle_step]");
+			p += scnprintf(p, end - p, " %-15s : ",
+				       "[cycle_step]");
 
-		seq_printf(m, "->b%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index]));
+		p += scnprintf(p, end - p, "->b%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
-		seq_printf(m, "->w%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
+		p += scnprintf(p, end - p, "->w%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index + 1];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
 		if (cnt % divide_cnt == 0 || cnt == c_end)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
 
 	if (a2dp->exist) {
-		seq_printf(m, " %-15s : a2dp_ept:%d, a2dp_late:%d",
-			   "[a2dp_t_sta]",
-			   le16_to_cpu(pcysta->a2dp_ept.cnt),
-			   le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
+		p += scnprintf(p, end - p,
+			       " %-15s : a2dp_ept:%d, a2dp_late:%d",
+			       "[a2dp_t_sta]",
+			       le16_to_cpu(pcysta->a2dp_ept.cnt),
+			       le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
 
-		seq_printf(m, ", avg_t:%d, max_t:%d",
-			   le16_to_cpu(pcysta->a2dp_ept.tavg),
-			   le16_to_cpu(pcysta->a2dp_ept.tmax));
+		p += scnprintf(p, end - p, ", avg_t:%d, max_t:%d",
+			       le16_to_cpu(pcysta->a2dp_ept.tavg),
+			       le16_to_cpu(pcysta->a2dp_ept.tmax));
 
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_fbtc_cysta_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_cysta_v4(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &btc->cx.bt.link_info.a2dp_desc;
@@ -9361,62 +9432,64 @@ static void _show_fbtc_cysta_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
 	u8 i, cnt = 0, slot_pair, divide_cnt;
 	u16 cycle, c_begin, c_end, store_index;
+	char *p = buf, *end = buf + bufsz;
 
 	pcinfo = &pfwinfo->rpt_fbtc_cysta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pcysta = &pfwinfo->rpt_fbtc_cysta.finfo.v4;
-	seq_printf(m,
-		   " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
-		   "[cycle_cnt]",
-		   le16_to_cpu(pcysta->cycles),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
+	p += scnprintf(p, end - p,
+		       " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
+		       "[cycle_cnt]",
+		       le16_to_cpu(pcysta->cycles),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
 
 	for (i = 0; i < CXST_MAX; i++) {
 		if (!le16_to_cpu(pcysta->slot_cnt[i]))
 			continue;
 
-		seq_printf(m, ", %s:%d", id_to_slot(i),
-			   le16_to_cpu(pcysta->slot_cnt[i]));
+		p += scnprintf(p, end - p, ", %s:%d", id_to_slot(i),
+			       le16_to_cpu(pcysta->slot_cnt[i]));
 	}
 
 	if (dm->tdma_now.rxflctrl)
-		seq_printf(m, ", leak_rx:%d",
-			   le32_to_cpu(pcysta->leak_slot.cnt_rximr));
+		p += scnprintf(p, end - p, ", leak_rx:%d",
+			       le32_to_cpu(pcysta->leak_slot.cnt_rximr));
 
 	if (pcysta->collision_cnt)
-		seq_printf(m, ", collision:%d", pcysta->collision_cnt);
+		p += scnprintf(p, end - p, ", collision:%d",
+			       pcysta->collision_cnt);
 
 	if (le16_to_cpu(pcysta->skip_cnt))
-		seq_printf(m, ", skip:%d",
-			   le16_to_cpu(pcysta->skip_cnt));
-
-	seq_puts(m, "\n");
-
-	seq_printf(m, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   "[cycle_time]",
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
-	seq_printf(m,
-		   ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
-	seq_printf(m,
-		   ", maxdiff_t[wl:%d/bt:%d]\n",
-		   le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_BT]));
+		p += scnprintf(p, end - p, ", skip:%d",
+			       le16_to_cpu(pcysta->skip_cnt));
+
+	p += scnprintf(p, end - p, "\n");
+
+	p += scnprintf(p, end - p, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       "[cycle_time]",
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
+	p += scnprintf(p, end - p,
+		       ", max_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
+	p += scnprintf(p, end - p,
+		       ", maxdiff_t[wl:%d/bt:%d]\n",
+		       le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmaxdiff[CXT_BT]));
 
 	cycle = le16_to_cpu(pcysta->cycles);
 	if (cycle <= 1)
-		return;
+		goto out;
 
 	/* 1 cycle record 1 wl-slot and 1 bt-slot */
 	slot_pair = BTC_CYCLE_SLOT_MAX / 2;
@@ -9438,51 +9511,56 @@ static void _show_fbtc_cysta_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
 		store_index = ((cycle - 1) % slot_pair) * 2;
 
 		if (cnt % divide_cnt == 1)
-			seq_printf(m, " %-15s : ", "[cycle_step]");
+			p += scnprintf(p, end - p, " %-15s : ",
+				       "[cycle_step]");
 
-		seq_printf(m, "->b%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index]));
+		p += scnprintf(p, end - p, "->b%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
-		seq_printf(m, "->w%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
+		p += scnprintf(p, end - p, "->w%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index + 1];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
 		if (cnt % divide_cnt == 0 || cnt == c_end)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
 
 	if (a2dp->exist) {
-		seq_printf(m, " %-15s : a2dp_ept:%d, a2dp_late:%d",
-			   "[a2dp_t_sta]",
-			   le16_to_cpu(pcysta->a2dp_ept.cnt),
-			   le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
+		p += scnprintf(p, end - p,
+			       " %-15s : a2dp_ept:%d, a2dp_late:%d",
+			       "[a2dp_t_sta]",
+			       le16_to_cpu(pcysta->a2dp_ept.cnt),
+			       le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
 
-		seq_printf(m, ", avg_t:%d, max_t:%d",
-			   le16_to_cpu(pcysta->a2dp_ept.tavg),
-			   le16_to_cpu(pcysta->a2dp_ept.tmax));
+		p += scnprintf(p, end - p, ", avg_t:%d, max_t:%d",
+			       le16_to_cpu(pcysta->a2dp_ept.tavg),
+			       le16_to_cpu(pcysta->a2dp_ept.tmax));
 
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_fbtc_cysta_v5(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_cysta_v5(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &btc->cx.bt.link_info.a2dp_desc;
@@ -9493,58 +9571,60 @@ static void _show_fbtc_cysta_v5(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
 	u8 i, cnt = 0, slot_pair, divide_cnt;
 	u16 cycle, c_begin, c_end, store_index;
+	char *p = buf, *end = buf + bufsz;
 
 	pcinfo = &pfwinfo->rpt_fbtc_cysta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pcysta = &pfwinfo->rpt_fbtc_cysta.finfo.v5;
-	seq_printf(m,
-		   " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
-		   "[cycle_cnt]",
-		   le16_to_cpu(pcysta->cycles),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
+	p += scnprintf(p, end - p,
+		       " %-15s : cycle:%d, bcn[all:%d/all_ok:%d/bt:%d/bt_ok:%d]",
+		       "[cycle_cnt]",
+		       le16_to_cpu(pcysta->cycles),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
 
 	for (i = 0; i < CXST_MAX; i++) {
 		if (!le16_to_cpu(pcysta->slot_cnt[i]))
 			continue;
 
-		seq_printf(m, ", %s:%d", id_to_slot(i),
-			   le16_to_cpu(pcysta->slot_cnt[i]));
+		p += scnprintf(p, end - p, ", %s:%d", id_to_slot(i),
+			       le16_to_cpu(pcysta->slot_cnt[i]));
 	}
 
 	if (dm->tdma_now.rxflctrl)
-		seq_printf(m, ", leak_rx:%d",
-			   le32_to_cpu(pcysta->leak_slot.cnt_rximr));
+		p += scnprintf(p, end - p, ", leak_rx:%d",
+			       le32_to_cpu(pcysta->leak_slot.cnt_rximr));
 
 	if (pcysta->collision_cnt)
-		seq_printf(m, ", collision:%d", pcysta->collision_cnt);
+		p += scnprintf(p, end - p, ", collision:%d",
+			       pcysta->collision_cnt);
 
 	if (le16_to_cpu(pcysta->skip_cnt))
-		seq_printf(m, ", skip:%d",
-			   le16_to_cpu(pcysta->skip_cnt));
-
-	seq_puts(m, "\n");
-
-	seq_printf(m, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   "[cycle_time]",
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
-	seq_printf(m,
-		   ", max_t[wl:%d/bt:%d/lk:%d.%03d]\n",
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
+		p += scnprintf(p, end - p, ", skip:%d",
+			       le16_to_cpu(pcysta->skip_cnt));
+
+	p += scnprintf(p, end - p, "\n");
+
+	p += scnprintf(p, end - p, " %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       "[cycle_time]",
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
+	p += scnprintf(p, end - p,
+		       ", max_t[wl:%d/bt:%d/lk:%d.%03d]\n",
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tmax) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tmax) % 1000);
 
 	cycle = le16_to_cpu(pcysta->cycles);
 	if (cycle <= 1)
-		return;
+		goto out;
 
 	/* 1 cycle record 1 wl-slot and 1 bt-slot */
 	slot_pair = BTC_CYCLE_SLOT_MAX / 2;
@@ -9562,58 +9642,63 @@ static void _show_fbtc_cysta_v5(struct rtw89_dev *rtwdev, struct seq_file *m)
 		divide_cnt = BTC_CYCLE_SLOT_MAX / 4;
 
 	if (c_begin > c_end)
-		return;
+		goto out;
 
 	for (cycle = c_begin; cycle <= c_end; cycle++) {
 		cnt++;
 		store_index = ((cycle - 1) % slot_pair) * 2;
 
 		if (cnt % divide_cnt == 1)
-			seq_printf(m, " %-15s : ", "[cycle_step]");
+			p += scnprintf(p, end - p, " %-15s : ",
+				       "[cycle_step]");
 
-		seq_printf(m, "->b%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index]));
+		p += scnprintf(p, end - p, "->b%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
-		seq_printf(m, "->w%02d",
-			   le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
+		p += scnprintf(p, end - p, "->w%02d",
+			       le16_to_cpu(pcysta->slot_step_time[store_index + 1]));
 		if (a2dp->exist) {
 			a2dp_trx = &pcysta->a2dp_trx[store_index + 1];
-			seq_printf(m, "(%d/%d/%dM/%d/%d/%d)",
-				   a2dp_trx->empty_cnt,
-				   a2dp_trx->retry_cnt,
-				   a2dp_trx->tx_rate ? 3 : 2,
-				   a2dp_trx->tx_cnt,
-				   a2dp_trx->ack_cnt,
-				   a2dp_trx->nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%dM/%d/%d/%d)",
+				       a2dp_trx->empty_cnt,
+				       a2dp_trx->retry_cnt,
+				       a2dp_trx->tx_rate ? 3 : 2,
+				       a2dp_trx->tx_cnt,
+				       a2dp_trx->ack_cnt,
+				       a2dp_trx->nack_cnt);
 		}
 		if (cnt % divide_cnt == 0 || cnt == c_end)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
 
 	if (a2dp->exist) {
-		seq_printf(m, " %-15s : a2dp_ept:%d, a2dp_late:%d",
-			   "[a2dp_t_sta]",
-			   le16_to_cpu(pcysta->a2dp_ept.cnt),
-			   le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
+		p += scnprintf(p, end - p,
+			       " %-15s : a2dp_ept:%d, a2dp_late:%d",
+			       "[a2dp_t_sta]",
+			       le16_to_cpu(pcysta->a2dp_ept.cnt),
+			       le16_to_cpu(pcysta->a2dp_ept.cnt_timeout));
 
-		seq_printf(m, ", avg_t:%d, max_t:%d",
-			   le16_to_cpu(pcysta->a2dp_ept.tavg),
-			   le16_to_cpu(pcysta->a2dp_ept.tmax));
+		p += scnprintf(p, end - p, ", avg_t:%d, max_t:%d",
+			       le16_to_cpu(pcysta->a2dp_ept.tavg),
+			       le16_to_cpu(pcysta->a2dp_ept.tmax));
 
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_fbtc_cysta_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_cysta_v7(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc_bt_info *bt = &rtwdev->btc.cx.bt;
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &bt->link_info.a2dp_desc;
@@ -9621,68 +9706,75 @@ static void _show_fbtc_cysta_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_fbtc_cysta_v7 *pcysta = NULL;
 	struct rtw89_btc_dm *dm = &rtwdev->btc.dm;
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
+	char *p = buf, *end = buf + bufsz;
 	u16 cycle, c_begin, c_end, s_id;
 	u8 i, cnt = 0, divide_cnt;
 	u8 slot_pair;
 
 	pcinfo = &pfwinfo->rpt_fbtc_cysta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pcysta = &pfwinfo->rpt_fbtc_cysta.finfo.v7;
-	seq_printf(m, "\n\r %-15s : cycle:%d", "[slot_stat]",
-		   le16_to_cpu(pcysta->cycles));
+	p += scnprintf(p, end - p, "\n\r %-15s : cycle:%d", "[slot_stat]",
+		       le16_to_cpu(pcysta->cycles));
 
 	for (i = 0; i < CXST_MAX; i++) {
 		if (!le16_to_cpu(pcysta->slot_cnt[i]))
 			continue;
-		seq_printf(m, ", %s:%d",
-			   id_to_slot(i), le16_to_cpu(pcysta->slot_cnt[i]));
+		p += scnprintf(p, end - p, ", %s:%d",
+			       id_to_slot(i),
+			       le16_to_cpu(pcysta->slot_cnt[i]));
 	}
 
 	if (dm->tdma_now.rxflctrl)
-		seq_printf(m, ", leak_rx:%d",
-			   le32_to_cpu(pcysta->leak_slot.cnt_rximr));
+		p += scnprintf(p, end - p, ", leak_rx:%d",
+			       le32_to_cpu(pcysta->leak_slot.cnt_rximr));
 
 	if (pcysta->collision_cnt)
-		seq_printf(m, ", collision:%d", pcysta->collision_cnt);
+		p += scnprintf(p, end - p, ", collision:%d",
+			       pcysta->collision_cnt);
 
 	if (pcysta->skip_cnt)
-		seq_printf(m, ", skip:%d", le16_to_cpu(pcysta->skip_cnt));
-
-	seq_printf(m, "\n\r %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
-		   "[cycle_stat]",
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
-		   le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
-	seq_printf(m, ", max_t[wl:%d/bt:%d(>%dms:%d)/lk:%d.%03d]",
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
-		   le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
-		   dm->bt_slot_flood, dm->cnt_dm[BTC_DCNT_BT_SLOT_FLOOD],
-		   le16_to_cpu(pcysta->leak_slot.tamx) / 1000,
-		   le16_to_cpu(pcysta->leak_slot.tamx) % 1000);
-	seq_printf(m, ", bcn[all:%d/ok:%d/in_bt:%d/in_bt_ok:%d]",
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
-		   le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
+		p += scnprintf(p, end - p, ", skip:%d",
+			       le16_to_cpu(pcysta->skip_cnt));
+
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : avg_t[wl:%d/bt:%d/lk:%d.%03d]",
+		       "[cycle_stat]",
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tavg[CXT_BT]),
+		       le16_to_cpu(pcysta->leak_slot.tavg) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tavg) % 1000);
+	p += scnprintf(p, end - p,
+		       ", max_t[wl:%d/bt:%d(>%dms:%d)/lk:%d.%03d]",
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_WL]),
+		       le16_to_cpu(pcysta->cycle_time.tmax[CXT_BT]),
+		       dm->bt_slot_flood, dm->cnt_dm[BTC_DCNT_BT_SLOT_FLOOD],
+		       le16_to_cpu(pcysta->leak_slot.tamx) / 1000,
+		       le16_to_cpu(pcysta->leak_slot.tamx) % 1000);
+	p += scnprintf(p, end - p, ", bcn[all:%d/ok:%d/in_bt:%d/in_bt_ok:%d]",
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_ALL_OK]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_SLOT]),
+		       le16_to_cpu(pcysta->bcn_cnt[CXBCN_BT_OK]));
 
 	if (a2dp->exist) {
-		seq_printf(m,
-			   "\n\r %-15s : a2dp_ept:%d, a2dp_late:%d(streak 2S:%d/max:%d)",
-			   "[a2dp_stat]",
-			   le16_to_cpu(pcysta->a2dp_ept.cnt),
-			   le16_to_cpu(pcysta->a2dp_ept.cnt_timeout),
-			   a2dp->no_empty_streak_2s, a2dp->no_empty_streak_max);
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : a2dp_ept:%d, a2dp_late:%d(streak 2S:%d/max:%d)",
+			       "[a2dp_stat]",
+			       le16_to_cpu(pcysta->a2dp_ept.cnt),
+			       le16_to_cpu(pcysta->a2dp_ept.cnt_timeout),
+			       a2dp->no_empty_streak_2s,
+			       a2dp->no_empty_streak_max);
 
-		seq_printf(m, ", avg_t:%d, max_t:%d",
-			   le16_to_cpu(pcysta->a2dp_ept.tavg),
-			   le16_to_cpu(pcysta->a2dp_ept.tmax));
+		p += scnprintf(p, end - p, ", avg_t:%d, max_t:%d",
+			       le16_to_cpu(pcysta->a2dp_ept.tavg),
+			       le16_to_cpu(pcysta->a2dp_ept.tmax));
 	}
 
 	if (le16_to_cpu(pcysta->cycles) <= 1)
-		return;
+		goto out;
 
 	/* 1 cycle = 1 wl-slot + 1 bt-slot */
 	slot_pair = BTC_CYCLE_SLOT_MAX / 2;
@@ -9700,7 +9792,7 @@ static void _show_fbtc_cysta_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 		divide_cnt = 6;
 
 	if (c_begin > c_end)
-		return;
+		goto out;
 
 	for (cycle = c_begin; cycle <= c_end; cycle++) {
 		cnt++;
@@ -9708,129 +9800,142 @@ static void _show_fbtc_cysta_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 
 		if (cnt % divide_cnt == 1) {
 			if (a2dp->exist)
-				seq_printf(m, "\n\r %-15s : ", "[slotT_wermtan]");
+				p += scnprintf(p, end - p, "\n\r %-15s : ",
+					       "[slotT_wermtan]");
 			else
-				seq_printf(m, "\n\r %-15s : ", "[slotT_rxerr]");
+				p += scnprintf(p, end - p, "\n\r %-15s : ",
+					       "[slotT_rxerr]");
 		}
 
-		seq_printf(m, "->b%d", le16_to_cpu(pcysta->slot_step_time[s_id]));
+		p += scnprintf(p, end - p, "->b%d",
+			       le16_to_cpu(pcysta->slot_step_time[s_id]));
 
 		if (a2dp->exist)
-			seq_printf(m, "(%d/%d/%d/%dM/%d/%d/%d)",
-				   pcysta->wl_rx_err_ratio[s_id],
-				   pcysta->a2dp_trx[s_id].empty_cnt,
-				   pcysta->a2dp_trx[s_id].retry_cnt,
-				   (pcysta->a2dp_trx[s_id].tx_rate ? 3 : 2),
-				   pcysta->a2dp_trx[s_id].tx_cnt,
-				   pcysta->a2dp_trx[s_id].ack_cnt,
-				   pcysta->a2dp_trx[s_id].nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%d/%dM/%d/%d/%d)",
+				       pcysta->wl_rx_err_ratio[s_id],
+				       pcysta->a2dp_trx[s_id].empty_cnt,
+				       pcysta->a2dp_trx[s_id].retry_cnt,
+				       (pcysta->a2dp_trx[s_id].tx_rate ? 3 : 2),
+				       pcysta->a2dp_trx[s_id].tx_cnt,
+				       pcysta->a2dp_trx[s_id].ack_cnt,
+				       pcysta->a2dp_trx[s_id].nack_cnt);
 		else
-			seq_printf(m, "(%d)", pcysta->wl_rx_err_ratio[s_id]);
+			p += scnprintf(p, end - p, "(%d)",
+				       pcysta->wl_rx_err_ratio[s_id]);
 
-		seq_printf(m, "->w%d", le16_to_cpu(pcysta->slot_step_time[s_id + 1]));
+		p += scnprintf(p, end - p, "->w%d",
+			       le16_to_cpu(pcysta->slot_step_time[s_id + 1]));
 
 		if (a2dp->exist)
-			seq_printf(m, "(%d/%d/%d/%dM/%d/%d/%d)",
-				   pcysta->wl_rx_err_ratio[s_id + 1],
-				   pcysta->a2dp_trx[s_id + 1].empty_cnt,
-				   pcysta->a2dp_trx[s_id + 1].retry_cnt,
-				   (pcysta->a2dp_trx[s_id + 1].tx_rate ? 3 : 2),
-				   pcysta->a2dp_trx[s_id + 1].tx_cnt,
-				   pcysta->a2dp_trx[s_id + 1].ack_cnt,
-				   pcysta->a2dp_trx[s_id + 1].nack_cnt);
+			p += scnprintf(p, end - p, "(%d/%d/%d/%dM/%d/%d/%d)",
+				       pcysta->wl_rx_err_ratio[s_id + 1],
+				       pcysta->a2dp_trx[s_id + 1].empty_cnt,
+				       pcysta->a2dp_trx[s_id + 1].retry_cnt,
+				       (pcysta->a2dp_trx[s_id + 1].tx_rate ? 3 : 2),
+				       pcysta->a2dp_trx[s_id + 1].tx_cnt,
+				       pcysta->a2dp_trx[s_id + 1].ack_cnt,
+				       pcysta->a2dp_trx[s_id + 1].nack_cnt);
 		else
-			seq_printf(m, "(%d)", pcysta->wl_rx_err_ratio[s_id + 1]);
+			p += scnprintf(p, end - p, "(%d)",
+				       pcysta->wl_rx_err_ratio[s_id + 1]);
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_fbtc_nullsta(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_nullsta(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
 	union rtw89_btc_fbtc_cynullsta_info *ns;
+	char *p = buf, *end = buf + bufsz;
 	u8 i = 0;
 
 	if (!btc->dm.tdma_now.rxflctrl)
-		return;
+		return 0;
 
 	pcinfo = &pfwinfo->rpt_fbtc_nullsta.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	ns = &pfwinfo->rpt_fbtc_nullsta.finfo;
 	if (ver->fcxnullsta == 1) {
 		for (i = 0; i < 2; i++) {
-			seq_printf(m, " %-15s : ", "[NULL-STA]");
-			seq_printf(m, "null-%d", i);
-			seq_printf(m, "[ok:%d/",
-				   le32_to_cpu(ns->v1.result[i][1]));
-			seq_printf(m, "fail:%d/",
-				   le32_to_cpu(ns->v1.result[i][0]));
-			seq_printf(m, "on_time:%d/",
-				   le32_to_cpu(ns->v1.result[i][2]));
-			seq_printf(m, "retry:%d/",
-				   le32_to_cpu(ns->v1.result[i][3]));
-			seq_printf(m, "avg_t:%d.%03d/",
-				   le32_to_cpu(ns->v1.avg_t[i]) / 1000,
-				   le32_to_cpu(ns->v1.avg_t[i]) % 1000);
-			seq_printf(m, "max_t:%d.%03d]\n",
-				   le32_to_cpu(ns->v1.max_t[i]) / 1000,
-				   le32_to_cpu(ns->v1.max_t[i]) % 1000);
+			p += scnprintf(p, end - p, " %-15s : ", "[NULL-STA]");
+			p += scnprintf(p, end - p, "null-%d", i);
+			p += scnprintf(p, end - p, "[ok:%d/",
+				       le32_to_cpu(ns->v1.result[i][1]));
+			p += scnprintf(p, end - p, "fail:%d/",
+				       le32_to_cpu(ns->v1.result[i][0]));
+			p += scnprintf(p, end - p, "on_time:%d/",
+				       le32_to_cpu(ns->v1.result[i][2]));
+			p += scnprintf(p, end - p, "retry:%d/",
+				       le32_to_cpu(ns->v1.result[i][3]));
+			p += scnprintf(p, end - p, "avg_t:%d.%03d/",
+				       le32_to_cpu(ns->v1.avg_t[i]) / 1000,
+				       le32_to_cpu(ns->v1.avg_t[i]) % 1000);
+			p += scnprintf(p, end - p, "max_t:%d.%03d]\n",
+				       le32_to_cpu(ns->v1.max_t[i]) / 1000,
+				       le32_to_cpu(ns->v1.max_t[i]) % 1000);
 		}
 	} else if (ver->fcxnullsta == 7) {
 		for (i = 0; i < 2; i++) {
-			seq_printf(m, " %-15s : ", "[NULL-STA]");
-			seq_printf(m, "null-%d", i);
-			seq_printf(m, "[Tx:%d/",
-				   le32_to_cpu(ns->v7.result[i][4]));
-			seq_printf(m, "[ok:%d/",
-				   le32_to_cpu(ns->v7.result[i][1]));
-			seq_printf(m, "fail:%d/",
-				   le32_to_cpu(ns->v7.result[i][0]));
-			seq_printf(m, "on_time:%d/",
-				   le32_to_cpu(ns->v7.result[i][2]));
-			seq_printf(m, "retry:%d/",
-				   le32_to_cpu(ns->v7.result[i][3]));
-			seq_printf(m, "avg_t:%d.%03d/",
-				   le32_to_cpu(ns->v7.tavg[i]) / 1000,
-				   le32_to_cpu(ns->v7.tavg[i]) % 1000);
-			seq_printf(m, "max_t:%d.%03d]\n",
-				   le32_to_cpu(ns->v7.tmax[i]) / 1000,
-				   le32_to_cpu(ns->v7.tmax[i]) % 1000);
+			p += scnprintf(p, end - p, " %-15s : ", "[NULL-STA]");
+			p += scnprintf(p, end - p, "null-%d", i);
+			p += scnprintf(p, end - p, "[Tx:%d/",
+				       le32_to_cpu(ns->v7.result[i][4]));
+			p += scnprintf(p, end - p, "[ok:%d/",
+				       le32_to_cpu(ns->v7.result[i][1]));
+			p += scnprintf(p, end - p, "fail:%d/",
+				       le32_to_cpu(ns->v7.result[i][0]));
+			p += scnprintf(p, end - p, "on_time:%d/",
+				       le32_to_cpu(ns->v7.result[i][2]));
+			p += scnprintf(p, end - p, "retry:%d/",
+				       le32_to_cpu(ns->v7.result[i][3]));
+			p += scnprintf(p, end - p, "avg_t:%d.%03d/",
+				       le32_to_cpu(ns->v7.tavg[i]) / 1000,
+				       le32_to_cpu(ns->v7.tavg[i]) % 1000);
+			p += scnprintf(p, end - p, "max_t:%d.%03d]\n",
+				       le32_to_cpu(ns->v7.tmax[i]) / 1000,
+				       le32_to_cpu(ns->v7.tmax[i]) % 1000);
 		}
 	} else {
 		for (i = 0; i < 2; i++) {
-			seq_printf(m, " %-15s : ", "[NULL-STA]");
-			seq_printf(m, "null-%d", i);
-			seq_printf(m, "[Tx:%d/",
-				   le32_to_cpu(ns->v2.result[i][4]));
-			seq_printf(m, "[ok:%d/",
-				   le32_to_cpu(ns->v2.result[i][1]));
-			seq_printf(m, "fail:%d/",
-				   le32_to_cpu(ns->v2.result[i][0]));
-			seq_printf(m, "on_time:%d/",
-				   le32_to_cpu(ns->v2.result[i][2]));
-			seq_printf(m, "retry:%d/",
-				   le32_to_cpu(ns->v2.result[i][3]));
-			seq_printf(m, "avg_t:%d.%03d/",
-				   le32_to_cpu(ns->v2.avg_t[i]) / 1000,
-				   le32_to_cpu(ns->v2.avg_t[i]) % 1000);
-			seq_printf(m, "max_t:%d.%03d]\n",
-				   le32_to_cpu(ns->v2.max_t[i]) / 1000,
-				   le32_to_cpu(ns->v2.max_t[i]) % 1000);
+			p += scnprintf(p, end - p, " %-15s : ", "[NULL-STA]");
+			p += scnprintf(p, end - p, "null-%d", i);
+			p += scnprintf(p, end - p, "[Tx:%d/",
+				       le32_to_cpu(ns->v2.result[i][4]));
+			p += scnprintf(p, end - p, "[ok:%d/",
+				       le32_to_cpu(ns->v2.result[i][1]));
+			p += scnprintf(p, end - p, "fail:%d/",
+				       le32_to_cpu(ns->v2.result[i][0]));
+			p += scnprintf(p, end - p, "on_time:%d/",
+				       le32_to_cpu(ns->v2.result[i][2]));
+			p += scnprintf(p, end - p, "retry:%d/",
+				       le32_to_cpu(ns->v2.result[i][3]));
+			p += scnprintf(p, end - p, "avg_t:%d.%03d/",
+				       le32_to_cpu(ns->v2.avg_t[i]) / 1000,
+				       le32_to_cpu(ns->v2.avg_t[i]) % 1000);
+			p += scnprintf(p, end - p, "max_t:%d.%03d]\n",
+				       le32_to_cpu(ns->v2.max_t[i]) / 1000,
+				       le32_to_cpu(ns->v2.max_t[i]) % 1000);
 		}
 	}
+
+	return p - buf;
 }
 
-static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_step_v2(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
 	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
 	struct rtw89_btc_fbtc_steps_v2 *pstep = NULL;
 	const struct rtw89_btc_ver *ver = btc->ver;
+	char *p = buf, *end = buf + bufsz;
 	u8 type, val, cnt = 0, state = 0;
 	bool outloop = false;
 	u16 i, diff_t, n_start = 0, n_stop = 0;
@@ -9838,14 +9943,14 @@ static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 
 	pcinfo = &pfwinfo->rpt_fbtc_step.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pstep = &pfwinfo->rpt_fbtc_step.finfo.v2;
 	pos_old = le16_to_cpu(pstep->pos_old);
 	pos_new = le16_to_cpu(pstep->pos_new);
 
 	if (pcinfo->req_fver != pstep->fver)
-		return;
+		return 0;
 
 	/* store step info by using ring instead of FIFO*/
 	do {
@@ -9874,13 +9979,15 @@ static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 					continue;
 
 				if (cnt % 10 == 0)
-					seq_printf(m, " %-15s : ", "[steps]");
+					p += scnprintf(p, end - p,
+						       " %-15s : ", "[steps]");
 
-				seq_printf(m, "-> %s(%02d)(%02d)",
-					   (type == CXSTEP_SLOT ? "SLT" :
-					    "EVT"), (u32)val, diff_t);
+				p += scnprintf(p, end - p,
+					       "-> %s(%02d)(%02d)",
+					       (type == CXSTEP_SLOT ? "SLT" :
+						"EVT"), (u32)val, diff_t);
 				if (cnt % 10 == 9)
-					seq_puts(m, "\n");
+					p += scnprintf(p, end - p, "\n");
 				cnt++;
 			}
 
@@ -9897,29 +10004,32 @@ static void _show_fbtc_step_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 			break;
 		}
 	} while (!outloop);
+
+	return p - buf;
 }
 
-static void _show_fbtc_step_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fbtc_step_v3(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
 	struct rtw89_btc_rpt_cmn_info *pcinfo;
 	struct rtw89_btc_fbtc_steps_v3 *pstep;
 	u32 i, n_begin, n_end, array_idx, cnt = 0;
+	char *p = buf, *end = buf + bufsz;
 	u8 type, val;
 	u16 diff_t;
 
 	if ((pfwinfo->rpt_en_map &
 	     rtw89_btc_fw_rpt_ver(rtwdev, RPT_EN_FW_STEP_INFO)) == 0)
-		return;
+		return 0;
 
 	pcinfo = &pfwinfo->rpt_fbtc_step.cinfo;
 	if (!pcinfo->valid)
-		return;
+		return 0;
 
 	pstep = &pfwinfo->rpt_fbtc_step.finfo.v3;
 	if (pcinfo->req_fver != pstep->fver)
-		return;
+		return 0;
 
 	if (le32_to_cpu(pstep->cnt) <= FCXDEF_STEP)
 		n_begin = 1;
@@ -9929,7 +10039,7 @@ static void _show_fbtc_step_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
 	n_end = le32_to_cpu(pstep->cnt);
 
 	if (n_begin > n_end)
-		return;
+		return 0;
 
 	/* restore step info by using ring instead of FIFO */
 	for (i = n_begin; i <= n_end; i++) {
@@ -9942,50 +10052,55 @@ static void _show_fbtc_step_v3(struct rtw89_dev *rtwdev, struct seq_file *m)
 			continue;
 
 		if (cnt % 10 == 0)
-			seq_printf(m, " %-15s : ", "[steps]");
+			p += scnprintf(p, end - p, " %-15s : ", "[steps]");
 
-		seq_printf(m, "-> %s(%02d)",
-			   (type == CXSTEP_SLOT ?
-			    id_to_slot((u32)val) :
-			    id_to_evt((u32)val)), diff_t);
+		p += scnprintf(p, end - p, "-> %s(%02d)",
+			       (type == CXSTEP_SLOT ?
+				id_to_slot((u32)val) :
+				id_to_evt((u32)val)), diff_t);
 
 		if (cnt % 10 == 9)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 
 		cnt++;
 	}
+
+	return p - buf;
 }
 
-static void _show_fw_dm_msg(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_fw_dm_msg(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
+	char *p = buf, *end = buf + bufsz;
 
 	if (!(btc->dm.coex_info_map & BTC_COEX_INFO_DM))
-		return;
+		goto out;
 
-	_show_error(rtwdev, m);
-	_show_fbtc_tdma(rtwdev, m);
-	_show_fbtc_slots(rtwdev, m);
+	p += _show_error(rtwdev, p, end - p);
+	p += _show_fbtc_tdma(rtwdev, p, end - p);
+	p += _show_fbtc_slots(rtwdev, p, end - p);
 
 	if (ver->fcxcysta == 2)
-		_show_fbtc_cysta_v2(rtwdev, m);
+		p += _show_fbtc_cysta_v2(rtwdev, p, end - p);
 	else if (ver->fcxcysta == 3)
-		_show_fbtc_cysta_v3(rtwdev, m);
+		p += _show_fbtc_cysta_v3(rtwdev, p, end - p);
 	else if (ver->fcxcysta == 4)
-		_show_fbtc_cysta_v4(rtwdev, m);
+		p += _show_fbtc_cysta_v4(rtwdev, p, end - p);
 	else if (ver->fcxcysta == 5)
-		_show_fbtc_cysta_v5(rtwdev, m);
+		p += _show_fbtc_cysta_v5(rtwdev, p, end - p);
 	else if (ver->fcxcysta == 7)
-		_show_fbtc_cysta_v7(rtwdev, m);
+		p += _show_fbtc_cysta_v7(rtwdev, p, end - p);
 
-	_show_fbtc_nullsta(rtwdev, m);
+	p += _show_fbtc_nullsta(rtwdev, p, end - p);
 
 	if (ver->fcxstep == 2)
-		_show_fbtc_step_v2(rtwdev, m);
+		p += _show_fbtc_step_v2(rtwdev, p, end - p);
 	else if (ver->fcxstep == 3)
-		_show_fbtc_step_v3(rtwdev, m);
+		p += _show_fbtc_step_v3(rtwdev, p, end - p);
 
+out:
+	return p - buf;
 }
 
 static void _get_gnt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_coex_gnt *gnt_cfg)
@@ -10030,12 +10145,13 @@ static void _get_gnt(struct rtw89_dev *rtwdev, struct rtw89_mac_ax_coex_gnt *gnt
 	}
 }
 
-static void _show_gpio_dbg(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_gpio_dbg(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &rtwdev->btc.fwinfo;
 	const struct rtw89_btc_ver *ver = rtwdev->btc.ver;
 	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
 	union rtw89_btc_fbtc_gpio_dbg *gdbg = NULL;
+	char *p = buf, *end = buf + bufsz;
 	u8 *gpio_map, i;
 	u32 en_map;
 
@@ -10045,8 +10161,8 @@ static void _show_gpio_dbg(struct rtw89_dev *rtwdev, struct seq_file *m)
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
 			    "[BTC], %s(): stop due rpt_fbtc_gpio_dbg.cinfo\n",
 			    __func__);
-		seq_puts(m, "\n");
-		return;
+		p += scnprintf(p, end - p, "\n");
+		goto out;
 	}
 
 	if (ver->fcxgpiodbg == 7) {
@@ -10058,20 +10174,24 @@ static void _show_gpio_dbg(struct rtw89_dev *rtwdev, struct seq_file *m)
 	}
 
 	if (!en_map)
-		return;
+		goto out;
 
-	seq_printf(m, " %-15s : enable_map:0x%08x",
-		   "[gpio_dbg]", en_map);
+	p += scnprintf(p, end - p, " %-15s : enable_map:0x%08x",
+		       "[gpio_dbg]", en_map);
 
 	for (i = 0; i < BTC_DBG_MAX1; i++) {
 		if (!(en_map & BIT(i)))
 			continue;
-		seq_printf(m, ", %s->GPIO%d", id_to_gdbg(i), gpio_map[i]);
+		p += scnprintf(p, end - p, ", %s->GPIO%d", id_to_gdbg(i),
+			       gpio_map[i]);
 	}
-	seq_puts(m, "\n");
+	p += scnprintf(p, end - p, "\n");
+
+out:
+	return p - buf;
 }
 
-static void _show_mreg_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_mreg_v1(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_btc *btc = &rtwdev->btc;
@@ -10083,45 +10203,47 @@ static void _show_mreg_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	struct rtw89_mac_ax_coex_gnt gnt_cfg = {};
 	struct rtw89_mac_ax_gnt gnt;
+	char *p = buf, *end = buf + bufsz;
 	u8 i = 0, type = 0, cnt = 0;
 	u32 val, offset;
 
 	if (!(btc->dm.coex_info_map & BTC_COEX_INFO_MREG))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [HW Status] ==========\n");
+	p += scnprintf(p, end - p, "========== [HW Status] ==========\n");
 
-	seq_printf(m,
-		   " %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)\n",
-		   "[scoreboard]", wl->scbd, cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
-		   bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
-		   cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
+	p += scnprintf(p, end - p,
+		       " %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)\n",
+		       "[scoreboard]", wl->scbd,
+		       cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
+		       bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
+		       cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
 
 	btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
 	_get_gnt(rtwdev, &gnt_cfg);
 
 	gnt = gnt_cfg.band[0];
-	seq_printf(m,
-		   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
-		   "[gnt_status]",
-		   chip->chip_id == RTL8852C ? "HW" :
-		   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
-		   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
-		   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
+	p += scnprintf(p, end - p,
+		       " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], ",
+		       "[gnt_status]",
+		       chip->chip_id == RTL8852C ? "HW" :
+		       btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
+		       gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
+		       gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt);
 
 	gnt = gnt_cfg.band[1];
-	seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
-		   gnt.gnt_wl_sw_en ? "SW" : "HW",
-		   gnt.gnt_wl,
-		   gnt.gnt_bt_sw_en ? "SW" : "HW",
-		   gnt.gnt_bt);
+	p += scnprintf(p, end - p, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
+		       gnt.gnt_wl_sw_en ? "SW" : "HW",
+		       gnt.gnt_wl,
+		       gnt.gnt_bt_sw_en ? "SW" : "HW",
+		       gnt.gnt_bt);
 
 	pcinfo = &pfwinfo->rpt_fbtc_mregval.cinfo;
 	if (!pcinfo->valid) {
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
 			    "[BTC], %s(): stop due rpt_fbtc_mregval.cinfo\n",
 			    __func__);
-		return;
+		goto out;
 	}
 
 	pmreg = &pfwinfo->rpt_fbtc_mregval.finfo.v1;
@@ -10135,21 +10257,26 @@ static void _show_mreg_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
 		val = le32_to_cpu(pmreg->mreg_val[i]);
 
 		if (cnt % 6 == 0)
-			seq_printf(m, " %-15s : %d_0x%04x=0x%08x",
-				   "[reg]", (u32)type, offset, val);
+			p += scnprintf(p, end - p,
+				       " %-15s : %d_0x%04x=0x%08x",
+				       "[reg]", (u32)type, offset, val);
 		else
-			seq_printf(m, ", %d_0x%04x=0x%08x", (u32)type,
-				   offset, val);
+			p += scnprintf(p, end - p, ", %d_0x%04x=0x%08x",
+				       (u32)type,
+				       offset, val);
 		if (cnt % 6 == 5)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 		cnt++;
 
 		if (i >= pmreg->reg_num)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_mreg_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_mreg_v2(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_btc *btc = &rtwdev->btc;
@@ -10161,46 +10288,48 @@ static void _show_mreg_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_bt_info *bt = &btc->cx.bt;
 	struct rtw89_mac_ax_coex_gnt gnt_cfg = {};
 	struct rtw89_mac_ax_gnt gnt;
+	char *p = buf, *end = buf + bufsz;
 	u8 i = 0, type = 0, cnt = 0;
 	u32 val, offset;
 
 	if (!(btc->dm.coex_info_map & BTC_COEX_INFO_MREG))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [HW Status] ==========\n");
+	p += scnprintf(p, end - p, "========== [HW Status] ==========\n");
 
-	seq_printf(m,
-		   " %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)\n",
-		   "[scoreboard]", wl->scbd, cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
-		   bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
-		   cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
+	p += scnprintf(p, end - p,
+		       " %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)\n",
+		       "[scoreboard]", wl->scbd,
+		       cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
+		       bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
+		       cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
 
 	btc->dm.pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
 	_get_gnt(rtwdev, &gnt_cfg);
 
 	gnt = gnt_cfg.band[0];
-	seq_printf(m,
-		   " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], polut_type:%s",
-		   "[gnt_status]",
-		   chip->chip_id == RTL8852C ? "HW" :
-		   btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
-		   gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
-		   gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt,
-		   id_to_polut(wl->bt_polut_type[wl->pta_req_mac]));
+	p += scnprintf(p, end - p,
+		       " %-15s : pta_owner:%s, phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d], polut_type:%s",
+		       "[gnt_status]",
+		       chip->chip_id == RTL8852C ? "HW" :
+		       btc->dm.pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
+		       gnt.gnt_wl_sw_en ? "SW" : "HW", gnt.gnt_wl,
+		       gnt.gnt_bt_sw_en ? "SW" : "HW", gnt.gnt_bt,
+		       id_to_polut(wl->bt_polut_type[wl->pta_req_mac]));
 
 	gnt = gnt_cfg.band[1];
-	seq_printf(m, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
-		   gnt.gnt_wl_sw_en ? "SW" : "HW",
-		   gnt.gnt_wl,
-		   gnt.gnt_bt_sw_en ? "SW" : "HW",
-		   gnt.gnt_bt);
+	p += scnprintf(p, end - p, "phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]\n",
+		       gnt.gnt_wl_sw_en ? "SW" : "HW",
+		       gnt.gnt_wl,
+		       gnt.gnt_bt_sw_en ? "SW" : "HW",
+		       gnt.gnt_bt);
 
 	pcinfo = &pfwinfo->rpt_fbtc_mregval.cinfo;
 	if (!pcinfo->valid) {
 		rtw89_debug(rtwdev, RTW89_DBG_BTC,
 			    "[BTC], %s(): stop due rpt_fbtc_mregval.cinfo\n",
 			    __func__);
-		return;
+		goto out;
 	}
 
 	pmreg = &pfwinfo->rpt_fbtc_mregval.finfo.v2;
@@ -10214,21 +10343,26 @@ static void _show_mreg_v2(struct rtw89_dev *rtwdev, struct seq_file *m)
 		val = le32_to_cpu(pmreg->mreg_val[i]);
 
 		if (cnt % 6 == 0)
-			seq_printf(m, " %-15s : %d_0x%04x=0x%08x",
-				   "[reg]", (u32)type, offset, val);
+			p += scnprintf(p, end - p,
+				       " %-15s : %d_0x%04x=0x%08x",
+				       "[reg]", (u32)type, offset, val);
 		else
-			seq_printf(m, ", %d_0x%04x=0x%08x", (u32)type,
-				   offset, val);
+			p += scnprintf(p, end - p, ", %d_0x%04x=0x%08x",
+				       (u32)type,
+				       offset, val);
 		if (cnt % 6 == 5)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 		cnt++;
 
 		if (i >= pmreg->reg_num)
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 	}
+
+out:
+	return p - buf;
 }
 
-static void _show_mreg_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_mreg_v7(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -10239,46 +10373,50 @@ static void _show_mreg_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_bt_info *bt = &cx->bt;
 	struct rtw89_mac_ax_gnt *gnt = NULL;
 	struct rtw89_btc_dm *dm = &btc->dm;
+	char *p = buf, *end = buf + bufsz;
 	u8 i, type, cnt = 0;
 	u32 val, offset;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_MREG))
-		return;
+		return 0;
 
-	seq_puts(m, "\n\r========== [HW Status] ==========");
+	p += scnprintf(p, end - p, "\n\r========== [HW Status] ==========");
 
-	seq_printf(m,
-		   "\n\r %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)",
-		   "[scoreboard]", wl->scbd, cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
-		   bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
-		   cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : WL->BT:0x%08x(cnt:%d), BT->WL:0x%08x(total:%d, bt_update:%d)",
+		       "[scoreboard]", wl->scbd,
+		       cx->cnt_wl[BTC_WCNT_SCBDUPDATE],
+		       bt->scbd, cx->cnt_bt[BTC_BCNT_SCBDREAD],
+		       cx->cnt_bt[BTC_BCNT_SCBDUPDATE]);
 
 	/* To avoid I/O if WL LPS or power-off  */
 	dm->pta_owner = rtw89_mac_get_ctrl_path(rtwdev);
 
-	seq_printf(m,
-		   "\n\r %-15s : pta_owner:%s, pta_req_mac:MAC%d, rf_gnt_source: polut_type:%s",
-		   "[gnt_status]",
-		   rtwdev->chip->para_ver & BTC_FEAT_PTA_ONOFF_CTRL ? "HW" :
-		   dm->pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
-		   wl->pta_req_mac, id_to_polut(wl->bt_polut_type[wl->pta_req_mac]));
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : pta_owner:%s, pta_req_mac:MAC%d, rf_gnt_source: polut_type:%s",
+		       "[gnt_status]",
+		       rtwdev->chip->para_ver & BTC_FEAT_PTA_ONOFF_CTRL ? "HW" :
+		       dm->pta_owner == BTC_CTRL_BY_WL ? "WL" : "BT",
+		       wl->pta_req_mac,
+		       id_to_polut(wl->bt_polut_type[wl->pta_req_mac]));
 
 	gnt = &dm->gnt.band[RTW89_PHY_0];
 
-	seq_printf(m, ", phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d]",
-		   gnt->gnt_wl_sw_en ? "SW" : "HW", gnt->gnt_wl,
-		   gnt->gnt_bt_sw_en ? "SW" : "HW", gnt->gnt_bt);
+	p += scnprintf(p, end - p, ", phy-0[gnt_wl:%s-%d/gnt_bt:%s-%d]",
+		       gnt->gnt_wl_sw_en ? "SW" : "HW", gnt->gnt_wl,
+		       gnt->gnt_bt_sw_en ? "SW" : "HW", gnt->gnt_bt);
 
 	if (rtwdev->dbcc_en) {
 		gnt = &dm->gnt.band[RTW89_PHY_1];
-		seq_printf(m, ", phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]",
-			   gnt->gnt_wl_sw_en ? "SW" : "HW", gnt->gnt_wl,
-			   gnt->gnt_bt_sw_en ? "SW" : "HW", gnt->gnt_bt);
+		p += scnprintf(p, end - p,
+			       ", phy-1[gnt_wl:%s-%d/gnt_bt:%s-%d]",
+			       gnt->gnt_wl_sw_en ? "SW" : "HW", gnt->gnt_wl,
+			       gnt->gnt_bt_sw_en ? "SW" : "HW", gnt->gnt_bt);
 	}
 
 	pcinfo = &pfwinfo->rpt_fbtc_mregval.cinfo;
 	if (!pcinfo->valid)
-		return;
+		goto out;
 
 	pmreg = &pfwinfo->rpt_fbtc_mregval.finfo.v7;
 
@@ -10288,17 +10426,21 @@ static void _show_mreg_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 		val = le32_to_cpu(pmreg->mreg_val[i]);
 
 		if (cnt % 6 == 0)
-			seq_printf(m, "\n\r %-15s : %s_0x%x=0x%x", "[reg]",
-				   id_to_regtype(type), offset, val);
+			p += scnprintf(p, end - p,
+				       "\n\r %-15s : %s_0x%x=0x%x", "[reg]",
+				       id_to_regtype(type), offset, val);
 		else
-			seq_printf(m, ", %s_0x%x=0x%x",
-				   id_to_regtype(type), offset, val);
+			p += scnprintf(p, end - p, ", %s_0x%x=0x%x",
+				       id_to_regtype(type), offset, val);
 		cnt++;
 	}
-	seq_puts(m, "\n");
+	p += scnprintf(p, end - p, "\n");
+
+out:
+	return p - buf;
 }
 
-static void _show_summary_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v1(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -10309,56 +10451,59 @@ static void _show_summary_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	struct rtw89_btc_bt_info *bt = &cx->bt;
 	u32 cnt_sum = 0, *cnt = btc->dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [Statistics] ==========\n");
+	p += scnprintf(p, end - p, "========== [Statistics] ==========\n");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && !wl->status.map.lps && !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v1;
 
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d), ",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail, prptctrl->h2c_cnt,
-			   pfwinfo->cnt_c2h, prptctrl->c2h_cnt);
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail, prptctrl->h2c_cnt,
+			       pfwinfo->cnt_c2h, prptctrl->c2h_cnt);
 
-		seq_printf(m,
-			   "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x, dm_error_map:0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT], prptctrl->rpt_cnt,
-			   prptctrl->rpt_enable, dm->error.val);
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x, dm_error_map:0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       prptctrl->rpt_cnt,
+			       prptctrl->rpt_enable, dm->error.val);
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : send_ok:%d, send_fail:%d, recv:%d",
-			   "[mailbox]", prptctrl->mb_send_ok_cnt,
-			   prptctrl->mb_send_fail_cnt, prptctrl->mb_recv_cnt);
-
-		seq_printf(m,
-			   "(A2DP_empty:%d, A2DP_flowstop:%d, A2DP_full:%d)\n",
-			   prptctrl->mb_a2dp_empty_cnt,
-			   prptctrl->mb_a2dp_flct_cnt,
-			   prptctrl->mb_a2dp_full_cnt);
-
-		seq_printf(m,
-			   " %-15s : wl_rfk[req:%d/go:%d/reject:%d/timeout:%d]",
-			   "[RFK]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
-
-		seq_printf(m,
-			   ", bt_rfk[req:%d/go:%d/reject:%d/timeout:%d/fail:%d]\n",
-			   prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_REQ],
-			   prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_GO],
-			   prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_REJECT],
-			   prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_TIMEOUT],
-			   prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_FAIL]);
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : send_ok:%d, send_fail:%d, recv:%d",
+			       "[mailbox]", prptctrl->mb_send_ok_cnt,
+			       prptctrl->mb_send_fail_cnt,
+			       prptctrl->mb_recv_cnt);
+
+		p += scnprintf(p, end - p,
+			       "(A2DP_empty:%d, A2DP_flowstop:%d, A2DP_full:%d)\n",
+			       prptctrl->mb_a2dp_empty_cnt,
+			       prptctrl->mb_a2dp_flct_cnt,
+			       prptctrl->mb_a2dp_full_cnt);
+
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rfk[req:%d/go:%d/reject:%d/timeout:%d]",
+			       "[RFK]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
+
+		p += scnprintf(p, end - p,
+			       ", bt_rfk[req:%d/go:%d/reject:%d/timeout:%d/fail:%d]\n",
+			       prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_REQ],
+			       prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_GO],
+			       prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_REJECT],
+			       prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_TIMEOUT],
+			       prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_FAIL]);
 
 		if (prptctrl->bt_rfk_cnt[BTC_BCNT_RFK_TIMEOUT] > 0)
 			bt->rfk_info.map.timeout = 1;
@@ -10367,42 +10512,44 @@ static void _show_summary_v1(struct rtw89_dev *rtwdev, struct seq_file *m)
 
 		dm->error.map.wl_rfk_timeout = bt->rfk_info.map.timeout;
 	} else {
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d, rpt_cnt=%d, rpt_map=0x%x",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h,
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   btc->fwinfo.rpt_en_map);
-		seq_puts(m, " (WL FW report invalid!!)\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d, rpt_cnt=%d, rpt_map=0x%x",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h,
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       btc->fwinfo.rpt_en_map);
+		p += scnprintf(p, end - p, " (WL FW report invalid!!)\n");
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_printf(m,
-		   " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]", cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p,
+		       " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]", cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d\n",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d\n",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
+		       "[notify_cnt]", cnt[BTC_NCNT_SCAN_START],
+		       cnt[BTC_NCNT_SCAN_FINISH], cnt[BTC_NCNT_SWITCH_BAND],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m,
-		   " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
-		   "[notify_cnt]", cnt[BTC_NCNT_SCAN_START],
-		   cnt[BTC_NCNT_SCAN_FINISH], cnt[BTC_NCNT_SWITCH_BAND],
-		   cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, control=%d, customerize=%d\n",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
+		       cnt[BTC_NCNT_CUSTOMERIZE]);
 
-	seq_printf(m,
-		   "timer=%d, control=%d, customerize=%d\n",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
-		   cnt[BTC_NCNT_CUSTOMERIZE]);
+	return p - buf;
 }
 
-static void _show_summary_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v4(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -10413,64 +10560,65 @@ static void _show_summary_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	struct rtw89_btc_bt_info *bt = &cx->bt;
 	u32 cnt_sum = 0, *cnt = btc->dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [Statistics] ==========\n");
+	p += scnprintf(p, end - p, "========== [Statistics] ==========\n");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && !wl->status.map.lps && !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v4;
 
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d), ",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail,
-			   le32_to_cpu(prptctrl->rpt_info.cnt_h2c),
-			   pfwinfo->cnt_c2h,
-			   le32_to_cpu(prptctrl->rpt_info.cnt_c2h));
-
-		seq_printf(m,
-			   "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x, dm_error_map:0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   le32_to_cpu(prptctrl->rpt_info.cnt),
-			   le32_to_cpu(prptctrl->rpt_info.en),
-			   dm->error.val);
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail,
+			       le32_to_cpu(prptctrl->rpt_info.cnt_h2c),
+			       pfwinfo->cnt_c2h,
+			       le32_to_cpu(prptctrl->rpt_info.cnt_c2h));
+
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x, dm_error_map:0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       le32_to_cpu(prptctrl->rpt_info.cnt),
+			       le32_to_cpu(prptctrl->rpt_info.en),
+			       dm->error.val);
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
-			   "[mailbox]",
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
-
-		seq_printf(m,
-			   "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
-
-		seq_printf(m,
-			   " %-15s : wl_rfk[req:%d/go:%d/reject:%d/timeout:%d]",
-			   "[RFK]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
-
-		seq_printf(m,
-			   ", bt_rfk[req:%d/go:%d/reject:%d/timeout:%d/fail:%d]\n",
-			   le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]),
-			   le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_GO]),
-			   le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REJECT]),
-			   le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_TIMEOUT]),
-			   le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_FAIL]));
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			       "[mailbox]",
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		p += scnprintf(p, end - p,
+			       "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rfk[req:%d/go:%d/reject:%d/timeout:%d]",
+			       "[RFK]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
+
+		p += scnprintf(p, end - p,
+			       ", bt_rfk[req:%d/go:%d/reject:%d/timeout:%d/fail:%d]\n",
+			       le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]),
+			       le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_GO]),
+			       le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REJECT]),
+			       le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_TIMEOUT]),
+			       le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_FAIL]));
 
 		if (le32_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_TIMEOUT]) > 0)
 			bt->rfk_info.map.timeout = 1;
@@ -10479,42 +10627,44 @@ static void _show_summary_v4(struct rtw89_dev *rtwdev, struct seq_file *m)
 
 		dm->error.map.wl_rfk_timeout = bt->rfk_info.map.timeout;
 	} else {
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d, rpt_cnt=%d, rpt_map=0x%x",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h,
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   btc->fwinfo.rpt_en_map);
-		seq_puts(m, " (WL FW report invalid!!)\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d, rpt_cnt=%d, rpt_map=0x%x",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h,
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       btc->fwinfo.rpt_en_map);
+		p += scnprintf(p, end - p, " (WL FW report invalid!!)\n");
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_printf(m,
-		   " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]", cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p,
+		       " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]", cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d\n",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d\n",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_printf(m,
-		   " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
-		   "[notify_cnt]", cnt[BTC_NCNT_SCAN_START],
-		   cnt[BTC_NCNT_SCAN_FINISH], cnt[BTC_NCNT_SWITCH_BAND],
-		   cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p,
+		       " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
+		       "[notify_cnt]", cnt[BTC_NCNT_SCAN_START],
+		       cnt[BTC_NCNT_SCAN_FINISH], cnt[BTC_NCNT_SWITCH_BAND],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m,
-		   "timer=%d, control=%d, customerize=%d\n",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
-		   cnt[BTC_NCNT_CUSTOMERIZE]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, control=%d, customerize=%d\n",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
+		       cnt[BTC_NCNT_CUSTOMERIZE]);
+
+	return p - buf;
 }
 
-static void _show_summary_v5(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v5(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -10524,112 +10674,118 @@ static void _show_summary_v5(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_dm *dm = &btc->dm;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	u32 cnt_sum = 0, *cnt = btc->dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [Statistics] ==========\n");
+	p += scnprintf(p, end - p, "========== [Statistics] ==========\n");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && !wl->status.map.lps && !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v5;
 
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d), ",
-			   "[summary]", pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
-			   pfwinfo->cnt_c2h,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
-			   le16_to_cpu(prptctrl->rpt_info.len_c2h));
-
-		seq_printf(m,
-			   "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   le16_to_cpu(prptctrl->rpt_info.cnt),
-			   le32_to_cpu(prptctrl->rpt_info.en));
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
+			       pfwinfo->cnt_c2h,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
+			       le16_to_cpu(prptctrl->rpt_info.len_c2h));
+
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       le16_to_cpu(prptctrl->rpt_info.cnt),
+			       le32_to_cpu(prptctrl->rpt_info.en));
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
-			   "[mailbox]",
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
-
-		seq_printf(m,
-			   "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
-
-		seq_printf(m,
-			   " %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d]",
-			   "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
-
-		seq_printf(m,
-			   ", bt_rfk[req:%d]",
-			   le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
-
-		seq_printf(m,
-			   ", AOAC[RF_on:%d/RF_off:%d]",
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			       "[mailbox]",
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		p += scnprintf(p, end - p,
+			       "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d]",
+			       "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
+
+		p += scnprintf(p, end - p,
+			       ", bt_rfk[req:%d]",
+			       le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
+
+		p += scnprintf(p, end - p,
+			       ", AOAC[RF_on:%d/RF_off:%d]",
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
 	} else {
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h);
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h);
 	}
 
 	if (!pcinfo->valid || pfwinfo->len_mismch || pfwinfo->fver_mismch ||
 	    pfwinfo->err[BTFRE_EXCEPTION]) {
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : WL FW rpt error!![rpt_ctrl_valid:%d/len:"
-			   "0x%x/ver:0x%x/ex:%d/lps=%d/rf_off=%d]",
-			   "[ERROR]", pcinfo->valid, pfwinfo->len_mismch,
-			   pfwinfo->fver_mismch, pfwinfo->err[BTFRE_EXCEPTION],
-			   wl->status.map.lps, wl->status.map.rf_off);
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : WL FW rpt error!![rpt_ctrl_valid:%d/len:"
+			       "0x%x/ver:0x%x/ex:%d/lps=%d/rf_off=%d]",
+			       "[ERROR]", pcinfo->valid, pfwinfo->len_mismch,
+			       pfwinfo->fver_mismch,
+			       pfwinfo->err[BTFRE_EXCEPTION],
+			       wl->status.map.lps, wl->status.map.rf_off);
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_puts(m, "\n");
-	seq_printf(m,
-		   " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]",
-		   cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p, "\n");
+	p += scnprintf(p, end - p,
+		       " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]",
+		       cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_puts(m, "\n");
-	seq_printf(m,
-		   " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
-		   "[notify_cnt]",
-		   cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
-		   cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p, "\n");
+	p += scnprintf(p, end - p,
+		       " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
+		       "[notify_cnt]",
+		       cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
+		       cnt[BTC_NCNT_SWITCH_BAND],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m,
-		   "timer=%d, control=%d, customerize=%d",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
-		   cnt[BTC_NCNT_CUSTOMERIZE]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, control=%d, customerize=%d",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
+		       cnt[BTC_NCNT_CUSTOMERIZE]);
+
+	return p - buf;
 }
 
-static void _show_summary_v105(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v105(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &btc->fwinfo;
@@ -10639,112 +10795,118 @@ static void _show_summary_v105(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_dm *dm = &btc->dm;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	u32 cnt_sum = 0, *cnt = btc->dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_puts(m, "========== [Statistics] ==========\n");
+	p += scnprintf(p, end - p, "========== [Statistics] ==========\n");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && !wl->status.map.lps && !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v105;
 
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d), ",
-			   "[summary]", pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
-			   pfwinfo->cnt_c2h,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
-			   le16_to_cpu(prptctrl->rpt_info.len_c2h));
-
-		seq_printf(m,
-			   "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   le16_to_cpu(prptctrl->rpt_info.cnt),
-			   le32_to_cpu(prptctrl->rpt_info.en));
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
+			       pfwinfo->cnt_c2h,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
+			       le16_to_cpu(prptctrl->rpt_info.len_c2h));
+
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       le16_to_cpu(prptctrl->rpt_info.cnt),
+			       le32_to_cpu(prptctrl->rpt_info.en));
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
-			   "[mailbox]",
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
-
-		seq_printf(m,
-			   "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
-
-		seq_printf(m,
-			   " %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d]",
-			   "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
-
-		seq_printf(m,
-			   ", bt_rfk[req:%d]",
-			   le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
-
-		seq_printf(m,
-			   ", AOAC[RF_on:%d/RF_off:%d]",
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			       "[mailbox]",
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		p += scnprintf(p, end - p,
+			       "A2DP_empty:%d(stop:%d, tx:%d, ack:%d, nack:%d)\n",
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		p += scnprintf(p, end - p,
+			       " %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d]",
+			       "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT]);
+
+		p += scnprintf(p, end - p,
+			       ", bt_rfk[req:%d]",
+			       le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
+
+		p += scnprintf(p, end - p,
+			       ", AOAC[RF_on:%d/RF_off:%d]",
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
 	} else {
-		seq_printf(m,
-			   " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d",
-			   "[summary]", pfwinfo->cnt_h2c,
-			   pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h);
+		p += scnprintf(p, end - p,
+			       " %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail, pfwinfo->cnt_c2h);
 	}
 
 	if (!pcinfo->valid || pfwinfo->len_mismch || pfwinfo->fver_mismch ||
 	    pfwinfo->err[BTFRE_EXCEPTION]) {
-		seq_puts(m, "\n");
-		seq_printf(m,
-			   " %-15s : WL FW rpt error!![rpt_ctrl_valid:%d/len:"
-			   "0x%x/ver:0x%x/ex:%d/lps=%d/rf_off=%d]",
-			   "[ERROR]", pcinfo->valid, pfwinfo->len_mismch,
-			   pfwinfo->fver_mismch, pfwinfo->err[BTFRE_EXCEPTION],
-			   wl->status.map.lps, wl->status.map.rf_off);
+		p += scnprintf(p, end - p, "\n");
+		p += scnprintf(p, end - p,
+			       " %-15s : WL FW rpt error!![rpt_ctrl_valid:%d/len:"
+			       "0x%x/ver:0x%x/ex:%d/lps=%d/rf_off=%d]",
+			       "[ERROR]", pcinfo->valid, pfwinfo->len_mismch,
+			       pfwinfo->fver_mismch,
+			       pfwinfo->err[BTFRE_EXCEPTION],
+			       wl->status.map.lps, wl->status.map.rf_off);
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_puts(m, "\n");
-	seq_printf(m,
-		   " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]",
-		   cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p, "\n");
+	p += scnprintf(p, end - p,
+		       " %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]",
+		       cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_puts(m, "\n");
-	seq_printf(m,
-		   " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
-		   "[notify_cnt]",
-		   cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
-		   cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p, "\n");
+	p += scnprintf(p, end - p,
+		       " %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, special_pkt=%d, ",
+		       "[notify_cnt]",
+		       cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
+		       cnt[BTC_NCNT_SWITCH_BAND],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m,
-		   "timer=%d, control=%d, customerize=%d",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
-		   cnt[BTC_NCNT_CUSTOMERIZE]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, control=%d, customerize=%d",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CONTROL],
+		       cnt[BTC_NCNT_CUSTOMERIZE]);
+
+	return p - buf;
 }
 
-static void _show_summary_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v7(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &rtwdev->btc.fwinfo;
 	struct rtw89_btc_fbtc_rpt_ctrl_v7 *prptctrl = NULL;
@@ -10753,100 +10915,111 @@ static void _show_summary_v7(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_dm *dm = &rtwdev->btc.dm;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	u32 *cnt = rtwdev->btc.dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u32 cnt_sum = 0;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_printf(m, "%s", "\n\r========== [Statistics] ==========");
+	p += scnprintf(p, end - p, "%s",
+		       "\n\r========== [Statistics] ==========");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && wl->status.map.lps != BTC_LPS_RF_OFF &&
 	    !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v7;
 
-		seq_printf(m,
-			   "\n\r %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d),"
-			   "c2h_cnt=%d(fw_send:%d, len:%d, max:%d), ",
-			   "[summary]", pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_h2c), pfwinfo->cnt_c2h,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
-			   le16_to_cpu(prptctrl->rpt_info.len_c2h),
-			   rtwdev->btc.ver->info_buf);
-
-		seq_printf(m, "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   le16_to_cpu(prptctrl->rpt_info.cnt),
-			   le32_to_cpu(prptctrl->rpt_info.en));
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d),"
+			       "c2h_cnt=%d(fw_send:%d, len:%d, max:%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
+			       pfwinfo->cnt_c2h,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
+			       le16_to_cpu(prptctrl->rpt_info.len_c2h),
+			       rtwdev->btc.ver->info_buf);
+
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       le16_to_cpu(prptctrl->rpt_info.cnt),
+			       le32_to_cpu(prptctrl->rpt_info.en));
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-
-		seq_printf(m, "\n\r %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
-			   "[mailbox]", le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
-
-		seq_printf(m, "A2DP_empty:%d(stop:%d/tx:%d/ack:%d/nack:%d)",
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
-
-		seq_printf(m,
-			   "\n\r %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d/time:%dms]",
-			   "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT],
-			   wl->rfk_info.proc_time);
-
-		seq_printf(m, ", bt_rfk[req:%d]",
-			   le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
-
-		seq_printf(m, ", AOAC[RF_on:%d/RF_off:%d]",
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			       "[mailbox]",
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		p += scnprintf(p, end - p,
+			       "A2DP_empty:%d(stop:%d/tx:%d/ack:%d/nack:%d)",
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d/time:%dms]",
+			       "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT],
+			       wl->rfk_info.proc_time);
+
+		p += scnprintf(p, end - p, ", bt_rfk[req:%d]",
+			       le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
+
+		p += scnprintf(p, end - p, ", AOAC[RF_on:%d/RF_off:%d]",
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
 	} else {
-		seq_printf(m,
-			   "\n\r %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d (lps=%d/rf_off=%d)",
-			   "[summary]",
-			   pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   pfwinfo->cnt_c2h,
-			   wl->status.map.lps, wl->status.map.rf_off);
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d (lps=%d/rf_off=%d)",
+			       "[summary]",
+			       pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
+			       pfwinfo->cnt_c2h,
+			       wl->status.map.lps, wl->status.map.rf_off);
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_printf(m,
-		   "\n\r %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]",
-		   cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]",
+		       cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_printf(m,
-		   "\n\r %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, switch_chbw=%d, special_pkt=%d, ",
-		   "[notify_cnt]",
-		   cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
-		   cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SWITCH_CHBW],
-		   cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, switch_chbw=%d, special_pkt=%d, ",
+		       "[notify_cnt]",
+		       cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
+		       cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SWITCH_CHBW],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m, "timer=%d, customerize=%d, hub_msg=%d, chg_fw=%d, send_cc=%d",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CUSTOMERIZE],
-		   rtwdev->btc.hubmsg_cnt, cnt[BTC_NCNT_RESUME_DL_FW],
-		   cnt[BTC_NCNT_COUNTRYCODE]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, customerize=%d, hub_msg=%d, chg_fw=%d, send_cc=%d",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CUSTOMERIZE],
+		       rtwdev->btc.hubmsg_cnt, cnt[BTC_NCNT_RESUME_DL_FW],
+		       cnt[BTC_NCNT_COUNTRYCODE]);
+
+	return p - buf;
 }
 
-static void _show_summary_v8(struct rtw89_dev *rtwdev, struct seq_file *m)
+static int _show_summary_v8(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_btc_btf_fwinfo *pfwinfo = &rtwdev->btc.fwinfo;
 	struct rtw89_btc_rpt_cmn_info *pcinfo = NULL;
@@ -10855,153 +11028,173 @@ static void _show_summary_v8(struct rtw89_dev *rtwdev, struct seq_file *m)
 	struct rtw89_btc_dm *dm = &rtwdev->btc.dm;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 	u32 *cnt = rtwdev->btc.dm.cnt_notify;
+	char *p = buf, *end = buf + bufsz;
 	u32 cnt_sum = 0;
 	u8 i;
 
 	if (!(dm->coex_info_map & BTC_COEX_INFO_SUMMARY))
-		return;
+		return 0;
 
-	seq_printf(m, "%s", "\n\r========== [Statistics] ==========");
+	p += scnprintf(p, end - p, "%s",
+		       "\n\r========== [Statistics] ==========");
 
 	pcinfo = &pfwinfo->rpt_ctrl.cinfo;
 	if (pcinfo->valid && wl->status.map.lps != BTC_LPS_RF_OFF &&
 	    !wl->status.map.rf_off) {
 		prptctrl = &pfwinfo->rpt_ctrl.finfo.v8;
 
-		seq_printf(m,
-			   "\n\r %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d, max:fw-%d/drv-%d), ",
-			   "[summary]", pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_h2c), pfwinfo->cnt_c2h,
-			   le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
-			   le16_to_cpu(prptctrl->rpt_info.len_c2h),
-			   (prptctrl->rpt_len_max_h << 8) + prptctrl->rpt_len_max_l,
-			   rtwdev->btc.ver->info_buf);
-
-		seq_printf(m, "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
-			   pfwinfo->event[BTF_EVNT_RPT],
-			   le16_to_cpu(prptctrl->rpt_info.cnt),
-			   le32_to_cpu(prptctrl->rpt_info.en));
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : h2c_cnt=%d(fail:%d, fw_recv:%d), c2h_cnt=%d(fw_send:%d, len:%d, max:fw-%d/drv-%d), ",
+			       "[summary]", pfwinfo->cnt_h2c,
+			       pfwinfo->cnt_h2c_fail,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_h2c),
+			       pfwinfo->cnt_c2h,
+			       le16_to_cpu(prptctrl->rpt_info.cnt_c2h),
+			       le16_to_cpu(prptctrl->rpt_info.len_c2h),
+			       (prptctrl->rpt_len_max_h << 8) + prptctrl->rpt_len_max_l,
+			       rtwdev->btc.ver->info_buf);
+
+		p += scnprintf(p, end - p,
+			       "rpt_cnt=%d(fw_send:%d), rpt_map=0x%x",
+			       pfwinfo->event[BTF_EVNT_RPT],
+			       le16_to_cpu(prptctrl->rpt_info.cnt),
+			       le32_to_cpu(prptctrl->rpt_info.en));
 
 		if (dm->error.map.wl_fw_hang)
-			seq_puts(m, " (WL FW Hang!!)");
-
-		seq_printf(m, "\n\r %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
-			   "[mailbox]", le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
-			   le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
-
-		seq_printf(m, "A2DP_empty:%d(stop:%d/tx:%d/ack:%d/nack:%d)",
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
-			   le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
-
-		seq_printf(m,
-			   "\n\r %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d/time:%dms]",
-			   "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
-			   cx->cnt_wl[BTC_WCNT_RFK_GO],
-			   cx->cnt_wl[BTC_WCNT_RFK_REJECT],
-			   cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT],
-			   wl->rfk_info.proc_time);
-
-		seq_printf(m, ", bt_rfk[req:%d]",
-			   le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
-
-		seq_printf(m, ", AOAC[RF_on:%d/RF_off:%d]",
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
-			   le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
+			p += scnprintf(p, end - p, " (WL FW Hang!!)");
+
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : send_ok:%d, send_fail:%d, recv:%d, ",
+			       "[mailbox]",
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_ok),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_send_fail),
+			       le32_to_cpu(prptctrl->bt_mbx_info.cnt_recv));
+
+		p += scnprintf(p, end - p,
+			       "A2DP_empty:%d(stop:%d/tx:%d/ack:%d/nack:%d)",
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_empty),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_flowctrl),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_tx),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_ack),
+			       le32_to_cpu(prptctrl->bt_mbx_info.a2dp.cnt_nack));
+
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : wl_rfk[req:%d/go:%d/reject:%d/tout:%d/time:%dms]",
+			       "[RFK/LPS]", cx->cnt_wl[BTC_WCNT_RFK_REQ],
+			       cx->cnt_wl[BTC_WCNT_RFK_GO],
+			       cx->cnt_wl[BTC_WCNT_RFK_REJECT],
+			       cx->cnt_wl[BTC_WCNT_RFK_TIMEOUT],
+			       wl->rfk_info.proc_time);
+
+		p += scnprintf(p, end - p, ", bt_rfk[req:%d]",
+			       le16_to_cpu(prptctrl->bt_cnt[BTC_BCNT_RFK_REQ]));
+
+		p += scnprintf(p, end - p, ", AOAC[RF_on:%d/RF_off:%d]",
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_on),
+			       le16_to_cpu(prptctrl->rpt_info.cnt_aoac_rf_off));
 	} else {
-		seq_printf(m,
-			   "\n\r %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d (lps=%d/rf_off=%d)",
-			   "[summary]",
-			   pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
-			   pfwinfo->cnt_c2h,
-			   wl->status.map.lps, wl->status.map.rf_off);
+		p += scnprintf(p, end - p,
+			       "\n\r %-15s : h2c_cnt=%d(fail:%d), c2h_cnt=%d (lps=%d/rf_off=%d)",
+			       "[summary]",
+			       pfwinfo->cnt_h2c, pfwinfo->cnt_h2c_fail,
+			       pfwinfo->cnt_c2h,
+			       wl->status.map.lps, wl->status.map.rf_off);
 	}
 
 	for (i = 0; i < BTC_NCNT_NUM; i++)
 		cnt_sum += dm->cnt_notify[i];
 
-	seq_printf(m,
-		   "\n\r %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
-		   "[notify_cnt]",
-		   cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
-		   cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : total=%d, show_coex_info=%d, power_on=%d, init_coex=%d, ",
+		       "[notify_cnt]",
+		       cnt_sum, cnt[BTC_NCNT_SHOW_COEX_INFO],
+		       cnt[BTC_NCNT_POWER_ON], cnt[BTC_NCNT_INIT_COEX]);
 
-	seq_printf(m,
-		   "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
-		   cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
-		   cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
-		   cnt[BTC_NCNT_WL_STA]);
+	p += scnprintf(p, end - p,
+		       "power_off=%d, radio_state=%d, role_info=%d, wl_rfk=%d, wl_sta=%d",
+		       cnt[BTC_NCNT_POWER_OFF], cnt[BTC_NCNT_RADIO_STATE],
+		       cnt[BTC_NCNT_ROLE_INFO], cnt[BTC_NCNT_WL_RFK],
+		       cnt[BTC_NCNT_WL_STA]);
 
-	seq_printf(m,
-		   "\n\r %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, switch_chbw=%d, special_pkt=%d, ",
-		   "[notify_cnt]",
-		   cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
-		   cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SWITCH_CHBW],
-		   cnt[BTC_NCNT_SPECIAL_PACKET]);
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : scan_start=%d, scan_finish=%d, switch_band=%d, switch_chbw=%d, special_pkt=%d, ",
+		       "[notify_cnt]",
+		       cnt[BTC_NCNT_SCAN_START], cnt[BTC_NCNT_SCAN_FINISH],
+		       cnt[BTC_NCNT_SWITCH_BAND], cnt[BTC_NCNT_SWITCH_CHBW],
+		       cnt[BTC_NCNT_SPECIAL_PACKET]);
 
-	seq_printf(m, "timer=%d, customerize=%d, hub_msg=%d, chg_fw=%d, send_cc=%d",
-		   cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CUSTOMERIZE],
-		   rtwdev->btc.hubmsg_cnt, cnt[BTC_NCNT_RESUME_DL_FW],
-		   cnt[BTC_NCNT_COUNTRYCODE]);
+	p += scnprintf(p, end - p,
+		       "timer=%d, customerize=%d, hub_msg=%d, chg_fw=%d, send_cc=%d",
+		       cnt[BTC_NCNT_TIMER], cnt[BTC_NCNT_CUSTOMERIZE],
+		       rtwdev->btc.hubmsg_cnt, cnt[BTC_NCNT_RESUME_DL_FW],
+		       cnt[BTC_NCNT_COUNTRYCODE]);
+
+	return p - buf;
 }
 
-void rtw89_btc_dump_info(struct rtw89_dev *rtwdev, struct seq_file *m)
+ssize_t rtw89_btc_dump_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_fw_suit *fw_suit = &rtwdev->fw.normal;
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	struct rtw89_btc_cx *cx = &btc->cx;
 	struct rtw89_btc_bt_info *bt = &cx->bt;
-
-	seq_puts(m, "=========================================\n");
-	seq_printf(m, "WL FW / BT FW		%d.%d.%d.%d / NA\n",
-		   fw_suit->major_ver, fw_suit->minor_ver,
-		   fw_suit->sub_ver, fw_suit->sub_idex);
-	seq_printf(m, "manual			%d\n", btc->manual_ctrl);
-
-	seq_puts(m, "=========================================\n");
-
-	seq_printf(m, "\n\r %-15s : raw_data[%02x %02x %02x %02x %02x %02x] (type:%s/cnt:%d/same:%d)",
-		   "[bt_info]",
-		   bt->raw_info[2], bt->raw_info[3],
-		   bt->raw_info[4], bt->raw_info[5],
-		   bt->raw_info[6], bt->raw_info[7],
-		   bt->raw_info[0] == BTC_BTINFO_AUTO ? "auto" : "reply",
-		   cx->cnt_bt[BTC_BCNT_INFOUPDATE],
-		   cx->cnt_bt[BTC_BCNT_INFOSAME]);
-
-	seq_puts(m, "\n=========================================\n");
-
-	_show_cx_info(rtwdev, m);
-	_show_wl_info(rtwdev, m);
-	_show_bt_info(rtwdev, m);
-	_show_dm_info(rtwdev, m);
-	_show_fw_dm_msg(rtwdev, m);
+	char *p = buf, *end = buf + bufsz;
+
+	p += scnprintf(p, end - p,
+		       "=========================================\n");
+	p += scnprintf(p, end - p,
+		       "WL FW / BT FW		%d.%d.%d.%d / NA\n",
+		       fw_suit->major_ver, fw_suit->minor_ver,
+		       fw_suit->sub_ver, fw_suit->sub_idex);
+	p += scnprintf(p, end - p, "manual			%d\n",
+		       btc->manual_ctrl);
+
+	p += scnprintf(p, end - p,
+		       "=========================================\n");
+
+	p += scnprintf(p, end - p,
+		       "\n\r %-15s : raw_data[%02x %02x %02x %02x %02x %02x] (type:%s/cnt:%d/same:%d)",
+		       "[bt_info]",
+		       bt->raw_info[2], bt->raw_info[3],
+		       bt->raw_info[4], bt->raw_info[5],
+		       bt->raw_info[6], bt->raw_info[7],
+		       bt->raw_info[0] == BTC_BTINFO_AUTO ? "auto" : "reply",
+		       cx->cnt_bt[BTC_BCNT_INFOUPDATE],
+		       cx->cnt_bt[BTC_BCNT_INFOSAME]);
+
+	p += scnprintf(p, end - p,
+		       "\n=========================================\n");
+
+	p += _show_cx_info(rtwdev, p, end - p);
+	p += _show_wl_info(rtwdev, p, end - p);
+	p += _show_bt_info(rtwdev, p, end - p);
+	p += _show_dm_info(rtwdev, p, end - p);
+	p += _show_fw_dm_msg(rtwdev, p, end - p);
 
 	if (ver->fcxmreg == 1)
-		_show_mreg_v1(rtwdev, m);
+		p += _show_mreg_v1(rtwdev, p, end - p);
 	else if (ver->fcxmreg == 2)
-		_show_mreg_v2(rtwdev, m);
+		p += _show_mreg_v2(rtwdev, p, end - p);
 	else if (ver->fcxmreg == 7)
-		_show_mreg_v7(rtwdev, m);
+		p += _show_mreg_v7(rtwdev, p, end - p);
 
-	_show_gpio_dbg(rtwdev, m);
+	p += _show_gpio_dbg(rtwdev, p, end - p);
 
 	if (ver->fcxbtcrpt == 1)
-		_show_summary_v1(rtwdev, m);
+		p += _show_summary_v1(rtwdev, p, end - p);
 	else if (ver->fcxbtcrpt == 4)
-		_show_summary_v4(rtwdev, m);
+		p += _show_summary_v4(rtwdev, p, end - p);
 	else if (ver->fcxbtcrpt == 5)
-		_show_summary_v5(rtwdev, m);
+		p += _show_summary_v5(rtwdev, p, end - p);
 	else if (ver->fcxbtcrpt == 105)
-		_show_summary_v105(rtwdev, m);
+		p += _show_summary_v105(rtwdev, p, end - p);
 	else if (ver->fcxbtcrpt == 7)
-		_show_summary_v7(rtwdev, m);
+		p += _show_summary_v7(rtwdev, p, end - p);
 	else if (ver->fcxbtcrpt == 8)
-		_show_summary_v8(rtwdev, m);
+		p += _show_summary_v8(rtwdev, p, end - p);
+
+	return p - buf;
 }
 
 void rtw89_coex_recognize_ver(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/coex.h b/drivers/net/wireless/realtek/rtw89/coex.h
index 30134f58d5317..e3a1fcd796201 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.h
+++ b/drivers/net/wireless/realtek/rtw89/coex.h
@@ -282,7 +282,7 @@ void rtw89_btc_ntfy_wl_rfk(struct rtw89_dev *rtwdev, u8 phy_map,
 void rtw89_btc_ntfy_wl_sta(struct rtw89_dev *rtwdev);
 void rtw89_btc_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 			  u32 len, u8 class, u8 func);
-void rtw89_btc_dump_info(struct rtw89_dev *rtwdev, struct seq_file *m);
+ssize_t rtw89_btc_dump_info(struct rtw89_dev *rtwdev, char *buf, size_t bufsz);
 void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work);
 void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work);
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 09fa977a6e6d2..db0e7a4beb07e 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -13,6 +13,7 @@
 #include "ps.h"
 #include "reg.h"
 #include "sar.h"
+#include "util.h"
 
 #ifdef CONFIG_RTW89_DEBUGMSG
 unsigned int rtw89_debug_mask;
@@ -24,9 +25,12 @@ MODULE_PARM_DESC(debug_mask, "Debugging mask");
 #ifdef CONFIG_RTW89_DEBUGFS
 struct rtw89_debugfs_priv {
 	struct rtw89_dev *rtwdev;
-	int (*cb_read)(struct seq_file *m, void *v);
-	ssize_t (*cb_write)(struct file *filp, const char __user *buffer,
-			    size_t count, loff_t *loff);
+	ssize_t (*cb_read)(struct rtw89_dev *rtwdev,
+			   struct rtw89_debugfs_priv *debugfs_priv,
+			   char *buf, size_t bufsz);
+	ssize_t (*cb_write)(struct rtw89_dev *rtwdev,
+			    struct rtw89_debugfs_priv *debugfs_priv,
+			    const char *buf, size_t count);
 	union {
 		u32 cb_data;
 		struct {
@@ -74,6 +78,28 @@ struct rtw89_debugfs {
 	struct rtw89_debugfs_priv disable_dm;
 };
 
+struct rtw89_debugfs_iter_data {
+	char *buf;
+	size_t bufsz;
+	int written_sz;
+};
+
+static void rtw89_debugfs_iter_data_setup(struct rtw89_debugfs_iter_data *iter_data,
+					  char *buf, size_t bufsz)
+{
+	iter_data->buf = buf;
+	iter_data->bufsz = bufsz;
+	iter_data->written_sz = 0;
+}
+
+static void rtw89_debugfs_iter_data_next(struct rtw89_debugfs_iter_data *iter_data,
+					 char *buf, size_t bufsz, int written_sz)
+{
+	iter_data->buf = buf;
+	iter_data->bufsz = bufsz;
+	iter_data->written_sz += written_sz;
+}
+
 static const u16 rtw89_rate_info_bw_to_mhz_map[] = {
 	[RATE_INFO_BW_20] = 20,
 	[RATE_INFO_BW_40] = 40,
@@ -90,84 +116,78 @@ static u16 rtw89_rate_info_bw_to_mhz(enum rate_info_bw bw)
 	return 0;
 }
 
-static int rtw89_debugfs_single_show(struct seq_file *m, void *v)
+static ssize_t rtw89_debugfs_file_read(struct file *file, char __user *userbuf,
+				       size_t count, loff_t *ppos)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
+	struct rtw89_debugfs_priv *debugfs_priv = file->private_data;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	size_t bufsz = PAGE_SIZE;
+	char *buf;
+	ssize_t n;
 
-	return debugfs_priv->cb_read(m, v);
-}
+	buf = kvmalloc(bufsz, GFP_KERNEL);
+	if (!buf)
+		return 0;
 
-static ssize_t rtw89_debugfs_single_write(struct file *filp,
-					  const char __user *buffer,
-					  size_t count, loff_t *loff)
-{
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
+	n = debugfs_priv->cb_read(rtwdev, debugfs_priv, buf, bufsz);
+	rtw89_might_trailing_ellipsis(buf, bufsz, n);
 
-	return debugfs_priv->cb_write(filp, buffer, count, loff);
-}
+	n = simple_read_from_buffer(userbuf, count, ppos, buf, n);
 
-static ssize_t rtw89_debugfs_seq_file_write(struct file *filp,
-					    const char __user *buffer,
-					    size_t count, loff_t *loff)
-{
-	struct seq_file *seqpriv = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = seqpriv->private;
+	kvfree(buf);
 
-	return debugfs_priv->cb_write(filp, buffer, count, loff);
+	return n;
 }
 
-static int rtw89_debugfs_single_open(struct inode *inode, struct file *filp)
+static ssize_t rtw89_debugfs_file_write(struct file *file,
+					const char __user *userbuf,
+					size_t count, loff_t *loff)
 {
-	return single_open(filp, rtw89_debugfs_single_show, inode->i_private);
-}
+	struct rtw89_debugfs_priv *debugfs_priv = file->private_data;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	char *buf __free(kfree) = kmalloc(count + 1, GFP_KERNEL);
 
-static int rtw89_debugfs_close(struct inode *inode, struct file *filp)
-{
-	return 0;
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, userbuf, count))
+		return -EFAULT;
+
+	buf[count] = '\0';
+
+	return debugfs_priv->cb_write(rtwdev, debugfs_priv, buf, count);
 }
 
 static const struct file_operations file_ops_single_r = {
 	.owner = THIS_MODULE,
-	.open = rtw89_debugfs_single_open,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.release = single_release,
+	.read = rtw89_debugfs_file_read,
+	.open = simple_open,
+	.llseek = generic_file_llseek,
 };
 
 static const struct file_operations file_ops_common_rw = {
 	.owner = THIS_MODULE,
-	.open = rtw89_debugfs_single_open,
-	.release = single_release,
-	.read = seq_read,
-	.llseek = seq_lseek,
-	.write = rtw89_debugfs_seq_file_write,
+	.read = rtw89_debugfs_file_read,
+	.write = rtw89_debugfs_file_write,
+	.open = simple_open,
+	.llseek = generic_file_llseek,
 };
 
 static const struct file_operations file_ops_single_w = {
 	.owner = THIS_MODULE,
-	.write = rtw89_debugfs_single_write,
+	.write = rtw89_debugfs_file_write,
 	.open = simple_open,
-	.release = rtw89_debugfs_close,
+	.llseek = generic_file_llseek,
 };
 
 static ssize_t
-rtw89_debug_priv_read_reg_select(struct file *filp,
-				 const char __user *user_buf,
-				 size_t count, loff_t *loff)
+rtw89_debug_priv_read_reg_select(struct rtw89_dev *rtwdev,
+				 struct rtw89_debugfs_priv *debugfs_priv,
+				 const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	u32 addr, len;
 	int num;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%x %x", &addr, &len);
 	if (num != 2) {
 		rtw89_info(rtwdev, "invalid format: <addr> <len>\n");
@@ -182,11 +202,13 @@ rtw89_debug_priv_read_reg_select(struct file *filp,
 	return count;
 }
 
-static int rtw89_debug_priv_read_reg_get(struct seq_file *m, void *v)
+static
+ssize_t rtw89_debug_priv_read_reg_get(struct rtw89_dev *rtwdev,
+				      struct rtw89_debugfs_priv *debugfs_priv,
+				      char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	u32 addr, end, data, k;
+	char *p = buf, *end = buf + bufsz;
+	u32 addr, addr_end, data, k;
 	u32 len;
 
 	len = debugfs_priv->read_reg.len;
@@ -210,41 +232,34 @@ static int rtw89_debug_priv_read_reg_get(struct seq_file *m, void *v)
 		return -EINVAL;
 	}
 
-	seq_printf(m, "get %d bytes at 0x%08x=0x%08x\n", len, addr, data);
+	p += scnprintf(p, end - p, "get %d bytes at 0x%08x=0x%08x\n", len,
+		       addr, data);
 
-	return 0;
+	return p - buf;
 
 ndata:
-	end = addr + len;
+	addr_end = addr + len;
 
-	for (; addr < end; addr += 16) {
-		seq_printf(m, "%08xh : ", 0x18600000 + addr);
+	for (; addr < addr_end; addr += 16) {
+		p += scnprintf(p, end - p, "%08xh : ", 0x18600000 + addr);
 		for (k = 0; k < 16; k += 4) {
 			data = rtw89_read32(rtwdev, addr + k);
-			seq_printf(m, "%08x ", data);
+			p += scnprintf(p, end - p, "%08x ", data);
 		}
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
 
-	return 0;
+	return p - buf;
 }
 
-static ssize_t rtw89_debug_priv_write_reg_set(struct file *filp,
-					      const char __user *user_buf,
-					      size_t count, loff_t *loff)
+static
+ssize_t rtw89_debug_priv_write_reg_set(struct rtw89_dev *rtwdev,
+				       struct rtw89_debugfs_priv *debugfs_priv,
+				       const char *buf, size_t count)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	u32 addr, val, len;
 	int num;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%x %x %x", &addr, &val, &len);
 	if (num !=  3) {
 		rtw89_info(rtwdev, "invalid format: <addr> <val> <len>\n");
@@ -273,24 +288,14 @@ static ssize_t rtw89_debug_priv_write_reg_set(struct file *filp,
 }
 
 static ssize_t
-rtw89_debug_priv_read_rf_select(struct file *filp,
-				const char __user *user_buf,
-				size_t count, loff_t *loff)
+rtw89_debug_priv_read_rf_select(struct rtw89_dev *rtwdev,
+				struct rtw89_debugfs_priv *debugfs_priv,
+				const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	u32 addr, mask;
 	u8 path;
 	int num;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%hhd %x %x", &path, &addr, &mask);
 	if (num != 3) {
 		rtw89_info(rtwdev, "invalid format: <path> <addr> <mask>\n");
@@ -310,10 +315,12 @@ rtw89_debug_priv_read_rf_select(struct file *filp,
 	return count;
 }
 
-static int rtw89_debug_priv_read_rf_get(struct seq_file *m, void *v)
+static
+ssize_t rtw89_debug_priv_read_rf_get(struct rtw89_dev *rtwdev,
+				     struct rtw89_debugfs_priv *debugfs_priv,
+				     char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	char *p = buf, *end = buf + bufsz;
 	u32 addr, data, mask;
 	u8 path;
 
@@ -323,28 +330,21 @@ static int rtw89_debug_priv_read_rf_get(struct seq_file *m, void *v)
 
 	data = rtw89_read_rf(rtwdev, path, addr, mask);
 
-	seq_printf(m, "path %d, rf register 0x%08x=0x%08x\n", path, addr, data);
+	p += scnprintf(p, end - p, "path %d, rf register 0x%08x=0x%08x\n",
+		       path, addr, data);
 
-	return 0;
+	return p - buf;
 }
 
-static ssize_t rtw89_debug_priv_write_rf_set(struct file *filp,
-					     const char __user *user_buf,
-					     size_t count, loff_t *loff)
+static
+ssize_t rtw89_debug_priv_write_rf_set(struct rtw89_dev *rtwdev,
+				      struct rtw89_debugfs_priv *debugfs_priv,
+				      const char *buf, size_t count)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	u32 addr, val, mask;
 	u8 path;
 	int num;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%hhd %x %x %x", &path, &addr, &mask, &val);
 	if (num != 4) {
 		rtw89_info(rtwdev, "invalid format: <path> <addr> <mask> <val>\n");
@@ -363,29 +363,31 @@ static ssize_t rtw89_debug_priv_write_rf_set(struct file *filp,
 	return count;
 }
 
-static int rtw89_debug_priv_rf_reg_dump_get(struct seq_file *m, void *v)
+static
+ssize_t rtw89_debug_priv_rf_reg_dump_get(struct rtw89_dev *rtwdev,
+					 struct rtw89_debugfs_priv *debugfs_priv,
+					 char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
+	char *p = buf, *end = buf + bufsz;
 	u32 addr, offset, data;
 	u8 path;
 
 	for (path = 0; path < chip->rf_path_num; path++) {
-		seq_printf(m, "RF path %d:\n\n", path);
+		p += scnprintf(p, end - p, "RF path %d:\n\n", path);
 		for (addr = 0; addr < 0x100; addr += 4) {
-			seq_printf(m, "0x%08x: ", addr);
+			p += scnprintf(p, end - p, "0x%08x: ", addr);
 			for (offset = 0; offset < 4; offset++) {
 				data = rtw89_read_rf(rtwdev, path,
 						     addr + offset, RFREG_MASK);
-				seq_printf(m, "0x%05x  ", data);
+				p += scnprintf(p, end - p, "0x%05x  ", data);
 			}
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 		}
-		seq_puts(m, "\n");
+		p += scnprintf(p, end - p, "\n");
 	}
 
-	return 0;
+	return p - buf;
 }
 
 struct txpwr_ent {
@@ -704,56 +706,71 @@ static const struct txpwr_map __txpwr_map_lmt_ru_be = {
 };
 
 static unsigned int
-__print_txpwr_ent(struct seq_file *m, const struct txpwr_ent *ent,
-		  const s8 *buf, const unsigned int cur)
+__print_txpwr_ent(char *buf, size_t bufsz, const struct txpwr_ent *ent,
+		  const s8 *bufp, const unsigned int cur, unsigned int *ate)
 {
+	char *p = buf, *end = buf + bufsz;
 	unsigned int cnt, i;
+	unsigned int eaten;
 	char *fmt;
 
 	if (ent->nested) {
-		for (cnt = 0, i = 0; i < ent->len; i++)
-			cnt += __print_txpwr_ent(m, ent->ptr + i, buf,
-						 cur + cnt);
-		return cnt;
+		for (cnt = 0, i = 0; i < ent->len; i++, cnt += eaten)
+			p += __print_txpwr_ent(p, end - p, ent->ptr + i, bufp,
+					       cur + cnt, &eaten);
+		*ate = cnt;
+		goto out;
 	}
 
 	switch (ent->len) {
 	case 0:
-		seq_printf(m, "\t<< %s >>\n", ent->txt);
-		return 0;
+		p += scnprintf(p, end - p, "\t<< %s >>\n", ent->txt);
+		*ate = 0;
+		goto out;
 	case 2:
 		fmt = "%s\t| %3d, %3d,\t\tdBm\n";
-		seq_printf(m, fmt, ent->txt, buf[cur], buf[cur + 1]);
-		return 2;
+		p += scnprintf(p, end - p, fmt, ent->txt, bufp[cur],
+			       bufp[cur + 1]);
+		*ate = 2;
+		goto out;
 	case 4:
 		fmt = "%s\t| %3d, %3d, %3d, %3d,\tdBm\n";
-		seq_printf(m, fmt, ent->txt, buf[cur], buf[cur + 1],
-			   buf[cur + 2], buf[cur + 3]);
-		return 4;
+		p += scnprintf(p, end - p, fmt, ent->txt, bufp[cur],
+			       bufp[cur + 1],
+			       bufp[cur + 2], bufp[cur + 3]);
+		*ate = 4;
+		goto out;
 	case 8:
 		fmt = "%s\t| %3d, %3d, %3d, %3d, %3d, %3d, %3d, %3d,\tdBm\n";
-		seq_printf(m, fmt, ent->txt, buf[cur], buf[cur + 1],
-			   buf[cur + 2], buf[cur + 3], buf[cur + 4],
-			   buf[cur + 5], buf[cur + 6], buf[cur + 7]);
-		return 8;
+		p += scnprintf(p, end - p, fmt, ent->txt, bufp[cur],
+			       bufp[cur + 1],
+			       bufp[cur + 2], bufp[cur + 3], bufp[cur + 4],
+			       bufp[cur + 5], bufp[cur + 6], bufp[cur + 7]);
+		*ate = 8;
+		goto out;
 	default:
 		return 0;
 	}
+
+out:
+	return p - buf;
 }
 
-static int __print_txpwr_map(struct seq_file *m, struct rtw89_dev *rtwdev,
-			     const struct txpwr_map *map)
+static ssize_t __print_txpwr_map(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+				 const struct txpwr_map *map)
 {
 	u8 fct = rtwdev->chip->txpwr_factor_mac;
 	u8 path_num = rtwdev->chip->rf_path_num;
+	char *p = buf, *end = buf + bufsz;
 	unsigned int cur, i;
+	unsigned int eaten;
 	u32 max_valid_addr;
 	u32 val, addr;
-	s8 *buf, tmp;
+	s8 *bufp, tmp;
 	int ret;
 
-	buf = vzalloc(map->addr_to - map->addr_from + 4);
-	if (!buf)
+	bufp = vzalloc(map->addr_to - map->addr_from + 4);
+	if (!bufp)
 		return -ENOMEM;
 
 	if (path_num == 1)
@@ -773,31 +790,32 @@ static int __print_txpwr_map(struct seq_file *m, struct rtw89_dev *rtwdev,
 		for (i = 0; i < 4; i++, val >>= 8) {
 			/* signed 7 bits, and reserved BIT(7) */
 			tmp = sign_extend32(val, 6);
-			buf[cur + i] = tmp >> fct;
+			bufp[cur + i] = tmp >> fct;
 		}
 	}
 
-	for (cur = 0, i = 0; i < map->size; i++)
-		cur += __print_txpwr_ent(m, &map->ent[i], buf, cur);
+	for (cur = 0, i = 0; i < map->size; i++, cur += eaten)
+		p += __print_txpwr_ent(p, end - p, &map->ent[i], bufp, cur, &eaten);
 
-	vfree(buf);
-	return 0;
+	vfree(bufp);
+	return p - buf;
 }
 
 #define case_REGD(_regd) \
 	case RTW89_ ## _regd: \
-		seq_puts(m, #_regd "\n"); \
+		p += scnprintf(p, end - p, #_regd "\n"); \
 		break
 
-static void __print_regd(struct seq_file *m, struct rtw89_dev *rtwdev,
-			 const struct rtw89_chan *chan)
+static int __print_regd(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+			const struct rtw89_chan *chan)
 {
+	char *p = buf, *end = buf + bufsz;
 	u8 band = chan->band_type;
 	u8 regd = rtw89_regd_get(rtwdev, band);
 
 	switch (regd) {
 	default:
-		seq_printf(m, "UNKNOWN: %d\n", regd);
+		p += scnprintf(p, end - p, "UNKNOWN: %d\n", regd);
 		break;
 	case_REGD(WW);
 	case_REGD(ETSI);
@@ -816,6 +834,8 @@ static void __print_regd(struct seq_file *m, struct rtw89_dev *rtwdev,
 	case_REGD(UK);
 	case_REGD(THAILAND);
 	}
+
+	return p - buf;
 }
 
 #undef case_REGD
@@ -844,96 +864,101 @@ static const struct dbgfs_txpwr_table *dbgfs_txpwr_tables[RTW89_CHIP_GEN_NUM] =
 };
 
 static
-void rtw89_debug_priv_txpwr_table_get_regd(struct seq_file *m,
-					   struct rtw89_dev *rtwdev,
-					   const struct rtw89_chan *chan)
+int rtw89_debug_priv_txpwr_table_get_regd(struct rtw89_dev *rtwdev,
+					  char *buf, size_t bufsz,
+					  const struct rtw89_chan *chan)
 {
 	const struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
 	const struct rtw89_reg_6ghz_tpe *tpe6 = &regulatory->reg_6ghz_tpe;
+	char *p = buf, *end = buf + bufsz;
 
-	seq_printf(m, "[Chanctx] band %u, ch %u, bw %u\n",
-		   chan->band_type, chan->channel, chan->band_width);
+	p += scnprintf(p, end - p, "[Chanctx] band %u, ch %u, bw %u\n",
+		       chan->band_type, chan->channel, chan->band_width);
 
-	seq_puts(m, "[Regulatory] ");
-	__print_regd(m, rtwdev, chan);
+	p += scnprintf(p, end - p, "[Regulatory] ");
+	p += __print_regd(rtwdev, p, end - p, chan);
 
 	if (chan->band_type == RTW89_BAND_6G) {
-		seq_printf(m, "[reg6_pwr_type] %u\n", regulatory->reg_6ghz_power);
+		p += scnprintf(p, end - p, "[reg6_pwr_type] %u\n",
+			       regulatory->reg_6ghz_power);
 
 		if (tpe6->valid)
-			seq_printf(m, "[TPE] %d dBm\n", tpe6->constraint);
+			p += scnprintf(p, end - p, "[TPE] %d dBm\n",
+				       tpe6->constraint);
 	}
+
+	return p - buf;
 }
 
-static int rtw89_debug_priv_txpwr_table_get(struct seq_file *m, void *v)
+static
+ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
+					 struct rtw89_debugfs_priv *debugfs_priv,
+					 char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	enum rtw89_chip_gen chip_gen = rtwdev->chip->chip_gen;
 	const struct dbgfs_txpwr_table *tbl;
 	const struct rtw89_chan *chan;
-	int ret = 0;
+	char *p = buf, *end = buf + bufsz;
+	ssize_t n;
 
 	mutex_lock(&rtwdev->mutex);
 	rtw89_leave_ps_mode(rtwdev);
 	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
-	rtw89_debug_priv_txpwr_table_get_regd(m, rtwdev, chan);
+	p += rtw89_debug_priv_txpwr_table_get_regd(rtwdev, p, end - p, chan);
 
-	seq_puts(m, "[SAR]\n");
-	rtw89_print_sar(m, rtwdev, chan->freq);
+	p += scnprintf(p, end - p, "[SAR]\n");
+	p += rtw89_print_sar(rtwdev, p, end - p, chan->freq);
 
-	seq_puts(m, "[TAS]\n");
-	rtw89_print_tas(m, rtwdev);
+	p += scnprintf(p, end - p, "[TAS]\n");
+	p += rtw89_print_tas(rtwdev, p, end - p);
 
-	seq_puts(m, "[DAG]\n");
-	rtw89_print_ant_gain(m, rtwdev, chan);
+	p += scnprintf(p, end - p, "[DAG]\n");
+	p += rtw89_print_ant_gain(rtwdev, p, end - p, chan);
 
 	tbl = dbgfs_txpwr_tables[chip_gen];
 	if (!tbl) {
-		ret = -EOPNOTSUPP;
+		n = -EOPNOTSUPP;
 		goto err;
 	}
 
-	seq_puts(m, "\n[TX power byrate]\n");
-	ret = __print_txpwr_map(m, rtwdev, tbl->byr);
-	if (ret)
+	p += scnprintf(p, end - p, "\n[TX power byrate]\n");
+	n = __print_txpwr_map(rtwdev, p, end - p, tbl->byr);
+	if (n < 0)
 		goto err;
+	p += n;
 
-	seq_puts(m, "\n[TX power limit]\n");
-	ret = __print_txpwr_map(m, rtwdev, tbl->lmt);
-	if (ret)
+	p += scnprintf(p, end - p, "\n[TX power limit]\n");
+	n = __print_txpwr_map(rtwdev, p, end - p, tbl->lmt);
+	if (n < 0)
 		goto err;
+	p += n;
 
-	seq_puts(m, "\n[TX power limit_ru]\n");
-	ret = __print_txpwr_map(m, rtwdev, tbl->lmt_ru);
-	if (ret)
+	p += scnprintf(p, end - p, "\n[TX power limit_ru]\n");
+	n = __print_txpwr_map(rtwdev, p, end - p, tbl->lmt_ru);
+	if (n < 0)
 		goto err;
+	p += n;
+
+	mutex_unlock(&rtwdev->mutex);
+
+	return p - buf;
 
 err:
 	mutex_unlock(&rtwdev->mutex);
-	return ret;
+
+	return n;
 }
 
 static ssize_t
-rtw89_debug_priv_mac_reg_dump_select(struct file *filp,
-				     const char __user *user_buf,
-				     size_t count, loff_t *loff)
+rtw89_debug_priv_mac_reg_dump_select(struct rtw89_dev *rtwdev,
+				     struct rtw89_debugfs_priv *debugfs_priv,
+				     const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
-	char buf[32];
-	size_t buf_size;
 	int sel;
 	int ret;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	ret = kstrtoint(buf, 0, &sel);
 	if (ret)
 		return ret;
@@ -957,99 +982,91 @@ rtw89_debug_priv_mac_reg_dump_select(struct file *filp,
 
 #define RTW89_MAC_PAGE_SIZE		0x100
 
-static int rtw89_debug_priv_mac_reg_dump_get(struct seq_file *m, void *v)
+static
+ssize_t rtw89_debug_priv_mac_reg_dump_get(struct rtw89_dev *rtwdev,
+					  struct rtw89_debugfs_priv *debugfs_priv,
+					  char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	enum rtw89_debug_mac_reg_sel reg_sel = debugfs_priv->cb_data;
-	u32 start, end;
+	char *p = buf, *end = buf + bufsz;
+	u32 start, end_addr;
 	u32 i, j, k, page;
 	u32 val;
 
 	switch (reg_sel) {
 	case RTW89_DBG_SEL_MAC_00:
-		seq_puts(m, "Debug selected MAC page 0x00\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0x00\n");
 		start = 0x000;
-		end = 0x014;
+		end_addr = 0x014;
 		break;
 	case RTW89_DBG_SEL_MAC_30:
-		seq_puts(m, "Debug selected MAC page 0x30\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0x30\n");
 		start = 0x030;
-		end = 0x033;
+		end_addr = 0x033;
 		break;
 	case RTW89_DBG_SEL_MAC_40:
-		seq_puts(m, "Debug selected MAC page 0x40\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0x40\n");
 		start = 0x040;
-		end = 0x07f;
+		end_addr = 0x07f;
 		break;
 	case RTW89_DBG_SEL_MAC_80:
-		seq_puts(m, "Debug selected MAC page 0x80\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0x80\n");
 		start = 0x080;
-		end = 0x09f;
+		end_addr = 0x09f;
 		break;
 	case RTW89_DBG_SEL_MAC_C0:
-		seq_puts(m, "Debug selected MAC page 0xc0\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0xc0\n");
 		start = 0x0c0;
-		end = 0x0df;
+		end_addr = 0x0df;
 		break;
 	case RTW89_DBG_SEL_MAC_E0:
-		seq_puts(m, "Debug selected MAC page 0xe0\n");
+		p += scnprintf(p, end - p, "Debug selected MAC page 0xe0\n");
 		start = 0x0e0;
-		end = 0x0ff;
+		end_addr = 0x0ff;
 		break;
 	case RTW89_DBG_SEL_BB:
-		seq_puts(m, "Debug selected BB register\n");
+		p += scnprintf(p, end - p, "Debug selected BB register\n");
 		start = 0x100;
-		end = 0x17f;
+		end_addr = 0x17f;
 		break;
 	case RTW89_DBG_SEL_IQK:
-		seq_puts(m, "Debug selected IQK register\n");
+		p += scnprintf(p, end - p, "Debug selected IQK register\n");
 		start = 0x180;
-		end = 0x1bf;
+		end_addr = 0x1bf;
 		break;
 	case RTW89_DBG_SEL_RFC:
-		seq_puts(m, "Debug selected RFC register\n");
+		p += scnprintf(p, end - p, "Debug selected RFC register\n");
 		start = 0x1c0;
-		end = 0x1ff;
+		end_addr = 0x1ff;
 		break;
 	default:
-		seq_puts(m, "Selected invalid register page\n");
+		p += scnprintf(p, end - p, "Selected invalid register page\n");
 		return -EINVAL;
 	}
 
-	for (i = start; i <= end; i++) {
+	for (i = start; i <= end_addr; i++) {
 		page = i << 8;
 		for (j = page; j < page + RTW89_MAC_PAGE_SIZE; j += 16) {
-			seq_printf(m, "%08xh : ", 0x18600000 + j);
+			p += scnprintf(p, end - p, "%08xh : ", 0x18600000 + j);
 			for (k = 0; k < 4; k++) {
 				val = rtw89_read32(rtwdev, j + (k << 2));
-				seq_printf(m, "%08x ", val);
+				p += scnprintf(p, end - p, "%08x ", val);
 			}
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 		}
 	}
 
-	return 0;
+	return p - buf;
 }
 
 static ssize_t
-rtw89_debug_priv_mac_mem_dump_select(struct file *filp,
-				     const char __user *user_buf,
-				     size_t count, loff_t *loff)
+rtw89_debug_priv_mac_mem_dump_select(struct rtw89_dev *rtwdev,
+				     struct rtw89_debugfs_priv *debugfs_priv,
+				     const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	u32 sel, start_addr, len;
 	int num;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%x %x %x", &sel, &start_addr, &len);
 	if (num != 3) {
 		rtw89_info(rtwdev, "invalid format: <sel> <start> <len>\n");
@@ -1066,15 +1083,16 @@ rtw89_debug_priv_mac_mem_dump_select(struct file *filp,
 	return count;
 }
 
-static void rtw89_debug_dump_mac_mem(struct seq_file *m,
-				     struct rtw89_dev *rtwdev,
-				     u8 sel, u32 start_addr, u32 len)
+static int rtw89_debug_dump_mac_mem(struct rtw89_dev *rtwdev,
+				    char *buf, size_t bufsz,
+				    u8 sel, u32 start_addr, u32 len)
 {
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u32 filter_model_addr = mac->filter_model_addr;
 	u32 indir_access_addr = mac->indir_access_addr;
 	u32 base_addr, start_page, residue;
-	u32 i, j, p, pages;
+	char *p = buf, *end = buf + bufsz;
+	u32 i, j, pp, pages;
 	u32 dump_len, remain;
 	u32 val;
 
@@ -1085,30 +1103,33 @@ static void rtw89_debug_dump_mac_mem(struct seq_file *m,
 	base_addr = mac->mem_base_addrs[sel];
 	base_addr += start_page * MAC_MEM_DUMP_PAGE_SIZE;
 
-	for (p = 0; p < pages; p++) {
+	for (pp = 0; pp < pages; pp++) {
 		dump_len = min_t(u32, remain, MAC_MEM_DUMP_PAGE_SIZE);
 		rtw89_write32(rtwdev, filter_model_addr, base_addr);
 		for (i = indir_access_addr + residue;
 		     i < indir_access_addr + dump_len;) {
-			seq_printf(m, "%08xh:", i);
+			p += scnprintf(p, end - p, "%08xh:", i);
 			for (j = 0;
 			     j < 4 && i < indir_access_addr + dump_len;
 			     j++, i += 4) {
 				val = rtw89_read32(rtwdev, i);
-				seq_printf(m, "  %08x", val);
+				p += scnprintf(p, end - p, "  %08x", val);
 				remain -= 4;
 			}
-			seq_puts(m, "\n");
+			p += scnprintf(p, end - p, "\n");
 		}
 		base_addr += MAC_MEM_DUMP_PAGE_SIZE;
 	}
+
+	return p - buf;
 }
 
-static int
-rtw89_debug_priv_mac_mem_dump_get(struct seq_file *m, void *v)
+static ssize_t
+rtw89_debug_priv_mac_mem_dump_get(struct rtw89_dev *rtwdev,
+				  struct rtw89_debugfs_priv *debugfs_priv,
+				  char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	char *p = buf, *end = buf + bufsz;
 	bool grant_read = false;
 
 	if (debugfs_priv->mac_mem.sel >= RTW89_MAC_MEM_NUM)
@@ -1131,36 +1152,26 @@ rtw89_debug_priv_mac_mem_dump_get(struct seq_file *m, void *v)
 	rtw89_leave_ps_mode(rtwdev);
 	if (grant_read)
 		rtw89_write32_set(rtwdev, R_AX_TCR1, B_AX_TCR_FORCE_READ_TXDFIFO);
-	rtw89_debug_dump_mac_mem(m, rtwdev,
-				 debugfs_priv->mac_mem.sel,
-				 debugfs_priv->mac_mem.start,
-				 debugfs_priv->mac_mem.len);
+	p += rtw89_debug_dump_mac_mem(rtwdev, p, end - p,
+				      debugfs_priv->mac_mem.sel,
+				      debugfs_priv->mac_mem.start,
+				      debugfs_priv->mac_mem.len);
 	if (grant_read)
 		rtw89_write32_clr(rtwdev, R_AX_TCR1, B_AX_TCR_FORCE_READ_TXDFIFO);
 	mutex_unlock(&rtwdev->mutex);
 
-	return 0;
+	return p - buf;
 }
 
 static ssize_t
-rtw89_debug_priv_mac_dbg_port_dump_select(struct file *filp,
-					  const char __user *user_buf,
-					  size_t count, loff_t *loff)
+rtw89_debug_priv_mac_dbg_port_dump_select(struct rtw89_dev *rtwdev,
+					  struct rtw89_debugfs_priv *debugfs_priv,
+					  const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	char buf[32];
-	size_t buf_size;
 	int sel, set;
 	int num;
 	bool enable;
 
-	buf_size = min(count, sizeof(buf) - 1);
-	if (copy_from_user(buf, user_buf, buf_size))
-		return -EFAULT;
-
-	buf[buf_size] = '\0';
 	num = sscanf(buf, "%d %d", &sel, &set);
 	if (num != 2) {
 		rtw89_info(rtwdev, "invalid format: <sel> <set>\n");
@@ -1196,13 +1207,13 @@ rtw89_debug_priv_mac_dbg_port_dump_select(struct file *filp,
 }
 
 static int rtw89_debug_mac_dump_ss_dbg(struct rtw89_dev *rtwdev,
-				       struct seq_file *m)
+				       char *buf, size_t bufsz)
 {
 	return 0;
 }
 
 static int rtw89_debug_mac_dump_dle_dbg(struct rtw89_dev *rtwdev,
-					struct seq_file *m)
+				       char *buf, size_t bufsz)
 {
 #define DLE_DFI_DUMP(__type, __target, __sel)				\
 ({									\
@@ -1231,7 +1242,7 @@ static int rtw89_debug_mac_dump_dle_dbg(struct rtw89_dev *rtwdev,
 	__data;								\
 })
 
-#define DLE_DFI_FREE_PAGE_DUMP(__m, __type)				\
+#define DLE_DFI_FREE_PAGE_DUMP(__p, __end, __type)			\
 ({									\
 	u32 __freepg, __pubpg;						\
 	u32 __freepg_head, __freepg_tail, __pubpg_num;			\
@@ -1241,24 +1252,25 @@ static int rtw89_debug_mac_dump_dle_dbg(struct rtw89_dev *rtwdev,
 	__freepg_head = FIELD_GET(B_AX_DLE_FREE_HEADPG, __freepg);	\
 	__freepg_tail = FIELD_GET(B_AX_DLE_FREE_TAILPG, __freepg);	\
 	__pubpg_num = FIELD_GET(B_AX_DLE_PUB_PGNUM, __pubpg);		\
-	seq_printf(__m, "[%s] freepg head: %d\n",			\
-		   #__type, __freepg_head);				\
-	seq_printf(__m, "[%s] freepg tail: %d\n",			\
-		   #__type, __freepg_tail);				\
-	seq_printf(__m, "[%s] pubpg num  : %d\n",			\
-		  #__type, __pubpg_num);				\
+	__p += scnprintf(__p, __end - __p, "[%s] freepg head: %d\n",	\
+			 #__type, __freepg_head);			\
+	__p += scnprintf(__p, __end - __p, "[%s] freepg tail: %d\n",	\
+			 #__type, __freepg_tail);			\
+	__p += scnprintf(__p, __end - __p, "[%s] pubpg num  : %d\n",	\
+			 #__type, __pubpg_num);				\
 })
 
-#define case_QUOTA(__m, __type, __id)					\
+#define case_QUOTA(__p, __end, __type, __id)				\
 	case __type##_QTAID_##__id:					\
-		val32 = DLE_DFI_DUMP(__type, QUOTA, __type##_QTAID_##__id);	\
+		val32 = DLE_DFI_DUMP(__type, QUOTA, __type##_QTAID_##__id); \
 		rsv_pgnum = FIELD_GET(B_AX_DLE_RSV_PGNUM, val32);	\
 		use_pgnum = FIELD_GET(B_AX_DLE_USE_PGNUM, val32);	\
-		seq_printf(__m, "[%s][%s] rsv_pgnum: %d\n",		\
-			   #__type, #__id, rsv_pgnum);			\
-		seq_printf(__m, "[%s][%s] use_pgnum: %d\n",		\
-			   #__type, #__id, use_pgnum);			\
+		__p += scnprintf(__p, __end - __p, "[%s][%s] rsv_pgnum: %d\n", \
+				 #__type, #__id, rsv_pgnum);		\
+		__p += scnprintf(__p, __end - __p, "[%s][%s] use_pgnum: %d\n", \
+				 #__type, #__id, use_pgnum);		\
 		break
+	char *p = buf, *end = buf + bufsz;
 	u32 quota_id;
 	u32 val32;
 	u16 rsv_pgnum, use_pgnum;
@@ -1266,38 +1278,39 @@ static int rtw89_debug_mac_dump_dle_dbg(struct rtw89_dev *rtwdev,
 
 	ret = rtw89_mac_check_mac_en(rtwdev, 0, RTW89_DMAC_SEL);
 	if (ret) {
-		seq_puts(m, "[DLE]  : DMAC not enabled\n");
-		return ret;
+		p += scnprintf(p, end - p, "[DLE]  : DMAC not enabled\n");
+		goto out;
 	}
 
-	DLE_DFI_FREE_PAGE_DUMP(m, WDE);
-	DLE_DFI_FREE_PAGE_DUMP(m, PLE);
+	DLE_DFI_FREE_PAGE_DUMP(p, end, WDE);
+	DLE_DFI_FREE_PAGE_DUMP(p, end, PLE);
 	for (quota_id = 0; quota_id <= WDE_QTAID_CPUIO; quota_id++) {
 		switch (quota_id) {
-		case_QUOTA(m, WDE, HOST_IF);
-		case_QUOTA(m, WDE, WLAN_CPU);
-		case_QUOTA(m, WDE, DATA_CPU);
-		case_QUOTA(m, WDE, PKTIN);
-		case_QUOTA(m, WDE, CPUIO);
+		case_QUOTA(p, end, WDE, HOST_IF);
+		case_QUOTA(p, end, WDE, WLAN_CPU);
+		case_QUOTA(p, end, WDE, DATA_CPU);
+		case_QUOTA(p, end, WDE, PKTIN);
+		case_QUOTA(p, end, WDE, CPUIO);
 		}
 	}
 	for (quota_id = 0; quota_id <= PLE_QTAID_CPUIO; quota_id++) {
 		switch (quota_id) {
-		case_QUOTA(m, PLE, B0_TXPL);
-		case_QUOTA(m, PLE, B1_TXPL);
-		case_QUOTA(m, PLE, C2H);
-		case_QUOTA(m, PLE, H2C);
-		case_QUOTA(m, PLE, WLAN_CPU);
-		case_QUOTA(m, PLE, MPDU);
-		case_QUOTA(m, PLE, CMAC0_RX);
-		case_QUOTA(m, PLE, CMAC1_RX);
-		case_QUOTA(m, PLE, CMAC1_BBRPT);
-		case_QUOTA(m, PLE, WDRLS);
-		case_QUOTA(m, PLE, CPUIO);
+		case_QUOTA(p, end, PLE, B0_TXPL);
+		case_QUOTA(p, end, PLE, B1_TXPL);
+		case_QUOTA(p, end, PLE, C2H);
+		case_QUOTA(p, end, PLE, H2C);
+		case_QUOTA(p, end, PLE, WLAN_CPU);
+		case_QUOTA(p, end, PLE, MPDU);
+		case_QUOTA(p, end, PLE, CMAC0_RX);
+		case_QUOTA(p, end, PLE, CMAC1_RX);
+		case_QUOTA(p, end, PLE, CMAC1_BBRPT);
+		case_QUOTA(p, end, PLE, WDRLS);
+		case_QUOTA(p, end, PLE, CPUIO);
 		}
 	}
 
-	return 0;
+out:
+	return p - buf;
 
 #undef case_QUOTA
 #undef DLE_DFI_DUMP
@@ -1305,73 +1318,88 @@ static int rtw89_debug_mac_dump_dle_dbg(struct rtw89_dev *rtwdev,
 }
 
 static int rtw89_debug_mac_dump_dmac_dbg(struct rtw89_dev *rtwdev,
-					 struct seq_file *m)
+					 char *buf, size_t bufsz)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
+	char *p = buf, *end = buf + bufsz;
 	u32 dmac_err;
 	int i, ret;
 
 	ret = rtw89_mac_check_mac_en(rtwdev, 0, RTW89_DMAC_SEL);
 	if (ret) {
-		seq_puts(m, "[DMAC] : DMAC not enabled\n");
-		return ret;
+		p += scnprintf(p, end - p, "[DMAC] : DMAC not enabled\n");
+		goto out;
 	}
 
 	dmac_err = rtw89_read32(rtwdev, R_AX_DMAC_ERR_ISR);
-	seq_printf(m, "R_AX_DMAC_ERR_ISR=0x%08x\n", dmac_err);
-	seq_printf(m, "R_AX_DMAC_ERR_IMR=0x%08x\n",
-		   rtw89_read32(rtwdev, R_AX_DMAC_ERR_IMR));
+	p += scnprintf(p, end - p, "R_AX_DMAC_ERR_ISR=0x%08x\n", dmac_err);
+	p += scnprintf(p, end - p, "R_AX_DMAC_ERR_IMR=0x%08x\n",
+		       rtw89_read32(rtwdev, R_AX_DMAC_ERR_IMR));
 
 	if (dmac_err) {
-		seq_printf(m, "R_AX_WDE_ERR_FLAG_CFG=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDE_ERR_FLAG_CFG_NUM1));
-		seq_printf(m, "R_AX_PLE_ERR_FLAG_CFG=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_CFG_NUM1));
+		p += scnprintf(p, end - p, "R_AX_WDE_ERR_FLAG_CFG=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDE_ERR_FLAG_CFG_NUM1));
+		p += scnprintf(p, end - p, "R_AX_PLE_ERR_FLAG_CFG=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_CFG_NUM1));
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_PLE_ERRFLAG_MSG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_PLE_ERRFLAG_MSG));
-			seq_printf(m, "R_AX_WDE_ERRFLAG_MSG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_WDE_ERRFLAG_MSG));
-			seq_printf(m, "R_AX_PLE_DBGERR_LOCKEN=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_PLE_DBGERR_LOCKEN));
-			seq_printf(m, "R_AX_PLE_DBGERR_STS=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_PLE_DBGERR_STS));
+			p += scnprintf(p, end - p,
+				       "R_AX_PLE_ERRFLAG_MSG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_PLE_ERRFLAG_MSG));
+			p += scnprintf(p, end - p,
+				       "R_AX_WDE_ERRFLAG_MSG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_WDE_ERRFLAG_MSG));
+			p += scnprintf(p, end - p,
+				       "R_AX_PLE_DBGERR_LOCKEN=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_PLE_DBGERR_LOCKEN));
+			p += scnprintf(p, end - p,
+				       "R_AX_PLE_DBGERR_STS=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_PLE_DBGERR_STS));
 		}
 	}
 
 	if (dmac_err & B_AX_WDRLS_ERR_FLAG) {
-		seq_printf(m, "R_AX_WDRLS_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDRLS_ERR_IMR));
-		seq_printf(m, "R_AX_WDRLS_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDRLS_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_WDRLS_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDRLS_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_WDRLS_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDRLS_ERR_ISR));
 		if (chip->chip_id == RTL8852C)
-			seq_printf(m, "R_AX_RPQ_RXBD_IDX=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX_V1));
+			p += scnprintf(p, end - p,
+				       "R_AX_RPQ_RXBD_IDX=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX_V1));
 		else
-			seq_printf(m, "R_AX_RPQ_RXBD_IDX=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX));
+			p += scnprintf(p, end - p,
+				       "R_AX_RPQ_RXBD_IDX=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RPQ_RXBD_IDX));
 	}
 
 	if (dmac_err & B_AX_WSEC_ERR_FLAG) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_SEC_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_ERROR_FLAG_IMR));
-			seq_printf(m, "R_AX_SEC_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_ERROR_FLAG));
-			seq_printf(m, "R_AX_SEC_ENG_CTRL=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_ENG_CTRL));
-			seq_printf(m, "R_AX_SEC_MPDU_PROC=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_MPDU_PROC));
-			seq_printf(m, "R_AX_SEC_CAM_ACCESS=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_CAM_ACCESS));
-			seq_printf(m, "R_AX_SEC_CAM_RDATA=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_CAM_RDATA));
-			seq_printf(m, "R_AX_SEC_DEBUG1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_DEBUG1));
-			seq_printf(m, "R_AX_SEC_TX_DEBUG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_TX_DEBUG));
-			seq_printf(m, "R_AX_SEC_RX_DEBUG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_RX_DEBUG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_ERROR_FLAG_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_ERROR_FLAG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_ENG_CTRL=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_ENG_CTRL));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_MPDU_PROC=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_MPDU_PROC));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_CAM_ACCESS=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_CAM_ACCESS));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_CAM_RDATA=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_CAM_RDATA));
+			p += scnprintf(p, end - p, "R_AX_SEC_DEBUG1=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_DEBUG1));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_TX_DEBUG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_TX_DEBUG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_RX_DEBUG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_RX_DEBUG));
 
 			rtw89_write32_mask(rtwdev, R_AX_DBG_CTRL,
 					   B_AX_DBG_SEL0, 0x8B);
@@ -1382,187 +1410,229 @@ static int rtw89_debug_mac_dump_dmac_dbg(struct rtw89_dev *rtwdev,
 			for (i = 0; i < 0x10; i++) {
 				rtw89_write32_mask(rtwdev, R_AX_SEC_ENG_CTRL,
 						   B_AX_SEC_DBG_PORT_FIELD_MASK, i);
-				seq_printf(m, "sel=%x,R_AX_SEC_DEBUG2=0x%08x\n",
-					   i, rtw89_read32(rtwdev, R_AX_SEC_DEBUG2));
+				p += scnprintf(p, end - p,
+					       "sel=%x,R_AX_SEC_DEBUG2=0x%08x\n",
+					       i,
+					       rtw89_read32(rtwdev, R_AX_SEC_DEBUG2));
 			}
 		} else {
-			seq_printf(m, "R_AX_SEC_ERR_IMR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_DEBUG));
-			seq_printf(m, "R_AX_SEC_ENG_CTRL=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_ENG_CTRL));
-			seq_printf(m, "R_AX_SEC_MPDU_PROC=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_MPDU_PROC));
-			seq_printf(m, "R_AX_SEC_CAM_ACCESS=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_CAM_ACCESS));
-			seq_printf(m, "R_AX_SEC_CAM_RDATA=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_CAM_RDATA));
-			seq_printf(m, "R_AX_SEC_CAM_WDATA=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_CAM_WDATA));
-			seq_printf(m, "R_AX_SEC_TX_DEBUG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_TX_DEBUG));
-			seq_printf(m, "R_AX_SEC_RX_DEBUG=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_RX_DEBUG));
-			seq_printf(m, "R_AX_SEC_TRX_PKT_CNT=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_TRX_PKT_CNT));
-			seq_printf(m, "R_AX_SEC_TRX_BLK_CNT=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_SEC_TRX_BLK_CNT));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_ERR_IMR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_DEBUG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_ENG_CTRL=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_ENG_CTRL));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_MPDU_PROC=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_MPDU_PROC));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_CAM_ACCESS=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_CAM_ACCESS));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_CAM_RDATA=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_CAM_RDATA));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_CAM_WDATA=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_CAM_WDATA));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_TX_DEBUG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_TX_DEBUG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_RX_DEBUG=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_RX_DEBUG));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_TRX_PKT_CNT=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_TRX_PKT_CNT));
+			p += scnprintf(p, end - p,
+				       "R_AX_SEC_TRX_BLK_CNT=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_SEC_TRX_BLK_CNT));
 		}
 	}
 
 	if (dmac_err & B_AX_MPDU_ERR_FLAG) {
-		seq_printf(m, "R_AX_MPDU_TX_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_MPDU_TX_ERR_IMR));
-		seq_printf(m, "R_AX_MPDU_TX_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_MPDU_TX_ERR_ISR));
-		seq_printf(m, "R_AX_MPDU_RX_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_MPDU_RX_ERR_IMR));
-		seq_printf(m, "R_AX_MPDU_RX_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_MPDU_RX_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_MPDU_TX_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_MPDU_TX_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_MPDU_TX_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_MPDU_TX_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_MPDU_RX_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_MPDU_RX_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_MPDU_RX_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_MPDU_RX_ERR_ISR));
 	}
 
 	if (dmac_err & B_AX_STA_SCHEDULER_ERR_FLAG) {
-		seq_printf(m, "R_AX_STA_SCHEDULER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_IMR));
-		seq_printf(m, "R_AX_STA_SCHEDULER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_ISR));
+		p += scnprintf(p, end - p,
+			       "R_AX_STA_SCHEDULER_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_IMR));
+		p += scnprintf(p, end - p,
+			       "R_AX_STA_SCHEDULER_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_STA_SCHEDULER_ERR_ISR));
 	}
 
 	if (dmac_err & B_AX_WDE_DLE_ERR_FLAG) {
-		seq_printf(m, "R_AX_WDE_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDE_ERR_IMR));
-		seq_printf(m, "R_AX_WDE_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDE_ERR_ISR));
-		seq_printf(m, "R_AX_PLE_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PLE_ERR_IMR));
-		seq_printf(m, "R_AX_PLE_ERR_FLAG_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_ISR));
+		p += scnprintf(p, end - p, "R_AX_WDE_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDE_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_WDE_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDE_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_PLE_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PLE_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_PLE_ERR_FLAG_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_ISR));
 	}
 
 	if (dmac_err & B_AX_TXPKTCTRL_ERR_FLAG) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_TXPKTCTL_B0_ERRFLAG_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_B0_ERRFLAG_IMR));
-			seq_printf(m, "R_AX_TXPKTCTL_B0_ERRFLAG_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_B0_ERRFLAG_ISR));
-			seq_printf(m, "R_AX_TXPKTCTL_B1_ERRFLAG_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_B1_ERRFLAG_IMR));
-			seq_printf(m, "R_AX_TXPKTCTL_B1_ERRFLAG_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_B1_ERRFLAG_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_B0_ERRFLAG_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_B0_ERRFLAG_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_B0_ERRFLAG_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_B0_ERRFLAG_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_B1_ERRFLAG_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_B1_ERRFLAG_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_B1_ERRFLAG_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_B1_ERRFLAG_ISR));
 		} else {
-			seq_printf(m, "R_AX_TXPKTCTL_ERR_IMR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_ERR_IMR_ISR));
-			seq_printf(m, "R_AX_TXPKTCTL_ERR_IMR_ISR_B1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_TXPKTCTL_ERR_IMR_ISR_B1));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_ERR_IMR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_ERR_IMR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_TXPKTCTL_ERR_IMR_ISR_B1=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_TXPKTCTL_ERR_IMR_ISR_B1));
 		}
 	}
 
 	if (dmac_err & B_AX_PLE_DLE_ERR_FLAG) {
-		seq_printf(m, "R_AX_WDE_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDE_ERR_IMR));
-		seq_printf(m, "R_AX_WDE_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WDE_ERR_ISR));
-		seq_printf(m, "R_AX_PLE_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PLE_ERR_IMR));
-		seq_printf(m, "R_AX_PLE_ERR_FLAG_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_ISR));
-		seq_printf(m, "R_AX_WD_CPUQ_OP_0=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_0));
-		seq_printf(m, "R_AX_WD_CPUQ_OP_1=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_1));
-		seq_printf(m, "R_AX_WD_CPUQ_OP_2=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_2));
-		seq_printf(m, "R_AX_WD_CPUQ_OP_STATUS=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_STATUS));
-		seq_printf(m, "R_AX_PL_CPUQ_OP_0=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_0));
-		seq_printf(m, "R_AX_PL_CPUQ_OP_1=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_1));
-		seq_printf(m, "R_AX_PL_CPUQ_OP_2=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_2));
-		seq_printf(m, "R_AX_PL_CPUQ_OP_STATUS=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_STATUS));
+		p += scnprintf(p, end - p, "R_AX_WDE_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDE_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_WDE_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WDE_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_PLE_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PLE_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_PLE_ERR_FLAG_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PLE_ERR_FLAG_ISR));
+		p += scnprintf(p, end - p, "R_AX_WD_CPUQ_OP_0=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_0));
+		p += scnprintf(p, end - p, "R_AX_WD_CPUQ_OP_1=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_1));
+		p += scnprintf(p, end - p, "R_AX_WD_CPUQ_OP_2=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_2));
+		p += scnprintf(p, end - p, "R_AX_WD_CPUQ_OP_STATUS=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_WD_CPUQ_OP_STATUS));
+		p += scnprintf(p, end - p, "R_AX_PL_CPUQ_OP_0=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_0));
+		p += scnprintf(p, end - p, "R_AX_PL_CPUQ_OP_1=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_1));
+		p += scnprintf(p, end - p, "R_AX_PL_CPUQ_OP_2=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_2));
+		p += scnprintf(p, end - p, "R_AX_PL_CPUQ_OP_STATUS=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PL_CPUQ_OP_STATUS));
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_RX_CTRL0=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL0));
-			seq_printf(m, "R_AX_RX_CTRL1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL1));
-			seq_printf(m, "R_AX_RX_CTRL2=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RX_CTRL2));
+			p += scnprintf(p, end - p, "R_AX_RX_CTRL0=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RX_CTRL0));
+			p += scnprintf(p, end - p, "R_AX_RX_CTRL1=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RX_CTRL1));
+			p += scnprintf(p, end - p, "R_AX_RX_CTRL2=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RX_CTRL2));
 		} else {
-			seq_printf(m, "R_AX_RXDMA_PKT_INFO_0=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_0));
-			seq_printf(m, "R_AX_RXDMA_PKT_INFO_1=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_1));
-			seq_printf(m, "R_AX_RXDMA_PKT_INFO_2=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_2));
+			p += scnprintf(p, end - p,
+				       "R_AX_RXDMA_PKT_INFO_0=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_0));
+			p += scnprintf(p, end - p,
+				       "R_AX_RXDMA_PKT_INFO_1=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_1));
+			p += scnprintf(p, end - p,
+				       "R_AX_RXDMA_PKT_INFO_2=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_RXDMA_PKT_INFO_2));
 		}
 	}
 
 	if (dmac_err & B_AX_PKTIN_ERR_FLAG) {
-		seq_printf(m, "R_AX_PKTIN_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PKTIN_ERR_IMR));
-		seq_printf(m, "R_AX_PKTIN_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_PKTIN_ERR_ISR));
+		p += scnprintf(p, end - p, "R_AX_PKTIN_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PKTIN_ERR_IMR));
+		p += scnprintf(p, end - p, "R_AX_PKTIN_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_PKTIN_ERR_ISR));
 	}
 
 	if (dmac_err & B_AX_DISPATCH_ERR_FLAG) {
-		seq_printf(m, "R_AX_HOST_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_IMR));
-		seq_printf(m, "R_AX_HOST_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_ISR));
-		seq_printf(m, "R_AX_CPU_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_IMR));
-		seq_printf(m, "R_AX_CPU_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_ISR));
-		seq_printf(m, "R_AX_OTHER_DISPATCHER_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_IMR));
-		seq_printf(m, "R_AX_OTHER_DISPATCHER_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_ISR));
+		p += scnprintf(p, end - p,
+			       "R_AX_HOST_DISPATCHER_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_IMR));
+		p += scnprintf(p, end - p,
+			       "R_AX_HOST_DISPATCHER_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_HOST_DISPATCHER_ERR_ISR));
+		p += scnprintf(p, end - p,
+			       "R_AX_CPU_DISPATCHER_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_IMR));
+		p += scnprintf(p, end - p,
+			       "R_AX_CPU_DISPATCHER_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_CPU_DISPATCHER_ERR_ISR));
+		p += scnprintf(p, end - p,
+			       "R_AX_OTHER_DISPATCHER_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_IMR));
+		p += scnprintf(p, end - p,
+			       "R_AX_OTHER_DISPATCHER_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_OTHER_DISPATCHER_ERR_ISR));
 	}
 
 	if (dmac_err & B_AX_BBRPT_ERR_FLAG) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_BBRPT_COM_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_IMR));
-			seq_printf(m, "R_AX_BBRPT_COM_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_ISR));
-			seq_printf(m, "R_AX_BBRPT_CHINFO_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_ISR));
-			seq_printf(m, "R_AX_BBRPT_CHINFO_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_IMR));
-			seq_printf(m, "R_AX_BBRPT_DFS_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_IMR));
-			seq_printf(m, "R_AX_BBRPT_DFS_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_COM_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_COM_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_CHINFO_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_CHINFO_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_DFS_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_DFS_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_ISR));
 		} else {
-			seq_printf(m, "R_AX_BBRPT_COM_ERR_IMR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_IMR_ISR));
-			seq_printf(m, "R_AX_BBRPT_CHINFO_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_ISR));
-			seq_printf(m, "R_AX_BBRPT_CHINFO_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_IMR));
-			seq_printf(m, "R_AX_BBRPT_DFS_ERR_IMR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_IMR));
-			seq_printf(m, "R_AX_BBRPT_DFS_ERR_ISR=0x%08x\n",
-				   rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_COM_ERR_IMR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_COM_ERR_IMR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_CHINFO_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_ISR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_CHINFO_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_CHINFO_ERR_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_DFS_ERR_IMR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_IMR));
+			p += scnprintf(p, end - p,
+				       "R_AX_BBRPT_DFS_ERR_ISR=0x%08x\n",
+				       rtw89_read32(rtwdev, R_AX_BBRPT_DFS_ERR_ISR));
 		}
 	}
 
 	if (dmac_err & B_AX_HAXIDMA_ERR_FLAG && chip->chip_id == RTL8852C) {
-		seq_printf(m, "R_AX_HAXIDMA_ERR_IMR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HAXI_IDCT_MSK));
-		seq_printf(m, "R_AX_HAXIDMA_ERR_ISR=0x%08x\n",
-			   rtw89_read32(rtwdev, R_AX_HAXI_IDCT));
+		p += scnprintf(p, end - p, "R_AX_HAXIDMA_ERR_IMR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_HAXI_IDCT_MSK));
+		p += scnprintf(p, end - p, "R_AX_HAXIDMA_ERR_ISR=0x%08x\n",
+			       rtw89_read32(rtwdev, R_AX_HAXI_IDCT));
 	}
 
-	return 0;
+out:
+	return p - buf;
 }
 
 static int rtw89_debug_mac_dump_cmac_err(struct rtw89_dev *rtwdev,
-					 struct seq_file *m,
+					 char *buf, size_t bufsz,
 					 enum rtw89_mac_idx band)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
+	char *p = buf, *end = buf + bufsz;
 	u32 offset = 0;
 	u32 cmac_err;
 	int ret;
@@ -1570,96 +1640,127 @@ static int rtw89_debug_mac_dump_cmac_err(struct rtw89_dev *rtwdev,
 	ret = rtw89_mac_check_mac_en(rtwdev, band, RTW89_CMAC_SEL);
 	if (ret) {
 		if (band)
-			seq_puts(m, "[CMAC] : CMAC1 not enabled\n");
+			p += scnprintf(p, end - p,
+				       "[CMAC] : CMAC1 not enabled\n");
 		else
-			seq_puts(m, "[CMAC] : CMAC0 not enabled\n");
-		return ret;
+			p += scnprintf(p, end - p,
+				       "[CMAC] : CMAC0 not enabled\n");
+		goto out;
 	}
 
 	if (band)
 		offset = RTW89_MAC_AX_BAND_REG_OFFSET;
 
 	cmac_err = rtw89_read32(rtwdev, R_AX_CMAC_ERR_ISR + offset);
-	seq_printf(m, "R_AX_CMAC_ERR_ISR [%d]=0x%08x\n", band,
-		   rtw89_read32(rtwdev, R_AX_CMAC_ERR_ISR + offset));
-	seq_printf(m, "R_AX_CMAC_FUNC_EN [%d]=0x%08x\n", band,
-		   rtw89_read32(rtwdev, R_AX_CMAC_FUNC_EN + offset));
-	seq_printf(m, "R_AX_CK_EN [%d]=0x%08x\n", band,
-		   rtw89_read32(rtwdev, R_AX_CK_EN + offset));
+	p += scnprintf(p, end - p, "R_AX_CMAC_ERR_ISR [%d]=0x%08x\n", band,
+		       rtw89_read32(rtwdev, R_AX_CMAC_ERR_ISR + offset));
+	p += scnprintf(p, end - p, "R_AX_CMAC_FUNC_EN [%d]=0x%08x\n", band,
+		       rtw89_read32(rtwdev, R_AX_CMAC_FUNC_EN + offset));
+	p += scnprintf(p, end - p, "R_AX_CK_EN [%d]=0x%08x\n", band,
+		       rtw89_read32(rtwdev, R_AX_CK_EN + offset));
 
 	if (cmac_err & B_AX_SCHEDULE_TOP_ERR_IND) {
-		seq_printf(m, "R_AX_SCHEDULE_ERR_IMR [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_SCHEDULE_ERR_IMR + offset));
-		seq_printf(m, "R_AX_SCHEDULE_ERR_ISR [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_SCHEDULE_ERR_ISR + offset));
+		p += scnprintf(p, end - p,
+			       "R_AX_SCHEDULE_ERR_IMR [%d]=0x%08x\n", band,
+			       rtw89_read32(rtwdev, R_AX_SCHEDULE_ERR_IMR + offset));
+		p += scnprintf(p, end - p,
+			       "R_AX_SCHEDULE_ERR_ISR [%d]=0x%08x\n", band,
+			       rtw89_read32(rtwdev, R_AX_SCHEDULE_ERR_ISR + offset));
 	}
 
 	if (cmac_err & B_AX_PTCL_TOP_ERR_IND) {
-		seq_printf(m, "R_AX_PTCL_IMR0 [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_PTCL_IMR0 + offset));
-		seq_printf(m, "R_AX_PTCL_ISR0 [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_PTCL_ISR0 + offset));
+		p += scnprintf(p, end - p, "R_AX_PTCL_IMR0 [%d]=0x%08x\n",
+			       band,
+			       rtw89_read32(rtwdev, R_AX_PTCL_IMR0 + offset));
+		p += scnprintf(p, end - p, "R_AX_PTCL_ISR0 [%d]=0x%08x\n",
+			       band,
+			       rtw89_read32(rtwdev, R_AX_PTCL_ISR0 + offset));
 	}
 
 	if (cmac_err & B_AX_DMA_TOP_ERR_IND) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_RX_ERR_FLAG [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_RX_ERR_FLAG + offset));
-			seq_printf(m, "R_AX_RX_ERR_FLAG_IMR [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_RX_ERR_FLAG_IMR + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_RX_ERR_FLAG [%d]=0x%08x\n", band,
+				       rtw89_read32(rtwdev, R_AX_RX_ERR_FLAG + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_RX_ERR_FLAG_IMR [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev, R_AX_RX_ERR_FLAG_IMR + offset));
 		} else {
-			seq_printf(m, "R_AX_DLE_CTRL [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_DLE_CTRL + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_DLE_CTRL [%d]=0x%08x\n", band,
+				       rtw89_read32(rtwdev, R_AX_DLE_CTRL + offset));
 		}
 	}
 
 	if (cmac_err & B_AX_DMA_TOP_ERR_IND || cmac_err & B_AX_WMAC_RX_ERR_IND) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_PHYINFO_ERR_ISR [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_ISR + offset));
-			seq_printf(m, "R_AX_PHYINFO_ERR_IMR [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_IMR + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_PHYINFO_ERR_ISR [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_ISR + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_PHYINFO_ERR_IMR [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_IMR + offset));
 		} else {
-			seq_printf(m, "R_AX_PHYINFO_ERR_IMR [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_IMR + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_PHYINFO_ERR_IMR [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev, R_AX_PHYINFO_ERR_IMR + offset));
 		}
 	}
 
 	if (cmac_err & B_AX_TXPWR_CTRL_ERR_IND) {
-		seq_printf(m, "R_AX_TXPWR_IMR [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_TXPWR_IMR + offset));
-		seq_printf(m, "R_AX_TXPWR_ISR [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_TXPWR_ISR + offset));
+		p += scnprintf(p, end - p, "R_AX_TXPWR_IMR [%d]=0x%08x\n",
+			       band,
+			       rtw89_read32(rtwdev, R_AX_TXPWR_IMR + offset));
+		p += scnprintf(p, end - p, "R_AX_TXPWR_ISR [%d]=0x%08x\n",
+			       band,
+			       rtw89_read32(rtwdev, R_AX_TXPWR_ISR + offset));
 	}
 
 	if (cmac_err & B_AX_WMAC_TX_ERR_IND) {
 		if (chip->chip_id == RTL8852C) {
-			seq_printf(m, "R_AX_TRXPTCL_ERROR_INDICA [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_TRXPTCL_ERROR_INDICA + offset));
-			seq_printf(m, "R_AX_TRXPTCL_ERROR_INDICA_MASK [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_TRXPTCL_ERROR_INDICA_MASK + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_TRXPTCL_ERROR_INDICA [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev,
+						    R_AX_TRXPTCL_ERROR_INDICA + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_TRXPTCL_ERROR_INDICA_MASK [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev,
+						    R_AX_TRXPTCL_ERROR_INDICA_MASK + offset));
 		} else {
-			seq_printf(m, "R_AX_TMAC_ERR_IMR_ISR [%d]=0x%08x\n", band,
-				   rtw89_read32(rtwdev, R_AX_TMAC_ERR_IMR_ISR + offset));
+			p += scnprintf(p, end - p,
+				       "R_AX_TMAC_ERR_IMR_ISR [%d]=0x%08x\n",
+				       band,
+				       rtw89_read32(rtwdev,
+						    R_AX_TMAC_ERR_IMR_ISR + offset));
 		}
-		seq_printf(m, "R_AX_DBGSEL_TRXPTCL [%d]=0x%08x\n", band,
-			   rtw89_read32(rtwdev, R_AX_DBGSEL_TRXPTCL + offset));
+		p += scnprintf(p, end - p,
+			       "R_AX_DBGSEL_TRXPTCL [%d]=0x%08x\n", band,
+			       rtw89_read32(rtwdev, R_AX_DBGSEL_TRXPTCL + offset));
 	}
 
-	seq_printf(m, "R_AX_CMAC_ERR_IMR [%d]=0x%08x\n", band,
-		   rtw89_read32(rtwdev, R_AX_CMAC_ERR_IMR + offset));
+	p += scnprintf(p, end - p, "R_AX_CMAC_ERR_IMR [%d]=0x%08x\n", band,
+		       rtw89_read32(rtwdev, R_AX_CMAC_ERR_IMR + offset));
 
-	return 0;
+out:
+	return p - buf;
 }
 
 static int rtw89_debug_mac_dump_cmac_dbg(struct rtw89_dev *rtwdev,
-					 struct seq_file *m)
+					 char *buf, size_t bufsz)
 {
-	rtw89_debug_mac_dump_cmac_err(rtwdev, m, RTW89_MAC_0);
+	char *p = buf, *end = buf + bufsz;
+
+	p += rtw89_debug_mac_dump_cmac_err(rtwdev, p, end - p, RTW89_MAC_0);
 	if (rtwdev->dbcc_en)
-		rtw89_debug_mac_dump_cmac_err(rtwdev, m, RTW89_MAC_1);
+		p += rtw89_debug_mac_dump_cmac_err(rtwdev, p, end - p, RTW89_MAC_1);
 
-	return 0;
+	return p - buf;
 }
 
 static const struct rtw89_mac_dbg_port_info dbg_port_ptcl_c0 = {
@@ -2465,11 +2566,12 @@ static const struct rtw89_mac_dbg_port_info dbg_port_pcie_misc2 = {
 	.rd_msk = B_AX_DEBUG_ST_MASK
 };
 
-static const struct rtw89_mac_dbg_port_info *
-rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
-			     struct rtw89_dev *rtwdev, u32 sel)
+static int
+rtw89_debug_mac_dbg_port_sel(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+			     u32 sel, const struct rtw89_mac_dbg_port_info **ppinfo)
 {
-	const struct rtw89_mac_dbg_port_info *info;
+	const struct rtw89_mac_dbg_port_info *info = NULL;
+	char *p = buf, *end = buf + bufsz;
 	u32 index;
 	u32 val32;
 	u16 val16;
@@ -2481,28 +2583,28 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val16 = rtw89_read16(rtwdev, R_AX_PTCL_DBG);
 		val16 |= B_AX_PTCL_DBG_EN;
 		rtw89_write16(rtwdev, R_AX_PTCL_DBG, val16);
-		seq_puts(m, "Enable PTCL C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable PTCL C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PTCL_C1:
 		info = &dbg_port_ptcl_c1;
 		val16 = rtw89_read16(rtwdev, R_AX_PTCL_DBG_C1);
 		val16 |= B_AX_PTCL_DBG_EN;
 		rtw89_write16(rtwdev, R_AX_PTCL_DBG_C1, val16);
-		seq_puts(m, "Enable PTCL C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable PTCL C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_SCH_C0:
 		info = &dbg_port_sch_c0;
 		val32 = rtw89_read32(rtwdev, R_AX_SCH_DBG_SEL);
 		val32 |= B_AX_SCH_DBG_EN;
 		rtw89_write32(rtwdev, R_AX_SCH_DBG_SEL, val32);
-		seq_puts(m, "Enable SCH C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable SCH C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_SCH_C1:
 		info = &dbg_port_sch_c1;
 		val32 = rtw89_read32(rtwdev, R_AX_SCH_DBG_SEL_C1);
 		val32 |= B_AX_SCH_DBG_EN;
 		rtw89_write32(rtwdev, R_AX_SCH_DBG_SEL_C1, val32);
-		seq_puts(m, "Enable SCH C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable SCH C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TMAC_C0:
 		info = &dbg_port_tmac_c0;
@@ -2519,7 +2621,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = rtw89_read32(rtwdev, R_AX_SYS_STATUS1);
 		val32 = u32_replace_bits(val32, MAC_DBG_SEL, B_AX_SEL_0XC0_MASK);
 		rtw89_write32(rtwdev, R_AX_SYS_STATUS1, val32);
-		seq_puts(m, "Enable TMAC C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable TMAC C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TMAC_C1:
 		info = &dbg_port_tmac_c1;
@@ -2536,7 +2638,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = rtw89_read32(rtwdev, R_AX_SYS_STATUS1);
 		val32 = u32_replace_bits(val32, MAC_DBG_SEL, B_AX_SEL_0XC0_MASK);
 		rtw89_write32(rtwdev, R_AX_SYS_STATUS1, val32);
-		seq_puts(m, "Enable TMAC C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable TMAC C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMAC_C0:
 		info = &dbg_port_rmac_c0;
@@ -2558,7 +2660,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val8 = u8_replace_bits(val8, RMAC_CMAC_DBG_SEL,
 				       B_AX_DBGSEL_TRXPTCL_MASK);
 		rtw89_write8(rtwdev, R_AX_DBGSEL_TRXPTCL, val8);
-		seq_puts(m, "Enable RMAC C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMAC_C1:
 		info = &dbg_port_rmac_c1;
@@ -2580,23 +2682,23 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val8 = u8_replace_bits(val8, RMAC_CMAC_DBG_SEL,
 				       B_AX_DBGSEL_TRXPTCL_MASK);
 		rtw89_write8(rtwdev, R_AX_DBGSEL_TRXPTCL_C1, val8);
-		seq_puts(m, "Enable RMAC C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMACST_C0:
 		info = &dbg_port_rmacst_c0;
-		seq_puts(m, "Enable RMAC state C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC state C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMACST_C1:
 		info = &dbg_port_rmacst_c1;
-		seq_puts(m, "Enable RMAC state C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC state C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMAC_PLCP_C0:
 		info = &dbg_port_rmac_plcp_c0;
-		seq_puts(m, "Enable RMAC PLCP C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC PLCP C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_RMAC_PLCP_C1:
 		info = &dbg_port_rmac_plcp_c1;
-		seq_puts(m, "Enable RMAC PLCP C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable RMAC PLCP C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TRXPTCL_C0:
 		info = &dbg_port_trxptcl_c0;
@@ -2608,7 +2710,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = rtw89_read32(rtwdev, R_AX_SYS_STATUS1);
 		val32 = u32_replace_bits(val32, MAC_DBG_SEL, B_AX_SEL_0XC0_MASK);
 		rtw89_write32(rtwdev, R_AX_SYS_STATUS1, val32);
-		seq_puts(m, "Enable TRXPTCL C0 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable TRXPTCL C0 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TRXPTCL_C1:
 		info = &dbg_port_trxptcl_c1;
@@ -2620,131 +2722,137 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = rtw89_read32(rtwdev, R_AX_SYS_STATUS1);
 		val32 = u32_replace_bits(val32, MAC_DBG_SEL, B_AX_SEL_0XC0_MASK);
 		rtw89_write32(rtwdev, R_AX_SYS_STATUS1, val32);
-		seq_puts(m, "Enable TRXPTCL C1 dbgport.\n");
+		p += scnprintf(p, end - p, "Enable TRXPTCL C1 dbgport.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TX_INFOL_C0:
 		info = &dbg_port_tx_infol_c0;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1, val32);
-		seq_puts(m, "Enable tx infol dump.\n");
+		p += scnprintf(p, end - p, "Enable tx infol dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TX_INFOH_C0:
 		info = &dbg_port_tx_infoh_c0;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1, val32);
-		seq_puts(m, "Enable tx infoh dump.\n");
+		p += scnprintf(p, end - p, "Enable tx infoh dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TX_INFOL_C1:
 		info = &dbg_port_tx_infol_c1;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1_C1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1_C1, val32);
-		seq_puts(m, "Enable tx infol dump.\n");
+		p += scnprintf(p, end - p, "Enable tx infol dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TX_INFOH_C1:
 		info = &dbg_port_tx_infoh_c1;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1_C1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1_C1, val32);
-		seq_puts(m, "Enable tx infoh dump.\n");
+		p += scnprintf(p, end - p, "Enable tx infoh dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TXTF_INFOL_C0:
 		info = &dbg_port_txtf_infol_c0;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1, val32);
-		seq_puts(m, "Enable tx tf infol dump.\n");
+		p += scnprintf(p, end - p, "Enable tx tf infol dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TXTF_INFOH_C0:
 		info = &dbg_port_txtf_infoh_c0;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1, val32);
-		seq_puts(m, "Enable tx tf infoh dump.\n");
+		p += scnprintf(p, end - p, "Enable tx tf infoh dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TXTF_INFOL_C1:
 		info = &dbg_port_txtf_infol_c1;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1_C1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1_C1, val32);
-		seq_puts(m, "Enable tx tf infol dump.\n");
+		p += scnprintf(p, end - p, "Enable tx tf infol dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_TXTF_INFOH_C1:
 		info = &dbg_port_txtf_infoh_c1;
 		val32 = rtw89_read32(rtwdev, R_AX_TCR1_C1);
 		val32 |= B_AX_TCR_FORCE_READ_TXDFIFO;
 		rtw89_write32(rtwdev, R_AX_TCR1_C1, val32);
-		seq_puts(m, "Enable tx tf infoh dump.\n");
+		p += scnprintf(p, end - p, "Enable tx tf infoh dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_BUFMGN_FREEPG:
 		info = &dbg_port_wde_bufmgn_freepg;
-		seq_puts(m, "Enable wde bufmgn freepg dump.\n");
+		p += scnprintf(p, end - p, "Enable wde bufmgn freepg dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_BUFMGN_QUOTA:
 		info = &dbg_port_wde_bufmgn_quota;
-		seq_puts(m, "Enable wde bufmgn quota dump.\n");
+		p += scnprintf(p, end - p, "Enable wde bufmgn quota dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_BUFMGN_PAGELLT:
 		info = &dbg_port_wde_bufmgn_pagellt;
-		seq_puts(m, "Enable wde bufmgn pagellt dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable wde bufmgn pagellt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_BUFMGN_PKTINFO:
 		info = &dbg_port_wde_bufmgn_pktinfo;
-		seq_puts(m, "Enable wde bufmgn pktinfo dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable wde bufmgn pktinfo dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_QUEMGN_PREPKT:
 		info = &dbg_port_wde_quemgn_prepkt;
-		seq_puts(m, "Enable wde quemgn prepkt dump.\n");
+		p += scnprintf(p, end - p, "Enable wde quemgn prepkt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_QUEMGN_NXTPKT:
 		info = &dbg_port_wde_quemgn_nxtpkt;
-		seq_puts(m, "Enable wde quemgn nxtpkt dump.\n");
+		p += scnprintf(p, end - p, "Enable wde quemgn nxtpkt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_QUEMGN_QLNKTBL:
 		info = &dbg_port_wde_quemgn_qlnktbl;
-		seq_puts(m, "Enable wde quemgn qlnktbl dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable wde quemgn qlnktbl dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_WDE_QUEMGN_QEMPTY:
 		info = &dbg_port_wde_quemgn_qempty;
-		seq_puts(m, "Enable wde quemgn qempty dump.\n");
+		p += scnprintf(p, end - p, "Enable wde quemgn qempty dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_BUFMGN_FREEPG:
 		info = &dbg_port_ple_bufmgn_freepg;
-		seq_puts(m, "Enable ple bufmgn freepg dump.\n");
+		p += scnprintf(p, end - p, "Enable ple bufmgn freepg dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_BUFMGN_QUOTA:
 		info = &dbg_port_ple_bufmgn_quota;
-		seq_puts(m, "Enable ple bufmgn quota dump.\n");
+		p += scnprintf(p, end - p, "Enable ple bufmgn quota dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_BUFMGN_PAGELLT:
 		info = &dbg_port_ple_bufmgn_pagellt;
-		seq_puts(m, "Enable ple bufmgn pagellt dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable ple bufmgn pagellt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_BUFMGN_PKTINFO:
 		info = &dbg_port_ple_bufmgn_pktinfo;
-		seq_puts(m, "Enable ple bufmgn pktinfo dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable ple bufmgn pktinfo dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_QUEMGN_PREPKT:
 		info = &dbg_port_ple_quemgn_prepkt;
-		seq_puts(m, "Enable ple quemgn prepkt dump.\n");
+		p += scnprintf(p, end - p, "Enable ple quemgn prepkt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_QUEMGN_NXTPKT:
 		info = &dbg_port_ple_quemgn_nxtpkt;
-		seq_puts(m, "Enable ple quemgn nxtpkt dump.\n");
+		p += scnprintf(p, end - p, "Enable ple quemgn nxtpkt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_QUEMGN_QLNKTBL:
 		info = &dbg_port_ple_quemgn_qlnktbl;
-		seq_puts(m, "Enable ple quemgn qlnktbl dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable ple quemgn qlnktbl dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PLE_QUEMGN_QEMPTY:
 		info = &dbg_port_ple_quemgn_qempty;
-		seq_puts(m, "Enable ple quemgn qempty dump.\n");
+		p += scnprintf(p, end - p, "Enable ple quemgn qempty dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PKTINFO:
 		info = &dbg_port_pktinfo;
-		seq_puts(m, "Enable pktinfo dump.\n");
+		p += scnprintf(p, end - p, "Enable pktinfo dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TX0:
 		rtw89_write32_mask(rtwdev, R_AX_DBG_CTRL,
@@ -2763,7 +2871,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, index);
-		seq_printf(m, "Enable Dispatcher hdt tx%x dump.\n", index);
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt tx%x dump.\n", index);
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TX6:
 		info = &dbg_port_dspt_hdt_tx6;
@@ -2771,7 +2880,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 6);
-		seq_puts(m, "Enable Dispatcher hdt tx6 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt tx6 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TX7:
 		info = &dbg_port_dspt_hdt_tx7;
@@ -2779,7 +2889,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 7);
-		seq_puts(m, "Enable Dispatcher hdt tx7 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt tx7 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TX8:
 		info = &dbg_port_dspt_hdt_tx8;
@@ -2787,7 +2898,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 8);
-		seq_puts(m, "Enable Dispatcher hdt tx8 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt tx8 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TX9:
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TXA:
@@ -2799,7 +2911,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, index);
-		seq_printf(m, "Enable Dispatcher hdt tx%x dump.\n", index);
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt tx%x dump.\n", index);
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_TXD:
 		info = &dbg_port_dspt_hdt_txD;
@@ -2807,7 +2920,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 0);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 0xD);
-		seq_puts(m, "Enable Dispatcher hdt txD dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt txD dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX0:
 		info = &dbg_port_dspt_cdt_tx0;
@@ -2815,7 +2929,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 0);
-		seq_puts(m, "Enable Dispatcher cdt tx0 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx0 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX1:
 		info = &dbg_port_dspt_cdt_tx1;
@@ -2823,7 +2938,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 1);
-		seq_puts(m, "Enable Dispatcher cdt tx1 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx1 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX3:
 		info = &dbg_port_dspt_cdt_tx3;
@@ -2831,7 +2947,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 3);
-		seq_puts(m, "Enable Dispatcher cdt tx3 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx3 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX4:
 		info = &dbg_port_dspt_cdt_tx4;
@@ -2839,7 +2956,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 4);
-		seq_puts(m, "Enable Dispatcher cdt tx4 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx4 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX5:
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX6:
@@ -2851,7 +2969,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, index);
-		seq_printf(m, "Enable Dispatcher cdt tx%x dump.\n", index);
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx%x dump.\n", index);
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TX9:
 		info = &dbg_port_dspt_cdt_tx9;
@@ -2859,7 +2978,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 9);
-		seq_puts(m, "Enable Dispatcher cdt tx9 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx9 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TXA:
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_TXB:
@@ -2870,7 +2990,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 1);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, index);
-		seq_printf(m, "Enable Dispatcher cdt tx%x dump.\n", index);
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt tx%x dump.\n", index);
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX0:
 		info = &dbg_port_dspt_hdt_rx0;
@@ -2878,7 +2999,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 2);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 0);
-		seq_puts(m, "Enable Dispatcher hdt rx0 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt rx0 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX1:
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX2:
@@ -2888,7 +3010,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 2);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, index);
-		seq_printf(m, "Enable Dispatcher hdt rx%x dump.\n", index);
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt rx%x dump.\n", index);
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX3:
 		info = &dbg_port_dspt_hdt_rx3;
@@ -2896,7 +3019,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 2);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 3);
-		seq_puts(m, "Enable Dispatcher hdt rx3 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt rx3 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX4:
 		info = &dbg_port_dspt_hdt_rx4;
@@ -2904,7 +3028,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 2);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 4);
-		seq_puts(m, "Enable Dispatcher hdt rx4 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt rx4 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_HDT_RX5:
 		info = &dbg_port_dspt_hdt_rx5;
@@ -2912,7 +3037,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 2);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 5);
-		seq_puts(m, "Enable Dispatcher hdt rx5 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher hdt rx5 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_RX_P0_0:
 		info = &dbg_port_dspt_cdt_rx_p0_0;
@@ -2920,7 +3046,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 3);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 0);
-		seq_puts(m, "Enable Dispatcher cdt rx part0 0 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt rx part0 0 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_RX_P0:
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_RX_P0_1:
@@ -2929,7 +3056,8 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 3);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 1);
-		seq_puts(m, "Enable Dispatcher cdt rx part0 1 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt rx part0 1 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_RX_P0_2:
 		info = &dbg_port_dspt_cdt_rx_p0_2;
@@ -2937,43 +3065,50 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 				   B_AX_DISPATCHER_INTN_SEL_MASK, 3);
 		rtw89_write16_mask(rtwdev, info->sel_addr,
 				   B_AX_DISPATCHER_CH_SEL_MASK, 2);
-		seq_puts(m, "Enable Dispatcher cdt rx part0 2 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt rx part0 2 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_CDT_RX_P1:
 		info = &dbg_port_dspt_cdt_rx_p1;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 3);
-		seq_puts(m, "Enable Dispatcher cdt rx part1 dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher cdt rx part1 dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_STF_CTRL:
 		info = &dbg_port_dspt_stf_ctrl;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 4);
-		seq_puts(m, "Enable Dispatcher stf control dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher stf control dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_ADDR_CTRL:
 		info = &dbg_port_dspt_addr_ctrl;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 5);
-		seq_puts(m, "Enable Dispatcher addr control dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher addr control dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_WDE_INTF:
 		info = &dbg_port_dspt_wde_intf;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 6);
-		seq_puts(m, "Enable Dispatcher wde interface dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher wde interface dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_PLE_INTF:
 		info = &dbg_port_dspt_ple_intf;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 7);
-		seq_puts(m, "Enable Dispatcher ple interface dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher ple interface dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_DSPT_FLOW_CTRL:
 		info = &dbg_port_dspt_flow_ctrl;
 		rtw89_write8_mask(rtwdev, info->sel_addr,
 				  B_AX_DISPATCHER_INTN_SEL_MASK, 8);
-		seq_puts(m, "Enable Dispatcher flow control dump.\n");
+		p += scnprintf(p, end - p,
+			       "Enable Dispatcher flow control dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_TXDMA:
 		info = &dbg_port_pcie_txdma;
@@ -2981,7 +3116,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_TXDMA_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_TXDMA_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie txdma dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie txdma dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_RXDMA:
 		info = &dbg_port_pcie_rxdma;
@@ -2989,7 +3124,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_RXDMA_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_RXDMA_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie rxdma dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie rxdma dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_CVT:
 		info = &dbg_port_pcie_cvt;
@@ -2997,7 +3132,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_CVT_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_CVT_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie cvt dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie cvt dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_CXPL:
 		info = &dbg_port_pcie_cxpl;
@@ -3005,7 +3140,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_CXPL_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_CXPL_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie cxpl dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie cxpl dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_IO:
 		info = &dbg_port_pcie_io;
@@ -3013,7 +3148,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_IO_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_IO_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie io dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie io dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_MISC:
 		info = &dbg_port_pcie_misc;
@@ -3021,7 +3156,7 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val32 = u32_replace_bits(val32, PCIE_MISC_DBG_SEL, B_AX_DBG_SEL0);
 		val32 = u32_replace_bits(val32, PCIE_MISC_DBG_SEL, B_AX_DBG_SEL1);
 		rtw89_write32(rtwdev, R_AX_DBG_CTRL, val32);
-		seq_puts(m, "Enable pcie misc dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie misc dump.\n");
 		break;
 	case RTW89_DBG_PORT_SEL_PCIE_MISC2:
 		info = &dbg_port_pcie_misc2;
@@ -3029,14 +3164,16 @@ rtw89_debug_mac_dbg_port_sel(struct seq_file *m,
 		val16 = u16_replace_bits(val16, PCIE_MISC2_DBG_SEL,
 					 B_AX_PCIE_DBG_SEL_MASK);
 		rtw89_write16(rtwdev, R_AX_PCIE_DBG_CTRL, val16);
-		seq_puts(m, "Enable pcie misc2 dump.\n");
+		p += scnprintf(p, end - p, "Enable pcie misc2 dump.\n");
 		break;
 	default:
-		seq_puts(m, "Dbg port select err\n");
-		return NULL;
+		p += scnprintf(p, end - p, "Dbg port select err\n");
+		break;
 	}
 
-	return info;
+	*ppinfo = info;
+
+	return p - buf;
 }
 
 static bool is_dbg_port_valid(struct rtw89_dev *rtwdev, u32 sel)
@@ -3070,23 +3207,25 @@ static bool is_dbg_port_valid(struct rtw89_dev *rtwdev, u32 sel)
 }
 
 static int rtw89_debug_mac_dbg_port_dump(struct rtw89_dev *rtwdev,
-					 struct seq_file *m, u32 sel)
+					 char *buf, size_t bufsz, u32 sel)
 {
-	const struct rtw89_mac_dbg_port_info *info;
-	u8 val8;
-	u16 val16;
+	const struct rtw89_mac_dbg_port_info *info = NULL;
+	char *p = buf, *end = buf + bufsz;
 	u32 val32;
+	u16 val16;
+	u8 val8;
 	u32 i;
 
-	info = rtw89_debug_mac_dbg_port_sel(m, rtwdev, sel);
+	p += rtw89_debug_mac_dbg_port_sel(rtwdev, p, end - p, sel, &info);
+
 	if (!info) {
 		rtw89_err(rtwdev, "failed to select debug port %d\n", sel);
-		return -EINVAL;
+		goto out;
 	}
 
 #define case_DBG_SEL(__sel) \
 	case RTW89_DBG_PORT_SEL_##__sel: \
-		seq_puts(m, "Dump debug port " #__sel ":\n"); \
+		p += scnprintf(p, end - p, "Dump debug port " #__sel ":\n"); \
 		break
 
 	switch (sel) {
@@ -3182,8 +3321,8 @@ static int rtw89_debug_mac_dbg_port_dump(struct rtw89_dev *rtwdev,
 
 #undef case_DBG_SEL
 
-	seq_printf(m, "Sel addr = 0x%X\n", info->sel_addr);
-	seq_printf(m, "Read addr = 0x%X\n", info->rd_addr);
+	p += scnprintf(p, end - p, "Sel addr = 0x%X\n", info->sel_addr);
+	p += scnprintf(p, end - p, "Read addr = 0x%X\n", info->rd_addr);
 
 	for (i = info->srt; i <= info->end; i++) {
 		switch (info->sel_byte) {
@@ -3191,17 +3330,17 @@ static int rtw89_debug_mac_dbg_port_dump(struct rtw89_dev *rtwdev,
 		default:
 			rtw89_write8_mask(rtwdev, info->sel_addr,
 					  info->sel_msk, i);
-			seq_printf(m, "0x%02X: ", i);
+			p += scnprintf(p, end - p, "0x%02X: ", i);
 			break;
 		case 2:
 			rtw89_write16_mask(rtwdev, info->sel_addr,
 					   info->sel_msk, i);
-			seq_printf(m, "0x%04X: ", i);
+			p += scnprintf(p, end - p, "0x%04X: ", i);
 			break;
 		case 4:
 			rtw89_write32_mask(rtwdev, info->sel_addr,
 					   info->sel_msk, i);
-			seq_printf(m, "0x%04X: ", i);
+			p += scnprintf(p, end - p, "0x%04X: ", i);
 			break;
 		}
 
@@ -3212,77 +3351,75 @@ static int rtw89_debug_mac_dbg_port_dump(struct rtw89_dev *rtwdev,
 		default:
 			val8 = rtw89_read8_mask(rtwdev,
 						info->rd_addr, info->rd_msk);
-			seq_printf(m, "0x%02X\n", val8);
+			p += scnprintf(p, end - p, "0x%02X\n", val8);
 			break;
 		case 2:
 			val16 = rtw89_read16_mask(rtwdev,
 						  info->rd_addr, info->rd_msk);
-			seq_printf(m, "0x%04X\n", val16);
+			p += scnprintf(p, end - p, "0x%04X\n", val16);
 			break;
 		case 4:
 			val32 = rtw89_read32_mask(rtwdev,
 						  info->rd_addr, info->rd_msk);
-			seq_printf(m, "0x%08X\n", val32);
+			p += scnprintf(p, end - p, "0x%08X\n", val32);
 			break;
 		}
 	}
 
-	return 0;
+out:
+	return p - buf;
 }
 
 static int rtw89_debug_mac_dump_dbg_port(struct rtw89_dev *rtwdev,
-					 struct seq_file *m)
+					 char *buf, size_t bufsz)
 {
+	char *p = buf, *end = buf + bufsz;
+	ssize_t n;
 	u32 sel;
-	int ret = 0;
 
 	for (sel = RTW89_DBG_PORT_SEL_PTCL_C0;
 	     sel < RTW89_DBG_PORT_SEL_LAST; sel++) {
 		if (!is_dbg_port_valid(rtwdev, sel))
 			continue;
-		ret = rtw89_debug_mac_dbg_port_dump(rtwdev, m, sel);
-		if (ret) {
+		n = rtw89_debug_mac_dbg_port_dump(rtwdev, p, end - p, sel);
+		if (n < 0) {
 			rtw89_err(rtwdev,
 				  "failed to dump debug port %d\n", sel);
 			break;
 		}
+		p += n;
 	}
 
-	return ret;
+	return p - buf;
 }
 
-static int
-rtw89_debug_priv_mac_dbg_port_dump_get(struct seq_file *m, void *v)
+static ssize_t
+rtw89_debug_priv_mac_dbg_port_dump_get(struct rtw89_dev *rtwdev,
+				       struct rtw89_debugfs_priv *debugfs_priv,
+				       char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	char *p = buf, *end = buf + bufsz;
 
 	if (debugfs_priv->dbgpkg_en.ss_dbg)
-		rtw89_debug_mac_dump_ss_dbg(rtwdev, m);
+		p += rtw89_debug_mac_dump_ss_dbg(rtwdev, p, end - p);
 	if (debugfs_priv->dbgpkg_en.dle_dbg)
-		rtw89_debug_mac_dump_dle_dbg(rtwdev, m);
+		p += rtw89_debug_mac_dump_dle_dbg(rtwdev, p, end - p);
 	if (debugfs_priv->dbgpkg_en.dmac_dbg)
-		rtw89_debug_mac_dump_dmac_dbg(rtwdev, m);
+		p += rtw89_debug_mac_dump_dmac_dbg(rtwdev, p, end - p);
 	if (debugfs_priv->dbgpkg_en.cmac_dbg)
-		rtw89_debug_mac_dump_cmac_dbg(rtwdev, m);
+		p += rtw89_debug_mac_dump_cmac_dbg(rtwdev, p, end - p);
 	if (debugfs_priv->dbgpkg_en.dbg_port)
-		rtw89_debug_mac_dump_dbg_port(rtwdev, m);
+		p += rtw89_debug_mac_dump_dbg_port(rtwdev, p, end - p);
 
-	return 0;
+	return p - buf;
 };
 
-static u8 *rtw89_hex2bin_user(struct rtw89_dev *rtwdev,
-			      const char __user *user_buf, size_t count)
+static u8 *rtw89_hex2bin(struct rtw89_dev *rtwdev, const char *buf, size_t count)
 {
-	char *buf;
 	u8 *bin;
 	int num;
 	int err = 0;
 
-	buf = memdup_user(user_buf, count);
-	if (IS_ERR(buf))
-		return buf;
-
 	num = count / 2;
 	bin = kmalloc(num, GFP_KERNEL);
 	if (!bin) {
@@ -3297,22 +3434,18 @@ static u8 *rtw89_hex2bin_user(struct rtw89_dev *rtwdev,
 	}
 
 out:
-	kfree(buf);
-
 	return err ? ERR_PTR(err) : bin;
 }
 
-static ssize_t rtw89_debug_priv_send_h2c_set(struct file *filp,
-					     const char __user *user_buf,
-					     size_t count, loff_t *loff)
+static ssize_t rtw89_debug_priv_send_h2c_set(struct rtw89_dev *rtwdev,
+					     struct rtw89_debugfs_priv *debugfs_priv,
+					     const char *buf, size_t count)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	u8 *h2c;
 	int ret;
 	u16 h2c_len = count / 2;
 
-	h2c = rtw89_hex2bin_user(rtwdev, user_buf, count);
+	h2c = rtw89_hex2bin(rtwdev, buf, count);
 	if (IS_ERR(h2c))
 		return -EFAULT;
 
@@ -3323,34 +3456,34 @@ static ssize_t rtw89_debug_priv_send_h2c_set(struct file *filp,
 	return ret ? ret : count;
 }
 
-static int
-rtw89_debug_priv_early_h2c_get(struct seq_file *m, void *v)
+static ssize_t
+rtw89_debug_priv_early_h2c_get(struct rtw89_dev *rtwdev,
+			       struct rtw89_debugfs_priv *debugfs_priv,
+			       char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_early_h2c *early_h2c;
+	char *p = buf, *end = buf + bufsz;
 	int seq = 0;
 
 	mutex_lock(&rtwdev->mutex);
 	list_for_each_entry(early_h2c, &rtwdev->early_h2c_list, list)
-		seq_printf(m, "%d: %*ph\n", ++seq, early_h2c->h2c_len, early_h2c->h2c);
+		p += scnprintf(p, end - p, "%d: %*ph\n", ++seq,
+			       early_h2c->h2c_len, early_h2c->h2c);
 	mutex_unlock(&rtwdev->mutex);
 
-	return 0;
+	return p - buf;
 }
 
 static ssize_t
-rtw89_debug_priv_early_h2c_set(struct file *filp, const char __user *user_buf,
-			       size_t count, loff_t *loff)
+rtw89_debug_priv_early_h2c_set(struct rtw89_dev *rtwdev,
+			       struct rtw89_debugfs_priv *debugfs_priv,
+			       const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_early_h2c *early_h2c;
 	u8 *h2c;
 	u16 h2c_len = count / 2;
 
-	h2c = rtw89_hex2bin_user(rtwdev, user_buf, count);
+	h2c = rtw89_hex2bin(rtwdev, buf, count);
 	if (IS_ERR(h2c))
 		return -EFAULT;
 
@@ -3404,15 +3537,16 @@ static int rtw89_dbg_trigger_ctrl_error(struct rtw89_dev *rtwdev)
 	return 0;
 }
 
-static int
-rtw89_debug_priv_fw_crash_get(struct seq_file *m, void *v)
+static ssize_t
+rtw89_debug_priv_fw_crash_get(struct rtw89_dev *rtwdev,
+			      struct rtw89_debugfs_priv *debugfs_priv,
+			      char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	char *p = buf, *end = buf + bufsz;
 
-	seq_printf(m, "%d\n",
-		   test_bit(RTW89_FLAG_CRASH_SIMULATING, rtwdev->flags));
-	return 0;
+	p += scnprintf(p, end - p, "%d\n",
+		       test_bit(RTW89_FLAG_CRASH_SIMULATING, rtwdev->flags));
+	return p - buf;
 }
 
 enum rtw89_dbg_crash_simulation_type {
@@ -3421,17 +3555,15 @@ enum rtw89_dbg_crash_simulation_type {
 };
 
 static ssize_t
-rtw89_debug_priv_fw_crash_set(struct file *filp, const char __user *user_buf,
-			      size_t count, loff_t *loff)
+rtw89_debug_priv_fw_crash_set(struct rtw89_dev *rtwdev,
+			      struct rtw89_debugfs_priv *debugfs_priv,
+			      const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	int (*sim)(struct rtw89_dev *rtwdev);
 	u8 crash_type;
 	int ret;
 
-	ret = kstrtou8_from_user(user_buf, count, 0, &crash_type);
+	ret = kstrtou8(buf, 0, &crash_type);
 	if (ret)
 		return -EINVAL;
 
@@ -3459,27 +3591,22 @@ rtw89_debug_priv_fw_crash_set(struct file *filp, const char __user *user_buf,
 	return count;
 }
 
-static int rtw89_debug_priv_btc_info_get(struct seq_file *m, void *v)
+static ssize_t rtw89_debug_priv_btc_info_get(struct rtw89_dev *rtwdev,
+					     struct rtw89_debugfs_priv *debugfs_priv,
+					     char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-
-	rtw89_btc_dump_info(rtwdev, m);
-
-	return 0;
+	return rtw89_btc_dump_info(rtwdev, buf, bufsz);
 }
 
-static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp,
-					       const char __user *user_buf,
-					       size_t count, loff_t *loff)
+static ssize_t rtw89_debug_priv_btc_manual_set(struct rtw89_dev *rtwdev,
+					       struct rtw89_debugfs_priv *debugfs_priv,
+					       const char *buf, size_t count)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_btc *btc = &rtwdev->btc;
 	const struct rtw89_btc_ver *ver = btc->ver;
 	int ret;
 
-	ret = kstrtobool_from_user(user_buf, count, &btc->manual_ctrl);
+	ret = kstrtobool(buf, &btc->manual_ctrl);
 	if (ret)
 		return ret;
 
@@ -3491,16 +3618,14 @@ static ssize_t rtw89_debug_priv_btc_manual_set(struct file *filp,
 	return count;
 }
 
-static ssize_t rtw89_debug_priv_fw_log_manual_set(struct file *filp,
-						  const char __user *user_buf,
-						  size_t count, loff_t *loff)
+static ssize_t rtw89_debug_priv_fw_log_manual_set(struct rtw89_dev *rtwdev,
+						  struct rtw89_debugfs_priv *debugfs_priv,
+						  const char *buf, size_t count)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = filp->private_data;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_fw_log *log = &rtwdev->fw.log;
 	bool fw_log_manual;
 
-	if (kstrtobool_from_user(user_buf, count, &fw_log_manual))
+	if (kstrtobool(buf, &fw_log_manual))
 		goto out;
 
 	mutex_lock(&rtwdev->mutex);
@@ -3513,9 +3638,9 @@ static ssize_t rtw89_debug_priv_fw_log_manual_set(struct file *filp,
 	return count;
 }
 
-static void rtw89_sta_link_info_get_iter(struct seq_file *m,
-					 struct rtw89_dev *rtwdev,
-					 struct rtw89_sta_link *rtwsta_link)
+static int rtw89_sta_link_info_get_iter(struct rtw89_dev *rtwdev,
+					char *buf, size_t bufsz,
+					struct rtw89_sta_link *rtwsta_link)
 {
 	static const char * const he_gi_str[] = {
 		[NL80211_RATE_INFO_HE_GI_0_8] = "0.8",
@@ -3533,6 +3658,7 @@ static void rtw89_sta_link_info_get_iter(struct seq_file *m,
 	u8 ant_num = hal->ant_diversity ? 2 : rtwdev->chip->rf_path_num;
 	bool ant_asterisk = hal->tx_path_diversity || hal->ant_diversity;
 	struct ieee80211_link_sta *link_sta;
+	char *p = buf, *end = buf + bufsz;
 	u8 evm_min, evm_max, evm_1ss;
 	u16 max_rc_amsdu_len;
 	u8 rssi;
@@ -3546,107 +3672,136 @@ static void rtw89_sta_link_info_get_iter(struct seq_file *m,
 
 	rcu_read_unlock();
 
-	seq_printf(m, "TX rate [%u, %u]: ", rtwsta_link->mac_id, rtwsta_link->link_id);
+	p += scnprintf(p, end - p, "TX rate [%u, %u]: ", rtwsta_link->mac_id,
+		       rtwsta_link->link_id);
 
 	if (rate->flags & RATE_INFO_FLAGS_MCS)
-		seq_printf(m, "HT MCS-%d%s", rate->mcs,
-			   rate->flags & RATE_INFO_FLAGS_SHORT_GI ? " SGI" : "");
+		p += scnprintf(p, end - p, "HT MCS-%d%s", rate->mcs,
+			       rate->flags & RATE_INFO_FLAGS_SHORT_GI ? " SGI" : "");
 	else if (rate->flags & RATE_INFO_FLAGS_VHT_MCS)
-		seq_printf(m, "VHT %dSS MCS-%d%s", rate->nss, rate->mcs,
-			   rate->flags & RATE_INFO_FLAGS_SHORT_GI ? " SGI" : "");
+		p += scnprintf(p, end - p, "VHT %dSS MCS-%d%s", rate->nss,
+			       rate->mcs,
+			       rate->flags & RATE_INFO_FLAGS_SHORT_GI ? " SGI" : "");
 	else if (rate->flags & RATE_INFO_FLAGS_HE_MCS)
-		seq_printf(m, "HE %dSS MCS-%d GI:%s", rate->nss, rate->mcs,
-			   rate->he_gi <= NL80211_RATE_INFO_HE_GI_3_2 ?
-			   he_gi_str[rate->he_gi] : "N/A");
+		p += scnprintf(p, end - p, "HE %dSS MCS-%d GI:%s", rate->nss,
+			       rate->mcs,
+			       rate->he_gi <= NL80211_RATE_INFO_HE_GI_3_2 ?
+			       he_gi_str[rate->he_gi] : "N/A");
 	else if (rate->flags & RATE_INFO_FLAGS_EHT_MCS)
-		seq_printf(m, "EHT %dSS MCS-%d GI:%s", rate->nss, rate->mcs,
-			   rate->eht_gi < ARRAY_SIZE(eht_gi_str) ?
-			   eht_gi_str[rate->eht_gi] : "N/A");
+		p += scnprintf(p, end - p, "EHT %dSS MCS-%d GI:%s", rate->nss,
+			       rate->mcs,
+			       rate->eht_gi < ARRAY_SIZE(eht_gi_str) ?
+			       eht_gi_str[rate->eht_gi] : "N/A");
 	else
-		seq_printf(m, "Legacy %d", rate->legacy);
-	seq_printf(m, "%s", rtwsta_link->ra_report.might_fallback_legacy ? " FB_G" : "");
-	seq_printf(m, " BW:%u", rtw89_rate_info_bw_to_mhz(rate->bw));
-	seq_printf(m, " (hw_rate=0x%x)", rtwsta_link->ra_report.hw_rate);
-	seq_printf(m, " ==> agg_wait=%d (%d)\n", rtwsta_link->max_agg_wait,
-		   max_rc_amsdu_len);
-
-	seq_printf(m, "RX rate [%u, %u]: ", rtwsta_link->mac_id, rtwsta_link->link_id);
+		p += scnprintf(p, end - p, "Legacy %d", rate->legacy);
+	p += scnprintf(p, end - p, "%s",
+		       rtwsta_link->ra_report.might_fallback_legacy ? " FB_G" : "");
+	p += scnprintf(p, end - p, " BW:%u",
+		       rtw89_rate_info_bw_to_mhz(rate->bw));
+	p += scnprintf(p, end - p, " (hw_rate=0x%x)",
+		       rtwsta_link->ra_report.hw_rate);
+	p += scnprintf(p, end - p, " ==> agg_wait=%d (%d)\n",
+		       rtwsta_link->max_agg_wait,
+		       max_rc_amsdu_len);
+
+	p += scnprintf(p, end - p, "RX rate [%u, %u]: ", rtwsta_link->mac_id,
+		       rtwsta_link->link_id);
 
 	switch (status->encoding) {
 	case RX_ENC_LEGACY:
-		seq_printf(m, "Legacy %d", status->rate_idx +
-			   (status->band != NL80211_BAND_2GHZ ? 4 : 0));
+		p += scnprintf(p, end - p, "Legacy %d", status->rate_idx +
+			       (status->band != NL80211_BAND_2GHZ ? 4 : 0));
 		break;
 	case RX_ENC_HT:
-		seq_printf(m, "HT MCS-%d%s", status->rate_idx,
-			   status->enc_flags & RX_ENC_FLAG_SHORT_GI ? " SGI" : "");
+		p += scnprintf(p, end - p, "HT MCS-%d%s", status->rate_idx,
+			       status->enc_flags & RX_ENC_FLAG_SHORT_GI ? " SGI" : "");
 		break;
 	case RX_ENC_VHT:
-		seq_printf(m, "VHT %dSS MCS-%d%s", status->nss, status->rate_idx,
-			   status->enc_flags & RX_ENC_FLAG_SHORT_GI ? " SGI" : "");
+		p += scnprintf(p, end - p, "VHT %dSS MCS-%d%s", status->nss,
+			       status->rate_idx,
+			       status->enc_flags & RX_ENC_FLAG_SHORT_GI ? " SGI" : "");
 		break;
 	case RX_ENC_HE:
-		seq_printf(m, "HE %dSS MCS-%d GI:%s", status->nss, status->rate_idx,
-			   status->he_gi <= NL80211_RATE_INFO_HE_GI_3_2 ?
-			   he_gi_str[status->he_gi] : "N/A");
+		p += scnprintf(p, end - p, "HE %dSS MCS-%d GI:%s",
+			       status->nss, status->rate_idx,
+			       status->he_gi <= NL80211_RATE_INFO_HE_GI_3_2 ?
+			       he_gi_str[status->he_gi] : "N/A");
 		break;
 	case RX_ENC_EHT:
-		seq_printf(m, "EHT %dSS MCS-%d GI:%s", status->nss, status->rate_idx,
-			   status->eht.gi < ARRAY_SIZE(eht_gi_str) ?
-			   eht_gi_str[status->eht.gi] : "N/A");
+		p += scnprintf(p, end - p, "EHT %dSS MCS-%d GI:%s",
+			       status->nss, status->rate_idx,
+			       status->eht.gi < ARRAY_SIZE(eht_gi_str) ?
+			       eht_gi_str[status->eht.gi] : "N/A");
 		break;
 	}
-	seq_printf(m, " BW:%u", rtw89_rate_info_bw_to_mhz(status->bw));
-	seq_printf(m, " (hw_rate=0x%x)\n", rtwsta_link->rx_hw_rate);
+	p += scnprintf(p, end - p, " BW:%u",
+		       rtw89_rate_info_bw_to_mhz(status->bw));
+	p += scnprintf(p, end - p, " (hw_rate=0x%x)\n",
+		       rtwsta_link->rx_hw_rate);
 
 	rssi = ewma_rssi_read(&rtwsta_link->avg_rssi);
-	seq_printf(m, "RSSI: %d dBm (raw=%d, prev=%d) [",
-		   RTW89_RSSI_RAW_TO_DBM(rssi), rssi, rtwsta_link->prev_rssi);
+	p += scnprintf(p, end - p, "RSSI: %d dBm (raw=%d, prev=%d) [",
+		       RTW89_RSSI_RAW_TO_DBM(rssi), rssi,
+		       rtwsta_link->prev_rssi);
 	for (i = 0; i < ant_num; i++) {
 		rssi = ewma_rssi_read(&rtwsta_link->rssi[i]);
-		seq_printf(m, "%d%s%s", RTW89_RSSI_RAW_TO_DBM(rssi),
-			   ant_asterisk && (hal->antenna_tx & BIT(i)) ? "*" : "",
-			   i + 1 == ant_num ? "" : ", ");
+		p += scnprintf(p, end - p, "%d%s%s",
+			       RTW89_RSSI_RAW_TO_DBM(rssi),
+			       ant_asterisk && (hal->antenna_tx & BIT(i)) ? "*" : "",
+			       i + 1 == ant_num ? "" : ", ");
 	}
-	seq_puts(m, "]\n");
+	p += scnprintf(p, end - p, "]\n");
 
 	evm_1ss = ewma_evm_read(&rtwsta_link->evm_1ss);
-	seq_printf(m, "EVM: [%2u.%02u, ", evm_1ss >> 2, (evm_1ss & 0x3) * 25);
+	p += scnprintf(p, end - p, "EVM: [%2u.%02u, ", evm_1ss >> 2,
+		       (evm_1ss & 0x3) * 25);
 	for (i = 0; i < (hal->ant_diversity ? 2 : 1); i++) {
 		evm_min = ewma_evm_read(&rtwsta_link->evm_min[i]);
 		evm_max = ewma_evm_read(&rtwsta_link->evm_max[i]);
 
-		seq_printf(m, "%s(%2u.%02u, %2u.%02u)", i == 0 ? "" : " ",
-			   evm_min >> 2, (evm_min & 0x3) * 25,
-			   evm_max >> 2, (evm_max & 0x3) * 25);
+		p += scnprintf(p, end - p, "%s(%2u.%02u, %2u.%02u)",
+			       i == 0 ? "" : " ",
+			       evm_min >> 2, (evm_min & 0x3) * 25,
+			       evm_max >> 2, (evm_max & 0x3) * 25);
 	}
-	seq_puts(m, "]\t");
+	p += scnprintf(p, end - p, "]\t");
 
 	snr = ewma_snr_read(&rtwsta_link->avg_snr);
-	seq_printf(m, "SNR: %u\n", snr);
+	p += scnprintf(p, end - p, "SNR: %u\n", snr);
+
+	return p - buf;
 }
 
 static void rtw89_sta_info_get_iter(void *data, struct ieee80211_sta *sta)
 {
-	struct seq_file *m = (struct seq_file *)data;
+	struct rtw89_debugfs_iter_data *iter_data =
+		(struct rtw89_debugfs_iter_data *)data;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_dev *rtwdev = rtwsta->rtwdev;
 	struct rtw89_sta_link *rtwsta_link;
+	size_t bufsz = iter_data->bufsz;
+	char *buf = iter_data->buf;
+	char *p = buf, *end = buf + bufsz;
 	unsigned int link_id;
 
 	rtw89_sta_for_each_link(rtwsta, rtwsta_link, link_id)
-		rtw89_sta_link_info_get_iter(m, rtwdev, rtwsta_link);
+		p += rtw89_sta_link_info_get_iter(rtwdev, p, end - p, rtwsta_link);
+
+	rtw89_debugfs_iter_data_next(iter_data, p, end - p, p - buf);
 }
 
-static void
-rtw89_debug_append_rx_rate(struct seq_file *m, struct rtw89_pkt_stat *pkt_stat,
+static int
+rtw89_debug_append_rx_rate(char *buf, size_t bufsz, struct rtw89_pkt_stat *pkt_stat,
 			   enum rtw89_hw_rate first_rate, int len)
 {
+	char *p = buf, *end = buf + bufsz;
 	int i;
 
 	for (i = 0; i < len; i++)
-		seq_printf(m, "%s%u", i == 0 ? "" : ", ",
-			   pkt_stat->rx_rate_cnt[first_rate + i]);
+		p += scnprintf(p, end - p, "%s%u", i == 0 ? "" : ", ",
+			       pkt_stat->rx_rate_cnt[first_rate + i]);
+
+	return p - buf;
 }
 
 #define FIRST_RATE_SAME(rate) {RTW89_HW_RATE_ ## rate, RTW89_HW_RATE_ ## rate}
@@ -3671,34 +3826,40 @@ static const struct rtw89_rx_rate_cnt_info {
 	{FIRST_RATE_GEV1(EHT_NSS2_MCS0), 14, 0, "EHT 2SS:"},
 };
 
-static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
+static ssize_t rtw89_debug_priv_phy_info_get(struct rtw89_dev *rtwdev,
+					     struct rtw89_debugfs_priv *debugfs_priv,
+					     char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_traffic_stats *stats = &rtwdev->stats;
 	struct rtw89_pkt_stat *pkt_stat = &rtwdev->phystat.last_pkt_stat;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_debugfs_iter_data iter_data;
 	const struct rtw89_rx_rate_cnt_info *info;
 	struct rtw89_hal *hal = &rtwdev->hal;
+	char *p = buf, *end = buf + bufsz;
 	enum rtw89_hw_rate first_rate;
 	u8 rssi;
 	int i;
 
 	rssi = ewma_rssi_read(&rtwdev->phystat.bcn_rssi);
 
-	seq_printf(m, "TP TX: %u [%u] Mbps (lv: %d",
-		   stats->tx_throughput, stats->tx_throughput_raw, stats->tx_tfc_lv);
+	p += scnprintf(p, end - p, "TP TX: %u [%u] Mbps (lv: %d",
+		       stats->tx_throughput, stats->tx_throughput_raw,
+		       stats->tx_tfc_lv);
 	if (hal->thermal_prot_lv)
-		seq_printf(m, ", duty: %d%%",
-			   100 - hal->thermal_prot_lv * RTW89_THERMAL_PROT_STEP);
-	seq_printf(m, "), RX: %u [%u] Mbps (lv: %d)\n",
-		   stats->rx_throughput, stats->rx_throughput_raw, stats->rx_tfc_lv);
-	seq_printf(m, "Beacon: %u (%d dBm), TF: %u\n", pkt_stat->beacon_nr,
-		   RTW89_RSSI_RAW_TO_DBM(rssi), stats->rx_tf_periodic);
-	seq_printf(m, "Avg packet length: TX=%u, RX=%u\n", stats->tx_avg_len,
-		   stats->rx_avg_len);
-
-	seq_puts(m, "RX count:\n");
+		p += scnprintf(p, end - p, ", duty: %d%%",
+			       100 - hal->thermal_prot_lv * RTW89_THERMAL_PROT_STEP);
+	p += scnprintf(p, end - p, "), RX: %u [%u] Mbps (lv: %d)\n",
+		       stats->rx_throughput, stats->rx_throughput_raw,
+		       stats->rx_tfc_lv);
+	p += scnprintf(p, end - p, "Beacon: %u (%d dBm), TF: %u\n",
+		       pkt_stat->beacon_nr,
+		       RTW89_RSSI_RAW_TO_DBM(rssi), stats->rx_tf_periodic);
+	p += scnprintf(p, end - p, "Avg packet length: TX=%u, RX=%u\n",
+		       stats->tx_avg_len,
+		       stats->rx_avg_len);
+
+	p += scnprintf(p, end - p, "RX count:\n");
 
 	for (i = 0; i < ARRAY_SIZE(rtw89_rx_rate_cnt_infos); i++) {
 		info = &rtw89_rx_rate_cnt_infos[i];
@@ -3706,189 +3867,240 @@ static int rtw89_debug_priv_phy_info_get(struct seq_file *m, void *v)
 		if (first_rate >= RTW89_HW_RATE_NR)
 			continue;
 
-		seq_printf(m, "%10s [", info->rate_mode);
-		rtw89_debug_append_rx_rate(m, pkt_stat,
-					   first_rate, info->len);
+		p += scnprintf(p, end - p, "%10s [", info->rate_mode);
+		p += rtw89_debug_append_rx_rate(p, end - p, pkt_stat,
+						first_rate, info->len);
 		if (info->ext) {
-			seq_puts(m, "][");
-			rtw89_debug_append_rx_rate(m, pkt_stat,
-						   first_rate + info->len, info->ext);
+			p += scnprintf(p, end - p, "][");
+			p += rtw89_debug_append_rx_rate(p, end - p, pkt_stat,
+							first_rate + info->len, info->ext);
 		}
-		seq_puts(m, "]\n");
+		p += scnprintf(p, end - p, "]\n");
 	}
 
-	ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_info_get_iter, m);
+	rtw89_debugfs_iter_data_setup(&iter_data, p, end - p);
+	ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_info_get_iter, &iter_data);
+	p += iter_data.written_sz;
 
-	return 0;
+	return p - buf;
 }
 
-static void rtw89_dump_addr_cam(struct seq_file *m,
-				struct rtw89_dev *rtwdev,
-				struct rtw89_addr_cam_entry *addr_cam)
+static int rtw89_dump_addr_cam(struct rtw89_dev *rtwdev,
+			       char *buf, size_t bufsz,
+			       struct rtw89_addr_cam_entry *addr_cam)
 {
 	struct rtw89_cam_info *cam_info = &rtwdev->cam_info;
 	const struct rtw89_sec_cam_entry *sec_entry;
+	char *p = buf, *end = buf + bufsz;
 	u8 sec_cam_idx;
 	int i;
 
-	seq_printf(m, "\taddr_cam_idx=%u\n", addr_cam->addr_cam_idx);
-	seq_printf(m, "\t-> bssid_cam_idx=%u\n", addr_cam->bssid_cam_idx);
-	seq_printf(m, "\tsec_cam_bitmap=%*ph\n", (int)sizeof(addr_cam->sec_cam_map),
-		   addr_cam->sec_cam_map);
+	p += scnprintf(p, end - p, "\taddr_cam_idx=%u\n",
+		       addr_cam->addr_cam_idx);
+	p += scnprintf(p, end - p, "\t-> bssid_cam_idx=%u\n",
+		       addr_cam->bssid_cam_idx);
+	p += scnprintf(p, end - p, "\tsec_cam_bitmap=%*ph\n",
+		       (int)sizeof(addr_cam->sec_cam_map),
+		       addr_cam->sec_cam_map);
 	for_each_set_bit(i, addr_cam->sec_cam_map, RTW89_SEC_CAM_IN_ADDR_CAM) {
 		sec_cam_idx = addr_cam->sec_ent[i];
 		sec_entry = cam_info->sec_entries[sec_cam_idx];
 		if (!sec_entry)
 			continue;
-		seq_printf(m, "\tsec[%d]: sec_cam_idx %u", i, sec_entry->sec_cam_idx);
+		p += scnprintf(p, end - p, "\tsec[%d]: sec_cam_idx %u", i,
+			       sec_entry->sec_cam_idx);
 		if (sec_entry->ext_key)
-			seq_printf(m, ", %u", sec_entry->sec_cam_idx + 1);
-		seq_puts(m, "\n");
+			p += scnprintf(p, end - p, ", %u",
+				       sec_entry->sec_cam_idx + 1);
+		p += scnprintf(p, end - p, "\n");
 	}
+
+	return p - buf;
 }
 
-__printf(3, 4)
-static void rtw89_dump_pkt_offload(struct seq_file *m, struct list_head *pkt_list,
-				   const char *fmt, ...)
+__printf(4, 5)
+static int rtw89_dump_pkt_offload(char *buf, size_t bufsz, struct list_head *pkt_list,
+				  const char *fmt, ...)
 {
+	char *p = buf, *end = buf + bufsz;
 	struct rtw89_pktofld_info *info;
 	struct va_format vaf;
 	va_list args;
 
 	if (list_empty(pkt_list))
-		return;
+		return 0;
 
 	va_start(args, fmt);
 	vaf.va = &args;
 	vaf.fmt = fmt;
 
-	seq_printf(m, "%pV", &vaf);
+	p += scnprintf(p, end - p, "%pV", &vaf);
 
 	va_end(args);
 
 	list_for_each_entry(info, pkt_list, list)
-		seq_printf(m, "%d ", info->id);
+		p += scnprintf(p, end - p, "%d ", info->id);
+
+	p += scnprintf(p, end - p, "\n");
 
-	seq_puts(m, "\n");
+	return p - buf;
 }
 
-static void rtw89_vif_link_ids_get(struct seq_file *m, u8 *mac,
-				   struct rtw89_dev *rtwdev,
-				   struct rtw89_vif_link *rtwvif_link)
+static int rtw89_vif_link_ids_get(struct rtw89_dev *rtwdev,
+				  char *buf, size_t bufsz, u8 *mac,
+				  struct rtw89_vif_link *rtwvif_link)
 {
 	struct rtw89_bssid_cam_entry *bssid_cam = &rtwvif_link->bssid_cam;
-
-	seq_printf(m, "    [%u] %pM\n", rtwvif_link->mac_id, rtwvif_link->mac_addr);
-	seq_printf(m, "\tlink_id=%u\n", rtwvif_link->link_id);
-	seq_printf(m, "\tbssid_cam_idx=%u\n", bssid_cam->bssid_cam_idx);
-	rtw89_dump_addr_cam(m, rtwdev, &rtwvif_link->addr_cam);
-	rtw89_dump_pkt_offload(m, &rtwvif_link->general_pkt_list,
-			       "\tpkt_ofld[GENERAL]: ");
+	char *p = buf, *end = buf + bufsz;
+
+	p += scnprintf(p, end - p, "    [%u] %pM\n", rtwvif_link->mac_id,
+		       rtwvif_link->mac_addr);
+	p += scnprintf(p, end - p, "\tlink_id=%u\n", rtwvif_link->link_id);
+	p += scnprintf(p, end - p, "\tbssid_cam_idx=%u\n",
+		       bssid_cam->bssid_cam_idx);
+	p += rtw89_dump_addr_cam(rtwdev, p, end - p, &rtwvif_link->addr_cam);
+	p += rtw89_dump_pkt_offload(p, end - p, &rtwvif_link->general_pkt_list,
+				    "\tpkt_ofld[GENERAL]: ");
+
+	return p - buf;
 }
 
 static
 void rtw89_vif_ids_get_iter(void *data, u8 *mac, struct ieee80211_vif *vif)
 {
-	struct seq_file *m = (struct seq_file *)data;
+	struct rtw89_debugfs_iter_data *iter_data =
+		(struct rtw89_debugfs_iter_data *)data;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
 	struct rtw89_vif_link *rtwvif_link;
+	size_t bufsz = iter_data->bufsz;
+	char *buf = iter_data->buf;
+	char *p = buf, *end = buf + bufsz;
 	unsigned int link_id;
 
-	seq_printf(m, "VIF %pM\n", rtwvif->mac_addr);
+	p += scnprintf(p, end - p, "VIF %pM\n", rtwvif->mac_addr);
 	rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id)
-		rtw89_vif_link_ids_get(m, mac, rtwdev, rtwvif_link);
+		p += rtw89_vif_link_ids_get(rtwdev, p, end - p, mac, rtwvif_link);
+
+	rtw89_debugfs_iter_data_next(iter_data, p, end - p, p - buf);
 }
 
-static void rtw89_dump_ba_cam(struct seq_file *m, struct rtw89_dev *rtwdev,
-			      struct rtw89_sta_link *rtwsta_link)
+static int rtw89_dump_ba_cam(struct rtw89_dev *rtwdev,
+			     char *buf, size_t bufsz,
+			     struct rtw89_sta_link *rtwsta_link)
 {
 	struct rtw89_ba_cam_entry *entry;
+	char *p = buf, *end = buf + bufsz;
 	bool first = true;
 
 	list_for_each_entry(entry, &rtwsta_link->ba_cam_list, list) {
 		if (first) {
-			seq_puts(m, "\tba_cam ");
+			p += scnprintf(p, end - p, "\tba_cam ");
 			first = false;
 		} else {
-			seq_puts(m, ", ");
+			p += scnprintf(p, end - p, ", ");
 		}
-		seq_printf(m, "tid[%u]=%d", entry->tid,
-			   (int)(entry - rtwdev->cam_info.ba_cam_entry));
+		p += scnprintf(p, end - p, "tid[%u]=%d", entry->tid,
+			       (int)(entry - rtwdev->cam_info.ba_cam_entry));
 	}
-	seq_puts(m, "\n");
+	p += scnprintf(p, end - p, "\n");
+
+	return p - buf;
 }
 
-static void rtw89_sta_link_ids_get(struct seq_file *m,
-				   struct rtw89_dev *rtwdev,
-				   struct rtw89_sta_link *rtwsta_link)
+static int rtw89_sta_link_ids_get(struct rtw89_dev *rtwdev,
+				  char *buf, size_t bufsz,
+				  struct rtw89_sta_link *rtwsta_link)
 {
 	struct ieee80211_link_sta *link_sta;
+	char *p = buf, *end = buf + bufsz;
 
 	rcu_read_lock();
 
 	link_sta = rtw89_sta_rcu_dereference_link(rtwsta_link, true);
 
-	seq_printf(m, "    [%u] %pM\n", rtwsta_link->mac_id, link_sta->addr);
+	p += scnprintf(p, end - p, "    [%u] %pM\n", rtwsta_link->mac_id,
+		       link_sta->addr);
 
 	rcu_read_unlock();
 
-	seq_printf(m, "\tlink_id=%u\n", rtwsta_link->link_id);
-	rtw89_dump_addr_cam(m, rtwdev, &rtwsta_link->addr_cam);
-	rtw89_dump_ba_cam(m, rtwdev, rtwsta_link);
+	p += scnprintf(p, end - p, "\tlink_id=%u\n", rtwsta_link->link_id);
+	p += rtw89_dump_addr_cam(rtwdev, p, end - p, &rtwsta_link->addr_cam);
+	p += rtw89_dump_ba_cam(rtwdev, p, end - p, rtwsta_link);
+
+	return p - buf;
 }
 
 static void rtw89_sta_ids_get_iter(void *data, struct ieee80211_sta *sta)
 {
-	struct seq_file *m = (struct seq_file *)data;
+	struct rtw89_debugfs_iter_data *iter_data =
+		(struct rtw89_debugfs_iter_data *)data;
 	struct rtw89_sta *rtwsta = sta_to_rtwsta(sta);
 	struct rtw89_dev *rtwdev = rtwsta->rtwdev;
 	struct rtw89_sta_link *rtwsta_link;
+	size_t bufsz = iter_data->bufsz;
+	char *buf = iter_data->buf;
+	char *p = buf, *end = buf + bufsz;
 	unsigned int link_id;
 
-	seq_printf(m, "STA %pM %s\n", sta->addr, sta->tdls ? "(TDLS)" : "");
+	p += scnprintf(p, end - p, "STA %pM %s\n", sta->addr,
+		       sta->tdls ? "(TDLS)" : "");
 	rtw89_sta_for_each_link(rtwsta, rtwsta_link, link_id)
-		rtw89_sta_link_ids_get(m, rtwdev, rtwsta_link);
+		p += rtw89_sta_link_ids_get(rtwdev, p, end - p, rtwsta_link);
+
+	rtw89_debugfs_iter_data_next(iter_data, p, end - p, p - buf);
 }
 
-static int rtw89_debug_priv_stations_get(struct seq_file *m, void *v)
+static ssize_t rtw89_debug_priv_stations_get(struct rtw89_dev *rtwdev,
+					     struct rtw89_debugfs_priv *debugfs_priv,
+					     char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_cam_info *cam_info = &rtwdev->cam_info;
+	struct rtw89_debugfs_iter_data iter_data;
+	char *p = buf, *end = buf + bufsz;
 	u8 idx;
 
 	mutex_lock(&rtwdev->mutex);
 
-	seq_puts(m, "map:\n");
-	seq_printf(m, "\tmac_id:    %*ph\n", (int)sizeof(rtwdev->mac_id_map),
-		   rtwdev->mac_id_map);
-	seq_printf(m, "\taddr_cam:  %*ph\n", (int)sizeof(cam_info->addr_cam_map),
-		   cam_info->addr_cam_map);
-	seq_printf(m, "\tbssid_cam: %*ph\n", (int)sizeof(cam_info->bssid_cam_map),
-		   cam_info->bssid_cam_map);
-	seq_printf(m, "\tsec_cam:   %*ph\n", (int)sizeof(cam_info->sec_cam_map),
-		   cam_info->sec_cam_map);
-	seq_printf(m, "\tba_cam:    %*ph\n", (int)sizeof(cam_info->ba_cam_map),
-		   cam_info->ba_cam_map);
-	seq_printf(m, "\tpkt_ofld:  %*ph\n", (int)sizeof(rtwdev->pkt_offload),
-		   rtwdev->pkt_offload);
+	p += scnprintf(p, end - p, "map:\n");
+	p += scnprintf(p, end - p, "\tmac_id:    %*ph\n",
+		       (int)sizeof(rtwdev->mac_id_map),
+		       rtwdev->mac_id_map);
+	p += scnprintf(p, end - p, "\taddr_cam:  %*ph\n",
+		       (int)sizeof(cam_info->addr_cam_map),
+		       cam_info->addr_cam_map);
+	p += scnprintf(p, end - p, "\tbssid_cam: %*ph\n",
+		       (int)sizeof(cam_info->bssid_cam_map),
+		       cam_info->bssid_cam_map);
+	p += scnprintf(p, end - p, "\tsec_cam:   %*ph\n",
+		       (int)sizeof(cam_info->sec_cam_map),
+		       cam_info->sec_cam_map);
+	p += scnprintf(p, end - p, "\tba_cam:    %*ph\n",
+		       (int)sizeof(cam_info->ba_cam_map),
+		       cam_info->ba_cam_map);
+	p += scnprintf(p, end - p, "\tpkt_ofld:  %*ph\n",
+		       (int)sizeof(rtwdev->pkt_offload),
+		       rtwdev->pkt_offload);
 
 	for (idx = NL80211_BAND_2GHZ; idx < NUM_NL80211_BANDS; idx++) {
 		if (!(rtwdev->chip->support_bands & BIT(idx)))
 			continue;
-		rtw89_dump_pkt_offload(m, &rtwdev->scan_info.pkt_list[idx],
-				       "\t\t[SCAN %u]: ", idx);
+		p += rtw89_dump_pkt_offload(p, end - p, &rtwdev->scan_info.pkt_list[idx],
+					    "\t\t[SCAN %u]: ", idx);
 	}
 
+	rtw89_debugfs_iter_data_setup(&iter_data, p, end - p);
 	ieee80211_iterate_active_interfaces_atomic(rtwdev->hw,
-		IEEE80211_IFACE_ITER_NORMAL, rtw89_vif_ids_get_iter, m);
+		IEEE80211_IFACE_ITER_NORMAL, rtw89_vif_ids_get_iter, &iter_data);
+	p += iter_data.written_sz;
 
-	ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_ids_get_iter, m);
+	rtw89_debugfs_iter_data_setup(&iter_data, p, end - p);
+	ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_ids_get_iter, &iter_data);
+	p += iter_data.written_sz;
 
 	mutex_unlock(&rtwdev->mutex);
 
-	return 0;
+	return p - buf;
 }
 
 #define DM_INFO(type) {RTW89_DM_ ## type, #type}
@@ -3901,41 +4113,42 @@ static const struct rtw89_disabled_dm_info {
 	DM_INFO(THERMAL_PROTECT),
 };
 
-static int
-rtw89_debug_priv_disable_dm_get(struct seq_file *m, void *v)
+static ssize_t
+rtw89_debug_priv_disable_dm_get(struct rtw89_dev *rtwdev,
+				struct rtw89_debugfs_priv *debugfs_priv,
+				char *buf, size_t bufsz)
 {
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	const struct rtw89_disabled_dm_info *info;
 	struct rtw89_hal *hal = &rtwdev->hal;
+	char *p = buf, *end = buf + bufsz;
 	u32 disabled;
 	int i;
 
-	seq_printf(m, "Disabled DM: 0x%x\n", hal->disabled_dm_bitmap);
+	p += scnprintf(p, end - p, "Disabled DM: 0x%x\n",
+		       hal->disabled_dm_bitmap);
 
 	for (i = 0; i < ARRAY_SIZE(rtw89_disabled_dm_infos); i++) {
 		info = &rtw89_disabled_dm_infos[i];
 		disabled = BIT(info->type) & hal->disabled_dm_bitmap;
 
-		seq_printf(m, "[%d] %s: %c\n", info->type, info->name,
-			   disabled ? 'X' : 'O');
+		p += scnprintf(p, end - p, "[%d] %s: %c\n", info->type,
+			       info->name,
+			       disabled ? 'X' : 'O');
 	}
 
-	return 0;
+	return p - buf;
 }
 
 static ssize_t
-rtw89_debug_priv_disable_dm_set(struct file *filp, const char __user *user_buf,
-				size_t count, loff_t *loff)
+rtw89_debug_priv_disable_dm_set(struct rtw89_dev *rtwdev,
+				struct rtw89_debugfs_priv *debugfs_priv,
+				const char *buf, size_t count)
 {
-	struct seq_file *m = (struct seq_file *)filp->private_data;
-	struct rtw89_debugfs_priv *debugfs_priv = m->private;
-	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	struct rtw89_hal *hal = &rtwdev->hal;
 	u32 conf;
 	int ret;
 
-	ret = kstrtou32_from_user(user_buf, count, 0, &conf);
+	ret = kstrtou32(buf, 0, &conf);
 	if (ret)
 		return -EINVAL;
 
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 2f8694fe4bd1c..fc8a93573144c 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2070,24 +2070,28 @@ s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
 }
 EXPORT_SYMBOL(rtw89_phy_ant_gain_pwr_offset);
 
-void rtw89_print_ant_gain(struct seq_file *m, struct rtw89_dev *rtwdev,
-			  const struct rtw89_chan *chan)
+int rtw89_print_ant_gain(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+			 const struct rtw89_chan *chan)
 {
 	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
 	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u8 regd = rtw89_regd_get(rtwdev, chan->band_type);
+	char *p = buf, *end = buf + bufsz;
 	s8 offset_patha, offset_pathb;
 
 	if (!chip->support_ant_gain || !(ant_gain->regd_enabled & BIT(regd))) {
-		seq_puts(m, "no DAG is applied\n");
-		return;
+		p += scnprintf(p, end - p, "no DAG is applied\n");
+		goto out;
 	}
 
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, chan->freq);
 	offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, chan->freq);
 
-	seq_printf(m, "ChainA offset: %d dBm\n", offset_patha);
-	seq_printf(m, "ChainB offset: %d dBm\n", offset_pathb);
+	p += scnprintf(p, end - p, "ChainA offset: %d dBm\n", offset_patha);
+	p += scnprintf(p, end - p, "ChainB offset: %d dBm\n", offset_pathb);
+
+out:
+	return p - buf;
 }
 
 static const u8 rtw89_rs_idx_num_ax[] = {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index cec165e222e7d..e20fff9bac3ee 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -835,8 +835,8 @@ s8 rtw89_phy_read_txpwr_byrate(struct rtw89_dev *rtwdev, u8 band, u8 bw,
 void rtw89_phy_ant_gain_init(struct rtw89_dev *rtwdev);
 s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
 				  const struct rtw89_chan *chan);
-void rtw89_print_ant_gain(struct seq_file *m, struct rtw89_dev *rtwdev,
-			  const struct rtw89_chan *chan);
+int rtw89_print_ant_gain(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+			 const struct rtw89_chan *chan);
 void rtw89_phy_load_txpwr_byrate(struct rtw89_dev *rtwdev,
 				 const struct rtw89_txpwr_table *tbl);
 s8 rtw89_phy_read_txpwr_limit(struct rtw89_dev *rtwdev, u8 band,
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 94db695e78e6f..1f67a2fbce818 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -178,12 +178,14 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 	return rtw89_txpwr_sar_to_mac(rtwdev, fct, cfg);
 }
 
-void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev, u32 center_freq)
+int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+		    u32 center_freq)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
 	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
 	const u8 fct_mac = rtwdev->chip->txpwr_factor_mac;
+	char *p = buf, *end = buf + bufsz;
 	int ret;
 	s32 cfg;
 	u8 fct;
@@ -191,36 +193,46 @@ void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev, u32 center_fr
 	lockdep_assert_held(&rtwdev->mutex);
 
 	if (src == RTW89_SAR_SOURCE_NONE) {
-		seq_puts(m, "no SAR is applied\n");
-		return;
+		p += scnprintf(p, end - p, "no SAR is applied\n");
+		goto out;
 	}
 
-	seq_printf(m, "source: %d (%s)\n", src, sar_hdl->descr_sar_source);
+	p += scnprintf(p, end - p, "source: %d (%s)\n", src,
+		       sar_hdl->descr_sar_source);
 
 	ret = sar_hdl->query_sar_config(rtwdev, center_freq, &cfg);
 	if (ret) {
-		seq_printf(m, "config: return code: %d\n", ret);
-		seq_printf(m, "assign: max setting: %d (unit: 1/%lu dBm)\n",
-			   RTW89_SAR_TXPWR_MAC_MAX, BIT(fct_mac));
-		return;
+		p += scnprintf(p, end - p, "config: return code: %d\n", ret);
+		p += scnprintf(p, end - p,
+			       "assign: max setting: %d (unit: 1/%lu dBm)\n",
+			       RTW89_SAR_TXPWR_MAC_MAX, BIT(fct_mac));
+		goto out;
 	}
 
 	fct = sar_hdl->txpwr_factor_sar;
 
-	seq_printf(m, "config: %d (unit: 1/%lu dBm)\n", cfg, BIT(fct));
+	p += scnprintf(p, end - p, "config: %d (unit: 1/%lu dBm)\n", cfg,
+		       BIT(fct));
+
+out:
+	return p - buf;
 }
 
-void rtw89_print_tas(struct seq_file *m, struct rtw89_dev *rtwdev)
+int rtw89_print_tas(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 {
 	struct rtw89_tas_info *tas = &rtwdev->tas;
+	char *p = buf, *end = buf + bufsz;
 
 	if (!tas->enable) {
-		seq_puts(m, "no TAS is applied\n");
-		return;
+		p += scnprintf(p, end - p, "no TAS is applied\n");
+		goto out;
 	}
 
-	seq_printf(m, "DPR gap: %d\n", tas->dpr_gap);
-	seq_printf(m, "TAS delta: %d\n", tas->delta);
+	p += scnprintf(p, end - p, "DPR gap: %d\n", tas->dpr_gap);
+	p += scnprintf(p, end - p, "TAS delta: %d\n", tas->delta);
+
+out:
+	return p - buf;
 }
 
 static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/sar.h b/drivers/net/wireless/realtek/rtw89/sar.h
index 4ae081d2d3b46..095277df5a710 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.h
+++ b/drivers/net/wireless/realtek/rtw89/sar.h
@@ -19,8 +19,9 @@ struct rtw89_sar_handler {
 extern const struct cfg80211_sar_capa rtw89_sar_capa;
 
 s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq);
-void rtw89_print_sar(struct seq_file *m, struct rtw89_dev *rtwdev, u32 center_freq);
-void rtw89_print_tas(struct seq_file *m, struct rtw89_dev *rtwdev);
+int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
+		    u32 center_freq);
+int rtw89_print_tas(struct rtw89_dev *rtwdev, char *buf, size_t bufsz);
 int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 			    const struct cfg80211_sar_specs *sar);
 void rtw89_tas_init(struct rtw89_dev *rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/util.c b/drivers/net/wireless/realtek/rtw89/util.c
index e71956ce98537..33be268734735 100644
--- a/drivers/net/wireless/realtek/rtw89/util.c
+++ b/drivers/net/wireless/realtek/rtw89/util.c
@@ -104,3 +104,14 @@ u64 rtw89_db_2_linear(u32 db)
 	return linear;
 }
 EXPORT_SYMBOL(rtw89_db_2_linear);
+
+void rtw89_might_trailing_ellipsis(char *buf, size_t size, ssize_t used)
+{
+	static const char ellipsis[] = "...";
+
+	/* length of null terminiator isn't included in 'used' */
+	if (used + 1 < size || size < sizeof(ellipsis))
+		return;
+
+	memcpy(buf + size - sizeof(ellipsis), ellipsis, sizeof(ellipsis));
+}
diff --git a/drivers/net/wireless/realtek/rtw89/util.h b/drivers/net/wireless/realtek/rtw89/util.h
index e669544cafd3f..71c7d3502202c 100644
--- a/drivers/net/wireless/realtek/rtw89/util.h
+++ b/drivers/net/wireless/realtek/rtw89/util.h
@@ -77,5 +77,6 @@ static inline void ether_addr_copy_mask(u8 *dst, const u8 *src, u8 mask)
 
 u32 rtw89_linear_2_db(u64 linear);
 u64 rtw89_db_2_linear(u32 db);
+void rtw89_might_trailing_ellipsis(char *buf, size_t size, ssize_t used);
 
 #endif

From 01fd45d9e102bd9bc9d234aa8f409fa8b94e3919 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:04 +0800
Subject: [PATCH 0069/2753] wifi: rtw89: debugfs: specify buffer size allocated
 by devm_kazlloc() for reading

Some debufs entries need output buffer over default size 4K. Since reading
of many debugfs entries is to access IO, it costs time to dynamically
re-allocate larger buffer and access IO again and again. Add an option to
specify the size it needs.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 62 ++++++++++++++++------
 1 file changed, 45 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index db0e7a4beb07e..f3ec18860797b 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -23,6 +23,10 @@ MODULE_PARM_DESC(debug_mask, "Debugging mask");
 #endif
 
 #ifdef CONFIG_RTW89_DEBUGFS
+struct rtw89_debugfs_priv_opt {
+	size_t rsize;
+};
+
 struct rtw89_debugfs_priv {
 	struct rtw89_dev *rtwdev;
 	ssize_t (*cb_read)(struct rtw89_dev *rtwdev,
@@ -31,6 +35,7 @@ struct rtw89_debugfs_priv {
 	ssize_t (*cb_write)(struct rtw89_dev *rtwdev,
 			    struct rtw89_debugfs_priv *debugfs_priv,
 			    const char *buf, size_t count);
+	struct rtw89_debugfs_priv_opt opt;
 	union {
 		u32 cb_data;
 		struct {
@@ -55,6 +60,8 @@ struct rtw89_debugfs_priv {
 			u8 sel;
 		} mac_mem;
 	};
+	ssize_t rused;
+	char *rbuf;
 };
 
 struct rtw89_debugfs {
@@ -120,23 +127,31 @@ static ssize_t rtw89_debugfs_file_read(struct file *file, char __user *userbuf,
 				       size_t count, loff_t *ppos)
 {
 	struct rtw89_debugfs_priv *debugfs_priv = file->private_data;
+	struct rtw89_debugfs_priv_opt *opt = &debugfs_priv->opt;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
-	size_t bufsz = PAGE_SIZE;
+	size_t bufsz = opt->rsize ? opt->rsize : PAGE_SIZE;
 	char *buf;
 	ssize_t n;
 
-	buf = kvmalloc(bufsz, GFP_KERNEL);
+	if (!debugfs_priv->rbuf)
+		debugfs_priv->rbuf = devm_kzalloc(rtwdev->dev, bufsz, GFP_KERNEL);
+
+	buf = debugfs_priv->rbuf;
 	if (!buf)
-		return 0;
+		return -ENOMEM;
+
+	if (*ppos) {
+		n = debugfs_priv->rused;
+		goto out;
+	}
 
 	n = debugfs_priv->cb_read(rtwdev, debugfs_priv, buf, bufsz);
 	rtw89_might_trailing_ellipsis(buf, bufsz, n);
 
-	n = simple_read_from_buffer(userbuf, count, ppos, buf, n);
-
-	kvfree(buf);
+	debugfs_priv->rused = n;
 
-	return n;
+out:
+	return simple_read_from_buffer(userbuf, count, ppos, buf, n);
 }
 
 static ssize_t rtw89_debugfs_file_write(struct file *file,
@@ -4157,42 +4172,55 @@ rtw89_debug_priv_disable_dm_set(struct rtw89_dev *rtwdev,
 	return count;
 }
 
-#define rtw89_debug_priv_get(name)				\
+#define rtw89_debug_priv_get(name, opts...)			\
 {								\
 	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+	.opt = { opts },					\
 }
 
-#define rtw89_debug_priv_set(name)				\
+#define rtw89_debug_priv_set(name, opts...)			\
 {								\
 	.cb_write = rtw89_debug_priv_ ##name## _set,		\
+	.opt = { opts },					\
 }
 
-#define rtw89_debug_priv_select_and_get(name)			\
+#define rtw89_debug_priv_select_and_get(name, opts...)		\
 {								\
 	.cb_write = rtw89_debug_priv_ ##name## _select,		\
 	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+	.opt = { opts },					\
 }
 
-#define rtw89_debug_priv_set_and_get(name)			\
+#define rtw89_debug_priv_set_and_get(name, opts...)		\
 {								\
 	.cb_write = rtw89_debug_priv_ ##name## _set,		\
 	.cb_read = rtw89_debug_priv_ ##name## _get,		\
+	.opt = { opts },					\
 }
 
+#define RSIZE_8K .rsize = 0x2000
+#define RSIZE_12K .rsize = 0x3000
+#define RSIZE_16K .rsize = 0x4000
+#define RSIZE_20K .rsize = 0x5000
+#define RSIZE_32K .rsize = 0x8000
+#define RSIZE_64K .rsize = 0x10000
+#define RSIZE_128K .rsize = 0x20000
+#define RSIZE_1M .rsize = 0x100000
+
 static const struct rtw89_debugfs rtw89_debugfs_templ = {
 	.read_reg = rtw89_debug_priv_select_and_get(read_reg),
 	.write_reg = rtw89_debug_priv_set(write_reg),
 	.read_rf = rtw89_debug_priv_select_and_get(read_rf),
 	.write_rf = rtw89_debug_priv_set(write_rf),
-	.rf_reg_dump = rtw89_debug_priv_get(rf_reg_dump),
-	.txpwr_table = rtw89_debug_priv_get(txpwr_table),
-	.mac_reg_dump = rtw89_debug_priv_select_and_get(mac_reg_dump),
-	.mac_mem_dump = rtw89_debug_priv_select_and_get(mac_mem_dump),
-	.mac_dbg_port_dump = rtw89_debug_priv_select_and_get(mac_dbg_port_dump),
+	.rf_reg_dump = rtw89_debug_priv_get(rf_reg_dump, RSIZE_8K),
+	.txpwr_table = rtw89_debug_priv_get(txpwr_table, RSIZE_20K),
+	.mac_reg_dump = rtw89_debug_priv_select_and_get(mac_reg_dump, RSIZE_128K),
+	.mac_mem_dump = rtw89_debug_priv_select_and_get(mac_mem_dump, RSIZE_16K),
+	.mac_dbg_port_dump = rtw89_debug_priv_select_and_get(mac_dbg_port_dump, RSIZE_1M),
 	.send_h2c = rtw89_debug_priv_set(send_h2c),
 	.early_h2c = rtw89_debug_priv_set_and_get(early_h2c),
 	.fw_crash = rtw89_debug_priv_set_and_get(fw_crash),
-	.btc_info = rtw89_debug_priv_get(btc_info),
+	.btc_info = rtw89_debug_priv_get(btc_info, RSIZE_12K),
 	.btc_manual = rtw89_debug_priv_set(btc_manual),
 	.fw_log_manual = rtw89_debug_priv_set(fw_log_manual),
 	.phy_info = rtw89_debug_priv_get(phy_info),

From 8fdf78f3cd5f87eced0c4f7eed7160a2ec31a008 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:05 +0800
Subject: [PATCH 0070/2753] wifi: rtw89: debugfs: use
 wiphy_locked_debugfs_{read,write}() if needed

If a debugfs entry takes driver mutex now, let it uses
wiphy_locked_debugfs_{read,write}() to take both driver mutex and
wiphy lock. Add rwlock option to support this.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 63 +++++++++++++++++++---
 1 file changed, 55 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index f3ec18860797b..35bf627dbae23 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -24,6 +24,8 @@ MODULE_PARM_DESC(debug_mask, "Debugging mask");
 
 #ifdef CONFIG_RTW89_DEBUGFS
 struct rtw89_debugfs_priv_opt {
+	bool rlock:1;
+	bool wlock:1;
 	size_t rsize;
 };
 
@@ -123,6 +125,19 @@ static u16 rtw89_rate_info_bw_to_mhz(enum rate_info_bw bw)
 	return 0;
 }
 
+static ssize_t rtw89_debugfs_file_read_helper(struct wiphy *wiphy, struct file *file,
+					      char *buf, size_t bufsz, void *data)
+{
+	struct rtw89_debugfs_priv *debugfs_priv = data;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+	ssize_t n;
+
+	n = debugfs_priv->cb_read(rtwdev, debugfs_priv, buf, bufsz);
+	rtw89_might_trailing_ellipsis(buf, bufsz, n);
+
+	return n;
+}
+
 static ssize_t rtw89_debugfs_file_read(struct file *file, char __user *userbuf,
 				       size_t count, loff_t *ppos)
 {
@@ -145,26 +160,55 @@ static ssize_t rtw89_debugfs_file_read(struct file *file, char __user *userbuf,
 		goto out;
 	}
 
-	n = debugfs_priv->cb_read(rtwdev, debugfs_priv, buf, bufsz);
-	rtw89_might_trailing_ellipsis(buf, bufsz, n);
+	if (opt->rlock) {
+		n = wiphy_locked_debugfs_read(rtwdev->hw->wiphy, file, buf, bufsz,
+					      userbuf, count, ppos,
+					      rtw89_debugfs_file_read_helper,
+					      debugfs_priv);
+		debugfs_priv->rused = n;
 
+		return n;
+	}
+
+	n = rtw89_debugfs_file_read_helper(rtwdev->hw->wiphy, file, buf, bufsz,
+					   debugfs_priv);
 	debugfs_priv->rused = n;
 
 out:
 	return simple_read_from_buffer(userbuf, count, ppos, buf, n);
 }
 
+static ssize_t rtw89_debugfs_file_write_helper(struct wiphy *wiphy, struct file *file,
+					       char *buf, size_t count, void *data)
+{
+	struct rtw89_debugfs_priv *debugfs_priv = data;
+	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
+
+	return debugfs_priv->cb_write(rtwdev, debugfs_priv, buf, count);
+}
+
 static ssize_t rtw89_debugfs_file_write(struct file *file,
 					const char __user *userbuf,
 					size_t count, loff_t *loff)
 {
 	struct rtw89_debugfs_priv *debugfs_priv = file->private_data;
+	struct rtw89_debugfs_priv_opt *opt = &debugfs_priv->opt;
 	struct rtw89_dev *rtwdev = debugfs_priv->rtwdev;
 	char *buf __free(kfree) = kmalloc(count + 1, GFP_KERNEL);
+	ssize_t n;
 
 	if (!buf)
 		return -ENOMEM;
 
+	if (opt->wlock) {
+		n = wiphy_locked_debugfs_write(rtwdev->hw->wiphy,
+					       file, buf, count + 1,
+					       userbuf, count,
+					       rtw89_debugfs_file_write_helper,
+					       debugfs_priv);
+		return n;
+	}
+
 	if (copy_from_user(buf, userbuf, count))
 		return -EFAULT;
 
@@ -4206,6 +4250,9 @@ rtw89_debug_priv_disable_dm_set(struct rtw89_dev *rtwdev,
 #define RSIZE_64K .rsize = 0x10000
 #define RSIZE_128K .rsize = 0x20000
 #define RSIZE_1M .rsize = 0x100000
+#define RLOCK .rlock = 1
+#define WLOCK .wlock = 1
+#define RWLOCK RLOCK, WLOCK
 
 static const struct rtw89_debugfs rtw89_debugfs_templ = {
 	.read_reg = rtw89_debug_priv_select_and_get(read_reg),
@@ -4213,18 +4260,18 @@ static const struct rtw89_debugfs rtw89_debugfs_templ = {
 	.read_rf = rtw89_debug_priv_select_and_get(read_rf),
 	.write_rf = rtw89_debug_priv_set(write_rf),
 	.rf_reg_dump = rtw89_debug_priv_get(rf_reg_dump, RSIZE_8K),
-	.txpwr_table = rtw89_debug_priv_get(txpwr_table, RSIZE_20K),
+	.txpwr_table = rtw89_debug_priv_get(txpwr_table, RSIZE_20K, RLOCK),
 	.mac_reg_dump = rtw89_debug_priv_select_and_get(mac_reg_dump, RSIZE_128K),
-	.mac_mem_dump = rtw89_debug_priv_select_and_get(mac_mem_dump, RSIZE_16K),
+	.mac_mem_dump = rtw89_debug_priv_select_and_get(mac_mem_dump, RSIZE_16K, RLOCK),
 	.mac_dbg_port_dump = rtw89_debug_priv_select_and_get(mac_dbg_port_dump, RSIZE_1M),
 	.send_h2c = rtw89_debug_priv_set(send_h2c),
-	.early_h2c = rtw89_debug_priv_set_and_get(early_h2c),
-	.fw_crash = rtw89_debug_priv_set_and_get(fw_crash),
+	.early_h2c = rtw89_debug_priv_set_and_get(early_h2c, RWLOCK),
+	.fw_crash = rtw89_debug_priv_set_and_get(fw_crash, WLOCK),
 	.btc_info = rtw89_debug_priv_get(btc_info, RSIZE_12K),
 	.btc_manual = rtw89_debug_priv_set(btc_manual),
-	.fw_log_manual = rtw89_debug_priv_set(fw_log_manual),
+	.fw_log_manual = rtw89_debug_priv_set(fw_log_manual, WLOCK),
 	.phy_info = rtw89_debug_priv_get(phy_info),
-	.stations = rtw89_debug_priv_get(stations),
+	.stations = rtw89_debug_priv_get(stations, RLOCK),
 	.disable_dm = rtw89_debug_priv_set_and_get(disable_dm),
 };
 

From bdf874dc3c7639aace300cd8c5d24486b1a8ec7a Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:06 +0800
Subject: [PATCH 0071/2753] wifi: rtw89: debugfs: use debugfs_short_fops

With this change, the object code size can reduce 768 bytes.

   text    data     bss     dec     hex filename
  77257    4262       4   81523   13e73 debug.o   (before)
  76489    4262       4   80755   13b73 debug.o   (after)

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-7-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/debug.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 35bf627dbae23..0863ed6acda29 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -217,25 +217,19 @@ static ssize_t rtw89_debugfs_file_write(struct file *file,
 	return debugfs_priv->cb_write(rtwdev, debugfs_priv, buf, count);
 }
 
-static const struct file_operations file_ops_single_r = {
-	.owner = THIS_MODULE,
+static const struct debugfs_short_fops file_ops_single_r = {
 	.read = rtw89_debugfs_file_read,
-	.open = simple_open,
 	.llseek = generic_file_llseek,
 };
 
-static const struct file_operations file_ops_common_rw = {
-	.owner = THIS_MODULE,
+static const struct debugfs_short_fops file_ops_common_rw = {
 	.read = rtw89_debugfs_file_read,
 	.write = rtw89_debugfs_file_write,
-	.open = simple_open,
 	.llseek = generic_file_llseek,
 };
 
-static const struct file_operations file_ops_single_w = {
-	.owner = THIS_MODULE,
+static const struct debugfs_short_fops file_ops_single_w = {
 	.write = rtw89_debugfs_file_write,
-	.open = simple_open,
 	.llseek = generic_file_llseek,
 };
 

From 6ee1937d8bc93fe0d3eaacbcfd582d84998d557f Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:07 +0800
Subject: [PATCH 0072/2753] wifi: rtw89: remove consumers of driver mutex

All need lock have taken both driver mutex and wiphy lock, so we can remove
driver mutex safely by below spatch script. Also, check every
lockdep_assert_wiphy() is executed without locks warning at runtime.

@ rule1_1 @
@@

- lockdep_assert_held(&rtwdev->mutex);
+ lockdep_assert_wiphy(rtwdev->hw->wiphy);

@ rule1_2 @
@@

- guard(mutex)(&rtwdev->mutex);
+ lockdep_assert_wiphy(rtwdev->hw->wiphy);

@ rule2_1 @
@@

- mutex_lock(&rtwdev->mutex);
+ lockdep_assert_wiphy(rtwdev->hw->wiphy);
  ...
- mutex_unlock(&rtwdev->mutex);

@ rule2_2 @
@@

- mutex_unlock(&rtwdev->mutex);
+ lockdep_assert_wiphy(rtwdev->hw->wiphy);
  ...
- mutex_lock(&rtwdev->mutex);

@ rule3_1 @
type t;
identifier fn;
@@
  t fn(struct wiphy *wiphy, ...)
  {
  ...
- lockdep_assert_wiphy(rtwdev->hw->wiphy);
+ lockdep_assert_wiphy(wiphy);
  ...
  }

@ rule3_1_1 @
type t;
identifier fn;
@@
  t fn(...)
  {
  ...
  struct wiphy *wiphy = ...;
  ...
- lockdep_assert_wiphy(rtwdev->hw->wiphy);
+ lockdep_assert_wiphy(wiphy);
  ...
  }

@ rule3_2 @
type t;
identifier fn;
@@
  t fn(struct ieee80211_hw *hw, ...)
  {
  ...
- lockdep_assert_wiphy(rtwdev->hw->wiphy);
+ lockdep_assert_wiphy(hw->wiphy);
  ...
  }

@ rule3_2_1 @
type t;
identifier fn;
@@
  t fn(...)
  {
  ...
  struct ieee80211_hw *hw = ...;
  ...
- lockdep_assert_wiphy(rtwdev->hw->wiphy);
+ lockdep_assert_wiphy(hw->wiphy);
  ...
  }

The compiler warnings will be fixed manually by latter patch:

  rtw89/mac80211.c:371:1: warning: statement expected after label

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-8-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c     |  19 ++-
 drivers/net/wireless/realtek/rtw89/coex.c     |  23 ++-
 drivers/net/wireless/realtek/rtw89/core.c     |  28 ++--
 drivers/net/wireless/realtek/rtw89/debug.c    |  24 +---
 drivers/net/wireless/realtek/rtw89/fw.c       |   7 +-
 drivers/net/wireless/realtek/rtw89/mac80211.c | 131 ++++++------------
 drivers/net/wireless/realtek/rtw89/phy.c      |   7 +-
 drivers/net/wireless/realtek/rtw89/ps.c       |   6 +-
 drivers/net/wireless/realtek/rtw89/regd.c     |   5 +-
 drivers/net/wireless/realtek/rtw89/sar.c      |   9 +-
 drivers/net/wireless/realtek/rtw89/ser.c      |   6 +-
 drivers/net/wireless/realtek/rtw89/util.h     |   2 +-
 drivers/net/wireless/realtek/rtw89/wow.c      |   3 +-
 13 files changed, 92 insertions(+), 178 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 9858894dfc236..98f4202086320 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -155,7 +155,7 @@ int rtw89_iterate_entity_chan(struct rtw89_dev *rtwdev,
 	int ret;
 	u8 idx;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	for_each_set_bit(idx,  hal->entity_map, NUM_OF_RTW89_CHANCTX) {
 		chan = rtw89_chan_get(rtwdev, idx);
@@ -310,7 +310,7 @@ const struct rtw89_chan *__rtw89_mgnt_chan_get(struct rtw89_dev *rtwdev,
 	enum rtw89_entity_mode mode;
 	u8 role_index;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (unlikely(link_index >= __RTW89_MLD_MAX_LINK_NUM)) {
 		WARN(1, "link index %u is invalid (max link inst num: %d)\n",
@@ -366,7 +366,7 @@ static void rtw89_entity_recalc_mgnt_roles(struct rtw89_dev *rtwdev)
 	u8 pos = 0;
 	int i, j;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	for (i = 0; i < RTW89_MAX_INTERFACE_NUM; i++)
 		mgnt->active_roles[i] = NULL;
@@ -427,7 +427,7 @@ enum rtw89_entity_mode rtw89_entity_recalc(struct rtw89_dev *rtwdev)
 	struct rtw89_chan chan;
 	u8 idx;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	bitmap_copy(recalc_map, hal->entity_map, NUM_OF_RTW89_CHANCTX);
 
@@ -2401,10 +2401,9 @@ void rtw89_chanctx_work(struct wiphy *wiphy, struct wiphy_work *work)
 	int ret;
 	int i;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	if (hal->entity_pause) {
-		mutex_unlock(&rtwdev->mutex);
 		return;
 	}
 
@@ -2445,8 +2444,6 @@ void rtw89_chanctx_work(struct wiphy *wiphy, struct wiphy_work *work)
 	default:
 		break;
 	}
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_queue_chanctx_change(struct rtw89_dev *rtwdev,
@@ -2491,7 +2488,7 @@ void rtw89_chanctx_track(struct rtw89_dev *rtwdev)
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_entity_mode mode;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (hal->entity_pause)
 		return;
@@ -2512,7 +2509,7 @@ void rtw89_chanctx_pause(struct rtw89_dev *rtwdev,
 	struct rtw89_hal *hal = &rtwdev->hal;
 	enum rtw89_entity_mode mode;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (hal->entity_pause)
 		return;
@@ -2555,7 +2552,7 @@ void rtw89_chanctx_proceed(struct rtw89_dev *rtwdev,
 	enum rtw89_entity_mode mode;
 	int ret;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (unlikely(!hal->entity_pause)) {
 		rtw89_chanctx_proceed_cb(rtwdev, cb_parm);
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 1065f610d80f1..a7b7675dca97a 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -6721,7 +6721,7 @@ void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_cx *cx = &btc->cx;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	if (wl->status.map._4way)
@@ -6730,7 +6730,6 @@ void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work)
 		wl->status.map.connecting = false;
 
 	_run_coex(rtwdev, BTC_RSN_ACT1_WORK);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work)
@@ -6741,12 +6740,11 @@ void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_dm *dm = &rtwdev->btc.dm;
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &btc->cx.bt.link_info.a2dp_desc;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	a2dp->play_latency = 0;
 	_run_coex(rtwdev, BTC_RSN_BT_DEVINFO_WORK);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work)
@@ -6758,7 +6756,7 @@ void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_cx *cx = &btc->cx;
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	if (wl->rfk_info.state != BTC_WRFK_STOP) {
@@ -6770,7 +6768,6 @@ void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work)
 		_write_scbd(rtwdev, BTC_WSCB_WLRFK, false);
 		_run_coex(rtwdev, BTC_RSN_RFK_CHK_WORK);
 	}
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void _update_bt_scbd(struct rtw89_dev *rtwdev, bool only_update)
@@ -6874,7 +6871,7 @@ void _run_coex(struct rtw89_dev *rtwdev, enum btc_reason_and_action reason)
 	struct rtw89_btc_wl_role_info_v8 *wl_rinfo_v8 = &wl->role_info_v8;
 	u8 mode, igno_bt, always_freerun;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	dm->run_reason = reason;
 	_update_dm_step(rtwdev, reason);
@@ -7311,10 +7308,9 @@ void rtw89_btc_ntfy_eapol_packet_work(struct wiphy *wiphy, struct wiphy_work *wo
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.eapol_notify_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_EAPOL);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_btc_ntfy_arp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
@@ -7322,9 +7318,8 @@ void rtw89_btc_ntfy_arp_packet_work(struct wiphy *wiphy, struct wiphy_work *work
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.arp_notify_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_ARP);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_btc_ntfy_dhcp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
@@ -7332,10 +7327,9 @@ void rtw89_btc_ntfy_dhcp_packet_work(struct wiphy *wiphy, struct wiphy_work *wor
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.dhcp_notify_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_DHCP);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_btc_ntfy_icmp_packet_work(struct wiphy *wiphy, struct wiphy_work *work)
@@ -7343,10 +7337,9 @@ void rtw89_btc_ntfy_icmp_packet_work(struct wiphy *wiphy, struct wiphy_work *wor
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						btc.icmp_notify_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_ICMP);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static u8 _update_bt_rssi_level(struct rtw89_dev *rtwdev, u8 rssi)
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 330b23db4868b..602185b3c9b04 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2079,7 +2079,7 @@ static void rtw89_cancel_6ghz_probe_work(struct wiphy *wiphy, struct wiphy_work
 	struct list_head *pkt_list = rtwdev->scan_info.pkt_list;
 	struct rtw89_pktofld_info *info;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	if (!rtwdev->scanning)
 		goto out;
@@ -2097,7 +2097,6 @@ static void rtw89_cancel_6ghz_probe_work(struct wiphy *wiphy, struct wiphy_work
 	}
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_core_cancel_6ghz_probe_tx(struct rtw89_dev *rtwdev,
@@ -3148,9 +3147,8 @@ static void rtw89_ips_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						ips_work);
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_enter_ips_by_hwflags(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_core_txq_work(struct work_struct *w)
@@ -3292,7 +3290,7 @@ void rtw89_roc_start(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	u32 reg;
 	int ret;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtw89_leave_ips_by_hwflags(rtwdev);
 	rtw89_leave_lps(rtwdev);
@@ -3346,7 +3344,7 @@ void rtw89_roc_end(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
 	u32 reg;
 	int ret;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	ieee80211_remain_on_channel_expired(hw);
 
@@ -3389,7 +3387,7 @@ void rtw89_roc_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_dev *rtwdev = rtwvif->rtwdev;
 	struct rtw89_roc *roc = &rtwvif->roc;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	switch (roc->state) {
 	case RTW89_ROC_IDLE:
@@ -3402,8 +3400,6 @@ void rtw89_roc_work(struct wiphy *wiphy, struct wiphy_work *work)
 	default:
 		break;
 	}
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static enum rtw89_tfc_lv rtw89_get_traffic_level(struct rtw89_dev *rtwdev,
@@ -3543,7 +3539,7 @@ static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 	if (test_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags))
 		return;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	if (!test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
 		goto out;
@@ -3580,7 +3576,6 @@ static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 		rtw89_enter_lps_track(rtwdev);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 u8 rtw89_core_acquire_bit_map(unsigned long *addr, unsigned long size)
@@ -3614,7 +3609,7 @@ int rtw89_core_acquire_sta_ba_entry(struct rtw89_dev *rtwdev,
 	u8 idx;
 	int i;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	idx = rtw89_core_acquire_bit_map(cam_info->ba_cam_map, chip->bacam_num);
 	if (idx == chip->bacam_num) {
@@ -3658,7 +3653,7 @@ int rtw89_core_release_sta_ba_entry(struct rtw89_dev *rtwdev,
 	struct rtw89_ba_cam_entry *entry = NULL, *tmp;
 	u8 idx;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	list_for_each_entry_safe(entry, tmp, &rtwsta_link->ba_cam_list, list) {
 		if (entry->tid != tid)
@@ -4450,9 +4445,8 @@ void rtw89_core_update_beacon_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	rtwdev = rtwvif_link->rtwvif->rtwdev;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_chip_h2c_update_beacon(rtwdev, rtwvif_link);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 int rtw89_wait_for_cond(struct rtw89_wait_info *wait, unsigned int cond)
@@ -4595,7 +4589,7 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 
 	clear_bit(RTW89_FLAG_RUNNING, rtwdev->flags);
 
-	mutex_unlock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	wiphy_work_cancel(wiphy, &rtwdev->c2h_work);
 	wiphy_work_cancel(wiphy, &rtwdev->cancel_6ghz_probe_work);
@@ -4613,8 +4607,6 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 	cancel_delayed_work_sync(&rtwdev->forbid_ba_work);
 	wiphy_delayed_work_cancel(wiphy, &rtwdev->antdiv_work);
 
-	mutex_lock(&rtwdev->mutex);
-
 	rtw89_btc_ntfy_poweroff(rtwdev);
 	rtw89_hci_flush_queues(rtwdev, BIT(rtwdev->hw->queues) - 1, true);
 	rtw89_mac_flush_txq(rtwdev, BIT(rtwdev->hw->queues) - 1, true);
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 0863ed6acda29..56be6705e9ea3 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -954,7 +954,7 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 	char *p = buf, *end = buf + bufsz;
 	ssize_t n;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
@@ -993,12 +993,9 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 		goto err;
 	p += n;
 
-	mutex_unlock(&rtwdev->mutex);
-
 	return p - buf;
 
 err:
-	mutex_unlock(&rtwdev->mutex);
 
 	return n;
 }
@@ -1201,7 +1198,7 @@ rtw89_debug_priv_mac_mem_dump_get(struct rtw89_dev *rtwdev,
 		}
 	}
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	if (grant_read)
 		rtw89_write32_set(rtwdev, R_AX_TCR1, B_AX_TCR_FORCE_READ_TXDFIFO);
@@ -1211,7 +1208,6 @@ rtw89_debug_priv_mac_mem_dump_get(struct rtw89_dev *rtwdev,
 				      debugfs_priv->mac_mem.len);
 	if (grant_read)
 		rtw89_write32_clr(rtwdev, R_AX_TCR1, B_AX_TCR_FORCE_READ_TXDFIFO);
-	mutex_unlock(&rtwdev->mutex);
 
 	return p - buf;
 }
@@ -3518,11 +3514,10 @@ rtw89_debug_priv_early_h2c_get(struct rtw89_dev *rtwdev,
 	char *p = buf, *end = buf + bufsz;
 	int seq = 0;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	list_for_each_entry(early_h2c, &rtwdev->early_h2c_list, list)
 		p += scnprintf(p, end - p, "%d: %*ph\n", ++seq,
 			       early_h2c->h2c_len, early_h2c->h2c);
-	mutex_unlock(&rtwdev->mutex);
 
 	return p - buf;
 }
@@ -3555,9 +3550,8 @@ rtw89_debug_priv_early_h2c_set(struct rtw89_dev *rtwdev,
 	early_h2c->h2c = h2c;
 	early_h2c->h2c_len = h2c_len;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	list_add_tail(&early_h2c->list, &rtwdev->early_h2c_list);
-	mutex_unlock(&rtwdev->mutex);
 
 out:
 	return count;
@@ -3633,10 +3627,9 @@ rtw89_debug_priv_fw_crash_set(struct rtw89_dev *rtwdev,
 		return -EINVAL;
 	}
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	set_bit(RTW89_FLAG_CRASH_SIMULATING, rtwdev->flags);
 	ret = sim(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 
 	if (ret)
 		return ret;
@@ -3681,12 +3674,11 @@ static ssize_t rtw89_debug_priv_fw_log_manual_set(struct rtw89_dev *rtwdev,
 	if (kstrtobool(buf, &fw_log_manual))
 		goto out;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	log->enable = fw_log_manual;
 	if (log->enable)
 		rtw89_fw_log_prepare(rtwdev);
 	rtw89_fw_h2c_fw_log(rtwdev, fw_log_manual);
-	mutex_unlock(&rtwdev->mutex);
 out:
 	return count;
 }
@@ -4113,7 +4105,7 @@ static ssize_t rtw89_debug_priv_stations_get(struct rtw89_dev *rtwdev,
 	char *p = buf, *end = buf + bufsz;
 	u8 idx;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	p += scnprintf(p, end - p, "map:\n");
 	p += scnprintf(p, end - p, "\tmac_id:    %*ph\n",
@@ -4151,8 +4143,6 @@ static ssize_t rtw89_debug_priv_stations_get(struct rtw89_dev *rtwdev,
 	ieee80211_iterate_stations_atomic(rtwdev->hw, rtw89_sta_ids_get_iter, &iter_data);
 	p += iter_data.written_sz;
 
-	mutex_unlock(&rtwdev->mutex);
-
 	return p - buf;
 }
 
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 64c2895309c6e..2713bae449900 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6096,7 +6096,7 @@ void rtw89_fw_send_all_early_h2c(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_early_h2c *early_h2c;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	list_for_each_entry(early_h2c, &rtwdev->early_h2c_list, list) {
 		rtw89_fw_h2c_raw(rtwdev, early_h2c->h2c, early_h2c->h2c_len);
@@ -6203,9 +6203,8 @@ void rtw89_fw_c2h_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	skb_queue_walk_safe(&rtwdev->c2h_queue, skb, tmp) {
 		skb_unlink(skb, &rtwdev->c2h_queue);
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_fw_c2h_cmd_handle(rtwdev, skb);
-		mutex_unlock(&rtwdev->mutex);
 		dev_kfree_skb_any(skb);
 	}
 }
@@ -6286,7 +6285,7 @@ int rtw89_fw_msg_reg(struct rtw89_dev *rtwdev,
 	u32 ret;
 
 	if (h2c_info && h2c_info->id != RTW89_FWCMD_H2CREG_FUNC_GET_FEATURE)
-		lockdep_assert_held(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (!h2c_info && !c2h_info)
 		return -EINVAL;
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 7b3520e6389bb..11516ede13e49 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -59,9 +59,8 @@ static int rtw89_ops_start(struct ieee80211_hw *hw)
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	ret = rtw89_core_start(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -70,9 +69,8 @@ static void rtw89_ops_stop(struct ieee80211_hw *hw, bool suspend)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_core_stop(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
@@ -82,7 +80,7 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
 	/* let previous ips work finish to ensure we don't leave ips twice */
 	wiphy_work_cancel(hw->wiphy, &rtwdev->ips_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	if ((changed & IEEE80211_CONF_CHANGE_IDLE) &&
@@ -100,8 +98,6 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
 	    !rtwdev->scanning)
 		rtw89_enter_ips(rtwdev);
 
-	mutex_unlock(&rtwdev->mutex);
-
 	return 0;
 }
 
@@ -142,9 +138,8 @@ static int __rtw89_ops_add_iface_link(struct rtw89_dev *rtwdev,
 static void __rtw89_ops_remove_iface_link(struct rtw89_dev *rtwdev,
 					  struct rtw89_vif_link *rtwvif_link)
 {
-	mutex_unlock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	wiphy_work_cancel(rtwdev->hw->wiphy, &rtwvif_link->update_beacon_work);
-	mutex_lock(&rtwdev->mutex);
 
 	rtw89_leave_ps_mode(rtwdev);
 
@@ -165,7 +160,7 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	rtw89_debug(rtwdev, RTW89_DBG_STATE, "add vif %pM type %d, p2p %d\n",
 		    vif->addr, vif->type, vif->p2p);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtw89_leave_ips_by_hwflags(rtwdev);
 
@@ -213,8 +208,6 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 		goto unset_link;
 
 	rtw89_recalc_lps(rtwdev);
-
-	mutex_unlock(&rtwdev->mutex);
 	return 0;
 
 unset_link:
@@ -225,7 +218,6 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 release_macid:
 	rtw89_release_mac_id(rtwdev, mac_id);
 err:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -244,7 +236,7 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw,
 
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtwvif->links[RTW89_VIF_IDLE_LINK_ID];
 	if (unlikely(!rtwvif_link)) {
@@ -265,8 +257,6 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw,
 
 	rtw89_recalc_lps(rtwdev);
 	rtw89_enter_ips_by_hwflags(rtwdev);
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_change_interface(struct ieee80211_hw *hw,
@@ -304,7 +294,7 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u32 rx_fltr;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	*new_flags &= FIF_ALLMULTI | FIF_OTHER_BSS | FIF_FCSFAIL |
@@ -374,7 +364,6 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 			   rx_fltr);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static const u8 ac_to_fw_idx[IEEE80211_NUM_ACS] = {
@@ -689,7 +678,7 @@ static void rtw89_ops_vif_cfg_changed(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	if (changed & BSS_CHANGED_ASSOC) {
@@ -712,8 +701,6 @@ static void rtw89_ops_vif_cfg_changed(struct ieee80211_hw *hw,
 
 	if (changed & BSS_CHANGED_ARP_FILTER)
 		rtwvif->ip_addr = vif->cfg.arp_addr_list[0];
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
@@ -725,7 +712,7 @@ static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	rtwvif_link = rtwvif->links[conf->link_id];
@@ -765,7 +752,6 @@ static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
 		rtw89_reg_6ghz_recalc(rtwdev, rtwvif_link, true);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
@@ -778,7 +764,7 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 	const struct rtw89_chan *chan;
 	int ret = 0;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtwvif->links[link_conf->link_id];
 	if (unlikely(!rtwvif_link)) {
@@ -791,7 +777,6 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 
 	chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx);
 	if (chan->band_type == RTW89_BAND_6G) {
-		mutex_unlock(&rtwdev->mutex);
 		return -EOPNOTSUPP;
 	}
 
@@ -816,7 +801,6 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 	rtw89_queue_chanctx_work(rtwdev);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -829,7 +813,7 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtwvif->links[link_conf->link_id];
 	if (unlikely(!rtwvif_link)) {
@@ -847,7 +831,6 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	rtw89_fw_h2c_join_info(rtwdev, rtwvif_link, NULL, true);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
@@ -874,7 +857,7 @@ static int rtw89_ops_conf_tx(struct ieee80211_hw *hw,
 	struct rtw89_vif_link *rtwvif_link;
 	int ret = 0;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	rtwvif_link = rtwvif->links[link_id];
@@ -890,7 +873,6 @@ static int rtw89_ops_conf_tx(struct ieee80211_hw *hw,
 	__rtw89_conf_tx(rtwdev, rtwvif_link, ac);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -938,10 +920,9 @@ static int rtw89_ops_sta_state(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	ret = __rtw89_ops_sta_state(hw, vif, sta, old_state, new_state);
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -954,7 +935,7 @@ static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret = 0;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	switch (cmd) {
@@ -979,7 +960,6 @@ static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	}
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -1002,32 +982,28 @@ static int rtw89_ops_ampdu_action(struct ieee80211_hw *hw,
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		clear_bit(RTW89_TXQ_F_AMPDU, &rtwtxq->flags);
 		clear_bit(tid, rtwsta->ampdu_map);
 		rtw89_chip_h2c_ampdu_cmac_tbl(rtwdev, rtwvif, rtwsta);
-		mutex_unlock(&rtwdev->mutex);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		set_bit(RTW89_TXQ_F_AMPDU, &rtwtxq->flags);
 		rtwsta->ampdu_params[tid].agg_num = params->buf_size;
 		rtwsta->ampdu_params[tid].amsdu = params->amsdu;
 		set_bit(tid, rtwsta->ampdu_map);
 		rtw89_leave_ps_mode(rtwdev);
 		rtw89_chip_h2c_ampdu_cmac_tbl(rtwdev, rtwvif, rtwsta);
-		mutex_unlock(&rtwdev->mutex);
 		break;
 	case IEEE80211_AMPDU_RX_START:
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_chip_h2c_ba_cam(rtwdev, rtwsta, true, params);
-		mutex_unlock(&rtwdev->mutex);
 		break;
 	case IEEE80211_AMPDU_RX_STOP:
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_chip_h2c_ba_cam(rtwdev, rtwsta, false, params);
-		mutex_unlock(&rtwdev->mutex);
 		break;
 	default:
 		WARN_ON(1);
@@ -1041,11 +1017,10 @@ static int rtw89_ops_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	if (test_bit(RTW89_FLAG_POWERON, rtwdev->flags))
 		rtw89_mac_update_rts_threshold(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
 }
@@ -1085,7 +1060,7 @@ static void rtw89_ops_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_lps(rtwdev);
 	rtw89_hci_flush_queues(rtwdev, queues, drop);
 
@@ -1093,8 +1068,6 @@ static void rtw89_ops_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		__rtw89_drop_packets(rtwdev, vif);
 	else
 		rtw89_mac_flush_txq(rtwdev, queues, drop);
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 struct rtw89_iter_bitrate_mask_data {
@@ -1141,10 +1114,9 @@ static int rtw89_ops_set_bitrate_mask(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_phy_rate_pattern_vif(rtwdev, vif, mask);
 	rtw89_ra_mask_info_update(rtwdev, vif, mask);
-	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
 }
@@ -1162,12 +1134,11 @@ int rtw89_ops_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 		return -EINVAL;
 	}
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	hal->antenna_tx = tx_ant;
 	hal->antenna_rx = rx_ant;
 	hal->tx_path_diversity = false;
 	hal->ant_diversity_fixed = true;
-	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
 }
@@ -1192,7 +1163,7 @@ static void rtw89_ops_sw_scan_start(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
@@ -1203,7 +1174,6 @@ static void rtw89_ops_sw_scan_start(struct ieee80211_hw *hw,
 	rtw89_core_scan_start(rtwdev, rtwvif_link, mac_addr, false);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
@@ -1213,7 +1183,7 @@ static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
@@ -1224,7 +1194,6 @@ static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
 	rtw89_core_scan_complete(rtwdev, rtwvif_link, false);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_ops_reconfig_complete(struct ieee80211_hw *hw,
@@ -1247,7 +1216,7 @@ static int rtw89_ops_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw))
 		return 1;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	if (rtwdev->scanning || rtwvif->offchan) {
 		ret = -EBUSY;
@@ -1269,7 +1238,6 @@ static int rtw89_ops_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	}
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -1284,7 +1252,7 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw,
 	if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw))
 		return;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	if (!rtwdev->scanning)
 		goto out;
@@ -1298,7 +1266,6 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw,
 	rtw89_hw_scan_abort(rtwdev, rtwvif_link);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_ops_sta_rc_update(struct ieee80211_hw *hw,
@@ -1323,9 +1290,8 @@ static int rtw89_ops_add_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	ret = rtw89_chanctx_ops_add(rtwdev, ctx);
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -1335,9 +1301,8 @@ static void rtw89_ops_remove_chanctx(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_chanctx_ops_remove(rtwdev, ctx);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_ops_change_chanctx(struct ieee80211_hw *hw,
@@ -1346,9 +1311,8 @@ static void rtw89_ops_change_chanctx(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_chanctx_ops_change(rtwdev, ctx, changed);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_assign_vif_chanctx(struct ieee80211_hw *hw,
@@ -1361,7 +1325,7 @@ static int rtw89_ops_assign_vif_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_vif_link *rtwvif_link;
 	int ret;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtwvif->links[link_conf->link_id];
 	if (unlikely(!rtwvif_link)) {
@@ -1375,7 +1339,6 @@ static int rtw89_ops_assign_vif_chanctx(struct ieee80211_hw *hw,
 	ret = rtw89_chanctx_ops_assign_vif(rtwdev, rtwvif_link, ctx);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 
 	return ret;
 }
@@ -1389,11 +1352,10 @@ static void rtw89_ops_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtwvif_link = rtwvif->links[link_conf->link_id];
 	if (unlikely(!rtwvif_link)) {
-		mutex_unlock(&rtwdev->mutex);
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, link_conf->link_id);
@@ -1401,7 +1363,6 @@ static void rtw89_ops_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	}
 
 	rtw89_chanctx_ops_unassign_vif(rtwdev, rtwvif_link, ctx);
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static int rtw89_ops_remain_on_channel(struct ieee80211_hw *hw,
@@ -1417,10 +1378,9 @@ static int rtw89_ops_remain_on_channel(struct ieee80211_hw *hw,
 	if (!rtwvif)
 		return -EINVAL;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	if (roc->state != RTW89_ROC_IDLE) {
-		mutex_unlock(&rtwdev->mutex);
 		return -EBUSY;
 	}
 
@@ -1438,8 +1398,6 @@ static int rtw89_ops_remain_on_channel(struct ieee80211_hw *hw,
 
 	rtw89_roc_start(rtwdev, rtwvif);
 
-	mutex_unlock(&rtwdev->mutex);
-
 	return 0;
 }
 
@@ -1454,9 +1412,8 @@ static int rtw89_ops_cancel_remain_on_channel(struct ieee80211_hw *hw,
 
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_roc_end(rtwdev, rtwvif);
-	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
 }
@@ -1477,14 +1434,13 @@ static int rtw89_ops_set_tid_config(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	if (sta)
 		rtw89_core_set_tid_config(rtwdev, sta, tid_config);
 	else
 		ieee80211_iterate_stations_atomic(rtwdev->hw,
 						  rtw89_set_tid_config_iter,
 						  tid_config);
-	mutex_unlock(&rtwdev->mutex);
 
 	return 0;
 }
@@ -1508,7 +1464,7 @@ static bool rtw89_ops_can_activate_links(struct ieee80211_hw *hw,
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	guard(mutex)(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	return rtw89_can_work_on_links(rtwdev, vif, active_links);
 }
@@ -1570,7 +1526,7 @@ int rtw89_ops_change_vif_links(struct ieee80211_hw *hw,
 	int ret = 0;
 	int i;
 
-	guard(mutex)(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtw89_debug(rtwdev, RTW89_DBG_STATE,
 		    "%s: old_links (0x%08x) -> new_links (0x%08x)\n",
@@ -1719,7 +1675,7 @@ int rtw89_ops_change_sta_links(struct ieee80211_hw *hw,
 	unsigned long set_links = new_links & ~old_links;
 	int ret = 0;
 
-	guard(mutex)(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	rtw89_debug(rtwdev, RTW89_DBG_STATE,
 		    "%s: old_links (0x%08x) -> new_links (0x%08x)\n",
@@ -1752,9 +1708,8 @@ static int rtw89_ops_suspend(struct ieee80211_hw *hw,
 	set_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwdev->track_work);
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	ret = rtw89_wow_suspend(rtwdev, wowlan);
-	mutex_unlock(&rtwdev->mutex);
 
 	if (ret) {
 		rtw89_warn(rtwdev, "failed to suspend for wow %d\n", ret);
@@ -1770,11 +1725,10 @@ static int rtw89_ops_resume(struct ieee80211_hw *hw)
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 	ret = rtw89_wow_resume(rtwdev);
 	if (ret)
 		rtw89_warn(rtwdev, "failed to resume for wow %d\n", ret);
-	mutex_unlock(&rtwdev->mutex);
 
 	clear_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
 	wiphy_delayed_work_queue(hw->wiphy, &rtwdev->track_work,
@@ -1804,12 +1758,10 @@ static void rtw89_set_rekey_data(struct ieee80211_hw *hw,
 		return;
 	}
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	memcpy(gtk_info->kek, data->kek, data->kek_len);
 	memcpy(gtk_info->kck, data->kck, data->kck_len);
-
-	mutex_unlock(&rtwdev->mutex);
 }
 #endif
 
@@ -1817,7 +1769,7 @@ static void rtw89_ops_rfkill_poll(struct ieee80211_hw *hw)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(hw->wiphy);
 
 	/* wl_disable GPIO get floating when entering LPS */
 	if (test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
@@ -1826,7 +1778,6 @@ static void rtw89_ops_rfkill_poll(struct ieee80211_hw *hw)
 	rtw89_core_rfkill_poll(rtwdev, false);
 
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 const struct ieee80211_ops rtw89_ops = {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index fc8a93573144c..26370eadf77f3 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -4661,7 +4661,7 @@ void rtw89_phy_cfo_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 						cfo_track_work.work);
 	struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	if (!cfo->cfo_trig_by_timer_en)
 		goto out;
 	rtw89_leave_ps_mode(rtwdev);
@@ -4669,7 +4669,6 @@ void rtw89_phy_cfo_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 	wiphy_delayed_work_queue(wiphy, &rtwdev->cfo_track_work,
 				 msecs_to_jiffies(cfo->cfo_timer_ms));
 out:
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_phy_cfo_start_work(struct rtw89_dev *rtwdev)
@@ -6537,7 +6536,7 @@ void rtw89_phy_antdiv_work(struct wiphy *wiphy, struct wiphy_work *work)
 						antdiv_work.work);
 	struct rtw89_antdiv_info *antdiv = &rtwdev->antdiv;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 
 	if (antdiv->training_count <= ANTDIV_TRAINNING_CNT) {
 		rtw89_phy_antdiv_training_state(rtwdev);
@@ -6545,8 +6544,6 @@ void rtw89_phy_antdiv_work(struct wiphy *wiphy, struct wiphy_work *work)
 		rtw89_phy_antdiv_decision_state(rtwdev);
 		rtw89_phy_antdiv_set_ant(rtwdev);
 	}
-
-	mutex_unlock(&rtwdev->mutex);
 }
 
 void rtw89_phy_antdiv_track(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/ps.c b/drivers/net/wireless/realtek/rtw89/ps.c
index 96ea04d90cd36..ac46a7baa00db 100644
--- a/drivers/net/wireless/realtek/rtw89/ps.c
+++ b/drivers/net/wireless/realtek/rtw89/ps.c
@@ -113,7 +113,7 @@ static void __rtw89_leave_lps(struct rtw89_dev *rtwdev,
 
 void rtw89_leave_ps_mode(struct rtw89_dev *rtwdev)
 {
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	__rtw89_leave_ps_mode(rtwdev);
 }
@@ -125,7 +125,7 @@ void rtw89_enter_lps(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif,
 	bool can_ps_mode = true;
 	unsigned int link_id;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (test_and_set_bit(RTW89_FLAG_LEISURE_PS, rtwdev->flags))
 		return;
@@ -162,7 +162,7 @@ void rtw89_leave_lps(struct rtw89_dev *rtwdev)
 	struct rtw89_vif *rtwvif;
 	unsigned int link_id;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (!test_and_clear_bit(RTW89_FLAG_LEISURE_PS, rtwdev->flags))
 		return;
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 46f5c7eb16830..cc4b080ecc3ca 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -745,7 +745,7 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	wiphy_lock(wiphy);
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	if (wiphy->regd) {
@@ -761,7 +761,6 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 	rtw89_core_set_chip_txpwr(rtwdev);
 
 exit:
-	mutex_unlock(&rtwdev->mutex);
 	wiphy_unlock(wiphy);
 }
 
@@ -1012,7 +1011,7 @@ int rtw89_reg_6ghz_recalc(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvi
 	unsigned int changed = 0;
 	int ret;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	/* The result of reg_6ghz_tpe may depend on reg_6ghz_power type,
 	 * so must do reg_6ghz_tpe_recalc() after reg_6ghz_power_recalc().
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 1f67a2fbce818..949edb4bd4dfa 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -150,7 +150,7 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 	s32 cfg;
 	u8 fct;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return RTW89_SAR_TXPWR_MAC_MAX;
@@ -190,7 +190,7 @@ int rtw89_print_sar(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 	s32 cfg;
 	u8 fct;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (src == RTW89_SAR_SOURCE_NONE) {
 		p += scnprintf(p, end - p, "no SAR is applied\n");
@@ -241,7 +241,7 @@ static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 	enum rtw89_sar_sources src;
 	int ret = 0;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	src = rtwdev->sar.src;
 	if (src != RTW89_SAR_SOURCE_NONE && src != RTW89_SAR_SOURCE_COMMON) {
@@ -254,7 +254,6 @@ static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 	rtw89_core_set_chip_txpwr(rtwdev);
 
 exit:
-	mutex_unlock(&rtwdev->mutex);
 	return ret;
 }
 
@@ -328,7 +327,7 @@ static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
 	const struct rtw89_chan *chan;
 	int ret;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	if (src == RTW89_SAR_SOURCE_NONE)
 		return;
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index 9658672ad2744..b9607bdca6c8b 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -157,9 +157,8 @@ static void ser_state_run(struct rtw89_ser *ser, u8 evt)
 		    ser_st_name(ser), ser_ev_name(ser, evt));
 
 	wiphy_lock(rtwdev->hw->wiphy);
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	rtw89_leave_lps(rtwdev);
-	mutex_unlock(&rtwdev->mutex);
 	wiphy_unlock(rtwdev->hw->wiphy);
 
 	ser->st_tbl[ser->state].st_func(ser, evt);
@@ -714,9 +713,8 @@ static void ser_l2_reset_st_hdl(struct rtw89_ser *ser, u8 evt)
 	switch (evt) {
 	case SER_EV_STATE_IN:
 		wiphy_lock(rtwdev->hw->wiphy);
-		mutex_lock(&rtwdev->mutex);
+		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		ser_l2_reset_st_pre_hdl(ser);
-		mutex_unlock(&rtwdev->mutex);
 		wiphy_unlock(rtwdev->hw->wiphy);
 
 		ieee80211_restart_hw(rtwdev->hw);
diff --git a/drivers/net/wireless/realtek/rtw89/util.h b/drivers/net/wireless/realtek/rtw89/util.h
index 71c7d3502202c..df283a8580464 100644
--- a/drivers/net/wireless/realtek/rtw89/util.h
+++ b/drivers/net/wireless/realtek/rtw89/util.h
@@ -25,7 +25,7 @@ static inline bool rtw89_rtwvif_in_list(struct rtw89_dev *rtwdev,
 {
 	struct rtw89_vif *rtwvif;
 
-	lockdep_assert_held(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	rtw89_for_each_rtwvif(rtwdev, rtwvif)
 		if (rtwvif == new)
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 01754d031bb43..6031633b27098 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -619,12 +619,11 @@ static struct ieee80211_key_conf *rtw89_wow_gtk_rekey(struct rtw89_dev *rtwdev,
 	/* ieee80211_gtk_rekey_add() will call set_key(), therefore we
 	 * need to unlock mutex
 	 */
-	mutex_unlock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	if (ieee80211_vif_is_mld(wow_vif))
 		key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, rtwvif_link->link_id);
 	else
 		key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, -1);
-	mutex_lock(&rtwdev->mutex);
 
 	kfree(rekey_conf);
 	if (IS_ERR(key)) {

From ed114a7ac636b7151b41935d566d07b2a84b092a Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:08 +0800
Subject: [PATCH 0073/2753] wifi: rtw89: manual cosmetic along
 lockdep_assert_wiphy()

With spatch script, already remove most driver mutex and generate
lockdep_assert_wiphy(), and some are needed to refine manually further to
be expected:

- lockdep_assert_wiphy() always be the first statement in function
- return directly rather than unnecessary goto
- change assert from mutex to wiphy lock, which script can't convert
  automatically.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-9-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c     |   3 +-
 drivers/net/wireless/realtek/rtw89/coex.c     |   7 +
 drivers/net/wireless/realtek/rtw89/core.c     |  23 ++-
 drivers/net/wireless/realtek/rtw89/debug.c    |  30 ++--
 drivers/net/wireless/realtek/rtw89/fw.c       |   7 +-
 drivers/net/wireless/realtek/rtw89/mac80211.c | 157 +++++++-----------
 drivers/net/wireless/realtek/rtw89/phy.c      |   4 +-
 drivers/net/wireless/realtek/rtw89/regd.c     |   1 -
 drivers/net/wireless/realtek/rtw89/sar.c      |  11 +-
 drivers/net/wireless/realtek/rtw89/ser.c      |   2 -
 drivers/net/wireless/realtek/rtw89/util.h     |   2 +-
 drivers/net/wireless/realtek/rtw89/wow.c      |   6 +-
 12 files changed, 112 insertions(+), 141 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index 98f4202086320..be6d732739104 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -2403,9 +2403,8 @@ void rtw89_chanctx_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	lockdep_assert_wiphy(wiphy);
 
-	if (hal->entity_pause) {
+	if (hal->entity_pause)
 		return;
-	}
 
 	for (i = 0; i < NUM_OF_RTW89_CHANCTX_CHANGES; i++) {
 		if (test_and_clear_bit(i, hal->changes))
diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index a7b7675dca97a..2c0ccf2f8bd96 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -6722,6 +6722,7 @@ void rtw89_coex_act1_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	if (wl->status.map._4way)
@@ -6741,6 +6742,7 @@ void rtw89_coex_bt_devinfo_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_bt_a2dp_desc *a2dp = &btc->cx.bt.link_info.a2dp_desc;
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	a2dp->play_latency = 0;
@@ -6757,6 +6759,7 @@ void rtw89_coex_rfk_chk_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_btc_wl_info *wl = &cx->wl;
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_debug(rtwdev, RTW89_DBG_BTC, "[BTC], %s(): enter\n", __func__);
 	dm->cnt_notify[BTC_NCNT_TIMER]++;
 	if (wl->rfk_info.state != BTC_WRFK_STOP) {
@@ -7309,6 +7312,7 @@ void rtw89_btc_ntfy_eapol_packet_work(struct wiphy *wiphy, struct wiphy_work *wo
 						btc.eapol_notify_work);
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_EAPOL);
 }
@@ -7319,6 +7323,7 @@ void rtw89_btc_ntfy_arp_packet_work(struct wiphy *wiphy, struct wiphy_work *work
 						btc.arp_notify_work);
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_ARP);
 }
 
@@ -7328,6 +7333,7 @@ void rtw89_btc_ntfy_dhcp_packet_work(struct wiphy *wiphy, struct wiphy_work *wor
 						btc.dhcp_notify_work);
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_DHCP);
 }
@@ -7338,6 +7344,7 @@ void rtw89_btc_ntfy_icmp_packet_work(struct wiphy *wiphy, struct wiphy_work *wor
 						btc.icmp_notify_work);
 
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_btc_ntfy_specific_packet(rtwdev, PACKET_ICMP);
 }
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 602185b3c9b04..4e6d117439a5f 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2082,7 +2082,7 @@ static void rtw89_cancel_6ghz_probe_work(struct wiphy *wiphy, struct wiphy_work
 	lockdep_assert_wiphy(wiphy);
 
 	if (!rtwdev->scanning)
-		goto out;
+		return;
 
 	list_for_each_entry(info, &pkt_list[NL80211_BAND_6GHZ], list) {
 		if (!info->cancel || !test_bit(info->id, rtwdev->pkt_offload))
@@ -2095,8 +2095,6 @@ static void rtw89_cancel_6ghz_probe_work(struct wiphy *wiphy, struct wiphy_work
 		 * since if during scanning, pkt_list is accessed in bottom half.
 		 */
 	}
-
-out:
 }
 
 static void rtw89_core_cancel_6ghz_probe_tx(struct rtw89_dev *rtwdev,
@@ -3147,7 +3145,9 @@ static void rtw89_ips_work(struct wiphy *wiphy, struct wiphy_work *work)
 {
 	struct rtw89_dev *rtwdev = container_of(work, struct rtw89_dev,
 						ips_work);
+
 	lockdep_assert_wiphy(wiphy);
+
 	rtw89_enter_ips_by_hwflags(rtwdev);
 }
 
@@ -3536,20 +3536,20 @@ static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 						track_work.work);
 	bool tfc_changed;
 
+	lockdep_assert_wiphy(wiphy);
+
 	if (test_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags))
 		return;
 
-	lockdep_assert_wiphy(wiphy);
-
 	if (!test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
-		goto out;
+		return;
 
 	wiphy_delayed_work_queue(wiphy, &rtwdev->track_work,
 				 RTW89_TRACK_WORK_PERIOD);
 
 	tfc_changed = rtw89_traffic_stats_track(rtwdev);
 	if (rtwdev->scanning)
-		goto out;
+		return;
 
 	rtw89_leave_lps(rtwdev);
 
@@ -3574,8 +3574,6 @@ static void rtw89_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 
 	if (rtwdev->lps_enabled && !rtwdev->btc.lps)
 		rtw89_enter_lps_track(rtwdev);
-
-out:
 }
 
 u8 rtw89_core_acquire_bit_map(unsigned long *addr, unsigned long size)
@@ -4440,12 +4438,13 @@ void rtw89_core_update_beacon_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_vif_link *rtwvif_link = container_of(work, struct rtw89_vif_link,
 							  update_beacon_work);
 
+	lockdep_assert_wiphy(wiphy);
+
 	if (rtwvif_link->net_type != RTW89_NET_TYPE_AP_MODE)
 		return;
 
 	rtwdev = rtwvif_link->rtwvif->rtwdev;
 
-	lockdep_assert_wiphy(wiphy);
 	rtw89_chip_h2c_update_beacon(rtwdev, rtwvif_link);
 }
 
@@ -4581,6 +4580,8 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 	struct wiphy *wiphy = rtwdev->hw->wiphy;
 	struct rtw89_btc *btc = &rtwdev->btc;
 
+	lockdep_assert_wiphy(wiphy);
+
 	/* Prvent to stop twice; enter_ips and ops_stop */
 	if (!test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
 		return;
@@ -4589,8 +4590,6 @@ void rtw89_core_stop(struct rtw89_dev *rtwdev)
 
 	clear_bit(RTW89_FLAG_RUNNING, rtwdev->flags);
 
-	lockdep_assert_wiphy(wiphy);
-
 	wiphy_work_cancel(wiphy, &rtwdev->c2h_work);
 	wiphy_work_cancel(wiphy, &rtwdev->cancel_6ghz_probe_work);
 	wiphy_work_cancel(wiphy, &btc->eapol_notify_work);
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 56be6705e9ea3..885a5ebeb6cd5 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -955,6 +955,7 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 	ssize_t n;
 
 	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 
@@ -970,34 +971,28 @@ ssize_t rtw89_debug_priv_txpwr_table_get(struct rtw89_dev *rtwdev,
 	p += rtw89_print_ant_gain(rtwdev, p, end - p, chan);
 
 	tbl = dbgfs_txpwr_tables[chip_gen];
-	if (!tbl) {
-		n = -EOPNOTSUPP;
-		goto err;
-	}
+	if (!tbl)
+		return -EOPNOTSUPP;
 
 	p += scnprintf(p, end - p, "\n[TX power byrate]\n");
 	n = __print_txpwr_map(rtwdev, p, end - p, tbl->byr);
 	if (n < 0)
-		goto err;
+		return n;
 	p += n;
 
 	p += scnprintf(p, end - p, "\n[TX power limit]\n");
 	n = __print_txpwr_map(rtwdev, p, end - p, tbl->lmt);
 	if (n < 0)
-		goto err;
+		return n;
 	p += n;
 
 	p += scnprintf(p, end - p, "\n[TX power limit_ru]\n");
 	n = __print_txpwr_map(rtwdev, p, end - p, tbl->lmt_ru);
 	if (n < 0)
-		goto err;
+		return n;
 	p += n;
 
 	return p - buf;
-
-err:
-
-	return n;
 }
 
 static ssize_t
@@ -1182,6 +1177,8 @@ rtw89_debug_priv_mac_mem_dump_get(struct rtw89_dev *rtwdev,
 	char *p = buf, *end = buf + bufsz;
 	bool grant_read = false;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	if (debugfs_priv->mac_mem.sel >= RTW89_MAC_MEM_NUM)
 		return -ENOENT;
 
@@ -1198,7 +1195,6 @@ rtw89_debug_priv_mac_mem_dump_get(struct rtw89_dev *rtwdev,
 		}
 	}
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 	if (grant_read)
 		rtw89_write32_set(rtwdev, R_AX_TCR1, B_AX_TCR_FORCE_READ_TXDFIFO);
@@ -3515,6 +3511,7 @@ rtw89_debug_priv_early_h2c_get(struct rtw89_dev *rtwdev,
 	int seq = 0;
 
 	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	list_for_each_entry(early_h2c, &rtwdev->early_h2c_list, list)
 		p += scnprintf(p, end - p, "%d: %*ph\n", ++seq,
 			       early_h2c->h2c_len, early_h2c->h2c);
@@ -3531,6 +3528,8 @@ rtw89_debug_priv_early_h2c_set(struct rtw89_dev *rtwdev,
 	u8 *h2c;
 	u16 h2c_len = count / 2;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	h2c = rtw89_hex2bin(rtwdev, buf, count);
 	if (IS_ERR(h2c))
 		return -EFAULT;
@@ -3550,7 +3549,6 @@ rtw89_debug_priv_early_h2c_set(struct rtw89_dev *rtwdev,
 	early_h2c->h2c = h2c;
 	early_h2c->h2c_len = h2c_len;
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	list_add_tail(&early_h2c->list, &rtwdev->early_h2c_list);
 
 out:
@@ -3610,6 +3608,8 @@ rtw89_debug_priv_fw_crash_set(struct rtw89_dev *rtwdev,
 	u8 crash_type;
 	int ret;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	ret = kstrtou8(buf, 0, &crash_type);
 	if (ret)
 		return -EINVAL;
@@ -3627,7 +3627,6 @@ rtw89_debug_priv_fw_crash_set(struct rtw89_dev *rtwdev,
 		return -EINVAL;
 	}
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	set_bit(RTW89_FLAG_CRASH_SIMULATING, rtwdev->flags);
 	ret = sim(rtwdev);
 
@@ -3671,10 +3670,11 @@ static ssize_t rtw89_debug_priv_fw_log_manual_set(struct rtw89_dev *rtwdev,
 	struct rtw89_fw_log *log = &rtwdev->fw.log;
 	bool fw_log_manual;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	if (kstrtobool(buf, &fw_log_manual))
 		goto out;
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	log->enable = fw_log_manual;
 	if (log->enable)
 		rtw89_fw_log_prepare(rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 2713bae449900..2982ec367d9d5 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6107,13 +6107,13 @@ void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_early_h2c *early_h2c, *tmp;
 
-	mutex_lock(&rtwdev->mutex);
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	list_for_each_entry_safe(early_h2c, tmp, &rtwdev->early_h2c_list, list) {
 		list_del(&early_h2c->list);
 		kfree(early_h2c->h2c);
 		kfree(early_h2c);
 	}
-	mutex_unlock(&rtwdev->mutex);
 }
 
 static void rtw89_fw_c2h_parse_attr(struct sk_buff *c2h)
@@ -6201,9 +6201,10 @@ void rtw89_fw_c2h_work(struct wiphy *wiphy, struct wiphy_work *work)
 						c2h_work);
 	struct sk_buff *skb, *tmp;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	skb_queue_walk_safe(&rtwdev->c2h_queue, skb, tmp) {
 		skb_unlink(skb, &rtwdev->c2h_queue);
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_fw_c2h_cmd_handle(rtwdev, skb);
 		dev_kfree_skb_any(skb);
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 11516ede13e49..778ca85892845 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -57,12 +57,10 @@ static void rtw89_ops_wake_tx_queue(struct ieee80211_hw *hw,
 static int rtw89_ops_start(struct ieee80211_hw *hw)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
-	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
-	ret = rtw89_core_start(rtwdev);
 
-	return ret;
+	return rtw89_core_start(rtwdev);
 }
 
 static void rtw89_ops_stop(struct ieee80211_hw *hw, bool suspend)
@@ -70,6 +68,7 @@ static void rtw89_ops_stop(struct ieee80211_hw *hw, bool suspend)
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_core_stop(rtwdev);
 }
 
@@ -77,10 +76,11 @@ static int rtw89_ops_config(struct ieee80211_hw *hw, u32 changed)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	/* let previous ips work finish to ensure we don't leave ips twice */
 	wiphy_work_cancel(hw->wiphy, &rtwdev->ips_work);
 
-	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	if ((changed & IEEE80211_CONF_CHANGE_IDLE) &&
@@ -139,6 +139,7 @@ static void __rtw89_ops_remove_iface_link(struct rtw89_dev *rtwdev,
 					  struct rtw89_vif_link *rtwvif_link)
 {
 	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	wiphy_work_cancel(rtwdev->hw->wiphy, &rtwvif_link->update_beacon_work);
 
 	rtw89_leave_ps_mode(rtwdev);
@@ -157,11 +158,11 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	u8 mac_id, port;
 	int ret = 0;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_debug(rtwdev, RTW89_DBG_STATE, "add vif %pM type %d, p2p %d\n",
 		    vif->addr, vif->type, vif->p2p);
 
-	lockdep_assert_wiphy(hw->wiphy);
-
 	rtw89_leave_ips_by_hwflags(rtwdev);
 
 	if (RTW89_CHK_FW_FEATURE(BEACON_FILTER, &rtwdev->fw))
@@ -169,10 +170,8 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 				     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
 
 	mac_id = rtw89_acquire_mac_id(rtwdev);
-	if (mac_id == RTW89_MAX_MAC_ID_NUM) {
-		ret = -ENOSPC;
-		goto err;
-	}
+	if (mac_id == RTW89_MAX_MAC_ID_NUM)
+		return -ENOSPC;
 
 	port = rtw89_core_acquire_bit_map(rtwdev->hw_port, RTW89_PORT_NUM);
 	if (port == RTW89_PORT_NUM) {
@@ -217,7 +216,6 @@ static int rtw89_ops_add_interface(struct ieee80211_hw *hw,
 	rtw89_core_release_bit_map(rtwdev->hw_port, port);
 release_macid:
 	rtw89_release_mac_id(rtwdev, mac_id);
-err:
 
 	return ret;
 }
@@ -231,13 +229,13 @@ static void rtw89_ops_remove_interface(struct ieee80211_hw *hw,
 	u8 port = rtw89_vif_get_main_port(rtwvif);
 	struct rtw89_vif_link *rtwvif_link;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_debug(rtwdev, RTW89_DBG_STATE, "remove vif %pM type %d p2p %d\n",
 		    vif->addr, vif->type, vif->p2p);
 
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
-	lockdep_assert_wiphy(hw->wiphy);
-
 	rtwvif_link = rtwvif->links[RTW89_VIF_IDLE_LINK_ID];
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev,
@@ -295,6 +293,7 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 	u32 rx_fltr;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	*new_flags &= FIF_ALLMULTI | FIF_OTHER_BSS | FIF_FCSFAIL |
@@ -357,13 +356,11 @@ static void rtw89_ops_configure_filter(struct ieee80211_hw *hw,
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rx_fltr);
 	if (!rtwdev->dbcc_en)
-		goto out;
+		return;
 	rtw89_write32_mask(rtwdev,
 			   rtw89_mac_reg_by_idx(rtwdev, mac->rx_fltr, RTW89_MAC_1),
 			   B_AX_RX_FLTR_CFG_MASK,
 			   rx_fltr);
-
-out:
 }
 
 static const u8 ac_to_fw_idx[IEEE80211_NUM_ACS] = {
@@ -679,6 +676,7 @@ static void rtw89_ops_vif_cfg_changed(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	if (changed & BSS_CHANGED_ASSOC) {
@@ -713,6 +711,7 @@ static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
 	struct rtw89_vif_link *rtwvif_link;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	rtwvif_link = rtwvif->links[conf->link_id];
@@ -720,7 +719,7 @@ static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, conf->link_id);
-		goto out;
+		return;
 	}
 
 	if (changed & BSS_CHANGED_BSSID) {
@@ -750,8 +749,6 @@ static void rtw89_ops_link_info_changed(struct ieee80211_hw *hw,
 
 	if (changed & BSS_CHANGED_TPE)
 		rtw89_reg_6ghz_recalc(rtwdev, rtwvif_link, true);
-
-out:
 }
 
 static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
@@ -771,14 +768,12 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, link_conf->link_id);
-		ret = -ENOLINK;
-		goto out;
+		return -ENOLINK;
 	}
 
 	chan = rtw89_chan_get(rtwdev, rtwvif_link->chanctx_idx);
-	if (chan->band_type == RTW89_BAND_6G) {
+	if (chan->band_type == RTW89_BAND_6G)
 		return -EOPNOTSUPP;
-	}
 
 	if (rtwdev->scanning)
 		rtw89_hw_scan_abort(rtwdev, rtwdev->scan_info.scanning_vif);
@@ -795,14 +790,12 @@ static int rtw89_ops_start_ap(struct ieee80211_hw *hw,
 	if (RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &rtwdev->fw)) {
 		ret = rtw89_fw_h2c_ap_info_refcount(rtwdev, true);
 		if (ret)
-			goto out;
+			return ret;
 	}
 
 	rtw89_queue_chanctx_work(rtwdev);
 
-out:
-
-	return ret;
+	return 0;
 }
 
 static
@@ -820,7 +813,7 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, link_conf->link_id);
-		goto out;
+		return;
 	}
 
 	if (RTW89_CHK_FW_FEATURE(NOTIFY_AP_INFO, &rtwdev->fw))
@@ -829,8 +822,6 @@ void rtw89_ops_stop_ap(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	rtw89_mac_stop_ap(rtwdev, rtwvif_link);
 	rtw89_chip_h2c_assoc_cmac_tbl(rtwdev, rtwvif_link, NULL);
 	rtw89_fw_h2c_join_info(rtwdev, rtwvif_link, NULL, true);
-
-out:
 }
 
 static int rtw89_ops_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta,
@@ -855,9 +846,9 @@ static int rtw89_ops_conf_tx(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
-	int ret = 0;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	rtwvif_link = rtwvif->links[link_id];
@@ -865,16 +856,13 @@ static int rtw89_ops_conf_tx(struct ieee80211_hw *hw,
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, link_id);
-		ret = -ENOLINK;
-		goto out;
+		return -ENOLINK;
 	}
 
 	rtwvif_link->tx_params[ac] = *params;
 	__rtw89_conf_tx(rtwdev, rtwvif_link, ac);
 
-out:
-
-	return ret;
+	return 0;
 }
 
 static int __rtw89_ops_sta_state(struct ieee80211_hw *hw,
@@ -918,13 +906,11 @@ static int rtw89_ops_sta_state(struct ieee80211_hw *hw,
 			       enum ieee80211_sta_state new_state)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
-	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
-	rtw89_leave_ps_mode(rtwdev);
-	ret = __rtw89_ops_sta_state(hw, vif, sta, old_state, new_state);
 
-	return ret;
+	rtw89_leave_ps_mode(rtwdev);
+	return __rtw89_ops_sta_state(hw, vif, sta, old_state, new_state);
 }
 
 static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
@@ -933,9 +919,10 @@ static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 			     struct ieee80211_key_conf *key)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
-	int ret = 0;
+	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 
 	switch (cmd) {
@@ -944,7 +931,7 @@ static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		ret = rtw89_cam_sec_key_add(rtwdev, vif, sta, key);
 		if (ret && ret != -EOPNOTSUPP) {
 			rtw89_err(rtwdev, "failed to add key to sec cam\n");
-			goto out;
+			return ret;
 		}
 		break;
 	case DISABLE_KEY:
@@ -954,13 +941,11 @@ static int rtw89_ops_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		ret = rtw89_cam_sec_key_del(rtwdev, vif, sta, key, true);
 		if (ret) {
 			rtw89_err(rtwdev, "failed to remove key from sec cam\n");
-			goto out;
+			return ret;
 		}
 		break;
 	}
 
-out:
-
 	return ret;
 }
 
@@ -976,20 +961,20 @@ static int rtw89_ops_ampdu_action(struct ieee80211_hw *hw,
 	struct ieee80211_txq *txq = sta->txq[tid];
 	struct rtw89_txq *rtwtxq = (struct rtw89_txq *)txq->drv_priv;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	switch (params->action) {
 	case IEEE80211_AMPDU_TX_START:
 		return IEEE80211_AMPDU_TX_START_IMMEDIATE;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		clear_bit(RTW89_TXQ_F_AMPDU, &rtwtxq->flags);
 		clear_bit(tid, rtwsta->ampdu_map);
 		rtw89_chip_h2c_ampdu_cmac_tbl(rtwdev, rtwvif, rtwsta);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		set_bit(RTW89_TXQ_F_AMPDU, &rtwtxq->flags);
 		rtwsta->ampdu_params[tid].agg_num = params->buf_size;
 		rtwsta->ampdu_params[tid].amsdu = params->amsdu;
@@ -998,11 +983,9 @@ static int rtw89_ops_ampdu_action(struct ieee80211_hw *hw,
 		rtw89_chip_h2c_ampdu_cmac_tbl(rtwdev, rtwvif, rtwsta);
 		break;
 	case IEEE80211_AMPDU_RX_START:
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_chip_h2c_ba_cam(rtwdev, rtwsta, true, params);
 		break;
 	case IEEE80211_AMPDU_RX_STOP:
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		rtw89_chip_h2c_ba_cam(rtwdev, rtwsta, false, params);
 		break;
 	default:
@@ -1018,6 +1001,7 @@ static int rtw89_ops_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_ps_mode(rtwdev);
 	if (test_bit(RTW89_FLAG_POWERON, rtwdev->flags))
 		rtw89_mac_update_rts_threshold(rtwdev);
@@ -1061,6 +1045,7 @@ static void rtw89_ops_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_leave_lps(rtwdev);
 	rtw89_hci_flush_queues(rtwdev, queues, drop);
 
@@ -1115,6 +1100,7 @@ static int rtw89_ops_set_bitrate_mask(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_phy_rate_pattern_vif(rtwdev, vif, mask);
 	rtw89_ra_mask_info_update(rtwdev, vif, mask);
 
@@ -1127,6 +1113,8 @@ int rtw89_ops_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_hal *hal = &rtwdev->hal;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (hal->ant_diversity) {
 		if (tx_ant != rx_ant || hweight32(tx_ant) != 1)
 			return -EINVAL;
@@ -1134,7 +1122,6 @@ int rtw89_ops_set_antenna(struct ieee80211_hw *hw, u32 tx_ant, u32 rx_ant)
 		return -EINVAL;
 	}
 
-	lockdep_assert_wiphy(hw->wiphy);
 	hal->antenna_tx = tx_ant;
 	hal->antenna_rx = rx_ant;
 	hal->tx_path_diversity = false;
@@ -1168,12 +1155,10 @@ static void rtw89_ops_sw_scan_start(struct ieee80211_hw *hw,
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev, "sw scan start: find no link on HW-0\n");
-		goto out;
+		return;
 	}
 
 	rtw89_core_scan_start(rtwdev, rtwvif_link, mac_addr, false);
-
-out:
 }
 
 static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
@@ -1188,12 +1173,10 @@ static void rtw89_ops_sw_scan_complete(struct ieee80211_hw *hw,
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev, "sw scan complete: find no link on HW-0\n");
-		goto out;
+		return;
 	}
 
 	rtw89_core_scan_complete(rtwdev, rtwvif_link, false);
-
-out:
 }
 
 static void rtw89_ops_reconfig_complete(struct ieee80211_hw *hw,
@@ -1213,21 +1196,18 @@ static int rtw89_ops_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct rtw89_vif_link *rtwvif_link;
 	int ret;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw))
 		return 1;
 
-	lockdep_assert_wiphy(hw->wiphy);
-
-	if (rtwdev->scanning || rtwvif->offchan) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (rtwdev->scanning || rtwvif->offchan)
+		return -EBUSY;
 
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev, "hw scan: find no link on HW-0\n");
-		ret = -ENOLINK;
-		goto out;
+		return -ENOLINK;
 	}
 
 	rtw89_hw_scan_start(rtwdev, rtwvif_link, req);
@@ -1237,8 +1217,6 @@ static int rtw89_ops_hw_scan(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		rtw89_err(rtwdev, "HW scan failed with status: %d\n", ret);
 	}
 
-out:
-
 	return ret;
 }
 
@@ -1249,23 +1227,21 @@ static void rtw89_ops_cancel_hw_scan(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (!RTW89_CHK_FW_FEATURE(SCAN_OFFLOAD, &rtwdev->fw))
 		return;
 
-	lockdep_assert_wiphy(hw->wiphy);
-
 	if (!rtwdev->scanning)
-		goto out;
+		return;
 
 	rtwvif_link = rtw89_vif_get_link_inst(rtwvif, 0);
 	if (unlikely(!rtwvif_link)) {
 		rtw89_err(rtwdev, "cancel hw scan: find no link on HW-0\n");
-		goto out;
+		return;
 	}
 
 	rtw89_hw_scan_abort(rtwdev, rtwvif_link);
-
-out:
 }
 
 static void rtw89_ops_sta_rc_update(struct ieee80211_hw *hw,
@@ -1288,12 +1264,10 @@ static int rtw89_ops_add_chanctx(struct ieee80211_hw *hw,
 				 struct ieee80211_chanctx_conf *ctx)
 {
 	struct rtw89_dev *rtwdev = hw->priv;
-	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
-	ret = rtw89_chanctx_ops_add(rtwdev, ctx);
 
-	return ret;
+	return rtw89_chanctx_ops_add(rtwdev, ctx);
 }
 
 static void rtw89_ops_remove_chanctx(struct ieee80211_hw *hw,
@@ -1302,6 +1276,7 @@ static void rtw89_ops_remove_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_chanctx_ops_remove(rtwdev, ctx);
 }
 
@@ -1312,6 +1287,7 @@ static void rtw89_ops_change_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	rtw89_chanctx_ops_change(rtwdev, ctx, changed);
 }
 
@@ -1323,7 +1299,6 @@ static int rtw89_ops_assign_vif_chanctx(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif(vif);
 	struct rtw89_vif_link *rtwvif_link;
-	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
 
@@ -1332,15 +1307,10 @@ static int rtw89_ops_assign_vif_chanctx(struct ieee80211_hw *hw,
 		rtw89_err(rtwdev,
 			  "%s: rtwvif link (link_id %u) is not active\n",
 			  __func__, link_conf->link_id);
-		ret = -ENOLINK;
-		goto out;
+		return -ENOLINK;
 	}
 
-	ret = rtw89_chanctx_ops_assign_vif(rtwdev, rtwvif_link, ctx);
-
-out:
-
-	return ret;
+	return rtw89_chanctx_ops_assign_vif(rtwdev, rtwvif_link, ctx);
 }
 
 static void rtw89_ops_unassign_vif_chanctx(struct ieee80211_hw *hw,
@@ -1375,11 +1345,11 @@ static int rtw89_ops_remain_on_channel(struct ieee80211_hw *hw,
 	struct rtw89_vif *rtwvif = vif_to_rtwvif_safe(vif);
 	struct rtw89_roc *roc = &rtwvif->roc;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (!rtwvif)
 		return -EINVAL;
 
-	lockdep_assert_wiphy(hw->wiphy);
-
 	if (roc->state != RTW89_ROC_IDLE) {
 		return -EBUSY;
 	}
@@ -1407,12 +1377,13 @@ static int rtw89_ops_cancel_remain_on_channel(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	struct rtw89_vif *rtwvif = vif_to_rtwvif_safe(vif);
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (!rtwvif)
 		return -EINVAL;
 
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwvif->roc.roc_work);
 
-	lockdep_assert_wiphy(hw->wiphy);
 	rtw89_roc_end(rtwdev, rtwvif);
 
 	return 0;
@@ -1435,6 +1406,7 @@ static int rtw89_ops_set_tid_config(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	if (sta)
 		rtw89_core_set_tid_config(rtwdev, sta, tid_config);
 	else
@@ -1705,12 +1677,12 @@ static int rtw89_ops_suspend(struct ieee80211_hw *hw,
 	struct rtw89_dev *rtwdev = hw->priv;
 	int ret;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	set_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
 	wiphy_delayed_work_cancel(hw->wiphy, &rtwdev->track_work);
 
-	lockdep_assert_wiphy(hw->wiphy);
 	ret = rtw89_wow_suspend(rtwdev, wowlan);
-
 	if (ret) {
 		rtw89_warn(rtwdev, "failed to suspend for wow %d\n", ret);
 		clear_bit(RTW89_FLAG_FORBIDDEN_TRACK_WROK, rtwdev->flags);
@@ -1726,6 +1698,7 @@ static int rtw89_ops_resume(struct ieee80211_hw *hw)
 	int ret;
 
 	lockdep_assert_wiphy(hw->wiphy);
+
 	ret = rtw89_wow_resume(rtwdev);
 	if (ret)
 		rtw89_warn(rtwdev, "failed to resume for wow %d\n", ret);
@@ -1752,14 +1725,14 @@ static void rtw89_set_rekey_data(struct ieee80211_hw *hw,
 	struct rtw89_wow_param *rtw_wow = &rtwdev->wow;
 	struct rtw89_wow_gtk_info *gtk_info = &rtw_wow->gtk_info;
 
+	lockdep_assert_wiphy(hw->wiphy);
+
 	if (data->kek_len > sizeof(gtk_info->kek) ||
 	    data->kck_len > sizeof(gtk_info->kck)) {
 		rtw89_warn(rtwdev, "kek or kck length over fw limit\n");
 		return;
 	}
 
-	lockdep_assert_wiphy(hw->wiphy);
-
 	memcpy(gtk_info->kek, data->kek, data->kek_len);
 	memcpy(gtk_info->kck, data->kck, data->kck_len);
 }
@@ -1773,11 +1746,9 @@ static void rtw89_ops_rfkill_poll(struct ieee80211_hw *hw)
 
 	/* wl_disable GPIO get floating when entering LPS */
 	if (test_bit(RTW89_FLAG_RUNNING, rtwdev->flags))
-		goto out;
+		return;
 
 	rtw89_core_rfkill_poll(rtwdev, false);
-
-out:
 }
 
 const struct ieee80211_ops rtw89_ops = {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index 26370eadf77f3..e4b690a5febc9 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -4662,13 +4662,13 @@ void rtw89_phy_cfo_track_work(struct wiphy *wiphy, struct wiphy_work *work)
 	struct rtw89_cfo_tracking_info *cfo = &rtwdev->cfo_tracking;
 
 	lockdep_assert_wiphy(wiphy);
+
 	if (!cfo->cfo_trig_by_timer_en)
-		goto out;
+		return;
 	rtw89_leave_ps_mode(rtwdev);
 	rtw89_phy_cfo_dm(rtwdev);
 	wiphy_delayed_work_queue(wiphy, &rtwdev->cfo_track_work,
 				 msecs_to_jiffies(cfo->cfo_timer_ms));
-out:
 }
 
 static void rtw89_phy_cfo_start_work(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index cc4b080ecc3ca..505a3d0767c60 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -745,7 +745,6 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 	struct rtw89_dev *rtwdev = hw->priv;
 
 	wiphy_lock(wiphy);
-	lockdep_assert_wiphy(wiphy);
 	rtw89_leave_ps_mode(rtwdev);
 
 	if (wiphy->regd) {
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 949edb4bd4dfa..24a32dc4e67d9 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -99,7 +99,7 @@ struct rtw89_sar_handler rtw89_sar_handlers[RTW89_SAR_SOURCE_NR] = {
 		typeof(_dev) _d = (_dev);				\
 		BUILD_BUG_ON(!rtw89_sar_handlers[_s].descr_sar_source);	\
 		BUILD_BUG_ON(!rtw89_sar_handlers[_s].query_sar_config);	\
-		lockdep_assert_held(&_d->mutex);			\
+		lockdep_assert_wiphy(_d->hw->wiphy);			\
 		_d->sar._cfg_name = *(_cfg_data);			\
 		_d->sar.src = _s;					\
 	} while (0)
@@ -239,22 +239,19 @@ static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 				  const struct rtw89_sar_cfg_common *sar)
 {
 	enum rtw89_sar_sources src;
-	int ret = 0;
 
 	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 
 	src = rtwdev->sar.src;
 	if (src != RTW89_SAR_SOURCE_NONE && src != RTW89_SAR_SOURCE_COMMON) {
 		rtw89_warn(rtwdev, "SAR source: %d is in use", src);
-		ret = -EBUSY;
-		goto exit;
+		return -EBUSY;
 	}
 
 	rtw89_sar_set_src(rtwdev, RTW89_SAR_SOURCE_COMMON, cfg_common, sar);
 	rtw89_core_set_chip_txpwr(rtwdev);
 
-exit:
-	return ret;
+	return 0;
 }
 
 static const struct cfg80211_sar_freq_ranges rtw89_common_sar_freq_ranges[] = {
@@ -290,6 +287,8 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 	s32 power;
 	u32 i, idx;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	if (sar->type != NL80211_SAR_TYPE_POWER)
 		return -EINVAL;
 
diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
index b9607bdca6c8b..0740e303680cf 100644
--- a/drivers/net/wireless/realtek/rtw89/ser.c
+++ b/drivers/net/wireless/realtek/rtw89/ser.c
@@ -157,7 +157,6 @@ static void ser_state_run(struct rtw89_ser *ser, u8 evt)
 		    ser_st_name(ser), ser_ev_name(ser, evt));
 
 	wiphy_lock(rtwdev->hw->wiphy);
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	rtw89_leave_lps(rtwdev);
 	wiphy_unlock(rtwdev->hw->wiphy);
 
@@ -713,7 +712,6 @@ static void ser_l2_reset_st_hdl(struct rtw89_ser *ser, u8 evt)
 	switch (evt) {
 	case SER_EV_STATE_IN:
 		wiphy_lock(rtwdev->hw->wiphy);
-		lockdep_assert_wiphy(rtwdev->hw->wiphy);
 		ser_l2_reset_st_pre_hdl(ser);
 		wiphy_unlock(rtwdev->hw->wiphy);
 
diff --git a/drivers/net/wireless/realtek/rtw89/util.h b/drivers/net/wireless/realtek/rtw89/util.h
index df283a8580464..80441e8da60bb 100644
--- a/drivers/net/wireless/realtek/rtw89/util.h
+++ b/drivers/net/wireless/realtek/rtw89/util.h
@@ -12,7 +12,7 @@
 	ieee80211_iterate_active_interfaces_atomic((rtwdev)->hw,               \
 			IEEE80211_IFACE_ITER_NORMAL, iterator, data)
 
-/* call this function with rtwdev->mutex is held */
+/* call this function with wiphy mutex is held */
 #define rtw89_for_each_rtwvif(rtwdev, rtwvif)				       \
 	list_for_each_entry(rtwvif, &(rtwdev)->rtwvifs_list, list)
 
diff --git a/drivers/net/wireless/realtek/rtw89/wow.c b/drivers/net/wireless/realtek/rtw89/wow.c
index 6031633b27098..17eee58503cb3 100644
--- a/drivers/net/wireless/realtek/rtw89/wow.c
+++ b/drivers/net/wireless/realtek/rtw89/wow.c
@@ -604,6 +604,8 @@ static struct ieee80211_key_conf *rtw89_wow_gtk_rekey(struct rtw89_dev *rtwdev,
 	struct ieee80211_key_conf *key;
 	u8 sz;
 
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
 	cipher_info = rtw89_cipher_alg_recognize(cipher);
 	sz = struct_size(rekey_conf, key, cipher_info->len);
 	rekey_conf = kmalloc(sz, GFP_KERNEL);
@@ -616,10 +618,6 @@ static struct ieee80211_key_conf *rtw89_wow_gtk_rekey(struct rtw89_dev *rtwdev,
 	memcpy(rekey_conf->key, gtk,
 	       flex_array_size(rekey_conf, key, cipher_info->len));
 
-	/* ieee80211_gtk_rekey_add() will call set_key(), therefore we
-	 * need to unlock mutex
-	 */
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
 	if (ieee80211_vif_is_mld(wow_vif))
 		key = ieee80211_gtk_rekey_add(wow_vif, rekey_conf, rtwvif_link->link_id);
 	else

From 2345f351c7f55b97c17d8387a9ff38d4327baf4b Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:09 +0800
Subject: [PATCH 0074/2753] wifi: rtw89: remove definition of driver mutex

No consumers of driver mutex now, so remove definition eventually.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-10-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 2 --
 drivers/net/wireless/realtek/rtw89/core.h | 2 --
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 4e6d117439a5f..559191a49c5a4 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4831,7 +4831,6 @@ int rtw89_core_init(struct rtw89_dev *rtwdev)
 		return -ENOMEM;
 	spin_lock_init(&rtwdev->ba_lock);
 	spin_lock_init(&rtwdev->rpwm_lock);
-	mutex_init(&rtwdev->mutex);
 	mutex_init(&rtwdev->rf_mutex);
 	rtwdev->total_sta_assoc = 0;
 
@@ -4890,7 +4889,6 @@ void rtw89_core_deinit(struct rtw89_dev *rtwdev)
 
 	destroy_workqueue(rtwdev->txq_wq);
 	mutex_destroy(&rtwdev->rf_mutex);
-	mutex_destroy(&rtwdev->mutex);
 }
 EXPORT_SYMBOL(rtw89_core_deinit);
 
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 6970e4d4e73fa..61fe2705cac6c 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5653,8 +5653,6 @@ struct rtw89_dev {
 	struct rtw89_sta_link __rcu *assoc_link_on_macid[RTW89_MAX_MAC_ID_NUM];
 	refcount_t refcount_ap_info;
 
-	/* ensures exclusive access from mac80211 callbacks */
-	struct mutex mutex;
 	struct list_head rtwvifs_list;
 	/* used to protect rf read write */
 	struct mutex rf_mutex;

From 8afa4ff99a00cd3f3c8aedd6b92ad6fc077021b7 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 22 Jan 2025 14:03:10 +0800
Subject: [PATCH 0075/2753] wifi: rtw89: pci: not assert wiphy_lock to free
 early_h2c for PCI probe/remove

Except probe/remove flow, the consumers of early_h2c list are interface
start and debugfs. There must be no race between probe/remove flow and
interface start. The failed probe flow is to free early_h2c list as well
as remove flow, at these two moments debugfs doesn't present. Thus, it is
safe to free early_h2c list without held wiphy_lock in these situations.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122060310.31976-11-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  2 +-
 drivers/net/wireless/realtek/rtw89/fw.c   | 11 ++++++++---
 drivers/net/wireless/realtek/rtw89/fw.h   |  1 +
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 559191a49c5a4..da41a417dd7d3 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4885,7 +4885,7 @@ void rtw89_core_deinit(struct rtw89_dev *rtwdev)
 {
 	rtw89_ser_deinit(rtwdev);
 	rtw89_unload_firmware(rtwdev);
-	rtw89_fw_free_all_early_h2c(rtwdev);
+	__rtw89_fw_free_all_early_h2c(rtwdev);
 
 	destroy_workqueue(rtwdev->txq_wq);
 	mutex_destroy(&rtwdev->rf_mutex);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 2982ec367d9d5..1afce0a0b9053 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -6103,12 +6103,10 @@ void rtw89_fw_send_all_early_h2c(struct rtw89_dev *rtwdev)
 	}
 }
 
-void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
+void __rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_early_h2c *early_h2c, *tmp;
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
-
 	list_for_each_entry_safe(early_h2c, tmp, &rtwdev->early_h2c_list, list) {
 		list_del(&early_h2c->list);
 		kfree(early_h2c->h2c);
@@ -6116,6 +6114,13 @@ void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
 	}
 }
 
+void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev)
+{
+	lockdep_assert_wiphy(rtwdev->hw->wiphy);
+
+	__rtw89_fw_free_all_early_h2c(rtwdev);
+}
+
 static void rtw89_fw_c2h_parse_attr(struct sk_buff *c2h)
 {
 	const struct rtw89_c2h_hdr *hdr = (const struct rtw89_c2h_hdr *)c2h->data;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index b621dbed2c615..fb107c0a29d7f 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4665,6 +4665,7 @@ int rtw89_fw_h2c_raw_with_hdr(struct rtw89_dev *rtwdev,
 			      bool rack, bool dack);
 int rtw89_fw_h2c_raw(struct rtw89_dev *rtwdev, const u8 *buf, u16 len);
 void rtw89_fw_send_all_early_h2c(struct rtw89_dev *rtwdev);
+void __rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev);
 void rtw89_fw_free_all_early_h2c(struct rtw89_dev *rtwdev);
 int rtw89_fw_h2c_general_pkt(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link,
 			     u8 macid);

From 4828f572b20bc406f580c66b67c05c1b9ae75085 Mon Sep 17 00:00:00 2001
From: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Date: Wed, 22 Jan 2025 15:15:11 +0800
Subject: [PATCH 0076/2753] wifi: rtl8xxxu: Enable AP mode for RTL8192CU
 (RTL8188CUS)

This allows the driver to be used in wireless access point mode on the
AT91SAM9G25-based GARDENA smart Gateway.

Unfortunately, the data throughput in AP mode appears to be lower than
with the vendor driver (or in STA mode). Especially when sending, the
data rate is significantly lower. My measurements performed with iperf3
and an Edimax EW-7811Un (VID: 7392, PID: 7811) showed a maximum TX rate
of about 4 Mbits/sec compared to the ~24 Mbits/sec measured with the
rtl8192cu driver.

Although the performance might be good enough for our use case, this is
something that should be further looked into.

Signed-off-by: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250122071512.10165-1-ezra@easyb.ch
---
 drivers/net/wireless/realtek/rtl8xxxu/8192c.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8192c.c b/drivers/net/wireless/realtek/rtl8xxxu/8192c.c
index 0abb1b092bc20..73034e7e41d14 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/8192c.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/8192c.c
@@ -644,6 +644,8 @@ struct rtl8xxxu_fileops rtl8192cu_fops = {
 	.rx_agg_buf_size = 16000,
 	.tx_desc_size = sizeof(struct rtl8xxxu_txdesc32),
 	.rx_desc_size = sizeof(struct rtl8xxxu_rxdesc16),
+	.supports_ap = 1,
+	.max_macid_num = 32,
 	.max_sec_cam_num = 32,
 	.adda_1t_init = 0x0b1b25a0,
 	.adda_1t_path_on = 0x0bdb25a0,

From 00451eb3bec763f708e7e58326468c1e575e5a66 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Sun, 26 Jan 2025 16:03:11 +0200
Subject: [PATCH 0077/2753] wifi: rtw88: Don't use static local variable in
 rtw8822b_set_tx_power_index_by_rate

Some users want to plug two identical USB devices at the same time.
This static variable could theoretically cause them to use incorrect
TX power values.

Move the variable to the caller and pass a pointer to it to
rtw8822b_set_tx_power_index_by_rate().

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/8a60f581-0ab5-4d98-a97d-dd83b605008f@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8822b.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index 7f03903ddf4bb..23a29019752da 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -935,11 +935,11 @@ static void query_phy_status(struct rtw_dev *rtwdev, u8 *phy_status,
 }
 
 static void
-rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
+rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path,
+				    u8 rs, u32 *phy_pwr_idx)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
 	static const u32 offset_txagc[2] = {0x1d00, 0x1d80};
-	static u32 phy_pwr_idx;
 	u8 rate, rate_idx, pwr_index, shift;
 	int j;
 
@@ -947,12 +947,12 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 		rate = rtw_rate_section[rs][j];
 		pwr_index = hal->tx_pwr_tbl[path][rate];
 		shift = rate & 0x3;
-		phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
+		*phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
 		if (shift == 0x3) {
 			rate_idx = rate & 0xfc;
 			rtw_write32(rtwdev, offset_txagc[path] + rate_idx,
-				    phy_pwr_idx);
-			phy_pwr_idx = 0;
+				    *phy_pwr_idx);
+			*phy_pwr_idx = 0;
 		}
 	}
 }
@@ -960,11 +960,13 @@ rtw8822b_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 static void rtw8822b_set_tx_power_index(struct rtw_dev *rtwdev)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
+	u32 phy_pwr_idx = 0;
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
 		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
-			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs);
+			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs,
+							    &phy_pwr_idx);
 	}
 }
 

From 0d1d165eff9d6cfad51113e18d9d8c9a8de27d6d Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Sun, 26 Jan 2025 16:04:21 +0200
Subject: [PATCH 0078/2753] wifi: rtw88: Don't use static local variable in
 rtw8821c_set_tx_power_index_by_rate

Some users want to plug two identical USB devices at the same time.
This static variable could theoretically cause them to use incorrect
TX power values.

Move the variable to the caller and pass a pointer to it to
rtw8821c_set_tx_power_index_by_rate().

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/fe42858c-9b9f-4f03-9aaa-737472c2cd90@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8821c.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index eb7e34c545d0c..cc152248407c7 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -680,11 +680,11 @@ static void query_phy_status(struct rtw_dev *rtwdev, u8 *phy_status,
 }
 
 static void
-rtw8821c_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
+rtw8821c_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path,
+				    u8 rs, u32 *phy_pwr_idx)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
 	static const u32 offset_txagc[2] = {0x1d00, 0x1d80};
-	static u32 phy_pwr_idx;
 	u8 rate, rate_idx, pwr_index, shift;
 	int j;
 
@@ -692,12 +692,12 @@ rtw8821c_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 		rate = rtw_rate_section[rs][j];
 		pwr_index = hal->tx_pwr_tbl[path][rate];
 		shift = rate & 0x3;
-		phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
+		*phy_pwr_idx |= ((u32)pwr_index << (shift * 8));
 		if (shift == 0x3 || rate == DESC_RATEVHT1SS_MCS9) {
 			rate_idx = rate & 0xfc;
 			rtw_write32(rtwdev, offset_txagc[path] + rate_idx,
-				    phy_pwr_idx);
-			phy_pwr_idx = 0;
+				    *phy_pwr_idx);
+			*phy_pwr_idx = 0;
 		}
 	}
 }
@@ -705,6 +705,7 @@ rtw8821c_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
 static void rtw8821c_set_tx_power_index(struct rtw_dev *rtwdev)
 {
 	struct rtw_hal *hal = &rtwdev->hal;
+	u32 phy_pwr_idx = 0;
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
@@ -712,7 +713,8 @@ static void rtw8821c_set_tx_power_index(struct rtw_dev *rtwdev)
 			if (rs == RTW_RATE_SECTION_HT_2S ||
 			    rs == RTW_RATE_SECTION_VHT_2S)
 				continue;
-			rtw8821c_set_tx_power_index_by_rate(rtwdev, path, rs);
+			rtw8821c_set_tx_power_index_by_rate(rtwdev, path, rs,
+							    &phy_pwr_idx);
 		}
 	}
 }

From 3d3e28feca7ac8c6cf2a390dbbe1f97e3feb7f36 Mon Sep 17 00:00:00 2001
From: Soeren Moch <smoch@web.de>
Date: Mon, 27 Jan 2025 20:48:28 +0100
Subject: [PATCH 0079/2753] wifi: rtl8xxxu: retry firmware download on error

Occasionally there is an EPROTO error during firmware download.
This error is converted to EAGAIN in the download function.
But nobody tries again and so device probe fails.

Implement download retry to fix this.

This error was observed (and fix tested) on a tbs2910 board [1]
with an embedded RTL8188EU (0bda:8179) device behind a USB hub.

[1] arch/arm/boot/dts/nxp/imx/imx6q-tbs2910.dts

Signed-off-by: Soeren Moch <smoch@web.de>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250127194828.599379-1-smoch@web.de
---
 drivers/net/wireless/realtek/rtl8xxxu/core.c | 17 ++++++++++++-----
 1 file changed, 12 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtl8xxxu/core.c b/drivers/net/wireless/realtek/rtl8xxxu/core.c
index 4ce0c05c51291..569856ca677f6 100644
--- a/drivers/net/wireless/realtek/rtl8xxxu/core.c
+++ b/drivers/net/wireless/realtek/rtl8xxxu/core.c
@@ -860,9 +860,10 @@ rtl8xxxu_writeN(struct rtl8xxxu_priv *priv, u16 addr, u8 *buf, u16 len)
 	return len;
 
 write_error:
-	dev_info(&udev->dev,
-		 "%s: Failed to write block at addr: %04x size: %04x\n",
-		 __func__, addr, blocksize);
+	if (rtl8xxxu_debug & RTL8XXXU_DEBUG_REG_WRITE)
+		dev_info(&udev->dev,
+			 "%s: Failed to write block at addr: %04x size: %04x\n",
+			 __func__, addr, blocksize);
 	return -EAGAIN;
 }
 
@@ -4064,8 +4065,14 @@ static int rtl8xxxu_init_device(struct ieee80211_hw *hw)
 	 */
 	rtl8xxxu_write16(priv, REG_TRXFF_BNDY + 2, fops->trxff_boundary);
 
-	ret = rtl8xxxu_download_firmware(priv);
-	dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret);
+	for (int retry = 5; retry >= 0 ; retry--) {
+		ret = rtl8xxxu_download_firmware(priv);
+		dev_dbg(dev, "%s: download_firmware %i\n", __func__, ret);
+		if (ret != -EAGAIN)
+			break;
+		if (retry)
+			dev_dbg(dev, "%s: retry firmware download\n", __func__);
+	}
 	if (ret)
 		goto exit;
 	ret = rtl8xxxu_start_firmware(priv);

From 5c8f9a05336cf5cadbd57ad461621b386aadb762 Mon Sep 17 00:00:00 2001
From: Alexander Shiyan <eagle.alexander923@gmail.com>
Date: Thu, 30 Jan 2025 08:38:49 +0300
Subject: [PATCH 0080/2753] arm64: dts: rockchip: Fix broken tsadc pinctrl
 names for rk3588

The tsadc driver does not handle pinctrl "gpio" and "otpout".
Let's use the correct pinctrl names "default" and "sleep".
Additionally, Alexey Charkov's testing [1] has established that
it is necessary for pinctrl state to reference the &tsadc_shut_org
configuration rather than &tsadc_shut for the driver to function correctly.

[1] https://lkml.org/lkml/2025/1/24/966

Fixes: 32641b8ab1a5 ("arm64: dts: rockchip: add rk3588 thermal sensor")
Cc: stable@vger.kernel.org
Reviewed-by: Dragan Simic <dsimic@manjaro.org>
Signed-off-by: Alexander Shiyan <eagle.alexander923@gmail.com>
Link: https://lore.kernel.org/r/20250130053849.4902-1-eagle.alexander923@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-base.dtsi | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index 8cfa30837ce72..978de506d4348 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -2668,9 +2668,9 @@
 		rockchip,hw-tshut-temp = <120000>;
 		rockchip,hw-tshut-mode = <0>; /* tshut mode 0:CRU 1:GPIO */
 		rockchip,hw-tshut-polarity = <0>; /* tshut polarity 0:LOW 1:HIGH */
-		pinctrl-0 = <&tsadc_gpio_func>;
-		pinctrl-1 = <&tsadc_shut>;
-		pinctrl-names = "gpio", "otpout";
+		pinctrl-0 = <&tsadc_shut_org>;
+		pinctrl-1 = <&tsadc_gpio_func>;
+		pinctrl-names = "default", "sleep";
 		#thermal-sensor-cells = <1>;
 		status = "disabled";
 	};

From a6a7cba17c544fb95d5a29ab9d9ed4503029cb29 Mon Sep 17 00:00:00 2001
From: Tianling Shen <cnsztl@gmail.com>
Date: Sun, 19 Jan 2025 17:11:54 +0800
Subject: [PATCH 0081/2753] arm64: dts: rockchip: change eth phy mode to
 rgmii-id for orangepi r1 plus lts

In general the delay should be added by the PHY instead of the MAC,
and this improves network stability on some boards which seem to
need different delay.

Fixes: 387b3bbac5ea ("arm64: dts: rockchip: Add Xunlong OrangePi R1 Plus LTS")
Cc: stable@vger.kernel.org # 6.6+
Signed-off-by: Tianling Shen <cnsztl@gmail.com>
Link: https://lore.kernel.org/r/20250119091154.1110762-1-cnsztl@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts | 3 +--
 arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts     | 1 +
 arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi    | 1 -
 3 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
index 67c246ad8b8c0..ec2ce894da1fc 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus-lts.dts
@@ -17,8 +17,7 @@
 
 &gmac2io {
 	phy-handle = <&yt8531c>;
-	tx_delay = <0x19>;
-	rx_delay = <0x05>;
+	phy-mode = "rgmii-id";
 	status = "okay";
 
 	mdio {
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
index 324a8e951f7e4..846b931e16d21 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dts
@@ -15,6 +15,7 @@
 
 &gmac2io {
 	phy-handle = <&rtl8211e>;
+	phy-mode = "rgmii";
 	tx_delay = <0x24>;
 	rx_delay = <0x18>;
 	status = "okay";
diff --git a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
index 4f193704e5dc2..09508e324a280 100644
--- a/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3328-orangepi-r1-plus.dtsi
@@ -109,7 +109,6 @@
 	assigned-clocks = <&cru SCLK_MAC2IO>, <&cru SCLK_MAC2IO_EXT>;
 	assigned-clock-parents = <&gmac_clk>, <&gmac_clk>;
 	clock_in_out = "input";
-	phy-mode = "rgmii";
 	phy-supply = <&vcc_io>;
 	pinctrl-0 = <&rgmiim1_pins>;
 	pinctrl-names = "default";

From 4eee627ea59304cdd66c5d4194ef13486a6c44fc Mon Sep 17 00:00:00 2001
From: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Date: Tue, 21 Jan 2025 13:56:03 +0100
Subject: [PATCH 0082/2753] arm64: dts: rockchip: Move uart5 pin configuration
 to px30 ringneck SoM

In the PX30-uQ7 (Ringneck) SoM, the hardware CTS and RTS pins for
uart5 cannot be used for the UART CTS/RTS, because they are already
allocated for different purposes. CTS pin is routed to SUS_S3#
signal, while RTS pin is used internally and is not available on
Q7 connector. Move definition of the pinctrl-0 property from
px30-ringneck-haikou.dts to px30-ringneck.dtsi.

This commit is a dependency to next commit in the patch series,
that disables DMA for uart5.

Cc: stable@vger.kernel.org
Reviewed-by: Quentin Schulz <quentin.schulz@cherry.de>
Signed-off-by: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Link: https://lore.kernel.org/r/20250121125604.3115235-2-lukasz.czechowski@thaumatec.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts | 1 -
 arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi       | 4 ++++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index e4517f47d519c..eb9470a00e549 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -226,7 +226,6 @@
 };
 
 &uart5 {
-	pinctrl-0 = <&uart5_xfer>;
 	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };
diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index ae050cc6cd050..2c87005c89bd3 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -396,6 +396,10 @@
 	status = "okay";
 };
 
+&uart5 {
+	pinctrl-0 = <&uart5_xfer>;
+};
+
 /* Mule UCAN */
 &usb_host0_ehci {
 	status = "okay";

From 5ae4dca718eacd0a56173a687a3736eb7e627c77 Mon Sep 17 00:00:00 2001
From: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Date: Tue, 21 Jan 2025 13:56:04 +0100
Subject: [PATCH 0083/2753] arm64: dts: rockchip: Disable DMA for uart5 on
 px30-ringneck
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

UART controllers without flow control seem to behave unstable
in case DMA is enabled. The issues were indicated in the message:
https://lore.kernel.org/linux-arm-kernel/CAMdYzYpXtMocCtCpZLU_xuWmOp2Ja_v0Aj0e6YFNRA-yV7u14g@mail.gmail.com/
In case of PX30-uQ7 Ringneck SoM, it was noticed that after couple
of hours of UART communication, the CPU stall was occurring,
leading to the system becoming unresponsive.
After disabling the DMA, extensive UART communication tests for
up to two weeks were performed, and no issues were further
observed.
The flow control pins for uart5 are not available on PX30-uQ7
Ringneck, as configured by pinctrl-0, so the DMA nodes were
removed on SoM dtsi.

Cc: stable@vger.kernel.org
Fixes: c484cf93f61b ("arm64: dts: rockchip: add PX30-µQ7 (Ringneck) SoM with Haikou baseboard")
Reviewed-by: Quentin Schulz <quentin.schulz@cherry.de>
Signed-off-by: Lukasz Czechowski <lukasz.czechowski@thaumatec.com>
Link: https://lore.kernel.org/r/20250121125604.3115235-3-lukasz.czechowski@thaumatec.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
index 2c87005c89bd3..e80412abec081 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck.dtsi
@@ -397,6 +397,8 @@
 };
 
 &uart5 {
+	/delete-property/ dmas;
+	/delete-property/ dma-names;
 	pinctrl-0 = <&uart5_xfer>;
 };
 

From 2f9eb5262e63396a315c7da34a6c80c5d335df9f Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko@sntech.de>
Date: Thu, 16 Jan 2025 15:36:31 +0100
Subject: [PATCH 0084/2753] arm64: dts: rockchip: fix fixed-regulator renames
 on rk3399-gru devices

rk3399-gru chromebooks have a regulator chains where one named regulator
supplies multiple regulators pp900-usb pp900_pcie that supply
the named peripherals.

The dtsi used somewhat creative structure to describe that in creating
the base node 3 times with different phandles and describing the EC
dependency in a comment.

This didn't register in the recent regulator-node renaming, as the
additional nodes were empty, so adapt the missing node names for now.

Fixes: 5c96e6330197 ("arm64: dts: rockchip: adapt regulator nodenames to preferred form")
Tested-by: Vicente Bergas <vicencb@gmail.com>
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20250116143631.3650469-1-heiko@sntech.de
---
 .../dts/rockchip/rk3399-gru-chromebook.dtsi   |  8 +++----
 .../boot/dts/rockchip/rk3399-gru-scarlet.dtsi |  6 ++---
 arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi  | 22 +++++++++----------
 3 files changed, 18 insertions(+), 18 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
index 988e6ca32fac9..a9ea4b0daa04c 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-chromebook.dtsi
@@ -22,11 +22,11 @@
 	};
 
 	/* EC turns on w/ pp900_usb_en */
-	pp900_usb: pp900-ap {
+	pp900_usb: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pcie_en */
-	pp900_pcie: pp900-ap {
+	pp900_pcie: regulator-pp900-ap {
 	};
 
 	pp3000: regulator-pp3000 {
@@ -126,7 +126,7 @@
 	};
 
 	/* Always on; plain and simple */
-	pp3000_ap: pp3000_emmc: pp3000 {
+	pp3000_ap: pp3000_emmc: regulator-pp3000 {
 	};
 
 	pp1500_ap_io: regulator-pp1500-ap-io {
@@ -160,7 +160,7 @@
 	};
 
 	/* EC turns on w/ pp3300_usb_en_l */
-	pp3300_usb: pp3300 {
+	pp3300_usb: regulator-pp3300 {
 	};
 
 	/* gpio is shared with pp1800_pcie and pinctrl is set there */
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
index 19b23b4389658..5e068377a0a28 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru-scarlet.dtsi
@@ -92,7 +92,7 @@
 	};
 
 	/* EC turns on pp1800_s3_en */
-	pp1800_s3: pp1800 {
+	pp1800_s3: regulator-pp1800 {
 	};
 
 	/* pp3300 children, sorted by name */
@@ -109,11 +109,11 @@
 	};
 
 	/* EC turns on pp3300_s0_en */
-	pp3300_s0: pp3300 {
+	pp3300_s0: regulator-pp3300 {
 	};
 
 	/* EC turns on pp3300_s3_en */
-	pp3300_s3: pp3300 {
+	pp3300_s3: regulator-pp3300 {
 	};
 
 	/*
diff --git a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
index 6d9e60b01225e..7eca1da78cffa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-gru.dtsi
@@ -189,39 +189,39 @@
 	};
 
 	/* EC turns on w/ pp900_ddrpll_en */
-	pp900_ddrpll: pp900-ap {
+	pp900_ddrpll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pll_en */
-	pp900_pll: pp900-ap {
+	pp900_pll: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp900_pmu_en */
-	pp900_pmu: pp900-ap {
+	pp900_pmu: regulator-pp900-ap {
 	};
 
 	/* EC turns on w/ pp1800_s0_en_l */
-	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: pp1800 {
+	pp1800_ap_io: pp1800_emmc: pp1800_nfc: pp1800_s0: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_avdd_en_l */
-	pp1800_avdd: pp1800 {
+	pp1800_avdd: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_lid_en_l */
-	pp1800_lid: pp1800_mic: pp1800 {
+	pp1800_lid: pp1800_mic: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ lpddr_pwr_en */
-	pp1800_lpddr: pp1800 {
+	pp1800_lpddr: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_pmu_en_l */
-	pp1800_pmu: pp1800 {
+	pp1800_pmu: regulator-pp1800 {
 	};
 
 	/* EC turns on w/ pp1800_usb_en_l */
-	pp1800_usb: pp1800 {
+	pp1800_usb: regulator-pp1800 {
 	};
 
 	pp3000_sd_slot: regulator-pp3000-sd-slot {
@@ -259,11 +259,11 @@
 	};
 
 	/* EC turns on w/ pp3300_trackpad_en_l */
-	pp3300_trackpad: pp3300-trackpad {
+	pp3300_trackpad: regulator-pp3300-trackpad {
 	};
 
 	/* EC turns on w/ usb_a_en */
-	pp5000_usb_a_vbus: pp5000 {
+	pp5000_usb_a_vbus: regulator-pp5000 {
 	};
 
 	ap_rtc_clk: ap-rtc-clk {

From a1d939055a22be06d8c12bf53afb258b9d38575f Mon Sep 17 00:00:00 2001
From: Andy Yan <andyshrk@163.com>
Date: Mon, 13 Jan 2025 18:47:34 +0800
Subject: [PATCH 0085/2753] arm64: dts: rockchip: Fix lcdpwr_en pin for Cool Pi
 GenBook

According to the schematic, the lcdpwr_en pin is GPIO0_C4,
not GPIO1_C4.

Fixes: 4a8c1161b843 ("arm64: dts: rockchip: Add support for rk3588 based Cool Pi CM5 GenBook")
Signed-off-by: Andy Yan <andyshrk@163.com>
Link: https://lore.kernel.org/r/20250113104825.2390427-1-andyshrk@163.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
index 92f0ed83c9902..bc6b43a771537 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-coolpi-cm5-genbook.dts
@@ -113,7 +113,7 @@
 		compatible = "regulator-fixed";
 		regulator-name = "vcc3v3_lcd";
 		enable-active-high;
-		gpio = <&gpio1 RK_PC4 GPIO_ACTIVE_HIGH>;
+		gpio = <&gpio0 RK_PC4 GPIO_ACTIVE_HIGH>;
 		pinctrl-names = "default";
 		pinctrl-0 = <&lcdpwr_en>;
 		vin-supply = <&vcc3v3_sys>;
@@ -241,7 +241,7 @@
 &pinctrl {
 	lcd {
 		lcdpwr_en: lcdpwr-en {
-			rockchip,pins = <1 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
+			rockchip,pins = <0 RK_PC4 RK_FUNC_GPIO &pcfg_pull_down>;
 		};
 
 		bl_en: bl-en {

From 3fb3cb4350befc4f901c54e0cb4a2a47b1302e08 Mon Sep 17 00:00:00 2001
From: Andrey Vatoropin <a.vatoropin@crpt.ru>
Date: Thu, 30 Jan 2025 09:00:34 +0000
Subject: [PATCH 0086/2753] power: supply: da9150-fg: fix potential overflow

Size of variable sd_gain equals four bytes - DA9150_QIF_SD_GAIN_SIZE.
Size of variable shunt_val equals two bytes - DA9150_QIF_SHUNT_VAL_SIZE.

The expression sd_gain * shunt_val is currently being evaluated using
32-bit arithmetic. So during the multiplication an overflow may occur.

As the value of type 'u64' is used as storage for the eventual result, put
ULL variable at the first position of each expression in order to give the
compiler complete information about the proper arithmetic to use. According
to C99 the guaranteed width for a variable of type 'unsigned long long' >=
64 bits.

Remove the explicit cast to u64 as it is meaningless.

Just for the sake of consistency, perform the similar trick with another
expression concerning 'iavg'.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: a419b4fd9138 ("power: Add support for DA9150 Fuel-Gauge")
Signed-off-by: Andrey Vatoropin <a.vatoropin@crpt.ru>
Link: https://lore.kernel.org/r/20250130090030.53422-1-a.vatoropin@crpt.ru
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/da9150-fg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/power/supply/da9150-fg.c b/drivers/power/supply/da9150-fg.c
index 652c1f213af1c..4f28ef1bba1a3 100644
--- a/drivers/power/supply/da9150-fg.c
+++ b/drivers/power/supply/da9150-fg.c
@@ -247,9 +247,9 @@ static int da9150_fg_current_avg(struct da9150_fg *fg,
 				      DA9150_QIF_SD_GAIN_SIZE);
 	da9150_fg_read_sync_end(fg);
 
-	div = (u64) (sd_gain * shunt_val * 65536ULL);
+	div = 65536ULL * sd_gain * shunt_val;
 	do_div(div, 1000000);
-	res = (u64) (iavg * 1000000ULL);
+	res = 1000000ULL * iavg;
 	do_div(res, div);
 
 	val->intval = (int) res;

From 64dd6edfc421479e416301c48b79cece8d0351fc Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Thu, 30 Jan 2025 15:00:35 +0100
Subject: [PATCH 0087/2753] power: supply: core: Fix extension related lockdep
 warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 6037802bbae8 ("power: supply: core: implement extension API")
there is the following ABBA deadlock (simplified) between the LED trigger
code and the power-supply code:

1) When registering a power-supply class device, power_supply_register()
calls led_trigger_register() from power_supply_create_triggers() in
a scoped_guard(rwsem_read, &psy->extensions_sem) context.
led_trigger_register() then in turn takes a LED subsystem lock.
So here we have the following locking order:

* Read-lock extensions_sem
* Lock LED subsystem lock(s)

2) When registering a LED class device, with its default trigger set
to a power-supply LED trigger (which has already been registered)
The LED class code calls power_supply_led_trigger_activate() when
setting up the default trigger. power_supply_led_trigger_activate()
calls power_supply_get_property() to determine the initial value of
to assign to the LED and that read-locks extensions_sem. So now we
have the following locking order:

* Lock LED subsystem lock(s)
* Read-lock extensions_sem

Fixing this is easy, there is no need to hold the extensions_sem when
calling power_supply_create_triggers() since all triggers are always
created rather then checking for the presence of certain attributes as
power_supply_add_hwmon_sysfs() does. Move power_supply_create_triggers()
out of the guard block to fix this.

Here is the lockdep report fixed by this change:

[   31.249343] ======================================================
[   31.249378] WARNING: possible circular locking dependency detected
[   31.249413] 6.13.0-rc6+ #251 Tainted: G         C  E
[   31.249440] ------------------------------------------------------
[   31.249471] (udev-worker)/553 is trying to acquire lock:
[   31.249501] ffff892adbcaf660 (&psy->extensions_sem){.+.+}-{4:4}, at: power_supply_get_property.part.0+0x22/0x150
[   31.249574]
               but task is already holding lock:
[   31.249603] ffff892adbc0bad0 (&led_cdev->trigger_lock){+.+.}-{4:4}, at: led_trigger_set_default+0x34/0xe0
[   31.249657]
               which lock already depends on the new lock.

[   31.249696]
               the existing dependency chain (in reverse order) is:
[   31.249735]
               -> #2 (&led_cdev->trigger_lock){+.+.}-{4:4}:
[   31.249778]        down_write+0x3b/0xd0
[   31.249803]        led_trigger_set_default+0x34/0xe0
[   31.249833]        led_classdev_register_ext+0x311/0x3a0
[   31.249863]        input_leds_connect+0x1dc/0x2a0
[   31.249889]        input_attach_handler.isra.0+0x75/0x90
[   31.249921]        input_register_device.cold+0xa1/0x150
[   31.249955]        hidinput_connect+0x8a2/0xb80
[   31.249982]        hid_connect+0x582/0x5c0
[   31.250007]        hid_hw_start+0x3f/0x60
[   31.250030]        hid_device_probe+0x122/0x1f0
[   31.250053]        really_probe+0xde/0x340
[   31.250080]        __driver_probe_device+0x78/0x110
[   31.250105]        driver_probe_device+0x1f/0xa0
[   31.250132]        __device_attach_driver+0x85/0x110
[   31.250160]        bus_for_each_drv+0x78/0xc0
[   31.250184]        __device_attach+0xb0/0x1b0
[   31.250207]        bus_probe_device+0x94/0xb0
[   31.250230]        device_add+0x64a/0x860
[   31.250252]        hid_add_device+0xe5/0x240
[   31.250279]        usbhid_probe+0x4dc/0x620
[   31.250303]        usb_probe_interface+0xe4/0x2a0
[   31.250329]        really_probe+0xde/0x340
[   31.250353]        __driver_probe_device+0x78/0x110
[   31.250377]        driver_probe_device+0x1f/0xa0
[   31.250404]        __device_attach_driver+0x85/0x110
[   31.250431]        bus_for_each_drv+0x78/0xc0
[   31.250455]        __device_attach+0xb0/0x1b0
[   31.250478]        bus_probe_device+0x94/0xb0
[   31.250501]        device_add+0x64a/0x860
[   31.250523]        usb_set_configuration+0x606/0x8a0
[   31.250552]        usb_generic_driver_probe+0x3e/0x60
[   31.250579]        usb_probe_device+0x3d/0x120
[   31.250605]        really_probe+0xde/0x340
[   31.250629]        __driver_probe_device+0x78/0x110
[   31.250653]        driver_probe_device+0x1f/0xa0
[   31.250680]        __device_attach_driver+0x85/0x110
[   31.250707]        bus_for_each_drv+0x78/0xc0
[   31.250731]        __device_attach+0xb0/0x1b0
[   31.250753]        bus_probe_device+0x94/0xb0
[   31.250776]        device_add+0x64a/0x860
[   31.250798]        usb_new_device.cold+0x141/0x38f
[   31.250828]        hub_event+0x1166/0x1980
[   31.250854]        process_one_work+0x20f/0x580
[   31.250879]        worker_thread+0x1d1/0x3b0
[   31.250904]        kthread+0xee/0x120
[   31.250926]        ret_from_fork+0x30/0x50
[   31.250954]        ret_from_fork_asm+0x1a/0x30
[   31.250982]
               -> #1 (triggers_list_lock){++++}-{4:4}:
[   31.251022]        down_write+0x3b/0xd0
[   31.251045]        led_trigger_register+0x40/0x1b0
[   31.251074]        power_supply_register_led_trigger+0x88/0x150
[   31.251107]        power_supply_create_triggers+0x55/0xe0
[   31.251135]        __power_supply_register.part.0+0x34e/0x4a0
[   31.251164]        devm_power_supply_register+0x70/0xc0
[   31.251190]        bq27xxx_battery_setup+0x1a1/0x6d0 [bq27xxx_battery]
[   31.251235]        bq27xxx_battery_i2c_probe+0xe5/0x17f [bq27xxx_battery_i2c]
[   31.251272]        i2c_device_probe+0x125/0x2b0
[   31.251299]        really_probe+0xde/0x340
[   31.251324]        __driver_probe_device+0x78/0x110
[   31.251348]        driver_probe_device+0x1f/0xa0
[   31.251375]        __driver_attach+0xba/0x1c0
[   31.251398]        bus_for_each_dev+0x6b/0xb0
[   31.251421]        bus_add_driver+0x111/0x1f0
[   31.251445]        driver_register+0x6e/0xc0
[   31.251470]        i2c_register_driver+0x41/0xb0
[   31.251498]        do_one_initcall+0x5e/0x3a0
[   31.251522]        do_init_module+0x60/0x220
[   31.251550]        __do_sys_init_module+0x15f/0x190
[   31.251575]        do_syscall_64+0x93/0x180
[   31.251598]        entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   31.251629]
               -> #0 (&psy->extensions_sem){.+.+}-{4:4}:
[   31.251668]        __lock_acquire+0x13ce/0x21c0
[   31.251694]        lock_acquire+0xcf/0x2e0
[   31.251719]        down_read+0x3e/0x170
[   31.251741]        power_supply_get_property.part.0+0x22/0x150
[   31.251774]        power_supply_update_leds+0x8d/0x230
[   31.251804]        power_supply_led_trigger_activate+0x18/0x20
[   31.251837]        led_trigger_set+0x1fc/0x300
[   31.251863]        led_trigger_set_default+0x90/0xe0
[   31.251892]        led_classdev_register_ext+0x311/0x3a0
[   31.251921]        devm_led_classdev_multicolor_register_ext+0x6e/0xb80 [led_class_multicolor]
[   31.251969]        ktd202x_probe+0x464/0x5c0 [leds_ktd202x]
[   31.252002]        i2c_device_probe+0x125/0x2b0
[   31.252027]        really_probe+0xde/0x340
[   31.252052]        __driver_probe_device+0x78/0x110
[   31.252076]        driver_probe_device+0x1f/0xa0
[   31.252103]        __driver_attach+0xba/0x1c0
[   31.252125]        bus_for_each_dev+0x6b/0xb0
[   31.252148]        bus_add_driver+0x111/0x1f0
[   31.252172]        driver_register+0x6e/0xc0
[   31.252197]        i2c_register_driver+0x41/0xb0
[   31.252225]        do_one_initcall+0x5e/0x3a0
[   31.252248]        do_init_module+0x60/0x220
[   31.252274]        __do_sys_init_module+0x15f/0x190
[   31.253986]        do_syscall_64+0x93/0x180
[   31.255826]        entry_SYSCALL_64_after_hwframe+0x76/0x7e
[   31.257614]
               other info that might help us debug this:

[   31.257619] Chain exists of:
                 &psy->extensions_sem --> triggers_list_lock --> &led_cdev->trigger_lock

[   31.257630]  Possible unsafe locking scenario:

[   31.257632]        CPU0                    CPU1
[   31.257633]        ----                    ----
[   31.257634]   lock(&led_cdev->trigger_lock);
[   31.257637]                                lock(triggers_list_lock);
[   31.257640]                                lock(&led_cdev->trigger_lock);
[   31.257643]   rlock(&psy->extensions_sem);
[   31.257646]
                *** DEADLOCK ***

[   31.289433] 4 locks held by (udev-worker)/553:
[   31.289443]  #0: ffff892ad9658108 (&dev->mutex){....}-{4:4}, at: __driver_attach+0xaf/0x1c0
[   31.289463]  #1: ffff892adbc0bbc8 (&led_cdev->led_access){+.+.}-{4:4}, at: led_classdev_register_ext+0x1c7/0x3a0
[   31.289476]  #2: ffffffffad0e30b0 (triggers_list_lock){++++}-{4:4}, at: led_trigger_set_default+0x2c/0xe0
[   31.289487]  #3: ffff892adbc0bad0 (&led_cdev->trigger_lock){+.+.}-{4:4}, at: led_trigger_set_default+0x34/0xe0

Fixes: 6037802bbae8 ("power: supply: core: implement extension API")
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: Armin Wolf <W_Armin@gmx.de>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Thomas Weißschuh <linux@weissschuh.net>
Link: https://lore.kernel.org/r/20250130140035.20636-1-hdegoede@redhat.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index d0bb52a7a0367..76c340b38015a 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1592,11 +1592,11 @@ __power_supply_register(struct device *parent,
 	if (rc)
 		goto register_thermal_failed;
 
-	scoped_guard(rwsem_read, &psy->extensions_sem) {
-		rc = power_supply_create_triggers(psy);
-		if (rc)
-			goto create_triggers_failed;
+	rc = power_supply_create_triggers(psy);
+	if (rc)
+		goto create_triggers_failed;
 
+	scoped_guard(rwsem_read, &psy->extensions_sem) {
 		rc = power_supply_add_hwmon_sysfs(psy);
 		if (rc)
 			goto add_hwmon_sysfs_failed;

From d97505baea64d93538b16baf14ce7b8c1fbad746 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Sun, 19 Jan 2025 14:36:13 +0200
Subject: [PATCH 0088/2753] RDMA/mlx5: Fix the recovery flow of the UMR QP

This patch addresses an issue in the recovery flow of the UMR QP,
ensuring tasks do not get stuck, as highlighted by the call trace [1].

During recovery, before transitioning the QP to the RESET state, the
software must wait for all outstanding WRs to complete.

Failing to do so can cause the firmware to skip sending some flushed
CQEs with errors and simply discard them upon the RESET, as per the IB
specification.

This race condition can result in lost CQEs and tasks becoming stuck.

To resolve this, the patch sends a final WR which serves only as a
barrier before moving the QP state to RESET.

Once a CQE is received for that final WR, it guarantees that no
outstanding WRs remain, making it safe to transition the QP to RESET and
subsequently back to RTS, restoring proper functionality.

Note:
For the barrier WR, we simply reuse the failed and ready WR.
Since the QP is in an error state, it will only receive
IB_WC_WR_FLUSH_ERR. However, as it serves only as a barrier we don't
care about its status.

[1]
INFO: task rdma_resource_l:1922 blocked for more than 120 seconds.
Tainted: G        W          6.12.0-rc7+ #1626
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:rdma_resource_l state:D stack:0  pid:1922 tgid:1922  ppid:1369
     flags:0x00004004
Call Trace:
<TASK>
__schedule+0x420/0xd30
schedule+0x47/0x130
schedule_timeout+0x280/0x300
? mark_held_locks+0x48/0x80
? lockdep_hardirqs_on_prepare+0xe5/0x1a0
wait_for_completion+0x75/0x130
mlx5r_umr_post_send_wait+0x3c2/0x5b0 [mlx5_ib]
? __pfx_mlx5r_umr_done+0x10/0x10 [mlx5_ib]
mlx5r_umr_revoke_mr+0x93/0xc0 [mlx5_ib]
__mlx5_ib_dereg_mr+0x299/0x520 [mlx5_ib]
? _raw_spin_unlock_irq+0x24/0x40
? wait_for_completion+0xfe/0x130
? rdma_restrack_put+0x63/0xe0 [ib_core]
ib_dereg_mr_user+0x5f/0x120 [ib_core]
? lock_release+0xc6/0x280
destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs]
uobj_destroy+0x3f/0x70 [ib_uverbs]
ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs]
? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs]
? __lock_acquire+0x64e/0x2080
? mark_held_locks+0x48/0x80
? find_held_lock+0x2d/0xa0
? lock_acquire+0xc1/0x2f0
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
? __fget_files+0xc3/0x1b0
ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
__x64_sys_ioctl+0x1b0/0xa70
do_syscall_64+0x6b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f99c918b17b
RSP: 002b:00007ffc766d0468 EFLAGS: 00000246 ORIG_RAX:
     0000000000000010
RAX: ffffffffffffffda RBX: 00007ffc766d0578 RCX:
     00007f99c918b17b
RDX: 00007ffc766d0560 RSI: 00000000c0181b01 RDI:
     0000000000000003
RBP: 00007ffc766d0540 R08: 00007f99c8f99010 R09:
     000000000000bd7e
R10: 00007f99c94c1c70 R11: 0000000000000246 R12:
     00007ffc766d0530
R13: 000000000000001c R14: 0000000040246a80 R15:
     0000000000000000
</TASK>

Fixes: 158e71bb69e3 ("RDMA/mlx5: Add a umr recovery flow")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/27b51b92ec42dfb09d8096fcbd51878f397ce6ec.1737290141.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/umr.c | 83 +++++++++++++++++++++-----------
 1 file changed, 56 insertions(+), 27 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index 887fd6fa3ba93..793f3c5c4d012 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -231,30 +231,6 @@ void mlx5r_umr_cleanup(struct mlx5_ib_dev *dev)
 	ib_dealloc_pd(dev->umrc.pd);
 }
 
-static int mlx5r_umr_recover(struct mlx5_ib_dev *dev)
-{
-	struct umr_common *umrc = &dev->umrc;
-	struct ib_qp_attr attr;
-	int err;
-
-	attr.qp_state = IB_QPS_RESET;
-	err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
-	if (err) {
-		mlx5_ib_dbg(dev, "Couldn't modify UMR QP\n");
-		goto err;
-	}
-
-	err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
-	if (err)
-		goto err;
-
-	umrc->state = MLX5_UMR_STATE_ACTIVE;
-	return 0;
-
-err:
-	umrc->state = MLX5_UMR_STATE_ERR;
-	return err;
-}
 
 static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
 			       struct mlx5r_umr_wqe *wqe, bool with_data)
@@ -302,6 +278,61 @@ static int mlx5r_umr_post_send(struct ib_qp *ibqp, u32 mkey, struct ib_cqe *cqe,
 	return err;
 }
 
+static int mlx5r_umr_recover(struct mlx5_ib_dev *dev, u32 mkey,
+			     struct mlx5r_umr_context *umr_context,
+			     struct mlx5r_umr_wqe *wqe, bool with_data)
+{
+	struct umr_common *umrc = &dev->umrc;
+	struct ib_qp_attr attr;
+	int err;
+
+	mutex_lock(&umrc->lock);
+	/* Preventing any further WRs to be sent now */
+	if (umrc->state != MLX5_UMR_STATE_RECOVER) {
+		mlx5_ib_warn(dev, "UMR recovery encountered an unexpected state=%d\n",
+			     umrc->state);
+		umrc->state = MLX5_UMR_STATE_RECOVER;
+	}
+	mutex_unlock(&umrc->lock);
+
+	/* Sending a final/barrier WR (the failed one) and wait for its completion.
+	 * This will ensure that all the previous WRs got a completion before
+	 * we set the QP state to RESET.
+	 */
+	err = mlx5r_umr_post_send(umrc->qp, mkey, &umr_context->cqe, wqe,
+				  with_data);
+	if (err) {
+		mlx5_ib_warn(dev, "UMR recovery post send failed, err %d\n", err);
+		goto err;
+	}
+
+	/* Since the QP is in an error state, it will only receive
+	 * IB_WC_WR_FLUSH_ERR. However, as it serves only as a barrier
+	 * we don't care about its status.
+	 */
+	wait_for_completion(&umr_context->done);
+
+	attr.qp_state = IB_QPS_RESET;
+	err = ib_modify_qp(umrc->qp, &attr, IB_QP_STATE);
+	if (err) {
+		mlx5_ib_warn(dev, "Couldn't modify UMR QP to RESET, err=%d\n", err);
+		goto err;
+	}
+
+	err = mlx5r_umr_qp_rst2rts(dev, umrc->qp);
+	if (err) {
+		mlx5_ib_warn(dev, "Couldn't modify UMR QP to RTS, err=%d\n", err);
+		goto err;
+	}
+
+	umrc->state = MLX5_UMR_STATE_ACTIVE;
+	return 0;
+
+err:
+	umrc->state = MLX5_UMR_STATE_ERR;
+	return err;
+}
+
 static void mlx5r_umr_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct mlx5_ib_umr_context *context =
@@ -366,9 +397,7 @@ static int mlx5r_umr_post_send_wait(struct mlx5_ib_dev *dev, u32 mkey,
 		mlx5_ib_warn(dev,
 			"reg umr failed (%u). Trying to recover and resubmit the flushed WQEs, mkey = %u\n",
 			umr_context.status, mkey);
-		mutex_lock(&umrc->lock);
-		err = mlx5r_umr_recover(dev);
-		mutex_unlock(&umrc->lock);
+		err = mlx5r_umr_recover(dev, mkey, &umr_context, wqe, with_data);
 		if (err)
 			mlx5_ib_warn(dev, "couldn't recover UMR, err %d\n",
 				     err);

From 12d044770e12c4205fa69535b4fa8a9981fea98f Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Sun, 19 Jan 2025 14:39:46 +0200
Subject: [PATCH 0089/2753] IB/mlx5: Set and get correct qp_num for a DCT QP

When a DCT QP is created on an active lag, it's dctc.port is assigned
in a round-robin way, which is from 1 to dev->lag_port. In this case
when querying this QP, we may get qp_attr.port_num > 2.
Fix this by setting qp->port when modifying a DCT QP, and read port_num
from qp->port instead of dctc.port when querying it.

Fixes: 7c4b1ab9f167 ("IB/mlx5: Add DCT RoCE LAG support")
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Link: https://patch.msgid.link/94c76bf0adbea997f87ffa27674e0a7118ad92a9.1737290358.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/qp.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index a43eba9d3572c..08d22db8dca91 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -4579,6 +4579,8 @@ static int mlx5_ib_modify_dct(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 
 		set_id = mlx5_ib_get_counters_id(dev, attr->port_num - 1);
 		MLX5_SET(dctc, dctc, counter_set_id, set_id);
+
+		qp->port = attr->port_num;
 	} else if (cur_state == IB_QPS_INIT && new_state == IB_QPS_RTR) {
 		struct mlx5_ib_modify_qp_resp resp = {};
 		u32 out[MLX5_ST_SZ_DW(create_dct_out)] = {};
@@ -5074,7 +5076,7 @@ static int mlx5_ib_dct_query_qp(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *mqp,
 	}
 
 	if (qp_attr_mask & IB_QP_PORT)
-		qp_attr->port_num = MLX5_GET(dctc, dctc, port);
+		qp_attr->port_num = mqp->port;
 	if (qp_attr_mask & IB_QP_MIN_RNR_TIMER)
 		qp_attr->min_rnr_timer = MLX5_GET(dctc, dctc, min_rnr_nak);
 	if (qp_attr_mask & IB_QP_AV) {

From 98380110bd48fbfd6a798ee11fffff893d36062c Mon Sep 17 00:00:00 2001
From: Chris Morgan <macromorgan@hotmail.com>
Date: Fri, 31 Jan 2025 17:14:51 -0600
Subject: [PATCH 0090/2753] power: supply: axp20x_battery: Fix fault handling
 for AXP717

Correct the fault handling for the AXP717 by changing the i2c write
from regmap_update_bits() to regmap_write_bits(). The update bits
function does not work properly on a RW1C register where we must
write a 1 back to an existing register to clear it.

Additionally, as part of this testing I confirmed the behavior of
errors reappearing, so remove comment about assumptions.

Fixes: 6625767049c2 ("power: supply: axp20x_battery: add support for AXP717")
Signed-off-by: Chris Morgan <macromorgan@hotmail.com>
Reviewed-by: Chen-Yu Tsai <wens@csie.org>
Link: https://lore.kernel.org/r/20250131231455.153447-2-macroalpha82@gmail.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/axp20x_battery.c | 31 +++++++++++++--------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c
index fa27195f074e7..3c3158f31a484 100644
--- a/drivers/power/supply/axp20x_battery.c
+++ b/drivers/power/supply/axp20x_battery.c
@@ -466,10 +466,9 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 
 	/*
 	 * If a fault is detected it must also be cleared; if the
-	 * condition persists it should reappear (This is an
-	 * assumption, it's actually not documented). A restart was
-	 * not sufficient to clear the bit in testing despite the
-	 * register listed as POR.
+	 * condition persists it should reappear. A restart was not
+	 * sufficient to clear the bit in testing despite the register
+	 * listed as POR.
 	 */
 	case POWER_SUPPLY_PROP_HEALTH:
 		ret = regmap_read(axp20x_batt->regmap, AXP717_PMU_FAULT,
@@ -480,26 +479,26 @@ static int axp717_battery_get_prop(struct power_supply *psy,
 		switch (reg & AXP717_BATT_PMU_FAULT_MASK) {
 		case AXP717_BATT_UVLO_2_5V:
 			val->intval = POWER_SUPPLY_HEALTH_DEAD;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_UVLO_2_5V,
-					   AXP717_BATT_UVLO_2_5V);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_UVLO_2_5V,
+					  AXP717_BATT_UVLO_2_5V);
 			return 0;
 
 		case AXP717_BATT_OVER_TEMP:
 			val->intval = POWER_SUPPLY_HEALTH_HOT;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_OVER_TEMP,
-					   AXP717_BATT_OVER_TEMP);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_OVER_TEMP,
+					  AXP717_BATT_OVER_TEMP);
 			return 0;
 
 		case AXP717_BATT_UNDER_TEMP:
 			val->intval = POWER_SUPPLY_HEALTH_COLD;
-			regmap_update_bits(axp20x_batt->regmap,
-					   AXP717_PMU_FAULT,
-					   AXP717_BATT_UNDER_TEMP,
-					   AXP717_BATT_UNDER_TEMP);
+			regmap_write_bits(axp20x_batt->regmap,
+					  AXP717_PMU_FAULT,
+					  AXP717_BATT_UNDER_TEMP,
+					  AXP717_BATT_UNDER_TEMP);
 			return 0;
 
 		default:

From c9ccb88f534ca760d06590b67571c353a2f0cbcd Mon Sep 17 00:00:00 2001
From: "H. Nikolaus Schaller" <hns@goldelico.com>
Date: Sat, 1 Feb 2025 12:43:24 +0100
Subject: [PATCH 0091/2753] Input: ads7846 - fix gpiod allocation

commit 767d83361aaa ("Input: ads7846 - Convert to use software nodes")

has simplified the code but accidentially converted a devm_gpiod_get()
to gpiod_get(). This leaves the gpio reserved on module remove and the
driver can no longer be loaded again.

Fixes: 767d83361aaa ("Input: ads7846 - Convert to use software nodes")
Cc: stable@vger.kernel.org
Signed-off-by: H. Nikolaus Schaller <hns@goldelico.com>
Link: https://lore.kernel.org/r/6e9b143f19cdfda835711a8a7a3966e5a2494cff.1738410204.git.hns@goldelico.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/ads7846.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 066dc04003fa8..67264c5b49cb4 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -1021,7 +1021,7 @@ static int ads7846_setup_pendown(struct spi_device *spi,
 	if (pdata->get_pendown_state) {
 		ts->get_pendown_state = pdata->get_pendown_state;
 	} else {
-		ts->gpio_pendown = gpiod_get(&spi->dev, "pendown", GPIOD_IN);
+		ts->gpio_pendown = devm_gpiod_get(&spi->dev, "pendown", GPIOD_IN);
 		if (IS_ERR(ts->gpio_pendown)) {
 			dev_err(&spi->dev, "failed to request pendown GPIO\n");
 			return PTR_ERR(ts->gpio_pendown);

From 36e093c8dcc585d0a9e79a005f721f01f3365eba Mon Sep 17 00:00:00 2001
From: Nilton Perim Neto <niltonperimneto@gmail.com>
Date: Mon, 3 Feb 2025 07:13:09 -0800
Subject: [PATCH 0092/2753] Input: xpad - add 8BitDo SN30 Pro, Hyperkin X91 and
 Gamesir G7 SE controllers

Add 8BitDo SN30 Pro, Hyperkin X91 and Gamesir G7 SE to the list of
recognized controllers, and update vendor comments to match.

Signed-off-by: Nilton Perim Neto <niltonperimneto@gmail.com>
Link: https://lore.kernel.org/r/20250122214814.102311-2-niltonperimneto@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 8fe2a51df649e..652afb37bf770 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -376,8 +376,10 @@ static const struct xpad_device {
 	{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
 	{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
+	{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
 	{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
@@ -389,6 +391,7 @@ static const struct xpad_device {
 	{ 0x3285, 0x0646, "Nacon Pro Compact", 0, XTYPE_XBOXONE },
 	{ 0x3285, 0x0663, "Nacon Evol-X", 0, XTYPE_XBOXONE },
 	{ 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 },
+	{ 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE },
 	{ 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX },
 	{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
 	{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
@@ -528,12 +531,12 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOXONE_VENDOR(0x24c6),		/* PowerA controllers */
 	XPAD_XBOX360_VENDOR(0x2563),		/* OneXPlayer Gamepad */
 	XPAD_XBOX360_VENDOR(0x260d),		/* Dareu H101 */
-       XPAD_XBOXONE_VENDOR(0x294b),            /* Snakebyte */
+	XPAD_XBOXONE_VENDOR(0x294b),		/* Snakebyte */
 	XPAD_XBOX360_VENDOR(0x2c22),		/* Qanba Controllers */
-	XPAD_XBOX360_VENDOR(0x2dc8),            /* 8BitDo Pro 2 Wired Controller */
-	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Pro 2 Wired Controller for Xbox */
-	XPAD_XBOXONE_VENDOR(0x2e24),		/* Hyperkin Duke Xbox One pad */
-	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir controllers */
+	XPAD_XBOX360_VENDOR(0x2dc8),		/* 8BitDo Controllers */
+	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Controllers */
+	XPAD_XBOXONE_VENDOR(0x2e24),		/* Hyperkin Controllers */
+	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir Controllers */
 	XPAD_XBOX360_VENDOR(0x31e3),		/* Wooting Keyboards */
 	XPAD_XBOX360_VENDOR(0x3285),		/* Nacon GC-100 */
 	XPAD_XBOXONE_VENDOR(0x3285),		/* Nacon Evol-X */

From 3492321e2e60ddfe91aa438bb9ac209016f48f7a Mon Sep 17 00:00:00 2001
From: Pavel Rojtberg <rojtberg@gmail.com>
Date: Mon, 3 Feb 2025 07:22:27 -0800
Subject: [PATCH 0093/2753] Input: xpad - add multiple supported devices

This is based on multiple commits at https://github.com/paroj/xpad
that had bouncing email addresses and were not signed off.

Signed-off-by: Pavel Rojtberg <rojtberg@gmail.com>
Link: https://lore.kernel.org/r/20250123175404.23254-1-rojtberg@gmail.com
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 652afb37bf770..16493235bf9ee 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -140,6 +140,7 @@ static const struct xpad_device {
 	{ 0x044f, 0x0f00, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f03, "Thrustmaster Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0x0f07, "Thrustmaster, Inc. Controller", 0, XTYPE_XBOX },
+	{ 0x044f, 0xd01e, "ThrustMaster, Inc. ESWAP X 2 ELDEN RING EDITION", 0, XTYPE_XBOXONE },
 	{ 0x044f, 0x0f10, "Thrustmaster Modena GT Wheel", 0, XTYPE_XBOX },
 	{ 0x044f, 0xb326, "Thrustmaster Gamepad GP XID", 0, XTYPE_XBOX360 },
 	{ 0x045e, 0x0202, "Microsoft X-Box pad v1 (US)", 0, XTYPE_XBOX },
@@ -177,6 +178,7 @@ static const struct xpad_device {
 	{ 0x06a3, 0x0200, "Saitek Racing Wheel", 0, XTYPE_XBOX },
 	{ 0x06a3, 0x0201, "Saitek Adrenalin", 0, XTYPE_XBOX },
 	{ 0x06a3, 0xf51a, "Saitek P3600", 0, XTYPE_XBOX360 },
+	{ 0x0738, 0x4503, "Mad Catz Racing Wheel", 0, XTYPE_XBOXONE },
 	{ 0x0738, 0x4506, "Mad Catz 4506 Wireless Controller", 0, XTYPE_XBOX },
 	{ 0x0738, 0x4516, "Mad Catz Control Pad", 0, XTYPE_XBOX },
 	{ 0x0738, 0x4520, "Mad Catz Control Pad Pro", 0, XTYPE_XBOX },
@@ -238,6 +240,7 @@ static const struct xpad_device {
 	{ 0x0e6f, 0x0146, "Rock Candy Wired Controller for Xbox One", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0147, "PDP Marvel Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x015c, "PDP Xbox One Arcade Stick", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
+	{ 0x0e6f, 0x015d, "PDP Mirror's Edge Official Wired Controller for Xbox One", XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0161, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0162, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
 	{ 0x0e6f, 0x0163, "PDP Xbox One Controller", 0, XTYPE_XBOXONE },
@@ -276,12 +279,15 @@ static const struct xpad_device {
 	{ 0x0f0d, 0x0078, "Hori Real Arcade Pro V Kai Xbox One", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x00c5, "Hori Fighting Commander ONE", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOXONE },
 	{ 0x0f0d, 0x00dc, "HORIPAD FPS for Nintendo Switch", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
+	{ 0x0f0d, 0x0151, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
+	{ 0x0f0d, 0x0152, "Hori Racing Wheel Overdrive for Xbox Series X", 0, XTYPE_XBOXONE },
 	{ 0x0f30, 0x010b, "Philips Recoil", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x0202, "Joytech Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x0f30, 0x8888, "BigBen XBMiniPad Controller", 0, XTYPE_XBOX },
 	{ 0x102c, 0xff0c, "Joytech Wireless Advanced Controller", 0, XTYPE_XBOX },
 	{ 0x1038, 0x1430, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
 	{ 0x1038, 0x1431, "SteelSeries Stratus Duo", 0, XTYPE_XBOX360 },
+	{ 0x10f5, 0x7005, "Turtle Beach Recon Controller", 0, XTYPE_XBOXONE },
 	{ 0x11c9, 0x55f0, "Nacon GC-100XF", 0, XTYPE_XBOX360 },
 	{ 0x11ff, 0x0511, "PXN V900", 0, XTYPE_XBOX360 },
 	{ 0x1209, 0x2882, "Ardwiino Controller", 0, XTYPE_XBOX360 },
@@ -366,6 +372,7 @@ static const struct xpad_device {
 	{ 0x24c6, 0x5510, "Hori Fighting Commander ONE (Xbox 360/PC Mode)", MAP_TRIGGERS_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x24c6, 0x551a, "PowerA FUSION Pro Controller", 0, XTYPE_XBOXONE },
 	{ 0x24c6, 0x561a, "PowerA FUSION Controller", 0, XTYPE_XBOXONE },
+	{ 0x24c6, 0x581a, "ThrustMaster XB1 Classic Controller", 0, XTYPE_XBOXONE },
 	{ 0x24c6, 0x5b00, "ThrustMaster Ferrari 458 Racing Wheel", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5b02, "Thrustmaster, Inc. GPX Controller", 0, XTYPE_XBOX360 },
 	{ 0x24c6, 0x5b03, "Thrustmaster Ferrari 458 Racing Wheel", 0, XTYPE_XBOX360 },
@@ -376,10 +383,12 @@ static const struct xpad_device {
 	{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
-	{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x310a, "8BitDo Ultimate 2C Wireless Controller", 0, XTYPE_XBOX360 },
+	{ 0x2dc8, 0x6001, "8BitDo SN30 Pro", 0, XTYPE_XBOX360 },
 	{ 0x2e24, 0x0652, "Hyperkin Duke X-Box One pad", 0, XTYPE_XBOXONE },
 	{ 0x2e24, 0x1688, "Hyperkin X91 X-Box One pad", 0, XTYPE_XBOXONE },
+	{ 0x2e95, 0x0504, "SCUF Gaming Controller", MAP_SELECT_BUTTON, XTYPE_XBOXONE },
 	{ 0x31e3, 0x1100, "Wooting One", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1200, "Wooting Two", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1210, "Wooting Lekker", 0, XTYPE_XBOX360 },
@@ -387,12 +396,16 @@ static const struct xpad_device {
 	{ 0x31e3, 0x1230, "Wooting Two HE (ARM)", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1300, "Wooting 60HE (AVR)", 0, XTYPE_XBOX360 },
 	{ 0x31e3, 0x1310, "Wooting 60HE (ARM)", 0, XTYPE_XBOX360 },
+	{ 0x3285, 0x0603, "Nacon Pro Compact controller for Xbox", 0, XTYPE_XBOXONE },
 	{ 0x3285, 0x0607, "Nacon GC-100", 0, XTYPE_XBOX360 },
+	{ 0x3285, 0x0614, "Nacon Pro Compact", 0, XTYPE_XBOXONE },
 	{ 0x3285, 0x0646, "Nacon Pro Compact", 0, XTYPE_XBOXONE },
+	{ 0x3285, 0x0662, "Nacon Revolution5 Pro", 0, XTYPE_XBOX360 },
 	{ 0x3285, 0x0663, "Nacon Evol-X", 0, XTYPE_XBOXONE },
 	{ 0x3537, 0x1004, "GameSir T4 Kaleid", 0, XTYPE_XBOX360 },
 	{ 0x3537, 0x1010, "GameSir G7 SE", 0, XTYPE_XBOXONE },
 	{ 0x3767, 0x0101, "Fanatec Speedster 3 Forceshock Wheel", 0, XTYPE_XBOX },
+	{ 0x413d, 0x2104, "Black Shark Green Ghost Gamepad", 0, XTYPE_XBOX360 },
 	{ 0xffff, 0xffff, "Chinese-made Xbox Controller", 0, XTYPE_XBOX },
 	{ 0x0000, 0x0000, "Generic X-Box pad", 0, XTYPE_UNKNOWN }
 };
@@ -491,6 +504,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x03f0),		/* HP HyperX Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x03f0),		/* HP HyperX Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x044f),		/* Thrustmaster Xbox 360 controllers */
+	XPAD_XBOXONE_VENDOR(0x044f),		/* Thrustmaster Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x045e),		/* Microsoft Xbox 360 controllers */
 	XPAD_XBOXONE_VENDOR(0x045e),		/* Microsoft Xbox One controllers */
 	XPAD_XBOX360_VENDOR(0x046d),		/* Logitech Xbox 360-style controllers */
@@ -537,11 +551,13 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Controllers */
 	XPAD_XBOXONE_VENDOR(0x2e24),		/* Hyperkin Controllers */
 	XPAD_XBOX360_VENDOR(0x2f24),		/* GameSir Controllers */
+	XPAD_XBOXONE_VENDOR(0x2e95),		/* SCUF Gaming Controller */
 	XPAD_XBOX360_VENDOR(0x31e3),		/* Wooting Keyboards */
 	XPAD_XBOX360_VENDOR(0x3285),		/* Nacon GC-100 */
 	XPAD_XBOXONE_VENDOR(0x3285),		/* Nacon Evol-X */
 	XPAD_XBOX360_VENDOR(0x3537),		/* GameSir Controllers */
 	XPAD_XBOXONE_VENDOR(0x3537),		/* GameSir Controllers */
+	XPAD_XBOX360_VENDOR(0x413d),		/* Black Shark Green Ghost Controller */
 	{ }
 };
 
@@ -694,7 +710,9 @@ static const struct xboxone_init_packet xboxone_init_packets[] = {
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, xboxone_s_init),
 	XBOXONE_INIT_PKT(0x045e, 0x0b00, extra_input_packet_init),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_led_on),
+	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_led_on),
 	XBOXONE_INIT_PKT(0x0e6f, 0x0000, xboxone_pdp_auth),
+	XBOXONE_INIT_PKT(0x20d6, 0xa01a, xboxone_pdp_auth),
 	XBOXONE_INIT_PKT(0x24c6, 0x541a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x542a, xboxone_rumblebegin_init),
 	XBOXONE_INIT_PKT(0x24c6, 0x543a, xboxone_rumblebegin_init),

From a96d3e2beca0e51c8444d0a3b6b3ec484c4c5a8f Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Date: Sun, 12 Jan 2025 01:08:11 +0100
Subject: [PATCH 0094/2753] iio: light: apds9306: fix max_scale_nano values
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The two provided max_scale_nano values must be multiplied by 100 and 10
respectively to achieve nano units. According to the comments:

Max scale for apds0306 is 16.326432 → the fractional part is 0.326432,
which is 326432000 in NANO. The current value is 3264320.

Max scale for apds0306-065 is 14.09721 → the fractional part is 0.09712,
which is 97120000 in NANO. The current value is 9712000.

Update max_scale_nano initialization to use the right NANO fractional
parts.

Cc: stable@vger.kernel.org
Fixes: 620d1e6c7a3f ("iio: light: Add support for APDS9306 Light Sensor")
Signed-off-by: Javier Carrasco <javier.carrasco.cruz@gmail.com>
Tested-by: subhajit.ghosh@tweaklogic.com
Link: https://patch.msgid.link/20250112-apds9306_nano_vals-v1-1-82fb145d0b16@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/apds9306.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iio/light/apds9306.c b/drivers/iio/light/apds9306.c
index 69a0d609cffc9..5ed7e17f49e76 100644
--- a/drivers/iio/light/apds9306.c
+++ b/drivers/iio/light/apds9306.c
@@ -108,11 +108,11 @@ static const struct part_id_gts_multiplier apds9306_gts_mul[] = {
 	{
 		.part_id = 0xB1,
 		.max_scale_int = 16,
-		.max_scale_nano = 3264320,
+		.max_scale_nano = 326432000,
 	}, {
 		.part_id = 0xB3,
 		.max_scale_int = 14,
-		.max_scale_nano = 9712000,
+		.max_scale_nano = 97120000,
 	},
 };
 

From 34d93804199fea23da2645dde35d0feb38a5d445 Mon Sep 17 00:00:00 2001
From: Victor Duicu <victor.duicu@microchip.com>
Date: Fri, 17 Jan 2025 08:53:14 +0200
Subject: [PATCH 0095/2753] iio: adc: pac1921: Move ACPI_FREE() to cover all
 branches

This patch moves ACPI_FREE() in pac1921_match_acpi_device()
in order to cover all branches.

Reported-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Fixes: 9fdf1d033316 ("iio: adc: pac1921: Add ACPI support to Microchip pac1921")
Acked-by: Matteo Martelli <matteomartelli3@gmail.com>
Signed-off-by: Victor Duicu <victor.duicu@microchip.com>
Reviewed-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Link: https://patch.msgid.link/20250117065314.4431-1-victor.duicu@microchip.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/pac1921.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/pac1921.c b/drivers/iio/adc/pac1921.c
index 90f61c47b1c46..63f5182151565 100644
--- a/drivers/iio/adc/pac1921.c
+++ b/drivers/iio/adc/pac1921.c
@@ -1198,11 +1198,11 @@ static int pac1921_match_acpi_device(struct iio_dev *indio_dev)
 
 	label = devm_kstrdup(dev, status->package.elements[0].string.pointer,
 			     GFP_KERNEL);
+	ACPI_FREE(status);
 	if (!label)
 		return -ENOMEM;
 
 	indio_dev->label = label;
-	ACPI_FREE(status);
 
 	return 0;
 }

From aa5119c36d19639397d29ef305aa53a5ecd72b27 Mon Sep 17 00:00:00 2001
From: Nayab Sayed <nayabbasha.sayed@microchip.com>
Date: Wed, 15 Jan 2025 11:37:04 +0530
Subject: [PATCH 0096/2753] iio: adc: at91-sama5d2_adc: fix sama7g5 realbits
 value

The number of valid bits in SAMA7G5 ADC channel data register are 16.
Hence changing the realbits value to 16

Fixes: 840bf6cb983f ("iio: adc: at91-sama5d2_adc: add support for sama7g5 device")
Signed-off-by: Nayab Sayed <nayabbasha.sayed@microchip.com>
Link: https://patch.msgid.link/20250115-fix-sama7g5-adc-realbits-v2-1-58a6e4087584@microchip.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/at91-sama5d2_adc.c | 68 ++++++++++++++++++------------
 1 file changed, 40 insertions(+), 28 deletions(-)

diff --git a/drivers/iio/adc/at91-sama5d2_adc.c b/drivers/iio/adc/at91-sama5d2_adc.c
index 8e5aaf15a9215..c3a1dea2aa82e 100644
--- a/drivers/iio/adc/at91-sama5d2_adc.c
+++ b/drivers/iio/adc/at91-sama5d2_adc.c
@@ -329,7 +329,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 #define AT91_HWFIFO_MAX_SIZE_STR	"128"
 #define AT91_HWFIFO_MAX_SIZE		128
 
-#define AT91_SAMA5D2_CHAN_SINGLE(index, num, addr)			\
+#define AT91_SAMA_CHAN_SINGLE(index, num, addr, rbits)			\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.channel = num,						\
@@ -337,7 +337,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.scan_index = index,					\
 		.scan_type = {						\
 			.sign = 'u',					\
-			.realbits = 14,					\
+			.realbits = rbits,				\
 			.storagebits = 16,				\
 		},							\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
@@ -350,7 +350,13 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.indexed = 1,						\
 	}
 
-#define AT91_SAMA5D2_CHAN_DIFF(index, num, num2, addr)			\
+#define AT91_SAMA5D2_CHAN_SINGLE(index, num, addr)			\
+	AT91_SAMA_CHAN_SINGLE(index, num, addr, 14)
+
+#define AT91_SAMA7G5_CHAN_SINGLE(index, num, addr)			\
+	AT91_SAMA_CHAN_SINGLE(index, num, addr, 16)
+
+#define AT91_SAMA_CHAN_DIFF(index, num, num2, addr, rbits)		\
 	{								\
 		.type = IIO_VOLTAGE,					\
 		.differential = 1,					\
@@ -360,7 +366,7 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.scan_index = index,					\
 		.scan_type = {						\
 			.sign = 's',					\
-			.realbits = 14,					\
+			.realbits = rbits,				\
 			.storagebits = 16,				\
 		},							\
 		.info_mask_separate = BIT(IIO_CHAN_INFO_RAW),		\
@@ -373,6 +379,12 @@ static const struct at91_adc_reg_layout sama7g5_layout = {
 		.indexed = 1,						\
 	}
 
+#define AT91_SAMA5D2_CHAN_DIFF(index, num, num2, addr)			\
+	AT91_SAMA_CHAN_DIFF(index, num, num2, addr, 14)
+
+#define AT91_SAMA7G5_CHAN_DIFF(index, num, num2, addr)			\
+	AT91_SAMA_CHAN_DIFF(index, num, num2, addr, 16)
+
 #define AT91_SAMA5D2_CHAN_TOUCH(num, name, mod)				\
 	{								\
 		.type = IIO_POSITIONRELATIVE,				\
@@ -666,30 +678,30 @@ static const struct iio_chan_spec at91_sama5d2_adc_channels[] = {
 };
 
 static const struct iio_chan_spec at91_sama7g5_adc_channels[] = {
-	AT91_SAMA5D2_CHAN_SINGLE(0, 0, 0x60),
-	AT91_SAMA5D2_CHAN_SINGLE(1, 1, 0x64),
-	AT91_SAMA5D2_CHAN_SINGLE(2, 2, 0x68),
-	AT91_SAMA5D2_CHAN_SINGLE(3, 3, 0x6c),
-	AT91_SAMA5D2_CHAN_SINGLE(4, 4, 0x70),
-	AT91_SAMA5D2_CHAN_SINGLE(5, 5, 0x74),
-	AT91_SAMA5D2_CHAN_SINGLE(6, 6, 0x78),
-	AT91_SAMA5D2_CHAN_SINGLE(7, 7, 0x7c),
-	AT91_SAMA5D2_CHAN_SINGLE(8, 8, 0x80),
-	AT91_SAMA5D2_CHAN_SINGLE(9, 9, 0x84),
-	AT91_SAMA5D2_CHAN_SINGLE(10, 10, 0x88),
-	AT91_SAMA5D2_CHAN_SINGLE(11, 11, 0x8c),
-	AT91_SAMA5D2_CHAN_SINGLE(12, 12, 0x90),
-	AT91_SAMA5D2_CHAN_SINGLE(13, 13, 0x94),
-	AT91_SAMA5D2_CHAN_SINGLE(14, 14, 0x98),
-	AT91_SAMA5D2_CHAN_SINGLE(15, 15, 0x9c),
-	AT91_SAMA5D2_CHAN_DIFF(16, 0, 1, 0x60),
-	AT91_SAMA5D2_CHAN_DIFF(17, 2, 3, 0x68),
-	AT91_SAMA5D2_CHAN_DIFF(18, 4, 5, 0x70),
-	AT91_SAMA5D2_CHAN_DIFF(19, 6, 7, 0x78),
-	AT91_SAMA5D2_CHAN_DIFF(20, 8, 9, 0x80),
-	AT91_SAMA5D2_CHAN_DIFF(21, 10, 11, 0x88),
-	AT91_SAMA5D2_CHAN_DIFF(22, 12, 13, 0x90),
-	AT91_SAMA5D2_CHAN_DIFF(23, 14, 15, 0x98),
+	AT91_SAMA7G5_CHAN_SINGLE(0, 0, 0x60),
+	AT91_SAMA7G5_CHAN_SINGLE(1, 1, 0x64),
+	AT91_SAMA7G5_CHAN_SINGLE(2, 2, 0x68),
+	AT91_SAMA7G5_CHAN_SINGLE(3, 3, 0x6c),
+	AT91_SAMA7G5_CHAN_SINGLE(4, 4, 0x70),
+	AT91_SAMA7G5_CHAN_SINGLE(5, 5, 0x74),
+	AT91_SAMA7G5_CHAN_SINGLE(6, 6, 0x78),
+	AT91_SAMA7G5_CHAN_SINGLE(7, 7, 0x7c),
+	AT91_SAMA7G5_CHAN_SINGLE(8, 8, 0x80),
+	AT91_SAMA7G5_CHAN_SINGLE(9, 9, 0x84),
+	AT91_SAMA7G5_CHAN_SINGLE(10, 10, 0x88),
+	AT91_SAMA7G5_CHAN_SINGLE(11, 11, 0x8c),
+	AT91_SAMA7G5_CHAN_SINGLE(12, 12, 0x90),
+	AT91_SAMA7G5_CHAN_SINGLE(13, 13, 0x94),
+	AT91_SAMA7G5_CHAN_SINGLE(14, 14, 0x98),
+	AT91_SAMA7G5_CHAN_SINGLE(15, 15, 0x9c),
+	AT91_SAMA7G5_CHAN_DIFF(16, 0, 1, 0x60),
+	AT91_SAMA7G5_CHAN_DIFF(17, 2, 3, 0x68),
+	AT91_SAMA7G5_CHAN_DIFF(18, 4, 5, 0x70),
+	AT91_SAMA7G5_CHAN_DIFF(19, 6, 7, 0x78),
+	AT91_SAMA7G5_CHAN_DIFF(20, 8, 9, 0x80),
+	AT91_SAMA7G5_CHAN_DIFF(21, 10, 11, 0x88),
+	AT91_SAMA7G5_CHAN_DIFF(22, 12, 13, 0x90),
+	AT91_SAMA7G5_CHAN_DIFF(23, 14, 15, 0x98),
 	IIO_CHAN_SOFT_TIMESTAMP(24),
 	AT91_SAMA5D2_CHAN_TEMP(AT91_SAMA7G5_ADC_TEMP_CHANNEL, "temp", 0xdc),
 };

From 5d702aa2a47bbab6231382f9ead5be40a287a53b Mon Sep 17 00:00:00 2001
From: Dheeraj Reddy Jonnalagadda <dheeraj.linuxdev@gmail.com>
Date: Tue, 7 Jan 2025 18:05:10 +0530
Subject: [PATCH 0097/2753] iio: proximity: Fix use-after-free in
 hx9023s_send_cfg()

Reorder the assignment of fw_size to happen before release_firmware()
to avoid accessing the firmware structure after it's been freed.

Fixes: e9ed97be4fcc ("iio: proximity: hx9023s: Added firmware file parsing functionality")
Closes: https://scan7.scan.coverity.com/#/project-view/52337/11354?selectedIssue=1602791
Signed-off-by: Dheeraj Reddy Jonnalagadda <dheeraj.linuxdev@gmail.com>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Link: https://patch.msgid.link/20250107123510.44978-1-dheeraj.linuxdev@gmail.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/proximity/hx9023s.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/iio/proximity/hx9023s.c b/drivers/iio/proximity/hx9023s.c
index e092a935dbac7..5aa8e5a22f326 100644
--- a/drivers/iio/proximity/hx9023s.c
+++ b/drivers/iio/proximity/hx9023s.c
@@ -1036,12 +1036,13 @@ static int hx9023s_send_cfg(const struct firmware *fw, struct hx9023s_data *data
 		return -ENOMEM;
 
 	memcpy(bin->data, fw->data, fw->size);
-	release_firmware(fw);
 
 	bin->fw_size = fw->size;
 	bin->fw_ver = bin->data[FW_VER_OFFSET];
 	bin->reg_count = get_unaligned_le16(bin->data + FW_REG_CNT_OFFSET);
 
+	release_firmware(fw);
+
 	return hx9023s_bin_load(data, bin);
 }
 

From 4eba4d92906c3814ca3ec65c16af27c46c12342e Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Mon, 16 Dec 2024 10:05:53 +0000
Subject: [PATCH 0098/2753] iio: hid-sensor-prox: Split difference from
 multiple channels

When the driver was originally created, it was decided that
sampling_frequency and hysteresis would be shared_per_type instead
of shared_by_all (even though it is internally shared by all). Eg:
in_proximity_raw
in_proximity_sampling_frequency

When we introduced support for more channels, we continued with
shared_by_type which. Eg:
in_proximity0_raw
in_proximity1_raw
in_proximity_sampling_frequency
in_attention_raw
in_attention_sampling_frequency

Ideally we should change to shared_by_all, but it is not an option,
because the current naming has been a stablished ABI by now. Luckily we
can use separate instead. That will be more consistent:
in_proximity0_raw
in_proximity0_sampling_frequency
in_proximity1_raw
in_proximity1_sampling_frequency
in_attention_raw
in_attention_sampling_frequency

Fixes: 596ef5cf654b ("iio: hid-sensor-prox: Add support for more channels")
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Link: https://patch.msgid.link/20241216-fix-hid-sensor-v2-1-ff8c1959ec4a@chromium.org
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/light/hid-sensor-prox.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/iio/light/hid-sensor-prox.c b/drivers/iio/light/hid-sensor-prox.c
index 7ab64f5c623c1..76b76d12b3882 100644
--- a/drivers/iio/light/hid-sensor-prox.c
+++ b/drivers/iio/light/hid-sensor-prox.c
@@ -49,9 +49,10 @@ static const u32 prox_sensitivity_addresses[] = {
 #define PROX_CHANNEL(_is_proximity, _channel) \
 	{\
 		.type = _is_proximity ? IIO_PROXIMITY : IIO_ATTENTION,\
-		.info_mask_separate = _is_proximity ? BIT(IIO_CHAN_INFO_RAW) :\
-				      BIT(IIO_CHAN_INFO_PROCESSED),\
-		.info_mask_shared_by_type = BIT(IIO_CHAN_INFO_OFFSET) |\
+		.info_mask_separate = \
+		(_is_proximity ? BIT(IIO_CHAN_INFO_RAW) :\
+				BIT(IIO_CHAN_INFO_PROCESSED)) |\
+		BIT(IIO_CHAN_INFO_OFFSET) |\
 		BIT(IIO_CHAN_INFO_SCALE) |\
 		BIT(IIO_CHAN_INFO_SAMP_FREQ) |\
 		BIT(IIO_CHAN_INFO_HYSTERESIS),\

From 21d7241faf406e8aee3ce348451cc362d5db6a02 Mon Sep 17 00:00:00 2001
From: Markus Burri <markus.burri@mt.com>
Date: Fri, 24 Jan 2025 16:07:03 +0100
Subject: [PATCH 0099/2753] iio: adc: ad7192: fix channel select
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Channel configuration doesn't work as expected.
For FIELD_PREP the bit mask is needed and not the bit number.

Fixes: 874bbd1219c7 ("iio: adc: ad7192: Use bitfield access macros")
Signed-off-by: Markus Burri <markus.burri@mt.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250124150703.97848-1-markus.burri@mt.com
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7192.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad7192.c b/drivers/iio/adc/ad7192.c
index e96a5ae92375d..cfaf8f7e0a07d 100644
--- a/drivers/iio/adc/ad7192.c
+++ b/drivers/iio/adc/ad7192.c
@@ -1084,7 +1084,7 @@ static int ad7192_update_scan_mode(struct iio_dev *indio_dev, const unsigned lon
 
 	conf &= ~AD7192_CONF_CHAN_MASK;
 	for_each_set_bit(i, scan_mask, 8)
-		conf |= FIELD_PREP(AD7192_CONF_CHAN_MASK, i);
+		conf |= FIELD_PREP(AD7192_CONF_CHAN_MASK, BIT(i));
 
 	ret = ad_sd_write_reg(&st->sd, AD7192_REG_CONF, 3, conf);
 	if (ret < 0)

From e17b9f20da7d2bc1f48878ab2230523b2512d965 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Sat, 25 Jan 2025 17:24:32 +0100
Subject: [PATCH 0100/2753] iio: dac: ad3552r: clear reset status flag

Clear reset status flag, to keep error status register clean after reset
(ad3552r manual, rev B table 38).

Reset error flag was left to 1, so debugging registers, the "Error
Status Register" was dirty (0x01). It is important to clear this bit, so
if there is any reset event over normal working mode, it is possible to
detect it.

Fixes: 8f2b54824b28 ("drivers:iio:dac: Add AD3552R driver support")
Signed-off-by: Angelo Dureghello <adureghello@baylibre.com>
Link: https://patch.msgid.link/20250125-wip-bl-ad3552r-clear-reset-v2-1-aa3a27f3ff8c@baylibre.com
Cc: <Stable@vger..kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/dac/ad3552r.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/iio/dac/ad3552r.c b/drivers/iio/dac/ad3552r.c
index e7206af53af61..7944f5c1d264d 100644
--- a/drivers/iio/dac/ad3552r.c
+++ b/drivers/iio/dac/ad3552r.c
@@ -410,6 +410,12 @@ static int ad3552r_reset(struct ad3552r_desc *dac)
 		return ret;
 	}
 
+	/* Clear reset error flag, see ad3552r manual, rev B table 38. */
+	ret = ad3552r_write_reg(dac, AD3552R_REG_ADDR_ERR_STATUS,
+				AD3552R_MASK_RESET_STATUS);
+	if (ret)
+		return ret;
+
 	return ad3552r_update_reg_field(dac,
 					AD3552R_REG_ADDR_INTERFACE_CONFIG_A,
 					AD3552R_MASK_ADDR_ASCENSION,

From 02ccd7e5d81af4ae20852fc1ad67e7d943fa5778 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Wed, 29 Jan 2025 12:03:02 +0100
Subject: [PATCH 0101/2753] dt-bindings: iio: dac: adi-axi-adc: fix ad7606
 pwm-names

Fix make dt_binding_check warning:

DTC [C] Documentation/devicetree/bindings/iio/adc/adi,axi-adc.example.dtb
.../adc/adi,axi-adc.example.dtb: adc@0: pwm-names: ['convst1'] is too short
    from schema $id: http://devicetree.org/schemas/iio/adc/adi,ad7606.yaml#

Add "minItems" to pwm-names, it allows to use one single pwm when
connected to both adc conversion inputs.

Fixes: 7c2357b10490 ("dt-bindings: iio: adc: ad7606: Add iio backend bindings")
Signed-off-by: Angelo Dureghello <adureghello@baylibre.com>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250129-wip-bl-ad7606_add_backend_sw_mode-v3-1-c3aec77c0ab7@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
index ab5881d0d017f..52d3f1ce33678 100644
--- a/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
+++ b/Documentation/devicetree/bindings/iio/adc/adi,ad7606.yaml
@@ -146,6 +146,7 @@ properties:
     maxItems: 2
 
   pwm-names:
+    minItems: 1
     items:
       - const: convst1
       - const: convst2

From bead181694df16de464ca2392d0cec2cf15fb978 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Wed, 29 Jan 2025 12:03:04 +0100
Subject: [PATCH 0102/2753] iio: adc: ad7606: fix wrong scale available

Fix wrong scale available list since only one value is returned:

...
iio:device1: ad7606b (buffer capable)
    8 channels found:
           voltage0:  (input, index: 0, format: le:S16/16>>0)
           2 channel-specific attributes found:
                 attr  0: scale value: 0.305176
                 attr  1: scale_available value: 0.076293
Fix as:
           voltage0:  (input, index: 0, format: le:S16/16>>0)
           2 channel-specific attributes found:
                 attr  0: scale value: 0.305176
                 attr  1: scale_available value: 0.076293 0.152588 0.305176

Fixes: 97c6d857041d ("iio: adc: ad7606: rework scale-available to be static")
Signed-off-by: Angelo Dureghello <adureghello@baylibre.com>
Link: https://patch.msgid.link/20250129-wip-bl-ad7606_add_backend_sw_mode-v3-3-c3aec77c0ab7@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad7606.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
index d8e3c7a43678c..d39354afd5394 100644
--- a/drivers/iio/adc/ad7606.c
+++ b/drivers/iio/adc/ad7606.c
@@ -1047,7 +1047,7 @@ static int ad7606_read_avail(struct iio_dev *indio_dev,
 
 		cs = &st->chan_scales[ch];
 		*vals = (int *)cs->scale_avail;
-		*length = cs->num_scales;
+		*length = cs->num_scales * 2;
 		*type = IIO_VAL_INT_PLUS_MICRO;
 
 		return IIO_AVAIL_LIST;

From 4094445969740028f9b637977781b73b64c5bc7c Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 24 Jan 2025 11:46:35 +0530
Subject: [PATCH 0103/2753] wifi: ath12k: update beacon template function to
 use arvif structure

The current code has ath12k_wmi_bcn_tmpl() accepting separate ar and
vdev_id parameters. However, ath12k_link_vif structure can be used to
derive both of these.

Hence, simplify the function signature.

Later change needs arvif pointer access within the function hence it is
better if arvif is directly passed now.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250124-ath12k_mlo_csa-v2-1-420c42fcfecf@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 5 ++---
 drivers/net/wireless/ath/ath12k/wmi.c | 4 +++-
 drivers/net/wireless/ath/ath12k/wmi.h | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index e9663c6ac72cd..a70b8bdda8559 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1671,8 +1671,7 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif)
 
 		ema_args.bcn_cnt = beacons->cnt;
 		ema_args.bcn_index = i;
-		ret = ath12k_wmi_bcn_tmpl(tx_arvif->ar, tx_arvif->vdev_id,
-					  &beacons->bcn[i].offs,
+		ret = ath12k_wmi_bcn_tmpl(tx_arvif, &beacons->bcn[i].offs,
 					  beacons->bcn[i].skb, &ema_args);
 		if (ret) {
 			ath12k_warn(tx_arvif->ar->ab,
@@ -1766,7 +1765,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 		}
 	}
 
-	ret = ath12k_wmi_bcn_tmpl(ar, arvif->vdev_id, &offs, bcn, NULL);
+	ret = ath12k_wmi_bcn_tmpl(arvif, &offs, bcn, NULL);
 
 	if (ret)
 		ath12k_warn(ab, "failed to submit beacon template command: %d\n",
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index ad29c4c99dc78..92d7d3c9d50cd 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1927,14 +1927,16 @@ int ath12k_wmi_p2p_go_bcn_ie(struct ath12k *ar, u32 vdev_id,
 	return ret;
 }
 
-int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
+int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 			struct ieee80211_mutable_offsets *offs,
 			struct sk_buff *bcn,
 			struct ath12k_wmi_bcn_tmpl_ema_arg *ema_args)
 {
+	struct ath12k *ar = arvif->ar;
 	struct ath12k_wmi_pdev *wmi = ar->wmi;
 	struct wmi_bcn_tmpl_cmd *cmd;
 	struct ath12k_wmi_bcn_prb_info_params *bcn_prb_info;
+	u32 vdev_id = arvif->vdev_id;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
 	u32 ema_params = 0;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index bd069a81e4c61..63a88fb821cad 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -5780,7 +5780,7 @@ int ath12k_wmi_mgmt_send(struct ath12k *ar, u32 vdev_id, u32 buf_id,
 			 struct sk_buff *frame);
 int ath12k_wmi_p2p_go_bcn_ie(struct ath12k *ar, u32 vdev_id,
 			     const u8 *p2p_ie);
-int ath12k_wmi_bcn_tmpl(struct ath12k *ar, u32 vdev_id,
+int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 			struct ieee80211_mutable_offsets *offs,
 			struct sk_buff *bcn,
 			struct ath12k_wmi_bcn_tmpl_ema_arg *ema_args);

From f9c88d65e805ca06f26806ac99f569a3dfac2229 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 24 Jan 2025 11:46:36 +0530
Subject: [PATCH 0104/2753] wifi: ath12k: fix handling of CSA offsets in beacon
 template command

The driver is informed of the counter offsets in the beacon during CSA
through the ieee80211_mutable_offsets structure. According to the
documentation for the cntdwn_counter_offs member, "This array can contain
zero values which should be ignored." However, the current implementation
uses these values unconditionally, without checking for zeros.

Whenever CSA is active, these offsets are guaranteed to be set. Therefore,
add a check for CSA active status before setting the CSA switch count
offsets. This ensures that the offsets are only set when CSA is active,
preventing incorrect configurations.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250124-ath12k_mlo_csa-v2-2-420c42fcfecf@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c |  2 +-
 drivers/net/wireless/ath/ath12k/mac.h |  1 +
 drivers/net/wireless/ath/ath12k/wmi.c | 23 ++++++++++++++++++++---
 3 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index a70b8bdda8559..cf8b6a1f7ae93 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -579,7 +579,7 @@ static int ath12k_mac_vif_link_chan(struct ieee80211_vif *vif, u8 link_id,
 	return 0;
 }
 
-static struct ieee80211_bss_conf *
+struct ieee80211_bss_conf *
 ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *arvif)
 {
 	struct ieee80211_vif *vif = arvif->ahvif->vif;
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index 1acaf3f68292c..5a6e3c3316bec 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -111,5 +111,6 @@ void ath12k_mac_get_any_chanctx_conf_iter(struct ieee80211_hw *hw,
 u16 ath12k_mac_he_convert_tones_to_ru_tones(u16 tones);
 enum nl80211_eht_ru_alloc ath12k_mac_eht_ru_tones_to_nl80211_eht_ru_alloc(u16 ru_tones);
 enum nl80211_eht_gi ath12k_mac_eht_gi_to_nl80211_eht_gi(u8 sgi);
+struct ieee80211_bss_conf *ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *arvif);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 92d7d3c9d50cd..7a133d39c9155 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1934,8 +1934,11 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 {
 	struct ath12k *ar = arvif->ar;
 	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct ath12k_base *ab = ar->ab;
 	struct wmi_bcn_tmpl_cmd *cmd;
 	struct ath12k_wmi_bcn_prb_info_params *bcn_prb_info;
+	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ieee80211_bss_conf *conf;
 	u32 vdev_id = arvif->vdev_id;
 	struct wmi_tlv *tlv;
 	struct sk_buff *skb;
@@ -1944,6 +1947,14 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 	int ret, len;
 	size_t aligned_len = roundup(bcn->len, 4);
 
+	conf = ath12k_mac_get_link_bss_conf(arvif);
+	if (!conf) {
+		ath12k_warn(ab,
+			    "unable to access bss link conf in beacon template command for vif %pM link %u\n",
+			    ahvif->vif->addr, arvif->link_id);
+		return -EINVAL;
+	}
+
 	len = sizeof(*cmd) + sizeof(*bcn_prb_info) + TLV_HDR_SIZE + aligned_len;
 
 	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, len);
@@ -1955,8 +1966,14 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 						 sizeof(*cmd));
 	cmd->vdev_id = cpu_to_le32(vdev_id);
 	cmd->tim_ie_offset = cpu_to_le32(offs->tim_offset);
-	cmd->csa_switch_count_offset = cpu_to_le32(offs->cntdwn_counter_offs[0]);
-	cmd->ext_csa_switch_count_offset = cpu_to_le32(offs->cntdwn_counter_offs[1]);
+
+	if (conf->csa_active) {
+		cmd->csa_switch_count_offset =
+				cpu_to_le32(offs->cntdwn_counter_offs[0]);
+		cmd->ext_csa_switch_count_offset =
+				cpu_to_le32(offs->cntdwn_counter_offs[1]);
+	}
+
 	cmd->buf_len = cpu_to_le32(bcn->len);
 	cmd->mbssid_ie_offset = cpu_to_le32(offs->mbssid_off);
 	if (ema_args) {
@@ -1986,7 +2003,7 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 
 	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_BCN_TMPL_CMDID);
 	if (ret) {
-		ath12k_warn(ar->ab, "failed to send WMI_BCN_TMPL_CMDID\n");
+		ath12k_warn(ab, "failed to send WMI_BCN_TMPL_CMDID\n");
 		dev_kfree_skb(skb);
 	}
 

From e26a6989b10a3dfc97b8c206023a6bf3a3ccb94e Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 24 Jan 2025 11:46:37 +0530
Subject: [PATCH 0105/2753] wifi: ath12k: update the latest CSA counter

At present, the driver configures the firmware to send the Channel Switch
(CS) count event only when the count reaches zero during a Channel Switch
Announcement (CSA). For frames managed by the upper layer, where the driver
does not update the counter, the CS count in these frames remains unchanged
throughout the entire CSA period. This is because the upper layer is not
aware of the latest ongoing count. Indicating same count value throughout
the CSA time is wrong and could lead to connection instabilities.

Fix this by configuring firmware to send CS count event for every count and
then accordingly decrementing the count in mac80211.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250124-ath12k_mlo_csa-v2-3-420c42fcfecf@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 7a133d39c9155..fdbb604e4fb09 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1972,6 +1972,7 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 				cpu_to_le32(offs->cntdwn_counter_offs[0]);
 		cmd->ext_csa_switch_count_offset =
 				cpu_to_le32(offs->cntdwn_counter_offs[1]);
+		cmd->csa_event_bitmap = cpu_to_le32(0xFFFFFFFF);
 	}
 
 	cmd->buf_len = cpu_to_le32(bcn->len);
@@ -7496,17 +7497,15 @@ ath12k_wmi_process_csa_switch_count_event(struct ath12k_base *ab,
 					  const struct ath12k_wmi_pdev_csa_event *ev,
 					  const u32 *vdev_ids)
 {
-	int i;
+	u32 current_switch_count = le32_to_cpu(ev->current_switch_count);
+	u32 num_vdevs = le32_to_cpu(ev->num_vdevs);
 	struct ieee80211_bss_conf *conf;
 	struct ath12k_link_vif *arvif;
 	struct ath12k_vif *ahvif;
-
-	/* Finish CSA once the switch count becomes NULL */
-	if (ev->current_switch_count)
-		return;
+	int i;
 
 	rcu_read_lock();
-	for (i = 0; i < le32_to_cpu(ev->num_vdevs); i++) {
+	for (i = 0; i < num_vdevs; i++) {
 		arvif = ath12k_mac_get_arvif_by_vdev_id(ab, vdev_ids[i]);
 
 		if (!arvif) {
@@ -7529,8 +7528,14 @@ ath12k_wmi_process_csa_switch_count_event(struct ath12k_base *ab,
 			continue;
 		}
 
-		if (arvif->is_up && conf->csa_active)
-			ieee80211_csa_finish(ahvif->vif, 0);
+		if (!arvif->is_up || !conf->csa_active)
+			continue;
+
+		/* Finish CSA when counter reaches zero */
+		if (!current_switch_count)
+			ieee80211_csa_finish(ahvif->vif, arvif->link_id);
+		else if (current_switch_count > 1)
+			ieee80211_beacon_update_cntdwn(ahvif->vif, arvif->link_id);
 	}
 	rcu_read_unlock();
 }

From 36f002a3e36efd3370f5b6abfc157e7481ecb1e0 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 24 Jan 2025 11:46:38 +0530
Subject: [PATCH 0106/2753] wifi: ath12k: prevent CSA counter to reach 0 and
 hit WARN_ON_ONCE

Currently, when the driver receives a channel switch count WMI event from
the firmware with a count greater than 1, it calls
ieee80211_beacon_update_cntdwn(). If the beacon transmission fails, the
event will be received again with the previous count value. In this
scenario, the host decrements the mac80211 counter again, causing it to
move ahead of the firmware counter. Ultimately, when the firmware count
reaches 1, the mac80211 counter will reach zero, triggering a
WARN_ON_ONCE(). Therefore, there is a need to check the count value in the
event.

Hence to fix this, maintain the current ongoing counter in arvif. If the
count in the event does not match the expected value, silently discard the
event.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250124-ath12k_mlo_csa-v2-4-420c42fcfecf@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h |  2 ++
 drivers/net/wireless/ath/ath12k/wmi.c  | 19 ++++++++++++++++---
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 28db100cfac06..407404e7abb75 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -301,6 +301,8 @@ struct ath12k_link_vif {
 	u8 link_id;
 	struct ath12k_vif *ahvif;
 	struct ath12k_rekey_data rekey_data;
+
+	u8 current_cntdown_counter;
 };
 
 struct ath12k_vif {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index fdbb604e4fb09..b43ab621a74e0 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -1973,6 +1973,7 @@ int ath12k_wmi_bcn_tmpl(struct ath12k_link_vif *arvif,
 		cmd->ext_csa_switch_count_offset =
 				cpu_to_le32(offs->cntdwn_counter_offs[1]);
 		cmd->csa_event_bitmap = cpu_to_le32(0xFFFFFFFF);
+		arvif->current_cntdown_counter = bcn->data[offs->cntdwn_counter_offs[0]];
 	}
 
 	cmd->buf_len = cpu_to_le32(bcn->len);
@@ -7532,10 +7533,22 @@ ath12k_wmi_process_csa_switch_count_event(struct ath12k_base *ab,
 			continue;
 
 		/* Finish CSA when counter reaches zero */
-		if (!current_switch_count)
+		if (!current_switch_count) {
 			ieee80211_csa_finish(ahvif->vif, arvif->link_id);
-		else if (current_switch_count > 1)
-			ieee80211_beacon_update_cntdwn(ahvif->vif, arvif->link_id);
+			arvif->current_cntdown_counter = 0;
+		} else if (current_switch_count > 1) {
+			/* If the count in event is not what we expect, don't update the
+			 * mac80211 count. Since during beacon Tx failure, count in the
+			 * firmware will not decrement and this event will come with the
+			 * previous count value again
+			 */
+			if (current_switch_count != arvif->current_cntdown_counter)
+				continue;
+
+			arvif->current_cntdown_counter =
+				ieee80211_beacon_update_cntdwn(ahvif->vif,
+							       arvif->link_id);
+		}
 	}
 	rcu_read_unlock();
 }

From 268c73d470a5790a492a2fc2ded084b909d144f3 Mon Sep 17 00:00:00 2001
From: Avula Sri Charan <quic_asrichar@quicinc.com>
Date: Fri, 24 Jan 2025 14:30:58 +0530
Subject: [PATCH 0107/2753] wifi: ath12k: Avoid napi_sync() before
 napi_enable()

In case of MHI error a reset work will be queued which will try
napi_disable() after napi_synchronize().

As the napi will be only enabled after qmi_firmware_ready event,
trying napi_synchronize() before napi_enable() will result in
indefinite sleep in case of a firmware crash in QMI init sequence.

To avoid this, introduce napi_enabled flag to check if napi is enabled
or not before calling napi_synchronize().

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Avula Sri Charan <quic_asrichar@quicinc.com>
Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124090058.3194299-1-quic_tamizhr@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h |  1 +
 drivers/net/wireless/ath/ath12k/pci.c  | 13 ++++++++++---
 2 files changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 407404e7abb75..983a5d735cebc 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -168,6 +168,7 @@ struct ath12k_ext_irq_grp {
 	u32 num_irq;
 	u32 grp_id;
 	u64 timestamp;
+	bool napi_enabled;
 	struct napi_struct napi;
 	struct net_device *napi_ndev;
 };
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 6c6a3cabab326..7126cc361deff 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -483,8 +483,11 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
 
 		ath12k_pci_ext_grp_disable(irq_grp);
 
-		napi_synchronize(&irq_grp->napi);
-		napi_disable(&irq_grp->napi);
+		if (irq_grp->napi_enabled) {
+			napi_synchronize(&irq_grp->napi);
+			napi_disable(&irq_grp->napi);
+			irq_grp->napi_enabled = false;
+		}
 	}
 }
 
@@ -1114,7 +1117,11 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab)
 	for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
 		struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
 
-		napi_enable(&irq_grp->napi);
+		if (!irq_grp->napi_enabled) {
+			napi_enable(&irq_grp->napi);
+			irq_grp->napi_enabled = true;
+		}
+
 		ath12k_pci_ext_grp_enable(irq_grp);
 	}
 

From 090c645b2acc835cccf52a8876dccec55629f479 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 10 Jan 2025 00:13:12 +0530
Subject: [PATCH 0108/2753] wifi: ath12k: relocate
 ath12k_mac_ieee80211_sta_bw_to_wmi()

An upcoming change will invoke ath12k_mac_ieee80211_sta_bw_to_wmi() from a
line located above its current definition. Hence, relocate it to above
so that it can be invoked later on.

No functionality changes. Compile tested only.

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Acked-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Link: https://patch.msgid.link/20250110-fix_link_sta_bandwidth_update-v1-1-61b6f3ef2ea3@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 62 +++++++++++++--------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index cf8b6a1f7ae93..55d4f3fb5cd11 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3218,6 +3218,37 @@ static int ath12k_setup_peer_smps(struct ath12k *ar, struct ath12k_link_vif *arv
 					 ath12k_smps_map[smps]);
 }
 
+static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar,
+					      struct ieee80211_sta *sta)
+{
+	u32 bw = WMI_PEER_CHWIDTH_20MHZ;
+
+	switch (sta->deflink.bandwidth) {
+	case IEEE80211_STA_RX_BW_20:
+		bw = WMI_PEER_CHWIDTH_20MHZ;
+		break;
+	case IEEE80211_STA_RX_BW_40:
+		bw = WMI_PEER_CHWIDTH_40MHZ;
+		break;
+	case IEEE80211_STA_RX_BW_80:
+		bw = WMI_PEER_CHWIDTH_80MHZ;
+		break;
+	case IEEE80211_STA_RX_BW_160:
+		bw = WMI_PEER_CHWIDTH_160MHZ;
+		break;
+	case IEEE80211_STA_RX_BW_320:
+		bw = WMI_PEER_CHWIDTH_320MHZ;
+		break;
+	default:
+		ath12k_warn(ar->ab, "Invalid bandwidth %d in rc update for %pM\n",
+			    sta->deflink.bandwidth, sta->addr);
+		bw = WMI_PEER_CHWIDTH_20MHZ;
+		break;
+	}
+
+	return bw;
+}
+
 static void ath12k_bss_assoc(struct ath12k *ar,
 			     struct ath12k_link_vif *arvif,
 			     struct ieee80211_bss_conf *bss_conf)
@@ -5495,37 +5526,6 @@ static int ath12k_mac_station_add(struct ath12k *ar,
 	return ret;
 }
 
-static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar,
-					      struct ieee80211_sta *sta)
-{
-	u32 bw = WMI_PEER_CHWIDTH_20MHZ;
-
-	switch (sta->deflink.bandwidth) {
-	case IEEE80211_STA_RX_BW_20:
-		bw = WMI_PEER_CHWIDTH_20MHZ;
-		break;
-	case IEEE80211_STA_RX_BW_40:
-		bw = WMI_PEER_CHWIDTH_40MHZ;
-		break;
-	case IEEE80211_STA_RX_BW_80:
-		bw = WMI_PEER_CHWIDTH_80MHZ;
-		break;
-	case IEEE80211_STA_RX_BW_160:
-		bw = WMI_PEER_CHWIDTH_160MHZ;
-		break;
-	case IEEE80211_STA_RX_BW_320:
-		bw = WMI_PEER_CHWIDTH_320MHZ;
-		break;
-	default:
-		ath12k_warn(ar->ab, "Invalid bandwidth %d in rc update for %pM\n",
-			    sta->deflink.bandwidth, sta->addr);
-		bw = WMI_PEER_CHWIDTH_20MHZ;
-		break;
-	}
-
-	return bw;
-}
-
 static int ath12k_mac_assign_link_sta(struct ath12k_hw *ah,
 				      struct ath12k_sta *ahsta,
 				      struct ath12k_link_sta *arsta,

From 2fc98b24adb93457254ee16418cffa89de038ad9 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <quic_adisi@quicinc.com>
Date: Fri, 10 Jan 2025 00:13:13 +0530
Subject: [PATCH 0109/2753] wifi: ath12k: handle
 ath12k_mac_ieee80211_sta_bw_to_wmi() for link sta

Currently ath12k_mac_ieee80211_sta_bw_to_wmi() handles the bandwidth from
sta's deflink member. This works only for non-ML station. Now that MLO
support is there, extend this function to use link sta instead of deflink.

Additionally, in ath12k_mac_handle_link_sta_state(), the link sta structure
is not accessible, making it difficult to fetch the bandwidth there.
However, ath12k_mac_station_assoc() does reference the link sta structure.
Therefore, move the initial assignment of the arsta bandwidth member to
ath12k_mac_station_assoc().

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Acked-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Link: https://patch.msgid.link/20250110-fix_link_sta_bandwidth_update-v1-2-61b6f3ef2ea3@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 25 +++++++++++--------------
 1 file changed, 11 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 55d4f3fb5cd11..aadace85dc117 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3219,11 +3219,11 @@ static int ath12k_setup_peer_smps(struct ath12k *ar, struct ath12k_link_vif *arv
 }
 
 static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar,
-					      struct ieee80211_sta *sta)
+					      struct ieee80211_link_sta *link_sta)
 {
-	u32 bw = WMI_PEER_CHWIDTH_20MHZ;
+	u32 bw;
 
-	switch (sta->deflink.bandwidth) {
+	switch (link_sta->bandwidth) {
 	case IEEE80211_STA_RX_BW_20:
 		bw = WMI_PEER_CHWIDTH_20MHZ;
 		break;
@@ -3240,8 +3240,8 @@ static u32 ath12k_mac_ieee80211_sta_bw_to_wmi(struct ath12k *ar,
 		bw = WMI_PEER_CHWIDTH_320MHZ;
 		break;
 	default:
-		ath12k_warn(ar->ab, "Invalid bandwidth %d in rc update for %pM\n",
-			    sta->deflink.bandwidth, sta->addr);
+		ath12k_warn(ar->ab, "Invalid bandwidth %d for link station %pM\n",
+			    link_sta->bandwidth, link_sta->addr);
 		bw = WMI_PEER_CHWIDTH_20MHZ;
 		break;
 	}
@@ -5020,6 +5020,11 @@ static int ath12k_mac_station_assoc(struct ath12k *ar,
 		return -EINVAL;
 	}
 
+	spin_lock_bh(&ar->data_lock);
+	arsta->bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, link_sta);
+	arsta->bw_prev = link_sta->bandwidth;
+	spin_unlock_bh(&ar->data_lock);
+
 	if (link_sta->vht_cap.vht_supported && num_vht_rates == 1) {
 		ret = ath12k_mac_set_peer_vht_fixed_rate(arvif, arsta, mask,
 							 band);
@@ -5609,7 +5614,6 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 					    enum ieee80211_sta_state new_state)
 {
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(arvif->ahvif);
-	struct ieee80211_sta *sta = ath12k_ahsta_to_sta(arsta->ahsta);
 	struct ath12k *ar = arvif->ar;
 	int ret = 0;
 
@@ -5652,13 +5656,6 @@ static int ath12k_mac_handle_link_sta_state(struct ieee80211_hw *hw,
 			ath12k_warn(ar->ab, "Failed to associate station: %pM\n",
 				    arsta->addr);
 
-		spin_lock_bh(&ar->data_lock);
-
-		arsta->bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, sta);
-		arsta->bw_prev = sta->deflink.bandwidth;
-
-		spin_unlock_bh(&ar->data_lock);
-
 	/* IEEE80211_STA_ASSOC -> IEEE80211_STA_AUTHORIZED: set peer status as
 	 * authorized
 	 */
@@ -5926,7 +5923,7 @@ static void ath12k_mac_op_link_sta_rc_update(struct ieee80211_hw *hw,
 	spin_lock_bh(&ar->data_lock);
 
 	if (changed & IEEE80211_RC_BW_CHANGED) {
-		bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, sta);
+		bw = ath12k_mac_ieee80211_sta_bw_to_wmi(ar, link_sta);
 		arsta->bw_prev = arsta->bw;
 		arsta->bw = bw;
 	}

From b59d1f8207de4e2ec763a5e58f95811d0eb2272c Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:48:07 +0800
Subject: [PATCH 0110/2753] wifi: ath12k: Add support for obtaining the buffer
 type ACPI function bitmap

Currently, ath12k does not support obtaining the buffer type ACPI function
bitmap.

To solve this issue, change the code to support obtaining the buffer type
ACPI function bitmap.

This patch will not affect QCN9274, because only WCN7850 supports ACPI.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20250113074810.29729-2-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/acpi.c | 18 ++++++++++++++++--
 drivers/net/wireless/ath/ath12k/acpi.h |  5 ++++-
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/acpi.c b/drivers/net/wireless/ath/ath12k/acpi.c
index 0555d35aab477..b6935ab1655e4 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.c
+++ b/drivers/net/wireless/ath/ath12k/acpi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -12,7 +12,7 @@ static int ath12k_acpi_dsm_get_data(struct ath12k_base *ab, int func)
 {
 	union acpi_object *obj;
 	acpi_handle root_handle;
-	int ret;
+	int ret, i;
 
 	root_handle = ACPI_HANDLE(ab->dev);
 	if (!root_handle) {
@@ -32,6 +32,20 @@ static int ath12k_acpi_dsm_get_data(struct ath12k_base *ab, int func)
 		ab->acpi.func_bit = obj->integer.value;
 	} else if (obj->type == ACPI_TYPE_BUFFER) {
 		switch (func) {
+		case ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS:
+			if (obj->buffer.length < ATH12K_ACPI_DSM_FUNC_MIN_BITMAP_SIZE ||
+			    obj->buffer.length > ATH12K_ACPI_DSM_FUNC_MAX_BITMAP_SIZE) {
+				ath12k_warn(ab, "invalid ACPI DSM func size: %d\n",
+					    obj->buffer.length);
+				ret = -EINVAL;
+				goto out;
+			}
+
+			ab->acpi.func_bit = 0;
+			for (i = 0; i < obj->buffer.length; i++)
+				ab->acpi.func_bit += obj->buffer.pointer[i] << (i * 8);
+
+			break;
 		case ATH12K_ACPI_DSM_FUNC_TAS_CFG:
 			if (obj->buffer.length != ATH12K_ACPI_DSM_TAS_CFG_SIZE) {
 				ath12k_warn(ab, "invalid ACPI DSM TAS config size: %d\n",
diff --git a/drivers/net/wireless/ath/ath12k/acpi.h b/drivers/net/wireless/ath/ath12k/acpi.h
index 39e003d86a48b..6ccc26250aafb 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.h
+++ b/drivers/net/wireless/ath/ath12k/acpi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #ifndef ATH12K_ACPI_H
 #define ATH12K_ACPI_H
@@ -48,6 +48,9 @@
 #define ATH12K_ACPI_DSM_BAND_EDGE_DATA_SIZE		100
 #define ATH12K_ACPI_DSM_TAS_CFG_SIZE			108
 
+#define ATH12K_ACPI_DSM_FUNC_MIN_BITMAP_SIZE	1
+#define ATH12K_ACPI_DSM_FUNC_MAX_BITMAP_SIZE	4
+
 #define ATH12K_ACPI_DSM_GEO_OFFSET_DATA_SIZE (ATH12K_ACPI_GEO_OFFSET_DATA_OFFSET + \
 					      ATH12K_ACPI_BIOS_SAR_GEO_OFFSET_LEN)
 #define ATH12K_ACPI_DSM_BIOS_SAR_DATA_SIZE (ATH12K_ACPI_POWER_LIMIT_DATA_OFFSET + \

From c6a7c0b09d5f430c36f860af1032e9dfa2dfcdc5 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:48:08 +0800
Subject: [PATCH 0111/2753] wifi: ath12k: Add Support for enabling or disabling
 specific features based on ACPI bitflag

Currently, ath12k does not support enable or disable specific features by
ACPI bitflag.

To address this issue, obtain the ACPI bitflag value and use it to
selectively enable or disable specific features.

This patch will not affect QCN9274, because only WCN7850 supports ACPI.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20250113074810.29729-3-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/acpi.c | 41 ++++++++++++++++++++++++--
 drivers/net/wireless/ath/ath12k/acpi.h | 18 +++++++++++
 drivers/net/wireless/ath/ath12k/core.c |  3 ++
 drivers/net/wireless/ath/ath12k/core.h |  3 ++
 drivers/net/wireless/ath/ath12k/mac.c  |  3 +-
 5 files changed, 64 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/acpi.c b/drivers/net/wireless/ath/ath12k/acpi.c
index b6935ab1655e4..186ef5d62813c 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.c
+++ b/drivers/net/wireless/ath/ath12k/acpi.c
@@ -29,7 +29,14 @@ static int ath12k_acpi_dsm_get_data(struct ath12k_base *ab, int func)
 	}
 
 	if (obj->type == ACPI_TYPE_INTEGER) {
-		ab->acpi.func_bit = obj->integer.value;
+		switch (func) {
+		case ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS:
+			ab->acpi.func_bit = obj->integer.value;
+			break;
+		case ATH12K_ACPI_DSM_FUNC_DISABLE_FLAG:
+			ab->acpi.bit_flag = obj->integer.value;
+			break;
+		}
 	} else if (obj->type == ACPI_TYPE_BUFFER) {
 		switch (func) {
 		case ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS:
@@ -261,24 +268,52 @@ static int ath12k_acpi_set_tas_params(struct ath12k_base *ab)
 	return 0;
 }
 
+bool ath12k_acpi_get_disable_rfkill(struct ath12k_base *ab)
+{
+	return ab->acpi.acpi_disable_rfkill;
+}
+
+bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab)
+{
+	return ab->acpi.acpi_disable_11be;
+}
+
 int ath12k_acpi_start(struct ath12k_base *ab)
 {
 	acpi_status status;
 	u8 *buf;
 	int ret;
 
+	ab->acpi.acpi_tas_enable = false;
+	ab->acpi.acpi_disable_11be = false;
+	ab->acpi.acpi_disable_rfkill = false;
+
 	if (!ab->hw_params->acpi_guid)
 		/* not supported with this hardware */
 		return 0;
 
-	ab->acpi.acpi_tas_enable = false;
-
 	ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS);
 	if (ret) {
 		ath12k_dbg(ab, ATH12K_DBG_BOOT, "failed to get ACPI DSM data: %d\n", ret);
 		return ret;
 	}
 
+	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi, ATH12K_ACPI_FUNC_BIT_DISABLE_FLAG)) {
+		ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_DISABLE_FLAG);
+		if (ret) {
+			ath12k_warn(ab, "failed to get ACPI DISABLE FLAG: %d\n", ret);
+			return ret;
+		}
+
+		if (ATH12K_ACPI_CHEK_BIT_VALID(ab->acpi,
+					       ATH12K_ACPI_DSM_DISABLE_11BE_BIT))
+			ab->acpi.acpi_disable_11be = true;
+
+		if (!ATH12K_ACPI_CHEK_BIT_VALID(ab->acpi,
+						ATH12K_ACPI_DSM_DISABLE_RFKILL_BIT))
+			ab->acpi.acpi_disable_rfkill = true;
+	}
+
 	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi, ATH12K_ACPI_FUNC_BIT_TAS_CFG)) {
 		ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_TAS_CFG);
 		if (ret) {
diff --git a/drivers/net/wireless/ath/ath12k/acpi.h b/drivers/net/wireless/ath/ath12k/acpi.h
index 6ccc26250aafb..242ea88fb6c20 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.h
+++ b/drivers/net/wireless/ath/ath12k/acpi.h
@@ -9,6 +9,7 @@
 #include <linux/acpi.h>
 
 #define ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS	0
+#define ATH12K_ACPI_DSM_FUNC_DISABLE_FLAG	2
 #define ATH12K_ACPI_DSM_FUNC_BIOS_SAR		4
 #define ATH12K_ACPI_DSM_FUNC_GEO_OFFSET		5
 #define ATH12K_ACPI_DSM_FUNC_INDEX_CCA		6
@@ -16,6 +17,7 @@
 #define ATH12K_ACPI_DSM_FUNC_TAS_DATA		9
 #define ATH12K_ACPI_DSM_FUNC_INDEX_BAND_EDGE		10
 
+#define ATH12K_ACPI_FUNC_BIT_DISABLE_FLAG		BIT(1)
 #define ATH12K_ACPI_FUNC_BIT_BIOS_SAR			BIT(3)
 #define ATH12K_ACPI_FUNC_BIT_GEO_OFFSET			BIT(4)
 #define ATH12K_ACPI_FUNC_BIT_CCA			BIT(5)
@@ -25,6 +27,7 @@
 
 #define ATH12K_ACPI_NOTIFY_EVENT			0x86
 #define ATH12K_ACPI_FUNC_BIT_VALID(_acdata, _func)	(((_acdata).func_bit) & (_func))
+#define ATH12K_ACPI_CHEK_BIT_VALID(_acdata, _func)	(((_acdata).bit_flag) & (_func))
 
 #define ATH12K_ACPI_TAS_DATA_VERSION		0x1
 #define ATH12K_ACPI_TAS_DATA_ENABLE		0x1
@@ -51,6 +54,9 @@
 #define ATH12K_ACPI_DSM_FUNC_MIN_BITMAP_SIZE	1
 #define ATH12K_ACPI_DSM_FUNC_MAX_BITMAP_SIZE	4
 
+#define ATH12K_ACPI_DSM_DISABLE_11BE_BIT	BIT(0)
+#define ATH12K_ACPI_DSM_DISABLE_RFKILL_BIT	BIT(2)
+
 #define ATH12K_ACPI_DSM_GEO_OFFSET_DATA_SIZE (ATH12K_ACPI_GEO_OFFSET_DATA_OFFSET + \
 					      ATH12K_ACPI_BIOS_SAR_GEO_OFFSET_LEN)
 #define ATH12K_ACPI_DSM_BIOS_SAR_DATA_SIZE (ATH12K_ACPI_POWER_LIMIT_DATA_OFFSET + \
@@ -62,6 +68,8 @@
 
 int ath12k_acpi_start(struct ath12k_base *ab);
 void ath12k_acpi_stop(struct ath12k_base *ab);
+bool ath12k_acpi_get_disable_rfkill(struct ath12k_base *ab);
+bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab);
 
 #else
 
@@ -74,6 +82,16 @@ static inline void ath12k_acpi_stop(struct ath12k_base *ab)
 {
 }
 
+static inline bool ath12k_acpi_get_disable_rfkill(struct ath12k_base *ab)
+{
+	return false;
+}
+
+static inline bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab)
+{
+	return false;
+}
+
 #endif /* CONFIG_ACPI */
 
 #endif /* ATH12K_ACPI_H */
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 60c077b016b40..6d09a51a1571e 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -40,6 +40,9 @@ static int ath12k_core_rfkill_config(struct ath12k_base *ab)
 	if (!(ab->target_caps.sys_cap_info & WMI_SYS_CAP_INFO_RFKILL))
 		return 0;
 
+	if (ath12k_acpi_get_disable_rfkill(ab))
+		return 0;
+
 	for (i = 0; i < ab->num_radios; i++) {
 		ar = ab->pdevs[i].ar;
 
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 983a5d735cebc..fd13c4e53ef20 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1058,6 +1058,9 @@ struct ath12k_base {
 		u32 func_bit;
 		bool acpi_tas_enable;
 		bool acpi_bios_sar_enable;
+		bool acpi_disable_11be;
+		bool acpi_disable_rfkill;
+		u32 bit_flag;
 		u8 tas_cfg[ATH12K_ACPI_DSM_TAS_CFG_SIZE];
 		u8 tas_sar_power_table[ATH12K_ACPI_DSM_TAS_DATA_SIZE];
 		u8 bios_sar_data[ATH12K_ACPI_DSM_BIOS_SAR_DATA_SIZE];
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index aadace85dc117..16e6f2fae943d 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -6751,7 +6751,8 @@ static void ath12k_mac_copy_eht_cap(struct ath12k *ar,
 
 	memset(eht_cap, 0, sizeof(struct ieee80211_sta_eht_cap));
 
-	if (!(test_bit(WMI_TLV_SERVICE_11BE, ar->ab->wmi_ab.svc_map)))
+	if (!(test_bit(WMI_TLV_SERVICE_11BE, ar->ab->wmi_ab.svc_map)) ||
+	    ath12k_acpi_get_disable_11be(ar->ab))
 		return;
 
 	eht_cap->has_eht = true;

From 33fdeb544ea5966abe247b9eb96a8017f7b9b2f2 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:48:09 +0800
Subject: [PATCH 0112/2753] wifi: ath12k: Adjust the timing to access ACPI
 table

Currently, the timing for accessing the ACPI table is inappropriate.

Due to special ACPI requirements, the ACPI table must be obtained before
downloading the board data file. Therefore, adjust the timing for accessing
the ACPI table accordingly.

This patch will not affect QCN9274, because only WCN7850 supports ACPI.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20250113074810.29729-4-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/acpi.c | 98 ++++++++++++++++----------
 drivers/net/wireless/ath/ath12k/acpi.h |  5 ++
 drivers/net/wireless/ath/ath12k/core.c |  5 +-
 drivers/net/wireless/ath/ath12k/core.h |  2 +
 drivers/net/wireless/ath/ath12k/qmi.c  |  7 +-
 5 files changed, 73 insertions(+), 44 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/acpi.c b/drivers/net/wireless/ath/ath12k/acpi.c
index 186ef5d62813c..231b4eb92a5df 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.c
+++ b/drivers/net/wireless/ath/ath12k/acpi.c
@@ -278,15 +278,69 @@ bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab)
 	return ab->acpi.acpi_disable_11be;
 }
 
+void ath12k_acpi_set_dsm_func(struct ath12k_base *ab)
+{
+	int ret;
+	u8 *buf;
+
+	if (!ab->hw_params->acpi_guid)
+		/* not supported with this hardware */
+		return;
+
+	if (ab->acpi.acpi_tas_enable) {
+		ret = ath12k_acpi_set_tas_params(ab);
+		if (ret) {
+			ath12k_warn(ab, "failed to send ACPI TAS parameters: %d\n", ret);
+			return;
+		}
+	}
+
+	if (ab->acpi.acpi_bios_sar_enable) {
+		ret = ath12k_acpi_set_bios_sar_params(ab);
+		if (ret) {
+			ath12k_warn(ab, "failed to send ACPI BIOS SAR: %d\n", ret);
+			return;
+		}
+	}
+
+	if (ab->acpi.acpi_cca_enable) {
+		buf = ab->acpi.cca_data + ATH12K_ACPI_CCA_THR_OFFSET_DATA_OFFSET;
+		ret = ath12k_wmi_set_bios_cmd(ab,
+					      WMI_BIOS_PARAM_CCA_THRESHOLD_TYPE,
+					      buf,
+					      ATH12K_ACPI_CCA_THR_OFFSET_LEN);
+		if (ret) {
+			ath12k_warn(ab, "failed to set ACPI DSM CCA threshold: %d\n",
+				    ret);
+			return;
+		}
+	}
+
+	if (ab->acpi.acpi_band_edge_enable) {
+		ret = ath12k_wmi_set_bios_cmd(ab,
+					      WMI_BIOS_PARAM_TYPE_BANDEDGE,
+					      ab->acpi.band_edge_power,
+					      sizeof(ab->acpi.band_edge_power));
+		if (ret) {
+			ath12k_warn(ab,
+				    "failed to set ACPI DSM band edge channel power: %d\n",
+				    ret);
+			return;
+		}
+	}
+}
+
 int ath12k_acpi_start(struct ath12k_base *ab)
 {
 	acpi_status status;
-	u8 *buf;
 	int ret;
 
 	ab->acpi.acpi_tas_enable = false;
 	ab->acpi.acpi_disable_11be = false;
 	ab->acpi.acpi_disable_rfkill = false;
+	ab->acpi.acpi_bios_sar_enable = false;
+	ab->acpi.acpi_cca_enable = false;
+	ab->acpi.acpi_band_edge_enable = false;
 
 	if (!ab->hw_params->acpi_guid)
 		/* not supported with this hardware */
@@ -357,20 +411,6 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 			ab->acpi.acpi_bios_sar_enable = true;
 	}
 
-	if (ab->acpi.acpi_tas_enable) {
-		ret = ath12k_acpi_set_tas_params(ab);
-		if (ret) {
-			ath12k_warn(ab, "failed to send ACPI parameters: %d\n", ret);
-			return ret;
-		}
-	}
-
-	if (ab->acpi.acpi_bios_sar_enable) {
-		ret = ath12k_acpi_set_bios_sar_params(ab);
-		if (ret)
-			return ret;
-	}
-
 	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi, ATH12K_ACPI_FUNC_BIT_CCA)) {
 		ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_INDEX_CCA);
 		if (ret) {
@@ -381,18 +421,8 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 
 		if (ab->acpi.cca_data[0] == ATH12K_ACPI_CCA_THR_VERSION &&
 		    ab->acpi.cca_data[ATH12K_ACPI_CCA_THR_OFFSET_DATA_OFFSET] ==
-		    ATH12K_ACPI_CCA_THR_ENABLE_FLAG) {
-			buf = ab->acpi.cca_data + ATH12K_ACPI_CCA_THR_OFFSET_DATA_OFFSET;
-			ret = ath12k_wmi_set_bios_cmd(ab,
-						      WMI_BIOS_PARAM_CCA_THRESHOLD_TYPE,
-						      buf,
-						      ATH12K_ACPI_CCA_THR_OFFSET_LEN);
-			if (ret) {
-				ath12k_warn(ab, "failed to set ACPI DSM CCA threshold: %d\n",
-					    ret);
-				return ret;
-			}
-		}
+		    ATH12K_ACPI_CCA_THR_ENABLE_FLAG)
+			ab->acpi.acpi_cca_enable = true;
 	}
 
 	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi,
@@ -405,18 +435,8 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 		}
 
 		if (ab->acpi.band_edge_power[0] == ATH12K_ACPI_BAND_EDGE_VERSION &&
-		    ab->acpi.band_edge_power[1] == ATH12K_ACPI_BAND_EDGE_ENABLE_FLAG) {
-			ret = ath12k_wmi_set_bios_cmd(ab,
-						      WMI_BIOS_PARAM_TYPE_BANDEDGE,
-						      ab->acpi.band_edge_power,
-						      sizeof(ab->acpi.band_edge_power));
-			if (ret) {
-				ath12k_warn(ab,
-					    "failed to set ACPI DSM band edge channel power: %d\n",
-					    ret);
-				return ret;
-			}
-		}
+		    ab->acpi.band_edge_power[1] == ATH12K_ACPI_BAND_EDGE_ENABLE_FLAG)
+			ab->acpi.acpi_band_edge_enable = true;
 	}
 
 	status = acpi_install_notify_handler(ACPI_HANDLE(ab->dev),
diff --git a/drivers/net/wireless/ath/ath12k/acpi.h b/drivers/net/wireless/ath/ath12k/acpi.h
index 242ea88fb6c20..19a1a1118e82b 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.h
+++ b/drivers/net/wireless/ath/ath12k/acpi.h
@@ -70,6 +70,7 @@ int ath12k_acpi_start(struct ath12k_base *ab);
 void ath12k_acpi_stop(struct ath12k_base *ab);
 bool ath12k_acpi_get_disable_rfkill(struct ath12k_base *ab);
 bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab);
+void ath12k_acpi_set_dsm_func(struct ath12k_base *ab);
 
 #else
 
@@ -92,6 +93,10 @@ static inline bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab)
 	return false;
 }
 
+static inline void ath12k_acpi_set_dsm_func(struct ath12k_base *ab)
+{
+}
+
 #endif /* CONFIG_ACPI */
 
 #endif /* ATH12K_ACPI_H */
diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 6d09a51a1571e..323bd5082a7dd 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -849,10 +849,7 @@ static int ath12k_core_start(struct ath12k_base *ab)
 		goto err_reo_cleanup;
 	}
 
-	ret = ath12k_acpi_start(ab);
-	if (ret)
-		/* ACPI is optional so continue in case of an error */
-		ath12k_dbg(ab, ATH12K_DBG_BOOT, "acpi failed: %d\n", ret);
+	ath12k_acpi_set_dsm_func(ab);
 
 	if (!test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags))
 		/* Indicate the core start in the appropriate group */
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index fd13c4e53ef20..79ffaa62bd2fd 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1060,6 +1060,8 @@ struct ath12k_base {
 		bool acpi_bios_sar_enable;
 		bool acpi_disable_11be;
 		bool acpi_disable_rfkill;
+		bool acpi_cca_enable;
+		bool acpi_band_edge_enable;
 		u32 bit_flag;
 		u8 tas_cfg[ATH12K_ACPI_DSM_TAS_CFG_SIZE];
 		u8 tas_sar_power_table[ATH12K_ACPI_DSM_TAS_DATA_SIZE];
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index 5c3563383fabb..c43f773c66ba4 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/elf.h>
@@ -2740,6 +2740,11 @@ int ath12k_qmi_request_target_cap(struct ath12k_base *ab)
 	if (r)
 		ath12k_dbg(ab, ATH12K_DBG_QMI, "SMBIOS bdf variant name not set.\n");
 
+	r = ath12k_acpi_start(ab);
+	if (r)
+		/* ACPI is optional so continue in case of an error */
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "acpi failed: %d\n", r);
+
 out:
 	return ret;
 }

From 0a43c3a520e96d086d0aee492bbcf73ba737a637 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:48:10 +0800
Subject: [PATCH 0113/2753] wifi: ath12k: Add support for reading variant from
 ACPI to download board data file

Currently, ath12k does not support reading variant from ACPI board data
filename extension for downloading board data file.

To address this issue, obtain the string of the ACPI data filename
extension and use it as part of the string to search for the board data
file from board-2.bin.

This patch will not affect QCN9274, because only WCN7850 supports ACPI.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20250113074810.29729-5-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/acpi.c | 45 ++++++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/acpi.h | 12 +++++++
 drivers/net/wireless/ath/ath12k/core.h |  2 ++
 drivers/net/wireless/ath/ath12k/qmi.c  |  4 +++
 4 files changed, 63 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/acpi.c b/drivers/net/wireless/ath/ath12k/acpi.c
index 231b4eb92a5df..d81367ce69294 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.c
+++ b/drivers/net/wireless/ath/ath12k/acpi.c
@@ -37,6 +37,24 @@ static int ath12k_acpi_dsm_get_data(struct ath12k_base *ab, int func)
 			ab->acpi.bit_flag = obj->integer.value;
 			break;
 		}
+	} else if (obj->type == ACPI_TYPE_STRING) {
+		switch (func) {
+		case ATH12K_ACPI_DSM_FUNC_BDF_EXT:
+			if (obj->string.length <= ATH12K_ACPI_BDF_ANCHOR_STRING_LEN ||
+			    obj->string.length > ATH12K_ACPI_BDF_MAX_LEN ||
+			    memcmp(obj->string.pointer, ATH12K_ACPI_BDF_ANCHOR_STRING,
+				   ATH12K_ACPI_BDF_ANCHOR_STRING_LEN)) {
+				ath12k_warn(ab, "invalid ACPI DSM BDF size: %d\n",
+					    obj->string.length);
+				ret = -EINVAL;
+				goto out;
+			}
+
+			memcpy(ab->acpi.bdf_string, obj->string.pointer,
+			       obj->buffer.length);
+
+			break;
+		}
 	} else if (obj->type == ACPI_TYPE_BUFFER) {
 		switch (func) {
 		case ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS:
@@ -341,6 +359,8 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 	ab->acpi.acpi_bios_sar_enable = false;
 	ab->acpi.acpi_cca_enable = false;
 	ab->acpi.acpi_band_edge_enable = false;
+	ab->acpi.acpi_enable_bdf = false;
+	ab->acpi.bdf_string[0] = '\0';
 
 	if (!ab->hw_params->acpi_guid)
 		/* not supported with this hardware */
@@ -368,6 +388,16 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 			ab->acpi.acpi_disable_rfkill = true;
 	}
 
+	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi, ATH12K_ACPI_FUNC_BIT_BDF_EXT)) {
+		ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_BDF_EXT);
+		if (ret || ab->acpi.bdf_string[0] == '\0') {
+			ath12k_warn(ab, "failed to get ACPI BDF EXT: %d\n", ret);
+			return ret;
+		}
+
+		ab->acpi.acpi_enable_bdf = true;
+	}
+
 	if (ATH12K_ACPI_FUNC_BIT_VALID(ab->acpi, ATH12K_ACPI_FUNC_BIT_TAS_CFG)) {
 		ret = ath12k_acpi_dsm_get_data(ab, ATH12K_ACPI_DSM_FUNC_TAS_CFG);
 		if (ret) {
@@ -452,6 +482,21 @@ int ath12k_acpi_start(struct ath12k_base *ab)
 	return 0;
 }
 
+int ath12k_acpi_check_bdf_variant_name(struct ath12k_base *ab)
+{
+	size_t max_len = sizeof(ab->qmi.target.bdf_ext);
+
+	if (!ab->acpi.acpi_enable_bdf)
+		return -ENODATA;
+
+	if (strscpy(ab->qmi.target.bdf_ext, ab->acpi.bdf_string + 4, max_len) < 0)
+		ath12k_dbg(ab, ATH12K_DBG_BOOT,
+			   "acpi bdf variant longer than the buffer (variant: %s)\n",
+			   ab->acpi.bdf_string);
+
+	return 0;
+}
+
 void ath12k_acpi_stop(struct ath12k_base *ab)
 {
 	if (!ab->acpi.started)
diff --git a/drivers/net/wireless/ath/ath12k/acpi.h b/drivers/net/wireless/ath/ath12k/acpi.h
index 19a1a1118e82b..3a26fea6af1a9 100644
--- a/drivers/net/wireless/ath/ath12k/acpi.h
+++ b/drivers/net/wireless/ath/ath12k/acpi.h
@@ -10,6 +10,7 @@
 
 #define ATH12K_ACPI_DSM_FUNC_SUPPORT_FUNCS	0
 #define ATH12K_ACPI_DSM_FUNC_DISABLE_FLAG	2
+#define ATH12K_ACPI_DSM_FUNC_BDF_EXT		3
 #define ATH12K_ACPI_DSM_FUNC_BIOS_SAR		4
 #define ATH12K_ACPI_DSM_FUNC_GEO_OFFSET		5
 #define ATH12K_ACPI_DSM_FUNC_INDEX_CCA		6
@@ -18,6 +19,7 @@
 #define ATH12K_ACPI_DSM_FUNC_INDEX_BAND_EDGE		10
 
 #define ATH12K_ACPI_FUNC_BIT_DISABLE_FLAG		BIT(1)
+#define ATH12K_ACPI_FUNC_BIT_BDF_EXT			BIT(2)
 #define ATH12K_ACPI_FUNC_BIT_BIOS_SAR			BIT(3)
 #define ATH12K_ACPI_FUNC_BIT_GEO_OFFSET			BIT(4)
 #define ATH12K_ACPI_FUNC_BIT_CCA			BIT(5)
@@ -57,6 +59,10 @@
 #define ATH12K_ACPI_DSM_DISABLE_11BE_BIT	BIT(0)
 #define ATH12K_ACPI_DSM_DISABLE_RFKILL_BIT	BIT(2)
 
+#define ATH12K_ACPI_BDF_ANCHOR_STRING_LEN	3
+#define ATH12K_ACPI_BDF_ANCHOR_STRING		"BDF"
+#define ATH12K_ACPI_BDF_MAX_LEN			100
+
 #define ATH12K_ACPI_DSM_GEO_OFFSET_DATA_SIZE (ATH12K_ACPI_GEO_OFFSET_DATA_OFFSET + \
 					      ATH12K_ACPI_BIOS_SAR_GEO_OFFSET_LEN)
 #define ATH12K_ACPI_DSM_BIOS_SAR_DATA_SIZE (ATH12K_ACPI_POWER_LIMIT_DATA_OFFSET + \
@@ -71,6 +77,7 @@ void ath12k_acpi_stop(struct ath12k_base *ab);
 bool ath12k_acpi_get_disable_rfkill(struct ath12k_base *ab);
 bool ath12k_acpi_get_disable_11be(struct ath12k_base *ab);
 void ath12k_acpi_set_dsm_func(struct ath12k_base *ab);
+int ath12k_acpi_check_bdf_variant_name(struct ath12k_base *ab);
 
 #else
 
@@ -97,6 +104,11 @@ static inline void ath12k_acpi_set_dsm_func(struct ath12k_base *ab)
 {
 }
 
+static inline int ath12k_acpi_check_bdf_variant_name(struct ath12k_base *ab)
+{
+	return 0;
+}
+
 #endif /* CONFIG_ACPI */
 
 #endif /* ATH12K_ACPI_H */
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 79ffaa62bd2fd..c34a144048650 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1062,7 +1062,9 @@ struct ath12k_base {
 		bool acpi_disable_rfkill;
 		bool acpi_cca_enable;
 		bool acpi_band_edge_enable;
+		bool acpi_enable_bdf;
 		u32 bit_flag;
+		char bdf_string[ATH12K_ACPI_BDF_MAX_LEN];
 		u8 tas_cfg[ATH12K_ACPI_DSM_TAS_CFG_SIZE];
 		u8 tas_sar_power_table[ATH12K_ACPI_DSM_TAS_DATA_SIZE];
 		u8 bios_sar_data[ATH12K_ACPI_DSM_BIOS_SAR_DATA_SIZE];
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index c43f773c66ba4..ef537c6bf0daa 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2745,6 +2745,10 @@ int ath12k_qmi_request_target_cap(struct ath12k_base *ab)
 		/* ACPI is optional so continue in case of an error */
 		ath12k_dbg(ab, ATH12K_DBG_BOOT, "acpi failed: %d\n", r);
 
+	r = ath12k_acpi_check_bdf_variant_name(ab);
+	if (r)
+		ath12k_dbg(ab, ATH12K_DBG_BOOT, "ACPI bdf variant name not set.\n");
+
 out:
 	return ret;
 }

From b78c02f7c7104f1e77ade12ebde267e6fb388ca9 Mon Sep 17 00:00:00 2001
From: "Yu Zhang(Yuriy)" <quic_yuzha@quicinc.com>
Date: Fri, 24 Jan 2025 14:13:43 +0800
Subject: [PATCH 0114/2753] wifi: ath11k: add support for MU EDCA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The current code does not have the MU EDCA feature, so it cannot support
the use of EDCA by STA in specific UL MU HE TB PPDU transmissions. Refer
to IEEE Std 802.11ax-2021 "9.4.2.251 MU EDCA Parameter Set element",
"26.2.7 EDCA operation using MU EDCA parameters".

Add ath11k_mac_op_conf_tx_mu_edca() to construct the MU EDCA parameters
received from mac80211 into WMI WMM parameters，and send to the firmware
according to the different WMM type flags.

Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-04523-QCAHSPSWPL_V1_V2_SILICONZ_IOE-1

Signed-off-by: Yu Zhang (Yuriy) <quic_yuzha@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124061343.2263467-1-quic_yuzha@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.h |  3 +-
 drivers/net/wireless/ath/ath11k/mac.c  | 53 +++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath11k/wmi.c  | 11 +++---
 drivers/net/wireless/ath/ath11k/wmi.h  | 10 ++++-
 4 files changed, 67 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index a9dc7fe7765a1..92b14fc43cb65 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_CORE_H
@@ -370,6 +370,7 @@ struct ath11k_vif {
 	struct ieee80211_vif *vif;
 
 	struct wmi_wmm_params_all_arg wmm_params;
+	struct wmi_wmm_params_all_arg muedca_params;
 	struct list_head list;
 	union {
 		struct {
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 1556392f7ad48..b76c44cdabbc9 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <net/mac80211.h>
@@ -5204,6 +5204,45 @@ static int ath11k_conf_tx_uapsd(struct ath11k *ar, struct ieee80211_vif *vif,
 	return ret;
 }
 
+static int ath11k_mac_op_conf_tx_mu_edca(struct ieee80211_hw *hw,
+					 struct ieee80211_vif *vif,
+					 unsigned int link_id, u16 ac,
+					 const struct ieee80211_tx_queue_params *params)
+{
+	struct ath11k_vif *arvif = ath11k_vif_to_arvif(vif);
+	struct ath11k *ar = hw->priv;
+	struct wmi_wmm_params_arg *p;
+	int ret;
+
+	switch (ac) {
+	case IEEE80211_AC_VO:
+		p = &arvif->muedca_params.ac_vo;
+		break;
+	case IEEE80211_AC_VI:
+		p = &arvif->muedca_params.ac_vi;
+		break;
+	case IEEE80211_AC_BE:
+		p = &arvif->muedca_params.ac_be;
+		break;
+	case IEEE80211_AC_BK:
+		p = &arvif->muedca_params.ac_bk;
+		break;
+	default:
+		ath11k_warn(ar->ab, "error ac: %d", ac);
+		return -EINVAL;
+	}
+
+	p->cwmin = u8_get_bits(params->mu_edca_param_rec.ecw_min_max, GENMASK(3, 0));
+	p->cwmax = u8_get_bits(params->mu_edca_param_rec.ecw_min_max, GENMASK(7, 4));
+	p->aifs = u8_get_bits(params->mu_edca_param_rec.aifsn, GENMASK(3, 0));
+	p->txop = params->mu_edca_param_rec.mu_edca_timer;
+
+	ret = ath11k_wmi_send_wmm_update_cmd_tlv(ar, arvif->vdev_id,
+						 &arvif->muedca_params,
+						 WMI_WMM_PARAM_TYPE_11AX_MU_EDCA);
+	return ret;
+}
+
 static int ath11k_mac_op_conf_tx(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
 				 unsigned int link_id, u16 ac,
@@ -5242,12 +5281,22 @@ static int ath11k_mac_op_conf_tx(struct ieee80211_hw *hw,
 	p->txop = params->txop;
 
 	ret = ath11k_wmi_send_wmm_update_cmd_tlv(ar, arvif->vdev_id,
-						 &arvif->wmm_params);
+						 &arvif->wmm_params,
+						 WMI_WMM_PARAM_TYPE_LEGACY);
 	if (ret) {
 		ath11k_warn(ar->ab, "failed to set wmm params: %d\n", ret);
 		goto exit;
 	}
 
+	if (params->mu_edca) {
+		ret = ath11k_mac_op_conf_tx_mu_edca(hw, vif, link_id, ac,
+						    params);
+		if (ret) {
+			ath11k_warn(ar->ab, "failed to set mu_edca params: %d\n", ret);
+			goto exit;
+		}
+	}
+
 	ret = ath11k_conf_tx_uapsd(ar, vif, ac, params->uapsd);
 
 	if (ret)
diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
index 87abfa5475295..d7f852bebf4aa 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.c
+++ b/drivers/net/wireless/ath/ath11k/wmi.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/skbuff.h>
 #include <linux/ctype.h>
@@ -2662,7 +2662,8 @@ int ath11k_wmi_send_scan_chan_list_cmd(struct ath11k *ar,
 }
 
 int ath11k_wmi_send_wmm_update_cmd_tlv(struct ath11k *ar, u32 vdev_id,
-				       struct wmi_wmm_params_all_arg *param)
+				       struct wmi_wmm_params_all_arg *param,
+				       enum wmi_wmm_params_type wmm_param_type)
 {
 	struct ath11k_pdev_wmi *wmi = ar->wmi;
 	struct wmi_vdev_set_wmm_params_cmd *cmd;
@@ -2681,7 +2682,7 @@ int ath11k_wmi_send_wmm_update_cmd_tlv(struct ath11k *ar, u32 vdev_id,
 			  FIELD_PREP(WMI_TLV_LEN, sizeof(*cmd) - TLV_HDR_SIZE);
 
 	cmd->vdev_id = vdev_id;
-	cmd->wmm_param_type = 0;
+	cmd->wmm_param_type = wmm_param_type;
 
 	for (ac = 0; ac < WME_NUM_AC; ac++) {
 		switch (ac) {
@@ -2714,8 +2715,8 @@ int ath11k_wmi_send_wmm_update_cmd_tlv(struct ath11k *ar, u32 vdev_id,
 		wmm_param->no_ack = wmi_wmm_arg->no_ack;
 
 		ath11k_dbg(ar->ab, ATH11K_DBG_WMI,
-			   "wmm set ac %d aifs %d cwmin %d cwmax %d txop %d acm %d no_ack %d\n",
-			   ac, wmm_param->aifs, wmm_param->cwmin,
+			   "wmm set type %d ac %d aifs %d cwmin %d cwmax %d txop %d acm %d no_ack %d\n",
+			   wmm_param_type, ac, wmm_param->aifs, wmm_param->cwmin,
 			   wmm_param->cwmax, wmm_param->txoplimit,
 			   wmm_param->acm, wmm_param->no_ack);
 	}
diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h
index 8982b909c821e..508bd496488a6 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.h
+++ b/drivers/net/wireless/ath/ath11k/wmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_WMI_H
@@ -6346,6 +6346,11 @@ enum wmi_sta_keepalive_method {
 #define WMI_STA_KEEPALIVE_INTERVAL_DEFAULT	30
 #define WMI_STA_KEEPALIVE_INTERVAL_DISABLE	0
 
+enum wmi_wmm_params_type {
+	WMI_WMM_PARAM_TYPE_LEGACY = 0,
+	WMI_WMM_PARAM_TYPE_11AX_MU_EDCA = 1,
+};
+
 const void **ath11k_wmi_tlv_parse_alloc(struct ath11k_base *ab,
 					struct sk_buff *skb, gfp_t gfp);
 int ath11k_wmi_cmd_send(struct ath11k_pdev_wmi *wmi, struct sk_buff *skb,
@@ -6402,7 +6407,8 @@ int ath11k_wmi_send_scan_start_cmd(struct ath11k *ar,
 int ath11k_wmi_send_scan_stop_cmd(struct ath11k *ar,
 				  struct scan_cancel_param *param);
 int ath11k_wmi_send_wmm_update_cmd_tlv(struct ath11k *ar, u32 vdev_id,
-				       struct wmi_wmm_params_all_arg *param);
+				       struct wmi_wmm_params_all_arg *param,
+				       enum wmi_wmm_params_type wmm_param_type);
 int ath11k_wmi_pdev_suspend(struct ath11k *ar, u32 suspend_opt,
 			    u32 pdev_id);
 int ath11k_wmi_pdev_resume(struct ath11k *ar, u32 pdev_id);

From 9d13950acb2a51342c93c69f1a5bf285adb90d88 Mon Sep 17 00:00:00 2001
From: "Yu Zhang(Yuriy)" <quic_yuzha@quicinc.com>
Date: Fri, 24 Jan 2025 15:59:53 +0800
Subject: [PATCH 0115/2753] wifi: ath11k: fix wrong overriding for VHT
 Beamformee STS Capability
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Current code in ath11k_mac_set_txbf_conf overrides nsts, which is
incorrect as it confuses nss and nsts. nss is Number of Spatial
Streams，nsts is Number of Space-Time Streams.

As mentioned in Fixes: 55b5ee3357d7, the nss used when acting as a
beamformee in VHT mode should be reported by the firmware and should not
be greater than the number of receiving antennas - 1. The num_rx_chains
related nss rather than nsts.

If STBC is enabled, nsts is greater than nss. About nss are mapped to
nsts, refer to IEEE Std 802.11-2020: 19.3.11.9.2 Space-time block coding
(STBC), Table 19-18—Constellation mapper output to spatial mapper input
for STBC.

Remove wrong overriding for nsts of VHT Beamformee STS Capability,
acting DL MU-MIMO in VHT mode is working properly.

Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-04479-QCAHSPSWPL_V1_V2_SILICONZ_IOE-1

Fixes: 55b5ee3357d7 ("wifi: ath11k: fix number of VHT beamformee spatial streams")
Signed-off-by: Yu Zhang (Yuriy) <quic_yuzha@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250124075953.2282354-1-quic_yuzha@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index b76c44cdabbc9..586898e5318fa 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -5385,8 +5385,6 @@ static int ath11k_mac_set_txbf_conf(struct ath11k_vif *arvif)
 	if (vht_cap & (IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE)) {
 		nsts = vht_cap & IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK;
 		nsts >>= IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT;
-		if (nsts > (ar->num_rx_chains - 1))
-			nsts = ar->num_rx_chains - 1;
 		value |= SM(nsts, WMI_TXBF_STS_CAP_OFFSET);
 	}
 
@@ -5470,9 +5468,6 @@ static void ath11k_set_vht_txbf_cap(struct ath11k *ar, u32 *vht_cap)
 
 	/* Enable Beamformee STS Field only if SU BF is enabled */
 	if (subfee) {
-		if (nsts > (ar->num_rx_chains - 1))
-			nsts = ar->num_rx_chains - 1;
-
 		nsts <<= IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT;
 		nsts &=  IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK;
 		*vht_cap |= nsts;

From ba42b22aa336c3ea0bd6f9c606f70a35a278bd61 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:17:56 +0800
Subject: [PATCH 0116/2753] wifi: ath12k: Dump PDEV transmit rate HTT stats

Support to dump PDEV transmit rate stats through HTT debugfs stats type 9.

Sample output:
-------------------------
echo 9 > /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats
HTT_TX_PDEV_RATE_STATS_TLV:
mac_id = 0
tx_ldpc = 1088
ac_mu_mimo_tx_ldpc = 0
ax_mu_mimo_tx_ldpc = 0
ofdma_tx_ldpc = 0
rts_cnt = 941
rts_success = 180
ack_rssi = 4294967168
Legacy CCK Rates: 1 Mbps: 830, 2 Mbps: 0, 5.5 Mbps: 0, 12 Mbps: 0
Legacy OFDM Rates: 6 Mbps: 942, 9 Mbps: 0, 12 Mbps: 0, 18 Mbps: 0
                   24 Mbps: 0, 36 Mbps: 0, 48 Mbps: 0, 54 Mbps: 0
HE LTF: 1x: 0, 2x: 957, 4x: 132
tx_mcs =  0:342, 1:260, 2:171, 3:148, 4:31, 5:34, 6:93, 7:10, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
ax_mu_mimo_tx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ofdma_tx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_nss = 1:754, 2:335, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
ac_mu_mimo_tx_nss = 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
ax_mu_mimo_tx_nss = 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
ofdma_tx_nss = 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
tx_bw =  0:1089, 1:0, 2:0, 3:0, 4:0
tx_stbc =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_gi[0] = 0:210, 1:260, 2:171, 3:148, 4:31, 5:34, 6:93, 7:10, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_gi[1] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_gi[2] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_gi[3] = 0:132, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ac_mu_mimo_tx_gi[0] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ac_mu_mimo_tx_gi[1] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ac_mu_mimo_tx_gi[2] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ac_mu_mimo_tx_gi[3] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ax_mu_mimo_tx_gi[0] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ax_mu_mimo_tx_gi[1] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ax_mu_mimo_tx_gi[2] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ax_mu_mimo_tx_gi[3] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ofdma_tx_gi[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ofdma_tx_gi[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ofdma_tx_gi[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ofdma_tx_gi[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
tx_su_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
tx_mu_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ac_mu_mimo_tx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ac_mu_mimo_tx_bw =  0:0, 1:0, 2:0, 3:0
ax_mu_mimo_tx_bw =  0:0, 1:0, 2:0, 3:0
ofdma_tx_bw =  0:0, 1:0, 2:0, 3:0
tx_pream =  0:942, 1:830, 2:0, 3:0, 4:1850, 5:0, 6:0
tx_dcm =  0:131, 1:0, 2:0, 3:0, 4:0

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250113071758.19589-2-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 206 +++++++++++++++++-
 .../wireless/ath/ath12k/debugfs_htt_stats.h   |  70 +++++-
 2 files changed, 274 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 41e4ef2ef3af6..29a79c800d546 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
@@ -3812,6 +3812,207 @@ ath12k_htt_print_pdev_mbssid_ctrl_frame_stats_tlv(const void *tag_buf, u16 tag_l
 	stats_req->buf_len = len;
 }
 
+static inline void
+ath12k_htt_print_tx_pdev_rate_stats_tlv(const void *tag_buf, u16 tag_len,
+					struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_pdev_rate_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u8 i, j;
+	u32 mac_id_word;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	mac_id_word = le32_to_cpu(htt_stats_buf->mac_id_word);
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_TX_PDEV_RATE_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n",
+			 u32_get_bits(mac_id_word, ATH12K_HTT_STATS_MAC_ID));
+	len += scnprintf(buf + len, buf_len - len, "tx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "ac_mu_mimo_tx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ac_mu_mimo_tx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "ax_mu_mimo_tx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ax_mu_mimo_tx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "ofdma_tx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ofdma_tx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "rts_cnt = %u\n",
+			 le32_to_cpu(htt_stats_buf->rts_cnt));
+	len += scnprintf(buf + len, buf_len - len, "rts_success = %u\n",
+			 le32_to_cpu(htt_stats_buf->rts_success));
+	len += scnprintf(buf + len, buf_len - len, "ack_rssi = %u\n",
+			 le32_to_cpu(htt_stats_buf->ack_rssi));
+	len += scnprintf(buf + len, buf_len - len,
+			 "Legacy CCK Rates: 1 Mbps: %u, 2 Mbps: %u, 5.5 Mbps: %u, 12 Mbps: %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_legacy_cck_rate[0]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_cck_rate[1]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_cck_rate[2]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_cck_rate[3]));
+	len += scnprintf(buf + len, buf_len - len,
+			 "Legacy OFDM Rates: 6 Mbps: %u, 9 Mbps: %u, 12 Mbps: %u, 18 Mbps: %u\n"
+			 "                   24 Mbps: %u, 36 Mbps: %u, 48 Mbps: %u, 54 Mbps: %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[0]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[1]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[2]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[3]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[4]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[5]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[6]),
+			 le32_to_cpu(htt_stats_buf->tx_legacy_ofdm_rate[7]));
+	len += scnprintf(buf + len, buf_len - len, "HE LTF: 1x: %u, 2x: %u, 4x: %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_he_ltf[1]),
+			 le32_to_cpu(htt_stats_buf->tx_he_ltf[2]),
+			 le32_to_cpu(htt_stats_buf->tx_he_ltf[3]));
+
+	len += print_array_to_buf(buf, len, "tx_mcs", htt_stats_buf->tx_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, NULL);
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->tx_mcs_ext[j]));
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS +
+				 ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->tx_mcs_ext_2[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += print_array_to_buf(buf, len, "ax_mu_mimo_tx_mcs",
+				  htt_stats_buf->ax_mu_mimo_tx_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, NULL);
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->ax_mu_mimo_tx_mcs_ext[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += print_array_to_buf(buf, len, "ofdma_tx_mcs",
+				  htt_stats_buf->ofdma_tx_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, NULL);
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->ofdma_tx_mcs_ext[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += scnprintf(buf + len, buf_len - len, "tx_nss =");
+	for (j = 1; j <= ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %u:%u,",
+				 j, le32_to_cpu(htt_stats_buf->tx_nss[j - 1]));
+	len--;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += scnprintf(buf + len, buf_len - len, "ac_mu_mimo_tx_nss =");
+	for (j = 1; j <= ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %u:%u,",
+				 j, le32_to_cpu(htt_stats_buf->ac_mu_mimo_tx_nss[j - 1]));
+	len--;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += scnprintf(buf + len, buf_len - len, "ax_mu_mimo_tx_nss =");
+	for (j = 1; j <= ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %u:%u,",
+				 j, le32_to_cpu(htt_stats_buf->ax_mu_mimo_tx_nss[j - 1]));
+	len--;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += scnprintf(buf + len, buf_len - len, "ofdma_tx_nss =");
+	for (j = 1; j <= ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %u:%u,",
+				 j, le32_to_cpu(htt_stats_buf->ofdma_tx_nss[j - 1]));
+	len--;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += print_array_to_buf(buf, len, "tx_bw", htt_stats_buf->tx_bw,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS, NULL);
+	len += scnprintf(buf + len, buf_len - len, ", %u:%u\n",
+			 ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS,
+			 le32_to_cpu(htt_stats_buf->tx_bw_320mhz));
+
+	len += print_array_to_buf(buf, len, "tx_stbc",
+				  htt_stats_buf->tx_stbc,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, NULL);
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->tx_stbc_ext[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, (buf_len - len),
+				 "tx_gi[%u] =", j);
+		len += print_array_to_buf(buf, len, NULL, htt_stats_buf->tx_gi[j],
+					  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  NULL);
+		for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; i++)
+			len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+					 i + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					 le32_to_cpu(htt_stats_buf->tx_gi_ext[j][i]));
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, (buf_len - len),
+				 "ac_mu_mimo_tx_gi[%u] =", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->ac_mu_mimo_tx_gi[j],
+					  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, (buf_len - len),
+				 "ax_mu_mimo_tx_gi[%u] =", j);
+		len += print_array_to_buf(buf, len, NULL, htt_stats_buf->ax_mimo_tx_gi[j],
+					  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  NULL);
+		for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; i++)
+			len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+					 i + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					 le32_to_cpu(htt_stats_buf->ax_tx_gi_ext[j][i]));
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, (buf_len - len),
+				 "ofdma_tx_gi[%u] = ", j);
+		len += print_array_to_buf(buf, len, NULL, htt_stats_buf->ofdma_tx_gi[j],
+					  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  NULL);
+		for (i = 0; i < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; i++)
+			len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+					 i + ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS,
+					 le32_to_cpu(htt_stats_buf->ofd_tx_gi_ext[j][i]));
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	len += print_array_to_buf(buf, len, "tx_su_mcs", htt_stats_buf->tx_su_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "tx_mu_mcs", htt_stats_buf->tx_mu_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "ac_mu_mimo_tx_mcs",
+				  htt_stats_buf->ac_mu_mimo_tx_mcs,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "ac_mu_mimo_tx_bw",
+				  htt_stats_buf->ac_mu_mimo_tx_bw,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "ax_mu_mimo_tx_bw",
+				  htt_stats_buf->ax_mu_mimo_tx_bw,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "ofdma_tx_bw",
+				  htt_stats_buf->ofdma_tx_bw,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "tx_pream", htt_stats_buf->tx_pream,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_PREAMBLE_TYPES, "\n");
+	len += print_array_to_buf(buf, len, "tx_dcm", htt_stats_buf->tx_dcm,
+				  ATH12K_HTT_TX_PDEV_STATS_NUM_DCM_COUNTERS, "\n");
+
+	stats_req->buf_len = len;
+}
+
 static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 					  u16 tag, u16 len, const void *tag_buf,
 					  void *user_data)
@@ -4047,6 +4248,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 		ath12k_htt_print_pdev_mbssid_ctrl_frame_stats_tlv(tag_buf, len,
 								  stats_req);
 		break;
+	case HTT_STATS_TX_PDEV_RATE_STATS_TAG:
+		ath12k_htt_print_tx_pdev_rate_stats_tlv(tag_buf, len, stats_req);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 4b59976fbc350..510d347242d26 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef DEBUG_HTT_STATS_H
@@ -129,6 +129,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_ERROR		= 5,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TQM		= 6,
 	ATH12K_DBG_HTT_EXT_STATS_TX_DE_INFO		= 8,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE		= 9,
 	ATH12K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO	= 12,
 	ATH12K_DBG_HTT_EXT_STATS_SRNG_INFO		= 15,
 	ATH12K_DBG_HTT_EXT_STATS_SFM_INFO		= 16,
@@ -173,6 +174,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_TX_PDEV_MU_MIMO_STATS_TAG		= 25,
 	HTT_STATS_SFM_CMN_TAG				= 26,
 	HTT_STATS_SRING_STATS_TAG			= 27,
+	HTT_STATS_TX_PDEV_RATE_STATS_TAG		= 34,
 	HTT_STATS_TX_PDEV_SCHEDULER_TXQ_STATS_TAG	= 36,
 	HTT_STATS_TX_SCHED_CMN_TAG			= 37,
 	HTT_STATS_SCHED_TXQ_CMD_POSTED_TAG		= 39,
@@ -387,6 +389,72 @@ struct ath12k_htt_tx_pdev_mu_ppdu_dist_stats_tlv {
 	__le32 num_ppdu_posted_per_burst[ATH12K_HTT_STATS_MU_PPDU_PER_BURST_WORDS];
 } __packed;
 
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS        12
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS          4
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_DCM_COUNTERS         5
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS          4
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS      8
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_PREAMBLE_TYPES       7
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_CCK_STATS     4
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS    8
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_LTF                  4
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS   2
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS  2
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_11AX_TRIGGER_TYPES   6
+
+struct ath12k_htt_tx_pdev_rate_stats_tlv {
+	__le32 mac_id_word;
+	__le32 tx_ldpc;
+	__le32 rts_cnt;
+	__le32 ack_rssi;
+	__le32 tx_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 tx_su_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 tx_mu_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 tx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 tx_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 tx_stbc[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 tx_pream[ATH12K_HTT_TX_PDEV_STATS_NUM_PREAMBLE_TYPES];
+	__le32 tx_gi[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+		[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 tx_dcm[ATH12K_HTT_TX_PDEV_STATS_NUM_DCM_COUNTERS];
+	__le32 rts_success;
+	__le32 tx_legacy_cck_rate[ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_CCK_STATS];
+	__le32 tx_legacy_ofdm_rate[ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS];
+	__le32 ac_mu_mimo_tx_ldpc;
+	__le32 ax_mu_mimo_tx_ldpc;
+	__le32 ofdma_tx_ldpc;
+	__le32 tx_he_ltf[ATH12K_HTT_TX_PDEV_STATS_NUM_LTF];
+	__le32 ac_mu_mimo_tx_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ax_mu_mimo_tx_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ofdma_tx_mcs[ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ac_mu_mimo_tx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 ax_mu_mimo_tx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 ofdma_tx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 ac_mu_mimo_tx_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 ax_mu_mimo_tx_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 ofdma_tx_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 ac_mu_mimo_tx_gi[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+			    [ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ax_mimo_tx_gi[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+			    [ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ofdma_tx_gi[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+		       [ATH12K_HTT_TX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 trigger_type_11ax[ATH12K_HTT_TX_PDEV_STATS_NUM_11AX_TRIGGER_TYPES];
+	__le32 tx_11ax_su_ext;
+	__le32 tx_mcs_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 tx_stbc_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 tx_gi_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+		     [ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 ax_mu_mimo_tx_mcs_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 ofdma_tx_mcs_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 ax_tx_gi_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+				[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 ofd_tx_gi_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+			   [ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+	__le32 tx_mcs_ext_2[ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS];
+	__le32 tx_bw_320mhz;
+};
+
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_MAC_ID	GENMASK(7, 0)
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_ID	GENMASK(15, 8)
 

From a24cd7583003824f8bd0034c02987e5da26088f6 Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:17:57 +0800
Subject: [PATCH 0117/2753] wifi: ath12k: Dump PDEV receive rate HTT stats

Support to dump PDEV receive rate stats through HTT debugfs stats type 10.

Sample output:
-----------------
echo 10 > /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats
HTT_RX_PDEV_RATE_STATS_TLV:
mac_id = 0
nsts = 0
rx_ldpc = 96
rts_cnt = 0
rssi_mgmt = 4294967240
rssi_data = 4294967250
rssi_comb = 4294967239
rssi_in_dbm = -46
rx_evm_nss_count = 0
rx_evm_pilot_count = 0
rx_11ax_su_ext = 0
rx_11ac_mumimo = 0
rx_11ax_mumimo = 0
rx_11ax_ofdma = 0
txbf = 0
rx_su_ndpa = 0
rx_mu_ndpa = 0
rx_br_poll = 0
rx_active_dur_us_low = 1000106
rx_active_dur_us_high = 0
rx_11ax_ul_ofdma = 0
ul_ofdma_rx_stbc = 0
ul_ofdma_rx_ldpc = 0
per_chain_rssi_pkt_type = 0x88
rx_nss =  0:40, 1:56, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_dcm =  0:0, 1:0, 2:0, 3:0, 4:0
rx_stbc =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_bw =  0:1175, 1:0, 2:0, 3:0
rx_pream =  0:435, 1:644, 2:0, 3:0, 4:96, 5:0, 6:0
rx_11ax_su_txbf_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_11ax_mu_txbf_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_legacy_cck_rate =  0:641, 1:0, 2:3, 3:0
rx_legacy_ofdm_rate =  0:267, 1:0, 2:72, 3:0, 4:96, 5:0, 6:0, 7:0
ul_ofdma_rx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_nss =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
ul_ofdma_rx_bw =  0:0, 1:0, 2:0, 3:0
rx_ulofdma_non_data_ppdu =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulofdma_data_ppdu =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulofdma_mpdu_ok =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulofdma_mpdu_fail =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulofdma_non_data_nusers =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulofdma_data_nusers =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_11ax_dl_ofdma_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_11ax_dl_ofdma_ru =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0
rx_ulmumimo_non_data_ppdu =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulmumimo_data_ppdu =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulmumimo_mpdu_ok =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulmumimo_mpdu_fail =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_mcs =  0:0, 1:0, 2:0, 3:0, 4:28, 5:8, 6:37, 7:21, 8:2, 9:0, 10:0, 11:0, 12:0, 13:0
pilot_evm_db[0] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[1] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[2] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[3] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[4] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[5] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[6] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db[7] = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
pilot_evm_db_mean = 0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rssi_chain_in_db[0] =  0: 196, 1: 29, 2: 29, 3: 29
rssi_chain_in_db[1] =  0: 196, 1: 29, 2: 29, 3: 29
rssi_chain_in_db[2] =  0: 128, 1: 128, 2: 128, 3: 128
rssi_chain_in_db[3] =  0: 128, 1: 128, 2: 128, 3: 128
rssi_chain_in_db[4] =  0: 128, 1: 128, 2: 128, 3: 128
rssi_chain_in_db[5] =  0: 128, 1: 128, 2: 128, 3: 128
rssi_chain_in_db[6] =  0: 128, 1: 128, 2: 128, 3: 128
rssi_chain_in_db[7] =  0: 128, 1: 128, 2: 128, 3: 128
rx_gi[0] =  0:0, 1:0, 2:0, 3:0, 4:28, 5:8, 6:37, 7:21, 8:2, 9:0, 10:0, 11:0
rx_gi[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_gi[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_gi[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
rx_ul_fd_rssi: nss[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[4] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[5] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[6] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_fd_rssi: nss[7] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_per_chain_rssi_in_dbm[0] = 0:-60, 1:29, 2:29, 3:29
rx_per_chain_rssi_in_dbm[1] = 0:-60, 1:29, 2:29, 3:29
rx_per_chain_rssi_in_dbm[2] = 0:-128, 1:-128, 2:-128, 3:-128
rx_per_chain_rssi_in_dbm[3] = 0:-128, 1:-128, 2:-128, 3:-128
rx_per_chain_rssi_in_dbm[4] = 0:-128, 1:-128, 2:-128, 3:-128
rx_per_chain_rssi_in_dbm[5] = 0:-128, 1:-128, 2:-128, 3:-128
rx_per_chain_rssi_in_dbm[6] = 0:-128, 1:-128, 2:-128, 3:-128
rx_per_chain_rssi_in_dbm[7] = 0:-128, 1:-128, 2:-128, 3:-128

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250113071758.19589-3-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 222 ++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   |  82 +++++++
 2 files changed, 304 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 29a79c800d546..c3a53d84f8b18 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -4013,6 +4013,225 @@ ath12k_htt_print_tx_pdev_rate_stats_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static inline void
+ath12k_htt_print_rx_pdev_rate_stats_tlv(const void *tag_buf, u16 tag_len,
+					struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_pdev_rate_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u8 i, j;
+	u32 mac_id_word;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	mac_id_word = le32_to_cpu(htt_stats_buf->mac_id_word);
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_RX_PDEV_RATE_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n",
+			 u32_get_bits(mac_id_word, ATH12K_HTT_STATS_MAC_ID));
+	len += scnprintf(buf + len, buf_len - len, "nsts = %u\n",
+			 le32_to_cpu(htt_stats_buf->nsts));
+	len += scnprintf(buf + len, buf_len - len, "rx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "rts_cnt = %u\n",
+			 le32_to_cpu(htt_stats_buf->rts_cnt));
+	len += scnprintf(buf + len, buf_len - len, "rssi_mgmt = %u\n",
+			 le32_to_cpu(htt_stats_buf->rssi_mgmt));
+	len += scnprintf(buf + len, buf_len - len, "rssi_data = %u\n",
+			 le32_to_cpu(htt_stats_buf->rssi_data));
+	len += scnprintf(buf + len, buf_len - len, "rssi_comb = %u\n",
+			 le32_to_cpu(htt_stats_buf->rssi_comb));
+	len += scnprintf(buf + len, buf_len - len, "rssi_in_dbm = %d\n",
+			 le32_to_cpu(htt_stats_buf->rssi_in_dbm));
+	len += scnprintf(buf + len, buf_len - len, "rx_evm_nss_count = %u\n",
+			 le32_to_cpu(htt_stats_buf->nss_count));
+	len += scnprintf(buf + len, buf_len - len, "rx_evm_pilot_count = %u\n",
+			 le32_to_cpu(htt_stats_buf->pilot_count));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_su_ext = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_su_ext));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ac_mumimo = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ac_mumimo));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_mumimo = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_mumimo));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_ofdma = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_ofdma));
+	len += scnprintf(buf + len, buf_len - len, "txbf = %u\n",
+			 le32_to_cpu(htt_stats_buf->txbf));
+	len += scnprintf(buf + len, buf_len - len, "rx_su_ndpa = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_su_ndpa));
+	len += scnprintf(buf + len, buf_len - len, "rx_mu_ndpa = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_mu_ndpa));
+	len += scnprintf(buf + len, buf_len - len, "rx_br_poll = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_br_poll));
+	len += scnprintf(buf + len, buf_len - len, "rx_active_dur_us_low = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_active_dur_us_low));
+	len += scnprintf(buf + len, buf_len - len, "rx_active_dur_us_high = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_active_dur_us_high));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_ul_ofdma = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_ul_ofdma));
+	len += scnprintf(buf + len, buf_len - len, "ul_ofdma_rx_stbc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_ofdma_rx_stbc));
+	len += scnprintf(buf + len, buf_len - len, "ul_ofdma_rx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_ofdma_rx_ldpc));
+	len += scnprintf(buf + len, buf_len - len, "per_chain_rssi_pkt_type = %#x\n",
+			 le32_to_cpu(htt_stats_buf->per_chain_rssi_pkt_type));
+
+	len += print_array_to_buf(buf, len, "rx_nss", htt_stats_buf->rx_nss,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS, "\n");
+	len += print_array_to_buf(buf, len, "rx_dcm", htt_stats_buf->rx_dcm,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_DCM_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_stbc", htt_stats_buf->rx_stbc,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_bw", htt_stats_buf->rx_bw,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_pream", htt_stats_buf->rx_pream,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_PREAMBLE_TYPES, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_su_txbf_mcs",
+				  htt_stats_buf->rx_11ax_su_txbf_mcs,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_mu_txbf_mcs",
+				  htt_stats_buf->rx_11ax_mu_txbf_mcs,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_legacy_cck_rate",
+				  htt_stats_buf->rx_legacy_cck_rate,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_CCK_STATS, "\n");
+	len += print_array_to_buf(buf, len, "rx_legacy_ofdm_rate",
+				  htt_stats_buf->rx_legacy_ofdm_rate,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_OFDM_STATS, "\n");
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_mcs",
+				  htt_stats_buf->ul_ofdma_rx_mcs,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_nss",
+				  htt_stats_buf->ul_ofdma_rx_nss,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS, "\n");
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_bw",
+				  htt_stats_buf->ul_ofdma_rx_bw,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_non_data_ppdu",
+				  htt_stats_buf->rx_ulofdma_non_data_ppdu,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_data_ppdu",
+				  htt_stats_buf->rx_ulofdma_data_ppdu,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_mpdu_ok",
+				  htt_stats_buf->rx_ulofdma_mpdu_ok,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_mpdu_fail",
+				  htt_stats_buf->rx_ulofdma_mpdu_fail,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_non_data_nusers",
+				  htt_stats_buf->rx_ulofdma_non_data_nusers,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulofdma_data_nusers",
+				  htt_stats_buf->rx_ulofdma_data_nusers,
+				  ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_dl_ofdma_mcs",
+				  htt_stats_buf->rx_11ax_dl_ofdma_mcs,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_dl_ofdma_ru",
+				  htt_stats_buf->rx_11ax_dl_ofdma_ru,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_RU_SIZE_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulmumimo_non_data_ppdu",
+				  htt_stats_buf->rx_ulmumimo_non_data_ppdu,
+				  ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulmumimo_data_ppdu",
+				  htt_stats_buf->rx_ulmumimo_data_ppdu,
+				  ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulmumimo_mpdu_ok",
+				  htt_stats_buf->rx_ulmumimo_mpdu_ok,
+				  ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER, "\n");
+	len += print_array_to_buf(buf, len, "rx_ulmumimo_mpdu_fail",
+				  htt_stats_buf->rx_ulmumimo_mpdu_fail,
+				  ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER, "\n");
+
+	len += print_array_to_buf(buf, len, "rx_mcs",
+				  htt_stats_buf->rx_mcs,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS, NULL);
+	for (j = 0; j < ATH12K_HTT_TX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS,
+				 le32_to_cpu(htt_stats_buf->rx_mcs_ext[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "pilot_evm_db[%u] =", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->rx_pil_evm_db[j],
+					  ATH12K_HTT_RX_PDEV_STATS_RXEVM_MAX_PILOTS_NSS,
+					  "\n");
+	}
+
+	len += scnprintf(buf + len, buf_len - len, "pilot_evm_db_mean =");
+	for (i = 0; i < ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS; i++)
+		len += scnprintf(buf + len,
+				 buf_len - len,
+				 " %u:%d,", i,
+				 le32_to_cpu(htt_stats_buf->rx_pilot_evm_db_mean[i]));
+	len--;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rssi_chain_in_db[%u] = ", j);
+		for (i = 0; i < ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS; i++)
+			len += scnprintf(buf + len,
+					 buf_len - len,
+					 " %u: %d,", i,
+					 htt_stats_buf->rssi_chain_in_db[j][i]);
+		len--;
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_gi[%u] = ", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->rx_gi[j],
+					  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "ul_ofdma_rx_gi[%u] = ", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->ul_ofdma_rx_gi[j],
+					  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS,
+					  "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_ul_fd_rssi: nss[%u] = ", j);
+		for (i = 0; i < ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER; i++)
+			len += scnprintf(buf + len,
+					 buf_len - len,
+					 " %u:%d,",
+					 i, htt_stats_buf->rx_ul_fd_rssi[j][i]);
+		len--;
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_per_chain_rssi_in_dbm[%u] =", j);
+		for (i = 0; i < ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS; i++)
+			len += scnprintf(buf + len,
+					 buf_len - len,
+					 " %u:%d,",
+					 i,
+					 htt_stats_buf->rx_per_chain_rssi_in_dbm[j][i]);
+		len--;
+		len += scnprintf(buf + len, buf_len - len, "\n");
+	}
+
+	stats_req->buf_len = len;
+}
+
 static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 					  u16 tag, u16 len, const void *tag_buf,
 					  void *user_data)
@@ -4251,6 +4470,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_TX_PDEV_RATE_STATS_TAG:
 		ath12k_htt_print_tx_pdev_rate_stats_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_RX_PDEV_RATE_STATS_TAG:
+		ath12k_htt_print_rx_pdev_rate_stats_tlv(tag_buf, len, stats_req);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 510d347242d26..13bafa793764d 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -130,6 +130,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TQM		= 6,
 	ATH12K_DBG_HTT_EXT_STATS_TX_DE_INFO		= 8,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE		= 9,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE		= 10,
 	ATH12K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO	= 12,
 	ATH12K_DBG_HTT_EXT_STATS_SRNG_INFO		= 15,
 	ATH12K_DBG_HTT_EXT_STATS_SFM_INFO		= 16,
@@ -175,6 +176,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_SFM_CMN_TAG				= 26,
 	HTT_STATS_SRING_STATS_TAG			= 27,
 	HTT_STATS_TX_PDEV_RATE_STATS_TAG		= 34,
+	HTT_STATS_RX_PDEV_RATE_STATS_TAG		= 35,
 	HTT_STATS_TX_PDEV_SCHEDULER_TXQ_STATS_TAG	= 36,
 	HTT_STATS_TX_SCHED_CMN_TAG			= 37,
 	HTT_STATS_SCHED_TXQ_CMD_POSTED_TAG		= 39,
@@ -455,6 +457,86 @@ struct ath12k_htt_tx_pdev_rate_stats_tlv {
 	__le32 tx_bw_320mhz;
 };
 
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_CCK_STATS		4
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS		12
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS		4
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_DCM_COUNTERS		5
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS		4
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS		8
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_PREAMBLE_TYPES		7
+#define ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER			8
+#define ATH12K_HTT_RX_PDEV_STATS_RXEVM_MAX_PILOTS_NSS		16
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_RU_SIZE_COUNTERS		6
+#define ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER		8
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS		2
+
+struct ath12k_htt_rx_pdev_rate_stats_tlv {
+	__le32 mac_id_word;
+	__le32 nsts;
+	__le32 rx_ldpc;
+	__le32 rts_cnt;
+	__le32 rssi_mgmt;
+	__le32 rssi_data;
+	__le32 rssi_comb;
+	__le32 rx_mcs[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rx_nss[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 rx_dcm[ATH12K_HTT_RX_PDEV_STATS_NUM_DCM_COUNTERS];
+	__le32 rx_stbc[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rx_bw[ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 rx_pream[ATH12K_HTT_RX_PDEV_STATS_NUM_PREAMBLE_TYPES];
+	u8 rssi_chain_in_db[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+		     [ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 rx_gi[ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS]
+		[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rssi_in_dbm;
+	__le32 rx_11ax_su_ext;
+	__le32 rx_11ac_mumimo;
+	__le32 rx_11ax_mumimo;
+	__le32 rx_11ax_ofdma;
+	__le32 txbf;
+	__le32 rx_legacy_cck_rate[ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_CCK_STATS];
+	__le32 rx_legacy_ofdm_rate[ATH12K_HTT_RX_PDEV_STATS_NUM_LEGACY_OFDM_STATS];
+	__le32 rx_active_dur_us_low;
+	__le32 rx_active_dur_us_high;
+	__le32 rx_11ax_ul_ofdma;
+	__le32 ul_ofdma_rx_mcs[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ul_ofdma_rx_gi[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+			  [ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 ul_ofdma_rx_nss[ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	__le32 ul_ofdma_rx_bw[ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 ul_ofdma_rx_stbc;
+	__le32 ul_ofdma_rx_ldpc;
+	__le32 rx_ulofdma_non_data_ppdu[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 rx_ulofdma_data_ppdu[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 rx_ulofdma_mpdu_ok[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 rx_ulofdma_mpdu_fail[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 nss_count;
+	__le32 pilot_count;
+	__le32 rx_pil_evm_db[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+			   [ATH12K_HTT_RX_PDEV_STATS_RXEVM_MAX_PILOTS_NSS];
+	__le32 rx_pilot_evm_db_mean[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS];
+	s8 rx_ul_fd_rssi[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+			[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 per_chain_rssi_pkt_type;
+	s8 rx_per_chain_rssi_in_dbm[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+				   [ATH12K_HTT_RX_PDEV_STATS_NUM_BW_COUNTERS];
+	__le32 rx_su_ndpa;
+	__le32 rx_11ax_su_txbf_mcs[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rx_mu_ndpa;
+	__le32 rx_11ax_mu_txbf_mcs[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rx_br_poll;
+	__le32 rx_11ax_dl_ofdma_mcs[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS];
+	__le32 rx_11ax_dl_ofdma_ru[ATH12K_HTT_RX_PDEV_STATS_NUM_RU_SIZE_COUNTERS];
+	__le32 rx_ulmumimo_non_data_ppdu[ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER];
+	__le32 rx_ulmumimo_data_ppdu[ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER];
+	__le32 rx_ulmumimo_mpdu_ok[ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER];
+	__le32 rx_ulmumimo_mpdu_fail[ATH12K_HTT_RX_PDEV_MAX_ULMUMIMO_NUM_USER];
+	__le32 rx_ulofdma_non_data_nusers[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 rx_ulofdma_data_nusers[ATH12K_HTT_RX_PDEV_MAX_OFDMA_NUM_USER];
+	__le32 rx_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
+};
+
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_MAC_ID	GENMASK(7, 0)
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_ID	GENMASK(15, 8)
 

From 7a3e8eec8d183d7b293bfb69caab9f213e0a6bbd Mon Sep 17 00:00:00 2001
From: Lingbo Kong <quic_lingbok@quicinc.com>
Date: Mon, 13 Jan 2025 15:17:58 +0800
Subject: [PATCH 0118/2753] wifi: ath12k: Dump additional PDEV receive rate HTT
 stats

Support to dump additional PDEV receive rate stats through HTT debugfs
stats type 30.

Sample output:
------------------
echo 30 > /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:03\:00.0/mac0/htt_stats
HTT_RX_PDEV_RATE_EXT_STATS_TLV:
rssi_mgmt_in_dbm = -48
rx_stbc_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_ofdma_rx_mcs_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
rx_11ax_su_txbf_mcs_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:9, 6:72, 7:41, 8:1, 9:0, 10:0, 11:0, 12:0, 13:0
rx_11ax_mu_txbf_mcs_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
rx_11ax_dl_ofdma_mcs_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
rx_bw_ext =  0:1395, 1:0, 2:0, 3:0, 4:0
rx_su_punctured_mode =  0:0, 1:0, 2:0, 3:0, 4:0
rx_mcs_ext =  0:0, 1:0, 2:0, 3:0, 4:0, 5:14, 6:149, 7:44, 8:1, 9:0, 10:0, 11:0, 12:0, 13:0, 14:0, 15:0
rx_gi_ext[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:14, 6:149, 7:44, 8:1, 9:0, 10:0, 11:0, 12:0, 13:0
rx_gi_ext[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
rx_gi_ext[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
rx_gi_ext[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_ofdma_rx_gi_ext[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_ofdma_rx_gi_ext[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_ofdma_rx_gi_ext[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_ofdma_rx_gi_ext[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.0.1-00029-QCAHKSWPL_SILICONZ-1

Signed-off-by: Lingbo Kong <quic_lingbok@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250113071758.19589-4-quic_lingbok@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 74 +++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   | 32 ++++++++
 2 files changed, 106 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index c3a53d84f8b18..bad1bd21d67d1 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -4232,6 +4232,77 @@ ath12k_htt_print_rx_pdev_rate_stats_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static inline void
+ath12k_htt_print_rx_pdev_rate_ext_stats_tlv(const void *tag_buf, u16 tag_len,
+					    struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_pdev_rate_ext_stats_tlv *htt_stats_buf = tag_buf;
+	u8 *buf = stats_req->buf;
+	u32 len = stats_req->buf_len;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u8 j;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_RX_PDEV_RATE_EXT_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "rssi_mgmt_in_dbm = %d\n",
+			 le32_to_cpu(htt_stats_buf->rssi_mgmt_in_dbm));
+
+	len += print_array_to_buf(buf, len, "rx_stbc_ext",
+				  htt_stats_buf->rx_stbc_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT, "\n");
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_mcs_ext",
+				  htt_stats_buf->ul_ofdma_rx_mcs_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_su_txbf_mcs_ext",
+				  htt_stats_buf->rx_11ax_su_txbf_mcs_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_mu_txbf_mcs_ext",
+				  htt_stats_buf->rx_11ax_mu_txbf_mcs_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT, "\n");
+	len += print_array_to_buf(buf, len, "rx_11ax_dl_ofdma_mcs_ext",
+				  htt_stats_buf->rx_11ax_dl_ofdma_mcs_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT, "\n");
+	len += print_array_to_buf(buf, len, "rx_bw_ext",
+				  htt_stats_buf->rx_bw_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT2_COUNTERS, "\n");
+	len += print_array_to_buf(buf, len, "rx_su_punctured_mode",
+				  htt_stats_buf->rx_su_punctured_mode,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_PUNCTURED_MODE_COUNTERS,
+				  "\n");
+
+	len += print_array_to_buf(buf, len, "rx_mcs_ext",
+				  htt_stats_buf->rx_mcs_ext,
+				  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT,
+				  NULL);
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS; j++)
+		len += scnprintf(buf + len, buf_len - len, ", %u:%u",
+				 j + ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT,
+				 le32_to_cpu(htt_stats_buf->rx_mcs_ext_2[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_gi_ext[%u] = ", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->rx_gi_ext[j],
+					  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT,
+					  "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "ul_ofdma_rx_gi_ext[%u] = ", j);
+		len += print_array_to_buf(buf, len, NULL,
+					  htt_stats_buf->ul_ofdma_rx_gi_ext[j],
+					  ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT,
+					  "\n");
+	}
+
+	stats_req->buf_len = len;
+}
+
 static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 					  u16 tag, u16 len, const void *tag_buf,
 					  void *user_data)
@@ -4473,6 +4544,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_RX_PDEV_RATE_STATS_TAG:
 		ath12k_htt_print_rx_pdev_rate_stats_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG:
+		ath12k_htt_print_rx_pdev_rate_ext_stats_tlv(tag_buf, len, stats_req);
+		break;
 	default:
 		break;
 	}
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 13bafa793764d..e557a5807bc6b 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -137,6 +137,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_MU		= 17,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS		= 19,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	= 23,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT	= 30,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF	= 31,
 	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA		= 32,
 	ATH12K_DBG_HTT_EXT_STATS_DLPAGER_STATS		= 36,
@@ -205,6 +206,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_HW_WAR_TAG				= 89,
 	HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG	= 100,
 	HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG		= 102,
+	HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG		= 103,
 	HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG		= 108,
 	HTT_STATS_TX_SELFGEN_AC_SCHED_STATUS_STATS_TAG	= 111,
 	HTT_STATS_TX_SELFGEN_AX_SCHED_STATUS_STATS_TAG	= 112,
@@ -537,6 +539,36 @@ struct ath12k_htt_rx_pdev_rate_stats_tlv {
 	__le32 rx_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA_MCS_COUNTERS];
 };
 
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT_COUNTERS		4
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT		14
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS	2
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT2_COUNTERS		5
+#define ATH12K_HTT_RX_PDEV_STATS_NUM_PUNCTURED_MODE_COUNTERS	5
+
+struct ath12k_htt_rx_pdev_rate_ext_stats_tlv {
+	u8 rssi_chain_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+			 [ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT_COUNTERS];
+	s8 rx_per_chain_rssi_ext_in_dbm[ATH12K_HTT_RX_PDEV_STATS_NUM_SPATIAL_STREAMS]
+				       [ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT_COUNTERS];
+	__le32 rssi_mcast_in_dbm;
+	__le32 rssi_mgmt_in_dbm;
+	__le32 rx_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_stbc_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_gi_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS]
+		     [ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 ul_ofdma_rx_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 ul_ofdma_rx_gi_ext[ATH12K_HTT_TX_PDEV_STATS_NUM_GI_COUNTERS]
+			      [ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_11ax_su_txbf_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_11ax_mu_txbf_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_11ax_dl_ofdma_mcs_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_MCS_COUNTERS_EXT];
+	__le32 rx_mcs_ext_2[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS];
+	__le32 rx_bw_ext[ATH12K_HTT_RX_PDEV_STATS_NUM_BW_EXT2_COUNTERS];
+	__le32 rx_gi_ext_2[ATH12K_HTT_RX_PDEV_STATS_NUM_GI_COUNTERS]
+		[ATH12K_HTT_RX_PDEV_STATS_NUM_EXTRA2_MCS_COUNTERS];
+	__le32 rx_su_punctured_mode[ATH12K_HTT_RX_PDEV_STATS_NUM_PUNCTURED_MODE_COUNTERS];
+};
+
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_MAC_ID	GENMASK(7, 0)
 #define ATH12K_HTT_TX_PDEV_STATS_SCHED_PER_TXQ_ID	GENMASK(15, 8)
 

From f0c3bb78e42f2f67403b2314486e42f40737b15c Mon Sep 17 00:00:00 2001
From: Sowmiya Sree Elavalagan <quic_ssreeela@quicinc.com>
Date: Thu, 30 Jan 2025 11:41:03 +0530
Subject: [PATCH 0119/2753] wifi: ath12k: Add Support to Parse TPC Event from
 Firmware

Host receives four Transmit Power Control(TPC) events from firmware on
sending TPC request. Fixed param TLV is present as part of all event to
indicate the event count and end of event. TPC config parameters along
with regulatory power array comes as first event. Rates array comes as
second and third event as it cannot be packed in single event.
Conformance Test Limit (CTL) power array comes as the fourth event.
Firmware packs different sets of array params which includes array
length and type inside master TLV as different subtlvs. And the actual
content of array is packed one after the other inside a separate TLV as
single buffer.

Parse various events and save it in local structures. Create tpc_stats
file using debugfs to store these local structures. Create function to
handle TPC stats read to relay the information to the user.

Command usage:
cat > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/tpc_stats

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00214-QCAHKSWPL_SILICONZ-1

Signed-off-by: Sowmiya Sree Elavalagan <quic_ssreeela@quicinc.com>
Co-developed-by: Ramya Gnanasekar <quic_rgnanase@quicinc.com>
Signed-off-by: Ramya Gnanasekar <quic_rgnanase@quicinc.com>
Co-developed-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250130061104.962124-2-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h    |   4 +
 drivers/net/wireless/ath/ath12k/debugfs.c |  96 +++++
 drivers/net/wireless/ath/ath12k/debugfs.h |   6 +
 drivers/net/wireless/ath/ath12k/wmi.c     | 451 ++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/wmi.h     | 139 +++++++
 5 files changed, 696 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index c34a144048650..57e71ccbbb674 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -575,6 +575,10 @@ struct ath12k_debug {
 	struct dentry *debugfs_pdev;
 	struct dentry *debugfs_pdev_symlink;
 	struct ath12k_dbg_htt_stats htt_stats;
+	enum wmi_halphy_ctrl_path_stats_id tpc_stats_type;
+	bool tpc_request;
+	struct completion tpc_complete;
+	struct wmi_tpc_stats_arg *tpc_stats;
 };
 
 struct ath12k_per_peer_tx_stats {
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index 6d6708486d142..8ddcae01a2a1d 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -32,6 +32,99 @@ static const struct file_operations fops_simulate_radar = {
 	.open = simple_open
 };
 
+static int ath12k_debug_tpc_stats_request(struct ath12k *ar)
+{
+	enum wmi_halphy_ctrl_path_stats_id tpc_stats_sub_id;
+	struct ath12k_base *ab = ar->ab;
+	int ret;
+
+	lockdep_assert_wiphy(ath12k_ar_to_hw(ar)->wiphy);
+
+	reinit_completion(&ar->debug.tpc_complete);
+
+	spin_lock_bh(&ar->data_lock);
+	ar->debug.tpc_request = true;
+	tpc_stats_sub_id = ar->debug.tpc_stats_type;
+	spin_unlock_bh(&ar->data_lock);
+
+	ret = ath12k_wmi_send_tpc_stats_request(ar, tpc_stats_sub_id);
+	if (ret) {
+		ath12k_warn(ab, "failed to request pdev tpc stats: %d\n", ret);
+		spin_lock_bh(&ar->data_lock);
+		ar->debug.tpc_request = false;
+		spin_unlock_bh(&ar->data_lock);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ath12k_open_tpc_stats(struct inode *inode, struct file *file)
+{
+	struct ath12k *ar = inode->i_private;
+	struct ath12k_hw *ah = ath12k_ar_to_ah(ar);
+	int ret;
+
+	guard(wiphy)(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (ah->state != ATH12K_HW_STATE_ON) {
+		ath12k_warn(ar->ab, "Interface not up\n");
+		return -ENETDOWN;
+	}
+
+	void *buf __free(kfree) = kzalloc(ATH12K_TPC_STATS_BUF_SIZE, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ret = ath12k_debug_tpc_stats_request(ar);
+	if (ret) {
+		ath12k_warn(ar->ab, "failed to request tpc stats: %d\n",
+			    ret);
+		return ret;
+	}
+
+	if (!wait_for_completion_timeout(&ar->debug.tpc_complete, TPC_STATS_WAIT_TIME)) {
+		spin_lock_bh(&ar->data_lock);
+		ath12k_wmi_free_tpc_stats_mem(ar);
+		ar->debug.tpc_request = false;
+		spin_unlock_bh(&ar->data_lock);
+		return -ETIMEDOUT;
+	}
+
+	file->private_data = no_free_ptr(buf);
+
+	spin_lock_bh(&ar->data_lock);
+	ath12k_wmi_free_tpc_stats_mem(ar);
+	spin_unlock_bh(&ar->data_lock);
+
+	return 0;
+}
+
+static ssize_t ath12k_read_tpc_stats(struct file *file,
+				     char __user *user_buf,
+				     size_t count, loff_t *ppos)
+{
+	const char *buf = file->private_data;
+	size_t len = strlen(buf);
+
+	return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static int ath12k_release_tpc_stats(struct inode *inode,
+				    struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static const struct file_operations fops_tpc_stats = {
+	.open = ath12k_open_tpc_stats,
+	.release = ath12k_release_tpc_stats,
+	.read = ath12k_read_tpc_stats,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
 void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
 	bool dput_needed;
@@ -468,6 +561,9 @@ void ath12k_debugfs_register(struct ath12k *ar)
 				    &fops_simulate_radar);
 	}
 
+	debugfs_create_file("tpc_stats", 0400, ar->debug.debugfs_pdev, ar,
+			    &fops_tpc_stats);
+
 	ath12k_debugfs_htt_stats_register(ar);
 	ath12k_debugfs_fw_stats_register(ar);
 }
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index 1c30745ee4153..25b5219ffe49c 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -15,6 +15,12 @@ void ath12k_debugfs_unregister(struct ath12k *ar);
 void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 				     struct ath12k_fw_stats *stats);
 void ath12k_debugfs_fw_stats_reset(struct ath12k *ar);
+
+#define TPC_STATS_WAIT_TIME		(1 * HZ)
+#define TPC_STATS_TOT_ROW		700
+#define TPC_STATS_TOT_COLUMN		100
+#define ATH12K_TPC_STATS_BUF_SIZE	(TPC_STATS_TOT_ROW * TPC_STATS_TOT_COLUMN)
+
 #else
 static inline void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index b43ab621a74e0..1d6b7af546bf7 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8100,6 +8100,386 @@ static void ath12k_wmi_event_teardown_complete(struct ath12k_base *ab,
 	kfree(tb);
 }
 
+#ifdef CONFIG_ATH12K_DEBUGFS
+static int ath12k_wmi_tpc_stats_copy_buffer(struct ath12k_base *ab,
+					    const void *ptr, u16 tag, u16 len,
+					    struct wmi_tpc_stats_arg *tpc_stats)
+{
+	u32 len1, len2, len3, len4;
+	s16 *dst_ptr;
+	s8 *dst_ptr_ctl;
+
+	len1 = le32_to_cpu(tpc_stats->max_reg_allowed_power.tpc_reg_pwr.reg_array_len);
+	len2 = le32_to_cpu(tpc_stats->rates_array1.tpc_rates_array.rate_array_len);
+	len3 = le32_to_cpu(tpc_stats->rates_array2.tpc_rates_array.rate_array_len);
+	len4 = le32_to_cpu(tpc_stats->ctl_array.tpc_ctl_pwr.ctl_array_len);
+
+	switch (tpc_stats->event_count) {
+	case ATH12K_TPC_STATS_CONFIG_REG_PWR_EVENT:
+		if (len1 > len)
+			return -ENOBUFS;
+
+		if (tpc_stats->tlvs_rcvd & WMI_TPC_REG_PWR_ALLOWED) {
+			dst_ptr = tpc_stats->max_reg_allowed_power.reg_pwr_array;
+			memcpy(dst_ptr, ptr, len1);
+		}
+		break;
+	case ATH12K_TPC_STATS_RATES_EVENT1:
+		if (len2 > len)
+			return -ENOBUFS;
+
+		if (tpc_stats->tlvs_rcvd & WMI_TPC_RATES_ARRAY1) {
+			dst_ptr = tpc_stats->rates_array1.rate_array;
+			memcpy(dst_ptr, ptr, len2);
+		}
+		break;
+	case ATH12K_TPC_STATS_RATES_EVENT2:
+		if (len3 > len)
+			return -ENOBUFS;
+
+		if (tpc_stats->tlvs_rcvd & WMI_TPC_RATES_ARRAY2) {
+			dst_ptr = tpc_stats->rates_array2.rate_array;
+			memcpy(dst_ptr, ptr, len3);
+		}
+		break;
+	case ATH12K_TPC_STATS_CTL_TABLE_EVENT:
+		if (len4 > len)
+			return -ENOBUFS;
+
+		if (tpc_stats->tlvs_rcvd & WMI_TPC_CTL_PWR_ARRAY) {
+			dst_ptr_ctl = tpc_stats->ctl_array.ctl_pwr_table;
+			memcpy(dst_ptr_ctl, ptr, len4);
+		}
+		break;
+	}
+	return 0;
+}
+
+static int ath12k_tpc_get_reg_pwr(struct ath12k_base *ab,
+				  struct wmi_tpc_stats_arg *tpc_stats,
+				  struct wmi_max_reg_power_fixed_params *ev)
+{
+	struct wmi_max_reg_power_allowed_arg *reg_pwr;
+	u32 total_size;
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "Received reg power array type %d length %d for tpc stats\n",
+		   ev->reg_power_type, ev->reg_array_len);
+
+	switch (le32_to_cpu(ev->reg_power_type)) {
+	case TPC_STATS_REG_PWR_ALLOWED_TYPE:
+		reg_pwr = &tpc_stats->max_reg_allowed_power;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Each entry is 2 byte hence multiplying the indices with 2 */
+	total_size = le32_to_cpu(ev->d1) * le32_to_cpu(ev->d2) *
+		     le32_to_cpu(ev->d3) * le32_to_cpu(ev->d4) * 2;
+	if (le32_to_cpu(ev->reg_array_len) != total_size) {
+		ath12k_warn(ab,
+			    "Total size and reg_array_len doesn't match for tpc stats\n");
+		return -EINVAL;
+	}
+
+	memcpy(&reg_pwr->tpc_reg_pwr, ev, sizeof(struct wmi_max_reg_power_fixed_params));
+
+	reg_pwr->reg_pwr_array = kzalloc(le32_to_cpu(reg_pwr->tpc_reg_pwr.reg_array_len),
+					 GFP_ATOMIC);
+	if (!reg_pwr->reg_pwr_array)
+		return -ENOMEM;
+
+	tpc_stats->tlvs_rcvd |= WMI_TPC_REG_PWR_ALLOWED;
+
+	return 0;
+}
+
+static int ath12k_tpc_get_rate_array(struct ath12k_base *ab,
+				     struct wmi_tpc_stats_arg *tpc_stats,
+				     struct wmi_tpc_rates_array_fixed_params *ev)
+{
+	struct wmi_tpc_rates_array_arg *rates_array;
+	u32 flag = 0, rate_array_len;
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "Received rates array type %d length %d for tpc stats\n",
+		   ev->rate_array_type, ev->rate_array_len);
+
+	switch (le32_to_cpu(ev->rate_array_type)) {
+	case ATH12K_TPC_STATS_RATES_ARRAY1:
+		rates_array = &tpc_stats->rates_array1;
+		flag = WMI_TPC_RATES_ARRAY1;
+		break;
+	case ATH12K_TPC_STATS_RATES_ARRAY2:
+		rates_array = &tpc_stats->rates_array2;
+		flag = WMI_TPC_RATES_ARRAY2;
+		break;
+	default:
+		ath12k_warn(ab,
+			    "Received invalid type of rates array for tpc stats\n");
+		return -EINVAL;
+	}
+	memcpy(&rates_array->tpc_rates_array, ev,
+	       sizeof(struct wmi_tpc_rates_array_fixed_params));
+	rate_array_len = le32_to_cpu(rates_array->tpc_rates_array.rate_array_len);
+	rates_array->rate_array = kzalloc(rate_array_len, GFP_ATOMIC);
+	if (!rates_array->rate_array)
+		return -ENOMEM;
+
+	tpc_stats->tlvs_rcvd |= flag;
+	return 0;
+}
+
+static int ath12k_tpc_get_ctl_pwr_tbl(struct ath12k_base *ab,
+				      struct wmi_tpc_stats_arg *tpc_stats,
+				      struct wmi_tpc_ctl_pwr_fixed_params *ev)
+{
+	struct wmi_tpc_ctl_pwr_table_arg *ctl_array;
+	u32 total_size, ctl_array_len, flag = 0;
+
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "Received ctl array type %d length %d for tpc stats\n",
+		   ev->ctl_array_type, ev->ctl_array_len);
+
+	switch (le32_to_cpu(ev->ctl_array_type)) {
+	case ATH12K_TPC_STATS_CTL_ARRAY:
+		ctl_array = &tpc_stats->ctl_array;
+		flag = WMI_TPC_CTL_PWR_ARRAY;
+		break;
+	default:
+		ath12k_warn(ab,
+			    "Received invalid type of ctl pwr table for tpc stats\n");
+		return -EINVAL;
+	}
+
+	total_size = le32_to_cpu(ev->d1) * le32_to_cpu(ev->d2) *
+		     le32_to_cpu(ev->d3) * le32_to_cpu(ev->d4);
+	if (le32_to_cpu(ev->ctl_array_len) != total_size) {
+		ath12k_warn(ab,
+			    "Total size and ctl_array_len doesn't match for tpc stats\n");
+		return -EINVAL;
+	}
+
+	memcpy(&ctl_array->tpc_ctl_pwr, ev, sizeof(struct wmi_tpc_ctl_pwr_fixed_params));
+	ctl_array_len = le32_to_cpu(ctl_array->tpc_ctl_pwr.ctl_array_len);
+	ctl_array->ctl_pwr_table = kzalloc(ctl_array_len, GFP_ATOMIC);
+	if (!ctl_array->ctl_pwr_table)
+		return -ENOMEM;
+
+	tpc_stats->tlvs_rcvd |= flag;
+	return 0;
+}
+
+static int ath12k_wmi_tpc_stats_subtlv_parser(struct ath12k_base *ab,
+					      u16 tag, u16 len,
+					      const void *ptr, void *data)
+{
+	struct wmi_tpc_rates_array_fixed_params *tpc_rates_array;
+	struct wmi_max_reg_power_fixed_params *tpc_reg_pwr;
+	struct wmi_tpc_ctl_pwr_fixed_params *tpc_ctl_pwr;
+	struct wmi_tpc_stats_arg *tpc_stats = data;
+	struct wmi_tpc_config_params *tpc_config;
+	int ret = 0;
+
+	if (!tpc_stats) {
+		ath12k_warn(ab, "tpc stats memory unavailable\n");
+		return -EINVAL;
+	}
+
+	switch (tag) {
+	case WMI_TAG_TPC_STATS_CONFIG_EVENT:
+		tpc_config = (struct wmi_tpc_config_params *)ptr;
+		memcpy(&tpc_stats->tpc_config, tpc_config,
+		       sizeof(struct wmi_tpc_config_params));
+		break;
+	case WMI_TAG_TPC_STATS_REG_PWR_ALLOWED:
+		tpc_reg_pwr = (struct wmi_max_reg_power_fixed_params *)ptr;
+		ret = ath12k_tpc_get_reg_pwr(ab, tpc_stats, tpc_reg_pwr);
+		break;
+	case WMI_TAG_TPC_STATS_RATES_ARRAY:
+		tpc_rates_array = (struct wmi_tpc_rates_array_fixed_params *)ptr;
+		ret = ath12k_tpc_get_rate_array(ab, tpc_stats, tpc_rates_array);
+		break;
+	case WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT:
+		tpc_ctl_pwr = (struct wmi_tpc_ctl_pwr_fixed_params *)ptr;
+		ret = ath12k_tpc_get_ctl_pwr_tbl(ab, tpc_stats, tpc_ctl_pwr);
+		break;
+	default:
+		ath12k_warn(ab,
+			    "Received invalid tag for tpc stats in subtlvs\n");
+		return -EINVAL;
+	}
+	return ret;
+}
+
+static int ath12k_wmi_tpc_stats_event_parser(struct ath12k_base *ab,
+					     u16 tag, u16 len,
+					     const void *ptr, void *data)
+{
+	struct wmi_tpc_stats_arg *tpc_stats = (struct wmi_tpc_stats_arg *)data;
+	int ret;
+
+	switch (tag) {
+	case WMI_TAG_HALPHY_CTRL_PATH_EVENT_FIXED_PARAM:
+		ret = 0;
+		/* Fixed param is already processed*/
+		break;
+	case WMI_TAG_ARRAY_STRUCT:
+		/* len 0 is expected for array of struct when there
+		 * is no content of that type to pack inside that tlv
+		 */
+		if (len == 0)
+			return 0;
+		ret = ath12k_wmi_tlv_iter(ab, ptr, len,
+					  ath12k_wmi_tpc_stats_subtlv_parser,
+					  tpc_stats);
+		break;
+	case WMI_TAG_ARRAY_INT16:
+		if (len == 0)
+			return 0;
+		ret = ath12k_wmi_tpc_stats_copy_buffer(ab, ptr,
+						       WMI_TAG_ARRAY_INT16,
+						       len, tpc_stats);
+		break;
+	case WMI_TAG_ARRAY_BYTE:
+		if (len == 0)
+			return 0;
+		ret = ath12k_wmi_tpc_stats_copy_buffer(ab, ptr,
+						       WMI_TAG_ARRAY_BYTE,
+						       len, tpc_stats);
+		break;
+	default:
+		ath12k_warn(ab, "Received invalid tag for tpc stats\n");
+		ret = -EINVAL;
+		break;
+	}
+	return ret;
+}
+
+void ath12k_wmi_free_tpc_stats_mem(struct ath12k *ar)
+{
+	struct wmi_tpc_stats_arg *tpc_stats = ar->debug.tpc_stats;
+
+	lockdep_assert_held(&ar->data_lock);
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "tpc stats mem free\n");
+	if (tpc_stats) {
+		kfree(tpc_stats->max_reg_allowed_power.reg_pwr_array);
+		kfree(tpc_stats->rates_array1.rate_array);
+		kfree(tpc_stats->rates_array2.rate_array);
+		kfree(tpc_stats->ctl_array.ctl_pwr_table);
+		kfree(tpc_stats);
+		ar->debug.tpc_stats = NULL;
+	}
+}
+
+static void ath12k_wmi_process_tpc_stats(struct ath12k_base *ab,
+					 struct sk_buff *skb)
+{
+	struct ath12k_wmi_pdev_tpc_stats_event_fixed_params *fixed_param;
+	struct wmi_tpc_stats_arg *tpc_stats;
+	const struct wmi_tlv *tlv;
+	void *ptr = skb->data;
+	struct ath12k *ar;
+	u16 tlv_tag;
+	u32 event_count;
+	int ret;
+
+	if (!skb->data) {
+		ath12k_warn(ab, "No data present in tpc stats event\n");
+		return;
+	}
+
+	if (skb->len < (sizeof(*fixed_param) + TLV_HDR_SIZE)) {
+		ath12k_warn(ab, "TPC stats event size invalid\n");
+		return;
+	}
+
+	tlv = (struct wmi_tlv *)ptr;
+	tlv_tag = le32_get_bits(tlv->header, WMI_TLV_TAG);
+	ptr += sizeof(*tlv);
+
+	if (tlv_tag != WMI_TAG_HALPHY_CTRL_PATH_EVENT_FIXED_PARAM) {
+		ath12k_warn(ab, "TPC stats without fixed param tlv at start\n");
+		return;
+	}
+
+	fixed_param = (struct ath12k_wmi_pdev_tpc_stats_event_fixed_params *)ptr;
+	rcu_read_lock();
+	ar = ath12k_mac_get_ar_by_pdev_id(ab, le32_to_cpu(fixed_param->pdev_id) + 1);
+	if (!ar) {
+		ath12k_warn(ab, "Failed to get ar for tpc stats\n");
+		rcu_read_unlock();
+		return;
+	}
+	spin_lock_bh(&ar->data_lock);
+	if (!ar->debug.tpc_request) {
+		/* Event is received either without request or the
+		 * timeout, if memory is already allocated free it
+		 */
+		if (ar->debug.tpc_stats) {
+			ath12k_warn(ab, "Freeing memory for tpc_stats\n");
+			ath12k_wmi_free_tpc_stats_mem(ar);
+		}
+		goto unlock;
+	}
+
+	event_count = le32_to_cpu(fixed_param->event_count);
+	if (event_count == 0) {
+		if (ar->debug.tpc_stats) {
+			ath12k_warn(ab,
+				    "Invalid tpc memory present\n");
+			goto unlock;
+		}
+		ar->debug.tpc_stats =
+			kzalloc(sizeof(struct wmi_tpc_stats_arg),
+				GFP_ATOMIC);
+		if (!ar->debug.tpc_stats) {
+			ath12k_warn(ab,
+				    "Failed to allocate memory for tpc stats\n");
+			goto unlock;
+		}
+	}
+
+	tpc_stats = ar->debug.tpc_stats;
+
+	if (!(event_count == 0)) {
+		if (event_count != tpc_stats->event_count + 1) {
+			ath12k_warn(ab,
+				    "Invalid tpc event received\n");
+			goto unlock;
+		}
+	}
+	tpc_stats->pdev_id = le32_to_cpu(fixed_param->pdev_id);
+	tpc_stats->end_of_event = le32_to_cpu(fixed_param->end_of_event);
+	tpc_stats->event_count = le32_to_cpu(fixed_param->event_count);
+	ath12k_dbg(ab, ATH12K_DBG_WMI,
+		   "tpc stats event_count %d\n",
+		   tpc_stats->event_count);
+	ret = ath12k_wmi_tlv_iter(ab, skb->data, skb->len,
+				  ath12k_wmi_tpc_stats_event_parser,
+				  tpc_stats);
+	if (ret) {
+		if (tpc_stats)
+			ath12k_wmi_free_tpc_stats_mem(ar);
+		ath12k_warn(ab, "failed to parse tpc_stats tlv: %d\n", ret);
+		goto unlock;
+	}
+
+	if (tpc_stats && tpc_stats->end_of_event)
+		complete(&ar->debug.tpc_complete);
+
+unlock:
+	spin_unlock_bh(&ar->data_lock);
+	rcu_read_unlock();
+}
+#else
+static void ath12k_wmi_process_tpc_stats(struct ath12k_base *ab,
+					 struct sk_buff *skb)
+{
+}
+#endif
+
 static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb)
 {
 	struct wmi_cmd_hdr *cmd_hdr;
@@ -8225,6 +8605,9 @@ static void ath12k_wmi_op_rx(struct ath12k_base *ab, struct sk_buff *skb)
 	case WMI_MLO_TEARDOWN_COMPLETE_EVENTID:
 		ath12k_wmi_event_teardown_complete(ab, skb);
 		break;
+	case WMI_HALPHY_STATS_CTRL_PATH_EVENTID:
+		ath12k_wmi_process_tpc_stats(ab, skb);
+		break;
 	/* add Unsupported events (rare) here */
 	case WMI_TBTTOFFSET_EXT_UPDATE_EVENTID:
 	case WMI_PEER_OPER_MODE_CHANGE_EVENTID:
@@ -8380,6 +8763,74 @@ int ath12k_wmi_simulate_radar(struct ath12k *ar)
 	return ath12k_wmi_send_unit_test_cmd(ar, wmi_ut, dfs_args);
 }
 
+int ath12k_wmi_send_tpc_stats_request(struct ath12k *ar,
+				      enum wmi_halphy_ctrl_path_stats_id tpc_stats_type)
+{
+	struct wmi_request_halphy_ctrl_path_stats_cmd_fixed_params *cmd;
+	struct ath12k_wmi_pdev *wmi = ar->wmi;
+	struct sk_buff *skb;
+	struct wmi_tlv *tlv;
+	__le32 *pdev_id;
+	u32 buf_len;
+	void *ptr;
+	int ret;
+
+	buf_len = sizeof(*cmd) + TLV_HDR_SIZE + sizeof(u32) + TLV_HDR_SIZE + TLV_HDR_SIZE;
+
+	skb = ath12k_wmi_alloc_skb(wmi->wmi_ab, buf_len);
+	if (!skb)
+		return -ENOMEM;
+	cmd = (struct wmi_request_halphy_ctrl_path_stats_cmd_fixed_params *)skb->data;
+	cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_HALPHY_CTRL_PATH_CMD_FIXED_PARAM,
+						 sizeof(*cmd));
+
+	cmd->stats_id_mask = cpu_to_le32(WMI_REQ_CTRL_PATH_PDEV_TX_STAT);
+	cmd->action = cpu_to_le32(WMI_REQUEST_CTRL_PATH_STAT_GET);
+	cmd->subid = cpu_to_le32(tpc_stats_type);
+
+	ptr = skb->data + sizeof(*cmd);
+
+	/* The below TLV arrays optionally follow this fixed param TLV structure
+	 * 1. ARRAY_UINT32 pdev_ids[]
+	 *      If this array is present and non-zero length, stats should only
+	 *      be provided from the pdevs identified in the array.
+	 * 2. ARRAY_UNIT32 vdev_ids[]
+	 *      If this array is present and non-zero length, stats should only
+	 *      be provided from the vdevs identified in the array.
+	 * 3. ath12k_wmi_mac_addr_params peer_macaddr[];
+	 *      If this array is present and non-zero length, stats should only
+	 *      be provided from the peers with the MAC addresses specified
+	 *      in the array
+	 */
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, sizeof(u32));
+	ptr += TLV_HDR_SIZE;
+
+	pdev_id = ptr;
+	*pdev_id = cpu_to_le32(ath12k_mac_get_target_pdev_id(ar));
+	ptr += sizeof(*pdev_id);
+
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_UINT32, 0);
+	ptr += TLV_HDR_SIZE;
+
+	tlv = ptr;
+	tlv->header = ath12k_wmi_tlv_hdr(WMI_TAG_ARRAY_FIXED_STRUCT, 0);
+	ptr += TLV_HDR_SIZE;
+
+	ret = ath12k_wmi_cmd_send(wmi, skb, WMI_REQUEST_HALPHY_CTRL_PATH_STATS_CMDID);
+	if (ret) {
+		ath12k_warn(ar->ab,
+			    "failed to submit WMI_REQUEST_STATS_CTRL_PATH_CMDID\n");
+		dev_kfree_skb(skb);
+		return ret;
+	}
+	ath12k_dbg(ar->ab, ATH12K_DBG_WMI, "WMI get TPC STATS sent on pdev %d\n",
+		   ar->pdev->pdev_id);
+
+	return ret;
+}
+
 int ath12k_wmi_connect(struct ath12k_base *ab)
 {
 	u32 i;
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index 63a88fb821cad..e8a4789b6ae1a 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -517,6 +517,9 @@ enum wmi_tlv_cmd_id {
 	WMI_REQUEST_RCPI_CMDID,
 	WMI_REQUEST_PEER_STATS_INFO_CMDID,
 	WMI_REQUEST_RADIO_CHAN_STATS_CMDID,
+	WMI_REQUEST_WLM_STATS_CMDID,
+	WMI_REQUEST_CTRL_PATH_STATS_CMDID,
+	WMI_REQUEST_HALPHY_CTRL_PATH_STATS_CMDID = WMI_REQUEST_CTRL_PATH_STATS_CMDID + 3,
 	WMI_SET_ARP_NS_OFFLOAD_CMDID = WMI_TLV_CMD(WMI_GRP_ARP_NS_OFL),
 	WMI_ADD_PROACTIVE_ARP_RSP_PATTERN_CMDID,
 	WMI_DEL_PROACTIVE_ARP_RSP_PATTERN_CMDID,
@@ -786,6 +789,9 @@ enum wmi_tlv_event_id {
 	WMI_UPDATE_RCPI_EVENTID,
 	WMI_PEER_STATS_INFO_EVENTID,
 	WMI_RADIO_CHAN_STATS_EVENTID,
+	WMI_WLM_STATS_EVENTID,
+	WMI_CTRL_PATH_STATS_EVENTID,
+	WMI_HALPHY_STATS_CTRL_PATH_EVENTID,
 	WMI_NLO_MATCH_EVENTID = WMI_TLV_CMD(WMI_GRP_NLO_OFL),
 	WMI_NLO_SCAN_COMPLETE_EVENTID,
 	WMI_APFIND_EVENTID,
@@ -1192,6 +1198,7 @@ enum wmi_tlv_tag {
 	WMI_TAG_ARRAY_BYTE,
 	WMI_TAG_ARRAY_STRUCT,
 	WMI_TAG_ARRAY_FIXED_STRUCT,
+	WMI_TAG_ARRAY_INT16,
 	WMI_TAG_LAST_ARRAY_ENUM = 31,
 	WMI_TAG_SERVICE_READY_EVENT,
 	WMI_TAG_HAL_REG_CAPABILITIES,
@@ -1942,6 +1949,12 @@ enum wmi_tlv_tag {
 	WMI_TAG_MAC_PHY_CAPABILITIES_EXT = 0x36F,
 	WMI_TAG_REGULATORY_RULE_EXT_STRUCT = 0x3A9,
 	WMI_TAG_REG_CHAN_LIST_CC_EXT_EVENT,
+	WMI_TAG_TPC_STATS_GET_CMD = 0x38B,
+	WMI_TAG_TPC_STATS_EVENT_FIXED_PARAM,
+	WMI_TAG_TPC_STATS_CONFIG_EVENT,
+	WMI_TAG_TPC_STATS_REG_PWR_ALLOWED,
+	WMI_TAG_TPC_STATS_RATES_ARRAY,
+	WMI_TAG_TPC_STATS_CTL_PWR_TABLE_EVENT,
 	WMI_TAG_EHT_RATE_SET = 0x3C4,
 	WMI_TAG_DCS_AWGN_INT_TYPE = 0x3C5,
 	WMI_TAG_MLO_TX_SEND_PARAMS,
@@ -1959,6 +1972,8 @@ enum wmi_tlv_tag {
 	WMI_TAG_PDEV_SET_BIOS_SAR_TABLE_CMD = 0x3D8,
 	WMI_TAG_PDEV_SET_BIOS_GEO_TABLE_CMD = 0x3D9,
 	WMI_TAG_PDEV_SET_BIOS_INTERFACE_CMD = 0x3FB,
+	WMI_TAG_HALPHY_CTRL_PATH_CMD_FIXED_PARAM = 0x442,
+	WMI_TAG_HALPHY_CTRL_PATH_EVENT_FIXED_PARAM,
 	WMI_TAG_MAX
 };
 
@@ -5769,6 +5784,126 @@ struct ath12k_fw_stats_req_params {
 	u32 pdev_id;
 };
 
+#define WMI_REQ_CTRL_PATH_PDEV_TX_STAT		1
+#define WMI_REQUEST_CTRL_PATH_STAT_GET		1
+
+#define WMI_TPC_CONFIG			BIT(1)
+#define WMI_TPC_REG_PWR_ALLOWED		BIT(2)
+#define WMI_TPC_RATES_ARRAY1		BIT(3)
+#define WMI_TPC_RATES_ARRAY2		BIT(4)
+#define WMI_TPC_RATES_DL_OFDMA_ARRAY	BIT(5)
+#define WMI_TPC_CTL_PWR_ARRAY		BIT(6)
+#define WMI_TPC_CONFIG_PARAM		0x1
+#define ATH12K_TPC_RATE_ARRAY_MU	GENMASK(15, 8)
+#define ATH12K_TPC_RATE_ARRAY_SU	GENMASK(7, 0)
+#define TPC_STATS_REG_PWR_ALLOWED_TYPE	0
+
+enum wmi_halphy_ctrl_path_stats_id {
+	WMI_HALPHY_PDEV_TX_SU_STATS = 0,
+	WMI_HALPHY_PDEV_TX_SUTXBF_STATS,
+	WMI_HALPHY_PDEV_TX_MU_STATS,
+	WMI_HALPHY_PDEV_TX_MUTXBF_STATS,
+	WMI_HALPHY_PDEV_TX_STATS_MAX,
+};
+
+enum ath12k_wmi_tpc_stats_rates_array {
+	ATH12K_TPC_STATS_RATES_ARRAY1,
+	ATH12K_TPC_STATS_RATES_ARRAY2,
+};
+
+enum ath12k_wmi_tpc_stats_ctl_array {
+	ATH12K_TPC_STATS_CTL_ARRAY,
+	ATH12K_TPC_STATS_CTL_160ARRAY,
+};
+
+enum ath12k_wmi_tpc_stats_events {
+	ATH12K_TPC_STATS_CONFIG_REG_PWR_EVENT,
+	ATH12K_TPC_STATS_RATES_EVENT1,
+	ATH12K_TPC_STATS_RATES_EVENT2,
+	ATH12K_TPC_STATS_CTL_TABLE_EVENT
+};
+
+struct wmi_request_halphy_ctrl_path_stats_cmd_fixed_params {
+	__le32 tlv_header;
+	__le32 stats_id_mask;
+	__le32 request_id;
+	__le32 action;
+	__le32 subid;
+} __packed;
+
+struct ath12k_wmi_pdev_tpc_stats_event_fixed_params {
+	__le32 pdev_id;
+	__le32 end_of_event;
+	__le32 event_count;
+} __packed;
+
+struct wmi_tpc_config_params {
+	__le32 reg_domain;
+	__le32 chan_freq;
+	__le32 phy_mode;
+	__le32 twice_antenna_reduction;
+	__le32 twice_max_reg_power;
+	__le32 twice_antenna_gain;
+	__le32 power_limit;
+	__le32 rate_max;
+	__le32 num_tx_chain;
+	__le32 ctl;
+	__le32 flags;
+	__le32 caps;
+} __packed;
+
+struct wmi_max_reg_power_fixed_params {
+	__le32 reg_power_type;
+	__le32 reg_array_len;
+	__le32 d1;
+	__le32 d2;
+	__le32 d3;
+	__le32 d4;
+} __packed;
+
+struct wmi_max_reg_power_allowed_arg {
+	struct wmi_max_reg_power_fixed_params tpc_reg_pwr;
+	s16 *reg_pwr_array;
+};
+
+struct wmi_tpc_rates_array_fixed_params {
+	__le32 rate_array_type;
+	__le32 rate_array_len;
+} __packed;
+
+struct wmi_tpc_rates_array_arg {
+	struct wmi_tpc_rates_array_fixed_params tpc_rates_array;
+	s16 *rate_array;
+};
+
+struct wmi_tpc_ctl_pwr_fixed_params {
+	__le32 ctl_array_type;
+	__le32 ctl_array_len;
+	__le32 end_of_ctl_pwr;
+	__le32 ctl_pwr_count;
+	__le32 d1;
+	__le32 d2;
+	__le32 d3;
+	__le32 d4;
+} __packed;
+
+struct wmi_tpc_ctl_pwr_table_arg {
+	struct wmi_tpc_ctl_pwr_fixed_params tpc_ctl_pwr;
+	s8 *ctl_pwr_table;
+};
+
+struct wmi_tpc_stats_arg {
+	u32 pdev_id;
+	u32 event_count;
+	u32 end_of_event;
+	u32 tlvs_rcvd;
+	struct wmi_max_reg_power_allowed_arg max_reg_allowed_power;
+	struct wmi_tpc_rates_array_arg rates_array1;
+	struct wmi_tpc_rates_array_arg rates_array2;
+	struct wmi_tpc_config_params tpc_config;
+	struct wmi_tpc_ctl_pwr_table_arg ctl_array;
+};
+
 void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
 			     struct ath12k_wmi_resource_config_arg *config);
 void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
@@ -5898,6 +6033,10 @@ int ath12k_wmi_send_stats_request_cmd(struct ath12k *ar, u32 stats_id,
 				      u32 vdev_id, u32 pdev_id);
 __le32 ath12k_wmi_tlv_hdr(u32 cmd, u32 len);
 
+int ath12k_wmi_send_tpc_stats_request(struct ath12k *ar,
+				      enum wmi_halphy_ctrl_path_stats_id tpc_stats_type);
+void ath12k_wmi_free_tpc_stats_mem(struct ath12k *ar);
+
 static inline u32
 ath12k_wmi_caps_ext_get_pdev_id(const struct ath12k_wmi_caps_ext_params *param)
 {

From f5c90ff80b4c0326e5fd1feecafd88718075b1b7 Mon Sep 17 00:00:00 2001
From: Sowmiya Sree Elavalagan <quic_ssreeela@quicinc.com>
Date: Thu, 30 Jan 2025 11:41:04 +0530
Subject: [PATCH 0120/2753] wifi: ath12k: Add Support to Calculate and Display
 TPC Values

Transmit Power Control(TPC) stats should display per chain TPC value per
radio. Add debugfs support to read and display TPC stats type and TPC
stats. Take power values for each preamble type, rate and NSS combination
from a particular index from each power arrays based on number of chains,
NSS, modes, MCS and tx beamforming enabled/disabled parameters. Minimum
of the values taken from reg power table, rates and Conformance Test
Limit(CTL) array table should give the TPC which is in 0.25 dBm steps.

Sample Output:
-------------
echo 1 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/tpc_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/tpc_stats

*************** TPC config **************
* powers are in 0.25 dBm steps
reg domain-22           chan freq-5955
power limit-126         max reg-domain Power-252
No.of tx chain-4        No.of rates-1164
**************** SU WITH TXBF ****************
                                TPC values for Active chains
Rate idx Preamble Rate code     1-Chain 2-Chain 3-Chain 4-Chain
4        OFDM    0x000          39      15      1       -9
5        OFDM    0x001          39      15      1       -9
.....
12       HT20    0x200          40      16      2       -8
13       HT20    0x201          40      16      2       -8
.....
44       HT40    0x200          88      88      88      88
45       HT40    0x201          88      88      88      88
.....
76       VHT20   0x300          40      16      2       -8
77       VHT20   0x301          40      16      2       -8
.....
172      VHT40   0x300          88      88      88      88
173      VHT40   0x301          88      88      88      88
.....
412      HE20    0x400          88      88      88      88
413      HE20    0x401          88      88      88      88
.....
508      HE40    0x400          76      76      76      76
509      HE40    0x401          76      76      76      76
.....
748      EHT20   0x50e          88      88      88      88
749      EHT20   0x50f          88      88      88      88
.....
812      EHT40   0x50e          88      88      88      88
813      EHT40   0x50f          88      88      88      88
.....

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.1.1-00214-QCAHKSWPL_SILICONZ-1

Signed-off-by: Sowmiya Sree Elavalagan <quic_ssreeela@quicinc.com>
Co-developed-by: Ramya Gnanasekar <quic_rgnanase@quicinc.com>
Signed-off-by: Ramya Gnanasekar <quic_rgnanase@quicinc.com>
Co-developed-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250130061104.962124-3-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/debugfs.c | 618 ++++++++++++++++++++++
 drivers/net/wireless/ath/ath12k/debugfs.h |  83 ++-
 drivers/net/wireless/ath/ath12k/reg.h     |   5 +-
 drivers/net/wireless/ath/ath12k/wmi.h     |   1 +
 4 files changed, 703 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index 8ddcae01a2a1d..d38ece46f1d0e 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -32,6 +32,28 @@ static const struct file_operations fops_simulate_radar = {
 	.open = simple_open
 };
 
+static ssize_t ath12k_write_tpc_stats_type(struct file *file,
+					   const char __user *user_buf,
+					   size_t count, loff_t *ppos)
+{
+	struct ath12k *ar = file->private_data;
+	u8 type;
+	int ret;
+
+	ret = kstrtou8_from_user(user_buf, count, 0, &type);
+	if (ret)
+		return ret;
+
+	if (type >= WMI_HALPHY_PDEV_TX_STATS_MAX)
+		return -EINVAL;
+
+	spin_lock_bh(&ar->data_lock);
+	ar->debug.tpc_stats_type = type;
+	spin_unlock_bh(&ar->data_lock);
+
+	return count;
+}
+
 static int ath12k_debug_tpc_stats_request(struct ath12k *ar)
 {
 	enum wmi_halphy_ctrl_path_stats_id tpc_stats_sub_id;
@@ -59,6 +81,592 @@ static int ath12k_debug_tpc_stats_request(struct ath12k *ar)
 	return 0;
 }
 
+static int ath12k_get_tpc_ctl_mode_idx(struct wmi_tpc_stats_arg *tpc_stats,
+				       enum wmi_tpc_pream_bw pream_bw, int *mode_idx)
+{
+	u32 chan_freq = le32_to_cpu(tpc_stats->tpc_config.chan_freq);
+	u8 band;
+
+	band = ((chan_freq > ATH12K_MIN_6G_FREQ) ? NL80211_BAND_6GHZ :
+		((chan_freq > ATH12K_MIN_5G_FREQ) ? NL80211_BAND_5GHZ :
+		NL80211_BAND_2GHZ));
+
+	if (band == NL80211_BAND_5GHZ || band == NL80211_BAND_6GHZ) {
+		switch (pream_bw) {
+		case WMI_TPC_PREAM_HT20:
+		case WMI_TPC_PREAM_VHT20:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HT_VHT20_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_HE20:
+		case WMI_TPC_PREAM_EHT20:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HE_EHT20_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_HT40:
+		case WMI_TPC_PREAM_VHT40:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HT_VHT40_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_HE40:
+		case WMI_TPC_PREAM_EHT40:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HE_EHT40_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_VHT80:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_VHT80_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_EHT60:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_EHT80_SU_PUNC20;
+			break;
+		case WMI_TPC_PREAM_HE80:
+		case WMI_TPC_PREAM_EHT80:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HE_EHT80_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_VHT160:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_VHT160_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_EHT120:
+		case WMI_TPC_PREAM_EHT140:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_EHT160_SU_PUNC20;
+			break;
+		case WMI_TPC_PREAM_HE160:
+		case WMI_TPC_PREAM_EHT160:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HE_EHT160_5GHZ_6GHZ;
+			break;
+		case WMI_TPC_PREAM_EHT200:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC120;
+			break;
+		case WMI_TPC_PREAM_EHT240:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC80;
+			break;
+		case WMI_TPC_PREAM_EHT280:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC40;
+			break;
+		case WMI_TPC_PREAM_EHT320:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HE_EHT320_5GHZ_6GHZ;
+			break;
+		default:
+			/* for 5GHZ and 6GHZ, default case will be for OFDM */
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_LEGACY_5GHZ_6GHZ;
+			break;
+		}
+	} else {
+		switch (pream_bw) {
+		case WMI_TPC_PREAM_OFDM:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_LEGACY_2GHZ;
+			break;
+		case WMI_TPC_PREAM_HT20:
+		case WMI_TPC_PREAM_VHT20:
+		case WMI_TPC_PREAM_HE20:
+		case WMI_TPC_PREAM_EHT20:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HT20_2GHZ;
+			break;
+		case WMI_TPC_PREAM_HT40:
+		case WMI_TPC_PREAM_VHT40:
+		case WMI_TPC_PREAM_HE40:
+		case WMI_TPC_PREAM_EHT40:
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_HT40_2GHZ;
+			break;
+		default:
+			/* for 2GHZ, default case will be CCK */
+			*mode_idx = ATH12K_TPC_STATS_CTL_MODE_CCK_2GHZ;
+			break;
+		}
+	}
+
+	return 0;
+}
+
+static s16 ath12k_tpc_get_rate(struct ath12k *ar,
+			       struct wmi_tpc_stats_arg *tpc_stats,
+			       u32 rate_idx, u32 num_chains, u32 rate_code,
+			       enum wmi_tpc_pream_bw pream_bw,
+			       enum wmi_halphy_ctrl_path_stats_id type,
+			       u32 eht_rate_idx)
+{
+	u32 tot_nss, tot_modes, txbf_on_off, index_offset1, index_offset2, index_offset3;
+	u8 chain_idx, stm_idx, num_streams;
+	bool is_mu, txbf_enabled = 0;
+	s8 rates_ctl_min, tpc_ctl;
+	s16 rates, tpc, reg_pwr;
+	u16 rate1, rate2;
+	int mode, ret;
+
+	num_streams = 1 + ATH12K_HW_NSS(rate_code);
+	chain_idx = num_chains - 1;
+	stm_idx = num_streams - 1;
+	mode = -1;
+
+	ret = ath12k_get_tpc_ctl_mode_idx(tpc_stats, pream_bw, &mode);
+	if (ret) {
+		ath12k_warn(ar->ab, "Invalid mode index received\n");
+		tpc = TPC_INVAL;
+		goto out;
+	}
+
+	if (num_chains < num_streams) {
+		tpc = TPC_INVAL;
+		goto out;
+	}
+
+	if (le32_to_cpu(tpc_stats->tpc_config.num_tx_chain) <= 1) {
+		tpc = TPC_INVAL;
+		goto out;
+	}
+
+	if (type == WMI_HALPHY_PDEV_TX_SUTXBF_STATS ||
+	    type == WMI_HALPHY_PDEV_TX_MUTXBF_STATS)
+		txbf_enabled = 1;
+
+	if (type == WMI_HALPHY_PDEV_TX_MU_STATS ||
+	    type == WMI_HALPHY_PDEV_TX_MUTXBF_STATS) {
+		is_mu = true;
+	} else {
+		is_mu = false;
+	}
+
+	/* Below is the min calculation of ctl array, rates array and
+	 * regulator power table. tpc is minimum of all 3
+	 */
+	if (pream_bw >= WMI_TPC_PREAM_EHT20 && pream_bw <= WMI_TPC_PREAM_EHT320) {
+		rate2 = tpc_stats->rates_array2.rate_array[eht_rate_idx];
+		if (is_mu)
+			rates = u32_get_bits(rate2, ATH12K_TPC_RATE_ARRAY_MU);
+		else
+			rates = u32_get_bits(rate2, ATH12K_TPC_RATE_ARRAY_SU);
+	} else {
+		rate1 = tpc_stats->rates_array1.rate_array[rate_idx];
+		if (is_mu)
+			rates = u32_get_bits(rate1, ATH12K_TPC_RATE_ARRAY_MU);
+		else
+			rates = u32_get_bits(rate1, ATH12K_TPC_RATE_ARRAY_SU);
+	}
+
+	if (tpc_stats->tlvs_rcvd & WMI_TPC_CTL_PWR_ARRAY) {
+		tot_nss = le32_to_cpu(tpc_stats->ctl_array.tpc_ctl_pwr.d1);
+		tot_modes = le32_to_cpu(tpc_stats->ctl_array.tpc_ctl_pwr.d2);
+		txbf_on_off = le32_to_cpu(tpc_stats->ctl_array.tpc_ctl_pwr.d3);
+		index_offset1 = txbf_on_off * tot_modes * tot_nss;
+		index_offset2 = tot_modes * tot_nss;
+		index_offset3 = tot_nss;
+
+		tpc_ctl = *(tpc_stats->ctl_array.ctl_pwr_table +
+			    chain_idx * index_offset1 + txbf_enabled * index_offset2
+			    + mode * index_offset3 + stm_idx);
+	} else {
+		tpc_ctl = TPC_MAX;
+		ath12k_warn(ar->ab,
+			    "ctl array for tpc stats not received from fw\n");
+	}
+
+	rates_ctl_min = min_t(s16, rates, tpc_ctl);
+
+	reg_pwr = tpc_stats->max_reg_allowed_power.reg_pwr_array[chain_idx];
+
+	if (reg_pwr < 0)
+		reg_pwr = TPC_INVAL;
+
+	tpc = min_t(s16, rates_ctl_min, reg_pwr);
+
+	/* MODULATION_LIMIT is the maximum power limit,tpc should not exceed
+	 * modulation limit even if min tpc of all three array is greater
+	 * modulation limit
+	 */
+	tpc = min_t(s16, tpc, MODULATION_LIMIT);
+
+out:
+	return tpc;
+}
+
+static u16 ath12k_get_ratecode(u16 pream_idx, u16 nss, u16 mcs_rate)
+{
+	u16 mode_type = ~0;
+
+	/* Below assignments are just for printing purpose only */
+	switch (pream_idx) {
+	case WMI_TPC_PREAM_CCK:
+		mode_type = WMI_RATE_PREAMBLE_CCK;
+		break;
+	case WMI_TPC_PREAM_OFDM:
+		mode_type = WMI_RATE_PREAMBLE_OFDM;
+		break;
+	case WMI_TPC_PREAM_HT20:
+	case WMI_TPC_PREAM_HT40:
+		mode_type = WMI_RATE_PREAMBLE_HT;
+		break;
+	case WMI_TPC_PREAM_VHT20:
+	case WMI_TPC_PREAM_VHT40:
+	case WMI_TPC_PREAM_VHT80:
+	case WMI_TPC_PREAM_VHT160:
+		mode_type = WMI_RATE_PREAMBLE_VHT;
+		break;
+	case WMI_TPC_PREAM_HE20:
+	case WMI_TPC_PREAM_HE40:
+	case WMI_TPC_PREAM_HE80:
+	case WMI_TPC_PREAM_HE160:
+		mode_type = WMI_RATE_PREAMBLE_HE;
+		break;
+	case WMI_TPC_PREAM_EHT20:
+	case WMI_TPC_PREAM_EHT40:
+	case WMI_TPC_PREAM_EHT60:
+	case WMI_TPC_PREAM_EHT80:
+	case WMI_TPC_PREAM_EHT120:
+	case WMI_TPC_PREAM_EHT140:
+	case WMI_TPC_PREAM_EHT160:
+	case WMI_TPC_PREAM_EHT200:
+	case WMI_TPC_PREAM_EHT240:
+	case WMI_TPC_PREAM_EHT280:
+	case WMI_TPC_PREAM_EHT320:
+		mode_type = WMI_RATE_PREAMBLE_EHT;
+		if (mcs_rate == 0 || mcs_rate == 1)
+			mcs_rate += 14;
+		else
+			mcs_rate -= 2;
+		break;
+	default:
+		return mode_type;
+	}
+	return ((mode_type << 8) | ((nss & 0x7) << 5) | (mcs_rate & 0x1F));
+}
+
+static bool ath12k_he_supports_extra_mcs(struct ath12k *ar, int freq)
+{
+	struct ath12k_pdev_cap *cap = &ar->pdev->cap;
+	struct ath12k_band_cap *cap_band;
+	bool extra_mcs_supported;
+
+	if (freq <= ATH12K_2GHZ_MAX_FREQUENCY)
+		cap_band = &cap->band[NL80211_BAND_2GHZ];
+	else if (freq <= ATH12K_5GHZ_MAX_FREQUENCY)
+		cap_band = &cap->band[NL80211_BAND_5GHZ];
+	else
+		cap_band = &cap->band[NL80211_BAND_6GHZ];
+
+	extra_mcs_supported = u32_get_bits(cap_band->he_cap_info[1],
+					   HE_EXTRA_MCS_SUPPORT);
+	return extra_mcs_supported;
+}
+
+static int ath12k_tpc_fill_pream(struct ath12k *ar, char *buf, int buf_len, int len,
+				 enum wmi_tpc_pream_bw pream_bw, u32 max_rix,
+				 int max_nss, int max_rates, int pream_type,
+				 enum wmi_halphy_ctrl_path_stats_id tpc_type,
+				 int rate_idx, int eht_rate_idx)
+{
+	struct wmi_tpc_stats_arg *tpc_stats = ar->debug.tpc_stats;
+	int nss, rates, chains;
+	u8 active_tx_chains;
+	u16 rate_code;
+	s16 tpc;
+
+	static const char *const pream_str[] = {
+		[WMI_TPC_PREAM_CCK]     = "CCK",
+		[WMI_TPC_PREAM_OFDM]    = "OFDM",
+		[WMI_TPC_PREAM_HT20]    = "HT20",
+		[WMI_TPC_PREAM_HT40]    = "HT40",
+		[WMI_TPC_PREAM_VHT20]   = "VHT20",
+		[WMI_TPC_PREAM_VHT40]   = "VHT40",
+		[WMI_TPC_PREAM_VHT80]   = "VHT80",
+		[WMI_TPC_PREAM_VHT160]  = "VHT160",
+		[WMI_TPC_PREAM_HE20]    = "HE20",
+		[WMI_TPC_PREAM_HE40]    = "HE40",
+		[WMI_TPC_PREAM_HE80]    = "HE80",
+		[WMI_TPC_PREAM_HE160]   = "HE160",
+		[WMI_TPC_PREAM_EHT20]   = "EHT20",
+		[WMI_TPC_PREAM_EHT40]   = "EHT40",
+		[WMI_TPC_PREAM_EHT60]   = "EHT60",
+		[WMI_TPC_PREAM_EHT80]   = "EHT80",
+		[WMI_TPC_PREAM_EHT120]   = "EHT120",
+		[WMI_TPC_PREAM_EHT140]   = "EHT140",
+		[WMI_TPC_PREAM_EHT160]   = "EHT160",
+		[WMI_TPC_PREAM_EHT200]   = "EHT200",
+		[WMI_TPC_PREAM_EHT240]   = "EHT240",
+		[WMI_TPC_PREAM_EHT280]   = "EHT280",
+		[WMI_TPC_PREAM_EHT320]   = "EHT320"};
+
+	active_tx_chains = ar->num_tx_chains;
+
+	for (nss = 0; nss < max_nss; nss++) {
+		for (rates = 0; rates < max_rates; rates++, rate_idx++, max_rix++) {
+			/* FW send extra MCS(10&11) for VHT and HE rates,
+			 *  this is not used. Hence skipping it here
+			 */
+			if (pream_type == WMI_RATE_PREAMBLE_VHT &&
+			    rates > ATH12K_VHT_MCS_MAX)
+				continue;
+
+			if (pream_type == WMI_RATE_PREAMBLE_HE &&
+			    rates > ATH12K_HE_MCS_MAX)
+				continue;
+
+			if (pream_type == WMI_RATE_PREAMBLE_EHT &&
+			    rates > ATH12K_EHT_MCS_MAX)
+				continue;
+
+			rate_code = ath12k_get_ratecode(pream_bw, nss, rates);
+			len += scnprintf(buf + len, buf_len - len,
+					 "%d\t %s\t 0x%03x\t", max_rix,
+					 pream_str[pream_bw], rate_code);
+
+			for (chains = 0; chains < active_tx_chains; chains++) {
+				if (nss > chains) {
+					len += scnprintf(buf + len,
+							 buf_len - len,
+							 "\t%s", "NA");
+				} else {
+					tpc = ath12k_tpc_get_rate(ar, tpc_stats,
+								  rate_idx, chains + 1,
+								  rate_code, pream_bw,
+								  tpc_type,
+								  eht_rate_idx);
+
+					if (tpc == TPC_INVAL) {
+						len += scnprintf(buf + len,
+								 buf_len - len, "\tNA");
+					} else {
+						len += scnprintf(buf + len,
+								 buf_len - len, "\t%d",
+								 tpc);
+					}
+				}
+			}
+			len += scnprintf(buf + len, buf_len - len, "\n");
+
+			if (pream_type == WMI_RATE_PREAMBLE_EHT)
+				/*For fetching the next eht rates pwr from rates array2*/
+				++eht_rate_idx;
+		}
+	}
+
+	return len;
+}
+
+static int ath12k_tpc_stats_print(struct ath12k *ar,
+				  struct wmi_tpc_stats_arg *tpc_stats,
+				  char *buf, size_t len,
+				  enum wmi_halphy_ctrl_path_stats_id type)
+{
+	u32 eht_idx = 0, pream_idx = 0, rate_pream_idx = 0, total_rates = 0, max_rix = 0;
+	u32 chan_freq, num_tx_chain, caps, i, j = 1;
+	size_t buf_len = ATH12K_TPC_STATS_BUF_SIZE;
+	u8 nss, active_tx_chains;
+	bool he_ext_mcs;
+	static const char *const type_str[WMI_HALPHY_PDEV_TX_STATS_MAX] = {
+		[WMI_HALPHY_PDEV_TX_SU_STATS]		= "SU",
+		[WMI_HALPHY_PDEV_TX_SUTXBF_STATS]	= "SU WITH TXBF",
+		[WMI_HALPHY_PDEV_TX_MU_STATS]		= "MU",
+		[WMI_HALPHY_PDEV_TX_MUTXBF_STATS]	= "MU WITH TXBF"};
+
+	u8 max_rates[WMI_TPC_PREAM_MAX] = {
+		[WMI_TPC_PREAM_CCK]     = ATH12K_CCK_RATES,
+		[WMI_TPC_PREAM_OFDM]    = ATH12K_OFDM_RATES,
+		[WMI_TPC_PREAM_HT20]    = ATH12K_HT_RATES,
+		[WMI_TPC_PREAM_HT40]    = ATH12K_HT_RATES,
+		[WMI_TPC_PREAM_VHT20]   = ATH12K_VHT_RATES,
+		[WMI_TPC_PREAM_VHT40]   = ATH12K_VHT_RATES,
+		[WMI_TPC_PREAM_VHT80]   = ATH12K_VHT_RATES,
+		[WMI_TPC_PREAM_VHT160]  = ATH12K_VHT_RATES,
+		[WMI_TPC_PREAM_HE20]    = ATH12K_HE_RATES,
+		[WMI_TPC_PREAM_HE40]    = ATH12K_HE_RATES,
+		[WMI_TPC_PREAM_HE80]    = ATH12K_HE_RATES,
+		[WMI_TPC_PREAM_HE160]   = ATH12K_HE_RATES,
+		[WMI_TPC_PREAM_EHT20]   = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT40]   = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT60]   = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT80]   = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT120]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT140]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT160]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT200]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT240]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT280]  = ATH12K_EHT_RATES,
+		[WMI_TPC_PREAM_EHT320]  = ATH12K_EHT_RATES};
+	static const u8 max_nss[WMI_TPC_PREAM_MAX] = {
+		[WMI_TPC_PREAM_CCK]     = ATH12K_NSS_1,
+		[WMI_TPC_PREAM_OFDM]    = ATH12K_NSS_1,
+		[WMI_TPC_PREAM_HT20]    = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_HT40]    = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_VHT20]   = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_VHT40]   = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_VHT80]   = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_VHT160]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_HE20]    = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_HE40]    = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_HE80]    = ATH12K_NSS_8,
+		[WMI_TPC_PREAM_HE160]   = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT20]   = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT40]   = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT60]   = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT80]   = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT120]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT140]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT160]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT200]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT240]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT280]  = ATH12K_NSS_4,
+		[WMI_TPC_PREAM_EHT320]  = ATH12K_NSS_4};
+
+	u16 rate_idx[WMI_TPC_PREAM_MAX] = {}, eht_rate_idx[WMI_TPC_PREAM_MAX] = {};
+	static const u8 pream_type[WMI_TPC_PREAM_MAX] = {
+		[WMI_TPC_PREAM_CCK]     = WMI_RATE_PREAMBLE_CCK,
+		[WMI_TPC_PREAM_OFDM]    = WMI_RATE_PREAMBLE_OFDM,
+		[WMI_TPC_PREAM_HT20]    = WMI_RATE_PREAMBLE_HT,
+		[WMI_TPC_PREAM_HT40]    = WMI_RATE_PREAMBLE_HT,
+		[WMI_TPC_PREAM_VHT20]   = WMI_RATE_PREAMBLE_VHT,
+		[WMI_TPC_PREAM_VHT40]   = WMI_RATE_PREAMBLE_VHT,
+		[WMI_TPC_PREAM_VHT80]   = WMI_RATE_PREAMBLE_VHT,
+		[WMI_TPC_PREAM_VHT160]  = WMI_RATE_PREAMBLE_VHT,
+		[WMI_TPC_PREAM_HE20]    = WMI_RATE_PREAMBLE_HE,
+		[WMI_TPC_PREAM_HE40]    = WMI_RATE_PREAMBLE_HE,
+		[WMI_TPC_PREAM_HE80]    = WMI_RATE_PREAMBLE_HE,
+		[WMI_TPC_PREAM_HE160]   = WMI_RATE_PREAMBLE_HE,
+		[WMI_TPC_PREAM_EHT20]   = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT40]   = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT60]   = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT80]   = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT120]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT140]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT160]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT200]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT240]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT280]  = WMI_RATE_PREAMBLE_EHT,
+		[WMI_TPC_PREAM_EHT320]  = WMI_RATE_PREAMBLE_EHT};
+
+	chan_freq = le32_to_cpu(tpc_stats->tpc_config.chan_freq);
+	num_tx_chain = le32_to_cpu(tpc_stats->tpc_config.num_tx_chain);
+	caps = le32_to_cpu(tpc_stats->tpc_config.caps);
+
+	active_tx_chains = ar->num_tx_chains;
+	he_ext_mcs = ath12k_he_supports_extra_mcs(ar, chan_freq);
+
+	/* mcs 12&13 is sent by FW for certain HWs in rate array, skipping it as
+	 * it is not supported
+	 */
+	if (he_ext_mcs) {
+		for (i = WMI_TPC_PREAM_HE20; i <= WMI_TPC_PREAM_HE160; ++i)
+			max_rates[i] = ATH12K_HE_RATES;
+	}
+
+	if (type == WMI_HALPHY_PDEV_TX_MU_STATS ||
+	    type == WMI_HALPHY_PDEV_TX_MUTXBF_STATS) {
+		pream_idx = WMI_TPC_PREAM_VHT20;
+
+		for (i = WMI_TPC_PREAM_CCK; i <= WMI_TPC_PREAM_HT40; ++i)
+			max_rix += max_nss[i] * max_rates[i];
+	}
+	/* Enumerate all the rate indices */
+	for (i = rate_pream_idx + 1; i < WMI_TPC_PREAM_MAX; i++) {
+		nss = (max_nss[i - 1] < num_tx_chain ?
+		       max_nss[i - 1] : num_tx_chain);
+
+		rate_idx[i] = rate_idx[i - 1] + max_rates[i - 1] * nss;
+
+		if (pream_type[i] == WMI_RATE_PREAMBLE_EHT) {
+			eht_rate_idx[j] = eht_rate_idx[j - 1] + max_rates[i] * nss;
+			++j;
+		}
+	}
+
+	for (i = 0; i < WMI_TPC_PREAM_MAX; i++) {
+		nss = (max_nss[i] < num_tx_chain ?
+		       max_nss[i] : num_tx_chain);
+		total_rates += max_rates[i] * nss;
+	}
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "No.of rates-%d\n", total_rates);
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "**************** %s ****************\n",
+			 type_str[type]);
+	len += scnprintf(buf + len, buf_len - len,
+			 "\t\t\t\tTPC values for Active chains\n");
+	len += scnprintf(buf + len, buf_len - len,
+			 "Rate idx Preamble Rate code");
+
+	for (i = 1; i <= active_tx_chains; ++i) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "\t%d-Chain", i);
+	}
+
+	len += scnprintf(buf + len, buf_len - len, "\n");
+	for (i = pream_idx; i < WMI_TPC_PREAM_MAX; i++) {
+		if (chan_freq <= 2483) {
+			if (i == WMI_TPC_PREAM_VHT80 ||
+			    i == WMI_TPC_PREAM_VHT160 ||
+			    i == WMI_TPC_PREAM_HE80 ||
+			    i == WMI_TPC_PREAM_HE160 ||
+			    (i >= WMI_TPC_PREAM_EHT60 &&
+			     i <= WMI_TPC_PREAM_EHT320)) {
+				max_rix += max_nss[i] * max_rates[i];
+				continue;
+			}
+		} else {
+			if (i == WMI_TPC_PREAM_CCK) {
+				max_rix += max_rates[i];
+				continue;
+			}
+		}
+
+		nss = (max_nss[i] < ar->num_tx_chains ? max_nss[i] : ar->num_tx_chains);
+
+		if (!(caps &
+		    (1 << ATH12K_TPC_STATS_SUPPORT_BE_PUNC))) {
+			if (i == WMI_TPC_PREAM_EHT60 || i == WMI_TPC_PREAM_EHT120 ||
+			    i == WMI_TPC_PREAM_EHT140 || i == WMI_TPC_PREAM_EHT200 ||
+			    i == WMI_TPC_PREAM_EHT240 || i == WMI_TPC_PREAM_EHT280) {
+				max_rix += max_nss[i] * max_rates[i];
+				continue;
+			}
+		}
+
+		len = ath12k_tpc_fill_pream(ar, buf, buf_len, len, i, max_rix, nss,
+					    max_rates[i], pream_type[i],
+					    type, rate_idx[i], eht_rate_idx[eht_idx]);
+
+		if (pream_type[i] == WMI_RATE_PREAMBLE_EHT)
+			/*For fetch the next index eht rates from rates array2*/
+			++eht_idx;
+
+		max_rix += max_nss[i] * max_rates[i];
+	}
+	return len;
+}
+
+static void ath12k_tpc_stats_fill(struct ath12k *ar,
+				  struct wmi_tpc_stats_arg *tpc_stats,
+				  char *buf)
+{
+	size_t buf_len = ATH12K_TPC_STATS_BUF_SIZE;
+	struct wmi_tpc_config_params *tpc;
+	size_t len = 0;
+
+	if (!tpc_stats) {
+		ath12k_warn(ar->ab, "failed to find tpc stats\n");
+		return;
+	}
+
+	spin_lock_bh(&ar->data_lock);
+
+	tpc = &tpc_stats->tpc_config;
+	len += scnprintf(buf + len, buf_len - len, "\n");
+	len += scnprintf(buf + len, buf_len - len,
+			 "*************** TPC config **************\n");
+	len += scnprintf(buf + len, buf_len - len,
+			 "* powers are in 0.25 dBm steps\n");
+	len += scnprintf(buf + len, buf_len - len,
+			 "reg domain-%d\t\tchan freq-%d\n",
+			 tpc->reg_domain, tpc->chan_freq);
+	len += scnprintf(buf + len, buf_len - len,
+			 "power limit-%d\t\tmax reg-domain Power-%d\n",
+			 le32_to_cpu(tpc->twice_max_reg_power) / 2, tpc->power_limit);
+	len += scnprintf(buf + len, buf_len - len,
+			 "No.of tx chain-%d\t",
+			 ar->num_tx_chains);
+
+	ath12k_tpc_stats_print(ar, tpc_stats, buf, len,
+			       ar->debug.tpc_stats_type);
+
+	spin_unlock_bh(&ar->data_lock);
+}
+
 static int ath12k_open_tpc_stats(struct inode *inode, struct file *file)
 {
 	struct ath12k *ar = inode->i_private;
@@ -91,6 +699,7 @@ static int ath12k_open_tpc_stats(struct inode *inode, struct file *file)
 		return -ETIMEDOUT;
 	}
 
+	ath12k_tpc_stats_fill(ar, ar->debug.tpc_stats, buf);
 	file->private_data = no_free_ptr(buf);
 
 	spin_lock_bh(&ar->data_lock);
@@ -125,6 +734,12 @@ static const struct file_operations fops_tpc_stats = {
 	.llseek = default_llseek,
 };
 
+static const struct file_operations fops_tpc_stats_type = {
+	.write = ath12k_write_tpc_stats_type,
+	.open = simple_open,
+	.llseek = default_llseek,
+};
+
 void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
 	bool dput_needed;
@@ -563,6 +1178,9 @@ void ath12k_debugfs_register(struct ath12k *ar)
 
 	debugfs_create_file("tpc_stats", 0400, ar->debug.debugfs_pdev, ar,
 			    &fops_tpc_stats);
+	debugfs_create_file("tpc_stats_type", 0200, ar->debug.debugfs_pdev,
+			    ar, &fops_tpc_stats_type);
+	init_completion(&ar->debug.tpc_complete);
 
 	ath12k_debugfs_htt_stats_register(ar);
 	ath12k_debugfs_fw_stats_register(ar);
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index 25b5219ffe49c..fb85113fc6258 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -16,11 +16,88 @@ void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 				     struct ath12k_fw_stats *stats);
 void ath12k_debugfs_fw_stats_reset(struct ath12k *ar);
 
-#define TPC_STATS_WAIT_TIME		(1 * HZ)
-#define TPC_STATS_TOT_ROW		700
-#define TPC_STATS_TOT_COLUMN		100
+#define ATH12K_CCK_RATES			4
+#define ATH12K_OFDM_RATES			8
+#define ATH12K_HT_RATES				8
+#define ATH12K_VHT_RATES			12
+#define ATH12K_HE_RATES				12
+#define ATH12K_HE_RATES_WITH_EXTRA_MCS		14
+#define ATH12K_EHT_RATES			16
+#define HE_EXTRA_MCS_SUPPORT			GENMASK(31, 16)
+#define ATH12K_NSS_1				1
+#define ATH12K_NSS_4				4
+#define ATH12K_NSS_8				8
+#define ATH12K_HW_NSS(_rcode)			(((_rcode) >> 5) & 0x7)
+#define TPC_STATS_WAIT_TIME			(1 * HZ)
+#define MAX_TPC_PREAM_STR_LEN			7
+#define TPC_INVAL				-128
+#define TPC_MAX					127
+#define TPC_STATS_WAIT_TIME			(1 * HZ)
+#define TPC_STATS_TOT_ROW			700
+#define TPC_STATS_TOT_COLUMN			100
+#define MODULATION_LIMIT			126
+
 #define ATH12K_TPC_STATS_BUF_SIZE	(TPC_STATS_TOT_ROW * TPC_STATS_TOT_COLUMN)
 
+enum wmi_tpc_pream_bw {
+	WMI_TPC_PREAM_CCK,
+	WMI_TPC_PREAM_OFDM,
+	WMI_TPC_PREAM_HT20,
+	WMI_TPC_PREAM_HT40,
+	WMI_TPC_PREAM_VHT20,
+	WMI_TPC_PREAM_VHT40,
+	WMI_TPC_PREAM_VHT80,
+	WMI_TPC_PREAM_VHT160,
+	WMI_TPC_PREAM_HE20,
+	WMI_TPC_PREAM_HE40,
+	WMI_TPC_PREAM_HE80,
+	WMI_TPC_PREAM_HE160,
+	WMI_TPC_PREAM_EHT20,
+	WMI_TPC_PREAM_EHT40,
+	WMI_TPC_PREAM_EHT60,
+	WMI_TPC_PREAM_EHT80,
+	WMI_TPC_PREAM_EHT120,
+	WMI_TPC_PREAM_EHT140,
+	WMI_TPC_PREAM_EHT160,
+	WMI_TPC_PREAM_EHT200,
+	WMI_TPC_PREAM_EHT240,
+	WMI_TPC_PREAM_EHT280,
+	WMI_TPC_PREAM_EHT320,
+	WMI_TPC_PREAM_MAX
+};
+
+enum ath12k_debug_tpc_stats_ctl_mode {
+	ATH12K_TPC_STATS_CTL_MODE_LEGACY_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HT_VHT20_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HE_EHT20_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HT_VHT40_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HE_EHT40_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_VHT80_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HE_EHT80_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_VHT160_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HE_EHT160_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HE_EHT320_5GHZ_6GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_CCK_2GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_LEGACY_2GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HT20_2GHZ,
+	ATH12K_TPC_STATS_CTL_MODE_HT40_2GHZ,
+
+	ATH12K_TPC_STATS_CTL_MODE_EHT80_SU_PUNC20 = 23,
+	ATH12K_TPC_STATS_CTL_MODE_EHT160_SU_PUNC20,
+	ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC40,
+	ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC80,
+	ATH12K_TPC_STATS_CTL_MODE_EHT320_SU_PUNC120
+};
+
+enum ath12k_debug_tpc_stats_support_modes {
+	ATH12K_TPC_STATS_SUPPORT_160 = 0,
+	ATH12K_TPC_STATS_SUPPORT_320,
+	ATH12K_TPC_STATS_SUPPORT_AX,
+	ATH12K_TPC_STATS_SUPPORT_AX_EXTRA_MCS,
+	ATH12K_TPC_STATS_SUPPORT_BE,
+	ATH12K_TPC_STATS_SUPPORT_BE_PUNC,
+};
+
 #else
 static inline void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
diff --git a/drivers/net/wireless/ath/ath12k/reg.h b/drivers/net/wireless/ath/ath12k/reg.h
index 29c7ec3260daf..75f80df2aa0c7 100644
--- a/drivers/net/wireless/ath/ath12k/reg.h
+++ b/drivers/net/wireless/ath/ath12k/reg.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_REG_H
@@ -13,6 +13,9 @@
 struct ath12k_base;
 struct ath12k;
 
+#define ATH12K_2GHZ_MAX_FREQUENCY	2495
+#define ATH12K_5GHZ_MAX_FREQUENCY	5920
+
 /* DFS regdomains supported by Firmware */
 enum ath12k_dfs_region {
 	ATH12K_DFS_REG_UNSET,
diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
index e8a4789b6ae1a..ca078718bcb69 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.h
+++ b/drivers/net/wireless/ath/ath12k/wmi.h
@@ -4641,6 +4641,7 @@ enum wmi_rate_preamble {
 	WMI_RATE_PREAMBLE_HT,
 	WMI_RATE_PREAMBLE_VHT,
 	WMI_RATE_PREAMBLE_HE,
+	WMI_RATE_PREAMBLE_EHT,
 };
 
 /**

From fcf5d353b09b3fc212ab24b89ef23a7a8f7b308e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 22 Jan 2025 07:52:44 +0100
Subject: [PATCH 0121/2753] phy: rockchip: fix Kconfig dependency more

A previous patch ensured that USB Type C connector support is enabled,
but it is still possible to build the phy driver without enabling
CONFIG_USB (host support) or CONFIG_USB_GADGET (device support), and
in that case the common helper functions are unavailable:

aarch64-linux-ld: drivers/phy/rockchip/phy-rockchip-usbdp.o: in function `rk_udphy_probe':
phy-rockchip-usbdp.c:(.text+0xe74): undefined reference to `usb_get_maximum_speed'

Select CONFIG_USB_COMMON directly here, like we do in some other phy
drivers, to make sure this is available even when actual USB support
is disabled or in a loadable module that cannot be reached from a
built-in phy driver.

Fixes: 9c79b779643e ("phy: rockchip: fix CONFIG_TYPEC dependency")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Reviewed-by: Heiko Stuebner <heiko@sntech.de>
Link: https://lore.kernel.org/r/20250122065249.1390081-1-arnd@kernel.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
index 2f7a05f21dc59..dcb8e1628632e 100644
--- a/drivers/phy/rockchip/Kconfig
+++ b/drivers/phy/rockchip/Kconfig
@@ -125,6 +125,7 @@ config PHY_ROCKCHIP_USBDP
 	depends on ARCH_ROCKCHIP && OF
 	depends on TYPEC
 	select GENERIC_PHY
+	select USB_COMMON
 	help
 	  Enable this to support the Rockchip USB3.0/DP combo PHY with
 	  Samsung IP block. This is required for USB3 support on RK3588.

From 3126ea9be66b53e607f87f067641ba724be24181 Mon Sep 17 00:00:00 2001
From: Chukun Pan <amadeus@jmu.edu.cn>
Date: Mon, 6 Jan 2025 18:00:01 +0800
Subject: [PATCH 0122/2753] phy: rockchip: naneng-combphy: compatible reset
 with old DT

The device tree of RK3568 did not specify reset-names before.
So add fallback to old behaviour to be compatible with old DT.

Fixes: fbcbffbac994 ("phy: rockchip: naneng-combphy: fix phy reset")
Cc: Jianfeng Liu <liujianfeng1994@gmail.com>
Signed-off-by: Chukun Pan <amadeus@jmu.edu.cn>
Reviewed-by: Jonas Karlman <jonas@kwiboo.se>
Link: https://lore.kernel.org/r/20250106100001.1344418-2-amadeus@jmu.edu.cn
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/rockchip/phy-rockchip-naneng-combphy.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
index a1532ef8bbe9d..8c3ce57f89151 100644
--- a/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
+++ b/drivers/phy/rockchip/phy-rockchip-naneng-combphy.c
@@ -324,7 +324,10 @@ static int rockchip_combphy_parse_dt(struct device *dev, struct rockchip_combphy
 
 	priv->ext_refclk = device_property_present(dev, "rockchip,ext-refclk");
 
-	priv->phy_rst = devm_reset_control_get(dev, "phy");
+	priv->phy_rst = devm_reset_control_get_exclusive(dev, "phy");
+	/* fallback to old behaviour */
+	if (PTR_ERR(priv->phy_rst) == -ENOENT)
+		priv->phy_rst = devm_reset_control_array_get_exclusive(dev);
 	if (IS_ERR(priv->phy_rst))
 		return dev_err_probe(dev, PTR_ERR(priv->phy_rst), "failed to get phy reset\n");
 

From 1b133129ad6b28186214259af3bd5fc651a85509 Mon Sep 17 00:00:00 2001
From: E Shattow <e@freeshell.de>
Date: Mon, 9 Dec 2024 20:19:56 -0800
Subject: [PATCH 0123/2753] riscv: dts: starfive: Fix a typo in StarFive JH7110
 pin function definitions

Fix a typo in StarFive JH7110 pin function definitions for GPOUT_SYS_SDIO1_DATA4

Fixes: e22f09e598d12 ("riscv: dts: starfive: Add StarFive JH7110 pin function definitions")
Signed-off-by: E Shattow <e@freeshell.de>
Acked-by: Hal Feng <hal.feng@starfivetech.com>
CC: stable@vger.kernel.org
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
---
 arch/riscv/boot/dts/starfive/jh7110-pinfunc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
index 256de17f52611..ae49c908e7fb3 100644
--- a/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
+++ b/arch/riscv/boot/dts/starfive/jh7110-pinfunc.h
@@ -89,7 +89,7 @@
 #define GPOUT_SYS_SDIO1_DATA1			59
 #define GPOUT_SYS_SDIO1_DATA2			60
 #define GPOUT_SYS_SDIO1_DATA3			61
-#define GPOUT_SYS_SDIO1_DATA4			63
+#define GPOUT_SYS_SDIO1_DATA4			62
 #define GPOUT_SYS_SDIO1_DATA5			63
 #define GPOUT_SYS_SDIO1_DATA6			64
 #define GPOUT_SYS_SDIO1_DATA7			65

From 546d98393abcf2f841e61163d95ed21fde346cc1 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Mon, 3 Feb 2025 14:59:23 +0200
Subject: [PATCH 0124/2753] bonding: delete always true device check

XFRM API makes sure that xs->xso.dev is valid in all XFRM offload
callbacks. There is no need to check it again.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/0b2f8f5f09701bb43bbd83b94bfe5cb506b57adc.1738587150.git.leon@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index e45bba240cbcd..f6d0628a36d9f 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -432,9 +432,6 @@ static struct net_device *bond_ipsec_dev(struct xfrm_state *xs)
 	struct bonding *bond;
 	struct slave *slave;
 
-	if (!bond_dev)
-		return NULL;
-
 	bond = netdev_priv(bond_dev);
 	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
 		return NULL;

From a064068bb6be51ed54f435fe7314c057f9eeb020 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 3 Feb 2025 15:11:52 +0000
Subject: [PATCH 0125/2753] neighbour: remove neigh_parms_destroy()

neigh_parms_destroy() is a simple kfree(), no need for
a forward declaration.

neigh_parms_put() can instead call kfree() directly.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250203151152.3163876-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/neighbour.c | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index 89656d180bc60..73260ca0fc223 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -832,12 +832,10 @@ static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
 	return -ENOENT;
 }
 
-static void neigh_parms_destroy(struct neigh_parms *parms);
-
 static inline void neigh_parms_put(struct neigh_parms *parms)
 {
 	if (refcount_dec_and_test(&parms->refcnt))
-		neigh_parms_destroy(parms);
+		kfree(parms);
 }
 
 /*
@@ -1713,11 +1711,6 @@ void neigh_parms_release(struct neigh_table *tbl, struct neigh_parms *parms)
 }
 EXPORT_SYMBOL(neigh_parms_release);
 
-static void neigh_parms_destroy(struct neigh_parms *parms)
-{
-	kfree(parms);
-}
-
 static struct lock_class_key neigh_table_proxy_queue_class;
 
 static struct neigh_table __rcu *neigh_tables[NEIGH_NR_TABLES] __read_mostly;

From ac335826115dbbe10e536f43cf6090957c21bdc8 Mon Sep 17 00:00:00 2001
From: Ninad Palsule <ninad@linux.ibm.com>
Date: Mon, 3 Feb 2025 09:12:55 -0600
Subject: [PATCH 0126/2753] dt-bindings: net: faraday,ftgmac100: Add phys mode

Aspeed device supports rgmii, rgmii-id, rgmii-rxid, rgmii-txid so
document them.

Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Ninad Palsule <ninad@linux.ibm.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250203151306.276358-2-ninad@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml b/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
index 9bcbacb6640db..55d6a8379025b 100644
--- a/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
+++ b/Documentation/devicetree/bindings/net/faraday,ftgmac100.yaml
@@ -44,6 +44,9 @@ properties:
   phy-mode:
     enum:
       - rgmii
+      - rgmii-id
+      - rgmii-rxid
+      - rgmii-txid
       - rmii
 
   phy-handle: true

From 185b1d53ea544a348dca679daefa4abd54d1322b Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Mon, 3 Feb 2025 19:53:24 +0200
Subject: [PATCH 0127/2753] net: qed: fix typos

There are some typos in comments/messages:
 - Valiate -> Validate
 - acceptible -> acceptable
 - acces -> access
 - relased -> released

Fix them via codespell.

Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250203175419.4146-1-algonell@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/qlogic/qed/qed_sriov.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
index fa167b1aa0190..5222a035fd198 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c
@@ -3033,7 +3033,7 @@ static void qed_iov_vf_mbx_vport_update(struct qed_hwfn *p_hwfn,
 	u16 length;
 	int rc;
 
-	/* Valiate PF can send such a request */
+	/* Validate PF can send such a request */
 	if (!vf->vport_instance) {
 		DP_VERBOSE(p_hwfn,
 			   QED_MSG_IOV,
@@ -3312,7 +3312,7 @@ static void qed_iov_vf_mbx_ucast_filter(struct qed_hwfn *p_hwfn,
 		goto out;
 	}
 
-	/* Determine if the unicast filtering is acceptible by PF */
+	/* Determine if the unicast filtering is acceptable by PF */
 	if ((p_bulletin->valid_bitmap & BIT(VLAN_ADDR_FORCED)) &&
 	    (params.type == QED_FILTER_VLAN ||
 	     params.type == QED_FILTER_MAC_VLAN)) {
@@ -3729,7 +3729,7 @@ qed_iov_execute_vf_flr_cleanup(struct qed_hwfn *p_hwfn,
 
 		rc = qed_iov_enable_vf_access(p_hwfn, p_ptt, p_vf);
 		if (rc) {
-			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] acces\n",
+			DP_ERR(p_hwfn, "Failed to re-enable VF[%d] access\n",
 			       vfid);
 			return rc;
 		}
@@ -4480,7 +4480,7 @@ int qed_sriov_disable(struct qed_dev *cdev, bool pci_enabled)
 		struct qed_ptt *ptt = qed_ptt_acquire(hwfn);
 
 		/* Failure to acquire the ptt in 100g creates an odd error
-		 * where the first engine has already relased IOV.
+		 * where the first engine has already released IOV.
 		 */
 		if (!ptt) {
 			DP_ERR(hwfn, "Failed to acquire ptt\n");

From 2cf424f5ac01682c93e3decfddee6282b7552f50 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Feb 2025 18:52:29 +0000
Subject: [PATCH 0128/2753] mlx4: Remove unused functions

The last use of mlx4_find_cached_mac() was removed in 2014 by
commit 2f5bb473681b ("mlx4: Add ref counting to port MAC table for RoCE")

mlx4_zone_free_entries() was added in 2014 by
commit 7a89399ffad7 ("net/mlx4: Add mlx4_bitmap zone allocator")
but hasn't been used. (The _unique version is used)

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250203185229.204279-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/alloc.c | 22 ----------------------
 drivers/net/ethernet/mellanox/mlx4/mlx4.h  |  6 ------
 drivers/net/ethernet/mellanox/mlx4/port.c  | 20 --------------------
 include/linux/mlx4/device.h                |  1 -
 4 files changed, 49 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index b330020dc0d67..598df63518c55 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -526,28 +526,6 @@ u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int coun
 	return res;
 }
 
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
-{
-	struct mlx4_zone_entry *zone;
-	int res = 0;
-
-	spin_lock(&zones->lock);
-
-	zone = __mlx4_find_zone_by_uid(zones, uid);
-
-	if (NULL == zone) {
-		res = -1;
-		goto out;
-	}
-
-	__mlx4_free_from_zone(zone, obj, count);
-
-out:
-	spin_unlock(&zones->lock);
-
-	return res;
-}
-
 u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
 {
 	struct mlx4_zone_entry *zone;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index d7d856d1758a3..b213094ea30f3 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -1478,12 +1478,6 @@ void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
 u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
 			    int align, u32 skip_mask, u32 *puid);
 
-/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
- * <zones>.
- */
-u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
-			   u32 uid, u32 obj, u32 count);
-
 /* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
  * specifying the uid when freeing an object, zone allocator could figure it by
  * itself. Other parameters are similar to mlx4_zone_free.
diff --git a/drivers/net/ethernet/mellanox/mlx4/port.c b/drivers/net/ethernet/mellanox/mlx4/port.c
index 4e43f4a7d2466..e3d0b13c1610e 100644
--- a/drivers/net/ethernet/mellanox/mlx4/port.c
+++ b/drivers/net/ethernet/mellanox/mlx4/port.c
@@ -147,26 +147,6 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
-{
-	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
-	struct mlx4_mac_table *table = &info->mac_table;
-	int i;
-
-	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
-		if (!table->refs[i])
-			continue;
-
-		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
-			*idx = i;
-			return 0;
-		}
-	}
-
-	return -ENOENT;
-}
-EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
-
 static bool mlx4_need_mf_bond(struct mlx4_dev *dev)
 {
 	int i, num_eth_ports = 0;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 27f42f713c891..87edb7a8173b1 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1415,7 +1415,6 @@ int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port,
 				      bool *vlan_offload_disabled);
 void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
 				       struct _rule_hw *eth_header);
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);

From 15c51f17bdc46418b2e1b2b7a21a9a3036da6bae Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Feb 2025 18:59:58 +0000
Subject: [PATCH 0129/2753] net/mlx5: Remove unused mlx5dr_domain_sync

mlx5dr_domain_sync() was added in 2019 by
commit 70605ea545e8 ("net/mlx5: DR, Expose APIs for direct rule managing")
but hasn't been used.

Remove it.

mlx5dr_domain_sync() was the only user of
mlx5dr_send_ring_force_drain().
Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250203185958.204794-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mlx5/core/steering/sws/dr_domain.c        | 24 --------------
 .../mellanox/mlx5/core/steering/sws/dr_send.c | 33 -------------------
 .../mlx5/core/steering/sws/dr_types.h         |  1 -
 .../mellanox/mlx5/core/steering/sws/mlx5dr.h  |  2 --
 4 files changed, 60 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
index 60cb4527588a5..65740bb68b09b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_domain.c
@@ -516,30 +516,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type)
 	return NULL;
 }
 
-/* Assure synchronization of the device steering tables with updates made by SW
- * insertion.
- */
-int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags)
-{
-	int ret = 0;
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) {
-		mlx5dr_domain_lock(dmn);
-		ret = mlx5dr_send_ring_force_drain(dmn);
-		mlx5dr_domain_unlock(dmn);
-		if (ret) {
-			mlx5dr_err(dmn, "Force drain failed flags: %d, ret: %d\n",
-				   flags, ret);
-			return ret;
-		}
-	}
-
-	if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW)
-		ret = mlx5dr_cmd_sync_steering(dmn->mdev);
-
-	return ret;
-}
-
 int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn)
 {
 	if (WARN_ON_ONCE(refcount_read(&dmn->refcount) > 1))
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
index f57c84e5128bc..4fd4e8483382c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_send.c
@@ -1331,36 +1331,3 @@ void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 	kfree(send_ring->sync_buff);
 	kfree(send_ring);
 }
-
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn)
-{
-	struct mlx5dr_send_ring *send_ring = dmn->send_ring;
-	struct postsend_info send_info = {};
-	u8 data[DR_STE_SIZE];
-	int num_of_sends_req;
-	int ret;
-	int i;
-
-	/* Sending this amount of requests makes sure we will get drain */
-	num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2;
-
-	/* Send fake requests forcing the last to be signaled */
-	send_info.write.addr = (uintptr_t)data;
-	send_info.write.length = DR_STE_SIZE;
-	send_info.write.lkey = 0;
-	/* Using the sync_mr in order to write/read */
-	send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr;
-	send_info.rkey = send_ring->sync_mr->mkey;
-
-	for (i = 0; i < num_of_sends_req; i++) {
-		ret = dr_postsend_icm_data(dmn, &send_info);
-		if (ret)
-			return ret;
-	}
-
-	spin_lock(&send_ring->lock);
-	ret = dr_handle_pending_wc(dmn, send_ring);
-	spin_unlock(&send_ring->lock);
-
-	return ret;
-}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
index 7618c6147f866..cc328292bf84a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_types.h
@@ -1473,7 +1473,6 @@ struct mlx5dr_send_ring {
 int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn);
 void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn,
 			   struct mlx5dr_send_ring *send_ring);
-int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn);
 int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn,
 			     struct mlx5dr_ste *ste,
 			     u8 *data,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
index 0bb3724c10c26..fc8a2169d1a13 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/mlx5dr.h
@@ -45,8 +45,6 @@ mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type);
 
 int mlx5dr_domain_destroy(struct mlx5dr_domain *domain);
 
-int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags);
-
 void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn,
 			    struct mlx5dr_domain *peer_dmn,
 			    u16 peer_vhca_id);

From 626b36727609e453fb3c9fd172e44cb67f39279e Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Feb 2025 19:01:41 +0000
Subject: [PATCH 0130/2753] mlxsw: spectrum_router: Remove unused functions

mlxsw_sp_ipip_lb_ul_vr_id() has been unused since 2020's
commit acde33bf7319 ("mlxsw: spectrum_router: Reduce
mlxsw_sp_ipip_fib_entry_op_gre4()")

mlxsw_sp_rif_exists() has been unused since 2023's
commit 49c3a615d382 ("mlxsw: spectrum_router: Replay MACVLANs when RIF is
made")

mlxsw_sp_rif_vid() has been unused since 2023's
commit a5b52692e693 ("mlxsw: spectrum_switchdev: Manage RIFs on PVID
change")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250203190141.204951-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |  3 --
 .../ethernet/mellanox/mlxsw/spectrum_router.c | 48 -------------------
 .../ethernet/mellanox/mlxsw/spectrum_router.h |  1 -
 3 files changed, 52 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index b10f80fc651b0..fa7082ee51839 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -754,9 +754,6 @@ void
 mlxsw_sp_port_vlan_router_leave(struct mlxsw_sp_port_vlan *mlxsw_sp_port_vlan);
 void mlxsw_sp_rif_destroy_by_dev(struct mlxsw_sp *mlxsw_sp,
 				 struct net_device *dev);
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev);
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev);
 u16 mlxsw_sp_router_port(const struct mlxsw_sp *mlxsw_sp);
 int mlxsw_sp_router_nve_promote_decap(struct mlxsw_sp *mlxsw_sp, u32 ul_tb_id,
 				      enum mlxsw_sp_l3proto ul_proto,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 7d6d859cef3f9..464821dd492da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -8184,41 +8184,6 @@ mlxsw_sp_rif_find_by_dev(const struct mlxsw_sp *mlxsw_sp,
 	return NULL;
 }
 
-bool mlxsw_sp_rif_exists(struct mlxsw_sp *mlxsw_sp,
-			 const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	mutex_unlock(&mlxsw_sp->router->lock);
-
-	return rif;
-}
-
-u16 mlxsw_sp_rif_vid(struct mlxsw_sp *mlxsw_sp, const struct net_device *dev)
-{
-	struct mlxsw_sp_rif *rif;
-	u16 vid = 0;
-
-	mutex_lock(&mlxsw_sp->router->lock);
-	rif = mlxsw_sp_rif_find_by_dev(mlxsw_sp, dev);
-	if (!rif)
-		goto out;
-
-	/* We only return the VID for VLAN RIFs. Otherwise we return an
-	 * invalid value (0).
-	 */
-	if (rif->ops->type != MLXSW_SP_RIF_TYPE_VLAN)
-		goto out;
-
-	vid = mlxsw_sp_fid_8021q_vid(rif->fid);
-
-out:
-	mutex_unlock(&mlxsw_sp->router->lock);
-	return vid;
-}
-
 static int mlxsw_sp_router_rif_disable(struct mlxsw_sp *mlxsw_sp, u16 rif)
 {
 	char ritr_pl[MLXSW_REG_RITR_LEN];
@@ -8417,19 +8382,6 @@ u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 	return lb_rif->common.rif_index;
 }
 
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
-{
-	struct net_device *dev = mlxsw_sp_rif_dev(&lb_rif->common);
-	u32 ul_tb_id = mlxsw_sp_ipip_dev_ul_tb_id(dev);
-	struct mlxsw_sp_vr *ul_vr;
-
-	ul_vr = mlxsw_sp_vr_get(lb_rif->common.mlxsw_sp, ul_tb_id, NULL);
-	if (WARN_ON(IS_ERR(ul_vr)))
-		return 0;
-
-	return ul_vr->id;
-}
-
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif)
 {
 	return lb_rif->ul_rif_id;
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
index 0432c7cc6b07a..313efab5c324c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.h
@@ -90,7 +90,6 @@ struct mlxsw_sp_ipip_entry;
 struct mlxsw_sp_rif *mlxsw_sp_rif_by_index(const struct mlxsw_sp *mlxsw_sp,
 					   u16 rif_index);
 u16 mlxsw_sp_ipip_lb_rif_index(const struct mlxsw_sp_rif_ipip_lb *rif);
-u16 mlxsw_sp_ipip_lb_ul_vr_id(const struct mlxsw_sp_rif_ipip_lb *rif);
 u16 mlxsw_sp_ipip_lb_ul_rif_id(const struct mlxsw_sp_rif_ipip_lb *lb_rif);
 u32 mlxsw_sp_ipip_dev_ul_tb_id(const struct net_device *ol_dev);
 int mlxsw_sp_rif_dev_ifindex(const struct mlxsw_sp_rif *rif);

From b565a8c750ef9d9d9e10d0fee17f4bf297be0e5a Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 3 Feb 2025 18:33:43 +0000
Subject: [PATCH 0131/2753] cavium/liquidio: Remove unused lio_get_device_id

lio_get_device_id() has been unused since 2018's
commit 64fecd3ec512 ("liquidio: remove obsolete functions and data
structures")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250203183343.193691-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/cavium/liquidio/octeon_device.c | 16 ----------------
 .../net/ethernet/cavium/liquidio/octeon_device.h |  7 -------
 2 files changed, 23 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
index 6b6cb73482d7f..1753bb87dfbd9 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c
@@ -1433,22 +1433,6 @@ int octeon_wait_for_ddr_init(struct octeon_device *oct, u32 *timeout)
 }
 EXPORT_SYMBOL_GPL(octeon_wait_for_ddr_init);
 
-/* Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev)
-{
-	struct octeon_device *octeon_dev = (struct octeon_device *)dev;
-	u32 i;
-
-	for (i = 0; i < MAX_OCTEON_DEVICES; i++)
-		if (octeon_device[i] == octeon_dev)
-			return octeon_dev->octeon_id;
-	return -1;
-}
-
 void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq)
 {
 	u64 instr_cnt;
diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
index d26364c2ac81c..19344b21f8fb9 100644
--- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h
+++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h
@@ -705,13 +705,6 @@ octeon_get_dispatch(struct octeon_device *octeon_dev, u16 opcode,
  */
 struct octeon_device *lio_get_device(u32 octeon_id);
 
-/** Get the octeon id assigned to the octeon device passed as argument.
- *  This function is exported to other modules.
- *  @param dev - octeon device pointer passed as a void *.
- *  @return octeon device id
- */
-int lio_get_device_id(void *dev);
-
 /** Read windowed register.
  *  @param  oct   -  pointer to the Octeon device.
  *  @param  addr  -  Address of the register to read.

From c3a392bdd31adc474f1009ee85c13fdd01fe800d Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:09 +0100
Subject: [PATCH 0132/2753] ice: count combined queues using Rx/Tx count

Previous implementation assumes that there is 1:1 matching between
vectors and queues. It isn't always true.

Get minimum value from Rx/Tx queues to determine combined queues number.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ethtool.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index f241493a6ac88..6bbb304ad9ab7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3817,8 +3817,7 @@ static u32 ice_get_combined_cnt(struct ice_vsi *vsi)
 	ice_for_each_q_vector(vsi, q_idx) {
 		struct ice_q_vector *q_vector = vsi->q_vectors[q_idx];
 
-		if (q_vector->rx.rx_ring && q_vector->tx.tx_ring)
-			combined++;
+		combined += min(q_vector->num_ring_tx, q_vector->num_ring_rx);
 	}
 
 	return combined;

From 9dd05df8403bda5b68178b795c554b3940628bb6 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Feb 2025 13:58:16 -0800
Subject: [PATCH 0133/2753] net: warn if NAPI instance wasn't shut down

Drivers should always disable a NAPI instance before removing it.
If they don't the instance may be queued for polling.
Since commit 86e25f40aa1e ("net: napi: Add napi_config")
we also remove the NAPI from the busy polling hash table
in napi_disable(), so not disabling would leave a stale
entry there.

Use of busy polling is relatively uncommon so bugs may be lurking
in the drivers. Add an explicit warning.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250203215816.1294081-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index c0021cbd28fc1..2b141f20b13b5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7071,6 +7071,9 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state))
 		return;
 
+	/* Make sure NAPI is disabled (or was never enabled). */
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
+
 	if (napi->config) {
 		napi->index = -1;
 		napi->config = NULL;

From 33b565fa2bc0af2d5b23b0fd954460b0b25b9280 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 4 Feb 2025 12:40:49 +1030
Subject: [PATCH 0134/2753] net: atlantic: Avoid -Wflex-array-member-not-at-end
 warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Remove unused flexible-array member `buf` and, with this, fix the following
warnings:
drivers/net/ethernet/aquantia/atlantic/aq_hw.h:197:36: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/ethernet/aquantia/atlantic/hw_atl/../aq_hw.h:197:36: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Suggested-by: Igor Russkikh <irusskikh@marvell.com>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Igor Russkikh <irusskikh@marvell.com>
Link: https://patch.msgid.link/Z6F3KZVfnAZ2FoJm@kspp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
index f5901f8e39077..f6b990b7f5b47 100644
--- a/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
+++ b/drivers/net/ethernet/aquantia/atlantic/hw_atl/hw_atl_utils.h
@@ -226,7 +226,6 @@ struct __packed offload_info {
 	struct offload_port_info ports;
 	struct offload_ka_info kas;
 	struct offload_rr_info rrs;
-	u8 buf[];
 };
 
 struct __packed hw_atl_utils_fw_rpc {

From d5fdfe480c7926960cb926964546c8704fe09626 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 3 Feb 2025 11:04:15 -0800
Subject: [PATCH 0135/2753] netconsole: selftest: Add test for fragmented
 messages

Add a new selftest to verify netconsole's handling of messages that
exceed the packet size limit and require fragmentation. The test sends
messages with varying sizes and userdata, validating that:

1. Large messages are correctly fragmented and reassembled
2. Userdata fields are properly preserved across fragments
3. Messages work correctly with and without kernel release version
   appending

The test creates a networking environment using netdevsim, sends
messages through /dev/kmsg, and verifies the received fragments maintain
message integrity.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250203-netcons_frag_msgs-v1-1-5bc6bedf2ac0@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/Makefile  |   1 +
 .../drivers/net/lib/sh/lib_netcons.sh         |   7 +
 .../drivers/net/netcons_fragmented_msg.sh     | 122 ++++++++++++++++++
 3 files changed, 130 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh

diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 137470bdee0c7..c7f1c443f2af0 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -7,6 +7,7 @@ TEST_INCLUDES := $(wildcard lib/py/*.py) \
 
 TEST_PROGS := \
 	netcons_basic.sh \
+	netcons_fragmented_msg.sh \
 	netcons_overflow.sh \
 	ping.py \
 	queues.py \
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
index 3acaba41ac7b2..0c262b123fdd3 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -110,6 +110,13 @@ function create_dynamic_target() {
 	echo 1 > "${NETCONS_PATH}"/enabled
 }
 
+# Do not append the release to the header of the message
+function disable_release_append() {
+	echo 0 > "${NETCONS_PATH}"/enabled
+	echo 0 > "${NETCONS_PATH}"/release
+	echo 1 > "${NETCONS_PATH}"/enabled
+}
+
 function cleanup() {
 	local NSIM_DEV_SYS_DEL="/sys/bus/netdevsim/del_device"
 
diff --git a/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
new file mode 100755
index 0000000000000..4a71e01a230c7
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_fragmented_msg.sh
@@ -0,0 +1,122 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# Test netconsole's message fragmentation functionality.
+#
+# When a message exceeds the maximum packet size, netconsole splits it into
+# multiple fragments for transmission. This test verifies:
+#  - Correct fragmentation of large messages
+#  - Proper reassembly of fragments at the receiver
+#  - Preservation of userdata across fragments
+#  - Behavior with and without kernel release version appending
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# The content of kmsg will be save to the following file
+OUTPUT_FILE="/tmp/${TARGET}"
+
+# set userdata to a long value. In this case, it is "1-2-3-4...50-"
+USERDATA_VALUE=$(printf -- '%.2s-' {1..60})
+
+# Convert the header string in a regexp, so, we can remove
+# the second header as well.
+# A header looks like "13,468,514729715,-,ncfrag=0/1135;". If
+# release is appended, you might find something like:L
+# "6.13.0-04048-g4f561a87745a,13,468,514729715,-,ncfrag=0/1135;"
+function header_to_regex() {
+	# header is everything before ;
+	local HEADER="${1}"
+	REGEX=$(echo "${HEADER}" | cut -d'=' -f1)
+	echo "${REGEX}=[0-9]*\/[0-9]*;"
+}
+
+# We have two headers in the message. Remove both to get the full message,
+# and extract the full message.
+function extract_msg() {
+	local MSGFILE="${1}"
+	# Extract the header, which is the very first thing that arrives in the
+	# first list.
+	HEADER=$(sed -n '1p' "${MSGFILE}" | cut -d';' -f1)
+	HEADER_REGEX=$(header_to_regex "${HEADER}")
+
+	# Remove the two headers from the received message
+	# This will return the message without any header, similarly to what
+	# was sent.
+	sed "s/""${HEADER_REGEX}""//g" "${MSGFILE}"
+}
+
+# Validate the message, which has two messages glued together.
+# unwrap them to make sure all the characters were transmitted.
+# File will look like the following:
+#  13,468,514729715,-,ncfrag=0/1135;<message>
+#   key=<part of key>-13,468,514729715,-,ncfrag=967/1135;<rest of the key>
+function validate_fragmented_result() {
+	# Discard the netconsole headers, and assemble the full message
+	RCVMSG=$(extract_msg "${1}")
+
+	# check for the main message
+	if ! echo "${RCVMSG}" | grep -q "${MSG}"; then
+		echo "Message body doesn't match." >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# check userdata
+	if ! echo "${RCVMSG}" | grep -q "${USERDATA_VALUE}"; then
+		echo "message userdata doesn't match" >&2
+		echo "msg received=" "${RCVMSG}" >&2
+		exit "${ksft_fail}"
+	fi
+	# test passed. hooray
+}
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+# Set userdata "key" with the "value" value
+set_user_data
+
+
+# TEST 1: Send message and userdata. They will fragment
+# =======
+MSG=$(printf -- 'MSG%.3s=' {1..150})
+
+# Listen for netconsole port inside the namespace and destination interface
+listen_port_and_save_to "${OUTPUT_FILE}" &
+# Wait for socat to start and listen to the port.
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+# Send the message
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+# Wait until socat saves the file to disk
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+# Check if the message was not corrupted
+validate_fragmented_result "${OUTPUT_FILE}"
+
+# TEST 2: Test with smaller message, and without release appended
+# =======
+MSG=$(printf -- 'FOOBAR%.3s=' {1..100})
+# Let's disable release and test again.
+disable_release_append
+
+listen_port_and_save_to "${OUTPUT_FILE}" &
+wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+echo "${MSG}: ${TARGET}" > /dev/kmsg
+busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+validate_fragmented_result "${OUTPUT_FILE}"
+exit "${ksft_pass}"

From 51773846fab24a353bed4ebb660997ced4bc32d7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Feb 2025 21:33:39 +0100
Subject: [PATCH 0136/2753] net: phy: realtek: make HWMON support a
 user-visible Kconfig symbol

Make config symbol REALTEK_PHY_HWMON user-visible, so that users can
remove support if not needed.

Suggested-by: Geert Uytterhoeven <geert@linux-m68k.org>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/3466ee92-166a-4b0f-9ae7-42b9e046f333@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/Kconfig | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/realtek/Kconfig b/drivers/net/phy/realtek/Kconfig
index 31935f147d879..b05c2a1e90243 100644
--- a/drivers/net/phy/realtek/Kconfig
+++ b/drivers/net/phy/realtek/Kconfig
@@ -4,8 +4,12 @@ config REALTEK_PHY
 	help
 	  Currently supports RTL821x/RTL822x and fast ethernet PHYs
 
+if REALTEK_PHY
+
 config REALTEK_PHY_HWMON
-	def_bool REALTEK_PHY && HWMON
-	depends on !(REALTEK_PHY=y && HWMON=m)
+	bool "HWMON support for Realtek PHYs"
+	depends on HWMON && !(REALTEK_PHY=y && HWMON=m)
 	help
 	  Optional hwmon support for the temperature sensor
+
+endif # REALTEK_PHY

From 135c3c86a7cef4ba3d368da15b16c275b74582d3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Feb 2025 21:35:24 +0100
Subject: [PATCH 0137/2753] r8169: make Kconfig option for LED support
 user-visible

Make config option R8169_LEDS user-visible, so that users can remove
support if not needed.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/d29f0cdb-32bf-435f-b59d-dc96bca1e3ab@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig
index 8a8ea51c639e9..fe136f61586fe 100644
--- a/drivers/net/ethernet/realtek/Kconfig
+++ b/drivers/net/ethernet/realtek/Kconfig
@@ -114,7 +114,8 @@ config R8169
 	  will be called r8169.  This is recommended.
 
 config R8169_LEDS
-	def_bool R8169 && LEDS_TRIGGER_NETDEV
+	bool "Support for controlling the NIC LEDs"
+	depends on R8169 && LEDS_TRIGGER_NETDEV
 	depends on !(R8169=y && LEDS_CLASS=m)
 	help
 	  Optional support for controlling the NIC LED's with the netdev

From ceb5faef848b2fbb5d1e99617093cc9d4deb2b30 Mon Sep 17 00:00:00 2001
From: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Date: Fri, 24 Jan 2025 01:07:44 +0530
Subject: [PATCH 0138/2753] integrity: fix typos and spelling errors

Fix typos and spelling errors in integrity module comments that were
identified using the codespell tool.
No functional changes - documentation only.

Signed-off-by: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Reviewed-by: Mimi Zohar <zohar@linux.ibm.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 security/integrity/evm/evm_crypto.c | 2 +-
 security/integrity/evm/evm_main.c   | 2 +-
 security/integrity/ima/ima_main.c   | 6 +++---
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/security/integrity/evm/evm_crypto.c b/security/integrity/evm/evm_crypto.c
index 7c06ffd633d24..a5e730ffda57f 100644
--- a/security/integrity/evm/evm_crypto.c
+++ b/security/integrity/evm/evm_crypto.c
@@ -180,7 +180,7 @@ static void hmac_add_misc(struct shash_desc *desc, struct inode *inode,
 }
 
 /*
- * Dump large security xattr values as a continuous ascii hexademical string.
+ * Dump large security xattr values as a continuous ascii hexadecimal string.
  * (pr_debug is limited to 64 bytes.)
  */
 static void dump_security_xattr_l(const char *prefix, const void *src,
diff --git a/security/integrity/evm/evm_main.c b/security/integrity/evm/evm_main.c
index 377e57e9084f0..0add782e73ba2 100644
--- a/security/integrity/evm/evm_main.c
+++ b/security/integrity/evm/evm_main.c
@@ -169,7 +169,7 @@ static int is_unsupported_hmac_fs(struct dentry *dentry)
  * and compare it against the stored security.evm xattr.
  *
  * For performance:
- * - use the previoulsy retrieved xattr value and length to calculate the
+ * - use the previously retrieved xattr value and length to calculate the
  *   HMAC.)
  * - cache the verification result in the iint, when available.
  *
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index 9f9897a7c217e..f2c9affa0c2ac 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -1011,9 +1011,9 @@ int process_buffer_measurement(struct mnt_idmap *idmap,
 	}
 
 	/*
-	 * Both LSM hooks and auxilary based buffer measurements are
-	 * based on policy.  To avoid code duplication, differentiate
-	 * between the LSM hooks and auxilary buffer measurements,
+	 * Both LSM hooks and auxiliary based buffer measurements are
+	 * based on policy. To avoid code duplication, differentiate
+	 * between the LSM hooks and auxiliary buffer measurements,
 	 * retrieving the policy rule information only for the LSM hook
 	 * buffer measurements.
 	 */

From 57a0ef02fefafc4b9603e33a18b669ba5ce59ba3 Mon Sep 17 00:00:00 2001
From: Roberto Sassu <roberto.sassu@huawei.com>
Date: Tue, 4 Feb 2025 13:57:20 +0100
Subject: [PATCH 0139/2753] ima: Reset IMA_NONACTION_RULE_FLAGS after
 post_setattr

Commit 0d73a55208e9 ("ima: re-introduce own integrity cache lock")
mistakenly reverted the performance improvement introduced in commit
42a4c603198f0 ("ima: fix ima_inode_post_setattr"). The unused bit mask was
subsequently removed by commit 11c60f23ed13 ("integrity: Remove unused
macro IMA_ACTION_RULE_FLAGS").

Restore the performance improvement by introducing the new mask
IMA_NONACTION_RULE_FLAGS, equal to IMA_NONACTION_FLAGS without
IMA_NEW_FILE, which is not a rule-specific flag.

Finally, reset IMA_NONACTION_RULE_FLAGS instead of IMA_NONACTION_FLAGS in
process_measurement(), if the IMA_CHANGE_ATTR atomic flag is set (after
file metadata modification).

With this patch, new files for which metadata were modified while they are
still open, can be reopened before the last file close (when security.ima
is written), since the IMA_NEW_FILE flag is not cleared anymore. Otherwise,
appraisal fails because security.ima is missing (files with IMA_NEW_FILE
set are an exception).

Cc: stable@vger.kernel.org # v4.16.x
Fixes: 0d73a55208e9 ("ima: re-introduce own integrity cache lock")
Signed-off-by: Roberto Sassu <roberto.sassu@huawei.com>
Signed-off-by: Mimi Zohar <zohar@linux.ibm.com>
---
 security/integrity/ima/ima.h      | 3 +++
 security/integrity/ima/ima_main.c | 7 +++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
index 24d09ea91b877..a4f284bd846c1 100644
--- a/security/integrity/ima/ima.h
+++ b/security/integrity/ima/ima.h
@@ -149,6 +149,9 @@ struct ima_kexec_hdr {
 #define IMA_CHECK_BLACKLIST	0x40000000
 #define IMA_VERITY_REQUIRED	0x80000000
 
+/* Exclude non-action flags which are not rule-specific. */
+#define IMA_NONACTION_RULE_FLAGS	(IMA_NONACTION_FLAGS & ~IMA_NEW_FILE)
+
 #define IMA_DO_MASK		(IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
 				 IMA_HASH | IMA_APPRAISE_SUBMASK)
 #define IMA_DONE_MASK		(IMA_MEASURED | IMA_APPRAISED | IMA_AUDITED | \
diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
index f2c9affa0c2ac..28b8b0db6f9bb 100644
--- a/security/integrity/ima/ima_main.c
+++ b/security/integrity/ima/ima_main.c
@@ -269,10 +269,13 @@ static int process_measurement(struct file *file, const struct cred *cred,
 	mutex_lock(&iint->mutex);
 
 	if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags))
-		/* reset appraisal flags if ima_inode_post_setattr was called */
+		/*
+		 * Reset appraisal flags (action and non-action rule-specific)
+		 * if ima_inode_post_setattr was called.
+		 */
 		iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED |
 				 IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK |
-				 IMA_NONACTION_FLAGS);
+				 IMA_NONACTION_RULE_FLAGS);
 
 	/*
 	 * Re-evaulate the file if either the xattr has changed or the

From 1ac98d6484c4a53e9b3ed1f59d03a2dd2d287b70 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Sat, 11 Jan 2025 18:23:26 +0100
Subject: [PATCH 0140/2753] soc: qcom: pmic_glink: Drop redundant pg assignment
 before taking lock

Commit e9f826b0459f ("soc: qcom: pmic_glink: simplify locking with
guard()") was on top of a fix [1] which was moving the 'pg =
__pmic_glink' assignment into the critical section.  Unfortunately the
actual fix was not applied and instead rebased version of the next patch
got in.  The resulting code is in general correct, but now there is a
duplicated assignment 'pg = __pmic_glink'.

[1] https://lore.kernel.org/all/20240822164815.230167-1-krzysztof.kozlowski@linaro.org/

Fixes: e9f826b0459f ("soc: qcom: pmic_glink: simplify locking with guard()")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250111172326.101779-1-krzysztof.kozlowski@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/pmic_glink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
index 052c292eeda61..cde19cdfd3c7f 100644
--- a/drivers/soc/qcom/pmic_glink.c
+++ b/drivers/soc/qcom/pmic_glink.c
@@ -233,7 +233,7 @@ static void pmic_glink_pdr_callback(int state, char *svc_path, void *priv)
 
 static int pmic_glink_rpmsg_probe(struct rpmsg_device *rpdev)
 {
-	struct pmic_glink *pg = __pmic_glink;
+	struct pmic_glink *pg;
 
 	guard(mutex)(&__pmic_glink_lock);
 	pg = __pmic_glink;

From 7f048b202333b967782a98aa21bb3354dc379bbf Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 15 Jan 2025 09:52:53 +0300
Subject: [PATCH 0141/2753] firmware: qcom: scm: Fix error code in probe()

Set the error code if devm_qcom_tzmem_pool_new() fails.  Don't return
success.

Fixes: 1e76b546e6fc ("firmware: qcom: scm: Cleanup global '__scm' on probe failures")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/a0845467-4f83-4070-ab1e-ff7e6764609f@stanley.mountain
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/firmware/qcom/qcom_scm.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
index f0569bb9411f7..fc4d67e4c4a67 100644
--- a/drivers/firmware/qcom/qcom_scm.c
+++ b/drivers/firmware/qcom/qcom_scm.c
@@ -2301,8 +2301,8 @@ static int qcom_scm_probe(struct platform_device *pdev)
 
 	__scm->mempool = devm_qcom_tzmem_pool_new(__scm->dev, &pool_config);
 	if (IS_ERR(__scm->mempool)) {
-		dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool),
-			      "Failed to create the SCM memory pool\n");
+		ret = dev_err_probe(__scm->dev, PTR_ERR(__scm->mempool),
+				    "Failed to create the SCM memory pool\n");
 		goto err;
 	}
 

From 0bea93fdbaf8675b7e8124bdcaf51497dcc8bcfa Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Feb 2025 21:41:36 +0100
Subject: [PATCH 0142/2753] net: phy: realtek: use string choices helpers

Use string choices helpers to simplify the code.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501190707.qQS8PGHW-lkp@intel.com/
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/realtek/realtek_main.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 572a933636b01..210fefac44d47 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/clk.h>
+#include <linux/string_choices.h>
 
 #include "realtek.h"
 
@@ -422,11 +423,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	} else if (ret) {
 		dev_dbg(dev,
 			"%s 2ns TX delay (and changing the value from pin-strapping RXD1 or the bootloader)\n",
-			val_txdly ? "Enabling" : "Disabling");
+			str_enable_disable(val_txdly));
 	} else {
 		dev_dbg(dev,
 			"2ns TX delay was already %s (by pin-strapping RXD1 or bootloader configuration)\n",
-			val_txdly ? "enabled" : "disabled");
+			str_enabled_disabled(val_txdly));
 	}
 
 	ret = phy_modify_paged_changed(phydev, 0xd08, 0x15, RTL8211F_RX_DELAY,
@@ -437,11 +438,11 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 	} else if (ret) {
 		dev_dbg(dev,
 			"%s 2ns RX delay (and changing the value from pin-strapping RXD0 or the bootloader)\n",
-			val_rxdly ? "Enabling" : "Disabling");
+			str_enable_disable(val_rxdly));
 	} else {
 		dev_dbg(dev,
 			"2ns RX delay was already %s (by pin-strapping RXD0 or bootloader configuration)\n",
-			val_rxdly ? "enabled" : "disabled");
+			str_enabled_disabled(val_rxdly));
 	}
 
 	if (priv->has_phycr2) {

From b2657259fce933ae0ba3e07cd0052fb6a8e90689 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:10 +0100
Subject: [PATCH 0143/2753] ice: devlink PF MSI-X max and min parameter

Use generic devlink PF MSI-X parameter to allow user to change MSI-X
range.

Add notes about this parameters into ice devlink documentation.

Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 Documentation/networking/devlink/ice.rst      | 11 +++
 .../net/ethernet/intel/ice/devlink/devlink.c  | 81 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice.h          |  7 ++
 drivers/net/ethernet/intel/ice/ice_irq.c      |  7 ++
 4 files changed, 106 insertions(+)

diff --git a/Documentation/networking/devlink/ice.rst b/Documentation/networking/devlink/ice.rst
index e3972d03cea04..792e9f8c846ab 100644
--- a/Documentation/networking/devlink/ice.rst
+++ b/Documentation/networking/devlink/ice.rst
@@ -69,6 +69,17 @@ Parameters
 
        To verify that value has been set:
        $ devlink dev param show pci/0000:16:00.0 name tx_scheduling_layers
+   * - ``msix_vec_per_pf_max``
+     - driverinit
+     - Set the max MSI-X that can be used by the PF, rest can be utilized for
+       SRIOV. The range is from min value set in msix_vec_per_pf_min to
+       2k/number of ports.
+   * - ``msix_vec_per_pf_min``
+     - driverinit
+     - Set the min MSI-X that will be used by the PF. This value inform how many
+       MSI-X will be allocated statically. The range is from 2 to value set
+       in msix_vec_per_pf_max.
+
 .. list-table:: Driver specific parameters implemented
     :widths: 5 5 90
 
diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index d116e2b10bcea..81de5fbc130ea 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1202,6 +1202,25 @@ static int ice_devlink_set_parent(struct devlink_rate *devlink_rate,
 	return status;
 }
 
+static void ice_set_min_max_msix(struct ice_pf *pf)
+{
+	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value val;
+	int err;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					      &val);
+	if (!err)
+		pf->msix.min = val.vu32;
+
+	err = devl_param_driverinit_value_get(devlink,
+					      DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					      &val);
+	if (!err)
+		pf->msix.max = val.vu32;
+}
+
 /**
  * ice_devlink_reinit_up - do reinit of the given PF
  * @pf: pointer to the PF struct
@@ -1217,6 +1236,9 @@ static int ice_devlink_reinit_up(struct ice_pf *pf)
 		return err;
 	}
 
+	/* load MSI-X values */
+	ice_set_min_max_msix(pf);
+
 	err = ice_init_dev(pf);
 	if (err)
 		goto unroll_hw_init;
@@ -1530,6 +1552,30 @@ static int ice_devlink_local_fwd_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int
+ice_devlink_msix_max_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+
+	if (val.vu32 > pf->hw.func_caps.common_cap.num_msix_vectors)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	if (val.vu32 < ICE_MIN_MSIX)
+		return -EINVAL;
+
+	return 0;
+}
+
 enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
@@ -1547,6 +1593,15 @@ static const struct devlink_param ice_dvl_rdma_params[] = {
 			      ice_devlink_enable_iw_validate),
 };
 
+static const struct devlink_param ice_dvl_msix_params[] = {
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MAX,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_max_pf_validate),
+	DEVLINK_PARAM_GENERIC(MSIX_VEC_PER_PF_MIN,
+			      BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_msix_min_pf_validate),
+};
+
 static const struct devlink_param ice_dvl_sched_params[] = {
 	DEVLINK_PARAM_DRIVER(ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
 			     "tx_scheduling_layers",
@@ -1648,6 +1703,7 @@ void ice_devlink_unregister(struct ice_pf *pf)
 int ice_devlink_register_params(struct ice_pf *pf)
 {
 	struct devlink *devlink = priv_to_devlink(pf);
+	union devlink_param_value value;
 	struct ice_hw *hw = &pf->hw;
 	int status;
 
@@ -1656,10 +1712,33 @@ int ice_devlink_register_params(struct ice_pf *pf)
 	if (status)
 		return status;
 
+	status = devl_params_register(devlink, ice_dvl_msix_params,
+				      ARRAY_SIZE(ice_dvl_msix_params));
+	if (status)
+		goto unregister_rdma_params;
+
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		status = devl_params_register(devlink, ice_dvl_sched_params,
 					      ARRAY_SIZE(ice_dvl_sched_params));
+	if (status)
+		goto unregister_msix_params;
+
+	value.vu32 = pf->msix.max;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX,
+					value);
+	value.vu32 = pf->msix.min;
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
+					value);
+	return 0;
 
+unregister_msix_params:
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
+unregister_rdma_params:
+	devl_params_unregister(devlink, ice_dvl_rdma_params,
+			       ARRAY_SIZE(ice_dvl_rdma_params));
 	return status;
 }
 
@@ -1670,6 +1749,8 @@ void ice_devlink_unregister_params(struct ice_pf *pf)
 
 	devl_params_unregister(devlink, ice_dvl_rdma_params,
 			       ARRAY_SIZE(ice_dvl_rdma_params));
+	devl_params_unregister(devlink, ice_dvl_msix_params,
+			       ARRAY_SIZE(ice_dvl_msix_params));
 
 	if (hw->func_caps.common_cap.tx_sched_topo_comp_mode_en)
 		devl_params_unregister(devlink, ice_dvl_sched_params,
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 71e05d30f0fda..d041b04ff3246 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -542,6 +542,12 @@ struct ice_agg_node {
 	u8 valid;
 };
 
+struct ice_pf_msix {
+	u32 cur;
+	u32 min;
+	u32 max;
+};
+
 struct ice_pf {
 	struct pci_dev *pdev;
 	struct ice_adapter *adapter;
@@ -612,6 +618,7 @@ struct ice_pf {
 	struct msi_map ll_ts_irq;	/* LL_TS interrupt MSIX vector */
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
+	struct ice_pf_msix msix;
 	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index ad82ff7d19957..0659b96b9b8c0 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -254,6 +254,13 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
 	int vectors, max_vectors;
 
+	/* load default PF MSI-X range */
+	if (!pf->msix.min)
+		pf->msix.min = ICE_MIN_MSIX;
+
+	if (!pf->msix.max)
+		pf->msix.max = total_vectors / 2;
+
 	vectors = ice_ena_msix_range(pf);
 
 	if (vectors < 0)

From 79d97b8cf9a8500e2a18bb37f96268b17b7e7dd5 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:11 +0100
Subject: [PATCH 0144/2753] ice: remove splitting MSI-X between features

With dynamic approach to alloc MSI-X there is no sense to statically
split MSI-X between PF features.

Splitting was also calculating needed MSI-X. Move this part to separate
function and use as max value.

Remove ICE_ESWITCH_MSIX, as there is no need for additional MSI-X for
switchdev.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h     |   2 -
 drivers/net/ethernet/intel/ice/ice_irq.c | 172 +++--------------------
 2 files changed, 16 insertions(+), 158 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index d041b04ff3246..c78bd45cf016a 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -98,8 +98,6 @@
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
 #define ICE_RDMA_NUM_AEQ_MSIX	4
-#define ICE_MIN_RDMA_MSIX	2
-#define ICE_ESWITCH_MSIX	1
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index 0659b96b9b8c0..4a50a6dc817ed 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -84,155 +84,11 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	return entry;
 }
 
-/**
- * ice_reduce_msix_usage - Reduce usage of MSI-X vectors
- * @pf: board private structure
- * @v_remain: number of remaining MSI-X vectors to be distributed
- *
- * Reduce the usage of MSI-X vectors when entire request cannot be fulfilled.
- * pf->num_lan_msix and pf->num_rdma_msix values are set based on number of
- * remaining vectors.
- */
-static void ice_reduce_msix_usage(struct ice_pf *pf, int v_remain)
+static int ice_get_default_msix_amount(struct ice_pf *pf)
 {
-	int v_rdma;
-
-	if (!ice_is_rdma_ena(pf)) {
-		pf->num_lan_msix = v_remain;
-		return;
-	}
-
-	/* RDMA needs at least 1 interrupt in addition to AEQ MSIX */
-	v_rdma = ICE_RDMA_NUM_AEQ_MSIX + 1;
-
-	if (v_remain < ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_RDMA_MSIX) {
-		dev_warn(ice_pf_to_dev(pf), "Not enough MSI-X vectors to support RDMA.\n");
-		clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
-
-		pf->num_rdma_msix = 0;
-		pf->num_lan_msix = ICE_MIN_LAN_TXRX_MSIX;
-	} else if ((v_remain < ICE_MIN_LAN_TXRX_MSIX + v_rdma) ||
-		   (v_remain - v_rdma < v_rdma)) {
-		/* Support minimum RDMA and give remaining vectors to LAN MSIX
-		 */
-		pf->num_rdma_msix = ICE_MIN_RDMA_MSIX;
-		pf->num_lan_msix = v_remain - ICE_MIN_RDMA_MSIX;
-	} else {
-		/* Split remaining MSIX with RDMA after accounting for AEQ MSIX
-		 */
-		pf->num_rdma_msix = (v_remain - ICE_RDMA_NUM_AEQ_MSIX) / 2 +
-				    ICE_RDMA_NUM_AEQ_MSIX;
-		pf->num_lan_msix = v_remain - pf->num_rdma_msix;
-	}
-}
-
-/**
- * ice_ena_msix_range - Request a range of MSIX vectors from the OS
- * @pf: board private structure
- *
- * Compute the number of MSIX vectors wanted and request from the OS. Adjust
- * device usage if there are not enough vectors. Return the number of vectors
- * reserved or negative on failure.
- */
-static int ice_ena_msix_range(struct ice_pf *pf)
-{
-	int num_cpus, hw_num_msix, v_other, v_wanted, v_actual;
-	struct device *dev = ice_pf_to_dev(pf);
-	int err;
-
-	hw_num_msix = pf->hw.func_caps.common_cap.num_msix_vectors;
-	num_cpus = num_online_cpus();
-
-	/* LAN miscellaneous handler */
-	v_other = ICE_MIN_LAN_OICR_MSIX;
-
-	/* Flow Director */
-	if (test_bit(ICE_FLAG_FD_ENA, pf->flags))
-		v_other += ICE_FDIR_MSIX;
-
-	/* switchdev */
-	v_other += ICE_ESWITCH_MSIX;
-
-	v_wanted = v_other;
-
-	/* LAN traffic */
-	pf->num_lan_msix = num_cpus;
-	v_wanted += pf->num_lan_msix;
-
-	/* RDMA auxiliary driver */
-	if (ice_is_rdma_ena(pf)) {
-		pf->num_rdma_msix = num_cpus + ICE_RDMA_NUM_AEQ_MSIX;
-		v_wanted += pf->num_rdma_msix;
-	}
-
-	if (v_wanted > hw_num_msix) {
-		int v_remain;
-
-		dev_warn(dev, "not enough device MSI-X vectors. wanted = %d, available = %d\n",
-			 v_wanted, hw_num_msix);
-
-		if (hw_num_msix < ICE_MIN_MSIX) {
-			err = -ERANGE;
-			goto exit_err;
-		}
-
-		v_remain = hw_num_msix - v_other;
-		if (v_remain < ICE_MIN_LAN_TXRX_MSIX) {
-			v_other = ICE_MIN_MSIX - ICE_MIN_LAN_TXRX_MSIX;
-			v_remain = ICE_MIN_LAN_TXRX_MSIX;
-		}
-
-		ice_reduce_msix_usage(pf, v_remain);
-		v_wanted = pf->num_lan_msix + pf->num_rdma_msix + v_other;
-
-		dev_notice(dev, "Reducing request to %d MSI-X vectors for LAN traffic.\n",
-			   pf->num_lan_msix);
-		if (ice_is_rdma_ena(pf))
-			dev_notice(dev, "Reducing request to %d MSI-X vectors for RDMA.\n",
-				   pf->num_rdma_msix);
-	}
-
-	/* actually reserve the vectors */
-	v_actual = pci_alloc_irq_vectors(pf->pdev, ICE_MIN_MSIX, v_wanted,
-					 PCI_IRQ_MSIX);
-	if (v_actual < 0) {
-		dev_err(dev, "unable to reserve MSI-X vectors\n");
-		err = v_actual;
-		goto exit_err;
-	}
-
-	if (v_actual < v_wanted) {
-		dev_warn(dev, "not enough OS MSI-X vectors. requested = %d, obtained = %d\n",
-			 v_wanted, v_actual);
-
-		if (v_actual < ICE_MIN_MSIX) {
-			/* error if we can't get minimum vectors */
-			pci_free_irq_vectors(pf->pdev);
-			err = -ERANGE;
-			goto exit_err;
-		} else {
-			int v_remain = v_actual - v_other;
-
-			if (v_remain < ICE_MIN_LAN_TXRX_MSIX)
-				v_remain = ICE_MIN_LAN_TXRX_MSIX;
-
-			ice_reduce_msix_usage(pf, v_remain);
-
-			dev_notice(dev, "Enabled %d MSI-X vectors for LAN traffic.\n",
-				   pf->num_lan_msix);
-
-			if (ice_is_rdma_ena(pf))
-				dev_notice(dev, "Enabled %d MSI-X vectors for RDMA.\n",
-					   pf->num_rdma_msix);
-		}
-	}
-
-	return v_actual;
-
-exit_err:
-	pf->num_rdma_msix = 0;
-	pf->num_lan_msix = 0;
-	return err;
+	return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() +
+	       (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) +
+	       (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_NUM_AEQ_MSIX : 0);
 }
 
 /**
@@ -259,17 +115,21 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 		pf->msix.min = ICE_MIN_MSIX;
 
 	if (!pf->msix.max)
-		pf->msix.max = total_vectors / 2;
-
-	vectors = ice_ena_msix_range(pf);
+		pf->msix.max = min(total_vectors,
+				   ice_get_default_msix_amount(pf));
 
-	if (vectors < 0)
-		return -ENOMEM;
-
-	if (pci_msix_can_alloc_dyn(pf->pdev))
+	if (pci_msix_can_alloc_dyn(pf->pdev)) {
+		vectors = pf->msix.min;
 		max_vectors = total_vectors;
-	else
+	} else {
+		vectors = pf->msix.max;
 		max_vectors = vectors;
+	}
+
+	vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors,
+					PCI_IRQ_MSIX);
+	if (vectors < pf->msix.min)
+		return -ENOMEM;
 
 	ice_init_irq_tracker(pf, max_vectors, vectors);
 

From ad61cd9c67ad592668fc0e7253c507b50f72acab Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:12 +0100
Subject: [PATCH 0145/2753] ice: get rid of num_lan_msix field

Remove the field to allow having more queues than MSI-X on VSI. As
default the number will be the same, but if there won't be more MSI-X
available VSI can run with at least one MSI-X.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h         |  1 -
 drivers/net/ethernet/intel/ice/ice_base.c    | 10 ++++----
 drivers/net/ethernet/intel/ice/ice_ethtool.c |  6 ++---
 drivers/net/ethernet/intel/ice/ice_irq.c     | 11 ++++-----
 drivers/net/ethernet/intel/ice/ice_lib.c     | 25 +++++++++++---------
 5 files changed, 24 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index c78bd45cf016a..ad61dd688871a 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -617,7 +617,6 @@ struct ice_pf {
 	u16 max_pf_txqs;	/* Total Tx queues PF wide */
 	u16 max_pf_rxqs;	/* Total Rx queues PF wide */
 	struct ice_pf_msix msix;
-	u16 num_lan_msix;	/* Total MSIX vectors for base driver */
 	u16 num_lan_tx;		/* num LAN Tx queues setup */
 	u16 num_lan_rx;		/* num LAN Rx queues setup */
 	u16 next_vsi;		/* Next free slot in pf->vsi[] - 0-based! */
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index b2af8e3586f76..0e862f20427ab 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -801,13 +801,11 @@ int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi)
 	return 0;
 
 err_out:
-	while (v_idx--)
-		ice_free_q_vector(vsi, v_idx);
 
-	dev_err(dev, "Failed to allocate %d q_vector for VSI %d, ret=%d\n",
-		vsi->num_q_vectors, vsi->vsi_num, err);
-	vsi->num_q_vectors = 0;
-	return err;
+	dev_info(dev, "Failed to allocate %d q_vectors for VSI %d, new value %d",
+		 vsi->num_q_vectors, vsi->vsi_num, v_idx);
+	vsi->num_q_vectors = v_idx;
+	return v_idx ? 0 : err;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index 6bbb304ad9ab7..b0805704834d7 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -3788,8 +3788,7 @@ ice_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info)
  */
 static int ice_get_max_txq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_txq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_txq);
 }
 
 /**
@@ -3798,8 +3797,7 @@ static int ice_get_max_txq(struct ice_pf *pf)
  */
 static int ice_get_max_rxq(struct ice_pf *pf)
 {
-	return min3(pf->num_lan_msix, (u16)num_online_cpus(),
-		    (u16)pf->hw.func_caps.common_cap.num_rxq);
+	return min(num_online_cpus(), pf->hw.func_caps.common_cap.num_rxq);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index 4a50a6dc817ed..1a7d446ab5f11 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -108,7 +108,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 int ice_init_interrupt_scheme(struct ice_pf *pf)
 {
 	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors, max_vectors;
+	int vectors;
 
 	/* load default PF MSI-X range */
 	if (!pf->msix.min)
@@ -118,20 +118,17 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 		pf->msix.max = min(total_vectors,
 				   ice_get_default_msix_amount(pf));
 
-	if (pci_msix_can_alloc_dyn(pf->pdev)) {
+	if (pci_msix_can_alloc_dyn(pf->pdev))
 		vectors = pf->msix.min;
-		max_vectors = total_vectors;
-	} else {
+	else
 		vectors = pf->msix.max;
-		max_vectors = vectors;
-	}
 
 	vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors,
 					PCI_IRQ_MSIX);
 	if (vectors < pf->msix.min)
 		return -ENOMEM;
 
-	ice_init_irq_tracker(pf, max_vectors, vectors);
+	ice_init_irq_tracker(pf, pf->msix.max, vectors);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 38a1c8372180b..4b8d7aa7b1bb5 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -157,6 +157,16 @@ static void ice_vsi_set_num_desc(struct ice_vsi *vsi)
 	}
 }
 
+static u16 ice_get_rxq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_rxq_count(pf), num_online_cpus());
+}
+
+static u16 ice_get_txq_count(struct ice_pf *pf)
+{
+	return min(ice_get_avail_txq_count(pf), num_online_cpus());
+}
+
 /**
  * ice_vsi_set_num_qs - Set number of queues, descriptors and vectors for a VSI
  * @vsi: the VSI being configured
@@ -178,9 +188,7 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 			vsi->alloc_txq = vsi->req_txq;
 			vsi->num_txq = vsi->req_txq;
 		} else {
-			vsi->alloc_txq = min3(pf->num_lan_msix,
-					      ice_get_avail_txq_count(pf),
-					      (u16)num_online_cpus());
+			vsi->alloc_txq = ice_get_txq_count(pf);
 		}
 
 		pf->num_lan_tx = vsi->alloc_txq;
@@ -193,17 +201,13 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi)
 				vsi->alloc_rxq = vsi->req_rxq;
 				vsi->num_rxq = vsi->req_rxq;
 			} else {
-				vsi->alloc_rxq = min3(pf->num_lan_msix,
-						      ice_get_avail_rxq_count(pf),
-						      (u16)num_online_cpus());
+				vsi->alloc_rxq = ice_get_rxq_count(pf);
 			}
 		}
 
 		pf->num_lan_rx = vsi->alloc_rxq;
 
-		vsi->num_q_vectors = min_t(int, pf->num_lan_msix,
-					   max_t(int, vsi->alloc_rxq,
-						 vsi->alloc_txq));
+		vsi->num_q_vectors = max(vsi->alloc_rxq, vsi->alloc_txq);
 		break;
 	case ICE_VSI_SF:
 		vsi->alloc_txq = 1;
@@ -1173,12 +1177,11 @@ static void ice_set_rss_vsi_ctx(struct ice_vsi_ctx *ctxt, struct ice_vsi *vsi)
 static void
 ice_chnl_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt)
 {
-	struct ice_pf *pf = vsi->back;
 	u16 qcount, qmap;
 	u8 offset = 0;
 	int pow;
 
-	qcount = min_t(int, vsi->num_rxq, pf->num_lan_msix);
+	qcount = vsi->num_rxq;
 
 	pow = order_base_2(qcount);
 	qmap = FIELD_PREP(ICE_AQ_VSI_TC_Q_OFFSET_M, offset);

From 3e0d3cb3fbe06a7bc09d98324a21a446c80f9d3b Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:13 +0100
Subject: [PATCH 0146/2753] ice, irdma: move interrupts code to irdma

Move responsibility of MSI-X requesting for RDMA feature from ice driver
to irdma driver. It is done to allow simple fallback when there is not
enough MSI-X available.

Change amount of MSI-X used for control from 4 to 1, as it isn't needed
to have more than one MSI-X for this purpose.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/infiniband/hw/irdma/hw.c         |  2 -
 drivers/infiniband/hw/irdma/main.c       | 46 ++++++++++++++++-
 drivers/infiniband/hw/irdma/main.h       |  3 ++
 drivers/net/ethernet/intel/ice/ice.h     |  1 -
 drivers/net/ethernet/intel/ice/ice_idc.c | 64 ++++++------------------
 drivers/net/ethernet/intel/ice/ice_irq.c |  3 +-
 include/linux/net/intel/iidc.h           |  2 +
 7 files changed, 65 insertions(+), 56 deletions(-)

diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c
index ad50b77282f8a..69ce1862eabe0 100644
--- a/drivers/infiniband/hw/irdma/hw.c
+++ b/drivers/infiniband/hw/irdma/hw.c
@@ -498,8 +498,6 @@ static int irdma_save_msix_info(struct irdma_pci_f *rf)
 	iw_qvlist->num_vectors = rf->msix_count;
 	if (rf->msix_count <= num_online_cpus())
 		rf->msix_shared = true;
-	else if (rf->msix_count > num_online_cpus() + 1)
-		rf->msix_count = num_online_cpus() + 1;
 
 	pmsix = rf->msix_entries;
 	for (i = 0, ceq_idx = 0; i < rf->msix_count; i++, iw_qvinfo++) {
diff --git a/drivers/infiniband/hw/irdma/main.c b/drivers/infiniband/hw/irdma/main.c
index 3f13200ff71bc..1ee8969595d3d 100644
--- a/drivers/infiniband/hw/irdma/main.c
+++ b/drivers/infiniband/hw/irdma/main.c
@@ -206,6 +206,43 @@ static void irdma_lan_unregister_qset(struct irdma_sc_vsi *vsi,
 		ibdev_dbg(&iwdev->ibdev, "WS: LAN free_res for rdma qset failed.\n");
 }
 
+static int irdma_init_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+{
+	int i;
+
+	rf->msix_count = num_online_cpus() + IRDMA_NUM_AEQ_MSIX;
+	rf->msix_entries = kcalloc(rf->msix_count, sizeof(*rf->msix_entries),
+				   GFP_KERNEL);
+	if (!rf->msix_entries)
+		return -ENOMEM;
+
+	for (i = 0; i < rf->msix_count; i++)
+		if (ice_alloc_rdma_qvector(pf, &rf->msix_entries[i]))
+			break;
+
+	if (i < IRDMA_MIN_MSIX) {
+		for (; i > 0; i--)
+			ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+
+		kfree(rf->msix_entries);
+		return -ENOMEM;
+	}
+
+	rf->msix_count = i;
+
+	return 0;
+}
+
+static void irdma_deinit_interrupts(struct irdma_pci_f *rf, struct ice_pf *pf)
+{
+	int i;
+
+	for (i = 0; i < rf->msix_count; i++)
+		ice_free_rdma_qvector(pf, &rf->msix_entries[i]);
+
+	kfree(rf->msix_entries);
+}
+
 static void irdma_remove(struct auxiliary_device *aux_dev)
 {
 	struct iidc_auxiliary_dev *iidc_adev = container_of(aux_dev,
@@ -216,6 +253,7 @@ static void irdma_remove(struct auxiliary_device *aux_dev)
 
 	irdma_ib_unregister_device(iwdev);
 	ice_rdma_update_vsi_filter(pf, iwdev->vsi_num, false);
+	irdma_deinit_interrupts(iwdev->rf, pf);
 
 	pr_debug("INIT: Gen2 PF[%d] device remove success\n", PCI_FUNC(pf->pdev->devfn));
 }
@@ -230,9 +268,7 @@ static void irdma_fill_device_info(struct irdma_device *iwdev, struct ice_pf *pf
 	rf->gen_ops.unregister_qset = irdma_lan_unregister_qset;
 	rf->hw.hw_addr = pf->hw.hw_addr;
 	rf->pcidev = pf->pdev;
-	rf->msix_count =  pf->num_rdma_msix;
 	rf->pf_id = pf->hw.pf_id;
-	rf->msix_entries = &pf->msix_entries[pf->rdma_base_vector];
 	rf->default_vsi.vsi_idx = vsi->vsi_num;
 	rf->protocol_used = pf->rdma_mode & IIDC_RDMA_PROTOCOL_ROCEV2 ?
 			    IRDMA_ROCE_PROTOCOL_ONLY : IRDMA_IWARP_PROTOCOL_ONLY;
@@ -281,6 +317,10 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 	irdma_fill_device_info(iwdev, pf, vsi);
 	rf = iwdev->rf;
 
+	err = irdma_init_interrupts(rf, pf);
+	if (err)
+		goto err_init_interrupts;
+
 	err = irdma_ctrl_init_hw(rf);
 	if (err)
 		goto err_ctrl_init;
@@ -311,6 +351,8 @@ static int irdma_probe(struct auxiliary_device *aux_dev, const struct auxiliary_
 err_rt_init:
 	irdma_ctrl_deinit_hw(rf);
 err_ctrl_init:
+	irdma_deinit_interrupts(rf, pf);
+err_init_interrupts:
 	kfree(iwdev->rf);
 	ib_dealloc_device(&iwdev->ibdev);
 
diff --git a/drivers/infiniband/hw/irdma/main.h b/drivers/infiniband/hw/irdma/main.h
index 9f0ed6e844711..ef9a9b79d711d 100644
--- a/drivers/infiniband/hw/irdma/main.h
+++ b/drivers/infiniband/hw/irdma/main.h
@@ -117,6 +117,9 @@ extern struct auxiliary_driver i40iw_auxiliary_drv;
 
 #define IRDMA_IRQ_NAME_STR_LEN (64)
 
+#define IRDMA_NUM_AEQ_MSIX	1
+#define IRDMA_MIN_MSIX		2
+
 enum init_completion_state {
 	INVALID_STATE = 0,
 	INITIAL_STATE,
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index ad61dd688871a..0dbc98ba69f41 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -97,7 +97,6 @@
 #define ICE_MIN_LAN_OICR_MSIX	1
 #define ICE_MIN_MSIX		(ICE_MIN_LAN_TXRX_MSIX + ICE_MIN_LAN_OICR_MSIX)
 #define ICE_FDIR_MSIX		2
-#define ICE_RDMA_NUM_AEQ_MSIX	4
 #define ICE_NO_VSI		0xffff
 #define ICE_VSI_MAP_CONTIG	0
 #define ICE_VSI_MAP_SCATTER	1
diff --git a/drivers/net/ethernet/intel/ice/ice_idc.c b/drivers/net/ethernet/intel/ice/ice_idc.c
index 145b27f2a4ce8..bab3e81cad5d0 100644
--- a/drivers/net/ethernet/intel/ice/ice_idc.c
+++ b/drivers/net/ethernet/intel/ice/ice_idc.c
@@ -228,61 +228,34 @@ void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos)
 }
 EXPORT_SYMBOL_GPL(ice_get_qos_params);
 
-/**
- * ice_alloc_rdma_qvectors - Allocate vector resources for RDMA driver
- * @pf: board private structure to initialize
- */
-static int ice_alloc_rdma_qvectors(struct ice_pf *pf)
+int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry)
 {
-	if (ice_is_rdma_ena(pf)) {
-		int i;
-
-		pf->msix_entries = kcalloc(pf->num_rdma_msix,
-					   sizeof(*pf->msix_entries),
-						  GFP_KERNEL);
-		if (!pf->msix_entries)
-			return -ENOMEM;
+	struct msi_map map = ice_alloc_irq(pf, true);
 
-		/* RDMA is the only user of pf->msix_entries array */
-		pf->rdma_base_vector = 0;
-
-		for (i = 0; i < pf->num_rdma_msix; i++) {
-			struct msix_entry *entry = &pf->msix_entries[i];
-			struct msi_map map;
+	if (map.index < 0)
+		return -ENOMEM;
 
-			map = ice_alloc_irq(pf, false);
-			if (map.index < 0)
-				break;
+	entry->entry = map.index;
+	entry->vector = map.virq;
 
-			entry->entry = map.index;
-			entry->vector = map.virq;
-		}
-	}
 	return 0;
 }
+EXPORT_SYMBOL_GPL(ice_alloc_rdma_qvector);
 
 /**
  * ice_free_rdma_qvector - free vector resources reserved for RDMA driver
  * @pf: board private structure to initialize
+ * @entry: MSI-X entry to be removed
  */
-static void ice_free_rdma_qvector(struct ice_pf *pf)
+void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry)
 {
-	int i;
-
-	if (!pf->msix_entries)
-		return;
-
-	for (i = 0; i < pf->num_rdma_msix; i++) {
-		struct msi_map map;
+	struct msi_map map;
 
-		map.index = pf->msix_entries[i].entry;
-		map.virq = pf->msix_entries[i].vector;
-		ice_free_irq(pf, map);
-	}
-
-	kfree(pf->msix_entries);
-	pf->msix_entries = NULL;
+	map.index = entry->entry;
+	map.virq = entry->vector;
+	ice_free_irq(pf, map);
 }
+EXPORT_SYMBOL_GPL(ice_free_rdma_qvector);
 
 /**
  * ice_adev_release - function to be mapped to AUX dev's release op
@@ -382,12 +355,6 @@ int ice_init_rdma(struct ice_pf *pf)
 		return -ENOMEM;
 	}
 
-	/* Reserve vector resources */
-	ret = ice_alloc_rdma_qvectors(pf);
-	if (ret < 0) {
-		dev_err(dev, "failed to reserve vectors for RDMA\n");
-		goto err_reserve_rdma_qvector;
-	}
 	pf->rdma_mode |= IIDC_RDMA_PROTOCOL_ROCEV2;
 	ret = ice_plug_aux_dev(pf);
 	if (ret)
@@ -395,8 +362,6 @@ int ice_init_rdma(struct ice_pf *pf)
 	return 0;
 
 err_plug_aux_dev:
-	ice_free_rdma_qvector(pf);
-err_reserve_rdma_qvector:
 	pf->adev = NULL;
 	xa_erase(&ice_aux_id, pf->aux_idx);
 	return ret;
@@ -412,6 +377,5 @@ void ice_deinit_rdma(struct ice_pf *pf)
 		return;
 
 	ice_unplug_aux_dev(pf);
-	ice_free_rdma_qvector(pf);
 	xa_erase(&ice_aux_id, pf->aux_idx);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index 1a7d446ab5f11..80c9ee2e64c18 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -84,11 +84,12 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	return entry;
 }
 
+#define ICE_RDMA_AEQ_MSIX 1
 static int ice_get_default_msix_amount(struct ice_pf *pf)
 {
 	return ICE_MIN_LAN_OICR_MSIX + num_online_cpus() +
 	       (test_bit(ICE_FLAG_FD_ENA, pf->flags) ? ICE_FDIR_MSIX : 0) +
-	       (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_NUM_AEQ_MSIX : 0);
+	       (ice_is_rdma_ena(pf) ? num_online_cpus() + ICE_RDMA_AEQ_MSIX : 0);
 }
 
 /**
diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h
index 1c1332e4df260..13274c3def660 100644
--- a/include/linux/net/intel/iidc.h
+++ b/include/linux/net/intel/iidc.h
@@ -78,6 +78,8 @@ int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
 int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type);
 int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable);
 void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos);
+int ice_alloc_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry);
+void ice_free_rdma_qvector(struct ice_pf *pf, struct msix_entry *entry);
 
 /* Structure representing auxiliary driver tailored information about the core
  * PCI dev, each auxiliary driver using the IIDC interface will have an

From a8c2d3932c1106af2764cc6869b29bcf3cb5bc47 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:14 +0100
Subject: [PATCH 0147/2753] ice: treat dyn_allowed only as suggestion

It can be needed to have some MSI-X allocated as static and rest as
dynamic. For example on PF VSI. We want to always have minimum one MSI-X
on it, because of that it is allocated as a static one, rest can be
dynamic if it is supported.

Change the ice_get_irq_res() to allow using static entries if they are
free even if caller wants dynamic one.

Adjust limit values to the new approach. Min and max in limit means the
values that are valid, so decrease max and num_static by one.

Set vsi::irq_dyn_alloc if dynamic allocation is supported.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_irq.c | 25 ++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_lib.c |  2 ++
 2 files changed, 15 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index 80c9ee2e64c18..d466d29b2ef1c 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -45,7 +45,7 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
 /**
  * ice_get_irq_res - get an interrupt resource
  * @pf: board private structure
- * @dyn_only: force entry to be dynamically allocated
+ * @dyn_allowed: allow entry to be dynamically allocated
  *
  * Allocate new irq entry in the free slot of the tracker. Since xarray
  * is used, always allocate new entry at the lowest possible index. Set
@@ -53,11 +53,12 @@ static void ice_free_irq_res(struct ice_pf *pf, u16 index)
  *
  * Returns allocated irq entry or NULL on failure.
  */
-static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
+static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf,
+					     bool dyn_allowed)
 {
-	struct xa_limit limit = { .max = pf->irq_tracker.num_entries,
+	struct xa_limit limit = { .max = pf->irq_tracker.num_entries - 1,
 				  .min = 0 };
-	unsigned int num_static = pf->irq_tracker.num_static;
+	unsigned int num_static = pf->irq_tracker.num_static - 1;
 	struct ice_irq_entry *entry;
 	unsigned int index;
 	int ret;
@@ -66,9 +67,9 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 	if (!entry)
 		return NULL;
 
-	/* skip preallocated entries if the caller says so */
-	if (dyn_only)
-		limit.min = num_static;
+	/* only already allocated if the caller says so */
+	if (!dyn_allowed)
+		limit.max = num_static;
 
 	ret = xa_alloc(&pf->irq_tracker.entries, &index, entry, limit,
 		       GFP_KERNEL);
@@ -78,7 +79,7 @@ static struct ice_irq_entry *ice_get_irq_res(struct ice_pf *pf, bool dyn_only)
 		entry = NULL;
 	} else {
 		entry->index = index;
-		entry->dynamic = index >= num_static;
+		entry->dynamic = index > num_static;
 	}
 
 	return entry;
@@ -137,7 +138,7 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 /**
  * ice_alloc_irq - Allocate new interrupt vector
  * @pf: board private structure
- * @dyn_only: force dynamic allocation of the interrupt
+ * @dyn_allowed: allow dynamic allocation of the interrupt
  *
  * Allocate new interrupt vector for a given owner id.
  * return struct msi_map with interrupt details and track
@@ -150,20 +151,20 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
  * interrupt will be allocated with pci_msix_alloc_irq_at.
  *
  * Some callers may only support dynamically allocated interrupts.
- * This is indicated with dyn_only flag.
+ * This is indicated with dyn_allowed flag.
  *
  * On failure, return map with negative .index. The caller
  * is expected to check returned map index.
  *
  */
-struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only)
+struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 {
 	int sriov_base_vector = pf->sriov_base_vector;
 	struct msi_map map = { .index = -ENOENT };
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_irq_entry *entry;
 
-	entry = ice_get_irq_res(pf, dyn_only);
+	entry = ice_get_irq_res(pf, dyn_allowed);
 	if (!entry)
 		return map;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 4b8d7aa7b1bb5..1827f1f20ce85 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -571,6 +571,8 @@ ice_vsi_alloc_def(struct ice_vsi *vsi, struct ice_channel *ch)
 			return -ENOMEM;
 	}
 
+	vsi->irq_dyn_alloc = pci_msix_can_alloc_dyn(vsi->back->pdev);
+
 	switch (vsi->type) {
 	case ICE_VSI_PF:
 	case ICE_VSI_SF:

From 87181cd6985fbd591ba2b7b7c5ab9772c7cab689 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:15 +0100
Subject: [PATCH 0148/2753] ice: enable_rdma devlink param

Implement enable_rdma devlink parameter to allow user to turn RDMA
feature on and off.

It is useful when there is no enough interrupts and user doesn't need
RDMA feature.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Jan Sokolowski <jan.sokolowski@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/devlink/devlink.c  | 21 +++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_lib.c      |  8 ++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink.c b/drivers/net/ethernet/intel/ice/devlink/devlink.c
index 81de5fbc130ea..504aaf4b88551 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink.c
@@ -1576,6 +1576,19 @@ ice_devlink_msix_min_pf_validate(struct devlink *devlink, u32 id,
 	return 0;
 }
 
+static int ice_devlink_enable_rdma_validate(struct devlink *devlink, u32 id,
+					    union devlink_param_value val,
+					    struct netlink_ext_ack *extack)
+{
+	struct ice_pf *pf = devlink_priv(devlink);
+	bool new_state = val.vbool;
+
+	if (new_state && !test_bit(ICE_FLAG_RDMA_ENA, pf->flags))
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
 enum ice_param_id {
 	ICE_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	ICE_DEVLINK_PARAM_ID_TX_SCHED_LAYERS,
@@ -1591,6 +1604,8 @@ static const struct devlink_param ice_dvl_rdma_params[] = {
 			      ice_devlink_enable_iw_get,
 			      ice_devlink_enable_iw_set,
 			      ice_devlink_enable_iw_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_RDMA, BIT(DEVLINK_PARAM_CMODE_DRIVERINIT),
+			      NULL, NULL, ice_devlink_enable_rdma_validate),
 };
 
 static const struct devlink_param ice_dvl_msix_params[] = {
@@ -1731,6 +1746,12 @@ int ice_devlink_register_params(struct ice_pf *pf)
 	devl_param_driverinit_value_set(devlink,
 					DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
 					value);
+
+	value.vbool = test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	devl_param_driverinit_value_set(devlink,
+					DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					value);
+
 	return 0;
 
 unregister_msix_params:
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1827f1f20ce85..16c419809849c 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -833,7 +833,13 @@ bool ice_is_safe_mode(struct ice_pf *pf)
  */
 bool ice_is_rdma_ena(struct ice_pf *pf)
 {
-	return test_bit(ICE_FLAG_RDMA_ENA, pf->flags);
+	union devlink_param_value value;
+	int err;
+
+	err = devl_param_driverinit_value_get(priv_to_devlink(pf),
+					      DEVLINK_PARAM_GENERIC_ID_ENABLE_RDMA,
+					      &value);
+	return err ? test_bit(ICE_FLAG_RDMA_ENA, pf->flags) : value.vbool;
 }
 
 /**

From a203163274a48501c88d96625c173773e3d7c6a0 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:16 +0100
Subject: [PATCH 0149/2753] ice: simplify VF MSI-X managing

After implementing pf->msix.max field, base vector for other use cases
(like VFs) can be fixed. This simplify code when changing MSI-X amount
on particular VF, because there is no need to move a base vector.

A fixed base vector allows to reserve vectors from the beginning
instead of from the end, which is also simpler in code.

Store total and rest value in the same struct as max and min for PF.
Move tracking vectors from ice_sriov.c to ice_irq.c as it can be also
use for other none PF use cases (SIOV).

Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h       |  10 +-
 drivers/net/ethernet/intel/ice/ice_irq.c   |  75 +++++++---
 drivers/net/ethernet/intel/ice/ice_irq.h   |  13 +-
 drivers/net/ethernet/intel/ice/ice_sriov.c | 154 ++-------------------
 4 files changed, 79 insertions(+), 173 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 0dbc98ba69f41..2a6de21151933 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -543,6 +543,8 @@ struct ice_pf_msix {
 	u32 cur;
 	u32 min;
 	u32 max;
+	u32 total;
+	u32 rest;
 };
 
 struct ice_pf {
@@ -559,13 +561,7 @@ struct ice_pf {
 	/* OS reserved IRQ details */
 	struct msix_entry *msix_entries;
 	struct ice_irq_tracker irq_tracker;
-	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
-	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
-	 * MSIX vectors allowed on this PF.
-	 */
-	u16 sriov_base_vector;
-	unsigned long *sriov_irq_bm;	/* bitmap to track irq usage */
-	u16 sriov_irq_size;		/* size of the irq_bm bitmap */
+	struct ice_virt_irq_tracker virt_irq_tracker;
 
 	u16 ctrl_vsi_idx;		/* control VSI index in pf->vsi array */
 
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index d466d29b2ef1c..cbae3d81f0f1d 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -20,6 +20,19 @@ ice_init_irq_tracker(struct ice_pf *pf, unsigned int max_vectors,
 	xa_init_flags(&pf->irq_tracker.entries, XA_FLAGS_ALLOC);
 }
 
+static int
+ice_init_virt_irq_tracker(struct ice_pf *pf, u32 base, u32 num_entries)
+{
+	pf->virt_irq_tracker.bm = bitmap_zalloc(num_entries, GFP_KERNEL);
+	if (!pf->virt_irq_tracker.bm)
+		return -ENOMEM;
+
+	pf->virt_irq_tracker.num_entries = num_entries;
+	pf->virt_irq_tracker.base = base;
+
+	return 0;
+}
+
 /**
  * ice_deinit_irq_tracker - free xarray tracker
  * @pf: board private structure
@@ -29,6 +42,11 @@ static void ice_deinit_irq_tracker(struct ice_pf *pf)
 	xa_destroy(&pf->irq_tracker.entries);
 }
 
+static void ice_deinit_virt_irq_tracker(struct ice_pf *pf)
+{
+	bitmap_free(pf->virt_irq_tracker.bm);
+}
+
 /**
  * ice_free_irq_res - free a block of resources
  * @pf: board private structure
@@ -101,6 +119,7 @@ void ice_clear_interrupt_scheme(struct ice_pf *pf)
 {
 	pci_free_irq_vectors(pf->pdev);
 	ice_deinit_irq_tracker(pf);
+	ice_deinit_virt_irq_tracker(pf);
 }
 
 /**
@@ -120,6 +139,9 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 		pf->msix.max = min(total_vectors,
 				   ice_get_default_msix_amount(pf));
 
+	pf->msix.total = total_vectors;
+	pf->msix.rest = total_vectors - pf->msix.max;
+
 	if (pci_msix_can_alloc_dyn(pf->pdev))
 		vectors = pf->msix.min;
 	else
@@ -132,7 +154,7 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 
 	ice_init_irq_tracker(pf, pf->msix.max, vectors);
 
-	return 0;
+	return ice_init_virt_irq_tracker(pf, pf->msix.max, pf->msix.rest);
 }
 
 /**
@@ -159,7 +181,6 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
  */
 struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 {
-	int sriov_base_vector = pf->sriov_base_vector;
 	struct msi_map map = { .index = -ENOENT };
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_irq_entry *entry;
@@ -168,10 +189,6 @@ struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_allowed)
 	if (!entry)
 		return map;
 
-	/* fail if we're about to violate SRIOV vectors space */
-	if (sriov_base_vector && entry->index >= sriov_base_vector)
-		goto exit_free_res;
-
 	if (pci_msix_can_alloc_dyn(pf->pdev) && entry->dynamic) {
 		map = pci_msix_alloc_irq_at(pf->pdev, entry->index, NULL);
 		if (map.index < 0)
@@ -219,26 +236,40 @@ void ice_free_irq(struct ice_pf *pf, struct msi_map map)
 }
 
 /**
- * ice_get_max_used_msix_vector - Get the max used interrupt vector
- * @pf: board private structure
+ * ice_virt_get_irqs - get irqs for SR-IOV usacase
+ * @pf: pointer to PF structure
+ * @needed: number of irqs to get
  *
- * Return index of maximum used interrupt vectors with respect to the
- * beginning of the MSIX table. Take into account that some interrupts
- * may have been dynamically allocated after MSIX was initially enabled.
+ * This returns the first MSI-X vector index in PF space that is used by this
+ * VF. This index is used when accessing PF relative registers such as
+ * GLINT_VECT2FUNC and GLINT_DYN_CTL.
+ * This will always be the OICR index in the AVF driver so any functionality
+ * using vf->first_vector_idx for queue configuration_id: id of VF which will
+ * use this irqs
  */
-int ice_get_max_used_msix_vector(struct ice_pf *pf)
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed)
 {
-	unsigned long start, index, max_idx;
-	void *entry;
+	int res = bitmap_find_next_zero_area(pf->virt_irq_tracker.bm,
+					     pf->virt_irq_tracker.num_entries,
+					     0, needed, 0);
 
-	/* Treat all preallocated interrupts as used */
-	start = pf->irq_tracker.num_static;
-	max_idx = start - 1;
+	if (res >= pf->virt_irq_tracker.num_entries)
+		return -ENOENT;
 
-	xa_for_each_start(&pf->irq_tracker.entries, index, entry, start) {
-		if (index > max_idx)
-			max_idx = index;
-	}
+	bitmap_set(pf->virt_irq_tracker.bm, res, needed);
 
-	return max_idx;
+	/* conversion from number in bitmap to global irq index */
+	return res + pf->virt_irq_tracker.base;
+}
+
+/**
+ * ice_virt_free_irqs - free irqs used by the VF
+ * @pf: pointer to PF structure
+ * @index: first index to be free
+ * @irqs: number of irqs to free
+ */
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs)
+{
+	bitmap_clear(pf->virt_irq_tracker.bm, index - pf->virt_irq_tracker.base,
+		     irqs);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_irq.h b/drivers/net/ethernet/intel/ice/ice_irq.h
index f35efc08575ef..b2f9dbafd57e9 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.h
+++ b/drivers/net/ethernet/intel/ice/ice_irq.h
@@ -15,11 +15,22 @@ struct ice_irq_tracker {
 	u16 num_static;	/* preallocated entries */
 };
 
+struct ice_virt_irq_tracker {
+	unsigned long *bm;	/* bitmap to track irq usage */
+	u32 num_entries;
+	/* First MSIX vector used by SR-IOV VFs. Calculated by subtracting the
+	 * number of MSIX vectors needed for all SR-IOV VFs from the number of
+	 * MSIX vectors allowed on this PF.
+	 */
+	u32 base;
+};
+
 int ice_init_interrupt_scheme(struct ice_pf *pf);
 void ice_clear_interrupt_scheme(struct ice_pf *pf);
 
 struct msi_map ice_alloc_irq(struct ice_pf *pf, bool dyn_only);
 void ice_free_irq(struct ice_pf *pf, struct msi_map map);
-int ice_get_max_used_msix_vector(struct ice_pf *pf);
 
+int ice_virt_get_irqs(struct ice_pf *pf, u32 needed);
+void ice_virt_free_irqs(struct ice_pf *pf, u32 index, u32 irqs);
 #endif
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index b83f99c01d91b..33eac29b6a500 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -122,27 +122,6 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 		dev_err(dev, "Scattered mode for VF Rx queues is not yet implemented\n");
 }
 
-/**
- * ice_sriov_free_msix_res - Reset/free any used MSIX resources
- * @pf: pointer to the PF structure
- *
- * Since no MSIX entries are taken from the pf->irq_tracker then just clear
- * the pf->sriov_base_vector.
- *
- * Returns 0 on success, and -EINVAL on error.
- */
-static int ice_sriov_free_msix_res(struct ice_pf *pf)
-{
-	if (!pf)
-		return -EINVAL;
-
-	bitmap_free(pf->sriov_irq_bm);
-	pf->sriov_irq_size = 0;
-	pf->sriov_base_vector = 0;
-
-	return 0;
-}
-
 /**
  * ice_free_vfs - Free all VFs
  * @pf: pointer to the PF structure
@@ -177,6 +156,7 @@ void ice_free_vfs(struct ice_pf *pf)
 
 		ice_eswitch_detach_vf(pf, vf);
 		ice_dis_vf_qs(vf);
+		ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 		if (test_bit(ICE_VF_STATE_INIT, vf->vf_states)) {
 			/* disable VF qp mappings and set VF disable state */
@@ -200,9 +180,6 @@ void ice_free_vfs(struct ice_pf *pf)
 		mutex_unlock(&vf->cfg_lock);
 	}
 
-	if (ice_sriov_free_msix_res(pf))
-		dev_err(dev, "Failed to free MSIX resources used by SR-IOV\n");
-
 	vfs->num_qps_per = 0;
 	ice_free_vf_entries(pf);
 
@@ -371,40 +348,6 @@ void ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector)
 	q_vector->reg_idx = vf->first_vector_idx + q_vector->vf_reg_idx;
 }
 
-/**
- * ice_sriov_set_msix_res - Set any used MSIX resources
- * @pf: pointer to PF structure
- * @num_msix_needed: number of MSIX vectors needed for all SR-IOV VFs
- *
- * This function allows SR-IOV resources to be taken from the end of the PF's
- * allowed HW MSIX vectors so that the irq_tracker will not be affected. We
- * just set the pf->sriov_base_vector and return success.
- *
- * If there are not enough resources available, return an error. This should
- * always be caught by ice_set_per_vf_res().
- *
- * Return 0 on success, and -EINVAL when there are not enough MSIX vectors
- * in the PF's space available for SR-IOV.
- */
-static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
-{
-	u16 total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
-	int vectors_used = ice_get_max_used_msix_vector(pf);
-	int sriov_base_vector;
-
-	sriov_base_vector = total_vectors - num_msix_needed;
-
-	/* make sure we only grab irq_tracker entries from the list end and
-	 * that we have enough available MSIX vectors
-	 */
-	if (sriov_base_vector < vectors_used)
-		return -EINVAL;
-
-	pf->sriov_base_vector = sriov_base_vector;
-
-	return 0;
-}
-
 /**
  * ice_set_per_vf_res - check if vectors and queues are available
  * @pf: pointer to the PF structure
@@ -429,11 +372,9 @@ static int ice_sriov_set_msix_res(struct ice_pf *pf, u16 num_msix_needed)
  */
 static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 {
-	int vectors_used = ice_get_max_used_msix_vector(pf);
 	u16 num_msix_per_vf, num_txq, num_rxq, avail_qs;
 	int msix_avail_per_vf, msix_avail_for_sriov;
 	struct device *dev = ice_pf_to_dev(pf);
-	int err;
 
 	lockdep_assert_held(&pf->vfs.table_lock);
 
@@ -441,8 +382,7 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -EINVAL;
 
 	/* determine MSI-X resources per VF */
-	msix_avail_for_sriov = pf->hw.func_caps.common_cap.num_msix_vectors -
-		vectors_used;
+	msix_avail_for_sriov = pf->virt_irq_tracker.num_entries;
 	msix_avail_per_vf = msix_avail_for_sriov / num_vfs;
 	if (msix_avail_per_vf >= ICE_NUM_VF_MSIX_MED) {
 		num_msix_per_vf = ICE_NUM_VF_MSIX_MED;
@@ -481,13 +421,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 		return -ENOSPC;
 	}
 
-	err = ice_sriov_set_msix_res(pf, num_msix_per_vf * num_vfs);
-	if (err) {
-		dev_err(dev, "Unable to set MSI-X resources for %d VFs, err %d\n",
-			num_vfs, err);
-		return err;
-	}
-
 	/* only allow equal Tx/Rx queue count (i.e. queue pairs) */
 	pf->vfs.num_qps_per = min_t(int, num_txq, num_rxq);
 	pf->vfs.num_msix_per = num_msix_per_vf;
@@ -497,52 +430,6 @@ static int ice_set_per_vf_res(struct ice_pf *pf, u16 num_vfs)
 	return 0;
 }
 
-/**
- * ice_sriov_get_irqs - get irqs for SR-IOV usacase
- * @pf: pointer to PF structure
- * @needed: number of irqs to get
- *
- * This returns the first MSI-X vector index in PF space that is used by this
- * VF. This index is used when accessing PF relative registers such as
- * GLINT_VECT2FUNC and GLINT_DYN_CTL.
- * This will always be the OICR index in the AVF driver so any functionality
- * using vf->first_vector_idx for queue configuration_id: id of VF which will
- * use this irqs
- *
- * Only SRIOV specific vectors are tracked in sriov_irq_bm. SRIOV vectors are
- * allocated from the end of global irq index. First bit in sriov_irq_bm means
- * last irq index etc. It simplifies extension of SRIOV vectors.
- * They will be always located from sriov_base_vector to the last irq
- * index. While increasing/decreasing sriov_base_vector can be moved.
- */
-static int ice_sriov_get_irqs(struct ice_pf *pf, u16 needed)
-{
-	int res = bitmap_find_next_zero_area(pf->sriov_irq_bm,
-					     pf->sriov_irq_size, 0, needed, 0);
-	/* conversion from number in bitmap to global irq index */
-	int index = pf->sriov_irq_size - res - needed;
-
-	if (res >= pf->sriov_irq_size || index < pf->sriov_base_vector)
-		return -ENOENT;
-
-	bitmap_set(pf->sriov_irq_bm, res, needed);
-	return index;
-}
-
-/**
- * ice_sriov_free_irqs - free irqs used by the VF
- * @pf: pointer to PF structure
- * @vf: pointer to VF structure
- */
-static void ice_sriov_free_irqs(struct ice_pf *pf, struct ice_vf *vf)
-{
-	/* Move back from first vector index to first index in bitmap */
-	int bm_i = pf->sriov_irq_size - vf->first_vector_idx - vf->num_msix;
-
-	bitmap_clear(pf->sriov_irq_bm, bm_i, vf->num_msix);
-	vf->first_vector_idx = 0;
-}
-
 /**
  * ice_init_vf_vsi_res - initialize/setup VF VSI resources
  * @vf: VF to initialize/setup the VSI for
@@ -556,7 +443,7 @@ static int ice_init_vf_vsi_res(struct ice_vf *vf)
 	struct ice_vsi *vsi;
 	int err;
 
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		return -ENOMEM;
 
@@ -856,16 +743,10 @@ static int ice_create_vf_entries(struct ice_pf *pf, u16 num_vfs)
  */
 static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 {
-	int total_vectors = pf->hw.func_caps.common_cap.num_msix_vectors;
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_hw *hw = &pf->hw;
 	int ret;
 
-	pf->sriov_irq_bm = bitmap_zalloc(total_vectors, GFP_KERNEL);
-	if (!pf->sriov_irq_bm)
-		return -ENOMEM;
-	pf->sriov_irq_size = total_vectors;
-
 	/* Disable global interrupt 0 so we don't try to handle the VFLR. */
 	wr32(hw, GLINT_DYN_CTL(pf->oicr_irq.index),
 	     ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S);
@@ -918,7 +799,6 @@ static int ice_ena_vfs(struct ice_pf *pf, u16 num_vfs)
 	/* rearm interrupts here */
 	ice_irq_dynamic_ena(hw, NULL, NULL);
 	clear_bit(ICE_OICR_INTR_DIS, pf->state);
-	bitmap_free(pf->sriov_irq_bm);
 	return ret;
 }
 
@@ -992,16 +872,7 @@ u32 ice_sriov_get_vf_total_msix(struct pci_dev *pdev)
 {
 	struct ice_pf *pf = pci_get_drvdata(pdev);
 
-	return pf->sriov_irq_size - ice_get_max_used_msix_vector(pf);
-}
-
-static int ice_sriov_move_base_vector(struct ice_pf *pf, int move)
-{
-	if (pf->sriov_base_vector - move < ice_get_max_used_msix_vector(pf))
-		return -ENOMEM;
-
-	pf->sriov_base_vector -= move;
-	return 0;
+	return pf->virt_irq_tracker.num_entries;
 }
 
 static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
@@ -1020,7 +891,8 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		ice_dis_vf_mappings(tmp_vf);
-		ice_sriov_free_irqs(pf, tmp_vf);
+		ice_virt_free_irqs(pf, tmp_vf->first_vector_idx,
+				   tmp_vf->num_msix);
 
 		vf_ids[to_remap] = tmp_vf->vf_id;
 		to_remap += 1;
@@ -1032,7 +904,7 @@ static void ice_sriov_remap_vectors(struct ice_pf *pf, u16 restricted_id)
 			continue;
 
 		tmp_vf->first_vector_idx =
-			ice_sriov_get_irqs(pf, tmp_vf->num_msix);
+			ice_virt_get_irqs(pf, tmp_vf->num_msix);
 		/* there is no need to rebuild VSI as we are only changing the
 		 * vector indexes not amount of MSI-X or queues
 		 */
@@ -1105,20 +977,15 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 	prev_msix = vf->num_msix;
 	prev_queues = vf->num_vf_qs;
 
-	if (ice_sriov_move_base_vector(pf, msix_vec_count - prev_msix)) {
-		ice_put_vf(vf);
-		return -ENOSPC;
-	}
-
 	ice_dis_vf_mappings(vf);
-	ice_sriov_free_irqs(pf, vf);
+	ice_virt_free_irqs(pf, vf->first_vector_idx, vf->num_msix);
 
 	/* Remap all VFs beside the one is now configured */
 	ice_sriov_remap_vectors(pf, vf->vf_id);
 
 	vf->num_msix = msix_vec_count;
 	vf->num_vf_qs = queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0)
 		goto unroll;
 
@@ -1147,7 +1014,8 @@ int ice_sriov_set_msix_vec_count(struct pci_dev *vf_dev, int msix_vec_count)
 
 	vf->num_msix = prev_msix;
 	vf->num_vf_qs = prev_queues;
-	vf->first_vector_idx = ice_sriov_get_irqs(pf, vf->num_msix);
+
+	vf->first_vector_idx = ice_virt_get_irqs(pf, vf->num_msix);
 	if (vf->first_vector_idx < 0) {
 		ice_put_vf(vf);
 		return -EINVAL;

From d67627e7b53203ca150e54723abbed81a0716286 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Tue, 3 Dec 2024 07:58:17 +0100
Subject: [PATCH 0150/2753] ice: init flow director before RDMA

Flow director needs only one MSI-X. Load it before RDMA to save MSI-X
for it.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c3a0fb97c5ee4..d7037de29545f 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5186,11 +5186,12 @@ int ice_load(struct ice_pf *pf)
 
 	ice_napi_add(vsi);
 
+	ice_init_features(pf);
+
 	err = ice_init_rdma(pf);
 	if (err)
 		goto err_init_rdma;
 
-	ice_init_features(pf);
 	ice_service_task_restart(pf);
 
 	clear_bit(ICE_DOWN, pf->state);
@@ -5198,6 +5199,7 @@ int ice_load(struct ice_pf *pf)
 	return 0;
 
 err_init_rdma:
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 err_tc_indir_block_register:
 	ice_unregister_netdev(vsi);
@@ -5221,8 +5223,8 @@ void ice_unload(struct ice_pf *pf)
 
 	devl_assert_locked(priv_to_devlink(pf));
 
-	ice_deinit_features(pf);
 	ice_deinit_rdma(pf);
+	ice_deinit_features(pf);
 	ice_tc_indir_block_unregister(vsi);
 	ice_unregister_netdev(vsi);
 	ice_devlink_destroy_pf_port(pf);

From 933ab187e679e6fbdeea1835ae39efcc59c022d2 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Fri, 17 Jan 2025 14:17:36 +0800
Subject: [PATCH 0151/2753] wifi: ath11k: update channel list in reg notifier
 instead reg worker

Currently when ath11k gets a new channel list, it will be processed
according to the following steps:
1. update new channel list to cfg80211 and queue reg_work.
2. cfg80211 handles new channel list during reg_work.
3. update cfg80211's handled channel list to firmware by
ath11k_reg_update_chan_list().

But ath11k will immediately execute step 3 after reg_work is just
queued. Since step 2 is asynchronous, cfg80211 may not have completed
handling the new channel list, which may leading to an out-of-bounds
write error:
BUG: KASAN: slab-out-of-bounds in ath11k_reg_update_chan_list
Call Trace:
    ath11k_reg_update_chan_list+0xbfe/0xfe0 [ath11k]
    kfree+0x109/0x3a0
    ath11k_regd_update+0x1cf/0x350 [ath11k]
    ath11k_regd_update_work+0x14/0x20 [ath11k]
    process_one_work+0xe35/0x14c0

Should ensure step 2 is completely done before executing step 3. Thus
Wen raised patch[1]. When flag NL80211_REGDOM_SET_BY_DRIVER is set,
cfg80211 will notify ath11k after step 2 is done.

So enable the flag NL80211_REGDOM_SET_BY_DRIVER then cfg80211 will
notify ath11k after step 2 is done. At this time, there will be no
KASAN bug during the execution of the step 3.

[1] https://patchwork.kernel.org/project/linux-wireless/patch/20230201065313.27203-1-quic_wgong@quicinc.com/

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Fixes: f45cb6b29cd3 ("wifi: ath11k: avoid deadlock during regulatory update in ath11k_regd_update()")
Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250117061737.1921-2-quic_kangyang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/reg.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index b0f289784dd3a..7bfe47ad62a07 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 #include <linux/rtnetlink.h>
 
@@ -55,6 +55,19 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
 	ath11k_dbg(ar->ab, ATH11K_DBG_REG,
 		   "Regulatory Notification received for %s\n", wiphy_name(wiphy));
 
+	if (request->initiator == NL80211_REGDOM_SET_BY_DRIVER) {
+		ath11k_dbg(ar->ab, ATH11K_DBG_REG,
+			   "driver initiated regd update\n");
+		if (ar->state != ATH11K_STATE_ON)
+			return;
+
+		ret = ath11k_reg_update_chan_list(ar, true);
+		if (ret)
+			ath11k_warn(ar->ab, "failed to update channel list: %d\n", ret);
+
+		return;
+	}
+
 	/* Currently supporting only General User Hints. Cell base user
 	 * hints to be handled later.
 	 * Hints from other sources like Core, Beacons are not expected for
@@ -293,12 +306,6 @@ int ath11k_regd_update(struct ath11k *ar)
 	if (ret)
 		goto err;
 
-	if (ar->state == ATH11K_STATE_ON) {
-		ret = ath11k_reg_update_chan_list(ar, true);
-		if (ret)
-			goto err;
-	}
-
 	return 0;
 err:
 	ath11k_warn(ab, "failed to perform regd update : %d\n", ret);
@@ -977,6 +984,7 @@ void ath11k_regd_update_work(struct work_struct *work)
 void ath11k_reg_init(struct ath11k *ar)
 {
 	ar->hw->wiphy->regulatory_flags = REGULATORY_WIPHY_SELF_MANAGED;
+	ar->hw->wiphy->flags |= WIPHY_FLAG_NOTIFY_REGDOM_BY_DRIVER;
 	ar->hw->wiphy->reg_notifier = ath11k_reg_notifier;
 }
 

From 02aae8e2f957adc1b15b6b8055316f8a154ac3f5 Mon Sep 17 00:00:00 2001
From: Wen Gong <quic_wgong@quicinc.com>
Date: Fri, 17 Jan 2025 14:17:37 +0800
Subject: [PATCH 0152/2753] wifi: ath11k: update channel list in worker when
 wait flag is set

With previous patch "wifi: ath11k: move update channel list from update
reg worker to reg notifier", ath11k_reg_update_chan_list() will be
called during reg_process_self_managed_hint().

reg_process_self_managed_hint() will hold rtnl_lock all the time.
But ath11k_reg_update_chan_list() may increase the occupation time of
rtnl_lock, because when wait flag is set, wait_for_completion_timeout()
will be called during 11d/hw scan.

Should minimize the occupation time of rtnl_lock as much as possible
to avoid interfering with rest of the system. So move the update channel
list operation to a new worker, so that wait_for_completion_timeout()
won't be called and will not increase the occupation time of rtnl_lock.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3

Signed-off-by: Wen Gong <quic_wgong@quicinc.com>
Co-developed-by: Kang Yang <quic_kangyang@quicinc.com>
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Reviewed-by: Aditya Kumar Singh <quic_adisi@quicinc.com>
Link: https://patch.msgid.link/20250117061737.1921-3-quic_kangyang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.c |  1 +
 drivers/net/wireless/ath/ath11k/core.h |  5 +-
 drivers/net/wireless/ath/ath11k/mac.c  | 14 +++++
 drivers/net/wireless/ath/ath11k/reg.c  | 85 ++++++++++++++++++--------
 drivers/net/wireless/ath/ath11k/reg.h  |  3 +-
 drivers/net/wireless/ath/ath11k/wmi.h  |  1 +
 6 files changed, 81 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 85077247b0251..12dd37c2e9044 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -2056,6 +2056,7 @@ void ath11k_core_halt(struct ath11k *ar)
 	ath11k_mac_scan_finish(ar);
 	ath11k_mac_peer_cleanup_all(ar);
 	cancel_delayed_work_sync(&ar->scan.timeout);
+	cancel_work_sync(&ar->channel_update_work);
 	cancel_work_sync(&ar->regd_update_work);
 	cancel_work_sync(&ab->update_11d_work);
 
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 92b14fc43cb65..9842a4d65c7b9 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -686,7 +686,7 @@ struct ath11k {
 	struct mutex conf_mutex;
 	/* protects the radio specific data like debug stats, ppdu_stats_info stats,
 	 * vdev_stop_status info, scan data, ath11k_sta info, ath11k_vif info,
-	 * channel context data, survey info, test mode data.
+	 * channel context data, survey info, test mode data, channel_update_queue.
 	 */
 	spinlock_t data_lock;
 
@@ -744,6 +744,9 @@ struct ath11k {
 	struct completion bss_survey_done;
 
 	struct work_struct regd_update_work;
+	struct work_struct channel_update_work;
+	/* protected with data_lock */
+	struct list_head channel_update_queue;
 
 	struct work_struct wmi_mgmt_tx_work;
 	struct sk_buff_head wmi_mgmt_tx_queue;
diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 586898e5318fa..14ed538365899 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -6332,6 +6332,7 @@ static void ath11k_mac_op_stop(struct ieee80211_hw *hw, bool suspend)
 {
 	struct ath11k *ar = hw->priv;
 	struct htt_ppdu_stats_info *ppdu_stats, *tmp;
+	struct scan_chan_list_params *params;
 	int ret;
 
 	ath11k_mac_drain_tx(ar);
@@ -6347,6 +6348,7 @@ static void ath11k_mac_op_stop(struct ieee80211_hw *hw, bool suspend)
 	mutex_unlock(&ar->conf_mutex);
 
 	cancel_delayed_work_sync(&ar->scan.timeout);
+	cancel_work_sync(&ar->channel_update_work);
 	cancel_work_sync(&ar->regd_update_work);
 	cancel_work_sync(&ar->ab->update_11d_work);
 
@@ -6356,10 +6358,19 @@ static void ath11k_mac_op_stop(struct ieee80211_hw *hw, bool suspend)
 	}
 
 	spin_lock_bh(&ar->data_lock);
+
 	list_for_each_entry_safe(ppdu_stats, tmp, &ar->ppdu_stats_info, list) {
 		list_del(&ppdu_stats->list);
 		kfree(ppdu_stats);
 	}
+
+	while ((params = list_first_entry_or_null(&ar->channel_update_queue,
+						  struct scan_chan_list_params,
+						  list))) {
+		list_del(&params->list);
+		kfree(params);
+	}
+
 	spin_unlock_bh(&ar->data_lock);
 
 	rcu_assign_pointer(ar->ab->pdevs_active[ar->pdev_idx], NULL);
@@ -10063,6 +10074,7 @@ static const struct wiphy_iftype_ext_capab ath11k_iftypes_ext_capa[] = {
 
 static void __ath11k_mac_unregister(struct ath11k *ar)
 {
+	cancel_work_sync(&ar->channel_update_work);
 	cancel_work_sync(&ar->regd_update_work);
 
 	ieee80211_unregister_hw(ar->hw);
@@ -10462,6 +10474,8 @@ int ath11k_mac_allocate(struct ath11k_base *ab)
 		init_completion(&ar->thermal.wmi_sync);
 
 		INIT_DELAYED_WORK(&ar->scan.timeout, ath11k_scan_timeout_work);
+		INIT_WORK(&ar->channel_update_work, ath11k_regd_update_chan_list_work);
+		INIT_LIST_HEAD(&ar->channel_update_queue);
 		INIT_WORK(&ar->regd_update_work, ath11k_regd_update_work);
 
 		INIT_WORK(&ar->wmi_mgmt_tx_work, ath11k_mgmt_over_wmi_tx_work);
diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
index 7bfe47ad62a07..d62a2014315a0 100644
--- a/drivers/net/wireless/ath/ath11k/reg.c
+++ b/drivers/net/wireless/ath/ath11k/reg.c
@@ -124,32 +124,7 @@ int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait)
 	struct channel_param *ch;
 	enum nl80211_band band;
 	int num_channels = 0;
-	int i, ret, left;
-
-	if (wait && ar->state_11d != ATH11K_11D_IDLE) {
-		left = wait_for_completion_timeout(&ar->completed_11d_scan,
-						   ATH11K_SCAN_TIMEOUT_HZ);
-		if (!left) {
-			ath11k_dbg(ar->ab, ATH11K_DBG_REG,
-				   "failed to receive 11d scan complete: timed out\n");
-			ar->state_11d = ATH11K_11D_IDLE;
-		}
-		ath11k_dbg(ar->ab, ATH11K_DBG_REG,
-			   "11d scan wait left time %d\n", left);
-	}
-
-	if (wait &&
-	    (ar->scan.state == ATH11K_SCAN_STARTING ||
-	    ar->scan.state == ATH11K_SCAN_RUNNING)) {
-		left = wait_for_completion_timeout(&ar->scan.completed,
-						   ATH11K_SCAN_TIMEOUT_HZ);
-		if (!left)
-			ath11k_dbg(ar->ab, ATH11K_DBG_REG,
-				   "failed to receive hw scan complete: timed out\n");
-
-		ath11k_dbg(ar->ab, ATH11K_DBG_REG,
-			   "hw scan wait left time %d\n", left);
-	}
+	int i, ret = 0;
 
 	if (ar->state == ATH11K_STATE_RESTARTING)
 		return 0;
@@ -231,6 +206,16 @@ int ath11k_reg_update_chan_list(struct ath11k *ar, bool wait)
 		}
 	}
 
+	if (wait) {
+		spin_lock_bh(&ar->data_lock);
+		list_add_tail(&params->list, &ar->channel_update_queue);
+		spin_unlock_bh(&ar->data_lock);
+
+		queue_work(ar->ab->workqueue, &ar->channel_update_work);
+
+		return 0;
+	}
+
 	ret = ath11k_wmi_send_scan_chan_list_cmd(ar, params);
 	kfree(params);
 
@@ -811,6 +796,54 @@ ath11k_reg_build_regd(struct ath11k_base *ab,
 	return new_regd;
 }
 
+void ath11k_regd_update_chan_list_work(struct work_struct *work)
+{
+	struct ath11k *ar = container_of(work, struct ath11k,
+					 channel_update_work);
+	struct scan_chan_list_params *params;
+	struct list_head local_update_list;
+	int left;
+
+	INIT_LIST_HEAD(&local_update_list);
+
+	spin_lock_bh(&ar->data_lock);
+	list_splice_tail_init(&ar->channel_update_queue, &local_update_list);
+	spin_unlock_bh(&ar->data_lock);
+
+	while ((params = list_first_entry_or_null(&local_update_list,
+						  struct scan_chan_list_params,
+						  list))) {
+		if (ar->state_11d != ATH11K_11D_IDLE) {
+			left = wait_for_completion_timeout(&ar->completed_11d_scan,
+							   ATH11K_SCAN_TIMEOUT_HZ);
+			if (!left) {
+				ath11k_dbg(ar->ab, ATH11K_DBG_REG,
+					   "failed to receive 11d scan complete: timed out\n");
+				ar->state_11d = ATH11K_11D_IDLE;
+			}
+
+			ath11k_dbg(ar->ab, ATH11K_DBG_REG,
+				   "reg 11d scan wait left time %d\n", left);
+		}
+
+		if ((ar->scan.state == ATH11K_SCAN_STARTING ||
+		     ar->scan.state == ATH11K_SCAN_RUNNING)) {
+			left = wait_for_completion_timeout(&ar->scan.completed,
+							   ATH11K_SCAN_TIMEOUT_HZ);
+			if (!left)
+				ath11k_dbg(ar->ab, ATH11K_DBG_REG,
+					   "failed to receive hw scan complete: timed out\n");
+
+			ath11k_dbg(ar->ab, ATH11K_DBG_REG,
+				   "reg hw scan wait left time %d\n", left);
+		}
+
+		ath11k_wmi_send_scan_chan_list_cmd(ar, params);
+		list_del(&params->list);
+		kfree(params);
+	}
+}
+
 static bool ath11k_reg_is_world_alpha(char *alpha)
 {
 	if (alpha[0] == '0' && alpha[1] == '0')
diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h
index 263ea90619483..72b4835940157 100644
--- a/drivers/net/wireless/ath/ath11k/reg.h
+++ b/drivers/net/wireless/ath/ath11k/reg.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2022-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_REG_H
@@ -33,6 +33,7 @@ void ath11k_reg_init(struct ath11k *ar);
 void ath11k_reg_reset_info(struct cur_regulatory_info *reg_info);
 void ath11k_reg_free(struct ath11k_base *ab);
 void ath11k_regd_update_work(struct work_struct *work);
+void ath11k_regd_update_chan_list_work(struct work_struct *work);
 struct ieee80211_regdomain *
 ath11k_reg_build_regd(struct ath11k_base *ab,
 		      struct cur_regulatory_info *reg_info, bool intersect,
diff --git a/drivers/net/wireless/ath/ath11k/wmi.h b/drivers/net/wireless/ath/ath11k/wmi.h
index 508bd496488a6..9fcffaa2f383c 100644
--- a/drivers/net/wireless/ath/ath11k/wmi.h
+++ b/drivers/net/wireless/ath/ath11k/wmi.h
@@ -3817,6 +3817,7 @@ struct wmi_stop_scan_cmd {
 };
 
 struct scan_chan_list_params {
+	struct list_head list;
 	u32 pdev_id;
 	u16 nallchans;
 	struct channel_param ch_param[];

From 79c61899b5eee317907efd1b0d06a1ada0cc00d8 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 4 Feb 2025 18:03:10 +0100
Subject: [PATCH 0153/2753] net-sysfs: remove rtnl_trylock from device
 attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is an ABBA deadlock between net device unregistration and sysfs
files being accessed[1][2]. To prevent this from happening all paths
taking the rtnl lock after the sysfs one (actually kn->active refcount)
use rtnl_trylock and return early (using restart_syscall)[3], which can
make syscalls to spin for a long time when there is contention on the
rtnl lock[4].

There are not many possibilities to improve the above:
- Rework the entire net/ locking logic.
- Invert two locks in one of the paths — not possible.

But here it's actually possible to drop one of the locks safely: the
kernfs_node refcount. More details in the code itself, which comes with
lots of comments.

Note that we check the device is alive in the added sysfs_rtnl_lock
helper to disallow sysfs operations to run after device dismantle has
started. This also help keeping the same behavior as before. Because of
this calls to dev_isalive in sysfs ops were removed.

[1] https://lore.kernel.org/netdev/49A4D5D5.5090602@trash.net/
[2] https://lore.kernel.org/netdev/m14oyhis31.fsf@fess.ebiederm.org/
[3] https://lore.kernel.org/netdev/20090226084924.16cb3e08@nehalam/
[4] https://lore.kernel.org/all/20210928125500.167943-1-atenart@kernel.org/T/

Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250204170314.146022-2-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/rtnetlink.h |   1 +
 net/core/net-sysfs.c      | 186 +++++++++++++++++++++++++++-----------
 net/core/rtnetlink.c      |   5 +
 3 files changed, 139 insertions(+), 53 deletions(-)

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 4bc2ee0b10b05..ccaaf4c7d5f6a 100644
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -43,6 +43,7 @@ extern void rtnl_lock(void);
 extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
+extern int rtnl_lock_interruptible(void);
 extern int rtnl_lock_killable(void);
 extern bool refcount_dec_and_rtnl_lock(refcount_t *r);
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 07cb99b114bdd..e012234c739a3 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -42,6 +42,87 @@ static inline int dev_isalive(const struct net_device *dev)
 	return READ_ONCE(dev->reg_state) <= NETREG_REGISTERED;
 }
 
+/* There is a possible ABBA deadlock between rtnl_lock and kernfs_node->active,
+ * when unregistering a net device and accessing associated sysfs files. The
+ * potential deadlock is as follow:
+ *
+ *         CPU 0                                         CPU 1
+ *
+ *    rtnl_lock                                   vfs_read
+ *    unregister_netdevice_many                   kernfs_seq_start
+ *    device_del / kobject_put                      kernfs_get_active (kn->active++)
+ *    kernfs_drain                                sysfs_kf_seq_show
+ *    wait_event(                                 rtnl_lock
+ *       kn->active == KN_DEACTIVATED_BIAS)       -> waits on CPU 0 to release
+ *    -> waits on CPU 1 to decrease kn->active       the rtnl lock.
+ *
+ * The historical fix was to use rtnl_trylock with restart_syscall to bail out
+ * of sysfs operations when the lock couldn't be taken. This fixed the above
+ * issue as it allowed CPU 1 to bail out of the ABBA situation.
+ *
+ * But it came with performances issues, as syscalls are being restarted in
+ * loops when there was contention on the rtnl lock, with huge slow downs in
+ * specific scenarios (e.g. lots of virtual interfaces created and userspace
+ * daemons querying their attributes).
+ *
+ * The idea below is to bail out of the active kernfs_node protection
+ * (kn->active) while trying to take the rtnl lock.
+ *
+ * This replaces rtnl_lock() and still has to be used with rtnl_unlock(). The
+ * net device is guaranteed to be alive if this returns successfully.
+ */
+static int sysfs_rtnl_lock(struct kobject *kobj, struct attribute *attr,
+			   struct net_device *ndev)
+{
+	struct kernfs_node *kn;
+	int ret = 0;
+
+	/* First, we hold a reference to the net device as the unregistration
+	 * path might run in parallel. This will ensure the net device and the
+	 * associated sysfs objects won't be freed while we try to take the rtnl
+	 * lock.
+	 */
+	dev_hold(ndev);
+	/* sysfs_break_active_protection was introduced to allow self-removal of
+	 * devices and their associated sysfs files by bailing out of the
+	 * sysfs/kernfs protection. We do this here to allow the unregistration
+	 * path to complete in parallel. The following takes a reference on the
+	 * kobject and the kernfs_node being accessed.
+	 *
+	 * This works because we hold a reference onto the net device and the
+	 * unregistration path will wait for us eventually in netdev_run_todo
+	 * (outside an rtnl lock section).
+	 */
+	kn = sysfs_break_active_protection(kobj, attr);
+	/* We can now try to take the rtnl lock. This can't deadlock us as the
+	 * unregistration path is able to drain sysfs files (kernfs_node) thanks
+	 * to the above dance.
+	 */
+	if (rtnl_lock_interruptible()) {
+		ret = -ERESTARTSYS;
+		goto unbreak;
+	}
+	/* Check dismantle on the device hasn't started, otherwise deny the
+	 * operation.
+	 */
+	if (!dev_isalive(ndev)) {
+		rtnl_unlock();
+		ret = -ENODEV;
+		goto unbreak;
+	}
+	/* We are now sure the device dismantle hasn't started nor that it can
+	 * start before we exit the locking section as we hold the rtnl lock.
+	 * There's no need to keep unbreaking the sysfs protection nor to hold
+	 * a net device reference from that point; that was only needed to take
+	 * the rtnl lock.
+	 */
+unbreak:
+	sysfs_unbreak_active_protection(kn);
+	dev_put(ndev);
+
+	return ret;
+}
+
 /* use same locking rules as GIF* ioctl's */
 static ssize_t netdev_show(const struct device *dev,
 			   struct device_attribute *attr, char *buf,
@@ -95,14 +176,14 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr,
 	if (ret)
 		goto err;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		goto err;
+
+	ret = (*set)(netdev, new);
+	if (ret == 0)
+		ret = len;
 
-	if (dev_isalive(netdev)) {
-		ret = (*set)(netdev, new);
-		if (ret == 0)
-			ret = len;
-	}
 	rtnl_unlock();
  err:
 	return ret;
@@ -220,7 +301,7 @@ static ssize_t carrier_store(struct device *dev, struct device_attribute *attr,
 	struct net_device *netdev = to_net_dev(dev);
 
 	/* The check is also done in change_carrier; this helps returning early
-	 * without hitting the trylock/restart in netdev_store.
+	 * without hitting the locking section in netdev_store.
 	 */
 	if (!netdev->netdev_ops->ndo_change_carrier)
 		return -EOPNOTSUPP;
@@ -234,8 +315,9 @@ static ssize_t carrier_show(struct device *dev,
 	struct net_device *netdev = to_net_dev(dev);
 	int ret = -EINVAL;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		/* Synchronize carrier state with link watch,
@@ -245,8 +327,8 @@ static ssize_t carrier_show(struct device *dev,
 
 		ret = sysfs_emit(buf, fmt_dec, !!netif_carrier_ok(netdev));
 	}
-	rtnl_unlock();
 
+	rtnl_unlock();
 	return ret;
 }
 static DEVICE_ATTR_RW(carrier);
@@ -258,13 +340,14 @@ static ssize_t speed_show(struct device *dev,
 	int ret = -EINVAL;
 
 	/* The check is also done in __ethtool_get_link_ksettings; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->ethtool_ops->get_link_ksettings)
 		return ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
@@ -284,13 +367,14 @@ static ssize_t duplex_show(struct device *dev,
 	int ret = -EINVAL;
 
 	/* The check is also done in __ethtool_get_link_ksettings; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->ethtool_ops->get_link_ksettings)
 		return ret;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
@@ -490,16 +574,15 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 	if (len >  0 && buf[len - 1] == '\n')
 		--count;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		ret = dev_set_alias(netdev, buf, count);
-		if (ret < 0)
-			goto err;
-		ret = len;
-		netdev_state_change(netdev);
-	}
+	ret = dev_set_alias(netdev, buf, count);
+	if (ret < 0)
+		goto err;
+	ret = len;
+	netdev_state_change(netdev);
 err:
 	rtnl_unlock();
 
@@ -551,24 +634,23 @@ static ssize_t phys_port_id_show(struct device *dev,
 				 struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
+	struct netdev_phys_item_id ppid;
 	ssize_t ret = -EINVAL;
 
 	/* The check is also done in dev_get_phys_port_id; this helps returning
-	 * early without hitting the trylock/restart below.
+	 * early without hitting the locking section below.
 	 */
 	if (!netdev->netdev_ops->ndo_get_phys_port_id)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		struct netdev_phys_item_id ppid;
+	ret = dev_get_phys_port_id(netdev, &ppid);
+	if (!ret)
+		ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
 
-		ret = dev_get_phys_port_id(netdev, &ppid);
-		if (!ret)
-			ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
-	}
 	rtnl_unlock();
 
 	return ret;
@@ -580,24 +662,23 @@ static ssize_t phys_port_name_show(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
+	char name[IFNAMSIZ];
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the trylock/restart below.
+	 * returning early without hitting the locking section below.
 	 */
 	if (!netdev->netdev_ops->ndo_get_phys_port_name &&
 	    !netdev->devlink_port)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		char name[IFNAMSIZ];
+	ret = dev_get_phys_port_name(netdev, name, sizeof(name));
+	if (!ret)
+		ret = sysfs_emit(buf, "%s\n", name);
 
-		ret = dev_get_phys_port_name(netdev, name, sizeof(name));
-		if (!ret)
-			ret = sysfs_emit(buf, "%s\n", name);
-	}
 	rtnl_unlock();
 
 	return ret;
@@ -608,26 +689,25 @@ static ssize_t phys_switch_id_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
+	struct netdev_phys_item_id ppid = { };
 	ssize_t ret = -EINVAL;
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the trylock/restart below. This works
+	 * returning early without hitting the locking section below. This works
 	 * because recurse is false when calling dev_get_port_parent_id.
 	 */
 	if (!netdev->netdev_ops->ndo_get_port_parent_id &&
 	    !netdev->devlink_port)
 		return -EOPNOTSUPP;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
+	if (ret)
+		return ret;
 
-	if (dev_isalive(netdev)) {
-		struct netdev_phys_item_id ppid = { };
+	ret = dev_get_port_parent_id(netdev, &ppid, false);
+	if (!ret)
+		ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
 
-		ret = dev_get_port_parent_id(netdev, &ppid, false);
-		if (!ret)
-			ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
-	}
 	rtnl_unlock();
 
 	return ret;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 1f4d4b5570ab8..cb7fad8d1f95f 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -80,6 +80,11 @@ void rtnl_lock(void)
 }
 EXPORT_SYMBOL(rtnl_lock);
 
+int rtnl_lock_interruptible(void)
+{
+	return mutex_lock_interruptible(&rtnl_mutex);
+}
+
 int rtnl_lock_killable(void)
 {
 	return mutex_lock_killable(&rtnl_mutex);

From b7ecc1de51ca7d0a9fa8dbc3f756ab87b99a1838 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 4 Feb 2025 18:03:11 +0100
Subject: [PATCH 0154/2753] net-sysfs: move queue attribute groups outside the
 default groups

Rx/tx queues embed their own kobject for registering their per-queue
sysfs files. The issue is they're using the kobject default groups for
this and entirely rely on the kobject refcounting for releasing their
sysfs paths.

In order to remove rtnl_trylock calls we need sysfs files not to rely on
their associated kobject refcounting for their release. Thus we here
move queues sysfs files from the kobject default groups to their own
groups which can be removed separately.

Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250204170314.146022-3-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h     |  1 +
 include/net/netdev_rx_queue.h |  1 +
 net/core/net-sysfs.c          | 27 +++++++++++++++++++++------
 3 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2a59034a5fa2f..1dcc76af75203 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -658,6 +658,7 @@ struct netdev_queue {
 	struct Qdisc __rcu	*qdisc_sleeping;
 #ifdef CONFIG_SYSFS
 	struct kobject		kobj;
+	const struct attribute_group	**groups;
 #endif
 	unsigned long		tx_maxrate;
 	/*
diff --git a/include/net/netdev_rx_queue.h b/include/net/netdev_rx_queue.h
index 596836abf7bf4..af40842f229d9 100644
--- a/include/net/netdev_rx_queue.h
+++ b/include/net/netdev_rx_queue.h
@@ -16,6 +16,7 @@ struct netdev_rx_queue {
 	struct rps_dev_flow_table __rcu	*rps_flow_table;
 #endif
 	struct kobject			kobj;
+	const struct attribute_group	**groups;
 	struct net_device		*dev;
 	netdevice_tracker		dev_tracker;
 
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index e012234c739a3..0b7ee260613d5 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1188,7 +1188,6 @@ static void rx_queue_get_ownership(const struct kobject *kobj,
 static const struct kobj_type rx_queue_ktype = {
 	.sysfs_ops = &rx_queue_sysfs_ops,
 	.release = rx_queue_release,
-	.default_groups = rx_queue_default_groups,
 	.namespace = rx_queue_namespace,
 	.get_ownership = rx_queue_get_ownership,
 };
@@ -1222,20 +1221,27 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		goto err;
 
+	queue->groups = rx_queue_default_groups;
+	error = sysfs_create_groups(kobj, queue->groups);
+	if (error)
+		goto err;
+
 	if (dev->sysfs_rx_queue_group) {
 		error = sysfs_create_group(kobj, dev->sysfs_rx_queue_group);
 		if (error)
-			goto err;
+			goto err_default_groups;
 	}
 
 	error = rx_queue_default_mask(dev, queue);
 	if (error)
-		goto err;
+		goto err_default_groups;
 
 	kobject_uevent(kobj, KOBJ_ADD);
 
 	return error;
 
+err_default_groups:
+	sysfs_remove_groups(kobj, queue->groups);
 err:
 	kobject_put(kobj);
 	return error;
@@ -1280,12 +1286,14 @@ net_rx_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 	}
 
 	while (--i >= new_num) {
-		struct kobject *kobj = &dev->_rx[i].kobj;
+		struct netdev_rx_queue *queue = &dev->_rx[i];
+		struct kobject *kobj = &queue->kobj;
 
 		if (!refcount_read(&dev_net(dev)->ns.count))
 			kobj->uevent_suppress = 1;
 		if (dev->sysfs_rx_queue_group)
 			sysfs_remove_group(kobj, dev->sysfs_rx_queue_group);
+		sysfs_remove_groups(kobj, queue->groups);
 		kobject_put(kobj);
 	}
 
@@ -1872,7 +1880,6 @@ static void netdev_queue_get_ownership(const struct kobject *kobj,
 static const struct kobj_type netdev_queue_ktype = {
 	.sysfs_ops = &netdev_queue_sysfs_ops,
 	.release = netdev_queue_release,
-	.default_groups = netdev_queue_default_groups,
 	.namespace = netdev_queue_namespace,
 	.get_ownership = netdev_queue_get_ownership,
 };
@@ -1902,15 +1909,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	if (error)
 		goto err;
 
+	queue->groups = netdev_queue_default_groups;
+	error = sysfs_create_groups(kobj, queue->groups);
+	if (error)
+		goto err;
+
 	if (netdev_uses_bql(dev)) {
 		error = sysfs_create_group(kobj, &dql_group);
 		if (error)
-			goto err;
+			goto err_default_groups;
 	}
 
 	kobject_uevent(kobj, KOBJ_ADD);
 	return 0;
 
+err_default_groups:
+	sysfs_remove_groups(kobj, queue->groups);
 err:
 	kobject_put(kobj);
 	return error;
@@ -1965,6 +1979,7 @@ netdev_queue_update_kobjects(struct net_device *dev, int old_num, int new_num)
 		if (netdev_uses_bql(dev))
 			sysfs_remove_group(&queue->kobj, &dql_group);
 
+		sysfs_remove_groups(&queue->kobj, queue->groups);
 		kobject_put(&queue->kobj);
 	}
 

From 7e54f85c60828842be27e0149f3533357225090e Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 4 Feb 2025 18:03:12 +0100
Subject: [PATCH 0155/2753] net-sysfs: prevent uncleared queues from being
 re-added

With the (upcoming) removal of the rtnl_trylock/restart_syscall logic
and because of how Tx/Rx queues are implemented (and their
requirements), it might happen that a queue is re-added before having
the chance to be cleared. In such rare case, do not complete the queue
addition operation.

Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250204170314.146022-4-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/net-sysfs.c | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 0b7ee260613d5..027af27517fa3 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1210,6 +1210,22 @@ static int rx_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Rx queues are cleared in rx_queue_release to allow later
+	 * re-registration. This is triggered when their kobj refcount is
+	 * dropped.
+	 *
+	 * If a queue is removed while both a read (or write) operation and a
+	 * the re-addition of the same queue are pending (waiting on rntl_lock)
+	 * it might happen that the re-addition will execute before the read,
+	 * making the initial removal to never happen (queue's kobj refcount
+	 * won't drop enough because of the pending read). In such rare case,
+	 * return to allow the removal operation to complete.
+	 */
+	if (unlikely(kobj->state_initialized)) {
+		netdev_warn_once(dev, "Cannot re-add rx queues before their removal completed");
+		return -EAGAIN;
+	}
+
 	/* Kobject_put later will trigger rx_queue_release call which
 	 * decreases dev refcount: Take that reference here
 	 */
@@ -1898,6 +1914,22 @@ static int netdev_queue_add_kobject(struct net_device *dev, int index)
 	struct kobject *kobj = &queue->kobj;
 	int error = 0;
 
+	/* Tx queues are cleared in netdev_queue_release to allow later
+	 * re-registration. This is triggered when their kobj refcount is
+	 * dropped.
+	 *
+	 * If a queue is removed while both a read (or write) operation and a
+	 * the re-addition of the same queue are pending (waiting on rntl_lock)
+	 * it might happen that the re-addition will execute before the read,
+	 * making the initial removal to never happen (queue's kobj refcount
+	 * won't drop enough because of the pending read). In such rare case,
+	 * return to allow the removal operation to complete.
+	 */
+	if (unlikely(kobj->state_initialized)) {
+		netdev_warn_once(dev, "Cannot re-add tx queues before their removal completed");
+		return -EAGAIN;
+	}
+
 	/* Kobject_put later will trigger netdev_queue_release call
 	 * which decreases dev refcount: Take that reference here
 	 */

From b0b6fcfa6ad8433e22b050c72cfbeec2548744b9 Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Tue, 4 Feb 2025 18:03:13 +0100
Subject: [PATCH 0156/2753] net-sysfs: remove rtnl_trylock from queue
 attributes

Similar to the commit removing remove rtnl_trylock from device
attributes we here apply the same technique to networking queues.

Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250204170314.146022-5-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/net-sysfs.c | 147 ++++++++++++++++++++++++++-----------------
 1 file changed, 89 insertions(+), 58 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 027af27517fa3..3fe2c521e5740 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1348,9 +1348,11 @@ static int net_rx_queue_change_owner(struct net_device *dev, int num,
  */
 struct netdev_queue_attribute {
 	struct attribute attr;
-	ssize_t (*show)(struct netdev_queue *queue, char *buf);
-	ssize_t (*store)(struct netdev_queue *queue,
-			 const char *buf, size_t len);
+	ssize_t (*show)(struct kobject *kobj, struct attribute *attr,
+			struct netdev_queue *queue, char *buf);
+	ssize_t (*store)(struct kobject *kobj, struct attribute *attr,
+			 struct netdev_queue *queue, const char *buf,
+			 size_t len);
 };
 #define to_netdev_queue_attr(_attr) \
 	container_of(_attr, struct netdev_queue_attribute, attr)
@@ -1367,7 +1369,7 @@ static ssize_t netdev_queue_attr_show(struct kobject *kobj,
 	if (!attribute->show)
 		return -EIO;
 
-	return attribute->show(queue, buf);
+	return attribute->show(kobj, attr, queue, buf);
 }
 
 static ssize_t netdev_queue_attr_store(struct kobject *kobj,
@@ -1381,7 +1383,7 @@ static ssize_t netdev_queue_attr_store(struct kobject *kobj,
 	if (!attribute->store)
 		return -EIO;
 
-	return attribute->store(queue, buf, count);
+	return attribute->store(kobj, attr, queue, buf, count);
 }
 
 static const struct sysfs_ops netdev_queue_sysfs_ops = {
@@ -1389,7 +1391,8 @@ static const struct sysfs_ops netdev_queue_sysfs_ops = {
 	.store = netdev_queue_attr_store,
 };
 
-static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf)
+static ssize_t tx_timeout_show(struct kobject *kobj, struct attribute *attr,
+			       struct netdev_queue *queue, char *buf)
 {
 	unsigned long trans_timeout = atomic_long_read(&queue->trans_timeout);
 
@@ -1407,18 +1410,18 @@ static unsigned int get_netdev_queue_index(struct netdev_queue *queue)
 	return i;
 }
 
-static ssize_t traffic_class_show(struct netdev_queue *queue,
-				  char *buf)
+static ssize_t traffic_class_show(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
-	int num_tc, tc;
-	int index;
+	int num_tc, tc, index, ret;
 
 	if (!netif_is_multiqueue(dev))
 		return -ENOENT;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, queue->dev);
+	if (ret)
+		return ret;
 
 	index = get_netdev_queue_index(queue);
 
@@ -1445,24 +1448,25 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 }
 
 #ifdef CONFIG_XPS
-static ssize_t tx_maxrate_show(struct netdev_queue *queue,
-			       char *buf)
+static ssize_t tx_maxrate_show(struct kobject *kobj, struct attribute *attr,
+			       struct netdev_queue *queue, char *buf)
 {
 	return sysfs_emit(buf, "%lu\n", queue->tx_maxrate);
 }
 
-static ssize_t tx_maxrate_store(struct netdev_queue *queue,
-				const char *buf, size_t len)
+static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr,
+				struct netdev_queue *queue, const char *buf,
+				size_t len)
 {
-	struct net_device *dev = queue->dev;
 	int err, index = get_netdev_queue_index(queue);
+	struct net_device *dev = queue->dev;
 	u32 rate = 0;
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
 	/* The check is also done later; this helps returning early without
-	 * hitting the trylock/restart below.
+	 * hitting the locking section below.
 	 */
 	if (!dev->netdev_ops->ndo_set_tx_maxrate)
 		return -EOPNOTSUPP;
@@ -1471,18 +1475,21 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue,
 	if (err < 0)
 		return err;
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err)
+		return err;
 
 	err = -EOPNOTSUPP;
 	if (dev->netdev_ops->ndo_set_tx_maxrate)
 		err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
 
-	rtnl_unlock();
 	if (!err) {
 		queue->tx_maxrate = rate;
+		rtnl_unlock();
 		return len;
 	}
+
+	rtnl_unlock();
 	return err;
 }
 
@@ -1526,16 +1533,17 @@ static ssize_t bql_set(const char *buf, const size_t count,
 	return count;
 }
 
-static ssize_t bql_show_hold_time(struct netdev_queue *queue,
-				  char *buf)
+static ssize_t bql_show_hold_time(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
 	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->slack_hold_time));
 }
 
-static ssize_t bql_set_hold_time(struct netdev_queue *queue,
-				 const char *buf, size_t len)
+static ssize_t bql_set_hold_time(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, const char *buf,
+				 size_t len)
 {
 	struct dql *dql = &queue->dql;
 	unsigned int value;
@@ -1554,15 +1562,17 @@ static struct netdev_queue_attribute bql_hold_time_attribute __ro_after_init
 	= __ATTR(hold_time, 0644,
 		 bql_show_hold_time, bql_set_hold_time);
 
-static ssize_t bql_show_stall_thrs(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_thrs(struct kobject *kobj, struct attribute *attr,
+				   struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
 	return sysfs_emit(buf, "%u\n", jiffies_to_msecs(dql->stall_thrs));
 }
 
-static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
-				  const char *buf, size_t len)
+static ssize_t bql_set_stall_thrs(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, const char *buf,
+				  size_t len)
 {
 	struct dql *dql = &queue->dql;
 	unsigned int value;
@@ -1588,13 +1598,15 @@ static ssize_t bql_set_stall_thrs(struct netdev_queue *queue,
 static struct netdev_queue_attribute bql_stall_thrs_attribute __ro_after_init =
 	__ATTR(stall_thrs, 0644, bql_show_stall_thrs, bql_set_stall_thrs);
 
-static ssize_t bql_show_stall_max(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_max(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	return sysfs_emit(buf, "%u\n", READ_ONCE(queue->dql.stall_max));
 }
 
-static ssize_t bql_set_stall_max(struct netdev_queue *queue,
-				 const char *buf, size_t len)
+static ssize_t bql_set_stall_max(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, const char *buf,
+				 size_t len)
 {
 	WRITE_ONCE(queue->dql.stall_max, 0);
 	return len;
@@ -1603,7 +1615,8 @@ static ssize_t bql_set_stall_max(struct netdev_queue *queue,
 static struct netdev_queue_attribute bql_stall_max_attribute __ro_after_init =
 	__ATTR(stall_max, 0644, bql_show_stall_max, bql_set_stall_max);
 
-static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
+static ssize_t bql_show_stall_cnt(struct kobject *kobj, struct attribute *attr,
+				  struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
@@ -1613,8 +1626,8 @@ static ssize_t bql_show_stall_cnt(struct netdev_queue *queue, char *buf)
 static struct netdev_queue_attribute bql_stall_cnt_attribute __ro_after_init =
 	__ATTR(stall_cnt, 0444, bql_show_stall_cnt, NULL);
 
-static ssize_t bql_show_inflight(struct netdev_queue *queue,
-				 char *buf)
+static ssize_t bql_show_inflight(struct kobject *kobj, struct attribute *attr,
+				 struct netdev_queue *queue, char *buf)
 {
 	struct dql *dql = &queue->dql;
 
@@ -1625,13 +1638,16 @@ static struct netdev_queue_attribute bql_inflight_attribute __ro_after_init =
 	__ATTR(inflight, 0444, bql_show_inflight, NULL);
 
 #define BQL_ATTR(NAME, FIELD)						\
-static ssize_t bql_show_ ## NAME(struct netdev_queue *queue,		\
-				 char *buf)				\
+static ssize_t bql_show_ ## NAME(struct kobject *kobj,			\
+				 struct attribute *attr,		\
+				 struct netdev_queue *queue, char *buf)	\
 {									\
 	return bql_show(buf, queue->dql.FIELD);				\
 }									\
 									\
-static ssize_t bql_set_ ## NAME(struct netdev_queue *queue,		\
+static ssize_t bql_set_ ## NAME(struct kobject *kobj,			\
+				struct attribute *attr,			\
+				struct netdev_queue *queue,		\
 				const char *buf, size_t len)		\
 {									\
 	return bql_set(buf, len, &queue->dql.FIELD);			\
@@ -1717,19 +1733,21 @@ static ssize_t xps_queue_show(struct net_device *dev, unsigned int index,
 	return len < PAGE_SIZE ? len : -EINVAL;
 }
 
-static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf)
+static ssize_t xps_cpus_show(struct kobject *kobj, struct attribute *attr,
+			     struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
-	int len, tc;
+	int len, tc, ret;
 
 	if (!netif_is_multiqueue(dev))
 		return -ENOENT;
 
 	index = get_netdev_queue_index(queue);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, queue->dev);
+	if (ret)
+		return ret;
 
 	/* If queue belongs to subordinate dev use its map */
 	dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
@@ -1740,18 +1758,21 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue, char *buf)
 		return -EINVAL;
 	}
 
-	/* Make sure the subordinate device can't be freed */
-	get_device(&dev->dev);
+	/* Increase the net device refcnt to make sure it won't be freed while
+	 * xps_queue_show is running.
+	 */
+	dev_hold(dev);
 	rtnl_unlock();
 
 	len = xps_queue_show(dev, index, tc, buf, XPS_CPUS);
 
-	put_device(&dev->dev);
+	dev_put(dev);
 	return len;
 }
 
-static ssize_t xps_cpus_store(struct netdev_queue *queue,
-			      const char *buf, size_t len)
+static ssize_t xps_cpus_store(struct kobject *kobj, struct attribute *attr,
+			      struct netdev_queue *queue, const char *buf,
+			      size_t len)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
@@ -1775,9 +1796,10 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 		return err;
 	}
 
-	if (!rtnl_trylock()) {
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err) {
 		free_cpumask_var(mask);
-		return restart_syscall();
+		return err;
 	}
 
 	err = netif_set_xps_queue(dev, mask, index);
@@ -1791,26 +1813,34 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 static struct netdev_queue_attribute xps_cpus_attribute __ro_after_init
 	= __ATTR_RW(xps_cpus);
 
-static ssize_t xps_rxqs_show(struct netdev_queue *queue, char *buf)
+static ssize_t xps_rxqs_show(struct kobject *kobj, struct attribute *attr,
+			     struct netdev_queue *queue, char *buf)
 {
 	struct net_device *dev = queue->dev;
 	unsigned int index;
-	int tc;
+	int tc, ret;
 
 	index = get_netdev_queue_index(queue);
 
-	if (!rtnl_trylock())
-		return restart_syscall();
+	ret = sysfs_rtnl_lock(kobj, attr, dev);
+	if (ret)
+		return ret;
 
 	tc = netdev_txq_to_tc(dev, index);
+
+	/* Increase the net device refcnt to make sure it won't be freed while
+	 * xps_queue_show is running.
+	 */
+	dev_hold(dev);
 	rtnl_unlock();
-	if (tc < 0)
-		return -EINVAL;
 
-	return xps_queue_show(dev, index, tc, buf, XPS_RXQS);
+	ret = tc >= 0 ? xps_queue_show(dev, index, tc, buf, XPS_RXQS) : -EINVAL;
+	dev_put(dev);
+	return ret;
 }
 
-static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
+static ssize_t xps_rxqs_store(struct kobject *kobj, struct attribute *attr,
+			      struct netdev_queue *queue, const char *buf,
 			      size_t len)
 {
 	struct net_device *dev = queue->dev;
@@ -1834,9 +1864,10 @@ static ssize_t xps_rxqs_store(struct netdev_queue *queue, const char *buf,
 		return err;
 	}
 
-	if (!rtnl_trylock()) {
+	err = sysfs_rtnl_lock(kobj, attr, dev);
+	if (err) {
 		bitmap_free(mask);
-		return restart_syscall();
+		return err;
 	}
 
 	cpus_read_lock();

From cbecd06a224962941f116e53f5673476ef6cd3f3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Feb 2025 13:48:50 -0800
Subject: [PATCH 0157/2753] selftests: net: suppress ReST file generation when
 building selftests

Some selftests need libynl.a. When building it try to skip
generating the ReST documentation, libynl.a does not depend
on them.

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250203214850.1282291-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ynl.mk | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/ynl.mk b/tools/testing/selftests/net/ynl.mk
index 12e7cae251be3..e907c2751956f 100644
--- a/tools/testing/selftests/net/ynl.mk
+++ b/tools/testing/selftests/net/ynl.mk
@@ -27,7 +27,8 @@ $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig:
 
 $(OUTPUT)/libynl.a: $(YNL_SPECS) $(OUTPUT)/.libynl-$(YNL_GENS_HASH).sig
 	$(Q)rm -f $(top_srcdir)/tools/net/ynl/libynl.a
-	$(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl GENS="$(YNL_GENS)" libynl.a
+	$(Q)$(MAKE) -C $(top_srcdir)/tools/net/ynl \
+		GENS="$(YNL_GENS)" RSTS="" libynl.a
 	$(Q)cp $(top_srcdir)/tools/net/ynl/libynl.a $(OUTPUT)/libynl.a
 
 EXTRA_CLEAN += \

From d9e9f6d7b7d0c520bb87f19d2cbc57aeeb2091d5 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 4 Feb 2025 18:37:15 +0100
Subject: [PATCH 0158/2753] bridge: mdb: Allow replace of a host-joined group

Attempts to replace an MDB group membership of the host itself are
currently bounced:

 # ip link add name br up type bridge vlan_filtering 1
 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2
 # bridge mdb replace dev br port br grp 239.0.0.1 vid 2
 Error: bridge: Group is already joined by host.

A similar operation done on a member port would succeed. Ignore the check
for replacement of host group memberships as well.

The bit of code that this enables is br_multicast_host_join(), which, for
already-joined groups only refreshes the MC group expiration timer, which
is desirable; and a userspace notification, also desirable.

Change a selftest that exercises this code path from expecting a rejection
to expecting a pass. The rest of MDB selftests pass without modification.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/e5c5188b9787ae806609e7ca3aa2a0a501b9b5c4.1738685648.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/bridge/br_mdb.c                                  | 2 +-
 tools/testing/selftests/net/forwarding/bridge_mdb.sh | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 1a52a0bca086d..7e1ad229e1330 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -1040,7 +1040,7 @@ static int br_mdb_add_group(const struct br_mdb_config *cfg,
 
 	/* host join */
 	if (!port) {
-		if (mp->host_joined) {
+		if (mp->host_joined && !(cfg->nlflags & NLM_F_REPLACE)) {
 			NL_SET_ERR_MSG_MOD(extack, "Group is already joined by host");
 			return -EEXIST;
 		}
diff --git a/tools/testing/selftests/net/forwarding/bridge_mdb.sh b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
index d9d587454d207..8c1597ebc2d38 100755
--- a/tools/testing/selftests/net/forwarding/bridge_mdb.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_mdb.sh
@@ -149,7 +149,7 @@ cfg_test_host_common()
 	check_err $? "Failed to add $name host entry"
 
 	bridge mdb replace dev br0 port br0 grp $grp $state vid 10 &> /dev/null
-	check_fail $? "Managed to replace $name host entry"
+	check_err $? "Failed to replace $name host entry"
 
 	bridge mdb del dev br0 port br0 grp $grp $state vid 10
 	bridge mdb get dev br0 grp $grp vid 10 &> /dev/null

From 863257c29fe9c882b21fe5d1596081ef55c4875a Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 4 Feb 2025 13:24:31 +1030
Subject: [PATCH 0159/2753] cxgb4: Avoid a -Wflex-array-member-not-at-end
 warning

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

Move the conflicting declaration to the end of the structure. Notice
that `struct ethtool_dump` is a flexible structure --a structure that
contains a flexible-array member.

Fix the following warning:
./drivers/net/ethernet/chelsio/cxgb4/cxgb4.h:1215:29: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/Z6GBZ4brXYffLkt_@kspp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
index c7c2c15a18155..95e6f015a6af0 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h
@@ -1211,9 +1211,6 @@ struct adapter {
 	struct timer_list flower_stats_timer;
 	struct work_struct flower_stats_work;
 
-	/* Ethtool Dump */
-	struct ethtool_dump eth_dump;
-
 	/* HMA */
 	struct hma_data hma;
 
@@ -1233,6 +1230,10 @@ struct adapter {
 
 	/* Ethtool n-tuple */
 	struct cxgb4_ethtool_filter *ethtool_filters;
+
+	/* Ethtool Dump */
+	/* Must be last - ends in a flex-array member. */
+	struct ethtool_dump eth_dump;
 };
 
 /* Support for "sched-class" command to allow a TX Scheduling Class to be

From 6cccb3bb0561812539d7f0ab35382e8d8998076a Mon Sep 17 00:00:00 2001
From: Aswin Karuvally <aswin@linux.ibm.com>
Date: Tue, 4 Feb 2025 11:31:35 +0100
Subject: [PATCH 0160/2753] s390/net: Remove LCS driver

The original Open Systems Adapter (OSA) was introduced by IBM in the
mid-90s. These were then superseded by OSA-Express in 1999 which used
Queued Direct IO to greatly improve throughput. The newer cards
retained the older, slower non-QDIO (OSE) modes for compatibility with
older systems. In Linux, the lcs driver was responsible for cards
operating in the older OSE mode and the qeth driver was introduced to
allow the OSA-Express cards to operate in the newer QDIO (OSD) mode.

For an S390 machine from 1998 or later, there is no reason to use the
OSE mode and lcs driver as all OSA cards since 1999 provide the faster
OSD mode. As a result, it's been years since we have heard of a
customer configuration involving the lcs driver.

This patch removes the lcs driver. The technology it supports has been
obsolete for past 25+ years and is irrelevant for current use cases.

Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Acked-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Peter Oberparleiter <oberpar@linux.ibm.com>
Signed-off-by: Aswin Karuvally <aswin@linux.ibm.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250204103135.1619097-1-wintera@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/arch/s390/driver-model.rst |    2 +-
 arch/s390/include/asm/irq.h              |    1 -
 arch/s390/kernel/irq.c                   |    1 -
 drivers/s390/net/Kconfig                 |   11 +-
 drivers/s390/net/Makefile                |    1 -
 drivers/s390/net/lcs.c                   | 2385 ----------------------
 drivers/s390/net/lcs.h                   |  342 ----
 7 files changed, 2 insertions(+), 2741 deletions(-)
 delete mode 100644 drivers/s390/net/lcs.c
 delete mode 100644 drivers/s390/net/lcs.h

diff --git a/Documentation/arch/s390/driver-model.rst b/Documentation/arch/s390/driver-model.rst
index ad4bc2dbea435..ad18f129fb0bc 100644
--- a/Documentation/arch/s390/driver-model.rst
+++ b/Documentation/arch/s390/driver-model.rst
@@ -244,7 +244,7 @@ information about the interrupt from the irb parameter.
 --------------------
 
 The ccwgroup mechanism is designed to handle devices consisting of multiple ccw
-devices, like lcs or ctc.
+devices, like qeth or ctc.
 
 The ccw driver provides a 'group' attribute. Piping bus ids of ccw devices to
 this attributes creates a ccwgroup device consisting of these ccw devices (if
diff --git a/arch/s390/include/asm/irq.h b/arch/s390/include/asm/irq.h
index d9e705f4a697e..bde6a496df5f8 100644
--- a/arch/s390/include/asm/irq.h
+++ b/arch/s390/include/asm/irq.h
@@ -54,7 +54,6 @@ enum interruption_class {
 	IRQIO_C70,
 	IRQIO_TAP,
 	IRQIO_VMR,
-	IRQIO_LCS,
 	IRQIO_CTC,
 	IRQIO_ADM,
 	IRQIO_CSC,
diff --git a/arch/s390/kernel/irq.c b/arch/s390/kernel/irq.c
index ef7be599e1f78..7ca157ffab30e 100644
--- a/arch/s390/kernel/irq.c
+++ b/arch/s390/kernel/irq.c
@@ -84,7 +84,6 @@ static const struct irq_class irqclass_sub_desc[] = {
 	{.irq = IRQIO_C70,  .name = "C70", .desc = "[I/O] 3270"},
 	{.irq = IRQIO_TAP,  .name = "TAP", .desc = "[I/O] Tape"},
 	{.irq = IRQIO_VMR,  .name = "VMR", .desc = "[I/O] Unit Record Devices"},
-	{.irq = IRQIO_LCS,  .name = "LCS", .desc = "[I/O] LCS"},
 	{.irq = IRQIO_CTC,  .name = "CTC", .desc = "[I/O] CTC"},
 	{.irq = IRQIO_ADM,  .name = "ADM", .desc = "[I/O] EADM Subchannel"},
 	{.irq = IRQIO_CSC,  .name = "CSC", .desc = "[I/O] CHSC Subchannel"},
diff --git a/drivers/s390/net/Kconfig b/drivers/s390/net/Kconfig
index c61e6427384c3..9eb9e3c49f815 100644
--- a/drivers/s390/net/Kconfig
+++ b/drivers/s390/net/Kconfig
@@ -2,15 +2,6 @@
 menu "S/390 network device drivers"
 	depends on NETDEVICES && S390
 
-config LCS
-	def_tristate m
-	prompt "Lan Channel Station Interface"
-	depends on CCW && NETDEVICES && ETHERNET
-	help
-	  Select this option if you want to use LCS networking on IBM System z.
-	  To compile as a module, choose M. The module name is lcs.
-	  If you do not use LCS, choose N.
-
 config CTCM
 	def_tristate m
 	prompt "CTC and MPC SNA device support"
@@ -98,7 +89,7 @@ config QETH_OSX
 
 config CCWGROUP
 	tristate
-	default (LCS || CTCM || QETH || SMC)
+	default (CTCM || QETH || SMC)
 
 config ISM
 	tristate "Support for ISM vPCI Adapter"
diff --git a/drivers/s390/net/Makefile b/drivers/s390/net/Makefile
index bc55ec316adb1..b5aaba2901274 100644
--- a/drivers/s390/net/Makefile
+++ b/drivers/s390/net/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_CTCM) += ctcm.o fsm.o
 obj-$(CONFIG_NETIUCV) += netiucv.o fsm.o
 obj-$(CONFIG_SMSGIUCV) += smsgiucv.o
 obj-$(CONFIG_SMSGIUCV_EVENT) += smsgiucv_app.o
-obj-$(CONFIG_LCS) += lcs.o
 qeth-y += qeth_core_sys.o qeth_core_main.o qeth_core_mpc.o qeth_ethtool.o
 obj-$(CONFIG_QETH) += qeth.o
 qeth_l2-y += qeth_l2_main.o qeth_l2_sys.o
diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c
deleted file mode 100644
index 88db8378325a3..0000000000000
--- a/drivers/s390/net/lcs.c
+++ /dev/null
@@ -1,2385 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0+
-/*
- *  Linux for S/390 LAN channel station device driver
- *
- *  Copyright IBM Corp. 1999, 2009
- *  Author(s): Original Code written by
- *			DJ Barrow <djbarrow@de.ibm.com,barrow_dj@yahoo.com>
- *	       Rewritten by
- *			Frank Pavlic <fpavlic@de.ibm.com> and
- *			Martin Schwidefsky <schwidefsky@de.ibm.com>
- */
-
-#define KMSG_COMPONENT		"lcs"
-#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt
-
-#include <linux/module.h>
-#include <linux/if.h>
-#include <linux/netdevice.h>
-#include <linux/etherdevice.h>
-#include <linux/inetdevice.h>
-#include <linux/in.h>
-#include <linux/igmp.h>
-#include <linux/delay.h>
-#include <linux/kthread.h>
-#include <linux/slab.h>
-#include <net/arp.h>
-#include <net/ip.h>
-
-#include <asm/debug.h>
-#include <asm/idals.h>
-#include <asm/timex.h>
-#include <linux/device.h>
-#include <asm/ccwgroup.h>
-
-#include "lcs.h"
-
-
-/*
- * initialization string for output
- */
-
-static char version[] __initdata = "LCS driver";
-
-/*
-  * the root device for lcs group devices
-  */
-static struct device *lcs_root_dev;
-
-/*
- * Some prototypes.
- */
-static void lcs_tasklet(unsigned long);
-static void lcs_start_kernel_thread(struct work_struct *);
-static void lcs_get_frames_cb(struct lcs_channel *, struct lcs_buffer *);
-#ifdef CONFIG_IP_MULTICAST
-static int lcs_send_delipm(struct lcs_card *, struct lcs_ipm_list *);
-#endif /* CONFIG_IP_MULTICAST */
-static int lcs_recovery(void *ptr);
-
-/*
- * Debug Facility Stuff
- */
-static char debug_buffer[255];
-static debug_info_t *lcs_dbf_setup;
-static debug_info_t *lcs_dbf_trace;
-
-/*
- *  LCS Debug Facility functions
- */
-static void
-lcs_unregister_debug_facility(void)
-{
-	debug_unregister(lcs_dbf_setup);
-	debug_unregister(lcs_dbf_trace);
-}
-
-static int
-lcs_register_debug_facility(void)
-{
-	lcs_dbf_setup = debug_register("lcs_setup", 2, 1, 8);
-	lcs_dbf_trace = debug_register("lcs_trace", 4, 1, 8);
-	if (lcs_dbf_setup == NULL || lcs_dbf_trace == NULL) {
-		pr_err("Not enough memory for debug facility.\n");
-		lcs_unregister_debug_facility();
-		return -ENOMEM;
-	}
-	debug_register_view(lcs_dbf_setup, &debug_hex_ascii_view);
-	debug_set_level(lcs_dbf_setup, 2);
-	debug_register_view(lcs_dbf_trace, &debug_hex_ascii_view);
-	debug_set_level(lcs_dbf_trace, 2);
-	return 0;
-}
-
-/*
- * Allocate io buffers.
- */
-static int
-lcs_alloc_channel(struct lcs_channel *channel)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ichalloc");
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		/* alloc memory fo iobuffer */
-		channel->iob[cnt].data =
-			kzalloc(LCS_IOBUFFERSIZE, GFP_DMA | GFP_KERNEL);
-		if (channel->iob[cnt].data == NULL)
-			break;
-		channel->iob[cnt].state = LCS_BUF_STATE_EMPTY;
-	}
-	if (cnt < LCS_NUM_BUFFS) {
-		/* Not all io buffers could be allocated. */
-		LCS_DBF_TEXT(2, setup, "echalloc");
-		while (cnt-- > 0)
-			kfree(channel->iob[cnt].data);
-		return -ENOMEM;
-	}
-	return 0;
-}
-
-/*
- * Free io buffers.
- */
-static void
-lcs_free_channel(struct lcs_channel *channel)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ichfree");
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		kfree(channel->iob[cnt].data);
-		channel->iob[cnt].data = NULL;
-	}
-}
-
-/*
- * Cleanup channel.
- */
-static void
-lcs_cleanup_channel(struct lcs_channel *channel)
-{
-	LCS_DBF_TEXT(3, setup, "cleanch");
-	/* Kill write channel tasklets. */
-	tasklet_kill(&channel->irq_tasklet);
-	/* Free channel buffers. */
-	lcs_free_channel(channel);
-}
-
-/*
- * LCS free memory for card and channels.
- */
-static void
-lcs_free_card(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, setup, "remcard");
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-	kfree(card);
-}
-
-/*
- * LCS alloc memory for card and channels
- */
-static struct lcs_card *
-lcs_alloc_card(void)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, setup, "alloclcs");
-
-	card = kzalloc(sizeof(struct lcs_card), GFP_KERNEL | GFP_DMA);
-	if (card == NULL)
-		return NULL;
-	card->lan_type = LCS_FRAME_TYPE_AUTO;
-	card->pkt_seq = 0;
-	card->lancmd_timeout = LCS_LANCMD_TIMEOUT_DEFAULT;
-	/* Allocate io buffers for the read channel. */
-	rc = lcs_alloc_channel(&card->read);
-	if (rc){
-		LCS_DBF_TEXT(2, setup, "iccwerr");
-		lcs_free_card(card);
-		return NULL;
-	}
-	/* Allocate io buffers for the write channel. */
-	rc = lcs_alloc_channel(&card->write);
-	if (rc) {
-		LCS_DBF_TEXT(2, setup, "iccwerr");
-		lcs_cleanup_channel(&card->read);
-		lcs_free_card(card);
-		return NULL;
-	}
-
-#ifdef CONFIG_IP_MULTICAST
-	INIT_LIST_HEAD(&card->ipm_list);
-#endif
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-	return card;
-}
-
-/*
- * Setup read channel.
- */
-static void
-lcs_setup_read_ccws(struct lcs_card *card)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(2, setup, "ireadccw");
-	/* Setup read ccws. */
-	memset(card->read.ccws, 0, sizeof (struct ccw1) * (LCS_NUM_BUFFS + 1));
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		card->read.ccws[cnt].cmd_code = LCS_CCW_READ;
-		card->read.ccws[cnt].count = LCS_IOBUFFERSIZE;
-		card->read.ccws[cnt].flags =
-			CCW_FLAG_CC | CCW_FLAG_SLI | CCW_FLAG_PCI;
-		/*
-		 * Note: we have allocated the buffer with GFP_DMA, so
-		 * we do not need to do set_normalized_cda.
-		 */
-		card->read.ccws[cnt].cda =
-			virt_to_dma32(card->read.iob[cnt].data);
-		((struct lcs_header *)
-		 card->read.iob[cnt].data)->offset = LCS_ILLEGAL_OFFSET;
-		card->read.iob[cnt].callback = lcs_get_frames_cb;
-		card->read.iob[cnt].state = LCS_BUF_STATE_READY;
-		card->read.iob[cnt].count = LCS_IOBUFFERSIZE;
-	}
-	card->read.ccws[0].flags &= ~CCW_FLAG_PCI;
-	card->read.ccws[LCS_NUM_BUFFS - 1].flags &= ~CCW_FLAG_PCI;
-	card->read.ccws[LCS_NUM_BUFFS - 1].flags |= CCW_FLAG_SUSPEND;
-	/* Last ccw is a tic (transfer in channel). */
-	card->read.ccws[LCS_NUM_BUFFS].cmd_code = LCS_CCW_TRANSFER;
-	card->read.ccws[LCS_NUM_BUFFS].cda = virt_to_dma32(card->read.ccws);
-	/* Setg initial state of the read channel. */
-	card->read.state = LCS_CH_STATE_INIT;
-
-	card->read.io_idx = 0;
-	card->read.buf_idx = 0;
-}
-
-static void
-lcs_setup_read(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(3, setup, "initread");
-
-	lcs_setup_read_ccws(card);
-	/* Initialize read channel tasklet. */
-	card->read.irq_tasklet.data = (unsigned long) &card->read;
-	card->read.irq_tasklet.func = lcs_tasklet;
-	/* Initialize waitqueue. */
-	init_waitqueue_head(&card->read.wait_q);
-}
-
-/*
- * Setup write channel.
- */
-static void
-lcs_setup_write_ccws(struct lcs_card *card)
-{
-	int cnt;
-
-	LCS_DBF_TEXT(3, setup, "iwritccw");
-	/* Setup write ccws. */
-	memset(card->write.ccws, 0, sizeof(struct ccw1) * (LCS_NUM_BUFFS + 1));
-	for (cnt = 0; cnt < LCS_NUM_BUFFS; cnt++) {
-		card->write.ccws[cnt].cmd_code = LCS_CCW_WRITE;
-		card->write.ccws[cnt].count = 0;
-		card->write.ccws[cnt].flags =
-			CCW_FLAG_SUSPEND | CCW_FLAG_CC | CCW_FLAG_SLI;
-		/*
-		 * Note: we have allocated the buffer with GFP_DMA, so
-		 * we do not need to do set_normalized_cda.
-		 */
-		card->write.ccws[cnt].cda =
-			virt_to_dma32(card->write.iob[cnt].data);
-	}
-	/* Last ccw is a tic (transfer in channel). */
-	card->write.ccws[LCS_NUM_BUFFS].cmd_code = LCS_CCW_TRANSFER;
-	card->write.ccws[LCS_NUM_BUFFS].cda = virt_to_dma32(card->write.ccws);
-	/* Set initial state of the write channel. */
-	card->read.state = LCS_CH_STATE_INIT;
-
-	card->write.io_idx = 0;
-	card->write.buf_idx = 0;
-}
-
-static void
-lcs_setup_write(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(3, setup, "initwrit");
-
-	lcs_setup_write_ccws(card);
-	/* Initialize write channel tasklet. */
-	card->write.irq_tasklet.data = (unsigned long) &card->write;
-	card->write.irq_tasklet.func = lcs_tasklet;
-	/* Initialize waitqueue. */
-	init_waitqueue_head(&card->write.wait_q);
-}
-
-static void
-lcs_set_allowed_threads(struct lcs_card *card, unsigned long threads)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-	card->thread_allowed_mask = threads;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-	wake_up(&card->wait_q);
-}
-static int lcs_threads_running(struct lcs_card *card, unsigned long threads)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        rc = (card->thread_running_mask & threads);
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-static int
-lcs_wait_for_threads(struct lcs_card *card, unsigned long threads)
-{
-        return wait_event_interruptible(card->wait_q,
-                        lcs_threads_running(card, threads) == 0);
-}
-
-static int lcs_set_thread_start_bit(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        if ( !(card->thread_allowed_mask & thread) ||
-              (card->thread_start_mask & thread) ) {
-                spin_unlock_irqrestore(&card->mask_lock, flags);
-                return -EPERM;
-        }
-        card->thread_start_mask |= thread;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return 0;
-}
-
-static void
-lcs_clear_thread_running_bit(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        card->thread_running_mask &= ~thread;
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        wake_up(&card->wait_q);
-}
-
-static int __lcs_do_run_thread(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        if (card->thread_start_mask & thread){
-                if ((card->thread_allowed_mask & thread) &&
-                    !(card->thread_running_mask & thread)){
-                        rc = 1;
-                        card->thread_start_mask &= ~thread;
-                        card->thread_running_mask |= thread;
-                } else
-                        rc = -EPERM;
-        }
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-static int
-lcs_do_run_thread(struct lcs_card *card, unsigned long thread)
-{
-        int rc = 0;
-        wait_event(card->wait_q,
-                   (rc = __lcs_do_run_thread(card, thread)) >= 0);
-        return rc;
-}
-
-static int
-lcs_do_start_thread(struct lcs_card *card, unsigned long thread)
-{
-        unsigned long flags;
-        int rc = 0;
-
-	spin_lock_irqsave(&card->mask_lock, flags);
-        LCS_DBF_TEXT_(4, trace, "  %02x%02x%02x",
-                        (u8) card->thread_start_mask,
-                        (u8) card->thread_allowed_mask,
-                        (u8) card->thread_running_mask);
-        rc = (card->thread_start_mask & thread);
-	spin_unlock_irqrestore(&card->mask_lock, flags);
-        return rc;
-}
-
-/*
- * Initialize channels,card and state machines.
- */
-static void
-lcs_setup_card(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, setup, "initcard");
-	LCS_DBF_HEX(2, setup, &card, sizeof(void*));
-
-	lcs_setup_read(card);
-	lcs_setup_write(card);
-	/* Set cards initial state. */
-	card->state = DEV_STATE_DOWN;
-	card->tx_buffer = NULL;
-	card->tx_emitted = 0;
-
-	init_waitqueue_head(&card->wait_q);
-	spin_lock_init(&card->lock);
-	spin_lock_init(&card->ipm_lock);
-	spin_lock_init(&card->mask_lock);
-#ifdef CONFIG_IP_MULTICAST
-	INIT_LIST_HEAD(&card->ipm_list);
-#endif
-	INIT_LIST_HEAD(&card->lancmd_waiters);
-}
-
-static void lcs_clear_multicast_list(struct lcs_card *card)
-{
-#ifdef	CONFIG_IP_MULTICAST
-	struct lcs_ipm_list *ipm;
-	unsigned long flags;
-
-	/* Free multicast list. */
-	LCS_DBF_TEXT(3, setup, "clmclist");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	while (!list_empty(&card->ipm_list)){
-		ipm = list_entry(card->ipm_list.next,
-				 struct lcs_ipm_list, list);
-		list_del(&ipm->list);
-		if (ipm->ipm_state != LCS_IPM_STATE_SET_REQUIRED){
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			lcs_send_delipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-		}
-		kfree(ipm);
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-#endif
-}
-
-/*
- * Cleanup channels,card and state machines.
- */
-static void
-lcs_cleanup_card(struct lcs_card *card)
-{
-
-	LCS_DBF_TEXT(3, setup, "cleancrd");
-	LCS_DBF_HEX(2,setup,&card,sizeof(void*));
-
-	if (card->dev != NULL)
-		free_netdev(card->dev);
-	/* Cleanup channels. */
-	lcs_cleanup_channel(&card->write);
-	lcs_cleanup_channel(&card->read);
-}
-
-/*
- * Start channel.
- */
-static int
-lcs_start_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT_(4, trace,"ssch%s", dev_name(&channel->ccwdev->dev));
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_start(channel->ccwdev,
-			      channel->ccws + channel->io_idx, 0, 0,
-			      DOIO_DENY_PREFETCH | DOIO_ALLOW_SUSPEND);
-	if (rc == 0)
-		channel->state = LCS_CH_STATE_RUNNING;
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4,trace,"essh%s",
-			      dev_name(&channel->ccwdev->dev));
-		dev_err(&channel->ccwdev->dev,
-			"Starting an LCS device resulted in an error,"
-			" rc=%d!\n", rc);
-	}
-	return rc;
-}
-
-static int
-lcs_clear_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4,trace,"clearch");
-	LCS_DBF_TEXT_(4, trace, "%s", dev_name(&channel->ccwdev->dev));
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_clear(channel->ccwdev, 0);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ecsc%s",
-			      dev_name(&channel->ccwdev->dev));
-		return rc;
-	}
-	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_CLEARED));
-	channel->state = LCS_CH_STATE_STOPPED;
-	return rc;
-}
-
-
-/*
- * Stop channel.
- */
-static int
-lcs_stop_channel(struct lcs_channel *channel)
-{
-	unsigned long flags;
-	int rc;
-
-	if (channel->state == LCS_CH_STATE_STOPPED)
-		return 0;
-	LCS_DBF_TEXT(4,trace,"haltsch");
-	LCS_DBF_TEXT_(4, trace, "%s", dev_name(&channel->ccwdev->dev));
-	channel->state = LCS_CH_STATE_INIT;
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	rc = ccw_device_halt(channel->ccwdev, 0);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ehsc%s",
-			      dev_name(&channel->ccwdev->dev));
-		return rc;
-	}
-	/* Asynchronous halt initialted. Wait for its completion. */
-	wait_event(channel->wait_q, (channel->state == LCS_CH_STATE_HALTED));
-	lcs_clear_channel(channel);
-	return 0;
-}
-
-/*
- * start read and write channel
- */
-static int
-lcs_start_channels(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "chstart");
-	/* start read channel */
-	rc = lcs_start_channel(&card->read);
-	if (rc)
-		return rc;
-	/* start write channel */
-	rc = lcs_start_channel(&card->write);
-	if (rc)
-		lcs_stop_channel(&card->read);
-	return rc;
-}
-
-/*
- * stop read and write channel
- */
-static int
-lcs_stop_channels(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, trace, "chhalt");
-	lcs_stop_channel(&card->read);
-	lcs_stop_channel(&card->write);
-	return 0;
-}
-
-/*
- * Get empty buffer.
- */
-static struct lcs_buffer *
-__lcs_get_buffer(struct lcs_channel *channel)
-{
-	int index;
-
-	LCS_DBF_TEXT(5, trace, "_getbuff");
-	index = channel->io_idx;
-	do {
-		if (channel->iob[index].state == LCS_BUF_STATE_EMPTY) {
-			channel->iob[index].state = LCS_BUF_STATE_LOCKED;
-			return channel->iob + index;
-		}
-		index = (index + 1) & (LCS_NUM_BUFFS - 1);
-	} while (index != channel->io_idx);
-	return NULL;
-}
-
-static struct lcs_buffer *
-lcs_get_buffer(struct lcs_channel *channel)
-{
-	struct lcs_buffer *buffer;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(5, trace, "getbuff");
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer = __lcs_get_buffer(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	return buffer;
-}
-
-/*
- * Resume channel program if the channel is suspended.
- */
-static int
-__lcs_resume_channel(struct lcs_channel *channel)
-{
-	int rc;
-
-	if (channel->state != LCS_CH_STATE_SUSPENDED)
-		return 0;
-	if (channel->ccws[channel->io_idx].flags & CCW_FLAG_SUSPEND)
-		return 0;
-	LCS_DBF_TEXT_(5, trace, "rsch%s", dev_name(&channel->ccwdev->dev));
-	rc = ccw_device_resume(channel->ccwdev);
-	if (rc) {
-		LCS_DBF_TEXT_(4, trace, "ersc%s",
-			      dev_name(&channel->ccwdev->dev));
-		dev_err(&channel->ccwdev->dev,
-			"Sending data from the LCS device to the LAN failed"
-			" with rc=%d\n",rc);
-	} else
-		channel->state = LCS_CH_STATE_RUNNING;
-	return rc;
-
-}
-
-/*
- * Make a buffer ready for processing.
- */
-static void __lcs_ready_buffer_bits(struct lcs_channel *channel, int index)
-{
-	int prev, next;
-
-	LCS_DBF_TEXT(5, trace, "rdybits");
-	prev = (index - 1) & (LCS_NUM_BUFFS - 1);
-	next = (index + 1) & (LCS_NUM_BUFFS - 1);
-	/* Check if we may clear the suspend bit of this buffer. */
-	if (channel->ccws[next].flags & CCW_FLAG_SUSPEND) {
-		/* Check if we have to set the PCI bit. */
-		if (!(channel->ccws[prev].flags & CCW_FLAG_SUSPEND))
-			/* Suspend bit of the previous buffer is not set. */
-			channel->ccws[index].flags |= CCW_FLAG_PCI;
-		/* Suspend bit of the next buffer is set. */
-		channel->ccws[index].flags &= ~CCW_FLAG_SUSPEND;
-	}
-}
-
-static int
-lcs_ready_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	unsigned long flags;
-	int index, rc;
-
-	LCS_DBF_TEXT(5, trace, "rdybuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
-	       buffer->state != LCS_BUF_STATE_PROCESSED);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = LCS_BUF_STATE_READY;
-	index = buffer - channel->iob;
-	/* Set length. */
-	channel->ccws[index].count = buffer->count;
-	/* Check relevant PCI/suspend bits. */
-	__lcs_ready_buffer_bits(channel, index);
-	rc = __lcs_resume_channel(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-	return rc;
-}
-
-/*
- * Mark the buffer as processed. Take care of the suspend bit
- * of the previous buffer. This function is called from
- * interrupt context, so the lock must not be taken.
- */
-static int
-__lcs_processed_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	int index, prev, next;
-
-	LCS_DBF_TEXT(5, trace, "prcsbuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_READY);
-	buffer->state = LCS_BUF_STATE_PROCESSED;
-	index = buffer - channel->iob;
-	prev = (index - 1) & (LCS_NUM_BUFFS - 1);
-	next = (index + 1) & (LCS_NUM_BUFFS - 1);
-	/* Set the suspend bit and clear the PCI bit of this buffer. */
-	channel->ccws[index].flags |= CCW_FLAG_SUSPEND;
-	channel->ccws[index].flags &= ~CCW_FLAG_PCI;
-	/* Check the suspend bit of the previous buffer. */
-	if (channel->iob[prev].state == LCS_BUF_STATE_READY) {
-		/*
-		 * Previous buffer is in state ready. It might have
-		 * happened in lcs_ready_buffer that the suspend bit
-		 * has not been cleared to avoid an endless loop.
-		 * Do it now.
-		 */
-		__lcs_ready_buffer_bits(channel, prev);
-	}
-	/* Clear PCI bit of next buffer. */
-	channel->ccws[next].flags &= ~CCW_FLAG_PCI;
-	return __lcs_resume_channel(channel);
-}
-
-/*
- * Put a processed buffer back to state empty.
- */
-static void
-lcs_release_buffer(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	unsigned long flags;
-
-	LCS_DBF_TEXT(5, trace, "relbuff");
-	BUG_ON(buffer->state != LCS_BUF_STATE_LOCKED &&
-	       buffer->state != LCS_BUF_STATE_PROCESSED);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	buffer->state = LCS_BUF_STATE_EMPTY;
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-}
-
-/*
- * Get buffer for a lan command.
- */
-static struct lcs_buffer *
-lcs_get_lancmd(struct lcs_card *card, int count)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(4, trace, "getlncmd");
-	/* Get buffer and wait if none is available. */
-	wait_event(card->write.wait_q,
-		   ((buffer = lcs_get_buffer(&card->write)) != NULL));
-	count += sizeof(struct lcs_header);
-	*(__u16 *)(buffer->data + count) = 0;
-	buffer->count = count + sizeof(__u16);
-	buffer->callback = lcs_release_buffer;
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->offset = count;
-	cmd->type = LCS_FRAME_TYPE_CONTROL;
-	cmd->slot = 0;
-	return buffer;
-}
-
-
-static void
-lcs_get_reply(struct lcs_reply *reply)
-{
-	refcount_inc(&reply->refcnt);
-}
-
-static void
-lcs_put_reply(struct lcs_reply *reply)
-{
-	if (refcount_dec_and_test(&reply->refcnt))
-		kfree(reply);
-}
-
-static struct lcs_reply *
-lcs_alloc_reply(struct lcs_cmd *cmd)
-{
-	struct lcs_reply *reply;
-
-	LCS_DBF_TEXT(4, trace, "getreply");
-
-	reply = kzalloc(sizeof(struct lcs_reply), GFP_ATOMIC);
-	if (!reply)
-		return NULL;
-	refcount_set(&reply->refcnt, 1);
-	reply->sequence_no = cmd->sequence_no;
-	reply->received = 0;
-	reply->rc = 0;
-	init_waitqueue_head(&reply->wait_q);
-
-	return reply;
-}
-
-/*
- * Notifier function for lancmd replies. Called from read irq.
- */
-static void
-lcs_notify_lancmd_waiters(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	struct list_head *l, *n;
-	struct lcs_reply *reply;
-
-	LCS_DBF_TEXT(4, trace, "notiwait");
-	spin_lock(&card->lock);
-	list_for_each_safe(l, n, &card->lancmd_waiters) {
-		reply = list_entry(l, struct lcs_reply, list);
-		if (reply->sequence_no == cmd->sequence_no) {
-			lcs_get_reply(reply);
-			list_del_init(&reply->list);
-			if (reply->callback != NULL)
-				reply->callback(card, cmd);
-			reply->received = 1;
-			reply->rc = cmd->return_code;
-			wake_up(&reply->wait_q);
-			lcs_put_reply(reply);
-			break;
-		}
-	}
-	spin_unlock(&card->lock);
-}
-
-/*
- * Emit buffer of a lan command.
- */
-static void
-lcs_lancmd_timeout(struct timer_list *t)
-{
-	struct lcs_reply *reply = from_timer(reply, t, timer);
-	struct lcs_reply *list_reply, *r;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "timeout");
-	spin_lock_irqsave(&reply->card->lock, flags);
-	list_for_each_entry_safe(list_reply, r,
-				 &reply->card->lancmd_waiters,list) {
-		if (reply == list_reply) {
-			lcs_get_reply(reply);
-			list_del_init(&reply->list);
-			spin_unlock_irqrestore(&reply->card->lock, flags);
-			reply->received = 1;
-			reply->rc = -ETIME;
-			wake_up(&reply->wait_q);
-			lcs_put_reply(reply);
-			return;
-		}
-	}
-	spin_unlock_irqrestore(&reply->card->lock, flags);
-}
-
-static int
-lcs_send_lancmd(struct lcs_card *card, struct lcs_buffer *buffer,
-		void (*reply_callback)(struct lcs_card *, struct lcs_cmd *))
-{
-	struct lcs_reply *reply;
-	struct lcs_cmd *cmd;
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4, trace, "sendcmd");
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->return_code = 0;
-	cmd->sequence_no = card->sequence_no++;
-	reply = lcs_alloc_reply(cmd);
-	if (!reply)
-		return -ENOMEM;
-	reply->callback = reply_callback;
-	reply->card = card;
-	spin_lock_irqsave(&card->lock, flags);
-	list_add_tail(&reply->list, &card->lancmd_waiters);
-	spin_unlock_irqrestore(&card->lock, flags);
-
-	buffer->callback = lcs_release_buffer;
-	rc = lcs_ready_buffer(&card->write, buffer);
-	if (rc)
-		return rc;
-	timer_setup(&reply->timer, lcs_lancmd_timeout, 0);
-	mod_timer(&reply->timer, jiffies + HZ * card->lancmd_timeout);
-	wait_event(reply->wait_q, reply->received);
-	del_timer_sync(&reply->timer);
-	LCS_DBF_TEXT_(4, trace, "rc:%d",reply->rc);
-	rc = reply->rc;
-	lcs_put_reply(reply);
-	return rc ? -EIO : 0;
-}
-
-/*
- * LCS startup command
- */
-static int
-lcs_send_startup(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "startup");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STARTUP;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_startup.buff_size = LCS_IOBUFFERSIZE;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * LCS shutdown command
- */
-static int
-lcs_send_shutdown(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "shutdown");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_SHUTDOWN;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * LCS lanstat command
- */
-static void
-__lcs_lanstat_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "statcb");
-	memcpy(card->mac, cmd->cmd.lcs_lanstat_cmd.mac_addr, LCS_MAC_LENGTH);
-}
-
-static int
-lcs_send_lanstat(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2,trace, "cmdstat");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	/* Setup lanstat command. */
-	cmd->cmd_code = LCS_CMD_LANSTAT;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, __lcs_lanstat_cb);
-}
-
-/*
- * send stoplan command
- */
-static int
-lcs_send_stoplan(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdstpln");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STOPLAN;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * send startlan command
- */
-static void
-__lcs_send_startlan_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "srtlancb");
-	card->lan_type = cmd->cmd.lcs_std_cmd.lan_type;
-	card->portno = cmd->cmd.lcs_std_cmd.portno;
-}
-
-static int
-lcs_send_startlan(struct lcs_card *card, __u8 initiator)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdstaln");
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_STARTLAN;
-	cmd->initiator = initiator;
-	cmd->cmd.lcs_std_cmd.lan_type = card->lan_type;
-	cmd->cmd.lcs_std_cmd.portno = card->portno;
-	return lcs_send_lancmd(card, buffer, __lcs_send_startlan_cb);
-}
-
-#ifdef CONFIG_IP_MULTICAST
-/*
- * send setipm command (Multicast)
- */
-static int
-lcs_send_setipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmdsetim");
-	buffer = lcs_get_lancmd(card, LCS_MULTICAST_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_SETIPM;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	memcpy(cmd->cmd.lcs_qipassist.lcs_ipass_ctlmsg.ip_mac_pair,
-	       &ipm_list->ipm, sizeof (struct lcs_ip_mac_pair));
-	LCS_DBF_TEXT_(2, trace, "%x",ipm_list->ipm.ip_addr);
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * send delipm command (Multicast)
- */
-static int
-lcs_send_delipm(struct lcs_card *card,struct lcs_ipm_list *ipm_list)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-
-	LCS_DBF_TEXT(2, trace, "cmddelim");
-	buffer = lcs_get_lancmd(card, LCS_MULTICAST_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_DELIPM;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	memcpy(cmd->cmd.lcs_qipassist.lcs_ipass_ctlmsg.ip_mac_pair,
-	       &ipm_list->ipm, sizeof (struct lcs_ip_mac_pair));
-	LCS_DBF_TEXT_(2, trace, "%x",ipm_list->ipm.ip_addr);
-	return lcs_send_lancmd(card, buffer, NULL);
-}
-
-/*
- * check if multicast is supported by LCS
- */
-static void
-__lcs_check_multicast_cb(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(2, trace, "chkmccb");
-	card->ip_assists_supported =
-		cmd->cmd.lcs_qipassist.ip_assists_supported;
-	card->ip_assists_enabled =
-		cmd->cmd.lcs_qipassist.ip_assists_enabled;
-}
-
-static int
-lcs_check_multicast_support(struct lcs_card *card)
-{
-	struct lcs_buffer *buffer;
-	struct lcs_cmd *cmd;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "cmdqipa");
-	/* Send query ipassist. */
-	buffer = lcs_get_lancmd(card, LCS_STD_CMD_SIZE);
-	cmd = (struct lcs_cmd *) buffer->data;
-	cmd->cmd_code = LCS_CMD_QIPASSIST;
-	cmd->initiator = LCS_INITIATOR_TCPIP;
-	cmd->cmd.lcs_qipassist.lan_type = card->lan_type;
-	cmd->cmd.lcs_qipassist.portno = card->portno;
-	cmd->cmd.lcs_qipassist.version = 4;
-	cmd->cmd.lcs_qipassist.num_ip_pairs = 1;
-	rc = lcs_send_lancmd(card, buffer, __lcs_check_multicast_cb);
-	if (rc != 0) {
-		pr_err("Query IPAssist failed. Assuming unsupported!\n");
-		return -EOPNOTSUPP;
-	}
-	if (card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT)
-		return 0;
-	return -EOPNOTSUPP;
-}
-
-/*
- * set or del multicast address on LCS card
- */
-static void
-lcs_fix_multicast_list(struct lcs_card *card)
-{
-	struct list_head failed_list;
-	struct lcs_ipm_list *ipm, *tmp;
-	unsigned long flags;
-	int rc;
-
-	LCS_DBF_TEXT(4,trace, "fixipm");
-	INIT_LIST_HEAD(&failed_list);
-	spin_lock_irqsave(&card->ipm_lock, flags);
-list_modified:
-	list_for_each_entry_safe(ipm, tmp, &card->ipm_list, list){
-		switch (ipm->ipm_state) {
-		case LCS_IPM_STATE_SET_REQUIRED:
-			/* del from ipm_list so no one else can tamper with
-			 * this entry */
-			list_del_init(&ipm->list);
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			rc = lcs_send_setipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-			if (rc) {
-				pr_info("Adding multicast address failed."
-					" Table possibly full!\n");
-				/* store ipm in failed list -> will be added
-				 * to ipm_list again, so a retry will be done
-				 * during the next call of this function */
-				list_add_tail(&ipm->list, &failed_list);
-			} else {
-				ipm->ipm_state = LCS_IPM_STATE_ON_CARD;
-				/* re-insert into ipm_list */
-				list_add_tail(&ipm->list, &card->ipm_list);
-			}
-			goto list_modified;
-		case LCS_IPM_STATE_DEL_REQUIRED:
-			list_del(&ipm->list);
-			spin_unlock_irqrestore(&card->ipm_lock, flags);
-			lcs_send_delipm(card, ipm);
-			spin_lock_irqsave(&card->ipm_lock, flags);
-			kfree(ipm);
-			goto list_modified;
-		case LCS_IPM_STATE_ON_CARD:
-			break;
-		}
-	}
-	/* re-insert all entries from the failed_list into ipm_list */
-	list_for_each_entry_safe(ipm, tmp, &failed_list, list)
-		list_move_tail(&ipm->list, &card->ipm_list);
-
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-}
-
-/*
- * get mac address for the relevant Multicast address
- */
-static void
-lcs_get_mac_for_ipm(__be32 ipm, char *mac, struct net_device *dev)
-{
-	LCS_DBF_TEXT(4,trace, "getmac");
-	ip_eth_mc_map(ipm, mac);
-}
-
-/*
- * function called by net device to handle multicast address relevant things
- */
-static void lcs_remove_mc_addresses(struct lcs_card *card,
-				    struct in_device *in4_dev)
-{
-	struct ip_mc_list *im4;
-	struct list_head *l;
-	struct lcs_ipm_list *ipm;
-	unsigned long flags;
-	char buf[MAX_ADDR_LEN];
-
-	LCS_DBF_TEXT(4, trace, "remmclst");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	list_for_each(l, &card->ipm_list) {
-		ipm = list_entry(l, struct lcs_ipm_list, list);
-		for (im4 = rcu_dereference(in4_dev->mc_list);
-		     im4 != NULL; im4 = rcu_dereference(im4->next_rcu)) {
-			lcs_get_mac_for_ipm(im4->multiaddr, buf, card->dev);
-			if ( (ipm->ipm.ip_addr == im4->multiaddr) &&
-			     (memcmp(buf, &ipm->ipm.mac_addr,
-				     LCS_MAC_LENGTH) == 0) )
-				break;
-		}
-		if (im4 == NULL)
-			ipm->ipm_state = LCS_IPM_STATE_DEL_REQUIRED;
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-}
-
-static struct lcs_ipm_list *lcs_check_addr_entry(struct lcs_card *card,
-						 struct ip_mc_list *im4,
-						 char *buf)
-{
-	struct lcs_ipm_list *tmp, *ipm = NULL;
-	struct list_head *l;
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "chkmcent");
-	spin_lock_irqsave(&card->ipm_lock, flags);
-	list_for_each(l, &card->ipm_list) {
-		tmp = list_entry(l, struct lcs_ipm_list, list);
-		if ( (tmp->ipm.ip_addr == im4->multiaddr) &&
-		     (memcmp(buf, &tmp->ipm.mac_addr,
-			     LCS_MAC_LENGTH) == 0) ) {
-			ipm = tmp;
-			break;
-		}
-	}
-	spin_unlock_irqrestore(&card->ipm_lock, flags);
-	return ipm;
-}
-
-static void lcs_set_mc_addresses(struct lcs_card *card,
-				 struct in_device *in4_dev)
-{
-
-	struct ip_mc_list *im4;
-	struct lcs_ipm_list *ipm;
-	char buf[MAX_ADDR_LEN];
-	unsigned long flags;
-
-	LCS_DBF_TEXT(4, trace, "setmclst");
-	for (im4 = rcu_dereference(in4_dev->mc_list); im4 != NULL;
-	     im4 = rcu_dereference(im4->next_rcu)) {
-		lcs_get_mac_for_ipm(im4->multiaddr, buf, card->dev);
-		ipm = lcs_check_addr_entry(card, im4, buf);
-		if (ipm != NULL)
-			continue;	/* Address already in list. */
-		ipm = kzalloc(sizeof(struct lcs_ipm_list), GFP_ATOMIC);
-		if (ipm == NULL) {
-			pr_info("Not enough memory to add"
-				" new multicast entry!\n");
-			break;
-		}
-		memcpy(&ipm->ipm.mac_addr, buf, LCS_MAC_LENGTH);
-		ipm->ipm.ip_addr = im4->multiaddr;
-		ipm->ipm_state = LCS_IPM_STATE_SET_REQUIRED;
-		spin_lock_irqsave(&card->ipm_lock, flags);
-		LCS_DBF_HEX(2,trace,&ipm->ipm.ip_addr,4);
-		list_add(&ipm->list, &card->ipm_list);
-		spin_unlock_irqrestore(&card->ipm_lock, flags);
-	}
-}
-
-static int
-lcs_register_mc_addresses(void *data)
-{
-	struct lcs_card *card;
-	struct in_device *in4_dev;
-
-	card = (struct lcs_card *) data;
-
-	if (!lcs_do_run_thread(card, LCS_SET_MC_THREAD))
-		return 0;
-	LCS_DBF_TEXT(4, trace, "regmulti");
-
-	in4_dev = in_dev_get(card->dev);
-	if (in4_dev == NULL)
-		goto out;
-	rcu_read_lock();
-	lcs_remove_mc_addresses(card,in4_dev);
-	lcs_set_mc_addresses(card, in4_dev);
-	rcu_read_unlock();
-	in_dev_put(in4_dev);
-
-	netif_carrier_off(card->dev);
-	netif_tx_disable(card->dev);
-	wait_event(card->write.wait_q,
-			(card->write.state != LCS_CH_STATE_RUNNING));
-	lcs_fix_multicast_list(card);
-	if (card->state == DEV_STATE_UP) {
-		netif_carrier_on(card->dev);
-		netif_wake_queue(card->dev);
-	}
-out:
-	lcs_clear_thread_running_bit(card, LCS_SET_MC_THREAD);
-	return 0;
-}
-#endif /* CONFIG_IP_MULTICAST */
-
-/*
- * function called by net device to
- * handle multicast address relevant things
- */
-static void
-lcs_set_multicast_list(struct net_device *dev)
-{
-#ifdef CONFIG_IP_MULTICAST
-        struct lcs_card *card;
-
-        LCS_DBF_TEXT(4, trace, "setmulti");
-        card = (struct lcs_card *) dev->ml_priv;
-
-        if (!lcs_set_thread_start_bit(card, LCS_SET_MC_THREAD))
-		schedule_work(&card->kernel_thread_starter);
-#endif /* CONFIG_IP_MULTICAST */
-}
-
-static long
-lcs_check_irb_error(struct ccw_device *cdev, struct irb *irb)
-{
-	if (!IS_ERR(irb))
-		return 0;
-
-	switch (PTR_ERR(irb)) {
-	case -EIO:
-		dev_warn(&cdev->dev,
-			"An I/O-error occurred on the LCS device\n");
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT_(2, trace, "  rc%d", -EIO);
-		break;
-	case -ETIMEDOUT:
-		dev_warn(&cdev->dev,
-			"A command timed out on the LCS device\n");
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT_(2, trace, "  rc%d", -ETIMEDOUT);
-		break;
-	default:
-		dev_warn(&cdev->dev,
-			"An error occurred on the LCS device, rc=%ld\n",
-			PTR_ERR(irb));
-		LCS_DBF_TEXT(2, trace, "ckirberr");
-		LCS_DBF_TEXT(2, trace, "  rc???");
-	}
-	return PTR_ERR(irb);
-}
-
-static int
-lcs_get_problem(struct ccw_device *cdev, struct irb *irb)
-{
-	int dstat, cstat;
-	char *sense;
-
-	sense = (char *) irb->ecw;
-	cstat = irb->scsw.cmd.cstat;
-	dstat = irb->scsw.cmd.dstat;
-
-	if (cstat & (SCHN_STAT_CHN_CTRL_CHK | SCHN_STAT_INTF_CTRL_CHK |
-		     SCHN_STAT_CHN_DATA_CHK | SCHN_STAT_CHAIN_CHECK |
-		     SCHN_STAT_PROT_CHECK   | SCHN_STAT_PROG_CHECK)) {
-		LCS_DBF_TEXT(2, trace, "CGENCHK");
-		return 1;
-	}
-	if (dstat & DEV_STAT_UNIT_CHECK) {
-		if (sense[LCS_SENSE_BYTE_1] &
-		    LCS_SENSE_RESETTING_EVENT) {
-			LCS_DBF_TEXT(2, trace, "REVIND");
-			return 1;
-		}
-		if (sense[LCS_SENSE_BYTE_0] &
-		    LCS_SENSE_CMD_REJECT) {
-			LCS_DBF_TEXT(2, trace, "CMDREJ");
-			return 0;
-		}
-		if ((!sense[LCS_SENSE_BYTE_0]) &&
-		    (!sense[LCS_SENSE_BYTE_1]) &&
-		    (!sense[LCS_SENSE_BYTE_2]) &&
-		    (!sense[LCS_SENSE_BYTE_3])) {
-			LCS_DBF_TEXT(2, trace, "ZEROSEN");
-			return 0;
-		}
-		LCS_DBF_TEXT(2, trace, "DGENCHK");
-		return 1;
-	}
-	return 0;
-}
-
-static void
-lcs_schedule_recovery(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(2, trace, "startrec");
-	if (!lcs_set_thread_start_bit(card, LCS_RECOVERY_THREAD))
-		schedule_work(&card->kernel_thread_starter);
-}
-
-/*
- * IRQ Handler for LCS channels
- */
-static void
-lcs_irq(struct ccw_device *cdev, unsigned long intparm, struct irb *irb)
-{
-	struct lcs_card *card;
-	struct lcs_channel *channel;
-	int rc, index;
-	int cstat, dstat;
-
-	if (lcs_check_irb_error(cdev, irb))
-		return;
-
-	card = CARD_FROM_DEV(cdev);
-	if (card->read.ccwdev == cdev)
-		channel = &card->read;
-	else
-		channel = &card->write;
-
-	cstat = irb->scsw.cmd.cstat;
-	dstat = irb->scsw.cmd.dstat;
-	LCS_DBF_TEXT_(5, trace, "Rint%s", dev_name(&cdev->dev));
-	LCS_DBF_TEXT_(5, trace, "%4x%4x", irb->scsw.cmd.cstat,
-		      irb->scsw.cmd.dstat);
-	LCS_DBF_TEXT_(5, trace, "%4x%4x", irb->scsw.cmd.fctl,
-		      irb->scsw.cmd.actl);
-
-	/* Check for channel and device errors presented */
-	rc = lcs_get_problem(cdev, irb);
-	if (rc || (dstat & DEV_STAT_UNIT_EXCEP)) {
-		dev_warn(&cdev->dev,
-			"The LCS device stopped because of an error,"
-			" dstat=0x%X, cstat=0x%X \n",
-			    dstat, cstat);
-		if (rc) {
-			channel->state = LCS_CH_STATE_ERROR;
-		}
-	}
-	if (channel->state == LCS_CH_STATE_ERROR) {
-		lcs_schedule_recovery(card);
-		wake_up(&card->wait_q);
-		return;
-	}
-	/* How far in the ccw chain have we processed? */
-	if ((channel->state != LCS_CH_STATE_INIT) &&
-	    (irb->scsw.cmd.fctl & SCSW_FCTL_START_FUNC) &&
-	    (irb->scsw.cmd.cpa != 0)) {
-		index = (struct ccw1 *)dma32_to_virt(irb->scsw.cmd.cpa)
-			- channel->ccws;
-		if ((irb->scsw.cmd.actl & SCSW_ACTL_SUSPENDED) ||
-		    (irb->scsw.cmd.cstat & SCHN_STAT_PCI))
-			/* Bloody io subsystem tells us lies about cpa... */
-			index = (index - 1) & (LCS_NUM_BUFFS - 1);
-		while (channel->io_idx != index) {
-			__lcs_processed_buffer(channel,
-					       channel->iob + channel->io_idx);
-			channel->io_idx =
-				(channel->io_idx + 1) & (LCS_NUM_BUFFS - 1);
-		}
-	}
-
-	if ((irb->scsw.cmd.dstat & DEV_STAT_DEV_END) ||
-	    (irb->scsw.cmd.dstat & DEV_STAT_CHN_END) ||
-	    (irb->scsw.cmd.dstat & DEV_STAT_UNIT_CHECK))
-		/* Mark channel as stopped. */
-		channel->state = LCS_CH_STATE_STOPPED;
-	else if (irb->scsw.cmd.actl & SCSW_ACTL_SUSPENDED)
-		/* CCW execution stopped on a suspend bit. */
-		channel->state = LCS_CH_STATE_SUSPENDED;
-	if (irb->scsw.cmd.fctl & SCSW_FCTL_HALT_FUNC) {
-		if (irb->scsw.cmd.cc != 0) {
-			ccw_device_halt(channel->ccwdev, 0);
-			return;
-		}
-		/* The channel has been stopped by halt_IO. */
-		channel->state = LCS_CH_STATE_HALTED;
-	}
-	if (irb->scsw.cmd.fctl & SCSW_FCTL_CLEAR_FUNC)
-		channel->state = LCS_CH_STATE_CLEARED;
-	/* Do the rest in the tasklet. */
-	tasklet_schedule(&channel->irq_tasklet);
-}
-
-/*
- * Tasklet for IRQ handler
- */
-static void
-lcs_tasklet(unsigned long data)
-{
-	unsigned long flags;
-	struct lcs_channel *channel;
-	struct lcs_buffer *iob;
-	int buf_idx;
-
-	channel = (struct lcs_channel *) data;
-	LCS_DBF_TEXT_(5, trace, "tlet%s", dev_name(&channel->ccwdev->dev));
-
-	/* Check for processed buffers. */
-	iob = channel->iob;
-	buf_idx = channel->buf_idx;
-	while (iob[buf_idx].state == LCS_BUF_STATE_PROCESSED) {
-		/* Do the callback thing. */
-		if (iob[buf_idx].callback != NULL)
-			iob[buf_idx].callback(channel, iob + buf_idx);
-		buf_idx = (buf_idx + 1) & (LCS_NUM_BUFFS - 1);
-	}
-	channel->buf_idx = buf_idx;
-
-	if (channel->state == LCS_CH_STATE_STOPPED)
-		lcs_start_channel(channel);
-	spin_lock_irqsave(get_ccwdev_lock(channel->ccwdev), flags);
-	if (channel->state == LCS_CH_STATE_SUSPENDED &&
-	    channel->iob[channel->io_idx].state == LCS_BUF_STATE_READY)
-		__lcs_resume_channel(channel);
-	spin_unlock_irqrestore(get_ccwdev_lock(channel->ccwdev), flags);
-
-	/* Something happened on the channel. Wake up waiters. */
-	wake_up(&channel->wait_q);
-}
-
-/*
- * Finish current tx buffer and make it ready for transmit.
- */
-static void
-__lcs_emit_txbuffer(struct lcs_card *card)
-{
-	LCS_DBF_TEXT(5, trace, "emittx");
-	*(__u16 *)(card->tx_buffer->data + card->tx_buffer->count) = 0;
-	card->tx_buffer->count += 2;
-	lcs_ready_buffer(&card->write, card->tx_buffer);
-	card->tx_buffer = NULL;
-	card->tx_emitted++;
-}
-
-/*
- * Callback for finished tx buffers.
- */
-static void
-lcs_txbuffer_cb(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(5, trace, "txbuffcb");
-	/* Put buffer back to pool. */
-	lcs_release_buffer(channel, buffer);
-	card = container_of(channel, struct lcs_card, write);
-	if (netif_queue_stopped(card->dev) && netif_carrier_ok(card->dev))
-		netif_wake_queue(card->dev);
-	spin_lock(&card->lock);
-	card->tx_emitted--;
-	if (card->tx_emitted <= 0 && card->tx_buffer != NULL)
-		/*
-		 * Last running tx buffer has finished. Submit partially
-		 * filled current buffer.
-		 */
-		__lcs_emit_txbuffer(card);
-	spin_unlock(&card->lock);
-}
-
-/*
- * Packet transmit function called by network stack
- */
-static netdev_tx_t __lcs_start_xmit(struct lcs_card *card, struct sk_buff *skb,
-				    struct net_device *dev)
-{
-	struct lcs_header *header;
-	int rc = NETDEV_TX_OK;
-
-	LCS_DBF_TEXT(5, trace, "hardxmit");
-	if (skb == NULL) {
-		card->stats.tx_dropped++;
-		card->stats.tx_errors++;
-		return NETDEV_TX_OK;
-	}
-	if (card->state != DEV_STATE_UP) {
-		dev_kfree_skb(skb);
-		card->stats.tx_dropped++;
-		card->stats.tx_errors++;
-		card->stats.tx_carrier_errors++;
-		return NETDEV_TX_OK;
-	}
-	if (skb->protocol == htons(ETH_P_IPV6)) {
-		dev_kfree_skb(skb);
-		return NETDEV_TX_OK;
-	}
-	netif_stop_queue(card->dev);
-	spin_lock(&card->lock);
-	if (card->tx_buffer != NULL &&
-	    card->tx_buffer->count + sizeof(struct lcs_header) +
-	    skb->len + sizeof(u16) > LCS_IOBUFFERSIZE)
-		/* skb too big for current tx buffer. */
-		__lcs_emit_txbuffer(card);
-	if (card->tx_buffer == NULL) {
-		/* Get new tx buffer */
-		card->tx_buffer = lcs_get_buffer(&card->write);
-		if (card->tx_buffer == NULL) {
-			card->stats.tx_dropped++;
-			rc = NETDEV_TX_BUSY;
-			goto out;
-		}
-		card->tx_buffer->callback = lcs_txbuffer_cb;
-		card->tx_buffer->count = 0;
-	}
-	header = (struct lcs_header *)
-		(card->tx_buffer->data + card->tx_buffer->count);
-	card->tx_buffer->count += skb->len + sizeof(struct lcs_header);
-	header->offset = card->tx_buffer->count;
-	header->type = card->lan_type;
-	header->slot = card->portno;
-	skb_copy_from_linear_data(skb, header + 1, skb->len);
-	spin_unlock(&card->lock);
-	card->stats.tx_bytes += skb->len;
-	card->stats.tx_packets++;
-	dev_kfree_skb(skb);
-	netif_wake_queue(card->dev);
-	spin_lock(&card->lock);
-	if (card->tx_emitted <= 0 && card->tx_buffer != NULL)
-		/* If this is the first tx buffer emit it immediately. */
-		__lcs_emit_txbuffer(card);
-out:
-	spin_unlock(&card->lock);
-	return rc;
-}
-
-static netdev_tx_t lcs_start_xmit(struct sk_buff *skb, struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(5, trace, "pktxmit");
-	card = (struct lcs_card *) dev->ml_priv;
-	rc = __lcs_start_xmit(card, skb, dev);
-	return rc;
-}
-
-/*
- * send startlan and lanstat command to make LCS device ready
- */
-static int
-lcs_startlan_auto(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "strtauto");
-	card->lan_type = LCS_FRAME_TYPE_ENET;
-	rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
-	if (rc == 0)
-		return 0;
-
-	return -EIO;
-}
-
-static int
-lcs_startlan(struct lcs_card *card)
-{
-	int rc, i;
-
-	LCS_DBF_TEXT(2, trace, "startlan");
-	rc = 0;
-	if (card->portno != LCS_INVALID_PORT_NO) {
-		if (card->lan_type == LCS_FRAME_TYPE_AUTO)
-			rc = lcs_startlan_auto(card);
-		else
-			rc = lcs_send_startlan(card, LCS_INITIATOR_TCPIP);
-	} else {
-                for (i = 0; i <= 16; i++) {
-                        card->portno = i;
-                        if (card->lan_type != LCS_FRAME_TYPE_AUTO)
-                                rc = lcs_send_startlan(card,
-                                                       LCS_INITIATOR_TCPIP);
-                        else
-                                /* autodetecting lan type */
-                                rc = lcs_startlan_auto(card);
-                        if (rc == 0)
-                                break;
-                }
-        }
-	if (rc == 0)
-		return lcs_send_lanstat(card);
-	return rc;
-}
-
-/*
- * LCS detect function
- * setup channels and make them I/O ready
- */
-static int
-lcs_detect(struct lcs_card *card)
-{
-	int rc = 0;
-
-	LCS_DBF_TEXT(2, setup, "lcsdetct");
-	/* start/reset card */
-	if (card->dev)
-		netif_stop_queue(card->dev);
-	rc = lcs_stop_channels(card);
-	if (rc == 0) {
-		rc = lcs_start_channels(card);
-		if (rc == 0) {
-			rc = lcs_send_startup(card, LCS_INITIATOR_TCPIP);
-			if (rc == 0)
-				rc = lcs_startlan(card);
-		}
-	}
-	if (rc == 0) {
-		card->state = DEV_STATE_UP;
-	} else {
-		card->state = DEV_STATE_DOWN;
-		card->write.state = LCS_CH_STATE_INIT;
-		card->read.state =  LCS_CH_STATE_INIT;
-	}
-	return rc;
-}
-
-/*
- * LCS Stop card
- */
-static int
-lcs_stopcard(struct lcs_card *card)
-{
-	int rc;
-
-	LCS_DBF_TEXT(3, setup, "stopcard");
-
-	if (card->read.state != LCS_CH_STATE_STOPPED &&
-	    card->write.state != LCS_CH_STATE_STOPPED &&
-	    card->read.state != LCS_CH_STATE_ERROR &&
-	    card->write.state != LCS_CH_STATE_ERROR &&
-	    card->state == DEV_STATE_UP) {
-		lcs_clear_multicast_list(card);
-		rc = lcs_send_stoplan(card,LCS_INITIATOR_TCPIP);
-		rc = lcs_send_shutdown(card);
-	}
-	rc = lcs_stop_channels(card);
-	card->state = DEV_STATE_DOWN;
-
-	return rc;
-}
-
-/*
- * Kernel Thread helper functions for LGW initiated commands
- */
-static void
-lcs_start_kernel_thread(struct work_struct *work)
-{
-	struct lcs_card *card = container_of(work, struct lcs_card, kernel_thread_starter);
-	LCS_DBF_TEXT(5, trace, "krnthrd");
-	if (lcs_do_start_thread(card, LCS_RECOVERY_THREAD))
-		kthread_run(lcs_recovery, card, "lcs_recover");
-#ifdef CONFIG_IP_MULTICAST
-	if (lcs_do_start_thread(card, LCS_SET_MC_THREAD))
-		kthread_run(lcs_register_mc_addresses, card, "regipm");
-#endif
-}
-
-/*
- * Process control frames.
- */
-static void
-lcs_get_control(struct lcs_card *card, struct lcs_cmd *cmd)
-{
-	LCS_DBF_TEXT(5, trace, "getctrl");
-	if (cmd->initiator == LCS_INITIATOR_LGW) {
-		switch(cmd->cmd_code) {
-		case LCS_CMD_STARTUP:
-		case LCS_CMD_STARTLAN:
-			lcs_schedule_recovery(card);
-			break;
-		case LCS_CMD_STOPLAN:
-			if (card->dev) {
-				pr_warn("Stoplan for %s initiated by LGW\n",
-					card->dev->name);
-				netif_carrier_off(card->dev);
-			}
-			break;
-		default:
-			LCS_DBF_TEXT(5, trace, "noLGWcmd");
-			break;
-		}
-	} else
-		lcs_notify_lancmd_waiters(card, cmd);
-}
-
-/*
- * Unpack network packet.
- */
-static void
-lcs_get_skb(struct lcs_card *card, char *skb_data, unsigned int skb_len)
-{
-	struct sk_buff *skb;
-
-	LCS_DBF_TEXT(5, trace, "getskb");
-	if (card->dev == NULL ||
-	    card->state != DEV_STATE_UP)
-		/* The card isn't up. Ignore the packet. */
-		return;
-
-	skb = dev_alloc_skb(skb_len);
-	if (skb == NULL) {
-		dev_err(&card->dev->dev,
-			" Allocating a socket buffer to interface %s failed\n",
-			  card->dev->name);
-		card->stats.rx_dropped++;
-		return;
-	}
-	skb_put_data(skb, skb_data, skb_len);
-	skb->protocol =	card->lan_type_trans(skb, card->dev);
-	card->stats.rx_bytes += skb_len;
-	card->stats.rx_packets++;
-	if (skb->protocol == htons(ETH_P_802_2))
-		*((__u32 *)skb->cb) = ++card->pkt_seq;
-	netif_rx(skb);
-}
-
-/*
- * LCS main routine to get packets and lancmd replies from the buffers
- */
-static void
-lcs_get_frames_cb(struct lcs_channel *channel, struct lcs_buffer *buffer)
-{
-	struct lcs_card *card;
-	struct lcs_header *lcs_hdr;
-	__u16 offset;
-
-	LCS_DBF_TEXT(5, trace, "lcsgtpkt");
-	lcs_hdr = (struct lcs_header *) buffer->data;
-	if (lcs_hdr->offset == LCS_ILLEGAL_OFFSET) {
-		LCS_DBF_TEXT(4, trace, "-eiogpkt");
-		return;
-	}
-	card = container_of(channel, struct lcs_card, read);
-	offset = 0;
-	while (lcs_hdr->offset != 0) {
-		if (lcs_hdr->offset <= 0 ||
-		    lcs_hdr->offset > LCS_IOBUFFERSIZE ||
-		    lcs_hdr->offset < offset) {
-			/* Offset invalid. */
-			card->stats.rx_length_errors++;
-			card->stats.rx_errors++;
-			return;
-		}
-		if (lcs_hdr->type == LCS_FRAME_TYPE_CONTROL)
-			lcs_get_control(card, (struct lcs_cmd *) lcs_hdr);
-		else if (lcs_hdr->type == LCS_FRAME_TYPE_ENET)
-			lcs_get_skb(card, (char *)(lcs_hdr + 1),
-				    lcs_hdr->offset - offset -
-				    sizeof(struct lcs_header));
-		else
-			dev_info_once(&card->dev->dev,
-				      "Unknown frame type %d\n",
-				      lcs_hdr->type);
-		offset = lcs_hdr->offset;
-		lcs_hdr->offset = LCS_ILLEGAL_OFFSET;
-		lcs_hdr = (struct lcs_header *) (buffer->data + offset);
-	}
-	/* The buffer is now empty. Make it ready again. */
-	lcs_ready_buffer(&card->read, buffer);
-}
-
-/*
- * get network statistics for ifconfig and other user programs
- */
-static struct net_device_stats *
-lcs_getstats(struct net_device *dev)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(4, trace, "netstats");
-	card = (struct lcs_card *) dev->ml_priv;
-	return &card->stats;
-}
-
-/*
- * stop lcs device
- * This function will be called by user doing ifconfig xxx down
- */
-static int
-lcs_stop_device(struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "stopdev");
-	card   = (struct lcs_card *) dev->ml_priv;
-	netif_carrier_off(dev);
-	netif_tx_disable(dev);
-	dev->flags &= ~IFF_UP;
-	wait_event(card->write.wait_q,
-		(card->write.state != LCS_CH_STATE_RUNNING));
-	rc = lcs_stopcard(card);
-	if (rc)
-		dev_err(&card->dev->dev,
-			" Shutting down the LCS device failed\n");
-	return rc;
-}
-
-/*
- * start lcs device and make it runnable
- * This function will be called by user doing ifconfig xxx up
- */
-static int
-lcs_open_device(struct net_device *dev)
-{
-	struct lcs_card *card;
-	int rc;
-
-	LCS_DBF_TEXT(2, trace, "opendev");
-	card = (struct lcs_card *) dev->ml_priv;
-	/* initialize statistics */
-	rc = lcs_detect(card);
-	if (rc) {
-		pr_err("Error in opening device!\n");
-
-	} else {
-		dev->flags |= IFF_UP;
-		netif_carrier_on(dev);
-		netif_wake_queue(dev);
-		card->state = DEV_STATE_UP;
-	}
-	return rc;
-}
-
-/*
- * show function for portno called by cat or similar things
- */
-static ssize_t
-lcs_portno_show (struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(dev);
-
-	if (!card)
-		return 0;
-
-	return sysfs_emit(buf, "%d\n", card->portno);
-}
-
-/*
- * store the value which is piped to file portno
- */
-static ssize_t
-lcs_portno_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
-{
-        struct lcs_card *card;
-	int rc;
-	s16 value;
-
-	card = dev_get_drvdata(dev);
-
-        if (!card)
-                return 0;
-
-	rc = kstrtos16(buf, 0, &value);
-	if (rc)
-		return -EINVAL;
-        /* TODO: sanity checks */
-        card->portno = value;
-	if (card->dev)
-		card->dev->dev_port = card->portno;
-
-        return count;
-
-}
-
-static DEVICE_ATTR(portno, 0644, lcs_portno_show, lcs_portno_store);
-
-static const char *lcs_type[] = {
-	"not a channel",
-	"2216 parallel",
-	"2216 channel",
-	"OSA LCS card",
-	"unknown channel type",
-	"unsupported channel type",
-};
-
-static ssize_t
-lcs_type_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct ccwgroup_device *cgdev;
-
-	cgdev = to_ccwgroupdev(dev);
-	if (!cgdev)
-		return -ENODEV;
-
-	return sysfs_emit(buf, "%s\n",
-			  lcs_type[cgdev->cdev[0]->id.driver_info]);
-}
-
-static DEVICE_ATTR(type, 0444, lcs_type_show, NULL);
-
-static ssize_t
-lcs_timeout_show(struct device *dev, struct device_attribute *attr, char *buf)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(dev);
-
-	return card ? sysfs_emit(buf, "%u\n", card->lancmd_timeout) : 0;
-}
-
-static ssize_t
-lcs_timeout_store (struct device *dev, struct device_attribute *attr, const char *buf, size_t count)
-{
-        struct lcs_card *card;
-	unsigned int value;
-	int rc;
-
-	card = dev_get_drvdata(dev);
-
-        if (!card)
-                return 0;
-
-	rc = kstrtouint(buf, 0, &value);
-	if (rc)
-		return -EINVAL;
-        /* TODO: sanity checks */
-        card->lancmd_timeout = value;
-
-        return count;
-
-}
-
-static DEVICE_ATTR(lancmd_timeout, 0644, lcs_timeout_show, lcs_timeout_store);
-
-static ssize_t
-lcs_dev_recover_store(struct device *dev, struct device_attribute *attr,
-		      const char *buf, size_t count)
-{
-	struct lcs_card *card = dev_get_drvdata(dev);
-	char *tmp;
-	int i;
-
-	if (!card)
-		return -EINVAL;
-	if (card->state != DEV_STATE_UP)
-		return -EPERM;
-	i = simple_strtoul(buf, &tmp, 16);
-	if (i == 1)
-		lcs_schedule_recovery(card);
-	return count;
-}
-
-static DEVICE_ATTR(recover, 0200, NULL, lcs_dev_recover_store);
-
-static struct attribute * lcs_attrs[] = {
-	&dev_attr_portno.attr,
-	&dev_attr_type.attr,
-	&dev_attr_lancmd_timeout.attr,
-	&dev_attr_recover.attr,
-	NULL,
-};
-static struct attribute_group lcs_attr_group = {
-	.attrs = lcs_attrs,
-};
-static const struct attribute_group *lcs_attr_groups[] = {
-	&lcs_attr_group,
-	NULL,
-};
-static const struct device_type lcs_devtype = {
-	.name = "lcs",
-	.groups = lcs_attr_groups,
-};
-
-/*
- * lcs_probe_device is called on establishing a new ccwgroup_device.
- */
-static int
-lcs_probe_device(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	if (!get_device(&ccwgdev->dev))
-		return -ENODEV;
-
-	LCS_DBF_TEXT(2, setup, "add_dev");
-        card = lcs_alloc_card();
-        if (!card) {
-		LCS_DBF_TEXT_(2, setup, "  rc%d", -ENOMEM);
-		put_device(&ccwgdev->dev);
-                return -ENOMEM;
-        }
-	dev_set_drvdata(&ccwgdev->dev, card);
-	ccwgdev->cdev[0]->handler = lcs_irq;
-	ccwgdev->cdev[1]->handler = lcs_irq;
-	card->gdev = ccwgdev;
-	INIT_WORK(&card->kernel_thread_starter, lcs_start_kernel_thread);
-	card->thread_start_mask = 0;
-	card->thread_allowed_mask = 0;
-	card->thread_running_mask = 0;
-	ccwgdev->dev.type = &lcs_devtype;
-
-	return 0;
-}
-
-static int
-lcs_register_netdev(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	LCS_DBF_TEXT(2, setup, "regnetdv");
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (card->dev->reg_state != NETREG_UNINITIALIZED)
-		return 0;
-	SET_NETDEV_DEV(card->dev, &ccwgdev->dev);
-	return register_netdev(card->dev);
-}
-
-/*
- * lcs_new_device will be called by setting the group device online.
- */
-static const struct net_device_ops lcs_netdev_ops = {
-	.ndo_open		= lcs_open_device,
-	.ndo_stop		= lcs_stop_device,
-	.ndo_get_stats		= lcs_getstats,
-	.ndo_start_xmit		= lcs_start_xmit,
-};
-
-static const struct net_device_ops lcs_mc_netdev_ops = {
-	.ndo_open		= lcs_open_device,
-	.ndo_stop		= lcs_stop_device,
-	.ndo_get_stats		= lcs_getstats,
-	.ndo_start_xmit		= lcs_start_xmit,
-	.ndo_set_rx_mode	= lcs_set_multicast_list,
-};
-
-static int
-lcs_new_device(struct ccwgroup_device *ccwgdev)
-{
-	struct  lcs_card *card;
-	struct net_device *dev=NULL;
-	enum lcs_dev_states recover_state;
-	int rc;
-
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return -ENODEV;
-
-	LCS_DBF_TEXT(2, setup, "newdev");
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	card->read.ccwdev  = ccwgdev->cdev[0];
-	card->write.ccwdev = ccwgdev->cdev[1];
-
-	recover_state = card->state;
-	rc = ccw_device_set_online(card->read.ccwdev);
-	if (rc)
-		goto out_err;
-	rc = ccw_device_set_online(card->write.ccwdev);
-	if (rc)
-		goto out_werr;
-
-	LCS_DBF_TEXT(3, setup, "lcsnewdv");
-
-	lcs_setup_card(card);
-	rc = lcs_detect(card);
-	if (rc) {
-		LCS_DBF_TEXT(2, setup, "dtctfail");
-		dev_err(&ccwgdev->dev,
-			"Detecting a network adapter for LCS devices"
-			" failed with rc=%d (0x%x)\n", rc, rc);
-		lcs_stopcard(card);
-		goto out;
-	}
-	if (card->dev) {
-		LCS_DBF_TEXT(2, setup, "samedev");
-		LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-		goto netdev_out;
-	}
-	switch (card->lan_type) {
-	case LCS_FRAME_TYPE_ENET:
-		card->lan_type_trans = eth_type_trans;
-		dev = alloc_etherdev(0);
-		break;
-	default:
-		LCS_DBF_TEXT(3, setup, "errinit");
-		pr_err(" Initialization failed\n");
-		goto out;
-	}
-	if (!dev)
-		goto out;
-	card->dev = dev;
-	card->dev->ml_priv = card;
-	card->dev->netdev_ops = &lcs_netdev_ops;
-	card->dev->dev_port = card->portno;
-	eth_hw_addr_set(card->dev, card->mac);
-#ifdef CONFIG_IP_MULTICAST
-	if (!lcs_check_multicast_support(card))
-		card->dev->netdev_ops = &lcs_mc_netdev_ops;
-#endif
-netdev_out:
-	lcs_set_allowed_threads(card,0xffffffff);
-	if (recover_state == DEV_STATE_RECOVER) {
-		lcs_set_multicast_list(card->dev);
-		card->dev->flags |= IFF_UP;
-		netif_carrier_on(card->dev);
-		netif_wake_queue(card->dev);
-		card->state = DEV_STATE_UP;
-	} else {
-		lcs_stopcard(card);
-	}
-
-	if (lcs_register_netdev(ccwgdev) != 0)
-		goto out;
-
-	/* Print out supported assists: IPv6 */
-	pr_info("LCS device %s %s IPv6 support\n", card->dev->name,
-		(card->ip_assists_supported & LCS_IPASS_IPV6_SUPPORT) ?
-		"with" : "without");
-	/* Print out supported assist: Multicast */
-	pr_info("LCS device %s %s Multicast support\n", card->dev->name,
-		(card->ip_assists_supported & LCS_IPASS_MULTICAST_SUPPORT) ?
-		"with" : "without");
-	return 0;
-out:
-
-	ccw_device_set_offline(card->write.ccwdev);
-out_werr:
-	ccw_device_set_offline(card->read.ccwdev);
-out_err:
-	return -ENODEV;
-}
-
-/*
- * lcs_shutdown_device, called when setting the group device offline.
- */
-static int
-__lcs_shutdown_device(struct ccwgroup_device *ccwgdev, int recovery_mode)
-{
-	struct lcs_card *card;
-	enum lcs_dev_states recover_state;
-	int ret = 0, ret2 = 0, ret3 = 0;
-
-	LCS_DBF_TEXT(3, setup, "shtdndev");
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return -ENODEV;
-	if (recovery_mode == 0) {
-		lcs_set_allowed_threads(card, 0);
-		if (lcs_wait_for_threads(card, LCS_SET_MC_THREAD))
-			return -ERESTARTSYS;
-	}
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	recover_state = card->state;
-
-	ret = lcs_stop_device(card->dev);
-	ret2 = ccw_device_set_offline(card->read.ccwdev);
-	ret3 = ccw_device_set_offline(card->write.ccwdev);
-	if (!ret)
-		ret = (ret2) ? ret2 : ret3;
-	if (ret)
-		LCS_DBF_TEXT_(3, setup, "1err:%d", ret);
-	if (recover_state == DEV_STATE_UP) {
-		card->state = DEV_STATE_RECOVER;
-	}
-	return 0;
-}
-
-static int
-lcs_shutdown_device(struct ccwgroup_device *ccwgdev)
-{
-	return __lcs_shutdown_device(ccwgdev, 0);
-}
-
-/*
- * drive lcs recovery after startup and startlan initiated by Lan Gateway
- */
-static int
-lcs_recovery(void *ptr)
-{
-	struct lcs_card *card;
-	struct ccwgroup_device *gdev;
-        int rc;
-
-	card = (struct lcs_card *) ptr;
-
-	LCS_DBF_TEXT(4, trace, "recover1");
-	if (!lcs_do_run_thread(card, LCS_RECOVERY_THREAD))
-		return 0;
-	LCS_DBF_TEXT(4, trace, "recover2");
-	gdev = card->gdev;
-	dev_warn(&gdev->dev,
-		"A recovery process has been started for the LCS device\n");
-	rc = __lcs_shutdown_device(gdev, 1);
-	rc = lcs_new_device(gdev);
-	if (!rc)
-		pr_info("Device %s successfully recovered!\n",
-			card->dev->name);
-	else
-		pr_info("Device %s could not be recovered!\n",
-			card->dev->name);
-	lcs_clear_thread_running_bit(card, LCS_RECOVERY_THREAD);
-	return 0;
-}
-
-/*
- * lcs_remove_device, free buffers and card
- */
-static void
-lcs_remove_device(struct ccwgroup_device *ccwgdev)
-{
-	struct lcs_card *card;
-
-	card = dev_get_drvdata(&ccwgdev->dev);
-	if (!card)
-		return;
-
-	LCS_DBF_TEXT(3, setup, "remdev");
-	LCS_DBF_HEX(3, setup, &card, sizeof(void*));
-	if (ccwgdev->state == CCWGROUP_ONLINE) {
-		lcs_shutdown_device(ccwgdev);
-	}
-	if (card->dev)
-		unregister_netdev(card->dev);
-	lcs_cleanup_card(card);
-	lcs_free_card(card);
-	dev_set_drvdata(&ccwgdev->dev, NULL);
-	put_device(&ccwgdev->dev);
-}
-
-static struct ccw_device_id lcs_ids[] = {
-	{CCW_DEVICE(0x3088, 0x08), .driver_info = lcs_channel_type_parallel},
-	{CCW_DEVICE(0x3088, 0x1f), .driver_info = lcs_channel_type_2216},
-	{CCW_DEVICE(0x3088, 0x60), .driver_info = lcs_channel_type_osa2},
-	{},
-};
-MODULE_DEVICE_TABLE(ccw, lcs_ids);
-
-static struct ccw_driver lcs_ccw_driver = {
-	.driver = {
-		.owner	= THIS_MODULE,
-		.name	= "lcs",
-	},
-	.ids	= lcs_ids,
-	.probe	= ccwgroup_probe_ccwdev,
-	.remove	= ccwgroup_remove_ccwdev,
-	.int_class = IRQIO_LCS,
-};
-
-/*
- * LCS ccwgroup driver registration
- */
-static struct ccwgroup_driver lcs_group_driver = {
-	.driver = {
-		.owner	= THIS_MODULE,
-		.name	= "lcs",
-	},
-	.ccw_driver  = &lcs_ccw_driver,
-	.setup	     = lcs_probe_device,
-	.remove      = lcs_remove_device,
-	.set_online  = lcs_new_device,
-	.set_offline = lcs_shutdown_device,
-};
-
-static ssize_t group_store(struct device_driver *ddrv, const char *buf,
-			   size_t count)
-{
-	int err;
-	err = ccwgroup_create_dev(lcs_root_dev, &lcs_group_driver, 2, buf);
-	return err ? err : count;
-}
-static DRIVER_ATTR_WO(group);
-
-static struct attribute *lcs_drv_attrs[] = {
-	&driver_attr_group.attr,
-	NULL,
-};
-static struct attribute_group lcs_drv_attr_group = {
-	.attrs = lcs_drv_attrs,
-};
-static const struct attribute_group *lcs_drv_attr_groups[] = {
-	&lcs_drv_attr_group,
-	NULL,
-};
-
-/*
- *  LCS Module/Kernel initialization function
- */
-static int
-__init lcs_init_module(void)
-{
-	int rc;
-
-	pr_info("Loading %s\n", version);
-	rc = lcs_register_debug_facility();
-	LCS_DBF_TEXT(0, setup, "lcsinit");
-	if (rc)
-		goto out_err;
-	lcs_root_dev = root_device_register("lcs");
-	rc = PTR_ERR_OR_ZERO(lcs_root_dev);
-	if (rc)
-		goto register_err;
-	rc = ccw_driver_register(&lcs_ccw_driver);
-	if (rc)
-		goto ccw_err;
-	lcs_group_driver.driver.groups = lcs_drv_attr_groups;
-	rc = ccwgroup_driver_register(&lcs_group_driver);
-	if (rc)
-		goto ccwgroup_err;
-	return 0;
-
-ccwgroup_err:
-	ccw_driver_unregister(&lcs_ccw_driver);
-ccw_err:
-	root_device_unregister(lcs_root_dev);
-register_err:
-	lcs_unregister_debug_facility();
-out_err:
-	pr_err("Initializing the lcs device driver failed\n");
-	return rc;
-}
-
-
-/*
- *  LCS module cleanup function
- */
-static void
-__exit lcs_cleanup_module(void)
-{
-	pr_info("Terminating lcs module.\n");
-	LCS_DBF_TEXT(0, trace, "cleanup");
-	ccwgroup_driver_unregister(&lcs_group_driver);
-	ccw_driver_unregister(&lcs_ccw_driver);
-	root_device_unregister(lcs_root_dev);
-	lcs_unregister_debug_facility();
-}
-
-module_init(lcs_init_module);
-module_exit(lcs_cleanup_module);
-
-MODULE_AUTHOR("Frank Pavlic <fpavlic@de.ibm.com>");
-MODULE_DESCRIPTION("S/390 LAN channel station device driver");
-MODULE_LICENSE("GPL");
-
diff --git a/drivers/s390/net/lcs.h b/drivers/s390/net/lcs.h
deleted file mode 100644
index a2699b70b0502..0000000000000
--- a/drivers/s390/net/lcs.h
+++ /dev/null
@@ -1,342 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*lcs.h*/
-
-#include <linux/interrupt.h>
-#include <linux/netdevice.h>
-#include <linux/skbuff.h>
-#include <linux/workqueue.h>
-#include <linux/refcount.h>
-#include <asm/ccwdev.h>
-
-#define LCS_DBF_TEXT(level, name, text) \
-	do { \
-		debug_text_event(lcs_dbf_##name, level, text); \
-	} while (0)
-
-#define LCS_DBF_HEX(level,name,addr,len) \
-do { \
-	debug_event(lcs_dbf_##name,level,(void*)(addr),len); \
-} while (0)
-
-#define LCS_DBF_TEXT_(level,name,text...) \
-	do { \
-		if (debug_level_enabled(lcs_dbf_##name, level)) { \
-			scnprintf(debug_buffer, sizeof(debug_buffer), text); \
-			debug_text_event(lcs_dbf_##name, level, debug_buffer); \
-		} \
-	} while (0)
-
-/**
- *	sysfs related stuff
- */
-#define CARD_FROM_DEV(cdev) \
-	(struct lcs_card *) dev_get_drvdata( \
-		&((struct ccwgroup_device *)dev_get_drvdata(&cdev->dev))->dev);
-
-/**
- * Enum for classifying detected devices.
- */
-enum lcs_channel_types {
-	/* Device is not a channel  */
-	lcs_channel_type_none,
-
-	/* Device is a 2216 channel */
-	lcs_channel_type_parallel,
-
-	/* Device is a 2216 channel */
-	lcs_channel_type_2216,
-
-	/* Device is a OSA2 card */
-	lcs_channel_type_osa2
-};
-
-/**
- * CCW commands used in this driver
- */
-#define LCS_CCW_WRITE		0x01
-#define LCS_CCW_READ		0x02
-#define LCS_CCW_TRANSFER	0x08
-
-/**
- * LCS device status primitives
- */
-#define LCS_CMD_STARTLAN	0x01
-#define LCS_CMD_STOPLAN		0x02
-#define LCS_CMD_LANSTAT		0x04
-#define LCS_CMD_STARTUP		0x07
-#define LCS_CMD_SHUTDOWN	0x08
-#define LCS_CMD_QIPASSIST	0xb2
-#define LCS_CMD_SETIPM		0xb4
-#define LCS_CMD_DELIPM		0xb5
-
-#define LCS_INITIATOR_TCPIP	0x00
-#define LCS_INITIATOR_LGW	0x01
-#define LCS_STD_CMD_SIZE	16
-#define LCS_MULTICAST_CMD_SIZE	404
-
-/**
- * LCS IPASSIST MASKS,only used when multicast is switched on
- */
-/* Not supported by LCS */
-#define LCS_IPASS_ARP_PROCESSING	0x0001
-#define LCS_IPASS_IN_CHECKSUM_SUPPORT	0x0002
-#define LCS_IPASS_OUT_CHECKSUM_SUPPORT	0x0004
-#define LCS_IPASS_IP_FRAG_REASSEMBLY	0x0008
-#define LCS_IPASS_IP_FILTERING		0x0010
-/* Supported by lcs 3172 */
-#define LCS_IPASS_IPV6_SUPPORT		0x0020
-#define LCS_IPASS_MULTICAST_SUPPORT	0x0040
-
-/**
- * LCS sense byte definitions
- */
-#define LCS_SENSE_BYTE_0 		0
-#define LCS_SENSE_BYTE_1 		1
-#define LCS_SENSE_BYTE_2 		2
-#define LCS_SENSE_BYTE_3 		3
-#define LCS_SENSE_INTERFACE_DISCONNECT	0x01
-#define LCS_SENSE_EQUIPMENT_CHECK	0x10
-#define LCS_SENSE_BUS_OUT_CHECK		0x20
-#define LCS_SENSE_INTERVENTION_REQUIRED 0x40
-#define LCS_SENSE_CMD_REJECT		0x80
-#define LCS_SENSE_RESETTING_EVENT	0x80
-#define LCS_SENSE_DEVICE_ONLINE		0x20
-
-/**
- * LCS packet type definitions
- */
-#define LCS_FRAME_TYPE_CONTROL		0
-#define LCS_FRAME_TYPE_ENET		1
-#define LCS_FRAME_TYPE_TR		2
-#define LCS_FRAME_TYPE_FDDI		7
-#define LCS_FRAME_TYPE_AUTO		-1
-
-/**
- * some more definitions,we will sort them later
- */
-#define LCS_ILLEGAL_OFFSET		0xffff
-#define LCS_IOBUFFERSIZE		0x5000
-#define LCS_NUM_BUFFS			32	/* needs to be power of 2 */
-#define LCS_MAC_LENGTH			6
-#define LCS_INVALID_PORT_NO		-1
-#define LCS_LANCMD_TIMEOUT_DEFAULT      5
-
-/**
- * Multicast state
- */
-#define	 LCS_IPM_STATE_SET_REQUIRED	0
-#define	 LCS_IPM_STATE_DEL_REQUIRED	1
-#define	 LCS_IPM_STATE_ON_CARD		2
-
-/**
- * LCS IP Assist declarations
- * seems to be only used for multicast
- */
-#define	 LCS_IPASS_ARP_PROCESSING	0x0001
-#define	 LCS_IPASS_INBOUND_CSUM_SUPP	0x0002
-#define	 LCS_IPASS_OUTBOUND_CSUM_SUPP	0x0004
-#define	 LCS_IPASS_IP_FRAG_REASSEMBLY	0x0008
-#define	 LCS_IPASS_IP_FILTERING		0x0010
-#define	 LCS_IPASS_IPV6_SUPPORT		0x0020
-#define	 LCS_IPASS_MULTICAST_SUPPORT	0x0040
-
-/**
- * LCS Buffer states
- */
-enum lcs_buffer_states {
-	LCS_BUF_STATE_EMPTY,	/* buffer is empty */
-	LCS_BUF_STATE_LOCKED,	/* buffer is locked, don't touch */
-	LCS_BUF_STATE_READY,	/* buffer is ready for read/write */
-	LCS_BUF_STATE_PROCESSED,
-};
-
-/**
- * LCS Channel State Machine declarations
- */
-enum lcs_channel_states {
-	LCS_CH_STATE_INIT,
-	LCS_CH_STATE_HALTED,
-	LCS_CH_STATE_STOPPED,
-	LCS_CH_STATE_RUNNING,
-	LCS_CH_STATE_SUSPENDED,
-	LCS_CH_STATE_CLEARED,
-	LCS_CH_STATE_ERROR,
-};
-
-/**
- * LCS device state machine
- */
-enum lcs_dev_states {
-	DEV_STATE_DOWN,
-	DEV_STATE_UP,
-	DEV_STATE_RECOVER,
-};
-
-enum lcs_threads {
-	LCS_SET_MC_THREAD 	= 1,
-	LCS_RECOVERY_THREAD 	= 2,
-};
-
-/**
- * LCS struct declarations
- */
-struct lcs_header {
-	__u16  offset;
-	__u8   type;
-	__u8   slot;
-}  __attribute__ ((packed));
-
-struct lcs_ip_mac_pair {
-	__be32  ip_addr;
-	__u8   mac_addr[LCS_MAC_LENGTH];
-	__u8   reserved[2];
-}  __attribute__ ((packed));
-
-struct lcs_ipm_list {
-	struct list_head list;
-	struct lcs_ip_mac_pair ipm;
-	__u8 ipm_state;
-};
-
-struct lcs_cmd {
-	__u16  offset;
-	__u8   type;
-	__u8   slot;
-	__u8   cmd_code;
-	__u8   initiator;
-	__u16  sequence_no;
-	__u16  return_code;
-	union {
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u16  parameter_count;
-			__u8   operator_flags[3];
-			__u8   reserved[3];
-		} lcs_std_cmd;
-		struct {
-			__u16  unused1;
-			__u16  buff_size;
-			__u8   unused2[6];
-		} lcs_startup;
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u8   unused[10];
-			__u8   mac_addr[LCS_MAC_LENGTH];
-			__u32  num_packets_deblocked;
-			__u32  num_packets_blocked;
-			__u32  num_packets_tx_on_lan;
-			__u32  num_tx_errors_detected;
-			__u32  num_tx_packets_disgarded;
-			__u32  num_packets_rx_from_lan;
-			__u32  num_rx_errors_detected;
-			__u32  num_rx_discarded_nobuffs_avail;
-			__u32  num_rx_packets_too_large;
-		} lcs_lanstat_cmd;
-#ifdef CONFIG_IP_MULTICAST
-		struct {
-			__u8   lan_type;
-			__u8   portno;
-			__u16  num_ip_pairs;
-			__u16  ip_assists_supported;
-			__u16  ip_assists_enabled;
-			__u16  version;
-			struct {
-				struct lcs_ip_mac_pair
-				ip_mac_pair[32];
-				__u32	  response_data;
-			} lcs_ipass_ctlmsg __attribute ((packed));
-		} lcs_qipassist __attribute__ ((packed));
-#endif /*CONFIG_IP_MULTICAST */
-	} cmd __attribute__ ((packed));
-}  __attribute__ ((packed));
-
-/**
- * Forward declarations.
- */
-struct lcs_card;
-struct lcs_channel;
-
-/**
- * Definition of an lcs buffer.
- */
-struct lcs_buffer {
-	enum lcs_buffer_states state;
-	void *data;
-	int count;
-	/* Callback for completion notification. */
-	void (*callback)(struct lcs_channel *, struct lcs_buffer *);
-};
-
-struct lcs_reply {
-	struct list_head list;
-	__u16 sequence_no;
-	refcount_t refcnt;
-	/* Callback for completion notification. */
-	void (*callback)(struct lcs_card *, struct lcs_cmd *);
-	wait_queue_head_t wait_q;
-	struct lcs_card *card;
-	struct timer_list timer;
-	int received;
-	int rc;
-};
-
-/**
- * Definition of an lcs channel
- */
-struct lcs_channel {
-	enum lcs_channel_states state;
-	struct ccw_device *ccwdev;
-	struct ccw1 ccws[LCS_NUM_BUFFS + 1];
-	wait_queue_head_t wait_q;
-	struct tasklet_struct irq_tasklet;
-	struct lcs_buffer iob[LCS_NUM_BUFFS];
-	int io_idx;
-	int buf_idx;
-};
-
-
-/**
- * definition of the lcs card
- */
-struct lcs_card {
-	spinlock_t lock;
-	spinlock_t ipm_lock;
-	enum lcs_dev_states state;
-	struct net_device *dev;
-	struct net_device_stats stats;
-	__be16 (*lan_type_trans)(struct sk_buff *skb,
-					 struct net_device *dev);
-	struct ccwgroup_device *gdev;
-	struct lcs_channel read;
-	struct lcs_channel write;
-	struct lcs_buffer *tx_buffer;
-	int tx_emitted;
-	struct list_head lancmd_waiters;
-	int lancmd_timeout;
-
-	struct work_struct kernel_thread_starter;
-	spinlock_t mask_lock;
-	unsigned long thread_start_mask;
-	unsigned long thread_running_mask;
-	unsigned long thread_allowed_mask;
-	wait_queue_head_t wait_q;
-
-#ifdef CONFIG_IP_MULTICAST
-	struct list_head ipm_list;
-#endif
-	__u8 mac[LCS_MAC_LENGTH];
-	__u16 ip_assists_supported;
-	__u16 ip_assists_enabled;
-	__s8 lan_type;
-	__u32 pkt_seq;
-	__u16 sequence_no;
-	__s16 portno;
-	/* Some info copied from probeinfo */
-	u8 device_forced;
-	u8 max_port_no;
-	u8 hint_port_no;
-	s16 port_protocol_no;
-}  __attribute__ ((aligned(8)));
-

From cbe08724c18078564abefbf6591078a7c98e5e0f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Feb 2025 14:48:25 +0000
Subject: [PATCH 0161/2753] net: flush_backlog() small changes

Add READ_ONCE() around reads of skb->dev->reg_state, because
this field can be changed from other threads/cpus.

Instead of calling dev_kfree_skb_irq() and kfree_skb()
while interrupts are masked and locks held,
use a temporary list and use __skb_queue_purge_reason()

Use SKB_DROP_REASON_DEV_READY drop reason to better
describe why these skbs are dropped.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250204144825.316785-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 2b141f20b13b5..c41d1e1cbf62e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6119,16 +6119,18 @@ EXPORT_SYMBOL(netif_receive_skb_list);
 static void flush_backlog(struct work_struct *work)
 {
 	struct sk_buff *skb, *tmp;
+	struct sk_buff_head list;
 	struct softnet_data *sd;
 
+	__skb_queue_head_init(&list);
 	local_bh_disable();
 	sd = this_cpu_ptr(&softnet_data);
 
 	backlog_lock_irq_disable(sd);
 	skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->input_pkt_queue);
-			dev_kfree_skb_irq(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
@@ -6136,14 +6138,16 @@ static void flush_backlog(struct work_struct *work)
 
 	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
-		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
+		if (READ_ONCE(skb->dev->reg_state) == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
-			kfree_skb(skb);
+			__skb_queue_tail(&list, skb);
 			rps_input_queue_head_incr(sd);
 		}
 	}
 	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
+
+	__skb_queue_purge_reason(&list, SKB_DROP_REASON_DEV_READY);
 }
 
 static bool flush_required(int cpu)

From faac69a4ae5abb49e62c79c66b51bb905c9aa5ec Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 4 Feb 2025 07:58:17 +0100
Subject: [PATCH 0162/2753] r8169: don't scan PHY addresses > 0

The PHY address is a dummy, because r8169 PHY access registers
don't support a PHY address. Therefore scan address 0 only.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/830637dd-4016-4a68-92b3-618fcac6589d@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5a5eba49c6515..7306c8e323d72 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5222,6 +5222,7 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->priv = tp;
 	new_bus->parent = &pdev->dev;
 	new_bus->irq[0] = PHY_MAC_INTERRUPT;
+	new_bus->phy_mask = GENMASK(31, 1);
 	snprintf(new_bus->id, MII_BUS_ID_SIZE, "r8169-%x-%x",
 		 pci_domain_nr(pdev->bus), pci_dev_id(pdev));
 

From 50f37fc2a39c4a8cc4813629b4cf239b71c6097d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert@linux-m68k.org>
Date: Tue, 4 Feb 2025 22:36:54 +0100
Subject: [PATCH 0163/2753] ipv4: ip_gre: Fix set but not used warning in
 ipgre_err() if IPv4-only
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

if CONFIG_NET_IPGRE is enabled, but CONFIG_IPV6 is disabled:

    net/ipv4/ip_gre.c: In function ‘ipgre_err’:
    net/ipv4/ip_gre.c:144:22: error: variable ‘data_len’ set but not used [-Werror=unused-but-set-variable]
      144 |         unsigned int data_len = 0;
	  |                      ^~~~~~~~

Fix this by moving all data_len processing inside the IPV6-only section
that uses its result.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501121007.2GofXmh5-lkp@intel.com/
Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/d09113cfe2bfaca02f3dddf832fb5f48dd20958b.1738704881.git.geert@linux-m68k.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_gre.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index ed1b6b44faf80..c9f11a046c263 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -141,7 +141,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	const struct iphdr *iph;
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
-	unsigned int data_len = 0;
 	struct ip_tunnel *t;
 
 	if (tpi->proto == htons(ETH_P_TEB))
@@ -182,7 +181,6 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	case ICMP_TIME_EXCEEDED:
 		if (code != ICMP_EXC_TTL)
 			return 0;
-		data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
 		break;
 
 	case ICMP_REDIRECT:
@@ -190,10 +188,16 @@ static int ipgre_err(struct sk_buff *skb, u32 info,
 	}
 
 #if IS_ENABLED(CONFIG_IPV6)
-	if (tpi->proto == htons(ETH_P_IPV6) &&
-	    !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
-					type, data_len))
-		return 0;
+	if (tpi->proto == htons(ETH_P_IPV6)) {
+		unsigned int data_len = 0;
+
+		if (type == ICMP_TIME_EXCEEDED)
+			data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */
+
+		if (!ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len,
+						type, data_len))
+			return 0;
+	}
 #endif
 
 	if (t->parms.iph.daddr == 0 ||

From f6205f8215f12a96518ac9469ff76294ae7bd612 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:42 +0200
Subject: [PATCH 0164/2753] vxlan: Annotate FDB data races

The 'used' and 'updated' fields in the FDB entry structure can be
accessed concurrently by multiple threads, leading to reports such as
[1]. Can be reproduced using [2].

Suppress these reports by annotating these accesses using
READ_ONCE() / WRITE_ONCE().

[1]
BUG: KCSAN: data-race in vxlan_xmit / vxlan_xmit

write to 0xffff942604d263a8 of 8 bytes by task 286 on cpu 0:
 vxlan_xmit+0xb29/0x2380
 dev_hard_start_xmit+0x84/0x2f0
 __dev_queue_xmit+0x45a/0x1650
 packet_xmit+0x100/0x150
 packet_sendmsg+0x2114/0x2ac0
 __sys_sendto+0x318/0x330
 __x64_sys_sendto+0x76/0x90
 x64_sys_call+0x14e8/0x1c00
 do_syscall_64+0x9e/0x1a0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

read to 0xffff942604d263a8 of 8 bytes by task 287 on cpu 2:
 vxlan_xmit+0xadf/0x2380
 dev_hard_start_xmit+0x84/0x2f0
 __dev_queue_xmit+0x45a/0x1650
 packet_xmit+0x100/0x150
 packet_sendmsg+0x2114/0x2ac0
 __sys_sendto+0x318/0x330
 __x64_sys_sendto+0x76/0x90
 x64_sys_call+0x14e8/0x1c00
 do_syscall_64+0x9e/0x1a0
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

value changed: 0x00000000fffbac6e -> 0x00000000fffbac6f

Reported by Kernel Concurrency Sanitizer on:
CPU: 2 UID: 0 PID: 287 Comm: mausezahn Not tainted 6.13.0-rc7-01544-gb4b270f11a02 #5
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-3.fc41 04/01/2014

[2]
 #!/bin/bash

 set +H
 echo whitelist > /sys/kernel/debug/kcsan
 echo !vxlan_xmit > /sys/kernel/debug/kcsan

 ip link add name vx0 up type vxlan id 10010 dstport 4789 local 192.0.2.1
 bridge fdb add 00:11:22:33:44:55 dev vx0 self static dst 198.51.100.1
 taskset -c 0 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 0 -q &
 taskset -c 2 mausezahn vx0 -a own -b 00:11:22:33:44:55 -c 0 -q &

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 05c10acb2a57e..2f2c6606f7191 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -227,9 +227,9 @@ static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
 			be32_to_cpu(fdb->vni)))
 		goto nla_put_failure;
 
-	ci.ndm_used	 = jiffies_to_clock_t(now - fdb->used);
+	ci.ndm_used	 = jiffies_to_clock_t(now - READ_ONCE(fdb->used));
 	ci.ndm_confirmed = 0;
-	ci.ndm_updated	 = jiffies_to_clock_t(now - fdb->updated);
+	ci.ndm_updated	 = jiffies_to_clock_t(now - READ_ONCE(fdb->updated));
 	ci.ndm_refcnt	 = 0;
 
 	if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
@@ -434,8 +434,8 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 
 	f = __vxlan_find_mac(vxlan, mac, vni);
-	if (f && f->used != jiffies)
-		f->used = jiffies;
+	if (f && READ_ONCE(f->used) != jiffies)
+		WRITE_ONCE(f->used, jiffies);
 
 	return f;
 }
@@ -1009,12 +1009,12 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
 		if (f->state != state) {
 			f->state = state;
-			f->updated = jiffies;
+			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 		if (f->flags != fdb_flags) {
 			f->flags = fdb_flags;
-			f->updated = jiffies;
+			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 	}
@@ -1048,7 +1048,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	}
 
 	if (ndm_flags & NTF_USE)
-		f->used = jiffies;
+		WRITE_ONCE(f->used, jiffies);
 
 	if (notify) {
 		if (rd == NULL)
@@ -1481,7 +1481,7 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 				    src_mac, &rdst->remote_ip.sa, &src_ip->sa);
 
 		rdst->remote_ip = *src_ip;
-		f->updated = jiffies;
+		WRITE_ONCE(f->updated, jiffies);
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
 		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);
@@ -2852,7 +2852,7 @@ static void vxlan_cleanup(struct timer_list *t)
 			if (f->flags & NTF_EXT_LEARNED)
 				continue;
 
-			timeout = f->used + vxlan->cfg.age_interval * HZ;
+			timeout = READ_ONCE(f->used) + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
 					   "garbage collect %pM\n",

From 1370c45d6e7e3cbac4b6dc71f54fd6e167848900 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:43 +0200
Subject: [PATCH 0165/2753] vxlan: Read jiffies once when updating FDB 'used'
 time

Avoid two volatile reads in the data path. Instead, read jiffies once
and only if an FDB entry was found.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 2f2c6606f7191..676a93ce3a197 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -434,8 +434,12 @@ static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 
 	f = __vxlan_find_mac(vxlan, mac, vni);
-	if (f && READ_ONCE(f->used) != jiffies)
-		WRITE_ONCE(f->used, jiffies);
+	if (f) {
+		unsigned long now = jiffies;
+
+		if (READ_ONCE(f->used) != now)
+			WRITE_ONCE(f->used, now);
+	}
 
 	return f;
 }

From c4f2082bf641d270fd518e8c218196eb26ac1c3c Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:44 +0200
Subject: [PATCH 0166/2753] vxlan: Always refresh FDB 'updated' time when
 learning is enabled

Currently, when learning is enabled and a packet is received from the
expected remote, the 'updated' field of the FDB entry is not refreshed.
This will become a problem when we switch the VXLAN driver to age out
entries based on the 'updated' field.

Solve this by always refreshing an FDB entry when we receive a packet
with a matching source MAC address, regardless if it was received via
the expected remote or not as it indicates the host is alive. This is
consistent with the bridge driver's FDB.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 676a93ce3a197..36cb06a56aca9 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1466,6 +1466,10 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 	f = vxlan_find_mac(vxlan, src_mac, vni);
 	if (likely(f)) {
 		struct vxlan_rdst *rdst = first_remote_rcu(f);
+		unsigned long now = jiffies;
+
+		if (READ_ONCE(f->updated) != now)
+			WRITE_ONCE(f->updated, now);
 
 		if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip) &&
 			   rdst->remote_ifindex == ifindex))
@@ -1485,7 +1489,6 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 				    src_mac, &rdst->remote_ip.sa, &src_ip->sa);
 
 		rdst->remote_ip = *src_ip;
-		WRITE_ONCE(f->updated, jiffies);
 		vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL);
 	} else {
 		u32 hash_index = fdb_head_index(vxlan, src_mac, vni);

From 40a9994f2fbddf299655073be947e9cfc57dfdf1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:45 +0200
Subject: [PATCH 0167/2753] vxlan: Refresh FDB 'updated' time upon 'NTF_USE'

The 'NTF_USE' flag can be used by user space to refresh FDB entries so
that they will not age out. Currently, the VXLAN driver implements it by
refreshing the 'used' field in the FDB entry as this is the field
according to which FDB entries are aged out.

Subsequent patches will switch the VXLAN driver to age out entries based
on the 'updated' field. Prepare for this change by refreshing the
'updated' field upon 'NTF_USE'. This is consistent with the bridge
driver's FDB:

 # ip link add name br1 up type bridge
 # ip link add name swp1 master br1 up type dummy
 # bridge fdb add 00:11:22:33:44:55 dev swp1 master dynamic vlan 1
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev swp1 master dynamic vlan 1
 # bridge -s -j fdb get 00:11:22:33:44:55 br br1 vlan 1 | jq '.[]["updated"]'
 10
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev swp1 master use dynamic vlan 1
 # bridge -s -j fdb get 00:11:22:33:44:55 br br1 vlan 1 | jq '.[]["updated"]'
 0

Before:

 # ip link add name vx1 up type vxlan id 10010 dstport 4789
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 10
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self use dynamic dst 198.51.100.1
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 20

After:

 # ip link add name vx1 up type vxlan id 10010 dstport 4789
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 10
 # sleep 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self use dynamic dst 198.51.100.1
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 0

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 36cb06a56aca9..c73138647110a 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1051,8 +1051,10 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 		notify |= rc;
 	}
 
-	if (ndm_flags & NTF_USE)
+	if (ndm_flags & NTF_USE) {
 		WRITE_ONCE(f->used, jiffies);
+		WRITE_ONCE(f->updated, jiffies);
+	}
 
 	if (notify) {
 		if (rd == NULL)

From fb2f449eca514a2dc23fdd35a0973d343f028a92 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:46 +0200
Subject: [PATCH 0168/2753] vxlan: Refresh FDB 'updated' time upon user space
 updates

When a host migrates to a different remote and a packet is received from
the new remote, the corresponding FDB entry is updated and its 'updated'
time is refreshed.

However, when user space replaces the remote of an FDB entry, its
'updated' time is not refreshed:

 # ip link add name vx1 up type vxlan id 10010 dstport 4789
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # sleep 10
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.2
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 10

This can lead to the entry being aged out prematurely and it is also
inconsistent with the bridge driver:

 # ip link add name br1 up type bridge
 # ip link add name swp1 master br1 up type dummy
 # ip link add name swp2 master br1 up type dummy
 # bridge fdb add 00:11:22:33:44:55 dev swp1 master dynamic vlan 1
 # sleep 10
 # bridge -s -j fdb get 00:11:22:33:44:55 br br1 vlan 1 | jq '.[]["updated"]'
 10
 # bridge fdb replace 00:11:22:33:44:55 dev swp2 master dynamic vlan 1
 # bridge -s -j fdb get 00:11:22:33:44:55 br br1 vlan 1 | jq '.[]["updated"]'
 0

Adjust the VXLAN driver to refresh the 'updated' time of an FDB entry
whenever one of its attributes is changed by user space:

 # ip link add name vx1 up type vxlan id 10010 dstport 4789
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # sleep 10
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 10
 # bridge fdb replace 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.2
 # bridge -s -j -p fdb get 00:11:22:33:44:55 br vx1 self | jq '.[]["updated"]'
 0

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index c73138647110a..c75fcb0679acc 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1013,12 +1013,10 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 	    !(f->flags & NTF_VXLAN_ADDED_BY_USER)) {
 		if (f->state != state) {
 			f->state = state;
-			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 		if (f->flags != fdb_flags) {
 			f->flags = fdb_flags;
-			WRITE_ONCE(f->updated, jiffies);
 			notify = 1;
 		}
 	}
@@ -1060,6 +1058,7 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 		if (rd == NULL)
 			rd = first_remote_rtnl(f);
 
+		WRITE_ONCE(f->updated, jiffies);
 		err = vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH,
 				       swdev_notify, extack);
 		if (err)

From b4a1d98b0fa533939128436e24df441a5c025ea7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:47 +0200
Subject: [PATCH 0169/2753] vxlan: Age out FDB entries based on 'updated' time

Currently, the VXLAN driver ages out FDB entries based on their 'used'
time which is refreshed by both the Tx and Rx paths. This means that an
FDB entry will not age out if traffic is only forwarded to the target
host:

 # ip link add name vx1 up type vxlan id 10010 local 192.0.2.1 dstport 4789 learning ageing 10
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # bridge fdb get 00:11:22:33:44:55 br vx1 self
 00:11:22:33:44:55 dev vx1 dst 198.51.100.1 self
 # mausezahn vx1 -a own -b 00:11:22:33:44:55 -c 0 -p 100 -q &
 # sleep 20
 # bridge fdb get 00:11:22:33:44:55 br vx1 self
 00:11:22:33:44:55 dev vx1 dst 198.51.100.1 self

This is wrong as an FDB entry will remain present when we no longer have
an indication that the host is still behind the current remote. It is
also inconsistent with the bridge driver:

 # ip link add name br1 up type bridge ageing_time $((10 * 100))
 # ip link add name swp1 up master br1 type dummy
 # bridge fdb add 00:11:22:33:44:55 dev swp1 master dynamic
 # bridge fdb get 00:11:22:33:44:55 br br1
 00:11:22:33:44:55 dev swp1 master br1
 # mausezahn br1 -a own -b 00:11:22:33:44:55 -c 0 -p 100 -q &
 # sleep 20
 # bridge fdb get 00:11:22:33:44:55 br br1
 Error: Fdb entry not found.

Solve this by aging out entries based on their 'updated' time, which is
not refreshed by the Tx path:

 # ip link add name vx1 up type vxlan id 10010 local 192.0.2.1 dstport 4789 learning ageing 10
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self dynamic dst 198.51.100.1
 # bridge fdb get 00:11:22:33:44:55 br vx1 self
 00:11:22:33:44:55 dev vx1 dst 198.51.100.1 self
 # mausezahn vx1 -a own -b 00:11:22:33:44:55 -c 0 -p 100 -q &
 # sleep 20
 # bridge fdb get 00:11:22:33:44:55 br vx1 self
 Error: Fdb entry not found.

But is refreshed by the Rx path:

 # ip address add 192.0.2.1/32 dev lo
 # ip link add name vx1 up type vxlan id 10010 local 192.0.2.1 dstport 4789 localbypass
 # ip link add name vx2 up type vxlan id 20010 local 192.0.2.1 dstport 4789 learning ageing 10
 # bridge fdb add 00:11:22:33:44:55 dev vx1 self static dst 127.0.0.1 vni 20010
 # mausezahn vx1 -a 00:aa:bb:cc:dd:ee -b 00:11:22:33:44:55 -c 0 -p 100 -q &
 # sleep 20
 # bridge fdb get 00:aa:bb:cc:dd:ee br vx2 self
 00:aa:bb:cc:dd:ee dev vx2 dst 127.0.0.1 self
 # pkill mausezahn
 # sleep 20
 # bridge fdb get 00:aa:bb:cc:dd:ee br vx2 self
 Error: Fdb entry not found.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-7-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index c75fcb0679acc..01797becae09b 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -2860,7 +2860,7 @@ static void vxlan_cleanup(struct timer_list *t)
 			if (f->flags & NTF_EXT_LEARNED)
 				continue;
 
-			timeout = READ_ONCE(f->used) + vxlan->cfg.age_interval * HZ;
+			timeout = READ_ONCE(f->updated) + vxlan->cfg.age_interval * HZ;
 			if (time_before_eq(timeout, jiffies)) {
 				netdev_dbg(vxlan->dev,
 					   "garbage collect %pM\n",

From 9722f834fe9a7c583591defa2cab3f652f50a5f0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:48 +0200
Subject: [PATCH 0170/2753] vxlan: Avoid unnecessary updates to FDB 'used' time

Now that the VXLAN driver ages out FDB entries based on their 'updated'
time we can remove unnecessary updates of the 'used' time from the Rx
path and the control path, so that the 'used' time is only updated by
the Tx path.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-8-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 01797becae09b..ece5415f9013d 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1049,10 +1049,8 @@ static int vxlan_fdb_update_existing(struct vxlan_dev *vxlan,
 		notify |= rc;
 	}
 
-	if (ndm_flags & NTF_USE) {
-		WRITE_ONCE(f->used, jiffies);
+	if (ndm_flags & NTF_USE)
 		WRITE_ONCE(f->updated, jiffies);
-	}
 
 	if (notify) {
 		if (rd == NULL)
@@ -1297,7 +1295,7 @@ int __vxlan_fdb_delete(struct vxlan_dev *vxlan,
 	struct vxlan_fdb *f;
 	int err = -ENOENT;
 
-	f = vxlan_find_mac(vxlan, addr, src_vni);
+	f = __vxlan_find_mac(vxlan, addr, src_vni);
 	if (!f)
 		return err;
 
@@ -1464,7 +1462,7 @@ static enum skb_drop_reason vxlan_snoop(struct net_device *dev,
 		ifindex = src_ifindex;
 #endif
 
-	f = vxlan_find_mac(vxlan, src_mac, vni);
+	f = __vxlan_find_mac(vxlan, src_mac, vni);
 	if (likely(f)) {
 		struct vxlan_rdst *rdst = first_remote_rcu(f);
 		unsigned long now = jiffies;
@@ -4773,7 +4771,7 @@ vxlan_fdb_offloaded_set(struct net_device *dev,
 
 	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
-	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		goto out;
 
@@ -4829,7 +4827,7 @@ vxlan_fdb_external_learn_del(struct net_device *dev,
 	hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	spin_lock_bh(&vxlan->hash_lock[hash_index]);
 
-	f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
+	f = __vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni);
 	if (!f)
 		err = -ENOENT;
 	else if (f->flags & NTF_EXT_LEARNED)

From c467a98e1de0359a0d8b6d881ecc2762c918cfc7 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 4 Feb 2025 16:55:49 +0200
Subject: [PATCH 0171/2753] selftests: forwarding: vxlan_bridge_1d: Check aging
 while forwarding

Extend the VXLAN FDB aging test case to verify that FDB entries are aged
out when they only forward traffic and not refreshed by received
traffic.

The test fails before "vxlan: Age out FDB entries based on 'updated'
time":

 # ./vxlan_bridge_1d.sh
 [...]
 TEST: VXLAN: Ageing of learned FDB entry                            [FAIL]
 [...]
 # echo $?
 1

And passes after it:

 # ./vxlan_bridge_1d.sh
 [...]
 TEST: VXLAN: Ageing of learned FDB entry                            [ OK ]
 [...]
 # echo $?
 0

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250204145549.1216254-9-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 3f9d50f1ef9ec..180c5eca556fe 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -740,6 +740,8 @@ test_learning()
 
 	vxlan_flood_test $mac $dst 0 10 0
 
+	# The entry should age out when it only forwards traffic
+	$MZ $h1 -c 50 -d 1sec -p 64 -b $mac -B $dst -t icmp -q &
 	sleep 60
 
 	bridge fdb show brport vx1 | grep $mac | grep -q self

From c7691aec5e991cec9c5c5fdab08c24856a1fc56f Mon Sep 17 00:00:00 2001
From: Vaishnav Achath <vaishnav.a@ti.com>
Date: Wed, 5 Feb 2025 11:52:29 +0530
Subject: [PATCH 0172/2753] arm64: defconfig: Enable TISCI Interrupt Router and
 Aggregator

Enable TISCI Interrupt Router and Interrupt Aggregator drivers.
These IPs are found in all TI K3 SoCs like J721E, AM62X and is required
for core functionality like DMA, GPIO Interrupts which is necessary
during boot, thus make them built-in.

bloat-o-meter summary on vmlinux:
	add/remove: 460/1 grow/shrink: 4/0 up/down: 162483/-8 (162475)
	...
	Total: Before=31615984, After=31778459, chg +0.51%

These configs were previously selected for ARCH_K3 in respective Kconfigs
till commit b8b26ae398c4 ("irqchip/ti-sci-inta : Add module build support")
and commit 2d95ffaecbc2 ("irqchip/ti-sci-intr: Add module build support")
dropped them and few driver configs (TI_K3_UDMA, TI_K3_RINGACC)
dependent on these also got disabled due to this. While re-enabling the
TI_SCI_INT_*_IRQCHIP configs, these configs with missing dependencies
(which are already part of arm64 defconfig) also get re-enabled which
explains the slightly larger size increase from the bloat-o-meter summary.

Fixes: 2d95ffaecbc2 ("irqchip/ti-sci-intr: Add module build support")
Fixes: b8b26ae398c4 ("irqchip/ti-sci-inta : Add module build support")

Signed-off-by: Vaishnav Achath <vaishnav.a@ti.com>
Tested-by: Dhruva Gole <d-gole@ti.com>
Reviewed-by: Dhruva Gole <d-gole@ti.com>
Link: https://lore.kernel.org/r/20250205062229.3869081-1-vaishnav.a@ti.com
Signed-off-by: Nishanth Menon <nm@ti.com>
---
 arch/arm64/configs/defconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index cb7da44155999..1f25423de3833 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -1551,6 +1551,8 @@ CONFIG_PWM_VISCONTI=m
 CONFIG_SL28CPLD_INTC=y
 CONFIG_QCOM_PDC=y
 CONFIG_QCOM_MPM=y
+CONFIG_TI_SCI_INTR_IRQCHIP=y
+CONFIG_TI_SCI_INTA_IRQCHIP=y
 CONFIG_RESET_GPIO=m
 CONFIG_RESET_IMX7=y
 CONFIG_RESET_QCOM_AOSS=y

From cc668a11e6ac8adb0e016711080d3f314722cc91 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 3 Feb 2025 14:50:59 +0200
Subject: [PATCH 0173/2753] RDMA/mlx5: Fix a race for DMABUF MR which can lead
 to CQE with error

This patch addresses a potential race condition for a DMABUF MR that can
result in a CQE with an error on the UMR QP.

During the __mlx5_ib_dereg_mr() flow, the following sequence of calls
occurs:
mlx5_revoke_mr()
mlx5r_umr_revoke_mr()
mlx5r_umr_post_send_wait()
At this point, the lkey is freed from the hardware's perspective.

However, concurrently, mlx5_ib_dmabuf_invalidate_cb() might be triggered
by another task attempting to invalidate the MR having that freed lkey.

Since the lkey has already been freed, this can lead to a CQE error,
causing the UMR QP to enter an error state.

To resolve this race condition, the dma_resv_lock() which was hold as
part of the mlx5_ib_dmabuf_invalidate_cb() is now also acquired as part
of the mlx5_revoke_mr() scope.

Upon a successful revoke, we set umem_dmabuf->private which points to
that MR to NULL, preventing any further invalidation attempts on its
lkey.

Fixes: e6fb246ccafb ("RDMA/mlx5: Consolidate MR destruction to mlx5_ib_dereg_mr()")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Artemy Kovalyov <artemyko@mnvidia.com>
Link: https://patch.msgid.link/70617067abbfaa0c816a2544c922e7f4346def58.1738587016.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/mr.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index bb02b6adbf2c2..0a3cbb14e1839 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1550,7 +1550,7 @@ static void mlx5_ib_dmabuf_invalidate_cb(struct dma_buf_attachment *attach)
 
 	dma_resv_assert_held(umem_dmabuf->attach->dmabuf->resv);
 
-	if (!umem_dmabuf->sgt)
+	if (!umem_dmabuf->sgt || !mr)
 		return;
 
 	mlx5r_umr_update_mr_pas(mr, MLX5_IB_UPD_XLT_ZAP);
@@ -2022,11 +2022,16 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 	struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
 	struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
 	bool is_odp = is_odp_mr(mr);
+	bool is_odp_dma_buf = is_dmabuf_mr(mr) &&
+			!to_ib_umem_dmabuf(mr->umem)->pinned;
 	int ret = 0;
 
 	if (is_odp)
 		mutex_lock(&to_ib_umem_odp(mr->umem)->umem_mutex);
 
+	if (is_odp_dma_buf)
+		dma_resv_lock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv, NULL);
+
 	if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
 		ent = mr->mmkey.cache_ent;
 		/* upon storing to a clean temp entry - schedule its cleanup */
@@ -2054,6 +2059,12 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
 		mutex_unlock(&to_ib_umem_odp(mr->umem)->umem_mutex);
 	}
 
+	if (is_odp_dma_buf) {
+		if (!ret)
+			to_ib_umem_dmabuf(mr->umem)->private = NULL;
+		dma_resv_unlock(to_ib_umem_dmabuf(mr->umem)->attach->dmabuf->resv);
+	}
+
 	return ret;
 }
 

From abc7b3f1f056d69a8f11d6dceecc0c9549ace770 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 3 Feb 2025 14:51:43 +0200
Subject: [PATCH 0174/2753] RDMA/mlx5: Fix a WARN during dereg_mr for DM type

Memory regions (MR) of type DM (device memory) do not have an associated
umem.

In the __mlx5_ib_dereg_mr() -> mlx5_free_priv_descs() flow, the code
incorrectly takes the wrong branch, attempting to call
dma_unmap_single() on a DMA address that is not mapped.

This results in a WARN [1], as shown below.

The issue is resolved by properly accounting for the DM type and
ensuring the correct branch is selected in mlx5_free_priv_descs().

[1]
WARNING: CPU: 12 PID: 1346 at drivers/iommu/dma-iommu.c:1230 iommu_dma_unmap_page+0x79/0x90
Modules linked in: ip6table_mangle ip6table_nat ip6table_filter ip6_tables iptable_mangle xt_conntrack xt_MASQUERADE nf_conntrack_netlink nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter rpcsec_gss_krb5 auth_rpcgss oid_registry ovelay rpcrdma rdma_ucm ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm ib_ipoib iw_cm ib_cm mlx5_ib ib_uverbs ib_core fuse mlx5_core
CPU: 12 UID: 0 PID: 1346 Comm: ibv_rc_pingpong Not tainted 6.12.0-rc7+ #1631
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
RIP: 0010:iommu_dma_unmap_page+0x79/0x90
Code: 2b 49 3b 29 72 26 49 3b 69 08 73 20 4d 89 f0 44 89 e9 4c 89 e2 48 89 ee 48 89 df 5b 5d 41 5c 41 5d 41 5e 41 5f e9 07 b8 88 ff <0f> 0b 5b 5d 41 5c 41 5d 41 5e 41 5f c3 cc cc cc cc 66 0f 1f 44 00
RSP: 0018:ffffc90001913a10 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff88810194b0a8 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000001
RBP: ffff88810194b0a8 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000000
R13: 0000000000000001 R14: 0000000000000000 R15: 0000000000000000
FS:  00007f537abdd740(0000) GS:ffff88885fb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f537aeb8000 CR3: 000000010c248001 CR4: 0000000000372eb0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
<TASK>
? __warn+0x84/0x190
? iommu_dma_unmap_page+0x79/0x90
? report_bug+0xf8/0x1c0
? handle_bug+0x55/0x90
? exc_invalid_op+0x13/0x60
? asm_exc_invalid_op+0x16/0x20
? iommu_dma_unmap_page+0x79/0x90
dma_unmap_page_attrs+0xe6/0x290
mlx5_free_priv_descs+0xb0/0xe0 [mlx5_ib]
__mlx5_ib_dereg_mr+0x37e/0x520 [mlx5_ib]
? _raw_spin_unlock_irq+0x24/0x40
? wait_for_completion+0xfe/0x130
? rdma_restrack_put+0x63/0xe0 [ib_core]
ib_dereg_mr_user+0x5f/0x120 [ib_core]
? lock_release+0xc6/0x280
destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs]
uobj_destroy+0x3f/0x70 [ib_uverbs]
ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs]
? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs]
? lock_acquire+0xc1/0x2f0
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0x116/0x170 [ib_uverbs]
? lock_release+0xc6/0x280
ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
__x64_sys_ioctl+0x1b0/0xa70
do_syscall_64+0x6b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f537adaf17b
Code: 0f 1e fa 48 8b 05 1d ad 0c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 0f 1f 44 00 00 f3 0f 1e fa b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d ed ac 0c 00 f7 d8 64 89 01 48
RSP: 002b:00007ffff218f0b8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffff218f1d8 RCX: 00007f537adaf17b
RDX: 00007ffff218f1c0 RSI: 00000000c0181b01 RDI: 0000000000000003
RBP: 00007ffff218f1a0 R08: 00007f537aa8d010 R09: 0000561ee2e4f270
R10: 00007f537aace3a8 R11: 0000000000000246 R12: 00007ffff218f190
R13: 000000000000001c R14: 0000561ee2e4d7c0 R15: 00007ffff218f450
</TASK>

Fixes: f18ec4223117 ("RDMA/mlx5: Use a union inside mlx5_ib_mr")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://patch.msgid.link/2039c22cfc3df02378747ba4d623a558b53fc263.1738587076.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/mr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
index 0a3cbb14e1839..753faa9ad06a8 100644
--- a/drivers/infiniband/hw/mlx5/mr.c
+++ b/drivers/infiniband/hw/mlx5/mr.c
@@ -1935,7 +1935,8 @@ mlx5_alloc_priv_descs(struct ib_device *device,
 static void
 mlx5_free_priv_descs(struct mlx5_ib_mr *mr)
 {
-	if (!mr->umem && !mr->data_direct && mr->descs) {
+	if (!mr->umem && !mr->data_direct &&
+	    mr->ibmr.type != IB_MR_TYPE_DM && mr->descs) {
 		struct ib_device *device = mr->ibmr.device;
 		int size = mr->max_descs * mr->desc_size;
 		struct mlx5_ib_dev *dev = to_mdev(device);

From 29b7bb98234cc287cebef9bccf638c2e3f39be71 Mon Sep 17 00:00:00 2001
From: Konstantin Taranov <kotaranov@microsoft.com>
Date: Wed, 5 Feb 2025 02:30:05 -0800
Subject: [PATCH 0175/2753] RDMA/mana_ib: Allocate PAGE aligned doorbell index

Allocate a PAGE aligned doorbell index to ensure each process gets a
separate PAGE sized doorbell area space remapped to it in mana_ib_mmap

Fixes: 0266a177631d ("RDMA/mana_ib: Add a driver for Microsoft Azure Network Adapter")
Signed-off-by: Shiraz Saleem <shirazsaleem@microsoft.com>
Signed-off-by: Konstantin Taranov <kotaranov@microsoft.com>
Link: https://patch.msgid.link/1738751405-15041-1-git-send-email-kotaranov@linux.microsoft.com
Reviewed-by: Long Li <longli@microsoft.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mana/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/mana/main.c b/drivers/infiniband/hw/mana/main.c
index 67c2d43135a8a..457cea6d99095 100644
--- a/drivers/infiniband/hw/mana/main.c
+++ b/drivers/infiniband/hw/mana/main.c
@@ -174,7 +174,7 @@ static int mana_gd_allocate_doorbell_page(struct gdma_context *gc,
 
 	req.resource_type = GDMA_RESOURCE_DOORBELL_PAGE;
 	req.num_resources = 1;
-	req.alignment = 1;
+	req.alignment = PAGE_SIZE / MANA_PAGE_SIZE;
 
 	/* Have GDMA start searching from 0 */
 	req.allocated_resources = 0;

From e3ad54f5bdb9432bf34673f1050e8c28eee7908a Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:02 +0200
Subject: [PATCH 0176/2753] net/mlx5: Add helper functions for PTP callbacks

The PTP callback functions should not be used directly by internal
callers. Add helpers that can be used internally and externally.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 32 +++++++++++++------
 1 file changed, 22 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index d61a1a9297c90..eaf3437560267 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -119,6 +119,13 @@ static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 		   ilog2((U32_MAX / NSEC_PER_MSEC) * dev_freq_khz));
 }
 
+static s32 mlx5_clock_getmaxphase(struct mlx5_core_dev *mdev)
+{
+	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
+		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
+			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+}
+
 static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
@@ -126,14 +133,12 @@ static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 
 	mdev = container_of(clock, struct mlx5_core_dev, clock);
 
-	return MLX5_CAP_MCAM_FEATURE(mdev, mtutc_time_adjustment_extended_range) ?
-		       MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX :
-			     MLX5_MTUTC_OPERATION_ADJUST_TIME_MAX;
+	return mlx5_clock_getmaxphase(mdev);
 }
 
 static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
 {
-	s64 max = mlx5_ptp_getmaxphase(&mdev->clock.ptp_info);
+	s64 max = mlx5_clock_getmaxphase(mdev);
 
 	if (delta < -max || delta > max)
 		return false;
@@ -361,15 +366,12 @@ static int mlx5_ptp_settime_real_time(struct mlx5_core_dev *mdev,
 	return mlx5_set_mtutc(mdev, in, sizeof(in));
 }
 
-static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+static int mlx5_clock_settime(struct mlx5_core_dev *mdev, struct mlx5_clock *clock,
+			      const struct timespec64 *ts)
 {
-	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_timer *timer = &clock->timer;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_settime_real_time(mdev, ts);
 
@@ -385,6 +387,16 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	return 0;
 }
 
+static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64 *ts)
+{
+	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
+	struct mlx5_core_dev *mdev;
+
+	mdev = container_of(clock, struct mlx5_core_dev, clock);
+
+	return  mlx5_clock_settime(mdev, clock, ts);
+}
+
 static
 struct timespec64 mlx5_ptp_gettimex_real_time(struct mlx5_core_dev *mdev,
 					      struct ptp_system_timestamp *sts)
@@ -1129,7 +1141,7 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 		struct timespec64 ts;
 
 		ktime_get_real_ts64(&ts);
-		mlx5_ptp_settime(&clock->ptp_info, &ts);
+		mlx5_clock_settime(mdev, clock, &ts);
 	}
 }
 

From 9f722fb105216771f3a494a83dfad445de8a7f2b Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:03 +0200
Subject: [PATCH 0177/2753] net/mlx5: Change parameters for PTP internal
 functions

In later patch, the mlx5_clock will be allocated dynamically, its
address can be obtained from mlx5_core_dev struct, but mdev can't be
obtained from mlx5_clock because it can be shared by multiple
interfaces. So change the parameter for such internal functions, only
mdev is passed down from the callers.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 19 ++++++++-----------
 1 file changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index eaf3437560267..e7e4bdba02a3a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -878,10 +878,8 @@ static int mlx5_query_mtpps_pin_mode(struct mlx5_core_dev *mdev, u8 pin,
 				    mtpps_size, MLX5_REG_MTPPS, 0, 0);
 }
 
-static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
+static int mlx5_get_pps_pin_mode(struct mlx5_core_dev *mdev, u8 pin)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
-
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {};
 	u8 mode;
 	int err;
@@ -900,8 +898,9 @@ static int mlx5_get_pps_pin_mode(struct mlx5_clock *clock, u8 pin)
 	return PTP_PF_NONE;
 }
 
-static void mlx5_init_pin_config(struct mlx5_clock *clock)
+static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 {
+	struct mlx5_clock *clock = &mdev->clock;
 	int i;
 
 	if (!clock->ptp_info.n_pins)
@@ -922,7 +921,7 @@ static void mlx5_init_pin_config(struct mlx5_clock *clock)
 			 sizeof(clock->ptp_info.pin_config[i].name),
 			 "mlx5_pps%d", i);
 		clock->ptp_info.pin_config[i].index = i;
-		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(clock, i);
+		clock->ptp_info.pin_config[i].func = mlx5_get_pps_pin_mode(mdev, i);
 		clock->ptp_info.pin_config[i].chan = 0;
 	}
 }
@@ -1041,10 +1040,10 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 			 ktime_to_ns(ktime_get_real()));
 }
 
-static void mlx5_init_overflow_period(struct mlx5_clock *clock)
+static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev, clock);
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
+	struct mlx5_clock *clock = &mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u64 overflow_cycles;
 	u64 frac = 0;
@@ -1135,7 +1134,7 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 
 	mlx5_timecounter_init(mdev);
 	mlx5_init_clock_info(mdev);
-	mlx5_init_overflow_period(clock);
+	mlx5_init_overflow_period(mdev);
 
 	if (mlx5_real_time_mode(mdev)) {
 		struct timespec64 ts;
@@ -1147,13 +1146,11 @@ static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
-
 	if (!MLX5_PPS_CAP(mdev))
 		return;
 
 	mlx5_get_pps_caps(mdev);
-	mlx5_init_pin_config(clock);
+	mlx5_init_pin_config(mdev);
 }
 
 void mlx5_init_clock(struct mlx5_core_dev *mdev)

From ccb717a88b2ed57e464c3099d2e8b0c9db7cef21 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:04 +0200
Subject: [PATCH 0178/2753] net/mlx5: Add init and destruction functions for a
 single HW clock

Move hardware clock initialization and destruction to the functions,
which will be used for dynamically allocated clock. Such clock is
shared by all the devices if the queried clock identities are same.

The out_work is for PPS out event, which can't be triggered when clock
is shared, so INIT_WORK is not moved to the initialization function.
Besides, we still need to register notifier for each device.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 48 ++++++++++++-------
 1 file changed, 31 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index e7e4bdba02a3a..cc0a491bf6173 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -1153,17 +1153,11 @@ static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 	mlx5_init_pin_config(mdev);
 }
 
-void mlx5_init_clock(struct mlx5_core_dev *mdev)
+static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
 
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
-		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
-	}
-
 	seqlock_init(&clock->lock);
-	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 
 	/* Initialize the device clock */
 	mlx5_init_timer_clock(mdev);
@@ -1179,28 +1173,19 @@ void mlx5_init_clock(struct mlx5_core_dev *mdev)
 		clock->ptp = NULL;
 	}
 
-	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
-
 	if (clock->ptp)
 		ptp_schedule_worker(clock->ptp, 0);
 }
 
-void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_clock *clock = &mdev->clock;
 
-	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
-		return;
-
-	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
 		clock->ptp = NULL;
 	}
 
-	cancel_work_sync(&clock->pps_info.out_work);
-
 	if (mdev->clock_info) {
 		free_page((unsigned long)mdev->clock_info);
 		mdev->clock_info = NULL;
@@ -1208,3 +1193,32 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 
 	kfree(clock->ptp_info.pin_config);
 }
+
+void mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
+		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
+		return;
+	}
+
+	mlx5_init_clock_dev(mdev);
+
+	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+}
+
+void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = &mdev->clock;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
+	cancel_work_sync(&clock->pps_info.out_work);
+
+	mlx5_destroy_clock_dev(mdev);
+}

From 355f58f10911f9654d42dcba3cbe127238b4fd94 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:05 +0200
Subject: [PATCH 0179/2753] net/mlx5: Add API to get mlx5_core_dev from
 mlx5_clock

The mdev is calculated directly from mlx5_clock, as it's one of the
fields in mlx5_core_dev. Move to a function so it can be easily
changed in next patch.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 35 ++++++++++---------
 1 file changed, 18 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index cc0a491bf6173..b2c88050ba36b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -77,6 +77,11 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
+{
+	return container_of(clock, struct mlx5_core_dev, clock);
+}
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -131,7 +136,7 @@ static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_clock_getmaxphase(mdev);
 }
@@ -226,7 +231,7 @@ static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 	struct system_time_snapshot history_begin = {0};
 	struct mlx5_core_dev *mdev;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (!mlx5_is_ptm_source_time_available(mdev))
 		return -EBUSY;
@@ -268,8 +273,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 {
 	struct mlx5_timer *timer = container_of(cc, struct mlx5_timer, cycles);
 	struct mlx5_clock *clock = container_of(timer, struct mlx5_clock, timer);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_read_time(mdev, NULL, false) & cc->mask;
 }
@@ -304,8 +308,7 @@ static void mlx5_pps_out(struct work_struct *work)
 						 out_work);
 	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
 						pps_info);
-	struct mlx5_core_dev *mdev = container_of(clock, struct mlx5_core_dev,
-						  clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	unsigned long flags;
 	int i;
@@ -335,7 +338,7 @@ static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 	unsigned long flags;
 
 	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	timer = &clock->timer;
 
 	if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR)
@@ -392,7 +395,7 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	return  mlx5_clock_settime(mdev, clock, ts);
 }
@@ -416,7 +419,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	struct mlx5_core_dev *mdev;
 	u64 cycles, ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 	if (mlx5_real_time_mode(mdev)) {
 		*ts = mlx5_ptp_gettimex_real_time(mdev, sts);
 		goto out;
@@ -457,7 +460,7 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
@@ -479,7 +482,7 @@ static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	return mlx5_ptp_adjtime_real_time(mdev, delta);
 }
@@ -512,7 +515,7 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	unsigned long flags;
 	u32 mult;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
 		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
@@ -539,8 +542,7 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 field_select = 0;
 	u8 pin_mode = 0;
@@ -724,8 +726,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev =
-			container_of(clock, struct mlx5_core_dev, clock);
+	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 	bool rt_mode = mlx5_real_time_mode(mdev);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 out_pulse_duration_ns = 0;
@@ -987,7 +988,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 	unsigned long flags;
 	u64 ns;
 
-	mdev = container_of(clock, struct mlx5_core_dev, clock);
+	mdev = mlx5_clock_mdev_get(clock);
 
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:

From f9beaf4fac64c84631ba9a2eb864cea6b52032a2 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:06 +0200
Subject: [PATCH 0180/2753] net/mlx5: Change clock in mlx5_core_dev to
 mlx5_clock pointer

Change clock member in mlx5_core_dev to a pointer, so it can point to
a clock shared by multiple functions in later patch.

For now, each function has its own clock, so mdev in mlx5_clock_priv
is the back pointer to the function. Later it points to one (normally
the first one) of the multiple functions sharing the same clock.

Change mlx5_init_clock() to return error if mlx5_clock is not
allocated. Besides, a null clock is defined and used when hardware
clock is not supported. So, the clock pointer is always pointing to
something valid.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/ptp.c  |  4 +-
 .../net/ethernet/mellanox/mlx5/core/en/trap.c |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  |  4 +-
 .../mellanox/mlx5/core/en/xsk/setup.c         |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  4 +-
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 87 ++++++++++++++-----
 .../ethernet/mellanox/mlx5/core/lib/clock.h   | 35 +++++++-
 .../net/ethernet/mellanox/mlx5/core/main.c    | 11 ++-
 include/linux/mlx5/driver.h                   | 31 +------
 9 files changed, 116 insertions(+), 64 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
index afd654583b6b1..131ed97ca997d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.c
@@ -326,7 +326,7 @@ static int mlx5e_ptp_alloc_txqsq(struct mlx5e_ptp *c, int txq_ix,
 	int node;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->priv      = c->priv;
@@ -696,7 +696,7 @@ static int mlx5e_init_ptp_rq(struct mlx5e_ptp *c, struct mlx5e_params *params,
 	rq->pdev         = c->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
index 53ca16cb9c41a..140606fcd23b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/trap.c
@@ -46,7 +46,7 @@ static void mlx5e_init_trap_rq(struct mlx5e_trap *t, struct mlx5e_params *params
 	rq->pdev         = t->pdev;
 	rq->netdev       = priv->netdev;
 	rq->priv         = priv;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->tstamp       = &priv->tstamp;
 	rq->mdev         = mdev;
 	rq->hw_mtu       = MLX5E_SW2HW_MTU(params, params->sw_mtu);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 94b2916620873..3cc4d55613bf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -289,9 +289,9 @@ static u64 mlx5e_xsk_fill_timestamp(void *_priv)
 	ts = get_cqe_ts(priv->cqe);
 
 	if (mlx5_is_real_time_rq(priv->cq->mdev) || mlx5_is_real_time_sq(priv->cq->mdev))
-		return mlx5_real_time_cyc2time(&priv->cq->mdev->clock, ts);
+		return mlx5_real_time_cyc2time(priv->cq->mdev->clock, ts);
 
-	return  mlx5_timecounter_cyc2time(&priv->cq->mdev->clock, ts);
+	return  mlx5_timecounter_cyc2time(priv->cq->mdev->clock, ts);
 }
 
 static void mlx5e_xsk_request_checksum(u16 csum_start, u16 csum_offset, void *priv)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
index 9240cfe25d102..d743e823362ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c
@@ -72,7 +72,7 @@ static int mlx5e_init_xsk_rq(struct mlx5e_channel *c,
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a814b63ed97e5..c754e0c759342 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -737,7 +737,7 @@ static int mlx5e_init_rxq_rq(struct mlx5e_channel *c, struct mlx5e_params *param
 	rq->netdev       = c->netdev;
 	rq->priv         = c->priv;
 	rq->tstamp       = c->tstamp;
-	rq->clock        = &mdev->clock;
+	rq->clock        = mdev->clock;
 	rq->icosq        = &c->icosq;
 	rq->ix           = c->ix;
 	rq->channel      = c;
@@ -1614,7 +1614,7 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	int err;
 
 	sq->pdev      = c->pdev;
-	sq->clock     = &mdev->clock;
+	sq->clock     = mdev->clock;
 	sq->mkey_be   = c->mkey_be;
 	sq->netdev    = c->netdev;
 	sq->mdev      = c->mdev;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index b2c88050ba36b..da2a21ce8060a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -77,9 +77,19 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+struct mlx5_clock_priv {
+	struct mlx5_clock clock;
+	struct mlx5_core_dev *mdev;
+};
+
+static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
+{
+	return container_of(clock, struct mlx5_clock_priv, clock);
+}
+
 static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
 {
-	return container_of(clock, struct mlx5_core_dev, clock);
+	return clock_priv(clock)->mdev;
 }
 
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
@@ -219,7 +229,7 @@ static int mlx5_mtctr_syncdevicetime(ktime_t *device_time,
 	if (real_time_mode)
 		*device_time = ns_to_ktime(REAL_TIME_TO_NS(device >> 32, device & U32_MAX));
 	else
-		*device_time = mlx5_timecounter_cyc2time(&mdev->clock, device);
+		*device_time = mlx5_timecounter_cyc2time(mdev->clock, device);
 
 	return 0;
 }
@@ -281,7 +291,7 @@ static u64 read_internal_timer(const struct cyclecounter *cc)
 static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer;
 	u32 sign;
 
@@ -599,7 +609,7 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 
 static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u64 cycles_now, cycles_delta;
 	u64 nsec_now, nsec_delta;
 	struct mlx5_timer *timer;
@@ -658,7 +668,7 @@ static int mlx5_perout_conf_out_pulse_duration(struct mlx5_core_dev *mdev,
 					       struct ptp_clock_request *rq,
 					       u32 *out_pulse_duration_ns)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	u32 out_pulse_duration;
 	struct timespec64 ts;
 
@@ -691,7 +701,7 @@ static int perout_conf_npps_real_time(struct mlx5_core_dev *mdev, struct ptp_clo
 				      u32 *field_select, u32 *out_pulse_duration_ns,
 				      u64 *period, u64 *time_stamp)
 {
-	struct mlx5_pps *pps_info = &mdev->clock.pps_info;
+	struct mlx5_pps *pps_info = &mdev->clock->pps_info;
 	struct ptp_clock_time *time = &rq->perout.start;
 	struct timespec64 ts;
 
@@ -901,7 +911,7 @@ static int mlx5_get_pps_pin_mode(struct mlx5_core_dev *mdev, u8 pin)
 
 static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	int i;
 
 	if (!clock->ptp_info.n_pins)
@@ -929,8 +939,8 @@ static void mlx5_init_pin_config(struct mlx5_core_dev *mdev)
 
 static void mlx5_get_pps_caps(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_clock *clock = mdev->clock;
 
 	mlx5_query_mtpps(mdev, out, sizeof(out));
 
@@ -1025,7 +1035,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 
 static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u32 dev_freq;
 
@@ -1044,7 +1054,7 @@ static void mlx5_timecounter_init(struct mlx5_core_dev *mdev)
 static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_clock_info *clock_info = mdev->clock_info;
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_timer *timer = &clock->timer;
 	u64 overflow_cycles;
 	u64 frac = 0;
@@ -1077,7 +1087,7 @@ static void mlx5_init_overflow_period(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	struct mlx5_ib_clock_info *info;
 	struct mlx5_timer *timer;
 
@@ -1100,7 +1110,7 @@ static void mlx5_init_clock_info(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 out[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u32 in[MLX5_ST_SZ_DW(mtutc_reg)] = {};
 	u8 log_max_freq_adjustment = 0;
@@ -1119,7 +1129,7 @@ static void mlx5_init_timer_max_freq_adjustment(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_timer_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	/* Configure the PHC */
 	clock->ptp_info = mlx5_ptp_clock_info;
@@ -1156,7 +1166,7 @@ static void mlx5_init_pps(struct mlx5_core_dev *mdev)
 
 static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	seqlock_init(&clock->lock);
 
@@ -1180,7 +1190,7 @@ static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 
 static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	if (clock->ptp) {
 		ptp_clock_unregister(clock->ptp);
@@ -1195,25 +1205,60 @@ static void mlx5_destroy_clock_dev(struct mlx5_core_dev *mdev)
 	kfree(clock->ptp_info.pin_config);
 }
 
-void mlx5_init_clock(struct mlx5_core_dev *mdev)
+static void mlx5_clock_free(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock_priv *cpriv = clock_priv(mdev->clock);
+
+	mlx5_destroy_clock_dev(mdev);
+	kfree(cpriv);
+	mdev->clock = NULL;
+}
+
+static int mlx5_clock_alloc(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock_priv *cpriv;
+	struct mlx5_clock *clock;
+
+	cpriv = kzalloc(sizeof(*cpriv), GFP_KERNEL);
+	if (!cpriv)
+		return -ENOMEM;
+
+	cpriv->mdev = mdev;
+	clock = &cpriv->clock;
+	mdev->clock = clock;
+	mlx5_init_clock_dev(mdev);
+
+	return 0;
+}
+
+static struct mlx5_clock null_clock;
+
+int mlx5_init_clock(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock;
+	int err;
 
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
+		mdev->clock = &null_clock;
 		mlx5_core_warn(mdev, "invalid device_frequency_khz, aborting HW clock init\n");
-		return;
+		return 0;
 	}
 
-	mlx5_init_clock_dev(mdev);
+	err = mlx5_clock_alloc(mdev);
+	if (err)
+		return err;
+	clock = mdev->clock;
 
 	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
 	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
 	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+
+	return 0;
 }
 
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = &mdev->clock;
+	struct mlx5_clock *clock = mdev->clock;
 
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
 		return;
@@ -1221,5 +1266,5 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
 	cancel_work_sync(&clock->pps_info.out_work);
 
-	mlx5_destroy_clock_dev(mdev);
+	mlx5_clock_free(mdev);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index bd95b9f8d1439..eca1dd9039be6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -33,6 +33,35 @@
 #ifndef __LIB_CLOCK_H__
 #define __LIB_CLOCK_H__
 
+#include <linux/ptp_clock_kernel.h>
+
+#define MAX_PIN_NUM	8
+struct mlx5_pps {
+	u8                         pin_caps[MAX_PIN_NUM];
+	struct work_struct         out_work;
+	u64                        start[MAX_PIN_NUM];
+	u8                         enabled;
+	u64                        min_npps_period;
+	u64                        min_out_pulse_duration_ns;
+};
+
+struct mlx5_timer {
+	struct cyclecounter        cycles;
+	struct timecounter         tc;
+	u32                        nominal_c_mult;
+	unsigned long              overflow_period;
+};
+
+struct mlx5_clock {
+	struct mlx5_nb             pps_nb;
+	seqlock_t                  lock;
+	struct hwtstamp_config     hwtstamp_config;
+	struct ptp_clock          *ptp;
+	struct ptp_clock_info      ptp_info;
+	struct mlx5_pps            pps_info;
+	struct mlx5_timer          timer;
+};
+
 static inline bool mlx5_is_real_time_rq(struct mlx5_core_dev *mdev)
 {
 	u8 rq_ts_format_cap = MLX5_CAP_GEN(mdev, rq_ts_format);
@@ -54,12 +83,12 @@ static inline bool mlx5_is_real_time_sq(struct mlx5_core_dev *mdev)
 typedef ktime_t (*cqe_ts_to_ns)(struct mlx5_clock *, u64);
 
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-void mlx5_init_clock(struct mlx5_core_dev *mdev);
+int mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
-	return mdev->clock.ptp ? ptp_clock_index(mdev->clock.ptp) : -1;
+	return mdev->clock->ptp ? ptp_clock_index(mdev->clock->ptp) : -1;
 }
 
 static inline ktime_t mlx5_timecounter_cyc2time(struct mlx5_clock *clock,
@@ -87,7 +116,7 @@ static inline ktime_t mlx5_real_time_cyc2time(struct mlx5_clock *clock,
 	return ns_to_ktime(time);
 }
 #else
-static inline void mlx5_init_clock(struct mlx5_core_dev *mdev) {}
+static inline int mlx5_init_clock(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec956c4bcebdb..996773521aee7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1038,7 +1038,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 
 	mlx5_init_reserved_gids(dev);
 
-	mlx5_init_clock(dev);
+	err = mlx5_init_clock(dev);
+	if (err) {
+		mlx5_core_err(dev, "failed to initialize hardware clock\n");
+		goto err_tables_cleanup;
+	}
 
 	dev->vxlan = mlx5_vxlan_create(dev);
 	dev->geneve = mlx5_geneve_create(dev);
@@ -1046,7 +1050,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	err = mlx5_init_rl_table(dev);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init rate limiting\n");
-		goto err_tables_cleanup;
+		goto err_clock_cleanup;
 	}
 
 	err = mlx5_mpfs_init(dev);
@@ -1123,10 +1127,11 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	mlx5_mpfs_cleanup(dev);
 err_rl_cleanup:
 	mlx5_cleanup_rl_table(dev);
-err_tables_cleanup:
+err_clock_cleanup:
 	mlx5_geneve_destroy(dev->geneve);
 	mlx5_vxlan_destroy(dev->vxlan);
 	mlx5_cleanup_clock(dev);
+err_tables_cleanup:
 	mlx5_cleanup_reserved_gids(dev);
 	mlx5_cq_debugfs_cleanup(dev);
 	mlx5_fw_reset_cleanup(dev);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af86097641b0b..5dab3d8d05e4f 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -54,7 +54,6 @@
 #include <linux/mlx5/doorbell.h>
 #include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
-#include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
 
 #define MLX5_ADEV_NAME "mlx5_core"
@@ -679,33 +678,7 @@ struct mlx5_rsvd_gids {
 	struct ida ida;
 };
 
-#define MAX_PIN_NUM	8
-struct mlx5_pps {
-	u8                         pin_caps[MAX_PIN_NUM];
-	struct work_struct         out_work;
-	u64                        start[MAX_PIN_NUM];
-	u8                         enabled;
-	u64                        min_npps_period;
-	u64                        min_out_pulse_duration_ns;
-};
-
-struct mlx5_timer {
-	struct cyclecounter        cycles;
-	struct timecounter         tc;
-	u32                        nominal_c_mult;
-	unsigned long              overflow_period;
-};
-
-struct mlx5_clock {
-	struct mlx5_nb             pps_nb;
-	seqlock_t                  lock;
-	struct hwtstamp_config     hwtstamp_config;
-	struct ptp_clock          *ptp;
-	struct ptp_clock_info      ptp_info;
-	struct mlx5_pps            pps_info;
-	struct mlx5_timer          timer;
-};
-
+struct mlx5_clock;
 struct mlx5_dm;
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
@@ -789,7 +762,7 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-	struct mlx5_clock        clock;
+	struct mlx5_clock       *clock;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct mlx5_fw_tracer   *tracer;
 	struct mlx5_rsc_dump    *rsc_dump;

From 574998cf3b3f59afa9e3a6bbb609d9d4eb2023b4 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:07 +0200
Subject: [PATCH 0181/2753] net/mlx5: Add devcom component for the clock shared
 by functions

Add new devcom component for hardware clock. When it is running in
real time mode, the functions are grouped by the identify they query.

According to firmware document, the clock identify size is 64 bits, so
it's safe to memcpy to component key, as the key size is also 64 bits.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 59 ++++++++++++++++++-
 .../ethernet/mellanox/mlx5/core/lib/devcom.h  |  1 +
 include/linux/mlx5/driver.h                   |  2 +
 3 files changed, 61 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index da2a21ce8060a..7e5882ea19e05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -43,6 +43,8 @@
 #include <linux/cpufeature.h>
 #endif /* CONFIG_X86 */
 
+#define MLX5_RT_CLOCK_IDENTITY_SIZE MLX5_FLD_SZ_BYTES(mrtcq_reg, rt_clock_identity)
+
 enum {
 	MLX5_PIN_MODE_IN		= 0x0,
 	MLX5_PIN_MODE_OUT		= 0x1,
@@ -77,6 +79,10 @@ enum {
 	MLX5_MTUTC_OPERATION_ADJUST_TIME_EXTENDED_MAX = 200000,
 };
 
+struct mlx5_clock_dev_state {
+	struct mlx5_devcom_comp_dev *compdev;
+};
+
 struct mlx5_clock_priv {
 	struct mlx5_clock clock;
 	struct mlx5_core_dev *mdev;
@@ -109,6 +115,22 @@ static bool mlx5_modify_mtutc_allowed(struct mlx5_core_dev *mdev)
 	return MLX5_CAP_MCAM_FEATURE(mdev, ptpcyc2realtime_modify);
 }
 
+static int mlx5_clock_identity_get(struct mlx5_core_dev *mdev,
+				   u8 identify[MLX5_RT_CLOCK_IDENTITY_SIZE])
+{
+	u32 out[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	u32 in[MLX5_ST_SZ_DW(mrtcq_reg)] = {};
+	int err;
+
+	err = mlx5_core_access_reg(mdev, in, sizeof(in),
+				   out, sizeof(out), MLX5_REG_MRTCQ, 0, 0);
+	if (!err)
+		memcpy(identify, MLX5_ADDR_OF(mrtcq_reg, out, rt_clock_identity),
+		       MLX5_RT_CLOCK_IDENTITY_SIZE);
+
+	return err;
+}
+
 static u32 mlx5_ptp_shift_constant(u32 dev_freq_khz)
 {
 	/* Optimal shift constant leads to corrections above just 1 scaled ppm.
@@ -1231,11 +1253,26 @@ static int mlx5_clock_alloc(struct mlx5_core_dev *mdev)
 	return 0;
 }
 
+static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key)
+{
+	mdev->clock_state->compdev = mlx5_devcom_register_component(mdev->priv.devc,
+								    MLX5_DEVCOM_SHARED_CLOCK,
+								    key, NULL, mdev);
+}
+
+static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
+{
+	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+}
+
 static struct mlx5_clock null_clock;
 
 int mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
+	u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE];
+	struct mlx5_clock_dev_state *clock_state;
 	struct mlx5_clock *clock;
+	u64 key;
 	int err;
 
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz)) {
@@ -1244,9 +1281,26 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 		return 0;
 	}
 
+	clock_state = kzalloc(sizeof(*clock_state), GFP_KERNEL);
+	if (!clock_state)
+		return -ENOMEM;
+	mdev->clock_state = clock_state;
+
+	if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) {
+		if (mlx5_clock_identity_get(mdev, identity)) {
+			mlx5_core_warn(mdev, "failed to get rt clock identity, create ptp dev per function\n");
+		} else {
+			memcpy(&key, &identity, sizeof(key));
+			mlx5_shared_clock_register(mdev, key);
+		}
+	}
+
 	err = mlx5_clock_alloc(mdev);
-	if (err)
+	if (err) {
+		kfree(clock_state);
+		mdev->clock_state = NULL;
 		return err;
+	}
 	clock = mdev->clock;
 
 	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
@@ -1267,4 +1321,7 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	cancel_work_sync(&clock->pps_info.out_work);
 
 	mlx5_clock_free(mdev);
+	mlx5_shared_clock_unregister(mdev);
+	kfree(mdev->clock_state);
+	mdev->clock_state = NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
index d58032dd0df74..c79699b94a025 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/devcom.h
@@ -11,6 +11,7 @@ enum mlx5_devcom_component {
 	MLX5_DEVCOM_MPV,
 	MLX5_DEVCOM_HCA_PORTS,
 	MLX5_DEVCOM_SD_GROUP,
+	MLX5_DEVCOM_SHARED_CLOCK,
 	MLX5_DEVCOM_NUM_COMPONENTS,
 };
 
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 5dab3d8d05e4f..46bd7550adf81 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -679,6 +679,7 @@ struct mlx5_rsvd_gids {
 };
 
 struct mlx5_clock;
+struct mlx5_clock_dev_state;
 struct mlx5_dm;
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
@@ -763,6 +764,7 @@ struct mlx5_core_dev {
 	struct mlx5_fpga_device *fpga;
 #endif
 	struct mlx5_clock       *clock;
+	struct mlx5_clock_dev_state *clock_state;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct mlx5_fw_tracer   *tracer;
 	struct mlx5_rsc_dump    *rsc_dump;

From 79faf9d76d66a1f846b61008ddf1596bd7944a08 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:08 +0200
Subject: [PATCH 0182/2753] net/mlx5: Move PPS notifier and out_work to
 clock_state

The PPS notifier is currently in mlx5_clock, and mlx5_clock can be
shared in later patch, so the notifier should be registered for each
device to avoid any event miss. Besides, the out_work is scheduled by
PPS out event which is triggered only when the device is in free
running mode. So, both are moved to mlx5_core_dev's clock_state.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 37 +++++++++----------
 .../ethernet/mellanox/mlx5/core/lib/clock.h   |  2 -
 2 files changed, 18 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 7e5882ea19e05..2586b0788b40f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -80,7 +80,10 @@ enum {
 };
 
 struct mlx5_clock_dev_state {
+	struct mlx5_core_dev *mdev;
 	struct mlx5_devcom_comp_dev *compdev;
+	struct mlx5_nb pps_nb;
+	struct work_struct out_work;
 };
 
 struct mlx5_clock_priv {
@@ -336,11 +339,10 @@ static void mlx5_update_clock_info_page(struct mlx5_core_dev *mdev)
 
 static void mlx5_pps_out(struct work_struct *work)
 {
-	struct mlx5_pps *pps_info = container_of(work, struct mlx5_pps,
-						 out_work);
-	struct mlx5_clock *clock = container_of(pps_info, struct mlx5_clock,
-						pps_info);
-	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
+	struct mlx5_clock_dev_state *clock_state = container_of(work, struct mlx5_clock_dev_state,
+								out_work);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	unsigned long flags;
 	int i;
@@ -1012,16 +1014,16 @@ static u64 perout_conf_next_event_timer(struct mlx5_core_dev *mdev,
 static int mlx5_pps_event(struct notifier_block *nb,
 			  unsigned long type, void *data)
 {
-	struct mlx5_clock *clock = mlx5_nb_cof(nb, struct mlx5_clock, pps_nb);
+	struct mlx5_clock_dev_state *clock_state = mlx5_nb_cof(nb, struct mlx5_clock_dev_state,
+							       pps_nb);
+	struct mlx5_core_dev *mdev = clock_state->mdev;
+	struct mlx5_clock *clock = mdev->clock;
 	struct ptp_clock_event ptp_event;
 	struct mlx5_eqe *eqe = data;
 	int pin = eqe->data.pps.pin;
-	struct mlx5_core_dev *mdev;
 	unsigned long flags;
 	u64 ns;
 
-	mdev = mlx5_clock_mdev_get(clock);
-
 	switch (clock->ptp_info.pin_config[pin].func) {
 	case PTP_PF_EXTTS:
 		ptp_event.index = pin;
@@ -1045,7 +1047,7 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		write_seqlock_irqsave(&clock->lock, flags);
 		clock->pps_info.start[pin] = ns;
 		write_sequnlock_irqrestore(&clock->lock, flags);
-		schedule_work(&clock->pps_info.out_work);
+		schedule_work(&clock_state->out_work);
 		break;
 	default:
 		mlx5_core_err(mdev, " Unhandled clock PPS event, func %d\n",
@@ -1271,7 +1273,6 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 {
 	u8 identity[MLX5_RT_CLOCK_IDENTITY_SIZE];
 	struct mlx5_clock_dev_state *clock_state;
-	struct mlx5_clock *clock;
 	u64 key;
 	int err;
 
@@ -1284,6 +1285,7 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 	clock_state = kzalloc(sizeof(*clock_state), GFP_KERNEL);
 	if (!clock_state)
 		return -ENOMEM;
+	clock_state->mdev = mdev;
 	mdev->clock_state = clock_state;
 
 	if (MLX5_CAP_MCAM_REG3(mdev, mrtcq) && mlx5_real_time_mode(mdev)) {
@@ -1301,24 +1303,21 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 		mdev->clock_state = NULL;
 		return err;
 	}
-	clock = mdev->clock;
 
-	INIT_WORK(&clock->pps_info.out_work, mlx5_pps_out);
-	MLX5_NB_INIT(&clock->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &clock->pps_nb);
+	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
 
 	return 0;
 }
 
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 {
-	struct mlx5_clock *clock = mdev->clock;
-
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
 		return;
 
-	mlx5_eq_notifier_unregister(mdev, &clock->pps_nb);
-	cancel_work_sync(&clock->pps_info.out_work);
+	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
+	cancel_work_sync(&mdev->clock_state->out_work);
 
 	mlx5_clock_free(mdev);
 	mlx5_shared_clock_unregister(mdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index eca1dd9039be6..3c5fee2465822 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -38,7 +38,6 @@
 #define MAX_PIN_NUM	8
 struct mlx5_pps {
 	u8                         pin_caps[MAX_PIN_NUM];
-	struct work_struct         out_work;
 	u64                        start[MAX_PIN_NUM];
 	u8                         enabled;
 	u64                        min_npps_period;
@@ -53,7 +52,6 @@ struct mlx5_timer {
 };
 
 struct mlx5_clock {
-	struct mlx5_nb             pps_nb;
 	seqlock_t                  lock;
 	struct hwtstamp_config     hwtstamp_config;
 	struct ptp_clock          *ptp;

From f538ffb7a22d092a8301440bc5d59488c311ea8b Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:09 +0200
Subject: [PATCH 0183/2753] net/mlx5: Support one PTP device per hardware clock

Currently, mlx5 driver exposes a PTP device for each network interface,
resulting in multiple device nodes representing the same underlying
PHC (PTP hardware clock). This causes problem if it is trying to
synchronize to itself. For instance, when ptp4l operates on multiple
interfaces following different masters, phc2sys attempts to
synchronize them in automatic mode.

PHC can be configured to work as free running mode or real time mode.
All functions can access it directly. In this patch, we create one PTP
device for each PHC when it's running in real time mode. All the
functions share the same PTP device if the clock identifies they query
are same, and they are already grouped by devcom in previous commit.
The first mdev in the peer list is chosen when sending
MTPPS/MTUTC/MTPPSE/MRTCQ to firmware. Since the function can be
unloaded at any time, we need to use a mutex lock to protect the mdev
pointer used in PTP and PPS callbacks. Besides, new one should be
picked from the peer list when the current is not available.

The clock info, which is used by IB, is shared by all the interfaces
using the same hardware clock.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 250 ++++++++++++++----
 .../ethernet/mellanox/mlx5/core/lib/clock.h   |   1 +
 2 files changed, 203 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 2586b0788b40f..42df3a6fda93e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -89,6 +89,7 @@ struct mlx5_clock_dev_state {
 struct mlx5_clock_priv {
 	struct mlx5_clock clock;
 	struct mlx5_core_dev *mdev;
+	struct mutex lock; /* protect mdev and used in PTP callbacks */
 };
 
 static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
@@ -96,11 +97,37 @@ static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
 	return container_of(clock, struct mlx5_clock_priv, clock);
 }
 
+static void mlx5_clock_lockdep_assert(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	lockdep_assert(lockdep_is_held(&clock_priv(clock)->lock));
+}
+
 static struct mlx5_core_dev *mlx5_clock_mdev_get(struct mlx5_clock *clock)
 {
+	mlx5_clock_lockdep_assert(clock);
+
 	return clock_priv(clock)->mdev;
 }
 
+static void mlx5_clock_lock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_lock(&clock_priv(clock)->lock);
+}
+
+static void mlx5_clock_unlock(struct mlx5_clock *clock)
+{
+	if (!clock->shared)
+		return;
+
+	mutex_unlock(&clock_priv(clock)->lock);
+}
+
 static bool mlx5_real_time_mode(struct mlx5_core_dev *mdev)
 {
 	return (mlx5_is_real_time_rq(mdev) || mlx5_is_real_time_sq(mdev));
@@ -170,10 +197,14 @@ static s32 mlx5_ptp_getmaxphase(struct ptp_clock_info *ptp)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	s32 ret;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
+	ret = mlx5_clock_getmaxphase(mdev);
+	mlx5_clock_unlock(clock);
 
-	return mlx5_clock_getmaxphase(mdev);
+	return ret;
 }
 
 static bool mlx5_is_mtutc_time_adj_cap(struct mlx5_core_dev *mdev, s64 delta)
@@ -265,16 +296,23 @@ static int mlx5_ptp_getcrosststamp(struct ptp_clock_info *ptp,
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct system_time_snapshot history_begin = {0};
 	struct mlx5_core_dev *mdev;
+	int err;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
 
-	if (!mlx5_is_ptm_source_time_available(mdev))
-		return -EBUSY;
+	if (!mlx5_is_ptm_source_time_available(mdev)) {
+		err = -EBUSY;
+		goto unlock;
+	}
 
 	ktime_get_snapshot(&history_begin);
 
-	return get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
-					     &history_begin, cts);
+	err = get_device_system_crosststamp(mlx5_mtctr_syncdevicetime, mdev,
+					    &history_begin, cts);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 #endif /* CONFIG_X86 */
 
@@ -372,6 +410,7 @@ static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 	unsigned long flags;
 
 	clock = container_of(ptp_info, struct mlx5_clock, ptp_info);
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
 	timer = &clock->timer;
 
@@ -384,6 +423,7 @@ static long mlx5_timestamp_overflow(struct ptp_clock_info *ptp_info)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
 out:
+	mlx5_clock_unlock(clock);
 	return timer->overflow_period;
 }
 
@@ -428,10 +468,14 @@ static int mlx5_ptp_settime(struct ptp_clock_info *ptp, const struct timespec64
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	int err;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_clock_settime(mdev, clock, ts);
+	mlx5_clock_unlock(clock);
 
-	return  mlx5_clock_settime(mdev, clock, ts);
+	return err;
 }
 
 static
@@ -453,6 +497,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	struct mlx5_core_dev *mdev;
 	u64 cycles, ns;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
 	if (mlx5_real_time_mode(mdev)) {
 		*ts = mlx5_ptp_gettimex_real_time(mdev, sts);
@@ -463,6 +508,7 @@ static int mlx5_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts,
 	ns = mlx5_timecounter_cyc2time(clock, cycles);
 	*ts = ns_to_timespec64(ns);
 out:
+	mlx5_clock_unlock(clock);
 	return 0;
 }
 
@@ -493,14 +539,16 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_adjtime_real_time(mdev, delta);
+		err = mlx5_ptp_adjtime_real_time(mdev, delta);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	write_seqlock_irqsave(&clock->lock, flags);
@@ -508,17 +556,23 @@ static int mlx5_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	mlx5_update_clock_info_page(mdev);
 	write_sequnlock_irqrestore(&clock->lock, flags);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_ptp_adjphase(struct ptp_clock_info *ptp, s32 delta)
 {
 	struct mlx5_clock *clock = container_of(ptp, struct mlx5_clock, ptp_info);
 	struct mlx5_core_dev *mdev;
+	int err;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
+	err = mlx5_ptp_adjtime_real_time(mdev, delta);
+	mlx5_clock_unlock(clock);
 
-	return mlx5_ptp_adjtime_real_time(mdev, delta);
+	return err;
 }
 
 static int mlx5_ptp_freq_adj_real_time(struct mlx5_core_dev *mdev, long scaled_ppm)
@@ -547,15 +601,17 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct mlx5_timer *timer = &clock->timer;
 	struct mlx5_core_dev *mdev;
 	unsigned long flags;
+	int err = 0;
 	u32 mult;
 
+	mlx5_clock_lock(clock);
 	mdev = mlx5_clock_mdev_get(clock);
 
 	if (mlx5_modify_mtutc_allowed(mdev)) {
-		int err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
+		err = mlx5_ptp_freq_adj_real_time(mdev, scaled_ppm);
 
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	mult = (u32)adjust_by_scaled_ppm(timer->nominal_c_mult, scaled_ppm);
@@ -567,7 +623,9 @@ static int mlx5_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 	write_sequnlock_irqrestore(&clock->lock, flags);
 	ptp_schedule_worker(clock->ptp, timer->overflow_period);
 
-	return 0;
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_extts_configure(struct ptp_clock_info *ptp,
@@ -576,17 +634,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
 	/* Reject requests with unsupported flags */
 	if (rq->extts.flags & ~(PTP_ENABLE_FEATURE |
 				PTP_RISING_EDGE |
@@ -617,6 +672,14 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 		field_select = MLX5_MTPPS_FS_ENABLE;
 	}
 
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
 	MLX5_SET(mtpps_reg, in, pin, pin);
 	MLX5_SET(mtpps_reg, in, pin_mode, pin_mode);
 	MLX5_SET(mtpps_reg, in, pattern, pattern);
@@ -625,10 +688,13 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
+
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static u64 find_target_cycles(struct mlx5_core_dev *mdev, s64 target_ns)
@@ -760,25 +826,18 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 {
 	struct mlx5_clock *clock =
 			container_of(ptp, struct mlx5_clock, ptp_info);
-	struct mlx5_core_dev *mdev = mlx5_clock_mdev_get(clock);
-	bool rt_mode = mlx5_real_time_mode(mdev);
 	u32 in[MLX5_ST_SZ_DW(mtpps_reg)] = {0};
 	u32 out_pulse_duration_ns = 0;
+	struct mlx5_core_dev *mdev;
 	u32 field_select = 0;
 	u64 npps_period = 0;
 	u64 time_stamp = 0;
 	u8 pin_mode = 0;
 	u8 pattern = 0;
+	bool rt_mode;
 	int pin = -1;
 	int err = 0;
 
-	if (!MLX5_PPS_CAP(mdev))
-		return -EOPNOTSUPP;
-
-	/* Reject requests with unsupported flags */
-	if (mlx5_perout_verify_flags(mdev, rq->perout.flags))
-		return -EOPNOTSUPP;
-
 	if (rq->perout.index >= clock->ptp_info.n_pins)
 		return -EINVAL;
 
@@ -787,14 +846,29 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	if (pin < 0)
 		return -EBUSY;
 
-	if (on) {
-		bool rt_mode = mlx5_real_time_mode(mdev);
+	mlx5_clock_lock(clock);
+	mdev = mlx5_clock_mdev_get(clock);
+	rt_mode = mlx5_real_time_mode(mdev);
+
+	if (!MLX5_PPS_CAP(mdev)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	/* Reject requests with unsupported flags */
+	if (mlx5_perout_verify_flags(mdev, rq->perout.flags)) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
 
+	if (on) {
 		pin_mode = MLX5_PIN_MODE_OUT;
 		pattern = MLX5_OUT_PATTERN_PERIODIC;
 
-		if (rt_mode &&  rq->perout.start.sec > U32_MAX)
-			return -EINVAL;
+		if (rt_mode &&  rq->perout.start.sec > U32_MAX) {
+			err = -EINVAL;
+			goto unlock;
+		}
 
 		field_select |= MLX5_MTPPS_FS_PIN_MODE |
 				MLX5_MTPPS_FS_PATTERN |
@@ -807,7 +881,7 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 		else
 			err = perout_conf_1pps(mdev, rq, &time_stamp, rt_mode);
 		if (err)
-			return err;
+			goto unlock;
 	}
 
 	MLX5_SET(mtpps_reg, in, pin, pin);
@@ -820,13 +894,16 @@ static int mlx5_perout_configure(struct ptp_clock_info *ptp,
 	MLX5_SET(mtpps_reg, in, out_pulse_duration_ns, out_pulse_duration_ns);
 	err = mlx5_set_mtpps(mdev, in, sizeof(in));
 	if (err)
-		return err;
+		goto unlock;
 
 	if (rt_mode)
-		return 0;
+		goto unlock;
 
-	return mlx5_set_mtppse(mdev, pin, 0,
-			       MLX5_EVENT_MODE_REPETETIVE & on);
+	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+
+unlock:
+	mlx5_clock_unlock(clock);
+	return err;
 }
 
 static int mlx5_pps_configure(struct ptp_clock_info *ptp,
@@ -1043,6 +1120,10 @@ static int mlx5_pps_event(struct notifier_block *nb,
 		ptp_clock_event(clock->ptp, &ptp_event);
 		break;
 	case PTP_PF_PEROUT:
+		if (clock->shared) {
+			mlx5_core_warn(mdev, " Received unexpected PPS out event\n");
+			break;
+		}
 		ns = perout_conf_next_event_timer(mdev, clock);
 		write_seqlock_irqsave(&clock->lock, flags);
 		clock->pps_info.start[pin] = ns;
@@ -1201,9 +1282,10 @@ static void mlx5_init_clock_dev(struct mlx5_core_dev *mdev)
 	mlx5_init_pps(mdev);
 
 	clock->ptp = ptp_clock_register(&clock->ptp_info,
-					&mdev->pdev->dev);
+					clock->shared ? NULL : &mdev->pdev->dev);
 	if (IS_ERR(clock->ptp)) {
-		mlx5_core_warn(mdev, "ptp_clock_register failed %ld\n",
+		mlx5_core_warn(mdev, "%sptp_clock_register failed %ld\n",
+			       clock->shared ? "shared clock " : "",
 			       PTR_ERR(clock->ptp));
 		clock->ptp = NULL;
 	}
@@ -1234,11 +1316,12 @@ static void mlx5_clock_free(struct mlx5_core_dev *mdev)
 	struct mlx5_clock_priv *cpriv = clock_priv(mdev->clock);
 
 	mlx5_destroy_clock_dev(mdev);
+	mutex_destroy(&cpriv->lock);
 	kfree(cpriv);
 	mdev->clock = NULL;
 }
 
-static int mlx5_clock_alloc(struct mlx5_core_dev *mdev)
+static int mlx5_clock_alloc(struct mlx5_core_dev *mdev, bool shared)
 {
 	struct mlx5_clock_priv *cpriv;
 	struct mlx5_clock *clock;
@@ -1247,23 +1330,90 @@ static int mlx5_clock_alloc(struct mlx5_core_dev *mdev)
 	if (!cpriv)
 		return -ENOMEM;
 
+	mutex_init(&cpriv->lock);
 	cpriv->mdev = mdev;
 	clock = &cpriv->clock;
+	clock->shared = shared;
 	mdev->clock = clock;
+	mlx5_clock_lock(clock);
 	mlx5_init_clock_dev(mdev);
+	mlx5_clock_unlock(clock);
+
+	if (!clock->shared)
+		return 0;
+
+	if (!clock->ptp) {
+		mlx5_core_warn(mdev, "failed to create ptp dev shared by multiple functions");
+		mlx5_clock_free(mdev);
+		return -EINVAL;
+	}
 
 	return 0;
 }
 
 static void mlx5_shared_clock_register(struct mlx5_core_dev *mdev, u64 key)
 {
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_devcom_comp_dev *pos;
+
 	mdev->clock_state->compdev = mlx5_devcom_register_component(mdev->priv.devc,
 								    MLX5_DEVCOM_SHARED_CLOCK,
 								    key, NULL, mdev);
+	if (IS_ERR(mdev->clock_state->compdev))
+		return;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		mdev->clock = next->clock;
+		/* clock info is shared among all the functions using the same clock */
+		mdev->clock_info = next->clock_info;
+	} else {
+		mlx5_clock_alloc(mdev, true);
+	}
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+	if (!mdev->clock) {
+		mlx5_devcom_unregister_component(mdev->clock_state->compdev);
+		mdev->clock_state->compdev = NULL;
+	}
 }
 
 static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
 {
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	if (next) {
+		struct mlx5_clock_priv *cpriv = clock_priv(clock);
+
+		mlx5_clock_lock(clock);
+		if (mdev == cpriv->mdev)
+			cpriv->mdev = next;
+		mlx5_clock_unlock(clock);
+	} else {
+		mlx5_clock_free(mdev);
+	}
+
+	mdev->clock = NULL;
+	mdev->clock_info = NULL;
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
 	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
 }
 
@@ -1297,11 +1447,13 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 		}
 	}
 
-	err = mlx5_clock_alloc(mdev);
-	if (err) {
-		kfree(clock_state);
-		mdev->clock_state = NULL;
-		return err;
+	if (!mdev->clock) {
+		err = mlx5_clock_alloc(mdev, false);
+		if (err) {
+			kfree(clock_state);
+			mdev->clock_state = NULL;
+			return err;
+		}
 	}
 
 	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
@@ -1319,8 +1471,10 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
 	cancel_work_sync(&mdev->clock_state->out_work);
 
-	mlx5_clock_free(mdev);
-	mlx5_shared_clock_unregister(mdev);
+	if (mdev->clock->shared)
+		mlx5_shared_clock_unregister(mdev);
+	else
+		mlx5_clock_free(mdev);
 	kfree(mdev->clock_state);
 	mdev->clock_state = NULL;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index 3c5fee2465822..093fa131014a4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -58,6 +58,7 @@ struct mlx5_clock {
 	struct ptp_clock_info      ptp_info;
 	struct mlx5_pps            pps_info;
 	struct mlx5_timer          timer;
+	bool                       shared;
 };
 
 static inline bool mlx5_is_real_time_rq(struct mlx5_core_dev *mdev)

From 39c1202fa9428bcb8d1242ee12f81cbcb298c020 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:10 +0200
Subject: [PATCH 0184/2753] net/mlx5: Generate PPS IN event on new function for
 shared clock

As a specific function (mdev) is chosen to send MTPPSE command to
firmware, the event is generated only on that function. When that
function is unloaded, the PPS event can't be forward to PTP device,
even when there are other functions in the group, and PTP device is
not destroyed. To resolve this problem, need to send MTPPSE again from
new function, and dis-arm the event on old function after that.

PPS events are handled by EQ notifier. The async EQs and notifiers are
destroyed in mlx5_eq_table_destroy() which is called before
mlx5_cleanup_clock(). During the period between
mlx5_eq_table_destroy() and mlx5_cleanup_clock(), the events can't be
handled. To avoid event loss, add mlx5_clock_unload() in mlx5_unload()
to arm the event on other available function, and mlx5_clock_load in
mlx5_load() for symmetry.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/lib/clock.c   | 97 +++++++++++++++++--
 .../ethernet/mellanox/mlx5/core/lib/clock.h   |  5 +
 .../net/ethernet/mellanox/mlx5/core/main.c    |  4 +
 3 files changed, 99 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index 42df3a6fda93e..65a94e46edcf1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -90,6 +90,7 @@ struct mlx5_clock_priv {
 	struct mlx5_clock clock;
 	struct mlx5_core_dev *mdev;
 	struct mutex lock; /* protect mdev and used in PTP callbacks */
+	struct mlx5_core_dev *event_mdev;
 };
 
 static struct mlx5_clock_priv *clock_priv(struct mlx5_clock *clock)
@@ -691,6 +692,11 @@ static int mlx5_extts_configure(struct ptp_clock_info *ptp,
 		goto unlock;
 
 	err = mlx5_set_mtppse(mdev, pin, 0, MLX5_EVENT_MODE_REPETETIVE & on);
+	if (err)
+		goto unlock;
+
+	clock->pps_info.pin_armed[pin] = on;
+	clock_priv(clock)->event_mdev = mdev;
 
 unlock:
 	mlx5_clock_unlock(clock);
@@ -1417,6 +1423,90 @@ static void mlx5_shared_clock_unregister(struct mlx5_core_dev *mdev)
 	mlx5_devcom_unregister_component(mdev->clock_state->compdev);
 }
 
+static void mlx5_clock_arm_pps_in_event(struct mlx5_clock *clock,
+					struct mlx5_core_dev *new_mdev,
+					struct mlx5_core_dev *old_mdev)
+{
+	struct ptp_clock_info *ptp_info = &clock->ptp_info;
+	struct mlx5_clock_priv *cpriv = clock_priv(clock);
+	int i;
+
+	for (i = 0; i < ptp_info->n_pins; i++) {
+		if (ptp_info->pin_config[i].func != PTP_PF_EXTTS ||
+		    !clock->pps_info.pin_armed[i])
+			continue;
+
+		if (new_mdev) {
+			mlx5_set_mtppse(new_mdev, i, 0, MLX5_EVENT_MODE_REPETETIVE);
+			cpriv->event_mdev = new_mdev;
+		} else {
+			cpriv->event_mdev = NULL;
+		}
+
+		if (old_mdev)
+			mlx5_set_mtppse(old_mdev, i, 0, MLX5_EVENT_MODE_DISABLE);
+	}
+}
+
+void mlx5_clock_load(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_clock_priv *cpriv;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
+	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
+	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, mdev, NULL);
+		return;
+	}
+
+	cpriv = clock_priv(clock);
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_clock_lock(clock);
+	if (mdev == cpriv->mdev && mdev != cpriv->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, mdev, cpriv->event_mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+}
+
+void mlx5_clock_unload(struct mlx5_core_dev *mdev)
+{
+	struct mlx5_core_dev *peer_dev, *next = NULL;
+	struct mlx5_clock *clock = mdev->clock;
+	struct mlx5_devcom_comp_dev *pos;
+
+	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
+		return;
+
+	if (!clock->shared) {
+		mlx5_clock_arm_pps_in_event(clock, NULL, mdev);
+		goto out;
+	}
+
+	mlx5_devcom_comp_lock(mdev->clock_state->compdev);
+	mlx5_devcom_for_each_peer_entry(mdev->clock_state->compdev, peer_dev, pos) {
+		if (peer_dev->clock && peer_dev != mdev) {
+			next = peer_dev;
+			break;
+		}
+	}
+
+	mlx5_clock_lock(clock);
+	if (mdev == clock_priv(clock)->event_mdev)
+		mlx5_clock_arm_pps_in_event(clock, next, mdev);
+	mlx5_clock_unlock(clock);
+	mlx5_devcom_comp_unlock(mdev->clock_state->compdev);
+
+out:
+	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
+	cancel_work_sync(&mdev->clock_state->out_work);
+}
+
 static struct mlx5_clock null_clock;
 
 int mlx5_init_clock(struct mlx5_core_dev *mdev)
@@ -1456,10 +1546,6 @@ int mlx5_init_clock(struct mlx5_core_dev *mdev)
 		}
 	}
 
-	INIT_WORK(&mdev->clock_state->out_work, mlx5_pps_out);
-	MLX5_NB_INIT(&mdev->clock_state->pps_nb, mlx5_pps_event, PPS_EVENT);
-	mlx5_eq_notifier_register(mdev, &mdev->clock_state->pps_nb);
-
 	return 0;
 }
 
@@ -1468,9 +1554,6 @@ void mlx5_cleanup_clock(struct mlx5_core_dev *mdev)
 	if (!MLX5_CAP_GEN(mdev, device_frequency_khz))
 		return;
 
-	mlx5_eq_notifier_unregister(mdev, &mdev->clock_state->pps_nb);
-	cancel_work_sync(&mdev->clock_state->out_work);
-
 	if (mdev->clock->shared)
 		mlx5_shared_clock_unregister(mdev);
 	else
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
index 093fa131014a4..c18a652c0faa1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.h
@@ -42,6 +42,7 @@ struct mlx5_pps {
 	u8                         enabled;
 	u64                        min_npps_period;
 	u64                        min_out_pulse_duration_ns;
+	bool                       pin_armed[MAX_PIN_NUM];
 };
 
 struct mlx5_timer {
@@ -84,6 +85,8 @@ typedef ktime_t (*cqe_ts_to_ns)(struct mlx5_clock *, u64);
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int mlx5_init_clock(struct mlx5_core_dev *mdev);
 void mlx5_cleanup_clock(struct mlx5_core_dev *mdev);
+void mlx5_clock_load(struct mlx5_core_dev *mdev);
+void mlx5_clock_unload(struct mlx5_core_dev *mdev);
 
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
@@ -117,6 +120,8 @@ static inline ktime_t mlx5_real_time_cyc2time(struct mlx5_clock *clock,
 #else
 static inline int mlx5_init_clock(struct mlx5_core_dev *mdev) { return 0; }
 static inline void mlx5_cleanup_clock(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_load(struct mlx5_core_dev *mdev) {}
+static inline void mlx5_clock_unload(struct mlx5_core_dev *mdev) {}
 static inline int mlx5_clock_get_ptp_index(struct mlx5_core_dev *mdev)
 {
 	return -1;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 996773521aee7..710633d5fdbe0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1364,6 +1364,8 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 		goto err_eq_table;
 	}
 
+	mlx5_clock_load(dev);
+
 	err = mlx5_fw_tracer_init(dev->tracer);
 	if (err) {
 		mlx5_core_err(dev, "Failed to init FW tracer %d\n", err);
@@ -1447,6 +1449,7 @@ static int mlx5_load(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 err_eq_table:
 	mlx5_irq_table_destroy(dev);
@@ -1473,6 +1476,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev)
 	mlx5_hv_vhca_cleanup(dev->hv_vhca);
 	mlx5_fw_reset_events_stop(dev);
 	mlx5_fw_tracer_cleanup(dev->tracer);
+	mlx5_clock_unload(dev);
 	mlx5_eq_table_destroy(dev);
 	mlx5_irq_table_destroy(dev);
 	mlx5_pagealloc_stop(dev);

From 4897f9b7f8bdcf93b8d3b466321fa00bb6d2e600 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:11 +0200
Subject: [PATCH 0185/2753] ethtool: Add support for 200Gbps per lane link
 modes

Define 200G, 400G and 800G link modes using 200Gbps per lane.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-core.c   | 20 ++++++++++++++++-
 include/uapi/linux/ethtool.h | 18 ++++++++++++++++
 net/ethtool/common.c         | 42 ++++++++++++++++++++++++++++++++++++
 3 files changed, 79 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 6bf3ec985f3d3..f181f05cb4297 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -13,7 +13,7 @@
  */
 const char *phy_speed_to_str(int speed)
 {
-	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 103,
+	BUILD_BUG_ON_MSG(__ETHTOOL_LINK_MODE_MASK_NBITS != 121,
 		"Enum ethtool_link_mode_bit_indices and phylib are out of sync. "
 		"If a speed or mode has been added please update phy_speed_to_str "
 		"and the PHY settings array.\n");
@@ -169,6 +169,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 800000, FULL, 800000baseDR8_2_Full		),
 	PHY_SETTING( 800000, FULL, 800000baseSR8_Full		),
 	PHY_SETTING( 800000, FULL, 800000baseVR8_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseCR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseKR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseDR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseDR4_2_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseSR4_Full		),
+	PHY_SETTING( 800000, FULL, 800000baseVR4_Full		),
 	/* 400G */
 	PHY_SETTING( 400000, FULL, 400000baseCR8_Full		),
 	PHY_SETTING( 400000, FULL, 400000baseKR8_Full		),
@@ -180,6 +186,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 400000, FULL, 400000baseLR4_ER4_FR4_Full	),
 	PHY_SETTING( 400000, FULL, 400000baseDR4_Full		),
 	PHY_SETTING( 400000, FULL, 400000baseSR4_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseCR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseKR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseDR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseDR2_2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseSR2_Full		),
+	PHY_SETTING( 400000, FULL, 400000baseVR2_Full		),
 	/* 200G */
 	PHY_SETTING( 200000, FULL, 200000baseCR4_Full		),
 	PHY_SETTING( 200000, FULL, 200000baseKR4_Full		),
@@ -191,6 +203,12 @@ static const struct phy_setting settings[] = {
 	PHY_SETTING( 200000, FULL, 200000baseLR2_ER2_FR2_Full	),
 	PHY_SETTING( 200000, FULL, 200000baseDR2_Full		),
 	PHY_SETTING( 200000, FULL, 200000baseSR2_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseCR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseKR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseDR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseDR_2_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseSR_Full		),
+	PHY_SETTING( 200000, FULL, 200000baseVR_Full		),
 	/* 100G */
 	PHY_SETTING( 100000, FULL, 100000baseCR4_Full		),
 	PHY_SETTING( 100000, FULL, 100000baseKR4_Full		),
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index d1089b88efc7d..e0bd726f84c17 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2057,6 +2057,24 @@ enum ethtool_link_mode_bit_indices {
 	ETHTOOL_LINK_MODE_10baseT1S_Half_BIT		 = 100,
 	ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT	 = 101,
 	ETHTOOL_LINK_MODE_10baseT1BRR_Full_BIT		 = 102,
+	ETHTOOL_LINK_MODE_200000baseCR_Full_BIT		 = 103,
+	ETHTOOL_LINK_MODE_200000baseKR_Full_BIT		 = 104,
+	ETHTOOL_LINK_MODE_200000baseDR_Full_BIT		 = 105,
+	ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT	 = 106,
+	ETHTOOL_LINK_MODE_200000baseSR_Full_BIT		 = 107,
+	ETHTOOL_LINK_MODE_200000baseVR_Full_BIT		 = 108,
+	ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT	 = 109,
+	ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT	 = 110,
+	ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT	 = 111,
+	ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT	 = 112,
+	ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT	 = 113,
+	ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT	 = 114,
+	ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT	 = 115,
+	ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT	 = 116,
+	ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT	 = 117,
+	ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT	 = 118,
+	ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT	 = 119,
+	ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT	 = 120,
 
 	/* must be last entry */
 	__ETHTOOL_LINK_MODE_MASK_NBITS
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 2bd77c94f9f1a..5489d0c9d13f9 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -213,6 +213,24 @@ const char link_mode_names[][ETH_GSTRING_LEN] = {
 	__DEFINE_LINK_MODE_NAME(10, T1S, Half),
 	__DEFINE_LINK_MODE_NAME(10, T1S_P2MP, Half),
 	__DEFINE_LINK_MODE_NAME(10, T1BRR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, CR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, KR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, DR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, DR_2, Full),
+	__DEFINE_LINK_MODE_NAME(200000, SR, Full),
+	__DEFINE_LINK_MODE_NAME(200000, VR, Full),
+	__DEFINE_LINK_MODE_NAME(400000, CR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, KR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, DR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, DR2_2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, SR2, Full),
+	__DEFINE_LINK_MODE_NAME(400000, VR2, Full),
+	__DEFINE_LINK_MODE_NAME(800000, CR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, KR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, DR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, DR4_2, Full),
+	__DEFINE_LINK_MODE_NAME(800000, SR4, Full),
+	__DEFINE_LINK_MODE_NAME(800000, VR4, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 
@@ -221,8 +239,11 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 #define __LINK_MODE_LANES_CR4		4
 #define __LINK_MODE_LANES_CR8		8
 #define __LINK_MODE_LANES_DR		1
+#define __LINK_MODE_LANES_DR_2		1
 #define __LINK_MODE_LANES_DR2		2
+#define __LINK_MODE_LANES_DR2_2		2
 #define __LINK_MODE_LANES_DR4		4
+#define __LINK_MODE_LANES_DR4_2		4
 #define __LINK_MODE_LANES_DR8		8
 #define __LINK_MODE_LANES_KR		1
 #define __LINK_MODE_LANES_KR2		2
@@ -251,6 +272,9 @@ static_assert(ARRAY_SIZE(link_mode_names) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 #define __LINK_MODE_LANES_T1L		1
 #define __LINK_MODE_LANES_T1S		1
 #define __LINK_MODE_LANES_T1S_P2MP	1
+#define __LINK_MODE_LANES_VR		1
+#define __LINK_MODE_LANES_VR2		2
+#define __LINK_MODE_LANES_VR4		4
 #define __LINK_MODE_LANES_VR8		8
 #define __LINK_MODE_LANES_DR8_2		8
 #define __LINK_MODE_LANES_T1BRR		1
@@ -378,6 +402,24 @@ const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(10, T1S, Half),
 	__DEFINE_LINK_MODE_PARAMS(10, T1S_P2MP, Half),
 	__DEFINE_LINK_MODE_PARAMS(10, T1BRR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, CR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, KR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, DR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, DR_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, SR, Full),
+	__DEFINE_LINK_MODE_PARAMS(200000, VR, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, CR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, KR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, DR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, DR2_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, SR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(400000, VR2, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, CR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, KR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, DR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, DR4_2, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, SR4, Full),
+	__DEFINE_LINK_MODE_PARAMS(800000, VR4, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS);
 

From ee0a4fc396f1b6fd1b34e99754896961fb67e4e3 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:12 +0200
Subject: [PATCH 0186/2753] net/mlx5: Add support for 200Gbps per lane link
 modes

This patch exposes new link modes using 200Gbps per lane, including
200G, 400G and 800G modes.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 21 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/port.c    |  3 +++
 include/linux/mlx5/port.h                     |  3 +++
 3 files changed, 27 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index cae39198b4dbc..9c5fcc6995159 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -237,6 +237,27 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_800000baseDR8_2_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseSR8_Full_BIT,
 				       ETHTOOL_LINK_MODE_800000baseVR8_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_200GAUI_1_200GBASE_CR1_KR1, ext,
+				       ETHTOOL_LINK_MODE_200000baseCR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseKR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseDR_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseSR_Full_BIT,
+				       ETHTOOL_LINK_MODE_200000baseVR_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_2_400GBASE_CR2_KR2, ext,
+				       ETHTOOL_LINK_MODE_400000baseCR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseKR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseDR2_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseSR2_Full_BIT,
+				       ETHTOOL_LINK_MODE_400000baseVR2_Full_BIT);
+	MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_800GAUI_4_800GBASE_CR4_KR4, ext,
+				       ETHTOOL_LINK_MODE_800000baseCR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseKR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseDR4_2_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseSR4_Full_BIT,
+				       ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT);
 }
 
 static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 50931584132b9..3995df064101d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1105,6 +1105,9 @@ static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
 	[MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000,
 	[MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000,
 	[MLX5E_800GAUI_8_800GBASE_CR8_KR8] = 800000,
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1] = 200000,
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2] = 400000,
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4] = 800000,
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index e68d42b8ce652..fd625e0dd8691 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -115,9 +115,12 @@ enum mlx5e_ext_link_mode {
 	MLX5E_100GAUI_1_100GBASE_CR_KR		= 11,
 	MLX5E_200GAUI_4_200GBASE_CR4_KR4	= 12,
 	MLX5E_200GAUI_2_200GBASE_CR2_KR2	= 13,
+	MLX5E_200GAUI_1_200GBASE_CR1_KR1	= 14,
 	MLX5E_400GAUI_8_400GBASE_CR8		= 15,
 	MLX5E_400GAUI_4_400GBASE_CR4_KR4	= 16,
+	MLX5E_400GAUI_2_400GBASE_CR2_KR2	= 17,
 	MLX5E_800GAUI_8_800GBASE_CR8_KR8	= 19,
+	MLX5E_800GAUI_4_800GBASE_CR4_KR4	= 20,
 	MLX5E_EXT_LINK_MODES_NUMBER,
 };
 

From 4e343c11efbbc9da8ac6e1a2f23704c9313e056d Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:13 +0200
Subject: [PATCH 0187/2753] net/mlx5e: Support FEC settings for 200G per lane
 link modes

Add support to show and config FEC by ethtool for 200G/lane link
modes. The RS encoding setting is mapped, and can be overridden to
FEC_RS_544_514_INTERLEAVED_QUAD for these modes.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c | 64 ++++++++++++++++---
 .../net/ethernet/mellanox/mlx5/core/en/port.h |  1 +
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  |  1 +
 3 files changed, 56 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index 5f6a0605e4ae8..f62fbfb67a1ba 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -296,11 +296,16 @@ enum mlx5e_fec_supported_link_mode {
 	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_2X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_4X,
 	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X,
+	MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X,
 	MLX5E_MAX_FEC_SUPPORTED_LINK_MODE,
 };
 
 #define MLX5E_FEC_FIRST_50G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_50G_1X
 #define MLX5E_FEC_FIRST_100G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_100G_1X
+#define MLX5E_FEC_FIRST_200G_PER_LANE_MODE MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X
 
 #define MLX5E_FEC_OVERRIDE_ADMIN_POLICY(buf, policy, write, link)			\
 	do {										\
@@ -320,8 +325,10 @@ static bool mlx5e_is_fec_supported_link_mode(struct mlx5_core_dev *dev,
 	return link_mode < MLX5E_FEC_FIRST_50G_PER_LANE_MODE ||
 	       (link_mode < MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
 		MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm)) ||
-	       (link_mode >= MLX5E_FEC_FIRST_100G_PER_LANE_MODE &&
-		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm));
+	       (link_mode < MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_100G_per_lane_in_pplm)) ||
+	       (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE &&
+		MLX5_CAP_PCAM_FEATURE(dev, fec_200G_per_lane_in_pplm));
 }
 
 /* get/set FEC admin field for a given speed */
@@ -368,6 +375,18 @@ static int mlx5e_fec_admin_field(u32 *pplm, u16 *fec_policy, bool write,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		MLX5E_FEC_OVERRIDE_ADMIN_POLICY(pplm, *fec_policy, write, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -421,6 +440,18 @@ static int mlx5e_get_fec_cap_field(u32 *pplm, u16 *fec_cap,
 	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_8X:
 		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_8x);
 		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_200G_1X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 200g_1x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_400G_2X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 400g_2x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_800G_4X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 800g_4x);
+		break;
+	case MLX5E_FEC_SUPPORTED_LINK_MODE_1600G_8X:
+		*fec_cap = MLX5E_GET_FEC_OVERRIDE_CAP(pplm, 1600g_8x);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -494,6 +525,26 @@ int mlx5e_get_fec_mode(struct mlx5_core_dev *dev, u32 *fec_mode_active,
 	return 0;
 }
 
+static u16 mlx5e_remap_fec_conf_mode(enum mlx5e_fec_supported_link_mode link_mode,
+				     u16 conf_fec)
+{
+	/* RS fec in ethtool is originally mapped to MLX5E_FEC_RS_528_514.
+	 * For link modes up to 25G per lane, the value is kept.
+	 * For 50G or 100G per lane, it's remapped to MLX5E_FEC_RS_544_514.
+	 * For 200G per lane, remapped to MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD.
+	 */
+	if (conf_fec != BIT(MLX5E_FEC_RS_528_514))
+		return conf_fec;
+
+	if (link_mode >= MLX5E_FEC_FIRST_200G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD);
+
+	if (link_mode >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
+		return BIT(MLX5E_FEC_RS_544_514);
+
+	return conf_fec;
+}
+
 int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 {
 	bool fec_50g_per_lane = MLX5_CAP_PCAM_FEATURE(dev, fec_50G_per_lane_in_pplm);
@@ -530,14 +581,7 @@ int mlx5e_set_fec_mode(struct mlx5_core_dev *dev, u16 fec_policy)
 		if (!mlx5e_is_fec_supported_link_mode(dev, i))
 			break;
 
-		/* RS fec in ethtool is mapped to MLX5E_FEC_RS_528_514
-		 * to link modes up to 25G per lane and to
-		 * MLX5E_FEC_RS_544_514 in the new link modes based on
-		 * 50G or 100G per lane
-		 */
-		if (conf_fec == (1 << MLX5E_FEC_RS_528_514) &&
-		    i >= MLX5E_FEC_FIRST_50G_PER_LANE_MODE)
-			conf_fec = (1 << MLX5E_FEC_RS_544_514);
+		conf_fec = mlx5e_remap_fec_conf_mode(i, conf_fec);
 
 		mlx5e_get_fec_cap_field(out, &fec_caps, i);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
index d1da225f35dad..fa2283dd383b0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.h
@@ -61,6 +61,7 @@ enum {
 	MLX5E_FEC_NOFEC,
 	MLX5E_FEC_FIRECODE,
 	MLX5E_FEC_RS_528_514,
+	MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD = 4,
 	MLX5E_FEC_RS_544_514 = 7,
 	MLX5E_FEC_LLRS_272_257_1 = 9,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 9c5fcc6995159..f9113cb13a0c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -952,6 +952,7 @@ static const u32 pplm_fec_2_ethtool[] = {
 	[MLX5E_FEC_RS_528_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_RS_544_514] = ETHTOOL_FEC_RS,
 	[MLX5E_FEC_LLRS_272_257_1] = ETHTOOL_FEC_LLRS,
+	[MLX5E_FEC_RS_544_514_INTERLEAVED_QUAD] = ETHTOOL_FEC_RS,
 };
 
 static u32 pplm2ethtool_fec(u_long fec_mode, unsigned long size)

From 6fa15a20b7c34e6558dddd7a63494a68058225ef Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:14 +0200
Subject: [PATCH 0188/2753] net/mlx5: Remove stray semicolon in LAG port
 selection table creation

Remove the stray semicolon in the mlx5_ldev_for_each_reverse() loop.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
index bde79cac33a97..d832a12ffec0e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/port_sel.c
@@ -97,7 +97,7 @@ static int mlx5_lag_create_port_sel_table(struct mlx5_lag *ldev,
 						mlx5_del_flow_rules(lag_definer->rules[idx]);
 					}
 					j = ldev->buckets;
-				};
+				}
 				goto destroy_fg;
 			}
 		}

From 96d64a1ab79516d6e19aa2c0d42b02251d8694ce Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:15 +0200
Subject: [PATCH 0189/2753] net/mlx5e: Remove unused mlx5e_tc_flow_action
 struct

Commit 67efaf45930d ("net/mlx5e: TC, Remove CT action reordering")
removed the usage of mlx5e_tc_flow_action struct, remove the struct as
well.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
index d6c12d0ea55ba..2e528b2c34d64 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/act.h
@@ -73,11 +73,6 @@ struct mlx5e_tc_act {
 	bool is_terminating_action;
 };
 
-struct mlx5e_tc_flow_action {
-	unsigned int num_entries;
-	struct flow_action_entry **entries;
-};
-
 extern struct mlx5e_tc_act mlx5e_tc_act_drop;
 extern struct mlx5e_tc_act mlx5e_tc_act_trap;
 extern struct mlx5e_tc_act mlx5e_tc_act_accept;

From 689805dcc474c2accb5cffbbcea1c06ee4a54570 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Mon, 3 Feb 2025 23:35:16 +0200
Subject: [PATCH 0190/2753] net/mlx5e: Avoid WARN_ON when configuring MQPRIO
 with HTB offload enabled

When attempting to enable MQPRIO while HTB offload is already
configured, the driver currently returns `-EINVAL` and triggers a
`WARN_ON`, leading to an unnecessary call trace.

Update the code to handle this case more gracefully by returning
`-EOPNOTSUPP` instead, while also providing a helpful user message.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index c754e0c759342..2fdc86432ac0f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3816,8 +3816,11 @@ static int mlx5e_setup_tc_mqprio(struct mlx5e_priv *priv,
 	/* MQPRIO is another toplevel qdisc that can't be attached
 	 * simultaneously with the offloaded HTB.
 	 */
-	if (WARN_ON(mlx5e_selq_is_htb_enabled(&priv->selq)))
-		return -EINVAL;
+	if (mlx5e_selq_is_htb_enabled(&priv->selq)) {
+		NL_SET_ERR_MSG_MOD(mqprio->extack,
+				   "MQPRIO cannot be configured when HTB offload is enabled.");
+		return -EOPNOTSUPP;
+	}
 
 	switch (mqprio->mode) {
 	case TC_MQPRIO_MODE_DCB:

From 7e8b24e24ac46038e48c9a042e7d9b31855cbca5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Feb 2025 13:55:09 -0800
Subject: [PATCH 0191/2753] tools: ynl-gen: don't output external constants

A definition with a "header" property is an "external" definition
for C code, as in it is defined already in another C header file.
Other languages will need the exact value but C codegen should
not recreate it. So don't output those definitions in the uAPI
header.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250203215510.1288728-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/net/ynl/pyynl/ynl_gen_c.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index c2eabc90dce8c..aa08b8b1463d0 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -2549,6 +2549,9 @@ def render_uapi(family, cw):
 
     defines = []
     for const in family['definitions']:
+        if const.get('header'):
+            continue
+
         if const['type'] != 'const':
             cw.writes_defines(defines)
             defines = []

From fa796178e5eb0078a9a6c36f60fd6494cfc3f81d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Feb 2025 13:55:10 -0800
Subject: [PATCH 0192/2753] tools: ynl-gen: support limits using definitions

Support using defines / constants in integer checks.
Carolina will need this for rate API extensions.

Reported-by: Carolina Jubran <cjubran@nvidia.com>
Link: https://lore.kernel.org/1e886aaf-e1eb-4f1a-b7ef-f63b350a3320@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250203215510.1288728-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/genetlink-c.yaml      | 5 +++--
 Documentation/netlink/genetlink-legacy.yaml | 5 +++--
 Documentation/netlink/genetlink.yaml        | 5 +++--
 tools/net/ynl/pyynl/ynl_gen_c.py            | 5 ++++-
 4 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 9660ffb1ed6ac..44f2226160cab 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index 16380e12cabe7..ed64acf1bef77 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index b036227b46f1b..e43e50dba2e48 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -14,9 +14,10 @@ $defs:
     pattern: ^[0-9A-Za-z_-]+( - 1)?$
     minimum: 0
   len-or-limit:
-    # literal int or limit based on fixed-width type e.g. u8-min, u16-max, etc.
+    # literal int, const name, or limit based on fixed-width type
+    # e.g. u8-min, u16-max, etc.
     type: [ string, integer ]
-    pattern: ^[su](8|16|32|64)-(min|max)$
+    pattern: ^[0-9A-Za-z_-]+$
     minimum: 0
 
 # Schema for specs
diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index aa08b8b1463d0..b22082fd660e9 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -100,7 +100,7 @@ def get_limit(self, limit, default=None):
         if isinstance(value, int):
             return value
         if value in self.family.consts:
-            raise Exception("Resolving family constants not implemented, yet")
+            return self.family.consts[value]["value"]
         return limit_to_number(value)
 
     def get_limit_str(self, limit, default=None, suffix=''):
@@ -110,6 +110,9 @@ def get_limit_str(self, limit, default=None, suffix=''):
         if isinstance(value, int):
             return str(value) + suffix
         if value in self.family.consts:
+            const = self.family.consts[value]
+            if const.get('header'):
+                return c_upper(value)
             return c_upper(f"{self.family['name']}-{value}")
         return c_upper(value)
 

From 79c0c4689bdf5d0032275f40c8fffe257235a679 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@meta.com>
Date: Mon, 3 Feb 2025 17:00:37 -0800
Subject: [PATCH 0193/2753] eth: fbnic: add MAC address TCAM to debugfs

Add read only access to the 32-entry MAC address TCAM via debugfs.
BMC filtering shares the same table so this is quite useful
to access during debug. See next commit for an example output.

Signed-off-by: Alexander Duyck <alexanderduyck@meta.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250204010038.1404268-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/meta/fbnic/fbnic_debugfs.c   | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index 59951b5abdb78..ac80981f67c00 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -10,6 +10,40 @@
 
 static struct dentry *fbnic_dbg_root;
 
+static void fbnic_dbg_desc_break(struct seq_file *s, int i)
+{
+	while (i--)
+		seq_putc(s, '-');
+
+	seq_putc(s, '\n');
+}
+
+static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES; i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   i, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
+
 static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
 {
 	struct fbnic_dev *fbd = s->private;
@@ -48,6 +82,8 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
 	fbd->dbg_fbd = debugfs_create_dir(name, fbnic_dbg_root);
 	debugfs_create_file("pcie_stats", 0400, fbd->dbg_fbd, fbd,
 			    &fbnic_dbg_pcie_stats_fops);
+	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_mac_addr_fops);
 }
 
 void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)

From 09717c28b76c30b1dc8c261c855ffb2406abab2e Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@meta.com>
Date: Mon, 3 Feb 2025 17:00:38 -0800
Subject: [PATCH 0194/2753] eth: fbnic: set IFF_UNICAST_FLT to avoid enabling
 promiscuous mode when adding unicast addrs

I realized when we were adding unicast addresses we were enabling
promiscuous mode. I did a bit of digging and realized we had overlooked
setting the driver private flag to indicate we supported unicast filtering.

Example below shows the table with 00deadbeef01 as the main NIC address,
and 5 additional addresses in the 00deadbeefX0 format.

  # cat $dbgfs/mac_addr
  Idx S TCAM Bitmap       Addr/Mask
  ----------------------------------
  00  0 00000000,00000000 000000000000
                          000000000000
  01  0 00000000,00000000 000000000000
                          000000000000
  02  0 00000000,00000000 000000000000
                          000000000000
  ...
  24  0 00000000,00000000 000000000000
                          000000000000
  25  1 00100000,00000000 00deadbeef50
                          000000000000
  26  1 00100000,00000000 00deadbeef40
                          000000000000
  27  1 00100000,00000000 00deadbeef30
                          000000000000
  28  1 00100000,00000000 00deadbeef20
                          000000000000
  29  1 00100000,00000000 00deadbeef10
                          000000000000
  30  1 00100000,00000000 00deadbeef01
                          000000000000
  31  0 00000000,00000000 000000000000
                          000000000000

Before rule 31 would be active. With this change it correctly sticks
to just the unicast filters.

Signed-off-by: Alexander Duyck <alexanderduyck@meta.com>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250204010038.1404268-2-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 7a96b6ee773f3..1db57c42333ef 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -628,6 +628,8 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbnic_rss_key_fill(fbn->rss_key);
 	fbnic_rss_init_en_mask(fbn);
 
+	netdev->priv_flags |= IFF_UNICAST_FLT;
+
 	netdev->features |=
 		NETIF_F_RXHASH |
 		NETIF_F_SG |

From 0bdcfaf84a9428c49f971be9024505b9e3b43038 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 5 Feb 2025 09:33:52 -0800
Subject: [PATCH 0195/2753] tools: ynl: add all headers to makefile deps

The Makefile.deps lists uAPI headers to make the build work when
system headers are older than in-tree headers. The problem doesn't
occur for new headers, because system headers are not there at all.
But out-of-tree YNL clone on GH also uses this header to identify
header dependencies, and one day the system headers will exist,
and will get out of date. So let's add the headers we missed.

I don't think this is a fix, but FWIW the commits which added
the missing headers are:

commit 04e65df94b31 ("netlink: spec: add shaper YAML spec")
commit 49922401c219 ("ethtool: separate definitions that are gonna be generated")

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250205173352.446704-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/Makefile.deps | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index 0712b5e82eb79..d027a07c1e2c1 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -17,9 +17,11 @@ get_hdr_inc=-D$(1) -include $(UAPI_PATH)/linux/$(2)
 CFLAGS_devlink:=$(call get_hdr_inc,_LINUX_DEVLINK_H_,devlink.h)
 CFLAGS_dpll:=$(call get_hdr_inc,_LINUX_DPLL_H,dpll.h)
 CFLAGS_ethtool:=$(call get_hdr_inc,_LINUX_ETHTOOL_H,ethtool.h) \
-		$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h)
+	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_H_,ethtool_netlink.h) \
+	$(call get_hdr_inc,_LINUX_ETHTOOL_NETLINK_GENERATED_H,ethtool_netlink_generated.h)
 CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
 CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h)
+CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
 CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h)
 CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)

From 8d522566ae9cb3f0609ddb2a6ce3f4f39988043c Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:12 -0800
Subject: [PATCH 0196/2753] net: page_pool: don't cast mp param to devmem

page_pool_check_memory_provider() is a generic path and shouldn't assume
anything about the actual type of the memory provider argument. It's
fine while devmem is the only provider, but cast away the devmem
specific binding types to avoid confusion.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-2-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/page_pool_user.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 6677e0c2e2565..d5e214c30c310 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -356,7 +356,7 @@ void page_pool_unlist(struct page_pool *pool)
 int page_pool_check_memory_provider(struct net_device *dev,
 				    struct netdev_rx_queue *rxq)
 {
-	struct net_devmem_dmabuf_binding *binding = rxq->mp_params.mp_priv;
+	void *binding = rxq->mp_params.mp_priv;
 	struct page_pool *pool;
 	struct hlist_node *n;
 

From 297d389e9e5bd4704b438257b08bc852281e51ce Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:13 -0800
Subject: [PATCH 0197/2753] net: prefix devmem specific helpers

Add prefixes to all helpers that are specific to devmem TCP, i.e.
net_iov_binding[_id].

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-3-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/devmem.c |  2 +-
 net/core/devmem.h | 14 +++++++-------
 net/ipv4/tcp.c    |  2 +-
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/core/devmem.c b/net/core/devmem.c
index 3bba3f018df03..66cd1ab9224fb 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -94,7 +94,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 
 void net_devmem_free_dmabuf(struct net_iov *niov)
 {
-	struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov);
+	struct net_devmem_dmabuf_binding *binding = net_devmem_iov_binding(niov);
 	unsigned long dma_addr = net_devmem_get_dma_addr(niov);
 
 	if (WARN_ON(!gen_pool_has_addr(binding->chunk_pool, dma_addr,
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 76099ef9c482f..99782ddeca408 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -86,11 +86,16 @@ static inline unsigned int net_iov_idx(const struct net_iov *niov)
 }
 
 static inline struct net_devmem_dmabuf_binding *
-net_iov_binding(const struct net_iov *niov)
+net_devmem_iov_binding(const struct net_iov *niov)
 {
 	return net_iov_owner(niov)->binding;
 }
 
+static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
+{
+	return net_devmem_iov_binding(niov)->id;
+}
+
 static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 {
 	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
@@ -99,11 +104,6 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);
 }
 
-static inline u32 net_iov_binding_id(const struct net_iov *niov)
-{
-	return net_iov_owner(niov)->binding->id;
-}
-
 static inline void
 net_devmem_dmabuf_binding_get(struct net_devmem_dmabuf_binding *binding)
 {
@@ -171,7 +171,7 @@ static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 	return 0;
 }
 
-static inline u32 net_iov_binding_id(const struct net_iov *niov)
+static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
 {
 	return 0;
 }
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c416..b872de9a8271b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2494,7 +2494,7 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 
 				/* Will perform the exchange later */
 				dmabuf_cmsg.frag_token = tcp_xa_pool.tokens[tcp_xa_pool.idx];
-				dmabuf_cmsg.dmabuf_id = net_iov_binding_id(niov);
+				dmabuf_cmsg.dmabuf_id = net_devmem_iov_binding_id(niov);
 
 				offset += copy;
 				remaining_len -= copy;

From 7d60fa9e1ab1e4618b2342d54b2035a0e44d19c6 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:14 -0800
Subject: [PATCH 0198/2753] net: generalise net_iov chunk owners

Currently net_iov stores a pointer to struct dmabuf_genpool_chunk_owner,
which serves as a useful abstraction to share data and provide a
context. However, it's too devmem specific, and we want to reuse it for
other memory providers, and for that we need to decouple net_iov from
devmem. Make net_iov to point to a new base structure called
net_iov_area, which dmabuf_genpool_chunk_owner extends.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-4-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netmem.h | 21 ++++++++++++++++++++-
 net/core/devmem.c    | 25 +++++++++++++------------
 net/core/devmem.h    | 25 +++++++++----------------
 3 files changed, 42 insertions(+), 29 deletions(-)

diff --git a/include/net/netmem.h b/include/net/netmem.h
index 1b58faa4f20f9..c61d5b21e7b42 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -24,11 +24,20 @@ struct net_iov {
 	unsigned long __unused_padding;
 	unsigned long pp_magic;
 	struct page_pool *pp;
-	struct dmabuf_genpool_chunk_owner *owner;
+	struct net_iov_area *owner;
 	unsigned long dma_addr;
 	atomic_long_t pp_ref_count;
 };
 
+struct net_iov_area {
+	/* Array of net_iovs for this area. */
+	struct net_iov *niovs;
+	size_t num_niovs;
+
+	/* Offset into the dma-buf where this chunk starts.  */
+	unsigned long base_virtual;
+};
+
 /* These fields in struct page are used by the page_pool and net stack:
  *
  *        struct {
@@ -54,6 +63,16 @@ NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
 NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
 #undef NET_IOV_ASSERT_OFFSET
 
+static inline struct net_iov_area *net_iov_owner(const struct net_iov *niov)
+{
+	return niov->owner;
+}
+
+static inline unsigned int net_iov_idx(const struct net_iov *niov)
+{
+	return niov - net_iov_owner(niov)->niovs;
+}
+
 /* netmem */
 
 /**
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 66cd1ab9224fb..fb0dddcb4e602 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -33,14 +33,15 @@ static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 {
 	struct dmabuf_genpool_chunk_owner *owner = chunk->owner;
 
-	kvfree(owner->niovs);
+	kvfree(owner->area.niovs);
 	kfree(owner);
 }
 
 static dma_addr_t net_devmem_get_dma_addr(const struct net_iov *niov)
 {
-	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+	struct dmabuf_genpool_chunk_owner *owner;
 
+	owner = net_devmem_iov_to_chunk_owner(niov);
 	return owner->base_dma_addr +
 	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
 }
@@ -83,7 +84,7 @@ net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 
 	offset = dma_addr - owner->base_dma_addr;
 	index = offset / PAGE_SIZE;
-	niov = &owner->niovs[index];
+	niov = &owner->area.niovs[index];
 
 	niov->pp_magic = 0;
 	niov->pp = NULL;
@@ -261,9 +262,9 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 			goto err_free_chunks;
 		}
 
-		owner->base_virtual = virtual;
+		owner->area.base_virtual = virtual;
 		owner->base_dma_addr = dma_addr;
-		owner->num_niovs = len / PAGE_SIZE;
+		owner->area.num_niovs = len / PAGE_SIZE;
 		owner->binding = binding;
 
 		err = gen_pool_add_owner(binding->chunk_pool, dma_addr,
@@ -275,17 +276,17 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 			goto err_free_chunks;
 		}
 
-		owner->niovs = kvmalloc_array(owner->num_niovs,
-					      sizeof(*owner->niovs),
-					      GFP_KERNEL);
-		if (!owner->niovs) {
+		owner->area.niovs = kvmalloc_array(owner->area.num_niovs,
+						   sizeof(*owner->area.niovs),
+						   GFP_KERNEL);
+		if (!owner->area.niovs) {
 			err = -ENOMEM;
 			goto err_free_chunks;
 		}
 
-		for (i = 0; i < owner->num_niovs; i++) {
-			niov = &owner->niovs[i];
-			niov->owner = owner;
+		for (i = 0; i < owner->area.num_niovs; i++) {
+			niov = &owner->area.niovs[i];
+			niov->owner = &owner->area;
 			page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov),
 						      net_devmem_get_dma_addr(niov));
 		}
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 99782ddeca408..a2b9913e9a171 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -10,6 +10,8 @@
 #ifndef _NET_DEVMEM_H
 #define _NET_DEVMEM_H
 
+#include <net/netmem.h>
+
 struct netlink_ext_ack;
 
 struct net_devmem_dmabuf_binding {
@@ -51,17 +53,11 @@ struct net_devmem_dmabuf_binding {
  * allocations from this chunk.
  */
 struct dmabuf_genpool_chunk_owner {
-	/* Offset into the dma-buf where this chunk starts.  */
-	unsigned long base_virtual;
+	struct net_iov_area area;
+	struct net_devmem_dmabuf_binding *binding;
 
 	/* dma_addr of the start of the chunk.  */
 	dma_addr_t base_dma_addr;
-
-	/* Array of net_iovs for this chunk. */
-	struct net_iov *niovs;
-	size_t num_niovs;
-
-	struct net_devmem_dmabuf_binding *binding;
 };
 
 void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding);
@@ -75,20 +71,17 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 void dev_dmabuf_uninstall(struct net_device *dev);
 
 static inline struct dmabuf_genpool_chunk_owner *
-net_iov_owner(const struct net_iov *niov)
+net_devmem_iov_to_chunk_owner(const struct net_iov *niov)
 {
-	return niov->owner;
-}
+	struct net_iov_area *owner = net_iov_owner(niov);
 
-static inline unsigned int net_iov_idx(const struct net_iov *niov)
-{
-	return niov - net_iov_owner(niov)->niovs;
+	return container_of(owner, struct dmabuf_genpool_chunk_owner, area);
 }
 
 static inline struct net_devmem_dmabuf_binding *
 net_devmem_iov_binding(const struct net_iov *niov)
 {
-	return net_iov_owner(niov)->binding;
+	return net_devmem_iov_to_chunk_owner(niov)->binding;
 }
 
 static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
@@ -98,7 +91,7 @@ static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
 
 static inline unsigned long net_iov_virtual_addr(const struct net_iov *niov)
 {
-	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+	struct net_iov_area *owner = net_iov_owner(niov);
 
 	return owner->base_virtual +
 	       ((unsigned long)net_iov_idx(niov) << PAGE_SHIFT);

From 57afb483015768903029c8336ee287f4b03c1235 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:15 -0800
Subject: [PATCH 0199/2753] net: page_pool: create hooks for custom memory
 providers

A spin off from the original page pool memory providers patch by Jakub,
which allows extending page pools with custom allocators. One of such
providers is devmem TCP, and the other is io_uring zerocopy added in
following patches.

Link: https://lore.kernel.org/netdev/20230707183935.997267-7-kuba@kernel.org/
Co-developed-by: Jakub Kicinski <kuba@kernel.org> # initial mp proposal
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-5-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/memory_provider.h | 15 +++++++++++++++
 include/net/page_pool/types.h           |  4 ++++
 net/core/devmem.c                       | 15 ++++++++++++++-
 net/core/page_pool.c                    | 23 +++++++++++++++--------
 4 files changed, 48 insertions(+), 9 deletions(-)
 create mode 100644 include/net/page_pool/memory_provider.h

diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
new file mode 100644
index 0000000000000..e49d0a52629d7
--- /dev/null
+++ b/include/net/page_pool/memory_provider.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _NET_PAGE_POOL_MEMORY_PROVIDER_H
+#define _NET_PAGE_POOL_MEMORY_PROVIDER_H
+
+#include <net/netmem.h>
+#include <net/page_pool/types.h>
+
+struct memory_provider_ops {
+	netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp);
+	bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem);
+	int (*init)(struct page_pool *pool);
+	void (*destroy)(struct page_pool *pool);
+};
+
+#endif
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 7f405672b089d..36eb57d73abc6 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -152,8 +152,11 @@ struct page_pool_stats {
  */
 #define PAGE_POOL_FRAG_GROUP_ALIGN	(4 * sizeof(long))
 
+struct memory_provider_ops;
+
 struct pp_memory_provider_params {
 	void *mp_priv;
+	const struct memory_provider_ops *mp_ops;
 };
 
 struct page_pool {
@@ -216,6 +219,7 @@ struct page_pool {
 	struct ptr_ring ring;
 
 	void *mp_priv;
+	const struct memory_provider_ops *mp_ops;
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
diff --git a/net/core/devmem.c b/net/core/devmem.c
index fb0dddcb4e602..c81625ca57c61 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -16,6 +16,7 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <trace/events/page_pool.h>
 
 #include "devmem.h"
@@ -27,6 +28,8 @@
 /* Protected by rtnl_lock() */
 static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
 
+static const struct memory_provider_ops dmabuf_devmem_ops;
+
 static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 					       struct gen_pool_chunk *chunk,
 					       void *not_used)
@@ -118,6 +121,7 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		WARN_ON(rxq->mp_params.mp_priv != binding);
 
 		rxq->mp_params.mp_priv = NULL;
+		rxq->mp_params.mp_ops = NULL;
 
 		rxq_idx = get_netdev_rx_queue_index(rxq);
 
@@ -153,7 +157,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	}
 
 	rxq = __netif_get_rx_queue(dev, rxq_idx);
-	if (rxq->mp_params.mp_priv) {
+	if (rxq->mp_params.mp_ops) {
 		NL_SET_ERR_MSG(extack, "designated queue already memory provider bound");
 		return -EEXIST;
 	}
@@ -171,6 +175,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 		return err;
 
 	rxq->mp_params.mp_priv = binding;
+	rxq->mp_params.mp_ops = &dmabuf_devmem_ops;
 
 	err = netdev_rx_queue_restart(dev, rxq_idx);
 	if (err)
@@ -180,6 +185,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 
 err_xa_erase:
 	rxq->mp_params.mp_priv = NULL;
+	rxq->mp_params.mp_ops = NULL;
 	xa_erase(&binding->bound_rxqs, xa_idx);
 
 	return err;
@@ -399,3 +405,10 @@ bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem)
 	/* We don't want the page pool put_page()ing our net_iovs. */
 	return false;
 }
+
+static const struct memory_provider_ops dmabuf_devmem_ops = {
+	.init			= mp_dmabuf_devmem_init,
+	.destroy		= mp_dmabuf_devmem_destroy,
+	.alloc_netmems		= mp_dmabuf_devmem_alloc_netmems,
+	.release_netmem		= mp_dmabuf_devmem_release_page,
+};
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index f5e908c9e7ad8..d632cf2c91c35 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -13,6 +13,7 @@
 
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/xdp.h>
 
 #include <linux/dma-direction.h>
@@ -285,13 +286,19 @@ static int page_pool_init(struct page_pool *pool,
 		rxq = __netif_get_rx_queue(pool->slow.netdev,
 					   pool->slow.queue_idx);
 		pool->mp_priv = rxq->mp_params.mp_priv;
+		pool->mp_ops = rxq->mp_params.mp_ops;
 	}
 
-	if (pool->mp_priv) {
+	if (pool->mp_ops) {
 		if (!pool->dma_map || !pool->dma_sync)
 			return -EOPNOTSUPP;
 
-		err = mp_dmabuf_devmem_init(pool);
+		if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) {
+			err = -EFAULT;
+			goto free_ptr_ring;
+		}
+
+		err = pool->mp_ops->init(pool);
 		if (err) {
 			pr_warn("%s() mem-provider init failed %d\n", __func__,
 				err);
@@ -587,8 +594,8 @@ netmem_ref page_pool_alloc_netmems(struct page_pool *pool, gfp_t gfp)
 		return netmem;
 
 	/* Slow-path: cache empty, do real allocation */
-	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
-		netmem = mp_dmabuf_devmem_alloc_netmems(pool, gfp);
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+		netmem = pool->mp_ops->alloc_netmems(pool, gfp);
 	else
 		netmem = __page_pool_alloc_pages_slow(pool, gfp);
 	return netmem;
@@ -679,8 +686,8 @@ void page_pool_return_page(struct page_pool *pool, netmem_ref netmem)
 	bool put;
 
 	put = true;
-	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_priv)
-		put = mp_dmabuf_devmem_release_page(pool, netmem);
+	if (static_branch_unlikely(&page_pool_mem_providers) && pool->mp_ops)
+		put = pool->mp_ops->release_netmem(pool, netmem);
 	else
 		__page_pool_release_page_dma(pool, netmem);
 
@@ -1048,8 +1055,8 @@ static void __page_pool_destroy(struct page_pool *pool)
 	page_pool_unlist(pool);
 	page_pool_uninit(pool);
 
-	if (pool->mp_priv) {
-		mp_dmabuf_devmem_destroy(pool);
+	if (pool->mp_ops) {
+		pool->mp_ops->destroy(pool);
 		static_branch_dec(&page_pool_mem_providers);
 	}
 

From dcc0113acd3b77cca3c7e805fffd8ea4c5a675b3 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 4 Feb 2025 13:56:16 -0800
Subject: [PATCH 0200/2753] netdev: add io_uring memory provider info

Add a nested attribute for io_uring memory provider info. For now it is
empty and its presence indicates that a particular page pool or queue
has an io_uring memory provider attached.

$ ./cli.py --spec netlink/specs/netdev.yaml --dump page-pool-get
[{'id': 80,
  'ifindex': 2,
  'inflight': 64,
  'inflight-mem': 262144,
  'napi-id': 525},
 {'id': 79,
  'ifindex': 2,
  'inflight': 320,
  'inflight-mem': 1310720,
  'io_uring': {},
  'napi-id': 525},
...

$ ./cli.py --spec netlink/specs/netdev.yaml --dump queue-get
[{'id': 0, 'ifindex': 1, 'type': 'rx'},
 {'id': 0, 'ifindex': 1, 'type': 'tx'},
 {'id': 0, 'ifindex': 2, 'napi-id': 513, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 514, 'type': 'rx'},
...
 {'id': 12, 'ifindex': 2, 'io_uring': {}, 'napi-id': 525, 'type': 'rx'},
...

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-6-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 15 +++++++++++++++
 include/uapi/linux/netdev.h             |  7 +++++++
 tools/include/uapi/linux/netdev.h       |  7 +++++++
 3 files changed, 29 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index cbb544bd6c848..288923e965aed 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -114,6 +114,9 @@ attribute-sets:
         doc: Bitmask of enabled AF_XDP features.
         type: u64
         enum: xsk-flags
+  -
+    name: io-uring-provider-info
+    attributes: []
   -
     name: page-pool
     attributes:
@@ -171,6 +174,11 @@ attribute-sets:
         name: dmabuf
         doc: ID of the dmabuf this page-pool is attached to.
         type: u32
+      -
+        name: io-uring
+        doc: io-uring memory provider information.
+        type: nest
+        nested-attributes: io-uring-provider-info
   -
     name: page-pool-info
     subset-of: page-pool
@@ -296,6 +304,11 @@ attribute-sets:
         name: dmabuf
         doc: ID of the dmabuf attached to this queue, if any.
         type: u32
+      -
+        name: io-uring
+        doc: io_uring memory provider information.
+        type: nest
+        nested-attributes: io-uring-provider-info
 
   -
     name: qstats
@@ -572,6 +585,7 @@ operations:
             - inflight-mem
             - detach-time
             - dmabuf
+            - io-uring
       dump:
         reply: *pp-reply
       config-cond: page-pool
@@ -637,6 +651,7 @@ operations:
             - napi-id
             - ifindex
             - dmabuf
+            - io-uring
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index e4be227d3ad64..6c6ee183802d3 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -86,6 +86,11 @@ enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
+	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
@@ -94,6 +99,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
 	NETDEV_A_PAGE_POOL_DMABUF,
+	NETDEV_A_PAGE_POOL_IO_URING,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -136,6 +142,7 @@ enum {
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
+	NETDEV_A_QUEUE_IO_URING,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index e4be227d3ad64..6c6ee183802d3 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -86,6 +86,11 @@ enum {
 	NETDEV_A_DEV_MAX = (__NETDEV_A_DEV_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_IO_URING_PROVIDER_INFO_MAX,
+	NETDEV_A_IO_URING_PROVIDER_INFO_MAX = (__NETDEV_A_IO_URING_PROVIDER_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_PAGE_POOL_ID = 1,
 	NETDEV_A_PAGE_POOL_IFINDEX,
@@ -94,6 +99,7 @@ enum {
 	NETDEV_A_PAGE_POOL_INFLIGHT_MEM,
 	NETDEV_A_PAGE_POOL_DETACH_TIME,
 	NETDEV_A_PAGE_POOL_DMABUF,
+	NETDEV_A_PAGE_POOL_IO_URING,
 
 	__NETDEV_A_PAGE_POOL_MAX,
 	NETDEV_A_PAGE_POOL_MAX = (__NETDEV_A_PAGE_POOL_MAX - 1)
@@ -136,6 +142,7 @@ enum {
 	NETDEV_A_QUEUE_TYPE,
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
+	NETDEV_A_QUEUE_IO_URING,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)

From 2508a46f920a3130e35ab2183a70fc93f0aaaee4 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:17 -0800
Subject: [PATCH 0201/2753] net: page_pool: add callback for mp info printing

Add a mandatory callback that prints information about the memory
provider to netlink.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-7-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/memory_provider.h |  5 +++++
 net/core/devmem.c                       | 10 ++++++++++
 net/core/netdev-genl.c                  | 11 ++++++-----
 net/core/page_pool_user.c               |  5 ++---
 4 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index e49d0a52629d7..6d10a0959d00c 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -5,11 +5,16 @@
 #include <net/netmem.h>
 #include <net/page_pool/types.h>
 
+struct netdev_rx_queue;
+struct sk_buff;
+
 struct memory_provider_ops {
 	netmem_ref (*alloc_netmems)(struct page_pool *pool, gfp_t gfp);
 	bool (*release_netmem)(struct page_pool *pool, netmem_ref netmem);
 	int (*init)(struct page_pool *pool);
 	void (*destroy)(struct page_pool *pool);
+	int (*nl_fill)(void *mp_priv, struct sk_buff *rsp,
+		       struct netdev_rx_queue *rxq);
 };
 
 #endif
diff --git a/net/core/devmem.c b/net/core/devmem.c
index c81625ca57c61..63b790326c7d4 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -406,9 +406,19 @@ bool mp_dmabuf_devmem_release_page(struct page_pool *pool, netmem_ref netmem)
 	return false;
 }
 
+static int mp_dmabuf_devmem_nl_fill(void *mp_priv, struct sk_buff *rsp,
+				    struct netdev_rx_queue *rxq)
+{
+	const struct net_devmem_dmabuf_binding *binding = mp_priv;
+	int type = rxq ? NETDEV_A_QUEUE_DMABUF : NETDEV_A_PAGE_POOL_DMABUF;
+
+	return nla_put_u32(rsp, type, binding->id);
+}
+
 static const struct memory_provider_ops dmabuf_devmem_ops = {
 	.init			= mp_dmabuf_devmem_init,
 	.destroy		= mp_dmabuf_devmem_destroy,
 	.alloc_netmems		= mp_dmabuf_devmem_alloc_netmems,
 	.release_netmem		= mp_dmabuf_devmem_release_page,
+	.nl_fill		= mp_dmabuf_devmem_nl_fill,
 };
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 715f85c6b62ea..5b459b4fef46d 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -10,6 +10,7 @@
 #include <net/sock.h>
 #include <net/xdp.h>
 #include <net/xdp_sock.h>
+#include <net/page_pool/memory_provider.h>
 
 #include "dev.h"
 #include "devmem.h"
@@ -368,7 +369,7 @@ static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
 {
-	struct net_devmem_dmabuf_binding *binding;
+	struct pp_memory_provider_params *params;
 	struct netdev_rx_queue *rxq;
 	struct netdev_queue *txq;
 	void *hdr;
@@ -385,15 +386,15 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 	switch (q_type) {
 	case NETDEV_QUEUE_TYPE_RX:
 		rxq = __netif_get_rx_queue(netdev, q_idx);
+
 		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
 					     rxq->napi->napi_id))
 			goto nla_put_failure;
 
-		binding = rxq->mp_params.mp_priv;
-		if (binding &&
-		    nla_put_u32(rsp, NETDEV_A_QUEUE_DMABUF, binding->id))
+		params = &rxq->mp_params;
+		if (params->mp_ops &&
+		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
 			goto nla_put_failure;
-
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index d5e214c30c310..9d8a3d8597fa8 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -8,9 +8,9 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/helpers.h>
 #include <net/page_pool/types.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/sock.h>
 
-#include "devmem.h"
 #include "page_pool_priv.h"
 #include "netdev-genl-gen.h"
 
@@ -216,7 +216,6 @@ static int
 page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		  const struct genl_info *info)
 {
-	struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
 	size_t inflight, refsz;
 	unsigned int napi_id;
 	void *hdr;
@@ -249,7 +248,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 			 pool->user.detach_time))
 		goto err_cancel;
 
-	if (binding && nla_put_u32(rsp, NETDEV_A_PAGE_POOL_DMABUF, binding->id))
+	if (pool->mp_ops && pool->mp_ops->nl_fill(pool->mp_priv, rsp, NULL))
 		goto err_cancel;
 
 	genlmsg_end(rsp, hdr);

From f8350a4358fc9c4801f2f4229cf9b6e678055d9a Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:18 -0800
Subject: [PATCH 0202/2753] net: page_pool: add a mp hook to
 unregister_netdevice*

Devmem TCP needs a hook in unregister_netdevice_many_notify() to upkeep
the set tracking queues it's bound to, i.e. ->bound_rxqs. Instead of
devmem sticking directly out of the genetic path, add a mp function.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-8-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/memory_provider.h |  1 +
 net/core/dev.c                          | 16 ++++++++++-
 net/core/devmem.c                       | 36 +++++++++++--------------
 net/core/devmem.h                       |  5 ----
 4 files changed, 32 insertions(+), 26 deletions(-)

diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index 6d10a0959d00c..36469a7e649f7 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -15,6 +15,7 @@ struct memory_provider_ops {
 	void (*destroy)(struct page_pool *pool);
 	int (*nl_fill)(void *mp_priv, struct sk_buff *rsp,
 		       struct netdev_rx_queue *rxq);
+	void (*uninstall)(void *mp_priv, struct netdev_rx_queue *rxq);
 };
 
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index c0021cbd28fc1..384b9109932ad 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -159,6 +159,7 @@
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/page_pool/helpers.h>
+#include <net/page_pool/memory_provider.h>
 #include <net/rps.h>
 #include <linux/phy_link_topology.h>
 
@@ -11724,6 +11725,19 @@ void unregister_netdevice_queue(struct net_device *dev, struct list_head *head)
 }
 EXPORT_SYMBOL(unregister_netdevice_queue);
 
+static void dev_memory_provider_uninstall(struct net_device *dev)
+{
+	unsigned int i;
+
+	for (i = 0; i < dev->real_num_rx_queues; i++) {
+		struct netdev_rx_queue *rxq = &dev->_rx[i];
+		struct pp_memory_provider_params *p = &rxq->mp_params;
+
+		if (p->mp_ops && p->mp_ops->uninstall)
+			p->mp_ops->uninstall(rxq->mp_params.mp_priv, rxq);
+	}
+}
+
 void unregister_netdevice_many_notify(struct list_head *head,
 				      u32 portid, const struct nlmsghdr *nlh)
 {
@@ -11778,7 +11792,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		dev_tcx_uninstall(dev);
 		dev_xdp_uninstall(dev);
 		bpf_dev_bound_netdev_unregister(dev);
-		dev_dmabuf_uninstall(dev);
+		dev_memory_provider_uninstall(dev);
 
 		netdev_offload_xstats_disable_all(dev);
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 63b790326c7d4..cbac6419fcc44 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -320,26 +320,6 @@ net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 	return ERR_PTR(err);
 }
 
-void dev_dmabuf_uninstall(struct net_device *dev)
-{
-	struct net_devmem_dmabuf_binding *binding;
-	struct netdev_rx_queue *rxq;
-	unsigned long xa_idx;
-	unsigned int i;
-
-	for (i = 0; i < dev->real_num_rx_queues; i++) {
-		binding = dev->_rx[i].mp_params.mp_priv;
-		if (!binding)
-			continue;
-
-		xa_for_each(&binding->bound_rxqs, xa_idx, rxq)
-			if (rxq == &dev->_rx[i]) {
-				xa_erase(&binding->bound_rxqs, xa_idx);
-				break;
-			}
-	}
-}
-
 /*** "Dmabuf devmem memory provider" ***/
 
 int mp_dmabuf_devmem_init(struct page_pool *pool)
@@ -415,10 +395,26 @@ static int mp_dmabuf_devmem_nl_fill(void *mp_priv, struct sk_buff *rsp,
 	return nla_put_u32(rsp, type, binding->id);
 }
 
+static void mp_dmabuf_devmem_uninstall(void *mp_priv,
+				       struct netdev_rx_queue *rxq)
+{
+	struct net_devmem_dmabuf_binding *binding = mp_priv;
+	struct netdev_rx_queue *bound_rxq;
+	unsigned long xa_idx;
+
+	xa_for_each(&binding->bound_rxqs, xa_idx, bound_rxq) {
+		if (bound_rxq == rxq) {
+			xa_erase(&binding->bound_rxqs, xa_idx);
+			break;
+		}
+	}
+}
+
 static const struct memory_provider_ops dmabuf_devmem_ops = {
 	.init			= mp_dmabuf_devmem_init,
 	.destroy		= mp_dmabuf_devmem_destroy,
 	.alloc_netmems		= mp_dmabuf_devmem_alloc_netmems,
 	.release_netmem		= mp_dmabuf_devmem_release_page,
 	.nl_fill		= mp_dmabuf_devmem_nl_fill,
+	.uninstall		= mp_dmabuf_devmem_uninstall,
 };
diff --git a/net/core/devmem.h b/net/core/devmem.h
index a2b9913e9a171..8e999fe2ae673 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -68,7 +68,6 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
 int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct net_devmem_dmabuf_binding *binding,
 				    struct netlink_ext_ack *extack);
-void dev_dmabuf_uninstall(struct net_device *dev);
 
 static inline struct dmabuf_genpool_chunk_owner *
 net_devmem_iov_to_chunk_owner(const struct net_iov *niov)
@@ -145,10 +144,6 @@ net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 	return -EOPNOTSUPP;
 }
 
-static inline void dev_dmabuf_uninstall(struct net_device *dev)
-{
-}
-
 static inline struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
 {

From 69e39537b66232103633f685b208f293bf9a15b5 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:19 -0800
Subject: [PATCH 0203/2753] net: prepare for non devmem TCP memory providers

There is a good bunch of places in generic paths assuming that the only
page pool memory provider is devmem TCP. As we want to reuse the net_iov
and provider infrastructure, we need to patch it up and explicitly check
the provider type when we branch into devmem TCP code.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-9-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/devmem.c | 5 +++++
 net/core/devmem.h | 7 +++++++
 net/ipv4/tcp.c    | 5 +++++
 3 files changed, 17 insertions(+)

diff --git a/net/core/devmem.c b/net/core/devmem.c
index cbac6419fcc44..7c6e0b5b6acb5 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -30,6 +30,11 @@ static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
 
 static const struct memory_provider_ops dmabuf_devmem_ops;
 
+bool net_is_devmem_iov(struct net_iov *niov)
+{
+	return niov->pp->mp_ops == &dmabuf_devmem_ops;
+}
+
 static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 					       struct gen_pool_chunk *chunk,
 					       void *not_used)
diff --git a/net/core/devmem.h b/net/core/devmem.h
index 8e999fe2ae673..7fc158d527293 100644
--- a/net/core/devmem.h
+++ b/net/core/devmem.h
@@ -115,6 +115,8 @@ struct net_iov *
 net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
 void net_devmem_free_dmabuf(struct net_iov *ppiov);
 
+bool net_is_devmem_iov(struct net_iov *niov);
+
 #else
 struct net_devmem_dmabuf_binding;
 
@@ -163,6 +165,11 @@ static inline u32 net_devmem_iov_binding_id(const struct net_iov *niov)
 {
 	return 0;
 }
+
+static inline bool net_is_devmem_iov(struct net_iov *niov)
+{
+	return false;
+}
 #endif
 
 #endif /* _NET_DEVMEM_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index b872de9a8271b..7f43d31c9400e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2476,6 +2476,11 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 			}
 
 			niov = skb_frag_net_iov(frag);
+			if (!net_is_devmem_iov(niov)) {
+				err = -ENODEV;
+				goto out;
+			}
+
 			end = start + skb_frag_size(frag);
 			copy = end - offset;
 

From 56102c013fa7b8dbba8c5d5f7e042ad5f18cf4ec Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 4 Feb 2025 13:56:20 -0800
Subject: [PATCH 0204/2753] net: page_pool: add memory provider helpers

Add helpers for memory providers to interact with page pools.
net_mp_niov_{set,clear}_page_pool() serve to [dis]associate a net_iov
with a page pool. If used, the memory provider is responsible to match
"set" calls with "clear" once a net_iov is not going to be used by a page
pool anymore, changing a page pool, etc.

Acked-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-10-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/memory_provider.h | 19 +++++++++++++++++
 net/core/page_pool.c                    | 28 +++++++++++++++++++++++++
 2 files changed, 47 insertions(+)

diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index 36469a7e649f7..4f0ffb8f6a0a0 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -18,4 +18,23 @@ struct memory_provider_ops {
 	void (*uninstall)(void *mp_priv, struct netdev_rx_queue *rxq);
 };
 
+bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
+void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
+void net_mp_niov_clear_page_pool(struct net_iov *niov);
+
+/**
+  * net_mp_netmem_place_in_cache() - give a netmem to a page pool
+  * @pool:      the page pool to place the netmem into
+  * @netmem:    netmem to give
+  *
+  * Push an accounted netmem into the page pool's allocation cache. The caller
+  * must ensure that there is space in the cache. It should only be called off
+  * the mp_ops->alloc_netmems() path.
+  */
+static inline void net_mp_netmem_place_in_cache(struct page_pool *pool,
+						netmem_ref netmem)
+{
+	pool->alloc.cache[pool->alloc.count++] = netmem;
+}
+
 #endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index d632cf2c91c35..686bd4a117d93 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -1197,3 +1197,31 @@ void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
+
+bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr)
+{
+	return page_pool_set_dma_addr_netmem(net_iov_to_netmem(niov), addr);
+}
+
+/* Associate a niov with a page pool. Should follow with a matching
+ * net_mp_niov_clear_page_pool()
+ */
+void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov)
+{
+	netmem_ref netmem = net_iov_to_netmem(niov);
+
+	page_pool_set_pp_info(pool, netmem);
+
+	pool->pages_state_hold_cnt++;
+	trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt);
+}
+
+/* Disassociate a niov from a page pool. Should only be used in the
+ * ->release_netmem() path.
+ */
+void net_mp_niov_clear_page_pool(struct net_iov *niov)
+{
+	netmem_ref netmem = net_iov_to_netmem(niov);
+
+	page_pool_clear_pp_info(netmem);
+}

From 6e18ed929d3ba9b3b92ba5894f9233686b3e3ec1 Mon Sep 17 00:00:00 2001
From: David Wei <dw@davidwei.uk>
Date: Tue, 4 Feb 2025 13:56:21 -0800
Subject: [PATCH 0205/2753] net: add helpers for setting a memory provider on
 an rx queue

Add helpers that properly prep or remove a memory provider for an rx
queue then restart the queue.

Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Signed-off-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250204215622.695511-11-dw@davidwei.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/page_pool/memory_provider.h |  5 ++
 net/core/netdev_rx_queue.c              | 69 +++++++++++++++++++++++++
 2 files changed, 74 insertions(+)

diff --git a/include/net/page_pool/memory_provider.h b/include/net/page_pool/memory_provider.h
index 4f0ffb8f6a0a0..b3e6658977675 100644
--- a/include/net/page_pool/memory_provider.h
+++ b/include/net/page_pool/memory_provider.h
@@ -22,6 +22,11 @@ bool net_mp_niov_set_dma_addr(struct net_iov *niov, dma_addr_t addr);
 void net_mp_niov_set_page_pool(struct page_pool *pool, struct net_iov *niov);
 void net_mp_niov_clear_page_pool(struct net_iov *niov);
 
+int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+		    struct pp_memory_provider_params *p);
+void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+		      struct pp_memory_provider_params *old_p);
+
 /**
   * net_mp_netmem_place_in_cache() - give a netmem to a page pool
   * @pool:      the page pool to place the netmem into
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index db82786fa0c40..db46880f37ccf 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -3,6 +3,7 @@
 #include <linux/netdevice.h>
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
+#include <net/page_pool/memory_provider.h>
 
 #include "page_pool_priv.h"
 
@@ -80,3 +81,71 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	return err;
 }
 EXPORT_SYMBOL_NS_GPL(netdev_rx_queue_restart, "NETDEV_INTERNAL");
+
+static int __net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+			     struct pp_memory_provider_params *p)
+{
+	struct netdev_rx_queue *rxq;
+	int ret;
+
+	if (ifq_idx >= dev->real_num_rx_queues)
+		return -EINVAL;
+	ifq_idx = array_index_nospec(ifq_idx, dev->real_num_rx_queues);
+
+	rxq = __netif_get_rx_queue(dev, ifq_idx);
+	if (rxq->mp_params.mp_ops)
+		return -EEXIST;
+
+	rxq->mp_params = *p;
+	ret = netdev_rx_queue_restart(dev, ifq_idx);
+	if (ret) {
+		rxq->mp_params.mp_ops = NULL;
+		rxq->mp_params.mp_priv = NULL;
+	}
+	return ret;
+}
+
+int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
+		    struct pp_memory_provider_params *p)
+{
+	int ret;
+
+	rtnl_lock();
+	ret = __net_mp_open_rxq(dev, ifq_idx, p);
+	rtnl_unlock();
+	return ret;
+}
+
+static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+			      struct pp_memory_provider_params *old_p)
+{
+	struct netdev_rx_queue *rxq;
+
+	if (WARN_ON_ONCE(ifq_idx >= dev->real_num_rx_queues))
+		return;
+
+	rxq = __netif_get_rx_queue(dev, ifq_idx);
+
+	/* Callers holding a netdev ref may get here after we already
+	 * went thru shutdown via dev_memory_provider_uninstall().
+	 */
+	if (dev->reg_state > NETREG_REGISTERED &&
+	    !rxq->mp_params.mp_ops)
+		return;
+
+	if (WARN_ON_ONCE(rxq->mp_params.mp_ops != old_p->mp_ops ||
+			 rxq->mp_params.mp_priv != old_p->mp_priv))
+		return;
+
+	rxq->mp_params.mp_ops = NULL;
+	rxq->mp_params.mp_priv = NULL;
+	WARN_ON(netdev_rx_queue_restart(dev, ifq_idx));
+}
+
+void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
+		      struct pp_memory_provider_params *old_p)
+{
+	rtnl_lock();
+	__net_mp_close_rxq(dev, ifq_idx, old_p);
+	rtnl_unlock();
+}

From 6597e8d35851e1e0cb381f76ce1d960518fd8c94 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Wed, 5 Feb 2025 19:37:47 +0000
Subject: [PATCH 0206/2753] netdev-genl: Elide napi_id when not present

There are at least two cases where napi_id may not present and the
napi_id should be elided:

1. Queues could be created, but napi_enable may not have been called
   yet. In this case, there may be a NAPI but it may not have an ID and
   output of a napi_id should be elided.

2. TX-only NAPIs currently do not have NAPI IDs. If a TX queue happens
   to be linked with a TX-only NAPI, elide the NAPI ID from the netlink
   output as a NAPI ID of 0 is not useful for users.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Sridhar Samudrala <sridhar.samudrala@intel.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250205193751.297211-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/busy_poll.h |  5 +++++
 net/core/netdev-genl.c  | 14 +++++++++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index c39a426ebf520..741fa77547001 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -24,6 +24,11 @@
  */
 #define MIN_NAPI_ID ((unsigned int)(NR_CPUS + 1))
 
+static inline bool napi_id_valid(unsigned int napi_id)
+{
+	return napi_id >= MIN_NAPI_ID;
+}
+
 #define BUSY_POLL_BUDGET 8
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5b459b4fef46d..0dcd4faefd8d4 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -365,6 +365,13 @@ int netdev_nl_napi_set_doit(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
+static int nla_put_napi_id(struct sk_buff *skb, const struct napi_struct *napi)
+{
+	if (napi && napi_id_valid(napi->napi_id))
+		return nla_put_u32(skb, NETDEV_A_QUEUE_NAPI_ID, napi->napi_id);
+	return 0;
+}
+
 static int
 netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 			 u32 q_idx, u32 q_type, const struct genl_info *info)
@@ -386,9 +393,7 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 	switch (q_type) {
 	case NETDEV_QUEUE_TYPE_RX:
 		rxq = __netif_get_rx_queue(netdev, q_idx);
-
-		if (rxq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
-					     rxq->napi->napi_id))
+		if (nla_put_napi_id(rsp, rxq->napi))
 			goto nla_put_failure;
 
 		params = &rxq->mp_params;
@@ -398,8 +403,7 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
-		if (txq->napi && nla_put_u32(rsp, NETDEV_A_QUEUE_NAPI_ID,
-					     txq->napi->napi_id))
+		if (nla_put_napi_id(rsp, txq->napi))
 			goto nla_put_failure;
 	}
 

From fe57762c6490581ae446956ab54d221262a4951b Mon Sep 17 00:00:00 2001
From: John Daley <johndale@cisco.com>
Date: Wed, 5 Feb 2025 15:54:13 -0800
Subject: [PATCH 0207/2753] enic: Move RX functions to their own file

Move RX handler code into its own file in preparation for further
changes. Some formatting changes were necessary in order to satisfy
checkpatch but there were no functional changes.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Link: https://patch.msgid.link/20250205235416.25410-2-johndale@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/Makefile    |   2 +-
 drivers/net/ethernet/cisco/enic/enic_main.c | 238 +------------------
 drivers/net/ethernet/cisco/enic/enic_rq.c   | 242 ++++++++++++++++++++
 drivers/net/ethernet/cisco/enic/enic_rq.h   |  10 +
 4 files changed, 254 insertions(+), 238 deletions(-)
 create mode 100644 drivers/net/ethernet/cisco/enic/enic_rq.c
 create mode 100644 drivers/net/ethernet/cisco/enic/enic_rq.h

diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile
index c3b6febfdbe44..b3b5196b2dfcc 100644
--- a/drivers/net/ethernet/cisco/enic/Makefile
+++ b/drivers/net/ethernet/cisco/enic/Makefile
@@ -3,5 +3,5 @@ obj-$(CONFIG_ENIC) := enic.o
 
 enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \
 	enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \
-	enic_ethtool.o enic_api.o enic_clsf.o
+	enic_ethtool.o enic_api.o enic_clsf.o enic_rq.o
 
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 49f6cab01ed51..1d9f109346b8c 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -58,6 +58,7 @@
 #include "enic_dev.h"
 #include "enic_pp.h"
 #include "enic_clsf.h"
+#include "enic_rq.h"
 
 #define ENIC_NOTIFY_TIMER_PERIOD	(2 * HZ)
 #define WQ_ENET_MAX_DESC_LEN		(1 << WQ_ENET_LEN_BITS)
@@ -1313,243 +1314,6 @@ static int enic_get_vf_port(struct net_device *netdev, int vf,
 	return -EMSGSIZE;
 }
 
-static void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-
-	if (!buf->os_buf)
-		return;
-
-	dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-			 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(buf->os_buf);
-	buf->os_buf = NULL;
-}
-
-static int enic_rq_alloc_buf(struct vnic_rq *rq)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
-	unsigned int os_buf_index = 0;
-	dma_addr_t dma_addr;
-	struct vnic_rq_buf *buf = rq->to_use;
-
-	if (buf->os_buf) {
-		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
-				   buf->len);
-
-		return 0;
-	}
-	skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!skb) {
-		enic->rq[rq->index].stats.no_skb++;
-		return -ENOMEM;
-	}
-
-	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
-				  DMA_FROM_DEVICE);
-	if (unlikely(enic_dma_map_check(enic, dma_addr))) {
-		dev_kfree_skb(skb);
-		return -ENOMEM;
-	}
-
-	enic_queue_rq_desc(rq, skb, os_buf_index,
-		dma_addr, len);
-
-	return 0;
-}
-
-static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
-				      u32 pkt_len)
-{
-	if (ENIC_LARGE_PKT_THRESHOLD <= pkt_len)
-		pkt_size->large_pkt_bytes_cnt += pkt_len;
-	else
-		pkt_size->small_pkt_bytes_cnt += pkt_len;
-}
-
-static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
-			     struct vnic_rq_buf *buf, u16 len)
-{
-	struct enic *enic = netdev_priv(netdev);
-	struct sk_buff *new_skb;
-
-	if (len > enic->rx_copybreak)
-		return false;
-	new_skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!new_skb)
-		return false;
-	dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len,
-				DMA_FROM_DEVICE);
-	memcpy(new_skb->data, (*skb)->data, len);
-	*skb = new_skb;
-
-	return true;
-}
-
-static void enic_rq_indicate_buf(struct vnic_rq *rq,
-	struct cq_desc *cq_desc, struct vnic_rq_buf *buf,
-	int skipped, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
-	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
-	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
-
-	u8 type, color, eop, sop, ingress_port, vlan_stripped;
-	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
-	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
-	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
-	u8 packet_error;
-	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
-	u32 rss_hash;
-	bool outer_csum_ok = true, encap = false;
-
-	rqstats->packets++;
-	if (skipped) {
-		rqstats->desc_skip++;
-		return;
-	}
-
-	skb = buf->os_buf;
-
-	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc,
-		&type, &color, &q_number, &completed_index,
-		&ingress_port, &fcoe, &eop, &sop, &rss_type,
-		&csum_not_calc, &rss_hash, &bytes_written,
-		&packet_error, &vlan_stripped, &vlan_tci, &checksum,
-		&fcoe_sof, &fcoe_fc_crc_ok, &fcoe_enc_error,
-		&fcoe_eof, &tcp_udp_csum_ok, &udp, &tcp,
-		&ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
-		&fcs_ok);
-
-	if (packet_error) {
-
-		if (!fcs_ok) {
-			if (bytes_written > 0)
-				rqstats->bad_fcs++;
-			else if (bytes_written == 0)
-				rqstats->pkt_truncated++;
-		}
-
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-
-		return;
-	}
-
-	if (eop && bytes_written > 0) {
-
-		/* Good receive
-		 */
-		rqstats->bytes += bytes_written;
-		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
-			buf->os_buf = NULL;
-			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
-					 buf->len, DMA_FROM_DEVICE);
-		}
-		prefetch(skb->data - NET_IP_ALIGN);
-
-		skb_put(skb, bytes_written);
-		skb->protocol = eth_type_trans(skb, netdev);
-		skb_record_rx_queue(skb, q_number);
-		if ((netdev->features & NETIF_F_RXHASH) && rss_hash &&
-		    (type == 3)) {
-			switch (rss_type) {
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
-				rqstats->l4_rss_hash++;
-				break;
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
-				rqstats->l3_rss_hash++;
-				break;
-			}
-		}
-		if (enic->vxlan.vxlan_udp_port_number) {
-			switch (enic->vxlan.patch_level) {
-			case 0:
-				if (fcoe) {
-					encap = true;
-					outer_csum_ok = fcoe_fc_crc_ok;
-				}
-				break;
-			case 2:
-				if ((type == 7) &&
-				    (rss_hash & BIT(0))) {
-					encap = true;
-					outer_csum_ok = (rss_hash & BIT(1)) &&
-							(rss_hash & BIT(2));
-				}
-				break;
-			}
-		}
-
-		/* Hardware does not provide whole packet checksum. It only
-		 * provides pseudo checksum. Since hw validates the packet
-		 * checksum but not provide us the checksum value. use
-		 * CHECSUM_UNNECESSARY.
-		 *
-		 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
-		 * inner csum_ok. outer_csum_ok is set by hw when outer udp
-		 * csum is correct or is zero.
-		 */
-		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && outer_csum_ok &&
-		    (ipv4_csum_ok || ipv6)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = encap;
-			if (encap)
-				rqstats->csum_unnecessary_encap++;
-			else
-				rqstats->csum_unnecessary++;
-		}
-
-		if (vlan_stripped) {
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
-			rqstats->vlan_stripped++;
-		}
-		skb_mark_napi_id(skb, &enic->napi[rq->index]);
-		if (!(netdev->features & NETIF_F_GRO))
-			netif_receive_skb(skb);
-		else
-			napi_gro_receive(&enic->napi[q_number], skb);
-		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
-			enic_intr_update_pkt_size(&cq->pkt_size_counter,
-						  bytes_written);
-	} else {
-
-		/* Buffer overflow
-		 */
-		rqstats->pkt_truncated++;
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-	}
-}
-
-static int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	vnic_rq_service(&enic->rq[q_number].vrq, cq_desc,
-		completed_index, VNIC_RQ_RETURN_DESC,
-		enic_rq_indicate_buf, opaque);
-
-	return 0;
-}
-
 static void enic_set_int_moderation(struct enic *enic, struct vnic_rq *rq)
 {
 	unsigned int intr = enic_msix_rq_intr(enic, rq->index);
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
new file mode 100644
index 0000000000000..e5b2f581c0555
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -0,0 +1,242 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+
+#include <linux/skbuff.h>
+#include <linux/if_vlan.h>
+#include <net/busy_poll.h>
+#include "enic.h"
+#include "enic_res.h"
+#include "enic_rq.h"
+#include "vnic_rq.h"
+#include "cq_enet_desc.h"
+
+#define ENIC_LARGE_PKT_THRESHOLD                1000
+
+static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
+				      u32 pkt_len)
+{
+	if (pkt_len > ENIC_LARGE_PKT_THRESHOLD)
+		pkt_size->large_pkt_bytes_cnt += pkt_len;
+	else
+		pkt_size->small_pkt_bytes_cnt += pkt_len;
+}
+
+static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
+			     struct vnic_rq_buf *buf, u16 len)
+{
+	struct enic *enic = netdev_priv(netdev);
+	struct sk_buff *new_skb;
+
+	if (len > enic->rx_copybreak)
+		return false;
+	new_skb = netdev_alloc_skb_ip_align(netdev, len);
+	if (!new_skb)
+		return false;
+	dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len,
+				DMA_FROM_DEVICE);
+	memcpy(new_skb->data, (*skb)->data, len);
+	*skb = new_skb;
+
+	return true;
+}
+
+int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
+		    u16 q_number, u16 completed_index, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(vdev);
+
+	vnic_rq_service(&enic->rq[q_number].vrq, cq_desc, completed_index,
+			VNIC_RQ_RETURN_DESC, enic_rq_indicate_buf, opaque);
+	return 0;
+}
+
+int enic_rq_alloc_buf(struct vnic_rq *rq)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct sk_buff *skb;
+	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
+	unsigned int os_buf_index = 0;
+	dma_addr_t dma_addr;
+	struct vnic_rq_buf *buf = rq->to_use;
+
+	if (buf->os_buf) {
+		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
+				   buf->len);
+
+		return 0;
+	}
+	skb = netdev_alloc_skb_ip_align(netdev, len);
+	if (!skb) {
+		enic->rq[rq->index].stats.no_skb++;
+		return -ENOMEM;
+	}
+
+	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
+				  DMA_FROM_DEVICE);
+	if (unlikely(enic_dma_map_check(enic, dma_addr))) {
+		dev_kfree_skb(skb);
+		return -ENOMEM;
+	}
+
+	enic_queue_rq_desc(rq, skb, os_buf_index, dma_addr, len);
+
+	return 0;
+}
+
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+
+	if (!buf->os_buf)
+		return;
+
+	dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+			 DMA_FROM_DEVICE);
+	dev_kfree_skb_any(buf->os_buf);
+	buf->os_buf = NULL;
+}
+
+void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
+			  struct vnic_rq_buf *buf, int skipped, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct sk_buff *skb;
+	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
+	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
+
+	u8 type, color, eop, sop, ingress_port, vlan_stripped;
+	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
+	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
+	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
+	u8 packet_error;
+	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
+	u32 rss_hash;
+	bool outer_csum_ok = true, encap = false;
+
+	rqstats->packets++;
+	if (skipped) {
+		rqstats->desc_skip++;
+		return;
+	}
+
+	skb = buf->os_buf;
+
+	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &type, &color,
+			    &q_number, &completed_index, &ingress_port, &fcoe,
+			    &eop, &sop, &rss_type, &csum_not_calc, &rss_hash,
+			    &bytes_written, &packet_error, &vlan_stripped,
+			    &vlan_tci, &checksum, &fcoe_sof, &fcoe_fc_crc_ok,
+			    &fcoe_enc_error, &fcoe_eof, &tcp_udp_csum_ok, &udp,
+			    &tcp, &ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
+			    &fcs_ok);
+
+	if (packet_error) {
+		if (!fcs_ok) {
+			if (bytes_written > 0)
+				rqstats->bad_fcs++;
+			else if (bytes_written == 0)
+				rqstats->pkt_truncated++;
+		}
+
+		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+		buf->os_buf = NULL;
+
+		return;
+	}
+
+	if (eop && bytes_written > 0) {
+		/* Good receive
+		 */
+		rqstats->bytes += bytes_written;
+		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
+			buf->os_buf = NULL;
+			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
+					 buf->len, DMA_FROM_DEVICE);
+		}
+		prefetch(skb->data - NET_IP_ALIGN);
+
+		skb_put(skb, bytes_written);
+		skb->protocol = eth_type_trans(skb, netdev);
+		skb_record_rx_queue(skb, q_number);
+		if ((netdev->features & NETIF_F_RXHASH) && rss_hash &&
+		    type == 3) {
+			switch (rss_type) {
+			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
+			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
+			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
+				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+				rqstats->l4_rss_hash++;
+				break;
+			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
+			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
+			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
+				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+				rqstats->l3_rss_hash++;
+				break;
+			}
+		}
+		if (enic->vxlan.vxlan_udp_port_number) {
+			switch (enic->vxlan.patch_level) {
+			case 0:
+				if (fcoe) {
+					encap = true;
+					outer_csum_ok = fcoe_fc_crc_ok;
+				}
+				break;
+			case 2:
+				if (type == 7 &&
+				    (rss_hash & BIT(0))) {
+					encap = true;
+					outer_csum_ok = (rss_hash & BIT(1)) &&
+							(rss_hash & BIT(2));
+				}
+				break;
+			}
+		}
+
+		/* Hardware does not provide whole packet checksum. It only
+		 * provides pseudo checksum. Since hw validates the packet
+		 * checksum but not provide us the checksum value. use
+		 * CHECSUM_UNNECESSARY.
+		 *
+		 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
+		 * inner csum_ok. outer_csum_ok is set by hw when outer udp
+		 * csum is correct or is zero.
+		 */
+		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
+		    tcp_udp_csum_ok && outer_csum_ok &&
+		    (ipv4_csum_ok || ipv6)) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb->csum_level = encap;
+			if (encap)
+				rqstats->csum_unnecessary_encap++;
+			else
+				rqstats->csum_unnecessary++;
+		}
+
+		if (vlan_stripped) {
+			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+			rqstats->vlan_stripped++;
+		}
+		skb_mark_napi_id(skb, &enic->napi[rq->index]);
+		if (!(netdev->features & NETIF_F_GRO))
+			netif_receive_skb(skb);
+		else
+			napi_gro_receive(&enic->napi[q_number], skb);
+		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
+			enic_intr_update_pkt_size(&cq->pkt_size_counter,
+						  bytes_written);
+	} else {
+		/* Buffer overflow
+		 */
+		rqstats->pkt_truncated++;
+		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+				 DMA_FROM_DEVICE);
+		dev_kfree_skb_any(skb);
+		buf->os_buf = NULL;
+	}
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.h b/drivers/net/ethernet/cisco/enic/enic_rq.h
new file mode 100644
index 0000000000000..a75d07562686a
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2024 Cisco Systems, Inc.  All rights reserved.
+ */
+
+int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
+		    u16 q_number, u16 completed_index, void *opaque);
+void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
+			  struct vnic_rq_buf *buf, int skipped, void *opaque);
+int enic_rq_alloc_buf(struct vnic_rq *rq);
+void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);

From eab3726347f8e38162ee2a0bef0f24fad11f4b61 Mon Sep 17 00:00:00 2001
From: John Daley <johndale@cisco.com>
Date: Wed, 5 Feb 2025 15:54:14 -0800
Subject: [PATCH 0208/2753] enic: Simplify RX handler function

Split up RX handler functions in preparation for moving
to a page pool based implementation.

No functional changes.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Link: https://patch.msgid.link/20250205235416.25410-3-johndale@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic_rq.c | 162 +++++++++++++---------
 1 file changed, 93 insertions(+), 69 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
index e5b2f581c0555..48aa385aa8313 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -50,6 +50,94 @@ int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
 	return 0;
 }
 
+static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
+				  u8 rss_type, u8 fcoe, u8 fcoe_fc_crc_ok,
+				  u8 vlan_stripped, u8 csum_not_calc,
+				  u8 tcp_udp_csum_ok, u8 ipv6, u8 ipv4_csum_ok,
+				  u16 vlan_tci, struct sk_buff *skb)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct net_device *netdev = enic->netdev;
+	struct enic_rq_stats *rqstats =  &enic->rq[vrq->index].stats;
+	bool outer_csum_ok = true, encap = false;
+
+	if ((netdev->features & NETIF_F_RXHASH) && rss_hash && type == 3) {
+		switch (rss_type) {
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
+			rqstats->l4_rss_hash++;
+			break;
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
+		case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
+			skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
+			rqstats->l3_rss_hash++;
+			break;
+		}
+	}
+	if (enic->vxlan.vxlan_udp_port_number) {
+		switch (enic->vxlan.patch_level) {
+		case 0:
+			if (fcoe) {
+				encap = true;
+				outer_csum_ok = fcoe_fc_crc_ok;
+			}
+			break;
+		case 2:
+			if (type == 7 && (rss_hash & BIT(0))) {
+				encap = true;
+				outer_csum_ok = (rss_hash & BIT(1)) &&
+						(rss_hash & BIT(2));
+			}
+			break;
+		}
+	}
+
+	/* Hardware does not provide whole packet checksum. It only
+	 * provides pseudo checksum. Since hw validates the packet
+	 * checksum but not provide us the checksum value. use
+	 * CHECSUM_UNNECESSARY.
+	 *
+	 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
+	 * inner csum_ok. outer_csum_ok is set by hw when outer udp
+	 * csum is correct or is zero.
+	 */
+	if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
+	    tcp_udp_csum_ok && outer_csum_ok && (ipv4_csum_ok || ipv6)) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = encap;
+		if (encap)
+			rqstats->csum_unnecessary_encap++;
+		else
+			rqstats->csum_unnecessary++;
+	}
+
+	if (vlan_stripped) {
+		__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
+		rqstats->vlan_stripped++;
+	}
+}
+
+static bool enic_rq_pkt_error(struct vnic_rq *vrq, u8 packet_error, u8 fcs_ok,
+			      u16 bytes_written)
+{
+	struct enic *enic = vnic_dev_priv(vrq->vdev);
+	struct enic_rq_stats *rqstats = &enic->rq[vrq->index].stats;
+
+	if (packet_error) {
+		if (!fcs_ok) {
+			if (bytes_written > 0)
+				rqstats->bad_fcs++;
+			else if (bytes_written == 0)
+				rqstats->pkt_truncated++;
+		}
+		return true;
+	}
+	return false;
+}
+
 int enic_rq_alloc_buf(struct vnic_rq *rq)
 {
 	struct enic *enic = vnic_dev_priv(rq->vdev);
@@ -113,7 +201,6 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 	u8 packet_error;
 	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
 	u32 rss_hash;
-	bool outer_csum_ok = true, encap = false;
 
 	rqstats->packets++;
 	if (skipped) {
@@ -132,14 +219,7 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 			    &tcp, &ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
 			    &fcs_ok);
 
-	if (packet_error) {
-		if (!fcs_ok) {
-			if (bytes_written > 0)
-				rqstats->bad_fcs++;
-			else if (bytes_written == 0)
-				rqstats->pkt_truncated++;
-		}
-
+	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written)) {
 		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
 				 DMA_FROM_DEVICE);
 		dev_kfree_skb_any(skb);
@@ -162,66 +242,10 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 		skb_put(skb, bytes_written);
 		skb->protocol = eth_type_trans(skb, netdev);
 		skb_record_rx_queue(skb, q_number);
-		if ((netdev->features & NETIF_F_RXHASH) && rss_hash &&
-		    type == 3) {
-			switch (rss_type) {
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_TCP_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L4);
-				rqstats->l4_rss_hash++;
-				break;
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv4:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6:
-			case CQ_ENET_RQ_DESC_RSS_TYPE_IPv6_EX:
-				skb_set_hash(skb, rss_hash, PKT_HASH_TYPE_L3);
-				rqstats->l3_rss_hash++;
-				break;
-			}
-		}
-		if (enic->vxlan.vxlan_udp_port_number) {
-			switch (enic->vxlan.patch_level) {
-			case 0:
-				if (fcoe) {
-					encap = true;
-					outer_csum_ok = fcoe_fc_crc_ok;
-				}
-				break;
-			case 2:
-				if (type == 7 &&
-				    (rss_hash & BIT(0))) {
-					encap = true;
-					outer_csum_ok = (rss_hash & BIT(1)) &&
-							(rss_hash & BIT(2));
-				}
-				break;
-			}
-		}
-
-		/* Hardware does not provide whole packet checksum. It only
-		 * provides pseudo checksum. Since hw validates the packet
-		 * checksum but not provide us the checksum value. use
-		 * CHECSUM_UNNECESSARY.
-		 *
-		 * In case of encap pkt tcp_udp_csum_ok/tcp_udp_csum_ok is
-		 * inner csum_ok. outer_csum_ok is set by hw when outer udp
-		 * csum is correct or is zero.
-		 */
-		if ((netdev->features & NETIF_F_RXCSUM) && !csum_not_calc &&
-		    tcp_udp_csum_ok && outer_csum_ok &&
-		    (ipv4_csum_ok || ipv6)) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = encap;
-			if (encap)
-				rqstats->csum_unnecessary_encap++;
-			else
-				rqstats->csum_unnecessary++;
-		}
-
-		if (vlan_stripped) {
-			__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_tci);
-			rqstats->vlan_stripped++;
-		}
+		enic_rq_set_skb_flags(rq, type, rss_hash, rss_type, fcoe,
+				      fcoe_fc_crc_ok, vlan_stripped,
+				      csum_not_calc, tcp_udp_csum_ok, ipv6,
+				      ipv4_csum_ok, vlan_tci, skb);
 		skb_mark_napi_id(skb, &enic->napi[rq->index]);
 		if (!(netdev->features & NETIF_F_GRO))
 			netif_receive_skb(skb);

From d24cb52b2d8abc89739694ac0be7f0bc2da58e37 Mon Sep 17 00:00:00 2001
From: John Daley <johndale@cisco.com>
Date: Wed, 5 Feb 2025 15:54:15 -0800
Subject: [PATCH 0209/2753] enic: Use the Page Pool API for RX

The Page Pool API improves bandwidth and CPU overhead by recycling pages
instead of allocating new buffers in the driver. Make use of page pool
fragment allocation for smaller MTUs so that multiple packets can share
a page. For MTUs larger than PAGE_SIZE, adjust the 'order' page
parameter so that contiguous pages can be used to receive the larger
packets.

The RQ descriptor field 'os_buf' is repurposed to hold page pointers
allocated from page_pool instead of SKBs. When packets arrive, SKBs are
allocated and the page pointers are attached instead of preallocating SKBs.

'alloc_fail' netdev statistic is incremented when page_pool_dev_alloc()
fails.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Link: https://patch.msgid.link/20250205235416.25410-4-johndale@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic.h      |  3 +
 drivers/net/ethernet/cisco/enic/enic_main.c | 33 +++++++-
 drivers/net/ethernet/cisco/enic/enic_rq.c   | 94 ++++++++-------------
 drivers/net/ethernet/cisco/enic/vnic_rq.h   |  2 +
 4 files changed, 71 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 10b7e02ba4d0e..2ccf2d2a77dbb 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -17,6 +17,7 @@
 #include "vnic_nic.h"
 #include "vnic_rss.h"
 #include <linux/irq.h>
+#include <net/page_pool/helpers.h>
 
 #define DRV_NAME		"enic"
 #define DRV_DESCRIPTION		"Cisco VIC Ethernet NIC Driver"
@@ -158,6 +159,7 @@ struct enic_rq_stats {
 	u64 pkt_truncated;		/* truncated pkts */
 	u64 no_skb;			/* out of skbs */
 	u64 desc_skip;			/* Rx pkt went into later buffer */
+	u64 pp_alloc_fail;		/* page pool alloc failure */
 };
 
 struct enic_wq {
@@ -169,6 +171,7 @@ struct enic_wq {
 struct enic_rq {
 	struct vnic_rq vrq;
 	struct enic_rq_stats stats;
+	struct page_pool *pool;
 } ____cacheline_aligned;
 
 /* Per-instance private data structure */
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 1d9f109346b8c..447c54dcd89b5 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1736,6 +1736,17 @@ static int enic_open(struct net_device *netdev)
 	struct enic *enic = netdev_priv(netdev);
 	unsigned int i;
 	int err, ret;
+	unsigned int max_pkt_len = netdev->mtu + VLAN_ETH_HLEN;
+	struct page_pool_params pp_params = {
+		.order = get_order(max_pkt_len),
+		.pool_size = enic->config.rq_desc_count,
+		.nid = dev_to_node(&enic->pdev->dev),
+		.dev = &enic->pdev->dev,
+		.dma_dir = DMA_FROM_DEVICE,
+		.max_len = (max_pkt_len > PAGE_SIZE) ? max_pkt_len : PAGE_SIZE,
+		.netdev = netdev,
+		.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+	};
 
 	err = enic_request_intr(enic);
 	if (err) {
@@ -1753,6 +1764,16 @@ static int enic_open(struct net_device *netdev)
 	}
 
 	for (i = 0; i < enic->rq_count; i++) {
+		/* create a page pool for each RQ */
+		pp_params.napi = &enic->napi[i];
+		pp_params.queue_idx = i;
+		enic->rq[i].pool = page_pool_create(&pp_params);
+		if (IS_ERR(enic->rq[i].pool)) {
+			err = PTR_ERR(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+			goto err_out_free_rq;
+		}
+
 		/* enable rq before updating rq desc */
 		vnic_rq_enable(&enic->rq[i].vrq);
 		vnic_rq_fill(&enic->rq[i].vrq, enic_rq_alloc_buf);
@@ -1793,8 +1814,11 @@ static int enic_open(struct net_device *netdev)
 err_out_free_rq:
 	for (i = 0; i < enic->rq_count; i++) {
 		ret = vnic_rq_disable(&enic->rq[i].vrq);
-		if (!ret)
+		if (!ret) {
 			vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+			page_pool_destroy(enic->rq[i].pool);
+			enic->rq[i].pool = NULL;
+		}
 	}
 	enic_dev_notify_unset(enic);
 err_out_free_intr:
@@ -1852,8 +1876,11 @@ static int enic_stop(struct net_device *netdev)
 
 	for (i = 0; i < enic->wq_count; i++)
 		vnic_wq_clean(&enic->wq[i].vwq, enic_free_wq_buf);
-	for (i = 0; i < enic->rq_count; i++)
+	for (i = 0; i < enic->rq_count; i++) {
 		vnic_rq_clean(&enic->rq[i].vrq, enic_free_rq_buf);
+		page_pool_destroy(enic->rq[i].pool);
+		enic->rq[i].pool = NULL;
+	}
 	for (i = 0; i < enic->cq_count; i++)
 		vnic_cq_clean(&enic->cq[i]);
 	for (i = 0; i < enic->intr_count; i++)
@@ -2363,6 +2390,7 @@ static void enic_get_queue_stats_rx(struct net_device *dev, int idx,
 	rxs->hw_drop_overruns = rqstats->pkt_truncated;
 	rxs->csum_unnecessary = rqstats->csum_unnecessary +
 				rqstats->csum_unnecessary_encap;
+	rxs->alloc_fail = rqstats->pp_alloc_fail;
 }
 
 static void enic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -2390,6 +2418,7 @@ static void enic_get_base_stats(struct net_device *dev,
 	rxs->hw_drops = 0;
 	rxs->hw_drop_overruns = 0;
 	rxs->csum_unnecessary = 0;
+	rxs->alloc_fail = 0;
 	txs->bytes = 0;
 	txs->packets = 0;
 	txs->csum_none = 0;
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
index 48aa385aa8313..e3228ef7988a1 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -21,25 +21,6 @@ static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
 		pkt_size->small_pkt_bytes_cnt += pkt_len;
 }
 
-static bool enic_rxcopybreak(struct net_device *netdev, struct sk_buff **skb,
-			     struct vnic_rq_buf *buf, u16 len)
-{
-	struct enic *enic = netdev_priv(netdev);
-	struct sk_buff *new_skb;
-
-	if (len > enic->rx_copybreak)
-		return false;
-	new_skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!new_skb)
-		return false;
-	dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr, len,
-				DMA_FROM_DEVICE);
-	memcpy(new_skb->data, (*skb)->data, len);
-	*skb = new_skb;
-
-	return true;
-}
-
 int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
 		    u16 q_number, u16 completed_index, void *opaque)
 {
@@ -142,11 +123,15 @@ int enic_rq_alloc_buf(struct vnic_rq *rq)
 {
 	struct enic *enic = vnic_dev_priv(rq->vdev);
 	struct net_device *netdev = enic->netdev;
-	struct sk_buff *skb;
+	struct enic_rq *erq = &enic->rq[rq->index];
+	struct enic_rq_stats *rqstats = &erq->stats;
+	unsigned int offset = 0;
 	unsigned int len = netdev->mtu + VLAN_ETH_HLEN;
 	unsigned int os_buf_index = 0;
 	dma_addr_t dma_addr;
 	struct vnic_rq_buf *buf = rq->to_use;
+	struct page *page;
+	unsigned int truesize = len;
 
 	if (buf->os_buf) {
 		enic_queue_rq_desc(rq, buf->os_buf, os_buf_index, buf->dma_addr,
@@ -154,20 +139,16 @@ int enic_rq_alloc_buf(struct vnic_rq *rq)
 
 		return 0;
 	}
-	skb = netdev_alloc_skb_ip_align(netdev, len);
-	if (!skb) {
-		enic->rq[rq->index].stats.no_skb++;
-		return -ENOMEM;
-	}
 
-	dma_addr = dma_map_single(&enic->pdev->dev, skb->data, len,
-				  DMA_FROM_DEVICE);
-	if (unlikely(enic_dma_map_check(enic, dma_addr))) {
-		dev_kfree_skb(skb);
+	page = page_pool_dev_alloc(erq->pool, &offset, &truesize);
+	if (unlikely(!page)) {
+		rqstats->pp_alloc_fail++;
 		return -ENOMEM;
 	}
-
-	enic_queue_rq_desc(rq, skb, os_buf_index, dma_addr, len);
+	buf->offset = offset;
+	buf->truesize = truesize;
+	dma_addr = page_pool_get_dma_addr(page) + offset;
+	enic_queue_rq_desc(rq, (void *)page, os_buf_index, dma_addr, len);
 
 	return 0;
 }
@@ -175,13 +156,12 @@ int enic_rq_alloc_buf(struct vnic_rq *rq)
 void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
 {
 	struct enic *enic = vnic_dev_priv(rq->vdev);
+	struct enic_rq *erq = &enic->rq[rq->index];
 
 	if (!buf->os_buf)
 		return;
 
-	dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-			 DMA_FROM_DEVICE);
-	dev_kfree_skb_any(buf->os_buf);
+	page_pool_put_full_page(erq->pool, (struct page *)buf->os_buf, true);
 	buf->os_buf = NULL;
 }
 
@@ -189,10 +169,10 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 			  struct vnic_rq_buf *buf, int skipped, void *opaque)
 {
 	struct enic *enic = vnic_dev_priv(rq->vdev);
-	struct net_device *netdev = enic->netdev;
 	struct sk_buff *skb;
 	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
 	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
+	struct napi_struct *napi;
 
 	u8 type, color, eop, sop, ingress_port, vlan_stripped;
 	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
@@ -208,8 +188,6 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 		return;
 	}
 
-	skb = buf->os_buf;
-
 	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &type, &color,
 			    &q_number, &completed_index, &ingress_port, &fcoe,
 			    &eop, &sop, &rss_type, &csum_not_calc, &rss_hash,
@@ -219,48 +197,46 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 			    &tcp, &ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
 			    &fcs_ok);
 
-	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written)) {
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
-
+	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written))
 		return;
-	}
 
 	if (eop && bytes_written > 0) {
 		/* Good receive
 		 */
 		rqstats->bytes += bytes_written;
-		if (!enic_rxcopybreak(netdev, &skb, buf, bytes_written)) {
-			buf->os_buf = NULL;
-			dma_unmap_single(&enic->pdev->dev, buf->dma_addr,
-					 buf->len, DMA_FROM_DEVICE);
+		napi = &enic->napi[rq->index];
+		skb = napi_get_frags(napi);
+		if (unlikely(!skb)) {
+			net_warn_ratelimited("%s: skb alloc error rq[%d], desc[%d]\n",
+					     enic->netdev->name, rq->index,
+					     completed_index);
+			rqstats->no_skb++;
+			return;
 		}
+
 		prefetch(skb->data - NET_IP_ALIGN);
 
-		skb_put(skb, bytes_written);
-		skb->protocol = eth_type_trans(skb, netdev);
+		dma_sync_single_for_cpu(&enic->pdev->dev, buf->dma_addr,
+					bytes_written, DMA_FROM_DEVICE);
+		skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+				(struct page *)buf->os_buf, buf->offset,
+				bytes_written, buf->truesize);
 		skb_record_rx_queue(skb, q_number);
 		enic_rq_set_skb_flags(rq, type, rss_hash, rss_type, fcoe,
 				      fcoe_fc_crc_ok, vlan_stripped,
 				      csum_not_calc, tcp_udp_csum_ok, ipv6,
 				      ipv4_csum_ok, vlan_tci, skb);
-		skb_mark_napi_id(skb, &enic->napi[rq->index]);
-		if (!(netdev->features & NETIF_F_GRO))
-			netif_receive_skb(skb);
-		else
-			napi_gro_receive(&enic->napi[q_number], skb);
+		skb_mark_for_recycle(skb);
+		napi_gro_frags(napi);
 		if (enic->rx_coalesce_setting.use_adaptive_rx_coalesce)
 			enic_intr_update_pkt_size(&cq->pkt_size_counter,
 						  bytes_written);
+		buf->os_buf = NULL;
+		buf->dma_addr = 0;
+		buf = buf->next;
 	} else {
 		/* Buffer overflow
 		 */
 		rqstats->pkt_truncated++;
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_FROM_DEVICE);
-		dev_kfree_skb_any(skb);
-		buf->os_buf = NULL;
 	}
 }
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 0bc595abc03b5..2ee4be2b9a343 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -61,6 +61,8 @@ struct vnic_rq_buf {
 	unsigned int index;
 	void *desc;
 	uint64_t wr_id;
+	unsigned int offset;
+	unsigned int truesize;
 };
 
 enum enic_poll_state {

From a3b2caaedeaa34891394fbb723b4f430bc6a08e2 Mon Sep 17 00:00:00 2001
From: John Daley <johndale@cisco.com>
Date: Wed, 5 Feb 2025 15:54:16 -0800
Subject: [PATCH 0210/2753] enic: remove copybreak tunable

With the move to using the Page Pool API for RX, rx copybreak was not
showing any improvement in host CPU overhead, latency or bandwidth so
the driver no longer makes use of the rx_copybreak setting. This patch
removes the ethtool tuneable hooks to set and get the rx copybreak since
they and now no-ops. Rx copybreak was the only tunable supported, so
remove the set and get tunable callbacks all together.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Link: https://patch.msgid.link/20250205235416.25410-5-johndale@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/enic.h        |  1 -
 .../net/ethernet/cisco/enic/enic_ethtool.c    | 39 -------------------
 drivers/net/ethernet/cisco/enic/enic_main.c   |  3 --
 3 files changed, 43 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 2ccf2d2a77dbb..305ed12aa0311 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -226,7 +226,6 @@ struct enic {
 	unsigned int cq_avail;
 	unsigned int cq_count;
 	struct enic_rfs_flw_tbl rfs_h;
-	u32 rx_copybreak;
 	u8 rss_key[ENIC_RSS_LEN];
 	struct vnic_gen_stats gen_stats;
 };
diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index d607b4f0542ce..18b929fc28799 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -608,43 +608,6 @@ static int enic_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd,
 	return ret;
 }
 
-static int enic_get_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna, void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		*(u32 *)data = enic->rx_copybreak;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
-static int enic_set_tunable(struct net_device *dev,
-			    const struct ethtool_tunable *tuna,
-			    const void *data)
-{
-	struct enic *enic = netdev_priv(dev);
-	int ret = 0;
-
-	switch (tuna->id) {
-	case ETHTOOL_RX_COPYBREAK:
-		enic->rx_copybreak = *(u32 *)data;
-		break;
-	default:
-		ret = -EINVAL;
-		break;
-	}
-
-	return ret;
-}
-
 static u32 enic_get_rxfh_key_size(struct net_device *netdev)
 {
 	return ENIC_RSS_LEN;
@@ -727,8 +690,6 @@ static const struct ethtool_ops enic_ethtool_ops = {
 	.get_coalesce = enic_get_coalesce,
 	.set_coalesce = enic_set_coalesce,
 	.get_rxnfc = enic_get_rxnfc,
-	.get_tunable = enic_get_tunable,
-	.set_tunable = enic_set_tunable,
 	.get_rxfh_key_size = enic_get_rxfh_key_size,
 	.get_rxfh = enic_get_rxfh,
 	.set_rxfh = enic_set_rxfh,
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 447c54dcd89b5..f24fd29ea2071 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -69,8 +69,6 @@
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN     0x0044  /* enet dynamic vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_VF      0x0071  /* enet SRIOV VF */
 
-#define RX_COPYBREAK_DEFAULT		256
-
 /* Supported devices */
 static const struct pci_device_id enic_id_table[] = {
 	{ PCI_VDEVICE(CISCO, PCI_DEVICE_ID_CISCO_VIC_ENET) },
@@ -2972,7 +2970,6 @@ static int enic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(dev, "Cannot register net device, aborting\n");
 		goto err_out_dev_deinit;
 	}
-	enic->rx_copybreak = RX_COPYBREAK_DEFAULT;
 
 	return 0;
 

From 508df2de7b3eabc72d773c5f29207745100986d0 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 15:43:32 +0000
Subject: [PATCH 0211/2753] net: pcs: rzn1-miic: fill in PCS
 supported_interfaces

Populate the PCS supported_interfaces bitmap with the interfaces that
this PCS supports. This makes the manual checking in miic_validate()
redundant, so remove that.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tfhYq-003aTm-Nx@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-rzn1-miic.c | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index 61944574d087d..11a96459a425d 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -268,17 +268,6 @@ static void miic_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 		     (MIIC_CONVCTRL_CONV_SPEED | MIIC_CONVCTRL_FULLD), val);
 }
 
-static int miic_validate(struct phylink_pcs *pcs, unsigned long *supported,
-			 const struct phylink_link_state *state)
-{
-	if (phy_interface_mode_is_rgmii(state->interface) ||
-	    state->interface == PHY_INTERFACE_MODE_RMII ||
-	    state->interface == PHY_INTERFACE_MODE_MII)
-		return 1;
-
-	return -EINVAL;
-}
-
 static int miic_pre_init(struct phylink_pcs *pcs)
 {
 	struct miic_port *miic_port = phylink_pcs_to_miic_port(pcs);
@@ -307,7 +296,6 @@ static int miic_pre_init(struct phylink_pcs *pcs)
 }
 
 static const struct phylink_pcs_ops miic_phylink_ops = {
-	.pcs_validate = miic_validate,
 	.pcs_config = miic_config,
 	.pcs_link_up = miic_link_up,
 	.pcs_pre_init = miic_pre_init,
@@ -363,6 +351,10 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np)
 	miic_port->pcs.ops = &miic_phylink_ops;
 	miic_port->pcs.neg_mode = true;
 
+	phy_interface_set_rgmii(miic_port->pcs.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_RMII, miic_port->pcs.supported_interfaces);
+	__set_bit(PHY_INTERFACE_MODE_MII, miic_port->pcs.supported_interfaces);
+
 	return &miic_port->pcs;
 }
 EXPORT_SYMBOL(miic_create);

From ec7309525a37b3f34c4efa85fc2ecaa65f41830e Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 5 Feb 2025 17:09:47 +0100
Subject: [PATCH 0212/2753] net: pcs: rzn1-miic: Convert to
 for_each_available_child_of_node() helper

Simplify miic_parse_dt() by using the for_each_available_child_of_node()
helper instead of manually skipping unavailable child nodes.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/3e394d4cf8204bcf17b184bfda474085aa8ed0dd.1738771631.git.geert+renesas@glider.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-rzn1-miic.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index 11a96459a425d..a808ac7375f5d 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -464,13 +464,10 @@ static int miic_parse_dt(struct device *dev, u32 *mode_cfg)
 	if (of_property_read_u32(np, "renesas,miic-switch-portin", &conf) == 0)
 		dt_val[0] = conf;
 
-	for_each_child_of_node(np, conv) {
+	for_each_available_child_of_node(np, conv) {
 		if (of_property_read_u32(conv, "reg", &port))
 			continue;
 
-		if (!of_device_is_available(conv))
-			continue;
-
 		if (of_property_read_u32(conv, "renesas,miic-input", &conf) == 0)
 			dt_val[port] = conf;
 	}

From 8d3bbe4355aded32961b9009b31de6d41b7352e9 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:21 +0000
Subject: [PATCH 0213/2753] of: base: Add of_get_available_child_by_name()

There are lot of drivers using of_get_child_by_name() followed by
of_device_is_available() to find the available child node by name for a
given parent. Provide a helper for these users to simplify the code.

Suggested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Rob Herring <robh@kernel.org>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/of/base.c  | 27 +++++++++++++++++++++++++++
 include/linux/of.h |  9 +++++++++
 2 files changed, 36 insertions(+)

diff --git a/drivers/of/base.c b/drivers/of/base.c
index af6c68bbb4277..e37b088f1fade 100644
--- a/drivers/of/base.c
+++ b/drivers/of/base.c
@@ -824,6 +824,33 @@ struct device_node *of_get_child_by_name(const struct device_node *node,
 }
 EXPORT_SYMBOL(of_get_child_by_name);
 
+/**
+ * of_get_available_child_by_name - Find the available child node by name for a given parent
+ * @node:	parent node
+ * @name:	child name to look for.
+ *
+ * This function looks for child node for given matching name and checks the
+ * device's availability for use.
+ *
+ * Return: A node pointer if found, with refcount incremented, use
+ * of_node_put() on it when done.
+ * Returns NULL if node is not found.
+ */
+struct device_node *of_get_available_child_by_name(const struct device_node *node,
+						   const char *name)
+{
+	struct device_node *child;
+
+	child = of_get_child_by_name(node, name);
+	if (child && !of_device_is_available(child)) {
+		of_node_put(child);
+		return NULL;
+	}
+
+	return child;
+}
+EXPORT_SYMBOL(of_get_available_child_by_name);
+
 struct device_node *__of_find_node_by_path(const struct device_node *parent,
 						const char *path)
 {
diff --git a/include/linux/of.h b/include/linux/of.h
index eaf0e2a2b75cb..9d6b8a61607f1 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -301,6 +301,8 @@ extern struct device_node *of_get_compatible_child(const struct device_node *par
 					const char *compatible);
 extern struct device_node *of_get_child_by_name(const struct device_node *node,
 					const char *name);
+extern struct device_node *of_get_available_child_by_name(const struct device_node *node,
+							  const char *name);
 
 /* cache lookup */
 extern struct device_node *of_find_next_cache_node(const struct device_node *);
@@ -578,6 +580,13 @@ static inline struct device_node *of_get_child_by_name(
 	return NULL;
 }
 
+static inline struct device_node *of_get_available_child_by_name(
+					const struct device_node *node,
+					const char *name)
+{
+	return NULL;
+}
+
 static inline int of_device_is_compatible(const struct device_node *device,
 					  const char *name)
 {

From 46df19a8dfdf48c9ef6fe1fc66e912eabb0213ed Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:22 +0000
Subject: [PATCH 0214/2753] net: dsa: rzn1_a5psw: Use
 of_get_available_child_by_name()

Simplify a5psw_probe() by using of_get_available_child_by_name().

While at it, move of_node_put(mdio) inside the if block to avoid code
duplication.

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/rzn1_a5psw.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/rzn1_a5psw.c b/drivers/net/dsa/rzn1_a5psw.c
index 66974379334a4..31ea8130a495f 100644
--- a/drivers/net/dsa/rzn1_a5psw.c
+++ b/drivers/net/dsa/rzn1_a5psw.c
@@ -1248,18 +1248,16 @@ static int a5psw_probe(struct platform_device *pdev)
 	if (ret)
 		goto clk_disable;
 
-	mdio = of_get_child_by_name(dev->of_node, "mdio");
-	if (of_device_is_available(mdio)) {
+	mdio = of_get_available_child_by_name(dev->of_node, "mdio");
+	if (mdio) {
 		ret = a5psw_probe_mdio(a5psw, mdio);
+		of_node_put(mdio);
 		if (ret) {
-			of_node_put(mdio);
 			dev_err(dev, "Failed to register MDIO: %d\n", ret);
 			goto hclk_disable;
 		}
 	}
 
-	of_node_put(mdio);
-
 	ds = &a5psw->ds;
 	ds->dev = dev;
 	ds->num_ports = A5PSW_PORTS_NUM;

From a76568865c1562b33176bf37d43e2b976c046931 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:23 +0000
Subject: [PATCH 0215/2753] net: dsa: sja1105: Use
 of_get_available_child_by_name()

Use the helper of_get_available_child_by_name() to simplify
sja1105_mdiobus_register().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/sja1105/sja1105_mdio.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_mdio.c b/drivers/net/dsa/sja1105/sja1105_mdio.c
index 84b7169f29748..8d535c033cef7 100644
--- a/drivers/net/dsa/sja1105/sja1105_mdio.c
+++ b/drivers/net/dsa/sja1105/sja1105_mdio.c
@@ -468,13 +468,10 @@ int sja1105_mdiobus_register(struct dsa_switch *ds)
 	if (rc)
 		return rc;
 
-	mdio_node = of_get_child_by_name(switch_node, "mdios");
+	mdio_node = of_get_available_child_by_name(switch_node, "mdios");
 	if (!mdio_node)
 		return 0;
 
-	if (!of_device_is_available(mdio_node))
-		goto out_put_mdio_node;
-
 	if (regs->mdio_100base_tx != SJA1105_RSV_ADDR) {
 		rc = sja1105_mdiobus_base_tx_register(priv, mdio_node);
 		if (rc)
@@ -487,7 +484,6 @@ int sja1105_mdiobus_register(struct dsa_switch *ds)
 			goto err_free_base_tx_mdiobus;
 	}
 
-out_put_mdio_node:
 	of_node_put(mdio_node);
 
 	return 0;

From 876e52b2d3f45082029538c4d0dcc20d5d722c01 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:24 +0000
Subject: [PATCH 0216/2753] net: ethernet: mtk-star-emac: Use
 of_get_available_child_by_name()

Use the helper of_get_available_child_by_name() to simplify
mtk_star_mdio_init().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_star_emac.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_star_emac.c b/drivers/net/ethernet/mediatek/mtk_star_emac.c
index 25989c79c92e6..76f202d7f0553 100644
--- a/drivers/net/ethernet/mediatek/mtk_star_emac.c
+++ b/drivers/net/ethernet/mediatek/mtk_star_emac.c
@@ -1427,15 +1427,10 @@ static int mtk_star_mdio_init(struct net_device *ndev)
 
 	of_node = dev->of_node;
 
-	mdio_node = of_get_child_by_name(of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto out_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;

From 1364004b5b918f2c4a26e84aca44250b9d82f9b6 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:25 +0000
Subject: [PATCH 0217/2753] net: ethernet: mtk_eth_soc: Use
 of_get_available_child_by_name()

Use the helper of_get_available_child_by_name() to simplify
mtk_mdio_init().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 53485142938c4..0ad965ced5ef8 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -830,17 +830,12 @@ static int mtk_mdio_init(struct mtk_eth *eth)
 	int ret;
 	u32 val;
 
-	mii_np = of_get_child_by_name(eth->dev->of_node, "mdio-bus");
+	mii_np = of_get_available_child_by_name(eth->dev->of_node, "mdio-bus");
 	if (!mii_np) {
 		dev_err(eth->dev, "no %s child node found", "mdio-bus");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	eth->mii_bus = devm_mdiobus_alloc(eth->dev);
 	if (!eth->mii_bus) {
 		ret = -ENOMEM;

From 76c82eb04332b0447b726a4a794e906669964008 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:26 +0000
Subject: [PATCH 0218/2753] net: ethernet: actions: Use
 of_get_available_child_by_name()

Use the helper of_get_available_child_by_name() to simplify
owl_emac_mdio_init().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/actions/owl-emac.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/actions/owl-emac.c b/drivers/net/ethernet/actions/owl-emac.c
index 115f48b3342cc..0a08da799255b 100644
--- a/drivers/net/ethernet/actions/owl-emac.c
+++ b/drivers/net/ethernet/actions/owl-emac.c
@@ -1325,15 +1325,10 @@ static int owl_emac_mdio_init(struct net_device *netdev)
 	struct device_node *mdio_node;
 	int ret;
 
-	mdio_node = of_get_child_by_name(dev->of_node, "mdio");
+	mdio_node = of_get_available_child_by_name(dev->of_node, "mdio");
 	if (!mdio_node)
 		return -ENODEV;
 
-	if (!of_device_is_available(mdio_node)) {
-		ret = -ENODEV;
-		goto err_put_node;
-	}
-
 	priv->mii = devm_mdiobus_alloc(dev);
 	if (!priv->mii) {
 		ret = -ENOMEM;

From 0584a917a2096a759976825e77d09ff215a7a543 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Wed, 5 Feb 2025 12:42:27 +0000
Subject: [PATCH 0219/2753] net: ibm: emac: Use
 of_get_available_child_by_name()

Use the helper of_get_available_child_by_name() to simplify
emac_dt_mdio_probe().

Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ibm/emac/core.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c
index 25b8a35560042..417dfa18daae3 100644
--- a/drivers/net/ethernet/ibm/emac/core.c
+++ b/drivers/net/ethernet/ibm/emac/core.c
@@ -2554,17 +2554,12 @@ static int emac_dt_mdio_probe(struct emac_instance *dev)
 	struct mii_bus *bus;
 	int res;
 
-	mii_np = of_get_child_by_name(dev->ofdev->dev.of_node, "mdio");
+	mii_np = of_get_available_child_by_name(dev->ofdev->dev.of_node, "mdio");
 	if (!mii_np) {
 		dev_err(&dev->ofdev->dev, "no mdio definition found.");
 		return -ENODEV;
 	}
 
-	if (!of_device_is_available(mii_np)) {
-		res = -ENODEV;
-		goto put_node;
-	}
-
 	bus = devm_mdiobus_alloc(&dev->ofdev->dev);
 	if (!bus) {
 		res = -ENOMEM;

From a494d1512c7c7ba2a05bac51ed4b133baa2a9bc8 Mon Sep 17 00:00:00 2001
From: Ted Chen <znscnchen@gmail.com>
Date: Thu, 6 Feb 2025 22:00:02 +0800
Subject: [PATCH 0220/2753] vxlan: Remove unnecessary comments for vxlan_rcv()
 and vxlan_err_lookup()

Remove the two unnecessary comments around vxlan_rcv() and
vxlan_err_lookup(), which indicate that the callers are from
net/ipv{4,6}/udp.c. These callers are trivial to find. Additionally, the
comment for vxlan_rcv() missed that the caller could also be from
net/ipv6/udp.c.

Suggested-by: Nikolay Aleksandrov <razor@blackwall.org>
Suggested-by: Ido Schimmel <idosch@idosch.org>
Signed-off-by: Ted Chen <znscnchen@gmail.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250206140002.116178-1-znscnchen@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vxlan/vxlan_core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index ece5415f9013d..44eba7aa831a4 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -1670,7 +1670,6 @@ static bool vxlan_ecn_decapsulate(struct vxlan_sock *vs, void *oiph,
 	return err <= 1;
 }
 
-/* Callback from net/ipv4/udp.c to receive packets */
 static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 {
 	struct vxlan_vni_node *vninode = NULL;
@@ -1840,7 +1839,6 @@ static int vxlan_rcv(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-/* Callback from net/ipv{4,6}/udp.c to check that we have a VNI for errors */
 static int vxlan_err_lookup(struct sock *sk, struct sk_buff *skb)
 {
 	struct vxlan_dev *vxlan;

From d876ec8d3ed3e2f9d29ed866248a294d71e40d86 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Feb 2025 09:34:36 +0000
Subject: [PATCH 0221/2753] tcp: do not export tcp_parse_mss_option() and
 tcp_mtup_init()

These two functions are not called from modules.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250206093436.2609008-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_input.c  | 1 -
 net/ipv4/tcp_output.c | 1 -
 2 files changed, 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index eb82e01da9110..61da8ffc2f86f 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4174,7 +4174,6 @@ u16 tcp_parse_mss_option(const struct tcphdr *th, u16 user_mss)
 	}
 	return mss;
 }
-EXPORT_SYMBOL_GPL(tcp_parse_mss_option);
 
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index bc95d2a5924fd..ef9f6172680f5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1813,7 +1813,6 @@ void tcp_mtup_init(struct sock *sk)
 	if (icsk->icsk_mtup.enabled)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
 }
-EXPORT_SYMBOL(tcp_mtup_init);
 
 /* This function synchronize snd mss to current pmtu/exthdr set.
 

From be258f654a6ef5ab0d777f40fd3bcee540934307 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Feb 2025 09:46:05 +0000
Subject: [PATCH 0222/2753] tcp: rename
 inet_csk_{delete|reset}_keepalive_timer()

inet_csk_delete_keepalive_timer() and inet_csk_reset_keepalive_timer()
are only used from core TCP, there is no need to export them.

Replace their prefix by tcp.

Move them to net/ipv4/tcp_timer.c and make tcp_delete_keepalive_timer()
static.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250206094605.2694118-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_connection_sock.h |  3 ---
 include/net/tcp.h                  |  1 +
 net/ipv4/inet_connection_sock.c    | 12 ------------
 net/ipv4/tcp.c                     |  4 ++--
 net/ipv4/tcp_input.c               |  6 +++---
 net/ipv4/tcp_minisocks.c           |  3 +--
 net/ipv4/tcp_timer.c               | 21 +++++++++++++++------
 7 files changed, 22 insertions(+), 28 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index c7f42844c79a9..055aa80b05c6d 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -189,9 +189,6 @@ static inline void inet_csk_delack_init(struct sock *sk)
 	memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
 }
 
-void inet_csk_delete_keepalive_timer(struct sock *sk);
-void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
-
 static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5b2b04835688f..bb7edf0e72aa0 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -415,6 +415,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		      sockptr_t optval, unsigned int optlen);
 int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen);
+void tcp_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
 void tcp_set_keepalive(struct sock *sk, int val);
 void tcp_syn_ack_timeout(const struct request_sock *req);
 int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e4decfb270fa1..2b7775b90a090 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -799,18 +799,6 @@ void inet_csk_clear_xmit_timers_sync(struct sock *sk)
 	sk_stop_timer_sync(sk, &sk->sk_timer);
 }
 
-void inet_csk_delete_keepalive_timer(struct sock *sk)
-{
-	sk_stop_timer(sk, &sk->sk_timer);
-}
-EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);
-
-void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
-{
-	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
-}
-EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
-
 struct dst_entry *inet_csk_route_req(const struct sock *sk,
 				     struct flowi4 *fl4,
 				     const struct request_sock *req)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 7f43d31c9400e..2021f2709ec32 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3179,7 +3179,7 @@ void __tcp_close(struct sock *sk, long timeout)
 			const int tmo = tcp_fin_time(sk);
 
 			if (tmo > TCP_TIMEWAIT_LEN) {
-				inet_csk_reset_keepalive_timer(sk,
+				tcp_reset_keepalive_timer(sk,
 						tmo - TCP_TIMEWAIT_LEN);
 			} else {
 				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
@@ -3632,7 +3632,7 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val)
 			elapsed = tp->keepalive_time - elapsed;
 		else
 			elapsed = 0;
-		inet_csk_reset_keepalive_timer(sk, elapsed);
+		tcp_reset_keepalive_timer(sk, elapsed);
 	}
 
 	return 0;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 61da8ffc2f86f..286f15e4994a9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6346,7 +6346,7 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
 	tp->lsndtime = tcp_jiffies32;
 
 	if (sock_flag(sk, SOCK_KEEPOPEN))
-		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tp));
+		tcp_reset_keepalive_timer(sk, keepalive_time_when(tp));
 
 	if (!tp->rx_opt.snd_wscale)
 		__tcp_fast_path_on(tp, tp->snd_wnd);
@@ -6921,7 +6921,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 
 		tmo = tcp_fin_time(sk);
 		if (tmo > TCP_TIMEWAIT_LEN) {
-			inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
+			tcp_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
 		} else if (th->fin || sock_owned_by_user(sk)) {
 			/* Bad case. We could lose such FIN otherwise.
 			 * It is not a big problem, but it looks confusing
@@ -6929,7 +6929,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			 * if it spins in bh_lock_sock(), but it is really
 			 * marginal case.
 			 */
-			inet_csk_reset_keepalive_timer(sk, tmo);
+			tcp_reset_keepalive_timer(sk, tmo);
 		} else {
 			tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
 			goto consume;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b089b08e96178..0deb2ac85acf7 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -566,8 +566,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 	WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1);
 
 	if (sock_flag(newsk, SOCK_KEEPOPEN))
-		inet_csk_reset_keepalive_timer(newsk,
-					       keepalive_time_when(newtp));
+		tcp_reset_keepalive_timer(newsk, keepalive_time_when(newtp));
 
 	newtp->rx_opt.tstamp_ok = ireq->tstamp_ok;
 	newtp->rx_opt.sack_ok = ireq->sack_ok;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b412ed88ccd9a..cfb6f4c4e4c9f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -751,20 +751,29 @@ void tcp_syn_ack_timeout(const struct request_sock *req)
 }
 EXPORT_SYMBOL(tcp_syn_ack_timeout);
 
+void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len)
+{
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+}
+
+static void tcp_delete_keepalive_timer(struct sock *sk)
+{
+	sk_stop_timer(sk, &sk->sk_timer);
+}
+
 void tcp_set_keepalive(struct sock *sk, int val)
 {
 	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
 		return;
 
 	if (val && !sock_flag(sk, SOCK_KEEPOPEN))
-		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
+		tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
 	else if (!val)
-		inet_csk_delete_keepalive_timer(sk);
+		tcp_delete_keepalive_timer(sk);
 }
 EXPORT_SYMBOL_GPL(tcp_set_keepalive);
 
-
-static void tcp_keepalive_timer (struct timer_list *t)
+static void tcp_keepalive_timer(struct timer_list *t)
 {
 	struct sock *sk = from_timer(sk, t, sk_timer);
 	struct inet_connection_sock *icsk = inet_csk(sk);
@@ -775,7 +784,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
 		/* Try again later. */
-		inet_csk_reset_keepalive_timer (sk, HZ/20);
+		tcp_reset_keepalive_timer(sk, HZ/20);
 		goto out;
 	}
 
@@ -841,7 +850,7 @@ static void tcp_keepalive_timer (struct timer_list *t)
 	}
 
 resched:
-	inet_csk_reset_keepalive_timer (sk, elapsed);
+	tcp_reset_keepalive_timer(sk, elapsed);
 	goto out;
 
 death:

From a923378ab0c438e43d7d35d1cf0be47d353f87b4 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:39:45 +0000
Subject: [PATCH 0223/2753] net: stmmac: delete software timer before disabling
 LPI

Delete the software timer to ensure that the timer doesn't fire while
we are modifying the LPI register state, potentially re-enabling LPI.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffd3-003ZHV-6C@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index b34ebb916b898..9a568339e9ae6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -447,8 +447,8 @@ static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv)
  */
 static void stmmac_stop_sw_lpi(struct stmmac_priv *priv)
 {
-	stmmac_reset_eee_mode(priv, priv->hw);
 	del_timer_sync(&priv->eee_ctrl_timer);
+	stmmac_reset_eee_mode(priv, priv->hw);
 	priv->tx_path_in_lpi_mode = false;
 }
 
@@ -492,8 +492,8 @@ static void stmmac_eee_init(struct stmmac_priv *priv, bool active)
 		if (priv->eee_enabled) {
 			netdev_dbg(priv->dev, "disable EEE\n");
 			priv->eee_sw_timer_en = false;
-			stmmac_disable_hw_lpi_timer(priv);
 			del_timer_sync(&priv->eee_ctrl_timer);
+			stmmac_disable_hw_lpi_timer(priv);
 			stmmac_set_eee_timer(priv, priv->hw, 0,
 					     STMMAC_DEFAULT_TWT_LS);
 			if (priv->hw->xpcs)

From 64c9936330ccba159f72faaaaa18bdc0f67f5a54 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:39:50 +0000
Subject: [PATCH 0224/2753] net: stmmac: ensure LPI is disabled when disabling
 EEE

When EEE is disabled, we call stmmac_set_eee_lpi_timer(..., 0).

For dwmac4, this will result in LPIATE being cleared, but LPIEN and
LPITXA being set, causing LPI mode to be signalled (if it wasn't
before).

For others MACs, stmmac_set_eee_lpi_timer() does nothing, which means
that LPI mode will continue to be signalled despite the expectation
for it to be disabled.

In both cases, LPI mode will be terminated when the transmitter has
a packet to send, and LPIEN will be cleared by hardware.

Call stmmac_reset_eee_mode() to ensure that LPI mode is disabled when
EEE mode is requested to be disabled.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffd8-003ZHb-AX@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 9a568339e9ae6..edcdd880f6f14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -494,6 +494,7 @@ static void stmmac_eee_init(struct stmmac_priv *priv, bool active)
 			priv->eee_sw_timer_en = false;
 			del_timer_sync(&priv->eee_ctrl_timer);
 			stmmac_disable_hw_lpi_timer(priv);
+			stmmac_reset_eee_mode(priv, priv->hw);
 			stmmac_set_eee_timer(priv, priv->hw, 0,
 					     STMMAC_DEFAULT_TWT_LS);
 			if (priv->hw->xpcs)

From 6e9c71ee65eb88f94ca0096268079a91b94403ad Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:39:55 +0000
Subject: [PATCH 0225/2753] net: stmmac: dwmac4: ensure LPIATE is cleared

LPIATE enables the hardware timer for entering LPI mode. To sure that
the correct mode is used, clear LPIATE when using manual/software-timed
mode to prevent the hardware using the timer.

stmmac_main.c avoids this being a problem at the moment by calling
stmmac_set_eee_lpi_timer(..., 0) before switching to software mode.

We no longer need to call stmmac_set_eee_lpi_timer(..., 0) when
disabling EEE as stmmac_reset_eee_mode() will now clear all LPI
settings.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdD-003ZHh-Ew@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 4 +++-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 1 -
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 9ed8620580a86..17bf836eba7fa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -387,6 +387,7 @@ static void dwmac4_set_eee_mode(struct mac_device_info *hw,
 	 * state.
 	 */
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
+	value &= ~GMAC4_LPI_CTRL_STATUS_LPIATE;
 	value |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
 
 	if (en_tx_lpi_clockgating)
@@ -401,7 +402,8 @@ static void dwmac4_reset_eee_mode(struct mac_device_info *hw)
 	u32 value;
 
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~(GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA);
+	value &= ~(GMAC4_LPI_CTRL_STATUS_LPIATE | GMAC4_LPI_CTRL_STATUS_LPIEN |
+		   GMAC4_LPI_CTRL_STATUS_LPITXA);
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index edcdd880f6f14..a42a3da92400c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -493,7 +493,6 @@ static void stmmac_eee_init(struct stmmac_priv *priv, bool active)
 			netdev_dbg(priv->dev, "disable EEE\n");
 			priv->eee_sw_timer_en = false;
 			del_timer_sync(&priv->eee_ctrl_timer);
-			stmmac_disable_hw_lpi_timer(priv);
 			stmmac_reset_eee_mode(priv, priv->hw);
 			stmmac_set_eee_timer(priv, priv->hw, 0,
 					     STMMAC_DEFAULT_TWT_LS);

From cc3f4d5508c87780aa62b34503ff093c86e1edd0 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:00 +0000
Subject: [PATCH 0226/2753] net: stmmac: split stmmac_init_eee() and move to
 phylink methods

Move the appropriate parts of stmmac_init_eee() into the phylink
mac_enable_tx_lpi() and mac_disable_tx_lpi() methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdI-003ZHn-Iz@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 133 +++++++++---------
 1 file changed, 63 insertions(+), 70 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a42a3da92400c..dfd4965404f93 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -466,74 +466,6 @@ static void stmmac_eee_ctrl_timer(struct timer_list *t)
 	stmmac_try_to_start_sw_lpi(priv);
 }
 
-/**
- * stmmac_eee_init - init EEE
- * @priv: driver private structure
- * @active: indicates whether EEE should be enabled.
- * Description:
- *  if the GMAC supports the EEE (from the HW cap reg) and the phy device
- *  can also manage EEE, this function enable the LPI state and start related
- *  timer.
- */
-static void stmmac_eee_init(struct stmmac_priv *priv, bool active)
-{
-	priv->eee_active = active;
-
-	/* Check if MAC core supports the EEE feature. */
-	if (!priv->dma_cap.eee) {
-		priv->eee_enabled = false;
-		return;
-	}
-
-	mutex_lock(&priv->lock);
-
-	/* Check if it needs to be deactivated */
-	if (!priv->eee_active) {
-		if (priv->eee_enabled) {
-			netdev_dbg(priv->dev, "disable EEE\n");
-			priv->eee_sw_timer_en = false;
-			del_timer_sync(&priv->eee_ctrl_timer);
-			stmmac_reset_eee_mode(priv, priv->hw);
-			stmmac_set_eee_timer(priv, priv->hw, 0,
-					     STMMAC_DEFAULT_TWT_LS);
-			if (priv->hw->xpcs)
-				xpcs_config_eee(priv->hw->xpcs,
-						priv->plat->mult_fact_100ns,
-						false);
-		}
-		priv->eee_enabled = false;
-		mutex_unlock(&priv->lock);
-		return;
-	}
-
-	if (priv->eee_active && !priv->eee_enabled) {
-		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
-				     STMMAC_DEFAULT_TWT_LS);
-		if (priv->hw->xpcs)
-			xpcs_config_eee(priv->hw->xpcs,
-					priv->plat->mult_fact_100ns,
-					true);
-	}
-
-	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
-		/* Use hardware LPI mode */
-		del_timer_sync(&priv->eee_ctrl_timer);
-		priv->tx_path_in_lpi_mode = false;
-		priv->eee_sw_timer_en = false;
-		stmmac_enable_hw_lpi_timer(priv);
-	} else {
-		/* Use software LPI mode */
-		priv->eee_sw_timer_en = true;
-		stmmac_disable_hw_lpi_timer(priv);
-		stmmac_restart_sw_lpi_timer(priv);
-	}
-
-	priv->eee_enabled = true;
-
-	mutex_unlock(&priv->lock);
-	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
-}
-
 /* stmmac_get_tx_hwtstamp - get HW TX timestamps
  * @priv: driver private structure
  * @p : descriptor pointer
@@ -1110,7 +1042,33 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 
-	stmmac_eee_init(priv, false);
+	priv->eee_active = false;
+
+	/* Check if MAC core supports the EEE feature. */
+	if (!priv->dma_cap.eee) {
+		priv->eee_enabled = false;
+		return;
+	}
+
+	mutex_lock(&priv->lock);
+
+	/* Check if it needs to be deactivated */
+	if (!priv->eee_active) {
+		if (priv->eee_enabled) {
+			netdev_dbg(priv->dev, "disable EEE\n");
+			priv->eee_sw_timer_en = false;
+			del_timer_sync(&priv->eee_ctrl_timer);
+			stmmac_reset_eee_mode(priv, priv->hw);
+			stmmac_set_eee_timer(priv, priv->hw, 0,
+					     STMMAC_DEFAULT_TWT_LS);
+			if (priv->hw->xpcs)
+				xpcs_config_eee(priv->hw->xpcs,
+						priv->plat->mult_fact_100ns,
+						false);
+		}
+		priv->eee_enabled = false;
+	}
+	mutex_unlock(&priv->lock);
 }
 
 static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
@@ -1119,7 +1077,42 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 
 	priv->tx_lpi_timer = timer;
-	stmmac_eee_init(priv, true);
+	priv->eee_active = true;
+
+	/* Check if MAC core supports the EEE feature. */
+	if (!priv->dma_cap.eee) {
+		priv->eee_enabled = false;
+		return 0;
+	}
+
+	mutex_lock(&priv->lock);
+
+	if (priv->eee_active && !priv->eee_enabled) {
+		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
+				     STMMAC_DEFAULT_TWT_LS);
+		if (priv->hw->xpcs)
+			xpcs_config_eee(priv->hw->xpcs,
+					priv->plat->mult_fact_100ns,
+					true);
+	}
+
+	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
+		/* Use hardware LPI mode */
+		del_timer_sync(&priv->eee_ctrl_timer);
+		priv->tx_path_in_lpi_mode = false;
+		priv->eee_sw_timer_en = false;
+		stmmac_enable_hw_lpi_timer(priv);
+	} else {
+		/* Use software LPI mode */
+		priv->eee_sw_timer_en = true;
+		stmmac_disable_hw_lpi_timer(priv);
+		stmmac_restart_sw_lpi_timer(priv);
+	}
+
+	priv->eee_enabled = true;
+
+	mutex_unlock(&priv->lock);
+	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
 
 	return 0;
 }

From 4abd576873559917b08cac646ad137ac249705bd Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:05 +0000
Subject: [PATCH 0227/2753] net: stmmac: remove priv->dma_cap.eee test in
 tx_lpi methods

The tests for priv->dma_cap.eee in stmmac_mac_{en,dis}able_tx_lpi()
is useless as these methods will only be called when using phylink
managed EEE, and that will only be enabled if the LPI capabilities
in phylink_config have been populated during initialisation. This
only occurs when priv->dma_cap.eee was true.

As priv->dma_cap.eee remains constant during the lifetime of the driver
instance, there is no need to re-check it in these methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdN-003ZHt-Mq@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index dfd4965404f93..d3854e1b4d269 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1044,12 +1044,6 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 
 	priv->eee_active = false;
 
-	/* Check if MAC core supports the EEE feature. */
-	if (!priv->dma_cap.eee) {
-		priv->eee_enabled = false;
-		return;
-	}
-
 	mutex_lock(&priv->lock);
 
 	/* Check if it needs to be deactivated */
@@ -1079,12 +1073,6 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 	priv->tx_lpi_timer = timer;
 	priv->eee_active = true;
 
-	/* Check if MAC core supports the EEE feature. */
-	if (!priv->dma_cap.eee) {
-		priv->eee_enabled = false;
-		return 0;
-	}
-
 	mutex_lock(&priv->lock);
 
 	if (priv->eee_active && !priv->eee_enabled) {

From 2cc8e6d308952abcc9bad8b88f28f9988a050135 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:10 +0000
Subject: [PATCH 0228/2753] net: stmmac: remove unnecessary priv->eee_active
 tests

Since priv->eee_active is assigned with a constant value in each of
these methods, there is no need to test its value later. Remove these
unnecessary tests.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdS-003ZHz-Qi@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 29 ++++++++-----------
 1 file changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d3854e1b4d269..517176533eb2d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1047,21 +1047,17 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 	mutex_lock(&priv->lock);
 
 	/* Check if it needs to be deactivated */
-	if (!priv->eee_active) {
-		if (priv->eee_enabled) {
-			netdev_dbg(priv->dev, "disable EEE\n");
-			priv->eee_sw_timer_en = false;
-			del_timer_sync(&priv->eee_ctrl_timer);
-			stmmac_reset_eee_mode(priv, priv->hw);
-			stmmac_set_eee_timer(priv, priv->hw, 0,
-					     STMMAC_DEFAULT_TWT_LS);
-			if (priv->hw->xpcs)
-				xpcs_config_eee(priv->hw->xpcs,
-						priv->plat->mult_fact_100ns,
-						false);
-		}
-		priv->eee_enabled = false;
+	if (priv->eee_enabled) {
+		netdev_dbg(priv->dev, "disable EEE\n");
+		priv->eee_sw_timer_en = false;
+		del_timer_sync(&priv->eee_ctrl_timer);
+		stmmac_reset_eee_mode(priv, priv->hw);
+		stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
+		if (priv->hw->xpcs)
+			xpcs_config_eee(priv->hw->xpcs,
+					priv->plat->mult_fact_100ns, false);
 	}
+	priv->eee_enabled = false;
 	mutex_unlock(&priv->lock);
 }
 
@@ -1075,13 +1071,12 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 
 	mutex_lock(&priv->lock);
 
-	if (priv->eee_active && !priv->eee_enabled) {
+	if (!priv->eee_enabled) {
 		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
 				     STMMAC_DEFAULT_TWT_LS);
 		if (priv->hw->xpcs)
 			xpcs_config_eee(priv->hw->xpcs,
-					priv->plat->mult_fact_100ns,
-					true);
+					priv->plat->mult_fact_100ns, true);
 	}
 
 	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {

From faafe39c77fbfb7001e8ed698eda15609f2745fc Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:15 +0000
Subject: [PATCH 0229/2753] net: stmmac: remove unnecessary priv->eee_enabled
 tests

Phylink will not call the mac_disable_tx_lpi() and mac_enable_tx_lpi()
methods randomly - the first method to be called will be the enable
method, and then after, the disable method will be called once between
subsequent enable calls. Thus there is a guaranteed ordering.

Therefore, we know the previous state of priv->eee_enabled, and can
remove it from both methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdX-003ZI5-UV@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 37 +++++++++----------
 1 file changed, 17 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 517176533eb2d..c57d800f0a853 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1046,18 +1046,17 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 
 	mutex_lock(&priv->lock);
 
-	/* Check if it needs to be deactivated */
-	if (priv->eee_enabled) {
-		netdev_dbg(priv->dev, "disable EEE\n");
-		priv->eee_sw_timer_en = false;
-		del_timer_sync(&priv->eee_ctrl_timer);
-		stmmac_reset_eee_mode(priv, priv->hw);
-		stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
-		if (priv->hw->xpcs)
-			xpcs_config_eee(priv->hw->xpcs,
-					priv->plat->mult_fact_100ns, false);
-	}
 	priv->eee_enabled = false;
+
+	netdev_dbg(priv->dev, "disable EEE\n");
+	priv->eee_sw_timer_en = false;
+	del_timer_sync(&priv->eee_ctrl_timer);
+	stmmac_reset_eee_mode(priv, priv->hw);
+	stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
+	if (priv->hw->xpcs)
+		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,
+				false);
+
 	mutex_unlock(&priv->lock);
 }
 
@@ -1071,13 +1070,13 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 
 	mutex_lock(&priv->lock);
 
-	if (!priv->eee_enabled) {
-		stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
-				     STMMAC_DEFAULT_TWT_LS);
-		if (priv->hw->xpcs)
-			xpcs_config_eee(priv->hw->xpcs,
-					priv->plat->mult_fact_100ns, true);
-	}
+	priv->eee_enabled = true;
+
+	stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
+			     STMMAC_DEFAULT_TWT_LS);
+	if (priv->hw->xpcs)
+		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,
+				true);
 
 	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
 		/* Use hardware LPI mode */
@@ -1092,8 +1091,6 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 		stmmac_restart_sw_lpi_timer(priv);
 	}
 
-	priv->eee_enabled = true;
-
 	mutex_unlock(&priv->lock);
 	netdev_dbg(priv->dev, "Energy-Efficient Ethernet initialized\n");
 

From 54f85e5221c30d703108278ef07d8ef97f2bcd7a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:21 +0000
Subject: [PATCH 0230/2753] net: stmmac: clear priv->tx_path_in_lpi_mode when
 disabling LPI

As other code paths do, clear priv->tx_path_in_lpi_mode when disabling
LPI. This is done after the software timer has been deleted and
hardware LPI has been disabled.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdd-003ZIB-22@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c57d800f0a853..bf549ab78f78f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1052,6 +1052,8 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 	priv->eee_sw_timer_en = false;
 	del_timer_sync(&priv->eee_ctrl_timer);
 	stmmac_reset_eee_mode(priv, priv->hw);
+	priv->tx_path_in_lpi_mode = false;
+
 	stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
 	if (priv->hw->xpcs)
 		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,

From 9b6649a810752bf2fc2c33d58efc97c48d1a1644 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:26 +0000
Subject: [PATCH 0231/2753] net: stmmac: remove unnecessary LPI disable when
 enabling LPI

Remove the unnecessary LPI disable when enabling LPI - as noted in
previous commits, there will never be two consecutive calls to
stmmac_mac_enable_tx_lpi() without an intervening
stmmac_mac_disable_tx_lpi.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdi-003ZIH-5h@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index bf549ab78f78f..5890a21d1ef9e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -390,11 +390,6 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 	return dirty;
 }
 
-static void stmmac_disable_hw_lpi_timer(struct stmmac_priv *priv)
-{
-	stmmac_set_eee_lpi_timer(priv, priv->hw, 0);
-}
-
 static void stmmac_enable_hw_lpi_timer(struct stmmac_priv *priv)
 {
 	stmmac_set_eee_lpi_timer(priv, priv->hw, priv->tx_lpi_timer);
@@ -1082,14 +1077,10 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 
 	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
 		/* Use hardware LPI mode */
-		del_timer_sync(&priv->eee_ctrl_timer);
-		priv->tx_path_in_lpi_mode = false;
-		priv->eee_sw_timer_en = false;
 		stmmac_enable_hw_lpi_timer(priv);
 	} else {
 		/* Use software LPI mode */
 		priv->eee_sw_timer_en = true;
-		stmmac_disable_hw_lpi_timer(priv);
 		stmmac_restart_sw_lpi_timer(priv);
 	}
 

From 6e37877d222d3ae634fdbf2468b6e53936d0d715 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:31 +0000
Subject: [PATCH 0232/2753] net: stmmac: use common LPI_CTRL_STATUS bit
 definitions

The bit definitions for the LPI control/status register are
identical across all MAC versions, with the exception that some
bits may not be implemented. Provide definitions for bits in this
register in common.h, convert to use them, and remove the core-
specific definitions.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdn-003ZIN-9p@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/common.h  | 14 ++++++++++
 .../net/ethernet/stmicro/stmmac/dwmac1000.h   | 13 +--------
 drivers/net/ethernet/stmicro/stmmac/dwmac4.h  | 12 +-------
 .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 28 +++++++++----------
 .../net/ethernet/stmicro/stmmac/dwxgmac2.h    |  9 +-----
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 18 ++++++------
 6 files changed, 40 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index e25db747a81a5..55053528e4984 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -530,6 +530,20 @@ struct dma_features {
 #define STMMAC_DEFAULT_TWT_LS	0x1E
 #define STMMAC_ET_MAX		0xFFFFF
 
+/* Common LPI register bits */
+#define LPI_CTRL_STATUS_LPITCSE	BIT(21)	/* LPI Tx Clock Stop Enable, gmac4, xgmac2 only */
+#define LPI_CTRL_STATUS_LPIATE	BIT(20)	/* LPI Timer Enable, gmac4 only */
+#define LPI_CTRL_STATUS_LPITXA	BIT(19)	/* Enable LPI TX Automate */
+#define LPI_CTRL_STATUS_PLSEN	BIT(18)	/* Enable PHY Link Status */
+#define LPI_CTRL_STATUS_PLS	BIT(17)	/* PHY Link Status */
+#define LPI_CTRL_STATUS_LPIEN	BIT(16)	/* LPI Enable */
+#define LPI_CTRL_STATUS_RLPIST	BIT(9)	/* Receive LPI state, gmac1000 only? */
+#define LPI_CTRL_STATUS_TLPIST	BIT(8)	/* Transmit LPI state, gmac1000 only? */
+#define LPI_CTRL_STATUS_RLPIEX	BIT(3)	/* Receive LPI Exit */
+#define LPI_CTRL_STATUS_RLPIEN	BIT(2)	/* Receive LPI Entry */
+#define LPI_CTRL_STATUS_TLPIEX	BIT(1)	/* Transmit LPI Exit */
+#define LPI_CTRL_STATUS_TLPIEN	BIT(0)	/* Transmit LPI Entry */
+
 #define STMMAC_CHAIN_MODE	0x1
 #define STMMAC_RING_MODE	0x2
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
index 600fea8f712fd..967a16212faf0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h
@@ -59,22 +59,11 @@ enum power_event {
 /* Energy Efficient Ethernet (EEE)
  *
  * LPI status, timer and control register offset
+ * For LPI control and status bit definitions, see common.h.
  */
 #define LPI_CTRL_STATUS	0x0030
 #define LPI_TIMER_CTRL	0x0034
 
-/* LPI control and status defines */
-#define LPI_CTRL_STATUS_LPITXA	0x00080000	/* Enable LPI TX Automate */
-#define LPI_CTRL_STATUS_PLSEN	0x00040000	/* Enable PHY Link Status */
-#define LPI_CTRL_STATUS_PLS	0x00020000	/* PHY Link Status */
-#define LPI_CTRL_STATUS_LPIEN	0x00010000	/* LPI Enable */
-#define LPI_CTRL_STATUS_RLPIST	0x00000200	/* Receive LPI state */
-#define LPI_CTRL_STATUS_TLPIST	0x00000100	/* Transmit LPI state */
-#define LPI_CTRL_STATUS_RLPIEX	0x00000008	/* Receive LPI Exit */
-#define LPI_CTRL_STATUS_RLPIEN	0x00000004	/* Receive LPI Entry */
-#define LPI_CTRL_STATUS_TLPIEX	0x00000002	/* Transmit LPI Exit */
-#define LPI_CTRL_STATUS_TLPIEN	0x00000001	/* Transmit LPI Entry */
-
 /* GMAC HW ADDR regs */
 #define GMAC_ADDR_HIGH(reg)	((reg > 15) ? 0x00000800 + (reg - 16) * 8 : \
 				 0x00000040 + (reg * 8))
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
index 184d41a306af0..42fe29a4e300b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h
@@ -177,23 +177,13 @@ enum power_event {
 /* Energy Efficient Ethernet (EEE) for GMAC4
  *
  * LPI status, timer and control register offset
+ * For LPI control and status bit definitions, see common.h.
  */
 #define GMAC4_LPI_CTRL_STATUS	0xd0
 #define GMAC4_LPI_TIMER_CTRL	0xd4
 #define GMAC4_LPI_ENTRY_TIMER	0xd8
 #define GMAC4_MAC_ONEUS_TIC_COUNTER	0xdc
 
-/* LPI control and status defines */
-#define GMAC4_LPI_CTRL_STATUS_LPITCSE	BIT(21)	/* LPI Tx Clock Stop Enable */
-#define GMAC4_LPI_CTRL_STATUS_LPIATE	BIT(20) /* LPI Timer Enable */
-#define GMAC4_LPI_CTRL_STATUS_LPITXA	BIT(19)	/* Enable LPI TX Automate */
-#define GMAC4_LPI_CTRL_STATUS_PLS	BIT(17) /* PHY Link Status */
-#define GMAC4_LPI_CTRL_STATUS_LPIEN	BIT(16)	/* LPI Enable */
-#define GMAC4_LPI_CTRL_STATUS_RLPIEX	BIT(3) /* Receive LPI Exit */
-#define GMAC4_LPI_CTRL_STATUS_RLPIEN	BIT(2) /* Receive LPI Entry */
-#define GMAC4_LPI_CTRL_STATUS_TLPIEX	BIT(1) /* Transmit LPI Exit */
-#define GMAC4_LPI_CTRL_STATUS_TLPIEN	BIT(0) /* Transmit LPI Entry */
-
 /* MAC Debug bitmap */
 #define GMAC_DEBUG_TFCSTS_MASK		GENMASK(18, 17)
 #define GMAC_DEBUG_TFCSTS_SHIFT		17
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index 17bf836eba7fa..c324aaf691e0d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -387,11 +387,11 @@ static void dwmac4_set_eee_mode(struct mac_device_info *hw,
 	 * state.
 	 */
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~GMAC4_LPI_CTRL_STATUS_LPIATE;
-	value |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
+	value &= ~LPI_CTRL_STATUS_LPIATE;
+	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
 
 	if (en_tx_lpi_clockgating)
-		value |= GMAC4_LPI_CTRL_STATUS_LPITCSE;
+		value |= LPI_CTRL_STATUS_LPITCSE;
 
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
@@ -402,8 +402,8 @@ static void dwmac4_reset_eee_mode(struct mac_device_info *hw)
 	u32 value;
 
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~(GMAC4_LPI_CTRL_STATUS_LPIATE | GMAC4_LPI_CTRL_STATUS_LPIEN |
-		   GMAC4_LPI_CTRL_STATUS_LPITXA);
+	value &= ~(LPI_CTRL_STATUS_LPIATE | LPI_CTRL_STATUS_LPIEN |
+		   LPI_CTRL_STATUS_LPITXA);
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
 
@@ -415,9 +415,9 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
 	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
 
 	if (link)
-		value |= GMAC4_LPI_CTRL_STATUS_PLS;
+		value |= LPI_CTRL_STATUS_PLS;
 	else
-		value &= ~GMAC4_LPI_CTRL_STATUS_PLS;
+		value &= ~LPI_CTRL_STATUS_PLS;
 
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
@@ -433,12 +433,12 @@ static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, u32 et)
 
 	/* Enable/disable LPI entry timer */
 	regval = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	regval |= GMAC4_LPI_CTRL_STATUS_LPIEN | GMAC4_LPI_CTRL_STATUS_LPITXA;
+	regval |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
 
 	if (et)
-		regval |= GMAC4_LPI_CTRL_STATUS_LPIATE;
+		regval |= LPI_CTRL_STATUS_LPIATE;
 	else
-		regval &= ~GMAC4_LPI_CTRL_STATUS_LPIATE;
+		regval &= ~LPI_CTRL_STATUS_LPIATE;
 
 	writel(regval, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
@@ -851,17 +851,17 @@ static int dwmac4_irq_status(struct mac_device_info *hw,
 		/* Clear LPI interrupt by reading MAC_LPI_Control_Status */
 		u32 status = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
 
-		if (status & GMAC4_LPI_CTRL_STATUS_TLPIEN) {
+		if (status & LPI_CTRL_STATUS_TLPIEN) {
 			ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE;
 			x->irq_tx_path_in_lpi_mode_n++;
 		}
-		if (status & GMAC4_LPI_CTRL_STATUS_TLPIEX) {
+		if (status & LPI_CTRL_STATUS_TLPIEX) {
 			ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE;
 			x->irq_tx_path_exit_lpi_mode_n++;
 		}
-		if (status & GMAC4_LPI_CTRL_STATUS_RLPIEN)
+		if (status & LPI_CTRL_STATUS_RLPIEN)
 			x->irq_rx_path_in_lpi_mode_n++;
-		if (status & GMAC4_LPI_CTRL_STATUS_RLPIEX)
+		if (status & LPI_CTRL_STATUS_RLPIEX)
 			x->irq_rx_path_exit_lpi_mode_n++;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
index 20027d3c25a79..a03f5d7715663 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h
@@ -112,14 +112,7 @@
 #define XGMAC_MGKPKTEN			BIT(1)
 #define XGMAC_PWRDWN			BIT(0)
 #define XGMAC_LPI_CTRL			0x000000d0
-#define XGMAC_TXCGE			BIT(21)
-#define XGMAC_LPITXA			BIT(19)
-#define XGMAC_PLS			BIT(17)
-#define XGMAC_LPITXEN			BIT(16)
-#define XGMAC_RLPIEX			BIT(3)
-#define XGMAC_RLPIEN			BIT(2)
-#define XGMAC_TLPIEX			BIT(1)
-#define XGMAC_TLPIEN			BIT(0)
+/* For definitions, see LPI_CTRL_STATUS_xxx in common.h */
 #define XGMAC_LPI_TIMER_CTRL		0x000000d4
 #define XGMAC_HW_FEATURE0		0x0000011c
 #define XGMAC_HWFEAT_EDMA		BIT(31)
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 9a60a6e8f6331..19cfb1dcb3324 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -316,17 +316,17 @@ static int dwxgmac2_host_irq_status(struct mac_device_info *hw,
 	if (stat & XGMAC_LPIIS) {
 		u32 lpi = readl(ioaddr + XGMAC_LPI_CTRL);
 
-		if (lpi & XGMAC_TLPIEN) {
+		if (lpi & LPI_CTRL_STATUS_TLPIEN) {
 			ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE;
 			x->irq_tx_path_in_lpi_mode_n++;
 		}
-		if (lpi & XGMAC_TLPIEX) {
+		if (lpi & LPI_CTRL_STATUS_TLPIEX) {
 			ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE;
 			x->irq_tx_path_exit_lpi_mode_n++;
 		}
-		if (lpi & XGMAC_RLPIEN)
+		if (lpi & LPI_CTRL_STATUS_RLPIEN)
 			x->irq_rx_path_in_lpi_mode_n++;
-		if (lpi & XGMAC_RLPIEX)
+		if (lpi & LPI_CTRL_STATUS_RLPIEX)
 			x->irq_rx_path_exit_lpi_mode_n++;
 	}
 
@@ -433,9 +433,9 @@ static void dwxgmac2_set_eee_mode(struct mac_device_info *hw,
 
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
 
-	value |= XGMAC_LPITXEN | XGMAC_LPITXA;
+	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
 	if (en_tx_lpi_clockgating)
-		value |= XGMAC_TXCGE;
+		value |= LPI_CTRL_STATUS_LPITCSE;
 
 	writel(value, ioaddr + XGMAC_LPI_CTRL);
 }
@@ -446,7 +446,7 @@ static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw)
 	u32 value;
 
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
-	value &= ~(XGMAC_LPITXEN | XGMAC_LPITXA | XGMAC_TXCGE);
+	value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA | LPI_CTRL_STATUS_LPITCSE);
 	writel(value, ioaddr + XGMAC_LPI_CTRL);
 }
 
@@ -457,9 +457,9 @@ static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link)
 
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
 	if (link)
-		value |= XGMAC_PLS;
+		value |= LPI_CTRL_STATUS_PLS;
 	else
-		value &= ~XGMAC_PLS;
+		value &= ~LPI_CTRL_STATUS_PLS;
 	writel(value, ioaddr + XGMAC_LPI_CTRL);
 }
 

From 395c92c0fe3ee69b2b126a44511a08b032810ebf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:36 +0000
Subject: [PATCH 0233/2753] net: stmmac: add new MAC method set_lpi_mode()

Add a new method to control LPI mode configuration. This is architected
to have three configuration states: LPI disabled, LPI forced (active),
or LPI under hardware timer control. This reflects the three modes
which the main body of the driver wishes to deal with.

We pass in whether transmit clock gating should be used, and the
hardware timer value in microseconds to be set when using hardware
timer control.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffds-003ZIT-E8@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac1000_core.c  | 33 ++++----
 .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 83 +++++++++++--------
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 36 +++++---
 drivers/net/ethernet/stmicro/stmmac/hwif.h    | 11 +++
 4 files changed, 102 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 96bcda0856ec6..622f5ef241d48 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -342,31 +342,35 @@ static int dwmac1000_irq_status(struct mac_device_info *hw,
 	return ret;
 }
 
-static void dwmac1000_set_eee_mode(struct mac_device_info *hw,
-				   bool en_tx_lpi_clockgating)
+static int dwmac1000_set_lpi_mode(struct mac_device_info *hw,
+				  enum stmmac_lpi_mode mode,
+				  bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
 
-	/*TODO - en_tx_lpi_clockgating treatment */
+	if (mode == STMMAC_LPI_TIMER)
+		return -EOPNOTSUPP;
 
-	/* Enable the link status receive on RGMII, SGMII ore SMII
-	 * receive path and instruct the transmit to enter in LPI
-	 * state.
-	 */
 	value = readl(ioaddr + LPI_CTRL_STATUS);
-	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+	if (mode == STMMAC_LPI_FORCED)
+		value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+	else
+		value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
 	writel(value, ioaddr + LPI_CTRL_STATUS);
+
+	return 0;
 }
 
-static void dwmac1000_reset_eee_mode(struct mac_device_info *hw)
+static void dwmac1000_set_eee_mode(struct mac_device_info *hw,
+				   bool en_tx_lpi_clockgating)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
+	dwmac1000_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
+}
 
-	value = readl(ioaddr + LPI_CTRL_STATUS);
-	value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA);
-	writel(value, ioaddr + LPI_CTRL_STATUS);
+static void dwmac1000_reset_eee_mode(struct mac_device_info *hw)
+{
+	dwmac1000_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
 }
 
 static void dwmac1000_set_eee_pls(struct mac_device_info *hw, int link)
@@ -509,6 +513,7 @@ const struct stmmac_ops dwmac1000_ops = {
 	.pmt = dwmac1000_pmt,
 	.set_umac_addr = dwmac1000_set_umac_addr,
 	.get_umac_addr = dwmac1000_get_umac_addr,
+	.set_lpi_mode = dwmac1000_set_lpi_mode,
 	.set_eee_mode = dwmac1000_set_eee_mode,
 	.reset_eee_mode = dwmac1000_reset_eee_mode,
 	.set_eee_timer = dwmac1000_set_eee_timer,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index c324aaf691e0d..dc2d8c096fa3b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -376,35 +376,61 @@ static void dwmac4_get_umac_addr(struct mac_device_info *hw,
 				   GMAC_ADDR_LOW(reg_n));
 }
 
-static void dwmac4_set_eee_mode(struct mac_device_info *hw,
-				bool en_tx_lpi_clockgating)
+static int dwmac4_set_lpi_mode(struct mac_device_info *hw,
+			       enum stmmac_lpi_mode mode,
+			       bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
+	u32 value, mask;
+
+	if (mode == STMMAC_LPI_DISABLE) {
+		value = 0;
+	} else {
+		value = LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+
+		if (mode == STMMAC_LPI_TIMER) {
+			/* Return ERANGE if the timer is larger than the
+			 * register field.
+			 */
+			if (et > STMMAC_ET_MAX)
+				return -ERANGE;
+
+			/* Set the hardware LPI entry timer */
+			writel(et, ioaddr + GMAC4_LPI_ENTRY_TIMER);
+
+			/* Interpret a zero LPI entry timer to mean
+			 * immediate entry into LPI mode.
+			 */
+			if (et)
+				value |= LPI_CTRL_STATUS_LPIATE;
+		}
+
+		if (en_tx_lpi_clockgating)
+			value |= LPI_CTRL_STATUS_LPITCSE;
+	}
+
+	mask = LPI_CTRL_STATUS_LPIATE | LPI_CTRL_STATUS_LPIEN |
+	       LPI_CTRL_STATUS_LPITXA;
+
+	value |= readl(ioaddr + GMAC4_LPI_CTRL_STATUS) & ~mask;
+	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
+
+	return 0;
+}
 
+static void dwmac4_set_eee_mode(struct mac_device_info *hw,
+				bool en_tx_lpi_clockgating)
+{
 	/* Enable the link status receive on RGMII, SGMII ore SMII
 	 * receive path and instruct the transmit to enter in LPI
 	 * state.
 	 */
-	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~LPI_CTRL_STATUS_LPIATE;
-	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
-
-	if (en_tx_lpi_clockgating)
-		value |= LPI_CTRL_STATUS_LPITCSE;
-
-	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
+	dwmac4_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
 }
 
 static void dwmac4_reset_eee_mode(struct mac_device_info *hw)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	value &= ~(LPI_CTRL_STATUS_LPIATE | LPI_CTRL_STATUS_LPIEN |
-		   LPI_CTRL_STATUS_LPITXA);
-	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
+	dwmac4_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
 }
 
 static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
@@ -424,23 +450,7 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
 
 static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, u32 et)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value = et & STMMAC_ET_MAX;
-	int regval;
-
-	/* Program LPI entry timer value into register */
-	writel(value, ioaddr + GMAC4_LPI_ENTRY_TIMER);
-
-	/* Enable/disable LPI entry timer */
-	regval = readl(ioaddr + GMAC4_LPI_CTRL_STATUS);
-	regval |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
-
-	if (et)
-		regval |= LPI_CTRL_STATUS_LPIATE;
-	else
-		regval &= ~LPI_CTRL_STATUS_LPIATE;
-
-	writel(regval, ioaddr + GMAC4_LPI_CTRL_STATUS);
+	dwmac4_set_lpi_mode(hw, STMMAC_LPI_TIMER, false, et & STMMAC_ET_MAX);
 }
 
 static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
@@ -1203,6 +1213,7 @@ const struct stmmac_ops dwmac4_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_mode = dwmac4_set_eee_mode,
 	.reset_eee_mode = dwmac4_reset_eee_mode,
 	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
@@ -1247,6 +1258,7 @@ const struct stmmac_ops dwmac410_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_mode = dwmac4_set_eee_mode,
 	.reset_eee_mode = dwmac4_reset_eee_mode,
 	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
@@ -1293,6 +1305,7 @@ const struct stmmac_ops dwmac510_ops = {
 	.pmt = dwmac4_pmt,
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
+	.set_lpi_mode = dwmac4_set_lpi_mode,
 	.set_eee_mode = dwmac4_set_eee_mode,
 	.reset_eee_mode = dwmac4_reset_eee_mode,
 	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 19cfb1dcb3324..51c37a1180ac0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -425,29 +425,39 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw,
 	addr[5] = (hi_addr >> 8) & 0xff;
 }
 
-static void dwxgmac2_set_eee_mode(struct mac_device_info *hw,
-				  bool en_tx_lpi_clockgating)
+static int dwxgmac2_set_lpi_mode(struct mac_device_info *hw,
+				 enum stmmac_lpi_mode mode,
+				 bool en_tx_lpi_clockgating, u32 et)
 {
 	void __iomem *ioaddr = hw->pcsr;
 	u32 value;
 
+	if (mode == STMMAC_LPI_TIMER)
+		return -EOPNOTSUPP;
+
 	value = readl(ioaddr + XGMAC_LPI_CTRL);
+	if (mode == STMMAC_LPI_FORCED) {
+		value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
+		if (en_tx_lpi_clockgating)
+			value |= LPI_CTRL_STATUS_LPITCSE;
+	} else {
+		value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA |
+			   LPI_CTRL_STATUS_LPITCSE);
+	}
+	writel(value, ioaddr + XGMAC_LPI_CTRL);
 
-	value |= LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA;
-	if (en_tx_lpi_clockgating)
-		value |= LPI_CTRL_STATUS_LPITCSE;
+	return 0;
+}
 
-	writel(value, ioaddr + XGMAC_LPI_CTRL);
+static void dwxgmac2_set_eee_mode(struct mac_device_info *hw,
+				  bool en_tx_lpi_clockgating)
+{
+	dwxgmac2_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
 }
 
 static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw)
 {
-	void __iomem *ioaddr = hw->pcsr;
-	u32 value;
-
-	value = readl(ioaddr + XGMAC_LPI_CTRL);
-	value &= ~(LPI_CTRL_STATUS_LPIEN | LPI_CTRL_STATUS_LPITXA | LPI_CTRL_STATUS_LPITCSE);
-	writel(value, ioaddr + XGMAC_LPI_CTRL);
+	dwxgmac2_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
 }
 
 static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link)
@@ -1525,6 +1535,7 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.pmt = dwxgmac2_pmt,
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
+	.set_lpi_mode = dwxgmac2_set_lpi_mode,
 	.set_eee_mode = dwxgmac2_set_eee_mode,
 	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
@@ -1582,6 +1593,7 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.pmt = dwxgmac2_pmt,
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
+	.set_lpi_mode = dwxgmac2_set_lpi_mode,
 	.set_eee_mode = dwxgmac2_set_eee_mode,
 	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 0f200b72c2250..7279d30d6a8b4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -306,6 +306,12 @@ struct stmmac_pps_cfg;
 struct stmmac_rss;
 struct stmmac_est;
 
+enum stmmac_lpi_mode {
+	STMMAC_LPI_DISABLE,
+	STMMAC_LPI_FORCED,
+	STMMAC_LPI_TIMER,
+};
+
 /* Helpers to program the MAC core */
 struct stmmac_ops {
 	/* MAC core initialization */
@@ -360,6 +366,9 @@ struct stmmac_ops {
 			      unsigned int reg_n);
 	void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr,
 			      unsigned int reg_n);
+	int (*set_lpi_mode)(struct mac_device_info *hw,
+			    enum stmmac_lpi_mode mode,
+			    bool en_tx_lpi_clockgating, u32 et);
 	void (*set_eee_mode)(struct mac_device_info *hw,
 			     bool en_tx_lpi_clockgating);
 	void (*reset_eee_mode)(struct mac_device_info *hw);
@@ -467,6 +476,8 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, set_umac_addr, __args)
 #define stmmac_get_umac_addr(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, get_umac_addr, __args)
+#define stmmac_set_lpi_mode(__priv, __args...) \
+	stmmac_do_callback(__priv, mac, set_lpi_mode, __args)
 #define stmmac_set_eee_mode(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_eee_mode, __args)
 #define stmmac_reset_eee_mode(__priv, __args...) \

From a323ed92e40e8e7220486f7e5a4cccf6666783fd Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:41 +0000
Subject: [PATCH 0234/2753] net: stmmac: dwmac4: clear LPI_CTRL_STATUS_LPITCSE
 too

Ensure that LPI_CTRL_STATUS_LPITCSE is also appropriately cleared when
disabling LPI or enabling LPI without TX clock gating.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffdx-003ZIZ-JQ@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index dc2d8c096fa3b..ed42e1477cf86 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -410,7 +410,7 @@ static int dwmac4_set_lpi_mode(struct mac_device_info *hw,
 	}
 
 	mask = LPI_CTRL_STATUS_LPIATE | LPI_CTRL_STATUS_LPIEN |
-	       LPI_CTRL_STATUS_LPITXA;
+	       LPI_CTRL_STATUS_LPITXA | LPI_CTRL_STATUS_LPITCSE;
 
 	value |= readl(ioaddr + GMAC4_LPI_CTRL_STATUS) & ~mask;
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);

From 305a0f68cfbf6b6d264557e9e5f8554a3622d5f4 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:46 +0000
Subject: [PATCH 0235/2753] net: stmmac: use stmmac_set_lpi_mode()

Use the new stmmac_set_lpi_mode() API to configure the parameters of
the desired LPI mode rather than the older methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffe2-003ZIg-Mx@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 29 ++++++++++---------
 1 file changed, 15 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 5890a21d1ef9e..3b77597ada522 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -390,11 +390,6 @@ static inline u32 stmmac_rx_dirty(struct stmmac_priv *priv, u32 queue)
 	return dirty;
 }
 
-static void stmmac_enable_hw_lpi_timer(struct stmmac_priv *priv)
-{
-	stmmac_set_eee_lpi_timer(priv, priv->hw, priv->tx_lpi_timer);
-}
-
 static bool stmmac_eee_tx_busy(struct stmmac_priv *priv)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
@@ -431,8 +426,9 @@ static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv)
 
 	/* Check and enter in LPI mode */
 	if (!priv->tx_path_in_lpi_mode)
-		stmmac_set_eee_mode(priv, priv->hw,
-			priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING);
+		stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_FORCED,
+			priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING,
+			0);
 }
 
 /**
@@ -443,7 +439,7 @@ static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv)
 static void stmmac_stop_sw_lpi(struct stmmac_priv *priv)
 {
 	del_timer_sync(&priv->eee_ctrl_timer);
-	stmmac_reset_eee_mode(priv, priv->hw);
+	stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_DISABLE, false, 0);
 	priv->tx_path_in_lpi_mode = false;
 }
 
@@ -1046,7 +1042,7 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 	netdev_dbg(priv->dev, "disable EEE\n");
 	priv->eee_sw_timer_en = false;
 	del_timer_sync(&priv->eee_ctrl_timer);
-	stmmac_reset_eee_mode(priv, priv->hw);
+	stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_DISABLE, false, 0);
 	priv->tx_path_in_lpi_mode = false;
 
 	stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
@@ -1061,6 +1057,7 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 				    bool tx_clk_stop)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	int ret;
 
 	priv->tx_lpi_timer = timer;
 	priv->eee_active = true;
@@ -1075,11 +1072,15 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,
 				true);
 
-	if (priv->plat->has_gmac4 && priv->tx_lpi_timer <= STMMAC_ET_MAX) {
-		/* Use hardware LPI mode */
-		stmmac_enable_hw_lpi_timer(priv);
-	} else {
-		/* Use software LPI mode */
+	/* Try to cnfigure the hardware timer. */
+	ret = stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_TIMER,
+				  priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING,
+				  priv->tx_lpi_timer);
+
+	if (ret) {
+		/* Hardware timer mode not supported, or value out of range.
+		 * Fall back to using software LPI mode
+		 */
 		priv->eee_sw_timer_en = true;
 		stmmac_restart_sw_lpi_timer(priv);
 	}

From 62b0a039cac249813d2cbb97c260f018a50f3aaf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Feb 2025 13:40:51 +0000
Subject: [PATCH 0236/2753] net: stmmac: remove old EEE methods

As we no longer call the set_eee_mode(), reset_eee_mode() and
set_eee_lpi_entry_timer() methods, remove these and their glue in
common.h

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tffe7-003ZIm-Qv@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac1000_core.c  | 13 ---------
 .../net/ethernet/stmicro/stmmac/dwmac4_core.c | 29 -------------------
 .../ethernet/stmicro/stmmac/dwxgmac2_core.c   | 15 ----------
 drivers/net/ethernet/stmicro/stmmac/hwif.h    | 10 -------
 4 files changed, 67 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 622f5ef241d48..7900bf3effa71 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -362,17 +362,6 @@ static int dwmac1000_set_lpi_mode(struct mac_device_info *hw,
 	return 0;
 }
 
-static void dwmac1000_set_eee_mode(struct mac_device_info *hw,
-				   bool en_tx_lpi_clockgating)
-{
-	dwmac1000_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
-}
-
-static void dwmac1000_reset_eee_mode(struct mac_device_info *hw)
-{
-	dwmac1000_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
-}
-
 static void dwmac1000_set_eee_pls(struct mac_device_info *hw, int link)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -514,8 +503,6 @@ const struct stmmac_ops dwmac1000_ops = {
 	.set_umac_addr = dwmac1000_set_umac_addr,
 	.get_umac_addr = dwmac1000_get_umac_addr,
 	.set_lpi_mode = dwmac1000_set_lpi_mode,
-	.set_eee_mode = dwmac1000_set_eee_mode,
-	.reset_eee_mode = dwmac1000_reset_eee_mode,
 	.set_eee_timer = dwmac1000_set_eee_timer,
 	.set_eee_pls = dwmac1000_set_eee_pls,
 	.debug = dwmac1000_debug,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
index ed42e1477cf86..cc4ddf608652c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
@@ -418,21 +418,6 @@ static int dwmac4_set_lpi_mode(struct mac_device_info *hw,
 	return 0;
 }
 
-static void dwmac4_set_eee_mode(struct mac_device_info *hw,
-				bool en_tx_lpi_clockgating)
-{
-	/* Enable the link status receive on RGMII, SGMII ore SMII
-	 * receive path and instruct the transmit to enter in LPI
-	 * state.
-	 */
-	dwmac4_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
-}
-
-static void dwmac4_reset_eee_mode(struct mac_device_info *hw)
-{
-	dwmac4_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
-}
-
 static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -448,11 +433,6 @@ static void dwmac4_set_eee_pls(struct mac_device_info *hw, int link)
 	writel(value, ioaddr + GMAC4_LPI_CTRL_STATUS);
 }
 
-static void dwmac4_set_eee_lpi_entry_timer(struct mac_device_info *hw, u32 et)
-{
-	dwmac4_set_lpi_mode(hw, STMMAC_LPI_TIMER, false, et & STMMAC_ET_MAX);
-}
-
 static void dwmac4_set_eee_timer(struct mac_device_info *hw, int ls, int tw)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -1214,9 +1194,6 @@ const struct stmmac_ops dwmac4_ops = {
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
 	.set_lpi_mode = dwmac4_set_lpi_mode,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
@@ -1259,9 +1236,6 @@ const struct stmmac_ops dwmac410_ops = {
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
 	.set_lpi_mode = dwmac4_set_lpi_mode,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
@@ -1306,9 +1280,6 @@ const struct stmmac_ops dwmac510_ops = {
 	.set_umac_addr = dwmac4_set_umac_addr,
 	.get_umac_addr = dwmac4_get_umac_addr,
 	.set_lpi_mode = dwmac4_set_lpi_mode,
-	.set_eee_mode = dwmac4_set_eee_mode,
-	.reset_eee_mode = dwmac4_reset_eee_mode,
-	.set_eee_lpi_entry_timer = dwmac4_set_eee_lpi_entry_timer,
 	.set_eee_timer = dwmac4_set_eee_timer,
 	.set_eee_pls = dwmac4_set_eee_pls,
 	.pcs_ctrl_ane = dwmac4_ctrl_ane,
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
index 51c37a1180ac0..a6d395c6bacd1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
@@ -449,17 +449,6 @@ static int dwxgmac2_set_lpi_mode(struct mac_device_info *hw,
 	return 0;
 }
 
-static void dwxgmac2_set_eee_mode(struct mac_device_info *hw,
-				  bool en_tx_lpi_clockgating)
-{
-	dwxgmac2_set_lpi_mode(hw, STMMAC_LPI_FORCED, en_tx_lpi_clockgating, 0);
-}
-
-static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw)
-{
-	dwxgmac2_set_lpi_mode(hw, STMMAC_LPI_DISABLE, false, 0);
-}
-
 static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link)
 {
 	void __iomem *ioaddr = hw->pcsr;
@@ -1536,8 +1525,6 @@ const struct stmmac_ops dwxgmac210_ops = {
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
 	.set_lpi_mode = dwxgmac2_set_lpi_mode,
-	.set_eee_mode = dwxgmac2_set_eee_mode,
-	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
 	.debug = NULL,
@@ -1594,8 +1581,6 @@ const struct stmmac_ops dwxlgmac2_ops = {
 	.set_umac_addr = dwxgmac2_set_umac_addr,
 	.get_umac_addr = dwxgmac2_get_umac_addr,
 	.set_lpi_mode = dwxgmac2_set_lpi_mode,
-	.set_eee_mode = dwxgmac2_set_eee_mode,
-	.reset_eee_mode = dwxgmac2_reset_eee_mode,
 	.set_eee_timer = dwxgmac2_set_eee_timer,
 	.set_eee_pls = dwxgmac2_set_eee_pls,
 	.debug = NULL,
diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
index 7279d30d6a8b4..27c63a9fc163d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
+++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
@@ -369,10 +369,6 @@ struct stmmac_ops {
 	int (*set_lpi_mode)(struct mac_device_info *hw,
 			    enum stmmac_lpi_mode mode,
 			    bool en_tx_lpi_clockgating, u32 et);
-	void (*set_eee_mode)(struct mac_device_info *hw,
-			     bool en_tx_lpi_clockgating);
-	void (*reset_eee_mode)(struct mac_device_info *hw);
-	void (*set_eee_lpi_entry_timer)(struct mac_device_info *hw, u32 et);
 	void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw);
 	void (*set_eee_pls)(struct mac_device_info *hw, int link);
 	void (*debug)(struct stmmac_priv *priv, void __iomem *ioaddr,
@@ -478,12 +474,6 @@ struct stmmac_ops {
 	stmmac_do_void_callback(__priv, mac, get_umac_addr, __args)
 #define stmmac_set_lpi_mode(__priv, __args...) \
 	stmmac_do_callback(__priv, mac, set_lpi_mode, __args)
-#define stmmac_set_eee_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_eee_mode, __args)
-#define stmmac_reset_eee_mode(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, reset_eee_mode, __args)
-#define stmmac_set_eee_lpi_timer(__priv, __args...) \
-	stmmac_do_void_callback(__priv, mac, set_eee_lpi_entry_timer, __args)
 #define stmmac_set_eee_timer(__priv, __args...) \
 	stmmac_do_void_callback(__priv, mac, set_eee_timer, __args)
 #define stmmac_set_eee_pls(__priv, __args...) \

From 7bca2b2d5fcc685b81eb32fe564689eca6a59a99 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 5 Feb 2025 17:12:09 +0100
Subject: [PATCH 0237/2753] net: renesas: rswitch: Convert to
 for_each_available_child_of_node()

Simplify rswitch_get_port_node() by using the
for_each_available_child_of_node() helper instead of manually ignoring
unavailable child nodes, and leaking a reference.

Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/54f544d573a64b96e01fd00d3481b10806f4d110.1738771798.git.geert+renesas@glider.be
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rswitch.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/renesas/rswitch.c b/drivers/net/ethernet/renesas/rswitch.c
index 84d09a8973b78..aba772e14555d 100644
--- a/drivers/net/ethernet/renesas/rswitch.c
+++ b/drivers/net/ethernet/renesas/rswitch.c
@@ -1287,17 +1287,14 @@ static struct device_node *rswitch_get_port_node(struct rswitch_device *rdev)
 	if (!ports)
 		return NULL;
 
-	for_each_child_of_node(ports, port) {
+	for_each_available_child_of_node(ports, port) {
 		err = of_property_read_u32(port, "reg", &index);
 		if (err < 0) {
 			port = NULL;
 			goto out;
 		}
-		if (index == rdev->etha->index) {
-			if (!of_device_is_available(port))
-				port = NULL;
+		if (index == rdev->etha->index)
 			break;
-		}
 	}
 
 out:

From 9dba9a45f8ca64a7df32aada14c20a3153af1ac8 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Wed, 5 Feb 2025 18:16:46 +0100
Subject: [PATCH 0238/2753] net: usb: qmi_wwan: add Telit Cinterion FN990B
 composition

Add the following Telit Cinterion FN990B composition:

0x10d0: rmnet + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 17 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10d0 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FN990
S:  SerialNumber=43b38f19
C:  #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=usbfs
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250205171649.618162-3-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index e9208a8d2bfa6..7548ac187c267 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1368,6 +1368,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c0, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c4, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c8, 0)}, /* Telit FE910C04 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10d0, 0)}, /* Telit FN990B */
 	{QMI_FIXED_INTF(0x1bc7, 0x1100, 3)},	/* Telit ME910 */
 	{QMI_FIXED_INTF(0x1bc7, 0x1101, 3)},	/* Telit ME910 dual modem */
 	{QMI_FIXED_INTF(0x1bc7, 0x1200, 5)},	/* Telit LE920 */

From ad1664fb699006f552dceeba331ef1e8874309a8 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Wed, 5 Feb 2025 18:16:48 +0100
Subject: [PATCH 0239/2753] net: usb: qmi_wwan: fix Telit Cinterion FN990A name

The correct name for FN990 is FN990A so use it in order to avoid
confusion with FN990B.

Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250205171649.618162-5-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 7548ac187c267..14d1c85c80004 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1360,7 +1360,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1050, 2)},	/* Telit FN980 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1057, 2)},	/* Telit FN980 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)},	/* Telit LN920 */
-	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */

From 9e5ac98829d90a830b5e37c6c62b25f91f39557f Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Wed, 5 Feb 2025 18:16:49 +0100
Subject: [PATCH 0240/2753] net: usb: cdc_mbim: fix Telit Cinterion FN990A name

The correct name for FN990 is FN990A so use it in order to avoid
confusion with FN990B.

Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250205171649.618162-6-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_mbim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index e13e4920ee9b2..88921c13b6294 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -660,7 +660,7 @@ static const struct usb_device_id mbim_devs[] = {
 	  .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle,
 	},
 
-	/* Telit FN990 */
+	/* Telit FN990A */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x1071, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle,
 	},

From 6a0ca73e5144a5d1c1f84cbfd96f4bc656c2ae6c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 6 Feb 2025 23:06:07 +0100
Subject: [PATCH 0241/2753] net: gianfar: simplify init_phy()

Use phy_set_max_speed() to simplify init_phy().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/b863dcf7-31e8-45a1-a284-7075da958ff0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/gianfar.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index 435138f4699d2..deb35b38c9766 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1647,20 +1647,11 @@ static void gfar_configure_serdes(struct net_device *dev)
  */
 static int init_phy(struct net_device *dev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct gfar_private *priv = netdev_priv(dev);
 	phy_interface_t interface = priv->interface;
 	struct phy_device *phydev;
 	struct ethtool_keee edata;
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT)
-		linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask);
-
 	priv->oldlink = 0;
 	priv->oldspeed = 0;
 	priv->oldduplex = -1;
@@ -1675,9 +1666,8 @@ static int init_phy(struct net_device *dev)
 	if (interface == PHY_INTERFACE_MODE_SGMII)
 		gfar_configure_serdes(dev);
 
-	/* Remove any features not supported by the controller */
-	linkmode_and(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT))
+		phy_set_max_speed(phydev, SPEED_100);
 
 	/* Add support for flow control */
 	phy_support_asym_pause(phydev);

From 1eb824d69f8d88405e4e80c568e8f07080309fb0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 14:56:35 -0800
Subject: [PATCH 0242/2753] net: refactor netdev_rx_queue_restart() to use
 local qops

Shorten the lines by storing dev->queue_mgmt_ops in a temp variable.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250206225638.1387810-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netdev_rx_queue.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index db46880f37ccf..d421abe06c030 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -10,28 +10,27 @@
 int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 {
 	struct netdev_rx_queue *rxq = __netif_get_rx_queue(dev, rxq_idx);
+	const struct netdev_queue_mgmt_ops *qops = dev->queue_mgmt_ops;
 	void *new_mem, *old_mem;
 	int err;
 
-	if (!dev->queue_mgmt_ops || !dev->queue_mgmt_ops->ndo_queue_stop ||
-	    !dev->queue_mgmt_ops->ndo_queue_mem_free ||
-	    !dev->queue_mgmt_ops->ndo_queue_mem_alloc ||
-	    !dev->queue_mgmt_ops->ndo_queue_start)
+	if (!qops || !qops->ndo_queue_stop || !qops->ndo_queue_mem_free ||
+	    !qops->ndo_queue_mem_alloc || !qops->ndo_queue_start)
 		return -EOPNOTSUPP;
 
 	ASSERT_RTNL();
 
-	new_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	new_mem = kvzalloc(qops->ndo_queue_mem_size, GFP_KERNEL);
 	if (!new_mem)
 		return -ENOMEM;
 
-	old_mem = kvzalloc(dev->queue_mgmt_ops->ndo_queue_mem_size, GFP_KERNEL);
+	old_mem = kvzalloc(qops->ndo_queue_mem_size, GFP_KERNEL);
 	if (!old_mem) {
 		err = -ENOMEM;
 		goto err_free_new_mem;
 	}
 
-	err = dev->queue_mgmt_ops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
+	err = qops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
 	if (err)
 		goto err_free_old_mem;
 
@@ -39,15 +38,15 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	if (err)
 		goto err_free_new_queue_mem;
 
-	err = dev->queue_mgmt_ops->ndo_queue_stop(dev, old_mem, rxq_idx);
+	err = qops->ndo_queue_stop(dev, old_mem, rxq_idx);
 	if (err)
 		goto err_free_new_queue_mem;
 
-	err = dev->queue_mgmt_ops->ndo_queue_start(dev, new_mem, rxq_idx);
+	err = qops->ndo_queue_start(dev, new_mem, rxq_idx);
 	if (err)
 		goto err_start_queue;
 
-	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+	qops->ndo_queue_mem_free(dev, old_mem);
 
 	kvfree(old_mem);
 	kvfree(new_mem);
@@ -62,15 +61,15 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	 * WARN if we fail to recover the old rx queue, and at least free
 	 * old_mem so we don't also leak that.
 	 */
-	if (dev->queue_mgmt_ops->ndo_queue_start(dev, old_mem, rxq_idx)) {
+	if (qops->ndo_queue_start(dev, old_mem, rxq_idx)) {
 		WARN(1,
 		     "Failed to restart old queue in error path. RX queue %d may be unhealthy.",
 		     rxq_idx);
-		dev->queue_mgmt_ops->ndo_queue_mem_free(dev, old_mem);
+		qops->ndo_queue_mem_free(dev, old_mem);
 	}
 
 err_free_new_queue_mem:
-	dev->queue_mgmt_ops->ndo_queue_mem_free(dev, new_mem);
+	qops->ndo_queue_mem_free(dev, new_mem);
 
 err_free_old_mem:
 	kvfree(old_mem);

From 3e7efc3f4f03bca0ea630c302e7c79cf807476bb Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 14:56:36 -0800
Subject: [PATCH 0243/2753] net: devmem: don't call queue stop / start when the
 interface is down

We seem to be missing a netif_running() check from the devmem
installation path. Starting a queue on a stopped device makes
no sense. We still want to be able to allocate the memory, just
to test that the device is indeed setting up the page pools
in a memory provider compatible way.

This is not a bug fix, because existing drivers check if
the interface is down as part of the ops. But new drivers
shouldn't have to do this, as long as they can correctly
alloc/free while down.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250206225638.1387810-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_queues.h |  4 ++++
 net/core/netdev_rx_queue.c  | 18 +++++++++++-------
 2 files changed, 15 insertions(+), 7 deletions(-)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index b02bb9f109d5e..73d3401261a62 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -117,6 +117,10 @@ struct netdev_stat_ops {
  *
  * @ndo_queue_stop:	Stop the RX queue at the specified index. The stopped
  *			queue's memory is written at the specified address.
+ *
+ * Note that @ndo_queue_mem_alloc and @ndo_queue_mem_free may be called while
+ * the interface is closed. @ndo_queue_start and @ndo_queue_stop will only
+ * be called for an interface which is open.
  */
 struct netdev_queue_mgmt_ops {
 	size_t			ndo_queue_mem_size;
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index d421abe06c030..ddd54e1e72897 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -38,13 +38,17 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	if (err)
 		goto err_free_new_queue_mem;
 
-	err = qops->ndo_queue_stop(dev, old_mem, rxq_idx);
-	if (err)
-		goto err_free_new_queue_mem;
-
-	err = qops->ndo_queue_start(dev, new_mem, rxq_idx);
-	if (err)
-		goto err_start_queue;
+	if (netif_running(dev)) {
+		err = qops->ndo_queue_stop(dev, old_mem, rxq_idx);
+		if (err)
+			goto err_free_new_queue_mem;
+
+		err = qops->ndo_queue_start(dev, new_mem, rxq_idx);
+		if (err)
+			goto err_start_queue;
+	} else {
+		swap(new_mem, old_mem);
+	}
 
 	qops->ndo_queue_mem_free(dev, old_mem);
 

From c1e00bc4be06cacee6307cedb9b55bbaddb5044d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 14:56:37 -0800
Subject: [PATCH 0244/2753] net: page_pool: avoid false positive warning if
 NAPI was never added

We expect NAPI to be in disabled state when page pool is torn down.
But it is also legal if the NAPI is completely uninitialized.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250206225638.1387810-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.h       | 12 ++++++++++++
 net/core/page_pool.c |  7 ++-----
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/core/dev.h b/net/core/dev.h
index a5b166bbd169a..caa13e431a6bc 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -299,6 +299,18 @@ void xdp_do_check_flushed(struct napi_struct *napi);
 static inline void xdp_do_check_flushed(struct napi_struct *napi) { }
 #endif
 
+/* Best effort check that NAPI is not idle (can't be scheduled to run) */
+static inline void napi_assert_will_not_race(const struct napi_struct *napi)
+{
+	/* uninitialized instance, can't race */
+	if (!napi->poll_list.next)
+		return;
+
+	/* SCHED bit is set on disabled instances */
+	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
+	WARN_ON(READ_ONCE(napi->list_owner) != -1);
+}
+
 void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu);
 
 #define XMIT_RECURSION_LIMIT	8
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 686bd4a117d93..1c6fec08bc434 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -26,6 +26,7 @@
 
 #include <trace/events/page_pool.h>
 
+#include "dev.h"
 #include "mp_dmabuf_devmem.h"
 #include "netmem_priv.h"
 #include "page_pool_priv.h"
@@ -1147,11 +1148,7 @@ void page_pool_disable_direct_recycling(struct page_pool *pool)
 	if (!pool->p.napi)
 		return;
 
-	/* To avoid races with recycling and additional barriers make sure
-	 * pool and NAPI are unlinked when NAPI is disabled.
-	 */
-	WARN_ON(!test_bit(NAPI_STATE_SCHED, &pool->p.napi->state));
-	WARN_ON(READ_ONCE(pool->p.napi->list_owner) != -1);
+	napi_assert_will_not_race(pool->p.napi);
 
 	mutex_lock(&page_pools_lock);
 	WRITE_ONCE(pool->p.napi, NULL);

From 285b3f78eabd951e59e98f01f86abaaa6c76cd44 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 14:56:38 -0800
Subject: [PATCH 0245/2753] netdevsim: allow normal queue reset while down

Resetting queues while the device is down should be legal.
Allow it, test it. Ideally we'd test this with a real device
supporting devmem but I don't have access to such devices.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250206225638.1387810-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c           | 10 ++++------
 tools/testing/selftests/net/nl_netdev.py | 18 +++++++++++++++++-
 2 files changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 42f247cbdceec..9b394ddc5206a 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -645,8 +645,11 @@ nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx)
 	if (ns->rq_reset_mode > 3)
 		return -EINVAL;
 
-	if (ns->rq_reset_mode == 1)
+	if (ns->rq_reset_mode == 1) {
+		if (!netif_running(ns->netdev))
+			return -ENETDOWN;
 		return nsim_create_page_pool(&qmem->pp, &ns->rq[idx]->napi);
+	}
 
 	qmem->rq = nsim_queue_alloc();
 	if (!qmem->rq)
@@ -754,11 +757,6 @@ nsim_qreset_write(struct file *file, const char __user *data,
 		return -EINVAL;
 
 	rtnl_lock();
-	if (!netif_running(ns->netdev)) {
-		ret = -ENETDOWN;
-		goto exit_unlock;
-	}
-
 	if (queue >= ns->netdev->real_num_rx_queues) {
 		ret = -EINVAL;
 		goto exit_unlock;
diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py
index 93e8cb671c3d9..beaee5e4e2aab 100755
--- a/tools/testing/selftests/net/nl_netdev.py
+++ b/tools/testing/selftests/net/nl_netdev.py
@@ -35,6 +35,21 @@ def napi_list_check(nf) -> None:
                         comment=f"queue count after reset queue {q} mode {i}")
 
 
+def nsim_rxq_reset_down(nf) -> None:
+    """
+    Test that the queue API supports resetting a queue
+    while the interface is down. We should convert this
+    test to testing real HW once more devices support
+    queue API.
+    """
+    with NetdevSimDev(queue_count=4) as nsimdev:
+        nsim = nsimdev.nsims[0]
+
+        ip(f"link set dev {nsim.ifname} down")
+        for i in [0, 2, 3]:
+            nsim.dfs_write("queue_reset", f"1 {i}")
+
+
 def page_pool_check(nf) -> None:
     with NetdevSimDev() as nsimdev:
         nsim = nsimdev.nsims[0]
@@ -106,7 +121,8 @@ def get_pp():
 
 def main() -> None:
     nf = NetdevFamily()
-    ksft_run([empty_check, lo_check, page_pool_check, napi_list_check],
+    ksft_run([empty_check, lo_check, page_pool_check, napi_list_check,
+              nsim_rxq_reset_down],
              args=(nf, ))
     ksft_exit()
 

From cc2c3540d9477a9931fb0fd851fcaeba524a5b35 Mon Sep 17 00:00:00 2001
From: Sam Winchenbach <swinchenbach@arka.org>
Date: Mon, 3 Feb 2025 13:34:34 +0000
Subject: [PATCH 0246/2753] iio: filter: admv8818: Force initialization of SDO

When a weak pull-up is present on the SDO line, regmap_update_bits fails
to write both the SOFTRESET and SDOACTIVE bits because it incorrectly
reads them as already set.

Since the soft reset disables the SDO line, performing a
read-modify-write operation on ADI_SPI_CONFIG_A to enable the SDO line
doesn't make sense. This change directly writes to the register instead
of using regmap_update_bits.

Fixes: f34fe888ad05 ("iio:filter:admv8818: add support for ADMV8818")
Signed-off-by: Sam Winchenbach <swinchenbach@arka.org>
Link: https://patch.msgid.link/SA1P110MB106904C961B0F3FAFFED74C0BCF5A@SA1P110MB1069.NAMP110.PROD.OUTLOOK.COM
Cc: <Stable@vger.kernel.org>
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/filter/admv8818.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/iio/filter/admv8818.c b/drivers/iio/filter/admv8818.c
index 848baa6e3bbf5..d85b7d3de8660 100644
--- a/drivers/iio/filter/admv8818.c
+++ b/drivers/iio/filter/admv8818.c
@@ -574,21 +574,15 @@ static int admv8818_init(struct admv8818_state *st)
 	struct spi_device *spi = st->spi;
 	unsigned int chip_id;
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SOFTRESET_N_MSK |
-				 ADMV8818_SOFTRESET_MSK,
-				 FIELD_PREP(ADMV8818_SOFTRESET_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SOFTRESET_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SOFTRESET_N_MSK | ADMV8818_SOFTRESET_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 Soft Reset failed.\n");
 		return ret;
 	}
 
-	ret = regmap_update_bits(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
-				 ADMV8818_SDOACTIVE_N_MSK |
-				 ADMV8818_SDOACTIVE_MSK,
-				 FIELD_PREP(ADMV8818_SDOACTIVE_N_MSK, 1) |
-				 FIELD_PREP(ADMV8818_SDOACTIVE_MSK, 1));
+	ret = regmap_write(st->regmap, ADMV8818_REG_SPI_CONFIG_A,
+			   ADMV8818_SDOACTIVE_N_MSK | ADMV8818_SDOACTIVE_MSK);
 	if (ret) {
 		dev_err(&spi->dev, "ADMV8818 SDO Enable failed.\n");
 		return ret;

From da8d493a80993972c427002684d0742560f3be4a Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Mon, 20 Jan 2025 16:10:00 +0100
Subject: [PATCH 0247/2753] firmware: qcom: uefisecapp: fix efivars
 registration race

Since the conversion to using the TZ allocator, the efivars service is
registered before the memory pool has been allocated, something which
can lead to a NULL-pointer dereference in case of a racing EFI variable
access.

Make sure that all resources have been set up before registering the
efivars.

Fixes: 6612103ec35a ("firmware: qcom: qseecom: convert to using the TZ allocator")
Cc: stable@vger.kernel.org	# 6.11
Cc: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Maximilian Luz <luzmaximilian@gmail.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/r/20250120151000.13870-1-johan+linaro@kernel.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 .../firmware/qcom/qcom_qseecom_uefisecapp.c    | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
index 447246bd04be3..98a463e9774bf 100644
--- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
@@ -814,15 +814,6 @@ static int qcom_uefisecapp_probe(struct auxiliary_device *aux_dev,
 
 	qcuefi->client = container_of(aux_dev, struct qseecom_client, aux_dev);
 
-	auxiliary_set_drvdata(aux_dev, qcuefi);
-	status = qcuefi_set_reference(qcuefi);
-	if (status)
-		return status;
-
-	status = efivars_register(&qcuefi->efivars, &qcom_efivar_ops);
-	if (status)
-		qcuefi_set_reference(NULL);
-
 	memset(&pool_config, 0, sizeof(pool_config));
 	pool_config.initial_size = SZ_4K;
 	pool_config.policy = QCOM_TZMEM_POLICY_MULTIPLIER;
@@ -833,6 +824,15 @@ static int qcom_uefisecapp_probe(struct auxiliary_device *aux_dev,
 	if (IS_ERR(qcuefi->mempool))
 		return PTR_ERR(qcuefi->mempool);
 
+	auxiliary_set_drvdata(aux_dev, qcuefi);
+	status = qcuefi_set_reference(qcuefi);
+	if (status)
+		return status;
+
+	status = efivars_register(&qcuefi->efivars, &qcom_efivar_ops);
+	if (status)
+		qcuefi_set_reference(NULL);
+
 	return status;
 }
 

From 548b0c5de7619ef53bbde5590700693f2f6d2a56 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 17:04:13 +0100
Subject: [PATCH 0248/2753] batman-adv: Ignore own maximum aggregation size
 during RX

An OGMv1 and OGMv2 packet receive processing were not only limited by the
number of bytes in the received packet but also by the nodes maximum
aggregation packet size limit. But this limit is relevant for TX and not
for RX. It must not be enforced by batadv_(i)v_ogm_aggr_packet to avoid
loss of information in case of a different limit for sender and receiver.

This has a minor side effect for B.A.T.M.A.N. IV because the
batadv_iv_ogm_aggr_packet is also used for the preprocessing for the TX.
But since the aggregation code itself will not allow more than
BATADV_MAX_AGGREGATION_BYTES bytes, this check was never triggering (in
this context) prior of removing it.

Cc: stable@vger.kernel.org
Fixes: c6c8fea29769 ("net: Add batman-adv meshing protocol")
Fixes: 9323158ef9f4 ("batman-adv: OGMv2 - implement originators logic")
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 3 +--
 net/batman-adv/bat_v_ogm.c  | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 07ae5dd1f150b..b12645949ae5a 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -325,8 +325,7 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
 	/* check if there is enough space for the optional TVLV */
 	next_buff_pos += ntohs(ogm_packet->tvlv_len);
 
-	return (next_buff_pos <= packet_len) &&
-	       (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
+	return next_buff_pos <= packet_len;
 }
 
 /* send a batman ogm to a given interface */
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index e503ee0d896bd..8f89ffe6020ce 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -839,8 +839,7 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
 	/* check if there is enough space for the optional TVLV */
 	next_buff_pos += ntohs(ogm2_packet->tvlv_len);
 
-	return (next_buff_pos <= packet_len) &&
-	       (next_buff_pos <= BATADV_MAX_AGGREGATION_BYTES);
+	return next_buff_pos <= packet_len;
 }
 
 /**

From ee9d1619ef6e4a3412a13788256cb8c3e5efbe3d Mon Sep 17 00:00:00 2001
From: Long Li <longli@microsoft.com>
Date: Fri, 7 Feb 2025 13:46:28 -0800
Subject: [PATCH 0249/2753] MAINTAINERS: update maintainer for Microsoft MANA
 RDMA driver

Ajay is no longer working on the MANA RDMA driver.

Konstantin Taranov has made significant contributions to implementing RC
QP in both kernel and user-mode.

He will take the responsibility of fixing bugs, reviewing patches and
developing new features for MANA RDMA driver.

Signed-off-by: Long Li <longli@microsoft.com>
Link: https://patch.msgid.link/1738964792-21140-1-git-send-email-longli@linuxonhyperv.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa0654..c51503268a026 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15689,7 +15689,7 @@ F:	include/uapi/linux/cciss*.h
 
 MICROSOFT MANA RDMA DRIVER
 M:	Long Li <longli@microsoft.com>
-M:	Ajay Sharma <sharmaajay@microsoft.com>
+M:	Konstantin Taranov <kotaranov@microsoft.com>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/mana/

From 9747c0c7791d4a5a62018a0c9c563dd2e6f6c1c0 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Sat, 8 Feb 2025 18:59:30 +0800
Subject: [PATCH 0250/2753] RDMA/hns: Fix mbox timing out by adding retry
 mechanism

If a QP is modified to error state and a flush CQE process is triggered,
the subsequent QP destruction mbox can still be successfully posted but
will be blocked in HW until the flush CQE process finishes. This causes
further mbox posting timeouts in driver. The blocking time is related
to QP depth. Considering an extreme case where SQ depth and RQ depth
are both 32K, the blocking time can reach about 135ms.

This patch adds a retry mechanism for mbox posting. For each try, FW
waits 15ms for HW to complete the previous mbox, otherwise return a
timeout error code to driver. Counting other time consumption in FW,
set 8 tries for mbox posting and a 5ms time gap before each retry to
increase to a sufficient timeout limit.

Fixes: 0425e3e6e0c7 ("RDMA/hns: Support flush cqe for hip08 in kernel space")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250208105930.522796-1-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 64 ++++++++++++++++------
 drivers/infiniband/hw/hns/hns_roce_hw_v2.h |  2 +
 2 files changed, 50 insertions(+), 16 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index dded339802b33..160e8927d364e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -1286,10 +1286,8 @@ static u32 hns_roce_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
 	return tx_timeout;
 }
 
-static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
+static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u32 tx_timeout)
 {
-	struct hns_roce_v2_priv *priv = hr_dev->priv;
-	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
 	u32 timeout = 0;
 
 	do {
@@ -1299,8 +1297,9 @@ static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
 	} while (++timeout < tx_timeout);
 }
 
-static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
-			       struct hns_roce_cmq_desc *desc, int num)
+static int __hns_roce_cmq_send_one(struct hns_roce_dev *hr_dev,
+				   struct hns_roce_cmq_desc *desc,
+				   int num, u32 tx_timeout)
 {
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
@@ -1309,8 +1308,6 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 	int ret;
 	int i;
 
-	spin_lock_bh(&csq->lock);
-
 	tail = csq->head;
 
 	for (i = 0; i < num; i++) {
@@ -1324,22 +1321,17 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 
 	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);
 
-	hns_roce_wait_csq_done(hr_dev, le16_to_cpu(desc->opcode));
+	hns_roce_wait_csq_done(hr_dev, tx_timeout);
 	if (hns_roce_cmq_csq_done(hr_dev)) {
 		ret = 0;
 		for (i = 0; i < num; i++) {
 			/* check the result of hardware write back */
-			desc[i] = csq->desc[tail++];
+			desc_ret = le16_to_cpu(csq->desc[tail++].retval);
 			if (tail == csq->desc_num)
 				tail = 0;
-
-			desc_ret = le16_to_cpu(desc[i].retval);
 			if (likely(desc_ret == CMD_EXEC_SUCCESS))
 				continue;
 
-			dev_err_ratelimited(hr_dev->dev,
-					    "Cmdq IO error, opcode = 0x%x, return = 0x%x.\n",
-					    desc->opcode, desc_ret);
 			ret = hns_roce_cmd_err_convert_errno(desc_ret);
 		}
 	} else {
@@ -1354,14 +1346,54 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 		ret = -EAGAIN;
 	}
 
-	spin_unlock_bh(&csq->lock);
-
 	if (ret)
 		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_ERR_CNT]);
 
 	return ret;
 }
 
+static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+			       struct hns_roce_cmq_desc *desc, int num)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
+	u16 opcode = le16_to_cpu(desc->opcode);
+	u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
+	u8 try_cnt = HNS_ROCE_OPC_POST_MB_TRY_CNT;
+	u32 rsv_tail;
+	int ret;
+	int i;
+
+	while (try_cnt) {
+		try_cnt--;
+
+		spin_lock_bh(&csq->lock);
+		rsv_tail = csq->head;
+		ret = __hns_roce_cmq_send_one(hr_dev, desc, num, tx_timeout);
+		if (opcode == HNS_ROCE_OPC_POST_MB && ret == -ETIME &&
+		    try_cnt) {
+			spin_unlock_bh(&csq->lock);
+			mdelay(HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC);
+			continue;
+		}
+
+		for (i = 0; i < num; i++) {
+			desc[i] = csq->desc[rsv_tail++];
+			if (rsv_tail == csq->desc_num)
+				rsv_tail = 0;
+		}
+		spin_unlock_bh(&csq->lock);
+		break;
+	}
+
+	if (ret)
+		dev_err_ratelimited(hr_dev->dev,
+				    "Cmdq IO error, opcode = 0x%x, return = %d.\n",
+				    opcode, ret);
+
+	return ret;
+}
+
 static int hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 			     struct hns_roce_cmq_desc *desc, int num)
 {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index cbdbc9edbce6e..91a5665465ffb 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -230,6 +230,8 @@ enum hns_roce_opcode_type {
 };
 
 #define HNS_ROCE_OPC_POST_MB_TIMEOUT 35000
+#define HNS_ROCE_OPC_POST_MB_TRY_CNT 8
+#define HNS_ROCE_OPC_POST_MB_RETRY_GAP_MSEC 5
 struct hns_roce_cmdq_tx_timeout_map {
 	u16 opcode;
 	u32 tx_timeout;

From d078f5857a00c06fa0ddee26d3cb722e938e1688 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 3 Feb 2025 15:29:08 +0800
Subject: [PATCH 0251/2753] wifi: rtw89: call power_on ahead before selecting
 firmware

Driver selects firmware by hardware version, which normally can be read
from registers before selecting firmware. However, certain chips such as
RTL8851B, it needs to read hardware version from efuse while doing
power_on, but do power_on after selecting firmware in current flow.

To resolve this flow problem, move power_on out from
rtw89_mac_partial_init(), and call rtw89_mac_pwr_on() separately at
proper places to have expected flow.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250203072911.47313-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c | 23 +++++++++++-------
 drivers/net/wireless/realtek/rtw89/mac.c  | 29 ++++++++++++++++-------
 drivers/net/wireless/realtek/rtw89/mac.h  |  1 +
 3 files changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index da41a417dd7d3..ad28f11f2d241 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -5040,8 +5040,6 @@ static int rtw89_chip_efuse_info_setup(struct rtw89_dev *rtwdev)
 
 	rtw89_hci_mac_pre_deinit(rtwdev);
 
-	rtw89_mac_pwr_off(rtwdev);
-
 	return 0;
 }
 
@@ -5122,36 +5120,45 @@ int rtw89_chip_info_setup(struct rtw89_dev *rtwdev)
 
 	rtw89_read_chip_ver(rtwdev);
 
+	ret = rtw89_mac_pwr_on(rtwdev);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to power on\n");
+		return ret;
+	}
+
 	ret = rtw89_wait_firmware_completion(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to wait firmware completion\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_fw_recognize(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to recognize firmware\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_chip_efuse_info_setup(rtwdev);
 	if (ret)
-		return ret;
+		goto out;
 
 	ret = rtw89_fw_recognize_elements(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to recognize firmware elements\n");
-		return ret;
+		goto out;
 	}
 
 	ret = rtw89_chip_board_info_setup(rtwdev);
 	if (ret)
-		return ret;
+		goto out;
 
 	rtw89_core_setup_rfe_parms(rtwdev);
 	rtwdev->ps_mode = rtw89_update_ps_mode(rtwdev);
 
-	return 0;
+out:
+	rtw89_mac_pwr_off(rtwdev);
+
+	return ret;
 }
 EXPORT_SYMBOL(rtw89_chip_info_setup);
 
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index f698807790ffc..3f38f8ed68760 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -1495,6 +1495,21 @@ static int rtw89_mac_power_switch(struct rtw89_dev *rtwdev, bool on)
 #undef PWR_ACT
 }
 
+int rtw89_mac_pwr_on(struct rtw89_dev *rtwdev)
+{
+	int ret;
+
+	ret = rtw89_mac_power_switch(rtwdev, true);
+	if (ret) {
+		rtw89_mac_power_switch(rtwdev, false);
+		ret = rtw89_mac_power_switch(rtwdev, true);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev)
 {
 	rtw89_mac_power_switch(rtwdev, false);
@@ -3996,14 +4011,6 @@ int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb)
 {
 	int ret;
 
-	ret = rtw89_mac_power_switch(rtwdev, true);
-	if (ret) {
-		rtw89_mac_power_switch(rtwdev, false);
-		ret = rtw89_mac_power_switch(rtwdev, true);
-		if (ret)
-			return ret;
-	}
-
 	rtw89_mac_ctrl_hci_dma_trx(rtwdev, true);
 
 	if (include_bb) {
@@ -4036,6 +4043,10 @@ int rtw89_mac_init(struct rtw89_dev *rtwdev)
 	bool include_bb = !!chip->bbmcu_nr;
 	int ret;
 
+	ret = rtw89_mac_pwr_on(rtwdev);
+	if (ret)
+		return ret;
+
 	ret = rtw89_mac_partial_init(rtwdev, include_bb);
 	if (ret)
 		goto fail;
@@ -4067,7 +4078,7 @@ int rtw89_mac_init(struct rtw89_dev *rtwdev)
 
 	return ret;
 fail:
-	rtw89_mac_power_switch(rtwdev, false);
+	rtw89_mac_pwr_off(rtwdev);
 
 	return ret;
 }
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 8edea96d037f6..6389f54264e5a 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -1145,6 +1145,7 @@ rtw89_write32_port_set(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_l
 	rtw89_write32_set(rtwdev, reg, bit);
 }
 
+int rtw89_mac_pwr_on(struct rtw89_dev *rtwdev);
 void rtw89_mac_pwr_off(struct rtw89_dev *rtwdev);
 int rtw89_mac_partial_init(struct rtw89_dev *rtwdev, bool include_bb);
 int rtw89_mac_init(struct rtw89_dev *rtwdev);

From 5dde1a569c13d1c97cde8445c2abcd3114f6e6ca Mon Sep 17 00:00:00 2001
From: Eric Huang <echuang@realtek.com>
Date: Mon, 3 Feb 2025 15:29:09 +0800
Subject: [PATCH 0252/2753] wifi: rtw89: ps: update H2C command with more info
 for PS

Adding beacon BW offset, OP1dB table and rfe_type to lps_ml_cmn_info.
These information will help FW to configure RX more accurately.

Signed-off-by: Eric Huang <echuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250203072911.47313-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c |  5 ++++-
 drivers/net/wireless/realtek/rtw89/core.h |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c   | 18 +++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/fw.h   |  6 +++++-
 4 files changed, 27 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index ad28f11f2d241..8d5dc22fb5080 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2192,8 +2192,11 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac,
 		}
 		pkt_stat->beacon_nr++;
 
-		if (phy_ppdu)
+		if (phy_ppdu) {
 			ewma_rssi_add(&rtwdev->phystat.bcn_rssi, phy_ppdu->rssi_avg);
+			if (!test_bit(RTW89_FLAG_LOW_POWER_MODE, rtwdev->flags))
+				rtwvif_link->bcn_bw_idx = phy_ppdu->bw_idx;
+		}
 
 		pkt_stat->beacon_rate = desc_info->data_rate;
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 61fe2705cac6c..b3fdd8eded210 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3501,6 +3501,7 @@ struct rtw89_vif_link {
 	u8 self_role;
 	u8 wmm;
 	u8 bcn_hit_cond;
+	u8 bcn_bw_idx;
 	u8 hit_rule;
 	u8 last_noa_nr;
 	u64 sync_bcn_tsf;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 1afce0a0b9053..c86a0d3284356 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -2795,7 +2795,9 @@ int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev,
 {
 	const struct rtw89_phy_bb_gain_info_be *gain = &rtwdev->bb_gain.be;
 	struct rtw89_pkt_stat *pkt_stat = &rtwdev->phystat.cur_pkt_stat;
+	static const u8 bcn_bw_ofst[] = {0, 0, 0, 3, 6, 9, 0, 12};
 	const struct rtw89_chip_info *chip = rtwdev->chip;
+	struct rtw89_efuse *efuse = &rtwdev->efuse;
 	struct rtw89_h2c_lps_ml_cmn_info *h2c;
 	struct rtw89_vif_link *rtwvif_link;
 	const struct rtw89_chan *chan;
@@ -2803,6 +2805,7 @@ int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev,
 	u32 len = sizeof(*h2c);
 	unsigned int link_id;
 	struct sk_buff *skb;
+	u8 beacon_bw_ofst;
 	u8 gain_band;
 	u32 done;
 	u8 path;
@@ -2820,9 +2823,10 @@ int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev,
 	skb_put(skb, len);
 	h2c = (struct rtw89_h2c_lps_ml_cmn_info *)skb->data;
 
-	h2c->fmt_id = 0x1;
+	h2c->fmt_id = 0x3;
 
 	h2c->mlo_dbcc_mode = cpu_to_le32(rtwdev->mlo_dbcc_mode);
+	h2c->rfe_type = efuse->rfe_type;
 
 	rtw89_vif_for_each_link(rtwvif, rtwvif_link, link_id) {
 		path = rtwvif_link->phy_idx == RTW89_PHY_1 ? RF_PATH_B : RF_PATH_A;
@@ -2843,9 +2847,21 @@ int rtw89_fw_h2c_lps_ml_cmn_info(struct rtw89_dev *rtwdev,
 			h2c->tia_gain[rtwvif_link->phy_idx][i] =
 				cpu_to_le16(gain->tia_gain[gain_band][bw_idx][path][i]);
 		}
+
+		if (rtwvif_link->bcn_bw_idx < ARRAY_SIZE(bcn_bw_ofst)) {
+			beacon_bw_ofst = bcn_bw_ofst[rtwvif_link->bcn_bw_idx];
+			h2c->dup_bcn_ofst[rtwvif_link->phy_idx] = beacon_bw_ofst;
+		}
+
 		memcpy(h2c->lna_gain[rtwvif_link->phy_idx],
 		       gain->lna_gain[gain_band][bw_idx][path],
 		       LNA_GAIN_NUM);
+		memcpy(h2c->tia_lna_op1db[rtwvif_link->phy_idx],
+		       gain->tia_lna_op1db[gain_band][bw_idx][path],
+		       LNA_GAIN_NUM + 1);
+		memcpy(h2c->lna_op1db[rtwvif_link->phy_idx],
+		       gain->lna_op1db[gain_band][bw_idx][path],
+		       LNA_GAIN_NUM);
 	}
 
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index fb107c0a29d7f..994d109a9c3c9 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -1801,7 +1801,8 @@ struct rtw89_h2c_lps_ch_info {
 
 struct rtw89_h2c_lps_ml_cmn_info {
 	u8 fmt_id;
-	u8 rsvd0[3];
+	u8 rfe_type;
+	u8 rsvd0[2];
 	__le32 mlo_dbcc_mode;
 	u8 central_ch[RTW89_PHY_NUM];
 	u8 pri_ch[RTW89_PHY_NUM];
@@ -1812,6 +1813,9 @@ struct rtw89_h2c_lps_ml_cmn_info {
 	__le16 tia_gain[RTW89_PHY_NUM][TIA_GAIN_NUM];
 	u8 lna_gain[RTW89_PHY_NUM][LNA_GAIN_NUM];
 	u8 rsvd2[2];
+	u8 tia_lna_op1db[RTW89_PHY_NUM][LNA_GAIN_NUM + 1];
+	u8 lna_op1db[RTW89_PHY_NUM][LNA_GAIN_NUM];
+	u8 dup_bcn_ofst[RTW89_PHY_NUM];
 } __packed;
 
 static inline void RTW89_SET_FWCMD_CPU_EXCEPTION_TYPE(void *cmd, u32 val)

From 1f0efffd597893404aea5c3d4f1bdaa1c61d4434 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 3 Feb 2025 15:29:10 +0800
Subject: [PATCH 0253/2753] wifi: rtw89: fw: validate multi-firmware header
 before accessing

A firmeware file contains multi-firmware with a header to represent
contents. The mfw_hdr->fw_nr is to define number of firmware in file.

         +-----+-------+------+---------+--------------+
         | sig | fw_nr | rsvd | version | reserved     |
         +---------------------------------------------+ --
 fw 0    | cv | type | mp | rsvd | shift | size | rsvd |   \
         +---------------------------------------------+   |
 fw 1    | cv | type | mp | rsvd | shift | size | rsvd |   | mfw_hdr->fw_nr
         +---------------------------------------------+   |
 fw N-1  |                  ...                        |   /
         +=============================================+ --
         |               fw 0 content                  |
         |       (pointed by fw0 shift/size)           |
         +=============================================+

To avoid Coverity warning, validate header is in range of firmware size,
and also validate the range of actual firmware content is in range.

Addresses-Coverity-ID: 1494046 ("Untrusted loop bound")

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250203072911.47313-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 35 +++++++++++++++++++++++++
 1 file changed, 35 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index c86a0d3284356..68e80e54ab5fa 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -489,6 +489,30 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev,
 	}
 }
 
+static int rtw89_mfw_validate_hdr(struct rtw89_dev *rtwdev,
+				  const struct firmware *firmware,
+				  const struct rtw89_mfw_hdr *mfw_hdr)
+{
+	const void *mfw = firmware->data;
+	u32 mfw_len = firmware->size;
+	u8 fw_nr = mfw_hdr->fw_nr;
+	const void *ptr;
+
+	if (fw_nr == 0) {
+		rtw89_err(rtwdev, "mfw header has no fw entry\n");
+		return -ENOENT;
+	}
+
+	ptr = &mfw_hdr->info[fw_nr];
+
+	if (ptr > mfw + mfw_len) {
+		rtw89_err(rtwdev, "mfw header out of address\n");
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 static
 int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 			struct rtw89_fw_suit *fw_suit, bool nowarn)
@@ -499,6 +523,7 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 	u32 mfw_len = firmware->size;
 	const struct rtw89_mfw_hdr *mfw_hdr = (const struct rtw89_mfw_hdr *)mfw;
 	const struct rtw89_mfw_info *mfw_info = NULL, *tmp;
+	int ret;
 	int i;
 
 	if (mfw_hdr->sig != RTW89_MFW_SIG) {
@@ -511,6 +536,10 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 		return 0;
 	}
 
+	ret = rtw89_mfw_validate_hdr(rtwdev, firmware, mfw_hdr);
+	if (ret)
+		return ret;
+
 	for (i = 0; i < mfw_hdr->fw_nr; i++) {
 		tmp = &mfw_hdr->info[i];
 		if (tmp->type != type)
@@ -540,6 +569,12 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 found:
 	fw_suit->data = mfw + le32_to_cpu(mfw_info->shift);
 	fw_suit->size = le32_to_cpu(mfw_info->size);
+
+	if (fw_suit->data + fw_suit->size > mfw + mfw_len) {
+		rtw89_err(rtwdev, "fw_suit %d out of address\n", type);
+		return -EFAULT;
+	}
+
 	return 0;
 }
 

From 2b8bdc5237014cc61784b3676cbaca5325959f3d Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 3 Feb 2025 15:29:11 +0800
Subject: [PATCH 0254/2753] wifi: rtw89: fw: validate multi-firmware header
 before getting its size

To access firmware elements appended after multi-firmware, add its size
as offset to get start address of firmware elements.

         +-----+-------+------+---------+--------------+ --
         | sig | fw_nr | rsvd | version | reserved     |   \
         +---------------------------------------------+   |
 fw 0    | cv | type | mp | rsvd | shift | size | rsvd |   |
         +---------------------------------------------+   |
 fw 1    | cv | type | mp | rsvd | shift | size | rsvd |   |
         +---------------------------------------------+   |
 fw N-1  |                  ...                        |   |
         +=============================================+   | mfw size
         |               fw 0 content                  |   |
         +=============================================+   |
         |               fw 1 content                  |   |
         +=============================================+   |
         |                  ...                        |   |
         +=============================================+   |
         |               fw N -1 content               |   |
         +=============================================+ --/
         |             fw element TLV X                |
         +=============================================+
         |             fw element TLV Y                |
         +=============================================+
         |             fw element TLV Z                |
         +=============================================+

To avoid Coverity warning when getting mfw size, validate it header ahead.

Addresses-Coverity-ID: 1544385 ("Untrusted array index read")

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250203072911.47313-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 68e80e54ab5fa..35b86970db2a4 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -586,12 +586,17 @@ static u32 rtw89_mfw_get_size(struct rtw89_dev *rtwdev)
 		(const struct rtw89_mfw_hdr *)firmware->data;
 	const struct rtw89_mfw_info *mfw_info;
 	u32 size;
+	int ret;
 
 	if (mfw_hdr->sig != RTW89_MFW_SIG) {
 		rtw89_warn(rtwdev, "not mfw format\n");
 		return 0;
 	}
 
+	ret = rtw89_mfw_validate_hdr(rtwdev, firmware, mfw_hdr);
+	if (ret)
+		return ret;
+
 	mfw_info = &mfw_hdr->info[mfw_hdr->fw_nr - 1];
 	size = le32_to_cpu(mfw_info->shift) + le32_to_cpu(mfw_info->size);
 

From 2e4c4717b3f6f019c71af984564b6e4d0ae8d0bd Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Wed, 5 Feb 2025 09:32:31 +0800
Subject: [PATCH 0255/2753] wifi: rtw89: coex: Assign value over than 0 to
 avoid firmware timer hang

If the slot duration is 0, the firmware timer will trigger timer hang at
the timer initializing state in a low rate due to hardware algorithm.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250205013233.10945-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 2c0ccf2f8bd96..806a51782467b 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -89,10 +89,10 @@ static const struct rtw89_btc_fbtc_slot s_def[] = {
 	[CXST_B4]	= __DEF_FBTC_SLOT(50,  0xe5555555, SLOT_MIX),
 	[CXST_LK]	= __DEF_FBTC_SLOT(20,  0xea5a5a5a, SLOT_ISO),
 	[CXST_BLK]	= __DEF_FBTC_SLOT(500, 0x55555555, SLOT_MIX),
-	[CXST_E2G]	= __DEF_FBTC_SLOT(0,   0xea5a5a5a, SLOT_MIX),
-	[CXST_E5G]	= __DEF_FBTC_SLOT(0,   0xffffffff, SLOT_ISO),
+	[CXST_E2G]	= __DEF_FBTC_SLOT(5,   0xea5a5a5a, SLOT_MIX),
+	[CXST_E5G]	= __DEF_FBTC_SLOT(5,   0xffffffff, SLOT_ISO),
 	[CXST_EBT]	= __DEF_FBTC_SLOT(5,   0xe5555555, SLOT_MIX),
-	[CXST_ENULL]	= __DEF_FBTC_SLOT(0,   0xaaaaaaaa, SLOT_ISO),
+	[CXST_ENULL]	= __DEF_FBTC_SLOT(5,   0xaaaaaaaa, SLOT_ISO),
 	[CXST_WLK]	= __DEF_FBTC_SLOT(250, 0xea5a5a5a, SLOT_MIX),
 	[CXST_W1FDD]	= __DEF_FBTC_SLOT(50,  0xffffffff, SLOT_ISO),
 	[CXST_B1FDD]	= __DEF_FBTC_SLOT(50,  0xffffdfff, SLOT_ISO),

From e53aa85e4b8a839a8a0daf283339357bdb0bcf1a Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Wed, 5 Feb 2025 09:32:32 +0800
Subject: [PATCH 0256/2753] wifi: rtw89: coex: To avoid TWS serials A2DP lag,
 adjust slot arrangement

The TWS(True wireless stereo) serials Bluetooth audio device need to keep
packet traffic not only with DUT, it also need to synchronize packet with
its assistant earbud. And all the BR/EDR Bluetooth device need to do page
scan to keep re-connect event sensitively between different DUT.
These behavior will make TWS Bluetooth device cost more time slot to keep
the good audio performance. This patch decrease half of Wi-Fi slot(from
40ms to 20ms) in a single cycle. Make the slot more flexible to prevent
audio lag. The single cycle will be shorter, then it will bring some slot
protection cost make Wi-Fi throughput decrease about 5%.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250205013233.10945-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 16 ++--------------
 1 file changed, 2 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 806a51782467b..28d29fa17316a 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -4583,17 +4583,11 @@ static void _action_bt_hid(struct rtw89_dev *rtwdev)
 static void _action_bt_a2dp(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
-	struct rtw89_btc_bt_link_info *bt_linfo = &btc->cx.bt.link_info;
-	struct rtw89_btc_bt_a2dp_desc a2dp = bt_linfo->a2dp_desc;
 	struct rtw89_btc_dm *dm = &btc->dm;
 
 	_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
 
-	if (a2dp.vendor_id == 0x4c || dm->leak_ap || bt_linfo->slave_role)
-		dm->slot_dur[CXST_W1] = 20;
-	else
-		dm->slot_dur[CXST_W1] = 40;
-
+	dm->slot_dur[CXST_W1] = 20;
 	dm->slot_dur[CXST_B1] = BTC_B1_MAX;
 
 	switch (btc->cx.state_map) {
@@ -4690,17 +4684,11 @@ static void _action_bt_pan(struct rtw89_dev *rtwdev)
 static void _action_bt_a2dp_hid(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_btc *btc = &rtwdev->btc;
-	struct rtw89_btc_bt_link_info *bt_linfo = &btc->cx.bt.link_info;
-	struct rtw89_btc_bt_a2dp_desc a2dp = bt_linfo->a2dp_desc;
 	struct rtw89_btc_dm *dm = &btc->dm;
 
 	_set_ant(rtwdev, NM_EXEC, BTC_PHY_ALL, BTC_ANT_W2G);
 
-	if (a2dp.vendor_id == 0x4c || dm->leak_ap || bt_linfo->slave_role)
-		dm->slot_dur[CXST_W1] = 20;
-	else
-		dm->slot_dur[CXST_W1] = 40;
-
+	dm->slot_dur[CXST_W1] = 20;
 	dm->slot_dur[CXST_B1] = BTC_B1_MAX;
 
 	switch (btc->cx.state_map) {

From f94ba3c640f6e95653c6e20661c0dd12ee5e2b66 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Wed, 5 Feb 2025 09:32:33 +0800
Subject: [PATCH 0257/2753] wifi: rtw89: coex: Update Wi-Fi/Bluetooth
 coexistence version to 7.0.3

Refine the TWS Bluetooth related coexistence mechanism.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250205013233.10945-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 28d29fa17316a..858ff0cd1a239 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -10,7 +10,7 @@
 #include "ps.h"
 #include "reg.h"
 
-#define RTW89_COEX_VERSION 0x07000213
+#define RTW89_COEX_VERSION 0x07000313
 #define FCXDEF_STEP 50 /* MUST <= FCXMAX_STEP and match with wl fw*/
 #define BTC_E2G_LIMIT_DEF 80
 

From 85c726b20f59f3069f6f243335be54afd5b46d9c Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Wed, 5 Feb 2025 09:40:51 +0800
Subject: [PATCH 0258/2753] wifi: rtw89: regd: avoid using BITMAP_FROM_U64() to
 assign function bitmap

Since there are two function features for now, func_bitmap[] has single
one element, which BITMAP_FROM_U64() generating two elements is exceeded.
Change to assign function bitmap barely.

With i386-allmodconfig (a 32 bit system), it throws

 >> include/linux/bitmap.h:736:33: warning: excess elements in array initializer
      736 |                                 ((unsigned long) ((u64)(n) >> 32))
          |                                 ^
    drivers/net/wireless/realtek/rtw89/regd.c:16:34: note: in expansion of macro 'BITMAP_FROM_U64'
       16 |                 .func_bitmap = { BITMAP_FROM_U64(_fmap), },     \
          |                                  ^~~~~~~~~~~~~~~
    drivers/net/wireless/realtek/rtw89/regd.c:20:9: note: in expansion of macro 'COUNTRY_REGD'
       20 |         COUNTRY_REGD("00", RTW89_WW, RTW89_WW, RTW89_WW, 0x0);
          |         ^~~~~~~~~~~~

Fixes: 79a36fc56bea ("wifi: rtw89: regd: handle supported regulatory functions by country")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502031932.BMQ4lhJT-lkp@intel.com/
Cc: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250205014051.13765-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/regd.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 505a3d0767c60..0e67d0f128ddc 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -16,9 +16,11 @@ void rtw89_regd_notifier(struct wiphy *wiphy, struct regulatory_request *request
 		.txpwr_regd[RTW89_BAND_2G] = _rule_2ghz,	\
 		.txpwr_regd[RTW89_BAND_5G] = _rule_5ghz,	\
 		.txpwr_regd[RTW89_BAND_6G] = _rule_6ghz,	\
-		.func_bitmap = { BITMAP_FROM_U64(_fmap), },	\
+		.func_bitmap = { _fmap, },	\
 	}
 
+static_assert(BITS_PER_TYPE(unsigned long) >= NUM_OF_RTW89_REGD_FUNC);
+
 static const struct rtw89_regd rtw89_ww_regd =
 	COUNTRY_REGD("00", RTW89_WW, RTW89_WW, RTW89_WW, 0x0);
 

From 105dc94233e48ff30e572a50fb39d7e3dec810fa Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Mon, 3 Feb 2025 20:08:27 +0200
Subject: [PATCH 0259/2753] wifi: rtw88: Fix a typo of debug message in
 rtw8723d_iqk_check_tx_failed()

There is a typo in debug messages:
 - afer -> after

Fix it via codespell.

Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250203180913.5435-1-algonell@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8723d.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.c b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
index eeca31bf71f16..87715bd54860a 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8723d.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
@@ -444,7 +444,7 @@ static u8 rtw8723d_iqk_check_tx_failed(struct rtw_dev *rtwdev,
 		rtw_read32(rtwdev, REG_IQK_RES_TX),
 		rtw_read32(rtwdev, REG_IQK_RES_TY));
 	rtw_dbg(rtwdev, RTW_DBG_RFK,
-		"[IQK] 0xe90(before IQK)= 0x%x, 0xe98(afer IQK) = 0x%x\n",
+		"[IQK] 0xe90(before IQK)= 0x%x, 0xe98(after IQK) = 0x%x\n",
 		rtw_read32(rtwdev, 0xe90),
 		rtw_read32(rtwdev, 0xe98));
 
@@ -472,7 +472,7 @@ static u8 rtw8723d_iqk_check_rx_failed(struct rtw_dev *rtwdev,
 		rtw_read32(rtwdev, REG_IQK_RES_RY));
 
 	rtw_dbg(rtwdev, RTW_DBG_RFK,
-		"[IQK] 0xea0(before IQK)= 0x%x, 0xea8(afer IQK) = 0x%x\n",
+		"[IQK] 0xea0(before IQK)= 0x%x, 0xea8(after IQK) = 0x%x\n",
 		rtw_read32(rtwdev, 0xea0),
 		rtw_read32(rtwdev, 0xea8));
 

From 8425f5c8f04dbcf11ade78f984a494fc0b90e7a0 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:36:56 +0200
Subject: [PATCH 0260/2753] wifi: rtw88: Fix __rtw_download_firmware() for
 RTL8814AU

Don't call ltecoex_read_reg() and ltecoex_reg_write() when the
ltecoex_addr member of struct rtw_chip_info is NULL. The RTL8814AU
doesn't have this feature.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/55b5641f-094e-4f94-9f79-ac053733f2cf@gmail.com
---
 drivers/net/wireless/realtek/rtw88/mac.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c
index cae9cca6dca3d..63edf6461de87 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.c
+++ b/drivers/net/wireless/realtek/rtw88/mac.c
@@ -784,7 +784,8 @@ static int __rtw_download_firmware(struct rtw_dev *rtwdev,
 	if (!check_firmware_size(data, size))
 		return -EINVAL;
 
-	if (!ltecoex_read_reg(rtwdev, 0x38, &ltecoex_bckp))
+	if (rtwdev->chip->ltecoex_addr &&
+	    !ltecoex_read_reg(rtwdev, 0x38, &ltecoex_bckp))
 		return -EBUSY;
 
 	wlan_cpu_enable(rtwdev, false);
@@ -802,7 +803,8 @@ static int __rtw_download_firmware(struct rtw_dev *rtwdev,
 
 	wlan_cpu_enable(rtwdev, true);
 
-	if (!ltecoex_reg_write(rtwdev, 0x38, ltecoex_bckp)) {
+	if (rtwdev->chip->ltecoex_addr &&
+	    !ltecoex_reg_write(rtwdev, 0x38, ltecoex_bckp)) {
 		ret = -EBUSY;
 		goto dlfw_fail;
 	}

From 9e8243025cc06abc975c876dffda052073207ab3 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:37:36 +0200
Subject: [PATCH 0261/2753] wifi: rtw88: Fix download_firmware_validate() for
 RTL8814AU

After the firmware is uploaded, download_firmware_validate() checks some
bits in REG_MCUFW_CTRL to see if everything went okay. The
RTL8814AU power on sequence sets bits 13 and 12 to 2, which this
function does not expect, so it thinks the firmware upload failed.

Make download_firmware_validate() ignore bits 13 and 12.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/049d2887-22fc-47b7-9e59-62627cb525f8@gmail.com
---
 drivers/net/wireless/realtek/rtw88/reg.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index e438405fba566..209b6fc08a73e 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -130,6 +130,7 @@
 #define BIT_SHIFT_ROM_PGE	16
 #define BIT_FW_INIT_RDY		BIT(15)
 #define BIT_FW_DW_RDY		BIT(14)
+#define BIT_CPU_CLK_SEL		(BIT(12) | BIT(13))
 #define BIT_RPWM_TOGGLE		BIT(7)
 #define BIT_RAM_DL_SEL		BIT(7)	/* legacy only */
 #define BIT_DMEM_CHKSUM_OK	BIT(6)
@@ -147,7 +148,7 @@
 				 BIT_CHECK_SUM_OK)
 #define FW_READY_LEGACY		(BIT_MCUFWDL_RDY | BIT_FWDL_CHK_RPT |	       \
 				 BIT_WINTINI_RDY | BIT_RAM_DL_SEL)
-#define FW_READY_MASK		0xffff
+#define FW_READY_MASK		(0xffff & ~BIT_CPU_CLK_SEL)
 
 #define REG_MCU_TST_CFG		0x84
 #define VAL_FW_TRIGGER		0x1

From 62f726848da42554e6d270dfda17ed19bfa3456f Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:38:17 +0200
Subject: [PATCH 0262/2753] wifi: rtw88: Extend struct rtw_pwr_track_tbl for
 RTL8814AU

Currently this struct has the members required for chips with 2 RF
paths. Add more members to support chips with 4 RF paths, like the
RTL8814AU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/be5a73f4-a0fe-43d6-9457-930cde199284@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 62cd4c5263019..e40e623029847 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -1130,14 +1130,26 @@ struct rtw_rfe_def {
  * For 2G there are cck rate and ofdm rate with different settings.
  */
 struct rtw_pwr_track_tbl {
+	const u8 *pwrtrk_5gd_n[RTW_PWR_TRK_5G_NUM];
+	const u8 *pwrtrk_5gd_p[RTW_PWR_TRK_5G_NUM];
+	const u8 *pwrtrk_5gc_n[RTW_PWR_TRK_5G_NUM];
+	const u8 *pwrtrk_5gc_p[RTW_PWR_TRK_5G_NUM];
 	const u8 *pwrtrk_5gb_n[RTW_PWR_TRK_5G_NUM];
 	const u8 *pwrtrk_5gb_p[RTW_PWR_TRK_5G_NUM];
 	const u8 *pwrtrk_5ga_n[RTW_PWR_TRK_5G_NUM];
 	const u8 *pwrtrk_5ga_p[RTW_PWR_TRK_5G_NUM];
+	const u8 *pwrtrk_2gd_n;
+	const u8 *pwrtrk_2gd_p;
+	const u8 *pwrtrk_2gc_n;
+	const u8 *pwrtrk_2gc_p;
 	const u8 *pwrtrk_2gb_n;
 	const u8 *pwrtrk_2gb_p;
 	const u8 *pwrtrk_2ga_n;
 	const u8 *pwrtrk_2ga_p;
+	const u8 *pwrtrk_2g_cckd_n;
+	const u8 *pwrtrk_2g_cckd_p;
+	const u8 *pwrtrk_2g_cckc_n;
+	const u8 *pwrtrk_2g_cckc_p;
 	const u8 *pwrtrk_2g_cckb_n;
 	const u8 *pwrtrk_2g_cckb_p;
 	const u8 *pwrtrk_2g_ccka_n;

From d80e7d9b6ba38102f92559dbb647330216ea290b Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:38:43 +0200
Subject: [PATCH 0263/2753] wifi: rtw88: Extend rf_base_addr and rf_sipi_addr
 for RTL8814AU

These members of struct rtw_chip_info each have a size of 2. Increase
their size to 4, which is the number of RF paths the RTL8814AU has.

This is required to read and write the RF registers of the RTL8814AU.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/7a4d8209-b8af-4943-b5de-f53d6edf591a@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index e40e623029847..ba64d269521a2 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -1239,8 +1239,8 @@ struct rtw_chip_info {
 
 	const struct rtw_hw_reg *dig;
 	const struct rtw_hw_reg *dig_cck;
-	u32 rf_base_addr[2];
-	u32 rf_sipi_addr[2];
+	u32 rf_base_addr[RTW_RF_PATH_MAX];
+	u32 rf_sipi_addr[RTW_RF_PATH_MAX];
 	const struct rtw_rf_sipi_addr *rf_sipi_read_addr;
 	u8 fix_rf_phy_num;
 	const struct rtw_ltecoex_addr *ltecoex_addr;

From 8f0076726b66a70727a1bef5c087c60291e90ad8 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:39:29 +0200
Subject: [PATCH 0264/2753] wifi: rtw88: Extend rtw_fw_send_ra_info() for
 RTL8814AU

The existing code is suitable for chips with up to 2 spatial streams.
Inform the firmware about the rates it's allowed to use when
transmitting 3 spatial streams.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/08e2f328-1aab-4e50-93ac-c1e5dd9541ac@gmail.com
---
 drivers/net/wireless/realtek/rtw88/fw.c   | 15 +++++++++++++++
 drivers/net/wireless/realtek/rtw88/fw.h   |  1 +
 drivers/net/wireless/realtek/rtw88/main.h |  1 +
 3 files changed, 17 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
index 02389b7c68768..6b563ac489a74 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.c
+++ b/drivers/net/wireless/realtek/rtw88/fw.c
@@ -735,6 +735,7 @@ void rtw_fw_send_ra_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 {
 	u8 h2c_pkt[H2C_PKT_SIZE] = {0};
 	bool disable_pt = true;
+	u32 mask_hi;
 
 	SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_RA_INFO);
 
@@ -755,6 +756,20 @@ void rtw_fw_send_ra_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 	si->init_ra_lv = 0;
 
 	rtw_fw_send_h2c_command(rtwdev, h2c_pkt);
+
+	if (rtwdev->chip->id != RTW_CHIP_TYPE_8814A)
+		return;
+
+	SET_H2C_CMD_ID_CLASS(h2c_pkt, H2C_CMD_RA_INFO_HI);
+
+	mask_hi = si->ra_mask >> 32;
+
+	SET_RA_INFO_RA_MASK0(h2c_pkt, (mask_hi & 0xff));
+	SET_RA_INFO_RA_MASK1(h2c_pkt, (mask_hi & 0xff00) >> 8);
+	SET_RA_INFO_RA_MASK2(h2c_pkt, (mask_hi & 0xff0000) >> 16);
+	SET_RA_INFO_RA_MASK3(h2c_pkt, (mask_hi & 0xff000000) >> 24);
+
+	rtw_fw_send_h2c_command(rtwdev, h2c_pkt);
 }
 
 void rtw_fw_media_status_report(struct rtw_dev *rtwdev, u8 mac_id, bool connect)
diff --git a/drivers/net/wireless/realtek/rtw88/fw.h b/drivers/net/wireless/realtek/rtw88/fw.h
index 404de1b0c407b..48ad9ceab6ea1 100644
--- a/drivers/net/wireless/realtek/rtw88/fw.h
+++ b/drivers/net/wireless/realtek/rtw88/fw.h
@@ -557,6 +557,7 @@ static inline void rtw_h2c_pkt_set_header(u8 *h2c_pkt, u8 sub_id)
 #define H2C_CMD_DEFAULT_PORT		0x2c
 #define H2C_CMD_RA_INFO			0x40
 #define H2C_CMD_RSSI_MONITOR		0x42
+#define H2C_CMD_RA_INFO_HI		0x46
 #define H2C_CMD_BCN_FILTER_OFFLOAD_P0	0x56
 #define H2C_CMD_BCN_FILTER_OFFLOAD_P1	0x57
 #define H2C_CMD_WL_PHY_INFO		0x58
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index ba64d269521a2..993c381e734bb 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -191,6 +191,7 @@ enum rtw_chip_type {
 	RTW_CHIP_TYPE_8703B,
 	RTW_CHIP_TYPE_8821A,
 	RTW_CHIP_TYPE_8812A,
+	RTW_CHIP_TYPE_8814A,
 };
 
 enum rtw_tx_queue_type {

From e66f3b5c7535bb508e9c561a047b32de4ddc1cda Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:40:22 +0200
Subject: [PATCH 0265/2753] wifi: rtw88: Constify some more structs and arrays

These structs and arrays are never modified, so make them const:

rtw_band_2ghz
rtw_band_5ghz
rtw_pci_tx_queue_idx_addr
rtw_pci_ops
rtw_cck_rates
rtw_ofdm_rates
rtw_ht_1s_rates
rtw_ht_2s_rates
rtw_vht_1s_rates
rtw_vht_2s_rates
rtw_rate_section
rtw_rate_size
rtw_sdio_ops
rtw_usb_ops

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/502f124e-ccf3-4c09-80a4-1e5c5304822b@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.c |  4 ++--
 drivers/net/wireless/realtek/rtw88/main.h |  2 +-
 drivers/net/wireless/realtek/rtw88/pci.c  |  4 ++--
 drivers/net/wireless/realtek/rtw88/phy.c  | 26 ++++++++++++++---------
 drivers/net/wireless/realtek/rtw88/phy.h  | 16 +++++++-------
 drivers/net/wireless/realtek/rtw88/sdio.c |  2 +-
 drivers/net/wireless/realtek/rtw88/usb.c  |  2 +-
 7 files changed, 31 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 0cee0fd8c0ef0..8d22df293e789 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -136,7 +136,7 @@ u16 rtw_desc_to_bitrate(u8 desc_rate)
 	return rate.bitrate;
 }
 
-static struct ieee80211_supported_band rtw_band_2ghz = {
+static const struct ieee80211_supported_band rtw_band_2ghz = {
 	.band = NL80211_BAND_2GHZ,
 
 	.channels = rtw_channeltable_2g,
@@ -149,7 +149,7 @@ static struct ieee80211_supported_band rtw_band_2ghz = {
 	.vht_cap = {0},
 };
 
-static struct ieee80211_supported_band rtw_band_5ghz = {
+static const struct ieee80211_supported_band rtw_band_5ghz = {
 	.band = NL80211_BAND_5GHZ,
 
 	.channels = rtw_channeltable_5g,
diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 993c381e734bb..c982d9d3c5d7b 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -61,7 +61,7 @@ enum rtw_hci_type {
 };
 
 struct rtw_hci {
-	struct rtw_hci_ops *ops;
+	const struct rtw_hci_ops *ops;
 	enum rtw_hci_type type;
 
 	u32 rpwm_addr;
diff --git a/drivers/net/wireless/realtek/rtw88/pci.c b/drivers/net/wireless/realtek/rtw88/pci.c
index 0ecaefc4c83dd..bb4c4ccb31d41 100644
--- a/drivers/net/wireless/realtek/rtw88/pci.c
+++ b/drivers/net/wireless/realtek/rtw88/pci.c
@@ -20,7 +20,7 @@ module_param_named(disable_aspm, rtw_pci_disable_aspm, bool, 0644);
 MODULE_PARM_DESC(disable_msi, "Set Y to disable MSI interrupt support");
 MODULE_PARM_DESC(disable_aspm, "Set Y to disable PCI ASPM support");
 
-static u32 rtw_pci_tx_queue_idx_addr[] = {
+static const u32 rtw_pci_tx_queue_idx_addr[] = {
 	[RTW_TX_QUEUE_BK]	= RTK_PCI_TXBD_IDX_BKQ,
 	[RTW_TX_QUEUE_BE]	= RTK_PCI_TXBD_IDX_BEQ,
 	[RTW_TX_QUEUE_VI]	= RTK_PCI_TXBD_IDX_VIQ,
@@ -1591,7 +1591,7 @@ static void rtw_pci_destroy(struct rtw_dev *rtwdev, struct pci_dev *pdev)
 	rtw_pci_io_unmapping(rtwdev, pdev);
 }
 
-static struct rtw_hci_ops rtw_pci_ops = {
+static const struct rtw_hci_ops rtw_pci_ops = {
 	.tx_write = rtw_pci_tx_write,
 	.tx_kick_off = rtw_pci_tx_kick_off,
 	.flush_queues = rtw_pci_flush_queues,
diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c
index 8ed20c89d2163..f6528016973de 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.c
+++ b/drivers/net/wireless/realtek/rtw88/phy.c
@@ -52,44 +52,50 @@ static const u32 db_invert_table[12][8] = {
 	 1995262315,	2511886432U,	3162277660U,	3981071706U}
 };
 
-u8 rtw_cck_rates[] = { DESC_RATE1M, DESC_RATE2M, DESC_RATE5_5M, DESC_RATE11M };
-u8 rtw_ofdm_rates[] = {
+const u8 rtw_cck_rates[] = { DESC_RATE1M, DESC_RATE2M, DESC_RATE5_5M, DESC_RATE11M };
+
+const u8 rtw_ofdm_rates[] = {
 	DESC_RATE6M,  DESC_RATE9M,  DESC_RATE12M,
 	DESC_RATE18M, DESC_RATE24M, DESC_RATE36M,
 	DESC_RATE48M, DESC_RATE54M
 };
-u8 rtw_ht_1s_rates[] = {
+
+const u8 rtw_ht_1s_rates[] = {
 	DESC_RATEMCS0, DESC_RATEMCS1, DESC_RATEMCS2,
 	DESC_RATEMCS3, DESC_RATEMCS4, DESC_RATEMCS5,
 	DESC_RATEMCS6, DESC_RATEMCS7
 };
-u8 rtw_ht_2s_rates[] = {
+
+const u8 rtw_ht_2s_rates[] = {
 	DESC_RATEMCS8,  DESC_RATEMCS9,  DESC_RATEMCS10,
 	DESC_RATEMCS11, DESC_RATEMCS12, DESC_RATEMCS13,
 	DESC_RATEMCS14, DESC_RATEMCS15
 };
-u8 rtw_vht_1s_rates[] = {
+
+const u8 rtw_vht_1s_rates[] = {
 	DESC_RATEVHT1SS_MCS0, DESC_RATEVHT1SS_MCS1,
 	DESC_RATEVHT1SS_MCS2, DESC_RATEVHT1SS_MCS3,
 	DESC_RATEVHT1SS_MCS4, DESC_RATEVHT1SS_MCS5,
 	DESC_RATEVHT1SS_MCS6, DESC_RATEVHT1SS_MCS7,
 	DESC_RATEVHT1SS_MCS8, DESC_RATEVHT1SS_MCS9
 };
-u8 rtw_vht_2s_rates[] = {
+
+const u8 rtw_vht_2s_rates[] = {
 	DESC_RATEVHT2SS_MCS0, DESC_RATEVHT2SS_MCS1,
 	DESC_RATEVHT2SS_MCS2, DESC_RATEVHT2SS_MCS3,
 	DESC_RATEVHT2SS_MCS4, DESC_RATEVHT2SS_MCS5,
 	DESC_RATEVHT2SS_MCS6, DESC_RATEVHT2SS_MCS7,
 	DESC_RATEVHT2SS_MCS8, DESC_RATEVHT2SS_MCS9
 };
-u8 *rtw_rate_section[RTW_RATE_SECTION_MAX] = {
+
+const u8 * const rtw_rate_section[RTW_RATE_SECTION_MAX] = {
 	rtw_cck_rates, rtw_ofdm_rates,
 	rtw_ht_1s_rates, rtw_ht_2s_rates,
 	rtw_vht_1s_rates, rtw_vht_2s_rates
 };
 EXPORT_SYMBOL(rtw_rate_section);
 
-u8 rtw_rate_size[RTW_RATE_SECTION_MAX] = {
+const u8 rtw_rate_size[RTW_RATE_SECTION_MAX] = {
 	ARRAY_SIZE(rtw_cck_rates),
 	ARRAY_SIZE(rtw_ofdm_rates),
 	ARRAY_SIZE(rtw_ht_1s_rates),
@@ -2214,7 +2220,7 @@ static void rtw_phy_set_tx_power_index_by_rs(struct rtw_dev *rtwdev,
 {
 	struct rtw_hal *hal = &rtwdev->hal;
 	u8 regd = rtw_regd_get(rtwdev);
-	u8 *rates;
+	const u8 *rates;
 	u8 size;
 	u8 rate;
 	u8 pwr_idx;
@@ -2274,7 +2280,7 @@ EXPORT_SYMBOL(rtw_phy_set_tx_power_level);
 
 static void
 rtw_phy_tx_power_by_rate_config_by_path(struct rtw_hal *hal, u8 path,
-					u8 rs, u8 size, u8 *rates)
+					u8 rs, u8 size, const u8 *rates)
 {
 	u8 rate;
 	u8 base_idx, rate_idx;
diff --git a/drivers/net/wireless/realtek/rtw88/phy.h b/drivers/net/wireless/realtek/rtw88/phy.h
index ccfcbd3ced03a..ce6ee16a77dc0 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.h
+++ b/drivers/net/wireless/realtek/rtw88/phy.h
@@ -7,14 +7,14 @@
 
 #include "debug.h"
 
-extern u8 rtw_cck_rates[];
-extern u8 rtw_ofdm_rates[];
-extern u8 rtw_ht_1s_rates[];
-extern u8 rtw_ht_2s_rates[];
-extern u8 rtw_vht_1s_rates[];
-extern u8 rtw_vht_2s_rates[];
-extern u8 *rtw_rate_section[];
-extern u8 rtw_rate_size[];
+extern const u8 rtw_cck_rates[];
+extern const u8 rtw_ofdm_rates[];
+extern const u8 rtw_ht_1s_rates[];
+extern const u8 rtw_ht_2s_rates[];
+extern const u8 rtw_vht_1s_rates[];
+extern const u8 rtw_vht_2s_rates[];
+extern const u8 * const rtw_rate_section[];
+extern const u8 rtw_rate_size[];
 
 void rtw_phy_init(struct rtw_dev *rtwdev);
 void rtw_phy_dynamic_mechanism(struct rtw_dev *rtwdev);
diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c
index e024061bdbf70..6209a49312f17 100644
--- a/drivers/net/wireless/realtek/rtw88/sdio.c
+++ b/drivers/net/wireless/realtek/rtw88/sdio.c
@@ -1147,7 +1147,7 @@ static void rtw_sdio_declaim(struct rtw_dev *rtwdev,
 	sdio_release_host(sdio_func);
 }
 
-static struct rtw_hci_ops rtw_sdio_ops = {
+static const struct rtw_hci_ops rtw_sdio_ops = {
 	.tx_write = rtw_sdio_tx_write,
 	.tx_kick_off = rtw_sdio_tx_kick_off,
 	.setup = rtw_sdio_setup,
diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
index c4908db4ff0e8..c8092fa0d9f13 100644
--- a/drivers/net/wireless/realtek/rtw88/usb.c
+++ b/drivers/net/wireless/realtek/rtw88/usb.c
@@ -881,7 +881,7 @@ static void rtw_usb_dynamic_rx_agg(struct rtw_dev *rtwdev, bool enable)
 	}
 }
 
-static struct rtw_hci_ops rtw_usb_ops = {
+static const struct rtw_hci_ops rtw_usb_ops = {
 	.tx_write = rtw_usb_tx_write,
 	.tx_kick_off = rtw_usb_tx_kick_off,
 	.setup = rtw_usb_setup,

From ad815f3920035a0c5b6ffe45bddc9fb308194b49 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:40:58 +0200
Subject: [PATCH 0266/2753] wifi: rtw88: Rename RTW_RATE_SECTION_MAX to
 RTW_RATE_SECTION_NUM

It fits the meaning of the enum better.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/5a1c5a46-8ebb-43b0-9ab1-b78e2a22b3d2@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.h     | 12 +++++-----
 drivers/net/wireless/realtek/rtw88/phy.c      | 24 +++++++++----------
 drivers/net/wireless/realtek/rtw88/rtw8821c.c |  2 +-
 drivers/net/wireless/realtek/rtw88/rtw8822b.c |  2 +-
 drivers/net/wireless/realtek/rtw88/rtw8822c.c |  2 +-
 drivers/net/wireless/realtek/rtw88/rtw88xxa.c |  2 +-
 drivers/net/wireless/realtek/rtw88/sar.c      |  2 +-
 7 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index c982d9d3c5d7b..057141e196e68 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -168,7 +168,7 @@ enum rtw_rate_section {
 	RTW_RATE_SECTION_VHT_2S,
 
 	/* keep last */
-	RTW_RATE_SECTION_MAX,
+	RTW_RATE_SECTION_NUM,
 };
 
 enum rtw_wireless_set {
@@ -1937,7 +1937,7 @@ union rtw_sar_cfg {
 
 struct rtw_sar {
 	enum rtw_sar_sources src;
-	union rtw_sar_cfg cfg[RTW_RF_PATH_MAX][RTW_RATE_SECTION_MAX];
+	union rtw_sar_cfg cfg[RTW_RF_PATH_MAX][RTW_RATE_SECTION_NUM];
 };
 
 struct rtw_hal {
@@ -1981,16 +1981,16 @@ struct rtw_hal {
 	s8 tx_pwr_by_rate_offset_5g[RTW_RF_PATH_MAX]
 				   [DESC_RATE_MAX];
 	s8 tx_pwr_by_rate_base_2g[RTW_RF_PATH_MAX]
-				 [RTW_RATE_SECTION_MAX];
+				 [RTW_RATE_SECTION_NUM];
 	s8 tx_pwr_by_rate_base_5g[RTW_RF_PATH_MAX]
-				 [RTW_RATE_SECTION_MAX];
+				 [RTW_RATE_SECTION_NUM];
 	s8 tx_pwr_limit_2g[RTW_REGD_MAX]
 			  [RTW_CHANNEL_WIDTH_MAX]
-			  [RTW_RATE_SECTION_MAX]
+			  [RTW_RATE_SECTION_NUM]
 			  [RTW_MAX_CHANNEL_NUM_2G];
 	s8 tx_pwr_limit_5g[RTW_REGD_MAX]
 			  [RTW_CHANNEL_WIDTH_MAX]
-			  [RTW_RATE_SECTION_MAX]
+			  [RTW_RATE_SECTION_NUM]
 			  [RTW_MAX_CHANNEL_NUM_5G];
 	s8 tx_pwr_tbl[RTW_RF_PATH_MAX]
 		     [DESC_RATE_MAX];
diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c
index f6528016973de..e3a5f8e1e30a3 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.c
+++ b/drivers/net/wireless/realtek/rtw88/phy.c
@@ -88,14 +88,14 @@ const u8 rtw_vht_2s_rates[] = {
 	DESC_RATEVHT2SS_MCS8, DESC_RATEVHT2SS_MCS9
 };
 
-const u8 * const rtw_rate_section[RTW_RATE_SECTION_MAX] = {
+const u8 * const rtw_rate_section[RTW_RATE_SECTION_NUM] = {
 	rtw_cck_rates, rtw_ofdm_rates,
 	rtw_ht_1s_rates, rtw_ht_2s_rates,
 	rtw_vht_1s_rates, rtw_vht_2s_rates
 };
 EXPORT_SYMBOL(rtw_rate_section);
 
-const u8 rtw_rate_size[RTW_RATE_SECTION_MAX] = {
+const u8 rtw_rate_size[RTW_RATE_SECTION_NUM] = {
 	ARRAY_SIZE(rtw_cck_rates),
 	ARRAY_SIZE(rtw_ofdm_rates),
 	ARRAY_SIZE(rtw_ht_1s_rates),
@@ -1596,7 +1596,7 @@ static void rtw_phy_set_tx_power_limit(struct rtw_dev *rtwdev, u8 regd, u8 band,
 	ch_idx = rtw_channel_to_idx(band, ch);
 
 	if (regd >= RTW_REGD_MAX || bw >= RTW_CHANNEL_WIDTH_MAX ||
-	    rs >= RTW_RATE_SECTION_MAX || ch_idx < 0) {
+	    rs >= RTW_RATE_SECTION_NUM || ch_idx < 0) {
 		WARN(1,
 		     "wrong txpwr_lmt regd=%u, band=%u bw=%u, rs=%u, ch_idx=%u, pwr_limit=%d\n",
 		     regd, band, bw, rs, ch_idx, pwr_limit);
@@ -1701,7 +1701,7 @@ rtw_cfg_txpwr_lmt_by_alt(struct rtw_dev *rtwdev, u8 regd, u8 regd_alt)
 	u8 bw, rs;
 
 	for (bw = 0; bw < RTW_CHANNEL_WIDTH_MAX; bw++)
-		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
+		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
 			__cfg_txpwr_lmt_by_alt(&rtwdev->hal, regd, regd_alt,
 					       bw, rs);
 }
@@ -2060,7 +2060,7 @@ static u8 rtw_phy_get_5g_tx_power_index(struct rtw_dev *rtwdev,
 	return tx_power;
 }
 
-/* return RTW_RATE_SECTION_MAX to indicate rate is invalid */
+/* return RTW_RATE_SECTION_NUM to indicate rate is invalid */
 static u8 rtw_phy_rate_to_rate_section(u8 rate)
 {
 	if (rate >= DESC_RATE1M && rate <= DESC_RATE11M)
@@ -2076,7 +2076,7 @@ static u8 rtw_phy_rate_to_rate_section(u8 rate)
 	else if (rate >= DESC_RATEVHT2SS_MCS0 && rate <= DESC_RATEVHT2SS_MCS9)
 		return RTW_RATE_SECTION_VHT_2S;
 	else
-		return RTW_RATE_SECTION_MAX;
+		return RTW_RATE_SECTION_NUM;
 }
 
 static s8 rtw_phy_get_tx_power_limit(struct rtw_dev *rtwdev, u8 band,
@@ -2094,7 +2094,7 @@ static s8 rtw_phy_get_tx_power_limit(struct rtw_dev *rtwdev, u8 band,
 	if (regd > RTW_REGD_WW)
 		return power_limit;
 
-	if (rs == RTW_RATE_SECTION_MAX)
+	if (rs == RTW_RATE_SECTION_NUM)
 		goto err;
 
 	/* only 20M BW with cck and ofdm */
@@ -2138,7 +2138,7 @@ static s8 rtw_phy_get_tx_power_sar(struct rtw_dev *rtwdev, u8 sar_band,
 		.rs = rs,
 	};
 
-	if (rs == RTW_RATE_SECTION_MAX)
+	if (rs == RTW_RATE_SECTION_NUM)
 		goto err;
 
 	return rtw_query_sar(rtwdev, &arg);
@@ -2227,7 +2227,7 @@ static void rtw_phy_set_tx_power_index_by_rs(struct rtw_dev *rtwdev,
 	u8 bw;
 	int i;
 
-	if (rs >= RTW_RATE_SECTION_MAX)
+	if (rs >= RTW_RATE_SECTION_NUM)
 		return;
 
 	rates = rtw_rate_section[rs];
@@ -2258,7 +2258,7 @@ static void rtw_phy_set_tx_power_level_by_path(struct rtw_dev *rtwdev,
 	else
 		rs = RTW_RATE_SECTION_OFDM;
 
-	for (; rs < RTW_RATE_SECTION_MAX; rs++)
+	for (; rs < RTW_RATE_SECTION_NUM; rs++)
 		rtw_phy_set_tx_power_index_by_rs(rtwdev, ch, path, rs);
 }
 
@@ -2353,7 +2353,7 @@ void rtw_phy_tx_power_limit_config(struct rtw_hal *hal)
 
 	for (regd = 0; regd < RTW_REGD_MAX; regd++)
 		for (bw = 0; bw < RTW_CHANNEL_WIDTH_MAX; bw++)
-			for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
+			for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
 				__rtw_phy_tx_power_limit_config(hal, regd, bw, rs);
 }
 
@@ -2389,7 +2389,7 @@ void rtw_phy_init_tx_power(struct rtw_dev *rtwdev)
 	/* init tx power limit */
 	for (regd = 0; regd < RTW_REGD_MAX; regd++)
 		for (bw = 0; bw < RTW_CHANNEL_WIDTH_MAX; bw++)
-			for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
+			for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
 				rtw_phy_init_tx_power_limit(rtwdev, regd, bw,
 							    rs);
 }
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index cc152248407c7..6abb21067aed6 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -709,7 +709,7 @@ static void rtw8821c_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++) {
+		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
 			if (rs == RTW_RATE_SECTION_HT_2S ||
 			    rs == RTW_RATE_SECTION_VHT_2S)
 				continue;
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index 23a29019752da..742a2a05632e3 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -964,7 +964,7 @@ static void rtw8822b_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++)
+		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
 			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs,
 							    &phy_pwr_idx);
 	}
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index ec362a817f5f5..2314d160292ad 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -2746,7 +2746,7 @@ static void rtw8822c_set_tx_power_index(struct rtw_dev *rtwdev)
 	s8 diff_idx[4];
 
 	rtw8822c_set_write_tx_power_ref(rtwdev, pwr_ref_cck, pwr_ref_ofdm);
-	for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++) {
+	for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
 		for (j = 0; j < rtw_rate_size[rs]; j++) {
 			rate = rtw_rate_section[rs][j];
 			pwr_a = hal->tx_pwr_tbl[RF_PATH_A][rate];
diff --git a/drivers/net/wireless/realtek/rtw88/rtw88xxa.c b/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
index 71e61b9c0becf..109ff42eda821 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
@@ -1637,7 +1637,7 @@ void rtw88xxa_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_MAX; rs++) {
+		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
 			if (hal->rf_path_num == 1 &&
 			    (rs == RTW_RATE_SECTION_HT_2S ||
 			     rs == RTW_RATE_SECTION_VHT_2S))
diff --git a/drivers/net/wireless/realtek/rtw88/sar.c b/drivers/net/wireless/realtek/rtw88/sar.c
index c472f1502b82a..50b9c2412bb1c 100644
--- a/drivers/net/wireless/realtek/rtw88/sar.c
+++ b/drivers/net/wireless/realtek/rtw88/sar.c
@@ -97,7 +97,7 @@ int rtw_set_sar_specs(struct rtw_dev *rtwdev,
 			power, BIT(RTW_COMMON_SAR_FCT));
 
 		for (j = 0; j < RTW_RF_PATH_MAX; j++) {
-			for (k = 0; k < RTW_RATE_SECTION_MAX; k++) {
+			for (k = 0; k < RTW_RATE_SECTION_NUM; k++) {
 				arg = (struct rtw_sar_arg){
 					.sar_band = idx,
 					.path = j,

From 0f98a59596579b34932c06aec7d52c1e835fa1f0 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:41:43 +0200
Subject: [PATCH 0267/2753] wifi: rtw88: Extend TX power stuff for 3-4 spatial
 streams

Although the RTL8814AU only has 3 spatial streams, maybe some other chip
has 4.

Correct the TX power index and TX power limit calculations for 3SS and
4SS HT/VHT rates.

With this the RTL8814AU can set the TX power correctly.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/d0c0e126-0794-4c4e-9203-ea39a707b673@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.h     |   5 +
 drivers/net/wireless/realtek/rtw88/phy.c      | 145 ++++++++++++------
 drivers/net/wireless/realtek/rtw88/phy.h      |   4 +
 drivers/net/wireless/realtek/rtw88/rtw8821c.c |   2 +-
 drivers/net/wireless/realtek/rtw88/rtw8822b.c |   2 +-
 drivers/net/wireless/realtek/rtw88/rtw8822c.c |   2 +-
 drivers/net/wireless/realtek/rtw88/rtw88xxa.c |   2 +-
 7 files changed, 111 insertions(+), 51 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 057141e196e68..24ac749271cc8 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -166,6 +166,11 @@ enum rtw_rate_section {
 	RTW_RATE_SECTION_HT_2S,
 	RTW_RATE_SECTION_VHT_1S,
 	RTW_RATE_SECTION_VHT_2S,
+	__RTW_RATE_SECTION_2SS_MAX = RTW_RATE_SECTION_VHT_2S,
+	RTW_RATE_SECTION_HT_3S,
+	RTW_RATE_SECTION_HT_4S,
+	RTW_RATE_SECTION_VHT_3S,
+	RTW_RATE_SECTION_VHT_4S,
 
 	/* keep last */
 	RTW_RATE_SECTION_NUM,
diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c
index e3a5f8e1e30a3..b487457d22158 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.c
+++ b/drivers/net/wireless/realtek/rtw88/phy.c
@@ -88,10 +88,40 @@ const u8 rtw_vht_2s_rates[] = {
 	DESC_RATEVHT2SS_MCS8, DESC_RATEVHT2SS_MCS9
 };
 
+const u8 rtw_ht_3s_rates[] = {
+	DESC_RATEMCS16, DESC_RATEMCS17, DESC_RATEMCS18,
+	DESC_RATEMCS19, DESC_RATEMCS20, DESC_RATEMCS21,
+	DESC_RATEMCS22, DESC_RATEMCS23
+};
+
+const u8 rtw_ht_4s_rates[] = {
+	DESC_RATEMCS24, DESC_RATEMCS25, DESC_RATEMCS26,
+	DESC_RATEMCS27, DESC_RATEMCS28, DESC_RATEMCS29,
+	DESC_RATEMCS30, DESC_RATEMCS31
+};
+
+const u8 rtw_vht_3s_rates[] = {
+	DESC_RATEVHT3SS_MCS0, DESC_RATEVHT3SS_MCS1,
+	DESC_RATEVHT3SS_MCS2, DESC_RATEVHT3SS_MCS3,
+	DESC_RATEVHT3SS_MCS4, DESC_RATEVHT3SS_MCS5,
+	DESC_RATEVHT3SS_MCS6, DESC_RATEVHT3SS_MCS7,
+	DESC_RATEVHT3SS_MCS8, DESC_RATEVHT3SS_MCS9
+};
+
+const u8 rtw_vht_4s_rates[] = {
+	DESC_RATEVHT4SS_MCS0, DESC_RATEVHT4SS_MCS1,
+	DESC_RATEVHT4SS_MCS2, DESC_RATEVHT4SS_MCS3,
+	DESC_RATEVHT4SS_MCS4, DESC_RATEVHT4SS_MCS5,
+	DESC_RATEVHT4SS_MCS6, DESC_RATEVHT4SS_MCS7,
+	DESC_RATEVHT4SS_MCS8, DESC_RATEVHT4SS_MCS9
+};
+
 const u8 * const rtw_rate_section[RTW_RATE_SECTION_NUM] = {
 	rtw_cck_rates, rtw_ofdm_rates,
 	rtw_ht_1s_rates, rtw_ht_2s_rates,
-	rtw_vht_1s_rates, rtw_vht_2s_rates
+	rtw_vht_1s_rates, rtw_vht_2s_rates,
+	rtw_ht_3s_rates, rtw_ht_4s_rates,
+	rtw_vht_3s_rates, rtw_vht_4s_rates
 };
 EXPORT_SYMBOL(rtw_rate_section);
 
@@ -101,17 +131,14 @@ const u8 rtw_rate_size[RTW_RATE_SECTION_NUM] = {
 	ARRAY_SIZE(rtw_ht_1s_rates),
 	ARRAY_SIZE(rtw_ht_2s_rates),
 	ARRAY_SIZE(rtw_vht_1s_rates),
-	ARRAY_SIZE(rtw_vht_2s_rates)
+	ARRAY_SIZE(rtw_vht_2s_rates),
+	ARRAY_SIZE(rtw_ht_3s_rates),
+	ARRAY_SIZE(rtw_ht_4s_rates),
+	ARRAY_SIZE(rtw_vht_3s_rates),
+	ARRAY_SIZE(rtw_vht_4s_rates)
 };
 EXPORT_SYMBOL(rtw_rate_size);
 
-static const u8 rtw_cck_size = ARRAY_SIZE(rtw_cck_rates);
-static const u8 rtw_ofdm_size = ARRAY_SIZE(rtw_ofdm_rates);
-static const u8 rtw_ht_1s_size = ARRAY_SIZE(rtw_ht_1s_rates);
-static const u8 rtw_ht_2s_size = ARRAY_SIZE(rtw_ht_2s_rates);
-static const u8 rtw_vht_1s_size = ARRAY_SIZE(rtw_vht_1s_rates);
-static const u8 rtw_vht_2s_size = ARRAY_SIZE(rtw_vht_2s_rates);
-
 enum rtw_phy_band_type {
 	PHY_BAND_2G	= 0,
 	PHY_BAND_5G	= 1,
@@ -1640,11 +1667,15 @@ rtw_xref_5g_txpwr_lmt(struct rtw_dev *rtwdev, u8 regd,
 static void
 rtw_xref_txpwr_lmt_by_rs(struct rtw_dev *rtwdev, u8 regd, u8 bw, u8 ch_idx)
 {
+	static const u8 rs_cmp[4][2] = {
+		{RTW_RATE_SECTION_HT_1S, RTW_RATE_SECTION_VHT_1S},
+		{RTW_RATE_SECTION_HT_2S, RTW_RATE_SECTION_VHT_2S},
+		{RTW_RATE_SECTION_HT_3S, RTW_RATE_SECTION_VHT_3S},
+		{RTW_RATE_SECTION_HT_4S, RTW_RATE_SECTION_VHT_4S}
+	};
 	u8 rs_idx, rs_ht, rs_vht;
-	u8 rs_cmp[2][2] = {{RTW_RATE_SECTION_HT_1S, RTW_RATE_SECTION_VHT_1S},
-			   {RTW_RATE_SECTION_HT_2S, RTW_RATE_SECTION_VHT_2S} };
 
-	for (rs_idx = 0; rs_idx < 2; rs_idx++) {
+	for (rs_idx = 0; rs_idx < 4; rs_idx++) {
 		rs_ht = rs_cmp[rs_idx][0];
 		rs_vht = rs_cmp[rs_idx][1];
 
@@ -1965,10 +1996,10 @@ static u8 rtw_phy_get_2g_tx_power_index(struct rtw_dev *rtwdev,
 					u8 rate, u8 group)
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
-	u8 tx_power;
-	bool mcs_rate;
-	bool above_2ss;
+	bool above_2ss, above_3ss, above_4ss;
 	u8 factor = chip->txgi_factor;
+	bool mcs_rate;
+	u8 tx_power;
 
 	if (rate <= DESC_RATE11M)
 		tx_power = pwr_idx_2g->cck_base[group];
@@ -1978,11 +2009,15 @@ static u8 rtw_phy_get_2g_tx_power_index(struct rtw_dev *rtwdev,
 	if (rate >= DESC_RATE6M && rate <= DESC_RATE54M)
 		tx_power += pwr_idx_2g->ht_1s_diff.ofdm * factor;
 
-	mcs_rate = (rate >= DESC_RATEMCS0 && rate <= DESC_RATEMCS15) ||
+	mcs_rate = (rate >= DESC_RATEMCS0 && rate <= DESC_RATEMCS31) ||
 		   (rate >= DESC_RATEVHT1SS_MCS0 &&
-		    rate <= DESC_RATEVHT2SS_MCS9);
-	above_2ss = (rate >= DESC_RATEMCS8 && rate <= DESC_RATEMCS15) ||
+		    rate <= DESC_RATEVHT4SS_MCS9);
+	above_2ss = (rate >= DESC_RATEMCS8 && rate <= DESC_RATEMCS31) ||
 		    (rate >= DESC_RATEVHT2SS_MCS0);
+	above_3ss = (rate >= DESC_RATEMCS16 && rate <= DESC_RATEMCS31) ||
+		    (rate >= DESC_RATEVHT3SS_MCS0);
+	above_4ss = (rate >= DESC_RATEMCS24 && rate <= DESC_RATEMCS31) ||
+		    (rate >= DESC_RATEVHT4SS_MCS0);
 
 	if (!mcs_rate)
 		return tx_power;
@@ -1995,11 +2030,19 @@ static u8 rtw_phy_get_2g_tx_power_index(struct rtw_dev *rtwdev,
 		tx_power += pwr_idx_2g->ht_1s_diff.bw20 * factor;
 		if (above_2ss)
 			tx_power += pwr_idx_2g->ht_2s_diff.bw20 * factor;
+		if (above_3ss)
+			tx_power += pwr_idx_2g->ht_3s_diff.bw20 * factor;
+		if (above_4ss)
+			tx_power += pwr_idx_2g->ht_4s_diff.bw20 * factor;
 		break;
 	case RTW_CHANNEL_WIDTH_40:
 		/* bw40 is the base power */
 		if (above_2ss)
 			tx_power += pwr_idx_2g->ht_2s_diff.bw40 * factor;
+		if (above_3ss)
+			tx_power += pwr_idx_2g->ht_3s_diff.bw40 * factor;
+		if (above_4ss)
+			tx_power += pwr_idx_2g->ht_4s_diff.bw40 * factor;
 		break;
 	}
 
@@ -2012,19 +2055,23 @@ static u8 rtw_phy_get_5g_tx_power_index(struct rtw_dev *rtwdev,
 					u8 rate, u8 group)
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
-	u8 tx_power;
+	bool above_2ss, above_3ss, above_4ss;
+	u8 factor = chip->txgi_factor;
 	u8 upper, lower;
 	bool mcs_rate;
-	bool above_2ss;
-	u8 factor = chip->txgi_factor;
+	u8 tx_power;
 
 	tx_power = pwr_idx_5g->bw40_base[group];
 
-	mcs_rate = (rate >= DESC_RATEMCS0 && rate <= DESC_RATEMCS15) ||
+	mcs_rate = (rate >= DESC_RATEMCS0 && rate <= DESC_RATEMCS31) ||
 		   (rate >= DESC_RATEVHT1SS_MCS0 &&
-		    rate <= DESC_RATEVHT2SS_MCS9);
-	above_2ss = (rate >= DESC_RATEMCS8 && rate <= DESC_RATEMCS15) ||
+		    rate <= DESC_RATEVHT4SS_MCS9);
+	above_2ss = (rate >= DESC_RATEMCS8 && rate <= DESC_RATEMCS31) ||
 		    (rate >= DESC_RATEVHT2SS_MCS0);
+	above_3ss = (rate >= DESC_RATEMCS16 && rate <= DESC_RATEMCS31) ||
+		    (rate >= DESC_RATEVHT3SS_MCS0);
+	above_4ss = (rate >= DESC_RATEMCS24 && rate <= DESC_RATEMCS31) ||
+		    (rate >= DESC_RATEVHT4SS_MCS0);
 
 	if (!mcs_rate) {
 		tx_power += pwr_idx_5g->ht_1s_diff.ofdm * factor;
@@ -2039,11 +2086,19 @@ static u8 rtw_phy_get_5g_tx_power_index(struct rtw_dev *rtwdev,
 		tx_power += pwr_idx_5g->ht_1s_diff.bw20 * factor;
 		if (above_2ss)
 			tx_power += pwr_idx_5g->ht_2s_diff.bw20 * factor;
+		if (above_3ss)
+			tx_power += pwr_idx_5g->ht_3s_diff.bw20 * factor;
+		if (above_4ss)
+			tx_power += pwr_idx_5g->ht_4s_diff.bw20 * factor;
 		break;
 	case RTW_CHANNEL_WIDTH_40:
 		/* bw40 is the base power */
 		if (above_2ss)
 			tx_power += pwr_idx_5g->ht_2s_diff.bw40 * factor;
+		if (above_3ss)
+			tx_power += pwr_idx_5g->ht_3s_diff.bw40 * factor;
+		if (above_4ss)
+			tx_power += pwr_idx_5g->ht_4s_diff.bw40 * factor;
 		break;
 	case RTW_CHANNEL_WIDTH_80:
 		/* the base idx of bw80 is the average of bw40+/bw40- */
@@ -2054,6 +2109,10 @@ static u8 rtw_phy_get_5g_tx_power_index(struct rtw_dev *rtwdev,
 		tx_power += pwr_idx_5g->vht_1s_diff.bw80 * factor;
 		if (above_2ss)
 			tx_power += pwr_idx_5g->vht_2s_diff.bw80 * factor;
+		if (above_3ss)
+			tx_power += pwr_idx_5g->vht_3s_diff.bw80 * factor;
+		if (above_4ss)
+			tx_power += pwr_idx_5g->vht_4s_diff.bw80 * factor;
 		break;
 	}
 
@@ -2071,10 +2130,18 @@ static u8 rtw_phy_rate_to_rate_section(u8 rate)
 		return RTW_RATE_SECTION_HT_1S;
 	else if (rate >= DESC_RATEMCS8 && rate <= DESC_RATEMCS15)
 		return RTW_RATE_SECTION_HT_2S;
+	else if (rate >= DESC_RATEMCS16 && rate <= DESC_RATEMCS23)
+		return RTW_RATE_SECTION_HT_3S;
+	else if (rate >= DESC_RATEMCS24 && rate <= DESC_RATEMCS31)
+		return RTW_RATE_SECTION_HT_4S;
 	else if (rate >= DESC_RATEVHT1SS_MCS0 && rate <= DESC_RATEVHT1SS_MCS9)
 		return RTW_RATE_SECTION_VHT_1S;
 	else if (rate >= DESC_RATEVHT2SS_MCS0 && rate <= DESC_RATEVHT2SS_MCS9)
 		return RTW_RATE_SECTION_VHT_2S;
+	else if (rate >= DESC_RATEVHT3SS_MCS0 && rate <= DESC_RATEVHT3SS_MCS9)
+		return RTW_RATE_SECTION_VHT_3S;
+	else if (rate >= DESC_RATEVHT4SS_MCS0 && rate <= DESC_RATEVHT4SS_MCS9)
+		return RTW_RATE_SECTION_VHT_4S;
 	else
 		return RTW_RATE_SECTION_NUM;
 }
@@ -2102,7 +2169,7 @@ static s8 rtw_phy_get_tx_power_limit(struct rtw_dev *rtwdev, u8 band,
 		bw = RTW_CHANNEL_WIDTH_20;
 
 	/* only 20/40M BW with ht */
-	if (rs == RTW_RATE_SECTION_HT_1S || rs == RTW_RATE_SECTION_HT_2S)
+	if (rate >= DESC_RATEMCS0 && rate <= DESC_RATEMCS31)
 		bw = min_t(u8, bw, RTW_CHANNEL_WIDTH_40);
 
 	/* select min power limit among [20M BW ~ current BW] */
@@ -2286,7 +2353,7 @@ rtw_phy_tx_power_by_rate_config_by_path(struct rtw_hal *hal, u8 path,
 	u8 base_idx, rate_idx;
 	s8 base_2g, base_5g;
 
-	if (rs >= RTW_RATE_SECTION_VHT_1S)
+	if (size == 10) /* VHT rates */
 		base_idx = rates[size - 3];
 	else
 		base_idx = rates[size - 1];
@@ -2303,28 +2370,12 @@ rtw_phy_tx_power_by_rate_config_by_path(struct rtw_hal *hal, u8 path,
 
 void rtw_phy_tx_power_by_rate_config(struct rtw_hal *hal)
 {
-	u8 path;
+	u8 path, rs;
 
-	for (path = 0; path < RTW_RF_PATH_MAX; path++) {
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_CCK,
-				rtw_cck_size, rtw_cck_rates);
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_OFDM,
-				rtw_ofdm_size, rtw_ofdm_rates);
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_HT_1S,
-				rtw_ht_1s_size, rtw_ht_1s_rates);
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_HT_2S,
-				rtw_ht_2s_size, rtw_ht_2s_rates);
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_VHT_1S,
-				rtw_vht_1s_size, rtw_vht_1s_rates);
-		rtw_phy_tx_power_by_rate_config_by_path(hal, path,
-				RTW_RATE_SECTION_VHT_2S,
-				rtw_vht_2s_size, rtw_vht_2s_rates);
-	}
+	for (path = 0; path < RTW_RF_PATH_MAX; path++)
+		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
+			rtw_phy_tx_power_by_rate_config_by_path(hal, path, rs,
+				rtw_rate_size[rs], rtw_rate_section[rs]);
 }
 
 static void
diff --git a/drivers/net/wireless/realtek/rtw88/phy.h b/drivers/net/wireless/realtek/rtw88/phy.h
index ce6ee16a77dc0..c9e6b869661d6 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.h
+++ b/drivers/net/wireless/realtek/rtw88/phy.h
@@ -13,6 +13,10 @@ extern const u8 rtw_ht_1s_rates[];
 extern const u8 rtw_ht_2s_rates[];
 extern const u8 rtw_vht_1s_rates[];
 extern const u8 rtw_vht_2s_rates[];
+extern const u8 rtw_ht_3s_rates[];
+extern const u8 rtw_ht_4s_rates[];
+extern const u8 rtw_vht_3s_rates[];
+extern const u8 rtw_vht_4s_rates[];
 extern const u8 * const rtw_rate_section[];
 extern const u8 rtw_rate_size[];
 
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
index 6abb21067aed6..0ade7f11cbd2e 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
@@ -709,7 +709,7 @@ static void rtw8821c_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
+		for (rs = 0; rs <= __RTW_RATE_SECTION_2SS_MAX; rs++) {
 			if (rs == RTW_RATE_SECTION_HT_2S ||
 			    rs == RTW_RATE_SECTION_VHT_2S)
 				continue;
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
index 742a2a05632e3..b4934da88e33a 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
@@ -964,7 +964,7 @@ static void rtw8822b_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++)
+		for (rs = 0; rs <= __RTW_RATE_SECTION_2SS_MAX; rs++)
 			rtw8822b_set_tx_power_index_by_rate(rtwdev, path, rs,
 							    &phy_pwr_idx);
 	}
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
index 2314d160292ad..5e53e0db177ef 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
@@ -2746,7 +2746,7 @@ static void rtw8822c_set_tx_power_index(struct rtw_dev *rtwdev)
 	s8 diff_idx[4];
 
 	rtw8822c_set_write_tx_power_ref(rtwdev, pwr_ref_cck, pwr_ref_ofdm);
-	for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
+	for (rs = 0; rs <= __RTW_RATE_SECTION_2SS_MAX; rs++) {
 		for (j = 0; j < rtw_rate_size[rs]; j++) {
 			rate = rtw_rate_section[rs][j];
 			pwr_a = hal->tx_pwr_tbl[RF_PATH_A][rate];
diff --git a/drivers/net/wireless/realtek/rtw88/rtw88xxa.c b/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
index 109ff42eda821..0fa943271fb64 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw88xxa.c
@@ -1637,7 +1637,7 @@ void rtw88xxa_set_tx_power_index(struct rtw_dev *rtwdev)
 	int rs, path;
 
 	for (path = 0; path < hal->rf_path_num; path++) {
-		for (rs = 0; rs < RTW_RATE_SECTION_NUM; rs++) {
+		for (rs = 0; rs <= __RTW_RATE_SECTION_2SS_MAX; rs++) {
 			if (hal->rf_path_num == 1 &&
 			    (rs == RTW_RATE_SECTION_HT_2S ||
 			     rs == RTW_RATE_SECTION_VHT_2S))

From 9f00e2218e15a2ea3c284567424a100c10b6fb85 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 4 Feb 2025 20:42:08 +0200
Subject: [PATCH 0268/2753] wifi: rtw88: Fix rtw_update_sta_info() for
 RTL8814AU

This function tells the firmware what rates it can use.

Put the 3SS and 4SS HT rates supported by the other station into the
rate mask.

Remove the 3SS and 4SS rates from the rate mask if the hardware only has
2 spatial streams.

And finally, select the right rate ID (a parameter for the firmware)
when the hardware has 3 spatial streams.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/48d1d90f-2aeb-4ec5-9a24-0980e10eae1e@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 8d22df293e789..e4f9b744f24de 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1234,7 +1234,9 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC)
 			ldpc_en = VHT_LDPC_EN;
 	} else if (sta->deflink.ht_cap.ht_supported) {
-		ra_mask |= (sta->deflink.ht_cap.mcs.rx_mask[1] << 20) |
+		ra_mask |= ((u64)sta->deflink.ht_cap.mcs.rx_mask[3] << 36) |
+			   ((u64)sta->deflink.ht_cap.mcs.rx_mask[2] << 28) |
+			   (sta->deflink.ht_cap.mcs.rx_mask[1] << 20) |
 			   (sta->deflink.ht_cap.mcs.rx_mask[0] << 12);
 		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
 			stbc_en = HT_STBC_EN;
@@ -1244,6 +1246,9 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 
 	if (efuse->hw_cap.nss == 1 || rtwdev->hal.txrx_1ss)
 		ra_mask &= RA_MASK_VHT_RATES_1SS | RA_MASK_HT_RATES_1SS;
+	else if (efuse->hw_cap.nss == 2)
+		ra_mask &= RA_MASK_VHT_RATES_2SS | RA_MASK_HT_RATES_2SS |
+			   RA_MASK_VHT_RATES_1SS | RA_MASK_HT_RATES_1SS;
 
 	if (hal->current_band_type == RTW_BAND_5G) {
 		ra_mask |= (u64)sta->deflink.supp_rates[NL80211_BAND_5GHZ] << 4;
@@ -1302,10 +1307,9 @@ void rtw_update_sta_info(struct rtw_dev *rtwdev, struct rtw_sta_info *si,
 		break;
 	}
 
-	if (sta->deflink.vht_cap.vht_supported && ra_mask & 0xffc00000)
-		tx_num = 2;
-	else if (sta->deflink.ht_cap.ht_supported && ra_mask & 0xfff00000)
-		tx_num = 2;
+	if (sta->deflink.vht_cap.vht_supported ||
+	    sta->deflink.ht_cap.ht_supported)
+		tx_num = efuse->hw_cap.nss;
 
 	rate_id = get_rate_id(wireless_set, bw_mode, tx_num);
 

From 6b39cc01af66a32c4d03952e0b3aae19cdf4b66e Mon Sep 17 00:00:00 2001
From: Andrew Kreimer <algonell@gmail.com>
Date: Thu, 6 Feb 2025 10:24:12 +0200
Subject: [PATCH 0269/2753] wifi: rtlwifi: rtl8192de: Fix typos of debug
 message of phy setting

There are some typos in comments/messages:
 - althougth -> although
 - asume -> assume

Fix them via codespell.

Signed-off-by: Andrew Kreimer <algonell@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250206082457.9148-1-algonell@gmail.com
---
 drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
index d429560009bb6..e07402e73ba32 100644
--- a/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
+++ b/drivers/net/wireless/realtek/rtlwifi/rtl8192de/phy.c
@@ -484,7 +484,7 @@ bool rtl92d_phy_config_rf_with_headerfile(struct ieee80211_hw *hw,
 	 * pathA or mac1 has to set phy0&phy1 pathA */
 	if ((content == radiob_txt) && (rfpath == RF90_PATH_A)) {
 		rtl_dbg(rtlpriv, COMP_INIT, DBG_LOUD,
-			" ===> althougth Path A, we load radiob.txt\n");
+			" ===> although Path A, we load radiob.txt\n");
 		radioa_arraylen = radiob_arraylen;
 		radioa_array_table = radiob_array_table;
 	}
@@ -750,7 +750,7 @@ static void _rtl92d_phy_switch_rf_setting(struct ieee80211_hw *hw, u8 channel)
 		    && rtlhal->interfaceindex == 1) {
 			need_pwr_down = rtl92d_phy_enable_anotherphy(hw, false);
 			rtlhal->during_mac1init_radioa = true;
-			/* asume no this case */
+			/* assume no this case */
 			if (need_pwr_down)
 				rtl92d_phy_enable_rf_env(hw, path,
 							 &u4regvalue);
@@ -1885,7 +1885,7 @@ static void _rtl92d_phy_reload_lck_setting(struct ieee80211_hw *hw,
 			bneed_powerdown_radio =
 				rtl92d_phy_enable_anotherphy(hw, false);
 			rtlpriv->rtlhal.during_mac1init_radioa = true;
-			/* asume no this case */
+			/* assume no this case */
 			if (bneed_powerdown_radio)
 				rtl92d_phy_enable_rf_env(hw, erfpath,
 							 &u4regvalue);

From a27c6f46dcec8f697cbf15c8a10f8534c7b8a2c3 Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:22 -0800
Subject: [PATCH 0270/2753] RDMA/bnxt_re: Fix an issue in
 bnxt_re_async_notifier

In the bnxt_re_async_notifier() callback, the way driver retrieves
rdev pointer is wrong. The rdev pointer should be parsed from
adev pointer as while registering with the L2 for ULP, driver uses
the aux device pointer for the handle.

Fixes: 7fea32784068 ("RDMA/bnxt_re: Add Async event handling support")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/main.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index e9e4da4dd576b..c4c3d67c42cc6 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -396,11 +396,16 @@ static void bnxt_re_dcb_wq_task(struct work_struct *work)
 
 static void bnxt_re_async_notifier(void *handle, struct hwrm_async_event_cmpl *cmpl)
 {
-	struct bnxt_re_dev *rdev = (struct bnxt_re_dev *)handle;
+	struct bnxt_re_en_dev_info *en_info = auxiliary_get_drvdata(handle);
 	struct bnxt_re_dcb_work *dcb_work;
+	struct bnxt_re_dev *rdev;
 	u32 data1, data2;
 	u16 event_id;
 
+	rdev = en_info->rdev;
+	if (!rdev)
+		return;
+
 	event_id = le16_to_cpu(cmpl->event_id);
 	data1 = le32_to_cpu(cmpl->event_data1);
 	data2 = le32_to_cpu(cmpl->event_data2);

From f0df225d12fcb049429fb5bf5122afe143c2dd15 Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:23 -0800
Subject: [PATCH 0271/2753] RDMA/bnxt_re: Add sanity checks on rdev validity

There is a possibility that ulp_irq_stop and ulp_irq_start
callbacks will be called when the device is in detached state.
This can cause a crash due to NULL pointer dereference as
the rdev is already freed.

Fixes: cc5b9b48d447 ("RDMA/bnxt_re: Recover the device when FW error is detected")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/main.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index c4c3d67c42cc6..89ac5c21ca7ad 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -438,6 +438,8 @@ static void bnxt_re_stop_irq(void *handle, bool reset)
 	int indx;
 
 	rdev = en_info->rdev;
+	if (!rdev)
+		return;
 	rcfw = &rdev->rcfw;
 
 	if (reset) {
@@ -466,6 +468,8 @@ static void bnxt_re_start_irq(void *handle, struct bnxt_msix_entry *ent)
 	int indx, rc;
 
 	rdev = en_info->rdev;
+	if (!rdev)
+		return;
 	msix_ent = rdev->nqr->msix_entries;
 	rcfw = &rdev->rcfw;
 	if (!ent) {
@@ -2438,6 +2442,7 @@ static int bnxt_re_suspend(struct auxiliary_device *adev, pm_message_t state)
 	ibdev_info(&rdev->ibdev, "%s: L2 driver notified to stop en_state 0x%lx",
 		   __func__, en_dev->en_state);
 	bnxt_re_remove_device(rdev, BNXT_RE_PRE_RECOVERY_REMOVE, adev);
+	bnxt_re_update_en_info_rdev(NULL, en_info, adev);
 	mutex_unlock(&bnxt_re_mutex);
 
 	return 0;

From e2f105277411c4ebacd00d4ae1a57f693ba7d22d Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:24 -0800
Subject: [PATCH 0272/2753] RDMA/bnxt_re: Fix issue in the unload path

The cited comment removed the netdev notifier register call
from the driver. But, it did not remove the cleanup code from
the unload path. As a result, driver unload is not clean and
resulted in undesired behaviour.

Fixes: d3b15fcc4201 ("RDMA/bnxt_re: Remove deliver net device event")
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-4-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h |  1 -
 drivers/infiniband/hw/bnxt_re/main.c    | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index b91a85a491d05..3721446c6ba4b 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -187,7 +187,6 @@ struct bnxt_re_dev {
 #define BNXT_RE_FLAG_ISSUE_ROCE_STATS          29
 	struct net_device		*netdev;
 	struct auxiliary_device         *adev;
-	struct notifier_block		nb;
 	unsigned int			version, major, minor;
 	struct bnxt_qplib_chip_ctx	*chip_ctx;
 	struct bnxt_en_dev		*en_dev;
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index 89ac5c21ca7ad..a94c8c5387d9e 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -1359,7 +1359,6 @@ static struct bnxt_re_dev *bnxt_re_dev_add(struct auxiliary_device *adev,
 		return NULL;
 	}
 	/* Default values */
-	rdev->nb.notifier_call = NULL;
 	rdev->netdev = en_dev->net;
 	rdev->en_dev = en_dev;
 	rdev->adev = adev;
@@ -2354,15 +2353,6 @@ static int bnxt_re_add_device(struct auxiliary_device *adev, u8 op_type)
 static void bnxt_re_remove_device(struct bnxt_re_dev *rdev, u8 op_type,
 				  struct auxiliary_device *aux_dev)
 {
-	if (rdev->nb.notifier_call) {
-		unregister_netdevice_notifier(&rdev->nb);
-		rdev->nb.notifier_call = NULL;
-	} else {
-		/* If notifier is null, we should have already done a
-		 * clean up before coming here.
-		 */
-		return;
-	}
 	bnxt_re_setup_cc(rdev, false);
 	ib_unregister_device(&rdev->ibdev);
 	bnxt_re_dev_uninit(rdev, op_type);

From 8238c7bd84209c8216b1381ab0dbe6db9e203769 Mon Sep 17 00:00:00 2001
From: Selvin Xavier <selvin.xavier@broadcom.com>
Date: Tue, 4 Feb 2025 00:21:25 -0800
Subject: [PATCH 0273/2753] RDMA/bnxt_re: Fix the statistics for Gen P7 VF

Gen P7 VF support the extended stats and is prevented
by a VF check. Fix the check to issue the FW command
for GenP7 VFs also.

Fixes: 1801d87b3598 ("RDMA/bnxt_re: Support new 5760X P7 devices")
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1738657285-23968-5-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/hw_counters.c | 4 ++--
 drivers/infiniband/hw/bnxt_re/qplib_res.h   | 8 ++++++++
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/hw_counters.c b/drivers/infiniband/hw/bnxt_re/hw_counters.c
index 3ac47f4e61229..f039aefcaf675 100644
--- a/drivers/infiniband/hw/bnxt_re/hw_counters.c
+++ b/drivers/infiniband/hw/bnxt_re/hw_counters.c
@@ -348,8 +348,8 @@ int bnxt_re_ib_get_hw_stats(struct ib_device *ibdev,
 			goto done;
 		}
 		bnxt_re_copy_err_stats(rdev, stats, err_s);
-		if (_is_ext_stats_supported(rdev->dev_attr->dev_cap_flags) &&
-		    !rdev->is_virtfn) {
+		if (bnxt_ext_stats_supported(rdev->chip_ctx, rdev->dev_attr->dev_cap_flags,
+					     rdev->is_virtfn)) {
 			rc = bnxt_re_get_ext_stat(rdev, stats);
 			if (rc) {
 				clear_bit(BNXT_RE_FLAG_ISSUE_ROCE_STATS,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index be5d907a036b6..711990232de1c 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -547,6 +547,14 @@ static inline bool _is_ext_stats_supported(u16 dev_cap_flags)
 		CREQ_QUERY_FUNC_RESP_SB_EXT_STATS;
 }
 
+static inline int bnxt_ext_stats_supported(struct bnxt_qplib_chip_ctx *ctx,
+					   u16 flags, bool virtfn)
+{
+	/* ext stats supported if cap flag is set AND is a PF OR a Thor2 VF */
+	return (_is_ext_stats_supported(flags) &&
+		((virtfn && bnxt_qplib_is_chip_gen_p7(ctx)) || (!virtfn)));
+}
+
 static inline bool _is_hw_retx_supported(u16 dev_cap_flags)
 {
 	return dev_cap_flags &

From b921f66ccf5e8cf1b8a5052b35ceda454f19f5dd Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Mon, 3 Feb 2025 15:30:56 -0600
Subject: [PATCH 0274/2753] dt-bindings: rockchip: pmu: Ensure all properties
 are defined

Device specific schemas should not allow undefined properties which is
what 'additionalProperties: true' allows. Add the missing child nodes
and fix this constraint.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250203213056.13827-1-robh@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 Documentation/devicetree/bindings/arm/rockchip/pmu.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
index 932f981265ccb..52016a141227b 100644
--- a/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
+++ b/Documentation/devicetree/bindings/arm/rockchip/pmu.yaml
@@ -53,11 +53,17 @@ properties:
   reg:
     maxItems: 1
 
+  power-controller:
+    type: object
+
+  reboot-mode:
+    type: object
+
 required:
   - compatible
   - reg
 
-additionalProperties: true
+additionalProperties: false
 
 examples:
   - |

From 2c202e6c4f4dd19d2e8c1dfac9df05170aa3934f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Sat, 8 Feb 2025 08:29:15 +0900
Subject: [PATCH 0275/2753] ata: libahci_platform: Do not set mask_port_map
 when not needed

Commit 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive
port numbers") modified ahci_platform_get_resources() to allow
identifying the ports of a controller that are defined as child nodes of
the controller node in order to support non-consecutive port numbers (as
defined by the platform device tree).

However, this commit also erroneously sets bit 0 of
hpriv->mask_port_map when the platform devices tree does not define port
child nodes, to match the fact that the temporary default number of
ports used in that case is 1 (which is also consistent with the fact
that only index 0 of hpriv->phys[] is initialized with the call to
ahci_platform_get_phy(). But doing so causes ahci_platform_init_host()
to initialize and probe only the first port, even if this function
determines that the controller has in fact multiple ports using the
capability register of the controller (through a call to
ahci_nr_ports()). This can be seen with the ahci_mvebu driver (Armada
385 SoC) with the second port declared as "dummy":

ahci-mvebu f10a8000.sata: masking port_map 0x3 -> 0x1
ahci-mvebu f10a8000.sata: AHCI vers 0001.0000, 32 command slots, 6 Gbps, platform mode
ahci-mvebu f10a8000.sata: 1/2 ports implemented (port mask 0x1)
ahci-mvebu f10a8000.sata: flags: 64bit ncq sntf led only pmp fbs pio slum part sxs
scsi host0: ahci-mvebu
scsi host1: ahci-mvebu
ata1: SATA max UDMA/133 mmio [mem 0xf10a8000-0xf10a9fff] port 0x100 irq 40 lpm-pol 0
ata2: DUMMY

Fix this issue by removing setting bit 0 of hpriv->mask_port_map when
the platform device tree does not define port child nodes.

Reported-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Fixes: 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port numbers")
Tested-by: Klaus Kudielka <klaus.kudielka@gmail.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Acked-by: Josua Mayer <josua@solid-run.com>
Link: https://lore.kernel.org/r/20250207232915.1439174-1-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libahci_platform.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/ata/libahci_platform.c b/drivers/ata/libahci_platform.c
index 53b2c7719dc51..91d44302eac92 100644
--- a/drivers/ata/libahci_platform.c
+++ b/drivers/ata/libahci_platform.c
@@ -651,8 +651,6 @@ struct ahci_host_priv *ahci_platform_get_resources(struct platform_device *pdev,
 		 * If no sub-node was found, keep this for device tree
 		 * compatibility
 		 */
-		hpriv->mask_port_map |= BIT(0);
-
 		rc = ahci_platform_get_phy(hpriv, 0, dev, dev->of_node);
 		if (rc)
 			goto err_out;

From a0519433ad8d347d8fb0e7f118f468456dff00fd Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 10 Feb 2025 20:31:05 +0800
Subject: [PATCH 0276/2753] wifi: rtw89: debugfs depends on CFG80211's one

The wiphy_locked_debugfs_read() and wiphy_locked_debugfs_write() used
by rtw89 are defined if CFG80211_DEBUGFS enabled. Add the dependency
accordingly.

Fixes: 8fdf78f3cd5f ("wifi: rtw89: debugfs: use wiphy_locked_debugfs_{read,write}() if needed")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502101810.3CUpUL7p-lkp@intel.com/
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250210123105.10466-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/Kconfig b/drivers/net/wireless/realtek/rtw89/Kconfig
index b1c86cdd9c0e8..205d7ecca7d78 100644
--- a/drivers/net/wireless/realtek/rtw89/Kconfig
+++ b/drivers/net/wireless/realtek/rtw89/Kconfig
@@ -123,7 +123,7 @@ config RTW89_DEBUGMSG
 
 config RTW89_DEBUGFS
 	bool "Realtek rtw89 debugfs support"
-	depends on RTW89_CORE
+	depends on RTW89_CORE && CFG80211_DEBUGFS
 	select RTW89_DEBUG
 	help
 	  Enable debugfs support

From 17987453a9d997c4d0749abc52f047bfa275427a Mon Sep 17 00:00:00 2001
From: Mohan Kumar D <mkumard@nvidia.com>
Date: Mon, 10 Feb 2025 19:24:12 +0530
Subject: [PATCH 0277/2753] dmaengine: tegra210-adma: Use div_u64 for 64 bit
 division

The ADMA base and page address are represented using a 64-bit variable.
To accurately derive the exact ADMA page number provided from the DT
properties, use the div_u64() to divide the address difference between
adma page and base address by the page offset.

This change fixes the below error
   "ERROR: modpost: "__udivdi3" [drivers/dma/tegra210-adma.ko] undefined!
    ld: drivers/dma/tegra210-adma.o: in function `tegra_adma_probe':
    tegra210-adma.c:(.text+0x12cf): undefined reference to `__udivdi3'"

Fixes: 68811c928f88 ("dmaengine: tegra210-adma: Support channel page")
Cc: stable@vger.kernel.org
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202412250204.GCQhdKe3-lkp@intel.com/
Signed-off-by: Mohan Kumar D <mkumard@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20250210135413.2504272-2-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra210-adma.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index 6896da8ac7ef6..a0bd4822ed808 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -887,7 +887,8 @@ static int tegra_adma_probe(struct platform_device *pdev)
 	const struct tegra_adma_chip_data *cdata;
 	struct tegra_adma *tdma;
 	struct resource *res_page, *res_base;
-	int ret, i, page_no;
+	u64 page_no, page_offset;
+	int ret, i;
 
 	cdata = of_device_get_match_data(&pdev->dev);
 	if (!cdata) {
@@ -914,10 +915,16 @@ static int tegra_adma_probe(struct platform_device *pdev)
 
 		res_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "global");
 		if (res_base) {
-			page_no = (res_page->start - res_base->start) / cdata->ch_base_offset;
-			if (page_no <= 0)
+			if (WARN_ON(res_page->start <= res_base->start))
 				return -EINVAL;
-			tdma->ch_page_no = page_no - 1;
+
+			page_offset = res_page->start - res_base->start;
+			page_no = div_u64(page_offset, cdata->ch_base_offset);
+
+			if (WARN_ON(page_no == 0))
+				return -EINVAL;
+
+			tdma->ch_page_no = lower_32_bits(page_no) - 1;
 			tdma->base_addr = devm_ioremap_resource(&pdev->dev, res_base);
 			if (IS_ERR(tdma->base_addr))
 				return PTR_ERR(tdma->base_addr);

From 76ed9b7d177ed5aa161a824ea857619b88542de1 Mon Sep 17 00:00:00 2001
From: Mohan Kumar D <mkumard@nvidia.com>
Date: Mon, 10 Feb 2025 19:24:13 +0530
Subject: [PATCH 0278/2753] dmaengine: tegra210-adma: check for adma max page

Have additional check for max channel page during the probe
to cover if any offset overshoot happens due to wrong DT
configuration.

Fixes: 68811c928f88 ("dmaengine: tegra210-adma: Support channel page")
Cc: stable@vger.kernel.org
Signed-off-by: Mohan Kumar D <mkumard@nvidia.com>
Reviewed-by: Jon Hunter <jonathanh@nvidia.com>
Acked-by: Thierry Reding <treding@nvidia.com>
Link: https://lore.kernel.org/r/20250210135413.2504272-3-mkumard@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/tegra210-adma.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/tegra210-adma.c b/drivers/dma/tegra210-adma.c
index a0bd4822ed808..801740ad8e0d9 100644
--- a/drivers/dma/tegra210-adma.c
+++ b/drivers/dma/tegra210-adma.c
@@ -83,7 +83,9 @@ struct tegra_adma;
  * @nr_channels: Number of DMA channels available.
  * @ch_fifo_size_mask: Mask for FIFO size field.
  * @sreq_index_offset: Slave channel index offset.
+ * @max_page: Maximum ADMA Channel Page.
  * @has_outstanding_reqs: If DMA channel can have outstanding requests.
+ * @set_global_pg_config: Global page programming.
  */
 struct tegra_adma_chip_data {
 	unsigned int (*adma_get_burst_config)(unsigned int burst_size);
@@ -99,6 +101,7 @@ struct tegra_adma_chip_data {
 	unsigned int nr_channels;
 	unsigned int ch_fifo_size_mask;
 	unsigned int sreq_index_offset;
+	unsigned int max_page;
 	bool has_outstanding_reqs;
 	void (*set_global_pg_config)(struct tegra_adma *tdma);
 };
@@ -854,6 +857,7 @@ static const struct tegra_adma_chip_data tegra210_chip_data = {
 	.nr_channels		= 22,
 	.ch_fifo_size_mask	= 0xf,
 	.sreq_index_offset	= 2,
+	.max_page		= 0,
 	.has_outstanding_reqs	= false,
 	.set_global_pg_config	= NULL,
 };
@@ -871,6 +875,7 @@ static const struct tegra_adma_chip_data tegra186_chip_data = {
 	.nr_channels		= 32,
 	.ch_fifo_size_mask	= 0x1f,
 	.sreq_index_offset	= 4,
+	.max_page		= 4,
 	.has_outstanding_reqs	= true,
 	.set_global_pg_config	= tegra186_adma_global_page_config,
 };
@@ -921,7 +926,7 @@ static int tegra_adma_probe(struct platform_device *pdev)
 			page_offset = res_page->start - res_base->start;
 			page_no = div_u64(page_offset, cdata->ch_base_offset);
 
-			if (WARN_ON(page_no == 0))
+			if (WARN_ON(page_no == 0 || page_no > cdata->max_page))
 				return -EINVAL;
 
 			tdma->ch_page_no = lower_32_bits(page_no) - 1;

From 1c1377d7b60c2d96eefab0bd9740d4a27fb0e1d3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:52 -0800
Subject: [PATCH 0279/2753] netconsole: consolidate send buffers into
 netconsole_target struct

Move the static buffers from send_msg_no_fragmentation() and
send_msg_fragmented() into the netconsole_target structure. This
simplifies the code by:
- Eliminating redundant static buffers
- Centralizing buffer management in the target structure
- Reducing memory usage by 1KB (one buffer instead of two)

The buffer in netconsole_target is protected by target_list_lock,
maintaining the same synchronization semantics as the original code.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 86ab4a42769a4..034caaa265635 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -123,6 +123,7 @@ struct netconsole_target_stats  {
  *		remote_ip	(read-write)
  *		local_mac	(read-only)
  *		remote_mac	(read-write)
+ * @buf:	The buffer used to send the full msg to the network stack
  */
 struct netconsole_target {
 	struct list_head	list;
@@ -137,6 +138,8 @@ struct netconsole_target {
 	bool			extended;
 	bool			release;
 	struct netpoll		np;
+	/* protected by target_list_lock */
+	char			buf[MAX_PRINT_CHUNK];
 };
 
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
@@ -1117,7 +1120,6 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 				      int msg_len,
 				      int release_len)
 {
-	static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */
 	const char *userdata = NULL;
 	const char *release;
 
@@ -1128,18 +1130,18 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 	if (release_len) {
 		release = init_utsname()->release;
 
-		scnprintf(buf, MAX_PRINT_CHUNK, "%s,%s", release, msg);
+		scnprintf(nt->buf, MAX_PRINT_CHUNK, "%s,%s", release, msg);
 		msg_len += release_len;
 	} else {
-		memcpy(buf, msg, msg_len);
+		memcpy(nt->buf, msg, msg_len);
 	}
 
 	if (userdata)
-		msg_len += scnprintf(&buf[msg_len],
+		msg_len += scnprintf(&nt->buf[msg_len],
 				     MAX_PRINT_CHUNK - msg_len,
 				     "%s", userdata);
 
-	send_udp(nt, buf, msg_len);
+	send_udp(nt, nt->buf, msg_len);
 }
 
 static void append_release(char *buf)
@@ -1150,7 +1152,7 @@ static void append_release(char *buf)
 	scnprintf(buf, MAX_PRINT_CHUNK, "%s,", release);
 }
 
-static void send_fragmented_body(struct netconsole_target *nt, char *buf,
+static void send_fragmented_body(struct netconsole_target *nt,
 				 const char *msgbody, int header_len,
 				 int msgbody_len)
 {
@@ -1181,7 +1183,7 @@ static void send_fragmented_body(struct netconsole_target *nt, char *buf,
 		int this_offset = 0;
 		int this_chunk = 0;
 
-		this_header += scnprintf(buf + this_header,
+		this_header += scnprintf(nt->buf + this_header,
 					 MAX_PRINT_CHUNK - this_header,
 					 ",ncfrag=%d/%d;", offset,
 					 body_len);
@@ -1192,7 +1194,8 @@ static void send_fragmented_body(struct netconsole_target *nt, char *buf,
 					 MAX_PRINT_CHUNK - this_header);
 			if (WARN_ON_ONCE(this_chunk <= 0))
 				return;
-			memcpy(buf + this_header, msgbody + offset, this_chunk);
+			memcpy(nt->buf + this_header, msgbody + offset,
+			       this_chunk);
 			this_offset += this_chunk;
 		}
 
@@ -1226,13 +1229,13 @@ static void send_fragmented_body(struct netconsole_target *nt, char *buf,
 				 */
 				return;
 
-			memcpy(buf + this_header + this_offset,
+			memcpy(nt->buf + this_header + this_offset,
 			       userdata + sent_userdata,
 			       this_chunk);
 			this_offset += this_chunk;
 		}
 
-		send_udp(nt, buf, this_header + this_offset);
+		send_udp(nt, nt->buf, this_header + this_offset);
 		offset += this_offset;
 	}
 }
@@ -1242,7 +1245,6 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 				int msg_len,
 				int release_len)
 {
-	static char buf[MAX_PRINT_CHUNK]; /* protected by target_list_lock */
 	int header_len, msgbody_len;
 	const char *msgbody;
 
@@ -1260,16 +1262,16 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 	 * "ncfrag=<byte-offset>/<total-bytes>"
 	 */
 	if (release_len)
-		append_release(buf);
+		append_release(nt->buf);
 
 	/* Copy the header into the buffer */
-	memcpy(buf + release_len, msg, header_len);
+	memcpy(nt->buf + release_len, msg, header_len);
 	header_len += release_len;
 
 	/* for now on, the header will be persisted, and the msgbody
 	 * will be replaced
 	 */
-	send_fragmented_body(nt, buf, msgbody, header_len, msgbody_len);
+	send_fragmented_body(nt, msgbody, header_len, msgbody_len);
 }
 
 /**

From 4205f6495eea62c7f4042346e045e4ac706e1830 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:53 -0800
Subject: [PATCH 0280/2753] netconsole: Rename userdata to extradata

Rename "userdata" to "extradata" since this structure will hold both
user and system data in future patches. Keep "userdata" term only for
data that comes from userspace (configfs), while "extradata" encompasses
both userdata and future kerneldata.

These are the rules of the design

1. extradata_complete will hold userdata and sysdata (coming)
2. sysdata will come after userdata_length
3. extradata_complete[userdata_length] string will be replaced at every
   message
5. userdata is replaced when configfs changes (update_userdata())
6. sysdata is replaced at every message

Example:
  extradata_complete = "userkey=uservalue cpu=42"
  userdata_length = 17
  sysdata_length = 7 (space (" ") is part of sysdata)

Since sysdata is still not available, you will see the following in the
send functions:

	extradata_len = nt->userdata_length;

The upcoming patches will, which will add support for sysdata, will
change it to:

	extradata_len = nt->userdata_length + sysdata_len;

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 87 ++++++++++++++++++++--------------------
 1 file changed, 44 insertions(+), 43 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 034caaa265635..7f05c7f74c31c 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -45,12 +45,12 @@ MODULE_DESCRIPTION("Console driver for network interfaces");
 MODULE_LICENSE("GPL");
 
 #define MAX_PARAM_LENGTH		256
-#define MAX_USERDATA_ENTRY_LENGTH	256
-#define MAX_USERDATA_VALUE_LENGTH	200
+#define MAX_EXTRADATA_ENTRY_LEN		256
+#define MAX_EXTRADATA_VALUE_LEN	200
 /* The number 3 comes from userdata entry format characters (' ', '=', '\n') */
-#define MAX_USERDATA_NAME_LENGTH	(MAX_USERDATA_ENTRY_LENGTH - \
-					MAX_USERDATA_VALUE_LENGTH - 3)
-#define MAX_USERDATA_ITEMS		16
+#define MAX_EXTRADATA_NAME_LEN		(MAX_EXTRADATA_ENTRY_LEN - \
+					MAX_EXTRADATA_VALUE_LEN - 3)
+#define MAX_EXTRADATA_ITEMS		16
 #define MAX_PRINT_CHUNK			1000
 
 static char config[MAX_PARAM_LENGTH];
@@ -102,8 +102,8 @@ struct netconsole_target_stats  {
  * @list:	Links this target into the target_list.
  * @group:	Links us into the configfs subsystem hierarchy.
  * @userdata_group:	Links to the userdata configfs hierarchy
- * @userdata_complete:	Cached, formatted string of append
- * @userdata_length:	String length of userdata_complete
+ * @extradata_complete:	Cached, formatted string of append
+ * @userdata_length:	String length of usedata in extradata_complete.
  * @stats:	Packet send stats for the target. Used for debugging.
  * @enabled:	On / off knob to enable / disable target.
  *		Visible from userspace (read-write).
@@ -130,7 +130,7 @@ struct netconsole_target {
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
 	struct config_group	group;
 	struct config_group	userdata_group;
-	char userdata_complete[MAX_USERDATA_ENTRY_LENGTH * MAX_USERDATA_ITEMS];
+	char extradata_complete[MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS];
 	size_t			userdata_length;
 #endif
 	struct netconsole_target_stats stats;
@@ -690,7 +690,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 
 struct userdatum {
 	struct config_item item;
-	char value[MAX_USERDATA_VALUE_LENGTH];
+	char value[MAX_EXTRADATA_VALUE_LEN];
 };
 
 static struct userdatum *to_userdatum(struct config_item *item)
@@ -727,13 +727,13 @@ static void update_userdata(struct netconsole_target *nt)
 
 	/* Clear the current string in case the last userdatum was deleted */
 	nt->userdata_length = 0;
-	nt->userdata_complete[0] = 0;
+	nt->extradata_complete[0] = 0;
 
 	list_for_each(entry, &nt->userdata_group.cg_children) {
 		struct userdatum *udm_item;
 		struct config_item *item;
 
-		if (WARN_ON_ONCE(child_count >= MAX_USERDATA_ITEMS))
+		if (WARN_ON_ONCE(child_count >= MAX_EXTRADATA_ITEMS))
 			break;
 		child_count++;
 
@@ -741,19 +741,19 @@ static void update_userdata(struct netconsole_target *nt)
 		udm_item = to_userdatum(item);
 
 		/* Skip userdata with no value set */
-		if (strnlen(udm_item->value, MAX_USERDATA_VALUE_LENGTH) == 0)
+		if (strnlen(udm_item->value, MAX_EXTRADATA_VALUE_LEN) == 0)
 			continue;
 
-		/* This doesn't overflow userdata_complete since it will write
-		 * one entry length (1/MAX_USERDATA_ITEMS long), entry count is
+		/* This doesn't overflow extradata_complete since it will write
+		 * one entry length (1/MAX_EXTRADATA_ITEMS long), entry count is
 		 * checked to not exceed MAX items with child_count above
 		 */
-		complete_idx += scnprintf(&nt->userdata_complete[complete_idx],
-					  MAX_USERDATA_ENTRY_LENGTH, " %s=%s\n",
+		complete_idx += scnprintf(&nt->extradata_complete[complete_idx],
+					  MAX_EXTRADATA_ENTRY_LEN, " %s=%s\n",
 					  item->ci_name, udm_item->value);
 	}
-	nt->userdata_length = strnlen(nt->userdata_complete,
-				      sizeof(nt->userdata_complete));
+	nt->userdata_length = strnlen(nt->extradata_complete,
+				      sizeof(nt->extradata_complete));
 }
 
 static ssize_t userdatum_value_store(struct config_item *item, const char *buf,
@@ -764,7 +764,7 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf,
 	struct userdata *ud;
 	ssize_t ret;
 
-	if (count > MAX_USERDATA_VALUE_LENGTH)
+	if (count > MAX_EXTRADATA_VALUE_LEN)
 		return -EMSGSIZE;
 
 	mutex_lock(&dynamic_netconsole_mutex);
@@ -813,13 +813,13 @@ static struct config_item *userdatum_make_item(struct config_group *group,
 	struct userdata *ud;
 	size_t child_count;
 
-	if (strlen(name) > MAX_USERDATA_NAME_LENGTH)
+	if (strlen(name) > MAX_EXTRADATA_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	ud = to_userdata(&group->cg_item);
 	nt = userdata_to_target(ud);
 	child_count = list_count_nodes(&nt->userdata_group.cg_children);
-	if (child_count >= MAX_USERDATA_ITEMS)
+	if (child_count >= MAX_EXTRADATA_ITEMS)
 		return ERR_PTR(-ENOSPC);
 
 	udm = kzalloc(sizeof(*udm), GFP_KERNEL);
@@ -1120,11 +1120,11 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 				      int msg_len,
 				      int release_len)
 {
-	const char *userdata = NULL;
+	const char *extradata = NULL;
 	const char *release;
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
-	userdata = nt->userdata_complete;
+	extradata = nt->extradata_complete;
 #endif
 
 	if (release_len) {
@@ -1136,10 +1136,10 @@ static void send_msg_no_fragmentation(struct netconsole_target *nt,
 		memcpy(nt->buf, msg, msg_len);
 	}
 
-	if (userdata)
+	if (extradata)
 		msg_len += scnprintf(&nt->buf[msg_len],
 				     MAX_PRINT_CHUNK - msg_len,
-				     "%s", userdata);
+				     "%s", extradata);
 
 	send_udp(nt, nt->buf, msg_len);
 }
@@ -1156,24 +1156,25 @@ static void send_fragmented_body(struct netconsole_target *nt,
 				 const char *msgbody, int header_len,
 				 int msgbody_len)
 {
-	const char *userdata = NULL;
+	int sent_extradata, preceding_bytes;
+	const char *extradata = NULL;
 	int body_len, offset = 0;
-	int userdata_len = 0;
+	int extradata_len = 0;
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
-	userdata = nt->userdata_complete;
-	userdata_len = nt->userdata_length;
+	extradata = nt->extradata_complete;
+	extradata_len = nt->userdata_length;
 #endif
 
 	/* body_len represents the number of bytes that will be sent. This is
 	 * bigger than MAX_PRINT_CHUNK, thus, it will be split in multiple
 	 * packets
 	 */
-	body_len = msgbody_len + userdata_len;
+	body_len = msgbody_len + extradata_len;
 
 	/* In each iteration of the while loop below, we send a packet
 	 * containing the header and a portion of the body. The body is
-	 * composed of two parts: msgbody and userdata. We keep track of how
+	 * composed of two parts: msgbody and extradata. We keep track of how
 	 * many bytes have been sent so far using the offset variable, which
 	 * ranges from 0 to the total length of the body.
 	 */
@@ -1201,36 +1202,36 @@ static void send_fragmented_body(struct netconsole_target *nt,
 
 		/* msgbody was finally written, either in the previous
 		 * messages and/or in the current buf. Time to write
-		 * the userdata.
+		 * the extradata.
 		 */
 		msgbody_written |= offset + this_offset >= msgbody_len;
 
-		/* Msg body is fully written and there is pending userdata to
-		 * write, append userdata in this chunk
+		/* Msg body is fully written and there is pending extradata to
+		 * write, append extradata in this chunk
 		 */
 		if (msgbody_written && offset + this_offset < body_len) {
 			/* Track how much user data was already sent. First
 			 * time here, sent_userdata is zero
 			 */
-			int sent_userdata = (offset + this_offset) - msgbody_len;
+			sent_extradata = (offset + this_offset) - msgbody_len;
 			/* offset of bytes used in current buf */
-			int preceding_bytes = this_chunk + this_header;
+			preceding_bytes = this_chunk + this_header;
 
-			if (WARN_ON_ONCE(sent_userdata < 0))
+			if (WARN_ON_ONCE(sent_extradata < 0))
 				return;
 
-			this_chunk = min(userdata_len - sent_userdata,
+			this_chunk = min(extradata_len - sent_extradata,
 					 MAX_PRINT_CHUNK - preceding_bytes);
 			if (WARN_ON_ONCE(this_chunk < 0))
 				/* this_chunk could be zero if all the previous
 				 * message used all the buffer. This is not a
-				 * problem, userdata will be sent in the next
+				 * problem, extradata will be sent in the next
 				 * iteration
 				 */
 				return;
 
 			memcpy(nt->buf + this_header + this_offset,
-			       userdata + sent_userdata,
+			       extradata + sent_extradata,
 			       this_chunk);
 			this_offset += this_chunk;
 		}
@@ -1287,17 +1288,17 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
 			     int msg_len)
 {
-	int userdata_len = 0;
+	int extradata_len = 0;
 	int release_len = 0;
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
-	userdata_len = nt->userdata_length;
+	extradata_len = nt->userdata_length;
 #endif
 
 	if (nt->release)
 		release_len = strlen(init_utsname()->release) + 1;
 
-	if (msg_len + release_len + userdata_len <= MAX_PRINT_CHUNK)
+	if (msg_len + release_len + extradata_len <= MAX_PRINT_CHUNK)
 		return send_msg_no_fragmentation(nt, msg, msg_len, release_len);
 
 	return send_msg_fragmented(nt, msg, msg_len, release_len);

From 563fe939a81ab08198b78dc8451ef3090969f30b Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:54 -0800
Subject: [PATCH 0281/2753] netconsole: Helper to count number of used entries

Add a helper function nr_extradata_entries() to count the number of used
extradata entries in a netconsole target. This refactors the duplicate
code for counting entries into a single function, which will be reused
by upcoming CPU sysdata changes.

The helper uses list_count_nodes() to count the number of children in
the userdata group configfs hierarchy.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 7f05c7f74c31c..15daaba65c882 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -662,6 +662,16 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf,
 	return ret;
 }
 
+/* Count number of entries we have in extradata.
+ * This is important because the extradata_complete only supports
+ * MAX_EXTRADATA_ITEMS entries. Before enabling any new {user,sys}data
+ * feature, number of entries needs to checked for available space.
+ */
+static size_t count_extradata_entries(struct netconsole_target *nt)
+{
+	return list_count_nodes(&nt->userdata_group.cg_children);
+}
+
 static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 		size_t count)
 {
@@ -811,15 +821,13 @@ static struct config_item *userdatum_make_item(struct config_group *group,
 	struct netconsole_target *nt;
 	struct userdatum *udm;
 	struct userdata *ud;
-	size_t child_count;
 
 	if (strlen(name) > MAX_EXTRADATA_NAME_LEN)
 		return ERR_PTR(-ENAMETOOLONG);
 
 	ud = to_userdata(&group->cg_item);
 	nt = userdata_to_target(ud);
-	child_count = list_count_nodes(&nt->userdata_group.cg_children);
-	if (child_count >= MAX_EXTRADATA_ITEMS)
+	if (count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS)
 		return ERR_PTR(-ENOSPC);
 
 	udm = kzalloc(sizeof(*udm), GFP_KERNEL);

From 364f67837e86cfd59ef8727dbf6db15594281d4d Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:55 -0800
Subject: [PATCH 0282/2753] netconsole: Introduce configfs helpers for sysdata
 features

This patch introduces a bitfield to store sysdata features in the
netconsole_target struct. It also adds configfs helpers to enable
or disable the CPU_NR feature, which populates the CPU number in
sysdata.

The patch provides the necessary infrastructure to set or unset the
CPU_NR feature, but does not modify the message itself.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 81 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 81 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 15daaba65c882..710330ae8ee46 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -97,6 +97,15 @@ struct netconsole_target_stats  {
 	struct u64_stats_sync syncp;
 };
 
+/* Features enabled in sysdata. Contrary to userdata, this data is populated by
+ * the kernel. The fields are designed as bitwise flags, allowing multiple
+ * features to be set in sysdata_fields.
+ */
+enum sysdata_feature {
+	/* Populate the CPU that sends the message */
+	CPU_NR = BIT(0),
+};
+
 /**
  * struct netconsole_target - Represents a configured netconsole target.
  * @list:	Links this target into the target_list.
@@ -104,6 +113,7 @@ struct netconsole_target_stats  {
  * @userdata_group:	Links to the userdata configfs hierarchy
  * @extradata_complete:	Cached, formatted string of append
  * @userdata_length:	String length of usedata in extradata_complete.
+ * @sysdata_fields:	Sysdata features enabled.
  * @stats:	Packet send stats for the target. Used for debugging.
  * @enabled:	On / off knob to enable / disable target.
  *		Visible from userspace (read-write).
@@ -132,6 +142,8 @@ struct netconsole_target {
 	struct config_group	userdata_group;
 	char extradata_complete[MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS];
 	size_t			userdata_length;
+	/* bit-wise with sysdata_feature bits */
+	u32			sysdata_fields;
 #endif
 	struct netconsole_target_stats stats;
 	bool			enabled;
@@ -399,6 +411,19 @@ static ssize_t transmit_errors_show(struct config_item *item, char *buf)
 	return sysfs_emit(buf, "%llu\n", xmit_drop_count + enomem_count);
 }
 
+/* configfs helper to display if cpu_nr sysdata feature is enabled */
+static ssize_t sysdata_cpu_nr_enabled_show(struct config_item *item, char *buf)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool cpu_nr_enabled;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	cpu_nr_enabled = !!(nt->sysdata_fields & CPU_NR);
+	mutex_unlock(&dynamic_netconsole_mutex);
+
+	return sysfs_emit(buf, "%d\n", cpu_nr_enabled);
+}
+
 /*
  * This one is special -- targets created through the configfs interface
  * are not enabled (and the corresponding netpoll activated) by default.
@@ -793,7 +818,62 @@ static ssize_t userdatum_value_store(struct config_item *item, const char *buf,
 	return ret;
 }
 
+/* disable_sysdata_feature - Disable sysdata feature and clean sysdata
+ * @nt: target that is disabling the feature
+ * @feature: feature being disabled
+ */
+static void disable_sysdata_feature(struct netconsole_target *nt,
+				    enum sysdata_feature feature)
+{
+	nt->sysdata_fields &= ~feature;
+	nt->extradata_complete[nt->userdata_length] = 0;
+}
+
+/* configfs helper to sysdata cpu_nr feature */
+static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
+					    const char *buf, size_t count)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool cpu_nr_enabled, curr;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &cpu_nr_enabled);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	curr = nt->sysdata_fields & CPU_NR;
+	if (cpu_nr_enabled == curr)
+		/* no change requested */
+		goto unlock_ok;
+
+	if (cpu_nr_enabled &&
+	    count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) {
+		/* user wants the new feature, but there is no space in the
+		 * buffer.
+		 */
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	if (cpu_nr_enabled)
+		nt->sysdata_fields |= CPU_NR;
+	else
+		/* This is special because extradata_complete might have
+		 * remaining data from previous sysdata, and it needs to be
+		 * cleaned.
+		 */
+		disable_sysdata_feature(nt, CPU_NR);
+
+unlock_ok:
+	ret = strnlen(buf, count);
+unlock:
+	mutex_unlock(&dynamic_netconsole_mutex);
+	return ret;
+}
+
 CONFIGFS_ATTR(userdatum_, value);
+CONFIGFS_ATTR(sysdata_, cpu_nr_enabled);
 
 static struct configfs_attribute *userdatum_attrs[] = {
 	&userdatum_attr_value,
@@ -853,6 +933,7 @@ static void userdatum_drop(struct config_group *group, struct config_item *item)
 }
 
 static struct configfs_attribute *userdata_attrs[] = {
+	&sysdata_attr_cpu_nr_enabled,
 	NULL,
 };
 

From 2bae25b16aea249f0e96757b6cd28b03d2b4397f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:56 -0800
Subject: [PATCH 0283/2753] netconsole: Include sysdata in extradata entry
 count

Modify count_extradata_entries() to include sysdata fields when
calculating the total number of extradata entries. This change ensures
that the sysdata feature, specifically the CPU number field, is
correctly counted against the MAX_EXTRADATA_ITEMS limit.

The modification adds a simple check for the CPU_NR flag in the
sysdata_fields, incrementing the entry count accordingly.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 710330ae8ee46..50739c7dbfb6a 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -694,7 +694,15 @@ static ssize_t remote_ip_store(struct config_item *item, const char *buf,
  */
 static size_t count_extradata_entries(struct netconsole_target *nt)
 {
-	return list_count_nodes(&nt->userdata_group.cg_children);
+	size_t entries;
+
+	/* Userdata entries */
+	entries = list_count_nodes(&nt->userdata_group.cg_children);
+	/* Plus sysdata entries */
+	if (nt->sysdata_fields & CPU_NR)
+		entries += 1;
+
+	return entries;
 }
 
 static ssize_t remote_mac_store(struct config_item *item, const char *buf,

From ec15bc46c63cc21bba4c4071060797a4b51f50de Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:57 -0800
Subject: [PATCH 0284/2753] netconsole: add support for sysdata and CPU
 population

Add infrastructure to automatically append kernel-generated data (sysdata)
to netconsole messages. As the first use case, implement CPU number
population, which adds the CPU that sent the message.

This change introduces three distinct data types:
- extradata: The complete set of appended data (sysdata + userdata)
- userdata: User-provided key-value pairs from userspace
- sysdata: Kernel-populated data (e.g. cpu=XX)

The implementation adds a new configfs attribute 'cpu_nr' to control CPU
number population per target. When enabled, each message is tagged with
its originating CPU. The sysdata is dynamically updated at message time
and appended after any existing userdata.

The CPU number is formatted as "cpu=XX" and is added to the extradata
buffer, respecting the existing size limits.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/netconsole.c | 53 ++++++++++++++++++++++++++++++++--------
 1 file changed, 43 insertions(+), 10 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 50739c7dbfb6a..f77eddf221850 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1117,6 +1117,40 @@ static void populate_configfs_item(struct netconsole_target *nt,
 	init_target_config_group(nt, target_name);
 }
 
+/*
+ * prepare_extradata - append sysdata at extradata_complete in runtime
+ * @nt: target to send message to
+ */
+static int prepare_extradata(struct netconsole_target *nt)
+{
+	int sysdata_len, extradata_len;
+
+	/* userdata was appended when configfs write helper was called
+	 * by update_userdata().
+	 */
+	extradata_len = nt->userdata_length;
+
+	if (!(nt->sysdata_fields & CPU_NR))
+		goto out;
+
+	/* Append cpu=%d at extradata_complete after userdata str */
+	sysdata_len = scnprintf(&nt->extradata_complete[nt->userdata_length],
+				MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n",
+				raw_smp_processor_id());
+
+	extradata_len += sysdata_len;
+
+	WARN_ON_ONCE(extradata_len >
+		     MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS);
+
+out:
+	return extradata_len;
+}
+#else /* CONFIG_NETCONSOLE_DYNAMIC not set */
+static int prepare_extradata(struct netconsole_target *nt)
+{
+	return 0;
+}
 #endif	/* CONFIG_NETCONSOLE_DYNAMIC */
 
 /* Handle network interface device notifications */
@@ -1251,16 +1285,14 @@ static void append_release(char *buf)
 
 static void send_fragmented_body(struct netconsole_target *nt,
 				 const char *msgbody, int header_len,
-				 int msgbody_len)
+				 int msgbody_len, int extradata_len)
 {
 	int sent_extradata, preceding_bytes;
 	const char *extradata = NULL;
 	int body_len, offset = 0;
-	int extradata_len = 0;
 
 #ifdef CONFIG_NETCONSOLE_DYNAMIC
 	extradata = nt->extradata_complete;
-	extradata_len = nt->userdata_length;
 #endif
 
 	/* body_len represents the number of bytes that will be sent. This is
@@ -1341,7 +1373,8 @@ static void send_fragmented_body(struct netconsole_target *nt,
 static void send_msg_fragmented(struct netconsole_target *nt,
 				const char *msg,
 				int msg_len,
-				int release_len)
+				int release_len,
+				int extradata_len)
 {
 	int header_len, msgbody_len;
 	const char *msgbody;
@@ -1369,7 +1402,8 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 	/* for now on, the header will be persisted, and the msgbody
 	 * will be replaced
 	 */
-	send_fragmented_body(nt, msgbody, header_len, msgbody_len);
+	send_fragmented_body(nt, msgbody, header_len, msgbody_len,
+			     extradata_len);
 }
 
 /**
@@ -1385,12 +1419,10 @@ static void send_msg_fragmented(struct netconsole_target *nt,
 static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
 			     int msg_len)
 {
-	int extradata_len = 0;
 	int release_len = 0;
+	int extradata_len;
 
-#ifdef CONFIG_NETCONSOLE_DYNAMIC
-	extradata_len = nt->userdata_length;
-#endif
+	extradata_len = prepare_extradata(nt);
 
 	if (nt->release)
 		release_len = strlen(init_utsname()->release) + 1;
@@ -1398,7 +1430,8 @@ static void send_ext_msg_udp(struct netconsole_target *nt, const char *msg,
 	if (msg_len + release_len + extradata_len <= MAX_PRINT_CHUNK)
 		return send_msg_no_fragmentation(nt, msg, msg_len, release_len);
 
-	return send_msg_fragmented(nt, msg, msg_len, release_len);
+	return send_msg_fragmented(nt, msg, msg_len, release_len,
+				   extradata_len);
 }
 
 static void write_ext_msg(struct console *con, const char *msg,

From 12fd83ca44d8c4b0a78beab8178a1a6754eae1b3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:58 -0800
Subject: [PATCH 0285/2753] netconsole: selftest: test for sysdata CPU

Add a new selftest to verify that the netconsole module correctly
handles CPU runtime data in sysdata. The test validates three scenarios:

1. Basic CPU sysdata functionality - verifies that cpu=X is appended to
   messages
2. CPU sysdata with userdata - ensures CPU data works alongside userdata
3. Disabled CPU sysdata - confirms no CPU data is included when disabled

The test uses taskset to control which CPU sends messages and verifies
the reported CPU matches the one used. This helps ensure that netconsole
accurately tracks and reports the originating CPU of messages.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/drivers/net/Makefile  |   1 +
 .../drivers/net/lib/sh/lib_netcons.sh         |  17 ++
 .../selftests/drivers/net/netcons_sysdata.sh  | 167 ++++++++++++++++++
 3 files changed, 185 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/netcons_sysdata.sh

diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index c7f1c443f2af0..28b6d47f812dd 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -9,6 +9,7 @@ TEST_PROGS := \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \
 	netcons_overflow.sh \
+	netcons_sysdata.sh \
 	ping.py \
 	queues.py \
 	stats.py \
diff --git a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
index 0c262b123fdd3..3c96b022954db 100644
--- a/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
+++ b/tools/testing/selftests/drivers/net/lib/sh/lib_netcons.sh
@@ -230,3 +230,20 @@ function check_for_dependencies() {
 		exit "${ksft_skip}"
 	fi
 }
+
+function check_for_taskset() {
+	if ! which taskset > /dev/null ; then
+		echo "SKIP: taskset(1) is not available" >&2
+		exit "${ksft_skip}"
+	fi
+}
+
+# This is necessary if running multiple tests in a row
+function pkill_socat() {
+	PROCESS_NAME="socat UDP-LISTEN:6666,fork ${OUTPUT_FILE}"
+	# socat runs under timeout(1), kill it if it is still alive
+	# do not fail if socat doesn't exist anymore
+	set +e
+	pkill -f "${PROCESS_NAME}"
+	set -e
+}
diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
new file mode 100755
index 0000000000000..2b78fd1f5982f
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
@@ -0,0 +1,167 @@
+#!/usr/bin/env bash
+# SPDX-License-Identifier: GPL-2.0
+
+# A test that makes sure that sysdata runtime CPU data is properly set
+# when a message is sent.
+#
+# There are 3 different tests, every time sent using a random CPU.
+#  - Test #1
+#    * Only enable cpu_nr sysdata feature.
+#  - Test #2
+#    * Keep cpu_nr sysdata feature enable and enable userdata.
+#  - Test #3
+#    * keep userdata enabled, and disable sysdata cpu_nr feature.
+#
+# Author: Breno Leitao <leitao@debian.org>
+
+set -euo pipefail
+
+SCRIPTDIR=$(dirname "$(readlink -e "${BASH_SOURCE[0]}")")
+
+source "${SCRIPTDIR}"/lib/sh/lib_netcons.sh
+
+# Enable the sysdata cpu_nr feature
+function set_cpu_nr() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/cpu_nr_enabled" ]]
+	then
+		echo "Populate CPU configfs path not available in ${NETCONS_PATH}/userdata/cpu_nr_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
+}
+
+# Disable the sysdata cpu_nr feature
+function unset_cpu_nr() {
+	echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
+}
+
+# Test if MSG content and `cpu=${CPU}` exists in OUTPUT_FILE
+function validate_sysdata_cpu_exists() {
+	# OUTPUT_FILE will contain something like:
+	# 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM
+	#  userdatakey=userdatavalue
+	#  cpu=X
+
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then
+		echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	# Check if cpu=XX exists in the file and matches the one used
+	# in taskset(1)
+	if ! grep -q "cpu=${CPU}\+" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'cpu=${CPU}' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	rm "${OUTPUT_FILE}"
+	pkill_socat
+}
+
+# Test if MSG content exists in OUTPUT_FILE but no `cpu=` string
+function validate_sysdata_no_cpu() {
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "${MSG}" "${OUTPUT_FILE}"; then
+		echo "FAIL: ${MSG} not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	if grep -q "cpu=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'cpu=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
+	rm "${OUTPUT_FILE}"
+}
+
+# Start socat, send the message and wait for the file to show up in the file
+# system
+function runtest {
+	# Listen for netconsole port inside the namespace and destination
+	# interface
+	listen_port_and_save_to "${OUTPUT_FILE}" &
+	# Wait for socat to start and listen to the port.
+	wait_local_port_listen "${NAMESPACE}" "${PORT}" udp
+	# Send the message
+	taskset -c "${CPU}" echo "${MSG}: ${TARGET}" > /dev/kmsg
+	# Wait until socat saves the file to disk
+	busywait "${BUSYWAIT_TIMEOUT}" test -s "${OUTPUT_FILE}"
+}
+
+# ========== #
+# Start here #
+# ========== #
+
+modprobe netdevsim 2> /dev/null || true
+modprobe netconsole 2> /dev/null || true
+
+# Check for basic system dependency and exit if not found
+check_for_dependencies
+# This test also depends on taskset(1). Check for it before starting the test
+check_for_taskset
+
+# Set current loglevel to KERN_INFO(6), and default to KERN_NOTICE(5)
+echo "6 5" > /proc/sys/kernel/printk
+# Remove the namespace, interfaces and netconsole target on exit
+trap cleanup EXIT
+# Create one namespace and two interfaces
+set_network
+# Create a dynamic target for netconsole
+create_dynamic_target
+
+#====================================================
+# TEST #1
+# Send message from a random CPU
+#====================================================
+# Random CPU in the system
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_1"
+MSG="Test #1 from CPU${CPU}"
+# Enable the auto population of cpu_nr
+set_cpu_nr
+runtest
+# Make sure the message was received in the dst part
+# and exit
+validate_sysdata_cpu_exists
+
+#====================================================
+# TEST #2
+# This test now adds userdata together with sysdata
+# ===================================================
+# Get a new random CPU
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_2"
+MSG="Test #2 from CPU${CPU}"
+set_user_data
+runtest
+validate_sysdata_cpu_exists
+
+# ===================================================
+# TEST #3
+# Unset cpu_nr, so, no CPU should be appended.
+# userdata is still set
+# ===================================================
+CPU=$((RANDOM % $(nproc)))
+OUTPUT_FILE="/tmp/${TARGET}_3"
+MSG="Test #3 from CPU${CPU}"
+# Enable the auto population of cpu_nr
+unset_cpu_nr
+runtest
+# At this time, cpu= shouldn't be present in the msg
+validate_sysdata_no_cpu
+
+exit "${ksft_pass}"

From a7aec70a9092aec61a29ad1e1fc387ef888a6ad6 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Feb 2025 03:05:59 -0800
Subject: [PATCH 0286/2753] netconsole: docs: Add documentation for CPU number
 auto-population

Update the netconsole documentation to explain the new feature that
allows automatic population of the CPU number.

The key changes include introducing a new section titled "CPU number
auto population in userdata", explaining how to enable the CPU number
auto-population feature by writing to the "populate_cpu_nr" file in the
netconsole configfs hierarchy.

This documentation update ensures users are aware of the new CPU number
auto-population functionality and how to leverage it for better
demultiplexing and visibility of parallel netconsole output.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 Documentation/networking/netconsole.rst | 45 +++++++++++++++++++++++++
 1 file changed, 45 insertions(+)

diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
index 94c4680fdf3e7..84803c59968a3 100644
--- a/Documentation/networking/netconsole.rst
+++ b/Documentation/networking/netconsole.rst
@@ -17,6 +17,8 @@ Release prepend support by Breno Leitao <leitao@debian.org>, Jul 7 2023
 
 Userdata append support by Matthew Wood <thepacketgeek@gmail.com>, Jan 22 2024
 
+Sysdata append support by Breno Leitao <leitao@debian.org>, Jan 15 2025
+
 Please send bug reports to Matt Mackall <mpm@selenic.com>
 Satyam Sharma <satyam.sharma@gmail.com>, and Cong Wang <xiyou.wangcong@gmail.com>
 
@@ -238,6 +240,49 @@ Delete `userdata` entries with `rmdir`::
 
    It is recommended to not write user data values with newlines.
 
+CPU number auto population in userdata
+--------------------------------------
+
+Inside the netconsole configfs hierarchy, there is a file called
+`cpu_nr` under the `userdata` directory. This file is used to enable or disable
+the automatic CPU number population feature. This feature automatically
+populates the CPU number that is sending the message.
+
+To enable the CPU number auto-population::
+
+  echo 1 > /sys/kernel/config/netconsole/target1/userdata/cpu_nr
+
+When this option is enabled, the netconsole messages will include an additional
+line in the userdata field with the format `cpu=<cpu_number>`. This allows the
+receiver of the netconsole messages to easily differentiate and demultiplex
+messages originating from different CPUs, which is particularly useful when
+dealing with parallel log output.
+
+Example::
+
+  echo "This is a message" > /dev/kmsg
+  12,607,22085407756,-;This is a message
+   cpu=42
+
+In this example, the message was sent by CPU 42.
+
+.. note::
+
+   If the user has set a conflicting `cpu` key in the userdata dictionary,
+   both keys will be reported, with the kernel-populated entry appearing after
+   the user one. For example::
+
+     # User-defined CPU entry
+     mkdir -p /sys/kernel/config/netconsole/target1/userdata/cpu
+     echo "1" > /sys/kernel/config/netconsole/target1/userdata/cpu/value
+
+   Output might look like::
+
+     12,607,22085407756,-;This is a message
+      cpu=1
+      cpu=42    # kernel-populated value
+
+
 Extended console:
 =================
 

From 2b9df00cded911e2ca2cfae5c45082166b24f8aa Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:49 +0800
Subject: [PATCH 0287/2753] mtd: rawnand: cadence: fix error code in
 cadence_nand_init()

Replace dma_request_channel() with dma_request_chan_by_mask() and use
helper functions to return proper error code instead of fixed -EBUSY.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 8d1d710e439dd..fb5f671bdb7bb 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2904,11 +2904,10 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	dma_cap_set(DMA_MEMCPY, mask);
 
 	if (cdns_ctrl->caps1->has_dma) {
-		cdns_ctrl->dmac = dma_request_channel(mask, NULL, NULL);
-		if (!cdns_ctrl->dmac) {
-			dev_err(cdns_ctrl->dev,
-				"Unable to get a DMA channel\n");
-			ret = -EBUSY;
+		cdns_ctrl->dmac = dma_request_chan_by_mask(&mask);
+		if (IS_ERR(cdns_ctrl->dmac)) {
+			ret = dev_err_probe(cdns_ctrl->dev, PTR_ERR(cdns_ctrl->dmac),
+					    "%d: Failed to get a DMA channel\n", ret);
 			goto disable_irq;
 		}
 	}

From d76d22b5096c5b05208fd982b153b3f182350b19 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:50 +0800
Subject: [PATCH 0288/2753] mtd: rawnand: cadence: use dma_map_resource for
 sdma address

Remap the slave DMA I/O resources to enhance driver portability.
Using a physical address causes DMA translation failure when the
ARM SMMU is enabled.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 .../mtd/nand/raw/cadence-nand-controller.c    | 29 ++++++++++++++++---
 1 file changed, 25 insertions(+), 4 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index fb5f671bdb7bb..47950a0ac6d28 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -471,6 +471,8 @@ struct cdns_nand_ctrl {
 	struct {
 		void __iomem *virt;
 		dma_addr_t dma;
+		dma_addr_t iova_dma;
+		u32 size;
 	} io;
 
 	int irq;
@@ -1835,11 +1837,11 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	}
 
 	if (dir == DMA_FROM_DEVICE) {
-		src_dma = cdns_ctrl->io.dma;
+		src_dma = cdns_ctrl->io.iova_dma;
 		dst_dma = buf_dma;
 	} else {
 		src_dma = buf_dma;
-		dst_dma = cdns_ctrl->io.dma;
+		dst_dma = cdns_ctrl->io.iova_dma;
 	}
 
 	tx = dmaengine_prep_dma_memcpy(cdns_ctrl->dmac, dst_dma, src_dma, len,
@@ -2869,6 +2871,7 @@ cadence_nand_irq_cleanup(int irqnum, struct cdns_nand_ctrl *cdns_ctrl)
 static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	dma_cap_mask_t mask;
+	struct dma_device *dma_dev = cdns_ctrl->dmac->device;
 	int ret;
 
 	cdns_ctrl->cdma_desc = dma_alloc_coherent(cdns_ctrl->dev,
@@ -2912,6 +2915,16 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 		}
 	}
 
+	cdns_ctrl->io.iova_dma = dma_map_resource(dma_dev->dev, cdns_ctrl->io.dma,
+						  cdns_ctrl->io.size,
+						  DMA_BIDIRECTIONAL, 0);
+
+	ret = dma_mapping_error(dma_dev->dev, cdns_ctrl->io.iova_dma);
+	if (ret) {
+		dev_err(cdns_ctrl->dev, "Failed to map I/O resource to DMA\n");
+		goto dma_release_chnl;
+	}
+
 	nand_controller_init(&cdns_ctrl->controller);
 	INIT_LIST_HEAD(&cdns_ctrl->chips);
 
@@ -2922,18 +2935,22 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 	if (ret) {
 		dev_err(cdns_ctrl->dev, "Failed to register MTD: %d\n",
 			ret);
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	kfree(cdns_ctrl->buf);
 	cdns_ctrl->buf = kzalloc(cdns_ctrl->buf_size, GFP_KERNEL);
 	if (!cdns_ctrl->buf) {
 		ret = -ENOMEM;
-		goto dma_release_chnl;
+		goto unmap_dma_resource;
 	}
 
 	return 0;
 
+unmap_dma_resource:
+	dma_unmap_resource(dma_dev->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
+
 dma_release_chnl:
 	if (cdns_ctrl->dmac)
 		dma_release_channel(cdns_ctrl->dmac);
@@ -2955,6 +2972,8 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	cadence_nand_chips_cleanup(cdns_ctrl);
+	dma_unmap_resource(cdns_ctrl->dmac->device->dev, cdns_ctrl->io.iova_dma,
+			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
 	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
 	kfree(cdns_ctrl->buf);
 	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),
@@ -3019,7 +3038,9 @@ static int cadence_nand_dt_probe(struct platform_device *ofdev)
 	cdns_ctrl->io.virt = devm_platform_get_and_ioremap_resource(ofdev, 1, &res);
 	if (IS_ERR(cdns_ctrl->io.virt))
 		return PTR_ERR(cdns_ctrl->io.virt);
+
 	cdns_ctrl->io.dma = res->start;
+	cdns_ctrl->io.size = resource_size(res);
 
 	dt->clk = devm_clk_get(cdns_ctrl->dev, "nf_clk");
 	if (IS_ERR(dt->clk))

From f37d135b42cb484bdecee93f56b9f483214ede78 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Mon, 10 Feb 2025 13:35:51 +0800
Subject: [PATCH 0289/2753] mtd: rawnand: cadence: fix incorrect device in
 dma_unmap_single

dma_map_single is using physical/bus device (DMA) but dma_unmap_single
is using framework device(NAND controller), which is incorrect.
Fixed dma_unmap_single to use correct physical/bus device.

Fixes: ec4ba01e894d ("mtd: rawnand: Add new Cadence NAND driver to MTD subsystem")
Cc: stable@vger.kernel.org
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 47950a0ac6d28..0b2db4173e723 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -1863,12 +1863,12 @@ static int cadence_nand_slave_dma_transfer(struct cdns_nand_ctrl *cdns_ctrl,
 	dma_async_issue_pending(cdns_ctrl->dmac);
 	wait_for_completion(&finished);
 
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 	return 0;
 
 err_unmap:
-	dma_unmap_single(cdns_ctrl->dev, buf_dma, len, dir);
+	dma_unmap_single(dma_dev->dev, buf_dma, len, dir);
 
 err:
 	dev_dbg(cdns_ctrl->dev, "Fall back to CPU I/O\n");

From de7f7582dff292832fbdeaeff34e6b2ee6f9f95f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 15:53:28 -0800
Subject: [PATCH 0290/2753] net: ethtool: prevent flow steering to RSS contexts
 which don't exist

Since commit 42dc431f5d0e ("ethtool: rss: prevent rss ctx deletion
when in use") we prevent removal of RSS contexts pointed to by
existing flow rules. Core should also prevent creation of rules
which point to RSS context which don't exist in the first place.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250206235334.1425329-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/ioctl.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 7609ce2b2c5e2..98b7dcea207a6 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -993,10 +993,14 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		return rc;
 
 	/* Nonzero ring with RSS only makes sense if NIC adds them together */
-	if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS &&
-	    !ops->cap_rss_rxnfc_adds &&
-	    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
-		return -EINVAL;
+	if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS) {
+		if (!ops->cap_rss_rxnfc_adds &&
+		    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
+			return -EINVAL;
+
+		if (!xa_load(&dev->ethtool->rss_ctx, info.rss_context))
+			return -EINVAL;
+	}
 
 	if (cmd == ETHTOOL_SRXFH && ops->get_rxfh) {
 		struct ethtool_rxfh_param rxfh = {};

From 23bac399104c0f23df379a94fe325fef951c287b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 15:53:29 -0800
Subject: [PATCH 0291/2753] selftests: net-drv: test adding flow rule to
 invalid RSS context

Check that adding Rx flow steering rules pointing to an RSS
context which does not exist is prevented.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250206235334.1425329-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/hw/rss_ctx.py       | 27 ++++++++++++++++++-
 1 file changed, 26 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 319aaa004c407..7e5f4602e6b3b 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -4,7 +4,8 @@
 import datetime
 import random
 import re
-from lib.py import ksft_run, ksft_pr, ksft_exit, ksft_eq, ksft_ne, ksft_ge, ksft_lt, ksft_true
+from lib.py import ksft_run, ksft_pr, ksft_exit
+from lib.py import ksft_eq, ksft_ne, ksft_ge, ksft_in, ksft_lt, ksft_true, ksft_raises
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
@@ -649,6 +650,29 @@ def test_rss_context_overlap2(cfg):
     test_rss_context_overlap(cfg, True)
 
 
+def test_flow_add_context_missing(cfg):
+    """
+    Test that we are not allowed to add a rule pointing to an RSS context
+    which was never created.
+    """
+
+    require_ntuple(cfg)
+
+    # Find a context which doesn't exist
+    for ctx_id in range(1, 100):
+        try:
+            get_rss(cfg, context=ctx_id)
+        except CmdExitFailure:
+            break
+
+    with ksft_raises(CmdExitFailure) as cm:
+        flow = f"flow-type tcp{cfg.addr_ipver} dst-ip {cfg.addr} dst-port 1234 context {ctx_id}"
+        ntuple_id = ethtool_create(cfg, "-N", flow)
+        ethtool(f"-N {cfg.ifname} delete {ntuple_id}")
+    if cm.exception:
+        ksft_in('Invalid argument', cm.exception.cmd.stderr)
+
+
 def test_delete_rss_context_busy(cfg):
     """
     Test that deletion returns -EBUSY when an rss context is being used
@@ -726,6 +750,7 @@ def main() -> None:
                   test_rss_context_dump, test_rss_context_queue_reconfigure,
                   test_rss_context_overlap, test_rss_context_overlap2,
                   test_rss_context_out_of_order, test_rss_context4_create_with_cfg,
+                  test_flow_add_context_missing,
                   test_delete_rss_context_busy, test_rss_ntuple_addition],
                  args=(cfg, ))
     ksft_exit()

From 260676ebb1f3b188796a045e0ecf79a699b8e857 Mon Sep 17 00:00:00 2001
From: Daniel Zahka <daniel.zahka@gmail.com>
Date: Thu, 6 Feb 2025 15:53:30 -0800
Subject: [PATCH 0292/2753] eth: fbnic: support an additional RSS context

Add support for an extra RSS context. The device has a primary
and a secondary context.

Signed-off-by: Daniel Zahka <daniel.zahka@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250206235334.1425329-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_ethtool.c   | 59 +++++++++++++++++++
 1 file changed, 59 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index 20cd9f5f89e27..4d73b405c8b9c 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -374,6 +374,61 @@ fbnic_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 	return 0;
 }
 
+static int
+fbnic_modify_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	const u32 *indir = rxfh->indir;
+	unsigned int changes;
+
+	if (!indir)
+		indir = ethtool_rxfh_context_indir(ctx);
+
+	changes = fbnic_set_indir(fbn, rxfh->rss_context, indir);
+	if (changes && netif_running(netdev))
+		fbnic_rss_reinit_hw(fbn->fbd, fbn);
+
+	return 0;
+}
+
+static int
+fbnic_create_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx,
+			  const struct ethtool_rxfh_param *rxfh,
+			  struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	if (rxfh->hfunc && rxfh->hfunc != ETH_RSS_HASH_TOP) {
+		NL_SET_ERR_MSG_MOD(extack, "RSS hash function not supported");
+		return -EOPNOTSUPP;
+	}
+	ctx->hfunc = ETH_RSS_HASH_TOP;
+
+	if (!rxfh->indir) {
+		u32 *indir = ethtool_rxfh_context_indir(ctx);
+		unsigned int num_rx = fbn->num_rx_queues;
+		unsigned int i;
+
+		for (i = 0; i < FBNIC_RPC_RSS_TBL_SIZE; i++)
+			indir[i] = ethtool_rxfh_indir_default(i, num_rx);
+	}
+
+	return fbnic_modify_rxfh_context(netdev, ctx, rxfh, extack);
+}
+
+static int
+fbnic_remove_rxfh_context(struct net_device *netdev,
+			  struct ethtool_rxfh_context *ctx, u32 rss_context,
+			  struct netlink_ext_ack *extack)
+{
+	/* Nothing to do, contexts are allocated statically */
+	return 0;
+}
+
 static void fbnic_get_channels(struct net_device *netdev,
 			       struct ethtool_channels *ch)
 {
@@ -586,6 +641,7 @@ fbnic_get_eth_mac_stats(struct net_device *netdev,
 }
 
 static const struct ethtool_ops fbnic_ethtool_ops = {
+	.rxfh_max_num_contexts	= FBNIC_RPC_RSS_TBL_COUNT,
 	.get_drvinfo		= fbnic_get_drvinfo,
 	.get_regs_len		= fbnic_get_regs_len,
 	.get_regs		= fbnic_get_regs,
@@ -598,6 +654,9 @@ static const struct ethtool_ops fbnic_ethtool_ops = {
 	.get_rxfh_indir_size	= fbnic_get_rxfh_indir_size,
 	.get_rxfh		= fbnic_get_rxfh,
 	.set_rxfh		= fbnic_set_rxfh,
+	.create_rxfh_context	= fbnic_create_rxfh_context,
+	.modify_rxfh_context	= fbnic_modify_rxfh_context,
+	.remove_rxfh_context	= fbnic_remove_rxfh_context,
 	.get_channels		= fbnic_get_channels,
 	.set_channels		= fbnic_set_channels,
 	.get_ts_info		= fbnic_get_ts_info,

From 3a265bd6a3ba27ff56a686d845e959ce365edcaa Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Thu, 6 Feb 2025 15:53:31 -0800
Subject: [PATCH 0293/2753] eth: fbnic: add IP TCAM programming

IPv6 addresses are huge so the device has 4 TCAMs used for narrowing
them down to a smaller key before the main match / action engine.

Add the tables in which we'll keep the IP addresses used by
ethtool n-tuple rules. Add the code for programming them
into the device, and code for allocating and freeing entries.

A bit of copy / paste here as we need to support IPv4 and
IPv6 in the same tables, and there is four of them.
But it makes the code easier to match up with the device.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/20250206235334.1425329-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic.h     |   6 +
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h |   3 +
 drivers/net/ethernet/meta/fbnic/fbnic_rpc.c | 354 ++++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_rpc.h |  26 ++
 4 files changed, 389 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 14751f16e1252..37f81db1fc301 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -60,6 +60,12 @@ struct fbnic_dev {
 	u8 mac_addr_boundary;
 	u8 tce_tcam_last;
 
+	/* IP TCAM */
+	struct fbnic_ip_addr ip_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ip_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_src[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+	struct fbnic_ip_addr ipo_dst[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES];
+
 	/* Number of TCQs/RCQs available on hardware */
 	u16 max_num_queues;
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 02bb81b3c5063..d5e9b11ed2f89 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -677,6 +677,9 @@ enum {
 
 #define FBNIC_RPC_TCAM_OUTER_IPSRC(m, n)\
 	(0x08c00 + 0x08 * (n) + (m))		/* 0x023000 + 32*n + 4*m */
+#define FBNIC_RPC_TCAM_IP_ADDR_VALUE		CSR_GENMASK(15, 0)
+#define FBNIC_RPC_TCAM_IP_ADDR_MASK		CSR_GENMASK(31, 16)
+
 #define FBNIC_RPC_TCAM_OUTER_IPDST(m, n)\
 	(0x08c48 + 0x08 * (n) + (m))		/* 0x023120 + 32*n + 4*m */
 #define FBNIC_RPC_TCAM_IPSRC(m, n)\
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
index c25bd300b9024..be06f43e51e4e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <net/ipv6.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -698,6 +699,359 @@ void fbnic_write_tce_tcam(struct fbnic_dev *fbd)
 		__fbnic_write_tce_tcam(fbd);
 }
 
+struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in_addr *addr,
+				       const struct in_addr *mask)
+{
+	struct fbnic_ip_addr *avail_addr = NULL;
+	unsigned int i;
+
+	/* Scan from top of list to bottom, filling bottom up. */
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		struct in6_addr *m = &ip_addr->mask;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DISABLED) {
+			avail_addr = ip_addr;
+			continue;
+		}
+
+		if (ip_addr->version != 4)
+			continue;
+
+		/* Drop avail_addr if mask is a subset of our current mask,
+		 * This prevents us from inserting a longer prefix behind a
+		 * shorter one.
+		 *
+		 * The mask is stored inverted value so as an example:
+		 * m	ffff ffff ffff ffff ffff ffff ffff 0000 0000
+		 * mask 0000 0000 0000 0000 0000 0000 0000 ffff ffff
+		 *
+		 * "m" and "mask" represent typical IPv4 mask stored in
+		 * the TCAM and those provided by the stack. The code below
+		 * should return a non-zero result if there is a 0 stored
+		 * anywhere in "m" where "mask" has a 0.
+		 */
+		if (~m->s6_addr32[3] & ~mask->s_addr) {
+			avail_addr = NULL;
+			continue;
+		}
+
+		/* Check to see if the mask actually contains fewer bits than
+		 * our new mask "m". The XOR below should only result in 0 if
+		 * "m" is masking a bit that we are looking for in our new
+		 * "mask", we eliminated the 0^0 case with the check above.
+		 *
+		 * If it contains fewer bits we need to stop here, otherwise
+		 * we might be adding an unreachable rule.
+		 */
+		if (~(m->s6_addr32[3] ^ mask->s_addr))
+			break;
+
+		if (ip_addr->value.s6_addr32[3] == addr->s_addr) {
+			avail_addr = ip_addr;
+			break;
+		}
+	}
+
+	if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) {
+		ipv6_addr_set(&avail_addr->value, 0, 0, 0, addr->s_addr);
+		ipv6_addr_set(&avail_addr->mask, htonl(~0), htonl(~0),
+			      htonl(~0), ~mask->s_addr);
+		avail_addr->version = 4;
+
+		avail_addr->state = FBNIC_TCAM_S_ADD;
+	}
+
+	return avail_addr;
+}
+
+struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in6_addr *addr,
+				       const struct in6_addr *mask)
+{
+	struct fbnic_ip_addr *avail_addr = NULL;
+	unsigned int i;
+
+	ip_addr = &ip_addr[FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES - 1];
+
+	/* Scan from bottom of list to top, filling top down. */
+	for (i = FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i--; ip_addr--) {
+		struct in6_addr *m = &ip_addr->mask;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DISABLED) {
+			avail_addr = ip_addr;
+			continue;
+		}
+
+		if (ip_addr->version != 6)
+			continue;
+
+		/* Drop avail_addr if mask is a superset of our current mask.
+		 * This prevents us from inserting a longer prefix behind a
+		 * shorter one.
+		 *
+		 * The mask is stored inverted value so as an example:
+		 * m	0000 0000 0000 0000 0000 0000 0000 0000 0000
+		 * mask ffff ffff ffff ffff ffff ffff ffff ffff ffff
+		 *
+		 * "m" and "mask" represent typical IPv6 mask stored in
+		 * the TCAM and those provided by the stack. The code below
+		 * should return a non-zero result which will cause us
+		 * to drop the avail_addr value that might be cached
+		 * to prevent us from dropping a v6 address behind it.
+		 */
+		if ((m->s6_addr32[0] & mask->s6_addr32[0]) |
+		    (m->s6_addr32[1] & mask->s6_addr32[1]) |
+		    (m->s6_addr32[2] & mask->s6_addr32[2]) |
+		    (m->s6_addr32[3] & mask->s6_addr32[3])) {
+			avail_addr = NULL;
+			continue;
+		}
+
+		/* The previous test eliminated any overlap between the
+		 * two values so now we need to check for gaps.
+		 *
+		 * If the mask is equal to our current mask then it should
+		 * result with m ^ mask = ffff ffff, if however the value
+		 * stored in m is bigger then we should see a 0 appear
+		 * somewhere in the mask.
+		 */
+		if (~(m->s6_addr32[0] ^ mask->s6_addr32[0]) |
+		    ~(m->s6_addr32[1] ^ mask->s6_addr32[1]) |
+		    ~(m->s6_addr32[2] ^ mask->s6_addr32[2]) |
+		    ~(m->s6_addr32[3] ^ mask->s6_addr32[3]))
+			break;
+
+		if (ipv6_addr_cmp(&ip_addr->value, addr))
+			continue;
+
+		avail_addr = ip_addr;
+		break;
+	}
+
+	if (avail_addr && avail_addr->state == FBNIC_TCAM_S_DISABLED) {
+		memcpy(&avail_addr->value, addr, sizeof(*addr));
+		ipv6_addr_set(&avail_addr->mask,
+			      ~mask->s6_addr32[0], ~mask->s6_addr32[1],
+			      ~mask->s6_addr32[2], ~mask->s6_addr32[3]);
+		avail_addr->version = 6;
+
+		avail_addr->state = FBNIC_TCAM_S_ADD;
+	}
+
+	return avail_addr;
+}
+
+int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx)
+{
+	if (!test_and_clear_bit(tcam_idx, ip_addr->act_tcam))
+		return -ENOENT;
+
+	if (bitmap_empty(ip_addr->act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES))
+		ip_addr->state = FBNIC_TCAM_S_DELETE;
+
+	return 0;
+}
+
+static void fbnic_clear_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i), 0);
+}
+
+static void fbnic_clear_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i), 0);
+}
+
+static void fbnic_clear_ip_outer_src_entry(struct fbnic_dev *fbd,
+					   unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), 0);
+}
+
+static void fbnic_clear_ip_outer_dst_entry(struct fbnic_dev *fbd,
+					   unsigned int idx)
+{
+	int i;
+
+	/* Invalidate entry and clear addr state info */
+	for (i = 0; i <= FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), 0);
+}
+
+static void fbnic_write_ip_src_entry(struct fbnic_dev *fbd, unsigned int idx,
+				     struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	/* Bit 129 is used to flag for v4/v6 */
+	wr32(fbd, FBNIC_RPC_TCAM_IPSRC(idx, i),
+	     (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_dst_entry(struct fbnic_dev *fbd, unsigned int idx,
+				     struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	/* Bit 129 is used to flag for v4/v6 */
+	wr32(fbd, FBNIC_RPC_TCAM_IPDST(idx, i),
+	     (ip_addr->version == 6) | FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_outer_src_entry(struct fbnic_dev *fbd,
+					   unsigned int idx,
+					   struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPSRC(idx, i), FBNIC_RPC_TCAM_VALIDATE);
+}
+
+static void fbnic_write_ip_outer_dst_entry(struct fbnic_dev *fbd,
+					   unsigned int idx,
+					   struct fbnic_ip_addr *ip_addr)
+{
+	__be16 *mask, *value;
+	int i;
+
+	mask = &ip_addr->mask.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+	value = &ip_addr->value.s6_addr16[FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN - 1];
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN; i++)
+		wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i),
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_MASK, ntohs(*mask--)) |
+		     FIELD_PREP(FBNIC_RPC_TCAM_IP_ADDR_VALUE, ntohs(*value--)));
+	wrfl(fbd);
+
+	wr32(fbd, FBNIC_RPC_TCAM_OUTER_IPDST(idx, i), FBNIC_RPC_TCAM_VALIDATE);
+}
+
+void fbnic_write_ip_addr(struct fbnic_dev *fbd)
+{
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->ip_src); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ip_src[idx];
+
+		/* Check if update flag is set else skip. */
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		/* Clear by writing 0s. */
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			/* Invalidate entry and clear addr state info */
+			fbnic_clear_ip_src_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_src_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	/* Repeat process for other IP TCAMs */
+	for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ip_dst[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_dst_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_dst_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ipo_src[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_outer_src_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_outer_src_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+
+	for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;) {
+		struct fbnic_ip_addr *ip_addr = &fbd->ipo_dst[idx];
+
+		if (!(ip_addr->state & FBNIC_TCAM_S_UPDATE))
+			continue;
+
+		if (ip_addr->state == FBNIC_TCAM_S_DELETE) {
+			fbnic_clear_ip_outer_dst_entry(fbd, idx);
+			memset(ip_addr, 0, sizeof(*ip_addr));
+
+			continue;
+		}
+
+		fbnic_write_ip_outer_dst_entry(fbd, idx, ip_addr);
+
+		ip_addr->state = FBNIC_TCAM_S_VALID;
+	}
+}
+
 void fbnic_clear_rules(struct fbnic_dev *fbd)
 {
 	u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
index 0d8285fa5b454..b3515f2f5f92e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
@@ -7,6 +7,8 @@
 #include <uapi/linux/in6.h>
 #include <linux/bitfield.h>
 
+struct in_addr;
+
 /*  The TCAM state definitions follow an expected ordering.
  *  They start out disabled, then move through the following states:
  *  Disabled  0	-> Add	      2
@@ -32,6 +34,12 @@ enum {
 #define FBNIC_RPC_TCAM_MACDA_WORD_LEN		3
 #define FBNIC_RPC_TCAM_MACDA_NUM_ENTRIES	32
 
+/* 8 IPSRC and IPDST TCAM Entries each
+ * 8 registers, Validate each
+ */
+#define FBNIC_RPC_TCAM_IP_ADDR_WORD_LEN		8
+#define FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES	8
+
 #define FBNIC_RPC_TCAM_ACT_WORD_LEN		11
 #define FBNIC_RPC_TCAM_ACT_NUM_ENTRIES		64
 
@@ -47,6 +55,13 @@ struct fbnic_mac_addr {
 	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
 };
 
+struct fbnic_ip_addr {
+	struct in6_addr mask, value;
+	unsigned char version;
+	unsigned char state;
+	DECLARE_BITMAP(act_tcam, FBNIC_RPC_TCAM_ACT_NUM_ENTRIES);
+};
+
 struct fbnic_act_tcam {
 	struct {
 		u16 tcam[FBNIC_RPC_TCAM_ACT_WORD_LEN];
@@ -177,6 +192,17 @@ struct fbnic_mac_addr *__fbnic_mc_sync(struct fbnic_dev *fbd,
 void fbnic_sift_macda(struct fbnic_dev *fbd);
 void fbnic_write_macda(struct fbnic_dev *fbd);
 
+struct fbnic_ip_addr *__fbnic_ip4_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in_addr *addr,
+				       const struct in_addr *mask);
+struct fbnic_ip_addr *__fbnic_ip6_sync(struct fbnic_dev *fbd,
+				       struct fbnic_ip_addr *ip_addr,
+				       const struct in6_addr *addr,
+				       const struct in6_addr *mask);
+int __fbnic_ip_unsync(struct fbnic_ip_addr *ip_addr, unsigned int tcam_idx);
+void fbnic_write_ip_addr(struct fbnic_dev *fbd);
+
 static inline int __fbnic_uc_unsync(struct fbnic_mac_addr *mac_addr)
 {
 	return __fbnic_xc_unsync(mac_addr, FBNIC_MAC_ADDR_T_UNICAST);

From 2230035439c8c666d1d010da1486b274a92e0075 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Thu, 6 Feb 2025 15:53:32 -0800
Subject: [PATCH 0294/2753] eth: fbnic: support n-tuple filters

Add ethtool -n / -N support. Support only "un-ordered" rule sets
(RX_CLS_LOC_ANY), just for simplicity of the code. It's unclear
anyone actually cares about the rule ordering.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/20250206235334.1425329-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h   |   3 +
 .../net/ethernet/meta/fbnic/fbnic_ethtool.c   | 646 ++++++++++++++++++
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    |   1 +
 drivers/net/ethernet/meta/fbnic/fbnic_rpc.c   |   2 +-
 drivers/net/ethernet/meta/fbnic/fbnic_rpc.h   |   9 +
 5 files changed, 660 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index d5e9b11ed2f89..6f24c5f2e175e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -605,8 +605,11 @@ enum {
 	FBNIC_RPC_ACT_TBL0_DEST_EI	= 4,
 };
 
+#define FBNIC_RPC_ACT_TBL0_Q_SEL		CSR_BIT(4)
+#define FBNIC_RPC_ACT_TBL0_Q_ID			CSR_GENMASK(15, 8)
 #define FBNIC_RPC_ACT_TBL0_DMA_HINT		CSR_GENMASK(24, 16)
 #define FBNIC_RPC_ACT_TBL0_TS_ENA		CSR_BIT(28)
+#define FBNIC_RPC_ACT_TBL0_ACT_TBL_IDX		CSR_BIT(29)
 #define FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID		CSR_BIT(30)
 
 #define FBNIC_RPC_ACT_TBL1_DEFAULT	0x0840b		/* 0x2102c */
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index 4d73b405c8b9c..9503c36620c6b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -4,6 +4,7 @@
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <net/ipv6.h>
 
 #include "fbnic.h"
 #include "fbnic_netdev.h"
@@ -218,11 +219,234 @@ fbnic_get_rss_hash_opts(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd)
 	return 0;
 }
 
+static int fbnic_get_cls_rule_all(struct fbnic_net *fbn,
+				  struct ethtool_rxnfc *cmd,
+				  u32 *rule_locs)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int i, cnt = 0;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	for (i = 0; i < FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i++) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+		struct fbnic_act_tcam *act_tcam;
+
+		act_tcam = &fbd->act_tcam[idx];
+		if (act_tcam->state != FBNIC_TCAM_S_VALID)
+			continue;
+
+		if (rule_locs) {
+			if (cnt == cmd->rule_cnt)
+				return -EMSGSIZE;
+
+			rule_locs[cnt] = i;
+		}
+
+		cnt++;
+	}
+
+	return cnt;
+}
+
+static int fbnic_get_cls_rule(struct fbnic_net *fbn, struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	/* Report maximum rule count */
+	cmd->data = FBNIC_RPC_ACT_TBL_NFC_ENTRIES;
+
+	/* Set flow type field */
+	if (!(act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_VALID)) {
+		fsp->flow_type = ETHER_FLOW;
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+			       act_tcam->mask.tcam[1])) {
+			struct fbnic_mac_addr *mac_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					act_tcam->value.tcam[1]);
+			mac_addr = &fbd->mac_addr[idx];
+
+			ether_addr_copy(fsp->h_u.ether_spec.h_dest,
+					mac_addr->value.addr8);
+			eth_broadcast_addr(fsp->m_u.ether_spec.h_dest);
+		}
+	} else if (act_tcam->value.tcam[1] &
+		   FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID) {
+		fsp->flow_type = IPV6_USER_FLOW;
+		fsp->h_u.usr_ip6_spec.l4_proto = IPPROTO_IPV6;
+		fsp->m_u.usr_ip6_spec.l4_proto = 0xff;
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ipo_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_IP_IS_V6)) {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V6_FLOW;
+			else
+				fsp->flow_type = TCP_V6_FLOW;
+			fsp->h_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip6_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip6_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV6_USER_FLOW;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6src[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6src[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+			int i;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			for (i = 0; i < 4; i++) {
+				fsp->h_u.usr_ip6_spec.ip6dst[i] =
+					ip_addr->value.s6_addr32[i];
+				fsp->m_u.usr_ip6_spec.ip6dst[i] =
+					~ip_addr->mask.s6_addr32[i];
+			}
+		}
+	} else {
+		if (act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L4_VALID) {
+			if (act_tcam->value.tcam[1] &
+			    FBNIC_RPC_TCAM_ACT1_L4_IS_UDP)
+				fsp->flow_type = UDP_V4_FLOW;
+			else
+				fsp->flow_type = TCP_V4_FLOW;
+			fsp->h_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(act_tcam->value.tcam[3]);
+			fsp->m_u.tcp_ip4_spec.psrc =
+				cpu_to_be16(~act_tcam->mask.tcam[3]);
+			fsp->h_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(act_tcam->value.tcam[4]);
+			fsp->m_u.tcp_ip4_spec.pdst =
+				cpu_to_be16(~act_tcam->mask.tcam[4]);
+		} else {
+			fsp->flow_type = IPV4_USER_FLOW;
+			fsp->h_u.usr_ip4_spec.ip_ver = ETH_RX_NFC_IP4;
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_src[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4src =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4src =
+				~ip_addr->mask.s6_addr32[3];
+		}
+
+		if (!FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+			       act_tcam->mask.tcam[0])) {
+			struct fbnic_ip_addr *ip_addr;
+
+			idx = FIELD_GET(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					act_tcam->value.tcam[0]);
+			ip_addr = &fbd->ip_dst[idx];
+
+			fsp->h_u.usr_ip4_spec.ip4dst =
+				ip_addr->value.s6_addr32[3];
+			fsp->m_u.usr_ip4_spec.ip4dst =
+				~ip_addr->mask.s6_addr32[3];
+		}
+	}
+
+	/* Record action */
+	if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_DROP)
+		fsp->ring_cookie = RX_CLS_FLOW_DISC;
+	else if (act_tcam->dest & FBNIC_RPC_ACT_TBL0_Q_SEL)
+		fsp->ring_cookie = FIELD_GET(FBNIC_RPC_ACT_TBL0_Q_ID,
+					     act_tcam->dest);
+	else
+		fsp->flow_type |= FLOW_RSS;
+
+	cmd->rss_context = FIELD_GET(FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID,
+				     act_tcam->dest);
+
+	return 0;
+}
+
 static int fbnic_get_rxnfc(struct net_device *netdev,
 			   struct ethtool_rxnfc *cmd, u32 *rule_locs)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
 	int ret = -EOPNOTSUPP;
+	u32 special = 0;
 
 	switch (cmd->cmd) {
 	case ETHTOOL_GRXRINGS:
@@ -232,6 +456,22 @@ static int fbnic_get_rxnfc(struct net_device *netdev,
 	case ETHTOOL_GRXFH:
 		ret = fbnic_get_rss_hash_opts(fbn, cmd);
 		break;
+	case ETHTOOL_GRXCLSRULE:
+		ret = fbnic_get_cls_rule(fbn, cmd);
+		break;
+	case ETHTOOL_GRXCLSRLCNT:
+		rule_locs = NULL;
+		special = RX_CLS_LOC_SPECIAL;
+		fallthrough;
+	case ETHTOOL_GRXCLSRLALL:
+		ret = fbnic_get_cls_rule_all(fbn, cmd, rule_locs);
+		if (ret < 0)
+			break;
+
+		cmd->data |= special;
+		cmd->rule_cnt = ret;
+		ret = 0;
+		break;
 	}
 
 	return ret;
@@ -272,6 +512,406 @@ fbnic_set_rss_hash_opts(struct fbnic_net *fbn, const struct ethtool_rxnfc *cmd)
 	return 0;
 }
 
+static int fbnic_cls_rule_any_loc(struct fbnic_dev *fbd)
+{
+	int i;
+
+	for (i = FBNIC_RPC_ACT_TBL_NFC_ENTRIES; i--;) {
+		int idx = i + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+
+		if (fbd->act_tcam[idx].state != FBNIC_TCAM_S_VALID)
+			return i;
+	}
+
+	return -ENOSPC;
+}
+
+static int fbnic_set_cls_rule_ins(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	u16 flow_value = 0, flow_mask = 0xffff, ip_value = 0, ip_mask = 0xffff;
+	u16 sport = 0, sport_mask = ~0, dport = 0, dport_mask = ~0;
+	u16 misc = 0, misc_mask = ~0;
+	u32 dest = FIELD_PREP(FBNIC_RPC_ACT_TBL0_DEST_MASK,
+			      FBNIC_RPC_ACT_TBL0_DEST_HOST);
+	struct fbnic_ip_addr *ip_src = NULL, *ip_dst = NULL;
+	struct fbnic_mac_addr *mac_addr = NULL;
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	struct in6_addr *addr6, *mask6;
+	struct in_addr *addr4, *mask4;
+	int hash_idx, location;
+	u32 flow_type;
+	int idx, j;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location != RX_CLS_LOC_ANY)
+		return -EINVAL;
+	location = fbnic_cls_rule_any_loc(fbd);
+	if (location < 0)
+		return location;
+
+	if (fsp->ring_cookie == RX_CLS_FLOW_DISC) {
+		dest = FBNIC_RPC_ACT_TBL0_DROP;
+	} else if (fsp->flow_type & FLOW_RSS) {
+		if (cmd->rss_context == 1)
+			dest |= FBNIC_RPC_ACT_TBL0_RSS_CTXT_ID;
+	} else {
+		u32 ring_idx = ethtool_get_flow_spec_ring(fsp->ring_cookie);
+
+		if (ring_idx >= fbn->num_rx_queues)
+			return -EINVAL;
+
+		dest |= FBNIC_RPC_ACT_TBL0_Q_SEL |
+			FIELD_PREP(FBNIC_RPC_ACT_TBL0_Q_ID, ring_idx);
+	}
+
+	idx = location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	/* Do not allow overwriting for now.
+	 * To support overwriting rules we will need to add logic to free
+	 * any IP or MACDA TCAMs that may be associated with the old rule.
+	 */
+	if (act_tcam->state != FBNIC_TCAM_S_DISABLED)
+		return -EBUSY;
+
+	flow_type = fsp->flow_type & ~(FLOW_EXT | FLOW_RSS);
+	hash_idx = fbnic_get_rss_hash_idx(flow_type);
+
+	switch (flow_type) {
+	case UDP_V4_FLOW:
+udp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V4_FLOW:
+tcp4_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			       FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip4_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip4_spec.pdst);
+		goto ip4_flow;
+	case IP_USER_FLOW:
+		if (!fsp->m_u.usr_ip4_spec.proto)
+			goto ip4_flow;
+		if (fsp->m_u.usr_ip4_spec.proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_UDP)
+			goto udp4_flow;
+		if (fsp->h_u.usr_ip4_spec.proto == IPPROTO_TCP)
+			goto tcp4_flow;
+		return -EINVAL;
+ip4_flow:
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4src;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4src;
+		if (mask4->s_addr) {
+			ip_src = __fbnic_ip4_sync(fbd, fbd->ip_src,
+						  addr4, mask4);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr4 = (struct in_addr *)&fsp->h_u.usr_ip4_spec.ip4dst;
+		mask4 = (struct in_addr *)&fsp->m_u.usr_ip4_spec.ip4dst;
+		if (mask4->s_addr) {
+			ip_dst = __fbnic_ip4_sync(fbd, fbd->ip_dst,
+						  addr4, mask4);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case UDP_V6_FLOW:
+udp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_IS_UDP;
+		fallthrough;
+	case TCP_V6_FLOW:
+tcp6_flow:
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L4_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_L4_IS_UDP |
+			  FBNIC_RPC_TCAM_ACT1_L4_VALID);
+
+		sport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.psrc);
+		sport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.psrc);
+		dport = be16_to_cpu(fsp->h_u.tcp_ip6_spec.pdst);
+		dport_mask = ~be16_to_cpu(fsp->m_u.tcp_ip6_spec.pdst);
+		goto ipv6_flow;
+	case IPV6_USER_FLOW:
+		if (!fsp->m_u.usr_ip6_spec.l4_proto)
+			goto ipv6_flow;
+
+		if (fsp->m_u.usr_ip6_spec.l4_proto != 0xff)
+			return -EINVAL;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_UDP)
+			goto udp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto == IPPROTO_TCP)
+			goto tcp6_flow;
+		if (fsp->h_u.usr_ip6_spec.l4_proto != IPPROTO_IPV6)
+			return -EINVAL;
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ipo_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX,
+					   ip_src - fbd->ipo_src);
+			ip_mask &=
+				~(FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+				  FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ipo_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |=
+				FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX,
+					   ip_dst - fbd->ipo_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID |
+				     FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+		flow_mask &= FBNIC_RPC_TCAM_ACT1_OUTER_IP_VALID;
+ipv6_flow:
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6src;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6src;
+		if (!ip_src && !ipv6_addr_any(mask6)) {
+			ip_src = __fbnic_ip6_sync(fbd, fbd->ip_src,
+						  addr6, mask6);
+			if (!ip_src)
+				return -ENOSPC;
+
+			set_bit(idx, ip_src->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPSRC_IDX,
+					       ip_src - fbd->ip_src);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPSRC_IDX);
+		}
+
+		addr6 = (struct in6_addr *)fsp->h_u.usr_ip6_spec.ip6dst;
+		mask6 = (struct in6_addr *)fsp->m_u.usr_ip6_spec.ip6dst;
+		if (!ip_dst && !ipv6_addr_any(mask6)) {
+			ip_dst = __fbnic_ip6_sync(fbd, fbd->ip_dst,
+						  addr6, mask6);
+			if (!ip_dst) {
+				if (ip_src && ip_src->state == FBNIC_TCAM_S_ADD)
+					memset(ip_src, 0, sizeof(*ip_src));
+				return -ENOSPC;
+			}
+
+			set_bit(idx, ip_dst->act_tcam);
+			ip_value |= FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				    FIELD_PREP(FBNIC_RPC_TCAM_ACT0_IPDST_IDX,
+					       ip_dst - fbd->ip_dst);
+			ip_mask &= ~(FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+				       FBNIC_RPC_TCAM_ACT0_IPDST_IDX);
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			      FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			      FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~(FBNIC_RPC_TCAM_ACT1_IP_IS_V6 |
+			       FBNIC_RPC_TCAM_ACT1_IP_VALID |
+			       FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID);
+		break;
+	case ETHER_FLOW:
+		if (!is_zero_ether_addr(fsp->m_u.ether_spec.h_dest)) {
+			u8 *addr = fsp->h_u.ether_spec.h_dest;
+			u8 *mask = fsp->m_u.ether_spec.h_dest;
+
+			/* Do not allow MAC addr of 0 */
+			if (is_zero_ether_addr(addr))
+				return -EINVAL;
+
+			/* Only support full MAC address to avoid
+			 * conflicts with other MAC addresses.
+			 */
+			if (!is_broadcast_ether_addr(mask))
+				return -EINVAL;
+
+			if (is_multicast_ether_addr(addr))
+				mac_addr = __fbnic_mc_sync(fbd, addr);
+			else
+				mac_addr = __fbnic_uc_sync(fbd, addr);
+
+			if (!mac_addr)
+				return -ENOSPC;
+
+			set_bit(idx, mac_addr->act_tcam);
+			flow_value |=
+				FIELD_PREP(FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX,
+					   mac_addr - fbd->mac_addr);
+			flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX;
+		}
+
+		flow_value |= FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		flow_mask &= ~FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Write action table values */
+	act_tcam->dest = dest;
+	act_tcam->rss_en_mask = fbnic_flow_hash_2_rss_en_mask(fbn, hash_idx);
+
+	/* Write IP Match value/mask to action_tcam[0] */
+	act_tcam->value.tcam[0] = ip_value;
+	act_tcam->mask.tcam[0] = ip_mask;
+
+	/* Write flow type value/mask to action_tcam[1] */
+	act_tcam->value.tcam[1] = flow_value;
+	act_tcam->mask.tcam[1] = flow_mask;
+
+	/* Write error, DSCP, extra L4 matches to action_tcam[2] */
+	act_tcam->value.tcam[2] = misc;
+	act_tcam->mask.tcam[2] = misc_mask;
+
+	/* Write source/destination port values */
+	act_tcam->value.tcam[3] = sport;
+	act_tcam->mask.tcam[3] = sport_mask;
+	act_tcam->value.tcam[4] = dport;
+	act_tcam->mask.tcam[4] = dport_mask;
+
+	for (j = 5; j < FBNIC_RPC_TCAM_ACT_WORD_LEN; j++)
+		act_tcam->mask.tcam[j] = 0xffff;
+
+	act_tcam->state = FBNIC_TCAM_S_UPDATE;
+	fsp->location = location;
+
+	if (netif_running(fbn->netdev)) {
+		fbnic_write_rules(fbd);
+		if (ip_src || ip_dst)
+			fbnic_write_ip_addr(fbd);
+		if (mac_addr)
+			fbnic_write_macda(fbd);
+	}
+
+	return 0;
+}
+
+static void fbnic_clear_nfc_macda(struct fbnic_net *fbn,
+				  unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->mac_addr); idx--;)
+		__fbnic_xc_unsync(&fbd->mac_addr[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_macda(fbd);
+}
+
+static void fbnic_clear_nfc_ip_addr(struct fbnic_net *fbn,
+				    unsigned int tcam_idx)
+{
+	struct fbnic_dev *fbd = fbn->fbd;
+	int idx;
+
+	for (idx = ARRAY_SIZE(fbd->ip_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ip_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ip_dst[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_src); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_src[idx], tcam_idx);
+	for (idx = ARRAY_SIZE(fbd->ipo_dst); idx--;)
+		__fbnic_ip_unsync(&fbd->ipo_dst[idx], tcam_idx);
+
+	/* Write updates to hardware */
+	if (netif_running(fbn->netdev))
+		fbnic_write_ip_addr(fbd);
+}
+
+static int fbnic_set_cls_rule_del(struct fbnic_net *fbn,
+				  const struct ethtool_rxnfc *cmd)
+{
+	struct ethtool_rx_flow_spec *fsp;
+	struct fbnic_dev *fbd = fbn->fbd;
+	struct fbnic_act_tcam *act_tcam;
+	int idx;
+
+	fsp = (struct ethtool_rx_flow_spec *)&cmd->fs;
+
+	if (fsp->location >= FBNIC_RPC_ACT_TBL_NFC_ENTRIES)
+		return -EINVAL;
+
+	idx = fsp->location + FBNIC_RPC_ACT_TBL_NFC_OFFSET;
+	act_tcam = &fbd->act_tcam[idx];
+
+	if (act_tcam->state != FBNIC_TCAM_S_VALID)
+		return -EINVAL;
+
+	act_tcam->state = FBNIC_TCAM_S_DELETE;
+
+	if ((act_tcam->value.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_VALID) &&
+	    (~act_tcam->mask.tcam[1] & FBNIC_RPC_TCAM_ACT1_L2_MACDA_IDX))
+		fbnic_clear_nfc_macda(fbn, idx);
+
+	if ((act_tcam->value.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_VALID |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_VALID)) &&
+	    (~act_tcam->mask.tcam[0] &
+	     (FBNIC_RPC_TCAM_ACT0_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_IPDST_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPSRC_IDX |
+	      FBNIC_RPC_TCAM_ACT0_OUTER_IPDST_IDX)))
+		fbnic_clear_nfc_ip_addr(fbn, idx);
+
+	if (netif_running(fbn->netdev))
+		fbnic_write_rules(fbd);
+
+	return 0;
+}
+
 static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 {
 	struct fbnic_net *fbn = netdev_priv(netdev);
@@ -281,6 +921,12 @@ static int fbnic_set_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd)
 	case ETHTOOL_SRXFH:
 		ret = fbnic_set_rss_hash_opts(fbn, cmd);
 		break;
+	case ETHTOOL_SRXCLSRLINS:
+		ret = fbnic_set_cls_rule_ins(fbn, cmd);
+		break;
+	case ETHTOOL_SRXCLSRLDEL:
+		ret = fbnic_set_cls_rule_del(fbn, cmd);
+		break;
 	}
 
 	return ret;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 1db57c42333ef..14e7a8384bce2 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -639,6 +639,7 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	netdev->hw_features |= netdev->features;
 	netdev->vlan_features |= netdev->features;
 	netdev->hw_enc_features |= netdev->features;
+	netdev->features |= NETIF_F_NTUPLE;
 
 	netdev->min_mtu = IPV6_MIN_MTU;
 	netdev->max_mtu = FBNIC_MAX_JUMBO_FRAME_SIZE - ETH_HLEN;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
index be06f43e51e4e..8ff07b5562e3b 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.c
@@ -61,7 +61,7 @@ void fbnic_rss_disable_hw(struct fbnic_dev *fbd)
 #define FBNIC_FH_2_RSSEM_BIT(_fh, _rssem, _val)		\
 	FIELD_PREP(FBNIC_RPC_ACT_TBL1_RSS_ENA_##_rssem,	\
 		   FIELD_GET(RXH_##_fh, _val))
-static u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type)
+u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type)
 {
 	u32 flow_hash = fbn->rss_flow_hash[flow_type];
 	u32 rss_en_mask = 0;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
index b3515f2f5f92e..6892414195c3e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_rpc.h
@@ -96,6 +96,11 @@ enum {
 #define FBNIC_RPC_ACT_TBL_BMC_OFFSET		0
 #define FBNIC_RPC_ACT_TBL_BMC_ALL_MULTI_OFFSET	1
 
+/* This should leave us with 48 total entries in the TCAM that can be used
+ * for NFC after also deducting the 14 needed for RSS table programming.
+ */
+#define FBNIC_RPC_ACT_TBL_NFC_OFFSET		2
+
 /* We reserve the last 14 entries for RSS rules on the host. The BMC
  * unicast rule will need to be populated above these and is expected to
  * use MACDA TCAM entry 23 to store the BMC MAC address.
@@ -103,6 +108,9 @@ enum {
 #define FBNIC_RPC_ACT_TBL_RSS_OFFSET \
 	(FBNIC_RPC_ACT_TBL_NUM_ENTRIES - FBNIC_RSS_EN_NUM_ENTRIES)
 
+#define FBNIC_RPC_ACT_TBL_NFC_ENTRIES \
+	(FBNIC_RPC_ACT_TBL_RSS_OFFSET - FBNIC_RPC_ACT_TBL_NFC_OFFSET)
+
 /* Flags used to identify the owner for this MAC filter. Note that any
  * flags set for Broadcast thru Promisc indicate that the rule belongs
  * to the RSS filters for the host.
@@ -183,6 +191,7 @@ void fbnic_rss_init_en_mask(struct fbnic_net *fbn);
 void fbnic_rss_disable_hw(struct fbnic_dev *fbd);
 void fbnic_rss_reinit_hw(struct fbnic_dev *fbd, struct fbnic_net *fbn);
 void fbnic_rss_reinit(struct fbnic_dev *fbd, struct fbnic_net *fbn);
+u16 fbnic_flow_hash_2_rss_en_mask(struct fbnic_net *fbn, int flow_type);
 
 int __fbnic_xc_unsync(struct fbnic_mac_addr *mac_addr, unsigned int tcam_idx);
 struct fbnic_mac_addr *__fbnic_uc_sync(struct fbnic_dev *fbd,

From d2348b4bf748543172079eacb4dc0d40100fb443 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Feb 2025 15:53:33 -0800
Subject: [PATCH 0295/2753] selftests: drv-net: rss_ctx: skip tests which need
 multiple contexts cleanly

There's no good API to check how many contexts device supports.
But initial tests sense the context count already, so just store
that number and skip tests which we know need more.

Link: https://patch.msgid.link/20250206235334.1425329-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/hw/rss_ctx.py       | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index 7e5f4602e6b3b..d6e69d7d5e438 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -59,6 +59,14 @@ def require_ntuple(cfg):
         raise KsftSkipEx("Ntuple filters not enabled on the device: " + str(features["ntuple-filters"]))
 
 
+def require_context_cnt(cfg, need_cnt):
+    # There's no good API to get the context count, so the tests
+    # which try to add a lot opportunisitically set the count they
+    # discovered. Careful with test ordering!
+    if need_cnt and cfg.context_cnt and cfg.context_cnt < need_cnt:
+        raise KsftSkipEx(f"Test requires at least {need_cnt} contexts, but device only has {cfg.context_cnt}")
+
+
 # Get Rx packet counts for all queues, as a simple list of integers
 # if @prev is specified the prev counts will be subtracted
 def _get_rx_cnts(cfg, prev=None):
@@ -457,6 +465,8 @@ def test_rss_context(cfg, ctx_cnt=1, create_with_cfg=None):
                 raise
             ksft_pr(f"Failed to create context {i + 1}, trying to test what we got")
             ctx_cnt = i
+            if cfg.context_cnt is None:
+                cfg.context_cnt = ctx_cnt
             break
 
         _rss_key_check(cfg, context=ctx_id)
@@ -512,8 +522,7 @@ def test_rss_context_out_of_order(cfg, ctx_cnt=4):
     """
 
     require_ntuple(cfg)
-
-    requested_ctx_cnt = ctx_cnt
+    require_context_cnt(cfg, 4)
 
     # Try to allocate more queues when necessary
     qcnt = len(_get_rx_cnts(cfg))
@@ -578,9 +587,6 @@ def check_traffic():
     remove_ctx(-1)
     check_traffic()
 
-    if requested_ctx_cnt != ctx_cnt:
-        raise KsftSkipEx(f"Tested only {ctx_cnt} contexts, wanted {requested_ctx_cnt}")
-
 
 def test_rss_context_overlap(cfg, other_ctx=0):
     """
@@ -589,6 +595,8 @@ def test_rss_context_overlap(cfg, other_ctx=0):
     """
 
     require_ntuple(cfg)
+    if other_ctx:
+        require_context_cnt(cfg, 2)
 
     queue_cnt = len(_get_rx_cnts(cfg))
     if queue_cnt < 4:
@@ -741,6 +749,7 @@ def test_rss_ntuple_addition(cfg):
 
 def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.context_cnt = None
         cfg.ethnl = EthtoolFamily()
         cfg.netdevnl = NetdevFamily()
 

From 5797d3c62db81fd03ba7aeb36a83b44fb0ac2ecc Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@meta.com>
Date: Thu, 6 Feb 2025 15:53:34 -0800
Subject: [PATCH 0296/2753] eth: fbnic: support listing tcam content via
 debugfs

The device has a handful of relatively small TCAM tables,
support dumping the driver state via debugfs.

  # ethtool -N eth0 flow-type tcp6 \
      dst-ip 1111::2222 dst-port $((0x1122)) \
      src-ip 3333::4444 src-port $((0x3344)) \
      action 2
  Added rule with ID 47

  # cd $dbgfs
  # cat ip_src
  Idx S TCAM Bitmap       V Addr/Mask
  ------------------------------------
  00  1 00020000,00000000 6 33330000000000000000000000004444
                            00000000000000000000000000000000
  ...
  # cat ip_dst
  Idx S TCAM Bitmap       V Addr/Mask
  ------------------------------------
  00  1 00020000,00000000 6 11110000000000000000000000002222
                            00000000000000000000000000000000
  ...

  # cat act_tcam
  Idx S Value/Mask                                              RSS  Dest
  ------------------------------------------------------------------------
  ...
  49  1 0000 0000 0000 0000 0000 0000 1122 3344 0000 9c00 0088  000f 00000212
        ffff ffff ffff ffff ffff ffff 0000 0000 ffff 23ff ff00
  ...

The ipo_* tables are for outer IP addresses.
The tce_* table is for directing/stealing traffic to NC-SI.

Signed-off-by: Alexander Duyck <alexanderduyck@meta.com>
Link: https://patch.msgid.link/20250206235334.1425329-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_debugfs.c   | 138 ++++++++++++++++++
 1 file changed, 138 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
index ac80981f67c00..e8f2d7f2d9629 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_debugfs.c
@@ -44,6 +44,132 @@ static int fbnic_dbg_mac_addr_show(struct seq_file *s, void *v)
 }
 DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_mac_addr);
 
+static int fbnic_dbg_tce_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	int i, tcam_idx = 0;
+	char hdr[80];
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < ARRAY_SIZE(fbd->mac_addr); i++) {
+		struct fbnic_mac_addr *mac_addr = &fbd->mac_addr[i];
+
+		/* Verify BMC bit is set */
+		if (!test_bit(FBNIC_MAC_ADDR_T_BMC, mac_addr->act_tcam))
+			continue;
+
+		if (tcam_idx == FBNIC_TCE_TCAM_NUM_ENTRIES)
+			break;
+
+		seq_printf(s, "%02d  %d %64pb %pm\n",
+			   tcam_idx, mac_addr->state, mac_addr->act_tcam,
+			   mac_addr->value.addr8);
+		seq_printf(s, "                        %pm\n",
+			   mac_addr->mask.addr8);
+		tcam_idx++;
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_tce_tcam);
+
+static int fbnic_dbg_act_tcam_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-55s %-4s %s\n",
+		 "Idx", "S", "Value/Mask", "RSS", "Dest");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_ACT_NUM_ENTRIES; i++) {
+		struct fbnic_act_tcam *act_tcam = &fbd->act_tcam[i];
+
+		seq_printf(s, "%02d  %d %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x  %04x %08x\n",
+			   i, act_tcam->state,
+			   act_tcam->value.tcam[10], act_tcam->value.tcam[9],
+			   act_tcam->value.tcam[8], act_tcam->value.tcam[7],
+			   act_tcam->value.tcam[6], act_tcam->value.tcam[5],
+			   act_tcam->value.tcam[4], act_tcam->value.tcam[3],
+			   act_tcam->value.tcam[2], act_tcam->value.tcam[1],
+			   act_tcam->value.tcam[0], act_tcam->rss_en_mask,
+			   act_tcam->dest);
+		seq_printf(s, "      %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x %04x\n",
+			   act_tcam->mask.tcam[10], act_tcam->mask.tcam[9],
+			   act_tcam->mask.tcam[8], act_tcam->mask.tcam[7],
+			   act_tcam->mask.tcam[6], act_tcam->mask.tcam[5],
+			   act_tcam->mask.tcam[4], act_tcam->mask.tcam[3],
+			   act_tcam->mask.tcam[2], act_tcam->mask.tcam[1],
+			   act_tcam->mask.tcam[0]);
+	}
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_act_tcam);
+
+static int fbnic_dbg_ip_addr_show(struct seq_file *s,
+				  struct fbnic_ip_addr *ip_addr)
+{
+	char hdr[80];
+	int i;
+
+	/* Generate Header */
+	snprintf(hdr, sizeof(hdr), "%3s %s %-17s %s %s\n",
+		 "Idx", "S", "TCAM Bitmap", "V", "Addr/Mask");
+	seq_puts(s, hdr);
+	fbnic_dbg_desc_break(s, strnlen(hdr, sizeof(hdr)));
+
+	for (i = 0; i < FBNIC_RPC_TCAM_IP_ADDR_NUM_ENTRIES; i++, ip_addr++) {
+		seq_printf(s, "%02d  %d %64pb %d %pi6\n",
+			   i, ip_addr->state, ip_addr->act_tcam,
+			   ip_addr->version, &ip_addr->value);
+		seq_printf(s, "                          %pi6\n",
+			   &ip_addr->mask);
+	}
+
+	return 0;
+}
+
+static int fbnic_dbg_ip_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_src);
+
+static int fbnic_dbg_ip_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ip_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ip_dst);
+
+static int fbnic_dbg_ipo_src_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_src);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_src);
+
+static int fbnic_dbg_ipo_dst_show(struct seq_file *s, void *v)
+{
+	struct fbnic_dev *fbd = s->private;
+
+	return fbnic_dbg_ip_addr_show(s, fbd->ipo_dst);
+}
+DEFINE_SHOW_ATTRIBUTE(fbnic_dbg_ipo_dst);
+
 static int fbnic_dbg_pcie_stats_show(struct seq_file *s, void *v)
 {
 	struct fbnic_dev *fbd = s->private;
@@ -84,6 +210,18 @@ void fbnic_dbg_fbd_init(struct fbnic_dev *fbd)
 			    &fbnic_dbg_pcie_stats_fops);
 	debugfs_create_file("mac_addr", 0400, fbd->dbg_fbd, fbd,
 			    &fbnic_dbg_mac_addr_fops);
+	debugfs_create_file("tce_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_tce_tcam_fops);
+	debugfs_create_file("act_tcam", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_act_tcam_fops);
+	debugfs_create_file("ip_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_src_fops);
+	debugfs_create_file("ip_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ip_dst_fops);
+	debugfs_create_file("ipo_src", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_src_fops);
+	debugfs_create_file("ipo_dst", 0400, fbd->dbg_fbd, fbd,
+			    &fbnic_dbg_ipo_dst_fops);
 }
 
 void fbnic_dbg_fbd_exit(struct fbnic_dev *fbd)

From e2c6737e6e82e9991646cd5389391bb6d3572a68 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 30 Sep 2024 14:12:38 +0200
Subject: [PATCH 0297/2753] ice: Don't check device type when checking GNSS
 presence

Don't check if the device type is E810T as non-E810T devices can support
GNSS too and PCA9575 check is enough to determine if GNSS is present or
not.

Rename ice_gnss_is_gps_present() to ice_gnss_is_module_present()
because GNSS module supports multiple GNSS providers, not only GPS.

Move functions related to PCA9575 from ice_ptp_hw.c to ice_common.c
to be able to access them when PTP is disabled in the kernel, but GNSS
is enabled.

Remove logical AND with ICE_AQC_LINK_TOPO_NODE_TYPE_M in
ice_get_pca9575_handle(), which has no effect, and reorder device type
checks to check the device_id first, then set other variables.

Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 90 ++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_common.h |  2 +
 drivers/net/ethernet/intel/ice/ice_gnss.c   | 29 +++----
 drivers/net/ethernet/intel/ice/ice_gnss.h   |  4 +-
 drivers/net/ethernet/intel/ice/ice_lib.c    |  2 +-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 93 ---------------------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  1 -
 7 files changed, 105 insertions(+), 116 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index 7a2a2e8da8fab..b61a50fda533b 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -5764,6 +5764,96 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
 }
 
+/**
+ * ice_get_pca9575_handle - find and return the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @pca9575_handle: GPIO controller's handle
+ *
+ * Find and return the GPIO controller's handle in the netlist.
+ * When found - the value will be cached in the hw structure and following calls
+ * will return cached value.
+ *
+ * Return: 0 on success, -ENXIO when there's no PCA9575 present.
+ */
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
+{
+	struct ice_aqc_get_link_topo *cmd;
+	struct ice_aq_desc desc;
+	int err;
+	u8 idx;
+
+	/* If handle was read previously return cached value */
+	if (hw->io_expander_handle) {
+		*pca9575_handle = hw->io_expander_handle;
+		return 0;
+	}
+
+#define SW_PCA9575_SFP_TOPO_IDX		2
+#define SW_PCA9575_QSFP_TOPO_IDX	1
+
+	/* Check if the SW IO expander controlling SMA exists in the netlist. */
+	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
+		idx = SW_PCA9575_SFP_TOPO_IDX;
+	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
+		idx = SW_PCA9575_QSFP_TOPO_IDX;
+	else
+		return -ENXIO;
+
+	/* If handle was not detected read it from the netlist */
+	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
+	cmd = &desc.params.get_link_topo;
+	cmd->addr.topo_params.node_type_ctx =
+		ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL;
+	cmd->addr.topo_params.index = idx;
+
+	err = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
+	if (err)
+		return -ENXIO;
+
+	/* Verify if we found the right IO expander type */
+	if (desc.params.get_link_topo.node_part_num !=
+	    ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
+		return -ENXIO;
+
+	/* If present save the handle and return it */
+	hw->io_expander_handle =
+		le16_to_cpu(desc.params.get_link_topo.addr.handle);
+	*pca9575_handle = hw->io_expander_handle;
+
+	return 0;
+}
+
+/**
+ * ice_read_pca9575_reg - read the register from the PCA9575 controller
+ * @hw: pointer to the hw struct
+ * @offset: GPIO controller register offset
+ * @data: pointer to data to be read from the GPIO controller
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
+{
+	struct ice_aqc_link_topo_addr link_topo;
+	__le16 addr;
+	u16 handle;
+	int err;
+
+	memset(&link_topo, 0, sizeof(link_topo));
+
+	err = ice_get_pca9575_handle(hw, &handle);
+	if (err)
+		return err;
+
+	link_topo.handle = cpu_to_le16(handle);
+	link_topo.topo_params.node_type_ctx =
+		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
+			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
+
+	addr = cpu_to_le16((u16)offset);
+
+	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
+}
+
 /**
  * ice_aq_set_gpio
  * @hw: pointer to the hw struct
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 15ba385437389..54a8692839dd0 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -306,5 +306,7 @@ int
 ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		 u16 bus_addr, __le16 addr, u8 params, const u8 *data,
 		 struct ice_sq_cd *cd);
+int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle);
+int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 bool ice_fw_supports_report_dflt_cfg(struct ice_hw *hw);
 #endif /* _ICE_COMMON_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.c b/drivers/net/ethernet/intel/ice/ice_gnss.c
index b2148dbe49b28..6b26290452d48 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.c
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.c
@@ -381,32 +381,23 @@ void ice_gnss_exit(struct ice_pf *pf)
 }
 
 /**
- * ice_gnss_is_gps_present - Check if GPS HW is present
+ * ice_gnss_is_module_present - Check if GNSS HW is present
  * @hw: pointer to HW struct
+ *
+ * Return: true when GNSS is present, false otherwise.
  */
-bool ice_gnss_is_gps_present(struct ice_hw *hw)
+bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
-	if (!hw->func_caps.ts_func_info.src_tmr_owned)
-		return false;
+	int err;
+	u8 data;
 
-	if (!ice_is_gps_in_netlist(hw))
+	if (!hw->func_caps.ts_func_info.src_tmr_owned ||
+	    !ice_is_gps_in_netlist(hw))
 		return false;
 
-#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
-	if (ice_is_e810t(hw)) {
-		int err;
-		u8 data;
-
-		err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
-		if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
-			return false;
-	} else {
-		return false;
-	}
-#else
-	if (!ice_is_e810t(hw))
+	err = ice_read_pca9575_reg(hw, ICE_PCA9575_P0_IN, &data);
+	if (err || !!(data & ICE_P0_GNSS_PRSNT_N))
 		return false;
-#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 
 	return true;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_gnss.h b/drivers/net/ethernet/intel/ice/ice_gnss.h
index 75e567ad70594..15daf603ed7bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_gnss.h
+++ b/drivers/net/ethernet/intel/ice/ice_gnss.h
@@ -37,11 +37,11 @@ struct gnss_serial {
 #if IS_ENABLED(CONFIG_GNSS)
 void ice_gnss_init(struct ice_pf *pf);
 void ice_gnss_exit(struct ice_pf *pf);
-bool ice_gnss_is_gps_present(struct ice_hw *hw);
+bool ice_gnss_is_module_present(struct ice_hw *hw);
 #else
 static inline void ice_gnss_init(struct ice_pf *pf) { }
 static inline void ice_gnss_exit(struct ice_pf *pf) { }
-static inline bool ice_gnss_is_gps_present(struct ice_hw *hw)
+static inline bool ice_gnss_is_module_present(struct ice_hw *hw)
 {
 	return false;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 16c419809849c..978f308d3b1b9 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3893,7 +3893,7 @@ void ice_init_feature_support(struct ice_pf *pf)
 			ice_set_feature_support(pf, ICE_F_CGU);
 		if (ice_is_clock_mux_in_netlist(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_SMA_CTRL);
-		if (ice_gnss_is_gps_present(&pf->hw))
+		if (ice_gnss_is_module_present(&pf->hw))
 			ice_set_feature_support(pf, ICE_F_GNSS);
 		break;
 	default:
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index ec91822e92806..53ce40fa2fe6b 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -5315,68 +5315,6 @@ ice_get_phy_tx_tstamp_ready_e810(struct ice_hw *hw, u8 port, u64 *tstamp_ready)
  * to access the extended GPIOs available.
  */
 
-/**
- * ice_get_pca9575_handle
- * @hw: pointer to the hw struct
- * @pca9575_handle: GPIO controller's handle
- *
- * Find and return the GPIO controller's handle in the netlist.
- * When found - the value will be cached in the hw structure and following calls
- * will return cached value
- */
-static int
-ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
-{
-	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
-	int status;
-	u8 idx;
-
-	/* If handle was read previously return cached value */
-	if (hw->io_expander_handle) {
-		*pca9575_handle = hw->io_expander_handle;
-		return 0;
-	}
-
-	/* If handle was not detected read it from the netlist */
-	cmd = &desc.params.get_link_topo;
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-
-	/* Set node type to GPIO controller */
-	cmd->addr.topo_params.node_type_ctx =
-		(ICE_AQC_LINK_TOPO_NODE_TYPE_M &
-		 ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL);
-
-#define SW_PCA9575_SFP_TOPO_IDX		2
-#define SW_PCA9575_QSFP_TOPO_IDX	1
-
-	/* Check if the SW IO expander controlling SMA exists in the netlist. */
-	if (hw->device_id == ICE_DEV_ID_E810C_SFP)
-		idx = SW_PCA9575_SFP_TOPO_IDX;
-	else if (hw->device_id == ICE_DEV_ID_E810C_QSFP)
-		idx = SW_PCA9575_QSFP_TOPO_IDX;
-	else
-		return -EOPNOTSUPP;
-
-	cmd->addr.topo_params.index = idx;
-
-	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
-	if (status)
-		return -EOPNOTSUPP;
-
-	/* Verify if we found the right IO expander type */
-	if (desc.params.get_link_topo.node_part_num !=
-		ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
-		return -EOPNOTSUPP;
-
-	/* If present save the handle and return it */
-	hw->io_expander_handle =
-		le16_to_cpu(desc.params.get_link_topo.addr.handle);
-	*pca9575_handle = hw->io_expander_handle;
-
-	return 0;
-}
-
 /**
  * ice_read_sma_ctrl
  * @hw: pointer to the hw struct
@@ -5441,37 +5379,6 @@ int ice_write_sma_ctrl(struct ice_hw *hw, u8 data)
 	return status;
 }
 
-/**
- * ice_read_pca9575_reg
- * @hw: pointer to the hw struct
- * @offset: GPIO controller register offset
- * @data: pointer to data to be read from the GPIO controller
- *
- * Read the register from the GPIO controller
- */
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data)
-{
-	struct ice_aqc_link_topo_addr link_topo;
-	__le16 addr;
-	u16 handle;
-	int err;
-
-	memset(&link_topo, 0, sizeof(link_topo));
-
-	err = ice_get_pca9575_handle(hw, &handle);
-	if (err)
-		return err;
-
-	link_topo.handle = cpu_to_le16(handle);
-	link_topo.topo_params.node_type_ctx =
-		FIELD_PREP(ICE_AQC_LINK_TOPO_NODE_CTX_M,
-			   ICE_AQC_LINK_TOPO_NODE_CTX_PROVIDED);
-
-	addr = cpu_to_le16((u16)offset);
-
-	return ice_aq_read_i2c(hw, link_topo, 0, addr, 1, data, NULL);
-}
-
 /**
  * ice_ptp_read_sdp_ac - read SDP available connections section from NVM
  * @hw: pointer to the HW struct
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 6779ce120515a..15f048d9b5823 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -395,7 +395,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold);
 /* E810 family functions */
 int ice_read_sma_ctrl(struct ice_hw *hw, u8 *data);
 int ice_write_sma_ctrl(struct ice_hw *hw, u8 data);
-int ice_read_pca9575_reg(struct ice_hw *hw, u8 offset, u8 *data);
 int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries);
 int ice_cgu_get_num_pins(struct ice_hw *hw, bool input);
 enum dpll_pin_type ice_cgu_get_pin_type(struct ice_hw *hw, u8 pin, bool input);

From fd75f371f3a1b04a33d2e750363d6ad76abf734e Mon Sep 17 00:00:00 2001
From: Christian Bruel <christian.bruel@foss.st.com>
Date: Mon, 10 Feb 2025 11:35:15 +0100
Subject: [PATCH 0298/2753] phy: stm32: Fix constant-value overflow assertion

Rework the workaround as the lookup tables always fits into the bitfield,
and the default values are defined by the hardware and cannot be 0:

Guard against false positive with a WARN_ON check to make the compiler
happy: The offset range is pre-checked against the sorted imp_lookup_table
values and overflow should not happen and would be caught by a warning and
return in error.

Also guard against a true positive found during the max_vswing lookup, as a
max vswing value can be 802000 or 803000 microvolt depending on the current
impedance. Therefore set the default impedence index.

Fixes: 2de679ecd724 ("phy: stm32: work around constant-value overflow assertion")
Signed-off-by: Christian Bruel <christian.bruel@foss.st.com>
Link: https://lore.kernel.org/r/20250210103515.2598377-1-christian.bruel@foss.st.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/st/phy-stm32-combophy.c | 38 ++++++++++++++---------------
 1 file changed, 18 insertions(+), 20 deletions(-)

diff --git a/drivers/phy/st/phy-stm32-combophy.c b/drivers/phy/st/phy-stm32-combophy.c
index 49e9fa90a6819..607b4d607eb5e 100644
--- a/drivers/phy/st/phy-stm32-combophy.c
+++ b/drivers/phy/st/phy-stm32-combophy.c
@@ -111,6 +111,7 @@ static const struct clk_impedance imp_lookup[] = {
 	{ 4204000, { 511000, 609000, 706000, 802000 } },
 	{ 3999000, { 571000, 648000, 726000, 803000 } }
 };
+#define DEFAULT_IMP_INDEX 3 /* Default impedance is 50 Ohm */
 
 static int stm32_impedance_tune(struct stm32_combophy *combophy)
 {
@@ -119,10 +120,9 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy)
 	u8 imp_of, vswing_of;
 	u32 max_imp = imp_lookup[0].microohm;
 	u32 min_imp = imp_lookup[imp_size - 1].microohm;
-	u32 max_vswing = imp_lookup[imp_size - 1].vswing[vswing_size - 1];
+	u32 max_vswing;
 	u32 min_vswing = imp_lookup[0].vswing[0];
 	u32 val;
-	u32 regval;
 
 	if (!of_property_read_u32(combophy->dev->of_node, "st,output-micro-ohms", &val)) {
 		if (val < min_imp || val > max_imp) {
@@ -130,45 +130,43 @@ static int stm32_impedance_tune(struct stm32_combophy *combophy)
 			return -EINVAL;
 		}
 
-		regval = 0;
-		for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++) {
-			if (imp_lookup[imp_of].microohm <= val) {
-				regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of);
+		for (imp_of = 0; imp_of < ARRAY_SIZE(imp_lookup); imp_of++)
+			if (imp_lookup[imp_of].microohm <= val)
 				break;
-			}
-		}
+
+		if (WARN_ON(imp_of == ARRAY_SIZE(imp_lookup)))
+			return -EINVAL;
 
 		dev_dbg(combophy->dev, "Set %u micro-ohms output impedance\n",
 			imp_lookup[imp_of].microohm);
 
 		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
 				   STM32MP25_PCIEPRG_IMPCTRL_OHM,
-				   regval);
-	} else {
-		regmap_read(combophy->regmap, SYSCFG_PCIEPRGCR, &val);
-		imp_of = FIELD_GET(STM32MP25_PCIEPRG_IMPCTRL_OHM, val);
-	}
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_OHM, imp_of));
+	} else
+		imp_of = DEFAULT_IMP_INDEX;
 
 	if (!of_property_read_u32(combophy->dev->of_node, "st,output-vswing-microvolt", &val)) {
+		max_vswing = imp_lookup[imp_of].vswing[vswing_size - 1];
+
 		if (val < min_vswing || val > max_vswing) {
 			dev_err(combophy->dev, "Invalid value %u for output vswing\n", val);
 			return -EINVAL;
 		}
 
-		regval = 0;
-		for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++) {
-			if (imp_lookup[imp_of].vswing[vswing_of] >= val) {
-				regval = FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of);
+		for (vswing_of = 0; vswing_of < ARRAY_SIZE(imp_lookup[imp_of].vswing); vswing_of++)
+			if (imp_lookup[imp_of].vswing[vswing_of] >= val)
 				break;
-			}
-		}
+
+		if (WARN_ON(vswing_of == ARRAY_SIZE(imp_lookup[imp_of].vswing)))
+			return -EINVAL;
 
 		dev_dbg(combophy->dev, "Set %u microvolt swing\n",
 			 imp_lookup[imp_of].vswing[vswing_of]);
 
 		regmap_update_bits(combophy->regmap, SYSCFG_PCIEPRGCR,
 				   STM32MP25_PCIEPRG_IMPCTRL_VSWING,
-				   regval);
+				   FIELD_PREP(STM32MP25_PCIEPRG_IMPCTRL_VSWING, vswing_of));
 	}
 
 	return 0;

From e2158c953c973adb49383ddea2504faf08d375b7 Mon Sep 17 00:00:00 2001
From: Kaustabh Chakraborty <kauschluss@disroot.org>
Date: Sun, 9 Feb 2025 00:29:30 +0530
Subject: [PATCH 0299/2753] phy: exynos5-usbdrd: fix MPLL_MULTIPLIER and
 SSC_REFCLKSEL masks in refclk

In exynos5_usbdrd_{pipe3,utmi}_set_refclk(), the masks
PHYCLKRST_MPLL_MULTIPLIER_MASK and PHYCLKRST_SSC_REFCLKSEL_MASK are not
inverted when applied to the register values. Fix it.

Cc: stable@vger.kernel.org
Fixes: 59025887fb08 ("phy: Add new Exynos5 USB 3.0 PHY driver")
Signed-off-by: Kaustabh Chakraborty <kauschluss@disroot.org>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Anand Moon <linux.amoon@gmail.com>
Link: https://lore.kernel.org/r/20250209-exynos5-usbdrd-masks-v1-1-4f7f83f323d7@disroot.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos5-usbdrd.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index c421b495eb0fe..4a108fdab118c 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -488,9 +488,9 @@ exynos5_usbdrd_pipe3_set_refclk(struct phy_usb_instance *inst)
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
 	/* FSEL settings corresponding to reference clock */
-	reg &= ~PHYCLKRST_FSEL_PIPE_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_PIPE_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	switch (phy_drd->extrefclk) {
 	case EXYNOS5_FSEL_50MHZ:
 		reg |= (PHYCLKRST_MPLL_MULTIPLIER_50M_REF |
@@ -532,9 +532,9 @@ exynos5_usbdrd_utmi_set_refclk(struct phy_usb_instance *inst)
 	reg &= ~PHYCLKRST_REFCLKSEL_MASK;
 	reg |=	PHYCLKRST_REFCLKSEL_EXT_REFCLK;
 
-	reg &= ~PHYCLKRST_FSEL_UTMI_MASK |
-		PHYCLKRST_MPLL_MULTIPLIER_MASK |
-		PHYCLKRST_SSC_REFCLKSEL_MASK;
+	reg &= ~(PHYCLKRST_FSEL_UTMI_MASK |
+		 PHYCLKRST_MPLL_MULTIPLIER_MASK |
+		 PHYCLKRST_SSC_REFCLKSEL_MASK);
 	reg |= PHYCLKRST_FSEL(phy_drd->extrefclk);
 
 	return reg;

From 9973ac9f23a79285d70365c72e98bffdb94a429d Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 30 Sep 2024 14:12:39 +0200
Subject: [PATCH 0300/2753] ice: Remove unnecessary ice_is_e8xx() functions

Remove unnecessary ice_is_e8xx() functions and PHY model. Instead, use
MAC type where applicable.

Don't check device type in ice_ptp_maybe_trigger_tx_interrupt(), because
in reality it depends on the ready bitmap, which only E810 does not
have.

Call ice_ptp_cfg_phy_interrupt() unconditionally, because all further
function calls check the MAC type anyway and this allows simpler code
in the future with addition of the new MAC types.

Reorder ICE_MAC_* cases in switches in ice_ptp* as in enum ice_mac_type.

Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice.h        |   5 -
 drivers/net/ethernet/intel/ice/ice_common.c | 118 +---------------
 drivers/net/ethernet/intel/ice/ice_common.h |   5 -
 drivers/net/ethernet/intel/ice/ice_ddp.c    |   4 +-
 drivers/net/ethernet/intel/ice/ice_ptp.c    | 133 +++++++++---------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 142 ++++++++++----------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  10 +-
 drivers/net/ethernet/intel/ice/ice_type.h   |   9 --
 8 files changed, 147 insertions(+), 279 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 2a6de21151933..c9104b13e1d2a 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -1046,10 +1046,5 @@ static inline void ice_clear_rdma_cap(struct ice_pf *pf)
 	clear_bit(ICE_FLAG_RDMA_ENA, pf->flags);
 }
 
-static inline enum ice_phy_model ice_get_phy_model(const struct ice_hw *hw)
-{
-	return hw->ptp.phy_model;
-}
-
 extern const struct xdp_metadata_ops ice_xdp_md_ops;
 #endif /* _ICE_H_ */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index b61a50fda533b..aaa592ffd2d82 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -186,7 +186,7 @@ static int ice_set_mac_type(struct ice_hw *hw)
  * ice_is_generic_mac - check if device's mac_type is generic
  * @hw: pointer to the hardware structure
  *
- * Return: true if mac_type is generic (with SBQ support), false if not
+ * Return: true if mac_type is ICE_MAC_GENERIC*, false otherwise.
  */
 bool ice_is_generic_mac(struct ice_hw *hw)
 {
@@ -194,120 +194,6 @@ bool ice_is_generic_mac(struct ice_hw *hw)
 		hw->mac_type == ICE_MAC_GENERIC_3K_E825);
 }
 
-/**
- * ice_is_e810
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E810 based, false if not.
- */
-bool ice_is_e810(struct ice_hw *hw)
-{
-	return hw->mac_type == ICE_MAC_E810;
-}
-
-/**
- * ice_is_e810t
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E810T based, false if not.
- */
-bool ice_is_e810t(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E810C_SFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T:
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T4:
-		case ICE_SUBDEV_ID_E810T6:
-		case ICE_SUBDEV_ID_E810T7:
-			return true;
-		}
-		break;
-	case ICE_DEV_ID_E810C_QSFP:
-		switch (hw->subsystem_device_id) {
-		case ICE_SUBDEV_ID_E810T2:
-		case ICE_SUBDEV_ID_E810T3:
-		case ICE_SUBDEV_ID_E810T5:
-			return true;
-		}
-		break;
-	default:
-		break;
-	}
-
-	return false;
-}
-
-/**
- * ice_is_e822 - Check if a device is E822 family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E822 based, false if not.
- */
-bool ice_is_e822(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E822C_BACKPLANE:
-	case ICE_DEV_ID_E822C_QSFP:
-	case ICE_DEV_ID_E822C_SFP:
-	case ICE_DEV_ID_E822C_10G_BASE_T:
-	case ICE_DEV_ID_E822C_SGMII:
-	case ICE_DEV_ID_E822L_BACKPLANE:
-	case ICE_DEV_ID_E822L_SFP:
-	case ICE_DEV_ID_E822L_10G_BASE_T:
-	case ICE_DEV_ID_E822L_SGMII:
-		return true;
-	default:
-		return false;
-	}
-}
-
-/**
- * ice_is_e823
- * @hw: pointer to the hardware structure
- *
- * returns true if the device is E823-L or E823-C based, false if not.
- */
-bool ice_is_e823(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E823L_BACKPLANE:
-	case ICE_DEV_ID_E823L_SFP:
-	case ICE_DEV_ID_E823L_10G_BASE_T:
-	case ICE_DEV_ID_E823L_1GBE:
-	case ICE_DEV_ID_E823L_QSFP:
-	case ICE_DEV_ID_E823C_BACKPLANE:
-	case ICE_DEV_ID_E823C_QSFP:
-	case ICE_DEV_ID_E823C_SFP:
-	case ICE_DEV_ID_E823C_10G_BASE_T:
-	case ICE_DEV_ID_E823C_SGMII:
-		return true;
-	default:
-		return false;
-	}
-}
-
-/**
- * ice_is_e825c - Check if a device is E825C family device
- * @hw: pointer to the hardware structure
- *
- * Return: true if the device is E825-C based, false if not.
- */
-bool ice_is_e825c(struct ice_hw *hw)
-{
-	switch (hw->device_id) {
-	case ICE_DEV_ID_E825C_BACKPLANE:
-	case ICE_DEV_ID_E825C_QSFP:
-	case ICE_DEV_ID_E825C_SFP:
-	case ICE_DEV_ID_E825C_SGMII:
-		return true;
-	default:
-		return false;
-	}
-}
-
 /**
  * ice_is_pf_c827 - check if pf contains c827 phy
  * @hw: pointer to the hw struct
@@ -2408,7 +2294,7 @@ ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 	info->tmr_index_owned = ((number & ICE_TS_TMR_IDX_OWND_M) != 0);
 	info->tmr_index_assoc = ((number & ICE_TS_TMR_IDX_ASSOC_M) != 0);
 
-	if (!ice_is_e825c(hw)) {
+	if (hw->mac_type != ICE_MAC_GENERIC_3K_E825) {
 		info->clk_freq = FIELD_GET(ICE_TS_CLK_FREQ_M, number);
 		info->clk_src = ((number & ICE_TS_CLK_SRC_M) != 0);
 	} else {
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 54a8692839dd0..9b00aa0ddf10e 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -131,7 +131,6 @@ int
 ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd);
 bool ice_is_generic_mac(struct ice_hw *hw);
-bool ice_is_e810(struct ice_hw *hw);
 int ice_clear_pf_cfg(struct ice_hw *hw);
 int
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
@@ -276,10 +275,6 @@ ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 void
 ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded,
 		  u64 *prev_stat, u64 *cur_stat);
-bool ice_is_e810t(struct ice_hw *hw);
-bool ice_is_e822(struct ice_hw *hw);
-bool ice_is_e823(struct ice_hw *hw);
-bool ice_is_e825c(struct ice_hw *hw);
 int
 ice_sched_query_elem(struct ice_hw *hw, u32 node_teid,
 		     struct ice_aqc_txsched_elem_data *buf);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 03988be03729b..69d5b1a28491d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -2345,14 +2345,14 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
 					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
 
-		if (ice_is_e825c(hw))
+		if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
 			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
 		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
 	}
 
-	if (!ice_is_e825c(hw))
+	if (hw->mac_type != ICE_MAC_GENERIC_3K_E825)
 		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index e26320ce52ca1..7bb4005a67f63 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1318,20 +1318,20 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 	struct ice_hw *hw = &pf->hw;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_stop_phy_timer_eth56g(hw, port, true);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
 		err = ice_stop_phy_timer_e82x(hw, port, true);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_stop_phy_timer_eth56g(hw, port, true);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1361,19 +1361,16 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 	unsigned long flags;
 	int err;
 
-	if (ice_is_e810(hw))
-		return 0;
-
 	if (!ptp_port->link_up)
 		return ice_ptp_port_phy_stop(ptp_port);
 
 	mutex_lock(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_start_phy_timer_eth56g(hw, port);
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		err = 0;
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		/* Start the PHY timer in Vernier mode */
 		kthread_cancel_delayed_work_sync(&ptp_port->ov_work);
 
@@ -1398,6 +1395,9 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 		kthread_queue_delayed_work(pf->ptp.kworker, &ptp_port->ov_work,
 					   0);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_start_phy_timer_eth56g(hw, port);
+		break;
 	default:
 		err = -ENODEV;
 	}
@@ -1432,12 +1432,13 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 	/* Skip HW writes if reset is in progress */
 	if (pf->hw.reset_ongoing)
 		return;
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		/* Do not reconfigure E810 PHY */
 		return;
-	case ICE_PHY_ETH56G:
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_port_phy_restart(ptp_port);
 		return;
 	default:
@@ -1465,46 +1466,44 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 
 	ice_ptp_reset_ts_memory(hw);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G: {
-		int port;
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		return 0;
+	case ICE_MAC_GENERIC: {
+		int quad;
 
-		for (port = 0; port < hw->ptp.num_lports; port++) {
+		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
+		     quad++) {
 			int err;
 
-			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
+			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
-					port, err);
+				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
+					quad, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E82X: {
-		int quad;
+	case ICE_MAC_GENERIC_3K_E825: {
+		int port;
 
-		for (quad = 0; quad < ICE_GET_QUAD_NUM(hw->ptp.num_lports);
-		     quad++) {
+		for (port = 0; port < hw->ptp.num_lports; port++) {
 			int err;
 
-			err = ice_phy_cfg_intr_e82x(hw, quad, ena, threshold);
+			err = ice_phy_cfg_intr_eth56g(hw, port, ena, threshold);
 			if (err) {
-				dev_err(dev, "Failed to configure PHY interrupt for quad %d, err %d\n",
-					quad, err);
+				dev_err(dev, "Failed to configure PHY interrupt for port %d, err %d\n",
+					port, err);
 				return err;
 			}
 		}
 
 		return 0;
 	}
-	case ICE_PHY_E810:
-		return 0;
-	case ICE_PHY_UNSUP:
+	case ICE_MAC_UNKNOWN:
 	default:
-		dev_warn(dev, "%s: Unexpected PHY model %d\n", __func__,
-			 ice_get_phy_model(hw));
 		return -EOPNOTSUPP;
 	}
 }
@@ -1740,7 +1739,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 	/* 0. Reset mode & out_en in AUX_OUT */
 	wr32(hw, GLTSYN_AUX_OUT(chan, tmr_idx), 0);
 
-	if (ice_is_e825c(hw)) {
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825) {
 		int err;
 
 		/* Enable/disable CGU 1PPS output for E825C */
@@ -1824,7 +1823,7 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		return ice_ptp_write_perout(hw, rq->index, gpio_pin, 0, 0);
 
 	if (strncmp(pf->ptp.pin_desc[pin_desc_idx].name, "1PPS", 64) == 0 &&
-	    period != NSEC_PER_SEC && hw->ptp.phy_model == ICE_PHY_E82X) {
+	    period != NSEC_PER_SEC && hw->mac_type == ICE_MAC_GENERIC) {
 		dev_err(ice_pf_to_dev(pf), "1PPS pin supports only 1 s period\n");
 		return -EOPNOTSUPP;
 	}
@@ -2078,7 +2077,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	/* For Vernier mode on E82X, we need to recalibrate after new settime.
 	 * Start with marking timestamps as invalid.
 	 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X) {
+	if (hw->mac_type == ICE_MAC_GENERIC) {
 		err = ice_ptp_clear_phy_offset_ready_e82x(hw);
 		if (err)
 			dev_warn(ice_pf_to_dev(pf), "Failed to mark timestamps as invalid before settime\n");
@@ -2102,7 +2101,7 @@ ice_ptp_settime64(struct ptp_clock_info *info, const struct timespec64 *ts)
 	ice_ptp_enable_all_perout(pf);
 
 	/* Recalibrate and re-enable timestamp blocks for E822/E823 */
-	if (ice_get_phy_model(hw) == ICE_PHY_E82X)
+	if (hw->mac_type == ICE_MAC_GENERIC)
 		ice_ptp_restart_all_phy(pf);
 exit:
 	if (err) {
@@ -2556,7 +2555,7 @@ static void ice_ptp_set_funcs_e82x(struct ice_pf *pf)
 		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x;
 
 #endif /* CONFIG_ICE_HWTS */
-	if (ice_is_e825c(&pf->hw)) {
+	if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) {
 		pf->ptp.ice_pin_desc = ice_pin_desc_e825c;
 		pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c);
 	} else {
@@ -2644,10 +2643,17 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	info->enable = ice_ptp_gpio_enable;
 	info->verify = ice_verify_pin;
 
-	if (ice_is_e810(&pf->hw))
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_set_funcs_e810(pf);
-	else
+		return;
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_set_funcs_e82x(pf);
+		return;
+	default:
+		return;
+	}
 }
 
 /**
@@ -2777,7 +2783,7 @@ static void ice_ptp_maybe_trigger_tx_interrupt(struct ice_pf *pf)
 	bool trigger_oicr = false;
 	unsigned int i;
 
-	if (ice_is_e810(hw))
+	if (!pf->ptp.port.tx.has_ready_bitmap)
 		return;
 
 	if (!ice_pf_src_tmr_owned(pf))
@@ -2912,14 +2918,12 @@ static int ice_ptp_rebuild_owner(struct ice_pf *pf)
 	 */
 	ice_ptp_flush_all_tx_tracker(pf);
 
-	if (!ice_is_e810(hw)) {
-		/* Enable quad interrupts */
-		err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
-		if (err)
-			return err;
+	/* Enable quad interrupts */
+	err = ice_ptp_cfg_phy_interrupt(pf, true, 1);
+	if (err)
+		return err;
 
-		ice_ptp_restart_all_phy(pf);
-	}
+	ice_ptp_restart_all_phy(pf);
 
 	/* Re-enable all periodic outputs and external timestamp events */
 	ice_ptp_enable_all_perout(pf);
@@ -2971,8 +2975,9 @@ void ice_ptp_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
 
 static bool ice_is_primary(struct ice_hw *hw)
 {
-	return ice_is_e825c(hw) && ice_is_dual(hw) ?
-		!!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) : true;
+	return hw->mac_type == ICE_MAC_GENERIC_3K_E825 && ice_is_dual(hw) ?
+		       !!(hw->dev_caps.nac_topo.mode & ICE_NAC_TOPO_PRIMARY_M) :
+		       true;
 }
 
 static int ice_ptp_setup_adapter(struct ice_pf *pf)
@@ -2990,7 +2995,7 @@ static int ice_ptp_setup_pf(struct ice_pf *pf)
 	struct ice_ptp *ctrl_ptp = ice_get_ctrl_ptp(pf);
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (WARN_ON(!ctrl_ptp) || ice_get_phy_model(&pf->hw) == ICE_PHY_UNSUP)
+	if (WARN_ON(!ctrl_ptp) || pf->hw.mac_type == ICE_MAC_UNKNOWN)
 		return -ENODEV;
 
 	INIT_LIST_HEAD(&ptp->port.list_node);
@@ -3007,7 +3012,7 @@ static void ice_ptp_cleanup_pf(struct ice_pf *pf)
 {
 	struct ice_ptp *ptp = &pf->ptp;
 
-	if (ice_get_phy_model(&pf->hw) != ICE_PHY_UNSUP) {
+	if (pf->hw.mac_type != ICE_MAC_UNKNOWN) {
 		mutex_lock(&pf->adapter->ports.lock);
 		list_del(&ptp->port.list_node);
 		mutex_unlock(&pf->adapter->ports.lock);
@@ -3134,18 +3139,18 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	mutex_init(&ptp_port->ps_lock);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
-					      ptp_port->port_num);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
 
 		return ice_ptp_init_tx_e82x(pf, &ptp_port->tx,
 					    ptp_port->port_num);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
+					      ptp_port->port_num);
 	default:
 		return -ENODEV;
 	}
@@ -3162,8 +3167,8 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
  */
 static void ice_ptp_init_tx_interrupt_mode(struct ice_pf *pf)
 {
-	switch (ice_get_phy_model(&pf->hw)) {
-	case ICE_PHY_E82X:
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
 		/* E822 based PHY has the clock owner process the interrupt
 		 * for all ports.
 		 */
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 53ce40fa2fe6b..8475d422f1ec4 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -746,7 +746,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 	int err;
 
 	/* Disable sticky lock detection so lock err reported is accurate */
-	if (ice_is_e825c(hw))
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
 		err = ice_cfg_cgu_pll_dis_sticky_bits_e825c(hw);
 	else
 		err = ice_cfg_cgu_pll_dis_sticky_bits_e82x(hw);
@@ -756,7 +756,7 @@ static int ice_init_cgu_e82x(struct ice_hw *hw)
 	/* Configure the CGU PLL using the parameters from the function
 	 * capabilities.
 	 */
-	if (ice_is_e825c(hw))
+	if (hw->mac_type == ICE_MAC_GENERIC_3K_E825)
 		err = ice_cfg_cgu_pll_e825c(hw, ts_info->time_ref,
 					    (enum ice_clk_src)ts_info->clk_src);
 	else
@@ -827,8 +827,8 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
 	/* Certain hardware families share the same register values for the
 	 * port register and source timer register.
 	 */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
 	default:
 		break;
@@ -2729,10 +2729,7 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 	struct ice_eth56g_params *params;
-	u32 phy_rev;
-	int err;
 
-	ptp->phy_model = ICE_PHY_ETH56G;
 	params = &ptp->phy.eth56g;
 	params->onestep_ena = false;
 	params->peer_delay = 0;
@@ -2742,9 +2739,6 @@ static void ice_ptp_init_phy_e825(struct ice_hw *hw)
 	ptp->num_lports = params->num_phys * ptp->ports_per_phy;
 
 	ice_sb_access_ena_eth56g(hw, true);
-	err = ice_read_phy_eth56g(hw, hw->pf_id, PHY_REG_REVISION, &phy_rev);
-	if (err || phy_rev != PHY_REVISION_ETH56G)
-		ptp->phy_model = ICE_PHY_UNSUP;
 }
 
 /* E822 family functions
@@ -4792,7 +4786,6 @@ int ice_phy_cfg_intr_e82x(struct ice_hw *hw, u8 quad, bool ena, u8 threshold)
  */
 static void ice_ptp_init_phy_e82x(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E82X;
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 8;
 }
@@ -5445,7 +5438,6 @@ int ice_ptp_read_sdp_ac(struct ice_hw *hw, __le16 *entries, uint *num_entries)
  */
 static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
 {
-	ptp->phy_model = ICE_PHY_E810;
 	ptp->num_lports = 8;
 	ptp->ports_per_phy = 4;
 
@@ -5454,9 +5446,8 @@ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
 
 /* Device agnostic functions
  *
- * The following functions implement shared behavior common to both E822 and
- * E810 devices, possibly calling a device specific implementation where
- * necessary.
+ * The following functions implement shared behavior common to all devices,
+ * possibly calling a device specific implementation where necessary.
  */
 
 /**
@@ -5519,14 +5510,19 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 {
 	struct ice_ptp_hw *ptp = &hw->ptp;
 
-	if (ice_is_e822(hw) || ice_is_e823(hw))
-		ice_ptp_init_phy_e82x(ptp);
-	else if (ice_is_e810(hw))
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		ice_ptp_init_phy_e810(ptp);
-	else if (ice_is_e825c(hw))
+		break;
+	case ICE_MAC_GENERIC:
+		ice_ptp_init_phy_e82x(ptp);
+		break;
+	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_init_phy_e825(hw);
-	else
-		ptp->phy_model = ICE_PHY_UNSUP;
+		break;
+	default:
+		return;
+	}
 }
 
 /**
@@ -5547,11 +5543,11 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 static int ice_ptp_write_port_cmd(struct ice_hw *hw, u8 port,
 				  enum ice_ptp_tmr_cmd cmd)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		return ice_ptp_write_port_cmd_e82x(hw, port, cmd);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_write_port_cmd_eth56g(hw, port, cmd);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5612,8 +5608,8 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	u32 port;
 
 	/* PHY models which can program all ports simultaneously */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_port_cmd_e810(hw, cmd);
 	default:
 		break;
@@ -5691,17 +5687,17 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 
 	/* PHY timers */
 	/* Fill Rx and Tx ports and send msg to PHY */
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_time_eth56g(hw,
-						   (u32)(time & 0xFFFFFFFF));
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_time_e810(hw, time & 0xFFFFFFFF);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_time_e82x(hw, time & 0xFFFFFFFF);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_time_eth56g(hw,
+						   (u32)(time & 0xFFFFFFFF));
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5737,16 +5733,16 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_incval_e810(hw, incval);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_incval_e82x(hw, incval);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_incval_eth56g(hw, incval);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5806,16 +5802,16 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), 0);
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), adj);
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
-		break;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_adj_e82x(hw, adj);
 		break;
+	case ICE_MAC_GENERIC_3K_E825:
+		err = ice_ptp_prep_phy_adj_eth56g(hw, adj);
+		break;
 	default:
 		err = -EOPNOTSUPP;
 	}
@@ -5839,13 +5835,13 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
  */
 int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_read_ptp_tstamp_eth56g(hw, block, idx, tstamp);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5869,13 +5865,13 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
  */
 int ice_clear_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_clear_phy_tstamp_e810(hw, block, idx);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_clear_phy_tstamp_e82x(hw, block, idx);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_clear_ptp_tstamp_eth56g(hw, block, idx);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5932,14 +5928,14 @@ static int ice_get_pf_c827_idx(struct ice_hw *hw, u8 *idx)
  */
 void ice_ptp_reset_ts_memory(struct ice_hw *hw)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		ice_ptp_reset_ts_memory_eth56g(hw);
-		break;
-	case ICE_PHY_E82X:
+	switch (hw->mac_type) {
+	case ICE_MAC_GENERIC:
 		ice_ptp_reset_ts_memory_e82x(hw);
 		break;
-	case ICE_PHY_E810:
+	case ICE_MAC_GENERIC_3K_E825:
+		ice_ptp_reset_ts_memory_eth56g(hw);
+		break;
+	case ICE_MAC_E810:
 	default:
 		return;
 	}
@@ -5961,13 +5957,13 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	/* Clear event err indications for auxiliary pins */
 	(void)rd32(hw, GLTSYN_STAT(src_idx));
 
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_ptp_init_phc_eth56g(hw);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_ptp_init_phc_e810(hw);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_ptp_init_phc_e82x(hw);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_phc_eth56g(hw);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -5986,16 +5982,16 @@ int ice_ptp_init_phc(struct ice_hw *hw)
  */
 int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 {
-	switch (ice_get_phy_model(hw)) {
-	case ICE_PHY_ETH56G:
-		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
-							  tstamp_ready);
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_get_phy_tx_tstamp_ready_e82x(hw, block,
 							tstamp_ready);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
+							  tstamp_ready);
 		break;
 	default:
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 15f048d9b5823..6b46794075584 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -430,13 +430,13 @@ int ice_phy_cfg_ptp_1step_eth56g(struct ice_hw *hw, u8 port);
  */
 static inline u64 ice_get_base_incval(struct ice_hw *hw)
 {
-	switch (hw->ptp.phy_model) {
-	case ICE_PHY_ETH56G:
-		return ICE_ETH56G_NOMINAL_INCVAL;
-	case ICE_PHY_E810:
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
 		return ICE_PTP_NOMINAL_INCVAL_E810;
-	case ICE_PHY_E82X:
+	case ICE_MAC_GENERIC:
 		return ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
+	case ICE_MAC_GENERIC_3K_E825:
+		return ICE_ETH56G_NOMINAL_INCVAL;
 	default:
 		return 0;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h
index 33a1a5934c0d5..0aab21113cc43 100644
--- a/drivers/net/ethernet/intel/ice/ice_type.h
+++ b/drivers/net/ethernet/intel/ice/ice_type.h
@@ -871,14 +871,6 @@ union ice_phy_params {
 	struct ice_eth56g_params eth56g;
 };
 
-/* PHY model */
-enum ice_phy_model {
-	ICE_PHY_UNSUP = -1,
-	ICE_PHY_E810 = 1,
-	ICE_PHY_E82X,
-	ICE_PHY_ETH56G,
-};
-
 /* Global Link Topology */
 enum ice_global_link_topo {
 	ICE_LINK_TOPO_UP_TO_2_LINKS,
@@ -888,7 +880,6 @@ enum ice_global_link_topo {
 };
 
 struct ice_ptp_hw {
-	enum ice_phy_model phy_model;
 	union ice_phy_params phy;
 	u8 num_lports;
 	u8 ports_per_phy;

From ea7029fe10f46fd1ec0367b1b86bc744f9d9b34f Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 30 Sep 2024 14:12:40 +0200
Subject: [PATCH 0301/2753] ice: Use FIELD_PREP for timestamp values

Instead of using shifts and casts, use FIELD_PREP after reading 40b
timestamp values.

Rename a couple defines for better clarity and consistency.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 11 ++++++-----
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h |  9 +++++----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 8475d422f1ec4..a2a666e6df863 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -1576,9 +1576,8 @@ static int ice_read_ptp_tstamp_eth56g(struct ice_hw *hw, u8 port, u8 idx,
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) |
-		  FIELD_PREP(TS_PHY_LOW_M, lo);
-
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 	return 0;
 }
 
@@ -3213,7 +3212,8 @@ ice_read_phy_tstamp_e82x(struct ice_hw *hw, u8 quad, u8 idx, u64 *tstamp)
 	 * lower 8 bits in the low register, and the upper 32 bits in the high
 	 * register.
 	 */
-	*tstamp = FIELD_PREP(TS_PHY_HIGH_M, hi) | FIELD_PREP(TS_PHY_LOW_M, lo);
+	*tstamp = FIELD_PREP(PHY_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_40B_LOW_M, lo);
 
 	return 0;
 }
@@ -4979,7 +4979,8 @@ ice_read_phy_tstamp_e810(struct ice_hw *hw, u8 lport, u8 idx, u64 *tstamp)
 	/* For E810 devices, the timestamp is reported with the lower 32 bits
 	 * in the low register, and the upper 8 bits in the high register.
 	 */
-	*tstamp = ((u64)hi) << TS_HIGH_S | ((u64)lo & TS_LOW_M);
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 6b46794075584..4381ef4a6c771 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -652,15 +652,16 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 /* Source timer incval macros */
 #define INCVAL_HIGH_M			0xFF
 
-/* Timestamp block macros */
+/* PHY 40b registers macros */
+#define PHY_EXT_40B_LOW_M		GENMASK(31, 0)
+#define PHY_EXT_40B_HIGH_M		GENMASK_ULL(39, 32)
+#define PHY_40B_LOW_M			GENMASK(7, 0)
+#define PHY_40B_HIGH_M			GENMASK_ULL(39, 8)
 #define TS_VALID			BIT(0)
 #define TS_LOW_M			0xFFFFFFFF
 #define TS_HIGH_M			0xFF
 #define TS_HIGH_S			32
 
-#define TS_PHY_LOW_M			GENMASK(7, 0)
-#define TS_PHY_HIGH_M			GENMASK_ULL(39, 8)
-
 #define BYTES_PER_IDX_ADDR_L_U		8
 #define BYTES_PER_IDX_ADDR_L		4
 

From f9472aaabd1f38954938838a1146db4855ad88e8 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 30 Sep 2024 14:12:41 +0200
Subject: [PATCH 0302/2753] ice: Process TSYN IRQ in a separate function

Simplify TSYN IRQ processing by moving it to a separate function and
having appropriate behavior per PHY model, instead of multiple
conditions not related to HW, but to specific timestamping modes.

When PTP is not enabled in the kernel, don't process timestamps and
return IRQ_HANDLED.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 18 +--------
 drivers/net/ethernet/intel/ice/ice_ptp.c  | 49 +++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_ptp.h  |  6 +++
 3 files changed, 57 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index d7037de29545f..c402ab9f34569 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3304,22 +3304,8 @@ static irqreturn_t ice_misc_intr(int __always_unused irq, void *data)
 
 	if (oicr & PFINT_OICR_TSYN_TX_M) {
 		ena_mask &= ~PFINT_OICR_TSYN_TX_M;
-		if (ice_pf_state_is_nominal(pf) &&
-		    pf->hw.dev_caps.ts_dev_info.ts_ll_int_read) {
-			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
-			unsigned long flags;
-			u8 idx;
-
-			spin_lock_irqsave(&tx->lock, flags);
-			idx = find_next_bit_wrap(tx->in_use, tx->len,
-						 tx->last_ll_ts_idx_read + 1);
-			if (idx != tx->len)
-				ice_ptp_req_tx_single_tstamp(tx, idx);
-			spin_unlock_irqrestore(&tx->lock, flags);
-		} else if (ice_ptp_pf_handles_tx_interrupt(pf)) {
-			set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
-			ret = IRQ_WAKE_THREAD;
-		}
+
+		ret = ice_ptp_ts_irq(pf);
 	}
 
 	if (oicr & PFINT_OICR_TSYN_EVNT_M) {
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 7bb4005a67f63..698f906e2e591 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2763,6 +2763,55 @@ enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf)
 	}
 }
 
+/**
+ * ice_ptp_ts_irq - Process the PTP Tx timestamps in IRQ context
+ * @pf: Board private structure
+ *
+ * Return: IRQ_WAKE_THREAD if Tx timestamp read has to be handled in the bottom
+ *         half of the interrupt and IRQ_HANDLED otherwise.
+ */
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	struct ice_hw *hw = &pf->hw;
+
+	switch (hw->mac_type) {
+	case ICE_MAC_E810:
+		/* E810 capable of low latency timestamping with interrupt can
+		 * request a single timestamp in the top half and wait for
+		 * a second LL TS interrupt from the FW when it's ready.
+		 */
+		if (hw->dev_caps.ts_dev_info.ts_ll_int_read) {
+			struct ice_ptp_tx *tx = &pf->ptp.port.tx;
+			u8 idx;
+
+			if (!ice_pf_state_is_nominal(pf))
+				return IRQ_HANDLED;
+
+			spin_lock(&tx->lock);
+			idx = find_next_bit_wrap(tx->in_use, tx->len,
+						 tx->last_ll_ts_idx_read + 1);
+			if (idx != tx->len)
+				ice_ptp_req_tx_single_tstamp(tx, idx);
+			spin_unlock(&tx->lock);
+
+			return IRQ_HANDLED;
+		}
+		fallthrough; /* non-LL_TS E810 */
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		/* All other devices process timestamps in the bottom half due
+		 * to sleeping or polling.
+		 */
+		if (!ice_ptp_pf_handles_tx_interrupt(pf))
+			return IRQ_HANDLED;
+
+		set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
+		return IRQ_WAKE_THREAD;
+	default:
+		return IRQ_HANDLED;
+	}
+}
+
 /**
  * ice_ptp_maybe_trigger_tx_interrupt - Trigger Tx timstamp interrupt
  * @pf: Board private structure
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index a1d0e988c084b..a3b27f7162825 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -304,6 +304,7 @@ s8 ice_ptp_request_ts(struct ice_ptp_tx *tx, struct sk_buff *skb);
 void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx);
 void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
+irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf);
 
 u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 			const struct ice_pkt_ctx *pkt_ctx);
@@ -342,6 +343,11 @@ static inline bool ice_ptp_process_ts(struct ice_pf *pf)
 	return true;
 }
 
+static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
+{
+	return IRQ_HANDLED;
+}
+
 static inline u64
 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 		    const struct ice_pkt_ctx *pkt_ctx)

From 92456e795ac6c3371750edce8d6a1979cece5c99 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 30 Sep 2024 14:12:42 +0200
Subject: [PATCH 0303/2753] ice: Add unified ice_capture_crosststamp

Devices supported by ice driver use essentially the same logic for
performing a crosstimestamp. The only difference is that E830 hardware
has different offsets. Instead of having multiple implementations,
combine them into a single ice_capture_crosststamp() function.

To support both hardware types, the ice_capture_crosststamp function
must be able to determine the appropriate registers to access. To handle
this, pass a custom context structure instead of the PF pointer. This
structure, ice_crosststamp_ctx, contains a pointer to the PF, and
a pointer to the device configuration structure. This new structure also
will make it easier to implement historic snapshot support in a future
commit.

The device configuration structure is a static const data which defines
the offsets and flags for the various registers. This includes the lock
register, the cross timestamp control register, the upper and lower ART
system time capture registers, and the upper and lower device time
capture registers for each timer index.

Use the configuration structure to access all of the registers in
ice_capture_crosststamp(). Ensure that we don't over-run the device time
array by checking that the timer index is 0 or 1. Previously this was
simply assumed, and it would cause the device to read an incorrect and
likely garbage register.

It does feel like there should be a kernel interface for managing
register offsets like this, but the closest thing I saw was
<linux/regmap.h> which is interesting but not quite what we're looking
for...

Use rd32_poll_timeout() to read lock_reg and ctl_reg.

Add snapshot system time for historic interpolation.

Remove X86_FEATURE_ART and X86_FEATURE_TSC_KNOWN_FREQ from all E82X
devices because those are SoCs, which will always have those features.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 204 ++++++++++++++---------
 1 file changed, 129 insertions(+), 75 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 698f906e2e591..6e1801285a5d6 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -2179,93 +2179,142 @@ static int ice_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
 	return 0;
 }
 
-#ifdef CONFIG_ICE_HWTS
 /**
- * ice_ptp_get_syncdevicetime - Get the cross time stamp info
+ * struct ice_crosststamp_cfg - Device cross timestamp configuration
+ * @lock_reg: The hardware semaphore lock to use
+ * @lock_busy: Bit in the semaphore lock indicating the lock is busy
+ * @ctl_reg: The hardware register to request cross timestamp
+ * @ctl_active: Bit in the control register to request cross timestamp
+ * @art_time_l: Lower 32-bits of ART system time
+ * @art_time_h: Upper 32-bits of ART system time
+ * @dev_time_l: Lower 32-bits of device time (per timer index)
+ * @dev_time_h: Upper 32-bits of device time (per timer index)
+ */
+struct ice_crosststamp_cfg {
+	/* HW semaphore lock register */
+	u32 lock_reg;
+	u32 lock_busy;
+
+	/* Capture control register */
+	u32 ctl_reg;
+	u32 ctl_active;
+
+	/* Time storage */
+	u32 art_time_l;
+	u32 art_time_h;
+	u32 dev_time_l[2];
+	u32 dev_time_h[2];
+};
+
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = {
+	.lock_reg = PFHH_SEM,
+	.lock_busy = PFHH_SEM_BUSY_M,
+	.ctl_reg = GLHH_ART_CTL,
+	.ctl_active = GLHH_ART_CTL_ACTIVE_M,
+	.art_time_l = GLHH_ART_TIME_L,
+	.art_time_h = GLHH_ART_TIME_H,
+	.dev_time_l[0] = GLTSYN_HHTIME_L(0),
+	.dev_time_h[0] = GLTSYN_HHTIME_H(0),
+	.dev_time_l[1] = GLTSYN_HHTIME_L(1),
+	.dev_time_h[1] = GLTSYN_HHTIME_H(1),
+};
+
+/**
+ * struct ice_crosststamp_ctx - Device cross timestamp context
+ * @snapshot: snapshot of system clocks for historic interpolation
+ * @pf: pointer to the PF private structure
+ * @cfg: pointer to hardware configuration for cross timestamp
+ */
+struct ice_crosststamp_ctx {
+	struct system_time_snapshot snapshot;
+	struct ice_pf *pf;
+	const struct ice_crosststamp_cfg *cfg;
+};
+
+/**
+ * ice_capture_crosststamp - Capture a device/system cross timestamp
  * @device: Current device time
  * @system: System counter value read synchronously with device time
- * @ctx: Context provided by timekeeping code
+ * @__ctx: Context passed from ice_ptp_getcrosststamp
  *
  * Read device and system (ART) clock simultaneously and return the corrected
  * clock values in ns.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_get_syncdevicetime(ktime_t *device,
-			   struct system_counterval_t *system,
-			   void *ctx)
+static int ice_capture_crosststamp(ktime_t *device,
+				   struct system_counterval_t *system,
+				   void *__ctx)
 {
-	struct ice_pf *pf = (struct ice_pf *)ctx;
-	struct ice_hw *hw = &pf->hw;
-	u32 hh_lock, hh_art_ctl;
-	int i;
+	struct ice_crosststamp_ctx *ctx = __ctx;
+	const struct ice_crosststamp_cfg *cfg;
+	u32 lock, ctl, ts_lo, ts_hi, tmr_idx;
+	struct ice_pf *pf;
+	struct ice_hw *hw;
+	int err;
+	u64 ts;
 
-#define MAX_HH_HW_LOCK_TRIES	5
-#define MAX_HH_CTL_LOCK_TRIES	100
+	cfg = ctx->cfg;
+	pf = ctx->pf;
+	hw = &pf->hw;
 
-	for (i = 0; i < MAX_HH_HW_LOCK_TRIES; i++) {
-		/* Get the HW lock */
-		hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-		if (hh_lock & PFHH_SEM_BUSY_M) {
-			usleep_range(10000, 15000);
-			continue;
-		}
-		break;
-	}
-	if (hh_lock & PFHH_SEM_BUSY_M) {
-		dev_err(ice_pf_to_dev(pf), "PTP failed to get hh lock\n");
+	tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
+	if (tmr_idx > 1)
+		return -EINVAL;
+
+	/* Poll until we obtain the cross-timestamp hardware semaphore */
+	err = rd32_poll_timeout(hw, cfg->lock_reg, lock,
+				!(lock & cfg->lock_busy),
+				10 * USEC_PER_MSEC, 50 * USEC_PER_MSEC);
+	if (err) {
+		dev_err(ice_pf_to_dev(pf), "PTP failed to get cross timestamp lock\n");
 		return -EBUSY;
 	}
 
+	/* Snapshot system time for historic interpolation */
+	ktime_get_snapshot(&ctx->snapshot);
+
 	/* Program cmd to master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_READ_TIME);
 
 	/* Start the ART and device clock sync sequence */
-	hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-	hh_art_ctl = hh_art_ctl | GLHH_ART_CTL_ACTIVE_M;
-	wr32(hw, GLHH_ART_CTL, hh_art_ctl);
-
-	for (i = 0; i < MAX_HH_CTL_LOCK_TRIES; i++) {
-		/* Wait for sync to complete */
-		hh_art_ctl = rd32(hw, GLHH_ART_CTL);
-		if (hh_art_ctl & GLHH_ART_CTL_ACTIVE_M) {
-			udelay(1);
-			continue;
-		} else {
-			u32 hh_ts_lo, hh_ts_hi, tmr_idx;
-			u64 hh_ts;
-
-			tmr_idx = hw->func_caps.ts_func_info.tmr_index_assoc;
-			/* Read ART time */
-			hh_ts_lo = rd32(hw, GLHH_ART_TIME_L);
-			hh_ts_hi = rd32(hw, GLHH_ART_TIME_H);
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			system->cycles = hh_ts;
-			system->cs_id = CSID_X86_ART;
-			/* Read Device source clock time */
-			hh_ts_lo = rd32(hw, GLTSYN_HHTIME_L(tmr_idx));
-			hh_ts_hi = rd32(hw, GLTSYN_HHTIME_H(tmr_idx));
-			hh_ts = ((u64)hh_ts_hi << 32) | hh_ts_lo;
-			*device = ns_to_ktime(hh_ts);
-			break;
-		}
-	}
+	ctl = rd32(hw, cfg->ctl_reg);
+	ctl |= cfg->ctl_active;
+	wr32(hw, cfg->ctl_reg, ctl);
 
+	/* Poll until hardware completes the capture */
+	err = rd32_poll_timeout(hw, cfg->ctl_reg, ctl, !(ctl & cfg->ctl_active),
+				5, 20 * USEC_PER_MSEC);
+	if (err)
+		goto err_timeout;
+
+	/* Read ART system time */
+	ts_lo = rd32(hw, cfg->art_time_l);
+	ts_hi = rd32(hw, cfg->art_time_h);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	system->cycles = ts;
+	system->cs_id = CSID_X86_ART;
+
+	/* Read Device source clock time */
+	ts_lo = rd32(hw, cfg->dev_time_l[tmr_idx]);
+	ts_hi = rd32(hw, cfg->dev_time_h[tmr_idx]);
+	ts = ((u64)ts_hi << 32) | ts_lo;
+	*device = ns_to_ktime(ts);
+
+err_timeout:
 	/* Clear the master timer */
 	ice_ptp_src_cmd(hw, ICE_PTP_NOP);
 
 	/* Release HW lock */
-	hh_lock = rd32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id));
-	hh_lock = hh_lock & ~PFHH_SEM_BUSY_M;
-	wr32(hw, PFHH_SEM + (PFTSYN_SEM_BYTES * hw->pf_id), hh_lock);
-
-	if (i == MAX_HH_CTL_LOCK_TRIES)
-		return -ETIMEDOUT;
+	lock = rd32(hw, cfg->lock_reg);
+	lock &= ~cfg->lock_busy;
+	wr32(hw, cfg->lock_reg, lock);
 
-	return 0;
+	return err;
 }
 
 /**
- * ice_ptp_getcrosststamp_e82x - Capture a device cross timestamp
+ * ice_ptp_getcrosststamp - Capture a device cross timestamp
  * @info: the driver's PTP info structure
  * @cts: The memory to fill the cross timestamp info
  *
@@ -2273,22 +2322,31 @@ ice_ptp_get_syncdevicetime(ktime_t *device,
  * clock. Fill the cross timestamp information and report it back to the
  * caller.
  *
- * This is only valid for E822 and E823 devices which have support for
- * generating the cross timestamp via PCIe PTM.
- *
  * In order to correctly correlate the ART timestamp back to the TSC time, the
  * CPU must have X86_FEATURE_TSC_KNOWN_FREQ.
+ *
+ * Return: zero on success, or a negative error code on failure.
  */
-static int
-ice_ptp_getcrosststamp_e82x(struct ptp_clock_info *info,
-			    struct system_device_crosststamp *cts)
+static int ice_ptp_getcrosststamp(struct ptp_clock_info *info,
+				  struct system_device_crosststamp *cts)
 {
 	struct ice_pf *pf = ptp_info_to_pf(info);
+	struct ice_crosststamp_ctx ctx = {
+		.pf = pf,
+	};
+
+	switch (pf->hw.mac_type) {
+	case ICE_MAC_GENERIC:
+	case ICE_MAC_GENERIC_3K_E825:
+		ctx.cfg = &ice_crosststamp_cfg_e82x;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
 
-	return get_device_system_crosststamp(ice_ptp_get_syncdevicetime,
-					     pf, NULL, cts);
+	return get_device_system_crosststamp(ice_capture_crosststamp, &ctx,
+					     &ctx.snapshot, cts);
 }
-#endif /* CONFIG_ICE_HWTS */
 
 /**
  * ice_ptp_get_ts_config - ioctl interface to read the timestamping config
@@ -2549,12 +2607,8 @@ static int ice_ptp_parse_sdp_entries(struct ice_pf *pf, __le16 *entries,
  */
 static void ice_ptp_set_funcs_e82x(struct ice_pf *pf)
 {
-#ifdef CONFIG_ICE_HWTS
-	if (boot_cpu_has(X86_FEATURE_ART) &&
-	    boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ))
-		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp_e82x;
+	pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
 
-#endif /* CONFIG_ICE_HWTS */
 	if (pf->hw.mac_type == ICE_MAC_GENERIC_3K_E825) {
 		pf->ptp.ice_pin_desc = ice_pin_desc_e825c;
 		pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e825c);

From 381d5779623aaa1266a3c33d2aec99f34312f0cb Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 30 Sep 2024 14:12:43 +0200
Subject: [PATCH 0304/2753] ice: Refactor ice_ptp_init_tx_*

Unify ice_ptp_init_tx_* functions for most of the MAC types except E82X.
This simplifies the code for the future use with new MAC types.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 56 ++++++++----------------
 drivers/net/ethernet/intel/ice/ice_ptp.h |  3 +-
 2 files changed, 20 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 6e1801285a5d6..79ec8727388b8 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -971,28 +971,6 @@ ice_ptp_release_tx_tracker(struct ice_pf *pf, struct ice_ptp_tx *tx)
 	tx->len = 0;
 }
 
-/**
- * ice_ptp_init_tx_eth56g - Initialize tracking for Tx timestamps
- * @pf: Board private structure
- * @tx: the Tx tracking structure to initialize
- * @port: the port this structure tracks
- *
- * Initialize the Tx timestamp tracker for this port. ETH56G PHYs
- * have independent memory blocks for all ports.
- *
- * Return: 0 for success, -ENOMEM when failed to allocate Tx tracker
- */
-static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
-				  u8 port)
-{
-	tx->block = port;
-	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_ETH56G;
-	tx->has_ready_bitmap = 1;
-
-	return ice_ptp_alloc_tx_tracker(tx);
-}
-
 /**
  * ice_ptp_init_tx_e82x - Initialize tracking for Tx timestamps
  * @pf: Board private structure
@@ -1003,9 +981,11 @@ static int ice_ptp_init_tx_eth56g(struct ice_pf *pf, struct ice_ptp_tx *tx,
  * the timestamp block is shared for all ports in the same quad. To avoid
  * ports using the same timestamp index, logically break the block of
  * registers into chunks based on the port number.
+ *
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
+static int ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx,
+				u8 port)
 {
 	tx->block = ICE_GET_QUAD_NUM(port);
 	tx->offset = (port % ICE_PORTS_PER_QUAD) * INDEX_PER_PORT_E82X;
@@ -1016,24 +996,27 @@ ice_ptp_init_tx_e82x(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 }
 
 /**
- * ice_ptp_init_tx_e810 - Initialize tracking for Tx timestamps
+ * ice_ptp_init_tx - Initialize tracking for Tx timestamps
  * @pf: Board private structure
  * @tx: the Tx tracking structure to initialize
+ * @port: the port this structure tracks
+ *
+ * Initialize the Tx timestamp tracker for this PF. For all PHYs except E82X,
+ * each port has its own block of timestamps, independent of the other ports.
  *
- * Initialize the Tx timestamp tracker for this PF. For E810 devices, each
- * port has its own block of timestamps, independent of the other ports.
+ * Return: 0 on success, -ENOMEM when out of memory
  */
-static int
-ice_ptp_init_tx_e810(struct ice_pf *pf, struct ice_ptp_tx *tx)
+static int ice_ptp_init_tx(struct ice_pf *pf, struct ice_ptp_tx *tx, u8 port)
 {
-	tx->block = pf->hw.port_info->lport;
+	tx->block = port;
 	tx->offset = 0;
-	tx->len = INDEX_PER_PORT_E810;
+	tx->len = INDEX_PER_PORT;
+
 	/* The E810 PHY does not provide a timestamp ready bitmap. Instead,
 	 * verify new timestamps against cached copy of the last read
 	 * timestamp.
 	 */
-	tx->has_ready_bitmap = 0;
+	tx->has_ready_bitmap = pf->hw.mac_type != ICE_MAC_E810;
 
 	return ice_ptp_alloc_tx_tracker(tx);
 }
@@ -3235,6 +3218,8 @@ static int ice_ptp_init_work(struct ice_pf *pf, struct ice_ptp *ptp)
  * ice_ptp_init_port - Initialize PTP port structure
  * @pf: Board private structure
  * @ptp_port: PTP port structure
+ *
+ * Return: 0 on success, -ENODEV on invalid MAC type, -ENOMEM on failed alloc.
  */
 static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 {
@@ -3244,16 +3229,13 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
-		return ice_ptp_init_tx_e810(pf, &ptp_port->tx);
+	case ICE_MAC_GENERIC_3K_E825:
+		return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num);
 	case ICE_MAC_GENERIC:
 		kthread_init_delayed_work(&ptp_port->ov_work,
 					  ice_ptp_wait_for_offsets);
-
 		return ice_ptp_init_tx_e82x(pf, &ptp_port->tx,
 					    ptp_port->port_num);
-	case ICE_MAC_GENERIC_3K_E825:
-		return ice_ptp_init_tx_eth56g(pf, &ptp_port->tx,
-					      ptp_port->port_num);
 	default:
 		return -ENODEV;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index a3b27f7162825..783139de7f741 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -128,8 +128,7 @@ struct ice_ptp_tx {
 /* Quad and port information for initializing timestamp blocks */
 #define INDEX_PER_QUAD			64
 #define INDEX_PER_PORT_E82X		16
-#define INDEX_PER_PORT_E810		64
-#define INDEX_PER_PORT_ETH56G		64
+#define INDEX_PER_PORT			64
 
 /**
  * struct ice_ptp_port - data used to initialize an external port for PTP

From f003075227864344c14f53302c28acd0174d9225 Mon Sep 17 00:00:00 2001
From: Michal Michalik <michal.michalik@intel.com>
Date: Mon, 30 Sep 2024 14:12:44 +0200
Subject: [PATCH 0305/2753] ice: Implement PTP support for E830 devices

Add specific functions and definitions for E830 devices to enable
PTP support.

E830 devices support direct write to GLTSYN_ registers without shadow
registers and 64 bit read of PHC time.

Enable PTM for E830 device, which is required for cross timestamp and
and dependency on PCIE_PTM for ICE_HWTS.

Check X86_FEATURE_ART for E830 as it may not be present in the CPU.

Cc: Anna-Maria Behnsen <anna-maria@linutronix.de>
Cc: Frederic Weisbecker <frederic@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Co-developed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Co-developed-by: Milena Olech <milena.olech@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Co-developed-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Signed-off-by: Michal Michalik <michal.michalik@intel.com>
Co-developed-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Tested-by: Pucha Himasekhar Reddy <himasekharx.reddy.pucha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/Kconfig            |   2 +-
 .../net/ethernet/intel/ice/ice_hw_autogen.h   |  12 ++
 drivers/net/ethernet/intel/ice/ice_main.c     |   9 +-
 drivers/net/ethernet/intel/ice/ice_ptp.c      |  71 +++++++-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   | 167 +++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h   |   8 +
 6 files changed, 262 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 24ec9a4f1ffa8..26b9938bc38d6 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -336,7 +336,7 @@ config ICE_SWITCHDEV
 config ICE_HWTS
 	bool "Support HW cross-timestamp on platforms with PTM support"
 	default y
-	depends on ICE && X86
+	depends on ICE && X86 && PCIE_PTM
 	help
 	  Say Y to enable hardware supported cross-timestamping on platforms
 	  with PCIe PTM support. The cross-timestamp is available through
diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
index dc88aea9f4731..aa4bfbcf85d28 100644
--- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
+++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h
@@ -541,10 +541,22 @@
 #define PFPM_WUS_MAG_M				BIT(1)
 #define PFPM_WUS_MNG_M				BIT(3)
 #define PFPM_WUS_FW_RST_WK_M			BIT(31)
+#define E830_PRTMAC_TS_TX_MEM_VALID_H		0x001E2020
+#define E830_PRTMAC_TS_TX_MEM_VALID_L		0x001E2000
 #define E830_PRTMAC_CL01_PS_QNT			0x001E32A0
 #define E830_PRTMAC_CL01_PS_QNT_CL0_M		GENMASK(15, 0)
 #define E830_PRTMAC_CL01_QNT_THR		0x001E3320
 #define E830_PRTMAC_CL01_QNT_THR_CL0_M		GENMASK(15, 0)
+#define E830_PRTTSYN_TXTIME_H(_i)		(0x001E5800 + ((_i) * 32))
+#define E830_PRTTSYN_TXTIME_L(_i)		(0x001E5000 + ((_i) * 32))
+#define E830_GLPTM_ART_CTL			0x00088B50
+#define E830_GLPTM_ART_CTL_ACTIVE_M		BIT(0)
+#define E830_GLPTM_ART_TIME_H			0x00088B54
+#define E830_GLPTM_ART_TIME_L			0x00088B58
+#define E830_GLTSYN_PTMTIME_H(_i)		(0x00088B48 + ((_i) * 4))
+#define E830_GLTSYN_PTMTIME_L(_i)		(0x00088B40 + ((_i) * 4))
+#define E830_PFPTM_SEM				0x00088B00
+#define E830_PFPTM_SEM_BUSY_M			BIT(0)
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))
 #define VFINT_DYN_CTLN_CLEARPBA_M		BIT(1)
 #define E830_MBX_PF_IN_FLIGHT_VF_MSGS_THRESH	0x00234000
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c402ab9f34569..b084839eb8113 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -4052,8 +4052,7 @@ static void ice_set_pf_caps(struct ice_pf *pf)
 	}
 
 	clear_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
-	if (func_caps->common_cap.ieee_1588 &&
-	    !(pf->hw.mac_type == ICE_MAC_E830))
+	if (func_caps->common_cap.ieee_1588)
 		set_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags);
 
 	pf->max_pf_txqs = func_caps->common_cap.num_txq;
@@ -5073,6 +5072,12 @@ static int ice_init(struct ice_pf *pf)
 	if (err)
 		return err;
 
+	if (pf->hw.mac_type == ICE_MAC_E830) {
+		err = pci_enable_ptm(pf->pdev, NULL);
+		if (err)
+			dev_dbg(ice_pf_to_dev(pf), "PCIe PTM not supported by PCIe bus/controller\n");
+	}
+
 	err = ice_alloc_vsis(pf);
 	if (err)
 		goto err_alloc_vsis;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 79ec8727388b8..b65114ff487b1 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -310,6 +310,15 @@ ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
 	/* Read the system timestamp pre PHC read */
 	ptp_read_system_prets(sts);
 
+	if (hw->mac_type == ICE_MAC_E830) {
+		u64 clk_time = rd64(hw, E830_GLTSYN_TIME_L(tmr_idx));
+
+		/* Read the system timestamp post PHC read */
+		ptp_read_system_postts(sts);
+
+		return clk_time;
+	}
+
 	lo = rd32(hw, GLTSYN_TIME_L(tmr_idx));
 
 	/* Read the system timestamp post PHC read */
@@ -1305,6 +1314,7 @@ ice_ptp_port_phy_stop(struct ice_ptp_port *ptp_port)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		err = 0;
 		break;
 	case ICE_MAC_GENERIC:
@@ -1351,6 +1361,7 @@ ice_ptp_port_phy_restart(struct ice_ptp_port *ptp_port)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		err = 0;
 		break;
 	case ICE_MAC_GENERIC:
@@ -1418,7 +1429,8 @@ void ice_ptp_link_change(struct ice_pf *pf, bool linkup)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
-		/* Do not reconfigure E810 PHY */
+	case ICE_MAC_E830:
+		/* Do not reconfigure E810 or E830 PHY */
 		return;
 	case ICE_MAC_GENERIC:
 	case ICE_MAC_GENERIC_3K_E825:
@@ -1451,6 +1463,7 @@ static int ice_ptp_cfg_phy_interrupt(struct ice_pf *pf, bool ena, u32 threshold)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return 0;
 	case ICE_MAC_GENERIC: {
 		int quad;
@@ -2202,6 +2215,21 @@ static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e82x = {
 	.dev_time_h[1] = GLTSYN_HHTIME_H(1),
 };
 
+#ifdef CONFIG_ICE_HWTS
+static const struct ice_crosststamp_cfg ice_crosststamp_cfg_e830 = {
+	.lock_reg = E830_PFPTM_SEM,
+	.lock_busy = E830_PFPTM_SEM_BUSY_M,
+	.ctl_reg = E830_GLPTM_ART_CTL,
+	.ctl_active = E830_GLPTM_ART_CTL_ACTIVE_M,
+	.art_time_l = E830_GLPTM_ART_TIME_L,
+	.art_time_h = E830_GLPTM_ART_TIME_H,
+	.dev_time_l[0] = E830_GLTSYN_PTMTIME_L(0),
+	.dev_time_h[0] = E830_GLTSYN_PTMTIME_H(0),
+	.dev_time_l[1] = E830_GLTSYN_PTMTIME_L(1),
+	.dev_time_h[1] = E830_GLTSYN_PTMTIME_H(1),
+};
+
+#endif /* CONFIG_ICE_HWTS */
 /**
  * struct ice_crosststamp_ctx - Device cross timestamp context
  * @snapshot: snapshot of system clocks for historic interpolation
@@ -2323,6 +2351,11 @@ static int ice_ptp_getcrosststamp(struct ptp_clock_info *info,
 	case ICE_MAC_GENERIC_3K_E825:
 		ctx.cfg = &ice_crosststamp_cfg_e82x;
 		break;
+#ifdef CONFIG_ICE_HWTS
+	case ICE_MAC_E830:
+		ctx.cfg = &ice_crosststamp_cfg_e830;
+		break;
+#endif /* CONFIG_ICE_HWTS */
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2658,6 +2691,28 @@ static void ice_ptp_set_funcs_e810(struct ice_pf *pf)
 	}
 }
 
+/**
+ * ice_ptp_set_funcs_e830 - Set specialized functions for E830 support
+ * @pf: Board private structure
+ *
+ * Assign functions to the PTP capabiltiies structure for E830 devices.
+ * Functions which operate across all device families should be set directly
+ * in ice_ptp_set_caps. Only add functions here which are distinct for E830
+ * devices.
+ */
+static void ice_ptp_set_funcs_e830(struct ice_pf *pf)
+{
+#ifdef CONFIG_ICE_HWTS
+	if (pcie_ptm_enabled(pf->pdev) && boot_cpu_has(X86_FEATURE_ART))
+		pf->ptp.info.getcrosststamp = ice_ptp_getcrosststamp;
+
+#endif /* CONFIG_ICE_HWTS */
+	/* Rest of the config is the same as base E810 */
+	pf->ptp.ice_pin_desc = ice_pin_desc_e810;
+	pf->ptp.info.n_pins = ICE_PIN_DESC_ARR_LEN(ice_pin_desc_e810);
+	ice_ptp_setup_pin_cfg(pf);
+}
+
 /**
  * ice_ptp_set_caps - Set PTP capabilities
  * @pf: Board private structure
@@ -2684,6 +2739,9 @@ static void ice_ptp_set_caps(struct ice_pf *pf)
 	case ICE_MAC_E810:
 		ice_ptp_set_funcs_e810(pf);
 		return;
+	case ICE_MAC_E830:
+		ice_ptp_set_funcs_e830(pf);
+		return;
 	case ICE_MAC_GENERIC:
 	case ICE_MAC_GENERIC_3K_E825:
 		ice_ptp_set_funcs_e82x(pf);
@@ -2844,6 +2902,16 @@ irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
 
 		set_bit(ICE_MISC_THREAD_TX_TSTAMP, pf->misc_thread);
 		return IRQ_WAKE_THREAD;
+	case ICE_MAC_E830:
+		/* E830 can read timestamps in the top half using rd32() */
+		if (ice_ptp_process_ts(pf) == ICE_TX_TSTAMP_WORK_PENDING) {
+			/* Process outstanding Tx timestamps. If there
+			 * is more work, re-arm the interrupt to trigger again.
+			 */
+			wr32(hw, PFINT_OICR, PFINT_OICR_TSYN_TX_M);
+			ice_flush(hw);
+		}
+		return IRQ_HANDLED;
 	default:
 		return IRQ_HANDLED;
 	}
@@ -3229,6 +3297,7 @@ static int ice_ptp_init_port(struct ice_pf *pf, struct ice_ptp_port *ptp_port)
 
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 	case ICE_MAC_GENERIC_3K_E825:
 		return ice_ptp_init_tx(pf, &ptp_port->tx, ptp_port->port_num);
 	case ICE_MAC_GENERIC:
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index a2a666e6df863..3e824f7b30c00 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -829,6 +829,7 @@ static u32 ice_ptp_tmr_cmd_to_port_reg(struct ice_hw *hw,
 	 */
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ice_ptp_tmr_cmd_to_src_reg(hw, cmd) & TS_CMD_MASK_E810;
 	default:
 		break;
@@ -895,6 +896,17 @@ static void ice_ptp_exec_tmr_cmd(struct ice_hw *hw)
 	ice_flush(hw);
 }
 
+/**
+ * ice_ptp_cfg_sync_delay - Configure PHC to PHY synchronization delay
+ * @hw: pointer to HW struct
+ * @delay: delay between PHC and PHY SYNC command execution in nanoseconds
+ */
+static void ice_ptp_cfg_sync_delay(const struct ice_hw *hw, u32 delay)
+{
+	wr32(hw, GLTSYN_SYNC_DLAY, delay);
+	ice_flush(hw);
+}
+
 /* 56G PHY device functions
  *
  * The following functions operate on devices with the ETH 56G PHY.
@@ -5043,8 +5055,7 @@ static int ice_ptp_init_phc_e810(struct ice_hw *hw)
 	u8 tmr_idx;
 	int err;
 
-	/* Ensure synchronization delay is zero */
-	wr32(hw, GLTSYN_SYNC_DLAY, 0);
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 	err = ice_write_phy_reg_e810(hw, ETH_GLTSYN_ENA(tmr_idx),
@@ -5445,6 +5456,128 @@ static void ice_ptp_init_phy_e810(struct ice_ptp_hw *ptp)
 	init_waitqueue_head(&ptp->phy.e810.atqbal_wq);
 }
 
+/* E830 functions
+ *
+ * The following functions operate on the E830 series devices.
+ *
+ */
+
+/**
+ * ice_ptp_init_phc_e830 - Perform E830 specific PHC initialization
+ * @hw: pointer to HW struct
+ *
+ * Perform E830-specific PTP hardware clock initialization steps.
+ */
+static void ice_ptp_init_phc_e830(const struct ice_hw *hw)
+{
+	ice_ptp_cfg_sync_delay(hw, ICE_E810_E830_SYNC_DELAY);
+}
+
+/**
+ * ice_ptp_write_direct_incval_e830 - Prep PHY port increment value change
+ * @hw: pointer to HW struct
+ * @incval: The new 40bit increment value to prepare
+ *
+ * Prepare the PHY port for a new increment value by programming the PHC
+ * GLTSYN_INCVAL_L and GLTSYN_INCVAL_H registers. The actual change is
+ * completed by FW automatically.
+ */
+static void ice_ptp_write_direct_incval_e830(const struct ice_hw *hw,
+					     u64 incval)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_INCVAL_L(tmr_idx), lower_32_bits(incval));
+	wr32(hw, GLTSYN_INCVAL_H(tmr_idx), upper_32_bits(incval));
+}
+
+/**
+ * ice_ptp_write_direct_phc_time_e830 - Prepare PHY port with initial time
+ * @hw: Board private structure
+ * @time: Time to initialize the PHY port clock to
+ *
+ * Program the PHY port ETH_GLTSYN_SHTIME registers in preparation setting the
+ * initial clock time. The time will not actually be programmed until the
+ * driver issues an ICE_PTP_INIT_TIME command.
+ *
+ * The time value is the upper 32 bits of the PHY timer, usually in units of
+ * nominal nanoseconds.
+ */
+static void ice_ptp_write_direct_phc_time_e830(const struct ice_hw *hw,
+					       u64 time)
+{
+	u8 tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
+
+	wr32(hw, GLTSYN_TIME_0(tmr_idx), 0);
+	wr32(hw, GLTSYN_TIME_L(tmr_idx), lower_32_bits(time));
+	wr32(hw, GLTSYN_TIME_H(tmr_idx), upper_32_bits(time));
+}
+
+/**
+ * ice_ptp_port_cmd_e830 - Prepare all external PHYs for a timer command
+ * @hw: pointer to HW struct
+ * @cmd: Command to be sent to the port
+ *
+ * Prepare the external PHYs connected to this device for a timer sync
+ * command.
+ *
+ * Return: 0 on success, negative error code when PHY write failed
+ */
+static int ice_ptp_port_cmd_e830(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
+{
+	u32 val = ice_ptp_tmr_cmd_to_port_reg(hw, cmd);
+
+	return ice_write_phy_reg_e810(hw, E830_ETH_GLTSYN_CMD, val);
+}
+
+/**
+ * ice_read_phy_tstamp_e830 - Read a PHY timestamp out of the external PHY
+ * @hw: pointer to the HW struct
+ * @idx: the timestamp index to read
+ * @tstamp: on return, the 40bit timestamp value
+ *
+ * Read a 40bit timestamp value out of the timestamp block of the external PHY
+ * on the E830 device.
+ */
+static void ice_read_phy_tstamp_e830(const struct ice_hw *hw, u8 idx,
+				     u64 *tstamp)
+{
+	u32 hi, lo;
+
+	hi = rd32(hw, E830_PRTTSYN_TXTIME_H(idx));
+	lo = rd32(hw, E830_PRTTSYN_TXTIME_L(idx));
+
+	/* For E830 devices, the timestamp is reported with the lower 32 bits
+	 * in the low register, and the upper 8 bits in the high register.
+	 */
+	*tstamp = FIELD_PREP(PHY_EXT_40B_HIGH_M, hi) |
+		  FIELD_PREP(PHY_EXT_40B_LOW_M, lo);
+}
+
+/**
+ * ice_get_phy_tx_tstamp_ready_e830 - Read Tx memory status register
+ * @hw: pointer to the HW struct
+ * @port: the PHY port to read
+ * @tstamp_ready: contents of the Tx memory status register
+ */
+static void ice_get_phy_tx_tstamp_ready_e830(const struct ice_hw *hw, u8 port,
+					     u64 *tstamp_ready)
+{
+	*tstamp_ready = rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_H);
+	*tstamp_ready <<= 32;
+	*tstamp_ready |= rd32(hw, E830_PRTMAC_TS_TX_MEM_VALID_L);
+}
+
+/**
+ * ice_ptp_init_phy_e830 - initialize PHY parameters
+ * @ptp: pointer to the PTP HW struct
+ */
+static void ice_ptp_init_phy_e830(struct ice_ptp_hw *ptp)
+{
+	ptp->num_lports = 8;
+	ptp->ports_per_phy = 4;
+}
+
 /* Device agnostic functions
  *
  * The following functions implement shared behavior common to all devices,
@@ -5515,6 +5648,9 @@ void ice_ptp_init_hw(struct ice_hw *hw)
 	case ICE_MAC_E810:
 		ice_ptp_init_phy_e810(ptp);
 		break;
+	case ICE_MAC_E830:
+		ice_ptp_init_phy_e830(ptp);
+		break;
 	case ICE_MAC_GENERIC:
 		ice_ptp_init_phy_e82x(ptp);
 		break;
@@ -5612,6 +5748,8 @@ static int ice_ptp_port_cmd(struct ice_hw *hw, enum ice_ptp_tmr_cmd cmd)
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
 		return ice_ptp_port_cmd_e810(hw, cmd);
+	case ICE_MAC_E830:
+		return ice_ptp_port_cmd_e830(hw, cmd);
 	default:
 		break;
 	}
@@ -5682,6 +5820,12 @@ int ice_ptp_init_time(struct ice_hw *hw, u64 time)
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
 	/* Source timers */
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_phc_time_e830(hw, time);
+		return 0;
+	}
+
 	wr32(hw, GLTSYN_SHTIME_L(tmr_idx), lower_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_H(tmr_idx), upper_32_bits(time));
 	wr32(hw, GLTSYN_SHTIME_0(tmr_idx), 0);
@@ -5730,6 +5874,12 @@ int ice_ptp_write_incval(struct ice_hw *hw, u64 incval)
 
 	tmr_idx = hw->func_caps.ts_func_info.tmr_index_owned;
 
+	/* For E830 we don't need to use shadow registers, its automatic */
+	if (hw->mac_type == ICE_MAC_E830) {
+		ice_ptp_write_direct_incval_e830(hw, incval);
+		return 0;
+	}
+
 	/* Shadow Adjust */
 	wr32(hw, GLTSYN_SHADJ_L(tmr_idx), lower_32_bits(incval));
 	wr32(hw, GLTSYN_SHADJ_H(tmr_idx), upper_32_bits(incval));
@@ -5807,6 +5957,9 @@ int ice_ptp_adj_clock(struct ice_hw *hw, s32 adj)
 	case ICE_MAC_E810:
 		err = ice_ptp_prep_phy_adj_e810(hw, adj);
 		break;
+	case ICE_MAC_E830:
+		/* E830 sync PHYs automatically after setting GLTSYN_SHADJ */
+		return 0;
 	case ICE_MAC_GENERIC:
 		err = ice_ptp_prep_phy_adj_e82x(hw, adj);
 		break;
@@ -5839,6 +5992,9 @@ int ice_read_phy_tstamp(struct ice_hw *hw, u8 block, u8 idx, u64 *tstamp)
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
 		return ice_read_phy_tstamp_e810(hw, block, idx, tstamp);
+	case ICE_MAC_E830:
+		ice_read_phy_tstamp_e830(hw, idx, tstamp);
+		return 0;
 	case ICE_MAC_GENERIC:
 		return ice_read_phy_tstamp_e82x(hw, block, idx, tstamp);
 	case ICE_MAC_GENERIC_3K_E825:
@@ -5961,6 +6117,9 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
 		return ice_ptp_init_phc_e810(hw);
+	case ICE_MAC_E830:
+		ice_ptp_init_phc_e830(hw);
+		return 0;
 	case ICE_MAC_GENERIC:
 		return ice_ptp_init_phc_e82x(hw);
 	case ICE_MAC_GENERIC_3K_E825:
@@ -5987,13 +6146,15 @@ int ice_get_phy_tx_tstamp_ready(struct ice_hw *hw, u8 block, u64 *tstamp_ready)
 	case ICE_MAC_E810:
 		return ice_get_phy_tx_tstamp_ready_e810(hw, block,
 							tstamp_ready);
+	case ICE_MAC_E830:
+		ice_get_phy_tx_tstamp_ready_e830(hw, block, tstamp_ready);
+		return 0;
 	case ICE_MAC_GENERIC:
 		return ice_get_phy_tx_tstamp_ready_e82x(hw, block,
 							tstamp_ready);
 	case ICE_MAC_GENERIC_3K_E825:
 		return ice_get_phy_tx_tstamp_ready_eth56g(hw, block,
 							  tstamp_ready);
-		break;
 	default:
 		return -EOPNOTSUPP;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 4381ef4a6c771..8442d1d603517 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -324,6 +324,7 @@ extern const struct ice_vernier_info_e82x e822_vernier[NUM_ICE_PTP_LNK_SPD];
  */
 #define ICE_E810_PLL_FREQ		812500000
 #define ICE_PTP_NOMINAL_INCVAL_E810	0x13b13b13bULL
+#define ICE_E810_E830_SYNC_DELAY	0
 
 /* Device agnostic functions */
 u8 ice_get_ptp_src_clock_index(struct ice_hw *hw);
@@ -432,6 +433,7 @@ static inline u64 ice_get_base_incval(struct ice_hw *hw)
 {
 	switch (hw->mac_type) {
 	case ICE_MAC_E810:
+	case ICE_MAC_E830:
 		return ICE_PTP_NOMINAL_INCVAL_E810;
 	case ICE_MAC_GENERIC:
 		return ice_e82x_nominal_incval(ice_e82x_time_ref(hw));
@@ -649,6 +651,12 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 /* E810 timer command register */
 #define E810_ETH_GLTSYN_CMD		0x03000344
 
+/* E830 timer command register */
+#define E830_ETH_GLTSYN_CMD		0x00088814
+
+/* E810 PHC time register */
+#define E830_GLTSYN_TIME_L(_tmr_idx)	(0x0008A000 + 0x1000 * (_tmr_idx))
+
 /* Source timer incval macros */
 #define INCVAL_HIGH_M			0xFF
 

From 5a7b0b6ff49ba5148cfa87c2fbe39a2b22266b1f Mon Sep 17 00:00:00 2001
From: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Date: Fri, 17 Jan 2025 09:06:32 +0100
Subject: [PATCH 0306/2753] ice: refactor ice_fdir_create_dflt_rules() function

The Flow Director function ice_fdir_create_dflt_rules() calls few
times function ice_create_init_fdir_rule() each time with different
enum ice_fltr_ptype parameter. Next step is to return error code if
error occurred.

Change the code to store all necessary default rules in constant array
and call ice_create_init_fdir_rule() in the loop. It makes it easy to
extend the list of default rules in the future, without the need of
duplicate code more and more.

Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../net/ethernet/intel/ice/ice_ethtool_fdir.c | 21 ++++++++-----------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index ee9862ddfe15e..1d118171de378 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1605,22 +1605,19 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf)
  */
 int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 {
+	const enum ice_fltr_ptype dflt_rules[] = {
+		ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP,
+		ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP,
+	};
 	int err;
 
 	/* Create perfect TCP and UDP rules in hardware. */
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV4_UDP);
-	if (err)
-		return err;
+	for (int i = 0; i < ARRAY_SIZE(dflt_rules); i++) {
+		err = ice_create_init_fdir_rule(pf, dflt_rules[i]);
 
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_TCP);
-	if (err)
-		return err;
-
-	err = ice_create_init_fdir_rule(pf, ICE_FLTR_PTYPE_NONF_IPV6_UDP);
+		if (err)
+			break;
+	}
 
 	return err;
 }

From be324b790368c1522f07c6bb5654122e07b5e588 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Mon, 16 Dec 2024 15:38:49 +0800
Subject: [PATCH 0307/2753] igc: Avoid unnecessary link down event in
 XDP_SETUP_PROG process

The igc_close()/igc_open() functions are too drastic for installing a new
XDP prog because they cause undesirable link down event and device reset.

To avoid delays in Ethernet traffic, improve the XDP_SETUP_PROG process by
using the same sequence as igc_xdp_setup_pool(), which performs only the
necessary steps, as follows:
 1. stop the traffic and clean buffer
 2. stop NAPI
 3. install the XDP program
 4. resume NAPI
 5. allocate buffer and resume the traffic

This patch has been tested using the 'ip link set xdpdrv' command to attach
a simple XDP prog that always returns XDP_PASS.

Before this patch, attaching xdp program will cause ptp4l to lose sync for
few seconds, as shown in ptp4l log below:
  ptp4l[198.082]: rms    4 max    8 freq   +906 +/-   2 delay    12 +/-   0
  ptp4l[199.082]: rms    3 max    4 freq   +906 +/-   3 delay    12 +/-   0
  ptp4l[199.536]: port 1 (enp2s0): link down
  ptp4l[199.536]: port 1 (enp2s0): SLAVE to FAULTY on FAULT_DETECTED (FT_UNSPECIFIED)
  ptp4l[199.600]: selected local clock 22abbc.fffe.bb1234 as best master
  ptp4l[199.600]: port 1 (enp2s0): assuming the grand master role
  ptp4l[199.600]: port 1 (enp2s0): master state recommended in slave only mode
  ptp4l[199.600]: port 1 (enp2s0): defaultDS.priority1 probably misconfigured
  ptp4l[202.266]: port 1 (enp2s0): link up
  ptp4l[202.300]: port 1 (enp2s0): FAULTY to LISTENING on INIT_COMPLETE
  ptp4l[205.558]: port 1 (enp2s0): new foreign master 44abbc.fffe.bb2144-1
  ptp4l[207.558]: selected best master clock 44abbc.fffe.bb2144
  ptp4l[207.559]: port 1 (enp2s0): LISTENING to UNCALIBRATED on RS_SLAVE
  ptp4l[208.308]: port 1 (enp2s0): UNCALIBRATED to SLAVE on MASTER_CLOCK_SELECTED
  ptp4l[208.933]: rms  742 max 1303 freq   -195 +/- 682 delay    12 +/-   0
  ptp4l[209.933]: rms  178 max  274 freq   +387 +/- 243 delay    12 +/-   0

After this patch, attaching xdp program no longer cause ptp4l to lose sync,
as shown in ptp4l log below:
  ptp4l[201.183]: rms    1 max    3 freq   +959 +/-   1 delay     8 +/-   0
  ptp4l[202.183]: rms    1 max    3 freq   +961 +/-   2 delay     8 +/-   0
  ptp4l[203.183]: rms    2 max    3 freq   +958 +/-   2 delay     8 +/-   0
  ptp4l[204.183]: rms    3 max    5 freq   +961 +/-   3 delay     8 +/-   0
  ptp4l[205.183]: rms    2 max    4 freq   +964 +/-   3 delay     8 +/-   0

Besides, before this patch, attaching xdp program will causes flood ping to
lose 10 packets, as shown in ping statistics below:
  --- 169.254.1.2 ping statistics ---
  100000 packets transmitted, 99990 received, +6 errors, 0.01% packet loss, time 34001ms
  rtt min/avg/max/mdev = 0.028/0.301/3104.360/13.838 ms, pipe 10, ipg/ewma 0.340/0.243 ms

After this patch, attaching xdp program no longer cause flood ping to loss
any packets, as shown in ping statistics below:
  --- 169.254.1.2 ping statistics ---
  100000 packets transmitted, 100000 received, 0% packet loss, time 32326ms
  rtt min/avg/max/mdev = 0.027/0.231/19.589/0.155 ms, pipe 2, ipg/ewma 0.323/0.322 ms

On the other hand, this patch has been tested with tools/testing/selftests/
bpf/xdp_hw_metadata app to make sure AF_XDP zero-copy is working fine with
XDP Tx and Rx metadata. Below is the result of last packet after received
10000 UDP packets with interval 1 ms:
  poll: 1 (0) skip=0 fail=0 redir=10000
  xsk_ring_cons__peek: 1
  0x55881c7ef7a8: rx_desc[9999]->addr=8f110 addr=8f110 comp_addr=8f110 EoP
  rx_hash: 0xFB9BB6A3 with RSS type:0x1
  HW RX-time:   1733923136269470866 (sec:1733923136.2695) delta to User RX-time sec:0.0000 (43.280 usec)
  XDP RX-time:   1733923136269482482 (sec:1733923136.2695) delta to User RX-time sec:0.0000 (31.664 usec)
  No rx_vlan_tci or rx_vlan_proto, err=-95
  0x55881c7ef7a8: ping-pong with csum=ab19 (want 315b) csum_start=34 csum_offset=6
  0x55881c7ef7a8: complete tx idx=9999 addr=f010
  HW TX-complete-time:   1733923136269591637 (sec:1733923136.2696) delta to User TX-complete-time sec:0.0001 (108.571 usec)
  XDP RX-time:   1733923136269482482 (sec:1733923136.2695) delta to User TX-complete-time sec:0.0002 (217.726 usec)
  HW RX-time:   1733923136269470866 (sec:1733923136.2695) delta to HW TX-complete-time sec:0.0001 (120.771 usec)
  0x55881c7ef7a8: complete rx idx=10127 addr=8f110

Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/igc/igc_xdp.c | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_xdp.c b/drivers/net/ethernet/intel/igc/igc_xdp.c
index 13bbd3346e01f..c538e6b18aad5 100644
--- a/drivers/net/ethernet/intel/igc/igc_xdp.c
+++ b/drivers/net/ethernet/intel/igc/igc_xdp.c
@@ -14,6 +14,7 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	bool if_running = netif_running(dev);
 	struct bpf_prog *old_prog;
 	bool need_update;
+	unsigned int i;
 
 	if (dev->mtu > ETH_DATA_LEN) {
 		/* For now, the driver doesn't support XDP functionality with
@@ -24,8 +25,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	}
 
 	need_update = !!adapter->xdp_prog != !!prog;
-	if (if_running && need_update)
-		igc_close(dev);
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			igc_disable_rx_ring(adapter->rx_ring[i]);
+			igc_disable_tx_ring(adapter->tx_ring[i]);
+			napi_disable(&adapter->rx_ring[i]->q_vector->napi);
+		}
+	}
 
 	old_prog = xchg(&adapter->xdp_prog, prog);
 	if (old_prog)
@@ -36,8 +42,13 @@ int igc_xdp_set_prog(struct igc_adapter *adapter, struct bpf_prog *prog,
 	else
 		xdp_features_clear_redirect_target(dev);
 
-	if (if_running && need_update)
-		igc_open(dev);
+	if (if_running && need_update) {
+		for (i = 0; i < adapter->num_rx_queues; i++) {
+			napi_enable(&adapter->rx_ring[i]->q_vector->napi);
+			igc_enable_tx_ring(adapter->tx_ring[i]);
+			igc_enable_rx_ring(adapter->rx_ring[i]);
+		}
+	}
 
 	return 0;
 }

From 13e22972471d1639c16081e95b1caed9351ed3be Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <eg@keba.com>
Date: Thu, 19 Dec 2024 20:27:43 +0100
Subject: [PATCH 0308/2753] e1000e: Fix real-time violations on link up

Link down and up triggers update of MTA table. This update executes many
PCIe writes and a final flush. Thus, PCIe will be blocked until all
writes are flushed. As a result, DMA transfers of other targets suffer
from delay in the range of 50us. This results in timing violations on
real-time systems during link down and up of e1000e in combination with
an Intel i3-2310E Sandy Bridge CPU.

The i3-2310E is quite old. Launched 2011 by Intel but still in use as
robot controller. The exact root cause of the problem is unclear and
this situation won't change as Intel support for this CPU has ended
years ago. Our experience is that the number of posted PCIe writes needs
to be limited at least for real-time systems. With posted PCIe writes a
much higher throughput can be generated than with PCIe reads which
cannot be posted. Thus, the load on the interconnect is much higher.
Additionally, a PCIe read waits until all posted PCIe writes are done.
Therefore, the PCIe read can block the CPU for much more than 10us if a
lot of PCIe writes were posted before. Both issues are the reason why we
are limiting the number of posted PCIe writes in row in general for our
real-time systems, not only for this driver.

A flush after a low enough number of posted PCIe writes eliminates the
delay but also increases the time needed for MTA table update. The
following measurements were done on i3-2310E with e1000e for 128 MTA
table entries:

Single flush after all writes: 106us
Flush after every write:       429us
Flush after every 2nd write:   266us
Flush after every 4th write:   180us
Flush after every 8th write:   141us
Flush after every 16th write:  121us

A flush after every 8th write delays the link up by 35us and the
negative impact to DMA transfers of other targets is still tolerable.

Execute a flush after every 8th write. This prevents overloading the
interconnect with posted writes.

Signed-off-by: Gerhard Engleder <eg@keba.com>
Link: https://lore.kernel.org/netdev/f8fe665a-5e6c-4f95-b47a-2f3281aa0e6c@lunn.ch/T/
CC: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Avigail Dahan <avigailx.dahan@intel.com>
Reviewed-by: Vitaly Lifshits <vitaly.lifshits@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/e1000e/mac.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c
index d7df2a0ed6290..44249dd91bd67 100644
--- a/drivers/net/ethernet/intel/e1000e/mac.c
+++ b/drivers/net/ethernet/intel/e1000e/mac.c
@@ -331,8 +331,21 @@ void e1000e_update_mc_addr_list_generic(struct e1000_hw *hw,
 	}
 
 	/* replace the entire MTA table */
-	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--)
+	for (i = hw->mac.mta_reg_count - 1; i >= 0; i--) {
 		E1000_WRITE_REG_ARRAY(hw, E1000_MTA, i, hw->mac.mta_shadow[i]);
+
+		if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+			/*
+			 * Do not queue up too many posted writes to prevent
+			 * increased latency for other devices on the
+			 * interconnect. Flush after each 8th posted write,
+			 * to keep additional execution time low while still
+			 * preventing increased latency.
+			 */
+			if (!(i % 8) && i)
+				e1e_flush();
+		}
+	}
 	e1e_flush();
 }
 

From 5b281fe7e396c519914863c5de5ce3a3f9cffd5b Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 5 Feb 2025 11:38:46 +0100
Subject: [PATCH 0309/2753] net: phy: dp83td510: introduce LED framework
 support

Add LED brightness, mode, HW control and polarity functions to enable
external LED control in the TI DP83TD510 PHY.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250205103846.2273833-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83td510.c | 187 ++++++++++++++++++++++++++++++++++++
 1 file changed, 187 insertions(+)

diff --git a/drivers/net/phy/dp83td510.c b/drivers/net/phy/dp83td510.c
index a42af9c168ec5..23af1ac194fa9 100644
--- a/drivers/net/phy/dp83td510.c
+++ b/drivers/net/phy/dp83td510.c
@@ -204,10 +204,191 @@ struct dp83td510_priv {
 #define DP83TD510E_UNKN_030E				0x30e
 #define DP83TD510E_030E_VAL				0x2520
 
+#define DP83TD510E_LEDS_CFG_1				0x460
+#define DP83TD510E_LED_FN(idx, val)		(((val) & 0xf) << ((idx) * 4))
+#define DP83TD510E_LED_FN_MASK(idx)			(0xf << ((idx) * 4))
+/* link OK */
+#define DP83TD510E_LED_MODE_LINK_OK			0x0
+/* TX/RX activity */
+#define DP83TD510E_LED_MODE_TX_RX_ACTIVITY		0x1
+/* TX activity */
+#define DP83TD510E_LED_MODE_TX_ACTIVITY			0x2
+/* RX activity */
+#define DP83TD510E_LED_MODE_RX_ACTIVITY			0x3
+/* LR */
+#define DP83TD510E_LED_MODE_LR				0x4
+/* SR */
+#define DP83TD510E_LED_MODE_SR				0x5
+/* LED SPEED: High for 10Base-T */
+#define DP83TD510E_LED_MODE_LED_SPEED			0x6
+/* Duplex mode */
+#define DP83TD510E_LED_MODE_DUPLEX			0x7
+/* link + blink on activity with stretch option */
+#define DP83TD510E_LED_MODE_LINK_BLINK			0x8
+/* blink on activity with stretch option */
+#define DP83TD510E_LED_MODE_BLINK_ACTIVITY		0x9
+/* blink on tx activity with stretch option */
+#define DP83TD510E_LED_MODE_BLINK_TX			0xa
+/* blink on rx activity with stretch option */
+#define DP83TD510E_LED_MODE_BLINK_RX			0xb
+/* link_lost */
+#define DP83TD510E_LED_MODE_LINK_LOST			0xc
+/* PRBS error: toggles on error */
+#define DP83TD510E_LED_MODE_PRBS_ERROR			0xd
+/* XMII TX/RX Error with stretch option */
+#define DP83TD510E_LED_MODE_XMII_ERR			0xe
+
+#define DP83TD510E_LED_COUNT				4
+
+#define DP83TD510E_LEDS_CFG_2				0x469
+#define DP83TD510E_LED_POLARITY(idx)			BIT((idx) * 4 + 2)
+#define DP83TD510E_LED_DRV_VAL(idx)			BIT((idx) * 4 + 1)
+#define DP83TD510E_LED_DRV_EN(idx)			BIT((idx) * 4)
+
 #define DP83TD510E_ALCD_STAT				0xa9f
 #define DP83TD510E_ALCD_COMPLETE			BIT(15)
 #define DP83TD510E_ALCD_CABLE_LENGTH			GENMASK(10, 0)
 
+static int dp83td510_led_brightness_set(struct phy_device *phydev, u8 index,
+					enum led_brightness brightness)
+{
+	u32 val;
+
+	if (index >= DP83TD510E_LED_COUNT)
+		return -EINVAL;
+
+	val = DP83TD510E_LED_DRV_EN(index);
+
+	if (brightness)
+		val |= DP83TD510E_LED_DRV_VAL(index);
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_LEDS_CFG_2,
+			      DP83TD510E_LED_DRV_VAL(index) |
+			      DP83TD510E_LED_DRV_EN(index), val);
+}
+
+static int dp83td510_led_mode(u8 index, unsigned long rules)
+{
+	if (index >= DP83TD510E_LED_COUNT)
+		return -EINVAL;
+
+	switch (rules) {
+	case BIT(TRIGGER_NETDEV_LINK):
+		return DP83TD510E_LED_MODE_LINK_OK;
+	case BIT(TRIGGER_NETDEV_LINK_10):
+		return DP83TD510E_LED_MODE_LED_SPEED;
+	case BIT(TRIGGER_NETDEV_FULL_DUPLEX):
+		return DP83TD510E_LED_MODE_DUPLEX;
+	case BIT(TRIGGER_NETDEV_TX):
+		return DP83TD510E_LED_MODE_TX_ACTIVITY;
+	case BIT(TRIGGER_NETDEV_RX):
+		return DP83TD510E_LED_MODE_RX_ACTIVITY;
+	case BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX):
+		return DP83TD510E_LED_MODE_TX_RX_ACTIVITY;
+	case BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) |
+			BIT(TRIGGER_NETDEV_RX):
+		return DP83TD510E_LED_MODE_LINK_BLINK;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int dp83td510_led_hw_is_supported(struct phy_device *phydev, u8 index,
+					 unsigned long rules)
+{
+	int ret;
+
+	ret = dp83td510_led_mode(index, rules);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static int dp83td510_led_hw_control_set(struct phy_device *phydev, u8 index,
+					unsigned long rules)
+{
+	int mode, ret;
+
+	mode = dp83td510_led_mode(index, rules);
+	if (mode < 0)
+		return mode;
+
+	ret = phy_modify_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_LEDS_CFG_1,
+			     DP83TD510E_LED_FN_MASK(index),
+			     DP83TD510E_LED_FN(index, mode));
+	if (ret)
+		return ret;
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_LEDS_CFG_2,
+				DP83TD510E_LED_DRV_EN(index), 0);
+}
+
+static int dp83td510_led_hw_control_get(struct phy_device *phydev,
+					u8 index, unsigned long *rules)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_LEDS_CFG_1);
+	if (val < 0)
+		return val;
+
+	val &= DP83TD510E_LED_FN_MASK(index);
+	val >>= index * 4;
+
+	switch (val) {
+	case DP83TD510E_LED_MODE_LINK_OK:
+		*rules = BIT(TRIGGER_NETDEV_LINK);
+		break;
+	/* LED mode: LED SPEED (10BaseT1L indicator) */
+	case DP83TD510E_LED_MODE_LED_SPEED:
+		*rules = BIT(TRIGGER_NETDEV_LINK_10);
+		break;
+	case DP83TD510E_LED_MODE_DUPLEX:
+		*rules = BIT(TRIGGER_NETDEV_FULL_DUPLEX);
+		break;
+	case DP83TD510E_LED_MODE_TX_ACTIVITY:
+		*rules = BIT(TRIGGER_NETDEV_TX);
+		break;
+	case DP83TD510E_LED_MODE_RX_ACTIVITY:
+		*rules = BIT(TRIGGER_NETDEV_RX);
+		break;
+	case DP83TD510E_LED_MODE_TX_RX_ACTIVITY:
+		*rules = BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX);
+		break;
+	case DP83TD510E_LED_MODE_LINK_BLINK:
+		*rules = BIT(TRIGGER_NETDEV_LINK) |
+			 BIT(TRIGGER_NETDEV_TX) |
+			 BIT(TRIGGER_NETDEV_RX);
+		break;
+	default:
+		*rules = 0;
+		break;
+	}
+
+	return 0;
+}
+
+static int dp83td510_led_polarity_set(struct phy_device *phydev, int index,
+				      unsigned long modes)
+{
+	u16 polarity = DP83TD510E_LED_POLARITY(index);
+	u32 mode;
+
+	for_each_set_bit(mode, &modes, __PHY_LED_MODES_NUM) {
+		switch (mode) {
+		case PHY_LED_ACTIVE_LOW:
+			polarity = 0;
+			break;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return phy_modify_mmd(phydev, MDIO_MMD_VEND2, DP83TD510E_LEDS_CFG_2,
+			      DP83TD510E_LED_POLARITY(index), polarity);
+}
+
 /**
  * dp83td510_update_stats - Update the PHY statistics for the DP83TD510 PHY.
  * @phydev: Pointer to the phy_device structure.
@@ -712,6 +893,12 @@ static struct phy_driver dp83td510_driver[] = {
 	.get_phy_stats	= dp83td510_get_phy_stats,
 	.update_stats	= dp83td510_update_stats,
 
+	.led_brightness_set = dp83td510_led_brightness_set,
+	.led_hw_is_supported = dp83td510_led_hw_is_supported,
+	.led_hw_control_set = dp83td510_led_hw_control_set,
+	.led_hw_control_get = dp83td510_led_hw_control_get,
+	.led_polarity_set = dp83td510_led_polarity_set,
+
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,
 } };

From c6594d64271704b335378e7b74c39fe4d4fcc777 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 6 Feb 2025 19:26:26 +0100
Subject: [PATCH 0310/2753] unroll: add generic loop unroll helpers

There are cases when we need to explicitly unroll loops. For example,
cache operations, filling DMA descriptors on very high speeds etc.
Add compiler-specific attribute macros to give the compiler a hint
that we'd like to unroll a loop.
Example usage:

 #define UNROLL_BATCH 8

	unrolled_count(UNROLL_BATCH)
	for (u32 i = 0; i < UNROLL_BATCH; i++)
		op(priv, i);

Note that sometimes the compilers won't unroll loops if they think this
would have worse optimization and perf than without unrolling, and that
unroll attributes are available only starting GCC 8. For older compiler
versions, no hints/attributes will be applied.
For better unrolling/parallelization, don't have any variables that
interfere between iterations except for the iterator itself.

Co-developed-by: Jose E. Marchesi <jose.marchesi@oracle.com> # pragmas
Signed-off-by: Jose E. Marchesi <jose.marchesi@oracle.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250206182630.3914318-2-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/unroll.h | 44 ++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/include/linux/unroll.h b/include/linux/unroll.h
index d42fd6366373e..863fb69f6a7e6 100644
--- a/include/linux/unroll.h
+++ b/include/linux/unroll.h
@@ -9,6 +9,50 @@
 
 #include <linux/args.h>
 
+#ifdef CONFIG_CC_IS_CLANG
+#define __pick_unrolled(x, y)		_Pragma(#x)
+#elif CONFIG_GCC_VERSION >= 80000
+#define __pick_unrolled(x, y)		_Pragma(#y)
+#else
+#define __pick_unrolled(x, y)		/* not supported */
+#endif
+
+/**
+ * unrolled - loop attributes to ask the compiler to unroll it
+ *
+ * Usage:
+ *
+ * #define BATCH 8
+ *
+ *	unrolled_count(BATCH)
+ *	for (u32 i = 0; i < BATCH; i++)
+ *		// loop body without cross-iteration dependencies
+ *
+ * This is only a hint and the compiler is free to disable unrolling if it
+ * thinks the count is suboptimal and may hurt performance and/or hugely
+ * increase object code size.
+ * Not having any cross-iteration dependencies (i.e. when iter x + 1 depends
+ * on what iter x will do with variables) is not a strict requirement, but
+ * provides best performance and object code size.
+ * Available only on Clang and GCC 8.x onwards.
+ */
+
+/* Ask the compiler to pick an optimal unroll count, Clang only */
+#define unrolled							\
+	__pick_unrolled(clang loop unroll(enable), /* nothing */)
+
+/* Unroll each @n iterations of the loop */
+#define unrolled_count(n)						\
+	__pick_unrolled(clang loop unroll_count(n), GCC unroll n)
+
+/* Unroll the whole loop */
+#define unrolled_full							\
+	__pick_unrolled(clang loop unroll(full), GCC unroll 65534)
+
+/* Never unroll the loop */
+#define unrolled_none							\
+	__pick_unrolled(clang loop unroll(disable), GCC unroll 1)
+
 #define UNROLL(N, MACRO, args...) CONCATENATE(__UNROLL_, N)(MACRO, args)
 
 #define __UNROLL_0(MACRO, args...)

From 9144e6f404da258a7620e66aadea953cf3b114d6 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 6 Feb 2025 19:26:27 +0100
Subject: [PATCH 0311/2753] i40e: use generic unrolled_count() macro

i40e, as well as ice, has a custom loop unrolling macro for unrolling
Tx descriptors filling on XSk xmit.
Replace i40e defs with generic unrolled_count(), which is also more
convenient as it allows passing defines as its argument, not hardcoded
values, while the loop declaration will still be a usual for-loop.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250206182630.3914318-3-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/i40e/i40e_xsk.c |  4 +++-
 drivers/net/ethernet/intel/i40e/i40e_xsk.h | 10 +---------
 2 files changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
index e28f1905a4a0f..9f47388eaba53 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include "i40e_txrx_common.h"
 #include "i40e_xsk.h"
@@ -529,7 +530,8 @@ static void i40e_xmit_pkt_batch(struct i40e_ring *xdp_ring, struct xdp_desc *des
 	dma_addr_t dma;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		u32 cmd = I40E_TX_DESC_CMD_ICRC | xsk_is_eop_desc(&desc[i]);
 
 		dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc[i].addr);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
index ef156fad52f26..dd16351a7af84 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h
@@ -6,7 +6,7 @@
 
 #include <linux/types.h>
 
-/* This value should match the pragma in the loop_unrolled_for
+/* This value should match the pragma in the unrolled_count()
  * macro. Why 4? It is strictly empirical. It seems to be a good
  * compromise between the advantage of having simultaneous outstanding
  * reads to the DMA array that can hide each others latency and the
@@ -14,14 +14,6 @@
  */
 #define PKTS_PER_BATCH 4
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(4)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 4") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct i40e_ring;
 struct i40e_vsi;
 struct net_device;

From 2fc6b26ac8aecd5f53164b00fe5d32417e1fbfc9 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 6 Feb 2025 19:26:28 +0100
Subject: [PATCH 0312/2753] ice: use generic unrolled_count() macro

ice, same as i40e, has a custom loop unrolling macros for unrolling
Tx descriptors filling on XSk xmit.
Replace ice defs with generic unrolled_count(), which is also more
convenient as it allows passing defines as its argument, not hardcoded
values, while the loop declaration will still be usual for-loop.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Acked-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250206182630.3914318-4-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_xsk.c | 4 +++-
 drivers/net/ethernet/intel/ice/ice_xsk.h | 8 --------
 2 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
index 8975d2971bc37..a3a4eaa17739a 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2019, Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/unroll.h>
 #include <net/xdp_sock_drv.h>
 #include <net/xdp.h>
 #include "ice.h"
@@ -989,7 +990,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
 	struct ice_tx_desc *tx_desc;
 	u32 i;
 
-	loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+	unrolled_count(PKTS_PER_BATCH)
+	for (i = 0; i < PKTS_PER_BATCH; i++) {
 		dma_addr_t dma;
 
 		dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
index 45adeb513253a..8dc5d55e26c52 100644
--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
+++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
@@ -7,14 +7,6 @@
 
 #define PKTS_PER_BATCH 8
 
-#ifdef __clang__
-#define loop_unrolled_for _Pragma("clang loop unroll_count(8)") for
-#elif __GNUC__ >= 8
-#define loop_unrolled_for _Pragma("GCC unroll 8") for
-#else
-#define loop_unrolled_for for
-#endif
-
 struct ice_vsi;
 
 #ifdef CONFIG_XDP_SOCKETS

From 23d9324a27a48858cfdd7f0342f52328e8595c6d Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Thu, 6 Feb 2025 19:26:29 +0100
Subject: [PATCH 0313/2753] xsk: add helper to get &xdp_desc's DMA and meta
 pointer in one go

Currently, when your driver supports XSk Tx metadata and you want to
send an XSk frame, you need to do the following:

* call external xsk_buff_raw_get_dma();
* call inline xsk_buff_get_metadata(), which calls external
  xsk_buff_raw_get_data() and then do some inline checks.

This effectively means that the following piece:

addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;

is done twice per frame, plus you have 2 external calls per frame, plus
this:

	meta = pool->addrs + addr - pool->tx_metadata_len;
	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))

is always inlined, even if there's no meta or it's invalid.

Add xsk_buff_raw_get_ctx() (xp_raw_get_ctx() to be precise) to do that
in one go. It returns a small structure with 2 fields: DMA address,
filled unconditionally, and metadata pointer, non-NULL only if it's
present and valid. The address correction is performed only once and
you also have only 1 external call per XSk frame, which does all the
calculations and checks outside of your hotpath. You only need to
check `if (ctx.meta)` for the metadata presence.
To not copy any existing code, derive address correction and getting
virtual and DMA address into small helpers. bloat-o-meter reports no
object code changes for the existing functionality.

Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250206182630.3914318-5-aleksander.lobakin@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/xdp_sock_drv.h  | 43 +++++++++++++++++++++++++++++++---
 include/net/xsk_buff_pool.h |  8 +++++++
 net/xdp/xsk_buff_pool.c     | 46 +++++++++++++++++++++++++++++++++----
 3 files changed, 90 insertions(+), 7 deletions(-)

diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 784cd34f5bba5..15086dcf51d85 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -196,6 +196,23 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return xp_raw_get_data(pool, addr);
 }
 
+/**
+ * xsk_buff_raw_get_ctx - get &xdp_desc context
+ * @pool: XSk buff pool desc address belongs to
+ * @addr: desc address (from userspace)
+ *
+ * Wrapper for xp_raw_get_ctx() to be used in drivers, see its kdoc for
+ * details.
+ *
+ * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
+ * pointer, if it is present and valid (initialized to %NULL otherwise).
+ */
+static inline struct xdp_desc_ctx
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return xp_raw_get_ctx(pool, addr);
+}
+
 #define XDP_TXMD_FLAGS_VALID ( \
 		XDP_TXMD_FLAGS_TIMESTAMP | \
 		XDP_TXMD_FLAGS_CHECKSUM | \
@@ -207,20 +224,27 @@ xsk_buff_valid_tx_metadata(const struct xsk_tx_metadata *meta)
 	return !(meta->flags & ~XDP_TXMD_FLAGS_VALID);
 }
 
-static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+static inline struct xsk_tx_metadata *
+__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
 {
 	struct xsk_tx_metadata *meta;
 
 	if (!pool->tx_metadata_len)
 		return NULL;
 
-	meta = xp_raw_get_data(pool, addr) - pool->tx_metadata_len;
+	meta = data - pool->tx_metadata_len;
 	if (unlikely(!xsk_buff_valid_tx_metadata(meta)))
 		return NULL; /* no way to signal the error to the user */
 
 	return meta;
 }
 
+static inline struct xsk_tx_metadata *
+xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+{
+	return __xsk_buff_get_metadata(pool, xp_raw_get_data(pool, addr));
+}
+
 static inline void xsk_buff_dma_sync_for_cpu(struct xdp_buff *xdp)
 {
 	struct xdp_buff_xsk *xskb = container_of(xdp, struct xdp_buff_xsk, xdp);
@@ -388,12 +412,25 @@ static inline void *xsk_buff_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
 	return NULL;
 }
 
+static inline struct xdp_desc_ctx
+xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return (struct xdp_desc_ctx){ };
+}
+
 static inline bool xsk_buff_valid_tx_metadata(struct xsk_tx_metadata *meta)
 {
 	return false;
 }
 
-static inline struct xsk_tx_metadata *xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
+static inline struct xsk_tx_metadata *
+__xsk_buff_get_metadata(const struct xsk_buff_pool *pool, void *data)
+{
+	return NULL;
+}
+
+static inline struct xsk_tx_metadata *
+xsk_buff_get_metadata(struct xsk_buff_pool *pool, u64 addr)
 {
 	return NULL;
 }
diff --git a/include/net/xsk_buff_pool.h b/include/net/xsk_buff_pool.h
index 50779406bc2d9..1dcd4d71468a5 100644
--- a/include/net/xsk_buff_pool.h
+++ b/include/net/xsk_buff_pool.h
@@ -141,6 +141,14 @@ u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max);
 bool xp_can_alloc(struct xsk_buff_pool *pool, u32 count);
 void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr);
 dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr);
+
+struct xdp_desc_ctx {
+	dma_addr_t dma;
+	struct xsk_tx_metadata *meta;
+};
+
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr);
+
 static inline dma_addr_t xp_get_dma(struct xdp_buff_xsk *xskb)
 {
 	return xskb->dma;
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 1f7975b496579..c263fb7a68dc3 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -699,18 +699,56 @@ void xp_free(struct xdp_buff_xsk *xskb)
 }
 EXPORT_SYMBOL(xp_free);
 
-void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
+static u64 __xp_raw_get_addr(const struct xsk_buff_pool *pool, u64 addr)
+{
+	return pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
+}
+
+static void *__xp_raw_get_data(const struct xsk_buff_pool *pool, u64 addr)
 {
-	addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
 	return pool->addrs + addr;
 }
+
+void *xp_raw_get_data(struct xsk_buff_pool *pool, u64 addr)
+{
+	return __xp_raw_get_data(pool, __xp_raw_get_addr(pool, addr));
+}
 EXPORT_SYMBOL(xp_raw_get_data);
 
-dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
+static dma_addr_t __xp_raw_get_dma(const struct xsk_buff_pool *pool, u64 addr)
 {
-	addr = pool->unaligned ? xp_unaligned_add_offset_to_addr(addr) : addr;
 	return (pool->dma_pages[addr >> PAGE_SHIFT] &
 		~XSK_NEXT_PG_CONTIG_MASK) +
 		(addr & ~PAGE_MASK);
 }
+
+dma_addr_t xp_raw_get_dma(struct xsk_buff_pool *pool, u64 addr)
+{
+	return __xp_raw_get_dma(pool, __xp_raw_get_addr(pool, addr));
+}
 EXPORT_SYMBOL(xp_raw_get_dma);
+
+/**
+ * xp_raw_get_ctx - get &xdp_desc context
+ * @pool: XSk buff pool desc address belongs to
+ * @addr: desc address (from userspace)
+ *
+ * Helper for getting desc's DMA address and metadata pointer, if present.
+ * Saves one call on hotpath, double calculation of the actual address,
+ * and inline checks for metadata presence and sanity.
+ *
+ * Return: new &xdp_desc_ctx struct containing desc's DMA address and metadata
+ * pointer, if it is present and valid (initialized to %NULL otherwise).
+ */
+struct xdp_desc_ctx xp_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
+{
+	struct xdp_desc_ctx ret;
+
+	addr = __xp_raw_get_addr(pool, addr);
+
+	ret.dma = __xp_raw_get_dma(pool, addr);
+	ret.meta = __xsk_buff_get_metadata(pool, __xp_raw_get_data(pool, addr));
+
+	return ret;
+}
+EXPORT_SYMBOL(xp_raw_get_ctx);

From 848b09d53d923b4caee5491f57a5c5b22d81febc Mon Sep 17 00:00:00 2001
From: Aleksander Jan Bajkowski <olek2@wp.pl>
Date: Thu, 6 Feb 2025 23:40:33 +0100
Subject: [PATCH 0314/2753] r8152: add vendor/device ID pair for Dell Alienware
 AW1022z

The Dell AW1022z is an RTL8156B based 2.5G Ethernet controller.

Add the vendor and product ID values to the driver. This makes Ethernet
work with the adapter.

Signed-off-by: Aleksander Jan Bajkowski <olek2@wp.pl>
Link: https://patch.msgid.link/20250206224033.980115-1-olek2@wp.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/r8152.c   | 1 +
 include/linux/usb/r8152.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 468c739740463..e1021148d3a69 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -10079,6 +10079,7 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
 	{ USB_DEVICE(VENDOR_ID_DLINK,   0xb301) },
+	{ USB_DEVICE(VENDOR_ID_DELL,    0xb097) },
 	{ USB_DEVICE(VENDOR_ID_ASUS,    0x1976) },
 	{}
 };
diff --git a/include/linux/usb/r8152.h b/include/linux/usb/r8152.h
index 33a4c146dc19c..2ca60828f28bb 100644
--- a/include/linux/usb/r8152.h
+++ b/include/linux/usb/r8152.h
@@ -30,6 +30,7 @@
 #define VENDOR_ID_NVIDIA		0x0955
 #define VENDOR_ID_TPLINK		0x2357
 #define VENDOR_ID_DLINK			0x2001
+#define VENDOR_ID_DELL			0x413c
 #define VENDOR_ID_ASUS			0x0b05
 
 #if IS_REACHABLE(CONFIG_USB_RTL8152)

From e76d1ea8cb18b6aa389a0d3202ffc63ed278215d Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 6 Feb 2025 15:10:33 -0500
Subject: [PATCH 0315/2753] net: xilinx: axienet: Combine CR calculation

Combine the common parts of the CR calculations for better code reuse.
While we're at it, simplify the code a bit.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20250206201036.1516800-2-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h  |  3 -
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 64 ++++++++++---------
 2 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index a3f4f3e42587b..8fd3b45ef6aa6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -112,9 +112,6 @@
 #define XAXIDMA_DELAY_MASK		0xFF000000 /* Delay timeout counter */
 #define XAXIDMA_COALESCE_MASK		0x00FF0000 /* Coalesce counter */
 
-#define XAXIDMA_DELAY_SHIFT		24
-#define XAXIDMA_COALESCE_SHIFT		16
-
 #define XAXIDMA_IRQ_IOC_MASK		0x00001000 /* Completion intr */
 #define XAXIDMA_IRQ_DELAY_MASK		0x00002000 /* Delay interrupt */
 #define XAXIDMA_IRQ_ERROR_MASK		0x00004000 /* Error interrupt */
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 9e7fa012e4fad..bd95f2ba3baed 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -224,22 +224,40 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 }
 
 /**
- * axienet_usec_to_timer - Calculate IRQ delay timer value
- * @lp:		Pointer to the axienet_local structure
- * @coalesce_usec: Microseconds to convert into timer value
+ * axienet_calc_cr() - Calculate control register value
+ * @lp: Device private data
+ * @count: Number of completions before an interrupt
+ * @usec: Microseconds after the last completion before an interrupt
+ *
+ * Calculate a control register value based on the coalescing settings. The
+ * run/stop bit is not set.
  */
-static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec)
+static u32 axienet_calc_cr(struct axienet_local *lp, u32 count, u32 usec)
 {
-	u32 result;
-	u64 clk_rate = 125000000; /* arbitrary guess if no clock rate set */
+	u32 cr;
+
+	cr = FIELD_PREP(XAXIDMA_COALESCE_MASK, count) | XAXIDMA_IRQ_IOC_MASK |
+	     XAXIDMA_IRQ_ERROR_MASK;
+	/* Only set interrupt delay timer if not generating an interrupt on
+	 * the first packet. Otherwise leave at 0 to disable delay interrupt.
+	 */
+	if (count > 1) {
+		u64 clk_rate = 125000000; /* arbitrary guess if no clock rate set */
+		u32 timer;
+
+		if (lp->axi_clk)
+			clk_rate = clk_get_rate(lp->axi_clk);
 
-	if (lp->axi_clk)
-		clk_rate = clk_get_rate(lp->axi_clk);
+		/* 1 Timeout Interval = 125 * (clock period of SG clock) */
+		timer = DIV64_U64_ROUND_CLOSEST((u64)usec * clk_rate,
+						XAXIDMA_DELAY_SCALE);
 
-	/* 1 Timeout Interval = 125 * (clock period of SG clock) */
-	result = DIV64_U64_ROUND_CLOSEST((u64)coalesce_usec * clk_rate,
-					 XAXIDMA_DELAY_SCALE);
-	return min(result, FIELD_MAX(XAXIDMA_DELAY_MASK));
+		timer = min(timer, FIELD_MAX(XAXIDMA_DELAY_MASK));
+		cr |= FIELD_PREP(XAXIDMA_DELAY_MASK, timer) |
+		      XAXIDMA_IRQ_DELAY_MASK;
+	}
+
+	return cr;
 }
 
 /**
@@ -249,27 +267,13 @@ static u32 axienet_usec_to_timer(struct axienet_local *lp, u32 coalesce_usec)
 static void axienet_dma_start(struct axienet_local *lp)
 {
 	/* Start updating the Rx channel control register */
-	lp->rx_dma_cr = (lp->coalesce_count_rx << XAXIDMA_COALESCE_SHIFT) |
-			XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_ERROR_MASK;
-	/* Only set interrupt delay timer if not generating an interrupt on
-	 * the first RX packet. Otherwise leave at 0 to disable delay interrupt.
-	 */
-	if (lp->coalesce_count_rx > 1)
-		lp->rx_dma_cr |= (axienet_usec_to_timer(lp, lp->coalesce_usec_rx)
-					<< XAXIDMA_DELAY_SHIFT) |
-				 XAXIDMA_IRQ_DELAY_MASK;
+	lp->rx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_rx,
+					lp->coalesce_usec_rx);
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
 
 	/* Start updating the Tx channel control register */
-	lp->tx_dma_cr = (lp->coalesce_count_tx << XAXIDMA_COALESCE_SHIFT) |
-			XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_ERROR_MASK;
-	/* Only set interrupt delay timer if not generating an interrupt on
-	 * the first TX packet. Otherwise leave at 0 to disable delay interrupt.
-	 */
-	if (lp->coalesce_count_tx > 1)
-		lp->tx_dma_cr |= (axienet_usec_to_timer(lp, lp->coalesce_usec_tx)
-					<< XAXIDMA_DELAY_SHIFT) |
-				 XAXIDMA_IRQ_DELAY_MASK;
+	lp->tx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_tx,
+					lp->coalesce_usec_tx);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
 
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of

From d048c717df33baf337a58b5d74c855a74abf4e04 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 6 Feb 2025 15:10:34 -0500
Subject: [PATCH 0316/2753] net: xilinx: axienet: Support adjusting coalesce
 settings while running

In preparation for adaptive IRQ coalescing, we first need to support
adjusting the settings at runtime. The existing code doesn't require any
locking because

- dma_start is the only function that modifies rx/tx_dma_cr. It is
  always called with IRQs and NAPI disabled, so nothing else is touching
  the hardware.
- The IRQs don't race with poll, since the latter is a softirq.
- The IRQs don't race with dma_stop since they both just clear the
  control registers.
- dma_stop doesn't race with poll since the former is called with NAPI
  disabled.

However, once we introduce another function that modifies rx/tx_dma_cr,
we need to have some locking to prevent races. Introduce two locks to
protect these variables and their registers.

The control register values are now generated where the coalescing
settings are set. Converting coalescing settings to control register
values may require sleeping because of clk_get_rate. However, the
read/modify/write of the control registers themselves can't sleep
because it needs to happen in IRQ context. By pre-calculating the
control register values, we avoid introducing an additional mutex.

Since axienet_dma_start writes the control settings when it runs, we
don't bother updating the CR registers when rx/tx_dma_started is false.
This prevents any issues from writing to the control registers in the
middle of a reset sequence.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20250206201036.1516800-3-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h  |   8 ++
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 134 +++++++++++++++---
 2 files changed, 119 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 8fd3b45ef6aa6..6b8e550c21551 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -484,7 +484,9 @@ struct skbuf_dma_descriptor {
  * @regs:	Base address for the axienet_local device address space
  * @dma_regs:	Base address for the axidma device address space
  * @napi_rx:	NAPI RX control structure
+ * @rx_cr_lock: Lock protecting @rx_dma_cr, its register, and @rx_dma_started
  * @rx_dma_cr:  Nominal content of RX DMA control register
+ * @rx_dma_started: Set when RX DMA is started
  * @rx_bd_v:	Virtual address of the RX buffer descriptor ring
  * @rx_bd_p:	Physical address(start address) of the RX buffer descr. ring
  * @rx_bd_num:	Size of RX buffer descriptor ring
@@ -494,7 +496,9 @@ struct skbuf_dma_descriptor {
  * @rx_bytes:	RX byte count for statistics
  * @rx_stat_sync: Synchronization object for RX stats
  * @napi_tx:	NAPI TX control structure
+ * @tx_cr_lock: Lock protecting @tx_dma_cr, its register, and @tx_dma_started
  * @tx_dma_cr:  Nominal content of TX DMA control register
+ * @tx_dma_started: Set when TX DMA is started
  * @tx_bd_v:	Virtual address of the TX buffer descriptor ring
  * @tx_bd_p:	Physical address(start address) of the TX buffer descr. ring
  * @tx_bd_num:	Size of TX buffer descriptor ring
@@ -566,7 +570,9 @@ struct axienet_local {
 	void __iomem *dma_regs;
 
 	struct napi_struct napi_rx;
+	spinlock_t rx_cr_lock;
 	u32 rx_dma_cr;
+	bool rx_dma_started;
 	struct axidma_bd *rx_bd_v;
 	dma_addr_t rx_bd_p;
 	u32 rx_bd_num;
@@ -576,7 +582,9 @@ struct axienet_local {
 	struct u64_stats_sync rx_stat_sync;
 
 	struct napi_struct napi_tx;
+	spinlock_t tx_cr_lock;
 	u32 tx_dma_cr;
+	bool tx_dma_started;
 	struct axidma_bd *tx_bd_v;
 	dma_addr_t tx_bd_p;
 	u32 tx_bd_num;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index bd95f2ba3baed..b70e657574541 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -266,16 +266,12 @@ static u32 axienet_calc_cr(struct axienet_local *lp, u32 count, u32 usec)
  */
 static void axienet_dma_start(struct axienet_local *lp)
 {
+	spin_lock_irq(&lp->rx_cr_lock);
+
 	/* Start updating the Rx channel control register */
-	lp->rx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_rx,
-					lp->coalesce_usec_rx);
+	lp->rx_dma_cr &= ~XAXIDMA_CR_RUNSTOP_MASK;
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
 
-	/* Start updating the Tx channel control register */
-	lp->tx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_tx,
-					lp->coalesce_usec_tx);
-	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
-
 	/* Populate the tail pointer and bring the Rx Axi DMA engine out of
 	 * halted state. This will make the Rx side ready for reception.
 	 */
@@ -284,6 +280,14 @@ static void axienet_dma_start(struct axienet_local *lp)
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
 	axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, lp->rx_bd_p +
 			     (sizeof(*lp->rx_bd_v) * (lp->rx_bd_num - 1)));
+	lp->rx_dma_started = true;
+
+	spin_unlock_irq(&lp->rx_cr_lock);
+	spin_lock_irq(&lp->tx_cr_lock);
+
+	/* Start updating the Tx channel control register */
+	lp->tx_dma_cr &= ~XAXIDMA_CR_RUNSTOP_MASK;
+	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
 
 	/* Write to the RS (Run-stop) bit in the Tx channel control register.
 	 * Tx channel is now ready to run. But only after we write to the
@@ -292,6 +296,9 @@ static void axienet_dma_start(struct axienet_local *lp)
 	axienet_dma_out_addr(lp, XAXIDMA_TX_CDESC_OFFSET, lp->tx_bd_p);
 	lp->tx_dma_cr |= XAXIDMA_CR_RUNSTOP_MASK;
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
+	lp->tx_dma_started = true;
+
+	spin_unlock_irq(&lp->tx_cr_lock);
 }
 
 /**
@@ -627,14 +634,22 @@ static void axienet_dma_stop(struct axienet_local *lp)
 	int count;
 	u32 cr, sr;
 
-	cr = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
-	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	spin_lock_irq(&lp->rx_cr_lock);
+
+	cr = lp->rx_dma_cr & ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
 	axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+	lp->rx_dma_started = false;
+
+	spin_unlock_irq(&lp->rx_cr_lock);
 	synchronize_irq(lp->rx_irq);
 
-	cr = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
-	cr &= ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
+	spin_lock_irq(&lp->tx_cr_lock);
+
+	cr = lp->tx_dma_cr & ~(XAXIDMA_CR_RUNSTOP_MASK | XAXIDMA_IRQ_ALL_MASK);
 	axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+	lp->tx_dma_started = false;
+
+	spin_unlock_irq(&lp->tx_cr_lock);
 	synchronize_irq(lp->tx_irq);
 
 	/* Give DMAs a chance to halt gracefully */
@@ -983,7 +998,9 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 		 * cause an immediate interrupt if any TX packets are
 		 * already pending.
 		 */
+		spin_lock_irq(&lp->tx_cr_lock);
 		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, lp->tx_dma_cr);
+		spin_unlock_irq(&lp->tx_cr_lock);
 	}
 	return packets;
 }
@@ -1249,7 +1266,9 @@ static int axienet_rx_poll(struct napi_struct *napi, int budget)
 		 * cause an immediate interrupt if any RX packets are
 		 * already pending.
 		 */
+		spin_lock_irq(&lp->rx_cr_lock);
 		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, lp->rx_dma_cr);
+		spin_unlock_irq(&lp->rx_cr_lock);
 	}
 	return packets;
 }
@@ -1287,11 +1306,14 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
 		/* Disable further TX completion interrupts and schedule
 		 * NAPI to handle the completions.
 		 */
-		u32 cr = lp->tx_dma_cr;
-
-		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 		if (napi_schedule_prep(&lp->napi_tx)) {
+			u32 cr;
+
+			spin_lock(&lp->tx_cr_lock);
+			cr = lp->tx_dma_cr;
+			cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 			axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+			spin_unlock(&lp->tx_cr_lock);
 			__napi_schedule(&lp->napi_tx);
 		}
 	}
@@ -1332,11 +1354,15 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		/* Disable further RX completion interrupts and schedule
 		 * NAPI receive.
 		 */
-		u32 cr = lp->rx_dma_cr;
-
-		cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 		if (napi_schedule_prep(&lp->napi_rx)) {
+			u32 cr;
+
+			spin_lock(&lp->rx_cr_lock);
+			cr = lp->rx_dma_cr;
+			cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
 			axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+			spin_unlock(&lp->rx_cr_lock);
+
 			__napi_schedule(&lp->napi_rx);
 		}
 	}
@@ -2002,6 +2028,62 @@ axienet_ethtools_set_pauseparam(struct net_device *ndev,
 	return phylink_ethtool_set_pauseparam(lp->phylink, epauseparm);
 }
 
+/**
+ * axienet_update_coalesce_rx() - Set RX CR
+ * @lp: Device private data
+ * @cr: Value to write to the RX CR
+ * @mask: Bits to set from @cr
+ */
+static void axienet_update_coalesce_rx(struct axienet_local *lp, u32 cr,
+				       u32 mask)
+{
+	spin_lock_irq(&lp->rx_cr_lock);
+	lp->rx_dma_cr &= ~mask;
+	lp->rx_dma_cr |= cr;
+	/* If DMA isn't started, then the settings will be applied the next
+	 * time dma_start() is called.
+	 */
+	if (lp->rx_dma_started) {
+		u32 reg = axienet_dma_in32(lp, XAXIDMA_RX_CR_OFFSET);
+
+		/* Don't enable IRQs if they are disabled by NAPI */
+		if (reg & XAXIDMA_IRQ_ALL_MASK)
+			cr = lp->rx_dma_cr;
+		else
+			cr = lp->rx_dma_cr & ~XAXIDMA_IRQ_ALL_MASK;
+		axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+	}
+	spin_unlock_irq(&lp->rx_cr_lock);
+}
+
+/**
+ * axienet_update_coalesce_tx() - Set TX CR
+ * @lp: Device private data
+ * @cr: Value to write to the TX CR
+ * @mask: Bits to set from @cr
+ */
+static void axienet_update_coalesce_tx(struct axienet_local *lp, u32 cr,
+				       u32 mask)
+{
+	spin_lock_irq(&lp->tx_cr_lock);
+	lp->tx_dma_cr &= ~mask;
+	lp->tx_dma_cr |= cr;
+	/* If DMA isn't started, then the settings will be applied the next
+	 * time dma_start() is called.
+	 */
+	if (lp->tx_dma_started) {
+		u32 reg = axienet_dma_in32(lp, XAXIDMA_TX_CR_OFFSET);
+
+		/* Don't enable IRQs if they are disabled by NAPI */
+		if (reg & XAXIDMA_IRQ_ALL_MASK)
+			cr = lp->tx_dma_cr;
+		else
+			cr = lp->tx_dma_cr & ~XAXIDMA_IRQ_ALL_MASK;
+		axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+	}
+	spin_unlock_irq(&lp->tx_cr_lock);
+}
+
 /**
  * axienet_ethtools_get_coalesce - Get DMA interrupt coalescing count.
  * @ndev:	Pointer to net_device structure
@@ -2050,12 +2132,7 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
-
-	if (netif_running(ndev)) {
-		NL_SET_ERR_MSG(extack,
-			       "Please stop netif before applying configuration");
-		return -EBUSY;
-	}
+	u32 cr;
 
 	if (ecoalesce->rx_max_coalesced_frames > 255 ||
 	    ecoalesce->tx_max_coalesced_frames > 255) {
@@ -2083,6 +2160,11 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 	lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames;
 	lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs;
 
+	cr = axienet_calc_cr(lp, lp->coalesce_count_rx, lp->coalesce_usec_rx);
+	axienet_update_coalesce_rx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
+
+	cr = axienet_calc_cr(lp, lp->coalesce_count_tx, lp->coalesce_usec_tx);
+	axienet_update_coalesce_tx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
 	return 0;
 }
 
@@ -2862,10 +2944,16 @@ static int axienet_probe(struct platform_device *pdev)
 		axienet_set_mac_address(ndev, NULL);
 	}
 
+	spin_lock_init(&lp->rx_cr_lock);
+	spin_lock_init(&lp->tx_cr_lock);
 	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
 	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
 	lp->coalesce_usec_rx = XAXIDMA_DFT_RX_USEC;
 	lp->coalesce_usec_tx = XAXIDMA_DFT_TX_USEC;
+	lp->rx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_rx,
+					lp->coalesce_usec_rx);
+	lp->tx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_tx,
+					lp->coalesce_usec_tx);
 
 	ret = axienet_mdio_setup(lp);
 	if (ret)

From eb80520e8a5be676cd546c2503aa78653ff4b026 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 6 Feb 2025 15:10:35 -0500
Subject: [PATCH 0317/2753] net: xilinx: axienet: Get coalesce parameters from
 driver state

The cr variables now contain the same values as the control registers
themselves. Extract/calculate the values from the variables instead of
saving the user-specified values. This allows us to remove some
bookeeping, and also lets the user know what the actual coalesce
settings are.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20250206201036.1516800-4-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h  |  8 ---
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 70 +++++++++++++------
 2 files changed, 47 insertions(+), 31 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 6b8e550c21551..45d8d80dbb1a6 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -533,10 +533,6 @@ struct skbuf_dma_descriptor {
  *		  supported, the maximum frame size would be 9k. Else it is
  *		  1522 bytes (assuming support for basic VLAN)
  * @rxmem:	Stores rx memory size for jumbo frame handling.
- * @coalesce_count_rx:	Store the irq coalesce on RX side.
- * @coalesce_usec_rx:	IRQ coalesce delay for RX
- * @coalesce_count_tx:	Store the irq coalesce on TX side.
- * @coalesce_usec_tx:	IRQ coalesce delay for TX
  * @use_dmaengine: flag to check dmaengine framework usage.
  * @tx_chan:	TX DMA channel.
  * @rx_chan:	RX DMA channel.
@@ -615,10 +611,6 @@ struct axienet_local {
 	u32 max_frm_size;
 	u32 rxmem;
 
-	u32 coalesce_count_rx;
-	u32 coalesce_usec_rx;
-	u32 coalesce_count_tx;
-	u32 coalesce_usec_tx;
 	u8  use_dmaengine;
 	struct dma_chan *tx_chan;
 	struct dma_chan *rx_chan;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index b70e657574541..da3d4193674e5 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -223,6 +223,13 @@ static void axienet_dma_bd_release(struct net_device *ndev)
 			  lp->rx_bd_p);
 }
 
+static u64 axienet_dma_rate(struct axienet_local *lp)
+{
+	if (lp->axi_clk)
+		return clk_get_rate(lp->axi_clk);
+	return 125000000; /* arbitrary guess if no clock rate set */
+}
+
 /**
  * axienet_calc_cr() - Calculate control register value
  * @lp: Device private data
@@ -242,12 +249,9 @@ static u32 axienet_calc_cr(struct axienet_local *lp, u32 count, u32 usec)
 	 * the first packet. Otherwise leave at 0 to disable delay interrupt.
 	 */
 	if (count > 1) {
-		u64 clk_rate = 125000000; /* arbitrary guess if no clock rate set */
+		u64 clk_rate = axienet_dma_rate(lp);
 		u32 timer;
 
-		if (lp->axi_clk)
-			clk_rate = clk_get_rate(lp->axi_clk);
-
 		/* 1 Timeout Interval = 125 * (clock period of SG clock) */
 		timer = DIV64_U64_ROUND_CLOSEST((u64)usec * clk_rate,
 						XAXIDMA_DELAY_SCALE);
@@ -260,6 +264,23 @@ static u32 axienet_calc_cr(struct axienet_local *lp, u32 count, u32 usec)
 	return cr;
 }
 
+/**
+ * axienet_coalesce_params() - Extract coalesce parameters from the CR
+ * @lp: Device private data
+ * @cr: The control register to parse
+ * @count: Number of packets before an interrupt
+ * @usec: Idle time (in usec) before an interrupt
+ */
+static void axienet_coalesce_params(struct axienet_local *lp, u32 cr,
+				    u32 *count, u32 *usec)
+{
+	u64 clk_rate = axienet_dma_rate(lp);
+	u64 timer = FIELD_GET(XAXIDMA_DELAY_MASK, cr);
+
+	*count = FIELD_GET(XAXIDMA_COALESCE_MASK, cr);
+	*usec = DIV64_U64_ROUND_CLOSEST(timer * XAXIDMA_DELAY_SCALE, clk_rate);
+}
+
 /**
  * axienet_dma_start - Set up DMA registers and start DMA operation
  * @lp:		Pointer to the axienet_local structure
@@ -2104,11 +2125,21 @@ axienet_ethtools_get_coalesce(struct net_device *ndev,
 			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
+	u32 cr;
 
-	ecoalesce->rx_max_coalesced_frames = lp->coalesce_count_rx;
-	ecoalesce->rx_coalesce_usecs = lp->coalesce_usec_rx;
-	ecoalesce->tx_max_coalesced_frames = lp->coalesce_count_tx;
-	ecoalesce->tx_coalesce_usecs = lp->coalesce_usec_tx;
+	spin_lock_irq(&lp->rx_cr_lock);
+	cr = lp->rx_dma_cr;
+	spin_unlock_irq(&lp->rx_cr_lock);
+	axienet_coalesce_params(lp, cr,
+				&ecoalesce->rx_max_coalesced_frames,
+				&ecoalesce->rx_coalesce_usecs);
+
+	spin_lock_irq(&lp->tx_cr_lock);
+	cr = lp->tx_dma_cr;
+	spin_unlock_irq(&lp->tx_cr_lock);
+	axienet_coalesce_params(lp, cr,
+				&ecoalesce->tx_max_coalesced_frames,
+				&ecoalesce->tx_coalesce_usecs);
 	return 0;
 }
 
@@ -2155,15 +2186,12 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 		return -EINVAL;
 	}
 
-	lp->coalesce_count_rx = ecoalesce->rx_max_coalesced_frames;
-	lp->coalesce_usec_rx = ecoalesce->rx_coalesce_usecs;
-	lp->coalesce_count_tx = ecoalesce->tx_max_coalesced_frames;
-	lp->coalesce_usec_tx = ecoalesce->tx_coalesce_usecs;
-
-	cr = axienet_calc_cr(lp, lp->coalesce_count_rx, lp->coalesce_usec_rx);
+	cr = axienet_calc_cr(lp, ecoalesce->rx_max_coalesced_frames,
+			     ecoalesce->rx_coalesce_usecs);
 	axienet_update_coalesce_rx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
 
-	cr = axienet_calc_cr(lp, lp->coalesce_count_tx, lp->coalesce_usec_tx);
+	cr = axienet_calc_cr(lp, ecoalesce->tx_max_coalesced_frames,
+			     ecoalesce->tx_coalesce_usecs);
 	axienet_update_coalesce_tx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
 	return 0;
 }
@@ -2946,14 +2974,10 @@ static int axienet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&lp->rx_cr_lock);
 	spin_lock_init(&lp->tx_cr_lock);
-	lp->coalesce_count_rx = XAXIDMA_DFT_RX_THRESHOLD;
-	lp->coalesce_count_tx = XAXIDMA_DFT_TX_THRESHOLD;
-	lp->coalesce_usec_rx = XAXIDMA_DFT_RX_USEC;
-	lp->coalesce_usec_tx = XAXIDMA_DFT_TX_USEC;
-	lp->rx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_rx,
-					lp->coalesce_usec_rx);
-	lp->tx_dma_cr = axienet_calc_cr(lp, lp->coalesce_count_tx,
-					lp->coalesce_usec_tx);
+	lp->rx_dma_cr = axienet_calc_cr(lp, XAXIDMA_DFT_RX_THRESHOLD,
+					XAXIDMA_DFT_RX_USEC);
+	lp->tx_dma_cr = axienet_calc_cr(lp, XAXIDMA_DFT_TX_THRESHOLD,
+					XAXIDMA_DFT_TX_USEC);
 
 	ret = axienet_mdio_setup(lp);
 	if (ret)

From e1d27d29dbe5139cd6b9a5e06bfe6e18149d1bff Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 6 Feb 2025 15:10:36 -0500
Subject: [PATCH 0318/2753] net: xilinx: axienet: Enable adaptive IRQ
 coalescing with DIM

The default RX IRQ coalescing settings of one IRQ per packet can represent
a significant CPU load. However, increasing the coalescing unilaterally
can result in undesirable latency under low load. Adaptive IRQ
coalescing with DIM offers a way to adjust the coalescing settings based
on load.

This device only supports "CQE" mode [1], where each packet resets the
timer. Therefore, an interrupt is fired either when we receive
coalesce_count_rx packets or when the interface is idle for
coalesce_usec_rx. With this in mind, consider the following scenarios:

Link saturated
    Here we want to set coalesce_count_rx to a large value, in order to
    coalesce more packets and reduce CPU load. coalesce_usec_rx should
    be set to at least the time for one packet. Otherwise the link will
    be "idle" and we will get an interrupt for each packet anyway.

Bursts of packets
    Each burst should be coalesced into a single interrupt, although it
    may be prudent to reduce coalesce_count_rx for better latency.
    coalesce_usec_rx should be set to at least the time for one packet
    so bursts are coalesced. However, additional time beyond the packet
    time will just increase latency at the end of a burst.

Sporadic packets
    Due to low load, we can set coalesce_count_rx to 1 in order to
    reduce latency to the minimum. coalesce_usec_rx does not matter in
    this case.

Based on this analysis, I expected the CQE profiles to look something
like

	usec =  0, pkts = 1   // Low load
	usec = 16, pkts = 4
	usec = 16, pkts = 16
	usec = 16, pkts = 64
	usec = 16, pkts = 256 // High load

Where usec is set to 16 to be a few us greater than the 12.3 us packet
time of a 1500 MTU packet at 1 GBit/s. However, the CQE profile is
instead

	usec =  2, pkts = 256 // Low load
	usec =  8, pkts = 128
	usec = 16, pkts =  64
	usec = 32, pkts =  64
	usec = 64, pkts =  64 // High load

I found this very surprising. The number of coalesced packets
*decreases* as load increases. But as load increases we have more
opportunities to coalesce packets without affecting latency as much.
Additionally, the profile *increases* the usec as the load increases.
But as load increases, the gaps between packets will tend to become
smaller, making it possible to *decrease* usec for better latency at the
end of a "burst".

I consider the default CQE profile unsuitable for this NIC. Therefore,
we use the first profile outlined in this commit instead.
coalesce_usec_rx is set to 16 by default, but the user can customize it.
This may be necessary if they are using jumbo frames. I think adjusting
the profile times based on the link speed/mtu would be good improvement
for generic DIM.

In addition to the above profile problems, I noticed the following
additional issues with DIM while testing:

- DIM tends to "wander" when at low load, since the performance gradient
  is pretty flat. If you only have 10p/ms anyway then adjusting the
  coalescing settings will not affect throughput very much.
- DIM takes a long time to adjust back to low indices when load is
  decreased following a period of high load. This is because it only
  re-evaluates its settings once every 64 interrupts. However, at low
  load 64 interrupts can be several seconds.

Finally: performance. This patch increases receive throughput with
iperf3 from 840 Mbits/sec to 938 Mbits/sec, decreases interrupts from
69920/sec to 316/sec, and decreases CPU utilization (4x Cortex-A53) from
43% to 9%.

[1] Who names this stuff?

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed by: Shannon Nelson <shannon.nelson@amd.com>
Link: https://patch.msgid.link/20250206201036.1516800-5-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/Kconfig           |  1 +
 drivers/net/ethernet/xilinx/xilinx_axienet.h  | 10 ++-
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 80 +++++++++++++++++--
 3 files changed, 82 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/Kconfig b/drivers/net/ethernet/xilinx/Kconfig
index 35d96c633a33d..7502214cc7d50 100644
--- a/drivers/net/ethernet/xilinx/Kconfig
+++ b/drivers/net/ethernet/xilinx/Kconfig
@@ -28,6 +28,7 @@ config XILINX_AXI_EMAC
 	depends on HAS_IOMEM
 	depends on XILINX_DMA
 	select PHYLINK
+	select DIMLIB
 	help
 	  This driver supports the 10/100/1000 Ethernet from Xilinx for the
 	  AXI bus interface used in Xilinx Virtex FPGAs and Soc's.
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index 45d8d80dbb1a6..5ff742103beb9 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -9,6 +9,7 @@
 #ifndef XILINX_AXIENET_H
 #define XILINX_AXIENET_H
 
+#include <linux/dim.h>
 #include <linux/netdevice.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
@@ -123,8 +124,7 @@
 /* Default TX/RX Threshold and delay timer values for SGDMA mode */
 #define XAXIDMA_DFT_TX_THRESHOLD	24
 #define XAXIDMA_DFT_TX_USEC		50
-#define XAXIDMA_DFT_RX_THRESHOLD	1
-#define XAXIDMA_DFT_RX_USEC		50
+#define XAXIDMA_DFT_RX_USEC		16
 
 #define XAXIDMA_BD_CTRL_TXSOF_MASK	0x08000000 /* First tx packet */
 #define XAXIDMA_BD_CTRL_TXEOF_MASK	0x04000000 /* Last tx packet */
@@ -484,6 +484,9 @@ struct skbuf_dma_descriptor {
  * @regs:	Base address for the axienet_local device address space
  * @dma_regs:	Base address for the axidma device address space
  * @napi_rx:	NAPI RX control structure
+ * @rx_dim:     DIM state for the receive queue
+ * @rx_dim_enabled: Whether DIM is enabled or not
+ * @rx_irqs:    Number of interrupts
  * @rx_cr_lock: Lock protecting @rx_dma_cr, its register, and @rx_dma_started
  * @rx_dma_cr:  Nominal content of RX DMA control register
  * @rx_dma_started: Set when RX DMA is started
@@ -566,6 +569,9 @@ struct axienet_local {
 	void __iomem *dma_regs;
 
 	struct napi_struct napi_rx;
+	struct dim rx_dim;
+	bool rx_dim_enabled;
+	u16 rx_irqs;
 	spinlock_t rx_cr_lock;
 	u32 rx_dma_cr;
 	bool rx_dma_started;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index da3d4193674e5..0673b2694e4cb 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1283,6 +1283,18 @@ static int axienet_rx_poll(struct napi_struct *napi, int budget)
 		axienet_dma_out_addr(lp, XAXIDMA_RX_TDESC_OFFSET, tail_p);
 
 	if (packets < budget && napi_complete_done(napi, packets)) {
+		if (READ_ONCE(lp->rx_dim_enabled)) {
+			struct dim_sample sample = {
+				.time = ktime_get(),
+				/* Safe because we are the only writer */
+				.pkt_ctr = u64_stats_read(&lp->rx_packets),
+				.byte_ctr = u64_stats_read(&lp->rx_bytes),
+				.event_ctr = READ_ONCE(lp->rx_irqs),
+			};
+
+			net_dim(&lp->rx_dim, &sample);
+		}
+
 		/* Re-enable RX completion interrupts. This should
 		 * cause an immediate interrupt if any RX packets are
 		 * already pending.
@@ -1375,6 +1387,7 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
 		/* Disable further RX completion interrupts and schedule
 		 * NAPI receive.
 		 */
+		WRITE_ONCE(lp->rx_irqs, READ_ONCE(lp->rx_irqs) + 1);
 		if (napi_schedule_prep(&lp->napi_rx)) {
 			u32 cr;
 
@@ -1676,6 +1689,7 @@ static int axienet_open(struct net_device *ndev)
 	if (lp->eth_irq > 0)
 		free_irq(lp->eth_irq, ndev);
 err_phy:
+	cancel_work_sync(&lp->rx_dim.work);
 	cancel_delayed_work_sync(&lp->stats_work);
 	phylink_stop(lp->phylink);
 	phylink_disconnect_phy(lp->phylink);
@@ -1705,6 +1719,7 @@ static int axienet_stop(struct net_device *ndev)
 		napi_disable(&lp->napi_rx);
 	}
 
+	cancel_work_sync(&lp->rx_dim.work);
 	cancel_delayed_work_sync(&lp->stats_work);
 
 	phylink_stop(lp->phylink);
@@ -2077,6 +2092,31 @@ static void axienet_update_coalesce_rx(struct axienet_local *lp, u32 cr,
 	spin_unlock_irq(&lp->rx_cr_lock);
 }
 
+/**
+ * axienet_dim_coalesce_count_rx() - RX coalesce count for DIM
+ * @lp: Device private data
+ */
+static u32 axienet_dim_coalesce_count_rx(struct axienet_local *lp)
+{
+	return min(1 << (lp->rx_dim.profile_ix << 1), 255);
+}
+
+/**
+ * axienet_rx_dim_work() - Adjust RX DIM settings
+ * @work: The work struct
+ */
+static void axienet_rx_dim_work(struct work_struct *work)
+{
+	struct axienet_local *lp =
+		container_of(work, struct axienet_local, rx_dim.work);
+	u32 cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp), 0);
+	u32 mask = XAXIDMA_COALESCE_MASK | XAXIDMA_IRQ_IOC_MASK |
+		   XAXIDMA_IRQ_ERROR_MASK;
+
+	axienet_update_coalesce_rx(lp, cr, mask);
+	lp->rx_dim.state = DIM_START_MEASURE;
+}
+
 /**
  * axienet_update_coalesce_tx() - Set TX CR
  * @lp: Device private data
@@ -2127,6 +2167,8 @@ axienet_ethtools_get_coalesce(struct net_device *ndev,
 	struct axienet_local *lp = netdev_priv(ndev);
 	u32 cr;
 
+	ecoalesce->use_adaptive_rx_coalesce = lp->rx_dim_enabled;
+
 	spin_lock_irq(&lp->rx_cr_lock);
 	cr = lp->rx_dma_cr;
 	spin_unlock_irq(&lp->rx_cr_lock);
@@ -2163,7 +2205,9 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 			      struct netlink_ext_ack *extack)
 {
 	struct axienet_local *lp = netdev_priv(ndev);
-	u32 cr;
+	bool new_dim = ecoalesce->use_adaptive_rx_coalesce;
+	bool old_dim = lp->rx_dim_enabled;
+	u32 cr, mask = ~XAXIDMA_CR_RUNSTOP_MASK;
 
 	if (ecoalesce->rx_max_coalesced_frames > 255 ||
 	    ecoalesce->tx_max_coalesced_frames > 255) {
@@ -2177,7 +2221,7 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 		return -EINVAL;
 	}
 
-	if ((ecoalesce->rx_max_coalesced_frames > 1 &&
+	if (((ecoalesce->rx_max_coalesced_frames > 1 || new_dim) &&
 	     !ecoalesce->rx_coalesce_usecs) ||
 	    (ecoalesce->tx_max_coalesced_frames > 1 &&
 	     !ecoalesce->tx_coalesce_usecs)) {
@@ -2186,9 +2230,27 @@ axienet_ethtools_set_coalesce(struct net_device *ndev,
 		return -EINVAL;
 	}
 
-	cr = axienet_calc_cr(lp, ecoalesce->rx_max_coalesced_frames,
-			     ecoalesce->rx_coalesce_usecs);
-	axienet_update_coalesce_rx(lp, cr, ~XAXIDMA_CR_RUNSTOP_MASK);
+	if (new_dim && !old_dim) {
+		cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp),
+				     ecoalesce->rx_coalesce_usecs);
+	} else if (!new_dim) {
+		if (old_dim) {
+			WRITE_ONCE(lp->rx_dim_enabled, false);
+			napi_synchronize(&lp->napi_rx);
+			flush_work(&lp->rx_dim.work);
+		}
+
+		cr = axienet_calc_cr(lp, ecoalesce->rx_max_coalesced_frames,
+				     ecoalesce->rx_coalesce_usecs);
+	} else {
+		/* Dummy value for count just to calculate timer */
+		cr = axienet_calc_cr(lp, 2, ecoalesce->rx_coalesce_usecs);
+		mask = XAXIDMA_DELAY_MASK | XAXIDMA_IRQ_DELAY_MASK;
+	}
+
+	axienet_update_coalesce_rx(lp, cr, mask);
+	if (new_dim && !old_dim)
+		WRITE_ONCE(lp->rx_dim_enabled, true);
 
 	cr = axienet_calc_cr(lp, ecoalesce->tx_max_coalesced_frames,
 			     ecoalesce->tx_coalesce_usecs);
@@ -2430,7 +2492,8 @@ axienet_ethtool_get_rmon_stats(struct net_device *dev,
 
 static const struct ethtool_ops axienet_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES |
-				     ETHTOOL_COALESCE_USECS,
+				     ETHTOOL_COALESCE_USECS |
+				     ETHTOOL_COALESCE_USE_ADAPTIVE_RX,
 	.get_drvinfo    = axienet_ethtools_get_drvinfo,
 	.get_regs_len   = axienet_ethtools_get_regs_len,
 	.get_regs       = axienet_ethtools_get_regs,
@@ -2974,7 +3037,10 @@ static int axienet_probe(struct platform_device *pdev)
 
 	spin_lock_init(&lp->rx_cr_lock);
 	spin_lock_init(&lp->tx_cr_lock);
-	lp->rx_dma_cr = axienet_calc_cr(lp, XAXIDMA_DFT_RX_THRESHOLD,
+	INIT_WORK(&lp->rx_dim.work, axienet_rx_dim_work);
+	lp->rx_dim_enabled = true;
+	lp->rx_dim.profile_ix = 1;
+	lp->rx_dma_cr = axienet_calc_cr(lp, axienet_dim_coalesce_count_rx(lp),
 					XAXIDMA_DFT_RX_USEC);
 	lp->tx_dma_cr = axienet_calc_cr(lp, XAXIDMA_DFT_TX_THRESHOLD,
 					XAXIDMA_DFT_TX_USEC);

From 5a9c5e5d8a1b70837287d03432757d10047c3bbb Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:51 +0900
Subject: [PATCH 0319/2753] tun: Refactor CONFIG_TUN_VNET_CROSS_LE

Check IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) to save some lines and make
future changes easier.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-1-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 29 ++++++++++-------------------
 1 file changed, 10 insertions(+), 19 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index acf96f2624887..8a9a29031bd88 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -298,17 +298,21 @@ static bool tun_napi_frags_enabled(const struct tun_file *tfile)
 	return tfile->napi_frags_enabled;
 }
 
-#ifdef CONFIG_TUN_VNET_CROSS_LE
 static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
 {
-	return tun->flags & TUN_VNET_BE ? false :
-		virtio_legacy_is_little_endian();
+	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
+		  (tun->flags & TUN_VNET_BE);
+
+	return !be && virtio_legacy_is_little_endian();
 }
 
 static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
 {
 	int be = !!(tun->flags & TUN_VNET_BE);
 
+	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
+		return -EINVAL;
+
 	if (put_user(be, argp))
 		return -EFAULT;
 
@@ -319,6 +323,9 @@ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
 {
 	int be;
 
+	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
+		return -EINVAL;
+
 	if (get_user(be, argp))
 		return -EFAULT;
 
@@ -329,22 +336,6 @@ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
 
 	return 0;
 }
-#else
-static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
-{
-	return virtio_legacy_is_little_endian();
-}
-
-static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	return -EINVAL;
-}
-
-static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_TUN_VNET_CROSS_LE */
 
 static inline bool tun_is_little_endian(struct tun_struct *tun)
 {

From 07e8b3bae2f8f49e3cd6ea51f899a3d062100822 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:52 +0900
Subject: [PATCH 0320/2753] tun: Keep hdr_len in tun_get_user()

hdr_len is repeatedly used so keep it in a local variable.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-2-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 24 +++++++++++-------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8a9a29031bd88..ecc32421dbb51 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1747,6 +1747,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	struct virtio_net_hdr gso = { 0 };
 	int good_linear;
 	int copylen;
+	int hdr_len = 0;
 	bool zerocopy = false;
 	int err;
 	u32 rxhash = 0;
@@ -1773,19 +1774,21 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (!copy_from_iter_full(&gso, sizeof(gso), from))
 			return -EFAULT;
 
-		if ((gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		    tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2 > tun16_to_cpu(tun, gso.hdr_len))
-			gso.hdr_len = cpu_to_tun16(tun, tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2);
+		hdr_len = tun16_to_cpu(tun, gso.hdr_len);
 
-		if (tun16_to_cpu(tun, gso.hdr_len) > len)
+		if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+			hdr_len = max(tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2, hdr_len);
+			gso.hdr_len = cpu_to_tun16(tun, hdr_len);
+		}
+
+		if (hdr_len > len)
 			return -EINVAL;
 		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
 		align += NET_IP_ALIGN;
-		if (unlikely(len < ETH_HLEN ||
-			     (gso.hdr_len && tun16_to_cpu(tun, gso.hdr_len) < ETH_HLEN)))
+		if (unlikely(len < ETH_HLEN || (hdr_len && hdr_len < ETH_HLEN)))
 			return -EINVAL;
 	}
 
@@ -1798,9 +1801,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		 * enough room for skb expand head in case it is used.
 		 * The rest of the buffer is mapped from userspace.
 		 */
-		copylen = gso.hdr_len ? tun16_to_cpu(tun, gso.hdr_len) : GOODCOPY_LEN;
-		if (copylen > good_linear)
-			copylen = good_linear;
+		copylen = min(hdr_len ? hdr_len : GOODCOPY_LEN, good_linear);
 		linear = copylen;
 		iov_iter_advance(&i, copylen);
 		if (iov_iter_npages(&i, INT_MAX) <= MAX_SKB_FRAGS)
@@ -1821,10 +1822,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 	} else {
 		if (!zerocopy) {
 			copylen = len;
-			if (tun16_to_cpu(tun, gso.hdr_len) > good_linear)
-				linear = good_linear;
-			else
-				linear = tun16_to_cpu(tun, gso.hdr_len);
+			linear = min(hdr_len, good_linear);
 		}
 
 		if (frags) {

From 60df67b94804b1adca74854db502a72f7aeaa125 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:53 +0900
Subject: [PATCH 0321/2753] tun: Decouple vnet from tun_struct

Decouple vnet-related functions from tun_struct so that we can reuse
them for tap in the future.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-3-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 51 ++++++++++++++++++++++++-----------------------
 1 file changed, 26 insertions(+), 25 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ecc32421dbb51..0f86697bca576 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -298,17 +298,17 @@ static bool tun_napi_frags_enabled(const struct tun_file *tfile)
 	return tfile->napi_frags_enabled;
 }
 
-static inline bool tun_legacy_is_little_endian(struct tun_struct *tun)
+static inline bool tun_legacy_is_little_endian(unsigned int flags)
 {
 	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
-		  (tun->flags & TUN_VNET_BE);
+		  (flags & TUN_VNET_BE);
 
 	return !be && virtio_legacy_is_little_endian();
 }
 
-static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
+static long tun_get_vnet_be(unsigned int flags, int __user *argp)
 {
-	int be = !!(tun->flags & TUN_VNET_BE);
+	int be = !!(flags & TUN_VNET_BE);
 
 	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
 		return -EINVAL;
@@ -319,7 +319,7 @@ static long tun_get_vnet_be(struct tun_struct *tun, int __user *argp)
 	return 0;
 }
 
-static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
+static long tun_set_vnet_be(unsigned int *flags, int __user *argp)
 {
 	int be;
 
@@ -330,27 +330,26 @@ static long tun_set_vnet_be(struct tun_struct *tun, int __user *argp)
 		return -EFAULT;
 
 	if (be)
-		tun->flags |= TUN_VNET_BE;
+		*flags |= TUN_VNET_BE;
 	else
-		tun->flags &= ~TUN_VNET_BE;
+		*flags &= ~TUN_VNET_BE;
 
 	return 0;
 }
 
-static inline bool tun_is_little_endian(struct tun_struct *tun)
+static inline bool tun_is_little_endian(unsigned int flags)
 {
-	return tun->flags & TUN_VNET_LE ||
-		tun_legacy_is_little_endian(tun);
+	return flags & TUN_VNET_LE || tun_legacy_is_little_endian(flags);
 }
 
-static inline u16 tun16_to_cpu(struct tun_struct *tun, __virtio16 val)
+static inline u16 tun16_to_cpu(unsigned int flags, __virtio16 val)
 {
-	return __virtio16_to_cpu(tun_is_little_endian(tun), val);
+	return __virtio16_to_cpu(tun_is_little_endian(flags), val);
 }
 
-static inline __virtio16 cpu_to_tun16(struct tun_struct *tun, u16 val)
+static inline __virtio16 cpu_to_tun16(unsigned int flags, u16 val)
 {
-	return __cpu_to_virtio16(tun_is_little_endian(tun), val);
+	return __cpu_to_virtio16(tun_is_little_endian(flags), val);
 }
 
 static inline u32 tun_hashfn(u32 rxhash)
@@ -1766,6 +1765,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (tun->flags & IFF_VNET_HDR) {
 		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+		int flags = tun->flags;
 
 		if (len < vnet_hdr_sz)
 			return -EINVAL;
@@ -1774,11 +1774,11 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		if (!copy_from_iter_full(&gso, sizeof(gso), from))
 			return -EFAULT;
 
-		hdr_len = tun16_to_cpu(tun, gso.hdr_len);
+		hdr_len = tun16_to_cpu(flags, gso.hdr_len);
 
 		if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			hdr_len = max(tun16_to_cpu(tun, gso.csum_start) + tun16_to_cpu(tun, gso.csum_offset) + 2, hdr_len);
-			gso.hdr_len = cpu_to_tun16(tun, hdr_len);
+			hdr_len = max(tun16_to_cpu(flags, gso.csum_start) + tun16_to_cpu(flags, gso.csum_offset) + 2, hdr_len);
+			gso.hdr_len = cpu_to_tun16(flags, hdr_len);
 		}
 
 		if (hdr_len > len)
@@ -1857,7 +1857,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		}
 	}
 
-	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun))) {
+	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun->flags))) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
@@ -2111,23 +2111,24 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso;
+		int flags = tun->flags;
 
 		if (iov_iter_count(iter) < vnet_hdr_sz)
 			return -EINVAL;
 
 		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(tun), true,
+					    tun_is_little_endian(flags), true,
 					    vlan_hlen)) {
 			struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 			if (net_ratelimit()) {
 				netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
-					   sinfo->gso_type, tun16_to_cpu(tun, gso.gso_size),
-					   tun16_to_cpu(tun, gso.hdr_len));
+					   sinfo->gso_type, tun16_to_cpu(flags, gso.gso_size),
+					   tun16_to_cpu(flags, gso.hdr_len));
 				print_hex_dump(KERN_ERR, "tun: ",
 					       DUMP_PREFIX_NONE,
 					       16, 1, skb->head,
-					       min((int)tun16_to_cpu(tun, gso.hdr_len), 64), true);
+					       min((int)tun16_to_cpu(flags, gso.hdr_len), 64), true);
 			}
 			WARN_ON_ONCE(1);
 			return -EINVAL;
@@ -2496,7 +2497,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
 
-	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun))) {
+	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun->flags))) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
@@ -3325,11 +3326,11 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		break;
 
 	case TUNGETVNETBE:
-		ret = tun_get_vnet_be(tun, argp);
+		ret = tun_get_vnet_be(tun->flags, argp);
 		break;
 
 	case TUNSETVNETBE:
-		ret = tun_set_vnet_be(tun, argp);
+		ret = tun_set_vnet_be(&tun->flags, argp);
 		break;
 
 	case TUNATTACHFILTER:

From 2506251e81d18783885d34a329795f4398488957 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:54 +0900
Subject: [PATCH 0322/2753] tun: Decouple vnet handling

Decouple the vnet handling code so that we can reuse it for tap.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-4-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c | 237 +++++++++++++++++++++++++++-------------------
 1 file changed, 139 insertions(+), 98 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 0f86697bca576..ed79a691eee01 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -352,6 +352,127 @@ static inline __virtio16 cpu_to_tun16(unsigned int flags, u16 val)
 	return __cpu_to_virtio16(tun_is_little_endian(flags), val);
 }
 
+static long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
+			   unsigned int cmd, int __user *sp)
+{
+	int s;
+
+	switch (cmd) {
+	case TUNGETVNETHDRSZ:
+		s = *vnet_hdr_sz;
+		if (put_user(s, sp))
+			return -EFAULT;
+		return 0;
+
+	case TUNSETVNETHDRSZ:
+		if (get_user(s, sp))
+			return -EFAULT;
+		if (s < (int)sizeof(struct virtio_net_hdr))
+			return -EINVAL;
+
+		*vnet_hdr_sz = s;
+		return 0;
+
+	case TUNGETVNETLE:
+		s = !!(*flags & TUN_VNET_LE);
+		if (put_user(s, sp))
+			return -EFAULT;
+		return 0;
+
+	case TUNSETVNETLE:
+		if (get_user(s, sp))
+			return -EFAULT;
+		if (s)
+			*flags |= TUN_VNET_LE;
+		else
+			*flags &= ~TUN_VNET_LE;
+		return 0;
+
+	case TUNGETVNETBE:
+		return tun_get_vnet_be(*flags, sp);
+
+	case TUNSETVNETBE:
+		return tun_set_vnet_be(flags, sp);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from,
+			    struct virtio_net_hdr *hdr)
+{
+	u16 hdr_len;
+
+	if (iov_iter_count(from) < sz)
+		return -EINVAL;
+
+	if (!copy_from_iter_full(hdr, sizeof(*hdr), from))
+		return -EFAULT;
+
+	hdr_len = tun16_to_cpu(flags, hdr->hdr_len);
+
+	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+		hdr_len = max(tun16_to_cpu(flags, hdr->csum_start) + tun16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len);
+		hdr->hdr_len = cpu_to_tun16(flags, hdr_len);
+	}
+
+	if (hdr_len > iov_iter_count(from))
+		return -EINVAL;
+
+	iov_iter_advance(from, sz - sizeof(*hdr));
+
+	return hdr_len;
+}
+
+static int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
+			    const struct virtio_net_hdr *hdr)
+{
+	if (unlikely(iov_iter_count(iter) < sz))
+		return -EINVAL;
+
+	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
+		return -EFAULT;
+
+	iov_iter_advance(iter, sz - sizeof(*hdr));
+
+	return 0;
+}
+
+static int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
+			       const struct virtio_net_hdr *hdr)
+{
+	return virtio_net_hdr_to_skb(skb, hdr, tun_is_little_endian(flags));
+}
+
+static int tun_vnet_hdr_from_skb(unsigned int flags,
+				 const struct net_device *dev,
+				 const struct sk_buff *skb,
+				 struct virtio_net_hdr *hdr)
+{
+	int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
+
+	if (virtio_net_hdr_from_skb(skb, hdr,
+				    tun_is_little_endian(flags), true,
+				    vlan_hlen)) {
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+		if (net_ratelimit()) {
+			netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
+				   sinfo->gso_type, tun16_to_cpu(flags, hdr->gso_size),
+				   tun16_to_cpu(flags, hdr->hdr_len));
+			print_hex_dump(KERN_ERR, "tun: ",
+				       DUMP_PREFIX_NONE,
+				       16, 1, skb->head,
+				       min(tun16_to_cpu(flags, hdr->hdr_len), 64), true);
+		}
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static inline u32 tun_hashfn(u32 rxhash)
 {
 	return rxhash & TUN_MASK_FLOW_ENTRIES;
@@ -1765,25 +1886,12 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 
 	if (tun->flags & IFF_VNET_HDR) {
 		int vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
-		int flags = tun->flags;
-
-		if (len < vnet_hdr_sz)
-			return -EINVAL;
-		len -= vnet_hdr_sz;
-
-		if (!copy_from_iter_full(&gso, sizeof(gso), from))
-			return -EFAULT;
-
-		hdr_len = tun16_to_cpu(flags, gso.hdr_len);
 
-		if (gso.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			hdr_len = max(tun16_to_cpu(flags, gso.csum_start) + tun16_to_cpu(flags, gso.csum_offset) + 2, hdr_len);
-			gso.hdr_len = cpu_to_tun16(flags, hdr_len);
-		}
+		hdr_len = tun_vnet_hdr_get(vnet_hdr_sz, tun->flags, from, &gso);
+		if (hdr_len < 0)
+			return hdr_len;
 
-		if (hdr_len > len)
-			return -EINVAL;
-		iov_iter_advance(from, vnet_hdr_sz - sizeof(gso));
+		len -= vnet_hdr_sz;
 	}
 
 	if ((tun->flags & TUN_TYPE_MASK) == IFF_TAP) {
@@ -1857,7 +1965,7 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile,
 		}
 	}
 
-	if (virtio_net_hdr_to_skb(skb, &gso, tun_is_little_endian(tun->flags))) {
+	if (tun_vnet_hdr_to_skb(tun->flags, skb, &gso)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		err = -EINVAL;
 		goto free_skb;
@@ -2052,18 +2160,15 @@ static ssize_t tun_put_user_xdp(struct tun_struct *tun,
 {
 	int vnet_hdr_sz = 0;
 	size_t size = xdp_frame->len;
-	size_t ret;
+	ssize_t ret;
 
 	if (tun->flags & IFF_VNET_HDR) {
 		struct virtio_net_hdr gso = { 0 };
 
 		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
-		if (unlikely(iov_iter_count(iter) < vnet_hdr_sz))
-			return -EINVAL;
-		if (unlikely(copy_to_iter(&gso, sizeof(gso), iter) !=
-			     sizeof(gso)))
-			return -EFAULT;
-		iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso));
+		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		if (ret)
+			return ret;
 	}
 
 	ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz;
@@ -2086,6 +2191,7 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	int vlan_offset = 0;
 	int vlan_hlen = 0;
 	int vnet_hdr_sz = 0;
+	int ret;
 
 	if (skb_vlan_tag_present(skb))
 		vlan_hlen = VLAN_HLEN;
@@ -2111,33 +2217,14 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 
 	if (vnet_hdr_sz) {
 		struct virtio_net_hdr gso;
-		int flags = tun->flags;
-
-		if (iov_iter_count(iter) < vnet_hdr_sz)
-			return -EINVAL;
-
-		if (virtio_net_hdr_from_skb(skb, &gso,
-					    tun_is_little_endian(flags), true,
-					    vlan_hlen)) {
-			struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-			if (net_ratelimit()) {
-				netdev_err(tun->dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
-					   sinfo->gso_type, tun16_to_cpu(flags, gso.gso_size),
-					   tun16_to_cpu(flags, gso.hdr_len));
-				print_hex_dump(KERN_ERR, "tun: ",
-					       DUMP_PREFIX_NONE,
-					       16, 1, skb->head,
-					       min((int)tun16_to_cpu(flags, gso.hdr_len), 64), true);
-			}
-			WARN_ON_ONCE(1);
-			return -EINVAL;
-		}
 
-		if (copy_to_iter(&gso, sizeof(gso), iter) != sizeof(gso))
-			return -EFAULT;
+		ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+		if (ret)
+			return ret;
 
-		iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso));
+		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
+		if (ret)
+			return ret;
 	}
 
 	if (vlan_hlen) {
@@ -2497,7 +2584,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
 
-	if (virtio_net_hdr_to_skb(skb, gso, tun_is_little_endian(tun->flags))) {
+	if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);
 		ret = -EINVAL;
@@ -3081,8 +3168,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	kgid_t group;
 	int ifindex;
 	int sndbuf;
-	int vnet_hdr_sz;
-	int le;
 	int ret;
 	bool do_notify = false;
 
@@ -3289,50 +3374,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		tun_set_sndbuf(tun);
 		break;
 
-	case TUNGETVNETHDRSZ:
-		vnet_hdr_sz = tun->vnet_hdr_sz;
-		if (copy_to_user(argp, &vnet_hdr_sz, sizeof(vnet_hdr_sz)))
-			ret = -EFAULT;
-		break;
-
-	case TUNSETVNETHDRSZ:
-		if (copy_from_user(&vnet_hdr_sz, argp, sizeof(vnet_hdr_sz))) {
-			ret = -EFAULT;
-			break;
-		}
-		if (vnet_hdr_sz < (int)sizeof(struct virtio_net_hdr)) {
-			ret = -EINVAL;
-			break;
-		}
-
-		tun->vnet_hdr_sz = vnet_hdr_sz;
-		break;
-
-	case TUNGETVNETLE:
-		le = !!(tun->flags & TUN_VNET_LE);
-		if (put_user(le, (int __user *)argp))
-			ret = -EFAULT;
-		break;
-
-	case TUNSETVNETLE:
-		if (get_user(le, (int __user *)argp)) {
-			ret = -EFAULT;
-			break;
-		}
-		if (le)
-			tun->flags |= TUN_VNET_LE;
-		else
-			tun->flags &= ~TUN_VNET_LE;
-		break;
-
-	case TUNGETVNETBE:
-		ret = tun_get_vnet_be(tun->flags, argp);
-		break;
-
-	case TUNSETVNETBE:
-		ret = tun_set_vnet_be(&tun->flags, argp);
-		break;
-
 	case TUNATTACHFILTER:
 		/* Can be set only for TAPs */
 		ret = -EINVAL;
@@ -3388,7 +3429,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		break;
 
 	default:
-		ret = -EINVAL;
+		ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp);
 		break;
 	}
 

From 1d41e2fa93f7d4dce4d05dfa2f980fba0898bea8 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:55 +0900
Subject: [PATCH 0323/2753] tun: Extract the vnet handling code

The vnet handling code will be reused by tap.

Functions are renamed to ensure that their names contain "vnet" to
clarify that they are part of the decoupled vnet handling code.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-5-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS            |   2 +-
 drivers/net/tun.c      | 180 +--------------------------------------
 drivers/net/tun_vnet.h | 185 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 188 insertions(+), 179 deletions(-)
 create mode 100644 drivers/net/tun_vnet.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 873aa2cce4d7f..67665d9dd5368 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24152,7 +24152,7 @@ W:	http://vtun.sourceforge.net/tun
 F:	Documentation/networking/tuntap.rst
 F:	arch/um/os-Linux/drivers/
 F:	drivers/net/tap.c
-F:	drivers/net/tun.c
+F:	drivers/net/tun*
 
 TURBOCHANNEL SUBSYSTEM
 M:	"Maciej W. Rozycki" <macro@orcam.me.uk>
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index ed79a691eee01..d8f4d3e996a7a 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -83,6 +83,8 @@
 #include <linux/uaccess.h>
 #include <linux/proc_fs.h>
 
+#include "tun_vnet.h"
+
 static void tun_default_link_ksettings(struct net_device *dev,
 				       struct ethtool_link_ksettings *cmd);
 
@@ -94,9 +96,6 @@ static void tun_default_link_ksettings(struct net_device *dev,
  * overload it to mean fasync when stored there.
  */
 #define TUN_FASYNC	IFF_ATTACH_QUEUE
-/* High bits in flags field are unused. */
-#define TUN_VNET_LE     0x80000000
-#define TUN_VNET_BE     0x40000000
 
 #define TUN_FEATURES (IFF_NO_PI | IFF_ONE_QUEUE | IFF_VNET_HDR | \
 		      IFF_MULTI_QUEUE | IFF_NAPI | IFF_NAPI_FRAGS)
@@ -298,181 +297,6 @@ static bool tun_napi_frags_enabled(const struct tun_file *tfile)
 	return tfile->napi_frags_enabled;
 }
 
-static inline bool tun_legacy_is_little_endian(unsigned int flags)
-{
-	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
-		  (flags & TUN_VNET_BE);
-
-	return !be && virtio_legacy_is_little_endian();
-}
-
-static long tun_get_vnet_be(unsigned int flags, int __user *argp)
-{
-	int be = !!(flags & TUN_VNET_BE);
-
-	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
-		return -EINVAL;
-
-	if (put_user(be, argp))
-		return -EFAULT;
-
-	return 0;
-}
-
-static long tun_set_vnet_be(unsigned int *flags, int __user *argp)
-{
-	int be;
-
-	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
-		return -EINVAL;
-
-	if (get_user(be, argp))
-		return -EFAULT;
-
-	if (be)
-		*flags |= TUN_VNET_BE;
-	else
-		*flags &= ~TUN_VNET_BE;
-
-	return 0;
-}
-
-static inline bool tun_is_little_endian(unsigned int flags)
-{
-	return flags & TUN_VNET_LE || tun_legacy_is_little_endian(flags);
-}
-
-static inline u16 tun16_to_cpu(unsigned int flags, __virtio16 val)
-{
-	return __virtio16_to_cpu(tun_is_little_endian(flags), val);
-}
-
-static inline __virtio16 cpu_to_tun16(unsigned int flags, u16 val)
-{
-	return __cpu_to_virtio16(tun_is_little_endian(flags), val);
-}
-
-static long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
-			   unsigned int cmd, int __user *sp)
-{
-	int s;
-
-	switch (cmd) {
-	case TUNGETVNETHDRSZ:
-		s = *vnet_hdr_sz;
-		if (put_user(s, sp))
-			return -EFAULT;
-		return 0;
-
-	case TUNSETVNETHDRSZ:
-		if (get_user(s, sp))
-			return -EFAULT;
-		if (s < (int)sizeof(struct virtio_net_hdr))
-			return -EINVAL;
-
-		*vnet_hdr_sz = s;
-		return 0;
-
-	case TUNGETVNETLE:
-		s = !!(*flags & TUN_VNET_LE);
-		if (put_user(s, sp))
-			return -EFAULT;
-		return 0;
-
-	case TUNSETVNETLE:
-		if (get_user(s, sp))
-			return -EFAULT;
-		if (s)
-			*flags |= TUN_VNET_LE;
-		else
-			*flags &= ~TUN_VNET_LE;
-		return 0;
-
-	case TUNGETVNETBE:
-		return tun_get_vnet_be(*flags, sp);
-
-	case TUNSETVNETBE:
-		return tun_set_vnet_be(flags, sp);
-
-	default:
-		return -EINVAL;
-	}
-}
-
-static int tun_vnet_hdr_get(int sz, unsigned int flags, struct iov_iter *from,
-			    struct virtio_net_hdr *hdr)
-{
-	u16 hdr_len;
-
-	if (iov_iter_count(from) < sz)
-		return -EINVAL;
-
-	if (!copy_from_iter_full(hdr, sizeof(*hdr), from))
-		return -EFAULT;
-
-	hdr_len = tun16_to_cpu(flags, hdr->hdr_len);
-
-	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-		hdr_len = max(tun16_to_cpu(flags, hdr->csum_start) + tun16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len);
-		hdr->hdr_len = cpu_to_tun16(flags, hdr_len);
-	}
-
-	if (hdr_len > iov_iter_count(from))
-		return -EINVAL;
-
-	iov_iter_advance(from, sz - sizeof(*hdr));
-
-	return hdr_len;
-}
-
-static int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
-			    const struct virtio_net_hdr *hdr)
-{
-	if (unlikely(iov_iter_count(iter) < sz))
-		return -EINVAL;
-
-	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
-		return -EFAULT;
-
-	iov_iter_advance(iter, sz - sizeof(*hdr));
-
-	return 0;
-}
-
-static int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
-			       const struct virtio_net_hdr *hdr)
-{
-	return virtio_net_hdr_to_skb(skb, hdr, tun_is_little_endian(flags));
-}
-
-static int tun_vnet_hdr_from_skb(unsigned int flags,
-				 const struct net_device *dev,
-				 const struct sk_buff *skb,
-				 struct virtio_net_hdr *hdr)
-{
-	int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
-
-	if (virtio_net_hdr_from_skb(skb, hdr,
-				    tun_is_little_endian(flags), true,
-				    vlan_hlen)) {
-		struct skb_shared_info *sinfo = skb_shinfo(skb);
-
-		if (net_ratelimit()) {
-			netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
-				   sinfo->gso_type, tun16_to_cpu(flags, hdr->gso_size),
-				   tun16_to_cpu(flags, hdr->hdr_len));
-			print_hex_dump(KERN_ERR, "tun: ",
-				       DUMP_PREFIX_NONE,
-				       16, 1, skb->head,
-				       min(tun16_to_cpu(flags, hdr->hdr_len), 64), true);
-		}
-		WARN_ON_ONCE(1);
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
 static inline u32 tun_hashfn(u32 rxhash)
 {
 	return rxhash & TUN_MASK_FLOW_ENTRIES;
diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
new file mode 100644
index 0000000000000..fd7411c4447ff
--- /dev/null
+++ b/drivers/net/tun_vnet.h
@@ -0,0 +1,185 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef TUN_VNET_H
+#define TUN_VNET_H
+
+/* High bits in flags field are unused. */
+#define TUN_VNET_LE     0x80000000
+#define TUN_VNET_BE     0x40000000
+
+static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags)
+{
+	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
+		  (flags & TUN_VNET_BE);
+
+	return !be && virtio_legacy_is_little_endian();
+}
+
+static inline long tun_get_vnet_be(unsigned int flags, int __user *argp)
+{
+	int be = !!(flags & TUN_VNET_BE);
+
+	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
+		return -EINVAL;
+
+	if (put_user(be, argp))
+		return -EFAULT;
+
+	return 0;
+}
+
+static inline long tun_set_vnet_be(unsigned int *flags, int __user *argp)
+{
+	int be;
+
+	if (!IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE))
+		return -EINVAL;
+
+	if (get_user(be, argp))
+		return -EFAULT;
+
+	if (be)
+		*flags |= TUN_VNET_BE;
+	else
+		*flags &= ~TUN_VNET_BE;
+
+	return 0;
+}
+
+static inline bool tun_vnet_is_little_endian(unsigned int flags)
+{
+	return flags & TUN_VNET_LE || tun_vnet_legacy_is_little_endian(flags);
+}
+
+static inline u16 tun_vnet16_to_cpu(unsigned int flags, __virtio16 val)
+{
+	return __virtio16_to_cpu(tun_vnet_is_little_endian(flags), val);
+}
+
+static inline __virtio16 cpu_to_tun_vnet16(unsigned int flags, u16 val)
+{
+	return __cpu_to_virtio16(tun_vnet_is_little_endian(flags), val);
+}
+
+static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
+				  unsigned int cmd, int __user *sp)
+{
+	int s;
+
+	switch (cmd) {
+	case TUNGETVNETHDRSZ:
+		s = *vnet_hdr_sz;
+		if (put_user(s, sp))
+			return -EFAULT;
+		return 0;
+
+	case TUNSETVNETHDRSZ:
+		if (get_user(s, sp))
+			return -EFAULT;
+		if (s < (int)sizeof(struct virtio_net_hdr))
+			return -EINVAL;
+
+		*vnet_hdr_sz = s;
+		return 0;
+
+	case TUNGETVNETLE:
+		s = !!(*flags & TUN_VNET_LE);
+		if (put_user(s, sp))
+			return -EFAULT;
+		return 0;
+
+	case TUNSETVNETLE:
+		if (get_user(s, sp))
+			return -EFAULT;
+		if (s)
+			*flags |= TUN_VNET_LE;
+		else
+			*flags &= ~TUN_VNET_LE;
+		return 0;
+
+	case TUNGETVNETBE:
+		return tun_get_vnet_be(*flags, sp);
+
+	case TUNSETVNETBE:
+		return tun_set_vnet_be(flags, sp);
+
+	default:
+		return -EINVAL;
+	}
+}
+
+static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
+				   struct iov_iter *from,
+				   struct virtio_net_hdr *hdr)
+{
+	u16 hdr_len;
+
+	if (iov_iter_count(from) < sz)
+		return -EINVAL;
+
+	if (!copy_from_iter_full(hdr, sizeof(*hdr), from))
+		return -EFAULT;
+
+	hdr_len = tun_vnet16_to_cpu(flags, hdr->hdr_len);
+
+	if (hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+		hdr_len = max(tun_vnet16_to_cpu(flags, hdr->csum_start) + tun_vnet16_to_cpu(flags, hdr->csum_offset) + 2, hdr_len);
+		hdr->hdr_len = cpu_to_tun_vnet16(flags, hdr_len);
+	}
+
+	if (hdr_len > iov_iter_count(from))
+		return -EINVAL;
+
+	iov_iter_advance(from, sz - sizeof(*hdr));
+
+	return hdr_len;
+}
+
+static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
+				   const struct virtio_net_hdr *hdr)
+{
+	if (unlikely(iov_iter_count(iter) < sz))
+		return -EINVAL;
+
+	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
+		return -EFAULT;
+
+	iov_iter_advance(iter, sz - sizeof(*hdr));
+
+	return 0;
+}
+
+static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
+				      const struct virtio_net_hdr *hdr)
+{
+	return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags));
+}
+
+static inline int tun_vnet_hdr_from_skb(unsigned int flags,
+					const struct net_device *dev,
+					const struct sk_buff *skb,
+					struct virtio_net_hdr *hdr)
+{
+	int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
+
+	if (virtio_net_hdr_from_skb(skb, hdr,
+				    tun_vnet_is_little_endian(flags), true,
+				    vlan_hlen)) {
+		struct skb_shared_info *sinfo = skb_shinfo(skb);
+
+		if (net_ratelimit()) {
+			netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
+				   sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size),
+				   tun_vnet16_to_cpu(flags, hdr->hdr_len));
+			print_hex_dump(KERN_ERR, "tun: ",
+				       DUMP_PREFIX_NONE,
+				       16, 1, skb->head,
+				       min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true);
+		}
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#endif /* TUN_VNET_H */

From 74212f20f366db41dd3148b951284ac38ef9bb10 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:56 +0900
Subject: [PATCH 0324/2753] tap: Keep hdr_len in tap_get_user()

hdr_len is repeatedly used so keep it in a local variable.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-6-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c | 28 ++++++++++------------------
 1 file changed, 10 insertions(+), 18 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 5ca6ecf0ce5fb..21b77c261fea1 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -645,6 +645,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	int err;
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int vnet_hdr_len = 0;
+	int hdr_len = 0;
 	int copylen = 0;
 	int depth;
 	bool zerocopy = false;
@@ -663,13 +664,13 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 		if (!copy_from_iter_full(&vnet_hdr, sizeof(vnet_hdr), from))
 			goto err;
 		iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
-		if ((vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) &&
-		     tap16_to_cpu(q, vnet_hdr.csum_start) +
-		     tap16_to_cpu(q, vnet_hdr.csum_offset) + 2 >
-			     tap16_to_cpu(q, vnet_hdr.hdr_len))
-			vnet_hdr.hdr_len = cpu_to_tap16(q,
-				 tap16_to_cpu(q, vnet_hdr.csum_start) +
-				 tap16_to_cpu(q, vnet_hdr.csum_offset) + 2);
+		hdr_len = tap16_to_cpu(q, vnet_hdr.hdr_len);
+		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
+			hdr_len = max(tap16_to_cpu(q, vnet_hdr.csum_start) +
+				      tap16_to_cpu(q, vnet_hdr.csum_offset) + 2,
+				      hdr_len);
+			vnet_hdr.hdr_len = cpu_to_tap16(q, hdr_len);
+		}
 		err = -EINVAL;
 		if (tap16_to_cpu(q, vnet_hdr.hdr_len) > len)
 			goto err;
@@ -682,12 +683,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	if (msg_control && sock_flag(&q->sk, SOCK_ZEROCOPY)) {
 		struct iov_iter i;
 
-		copylen = vnet_hdr.hdr_len ?
-			tap16_to_cpu(q, vnet_hdr.hdr_len) : GOODCOPY_LEN;
-		if (copylen > good_linear)
-			copylen = good_linear;
-		else if (copylen < ETH_HLEN)
-			copylen = ETH_HLEN;
+		copylen = clamp(hdr_len ?: GOODCOPY_LEN, ETH_HLEN, good_linear);
 		linear = copylen;
 		i = *from;
 		iov_iter_advance(&i, copylen);
@@ -697,11 +693,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 
 	if (!zerocopy) {
 		copylen = len;
-		linear = tap16_to_cpu(q, vnet_hdr.hdr_len);
-		if (linear > good_linear)
-			linear = good_linear;
-		else if (linear < ETH_HLEN)
-			linear = ETH_HLEN;
+		linear = clamp(hdr_len, ETH_HLEN, good_linear);
 	}
 
 	skb = tap_alloc_skb(&q->sk, TAP_RESERVE, copylen,

From 6a53fc5a877098889b4bce45ec7ea44948819905 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 7 Feb 2025 15:10:57 +0900
Subject: [PATCH 0325/2753] tap: Use tun's vnet-related code

tun and tap implements the same vnet-related features so reuse the code.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250207-tun-v6-7-fb49cf8b103e@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c | 152 +++++-----------------------------------------
 1 file changed, 16 insertions(+), 136 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 21b77c261fea1..d4ece538f1b23 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -26,74 +26,9 @@
 #include <linux/virtio_net.h>
 #include <linux/skb_array.h>
 
-#define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
-
-#define TAP_VNET_LE 0x80000000
-#define TAP_VNET_BE 0x40000000
-
-#ifdef CONFIG_TUN_VNET_CROSS_LE
-static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
-{
-	return q->flags & TAP_VNET_BE ? false :
-		virtio_legacy_is_little_endian();
-}
-
-static long tap_get_vnet_be(struct tap_queue *q, int __user *sp)
-{
-	int s = !!(q->flags & TAP_VNET_BE);
-
-	if (put_user(s, sp))
-		return -EFAULT;
-
-	return 0;
-}
-
-static long tap_set_vnet_be(struct tap_queue *q, int __user *sp)
-{
-	int s;
-
-	if (get_user(s, sp))
-		return -EFAULT;
-
-	if (s)
-		q->flags |= TAP_VNET_BE;
-	else
-		q->flags &= ~TAP_VNET_BE;
-
-	return 0;
-}
-#else
-static inline bool tap_legacy_is_little_endian(struct tap_queue *q)
-{
-	return virtio_legacy_is_little_endian();
-}
-
-static long tap_get_vnet_be(struct tap_queue *q, int __user *argp)
-{
-	return -EINVAL;
-}
-
-static long tap_set_vnet_be(struct tap_queue *q, int __user *argp)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_TUN_VNET_CROSS_LE */
-
-static inline bool tap_is_little_endian(struct tap_queue *q)
-{
-	return q->flags & TAP_VNET_LE ||
-		tap_legacy_is_little_endian(q);
-}
-
-static inline u16 tap16_to_cpu(struct tap_queue *q, __virtio16 val)
-{
-	return __virtio16_to_cpu(tap_is_little_endian(q), val);
-}
+#include "tun_vnet.h"
 
-static inline __virtio16 cpu_to_tap16(struct tap_queue *q, u16 val)
-{
-	return __cpu_to_virtio16(tap_is_little_endian(q), val);
-}
+#define TAP_IFFEATURES (IFF_VNET_HDR | IFF_MULTI_QUEUE)
 
 static struct proto tap_proto = {
 	.name = "tap",
@@ -655,25 +590,13 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	if (q->flags & IFF_VNET_HDR) {
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
-		err = -EINVAL;
-		if (len < vnet_hdr_len)
+		hdr_len = tun_vnet_hdr_get(vnet_hdr_len, q->flags, from, &vnet_hdr);
+		if (hdr_len < 0) {
+			err = hdr_len;
 			goto err;
-		len -= vnet_hdr_len;
-
-		err = -EFAULT;
-		if (!copy_from_iter_full(&vnet_hdr, sizeof(vnet_hdr), from))
-			goto err;
-		iov_iter_advance(from, vnet_hdr_len - sizeof(vnet_hdr));
-		hdr_len = tap16_to_cpu(q, vnet_hdr.hdr_len);
-		if (vnet_hdr.flags & VIRTIO_NET_HDR_F_NEEDS_CSUM) {
-			hdr_len = max(tap16_to_cpu(q, vnet_hdr.csum_start) +
-				      tap16_to_cpu(q, vnet_hdr.csum_offset) + 2,
-				      hdr_len);
-			vnet_hdr.hdr_len = cpu_to_tap16(q, hdr_len);
 		}
-		err = -EINVAL;
-		if (tap16_to_cpu(q, vnet_hdr.hdr_len) > len)
-			goto err;
+
+		len -= vnet_hdr_len;
 	}
 
 	err = -EINVAL;
@@ -725,8 +648,7 @@ static ssize_t tap_get_user(struct tap_queue *q, void *msg_control,
 	skb->dev = tap->dev;
 
 	if (vnet_hdr_len) {
-		err = virtio_net_hdr_to_skb(skb, &vnet_hdr,
-					    tap_is_little_endian(q));
+		err = tun_vnet_hdr_to_skb(q->flags, skb, &vnet_hdr);
 		if (err) {
 			rcu_read_unlock();
 			drop_reason = SKB_DROP_REASON_DEV_HDR;
@@ -789,23 +711,17 @@ static ssize_t tap_put_user(struct tap_queue *q,
 	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
-		int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
 		struct virtio_net_hdr vnet_hdr;
 
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
-		if (iov_iter_count(iter) < vnet_hdr_len)
-			return -EINVAL;
-
-		if (virtio_net_hdr_from_skb(skb, &vnet_hdr,
-					    tap_is_little_endian(q), true,
-					    vlan_hlen))
-			BUG();
 
-		if (copy_to_iter(&vnet_hdr, sizeof(vnet_hdr), iter) !=
-		    sizeof(vnet_hdr))
-			return -EFAULT;
+		ret = tun_vnet_hdr_from_skb(q->flags, NULL, skb, &vnet_hdr);
+		if (ret)
+			return ret;
 
-		iov_iter_advance(iter, vnet_hdr_len - sizeof(vnet_hdr));
+		ret = tun_vnet_hdr_put(vnet_hdr_len, iter, &vnet_hdr);
+		if (ret)
+			return ret;
 	}
 	total = vnet_hdr_len;
 	total += skb->len;
@@ -1064,42 +980,6 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 		q->sk.sk_sndbuf = s;
 		return 0;
 
-	case TUNGETVNETHDRSZ:
-		s = q->vnet_hdr_sz;
-		if (put_user(s, sp))
-			return -EFAULT;
-		return 0;
-
-	case TUNSETVNETHDRSZ:
-		if (get_user(s, sp))
-			return -EFAULT;
-		if (s < (int)sizeof(struct virtio_net_hdr))
-			return -EINVAL;
-
-		q->vnet_hdr_sz = s;
-		return 0;
-
-	case TUNGETVNETLE:
-		s = !!(q->flags & TAP_VNET_LE);
-		if (put_user(s, sp))
-			return -EFAULT;
-		return 0;
-
-	case TUNSETVNETLE:
-		if (get_user(s, sp))
-			return -EFAULT;
-		if (s)
-			q->flags |= TAP_VNET_LE;
-		else
-			q->flags &= ~TAP_VNET_LE;
-		return 0;
-
-	case TUNGETVNETBE:
-		return tap_get_vnet_be(q, sp);
-
-	case TUNSETVNETBE:
-		return tap_set_vnet_be(q, sp);
-
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
@@ -1143,7 +1023,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 		return ret;
 
 	default:
-		return -EINVAL;
+		return tun_vnet_ioctl(&q->vnet_hdr_sz, &q->flags, cmd, sp);
 	}
 }
 
@@ -1190,7 +1070,7 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 	skb->protocol = eth_hdr(skb)->h_proto;
 
 	if (vnet_hdr_len) {
-		err = virtio_net_hdr_to_skb(skb, gso, tap_is_little_endian(q));
+		err = tun_vnet_hdr_to_skb(q->flags, skb, gso);
 		if (err)
 			goto err_kfree;
 	}

From 7b7df666a23329c5bbcf31166abc7f7468b13950 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:24:55 +0900
Subject: [PATCH 0326/2753] net: fib_rules: Don't check net in rule_exists()
 and rule_find().

fib_nl_newrule() / fib_nl_delrule() looks up struct fib_rules_ops
in sock_net(skb->sk) and calls rule_exists() / rule_find() respectively.

fib_nl_newrule() creates a new rule and links it to the found ops, so
struct fib_rule never belongs to a different netns's ops->rules_list.

Let's remove redundant netns check in rule_exists() and rule_find().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index e684ba3ebb385..02dfb841ab297 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -459,9 +459,6 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 		if (rule->tun_id && r->tun_id != rule->tun_id)
 			continue;
 
-		if (r->fr_net != rule->fr_net)
-			continue;
-
 		if (rule->l3mdev && r->l3mdev != rule->l3mdev)
 			continue;
 
@@ -719,9 +716,6 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 		if (r->tun_id != rule->tun_id)
 			continue;
 
-		if (r->fr_net != rule->fr_net)
-			continue;
-
 		if (r->l3mdev != rule->l3mdev)
 			continue;
 

From a9ffd24b5528f800c5cc994832e05adc1fcf0a5e Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:24:56 +0900
Subject: [PATCH 0327/2753] net: fib_rules: Pass net to fib_nl2rule() instead
 of skb.

skb is not used in fib_nl2rule() other than sock_net(skb->sk),
which is already available in callers, fib_nl_newrule() and
fib_nl_delrule().

Let's pass net directly to fib_nl2rule().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 02dfb841ab297..87f7311995383 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -512,14 +512,13 @@ static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
 }
 #endif
 
-static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh,
+static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 		       struct netlink_ext_ack *extack,
 		       struct fib_rules_ops *ops,
 		       struct nlattr *tb[],
 		       struct fib_rule **rule,
 		       bool *user_priority)
 {
-	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	struct fib_rule *nlrule = NULL;
 	int err = -EINVAL;
@@ -798,7 +797,7 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority);
+	err = fib_nl2rule(net, nlh, extack, ops, tb, &rule, &user_priority);
 	if (err)
 		goto errout;
 
@@ -906,7 +905,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto errout;
 	}
 
-	err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority);
+	err = fib_nl2rule(net, nlh, extack, ops, tb, &nlrule, &user_priority);
 	if (err)
 		goto errout;
 

From 8b498773c8614a8bd0e54c445c5ebca5f9bb81b7 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:24:57 +0900
Subject: [PATCH 0328/2753] net: fib_rules: Split fib_nl2rule().

We will move RTNL down to fib_nl_newrule() and fib_nl_delrule().

Some operations in fib_nl2rule() require RTNL: fib_default_rule_pref()
and __dev_get_by_name().

Let's split the RTNL parts as fib_nl2rule_rtnl().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-4-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 58 +++++++++++++++++++++++++++++++-------------
 1 file changed, 41 insertions(+), 17 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 87f7311995383..694a8c2884a8f 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -550,30 +550,18 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 	if (tb[FRA_PRIORITY]) {
 		nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]);
 		*user_priority = true;
-	} else {
-		nlrule->pref = fib_default_rule_pref(ops);
 	}
 
 	nlrule->proto = nla_get_u8_default(tb[FRA_PROTOCOL], RTPROT_UNSPEC);
 
 	if (tb[FRA_IIFNAME]) {
-		struct net_device *dev;
-
 		nlrule->iifindex = -1;
 		nla_strscpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
-		dev = __dev_get_by_name(net, nlrule->iifname);
-		if (dev)
-			nlrule->iifindex = dev->ifindex;
 	}
 
 	if (tb[FRA_OIFNAME]) {
-		struct net_device *dev;
-
 		nlrule->oifindex = -1;
 		nla_strscpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
-		dev = __dev_get_by_name(net, nlrule->oifname);
-		if (dev)
-			nlrule->oifindex = dev->ifindex;
 	}
 
 	if (tb[FRA_FWMARK]) {
@@ -615,11 +603,6 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 		}
 
 		nlrule->target = nla_get_u32(tb[FRA_GOTO]);
-		/* Backward jumps are prohibited to avoid endless loops */
-		if (nlrule->target <= nlrule->pref) {
-			NL_SET_ERR_MSG(extack, "Backward goto not supported");
-			goto errout_free;
-		}
 	} else if (nlrule->action == FR_ACT_GOTO) {
 		NL_SET_ERR_MSG(extack, "Missing goto target for action goto");
 		goto errout_free;
@@ -679,6 +662,39 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 	return err;
 }
 
+static int fib_nl2rule_rtnl(struct fib_rule *nlrule,
+			    struct fib_rules_ops *ops,
+			    struct nlattr *tb[],
+			    struct netlink_ext_ack *extack)
+{
+	if (!tb[FRA_PRIORITY])
+		nlrule->pref = fib_default_rule_pref(ops);
+
+	/* Backward jumps are prohibited to avoid endless loops */
+	if (tb[FRA_GOTO] && nlrule->target <= nlrule->pref) {
+		NL_SET_ERR_MSG(extack, "Backward goto not supported");
+		return -EINVAL;
+	}
+
+	if (tb[FRA_IIFNAME]) {
+		struct net_device *dev;
+
+		dev = __dev_get_by_name(nlrule->fr_net, nlrule->iifname);
+		if (dev)
+			nlrule->iifindex = dev->ifindex;
+	}
+
+	if (tb[FRA_OIFNAME]) {
+		struct net_device *dev;
+
+		dev = __dev_get_by_name(nlrule->fr_net, nlrule->oifname);
+		if (dev)
+			nlrule->oifindex = dev->ifindex;
+	}
+
+	return 0;
+}
+
 static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 		       struct nlattr **tb, struct fib_rule *rule)
 {
@@ -801,6 +817,10 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
+	err = fib_nl2rule_rtnl(rule, ops, tb, extack);
+	if (err)
+		goto errout_free;
+
 	if ((nlh->nlmsg_flags & NLM_F_EXCL) &&
 	    rule_exists(ops, frh, tb, rule)) {
 		err = -EEXIST;
@@ -909,6 +929,10 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
+	err = fib_nl2rule_rtnl(nlrule, ops, tb, extack);
+	if (err)
+		goto errout;
+
 	rule = rule_find(ops, frh, tb, nlrule, user_priority);
 	if (!rule) {
 		err = -ENOENT;

From 5a1ccffd30a08f5a2428cd5fbb3ab03e8eb6c66d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:24:58 +0900
Subject: [PATCH 0329/2753] ip: fib_rules: Fetch net from fib_rule in
 fib[46]_rule_configure().

The following patch will not set skb->sk from VRF path.

Let's fetch net from fib_rule->fr_net instead of sock_net(skb->sk)
in fib[46]_rule_configure().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_rules.c  | 4 ++--
 net/ipv6/fib6_rules.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 9517b8667e000..041c46787d941 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -245,9 +245,9 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct nlattr **tb,
 			       struct netlink_ext_ack *extack)
 {
-	struct net *net = sock_net(skb->sk);
+	struct fib4_rule *rule4 = (struct fib4_rule *)rule;
+	struct net *net = rule->fr_net;
 	int err = -EINVAL;
-	struct fib4_rule *rule4 = (struct fib4_rule *) rule;
 
 	if (tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) {
 		NL_SET_ERR_MSG(extack,
diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 67d39114d9a63..40af8fd6efa70 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -399,9 +399,9 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct nlattr **tb,
 			       struct netlink_ext_ack *extack)
 {
+	struct fib6_rule *rule6 = (struct fib6_rule *)rule;
+	struct net *net = rule->fr_net;
 	int err = -EINVAL;
-	struct net *net = sock_net(skb->sk);
-	struct fib6_rule *rule6 = (struct fib6_rule *) rule;
 
 	if (!inet_validate_dscp(frh->tos)) {
 		NL_SET_ERR_MSG(extack,

From a0596c2c63fc9d9ad16d701044293e11d8f97953 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:24:59 +0900
Subject: [PATCH 0330/2753] net: fib_rules: Factorise fib_newrule() and
 fib_delrule().

fib_nl_newrule() / fib_nl_delrule() is the doit() handler for
RTM_NEWRULE / RTM_DELRULE but also called from vrf_newlink().

Currently, we hold RTNL on both paths but will not on the former.

Also, we set dev_net(dev)->rtnl to skb->sk in vrf_fib_rule() because
fib_nl_newrule() / fib_nl_delrule() fetch net as sock_net(skb->sk).

Let's Factorise the two functions and pass net and rtnl_held flag.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/vrf.c       |  6 ++----
 include/net/fib_rules.h |  8 ++++----
 net/core/fib_rules.c    | 36 +++++++++++++++++++++++-------------
 3 files changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index ca81b212a246b..5f21ce1013c42 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1537,14 +1537,12 @@ static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
 
 	nlmsg_end(skb, nlh);
 
-	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
-	skb->sk = dev_net(dev)->rtnl;
 	if (add_it) {
-		err = fib_nl_newrule(skb, nlh, NULL);
+		err = fib_newrule(dev_net(dev), skb, nlh, NULL, true);
 		if (err == -EEXIST)
 			err = 0;
 	} else {
-		err = fib_nl_delrule(skb, nlh, NULL);
+		err = fib_delrule(dev_net(dev), skb, nlh, NULL, true);
 		if (err == -ENOENT)
 			err = 0;
 	}
diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 04383d90a1e38..710caacad9da1 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -178,10 +178,10 @@ int fib_rules_dump(struct net *net, struct notifier_block *nb, int family,
 		   struct netlink_ext_ack *extack);
 unsigned int fib_rules_seq_read(const struct net *net, int family);
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-		   struct netlink_ext_ack *extack);
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-		   struct netlink_ext_ack *extack);
+int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
+		struct netlink_ext_ack *extack, bool rtnl_held);
+int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
+		struct netlink_ext_ack *extack, bool rtnl_held);
 
 INDIRECT_CALLABLE_DECLARE(int fib6_rule_match(struct fib_rule *rule,
 					    struct flowi *fl, int flags));
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 694a8c2884a8f..d68332d9cac61 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -783,15 +783,14 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
 };
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-		   struct netlink_ext_ack *extack)
+int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
+		struct netlink_ext_ack *extack, bool rtnl_held)
 {
-	struct net *net = sock_net(skb->sk);
+	struct fib_rule *rule = NULL, *r, *last = NULL;
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
+	int err = -EINVAL, unresolved = 0;
 	struct fib_rules_ops *ops = NULL;
-	struct fib_rule *rule = NULL, *r, *last = NULL;
 	struct nlattr *tb[FRA_MAX + 1];
-	int err = -EINVAL, unresolved = 0;
 	bool user_priority = false;
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
@@ -893,18 +892,23 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	rules_ops_put(ops);
 	return err;
 }
-EXPORT_SYMBOL_GPL(fib_nl_newrule);
+EXPORT_SYMBOL_GPL(fib_newrule);
 
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
-		   struct netlink_ext_ack *extack)
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
 {
-	struct net *net = sock_net(skb->sk);
+	return fib_newrule(sock_net(skb->sk), skb, nlh, extack, true);
+}
+
+int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
+		struct netlink_ext_ack *extack, bool rtnl_held)
+{
+	struct fib_rule *rule = NULL, *nlrule = NULL;
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	struct fib_rules_ops *ops = NULL;
-	struct fib_rule *rule = NULL, *r, *nlrule = NULL;
 	struct nlattr *tb[FRA_MAX+1];
-	int err = -EINVAL;
 	bool user_priority = false;
+	int err = -EINVAL;
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) {
 		NL_SET_ERR_MSG(extack, "Invalid msg length");
@@ -969,7 +973,7 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	 * current if it is goto rule, have actually been added.
 	 */
 	if (ops->nr_goto_rules > 0) {
-		struct fib_rule *n;
+		struct fib_rule *n, *r;
 
 		n = list_next_entry(rule, list);
 		if (&n->list == &ops->rules_list || n->pref != rule->pref)
@@ -998,7 +1002,13 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 	rules_ops_put(ops);
 	return err;
 }
-EXPORT_SYMBOL_GPL(fib_nl_delrule);
+EXPORT_SYMBOL_GPL(fib_delrule);
+
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	return fib_delrule(sock_net(skb->sk), skb, nlh, extack, true);
+}
 
 static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 					 struct fib_rule *rule)

From 98d3a6f681caad8e89e365be00a11d55176bc328 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:25:00 +0900
Subject: [PATCH 0331/2753] net: fib_rules: Convert RTM_NEWRULE to per-netns
 RTNL.

fib_nl_newrule() is the doit() handler for RTM_NEWRULE but also called
from vrf_newlink().

In the latter case, RTNL is already held and the 4th arg is true.

Let's hold per-netns RTNL in fib_newrule() if rtnl_held is false.

Note that we call fib_rule_get() before releasing per-netns RTNL to call
notify_rule_change() without RTNL and prevent freeing the new rule.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d68332d9cac61..d0995ea9d8523 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -816,6 +816,9 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
+	if (!rtnl_held)
+		rtnl_net_lock(net);
+
 	err = fib_nl2rule_rtnl(rule, ops, tb, extack);
 	if (err)
 		goto errout_free;
@@ -881,12 +884,20 @@ int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rule->tun_id)
 		ip_tunnel_need_metadata();
 
+	fib_rule_get(rule);
+
+	if (!rtnl_held)
+		rtnl_net_unlock(net);
+
 	notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
+	fib_rule_put(rule);
 	flush_route_cache(ops);
 	rules_ops_put(ops);
 	return 0;
 
 errout_free:
+	if (!rtnl_held)
+		rtnl_net_unlock(net);
 	kfree(rule);
 errout:
 	rules_ops_put(ops);
@@ -897,7 +908,7 @@ EXPORT_SYMBOL_GPL(fib_newrule);
 static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
-	return fib_newrule(sock_net(skb->sk), skb, nlh, extack, true);
+	return fib_newrule(sock_net(skb->sk), skb, nlh, extack, false);
 }
 
 int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
@@ -1320,7 +1331,8 @@ static struct pernet_operations fib_rules_net_ops = {
 };
 
 static const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = {
-	{.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule},
+	{.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
 	{.msgtype = RTM_DELRULE, .doit = fib_nl_delrule},
 	{.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule,
 	 .flags = RTNL_FLAG_DUMP_UNLOCKED},

From 1cf770da01120c0a84d53c4dddc57a62d1ca4f96 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:25:01 +0900
Subject: [PATCH 0332/2753] net: fib_rules: Add error_free label in
 fib_delrule().

We will hold RTNL just before calling fib_nl2rule_rtnl() in
fib_delrule() and release it before kfree(nlrule).

Let's add a new rule to make the following change cleaner.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-8-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index d0995ea9d8523..10a7336b8d44f 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -946,23 +946,23 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	err = fib_nl2rule_rtnl(nlrule, ops, tb, extack);
 	if (err)
-		goto errout;
+		goto errout_free;
 
 	rule = rule_find(ops, frh, tb, nlrule, user_priority);
 	if (!rule) {
 		err = -ENOENT;
-		goto errout;
+		goto errout_free;
 	}
 
 	if (rule->flags & FIB_RULE_PERMANENT) {
 		err = -EPERM;
-		goto errout;
+		goto errout_free;
 	}
 
 	if (ops->delete) {
 		err = ops->delete(rule);
 		if (err)
-			goto errout;
+			goto errout_free;
 	}
 
 	if (rule->tun_id)
@@ -1008,8 +1008,9 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 	kfree(nlrule);
 	return 0;
 
-errout:
+errout_free:
 	kfree(nlrule);
+errout:
 	rules_ops_put(ops);
 	return err;
 }

From 88b9cfca8d7735b0e8c809241365577f07c52cb2 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Fri, 7 Feb 2025 16:25:02 +0900
Subject: [PATCH 0333/2753] net: fib_rules: Convert RTM_DELRULE to per-netns
 RTNL.

fib_nl_delrule() is the doit() handler for RTM_DELRULE but also called
from vrf_newlink() in case something fails in vrf_add_fib_rules().

In the latter case, RTNL is already held and the 4th arg is true.

Let's hold per-netns RTNL in fib_delrule() if rtnl_held is false.

Now we can place ASSERT_RTNL_NET() in call_fib_rule_notifiers().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250207072502.87775-9-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 23 ++++++++++++++++-------
 1 file changed, 16 insertions(+), 7 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 10a7336b8d44f..5045affeac78d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -371,7 +371,8 @@ static int call_fib_rule_notifiers(struct net *net,
 		.rule = rule,
 	};
 
-	ASSERT_RTNL();
+	ASSERT_RTNL_NET(net);
+
 	/* Paired with READ_ONCE() in fib_rules_seq() */
 	WRITE_ONCE(ops->fib_rules_seq, ops->fib_rules_seq + 1);
 	return call_fib_notifiers(net, event_type, &info.info);
@@ -944,6 +945,9 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto errout;
 
+	if (!rtnl_held)
+		rtnl_net_lock(net);
+
 	err = fib_nl2rule_rtnl(nlrule, ops, tb, extack);
 	if (err)
 		goto errout_free;
@@ -998,10 +1002,12 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 		}
 	}
 
-	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops,
-				NULL);
-	notify_rule_change(RTM_DELRULE, rule, ops, nlh,
-			   NETLINK_CB(skb).portid);
+	call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, NULL);
+
+	if (!rtnl_held)
+		rtnl_net_unlock(net);
+
+	notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
 	fib_rule_put(rule);
 	flush_route_cache(ops);
 	rules_ops_put(ops);
@@ -1009,6 +1015,8 @@ int fib_delrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,
 	return 0;
 
 errout_free:
+	if (!rtnl_held)
+		rtnl_net_unlock(net);
 	kfree(nlrule);
 errout:
 	rules_ops_put(ops);
@@ -1019,7 +1027,7 @@ EXPORT_SYMBOL_GPL(fib_delrule);
 static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {
-	return fib_delrule(sock_net(skb->sk), skb, nlh, extack, true);
+	return fib_delrule(sock_net(skb->sk), skb, nlh, extack, false);
 }
 
 static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
@@ -1334,7 +1342,8 @@ static struct pernet_operations fib_rules_net_ops = {
 static const struct rtnl_msg_handler fib_rules_rtnl_msg_handlers[] __initconst = {
 	{.msgtype = RTM_NEWRULE, .doit = fib_nl_newrule,
 	 .flags = RTNL_FLAG_DOIT_PERNET},
-	{.msgtype = RTM_DELRULE, .doit = fib_nl_delrule},
+	{.msgtype = RTM_DELRULE, .doit = fib_nl_delrule,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
 	{.msgtype = RTM_GETRULE, .dumpit = fib_nl_dumprule,
 	 .flags = RTNL_FLAG_DUMP_UNLOCKED},
 };

From a980da54b6a457e8d9ceb02d7c2ba6a47fc3d502 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 7 Feb 2025 10:31:19 -0800
Subject: [PATCH 0334/2753] selftests: drv-net: remove an unnecessary libmnl
 include

ncdevmem doesn't need libmnl, remove the unnecessary include.

Since YNL doesn't depend on libmnl either, any more, it's actually
possible to build selftests without having libmnl installed.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250207183119.1721424-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/ncdevmem.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/ncdevmem.c b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
index 19a6969643f46..2bf14ac2b8c62 100644
--- a/tools/testing/selftests/drivers/net/hw/ncdevmem.c
+++ b/tools/testing/selftests/drivers/net/hw/ncdevmem.c
@@ -50,7 +50,6 @@
 #include <linux/memfd.h>
 #include <linux/dma-buf.h>
 #include <linux/udmabuf.h>
-#include <libmnl/libmnl.h>
 #include <linux/types.h>
 #include <linux/netlink.h>
 #include <linux/genetlink.h>

From 29604bc2aaed5a8f5264018b29d73cb4a7a34960 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 7 Feb 2025 10:41:39 -0800
Subject: [PATCH 0335/2753] selftests: drv-net: factor out a DrvEnv base class

We have separate Env classes for local tests and tests with a remote
endpoint. Make it easier to share the code by creating a base class.
Make env loading a method of this class.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250207184140.1730466-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../selftests/drivers/net/lib/py/env.py       | 63 ++++++++++---------
 1 file changed, 35 insertions(+), 28 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 987e452d3a457..2f17880e411d6 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -10,38 +10,46 @@
 from .remote import Remote
 
 
-def _load_env_file(src_path):
-    env = os.environ.copy()
-
-    src_dir = Path(src_path).parent.resolve()
-    if not (src_dir / "net.config").exists():
+class NetDrvEnvBase:
+    """
+    Base class for a NIC / host envirnoments
+    """
+    def __init__(self, src_path):
+        self.src_path = src_path
+        self.env = self._load_env_file()
+
+    def _load_env_file(self):
+        env = os.environ.copy()
+
+        src_dir = Path(self.src_path).parent.resolve()
+        if not (src_dir / "net.config").exists():
+            return ksft_setup(env)
+
+        with open((src_dir / "net.config").as_posix(), 'r') as fp:
+            for line in fp.readlines():
+                full_file = line
+                # Strip comments
+                pos = line.find("#")
+                if pos >= 0:
+                    line = line[:pos]
+                line = line.strip()
+                if not line:
+                    continue
+                pair = line.split('=', maxsplit=1)
+                if len(pair) != 2:
+                    raise Exception("Can't parse configuration line:", full_file)
+                env[pair[0]] = pair[1]
         return ksft_setup(env)
 
-    with open((src_dir / "net.config").as_posix(), 'r') as fp:
-        for line in fp.readlines():
-            full_file = line
-            # Strip comments
-            pos = line.find("#")
-            if pos >= 0:
-                line = line[:pos]
-            line = line.strip()
-            if not line:
-                continue
-            pair = line.split('=', maxsplit=1)
-            if len(pair) != 2:
-                raise Exception("Can't parse configuration line:", full_file)
-            env[pair[0]] = pair[1]
-    return ksft_setup(env)
-
-
-class NetDrvEnv:
+
+class NetDrvEnv(NetDrvEnvBase):
     """
     Class for a single NIC / host env, with no remote end
     """
     def __init__(self, src_path, **kwargs):
-        self._ns = None
+        super().__init__(src_path)
 
-        self.env = _load_env_file(src_path)
+        self._ns = None
 
         if 'NETIF' in self.env:
             self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0]
@@ -68,7 +76,7 @@ def __del__(self):
             self._ns = None
 
 
-class NetDrvEpEnv:
+class NetDrvEpEnv(NetDrvEnvBase):
     """
     Class for an environment with a local device and "remote endpoint"
     which can be used to send traffic in.
@@ -82,8 +90,7 @@ class NetDrvEpEnv:
     nsim_v6_pfx = "2001:db8::"
 
     def __init__(self, src_path, nsim_test=None):
-
-        self.env = _load_env_file(src_path)
+        super().__init__(src_path)
 
         self._stats_settle_time = None
 

From 3337064f4204572a97f701b936436336e37b99d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 7 Feb 2025 10:41:40 -0800
Subject: [PATCH 0336/2753] selftests: drv-net: add helper for path resolution

Refering to C binaries from Python code is going to be a common
need. Add a helper to convert from path in relation to the test.
Meaning, if the test is in the same directory as the binary, the
call would be simply: cfg.rpath("binary").

The helper name "rpath" is not great. I can't think of a better
name that would be accurate yet concise.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250207184140.1730466-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hw/csum.py    |  2 +-
 tools/testing/selftests/drivers/net/lib/py/env.py | 12 ++++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index cb40497faee44..cd477f3440caf 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -100,7 +100,7 @@ def main() -> None:
     with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
         check_nic_features(cfg)
 
-        cfg.bin_local = path.abspath(path.dirname(__file__) + "/../../../net/lib/csum")
+        cfg.bin_local = cfg.rpath("../../../net/lib/csum")
         cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
 
         cases = []
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 2f17880e411d6..886b4904613c3 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -18,6 +18,18 @@ def __init__(self, src_path):
         self.src_path = src_path
         self.env = self._load_env_file()
 
+    def rpath(self, path):
+        """
+        Get an absolute path to a file based on a path relative to the directory
+        containing the test which constructed env.
+
+        For example, if the test.py is in the same directory as
+        a binary (built from helper.c), the test can use env.rpath("helper")
+        to get the absolute path to the binary
+        """
+        src_dir = Path(self.src_path).parent.resolve()
+        return (src_dir / path).as_posix()
+
     def _load_env_file(self):
         env = os.environ.copy()
 

From 907dd32b4a8aa7fedc2ef1867a6c3a1033738bcb Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Fri, 7 Feb 2025 19:00:44 +0100
Subject: [PATCH 0337/2753] mlxsw: Enable Tx checksum offload

The device is able to checksum plain TCP / UDP packets over IPv4 / IPv6
when the 'ipcs' bit in the send descriptor is set. Advertise support for
the 'NETIF_F_IP{,6}_CSUM' features in net devices registered by the
driver and VLAN uppers and set the 'ipcs' bit when the stack requests Tx
checksum offload.

Note that the device also calculates the IPv4 checksum, but it first
zeroes the current checksum so there should not be any difference
compared to the checksum calculated by the kernel.

On SN5600 (Spectrum-4) there is about 10% improvement in Tx packet rate
with 1400 byte packets when using pktgen.

Tested on Spectrum-{1,2,3,4} with all the combinations of IPv4 / IPv6,
TCP / UDP, with and without VLAN.

Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/8dc86c95474ce10572a0fa83b8adb0259558e982.1738950446.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlxsw/pci.c      | 2 ++
 drivers/net/ethernet/mellanox/mlxsw/pci_hw.h   | 5 +++++
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c | 6 ++++--
 3 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 5b44c931b6604..058dcabfaa2e4 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -2214,6 +2214,8 @@ static int mlxsw_pci_skb_transmit(void *bus_priv, struct sk_buff *skb,
 	for (i++; i < MLXSW_PCI_WQE_SG_ENTRIES; i++)
 		mlxsw_pci_wqe_byte_count_set(wqe, i, 0);
 
+	mlxsw_pci_wqe_ipcs_set(wqe, skb->ip_summed == CHECKSUM_PARTIAL);
+
 	/* Everything is set up, ring producer doorbell to get HW going */
 	q->producer_counter++;
 	mlxsw_pci_queue_doorbell_producer_ring(mlxsw_pci, q);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
index 6bed495dcf0ff..7fa94e5828deb 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h
@@ -90,6 +90,11 @@ MLXSW_ITEM32(pci, wqe, lp, 0x00, 30, 1);
  */
 MLXSW_ITEM32(pci, wqe, type, 0x00, 23, 4);
 
+/* pci_wqe_ipcs
+ * Calculate IPv4 and TCP / UDP checksums.
+ */
+MLXSW_ITEM32(pci, wqe, ipcs, 0x00, 14, 1);
+
 /* pci_wqe_byte_count
  * Size of i-th scatter/gather entry, 0 if entry is unused.
  */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index d714311fd884e..1f8362788c756 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1574,8 +1574,10 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 	netif_carrier_off(dev);
 
 	dev->features |= NETIF_F_SG | NETIF_F_HW_VLAN_CTAG_FILTER |
-			 NETIF_F_HW_TC;
-	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK;
+			 NETIF_F_HW_TC | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->hw_features |= NETIF_F_HW_TC | NETIF_F_LOOPBACK |
+			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
 	dev->netns_local = true;
 

From 67800d296191d0a9bde0a7776f99ca1ddfa0fc26 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cs=C3=B3k=C3=A1s=2C=20Bence?= <csokas.bence@prolan.hu>
Date: Fri, 7 Feb 2025 13:12:55 +0100
Subject: [PATCH 0338/2753] net: fec: Refactor MAC reset to function
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The core is reset both in `fec_restart()` (called on link-up) and
`fec_stop()` (going to sleep, driver remove etc.). These two functions
had their separate implementations, which was at first only a register
write and a `udelay()` (and the accompanying block comment). However,
since then we got soft-reset (MAC disable) and Wake-on-LAN support, which
meant that these implementations diverged, often causing bugs.

For instance, as of now, `fec_stop()` does not check for
`FEC_QUIRK_NO_HARD_RESET`, meaning the MII/RMII mode is cleared on eg.
a PM power-down event; and `fec_restart()` missed the refactor renaming
the "magic" constant `1` to `FEC_ECR_RESET`.

To harmonize current implementations, and eliminate this source of
potential future bugs, refactor implementation to a common function.

Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Csókás, Bence <csokas.bence@prolan.hu>
Link: https://patch.msgid.link/20250207121255.161146-2-csokas.bence@prolan.hu
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/freescale/fec_main.c | 52 +++++++++++------------
 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index f7c4ce8e9a265..a86cfebedaa8b 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -1093,6 +1093,29 @@ static void fec_enet_enable_ring(struct net_device *ndev)
 	}
 }
 
+/* Whack a reset.  We should wait for this.
+ * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
+ * instead of reset MAC itself.
+ */
+static void fec_ctrl_reset(struct fec_enet_private *fep, bool allow_wol)
+{
+	u32 val;
+
+	if (!allow_wol || !(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
+		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
+		    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
+			writel(0, fep->hwp + FEC_ECNTRL);
+		} else {
+			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
+			udelay(10);
+		}
+	} else {
+		val = readl(fep->hwp + FEC_ECNTRL);
+		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
+		writel(val, fep->hwp + FEC_ECNTRL);
+	}
+}
+
 /*
  * This function is called to start or restart the FEC during a link
  * change, transmit timeout, or to reconfigure the FEC.  The network
@@ -1109,17 +1132,7 @@ fec_restart(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES ||
-	    ((fep->quirks & FEC_QUIRK_NO_HARD_RESET) && fep->link)) {
-		writel(0, fep->hwp + FEC_ECNTRL);
-	} else {
-		writel(1, fep->hwp + FEC_ECNTRL);
-		udelay(10);
-	}
+	fec_ctrl_reset(fep, false);
 
 	/*
 	 * enet-mac reset will reset mac address registers too,
@@ -1373,22 +1386,7 @@ fec_stop(struct net_device *ndev)
 	if (fep->bufdesc_ex)
 		fec_ptp_save_state(fep);
 
-	/* Whack a reset.  We should wait for this.
-	 * For i.MX6SX SOC, enet use AXI bus, we use disable MAC
-	 * instead of reset MAC itself.
-	 */
-	if (!(fep->wol_flag & FEC_WOL_FLAG_SLEEP_ON)) {
-		if (fep->quirks & FEC_QUIRK_HAS_MULTI_QUEUES) {
-			writel(0, fep->hwp + FEC_ECNTRL);
-		} else {
-			writel(FEC_ECR_RESET, fep->hwp + FEC_ECNTRL);
-			udelay(10);
-		}
-	} else {
-		val = readl(fep->hwp + FEC_ECNTRL);
-		val |= (FEC_ECR_MAGICEN | FEC_ECR_SLEEP);
-		writel(val, fep->hwp + FEC_ECNTRL);
-	}
+	fec_ctrl_reset(fep, true);
 	writel(fep->phy_speed, fep->hwp + FEC_MII_SPEED);
 	writel(FEC_DEFAULT_IMASK, fep->hwp + FEC_IMASK);
 

From eb4e17a1d915d3c550e5a58c4bf370659dbe0dc8 Mon Sep 17 00:00:00 2001
From: Yuyang Huang <yuyanghuang@google.com>
Date: Fri, 7 Feb 2025 20:08:35 +0900
Subject: [PATCH 0339/2753] netlink: support dumping IPv4 multicast addresses
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extended RTM_GETMULTICAST to support dumping joined IPv4 multicast
addresses, in addition to the existing IPv6 functionality. This allows
userspace applications to retrieve both IPv4 and IPv6 multicast
addresses through similar netlink command and then monitor future
changes by registering to RTNLGRP_IPV4_MCADDR and RTNLGRP_IPV6_MCADDR.

Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Yuyang Huang <yuyanghuang@google.com>
Link: https://patch.msgid.link/20250207110836.2407224-1-yuyanghuang@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/devinet.c       | 77 ++++++++++++++++++++++++++++++++--------
 net/ipv4/igmp.c          | 14 +++++---
 net/ipv4/igmp_internal.h | 17 +++++++++
 3 files changed, 90 insertions(+), 18 deletions(-)
 create mode 100644 net/ipv4/igmp_internal.h

diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index c8b3cf5fba4c0..f51e026d7a843 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -46,6 +46,7 @@
 #include <linux/notifier.h>
 #include <linux/inetdevice.h>
 #include <linux/igmp.h>
+#include "igmp_internal.h"
 #include <linux/slab.h>
 #include <linux/hash.h>
 #ifdef CONFIG_SYSCTL
@@ -107,15 +108,6 @@ static const struct nla_policy ifa_ipv4_policy[IFA_MAX+1] = {
 	[IFA_PROTO]		= { .type = NLA_U8 },
 };
 
-struct inet_fill_args {
-	u32 portid;
-	u32 seq;
-	int event;
-	unsigned int flags;
-	int netnsid;
-	int ifindex;
-};
-
 #define IN4_ADDR_HSIZE_SHIFT	8
 #define IN4_ADDR_HSIZE		(1U << IN4_ADDR_HSIZE_SHIFT)
 
@@ -1846,9 +1838,38 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 	return 0;
 }
 
-static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb,
-			    struct netlink_callback *cb, int *s_ip_idx,
-			    struct inet_fill_args *fillargs)
+static int in_dev_dump_ifmcaddr(struct in_device *in_dev, struct sk_buff *skb,
+				struct netlink_callback *cb, int *s_ip_idx,
+				struct inet_fill_args *fillargs)
+{
+	struct ip_mc_list *im;
+	int ip_idx = 0;
+	int err;
+
+	for (im = rcu_dereference(in_dev->mc_list);
+	     im;
+	     im = rcu_dereference(im->next_rcu)) {
+		if (ip_idx < *s_ip_idx) {
+			ip_idx++;
+			continue;
+		}
+		err = inet_fill_ifmcaddr(skb, in_dev->dev, im, fillargs);
+		if (err < 0)
+			goto done;
+
+		nl_dump_check_consistent(cb, nlmsg_hdr(skb));
+		ip_idx++;
+	}
+	err = 0;
+	ip_idx = 0;
+done:
+	*s_ip_idx = ip_idx;
+	return err;
+}
+
+static int in_dev_dump_ifaddr(struct in_device *in_dev, struct sk_buff *skb,
+			      struct netlink_callback *cb, int *s_ip_idx,
+			      struct inet_fill_args *fillargs)
 {
 	struct in_ifaddr *ifa;
 	int ip_idx = 0;
@@ -1874,6 +1895,21 @@ static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb,
 	return err;
 }
 
+static int in_dev_dump_addr(struct in_device *in_dev, struct sk_buff *skb,
+			    struct netlink_callback *cb, int *s_ip_idx,
+			    struct inet_fill_args *fillargs)
+{
+	switch (fillargs->event) {
+	case RTM_NEWADDR:
+		return in_dev_dump_ifaddr(in_dev, skb, cb, s_ip_idx, fillargs);
+	case RTM_GETMULTICAST:
+		return in_dev_dump_ifmcaddr(in_dev, skb, cb, s_ip_idx,
+					    fillargs);
+	default:
+		return -EINVAL;
+	}
+}
+
 /* Combine dev_addr_genid and dev_base_seq to detect changes.
  */
 static u32 inet_base_seq(const struct net *net)
@@ -1889,13 +1925,14 @@ static u32 inet_base_seq(const struct net *net)
 	return res;
 }
 
-static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
+static int inet_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
+			  int event)
 {
 	const struct nlmsghdr *nlh = cb->nlh;
 	struct inet_fill_args fillargs = {
 		.portid = NETLINK_CB(cb->skb).portid,
 		.seq = nlh->nlmsg_seq,
-		.event = RTM_NEWADDR,
+		.event = event,
 		.flags = NLM_F_MULTI,
 		.netnsid = -1,
 	};
@@ -1949,6 +1986,16 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	return err;
 }
 
+static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return inet_dump_addr(skb, cb, RTM_NEWADDR);
+}
+
+static int inet_dump_ifmcaddr(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return inet_dump_addr(skb, cb, RTM_GETMULTICAST);
+}
+
 static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,
 		      u32 portid)
 {
@@ -2845,6 +2892,8 @@ static const struct rtnl_msg_handler devinet_rtnl_msg_handlers[] __initconst = {
 	{.protocol = PF_INET, .msgtype = RTM_GETNETCONF,
 	 .doit = inet_netconf_get_devconf, .dumpit = inet_netconf_dump_devconf,
 	 .flags = RTNL_FLAG_DOIT_UNLOCKED | RTNL_FLAG_DUMP_UNLOCKED},
+	{.owner = THIS_MODULE, .protocol = PF_INET, .msgtype = RTM_GETMULTICAST,
+	 .dumpit = inet_dump_ifmcaddr, .flags = RTNL_FLAG_DUMP_UNLOCKED},
 };
 
 void __init devinet_init(void)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 3da126cea884d..2c394c364cb9a 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -81,6 +81,7 @@
 #include <linux/skbuff.h>
 #include <linux/inetdevice.h>
 #include <linux/igmp.h>
+#include "igmp_internal.h"
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/times.h>
@@ -1432,14 +1433,16 @@ static void ip_mc_hash_remove(struct in_device *in_dev,
 	*mc_hash = im->next_hash;
 }
 
-static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev,
-			      const struct ip_mc_list *im, int event)
+int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev,
+		       const struct ip_mc_list *im,
+		       struct inet_fill_args *args)
 {
 	struct ifa_cacheinfo ci;
 	struct ifaddrmsg *ifm;
 	struct nlmsghdr *nlh;
 
-	nlh = nlmsg_put(skb, 0, 0, event, sizeof(struct ifaddrmsg), 0);
+	nlh = nlmsg_put(skb, args->portid, args->seq, args->event,
+			sizeof(struct ifaddrmsg), args->flags);
 	if (!nlh)
 		return -EMSGSIZE;
 
@@ -1468,6 +1471,9 @@ static int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev,
 static void inet_ifmcaddr_notify(struct net_device *dev,
 				 const struct ip_mc_list *im, int event)
 {
+	struct inet_fill_args fillargs = {
+		.event = event,
+	};
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOMEM;
@@ -1479,7 +1485,7 @@ static void inet_ifmcaddr_notify(struct net_device *dev,
 	if (!skb)
 		goto error;
 
-	err = inet_fill_ifmcaddr(skb, dev, im, event);
+	err = inet_fill_ifmcaddr(skb, dev, im, &fillargs);
 	if (err < 0) {
 		WARN_ON_ONCE(err == -EMSGSIZE);
 		nlmsg_free(skb);
diff --git a/net/ipv4/igmp_internal.h b/net/ipv4/igmp_internal.h
new file mode 100644
index 0000000000000..0a1bcc8ec8e15
--- /dev/null
+++ b/net/ipv4/igmp_internal.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IGMP_INTERNAL_H
+#define _LINUX_IGMP_INTERNAL_H
+
+struct inet_fill_args {
+	u32 portid;
+	u32 seq;
+	int event;
+	unsigned int flags;
+	int netnsid;
+	int ifindex;
+};
+
+int inet_fill_ifmcaddr(struct sk_buff *skb, struct net_device *dev,
+		       const struct ip_mc_list *im,
+		       struct inet_fill_args *args);
+#endif

From 4f280376e5318f17f7388999f9a0098ccaae931d Mon Sep 17 00:00:00 2001
From: Yuyang Huang <yuyanghuang@google.com>
Date: Fri, 7 Feb 2025 20:08:36 +0900
Subject: [PATCH 0340/2753] selftests/net: Add selftest for IPv4
 RTM_GETMULTICAST support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This change introduces a new selftest case to verify the functionality
of dumping IPv4 multicast addresses using the RTM_GETMULTICAST netlink
message. The test utilizes the ynl library to interact with the
netlink interface and validate that the kernel correctly reports the
joined IPv4 multicast addresses.

To run the test, execute the following command:

$ vng -v --user root --cpus 16 -- \
    make -C tools/testing/selftests TARGETS=net \
    TEST_PROGS=rtnetlink.py TEST_GEN_PROGS="" run_tests

Cc: Maciej Żenczykowski <maze@google.com>
Cc: Lorenzo Colitti <lorenzo@google.com>
Signed-off-by: Yuyang Huang <yuyanghuang@google.com>
Link: https://patch.msgid.link/20250207110836.2407224-2-yuyanghuang@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/rt_addr.yaml      | 23 ++++++++++++++
 tools/testing/selftests/net/Makefile          |  1 +
 .../testing/selftests/net/lib/py/__init__.py  |  2 +-
 tools/testing/selftests/net/lib/py/ynl.py     |  4 +++
 tools/testing/selftests/net/rtnetlink.py      | 30 +++++++++++++++++++
 5 files changed, 59 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/net/rtnetlink.py

diff --git a/Documentation/netlink/specs/rt_addr.yaml b/Documentation/netlink/specs/rt_addr.yaml
index cbee1cedb177c..5dd5469044c79 100644
--- a/Documentation/netlink/specs/rt_addr.yaml
+++ b/Documentation/netlink/specs/rt_addr.yaml
@@ -168,6 +168,29 @@ operations:
         reply:
           value: 20
           attributes: *ifaddr-all
+    -
+      name: getmaddrs
+      doc: Get / dump IPv4/IPv6 multicast addresses.
+      attribute-set: addr-attrs
+      fixed-header: ifaddrmsg
+      do:
+        request:
+          value: 58
+          attributes:
+            - ifa-family
+            - ifa-index
+        reply:
+          value: 58
+          attributes: &mcaddr-attrs
+            - ifa-multicast
+            - ifa-cacheinfo
+      dump:
+        request:
+          value: 58
+            - ifa-family
+        reply:
+          value: 58
+          attributes: *mcaddr-attrs
 
 mcast-groups:
   list:
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 73ee88d6b0430..e2f03211f9b38 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -36,6 +36,7 @@ TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
 TEST_PROGS += netns-name.sh
 TEST_PROGS += nl_netdev.py
+TEST_PROGS += rtnetlink.py
 TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt4_l3vpn_test.sh
 TEST_PROGS += srv6_end_dt6_l3vpn_test.sh
diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 54d8f5eba8101..7294578593165 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -5,5 +5,5 @@
 from .netns import NetNS
 from .nsim import *
 from .utils import *
-from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily
+from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
 from .ynl import NetshaperFamily
diff --git a/tools/testing/selftests/net/lib/py/ynl.py b/tools/testing/selftests/net/lib/py/ynl.py
index ad1e36baee2a1..8986c584cb371 100644
--- a/tools/testing/selftests/net/lib/py/ynl.py
+++ b/tools/testing/selftests/net/lib/py/ynl.py
@@ -42,6 +42,10 @@ def __init__(self, recv_size=0):
         super().__init__((SPEC_PATH / Path('rt_link.yaml')).as_posix(),
                          schema='', recv_size=recv_size)
 
+class RtnlAddrFamily(YnlFamily):
+    def __init__(self, recv_size=0):
+        super().__init__((SPEC_PATH / Path('rt_addr.yaml')).as_posix(),
+                         schema='', recv_size=recv_size)
 
 class NetdevFamily(YnlFamily):
     def __init__(self, recv_size=0):
diff --git a/tools/testing/selftests/net/rtnetlink.py b/tools/testing/selftests/net/rtnetlink.py
new file mode 100755
index 0000000000000..80950888800be
--- /dev/null
+++ b/tools/testing/selftests/net/rtnetlink.py
@@ -0,0 +1,30 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_exit, ksft_run, ksft_ge, RtnlAddrFamily
+import socket
+
+IPV4_ALL_HOSTS_MULTICAST = b'\xe0\x00\x00\x01'
+
+def dump_mcaddr_check(rtnl: RtnlAddrFamily) -> None:
+    """
+    Verify that at least one interface has the IPv4 all-hosts multicast address.
+    At least the loopback interface should have this address.
+    """
+
+    addresses = rtnl.getmaddrs({"ifa-family": socket.AF_INET}, dump=True)
+
+    all_host_multicasts = [
+        addr for addr in addresses if addr['ifa-multicast'] == IPV4_ALL_HOSTS_MULTICAST
+    ]
+
+    ksft_ge(len(all_host_multicasts), 1,
+            "No interface found with the IPv4 all-hosts multicast address")
+
+def main() -> None:
+    rtnl = RtnlAddrFamily()
+    ksft_run([dump_mcaddr_check], args=(rtnl, ))
+    ksft_exit()
+
+if __name__ == "__main__":
+    main()

From fa5b663bbf0bb5ed339761d5b82ca7137a571b25 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:31:57 +0000
Subject: [PATCH 0341/2753] wifi: iwlwifi: dvm: Remove unused
 iwl_rx_ant_restriction

iwl_rx_ant_restriction() was added in 2009 by
commit 46f9381aa3fb ("iwlwifi: Thermal Throttling Management - part 2")
but never used.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-2-linux@treblig.org
---
 drivers/net/wireless/intel/iwlwifi/dvm/tt.c | 11 -----------
 drivers/net/wireless/intel/iwlwifi/dvm/tt.h |  1 -
 2 files changed, 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tt.c b/drivers/net/wireless/intel/iwlwifi/dvm/tt.c
index 43e8d04d5a8b2..e1d78550e4439 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tt.c
@@ -124,17 +124,6 @@ enum iwl_antenna_ok iwl_tx_ant_restriction(struct iwl_priv *priv)
 	return restriction->tx_stream;
 }
 
-enum iwl_antenna_ok iwl_rx_ant_restriction(struct iwl_priv *priv)
-{
-	struct iwl_tt_mgmt *tt = &priv->thermal_throttle;
-	struct iwl_tt_restriction *restriction;
-
-	if (!priv->thermal_throttle.advanced_tt)
-		return IWL_ANT_OK_MULTI;
-	restriction = tt->restriction + tt->state;
-	return restriction->rx_stream;
-}
-
 #define CT_KILL_EXIT_DURATION (5)	/* 5 seconds duration */
 #define CT_KILL_WAITING_DURATION (300)	/* 300ms duration */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/tt.h b/drivers/net/wireless/intel/iwlwifi/dvm/tt.h
index 4af792d41dce6..198f934a0d166 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/tt.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/tt.h
@@ -100,7 +100,6 @@ u8 iwl_tt_current_power_mode(struct iwl_priv *priv);
 bool iwl_tt_is_low_power_state(struct iwl_priv *priv);
 bool iwl_ht_enabled(struct iwl_priv *priv);
 enum iwl_antenna_ok iwl_tx_ant_restriction(struct iwl_priv *priv);
-enum iwl_antenna_ok iwl_rx_ant_restriction(struct iwl_priv *priv);
 void iwl_tt_enter_ct_kill(struct iwl_priv *priv);
 void iwl_tt_exit_ct_kill(struct iwl_priv *priv);
 void iwl_tt_handler(struct iwl_priv *priv);

From 63e616649c901e3a123f08500abbde946ab4ea55 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:31:58 +0000
Subject: [PATCH 0342/2753] wifi: iwlwifi: mvm: Remove unused
 iwl_mvm_rx_missed_vap_notif

iwl_mvm_rx_missed_vap_notif() was added in 2019 by
commit 449a29d0fead ("iwlwifi: mvm: add notification for missed VAP")

but hasn't been used.

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-3-linux@treblig.org
---
 .../net/wireless/intel/iwlwifi/mvm/mac-ctxt.c | 23 -------------------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  2 --
 2 files changed, 25 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
index 6b06732441c35..bec18d197f310 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c
@@ -1960,26 +1960,3 @@ void iwl_mvm_channel_switch_error_notif(struct iwl_mvm *mvm,
 		ieee80211_channel_switch_disconnect(vif);
 	rcu_read_unlock();
 }
-
-void iwl_mvm_rx_missed_vap_notif(struct iwl_mvm *mvm,
-				 struct iwl_rx_cmd_buffer *rxb)
-{
-	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_missed_vap_notif *mb = (void *)pkt->data;
-	struct ieee80211_vif *vif;
-	u32 id = le32_to_cpu(mb->mac_id);
-
-	IWL_DEBUG_INFO(mvm,
-		       "missed_vap notify mac_id=%u, num_beacon_intervals_elapsed=%u, profile_periodicity=%u\n",
-		       le32_to_cpu(mb->mac_id),
-		       mb->num_beacon_intervals_elapsed,
-		       mb->profile_periodicity);
-
-	rcu_read_lock();
-
-	vif = iwl_mvm_rcu_dereference_vif_id(mvm, id, true);
-	if (vif)
-		iwl_mvm_connection_loss(mvm, vif, "missed vap beacon");
-
-	rcu_read_unlock();
-}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index ee769da72e68c..9f0db96ac320a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2095,8 +2095,6 @@ void iwl_mvm_mac_ctxt_recalc_tsf_id(struct iwl_mvm *mvm,
 				    struct ieee80211_vif *vif);
 void iwl_mvm_probe_resp_data_notif(struct iwl_mvm *mvm,
 				   struct iwl_rx_cmd_buffer *rxb);
-void iwl_mvm_rx_missed_vap_notif(struct iwl_mvm *mvm,
-				 struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_channel_switch_start_notif(struct iwl_mvm *mvm,
 					struct iwl_rx_cmd_buffer *rxb);
 void iwl_mvm_channel_switch_error_notif(struct iwl_mvm *mvm,

From 7efd4b61307d99f0fc8c01152af270731c70c2fe Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:31:59 +0000
Subject: [PATCH 0343/2753] wifi: iwlwifi: mvm: Remove unused
 iwl_mvm_ftm_*_add_pasn_sta functions

iwl_mvm_ftm_respoder_add_pasn_sta() and
iwl_mvm_ftm_resp_remove_pasn_sta() were added in 2020 by
commit be82ecd3a5c8 ("iwlwifi: mvm: add an option to add PASN station")
but have remained unused.

Remove them.

After that removal iwl_mvm_add_pasn_sta() is now unused.
Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-4-linux@treblig.org
---
 .../intel/iwlwifi/mvm/ftm-responder.c         | 86 -------------------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  6 --
 drivers/net/wireless/intel/iwlwifi/mvm/sta.c  | 61 -------------
 drivers/net/wireless/intel/iwlwifi/mvm/sta.h  |  4 -
 4 files changed, 157 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
index e6e468e81ab3a..83f6e508a094c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-responder.c
@@ -324,92 +324,6 @@ static void iwl_mvm_resp_del_pasn_sta(struct iwl_mvm *mvm,
 	kfree(sta);
 }
 
-int iwl_mvm_ftm_respoder_add_pasn_sta(struct iwl_mvm *mvm,
-				      struct ieee80211_vif *vif,
-				      u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
-				      u8 *hltk, u32 hltk_len)
-{
-	int ret;
-	struct iwl_mvm_pasn_sta *sta = NULL;
-	struct iwl_mvm_pasn_hltk_data hltk_data = {
-		.addr = addr,
-		.hltk = hltk,
-	};
-	struct iwl_mvm_pasn_hltk_data *hltk_data_ptr = NULL;
-
-	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mvm->fw,
-					   WIDE_ID(LOCATION_GROUP, TOF_RESPONDER_DYN_CONFIG_CMD),
-					   2);
-
-	lockdep_assert_held(&mvm->mutex);
-
-	if (cmd_ver < 3) {
-		IWL_ERR(mvm, "Adding PASN station not supported by FW\n");
-		return -EOPNOTSUPP;
-	}
-
-	if ((!hltk || !hltk_len) && (!tk || !tk_len)) {
-		IWL_ERR(mvm, "TK and HLTK not set\n");
-		return -EINVAL;
-	}
-
-	if (hltk && hltk_len) {
-		if (!fw_has_capa(&mvm->fw->ucode_capa,
-				 IWL_UCODE_TLV_CAPA_SECURE_LTF_SUPPORT)) {
-			IWL_ERR(mvm, "No support for secure LTF measurement\n");
-			return -EINVAL;
-		}
-
-		hltk_data.cipher = iwl_mvm_cipher_to_location_cipher(cipher);
-		if (hltk_data.cipher == IWL_LOCATION_CIPHER_INVALID) {
-			IWL_ERR(mvm, "invalid cipher: %u\n", cipher);
-			return -EINVAL;
-		}
-
-		hltk_data_ptr = &hltk_data;
-	}
-
-	if (tk && tk_len) {
-		sta = kzalloc(sizeof(*sta) + tk_len, GFP_KERNEL);
-		if (!sta)
-			return -ENOBUFS;
-
-		ret = iwl_mvm_add_pasn_sta(mvm, vif, &sta->int_sta, addr,
-					   cipher, tk, tk_len, &sta->keyconf);
-		if (ret) {
-			kfree(sta);
-			return ret;
-		}
-
-		memcpy(sta->addr, addr, ETH_ALEN);
-		list_add_tail(&sta->list, &mvm->resp_pasn_list);
-	}
-
-	ret = iwl_mvm_ftm_responder_dyn_cfg_v3(mvm, vif, NULL, hltk_data_ptr);
-	if (ret && sta)
-		iwl_mvm_resp_del_pasn_sta(mvm, vif, sta);
-
-	return ret;
-}
-
-int iwl_mvm_ftm_resp_remove_pasn_sta(struct iwl_mvm *mvm,
-				     struct ieee80211_vif *vif, u8 *addr)
-{
-	struct iwl_mvm_pasn_sta *sta, *prev;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	list_for_each_entry_safe(sta, prev, &mvm->resp_pasn_list, list) {
-		if (!memcmp(sta->addr, addr, ETH_ALEN)) {
-			iwl_mvm_resp_del_pasn_sta(mvm, vif, sta);
-			return 0;
-		}
-	}
-
-	IWL_ERR(mvm, "FTM: PASN station %pM not found\n", addr);
-	return -EINVAL;
-}
-
 int iwl_mvm_ftm_start_responder(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 				struct ieee80211_bss_conf *bss_conf)
 {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 9f0db96ac320a..69ad8d4898324 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2518,12 +2518,6 @@ void iwl_mvm_ftm_restart_responder(struct iwl_mvm *mvm,
 				   struct ieee80211_bss_conf *bss_conf);
 void iwl_mvm_ftm_responder_stats(struct iwl_mvm *mvm,
 				 struct iwl_rx_cmd_buffer *rxb);
-int iwl_mvm_ftm_resp_remove_pasn_sta(struct iwl_mvm *mvm,
-				     struct ieee80211_vif *vif, u8 *addr);
-int iwl_mvm_ftm_respoder_add_pasn_sta(struct iwl_mvm *mvm,
-				      struct ieee80211_vif *vif,
-				      u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
-				      u8 *hltk, u32 hltk_len);
 void iwl_mvm_ftm_responder_clear(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 7a4844ec3c104..78fd7faaed97d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -4311,67 +4311,6 @@ u16 iwl_mvm_tid_queued(struct iwl_mvm *mvm, struct iwl_mvm_tid_data *tid_data)
 	return ieee80211_sn_sub(sn, tid_data->next_reclaimed);
 }
 
-int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
-			 u8 *key, u32 key_len,
-			 struct ieee80211_key_conf *keyconf)
-{
-	int ret;
-	u16 queue;
-	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-	unsigned int wdg_timeout =
-		iwl_mvm_get_wd_timeout(mvm, vif);
-	bool mld = iwl_mvm_has_mld_api(mvm->fw);
-	u32 type = IWL_STA_LINK;
-
-	if (mld)
-		type = STATION_TYPE_PEER;
-
-	ret = iwl_mvm_allocate_int_sta(mvm, sta, 0,
-				       NL80211_IFTYPE_UNSPECIFIED, type);
-	if (ret)
-		return ret;
-
-	if (mld)
-		ret = iwl_mvm_mld_add_int_sta_with_queue(mvm, sta, addr,
-							 mvmvif->deflink.fw_link_id,
-							 &queue,
-							 IWL_MAX_TID_COUNT,
-							 &wdg_timeout);
-	else
-		ret = iwl_mvm_add_int_sta_with_queue(mvm, mvmvif->id,
-						     mvmvif->color, addr, sta,
-						     &queue,
-						     IWL_MVM_TX_FIFO_BE);
-	if (ret)
-		goto out;
-
-	keyconf->cipher = cipher;
-	memcpy(keyconf->key, key, key_len);
-	keyconf->keylen = key_len;
-	keyconf->flags = IEEE80211_KEY_FLAG_PAIRWISE;
-
-	if (mld) {
-		/* The MFP flag is set according to the station mfp field. Since
-		 * we don't have a station, set it manually.
-		 */
-		u32 key_flags =
-			iwl_mvm_get_sec_flags(mvm, vif, NULL, keyconf) |
-			IWL_SEC_KEY_FLAG_MFP;
-		u32 sta_mask = BIT(sta->sta_id);
-
-		ret = iwl_mvm_mld_send_key(mvm, sta_mask, key_flags, keyconf);
-	} else {
-		ret = iwl_mvm_send_sta_key(mvm, sta->sta_id, keyconf, false,
-					   0, NULL, 0, 0, true);
-	}
-
-out:
-	if (ret)
-		iwl_mvm_dealloc_int_sta(mvm, sta);
-	return ret;
-}
-
 void iwl_mvm_cancel_channel_switch(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif,
 				   u32 id)
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
index 6856f7440ef3e..19c905b641e2a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.h
@@ -597,10 +597,6 @@ void iwl_mvm_modify_all_sta_disable_tx(struct iwl_mvm *mvm,
 void iwl_mvm_csa_client_absent(struct iwl_mvm *mvm, struct ieee80211_vif *vif);
 int iwl_mvm_sta_ensure_queue(struct iwl_mvm *mvm, struct ieee80211_txq *txq);
 void iwl_mvm_add_new_dqa_stream_wk(struct work_struct *wk);
-int iwl_mvm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			 struct iwl_mvm_int_sta *sta, u8 *addr, u32 cipher,
-			 u8 *key, u32 key_len,
-			 struct ieee80211_key_conf *key_conf_out);
 void iwl_mvm_cancel_channel_switch(struct iwl_mvm *mvm,
 				   struct ieee80211_vif *vif,
 				   u32 id);

From 8c7df6490b600c9500a5ad698ecd435c5a482940 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:32:00 +0000
Subject: [PATCH 0344/2753] wifi: iwlwifi: mvm: Remove unused
 iwl_mvm_ftm_add_pasn_sta

iwl_mvm_ftm_add_pasn_sta() was added in 2020 by
commit 0739a7d70e00 ("iwlwifi: mvm: initiator: add option for adding a
PASN responder")
but hasn't been used.

Remove it.

That was the only caller of iwl_mvm_ftm_remove_pasn_sta().

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-5-linux@treblig.org
---
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 101 ------------------
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |   4 -
 2 files changed, 105 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index b26141c30c61c..f7034fa40c265 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -46,107 +46,6 @@ struct iwl_mvm_ftm_iter_data {
 	u8 *tk;
 };
 
-int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			     u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
-			     u8 *hltk, u32 hltk_len)
-{
-	struct iwl_mvm_ftm_pasn_entry *pasn = kzalloc(sizeof(*pasn),
-						      GFP_KERNEL);
-	u32 expected_tk_len;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	if (!pasn)
-		return -ENOBUFS;
-
-	iwl_mvm_ftm_remove_pasn_sta(mvm, addr);
-
-	pasn->cipher = iwl_mvm_cipher_to_location_cipher(cipher);
-
-	switch (pasn->cipher) {
-	case IWL_LOCATION_CIPHER_CCMP_128:
-	case IWL_LOCATION_CIPHER_GCMP_128:
-		expected_tk_len = WLAN_KEY_LEN_CCMP;
-		break;
-	case IWL_LOCATION_CIPHER_GCMP_256:
-		expected_tk_len = WLAN_KEY_LEN_GCMP_256;
-		break;
-	default:
-		goto out;
-	}
-
-	/*
-	 * If associated to this AP and already have security context,
-	 * the TK is already configured for this station, so it
-	 * shouldn't be set again here.
-	 */
-	if (vif->cfg.assoc) {
-		struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
-		struct ieee80211_bss_conf *link_conf;
-		unsigned int link_id;
-		struct ieee80211_sta *sta;
-		u8 sta_id;
-
-		rcu_read_lock();
-		for_each_vif_active_link(vif, link_conf, link_id) {
-			if (memcmp(addr, link_conf->bssid, ETH_ALEN))
-				continue;
-
-			sta_id = mvmvif->link[link_id]->ap_sta_id;
-			sta = rcu_dereference(mvm->fw_id_to_mac_id[sta_id]);
-			if (!IS_ERR_OR_NULL(sta) && sta->mfp)
-				expected_tk_len = 0;
-			break;
-		}
-		rcu_read_unlock();
-	}
-
-	if (tk_len != expected_tk_len ||
-	    (hltk_len && hltk_len != sizeof(pasn->hltk))) {
-		IWL_ERR(mvm, "Invalid key length: tk_len=%u hltk_len=%u\n",
-			tk_len, hltk_len);
-		goto out;
-	}
-
-	if (!expected_tk_len && !hltk_len) {
-		IWL_ERR(mvm, "TK and HLTK not set\n");
-		goto out;
-	}
-
-	memcpy(pasn->addr, addr, sizeof(pasn->addr));
-
-	if (hltk_len) {
-		memcpy(pasn->hltk, hltk, sizeof(pasn->hltk));
-		pasn->flags |= IWL_MVM_PASN_FLAG_HAS_HLTK;
-	}
-
-	if (tk && tk_len)
-		memcpy(pasn->tk, tk, sizeof(pasn->tk));
-
-	list_add_tail(&pasn->list, &mvm->ftm_initiator.pasn_list);
-	return 0;
-out:
-	kfree(pasn);
-	return -EINVAL;
-}
-
-void iwl_mvm_ftm_remove_pasn_sta(struct iwl_mvm *mvm, u8 *addr)
-{
-	struct iwl_mvm_ftm_pasn_entry *entry, *prev;
-
-	lockdep_assert_held(&mvm->mutex);
-
-	list_for_each_entry_safe(entry, prev, &mvm->ftm_initiator.pasn_list,
-				 list) {
-		if (memcmp(entry->addr, addr, sizeof(entry->addr)))
-			continue;
-
-		list_del(&entry->list);
-		kfree(entry);
-		return;
-	}
-}
-
 static void iwl_mvm_ftm_reset(struct iwl_mvm *mvm)
 {
 	struct iwl_mvm_loc_entry *e, *t;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index 69ad8d4898324..d17592d3f6c8e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -2532,10 +2532,6 @@ int iwl_mvm_ftm_start(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 void iwl_mvm_ftm_abort(struct iwl_mvm *mvm, struct cfg80211_pmsr_request *req);
 void iwl_mvm_ftm_initiator_smooth_config(struct iwl_mvm *mvm);
 void iwl_mvm_ftm_initiator_smooth_stop(struct iwl_mvm *mvm);
-int iwl_mvm_ftm_add_pasn_sta(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
-			     u8 *addr, u32 cipher, u8 *tk, u32 tk_len,
-			     u8 *hltk, u32 hltk_len);
-void iwl_mvm_ftm_remove_pasn_sta(struct iwl_mvm *mvm, u8 *addr);
 
 /* TDLS */
 

From 619bd63a9428bcd6f34da12c0015f8949c1f6274 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:32:01 +0000
Subject: [PATCH 0345/2753] wifi: iwlwifi: Remove unused iwl_bz_name

iwl_bz_name[] has been unused since the resent
commit 6795a37161fb ("wifi: iwlwifi: Print a specific device name.")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-6-linux@treblig.org
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c     | 1 -
 drivers/net/wireless/intel/iwlwifi/iwl-config.h | 1 -
 2 files changed, 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index efa3e0e35f799..074b2c9ea003b 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -145,7 +145,6 @@ const struct iwl_cfg_trans_params iwl_gl_trans_cfg = {
 	.low_latency_xtal = true,
 };
 
-const char iwl_bz_name[] = "Intel(R) TBD Bz device";
 const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz";
 const char iwl_wh_name[] = "Intel(R) Wi-Fi 7 BE211 320MHz";
 const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz";
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 2b6a80142aba9..b51e3b5d902ba 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -553,7 +553,6 @@ extern const char iwl_ax211_name[];
 extern const char iwl_ax221_name[];
 extern const char iwl_ax231_name[];
 extern const char iwl_ax411_name[];
-extern const char iwl_bz_name[];
 extern const char iwl_fm_name[];
 extern const char iwl_wh_name[];
 extern const char iwl_gl_name[];

From 5f60a40ee524422bebc233281a6d7fa34a986a77 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Dec 2024 01:32:02 +0000
Subject: [PATCH 0346/2753] wifi: iwlwifi: Remove old device data

The last use of iwl_ax204_name[], iwl_ax221_name[] and iwl_cfg_so_a0_ms_a0
was removed by
commit f473a7fd6d60 ("wifi: iwlwifi: remove devices that never came out")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20241223013202.340180-7-linux@treblig.org
---
 drivers/net/wireless/intel/iwlwifi/cfg/22000.c  | 1 -
 drivers/net/wireless/intel/iwlwifi/cfg/ax210.c  | 1 -
 drivers/net/wireless/intel/iwlwifi/iwl-config.h | 2 --
 3 files changed, 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
index 2e2fcb3807efb..130b9a8aa7ebe 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/22000.c
@@ -205,7 +205,6 @@ const char iwl_ax101_name[] = "Intel(R) Wi-Fi 6 AX101";
 const char iwl_ax200_name[] = "Intel(R) Wi-Fi 6 AX200 160MHz";
 const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
 const char iwl_ax203_name[] = "Intel(R) Wi-Fi 6 AX203";
-const char iwl_ax204_name[] = "Intel(R) Wi-Fi 6 AX204 160MHz";
 
 const char iwl_ax200_killer_1650w_name[] =
 	"Killer(R) Wi-Fi 6 AX1650w 160MHz Wireless Network Adapter (200D2W)";
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
index dcba1a5d793b7..e87b57b9e2c04 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/ax210.c
@@ -180,7 +180,6 @@ const struct iwl_cfg_trans_params iwl_ma_trans_cfg = {
 };
 
 const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
-const char iwl_ax221_name[] = "Intel(R) Wi-Fi 6E AX221 160MHz";
 const char iwl_ax231_name[] = "Intel(R) Wi-Fi 6E AX231 160MHz";
 const char iwl_ax411_name[] = "Intel(R) Wi-Fi 6E AX411 160MHz";
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index b51e3b5d902ba..91275680dd2cb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -534,7 +534,6 @@ extern const char iwl9560_killer_1550i_name[];
 extern const char iwl9560_killer_1550s_name[];
 extern const char iwl_ax200_name[];
 extern const char iwl_ax203_name[];
-extern const char iwl_ax204_name[];
 extern const char iwl_ax201_name[];
 extern const char iwl_ax101_name[];
 extern const char iwl_ax200_killer_1650w_name[];
@@ -550,7 +549,6 @@ extern const char iwl_ax211_killer_1675i_name[];
 extern const char iwl_ax411_killer_1690s_name[];
 extern const char iwl_ax411_killer_1690i_name[];
 extern const char iwl_ax211_name[];
-extern const char iwl_ax221_name[];
 extern const char iwl_ax231_name[];
 extern const char iwl_ax411_name[];
 extern const char iwl_fm_name[];

From 7951e8099c2f12c1b98ce964ee05fd6bb7f2e7e7 Mon Sep 17 00:00:00 2001
From: Catalin Popescu <catalin.popescu@leica-geosystems.com>
Date: Thu, 16 Jan 2025 09:47:01 +0100
Subject: [PATCH 0347/2753] dt-bindings: net: rfkill-gpio: enable booting in
 blocked state

By default, rfkill state is set to unblocked. Sometimes, we want to boot
in blocked state and let the application unblock the rfkill.

Signed-off-by: Catalin Popescu <catalin.popescu@leica-geosystems.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250116084702.3473176-1-catalin.popescu@leica-geosystems.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 Documentation/devicetree/bindings/net/rfkill-gpio.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/rfkill-gpio.yaml b/Documentation/devicetree/bindings/net/rfkill-gpio.yaml
index 9630c8466fac0..4a706a41ab38c 100644
--- a/Documentation/devicetree/bindings/net/rfkill-gpio.yaml
+++ b/Documentation/devicetree/bindings/net/rfkill-gpio.yaml
@@ -32,6 +32,10 @@ properties:
   shutdown-gpios:
     maxItems: 1
 
+  default-blocked:
+    $ref: /schemas/types.yaml#/definitions/flag
+    description: configure rfkill state as blocked at boot
+
 required:
   - compatible
   - radio-type
@@ -48,4 +52,5 @@ examples:
         label = "rfkill-pcie-wlan";
         radio-type = "wlan";
         shutdown-gpios = <&gpio2 25 GPIO_ACTIVE_HIGH>;
+        default-blocked;
     };

From 2882bf7dd4f5dc732aa98d206026582cc136cb4d Mon Sep 17 00:00:00 2001
From: Catalin Popescu <catalin.popescu@leica-geosystems.com>
Date: Thu, 16 Jan 2025 09:47:02 +0100
Subject: [PATCH 0348/2753] net: rfkill: gpio: allow booting in blocked state

By default, rfkill state is unblocked and this behavior is not
configurable. Add support for booting in blocked state based on the
presence of a devicetree property.

Signed-off-by: Catalin Popescu <catalin.popescu@leica-geosystems.com>
Link: https://patch.msgid.link/20250116084702.3473176-2-catalin.popescu@leica-geosystems.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/rfkill/rfkill-gpio.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/rfkill/rfkill-gpio.c b/net/rfkill/rfkill-gpio.c
index 9fa019e0dcadd..41e657e977618 100644
--- a/net/rfkill/rfkill-gpio.c
+++ b/net/rfkill/rfkill-gpio.c
@@ -162,6 +162,9 @@ static int rfkill_gpio_probe(struct platform_device *pdev)
 	if (!rfkill->rfkill_dev)
 		return -ENOMEM;
 
+	if (device_property_present(&pdev->dev, "default-blocked"))
+		rfkill_init_sw_state(rfkill->rfkill_dev, true);
+
 	ret = rfkill_register(rfkill->rfkill_dev);
 	if (ret < 0)
 		goto err_destroy;

From 8c2ffc65563fff5d596c4bef60445d443991ae26 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 19 Jan 2025 21:03:13 +0200
Subject: [PATCH 0349/2753] wifi: iwlwifi: remove the mvm prefix from
 iwl_mvm_ctdp_cmd

This command is not specific to iwlmvm.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250119210104.04f3afcf9c77.Ic2b6f265d0b4aea25ccc7114d6f48afa621871be@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/phy.h | 12 ++++++------
 drivers/net/wireless/intel/iwlwifi/mvm/tt.c     |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
index c73d4d5978572..1dce28f3afa03 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
@@ -19,7 +19,7 @@ enum iwl_phy_ops_subcmd_ids {
 	CMD_DTS_MEASUREMENT_TRIGGER_WIDE = 0x0,
 
 	/**
-	 * @CTDP_CONFIG_CMD: &struct iwl_mvm_ctdp_cmd
+	 * @CTDP_CONFIG_CMD: &struct iwl_ctdp_cmd
 	 */
 	CTDP_CONFIG_CMD = 0x03,
 
@@ -195,25 +195,25 @@ struct ct_kill_notif {
 } __packed; /* CT_KILL_NOTIFICATION_API_S_VER_1, CT_KILL_NOTIFICATION_API_S_VER_2 */
 
 /**
-* enum iwl_mvm_ctdp_cmd_operation - CTDP command operations
+* enum iwl_ctdp_cmd_operation - CTDP command operations
 * @CTDP_CMD_OPERATION_START: update the current budget
 * @CTDP_CMD_OPERATION_STOP: stop ctdp
 * @CTDP_CMD_OPERATION_REPORT: get the average budget
 */
-enum iwl_mvm_ctdp_cmd_operation {
+enum iwl_ctdp_cmd_operation {
 	CTDP_CMD_OPERATION_START	= 0x1,
 	CTDP_CMD_OPERATION_STOP		= 0x2,
 	CTDP_CMD_OPERATION_REPORT	= 0x4,
 };/* CTDP_CMD_OPERATION_TYPE_E */
 
 /**
- * struct iwl_mvm_ctdp_cmd - track and manage the FW power consumption budget
+ * struct iwl_ctdp_cmd - track and manage the FW power consumption budget
  *
- * @operation: see &enum iwl_mvm_ctdp_cmd_operation
+ * @operation: see &enum iwl_ctdp_cmd_operation
  * @budget: the budget in milliwatt
  * @window_size: defined in API but not used
  */
-struct iwl_mvm_ctdp_cmd {
+struct iwl_ctdp_cmd {
 	__le32 operation;
 	__le32 budget;
 	__le32 window_size;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index d92470960b38b..256f8f558b154 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -506,7 +506,7 @@ static const u32 iwl_mvm_cdev_budgets[] = {
 
 int iwl_mvm_ctdp_command(struct iwl_mvm *mvm, u32 op, u32 state)
 {
-	struct iwl_mvm_ctdp_cmd cmd = {
+	struct iwl_ctdp_cmd cmd = {
 		.operation = cpu_to_le32(op),
 		.budget = cpu_to_le32(iwl_mvm_cdev_budgets[state]),
 		.window_size = 0,

From 55e52a3b8f60413e1e935d9de1719ceafeb5ee64 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 19 Jan 2025 21:03:14 +0200
Subject: [PATCH 0350/2753] wifi: iwlwifi: remove the version number from
 iwl_dts_measurement_notif_v2

No need to carry the version number in the structure name if this is the
latest version available.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250119210104.9d218a5c4f6b.I9de3e424be48d66994cde3684ce7e9e99456067d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/commands.h | 2 +-
 drivers/net/wireless/intel/iwlwifi/fw/api/phy.h      | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/tt.c          | 2 +-
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 34a1f97653c06..4b450c722a9ce 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -502,7 +502,7 @@ enum iwl_legacy_cmds {
 	/**
 	 * @DTS_MEASUREMENT_NOTIFICATION:
 	 * &struct iwl_dts_measurement_notif_v1 or
-	 * &struct iwl_dts_measurement_notif_v2
+	 * &struct iwl_dts_measurement_notif
 	 */
 	DTS_MEASUREMENT_NOTIFICATION = 0xdd,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
index 1dce28f3afa03..eb8961b51cb01 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
@@ -55,7 +55,7 @@ enum iwl_phy_ops_subcmd_ids {
 	/**
 	 * @DTS_MEASUREMENT_NOTIF_WIDE:
 	 * &struct iwl_dts_measurement_notif_v1 or
-	 * &struct iwl_dts_measurement_notif_v2
+	 * &struct iwl_dts_measurement_notif
 	 */
 	DTS_MEASUREMENT_NOTIF_WIDE = 0xFF,
 };
@@ -152,13 +152,13 @@ struct iwl_dts_measurement_notif_v1 {
 } __packed; /* TEMPERATURE_MEASUREMENT_TRIGGER_NTFY_S_VER_1*/
 
 /**
- * struct iwl_dts_measurement_notif_v2 - measurements notification
+ * struct iwl_dts_measurement_notif - measurements notification
  *
  * @temp: the measured temperature
  * @voltage: the measured voltage
  * @threshold_idx: the trip index that was crossed
  */
-struct iwl_dts_measurement_notif_v2 {
+struct iwl_dts_measurement_notif {
 	__le32 temp;
 	__le32 voltage;
 	__le32 threshold_idx;
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
index 256f8f558b154..c851290e75a24 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
@@ -105,7 +105,7 @@ static bool iwl_mvm_temp_notif_wait(struct iwl_notif_wait_data *notif_wait,
 void iwl_mvm_temp_notif(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_dts_measurement_notif_v2 *notif_v2;
+	struct iwl_dts_measurement_notif *notif_v2;
 	int len = iwl_rx_packet_payload_len(pkt);
 	int temp;
 	u32 ths_crossed;

From 3d4b0f0c5cda8f071641a151a2eb494099ed7337 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 19 Jan 2025 21:03:15 +0200
Subject: [PATCH 0351/2753] wifi: iwlwifi: remove the mvm prefix from
 iwl_mvm_aux_sta_cmd

This is a firmware command and is not specific to the iwlmvm op_mode

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250119210104.276658439163.I70641851f9e5210ec3a7033db38a45d24814083b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h | 6 +++---
 drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c    | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 37bb7002c1c93..232e20482e2d8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -46,7 +46,7 @@ enum iwl_mac_conf_subcmd_ids {
 	 */
 	STA_CONFIG_CMD = 0xA,
 	/**
-	 * @AUX_STA_CMD: &struct iwl_mvm_aux_sta_cmd
+	 * @AUX_STA_CMD: &struct iwl_aux_sta_cmd
 	 */
 	AUX_STA_CMD = 0xB,
 	/**
@@ -641,7 +641,7 @@ struct iwl_sta_cfg_cmd {
 } __packed; /* STA_CMD_API_S_VER_1 */
 
 /**
- * struct iwl_mvm_aux_sta_cmd - command for AUX STA configuration
+ * struct iwl_aux_sta_cmd - command for AUX STA configuration
  * ( AUX_STA_CMD = 0xB )
  *
  * @sta_id: index of aux sta to configure
@@ -649,7 +649,7 @@ struct iwl_sta_cfg_cmd {
  * @mac_addr: mac addr of the auxilary sta
  * @reserved_for_mac_addr: reserved
  */
-struct iwl_mvm_aux_sta_cmd {
+struct iwl_aux_sta_cmd {
 	__le32 sta_id;
 	__le32 lmac_id;
 	u8 mac_addr[ETH_ALEN];
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
index 2f159024eeb89..9dd6700411370 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-sta.c
@@ -121,7 +121,7 @@ static int iwl_mvm_add_aux_sta_to_fw(struct iwl_mvm *mvm,
 {
 	int ret;
 
-	struct iwl_mvm_aux_sta_cmd cmd = {
+	struct iwl_aux_sta_cmd cmd = {
 		.sta_id = cpu_to_le32(sta->sta_id),
 		.lmac_id = cpu_to_le32(lmac_id),
 	};

From b7016fd817120d89223c5cfc6022ce328b499994 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Sun, 2 Feb 2025 22:06:59 +0000
Subject: [PATCH 0352/2753] wifi: ipw2x00: Fix spelling mistake "stablization"
 -> "stabilization"

There is a spelling mistake in a IPW_DEBUG_INFO message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://patch.msgid.link/20250202220659.199341-1-colin.i.king@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/ipw2x00/ipw2200.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/ipw2x00/ipw2200.c b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
index be1d971b3d32d..24a5624ef2071 100644
--- a/drivers/net/wireless/intel/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/intel/ipw2x00/ipw2200.c
@@ -3295,7 +3295,7 @@ static int ipw_init_nic(struct ipw_priv *priv)
 	rc = ipw_poll_bit(priv, IPW_GP_CNTRL_RW,
 			  IPW_GP_CNTRL_BIT_CLOCK_READY, 250);
 	if (rc < 0)
-		IPW_DEBUG_INFO("FAILED wait for clock stablization\n");
+		IPW_DEBUG_INFO("FAILED wait for clock stabilization\n");
 
 	/* assert SW reset */
 	ipw_set_bit(priv, IPW_RESET_REG, IPW_RESET_REG_SW_RESET);

From f5903ca220360d2e5539473aacd845909a2d5274 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 4 Feb 2025 01:25:12 +0000
Subject: [PATCH 0353/2753] wifi: mwifiex: Remove unused
 mwifiex_uap_del_sta_data

The last use of mwifiex_uap_del_sta_data() was removed in 2014 by
commit dda9ddeb2638 ("mwifiex: do not delete station entries in del_sta
handler")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://patch.msgid.link/20250204012512.390209-1-linux@treblig.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/main.h      |  2 --
 drivers/net/wireless/marvell/mwifiex/uap_event.c | 16 ----------------
 2 files changed, 18 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
index fb15831201f74..63f1c900e0967 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.h
+++ b/drivers/net/wireless/marvell/mwifiex/main.h
@@ -1571,8 +1571,6 @@ void mwifiex_uap_set_channel(struct mwifiex_private *priv,
 			     struct cfg80211_chan_def chandef);
 int mwifiex_config_start_uap(struct mwifiex_private *priv,
 			     struct mwifiex_uap_bss_param *bss_cfg);
-void mwifiex_uap_del_sta_data(struct mwifiex_private *priv,
-			      struct mwifiex_sta_node *node);
 
 void mwifiex_config_uap_11d(struct mwifiex_private *priv,
 			    struct cfg80211_beacon_data *beacon_data);
diff --git a/drivers/net/wireless/marvell/mwifiex/uap_event.c b/drivers/net/wireless/marvell/mwifiex/uap_event.c
index 58ef5020a46a7..245cb99a3daad 100644
--- a/drivers/net/wireless/marvell/mwifiex/uap_event.c
+++ b/drivers/net/wireless/marvell/mwifiex/uap_event.c
@@ -325,19 +325,3 @@ int mwifiex_process_uap_event(struct mwifiex_private *priv)
 
 	return 0;
 }
-
-/* This function deletes station entry from associated station list.
- * Also if both AP and STA are 11n enabled, RxReorder tables and TxBA stream
- * tables created for this station are deleted.
- */
-void mwifiex_uap_del_sta_data(struct mwifiex_private *priv,
-			      struct mwifiex_sta_node *node)
-{
-	if (priv->ap_11n_enabled && node->is_11n_enabled) {
-		mwifiex_11n_del_rx_reorder_tbl_by_ta(priv, node->mac_addr);
-		mwifiex_del_tx_ba_stream_tbl_by_ra(priv, node->mac_addr);
-	}
-	mwifiex_del_sta_entry(priv, node->mac_addr);
-
-	return;
-}

From be22179cfb2fb1164004b70b33a4bdf67e6dd349 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 12:13:51 +0100
Subject: [PATCH 0354/2753] wifi: nl80211/cfg80211: Stop supporting cooked
 monitor

Unconditionally start to refuse creating cooked monitor interfaces to
phase them out.

There is no feature flag for drivers to opt-in for cooked monitor and
all known users are using/preferring the modern API since the hostapd
release 1.0 in May 2012.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204111352.7004-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 2 +-
 include/uapi/linux/nl80211.h | 4 ++--
 net/wireless/nl80211.c       | 4 ++++
 3 files changed, 7 insertions(+), 3 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 363d7dd2255aa..a72e7eb7027f2 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2265,7 +2265,7 @@ static inline int cfg80211_get_station(struct net_device *dev,
  * @MONITOR_FLAG_PLCPFAIL: pass frames with bad PLCP
  * @MONITOR_FLAG_CONTROL: pass control frames
  * @MONITOR_FLAG_OTHER_BSS: disable BSSID filtering
- * @MONITOR_FLAG_COOK_FRAMES: report frames after processing
+ * @MONITOR_FLAG_COOK_FRAMES: deprecated, will unconditionally be refused
  * @MONITOR_FLAG_ACTIVE: active monitor, ACKs frames on its MAC address
  * @MONITOR_FLAG_SKIP_TX: do not pass locally transmitted frames
  */
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index f6c1b181c886d..9d8ecf20ef0d4 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4727,8 +4727,8 @@ enum nl80211_survey_info {
  * @NL80211_MNTR_FLAG_PLCPFAIL: pass frames with bad PLCP
  * @NL80211_MNTR_FLAG_CONTROL: pass control frames
  * @NL80211_MNTR_FLAG_OTHER_BSS: disable BSSID filtering
- * @NL80211_MNTR_FLAG_COOK_FRAMES: report frames after processing.
- *	overrides all other flags.
+ * @NL80211_MNTR_FLAG_COOK_FRAMES: deprecated
+ *	will unconditionally be refused
  * @NL80211_MNTR_FLAG_ACTIVE: use the configured MAC address
  *	and ACK incoming unicast packets.
  * @NL80211_MNTR_FLAG_SKIP_TX: do not pass local tx packets
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7d3da0f6833d..8bd09110d393e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4245,6 +4245,10 @@ static int nl80211_parse_mon_options(struct cfg80211_registered_device *rdev,
 		change = true;
 	}
 
+	/* MONITOR_FLAG_COOK_FRAMES is deprecated, refuse cooperation */
+	if (params->flags & MONITOR_FLAG_COOK_FRAMES)
+		return -EOPNOTSUPP;
+
 	if (params->flags & MONITOR_FLAG_ACTIVE &&
 	    !(rdev->wiphy.features & NL80211_FEATURE_ACTIVE_MONITOR))
 		return -EOPNOTSUPP;

From 286e696770654d79b34bd15953e7101a1c4784c7 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 12:13:52 +0100
Subject: [PATCH 0355/2753] wifi: mac80211: Drop cooked monitor support

Hostapd switched from cooked monitor interfaces to nl80211 Dec 2011.
Drop support for the outdated cooked monitor interfaces and fix
creating the virtual monitor interfaces in the following cases:

 1) We have one non-monitor and one monitor interface with
    %MONITOR_FLAG_ACTIVE enabled and then delete the non-monitor
    interface.

 2) We only have monitor interfaces enabled on resume while at least one
    has %MONITOR_FLAG_ACTIVE set.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204111352.7004-2-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/dropreason.h   |   6 --
 net/mac80211/cfg.c         |   9 +-
 net/mac80211/drop.h        |  21 ++--
 net/mac80211/ieee80211_i.h |  11 +--
 net/mac80211/iface.c       |  50 ++++------
 net/mac80211/main.c        |  16 +--
 net/mac80211/rx.c          | 194 ++++++++++---------------------------
 net/mac80211/status.c      |  34 +------
 net/mac80211/tx.c          |   2 +-
 9 files changed, 94 insertions(+), 249 deletions(-)

diff --git a/include/net/dropreason.h b/include/net/dropreason.h
index 56cb7be92244c..7d3b1a2a6feca 100644
--- a/include/net/dropreason.h
+++ b/include/net/dropreason.h
@@ -17,12 +17,6 @@ enum skb_drop_reason_subsys {
 	 */
 	SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE,
 
-	/**
-	 * @SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR: mac80211 drop reasons
-	 * for frames still going to monitor, see net/mac80211/drop.h
-	 */
-	SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR,
-
 	/**
 	 * @SKB_DROP_REASON_SUBSYS_OPENVSWITCH: openvswitch drop reasons,
 	 * see net/openvswitch/drop.h
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 9351c64608a99..88949b90f117e 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -89,15 +89,14 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
 
 	/* check flags first */
 	if (params->flags && ieee80211_sdata_running(sdata)) {
-		u32 mask = MONITOR_FLAG_COOK_FRAMES | MONITOR_FLAG_ACTIVE;
+		u32 mask = MONITOR_FLAG_ACTIVE;
 
 		/*
-		 * Prohibit MONITOR_FLAG_COOK_FRAMES and
-		 * MONITOR_FLAG_ACTIVE to be changed while the
-		 * interface is up.
+		 * Prohibit MONITOR_FLAG_ACTIVE to be changed
+		 * while the interface is up.
 		 * Else we would need to add a lot of cruft
 		 * to update everything:
-		 *	cooked_mntrs, monitor and all fif_* counters
+		 *	monitor and all fif_* counters
 		 *	reconfigure hardware
 		 */
 		if ((params->flags & mask) != (sdata->u.mntr.flags & mask))
diff --git a/net/mac80211/drop.h b/net/mac80211/drop.h
index 59e3ec4dc9607..eb9ab310f91ca 100644
--- a/net/mac80211/drop.h
+++ b/net/mac80211/drop.h
@@ -11,12 +11,6 @@
 
 typedef unsigned int __bitwise ieee80211_rx_result;
 
-#define MAC80211_DROP_REASONS_MONITOR(R)	\
-	R(RX_DROP_M_UNEXPECTED_4ADDR_FRAME)	\
-	R(RX_DROP_M_BAD_BCN_KEYIDX)		\
-	R(RX_DROP_M_BAD_MGMT_KEYIDX)		\
-/* this line for the trailing \ - add before this */
-
 #define MAC80211_DROP_REASONS_UNUSABLE(R)	\
 	/* 0x00 == ___RX_DROP_UNUSABLE */	\
 	R(RX_DROP_U_MIC_FAIL)			\
@@ -66,6 +60,10 @@ typedef unsigned int __bitwise ieee80211_rx_result;
 	R(RX_DROP_U_UNEXPECTED_STA_4ADDR)	\
 	R(RX_DROP_U_UNEXPECTED_VLAN_MCAST)	\
 	R(RX_DROP_U_NOT_PORT_CONTROL)		\
+	R(RX_DROP_U_UNEXPECTED_4ADDR_FRAME)	\
+	R(RX_DROP_U_BAD_BCN_KEYIDX)		\
+	/* 0x30 */				\
+	R(RX_DROP_U_BAD_MGMT_KEYIDX)		\
 	R(RX_DROP_U_UNKNOWN_ACTION_REJECTED)	\
 /* this line for the trailing \ - add before this */
 
@@ -78,10 +76,6 @@ enum ___mac80211_drop_reason {
 	___RX_QUEUED	= SKB_NOT_DROPPED_YET,
 
 #define ENUM(x) ___ ## x,
-	___RX_DROP_MONITOR = SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR <<
-		SKB_DROP_REASON_SUBSYS_SHIFT,
-	MAC80211_DROP_REASONS_MONITOR(ENUM)
-
 	___RX_DROP_UNUSABLE = SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE <<
 		SKB_DROP_REASON_SUBSYS_SHIFT,
 	MAC80211_DROP_REASONS_UNUSABLE(ENUM)
@@ -89,11 +83,10 @@ enum ___mac80211_drop_reason {
 };
 
 enum mac80211_drop_reason {
-	RX_CONTINUE	 = (__force ieee80211_rx_result)___RX_CONTINUE,
-	RX_QUEUED	 = (__force ieee80211_rx_result)___RX_QUEUED,
-	RX_DROP_MONITOR	 = (__force ieee80211_rx_result)___RX_DROP_MONITOR,
+	RX_CONTINUE	= (__force ieee80211_rx_result)___RX_CONTINUE,
+	RX_QUEUED	= (__force ieee80211_rx_result)___RX_QUEUED,
+	RX_DROP		= (__force ieee80211_rx_result)___RX_DROP_UNUSABLE,
 #define DEF(x) x = (__force ieee80211_rx_result)___ ## x,
-	MAC80211_DROP_REASONS_MONITOR(DEF)
 	MAC80211_DROP_REASONS_UNUSABLE(DEF)
 #undef DEF
 };
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index e7dc3f0cfc9a9..a90a44aa5758b 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -200,7 +200,6 @@ enum ieee80211_packet_rx_flags {
 /**
  * enum ieee80211_rx_flags - RX data flags
  *
- * @IEEE80211_RX_CMNTR: received on cooked monitor already
  * @IEEE80211_RX_BEACON_REPORTED: This frame was already reported
  *	to cfg80211_report_obss_beacon().
  *
@@ -208,8 +207,7 @@ enum ieee80211_packet_rx_flags {
  * for a single frame.
  */
 enum ieee80211_rx_flags {
-	IEEE80211_RX_CMNTR		= BIT(0),
-	IEEE80211_RX_BEACON_REPORTED	= BIT(1),
+	IEEE80211_RX_BEACON_REPORTED	= BIT(0),
 };
 
 struct ieee80211_rx_data {
@@ -1380,7 +1378,7 @@ struct ieee80211_local {
 	spinlock_t queue_stop_reason_lock;
 
 	int open_count;
-	int monitors, cooked_mntrs, tx_mntrs;
+	int monitors, tx_mntrs;
 	/* number of interfaces with corresponding FIF_ flags */
 	int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss, fif_pspoll,
 	    fif_probe_req;
@@ -1492,7 +1490,7 @@ struct ieee80211_local {
 
 	/* see iface.c */
 	struct list_head interfaces;
-	struct list_head mon_list; /* only that are IFF_UP && !cooked */
+	struct list_head mon_list; /* only that are IFF_UP */
 	struct mutex iflist_mtx;
 
 	/* Scanning and BSS list */
@@ -2090,8 +2088,7 @@ struct sk_buff *
 ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata,
 			      struct sk_buff *skb, u32 info_flags);
 void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
-			  int retry_count, bool send_to_cooked,
-			  struct ieee80211_tx_status *status);
+			  int retry_count, struct ieee80211_tx_status *status);
 
 void ieee80211_check_fast_xmit(struct sta_info *sta);
 void ieee80211_check_fast_xmit_all(struct ieee80211_local *local);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 0ea7e77860b73..7d3ebfcb8c2b0 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -483,8 +483,6 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		ieee80211_ibss_stop(sdata);
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
-			break;
 		list_del_rcu(&sdata->u.mntr.list);
 		break;
 	default:
@@ -584,18 +582,17 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		/* no need to tell driver */
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) {
-			local->cooked_mntrs--;
-			break;
-		}
+		if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) &&
+		    !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
 
-		local->monitors--;
-		if (local->monitors == 0) {
-			local->hw.conf.flags &= ~IEEE80211_CONF_MONITOR;
-			hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
-		}
+			local->monitors--;
+			if (local->monitors == 0) {
+				local->hw.conf.flags &= ~IEEE80211_CONF_MONITOR;
+				hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
+			}
 
-		ieee80211_adjust_monitor_flags(sdata, -1);
+			ieee80211_adjust_monitor_flags(sdata, -1);
+		}
 		break;
 	case NL80211_IFTYPE_NAN:
 		/* clean all the functions */
@@ -1326,27 +1323,24 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		}
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) {
-			local->cooked_mntrs++;
-			break;
-		}
-
 		if ((sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) ||
 		    ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
 			res = drv_add_interface(local, sdata);
 			if (res)
 				goto err_stop;
-		} else if (local->monitors == 0 && local->open_count == 0) {
-			res = ieee80211_add_virtual_monitor(local);
-			if (res)
-				goto err_stop;
-		}
+		} else {
+			if (local->monitors == 0 && local->open_count == 0) {
+				res = ieee80211_add_virtual_monitor(local);
+				if (res)
+					goto err_stop;
+			}
+			local->monitors++;
 
-		/* must be before the call to ieee80211_configure_filter */
-		local->monitors++;
-		if (local->monitors == 1) {
-			local->hw.conf.flags |= IEEE80211_CONF_MONITOR;
-			hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
+			/* must be before the call to ieee80211_configure_filter */
+			if (local->monitors == 1) {
+				local->hw.conf.flags |= IEEE80211_CONF_MONITOR;
+				hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
+			}
 		}
 
 		ieee80211_adjust_monitor_flags(sdata, 1);
@@ -1423,8 +1417,6 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 		rcu_assign_pointer(local->p2p_sdata, sdata);
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES)
-			break;
 		list_add_tail_rcu(&sdata->u.mntr.list, &local->mon_list);
 		break;
 	default:
diff --git a/net/mac80211/main.c b/net/mac80211/main.c
index 53e5aee468856..741e6c7edcb7c 100644
--- a/net/mac80211/main.c
+++ b/net/mac80211/main.c
@@ -1744,18 +1744,7 @@ void ieee80211_free_hw(struct ieee80211_hw *hw)
 	wiphy_free(local->hw.wiphy);
 }
 EXPORT_SYMBOL(ieee80211_free_hw);
-
-static const char * const drop_reasons_monitor[] = {
-#define V(x)	#x,
-	[0] = "RX_DROP_MONITOR",
-	MAC80211_DROP_REASONS_MONITOR(V)
-};
-
-static struct drop_reason_list drop_reason_list_monitor = {
-	.reasons = drop_reasons_monitor,
-	.n_reasons = ARRAY_SIZE(drop_reasons_monitor),
-};
-
+#define V(x)   #x,
 static const char * const drop_reasons_unusable[] = {
 	[0] = "RX_DROP_UNUSABLE",
 	MAC80211_DROP_REASONS_UNUSABLE(V)
@@ -1784,8 +1773,6 @@ static int __init ieee80211_init(void)
 	if (ret)
 		goto err_netdev;
 
-	drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR,
-				     &drop_reason_list_monitor);
 	drop_reasons_register_subsys(SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE,
 				     &drop_reason_list_unusable);
 
@@ -1804,7 +1791,6 @@ static void __exit ieee80211_exit(void)
 
 	ieee80211_iface_exit();
 
-	drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_MAC80211_MONITOR);
 	drop_reasons_unregister_subsys(SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE);
 
 	rcu_barrier();
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1e28efe4203c0..d33970009e00d 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -1045,14 +1045,14 @@ static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx)
 		if (is_multicast_ether_addr(hdr->addr1)) {
 			if (ieee80211_has_tods(hdr->frame_control) ||
 			    !ieee80211_has_fromds(hdr->frame_control))
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 			if (ether_addr_equal(hdr->addr3, dev_addr))
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 		} else {
 			if (!ieee80211_has_a4(hdr->frame_control))
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 			if (ether_addr_equal(hdr->addr4, dev_addr))
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 		}
 	}
 
@@ -1064,20 +1064,20 @@ static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx)
 		struct ieee80211_mgmt *mgmt;
 
 		if (!ieee80211_is_mgmt(hdr->frame_control))
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		if (ieee80211_is_action(hdr->frame_control)) {
 			u8 category;
 
 			/* make sure category field is present */
 			if (rx->skb->len < IEEE80211_MIN_ACTION_SIZE)
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 
 			mgmt = (struct ieee80211_mgmt *)hdr;
 			category = mgmt->u.action.category;
 			if (category != WLAN_CATEGORY_MESH_ACTION &&
 			    category != WLAN_CATEGORY_SELF_PROTECTED)
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 			return RX_CONTINUE;
 		}
 
@@ -1087,7 +1087,7 @@ static ieee80211_rx_result ieee80211_rx_mesh_check(struct ieee80211_rx_data *rx)
 		    ieee80211_is_auth(hdr->frame_control))
 			return RX_CONTINUE;
 
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	return RX_CONTINUE;
@@ -1513,7 +1513,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 			hdrlen = ieee80211_hdrlen(hdr->frame_control);
 
 			if (rx->skb->len < hdrlen + 8)
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 
 			skb_copy_bits(rx->skb, hdrlen + 6, &ethertype, 2);
 			if (ethertype == rx->sdata->control_port_protocol)
@@ -1526,7 +1526,7 @@ ieee80211_rx_h_check(struct ieee80211_rx_data *rx)
 					       GFP_ATOMIC))
 			return RX_DROP_U_SPURIOUS;
 
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	return RX_CONTINUE;
@@ -1862,7 +1862,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx)
 				cfg80211_rx_unexpected_4addr_frame(
 					rx->sdata->dev, sta->sta.addr,
 					GFP_ATOMIC);
-			return RX_DROP_M_UNEXPECTED_4ADDR_FRAME;
+			return RX_DROP_U_UNEXPECTED_4ADDR_FRAME;
 		}
 		/*
 		 * Update counter and free packet here to avoid
@@ -1997,7 +1997,7 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 				cfg80211_rx_unprot_mlme_mgmt(rx->sdata->dev,
 							     skb->data,
 							     skb->len);
-			return RX_DROP_M_BAD_BCN_KEYIDX;
+			return RX_DROP_U_BAD_BCN_KEYIDX;
 		}
 
 		rx->key = ieee80211_rx_get_bigtk(rx, mmie_keyidx);
@@ -2011,11 +2011,11 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 
 		if (mmie_keyidx < NUM_DEFAULT_KEYS ||
 		    mmie_keyidx >= NUM_DEFAULT_KEYS + NUM_DEFAULT_MGMT_KEYS)
-			return RX_DROP_M_BAD_MGMT_KEYIDX; /* unexpected BIP keyidx */
+			return RX_DROP_U_BAD_MGMT_KEYIDX; /* unexpected BIP keyidx */
 		if (rx->link_sta) {
 			if (ieee80211_is_group_privacy_action(skb) &&
 			    test_sta_flag(rx->sta, WLAN_STA_MFP))
-				return RX_DROP_MONITOR;
+				return RX_DROP;
 
 			rx->key = rcu_dereference(rx->link_sta->gtk[mmie_keyidx]);
 		}
@@ -2100,11 +2100,11 @@ ieee80211_rx_h_decrypt(struct ieee80211_rx_data *rx)
 
 	if (rx->key) {
 		if (unlikely(rx->key->flags & KEY_FLAG_TAINTED))
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		/* TODO: add threshold stuff again */
 	} else {
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	switch (rx->key->conf.cipher) {
@@ -2278,7 +2278,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 		goto out;
 
 	if (is_multicast_ether_addr(hdr->addr1))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	I802_DEBUG_INC(rx->local->rx_handlers_fragments);
 
@@ -2333,7 +2333,7 @@ ieee80211_rx_h_defragment(struct ieee80211_rx_data *rx)
 					  rx->seqno_idx, hdr);
 	if (!entry) {
 		I802_DEBUG_INC(rx->local->rx_handlers_drop_defrag);
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	/* "The receiver shall discard MSDUs and MMPDUs whose constituent
@@ -2855,25 +2855,25 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta
 		return RX_CONTINUE;
 
 	if (!pskb_may_pull(skb, sizeof(*eth) + 6))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	mesh_hdr = (struct ieee80211s_hdr *)(skb->data + sizeof(*eth));
 	mesh_hdrlen = ieee80211_get_mesh_hdrlen(mesh_hdr);
 
 	if (!pskb_may_pull(skb, sizeof(*eth) + mesh_hdrlen))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	eth = (struct ethhdr *)skb->data;
 	multicast = is_multicast_ether_addr(eth->h_dest);
 
 	mesh_hdr = (struct ieee80211s_hdr *)(eth + 1);
 	if (!mesh_hdr->ttl)
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* frame is in RMC, don't forward */
 	if (is_multicast_ether_addr(eth->h_dest) &&
 	    mesh_rmc_check(sdata, eth->h_source, mesh_hdr))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* forward packet */
 	if (sdata->crypto_tx_tailroom_needed_cnt)
@@ -2890,7 +2890,7 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta
 			/* has_a4 already checked in ieee80211_rx_mesh_check */
 			proxied_addr = mesh_hdr->eaddr2;
 		else
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		rcu_read_lock();
 		mppath = mpp_path_lookup(sdata, proxied_addr);
@@ -2922,14 +2922,14 @@ ieee80211_rx_mesh_data(struct ieee80211_sub_if_data *sdata, struct sta_info *sta
 			goto rx_accept;
 
 		IEEE80211_IFSTA_MESH_CTR_INC(ifmsh, dropped_frames_ttl);
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	if (!ifmsh->mshcfg.dot11MeshForwarding) {
 		if (is_multicast_ether_addr(eth->h_dest))
 			goto rx_accept;
 
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	skb_set_queue_mapping(skb, ieee802_1d_to_ac[skb->priority]);
@@ -3122,7 +3122,7 @@ ieee80211_rx_h_amsdu(struct ieee80211_rx_data *rx)
 		return RX_CONTINUE;
 
 	if (unlikely(!ieee80211_is_data_present(fc)))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	if (unlikely(ieee80211_has_a4(hdr->frame_control))) {
 		switch (rx->sdata->vif.type) {
@@ -3179,19 +3179,16 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 		return RX_CONTINUE;
 
 	if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
-	/*
-	 * Send unexpected-4addr-frame event to hostapd. For older versions,
-	 * also drop the frame to cooked monitor interfaces.
-	 */
+	/* Send unexpected-4addr-frame event to hostapd */
 	if (ieee80211_has_a4(hdr->frame_control) &&
 	    sdata->vif.type == NL80211_IFTYPE_AP) {
 		if (rx->sta &&
 		    !test_and_set_sta_flag(rx->sta, WLAN_STA_4ADDR_EVENT))
 			cfg80211_rx_unexpected_4addr_frame(
 				rx->sdata->dev, rx->sta->sta.addr, GFP_ATOMIC);
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	res = __ieee80211_data_to_8023(rx, &port_control);
@@ -3203,7 +3200,7 @@ ieee80211_rx_h_data(struct ieee80211_rx_data *rx)
 		return res;
 
 	if (!ieee80211_frame_allowed(rx, fc))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* directly handle TDLS channel switch requests/responses */
 	if (unlikely(((struct ethhdr *)rx->skb->data)->h_proto ==
@@ -3268,11 +3265,11 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames)
 		};
 
 		if (!rx->sta)
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		if (skb_copy_bits(skb, offsetof(struct ieee80211_bar, control),
 				  &bar_data, sizeof(bar_data)))
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		tid = le16_to_cpu(bar_data.control) >> 12;
 
@@ -3284,7 +3281,7 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames)
 
 		tid_agg_rx = rcu_dereference(rx->sta->ampdu_mlme.tid_rx[tid]);
 		if (!tid_agg_rx)
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		start_seq_num = le16_to_cpu(bar_data.start_seq_num) >> 4;
 		event.u.ba.tid = tid;
@@ -3308,12 +3305,7 @@ ieee80211_rx_h_ctrl(struct ieee80211_rx_data *rx, struct sk_buff_head *frames)
 		return RX_QUEUED;
 	}
 
-	/*
-	 * After this point, we only want management frames,
-	 * so we can drop all remaining control frames to
-	 * cooked monitor interfaces.
-	 */
-	return RX_DROP_MONITOR;
+	return RX_DROP;
 }
 
 static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata,
@@ -3422,10 +3414,10 @@ ieee80211_rx_h_mgmt_check(struct ieee80211_rx_data *rx)
 	 * and unknown (reserved) frames are useless.
 	 */
 	if (rx->skb->len < 24)
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	if (!ieee80211_is_mgmt(mgmt->frame_control))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* drop too small action frames */
 	if (ieee80211_is_action(mgmt->frame_control) &&
@@ -3951,17 +3943,16 @@ ieee80211_rx_h_action_return(struct ieee80211_rx_data *rx)
 	 * ones. For all other modes we will return them to the sender,
 	 * setting the 0x80 bit in the action category, as required by
 	 * 802.11-2012 9.24.4.
-	 * Newer versions of hostapd shall also use the management frame
-	 * registration mechanisms, but older ones still use cooked
-	 * monitor interfaces so push all frames there.
+	 * Newer versions of hostapd use the management frame registration
+	 * mechanisms and old cooked monitor interface is no longer supported.
 	 */
 	if (!(status->rx_flags & IEEE80211_RX_MALFORMED_ACTION_FRM) &&
 	    (sdata->vif.type == NL80211_IFTYPE_AP ||
 	     sdata->vif.type == NL80211_IFTYPE_AP_VLAN))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	if (is_multicast_ether_addr(mgmt->da))
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* do not return rejected action frames */
 	if (mgmt->u.action.category & 0x80)
@@ -4006,7 +3997,7 @@ ieee80211_rx_h_ext(struct ieee80211_rx_data *rx)
 		return RX_CONTINUE;
 
 	if (sdata->vif.type != NL80211_IFTYPE_STATION)
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	/* for now only beacons are ext, so queue them */
 	ieee80211_queue_skb_to_iface(sdata, rx->link_id, rx->sta, rx->skb);
@@ -4027,7 +4018,7 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 	    sdata->vif.type != NL80211_IFTYPE_ADHOC &&
 	    sdata->vif.type != NL80211_IFTYPE_OCB &&
 	    sdata->vif.type != NL80211_IFTYPE_STATION)
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 
 	switch (stype) {
 	case cpu_to_le16(IEEE80211_STYPE_AUTH):
@@ -4038,32 +4029,32 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 	case cpu_to_le16(IEEE80211_STYPE_DEAUTH):
 		if (is_multicast_ether_addr(mgmt->da) &&
 		    !is_broadcast_ether_addr(mgmt->da))
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		/* process only for station/IBSS */
 		if (sdata->vif.type != NL80211_IFTYPE_STATION &&
 		    sdata->vif.type != NL80211_IFTYPE_ADHOC)
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 		break;
 	case cpu_to_le16(IEEE80211_STYPE_ASSOC_RESP):
 	case cpu_to_le16(IEEE80211_STYPE_REASSOC_RESP):
 	case cpu_to_le16(IEEE80211_STYPE_DISASSOC):
 		if (is_multicast_ether_addr(mgmt->da) &&
 		    !is_broadcast_ether_addr(mgmt->da))
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 
 		/* process only for station */
 		if (sdata->vif.type != NL80211_IFTYPE_STATION)
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 		break;
 	case cpu_to_le16(IEEE80211_STYPE_PROBE_REQ):
 		/* process only for ibss and mesh */
 		if (sdata->vif.type != NL80211_IFTYPE_ADHOC &&
 		    sdata->vif.type != NL80211_IFTYPE_MESH_POINT)
-			return RX_DROP_MONITOR;
+			return RX_DROP;
 		break;
 	default:
-		return RX_DROP_MONITOR;
+		return RX_DROP;
 	}
 
 	ieee80211_queue_skb_to_iface(sdata, rx->link_id, rx->sta, rx->skb);
@@ -4071,82 +4062,9 @@ ieee80211_rx_h_mgmt(struct ieee80211_rx_data *rx)
 	return RX_QUEUED;
 }
 
-static void ieee80211_rx_cooked_monitor(struct ieee80211_rx_data *rx,
-					struct ieee80211_rate *rate,
-					ieee80211_rx_result reason)
-{
-	struct ieee80211_sub_if_data *sdata;
-	struct ieee80211_local *local = rx->local;
-	struct sk_buff *skb = rx->skb, *skb2;
-	struct net_device *prev_dev = NULL;
-	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb);
-	int needed_headroom;
-
-	/*
-	 * If cooked monitor has been processed already, then
-	 * don't do it again. If not, set the flag.
-	 */
-	if (rx->flags & IEEE80211_RX_CMNTR)
-		goto out_free_skb;
-	rx->flags |= IEEE80211_RX_CMNTR;
-
-	/* If there are no cooked monitor interfaces, just free the SKB */
-	if (!local->cooked_mntrs)
-		goto out_free_skb;
-
-	/* room for the radiotap header based on driver features */
-	needed_headroom = ieee80211_rx_radiotap_hdrlen(local, status, skb);
-
-	if (skb_headroom(skb) < needed_headroom &&
-	    pskb_expand_head(skb, needed_headroom, 0, GFP_ATOMIC))
-		goto out_free_skb;
-
-	/* prepend radiotap information */
-	ieee80211_add_rx_radiotap_header(local, skb, rate, needed_headroom,
-					 false);
-
-	skb_reset_mac_header(skb);
-	skb->ip_summed = CHECKSUM_UNNECESSARY;
-	skb->pkt_type = PACKET_OTHERHOST;
-	skb->protocol = htons(ETH_P_802_2);
-
-	list_for_each_entry_rcu(sdata, &local->interfaces, list) {
-		if (!ieee80211_sdata_running(sdata))
-			continue;
-
-		if (sdata->vif.type != NL80211_IFTYPE_MONITOR ||
-		    !(sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES))
-			continue;
-
-		if (prev_dev) {
-			skb2 = skb_clone(skb, GFP_ATOMIC);
-			if (skb2) {
-				skb2->dev = prev_dev;
-				netif_receive_skb(skb2);
-			}
-		}
-
-		prev_dev = sdata->dev;
-		dev_sw_netstats_rx_add(sdata->dev, skb->len);
-	}
-
-	if (prev_dev) {
-		skb->dev = prev_dev;
-		netif_receive_skb(skb);
-		return;
-	}
-
- out_free_skb:
-	kfree_skb_reason(skb, (__force u32)reason);
-}
-
 static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx,
 					 ieee80211_rx_result res)
 {
-	struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(rx->skb);
-	struct ieee80211_supported_band *sband;
-	struct ieee80211_rate *rate = NULL;
-
 	if (res == RX_QUEUED) {
 		I802_DEBUG_INC(rx->sdata->local->rx_handlers_queued);
 		return;
@@ -4158,23 +4076,13 @@ static void ieee80211_rx_handlers_result(struct ieee80211_rx_data *rx,
 			rx->link_sta->rx_stats.dropped++;
 	}
 
-	if (u32_get_bits((__force u32)res, SKB_DROP_REASON_SUBSYS_MASK) ==
-			SKB_DROP_REASON_SUBSYS_MAC80211_UNUSABLE) {
-		kfree_skb_reason(rx->skb, (__force u32)res);
-		return;
-	}
-
-	sband = rx->local->hw.wiphy->bands[status->band];
-	if (status->encoding == RX_ENC_LEGACY)
-		rate = &sband->bitrates[status->rate_idx];
-
-	ieee80211_rx_cooked_monitor(rx, rate, res);
+	kfree_skb_reason(rx->skb, (__force u32)res);
 }
 
 static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx,
 				  struct sk_buff_head *frames)
 {
-	ieee80211_rx_result res = RX_DROP_MONITOR;
+	ieee80211_rx_result res = RX_DROP;
 	struct sk_buff *skb;
 
 #define CALL_RXH(rxh)			\
@@ -4238,7 +4146,7 @@ static void ieee80211_rx_handlers(struct ieee80211_rx_data *rx,
 static void ieee80211_invoke_rx_handlers(struct ieee80211_rx_data *rx)
 {
 	struct sk_buff_head reorder_release;
-	ieee80211_rx_result res = RX_DROP_MONITOR;
+	ieee80211_rx_result res = RX_DROP;
 
 	__skb_queue_head_init(&reorder_release);
 
diff --git a/net/mac80211/status.c b/net/mac80211/status.c
index 5f28f3633fa0a..b17b3cc7fb903 100644
--- a/net/mac80211/status.c
+++ b/net/mac80211/status.c
@@ -895,8 +895,7 @@ static int ieee80211_tx_get_rates(struct ieee80211_hw *hw,
 }
 
 void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
-			  int retry_count, bool send_to_cooked,
-			  struct ieee80211_tx_status *status)
+			  int retry_count, struct ieee80211_tx_status *status)
 {
 	struct sk_buff *skb2;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
@@ -930,10 +929,6 @@ void ieee80211_tx_monitor(struct ieee80211_local *local, struct sk_buff *skb,
 			if (sdata->u.mntr.flags & MONITOR_FLAG_SKIP_TX)
 				continue;
 
-			if ((sdata->u.mntr.flags & MONITOR_FLAG_COOK_FRAMES) &&
-			    !send_to_cooked)
-				continue;
-
 			if (prev_dev) {
 				skb2 = skb_clone(skb, GFP_ATOMIC);
 				if (skb2) {
@@ -964,7 +959,6 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 	struct ieee80211_tx_info *info = status->info;
 	struct sta_info *sta;
 	__le16 fc;
-	bool send_to_cooked;
 	bool acked;
 	bool noack_success;
 	struct ieee80211_bar *bar;
@@ -1091,28 +1085,10 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw,
 
 	ieee80211_report_used_skb(local, skb, false, status->ack_hwtstamp);
 
-	/* this was a transmitted frame, but now we want to reuse it */
-	skb_orphan(skb);
-
-	/* Need to make a copy before skb->cb gets cleared */
-	send_to_cooked = !!(info->flags & IEEE80211_TX_CTL_INJECTED) ||
-			 !(ieee80211_is_data(fc));
-
-	/*
-	 * This is a bit racy but we can avoid a lot of work
-	 * with this test...
-	 */
-	if (!local->tx_mntrs && (!send_to_cooked || !local->cooked_mntrs)) {
-		if (status->free_list)
-			list_add_tail(&skb->list, status->free_list);
-		else
-			dev_kfree_skb(skb);
-		return;
-	}
-
-	/* send to monitor interfaces */
-	ieee80211_tx_monitor(local, skb, retry_count,
-			     send_to_cooked, status);
+	if (status->free_list)
+		list_add_tail(&skb->list, status->free_list);
+	else
+		dev_kfree_skb(skb);
 }
 
 void ieee80211_tx_status_skb(struct ieee80211_hw *hw, struct sk_buff *skb)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index a24636bda6793..1289df373795e 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -5617,7 +5617,7 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw,
 	if (!copy)
 		return bcn;
 
-	ieee80211_tx_monitor(hw_to_local(hw), copy, 1, false, NULL);
+	ieee80211_tx_monitor(hw_to_local(hw), copy, 1, NULL);
 
 	return bcn;
 }

From c54979a3abc40986996472632a32871951750b69 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 5 Feb 2025 11:13:33 +1030
Subject: [PATCH 0356/2753] wifi: qtnfmac: Avoid multiple
 -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of other structs, we use the `__struct_group()` helper to
create a new tagged `struct qlink_tlv_hdr_fixed`. This structure
groups together all the members of the flexible `struct qlink_tlv_hdr`
except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct member currently causing
trouble from `struct qlink_tlv_hdr` to `struct qlink_tlv_hdr_fixed`.

We also want to ensure that when new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that
the memory layout for both the flexible structure and the new tagged
struct is the same after any changes.

This approach avoids having to implement `struct qlink_tlv_hdr_fixed`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

So, with this changes, fix 66 of the following warnings:
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1681:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1660:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1646:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1621:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1609:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/quantenna/qtnfmac/qlink.h:1570:30: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://patch.msgid.link/Z6K0Nd_IprrhS6pn@kspp
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/quantenna/qtnfmac/qlink.h    | 21 ++++++++++++-------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/quantenna/qtnfmac/qlink.h b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
index 674461fa7fb34..eae35b678952d 100644
--- a/drivers/net/wireless/quantenna/qtnfmac/qlink.h
+++ b/drivers/net/wireless/quantenna/qtnfmac/qlink.h
@@ -1510,10 +1510,15 @@ enum qlink_tlv_id {
 };
 
 struct qlink_tlv_hdr {
-	__le16 type;
-	__le16 len;
+	/* New members MUST be added within the struct_group() macro below. */
+	__struct_group(qlink_tlv_hdr_fixed, __hdr, __packed,
+		__le16 type;
+		__le16 len;
+	);
 	u8 val[];
 } __packed;
+static_assert(offsetof(struct qlink_tlv_hdr, val) == sizeof(struct qlink_tlv_hdr_fixed),
+	      "struct member likely outside of __struct_group()");
 
 struct qlink_iface_limit {
 	__le16 max_num;
@@ -1567,7 +1572,7 @@ enum qlink_reg_rule_flags {
  * @dfs_cac_ms: DFS CAC period.
  */
 struct qlink_tlv_reg_rule {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	__le32 start_freq_khz;
 	__le32 end_freq_khz;
 	__le32 max_bandwidth_khz;
@@ -1606,7 +1611,7 @@ enum qlink_dfs_state {
  * @channel: ieee80211 channel settings.
  */
 struct qlink_tlv_channel {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	struct qlink_channel chan;
 } __packed;
 
@@ -1618,7 +1623,7 @@ struct qlink_tlv_channel {
  * @chan: channel definition data.
  */
 struct qlink_tlv_chandef {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	struct qlink_chandef chdef;
 } __packed;
 
@@ -1643,7 +1648,7 @@ enum qlink_ie_set_type {
  * @ie_data: IEs data.
  */
 struct qlink_tlv_ie_set {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	u8 type;
 	u8 flags;
 	u8 rsvd[2];
@@ -1657,7 +1662,7 @@ struct qlink_tlv_ie_set {
  * @ie_data: IEs data.
  */
 struct qlink_tlv_ext_ie {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	u8 eid_ext;
 	u8 rsvd[3];
 	u8 ie_data[];
@@ -1678,7 +1683,7 @@ struct qlink_sband_iftype_data {
  * @iftype_data: interface type data entries.
  */
 struct qlink_tlv_iftype_data {
-	struct qlink_tlv_hdr hdr;
+	struct qlink_tlv_hdr_fixed hdr;
 	u8 n_iftype_data;
 	u8 rsvd[3];
 	struct qlink_sband_iftype_data iftype_data[];

From 31320ccb09a06df35d1cd1fe2531c55fe983ca19 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 11:39:11 +0200
Subject: [PATCH 0357/2753] wifi: cfg80211: Fix trace print for removed links

Print the mask of removed links in hexadecimal.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.1dd2831cab5f.Ib9f5e82286f0352cd057b4bf76737223e9de8274@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/trace.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 4f0abd5d49df8..9aa8081ca454f 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -4118,7 +4118,7 @@ TRACE_EVENT(cfg80211_links_removed,
 		NETDEV_ASSIGN;
 		__entry->link_mask = link_mask;
 	),
-	TP_printk(NETDEV_PR_FMT ", link_mask:%u", NETDEV_PR_ARG,
+	TP_printk(NETDEV_PR_FMT ", link_mask:0x%x", NETDEV_PR_ARG,
 		  __entry->link_mask)
 );
 

From 9696b80b87a0db5779f37c7818650966dd32d4ee Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 11:39:12 +0200
Subject: [PATCH 0358/2753] wifi: mac80211: Refactor ieee80211_sta_wmm_params()

The function first updates the link configuration and then
calls the driver to set the link parameters. Since the call
to the driver might sleep, split the function such that
the link configuration could be done without calling the
driver. This would be useful in cases that WMM parameters
need to be configured, but the current locking doesn't allow
to call the driver.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.b1cedcf93763.I65783c102d44127035838f97fab64ec4df5c40f3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 21 +++++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f8d52b3b0d0e4..6feb4ce2c90d5 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3375,10 +3375,10 @@ void ieee80211_mgd_set_link_qos_params(struct ieee80211_link_data *link)
 
 /* MLME */
 static bool
-ieee80211_sta_wmm_params(struct ieee80211_local *local,
-			 struct ieee80211_link_data *link,
-			 const u8 *wmm_param, size_t wmm_param_len,
-			 const struct ieee80211_mu_edca_param_set *mu_edca)
+_ieee80211_sta_wmm_params(struct ieee80211_local *local,
+			  struct ieee80211_link_data *link,
+			  const u8 *wmm_param, size_t wmm_param_len,
+			  const struct ieee80211_mu_edca_param_set *mu_edca)
 {
 	struct ieee80211_sub_if_data *sdata = link->sdata;
 	struct ieee80211_tx_queue_params params[IEEE80211_NUM_ACS];
@@ -3507,6 +3507,19 @@ ieee80211_sta_wmm_params(struct ieee80211_local *local,
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++)
 		link->tx_conf[ac] = params[ac];
 
+	return true;
+}
+
+static bool
+ieee80211_sta_wmm_params(struct ieee80211_local *local,
+			 struct ieee80211_link_data *link,
+			 const u8 *wmm_param, size_t wmm_param_len,
+			 const struct ieee80211_mu_edca_param_set *mu_edca)
+{
+	if (!_ieee80211_sta_wmm_params(local, link, wmm_param, wmm_param_len,
+				       mu_edca))
+		return false;
+
 	ieee80211_mgd_set_link_qos_params(link);
 
 	/* enable WMM or activate new settings */

From de86c5f60839dc0d771711a848b4f55ad3f90844 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 11:39:13 +0200
Subject: [PATCH 0359/2753] wifi: mac80211: Add support for EPCS configuration

Add support for configuring EPCS state:

- When EPCS is enabled, send an EPCS enable request action frame
  to the AP. When the AP replies with EPCS enable response, enable
  EPCS by applying the QoS parameters provided by the AP. Do so for
  all the valid MLD links. Once EPCS is enabled, support processing
  of unsolicited EPCS enable response frames.
- When EPCS is disabled, send an EPCS teardown request to the AP
  and apply the QoS parameters as obtained from the last received
  beacons. Do so for all the valid links.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.7a90afd7e140.I3f602d65f5c1fd849d6c70b12307dda33aa91ccb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  |   7 +
 include/net/mac80211.h     |   3 +-
 net/mac80211/cfg.c         |   9 ++
 net/mac80211/ieee80211_i.h |  11 ++
 net/mac80211/iface.c       |   8 +
 net/mac80211/mlme.c        | 291 ++++++++++++++++++++++++++++++++++++-
 net/mac80211/rx.c          |  17 +++
 7 files changed, 344 insertions(+), 2 deletions(-)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 16741e542e81c..8f35a3a5211cf 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1543,6 +1543,10 @@ struct ieee80211_mgmt {
 					u8 count;
 					u8 variable[];
 				} __packed ml_reconf_resp;
+				struct {
+					u8 action_code;
+					u8 variable[];
+				} __packed epcs;
 			} u;
 		} __packed action;
 		DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */
@@ -5570,6 +5574,9 @@ static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data,
 	       fixed + prof->sta_info_len - 1 <= len;
 }
 
+#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID			0x000f
+#define IEEE80211_EPCS_ENA_RESP_BODY_LEN                        3
+
 static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len)
 {
 	const struct ieee80211_ttlm_elem *t2l = (const void *)data;
diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index c3ed2fcff8b79..a3a0de4a5d630 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -702,6 +702,7 @@ struct ieee80211_parsed_tpe {
  * @tpe: transmit power envelope information
  * @pwr_reduction: power constraint of BSS.
  * @eht_support: does this BSS support EHT
+ * @epcs_support: does this BSS support EPCS
  * @csa_active: marks whether a channel switch is going on.
  * @mu_mimo_owner: indicates interface owns MU-MIMO capability
  * @chanctx_conf: The channel context this interface is assigned to, or %NULL
@@ -823,7 +824,7 @@ struct ieee80211_bss_conf {
 
 	u8 pwr_reduction;
 	bool eht_support;
-
+	bool epcs_support;
 	bool csa_active;
 
 	bool mu_mimo_owner;
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 88949b90f117e..5785fe30adaa1 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5196,6 +5196,14 @@ ieee80211_assoc_ml_reconf(struct wiphy *wiphy, struct net_device *dev,
 	return ieee80211_mgd_assoc_ml_reconf(sdata, add_links, rem_links);
 }
 
+static int
+ieee80211_set_epcs(struct wiphy *wiphy, struct net_device *dev, bool enable)
+{
+	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
+
+	return ieee80211_mgd_set_epcs(sdata, enable);
+}
+
 const struct cfg80211_ops mac80211_config_ops = {
 	.add_virtual_intf = ieee80211_add_iface,
 	.del_virtual_intf = ieee80211_del_iface,
@@ -5311,4 +5319,5 @@ const struct cfg80211_ops mac80211_config_ops = {
 	.set_ttlm = ieee80211_set_ttlm,
 	.get_radio_mask = ieee80211_get_radio_mask,
 	.assoc_ml_reconf = ieee80211_assoc_ml_reconf,
+	.set_epcs = ieee80211_set_epcs,
 };
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index a90a44aa5758b..b6c769fc9abf6 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -613,6 +613,12 @@ struct ieee80211_if_managed {
 		u16 added_links;
 		u8 dialog_token;
 	} reconf;
+
+	/* Support for epcs */
+	struct {
+		bool enabled;
+		u8 dialog_token;
+	} epcs;
 };
 
 struct ieee80211_if_ibss {
@@ -2775,6 +2781,11 @@ int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata,
 void ieee80211_check_wbrf_support(struct ieee80211_local *local);
 void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef);
 void ieee80211_remove_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef);
+int ieee80211_mgd_set_epcs(struct ieee80211_sub_if_data *sdata, bool enable);
+void ieee80211_process_epcs_ena_resp(struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_mgmt *mgmt, size_t len);
+void ieee80211_process_epcs_teardown(struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_mgmt *mgmt, size_t len);
 
 int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 				  struct cfg80211_assoc_link *add_links,
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 7d3ebfcb8c2b0..56fde5afe79a8 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1556,6 +1556,14 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local,
 				ieee80211_process_ml_reconf_resp(sdata, mgmt,
 								 skb->len);
 				break;
+			case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP:
+				ieee80211_process_epcs_ena_resp(sdata, mgmt,
+								skb->len);
+				break;
+			case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN:
+				ieee80211_process_epcs_teardown(sdata, mgmt,
+								skb->len);
+				break;
 			default:
 				break;
 			}
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 6feb4ce2c90d5..aaf84c52cd2d8 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3794,6 +3794,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	/* other links will be destroyed */
 	sdata->deflink.conf->bss = NULL;
+	sdata->deflink.conf->epcs_support = false;
 	sdata->deflink.smps_mode = IEEE80211_SMPS_OFF;
 
 	netif_carrier_off(sdata->dev);
@@ -3980,6 +3981,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	 * when the flow started.
 	 */
 	ieee80211_ml_reconf_reset(sdata);
+
+	ifmgd->epcs.enabled = false;
+	ifmgd->epcs.dialog_token = 0;
 }
 
 static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata)
@@ -4848,6 +4852,82 @@ static bool ieee80211_twt_bcast_support(struct ieee80211_sub_if_data *sdata,
 			IEEE80211_HE_MAC_CAP2_BCAST_TWT);
 }
 
+static void ieee80211_epcs_changed(struct ieee80211_sub_if_data *sdata,
+				   bool enabled)
+{
+	/* in any case this is called, dialog token should be reset */
+	sdata->u.mgd.epcs.dialog_token = 0;
+
+	if (sdata->u.mgd.epcs.enabled == enabled)
+		return;
+
+	sdata->u.mgd.epcs.enabled = enabled;
+	cfg80211_epcs_changed(sdata->dev, enabled);
+}
+
+static void ieee80211_epcs_teardown(struct ieee80211_sub_if_data *sdata)
+{
+	struct ieee80211_local *local = sdata->local;
+	u8 link_id;
+
+	if (!sdata->u.mgd.epcs.enabled)
+		return;
+
+	lockdep_assert_wiphy(local->hw.wiphy);
+
+	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
+		struct ieee802_11_elems *elems;
+		struct ieee80211_link_data *link;
+		const struct cfg80211_bss_ies *ies;
+		bool ret;
+
+		rcu_read_lock();
+
+		link = sdata_dereference(sdata->link[link_id], sdata);
+		if (!link || !link->conf || !link->conf->bss) {
+			rcu_read_unlock();
+			continue;
+		}
+
+		if (link->u.mgd.disable_wmm_tracking) {
+			rcu_read_unlock();
+			ieee80211_set_wmm_default(link, false, false);
+			continue;
+		}
+
+		ies = rcu_dereference(link->conf->bss->beacon_ies);
+		if (!ies) {
+			rcu_read_unlock();
+			ieee80211_set_wmm_default(link, false, false);
+			continue;
+		}
+
+		elems = ieee802_11_parse_elems(ies->data, ies->len, false,
+					       NULL);
+		if (!elems) {
+			rcu_read_unlock();
+			ieee80211_set_wmm_default(link, false, false);
+			continue;
+		}
+
+		ret = _ieee80211_sta_wmm_params(local, link,
+						elems->wmm_param,
+						elems->wmm_param_len,
+						elems->mu_edca_param_set);
+
+		kfree(elems);
+		rcu_read_unlock();
+
+		if (!ret) {
+			ieee80211_set_wmm_default(link, false, false);
+			continue;
+		}
+
+		ieee80211_mgd_set_link_qos_params(link);
+		ieee80211_link_info_change_notify(sdata, link, BSS_CHANGED_QOS);
+	}
+}
+
 static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 					struct link_sta_info *link_sta,
 					struct cfg80211_bss *cbss,
@@ -5121,14 +5201,27 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 							    link_sta);
 
 			bss_conf->eht_support = link_sta->pub->eht_cap.has_eht;
+			bss_conf->epcs_support = bss_conf->eht_support &&
+				!!(elems->eht_cap->fixed.mac_cap_info[0] &
+				   IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS);
+
+			/* EPCS might be already enabled but a new added link
+			 * does not support EPCS. This should not really happen
+			 * in practice.
+			 */
+			if (sdata->u.mgd.epcs.enabled &&
+			    !bss_conf->epcs_support)
+				ieee80211_epcs_teardown(sdata);
 		} else {
 			bss_conf->eht_support = false;
+			bss_conf->epcs_support = false;
 		}
 	} else {
 		bss_conf->he_support = false;
 		bss_conf->twt_requester = false;
 		bss_conf->twt_protected = false;
 		bss_conf->eht_support = false;
+		bss_conf->epcs_support = false;
 	}
 
 	bss_conf->twt_broadcast =
@@ -7159,7 +7252,8 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 
 	ieee80211_mgd_update_bss_param_ch_cnt(sdata, bss_conf, elems);
 
-	if (!link->u.mgd.disable_wmm_tracking &&
+	if (!sdata->u.mgd.epcs.enabled &&
+	    !link->u.mgd.disable_wmm_tracking &&
 	    ieee80211_sta_wmm_params(local, link, elems->wmm_param,
 				     elems->wmm_param_len,
 				     elems->mu_edca_param_set))
@@ -10334,3 +10428,198 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	kfree(data);
 	return err;
 }
+
+static bool ieee80211_mgd_epcs_supp(struct ieee80211_sub_if_data *sdata)
+{
+	unsigned long valid_links = sdata->vif.valid_links;
+	u8 link_id;
+
+	lockdep_assert_wiphy(sdata->local->hw.wiphy);
+
+	if (!ieee80211_vif_is_mld(&sdata->vif))
+		return false;
+
+	for_each_set_bit(link_id, &valid_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *bss_conf =
+			sdata_dereference(sdata->vif.link_conf[link_id], sdata);
+
+		if (WARN_ON(!bss_conf) || !bss_conf->epcs_support)
+			return false;
+	}
+
+	return true;
+}
+
+int ieee80211_mgd_set_epcs(struct ieee80211_sub_if_data *sdata, bool enable)
+{
+	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_mgmt *mgmt;
+	struct sk_buff *skb;
+	int frame_len = offsetofend(struct ieee80211_mgmt,
+				    u.action.u.epcs) + (enable ? 1 : 0);
+
+	if (!ieee80211_mgd_epcs_supp(sdata))
+		return -EINVAL;
+
+	if (sdata->u.mgd.epcs.enabled == enable &&
+	    !sdata->u.mgd.epcs.dialog_token)
+		return 0;
+
+	/* Do not allow enabling EPCS if the AP didn't respond yet.
+	 * However, allow disabling EPCS in such a case.
+	 */
+	if (sdata->u.mgd.epcs.dialog_token && enable)
+		return -EALREADY;
+
+	skb = dev_alloc_skb(local->hw.extra_tx_headroom + frame_len);
+	if (!skb)
+		return -ENOBUFS;
+
+	skb_reserve(skb, local->hw.extra_tx_headroom);
+	mgmt = skb_put_zero(skb, frame_len);
+	mgmt->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
+					  IEEE80211_STYPE_ACTION);
+	memcpy(mgmt->da, sdata->vif.cfg.ap_addr, ETH_ALEN);
+	memcpy(mgmt->sa, sdata->vif.addr, ETH_ALEN);
+	memcpy(mgmt->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
+
+	mgmt->u.action.category = WLAN_CATEGORY_PROTECTED_EHT;
+	if (enable) {
+		u8 *pos = mgmt->u.action.u.epcs.variable;
+
+		mgmt->u.action.u.epcs.action_code =
+			WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ;
+
+		*pos = ++sdata->u.mgd.dialog_token_alloc;
+		sdata->u.mgd.epcs.dialog_token = *pos;
+	} else {
+		mgmt->u.action.u.epcs.action_code =
+			WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN;
+
+		ieee80211_epcs_teardown(sdata);
+		ieee80211_epcs_changed(sdata, false);
+	}
+
+	ieee80211_tx_skb(sdata, skb);
+	return 0;
+}
+
+static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata,
+			      struct ieee802_11_elems *elems)
+{
+	const struct element *sub;
+	size_t scratch_len = elems->ml_epcs_len;
+	u8 *scratch __free(kfree) = kzalloc(scratch_len, GFP_KERNEL);
+
+	lockdep_assert_wiphy(sdata->local->hw.wiphy);
+
+	if (!ieee80211_vif_is_mld(&sdata->vif) || !elems->ml_epcs)
+		return;
+
+	if (WARN_ON(!scratch))
+		return;
+
+	/* Directly parse the sub elements as the common information doesn't
+	 * hold any useful information.
+	 */
+	for_each_mle_subelement(sub, (const u8 *)elems->ml_epcs,
+				elems->ml_epcs_len) {
+		struct ieee80211_link_data *link;
+		struct ieee802_11_elems *link_elems __free(kfree);
+		u8 *pos = (void *)sub->data;
+		u16 control;
+		ssize_t len;
+		u8 link_id;
+
+		if (sub->id != IEEE80211_MLE_SUBELEM_PER_STA_PROFILE)
+			continue;
+
+		if (sub->datalen < sizeof(control))
+			break;
+
+		control = get_unaligned_le16(pos);
+		link_id = control & IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID;
+
+		link = sdata_dereference(sdata->link[link_id], sdata);
+		if (!link)
+			continue;
+
+		len = cfg80211_defragment_element(sub, (u8 *)elems->ml_epcs,
+						  elems->ml_epcs_len,
+						  scratch, scratch_len,
+						  IEEE80211_MLE_SUBELEM_FRAGMENT);
+		if (len < sizeof(control))
+			continue;
+
+		pos = scratch + sizeof(control);
+		len -= sizeof(control);
+
+		link_elems = ieee802_11_parse_elems(pos, len, false, NULL);
+		if (!link_elems)
+			continue;
+
+		if (ieee80211_sta_wmm_params(sdata->local, link,
+					     link_elems->wmm_param,
+					     link_elems->wmm_param_len,
+					     link_elems->mu_edca_param_set))
+			ieee80211_link_info_change_notify(sdata, link,
+							  BSS_CHANGED_QOS);
+	}
+}
+
+void ieee80211_process_epcs_ena_resp(struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_mgmt *mgmt, size_t len)
+{
+	struct ieee802_11_elems *elems __free(kfree) = NULL;
+	size_t ies_len;
+	u16 status_code;
+	u8 *pos, dialog_token;
+
+	if (!ieee80211_mgd_epcs_supp(sdata))
+		return;
+
+	/* Handle dialog token and status code */
+	pos = mgmt->u.action.u.epcs.variable;
+	dialog_token = *pos;
+	status_code = get_unaligned_le16(pos + 1);
+
+	/* An EPCS enable response with dialog token == 0 is an unsolicited
+	 * notification from the AP MLD. In such a case, EPCS should already be
+	 * enabled and status must be success
+	 */
+	if (!dialog_token &&
+	    (!sdata->u.mgd.epcs.enabled ||
+	     status_code != WLAN_STATUS_SUCCESS))
+		return;
+
+	if (sdata->u.mgd.epcs.dialog_token != dialog_token)
+		return;
+
+	sdata->u.mgd.epcs.dialog_token = 0;
+
+	if (status_code != WLAN_STATUS_SUCCESS)
+		return;
+
+	pos += IEEE80211_EPCS_ENA_RESP_BODY_LEN;
+	ies_len = len - offsetof(struct ieee80211_mgmt,
+				 u.action.u.epcs.variable) -
+		IEEE80211_EPCS_ENA_RESP_BODY_LEN;
+
+	elems = ieee802_11_parse_elems(pos, ies_len, true, NULL);
+	if (!elems)
+		return;
+
+	ieee80211_ml_epcs(sdata, elems);
+	ieee80211_epcs_changed(sdata, true);
+}
+
+void ieee80211_process_epcs_teardown(struct ieee80211_sub_if_data *sdata,
+				     struct ieee80211_mgmt *mgmt, size_t len)
+{
+	if (!ieee80211_vif_is_mld(&sdata->vif) ||
+	    !sdata->u.mgd.epcs.enabled)
+		return;
+
+	ieee80211_epcs_teardown(sdata);
+	ieee80211_epcs_changed(sdata, false);
+}
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index d33970009e00d..1790e7221a145 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3823,6 +3823,23 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 					u.action.u.ml_reconf_resp) + 3)
 				goto invalid;
 			goto queue;
+		case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP:
+			if (sdata->vif.type != NL80211_IFTYPE_STATION)
+				break;
+
+			if (len < offsetofend(typeof(*mgmt),
+					      u.action.u.epcs) +
+			    IEEE80211_EPCS_ENA_RESP_BODY_LEN)
+				goto invalid;
+			goto queue;
+		case WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN:
+			if (sdata->vif.type != NL80211_IFTYPE_STATION)
+				break;
+
+			if (len < offsetofend(typeof(*mgmt),
+					      u.action.u.epcs))
+				goto invalid;
+			goto queue;
 		default:
 			break;
 		}

From 282eeec9196fc6593540c7bf7479305a8384de32 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 11:39:14 +0200
Subject: [PATCH 0360/2753] wifi: ieee80211: Add missing EHT MAC capabilities

Add missing EHT MAC capabilities definitions.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.6c1643c345a1.I7405b9c35cb39ae97a52c3fbcc36b0bd81e495dc@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 8f35a3a5211cf..508d466de1cc2 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -3113,6 +3113,11 @@ ieee80211_he_spr_size(const u8 *he_spr_ie)
 #define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454	        2
 
 #define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK		0x01
+#define IEEE80211_EHT_MAC_CAP1_EHT_TRS				0x02
+#define IEEE80211_EHT_MAC_CAP1_TXOP_RET				0x04
+#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS				0x08
+#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK		0x30
+#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS		0x40
 
 /* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */
 #define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ			0x02

From 8b8a673155edb97a0938fb7900dc83a7d80ca0ff Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 11:39:15 +0200
Subject: [PATCH 0361/2753] wifi: mac80211: Add processing of TTLM teardown
 frame

Add processing of negotiated TTLM tear down frame.
Handle this frame similar to the way a locally initiated
tear down is handled.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.860691076786.I32df71182c25c5f84e4534f40efe1316926b8249@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  1 +
 net/mac80211/iface.c       |  3 +++
 net/mac80211/mlme.c        | 16 +++++++++++-----
 net/mac80211/rx.c          |  8 ++++++++
 4 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index b6c769fc9abf6..df7c803134fd8 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2777,6 +2777,7 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
 				    struct ieee80211_mgmt *mgmt, size_t len);
 int ieee80211_req_neg_ttlm(struct ieee80211_sub_if_data *sdata,
 			   struct cfg80211_ttlm_params *params);
+void ieee80211_process_ttlm_teardown(struct ieee80211_sub_if_data *sdata);
 
 void ieee80211_check_wbrf_support(struct ieee80211_local *local);
 void ieee80211_add_wbrf(struct ieee80211_local *local, struct cfg80211_chan_def *chandef);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 56fde5afe79a8..edb4ca333528d 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1552,6 +1552,9 @@ static void ieee80211_iface_process_skb(struct ieee80211_local *local,
 				ieee80211_process_neg_ttlm_res(sdata, mgmt,
 							       skb->len);
 				break;
+			case WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN:
+				ieee80211_process_ttlm_teardown(sdata);
+				break;
 			case WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP:
 				ieee80211_process_ml_reconf_resp(sdata, mgmt,
 								 skb->len);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index aaf84c52cd2d8..04e1ea43b2df8 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7705,13 +7705,9 @@ void ieee80211_process_neg_ttlm_res(struct ieee80211_sub_if_data *sdata,
 		__ieee80211_disconnect(sdata);
 }
 
-static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy,
-					 struct wiphy_work *work)
+void ieee80211_process_ttlm_teardown(struct ieee80211_sub_if_data *sdata)
 {
 	u16 new_dormant_links;
-	struct ieee80211_sub_if_data *sdata =
-		container_of(work, struct ieee80211_sub_if_data,
-			     u.mgd.teardown_ttlm_work);
 
 	if (!sdata->vif.neg_ttlm.valid)
 		return;
@@ -7726,6 +7722,16 @@ static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy,
 					       BSS_CHANGED_MLD_VALID_LINKS);
 }
 
+static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy,
+					 struct wiphy_work *work)
+{
+	struct ieee80211_sub_if_data *sdata =
+		container_of(work, struct ieee80211_sub_if_data,
+			     u.mgd.teardown_ttlm_work);
+
+	ieee80211_process_ttlm_teardown(sdata);
+}
+
 void ieee80211_send_teardown_neg_ttlm(struct ieee80211_vif *vif)
 {
 	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1790e7221a145..f40e2ea1b09ac 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -3811,6 +3811,14 @@ ieee80211_rx_h_action(struct ieee80211_rx_data *rx)
 					      u.action.u.ttlm_res))
 				goto invalid;
 			goto queue;
+		case WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN:
+			if (sdata->vif.type != NL80211_IFTYPE_STATION)
+				break;
+
+			if (len < offsetofend(typeof(*mgmt),
+					      u.action.u.ttlm_tear_down))
+				goto invalid;
+			goto queue;
 		case WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP:
 			if (sdata->vif.type != NL80211_IFTYPE_STATION)
 				break;

From 3ad4fce66e4f9d82abfc366707757e29cc14a9d2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:16 +0200
Subject: [PATCH 0362/2753] wifi: mac80211: add strict mode disabling
 workarounds

Add a strict mode where we disable certain workarounds and have
additional checks such as, for now, that VHT capabilities from
association response match those from beacon/probe response. We
can extend the checks in the future.

Make it an opt-in setting by the driver so it can be set there
in some driver-specific way, for example. Also allow setting
this one hw flag through the hwflags debugfs, by writing a new
strict=0 or strict=1 value.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.5cecb0469479.I4a69617dc60ba0d6308416ffbc3102cfd08ba068@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h |  6 ++++++
 net/mac80211/debugfs.c | 44 +++++++++++++++++++++++++++++++++++++++--
 net/mac80211/mlme.c    | 45 +++++++++++++++++++++++++++++-------------
 3 files changed, 79 insertions(+), 16 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index a3a0de4a5d630..398d4e30b0db7 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -2852,6 +2852,11 @@ struct ieee80211_txq {
  *	implements MLO, so operation can continue on other links when one
  *	link is switching.
  *
+ * @IEEE80211_HW_STRICT: strictly enforce certain things mandated by the spec
+ *	but otherwise ignored/worked around for interoperability. This is a
+ *	HW flag so drivers can opt in according to their own control, e.g. in
+ *	testing.
+ *
  * @NUM_IEEE80211_HW_FLAGS: number of hardware flags, used for sizing arrays
  */
 enum ieee80211_hw_flags {
@@ -2912,6 +2917,7 @@ enum ieee80211_hw_flags {
 	IEEE80211_HW_DISALLOW_PUNCTURING,
 	IEEE80211_HW_DISALLOW_PUNCTURING_5GHZ,
 	IEEE80211_HW_HANDLES_QUIET_CSA,
+	IEEE80211_HW_STRICT,
 
 	/* keep last, obviously */
 	NUM_IEEE80211_HW_FLAGS
diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c
index bf0a2902d93c6..69e03630f64c9 100644
--- a/net/mac80211/debugfs.c
+++ b/net/mac80211/debugfs.c
@@ -492,6 +492,7 @@ static const char *hw_flag_names[] = {
 	FLAG(DISALLOW_PUNCTURING),
 	FLAG(DISALLOW_PUNCTURING_5GHZ),
 	FLAG(HANDLES_QUIET_CSA),
+	FLAG(STRICT),
 #undef FLAG
 };
 
@@ -524,6 +525,46 @@ static ssize_t hwflags_read(struct file *file, char __user *user_buf,
 	return rv;
 }
 
+static ssize_t hwflags_write(struct file *file, const char __user *user_buf,
+			     size_t count, loff_t *ppos)
+{
+	struct ieee80211_local *local = file->private_data;
+	char buf[100];
+	int val;
+
+	if (count >= sizeof(buf))
+		return -EINVAL;
+
+	if (copy_from_user(buf, user_buf, count))
+		return -EFAULT;
+
+	if (count && buf[count - 1] == '\n')
+		buf[count - 1] = '\0';
+	else
+		buf[count] = '\0';
+
+	if (sscanf(buf, "strict=%d", &val) == 1) {
+		switch (val) {
+		case 0:
+			ieee80211_hw_set(&local->hw, STRICT);
+			return count;
+		case 1:
+			__clear_bit(IEEE80211_HW_STRICT, local->hw.flags);
+			return count;
+		default:
+			return -EINVAL;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static const struct file_operations hwflags_ops = {
+	.open = simple_open,
+	.read = hwflags_read,
+	.write = hwflags_write,
+};
+
 static ssize_t misc_read(struct file *file, char __user *user_buf,
 			 size_t count, loff_t *ppos)
 {
@@ -574,7 +615,6 @@ static ssize_t queues_read(struct file *file, char __user *user_buf,
 	return simple_read_from_buffer(user_buf, count, ppos, buf, res);
 }
 
-DEBUGFS_READONLY_FILE_OPS(hwflags);
 DEBUGFS_READONLY_FILE_OPS(queues);
 DEBUGFS_READONLY_FILE_OPS(misc);
 
@@ -651,7 +691,7 @@ void debugfs_hw_add(struct ieee80211_local *local)
 #ifdef CONFIG_PM
 	DEBUGFS_ADD_MODE(reset, 0200);
 #endif
-	DEBUGFS_ADD(hwflags);
+	DEBUGFS_ADD_MODE(hwflags, 0600);
 	DEBUGFS_ADD(user_power);
 	DEBUGFS_ADD(power);
 	DEBUGFS_ADD(hw_conf);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 04e1ea43b2df8..a963e020a2492 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -168,6 +168,9 @@ ieee80211_determine_ap_chan(struct ieee80211_sub_if_data *sdata,
 	bool no_vht = false;
 	u32 ht_cfreq;
 
+	if (ieee80211_hw_check(&sdata->local->hw, STRICT))
+		ignore_ht_channel_mismatch = false;
+
 	*chandef = (struct cfg80211_chan_def) {
 		.chan = channel,
 		.width = NL80211_CHAN_WIDTH_20_NOHT,
@@ -388,7 +391,7 @@ ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata,
 	 * zeroes, which is nonsense, and completely inconsistent with itself
 	 * (it doesn't have 8 streams). Accept the settings in this case anyway.
 	 */
-	if (!ap_min_req_set)
+	if (!ieee80211_hw_check(&sdata->local->hw, STRICT) && !ap_min_req_set)
 		return true;
 
 	/* make sure the AP is consistent with itself
@@ -448,7 +451,7 @@ ieee80211_verify_sta_he_mcs_support(struct ieee80211_sub_if_data *sdata,
 	 * zeroes, which is nonsense, and completely inconsistent with itself
 	 * (it doesn't have 8 streams). Accept the settings in this case anyway.
 	 */
-	if (!ap_min_req_set)
+	if (!ieee80211_hw_check(&sdata->local->hw, STRICT) && !ap_min_req_set)
 		return true;
 
 	/* Need to go over for 80MHz, 160MHz and for 80+80 */
@@ -1313,13 +1316,15 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	 * Some APs apparently get confused if our capabilities are better
 	 * than theirs, so restrict what we advertise in the assoc request.
 	 */
-	if (!(ap_vht_cap->vht_cap_info &
-			cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE)))
-		cap &= ~(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
-			 IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE);
-	else if (!(ap_vht_cap->vht_cap_info &
-			cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE)))
-		cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE;
+	if (!ieee80211_hw_check(&local->hw, STRICT)) {
+		if (!(ap_vht_cap->vht_cap_info &
+				cpu_to_le32(IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE)))
+			cap &= ~(IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE |
+				 IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE);
+		else if (!(ap_vht_cap->vht_cap_info &
+				cpu_to_le32(IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE)))
+			cap &= ~IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE;
+	}
 
 	/*
 	 * If some other vif is using the MU-MIMO capability we cannot associate
@@ -1361,14 +1366,16 @@ static bool ieee80211_add_vht_ie(struct ieee80211_sub_if_data *sdata,
 	return mu_mimo_owner;
 }
 
-static void ieee80211_assoc_add_rates(struct sk_buff *skb,
+static void ieee80211_assoc_add_rates(struct ieee80211_local *local,
+				      struct sk_buff *skb,
 				      enum nl80211_chan_width width,
 				      struct ieee80211_supported_band *sband,
 				      struct ieee80211_mgd_assoc_data *assoc_data)
 {
 	u32 rates;
 
-	if (assoc_data->supp_rates_len) {
+	if (assoc_data->supp_rates_len &&
+	    !ieee80211_hw_check(&local->hw, STRICT)) {
 		/*
 		 * Get all rates supported by the device and the AP as
 		 * some APs don't like getting a superset of their rates
@@ -1584,7 +1591,7 @@ ieee80211_add_link_elems(struct ieee80211_sub_if_data *sdata,
 		*capab |= WLAN_CAPABILITY_SPECTRUM_MGMT;
 
 	if (sband->band != NL80211_BAND_S1GHZ)
-		ieee80211_assoc_add_rates(skb, width, sband, assoc_data);
+		ieee80211_assoc_add_rates(local, skb, width, sband, assoc_data);
 
 	if (*capab & WLAN_CAPABILITY_SPECTRUM_MGMT ||
 	    *capab & WLAN_CAPABILITY_RADIO_MEASURE) {
@@ -2051,7 +2058,8 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 	 * for some reason check it and want it to be set, set the bit for all
 	 * pre-EHT connections as we used to do.
 	 */
-	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT)
+	if (link->u.mgd.conn.mode < IEEE80211_CONN_MODE_EHT &&
+	    !ieee80211_hw_check(&local->hw, STRICT))
 		capab |= WLAN_CAPABILITY_ESS;
 
 	/* add the elements for the assoc (main) link */
@@ -5029,7 +5037,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 	 * 2G/3G/4G wifi routers, reported models include the "Onda PN51T",
 	 * "Vodafone PocketWiFi 2", "ZTE MF60" and a similar T-Mobile device.
 	 */
-	if (!is_6ghz &&
+	if (!ieee80211_hw_check(&local->hw, STRICT) && !is_6ghz &&
 	    ((assoc_data->wmm && !elems->wmm_param) ||
 	     (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT &&
 	      (!elems->ht_cap_elem || !elems->ht_operation)) ||
@@ -5164,6 +5172,15 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 				bss_vht_cap = (const void *)elem->data;
 		}
 
+		if (ieee80211_hw_check(&local->hw, STRICT) &&
+		    (!bss_vht_cap || memcmp(bss_vht_cap, elems->vht_cap_elem,
+					    sizeof(*bss_vht_cap)))) {
+			rcu_read_unlock();
+			ret = false;
+			link_info(link, "VHT capabilities mismatch\n");
+			goto out;
+		}
+
 		ieee80211_vht_cap_ie_to_sta_vht_cap(sdata, sband,
 						    elems->vht_cap_elem,
 						    bss_vht_cap, link_sta);

From 7364a4688ba4ab4f90d9da0ebbb4e4250bae0a27 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:17 +0200
Subject: [PATCH 0363/2753] wifi: mac80211_hwsim: enable strict mode

Since we use hwsim for testing e.g. the hostapd implementation,
enable strict mode to catch errors that would otherwise not be
caught.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.85bee694f09c.I61ec37d20fe97699d47fce252dc4ae2e4475fc51@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index cf6a331d40427..d0d9dab7f11fa 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -5345,6 +5345,7 @@ static int mac80211_hwsim_new_radio(struct genl_info *info,
 	ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS);
 	ieee80211_hw_set(hw, TDLS_WIDER_BW);
 	ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID);
+	ieee80211_hw_set(hw, STRICT);
 
 	if (param->mlo) {
 		hw->wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;

From 574faa0e936d12718e2cadad11ce1e184d9e5a32 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:18 +0200
Subject: [PATCH 0364/2753] wifi: mac80211: add HT and VHT basic set
 verification

So far we did not verify the HT and VHT basic MCS set. However, in
P802.11REVme/D7.0 (6.5.4.2.4) says that the MLME-JOIN.request shall
return an error if the VHT and HT basic set requirements are not met.

Given broken APs, apply VHT basic MCS/NSS set checks only in
strict mode.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.e2d8d4095f6b.I66bcf6c2de3b9d3325e4ffd9f573f4cd26ce5685@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 129 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 129 insertions(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index a963e020a2492..3749b3e23bb7a 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -345,6 +345,115 @@ ieee80211_determine_ap_chan(struct ieee80211_sub_if_data *sdata,
 	return IEEE80211_CONN_MODE_EHT;
 }
 
+static bool
+ieee80211_verify_sta_ht_mcs_support(struct ieee80211_sub_if_data *sdata,
+				    struct ieee80211_supported_band *sband,
+				    const struct ieee80211_ht_operation *ht_op)
+{
+	struct ieee80211_sta_ht_cap sta_ht_cap;
+	int i;
+
+	if (sband->band == NL80211_BAND_6GHZ)
+		return true;
+
+	if (!ht_op)
+		return false;
+
+	memcpy(&sta_ht_cap, &sband->ht_cap, sizeof(sta_ht_cap));
+	ieee80211_apply_htcap_overrides(sdata, &sta_ht_cap);
+
+	/*
+	 * P802.11REVme/D7.0 - 6.5.4.2.4
+	 * ...
+	 * If the MLME of an HT STA receives an MLME-JOIN.request primitive
+	 * with the SelectedBSS parameter containing a Basic HT-MCS Set field
+	 * in the HT Operation parameter that contains any unsupported MCSs,
+	 * the MLME response in the resulting MLME-JOIN.confirm primitive shall
+	 * contain a ResultCode parameter that is not set to the value SUCCESS.
+	 * ...
+	 */
+
+	/* Simply check that all basic rates are in the STA RX mask */
+	for (i = 0; i < IEEE80211_HT_MCS_MASK_LEN; i++) {
+		if ((ht_op->basic_set[i] & sta_ht_cap.mcs.rx_mask[i]) !=
+		    ht_op->basic_set[i])
+			return false;
+	}
+
+	return true;
+}
+
+static bool
+ieee80211_verify_sta_vht_mcs_support(struct ieee80211_sub_if_data *sdata,
+				     int link_id,
+				     struct ieee80211_supported_band *sband,
+				     const struct ieee80211_vht_operation *vht_op)
+{
+	struct ieee80211_sta_vht_cap sta_vht_cap;
+	u16 ap_min_req_set, sta_rx_mcs_map, sta_tx_mcs_map;
+	int nss;
+
+	if (sband->band != NL80211_BAND_5GHZ)
+		return true;
+
+	if (!vht_op)
+		return false;
+
+	memcpy(&sta_vht_cap, &sband->vht_cap, sizeof(sta_vht_cap));
+	ieee80211_apply_vhtcap_overrides(sdata, &sta_vht_cap);
+
+	ap_min_req_set = le16_to_cpu(vht_op->basic_mcs_set);
+	sta_rx_mcs_map = le16_to_cpu(sta_vht_cap.vht_mcs.rx_mcs_map);
+	sta_tx_mcs_map = le16_to_cpu(sta_vht_cap.vht_mcs.tx_mcs_map);
+
+	/*
+	 * Many APs are incorrectly advertising an all-zero value here,
+	 * which really means MCS 0-7 are required for 1-8 streams, but
+	 * they don't really mean it that way.
+	 * Some other APs are incorrectly advertising 3 spatial streams
+	 * with MCS 0-7 are required, but don't really mean it that way
+	 * and we'll connect only with HT, rather than even HE.
+	 * As a result, unfortunately the VHT basic MCS/NSS set cannot
+	 * be used at all, so check it only in strict mode.
+	 */
+	if (!ieee80211_hw_check(&sdata->local->hw, STRICT))
+		return true;
+
+	/*
+	 * P802.11REVme/D7.0 - 6.5.4.2.4
+	 * ...
+	 * If the MLME of a VHT STA receives an MLME-JOIN.request primitive
+	 * with a SelectedBSS parameter containing a Basic VHT-MCS And NSS Set
+	 * field in the VHT Operation parameter that contains any unsupported
+	 * <VHT-MCS, NSS> tuple, the MLME response in the resulting
+	 * MLME-JOIN.confirm primitive shall contain a ResultCode parameter
+	 * that is not set to the value SUCCESS.
+	 * ...
+	 */
+	for (nss = 8; nss > 0; nss--) {
+		u8 ap_op_val = (ap_min_req_set >> (2 * (nss - 1))) & 3;
+		u8 sta_rx_val;
+		u8 sta_tx_val;
+
+		if (ap_op_val == IEEE80211_HE_MCS_NOT_SUPPORTED)
+			continue;
+
+		sta_rx_val = (sta_rx_mcs_map >> (2 * (nss - 1))) & 3;
+		sta_tx_val = (sta_tx_mcs_map >> (2 * (nss - 1))) & 3;
+
+		if (sta_rx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+		    sta_tx_val == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+		    sta_rx_val < ap_op_val || sta_tx_val < ap_op_val) {
+			link_id_info(sdata, link_id,
+				     "Missing mandatory rates for %d Nss, rx %d, tx %d oper %d, disable VHT\n",
+				     nss, sta_rx_val, sta_tx_val, ap_op_val);
+			return false;
+		}
+	}
+
+	return true;
+}
+
 static bool
 ieee80211_verify_peer_he_mcs_support(struct ieee80211_sub_if_data *sdata,
 				     int link_id,
@@ -1042,6 +1151,26 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 		link_id_info(sdata, link_id,
 			     "regulatory prevented using AP config, downgraded\n");
 
+	if (conn->mode >= IEEE80211_CONN_MODE_HT &&
+	    !ieee80211_verify_sta_ht_mcs_support(sdata, sband,
+						 elems->ht_operation)) {
+		conn->mode = IEEE80211_CONN_MODE_LEGACY;
+		conn->bw_limit = IEEE80211_CONN_BW_LIMIT_20;
+		link_id_info(sdata, link_id,
+			     "required MCSes not supported, disabling HT\n");
+	}
+
+	if (conn->mode >= IEEE80211_CONN_MODE_VHT &&
+	    !ieee80211_verify_sta_vht_mcs_support(sdata, link_id, sband,
+						  elems->vht_operation)) {
+		conn->mode = IEEE80211_CONN_MODE_HT;
+		conn->bw_limit = min_t(enum ieee80211_conn_bw_limit,
+				       conn->bw_limit,
+				       IEEE80211_CONN_BW_LIMIT_40);
+		link_id_info(sdata, link_id,
+			     "required MCSes not supported, disabling VHT\n");
+	}
+
 	if (conn->mode >= IEEE80211_CONN_MODE_HE &&
 	    (!ieee80211_verify_peer_he_mcs_support(sdata, link_id,
 						   (void *)elems->he_cap,

From b46524b57afdde8ed9ee9567e78d1293ad0e6ea7 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:19 +0200
Subject: [PATCH 0365/2753] wifi: mac80211: tests: add tests for
 ieee80211_determine_chan_mode

Add a few tests for ieee80211_determine_chan_mode that check that
mac80211 will not try to connect to an AP if an advertised basic rate is
not supported.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.530c81eb7fdc.Ia77f5efdf9efb70d2766a3d6bf425553bcb308e8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h     |   7 +
 net/mac80211/mlme.c            |   3 +-
 net/mac80211/tests/Makefile    |   2 +-
 net/mac80211/tests/chan-mode.c | 254 +++++++++++++++++++++++++++++++++
 net/mac80211/tests/util.c      |   6 +-
 5 files changed, 265 insertions(+), 7 deletions(-)
 create mode 100644 net/mac80211/tests/chan-mode.c

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index df7c803134fd8..f23be8b5d0d87 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2804,6 +2804,13 @@ int ieee80211_calc_chandef_subchan_offset(const struct cfg80211_chan_def *ap,
 void ieee80211_rearrange_tpe_psd(struct ieee80211_parsed_tpe_psd *psd,
 				 const struct cfg80211_chan_def *ap,
 				 const struct cfg80211_chan_def *used);
+struct ieee802_11_elems *
+ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
+			      struct ieee80211_conn_settings *conn,
+			      struct cfg80211_bss *cbss, int link_id,
+			      struct ieee80211_chan_req *chanreq,
+			      struct cfg80211_chan_def *ap_chandef,
+			      unsigned long *userspace_selectors);
 #else
 #define EXPORT_SYMBOL_IF_MAC80211_KUNIT(sym)
 #define VISIBLE_IF_MAC80211_KUNIT static
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3749b3e23bb7a..686b33654b52b 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -989,7 +989,7 @@ static void ieee80211_set_chanreq_ap(struct ieee80211_sub_if_data *sdata,
 	chanreq->ap = *ap_chandef;
 }
 
-static struct ieee802_11_elems *
+VISIBLE_IF_MAC80211_KUNIT struct ieee802_11_elems *
 ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 			      struct ieee80211_conn_settings *conn,
 			      struct cfg80211_bss *cbss, int link_id,
@@ -1214,6 +1214,7 @@ ieee80211_determine_chan_mode(struct ieee80211_sub_if_data *sdata,
 	kfree(elems);
 	return ERR_PTR(ret);
 }
+EXPORT_SYMBOL_IF_MAC80211_KUNIT(ieee80211_determine_chan_mode);
 
 static int ieee80211_config_bw(struct ieee80211_link_data *link,
 			       struct ieee802_11_elems *elems,
diff --git a/net/mac80211/tests/Makefile b/net/mac80211/tests/Makefile
index 0f5336bc7314e..3b0c08356fc55 100644
--- a/net/mac80211/tests/Makefile
+++ b/net/mac80211/tests/Makefile
@@ -1,3 +1,3 @@
-mac80211-tests-y += module.o util.o elems.o mfp.o tpe.o
+mac80211-tests-y += module.o util.o elems.o mfp.o tpe.o chan-mode.o
 
 obj-$(CONFIG_MAC80211_KUNIT_TEST) += mac80211-tests.o
diff --git a/net/mac80211/tests/chan-mode.c b/net/mac80211/tests/chan-mode.c
new file mode 100644
index 0000000000000..96c7b3ab27444
--- /dev/null
+++ b/net/mac80211/tests/chan-mode.c
@@ -0,0 +1,254 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * KUnit tests for channel mode functions
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <net/cfg80211.h>
+#include <kunit/test.h>
+
+#include "util.h"
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+static const struct determine_chan_mode_case {
+	const char *desc;
+	u8 extra_supp_rate;
+	enum ieee80211_conn_mode conn_mode;
+	enum ieee80211_conn_mode expected_mode;
+	bool strict;
+	u8 userspace_selector;
+	struct ieee80211_ht_cap ht_capa_mask;
+	struct ieee80211_vht_cap vht_capa;
+	struct ieee80211_vht_cap vht_capa_mask;
+	u8 vht_basic_mcs_1_4_set:1,
+	   vht_basic_mcs_5_8_set:1,
+	   he_basic_mcs_1_4_set:1,
+	   he_basic_mcs_5_8_set:1;
+	u8 vht_basic_mcs_1_4, vht_basic_mcs_5_8;
+	u8 he_basic_mcs_1_4, he_basic_mcs_5_8;
+	u8 eht_mcs7_min_nss;
+	int error;
+} determine_chan_mode_cases[] = {
+	{
+		.desc = "Normal case, EHT is working",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_EHT,
+	}, {
+		.desc = "Requiring EHT support is fine",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_EHT,
+		.extra_supp_rate = 0x80 | BSS_MEMBERSHIP_SELECTOR_EHT_PHY,
+	}, {
+		.desc = "Lowering the mode limits us",
+		.conn_mode = IEEE80211_CONN_MODE_VHT,
+		.expected_mode = IEEE80211_CONN_MODE_VHT,
+	}, {
+		.desc = "Requesting a basic rate/selector that we do not support",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.extra_supp_rate = 0x80 | (BSS_MEMBERSHIP_SELECTOR_MIN - 1),
+		.error = EINVAL,
+	}, {
+		.desc = "As before, but userspace says it is taking care of it",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.userspace_selector = BSS_MEMBERSHIP_SELECTOR_MIN - 1,
+		.extra_supp_rate = 0x80 | (BSS_MEMBERSHIP_SELECTOR_MIN - 1),
+		.expected_mode = IEEE80211_CONN_MODE_EHT,
+	}, {
+		.desc = "Masking out a supported rate in HT capabilities",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_LEGACY,
+		.ht_capa_mask = {
+			.mcs.rx_mask[0] = 0xf7,
+		},
+	}, {
+		.desc = "Masking out a RX rate in VHT capabilities",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HT,
+		/* Only one RX stream at MCS 0-7 */
+		.vht_capa = {
+			.supp_mcs.rx_mcs_map =
+				cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_7),
+		},
+		.vht_capa_mask = {
+			.supp_mcs.rx_mcs_map = cpu_to_le16(0xffff),
+		},
+		.strict = true,
+	}, {
+		.desc = "Masking out a TX rate in VHT capabilities",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HT,
+		/* Only one TX stream at MCS 0-7 */
+		.vht_capa = {
+			.supp_mcs.tx_mcs_map =
+				cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_7),
+		},
+		.vht_capa_mask = {
+			.supp_mcs.tx_mcs_map = cpu_to_le16(0xffff),
+		},
+		.strict = true,
+	}, {
+		.desc = "AP has higher VHT requirement than client",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HT,
+		.vht_basic_mcs_5_8_set = 1,
+		.vht_basic_mcs_5_8 = 0xFE, /* require 5th stream */
+		.strict = true,
+	}, {
+		.desc = "all zero VHT basic rates are ignored (many APs broken)",
+		.conn_mode = IEEE80211_CONN_MODE_VHT,
+		.expected_mode = IEEE80211_CONN_MODE_VHT,
+		.vht_basic_mcs_1_4_set = 1,
+		.vht_basic_mcs_5_8_set = 1,
+	}, {
+		.desc = "AP requires 3 HE streams but client only has two",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_VHT,
+		.he_basic_mcs_1_4 = 0b11001010,
+		.he_basic_mcs_1_4_set = 1,
+	}, {
+		.desc = "all zero HE basic rates are ignored (iPhone workaround)",
+		.conn_mode = IEEE80211_CONN_MODE_HE,
+		.expected_mode = IEEE80211_CONN_MODE_HE,
+		.he_basic_mcs_1_4_set = 1,
+		.he_basic_mcs_5_8_set = 1,
+	}, {
+		.desc = "AP requires too many RX streams with EHT MCS 7",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HE,
+		.eht_mcs7_min_nss = 0x15,
+	}, {
+		.desc = "AP requires too many TX streams with EHT MCS 7",
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.expected_mode = IEEE80211_CONN_MODE_HE,
+		.eht_mcs7_min_nss = 0x51,
+	}, {
+		.desc = "AP requires too many RX streams with EHT MCS 7 and EHT is required",
+		.extra_supp_rate = 0x80 | BSS_MEMBERSHIP_SELECTOR_EHT_PHY,
+		.conn_mode = IEEE80211_CONN_MODE_EHT,
+		.eht_mcs7_min_nss = 0x15,
+		.error = EINVAL,
+	}
+};
+KUNIT_ARRAY_PARAM_DESC(determine_chan_mode, determine_chan_mode_cases, desc)
+
+static void test_determine_chan_mode(struct kunit *test)
+{
+	const struct determine_chan_mode_case *params = test->param_value;
+	struct t_sdata *t_sdata = T_SDATA(test);
+	struct ieee80211_conn_settings conn = {
+		.mode = params->conn_mode,
+		.bw_limit = IEEE80211_CONN_BW_LIMIT_20,
+	};
+	struct cfg80211_bss cbss = {
+		.channel = &t_sdata->band_5ghz.channels[0],
+	};
+	unsigned long userspace_selectors[BITS_TO_LONGS(128)] = {};
+	u8 bss_ies[] = {
+		/* Supported Rates */
+		WLAN_EID_SUPP_RATES, 0x08,
+		0x82, 0x84, 0x8b, 0x96, 0xc, 0x12, 0x18, 0x24,
+		/* Extended Supported Rates */
+		WLAN_EID_EXT_SUPP_RATES, 0x05,
+		0x30, 0x48, 0x60, 0x6c, params->extra_supp_rate,
+		/* HT Capabilities */
+		WLAN_EID_HT_CAPABILITY, 0x1a,
+		0x0c, 0x00, 0x1b, 0xff, 0xff, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		0x00, 0x00,
+		/* HT Information (0xff for 1 stream) */
+		WLAN_EID_HT_OPERATION, 0x16,
+		0x24, 0x00, 0x00, 0x00, 0x00, 0x00, 0xff, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		/* VHT Capabilities */
+		WLAN_EID_VHT_CAPABILITY, 0xc,
+		0x00, 0x00, 0x00, 0x00, 0xff, 0xff, 0x00, 0x00,
+		0xff, 0xff, 0x00, 0x00,
+		/* VHT Operation */
+		WLAN_EID_VHT_OPERATION, 0x05,
+		0x00, 0x00, 0x00,
+		params->vht_basic_mcs_1_4_set ?
+			params->vht_basic_mcs_1_4 :
+			le16_get_bits(t_sdata->band_5ghz.vht_cap.vht_mcs.rx_mcs_map, 0xff),
+		params->vht_basic_mcs_5_8_set ?
+			params->vht_basic_mcs_5_8 :
+			le16_get_bits(t_sdata->band_5ghz.vht_cap.vht_mcs.rx_mcs_map, 0xff00),
+		/* HE Capabilities */
+		WLAN_EID_EXTENSION, 0x16, WLAN_EID_EXT_HE_CAPABILITY,
+		0x01, 0x78, 0xc8, 0x1a, 0x40, 0x00, 0x00, 0xbf,
+		0xce, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+		0x00, 0xfa, 0xff, 0xfa, 0xff,
+		/* HE Operation (permit overriding values) */
+		WLAN_EID_EXTENSION, 0x07, WLAN_EID_EXT_HE_OPERATION,
+		0xf0, 0x3f, 0x00, 0xb0,
+		params->he_basic_mcs_1_4_set ? params->he_basic_mcs_1_4 : 0xfc,
+		params->he_basic_mcs_5_8_set ? params->he_basic_mcs_5_8 : 0xff,
+		/* EHT Capabilities */
+		WLAN_EID_EXTENSION, 0x12, WLAN_EID_EXT_EHT_CAPABILITY,
+		0x07, 0x00, 0x1c, 0x00, 0x00, 0xfe, 0xff, 0xff,
+		0x7f, 0x01, 0x00, 0x88, 0x88, 0x88, 0x00, 0x00,
+		0x00,
+		/* EHT Operation */
+		WLAN_EID_EXTENSION, 0x09, WLAN_EID_EXT_EHT_OPERATION,
+		0x01, params->eht_mcs7_min_nss ? params->eht_mcs7_min_nss : 0x11,
+		0x00, 0x00, 0x00, 0x00, 0x24, 0x00,
+	};
+	struct ieee80211_chan_req chanreq = {};
+	struct cfg80211_chan_def ap_chandef = {};
+	struct ieee802_11_elems *elems;
+
+	if (params->strict)
+		set_bit(IEEE80211_HW_STRICT, t_sdata->local.hw.flags);
+	else
+		clear_bit(IEEE80211_HW_STRICT, t_sdata->local.hw.flags);
+
+	t_sdata->sdata->u.mgd.ht_capa_mask = params->ht_capa_mask;
+	t_sdata->sdata->u.mgd.vht_capa = params->vht_capa;
+	t_sdata->sdata->u.mgd.vht_capa_mask = params->vht_capa_mask;
+
+	if (params->userspace_selector)
+		set_bit(params->userspace_selector, userspace_selectors);
+
+	rcu_assign_pointer(cbss.ies,
+			   kunit_kzalloc(test,
+					 sizeof(cbss) + sizeof(bss_ies),
+					 GFP_KERNEL));
+	KUNIT_ASSERT_NOT_NULL(test, rcu_access_pointer(cbss.ies));
+	((struct cfg80211_bss_ies *)rcu_access_pointer(cbss.ies))->len = sizeof(bss_ies);
+
+	memcpy((void *)rcu_access_pointer(cbss.ies)->data, bss_ies,
+	       sizeof(bss_ies));
+
+	rcu_read_lock();
+	elems = ieee80211_determine_chan_mode(t_sdata->sdata, &conn, &cbss,
+					      0, &chanreq, &ap_chandef,
+					      userspace_selectors);
+	rcu_read_unlock();
+
+	/* We do not need elems, free them if they are valid. */
+	if (!IS_ERR_OR_NULL(elems))
+		kfree(elems);
+
+	if (params->error) {
+		KUNIT_ASSERT_TRUE(test, IS_ERR(elems));
+		KUNIT_ASSERT_EQ(test, PTR_ERR(elems), -params->error);
+	} else {
+		KUNIT_ASSERT_NOT_ERR_OR_NULL(test, elems);
+		KUNIT_ASSERT_EQ(test, conn.mode, params->expected_mode);
+	}
+}
+
+static struct kunit_case chan_mode_cases[] = {
+	KUNIT_CASE_PARAM(test_determine_chan_mode,
+			 determine_chan_mode_gen_params),
+	{}
+};
+
+static struct kunit_suite chan_mode = {
+	.name = "mac80211-mlme-chan-mode",
+	.test_cases = chan_mode_cases,
+};
+
+kunit_test_suite(chan_mode);
diff --git a/net/mac80211/tests/util.c b/net/mac80211/tests/util.c
index 0936a73e36175..9c2d63a5cd2bf 100644
--- a/net/mac80211/tests/util.c
+++ b/net/mac80211/tests/util.c
@@ -266,11 +266,7 @@ int t_sdata_init(struct kunit_resource *resource, void *ctx)
 				cpu_to_le16(IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 |
 					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 2 |
 					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 4 |
-					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 6 |
-					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 8 |
-					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 10 |
-					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 12 |
-					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 14);
+					    IEEE80211_VHT_MCS_SUPPORT_0_9 << 6);
 			sband->vht_cap.vht_mcs.tx_mcs_map =
 				sband->vht_cap.vht_mcs.rx_mcs_map;
 			break;

From 8c60179b64434894eac1ffab7396bac131bc8b6e Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 11:39:20 +0200
Subject: [PATCH 0366/2753] wifi: mac80211: set ieee80211_prep_tx_info::link_id
 upon Auth Rx

This will be used by the low level driver.
Note that link_id  will be 0 in case of a non-MLO authentication.
Also fix a call-site of mgd_prepare_tx() where the link_id was not
populated.

Update the documentation to reflect the current state
ieee80211_prep_tx_info::link_id is also available in mgd_complete_tx().

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.6a590f189ce5.I1fc5c0da26b143f5b07191eb592f01f7083d55ae@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h    | 4 ++--
 net/mac80211/driver-ops.h | 3 ++-
 net/mac80211/mlme.c       | 4 +++-
 3 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 398d4e30b0db7..22d32419e8a05 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -7,7 +7,7 @@
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2024 Intel Corporation
+ * Copyright (C) 2018 - 2025 Intel Corporation
  */
 
 #ifndef MAC80211_H
@@ -3830,7 +3830,7 @@ enum ieee80211_reconfig_type {
  * @was_assoc: set if this call is due to deauth/disassoc
  *	while just having been associated
  * @link_id: the link id on which the frame will be TX'ed.
- *	Only used with the mgd_prepare_tx() method.
+ *	0 for a non-MLO connection.
  */
 struct ieee80211_prep_tx_info {
 	u16 duration;
diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h
index 5acecc7bd4a99..307587c8a0037 100644
--- a/net/mac80211/driver-ops.h
+++ b/net/mac80211/driver-ops.h
@@ -2,7 +2,7 @@
 /*
 * Portions of this file
 * Copyright(c) 2016 Intel Deutschland GmbH
-* Copyright (C) 2018-2019, 2021-2024 Intel Corporation
+* Copyright (C) 2018-2019, 2021-2025 Intel Corporation
 */
 
 #ifndef __MAC80211_DRIVER_OPS
@@ -955,6 +955,7 @@ static inline void drv_mgd_complete_tx(struct ieee80211_local *local,
 		return;
 	WARN_ON_ONCE(sdata->vif.type != NL80211_IFTYPE_STATION);
 
+	info->link_id = info->link_id < 0 ? 0 : info->link_id;
 	trace_drv_mgd_complete_tx(local, sdata, info->duration,
 				  info->subtype, info->success);
 	if (local->ops->mgd_complete_tx)
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 686b33654b52b..184b328d92cb0 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -8,7 +8,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2024 Intel Corporation
+ * Copyright (C) 2018 - 2025 Intel Corporation
  */
 
 #include <linux/delay.h>
@@ -4725,6 +4725,8 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata,
 	auth_transaction = le16_to_cpu(mgmt->u.auth.auth_transaction);
 	status_code = le16_to_cpu(mgmt->u.auth.status_code);
 
+	info.link_id = ifmgd->auth_data->link_id;
+
 	if (auth_alg != ifmgd->auth_data->algorithm ||
 	    (auth_alg != WLAN_AUTH_SAE &&
 	     auth_transaction != ifmgd->auth_data->expected_transaction) ||

From f4995cdc4d02d0abc8e9fcccad5c71ce676c1e3f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:21 +0200
Subject: [PATCH 0367/2753] wifi: mac80211: remove misplaced
 drv_mgd_complete_tx() call

In the original commit 15fae3410f1d ("mac80211: notify driver on
mgd TX completion") I evidently made a mistake and placed the
call in the "associated" if, rather than the "assoc_data". Later
I noticed the missing call and placed it in commit c042600c17d8
("wifi: mac80211: adding missing drv_mgd_complete_tx() call"),
but didn't remove the wrong one. Remove it now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.6ed954179bbf.Id8ef8835b7e6da3bf913c76f77d201017dc8a3c9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 184b328d92cb0..bb3e42afd34ef 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -9751,7 +9751,6 @@ int ieee80211_mgd_deauth(struct ieee80211_sub_if_data *sdata,
 		ieee80211_report_disconnect(sdata, frame_buf,
 					    sizeof(frame_buf), true,
 					    req->reason_code, false);
-		drv_mgd_complete_tx(sdata->local, sdata, &info);
 		return 0;
 	}
 

From 1798271b3604b902d45033ec569f2bf77e94ecc2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:22 +0200
Subject: [PATCH 0368/2753] wifi: mac80211: don't unconditionally call
 drv_mgd_complete_tx()

We might not have called drv_mgd_prepare_tx(), so only call
drv_mgd_complete_tx() under the same conditions.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.e091fc39a351.Ie6a3cdca070612a0aa4b3c6914ab9ed602d1f456@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index bb3e42afd34ef..1d118c30948d1 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3976,7 +3976,8 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	if (tx)
 		ieee80211_flush_queues(local, sdata, false);
 
-	drv_mgd_complete_tx(sdata->local, sdata, &info);
+	if (tx || frame_buf)
+		drv_mgd_complete_tx(sdata->local, sdata, &info);
 
 	/* clear AP addr only after building the needed mgmt frames */
 	eth_zero_addr(sdata->deflink.u.mgd.bssid);

From 3fca951123b68df8d1b47bbf90409f8a3671362b Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:23 +0200
Subject: [PATCH 0369/2753] wifi: mac80211: always send max agg subframe num in
 strict mode

Instead of only sending the correct number for EHT and up,
always send the correct number as it should be in strict
mode.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.5910263db6da.Icd1f93fabc9705e4e760d834095c29b60b934d9e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/agg-tx.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 61f2cac37728c..92120f9051499 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2023 Intel Corporation
+ * Copyright (C) 2018 - 2024 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -464,7 +464,8 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta,
 	sta->ampdu_mlme.addba_req_num[tid]++;
 	spin_unlock_bh(&sta->lock);
 
-	if (sta->sta.deflink.eht_cap.has_eht) {
+	if (sta->sta.deflink.eht_cap.has_eht ||
+	    ieee80211_hw_check(&local->hw, STRICT)) {
 		buf_size = local->hw.max_tx_aggregation_subframes;
 	} else if (sta->sta.deflink.he_cap.has_he) {
 		buf_size = min_t(u16, local->hw.max_tx_aggregation_subframes,

From 3979c8e6205b268ef99d34d09447981eafcd1ed9 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:24 +0200
Subject: [PATCH 0370/2753] wifi: mac80211: aggregation: remove deflink
 accesses for MLO

If a station has connected with MLO (as indicated by valid_links
being non-zero, even if that may have just a single bit set), it
necessarily supports EHT/aggregation, so we don't need to check
the deflink for those cases.

Add conditions so we can support removing the link it/we used to
associate on.

Note that we still use the statistics in the deflink, but that's
a whole different story we will need to address separately.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.daf2a9e367f2.Id2c2dfbbe7451cc900ed88c5a81b33c55b4ab1cf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/agg-rx.c | 22 +++++++++++++---------
 net/mac80211/agg-tx.c |  6 ++++--
 net/mac80211/tx.c     |  3 ++-
 3 files changed, 19 insertions(+), 12 deletions(-)

diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c
index f3fbe5a4395e5..aeb99d102c6e9 100644
--- a/net/mac80211/agg-rx.c
+++ b/net/mac80211/agg-rx.c
@@ -9,7 +9,7 @@
  * Copyright 2007, Michael Wu <flamingice@sourmilk.net>
  * Copyright 2007-2010, Intel Corporation
  * Copyright(c) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 /**
@@ -206,17 +206,19 @@ u8 ieee80211_retrieve_addba_ext_data(struct sta_info *sta,
 
 	elems = ieee802_11_parse_elems(elem_data, elem_len, true, NULL);
 
-	if (elems && !elems->parse_error && elems->addba_ext_ie) {
-		data = elems->addba_ext_ie->data;
+	if (!elems || elems->parse_error || !elems->addba_ext_ie)
+		goto free;
 
-		if (!sta->sta.deflink.eht_cap.has_eht || !buf_size)
-			goto free;
+	data = elems->addba_ext_ie->data;
 
+	if (buf_size &&
+	    (sta->sta.valid_links || sta->sta.deflink.eht_cap.has_eht)) {
 		buf_size_1k = u8_get_bits(elems->addba_ext_ie->data,
 					  IEEE80211_ADDBA_EXT_BUF_SIZE_MASK);
 		*buf_size |= (u16)buf_size_1k <<
 			     IEEE80211_ADDBA_EXT_BUF_SIZE_SHIFT;
 	}
+
 free:
 	kfree(elems);
 
@@ -258,7 +260,7 @@ static void ieee80211_send_addba_resp(struct sta_info *sta, u8 *da, u16 tid,
 	mgmt->u.action.u.addba_resp.timeout = cpu_to_le16(timeout);
 	mgmt->u.action.u.addba_resp.status = cpu_to_le16(status);
 
-	if (sta->sta.deflink.he_cap.has_he)
+	if (sta->sta.valid_links || sta->sta.deflink.he_cap.has_he)
 		ieee80211_add_addbaext(skb, req_addba_ext_data, buf_size);
 
 	ieee80211_tx_skb(sdata, skb);
@@ -293,7 +295,8 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 		goto end;
 	}
 
-	if (!sta->sta.deflink.ht_cap.ht_supported &&
+	if (!sta->sta.valid_links &&
+	    !sta->sta.deflink.ht_cap.ht_supported &&
 	    !sta->sta.deflink.he_cap.has_he) {
 		ht_dbg(sta->sdata,
 		       "STA %pM erroneously requests BA session on tid %d w/o HT\n",
@@ -309,7 +312,7 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 		goto end;
 	}
 
-	if (sta->sta.deflink.eht_cap.has_eht)
+	if (sta->sta.valid_links || sta->sta.deflink.eht_cap.has_eht)
 		max_buf_size = IEEE80211_MAX_AMPDU_BUF_EHT;
 	else if (sta->sta.deflink.he_cap.has_he)
 		max_buf_size = IEEE80211_MAX_AMPDU_BUF_HE;
@@ -321,7 +324,8 @@ void __ieee80211_start_rx_ba_session(struct sta_info *sta,
 	 * and if buffer size does not exceeds max value */
 	/* XXX: check own ht delayed BA capability?? */
 	if (((ba_policy != 1) &&
-	     (!(sta->sta.deflink.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) ||
+	     (sta->sta.valid_links ||
+	      !(sta->sta.deflink.ht_cap.cap & IEEE80211_HT_CAP_DELAY_BA))) ||
 	    (buf_size > max_buf_size)) {
 		status = WLAN_STATUS_INVALID_QOS_PARAM;
 		ht_dbg_ratelimited(sta->sdata,
diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
index 92120f9051499..63a5e48291ac3 100644
--- a/net/mac80211/agg-tx.c
+++ b/net/mac80211/agg-tx.c
@@ -464,7 +464,8 @@ static void ieee80211_send_addba_with_timeout(struct sta_info *sta,
 	sta->ampdu_mlme.addba_req_num[tid]++;
 	spin_unlock_bh(&sta->lock);
 
-	if (sta->sta.deflink.eht_cap.has_eht ||
+	if (sta->sta.valid_links ||
+	    sta->sta.deflink.eht_cap.has_eht ||
 	    ieee80211_hw_check(&local->hw, STRICT)) {
 		buf_size = local->hw.max_tx_aggregation_subframes;
 	} else if (sta->sta.deflink.he_cap.has_he) {
@@ -609,7 +610,8 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
 		 "Requested to start BA session on reserved tid=%d", tid))
 		return -EINVAL;
 
-	if (!pubsta->deflink.ht_cap.ht_supported &&
+	if (!pubsta->valid_links &&
+	    !pubsta->deflink.ht_cap.ht_supported &&
 	    !pubsta->deflink.vht_cap.vht_supported &&
 	    !pubsta->deflink.he_cap.has_he &&
 	    !pubsta->deflink.eht_cap.has_eht)
diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 1289df373795e..20179db88c4a6 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -1182,7 +1182,8 @@ void ieee80211_aggr_check(struct ieee80211_sub_if_data *sdata,
 	if (!ref || !(ref->ops->capa & RATE_CTRL_CAPA_AMPDU_TRIGGER))
 		return;
 
-	if (!sta || !sta->sta.deflink.ht_cap.ht_supported ||
+	if (!sta ||
+	    (!sta->sta.valid_links && !sta->sta.deflink.ht_cap.ht_supported) ||
 	    !sta->sta.wme || skb_get_queue_mapping(skb) == IEEE80211_AC_VO ||
 	    skb->protocol == sdata->control_port_protocol)
 		return;

From a883ad479dbbbab80543678389582fa90d2b9339 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 11:39:25 +0200
Subject: [PATCH 0371/2753] wifi: mac80211: enable removing assoc link

With the previous patch to no longer access deflink for aggregation
it seems we no longer access the deflink for MLO stations (MLDs) so
we can allow removing the assoc link.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.05bc2175cea2.I8f62609a682fdf3f703872d0fce63ab6a4780a7e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1d118c30948d1..3fb7e624834fe 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10391,9 +10391,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	if (WARN_ON(!sta))
 		return -ENOLINK;
 
-	if (rem_links & BIT(sta->sta.deflink.link_id))
-		return -EINVAL;
-
 	/* Adding links to the set of valid link is done only after a successful
 	 * ML reconfiguration frame exchange. Here prepare the data for the ML
 	 * reconfiguration frame construction and allocate the required

From 6c93fd502023dd919b5987ccbe990735410edd49 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 5 Feb 2025 11:39:26 +0200
Subject: [PATCH 0372/2753] wifi: mac80211: ensure sdata->work is canceled
 before initialized.

This wiphy work is canceled when the iface is stopped,
and shouldn't be queued for a non-running iface.
If it happens to be queued for a non-running iface (due to a bug)
it can cause a corruption of wiphy_work_list when ieee80211_setup_sdata
is called. Make sure to cancel it in this case and warn on.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250205110958.99204c767c10.I84ce27a239059f6009cee197b252549a11426046@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/iface.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index edb4ca333528d..d8b14ba95ae24 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -8,7 +8,7 @@
  * Copyright 2008, Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (c) 2016        Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/slab.h>
 #include <linux/kernel.h>
@@ -804,6 +804,9 @@ static void ieee80211_set_multicast_list(struct net_device *dev)
  */
 static void ieee80211_teardown_sdata(struct ieee80211_sub_if_data *sdata)
 {
+	if (WARN_ON(!list_empty(&sdata->work.entry)))
+		wiphy_work_cancel(sdata->local->hw.wiphy, &sdata->work);
+
 	/* free extra data */
 	ieee80211_free_keys(sdata, false);
 

From ccbaf782390deb584d64dd2cf6aba983737bc48a Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 11:39:27 +0200
Subject: [PATCH 0373/2753] wifi: mac80211: rework the Tx of the deauth in
 ieee80211_set_disassoc()

When we disassociate we may need to send a deauth frame.
Regardless of this decision, we need to flush the queues to drop all the
packets on the Tx queues.

The flow looks like this:

1) Flush packets waiting on the queues (drop=true)
2) Prepare Tx to send the deauth
3) Build the deauth header
4) send the deauth
5) Flush the deauth packet (drop=false)
6) Complete_tx

Step 3 and 4 are done in ieee80211_send_deauth_disassoc() and that
function  must be called even if we decide not to send the deauth
frame because we need step 3 for cfg80211.

This means that if we want to send the deauth frame, we need all the
steps, but if we don't want to send the deauth frame we still want step
1 and 3.

Change the code to do that.

Also, prevent sending the deauth frame if we are in the middle of a CSA
with mode=1 in which case we won't be able to send the frame anyway.
This caused issues in iwlwifi at step 5 since the firmware wouldn't
send the frame and we'd be stuck flushing with drop=false.
Implement this in ieee80211_set_disassoc() which has many callers.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205110958.480bfea605e0.I91131eed942e49b9885d73f4180a3c9c26691c62@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 68 ++++++++++++++++++++++++---------------------
 1 file changed, 36 insertions(+), 32 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3fb7e624834fe..4e8f0a5f6251e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -3930,6 +3930,31 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	ifmgd->associated = false;
 
+	if (tx) {
+		bool tx_link_found = false;
+
+		for (link_id = 0;
+		     link_id < ARRAY_SIZE(sdata->link);
+		     link_id++) {
+			struct ieee80211_link_data *link;
+
+			if (!ieee80211_vif_link_active(&sdata->vif, link_id))
+				continue;
+
+			link = sdata_dereference(sdata->link[link_id], sdata);
+			if (WARN_ON_ONCE(!link))
+				continue;
+
+			if (link->u.mgd.csa.blocked_tx)
+				continue;
+
+			tx_link_found = true;
+			break;
+		}
+
+		tx = tx_link_found;
+	}
+
 	/* other links will be destroyed */
 	sdata->deflink.conf->bss = NULL;
 	sdata->deflink.conf->epcs_support = false;
@@ -3960,24 +3985,24 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	 * insist sending these frames which can take time and delay
 	 * the disconnection and possible the roaming.
 	 */
-	if (tx)
-		ieee80211_flush_queues(local, sdata, true);
+	ieee80211_flush_queues(local, sdata, true);
 
-	/* deauthenticate/disassociate now */
-	if (tx || frame_buf) {
+	if (tx) {
 		drv_mgd_prepare_tx(sdata->local, sdata, &info);
 
 		ieee80211_send_deauth_disassoc(sdata, sdata->vif.cfg.ap_addr,
 					       sdata->vif.cfg.ap_addr, stype,
-					       reason, tx, frame_buf);
-	}
+					       reason, true, frame_buf);
 
-	/* flush out frame - make sure the deauth was actually sent */
-	if (tx)
+		/* flush out frame - make sure the deauth was actually sent */
 		ieee80211_flush_queues(local, sdata, false);
 
-	if (tx || frame_buf)
 		drv_mgd_complete_tx(sdata->local, sdata, &info);
+	} else if (frame_buf) {
+		ieee80211_send_deauth_disassoc(sdata, sdata->vif.cfg.ap_addr,
+					       sdata->vif.cfg.ap_addr, stype,
+					       reason, false, frame_buf);
+	}
 
 	/* clear AP addr only after building the needed mgmt frames */
 	eth_zero_addr(sdata->deflink.u.mgd.bssid);
@@ -4403,33 +4428,12 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_if_managed *ifmgd = &sdata->u.mgd;
 	u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
-	bool tx = false;
 
 	lockdep_assert_wiphy(local->hw.wiphy);
 
 	if (!ifmgd->associated)
 		return;
 
-	/* only transmit if we have a link that makes that worthwhile */
-	for (unsigned int link_id = 0;
-	     link_id < ARRAY_SIZE(sdata->link);
-	     link_id++) {
-		struct ieee80211_link_data *link;
-
-		if (!ieee80211_vif_link_active(&sdata->vif, link_id))
-			continue;
-
-		link = sdata_dereference(sdata->link[link_id], sdata);
-		if (WARN_ON_ONCE(!link))
-			continue;
-
-		if (link->u.mgd.csa.blocked_tx)
-			continue;
-
-		tx = true;
-		break;
-	}
-
 	if (!ifmgd->driver_disconnect) {
 		unsigned int link_id;
 
@@ -4457,14 +4461,14 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			       ifmgd->driver_disconnect ?
 					WLAN_REASON_DEAUTH_LEAVING :
 					WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
-			       tx, frame_buf);
+			       true, frame_buf);
 	/* the other links will be destroyed */
 	sdata->vif.bss_conf.csa_active = false;
 	sdata->deflink.u.mgd.csa.waiting_bcn = false;
 	sdata->deflink.u.mgd.csa.blocked_tx = false;
 	ieee80211_vif_unblock_queues_csa(sdata);
 
-	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), tx,
+	ieee80211_report_disconnect(sdata, frame_buf, sizeof(frame_buf), true,
 				    WLAN_REASON_DISASSOC_DUE_TO_INACTIVITY,
 				    ifmgd->reconnect);
 	ifmgd->reconnect = false;

From 1742b03d2800300f241bff3465291f3fa06327f3 Mon Sep 17 00:00:00 2001
From: Salvatore Bonaccorso <carnil@debian.org>
Date: Wed, 5 Feb 2025 12:06:14 +0100
Subject: [PATCH 0374/2753] wifi: b43: Replace outdated firmware URL
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

https://wireless.wiki.kernel.org site now redirects to
https://wireless.docs.kernel.org/en/latest/ making the reference
information for the b43 firmware inaccessible. Update the URL to the
current location.

Link: https://bugs.debian.org/1095062
Signed-off-by: Salvatore Bonaccorso <carnil@debian.org>
Acked-by: Michael Büsch <m@bues.ch>
Link: https://patch.msgid.link/20250205110614.216958-1-carnil@debian.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/b43/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/broadcom/b43/main.c b/drivers/net/wireless/broadcom/b43/main.c
index 25b4ef9d3c9a1..7529afd24aed1 100644
--- a/drivers/net/wireless/broadcom/b43/main.c
+++ b/drivers/net/wireless/broadcom/b43/main.c
@@ -2166,7 +2166,7 @@ static void b43_print_fw_helptext(struct b43_wl *wl, bool error)
 {
 	const char text[] =
 		"You must go to " \
-		"https://wireless.wiki.kernel.org/en/users/Drivers/b43#devicefirmware " \
+		"https://wireless.docs.kernel.org/en/latest/en/users/drivers/b43/developers.html#list-of-firmware " \
 		"and download the correct firmware for this driver version. " \
 		"Please carefully read all instructions on this website.\n";
 

From ca47dcc0d0ffd177cbe7cf172c32bef4b0ae3f3a Mon Sep 17 00:00:00 2001
From: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Wed, 5 Feb 2025 14:55:33 +0200
Subject: [PATCH 0375/2753] wifi: iwlwifi: mvm: rename and move
 iwl_mvm_eval_dsm_rfi() to iwl_rfi_is_enabled_in_bios()

Renamed iwl_mvm_eval_dsm_rfi() to iwl_rfi_is_enabled_in_bios() to better
reflect the function's operation. Additionally, moved the function to the
regulatory.c file for better organization. optimize local variable
usage in it.

Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.b7ac9d05234e.Ieb623d7e8dca6bb6a5733682b31e4ff1e39373f0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/regulatory.c    | 31 +++++++++++++++++
 .../wireless/intel/iwlwifi/fw/regulatory.h    |  2 ++
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c   | 34 +------------------
 3 files changed, 34 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index ea435ee94312b..63320689e05d8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -674,3 +674,34 @@ bool iwl_puncturing_is_allowed_in_bios(u32 puncturing, u16 mcc)
 	}
 }
 IWL_EXPORT_SYMBOL(iwl_puncturing_is_allowed_in_bios);
+
+bool iwl_rfi_is_enabled_in_bios(struct iwl_fw_runtime *fwrt)
+{
+	/* default behaviour is disabled */
+	u32 value = 0;
+	int ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_RFI_CONFIG, &value);
+
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(fwrt, "Failed to get DSM RFI, ret=%d\n", ret);
+		return false;
+	}
+
+	value &= DSM_VALUE_RFI_DISABLE;
+	/* RFI BIOS CONFIG value can be 0 or 3 only.
+	 * i.e 0 means DDR and DLVR enabled. 3 means DDR and DLVR disabled.
+	 * 1 and 2 are invalid BIOS configurations, So, it's not possible to
+	 * disable ddr/dlvr separately.
+	 */
+	if (!value) {
+		IWL_DEBUG_RADIO(fwrt, "DSM RFI is evaluated to enable\n");
+		return true;
+	} else if (value == DSM_VALUE_RFI_DISABLE) {
+		IWL_DEBUG_RADIO(fwrt, "DSM RFI is evaluated to disable\n");
+	} else {
+		IWL_DEBUG_RADIO(fwrt,
+				"DSM RFI got invalid value, value=%d\n", value);
+	}
+
+	return false;
+}
+IWL_EXPORT_SYMBOL(iwl_rfi_is_enabled_in_bios);
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index b355d7bef14cd..ed61bc35ef5ba 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -167,6 +167,8 @@ enum iwl_dsm_values_rfi {
 #define DSM_VALUE_RFI_DISABLE	(DSM_VALUE_RFI_DLVR_DISABLE |\
 				 DSM_VALUE_RFI_DDR_DISABLE)
 
+bool iwl_rfi_is_enabled_in_bios(struct iwl_fw_runtime *fwrt);
+
 enum iwl_dsm_masks_reg {
 	DSM_MASK_CHINA_22_REG = BIT(2)
 };
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index df49dd2e2026d..5a9ce7dba7149 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1213,38 +1213,6 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm)
 		IWL_DEBUG_RADIO(mvm, "failed to send TAS_CONFIG (%d)\n", ret);
 }
 
-static bool iwl_mvm_eval_dsm_rfi(struct iwl_mvm *mvm)
-{
-	u32 value = 0;
-	/* default behaviour is disabled */
-	bool bios_enable_rfi = false;
-	int ret = iwl_bios_get_dsm(&mvm->fwrt, DSM_FUNC_RFI_CONFIG, &value);
-
-
-	if (ret < 0) {
-		IWL_DEBUG_RADIO(mvm, "Failed to get DSM RFI, ret=%d\n", ret);
-		return bios_enable_rfi;
-	}
-
-	value &= DSM_VALUE_RFI_DISABLE;
-	/* RFI BIOS CONFIG value can be 0 or 3 only.
-	 * i.e 0 means DDR and DLVR enabled. 3 means DDR and DLVR disabled.
-	 * 1 and 2 are invalid BIOS configurations, So, it's not possible to
-	 * disable ddr/dlvr separately.
-	 */
-	if (!value) {
-		IWL_DEBUG_RADIO(mvm, "DSM RFI is evaluated to enable\n");
-		bios_enable_rfi = true;
-	} else if (value == DSM_VALUE_RFI_DISABLE) {
-		IWL_DEBUG_RADIO(mvm, "DSM RFI is evaluated to disable\n");
-	} else {
-		IWL_DEBUG_RADIO(mvm,
-				"DSM RFI got invalid value, value=%d\n", value);
-	}
-
-	return bios_enable_rfi;
-}
-
 static void iwl_mvm_lari_cfg(struct iwl_mvm *mvm)
 {
 	struct iwl_lari_config_change_cmd cmd;
@@ -1631,7 +1599,7 @@ int iwl_mvm_up(struct iwl_mvm *mvm)
 	iwl_mvm_uats_init(mvm);
 
 	if (iwl_rfi_supported(mvm)) {
-		if (iwl_mvm_eval_dsm_rfi(mvm))
+		if (iwl_rfi_is_enabled_in_bios(&mvm->fwrt))
 			iwl_rfi_send_config_cmd(mvm, NULL);
 	}
 

From 3b67a2c5aa0fea981569426000b0adbe6271703e Mon Sep 17 00:00:00 2001
From: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Wed, 5 Feb 2025 14:55:34 +0200
Subject: [PATCH 0376/2753] wifi: iwlwifi: Unify TAS block list handling in
 regulatory.c

Created a common function iwl_add_mcc_to_tas_block_list() to handle the
operations previously performed by iwl_mld_add_to_tas_block_list() and
iwl_mvm_add_to_tas_block_list(). moved this new function to regulatory.c
to better reflect its purpose and improve code organization.

Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.157d26fb7f02.I87e20e967835bc895be390daf1c6637e20b52aae@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/regulatory.c    | 18 +++++++++++++++++
 .../wireless/intel/iwlwifi/fw/regulatory.h    |  1 +
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c   | 20 ++-----------------
 3 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index 63320689e05d8..11f54339acc65 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -456,6 +456,24 @@ iwl_parse_tas_selection(const u32 tas_selection_in, const u8 tbl_rev)
 }
 IWL_EXPORT_SYMBOL(iwl_parse_tas_selection);
 
+bool iwl_add_mcc_to_tas_block_list(u16 *list, u8 *size, u16 mcc)
+{
+	for (int i = 0; i < *size; i++) {
+		if (list[i] == mcc)
+			return true;
+	}
+
+	/* Verify that there is room for another country
+	 * If *size == IWL_WTAS_BLACK_LIST_MAX, then the table is full.
+	 */
+	if (*size >= IWL_WTAS_BLACK_LIST_MAX)
+		return false;
+
+	list[*size++] = mcc;
+	return true;
+}
+IWL_EXPORT_SYMBOL(iwl_add_mcc_to_tas_block_list);
+
 static __le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt)
 {
 	int ret;
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index ed61bc35ef5ba..d978a4fadfae6 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -192,6 +192,7 @@ int iwl_fill_ppag_table(struct iwl_fw_runtime *fwrt,
 bool iwl_is_ppag_approved(struct iwl_fw_runtime *fwrt);
 
 bool iwl_is_tas_approved(void);
+bool iwl_add_mcc_to_tas_block_list(u16 *list, u8 *size, u16 mcc);
 
 struct iwl_tas_selection_data
 iwl_parse_tas_selection(const u32 tas_selection, const u8 tbl_rev);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index 5a9ce7dba7149..822244b87df3e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1094,22 +1094,6 @@ static int iwl_mvm_ppag_init(struct iwl_mvm *mvm)
 	return iwl_mvm_ppag_send_cmd(mvm);
 }
 
-static bool
-iwl_mvm_add_to_tas_block_list(u16 *list, u8 *size, u16 mcc)
-{
-	/* Verify that there is room for another country */
-	if (*size >= IWL_WTAS_BLACK_LIST_MAX)
-		return false;
-
-	for (u8 i = 0; i < *size; i++) {
-		if (list[i] == mcc)
-			return true;
-	}
-
-	list[*size++] = mcc;
-	return true;
-}
-
 static void iwl_mvm_tas_init(struct iwl_mvm *mvm)
 {
 	u32 cmd_id = WIDE_ID(REGULATORY_AND_NVM_GROUP, TAS_CONFIG);
@@ -1150,10 +1134,10 @@ static void iwl_mvm_tas_init(struct iwl_mvm *mvm)
 		IWL_DEBUG_RADIO(mvm,
 				"System vendor '%s' is not in the approved list, disabling TAS in US and Canada.\n",
 				dmi_get_system_info(DMI_SYS_VENDOR) ?: "<unknown>");
-		if ((!iwl_mvm_add_to_tas_block_list(data.block_list_array,
+		if ((!iwl_add_mcc_to_tas_block_list(data.block_list_array,
 						    &data.block_list_size,
 						    IWL_MCC_US)) ||
-		    (!iwl_mvm_add_to_tas_block_list(data.block_list_array,
+		    (!iwl_add_mcc_to_tas_block_list(data.block_list_array,
 						    &data.block_list_size,
 						    IWL_MCC_CANADA))) {
 			IWL_DEBUG_RADIO(mvm,

From 696cca64308dc641d0bbe4aa2c09dd9752aa288d Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 5 Feb 2025 14:55:35 +0200
Subject: [PATCH 0377/2753] wifi: iwlwifi: don't warn during reprobe

During reprobe, the sw state is being destroyd, and so is the
connection. When the peer STA is being removed, the opmode sends a
command to flush the TXQs of the STA and uses iwl_trans_wait_txq_empty.

This one warns if the FW is not alive, but it really shouldn't if
there is a FW error - and return silently instead, just like we do when
sending a hcmd.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250205145347.76425b10e5a0.I3bf0de2eb090a8b94c4e36d93dd91df61fadb808@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 49c8507d1a6b1..8ba24903a8708 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -671,6 +671,9 @@ IWL_EXPORT_SYMBOL(iwl_trans_txq_enable_cfg);
 
 int iwl_trans_wait_txq_empty(struct iwl_trans *trans, int queue)
 {
+	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
+		return -EIO;
+
 	if (WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
 		      "bad state = %d\n", trans->state))
 		return -EIO;

From 8a065234e877f9ffa51112539aff7bdf179a40c4 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 14:55:36 +0200
Subject: [PATCH 0378/2753] wifi: iwlwifi: enable 320 MHz on slow PCIe links

Despite not being able to sustain the full 320 MHz throughput
even at MCS 9, enable 320 MHz on slow PCIe links. This may in
some cases result in frames being dropped (on the air) by the
firmware if they cannot be delivered to the host, but it can
still be better to use 320 MHz.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.1e5356a3b124.I1224023721aaeff8ebcaa47dff88613c7fd0533a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/iwl-nvm-parse.c  | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 9f7e013252feb..76259ac261cb4 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -913,11 +913,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 {
 	bool is_ap = iftype_data->types_mask & (BIT(NL80211_IFTYPE_AP) |
 						BIT(NL80211_IFTYPE_P2P_GO));
-	bool no_320;
-
-	no_320 = (!trans->trans_cfg->integrated &&
-		 trans->pcie_link_speed < PCI_EXP_LNKSTA_CLS_8_0GB) ||
-		 trans->reduced_cap_sku;
+	bool slow_pcie = (!trans->trans_cfg->integrated &&
+			  trans->pcie_link_speed < PCI_EXP_LNKSTA_CLS_8_0GB);
 
 	if (!data->sku_cap_11be_enable || iwlwifi_mod_params.disable_11be)
 		iftype_data->eht_cap.has_eht = false;
@@ -944,7 +941,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 				       IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
 		break;
 	case NL80211_BAND_6GHZ:
-		if (!no_320) {
+		if (!trans->reduced_cap_sku) {
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[0] |=
 				IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[1] |=
@@ -986,6 +983,14 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 				iftype_data->eht_cap.eht_cap_elem.phy_cap_info[4] |= 0x10;
 			}
 		}
+
+		if (slow_pcie) {
+			struct ieee80211_eht_mcs_nss_supp *mcs_nss =
+				&iftype_data->eht_cap.eht_mcs_nss_supp;
+
+			mcs_nss->bw._320.rx_tx_mcs11_max_nss = 0;
+			mcs_nss->bw._320.rx_tx_mcs13_max_nss = 0;
+		}
 	} else {
 		struct ieee80211_he_mcs_nss_supp *he_mcs_nss_supp =
 			&iftype_data->he_cap.he_mcs_nss_supp;

From 4cb46c1c732dd40220aa7c938c9647a6041e0a29 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 14:55:37 +0200
Subject: [PATCH 0379/2753] wifi: iwlwifi: cfg: separate 22000/BZ family HT
 params

We're adding a new IWLMLD opmode for just BZ and later
devices. If that's enabled but IWLMVM isn't, the build
fails because 22000 family configs aren't built but BZ
and later refer to it. Rather than trying to make some
new file to build it in all cases, just copy the small
struct.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.1d6186c23bee.I3c61a6c9e0db3ba6eea4dac63e1547945ad01703@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c     | 9 ++++++++-
 drivers/net/wireless/intel/iwlwifi/cfg/dr.c     | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c     | 2 +-
 drivers/net/wireless/intel/iwlwifi/iwl-config.h | 2 ++
 4 files changed, 12 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index 074b2c9ea003b..64a5bbb45c836 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -50,6 +50,13 @@ static const struct iwl_base_params iwl_bz_base_params = {
 	.pcie_l1_allowed = true,
 };
 
+const struct iwl_ht_params iwl_bz_ht_params = {
+	.stbc = true,
+	.ldpc = true,
+	.ht40_bands = BIT(NL80211_BAND_2GHZ) | BIT(NL80211_BAND_5GHZ) |
+		      BIT(NL80211_BAND_6GHZ),
+};
+
 #define IWL_DEVICE_BZ_COMMON						\
 	.ucode_api_max = IWL_BZ_UCODE_API_MAX,			\
 	.ucode_api_min = IWL_BZ_UCODE_API_MIN,			\
@@ -113,7 +120,7 @@ static const struct iwl_base_params iwl_bz_base_params = {
 
 #define IWL_DEVICE_BZ							\
 	IWL_DEVICE_BZ_COMMON,						\
-	.ht_params = &iwl_22000_ht_params
+	.ht_params = &iwl_bz_ht_params
 
 /*
  * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
index ab7c0f8d54f42..69176b59b4dee 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
@@ -114,7 +114,7 @@ static const struct iwl_base_params iwl_dr_base_params = {
 	.uhb_supported = true,						\
 	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
 	.num_rbds = IWL_NUM_RBDS_DR_EHT,				\
-	.ht_params = &iwl_22000_ht_params
+	.ht_params = &iwl_bz_ht_params
 
 /*
  * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index c9eeb3f6704e2..eee47af728d7f 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -121,7 +121,7 @@ static const struct iwl_base_params iwl_sc_base_params = {
 	.uhb_supported = true,						\
 	.features = IWL_TX_CSUM_NETIF_FLAGS | NETIF_F_RXCSUM,		\
 	.num_rbds = IWL_NUM_RBDS_SC_EHT,				\
-	.ht_params = &iwl_22000_ht_params
+	.ht_params = &iwl_bz_ht_params
 
 /*
  * This size was picked according to 8 MSDUs inside 512 A-MSDUs in an
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 91275680dd2cb..c2caaf875c117 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -660,6 +660,8 @@ extern const struct iwl_cfg iwl_cfg_ma;
 extern const struct iwl_cfg iwl_cfg_so_a0_hr_a0;
 extern const struct iwl_cfg iwl_cfg_quz_a0_hr_b0;
 
+extern const struct iwl_ht_params iwl_bz_ht_params;
+
 extern const struct iwl_cfg iwl_cfg_bz;
 extern const struct iwl_cfg iwl_cfg_gl;
 

From bdfc32abd5d640198a00aceb1d497223b85bca7e Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 14:55:38 +0200
Subject: [PATCH 0380/2753] wifi: iwlwifi: Indicate support for EPCS

Indicate support for EPCS and unsolicited EPCS in the EHT MAC
capabilities.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.6b1c7cc8a958.Idd72ea53f70eb452d43d99e6c45ff21f891100bd@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 76259ac261cb4..c381511e9ec65 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -684,10 +684,13 @@ static const struct ieee80211_sband_iftype_data iwl_he_eht_capa[] = {
 			.has_eht = true,
 			.eht_cap_elem = {
 				.mac_cap_info[0] =
+					IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS |
 					IEEE80211_EHT_MAC_CAP0_OM_CONTROL |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1 |
 					IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2 |
 					IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC,
+				.mac_cap_info[1] =
+					IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS,
 				.phy_cap_info[0] =
 					IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ |
 					IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI |

From 926ad5f970d6b6573ba508da69e91cc6dba3611f Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Wed, 5 Feb 2025 14:55:39 +0200
Subject: [PATCH 0381/2753] wifi: iwlwifi: mvm: Indicate support link
 reconfiguration

As MLO link configuration is supported by mac80211, indicate
support for MLO link reconfiguration in station mode.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
----------------
depends on "wifi: ieee80211: Add some missing MLO related definitions"
Link: https://patch.msgid.link/20250205145347.92d19705d2b9.Id07fa3ebad6bc23ecf6e91868f67150ce70f47b0@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index af6644b7e95fb..014777c9cc5d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -272,9 +272,10 @@ static const u8 tm_if_types_ext_capa_sta[] = {
 					__bf_shf(IEEE80211_EML_CAP_EMLSR_PADDING_DELAY) | \
 				 IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US << \
 					__bf_shf(IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY))
-#define IWL_MVM_MLD_CAPA_OPS FIELD_PREP_CONST( \
+#define IWL_MVM_MLD_CAPA_OPS (FIELD_PREP_CONST( \
 			IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP, \
-			IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME)
+			IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME) | \
+			IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT)
 
 static const struct wiphy_iftype_ext_capab add_iftypes_ext_capa[] = {
 	{

From c9afb4cf6d2fe1b34e95b1d1db695d6054a7dc35 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 14:55:40 +0200
Subject: [PATCH 0382/2753] wifi: iwlwifi: fw: make
 iwl_send_dbg_dump_complete_cmd() static

It's only used in the same file, so can be static.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.319b66c00676.I3c06d6c2ee5850a5a89feff7d770e557fd625a6d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 5 ++---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.h | 3 ---
 2 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fb2ea38e89aca..10bde19e9dca3 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -3042,9 +3042,8 @@ int iwl_fw_start_dbg_conf(struct iwl_fw_runtime *fwrt, u8 conf_id)
 }
 IWL_EXPORT_SYMBOL(iwl_fw_start_dbg_conf);
 
-void iwl_send_dbg_dump_complete_cmd(struct iwl_fw_runtime *fwrt,
-				    u32 timepoint,
-				    u32 timepoint_data)
+static void iwl_send_dbg_dump_complete_cmd(struct iwl_fw_runtime *fwrt,
+					   u32 timepoint, u32 timepoint_data)
 {
 	struct iwl_dbg_dump_complete_cmd hcmd_data;
 	struct iwl_host_cmd hcmd = {
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
index 87998374f459e..35e30e5db462d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.h
@@ -324,9 +324,6 @@ static inline void iwl_fwrt_update_fw_versions(struct iwl_fw_runtime *fwrt,
 }
 
 void iwl_fwrt_dump_error_logs(struct iwl_fw_runtime *fwrt);
-void iwl_send_dbg_dump_complete_cmd(struct iwl_fw_runtime *fwrt,
-				    u32 timepoint,
-				    u32 timepoint_data);
 bool iwl_fwrt_read_err_table(struct iwl_trans *trans, u32 base, u32 *err_id);
 void iwl_fw_disable_dbg_asserts(struct iwl_fw_runtime *fwrt);
 void iwl_fw_dbg_clear_monitor_buf(struct iwl_fw_runtime *fwrt);

From 1bbc086f49b436ec6773ce48864c80cd682888e8 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 14:55:41 +0200
Subject: [PATCH 0383/2753] wifi: iwlwifi: be less aggressive with re-probe

Re-probing if we had 2 firmware crash within 3 minutes is really too
aggressive. Drastically reduce the threshold to 7 seconds.
After 7 seconds, a new firmware crash will be considered "new" and not
cause a PCI re-probe.
This allows to pass tests that cause a firmware crash every 10 seconds
and expect to see no impact on the traffic.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.38f912b047f4.I03f0c10ae9e7ecea639431f3e089b757cc8a4347@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 8ba24903a8708..1632ab20a23f7 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -97,7 +97,7 @@ static void iwl_trans_reprobe_wk(struct work_struct *wk)
 	module_put(THIS_MODULE);
 }
 
-#define IWL_TRANS_RESET_OK_TIME	180 /* seconds */
+#define IWL_TRANS_RESET_OK_TIME	7 /* seconds */
 
 static enum iwl_reset_mode
 iwl_trans_determine_restart_mode(struct iwl_trans *trans)

From 75a3313f52b7e08e7e73746f69a68c2b7c28bb2b Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 14:55:42 +0200
Subject: [PATCH 0384/2753] wifi: iwlwifi: make no_160 more generic

We'll have devices that are EHT capable but don't support 320 MHz and
those devices look like the 320 MHz capable devices, but have distinct
subsystem ID.
We already had the same type of differentiation for HE devices that
support 160 MHz or not.
Enhance that mechanism and now the _IWL_DEV_INFO macro gets an
indication whether the bandwidth should be limited for that specific
device.
The subsystem ID gives a binary answer about the bandwidth limitation
and iwl_pci_find_dev_info() compares this to the list of _IWL_DEV_INFO
entries.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.1ba406c538a5.I6e24123f60a764aedfeaaac8768c26e136c320cf@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/iwl-config.h   |  15 +-
 .../wireless/intel/iwlwifi/iwl-nvm-parse.c    |   4 +-
 .../net/wireless/intel/iwlwifi/iwl-trans.h    |   7 +-
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 194 +++++++++---------
 .../wireless/intel/iwlwifi/tests/devinfo.c    |  15 +-
 5 files changed, 123 insertions(+), 112 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index c2caaf875c117..c2cdb5026460b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2005-2014, 2018-2021 Intel Corporation
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #ifndef __IWL_CONFIG_H__
 #define __IWL_CONFIG_H__
@@ -451,11 +451,8 @@ struct iwl_cfg {
 #define IWL_CFG_RF_ID_HR		0x7
 #define IWL_CFG_RF_ID_HR1		0x4
 
-#define IWL_CFG_NO_160			0x1
-#define IWL_CFG_160			0x0
-
-#define IWL_CFG_NO_320			0x1
-#define IWL_CFG_320			0x0
+#define IWL_CFG_BW_NO_LIM		(U16_MAX - 1)
+#define IWL_CFG_BW_ANY			U16_MAX
 
 #define IWL_CFG_CORES_BT		0x0
 #define IWL_CFG_CORES_BT_GNSS		0x5
@@ -467,7 +464,7 @@ struct iwl_cfg {
 #define IWL_CFG_IS_JACKET		0x1
 
 #define IWL_SUBDEVICE_RF_ID(subdevice)	((u16)((subdevice) & 0x00F0) >> 4)
-#define IWL_SUBDEVICE_NO_160(subdevice)	((u16)((subdevice) & 0x0200) >> 9)
+#define IWL_SUBDEVICE_BW_LIM(subdevice)	((u16)((subdevice) & 0x0200) >> 9)
 #define IWL_SUBDEVICE_CORES(subdevice)	((u16)((subdevice) & 0x1C00) >> 10)
 
 struct iwl_dev_info {
@@ -475,10 +472,10 @@ struct iwl_dev_info {
 	u16 subdevice;
 	u16 mac_type;
 	u16 rf_type;
+	u16 bw_limit;
 	u8 mac_step;
 	u8 rf_step;
 	u8 rf_id;
-	u8 no_160;
 	u8 cores;
 	u8 cdb;
 	u8 jacket;
@@ -492,7 +489,7 @@ extern const unsigned int iwl_dev_info_table_size;
 const struct iwl_dev_info *
 iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
 		      u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
-		      u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step);
+		      u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step);
 extern const struct pci_device_id iwl_hw_card_ids[];
 #endif
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index c381511e9ec65..08269168b2fab 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1094,7 +1094,7 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		iftype_data->eht_cap.eht_mcs_nss_supp.bw._320.rx_tx_mcs13_max_nss = 0;
 	}
 
-	if (trans->no_160)
+	if (trans->bw_limit < 160)
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[0] &=
 			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index f6234065dbdde..3561ff8483f20 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2023, 2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -876,7 +876,7 @@ struct iwl_txq {
  *	only valid for discrete (not integrated) NICs
  * @invalid_tx_cmd: invalid TX command buffer
  * @reduced_cap_sku: reduced capability supported SKU
- * @no_160: device not supporting 160 MHz
+ * @bw_limit: the max bandwidth
  * @step_urm: STEP is in URM, no support for MCS>9 in 320 MHz
  * @restart: restart worker data
  * @restart.wk: restart worker
@@ -910,7 +910,8 @@ struct iwl_trans {
 	char hw_id_str[52];
 	u32 sku_id[3];
 	bool reduced_cap_sku;
-	u8 no_160:1, step_urm:1;
+	u16 bw_limit;
+	bool step_urm;
 
 	u8 dsbr_urm_fw_dependent:1,
 	   dsbr_urm_permanent:1;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index e0b657b2f74b0..346a5c178dc24 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -551,16 +551,17 @@ MODULE_DEVICE_TABLE(pci, iwl_hw_card_ids);
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_hw_card_ids);
 
 #define _IWL_DEV_INFO(_device, _subdevice, _mac_type, _mac_step, _rf_type, \
-		      _rf_id, _rf_step, _no_160, _cores, _cdb, _cfg, _name) \
+		      _rf_id, _rf_step, _bw_limit, _cores, _cdb, _cfg, _name) \
 	{ .device = (_device), .subdevice = (_subdevice), .cfg = &(_cfg), \
 	  .name = _name, .mac_type = _mac_type, .rf_type = _rf_type, .rf_step = _rf_step, \
-	  .no_160 = _no_160, .cores = _cores, .rf_id = _rf_id, \
+	  .bw_limit = _bw_limit, .cores = _cores, .rf_id = _rf_id, \
 	  .mac_step = _mac_step, .cdb = _cdb, .jacket = IWL_CFG_ANY }
 
 #define IWL_DEV_INFO(_device, _subdevice, _cfg, _name) \
 	_IWL_DEV_INFO(_device, _subdevice, IWL_CFG_ANY, IWL_CFG_ANY,   \
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,  \
-		      IWL_CFG_ANY, _cfg, _name)
+		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY, \
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY, \
+		      _cfg, _name)
 
 VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 #if IS_ENABLED(CONFIG_IWLMVM)
@@ -723,66 +724,66 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9462_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_PU, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_2ac_cfg_soc, iwl9560_name),
 
 	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9270_160_name),
 	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT_GNSS, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9270_name),
 
 	_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9162_160_name),
 	_IWL_DEV_INFO(0x271B, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9162_name),
 
 	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9260_160_name),
 	_IWL_DEV_INFO(0x2526, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_TH, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_TH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9260_2ac_cfg, iwl9260_name),
 
 /* Qu with Jf */
@@ -790,132 +791,132 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9462_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550s_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_b0_jf_b0_cfg, iwl9560_killer_1550i_name),
 
 	/* Qu C step */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9462_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550s_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_qu_c0_jf_b0_cfg, iwl9560_killer_1550i_name),
 
 	/* QuZ */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9462_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1551,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550s_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, 0x1552,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwl9560_quz_a0_jf_b0_cfg, iwl9560_killer_1550i_name),
 
 /* Qu with Hr */
@@ -923,202 +924,202 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_qu_b0_hr1_b0, iwl_ax101_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_qu_b0_hr_b0, iwl_ax203_name),
 
 	/* Qu C step */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_qu_c0_hr1_b0, iwl_ax101_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_qu_c0_hr_b0, iwl_ax203_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QU, SILICON_C_STEP,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_qu_c0_hr_b0, iwl_ax201_name),
 
 	/* QuZ */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_quz_a0_hr1_b0, iwl_ax101_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_quz_a0_hr_b0, iwl_ax203_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_QUZ, SILICON_B_STEP,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_quz_a0_hr_b0, iwl_ax201_name),
 
 /* Ma */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_ma, iwl_ax201_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_ma, iwl_ax211_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_MA, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_ma, iwl_ax231_name),
 
 /* So with Hr */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
 
 /* So-F with Hr */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax203_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR1, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax101_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_so_a0_hr_a0, iwl_ax201_name),
 
 /* So-F with Gf */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
 		      iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
 
 /* SoF with JF2 */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
 
 /* SoF with JF */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SOF, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
 
 /* So with GF */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwlax211_2ax_cfg_so_gf_a0, iwl_ax211_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_ANY, IWL_CFG_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_CDB,
 		      iwlax411_2ax_cfg_so_gf4_a0, iwl_ax411_name),
 
 /* So with JF2 */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF2, IWL_CFG_RF_ID_JF, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9560_name),
 
 /* So with JF */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_160_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9461_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SO, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_JF1, IWL_CFG_RF_ID_JF1_DIV, IWL_CFG_ANY,
-		      IWL_CFG_NO_160, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
+		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
 
 /* Bz */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_ax201_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_ax211_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
@@ -1130,73 +1131,73 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_wh_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_HR2, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_ax201_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_ax211_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_fm_name),
 
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ_W, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_bz, iwl_wh_name),
 
 /* Ga (Gl) */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_gl, iwl_gl_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_GL, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_NO_320, IWL_CFG_ANY, IWL_CFG_NO_CDB,
+		      160, IWL_CFG_ANY, IWL_CFG_NO_CDB,
 		      iwl_cfg_gl, iwl_mtp_name),
 
 /* Sc */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc, iwl_sc_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc2, iwl_sc2_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc2f, iwl_sc2f_name),
 /* Dr */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_dr, iwl_dr_name),
 
 /* Br */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BR, IWL_CFG_ANY,
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_br, iwl_br_name),
 #endif /* CONFIG_IWLMVM */
 };
@@ -1348,7 +1349,7 @@ static int map_crf_id(struct iwl_trans *iwl_trans)
 VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info *
 iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
 		      u16 mac_type, u8 mac_step, u16 rf_type, u8 cdb,
-		      u8 jacket, u8 rf_id, u8 no_160, u8 cores, u8 rf_step)
+		      u8 jacket, u8 rf_id, u8 bw_limit, u8 cores, u8 rf_step)
 {
 	int num_devices = ARRAY_SIZE(iwl_dev_info_table);
 	int i;
@@ -1391,8 +1392,15 @@ iwl_pci_find_dev_info(u16 device, u16 subsystem_device,
 		    dev_info->rf_id != rf_id)
 			continue;
 
-		if (dev_info->no_160 != (u8)IWL_CFG_ANY &&
-		    dev_info->no_160 != no_160)
+		/*
+		 * Check that bw_limit have the same "boolean" value since
+		 * IWL_SUBDEVICE_BW_LIM can only return a boolean value and
+		 * dev_info->bw_limit encodes a non-boolean value.
+		 * dev_info->bw_limit == IWL_CFG_BW_NO_LIM must be equal to
+		 * !bw_limit to have a match.
+		 */
+		if (dev_info->bw_limit != IWL_CFG_BW_ANY &&
+		    (dev_info->bw_limit == IWL_CFG_BW_NO_LIM) == !!bw_limit)
 			continue;
 
 		if (dev_info->cores != (u8)IWL_CFG_ANY &&
@@ -1530,13 +1538,13 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 					 CSR_HW_RFID_IS_CDB(iwl_trans->hw_rf_id),
 					 CSR_HW_RFID_IS_JACKET(iwl_trans->hw_rf_id),
 					 IWL_SUBDEVICE_RF_ID(pdev->subsystem_device),
-					 IWL_SUBDEVICE_NO_160(pdev->subsystem_device),
+					 IWL_SUBDEVICE_BW_LIM(pdev->subsystem_device),
 					 IWL_SUBDEVICE_CORES(pdev->subsystem_device),
 					 CSR_HW_RFID_STEP(iwl_trans->hw_rf_id));
 	if (dev_info) {
 		iwl_trans->cfg = dev_info->cfg;
 		iwl_trans->name = dev_info->name;
-		iwl_trans->no_160 = dev_info->no_160 == IWL_CFG_NO_160;
+		iwl_trans->bw_limit = dev_info->bw_limit;
 	}
 
 #if IS_ENABLED(CONFIG_IWLMVM)
diff --git a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
index d0bda23c628aa..7ef5e89c6af27 100644
--- a/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
+++ b/drivers/net/wireless/intel/iwlwifi/tests/devinfo.c
@@ -2,7 +2,7 @@
 /*
  * KUnit tests for the iwlwifi device info table
  *
- * Copyright (C) 2023-2024 Intel Corporation
+ * Copyright (C) 2023-2025 Intel Corporation
  */
 #include <kunit/test.h>
 #include <linux/pci.h>
@@ -13,9 +13,9 @@ MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
 
 static void iwl_pci_print_dev_info(const char *pfx, const struct iwl_dev_info *di)
 {
-	printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,no_160=%d,cores=%.2x\n",
+	printk(KERN_DEBUG "%sdev=%.4x,subdev=%.4x,mac_type=%.4x,mac_step=%.4x,rf_type=%.4x,cdb=%d,jacket=%d,rf_id=%.2x,bw_limit=%d,cores=%.2x\n",
 	       pfx, di->device, di->subdevice, di->mac_type, di->mac_step,
-	       di->rf_type, di->cdb, di->jacket, di->rf_id, di->no_160,
+	       di->rf_type, di->cdb, di->jacket, di->rf_id, di->bw_limit,
 	       di->cores);
 }
 
@@ -31,8 +31,13 @@ static void devinfo_table_order(struct kunit *test)
 					    di->mac_type, di->mac_step,
 					    di->rf_type, di->cdb,
 					    di->jacket, di->rf_id,
-					    di->no_160, di->cores, di->rf_step);
-		if (ret != di) {
+					    di->bw_limit != IWL_CFG_BW_NO_LIM,
+					    di->cores, di->rf_step);
+		if (!ret) {
+			iwl_pci_print_dev_info("No entry found for: ", di);
+			KUNIT_FAIL(test,
+				   "No entry found for entry at index %d\n", idx);
+		} else if (ret != di) {
 			iwl_pci_print_dev_info("searched: ", di);
 			iwl_pci_print_dev_info("found:    ", ret);
 			KUNIT_FAIL(test,

From 66672fa681b3f21d90300a723a22cc2a0d5d3446 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 14:55:43 +0200
Subject: [PATCH 0385/2753] wifi: iwlwifi: properly set the names for SC
 devices

Sc devices can come with several CRFs. Use the CRF to determine the name
of the device.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.5bf5d931204e.I5eb435db1b8df46687c43ebae6488c0c4430d530@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c   |  6 ---
 .../net/wireless/intel/iwlwifi/iwl-config.h   |  3 --
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 43 ++++++++++++++++---
 3 files changed, 37 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index eee47af728d7f..eb56af9a8411b 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -142,22 +142,16 @@ const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
-const char iwl_sc_name[] = "Intel(R) TBD Sc device";
-
 const struct iwl_cfg iwl_cfg_sc = {
 	.fw_name_mac = "sc",
 	IWL_DEVICE_SC,
 };
 
-const char iwl_sc2_name[] = "Intel(R) TBD Sc2 device";
-
 const struct iwl_cfg iwl_cfg_sc2 = {
 	.fw_name_mac = "sc2",
 	IWL_DEVICE_SC,
 };
 
-const char iwl_sc2f_name[] = "Intel(R) TBD Sc2f device";
-
 const struct iwl_cfg iwl_cfg_sc2f = {
 	.fw_name_mac = "sc2f",
 	IWL_DEVICE_SC,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index c2cdb5026460b..5fc9ce2b350e9 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -552,9 +552,6 @@ extern const char iwl_fm_name[];
 extern const char iwl_wh_name[];
 extern const char iwl_gl_name[];
 extern const char iwl_mtp_name[];
-extern const char iwl_sc_name[];
-extern const char iwl_sc2_name[];
-extern const char iwl_sc2f_name[];
 extern const char iwl_dr_name[];
 extern const char iwl_br_name[];
 #if IS_ENABLED(CONFIG_IWLDVM)
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 346a5c178dc24..cd347cd8176a7 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1173,19 +1173,50 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 /* Sc */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc, iwl_ax211_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc, iwl_fm_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc, iwl_sc_name),
+		      iwl_cfg_sc, iwl_wh_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2, iwl_ax211_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2, iwl_sc2_name),
+		      iwl_cfg_sc2, iwl_fm_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2, iwl_wh_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
-		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
-		      iwl_cfg_sc2f, iwl_sc2f_name),
+		      iwl_cfg_sc2f, iwl_ax211_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_FM, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2f, iwl_fm_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2f, iwl_wh_name),
+
 /* Dr */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_DR, IWL_CFG_ANY,

From 9e8c760471243a10e78090f38198d846c41140a3 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 5 Feb 2025 14:55:44 +0200
Subject: [PATCH 0386/2753] wifi: iwlwifi: clarify the meaning of IWL_INIT_PHY

This is a bit that tells the firmware to wait for the
PHY_CONFIGURATION_CMD before completing its init sequence.
Clarify this in the comment.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.097510347ae2.Ica00b4b30163a21bf993fa968dd406ee4023fc9e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/alive.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
index ebe85fdf08d31..42360a8f23aaf 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/alive.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018, 2020-2021, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018, 2020-2021, 2024-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -117,7 +117,7 @@ struct iwl_alive_ntf_v6 {
  *	finishing init flow
  * @IWL_INIT_DEBUG_CFG: driver is going to send debug config command
  * @IWL_INIT_NVM: driver is going to send NVM_ACCESS commands
- * @IWL_INIT_PHY: driver is going to send PHY_DB commands
+ * @IWL_INIT_PHY: driver is going to send the PHY_CONFIGURATION_CMD
  */
 enum iwl_extended_cfg_flags {
 	IWL_INIT_DEBUG_CFG,

From af3be9088404ef8007e895ecaff5d173a227ea61 Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 5 Feb 2025 14:55:45 +0200
Subject: [PATCH 0387/2753] wifi: iwlwifi: support ROC version 6

Version 6 added ROC with multi repetitions.
We don't use it, but need to update the command
length.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.956c33729d48.I609835c08f0003c084a13a1e1e505cb7bc8ecbc6@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../intel/iwlwifi/fw/api/time-event.h         |  42 +++-
 drivers/net/wireless/intel/iwlwifi/mld/roc.c  | 224 ++++++++++++++++++
 .../wireless/intel/iwlwifi/mvm/time-event.c   |   6 +-
 3 files changed, 265 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/roc.c

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h
index 18d030334a6a6..f586379d66ddd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/time-event.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2020, 2022-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2020, 2022-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -351,7 +351,7 @@ enum iwl_roc_activity {
 }; /* ROC_ACTIVITY_API_E_VER_1 */
 
 /*
- * ROC command
+ * ROC command v5
  *
  * Command requests the firmware to remain on a channel for a certain duration.
  *
@@ -366,7 +366,7 @@ enum iwl_roc_activity {
  * @max_delay: max delay the ROC can start in TU
  * @duration: remain on channel duration in TU
  */
-struct iwl_roc_req {
+struct iwl_roc_req_v5 {
 	__le32 action;
 	__le32 activity;
 	__le32 sta_id;
@@ -375,7 +375,41 @@ struct iwl_roc_req {
 	__le16 reserved;
 	__le32 max_delay;
 	__le32 duration;
-} __packed; /* ROC_CMD_API_S_VER_3 */
+} __packed; /* ROC_CMD_API_S_VER_5 */
+
+/*
+ * ROC command
+ *
+ * Command requests the firmware to remain on a channel for a certain duration.
+ *
+ * ( MAC_CONF_GROUP 0x3, ROC_CMD 0xE )
+ *
+ * @action: action to perform, see &enum iwl_ctxt_action
+ * @activity: type of activity, see &enum iwl_roc_activity
+ * @sta_id: station id, resumed during "Remain On Channel" activity.
+ * @channel_info: &struct iwl_fw_channel_info
+ * @node_addr: node MAC address for Rx filtering
+ * @reserved1: align to a dword
+ * @max_delay: max delay the ROC can start in TU
+ * @duration: remain on channel duration in TU
+ * @interval: interval between repetitions (when repetitions > 1).
+ * @repetitions: number of repetitions
+ *	0xFF: infinite repetitions. 0 or 1: single repetition.
+ * @reserved2: align to a dword
+ */
+struct iwl_roc_req {
+	__le32 action;
+	__le32 activity;
+	__le32 sta_id;
+	struct iwl_fw_channel_info channel_info;
+	u8 node_addr[ETH_ALEN];
+	__le16 reserved1;
+	__le32 max_delay;
+	__le32 duration;
+	__le32 interval;
+	u8 repetitions;
+	u8 reserved2[3];
+} __packed; /* ROC_CMD_API_S_VER_6 */
 
 /*
  * ROC notification
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.c b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
new file mode 100644
index 0000000000000..b87faca23cebe
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 - 2025 Intel Corporation
+ */
+#include <net/cfg80211.h>
+#include <net/mac80211.h>
+
+#include "mld.h"
+#include "roc.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "sta.h"
+#include "mlo.h"
+
+#include "fw/api/context.h"
+#include "fw/api/time-event.h"
+
+#define AUX_ROC_MAX_DELAY MSEC_TO_TU(200)
+
+static void
+iwl_mld_vif_iter_emlsr_block_roc(void *data, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int *result = data;
+	int ret;
+
+	ret = iwl_mld_block_emlsr_sync(mld_vif->mld, vif,
+				       IWL_MLD_EMLSR_BLOCKED_ROC,
+				       iwl_mld_get_primary_link(vif));
+	if (ret)
+		*result = ret;
+}
+
+int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_channel *channel, int duration,
+		      enum ieee80211_roc_type type)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_int_sta *aux_sta;
+	struct iwl_roc_req cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
+	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
+				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
+	enum iwl_roc_activity activity;
+	int ret = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_block_roc,
+						&ret);
+	if (ret)
+		return ret;
+
+	/* TODO: task=Hotspot 2.0 */
+	if (vif->type != NL80211_IFTYPE_P2P_DEVICE) {
+		IWL_ERR(mld, "NOT SUPPORTED: ROC on vif->type %d\n",
+			vif->type);
+
+		return -EOPNOTSUPP;
+	}
+
+	switch (type) {
+	case IEEE80211_ROC_TYPE_NORMAL:
+		activity = ROC_ACTIVITY_P2P_DISC;
+		break;
+	case IEEE80211_ROC_TYPE_MGMT_TX:
+		activity = ROC_ACTIVITY_P2P_NEG;
+		break;
+	default:
+		WARN_ONCE(1, "Got an invalid P2P ROC type\n");
+		return -EINVAL;
+	}
+
+	if (WARN_ON(mld_vif->roc_activity != ROC_NUM_ACTIVITIES))
+		return -EBUSY;
+
+	/* No MLO on P2P device */
+	aux_sta = &mld_vif->deflink.aux_sta;
+
+	ret = iwl_mld_add_aux_sta(mld, aux_sta);
+	if (ret)
+		return ret;
+
+	cmd.activity = cpu_to_le32(activity);
+	cmd.sta_id = cpu_to_le32(aux_sta->sta_id);
+	cmd.channel_info.channel = cpu_to_le32(channel->hw_value);
+	cmd.channel_info.band = iwl_mld_nl80211_band_to_fw(channel->band);
+	cmd.channel_info.width = IWL_PHY_CHANNEL_MODE20;
+	/* TODO: task=Hotspot 2.0, revisit those parameters when we add an ROC
+	 * on the BSS vif
+	 */
+	cmd.max_delay = cpu_to_le32(AUX_ROC_MAX_DELAY);
+	cmd.duration = cpu_to_le32(MSEC_TO_TU(duration));
+
+	memcpy(cmd.node_addr, vif->addr, ETH_ALEN);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
+				   &cmd, cmd_len);
+	if (ret) {
+		IWL_ERR(mld, "Couldn't send the ROC_CMD\n");
+		return ret;
+	}
+	mld_vif->roc_activity = activity;
+
+	return 0;
+}
+
+static void
+iwl_mld_vif_iter_emlsr_unblock_roc(void *data, u8 *mac,
+				   struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	iwl_mld_unblock_emlsr(mld_vif->mld, vif, IWL_MLD_EMLSR_BLOCKED_ROC);
+}
+
+static void iwl_mld_destroy_roc(struct iwl_mld *mld,
+				struct ieee80211_vif *vif,
+				struct iwl_mld_vif *mld_vif)
+{
+	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_unblock_roc,
+						NULL);
+
+	/* wait until every tx has seen that roc_activity has been reset */
+	synchronize_net();
+	/* from here, no new tx will be added
+	 * we can flush the Tx on the queues
+	 */
+
+	iwl_mld_flush_link_sta_txqs(mld, mld_vif->deflink.aux_sta.sta_id);
+
+	iwl_mld_remove_aux_sta(mld, vif, &vif->bss_conf);
+}
+
+int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_roc_req cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
+				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* TODO: task=Hotspot 2.0 */
+	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
+		return -EOPNOTSUPP;
+
+	/* No roc activity running it's probably already done */
+	if (mld_vif->roc_activity == ROC_NUM_ACTIVITIES)
+		return 0;
+
+	cmd.activity = cpu_to_le32(mld_vif->roc_activity);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
+				   &cmd, cmd_len);
+	if (ret)
+		IWL_ERR(mld, "Couldn't send the command to cancel the ROC\n");
+
+	/* We may have raced with the firmware expiring the ROC instance at
+	 * this very moment. In that case, we can have a notification in the
+	 * async processing queue. However, none can arrive _after_ this as
+	 * ROC_CMD was sent synchronously, i.e. we waited for a response and
+	 * the firmware cannot refer to this ROC after the response. Thus,
+	 * if we just cancel the notification (if there's one) we'll be at a
+	 * clean state for any possible next ROC.
+	 */
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_ROC,
+					       mld_vif->roc_activity);
+
+	iwl_mld_destroy_roc(mld, vif, mld_vif);
+
+	return 0;
+}
+
+void iwl_mld_handle_roc_notif(struct iwl_mld *mld,
+			      struct iwl_rx_packet *pkt)
+{
+	const struct iwl_roc_notif *notif = (void *)pkt->data;
+	u32 activity = le32_to_cpu(notif->activity);
+	/* TODO: task=Hotspot 2.0 - roc can run on BSS */
+	struct ieee80211_vif *vif = mld->p2p_device_vif;
+	struct iwl_mld_vif *mld_vif;
+
+	if (WARN_ON(!vif))
+		return;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	/* It is possible that the ROC was canceled
+	 * but the notification was already fired.
+	 */
+	if (mld_vif->roc_activity != activity)
+		return;
+
+	if (le32_to_cpu(notif->success) &&
+	    le32_to_cpu(notif->started)) {
+		/* We had a successful start */
+		ieee80211_ready_on_channel(mld->hw);
+	} else {
+		/* ROC was not successful, tell the firmware to remove it */
+		if (le32_to_cpu(notif->started))
+			iwl_mld_cancel_roc(mld->hw, vif);
+		else
+			iwl_mld_destroy_roc(mld, vif, mld_vif);
+		/* we need to let know mac80211 about end OR
+		 * an unsuccessful start
+		 */
+		ieee80211_remain_on_channel_expired(mld->hw);
+	}
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 9216c43a35c4d..198f942926744 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2017 Intel Deutschland GmbH
  */
@@ -771,7 +771,7 @@ static void iwl_mvm_cancel_session_protection(struct iwl_mvm *mvm,
 
 static void iwl_mvm_roc_rm_cmd(struct iwl_mvm *mvm, u32 activity)
 {
-	struct iwl_roc_req roc_cmd = {
+	struct iwl_roc_req_v5 roc_cmd = {
 		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
 		.activity = cpu_to_le32(activity),
 	};
@@ -1100,7 +1100,7 @@ int iwl_mvm_roc_add_cmd(struct iwl_mvm *mvm,
 {
 	int res;
 	u32 duration_tu, delay;
-	struct iwl_roc_req roc_req = {
+	struct iwl_roc_req_v5 roc_req = {
 		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
 		.activity = cpu_to_le32(activity),
 		.sta_id = cpu_to_le32(mvm->aux_sta.sta_id),

From 21e4d29ac0def546d57bacebe4a51cbed1209b03 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 14:55:46 +0200
Subject: [PATCH 0388/2753] wifi: iwlwifi: use correct IMR dump variable

We shouldn't dump the reg_data here which dumps the last
entry again, it should use the imr_reg_data.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.3313b18667d1.Iaa9ab66b1d397912a573525e060d39ea01b29d19@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 10bde19e9dca3..6819c615fef61 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  */
@@ -2661,7 +2661,7 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 	}
 	/* collect DRAM_IMR region in the last */
 	if (imr_reg_data.reg_tlv)
-		size += iwl_dump_ini_mem(fwrt, list, &reg_data,
+		size += iwl_dump_ini_mem(fwrt, list, &imr_reg_data,
 					 &iwl_dump_ini_region_ops[IWL_FW_INI_REGION_DRAM_IMR]);
 
 	if (size) {

From 11ccf9a76fa7764f33f884b746d17589e78a2a8e Mon Sep 17 00:00:00 2001
From: Shaul Triebitz <shaul.triebitz@intel.com>
Date: Wed, 5 Feb 2025 14:55:47 +0200
Subject: [PATCH 0389/2753] wifi: iwlwifi: add twt operation cmd

Add the firmware API.

Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.50a9f7bebe4c.I15ac1361fdab547dbf680a6fa6e88fdc5b177082@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/mac-cfg.h   | 85 ++++++++++++++++++-
 1 file changed, 84 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 232e20482e2d8..511e86ea11d44 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2019, 2021-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2019, 2021-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -61,6 +61,10 @@ enum iwl_mac_conf_subcmd_ids {
 	 * @ROC_CMD: &struct iwl_roc_req
 	 */
 	ROC_CMD = 0xE,
+	/**
+	 * @TWT_OPERATION_CMD: &struct iwl_twt_operation_cmd
+	 */
+	TWT_OPERATION_CMD = 0x10,
 	/**
 	 * @MISSED_BEACONS_NOTIF: &struct iwl_missed_beacons_notif
 	 */
@@ -748,4 +752,83 @@ struct iwl_esr_trans_fail_notif {
 	__le32 err_code;
 } __packed; /* ESR_TRANSITION_FAILED_NTFY_API_S_VER_1 */
 
+/*
+ * enum iwl_twt_operation_type: TWT operation in a TWT action frame
+ *
+ * @TWT_OPERATION_REQUEST: TWT Request
+ * @TWT_OPERATION_SUGGEST: TWT Suggest
+ * @TWT_OPERATION_DEMAND: TWT Demand
+ * @TWT_OPERATION_GROUPING: TWT Grouping
+ * @TWT_OPERATION_ACCEPT: TWT Accept
+ * @TWT_OPERATION_ALTERNATE: TWT Alternate
+ * @TWT_OPERATION_DICTATE: TWT Dictate
+ * @TWT_OPERATION_REJECT: TWT Reject
+ * @TWT_OPERATION_TEARDOWN: TWT Teardown
+ * @TWT_OPERATION_UNAVAILABILITY: TWT Unavailability
+ */
+enum iwl_twt_operation_type {
+	TWT_OPERATION_REQUEST,
+	TWT_OPERATION_SUGGEST,
+	TWT_OPERATION_DEMAND,
+	TWT_OPERATION_GROUPING,
+	TWT_OPERATION_ACCEPT,
+	TWT_OPERATION_ALTERNATE,
+	TWT_OPERATION_DICTATE,
+	TWT_OPERATION_REJECT,
+	TWT_OPERATION_TEARDOWN,
+	TWT_OPERATION_UNAVAILABILITY,
+	TWT_OPERATION_MAX,
+}; /* TWT_OPERATION_TYPE_E_VER_1 */
+
+/**
+ * struct iwl_twt_operation_cmd - initiate a TWT session from driver
+ *
+ * @link_id: FW link id to initiate the TWT
+ * @twt_operation: &enum iwl_twt_operation_type
+ * @target_wake_time: TSF time to start the TWT
+ * @interval_exponent: the exponent for the interval
+ * @interval_mantissa: the mantissa for the interval
+ * @minimum_wake_duration: the minimum duration for the wake period
+ * @trigger: is the TWT triggered or not
+ * @flow_type: is the TWT announced (0) or not (1)
+ * @flow_id: the TWT flow identifier 0 - 7
+ * @twt_protection: is the TWT protected
+ * @ndp_paging_indicator: is ndp paging indicator set
+ * @responder_pm_mode: is responder pm mode set
+ * @negotiation_type: if the responder wants to doze outside the TWT SP
+ * @twt_request: 1 for TWT request (STA), 0 for TWT response (AP)
+ * @implicit: is TWT implicit
+ * @twt_group_assignment: the TWT group assignment
+ * @twt_channel: the TWT channel
+ * @restricted_info_present: is this a restricted TWT
+ * @dl_bitmap_valid: is DL (download) bitmap valid (restricted TWT)
+ * @ul_bitmap_valid: is UL (upload) bitmap valid (restricted TWT)
+ * @dl_tid_bitmap: DL TID bitmap (restricted TWT)
+ * @ul_tid_bitmap: UL TID bitmap (restricted TWT)
+ */
+struct iwl_twt_operation_cmd {
+	__le32 link_id;
+	__le32 twt_operation;
+	__le64 target_wake_time;
+	__le32 interval_exponent;
+	__le32 interval_mantissa;
+	__le32 minimum_wake_duration;
+	u8 trigger;
+	u8 flow_type;
+	u8 flow_id;
+	u8 twt_protection;
+	u8 ndp_paging_indicator;
+	u8 responder_pm_mode;
+	u8 negotiation_type;
+	u8 twt_request;
+	u8 implicit;
+	u8 twt_group_assignment;
+	u8 twt_channel;
+	u8 restricted_info_present;
+	u8 dl_bitmap_valid;
+	u8 ul_bitmap_valid;
+	u8 dl_tid_bitmap;
+	u8 ul_tid_bitmap;
+} __packed; /* TWT_OPERATION_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_mac_cfg_h__ */

From 85ccbdc4d3930f2a6e22d6ba7d42aad241176d09 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 5 Feb 2025 14:55:48 +0200
Subject: [PATCH 0390/2753] wifi: iwlwifi: implement dump region split

Due to hardware design constraints, a reset handshake may be
necessary even when the firmware has already crashed, with
the dump descriptions indicating which parts should be done
before/after the handshake, if needed. Implement that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250205145347.9296e3113d42.Ifb32703fd06a644d08a86b7af1b990738e3c8134@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/dbg-tlv.h   |  9 +-
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c   | 99 ++++++++++++++-----
 .../net/wireless/intel/iwlwifi/iwl-trans.h    |  1 +
 .../wireless/intel/iwlwifi/pcie/trans-gen2.c  |  4 +-
 4 files changed, 85 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
index 550de6db18340..4fab6c66994e5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dbg-tlv.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #ifndef __iwl_fw_dbg_tlv_h__
 #define __iwl_fw_dbg_tlv_h__
@@ -527,6 +527,8 @@ enum iwl_fw_ini_time_point {
  * @IWL_FW_INI_APPLY_POLICY_OVERRIDE_DATA: override trigger data.
  *	Append otherwise
  * @IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD: send cmd once dump collected
+ * @IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE: perform reset handshake and
+ *	split dump to before/after with region marking
  */
 enum iwl_fw_ini_trigger_apply_policy {
 	IWL_FW_INI_APPLY_POLICY_MATCH_TIME_POINT	= BIT(0),
@@ -535,6 +537,7 @@ enum iwl_fw_ini_trigger_apply_policy {
 	IWL_FW_INI_APPLY_POLICY_OVERRIDE_CFG		= BIT(9),
 	IWL_FW_INI_APPLY_POLICY_OVERRIDE_DATA		= BIT(10),
 	IWL_FW_INI_APPLY_POLICY_DUMP_COMPLETE_CMD	= BIT(16),
+	IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE		= BIT(17),
 };
 
 /**
@@ -556,12 +559,14 @@ enum iwl_fw_ini_trigger_reset_fw_policy {
  * @IWL_FW_INI_DEBUG_DUMP_POLICY_NO_LIMIT: OS has no limit of dump size
  * @IWL_FW_INI_DEBUG_DUMP_POLICY_MAX_LIMIT_600KB: mini dump only 600KB region dump
  * @IWL_FW_IWL_DEBUG_DUMP_POLICY_MAX_LIMIT_5MB: mini dump 5MB size dump
+ * @IWL_FW_IWL_DEBUG_DUMP_POLICY_BEFORE_RESET: dump this region before reset
+ *	handshake (if requested by %IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE)
  */
 enum iwl_fw_ini_dump_policy {
 	IWL_FW_INI_DEBUG_DUMP_POLICY_NO_LIMIT           = BIT(0),
 	IWL_FW_INI_DEBUG_DUMP_POLICY_MAX_LIMIT_600KB    = BIT(1),
 	IWL_FW_IWL_DEBUG_DUMP_POLICY_MAX_LIMIT_5MB      = BIT(2),
-
+	IWL_FW_IWL_DEBUG_DUMP_POLICY_BEFORE_RESET	= BIT(3),
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index 6819c615fef61..634e2543ba6dd 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -2588,29 +2588,28 @@ static const struct iwl_dump_ini_mem_ops iwl_dump_ini_region_ops[] = {
 	},
 };
 
-static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
-				struct iwl_fwrt_dump_data *dump_data,
-				struct list_head *list)
+enum iwl_dump_ini_region_selector {
+	IWL_INI_DUMP_ALL_REGIONS,
+	IWL_INI_DUMP_EARLY_REGIONS,
+	IWL_INI_DUMP_LATE_REGIONS,
+};
+
+static u32
+iwl_dump_ini_dump_regions(struct iwl_fw_runtime *fwrt,
+			  struct iwl_fwrt_dump_data *dump_data,
+			  struct list_head *list,
+			  enum iwl_fw_ini_time_point tp_id,
+			  u64 regions_mask,
+			  struct iwl_dump_ini_region_data *imr_reg_data,
+			  enum iwl_dump_ini_region_selector which)
 {
-	struct iwl_fw_ini_trigger_tlv *trigger = dump_data->trig;
-	enum iwl_fw_ini_time_point tp_id = le32_to_cpu(trigger->time_point);
-	struct iwl_dump_ini_region_data reg_data = {
-		.dump_data = dump_data,
-	};
-	struct iwl_dump_ini_region_data imr_reg_data = {
-		.dump_data = dump_data,
-	};
-	int i;
 	u32 size = 0;
-	u64 regions_mask = le64_to_cpu(trigger->regions_mask) &
-			   ~(fwrt->trans->dbg.unsupported_region_msk);
 
-	BUILD_BUG_ON(sizeof(trigger->regions_mask) != sizeof(regions_mask));
-	BUILD_BUG_ON((sizeof(trigger->regions_mask) * BITS_PER_BYTE) <
-		     ARRAY_SIZE(fwrt->trans->dbg.active_regions));
-
-	for (i = 0; i < ARRAY_SIZE(fwrt->trans->dbg.active_regions); i++) {
-		u32 reg_type;
+	for (int i = 0; i < ARRAY_SIZE(fwrt->trans->dbg.active_regions); i++) {
+		struct iwl_dump_ini_region_data reg_data = {
+			.dump_data = dump_data,
+		};
+		u32 reg_type, dp;
 		struct iwl_fw_ini_region_tlv *reg;
 
 		if (!(BIT_ULL(i) & regions_mask))
@@ -2628,6 +2627,8 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 		if (reg_type >= ARRAY_SIZE(iwl_dump_ini_region_ops))
 			continue;
 
+		dp = le32_get_bits(reg->id, IWL_FW_INI_REGION_DUMP_POLICY_MASK);
+
 		if ((reg_type == IWL_FW_INI_REGION_PERIPHERY_PHY ||
 		     reg_type == IWL_FW_INI_REGION_PERIPHERY_PHY_RANGE ||
 		     reg_type == IWL_FW_INI_REGION_PERIPHERY_SNPS_DPHYIP) &&
@@ -2637,6 +2638,20 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 				 tp_id);
 			continue;
 		}
+
+		switch (which) {
+		case IWL_INI_DUMP_ALL_REGIONS:
+			break;
+		case IWL_INI_DUMP_EARLY_REGIONS:
+			if (!(dp & IWL_FW_IWL_DEBUG_DUMP_POLICY_BEFORE_RESET))
+				continue;
+			break;
+		case IWL_INI_DUMP_LATE_REGIONS:
+			if (dp & IWL_FW_IWL_DEBUG_DUMP_POLICY_BEFORE_RESET)
+				continue;
+			break;
+		}
+
 		/*
 		 * DRAM_IMR can be collected only for FW/HW error timepoint
 		 * when fw is not alive. In addition, it must be collected
@@ -2646,7 +2661,8 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 		if (reg_type == IWL_FW_INI_REGION_DRAM_IMR) {
 			if (tp_id == IWL_FW_INI_TIME_POINT_FW_ASSERT ||
 			    tp_id == IWL_FW_INI_TIME_POINT_FW_HW_ERROR)
-				imr_reg_data.reg_tlv = fwrt->trans->dbg.active_regions[i];
+				imr_reg_data->reg_tlv =
+					fwrt->trans->dbg.active_regions[i];
 			else
 				IWL_INFO(fwrt,
 					 "WRT: trying to collect DRAM_IMR at time point: %d, skipping\n",
@@ -2659,6 +2675,41 @@ static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
 		size += iwl_dump_ini_mem(fwrt, list, &reg_data,
 					 &iwl_dump_ini_region_ops[reg_type]);
 	}
+
+	return size;
+}
+
+static u32 iwl_dump_ini_trigger(struct iwl_fw_runtime *fwrt,
+				struct iwl_fwrt_dump_data *dump_data,
+				struct list_head *list)
+{
+	struct iwl_fw_ini_trigger_tlv *trigger = dump_data->trig;
+	enum iwl_fw_ini_time_point tp_id = le32_to_cpu(trigger->time_point);
+	struct iwl_dump_ini_region_data imr_reg_data = {
+		.dump_data = dump_data,
+	};
+	u32 size = 0;
+	u64 regions_mask = le64_to_cpu(trigger->regions_mask) &
+			   ~(fwrt->trans->dbg.unsupported_region_msk);
+
+	BUILD_BUG_ON(sizeof(trigger->regions_mask) != sizeof(regions_mask));
+	BUILD_BUG_ON((sizeof(trigger->regions_mask) * BITS_PER_BYTE) <
+		     ARRAY_SIZE(fwrt->trans->dbg.active_regions));
+
+	if (trigger->time_point &
+			cpu_to_le32(IWL_FW_INI_APPLY_POLICY_RESET_HANDSHAKE)) {
+		size += iwl_dump_ini_dump_regions(fwrt, dump_data, list, tp_id,
+						  regions_mask, &imr_reg_data,
+						  IWL_INI_DUMP_EARLY_REGIONS);
+		iwl_trans_pcie_fw_reset_handshake(fwrt->trans);
+		size += iwl_dump_ini_dump_regions(fwrt, dump_data, list, tp_id,
+						  regions_mask, &imr_reg_data,
+						  IWL_INI_DUMP_LATE_REGIONS);
+	} else {
+		size += iwl_dump_ini_dump_regions(fwrt, dump_data, list, tp_id,
+						  regions_mask, &imr_reg_data,
+						  IWL_INI_DUMP_ALL_REGIONS);
+	}
 	/* collect DRAM_IMR region in the last */
 	if (imr_reg_data.reg_tlv)
 		size += iwl_dump_ini_mem(fwrt, list, &imr_reg_data,
@@ -3071,6 +3122,7 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx)
 	struct iwl_fw_dbg_params params = {0};
 	struct iwl_fwrt_dump_data *dump_data =
 		&fwrt->dump.wks[wk_idx].dump_data;
+
 	if (!test_bit(wk_idx, &fwrt->dump.active_wks))
 		return;
 
@@ -3095,9 +3147,9 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx)
 
 	IWL_DEBUG_FW_INFO(fwrt, "WRT: Data collection start\n");
 	if (iwl_trans_dbg_ini_valid(fwrt->trans))
-		iwl_fw_error_ini_dump(fwrt, &fwrt->dump.wks[wk_idx].dump_data);
+		iwl_fw_error_ini_dump(fwrt, dump_data);
 	else
-		iwl_fw_error_dump(fwrt, &fwrt->dump.wks[wk_idx].dump_data);
+		iwl_fw_error_dump(fwrt, dump_data);
 	IWL_DEBUG_FW_INFO(fwrt, "WRT: Data collection done\n");
 
 	iwl_fw_dbg_stop_restart_recording(fwrt, &params, false);
@@ -3114,7 +3166,6 @@ static void iwl_fw_dbg_collect_sync(struct iwl_fw_runtime *fwrt, u8 wk_idx)
 
 	if (fwrt->trans->dbg.last_tp_resetfw == IWL_FW_INI_RESET_FW_MODE_STOP_FW_ONLY)
 		iwl_force_nmi(fwrt->trans);
-
 out:
 	if (iwl_trans_dbg_ini_valid(fwrt->trans)) {
 		iwl_fw_error_dump_data_free(dump_data);
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 3561ff8483f20..021691513a576 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -1262,6 +1262,7 @@ enum iwl_reset_mode {
 };
 
 void iwl_trans_pcie_reset(struct iwl_trans *trans, enum iwl_reset_mode mode);
+void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans);
 
 int iwl_trans_pcie_send_hcmd(struct iwl_trans *trans,
 			     struct iwl_host_cmd *cmd);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
index 793514a1852a3..3ece34e30d580 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans-gen2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include "iwl-trans.h"
 #include "iwl-prph.h"
@@ -95,7 +95,7 @@ static void iwl_pcie_gen2_apm_stop(struct iwl_trans *trans, bool op_mode_leave)
 			      CSR_GP_CNTRL_REG_FLAG_INIT_DONE);
 }
 
-static void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
+void iwl_trans_pcie_fw_reset_handshake(struct iwl_trans *trans)
 {
 	struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);
 	int ret;

From 49f27f29446a5bfe633dd2cc0cfebd48a1a5e77f Mon Sep 17 00:00:00 2001
From: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Date: Fri, 31 Jan 2025 20:26:55 +0500
Subject: [PATCH 0391/2753] wifi: nl80211: reject cooked mode if it is set
 along with other flags

It is possible to set both MONITOR_FLAG_COOK_FRAMES and MONITOR_FLAG_ACTIVE
flags simultaneously on the same monitor interface from the userspace. This
causes a sub-interface to be created with no IEEE80211_SDATA_IN_DRIVER bit
set because the monitor interface is in the cooked state and it takes
precedence over all other states. When the interface is then being deleted
the kernel calls WARN_ONCE() from check_sdata_in_driver() because of missing
that bit.

Fix this by rejecting MONITOR_FLAG_COOK_FRAMES if it is set along with
other flags.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 66f7ac50ed7c ("nl80211: Add monitor interface configuration flags")
Cc: stable@vger.kernel.org
Reported-by: syzbot+2e5c1e55b9e5c28a3da7@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=2e5c1e55b9e5c28a3da7
Signed-off-by: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Link: https://patch.msgid.link/20250131152657.5606-1-v.shevtsov@mt-integration.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index d7d3da0f6833d..fdb2aac951d18 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4220,6 +4220,11 @@ static int parse_monitor_flags(struct nlattr *nla, u32 *mntrflags)
 		if (flags[flag])
 			*mntrflags |= (1<<flag);
 
+	/* cooked monitor mode is incompatible with other modes */
+	if (*mntrflags & MONITOR_FLAG_COOK_FRAMES &&
+	    *mntrflags != MONITOR_FLAG_COOK_FRAMES)
+		return -EOPNOTSUPP;
+
 	*mntrflags |= MONITOR_FLAG_CHANGED;
 
 	return 0;

From 5b999006e35ea9c11116ddff7e375b256421d0af Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 13:31:29 +0100
Subject: [PATCH 0392/2753] wifi: mac80211: Cleanup sta TXQs on flush

Drop the sta TXQs on flush when the drivers is not supporting
flush.

ieee80211_set_disassoc() tries to clean up everything for the sta.
But it ignored queued frames in the sta TX queues when the driver
isn't supporting the flush driver ops.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204123129.9162-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index f6b631faf4f7f..7f02bd5891eb9 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -687,7 +687,7 @@ void __ieee80211_flush_queues(struct ieee80211_local *local,
 			      struct ieee80211_sub_if_data *sdata,
 			      unsigned int queues, bool drop)
 {
-	if (!local->ops->flush)
+	if (!local->ops->flush && !drop)
 		return;
 
 	/*
@@ -714,7 +714,8 @@ void __ieee80211_flush_queues(struct ieee80211_local *local,
 		}
 	}
 
-	drv_flush(local, sdata, queues, drop);
+	if (local->ops->flush)
+		drv_flush(local, sdata, queues, drop);
 
 	ieee80211_wake_queues_by_reason(&local->hw, queues,
 					IEEE80211_QUEUE_STOP_REASON_FLUSH,

From 646262c71aca87bb66945933abe4e620796d6c5a Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Tue, 4 Feb 2025 17:42:40 +0100
Subject: [PATCH 0393/2753] wifi: mac80211: remove debugfs dir for virtual
 monitor

Don't call ieee80211_debugfs_recreate_netdev() for virtual monitor
interface when deleting it.

The virtual monitor interface shouldn't have debugfs entries and trying
to update them will *create* them on deletion.

And when the virtual monitor interface is created/destroyed multiple
times we'll get warnings about debugfs name conflicts.

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Link: https://patch.msgid.link/20250204164240.370153-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.c | 10 ++++++++--
 net/mac80211/iface.c      | 11 ++++++-----
 2 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 299d38e9e8630..2fc60e1e77a55 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -116,8 +116,14 @@ void drv_remove_interface(struct ieee80211_local *local,
 
 	sdata->flags &= ~IEEE80211_SDATA_IN_DRIVER;
 
-	/* Remove driver debugfs entries */
-	ieee80211_debugfs_recreate_netdev(sdata, sdata->vif.valid_links);
+	/*
+	 * Remove driver debugfs entries.
+	 * The virtual monitor interface doesn't get a debugfs
+	 * entry, so it's exempt here.
+	 */
+	if (sdata != local->monitor_sdata)
+		ieee80211_debugfs_recreate_netdev(sdata,
+						  sdata->vif.valid_links);
 
 	trace_drv_remove_interface(local, sdata);
 	local->ops->remove_interface(&local->hw, &sdata->vif);
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index 0ea7e77860b73..738de269e13f0 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -1206,16 +1206,17 @@ void ieee80211_del_virtual_monitor(struct ieee80211_local *local)
 		return;
 	}
 
-	RCU_INIT_POINTER(local->monitor_sdata, NULL);
-	mutex_unlock(&local->iflist_mtx);
-
-	synchronize_net();
-
+	clear_bit(SDATA_STATE_RUNNING, &sdata->state);
 	ieee80211_link_release_channel(&sdata->deflink);
 
 	if (ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
 		drv_remove_interface(local, sdata);
 
+	RCU_INIT_POINTER(local->monitor_sdata, NULL);
+	mutex_unlock(&local->iflist_mtx);
+
+	synchronize_net();
+
 	kfree(sdata);
 }
 

From 7774e3920029398ad49dc848b23840593f14d515 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:45 +0200
Subject: [PATCH 0394/2753] wifi: iwlwifi: fw: allocate chained SG tables for
 dump

The firmware dumps can be pretty big, and since we use single
pages for each SG table entry, even the table itself may end
up being an order-5 allocation. Build chained tables so that
we need not allocate a higher-order table here.

This could be improved and cleaned up, e.g. by using the SG
pool code or simply kvmalloc(), but all of that would require
also updating the devcoredump first since that frees it all,
so we need to be more careful. SG pool might also run against
the CONFIG_ARCH_NO_SG_CHAIN limitation, which is irrelevant
here.

Also use _devcd_free_sgtable() for the error paths now, much
simpler especially since it's in two places now.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.697c7a465ac9.Iea982df46b5c075bfb77ade36f187d99a70c63db@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dbg.c | 86 ++++++++++++++-------
 1 file changed, 58 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
index fb2ea38e89aca..6594216f873c4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
@@ -558,41 +558,71 @@ static void iwl_dump_prph(struct iwl_fw_runtime *fwrt,
 }
 
 /*
- * alloc_sgtable - allocates scallerlist table in the given size,
- * fills it with pages and returns it
+ * alloc_sgtable - allocates (chained) scatterlist in the given size,
+ *	fills it with pages and returns it
  * @size: the size (in bytes) of the table
-*/
-static struct scatterlist *alloc_sgtable(int size)
+ */
+static struct scatterlist *alloc_sgtable(ssize_t size)
 {
-	int alloc_size, nents, i;
-	struct page *new_page;
-	struct scatterlist *iter;
-	struct scatterlist *table;
+	struct scatterlist *result = NULL, *prev;
+	int nents, i, n_prev;
 
 	nents = DIV_ROUND_UP(size, PAGE_SIZE);
-	table = kcalloc(nents, sizeof(*table), GFP_KERNEL);
-	if (!table)
-		return NULL;
-	sg_init_table(table, nents);
-	iter = table;
-	for_each_sg(table, iter, sg_nents(table), i) {
-		new_page = alloc_page(GFP_KERNEL);
-		if (!new_page) {
-			/* release all previous allocated pages in the table */
-			iter = table;
-			for_each_sg(table, iter, sg_nents(table), i) {
-				new_page = sg_page(iter);
-				if (new_page)
-					__free_page(new_page);
-			}
-			kfree(table);
+
+#define N_ENTRIES_PER_PAGE (PAGE_SIZE / sizeof(*result))
+	/*
+	 * We need an additional entry for table chaining,
+	 * this ensures the loop can finish i.e. we can
+	 * fit at least two entries per page (obviously,
+	 * many more really fit.)
+	 */
+	BUILD_BUG_ON(N_ENTRIES_PER_PAGE < 2);
+
+	while (nents > 0) {
+		struct scatterlist *new, *iter;
+		int n_fill, n_alloc;
+
+		if (nents <= N_ENTRIES_PER_PAGE) {
+			/* last needed table */
+			n_fill = nents;
+			n_alloc = nents;
+			nents = 0;
+		} else {
+			/* fill a page with entries */
+			n_alloc = N_ENTRIES_PER_PAGE;
+			/* reserve one for chaining */
+			n_fill = n_alloc - 1;
+			nents -= n_fill;
+		}
+
+		new = kcalloc(n_alloc, sizeof(*new), GFP_KERNEL);
+		if (!new) {
+			if (result)
+				_devcd_free_sgtable(result);
 			return NULL;
 		}
-		alloc_size = min_t(int, size, PAGE_SIZE);
-		size -= PAGE_SIZE;
-		sg_set_page(iter, new_page, alloc_size, 0);
+		sg_init_table(new, n_alloc);
+
+		if (!result)
+			result = new;
+		else
+			sg_chain(prev, n_prev, new);
+		prev = new;
+		n_prev = n_alloc;
+
+		for_each_sg(new, iter, n_fill, i) {
+			struct page *new_page = alloc_page(GFP_KERNEL);
+
+			if (!new_page) {
+				_devcd_free_sgtable(result);
+				return NULL;
+			}
+
+			sg_set_page(iter, new_page, PAGE_SIZE, 0);
+		}
 	}
-	return table;
+
+	return result;
 }
 
 static void iwl_fw_get_prph_len(struct iwl_fw_runtime *fwrt,

From 3f8aa0b8a53df2247a84eaf3b3aa38b6ef86cb1c Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Feb 2025 14:34:46 +0200
Subject: [PATCH 0395/2753] wifi: iwlwifi: fw: avoid using an uninitialized
 variable

iwl_fwrt_read_err_table can return true also when it failed to read
the memory. In this case, err_id argument is not initialized,
but the callers are still using it.

Simply initialize it to 0. If the error table was read successfully it'll
be overridden.

Fixes: 43e0b2ada519 ("wifi: iwlwifi: fw: add an error table status getter")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250209143303.37cdbba4eb56.I95fe9bd95303b8179f946766558a9f15f4fe254c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/dump.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dump.c b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
index 8e0c85a1240d7..c7b261c8ec969 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/dump.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dump.c
@@ -540,6 +540,9 @@ bool iwl_fwrt_read_err_table(struct iwl_trans *trans, u32 base, u32 *err_id)
 	} err_info = {};
 	int ret;
 
+	if (err_id)
+		*err_id = 0;
+
 	if (!base)
 		return false;
 

From f9751163bffd3fe60794929829f810968c6de73d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:47 +0200
Subject: [PATCH 0396/2753] wifi: iwlwifi: mvm: clean up ROC on failure

If the firmware fails to start the session protection, then we
do call iwl_mvm_roc_finished() here, but that won't do anything
at all because IWL_MVM_STATUS_ROC_P2P_RUNNING was never set.
Set IWL_MVM_STATUS_ROC_P2P_RUNNING in the failure/stop path.
If it started successfully before, it's already set, so that
doesn't matter, and if it didn't start it needs to be set to
clean up.

Not doing so will lead to a WARN_ON() later on a fresh remain-
on-channel, since the link is already active when activated as
it was never deactivated.

Fixes: 35c1bbd93c4e ("wifi: iwlwifi: mvm: remove IWL_MVM_STATUS_NEED_FLUSH_P2P")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.0fe36c291068.I67f5dac742170dd937f11e4d4f937f45f71b7cb4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/time-event.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
index 9216c43a35c4d..ebfa88b38b71b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
@@ -1030,6 +1030,8 @@ void iwl_mvm_rx_session_protect_notif(struct iwl_mvm *mvm,
 		/* End TE, notify mac80211 */
 		mvmvif->time_event_data.id = SESSION_PROTECT_CONF_MAX_ID;
 		mvmvif->time_event_data.link_id = -1;
+		/* set the bit so the ROC cleanup will actually clean up */
+		set_bit(IWL_MVM_STATUS_ROC_P2P_RUNNING, &mvm->status);
 		iwl_mvm_roc_finished(mvm);
 		ieee80211_remain_on_channel_expired(mvm->hw);
 	} else if (le32_to_cpu(notif->start)) {

From d48ff3ce92259bae7e77732c7cfd7cbc7992c021 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:48 +0200
Subject: [PATCH 0397/2753] wifi: iwlwifi: mvm: don't dump the firmware state
 upon RFKILL while suspend

This is not really a firmware error. We need to reload the firmware, but
this doesn't mean that we should consider this as a firmware error.
When the firmware was restarted upon resume, this wasn't felt by the
driver. Now that we keep the firmware running during suspend even if we
don't have wowlan, this started to pop-up.

Fixes: e8bb19c1d590 ("wifi: iwlwifi: support fast resume")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.a10463a40318.I14131781c3124b58e60e1f5e9d793a2bc88b464c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c | 77 ++++++++++++++-------
 1 file changed, 51 insertions(+), 26 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 129b6bdf9ef90..82ca7f8b1bb27 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -3092,8 +3092,14 @@ static void iwl_mvm_d3_disconnect_iter(void *data, u8 *mac,
 		ieee80211_resume_disconnect(vif);
 }
 
-static bool iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
-				   struct ieee80211_vif *vif)
+enum rt_status {
+	FW_ALIVE,
+	FW_NEEDS_RESET,
+	FW_ERROR,
+};
+
+static enum rt_status iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
+					      struct ieee80211_vif *vif)
 {
 	u32 err_id;
 
@@ -3101,29 +3107,35 @@ static bool iwl_mvm_check_rt_status(struct iwl_mvm *mvm,
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.lmac_error_event_table[0],
 				    &err_id)) {
-		if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN && vif) {
-			struct cfg80211_wowlan_wakeup wakeup = {
-				.rfkill_release = true,
-			};
-			ieee80211_report_wowlan_wakeup(vif, &wakeup,
-						       GFP_KERNEL);
+		if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN) {
+			IWL_WARN(mvm, "Rfkill was toggled during suspend\n");
+			if (vif) {
+				struct cfg80211_wowlan_wakeup wakeup = {
+					.rfkill_release = true,
+				};
+
+				ieee80211_report_wowlan_wakeup(vif, &wakeup,
+							       GFP_KERNEL);
+			}
+
+			return FW_NEEDS_RESET;
 		}
-		return true;
+		return FW_ERROR;
 	}
 
 	/* check if we have lmac2 set and check for error */
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.lmac_error_event_table[1],
 				    NULL))
-		return true;
+		return FW_ERROR;
 
 	/* check for umac error */
 	if (iwl_fwrt_read_err_table(mvm->trans,
 				    mvm->trans->dbg.umac_error_event_table,
 				    NULL))
-		return true;
+		return FW_ERROR;
 
-	return false;
+	return FW_ALIVE;
 }
 
 /*
@@ -3492,6 +3504,7 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 	bool d0i3_first = fw_has_capa(&mvm->fw->ucode_capa,
 				      IWL_UCODE_TLV_CAPA_D0I3_END_FIRST);
 	bool resume_notif_based = iwl_mvm_d3_resume_notif_based(mvm);
+	enum rt_status rt_status;
 	bool keep = false;
 
 	mutex_lock(&mvm->mutex);
@@ -3515,14 +3528,19 @@ static int __iwl_mvm_resume(struct iwl_mvm *mvm, bool test)
 
 	iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt);
 
-	if (iwl_mvm_check_rt_status(mvm, vif)) {
-		IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+	rt_status = iwl_mvm_check_rt_status(mvm, vif);
+	if (rt_status != FW_ALIVE) {
 		set_bit(STATUS_FW_ERROR, &mvm->trans->status);
-		iwl_mvm_dump_nic_error_log(mvm);
-		iwl_dbg_tlv_time_point(&mvm->fwrt,
-				       IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL);
-		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					false, 0);
+		if (rt_status == FW_ERROR) {
+			IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+			iwl_mvm_dump_nic_error_log(mvm);
+			iwl_dbg_tlv_time_point(&mvm->fwrt,
+					       IWL_FW_INI_TIME_POINT_FW_ASSERT,
+					       NULL);
+			iwl_fw_dbg_collect_desc(&mvm->fwrt,
+						&iwl_dump_desc_assert,
+						false, 0);
+		}
 		ret = 1;
 		goto err;
 	}
@@ -3679,6 +3697,7 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm)
 		.notif_expected =
 			IWL_D3_NOTIF_D3_END_NOTIF,
 	};
+	enum rt_status rt_status;
 	int ret;
 
 	lockdep_assert_held(&mvm->mutex);
@@ -3688,14 +3707,20 @@ int iwl_mvm_fast_resume(struct iwl_mvm *mvm)
 	mvm->last_reset_or_resume_time_jiffies = jiffies;
 	iwl_fw_dbg_read_d3_debug_data(&mvm->fwrt);
 
-	if (iwl_mvm_check_rt_status(mvm, NULL)) {
-		IWL_ERR(mvm, "FW Error occurred during suspend. Restarting.\n");
+	rt_status = iwl_mvm_check_rt_status(mvm, NULL);
+	if (rt_status != FW_ALIVE) {
 		set_bit(STATUS_FW_ERROR, &mvm->trans->status);
-		iwl_mvm_dump_nic_error_log(mvm);
-		iwl_dbg_tlv_time_point(&mvm->fwrt,
-				       IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL);
-		iwl_fw_dbg_collect_desc(&mvm->fwrt, &iwl_dump_desc_assert,
-					false, 0);
+		if (rt_status == FW_ERROR) {
+			IWL_ERR(mvm,
+				"iwl_mvm_check_rt_status failed, device is gone during suspend\n");
+			iwl_mvm_dump_nic_error_log(mvm);
+			iwl_dbg_tlv_time_point(&mvm->fwrt,
+					       IWL_FW_INI_TIME_POINT_FW_ASSERT,
+					       NULL);
+			iwl_fw_dbg_collect_desc(&mvm->fwrt,
+						&iwl_dump_desc_assert,
+						false, 0);
+		}
 		mvm->trans->state = IWL_TRANS_NO_FW;
 		ret = -ENODEV;
 

From d73d2c6e3313f0ba60711ab4f4b9044eddca9ca5 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:49 +0200
Subject: [PATCH 0398/2753] wifi: iwlwifi: mvm: don't try to talk to a dead
 firmware

This fixes:

 bad state = 0
 WARNING: CPU: 10 PID: 702 at drivers/net/wireless/inel/iwlwifi/iwl-trans.c:178 iwl_trans_send_cmd+0xba/0xe0 [iwlwifi]
 Call Trace:
  <TASK>
  ? __warn+0xca/0x1c0
  ? iwl_trans_send_cmd+0xba/0xe0 [iwlwifi 64fa9ad799a0e0d2ba53d4af93a53ad9a531f8d4]
  iwl_fw_dbg_clear_monitor_buf+0xd7/0x110 [iwlwifi 64fa9ad799a0e0d2ba53d4af93a53ad9a531f8d4]
  _iwl_dbgfs_fw_dbg_clear_write+0xe2/0x120 [iwlmvm 0e8adb18cea92d2c341766bcc10b18699290068a]

Ask whether the firmware is alive before sending a command.

Fixes: 268712dc3b34 ("wifi: iwlwifi: mvm: add a debugfs hook to clear the monitor data")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.8e1597b62c70.I12ea71dd9b805b095c9fc12a10c9f34a4e801b61@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 83e3c11603622..55d035b896e91 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1479,6 +1479,13 @@ static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mvm *mvm,
 	if (mvm->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_9000)
 		return -EOPNOTSUPP;
 
+	/*
+	 * If the firmware is not running, silently succeed since there is
+	 * no data to clear.
+	 */
+	if (!iwl_mvm_firmware_running(mvm))
+		return count;
+
 	mutex_lock(&mvm->mutex);
 	iwl_fw_dbg_clear_monitor_buf(&mvm->fwrt);
 	mutex_unlock(&mvm->mutex);

From a03e2082e678ea10d0d8bdf3ed933eb05a8ddbb0 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sun, 9 Feb 2025 14:34:50 +0200
Subject: [PATCH 0399/2753] wifi: iwlwifi: mvm: use the right version of the
 rate API

The firmware uses the newer version of the API in recent devices. For
older devices, we translate the rate to the new format.
Don't parse the rate with old parsing macros.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.13d70cdcbb4e.Ic92193bce4013b70a823cfef250ee79c16cf7c17@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
index 09fd8752046ee..14ea89f931bbf 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rxmq.c
@@ -995,7 +995,7 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 	 */
 	u8 ru = le32_get_bits(phy_data->d1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK);
 	u32 rate_n_flags = phy_data->rate_n_flags;
-	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK_V1;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
 	u8 offs = 0;
 
 	rx_status->bw = RATE_INFO_BW_HE_RU;
@@ -1050,13 +1050,13 @@ iwl_mvm_decode_he_phy_ru_alloc(struct iwl_mvm_rx_phy_data *phy_data,
 
 	if (he_mu)
 		he_mu->flags2 |=
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW);
-	else if (he_type == RATE_MCS_HE_TYPE_TRIG_V1)
+	else if (he_type == RATE_MCS_HE_TYPE_TRIG)
 		he->data6 |=
 			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) |
-			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK_V1,
+			le16_encode_bits(FIELD_GET(RATE_MCS_CHAN_WIDTH_MSK,
 						   rate_n_flags),
 					 IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW);
 }

From e0dc2c1bef722cbf16ae557690861e5f91208129 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Feb 2025 14:34:51 +0200
Subject: [PATCH 0400/2753] wifi: iwlwifi: limit printed string from FW file

There's no guarantee here that the file is always with a
NUL-termination, so reading the string may read beyond the
end of the TLV. If that's the last TLV in the file, it can
perhaps even read beyond the end of the file buffer.

Fix that by limiting the print format to the size of the
buffer we have.

Fixes: aee1b6385e29 ("iwlwifi: support fseq tlv and print fseq version")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.cb5f9d0c2f5d.Idec695d53c6c2234aade306f7647b576c7e3d928@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index d3a65f33097cb..352b6e73e08f3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1181,7 +1181,7 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 
 			if (tlv_len != sizeof(*fseq_ver))
 				goto invalid_tlv_len;
-			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %s\n",
+			IWL_INFO(drv, "TLV_FW_FSEQ_VERSION: %.32s\n",
 				 fseq_ver->version);
 			}
 			break;

From 3b08e608d50c44ca1135beed179f266aa0461da7 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 9 Feb 2025 14:34:52 +0200
Subject: [PATCH 0401/2753] wifi: iwlwifi: Free pages allocated when failing to
 build A-MSDU

When failing to prepare the data needed for A-MSDU transmission, the memory
allocated for the TSO management was not freed. Fix it.

Fixes: 7f5e3038f029 ("wifi: iwlwifi: map entire SKB when sending AMSDUs")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.bc27fad9b3d5.Ibf43dd18fb652b1a59061204e081f11c9fa34a3f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index 1f483f15c2383..dce5096db82b6 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -347,6 +347,7 @@ iwl_tfh_tfd *iwl_txq_gen2_build_tx_amsdu(struct iwl_trans *trans,
 	return tfd;
 
 out_err:
+	iwl_pcie_free_tso_pages(trans, skb, out_meta);
 	iwl_txq_gen2_tfd_unmap(trans, out_meta, tfd);
 	return NULL;
 }

From 3640dbc1f75ce15d128ea4af44226960d894f3fd Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 9 Feb 2025 14:34:53 +0200
Subject: [PATCH 0402/2753] wifi: iwlwifi: Fix A-MSDU TSO preparation

The TSO preparation assumed that the skb head contained the headers
while the rest of the data was in the fragments. Since this is not
always true, e.g., it is possible that the data was linearised, modify
the TSO preparation to start the data processing after the network
headers.

Fixes: 7f5e3038f029 ("wifi: iwlwifi: map entire SKB when sending AMSDUs")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250209143303.75769a4769bf.Iaf79e8538093cdf8c446c292cc96164ad6498f61@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/pcie/internal.h    |  5 +++--
 .../net/wireless/intel/iwlwifi/pcie/tx-gen2.c |  5 +++--
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c  | 20 +++++++++++--------
 3 files changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
index 856b7e9f717d5..45460f93d24ad 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/internal.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2003-2015, 2018-2024 Intel Corporation
+ * Copyright (C) 2003-2015, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -646,7 +646,8 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
 				    unsigned int len);
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room);
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset);
 
 void iwl_pcie_free_tso_pages(struct iwl_trans *trans, struct sk_buff *skb,
 			     struct iwl_cmd_meta *cmd_meta);
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
index dce5096db82b6..401919f9fe88e 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx-gen2.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2020, 2023-2024 Intel Corporation
+ * Copyright (C) 2018-2020, 2023-2025 Intel Corporation
  */
 #include <net/tso.h>
 #include <linux/tcp.h>
@@ -188,7 +188,8 @@ static int iwl_txq_gen2_build_amsdu(struct iwl_trans *trans,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr));
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len);
 	if (!sgt)
 		return -ENOMEM;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 334ebd4c12fa7..7b6071a59b694 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2003-2014, 2018-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2003-2014, 2018-2021, 2023-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1855,6 +1855,7 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  * @cmd_meta: command meta to store the scatter list information for unmapping
  * @hdr: output argument for TSO headers
  * @hdr_room: requested length for TSO headers
+ * @offset: offset into the data from which mapping should start
  *
  * Allocate space for a scatter gather list and TSO headers and map the SKB
  * using the scatter gather list. The SKB is unmapped again when the page is
@@ -1864,18 +1865,20 @@ dma_addr_t iwl_pcie_get_sgt_tb_phys(struct sg_table *sgt, unsigned int offset,
  */
 struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   struct iwl_cmd_meta *cmd_meta,
-				   u8 **hdr, unsigned int hdr_room)
+				   u8 **hdr, unsigned int hdr_room,
+				   unsigned int offset)
 {
 	struct sg_table *sgt;
+	unsigned int n_segments;
 
 	if (WARN_ON_ONCE(skb_has_frag_list(skb)))
 		return NULL;
 
+	n_segments = DIV_ROUND_UP(skb->len - offset, skb_shinfo(skb)->gso_size);
 	*hdr = iwl_pcie_get_page_hdr(trans,
 				     hdr_room + __alignof__(struct sg_table) +
 				     sizeof(struct sg_table) +
-				     (skb_shinfo(skb)->nr_frags + 1) *
-				     sizeof(struct scatterlist),
+				     n_segments * sizeof(struct scatterlist),
 				     skb);
 	if (!*hdr)
 		return NULL;
@@ -1883,11 +1886,11 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 	sgt = (void *)PTR_ALIGN(*hdr + hdr_room, __alignof__(struct sg_table));
 	sgt->sgl = (void *)(sgt + 1);
 
-	sg_init_table(sgt->sgl, skb_shinfo(skb)->nr_frags + 1);
+	sg_init_table(sgt->sgl, n_segments);
 
 	/* Only map the data, not the header (it is copied to the TSO page) */
-	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, skb_headlen(skb),
-				       skb->data_len);
+	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, offset,
+				       skb->len - offset);
 	if (WARN_ON_ONCE(sgt->orig_nents <= 0))
 		return NULL;
 
@@ -1939,7 +1942,8 @@ static int iwl_fill_data_tbs_amsdu(struct iwl_trans *trans, struct sk_buff *skb,
 		(3 + snap_ip_tcp_hdrlen + sizeof(struct ethhdr)) + iv_len;
 
 	/* Our device supports 9 segments at most, it will fit in 1 page */
-	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room);
+	sgt = iwl_pcie_prep_tso(trans, skb, out_meta, &start_hdr, hdr_room,
+				snap_ip_tcp_hdrlen + hdr_len + iv_len);
 	if (!sgt)
 		return -ENOMEM;
 

From a9d71b5de76ccc50318d13b828f1a753d8e6a63f Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:19 +0100
Subject: [PATCH 0403/2753] mptcp: pm: drop info of
 userspace_pm_remove_id_zero_address

The only use of 'info' parameter of userspace_pm_remove_id_zero_address()
is to set an error message into it.

Plus, this helper will only fail when it cannot find any subflows with a
local address ID 0.

This patch drops this parameter and sets the error message where this
function is called in mptcp_pm_nl_remove_doit().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index a3d477059b11c..4de38bc03ab8a 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -253,8 +253,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,
-						     struct genl_info *info)
+static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk)
 {
 	struct mptcp_rm_list list = { .nr = 0 };
 	struct mptcp_subflow_context *subflow;
@@ -269,10 +268,8 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk,
 			break;
 		}
 	}
-	if (!has_id_0) {
-		GENL_SET_ERR_MSG(info, "address with id 0 not found");
+	if (!has_id_0)
 		goto remove_err;
-	}
 
 	list.ids[list.nr++] = 0;
 
@@ -330,7 +327,7 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	sk = (struct sock *)msk;
 
 	if (id_val == 0) {
-		err = mptcp_userspace_pm_remove_id_zero_address(msk, info);
+		err = mptcp_userspace_pm_remove_id_zero_address(msk);
 		goto out;
 	}
 
@@ -339,7 +336,6 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	spin_lock_bh(&msk->pm.lock);
 	match = mptcp_userspace_pm_lookup_addr_by_id(msk, id_val);
 	if (!match) {
-		GENL_SET_ERR_MSG(info, "address with specified id not found");
 		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
 		goto out;
@@ -356,6 +352,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 	err = 0;
 out:
+	if (err)
+		GENL_SET_ERR_MSG_FMT(info,
+				     "address with id %u not found",
+				     id_val);
+
 	sock_put(sk);
 	return err;
 }

From 58b21309f97b08b6b9814d1ee1419249eba9ef08 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:20 +0100
Subject: [PATCH 0404/2753] mptcp: pm: userspace: flags: clearer msg if no
 remote addr

Since its introduction in commit 892f396c8e68 ("mptcp: netlink: issue
MP_PRIO signals from userspace PMs"), it was mandatory to specify the
remote address, because of the 'if (rem->addr.family == AF_UNSPEC)'
check done later one.

In theory, this attribute can be optional, but it sounds better to be
precise to avoid sending the MP_PRIO on the wrong subflow, e.g. if there
are multiple subflows attached to the same local ID. This can be relaxed
later on if there is a need to act on multiple subflows with one
command.

For the moment, the check to see if attr_rem is NULL can be removed,
because mptcp_pm_parse_entry() will do this check as well, no need to do
that differently here.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 4de38bc03ab8a..b6cf8ea1161dd 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -580,11 +580,9 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto set_flags_err;
 
-	if (attr_rem) {
-		ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
-		if (ret < 0)
-			goto set_flags_err;
-	}
+	ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
+	if (ret < 0)
+		goto set_flags_err;
 
 	if (loc.addr.family == AF_UNSPEC ||
 	    rem.addr.family == AF_UNSPEC) {

From 891a87f7a76c77f8afde876e08b55a2af9819709 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:21 +0100
Subject: [PATCH 0405/2753] mptcp: pm: more precise error messages

Some errors reported by the userspace PM were vague: "this or that is
invalid".

It is easier for the userspace to know which part is wrong, instead of
having to guess that.

While at it, in mptcp_userspace_pm_set_flags() move the parsing after
the check linked to the local attribute.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 31 ++++++++++++++++++++++++-------
 1 file changed, 24 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b6cf8ea1161dd..cdc83fabb7c2c 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -223,8 +223,14 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 		goto announce_err;
 	}
 
-	if (addr_val.addr.id == 0 || !(addr_val.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
-		GENL_SET_ERR_MSG(info, "invalid addr id or flags");
+	if (addr_val.addr.id == 0) {
+		GENL_SET_ERR_MSG(info, "invalid addr id");
+		err = -EINVAL;
+		goto announce_err;
+	}
+
+	if (!(addr_val.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+		GENL_SET_ERR_MSG(info, "invalid addr flags");
 		err = -EINVAL;
 		goto announce_err;
 	}
@@ -531,8 +537,14 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 		goto destroy_err;
 	}
 
-	if (!addr_l.addr.port || !addr_r.port) {
-		GENL_SET_ERR_MSG(info, "missing local or remote port");
+	if (!addr_l.addr.port) {
+		GENL_SET_ERR_MSG(info, "missing local port");
+		err = -EINVAL;
+		goto destroy_err;
+	}
+
+	if (!addr_r.port) {
+		GENL_SET_ERR_MSG(info, "missing remote port");
 		err = -EINVAL;
 		goto destroy_err;
 	}
@@ -580,13 +592,18 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		goto set_flags_err;
 
+	if (loc.addr.family == AF_UNSPEC) {
+		GENL_SET_ERR_MSG(info, "invalid local address family");
+		ret = -EINVAL;
+		goto set_flags_err;
+	}
+
 	ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
 	if (ret < 0)
 		goto set_flags_err;
 
-	if (loc.addr.family == AF_UNSPEC ||
-	    rem.addr.family == AF_UNSPEC) {
-		GENL_SET_ERR_MSG(info, "invalid address families");
+	if (rem.addr.family == AF_UNSPEC) {
+		GENL_SET_ERR_MSG(info, "invalid remote address family");
 		ret = -EINVAL;
 		goto set_flags_err;
 	}

From b2bdec19beecf9351ff9f7ca3131f5f61aacfc9d Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:22 +0100
Subject: [PATCH 0406/2753] mptcp: pm: improve error messages

Some error messages were:

 - too generic: "missing input", "invalid request"

 - not precise enough: "limit greater than maximum" but what's the max?

 - missing: subflow not found, or connect error.

This can be easily improved by being more precise, or adding new error
messages.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_netlink.c   |  6 ++++--
 net/mptcp/pm_userspace.c | 10 +++++++++-
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 572d160edca33..1afa2bd898623 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1875,7 +1875,9 @@ static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
 
 	*limit = nla_get_u32(attr);
 	if (*limit > MPTCP_PM_ADDR_MAX) {
-		GENL_SET_ERR_MSG(info, "limit greater than maximum");
+		NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr,
+					"limit greater than maximum (%u)",
+					MPTCP_PM_ADDR_MAX);
 		return -EINVAL;
 	}
 	return 0;
@@ -2003,7 +2005,7 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (addr.addr.family == AF_UNSPEC) {
 		lookup_by_id = 1;
 		if (!addr.addr.id) {
-			GENL_SET_ERR_MSG(info, "missing required inputs");
+			GENL_SET_ERR_MSG(info, "missing address ID");
 			return -EOPNOTSUPP;
 		}
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index cdc83fabb7c2c..e350d6cc23bf2 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -190,7 +190,7 @@ static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *in
 	}
 
 	if (!mptcp_pm_is_userspace(msk)) {
-		GENL_SET_ERR_MSG(info, "invalid request; userspace PM not selected");
+		GENL_SET_ERR_MSG(info, "userspace PM not selected");
 		sock_put((struct sock *)msk);
 		return NULL;
 	}
@@ -428,6 +428,9 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 	err = __mptcp_subflow_connect(sk, &local, &addr_r);
 	release_sock(sk);
 
+	if (err)
+		GENL_SET_ERR_MSG_FMT(info, "connect error: %d", err);
+
 	spin_lock_bh(&msk->pm.lock);
 	if (err)
 		mptcp_userspace_pm_delete_local_addr(msk, &entry);
@@ -552,6 +555,7 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 	lock_sock(sk);
 	ssk = mptcp_nl_find_ssk(msk, &addr_l.addr, &addr_r);
 	if (!ssk) {
+		GENL_SET_ERR_MSG(info, "subflow not found");
 		err = -ESRCH;
 		goto release_sock;
 	}
@@ -625,6 +629,10 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup);
 	release_sock(sk);
 
+	/* mptcp_pm_nl_mp_prio_send_ack() only fails in one case */
+	if (ret < 0)
+		GENL_SET_ERR_MSG(info, "subflow not found");
+
 set_flags_err:
 	sock_put(sk);
 	return ret;

From 07bfabf8407b4c4cc010e0c41feeebed75594bd0 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:23 +0100
Subject: [PATCH 0407/2753] mptcp: pm: userspace: use GENL_REQ_ATTR_CHECK

A more general way to check if MPTCP_PM_ATTR_* exists in 'info'
is to use GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_*) instead of
directly reading info->attrs[MPTCP_PM_ATTR_*] and then checking
if it's NULL.

So this patch uses GENL_REQ_ATTR_CHECK() for userspace PM in
mptcp_pm_nl_announce_doit(), mptcp_pm_nl_remove_doit(),
mptcp_pm_nl_subflow_create_doit(), mptcp_pm_nl_subflow_destroy_doit()
and mptcp_userspace_pm_get_sock().

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 41 +++++++++++++++++++---------------------
 1 file changed, 19 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index e350d6cc23bf2..4cbd234e26701 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -175,14 +175,13 @@ bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
 
 static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *info)
 {
-	struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	struct mptcp_sock *msk;
+	struct nlattr *token;
 
-	if (!token) {
-		GENL_SET_ERR_MSG(info, "missing required token");
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_TOKEN))
 		return NULL;
-	}
 
+	token = info->attrs[MPTCP_PM_ATTR_TOKEN];
 	msk = mptcp_token_get_sock(genl_info_net(info), nla_get_u32(token));
 	if (!msk) {
 		NL_SET_ERR_MSG_ATTR(info->extack, token, "invalid token");
@@ -200,16 +199,14 @@ static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *in
 
 int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *addr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct mptcp_pm_addr_entry addr_val;
 	struct mptcp_sock *msk;
+	struct nlattr *addr;
 	int err = -EINVAL;
 	struct sock *sk;
 
-	if (!addr) {
-		GENL_SET_ERR_MSG(info, "missing required address");
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
 		return err;
-	}
 
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
@@ -217,6 +214,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 
 	sk = (struct sock *)msk;
 
+	addr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(addr, info, true, &addr_val);
 	if (err < 0) {
 		GENL_SET_ERR_MSG(info, "error parsing local address");
@@ -312,18 +310,17 @@ void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
 
 int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *id = info->attrs[MPTCP_PM_ATTR_LOC_ID];
 	struct mptcp_pm_addr_entry *match;
 	struct mptcp_sock *msk;
+	struct nlattr *id;
 	int err = -EINVAL;
 	struct sock *sk;
 	u8 id_val;
 
-	if (!id) {
-		GENL_SET_ERR_MSG(info, "missing required ID");
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_LOC_ID))
 		return err;
-	}
 
+	id = info->attrs[MPTCP_PM_ATTR_LOC_ID];
 	id_val = nla_get_u8(id);
 
 	msk = mptcp_userspace_pm_get_sock(info);
@@ -369,19 +366,17 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 
 int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
-	struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct mptcp_pm_addr_entry entry = { 0 };
 	struct mptcp_addr_info addr_r;
+	struct nlattr *raddr, *laddr;
 	struct mptcp_pm_local local;
 	struct mptcp_sock *msk;
 	int err = -EINVAL;
 	struct sock *sk;
 
-	if (!laddr || !raddr) {
-		GENL_SET_ERR_MSG(info, "missing required address(es)");
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR) ||
+	    GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR_REMOTE))
 		return err;
-	}
 
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
@@ -389,6 +384,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	sk = (struct sock *)msk;
 
+	laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(laddr, info, true, &entry);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
@@ -402,6 +398,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 	entry.flags |= MPTCP_PM_ADDR_FLAG_SUBFLOW;
 
+	raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
@@ -493,18 +490,16 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
 
 int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
-	struct nlattr *laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct mptcp_pm_addr_entry addr_l;
 	struct mptcp_addr_info addr_r;
+	struct nlattr *raddr, *laddr;
 	struct mptcp_sock *msk;
 	struct sock *sk, *ssk;
 	int err = -EINVAL;
 
-	if (!laddr || !raddr) {
-		GENL_SET_ERR_MSG(info, "missing required address(es)");
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR) ||
+	    GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR_REMOTE))
 		return err;
-	}
 
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
@@ -512,12 +507,14 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 
 	sk = (struct sock *)msk;
 
+	laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(laddr, info, true, &addr_l);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
 		goto destroy_err;
 	}
 
+	raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
 	if (err < 0) {
 		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");

From 60097f03fc7a96fecb4ea9a993397032fe586778 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:24 +0100
Subject: [PATCH 0408/2753] mptcp: pm: remove duplicated error messages

mptcp_pm_parse_entry() and mptcp_pm_parse_addr() will already set a
error message in case of parsing issue.

Then, no need to override this error message with another less precise
one: "error parsing address".

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 20 +++++---------------
 1 file changed, 5 insertions(+), 15 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 4cbd234e26701..ab915716ed418 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -216,10 +216,8 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 
 	addr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(addr, info, true, &addr_val);
-	if (err < 0) {
-		GENL_SET_ERR_MSG(info, "error parsing local address");
+	if (err < 0)
 		goto announce_err;
-	}
 
 	if (addr_val.addr.id == 0) {
 		GENL_SET_ERR_MSG(info, "invalid addr id");
@@ -386,10 +384,8 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(laddr, info, true, &entry);
-	if (err < 0) {
-		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
+	if (err < 0)
 		goto create_err;
-	}
 
 	if (entry.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
 		GENL_SET_ERR_MSG(info, "invalid addr flags");
@@ -400,10 +396,8 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
-	if (err < 0) {
-		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
+	if (err < 0)
 		goto create_err;
-	}
 
 	if (!mptcp_pm_addr_families_match(sk, &entry.addr, &addr_r)) {
 		GENL_SET_ERR_MSG(info, "families mismatch");
@@ -509,17 +503,13 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 
 	laddr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	err = mptcp_pm_parse_entry(laddr, info, true, &addr_l);
-	if (err < 0) {
-		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "error parsing local addr");
+	if (err < 0)
 		goto destroy_err;
-	}
 
 	raddr = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	err = mptcp_pm_parse_addr(raddr, info, &addr_r);
-	if (err < 0) {
-		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "error parsing remote addr");
+	if (err < 0)
 		goto destroy_err;
-	}
 
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	if (addr_l.addr.family == AF_INET && ipv6_addr_v4mapped(&addr_r.addr6)) {

From 8cdc56f99e6c33abc855891dbd4d802be06d1404 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:25 +0100
Subject: [PATCH 0409/2753] mptcp: pm: mark missing address attributes

mptcp_pm_parse_entry() will check if the given attribute is defined. If
not, it will return a generic error: "missing address info".

It might then not be clear for the userspace developer which attribute
is missing, especially when the command takes multiple addresses.

By using GENL_REQ_ATTR_CHECK(), the userspace will get a hint about
which attribute is missing, making thing clearer. Note that this is what
was already done for most of the other MPTCP NL commands, this patch
simply adds the missing ones.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_netlink.c   | 24 ++++++++++++++++++++----
 net/mptcp/pm_userspace.c | 15 ++++++++++++---
 2 files changed, 32 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1afa2bd898623..4a1ba2bbb54d5 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1393,11 +1393,15 @@ static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
 
 int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	struct mptcp_pm_addr_entry addr, *entry;
+	struct nlattr *attr;
 	int ret;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, true, &addr);
 	if (ret < 0)
 		return ret;
@@ -1587,12 +1591,16 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
 
 int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	struct mptcp_pm_addr_entry addr, *entry;
 	unsigned int addr_max;
+	struct nlattr *attr;
 	int ret;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
@@ -1764,13 +1772,17 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 
 int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info)
 {
-	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	struct mptcp_pm_addr_entry addr, *entry;
 	struct sk_buff *msg;
+	struct nlattr *attr;
 	void *reply;
 	int ret;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
@@ -1986,18 +1998,22 @@ static int mptcp_nl_set_flags(struct net *net,
 int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
-	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
 			   MPTCP_PM_ADDR_FLAG_FULLMESH;
 	struct net *net = sock_net(skb->sk);
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
+	struct nlattr *attr;
 	u8 lookup_by_id = 0;
 	u8 bkup = 0;
 	int ret;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
+		return -EINVAL;
+
 	pernet = pm_nl_get_pernet(net);
 
+	attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		return ret;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index ab915716ed418..525dcb84353f9 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -565,20 +565,24 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
 	struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, };
-	struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
-	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	struct mptcp_pm_addr_entry *entry;
+	struct nlattr *attr, *attr_rem;
 	struct mptcp_sock *msk;
 	int ret = -EINVAL;
 	struct sock *sk;
 	u8 bkup = 0;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR) ||
+	    GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR_REMOTE))
+		return ret;
+
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
 		return ret;
 
 	sk = (struct sock *)msk;
 
+	attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, false, &loc);
 	if (ret < 0)
 		goto set_flags_err;
@@ -589,6 +593,7 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 		goto set_flags_err;
 	}
 
+	attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
 	ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
 	if (ret < 0)
 		goto set_flags_err;
@@ -677,20 +682,24 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
 				struct genl_info *info)
 {
-	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct mptcp_pm_addr_entry addr, *entry;
 	struct mptcp_sock *msk;
 	struct sk_buff *msg;
+	struct nlattr *attr;
 	int ret = -EINVAL;
 	struct sock *sk;
 	void *reply;
 
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return ret;
+
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
 		return ret;
 
 	sk = (struct sock *)msk;
 
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
 	if (ret < 0)
 		goto out;

From a25a8b10491bb94e905fdbef06f0f2b80fd9f74f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Feb 2025 14:59:26 +0100
Subject: [PATCH 0410/2753] mptcp: pm: use NL_SET_ERR_MSG_ATTR when possible

Instead of only returning a text message with GENL_SET_ERR_MSG(),
NL_SET_ERR_MSG_ATTR() can help the userspace developers by also
reporting which attribute is faulty.

When the error is specific to an attribute, NL_SET_ERR_MSG_ATTR() is now
used. The error messages have not been modified in this commit.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_netlink.c   | 20 ++++++++++++--------
 net/mptcp/pm_userspace.c | 33 +++++++++++++++++++--------------
 2 files changed, 31 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 4a1ba2bbb54d5..bbdfb7700538e 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1407,18 +1407,21 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	if (addr.addr.port && !address_use_port(&addr)) {
-		GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "flags must have signal and not subflow when using port");
 		return -EINVAL;
 	}
 
 	if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
 	    addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
-		GENL_SET_ERR_MSG(info, "flags mustn't have both signal and fullmesh");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "flags mustn't have both signal and fullmesh");
 		return -EINVAL;
 	}
 
 	if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
-		GENL_SET_ERR_MSG(info, "can't create IMPLICIT endpoint");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "can't create IMPLICIT endpoint");
 		return -EINVAL;
 	}
 
@@ -1616,7 +1619,7 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
 	spin_lock_bh(&pernet->lock);
 	entry = __lookup_addr_by_id(pernet, addr.addr.id);
 	if (!entry) {
-		GENL_SET_ERR_MSG(info, "address not found");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		spin_unlock_bh(&pernet->lock);
 		return -EINVAL;
 	}
@@ -1802,7 +1805,7 @@ int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info)
 	rcu_read_lock();
 	entry = __lookup_addr_by_id(pernet, addr.addr.id);
 	if (!entry) {
-		GENL_SET_ERR_MSG(info, "address not found");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		ret = -EINVAL;
 		goto unlock_fail;
 	}
@@ -2021,7 +2024,8 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 	if (addr.addr.family == AF_UNSPEC) {
 		lookup_by_id = 1;
 		if (!addr.addr.id) {
-			GENL_SET_ERR_MSG(info, "missing address ID");
+			NL_SET_ERR_MSG_ATTR(info->extack, attr,
+					    "missing address ID");
 			return -EOPNOTSUPP;
 		}
 	}
@@ -2034,14 +2038,14 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 			       __lookup_addr(pernet, &addr.addr);
 	if (!entry) {
 		spin_unlock_bh(&pernet->lock);
-		GENL_SET_ERR_MSG(info, "address not found");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		return -EINVAL;
 	}
 	if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
 	    (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |
 			     MPTCP_PM_ADDR_FLAG_IMPLICIT))) {
 		spin_unlock_bh(&pernet->lock);
-		GENL_SET_ERR_MSG(info, "invalid addr flags");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "invalid addr flags");
 		return -EINVAL;
 	}
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 525dcb84353f9..8dddb16247363 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -189,7 +189,8 @@ static struct mptcp_sock *mptcp_userspace_pm_get_sock(const struct genl_info *in
 	}
 
 	if (!mptcp_pm_is_userspace(msk)) {
-		GENL_SET_ERR_MSG(info, "userspace PM not selected");
+		NL_SET_ERR_MSG_ATTR(info->extack, token,
+				    "userspace PM not selected");
 		sock_put((struct sock *)msk);
 		return NULL;
 	}
@@ -220,20 +221,21 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 		goto announce_err;
 
 	if (addr_val.addr.id == 0) {
-		GENL_SET_ERR_MSG(info, "invalid addr id");
+		NL_SET_ERR_MSG_ATTR(info->extack, addr, "invalid addr id");
 		err = -EINVAL;
 		goto announce_err;
 	}
 
 	if (!(addr_val.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
-		GENL_SET_ERR_MSG(info, "invalid addr flags");
+		NL_SET_ERR_MSG_ATTR(info->extack, addr, "invalid addr flags");
 		err = -EINVAL;
 		goto announce_err;
 	}
 
 	err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false);
 	if (err < 0) {
-		GENL_SET_ERR_MSG(info, "did not match address and id");
+		NL_SET_ERR_MSG_ATTR(info->extack, addr,
+				    "did not match address and id");
 		goto announce_err;
 	}
 
@@ -354,9 +356,9 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)
 	err = 0;
 out:
 	if (err)
-		GENL_SET_ERR_MSG_FMT(info,
-				     "address with id %u not found",
-				     id_val);
+		NL_SET_ERR_MSG_ATTR_FMT(info->extack, id,
+					"address with id %u not found",
+					id_val);
 
 	sock_put(sk);
 	return err;
@@ -388,7 +390,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 		goto create_err;
 
 	if (entry.flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
-		GENL_SET_ERR_MSG(info, "invalid addr flags");
+		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "invalid addr flags");
 		err = -EINVAL;
 		goto create_err;
 	}
@@ -407,7 +409,8 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info)
 
 	err = mptcp_userspace_pm_append_new_local_addr(msk, &entry, false);
 	if (err < 0) {
-		GENL_SET_ERR_MSG(info, "did not match address and id");
+		NL_SET_ERR_MSG_ATTR(info->extack, laddr,
+				    "did not match address and id");
 		goto create_err;
 	}
 
@@ -528,13 +531,13 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 	}
 
 	if (!addr_l.addr.port) {
-		GENL_SET_ERR_MSG(info, "missing local port");
+		NL_SET_ERR_MSG_ATTR(info->extack, laddr, "missing local port");
 		err = -EINVAL;
 		goto destroy_err;
 	}
 
 	if (!addr_r.port) {
-		GENL_SET_ERR_MSG(info, "missing remote port");
+		NL_SET_ERR_MSG_ATTR(info->extack, raddr, "missing remote port");
 		err = -EINVAL;
 		goto destroy_err;
 	}
@@ -588,7 +591,8 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 		goto set_flags_err;
 
 	if (loc.addr.family == AF_UNSPEC) {
-		GENL_SET_ERR_MSG(info, "invalid local address family");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "invalid local address family");
 		ret = -EINVAL;
 		goto set_flags_err;
 	}
@@ -599,7 +603,8 @@ int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 		goto set_flags_err;
 
 	if (rem.addr.family == AF_UNSPEC) {
-		GENL_SET_ERR_MSG(info, "invalid remote address family");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr_rem,
+				    "invalid remote address family");
 		ret = -EINVAL;
 		goto set_flags_err;
 	}
@@ -722,7 +727,7 @@ int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_userspace_pm_lookup_addr_by_id(msk, addr.addr.id);
 	if (!entry) {
-		GENL_SET_ERR_MSG(info, "address not found");
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		ret = -EINVAL;
 		goto unlock_fail;
 	}

From 7aeab89b090fe40bc96e4af68c2b57f019d654d7 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:27 +0100
Subject: [PATCH 0411/2753] mptcp: pm: make three pm wrappers static

Three netlink functions:

	mptcp_pm_nl_get_addr_doit()
	mptcp_pm_nl_get_addr_dumpit()
	mptcp_pm_nl_set_flags_doit()

are generic, implemented for each PM, in-kernel PM and userspace PM. It's
clearer to move them from pm_netlink.c to pm.c.

And the linked three path manager wrappers

	mptcp_pm_get_addr()
	mptcp_pm_dump_addr()
	mptcp_pm_set_flags()

can be changed as static functions, no need to export them in protocol.h.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c         | 23 ++++++++++++++++++++---
 net/mptcp/pm_netlink.c | 16 ----------------
 net/mptcp/protocol.h   |  3 ---
 3 files changed, 20 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 16c336c519403..a29be5ff73a6b 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -10,6 +10,7 @@
 #include "protocol.h"
 
 #include "mib.h"
+#include "mptcp_pm_gen.h"
 
 /* path manager command handlers */
 
@@ -433,14 +434,19 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info)
+static int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
 		return mptcp_userspace_pm_get_addr(skb, info);
 	return mptcp_pm_nl_get_addr(skb, info);
 }
 
-int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
+int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return mptcp_pm_get_addr(skb, info);
+}
+
+static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	const struct genl_info *info = genl_info_dump(cb);
 
@@ -449,13 +455,24 @@ int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
 	return mptcp_pm_nl_dump_addr(msg, cb);
 }
 
-int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
+int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
+				struct netlink_callback *cb)
+{
+	return mptcp_pm_dump_addr(msg, cb);
+}
+
+static int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
 		return mptcp_userspace_pm_set_flags(skb, info);
 	return mptcp_pm_nl_set_flags(skb, info);
 }
 
+int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return mptcp_pm_set_flags(skb, info);
+}
+
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index bbdfb7700538e..eb8f68ee24cfb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1827,11 +1827,6 @@ int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
-int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	return mptcp_pm_get_addr(skb, info);
-}
-
 int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb)
 {
@@ -1875,12 +1870,6 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 	return msg->len;
 }
 
-int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
-				struct netlink_callback *cb)
-{
-	return mptcp_pm_dump_addr(msg, cb);
-}
-
 static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
 {
 	struct nlattr *attr = info->attrs[id];
@@ -2058,11 +2047,6 @@ int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
-int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	return mptcp_pm_set_flags(skb, info);
-}
-
 static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
 {
 	genlmsg_multicast_netns(&mptcp_genl_family, net,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f6a207958459d..6bfcde68d915c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1038,7 +1038,6 @@ bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
 				   const struct mptcp_addr_info *saddr);
 bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
 				     const struct mptcp_addr_info *addr);
-int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
 int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info);
 int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
@@ -1131,12 +1130,10 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_in
 bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
 bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
-int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
 int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 				 struct netlink_callback *cb);
-int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info);
 int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info);
 int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
 				struct genl_info *info);

From 67dcf659254406596a6ff8600763244c3f4d75b0 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:28 +0100
Subject: [PATCH 0412/2753] mptcp: pm: drop skb parameter of get_addr

The first parameters 'skb' of get_addr() interfaces are now useless
since mptcp_userspace_pm_get_sock() helper is used. This patch drops
these useless parameters of them.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           | 8 ++++----
 net/mptcp/pm_netlink.c   | 2 +-
 net/mptcp/pm_userspace.c | 3 +--
 net/mptcp/protocol.h     | 5 ++---
 4 files changed, 8 insertions(+), 10 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index a29be5ff73a6b..526e5bca1fa1b 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -434,16 +434,16 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static int mptcp_pm_get_addr(struct sk_buff *skb, struct genl_info *info)
+static int mptcp_pm_get_addr(struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_get_addr(skb, info);
-	return mptcp_pm_nl_get_addr(skb, info);
+		return mptcp_userspace_pm_get_addr(info);
+	return mptcp_pm_nl_get_addr(info);
 }
 
 int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return mptcp_pm_get_addr(skb, info);
+	return mptcp_pm_get_addr(info);
 }
 
 static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index eb8f68ee24cfb..8185697044e2b 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1773,7 +1773,7 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
-int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info)
+int mptcp_pm_nl_get_addr(struct genl_info *info)
 {
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	struct mptcp_pm_addr_entry addr, *entry;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 8dddb16247363..1246063598c81 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -684,8 +684,7 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	return ret;
 }
 
-int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
-				struct genl_info *info)
+int mptcp_userspace_pm_get_addr(struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry addr, *entry;
 	struct mptcp_sock *msk;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 6bfcde68d915c..a4c799ecceffe 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1134,9 +1134,8 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 				 struct netlink_callback *cb);
-int mptcp_pm_nl_get_addr(struct sk_buff *skb, struct genl_info *info);
-int mptcp_userspace_pm_get_addr(struct sk_buff *skb,
-				struct genl_info *info);
+int mptcp_pm_nl_get_addr(struct genl_info *info);
+int mptcp_userspace_pm_get_addr(struct genl_info *info);
 
 static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
 {

From d47b80758f4c5d72a82cd8416cbf34617ded5c0b Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:29 +0100
Subject: [PATCH 0413/2753] mptcp: pm: add id parameter for get_addr

The address id is parsed both in mptcp_pm_nl_get_addr() and
mptcp_userspace_pm_get_addr(), this makes the code somewhat repetitive.

So this patch adds a new parameter 'id' for all get_addr() interfaces.
The address id is only parsed in mptcp_pm_nl_get_addr_doit(), then pass
it to both mptcp_pm_nl_get_addr() and mptcp_userspace_pm_get_addr().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           | 20 ++++++++++++++++----
 net/mptcp/pm_netlink.c   | 16 ++++------------
 net/mptcp/pm_userspace.c | 16 ++++------------
 net/mptcp/protocol.h     |  4 ++--
 4 files changed, 26 insertions(+), 30 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 526e5bca1fa1b..caf5bfc3cd1dd 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -434,16 +434,28 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static int mptcp_pm_get_addr(struct genl_info *info)
+static int mptcp_pm_get_addr(u8 id, struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_get_addr(info);
-	return mptcp_pm_nl_get_addr(info);
+		return mptcp_userspace_pm_get_addr(id, info);
+	return mptcp_pm_nl_get_addr(id, info);
 }
 
 int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return mptcp_pm_get_addr(info);
+	struct mptcp_pm_addr_entry addr;
+	struct nlattr *attr;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
+	if (ret < 0)
+		return ret;
+
+	return mptcp_pm_get_addr(addr.addr.id, info);
 }
 
 static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 8185697044e2b..5a6c33d0063df 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1773,23 +1773,15 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
-int mptcp_pm_nl_get_addr(struct genl_info *info)
+int mptcp_pm_nl_get_addr(u8 id, struct genl_info *info)
 {
+	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct mptcp_pm_addr_entry addr, *entry;
+	struct mptcp_pm_addr_entry *entry;
 	struct sk_buff *msg;
-	struct nlattr *attr;
 	void *reply;
 	int ret;
 
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
-		return -EINVAL;
-
-	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
-	if (ret < 0)
-		return ret;
-
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg)
 		return -ENOMEM;
@@ -1803,7 +1795,7 @@ int mptcp_pm_nl_get_addr(struct genl_info *info)
 	}
 
 	rcu_read_lock();
-	entry = __lookup_addr_by_id(pernet, addr.addr.id);
+	entry = __lookup_addr_by_id(pernet, id);
 	if (!entry) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		ret = -EINVAL;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 1246063598c81..99e882a5a6718 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -684,30 +684,22 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	return ret;
 }
 
-int mptcp_userspace_pm_get_addr(struct genl_info *info)
+int mptcp_userspace_pm_get_addr(u8 id, struct genl_info *info)
 {
-	struct mptcp_pm_addr_entry addr, *entry;
+	struct nlattr *attr = attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+	struct mptcp_pm_addr_entry *entry;
 	struct mptcp_sock *msk;
 	struct sk_buff *msg;
-	struct nlattr *attr;
 	int ret = -EINVAL;
 	struct sock *sk;
 	void *reply;
 
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
-		return ret;
-
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
 		return ret;
 
 	sk = (struct sock *)msk;
 
-	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
-	if (ret < 0)
-		goto out;
-
 	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!msg) {
 		ret = -ENOMEM;
@@ -724,7 +716,7 @@ int mptcp_userspace_pm_get_addr(struct genl_info *info)
 
 	lock_sock(sk);
 	spin_lock_bh(&msk->pm.lock);
-	entry = mptcp_userspace_pm_lookup_addr_by_id(msk, addr.addr.id);
+	entry = mptcp_userspace_pm_lookup_addr_by_id(msk, id);
 	if (!entry) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		ret = -EINVAL;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a4c799ecceffe..ffe370245ec55 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1134,8 +1134,8 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 				 struct netlink_callback *cb);
-int mptcp_pm_nl_get_addr(struct genl_info *info);
-int mptcp_userspace_pm_get_addr(struct genl_info *info);
+int mptcp_pm_nl_get_addr(u8 id, struct genl_info *info);
+int mptcp_userspace_pm_get_addr(u8 id, struct genl_info *info);
 
 static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
 {

From 8556f4aecc9a0620c1e411d6da1fe232d1c14138 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:30 +0100
Subject: [PATCH 0414/2753] mptcp: pm: reuse sending nlmsg code in get_addr

The netlink messages are sent both in mptcp_pm_nl_get_addr() and
mptcp_userspace_pm_get_addr(), this makes the code somewhat repetitive.
This is because the netlink PM and userspace PM use different locks to
protect the address entry that needs to be sent via the netlink message.
The former uses rcu read lock, and the latter uses msk->pm.lock.

The current get_addr() flow looks like this:

	lock();
	entry = get_entry();
	send_nlmsg(entry);
	unlock();

After holding the lock, get the entry from the list, send the entry, and
finally release the lock.

This patch changes the process by getting the entry while holding the lock,
then making a copy of the entry so that the lock can be released. Finally,
the copy of the entry is sent without locking:

	lock();
	entry = get_entry();
	*copy = *entry;
	unlock();

	send_nlmsg(copy);

This way we can reuse the send_nlmsg() code in get_addr() interfaces
between the netlink PM and userspace PM. They only need to implement their
own get_addr() interfaces to hold the different locks, get the entry from
the different lists, then release the locks.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           | 39 +++++++++++++++++++++++++++++++++----
 net/mptcp/pm_netlink.c   | 40 ++++++--------------------------------
 net/mptcp/pm_userspace.c | 42 +++++-----------------------------------
 net/mptcp/protocol.h     |  6 ++++--
 4 files changed, 50 insertions(+), 77 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index caf5bfc3cd1dd..ba22d17c14518 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -434,17 +434,20 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static int mptcp_pm_get_addr(u8 id, struct genl_info *info)
+static int mptcp_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+			     struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_get_addr(id, info);
-	return mptcp_pm_nl_get_addr(id, info);
+		return mptcp_userspace_pm_get_addr(id, addr, info);
+	return mptcp_pm_nl_get_addr(id, addr, info);
 }
 
 int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry addr;
 	struct nlattr *attr;
+	struct sk_buff *msg;
+	void *reply;
 	int ret;
 
 	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
@@ -455,7 +458,35 @@ int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
 	if (ret < 0)
 		return ret;
 
-	return mptcp_pm_get_addr(addr.addr.id, info);
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
+				  info->genlhdr->cmd);
+	if (!reply) {
+		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
+		ret = -EMSGSIZE;
+		goto fail;
+	}
+
+	ret = mptcp_pm_get_addr(addr.addr.id, &addr, info);
+	if (ret) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
+		goto fail;
+	}
+
+	ret = mptcp_nl_fill_addr(msg, &addr);
+	if (ret)
+		goto fail;
+
+	genlmsg_end(msg, reply);
+	ret = genlmsg_reply(msg, info);
+	return ret;
+
+fail:
+	nlmsg_free(msg);
+	return ret;
 }
 
 static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 5a6c33d0063df..25b66674171fc 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1773,49 +1773,21 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
-int mptcp_pm_nl_get_addr(u8 id, struct genl_info *info)
+int mptcp_pm_nl_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+			 struct genl_info *info)
 {
-	struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
 	struct mptcp_pm_addr_entry *entry;
-	struct sk_buff *msg;
-	void *reply;
-	int ret;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
-				  info->genlhdr->cmd);
-	if (!reply) {
-		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
-		ret = -EMSGSIZE;
-		goto fail;
-	}
+	int ret = -EINVAL;
 
 	rcu_read_lock();
 	entry = __lookup_addr_by_id(pernet, id);
-	if (!entry) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
-		ret = -EINVAL;
-		goto unlock_fail;
+	if (entry) {
+		*addr = *entry;
+		ret = 0;
 	}
-
-	ret = mptcp_nl_fill_addr(msg, entry);
-	if (ret)
-		goto unlock_fail;
-
-	genlmsg_end(msg, reply);
-	ret = genlmsg_reply(msg, info);
-	rcu_read_unlock();
-	return ret;
-
-unlock_fail:
 	rcu_read_unlock();
 
-fail:
-	nlmsg_free(msg);
 	return ret;
 }
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 99e882a5a6718..80d75df18b039 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -684,15 +684,13 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	return ret;
 }
 
-int mptcp_userspace_pm_get_addr(u8 id, struct genl_info *info)
+int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+				struct genl_info *info)
 {
-	struct nlattr *attr = attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
 	struct mptcp_pm_addr_entry *entry;
 	struct mptcp_sock *msk;
-	struct sk_buff *msg;
 	int ret = -EINVAL;
 	struct sock *sk;
-	void *reply;
 
 	msk = mptcp_userspace_pm_get_sock(info);
 	if (!msk)
@@ -700,46 +698,16 @@ int mptcp_userspace_pm_get_addr(u8 id, struct genl_info *info)
 
 	sk = (struct sock *)msk;
 
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
-				  info->genlhdr->cmd);
-	if (!reply) {
-		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
-		ret = -EMSGSIZE;
-		goto fail;
-	}
-
 	lock_sock(sk);
 	spin_lock_bh(&msk->pm.lock);
 	entry = mptcp_userspace_pm_lookup_addr_by_id(msk, id);
-	if (!entry) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
-		ret = -EINVAL;
-		goto unlock_fail;
+	if (entry) {
+		*addr = *entry;
+		ret = 0;
 	}
-
-	ret = mptcp_nl_fill_addr(msg, entry);
-	if (ret)
-		goto unlock_fail;
-
-	genlmsg_end(msg, reply);
-	ret = genlmsg_reply(msg, info);
 	spin_unlock_bh(&msk->pm.lock);
 	release_sock(sk);
-	sock_put(sk);
-	return ret;
 
-unlock_fail:
-	spin_unlock_bh(&msk->pm.lock);
-	release_sock(sk);
-fail:
-	nlmsg_free(msg);
-out:
 	sock_put(sk);
 	return ret;
 }
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ffe370245ec55..e18ecd77a7f76 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1134,8 +1134,10 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			  struct netlink_callback *cb);
 int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 				 struct netlink_callback *cb);
-int mptcp_pm_nl_get_addr(u8 id, struct genl_info *info);
-int mptcp_userspace_pm_get_addr(u8 id, struct genl_info *info);
+int mptcp_pm_nl_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+			 struct genl_info *info);
+int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+				struct genl_info *info);
 
 static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow)
 {

From 2c8971c04f745de69814ae9cfd2273e8a1fefca9 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:31 +0100
Subject: [PATCH 0415/2753] mptcp: pm: drop skb parameter of set_flags

The first parameter 'skb' in mptcp_pm_nl_set_flags() is only used to
obtained the network namespace, which can also be obtained through the
second parameters 'info' by using genl_info_net() helper.

This patch drops these useless parameters 'skb' in all three set_flags()
interfaces.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           | 8 ++++----
 net/mptcp/pm_netlink.c   | 4 ++--
 net/mptcp/pm_userspace.c | 2 +-
 net/mptcp/protocol.h     | 4 ++--
 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index ba22d17c14518..c213f06bc7023 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -504,16 +504,16 @@ int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
 	return mptcp_pm_dump_addr(msg, cb);
 }
 
-static int mptcp_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
+static int mptcp_pm_set_flags(struct genl_info *info)
 {
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_set_flags(skb, info);
-	return mptcp_pm_nl_set_flags(skb, info);
+		return mptcp_userspace_pm_set_flags(info);
+	return mptcp_pm_nl_set_flags(info);
 }
 
 int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return mptcp_pm_set_flags(skb, info);
+	return mptcp_pm_set_flags(info);
 }
 
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 25b66674171fc..172ddb04e3495 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1951,12 +1951,12 @@ static int mptcp_nl_set_flags(struct net *net,
 	return ret;
 }
 
-int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info)
+int mptcp_pm_nl_set_flags(struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
 	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
 			   MPTCP_PM_ADDR_FLAG_FULLMESH;
-	struct net *net = sock_net(skb->sk);
+	struct net *net = genl_info_net(info);
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
 	struct nlattr *attr;
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 80d75df18b039..4fa3935c5b477 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -564,7 +564,7 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 	return err;
 }
 
-int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info)
+int mptcp_userspace_pm_set_flags(struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
 	struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, };
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index e18ecd77a7f76..6e7dc5375e291 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1038,8 +1038,8 @@ bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
 				   const struct mptcp_addr_info *saddr);
 bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
 				     const struct mptcp_addr_info *addr);
-int mptcp_pm_nl_set_flags(struct sk_buff *skb, struct genl_info *info);
-int mptcp_userspace_pm_set_flags(struct sk_buff *skb, struct genl_info *info);
+int mptcp_pm_nl_set_flags(struct genl_info *info);
+int mptcp_userspace_pm_set_flags(struct genl_info *info);
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo);

From ab5723599cfd00a1898b11c9d67a770384a7f51b Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:32 +0100
Subject: [PATCH 0416/2753] mptcp: pm: change rem type of set_flags

Generally, in the path manager interfaces, the local address is defined
as an mptcp_pm_addr_entry type address, while the remote address is
defined as an mptcp_addr_info type one:

    (struct mptcp_pm_addr_entry *local, struct mptcp_addr_info *remote)

But the set_flags() interface uses two mptcp_pm_addr_entry type
parameters.

This patch changes the second one to mptcp_addr_info type and use helper
mptcp_pm_parse_addr() to parse it instead of using mptcp_pm_parse_entry().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_userspace.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 4fa3935c5b477..1af70828c03c2 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -567,7 +567,7 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 int mptcp_userspace_pm_set_flags(struct genl_info *info)
 {
 	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
-	struct mptcp_pm_addr_entry rem = { .addr = { .family = AF_UNSPEC }, };
+	struct mptcp_addr_info rem = { .family = AF_UNSPEC, };
 	struct mptcp_pm_addr_entry *entry;
 	struct nlattr *attr, *attr_rem;
 	struct mptcp_sock *msk;
@@ -598,11 +598,11 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 	}
 
 	attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE];
-	ret = mptcp_pm_parse_entry(attr_rem, info, false, &rem);
+	ret = mptcp_pm_parse_addr(attr_rem, info, &rem);
 	if (ret < 0)
 		goto set_flags_err;
 
-	if (rem.addr.family == AF_UNSPEC) {
+	if (rem.family == AF_UNSPEC) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr_rem,
 				    "invalid remote address family");
 		ret = -EINVAL;
@@ -623,7 +623,7 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 	spin_unlock_bh(&msk->pm.lock);
 
 	lock_sock(sk);
-	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem.addr, bkup);
+	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem, bkup);
 	release_sock(sk);
 
 	/* mptcp_pm_nl_mp_prio_send_ack() only fails in one case */

From c7f25f7987c060b43b926c7c03c8ef8f0054a182 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Feb 2025 14:59:33 +0100
Subject: [PATCH 0417/2753] mptcp: pm: add local parameter for set_flags

This patch updates the interfaces set_flags to reduce repetitive
code, adds a new parameter 'local' for them.

The local address is parsed in public helper mptcp_pm_nl_set_flags_doit(),
then pass it to mptcp_pm_nl_set_flags() and mptcp_userspace_pm_set_flags().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           | 16 ++++++++++++++--
 net/mptcp/pm_netlink.c   | 35 +++++++++++++----------------------
 net/mptcp/pm_userspace.c | 19 +++++++------------
 net/mptcp/protocol.h     |  6 ++++--
 4 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index c213f06bc7023..b1f36dc1a0911 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -506,9 +506,21 @@ int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
 
 static int mptcp_pm_set_flags(struct genl_info *info)
 {
+	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
+	struct nlattr *attr_loc;
+	int ret = -EINVAL;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
+		return ret;
+
+	attr_loc = info->attrs[MPTCP_PM_ATTR_ADDR];
+	ret = mptcp_pm_parse_entry(attr_loc, info, false, &loc);
+	if (ret < 0)
+		return ret;
+
 	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_set_flags(info);
-	return mptcp_pm_nl_set_flags(info);
+		return mptcp_userspace_pm_set_flags(&loc, info);
+	return mptcp_pm_nl_set_flags(&loc, info);
 }
 
 int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 172ddb04e3495..99705a9c2238c 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1951,50 +1951,41 @@ static int mptcp_nl_set_flags(struct net *net,
 	return ret;
 }
 
-int mptcp_pm_nl_set_flags(struct genl_info *info)
+int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
+			  struct genl_info *info)
 {
-	struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, };
+	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
 	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
 			   MPTCP_PM_ADDR_FLAG_FULLMESH;
 	struct net *net = genl_info_net(info);
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
-	struct nlattr *attr;
 	u8 lookup_by_id = 0;
 	u8 bkup = 0;
-	int ret;
-
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
-		return -EINVAL;
 
 	pernet = pm_nl_get_pernet(net);
 
-	attr = info->attrs[MPTCP_PM_ATTR_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
-	if (ret < 0)
-		return ret;
-
-	if (addr.addr.family == AF_UNSPEC) {
+	if (local->addr.family == AF_UNSPEC) {
 		lookup_by_id = 1;
-		if (!addr.addr.id) {
+		if (!local->addr.id) {
 			NL_SET_ERR_MSG_ATTR(info->extack, attr,
 					    "missing address ID");
 			return -EOPNOTSUPP;
 		}
 	}
 
-	if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
+	if (local->flags & MPTCP_PM_ADDR_FLAG_BACKUP)
 		bkup = 1;
 
 	spin_lock_bh(&pernet->lock);
-	entry = lookup_by_id ? __lookup_addr_by_id(pernet, addr.addr.id) :
-			       __lookup_addr(pernet, &addr.addr);
+	entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) :
+			       __lookup_addr(pernet, &local->addr);
 	if (!entry) {
 		spin_unlock_bh(&pernet->lock);
 		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
 		return -EINVAL;
 	}
-	if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+	if ((local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
 	    (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |
 			     MPTCP_PM_ADDR_FLAG_IMPLICIT))) {
 		spin_unlock_bh(&pernet->lock);
@@ -2002,12 +1993,12 @@ int mptcp_pm_nl_set_flags(struct genl_info *info)
 		return -EINVAL;
 	}
 
-	changed = (addr.flags ^ entry->flags) & mask;
-	entry->flags = (entry->flags & ~mask) | (addr.flags & mask);
-	addr = *entry;
+	changed = (local->flags ^ entry->flags) & mask;
+	entry->flags = (entry->flags & ~mask) | (local->flags & mask);
+	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, &addr.addr, bkup, changed);
+	mptcp_nl_set_flags(net, &local->addr, bkup, changed);
 	return 0;
 }
 
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 1af70828c03c2..277cf092a8704 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -564,9 +564,9 @@ int mptcp_pm_nl_subflow_destroy_doit(struct sk_buff *skb, struct genl_info *info
 	return err;
 }
 
-int mptcp_userspace_pm_set_flags(struct genl_info *info)
+int mptcp_userspace_pm_set_flags(struct mptcp_pm_addr_entry *local,
+				 struct genl_info *info)
 {
-	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
 	struct mptcp_addr_info rem = { .family = AF_UNSPEC, };
 	struct mptcp_pm_addr_entry *entry;
 	struct nlattr *attr, *attr_rem;
@@ -575,8 +575,7 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 	struct sock *sk;
 	u8 bkup = 0;
 
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR) ||
-	    GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR_REMOTE))
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR_REMOTE))
 		return ret;
 
 	msk = mptcp_userspace_pm_get_sock(info);
@@ -586,11 +585,7 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 	sk = (struct sock *)msk;
 
 	attr = info->attrs[MPTCP_PM_ATTR_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &loc);
-	if (ret < 0)
-		goto set_flags_err;
-
-	if (loc.addr.family == AF_UNSPEC) {
+	if (local->addr.family == AF_UNSPEC) {
 		NL_SET_ERR_MSG_ATTR(info->extack, attr,
 				    "invalid local address family");
 		ret = -EINVAL;
@@ -609,11 +604,11 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 		goto set_flags_err;
 	}
 
-	if (loc.flags & MPTCP_PM_ADDR_FLAG_BACKUP)
+	if (local->flags & MPTCP_PM_ADDR_FLAG_BACKUP)
 		bkup = 1;
 
 	spin_lock_bh(&msk->pm.lock);
-	entry = mptcp_userspace_pm_lookup_addr(msk, &loc.addr);
+	entry = mptcp_userspace_pm_lookup_addr(msk, &local->addr);
 	if (entry) {
 		if (bkup)
 			entry->flags |= MPTCP_PM_ADDR_FLAG_BACKUP;
@@ -623,7 +618,7 @@ int mptcp_userspace_pm_set_flags(struct genl_info *info)
 	spin_unlock_bh(&msk->pm.lock);
 
 	lock_sock(sk);
-	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc.addr, &rem, bkup);
+	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &local->addr, &rem, bkup);
 	release_sock(sk);
 
 	/* mptcp_pm_nl_mp_prio_send_ack() only fails in one case */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 6e7dc5375e291..37226cdd9e371 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1038,8 +1038,10 @@ bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
 				   const struct mptcp_addr_info *saddr);
 bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
 				     const struct mptcp_addr_info *addr);
-int mptcp_pm_nl_set_flags(struct genl_info *info);
-int mptcp_userspace_pm_set_flags(struct genl_info *info);
+int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
+			  struct genl_info *info);
+int mptcp_userspace_pm_set_flags(struct mptcp_pm_addr_entry *local,
+				 struct genl_info *info);
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo);

From 0fed463777b83abe6410a8073de3f997c29afe18 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2025 15:28:26 +0000
Subject: [PATCH 0418/2753] tcp: remove tcp_reset_xmit_timer() @max_when
 argument

All callers use TCP_RTO_MAX, we can factorize this constant,
becoming a variable soon.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h     | 7 +++----
 net/ipv4/tcp_input.c  | 5 ++---
 net/ipv4/tcp_output.c | 7 +++----
 3 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index bb7edf0e72aa0..8678a2d37ef8d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1423,11 +1423,10 @@ static inline unsigned long tcp_pacing_delay(const struct sock *sk)
 
 static inline void tcp_reset_xmit_timer(struct sock *sk,
 					const int what,
-					unsigned long when,
-					const unsigned long max_when)
+					unsigned long when)
 {
 	inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk),
-				  max_when);
+				  TCP_RTO_MAX);
 }
 
 /* Something is really bad, we could not queue an additional packet,
@@ -1456,7 +1455,7 @@ static inline void tcp_check_probe_timer(struct sock *sk)
 {
 	if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
 		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				     tcp_probe0_base(sk), TCP_RTO_MAX);
+				     tcp_probe0_base(sk));
 }
 
 static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 286f15e4994a9..1a3ce47b8c750 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3282,8 +3282,7 @@ void tcp_rearm_rto(struct sock *sk)
 			 */
 			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
 		}
-		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
-				     TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto);
 	}
 }
 
@@ -3563,7 +3562,7 @@ static void tcp_ack_probe(struct sock *sk)
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
 		when = tcp_clamp_probe0_to_user_timeout(sk, when);
-		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index ef9f6172680f5..093476fb2b2e2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2910,7 +2910,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	if (rto_delta_us > 0)
 		timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
 
-	tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout);
 	return true;
 }
 
@@ -3544,8 +3544,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 	}
 	if (rearm_timer)
 		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				     inet_csk(sk)->icsk_rto,
-				     TCP_RTO_MAX);
+				     inet_csk(sk)->icsk_rto);
 }
 
 /* We allow to exceed memory limits for FIN packets to expedite
@@ -4401,7 +4400,7 @@ void tcp_send_probe0(struct sock *sk)
 	}
 
 	timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
-	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout);
 }
 
 int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)

From 7baa030155e8fa2a1bd9ea6425083c3b16787636 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2025 15:28:27 +0000
Subject: [PATCH 0419/2753] tcp: add a @pace_delay parameter to
 tcp_reset_xmit_timer()

We want to factorize calls to inet_csk_reset_xmit_timer(),
to ease TCP_RTO_MAX change.

Current users want to add tcp_pacing_delay(sk)
to the timeout.

Remaining calls to inet_csk_reset_xmit_timer()
do not add the pacing delay. Following patch
will convert them, passing false for @pace_delay.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/tcp.h     | 10 ++++++----
 net/ipv4/tcp_input.c  |  4 ++--
 net/ipv4/tcp_output.c |  6 +++---
 3 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8678a2d37ef8d..56557b0104e3f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1423,10 +1423,12 @@ static inline unsigned long tcp_pacing_delay(const struct sock *sk)
 
 static inline void tcp_reset_xmit_timer(struct sock *sk,
 					const int what,
-					unsigned long when)
+					unsigned long when,
+					bool pace_delay)
 {
-	inet_csk_reset_xmit_timer(sk, what, when + tcp_pacing_delay(sk),
-				  TCP_RTO_MAX);
+	if (pace_delay)
+		when += tcp_pacing_delay(sk);
+	inet_csk_reset_xmit_timer(sk, what, when, TCP_RTO_MAX);
 }
 
 /* Something is really bad, we could not queue an additional packet,
@@ -1455,7 +1457,7 @@ static inline void tcp_check_probe_timer(struct sock *sk)
 {
 	if (!tcp_sk(sk)->packets_out && !inet_csk(sk)->icsk_pending)
 		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				     tcp_probe0_base(sk));
+				     tcp_probe0_base(sk), true);
 }
 
 static inline void tcp_init_wl(struct tcp_sock *tp, u32 seq)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1a3ce47b8c750..5c9ed7657c9f0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3282,7 +3282,7 @@ void tcp_rearm_rto(struct sock *sk)
 			 */
 			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
 		}
-		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto, true);
 	}
 }
 
@@ -3562,7 +3562,7 @@ static void tcp_ack_probe(struct sock *sk)
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
 		when = tcp_clamp_probe0_to_user_timeout(sk, when);
-		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, true);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 093476fb2b2e2..27438ca2d5e68 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2910,7 +2910,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	if (rto_delta_us > 0)
 		timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
 
-	tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout, true);
 	return true;
 }
 
@@ -3544,7 +3544,7 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 	}
 	if (rearm_timer)
 		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				     inet_csk(sk)->icsk_rto);
+				     inet_csk(sk)->icsk_rto, true);
 }
 
 /* We allow to exceed memory limits for FIN packets to expedite
@@ -4400,7 +4400,7 @@ void tcp_send_probe0(struct sock *sk)
 	}
 
 	timeout = tcp_clamp_probe0_to_user_timeout(sk, timeout);
-	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, true);
 }
 
 int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)

From 48b69b4c7e5d74ad66e5214ae8cbdae0b9ea154c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2025 15:28:28 +0000
Subject: [PATCH 0420/2753] tcp: use tcp_reset_xmit_timer()

In order to reduce TCP_RTO_MAX occurrences, replace:

    inet_csk_reset_xmit_timer(sk, what, when, TCP_RTO_MAX)

With:

    tcp_reset_xmit_timer(sk, what, when, false);

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/tcp_fastopen.c |  4 ++--
 net/ipv4/tcp_input.c    | 12 +++++-------
 net/ipv4/tcp_ipv4.c     |  3 +--
 net/ipv4/tcp_output.c   |  6 +++---
 net/ipv4/tcp_timer.c    | 14 +++++++-------
 5 files changed, 18 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 0f523cbfe329e..e4c95238df58f 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -274,8 +274,8 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk,
 	 * because it's been added to the accept queue directly.
 	 */
 	req->timeout = tcp_timeout_init(child);
-	inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS,
-				  req->timeout, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(child, ICSK_TIME_RETRANS,
+			     req->timeout, false);
 
 	refcount_set(&req->rsk_refcnt, 2);
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5c9ed7657c9f0..9153fae2ebd81 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2252,8 +2252,7 @@ static bool tcp_check_sack_reneging(struct sock *sk, int *ack_flag)
 		unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
 					  msecs_to_jiffies(10));
 
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  delay, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, delay, false);
 		*ack_flag &= ~FLAG_SET_XMIT_TIMER;
 		return true;
 	}
@@ -6468,9 +6467,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		    after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
 			/* Previous FIN/ACK or RST/ACK might be ignored. */
 			if (icsk->icsk_retransmits == 0)
-				inet_csk_reset_xmit_timer(sk,
-						ICSK_TIME_RETRANS,
-						TCP_TIMEOUT_MIN, TCP_RTO_MAX);
+				tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+						     TCP_TIMEOUT_MIN, false);
 			SKB_DR_SET(reason, TCP_INVALID_ACK_SEQUENCE);
 			goto reset_and_undo;
 		}
@@ -6585,8 +6583,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 			 */
 			inet_csk_schedule_ack(sk);
 			tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
-						  TCP_DELACK_MAX, TCP_RTO_MAX);
+			tcp_reset_xmit_timer(sk, ICSK_TIME_DACK,
+					     TCP_DELACK_MAX, false);
 			goto consume;
 		}
 		tcp_send_ack(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index cc2b5194a18d2..e065f7097611b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -465,8 +465,7 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq)
 	remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us);
 
 	if (remaining > 0) {
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  remaining, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, false);
 	} else {
 		/* RTO revert clocked out retransmission.
 		 * Will retransmit now.
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 27438ca2d5e68..3623d19b7c6ed 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4161,8 +4161,8 @@ int tcp_connect(struct sock *sk)
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS);
 
 	/* Timer for repeating the SYN until an answer. */
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  inet_csk(sk)->icsk_rto, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			     inet_csk(sk)->icsk_rto, false);
 	return 0;
 }
 EXPORT_SYMBOL(tcp_connect);
@@ -4255,7 +4255,7 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
 		icsk->icsk_ack.ato = TCP_ATO_MIN;
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_DACK, delay, false);
 		return;
 	}
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index cfb6f4c4e4c9f..6472f560f6539 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -481,8 +481,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
 	tcp_update_rto_stats(sk);
 	if (!tp->retrans_stamp)
 		tp->retrans_stamp = tcp_time_stamp_ts(tp);
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-			  req->timeout << req->num_timeout, TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			  req->timeout << req->num_timeout, false);
 }
 
 static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
@@ -626,9 +626,9 @@ void tcp_retransmit_timer(struct sock *sk)
 		/* Retransmission failed because of local congestion,
 		 * Let senders fight for local resources conservatively.
 		 */
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-					  TCP_RESOURCE_PROBE_INTERVAL,
-					  TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+				     TCP_RESOURCE_PROBE_INTERVAL,
+				     false);
 		goto out;
 	}
 
@@ -675,8 +675,8 @@ void tcp_retransmit_timer(struct sock *sk)
 		icsk->icsk_backoff++;
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-				  tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+			     tcp_clamp_rto_to_user_timeout(sk), false);
 	if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
 		__sk_dst_reset(sk);
 

From 54a378f43425085d0684679d99735696b69165bc Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2025 15:28:29 +0000
Subject: [PATCH 0421/2753] tcp: add the ability to control max RTO

Currently, TCP stack uses a constant (120 seconds)
to limit the RTO value exponential growth.

Some applications want to set a lower value.

Add TCP_RTO_MAX_MS socket option to set a value (in ms)
between 1 and 120 seconds.

It is discouraged to change the socket rto max on a live
socket, as it might lead to unexpected disconnects.

Following patch is adding a netns sysctl to control the
default value at socket creation time.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net_cachelines/inet_connection_sock.rst     |  1 +
 include/net/inet_connection_sock.h              |  1 +
 include/net/tcp.h                               | 16 +++++++++++-----
 include/uapi/linux/tcp.h                        |  1 +
 net/ipv4/tcp.c                                  | 12 ++++++++++++
 net/ipv4/tcp_input.c                            |  2 +-
 net/ipv4/tcp_ipv4.c                             |  2 +-
 net/ipv4/tcp_output.c                           |  4 ++--
 net/ipv4/tcp_timer.c                            | 17 +++++++++--------
 9 files changed, 39 insertions(+), 17 deletions(-)

diff --git a/Documentation/networking/net_cachelines/inet_connection_sock.rst b/Documentation/networking/net_cachelines/inet_connection_sock.rst
index 4a15627fc93b8..b2401aa7c4509 100644
--- a/Documentation/networking/net_cachelines/inet_connection_sock.rst
+++ b/Documentation/networking/net_cachelines/inet_connection_sock.rst
@@ -17,6 +17,7 @@ struct timer_list                   icsk_retransmit_timer  read_mostly
 struct timer_list                   icsk_delack_timer      read_mostly                             inet_csk_reset_xmit_timer,tcp_connect
 u32                                 icsk_rto               read_write                              tcp_cwnd_validate,tcp_schedule_loss_probe,tcp_connect_init,tcp_connect,tcp_write_xmit,tcp_push_one
 u32                                 icsk_rto_min
+u32                                 icsk_rto_max           read_mostly                             tcp_reset_xmit_timer
 u32                                 icsk_delack_max
 u32                                 icsk_pmtu_cookie       read_write                              tcp_sync_mss,tcp_current_mss,tcp_send_syn_data,tcp_connect_init,tcp_connect
 struct tcp_congestion_ops           icsk_ca_ops            read_write                              tcp_cwnd_validate,tcp_tso_segs,tcp_ca_dst_init,tcp_connect_init,tcp_connect,tcp_write_xmit
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 055aa80b05c6d..d9978ffacc970 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -90,6 +90,7 @@ struct inet_connection_sock {
  	struct timer_list	  icsk_delack_timer;
 	__u32			  icsk_rto;
 	__u32                     icsk_rto_min;
+	u32			  icsk_rto_max;
 	__u32                     icsk_delack_max;
 	__u32			  icsk_pmtu_cookie;
 	const struct tcp_congestion_ops *icsk_ca_ops;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 56557b0104e3f..7fd2d7fa4532b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -143,8 +143,9 @@ static_assert((1 << ATO_BITS) > TCP_DELACK_MAX);
 #define TCP_DELACK_MIN	4U
 #define TCP_ATO_MIN	4U
 #endif
-#define TCP_RTO_MAX	((unsigned)(120*HZ))
-#define TCP_RTO_MIN	((unsigned)(HZ/5))
+#define TCP_RTO_MAX_SEC 120
+#define TCP_RTO_MAX	((unsigned)(TCP_RTO_MAX_SEC * HZ))
+#define TCP_RTO_MIN	((unsigned)(HZ / 5))
 #define TCP_TIMEOUT_MIN	(2U) /* Min timeout for TCP timers in jiffies */
 
 #define TCP_TIMEOUT_MIN_US (2*USEC_PER_MSEC) /* Min TCP timeout in microsecs */
@@ -740,10 +741,14 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu);
 int tcp_mss_to_mtu(struct sock *sk, int mss);
 void tcp_mtup_init(struct sock *sk);
 
+static inline unsigned int tcp_rto_max(const struct sock *sk)
+{
+	return READ_ONCE(inet_csk(sk)->icsk_rto_max);
+}
+
 static inline void tcp_bound_rto(struct sock *sk)
 {
-	if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
-		inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
+	inet_csk(sk)->icsk_rto = min(inet_csk(sk)->icsk_rto, tcp_rto_max(sk));
 }
 
 static inline u32 __tcp_set_rto(const struct tcp_sock *tp)
@@ -1428,7 +1433,8 @@ static inline void tcp_reset_xmit_timer(struct sock *sk,
 {
 	if (pace_delay)
 		when += tcp_pacing_delay(sk);
-	inet_csk_reset_xmit_timer(sk, what, when, TCP_RTO_MAX);
+	inet_csk_reset_xmit_timer(sk, what, when,
+				  tcp_rto_max(sk));
 }
 
 /* Something is really bad, we could not queue an additional packet,
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index dbf896f3146c5..32a27b4a5020a 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -136,6 +136,7 @@ enum {
 #define TCP_AO_REPAIR		42	/* Get/Set SNEs and ISNs */
 
 #define TCP_IS_MPTCP		43	/* Is MPTCP being used? */
+#define TCP_RTO_MAX_MS		44	/* max rto time in ms */
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2021f2709ec32..3bb8fbbb01d98 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -432,6 +432,10 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
+
+	/* Use a sysctl ? */
+	icsk->icsk_rto_max = TCP_RTO_MAX;
+
 	rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us);
 	icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
@@ -3807,6 +3811,11 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			   secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ,
 					   TCP_RTO_MAX / HZ));
 		return 0;
+	case TCP_RTO_MAX_MS:
+		if (val < MSEC_PER_SEC || val > TCP_RTO_MAX_SEC * MSEC_PER_SEC)
+			return -EINVAL;
+		WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val));
+		return 0;
 	}
 
 	sockopt_lock_sock(sk);
@@ -4643,6 +4652,9 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_IS_MPTCP:
 		val = 0;
 		break;
+	case TCP_RTO_MAX_MS:
+		val = jiffies_to_msecs(tcp_rto_max(sk));
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9153fae2ebd81..4686783b70def 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3558,7 +3558,7 @@ static void tcp_ack_probe(struct sock *sk)
 		 * This function is not for random using!
 		 */
 	} else {
-		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
+		unsigned long when = tcp_probe0_when(sk, tcp_rto_max(sk));
 
 		when = tcp_clamp_probe0_to_user_timeout(sk, when);
 		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, when, true);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e065f7097611b..06fb0123d2d60 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -458,7 +458,7 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq)
 
 	icsk->icsk_backoff--;
 	icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT;
-	icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX);
+	icsk->icsk_rto = inet_csk_rto_backoff(icsk, tcp_rto_max(sk));
 
 	tcp_mstamp_refresh(tp);
 	delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb));
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3623d19b7c6ed..464232a0d6379 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4251,7 +4251,7 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 		unsigned long delay;
 
 		delay = TCP_DELACK_MAX << icsk->icsk_ack.retry;
-		if (delay < TCP_RTO_MAX)
+		if (delay < tcp_rto_max(sk))
 			icsk->icsk_ack.retry++;
 		inet_csk_schedule_ack(sk);
 		icsk->icsk_ack.ato = TCP_ATO_MIN;
@@ -4391,7 +4391,7 @@ void tcp_send_probe0(struct sock *sk)
 	if (err <= 0) {
 		if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
 			icsk->icsk_backoff++;
-		timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
+		timeout = tcp_probe0_when(sk, tcp_rto_max(sk));
 	} else {
 		/* If packet was not sent due to local congestion,
 		 * Let senders fight for local resources conservatively.
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6472f560f6539..c0e601e4f39c1 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -109,7 +109,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
 
 	/* If peer does not open window for long time, or did not transmit
 	 * anything for long time, penalize it. */
-	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
+	if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset)
 		shift++;
 
 	/* If some dubious ICMP arrived, penalize even more. */
@@ -189,12 +189,12 @@ static unsigned int tcp_model_timeout(struct sock *sk,
 {
 	unsigned int linear_backoff_thresh, timeout;
 
-	linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base);
+	linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base);
 	if (boundary <= linear_backoff_thresh)
 		timeout = ((2 << boundary) - 1) * rto_base;
 	else
 		timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
-			(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+			(boundary - linear_backoff_thresh) * tcp_rto_max(sk);
 	return jiffies_to_msecs(timeout);
 }
 /**
@@ -268,7 +268,7 @@ static int tcp_write_timeout(struct sock *sk)
 
 		retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
 		if (sock_flag(sk, SOCK_DEAD)) {
-			const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
+			const bool alive = icsk->icsk_rto < tcp_rto_max(sk);
 
 			retry_until = tcp_orphan_retries(sk, alive);
 			do_reset = alive ||
@@ -416,7 +416,8 @@ static void tcp_probe_timer(struct sock *sk)
 	}
 	max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
 	if (sock_flag(sk, SOCK_DEAD)) {
-		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
+		unsigned int rto_max = tcp_rto_max(sk);
+		const bool alive = inet_csk_rto_backoff(icsk, rto_max) < rto_max;
 
 		max_probes = tcp_orphan_retries(sk, alive);
 		if (!alive && icsk->icsk_backoff >= max_probes)
@@ -492,7 +493,7 @@ static bool tcp_rtx_probe0_timed_out(const struct sock *sk,
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout);
 	const struct tcp_sock *tp = tcp_sk(sk);
-	int timeout = TCP_RTO_MAX * 2;
+	int timeout = tcp_rto_max(sk) * 2;
 	s32 rcv_delta;
 
 	if (user_timeout) {
@@ -665,7 +666,7 @@ void tcp_retransmit_timer(struct sock *sk)
 		icsk->icsk_backoff = 0;
 		icsk->icsk_rto = clamp(__tcp_set_rto(tp),
 				       tcp_rto_min(sk),
-				       TCP_RTO_MAX);
+				       tcp_rto_max(sk));
 	} else if (sk->sk_state != TCP_SYN_SENT ||
 		   tp->total_rto >
 		   READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
@@ -673,7 +674,7 @@ void tcp_retransmit_timer(struct sock *sk)
 		 * activated.
 		 */
 		icsk->icsk_backoff++;
-		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
+		icsk->icsk_rto = min(icsk->icsk_rto << 1, tcp_rto_max(sk));
 	}
 	tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 			     tcp_clamp_rto_to_user_timeout(sk), false);

From 1280c26228bd7eb14bdecd67dedbdd871f8fdda5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Feb 2025 15:28:30 +0000
Subject: [PATCH 0422/2753] tcp: add tcp_rto_max_ms sysctl

Previous patch added a TCP_RTO_MAX_MS socket option
to tune a TCP socket max RTO value.

Many setups prefer to change a per netns sysctl.

This patch adds /proc/sys/net/ipv4/tcp_rto_max_ms

Its initial value is 120000 (120 seconds).

Keep in mind that a decrease of tcp_rto_max_ms
means shorter overall timeouts, unless tcp_retries2
sysctl is increased.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/ip-sysctl.rst              | 13 +++++++++++++
 .../networking/net_cachelines/netns_ipv4_sysctl.rst |  1 +
 include/net/netns/ipv4.h                            |  1 +
 net/ipv4/sysctl_net_ipv4.c                          | 10 ++++++++++
 net/ipv4/tcp.c                                      |  6 +++---
 net/ipv4/tcp_ipv4.c                                 |  1 +
 6 files changed, 29 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 363b4950d542a..054561f8dcae7 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -705,6 +705,8 @@ tcp_retries2 - INTEGER
 	seconds and is a lower bound for the effective timeout.
 	TCP will effectively time out at the first RTO which exceeds the
 	hypothetical timeout.
+	If tcp_rto_max_ms is decreased, it is recommended to also
+	change tcp_retries2.
 
 	RFC 1122 recommends at least 100 seconds for the timeout,
 	which corresponds to a value of at least 8.
@@ -1237,6 +1239,17 @@ tcp_rto_min_us - INTEGER
 
 	Default: 200000
 
+tcp_rto_max_ms - INTEGER
+	Maximal TCP retransmission timeout (in ms).
+	Note that TCP_RTO_MAX_MS socket option has higher precedence.
+
+	When changing tcp_rto_max_ms, it is important to understand
+	that tcp_retries2 might need a change.
+
+	Possible Values: 1000 - 120,000
+
+	Default: 120,000
+
 UDP variables
 =============
 
diff --git a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
index de0263302f16d..6e7b20afd2d49 100644
--- a/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
+++ b/Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst
@@ -86,6 +86,7 @@ u8                              sysctl_tcp_sack
 u8                              sysctl_tcp_window_scaling                                                            tcp_syn_options,tcp_parse_options
 u8                              sysctl_tcp_timestamps
 u8                              sysctl_tcp_early_retrans                     read_mostly                             tcp_schedule_loss_probe(tcp_write_xmit)
+u32                             sysctl_tcp_rto_max_ms
 u8                              sysctl_tcp_recovery                                                                  tcp_fastretrans_alert
 u8                              sysctl_tcp_thin_linear_timeouts                                                      tcp_retrans_timer(on_thin_streams)
 u8                              sysctl_tcp_slow_start_after_idle                                                     unlikely(tcp_cwnd_validate-network-not-starved)
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 46452da352061..45ac125e8aebb 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -181,6 +181,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
 	int sysctl_tcp_rto_min_us;
+	int sysctl_tcp_rto_max_ms;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 42cb5dc9cb245..3a43010d726fb 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -28,6 +28,7 @@ static int tcp_adv_win_scale_max = 31;
 static int tcp_app_win_max = 31;
 static int tcp_min_snd_mss_min = TCP_MIN_SND_MSS;
 static int tcp_min_snd_mss_max = 65535;
+static int tcp_rto_max_max = TCP_RTO_MAX_SEC * MSEC_PER_SEC;
 static int ip_privileged_port_min;
 static int ip_privileged_port_max = 65535;
 static int ip_ttl_min = 1;
@@ -1583,6 +1584,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dointvec_minmax,
 		.extra1		= SYSCTL_ONE,
 	},
+	{
+		.procname	= "tcp_rto_max_ms",
+		.data		= &init_net.ipv4.sysctl_tcp_rto_max_ms,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE_THOUSAND,
+		.extra2		= &tcp_rto_max_max,
+	},
 };
 
 static __net_init int ipv4_sysctl_init_net(struct net *net)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3bb8fbbb01d98..992d5c9b2487c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -423,7 +423,7 @@ void tcp_init_sock(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
-	int rto_min_us;
+	int rto_min_us, rto_max_ms;
 
 	tp->out_of_order_queue = RB_ROOT;
 	sk->tcp_rtx_queue = RB_ROOT;
@@ -433,8 +433,8 @@ void tcp_init_sock(struct sock *sk)
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 
-	/* Use a sysctl ? */
-	icsk->icsk_rto_max = TCP_RTO_MAX;
+	rto_max_ms = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_max_ms);
+	icsk->icsk_rto_max = msecs_to_jiffies(rto_max_ms);
 
 	rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us);
 	icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 06fb0123d2d60..d1fd2128ac6cc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3532,6 +3532,7 @@ static int __net_init tcp_sk_init(struct net *net)
 
 	net->ipv4.sysctl_tcp_pingpong_thresh = 1;
 	net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN);
+	net->ipv4.sysctl_tcp_rto_max_ms = TCP_RTO_MAX_SEC * MSEC_PER_SEC;
 
 	return 0;
 }

From 86ede0a61f8576a84bb0a93c5d9861d2ec1cdf9a Mon Sep 17 00:00:00 2001
From: Christian Marangi <ansuelsmth@gmail.com>
Date: Sun, 9 Feb 2025 15:09:38 +0100
Subject: [PATCH 0423/2753] mtd: rawnand: qcom: fix broken config in
 qcom_param_page_type_exec

Fix broken config in qcom_param_page_type_exec caused by copy-paste error
from commit 0c08080fd71c ("mtd: rawnand: qcom: use FIELD_PREP and GENMASK")

In qcom_param_page_type_exec the value needs to be set to
nandc->regs->cfg0 instead of host->cfg0. This wrong configuration caused
the Qcom NANDC driver to malfunction on any device that makes use of it
(IPQ806x, IPQ40xx, IPQ807x, IPQ60xx) with the following error:

[    0.885369] nand: device found, Manufacturer ID: 0x2c, Chip ID: 0xaa
[    0.885909] nand: Micron NAND 256MiB 1,8V 8-bit
[    0.892499] nand: 256 MiB, SLC, erase size: 128 KiB, page size: 2048, OOB size: 64
[    0.896823] nand: ECC (step, strength) = (512, 8) does not fit in OOB
[    0.896836] qcom-nandc 79b0000.nand-controller: No valid ECC settings possible
[    0.910996] bam-dma-engine 7984000.dma-controller: Cannot free busy channel
[    0.918070] qcom-nandc: probe of 79b0000.nand-controller failed with error -28

Restore original configuration fix the problem and makes the driver work
again.

Also restore the wrongly dropped cpu_to_le32 to correctly support BE
systems.

Cc: stable@vger.kernel.org
Fixes: 0c08080fd71c ("mtd: rawnand: qcom: use FIELD_PREP and GENMASK")
Tested-by: Robert Marko <robimarko@gmail.com> # IPQ8074 and IPQ6018
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/qcom_nandc.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index d2d2aeee42a7e..6720b547892ba 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1881,18 +1881,18 @@ static int qcom_param_page_type_exec(struct nand_chip *chip,  const struct nand_
 	nandc->regs->addr0 = 0;
 	nandc->regs->addr1 = 0;
 
-	host->cfg0 = FIELD_PREP(CW_PER_PAGE_MASK, 0) |
-		     FIELD_PREP(UD_SIZE_BYTES_MASK, 512) |
-		     FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) |
-		     FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0);
-
-	host->cfg1 = FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) |
-		     FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) |
-		     FIELD_PREP(CS_ACTIVE_BSY, 0) |
-		     FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) |
-		     FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) |
-		     FIELD_PREP(WIDE_FLASH, 0) |
-		     FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1);
+	nandc->regs->cfg0 = cpu_to_le32(FIELD_PREP(CW_PER_PAGE_MASK, 0) |
+					FIELD_PREP(UD_SIZE_BYTES_MASK, 512) |
+					FIELD_PREP(NUM_ADDR_CYCLES_MASK, 5) |
+					FIELD_PREP(SPARE_SIZE_BYTES_MASK, 0));
+
+	nandc->regs->cfg1 = cpu_to_le32(FIELD_PREP(NAND_RECOVERY_CYCLES_MASK, 7) |
+					FIELD_PREP(BAD_BLOCK_BYTE_NUM_MASK, 17) |
+					FIELD_PREP(CS_ACTIVE_BSY, 0) |
+					FIELD_PREP(BAD_BLOCK_IN_SPARE_AREA, 1) |
+					FIELD_PREP(WR_RD_BSY_GAP_MASK, 2) |
+					FIELD_PREP(WIDE_FLASH, 0) |
+					FIELD_PREP(DEV0_CFG1_ECC_DISABLE, 1));
 
 	if (!nandc->props->qpic_version2)
 		nandc->regs->ecc_buf_cfg = cpu_to_le32(ECC_CFG_ECC_DISABLE);

From cb53a6785ea5b0a14e7e5af4322bee3df266e949 Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Sat, 1 Feb 2025 22:13:01 +0100
Subject: [PATCH 0424/2753] wifi: ath12k: add support of station average signal
 strength

This adds support for reporting to the kernel the average rssi. This is
done the same way as it was done in ath11k. A simple ewma (with the same
parameters) is updated with each rssi update.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250201211301.357985-1-nico.escande@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h   | 4 ++++
 drivers/net/wireless/ath/ath12k/dp_mon.c | 2 ++
 drivers/net/wireless/ath/ath12k/mac.c    | 8 ++++++++
 3 files changed, 14 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 57e71ccbbb674..3dcdedf9e9de1 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -15,6 +15,7 @@
 #include <linux/ctype.h>
 #include <linux/firmware.h>
 #include <linux/panic_notifier.h>
+#include <linux/average.h>
 #include "qmi.h"
 #include "htc.h"
 #include "wmi.h"
@@ -483,6 +484,8 @@ struct ath12k_wbm_tx_stats {
 	u64 wbm_tx_comp_stats[HAL_WBM_REL_HTT_TX_COMP_STATUS_MAX];
 };
 
+DECLARE_EWMA(avg_rssi, 10, 8)
+
 struct ath12k_link_sta {
 	struct ath12k_link_vif *arvif;
 	struct ath12k_sta *ahsta;
@@ -502,6 +505,7 @@ struct ath12k_link_sta {
 	u64 rx_duration;
 	u64 tx_duration;
 	u8 rssi_comb;
+	struct ewma_avg_rssi avg_rssi;
 	u8 link_id;
 	struct ath12k_rx_peer_stats *rx_stats;
 	struct ath12k_wbm_tx_stats *wbm_tx_stats;
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 4e9a60181c067..d529229f2d0fa 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2002,6 +2002,7 @@ static void ath12k_dp_mon_rx_update_peer_su_stats(struct ath12k *ar,
 		return;
 
 	arsta->rssi_comb = ppdu_info->rssi_comb;
+	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
 
 	num_msdu = ppdu_info->tcp_msdu_count + ppdu_info->tcp_ack_msdu_count +
 		   ppdu_info->udp_msdu_count + ppdu_info->other_msdu_count;
@@ -2174,6 +2175,7 @@ ath12k_dp_mon_rx_update_user_stats(struct ath12k *ar,
 		return;
 
 	arsta->rssi_comb = ppdu_info->rssi_comb;
+	ewma_avg_rssi_add(&arsta->avg_rssi, ppdu_info->rssi_comb);
 
 	num_msdu = user_stats->tcp_msdu_count + user_stats->tcp_ack_msdu_count +
 		   user_stats->udp_msdu_count + user_stats->other_msdu_count;
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 16e6f2fae943d..fc5cfd860d4d6 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -5519,6 +5519,7 @@ static int ath12k_mac_station_add(struct ath12k *ar,
 		}
 	}
 
+	ewma_avg_rssi_init(&arsta->avg_rssi);
 	return 0;
 
 free_peer:
@@ -10197,6 +10198,13 @@ static void ath12k_mac_op_sta_statistics(struct ieee80211_hw *hw,
 		sinfo->signal = db2dbm ? signal : signal + ATH12K_DEFAULT_NOISE_FLOOR;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL);
 	}
+
+	sinfo->signal_avg = ewma_avg_rssi_read(&arsta->avg_rssi);
+
+	if (!db2dbm)
+		sinfo->signal_avg += ATH12K_DEFAULT_NOISE_FLOOR;
+
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
 }
 
 static int ath12k_mac_op_cancel_remain_on_channel(struct ieee80211_hw *hw,

From a5f3c2b89136f13f18ea64fc1144691ca771b98b Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:46 +0530
Subject: [PATCH 0425/2753] wifi: ath12k: Add HAL_PHYRX_GENERIC_U_SIG TLV
 parsing support

Currently, monitor is not enabled. However, in the future, the monitor
will be enabled. Therefore, add the necessary HAL_PHYRX_GENERIC_U_SIG TLV
parsing support in monitor Rx path, which help to populate the EHT
radiotap data.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-2-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 205 ++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/hal_rx.h |  60 +++++++
 2 files changed, 264 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index d529229f2d0fa..3b0b759585890 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -10,6 +10,9 @@
 #include "dp_tx.h"
 #include "peer.h"
 
+#define ATH12K_LE32_DEC_ENC(value, dec_bits, enc_bits)	\
+		u32_encode_bits(le32_get_bits(value, dec_bits), enc_bits)
+
 static void
 ath12k_dp_mon_rx_handle_ofdma_info(const struct hal_rx_ppdu_end_user_stats *ppdu_end_user,
 				   struct hal_rx_user_status *rx_user_status)
@@ -562,6 +565,187 @@ static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *
 	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
 }
 
+static void
+ath12k_dp_mon_hal_rx_parse_u_sig_cmn(const struct hal_mon_usig_cmn *cmn,
+				     struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	u32 common;
+	u8 bw;
+
+	bw = le32_get_bits(cmn->info0, HAL_RX_USIG_CMN_INFO0_BW);
+
+	common = __le32_to_cpu(ppdu_info->usig.common);
+	common |= IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER_KNOWN |
+		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_KNOWN |
+		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL_KNOWN |
+		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR_KNOWN |
+		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP_KNOWN |
+		  ATH12K_LE32_DEC_ENC(cmn->info0,
+				      HAL_RX_USIG_CMN_INFO0_PHY_VERSION,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER) |
+		  u32_encode_bits(bw, IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW) |
+		  ATH12K_LE32_DEC_ENC(cmn->info0,
+				      HAL_RX_USIG_CMN_INFO0_UL_DL,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL) |
+		  ATH12K_LE32_DEC_ENC(cmn->info0,
+				      HAL_RX_USIG_CMN_INFO0_BSS_COLOR,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR) |
+		  ATH12K_LE32_DEC_ENC(cmn->info0,
+				      HAL_RX_USIG_CMN_INFO0_TXOP,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP);
+	ppdu_info->usig.common = cpu_to_le32(common);
+
+	switch (bw) {
+	default:
+		fallthrough;
+	case HAL_EHT_BW_20:
+		ppdu_info->bw = HAL_RX_BW_20MHZ;
+		break;
+	case HAL_EHT_BW_40:
+		ppdu_info->bw = HAL_RX_BW_40MHZ;
+		break;
+	case HAL_EHT_BW_80:
+		ppdu_info->bw = HAL_RX_BW_80MHZ;
+		break;
+	case HAL_EHT_BW_160:
+		ppdu_info->bw = HAL_RX_BW_160MHZ;
+		break;
+	case HAL_EHT_BW_320_1:
+	case HAL_EHT_BW_320_2:
+		ppdu_info->bw = HAL_RX_BW_320MHZ;
+		break;
+	}
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_u_sig_tb(const struct hal_mon_usig_tb *usig_tb,
+				    struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	enum ieee80211_radiotap_eht_usig_tb spatial_reuse1, spatial_reuse2;
+	u32 common, value, mask;
+
+	spatial_reuse1 = IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1;
+	spatial_reuse2 = IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2;
+
+	common = __le32_to_cpu(ppdu_info->usig.common);
+	value = __le32_to_cpu(ppdu_info->usig.value);
+	mask = __le32_to_cpu(ppdu_info->usig.mask);
+
+	common |= ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				      HAL_RX_USIG_TB_INFO0_RX_INTEG_CHECK_PASS,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC);
+
+	value |= IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD |
+		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				     HAL_RX_USIG_TB_INFO0_PPDU_TYPE_COMP_MODE,
+				     IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE) |
+		 IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE |
+		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				     HAL_RX_USIG_TB_INFO0_SPATIAL_REUSE_1,
+				     spatial_reuse1) |
+		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				     HAL_RX_USIG_TB_INFO0_SPATIAL_REUSE_2,
+				     spatial_reuse2) |
+		 IEEE80211_RADIOTAP_EHT_USIG2_TB_B11_B15_DISREGARD |
+		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				     HAL_RX_USIG_TB_INFO0_CRC,
+				     IEEE80211_RADIOTAP_EHT_USIG2_TB_B16_B19_CRC) |
+		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
+				     HAL_RX_USIG_TB_INFO0_TAIL,
+				     IEEE80211_RADIOTAP_EHT_USIG2_TB_B20_B25_TAIL);
+
+	mask |= IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD |
+		IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE |
+		IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE |
+		spatial_reuse1 | spatial_reuse2 |
+		IEEE80211_RADIOTAP_EHT_USIG2_TB_B11_B15_DISREGARD |
+		IEEE80211_RADIOTAP_EHT_USIG2_TB_B16_B19_CRC |
+		IEEE80211_RADIOTAP_EHT_USIG2_TB_B20_B25_TAIL;
+
+	ppdu_info->usig.common = cpu_to_le32(common);
+	ppdu_info->usig.value = cpu_to_le32(value);
+	ppdu_info->usig.mask = cpu_to_le32(mask);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_u_sig_mu(const struct hal_mon_usig_mu *usig_mu,
+				    struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	enum ieee80211_radiotap_eht_usig_mu sig_symb, punc;
+	u32 common, value, mask;
+
+	sig_symb = IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS;
+	punc = IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO;
+
+	common = __le32_to_cpu(ppdu_info->usig.common);
+	value = __le32_to_cpu(ppdu_info->usig.value);
+	mask = __le32_to_cpu(ppdu_info->usig.mask);
+
+	common |= ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				      HAL_RX_USIG_MU_INFO0_RX_INTEG_CHECK_PASS,
+				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC);
+
+	value |= IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD |
+		 IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE,
+				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE) |
+		 IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_PUNC_CH_INFO,
+				     punc) |
+		 IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_EHT_SIG_MCS,
+				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS) |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_NUM_EHT_SIG_SYM,
+				     sig_symb) |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_CRC,
+				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC) |
+		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
+				     HAL_RX_USIG_MU_INFO0_TAIL,
+				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B20_B25_TAIL);
+
+	mask |= IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD |
+		IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE |
+		punc |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS |
+		sig_symb |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC |
+		IEEE80211_RADIOTAP_EHT_USIG2_MU_B20_B25_TAIL;
+
+	ppdu_info->usig.common = cpu_to_le32(common);
+	ppdu_info->usig.value = cpu_to_le32(value);
+	ppdu_info->usig.mask = cpu_to_le32(mask);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_u_sig_hdr(const struct hal_mon_usig_hdr *usig,
+				     struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	const struct hal_mon_usig_cmn *usig_cmn = &usig->cmn;
+	u8 comp_mode;
+	bool ap_ppdu;
+
+	ppdu_info->eht_usig = true;
+
+	ath12k_dp_mon_hal_rx_parse_u_sig_cmn(&usig->cmn, ppdu_info);
+
+	ap_ppdu = le32_get_bits(usig_cmn->info0, HAL_RX_USIG_CMN_INFO0_UL_DL);
+	comp_mode = le32_get_bits(usig->non_cmn.mu.info0,
+				  HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE);
+
+	if (comp_mode == 0 && ap_ppdu)
+		ath12k_dp_mon_hal_rx_parse_u_sig_tb(&usig->non_cmn.tb, ppdu_info);
+	else
+		ath12k_dp_mon_hal_rx_parse_u_sig_mu(&usig->non_cmn.mu, ppdu_info);
+}
+
 static enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
@@ -774,6 +958,9 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 		return HAL_RX_MON_STATUS_MSDU_END;
 	case HAL_RX_MPDU_END:
 		return HAL_RX_MON_STATUS_MPDU_END;
+	case HAL_PHYRX_GENERIC_U_SIG:
+		ath12k_dp_mon_hal_rx_parse_u_sig_hdr(tlv_data, ppdu_info);
+		break;
 	case HAL_DUMMY:
 		return HAL_RX_MON_STATUS_BUF_DONE;
 	case HAL_RX_PPDU_END_STATUS_DONE:
@@ -971,7 +1158,23 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar,
 		rxs->ampdu_reference = ampdu_id;
 	}
 
-	if (ppduinfo->he_mu_flags) {
+	if (ppduinfo->eht_usig) {
+		struct ieee80211_radiotap_tlv *tlv;
+		struct ieee80211_radiotap_eht_usig *usig;
+		u16 len = sizeof(*usig);
+
+		rxs->flag |= RX_FLAG_RADIOTAP_TLV_AT_END;
+		rxs->encoding = RX_ENC_EHT;
+
+		skb_reset_mac_header(mon_skb);
+
+		tlv = skb_push(mon_skb, sizeof(*tlv) + len);
+		tlv->type = cpu_to_le16(IEEE80211_RADIOTAP_EHT_USIG);
+		tlv->len = cpu_to_le16(len);
+
+		usig = (struct ieee80211_radiotap_eht_usig *)tlv->data;
+		*usig = ppduinfo->usig;
+	} else if (ppduinfo->he_mu_flags) {
 		rxs->flag |= RX_FLAG_RADIOTAP_HE_MU;
 		rxs->encoding = RX_ENC_HE;
 		ptr = skb_push(mon_skb, sizeof(struct ieee80211_radiotap_he_mu));
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 96954b2f7ca66..2da16f27e76c9 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -235,6 +235,8 @@ struct hal_rx_mon_ppdu_info {
 	bool is_ampdu;
 	u8 medium_prot_type;
 	bool ppdu_continuation;
+	bool eht_usig;
+	struct ieee80211_radiotap_eht_usig usig;
 };
 
 #define HAL_RX_PPDU_START_INFO0_PPDU_ID			GENMASK(15, 0)
@@ -678,6 +680,64 @@ enum nl80211_he_ru_alloc ath12k_he_ru_tones_to_nl80211_he_ru_alloc(u16 ru_tones)
 	return ret;
 }
 
+enum hal_eht_bw {
+	HAL_EHT_BW_20,
+	HAL_EHT_BW_40,
+	HAL_EHT_BW_80,
+	HAL_EHT_BW_160,
+	HAL_EHT_BW_320_1,
+	HAL_EHT_BW_320_2,
+};
+
+#define HAL_RX_USIG_CMN_INFO0_PHY_VERSION	GENMASK(2, 0)
+#define HAL_RX_USIG_CMN_INFO0_BW		GENMASK(5, 3)
+#define HAL_RX_USIG_CMN_INFO0_UL_DL		BIT(6)
+#define HAL_RX_USIG_CMN_INFO0_BSS_COLOR		GENMASK(12, 7)
+#define HAL_RX_USIG_CMN_INFO0_TXOP		GENMASK(19, 13)
+#define HAL_RX_USIG_CMN_INFO0_DISREGARD		GENMASK(25, 20)
+#define HAL_RX_USIG_CMN_INFO0_VALIDATE		BIT(26)
+
+struct hal_mon_usig_cmn {
+	__le32 info0;
+} __packed;
+
+#define HAL_RX_USIG_TB_INFO0_PPDU_TYPE_COMP_MODE	GENMASK(1, 0)
+#define HAL_RX_USIG_TB_INFO0_VALIDATE			BIT(2)
+#define HAL_RX_USIG_TB_INFO0_SPATIAL_REUSE_1		GENMASK(6, 3)
+#define HAL_RX_USIG_TB_INFO0_SPATIAL_REUSE_2		GENMASK(10, 7)
+#define HAL_RX_USIG_TB_INFO0_DISREGARD_1		GENMASK(15, 11)
+#define HAL_RX_USIG_TB_INFO0_CRC			GENMASK(19, 16)
+#define HAL_RX_USIG_TB_INFO0_TAIL			GENMASK(25, 20)
+#define HAL_RX_USIG_TB_INFO0_RX_INTEG_CHECK_PASS	BIT(31)
+
+struct hal_mon_usig_tb {
+	__le32 info0;
+} __packed;
+
+#define HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE	GENMASK(1, 0)
+#define HAL_RX_USIG_MU_INFO0_VALIDATE_1			BIT(2)
+#define HAL_RX_USIG_MU_INFO0_PUNC_CH_INFO		GENMASK(7, 3)
+#define HAL_RX_USIG_MU_INFO0_VALIDATE_2			BIT(8)
+#define HAL_RX_USIG_MU_INFO0_EHT_SIG_MCS		GENMASK(10, 9)
+#define HAL_RX_USIG_MU_INFO0_NUM_EHT_SIG_SYM		GENMASK(15, 11)
+#define HAL_RX_USIG_MU_INFO0_CRC			GENMASK(20, 16)
+#define HAL_RX_USIG_MU_INFO0_TAIL			GENMASK(26, 21)
+#define HAL_RX_USIG_MU_INFO0_RX_INTEG_CHECK_PASS	BIT(31)
+
+struct hal_mon_usig_mu {
+	__le32 info0;
+} __packed;
+
+union hal_mon_usig_non_cmn {
+	struct hal_mon_usig_tb tb;
+	struct hal_mon_usig_mu mu;
+};
+
+struct hal_mon_usig_hdr {
+	struct hal_mon_usig_cmn cmn;
+	union hal_mon_usig_non_cmn non_cmn;
+} __packed;
+
 void ath12k_hal_reo_status_queue_stats(struct ath12k_base *ab,
 				       struct hal_tlv_64_hdr *tlv,
 				       struct hal_reo_status *status);

From f756f878692f688640f6994a4dacd98665a2bc2f Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:47 +0530
Subject: [PATCH 0426/2753] wifi: ath12k: Add HAL_PHYRX_GENERIC_EHT_SIG TLV
 parsing support

Currently, monitor is not enabled. However, in the future, the monitor
will be enabled. Therefore, add the necessary HAL_PHYRX_GENERIC_EHT_SIG
TLV parsing support in monitor Rx path, which help to populate the EHT
radiotap data.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-3-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 548 +++++++++++++++++++++--
 drivers/net/wireless/ath/ath12k/hal_rx.h | 136 +++++-
 2 files changed, 638 insertions(+), 46 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 3b0b759585890..0b12701beaef7 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -13,6 +13,9 @@
 #define ATH12K_LE32_DEC_ENC(value, dec_bits, enc_bits)	\
 		u32_encode_bits(le32_get_bits(value, dec_bits), enc_bits)
 
+#define ATH12K_LE64_DEC_ENC(value, dec_bits, enc_bits) \
+		u32_encode_bits(le64_get_bits(value, dec_bits), enc_bits)
+
 static void
 ath12k_dp_mon_rx_handle_ofdma_info(const struct hal_rx_ppdu_end_user_stats *ppdu_end_user,
 				   struct hal_rx_user_status *rx_user_status)
@@ -570,11 +573,13 @@ ath12k_dp_mon_hal_rx_parse_u_sig_cmn(const struct hal_mon_usig_cmn *cmn,
 				     struct hal_rx_mon_ppdu_info *ppdu_info)
 {
 	u32 common;
-	u8 bw;
 
-	bw = le32_get_bits(cmn->info0, HAL_RX_USIG_CMN_INFO0_BW);
+	ppdu_info->u_sig_info.bw = le32_get_bits(cmn->info0,
+						 HAL_RX_USIG_CMN_INFO0_BW);
+	ppdu_info->u_sig_info.ul_dl = le32_get_bits(cmn->info0,
+						    HAL_RX_USIG_CMN_INFO0_UL_DL);
 
-	common = __le32_to_cpu(ppdu_info->usig.common);
+	common = __le32_to_cpu(ppdu_info->u_sig_info.usig.common);
 	common |= IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER_KNOWN |
 		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_KNOWN |
 		  IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL_KNOWN |
@@ -583,19 +588,19 @@ ath12k_dp_mon_hal_rx_parse_u_sig_cmn(const struct hal_mon_usig_cmn *cmn,
 		  ATH12K_LE32_DEC_ENC(cmn->info0,
 				      HAL_RX_USIG_CMN_INFO0_PHY_VERSION,
 				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER) |
-		  u32_encode_bits(bw, IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW) |
-		  ATH12K_LE32_DEC_ENC(cmn->info0,
-				      HAL_RX_USIG_CMN_INFO0_UL_DL,
-				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL) |
+		  u32_encode_bits(ppdu_info->u_sig_info.bw,
+				  IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW) |
+		  u32_encode_bits(ppdu_info->u_sig_info.ul_dl,
+				  IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL) |
 		  ATH12K_LE32_DEC_ENC(cmn->info0,
 				      HAL_RX_USIG_CMN_INFO0_BSS_COLOR,
 				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR) |
 		  ATH12K_LE32_DEC_ENC(cmn->info0,
 				      HAL_RX_USIG_CMN_INFO0_TXOP,
 				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP);
-	ppdu_info->usig.common = cpu_to_le32(common);
+	ppdu_info->u_sig_info.usig.common = cpu_to_le32(common);
 
-	switch (bw) {
+	switch (ppdu_info->u_sig_info.bw) {
 	default:
 		fallthrough;
 	case HAL_EHT_BW_20:
@@ -621,24 +626,28 @@ static void
 ath12k_dp_mon_hal_rx_parse_u_sig_tb(const struct hal_mon_usig_tb *usig_tb,
 				    struct hal_rx_mon_ppdu_info *ppdu_info)
 {
+	struct ieee80211_radiotap_eht_usig *usig = &ppdu_info->u_sig_info.usig;
 	enum ieee80211_radiotap_eht_usig_tb spatial_reuse1, spatial_reuse2;
 	u32 common, value, mask;
 
 	spatial_reuse1 = IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1;
 	spatial_reuse2 = IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2;
 
-	common = __le32_to_cpu(ppdu_info->usig.common);
-	value = __le32_to_cpu(ppdu_info->usig.value);
-	mask = __le32_to_cpu(ppdu_info->usig.mask);
+	common = __le32_to_cpu(usig->common);
+	value = __le32_to_cpu(usig->value);
+	mask = __le32_to_cpu(usig->mask);
+
+	ppdu_info->u_sig_info.ppdu_type_comp_mode =
+				le32_get_bits(usig_tb->info0,
+					      HAL_RX_USIG_TB_INFO0_PPDU_TYPE_COMP_MODE);
 
 	common |= ATH12K_LE32_DEC_ENC(usig_tb->info0,
 				      HAL_RX_USIG_TB_INFO0_RX_INTEG_CHECK_PASS,
 				      IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC);
 
 	value |= IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD |
-		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
-				     HAL_RX_USIG_TB_INFO0_PPDU_TYPE_COMP_MODE,
-				     IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE) |
+		 u32_encode_bits(ppdu_info->u_sig_info.ppdu_type_comp_mode,
+				 IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE) |
 		 IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE |
 		 ATH12K_LE32_DEC_ENC(usig_tb->info0,
 				     HAL_RX_USIG_TB_INFO0_SPATIAL_REUSE_1,
@@ -662,24 +671,35 @@ ath12k_dp_mon_hal_rx_parse_u_sig_tb(const struct hal_mon_usig_tb *usig_tb,
 		IEEE80211_RADIOTAP_EHT_USIG2_TB_B16_B19_CRC |
 		IEEE80211_RADIOTAP_EHT_USIG2_TB_B20_B25_TAIL;
 
-	ppdu_info->usig.common = cpu_to_le32(common);
-	ppdu_info->usig.value = cpu_to_le32(value);
-	ppdu_info->usig.mask = cpu_to_le32(mask);
+	usig->common = cpu_to_le32(common);
+	usig->value = cpu_to_le32(value);
+	usig->mask = cpu_to_le32(mask);
 }
 
 static void
 ath12k_dp_mon_hal_rx_parse_u_sig_mu(const struct hal_mon_usig_mu *usig_mu,
 				    struct hal_rx_mon_ppdu_info *ppdu_info)
 {
+	struct ieee80211_radiotap_eht_usig *usig = &ppdu_info->u_sig_info.usig;
 	enum ieee80211_radiotap_eht_usig_mu sig_symb, punc;
 	u32 common, value, mask;
 
 	sig_symb = IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS;
 	punc = IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO;
 
-	common = __le32_to_cpu(ppdu_info->usig.common);
-	value = __le32_to_cpu(ppdu_info->usig.value);
-	mask = __le32_to_cpu(ppdu_info->usig.mask);
+	common = __le32_to_cpu(usig->common);
+	value = __le32_to_cpu(usig->value);
+	mask = __le32_to_cpu(usig->mask);
+
+	ppdu_info->u_sig_info.ppdu_type_comp_mode =
+				le32_get_bits(usig_mu->info0,
+					      HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE);
+	ppdu_info->u_sig_info.eht_sig_mcs =
+				le32_get_bits(usig_mu->info0,
+					      HAL_RX_USIG_MU_INFO0_EHT_SIG_MCS);
+	ppdu_info->u_sig_info.num_eht_sig_sym =
+				le32_get_bits(usig_mu->info0,
+					      HAL_RX_USIG_MU_INFO0_NUM_EHT_SIG_SYM);
 
 	common |= ATH12K_LE32_DEC_ENC(usig_mu->info0,
 				      HAL_RX_USIG_MU_INFO0_RX_INTEG_CHECK_PASS,
@@ -687,20 +707,17 @@ ath12k_dp_mon_hal_rx_parse_u_sig_mu(const struct hal_mon_usig_mu *usig_mu,
 
 	value |= IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD |
 		 IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE |
-		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
-				     HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE,
-				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE) |
+		 u32_encode_bits(ppdu_info->u_sig_info.ppdu_type_comp_mode,
+				 IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE) |
 		 IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE |
 		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
 				     HAL_RX_USIG_MU_INFO0_PUNC_CH_INFO,
 				     punc) |
 		 IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE |
-		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
-				     HAL_RX_USIG_MU_INFO0_EHT_SIG_MCS,
-				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS) |
-		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
-				     HAL_RX_USIG_MU_INFO0_NUM_EHT_SIG_SYM,
-				     sig_symb) |
+		 u32_encode_bits(ppdu_info->u_sig_info.eht_sig_mcs,
+				 IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS) |
+		 u32_encode_bits(ppdu_info->u_sig_info.num_eht_sig_sym,
+				 sig_symb) |
 		 ATH12K_LE32_DEC_ENC(usig_mu->info0,
 				     HAL_RX_USIG_MU_INFO0_CRC,
 				     IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC) |
@@ -719,33 +736,411 @@ ath12k_dp_mon_hal_rx_parse_u_sig_mu(const struct hal_mon_usig_mu *usig_mu,
 		IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC |
 		IEEE80211_RADIOTAP_EHT_USIG2_MU_B20_B25_TAIL;
 
-	ppdu_info->usig.common = cpu_to_le32(common);
-	ppdu_info->usig.value = cpu_to_le32(value);
-	ppdu_info->usig.mask = cpu_to_le32(mask);
+	usig->common = cpu_to_le32(common);
+	usig->value = cpu_to_le32(value);
+	usig->mask = cpu_to_le32(mask);
 }
 
 static void
 ath12k_dp_mon_hal_rx_parse_u_sig_hdr(const struct hal_mon_usig_hdr *usig,
 				     struct hal_rx_mon_ppdu_info *ppdu_info)
 {
-	const struct hal_mon_usig_cmn *usig_cmn = &usig->cmn;
 	u8 comp_mode;
-	bool ap_ppdu;
 
 	ppdu_info->eht_usig = true;
 
 	ath12k_dp_mon_hal_rx_parse_u_sig_cmn(&usig->cmn, ppdu_info);
 
-	ap_ppdu = le32_get_bits(usig_cmn->info0, HAL_RX_USIG_CMN_INFO0_UL_DL);
 	comp_mode = le32_get_bits(usig->non_cmn.mu.info0,
 				  HAL_RX_USIG_MU_INFO0_PPDU_TYPE_COMP_MODE);
 
-	if (comp_mode == 0 && ap_ppdu)
+	if (comp_mode == 0 && ppdu_info->u_sig_info.ul_dl)
 		ath12k_dp_mon_hal_rx_parse_u_sig_tb(&usig->non_cmn.tb, ppdu_info);
 	else
 		ath12k_dp_mon_hal_rx_parse_u_sig_mu(&usig->non_cmn.mu, ppdu_info);
 }
 
+static void
+ath12k_dp_mon_hal_aggr_tlv(struct hal_rx_mon_ppdu_info *ppdu_info,
+			   u16 tlv_len, const void *tlv_data)
+{
+	if (tlv_len <= HAL_RX_MON_MAX_AGGR_SIZE - ppdu_info->tlv_aggr.cur_len) {
+		memcpy(ppdu_info->tlv_aggr.buf + ppdu_info->tlv_aggr.cur_len,
+		       tlv_data, tlv_len);
+		ppdu_info->tlv_aggr.cur_len += tlv_len;
+	}
+}
+
+static inline bool
+ath12k_dp_mon_hal_rx_is_frame_type_ndp(const struct hal_rx_u_sig_info *usig_info)
+{
+	if (usig_info->ppdu_type_comp_mode == 1 &&
+	    usig_info->eht_sig_mcs == 0 &&
+	    usig_info->num_eht_sig_sym == 0)
+		return true;
+
+	return false;
+}
+
+static inline bool
+ath12k_dp_mon_hal_rx_is_non_ofdma(const struct hal_rx_u_sig_info *usig_info)
+{
+	u32 ppdu_type_comp_mode = usig_info->ppdu_type_comp_mode;
+	u32 ul_dl = usig_info->ul_dl;
+
+	if ((ppdu_type_comp_mode == HAL_RX_RECEPTION_TYPE_MU_MIMO && ul_dl == 0) ||
+	    (ppdu_type_comp_mode == HAL_RX_RECEPTION_TYPE_MU_OFDMA && ul_dl == 0) ||
+	    (ppdu_type_comp_mode == HAL_RX_RECEPTION_TYPE_MU_MIMO  && ul_dl == 1))
+		return true;
+
+	return false;
+}
+
+static inline bool
+ath12k_dp_mon_hal_rx_is_ofdma(const struct hal_rx_u_sig_info *usig_info)
+{
+	if (usig_info->ppdu_type_comp_mode == 0 && usig_info->ul_dl == 0)
+		return true;
+
+	return false;
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_eht_sig_ndp(const struct hal_eht_sig_ndp_cmn_eb *eht_sig_ndp,
+				       struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_radiotap_eht *eht = &ppdu_info->eht_info.eht;
+	u32 known, data;
+
+	known = __le32_to_cpu(eht->known);
+	known |= IEEE80211_RADIOTAP_EHT_KNOWN_SPATIAL_REUSE |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_NSS_S |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_BEAMFORMED_S |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_DISREGARD_S |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_CRC1 |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_TAIL1;
+	eht->known = cpu_to_le32(known);
+
+	data = __le32_to_cpu(eht->data[0]);
+	data |= ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_SPATIAL_REUSE,
+				    IEEE80211_RADIOTAP_EHT_DATA0_SPATIAL_REUSE);
+	/* GI and LTF size are separately indicated in radiotap header
+	 * and hence will be parsed from other TLV
+	 */
+	data |=	ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_NUM_LTF_SYM,
+				    IEEE80211_RADIOTAP_EHT_DATA0_EHT_LTF);
+
+	data |=	ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_CRC,
+				    IEEE80211_RADIOTAP_EHT_DATA0_CRC1_O);
+
+	data |= ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_DISREGARD,
+				    IEEE80211_RADIOTAP_EHT_DATA0_DISREGARD_S);
+	eht->data[0] = cpu_to_le32(data);
+
+	data = __le32_to_cpu(eht->data[7]);
+	data |=	ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_NSS,
+				    IEEE80211_RADIOTAP_EHT_DATA7_NSS_S);
+
+	data |=	ATH12K_LE32_DEC_ENC(eht_sig_ndp->info0,
+				    HAL_RX_EHT_SIG_NDP_CMN_INFO0_BEAMFORMED,
+				    IEEE80211_RADIOTAP_EHT_DATA7_BEAMFORMED_S);
+	eht->data[7] = cpu_to_le32(data);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_usig_overflow(const struct hal_eht_sig_usig_overflow *ovflow,
+					 struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_radiotap_eht *eht = &ppdu_info->eht_info.eht;
+	u32 known, data;
+
+	known = __le32_to_cpu(eht->known);
+	known |= IEEE80211_RADIOTAP_EHT_KNOWN_SPATIAL_REUSE |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_LDPC_EXTRA_SYM_OM |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_PRE_PADD_FACOR_OM |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_PE_DISAMBIGUITY_OM |
+		 IEEE80211_RADIOTAP_EHT_KNOWN_DISREGARD_O;
+	eht->known = cpu_to_le32(known);
+
+	data = __le32_to_cpu(eht->data[0]);
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_SPATIAL_REUSE,
+				    IEEE80211_RADIOTAP_EHT_DATA0_SPATIAL_REUSE);
+
+	/* GI and LTF size are separately indicated in radiotap header
+	 * and hence will be parsed from other TLV
+	 */
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_NUM_LTF_SYM,
+				    IEEE80211_RADIOTAP_EHT_DATA0_EHT_LTF);
+
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_LDPC_EXTA_SYM,
+				    IEEE80211_RADIOTAP_EHT_DATA0_LDPC_EXTRA_SYM_OM);
+
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_PRE_FEC_PAD_FACTOR,
+				    IEEE80211_RADIOTAP_EHT_DATA0_PRE_PADD_FACOR_OM);
+
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_DISAMBIGUITY,
+				    IEEE80211_RADIOTAP_EHT_DATA0_PE_DISAMBIGUITY_OM);
+
+	data |=	ATH12K_LE32_DEC_ENC(ovflow->info0,
+				    HAL_RX_EHT_SIG_OVERFLOW_INFO0_DISREGARD,
+				    IEEE80211_RADIOTAP_EHT_DATA0_DISREGARD_O);
+	eht->data[0] = cpu_to_le32(data);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_non_ofdma_users(const struct hal_eht_sig_non_ofdma_cmn_eb *eb,
+					   struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_radiotap_eht *eht = &ppdu_info->eht_info.eht;
+	u32 known, data;
+
+	known = __le32_to_cpu(eht->known);
+	known |= IEEE80211_RADIOTAP_EHT_KNOWN_NR_NON_OFDMA_USERS_M;
+	eht->known = cpu_to_le32(known);
+
+	data = __le32_to_cpu(eht->data[7]);
+	data |=	ATH12K_LE32_DEC_ENC(eb->info0,
+				    HAL_RX_EHT_SIG_NON_OFDMA_INFO0_NUM_USERS,
+				    IEEE80211_RADIOTAP_EHT_DATA7_NUM_OF_NON_OFDMA_USERS);
+	eht->data[7] = cpu_to_le32(data);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_eht_mumimo_user(const struct hal_eht_sig_mu_mimo *user,
+					   struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_eht_info *eht_info = &ppdu_info->eht_info;
+	u32 user_idx;
+
+	if (eht_info->num_user_info >= ARRAY_SIZE(eht_info->user_info))
+		return;
+
+	user_idx = eht_info->num_user_info++;
+
+	eht_info->user_info[user_idx] |=
+		IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_MCS_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_CODING_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_SPATIAL_CONFIG_KNOWN_M |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_STA_ID,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_CODING,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_CODING) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_MCS,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_MCS) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_SPATIAL_CODING,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_SPATIAL_CONFIG_M);
+
+	ppdu_info->mcs = le32_get_bits(user->info0,
+				       HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_MCS);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_eht_non_mumimo_user(const struct hal_eht_sig_non_mu_mimo *user,
+					       struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_eht_info *eht_info = &ppdu_info->eht_info;
+	u32 user_idx;
+
+	if (eht_info->num_user_info >= ARRAY_SIZE(eht_info->user_info))
+		return;
+
+	user_idx = eht_info->num_user_info++;
+
+	eht_info->user_info[user_idx] |=
+		IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_MCS_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_CODING_KNOWN |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_KNOWN_O |
+		IEEE80211_RADIOTAP_EHT_USER_INFO_BEAMFORMING_KNOWN_O |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_STA_ID,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_CODING,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_CODING) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_MCS,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_MCS) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_NSS,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O) |
+		ATH12K_LE32_DEC_ENC(user->info0,
+				    HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_BEAMFORMED,
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_BEAMFORMING_O);
+
+	ppdu_info->mcs = le32_get_bits(user->info0,
+				       HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_MCS);
+
+	ppdu_info->nss = le32_get_bits(user->info0,
+				       HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_NSS) + 1;
+}
+
+static inline bool
+ath12k_dp_mon_hal_rx_is_mu_mimo_user(const struct hal_rx_u_sig_info *usig_info)
+{
+	if (usig_info->ppdu_type_comp_mode == HAL_RX_RECEPTION_TYPE_SU &&
+	    usig_info->ul_dl == 1)
+		return true;
+
+	return false;
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_eht_sig_non_ofdma(const void *tlv,
+					     struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	const struct hal_eht_sig_non_ofdma_cmn_eb *eb = tlv;
+
+	ath12k_dp_mon_hal_rx_parse_usig_overflow(tlv, ppdu_info);
+	ath12k_dp_mon_hal_rx_parse_non_ofdma_users(eb, ppdu_info);
+
+	if (ath12k_dp_mon_hal_rx_is_mu_mimo_user(&ppdu_info->u_sig_info))
+		ath12k_dp_mon_hal_rx_parse_eht_mumimo_user(&eb->user_field.mu_mimo,
+							   ppdu_info);
+	else
+		ath12k_dp_mon_hal_rx_parse_eht_non_mumimo_user(&eb->user_field.n_mu_mimo,
+							       ppdu_info);
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_ru_allocation(const struct hal_eht_sig_ofdma_cmn_eb *eb,
+					 struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	const struct hal_eht_sig_ofdma_cmn_eb1 *ofdma_cmn_eb1 = &eb->eb1;
+	const struct hal_eht_sig_ofdma_cmn_eb2 *ofdma_cmn_eb2 = &eb->eb2;
+	struct hal_rx_radiotap_eht *eht = &ppdu_info->eht_info.eht;
+	enum ieee80211_radiotap_eht_data ru_123, ru_124, ru_125, ru_126;
+	enum ieee80211_radiotap_eht_data ru_121, ru_122, ru_112, ru_111;
+	u32 data;
+
+	ru_123 = IEEE80211_RADIOTAP_EHT_DATA4_RU_ALLOC_CC_1_2_3;
+	ru_124 = IEEE80211_RADIOTAP_EHT_DATA5_RU_ALLOC_CC_1_2_4;
+	ru_125 = IEEE80211_RADIOTAP_EHT_DATA5_RU_ALLOC_CC_1_2_5;
+	ru_126 = IEEE80211_RADIOTAP_EHT_DATA6_RU_ALLOC_CC_1_2_6;
+	ru_121 = IEEE80211_RADIOTAP_EHT_DATA3_RU_ALLOC_CC_1_2_1;
+	ru_122 = IEEE80211_RADIOTAP_EHT_DATA3_RU_ALLOC_CC_1_2_2;
+	ru_112 = IEEE80211_RADIOTAP_EHT_DATA2_RU_ALLOC_CC_1_1_2;
+	ru_111 = IEEE80211_RADIOTAP_EHT_DATA1_RU_ALLOC_CC_1_1_1;
+
+	switch (ppdu_info->u_sig_info.bw) {
+	case HAL_EHT_BW_320_2:
+	case HAL_EHT_BW_320_1:
+		data = __le32_to_cpu(eht->data[4]);
+		/* CC1 2::3 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA4_RU_ALLOC_CC_1_2_3_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_3,
+					    ru_123);
+		eht->data[4] = cpu_to_le32(data);
+
+		data = __le32_to_cpu(eht->data[5]);
+		/* CC1 2::4 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA5_RU_ALLOC_CC_1_2_4_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_4,
+					    ru_124);
+
+		/* CC1 2::5 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA5_RU_ALLOC_CC_1_2_5_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_5,
+					    ru_125);
+		eht->data[5] = cpu_to_le32(data);
+
+		data = __le32_to_cpu(eht->data[6]);
+		/* CC1 2::6 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA6_RU_ALLOC_CC_1_2_6_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_6,
+					    ru_126);
+		eht->data[6] = cpu_to_le32(data);
+
+		fallthrough;
+	case HAL_EHT_BW_160:
+		data = __le32_to_cpu(eht->data[3]);
+		/* CC1 2::1 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA3_RU_ALLOC_CC_1_2_1_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_1,
+					    ru_121);
+		/* CC1 2::2 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA3_RU_ALLOC_CC_1_2_2_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb2->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_2,
+					    ru_122);
+		eht->data[3] = cpu_to_le32(data);
+
+		fallthrough;
+	case HAL_EHT_BW_80:
+		data = __le32_to_cpu(eht->data[2]);
+		/* CC1 1::2 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA2_RU_ALLOC_CC_1_1_2_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb1->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB1_RU_ALLOC_1_2,
+					    ru_112);
+		eht->data[2] = cpu_to_le32(data);
+
+		fallthrough;
+	case HAL_EHT_BW_40:
+		fallthrough;
+	case HAL_EHT_BW_20:
+		data = __le32_to_cpu(eht->data[1]);
+		/* CC1 1::1 */
+		data |=	IEEE80211_RADIOTAP_EHT_DATA1_RU_ALLOC_CC_1_1_1_KNOWN |
+			ATH12K_LE64_DEC_ENC(ofdma_cmn_eb1->info0,
+					    HAL_RX_EHT_SIG_OFDMA_EB1_RU_ALLOC_1_1,
+					    ru_111);
+		eht->data[1] = cpu_to_le32(data);
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_eht_sig_ofdma(const void *tlv,
+					 struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	const struct hal_eht_sig_ofdma_cmn_eb *ofdma = tlv;
+
+	ath12k_dp_mon_hal_rx_parse_usig_overflow(tlv, ppdu_info);
+	ath12k_dp_mon_hal_rx_parse_ru_allocation(ofdma, ppdu_info);
+
+	ath12k_dp_mon_hal_rx_parse_eht_non_mumimo_user(&ofdma->user_field.n_mu_mimo,
+						       ppdu_info);
+}
+
+static void
+ath12k_dp_mon_parse_eht_sig_hdr(struct hal_rx_mon_ppdu_info *ppdu_info,
+				const void *tlv_data)
+{
+	ppdu_info->is_eht = true;
+
+	if (ath12k_dp_mon_hal_rx_is_frame_type_ndp(&ppdu_info->u_sig_info))
+		ath12k_dp_mon_hal_rx_parse_eht_sig_ndp(tlv_data, ppdu_info);
+	else if (ath12k_dp_mon_hal_rx_is_non_ofdma(&ppdu_info->u_sig_info))
+		ath12k_dp_mon_hal_rx_parse_eht_sig_non_ofdma(tlv_data, ppdu_info);
+	else if (ath12k_dp_mon_hal_rx_is_ofdma(&ppdu_info->u_sig_info))
+		ath12k_dp_mon_hal_rx_parse_eht_sig_ofdma(tlv_data, ppdu_info);
+}
+
 static enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
@@ -754,11 +1149,19 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 	struct hal_rx_mon_ppdu_info *ppdu_info = &pmon->mon_ppdu_info;
 	const void *tlv_data = tlv->value;
 	u32 info[7], userid;
-	u16 tlv_tag;
+	u16 tlv_tag, tlv_len;
 
 	tlv_tag = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_TAG);
+	tlv_len = le64_get_bits(tlv->tl, HAL_TLV_64_HDR_LEN);
 	userid = le64_get_bits(tlv->tl, HAL_TLV_64_USR_ID);
 
+	if (ppdu_info->tlv_aggr.in_progress && ppdu_info->tlv_aggr.tlv_tag != tlv_tag) {
+		ath12k_dp_mon_parse_eht_sig_hdr(ppdu_info, ppdu_info->tlv_aggr.buf);
+
+		ppdu_info->tlv_aggr.in_progress = false;
+		ppdu_info->tlv_aggr.cur_len = 0;
+	}
+
 	switch (tlv_tag) {
 	case HAL_RX_PPDU_START: {
 		const struct hal_rx_ppdu_start *ppdu_start = tlv_data;
@@ -836,6 +1239,9 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 		case HAL_RX_PREAMBLE_11AX:
 			ppdu_info->he_flags = 1;
 			break;
+		case HAL_RX_PREAMBLE_11BE:
+			ppdu_info->is_eht = true;
+			break;
 		default:
 			break;
 		}
@@ -961,6 +1367,21 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 	case HAL_PHYRX_GENERIC_U_SIG:
 		ath12k_dp_mon_hal_rx_parse_u_sig_hdr(tlv_data, ppdu_info);
 		break;
+	case HAL_PHYRX_GENERIC_EHT_SIG:
+		/* Handle the case where aggregation is in progress
+		 * or the current TLV is one of the TLVs which should be
+		 * aggregated
+		 */
+		if (!ppdu_info->tlv_aggr.in_progress) {
+			ppdu_info->tlv_aggr.in_progress = true;
+			ppdu_info->tlv_aggr.tlv_tag = tlv_tag;
+			ppdu_info->tlv_aggr.cur_len = 0;
+		}
+
+		ppdu_info->is_eht = true;
+
+		ath12k_dp_mon_hal_aggr_tlv(ppdu_info, tlv_len, tlv_data);
+		break;
 	case HAL_DUMMY:
 		return HAL_RX_MON_STATUS_BUF_DONE;
 	case HAL_RX_PPDU_END_STATUS_DONE:
@@ -1158,22 +1579,59 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar,
 		rxs->ampdu_reference = ampdu_id;
 	}
 
-	if (ppduinfo->eht_usig) {
+	if (ppduinfo->is_eht || ppduinfo->eht_usig) {
 		struct ieee80211_radiotap_tlv *tlv;
+		struct ieee80211_radiotap_eht *eht;
 		struct ieee80211_radiotap_eht_usig *usig;
-		u16 len = sizeof(*usig);
+		u16 len = 0, i, eht_len, usig_len;
+		u8 user;
+
+		if (ppduinfo->is_eht) {
+			eht_len = struct_size(eht,
+					      user_info,
+					      ppduinfo->eht_info.num_user_info);
+			len += sizeof(*tlv) + eht_len;
+		}
+
+		if (ppduinfo->eht_usig) {
+			usig_len = sizeof(*usig);
+			len += sizeof(*tlv) + usig_len;
+		}
 
 		rxs->flag |= RX_FLAG_RADIOTAP_TLV_AT_END;
 		rxs->encoding = RX_ENC_EHT;
 
 		skb_reset_mac_header(mon_skb);
 
-		tlv = skb_push(mon_skb, sizeof(*tlv) + len);
-		tlv->type = cpu_to_le16(IEEE80211_RADIOTAP_EHT_USIG);
-		tlv->len = cpu_to_le16(len);
+		tlv = skb_push(mon_skb, len);
+
+		if (ppduinfo->is_eht) {
+			tlv->type = cpu_to_le16(IEEE80211_RADIOTAP_EHT);
+			tlv->len = cpu_to_le16(eht_len);
 
-		usig = (struct ieee80211_radiotap_eht_usig *)tlv->data;
-		*usig = ppduinfo->usig;
+			eht = (struct ieee80211_radiotap_eht *)tlv->data;
+			eht->known = ppduinfo->eht_info.eht.known;
+
+			for (i = 0;
+			     i < ARRAY_SIZE(eht->data) &&
+			     i < ARRAY_SIZE(ppduinfo->eht_info.eht.data);
+			     i++)
+				eht->data[i] = ppduinfo->eht_info.eht.data[i];
+
+			for (user = 0; user < ppduinfo->eht_info.num_user_info; user++)
+				put_unaligned_le32(ppduinfo->eht_info.user_info[user],
+						   &eht->user_info[user]);
+
+			tlv = (struct ieee80211_radiotap_tlv *)&tlv->data[eht_len];
+		}
+
+		if (ppduinfo->eht_usig) {
+			tlv->type = cpu_to_le16(IEEE80211_RADIOTAP_EHT_USIG);
+			tlv->len = cpu_to_le16(usig_len);
+
+			usig = (struct ieee80211_radiotap_eht_usig *)tlv->data;
+			*usig = ppduinfo->u_sig_info.usig;
+		}
 	} else if (ppduinfo->he_mu_flags) {
 		rxs->flag |= RX_FLAG_RADIOTAP_HE_MU;
 		rxs->encoding = RX_ENC_HE;
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 2da16f27e76c9..959f2283294c3 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -71,6 +71,8 @@ enum hal_rx_preamble {
 	HAL_RX_PREAMBLE_11N,
 	HAL_RX_PREAMBLE_11AC,
 	HAL_RX_PREAMBLE_11AX,
+	HAL_RX_PREAMBLE_11BA,
+	HAL_RX_PREAMBLE_11BE,
 	HAL_RX_PREAMBLE_MAX,
 };
 
@@ -150,6 +152,37 @@ struct hal_rx_user_status {
 
 #define HAL_MAX_UL_MU_USERS	37
 
+struct hal_rx_u_sig_info {
+	bool ul_dl;
+	u8 bw;
+	u8 ppdu_type_comp_mode;
+	u8 eht_sig_mcs;
+	u8 num_eht_sig_sym;
+	struct ieee80211_radiotap_eht_usig usig;
+};
+
+#define HAL_RX_MON_MAX_AGGR_SIZE	128
+
+struct hal_rx_tlv_aggr_info {
+	bool in_progress;
+	u16 cur_len;
+	u16 tlv_tag;
+	u8 buf[HAL_RX_MON_MAX_AGGR_SIZE];
+};
+
+struct hal_rx_radiotap_eht {
+	__le32 known;
+	__le32 data[9];
+};
+
+#define EHT_MAX_USER_INFO	4
+
+struct hal_rx_eht_info {
+	u8 num_user_info;
+	struct hal_rx_radiotap_eht eht;
+	u32 user_info[EHT_MAX_USER_INFO];
+};
+
 struct hal_rx_mon_ppdu_info {
 	u32 ppdu_id;
 	u32 last_ppdu_id;
@@ -236,7 +269,10 @@ struct hal_rx_mon_ppdu_info {
 	u8 medium_prot_type;
 	bool ppdu_continuation;
 	bool eht_usig;
-	struct ieee80211_radiotap_eht_usig usig;
+	struct hal_rx_u_sig_info u_sig_info;
+	bool is_eht;
+	struct hal_rx_eht_info eht_info;
+	struct hal_rx_tlv_aggr_info tlv_aggr;
 };
 
 #define HAL_RX_PPDU_START_INFO0_PPDU_ID			GENMASK(15, 0)
@@ -647,6 +683,104 @@ struct hal_rx_resp_req_info {
 #define HAL_RX_MPDU_ERR_MPDU_LEN		BIT(6)
 #define HAL_RX_MPDU_ERR_UNENCRYPTED_FRAME	BIT(7)
 
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_SPATIAL_REUSE	GENMASK(3, 0)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_GI_LTF		GENMASK(5, 4)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_NUM_LTF_SYM	GENMASK(8, 6)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_NSS		GENMASK(10, 7)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_BEAMFORMED		BIT(11)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_DISREGARD		GENMASK(13, 12)
+#define HAL_RX_EHT_SIG_NDP_CMN_INFO0_CRC		GENMASK(17, 14)
+
+struct hal_eht_sig_ndp_cmn_eb {
+	__le32 info0;
+} __packed;
+
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_SPATIAL_REUSE		GENMASK(3, 0)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_GI_LTF			GENMASK(5, 4)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_NUM_LTF_SYM		GENMASK(8, 6)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_LDPC_EXTA_SYM		BIT(9)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_PRE_FEC_PAD_FACTOR	GENMASK(11, 10)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_DISAMBIGUITY		BIT(12)
+#define HAL_RX_EHT_SIG_OVERFLOW_INFO0_DISREGARD			GENMASK(16, 13)
+
+struct hal_eht_sig_usig_overflow {
+	__le32 info0;
+} __packed;
+
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_STA_ID	GENMASK(10, 0)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_MCS	GENMASK(14, 11)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_VALIDATE	BIT(15)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_NSS	GENMASK(19, 16)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_BEAMFORMED	BIT(20)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_CODING	BIT(21)
+#define HAL_RX_EHT_SIG_NON_MUMIMO_USER_INFO0_CRC	GENMASK(25, 22)
+
+struct hal_eht_sig_non_mu_mimo {
+	__le32 info0;
+} __packed;
+
+#define HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_STA_ID		GENMASK(10, 0)
+#define HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_MCS		GENMASK(14, 11)
+#define HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_CODING		BIT(15)
+#define HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_SPATIAL_CODING	GENMASK(22, 16)
+#define HAL_RX_EHT_SIG_MUMIMO_USER_INFO0_CRC		GENMASK(26, 23)
+
+struct hal_eht_sig_mu_mimo {
+	__le32 info0;
+} __packed;
+
+union hal_eht_sig_user_field {
+	struct hal_eht_sig_mu_mimo mu_mimo;
+	struct hal_eht_sig_non_mu_mimo n_mu_mimo;
+};
+
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_SPATIAL_REUSE		GENMASK(3, 0)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_GI_LTF			GENMASK(5, 4)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_NUM_LTF_SYM		GENMASK(8, 6)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_LDPC_EXTA_SYM		BIT(9)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_PRE_FEC_PAD_FACTOR	GENMASK(11, 10)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_DISAMBIGUITY		BIT(12)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_DISREGARD		GENMASK(16, 13)
+#define HAL_RX_EHT_SIG_NON_OFDMA_INFO0_NUM_USERS		GENMASK(19, 17)
+
+struct hal_eht_sig_non_ofdma_cmn_eb {
+	__le32 info0;
+	union hal_eht_sig_user_field user_field;
+} __packed;
+
+#define HAL_RX_EHT_SIG_OFDMA_EB1_SPATIAL_REUSE		GENMASK_ULL(3, 0)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_GI_LTF			GENMASK_ULL(5, 4)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_NUM_LFT_SYM		GENMASK_ULL(8, 6)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_LDPC_EXTRA_SYM		BIT(9)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_PRE_FEC_PAD_FACTOR	GENMASK_ULL(11, 10)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_PRE_DISAMBIGUITY	BIT(12)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_DISREGARD		GENMASK_ULL(16, 13)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_RU_ALLOC_1_1		GENMASK_ULL(25, 17)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_RU_ALLOC_1_2		GENMASK_ULL(34, 26)
+#define HAL_RX_EHT_SIG_OFDMA_EB1_CRC			GENMASK_ULL(30, 27)
+
+struct hal_eht_sig_ofdma_cmn_eb1 {
+	__le64 info0;
+} __packed;
+
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_1		GENMASK_ULL(8, 0)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_2		GENMASK_ULL(17, 9)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_3		GENMASK_ULL(26, 18)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_4		GENMASK_ULL(35, 27)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_5		GENMASK_ULL(44, 36)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_RU_ALLOC_2_6		GENMASK_ULL(53, 45)
+#define HAL_RX_EHT_SIG_OFDMA_EB2_MCS			GNEMASK_ULL(57, 54)
+
+struct hal_eht_sig_ofdma_cmn_eb2 {
+	__le64 info0;
+} __packed;
+
+struct hal_eht_sig_ofdma_cmn_eb {
+	struct hal_eht_sig_ofdma_cmn_eb1 eb1;
+	struct hal_eht_sig_ofdma_cmn_eb2 eb2;
+	union hal_eht_sig_user_field user_field;
+} __packed;
+
 static inline
 enum nl80211_he_ru_alloc ath12k_he_ru_tones_to_nl80211_he_ru_alloc(u16 ru_tones)
 {

From e6fa62bada8796d13f04e2538297b81decc1e335 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:48 +0530
Subject: [PATCH 0427/2753] wifi: ath12k: Add HAL_RX_PPDU_START_USER_INFO TLV
 parsing support

Currently, monitor is not enabled. However, in the future, the monitor
will be enabled. Therefore, add necessary HAL_RX_PPDU_START_USER_INFO TLV
parsing support in monitor Rx path, which help to populate the EHT radiotap
data.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-4-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c  | 307 +++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/hal_rx.h  | 291 +++++++++++++++++---
 drivers/net/wireless/ath/ath12k/rx_desc.h |   9 -
 3 files changed, 551 insertions(+), 56 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 0b12701beaef7..76b6d5861e253 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -81,7 +81,7 @@ ath12k_dp_mon_rx_populate_mu_user_info(const struct hal_rx_ppdu_end_user_stats *
 static void ath12k_dp_mon_parse_vht_sig_a(const struct hal_rx_vht_sig_a_info *vht_sig,
 					  struct hal_rx_mon_ppdu_info *ppdu_info)
 {
-	u32 nsts, group_id, info0, info1;
+	u32 nsts, info0, info1;
 	u8 gi_setting;
 
 	info0 = __le32_to_cpu(vht_sig->info0);
@@ -109,12 +109,8 @@ static void ath12k_dp_mon_parse_vht_sig_a(const struct hal_rx_vht_sig_a_info *vh
 	ppdu_info->bw = u32_get_bits(info0, HAL_RX_VHT_SIG_A_INFO_INFO0_BW);
 	ppdu_info->beamformed = u32_get_bits(info1,
 					     HAL_RX_VHT_SIG_A_INFO_INFO1_BEAMFORMED);
-	group_id = u32_get_bits(info0, HAL_RX_VHT_SIG_A_INFO_INFO0_GROUP_ID);
-	if (group_id == 0 || group_id == 63)
-		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
-	else
-		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO;
-	ppdu_info->vht_flag_values5 = group_id;
+	ppdu_info->vht_flag_values5 = u32_get_bits(info0,
+						   HAL_RX_VHT_SIG_A_INFO_INFO0_GROUP_ID);
 	ppdu_info->vht_flag_values3[0] = (((ppdu_info->mcs) << 4) |
 					    ppdu_info->nss);
 	ppdu_info->vht_flag_values2 = ppdu_info->bw;
@@ -134,7 +130,6 @@ static void ath12k_dp_mon_parse_ht_sig(const struct hal_rx_ht_sig_info *ht_sig,
 	ppdu_info->ldpc = u32_get_bits(info1, HAL_RX_HT_SIG_INFO_INFO1_FEC_CODING);
 	ppdu_info->gi = u32_get_bits(info1, HAL_RX_HT_SIG_INFO_INFO1_GI);
 	ppdu_info->nss = (ppdu_info->mcs >> 3);
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
 }
 
 static void ath12k_dp_mon_parse_l_sig_b(const struct hal_rx_lsig_b_info *lsigb,
@@ -166,7 +161,6 @@ static void ath12k_dp_mon_parse_l_sig_b(const struct hal_rx_lsig_b_info *lsigb,
 
 	ppdu_info->rate = rate;
 	ppdu_info->cck_flag = 1;
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
 }
 
 static void ath12k_dp_mon_parse_l_sig_a(const struct hal_rx_lsig_a_info *lsiga,
@@ -206,7 +200,6 @@ static void ath12k_dp_mon_parse_l_sig_a(const struct hal_rx_lsig_a_info *lsiga,
 	}
 
 	ppdu_info->rate = rate;
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
 }
 
 static void
@@ -243,7 +236,6 @@ ath12k_dp_mon_parse_he_sig_b2_ofdma(const struct hal_rx_he_sig_b2_ofdma_info *of
 	ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_NSTS);
 	ppdu_info->beamformed = u32_get_bits(info0,
 					     HAL_RX_HE_SIG_B2_OFDMA_INFO_INFO0_STA_TXBF);
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_OFDMA;
 }
 
 static void
@@ -283,7 +275,6 @@ ath12k_dp_mon_parse_he_sig_b1_mu(const struct hal_rx_he_sig_b1_mu_info *he_sig_b
 				HAL_RX_HE_SIG_B1_MU_INFO_INFO0_RU_ALLOCATION);
 	ppdu_info->ru_alloc = ath12k_he_ru_tones_to_nl80211_he_ru_alloc(ru_tones);
 	ppdu_info->he_RU[0] = ru_tones;
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO;
 }
 
 static void
@@ -417,7 +408,6 @@ ath12k_dp_mon_parse_he_sig_mu(const struct hal_rx_he_sig_a_mu_dl_info *he_sig_a_
 
 	ppdu_info->is_stbc = info1 &
 			     HAL_RX_HE_SIG_A_MU_DL_INFO1_STBC;
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO;
 }
 
 static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *he_sig_a,
@@ -565,7 +555,6 @@ static void ath12k_dp_mon_parse_he_sig_su(const struct hal_rx_he_sig_a_su_info *
 	dcm = u32_get_bits(info0, HAL_RX_HE_SIG_A_SU_INFO_INFO0_DCM);
 	ppdu_info->nss = u32_get_bits(info0, HAL_RX_HE_SIG_A_SU_INFO_INFO0_NSTS);
 	ppdu_info->dcm = dcm;
-	ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
 }
 
 static void
@@ -1141,6 +1130,292 @@ ath12k_dp_mon_parse_eht_sig_hdr(struct hal_rx_mon_ppdu_info *ppdu_info,
 		ath12k_dp_mon_hal_rx_parse_eht_sig_ofdma(tlv_data, ppdu_info);
 }
 
+static inline enum ath12k_eht_ru_size
+hal_rx_mon_hal_ru_size_to_ath12k_ru_size(u32 hal_ru_size)
+{
+	switch (hal_ru_size) {
+	case HAL_EHT_RU_26:
+		return ATH12K_EHT_RU_26;
+	case HAL_EHT_RU_52:
+		return ATH12K_EHT_RU_52;
+	case HAL_EHT_RU_78:
+		return ATH12K_EHT_RU_52_26;
+	case HAL_EHT_RU_106:
+		return ATH12K_EHT_RU_106;
+	case HAL_EHT_RU_132:
+		return ATH12K_EHT_RU_106_26;
+	case HAL_EHT_RU_242:
+		return ATH12K_EHT_RU_242;
+	case HAL_EHT_RU_484:
+		return ATH12K_EHT_RU_484;
+	case HAL_EHT_RU_726:
+		return ATH12K_EHT_RU_484_242;
+	case HAL_EHT_RU_996:
+		return ATH12K_EHT_RU_996;
+	case HAL_EHT_RU_996x2:
+		return ATH12K_EHT_RU_996x2;
+	case HAL_EHT_RU_996x3:
+		return ATH12K_EHT_RU_996x3;
+	case HAL_EHT_RU_996x4:
+		return ATH12K_EHT_RU_996x4;
+	case HAL_EHT_RU_NONE:
+		return ATH12K_EHT_RU_INVALID;
+	case HAL_EHT_RU_996_484:
+		return ATH12K_EHT_RU_996_484;
+	case HAL_EHT_RU_996x2_484:
+		return ATH12K_EHT_RU_996x2_484;
+	case HAL_EHT_RU_996x3_484:
+		return ATH12K_EHT_RU_996x3_484;
+	case HAL_EHT_RU_996_484_242:
+		return ATH12K_EHT_RU_996_484_242;
+	default:
+		return ATH12K_EHT_RU_INVALID;
+	}
+}
+
+static inline u32
+hal_rx_ul_ofdma_ru_size_to_width(enum ath12k_eht_ru_size ru_size)
+{
+	switch (ru_size) {
+	case ATH12K_EHT_RU_26:
+		return RU_26;
+	case ATH12K_EHT_RU_52:
+		return RU_52;
+	case ATH12K_EHT_RU_52_26:
+		return RU_52_26;
+	case ATH12K_EHT_RU_106:
+		return RU_106;
+	case ATH12K_EHT_RU_106_26:
+		return RU_106_26;
+	case ATH12K_EHT_RU_242:
+		return RU_242;
+	case ATH12K_EHT_RU_484:
+		return RU_484;
+	case ATH12K_EHT_RU_484_242:
+		return RU_484_242;
+	case ATH12K_EHT_RU_996:
+		return RU_996;
+	case ATH12K_EHT_RU_996_484:
+		return RU_996_484;
+	case ATH12K_EHT_RU_996_484_242:
+		return RU_996_484_242;
+	case ATH12K_EHT_RU_996x2:
+		return RU_2X996;
+	case ATH12K_EHT_RU_996x2_484:
+		return RU_2X996_484;
+	case ATH12K_EHT_RU_996x3:
+		return RU_3X996;
+	case ATH12K_EHT_RU_996x3_484:
+		return RU_3X996_484;
+	case ATH12K_EHT_RU_996x4:
+		return RU_4X996;
+	default:
+		return RU_INVALID;
+	}
+}
+
+static void
+ath12k_dp_mon_hal_rx_parse_user_info(const struct hal_receive_user_info *rx_usr_info,
+				     u16 user_id,
+				     struct hal_rx_mon_ppdu_info *ppdu_info)
+{
+	struct hal_rx_user_status *mon_rx_user_status = NULL;
+	struct hal_rx_radiotap_eht *eht = &ppdu_info->eht_info.eht;
+	enum ath12k_eht_ru_size rtap_ru_size = ATH12K_EHT_RU_INVALID;
+	u32 ru_width, reception_type, ru_index = HAL_EHT_RU_INVALID;
+	u32 ru_type_80_0, ru_start_index_80_0;
+	u32 ru_type_80_1, ru_start_index_80_1;
+	u32 ru_type_80_2, ru_start_index_80_2;
+	u32 ru_type_80_3, ru_start_index_80_3;
+	u32 ru_size = 0, num_80mhz_with_ru = 0;
+	u64 ru_index_320mhz = 0;
+	u32 ru_index_per80mhz;
+
+	reception_type = le32_get_bits(rx_usr_info->info0,
+				       HAL_RX_USR_INFO0_RECEPTION_TYPE);
+
+	switch (reception_type) {
+	case HAL_RECEPTION_TYPE_SU:
+		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_SU;
+		break;
+	case HAL_RECEPTION_TYPE_DL_MU_MIMO:
+	case HAL_RECEPTION_TYPE_UL_MU_MIMO:
+		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_MIMO;
+		break;
+	case HAL_RECEPTION_TYPE_DL_MU_OFMA:
+	case HAL_RECEPTION_TYPE_UL_MU_OFDMA:
+		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_OFDMA;
+		break;
+	case HAL_RECEPTION_TYPE_DL_MU_OFDMA_MIMO:
+	case HAL_RECEPTION_TYPE_UL_MU_OFDMA_MIMO:
+		ppdu_info->reception_type = HAL_RX_RECEPTION_TYPE_MU_OFDMA_MIMO;
+	}
+
+	ppdu_info->is_stbc = le32_get_bits(rx_usr_info->info0, HAL_RX_USR_INFO0_STBC);
+	ppdu_info->ldpc = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_LDPC);
+	ppdu_info->dcm = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_STA_DCM);
+	ppdu_info->bw = le32_get_bits(rx_usr_info->info1, HAL_RX_USR_INFO1_RX_BW);
+	ppdu_info->mcs = le32_get_bits(rx_usr_info->info1, HAL_RX_USR_INFO1_MCS);
+	ppdu_info->nss = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_NSS) + 1;
+
+	if (user_id < HAL_MAX_UL_MU_USERS) {
+		mon_rx_user_status = &ppdu_info->userstats[user_id];
+		mon_rx_user_status->mcs = ppdu_info->mcs;
+		mon_rx_user_status->nss = ppdu_info->nss;
+	}
+
+	if (!(ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_MU_MIMO ||
+	      ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_MU_OFDMA ||
+	      ppdu_info->reception_type == HAL_RX_RECEPTION_TYPE_MU_OFDMA_MIMO))
+		return;
+
+	/* RU allocation present only for OFDMA reception */
+	ru_type_80_0 = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_RU_TYPE_80_0);
+	ru_start_index_80_0 = le32_get_bits(rx_usr_info->info3,
+					    HAL_RX_USR_INFO3_RU_START_IDX_80_0);
+	if (ru_type_80_0 != HAL_EHT_RU_NONE) {
+		ru_size += ru_type_80_0;
+		ru_index_per80mhz = ru_start_index_80_0;
+		ru_index = ru_index_per80mhz;
+		ru_index_320mhz |= HAL_RU_PER80(ru_type_80_0, 0, ru_index_per80mhz);
+		num_80mhz_with_ru++;
+	}
+
+	ru_type_80_1 = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_RU_TYPE_80_1);
+	ru_start_index_80_1 = le32_get_bits(rx_usr_info->info3,
+					    HAL_RX_USR_INFO3_RU_START_IDX_80_1);
+	if (ru_type_80_1 != HAL_EHT_RU_NONE) {
+		ru_size += ru_type_80_1;
+		ru_index_per80mhz = ru_start_index_80_1;
+		ru_index = ru_index_per80mhz;
+		ru_index_320mhz |= HAL_RU_PER80(ru_type_80_1, 1, ru_index_per80mhz);
+		num_80mhz_with_ru++;
+	}
+
+	ru_type_80_2 = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_RU_TYPE_80_2);
+	ru_start_index_80_2 = le32_get_bits(rx_usr_info->info3,
+					    HAL_RX_USR_INFO3_RU_START_IDX_80_2);
+	if (ru_type_80_2 != HAL_EHT_RU_NONE) {
+		ru_size += ru_type_80_2;
+		ru_index_per80mhz = ru_start_index_80_2;
+		ru_index = ru_index_per80mhz;
+		ru_index_320mhz |= HAL_RU_PER80(ru_type_80_2, 2, ru_index_per80mhz);
+		num_80mhz_with_ru++;
+	}
+
+	ru_type_80_3 = le32_get_bits(rx_usr_info->info2, HAL_RX_USR_INFO2_RU_TYPE_80_3);
+	ru_start_index_80_3 = le32_get_bits(rx_usr_info->info2,
+					    HAL_RX_USR_INFO3_RU_START_IDX_80_3);
+	if (ru_type_80_3 != HAL_EHT_RU_NONE) {
+		ru_size += ru_type_80_3;
+		ru_index_per80mhz = ru_start_index_80_3;
+		ru_index = ru_index_per80mhz;
+		ru_index_320mhz |= HAL_RU_PER80(ru_type_80_3, 3, ru_index_per80mhz);
+		num_80mhz_with_ru++;
+	}
+
+	if (num_80mhz_with_ru > 1) {
+		/* Calculate the MRU index */
+		switch (ru_index_320mhz) {
+		case HAL_EHT_RU_996_484_0:
+		case HAL_EHT_RU_996x2_484_0:
+		case HAL_EHT_RU_996x3_484_0:
+			ru_index = 0;
+			break;
+		case HAL_EHT_RU_996_484_1:
+		case HAL_EHT_RU_996x2_484_1:
+		case HAL_EHT_RU_996x3_484_1:
+			ru_index = 1;
+			break;
+		case HAL_EHT_RU_996_484_2:
+		case HAL_EHT_RU_996x2_484_2:
+		case HAL_EHT_RU_996x3_484_2:
+			ru_index = 2;
+			break;
+		case HAL_EHT_RU_996_484_3:
+		case HAL_EHT_RU_996x2_484_3:
+		case HAL_EHT_RU_996x3_484_3:
+			ru_index = 3;
+			break;
+		case HAL_EHT_RU_996_484_4:
+		case HAL_EHT_RU_996x2_484_4:
+		case HAL_EHT_RU_996x3_484_4:
+			ru_index = 4;
+			break;
+		case HAL_EHT_RU_996_484_5:
+		case HAL_EHT_RU_996x2_484_5:
+		case HAL_EHT_RU_996x3_484_5:
+			ru_index = 5;
+			break;
+		case HAL_EHT_RU_996_484_6:
+		case HAL_EHT_RU_996x2_484_6:
+		case HAL_EHT_RU_996x3_484_6:
+			ru_index = 6;
+			break;
+		case HAL_EHT_RU_996_484_7:
+		case HAL_EHT_RU_996x2_484_7:
+		case HAL_EHT_RU_996x3_484_7:
+			ru_index = 7;
+			break;
+		case HAL_EHT_RU_996x2_484_8:
+			ru_index = 8;
+			break;
+		case HAL_EHT_RU_996x2_484_9:
+			ru_index = 9;
+			break;
+		case HAL_EHT_RU_996x2_484_10:
+			ru_index = 10;
+			break;
+		case HAL_EHT_RU_996x2_484_11:
+			ru_index = 11;
+			break;
+		default:
+			ru_index = HAL_EHT_RU_INVALID;
+			break;
+		}
+
+		ru_size += 4;
+	}
+
+	rtap_ru_size = hal_rx_mon_hal_ru_size_to_ath12k_ru_size(ru_size);
+	if (rtap_ru_size != ATH12K_EHT_RU_INVALID) {
+		u32 known, data;
+
+		known = __le32_to_cpu(eht->known);
+		known |= IEEE80211_RADIOTAP_EHT_KNOWN_RU_MRU_SIZE_OM;
+		eht->known = cpu_to_le32(known);
+
+		data = __le32_to_cpu(eht->data[1]);
+		data |=	u32_encode_bits(rtap_ru_size,
+					IEEE80211_RADIOTAP_EHT_DATA1_RU_SIZE);
+		eht->data[1] = cpu_to_le32(data);
+	}
+
+	if (ru_index != HAL_EHT_RU_INVALID) {
+		u32 known, data;
+
+		known = __le32_to_cpu(eht->known);
+		known |= IEEE80211_RADIOTAP_EHT_KNOWN_RU_MRU_INDEX_OM;
+		eht->known = cpu_to_le32(known);
+
+		data = __le32_to_cpu(eht->data[1]);
+		data |=	u32_encode_bits(rtap_ru_size,
+					IEEE80211_RADIOTAP_EHT_DATA1_RU_INDEX);
+		eht->data[1] = cpu_to_le32(data);
+	}
+
+	if (mon_rx_user_status && ru_index != HAL_EHT_RU_INVALID &&
+	    rtap_ru_size != ATH12K_EHT_RU_INVALID) {
+		mon_rx_user_status->ul_ofdma_ru_start_index = ru_index;
+		mon_rx_user_status->ul_ofdma_ru_size = rtap_ru_size;
+
+		ru_width = hal_rx_ul_ofdma_ru_size_to_width(rtap_ru_size);
+
+		mon_rx_user_status->ul_ofdma_ru_width = ru_width;
+		mon_rx_user_status->ofdma_info_valid = 1;
+	}
+}
+
 static enum hal_rx_mon_status
 ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 				  struct ath12k_mon_data *pmon,
@@ -1324,6 +1599,10 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 					     HAL_RX_PHYRX_RSSI_LEGACY_INFO_INFO0_RX_BW);
 		break;
 	}
+	case HAL_RX_PPDU_START_USER_INFO:
+		ath12k_dp_mon_hal_rx_parse_user_info(tlv_data, userid, ppdu_info);
+		break;
+
 	case HAL_RXPCU_PPDU_END_INFO: {
 		const struct hal_rx_ppdu_end_duration *ppdu_rx_duration = tlv_data;
 
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 959f2283294c3..765b53741861e 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -781,39 +781,6 @@ struct hal_eht_sig_ofdma_cmn_eb {
 	union hal_eht_sig_user_field user_field;
 } __packed;
 
-static inline
-enum nl80211_he_ru_alloc ath12k_he_ru_tones_to_nl80211_he_ru_alloc(u16 ru_tones)
-{
-	enum nl80211_he_ru_alloc ret;
-
-	switch (ru_tones) {
-	case RU_52:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_52;
-		break;
-	case RU_106:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_106;
-		break;
-	case RU_242:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_242;
-		break;
-	case RU_484:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_484;
-		break;
-	case RU_996:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_996;
-		break;
-	case RU_2X996:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
-		break;
-	case RU_26:
-		fallthrough;
-	default:
-		ret = NL80211_RATE_INFO_HE_RU_ALLOC_26;
-		break;
-	}
-	return ret;
-}
-
 enum hal_eht_bw {
 	HAL_EHT_BW_20,
 	HAL_EHT_BW_40,
@@ -872,6 +839,264 @@ struct hal_mon_usig_hdr {
 	union hal_mon_usig_non_cmn non_cmn;
 } __packed;
 
+#define HAL_RX_USR_INFO0_PHY_PPDU_ID		GENMASK(15, 0)
+#define HAL_RX_USR_INFO0_USR_RSSI		GENMASK(23, 16)
+#define HAL_RX_USR_INFO0_PKT_TYPE		GENMASK(27, 24)
+#define HAL_RX_USR_INFO0_STBC			BIT(28)
+#define HAL_RX_USR_INFO0_RECEPTION_TYPE		GENMASK(31, 29)
+
+#define HAL_RX_USR_INFO1_MCS			GENMASK(3, 0)
+#define HAL_RX_USR_INFO1_SGI			GENMASK(5, 4)
+#define HAL_RX_USR_INFO1_HE_RANGING_NDP		BIT(6)
+#define HAL_RX_USR_INFO1_MIMO_SS_BITMAP		GENMASK(15, 8)
+#define HAL_RX_USR_INFO1_RX_BW			GENMASK(18, 16)
+#define HAL_RX_USR_INFO1_DL_OFMDA_USR_IDX	GENMASK(31, 24)
+
+#define HAL_RX_USR_INFO2_DL_OFDMA_CONTENT_CHAN	BIT(0)
+#define HAL_RX_USR_INFO2_NSS			GENMASK(10, 8)
+#define HAL_RX_USR_INFO2_STREAM_OFFSET		GENMASK(13, 11)
+#define HAL_RX_USR_INFO2_STA_DCM		BIT(14)
+#define HAL_RX_USR_INFO2_LDPC			BIT(15)
+#define HAL_RX_USR_INFO2_RU_TYPE_80_0		GENMASK(19, 16)
+#define HAL_RX_USR_INFO2_RU_TYPE_80_1		GENMASK(23, 20)
+#define HAL_RX_USR_INFO2_RU_TYPE_80_2		GENMASK(27, 24)
+#define HAL_RX_USR_INFO2_RU_TYPE_80_3		GENMASK(31, 28)
+
+#define HAL_RX_USR_INFO3_RU_START_IDX_80_0	GENMASK(5, 0)
+#define HAL_RX_USR_INFO3_RU_START_IDX_80_1	GENMASK(13, 8)
+#define HAL_RX_USR_INFO3_RU_START_IDX_80_2	GENMASK(21, 16)
+#define HAL_RX_USR_INFO3_RU_START_IDX_80_3	GENMASK(29, 24)
+
+struct hal_receive_user_info {
+	__le32 info0;
+	__le32 info1;
+	__le32 info2;
+	__le32 info3;
+	__le32 user_fd_rssi_seg0;
+	__le32 user_fd_rssi_seg1;
+	__le32 user_fd_rssi_seg2;
+	__le32 user_fd_rssi_seg3;
+} __packed;
+
+enum hal_mon_reception_type {
+	HAL_RECEPTION_TYPE_SU,
+	HAL_RECEPTION_TYPE_DL_MU_MIMO,
+	HAL_RECEPTION_TYPE_DL_MU_OFMA,
+	HAL_RECEPTION_TYPE_DL_MU_OFDMA_MIMO,
+	HAL_RECEPTION_TYPE_UL_MU_MIMO,
+	HAL_RECEPTION_TYPE_UL_MU_OFDMA,
+	HAL_RECEPTION_TYPE_UL_MU_OFDMA_MIMO,
+};
+
+/* Different allowed RU in 11BE */
+#define HAL_EHT_RU_26		0ULL
+#define HAL_EHT_RU_52		1ULL
+#define HAL_EHT_RU_78		2ULL
+#define HAL_EHT_RU_106		3ULL
+#define HAL_EHT_RU_132		4ULL
+#define HAL_EHT_RU_242		5ULL
+#define HAL_EHT_RU_484		6ULL
+#define HAL_EHT_RU_726		7ULL
+#define HAL_EHT_RU_996		8ULL
+#define HAL_EHT_RU_996x2	9ULL
+#define HAL_EHT_RU_996x3	10ULL
+#define HAL_EHT_RU_996x4	11ULL
+#define HAL_EHT_RU_NONE		15ULL
+#define HAL_EHT_RU_INVALID	31ULL
+/* MRUs spanning above 80Mhz
+ * HAL_EHT_RU_996_484 = HAL_EHT_RU_484 + HAL_EHT_RU_996 + 4 (reserved)
+ */
+#define HAL_EHT_RU_996_484	18ULL
+#define HAL_EHT_RU_996x2_484	28ULL
+#define HAL_EHT_RU_996x3_484	40ULL
+#define HAL_EHT_RU_996_484_242	23ULL
+
+#define NUM_RU_BITS_PER80	16
+#define NUM_RU_BITS_PER20	4
+
+/* Different per_80Mhz band in 320Mhz bandwidth */
+#define HAL_80_0	0
+#define HAL_80_1	1
+#define HAL_80_2	2
+#define HAL_80_3	3
+
+#define HAL_RU_80MHZ(num_band)		((num_band) * NUM_RU_BITS_PER80)
+#define HAL_RU_20MHZ(idx_per_80)	((idx_per_80) * NUM_RU_BITS_PER20)
+
+#define HAL_RU_SHIFT(num_band, idx_per_80)	\
+		(HAL_RU_80MHZ(num_band) + HAL_RU_20MHZ(idx_per_80))
+
+#define HAL_RU(ru, num_band, idx_per_80)	\
+		((u64)(ru) << HAL_RU_SHIFT(num_band, idx_per_80))
+
+/* MRU-996+484 */
+#define HAL_EHT_RU_996_484_0	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996, HAL_80_1, 0))
+#define HAL_EHT_RU_996_484_1	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996, HAL_80_1, 0))
+#define HAL_EHT_RU_996_484_2	(HAL_RU(HAL_EHT_RU_996, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 1))
+#define HAL_EHT_RU_996_484_3	(HAL_RU(HAL_EHT_RU_996, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 0))
+#define HAL_EHT_RU_996_484_4	(HAL_RU(HAL_EHT_RU_484, HAL_80_2, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996, HAL_80_3, 0))
+#define HAL_EHT_RU_996_484_5	(HAL_RU(HAL_EHT_RU_484, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996, HAL_80_3, 0))
+#define HAL_EHT_RU_996_484_6	(HAL_RU(HAL_EHT_RU_996, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 1))
+#define HAL_EHT_RU_996_484_7	(HAL_RU(HAL_EHT_RU_996, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 0))
+
+/* MRU-996x2+484 */
+#define HAL_EHT_RU_996x2_484_0	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0))
+#define HAL_EHT_RU_996x2_484_1	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0))
+#define HAL_EHT_RU_996x2_484_2	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0))
+#define HAL_EHT_RU_996x2_484_3	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0))
+#define HAL_EHT_RU_996x2_484_4	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 1))
+#define HAL_EHT_RU_996x2_484_5	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 0))
+#define HAL_EHT_RU_996x2_484_6	(HAL_RU(HAL_EHT_RU_484, HAL_80_1, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_3, 0))
+#define HAL_EHT_RU_996x2_484_7	(HAL_RU(HAL_EHT_RU_484, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_3, 0))
+#define HAL_EHT_RU_996x2_484_8	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_3, 0))
+#define HAL_EHT_RU_996x2_484_9	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_3, 0))
+#define HAL_EHT_RU_996x2_484_10	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 1))
+#define HAL_EHT_RU_996x2_484_11	(HAL_RU(HAL_EHT_RU_996x2, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x2, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 0))
+
+/* MRU-996x3+484 */
+#define HAL_EHT_RU_996x3_484_0	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_1	(HAL_RU(HAL_EHT_RU_484, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_2	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_3	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_4	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 1) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_5	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_3, 0))
+#define HAL_EHT_RU_996x3_484_6	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 1))
+#define HAL_EHT_RU_996x3_484_7	(HAL_RU(HAL_EHT_RU_996x3, HAL_80_0, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_1, 0) |	\
+				 HAL_RU(HAL_EHT_RU_996x3, HAL_80_2, 0) |	\
+				 HAL_RU(HAL_EHT_RU_484, HAL_80_3, 0))
+
+#define HAL_RU_PER80(ru_per80, num_80mhz, ru_idx_per80mhz) \
+			(HAL_RU(ru_per80, num_80mhz, ru_idx_per80mhz))
+
+#define RU_INVALID		0
+#define RU_26			1
+#define RU_52			2
+#define RU_106			4
+#define RU_242			9
+#define RU_484			18
+#define RU_996			37
+#define RU_2X996		74
+#define RU_3X996		111
+#define RU_4X996		148
+#define RU_52_26		(RU_52 + RU_26)
+#define RU_106_26		(RU_106 + RU_26)
+#define RU_484_242		(RU_484 + RU_242)
+#define RU_996_484		(RU_996 + RU_484)
+#define RU_996_484_242		(RU_996 + RU_484_242)
+#define RU_2X996_484		(RU_2X996 + RU_484)
+#define RU_3X996_484		(RU_3X996 + RU_484)
+
+enum ath12k_eht_ru_size {
+	ATH12K_EHT_RU_26,
+	ATH12K_EHT_RU_52,
+	ATH12K_EHT_RU_106,
+	ATH12K_EHT_RU_242,
+	ATH12K_EHT_RU_484,
+	ATH12K_EHT_RU_996,
+	ATH12K_EHT_RU_996x2,
+	ATH12K_EHT_RU_996x4,
+	ATH12K_EHT_RU_52_26,
+	ATH12K_EHT_RU_106_26,
+	ATH12K_EHT_RU_484_242,
+	ATH12K_EHT_RU_996_484,
+	ATH12K_EHT_RU_996_484_242,
+	ATH12K_EHT_RU_996x2_484,
+	ATH12K_EHT_RU_996x3,
+	ATH12K_EHT_RU_996x3_484,
+
+	/* Keep last */
+	ATH12K_EHT_RU_INVALID,
+};
+
+#define HAL_RX_RU_ALLOC_TYPE_MAX	ATH12K_EHT_RU_INVALID
+
+static inline
+enum nl80211_he_ru_alloc ath12k_he_ru_tones_to_nl80211_he_ru_alloc(u16 ru_tones)
+{
+	enum nl80211_he_ru_alloc ret;
+
+	switch (ru_tones) {
+	case RU_52:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_52;
+		break;
+	case RU_106:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+		break;
+	case RU_242:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_242;
+		break;
+	case RU_484:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_484;
+		break;
+	case RU_996:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_996;
+		break;
+	case RU_2X996:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+		break;
+	case RU_26:
+		fallthrough;
+	default:
+		ret = NL80211_RATE_INFO_HE_RU_ALLOC_26;
+		break;
+	}
+	return ret;
+}
+
 void ath12k_hal_reo_status_queue_stats(struct ath12k_base *ab,
 				       struct hal_tlv_64_hdr *tlv,
 				       struct hal_reo_status *status);
diff --git a/drivers/net/wireless/ath/ath12k/rx_desc.h b/drivers/net/wireless/ath/ath12k/rx_desc.h
index 7367935ee68b3..6c600473b4021 100644
--- a/drivers/net/wireless/ath/ath12k/rx_desc.h
+++ b/drivers/net/wireless/ath/ath12k/rx_desc.h
@@ -1541,13 +1541,4 @@ struct hal_rx_desc {
 #define MAX_MU_GROUP_SHOW 16
 #define MAX_MU_GROUP_LENGTH (6 * MAX_MU_GROUP_SHOW)
 
-#define HAL_RX_RU_ALLOC_TYPE_MAX 6
-#define RU_26  1
-#define RU_52  2
-#define RU_106 4
-#define RU_242 9
-#define RU_484 18
-#define RU_996 37
-#define RU_2X996 74
-
 #endif /* ATH12K_RX_DESC_H */

From d939919a36f4606fb8312c502a53c0ecfbd85b2d Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:49 +0530
Subject: [PATCH 0428/2753] wifi: ath12k: Add HAL_PHYRX_OTHER_RECEIVE_INFO TLV
 parsing support

Currently, monitor is not enabled. However, in the future, the monitor
will be enabled. Therefore, add the necessary HAL_PHYRX_OTHER_RECEIVE_INFO
TLV parsing support in the monitor Rx path, which helps to populate the
extended Rx statistics.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-5-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 7 +++++++
 drivers/net/wireless/ath/ath12k/hal_rx.h | 8 ++++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 76b6d5861e253..0bd7dfef43107 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1599,6 +1599,13 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 					     HAL_RX_PHYRX_RSSI_LEGACY_INFO_INFO0_RX_BW);
 		break;
 	}
+	case HAL_PHYRX_OTHER_RECEIVE_INFO: {
+		const struct hal_phyrx_common_user_info *cmn_usr_info = tlv_data;
+
+		ppdu_info->gi = le32_get_bits(cmn_usr_info->info0,
+					      HAL_RX_PHY_CMN_USER_INFO0_GI);
+		break;
+	}
 	case HAL_RX_PPDU_START_USER_INFO:
 		ath12k_dp_mon_hal_rx_parse_user_info(tlv_data, userid, ppdu_info);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 765b53741861e..445d1c33b41fe 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -683,6 +683,14 @@ struct hal_rx_resp_req_info {
 #define HAL_RX_MPDU_ERR_MPDU_LEN		BIT(6)
 #define HAL_RX_MPDU_ERR_UNENCRYPTED_FRAME	BIT(7)
 
+#define HAL_RX_PHY_CMN_USER_INFO0_GI		GENMASK(17, 16)
+
+struct hal_phyrx_common_user_info {
+	__le32 rsvd[2];
+	__le32 info0;
+	__le32 rsvd1;
+} __packed;
+
 #define HAL_RX_EHT_SIG_NDP_CMN_INFO0_SPATIAL_REUSE	GENMASK(3, 0)
 #define HAL_RX_EHT_SIG_NDP_CMN_INFO0_GI_LTF		GENMASK(5, 4)
 #define HAL_RX_EHT_SIG_NDP_CMN_INFO0_NUM_LTF_SYM	GENMASK(8, 6)

From 0cded0e413468183a3b2dd445ab3bdc4d4375967 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:50 +0530
Subject: [PATCH 0429/2753] wifi: ath12k: Update the peer id in PPDU end user
 stats TLV

Currently, peer id get reported in the PPDU end user TLV tag. But the
monitor status handler is inherited from ath11k, but it was not updated
to incorporate the changes made to ath12k 802.11be hardware architecture.
Therefore, update the peer id from the PPDU end user TLV data to get latest
peer id update, it helps to populate accurate peer information on the
statistics data.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-6-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 0bd7dfef43107..a99a124f413c5 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1504,6 +1504,9 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 		ppdu_info->num_mpdu_fcs_err =
 			u32_get_bits(info[0],
 				     HAL_RX_PPDU_END_USER_STATS_INFO0_MPDU_CNT_FCS_ERR);
+		ppdu_info->peer_id =
+			u32_get_bits(info[0], HAL_RX_PPDU_END_USER_STATS_INFO0_PEER_ID);
+
 		switch (ppdu_info->preamble_type) {
 		case HAL_RX_PREAMBLE_11N:
 			ppdu_info->ht_flags = 1;

From dff4f278ee1ef12d822b7ed2a1048d27037209bb Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:51 +0530
Subject: [PATCH 0430/2753] wifi: ath12k: fix the ampdu id fetch in the
 HAL_RX_MPDU_START TLV

Currently, ampdu id is update with peer id mask which is incorrect.
Therefore, update the ampdu id with PPDU id mask value. Also move
the ampdu_id field inside the user stats since it is a user id based
statistics.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-7-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_mon.c | 16 ++++++++++------
 drivers/net/wireless/ath/ath12k/hal_rx.h |  3 ++-
 2 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index a99a124f413c5..a7e85d131ce3f 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2019-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "dp_mon.h"
@@ -1527,6 +1527,11 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 		if (userid < HAL_MAX_UL_MU_USERS) {
 			struct hal_rx_user_status *rxuser_stats =
 				&ppdu_info->userstats[userid];
+
+			if (ppdu_info->num_mpdu_fcs_ok > 1 ||
+			    ppdu_info->num_mpdu_fcs_err > 1)
+				ppdu_info->userstats[userid].ampdu_present = true;
+
 			ppdu_info->num_users += 1;
 
 			ath12k_dp_mon_rx_handle_ofdma_info(eu_stats, rxuser_stats);
@@ -1638,8 +1643,8 @@ ath12k_dp_mon_rx_parse_status_tlv(struct ath12k *ar,
 		if (userid < HAL_MAX_UL_MU_USERS) {
 			info[0] = __le32_to_cpu(mpdu_start->info0);
 			ppdu_info->userid = userid;
-			ppdu_info->ampdu_id[userid] =
-				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO1_PEERID);
+			ppdu_info->userstats[userid].ampdu_id =
+				u32_get_bits(info[0], HAL_RX_MPDU_START_INFO0_PPDU_ID);
 		}
 
 		break;
@@ -1857,15 +1862,14 @@ static void ath12k_dp_mon_update_radiotap(struct ath12k *ar,
 {
 	struct ieee80211_supported_band *sband;
 	u8 *ptr = NULL;
-	u16 ampdu_id = ppduinfo->ampdu_id[ppduinfo->userid];
 
 	rxs->flag |= RX_FLAG_MACTIME_START;
 	rxs->signal = ppduinfo->rssi_comb + ATH12K_DEFAULT_NOISE_FLOOR;
 	rxs->nss = ppduinfo->nss + 1;
 
-	if (ampdu_id) {
+	if (ppduinfo->userstats[ppduinfo->userid].ampdu_present) {
 		rxs->flag |= RX_FLAG_AMPDU_DETAILS;
-		rxs->ampdu_reference = ampdu_id;
+		rxs->ampdu_reference = ppduinfo->userstats[ppduinfo->userid].ampdu_id;
 	}
 
 	if (ppduinfo->is_eht || ppduinfo->eht_usig) {
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 445d1c33b41fe..163f9235fcf0a 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -148,6 +148,8 @@ struct hal_rx_user_status {
 	u32 mpdu_fcs_ok_bitmap[HAL_RX_NUM_WORDS_PER_PPDU_BITMAP];
 	u32 mpdu_ok_byte_count;
 	u32 mpdu_err_byte_count;
+	bool ampdu_present;
+	u16 ampdu_id;
 };
 
 #define HAL_MAX_UL_MU_USERS	37
@@ -263,7 +265,6 @@ struct hal_rx_mon_ppdu_info {
 	u8 addr4[ETH_ALEN];
 	struct hal_rx_user_status userstats[HAL_MAX_UL_MU_USERS];
 	u8 userid;
-	u16 ampdu_id[HAL_MAX_UL_MU_USERS];
 	bool first_msdu_in_mpdu;
 	bool is_ampdu;
 	u8 medium_prot_type;

From 03ac9e9144c59dcfaeb213f80e7e00974325045a Mon Sep 17 00:00:00 2001
From: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:52 +0530
Subject: [PATCH 0431/2753] wifi: ath12k: Add EHT MCS support in Extended Rx
 statistics

Currently, EHT MCS information is not populated. Therefore, add the EHT
MCS counter array to the peer rate statistics and update the EHT MCS
statistics from the status TLV data in the monitor Rx path. In the future,
this information will be used in the peer extended Rx statistics dump.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-8-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h   | 2 ++
 drivers/net/wireless/ath/ath12k/dp_mon.c | 6 ++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index 3dcdedf9e9de1..ef6ef6ad914df 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -361,6 +361,7 @@ struct ath12k_vif_iter {
 #define HAL_RX_MAX_MCS_HT	31
 #define HAL_RX_MAX_MCS_VHT	9
 #define HAL_RX_MAX_MCS_HE	11
+#define HAL_RX_MAX_MCS_BE	15
 #define HAL_RX_MAX_NSS		8
 #define HAL_RX_MAX_NUM_LEGACY_RATES 12
 #define ATH12K_RX_RATE_TABLE_11AX_NUM	576
@@ -370,6 +371,7 @@ struct ath12k_rx_peer_rate_stats {
 	u64 ht_mcs_count[HAL_RX_MAX_MCS_HT + 1];
 	u64 vht_mcs_count[HAL_RX_MAX_MCS_VHT + 1];
 	u64 he_mcs_count[HAL_RX_MAX_MCS_HE + 1];
+	u64 be_mcs_count[HAL_RX_MAX_MCS_BE + 1];
 	u64 nss_count[HAL_RX_MAX_NSS];
 	u64 bw_count[HAL_RX_BW_MAX];
 	u64 gi_count[HAL_RX_GI_MAX];
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index a7e85d131ce3f..514bbd63db1c2 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -3029,6 +3029,12 @@ static void ath12k_dp_mon_rx_update_peer_su_stats(struct ath12k *ar,
 		rx_stats->byte_stats.he_mcs_count[ppdu_info->mcs] += ppdu_info->mpdu_len;
 	}
 
+	if (ppdu_info->preamble_type == HAL_RX_PREAMBLE_11BE &&
+	    ppdu_info->mcs <= HAL_RX_MAX_MCS_BE) {
+		rx_stats->pkt_stats.be_mcs_count[ppdu_info->mcs] += num_msdu;
+		rx_stats->byte_stats.be_mcs_count[ppdu_info->mcs] += ppdu_info->mpdu_len;
+	}
+
 	if ((ppdu_info->preamble_type == HAL_RX_PREAMBLE_11A ||
 	     ppdu_info->preamble_type == HAL_RX_PREAMBLE_11B) &&
 	     ppdu_info->rate < HAL_RX_LEGACY_RATE_INVALID) {

From 98677080467c2a6529a3288f430acb8c44f583a0 Mon Sep 17 00:00:00 2001
From: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:53 +0530
Subject: [PATCH 0432/2753] wifi: ath12k: Refactor the format of peer rate
 table information

Currently, peer rate table information involves complex computation for
the rate index to update the rate table. To simplify this process, avoid
the rate index calculation by defining the rate table with bandwidth, GI,
NSS, MCS. Therefore, update the rate information based on the bandwidth,
GI, NSS and MCS information from the TLV data of monitor status Rx path.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-9-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h   |  6 +----
 drivers/net/wireless/ath/ath12k/dp_mon.c | 29 +++++++++++-------------
 2 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index ef6ef6ad914df..bc5b1b3a056c5 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -53,8 +53,6 @@
 
 #define ATH12K_INVALID_HW_MAC_ID	0xFF
 #define ATH12K_CONNECTION_LOSS_HZ	(3 * HZ)
-#define	ATH12K_RX_RATE_TABLE_NUM	320
-#define	ATH12K_RX_RATE_TABLE_11AX_NUM	576
 
 #define ATH12K_MON_TIMER_INTERVAL  10
 #define ATH12K_RESET_TIMEOUT_HZ			(20 * HZ)
@@ -364,8 +362,6 @@ struct ath12k_vif_iter {
 #define HAL_RX_MAX_MCS_BE	15
 #define HAL_RX_MAX_NSS		8
 #define HAL_RX_MAX_NUM_LEGACY_RATES 12
-#define ATH12K_RX_RATE_TABLE_11AX_NUM	576
-#define ATH12K_RX_RATE_TABLE_NUM 320
 
 struct ath12k_rx_peer_rate_stats {
 	u64 ht_mcs_count[HAL_RX_MAX_MCS_HT + 1];
@@ -376,7 +372,7 @@ struct ath12k_rx_peer_rate_stats {
 	u64 bw_count[HAL_RX_BW_MAX];
 	u64 gi_count[HAL_RX_GI_MAX];
 	u64 legacy_count[HAL_RX_MAX_NUM_LEGACY_RATES];
-	u64 rx_rate[ATH12K_RX_RATE_TABLE_11AX_NUM];
+	u64 rx_rate[HAL_RX_BW_MAX][HAL_RX_GI_MAX][HAL_RX_MAX_NSS][HAL_RX_MAX_MCS_HT + 1];
 };
 
 struct ath12k_rx_peer_stats {
diff --git a/drivers/net/wireless/ath/ath12k/dp_mon.c b/drivers/net/wireless/ath/ath12k/dp_mon.c
index 514bbd63db1c2..d22800e894850 100644
--- a/drivers/net/wireless/ath/ath12k/dp_mon.c
+++ b/drivers/net/wireless/ath/ath12k/dp_mon.c
@@ -2915,34 +2915,31 @@ ath12k_dp_mon_rx_update_peer_rate_table_stats(struct ath12k_rx_peer_stats *rx_st
 					      struct hal_rx_user_status *user_stats,
 					      u32 num_msdu)
 {
-	u32 rate_idx = 0;
+	struct ath12k_rx_peer_rate_stats *stats;
 	u32 mcs_idx = (user_stats) ? user_stats->mcs : ppdu_info->mcs;
 	u32 nss_idx = (user_stats) ? user_stats->nss - 1 : ppdu_info->nss - 1;
 	u32 bw_idx = ppdu_info->bw;
 	u32 gi_idx = ppdu_info->gi;
+	u32 len;
 
-	if ((mcs_idx > HAL_RX_MAX_MCS_HE) || (nss_idx >= HAL_RX_MAX_NSS) ||
-	    (bw_idx >= HAL_RX_BW_MAX) || (gi_idx >= HAL_RX_GI_MAX)) {
+	if (mcs_idx > HAL_RX_MAX_MCS_HT || nss_idx >= HAL_RX_MAX_NSS ||
+	    bw_idx >= HAL_RX_BW_MAX || gi_idx >= HAL_RX_GI_MAX) {
 		return;
 	}
 
-	if (ppdu_info->preamble_type == HAL_RX_PREAMBLE_11N ||
-	    ppdu_info->preamble_type == HAL_RX_PREAMBLE_11AC) {
-		rate_idx = mcs_idx * 8 + 8 * 10 * nss_idx;
-		rate_idx += bw_idx * 2 + gi_idx;
-	} else if (ppdu_info->preamble_type == HAL_RX_PREAMBLE_11AX) {
+	if (ppdu_info->preamble_type == HAL_RX_PREAMBLE_11AX ||
+	    ppdu_info->preamble_type == HAL_RX_PREAMBLE_11BE)
 		gi_idx = ath12k_he_gi_to_nl80211_he_gi(ppdu_info->gi);
-		rate_idx = mcs_idx * 12 + 12 * 12 * nss_idx;
-		rate_idx += bw_idx * 3 + gi_idx;
-	} else {
-		return;
-	}
 
-	rx_stats->pkt_stats.rx_rate[rate_idx] += num_msdu;
+	rx_stats->pkt_stats.rx_rate[bw_idx][gi_idx][nss_idx][mcs_idx] += num_msdu;
+	stats = &rx_stats->byte_stats;
+
 	if (user_stats)
-		rx_stats->byte_stats.rx_rate[rate_idx] += user_stats->mpdu_ok_byte_count;
+		len = user_stats->mpdu_ok_byte_count;
 	else
-		rx_stats->byte_stats.rx_rate[rate_idx] += ppdu_info->mpdu_len;
+		len = ppdu_info->mpdu_len;
+
+	stats->rx_rate[bw_idx][gi_idx][nss_idx][mcs_idx] += len;
 }
 
 static void ath12k_dp_mon_rx_update_peer_su_stats(struct ath12k *ar,

From a412547f2a8bfcf6337691b6d498536f29dbf4b5 Mon Sep 17 00:00:00 2001
From: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Date: Thu, 6 Feb 2025 07:08:54 +0530
Subject: [PATCH 0433/2753] wifi: ath12k: Add peer extended Rx statistics
 debugfs support

Currently, peer extended Rx statistics are not supported. Therefore, expose
peer extended Rx statistics support through debugfs, allowing users to
enable or disable the collection of statistics information. After that
the statistics information can be dumped through debugfs. Below are the
debugfs commands exposed.

Enable/Disable:
 echo <1/0> > /sys/kernel/debug/ieee80211/phyX/ath12k/ext_rx_stats

Dump:
 cat /sys/kernel/debug/ieee80211/phyX/netdev:wlanX/stations/<peer MAC addr>/rx_stats

Sample output:
==============
RX peer stats:

Num of MSDUs: 1087
Num of MSDUs with TCP L4: 0
Num of MSDUs with UDP L4: 13
Num of other MSDUs: 1074
Num of MSDUs part of AMPDU: 363
Num of MSDUs not part of AMPDU: 724
Num of MSDUs using STBC: 0
Num of MSDUs beamformed: 0
Num of MPDUs with FCS ok: 695
Num of MPDUs with FCS error: 0
preamble: 11A 395 11B 0 11N 0 11AC 0 11AX 692 11BE 0
reception type: SU 1087 MU_MIMO 0 MU_OFDMA 0 MU_OFDMA_MIMO 0
TID(0-15) Legacy TID(16):690 1 0 0 1 0 0 0 0 0 0 0 0 0 0 0 395
RX Duration:39537

DCM: 0
RU26:  0
RU52:  0
RU106: 0
RU242: 0
RU484: 0
RU996: 0

RX success packet stats:

EHT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0        MCS 6: 0        MCS 7: 0
MCS 8: 0        MCS 9: 0        MCS 10: 0       MCS 11: 0       MCS 12: 0       MCS 13: 0       MCS 14: 0       MCS 15: 0

HE stats:
MCS 0: 1        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0
MCS 6: 66       MCS 7: 46       MCS 8: 46       MCS 9: 34       MCS 10: 28      MCS 11: 471

VHT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0
MCS 5: 0        MCS 6: 0        MCS 7: 0        MCS 8: 0        MCS 9: 0

HT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0        MCS 6: 0        MCS 7: 0
MCS 8: 0        MCS 9: 0        MCS 10: 0       MCS 11: 0       MCS 12: 0       MCS 13: 0       MCS 14: 0       MCS 15: 0
MCS 16: 0       MCS 17: 0       MCS 18: 0       MCS 19: 0       MCS 20: 0       MCS 21: 0       MCS 22: 0       MCS 23: 0
MCS 24: 0       MCS 25: 0       MCS 26: 0       MCS 27: 0       MCS 28: 0       MCS 29: 0       MCS 30: 0       MCS 31: 0

Legacy stats:
1 Mbps: 0       2 Mbps: 0       5.5 Mbps: 0     6 Mbps: 395
9 Mbps: 0       11 Mbps: 0      12 Mbps: 0      18 Mbps: 0
24 Mbps: 0      36 Mbps: 0      48 Mbps: 0      54 Mbps: 0

NSS stats:
1x1: 1086 2x2: 0 3x3: 0 4x4: 0 5x5: 0 6x6: 0 7x7: 0 8x8: 0

GI: 0.8 us 0 0.4 us 396 1.6 us 691 3.2 us 0
BW: 20 MHz 785 40 MHz 2 80 MHz 300 160 MHz 0 320 MHz 0

20 Mhz gi 1 us 1x1 :  6:5 7:3 8:3 9:4 10:4 11:374 12:391
40 Mhz gi 1 us 1x1 :  12:2
80 Mhz gi 1 us 1x1 :  6:61 7:43 8:43 9:30 10:24 11:97 12:2

RX success byte stats:

EHT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0        MCS 6: 0        MCS 7: 0
MCS 8: 0        MCS 9: 0        MCS 10: 0       MCS 11: 0       MCS 12: 0       MCS 13: 0       MCS 14: 0       MCS 15: 0

HE stats:
MCS 0: 41       MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0
MCS 6: 1435     MCS 7: 943      MCS 8: 697      MCS 9: 533      MCS 10: 492     MCS 11: 8159

VHT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0
MCS 5: 0        MCS 6: 0        MCS 7: 0        MCS 8: 0        MCS 9: 0

HT stats:
MCS 0: 0        MCS 1: 0        MCS 2: 0        MCS 3: 0        MCS 4: 0        MCS 5: 0        MCS 6: 0        MCS 7: 0
MCS 8: 0        MCS 9: 0        MCS 10: 0       MCS 11: 0       MCS 12: 0       MCS 13: 0       MCS 14: 0       MCS 15: 0
MCS 16: 0       MCS 17: 0       MCS 18: 0       MCS 19: 0       MCS 20: 0       MCS 21: 0       MCS 22: 0       MCS 23: 0
MCS 24: 0       MCS 25: 0       MCS 26: 0       MCS 27: 0       MCS 28: 0       MCS 29: 0       MCS 30: 0       MCS 31: 0

Legacy stats:
1 Mbps: 0       2 Mbps: 0       5.5 Mbps: 0     6 Mbps: 16195
9 Mbps: 0       11 Mbps: 0      12 Mbps: 0      18 Mbps: 0
24 Mbps: 0      36 Mbps: 0      48 Mbps: 0      54 Mbps: 0

NSS stats:
1x1: 28454 2x2: 0 3x3: 0 4x4: 0 5x5: 0 6x6: 0 7x7: 0 8x8: 0

GI: 0.8 us 0 0.4 us 16236 1.6 us 12259 3.2 us 0
BW: 20 MHz 24108 40 MHz 82 80 MHz 4305 160 MHz 0 320 MHz 0

20 Mhz gi 1 us 1x1 :  6:205 7:123 8:123 9:164 10:164 11:7257 12:16031
40 Mhz gi 1 us 1x1 :  12:82
80 Mhz gi 1 us 1x1 :  6:1230 7:820 8:574 9:369 10:328 11:902 12:82

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Co-developed-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Co-developed-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Signed-off-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250206013854.174765-10-quic_periyasa@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/Makefile      |   2 +-
 drivers/net/wireless/ath/ath12k/core.h        |   2 +
 drivers/net/wireless/ath/ath12k/debugfs.c     |  97 +++++
 drivers/net/wireless/ath/ath12k/debugfs.h     |  21 +-
 drivers/net/wireless/ath/ath12k/debugfs_sta.c | 337 ++++++++++++++++++
 drivers/net/wireless/ath/ath12k/debugfs_sta.h |  24 ++
 drivers/net/wireless/ath/ath12k/hal_rx.h      |   3 -
 drivers/net/wireless/ath/ath12k/mac.c         |  18 +-
 drivers/net/wireless/ath/ath12k/mac.h         |   4 +-
 9 files changed, 497 insertions(+), 11 deletions(-)
 create mode 100644 drivers/net/wireless/ath/ath12k/debugfs_sta.c
 create mode 100644 drivers/net/wireless/ath/ath12k/debugfs_sta.h

diff --git a/drivers/net/wireless/ath/ath12k/Makefile b/drivers/net/wireless/ath/ath12k/Makefile
index 4a7f5e87384c2..60644cb42c76e 100644
--- a/drivers/net/wireless/ath/ath12k/Makefile
+++ b/drivers/net/wireless/ath/ath12k/Makefile
@@ -23,7 +23,7 @@ ath12k-y += core.o \
 	    fw.o \
 	    p2p.o
 
-ath12k-$(CONFIG_ATH12K_DEBUGFS) += debugfs.o debugfs_htt_stats.o
+ath12k-$(CONFIG_ATH12K_DEBUGFS) += debugfs.o debugfs_htt_stats.o debugfs_sta.o
 ath12k-$(CONFIG_ACPI) += acpi.o
 ath12k-$(CONFIG_ATH12K_TRACING) += trace.o
 ath12k-$(CONFIG_PM) += wow.o
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index bc5b1b3a056c5..b60a636a6e19f 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -581,6 +581,8 @@ struct ath12k_debug {
 	bool tpc_request;
 	struct completion tpc_complete;
 	struct wmi_tpc_stats_arg *tpc_stats;
+	u32 rx_filter;
+	bool extd_rx_stats;
 };
 
 struct ath12k_per_peer_tx_stats {
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.c b/drivers/net/wireless/ath/ath12k/debugfs.c
index d38ece46f1d0e..57002215ddf16 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs.c
@@ -5,6 +5,7 @@
  */
 
 #include "core.h"
+#include "dp_tx.h"
 #include "debug.h"
 #include "debugfs.h"
 #include "debugfs_htt_stats.h"
@@ -740,6 +741,98 @@ static const struct file_operations fops_tpc_stats_type = {
 	.llseek = default_llseek,
 };
 
+static ssize_t ath12k_write_extd_rx_stats(struct file *file,
+					  const char __user *ubuf,
+					  size_t count, loff_t *ppos)
+{
+	struct ath12k *ar = file->private_data;
+	struct htt_rx_ring_tlv_filter tlv_filter = {0};
+	u32 ring_id, rx_filter = 0;
+	bool enable;
+	int ret, i;
+
+	if (kstrtobool_from_user(ubuf, count, &enable))
+		return -EINVAL;
+
+	wiphy_lock(ath12k_ar_to_hw(ar)->wiphy);
+
+	if (!ar->ab->hw_params->rxdma1_enable) {
+		ret = count;
+		goto exit;
+	}
+
+	if (ar->ah->state != ATH12K_HW_STATE_ON) {
+		ret = -ENETDOWN;
+		goto exit;
+	}
+
+	if (enable == ar->debug.extd_rx_stats) {
+		ret = count;
+		goto exit;
+	}
+
+	if (enable) {
+		rx_filter =  HTT_RX_FILTER_TLV_FLAGS_MPDU_START;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_START;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_USER_STATS_EXT;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_END_STATUS_DONE;
+		rx_filter |= HTT_RX_FILTER_TLV_FLAGS_PPDU_START_USER_INFO;
+
+		tlv_filter.rx_filter = rx_filter;
+		tlv_filter.pkt_filter_flags0 = HTT_RX_FP_MGMT_FILTER_FLAGS0;
+		tlv_filter.pkt_filter_flags1 = HTT_RX_FP_MGMT_FILTER_FLAGS1;
+		tlv_filter.pkt_filter_flags2 = HTT_RX_FP_CTRL_FILTER_FLASG2;
+		tlv_filter.pkt_filter_flags3 = HTT_RX_FP_CTRL_FILTER_FLASG3 |
+			HTT_RX_FP_DATA_FILTER_FLASG3;
+	} else {
+		tlv_filter = ath12k_mac_mon_status_filter_default;
+	}
+
+	ar->debug.rx_filter = tlv_filter.rx_filter;
+
+	for (i = 0; i < ar->ab->hw_params->num_rxdma_per_pdev; i++) {
+		ring_id = ar->dp.rxdma_mon_dst_ring[i].ring_id;
+		ret = ath12k_dp_tx_htt_rx_filter_setup(ar->ab, ring_id, ar->dp.mac_id + i,
+						       HAL_RXDMA_MONITOR_DST,
+						       DP_RXDMA_REFILL_RING_SIZE,
+						       &tlv_filter);
+		if (ret) {
+			ath12k_warn(ar->ab, "failed to set rx filter for monitor status ring\n");
+			goto exit;
+		}
+	}
+
+	ar->debug.extd_rx_stats = !!enable;
+	ret = count;
+exit:
+	wiphy_unlock(ath12k_ar_to_hw(ar)->wiphy);
+	return ret;
+}
+
+static ssize_t ath12k_read_extd_rx_stats(struct file *file,
+					 char __user *ubuf,
+					 size_t count, loff_t *ppos)
+{
+	struct ath12k *ar = file->private_data;
+	char buf[32];
+	int len = 0;
+
+	wiphy_lock(ath12k_ar_to_hw(ar)->wiphy);
+	len = scnprintf(buf, sizeof(buf) - len, "%d\n",
+			ar->debug.extd_rx_stats);
+	wiphy_unlock(ath12k_ar_to_hw(ar)->wiphy);
+
+	return simple_read_from_buffer(ubuf, count, ppos, buf, len);
+}
+
+static const struct file_operations fops_extd_rx_stats = {
+	.read = ath12k_read_extd_rx_stats,
+	.write = ath12k_write_extd_rx_stats,
+	.open = simple_open,
+};
+
 void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
 	bool dput_needed;
@@ -1184,6 +1277,10 @@ void ath12k_debugfs_register(struct ath12k *ar)
 
 	ath12k_debugfs_htt_stats_register(ar);
 	ath12k_debugfs_fw_stats_register(ar);
+
+	debugfs_create_file("ext_rx_stats", 0644,
+			    ar->debug.debugfs_pdev, ar,
+			    &fops_extd_rx_stats);
 }
 
 void ath12k_debugfs_unregister(struct ath12k *ar)
diff --git a/drivers/net/wireless/ath/ath12k/debugfs.h b/drivers/net/wireless/ath/ath12k/debugfs.h
index fb85113fc6258..d7041297d5d88 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs.h
@@ -16,6 +16,16 @@ void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 				     struct ath12k_fw_stats *stats);
 void ath12k_debugfs_fw_stats_reset(struct ath12k *ar);
 
+static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
+{
+	return ar->debug.extd_rx_stats;
+}
+
+static inline int ath12k_debugfs_rx_filter(struct ath12k *ar)
+{
+	return ar->debug.rx_filter;
+}
+
 #define ATH12K_CCK_RATES			4
 #define ATH12K_OFDM_RATES			8
 #define ATH12K_HT_RATES				8
@@ -97,7 +107,6 @@ enum ath12k_debug_tpc_stats_support_modes {
 	ATH12K_TPC_STATS_SUPPORT_BE,
 	ATH12K_TPC_STATS_SUPPORT_BE_PUNC,
 };
-
 #else
 static inline void ath12k_debugfs_soc_create(struct ath12k_base *ab)
 {
@@ -123,6 +132,16 @@ static inline void ath12k_debugfs_fw_stats_process(struct ath12k *ar,
 static inline void ath12k_debugfs_fw_stats_reset(struct ath12k *ar)
 {
 }
+
+static inline bool ath12k_debugfs_is_extd_rx_stats_enabled(struct ath12k *ar)
+{
+	return false;
+}
+
+static inline int ath12k_debugfs_rx_filter(struct ath12k *ar)
+{
+	return 0;
+}
 #endif /* CONFIG_ATH12K_DEBUGFS */
 
 #endif /* _ATH12K_DEBUGFS_H_ */
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_sta.c b/drivers/net/wireless/ath/ath12k/debugfs_sta.c
new file mode 100644
index 0000000000000..5bd2bf4c9dac3
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/debugfs_sta.c
@@ -0,0 +1,337 @@
+// SPDX-License-Identifier: BSD-3-Clause-Clear
+/*
+ * Copyright (c) 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#include <linux/vmalloc.h>
+
+#include "debugfs_sta.h"
+#include "core.h"
+#include "peer.h"
+#include "debug.h"
+#include "debugfs_htt_stats.h"
+#include "debugfs.h"
+
+static
+u32 ath12k_dbg_sta_dump_rate_stats(u8 *buf, u32 offset, const int size,
+				   bool he_rates_avail,
+				   const struct ath12k_rx_peer_rate_stats *stats)
+{
+	static const char *legacy_rate_str[HAL_RX_MAX_NUM_LEGACY_RATES] = {
+					"1 Mbps", "2 Mbps", "5.5 Mbps", "6 Mbps",
+					"9 Mbps", "11 Mbps", "12 Mbps", "18 Mbps",
+					"24 Mbps", "36 Mbps", "48 Mbps", "54 Mbps"};
+	u8 max_bw = HAL_RX_BW_MAX, max_gi = HAL_RX_GI_MAX, max_mcs = HAL_RX_MAX_NSS;
+	int mcs = 0, bw = 0, nss = 0, gi = 0, bw_num = 0;
+	u32 i, len = offset, max = max_bw * max_gi * max_mcs;
+	bool found;
+
+	len += scnprintf(buf + len, size - len, "\nEHT stats:\n");
+	for (i = 0; i <= HAL_RX_MAX_MCS_BE; i++)
+		len += scnprintf(buf + len, size - len,
+				   "MCS %d: %llu%s", i, stats->be_mcs_count[i],
+				   (i + 1) % 8 ? "\t" : "\n");
+
+	len += scnprintf(buf + len, size - len, "\nHE stats:\n");
+	for (i = 0; i <= HAL_RX_MAX_MCS_HE; i++)
+		len += scnprintf(buf + len, size - len,
+				   "MCS %d: %llu%s", i, stats->he_mcs_count[i],
+				   (i + 1) % 6 ? "\t" : "\n");
+
+	len += scnprintf(buf + len, size - len, "\nVHT stats:\n");
+	for (i = 0; i <= HAL_RX_MAX_MCS_VHT; i++)
+		len += scnprintf(buf + len, size - len,
+				   "MCS %d: %llu%s", i, stats->vht_mcs_count[i],
+				   (i + 1) % 5 ? "\t" : "\n");
+
+	len += scnprintf(buf + len, size - len, "\nHT stats:\n");
+	for (i = 0; i <= HAL_RX_MAX_MCS_HT; i++)
+		len += scnprintf(buf + len, size - len,
+				   "MCS %d: %llu%s", i, stats->ht_mcs_count[i],
+				   (i + 1) % 8 ? "\t" : "\n");
+
+	len += scnprintf(buf + len, size - len, "\nLegacy stats:\n");
+	for (i = 0; i < HAL_RX_MAX_NUM_LEGACY_RATES; i++)
+		len += scnprintf(buf + len, size - len,
+				   "%s: %llu%s", legacy_rate_str[i],
+				   stats->legacy_count[i],
+				   (i + 1) % 4 ? "\t" : "\n");
+
+	len += scnprintf(buf + len, size - len, "\nNSS stats:\n");
+	for (i = 0; i < HAL_RX_MAX_NSS; i++)
+		len += scnprintf(buf + len, size - len,
+				   "%dx%d: %llu ", i + 1, i + 1,
+				   stats->nss_count[i]);
+
+	len += scnprintf(buf + len, size - len,
+			  "\n\nGI: 0.8 us %llu 0.4 us %llu 1.6 us %llu 3.2 us %llu\n",
+			  stats->gi_count[0],
+			  stats->gi_count[1],
+			  stats->gi_count[2],
+			  stats->gi_count[3]);
+
+	len += scnprintf(buf + len, size - len,
+			   "BW: 20 MHz %llu 40 MHz %llu 80 MHz %llu 160 MHz %llu 320 MHz %llu\n",
+			   stats->bw_count[0],
+			   stats->bw_count[1],
+			   stats->bw_count[2],
+			   stats->bw_count[3],
+			   stats->bw_count[4]);
+
+	for (i = 0; i < max; i++) {
+		found = false;
+
+		for (mcs = 0; mcs <= HAL_RX_MAX_MCS_HT; mcs++) {
+			if (stats->rx_rate[bw][gi][nss][mcs]) {
+				found = true;
+				break;
+			}
+		}
+
+		if (!found)
+			goto skip_report;
+
+		switch (bw) {
+		case HAL_RX_BW_20MHZ:
+			bw_num = 20;
+			break;
+		case HAL_RX_BW_40MHZ:
+			bw_num = 40;
+			break;
+		case HAL_RX_BW_80MHZ:
+			bw_num = 80;
+			break;
+		case HAL_RX_BW_160MHZ:
+			bw_num = 160;
+			break;
+		case HAL_RX_BW_320MHZ:
+			bw_num = 320;
+			break;
+		}
+
+		len += scnprintf(buf + len, size - len, "\n%d Mhz gi %d us %dx%d : ",
+				 bw_num, gi, nss + 1, nss + 1);
+
+		for (mcs = 0; mcs <= HAL_RX_MAX_MCS_HT; mcs++) {
+			if (stats->rx_rate[bw][gi][nss][mcs])
+				len += scnprintf(buf + len, size - len,
+						 " %d:%llu", mcs,
+						 stats->rx_rate[bw][gi][nss][mcs]);
+		}
+
+skip_report:
+		if (nss++ >= max_mcs - 1) {
+			nss = 0;
+			if (gi++ >= max_gi - 1) {
+				gi = 0;
+				if (bw < max_bw - 1)
+					bw++;
+			}
+		}
+	}
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	return len - offset;
+}
+
+static ssize_t ath12k_dbg_sta_dump_rx_stats(struct file *file,
+					    char __user *user_buf,
+					    size_t count, loff_t *ppos)
+{
+	struct ieee80211_link_sta *link_sta = file->private_data;
+	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(link_sta->sta);
+	const int size = ATH12K_STA_RX_STATS_BUF_SIZE;
+	struct ath12k_hw *ah = ahsta->ahvif->ah;
+	struct ath12k_rx_peer_stats *rx_stats;
+	struct ath12k_link_sta *arsta;
+	u8 link_id = link_sta->link_id;
+	int len = 0, i, ret = 0;
+	bool he_rates_avail;
+	struct ath12k *ar;
+
+	wiphy_lock(ah->hw->wiphy);
+
+	if (!(BIT(link_id) & ahsta->links_map)) {
+		wiphy_unlock(ah->hw->wiphy);
+		return -ENOENT;
+	}
+
+	arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]);
+	if (!arsta || !arsta->arvif->ar) {
+		wiphy_unlock(ah->hw->wiphy);
+		return -ENOENT;
+	}
+
+	ar = arsta->arvif->ar;
+
+	u8 *buf __free(kfree) = kzalloc(size, GFP_KERNEL);
+	if (!buf) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	spin_lock_bh(&ar->ab->base_lock);
+
+	rx_stats = arsta->rx_stats;
+	if (!rx_stats) {
+		ret = -ENOENT;
+		goto unlock;
+	}
+
+	len += scnprintf(buf + len, size - len, "RX peer stats:\n\n");
+	len += scnprintf(buf + len, size - len, "Num of MSDUs: %llu\n",
+			 rx_stats->num_msdu);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs with TCP L4: %llu\n",
+			 rx_stats->tcp_msdu_count);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs with UDP L4: %llu\n",
+			 rx_stats->udp_msdu_count);
+	len += scnprintf(buf + len, size - len, "Num of other MSDUs: %llu\n",
+			 rx_stats->other_msdu_count);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs part of AMPDU: %llu\n",
+			 rx_stats->ampdu_msdu_count);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs not part of AMPDU: %llu\n",
+			 rx_stats->non_ampdu_msdu_count);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs using STBC: %llu\n",
+			 rx_stats->stbc_count);
+	len += scnprintf(buf + len, size - len, "Num of MSDUs beamformed: %llu\n",
+			 rx_stats->beamformed_count);
+	len += scnprintf(buf + len, size - len, "Num of MPDUs with FCS ok: %llu\n",
+			 rx_stats->num_mpdu_fcs_ok);
+	len += scnprintf(buf + len, size - len, "Num of MPDUs with FCS error: %llu\n",
+			 rx_stats->num_mpdu_fcs_err);
+
+	he_rates_avail = (rx_stats->pream_cnt[HAL_RX_PREAMBLE_11AX] > 1) ? true : false;
+
+	len += scnprintf(buf + len, size - len,
+			 "preamble: 11A %llu 11B %llu 11N %llu 11AC %llu 11AX %llu 11BE %llu\n",
+			 rx_stats->pream_cnt[0], rx_stats->pream_cnt[1],
+			 rx_stats->pream_cnt[2], rx_stats->pream_cnt[3],
+			 rx_stats->pream_cnt[4], rx_stats->pream_cnt[6]);
+	len += scnprintf(buf + len, size - len,
+			 "reception type: SU %llu MU_MIMO %llu MU_OFDMA %llu MU_OFDMA_MIMO %llu\n",
+			 rx_stats->reception_type[0], rx_stats->reception_type[1],
+			 rx_stats->reception_type[2], rx_stats->reception_type[3]);
+
+	len += scnprintf(buf + len, size - len, "TID(0-15) Legacy TID(16):");
+	for (i = 0; i <= IEEE80211_NUM_TIDS; i++)
+		len += scnprintf(buf + len, size - len, "%llu ", rx_stats->tid_count[i]);
+
+	len += scnprintf(buf + len, size - len, "\nRX Duration:%llu\n",
+			 rx_stats->rx_duration);
+
+	len += scnprintf(buf + len, size - len,
+			 "\nDCM: %llu\nRU26:  %llu\nRU52:  %llu\nRU106: %llu\nRU242: %llu\nRU484: %llu\nRU996: %llu\nRU996x2: %llu\n",
+			 rx_stats->dcm_count, rx_stats->ru_alloc_cnt[0],
+			 rx_stats->ru_alloc_cnt[1], rx_stats->ru_alloc_cnt[2],
+			 rx_stats->ru_alloc_cnt[3], rx_stats->ru_alloc_cnt[4],
+			 rx_stats->ru_alloc_cnt[5], rx_stats->ru_alloc_cnt[6]);
+
+	len += scnprintf(buf + len, size - len, "\nRX success packet stats:\n");
+	len += ath12k_dbg_sta_dump_rate_stats(buf, len, size, he_rates_avail,
+					      &rx_stats->pkt_stats);
+
+	len += scnprintf(buf + len, size - len, "\n");
+
+	len += scnprintf(buf + len, size - len, "\nRX success byte stats:\n");
+	len += ath12k_dbg_sta_dump_rate_stats(buf, len, size, he_rates_avail,
+					      &rx_stats->byte_stats);
+
+unlock:
+	spin_unlock_bh(&ar->ab->base_lock);
+
+	if (len)
+		ret = simple_read_from_buffer(user_buf, count, ppos, buf, len);
+out:
+	wiphy_unlock(ah->hw->wiphy);
+	return ret;
+}
+
+static const struct file_operations fops_rx_stats = {
+	.read = ath12k_dbg_sta_dump_rx_stats,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+static ssize_t ath12k_dbg_sta_reset_rx_stats(struct file *file,
+					     const char __user *buf,
+					     size_t count, loff_t *ppos)
+{
+	struct ieee80211_link_sta *link_sta = file->private_data;
+	struct ath12k_sta *ahsta = ath12k_sta_to_ahsta(link_sta->sta);
+	struct ath12k_hw *ah = ahsta->ahvif->ah;
+	struct ath12k_rx_peer_stats *rx_stats;
+	struct ath12k_link_sta *arsta;
+	u8 link_id = link_sta->link_id;
+	struct ath12k *ar;
+	bool reset;
+	int ret;
+
+	ret = kstrtobool_from_user(buf, count, &reset);
+	if (ret)
+		return ret;
+
+	if (!reset)
+		return -EINVAL;
+
+	wiphy_lock(ah->hw->wiphy);
+
+	if (!(BIT(link_id) & ahsta->links_map)) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	arsta = wiphy_dereference(ah->hw->wiphy, ahsta->link[link_id]);
+	if (!arsta || !arsta->arvif->ar) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	ar = arsta->arvif->ar;
+
+	spin_lock_bh(&ar->ab->base_lock);
+
+	rx_stats = arsta->rx_stats;
+	if (!rx_stats) {
+		spin_unlock_bh(&ar->ab->base_lock);
+		ret = -ENOENT;
+		goto out;
+	}
+
+	memset(rx_stats, 0, sizeof(*rx_stats));
+	spin_unlock_bh(&ar->ab->base_lock);
+
+	ret = count;
+out:
+	wiphy_unlock(ah->hw->wiphy);
+	return ret;
+}
+
+static const struct file_operations fops_reset_rx_stats = {
+	.write = ath12k_dbg_sta_reset_rx_stats,
+	.open = simple_open,
+	.owner = THIS_MODULE,
+	.llseek = default_llseek,
+};
+
+void ath12k_debugfs_link_sta_op_add(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_link_sta *link_sta,
+				    struct dentry *dir)
+{
+	struct ath12k *ar;
+
+	lockdep_assert_wiphy(hw->wiphy);
+
+	ar = ath12k_get_ar_by_vif(hw, vif, link_sta->link_id);
+	if (!ar)
+		return;
+
+	if (ath12k_debugfs_is_extd_rx_stats_enabled(ar)) {
+		debugfs_create_file("rx_stats", 0400, dir, link_sta,
+				    &fops_rx_stats);
+		debugfs_create_file("reset_rx_stats", 0200, dir, link_sta,
+				    &fops_reset_rx_stats);
+	}
+}
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_sta.h b/drivers/net/wireless/ath/ath12k/debugfs_sta.h
new file mode 100644
index 0000000000000..8de924f4d7d52
--- /dev/null
+++ b/drivers/net/wireless/ath/ath12k/debugfs_sta.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+#ifndef _ATH12K_DEBUGFS_STA_H_
+#define _ATH12K_DEBUGFS_STA_H_
+
+#include <net/mac80211.h>
+
+#include "core.h"
+
+#define ATH12K_STA_RX_STATS_BUF_SIZE		(1024 * 16)
+
+#ifdef CONFIG_ATH12K_DEBUGFS
+
+void ath12k_debugfs_link_sta_op_add(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_link_sta *link_sta,
+				    struct dentry *dir);
+
+#endif /* CONFIG_ATH12K_DEBUGFS */
+
+#endif /* _ATH12K_DEBUGFS_STA_H_ */
diff --git a/drivers/net/wireless/ath/ath12k/hal_rx.h b/drivers/net/wireless/ath/ath12k/hal_rx.h
index 163f9235fcf0a..6bdcd0867d86e 100644
--- a/drivers/net/wireless/ath/ath12k/hal_rx.h
+++ b/drivers/net/wireless/ath/ath12k/hal_rx.h
@@ -22,9 +22,6 @@ struct hal_rx_wbm_rel_info {
 #define HAL_INVALID_PEERID	0x3fff
 #define VHT_SIG_SU_NSS_MASK 0x7
 
-#define HAL_RX_MAX_MCS 12
-#define HAL_RX_MAX_NSS 8
-
 #define HAL_RX_MPDU_INFO_PN_GET_BYTE1(__val) \
 	le32_get_bits((__val), GENMASK(7, 0))
 
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index fc5cfd860d4d6..664b13c259654 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -20,6 +20,7 @@
 #include "debugfs.h"
 #include "hif.h"
 #include "wow.h"
+#include "debugfs_sta.h"
 
 #define CHAN2G(_channel, _freq, _flags) { \
 	.band                   = NL80211_BAND_2GHZ, \
@@ -805,9 +806,9 @@ static struct ath12k *ath12k_get_ar_by_ctx(struct ieee80211_hw *hw,
 	return ath12k_mac_get_ar_by_chan(hw, ctx->def.chan);
 }
 
-static struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw,
-					   struct ieee80211_vif *vif,
-					   u8 link_id)
+struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    u8 link_id)
 {
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
@@ -7344,10 +7345,14 @@ static int ath12k_mac_config_mon_status_default(struct ath12k *ar, bool enable)
 	if (!ab->hw_params->rxdma1_enable)
 		return ret;
 
-	if (enable)
+	if (enable) {
 		tlv_filter = ath12k_mac_mon_status_filter_default;
-	else
+
+		if (ath12k_debugfs_rx_filter(ar))
+			tlv_filter.rx_filter = ath12k_debugfs_rx_filter(ar);
+	} else {
 		tlv_filter.rxmon_disable = true;
+	}
 
 	for (i = 0; i < ab->hw_params->num_rxdma_per_pdev; i++) {
 		ring_id = ar->dp.rxdma_mon_dst_ring[i].ring_id;
@@ -10451,6 +10456,9 @@ static const struct ieee80211_ops ath12k_ops = {
 	.set_wakeup			= ath12k_wow_op_set_wakeup,
 #endif
 	CFG80211_TESTMODE_CMD(ath12k_tm_cmd)
+#ifdef CONFIG_ATH12K_DEBUGFS
+	.link_sta_add_debugfs           = ath12k_debugfs_link_sta_op_add,
+#endif
 };
 
 static void ath12k_mac_update_ch_list(struct ath12k *ar,
diff --git a/drivers/net/wireless/ath/ath12k/mac.h b/drivers/net/wireless/ath/ath12k/mac.h
index 5a6e3c3316bec..ae35b73312bf2 100644
--- a/drivers/net/wireless/ath/ath12k/mac.h
+++ b/drivers/net/wireless/ath/ath12k/mac.h
@@ -112,5 +112,7 @@ u16 ath12k_mac_he_convert_tones_to_ru_tones(u16 tones);
 enum nl80211_eht_ru_alloc ath12k_mac_eht_ru_tones_to_nl80211_eht_ru_alloc(u16 ru_tones);
 enum nl80211_eht_gi ath12k_mac_eht_gi_to_nl80211_eht_gi(u8 sgi);
 struct ieee80211_bss_conf *ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *arvif);
-
+struct ath12k *ath12k_get_ar_by_vif(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    u8 link_id);
 #endif

From cc5faf08aa3afc6f60d7df1a0edf041c4384fc95 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:07 +0530
Subject: [PATCH 0434/2753] wifi: ath12k: eliminate redundant debug mask check
 in ath12k_dbg()

The current implementation includes a debug mask check both in the macro
expansion and in the function __ath12k_dbg(), which is unnecessary.

Simplify the code by removing the redundant check from the helper function
__ath12k_dbg().

While at this, rename the first argument in macro from ar to ab since the
first argument name in the function __ath12k_dbg() is ab.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-1-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/debug.c | 5 ++---
 drivers/net/wireless/ath/ath12k/debug.h | 4 ++--
 2 files changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debug.c b/drivers/net/wireless/ath/ath12k/debug.c
index ff6eaeafa092c..fd9796b5ad3b9 100644
--- a/drivers/net/wireless/ath/ath12k/debug.c
+++ b/drivers/net/wireless/ath/ath12k/debug.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include <linux/vmalloc.h>
@@ -63,8 +63,7 @@ void __ath12k_dbg(struct ath12k_base *ab, enum ath12k_debug_mask mask,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	if (ath12k_debug_mask & mask)
-		dev_printk(KERN_DEBUG, ab->dev, "%pV", &vaf);
+	dev_printk(KERN_DEBUG, ab->dev, "%pV", &vaf);
 
 	/* TODO: trace log */
 
diff --git a/drivers/net/wireless/ath/ath12k/debug.h b/drivers/net/wireless/ath/ath12k/debug.h
index 0aa7c8ccb14cc..ba0e4da3bb761 100644
--- a/drivers/net/wireless/ath/ath12k/debug.h
+++ b/drivers/net/wireless/ath/ath12k/debug.h
@@ -62,11 +62,11 @@ static inline void ath12k_dbg_dump(struct ath12k_base *ab,
 }
 #endif /* CONFIG_ATH12K_DEBUG */
 
-#define ath12k_dbg(ar, dbg_mask, fmt, ...)			\
+#define ath12k_dbg(ab, dbg_mask, fmt, ...)			\
 do {								\
 	typeof(dbg_mask) mask = (dbg_mask);			\
 	if (ath12k_debug_mask & mask)				\
-		__ath12k_dbg(ar, mask, fmt, ##__VA_ARGS__);	\
+		__ath12k_dbg(ab, mask, fmt, ##__VA_ARGS__);	\
 } while (0)
 
 #endif /* _ATH12K_DEBUG_H_ */

From 80f816d07ba0cf80a9b6aa90a30af2b2073c6cb7 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:08 +0530
Subject: [PATCH 0435/2753] wifi: ath12k: introduce ath12k_generic_dbg()

There might be instances where ath12k_dbg() is needed, but access to
struct ath12k_base (ab) is not readily available. To address this, add
support to print the debug message using printk() when ab is not present.

To avoid the need to explicitly pass NULL each time, introduce a new macro
ath12k_generic_dbg() which resolves to ath12k_dbg() with ab set to NULL.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-2-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/debug.c | 5 ++++-
 drivers/net/wireless/ath/ath12k/debug.h | 3 +++
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/debug.c b/drivers/net/wireless/ath/ath12k/debug.c
index fd9796b5ad3b9..5ce100cd9a9d1 100644
--- a/drivers/net/wireless/ath/ath12k/debug.c
+++ b/drivers/net/wireless/ath/ath12k/debug.c
@@ -63,7 +63,10 @@ void __ath12k_dbg(struct ath12k_base *ab, enum ath12k_debug_mask mask,
 	vaf.fmt = fmt;
 	vaf.va = &args;
 
-	dev_printk(KERN_DEBUG, ab->dev, "%pV", &vaf);
+	if (likely(ab))
+		dev_printk(KERN_DEBUG, ab->dev, "%pV", &vaf);
+	else
+		printk(KERN_DEBUG "ath12k: %pV", &vaf);
 
 	/* TODO: trace log */
 
diff --git a/drivers/net/wireless/ath/ath12k/debug.h b/drivers/net/wireless/ath/ath12k/debug.h
index ba0e4da3bb761..48916e4e1f601 100644
--- a/drivers/net/wireless/ath/ath12k/debug.h
+++ b/drivers/net/wireless/ath/ath12k/debug.h
@@ -69,4 +69,7 @@ do {								\
 		__ath12k_dbg(ab, mask, fmt, ##__VA_ARGS__);	\
 } while (0)
 
+#define ath12k_generic_dbg(dbg_mask, fmt, ...)			\
+	ath12k_dbg(NULL, dbg_mask, fmt, ##__VA_ARGS__)
+
 #endif /* _ATH12K_DEBUG_H_ */

From ab6270c4dec3b1a506291c3b0050230b32464781 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:09 +0530
Subject: [PATCH 0436/2753] wifi: ath12k: remove redundant vif settings during
 link interface creation

Currently, vif level settings are done in ath12k_mac_assign_link_vif() as
well as in ath12k_mac_op_add_interface(). Since it is vif level settings,
doing this on per link does not make sense and it contributes to redundant
code. Get rid of this redundant code from ath12k_mac_assign_link_vif().

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-3-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 664b13c259654..7168b268b4a10 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4023,13 +4023,6 @@ static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
 		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
 	}
 
-	/* Allocate Default Queue now and reassign during actual vdev create */
-	vif->cab_queue = ATH12K_HW_DEFAULT_QUEUE;
-	for (i = 0; i < ARRAY_SIZE(vif->hw_queue); i++)
-		vif->hw_queue[i] = ATH12K_HW_DEFAULT_QUEUE;
-
-	vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
-
 	rcu_assign_pointer(ahvif->link[arvif->link_id], arvif);
 	ahvif->links_map |= BIT(link_id);
 	synchronize_rcu();

From 8acc7ec53ac43aea8f49573b5a173570f308b775 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:10 +0530
Subject: [PATCH 0437/2753] wifi: ath12k: remove redundant logic for
 initializing arvif

The current logic for initializing arvif is present in both the add
interface operation callback and ath12k_mac_assign_link_vif(). The former
handles deflink initialization, while the latter is responsible for other
links. This redundancy could be avoided by using a common helper function.

Hence, add a new helper ath12k_mac_init_arvif() which initializes a
given arvif.

Since synchronizing rcu is not required after adding a rcu pointer, remove
that now.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-4-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 80 ++++++++++++++++-----------
 1 file changed, 49 insertions(+), 31 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 7168b268b4a10..b7f605eeb254f 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3974,13 +3974,59 @@ static void ath12k_mac_op_link_info_changed(struct ieee80211_hw *hw,
 	ath12k_mac_bss_info_changed(ar, arvif, info, changed);
 }
 
+static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif,
+				  struct ath12k_link_vif *arvif, int link_id)
+{
+	struct ath12k_hw *ah = ahvif->ah;
+	u8 _link_id;
+	int i;
+
+	lockdep_assert_wiphy(ah->hw->wiphy);
+
+	if (WARN_ON(!arvif))
+		return;
+
+	if (WARN_ON(link_id >= ATH12K_NUM_MAX_LINKS))
+		return;
+
+	if (link_id < 0)
+		_link_id = 0;
+	else
+		_link_id = link_id;
+
+	arvif->ahvif = ahvif;
+	arvif->link_id = _link_id;
+
+	INIT_LIST_HEAD(&arvif->list);
+	INIT_DELAYED_WORK(&arvif->connection_loss_work,
+			  ath12k_mac_vif_sta_connection_loss_work);
+
+	for (i = 0; i < ARRAY_SIZE(arvif->bitrate_mask.control); i++) {
+		arvif->bitrate_mask.control[i].legacy = 0xffffffff;
+		memset(arvif->bitrate_mask.control[i].ht_mcs, 0xff,
+		       sizeof(arvif->bitrate_mask.control[i].ht_mcs));
+		memset(arvif->bitrate_mask.control[i].vht_mcs, 0xff,
+		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
+	}
+
+	/* Handle MLO related assignments */
+	if (link_id >= 0) {
+		rcu_assign_pointer(ahvif->link[arvif->link_id], arvif);
+		ahvif->links_map |= BIT(_link_id);
+	}
+
+	ath12k_generic_dbg(ATH12K_DBG_MAC,
+			   "mac init link arvif (link_id %d%s) for vif %pM. links_map 0x%x",
+			   _link_id, (link_id < 0) ? " deflink" : "", ahvif->vif->addr,
+			   ahvif->links_map);
+}
+
 static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
 							  struct ieee80211_vif *vif,
 							  u8 link_id)
 {
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
 	struct ath12k_link_vif *arvif;
-	int i;
 
 	lockdep_assert_wiphy(ah->hw->wiphy);
 
@@ -4007,25 +4053,8 @@ static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
 		}
 	}
 
-	arvif->ahvif = ahvif;
-	arvif->link_id = link_id;
-	ahvif->links_map |= BIT(link_id);
-
-	INIT_LIST_HEAD(&arvif->list);
-	INIT_DELAYED_WORK(&arvif->connection_loss_work,
-			  ath12k_mac_vif_sta_connection_loss_work);
-
-	for (i = 0; i < ARRAY_SIZE(arvif->bitrate_mask.control); i++) {
-		arvif->bitrate_mask.control[i].legacy = 0xffffffff;
-		memset(arvif->bitrate_mask.control[i].ht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].ht_mcs));
-		memset(arvif->bitrate_mask.control[i].vht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
-	}
+	ath12k_mac_init_arvif(ahvif, arvif, link_id);
 
-	rcu_assign_pointer(ahvif->link[arvif->link_id], arvif);
-	ahvif->links_map |= BIT(link_id);
-	synchronize_rcu();
 	return arvif;
 }
 
@@ -8318,19 +8347,8 @@ static int ath12k_mac_op_add_interface(struct ieee80211_hw *hw,
 	ahvif->ah = ah;
 	ahvif->vif = vif;
 	arvif = &ahvif->deflink;
-	arvif->ahvif = ahvif;
-
-	INIT_LIST_HEAD(&arvif->list);
-	INIT_DELAYED_WORK(&arvif->connection_loss_work,
-			  ath12k_mac_vif_sta_connection_loss_work);
 
-	for (i = 0; i < ARRAY_SIZE(arvif->bitrate_mask.control); i++) {
-		arvif->bitrate_mask.control[i].legacy = 0xffffffff;
-		memset(arvif->bitrate_mask.control[i].ht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].ht_mcs));
-		memset(arvif->bitrate_mask.control[i].vht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
-	}
+	ath12k_mac_init_arvif(ahvif, arvif, -1);
 
 	/* Allocate Default Queue now and reassign during actual vdev create */
 	vif->cab_queue = ATH12K_HW_DEFAULT_QUEUE;

From 00e4dc11695d48322780812b503314682659e98b Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:11 +0530
Subject: [PATCH 0438/2753] wifi: ath12k: use arvif instead of link_conf in
 ath12k_mac_set_key()

Currently, in ath12k_mac_set_key(), if sta is not present, the address is
retrieved from link_conf's bssid or addr member, depending on the interface
type.

When operating as an ML station and during shutdown, link_conf will not be
available. This can result in the following error:

ath12k_pci 0004:01:00.0: unable to access bss link conf in set key for vif AA:BB:CC:DD:EE:FF link 1

The primary purpose of accessing link_conf is to obtain the address for
finding the peer. However, since arvif is always valid in this call, it can
be used instead.

Add change to use arvif instead of link_conf.

A subsequent change will expose this issue but since tear down will give
error, this is included first.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-5-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index b7f605eeb254f..97d7f95a3796d 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -4668,9 +4668,6 @@ static int ath12k_mac_set_key(struct ath12k *ar, enum set_key_cmd cmd,
 			      struct ath12k_link_sta *arsta,
 			      struct ieee80211_key_conf *key)
 {
-	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
-	struct ieee80211_bss_conf *link_conf;
 	struct ieee80211_sta *sta = NULL;
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_peer *peer;
@@ -4687,19 +4684,10 @@ static int ath12k_mac_set_key(struct ath12k *ar, enum set_key_cmd cmd,
 	if (test_bit(ATH12K_FLAG_HW_CRYPTO_DISABLED, &ab->dev_flags))
 		return 1;
 
-	link_conf = ath12k_mac_get_link_bss_conf(arvif);
-	if (!link_conf) {
-		ath12k_warn(ab, "unable to access bss link conf in set key for vif %pM link %u\n",
-			    vif->addr, arvif->link_id);
-		return -ENOLINK;
-	}
-
 	if (sta)
 		peer_addr = arsta->addr;
-	else if (ahvif->vdev_type == WMI_VDEV_TYPE_STA)
-		peer_addr = link_conf->bssid;
 	else
-		peer_addr = link_conf->addr;
+		peer_addr = arvif->bssid;
 
 	key->hw_key_idx = key->keyidx;
 

From b81c39d67fbfcaccb33a1fc5494a87b29f2724ab Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:12 +0530
Subject: [PATCH 0439/2753] wifi: ath12k: relocate a few functions in mac.c

An upcoming change will invoke ath12k_mac_init_arvif(),
ath12k_mac_assign_link_vif(), ath12k_mac_unassign_link_vif(), and
ath12k_mac_remove_link_interface() from a line located above their current
definition. Hence, relocate these functions to above so that these can be
invoked later on.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-6-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 250 +++++++++++++-------------
 1 file changed, 125 insertions(+), 125 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 97d7f95a3796d..493d3d43b121d 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3470,6 +3470,131 @@ static void ath12k_recalculate_mgmt_rate(struct ath12k *ar,
 		ath12k_warn(ar->ab, "failed to set beacon tx rate %d\n", ret);
 }
 
+static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif,
+				  struct ath12k_link_vif *arvif, int link_id)
+{
+	struct ath12k_hw *ah = ahvif->ah;
+	u8 _link_id;
+	int i;
+
+	lockdep_assert_wiphy(ah->hw->wiphy);
+
+	if (WARN_ON(!arvif))
+		return;
+
+	if (WARN_ON(link_id >= ATH12K_NUM_MAX_LINKS))
+		return;
+
+	if (link_id < 0)
+		_link_id = 0;
+	else
+		_link_id = link_id;
+
+	arvif->ahvif = ahvif;
+	arvif->link_id = _link_id;
+
+	INIT_LIST_HEAD(&arvif->list);
+	INIT_DELAYED_WORK(&arvif->connection_loss_work,
+			  ath12k_mac_vif_sta_connection_loss_work);
+
+	for (i = 0; i < ARRAY_SIZE(arvif->bitrate_mask.control); i++) {
+		arvif->bitrate_mask.control[i].legacy = 0xffffffff;
+		memset(arvif->bitrate_mask.control[i].ht_mcs, 0xff,
+		       sizeof(arvif->bitrate_mask.control[i].ht_mcs));
+		memset(arvif->bitrate_mask.control[i].vht_mcs, 0xff,
+		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
+	}
+
+	/* Handle MLO related assignments */
+	if (link_id >= 0) {
+		rcu_assign_pointer(ahvif->link[arvif->link_id], arvif);
+		ahvif->links_map |= BIT(_link_id);
+	}
+
+	ath12k_generic_dbg(ATH12K_DBG_MAC,
+			   "mac init link arvif (link_id %d%s) for vif %pM. links_map 0x%x",
+			   _link_id, (link_id < 0) ? " deflink" : "", ahvif->vif->addr,
+			   ahvif->links_map);
+}
+
+static void ath12k_mac_remove_link_interface(struct ieee80211_hw *hw,
+					     struct ath12k_link_vif *arvif)
+{
+	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ath12k_hw *ah = hw->priv;
+	struct ath12k *ar = arvif->ar;
+	int ret;
+
+	lockdep_assert_wiphy(ah->hw->wiphy);
+
+	cancel_delayed_work_sync(&arvif->connection_loss_work);
+
+	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac remove link interface (vdev %d link id %d)",
+		   arvif->vdev_id, arvif->link_id);
+
+	if (ahvif->vdev_type == WMI_VDEV_TYPE_AP) {
+		ret = ath12k_peer_delete(ar, arvif->vdev_id, arvif->bssid);
+		if (ret)
+			ath12k_warn(ar->ab, "failed to submit AP self-peer removal on vdev %d link id %d: %d",
+				    arvif->vdev_id, arvif->link_id, ret);
+	}
+	ath12k_mac_vdev_delete(ar, arvif);
+}
+
+static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
+							  struct ieee80211_vif *vif,
+							  u8 link_id)
+{
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	struct ath12k_link_vif *arvif;
+
+	lockdep_assert_wiphy(ah->hw->wiphy);
+
+	arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]);
+	if (arvif)
+		return arvif;
+
+	if (!vif->valid_links) {
+		/* Use deflink for Non-ML VIFs and mark the link id as 0
+		 */
+		link_id = 0;
+		arvif = &ahvif->deflink;
+	} else {
+		/* If this is the first link arvif being created for an ML VIF
+		 * use the preallocated deflink memory except for scan arvifs
+		 */
+		if (!ahvif->links_map && link_id != ATH12K_DEFAULT_SCAN_LINK) {
+			arvif = &ahvif->deflink;
+		} else {
+			arvif = (struct ath12k_link_vif *)
+			kzalloc(sizeof(struct ath12k_link_vif), GFP_KERNEL);
+			if (!arvif)
+				return NULL;
+		}
+	}
+
+	ath12k_mac_init_arvif(ahvif, arvif, link_id);
+
+	return arvif;
+}
+
+static void ath12k_mac_unassign_link_vif(struct ath12k_link_vif *arvif)
+{
+	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ath12k_hw *ah = ahvif->ah;
+
+	lockdep_assert_wiphy(ah->hw->wiphy);
+
+	rcu_assign_pointer(ahvif->link[arvif->link_id], NULL);
+	synchronize_rcu();
+	ahvif->links_map &= ~BIT(arvif->link_id);
+
+	if (arvif != &ahvif->deflink)
+		kfree(arvif);
+	else
+		memset(arvif, 0, sizeof(*arvif));
+}
+
 static int
 ath12k_mac_op_change_vif_links(struct ieee80211_hw *hw,
 			       struct ieee80211_vif *vif,
@@ -3974,131 +4099,6 @@ static void ath12k_mac_op_link_info_changed(struct ieee80211_hw *hw,
 	ath12k_mac_bss_info_changed(ar, arvif, info, changed);
 }
 
-static void ath12k_mac_init_arvif(struct ath12k_vif *ahvif,
-				  struct ath12k_link_vif *arvif, int link_id)
-{
-	struct ath12k_hw *ah = ahvif->ah;
-	u8 _link_id;
-	int i;
-
-	lockdep_assert_wiphy(ah->hw->wiphy);
-
-	if (WARN_ON(!arvif))
-		return;
-
-	if (WARN_ON(link_id >= ATH12K_NUM_MAX_LINKS))
-		return;
-
-	if (link_id < 0)
-		_link_id = 0;
-	else
-		_link_id = link_id;
-
-	arvif->ahvif = ahvif;
-	arvif->link_id = _link_id;
-
-	INIT_LIST_HEAD(&arvif->list);
-	INIT_DELAYED_WORK(&arvif->connection_loss_work,
-			  ath12k_mac_vif_sta_connection_loss_work);
-
-	for (i = 0; i < ARRAY_SIZE(arvif->bitrate_mask.control); i++) {
-		arvif->bitrate_mask.control[i].legacy = 0xffffffff;
-		memset(arvif->bitrate_mask.control[i].ht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].ht_mcs));
-		memset(arvif->bitrate_mask.control[i].vht_mcs, 0xff,
-		       sizeof(arvif->bitrate_mask.control[i].vht_mcs));
-	}
-
-	/* Handle MLO related assignments */
-	if (link_id >= 0) {
-		rcu_assign_pointer(ahvif->link[arvif->link_id], arvif);
-		ahvif->links_map |= BIT(_link_id);
-	}
-
-	ath12k_generic_dbg(ATH12K_DBG_MAC,
-			   "mac init link arvif (link_id %d%s) for vif %pM. links_map 0x%x",
-			   _link_id, (link_id < 0) ? " deflink" : "", ahvif->vif->addr,
-			   ahvif->links_map);
-}
-
-static struct ath12k_link_vif *ath12k_mac_assign_link_vif(struct ath12k_hw *ah,
-							  struct ieee80211_vif *vif,
-							  u8 link_id)
-{
-	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
-	struct ath12k_link_vif *arvif;
-
-	lockdep_assert_wiphy(ah->hw->wiphy);
-
-	arvif = wiphy_dereference(ah->hw->wiphy, ahvif->link[link_id]);
-	if (arvif)
-		return arvif;
-
-	if (!vif->valid_links) {
-		/* Use deflink for Non-ML VIFs and mark the link id as 0
-		 */
-		link_id = 0;
-		arvif = &ahvif->deflink;
-	} else {
-		/* If this is the first link arvif being created for an ML VIF
-		 * use the preallocated deflink memory except for scan arvifs
-		 */
-		if (!ahvif->links_map && link_id != ATH12K_DEFAULT_SCAN_LINK) {
-			arvif = &ahvif->deflink;
-		} else {
-			arvif = (struct ath12k_link_vif *)
-			kzalloc(sizeof(struct ath12k_link_vif), GFP_KERNEL);
-			if (!arvif)
-				return NULL;
-		}
-	}
-
-	ath12k_mac_init_arvif(ahvif, arvif, link_id);
-
-	return arvif;
-}
-
-static void ath12k_mac_unassign_link_vif(struct ath12k_link_vif *arvif)
-{
-	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ath12k_hw *ah = ahvif->ah;
-
-	lockdep_assert_wiphy(ah->hw->wiphy);
-
-	rcu_assign_pointer(ahvif->link[arvif->link_id], NULL);
-	synchronize_rcu();
-	ahvif->links_map &= ~BIT(arvif->link_id);
-
-	if (arvif != &ahvif->deflink)
-		kfree(arvif);
-	else
-		memset(arvif, 0, sizeof(*arvif));
-}
-
-static void ath12k_mac_remove_link_interface(struct ieee80211_hw *hw,
-					     struct ath12k_link_vif *arvif)
-{
-	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ath12k_hw *ah = hw->priv;
-	struct ath12k *ar = arvif->ar;
-	int ret;
-
-	lockdep_assert_wiphy(ah->hw->wiphy);
-
-	cancel_delayed_work_sync(&arvif->connection_loss_work);
-
-	ath12k_dbg(ar->ab, ATH12K_DBG_MAC, "mac remove link interface (vdev %d link id %d)",
-		   arvif->vdev_id, arvif->link_id);
-
-	if (ahvif->vdev_type == WMI_VDEV_TYPE_AP) {
-		ret = ath12k_peer_delete(ar, arvif->vdev_id, arvif->bssid);
-		if (ret)
-			ath12k_warn(ar->ab, "failed to submit AP self-peer removal on vdev %d link id %d: %d",
-				    arvif->vdev_id, arvif->link_id, ret);
-	}
-	ath12k_mac_vdev_delete(ar, arvif);
-}
-
 static struct ath12k*
 ath12k_mac_select_scan_device(struct ieee80211_hw *hw,
 			      struct ieee80211_vif *vif,

From 315d80be304ac1d47da38c2b0c85286c9220c23a Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:13 +0530
Subject: [PATCH 0440/2753] wifi: ath12k: allocate new links in
 change_vif_links()

Currently, links in an interface are allocated during channel assignment
via assign_vif_chanctx(). Conversely, links are deleted during channel
unassignment via unassign_vif_chanctx(). However, deleting links during
channel unassignment does not comply with mac80211 link handling.
Therefore, this process should be managed within change_vif_links(). To
maintain symmetry, link addition should also be handled in
change_vif_links().

Hence, add changes to allocate link arvif in change_vif_links(). Creating
the link interface on firmware will still be done during channel
assignment.

And since link will be created but channel might not be assigned, there is
a need now to test is_created flag in ath12k_mac_mlo_get_vdev_args() before
accessing link_conf or else link bring up will fail.

A subsequent change will handle link removal part.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-7-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 28 +++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 493d3d43b121d..156ea7a975d91 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3601,6 +3601,31 @@ ath12k_mac_op_change_vif_links(struct ieee80211_hw *hw,
 			       u16 old_links, u16 new_links,
 			       struct ieee80211_bss_conf *ol[IEEE80211_MLD_MAX_NUM_LINKS])
 {
+	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	unsigned long to_add = ~old_links & new_links;
+	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
+	struct ath12k_link_vif *arvif;
+	u8 link_id;
+
+	lockdep_assert_wiphy(hw->wiphy);
+
+	ath12k_generic_dbg(ATH12K_DBG_MAC,
+			   "mac vif link changed for MLD %pM old_links 0x%x new_links 0x%x\n",
+			   vif->addr, old_links, new_links);
+
+	for_each_set_bit(link_id, &to_add, IEEE80211_MLD_MAX_NUM_LINKS) {
+		arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+		/* mac80211 wants to add link but driver already has the
+		 * link. This should not happen ideally.
+		 */
+		if (WARN_ON(arvif))
+			return -EINVAL;
+
+		arvif = ath12k_mac_assign_link_vif(ah, vif, link_id);
+		if (WARN_ON(!arvif))
+			return -EINVAL;
+	}
+
 	return 0;
 }
 
@@ -8771,6 +8796,9 @@ ath12k_mac_mlo_get_vdev_args(struct ath12k_link_vif *arvif,
 		if (arvif == arvif_p)
 			continue;
 
+		if (!arvif_p->is_created)
+			continue;
+
 		link_conf = wiphy_dereference(ahvif->ah->hw->wiphy,
 					      ahvif->vif->link_conf[arvif_p->link_id]);
 

From 81e4be30544ee7e8da80e9aae7acd69d3be6d05a Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Tue, 4 Feb 2025 22:35:14 +0530
Subject: [PATCH 0441/2753] wifi: ath12k: handle link removal in
 change_vif_links()

Currently, the link interface is deleted during channel unassignment, which
does not align with mac80211 link handling. Therefore, add changes to only
perform vdev stop during channel unassignment. The actual vdev deletion
will occur in change_vif_links().

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00130-QCAHKSWPL_SILICONZ-1.97421.5 # Nicolas Escande

Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Tested-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://patch.msgid.link/20250204-unlink_link_arvif_from_chanctx-v2-8-764fb5973c1a@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 156ea7a975d91..c9f7bea4e04a9 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -3602,6 +3602,7 @@ ath12k_mac_op_change_vif_links(struct ieee80211_hw *hw,
 			       struct ieee80211_bss_conf *ol[IEEE80211_MLD_MAX_NUM_LINKS])
 {
 	struct ath12k_vif *ahvif = ath12k_vif_to_ahvif(vif);
+	unsigned long to_remove = old_links & ~new_links;
 	unsigned long to_add = ~old_links & new_links;
 	struct ath12k_hw *ah = ath12k_hw_to_ah(hw);
 	struct ath12k_link_vif *arvif;
@@ -3626,6 +3627,21 @@ ath12k_mac_op_change_vif_links(struct ieee80211_hw *hw,
 			return -EINVAL;
 	}
 
+	for_each_set_bit(link_id, &to_remove, IEEE80211_MLD_MAX_NUM_LINKS) {
+		arvif = wiphy_dereference(hw->wiphy, ahvif->link[link_id]);
+		if (WARN_ON(!arvif))
+			return -EINVAL;
+
+		if (!arvif->is_created)
+			continue;
+
+		if (WARN_ON(!arvif->ar))
+			return -EINVAL;
+
+		ath12k_mac_remove_link_interface(hw, arvif);
+		ath12k_mac_unassign_link_vif(arvif);
+	}
+
 	return 0;
 }
 
@@ -9444,9 +9460,6 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
 	if (ahvif->vdev_type != WMI_VDEV_TYPE_MONITOR &&
 	    ar->num_started_vdevs == 1 && ar->monitor_vdev_created)
 		ath12k_mac_monitor_stop(ar);
-
-	ath12k_mac_remove_link_interface(hw, arvif);
-	ath12k_mac_unassign_link_vif(arvif);
 }
 
 static int

From 16c6c35c03ea73054a1f6d3302a4ce4a331b427d Mon Sep 17 00:00:00 2001
From: P Praneesh <quic_ppranees@quicinc.com>
Date: Thu, 19 Dec 2024 19:05:30 +0800
Subject: [PATCH 0442/2753] wifi: ath11k: fix RCU stall while reaping monitor
 destination ring

While processing the monitor destination ring, MSDUs are reaped from the
link descriptor based on the corresponding buf_id.

However, sometimes the driver cannot obtain a valid buffer corresponding
to the buf_id received from the hardware. This causes an infinite loop
in the destination processing, resulting in a kernel crash.

kernel log:
ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309
ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed
ath11k_pci 0000:58:00.0: data msdu_pop: invalid buf_id 309
ath11k_pci 0000:58:00.0: data dp_rx_monitor_link_desc_return failed

Fix this by skipping the problematic buf_id and reaping the next entry,
replacing the break with the next MSDU processing.

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Signed-off-by: P Praneesh <quic_ppranees@quicinc.com>
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Kalle Valo <kvalo@kernel.org>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20241219110531.2096-2-quic_kangyang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index 640d617a585af..d010b25b8503f 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -4772,7 +4772,7 @@ u32 ath11k_dp_rx_mon_mpdu_pop(struct ath11k *ar, int mac_id,
 			if (!msdu) {
 				ath11k_dbg(ar->ab, ATH11K_DBG_DATA,
 					   "msdu_pop: invalid buf_id %d\n", buf_id);
-				break;
+				goto next_msdu;
 			}
 			rxcb = ATH11K_SKB_RXCB(msdu);
 			if (!rxcb->unmapped) {
@@ -5399,7 +5399,7 @@ ath11k_dp_rx_full_mon_mpdu_pop(struct ath11k *ar,
 					   "full mon msdu_pop: invalid buf_id %d\n",
 					    buf_id);
 				spin_unlock_bh(&rx_ring->idr_lock);
-				break;
+				goto next_msdu;
 			}
 			idr_remove(&rx_ring->bufs_idr, buf_id);
 			spin_unlock_bh(&rx_ring->idr_lock);

From 63b7af49496d0e32f7a748b6af3361ec138b1bd3 Mon Sep 17 00:00:00 2001
From: Kang Yang <quic_kangyang@quicinc.com>
Date: Thu, 19 Dec 2024 19:05:31 +0800
Subject: [PATCH 0443/2753] wifi: ath11k: add srng->lock for ath11k_hal_srng_*
 in monitor mode

ath11k_hal_srng_* should be used with srng->lock to protect srng data.

For ath11k_dp_rx_mon_dest_process() and ath11k_dp_full_mon_process_rx(),
they use ath11k_hal_srng_* for many times but never call srng->lock.

So when running (full) monitor mode, warning will occur:
RIP: 0010:ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k]
Call Trace:
 ? ath11k_hal_srng_dst_peek+0x18/0x30 [ath11k]
 ath11k_dp_rx_process_mon_status+0xc45/0x1190 [ath11k]
 ? idr_alloc_u32+0x97/0xd0
 ath11k_dp_rx_process_mon_rings+0x32a/0x550 [ath11k]
 ath11k_dp_service_srng+0x289/0x5a0 [ath11k]
 ath11k_pcic_ext_grp_napi_poll+0x30/0xd0 [ath11k]
 __napi_poll+0x30/0x1f0
 net_rx_action+0x198/0x320
 __do_softirq+0xdd/0x319

So add srng->lock for them to avoid such warnings.

Inorder to fetch the srng->lock, should change srng's definition from
'void' to 'struct hal_srng'. And initialize them elsewhere to prevent
one line of code from being too long. This is consistent with other ring
process functions, such as ath11k_dp_process_rx().

Tested-on: WCN6855 hw2.0 PCI WLAN.HSP.1.1-03125-QCAHSPSWPL_V1_V2_SILICONZ_LITE-3.6510.30
Tested-on: QCN9074 hw1.0 PCI WLAN.HK.2.7.0.1-01744-QCAHKSWPL_SILICONZ-1

Fixes: d5c65159f289 ("ath11k: driver for Qualcomm IEEE 802.11ax devices")
Signed-off-by: Kang Yang <quic_kangyang@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20241219110531.2096-3-quic_kangyang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/dp_rx.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
index d010b25b8503f..f2bdbac2a0b7f 100644
--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
@@ -5137,7 +5137,7 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, int mac_id,
 	struct ath11k_mon_data *pmon = (struct ath11k_mon_data *)&dp->mon_data;
 	const struct ath11k_hw_hal_params *hal_params;
 	void *ring_entry;
-	void *mon_dst_srng;
+	struct hal_srng *mon_dst_srng;
 	u32 ppdu_id;
 	u32 rx_bufs_used;
 	u32 ring_id;
@@ -5154,6 +5154,7 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, int mac_id,
 
 	spin_lock_bh(&pmon->mon_lock);
 
+	spin_lock_bh(&mon_dst_srng->lock);
 	ath11k_hal_srng_access_begin(ar->ab, mon_dst_srng);
 
 	ppdu_id = pmon->mon_ppdu_info.ppdu_id;
@@ -5212,6 +5213,7 @@ static void ath11k_dp_rx_mon_dest_process(struct ath11k *ar, int mac_id,
 								mon_dst_srng);
 	}
 	ath11k_hal_srng_access_end(ar->ab, mon_dst_srng);
+	spin_unlock_bh(&mon_dst_srng->lock);
 
 	spin_unlock_bh(&pmon->mon_lock);
 
@@ -5601,7 +5603,7 @@ static int ath11k_dp_full_mon_process_rx(struct ath11k_base *ab, int mac_id,
 	struct hal_sw_mon_ring_entries *sw_mon_entries;
 	struct ath11k_pdev_mon_stats *rx_mon_stats;
 	struct sk_buff *head_msdu, *tail_msdu;
-	void *mon_dst_srng = &ar->ab->hal.srng_list[dp->rxdma_mon_dst_ring.ring_id];
+	struct hal_srng *mon_dst_srng;
 	void *ring_entry;
 	u32 rx_bufs_used = 0, mpdu_rx_bufs_used;
 	int quota = 0, ret;
@@ -5617,6 +5619,9 @@ static int ath11k_dp_full_mon_process_rx(struct ath11k_base *ab, int mac_id,
 		goto reap_status_ring;
 	}
 
+	mon_dst_srng = &ar->ab->hal.srng_list[dp->rxdma_mon_dst_ring.ring_id];
+	spin_lock_bh(&mon_dst_srng->lock);
+
 	ath11k_hal_srng_access_begin(ar->ab, mon_dst_srng);
 	while ((ring_entry = ath11k_hal_srng_dst_peek(ar->ab, mon_dst_srng))) {
 		head_msdu = NULL;
@@ -5660,6 +5665,7 @@ static int ath11k_dp_full_mon_process_rx(struct ath11k_base *ab, int mac_id,
 	}
 
 	ath11k_hal_srng_access_end(ar->ab, mon_dst_srng);
+	spin_unlock_bh(&mon_dst_srng->lock);
 	spin_unlock_bh(&pmon->mon_lock);
 
 	if (rx_bufs_used) {

From 5d964966bd3ff48af92d941e1dcb581e6e572642 Mon Sep 17 00:00:00 2001
From: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Date: Mon, 3 Feb 2025 13:26:46 -0800
Subject: [PATCH 0444/2753] wifi: ath12k: Update HTT_TCL_METADATA version and
 bit mask definitions

Update the HTT_TCL_METADATA version to the latest version (2)
as the bit definitions have changed a little to support more
features. This new version allows the host to submit a packet with
more information to the firmware. Firmware uses this additional
information to do special processing for certain frames.

All the firmware binaries available in upstream/public are compatible with
this HTT version update.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250203212647.2694566-2-quic_bmahalin@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp.h    | 21 ++++++++++++++-------
 drivers/net/wireless/ath/ath12k/dp_tx.c | 11 +++++++++--
 2 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index f68bb78d4a110..7cdc62aa35be1 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_H
@@ -372,17 +372,18 @@ struct ath12k_dp {
 };
 
 /* HTT definitions */
+#define HTT_TAG_TCL_METADATA_VERSION		5
 
-#define HTT_TCL_META_DATA_TYPE			BIT(0)
-#define HTT_TCL_META_DATA_VALID_HTT		BIT(1)
+#define HTT_TCL_META_DATA_TYPE			GENMASK(1, 0)
+#define HTT_TCL_META_DATA_VALID_HTT		BIT(2)
 
 /* vdev meta data */
-#define HTT_TCL_META_DATA_VDEV_ID		GENMASK(9, 2)
-#define HTT_TCL_META_DATA_PDEV_ID		GENMASK(11, 10)
-#define HTT_TCL_META_DATA_HOST_INSPECTED	BIT(12)
+#define HTT_TCL_META_DATA_VDEV_ID		 GENMASK(10, 3)
+#define HTT_TCL_META_DATA_PDEV_ID		 GENMASK(12, 11)
+#define HTT_TCL_META_DATA_HOST_INSPECTED_MISSION BIT(13)
 
 /* peer meta data */
-#define HTT_TCL_META_DATA_PEER_ID		GENMASK(15, 2)
+#define HTT_TCL_META_DATA_PEER_ID		GENMASK(15, 3)
 
 /* HTT tx completion is overlaid in wbm_release_ring */
 #define HTT_TX_WBM_COMP_INFO0_STATUS		GENMASK(16, 13)
@@ -413,9 +414,15 @@ enum htt_h2t_msg_type {
 };
 
 #define HTT_VER_REQ_INFO_MSG_ID		GENMASK(7, 0)
+#define HTT_OPTION_TCL_METADATA_VER_V2	2
+#define HTT_OPTION_TAG			GENMASK(7, 0)
+#define HTT_OPTION_LEN			GENMASK(15, 8)
+#define HTT_OPTION_VALUE		GENMASK(31, 16)
+#define HTT_TCL_METADATA_VER_SZ		4
 
 struct htt_ver_req_cmd {
 	__le32 ver_reg_info;
+	__le32 tcl_metadata_version;
 } __packed;
 
 enum htt_srng_ring_type {
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 94310bcc620cb..da30d1054f61e 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: BSD-3-Clause-Clear
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #include "core.h"
@@ -1103,7 +1103,14 @@ int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab)
 	skb_put(skb, len);
 	cmd = (struct htt_ver_req_cmd *)skb->data;
 	cmd->ver_reg_info = le32_encode_bits(HTT_H2T_MSG_TYPE_VERSION_REQ,
-					     HTT_VER_REQ_INFO_MSG_ID);
+					     HTT_OPTION_TAG);
+
+	cmd->tcl_metadata_version = le32_encode_bits(HTT_TAG_TCL_METADATA_VERSION,
+						     HTT_OPTION_TAG) |
+				    le32_encode_bits(HTT_TCL_METADATA_VER_SZ,
+						     HTT_OPTION_LEN) |
+				    le32_encode_bits(HTT_OPTION_TCL_METADATA_VER_V2,
+						     HTT_OPTION_VALUE);
 
 	ret = ath12k_htc_send(&ab->htc, dp->eid, skb);
 	if (ret) {

From 2f50de7256777003d40931f1732e6c644ec8cb80 Mon Sep 17 00:00:00 2001
From: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Date: Mon, 3 Feb 2025 13:26:47 -0800
Subject: [PATCH 0445/2753] wifi: ath12k: Add support for MLO Multicast
 handling in driver

For MLO netdevice, the broadcast frame should be transmitted with the
same sequence number on all the links.

Per IEEE 802.11be-2024 section 10.3.2.14.2 "Transmitter requirements",
An AP MLD shall use SNS11 in Table 10-5 (Transmitter sequence number
spaces) maintained by the MLD to determine the sequence number of a
group addressed data frame that is transmitted by an AP affiliated
with the AP MLD so that the same group addressed Data frame
transmitted over multiple links by the AP MLD uses the same
sequence number for transmission on each link.

Currently the MLO multicast handling is done in the mac80211 layer.
Enable support for handling MLO Multicast in the driver to update the
hardware descriptors in a custom way to handle the multicast frames.
Firmware expects the MLO multicast frames to the submitted to the
hardware with special vdev_id (actual vdev_id + 128) to recognize it as
a host inspected frame to avoid using the reinjected path and it also
uses the multicast global sequence number (GSN) provided by the host
in the HTT metadata to process and transmit it with the same sequence
number.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Balamurugan Mahalingam <quic_bmahalin@quicinc.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250203212647.2694566-3-quic_bmahalin@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.h  |   1 +
 drivers/net/wireless/ath/ath12k/dp.h    |   6 ++
 drivers/net/wireless/ath/ath12k/dp_tx.c |  16 ++-
 drivers/net/wireless/ath/ath12k/dp_tx.h |   4 +-
 drivers/net/wireless/ath/ath12k/mac.c   | 123 +++++++++++++++++++++++-
 5 files changed, 142 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index b60a636a6e19f..e9388bdf532da 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -332,6 +332,7 @@ struct ath12k_vif {
 	u32 key_cipher;
 	u8 tx_encap_type;
 	bool ps;
+	atomic_t mcbc_gsn;
 
 	struct ath12k_link_vif deflink;
 	struct ath12k_link_vif __rcu *link[ATH12K_NUM_MAX_LINKS];
diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
index 7cdc62aa35be1..75435a931548c 100644
--- a/drivers/net/wireless/ath/ath12k/dp.h
+++ b/drivers/net/wireless/ath/ath12k/dp.h
@@ -385,6 +385,12 @@ struct ath12k_dp {
 /* peer meta data */
 #define HTT_TCL_META_DATA_PEER_ID		GENMASK(15, 3)
 
+/* Global sequence number */
+#define HTT_TCL_META_DATA_TYPE_GLOBAL_SEQ_NUM		3
+#define HTT_TCL_META_DATA_GLOBAL_SEQ_HOST_INSPECTED	BIT(2)
+#define HTT_TCL_META_DATA_GLOBAL_SEQ_NUM		GENMASK(14, 3)
+#define HTT_TX_MLO_MCAST_HOST_REINJECT_BASE_VDEV_ID	128
+
 /* HTT tx completion is overlaid in wbm_release_ring */
 #define HTT_TX_WBM_COMP_INFO0_STATUS		GENMASK(16, 13)
 #define HTT_TX_WBM_COMP_INFO1_REINJECT_REASON	GENMASK(3, 0)
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index da30d1054f61e..4e11b7b61b823 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -219,7 +219,7 @@ static int ath12k_dp_tx_align_payload(struct ath12k_base *ab,
 }
 
 int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
-		 struct sk_buff *skb)
+		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn)
 {
 	struct ath12k_base *ab = ar->ab;
 	struct ath12k_dp *dp = &ab->dp;
@@ -292,13 +292,27 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
 		msdu_ext_desc = true;
 	}
 
+	if (gsn_valid) {
+		/* Reset and Initialize meta_data_flags with Global Sequence
+		 * Number (GSN) info.
+		 */
+		ti.meta_data_flags =
+			u32_encode_bits(HTT_TCL_META_DATA_TYPE_GLOBAL_SEQ_NUM,
+					HTT_TCL_META_DATA_TYPE) |
+			u32_encode_bits(mcbc_gsn, HTT_TCL_META_DATA_GLOBAL_SEQ_NUM);
+	}
+
 	ti.encap_type = ath12k_dp_tx_get_encap_type(arvif, skb);
 	ti.addr_search_flags = arvif->hal_addr_search_flags;
 	ti.search_type = arvif->search_type;
 	ti.type = HAL_TCL_DESC_TYPE_BUFFER;
 	ti.pkt_offset = 0;
 	ti.lmac_id = ar->lmac_id;
+
 	ti.vdev_id = arvif->vdev_id;
+	if (gsn_valid)
+		ti.vdev_id += HTT_TX_MLO_MCAST_HOST_REINJECT_BASE_VDEV_ID;
+
 	ti.bss_ast_hash = arvif->ast_hash;
 	ti.bss_ast_idx = arvif->ast_idx;
 	ti.dscp_tid_tbl_idx = 0;
diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.h b/drivers/net/wireless/ath/ath12k/dp_tx.h
index 46dce23501f38..a5904097dc342 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2022, 2024-2025 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH12K_DP_TX_H
@@ -17,7 +17,7 @@ struct ath12k_dp_htt_wbm_tx_status {
 
 int ath12k_dp_tx_htt_h2t_ver_req_msg(struct ath12k_base *ab);
 int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
-		 struct sk_buff *skb);
+		 struct sk_buff *skb, bool gsn_valid, int mcbc_gsn);
 void ath12k_dp_tx_completion_handler(struct ath12k_base *ab, int ring_id);
 
 int ath12k_dp_tx_htt_h2t_ppdu_stats_req(struct ath12k *ar, u32 mask);
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index c9f7bea4e04a9..1536328d58547 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -7201,6 +7201,22 @@ static void ath12k_mac_add_p2p_noa_ie(struct ath12k *ar,
 	spin_unlock_bh(&ar->data_lock);
 }
 
+/* Note: called under rcu_read_lock() */
+static void ath12k_mlo_mcast_update_tx_link_address(struct ieee80211_vif *vif,
+						    u8 link_id, struct sk_buff *skb,
+						    u32 info_flags)
+{
+	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
+	struct ieee80211_bss_conf *bss_conf;
+
+	if (info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP)
+		return;
+
+	bss_conf = rcu_dereference(vif->link_conf[link_id]);
+	if (bss_conf)
+		ether_addr_copy(hdr->addr2, bss_conf->addr);
+}
+
 /* Note: called under rcu_read_lock() */
 static u8 ath12k_mac_get_tx_link(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 				 u8 link, struct sk_buff *skb, u32 info_flags)
@@ -7312,9 +7328,16 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_key_conf *key = info->control.hw_key;
 	struct ieee80211_sta *sta = control->sta;
+	struct ath12k_link_vif *tmp_arvif;
 	u32 info_flags = info->flags;
-	struct ath12k *ar;
+	struct sk_buff *msdu_copied;
+	struct ath12k *ar, *tmp_ar;
+	struct ath12k_peer *peer;
+	unsigned long links_map;
+	bool is_mcast = false;
+	struct ethhdr *eth;
 	bool is_prb_rsp;
+	u16 mcbc_gsn;
 	u8 link_id;
 	int ret;
 
@@ -7351,6 +7374,9 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 	is_prb_rsp = ieee80211_is_probe_resp(hdr->frame_control);
 
 	if (info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP) {
+		eth = (struct ethhdr *)skb->data;
+		is_mcast = is_multicast_ether_addr(eth->h_dest);
+
 		skb_cb->flags |= ATH12K_SKB_HW_80211_ENCAP;
 	} else if (ieee80211_is_mgmt(hdr->frame_control)) {
 		ret = ath12k_mac_mgmt_tx(ar, skb, is_prb_rsp);
@@ -7362,14 +7388,99 @@ static void ath12k_mac_op_tx(struct ieee80211_hw *hw,
 		return;
 	}
 
+	if (!(info_flags & IEEE80211_TX_CTL_HW_80211_ENCAP))
+		is_mcast = is_multicast_ether_addr(hdr->addr1);
+
 	/* This is case only for P2P_GO */
 	if (vif->type == NL80211_IFTYPE_AP && vif->p2p)
 		ath12k_mac_add_p2p_noa_ie(ar, vif, skb, is_prb_rsp);
 
-	ret = ath12k_dp_tx(ar, arvif, skb);
-	if (ret) {
-		ath12k_warn(ar->ab, "failed to transmit frame %d\n", ret);
-		ieee80211_free_txskb(hw, skb);
+	if (!vif->valid_links || !is_mcast ||
+	    test_bit(ATH12K_FLAG_RAW_MODE, &ar->ab->dev_flags)) {
+		ret = ath12k_dp_tx(ar, arvif, skb, false, 0);
+		if (unlikely(ret)) {
+			ath12k_warn(ar->ab, "failed to transmit frame %d\n", ret);
+			ieee80211_free_txskb(ar->ah->hw, skb);
+			return;
+		}
+	} else {
+		mcbc_gsn = atomic_inc_return(&ahvif->mcbc_gsn) & 0xfff;
+
+		links_map = ahvif->links_map;
+		for_each_set_bit(link_id, &links_map,
+				 IEEE80211_MLD_MAX_NUM_LINKS) {
+			tmp_arvif = rcu_dereference(ahvif->link[link_id]);
+			if (!tmp_arvif || !tmp_arvif->is_up)
+				continue;
+
+			tmp_ar = tmp_arvif->ar;
+			msdu_copied = skb_copy(skb, GFP_ATOMIC);
+			if (!msdu_copied) {
+				ath12k_err(ar->ab,
+					   "skb copy failure link_id 0x%X vdevid 0x%X\n",
+					   link_id, tmp_arvif->vdev_id);
+				continue;
+			}
+
+			ath12k_mlo_mcast_update_tx_link_address(vif, link_id,
+								msdu_copied,
+								info_flags);
+
+			skb_cb = ATH12K_SKB_CB(msdu_copied);
+			info = IEEE80211_SKB_CB(msdu_copied);
+			skb_cb->link_id = link_id;
+
+			/* For open mode, skip peer find logic */
+			if (unlikely(ahvif->key_cipher == WMI_CIPHER_NONE))
+				goto skip_peer_find;
+
+			spin_lock_bh(&tmp_ar->ab->base_lock);
+			peer = ath12k_peer_find_by_addr(tmp_ar->ab, tmp_arvif->bssid);
+			if (!peer) {
+				spin_unlock_bh(&tmp_ar->ab->base_lock);
+				ath12k_warn(tmp_ar->ab,
+					    "failed to find peer for vdev_id 0x%X addr %pM link_map 0x%X\n",
+					    tmp_arvif->vdev_id, tmp_arvif->bssid,
+					    ahvif->links_map);
+				dev_kfree_skb_any(msdu_copied);
+				continue;
+			}
+
+			key = peer->keys[peer->mcast_keyidx];
+			if (key) {
+				skb_cb->cipher = key->cipher;
+				skb_cb->flags |= ATH12K_SKB_CIPHER_SET;
+				info->control.hw_key = key;
+
+				hdr = (struct ieee80211_hdr *)msdu_copied->data;
+				if (!ieee80211_has_protected(hdr->frame_control))
+					hdr->frame_control |=
+						cpu_to_le16(IEEE80211_FCTL_PROTECTED);
+			}
+			spin_unlock_bh(&tmp_ar->ab->base_lock);
+
+skip_peer_find:
+			ret = ath12k_dp_tx(tmp_ar, tmp_arvif,
+					   msdu_copied, true, mcbc_gsn);
+			if (unlikely(ret)) {
+				if (ret == -ENOMEM) {
+					/* Drops are expected during heavy multicast
+					 * frame flood. Print with debug log
+					 * level to avoid lot of console prints
+					 */
+					ath12k_dbg(ar->ab, ATH12K_DBG_MAC,
+						   "failed to transmit frame %d\n",
+						   ret);
+				} else {
+					ath12k_warn(ar->ab,
+						    "failed to transmit frame %d\n",
+						    ret);
+				}
+
+				dev_kfree_skb_any(msdu_copied);
+			}
+		}
+		ieee80211_free_txskb(ar->ah->hw, skb);
 	}
 }
 
@@ -11150,6 +11261,8 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
 		ath12k_iftypes_ext_capa[2].eml_capabilities = cap->eml_cap;
 		ath12k_iftypes_ext_capa[2].mld_capa_and_ops = cap->mld_cap;
 		wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
+
+		ieee80211_hw_set(hw, MLO_MCAST_MULTI_LINK_TX);
 	}
 
 	hw->queues = ATH12K_HW_MAX_QUEUES;

From b9c7299a3341a737622e4de45b9c27e60ad01e3b Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Thu, 6 Feb 2025 14:13:17 -0800
Subject: [PATCH 0446/2753] wifi: ath12k: Fix locking in "QMI firmware ready"
 error paths

If ag->mutex has been locked, unlock it before returning. If it has not
been locked, do not unlock it before returning. These bugs have been
detected by the Clang thread-safety analyzer.

Cc: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Cc: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Fixes: ee146e11b4d9 ("wifi: ath12k: refactor core start based on hardware group")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250206221317.3845663-1-bvanassche@acm.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 323bd5082a7dd..e820462f4f1dd 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1132,16 +1132,18 @@ int ath12k_core_qmi_firmware_ready(struct ath12k_base *ab)
 		ath12k_core_stop(ab);
 		mutex_unlock(&ab->core_lock);
 	}
+	mutex_unlock(&ag->mutex);
 	goto exit;
 
 err_dp_free:
 	ath12k_dp_free(ab);
 	mutex_unlock(&ab->core_lock);
+	mutex_unlock(&ag->mutex);
+
 err_firmware_stop:
 	ath12k_qmi_firmware_stop(ab);
 
 exit:
-	mutex_unlock(&ag->mutex);
 	return ret;
 }
 

From 5cec2d86c7f4242fb30a696d8e6fd48109bf3e8f Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Fri, 7 Feb 2025 10:33:25 +0530
Subject: [PATCH 0447/2753] wifi: ath12k: Enable MLO setup ready and teardown
 commands for single split-phy device

When multi-link operation(MLO) is enabled through follow-up patches in
the single split-phy device, the firmware expects hardware links
(hw_links) information from the driver.

If driver does not send WMI multi-link setup and ready command to the
firmware during MLO setup for single split-phy device, the firmware will
be unaware of the hw_links component of the multi-link operation. This may
lead to firmware assert during multi-link association.

Therefore, enable WMI setup, ready and teardown commands for single
split-phy PCI device.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250207050327.360987-2-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 33 +++++++++++++++++++++++++-
 drivers/net/wireless/ath/ath12k/core.h |  1 +
 drivers/net/wireless/ath/ath12k/mac.c  |  9 +++++++
 3 files changed, 42 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index e820462f4f1dd..1195eba0950ac 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -897,10 +897,41 @@ static void ath12k_core_hw_group_stop(struct ath12k_hw_group *ag)
 	ath12k_mac_destroy(ag);
 }
 
+u8 ath12k_get_num_partner_link(struct ath12k *ar)
+{
+	struct ath12k_base *partner_ab, *ab = ar->ab;
+	struct ath12k_hw_group *ag = ab->ag;
+	struct ath12k_pdev *pdev;
+	u8 num_link = 0;
+	int i, j;
+
+	lockdep_assert_held(&ag->mutex);
+
+	for (i = 0; i < ag->num_devices; i++) {
+		partner_ab = ag->ab[i];
+
+		for (j = 0; j < partner_ab->num_radios; j++) {
+			pdev = &partner_ab->pdevs[j];
+
+			/* Avoid the self link */
+			if (ar == pdev->ar)
+				continue;
+
+			num_link++;
+		}
+	}
+
+	return num_link;
+}
+
 static int __ath12k_mac_mlo_ready(struct ath12k *ar)
 {
+	u8 num_link = ath12k_get_num_partner_link(ar);
 	int ret;
 
+	if (num_link == 0)
+		return 0;
+
 	ret = ath12k_wmi_mlo_ready(ar);
 	if (ret) {
 		ath12k_err(ar->ab, "MLO ready failed for pdev %d: %d\n",
@@ -942,7 +973,7 @@ static int ath12k_core_mlo_setup(struct ath12k_hw_group *ag)
 {
 	int ret, i;
 
-	if (!ag->mlo_capable || ag->num_devices == 1)
+	if (!ag->mlo_capable)
 		return 0;
 
 	ret = ath12k_mac_mlo_setup(ag);
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index e9388bdf532da..ff023d751bf11 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1209,6 +1209,7 @@ int ath12k_core_resume(struct ath12k_base *ab);
 int ath12k_core_suspend(struct ath12k_base *ab);
 int ath12k_core_suspend_late(struct ath12k_base *ab);
 void ath12k_core_hw_group_unassign(struct ath12k_base *ab);
+u8 ath12k_get_num_partner_link(struct ath12k *ar);
 
 const struct firmware *ath12k_core_firmware_request(struct ath12k_base *ab,
 						    const char *filename);
diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 1536328d58547..27d2fad1b915c 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -11448,6 +11448,9 @@ static int __ath12k_mac_mlo_setup(struct ath12k *ar)
 		}
 	}
 
+	if (num_link == 0)
+		return 0;
+
 	mlo.group_id = cpu_to_le32(ag->id);
 	mlo.partner_link_id = partner_link_id;
 	mlo.num_partner_links = num_link;
@@ -11477,10 +11480,16 @@ static int __ath12k_mac_mlo_teardown(struct ath12k *ar)
 {
 	struct ath12k_base *ab = ar->ab;
 	int ret;
+	u8 num_link;
 
 	if (test_bit(ATH12K_FLAG_RECOVERY, &ab->dev_flags))
 		return 0;
 
+	num_link = ath12k_get_num_partner_link(ar);
+
+	if (num_link == 0)
+		return 0;
+
 	ret = ath12k_wmi_mlo_teardown(ar);
 	if (ret) {
 		ath12k_warn(ab, "failed to send MLO teardown WMI command for pdev %d: %d\n",

From 16266b7ad6c011f760083851e8caa0d6b657f5e8 Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Fri, 7 Feb 2025 10:33:26 +0530
Subject: [PATCH 0448/2753] wifi: ath12k: Remove dependency on
 single_chip_mlo_support for mlo_capable flag

The mlo_capable flag in structure ath12k_hw_group indicate that a device
is capable of operating in multi-link mode. Currently this is enabled
based on single_chip_mlo_support advertised by the firmware within
ath12k_qmi_phy_cap_send().

Since the firmware advertises multi-link operation (MLO) support through
the ATH12K_FW_FEATURE_MLO feature in firmware-2.bin, there is no need to
rely on the QMI phy capability (single_chip_mlo_support). Therefore remove
the dependency on single_chip_mlo_support to set mlo_capable flag.

Below is the impact on single split-phy PCI device with and without this
patch:

Note: This patch does not change the existing behavior of the single
split-phy PCI device.

1. Driver without this patch + firmware with single_chip_mlo_support
    as false: MLO is not enabled.
2. Driver without this patch + firmware with single_chip_mlo_support
    as true: MLO works fine.
3. Driver with this patch + firmware with single_chip_mlo_support as
    false: MLO is not enabled.
4. Driver with this patch + firmware with single_chip_mlo_support as
    true: MLO works fine.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250207050327.360987-3-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/qmi.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index ef537c6bf0daa..fcbe234758e11 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2265,10 +2265,6 @@ static void ath12k_qmi_phy_cap_send(struct ath12k_base *ab)
 		goto out;
 	}
 
-	if (resp.single_chip_mlo_support_valid &&
-	    resp.single_chip_mlo_support)
-		ab->single_chip_mlo_supp = true;
-
 	if (!resp.num_phy_valid) {
 		ret = -ENODATA;
 		goto out;
@@ -2277,10 +2273,9 @@ static void ath12k_qmi_phy_cap_send(struct ath12k_base *ab)
 	ab->qmi.num_radios = resp.num_phy;
 
 	ath12k_dbg(ab, ATH12K_DBG_QMI,
-		   "phy capability resp valid %d num_phy %d valid %d board_id %d valid %d single_chip_mlo_support %d\n",
+		   "phy capability resp valid %d num_phy %d valid %d board_id %d\n",
 		   resp.num_phy_valid, resp.num_phy,
-		   resp.board_id_valid, resp.board_id,
-		   resp.single_chip_mlo_support_valid, resp.single_chip_mlo_support);
+		   resp.board_id_valid, resp.board_id);
 
 	return;
 

From 4f4bd1f8a5c2f7b1b24ecc553033b210de2a0513 Mon Sep 17 00:00:00 2001
From: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Date: Fri, 7 Feb 2025 10:33:27 +0530
Subject: [PATCH 0449/2753] wifi: ath12k: Enable MLO for single split-phy PCI
 device

The single split-phy PCI device can perform multi-link operation (MLO)
within its own radio, and the MLO-supporting firmware also supports MLO
for split-phy PCI devices.

Therefore, enable MLO for the single split-phy PCI device.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aaradhana Sahu <quic_aarasahu@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250207050327.360987-4-quic_aarasahu@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 13 ++++---------
 drivers/net/wireless/ath/ath12k/core.h |  3 ---
 drivers/net/wireless/ath/ath12k/qmi.c  |  3 +--
 3 files changed, 5 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 1195eba0950ac..0c556023141b0 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -1847,14 +1847,11 @@ void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag)
 	/* If more than one devices are grouped, then inter MLO
 	 * functionality can work still independent of whether internally
 	 * each device supports single_chip_mlo or not.
-	 * Only when there is one device, then it depends whether the
-	 * device can support intra chip MLO or not
+	 * Only when there is one device, then disable for WCN chipsets
+	 * till the required driver implementation is in place.
 	 */
-	if (ag->num_devices > 1) {
-		ag->mlo_capable = true;
-	} else {
+	if (ag->num_devices == 1) {
 		ab = ag->ab[0];
-		ag->mlo_capable = ab->single_chip_mlo_supp;
 
 		/* WCN chipsets does not advertise in firmware features
 		 * hence skip checking
@@ -1863,8 +1860,7 @@ void ath12k_core_hw_group_set_mlo_capable(struct ath12k_hw_group *ag)
 			return;
 	}
 
-	if (!ag->mlo_capable)
-		return;
+	ag->mlo_capable = true;
 
 	for (i = 0; i < ag->num_devices; i++) {
 		ab = ag->ab[i];
@@ -1980,7 +1976,6 @@ struct ath12k_base *ath12k_core_alloc(struct device *dev, size_t priv_size,
 	ab->dev = dev;
 	ab->hif.bus = bus;
 	ab->qmi.num_radios = U8_MAX;
-	ab->single_chip_mlo_supp = false;
 
 	/* Device index used to identify the devices in a group.
 	 *
diff --git a/drivers/net/wireless/ath/ath12k/core.h b/drivers/net/wireless/ath/ath12k/core.h
index ff023d751bf11..3fac4f00d3832 100644
--- a/drivers/net/wireless/ath/ath12k/core.h
+++ b/drivers/net/wireless/ath/ath12k/core.h
@@ -1055,9 +1055,6 @@ struct ath12k_base {
 
 	const struct hal_rx_ops *hal_rx_ops;
 
-	/* Denotes the whether MLO is possible within the chip */
-	bool single_chip_mlo_supp;
-
 	struct completion restart_completed;
 
 #ifdef CONFIG_ACPI
diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
index fcbe234758e11..348dbc81bad8c 100644
--- a/drivers/net/wireless/ath/ath12k/qmi.c
+++ b/drivers/net/wireless/ath/ath12k/qmi.c
@@ -2056,8 +2056,7 @@ static int ath12k_host_cap_parse_mlo(struct ath12k_base *ab,
 	}
 
 	if (!ab->qmi.num_radios || ab->qmi.num_radios == U8_MAX) {
-		ab->single_chip_mlo_supp = false;
-
+		ag->mlo_capable = false;
 		ath12k_dbg(ab, ATH12K_DBG_QMI,
 			   "skip QMI MLO cap due to invalid num_radio %d\n",
 			   ab->qmi.num_radios);

From 5c1963119b82b369b902091502a2135b238c9793 Mon Sep 17 00:00:00 2001
From: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Date: Tue, 4 Feb 2025 12:14:13 +0530
Subject: [PATCH 0450/2753] wifi: ath12k: Support Sounding Stats

Add support to request sounding stats from firmware through HTT stats
type 22. These stats give sounding information of different Wi-Fi
standards, channel vector upload status and correlation details.

Sample output:
-------------
echo 22 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_TX_AC_SOUNDING_STATS_TLV:
ac_cbf_20 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
ac_cbf_40 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
.....
Sounding User_0 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0
Sounding User_1 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0
.....

HTT_TX_AX_SOUNDING_STATS_TLV:
ax_cbf_20 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
ax_cbf_40 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
.....
Sounding User_0 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0
Sounding User_1 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0
.....

HTT_TX_BE_SOUNDING_STATS_TLV:
be_cbf_20 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
be_cbf_40 = IBF: 0, SU_SIFS: 0, SU_RBO: 0, MU_SIFS: 0, MU_RBO: 0
.....
Sounding User_0 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0, 320MHz: 0
Sounding User_1 = 20MHz: 0, 40MHz: 0, 80MHz: 0, 160MHz: 0, 320MHz: 0
.....

CV UPLOAD HANDLER STATS:
cv_nc_mismatch_err = 0
cv_fcs_err = 0
cv_frag_idx_mismatch = 0
cv_invalid_peer_id = 0
.....

CV QUERY STATS:
cv_total_query = 0
cv_total_pattern_query = 0
cv_total_bw_query = 0
cv_invalid_bw_coding = 0
.....

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Link: https://patch.msgid.link/20250204064417.3671928-2-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 265 ++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   |  78 ++++++
 2 files changed, 343 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index bad1bd21d67d1..9998c5cf7ab0e 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -2511,6 +2511,268 @@ ath12k_htt_print_pdev_stats_cca_counters_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_tx_sounding_stats_tlv(const void *tag_buf, u16 tag_len,
+				       struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_tx_sounding_stats_tlv *htt_stats_buf = tag_buf;
+	const __le32 *cbf_20, *cbf_40, *cbf_80, *cbf_160, *cbf_320;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+	u32 tx_sounding_mode;
+	u8 i, u;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	cbf_20 = htt_stats_buf->cbf_20;
+	cbf_40 = htt_stats_buf->cbf_40;
+	cbf_80 = htt_stats_buf->cbf_80;
+	cbf_160 = htt_stats_buf->cbf_160;
+	cbf_320 = htt_stats_buf->cbf_320;
+	tx_sounding_mode = le32_to_cpu(htt_stats_buf->tx_sounding_mode);
+
+	if (tx_sounding_mode == ATH12K_HTT_TX_AC_SOUNDING_MODE) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "HTT_TX_AC_SOUNDING_STATS_TLV:\n");
+		len += scnprintf(buf + len, buf_len - len,
+				 "ac_cbf_20 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ac_cbf_40 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ac_cbf_80 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ac_cbf_160 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+
+		for (u = 0, i = 0; u < ATH12K_HTT_TX_NUM_AC_MUMIMO_USER_STATS; u++) {
+			len += scnprintf(buf + len, buf_len - len,
+					 "Sounding User_%u = 20MHz: %u, ", u,
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "40MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "80MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "160MHz: %u\n",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+		}
+	} else if (tx_sounding_mode == ATH12K_HTT_TX_AX_SOUNDING_MODE) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "\nHTT_TX_AX_SOUNDING_STATS_TLV:\n");
+		len += scnprintf(buf + len, buf_len - len,
+				 "ax_cbf_20 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ax_cbf_40 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ax_cbf_80 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "ax_cbf_160 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+
+		for (u = 0, i = 0; u < ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS; u++) {
+			len += scnprintf(buf + len, buf_len - len,
+					 "Sounding User_%u = 20MHz: %u, ", u,
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "40MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "80MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "160MHz: %u\n",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+		}
+	} else if (tx_sounding_mode == ATH12K_HTT_TX_BE_SOUNDING_MODE) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "\nHTT_TX_BE_SOUNDING_STATS_TLV:\n");
+		len += scnprintf(buf + len, buf_len - len,
+				 "be_cbf_20 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_20[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "be_cbf_40 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_40[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "be_cbf_80 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_80[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "be_cbf_160 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_160[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len,
+				 "be_cbf_320 = IBF: %u, SU_SIFS: %u, SU_RBO: %u, ",
+				 le32_to_cpu(cbf_320[ATH12K_HTT_IMPL_STEER_STATS]),
+				 le32_to_cpu(cbf_320[ATH12K_HTT_EXPL_SUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_320[ATH12K_HTT_EXPL_SURBO_STEER_STATS]));
+		len += scnprintf(buf + len, buf_len - len, "MU_SIFS: %u, MU_RBO: %u\n",
+				 le32_to_cpu(cbf_320[ATH12K_HTT_EXPL_MUSIFS_STEER_STATS]),
+				 le32_to_cpu(cbf_320[ATH12K_HTT_EXPL_MURBO_STEER_STATS]));
+		for (u = 0, i = 0; u < ATH12K_HTT_TX_NUM_BE_MUMIMO_USER_STATS; u++) {
+			len += scnprintf(buf + len, buf_len - len,
+					 "Sounding User_%u = 20MHz: %u, ", u,
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "40MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len, "80MHz: %u, ",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]));
+			len += scnprintf(buf + len, buf_len - len,
+					 "160MHz: %u, 320MHz: %u\n",
+					 le32_to_cpu(htt_stats_buf->sounding[i++]),
+					 le32_to_cpu(htt_stats_buf->sounding_320[u]));
+		}
+	} else if (tx_sounding_mode == ATH12K_HTT_TX_CMN_SOUNDING_MODE) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "\nCV UPLOAD HANDLER STATS:\n");
+		len += scnprintf(buf + len, buf_len - len, "cv_nc_mismatch_err = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_nc_mismatch_err));
+		len += scnprintf(buf + len, buf_len - len, "cv_fcs_err = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_fcs_err));
+		len += scnprintf(buf + len, buf_len - len, "cv_frag_idx_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_frag_idx_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_invalid_peer_id = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_invalid_peer_id));
+		len += scnprintf(buf + len, buf_len - len, "cv_no_txbf_setup = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_no_txbf_setup));
+		len += scnprintf(buf + len, buf_len - len, "cv_expiry_in_update = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_expiry_in_update));
+		len += scnprintf(buf + len, buf_len - len, "cv_pkt_bw_exceed = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_pkt_bw_exceed));
+		len += scnprintf(buf + len, buf_len - len, "cv_dma_not_done_err = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_dma_not_done_err));
+		len += scnprintf(buf + len, buf_len - len, "cv_update_failed = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_update_failed));
+		len += scnprintf(buf + len, buf_len - len, "cv_dma_timeout_error = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_dma_timeout_error));
+		len += scnprintf(buf + len, buf_len - len, "cv_buf_ibf_uploads = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_buf_ibf_uploads));
+		len += scnprintf(buf + len, buf_len - len, "cv_buf_ebf_uploads = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_buf_ebf_uploads));
+		len += scnprintf(buf + len, buf_len - len, "cv_buf_received = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_buf_received));
+		len += scnprintf(buf + len, buf_len - len, "cv_buf_fed_back = %u\n\n",
+				 le32_to_cpu(htt_stats_buf->cv_buf_fed_back));
+
+		len += scnprintf(buf + len, buf_len - len, "CV QUERY STATS:\n");
+		len += scnprintf(buf + len, buf_len - len, "cv_total_query = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_total_query));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_total_pattern_query = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_total_pattern_query));
+		len += scnprintf(buf + len, buf_len - len, "cv_total_bw_query = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_total_bw_query));
+		len += scnprintf(buf + len, buf_len - len, "cv_invalid_bw_coding = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_invalid_bw_coding));
+		len += scnprintf(buf + len, buf_len - len, "cv_forced_sounding = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_forced_sounding));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_standalone_sounding = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_standalone_sounding));
+		len += scnprintf(buf + len, buf_len - len, "cv_nc_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_nc_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_fb_type_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_fb_type_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_ofdma_bw_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_ofdma_bw_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_bw_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_bw_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_pattern_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_pattern_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_preamble_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_preamble_mismatch));
+		len += scnprintf(buf + len, buf_len - len, "cv_nr_mismatch = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_nr_mismatch));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_in_use_cnt_exceeded = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_in_use_cnt_exceeded));
+		len += scnprintf(buf + len, buf_len - len, "cv_ntbr_sounding = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_ntbr_sounding));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_found_upload_in_progress = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_found_upload_in_progress));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_expired_during_query = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_expired_during_query));
+		len += scnprintf(buf + len, buf_len - len, "cv_found = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_found));
+		len += scnprintf(buf + len, buf_len - len, "cv_not_found = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_not_found));
+		len += scnprintf(buf + len, buf_len - len, "cv_total_query_ibf = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_total_query_ibf));
+		len += scnprintf(buf + len, buf_len - len, "cv_found_ibf = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_found_ibf));
+		len += scnprintf(buf + len, buf_len - len, "cv_not_found_ibf = %u\n",
+				 le32_to_cpu(htt_stats_buf->cv_not_found_ibf));
+		len += scnprintf(buf + len, buf_len - len,
+				 "cv_expired_during_query_ibf = %u\n\n",
+				 le32_to_cpu(htt_stats_buf->cv_expired_during_query_ibf));
+	}
+
+	stats_req->buf_len = len;
+}
+
 static void
 ath12k_htt_print_pdev_obss_pd_stats_tlv(const void *tag_buf, u16 tag_len,
 					struct debug_htt_stats_req *stats_req)
@@ -4473,6 +4735,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_PDEV_CCA_COUNTERS_TAG:
 		ath12k_htt_print_pdev_stats_cca_counters_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_TX_SOUNDING_STATS_TAG:
+		ath12k_htt_print_tx_sounding_stats_tlv(tag_buf, len, stats_req);
+		break;
 	case HTT_STATS_PDEV_OBSS_PD_TAG:
 		ath12k_htt_print_pdev_obss_pd_stats_tlv(tag_buf, len, stats_req);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index e557a5807bc6b..a4dd894df0770 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -136,6 +136,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_SFM_INFO		= 16,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_MU		= 17,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS		= 19,
+	ATH12K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO	= 22,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	= 23,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT	= 30,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF	= 31,
@@ -200,6 +201,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_PDEV_CCA_STAT_CUMULATIVE_TAG		= 72,
 	HTT_STATS_PDEV_CCA_COUNTERS_TAG			= 73,
 	HTT_STATS_TX_PDEV_MPDU_STATS_TAG		= 74,
+	HTT_STATS_TX_SOUNDING_STATS_TAG			= 80,
 	HTT_STATS_SCHED_TXQ_SCHED_ORDER_SU_TAG		= 86,
 	HTT_STATS_SCHED_TXQ_SCHED_INELIGIBILITY_TAG	= 87,
 	HTT_STATS_PDEV_OBSS_PD_TAG			= 88,
@@ -1240,6 +1242,82 @@ struct ath12k_htt_pdev_cca_stats_hist_v1_tlv {
 	__le32 collection_interval;
 } __packed;
 
+#define ATH12K_HTT_TX_CV_CORR_MAX_NUM_COLUMNS		8
+#define ATH12K_HTT_TX_NUM_AC_MUMIMO_USER_STATS		4
+#define ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS          8
+#define ATH12K_HTT_TX_NUM_BE_MUMIMO_USER_STATS		8
+#define ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS	4
+#define ATH12K_HTT_TX_NUM_MCS_CNTRS			12
+#define ATH12K_HTT_TX_NUM_EXTRA_MCS_CNTRS		2
+
+#define ATH12K_HTT_TX_NUM_OF_SOUNDING_STATS_WORDS \
+	(ATH12K_HTT_TX_PDEV_STATS_NUM_BW_COUNTERS * \
+	 ATH12K_HTT_TX_NUM_AX_MUMIMO_USER_STATS)
+
+enum ath12k_htt_txbf_sound_steer_modes {
+	ATH12K_HTT_IMPL_STEER_STATS		= 0,
+	ATH12K_HTT_EXPL_SUSIFS_STEER_STATS	= 1,
+	ATH12K_HTT_EXPL_SURBO_STEER_STATS	= 2,
+	ATH12K_HTT_EXPL_MUSIFS_STEER_STATS	= 3,
+	ATH12K_HTT_EXPL_MURBO_STEER_STATS	= 4,
+	ATH12K_HTT_TXBF_MAX_NUM_OF_MODES	= 5
+};
+
+enum ath12k_htt_stats_sounding_tx_mode {
+	ATH12K_HTT_TX_AC_SOUNDING_MODE		= 0,
+	ATH12K_HTT_TX_AX_SOUNDING_MODE		= 1,
+	ATH12K_HTT_TX_BE_SOUNDING_MODE		= 2,
+	ATH12K_HTT_TX_CMN_SOUNDING_MODE		= 3,
+};
+
+struct ath12k_htt_tx_sounding_stats_tlv {
+	__le32 tx_sounding_mode;
+	__le32 cbf_20[ATH12K_HTT_TXBF_MAX_NUM_OF_MODES];
+	__le32 cbf_40[ATH12K_HTT_TXBF_MAX_NUM_OF_MODES];
+	__le32 cbf_80[ATH12K_HTT_TXBF_MAX_NUM_OF_MODES];
+	__le32 cbf_160[ATH12K_HTT_TXBF_MAX_NUM_OF_MODES];
+	__le32 sounding[ATH12K_HTT_TX_NUM_OF_SOUNDING_STATS_WORDS];
+	__le32 cv_nc_mismatch_err;
+	__le32 cv_fcs_err;
+	__le32 cv_frag_idx_mismatch;
+	__le32 cv_invalid_peer_id;
+	__le32 cv_no_txbf_setup;
+	__le32 cv_expiry_in_update;
+	__le32 cv_pkt_bw_exceed;
+	__le32 cv_dma_not_done_err;
+	__le32 cv_update_failed;
+	__le32 cv_total_query;
+	__le32 cv_total_pattern_query;
+	__le32 cv_total_bw_query;
+	__le32 cv_invalid_bw_coding;
+	__le32 cv_forced_sounding;
+	__le32 cv_standalone_sounding;
+	__le32 cv_nc_mismatch;
+	__le32 cv_fb_type_mismatch;
+	__le32 cv_ofdma_bw_mismatch;
+	__le32 cv_bw_mismatch;
+	__le32 cv_pattern_mismatch;
+	__le32 cv_preamble_mismatch;
+	__le32 cv_nr_mismatch;
+	__le32 cv_in_use_cnt_exceeded;
+	__le32 cv_found;
+	__le32 cv_not_found;
+	__le32 sounding_320[ATH12K_HTT_TX_NUM_BE_MUMIMO_USER_STATS];
+	__le32 cbf_320[ATH12K_HTT_TXBF_MAX_NUM_OF_MODES];
+	__le32 cv_ntbr_sounding;
+	__le32 cv_found_upload_in_progress;
+	__le32 cv_expired_during_query;
+	__le32 cv_dma_timeout_error;
+	__le32 cv_buf_ibf_uploads;
+	__le32 cv_buf_ebf_uploads;
+	__le32 cv_buf_received;
+	__le32 cv_buf_fed_back;
+	__le32 cv_total_query_ibf;
+	__le32 cv_found_ibf;
+	__le32 cv_not_found_ibf;
+	__le32 cv_expired_during_query_ibf;
+} __packed;
+
 struct ath12k_htt_pdev_obss_pd_stats_tlv {
 	__le32 num_obss_tx_ppdu_success;
 	__le32 num_obss_tx_ppdu_failure;

From f7c5e24bb1918677f7d6195a8825b39462e0a9fc Mon Sep 17 00:00:00 2001
From: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Date: Tue, 4 Feb 2025 12:14:14 +0530
Subject: [PATCH 0451/2753] wifi: ath12k: Support Latency Stats

Add support to request latency stats from firmware through HTT stats
type 25. These stats give information about count of transmitted and
received MAC Protocol Data Units(PDU) and Service Data Units(SDU)
and other latency stats.

Sample output:
-------------
echo 25 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_STATS_LATENCY_CTX_TLV:
duration = 0
tx_msdu_cnt = 0
tx_mpdu_cnt = 0
rx_msdu_cnt = 0
rx_mpdu_cnt = 0

HTT_STATS_LATENCY_PROF_TLV:
Latency name = PROF_SCH_ENQ_TQM_CMDS
count = 0
minimum = 4294967295
maximum = 0
.....

HTT_STATS_LATENCY_CNT_TLV:
prof_enable_cnt = 39

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Link: https://patch.msgid.link/20250204064417.3671928-3-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 94 +++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   | 34 +++++++
 2 files changed, 128 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 9998c5cf7ab0e..0abca93e08020 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -2838,6 +2838,91 @@ ath12k_htt_print_pdev_obss_pd_stats_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_latency_prof_ctx_tlv(const void *tag_buf, u16 tag_len,
+				      struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_latency_prof_ctx_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_STATS_LATENCY_CTX_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "duration = %u\n",
+			 le32_to_cpu(htt_stats_buf->duration));
+	len += scnprintf(buf + len, buf_len - len, "tx_msdu_cnt = %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_msdu_cnt));
+	len += scnprintf(buf + len, buf_len - len, "tx_mpdu_cnt = %u\n",
+			 le32_to_cpu(htt_stats_buf->tx_mpdu_cnt));
+	len += scnprintf(buf + len, buf_len - len, "rx_msdu_cnt = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_msdu_cnt));
+	len += scnprintf(buf + len, buf_len - len, "rx_mpdu_cnt = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->rx_mpdu_cnt));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_latency_prof_cnt(const void *tag_buf, u16 tag_len,
+				  struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_latency_prof_cnt_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_STATS_LATENCY_CNT_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "prof_enable_cnt = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->prof_enable_cnt));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_latency_prof_stats_tlv(const void *tag_buf, u16 tag_len,
+					struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_latency_prof_stats_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	if (le32_to_cpu(htt_stats_buf->print_header) == 1) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "HTT_STATS_LATENCY_PROF_TLV:\n");
+	}
+
+	len += scnprintf(buf + len, buf_len - len, "Latency name = %s\n",
+			 htt_stats_buf->latency_prof_name);
+	len += scnprintf(buf + len, buf_len - len, "count = %u\n",
+			 le32_to_cpu(htt_stats_buf->cnt));
+	len += scnprintf(buf + len, buf_len - len, "minimum = %u\n",
+			 le32_to_cpu(htt_stats_buf->min));
+	len += scnprintf(buf + len, buf_len - len, "maximum = %u\n",
+			 le32_to_cpu(htt_stats_buf->max));
+	len += scnprintf(buf + len, buf_len - len, "last = %u\n",
+			 le32_to_cpu(htt_stats_buf->last));
+	len += scnprintf(buf + len, buf_len - len, "total = %u\n",
+			 le32_to_cpu(htt_stats_buf->tot));
+	len += scnprintf(buf + len, buf_len - len, "average = %u\n",
+			 le32_to_cpu(htt_stats_buf->avg));
+	len += scnprintf(buf + len, buf_len - len, "histogram interval = %u\n",
+			 le32_to_cpu(htt_stats_buf->hist_intvl));
+	len += print_array_to_buf(buf, len, "histogram", htt_stats_buf->hist,
+				  ATH12K_HTT_LATENCY_PROFILE_NUM_MAX_HIST, "\n\n");
+
+	stats_req->buf_len = len;
+}
+
 static void
 ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(const void *tag_buf, u16 tag_len,
 					     struct debug_htt_stats_req *stats_req)
@@ -4741,6 +4826,15 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_PDEV_OBSS_PD_TAG:
 		ath12k_htt_print_pdev_obss_pd_stats_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_LATENCY_CTX_TAG:
+		ath12k_htt_print_latency_prof_ctx_tlv(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_LATENCY_CNT_TAG:
+		ath12k_htt_print_latency_prof_cnt(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_LATENCY_PROF_STATS_TAG:
+		ath12k_htt_print_latency_prof_stats_tlv(tag_buf, len, stats_req);
+		break;
 	case HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG:
 		ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(tag_buf, len, stats_req);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index a4dd894df0770..1b835473f419c 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -138,6 +138,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS		= 19,
 	ATH12K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO	= 22,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	= 23,
+	ATH12K_DBG_HTT_EXT_STATS_LATENCY_PROF_STATS	= 25,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT	= 30,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF	= 31,
 	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA		= 32,
@@ -206,6 +207,9 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_SCHED_TXQ_SCHED_INELIGIBILITY_TAG	= 87,
 	HTT_STATS_PDEV_OBSS_PD_TAG			= 88,
 	HTT_STATS_HW_WAR_TAG				= 89,
+	HTT_STATS_LATENCY_PROF_STATS_TAG		= 91,
+	HTT_STATS_LATENCY_CTX_TAG			= 92,
+	HTT_STATS_LATENCY_CNT_TAG			= 93,
 	HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG	= 100,
 	HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG		= 102,
 	HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG		= 103,
@@ -1340,6 +1344,36 @@ struct ath12k_htt_pdev_obss_pd_stats_tlv {
 	__le32 num_sr_ppdu_abort_flush_cnt;
 } __packed;
 
+#define ATH12K_HTT_STATS_MAX_PROF_STATS_NAME_LEN	32
+#define ATH12K_HTT_LATENCY_PROFILE_NUM_MAX_HIST		3
+#define ATH12K_HTT_INTERRUPTS_LATENCY_PROFILE_MAX_HIST	3
+
+struct ath12k_htt_latency_prof_stats_tlv {
+	__le32 print_header;
+	s8 latency_prof_name[ATH12K_HTT_STATS_MAX_PROF_STATS_NAME_LEN];
+	__le32 cnt;
+	__le32 min;
+	__le32 max;
+	__le32 last;
+	__le32 tot;
+	__le32 avg;
+	__le32 hist_intvl;
+	__le32 hist[ATH12K_HTT_LATENCY_PROFILE_NUM_MAX_HIST];
+}  __packed;
+
+struct ath12k_htt_latency_prof_ctx_tlv {
+	__le32 duration;
+	__le32 tx_msdu_cnt;
+	__le32 tx_mpdu_cnt;
+	__le32 tx_ppdu_cnt;
+	__le32 rx_msdu_cnt;
+	__le32 rx_mpdu_cnt;
+} __packed;
+
+struct ath12k_htt_latency_prof_cnt_tlv {
+	__le32 prof_enable_cnt;
+} __packed;
+
 #define ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS		14
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS		8

From e669a18b20e205dc51a71a07bd3597f123979751 Mon Sep 17 00:00:00 2001
From: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Date: Tue, 4 Feb 2025 12:14:15 +0530
Subject: [PATCH 0452/2753] wifi: ath12k: Support Uplink OFDMA Trigger Stats

Add support to request uplink trigger stats from firmware through
HTT stats type 26. These stats give information about uplink
OFDMA bandwidth, received RSSI, power headroom, QoS, data size,
PPDU info and pass/fail info for each user.

Note: MCC firmware version
WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4
does not support tags HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG(94) and
HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG(95), currently.

Sample output:
-------------
echo 26 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_RX_PDEV_UL_TRIGGER_STATS_TLV:
mac_id = 0
rx_11ax_ul_ofdma = 0
ul_ofdma_rx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[0] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[1] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[2] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_gi[3] =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0
ul_ofdma_rx_nss =  1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
ul_ofdma_rx_bw =  0:0, 1:0, 2:0, 3:0
half_ul_ofdma_rx_bw =  0:0, 1:0, 2:0, 3:0
quarter_ul_ofdma_rx_bw =  0:0, 1:0, 2:0, 3:0
.....

HTT_RX_PDEV_UL_OFDMA_USER_STAS_TLV:
rx_ulofdma_non_data_ppdu_0 = 0
rx_ulofdma_data_ppdu_0 = 0
rx_ulofdma_mpdu_ok_0 = 0
rx_ulofdma_mpdu_fail_0 = 0
rx_ulofdma_non_data_nusers_0 = 0
rx_ulofdma_data_nusers_0 = 0
.....

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Link: https://patch.msgid.link/20250204064417.3671928-4-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 131 ++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   |  63 +++++++--
 2 files changed, 183 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 0abca93e08020..a235c5b6dcab2 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -2923,6 +2923,131 @@ ath12k_htt_print_latency_prof_stats_tlv(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_ul_ofdma_trigger_stats(const void *tag_buf, u16 tag_len,
+					struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_pdev_ul_trigger_stats_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+	u32 mac_id;
+	u8 j;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	mac_id = __le32_to_cpu(htt_stats_buf->mac_id__word);
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_RX_PDEV_UL_TRIGGER_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n",
+			 u32_get_bits(mac_id, ATH12K_HTT_STATS_MAC_ID));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_ul_ofdma = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_ul_ofdma));
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_mcs",
+				  htt_stats_buf->ul_ofdma_rx_mcs,
+				  ATH12K_HTT_RX_NUM_MCS_CNTRS, "\n");
+	for (j = 0; j < ATH12K_HTT_RX_NUM_GI_CNTRS; j++) {
+		len += scnprintf(buf + len, buf_len - len, "ul_ofdma_rx_gi[%u]", j);
+		len += print_array_to_buf(buf, len, "",
+					  htt_stats_buf->ul_ofdma_rx_gi[j],
+					  ATH12K_HTT_RX_NUM_MCS_CNTRS, "\n");
+	}
+
+	len += print_array_to_buf_index(buf, len, "ul_ofdma_rx_nss", 1,
+					htt_stats_buf->ul_ofdma_rx_nss,
+					ATH12K_HTT_RX_NUM_SPATIAL_STREAMS, "\n");
+	len += print_array_to_buf(buf, len, "ul_ofdma_rx_bw",
+				  htt_stats_buf->ul_ofdma_rx_bw,
+				  ATH12K_HTT_RX_NUM_BW_CNTRS, "\n");
+
+	for (j = 0; j < ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES; j++) {
+		len += scnprintf(buf + len, buf_len - len, j == 0 ?
+				 "half_ul_ofdma_rx_bw" :
+				 "quarter_ul_ofdma_rx_bw");
+		len += print_array_to_buf(buf, len, "", htt_stats_buf->red_bw[j],
+					  ATH12K_HTT_RX_NUM_BW_CNTRS, "\n");
+	}
+	len += scnprintf(buf + len, buf_len - len, "ul_ofdma_rx_stbc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_ofdma_rx_stbc));
+	len += scnprintf(buf + len, buf_len - len, "ul_ofdma_rx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_ofdma_rx_ldpc));
+
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_data_ru_size_ppdu = ");
+	for (j = 0; j < ATH12K_HTT_RX_NUM_RU_SIZE_CNTRS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %s:%u ",
+				 ath12k_htt_ax_tx_rx_ru_size_to_str(j),
+				 le32_to_cpu(htt_stats_buf->data_ru_size_ppdu[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "rx_ulofdma_non_data_ru_size_ppdu = ");
+	for (j = 0; j < ATH12K_HTT_RX_NUM_RU_SIZE_CNTRS; j++)
+		len += scnprintf(buf + len, buf_len - len, " %s:%u ",
+				 ath12k_htt_ax_tx_rx_ru_size_to_str(j),
+				 le32_to_cpu(htt_stats_buf->non_data_ru_size_ppdu[j]));
+	len += scnprintf(buf + len, buf_len - len, "\n");
+
+	len += print_array_to_buf(buf, len, "rx_rssi_track_sta_aid",
+				  htt_stats_buf->uplink_sta_aid,
+				  ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK, "\n");
+	len += print_array_to_buf(buf, len, "rx_sta_target_rssi",
+				  htt_stats_buf->uplink_sta_target_rssi,
+				  ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK, "\n");
+	len += print_array_to_buf(buf, len, "rx_sta_fd_rssi",
+				  htt_stats_buf->uplink_sta_fd_rssi,
+				  ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK, "\n");
+	len += print_array_to_buf(buf, len, "rx_sta_power_headroom",
+				  htt_stats_buf->uplink_sta_power_headroom,
+				  ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK, "\n");
+	len += scnprintf(buf + len, buf_len - len,
+			 "ul_ofdma_basic_trigger_rx_qos_null_only = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->ul_ofdma_bsc_trig_rx_qos_null_only));
+
+	stats_req->buf_len = len;
+}
+
+static void
+ath12k_htt_print_ul_ofdma_user_stats(const void *tag_buf, u16 tag_len,
+				     struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_pdev_ul_ofdma_user_stats_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+	u32 user_index;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	user_index = __le32_to_cpu(htt_stats_buf->user_index);
+
+	if (!user_index)
+		len += scnprintf(buf + len, buf_len - len,
+				 "HTT_RX_PDEV_UL_OFDMA_USER_STAS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_non_data_ppdu_%u = %u\n",
+			 user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_non_data_ppdu));
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_data_ppdu_%u = %u\n",
+			 user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_data_ppdu));
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_mpdu_ok_%u = %u\n",
+			 user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_mpdu_ok));
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_mpdu_fail_%u = %u\n",
+			 user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_mpdu_fail));
+	len += scnprintf(buf + len, buf_len - len,
+			 "rx_ulofdma_non_data_nusers_%u = %u\n", user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_non_data_nusers));
+	len += scnprintf(buf + len, buf_len - len, "rx_ulofdma_data_nusers_%u = %u\n\n",
+			 user_index,
+			 le32_to_cpu(htt_stats_buf->rx_ulofdma_data_nusers));
+
+	stats_req->buf_len = len;
+}
+
 static void
 ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(const void *tag_buf, u16 tag_len,
 					     struct debug_htt_stats_req *stats_req)
@@ -4835,6 +4960,12 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_LATENCY_PROF_STATS_TAG:
 		ath12k_htt_print_latency_prof_stats_tlv(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG:
+		ath12k_htt_print_ul_ofdma_trigger_stats(tag_buf, len, stats_req);
+		break;
+	case HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG:
+		ath12k_htt_print_ul_ofdma_user_stats(tag_buf, len, stats_req);
+		break;
 	case HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG:
 		ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(tag_buf, len, stats_req);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 1b835473f419c..ab293dff7e44e 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -139,6 +139,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO	= 22,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	= 23,
 	ATH12K_DBG_HTT_EXT_STATS_LATENCY_PROF_STATS	= 25,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_TRIG_STATS	= 26,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT	= 30,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF	= 31,
 	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA		= 32,
@@ -210,6 +211,8 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_LATENCY_PROF_STATS_TAG		= 91,
 	HTT_STATS_LATENCY_CTX_TAG			= 92,
 	HTT_STATS_LATENCY_CNT_TAG			= 93,
+	HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG		= 94,
+	HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG	= 95,
 	HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG	= 100,
 	HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG		= 102,
 	HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG		= 103,
@@ -1374,6 +1377,55 @@ struct ath12k_htt_latency_prof_cnt_tlv {
 	__le32 prof_enable_cnt;
 } __packed;
 
+#define ATH12K_HTT_RX_NUM_MCS_CNTRS		12
+#define ATH12K_HTT_RX_NUM_GI_CNTRS		4
+#define ATH12K_HTT_RX_NUM_SPATIAL_STREAMS	8
+#define ATH12K_HTT_RX_NUM_BW_CNTRS		4
+#define ATH12K_HTT_RX_NUM_RU_SIZE_CNTRS		6
+#define ATH12K_HTT_RX_NUM_RU_SIZE_160MHZ_CNTRS	7
+#define ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK	5
+#define ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES	2
+
+enum ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE {
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_26,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_52,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_106,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_242,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_484,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996,
+	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996x2,
+	ATH12K_HTT_TX_RX_PDEV_STATS_NUM_AX_RU_SIZE_CNTRS,
+};
+
+struct ath12k_htt_rx_pdev_ul_ofdma_user_stats_tlv {
+	__le32 user_index;
+	__le32 rx_ulofdma_non_data_ppdu;
+	__le32 rx_ulofdma_data_ppdu;
+	__le32 rx_ulofdma_mpdu_ok;
+	__le32 rx_ulofdma_mpdu_fail;
+	__le32 rx_ulofdma_non_data_nusers;
+	__le32 rx_ulofdma_data_nusers;
+} __packed;
+
+struct ath12k_htt_rx_pdev_ul_trigger_stats_tlv {
+	__le32 mac_id__word;
+	__le32 rx_11ax_ul_ofdma;
+	__le32 ul_ofdma_rx_mcs[ATH12K_HTT_RX_NUM_MCS_CNTRS];
+	__le32 ul_ofdma_rx_gi[ATH12K_HTT_RX_NUM_GI_CNTRS][ATH12K_HTT_RX_NUM_MCS_CNTRS];
+	__le32 ul_ofdma_rx_nss[ATH12K_HTT_RX_NUM_SPATIAL_STREAMS];
+	__le32 ul_ofdma_rx_bw[ATH12K_HTT_RX_NUM_BW_CNTRS];
+	__le32 ul_ofdma_rx_stbc;
+	__le32 ul_ofdma_rx_ldpc;
+	__le32 data_ru_size_ppdu[ATH12K_HTT_RX_NUM_RU_SIZE_160MHZ_CNTRS];
+	__le32 non_data_ru_size_ppdu[ATH12K_HTT_RX_NUM_RU_SIZE_160MHZ_CNTRS];
+	__le32 uplink_sta_aid[ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK];
+	__le32 uplink_sta_target_rssi[ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK];
+	__le32 uplink_sta_fd_rssi[ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK];
+	__le32 uplink_sta_power_headroom[ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK];
+	__le32 red_bw[ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES][ATH12K_HTT_RX_NUM_BW_CNTRS];
+	__le32 ul_ofdma_bsc_trig_rx_qos_null_only;
+} __packed;
+
 #define ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS		14
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS		8
@@ -1711,17 +1763,6 @@ enum ATH12K_HTT_RC_MODE {
 	ATH12K_HTT_RC_MODE_2D_COUNT
 };
 
-enum ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE {
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_26,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_52,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_106,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_242,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_484,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996,
-	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_996x2,
-	ATH12K_HTT_TX_RX_PDEV_STATS_NUM_AX_RU_SIZE_CNTRS
-};
-
 enum ath12k_htt_stats_rc_mode {
 	ATH12K_HTT_STATS_RC_MODE_DLSU     = 0,
 	ATH12K_HTT_STATS_RC_MODE_DLMUMIMO = 1,

From 1dbaae78e7f23819eb75f4ba8a4484e43cf625f9 Mon Sep 17 00:00:00 2001
From: Roopni Devanathan <quic_rdevanat@quicinc.com>
Date: Tue, 4 Feb 2025 12:14:16 +0530
Subject: [PATCH 0453/2753] wifi: ath12k: Support Uplink MUMIMO Trigger Stats

Add support to request uplink MUMIMO trigger stats from firmware
through HTT stats type 27. These stats give information about
bandwidth, RSSI of signal received, dB mean of pilots received,
etc., of all users.

Note: MCC firmware version WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4
does not support tags HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG(94) and
HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG(95), currently.

Sample output:
-------------
echo 27 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_RX_PDEV_UL_MUMIMO_TRIG_STATS_TLV:
mac_id = 0
rx_11ax_ul_mumimo = 0
ul_mumimo_rx_mcs =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_mumimo_rx_gi_0 =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
ul_mumimo_rx_gi_1 =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0, 9:0, 10:0, 11:0, 12:0, 13:0
.....
ul_mumimo_rx_nss =  1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0, 8:0
ul_mumimo_rx_bw =  0:0, 1:0, 2:0, 3:0
half_ul_mumimo_rx_bw =  0:0, 1:0, 2:0, 3:0
quarter_ul_mumimo_rx_bw =  0:0, 1:0, 2:0, 3:0
ul_mumimo_rx_stbc = 0
ul_mumimo_rx_ldpc = 0
rx_ul_mumimo_rssi_in_dbm: chain0  =  0:6, 1:0, 2:0, 3:0
rx_ul_mumimo_rssi_in_dbm: chain1  =  0:0, 1:0, 2:0, 3:0
.....
rx_ul_mumimo_target_rssi: user_0  =  0:-128, 1:-128, 2:-128, 3:-128
rx_ul_mumimo_target_rssi: user_1  =  0:-128, 1:-128, 2:-128, 3:-128
.....
rx_ul_mumimo_fd_rssi: user_0  =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ul_mumimo_fd_rssi: user_1  =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
.....
rx_ulmumimo_pilot_evm_db_mean: user_0  =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
rx_ulmumimo_pilot_evm_db_mean: user_1  =  0:0, 1:0, 2:0, 3:0, 4:0, 5:0, 6:0, 7:0
.....
ul_mumimo_basic_trigger_rx_qos_null_only = 0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Link: https://patch.msgid.link/20250204064417.3671928-5-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 155 ++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   |  84 ++++++----
 2 files changed, 209 insertions(+), 30 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index a235c5b6dcab2..935ea9852a8e1 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -48,6 +48,34 @@ print_array_to_buf(u8 *buf, u32 offset, const char *header,
 					footer);
 }
 
+static u32
+print_array_to_buf_s8(u8 *buf, u32 offset, const char *header, u32 stats_index,
+		      const s8 *array, u32 array_len, const char *footer)
+{
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	int index = 0;
+	u8 i;
+
+	if (header)
+		index += scnprintf(buf + offset, buf_len - offset, "%s = ", header);
+
+	for (i = 0; i < array_len; i++) {
+		index += scnprintf(buf + offset + index, (buf_len - offset) - index,
+				   " %u:%d,", stats_index++, array[i]);
+	}
+
+	index--;
+	if ((offset + index) < buf_len)
+		buf[offset + index] = '\0';
+
+	if (footer) {
+		index += scnprintf(buf + offset + index, (buf_len - offset) - index,
+				   "%s", footer);
+	}
+
+	return index;
+}
+
 static const char *ath12k_htt_ax_tx_rx_ru_size_to_str(u8 ru_size)
 {
 	switch (ru_size) {
@@ -3048,6 +3076,130 @@ ath12k_htt_print_ul_ofdma_user_stats(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_ul_mumimo_trig_stats(const void *tag_buf, u16 tag_len,
+				      struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_ul_mumimo_trig_stats_tlv *htt_stats_buf = tag_buf;
+	char str_buf[ATH12K_HTT_MAX_STRING_LEN] = {0};
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+	u32 mac_id;
+	u16 index;
+	u8 i, j;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	mac_id = __le32_to_cpu(htt_stats_buf->mac_id__word);
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "HTT_RX_PDEV_UL_MUMIMO_TRIG_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "mac_id = %u\n",
+			 u32_get_bits(mac_id, ATH12K_HTT_STATS_MAC_ID));
+	len += scnprintf(buf + len, buf_len - len, "rx_11ax_ul_mumimo = %u\n",
+			 le32_to_cpu(htt_stats_buf->rx_11ax_ul_mumimo));
+	index = 0;
+	memset(str_buf, 0x0, ATH12K_HTT_MAX_STRING_LEN);
+	for (i = 0; i < ATH12K_HTT_RX_NUM_MCS_CNTRS; i++)
+		index += scnprintf(&str_buf[index], ATH12K_HTT_MAX_STRING_LEN - index,
+				  " %u:%u,", i,
+				  le32_to_cpu(htt_stats_buf->ul_mumimo_rx_mcs[i]));
+
+	for (i = 0; i < ATH12K_HTT_RX_NUM_EXTRA_MCS_CNTRS; i++)
+		index += scnprintf(&str_buf[index], ATH12K_HTT_MAX_STRING_LEN - index,
+				  " %u:%u,", i + ATH12K_HTT_RX_NUM_MCS_CNTRS,
+				  le32_to_cpu(htt_stats_buf->ul_mumimo_rx_mcs_ext[i]));
+	str_buf[--index] = '\0';
+	len += scnprintf(buf + len, buf_len - len, "ul_mumimo_rx_mcs = %s\n", str_buf);
+
+	for (j = 0; j < ATH12K_HTT_RX_NUM_GI_CNTRS; j++) {
+		index = 0;
+		memset(&str_buf[index], 0x0, ATH12K_HTT_MAX_STRING_LEN);
+		for (i = 0; i < ATH12K_HTT_RX_NUM_MCS_CNTRS; i++)
+			index += scnprintf(&str_buf[index],
+					  ATH12K_HTT_MAX_STRING_LEN - index,
+					  " %u:%u,", i,
+					  le32_to_cpu(htt_stats_buf->ul_rx_gi[j][i]));
+
+		for (i = 0; i < ATH12K_HTT_RX_NUM_EXTRA_MCS_CNTRS; i++)
+			index += scnprintf(&str_buf[index],
+					  ATH12K_HTT_MAX_STRING_LEN - index,
+					  " %u:%u,", i + ATH12K_HTT_RX_NUM_MCS_CNTRS,
+					  le32_to_cpu(htt_stats_buf->ul_gi_ext[j][i]));
+		str_buf[--index] = '\0';
+		len += scnprintf(buf + len, buf_len - len,
+				 "ul_mumimo_rx_gi_%u = %s\n", j, str_buf);
+	}
+
+	index = 0;
+	memset(str_buf, 0x0, ATH12K_HTT_MAX_STRING_LEN);
+	len += print_array_to_buf_index(buf, len, "ul_mumimo_rx_nss", 1,
+					htt_stats_buf->ul_mumimo_rx_nss,
+					ATH12K_HTT_RX_NUM_SPATIAL_STREAMS, "\n");
+
+	len += print_array_to_buf(buf, len, "ul_mumimo_rx_bw",
+				  htt_stats_buf->ul_mumimo_rx_bw,
+				  ATH12K_HTT_RX_NUM_BW_CNTRS, "\n");
+	for (i = 0; i < ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES; i++) {
+		index = 0;
+		memset(str_buf, 0x0, ATH12K_HTT_MAX_STRING_LEN);
+		for (j = 0; j < ATH12K_HTT_RX_NUM_BW_CNTRS; j++)
+			index += scnprintf(&str_buf[index],
+					  ATH12K_HTT_MAX_STRING_LEN - index,
+					  " %u:%u,", j,
+					  le32_to_cpu(htt_stats_buf->red_bw[i][j]));
+		str_buf[--index] = '\0';
+		len += scnprintf(buf + len, buf_len - len, "%s = %s\n",
+				 i == 0 ? "half_ul_mumimo_rx_bw" :
+				 "quarter_ul_mumimo_rx_bw", str_buf);
+	}
+
+	len += scnprintf(buf + len, buf_len - len, "ul_mumimo_rx_stbc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_mumimo_rx_stbc));
+	len += scnprintf(buf + len, buf_len - len, "ul_mumimo_rx_ldpc = %u\n",
+			 le32_to_cpu(htt_stats_buf->ul_mumimo_rx_ldpc));
+
+	for (j = 0; j < ATH12K_HTT_RX_NUM_SPATIAL_STREAMS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_ul_mumimo_rssi_in_dbm: chain%u ", j);
+		len += print_array_to_buf_s8(buf, len, "", 0,
+					     htt_stats_buf->ul_rssi[j],
+					     ATH12K_HTT_RX_NUM_BW_CNTRS, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_UL_MUMIMO_USER_STATS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_ul_mumimo_target_rssi: user_%u ", j);
+		len += print_array_to_buf_s8(buf, len, "", 0,
+					     htt_stats_buf->tgt_rssi[j],
+					     ATH12K_HTT_RX_NUM_BW_CNTRS, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_UL_MUMIMO_USER_STATS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_ul_mumimo_fd_rssi: user_%u ", j);
+		len += print_array_to_buf_s8(buf, len, "", 0,
+					     htt_stats_buf->fd[j],
+					     ATH12K_HTT_RX_NUM_SPATIAL_STREAMS, "\n");
+	}
+
+	for (j = 0; j < ATH12K_HTT_TX_UL_MUMIMO_USER_STATS; j++) {
+		len += scnprintf(buf + len, buf_len - len,
+				 "rx_ulmumimo_pilot_evm_db_mean: user_%u ", j);
+		len += print_array_to_buf_s8(buf, len, "", 0,
+					     htt_stats_buf->db[j],
+					     ATH12K_HTT_RX_NUM_SPATIAL_STREAMS, "\n");
+	}
+
+	len += scnprintf(buf + len, buf_len - len,
+			 "ul_mumimo_basic_trigger_rx_qos_null_only = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->mumimo_bsc_trig_rx_qos_null_only));
+
+	stats_req->buf_len = len;
+}
+
 static void
 ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(const void *tag_buf, u16 tag_len,
 					     struct debug_htt_stats_req *stats_req)
@@ -4966,6 +5118,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG:
 		ath12k_htt_print_ul_ofdma_user_stats(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_RX_PDEV_UL_MUMIMO_TRIG_STATS_TAG:
+		ath12k_htt_print_ul_mumimo_trig_stats(tag_buf, len, stats_req);
+		break;
 	case HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG:
 		ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(tag_buf, len, stats_req);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index ab293dff7e44e..9700412c03e00 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -123,36 +123,37 @@ struct ath12k_htt_extd_stats_msg {
 
 /* htt_dbg_ext_stats_type */
 enum ath12k_dbg_htt_ext_stats_type {
-	ATH12K_DBG_HTT_EXT_STATS_RESET			= 0,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX		= 1,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_SCHED		= 4,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_ERROR		= 5,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TQM		= 6,
-	ATH12K_DBG_HTT_EXT_STATS_TX_DE_INFO		= 8,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE		= 9,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE		= 10,
-	ATH12K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO	= 12,
-	ATH12K_DBG_HTT_EXT_STATS_SRNG_INFO		= 15,
-	ATH12K_DBG_HTT_EXT_STATS_SFM_INFO		= 16,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_MU		= 17,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS		= 19,
-	ATH12K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO	= 22,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS	= 23,
-	ATH12K_DBG_HTT_EXT_STATS_LATENCY_PROF_STATS	= 25,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_TRIG_STATS	= 26,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT	= 30,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF	= 31,
-	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA		= 32,
-	ATH12K_DBG_HTT_EXT_STATS_DLPAGER_STATS		= 36,
-	ATH12K_DBG_HTT_EXT_PHY_COUNTERS_AND_PHY_STATS	= 37,
-	ATH12K_DBG_HTT_EXT_VDEVS_TXRX_STATS		= 38,
-	ATH12K_DBG_HTT_EXT_PDEV_PER_STATS		= 40,
-	ATH12K_DBG_HTT_EXT_AST_ENTRIES			= 41,
-	ATH12K_DBG_HTT_EXT_STATS_SOC_ERROR		= 45,
-	ATH12K_DBG_HTT_DBG_PDEV_PUNCTURE_STATS		= 46,
-	ATH12K_DBG_HTT_EXT_STATS_PDEV_SCHED_ALGO	= 49,
-	ATH12K_DBG_HTT_EXT_STATS_MANDATORY_MUOFDMA	= 51,
-	ATH12K_DGB_HTT_EXT_STATS_PDEV_MBSSID_CTRL_FRAME	= 54,
+	ATH12K_DBG_HTT_EXT_STATS_RESET				= 0,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX			= 1,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_SCHED			= 4,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_ERROR			= 5,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TQM			= 6,
+	ATH12K_DBG_HTT_EXT_STATS_TX_DE_INFO			= 8,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE			= 9,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE			= 10,
+	ATH12K_DBG_HTT_EXT_STATS_TX_SELFGEN_INFO		= 12,
+	ATH12K_DBG_HTT_EXT_STATS_SRNG_INFO			= 15,
+	ATH12K_DBG_HTT_EXT_STATS_SFM_INFO			= 16,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_MU			= 17,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_CCA_STATS			= 19,
+	ATH12K_DBG_HTT_EXT_STATS_TX_SOUNDING_INFO		= 22,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_OBSS_PD_STATS		= 23,
+	ATH12K_DBG_HTT_EXT_STATS_LATENCY_PROF_STATS		= 25,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_TRIG_STATS		= 26,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_MUMIMO_TRIG_STATS	= 27,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT		= 30,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF		= 31,
+	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA			= 32,
+	ATH12K_DBG_HTT_EXT_STATS_DLPAGER_STATS			= 36,
+	ATH12K_DBG_HTT_EXT_PHY_COUNTERS_AND_PHY_STATS		= 37,
+	ATH12K_DBG_HTT_EXT_VDEVS_TXRX_STATS			= 38,
+	ATH12K_DBG_HTT_EXT_PDEV_PER_STATS			= 40,
+	ATH12K_DBG_HTT_EXT_AST_ENTRIES				= 41,
+	ATH12K_DBG_HTT_EXT_STATS_SOC_ERROR			= 45,
+	ATH12K_DBG_HTT_DBG_PDEV_PUNCTURE_STATS			= 46,
+	ATH12K_DBG_HTT_EXT_STATS_PDEV_SCHED_ALGO		= 49,
+	ATH12K_DBG_HTT_EXT_STATS_MANDATORY_MUOFDMA		= 51,
+	ATH12K_DGB_HTT_EXT_STATS_PDEV_MBSSID_CTRL_FRAME		= 54,
 
 	/* keep this last */
 	ATH12K_DBG_HTT_NUM_EXT_STATS,
@@ -213,6 +214,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_LATENCY_CNT_TAG			= 93,
 	HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG		= 94,
 	HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG	= 95,
+	HTT_STATS_RX_PDEV_UL_MUMIMO_TRIG_STATS_TAG	= 97,
 	HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG	= 100,
 	HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG		= 102,
 	HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG		= 103,
@@ -1385,6 +1387,7 @@ struct ath12k_htt_latency_prof_cnt_tlv {
 #define ATH12K_HTT_RX_NUM_RU_SIZE_160MHZ_CNTRS	7
 #define ATH12K_HTT_RX_UL_MAX_UPLINK_RSSI_TRACK	5
 #define ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES	2
+#define ATH12K_HTT_RX_NUM_EXTRA_MCS_CNTRS	2
 
 enum ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE {
 	ATH12K_HTT_TX_RX_PDEV_STATS_AX_RU_SIZE_26,
@@ -1426,6 +1429,27 @@ struct ath12k_htt_rx_pdev_ul_trigger_stats_tlv {
 	__le32 ul_ofdma_bsc_trig_rx_qos_null_only;
 } __packed;
 
+#define ATH12K_HTT_TX_UL_MUMIMO_USER_STATS	8
+
+struct ath12k_htt_rx_ul_mumimo_trig_stats_tlv {
+	__le32 mac_id__word;
+	__le32 rx_11ax_ul_mumimo;
+	__le32 ul_mumimo_rx_mcs[ATH12K_HTT_RX_NUM_MCS_CNTRS];
+	__le32 ul_rx_gi[ATH12K_HTT_RX_NUM_GI_CNTRS][ATH12K_HTT_RX_NUM_MCS_CNTRS];
+	__le32 ul_mumimo_rx_nss[ATH12K_HTT_RX_NUM_SPATIAL_STREAMS];
+	__le32 ul_mumimo_rx_bw[ATH12K_HTT_RX_NUM_BW_CNTRS];
+	__le32 ul_mumimo_rx_stbc;
+	__le32 ul_mumimo_rx_ldpc;
+	__le32 ul_mumimo_rx_mcs_ext[ATH12K_HTT_RX_NUM_EXTRA_MCS_CNTRS];
+	__le32 ul_gi_ext[ATH12K_HTT_RX_NUM_GI_CNTRS][ATH12K_HTT_RX_NUM_EXTRA_MCS_CNTRS];
+	s8 ul_rssi[ATH12K_HTT_RX_NUM_SPATIAL_STREAMS][ATH12K_HTT_RX_NUM_BW_CNTRS];
+	s8 tgt_rssi[ATH12K_HTT_TX_UL_MUMIMO_USER_STATS][ATH12K_HTT_RX_NUM_BW_CNTRS];
+	s8 fd[ATH12K_HTT_TX_UL_MUMIMO_USER_STATS][ATH12K_HTT_RX_NUM_SPATIAL_STREAMS];
+	s8 db[ATH12K_HTT_TX_UL_MUMIMO_USER_STATS][ATH12K_HTT_RX_NUM_SPATIAL_STREAMS];
+	__le32 red_bw[ATH12K_HTT_RX_NUM_REDUCED_CHAN_TYPES][ATH12K_HTT_RX_NUM_BW_CNTRS];
+	__le32 mumimo_bsc_trig_rx_qos_null_only;
+} __packed;
+
 #define ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS		14
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS		8

From 7b19d5adadfef791d52fd0412a75ebb8f9f27a6b Mon Sep 17 00:00:00 2001
From: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Date: Tue, 4 Feb 2025 12:14:17 +0530
Subject: [PATCH 0454/2753] wifi: ath12k: Support Received FSE Stats

Add support to request received Finite State Entropy stats from
firmware through HTT stats type 28. These stats give software and
hardware FSE stats such as cache entry count, full cache count,
current and peak occupancy count, pending search counts, etc.

Sample output:
-------------
echo 28 > /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats_type
cat /sys/kernel/debug/ath12k/pci-0000\:06\:00.0/mac0/htt_stats
HTT_STATS_RX_FSE_STATS_TLV:
=== Software RX FSE STATS ===
Enable count  = 0
Disable count = 0
Cache invalidate entry count = 0
Full cache invalidate count = 0

=== Hardware RX FSE STATS ===
Cache hits count = 0
Cache no. of searches = 0
Cache occupancy peak count:
[0] = 0 [1-16] = 0 [17-32] = 0 [33-48] = 0 [49-64] = 0 [65-80] = 0 [81-96] = 0 [97-112] = 0 [113-127] = 0 [128] = 0
Cache occupancy current count:
[0] = 0 [1-16] = 0 [17-32] = 0 [33-48] = 0 [49-64] = 0 [65-80] = 0 [81-96] = 0 [97-112] = 0 [113-127] = 0 [128] = 0
Cache search square count:
[0] = 0 [1-50] = 0 [51-100] = 0 [101-200] = 0 [201-255] = 0 [256] = 0
Cache search peak pending count:
[0] = 0 [1-2] = 0 [3-4] = 0 [Greater/Equal to 5] = 0
Cache search tot pending count:
[0] = 0 [1-2] = 0 [3-4] = 0 [Greater/Equal to 5] = 0

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Signed-off-by: Dinesh Karthikeyan <quic_dinek@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Link: https://patch.msgid.link/20250204064417.3671928-6-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../wireless/ath/ath12k/debugfs_htt_stats.c   | 91 +++++++++++++++++++
 .../wireless/ath/ath12k/debugfs_htt_stats.h   | 22 +++++
 2 files changed, 113 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
index 935ea9852a8e1..1c0d5fa39a8dc 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.c
@@ -3200,6 +3200,94 @@ ath12k_htt_print_ul_mumimo_trig_stats(const void *tag_buf, u16 tag_len,
 	stats_req->buf_len = len;
 }
 
+static void
+ath12k_htt_print_rx_fse_stats_tlv(const void *tag_buf, u16 tag_len,
+				  struct debug_htt_stats_req *stats_req)
+{
+	const struct ath12k_htt_rx_fse_stats_tlv *htt_stats_buf = tag_buf;
+	u32 buf_len = ATH12K_HTT_STATS_BUF_SIZE;
+	u32 len = stats_req->buf_len;
+	u8 *buf = stats_req->buf;
+
+	if (tag_len < sizeof(*htt_stats_buf))
+		return;
+
+	len += scnprintf(buf + len, buf_len - len, "HTT_STATS_RX_FSE_STATS_TLV:\n");
+	len += scnprintf(buf + len, buf_len - len, "=== Software RX FSE STATS ===\n");
+	len += scnprintf(buf + len, buf_len - len, "Enable count  = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_enable_cnt));
+	len += scnprintf(buf + len, buf_len - len, "Disable count = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_disable_cnt));
+	len += scnprintf(buf + len, buf_len - len, "Cache invalidate entry count = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_cache_invalidate_entry_cnt));
+	len += scnprintf(buf + len, buf_len - len, "Full cache invalidate count = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_full_cache_invalidate_cnt));
+
+	len += scnprintf(buf + len, buf_len - len, "\n=== Hardware RX FSE STATS ===\n");
+	len += scnprintf(buf + len, buf_len - len, "Cache hits count = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_num_cache_hits_cnt));
+	len += scnprintf(buf + len, buf_len - len, "Cache no. of searches = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_num_searches_cnt));
+	len += scnprintf(buf + len, buf_len - len, "Cache occupancy peak count:\n");
+	len += scnprintf(buf + len, buf_len - len, "[0] = %u [1-16] = %u [17-32] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[0]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[1]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[2]));
+	len += scnprintf(buf + len, buf_len - len, "[33-48] = %u [49-64] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[3]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[4]));
+	len += scnprintf(buf + len, buf_len - len, "[65-80] = %u [81-96] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[5]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[6]));
+	len += scnprintf(buf + len, buf_len - len, "[97-112] = %u [113-127] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[7]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[8]));
+	len += scnprintf(buf + len, buf_len - len, "[128] = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_peak_cnt[9]));
+	len += scnprintf(buf + len, buf_len - len, "Cache occupancy current count:\n");
+	len += scnprintf(buf + len, buf_len - len, "[0] = %u [1-16] = %u [17-32] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[0]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[1]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[2]));
+	len += scnprintf(buf + len, buf_len - len, "[33-48] = %u [49-64] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[3]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[4]));
+	len += scnprintf(buf + len, buf_len - len, "[65-80] = %u [81-96] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[5]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[6]));
+	len += scnprintf(buf + len, buf_len - len, "[97-112] = %u [113-127] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[7]),
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[8]));
+	len += scnprintf(buf + len, buf_len - len, "[128] = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_cache_occupancy_curr_cnt[9]));
+	len += scnprintf(buf + len, buf_len - len, "Cache search square count:\n");
+	len += scnprintf(buf + len, buf_len - len, "[0] = %u [1-50] = %u [51-100] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[0]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[1]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[2]));
+	len += scnprintf(buf + len, buf_len - len, "[101-200] = %u [201-255] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[3]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[4]));
+	len += scnprintf(buf + len, buf_len - len, "[256] = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_square_cnt[5]));
+	len += scnprintf(buf + len, buf_len - len, "Cache search peak pending count:\n");
+	len += scnprintf(buf + len, buf_len - len, "[0] = %u [1-2] = %u [3-4] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_peak_cnt[0]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_peak_cnt[1]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_peak_cnt[2]));
+	len += scnprintf(buf + len, buf_len - len, "[Greater/Equal to 5] = %u\n",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_peak_cnt[3]));
+	len += scnprintf(buf + len, buf_len - len, "Cache search tot pending count:\n");
+	len += scnprintf(buf + len, buf_len - len, "[0] = %u [1-2] = %u [3-4] = %u ",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_pending_cnt[0]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_pending_cnt[1]),
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_pending_cnt[2]));
+	len += scnprintf(buf + len, buf_len - len, "[Greater/Equal to 5] = %u\n\n",
+			 le32_to_cpu(htt_stats_buf->fse_search_stat_pending_cnt[3]));
+
+	stats_req->buf_len = len;
+}
+
 static void
 ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(const void *tag_buf, u16 tag_len,
 					     struct debug_htt_stats_req *stats_req)
@@ -5121,6 +5209,9 @@ static int ath12k_dbg_htt_ext_stats_parse(struct ath12k_base *ab,
 	case HTT_STATS_RX_PDEV_UL_MUMIMO_TRIG_STATS_TAG:
 		ath12k_htt_print_ul_mumimo_trig_stats(tag_buf, len, stats_req);
 		break;
+	case HTT_STATS_RX_FSE_STATS_TAG:
+		ath12k_htt_print_rx_fse_stats_tlv(tag_buf, len, stats_req);
+		break;
 	case HTT_STATS_PDEV_TX_RATE_TXBF_STATS_TAG:
 		ath12k_htt_print_pdev_tx_rate_txbf_stats_tlv(tag_buf, len, stats_req);
 		break;
diff --git a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
index 9700412c03e00..c2a02cf8a38b7 100644
--- a/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
+++ b/drivers/net/wireless/ath/ath12k/debugfs_htt_stats.h
@@ -141,6 +141,7 @@ enum ath12k_dbg_htt_ext_stats_type {
 	ATH12K_DBG_HTT_EXT_STATS_LATENCY_PROF_STATS		= 25,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_TRIG_STATS		= 26,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_UL_MUMIMO_TRIG_STATS	= 27,
+	ATH12K_DBG_HTT_EXT_STATS_FSE_RX				= 28,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_RX_RATE_EXT		= 30,
 	ATH12K_DBG_HTT_EXT_STATS_PDEV_TX_RATE_TXBF		= 31,
 	ATH12K_DBG_HTT_EXT_STATS_TXBF_OFDMA			= 32,
@@ -215,6 +216,7 @@ enum ath12k_dbg_htt_tlv_tag {
 	HTT_STATS_RX_PDEV_UL_TRIG_STATS_TAG		= 94,
 	HTT_STATS_RX_PDEV_UL_OFDMA_USER_STATS_TAG	= 95,
 	HTT_STATS_RX_PDEV_UL_MUMIMO_TRIG_STATS_TAG	= 97,
+	HTT_STATS_RX_FSE_STATS_TAG			= 98,
 	HTT_STATS_SCHED_TXQ_SUPERCYCLE_TRIGGER_TAG	= 100,
 	HTT_STATS_PDEV_CTRL_PATH_TX_STATS_TAG		= 102,
 	HTT_STATS_RX_PDEV_RATE_EXT_STATS_TAG		= 103,
@@ -1450,6 +1452,26 @@ struct ath12k_htt_rx_ul_mumimo_trig_stats_tlv {
 	__le32 mumimo_bsc_trig_rx_qos_null_only;
 } __packed;
 
+#define ATH12K_HTT_RX_NUM_MAX_PEAK_OCCUPANCY_INDEX	10
+#define ATH12K_HTT_RX_NUM_MAX_CURR_OCCUPANCY_INDEX	10
+#define ATH12K_HTT_RX_NUM_SQUARE_INDEX			6
+#define ATH12K_HTT_RX_NUM_MAX_PEAK_SEARCH_INDEX		4
+#define ATH12K_HTT_RX_NUM_MAX_PENDING_SEARCH_INDEX	4
+
+struct ath12k_htt_rx_fse_stats_tlv {
+	__le32 fse_enable_cnt;
+	__le32 fse_disable_cnt;
+	__le32 fse_cache_invalidate_entry_cnt;
+	__le32 fse_full_cache_invalidate_cnt;
+	__le32 fse_num_cache_hits_cnt;
+	__le32 fse_num_searches_cnt;
+	__le32 fse_cache_occupancy_peak_cnt[ATH12K_HTT_RX_NUM_MAX_PEAK_OCCUPANCY_INDEX];
+	__le32 fse_cache_occupancy_curr_cnt[ATH12K_HTT_RX_NUM_MAX_CURR_OCCUPANCY_INDEX];
+	__le32 fse_search_stat_square_cnt[ATH12K_HTT_RX_NUM_SQUARE_INDEX];
+	__le32 fse_search_stat_peak_cnt[ATH12K_HTT_RX_NUM_MAX_PEAK_SEARCH_INDEX];
+	__le32 fse_search_stat_pending_cnt[ATH12K_HTT_RX_NUM_MAX_PENDING_SEARCH_INDEX];
+} __packed;
+
 #define ATH12K_HTT_TX_BF_RATE_STATS_NUM_MCS_COUNTERS		14
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_LEGACY_OFDM_STATS		8
 #define ATH12K_HTT_TX_PDEV_STATS_NUM_SPATIAL_STREAMS		8

From 7d1163fc08936fcb5cf5d9daf366c322c3b4e882 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Fri, 7 Feb 2025 15:39:01 +0100
Subject: [PATCH 0455/2753] arm64: dts: rockchip: disable IOMMU when running
 rk3588 in PCIe endpoint mode

Commit da92d3dfc871 ("arm64: dts: rockchip: enable the mmu600_pcie IOMMU
on the rk3588 SoC") enabled the mmu600_pcie IOMMU, both in the normal case
(when all PCIe controllers are running in Root Complex mode) and in the
case when running the pcie3x4 PCIe controller in Endpoint mode.

There have been no issues detected when running the PCIe controllers in
Root Complex mode. During PCI probe time, we will add a SID to the IOMMU
for each PCI device enumerated on the bus, including the root port itself.

However, when running the pcie3x4 PCIe controller in Endpoint mode, we
will only add a single SID to the IOMMU (the SID specified in the iommus
DT property).

The enablement of IOMMU in endpoint mode was verified on setup with two
Rock 5b:s, where the BDF of the Root Complex has BDF (00:00.0).

A Root Complex sending a TLP to the Endpoint will have Requester ID set
to the BDF of the initiator. On the EP side, the Requester ID will then
be used as the SID. This works fine if the Root Complex has a BDF that
matches the iommus DT property, however, if the Root Complex has any other
BDF, we will see something like:
arm-smmu-v3 fc900000.iommu: event: C_BAD_STREAMID client: (unassigned sid) sid: 0x1600 ssid: 0x0
on the endpoint side.

For PCIe controllers running in endpoint mode that always uses the
incoming Requester ID as the SID, the iommus DT property simply isn't
a viable solution. (Neither is iommu-map a viable solution, as there is
no enumeration done on the endpoint side.)

Thus, partly revert commit da92d3dfc871 ("arm64: dts: rockchip: enable the
mmu600_pcie IOMMU on the rk3588 SoC") by disabling the PCI IOMMU when
running the pcie3x4 PCIe controller in Endpoint mode.

Since the PCI IOMMU is working as expected in the normal case, keep it
enabled when running all PCIe controllers in Root Complex mode.

Fixes: da92d3dfc871 ("arm64: dts: rockchip: enable the mmu600_pcie IOMMU on the rk3588 SoC")
Signed-off-by: Niklas Cassel <cassel@kernel.org>
Acked-by: Robin Murphy <robin.murphy@arm.com>
Link: https://lore.kernel.org/r/20250207143900.2047949-2-cassel@kernel.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi           | 1 -
 arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso | 4 ++++
 2 files changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
index 4a950907ea6f5..840b638af1c24 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-extra.dtsi
@@ -213,7 +213,6 @@
 		interrupt-names = "sys", "pmc", "msg", "legacy", "err",
 				  "dma0", "dma1", "dma2", "dma3";
 		max-link-speed = <3>;
-		iommus = <&mmu600_pcie 0x0000>;
 		num-lanes = <4>;
 		phys = <&pcie30phy>;
 		phy-names = "pcie-phy";
diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
index 672d748fcc67c..f229cb49da680 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5b-pcie-ep.dtso
@@ -23,3 +23,7 @@
 	vpcie3v3-supply = <&vcc3v3_pcie30>;
 	status = "okay";
 };
+
+&mmu600_pcie {
+	status = "disabled";
+};

From 8546cfd08aa4b982acd2357403a1f15495d622ec Mon Sep 17 00:00:00 2001
From: Patrick Wildt <patrick@blueri.se>
Date: Mon, 10 Feb 2025 22:37:29 +0100
Subject: [PATCH 0456/2753] arm64: dts: rockchip: adjust SMMU interrupt type on
 rk3588

The SMMU architecture requires wired interrupts to be edge triggered,
which does not align with the DT description for the RK3588.  This leads
to interrupt storms, as the SMMU continues to hold the pin high and only
pulls it down for a short amount when issuing an IRQ.  Update the DT
description to be in line with the spec and perceived reality.

Signed-off-by: Patrick Wildt <patrick@blueri.se>
Fixes: cd81d3a0695c ("arm64: dts: rockchip: add rk3588 pcie and php IOMMUs")
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/Z6pxme2Chmf3d3uK@windev.fritz.box
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-base.dtsi | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
index 978de506d4348..c3abdfb04f8f4 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-base.dtsi
@@ -549,10 +549,10 @@
 	mmu600_pcie: iommu@fc900000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfc900000 0x0 0x200000>;
-		interrupts = <GIC_SPI 369 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 371 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 374 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 367 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 369 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 371 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 374 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 367 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 	};
@@ -560,10 +560,10 @@
 	mmu600_php: iommu@fcb00000 {
 		compatible = "arm,smmu-v3";
 		reg = <0x0 0xfcb00000 0x0 0x200000>;
-		interrupts = <GIC_SPI 381 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 383 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 386 IRQ_TYPE_LEVEL_HIGH 0>,
-			     <GIC_SPI 379 IRQ_TYPE_LEVEL_HIGH 0>;
+		interrupts = <GIC_SPI 381 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 383 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 386 IRQ_TYPE_EDGE_RISING 0>,
+			     <GIC_SPI 379 IRQ_TYPE_EDGE_RISING 0>;
 		interrupt-names = "eventq", "gerror", "priq", "cmdq-sync";
 		#iommu-cells = <1>;
 		status = "disabled";

From 8eb0d381be31bfa01f768ad38a15af7ade805e69 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 10 Feb 2025 21:49:22 +0100
Subject: [PATCH 0457/2753] net: phy: rename eee_broken_modes to
 eee_disabled_modes

This bitmap is used also if the MAC doesn't support an EEE mode.
So the mode isn't necessarily broken in the PHY. Therefore rename
the bitmap.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/6cd11422-dd67-4c87-a642-308de694af92@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c    | 2 +-
 drivers/net/phy/phy-core.c   | 2 +-
 drivers/net/phy/phy_device.c | 2 +-
 include/linux/phy.h          | 6 +++---
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 0dac08e85304b..468d246113a4b 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -686,7 +686,7 @@ static int genphy_c45_write_eee_adv(struct phy_device *phydev,
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(tmp);
 	int val, changed = 0;
 
-	linkmode_andnot(tmp, adv, phydev->eee_broken_modes);
+	linkmode_andnot(tmp, adv, phydev->eee_disabled_modes);
 
 	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) {
 		val = linkmode_to_mii_eee_cap1_t(tmp);
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index f181f05cb4297..2fd1d153abc99 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -406,7 +406,7 @@ void of_set_phy_supported(struct phy_device *phydev)
 void of_set_phy_eee_broken(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
-	unsigned long *modes = phydev->eee_broken_modes;
+	unsigned long *modes = phydev->eee_disabled_modes;
 
 	if (!IS_ENABLED(CONFIG_OF_MDIO) || !node)
 		return;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 46713d27412b7..9b06ba92f2ed2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2966,7 +2966,7 @@ void phy_disable_eee(struct phy_device *phydev)
 	phydev->eee_cfg.tx_lpi_enabled = false;
 	phydev->eee_cfg.eee_enabled = false;
 	/* don't let userspace re-enable EEE advertisement */
-	linkmode_fill(phydev->eee_broken_modes);
+	linkmode_fill(phydev->eee_disabled_modes);
 }
 EXPORT_SYMBOL_GPL(phy_disable_eee);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 19f076a71f946..dbc7e72458816 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -611,7 +611,7 @@ struct macsec_ops;
  * @eee_cfg: User configuration of EEE
  * @lp_advertising: Current link partner advertised linkmodes
  * @host_interfaces: PHY interface modes supported by host
- * @eee_broken_modes: Energy efficient ethernet modes which should be prohibited
+ * @eee_disabled_modes: Energy efficient ethernet modes not to be advertised
  * @autoneg: Flag autoneg being used
  * @rate_matching: Current rate matching mode
  * @link: Current link state
@@ -727,7 +727,7 @@ struct phy_device {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported_eee);
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertising_eee);
 	/* Energy efficient ethernet modes which should be prohibited */
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(eee_broken_modes);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(eee_disabled_modes);
 	bool enable_tx_lpi;
 	bool eee_active;
 	struct eee_config eee_cfg;
@@ -1353,7 +1353,7 @@ int phy_speed_down_core(struct phy_device *phydev);
  */
 static inline void phy_set_eee_broken(struct phy_device *phydev, u32 link_mode)
 {
-	linkmode_set_bit(link_mode, phydev->eee_broken_modes);
+	linkmode_set_bit(link_mode, phydev->eee_disabled_modes);
 }
 
 /**

From 5e7a74b6a35782be83b433979e71df2636ab05f0 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 10 Feb 2025 21:50:10 +0100
Subject: [PATCH 0458/2753] net: phy: rename phy_set_eee_broken to
 phy_disable_eee_mode

Consider that an EEE mode may not be broken but simply not supported
by the MAC, and rename function phy_set_eee_broken().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/30deb630-3f6b-4ffb-a1e6-a9736021f43a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 6 +++---
 include/linux/phy.h                       | 6 +++---
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 7306c8e323d72..32eb4a4482f9f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5252,9 +5252,9 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 
 	/* mimic behavior of r8125/r8126 vendor drivers */
 	if (tp->mac_version == RTL_GIGA_MAC_VER_61)
-		phy_set_eee_broken(tp->phydev,
-				   ETHTOOL_LINK_MODE_2500baseT_Full_BIT);
-	phy_set_eee_broken(tp->phydev, ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
+		phy_disable_eee_mode(tp->phydev,
+				     ETHTOOL_LINK_MODE_2500baseT_Full_BIT);
+	phy_disable_eee_mode(tp->phydev, ETHTOOL_LINK_MODE_5000baseT_Full_BIT);
 
 	/* PHY will be woken up in rtl_open() */
 	phy_suspend(tp->phydev);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index dbc7e72458816..29df4c6025898 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1347,11 +1347,11 @@ void of_set_phy_timing_role(struct phy_device *phydev);
 int phy_speed_down_core(struct phy_device *phydev);
 
 /**
- * phy_set_eee_broken - Mark an EEE mode as broken so that it isn't advertised.
+ * phy_disable_eee_mode - Don't advertise an EEE mode.
  * @phydev: The phy_device struct
- * @link_mode: The broken EEE mode
+ * @link_mode: The EEE mode to be disabled
  */
-static inline void phy_set_eee_broken(struct phy_device *phydev, u32 link_mode)
+static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode)
 {
 	linkmode_set_bit(link_mode, phydev->eee_disabled_modes);
 }

From b341f6fd45abb188653d9e0a2816bc53d64278b1 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Sat, 8 Feb 2025 14:26:43 -0500
Subject: [PATCH 0459/2753] blackhole_dev: convert self-test to KUnit

Convert this very simple smoke test to a KUnit test.

Add a missing `htons` call that was spotted[0] by kernel test robot
<lkp@intel.com> after initial conversion to KUnit.

Link: https://lore.kernel.org/oe-kbuild-all/202502090223.qCYMBjWT-lkp@intel.com/ [0]
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Link: https://patch.msgid.link/20250208-blackholedev-kunit-convert-v2-1-182db9bd56ec@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 lib/Kconfig.debug                             | 20 ++++----
 lib/Makefile                                  |  2 +-
 ..._blackhole_dev.c => blackhole_dev_kunit.c} | 47 +++++++------------
 tools/testing/selftests/net/Makefile          |  2 +-
 .../selftests/net/test_blackhole_dev.sh       | 11 -----
 5 files changed, 29 insertions(+), 53 deletions(-)
 rename lib/{test_blackhole_dev.c => blackhole_dev_kunit.c} (68%)
 delete mode 100755 tools/testing/selftests/net/test_blackhole_dev.sh

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1af972a92d06f..238321830993b 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2557,15 +2557,6 @@ config TEST_BPF
 
 	  If unsure, say N.
 
-config TEST_BLACKHOLE_DEV
-	tristate "Test blackhole netdev functionality"
-	depends on m && NET
-	help
-	  This builds the "test_blackhole_dev" module that validates the
-	  data path through this blackhole netdev.
-
-	  If unsure, say N.
-
 config FIND_BIT_BENCHMARK
 	tristate "Test find_bit functions"
 	help
@@ -2888,6 +2879,17 @@ config USERCOPY_KUNIT_TEST
 	  on the copy_to/from_user infrastructure, making sure basic
 	  user/kernel boundary testing is working.
 
+config BLACKHOLE_DEV_KUNIT_TEST
+	tristate "Test blackhole netdev functionality" if !KUNIT_ALL_TESTS
+	depends on NET
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  This builds the "blackhole_dev_kunit" module that validates the
+	  data path through this blackhole netdev.
+
+	  If unsure, say N.
+
 config TEST_UDELAY
 	tristate "udelay test driver"
 	help
diff --git a/lib/Makefile b/lib/Makefile
index d5cfc7afbbb82..19ff6993c2bc6 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -102,7 +102,6 @@ obj-$(CONFIG_TEST_RUNTIME) += tests/
 obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += test_debug_virtual.o
 obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o
 obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o
-obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o
 obj-$(CONFIG_TEST_MEMINIT) += test_meminit.o
 obj-$(CONFIG_TEST_LOCKUP) += test_lockup.o
 obj-$(CONFIG_TEST_HMM) += test_hmm.o
@@ -393,6 +392,7 @@ obj-$(CONFIG_FORTIFY_KUNIT_TEST) += fortify_kunit.o
 obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o
 obj-$(CONFIG_SIPHASH_KUNIT_TEST) += siphash_kunit.o
 obj-$(CONFIG_USERCOPY_KUNIT_TEST) += usercopy_kunit.o
+obj-$(CONFIG_BLACKHOLE_DEV_KUNIT_TEST) += blackhole_dev_kunit.o
 
 obj-$(CONFIG_GENERIC_LIB_DEVMEM_IS_ALLOWED) += devmem_is_allowed.o
 
diff --git a/lib/test_blackhole_dev.c b/lib/blackhole_dev_kunit.c
similarity index 68%
rename from lib/test_blackhole_dev.c
rename to lib/blackhole_dev_kunit.c
index ec290ac2a0d9a..06834ab35f43c 100644
--- a/lib/test_blackhole_dev.c
+++ b/lib/blackhole_dev_kunit.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * This module tests the blackhole_dev that is created during the
+ * This tests the blackhole_dev that is created during the
  * net subsystem initialization. The test this module performs is
  * by injecting an skb into the stack with skb->dev as the
  * blackhole_dev and expects kernel to behave in a sane manner
@@ -9,9 +9,8 @@
  * Copyright (c) 2018, Mahesh Bandewar <maheshb@google.com>
  */
 
-#include <linux/init.h>
+#include <kunit/test.h>
 #include <linux/module.h>
-#include <linux/printk.h>
 #include <linux/skbuff.h>
 #include <linux/netdevice.h>
 #include <linux/udp.h>
@@ -25,17 +24,15 @@
 
 #define UDP_PORT 1234
 
-static int __init test_blackholedev_init(void)
+static void test_blackholedev(struct kunit *test)
 {
 	struct ipv6hdr *ip6h;
 	struct sk_buff *skb;
 	struct udphdr *uh;
 	int data_len;
-	int ret;
 
 	skb = alloc_skb(SKB_SIZE, GFP_KERNEL);
-	if (!skb)
-		return -ENOMEM;
+	KUNIT_ASSERT_NOT_NULL(test, skb);
 
 	/* Reserve head-room for the headers */
 	skb_reserve(skb, HEAD_SIZE);
@@ -55,7 +52,7 @@ static int __init test_blackholedev_init(void)
 	ip6h = (struct ipv6hdr *)skb_push(skb, sizeof(struct ipv6hdr));
 	skb_set_network_header(skb, 0);
 	ip6h->hop_limit = 32;
-	ip6h->payload_len = data_len + sizeof(struct udphdr);
+	ip6h->payload_len = htons(data_len + sizeof(struct udphdr));
 	ip6h->nexthdr = IPPROTO_UDP;
 	ip6h->saddr = in6addr_loopback;
 	ip6h->daddr = in6addr_loopback;
@@ -68,32 +65,20 @@ static int __init test_blackholedev_init(void)
 	skb->dev = blackhole_netdev;
 
 	/* Now attempt to send the packet */
-	ret = dev_queue_xmit(skb);
-
-	switch (ret) {
-	case NET_XMIT_SUCCESS:
-		pr_warn("dev_queue_xmit() returned NET_XMIT_SUCCESS\n");
-		break;
-	case NET_XMIT_DROP:
-		pr_warn("dev_queue_xmit() returned NET_XMIT_DROP\n");
-		break;
-	case NET_XMIT_CN:
-		pr_warn("dev_queue_xmit() returned NET_XMIT_CN\n");
-		break;
-	default:
-		pr_err("dev_queue_xmit() returned UNKNOWN(%d)\n", ret);
-	}
-
-	return 0;
+	KUNIT_EXPECT_EQ(test, dev_queue_xmit(skb), NET_XMIT_SUCCESS);
 }
 
-static void __exit test_blackholedev_exit(void)
-{
-	pr_warn("test_blackholedev module terminating.\n");
-}
+static struct kunit_case blackholedev_cases[] = {
+	KUNIT_CASE(test_blackholedev),
+	{},
+};
+
+static struct kunit_suite blackholedev_suite = {
+	.name = "blackholedev",
+	.test_cases = blackholedev_cases,
+};
 
-module_init(test_blackholedev_init);
-module_exit(test_blackholedev_exit);
+kunit_test_suite(blackholedev_suite);
 
 MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
 MODULE_DESCRIPTION("module test of the blackhole_dev");
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index e2f03211f9b38..b6271714504d9 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -I../../../../usr/include/ $(KHDR_INCLUDES)
 CFLAGS += -I../
 
 TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh \
-	      rtnetlink.sh xfrm_policy.sh test_blackhole_dev.sh
+	      rtnetlink.sh xfrm_policy.sh
 TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh
 TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh
 TEST_PROGS += udpgro_bench.sh udpgro.sh test_vxlan_under_vrf.sh reuseport_addr_any.sh
diff --git a/tools/testing/selftests/net/test_blackhole_dev.sh b/tools/testing/selftests/net/test_blackhole_dev.sh
deleted file mode 100755
index 3119b80e711fd..0000000000000
--- a/tools/testing/selftests/net/test_blackhole_dev.sh
+++ /dev/null
@@ -1,11 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-# Runs blackhole-dev test using blackhole-dev kernel module
-
-if /sbin/modprobe -q test_blackhole_dev ; then
-	/sbin/modprobe -q -r test_blackhole_dev;
-	echo "test_blackhole_dev: ok";
-else
-	echo "test_blackhole_dev: [FAIL]";
-	exit 1;
-fi

From 3b147be9ef08247bb74a801b4e95f9a626a27322 Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Sat, 8 Feb 2025 23:06:21 -0500
Subject: [PATCH 0460/2753] hamradio: baycom: replace strcpy() with strscpy()

The strcpy() function has been deprecated and replaced with strscpy().
There is an effort to make this change treewide:
https://github.com/KSPP/linux/issues/88.

Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/3qo3fbrak7undfgocsi2s74v4uyjbylpdqhie4dohfoh4welfn@joq7up65ug6v
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hamradio/baycom_par.c     | 4 ++--
 drivers/net/hamradio/baycom_ser_fdx.c | 2 +-
 drivers/net/hamradio/baycom_ser_hdx.c | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/hamradio/baycom_par.c b/drivers/net/hamradio/baycom_par.c
index 00ebc25d0b22a..f03797103c6a2 100644
--- a/drivers/net/hamradio/baycom_par.c
+++ b/drivers/net/hamradio/baycom_par.c
@@ -427,7 +427,7 @@ static int baycom_ioctl(struct net_device *dev, void __user *data,
 		break;
 
 	case HDLCDRVCTL_GETMODE:
-		strcpy(hi->data.modename, bc->options ? "par96" : "picpar");
+		strscpy(hi->data.modename, bc->options ? "par96" : "picpar");
 		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
@@ -439,7 +439,7 @@ static int baycom_ioctl(struct net_device *dev, void __user *data,
 		return baycom_setmode(bc, hi->data.modename);
 
 	case HDLCDRVCTL_MODELIST:
-		strcpy(hi->data.modename, "par96,picpar");
+		strscpy(hi->data.modename, "par96,picpar");
 		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
diff --git a/drivers/net/hamradio/baycom_ser_fdx.c b/drivers/net/hamradio/baycom_ser_fdx.c
index 799f8ece7824f..ee5bd3c120400 100644
--- a/drivers/net/hamradio/baycom_ser_fdx.c
+++ b/drivers/net/hamradio/baycom_ser_fdx.c
@@ -531,7 +531,7 @@ static int baycom_ioctl(struct net_device *dev, void __user *data,
 		return baycom_setmode(bc, hi->data.modename);
 
 	case HDLCDRVCTL_MODELIST:
-		strcpy(hi->data.modename, "ser12,ser3,ser24");
+		strscpy(hi->data.modename, "ser12,ser3,ser24");
 		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;
diff --git a/drivers/net/hamradio/baycom_ser_hdx.c b/drivers/net/hamradio/baycom_ser_hdx.c
index 5d1ab4840753f..05bdad2147999 100644
--- a/drivers/net/hamradio/baycom_ser_hdx.c
+++ b/drivers/net/hamradio/baycom_ser_hdx.c
@@ -570,7 +570,7 @@ static int baycom_ioctl(struct net_device *dev, void __user *data,
 		break;
 
 	case HDLCDRVCTL_GETMODE:
-		strcpy(hi->data.modename, "ser12");
+		strscpy(hi->data.modename, "ser12");
 		if (bc->opt_dcd <= 0)
 			strcat(hi->data.modename, (!bc->opt_dcd) ? "*" : (bc->opt_dcd == -2) ? "@" : "+");
 		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
@@ -584,7 +584,7 @@ static int baycom_ioctl(struct net_device *dev, void __user *data,
 		return baycom_setmode(bc, hi->data.modename);
 
 	case HDLCDRVCTL_MODELIST:
-		strcpy(hi->data.modename, "ser12");
+		strscpy(hi->data.modename, "ser12");
 		if (copy_to_user(data, hi, sizeof(struct hdlcdrv_ioctl)))
 			return -EFAULT;
 		return 0;

From 16d11fdaeb22715d8b55b08890173ffa2326baee Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 9 Feb 2025 13:12:44 +0100
Subject: [PATCH 0461/2753] net: phy: remove unused PHY_INIT_TIMEOUT and
 PHY_FORCE_TIMEOUT

Both definitions are unused. Last users have been removed with:

f3ba9d490d6e ("net: s6gmac: remove driver")
2bd229df5e2e ("net: phy: remove state PHY_FORCING")

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/f8e7b8ed-a665-41ad-b0ce-cbfdb65262ef@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 29df4c6025898..83994b394d8e3 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -303,9 +303,6 @@ static inline long rgmii_clock(int speed)
 	}
 }
 
-#define PHY_INIT_TIMEOUT	100000
-#define PHY_FORCE_TIMEOUT	10
-
 #define PHY_MAX_ADDR	32
 
 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */

From 8729a9bd6efcf96d3bb0468dfa2168a78fa89cc5 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 9 Feb 2025 13:27:44 +0100
Subject: [PATCH 0462/2753] net: freescale: ucc_geth: remove unused
 PHY_INIT_TIMEOUT and PHY_CHANGE_TIME

Both definitions are unused. Last users have been removed with:

1577ecef7666 ("netdev: Merge UCC and gianfar MDIO bus drivers")
728de4c927a3 ("ucc_geth: migrate ucc_geth to phylib")

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/62e9429b-57e0-42ec-96a5-6a89553f441d@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/ucc_geth.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.h b/drivers/net/ethernet/freescale/ucc_geth.h
index 38789faae706b..84f92f6384e70 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.h
+++ b/drivers/net/ethernet/freescale/ucc_geth.h
@@ -890,8 +890,6 @@ struct ucc_geth_hardware_statistics {
 							   addresses */
 
 #define TX_TIMEOUT                              (1*HZ)
-#define PHY_INIT_TIMEOUT                        100000
-#define PHY_CHANGE_TIME                         2
 
 /* Fast Ethernet (10/100 Mbps) */
 #define UCC_GETH_URFS_INIT                      512	/* Rx virtual FIFO size

From ad30ee8013881907082e127e88504686ea15cac4 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 10 Feb 2025 12:36:59 +0100
Subject: [PATCH 0463/2753] net: phy: broadcom: don't include
 '<linux/pm_wakeup.h>' directly

The header clearly states that it does not want to be included directly,
only via '<linux/(platform_)?device.h>'. Replace the include accordingly.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250210113658.52019-2-wsa+renesas@sang-engineering.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/broadcom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 22edb7e4c1a1f..13e43fee1906e 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -16,7 +16,7 @@
 #include <linux/delay.h>
 #include <linux/module.h>
 #include <linux/phy.h>
-#include <linux/pm_wakeup.h>
+#include <linux/device.h>
 #include <linux/brcmphy.h>
 #include <linux/of.h>
 #include <linux/interrupt.h>

From 4d3f687e2432e4f40e0e21b65c965bcbb98d3951 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 10 Feb 2025 12:37:11 +0100
Subject: [PATCH 0464/2753] net: wwan: t7xx: don't include
 '<linux/pm_wakeup.h>' directly

The header clearly states that it does not want to be included directly,
only via '<linux/(platform_)?device.h>'. Which is already present, so
delete the superfluous include.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Acked-by: Sergey Ryazanov <ryazanov.s.a@gmail.com>
Link: https://patch.msgid.link/20250210113710.52071-2-wsa+renesas@sang-engineering.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/wwan/t7xx/t7xx_pci.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wwan/t7xx/t7xx_pci.c b/drivers/net/wwan/t7xx/t7xx_pci.c
index 02f2ec7cf4cee..8bf63f2dcbbfd 100644
--- a/drivers/net/wwan/t7xx/t7xx_pci.c
+++ b/drivers/net/wwan/t7xx/t7xx_pci.c
@@ -32,7 +32,6 @@
 #include <linux/pci.h>
 #include <linux/pm.h>
 #include <linux/pm_runtime.h>
-#include <linux/pm_wakeup.h>
 #include <linux/spinlock.h>
 
 #include "t7xx_mhccif.h"

From 43a0d7f26ad795d43bb1fffcf993170d0a69a045 Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Mon, 10 Feb 2025 13:47:06 +0800
Subject: [PATCH 0465/2753] net: aquantia: Use HWMON_CHANNEL_INFO macro to
 simplify code

Use HWMON_CHANNEL_INFO macro to simplify code.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://patch.msgid.link/20250210054710.12855-2-lihuisong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/aquantia/atlantic/aq_drvinfo.c    | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
index 414b2e448d593..787ea91802e75 100644
--- a/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
+++ b/drivers/net/ethernet/aquantia/atlantic/aq_drvinfo.c
@@ -113,19 +113,9 @@ static const struct hwmon_ops aq_hwmon_ops = {
 	.read_string = aq_hwmon_read_string,
 };
 
-static u32 aq_hwmon_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	HWMON_T_INPUT | HWMON_T_LABEL,
-	0,
-};
-
-static const struct hwmon_channel_info aq_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = aq_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const aq_hwmon_info[] = {
-	&aq_hwmon_temp,
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_LABEL,
+			   HWMON_T_INPUT | HWMON_T_LABEL),
 	NULL,
 };
 

From e05427c4d1380c326ee022d506679ab38a24213c Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Mon, 10 Feb 2025 13:47:07 +0800
Subject: [PATCH 0466/2753] net: nfp: Use HWMON_CHANNEL_INFO macro to simplify
 code

Use HWMON_CHANNEL_INFO macro to simplify code.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://patch.msgid.link/20250210054710.12855-3-lihuisong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/netronome/nfp/nfp_hwmon.c    | 40 +++----------------
 1 file changed, 5 insertions(+), 35 deletions(-)

diff --git a/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c b/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
index 0d6c59d6d4aed..ea6a288c0d5ed 100644
--- a/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
+++ b/drivers/net/ethernet/netronome/nfp/nfp_hwmon.c
@@ -83,42 +83,12 @@ nfp_hwmon_is_visible(const void *data, enum hwmon_sensor_types type, u32 attr,
 	return 0;
 }
 
-static u32 nfp_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info nfp_chip = {
-	.type = hwmon_chip,
-	.config = nfp_chip_config,
-};
-
-static u32 nfp_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT,
-	0
-};
-
-static const struct hwmon_channel_info nfp_temp = {
-	.type = hwmon_temp,
-	.config = nfp_temp_config,
-};
-
-static u32 nfp_power_config[] = {
-	HWMON_P_INPUT | HWMON_P_MAX,
-	HWMON_P_INPUT,
-	HWMON_P_INPUT,
-	0
-};
-
-static const struct hwmon_channel_info nfp_power = {
-	.type = hwmon_power,
-	.config = nfp_power_config,
-};
-
 static const struct hwmon_channel_info * const nfp_hwmon_info[] = {
-	&nfp_chip,
-	&nfp_temp,
-	&nfp_power,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_MAX | HWMON_T_CRIT),
+	HWMON_CHANNEL_INFO(power, HWMON_P_INPUT | HWMON_P_MAX,
+			   HWMON_P_INPUT,
+			   HWMON_P_INPUT),
 	NULL
 };
 

From 0cb595e80edca7cc4cb149f6d2a9de78eb8600ba Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Mon, 10 Feb 2025 13:47:08 +0800
Subject: [PATCH 0467/2753] net: phy: marvell: Use HWMON_CHANNEL_INFO macro to
 simplify code

Use HWMON_CHANNEL_INFO macro to simplify code.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://patch.msgid.link/20250210054710.12855-4-lihuisong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/marvell.c | 24 ++----------------------
 1 file changed, 2 insertions(+), 22 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index 44e1927de4997..dd254e36ca8ae 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -3124,33 +3124,13 @@ static umode_t marvell_hwmon_is_visible(const void *data,
 	}
 }
 
-static u32 marvell_hwmon_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0
-};
-
-static const struct hwmon_channel_info marvell_hwmon_chip = {
-	.type = hwmon_chip,
-	.config = marvell_hwmon_chip_config,
-};
-
 /* we can define HWMON_T_CRIT and HWMON_T_MAX_ALARM even though these are not
  * defined for all PHYs, because the hwmon code checks whether the attributes
  * exists via the .is_visible method
  */
-static u32 marvell_hwmon_temp_config[] = {
-	HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_MAX_ALARM,
-	0
-};
-
-static const struct hwmon_channel_info marvell_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = marvell_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const marvell_hwmon_info[] = {
-	&marvell_hwmon_chip,
-	&marvell_hwmon_temp,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT | HWMON_T_CRIT | HWMON_T_MAX_ALARM),
 	NULL
 };
 

From 4798f4834b2e6a32c75908831ee0262941b70de1 Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Mon, 10 Feb 2025 13:47:09 +0800
Subject: [PATCH 0468/2753] net: phy: marvell10g: Use HWMON_CHANNEL_INFO macro
 to simplify code

Use HWMON_CHANNEL_INFO macro to simplify code.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://patch.msgid.link/20250210054710.12855-5-lihuisong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/marvell10g.c | 24 ++----------------------
 1 file changed, 2 insertions(+), 22 deletions(-)

diff --git a/drivers/net/phy/marvell10g.c b/drivers/net/phy/marvell10g.c
index 623bdb8466b86..5354c8895163a 100644
--- a/drivers/net/phy/marvell10g.c
+++ b/drivers/net/phy/marvell10g.c
@@ -230,29 +230,9 @@ static const struct hwmon_ops mv3310_hwmon_ops = {
 	.read = mv3310_hwmon_read,
 };
 
-static u32 mv3310_hwmon_chip_config[] = {
-	HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL,
-	0,
-};
-
-static const struct hwmon_channel_info mv3310_hwmon_chip = {
-	.type = hwmon_chip,
-	.config = mv3310_hwmon_chip_config,
-};
-
-static u32 mv3310_hwmon_temp_config[] = {
-	HWMON_T_INPUT,
-	0,
-};
-
-static const struct hwmon_channel_info mv3310_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = mv3310_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const mv3310_hwmon_info[] = {
-	&mv3310_hwmon_chip,
-	&mv3310_hwmon_temp,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ | HWMON_C_UPDATE_INTERVAL),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
 	NULL,
 };
 

From d6085a23b3b41d379b84a5beb208c7f404c02fdd Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Mon, 10 Feb 2025 13:47:10 +0800
Subject: [PATCH 0469/2753] net: phy: aquantia: Use HWMON_CHANNEL_INFO macro to
 simplify code

Use HWMON_CHANNEL_INFO macro to simplify code.

Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://patch.msgid.link/20250210054710.12855-6-lihuisong@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/aquantia/aquantia_hwmon.c | 32 +++++------------------
 1 file changed, 6 insertions(+), 26 deletions(-)

diff --git a/drivers/net/phy/aquantia/aquantia_hwmon.c b/drivers/net/phy/aquantia/aquantia_hwmon.c
index 7b3c49c3bf49b..1a714b56b765a 100644
--- a/drivers/net/phy/aquantia/aquantia_hwmon.c
+++ b/drivers/net/phy/aquantia/aquantia_hwmon.c
@@ -172,33 +172,13 @@ static const struct hwmon_ops aqr_hwmon_ops = {
 	.write = aqr_hwmon_write,
 };
 
-static u32 aqr_hwmon_chip_config[] = {
-	HWMON_C_REGISTER_TZ,
-	0,
-};
-
-static const struct hwmon_channel_info aqr_hwmon_chip = {
-	.type = hwmon_chip,
-	.config = aqr_hwmon_chip_config,
-};
-
-static u32 aqr_hwmon_temp_config[] = {
-	HWMON_T_INPUT |
-	HWMON_T_MAX | HWMON_T_MIN |
-	HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM |
-	HWMON_T_CRIT | HWMON_T_LCRIT |
-	HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM,
-	0,
-};
-
-static const struct hwmon_channel_info aqr_hwmon_temp = {
-	.type = hwmon_temp,
-	.config = aqr_hwmon_temp_config,
-};
-
 static const struct hwmon_channel_info * const aqr_hwmon_info[] = {
-	&aqr_hwmon_chip,
-	&aqr_hwmon_temp,
+	HWMON_CHANNEL_INFO(chip, HWMON_C_REGISTER_TZ),
+	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT |
+			   HWMON_T_MAX | HWMON_T_MIN |
+			   HWMON_T_MAX_ALARM | HWMON_T_MIN_ALARM |
+			   HWMON_T_CRIT | HWMON_T_LCRIT |
+			   HWMON_T_CRIT_ALARM | HWMON_T_LCRIT_ALARM),
 	NULL,
 };
 

From fd118a77ede759baf1c815a0a6e288315425e92b Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 10 Feb 2025 11:25:42 +0000
Subject: [PATCH 0470/2753] sfc: parse headers of devlink flash images

This parsing is necessary to obtain the metadata which will be
 used in a subsequent patch to write the image to the device.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/65318300f3f1b1462925f917f7c0d0ac833955ae.1739186253.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/Makefile      |   2 +-
 drivers/net/ethernet/sfc/efx_devlink.c |  13 ++
 drivers/net/ethernet/sfc/efx_reflash.c | 289 +++++++++++++++++++++++++
 drivers/net/ethernet/sfc/efx_reflash.h |  20 ++
 drivers/net/ethernet/sfc/fw_formats.h  | 114 ++++++++++
 5 files changed, 437 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/sfc/efx_reflash.c
 create mode 100644 drivers/net/ethernet/sfc/efx_reflash.h
 create mode 100644 drivers/net/ethernet/sfc/fw_formats.h

diff --git a/drivers/net/ethernet/sfc/Makefile b/drivers/net/ethernet/sfc/Makefile
index 8f446b9bd5ee3..d99039ec468d6 100644
--- a/drivers/net/ethernet/sfc/Makefile
+++ b/drivers/net/ethernet/sfc/Makefile
@@ -7,7 +7,7 @@ sfc-y			+= efx.o efx_common.o efx_channels.o nic.o \
 			   mcdi_functions.o mcdi_filters.o mcdi_mon.o \
 			   ef100.o ef100_nic.o ef100_netdev.o \
 			   ef100_ethtool.o ef100_rx.o ef100_tx.o \
-			   efx_devlink.o
+			   efx_devlink.o efx_reflash.o
 sfc-$(CONFIG_SFC_MTD)	+= mtd.o
 sfc-$(CONFIG_SFC_SRIOV)	+= sriov.o ef10_sriov.o ef100_sriov.o ef100_rep.o \
                            mae.o tc.o tc_bindings.o tc_counters.o \
diff --git a/drivers/net/ethernet/sfc/efx_devlink.c b/drivers/net/ethernet/sfc/efx_devlink.c
index 3cd750820fdde..d842c60dfc100 100644
--- a/drivers/net/ethernet/sfc/efx_devlink.c
+++ b/drivers/net/ethernet/sfc/efx_devlink.c
@@ -19,6 +19,7 @@
 #include "mae.h"
 #include "ef100_rep.h"
 #endif
+#include "efx_reflash.h"
 
 struct efx_devlink {
 	struct efx_nic *efx;
@@ -615,7 +616,19 @@ static int efx_devlink_info_get(struct devlink *devlink,
 	return 0;
 }
 
+static int efx_devlink_flash_update(struct devlink *devlink,
+				    struct devlink_flash_update_params *params,
+				    struct netlink_ext_ack *extack)
+{
+	struct efx_devlink *devlink_private = devlink_priv(devlink);
+	struct efx_nic *efx = devlink_private->efx;
+
+	return efx_reflash_flash_firmware(efx, params->fw, extack);
+}
+
 static const struct devlink_ops sfc_devlink_ops = {
+	.supported_flash_update_params	= 0,
+	.flash_update			= efx_devlink_flash_update,
 	.info_get			= efx_devlink_info_get,
 };
 
diff --git a/drivers/net/ethernet/sfc/efx_reflash.c b/drivers/net/ethernet/sfc/efx_reflash.c
new file mode 100644
index 0000000000000..9a8d8211e18b9
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_reflash.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#include <linux/crc32.h>
+#include <net/devlink.h>
+#include "efx_reflash.h"
+#include "net_driver.h"
+#include "fw_formats.h"
+#include "mcdi_pcol.h"
+#include "mcdi.h"
+
+/* Try to parse a Reflash header at the specified offset */
+static bool efx_reflash_parse_reflash_header(const struct firmware *fw,
+					     size_t header_offset, u32 *type,
+					     u32 *subtype, const u8 **data,
+					     size_t *data_size)
+{
+	size_t header_end, trailer_offset, trailer_end;
+	u32 magic, version, payload_size, header_len;
+	const u8 *header, *trailer;
+	u32 expected_crc, crc;
+
+	if (check_add_overflow(header_offset, EFX_REFLASH_HEADER_LENGTH_OFST +
+					      EFX_REFLASH_HEADER_LENGTH_LEN,
+			       &header_end))
+		return false;
+	if (fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_REFLASH_HEADER_MAGIC_OFST);
+	if (magic != EFX_REFLASH_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_REFLASH_HEADER_VERSION_OFST);
+	if (version != EFX_REFLASH_HEADER_VERSION_VALUE)
+		return false;
+
+	payload_size = get_unaligned_le32(header + EFX_REFLASH_HEADER_PAYLOAD_SIZE_OFST);
+	header_len = get_unaligned_le32(header + EFX_REFLASH_HEADER_LENGTH_OFST);
+	if (check_add_overflow(header_offset, header_len, &trailer_offset) ||
+	    check_add_overflow(trailer_offset, payload_size, &trailer_offset) ||
+	    check_add_overflow(trailer_offset, EFX_REFLASH_TRAILER_LEN,
+			       &trailer_end))
+		return false;
+	if (fw->size < trailer_end)
+		return false;
+
+	trailer = fw->data + trailer_offset;
+	expected_crc = get_unaligned_le32(trailer + EFX_REFLASH_TRAILER_CRC_OFST);
+	/* Addition could overflow u32, but not size_t since we already
+	 * checked trailer_offset didn't overflow.  So cast to size_t first.
+	 */
+	crc = crc32_le(0, header, (size_t)header_len + payload_size);
+	if (crc != expected_crc)
+		return false;
+
+	*type = get_unaligned_le32(header + EFX_REFLASH_HEADER_FIRMWARE_TYPE_OFST);
+	*subtype = get_unaligned_le32(header + EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_OFST);
+	if (*type == EFX_REFLASH_FIRMWARE_TYPE_BUNDLE) {
+		/* All the bundle data is written verbatim to NVRAM */
+		*data = fw->data;
+		*data_size = fw->size;
+	} else {
+		/* Other payload types strip the reflash header and trailer
+		 * from the data written to NVRAM
+		 */
+		*data = header + header_len;
+		*data_size = payload_size;
+	}
+
+	return true;
+}
+
+/* Map from FIRMWARE_TYPE to NVRAM_PARTITION_TYPE */
+static int efx_reflash_partition_type(u32 type, u32 subtype,
+				      u32 *partition_type,
+				      u32 *partition_subtype)
+{
+	int rc = 0;
+
+	switch (type) {
+	case EFX_REFLASH_FIRMWARE_TYPE_BOOTROM:
+		*partition_type = NVRAM_PARTITION_TYPE_EXPANSION_ROM;
+		*partition_subtype = subtype;
+		break;
+	case EFX_REFLASH_FIRMWARE_TYPE_BUNDLE:
+		*partition_type = NVRAM_PARTITION_TYPE_BUNDLE;
+		*partition_subtype = subtype;
+		break;
+	default:
+		/* Not supported */
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+/* Try to parse a SmartNIC image header at the specified offset */
+static bool efx_reflash_parse_snic_header(const struct firmware *fw,
+					  size_t header_offset,
+					  u32 *partition_type,
+					  u32 *partition_subtype,
+					  const u8 **data, size_t *data_size)
+{
+	u32 magic, version, payload_size, header_len, expected_crc, crc;
+	size_t header_end, payload_end;
+	const u8 *header;
+
+	if (check_add_overflow(header_offset, EFX_SNICIMAGE_HEADER_MINLEN,
+			       &header_end) ||
+	    fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_MAGIC_OFST);
+	if (magic != EFX_SNICIMAGE_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_VERSION_OFST);
+	if (version != EFX_SNICIMAGE_HEADER_VERSION_VALUE)
+		return false;
+
+	header_len = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_LENGTH_OFST);
+	if (check_add_overflow(header_offset, header_len, &header_end))
+		return false;
+	payload_size = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_OFST);
+	if (check_add_overflow(header_end, payload_size, &payload_end) ||
+	    fw->size < payload_end)
+		return false;
+
+	expected_crc = get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_CRC_OFST);
+
+	/* Calculate CRC omitting the expected CRC field itself */
+	crc = crc32_le(~0, header, EFX_SNICIMAGE_HEADER_CRC_OFST);
+	crc = ~crc32_le(crc,
+			header + EFX_SNICIMAGE_HEADER_CRC_OFST +
+			EFX_SNICIMAGE_HEADER_CRC_LEN,
+			header_len + payload_size - EFX_SNICIMAGE_HEADER_CRC_OFST -
+			EFX_SNICIMAGE_HEADER_CRC_LEN);
+	if (crc != expected_crc)
+		return false;
+
+	*partition_type =
+		get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PARTITION_TYPE_OFST);
+	*partition_subtype =
+		get_unaligned_le32(header + EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_OFST);
+	*data = fw->data;
+	*data_size = fw->size;
+	return true;
+}
+
+/* Try to parse a SmartNIC bundle header at the specified offset */
+static bool efx_reflash_parse_snic_bundle_header(const struct firmware *fw,
+						 size_t header_offset,
+						 u32 *partition_type,
+						 u32 *partition_subtype,
+						 const u8 **data,
+						 size_t *data_size)
+{
+	u32 magic, version, bundle_type, header_len, expected_crc, crc;
+	size_t header_end;
+	const u8 *header;
+
+	if (check_add_overflow(header_offset, EFX_SNICBUNDLE_HEADER_LEN,
+			       &header_end))
+		return false;
+	if (fw->size < header_end)
+		return false;
+
+	header = fw->data + header_offset;
+	magic = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_MAGIC_OFST);
+	if (magic != EFX_SNICBUNDLE_HEADER_MAGIC_VALUE)
+		return false;
+
+	version = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_VERSION_OFST);
+	if (version != EFX_SNICBUNDLE_HEADER_VERSION_VALUE)
+		return false;
+
+	bundle_type = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_OFST);
+	if (bundle_type != NVRAM_PARTITION_TYPE_BUNDLE)
+		return false;
+
+	header_len = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_LENGTH_OFST);
+	if (header_len != EFX_SNICBUNDLE_HEADER_LEN)
+		return false;
+
+	expected_crc = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_CRC_OFST);
+	crc = ~crc32_le(~0, header, EFX_SNICBUNDLE_HEADER_CRC_OFST);
+	if (crc != expected_crc)
+		return false;
+
+	*partition_type = NVRAM_PARTITION_TYPE_BUNDLE;
+	*partition_subtype = get_unaligned_le32(header + EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_OFST);
+	*data = fw->data;
+	*data_size = fw->size;
+	return true;
+}
+
+/* Try to find a valid firmware payload in the firmware data.
+ * When we recognise a valid header, we parse it for the partition type
+ * (so we know where to ask the MC to write it to) and the location of
+ * the data blob to write.
+ */
+static int efx_reflash_parse_firmware_data(const struct firmware *fw,
+					   u32 *partition_type,
+					   u32 *partition_subtype,
+					   const u8 **data, size_t *data_size)
+{
+	size_t header_offset;
+	u32 type, subtype;
+
+	/* Some packaging formats (such as CMS/PKCS#7 signed images)
+	 * prepend a header for which finding the size is a non-trivial
+	 * task, so step through the firmware data until we find a valid
+	 * header.
+	 *
+	 * The checks are intended to reject firmware data that is clearly not
+	 * in the expected format.  They do not need to be exhaustive as the
+	 * running firmware will perform its own comprehensive validity and
+	 * compatibility checks during the update procedure.
+	 *
+	 * Firmware packages may contain multiple reflash images, e.g. a
+	 * bundle containing one or more other images.  Only check the
+	 * outermost container by stopping after the first candidate image
+	 * found even it is for an unsupported partition type.
+	 */
+	for (header_offset = 0; header_offset < fw->size; header_offset++) {
+		if (efx_reflash_parse_snic_bundle_header(fw, header_offset,
+							 partition_type,
+							 partition_subtype,
+							 data, data_size))
+			return 0;
+
+		if (efx_reflash_parse_snic_header(fw, header_offset,
+						  partition_type,
+						  partition_subtype, data,
+						  data_size))
+			return 0;
+
+		if (efx_reflash_parse_reflash_header(fw, header_offset, &type,
+						     &subtype, data, data_size))
+			return efx_reflash_partition_type(type, subtype,
+							  partition_type,
+							  partition_subtype);
+	}
+
+	return -EINVAL;
+}
+
+int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
+			       struct netlink_ext_ack *extack)
+{
+	struct devlink *devlink = efx->devlink;
+	u32 type, data_subtype;
+	size_t data_size;
+	const u8 *data;
+	int rc;
+
+	if (!efx_has_cap(efx, BUNDLE_UPDATE)) {
+		NL_SET_ERR_MSG_MOD(extack, "NVRAM bundle updates are not supported by the firmware");
+		return -EOPNOTSUPP;
+	}
+
+	devlink_flash_update_status_notify(devlink, "Checking update", NULL, 0, 0);
+
+	rc = efx_reflash_parse_firmware_data(fw, &type, &data_subtype, &data,
+					     &data_size);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware image validation check failed");
+		goto out;
+	}
+
+	rc = -EOPNOTSUPP;
+
+out:
+	devlink_flash_update_status_notify(devlink, rc ? "Update failed" :
+							 "Update complete",
+					   NULL, 0, 0);
+	return rc;
+}
diff --git a/drivers/net/ethernet/sfc/efx_reflash.h b/drivers/net/ethernet/sfc/efx_reflash.h
new file mode 100644
index 0000000000000..3dffac5651615
--- /dev/null
+++ b/drivers/net/ethernet/sfc/efx_reflash.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef _EFX_REFLASH_H
+#define _EFX_REFLASH_H
+
+#include "net_driver.h"
+#include <linux/firmware.h>
+
+int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
+			       struct netlink_ext_ack *extack);
+
+#endif /* _EFX_REFLASH_H */
diff --git a/drivers/net/ethernet/sfc/fw_formats.h b/drivers/net/ethernet/sfc/fw_formats.h
new file mode 100644
index 0000000000000..cbc350c960133
--- /dev/null
+++ b/drivers/net/ethernet/sfc/fw_formats.h
@@ -0,0 +1,114 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/****************************************************************************
+ * Driver for AMD network controllers and boards
+ * Copyright (C) 2025, Advanced Micro Devices, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation, incorporated herein by reference.
+ */
+
+#ifndef _EFX_FW_FORMATS_H
+#define _EFX_FW_FORMATS_H
+
+/* Header layouts of firmware update images recognised by Efx NICs.
+ * The sources-of-truth for these layouts are AMD internal documents
+ * and sfregistry headers, neither of which are available externally
+ * nor usable directly by the driver.
+ *
+ * While each format includes a 'magic number', these are at different
+ * offsets in the various formats, and a legal header for one format
+ * could have the right value in whichever field occupies that offset
+ * to match another format's magic.
+ * Besides, some packaging formats (such as CMS/PKCS#7 signed images)
+ * prepend a header for which finding the size is a non-trivial task;
+ * rather than trying to parse those headers, we search byte-by-byte
+ * through the provided firmware image looking for a valid header.
+ * Thus, format recognition has to include validation of the checksum
+ * field, even though the firmware will validate that itself before
+ * applying the image.
+ */
+
+/* EF10 (Medford2, X2) "reflash" header format.  Defined in SF-121352-AN */
+#define EFX_REFLASH_HEADER_MAGIC_OFST 0
+#define EFX_REFLASH_HEADER_MAGIC_LEN 4
+#define EFX_REFLASH_HEADER_MAGIC_VALUE 0x106F1A5
+
+#define EFX_REFLASH_HEADER_VERSION_OFST 4
+#define EFX_REFLASH_HEADER_VERSION_LEN 4
+#define EFX_REFLASH_HEADER_VERSION_VALUE 4
+
+#define EFX_REFLASH_HEADER_FIRMWARE_TYPE_OFST 8
+#define EFX_REFLASH_HEADER_FIRMWARE_TYPE_LEN 4
+#define EFX_REFLASH_FIRMWARE_TYPE_BOOTROM 0x2
+#define EFX_REFLASH_FIRMWARE_TYPE_BUNDLE 0xd
+
+#define EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_OFST 12
+#define EFX_REFLASH_HEADER_FIRMWARE_SUBTYPE_LEN 4
+
+#define EFX_REFLASH_HEADER_PAYLOAD_SIZE_OFST 16
+#define EFX_REFLASH_HEADER_PAYLOAD_SIZE_LEN 4
+
+#define EFX_REFLASH_HEADER_LENGTH_OFST 20
+#define EFX_REFLASH_HEADER_LENGTH_LEN 4
+
+/* Reflash trailer */
+#define EFX_REFLASH_TRAILER_CRC_OFST 0
+#define EFX_REFLASH_TRAILER_CRC_LEN 4
+
+#define EFX_REFLASH_TRAILER_LEN	\
+	(EFX_REFLASH_TRAILER_CRC_OFST + EFX_REFLASH_TRAILER_CRC_LEN)
+
+/* EF100 "SmartNIC image" header format.
+ * Defined in sfregistry "src/layout/snic_image_hdr.h".
+ */
+#define EFX_SNICIMAGE_HEADER_MAGIC_OFST 16
+#define EFX_SNICIMAGE_HEADER_MAGIC_LEN 4
+#define EFX_SNICIMAGE_HEADER_MAGIC_VALUE 0x541C057A
+
+#define EFX_SNICIMAGE_HEADER_VERSION_OFST 20
+#define EFX_SNICIMAGE_HEADER_VERSION_LEN 4
+#define EFX_SNICIMAGE_HEADER_VERSION_VALUE 1
+
+#define EFX_SNICIMAGE_HEADER_LENGTH_OFST 24
+#define EFX_SNICIMAGE_HEADER_LENGTH_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PARTITION_TYPE_OFST 36
+#define EFX_SNICIMAGE_HEADER_PARTITION_TYPE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_OFST 40
+#define EFX_SNICIMAGE_HEADER_PARTITION_SUBTYPE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_OFST 60
+#define EFX_SNICIMAGE_HEADER_PAYLOAD_SIZE_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_CRC_OFST 64
+#define EFX_SNICIMAGE_HEADER_CRC_LEN 4
+
+#define EFX_SNICIMAGE_HEADER_MINLEN 256
+
+/* EF100 "SmartNIC bundle" header format.  Defined in SF-122606-TC */
+#define EFX_SNICBUNDLE_HEADER_MAGIC_OFST 0
+#define EFX_SNICBUNDLE_HEADER_MAGIC_LEN 4
+#define EFX_SNICBUNDLE_HEADER_MAGIC_VALUE 0xB1001001
+
+#define EFX_SNICBUNDLE_HEADER_VERSION_OFST 4
+#define EFX_SNICBUNDLE_HEADER_VERSION_LEN 4
+#define EFX_SNICBUNDLE_HEADER_VERSION_VALUE 1
+
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_OFST 8
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_TYPE_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_OFST 12
+#define EFX_SNICBUNDLE_HEADER_BUNDLE_SUBTYPE_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_LENGTH_OFST 20
+#define EFX_SNICBUNDLE_HEADER_LENGTH_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_CRC_OFST 224
+#define EFX_SNICBUNDLE_HEADER_CRC_LEN 4
+
+#define EFX_SNICBUNDLE_HEADER_LEN	\
+	(EFX_SNICBUNDLE_HEADER_CRC_OFST + EFX_SNICBUNDLE_HEADER_CRC_LEN)
+
+#endif /* _EFX_FW_FORMATS_H */

From d41987e906e75d4c97b3db23ce3caf7252a38eef Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 10 Feb 2025 11:25:43 +0000
Subject: [PATCH 0471/2753] sfc: extend NVRAM MCDI handlers

Support variable write-alignment, and background updates.  The latter
 allows other MCDI to continue while the device is processing an
 MC_CMD_NVRAM_UPDATE_FINISH, since this can take a long time owing to
 e.g. cryptographic signature verification.
Expose these handlers in mcdi.h, and build them even when
 CONFIG_SFC_MTD=n, so they can be used for devlink flash in a
 subsequent patch.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/de3d9e14fee69e15d95b46258401a93b75659f78.1739186253.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/ef10.c |   7 +-
 drivers/net/ethernet/sfc/mcdi.c | 115 ++++++++++++++++++++++++++------
 drivers/net/ethernet/sfc/mcdi.h |  22 +++++-
 3 files changed, 121 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 452009ed7a435..47d78abecf30d 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -3501,7 +3501,7 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_METADATA_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_METADATA_OUT_LENMAX);
 	const struct efx_ef10_nvram_type_info *info;
-	size_t size, erase_size, outlen;
+	size_t size, erase_size, write_size, outlen;
 	int type_idx = 0;
 	bool protected;
 	int rc;
@@ -3516,7 +3516,8 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	if (info->port != efx_port_num(efx))
 		return -ENODEV;
 
-	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &protected);
+	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_size, &write_size,
+				 &protected);
 	if (rc)
 		return rc;
 	if (protected &&
@@ -3561,6 +3562,8 @@ static int efx_ef10_mtd_probe_partition(struct efx_nic *efx,
 	if (!erase_size)
 		part->common.mtd.flags |= MTD_NO_ERASE;
 
+	part->common.mtd.writesize = write_size;
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c
index d461b1a6ce810..dbd2ee915838c 100644
--- a/drivers/net/ethernet/sfc/mcdi.c
+++ b/drivers/net/ethernet/sfc/mcdi.c
@@ -1625,12 +1625,15 @@ static int efx_new_mcdi_nvram_types(struct efx_nic *efx, u32 *number,
 	return rc;
 }
 
+#define EFX_MCDI_NVRAM_DEFAULT_WRITE_LEN 128
+
 int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 			size_t *size_out, size_t *erase_size_out,
-			bool *protected_out)
+			size_t *write_size_out, bool *protected_out)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_INFO_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_INFO_OUT_LEN);
+	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_INFO_V2_OUT_LEN);
+	size_t write_size = 0;
 	size_t outlen;
 	int rc;
 
@@ -1645,6 +1648,12 @@ int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 		goto fail;
 	}
 
+	if (outlen >= MC_CMD_NVRAM_INFO_V2_OUT_LEN)
+		write_size = MCDI_DWORD(outbuf, NVRAM_INFO_V2_OUT_WRITESIZE);
+	else
+		write_size = EFX_MCDI_NVRAM_DEFAULT_WRITE_LEN;
+
+	*write_size_out = write_size;
 	*size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_SIZE);
 	*erase_size_out = MCDI_DWORD(outbuf, NVRAM_INFO_OUT_ERASESIZE);
 	*protected_out = !!(MCDI_DWORD(outbuf, NVRAM_INFO_OUT_FLAGS) &
@@ -2163,11 +2172,9 @@ int efx_mcdi_nvram_metadata(struct efx_nic *efx, unsigned int type,
 	return rc;
 }
 
-#ifdef CONFIG_SFC_MTD
-
 #define EFX_MCDI_NVRAM_LEN_MAX 128
 
-static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
+int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_START_V2_IN_LEN);
 	int rc;
@@ -2185,6 +2192,8 @@ static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type)
 	return rc;
 }
 
+#ifdef CONFIG_SFC_MTD
+
 static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 			       loff_t offset, u8 *buffer, size_t length)
 {
@@ -2209,13 +2218,20 @@ static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type,
 	return 0;
 }
 
-static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
-				loff_t offset, const u8 *buffer, size_t length)
+#endif /* CONFIG_SFC_MTD */
+
+int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, const u8 *buffer, size_t length)
 {
-	MCDI_DECLARE_BUF(inbuf,
-			 MC_CMD_NVRAM_WRITE_IN_LEN(EFX_MCDI_NVRAM_LEN_MAX));
+	efx_dword_t *inbuf;
+	size_t inlen;
 	int rc;
 
+	inlen = ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4);
+	inbuf = kzalloc(inlen, GFP_KERNEL);
+	if (!inbuf)
+		return -ENOMEM;
+
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_TYPE, type);
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_OFFSET, offset);
 	MCDI_SET_DWORD(inbuf, NVRAM_WRITE_IN_LENGTH, length);
@@ -2223,14 +2239,14 @@ static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
 
 	BUILD_BUG_ON(MC_CMD_NVRAM_WRITE_OUT_LEN != 0);
 
-	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf,
-			  ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4),
-			  NULL, 0, NULL);
+	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf, inlen, NULL, 0, NULL);
+	kfree(inbuf);
+
 	return rc;
 }
 
-static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
-				loff_t offset, size_t length)
+int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type, loff_t offset,
+			 size_t length)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_ERASE_IN_LEN);
 	int rc;
@@ -2246,7 +2262,8 @@ static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
 	return rc;
 }
 
-static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
+int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type,
+				 enum efx_update_finish_mode mode)
 {
 	MCDI_DECLARE_BUF(inbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_IN_LEN);
 	MCDI_DECLARE_BUF(outbuf, MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN);
@@ -2254,22 +2271,41 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 	int rc, rc2;
 
 	MCDI_SET_DWORD(inbuf, NVRAM_UPDATE_FINISH_IN_TYPE, type);
-	/* Always set this flag. Old firmware ignores it */
-	MCDI_POPULATE_DWORD_1(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
+
+	/* Old firmware doesn't support background update finish and abort
+	 * operations. Fallback to waiting if the requested mode is not
+	 * supported.
+	 */
+	if (!efx_has_cap(efx, NVRAM_UPDATE_POLL_VERIFY_RESULT) ||
+	    (!efx_has_cap(efx, NVRAM_UPDATE_ABORT_SUPPORTED) &&
+	     mode == EFX_UPDATE_FINISH_ABORT))
+		mode = EFX_UPDATE_FINISH_WAIT;
+
+	MCDI_POPULATE_DWORD_4(inbuf, NVRAM_UPDATE_FINISH_V2_IN_FLAGS,
 			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_REPORT_VERIFY_RESULT,
-			      1);
+			      (mode != EFX_UPDATE_FINISH_ABORT),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_RUN_IN_BACKGROUND,
+			      (mode == EFX_UPDATE_FINISH_BACKGROUND),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_POLL_VERIFY_RESULT,
+			      (mode == EFX_UPDATE_FINISH_POLL),
+			      NVRAM_UPDATE_FINISH_V2_IN_FLAG_ABORT,
+			      (mode == EFX_UPDATE_FINISH_ABORT));
 
 	rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf),
 			  outbuf, sizeof(outbuf), &outlen);
 	if (!rc && outlen >= MC_CMD_NVRAM_UPDATE_FINISH_V2_OUT_LEN) {
 		rc2 = MCDI_DWORD(outbuf, NVRAM_UPDATE_FINISH_V2_OUT_RESULT_CODE);
-		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS)
+		if (rc2 != MC_CMD_NVRAM_VERIFY_RC_SUCCESS &&
+		    rc2 != MC_CMD_NVRAM_VERIFY_RC_PENDING)
 			netif_err(efx, drv, efx->net_dev,
 				  "NVRAM update failed verification with code 0x%x\n",
 				  rc2);
 		switch (rc2) {
 		case MC_CMD_NVRAM_VERIFY_RC_SUCCESS:
 			break;
+		case MC_CMD_NVRAM_VERIFY_RC_PENDING:
+			rc = -EAGAIN;
+			break;
 		case MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED:
 		case MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED:
 		case MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED:
@@ -2284,6 +2320,8 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 		case MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES:
 		case MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS:
 		case MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH:
+		case MC_CMD_NVRAM_VERIFY_RC_REJECT_TEST_SIGNED:
+		case MC_CMD_NVRAM_VERIFY_RC_SECURITY_LEVEL_DOWNGRADE:
 			rc = -EPERM;
 			break;
 		default:
@@ -2296,6 +2334,42 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type)
 	return rc;
 }
 
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_INITIAL_POLL_DELAY_MS 5
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_MAX_POLL_DELAY_MS 5000
+#define	EFX_MCDI_NVRAM_UPDATE_FINISH_RETRIES 185
+
+int efx_mcdi_nvram_update_finish_polled(struct efx_nic *efx, unsigned int type)
+{
+	unsigned int delay = EFX_MCDI_NVRAM_UPDATE_FINISH_INITIAL_POLL_DELAY_MS;
+	unsigned int retry = 0;
+	int rc;
+
+	/* NVRAM updates can take a long time (e.g. up to 1 minute for bundle
+	 * images). Polling for NVRAM update completion ensures that other MCDI
+	 * commands can be issued before the background NVRAM update completes.
+	 *
+	 * The initial call either completes the update synchronously, or
+	 * returns -EAGAIN to indicate processing is continuing. In the latter
+	 * case, we poll for at least 900 seconds, at increasing intervals
+	 * (5ms, 50ms, 500ms, 5s).
+	 */
+	rc = efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_BACKGROUND);
+	while (rc == -EAGAIN) {
+		if (retry > EFX_MCDI_NVRAM_UPDATE_FINISH_RETRIES)
+			return -ETIMEDOUT;
+		retry++;
+
+		msleep(delay);
+		if (delay < EFX_MCDI_NVRAM_UPDATE_FINISH_MAX_POLL_DELAY_MS)
+			delay *= 10;
+
+		rc = efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_POLL);
+	}
+	return rc;
+}
+
+#ifdef CONFIG_SFC_MTD
+
 int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start,
 		      size_t len, size_t *retlen, u8 *buffer)
 {
@@ -2389,7 +2463,8 @@ int efx_mcdi_mtd_sync(struct mtd_info *mtd)
 
 	if (part->updating) {
 		part->updating = false;
-		rc = efx_mcdi_nvram_update_finish(efx, part->nvram_type);
+		rc = efx_mcdi_nvram_update_finish(efx, part->nvram_type,
+						  EFX_UPDATE_FINISH_WAIT);
 	}
 
 	return rc;
diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h
index cdb17d7c147fc..3755cd3fe1e60 100644
--- a/drivers/net/ethernet/sfc/mcdi.h
+++ b/drivers/net/ethernet/sfc/mcdi.h
@@ -392,7 +392,7 @@ int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq);
 int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out);
 int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type,
 			size_t *size_out, size_t *erase_size_out,
-			bool *protected_out);
+			size_t *write_size_out, bool *protected_out);
 int efx_new_mcdi_nvram_test_all(struct efx_nic *efx);
 int efx_mcdi_nvram_metadata(struct efx_nic *efx, unsigned int type,
 			    u32 *subtype, u16 version[4], char *desc,
@@ -424,6 +424,26 @@ static inline int efx_mcdi_mon_probe(struct efx_nic *efx) { return 0; }
 static inline void efx_mcdi_mon_remove(struct efx_nic *efx) {}
 #endif
 
+int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type);
+int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, const u8 *buffer, size_t length);
+int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type,
+			 loff_t offset, size_t length);
+int efx_mcdi_nvram_metadata(struct efx_nic *efx, unsigned int type,
+			    u32 *subtype, u16 version[4], char *desc,
+			    size_t descsize);
+
+enum efx_update_finish_mode {
+	EFX_UPDATE_FINISH_WAIT,
+	EFX_UPDATE_FINISH_BACKGROUND,
+	EFX_UPDATE_FINISH_POLL,
+	EFX_UPDATE_FINISH_ABORT,
+};
+
+int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type,
+				 enum efx_update_finish_mode mode);
+int efx_mcdi_nvram_update_finish_polled(struct efx_nic *efx, unsigned int type);
+
 #ifdef CONFIG_SFC_MTD
 int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start, size_t len,
 		      size_t *retlen, u8 *buffer);

From 3ed63980ae7998b0a75d9f4e12918047d7493465 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 10 Feb 2025 11:25:44 +0000
Subject: [PATCH 0472/2753] sfc: deploy devlink flash images to NIC over MCDI

Use MC_CMD_NVRAM_* wrappers to write the firmware to the partition
 identified from the image header.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/a746335876b621b3e54cf4e49948148e349a1745.1739186253.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/efx_common.c  |   1 +
 drivers/net/ethernet/sfc/efx_reflash.c | 231 ++++++++++++++++++++++++-
 drivers/net/ethernet/sfc/net_driver.h  |   2 +
 3 files changed, 231 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/sfc/efx_common.c b/drivers/net/ethernet/sfc/efx_common.c
index c88ec3e248362..5a14d94163b19 100644
--- a/drivers/net/ethernet/sfc/efx_common.c
+++ b/drivers/net/ethernet/sfc/efx_common.c
@@ -1003,6 +1003,7 @@ int efx_init_struct(struct efx_nic *efx, struct pci_dev *pci_dev)
 	INIT_LIST_HEAD(&efx->vf_reps);
 	INIT_WORK(&efx->mac_work, efx_mac_work);
 	init_waitqueue_head(&efx->flush_wq);
+	mutex_init(&efx->reflash_mutex);
 
 	efx->tx_queues_per_channel = 1;
 	efx->rxq_entries = EFX_DEFAULT_DMAQ_SIZE;
diff --git a/drivers/net/ethernet/sfc/efx_reflash.c b/drivers/net/ethernet/sfc/efx_reflash.c
index 9a8d8211e18b9..ddc53740f0986 100644
--- a/drivers/net/ethernet/sfc/efx_reflash.c
+++ b/drivers/net/ethernet/sfc/efx_reflash.c
@@ -255,13 +255,151 @@ static int efx_reflash_parse_firmware_data(const struct firmware *fw,
 	return -EINVAL;
 }
 
+/* Limit the number of status updates during the erase or write phases */
+#define EFX_DEVLINK_STATUS_UPDATE_COUNT		50
+
+/* Expected timeout for the efx_mcdi_nvram_update_finish_polled() */
+#define EFX_DEVLINK_UPDATE_FINISH_TIMEOUT	900
+
+/* Ideal erase chunk size.  This is a balance between minimising the number of
+ * MCDI requests to erase an entire partition whilst avoiding tripping the MCDI
+ * RPC timeout.
+ */
+#define EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE	(64 * 1024)
+
+static int efx_reflash_erase_partition(struct efx_nic *efx,
+				       struct netlink_ext_ack *extack,
+				       struct devlink *devlink, u32 type,
+				       size_t partition_size,
+				       size_t align)
+{
+	size_t chunk, offset, next_update;
+	int rc;
+
+	/* Partitions that cannot be erased or do not require erase before
+	 * write are advertised with a erase alignment/sector size of zero.
+	 */
+	if (align == 0)
+		/* Nothing to do */
+		return 0;
+
+	if (partition_size % align)
+		return -EINVAL;
+
+	/* Erase the entire NVRAM partition a chunk at a time to avoid
+	 * potentially tripping the MCDI RPC timeout.
+	 */
+	if (align >= EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE)
+		chunk = align;
+	else
+		chunk = rounddown(EFX_NVRAM_ERASE_IDEAL_CHUNK_SIZE, align);
+
+	for (offset = 0, next_update = 0; offset < partition_size; offset += chunk) {
+		if (offset >= next_update) {
+			devlink_flash_update_status_notify(devlink, "Erasing",
+							   NULL, offset,
+							   partition_size);
+			next_update += partition_size / EFX_DEVLINK_STATUS_UPDATE_COUNT;
+		}
+
+		chunk = min_t(size_t, partition_size - offset, chunk);
+		rc = efx_mcdi_nvram_erase(efx, type, offset, chunk);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Erase failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	devlink_flash_update_status_notify(devlink, "Erasing", NULL,
+					   partition_size, partition_size);
+
+	return 0;
+}
+
+static int efx_reflash_write_partition(struct efx_nic *efx,
+				       struct netlink_ext_ack *extack,
+				       struct devlink *devlink, u32 type,
+				       const u8 *data, size_t data_size,
+				       size_t align)
+{
+	size_t write_max, chunk, offset, next_update;
+	int rc;
+
+	if (align == 0)
+		return -EINVAL;
+
+	/* Write the NVRAM partition in chunks that are the largest multiple
+	 * of the partition's required write alignment that will fit into the
+	 * MCDI NVRAM_WRITE RPC payload.
+	 */
+	if (efx->type->mcdi_max_ver < 2)
+		write_max = MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN *
+			    MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM;
+	else
+		write_max = MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_LEN *
+			    MC_CMD_NVRAM_WRITE_IN_WRITE_BUFFER_MAXNUM_MCDI2;
+	chunk = rounddown(write_max, align);
+
+	for (offset = 0, next_update = 0; offset + chunk <= data_size; offset += chunk) {
+		if (offset >= next_update) {
+			devlink_flash_update_status_notify(devlink, "Writing",
+							   NULL, offset,
+							   data_size);
+			next_update += data_size / EFX_DEVLINK_STATUS_UPDATE_COUNT;
+		}
+
+		rc = efx_mcdi_nvram_write(efx, type, offset, data + offset, chunk);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Write failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	/* Round up left over data to satisfy write alignment */
+	if (offset < data_size) {
+		size_t remaining = data_size - offset;
+		u8 *buf;
+
+		if (offset >= next_update)
+			devlink_flash_update_status_notify(devlink, "Writing",
+							   NULL, offset,
+							   data_size);
+
+		chunk = roundup(remaining, align);
+		buf = kmalloc(chunk, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+
+		memcpy(buf, data + offset, remaining);
+		memset(buf + remaining, 0xFF, chunk - remaining);
+		rc = efx_mcdi_nvram_write(efx, type, offset, buf, chunk);
+		kfree(buf);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Write failed for NVRAM partition %#x at %#zx-%#zx",
+					       type, offset, offset + chunk - 1);
+			return rc;
+		}
+	}
+
+	devlink_flash_update_status_notify(devlink, "Writing", NULL, data_size,
+					   data_size);
+
+	return 0;
+}
+
 int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
 			       struct netlink_ext_ack *extack)
 {
+	size_t data_size, size, erase_align, write_align;
 	struct devlink *devlink = efx->devlink;
-	u32 type, data_subtype;
-	size_t data_size;
+	u32 type, data_subtype, subtype;
 	const u8 *data;
+	bool protected;
 	int rc;
 
 	if (!efx_has_cap(efx, BUNDLE_UPDATE)) {
@@ -279,8 +417,95 @@ int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
 		goto out;
 	}
 
-	rc = -EOPNOTSUPP;
+	mutex_lock(&efx->reflash_mutex);
+
+	rc = efx_mcdi_nvram_metadata(efx, type, &subtype, NULL, NULL, 0);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Metadata query for NVRAM partition %#x failed",
+				       type);
+		goto out_unlock;
+	}
+
+	if (subtype != data_subtype) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Firmware image is not appropriate for this adapter");
+		rc = -EINVAL;
+		goto out_unlock;
+	}
+
+	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_align, &write_align,
+				 &protected);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Info query for NVRAM partition %#x failed",
+				       type);
+		goto out_unlock;
+	}
+
+	if (protected) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x is protected",
+				       type);
+		rc = -EPERM;
+		goto out_unlock;
+	}
+
+	if (write_align == 0) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x is not writable",
+				       type);
+		rc = -EACCES;
+		goto out_unlock;
+	}
+
+	if (erase_align != 0 && size % erase_align) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "NVRAM partition %#x has a bad partition table entry, can't erase it",
+				       type);
+		rc = -EACCES;
+		goto out_unlock;
+	}
+
+	if (data_size > size) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Firmware image is too big for NVRAM partition %#x",
+				       type);
+		rc = -EFBIG;
+		goto out_unlock;
+	}
+
+	devlink_flash_update_status_notify(devlink, "Starting update", NULL, 0, 0);
+
+	rc = efx_mcdi_nvram_update_start(efx, type);
+	if (rc) {
+		NL_SET_ERR_MSG_FMT_MOD(extack,
+				       "Update start request for NVRAM partition %#x failed",
+				       type);
+		goto out_unlock;
+	}
 
+	rc = efx_reflash_erase_partition(efx, extack, devlink, type, size,
+					 erase_align);
+	if (rc)
+		goto out_update_finish;
+
+	rc = efx_reflash_write_partition(efx, extack, devlink, type, data,
+					 data_size, write_align);
+	if (rc)
+		goto out_update_finish;
+
+	devlink_flash_update_timeout_notify(devlink, "Finishing update", NULL,
+					    EFX_DEVLINK_UPDATE_FINISH_TIMEOUT);
+
+out_update_finish:
+	if (rc)
+		/* Don't obscure the return code from an earlier failure */
+		efx_mcdi_nvram_update_finish(efx, type, EFX_UPDATE_FINISH_ABORT);
+	else
+		rc = efx_mcdi_nvram_update_finish_polled(efx, type);
+out_unlock:
+	mutex_unlock(&efx->reflash_mutex);
 out:
 	devlink_flash_update_status_notify(devlink, rc ? "Update failed" :
 							 "Update complete",
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index f70a7b7d6345c..8b0689f749b53 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1006,6 +1006,7 @@ struct efx_mae;
  * @dl_port: devlink port associated with the PF
  * @mem_bar: The BAR that is mapped into membase.
  * @reg_base: Offset from the start of the bar to the function control window.
+ * @reflash_mutex: Mutex for serialising firmware reflash operations.
  * @monitor_work: Hardware monitor workitem
  * @biu_lock: BIU (bus interface unit) lock
  * @last_irq_cpu: Last CPU to handle a possible test interrupt.  This
@@ -1191,6 +1192,7 @@ struct efx_nic {
 	struct devlink_port *dl_port;
 	unsigned int mem_bar;
 	u32 reg_base;
+	struct mutex reflash_mutex;
 
 	/* The following fields may be written more often */
 

From 5ea73bf3c40d03f09d4cd19b8222ad6b585afbbb Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Mon, 10 Feb 2025 11:25:45 +0000
Subject: [PATCH 0473/2753] sfc: document devlink flash support

Update the information in sfc's devlink documentation including
 support for firmware update with devlink flash.
Also update the help text for CONFIG_SFC_MTD, as it is no longer
 strictly required for firmware updates.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/3476b0ef04a0944f03e0b771ec8ed1a9c70db4dc.1739186253.git.ecree.xilinx@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/devlink/sfc.rst | 16 +++++++++++++++-
 drivers/net/ethernet/sfc/Kconfig         |  5 +++--
 2 files changed, 18 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/devlink/sfc.rst b/Documentation/networking/devlink/sfc.rst
index db64a1bd97336..0398d59ea1848 100644
--- a/Documentation/networking/devlink/sfc.rst
+++ b/Documentation/networking/devlink/sfc.rst
@@ -5,7 +5,7 @@ sfc devlink support
 ===================
 
 This document describes the devlink features implemented by the ``sfc``
-device driver for the ef100 device.
+device driver for the ef10 and ef100 devices.
 
 Info versions
 =============
@@ -18,6 +18,10 @@ The ``sfc`` driver reports the following versions
    * - Name
      - Type
      - Description
+   * - ``fw.bundle_id``
+     - stored
+     - Version of the firmware "bundle" image that was last used to update
+       multiple components.
    * - ``fw.mgmt.suc``
      - running
      - For boards where the management function is split between multiple
@@ -55,3 +59,13 @@ The ``sfc`` driver reports the following versions
    * - ``fw.uefi``
      - running
      - UEFI driver version (No UNDI support).
+
+Flash Update
+============
+
+The ``sfc`` driver implements support for flash update using the
+``devlink-flash`` interface. It supports updating the device flash using a
+combined flash image ("bundle") that contains multiple components (on ef10,
+typically ``fw.mgmt``, ``fw.app``, ``fw.exprom`` and ``fw.uefi``).
+
+The driver does not support any overwrite mask flags.
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig
index 3eb55dcfa8a61..c4c43434f3143 100644
--- a/drivers/net/ethernet/sfc/Kconfig
+++ b/drivers/net/ethernet/sfc/Kconfig
@@ -38,8 +38,9 @@ config SFC_MTD
 	default y
 	help
 	  This exposes the on-board flash and/or EEPROM as MTD devices
-	  (e.g. /dev/mtd1).  This is required to update the firmware or
-	  the boot configuration under Linux.
+	  (e.g. /dev/mtd1).  This is required to update the boot
+	  configuration under Linux, or use some older userland tools to
+	  update the firmware.
 config SFC_MCDI_MON
 	bool "Solarflare SFC9100-family hwmon support"
 	depends on SFC && HWMON && !(SFC=y && HWMON=m)

From 59115e2e25f42924181055ed7cc1d123af7598b7 Mon Sep 17 00:00:00 2001
From: Naman Jain <namjain@linux.microsoft.com>
Date: Thu, 16 Jan 2025 06:12:24 +0000
Subject: [PATCH 0474/2753] x86/hyperv/vtl: Stop kernel from probing VTL0 low
 memory

For Linux, running in Hyper-V VTL (Virtual Trust Level), kernel in VTL2
tries to access VTL0 low memory in probe_roms. This memory is not
described in the e820 map. Initialize probe_roms call to no-ops
during boot for VTL2 kernel to avoid this. The issue got identified
in OpenVMM which detects invalid accesses initiated from kernel running
in VTL2.

Co-developed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Signed-off-by: Naman Jain <namjain@linux.microsoft.com>
Tested-by: Roman Kisel <romank@linux.microsoft.com>
Reviewed-by: Roman Kisel <romank@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250116061224.1701-1-namjain@linux.microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250116061224.1701-1-namjain@linux.microsoft.com>
---
 arch/x86/hyperv/hv_vtl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 4e1b1e3b56584..3f4e20d7b724b 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -30,6 +30,7 @@ void __init hv_vtl_init_platform(void)
 	x86_platform.realmode_init = x86_init_noop;
 	x86_init.irqs.pre_vector_init = x86_init_noop;
 	x86_init.timers.timer_init = x86_init_noop;
+	x86_init.resources.probe_roms = x86_init_noop;
 
 	/* Avoid searching for BIOS MP tables */
 	x86_init.mpparse.find_mptable = x86_init_noop;

From e1d68ea58c7e9ebacd9ad7a99b25a3578fa62182 Mon Sep 17 00:00:00 2001
From: William Tu <witu@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:07 +0200
Subject: [PATCH 0475/2753] net/mlx5e: reduce the max log mpwrq sz for ECPF and
 reps

For the ECPF and representors, reduce the max MPWRQ size from 256KB (18)
to 128KB (17). This prepares the later patch for saving representor
memory.

With Striding RQ, there is a minimum of 4 MPWQEs. So with 128KB of max
MPWRQ size, the minimal memory is 4 * 128KB = 512KB. When creating page
pool, consider 1500 mtu, the minimal page pool size will be 512KB/4KB =
128 pages = 256 rx ring entries (2 entries per page).

Before this patch, setting RX ringsize (ethtool -G rx) to 256 causes
driver to allocate page pool size more than it needs due to max MPWRQ
is 256KB (18). Ex: 4 * 256KB = 1MB, 1MB/4KB = 256 pages, but actually
128 pages is good enough. Reducing the max MPWRQ to 128KB fixes the
limitation.

Signed-off-by: William Tu <witu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250209101716.112774-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h      |  2 --
 .../net/ethernet/mellanox/mlx5/core/en/params.c   | 15 +++++++++++----
 2 files changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 979fc56205e1f..534fdd27c8de0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -95,8 +95,6 @@ struct page_pool;
 #define MLX5_MPWRQ_DEF_LOG_STRIDE_SZ(mdev) \
 	MLX5_MPWRQ_LOG_STRIDE_SZ(mdev, order_base_2(MLX5E_RX_MAX_HEAD))
 
-#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
-
 /* Keep in sync with mlx5e_mpwrq_log_wqe_sz.
  * These are theoretical maximums, which can be further restricted by
  * capabilities. These values are used for static resource allocations and
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index 64b62ed17b07a..e37d4c202bba4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -10,6 +10,9 @@
 #include <net/page_pool/types.h>
 #include <net/xdp_sock_drv.h>
 
+#define MLX5_MPWRQ_MAX_LOG_WQE_SZ 18
+#define MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ 17
+
 static u8 mlx5e_mpwrq_min_page_shift(struct mlx5_core_dev *mdev)
 {
 	u8 min_page_shift = MLX5_CAP_GEN_2(mdev, log_min_mkey_entity_size);
@@ -103,18 +106,22 @@ u8 mlx5e_mpwrq_log_wqe_sz(struct mlx5_core_dev *mdev, u8 page_shift,
 			  enum mlx5e_mpwrq_umr_mode umr_mode)
 {
 	u8 umr_entry_size = mlx5e_mpwrq_umr_entry_size(umr_mode);
-	u8 max_pages_per_wqe, max_log_mpwqe_size;
+	u8 max_pages_per_wqe, max_log_wqe_size_calc;
+	u8 max_log_wqe_size_cap;
 	u16 max_wqe_size;
 
 	/* Keep in sync with MLX5_MPWRQ_MAX_PAGES_PER_WQE. */
 	max_wqe_size = mlx5e_get_max_sq_aligned_wqebbs(mdev) * MLX5_SEND_WQE_BB;
 	max_pages_per_wqe = ALIGN_DOWN(max_wqe_size - sizeof(struct mlx5e_umr_wqe),
 				       MLX5_UMR_FLEX_ALIGNMENT) / umr_entry_size;
-	max_log_mpwqe_size = ilog2(max_pages_per_wqe) + page_shift;
+	max_log_wqe_size_calc = ilog2(max_pages_per_wqe) + page_shift;
+
+	WARN_ON_ONCE(max_log_wqe_size_calc < MLX5E_ORDER2_MAX_PACKET_MTU);
 
-	WARN_ON_ONCE(max_log_mpwqe_size < MLX5E_ORDER2_MAX_PACKET_MTU);
+	max_log_wqe_size_cap = mlx5_core_is_ecpf(mdev) ?
+			   MLX5_REP_MPWRQ_MAX_LOG_WQE_SZ : MLX5_MPWRQ_MAX_LOG_WQE_SZ;
 
-	return min_t(u8, max_log_mpwqe_size, MLX5_MPWRQ_MAX_LOG_WQE_SZ);
+	return min_t(u8, max_log_wqe_size_calc, max_log_wqe_size_cap);
 }
 
 u8 mlx5e_mpwrq_pages_per_wqe(struct mlx5_core_dev *mdev, u8 page_shift,

From b9cc8f9d700867aaa77aedddfea85e53d5e5d584 Mon Sep 17 00:00:00 2001
From: William Tu <witu@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:08 +0200
Subject: [PATCH 0476/2753] net/mlx5e: reduce rep rxq depth to 256 for ECPF

By experiments, a single queue representor netdev consumes kernel
memory around 2.8MB, and 1.8MB out of the 2.8MB is due to page
pool for the RXQ. Scaling to a thousand representors consumes 2.8GB,
which becomes a memory pressure issue for embedded devices such as
BlueField-2 16GB / BlueField-3 32GB memory.

Since representor netdevs mostly handles miss traffic, and ideally,
most of the traffic will be offloaded, reduce the default non-uplink
rep netdev's RXQ default depth from 1024 to 256 if mdev is ecpf eswitch
manager. This saves around 1MB of memory per regular RQ,
(1024 - 256) * 2KB, allocated from page pool.

With rxq depth of 256, the netlink page pool tool reports
$./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
	 --dump page-pool-get
 {'id': 277,
  'ifindex': 9,
  'inflight': 128,
  'inflight-mem': 786432,
  'napi-id': 775}]

This is due to mtu 1500 + headroom consumes half pages, so 256 rxq
entries consumes around 128 pages (thus create a page pool with
size 128), shown above at inflight.

Note that each netdev has multiple types of RQs, including
Regular RQ, XSK, PTP, Drop, Trap RQ. Since non-uplink representor
only supports regular rq, this patch only changes the regular RQ's
default depth.

Signed-off-by: William Tu <witu@nvidia.com>
Reviewed-by: Bodong Wang <bodong@nvidia.com>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250209101716.112774-8-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index fdff9fd8a89ec..da399adc88541 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -65,6 +65,7 @@
 #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \
 	max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE)
 #define MLX5E_REP_PARAMS_DEF_NUM_CHANNELS 1
+#define MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE 0x8
 
 static const char mlx5e_rep_driver_name[] = "mlx5e_rep";
 
@@ -855,6 +856,8 @@ static void mlx5e_build_rep_params(struct net_device *netdev)
 
 	/* RQ */
 	mlx5e_build_rq_params(mdev, params);
+	if (!mlx5e_is_uplink_rep(priv) && mlx5_core_is_ecpf(mdev))
+		params->log_rq_mtu_frames = MLX5E_REP_PARAMS_DEF_LOG_RQ_SIZE;
 
 	/* If netdev is already registered (e.g. move from nic profile to uplink,
 	 * RTNL lock must be held before triggering netdev notifiers.

From a38cc5706fb9f7dc4ee3a443f61de13ce1e410ed Mon Sep 17 00:00:00 2001
From: William Tu <witu@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:09 +0200
Subject: [PATCH 0477/2753] net/mlx5e: set the tx_queue_len for pfifo_fast

By default, the mq netdev creates a pfifo_fast qdisc. On a
system with 16 core, the pfifo_fast with 3 bands consumes
16 * 3 * 8 (size of pointer) * 1024 (default tx queue len)
= 393KB. The patch sets the tx qlen to representor default
value, 128 (1<<MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE), which
consumes 16 * 3 * 8 * 128 = 49KB, saving 344KB for each
representor at ECPF.

Signed-off-by: William Tu <witu@nvidia.com>
Reviewed-by: Daniel Jurgens <danielj@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250209101716.112774-9-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index da399adc88541..07f38f472a279 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -889,6 +889,8 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 	netdev->ethtool_ops = &mlx5e_rep_ethtool_ops;
 
 	netdev->watchdog_timeo    = 15 * HZ;
+	if (mlx5_core_is_ecpf(mdev))
+		netdev->tx_queue_len = 1 << MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE;
 
 #if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
 	netdev->hw_features    |= NETIF_F_HW_TC;

From 38b3d42e5afa30bb59943b5410edeeb2a55b169d Mon Sep 17 00:00:00 2001
From: Akiva Goldberger <agoldberger@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:10 +0200
Subject: [PATCH 0478/2753] net/mlx5: Rename and move
 mlx5_esw_query_vport_vhca_id

Rename mlx5_esw_query_vport_vhca_id to mlx5_vport_get_vhca_id and move
it to vport file. Also, add function declaration to mlx5_core header
file. This better represents the function's usage and allows for it to
be called from other parts of the mlx5_core driver.

Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-10-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/eswitch_offloads.c     | 29 ++-----------------
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  2 ++
 .../net/ethernet/mellanox/mlx5/core/vport.c   | 25 ++++++++++++++++
 3 files changed, 29 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 20cc01ceee8a9..0fa0333106a2f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -4157,37 +4157,12 @@ u32 mlx5_eswitch_get_vport_metadata_for_match(struct mlx5_eswitch *esw,
 }
 EXPORT_SYMBOL(mlx5_eswitch_get_vport_metadata_for_match);
 
-static int mlx5_esw_query_vport_vhca_id(struct mlx5_eswitch *esw, u16 vport_num, u16 *vhca_id)
-{
-	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
-	void *query_ctx;
-	void *hca_caps;
-	int err;
-
-	*vhca_id = 0;
-
-	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
-	if (!query_ctx)
-		return -ENOMEM;
-
-	err = mlx5_vport_get_other_func_general_cap(esw->dev, vport_num, query_ctx);
-	if (err)
-		goto out_free;
-
-	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
-	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
-
-out_free:
-	kfree(query_ctx);
-	return err;
-}
-
 int mlx5_esw_vport_vhca_id_set(struct mlx5_eswitch *esw, u16 vport_num)
 {
 	u16 *old_entry, *vhca_map_entry, vhca_id;
 	int err;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
+	err = mlx5_vport_get_vhca_id(esw->dev, vport_num, &vhca_id);
 	if (err) {
 		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%u,err=%d)\n",
 			 vport_num, err);
@@ -4213,7 +4188,7 @@ void mlx5_esw_vport_vhca_id_clear(struct mlx5_eswitch *esw, u16 vport_num)
 	u16 *vhca_map_entry, vhca_id;
 	int err;
 
-	err = mlx5_esw_query_vport_vhca_id(esw, vport_num, &vhca_id);
+	err = mlx5_vport_get_vhca_id(esw->dev, vport_num, &vhca_id);
 	if (err)
 		esw_warn(esw->dev, "Getting vhca_id for vport failed (vport=%hu,err=%d)\n",
 			 vport_num, err);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 99de67c3aa743..6fef1005c469c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -346,6 +346,8 @@ int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap
 #define mlx5_vport_get_other_func_general_cap(dev, vport, out)		\
 	mlx5_vport_get_other_func_cap(dev, vport, out, MLX5_CAP_GENERAL)
 
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id);
+
 static inline u32 mlx5_sriov_get_vf_total_msix(struct pci_dev *pdev)
 {
 	struct mlx5_core_dev *dev = pci_get_drvdata(pdev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
index 0d5f750faa455..d10d4c3960408 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c
@@ -1199,6 +1199,31 @@ int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *ou
 }
 EXPORT_SYMBOL_GPL(mlx5_vport_get_other_func_cap);
 
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id)
+{
+	int query_out_sz = MLX5_ST_SZ_BYTES(query_hca_cap_out);
+	void *query_ctx;
+	void *hca_caps;
+	int err;
+
+	*vhca_id = 0;
+
+	query_ctx = kzalloc(query_out_sz, GFP_KERNEL);
+	if (!query_ctx)
+		return -ENOMEM;
+
+	err = mlx5_vport_get_other_func_general_cap(dev, vport, query_ctx);
+	if (err)
+		goto out_free;
+
+	hca_caps = MLX5_ADDR_OF(query_hca_cap_out, query_ctx, capability);
+	*vhca_id = MLX5_GET(cmd_hca_cap, hca_caps, vhca_id);
+
+out_free:
+	kfree(query_ctx);
+	return err;
+}
+
 int mlx5_vport_set_other_func_cap(struct mlx5_core_dev *dev, const void *hca_cap,
 				  u16 vport, u16 opmod)
 {

From b820864335c8b39b0e90d04ecbebdeed4d3d6dfd Mon Sep 17 00:00:00 2001
From: Akiva Goldberger <agoldberger@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:11 +0200
Subject: [PATCH 0479/2753] net/mlx5: Expose ICM consumption per function

ICM is a portion of the host's memory assigned to a function by the OS
through requests made by the NIC's firmware.

PF ICM consumption can be accessed directly, while VF/SF ICM consumption
can be accessed through their representors in switchdev mode.

The value is exposed to the user in granularity of 4KB through the vnic
health reporter as follows:

$ devlink health diagnose pci/0000:08:00.0 reporter vnic
 vNIC env counters:
     total_error_queues: 0 send_queue_priority_update_flow: 0
     comp_eq_overrun: 0 async_eq_overrun: 0 cq_overrun: 0
     invalid_command: 0 quota_exceeded_command: 0
     nic_receive_steering_discard: 0 icm_consumption: 1032

Signed-off-by: Akiva Goldberger <agoldberger@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-11-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/devlink/mlx5.rst     |  4 ++
 .../mellanox/mlx5/core/diag/reporter_vnic.c   | 46 +++++++++++++++++++
 2 files changed, 50 insertions(+)

diff --git a/Documentation/networking/devlink/mlx5.rst b/Documentation/networking/devlink/mlx5.rst
index 41618538fc70c..7febe0aecd53f 100644
--- a/Documentation/networking/devlink/mlx5.rst
+++ b/Documentation/networking/devlink/mlx5.rst
@@ -280,6 +280,10 @@ Description of the vnic counters:
 	number of packets handled by the VNIC experiencing unexpected steering
 	failure (at any point in steering flow owned by the VNIC, including the FDB
 	for the eswitch owner).
+- icm_consumption
+        amount of Interconnect Host Memory (ICM) consumed by the vnic in
+        granularity of 4KB. ICM is host memory allocated by SW upon HCA request
+        and is used for storing data structures that control HCA operation.
 
 User commands examples:
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
index c7216e84ef8c0..86253a89c24c9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/reporter_vnic.c
@@ -13,6 +13,50 @@ struct mlx5_vnic_diag_stats {
 	__be64 query_vnic_env_out[MLX5_ST_SZ_QW(query_vnic_env_out)];
 };
 
+static void mlx5_reporter_vnic_diagnose_counter_icm(struct mlx5_core_dev *dev,
+						    struct devlink_fmsg *fmsg,
+						    u16 vport_num, bool other_vport)
+{
+	u32 out_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 in_icm_reg[MLX5_ST_SZ_DW(vhca_icm_ctrl_reg)] = {};
+	u32 out_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 in_reg[MLX5_ST_SZ_DW(nic_cap_reg)] = {};
+	u32 cur_alloc_icm;
+	int vhca_icm_ctrl;
+	u16 vhca_id;
+	int err;
+
+	err = mlx5_core_access_reg(dev, in_reg, sizeof(in_reg), out_reg,
+				   sizeof(out_reg), MLX5_REG_NIC_CAP, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading nic_cap_reg failed. err = %d\n", err);
+		return;
+	}
+	vhca_icm_ctrl = MLX5_GET(nic_cap_reg, out_reg, vhca_icm_ctrl);
+	if (!vhca_icm_ctrl)
+		return;
+
+	MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id_valid, other_vport);
+	if (other_vport) {
+		err = mlx5_vport_get_vhca_id(dev, vport_num, &vhca_id);
+		if (err) {
+			mlx5_core_warn(dev, "vport to vhca_id failed. vport_num = %d, err = %d\n",
+				       vport_num, err);
+			return;
+		}
+		MLX5_SET(vhca_icm_ctrl_reg, in_icm_reg, vhca_id, vhca_id);
+	}
+	err = mlx5_core_access_reg(dev, in_icm_reg, sizeof(in_icm_reg),
+				   out_icm_reg, sizeof(out_icm_reg),
+				   MLX5_REG_VHCA_ICM_CTRL, 0, 0);
+	if (err) {
+		mlx5_core_warn(dev, "Reading vhca_icm_ctrl failed. err = %d\n", err);
+		return;
+	}
+	cur_alloc_icm = MLX5_GET(vhca_icm_ctrl_reg, out_icm_reg, cur_alloc_icm);
+	devlink_fmsg_u32_pair_put(fmsg, "icm_consumption", cur_alloc_icm);
+}
+
 void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 					  struct devlink_fmsg *fmsg,
 					  u16 vport_num, bool other_vport)
@@ -59,6 +103,8 @@ void mlx5_reporter_vnic_diagnose_counters(struct mlx5_core_dev *dev,
 		devlink_fmsg_u64_pair_put(fmsg, "handled_pkt_steering_fail",
 					  VNIC_ENV_GET64(&vnic, handled_pkt_steering_fail));
 	}
+	if (MLX5_CAP_GEN(dev, nic_cap_reg))
+		mlx5_reporter_vnic_diagnose_counter_icm(dev, fmsg, vport_num, other_vport);
 
 	devlink_fmsg_obj_nest_end(fmsg);
 	devlink_fmsg_pair_nest_end(fmsg);

From 913175b3f919eacba5e5d303897371f6058648a0 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:12 +0200
Subject: [PATCH 0480/2753] net/mlx5e: Move RQs diagnose to a dedicated
 function

Move rx reporter RQs diagnose from mlx5e_rx_reporter_diagnose() to a
dedicated function. This change is a preparation for the following
series which extends diagnose output for the rx reporter. While at it,
also pass a mlx5e_priv pointer to
mlx5e_rx_reporter_diagnose_common_config() as this is the argument the
latter actually needs.

Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-12-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en/reporter_rx.c       | 31 +++++++++++--------
 1 file changed, 18 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 25d751eba99ba..9255ab662af95 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -317,10 +317,8 @@ mlx5e_rx_reporter_diagnose_common_ptp_config(struct mlx5e_priv *priv, struct mlx
 }
 
 static void
-mlx5e_rx_reporter_diagnose_common_config(struct devlink_health_reporter *reporter,
-					 struct devlink_fmsg *fmsg)
+mlx5e_rx_reporter_diagnose_common_config(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_rq *generic_rq = &priv->channels.c[0]->rq;
 	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
 
@@ -340,20 +338,11 @@ static void mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq,
 	devlink_fmsg_obj_nest_end(fmsg);
 }
 
-static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
-				      struct devlink_fmsg *fmsg,
-				      struct netlink_ext_ack *extack)
+static void mlx5e_rx_reporter_diagnose_rqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
 {
-	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
 	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
 	int i;
 
-	mutex_lock(&priv->state_lock);
-
-	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
-		goto unlock;
-
-	mlx5e_rx_reporter_diagnose_common_config(reporter, fmsg);
 	devlink_fmsg_arr_pair_nest_start(fmsg, "RQs");
 
 	for (i = 0; i < priv->channels.num; i++) {
@@ -367,7 +356,23 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 	}
 	if (ptp_ch && test_bit(MLX5E_PTP_STATE_RX, ptp_ch->state))
 		mlx5e_rx_reporter_build_diagnose_output_ptp_rq(&ptp_ch->rq, fmsg);
+
 	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
+				      struct devlink_fmsg *fmsg,
+				      struct netlink_ext_ack *extack)
+{
+	struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter);
+
+	mutex_lock(&priv->state_lock);
+
+	if (!test_bit(MLX5E_STATE_OPENED, &priv->state))
+		goto unlock;
+
+	mlx5e_rx_reporter_diagnose_common_config(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rqs(priv, fmsg);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;

From 99c55284e85b3e2f28e1fd28e9946233424880d7 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:13 +0200
Subject: [PATCH 0481/2753] net/mlx5e: Add direct TIRs to devlink rx reporter
 diagnose

Add "RX resources" tag to the output of rx reporter diagnose callback.
Underneath add tag for direct TIRs, for each TIR expose its tirn and
the corresponding rqtn.

$ sudo devlink health diagnose auxiliary/mlx5_core.eth.0/65535 reporter rx
 ....
 rx resources:
   Direct TIRs:
       ix: 0 tirn: 20 rqtn: 1
       ix: 1 tirn: 21 rqtn: 2
       ix: 2 tirn: 22 rqtn: 3
       ix: 3 tirn: 23 rqtn: 4
       ix: 4 tirn: 24 rqtn: 5
       ix: 5 tirn: 25 rqtn: 6
       ix: 6 tirn: 26 rqtn: 7
       ix: 7 tirn: 27 rqtn: 8
       ix: 8 tirn: 28 rqtn: 9
       ix: 9 tirn: 29 rqtn: 10
       ix: 10 tirn: 30 rqtn: 11
       ix: 11 tirn: 31 rqtn: 12
       ix: 12 tirn: 32 rqtn: 13
       ix: 13 tirn: 33 rqtn: 14
       ix: 14 tirn: 34 rqtn: 15
       ix: 15 tirn: 35 rqtn: 16
       ix: 16 tirn: 36 rqtn: 17
       ix: 17 tirn: 37 rqtn: 18
       ix: 18 tirn: 38 rqtn: 19
       ix: 19 tirn: 39 rqtn: 20
       ix: 20 tirn: 40 rqtn: 21
       ix: 21 tirn: 41 rqtn: 22
       ix: 22 tirn: 42 rqtn: 23
       ix: 23 tirn: 43 rqtn: 24

Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-13-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en/reporter_rx.c       | 32 +++++++++++++++++++
 .../ethernet/mellanox/mlx5/core/en/rx_res.c   |  7 +++-
 .../ethernet/mellanox/mlx5/core/en/rx_res.h   |  2 ++
 3 files changed, 40 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index 9255ab662af95..bb513a22dc66d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -338,6 +338,37 @@ static void mlx5e_rx_reporter_build_diagnose_output_ptp_rq(struct mlx5e_rq *rq,
 	devlink_fmsg_obj_nest_end(fmsg);
 }
 
+static void mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(struct mlx5e_rx_res *rx_res,
+							struct devlink_fmsg *fmsg)
+{
+	unsigned int max_nch = mlx5e_rx_res_get_max_nch(rx_res);
+	int i;
+
+	devlink_fmsg_arr_pair_nest_start(fmsg, "Direct TIRs");
+
+	for (i = 0; i < max_nch; i++) {
+		devlink_fmsg_obj_nest_start(fmsg);
+
+		devlink_fmsg_u32_pair_put(fmsg, "ix", i);
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rx_res_get_tirn_direct(rx_res, i));
+		devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rx_res_get_rqtn_direct(rx_res, i));
+
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res(struct mlx5e_priv *priv,
+					      struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rx_res *rx_res = priv->rx_res;
+
+	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX resources");
+	mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(rx_res, fmsg);
+	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
+}
+
 static void mlx5e_rx_reporter_diagnose_rqs(struct mlx5e_priv *priv, struct devlink_fmsg *fmsg)
 {
 	struct mlx5e_ptp *ptp_ch = priv->channels.ptp;
@@ -373,6 +404,7 @@ static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter,
 
 	mlx5e_rx_reporter_diagnose_common_config(priv, fmsg);
 	mlx5e_rx_reporter_diagnose_rqs(priv, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res(priv, fmsg);
 unlock:
 	mutex_unlock(&priv->state_lock);
 	return 0;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index a86eade9a9e07..4e301bb5e3057 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -497,6 +497,11 @@ void mlx5e_rx_res_destroy(struct mlx5e_rx_res *res)
 	mlx5e_rx_res_free(res);
 }
 
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res)
+{
+	return res->max_nch;
+}
+
 u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_tir_get_tirn(&res->channels[ix].direct_tir);
@@ -522,7 +527,7 @@ u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res)
 	return mlx5e_tir_get_tirn(&res->ptp.tir);
 }
 
-static u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix)
 {
 	return mlx5e_rqt_get_rqtn(&res->channels[ix].direct_rqt);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 7b1a9f0f18741..391671b09c915 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -34,6 +34,8 @@ u32 mlx5e_rx_res_get_tirn_direct(struct mlx5e_rx_res *res, unsigned int ix);
 u32 mlx5e_rx_res_get_tirn_rss(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_types tt);
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
+u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
+unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res);
 
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);

From 896c92aa7429e1edd1418610e0b73120a89c7b07 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:14 +0200
Subject: [PATCH 0482/2753] net/mlx5e: Expose RSS via devlink rx reporter
 diagnose

Underneath "rx resources" tag expose RSS diagnostic information. For
each RSS expose its rqtn, TIRs and inner TIRs.

$ devlink health diagnose auxiliary/mlx5_core.eth.0/65535 reporter rx
 .......
RSS:
    Index: 0 rqtn: 0
    TIRs Numbers:
        tt: TT_IPV4_TCP tirn: 0
        tt: TT_IPV6_TCP tirn: 1
        tt: TT_IPV4_UDP tirn: 2
        tt: TT_IPV6_UDP tirn: 3
        tt: TT_IPV4_IPSEC_AH tirn: 4
        tt: TT_IPV6_IPSEC_AH tirn: 5
        tt: TT_IPV4_IPSEC_ESP tirn: 6
        tt: TT_IPV6_IPSEC_ESP tirn: 7
        tt: TT_IPV4 tirn: 8
        tt: TT_IPV6 tirn: 9
    Inner TIRs Numbers:
        tt: TT_IPV4_TCP tirn: 10
        tt: TT_IPV6_TCP tirn: 11
        tt: TT_IPV4_UDP tirn: 12
        tt: TT_IPV6_UDP tirn: 13
        tt: TT_IPV4_IPSEC_AH tirn: 14
        tt: TT_IPV6_IPSEC_AH tirn: 15
        tt: TT_IPV4_IPSEC_ESP tirn: 16
        tt: TT_IPV6_IPSEC_ESP tirn: 17
        tt: TT_IPV4 tirn: 18
        tt: TT_IPV6 tirn: 19
    Index: 2 rqtn: 27
    TIRs Numbers:
        tt: TT_IPV6_TCP tirn: 46

Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Reviewed-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-14-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en/reporter_rx.c       | 58 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/en/rss.c  | 15 +++++
 .../net/ethernet/mellanox/mlx5/core/en/rss.h  |  3 +
 .../ethernet/mellanox/mlx5/core/en/rx_res.c   |  2 -
 .../ethernet/mellanox/mlx5/core/en/rx_res.h   |  3 +
 .../ethernet/mellanox/mlx5/core/lib/fs_ttc.c  | 19 ++++++
 .../ethernet/mellanox/mlx5/core/lib/fs_ttc.h  |  1 +
 7 files changed, 99 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
index bb513a22dc66d..e75759533ae0c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c
@@ -359,6 +359,63 @@ static void mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(struct mlx5e_rx_res *rx_
 	devlink_fmsg_arr_pair_nest_end(fmsg);
 }
 
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(struct mlx5e_rss *rss, bool inner,
+						       struct devlink_fmsg *fmsg)
+{
+	bool found_valid_tir = false;
+	int tt;
+
+	for (tt = 0; tt < MLX5E_NUM_INDIR_TIRS; tt++) {
+		if (!mlx5e_rss_valid_tir(rss, tt, inner))
+			continue;
+
+		if (!found_valid_tir) {
+			char *tir_msg = inner ? "Inner TIRs Numbers" : "TIRs Numbers";
+
+			found_valid_tir = true;
+			devlink_fmsg_arr_pair_nest_start(fmsg, tir_msg);
+		}
+
+		devlink_fmsg_obj_nest_start(fmsg);
+		devlink_fmsg_string_pair_put(fmsg, "tt", mlx5_ttc_get_name(tt));
+		devlink_fmsg_u32_pair_put(fmsg, "tirn", mlx5e_rss_get_tirn(rss, tt, inner));
+		devlink_fmsg_obj_nest_end(fmsg);
+	}
+
+	if (found_valid_tir)
+		devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss_ix(struct mlx5e_rx_res *rx_res, u32 rss_idx,
+						     struct devlink_fmsg *fmsg)
+{
+	struct mlx5e_rss *rss = mlx5e_rx_res_rss_get(rx_res, rss_idx);
+
+	if (!rss)
+		return;
+
+	devlink_fmsg_obj_nest_start(fmsg);
+
+	devlink_fmsg_u32_pair_put(fmsg, "Index", rss_idx);
+	devlink_fmsg_u32_pair_put(fmsg, "rqtn", mlx5e_rss_get_rqtn(rss));
+	mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, false, fmsg);
+	if (mlx5e_rss_get_inner_ft_support(rss))
+		mlx5e_rx_reporter_diagnose_rx_res_rss_tirn(rss, true, fmsg);
+
+	devlink_fmsg_obj_nest_end(fmsg);
+}
+
+static void mlx5e_rx_reporter_diagnose_rx_res_rss(struct mlx5e_rx_res *rx_res,
+						  struct devlink_fmsg *fmsg)
+{
+	int rss_ix;
+
+	devlink_fmsg_arr_pair_nest_start(fmsg, "RSS");
+	for (rss_ix = 0; rss_ix < MLX5E_MAX_NUM_RSS; rss_ix++)
+		mlx5e_rx_reporter_diagnose_rx_res_rss_ix(rx_res, rss_ix, fmsg);
+	devlink_fmsg_arr_pair_nest_end(fmsg);
+}
+
 static void mlx5e_rx_reporter_diagnose_rx_res(struct mlx5e_priv *priv,
 					      struct devlink_fmsg *fmsg)
 {
@@ -366,6 +423,7 @@ static void mlx5e_rx_reporter_diagnose_rx_res(struct mlx5e_priv *priv,
 
 	mlx5e_health_fmsg_named_obj_nest_start(fmsg, "RX resources");
 	mlx5e_rx_reporter_diagnose_rx_res_dir_tirns(rx_res, fmsg);
+	mlx5e_rx_reporter_diagnose_rx_res_rss(rx_res, fmsg);
 	mlx5e_health_fmsg_named_obj_nest_end(fmsg);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 5f742f8966004..0d8ccc7b6c11d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -81,6 +81,11 @@ struct mlx5e_rss {
 	refcount_t refcnt;
 };
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss)
+{
+	return rss->inner_ft_support;
+}
+
 void mlx5e_rss_params_indir_modify_actual_size(struct mlx5e_rss *rss, u32 num_channels)
 {
 	rss->indir.actual_table_size = mlx5e_rqt_size(rss->mdev, num_channels);
@@ -449,6 +454,16 @@ u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 	return mlx5e_tir_get_tirn(tir);
 }
 
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss)
+{
+	return mlx5e_rqt_get_rqtn(&rss->rqt);
+}
+
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner)
+{
+	return !!rss_get_tir(rss, tt, inner);
+}
+
 /* Fill the "tirn" output parameter.
  * Create the requested TIR if it's its first usage.
  */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index d0df98963c8dd..72089f5f473c2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -32,8 +32,11 @@ void mlx5e_rss_refcnt_inc(struct mlx5e_rss *rss);
 void mlx5e_rss_refcnt_dec(struct mlx5e_rss *rss);
 unsigned int mlx5e_rss_refcnt_read(struct mlx5e_rss *rss);
 
+bool mlx5e_rss_get_inner_ft_support(struct mlx5e_rss *rss);
 u32 mlx5e_rss_get_tirn(struct mlx5e_rss *rss, enum mlx5_traffic_types tt,
 		       bool inner);
+bool mlx5e_rss_valid_tir(struct mlx5e_rss *rss, enum mlx5_traffic_types tt, bool inner);
+u32 mlx5e_rss_get_rqtn(struct mlx5e_rss *rss);
 int mlx5e_rss_obtain_tirn(struct mlx5e_rss *rss,
 			  enum mlx5_traffic_types tt,
 			  const struct mlx5e_packet_merge_param *init_pkt_merge_param,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 4e301bb5e3057..9d8b2f5f6c967 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -5,8 +5,6 @@
 #include "channels.h"
 #include "params.h"
 
-#define MLX5E_MAX_NUM_RSS 16
-
 struct mlx5e_rx_res {
 	struct mlx5_core_dev *mdev; /* primary */
 	enum mlx5e_rx_res_features features;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 391671b09c915..05b438043bcb3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -10,6 +10,8 @@
 #include "fs.h"
 #include "rss.h"
 
+#define MLX5E_MAX_NUM_RSS 16
+
 struct mlx5e_rx_res;
 
 struct mlx5e_channels;
@@ -36,6 +38,7 @@ u32 mlx5e_rx_res_get_tirn_rss_inner(struct mlx5e_rx_res *res, enum mlx5_traffic_
 u32 mlx5e_rx_res_get_tirn_ptp(struct mlx5e_rx_res *res);
 u32 mlx5e_rx_res_get_rqtn_direct(struct mlx5e_rx_res *res, unsigned int ix);
 unsigned int mlx5e_rx_res_get_max_nch(struct mlx5e_rx_res *res);
+bool mlx5_rx_res_rss_inner_ft_support(struct mlx5e_rx_res *res);
 
 /* Activate/deactivate API */
 void mlx5e_rx_res_channels_activate(struct mlx5e_rx_res *res, struct mlx5e_channels *chs);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
index 9f13cea164465..eb3bd9c7f66eb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.c
@@ -61,6 +61,25 @@ static void mlx5_cleanup_ttc_rules(struct mlx5_ttc_table *ttc)
 	}
 }
 
+static const char *mlx5_traffic_types_names[MLX5_NUM_TT] = {
+	[MLX5_TT_IPV4_TCP] =  "TT_IPV4_TCP",
+	[MLX5_TT_IPV6_TCP] =  "TT_IPV6_TCP",
+	[MLX5_TT_IPV4_UDP] =  "TT_IPV4_UDP",
+	[MLX5_TT_IPV6_UDP] =  "TT_IPV6_UDP",
+	[MLX5_TT_IPV4_IPSEC_AH] = "TT_IPV4_IPSEC_AH",
+	[MLX5_TT_IPV6_IPSEC_AH] = "TT_IPV6_IPSEC_AH",
+	[MLX5_TT_IPV4_IPSEC_ESP] = "TT_IPV4_IPSEC_ESP",
+	[MLX5_TT_IPV6_IPSEC_ESP] = "TT_IPV6_IPSEC_ESP",
+	[MLX5_TT_IPV4] = "TT_IPV4",
+	[MLX5_TT_IPV6] = "TT_IPV6",
+	[MLX5_TT_ANY] = "TT_ANY"
+};
+
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt)
+{
+	return mlx5_traffic_types_names[tt];
+}
+
 struct mlx5_etype_proto {
 	u16 etype;
 	u8 proto;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
index 92eea6bea310b..ab9434fe3ae66 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_ttc.h
@@ -49,6 +49,7 @@ struct ttc_params {
 	struct mlx5_flow_destination tunnel_dests[MLX5_NUM_TUNNEL_TT];
 };
 
+const char *mlx5_ttc_get_name(enum mlx5_traffic_types tt);
 struct mlx5_flow_table *mlx5_get_ttc_flow_table(struct mlx5_ttc_table *ttc);
 
 struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,

From 95b9606b15bb3ce1198d28d2393dd0e1f0a5f3e9 Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:15 +0200
Subject: [PATCH 0483/2753] net/mlx5: Extend Ethtool loopback selftest to
 support non-linear SKB

Current loopback test validation ignores non-linear SKB case in
the SKB access, which can lead to failures in scenarios such as
when HW GRO is enabled.
Linearize the SKB so both cases will be handled.

Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-15-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
index 1d60465cc2ca4..2f7a543feca62 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_selftest.c
@@ -166,6 +166,9 @@ mlx5e_test_loopback_validate(struct sk_buff *skb,
 	struct udphdr *udph;
 	struct iphdr *iph;
 
+	if (skb_linearize(skb))
+		goto out;
+
 	/* We are only going to peek, no need to clone the SKB */
 	if (MLX5E_TEST_PKT_SIZE - ETH_HLEN > skb_headlen(skb))
 		goto out;

From 1a9304859b3a4119579524c293b902a8927180f3 Mon Sep 17 00:00:00 2001
From: Alexei Lazar <alazar@nvidia.com>
Date: Sun, 9 Feb 2025 12:17:16 +0200
Subject: [PATCH 0484/2753] net/mlx5: XDP, Enable TX side XDP multi-buffer
 support

In XDP scenarios, fragmented packets can occur if the MTU is larger
than the page size, even when the packet size fits within the linear
part.
If XDP multi-buffer support is disabled, the fragmented part won't be
handled in the TX flow, leading to packet drops.

Since XDP multi-buffer support is always available, this commit removes
the conditional check for enabling it.
This ensures that XDP multi-buffer support is always enabled,
regardless of the `is_xdp_mb` parameter, and guarantees the handling of
fragmented packets in such scenarios.

Signed-off-by: Alexei Lazar <alazar@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250209101716.112774-16-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  1 -
 .../ethernet/mellanox/mlx5/core/en/params.c   |  1 -
 .../ethernet/mellanox/mlx5/core/en/params.h   |  1 -
 .../mellanox/mlx5/core/en/reporter_tx.c       |  1 -
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c  | 49 ++++++++-----------
 .../net/ethernet/mellanox/mlx5/core/en_main.c | 29 -----------
 6 files changed, 21 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 534fdd27c8de0..769e683f24883 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -384,7 +384,6 @@ enum {
 	MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE,
 	MLX5E_SQ_STATE_PENDING_XSK_TX,
 	MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC,
-	MLX5E_SQ_STATE_XDP_MULTIBUF,
 	MLX5E_NUM_SQ_STATES, /* Must be kept last */
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
index e37d4c202bba4..aa36670d9a369 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
@@ -1247,7 +1247,6 @@ void mlx5e_build_xdpsq_param(struct mlx5_core_dev *mdev,
 	mlx5e_build_sq_param_common(mdev, param);
 	MLX5_SET(wq, wq, log_wq_sz, params->log_sq_size);
 	param->is_mpw = MLX5E_GET_PFLAG(params, MLX5E_PFLAG_XDP_TX_MPWQE);
-	param->is_xdp_mb = !mlx5e_rx_is_linear_skb(mdev, params, xsk);
 	mlx5e_build_tx_cq_param(mdev, params, &param->cqp);
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
index 3f8986f9d8629..bd5877acc5b1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h
@@ -33,7 +33,6 @@ struct mlx5e_sq_param {
 	struct mlx5_wq_param       wq;
 	bool                       is_mpw;
 	bool                       is_tls;
-	bool                       is_xdp_mb;
 	u16                        stop_room;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
index 09433b91be176..532c7fa94d172 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
@@ -16,7 +16,6 @@ static const char * const sq_sw_state_type_name[] = {
 	[MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE] = "vlan_need_l2_inline",
 	[MLX5E_SQ_STATE_PENDING_XSK_TX] = "pending_xsk_tx",
 	[MLX5E_SQ_STATE_PENDING_TLS_RX_RESYNC] = "pending_tls_rx_resync",
-	[MLX5E_SQ_STATE_XDP_MULTIBUF] = "xdp_multibuf",
 };
 
 static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 3cc4d55613bf2..6f3094a479e1e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -546,6 +546,7 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 	bool inline_ok;
 	bool linear;
 	u16 pi;
+	int i;
 
 	struct mlx5e_xdpsq_stats *stats = sq->stats;
 
@@ -612,41 +613,33 @@ mlx5e_xmit_xdp_frame(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptxd,
 
 	cseg->opmod_idx_opcode = cpu_to_be32((sq->pc << 8) | MLX5_OPCODE_SEND);
 
-	if (test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		int i;
-
-		memset(&cseg->trailer, 0, sizeof(cseg->trailer));
-		memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
-
-		eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
+	memset(&cseg->trailer, 0, sizeof(cseg->trailer));
+	memset(eseg, 0, sizeof(*eseg) - sizeof(eseg->trailer));
 
-		for (i = 0; i < num_frags; i++) {
-			skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
-			dma_addr_t addr;
+	eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
 
-			addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
-				page_pool_get_dma_addr(skb_frag_page(frag)) +
-				skb_frag_off(frag);
+	for (i = 0; i < num_frags; i++) {
+		skb_frag_t *frag = &xdptxdf->sinfo->frags[i];
+		dma_addr_t addr;
 
-			dseg->addr = cpu_to_be64(addr);
-			dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
-			dseg->lkey = sq->mkey_be;
-			dseg++;
-		}
+		addr = xdptxdf->dma_arr ? xdptxdf->dma_arr[i] :
+			page_pool_get_dma_addr(skb_frag_page(frag)) +
+			skb_frag_off(frag);
 
-		cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
+		dseg->addr = cpu_to_be64(addr);
+		dseg->byte_count = cpu_to_be32(skb_frag_size(frag));
+		dseg->lkey = sq->mkey_be;
+		dseg++;
+	}
 
-		sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
-			.num_wqebbs = num_wqebbs,
-			.num_pkts = 1,
-		};
+	cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
 
-		sq->pc += num_wqebbs;
-	} else {
-		cseg->fm_ce_se = 0;
+	sq->db.wqe_info[pi] = (struct mlx5e_xdp_wqe_info) {
+		.num_wqebbs = num_wqebbs,
+		.num_pkts = 1,
+	};
 
-		sq->pc++;
-	}
+	sq->pc += num_wqebbs;
 
 	xsk_tx_metadata_request(meta, &mlx5e_xsk_tx_metadata_ops, eseg);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2fdc86432ac0f..5d5e7b19c396b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -2023,41 +2023,12 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params,
 	csp.min_inline_mode = sq->min_inline_mode;
 	set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state);
 
-	if (param->is_xdp_mb)
-		set_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state);
-
 	err = mlx5e_create_sq_rdy(c->mdev, param, &csp, 0, &sq->sqn);
 	if (err)
 		goto err_free_xdpsq;
 
 	mlx5e_set_xmit_fp(sq, param->is_mpw);
 
-	if (!param->is_mpw && !test_bit(MLX5E_SQ_STATE_XDP_MULTIBUF, &sq->state)) {
-		unsigned int ds_cnt = MLX5E_TX_WQE_EMPTY_DS_COUNT + 1;
-		unsigned int inline_hdr_sz = 0;
-		int i;
-
-		if (sq->min_inline_mode != MLX5_INLINE_MODE_NONE) {
-			inline_hdr_sz = MLX5E_XDP_MIN_INLINE;
-			ds_cnt++;
-		}
-
-		/* Pre initialize fixed WQE fields */
-		for (i = 0; i < mlx5_wq_cyc_get_size(&sq->wq); i++) {
-			struct mlx5e_tx_wqe      *wqe  = mlx5_wq_cyc_get_wqe(&sq->wq, i);
-			struct mlx5_wqe_ctrl_seg *cseg = &wqe->ctrl;
-			struct mlx5_wqe_eth_seg  *eseg = &wqe->eth;
-
-			sq->db.wqe_info[i] = (struct mlx5e_xdp_wqe_info) {
-				.num_wqebbs = 1,
-				.num_pkts   = 1,
-			};
-
-			cseg->qpn_ds = cpu_to_be32((sq->sqn << 8) | ds_cnt);
-			eseg->inline_hdr.sz = cpu_to_be16(inline_hdr_sz);
-		}
-	}
-
 	return 0;
 
 err_free_xdpsq:

From 8bf47e4d7b87cbd6a69541643d3fa4003c99d95f Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 10 Feb 2025 09:23:57 +0100
Subject: [PATCH 0485/2753] net: phy: Add support for driver-specific next
 update time

Introduce the `phy_get_next_update_time` function to allow PHY drivers
to dynamically determine the time (in jiffies) until the next state
update event. This enables more flexible and adaptive polling intervals
based on the link state or other conditions.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250210082358.200751-2-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c | 21 ++++++++++++++++++++-
 include/linux/phy.h   | 13 +++++++++++++
 2 files changed, 33 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index d0c1718e2b16a..347ad1b644978 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1501,6 +1501,24 @@ void phy_free_interrupt(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_free_interrupt);
 
+/**
+ * phy_get_next_update_time - Determine the next PHY update time
+ * @phydev: Pointer to the phy_device structure
+ *
+ * This function queries the PHY driver to get the time for the next polling
+ * event. If the driver does not implement the callback, a default value is
+ * used.
+ *
+ * Return: The time for the next polling event in jiffies
+ */
+static unsigned int phy_get_next_update_time(struct phy_device *phydev)
+{
+	if (phydev->drv && phydev->drv->get_next_update_time)
+		return phydev->drv->get_next_update_time(phydev);
+
+	return PHY_STATE_TIME;
+}
+
 enum phy_state_work {
 	PHY_STATE_WORK_NONE,
 	PHY_STATE_WORK_ANEG,
@@ -1580,7 +1598,8 @@ static enum phy_state_work _phy_state_machine(struct phy_device *phydev)
 	 * called from phy_disconnect() synchronously.
 	 */
 	if (phy_polling_mode(phydev) && phy_is_started(phydev))
-		phy_queue_state_machine(phydev, PHY_STATE_TIME);
+		phy_queue_state_machine(phydev,
+					phy_get_next_update_time(phydev));
 
 	return state_work;
 }
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 83994b394d8e3..64982eba71d1e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1270,6 +1270,19 @@ struct phy_driver {
 	 */
 	int (*led_polarity_set)(struct phy_device *dev, int index,
 				unsigned long modes);
+
+	/**
+	 * @get_next_update_time: Get the time until the next update event
+	 * @dev: PHY device
+	 *
+	 * Callback to determine the time (in jiffies) until the next
+	 * update event for the PHY state  machine. Allows PHY drivers to
+	 * dynamically adjust polling intervals based on link state or other
+	 * conditions.
+	 *
+	 * Returns the time in jiffies until the next update event.
+	 */
+	unsigned int (*get_next_update_time)(struct phy_device *dev);
 };
 #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d),		\
 				      struct phy_driver, mdiodrv)

From e252af1a67fe66ec901e33035210b231d9d211b7 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Mon, 10 Feb 2025 09:23:58 +0100
Subject: [PATCH 0486/2753] net: phy: dp83tg720: Add randomized polling
 intervals for link detection

Address the limitations of the DP83TG720 PHY, which cannot reliably
detect or report a stable link state. To handle this, the PHY must be
periodically reset when the link is down. However, synchronized reset
intervals between the PHY and its link partner can result in a deadlock,
preventing the link from re-establishing.

This change introduces a randomized polling interval when the link is
down to desynchronize resets between link partners.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250210082358.200751-3-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83tg720.c | 78 +++++++++++++++++++++++++++++++++++++
 1 file changed, 78 insertions(+)

diff --git a/drivers/net/phy/dp83tg720.c b/drivers/net/phy/dp83tg720.c
index 050f4537d140f..7e76323409c4b 100644
--- a/drivers/net/phy/dp83tg720.c
+++ b/drivers/net/phy/dp83tg720.c
@@ -4,12 +4,31 @@
  */
 #include <linux/bitfield.h>
 #include <linux/ethtool_netlink.h>
+#include <linux/jiffies.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/phy.h>
+#include <linux/random.h>
 
 #include "open_alliance_helpers.h"
 
+/*
+ * DP83TG720S_POLL_ACTIVE_LINK - Polling interval in milliseconds when the link
+ *				 is active.
+ * DP83TG720S_POLL_NO_LINK_MIN - Minimum polling interval in milliseconds when
+ *				 the link is down.
+ * DP83TG720S_POLL_NO_LINK_MAX - Maximum polling interval in milliseconds when
+ *				 the link is down.
+ *
+ * These values are not documented or officially recommended by the vendor but
+ * were determined through empirical testing. They achieve a good balance in
+ * minimizing the number of reset retries while ensuring reliable link recovery
+ * within a reasonable timeframe.
+ */
+#define DP83TG720S_POLL_ACTIVE_LINK		1000
+#define DP83TG720S_POLL_NO_LINK_MIN		100
+#define DP83TG720S_POLL_NO_LINK_MAX		1000
+
 #define DP83TG720S_PHY_ID			0x2000a284
 
 /* MDIO_MMD_VEND2 registers */
@@ -371,6 +390,13 @@ static int dp83tg720_read_status(struct phy_device *phydev)
 		if (ret)
 			return ret;
 
+		/* Sleep 600ms for PHY stabilization post-reset.
+		 * Empirically chosen value (not documented).
+		 * Helps reduce reset bounces with link partners having similar
+		 * issues.
+		 */
+		msleep(600);
+
 		/* After HW reset we need to restore master/slave configuration.
 		 * genphy_c45_pma_baset1_read_master_slave() call will be done
 		 * by the dp83tg720_config_aneg() function.
@@ -498,6 +524,57 @@ static int dp83tg720_probe(struct phy_device *phydev)
 	return 0;
 }
 
+/**
+ * dp83tg720_get_next_update_time - Determine the next update time for PHY
+ *                                  state
+ * @phydev: Pointer to the phy_device structure
+ *
+ * This function addresses a limitation of the DP83TG720 PHY, which cannot
+ * reliably detect or report a stable link state. To recover from such
+ * scenarios, the PHY must be periodically reset when the link is down. However,
+ * if the link partner also runs Linux with the same driver, synchronized reset
+ * intervals can lead to a deadlock where the link never establishes due to
+ * simultaneous resets on both sides.
+ *
+ * To avoid this, the function implements randomized polling intervals when the
+ * link is down. It ensures that reset intervals are desynchronized by
+ * introducing a random delay between a configured minimum and maximum range.
+ * When the link is up, a fixed polling interval is used to minimize overhead.
+ *
+ * This mechanism guarantees that the link will reestablish within 10 seconds
+ * in the worst-case scenario.
+ *
+ * Return: Time (in jiffies) until the next update event for the PHY state
+ * machine.
+ */
+static unsigned int dp83tg720_get_next_update_time(struct phy_device *phydev)
+{
+	unsigned int next_time_jiffies;
+
+	if (phydev->link) {
+		/* When the link is up, use a fixed 1000ms interval
+		 * (in jiffies)
+		 */
+		next_time_jiffies =
+			msecs_to_jiffies(DP83TG720S_POLL_ACTIVE_LINK);
+	} else {
+		unsigned int min_jiffies, max_jiffies, rand_jiffies;
+
+		/* When the link is down, randomize interval between min/max
+		 * (in jiffies)
+		 */
+		min_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MIN);
+		max_jiffies = msecs_to_jiffies(DP83TG720S_POLL_NO_LINK_MAX);
+
+		rand_jiffies = min_jiffies +
+			get_random_u32_below(max_jiffies - min_jiffies + 1);
+		next_time_jiffies = rand_jiffies;
+	}
+
+	/* Ensure the polling time is at least one jiffy */
+	return max(next_time_jiffies, 1U);
+}
+
 static struct phy_driver dp83tg720_driver[] = {
 {
 	PHY_ID_MATCH_MODEL(DP83TG720S_PHY_ID),
@@ -516,6 +593,7 @@ static struct phy_driver dp83tg720_driver[] = {
 	.get_link_stats	= dp83tg720_get_link_stats,
 	.get_phy_stats	= dp83tg720_get_phy_stats,
 	.update_stats	= dp83tg720_update_stats,
+	.get_next_update_time = dp83tg720_get_next_update_time,
 
 	.suspend	= genphy_suspend,
 	.resume		= genphy_resume,

From 34eea78a1112afc3579e06abb510a9f57521adaf Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Feb 2025 10:13:52 -0800
Subject: [PATCH 0487/2753] net: report csum_complete via qstats

Commit 13c7c941e729 ("netdev: add qstat for csum complete") reserved
the entry for csum complete in the qstats uAPI. Start reporting this
value now that we have a driver which needs it.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250211181356.580800-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_queues.h | 1 +
 net/core/netdev-genl.c      | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/net/netdev_queues.h b/include/net/netdev_queues.h
index 73d3401261a62..825141d675e58 100644
--- a/include/net/netdev_queues.h
+++ b/include/net/netdev_queues.h
@@ -23,6 +23,7 @@ struct netdev_queue_stats_rx {
 	u64 hw_drops;
 	u64 hw_drop_overruns;
 
+	u64 csum_complete;
 	u64 csum_unnecessary;
 	u64 csum_none;
 	u64 csum_bad;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 0dcd4faefd8d4..c18bb53d13fd8 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -581,6 +581,7 @@ netdev_nl_stats_write_rx(struct sk_buff *rsp, struct netdev_queue_stats_rx *rx)
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_ALLOC_FAIL, rx->alloc_fail) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROPS, rx->hw_drops) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_HW_DROP_OVERRUNS, rx->hw_drop_overruns) ||
+	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_COMPLETE, rx->csum_complete) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_UNNECESSARY, rx->csum_unnecessary) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_NONE, rx->csum_none) ||
 	    netdev_stat_put(rsp, NETDEV_A_QSTATS_RX_CSUM_BAD, rx->csum_bad) ||

From 93d2f2f36ea993841d2efec4caef1cc95f4baa84 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Feb 2025 10:13:53 -0800
Subject: [PATCH 0488/2753] eth: fbnic: wrap tx queue stats in a struct

The queue stats struct is used for Rx and Tx queues. Wrap
the Tx stats in a struct and a union, so that we can reuse
the same space for Rx stats on Rx queues.

This also makes it easy to add an assert to the stat handling
code to catch new stats not being aggregated on shutdown.

Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250211181356.580800-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c |  8 ++++----
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c    | 10 ++++++----
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h    |  8 ++++++--
 3 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index 9503c36620c6b..fb7139a1da465 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -1224,14 +1224,14 @@ static void fbnic_get_ts_stats(struct net_device *netdev,
 	unsigned int start;
 	int i;
 
-	ts_stats->pkts = fbn->tx_stats.ts_packets;
-	ts_stats->lost = fbn->tx_stats.ts_lost;
+	ts_stats->pkts = fbn->tx_stats.twq.ts_packets;
+	ts_stats->lost = fbn->tx_stats.twq.ts_lost;
 	for (i = 0; i < fbn->num_tx_queues; i++) {
 		ring = fbn->tx[i];
 		do {
 			start = u64_stats_fetch_begin(&ring->stats.syncp);
-			ts_packets = ring->stats.ts_packets;
-			ts_lost = ring->stats.ts_lost;
+			ts_packets = ring->stats.twq.ts_packets;
+			ts_lost = ring->stats.twq.ts_lost;
 		} while (u64_stats_fetch_retry(&ring->stats.syncp, start));
 		ts_stats->pkts += ts_packets;
 		ts_stats->lost += ts_lost;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index d4d7027df9a03..b60dd1c9918e4 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -444,7 +444,7 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 	if (unlikely(discard)) {
 		u64_stats_update_begin(&ring->stats.syncp);
 		ring->stats.dropped += total_packets;
-		ring->stats.ts_lost += ts_lost;
+		ring->stats.twq.ts_lost += ts_lost;
 		u64_stats_update_end(&ring->stats.syncp);
 
 		netdev_tx_completed_queue(txq, total_packets, total_bytes);
@@ -507,7 +507,7 @@ static void fbnic_clean_tsq(struct fbnic_napi_vector *nv,
 
 	skb_tstamp_tx(skb, &hwtstamp);
 	u64_stats_update_begin(&ring->stats.syncp);
-	ring->stats.ts_packets++;
+	ring->stats.twq.ts_packets++;
 	u64_stats_update_end(&ring->stats.syncp);
 }
 
@@ -1065,8 +1065,10 @@ void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
 	fbn->tx_stats.bytes += stats->bytes;
 	fbn->tx_stats.packets += stats->packets;
 	fbn->tx_stats.dropped += stats->dropped;
-	fbn->tx_stats.ts_lost += stats->ts_lost;
-	fbn->tx_stats.ts_packets += stats->ts_packets;
+	fbn->tx_stats.twq.ts_lost += stats->twq.ts_lost;
+	fbn->tx_stats.twq.ts_packets += stats->twq.ts_packets;
+	/* Remember to add new stats here */
+	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 2);
 }
 
 static void fbnic_remove_tx_ring(struct fbnic_net *fbn,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index c2a94f31f71bd..6b549b0e7fa4a 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -56,9 +56,13 @@ struct fbnic_pkt_buff {
 struct fbnic_queue_stats {
 	u64 packets;
 	u64 bytes;
+	union {
+		struct {
+			u64 ts_packets;
+			u64 ts_lost;
+		} twq;
+	};
 	u64 dropped;
-	u64 ts_packets;
-	u64 ts_lost;
 	struct u64_stats_sync syncp;
 };
 

From 67dc4eb5fc926b96145ca6d81da35f0fa20396f0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Feb 2025 10:13:54 -0800
Subject: [PATCH 0489/2753] eth: fbnic: report software Rx queue stats

Gather and report software Rx queue stats - checksum stats
and allocation failures.

Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250211181356.580800-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    | 12 +++++-
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c  | 43 +++++++++++++++----
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h  |  5 +++
 3 files changed, 51 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index 14e7a8384bce2..ceb6d1de9bcf6 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -487,8 +487,9 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *rxr = fbn->rx[idx];
 	struct fbnic_queue_stats *stats;
+	u64 bytes, packets, alloc_fail;
+	u64 csum_complete, csum_none;
 	unsigned int start;
-	u64 bytes, packets;
 
 	if (!rxr)
 		return;
@@ -498,10 +499,16 @@ static void fbnic_get_queue_stats_rx(struct net_device *dev, int idx,
 		start = u64_stats_fetch_begin(&stats->syncp);
 		bytes = stats->bytes;
 		packets = stats->packets;
+		alloc_fail = stats->rx.alloc_failed;
+		csum_complete = stats->rx.csum_complete;
+		csum_none = stats->rx.csum_none;
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	rx->bytes = bytes;
 	rx->packets = packets;
+	rx->alloc_fail = alloc_fail;
+	rx->csum_complete = csum_complete;
+	rx->csum_none = csum_none;
 }
 
 static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
@@ -538,6 +545,9 @@ static void fbnic_get_base_stats(struct net_device *dev,
 
 	rx->bytes = fbn->rx_stats.bytes;
 	rx->packets = fbn->rx_stats.packets;
+	rx->alloc_fail = fbn->rx_stats.rx.alloc_failed;
+	rx->csum_complete = fbn->rx_stats.rx.csum_complete;
+	rx->csum_none = fbn->rx_stats.rx.csum_none;
 }
 
 static const struct netdev_stat_ops fbnic_stat_ops = {
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index b60dd1c9918e4..66ba36fd3c081 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -198,12 +198,15 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 }
 
 static void
-fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq)
+fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq,
+	      u64 *csum_cmpl, u64 *csum_none)
 {
 	skb_checksum_none_assert(skb);
 
-	if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM)))
+	if (unlikely(!(skb->dev->features & NETIF_F_RXCSUM))) {
+		(*csum_none)++;
 		return;
+	}
 
 	if (FIELD_GET(FBNIC_RCD_META_L4_CSUM_UNNECESSARY, rcd)) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -212,6 +215,7 @@ fbnic_rx_csum(u64 rcd, struct sk_buff *skb, struct fbnic_ring *rcq)
 
 		skb->ip_summed = CHECKSUM_COMPLETE;
 		skb->csum = (__force __wsum)csum;
+		(*csum_cmpl)++;
 	}
 }
 
@@ -661,8 +665,13 @@ static void fbnic_fill_bdq(struct fbnic_napi_vector *nv, struct fbnic_ring *bdq)
 		struct page *page;
 
 		page = page_pool_dev_alloc_pages(nv->page_pool);
-		if (!page)
+		if (!page) {
+			u64_stats_update_begin(&bdq->stats.syncp);
+			bdq->stats.rx.alloc_failed++;
+			u64_stats_update_end(&bdq->stats.syncp);
+
 			break;
+		}
 
 		fbnic_page_pool_init(bdq, i, page);
 		fbnic_bd_prep(bdq, i, page);
@@ -875,12 +884,13 @@ static void fbnic_rx_tstamp(struct fbnic_napi_vector *nv, u64 rcd,
 
 static void fbnic_populate_skb_fields(struct fbnic_napi_vector *nv,
 				      u64 rcd, struct sk_buff *skb,
-				      struct fbnic_q_triad *qt)
+				      struct fbnic_q_triad *qt,
+				      u64 *csum_cmpl, u64 *csum_none)
 {
 	struct net_device *netdev = nv->napi.dev;
 	struct fbnic_ring *rcq = &qt->cmpl;
 
-	fbnic_rx_csum(rcd, skb, rcq);
+	fbnic_rx_csum(rcd, skb, rcq, csum_cmpl, csum_none);
 
 	if (netdev->features & NETIF_F_RXHASH)
 		skb_set_hash(skb,
@@ -898,7 +908,8 @@ static bool fbnic_rcd_metadata_err(u64 rcd)
 static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 			   struct fbnic_q_triad *qt, int budget)
 {
-	unsigned int packets = 0, bytes = 0, dropped = 0;
+	unsigned int packets = 0, bytes = 0, dropped = 0, alloc_failed = 0;
+	u64 csum_complete = 0, csum_none = 0;
 	struct fbnic_ring *rcq = &qt->cmpl;
 	struct fbnic_pkt_buff *pkt;
 	s32 head0 = -1, head1 = -1;
@@ -947,14 +958,22 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 
 			/* Populate skb and invalidate XDP */
 			if (!IS_ERR_OR_NULL(skb)) {
-				fbnic_populate_skb_fields(nv, rcd, skb, qt);
+				fbnic_populate_skb_fields(nv, rcd, skb, qt,
+							  &csum_complete,
+							  &csum_none);
 
 				packets++;
 				bytes += skb->len;
 
 				napi_gro_receive(&nv->napi, skb);
 			} else {
-				dropped++;
+				if (!skb) {
+					alloc_failed++;
+					dropped++;
+				} else {
+					dropped++;
+				}
+
 				fbnic_put_pkt_buff(nv, pkt, 1);
 			}
 
@@ -977,6 +996,9 @@ static int fbnic_clean_rcq(struct fbnic_napi_vector *nv,
 	/* Re-add ethernet header length (removed in fbnic_build_skb) */
 	rcq->stats.bytes += ETH_HLEN * packets;
 	rcq->stats.dropped += dropped;
+	rcq->stats.rx.alloc_failed += alloc_failed;
+	rcq->stats.rx.csum_complete += csum_complete;
+	rcq->stats.rx.csum_none += csum_none;
 	u64_stats_update_end(&rcq->stats.syncp);
 
 	/* Unmap and free processed buffers */
@@ -1054,6 +1076,11 @@ void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
 	fbn->rx_stats.bytes += stats->bytes;
 	fbn->rx_stats.packets += stats->packets;
 	fbn->rx_stats.dropped += stats->dropped;
+	fbn->rx_stats.rx.alloc_failed += stats->rx.alloc_failed;
+	fbn->rx_stats.rx.csum_complete += stats->rx.csum_complete;
+	fbn->rx_stats.rx.csum_none += stats->rx.csum_none;
+	/* Remember to add new stats here */
+	BUILD_BUG_ON(sizeof(fbn->tx_stats.rx) / 8 != 3);
 }
 
 void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 6b549b0e7fa4a..c9d9001042dc2 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -61,6 +61,11 @@ struct fbnic_queue_stats {
 			u64 ts_packets;
 			u64 ts_lost;
 		} twq;
+		struct {
+			u64 alloc_failed;
+			u64 csum_complete;
+			u64 csum_none;
+		} rx;
 	};
 	u64 dropped;
 	struct u64_stats_sync syncp;

From 1e07e361fd8339eff761ef9bc4c3c1dd9a9cd887 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Feb 2025 10:13:55 -0800
Subject: [PATCH 0490/2753] eth: fbnic: report software Tx queue stats

Gather and report software Tx queue stats - checksum stats
and queue stop / start.

Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250211181356.580800-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    | 10 ++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c  | 23 +++++++++++++++----
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h  |  3 +++
 3 files changed, 32 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index ceb6d1de9bcf6..b12672d1607e9 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -517,6 +517,7 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *txr = fbn->tx[idx];
 	struct fbnic_queue_stats *stats;
+	u64 stop, wake, csum;
 	unsigned int start;
 	u64 bytes, packets;
 
@@ -528,10 +529,16 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 		start = u64_stats_fetch_begin(&stats->syncp);
 		bytes = stats->bytes;
 		packets = stats->packets;
+		csum = stats->twq.csum_partial;
+		stop = stats->twq.stop;
+		wake = stats->twq.wake;
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	tx->bytes = bytes;
 	tx->packets = packets;
+	tx->needs_csum = csum;
+	tx->stop = stop;
+	tx->wake = wake;
 }
 
 static void fbnic_get_base_stats(struct net_device *dev,
@@ -542,6 +549,9 @@ static void fbnic_get_base_stats(struct net_device *dev,
 
 	tx->bytes = fbn->tx_stats.bytes;
 	tx->packets = fbn->tx_stats.packets;
+	tx->needs_csum = fbn->tx_stats.twq.csum_partial;
+	tx->stop = fbn->tx_stats.twq.stop;
+	tx->wake = fbn->tx_stats.twq.wake;
 
 	rx->bytes = fbn->rx_stats.bytes;
 	rx->packets = fbn->rx_stats.packets;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 66ba36fd3c081..24d2b528b66c0 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -113,6 +113,11 @@ static int fbnic_maybe_stop_tx(const struct net_device *dev,
 
 	res = netif_txq_maybe_stop(txq, fbnic_desc_unused(ring), size,
 				   FBNIC_TX_DESC_WAKEUP);
+	if (!res) {
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.stop++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 
 	return !res;
 }
@@ -191,6 +196,9 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 					skb->csum_offset / 2));
 
 	*meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO);
+	u64_stats_update_begin(&ring->stats.syncp);
+	ring->stats.twq.csum_partial++;
+	u64_stats_update_end(&ring->stats.syncp);
 
 	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) |
 			     FIELD_PREP(FBNIC_TWD_L3_IHLEN_MASK, i3len / 2));
@@ -460,9 +468,13 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 	ring->stats.packets += total_packets;
 	u64_stats_update_end(&ring->stats.syncp);
 
-	netif_txq_completed_wake(txq, total_packets, total_bytes,
-				 fbnic_desc_unused(ring),
-				 FBNIC_TX_DESC_WAKEUP);
+	if (!netif_txq_completed_wake(txq, total_packets, total_bytes,
+				      fbnic_desc_unused(ring),
+				      FBNIC_TX_DESC_WAKEUP)) {
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.wake++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 }
 
 static void fbnic_clean_tsq(struct fbnic_napi_vector *nv,
@@ -1092,10 +1104,13 @@ void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
 	fbn->tx_stats.bytes += stats->bytes;
 	fbn->tx_stats.packets += stats->packets;
 	fbn->tx_stats.dropped += stats->dropped;
+	fbn->tx_stats.twq.csum_partial += stats->twq.csum_partial;
 	fbn->tx_stats.twq.ts_lost += stats->twq.ts_lost;
 	fbn->tx_stats.twq.ts_packets += stats->twq.ts_packets;
+	fbn->tx_stats.twq.stop += stats->twq.stop;
+	fbn->tx_stats.twq.wake += stats->twq.wake;
 	/* Remember to add new stats here */
-	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 2);
+	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 5);
 }
 
 static void fbnic_remove_tx_ring(struct fbnic_net *fbn,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index c9d9001042dc2..b53a7d28ecd36 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -58,8 +58,11 @@ struct fbnic_queue_stats {
 	u64 bytes;
 	union {
 		struct {
+			u64 csum_partial;
 			u64 ts_packets;
 			u64 ts_lost;
+			u64 stop;
+			u64 wake;
 		} twq;
 		struct {
 			u64 alloc_failed;

From 0ec023282a9d9487d5f80fd785b0c2e80a40ba43 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Feb 2025 10:13:56 -0800
Subject: [PATCH 0491/2753] eth: fbnic: re-sort the objects in the Makefile

Looks like recent commit broke the sort order, fix it.

Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Link: https://patch.msgid.link/20250211181356.580800-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/Makefile | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 239b2258ec658..0dbc634adb4b8 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -20,6 +20,7 @@ fbnic-y := fbnic_csr.o \
 	   fbnic_pci.o \
 	   fbnic_phylink.o \
 	   fbnic_rpc.o \
+	   fbnic_time.o \
 	   fbnic_tlv.o \
 	   fbnic_txrx.o \
-	   fbnic_time.o
+# End of objects

From 2001d21592e5eb531d23950223eedad55c987db8 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:36:44 +0000
Subject: [PATCH 0492/2753] net: phylink: provide phylink_mac_implements_lpi()

Provide a helper to determine whether the MAC operations structure
implements the LPI operations, which will be used by both phylink and
DSA.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thR9g-003vX6-4s@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c |  3 +--
 include/linux/phylink.h   | 12 ++++++++++++
 2 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 214b62fba991e..6fbb5fd5b400d 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1957,8 +1957,7 @@ struct phylink *phylink_create(struct phylink_config *config,
 		return ERR_PTR(-EINVAL);
 	}
 
-	pl->mac_supports_eee_ops = mac_ops->mac_disable_tx_lpi &&
-				   mac_ops->mac_enable_tx_lpi;
+	pl->mac_supports_eee_ops = phylink_mac_implements_lpi(mac_ops);
 	pl->mac_supports_eee = pl->mac_supports_eee_ops &&
 			       pl->config->lpi_capabilities &&
 			       !phy_interface_empty(pl->config->lpi_interfaces);
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 898b00451bbfd..0de78673172de 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -737,6 +737,18 @@ static inline int phylink_get_link_timer_ns(phy_interface_t interface)
 	}
 }
 
+/**
+ * phylink_mac_implements_lpi() - determine if MAC implements LPI ops
+ * @ops: phylink_mac_ops structure
+ *
+ * Returns true if the phylink MAC operations structure indicates that the
+ * LPI operations have been implemented, false otherwise.
+ */
+static inline bool phylink_mac_implements_lpi(const struct phylink_mac_ops *ops)
+{
+	return ops && ops->mac_disable_tx_lpi && ops->mac_enable_tx_lpi;
+}
+
 void phylink_mii_c22_pcs_decode_state(struct phylink_link_state *state,
 				      unsigned int neg_mode, u16 bmsr, u16 lpa);
 void phylink_mii_c22_pcs_get_state(struct mdio_device *pcs,

From b8927bd44f78eee1e754bb5d8c6db92732cd31dc Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:36:49 +0000
Subject: [PATCH 0493/2753] net: dsa: allow use of phylink managed EEE support

In order to allow DSA drivers to use phylink managed EEE, we need to
change the behaviour of the DSA's .set_eee() ethtool method.
Implementation of the DSA .set_mac_eee() method becomes optional with
phylink managed EEE as it is only used to validate the EEE parameters
supplied from userspace. The rest of the EEE state management should
be left to phylink.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thR9l-003vXC-9F@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dsa/user.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/net/dsa/user.c b/net/dsa/user.c
index 291ab1b4acc4d..2296a4ead0203 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -1243,16 +1243,25 @@ static int dsa_user_set_eee(struct net_device *dev, struct ethtool_keee *e)
 	if (!ds->ops->support_eee || !ds->ops->support_eee(ds, dp->index))
 		return -EOPNOTSUPP;
 
-	/* Port's PHY and MAC both need to be EEE capable */
-	if (!dev->phydev)
-		return -ENODEV;
+	/* If the port is using phylink managed EEE, then an unimplemented
+	 * set_mac_eee() is permissible.
+	 */
+	if (!phylink_mac_implements_lpi(ds->phylink_mac_ops)) {
+		/* Port's PHY and MAC both need to be EEE capable */
+		if (!dev->phydev)
+			return -ENODEV;
 
-	if (!ds->ops->set_mac_eee)
-		return -EOPNOTSUPP;
+		if (!ds->ops->set_mac_eee)
+			return -EOPNOTSUPP;
 
-	ret = ds->ops->set_mac_eee(ds, dp->index, e);
-	if (ret)
-		return ret;
+		ret = ds->ops->set_mac_eee(ds, dp->index, e);
+		if (ret)
+			return ret;
+	} else if (ds->ops->set_mac_eee) {
+		ret = ds->ops->set_mac_eee(ds, dp->index, e);
+		if (ret)
+			return ret;
+	}
 
 	return phylink_ethtool_set_eee(dp->pl, e);
 }

From 9cf21773f535d67d9301a8d2ef4f0c722deac5a1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:36:54 +0000
Subject: [PATCH 0494/2753] net: dsa: mt7530: convert to phylink managed EEE

Convert mt7530 to use phylink managed EEE. When enabling EEE, we set
both PMCR_FORCE_EEE1G and PMCR_FORCE_EEE100 irrespective of the speed,
and clear them both when disabling.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thR9q-003vXI-Cp@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mt7530.c | 68 +++++++++++++++++++++++++++-------------
 1 file changed, 47 insertions(+), 21 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1c83af805209c..9fd44e55d5196 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2957,28 +2957,61 @@ static void mt753x_phylink_mac_link_up(struct phylink_config *config,
 			mcr |= PMCR_FORCE_RX_FC_EN;
 	}
 
-	if (mode == MLO_AN_PHY && phydev && phy_init_eee(phydev, false) >= 0) {
-		switch (speed) {
-		case SPEED_1000:
-		case SPEED_2500:
-			mcr |= PMCR_FORCE_EEE1G;
-			break;
-		case SPEED_100:
-			mcr |= PMCR_FORCE_EEE100;
-			break;
-		}
-	}
-
 	mt7530_set(priv, MT753X_PMCR_P(dp->index), mcr);
 }
 
+static void mt753x_phylink_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct mt7530_priv *priv = dp->ds->priv;
+
+	mt7530_clear(priv, MT753X_PMCR_P(dp->index),
+		     PMCR_FORCE_EEE1G | PMCR_FORCE_EEE100);
+}
+
+static int mt753x_phylink_mac_enable_tx_lpi(struct phylink_config *config,
+					    u32 timer, bool tx_clock_stop)
+{
+	struct dsa_port *dp = dsa_phylink_to_port(config);
+	struct mt7530_priv *priv = dp->ds->priv;
+	u32 val;
+
+	/* If the timer is zero, then set LPI_MODE_EN, which allows the
+	 * system to enter LPI mode immediately rather than waiting for
+	 * the LPI threshold.
+	 */
+	if (!timer)
+		val = LPI_MODE_EN;
+	else if (FIELD_FIT(LPI_THRESH_MASK, timer))
+		val = FIELD_PREP(LPI_THRESH_MASK, timer);
+	else
+		val = LPI_THRESH_MASK;
+
+	mt7530_rmw(priv, MT753X_PMEEECR_P(dp->index),
+		   LPI_THRESH_MASK | LPI_MODE_EN, val);
+
+	mt7530_set(priv, MT753X_PMCR_P(dp->index),
+		   PMCR_FORCE_EEE1G | PMCR_FORCE_EEE100);
+
+	return 0;
+}
+
 static void mt753x_phylink_get_caps(struct dsa_switch *ds, int port,
 				    struct phylink_config *config)
 {
 	struct mt7530_priv *priv = ds->priv;
+	u32 eeecr;
 
 	config->mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE;
 
+	config->lpi_capabilities = MAC_100FD | MAC_1000FD | MAC_2500FD;
+
+	eeecr = mt7530_read(priv, MT753X_PMEEECR_P(port));
+	/* tx_lpi_timer should be in microseconds. The time units for
+	 * LPI threshold are unspecified.
+	 */
+	config->lpi_timer_default = FIELD_GET(LPI_THRESH_MASK, eeecr);
+
 	priv->info->mac_port_get_caps(ds, port, config);
 }
 
@@ -3088,18 +3121,9 @@ mt753x_setup(struct dsa_switch *ds)
 static int mt753x_set_mac_eee(struct dsa_switch *ds, int port,
 			      struct ethtool_keee *e)
 {
-	struct mt7530_priv *priv = ds->priv;
-	u32 set, mask = LPI_THRESH_MASK | LPI_MODE_EN;
-
 	if (e->tx_lpi_timer > 0xFFF)
 		return -EINVAL;
 
-	set = LPI_THRESH_SET(e->tx_lpi_timer);
-	if (!e->tx_lpi_enabled)
-		/* Force LPI Mode without a delay */
-		set |= LPI_MODE_EN;
-	mt7530_rmw(priv, MT753X_PMEEECR_P(port), mask, set);
-
 	return 0;
 }
 
@@ -3238,6 +3262,8 @@ static const struct phylink_mac_ops mt753x_phylink_mac_ops = {
 	.mac_config	= mt753x_phylink_mac_config,
 	.mac_link_down	= mt753x_phylink_mac_link_down,
 	.mac_link_up	= mt753x_phylink_mac_link_up,
+	.mac_disable_tx_lpi = mt753x_phylink_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mt753x_phylink_mac_enable_tx_lpi,
 };
 
 const struct mt753x_info mt753x_table[] = {

From 2151003e773c7e7dba4d64bed4bfc483681b5f6a Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:18 +0000
Subject: [PATCH 0495/2753] tools/net/ynl: remove extraneous plural from
 variable names

_decode_array_attr() uses variable subattrs in every branch when only
one branch decodes more than a single attribute.

Change the variable name to subattr in the branches that only decode a
single attribute so that the intent is more obvious.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-2-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/lib/ynl.py | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index 08f8bf89cfc20..8b39d8b1eaa8a 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -644,15 +644,15 @@ def _decode_array_attr(self, attr, attr_spec):
                 subattrs = self._decode(NlAttrs(item.raw), attr_spec['nested-attributes'])
                 decoded.append({ item.type: subattrs })
             elif attr_spec["sub-type"] == 'binary':
-                subattrs = item.as_bin()
+                subattr = item.as_bin()
                 if attr_spec.display_hint:
-                    subattrs = self._formatted_string(subattrs, attr_spec.display_hint)
-                decoded.append(subattrs)
+                    subattr = self._formatted_string(subattr, attr_spec.display_hint)
+                decoded.append(subattr)
             elif attr_spec["sub-type"] in NlAttr.type_formats:
-                subattrs = item.as_scalar(attr_spec['sub-type'], attr_spec.byte_order)
+                subattr = item.as_scalar(attr_spec['sub-type'], attr_spec.byte_order)
                 if attr_spec.display_hint:
-                    subattrs = self._formatted_string(subattrs, attr_spec.display_hint)
-                decoded.append(subattrs)
+                    subattr = self._formatted_string(subattr, attr_spec.display_hint)
+                decoded.append(subattr)
             else:
                 raise Exception(f'Unknown {attr_spec["sub-type"]} with name {attr_spec["name"]}')
         return decoded

From 678d8ddd0087a533c8eb06eabd0e3d25c02fcead Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:19 +0000
Subject: [PATCH 0496/2753] tools/net/ynl: support decoding indexed arrays as
 enums

When decoding an indexed-array with a scalar subtype, it is currently
only possible to add a display-hint. Add support for decoding each value
as an enum.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-3-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/lib/ynl.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index 8b39d8b1eaa8a..b73e07f1f60cd 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -650,7 +650,9 @@ def _decode_array_attr(self, attr, attr_spec):
                 decoded.append(subattr)
             elif attr_spec["sub-type"] in NlAttr.type_formats:
                 subattr = item.as_scalar(attr_spec['sub-type'], attr_spec.byte_order)
-                if attr_spec.display_hint:
+                if 'enum' in attr_spec:
+                    subattr = self._decode_enum(subattr, attr_spec)
+                elif attr_spec.display_hint:
                     subattr = self._formatted_string(subattr, attr_spec.display_hint)
                 decoded.append(subattr)
             else:

From 569a5d63fd1b2b106a2134625f4ee7a7f9056996 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:20 +0000
Subject: [PATCH 0497/2753] tools/net/ynl: support rendering C array members to
 strings

The nl80211 family encodes the list of supported ciphers as a C array of
u32 values. Add support for translating arrays of scalars into strings
for enum names and display hints.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-4-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/lib/ynl.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index b73e07f1f60cd..62ce3340796ff 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -627,6 +627,11 @@ def _decode_binary(self, attr, attr_spec):
             decoded = self._decode_struct(attr.raw, attr_spec.struct_name)
         elif attr_spec.sub_type:
             decoded = attr.as_c_array(attr_spec.sub_type)
+            if 'enum' in attr_spec:
+                decoded = [ self._decode_enum(x, attr_spec) for x in decoded ]
+            elif attr_spec.display_hint:
+                decoded = [ self._formatted_string(x, attr_spec.display_hint)
+                            for x in decoded ]
         else:
             decoded = attr.as_bin()
             if attr_spec.display_hint:

From c578bc3a00f1fe04fd56bbef1fc779a848827ed2 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:21 +0000
Subject: [PATCH 0498/2753] tools/net/ynl: accept IP string inputs

The ynl tool uses display-hint to know when to format IP addresses in
printed output, but not to parse IP addresses from --json input. Add
support for parsing ipv4 and ipv6 strings.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-5-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/lib/ynl.py | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/tools/net/ynl/pyynl/lib/ynl.py b/tools/net/ynl/pyynl/lib/ynl.py
index 62ce3340796ff..dcc2c6b298d60 100644
--- a/tools/net/ynl/pyynl/lib/ynl.py
+++ b/tools/net/ynl/pyynl/lib/ynl.py
@@ -536,9 +536,11 @@ def _get_scalar(self, attr_spec, value):
         try:
             return int(value)
         except (ValueError, TypeError) as e:
-            if 'enum' not in attr_spec:
-                raise e
-        return self._encode_enum(attr_spec, value)
+            if 'enum' in attr_spec:
+                return self._encode_enum(attr_spec, value)
+            if attr_spec.display_hint:
+                return self._from_string(value, attr_spec)
+            raise e
 
     def _add_attr(self, space, name, value, search_attrs):
         try:
@@ -571,7 +573,10 @@ def _add_attr(self, space, name, value, search_attrs):
             if isinstance(value, bytes):
                 attr_payload = value
             elif isinstance(value, str):
-                attr_payload = bytes.fromhex(value)
+                if attr.display_hint:
+                    attr_payload = self._from_string(value, attr)
+                else:
+                    attr_payload = bytes.fromhex(value)
             elif isinstance(value, dict) and attr.struct_name:
                 attr_payload = self._encode_struct(attr.struct_name, value)
             else:
@@ -906,6 +911,18 @@ def _formatted_string(self, raw, display_hint):
             formatted = raw
         return formatted
 
+    def _from_string(self, string, attr_spec):
+        if attr_spec.display_hint in ['ipv4', 'ipv6']:
+            ip = ipaddress.ip_address(string)
+            if attr_spec['type'] == 'binary':
+                raw = ip.packed
+            else:
+                raw = int(ip)
+        else:
+            raise Exception(f"Display hint '{attr_spec.display_hint}' not implemented"
+                            f" when parsing '{attr_spec['name']}'")
+        return raw
+
     def handle_ntf(self, decoded):
         msg = dict()
         if self.include_raw:

From 8798892b800f8f29573bbea759a122f92f83d32e Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:22 +0000
Subject: [PATCH 0499/2753] tools/net/ynl: add s8, s16 to valid scalars in
 ynl-gen-c

Add the missing s8 and s16 scalar types to the list of recognised
scalars in ynl-gen-c.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-6-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/ynl_gen_c.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index b22082fd660e9..d8fdee24ce257 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -1440,7 +1440,7 @@ def ifdef_block(self, config):
         self._ifdef_block = config_option
 
 
-scalars = {'u8', 'u16', 'u32', 'u64', 's32', 's64', 'uint', 'sint'}
+scalars = {'u8', 'u16', 'u32', 'u64', 's8', 's16', 's32', 's64', 'uint', 'sint'}
 
 direction_to_suffix = {
     'reply': '_rsp',

From 16cd1a5299eedc0328398bff9bf57e08b9925c52 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:23 +0000
Subject: [PATCH 0500/2753] tools/net/ynl: sanitise enums with leading digits
 in ynl-gen-c

Turn attribute names with leading digits into valid C names by
prepending an underscore, e.g. 5ghz -> _5ghz

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-7-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/ynl_gen_c.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index d8fdee24ce257..62a6d8c937652 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -74,6 +74,8 @@ def __init__(self, family, attr_set, attr, value):
         self.c_name = c_lower(self.name)
         if self.c_name in _C_KW:
             self.c_name += '_'
+        if self.c_name[0].isdigit():
+            self.c_name = '_' + self.c_name
 
         # Added by resolve():
         self.enum_name = None

From 9fcfc1e210a662cfbd67a76511b45abc2c72e482 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:24 +0000
Subject: [PATCH 0501/2753] tools/net/ynl: add indexed-array scalar support to
 ynl-gen-c

Extend ynl-gen-c.py with support for indexed-array that has a scalar
sub-type.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-8-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/net/ynl/pyynl/ynl_gen_c.py | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/tools/net/ynl/pyynl/ynl_gen_c.py b/tools/net/ynl/pyynl/ynl_gen_c.py
index 62a6d8c937652..a1427c5370302 100755
--- a/tools/net/ynl/pyynl/ynl_gen_c.py
+++ b/tools/net/ynl/pyynl/ynl_gen_c.py
@@ -688,7 +688,10 @@ def _complex_member_type(self, ri):
             raise Exception(f"Sub-type {self.attr['sub-type']} not supported yet")
 
     def _attr_typol(self):
-        return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
+        if self.attr['sub-type'] in scalars:
+            return f'.type = YNL_PT_U{c_upper(self.sub_type[1:])}, '
+        else:
+            return f'.type = YNL_PT_NEST, .nest = &{self.nested_render_name}_nest, '
 
     def _attr_get(self, ri, var):
         local_vars = ['const struct nlattr *attr2;']
@@ -890,7 +893,7 @@ def new_attr(self, elem, value):
         elif elem['type'] == 'nest':
             t = TypeNest(self.family, self, elem, value)
         elif elem['type'] == 'indexed-array' and 'sub-type' in elem:
-            if elem["sub-type"] == 'nest':
+            if elem["sub-type"] in ['nest', 'u32']:
                 t = TypeArrayNest(self.family, self, elem, value)
             else:
                 raise Exception(f'new_attr: unsupported sub-type {elem["sub-type"]}')
@@ -1674,6 +1677,9 @@ def _multi_parse(ri, struct, init_lines, local_vars):
             if aspec["sub-type"] == 'nest':
                 local_vars.append(f'const struct nlattr *attr_{aspec.c_name};')
                 array_nests.add(arg)
+            elif aspec['sub-type'] in scalars:
+                local_vars.append(f'const struct nlattr *attr_{aspec.c_name};')
+                array_nests.add(arg)
             else:
                 raise Exception(f'Not supported sub-type {aspec["sub-type"]}')
         if 'multi-attr' in aspec:
@@ -1729,11 +1735,17 @@ def _multi_parse(ri, struct, init_lines, local_vars):
         ri.cw.p(f"dst->{aspec.c_name} = calloc(n_{aspec.c_name}, sizeof(*dst->{aspec.c_name}));")
         ri.cw.p(f"dst->n_{aspec.c_name} = n_{aspec.c_name};")
         ri.cw.p('i = 0;')
-        ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
+        if 'nested-attributes' in aspec:
+            ri.cw.p(f"parg.rsp_policy = &{aspec.nested_render_name}_nest;")
         ri.cw.block_start(line=f"ynl_attr_for_each_nested(attr, attr_{aspec.c_name})")
-        ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];")
-        ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr, ynl_attr_type(attr)))")
-        ri.cw.p('return YNL_PARSE_CB_ERROR;')
+        if 'nested-attributes' in aspec:
+            ri.cw.p(f"parg.data = &dst->{aspec.c_name}[i];")
+            ri.cw.p(f"if ({aspec.nested_render_name}_parse(&parg, attr, ynl_attr_type(attr)))")
+            ri.cw.p('return YNL_PARSE_CB_ERROR;')
+        elif aspec.sub_type in scalars:
+            ri.cw.p(f"dst->{aspec.c_name}[i] = ynl_attr_get_{aspec.sub_type}(attr);")
+        else:
+            raise Exception(f"Nest parsing type not supported in {aspec['name']}")
         ri.cw.p('i++;')
         ri.cw.block_end()
         ri.cw.block_end()

From 718a8360719b2cbde73b627bf45801b1780caf32 Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:25 +0000
Subject: [PATCH 0502/2753] netlink: specs: support nested structs in genetlink
 legacy

Nested structs are already supported in netlink-raw. Add the same
capability to the genetlink legacy schema.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-9-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-legacy.yaml | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index ed64acf1bef77..c02ed80897460 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -152,6 +152,9 @@ properties:
                   the right formatting mechanism when displaying values of this
                   type.
                 enum: [ hex, mac, fddi, ipv4, ipv6, uuid ]
+              struct:
+                description: Name of the nested struct type.
+                type: string
         # End genetlink-legacy
 
   attribute-sets:

From fdb8050e1a873c87d99dc65a0468e257b632602e Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:26 +0000
Subject: [PATCH 0503/2753] netlink: specs: add s8, s16 to genetlink schemas

Add s8 and s16 types to the genetlink schemas to align scalar types
across all schemas.

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Link: https://patch.msgid.link/20250211120127.84858-10-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/genetlink-c.yaml      | 2 +-
 Documentation/netlink/genetlink-legacy.yaml | 2 +-
 Documentation/netlink/genetlink.yaml        | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/Documentation/netlink/genetlink-c.yaml b/Documentation/netlink/genetlink-c.yaml
index 44f2226160cab..96fa1f1522ed1 100644
--- a/Documentation/netlink/genetlink-c.yaml
+++ b/Documentation/netlink/genetlink-c.yaml
@@ -161,7 +161,7 @@ properties:
                 type: string
               type: &attr-type
                 enum: [ unused, pad, flag, binary,
-                        uint, sint, u8, u16, u32, u64, s32, s64,
+                        uint, sint, u8, u16, u32, u64, s8, s16, s32, s64,
                         string, nest, indexed-array, nest-type-value ]
               doc:
                 description: Documentation of the attribute.
diff --git a/Documentation/netlink/genetlink-legacy.yaml b/Documentation/netlink/genetlink-legacy.yaml
index c02ed80897460..a8c5b521937d1 100644
--- a/Documentation/netlink/genetlink-legacy.yaml
+++ b/Documentation/netlink/genetlink-legacy.yaml
@@ -207,7 +207,7 @@ properties:
               type: &attr-type
                 description: The netlink attribute type
                 enum: [ unused, pad, flag, binary, bitfield32,
-                        uint, sint, u8, u16, u32, u64, s32, s64,
+                        uint, sint, u8, u16, u32, u64, s8, s16, s32, s64,
                         string, nest, indexed-array, nest-type-value ]
               doc:
                 description: Documentation of the attribute.
diff --git a/Documentation/netlink/genetlink.yaml b/Documentation/netlink/genetlink.yaml
index e43e50dba2e48..40efbbad76ab8 100644
--- a/Documentation/netlink/genetlink.yaml
+++ b/Documentation/netlink/genetlink.yaml
@@ -124,7 +124,7 @@ properties:
                 type: string
               type: &attr-type
                 enum: [ unused, pad, flag, binary,
-                        uint, sint, u8, u16, u32, u64, s32, s64,
+                        uint, sint, u8, u16, u32, u64, s8, s16, s32, s64,
                         string, nest, indexed-array, nest-type-value ]
               doc:
                 description: Documentation of the attribute.

From 31438709ecdb12539fc48ad691c27c4c11c0a56b Mon Sep 17 00:00:00 2001
From: Donald Hunter <donald.hunter@gmail.com>
Date: Tue, 11 Feb 2025 12:01:27 +0000
Subject: [PATCH 0504/2753] netlink: specs: wireless: add a spec for nl80211

Add a rudimentary YNL spec for nl80211 that covers get-wiphy,
get-interface and get-protocol-features.

./tools/net/ynl/pyynl/cli.py --family nl80211 \
    --do get-protocol-features
{'protocol-features': {'split-wiphy-dump'}}

./tools/net/ynl/pyynl/cli.py --family nl80211 \
    --dump get-wiphy --json '{ "split-wiphy-dump": true }'

./tools/net/ynl/pyynl/cli.py --family nl80211 \
    --dump get-interface

Signed-off-by: Donald Hunter <donald.hunter@gmail.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Link: https://patch.msgid.link/20250211120127.84858-11-donald.hunter@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/nl80211.yaml | 2000 ++++++++++++++++++++++
 tools/net/ynl/Makefile.deps              |    1 +
 2 files changed, 2001 insertions(+)
 create mode 100644 Documentation/netlink/specs/nl80211.yaml

diff --git a/Documentation/netlink/specs/nl80211.yaml b/Documentation/netlink/specs/nl80211.yaml
new file mode 100644
index 0000000000000..1ec49c3562cdc
--- /dev/null
+++ b/Documentation/netlink/specs/nl80211.yaml
@@ -0,0 +1,2000 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: nl80211
+protocol: genetlink-legacy
+
+doc:
+  Netlink API for 802.11 wireless devices
+
+definitions:
+  -
+    name: commands
+    type: enum
+    entries:
+      - unspec
+      - get-wiphy
+      - set-wiphy
+      - new-wiphy
+      - del-wiphy
+      - get-interface
+      - set-interface
+      - new-interface
+      - del-interface
+      - get-key
+      - set-key
+      - new-key
+      - del-key
+      - get-beacon
+      - set-beacon
+      - new-beacon
+      - del-beacon
+      - get-station
+      - set-station
+      - new-station
+      - del-station
+      - get-mpath
+      - set-mpath
+      - new-mpath
+      - del-mpath
+      - set-bss
+      - set-reg
+      - req-set-reg
+      - get-mesh-config
+      - set-mesh-config
+      - set-mgmt-extra-ie
+      - get-reg
+      - get-scan
+      - trigger-scan
+      - new-scan-results
+      - scan-aborted
+      - reg-change
+      - authenticate
+      - associate
+      - deauthenticate
+      - disassociate
+      - michael-mic-failure
+      - reg-beacon-hint
+      - join-ibss
+      - leave-ibss
+      - testmode
+      - connect
+      - roam
+      - disconnect
+      - set-wiphy-netns
+      - get-survey
+      - new-survey-results
+      - set-pmksa
+      - del-pmksa
+      - flush-pmksa
+      - remain-on-channel
+      - cancel-remain-on-channel
+      - set-tx-bitrate-mask
+      - register-action
+      - action
+      - action-tx-status
+      - set-power-save
+      - get-power-save
+      - set-cqm
+      - notify-cqm
+      - set-channel
+      - set-wds-peer
+      - frame-wait-cancel
+      - join-mesh
+      - leave-mesh
+      - unprot-deauthenticate
+      - unprot-disassociate
+      - new-peer-candidate
+      - get-wowlan
+      - set-wowlan
+      - start-sched-scan
+      - stop-sched-scan
+      - sched-scan-results
+      - sched-scan-stopped
+      - set-rekey-offload
+      - pmksa-candidate
+      - tdls-oper
+      - tdls-mgmt
+      - unexpected-frame
+      - probe-client
+      - register-beacons
+      - unexpected-4-addr-frame
+      - set-noack-map
+      - ch-switch-notify
+      - start-p2p-device
+      - stop-p2p-device
+      - conn-failed
+      - set-mcast-rate
+      - set-mac-acl
+      - radar-detect
+      - get-protocol-features
+      - update-ft-ies
+      - ft-event
+      - crit-protocol-start
+      - crit-protocol-stop
+      - get-coalesce
+      - set-coalesce
+      - channel-switch
+      - vendor
+      - set-qos-map
+      - add-tx-ts
+      - del-tx-ts
+      - get-mpp
+      - join-ocb
+      - leave-ocb
+      - ch-switch-started-notify
+      - tdls-channel-switch
+      - tdls-cancel-channel-switch
+      - wiphy-reg-change
+      - abort-scan
+      - start-nan
+      - stop-nan
+      - add-nan-function
+      - del-nan-function
+      - change-nan-config
+      - nan-match
+      - set-multicast-to-unicast
+      - update-connect-params
+      - set-pmk
+      - del-pmk
+      - port-authorized
+      - reload-regdb
+      - external-auth
+      - sta-opmode-changed
+      - control-port-frame
+      - get-ftm-responder-stats
+      - peer-measurement-start
+      - peer-measurement-result
+      - peer-measurement-complete
+      - notify-radar
+      - update-owe-info
+      - probe-mesh-link
+      - set-tid-config
+      - unprot-beacon
+      - control-port-frame-tx-status
+      - set-sar-specs
+      - obss-color-collision
+      - color-change-request
+      - color-change-started
+      - color-change-aborted
+      - color-change-completed
+      - set-fils-aad
+      - assoc-comeback
+      - add-link
+      - remove-link
+      - add-link-sta
+      - modify-link-sta
+      - remove-link-sta
+      - set-hw-timestamp
+      - links-removed
+      - set-tid-to-link-mapping
+  -
+    name: feature-flags
+    type: flags
+    entries:
+      - sk-tx-status
+      - ht-ibss
+      - inactivity-timer
+      - cell-base-reg-hints
+      - p2p-device-needs-channel
+      - sae
+      - low-priority-scan
+      - scan-flush
+      - ap-scan
+      - vif-txpower
+      - need-obss-scan
+      - p2p-go-ctwin
+      - p2p-go-oppps
+      - reserved
+      - advertise-chan-limits
+      - full-ap-client-state
+      - userspace-mpm
+      - active-monitor
+      - ap-mode-chan-width-change
+      - ds-param-set-ie-in-probes
+      - wfa-tpc-ie-in-probes
+      - quiet
+      - tx-power-insertion
+      - ackto-estimation
+      - static-smps
+      - dynamic-smps
+      - supports-wmm-admission
+      - mac-on-create
+      - tdls-channel-switch
+      - scan-random-mac-addr
+      - sched-scan-random-mac-addr
+      - no-random-mac-addr
+  -
+    name: ieee80211-mcs-info
+    type: struct
+    members:
+      -
+        name: rx-mask
+        type: binary
+        len: 10
+      -
+        name: rx-highest
+        type: u16
+        byte-order: little-endian
+      -
+        name: tx-params
+        type: u8
+      -
+        name: reserved
+        type: binary
+        len: 3
+  -
+    name: ieee80211-vht-mcs-info
+    type: struct
+    members:
+      -
+        name: rx-mcs-map
+        type: u16
+        byte-order: little-endian
+      -
+        name: rx-highest
+        type: u16
+        byte-order: little-endian
+      -
+        name: tx-mcs-map
+        type: u16
+        byte-order: little-endian
+      -
+        name: tx-highest
+        type: u16
+        byte-order: little-endian
+  -
+    name: ieee80211-ht-cap
+    type: struct
+    members:
+      -
+        name: cap-info
+        type: u16
+        byte-order: little-endian
+      -
+        name: ampdu-params-info
+        type: u8
+      -
+        name: mcs
+        type: binary
+        struct: ieee80211-mcs-info
+      -
+        name: extended-ht-cap-info
+        type: u16
+        byte-order: little-endian
+      -
+        name: tx-bf-cap-info
+        type: u32
+        byte-order: little-endian
+      -
+        name: antenna-selection-info
+        type: u8
+  -
+    name: channel-type
+    type: enum
+    entries:
+      - no-ht
+      - ht20
+      - ht40minus
+      - ht40plus
+  -
+    name: sta-flag-update
+    type: struct
+    members:
+      -
+        name: mask
+        type: u32
+      -
+        name: set
+        type: u32
+  -
+    name: protocol-features
+    type: flags
+    entries:
+      - split-wiphy-dump
+
+attribute-sets:
+  -
+    name: nl80211-attrs
+    name-prefix: nl80211-attr-
+    enum-name: nl80211-attrs
+    attr-max-name: num-nl80211-attr
+    attributes:
+      -
+        name: wiphy
+        type: u32
+      -
+        name: wiphy-name
+        type: string
+      -
+        name: ifindex
+        type: u32
+      -
+        name: ifname
+        type: string
+      -
+        name: iftype
+        type: u32
+      -
+        name: mac
+        type: binary
+        display-hint: mac
+      -
+        name: key-data
+        type: binary
+      -
+        name: key-idx
+        type: u8
+      -
+        name: key-cipher
+        type: u32
+      -
+        name: key-seq
+        type: binary
+      -
+        name: key-default
+        type: flag
+      -
+        name: beacon-interval
+        type: u32
+      -
+        name: dtim-period
+        type: u32
+      -
+        name: beacon-head
+        type: binary
+      -
+        name: beacon-tail
+        type: binary
+      -
+        name: sta-aid
+        type: u16
+      -
+        name: sta-flags
+        type: binary # TODO: nest
+      -
+        name: sta-listen-interval
+        type: u16
+      -
+        name: sta-supported-rates
+        type: binary
+      -
+        name: sta-vlan
+        type: u32
+      -
+        name: sta-info
+        type: binary # TODO: nest
+      -
+        name: wiphy-bands
+        type: nest
+        nested-attributes: wiphy-bands
+      -
+        name: mntr-flags
+        type: binary # TODO: nest
+      -
+        name: mesh-id
+        type: binary
+      -
+        name: sta-plink-action
+        type: u8
+      -
+        name: mpath-next-hop
+        type: binary
+        display-hint: mac
+      -
+        name: mpath-info
+        type: binary # TODO: nest
+      -
+        name: bss-cts-prot
+        type: u8
+      -
+        name: bss-short-preamble
+        type: u8
+      -
+        name: bss-short-slot-time
+        type: u8
+      -
+        name: ht-capability
+        type: binary
+      -
+        name: supported-iftypes
+        type: nest
+        nested-attributes: supported-iftypes
+      -
+        name: reg-alpha2
+        type: binary
+      -
+        name: reg-rules
+        type: binary # TODO: nest
+      -
+        name: mesh-config
+        type: binary # TODO: nest
+      -
+        name: bss-basic-rates
+        type: binary
+      -
+        name: wiphy-txq-params
+        type: binary # TODO: nest
+      -
+        name: wiphy-freq
+        type: u32
+      -
+        name: wiphy-channel-type
+        type: u32
+        enum: channel-type
+      -
+        name: key-default-mgmt
+        type: flag
+      -
+        name: mgmt-subtype
+        type: u8
+      -
+        name: ie
+        type: binary
+      -
+        name: max-num-scan-ssids
+        type: u8
+      -
+        name: scan-frequencies
+        type: binary # TODO: nest
+      -
+        name: scan-ssids
+        type: binary # TODO: nest
+      -
+        name: generation
+        type: u32
+      -
+        name: bss
+        type: binary # TODO: nest
+      -
+        name: reg-initiator
+        type: u8
+      -
+        name: reg-type
+        type: u8
+      -
+        name: supported-commands
+        type: indexed-array
+        sub-type: u32
+        enum: commands
+      -
+        name: frame
+        type: binary
+      -
+        name: ssid
+        type: binary
+      -
+        name: auth-type
+        type: u32
+      -
+        name: reason-code
+        type: u16
+      -
+        name: key-type
+        type: u32
+      -
+        name: max-scan-ie-len
+        type: u16
+      -
+        name: cipher-suites
+        type: binary
+        sub-type: u32
+        display-hint: hex
+      -
+        name: freq-before
+        type: binary # TODO: nest
+      -
+        name: freq-after
+        type: binary # TODO: nest
+      -
+        name: freq-fixed
+        type: flag
+      -
+        name: wiphy-retry-short
+        type: u8
+      -
+        name: wiphy-retry-long
+        type: u8
+      -
+        name: wiphy-frag-threshold
+        type: u32
+      -
+        name: wiphy-rts-threshold
+        type: u32
+      -
+        name: timed-out
+        type: flag
+      -
+        name: use-mfp
+        type: u32
+      -
+        name: sta-flags2
+        type: binary
+        struct: sta-flag-update
+      -
+        name: control-port
+        type: flag
+      -
+        name: testdata
+        type: binary
+      -
+        name: privacy
+        type: flag
+      -
+        name: disconnected-by-ap
+        type: flag
+      -
+        name: status-code
+        type: u16
+      -
+        name: cipher-suites-pairwise
+        type: binary
+      -
+        name: cipher-suite-group
+        type: u32
+      -
+        name: wpa-versions
+        type: u32
+      -
+        name: akm-suites
+        type: binary
+      -
+        name: req-ie
+        type: binary
+      -
+        name: resp-ie
+        type: binary
+      -
+        name: prev-bssid
+        type: binary
+      -
+        name: key
+        type: binary # TODO: nest
+      -
+        name: keys
+        type: binary # TODO: nest
+      -
+        name: pid
+        type: u32
+      -
+        name: 4addr
+        type: u8
+      -
+        name: survey-info
+        type: binary # TODO: nest
+      -
+        name: pmkid
+        type: binary
+      -
+        name: max-num-pmkids
+        type: u8
+      -
+        name: duration
+        type: u32
+      -
+        name: cookie
+        type: u64
+      -
+        name: wiphy-coverage-class
+        type: u8
+      -
+        name: tx-rates
+        type: binary # TODO: nest
+      -
+        name: frame-match
+        type: binary
+      -
+        name: ack
+        type: flag
+      -
+        name: ps-state
+        type: u32
+      -
+        name: cqm
+        type: binary # TODO: nest
+      -
+        name: local-state-change
+        type: flag
+      -
+        name: ap-isolate
+        type: u8
+      -
+        name: wiphy-tx-power-setting
+        type: u32
+      -
+        name: wiphy-tx-power-level
+        type: u32
+      -
+        name: tx-frame-types
+        type: nest
+        nested-attributes: iftype-attrs
+      -
+        name: rx-frame-types
+        type: nest
+        nested-attributes: iftype-attrs
+      -
+        name: frame-type
+        type: u16
+      -
+        name: control-port-ethertype
+        type: flag
+      -
+        name: control-port-no-encrypt
+        type: flag
+      -
+        name: support-ibss-rsn
+        type: flag
+      -
+        name: wiphy-antenna-tx
+        type: u32
+      -
+        name: wiphy-antenna-rx
+        type: u32
+      -
+        name: mcast-rate
+        type: u32
+      -
+        name: offchannel-tx-ok
+        type: flag
+      -
+        name: bss-ht-opmode
+        type: u16
+      -
+        name: key-default-types
+        type: binary # TODO: nest
+      -
+        name: max-remain-on-channel-duration
+        type: u32
+      -
+        name: mesh-setup
+        type: binary # TODO: nest
+      -
+        name: wiphy-antenna-avail-tx
+        type: u32
+      -
+        name: wiphy-antenna-avail-rx
+        type: u32
+      -
+        name: support-mesh-auth
+        type: flag
+      -
+        name: sta-plink-state
+        type: u8
+      -
+        name: wowlan-triggers
+        type: binary # TODO: nest
+      -
+        name: wowlan-triggers-supported
+        type: nest
+        nested-attributes: wowlan-triggers-attrs
+      -
+        name: sched-scan-interval
+        type: u32
+      -
+        name: interface-combinations
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: if-combination-attributes
+      -
+        name: software-iftypes
+        type: nest
+        nested-attributes: supported-iftypes
+      -
+        name: rekey-data
+        type: binary # TODO: nest
+      -
+        name: max-num-sched-scan-ssids
+        type: u8
+      -
+        name: max-sched-scan-ie-len
+        type: u16
+      -
+        name: scan-supp-rates
+        type: binary # TODO: nest
+      -
+        name: hidden-ssid
+        type: u32
+      -
+        name: ie-probe-resp
+        type: binary
+      -
+        name: ie-assoc-resp
+        type: binary
+      -
+        name: sta-wme
+        type: binary # TODO: nest
+      -
+        name: support-ap-uapsd
+        type: flag
+      -
+        name: roam-support
+        type: flag
+      -
+        name: sched-scan-match
+        type: binary # TODO: nest
+      -
+        name: max-match-sets
+        type: u8
+      -
+        name: pmksa-candidate
+        type: binary # TODO: nest
+      -
+        name: tx-no-cck-rate
+        type: flag
+      -
+        name: tdls-action
+        type: u8
+      -
+        name: tdls-dialog-token
+        type: u8
+      -
+        name: tdls-operation
+        type: u8
+      -
+        name: tdls-support
+        type: flag
+      -
+        name: tdls-external-setup
+        type: flag
+      -
+        name: device-ap-sme
+        type: u32
+      -
+        name: dont-wait-for-ack
+        type: flag
+      -
+        name: feature-flags
+        type: u32
+        enum: feature-flags
+        enum-as-flags: True
+      -
+        name: probe-resp-offload
+        type: u32
+      -
+        name: probe-resp
+        type: binary
+      -
+        name: dfs-region
+        type: u8
+      -
+        name: disable-ht
+        type: flag
+      -
+        name: ht-capability-mask
+        type: binary
+        struct: ieee80211-ht-cap
+      -
+        name: noack-map
+        type: u16
+      -
+        name: inactivity-timeout
+        type: u16
+      -
+        name: rx-signal-dbm
+        type: u32
+      -
+        name: bg-scan-period
+        type: u16
+      -
+        name: wdev
+        type: u64
+      -
+        name: user-reg-hint-type
+        type: u32
+      -
+        name: conn-failed-reason
+        type: u32
+      -
+        name: auth-data
+        type: binary
+      -
+        name: vht-capability
+        type: binary
+      -
+        name: scan-flags
+        type: u32
+      -
+        name: channel-width
+        type: u32
+      -
+        name: center-freq1
+        type: u32
+      -
+        name: center-freq2
+        type: u32
+      -
+        name: p2p-ctwindow
+        type: u8
+      -
+        name: p2p-oppps
+        type: u8
+      -
+        name: local-mesh-power-mode
+        type: u32
+      -
+        name: acl-policy
+        type: u32
+      -
+        name: mac-addrs
+        type: binary # TODO: nest
+      -
+        name: mac-acl-max
+        type: u32
+      -
+        name: radar-event
+        type: u32
+      -
+        name: ext-capa
+        type: binary
+      -
+        name: ext-capa-mask
+        type: binary
+      -
+        name: sta-capability
+        type: u16
+      -
+        name: sta-ext-capability
+        type: binary
+      -
+        name: protocol-features
+        type: u32
+        enum: protocol-features
+      -
+        name: split-wiphy-dump
+        type: flag
+      -
+        name: disable-vht
+        type: flag
+      -
+        name: vht-capability-mask
+        type: binary
+      -
+        name: mdid
+        type: u16
+      -
+        name: ie-ric
+        type: binary
+      -
+        name: crit-prot-id
+        type: u16
+      -
+        name: max-crit-prot-duration
+        type: u16
+      -
+        name: peer-aid
+        type: u16
+      -
+        name: coalesce-rule
+        type: binary # TODO: nest
+      -
+        name: ch-switch-count
+        type: u32
+      -
+        name: ch-switch-block-tx
+        type: flag
+      -
+        name: csa-ies
+        type: binary # TODO: nest
+      -
+        name: cntdwn-offs-beacon
+        type: binary
+      -
+        name: cntdwn-offs-presp
+        type: binary
+      -
+        name: rxmgmt-flags
+        type: binary
+      -
+        name: sta-supported-channels
+        type: binary
+      -
+        name: sta-supported-oper-classes
+        type: binary
+      -
+        name: handle-dfs
+        type: flag
+      -
+        name: support-5-mhz
+        type: flag
+      -
+        name: support-10-mhz
+        type: flag
+      -
+        name: opmode-notif
+        type: u8
+      -
+        name: vendor-id
+        type: u32
+      -
+        name: vendor-subcmd
+        type: u32
+      -
+        name: vendor-data
+        type: binary
+      -
+        name: vendor-events
+        type: binary
+      -
+        name: qos-map
+        type: binary
+      -
+        name: mac-hint
+        type: binary
+        display-hint: mac
+      -
+        name: wiphy-freq-hint
+        type: u32
+      -
+        name: max-ap-assoc-sta
+        type: u32
+      -
+        name: tdls-peer-capability
+        type: u32
+      -
+        name: socket-owner
+        type: flag
+      -
+        name: csa-c-offsets-tx
+        type: binary
+      -
+        name: max-csa-counters
+        type: u8
+      -
+        name: tdls-initiator
+        type: flag
+      -
+        name: use-rrm
+        type: flag
+      -
+        name: wiphy-dyn-ack
+        type: flag
+      -
+        name: tsid
+        type: u8
+      -
+        name: user-prio
+        type: u8
+      -
+        name: admitted-time
+        type: u16
+      -
+        name: smps-mode
+        type: u8
+      -
+        name: oper-class
+        type: u8
+      -
+        name: mac-mask
+        type: binary
+        display-hint: mac
+      -
+        name: wiphy-self-managed-reg
+        type: flag
+      -
+        name: ext-features
+        type: binary
+      -
+        name: survey-radio-stats
+        type: binary
+      -
+        name: netns-fd
+        type: u32
+      -
+        name: sched-scan-delay
+        type: u32
+      -
+        name: reg-indoor
+        type: flag
+      -
+        name: max-num-sched-scan-plans
+        type: u32
+      -
+        name: max-scan-plan-interval
+        type: u32
+      -
+        name: max-scan-plan-iterations
+        type: u32
+      -
+        name: sched-scan-plans
+        type: binary # TODO: nest
+      -
+        name: pbss
+        type: flag
+      -
+        name: bss-select
+        type: binary # TODO: nest
+      -
+        name: sta-support-p2p-ps
+        type: u8
+      -
+        name: pad
+        type: binary
+      -
+        name: iftype-ext-capa
+        type: binary # TODO: nest
+      -
+        name: mu-mimo-group-data
+        type: binary
+      -
+        name: mu-mimo-follow-mac-addr
+        type: binary
+        display-hint: mac
+      -
+        name: scan-start-time-tsf
+        type: u64
+      -
+        name: scan-start-time-tsf-bssid
+        type: binary
+      -
+        name: measurement-duration
+        type: u16
+      -
+        name: measurement-duration-mandatory
+        type: flag
+      -
+        name: mesh-peer-aid
+        type: u16
+      -
+        name: nan-master-pref
+        type: u8
+      -
+        name: bands
+        type: u32
+      -
+        name: nan-func
+        type: binary # TODO: nest
+      -
+        name: nan-match
+        type: binary # TODO: nest
+      -
+        name: fils-kek
+        type: binary
+      -
+        name: fils-nonces
+        type: binary
+      -
+        name: multicast-to-unicast-enabled
+        type: flag
+      -
+        name: bssid
+        type: binary
+        display-hint: mac
+      -
+        name: sched-scan-relative-rssi
+        type: s8
+      -
+        name: sched-scan-rssi-adjust
+        type: binary
+      -
+        name: timeout-reason
+        type: u32
+      -
+        name: fils-erp-username
+        type: binary
+      -
+        name: fils-erp-realm
+        type: binary
+      -
+        name: fils-erp-next-seq-num
+        type: u16
+      -
+        name: fils-erp-rrk
+        type: binary
+      -
+        name: fils-cache-id
+        type: binary
+      -
+        name: pmk
+        type: binary
+      -
+        name: sched-scan-multi
+        type: flag
+      -
+        name: sched-scan-max-reqs
+        type: u32
+      -
+        name: want-1x-4way-hs
+        type: flag
+      -
+        name: pmkr0-name
+        type: binary
+      -
+        name: port-authorized
+        type: binary
+      -
+        name: external-auth-action
+        type: u32
+      -
+        name: external-auth-support
+        type: flag
+      -
+        name: nss
+        type: u8
+      -
+        name: ack-signal
+        type: s32
+      -
+        name: control-port-over-nl80211
+        type: flag
+      -
+        name: txq-stats
+        type: nest
+        nested-attributes: txq-stats-attrs
+      -
+        name: txq-limit
+        type: u32
+      -
+        name: txq-memory-limit
+        type: u32
+      -
+        name: txq-quantum
+        type: u32
+      -
+        name: he-capability
+        type: binary
+      -
+        name: ftm-responder
+        type: binary # TODO: nest
+      -
+        name: ftm-responder-stats
+        type: binary # TODO: nest
+      -
+        name: timeout
+        type: u32
+      -
+        name: peer-measurements
+        type: binary # TODO: nest
+      -
+        name: airtime-weight
+        type: u16
+      -
+        name: sta-tx-power-setting
+        type: u8
+      -
+        name: sta-tx-power
+        type: s16
+      -
+        name: sae-password
+        type: binary
+      -
+        name: twt-responder
+        type: flag
+      -
+        name: he-obss-pd
+        type: binary # TODO: nest
+      -
+        name: wiphy-edmg-channels
+        type: u8
+      -
+        name: wiphy-edmg-bw-config
+        type: u8
+      -
+        name: vlan-id
+        type: u16
+      -
+        name: he-bss-color
+        type: binary # TODO: nest
+      -
+        name: iftype-akm-suites
+        type: binary # TODO: nest
+      -
+        name: tid-config
+        type: binary # TODO: nest
+      -
+        name: control-port-no-preauth
+        type: flag
+      -
+        name: pmk-lifetime
+        type: u32
+      -
+        name: pmk-reauth-threshold
+        type: u8
+      -
+        name: receive-multicast
+        type: flag
+      -
+        name: wiphy-freq-offset
+        type: u32
+      -
+        name: center-freq1-offset
+        type: u32
+      -
+        name: scan-freq-khz
+        type: binary # TODO: nest
+      -
+        name: he-6ghz-capability
+        type: binary
+      -
+        name: fils-discovery
+        type: binary # TOOD: nest
+      -
+        name: unsol-bcast-probe-resp
+        type: binary # TOOD: nest
+      -
+        name: s1g-capability
+        type: binary
+      -
+        name: s1g-capability-mask
+        type: binary
+      -
+        name: sae-pwe
+        type: u8
+      -
+        name: reconnect-requested
+        type: binary
+      -
+        name: sar-spec
+        type: nest
+        nested-attributes: sar-attributes
+      -
+        name: disable-he
+        type: flag
+      -
+        name: obss-color-bitmap
+        type: u64
+      -
+        name: color-change-count
+        type: u8
+      -
+        name: color-change-color
+        type: u8
+      -
+        name: color-change-elems
+        type: binary # TODO: nest
+      -
+        name: mbssid-config
+        type: binary # TODO: nest
+      -
+        name: mbssid-elems
+        type: binary # TODO: nest
+      -
+        name: radar-background
+        type: flag
+      -
+        name: ap-settings-flags
+        type: u32
+      -
+        name: eht-capability
+        type: binary
+      -
+        name: disable-eht
+        type: flag
+      -
+        name: mlo-links
+        type: binary # TODO: nest
+      -
+        name: mlo-link-id
+        type: u8
+      -
+        name: mld-addr
+        type: binary
+        display-hint: mac
+      -
+        name: mlo-support
+        type: flag
+      -
+        name: max-num-akm-suites
+        type: binary
+      -
+        name: eml-capability
+        type: u16
+      -
+        name: mld-capa-and-ops
+        type: u16
+      -
+        name: tx-hw-timestamp
+        type: u64
+      -
+        name: rx-hw-timestamp
+        type: u64
+      -
+        name: td-bitmap
+        type: binary
+      -
+        name: punct-bitmap
+        type: u32
+      -
+        name: max-hw-timestamp-peers
+        type: u16
+      -
+        name: hw-timestamp-enabled
+        type: flag
+      -
+        name: ema-rnr-elems
+        type: binary # TODO: nest
+      -
+        name: mlo-link-disabled
+        type: flag
+      -
+        name: bss-dump-include-use-data
+        type: flag
+      -
+        name: mlo-ttlm-dlink
+        type: u16
+      -
+        name: mlo-ttlm-ulink
+        type: u16
+      -
+        name: assoc-spp-amsdu
+        type: flag
+      -
+        name: wiphy-radios
+        type: binary # TODO: nest
+      -
+        name: wiphy-interface-combinations
+        type: binary # TODO: nest
+      -
+        name: vif-radio-mask
+        type: u32
+  -
+    name: frame-type-attrs
+    subset-of: nl80211-attrs
+    attributes:
+      -
+        name: frame-type
+  -
+    name: wiphy-bands
+    name-prefix: nl80211-band-
+    attr-max-name: num-nl80211-bands
+    attributes:
+      -
+        name: 2ghz
+        doc: 2.4 GHz ISM band
+        value: 0
+        type: nest
+        nested-attributes: band-attrs
+      -
+        name: 5ghz
+        doc: around 5 GHz band (4.9 - 5.7 GHz)
+        type: nest
+        nested-attributes: band-attrs
+      -
+        name: 60ghz
+        doc: around 60 GHz band (58.32 - 69.12 GHz)
+        type: nest
+        nested-attributes: band-attrs
+      -
+        name: 6ghz
+        type: nest
+        nested-attributes: band-attrs
+      -
+        name: s1ghz
+        type: nest
+        nested-attributes: band-attrs
+      -
+        name: lc
+        type: nest
+        nested-attributes: band-attrs
+  -
+    name: band-attrs
+    enum-name: nl80211-band-attr
+    name-prefix: nl80211-band-attr-
+    attributes:
+      -
+        name: freqs
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: frequency-attrs
+      -
+        name: rates
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: bitrate-attrs
+      -
+        name: ht-mcs-set
+        type: binary
+        struct: ieee80211-mcs-info
+      -
+        name: ht-capa
+        type: u16
+      -
+        name: ht-ampdu-factor
+        type: u8
+      -
+        name: ht-ampdu-density
+        type: u8
+      -
+        name: vht-mcs-set
+        type: binary
+        struct: ieee80211-vht-mcs-info
+      -
+        name: vht-capa
+        type: u32
+      -
+        name: iftype-data
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: iftype-data-attrs
+      -
+        name: edmg-channels
+        type: binary
+      -
+        name: edmg-bw-config
+        type: binary
+      -
+        name: s1g-mcs-nss-set
+        type: binary
+      -
+        name: s1g-capa
+        type: binary
+  -
+    name: bitrate-attrs
+    name-prefix: nl80211-bitrate-attr-
+    attributes:
+      -
+        name: rate
+        type: u32
+      -
+        name: 2ghz-shortpreamble
+        type: flag
+  -
+    name: frequency-attrs
+    name-prefix: nl80211-frequency-attr-
+    attributes:
+      -
+        name: freq
+        type: u32
+      -
+        name: disabled
+        type: flag
+      -
+        name: no-ir
+        type: flag
+      -
+        name: no-ibss
+        name-prefix: __nl80211-frequency-attr-
+        type: flag
+      -
+        name: radar
+        type: flag
+      -
+        name: max-tx-power
+        type: u32
+      -
+        name: dfs-state
+        type: u32
+      -
+        name: dfs-time
+        type: binary
+      -
+        name: no-ht40-minus
+        type: binary
+      -
+        name: no-ht40-plus
+        type: binary
+      -
+        name: no-80mhz
+        type: binary
+      -
+        name: no-160mhz
+        type: binary
+      -
+        name: dfs-cac-time
+        type: binary
+      -
+        name: indoor-only
+        type: binary
+      -
+        name: ir-concurrent
+        type: binary
+      -
+        name: no-20mhz
+        type: binary
+      -
+        name: no-10mhz
+        type: binary
+      -
+        name: wmm
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: wmm-attrs
+      -
+        name: no-he
+        type: binary
+      -
+        name: offset
+        type: u32
+      -
+        name: 1mhz
+        type: binary
+      -
+        name: 2mhz
+        type: binary
+      -
+        name: 4mhz
+        type: binary
+      -
+        name: 8mhz
+        type: binary
+      -
+        name: 16mhz
+        type: binary
+      -
+        name: no-320mhz
+        type: binary
+      -
+        name: no-eht
+        type: binary
+      -
+        name: psd
+        type: binary
+      -
+        name: dfs-concurrent
+        type: binary
+      -
+        name: no-6ghz-vlp-client
+        type: binary
+      -
+        name: no-6ghz-afc-client
+        type: binary
+      -
+        name: can-monitor
+        type: binary
+      -
+        name: allow-6ghz-vlp-ap
+        type: binary
+  -
+    name: if-combination-attributes
+    enum-name: nl80211-if-combination-attrs
+    name-prefix: nl80211-iface-comb-
+    attr-max-name: max-nl80211-iface-comb
+    attributes:
+      -
+        name: limits
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: iface-limit-attributes
+      -
+        name: maxnum
+        type: u32
+      -
+        name: sta-ap-bi-match
+        type: flag
+      -
+        name: num-channels
+        type: u32
+      -
+        name: radar-detect-widths
+        type: u32
+      -
+        name: radar-detect-regions
+        type: u32
+      -
+        name: bi-min-gcd
+        type: u32
+  -
+    name: iface-limit-attributes
+    enum-name: nl80211-iface-limit-attrs
+    name-prefix: nl80211-iface-limit-
+    attr-max-name: max-nl80211-iface-limit
+    attributes:
+      -
+        name: max
+        type: u32
+      -
+        name: types
+        type: nest
+        nested-attributes: supported-iftypes
+  -
+    name: iftype-data-attrs
+    name-prefix: nl80211-band-iftype-attr-
+    attributes:
+      -
+        name: iftypes
+        type: binary
+      -
+        name: he-cap-mac
+        type: binary
+      -
+        name: he-cap-phy
+        type: binary
+      -
+        name: he-cap-mcs-set
+        type: binary
+      -
+        name: he-cap-ppe
+        type: binary
+      -
+        name: he-6ghz-capa
+        type: binary
+      -
+        name: vendor-elems
+        type: binary
+      -
+        name: eht-cap-mac
+        type: binary
+      -
+        name: eht-cap-phy
+        type: binary
+      -
+        name: eht-cap-mcs-set
+        type: binary
+      -
+        name: eht-cap-ppe
+        type: binary
+  -
+    name: iftype-attrs
+    enum-name: nl80211-iftype
+    name-prefix: nl80211-iftype-
+    attributes:
+      -
+        name: unspecified
+        type: nest
+        value: 0
+        nested-attributes: frame-type-attrs
+      -
+        name: adhoc
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: station
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: ap
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: ap-vlan
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: wds
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: monitor
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: mesh-point
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: p2p-client
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: p2p-go
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: p2p-device
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: ocb
+        type: nest
+        nested-attributes: frame-type-attrs
+      -
+        name: nan
+        type: nest
+        nested-attributes: frame-type-attrs
+  -
+    name: sar-attributes
+    enum-name: nl80211-sar-attrs
+    name-prefix: nl80211-sar-attr-
+    attributes:
+      -
+        name: type
+        type: u32
+      -
+        name: specs
+        type: indexed-array
+        sub-type: nest
+        nested-attributes: sar-specs
+  -
+    name: sar-specs
+    enum-name: nl80211-sar-specs-attrs
+    name-prefix: nl80211-sar-attr-specs-
+    attributes:
+      -
+        name: power
+        type: s32
+      -
+        name: range-index
+        type: u32
+      -
+        name: start-freq
+        type: u32
+      -
+        name: end-freq
+        type: u32
+  -
+    name: supported-iftypes
+    enum-name: nl80211-iftype
+    name-prefix: nl80211-iftype-
+    attributes:
+      -
+        name: adhoc
+        type: flag
+      -
+        name: station
+        type: flag
+      -
+        name: ap
+        type: flag
+      -
+        name: ap-vlan
+        type: flag
+      -
+        name: wds
+        type: flag
+      -
+        name: monitor
+        type: flag
+      -
+        name: mesh-point
+        type: flag
+      -
+        name: p2p-client
+        type: flag
+      -
+        name: p2p-go
+        type: flag
+      -
+        name: p2p-device
+        type: flag
+      -
+        name: ocb
+        type: flag
+      -
+        name: nan
+        type: flag
+  -
+    name: txq-stats-attrs
+    name-prefix: nl80211-txq-stats-
+    attributes:
+      -
+        name: backlog-bytes
+        type: u32
+      -
+        name: backlog-packets
+        type: u32
+      -
+        name: flows
+        type: u32
+      -
+        name: drops
+        type: u32
+      -
+        name: ecn-marks
+        type: u32
+      -
+        name: overlimit
+        type: u32
+      -
+        name: overmemory
+        type: u32
+      -
+        name: collisions
+        type: u32
+      -
+        name: tx-bytes
+        type: u32
+      -
+        name: tx-packets
+        type: u32
+      -
+        name: max-flows
+        type: u32
+  -
+    name: wmm-attrs
+    enum-name: nl80211-wmm-rule
+    name-prefix: nl80211-wmmr-
+    attributes:
+      -
+        name: cw-min
+        type: u16
+      -
+        name: cw-max
+        type: u16
+      -
+        name: aifsn
+        type: u8
+      -
+        name: txop
+        type: u16
+  -
+    name: wowlan-triggers-attrs
+    enum-name: nl80211-wowlan-triggers
+    name-prefix: nl80211-wowlan-trig-
+    attr-max-name: max-nl80211-wowlan-trig
+    attributes:
+      -
+        name: any
+        type: flag
+      -
+        name: disconnect
+        type: flag
+      -
+        name: magic-pkt
+        type: flag
+      -
+        name: pkt-pattern
+        type: flag
+      -
+        name: gtk-rekey-supported
+        type: flag
+      -
+        name: gtk-rekey-failure
+        type: flag
+      -
+        name: eap-ident-request
+        type: flag
+      -
+        name: 4way-handshake
+        type: flag
+      -
+        name: rfkill-release
+        type: flag
+      -
+        name: wakeup-pkt-80211
+        type: flag
+      -
+        name: wakeup-pkt-80211-len
+        type: flag
+      -
+        name: wakeup-pkt-8023
+        type: flag
+      -
+        name: wakeup-pkt-8023-len
+        type: flag
+      -
+        name: tcp-connection
+        type: flag
+      -
+        name: wakeup-tcp-match
+        type: flag
+      -
+        name: wakeup-tcp-connlost
+        type: flag
+      -
+        name: wakeup-tcp-nomoretokens
+        type: flag
+      -
+        name: net-detect
+        type: flag
+      -
+        name: net-detect-results
+        type: flag
+      -
+        name: unprotected-deauth-disassoc
+        type: flag
+
+operations:
+  enum-model: directional
+  list:
+    -
+      name: get-wiphy
+      doc: |
+        Get information about a wiphy or dump a list of all wiphys. Requests to dump get-wiphy
+        should unconditionally include the split-wiphy-dump flag in the request.
+      attribute-set: nl80211-attrs
+      do:
+        request:
+          value: 1
+          attributes:
+            - wiphy
+            - wdev
+            - ifindex
+        reply:
+          value: 3
+          attributes: &wiphy-reply-attrs
+            - bands
+            - cipher-suites
+            - control-port-ethertype
+            - ext-capa
+            - ext-capa-mask
+            - ext-features
+            - feature-flags
+            - generation
+            - ht-capability-mask
+            - interface-combinations
+            - mac
+            - max-csa-counters
+            - max-match-sets
+            - max-num-akm-suites
+            - max-num-pmkids
+            - max-num-scan-ssids
+            - max-num-sched-scan-plans
+            - max-num-sched-scan-ssids
+            - max-remain-on-channel-duration
+            - max-scan-ie-len
+            - max-scan-plan-interval
+            - max-scan-plan-iterations
+            - max-sched-scan-ie-len
+            - offchannel-tx-ok
+            - rx-frame-types
+            - sar-spec
+            - sched-scan-max-reqs
+            - software-iftypes
+            - support-ap-uapsd
+            - supported-commands
+            - supported-iftypes
+            - tdls-external-setup
+            - tdls-support
+            - tx-frame-types
+            - txq-limit
+            - txq-memory-limit
+            - txq-quantum
+            - txq-stats
+            - vht-capability-mask
+            - wiphy
+            - wiphy-antenna-avail-rx
+            - wiphy-antenna-avail-tx
+            - wiphy-antenna-rx
+            - wiphy-antenna-tx
+            - wiphy-bands
+            - wiphy-coverage-class
+            - wiphy-frag-threshold
+            - wiphy-name
+            - wiphy-retry-long
+            - wiphy-retry-short
+            - wiphy-rts-threshold
+            - wowlan-triggers-supported
+      dump:
+        request:
+          attributes:
+            - wiphy
+            - wdev
+            - ifindex
+            - split-wiphy-dump
+        reply:
+          attributes: *wiphy-reply-attrs
+    -
+      name: get-interface
+      doc: Get information about an interface or dump a list of all interfaces
+      attribute-set: nl80211-attrs
+      do:
+        request:
+          value: 5
+          attributes:
+            - ifname
+        reply:
+          value: 7
+          attributes: &interface-reply-attrs
+            - ifname
+            - iftype
+            - ifindex
+            - wiphy
+            - wdev
+            - mac
+            - generation
+            - txq-stats
+            - 4addr
+      dump:
+        request:
+          attributes:
+            - ifname
+        reply:
+          attributes: *interface-reply-attrs
+    -
+      name: get-protocol-features
+      doc: Get information about supported protocol features
+      attribute-set: nl80211-attrs
+      do:
+        request:
+          value: 95
+          attributes:
+            - protocol-features
+        reply:
+          value: 95
+          attributes:
+            - protocol-features
+
+mcast-groups:
+  list:
+    -
+      name: config
+    -
+      name: scan
+    -
+      name: regulatory
+    -
+      name: mlme
+    -
+      name: vendor
+    -
+      name: nan
+    -
+      name: testmode
diff --git a/tools/net/ynl/Makefile.deps b/tools/net/ynl/Makefile.deps
index d027a07c1e2c1..f3269ce39e5b7 100644
--- a/tools/net/ynl/Makefile.deps
+++ b/tools/net/ynl/Makefile.deps
@@ -23,6 +23,7 @@ CFLAGS_handshake:=$(call get_hdr_inc,_LINUX_HANDSHAKE_H,handshake.h)
 CFLAGS_mptcp_pm:=$(call get_hdr_inc,_LINUX_MPTCP_PM_H,mptcp_pm.h)
 CFLAGS_net_shaper:=$(call get_hdr_inc,_LINUX_NET_SHAPER_H,net_shaper.h)
 CFLAGS_netdev:=$(call get_hdr_inc,_LINUX_NETDEV_H,netdev.h)
+CFLAGS_nl80211:=$(call get_hdr_inc,__LINUX_NL802121_H,nl80211.h)
 CFLAGS_nlctrl:=$(call get_hdr_inc,__LINUX_GENERIC_NETLINK_H,genetlink.h)
 CFLAGS_nfsd:=$(call get_hdr_inc,_LINUX_NFSD_NETLINK_H,nfsd_netlink.h)
 CFLAGS_ovs_datapath:=$(call get_hdr_inc,__LINUX_OPENVSWITCH_H,openvswitch.h)

From f0e70409b7eb0584d451f74db0c72af67b6170b3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 11 Feb 2025 18:17:31 +0100
Subject: [PATCH 0505/2753] net: avoid unconditionally touching sk_tsflags on
 RX

After commit 5d4cc87414c5 ("net: reorganize "struct sock" fields"),
the sk_tsflags field shares the same cacheline with sk_forward_alloc.

The UDP protocol does not acquire the sock lock in the RX path;
forward allocations are protected via the receive queue spinlock;
additionally udp_recvmsg() calls sock_recv_cmsgs() unconditionally
touching sk_tsflags on each packet reception.

Due to the above, under high packet rate traffic, when the BH and the
user-space process run on different CPUs, UDP packet reception
experiences a cache miss while accessing sk_tsflags.

The receive path doesn't strictly need to access the problematic field;
change sock_set_timestamping() to maintain the relevant information
in a newly allocated sk_flags bit, so that sock_recv_cmsgs() can
take decisions accessing the latter field only.

With this patch applied, on an AMD epic server with i40e NICs, I
measured a 10% performance improvement for small packets UDP flood
performance tests - possibly a larger delta could be observed with more
recent H/W.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/dbd18c8a1171549f8249ac5a8b30b1b5ec88a425.1739294057.git.pabeni@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h | 9 +++++----
 net/core/sock.c    | 1 +
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 8036b3b79cd8b..60ebf3c7b229e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -954,6 +954,7 @@ enum sock_flags {
 	SOCK_TSTAMP_NEW, /* Indicates 64 bit timestamps always */
 	SOCK_RCVMARK, /* Receive SO_MARK  ancillary data with packet */
 	SOCK_RCVPRIORITY, /* Receive SO_PRIORITY ancillary data with packet */
+	SOCK_TIMESTAMPING_ANY, /* Copy of sk_tsflags & TSFLAGS_ANY */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -2664,13 +2665,13 @@ static inline void sock_recv_cmsgs(struct msghdr *msg, struct sock *sk,
 {
 #define FLAGS_RECV_CMSGS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP)			| \
-			   (1UL << SOCK_RCVMARK)			|\
-			   (1UL << SOCK_RCVPRIORITY))
+			   (1UL << SOCK_RCVMARK)			| \
+			   (1UL << SOCK_RCVPRIORITY)			| \
+			   (1UL << SOCK_TIMESTAMPING_ANY))
 #define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
-	if (sk->sk_flags & FLAGS_RECV_CMSGS ||
-	    READ_ONCE(sk->sk_tsflags) & TSFLAGS_ANY)
+	if (READ_ONCE(sk->sk_flags) & FLAGS_RECV_CMSGS)
 		__sock_recv_cmsgs(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sock_write_timestamp(sk, skb->tstamp);
diff --git a/net/core/sock.c b/net/core/sock.c
index eae2ae70a2e03..a197f0a0b8788 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -938,6 +938,7 @@ int sock_set_timestamping(struct sock *sk, int optname,
 
 	WRITE_ONCE(sk->sk_tsflags, val);
 	sock_valbool_flag(sk, SOCK_TSTAMP_NEW, optname == SO_TIMESTAMPING_NEW);
+	sock_valbool_flag(sk, SOCK_TIMESTAMPING_ANY, !!(val & TSFLAGS_ANY));
 
 	if (val & SOF_TIMESTAMPING_RX_SOFTWARE)
 		sock_enable_timestamp(sk,

From 23fc9311a526aa3874ebf1fed4d8b8757d2a6bdb Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Mon, 10 Feb 2025 16:21:52 +0100
Subject: [PATCH 0506/2753] netlink: specs: add conntrack dump and stats dump
 support

This adds support to dump the connection tracking table
("conntrack -L") and the conntrack statistics, ("conntrack -S").

Example conntrack dump:
tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/conntrack.yaml --dump get
[{'id': 59489769,
  'mark': 0,
  'nfgen-family': 2,
  'protoinfo': {'protoinfo-tcp': {'tcp-flags-original': {'flags': {'maxack',
                                                                   'sack-perm',
                                                                   'window-scale'},
                                                         'mask': set()},
                                  'tcp-flags-reply': {'flags': {'maxack',
                                                                'sack-perm',
                                                                'window-scale'},
                                                      'mask': set()},
                                  'tcp-state': 'established',
                                  'tcp-wscale-original': 7,
                                  'tcp-wscale-reply': 8}},
  'res-id': 0,
  'secctx': {'secctx-name': 'system_u:object_r:unlabeled_t:s0'},
  'status': {'assured',
             'confirmed',
             'dst-nat-done',
             'seen-reply',
             'src-nat-done'},
  'timeout': 431949,
  'tuple-orig': {'tuple-ip': {'ip-v4-dst': '34.107.243.93',
                              'ip-v4-src': '192.168.0.114'},
                 'tuple-proto': {'proto-dst-port': 443,
                                 'proto-num': 6,
                                 'proto-src-port': 37104}},
  'tuple-reply': {'tuple-ip': {'ip-v4-dst': '192.168.0.114',
                               'ip-v4-src': '34.107.243.93'},
                  'tuple-proto': {'proto-dst-port': 37104,
                                  'proto-num': 6,
                                  'proto-src-port': 443}},
  'use': 1,
  'version': 0},
 {'id': 3402229480,

Example stats dump:
tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/conntrack.yaml --dump get-stats
[{'chain-toolong': 0,
  'clash-resolve': 3,
  'drop': 0,
 ....

Changes since last iteration:
 - Address comments from Donald Hunter, in particular, fixup "get" and
   "get-stats" descriptions, the former operation supports both dump
   and normal request (returns a single entry, if found), the latter
   only supports dumps.

Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20250210152159.41077-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/conntrack.yaml | 643 +++++++++++++++++++++
 1 file changed, 643 insertions(+)
 create mode 100644 Documentation/netlink/specs/conntrack.yaml

diff --git a/Documentation/netlink/specs/conntrack.yaml b/Documentation/netlink/specs/conntrack.yaml
new file mode 100644
index 0000000000000..840dc4504216b
--- /dev/null
+++ b/Documentation/netlink/specs/conntrack.yaml
@@ -0,0 +1,643 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+
+name: conntrack
+protocol: netlink-raw
+protonum: 12
+
+doc:
+  Netfilter connection tracking subsystem over nfnetlink
+
+definitions:
+  -
+    name: nfgenmsg
+    type: struct
+    members:
+      -
+        name: nfgen-family
+        type: u8
+      -
+        name: version
+        type: u8
+      -
+        name: res-id
+        byte-order: big-endian
+        type: u16
+  -
+    name: nf-ct-tcp-flags-mask
+    type: struct
+    members:
+      -
+        name: flags
+        type: u8
+        enum: nf-ct-tcp-flags
+        enum-as-flags: true
+      -
+        name: mask
+        type: u8
+        enum: nf-ct-tcp-flags
+        enum-as-flags: true
+  -
+    name: nf-ct-tcp-flags
+    type: flags
+    entries:
+      - window-scale
+      - sack-perm
+      - close-init
+      - be-liberal
+      - unacked
+      - maxack
+      - challenge-ack
+      - simultaneous-open
+  -
+    name: nf-ct-tcp-state
+    type: enum
+    entries:
+      - none
+      - syn-sent
+      - syn-recv
+      - established
+      - fin-wait
+      - close-wait
+      - last-ack
+      - time-wait
+      - close
+      - syn-sent2
+      - max
+      - ignore
+      - retrans
+      - unack
+      - timeout-max
+  -
+    name: nf-ct-sctp-state
+    type: enum
+    entries:
+      - none
+      - cloned
+      - cookie-wait
+      - cookie-echoed
+      - established
+      - shutdown-sent
+      - shutdown-received
+      - shutdown-ack-sent
+      - shutdown-heartbeat-sent
+  -
+    name: nf-ct-status
+    type: flags
+    entries:
+      - expected
+      - seen-reply
+      - assured
+      - confirmed
+      - src-nat
+      - dst-nat
+      - seq-adj
+      - src-nat-done
+      - dst-nat-done
+      - dying
+      - fixed-timeout
+      - template
+      - nat-clash
+      - helper
+      - offload
+      - hw-offload
+
+attribute-sets:
+  -
+    name: counter-attrs
+    attributes:
+      -
+        name: packets
+        type: u64
+        byte-order: big-endian
+      -
+        name: bytes
+        type: u64
+        byte-order: big-endian
+      -
+        name: packets-old
+        type: u32
+      -
+        name: bytes-old
+        type: u32
+      -
+        name: pad
+        type: pad
+  -
+    name: tuple-proto-attrs
+    attributes:
+      -
+        name: proto-num
+        type: u8
+        doc: l4 protocol number
+      -
+        name: proto-src-port
+        type: u16
+        byte-order: big-endian
+        doc: l4 source port
+      -
+        name: proto-dst-port
+        type: u16
+        byte-order: big-endian
+        doc: l4 source port
+      -
+        name: proto-icmp-id
+        type: u16
+        byte-order: big-endian
+        doc: l4 icmp id
+      -
+        name: proto-icmp-type
+        type: u8
+      -
+        name: proto-icmp-code
+        type: u8
+      -
+        name: proto-icmpv6-id
+        type: u16
+        byte-order: big-endian
+        doc: l4 icmp id
+      -
+        name: proto-icmpv6-type
+        type: u8
+      -
+        name: proto-icmpv6-code
+        type: u8
+  -
+    name: tuple-ip-attrs
+    attributes:
+      -
+        name: ip-v4-src
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+        doc: ipv4 source address
+      -
+        name: ip-v4-dst
+        type: u32
+        byte-order: big-endian
+        display-hint: ipv4
+        doc: ipv4 destination address
+      -
+        name: ip-v6-src
+        type: binary
+        checks:
+          min-len: 16
+        byte-order: big-endian
+        display-hint: ipv6
+        doc: ipv6 source address
+      -
+        name: ip-v6-dst
+        type: binary
+        checks:
+          min-len: 16
+        byte-order: big-endian
+        display-hint: ipv6
+        doc: ipv6 destination address
+  -
+    name: tuple-attrs
+    attributes:
+    -
+        name: tuple-ip
+        type: nest
+        nested-attributes: tuple-ip-attrs
+        doc: conntrack l3 information
+    -
+        name: tuple-proto
+        type: nest
+        nested-attributes: tuple-proto-attrs
+        doc: conntrack l4 information
+    -
+        name: tuple-zone
+        type: u16
+        byte-order: big-endian
+        doc: conntrack zone id
+  -
+    name: protoinfo-tcp-attrs
+    attributes:
+    -
+        name: tcp-state
+        type: u8
+        enum: nf-ct-tcp-state
+        doc: tcp connection state
+    -
+        name: tcp-wscale-original
+        type: u8
+        doc: window scaling factor in original direction
+    -
+        name: tcp-wscale-reply
+        type: u8
+        doc: window scaling factor in reply direction
+    -
+        name: tcp-flags-original
+        type: binary
+        struct: nf-ct-tcp-flags-mask
+    -
+        name: tcp-flags-reply
+        type: binary
+        struct: nf-ct-tcp-flags-mask
+  -
+    name: protoinfo-dccp-attrs
+    attributes:
+    -
+        name: dccp-state
+        type: u8
+        doc: dccp connection state
+    -
+        name: dccp-role
+        type: u8
+    -
+        name: dccp-handshake-seq
+        type: u64
+        byte-order: big-endian
+    -
+        name: dccp-pad
+        type: pad
+  -
+    name: protoinfo-sctp-attrs
+    attributes:
+    -
+        name: sctp-state
+        type: u8
+        doc: sctp connection state
+        enum: nf-ct-sctp-state
+    -
+        name: vtag-original
+        type: u32
+        byte-order: big-endian
+    -
+        name: vtag-reply
+        type: u32
+        byte-order: big-endian
+  -
+    name: protoinfo-attrs
+    attributes:
+    -
+        name: protoinfo-tcp
+        type: nest
+        nested-attributes: protoinfo-tcp-attrs
+        doc: conntrack tcp state information
+    -
+        name: protoinfo-dccp
+        type: nest
+        nested-attributes: protoinfo-dccp-attrs
+        doc: conntrack dccp state information
+    -
+        name: protoinfo-sctp
+        type: nest
+        nested-attributes: protoinfo-sctp-attrs
+        doc: conntrack sctp state information
+  -
+    name: help-attrs
+    attributes:
+      -
+        name: help-name
+        type: string
+        doc: helper name
+  -
+    name: nat-proto-attrs
+    attributes:
+      -
+        name: nat-port-min
+        type: u16
+        byte-order: big-endian
+      -
+        name: nat-port-max
+        type: u16
+        byte-order: big-endian
+  -
+    name: nat-attrs
+    attributes:
+      -
+        name: nat-v4-minip
+        type: u32
+        byte-order: big-endian
+      -
+        name: nat-v4-maxip
+        type: u32
+        byte-order: big-endian
+      -
+        name: nat-v6-minip
+        type: binary
+      -
+        name: nat-v6-maxip
+        type: binary
+      -
+        name: nat-proto
+        type: nest
+        nested-attributes: nat-proto-attrs
+  -
+    name: seqadj-attrs
+    attributes:
+      -
+        name: correction-pos
+        type: u32
+        byte-order: big-endian
+      -
+        name: offset-before
+        type: u32
+        byte-order: big-endian
+      -
+        name: offset-after
+        type: u32
+        byte-order: big-endian
+  -
+    name: secctx-attrs
+    attributes:
+      -
+        name: secctx-name
+        type: string
+  -
+    name: synproxy-attrs
+    attributes:
+      -
+        name: isn
+        type: u32
+        byte-order: big-endian
+      -
+        name: its
+        type: u32
+        byte-order: big-endian
+      -
+        name: tsoff
+        type: u32
+        byte-order: big-endian
+  -
+    name: conntrack-attrs
+    attributes:
+      -
+        name: tuple-orig
+        type: nest
+        nested-attributes: tuple-attrs
+        doc: conntrack l3+l4 protocol information, original direction
+      -
+        name: tuple-reply
+        type: nest
+        nested-attributes: tuple-attrs
+        doc: conntrack l3+l4 protocol information, reply direction
+      -
+        name: status
+        type: u32
+        byte-order: big-endian
+        enum: nf-ct-status
+        enum-as-flags: true
+        doc: conntrack flag bits
+      -
+        name: protoinfo
+        type: nest
+        nested-attributes: protoinfo-attrs
+      -
+        name: help
+        type: nest
+        nested-attributes: help-attrs
+      -
+        name: nat-src
+        type: nest
+        nested-attributes: nat-attrs
+      -
+        name: timeout
+        type: u32
+        byte-order: big-endian
+      -
+        name: mark
+        type: u32
+        byte-order: big-endian
+      -
+        name: counters-orig
+        type: nest
+        nested-attributes: counter-attrs
+      -
+        name: counters-reply
+        type: nest
+        nested-attributes: counter-attrs
+      -
+        name: use
+        type: u32
+        byte-order: big-endian
+      -
+        name: id
+        type: u32
+        byte-order: big-endian
+      -
+        name: nat-dst
+        type: nest
+        nested-attributes: nat-attrs
+      -
+        name: tuple-master
+        type: nest
+        nested-attributes: tuple-attrs
+      -
+        name: seq-adj-orig
+        type: nest
+        nested-attributes: seqadj-attrs
+      -
+        name: seq-adj-reply
+        type: nest
+        nested-attributes: seqadj-attrs
+      -
+        name: secmark
+        type: binary
+        doc: obsolete
+      -
+        name: zone
+        type: u16
+        byte-order: big-endian
+        doc: conntrack zone id
+      -
+        name: secctx
+        type: nest
+        nested-attributes: secctx-attrs
+      -
+        name: timestamp
+        type: u64
+        byte-order: big-endian
+      -
+        name: mark-mask
+        type: u32
+        byte-order: big-endian
+      -
+        name: labels
+        type: binary
+      -
+        name: labels mask
+        type: binary
+      -
+        name: synproxy
+        type: nest
+        nested-attributes: synproxy-attrs
+      -
+        name: filter
+        type: nest
+        nested-attributes: tuple-attrs
+      -
+        name: status-mask
+        type: u32
+        byte-order: big-endian
+        enum: nf-ct-status
+        enum-as-flags: true
+        doc: conntrack flag bits to change
+      -
+        name: timestamp-event
+        type: u64
+        byte-order: big-endian
+  -
+    name: conntrack-stats-attrs
+    attributes:
+      -
+        name: searched
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: found
+        type: u32
+        byte-order: big-endian
+      -
+        name: new
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: invalid
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: ignore
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: delete
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: delete-list
+        type: u32
+        byte-order: big-endian
+        doc: obsolete
+      -
+        name: insert
+        type: u32
+        byte-order: big-endian
+      -
+        name: insert-failed
+        type: u32
+        byte-order: big-endian
+      -
+        name: drop
+        type: u32
+        byte-order: big-endian
+      -
+        name: early-drop
+        type: u32
+        byte-order: big-endian
+      -
+        name: error
+        type: u32
+        byte-order: big-endian
+      -
+        name: search-restart
+        type: u32
+        byte-order: big-endian
+      -
+        name: clash-resolve
+        type: u32
+        byte-order: big-endian
+      -
+        name: chain-toolong
+        type: u32
+        byte-order: big-endian
+
+operations:
+  enum-model: directional
+  list:
+    -
+      name: get
+      doc: get / dump entries
+      attribute-set: conntrack-attrs
+      fixed-header: nfgenmsg
+      do:
+        request:
+          value: 0x101
+          attributes:
+            - tuple-orig
+            - tuple-reply
+            - zone
+        reply:
+          value: 0x100
+          attributes:
+            - tuple-orig
+            - tuple-reply
+            - status
+            - protoinfo
+            - help
+            - nat-src
+            - nat-dst
+            - timeout
+            - mark
+            - counter-orig
+            - counter-reply
+            - use
+            - id
+            - nat-dst
+            - tuple-master
+            - seq-adj-orig
+            - seq-adj-reply
+            - zone
+            - secctx
+            - labels
+            - synproxy
+      dump:
+        request:
+          value: 0x101
+          attributes:
+            - nfgen-family
+            - mark
+            - filter
+            - status
+            - zone
+        reply:
+          value: 0x100
+          attributes:
+            - tuple-orig
+            - tuple-reply
+            - status
+            - protoinfo
+            - help
+            - nat-src
+            - nat-dst
+            - timeout
+            - mark
+            - counter-orig
+            - counter-reply
+            - use
+            - id
+            - nat-dst
+            - tuple-master
+            - seq-adj-orig
+            - seq-adj-reply
+            - zone
+            - secctx
+            - labels
+            - synproxy
+    -
+      name: get-stats
+      doc: dump pcpu conntrack stats
+      attribute-set: conntrack-stats-attrs
+      fixed-header: nfgenmsg
+      dump:
+        request:
+          value: 0x104
+        reply:
+          value: 0x104
+          attributes:
+            - searched
+            - found
+            - insert
+            - insert-failed
+            - drop
+            - early-drop
+            - error
+            - search-restart
+            - clash-resolve
+            - chain-toolong

From 8dbf0c7556454b52af91bae305ca71500c31495c Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Mon, 10 Feb 2025 21:43:28 +0800
Subject: [PATCH 0507/2753] net: stmmac: dwmac-loongson: Set correct
 {tx,rx}_fifo_size

Now for dwmac-loongson {tx,rx}_fifo_size are uninitialised, which means
zero. This means dwmac-loongson doesn't support changing MTU because in
stmmac_change_mtu() it requires the fifo size be no less than MTU. Thus,
set the correct tx_fifo_size and rx_fifo_size for it (16KB multiplied by
queue counts).

Here {tx,rx}_fifo_size is initialised with the initial value (also the
maximum value) of {tx,rx}_queues_to_use. So it will keep as 16KB if we
don't change the queue count, and will be larger than 16KB if we change
(decrease) the queue count. However stmmac_change_mtu() still work well
with current logic (MTU cannot be larger than 16KB for stmmac).

Note: the Fixes tag picked here is the oldest commit and key commit of
the dwmac-loongson series "stmmac: Add Loongson platform support".

Acked-by: Yanteng Si <si.yanteng@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Chong Qiao <qiaochong@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Link: https://patch.msgid.link/20250210134328.2755328-1-chenhuacai@loongson.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index bfe6e2d631bdf..79acdf38c5254 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -574,6 +574,9 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	if (ret)
 		goto err_disable_device;
 
+	plat->tx_fifo_size = SZ_16K * plat->tx_queues_to_use;
+	plat->rx_fifo_size = SZ_16K * plat->rx_queues_to_use;
+
 	if (dev_of_node(&pdev->dev))
 		ret = loongson_dwmac_dt_config(pdev, plat, &res);
 	else

From a3783dbf2574c2d76b37bcb8b669852f494e9932 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dima.fedrau@gmail.com>
Date: Mon, 10 Feb 2025 15:53:40 +0100
Subject: [PATCH 0508/2753] net: phy: marvell-88q2xxx: Add support for PHY LEDs
 on 88q2xxx

Marvell 88Q2XXX devices support up to two configurable Light Emitting
Diode (LED). Add minimal LED controller driver supporting the most common
uses with the 'netdev' trigger.

Reviewed-by: Stefan Eichenberger <eichest@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Link: https://patch.msgid.link/20250210-marvell-88q2xxx-leds-v4-1-3a0900dc121f@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell-88q2xxx.c | 189 +++++++++++++++++++++++++++++-
 1 file changed, 185 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index a3996471a1c9a..bad5e7b2357da 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -8,6 +8,7 @@
  */
 #include <linux/ethtool_netlink.h>
 #include <linux/marvell_phy.h>
+#include <linux/of.h>
 #include <linux/phy.h>
 #include <linux/hwmon.h>
 
@@ -27,6 +28,9 @@
 #define MDIO_MMD_AN_MV_STAT2_100BT1		0x2000
 #define MDIO_MMD_AN_MV_STAT2_1000BT1		0x4000
 
+#define MDIO_MMD_PCS_MV_RESET_CTRL		32768
+#define MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE	0x8
+
 #define MDIO_MMD_PCS_MV_INT_EN			32784
 #define MDIO_MMD_PCS_MV_INT_EN_LINK_UP		0x0040
 #define MDIO_MMD_PCS_MV_INT_EN_LINK_DOWN	0x0080
@@ -40,6 +44,22 @@
 #define MDIO_MMD_PCS_MV_GPIO_INT_CTRL			32787
 #define MDIO_MMD_PCS_MV_GPIO_INT_CTRL_TRI_DIS		0x0800
 
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL			32790
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_1_MASK	GENMASK(7, 4)
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_0_MASK	GENMASK(3, 0)
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK		0x0 /* Link established */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_RX_TX	0x1 /* Link established, blink for rx or tx activity */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_1000BT1	0x2 /* Blink 3x for 1000BT1 link established */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_RX_TX_ON		0x3 /* Receive or transmit activity */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_RX_TX		0x4 /* Blink on receive or transmit activity */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_TX		0x5 /* Transmit activity */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_COPPER	0x6 /* Copper Link established */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_1000BT1_ON	0x7 /* 1000BT1 link established */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_FORCE_OFF		0x8 /* Force off */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_FORCE_ON		0x9 /* Force on */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_FORCE_HIGHZ	0xa /* Force Hi-Z */
+#define MDIO_MMD_PCS_MV_LED_FUNC_CTRL_FORCE_BLINK	0xb /* Force blink */
+
 #define MDIO_MMD_PCS_MV_TEMP_SENSOR1			32833
 #define MDIO_MMD_PCS_MV_TEMP_SENSOR1_RAW_INT		0x0001
 #define MDIO_MMD_PCS_MV_TEMP_SENSOR1_INT		0x0040
@@ -95,8 +115,12 @@
 
 #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF			65246
 
+#define MV88Q2XXX_LED_INDEX_TX_ENABLE	0
+#define MV88Q2XXX_LED_INDEX_GPIO	1
+
 struct mv88q2xxx_priv {
 	bool enable_temp;
+	bool enable_led0;
 };
 
 struct mmd_val {
@@ -460,6 +484,9 @@ static int mv88q2xxx_config_aneg(struct phy_device *phydev)
 
 static int mv88q2xxx_config_init(struct phy_device *phydev)
 {
+	struct mv88q2xxx_priv *priv = phydev->priv;
+	int ret;
+
 	/* The 88Q2XXX PHYs do have the extended ability register available, but
 	 * register MDIO_PMA_EXTABLE where they should signalize it does not
 	 * work according to specification. Therefore, we force it here.
@@ -469,10 +496,22 @@ static int mv88q2xxx_config_init(struct phy_device *phydev)
 	/* Configure interrupt with default settings, output is driven low for
 	 * active interrupt and high for inactive.
 	 */
-	if (phy_interrupt_is_valid(phydev))
-		return phy_set_bits_mmd(phydev, MDIO_MMD_PCS,
-					MDIO_MMD_PCS_MV_GPIO_INT_CTRL,
-					MDIO_MMD_PCS_MV_GPIO_INT_CTRL_TRI_DIS);
+	if (phy_interrupt_is_valid(phydev)) {
+		ret = phy_set_bits_mmd(phydev, MDIO_MMD_PCS,
+				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL,
+				       MDIO_MMD_PCS_MV_GPIO_INT_CTRL_TRI_DIS);
+		if (ret < 0)
+			return ret;
+	}
+
+	/* Enable LED function and disable TX disable feature on LED/TX_ENABLE */
+	if (priv->enable_led0) {
+		ret = phy_clear_bits_mmd(phydev, MDIO_MMD_PCS,
+					 MDIO_MMD_PCS_MV_RESET_CTRL,
+					 MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE);
+		if (ret < 0)
+			return ret;
+	}
 
 	return 0;
 }
@@ -740,15 +779,62 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 }
 #endif
 
+#if IS_ENABLED(CONFIG_OF_MDIO)
+static int mv88q2xxx_leds_probe(struct phy_device *phydev)
+{
+	struct device_node *node = phydev->mdio.dev.of_node;
+	struct mv88q2xxx_priv *priv = phydev->priv;
+	struct device_node *leds;
+	int ret = 0;
+	u32 index;
+
+	if (!node)
+		return 0;
+
+	leds = of_get_child_by_name(node, "leds");
+	if (!leds)
+		return 0;
+
+	for_each_available_child_of_node_scoped(leds, led) {
+		ret = of_property_read_u32(led, "reg", &index);
+		if (ret)
+			goto exit;
+
+		if (index > MV88Q2XXX_LED_INDEX_GPIO) {
+			ret = -EINVAL;
+			goto exit;
+		}
+
+		if (index == MV88Q2XXX_LED_INDEX_TX_ENABLE)
+			priv->enable_led0 = true;
+	}
+
+exit:
+	of_node_put(leds);
+
+	return ret;
+}
+
+#else
+static int mv88q2xxx_leds_probe(struct phy_device *phydev)
+{
+	return 0;
+}
+#endif
+
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
 	struct mv88q2xxx_priv *priv;
+	int ret;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	phydev->priv = priv;
+	ret = mv88q2xxx_leds_probe(phydev);
+	if (ret)
+		return ret;
 
 	return mv88q2xxx_hwmon_probe(phydev);
 }
@@ -918,6 +1004,98 @@ static int mv88q222x_cable_test_get_status(struct phy_device *phydev,
 	return 0;
 }
 
+static int mv88q2xxx_led_mode(u8 index, unsigned long rules)
+{
+	switch (rules) {
+	case BIT(TRIGGER_NETDEV_LINK):
+		return MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK;
+	case BIT(TRIGGER_NETDEV_LINK_1000):
+		return MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_1000BT1_ON;
+	case BIT(TRIGGER_NETDEV_TX):
+		return MDIO_MMD_PCS_MV_LED_FUNC_CTRL_TX;
+	case BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX):
+		return MDIO_MMD_PCS_MV_LED_FUNC_CTRL_RX_TX;
+	case BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX):
+		return MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_RX_TX;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static int mv88q2xxx_led_hw_is_supported(struct phy_device *phydev, u8 index,
+					 unsigned long rules)
+{
+	int mode;
+
+	mode = mv88q2xxx_led_mode(index, rules);
+	if (mode < 0)
+		return mode;
+
+	return 0;
+}
+
+static int mv88q2xxx_led_hw_control_set(struct phy_device *phydev, u8 index,
+					unsigned long rules)
+{
+	int mode;
+
+	mode = mv88q2xxx_led_mode(index, rules);
+	if (mode < 0)
+		return mode;
+
+	if (index == MV88Q2XXX_LED_INDEX_TX_ENABLE)
+		return phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				      MDIO_MMD_PCS_MV_LED_FUNC_CTRL,
+				      MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_0_MASK,
+				      FIELD_PREP(MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_0_MASK,
+						 mode));
+	else
+		return phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				      MDIO_MMD_PCS_MV_LED_FUNC_CTRL,
+				      MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_1_MASK,
+				      FIELD_PREP(MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_1_MASK,
+						 mode));
+}
+
+static int mv88q2xxx_led_hw_control_get(struct phy_device *phydev, u8 index,
+					unsigned long *rules)
+{
+	int val;
+
+	val = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_MMD_PCS_MV_LED_FUNC_CTRL);
+	if (val < 0)
+		return val;
+
+	if (index == MV88Q2XXX_LED_INDEX_TX_ENABLE)
+		val = FIELD_GET(MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_0_MASK, val);
+	else
+		val = FIELD_GET(MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LED_1_MASK, val);
+
+	switch (val) {
+	case MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK:
+		*rules = BIT(TRIGGER_NETDEV_LINK);
+		break;
+	case MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_1000BT1_ON:
+		*rules = BIT(TRIGGER_NETDEV_LINK_1000);
+		break;
+	case MDIO_MMD_PCS_MV_LED_FUNC_CTRL_TX:
+		*rules = BIT(TRIGGER_NETDEV_TX);
+		break;
+	case MDIO_MMD_PCS_MV_LED_FUNC_CTRL_RX_TX:
+		*rules = BIT(TRIGGER_NETDEV_TX) | BIT(TRIGGER_NETDEV_RX);
+		break;
+	case MDIO_MMD_PCS_MV_LED_FUNC_CTRL_LINK_RX_TX:
+		*rules = BIT(TRIGGER_NETDEV_LINK) | BIT(TRIGGER_NETDEV_TX) |
+			 BIT(TRIGGER_NETDEV_RX);
+		break;
+	default:
+		*rules = 0;
+		break;
+	}
+
+	return 0;
+}
+
 static struct phy_driver mv88q2xxx_driver[] = {
 	{
 		.phy_id			= MARVELL_PHY_ID_88Q2110,
@@ -953,6 +1131,9 @@ static struct phy_driver mv88q2xxx_driver[] = {
 		.get_sqi_max		= mv88q2xxx_get_sqi_max,
 		.suspend		= mv88q2xxx_suspend,
 		.resume			= mv88q2xxx_resume,
+		.led_hw_is_supported	= mv88q2xxx_led_hw_is_supported,
+		.led_hw_control_set	= mv88q2xxx_led_hw_control_set,
+		.led_hw_control_get	= mv88q2xxx_led_hw_control_get,
 	},
 };
 

From 7aca0d8a727da503a8adeb6866a136ded5bea4b1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 11 Feb 2025 13:50:57 +0900
Subject: [PATCH 0509/2753] arp: Convert SIOCDARP and SIOCSARP to per-netns
 RTNL.

ioctl(SIOCDARP/SIOCSARP) operates on a single netns fetched from
an AF_INET socket in inet_ioctl().

Let's hold rtnl_net_lock() for SIOCDARP and SIOCSARP.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250211045057.10419-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/arp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index cb9a7ed8abd3a..431d900c136c4 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1062,8 +1062,8 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on)
 		IPV4_DEVCONF_ALL(net, PROXY_ARP) = on;
 		return 0;
 	}
-	if (__in_dev_get_rtnl(dev)) {
-		IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on);
+	if (__in_dev_get_rtnl_net(dev)) {
+		IN_DEV_CONF_SET(__in_dev_get_rtnl_net(dev), PROXY_ARP, on);
 		return 0;
 	}
 	return -ENXIO;
@@ -1293,14 +1293,14 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
 
 	switch (cmd) {
 	case SIOCDARP:
-		rtnl_lock();
+		rtnl_net_lock(net);
 		err = arp_req_delete(net, &r);
-		rtnl_unlock();
+		rtnl_net_unlock(net);
 		break;
 	case SIOCSARP:
-		rtnl_lock();
+		rtnl_net_lock(net);
 		err = arp_req_set(net, &r);
-		rtnl_unlock();
+		rtnl_net_unlock(net);
 		break;
 	case SIOCGARP:
 		rcu_read_lock();

From ab027c488fc4a1fff0a5b712d4bdb2d2d324e8f8 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Thu, 23 Jan 2025 14:34:41 +0800
Subject: [PATCH 0510/2753] firmware: arm_scmi: imx: Correct tx size of
 scmi_imx_misc_ctrl_set

'struct scmi_imx_misc_ctrl_set_in' has a zero length array in the end,
The sizeof will not count 'value[]', and hence Tx size will be smaller
than actual size for Tx,and SCMI firmware will flag this as protocol
error.

Fix this by enlarge the Tx size with 'num * sizeof(__le32)' to count in
the size of data.

Fixes: 61c9f03e22fc ("firmware: arm_scmi: Add initial support for i.MX MISC protocol")
Reviewed-by: Jacky Bai <ping.bai@nxp.com>
Tested-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Acked-by: Jason Liu <jason.hui.liu@nxp.com>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Message-Id: <20250123063441.392555-1-peng.fan@oss.nxp.com>
(sudeep.holla: Commit rewording and replace hardcoded sizeof(__le32) value)
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
index 83b69fc4fba5b..a8915d3b4df51 100644
--- a/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
+++ b/drivers/firmware/arm_scmi/vendors/imx/imx-sm-misc.c
@@ -254,8 +254,8 @@ static int scmi_imx_misc_ctrl_set(const struct scmi_protocol_handle *ph,
 	if (num > max_num)
 		return -EINVAL;
 
-	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET, sizeof(*in),
-				      0, &t);
+	ret = ph->xops->xfer_get_init(ph, SCMI_IMX_MISC_CTRL_SET,
+				      sizeof(*in) + num * sizeof(__le32), 0, &t);
 	if (ret)
 		return ret;
 

From c3a97ccaed80986fc3c0581661bf9170847d23ba Mon Sep 17 00:00:00 2001
From: Ritvik Gupta <ritvikfoss@gmail.com>
Date: Wed, 12 Feb 2025 02:13:11 +0000
Subject: [PATCH 0511/2753] Documentation: dpaa2 ethernet switch driver: Fix
 spelling

Corrected spelling mistake

Signed-off-by: Ritvik Gupta <ritvikfoss@gmail.com>
Link: https://patch.msgid.link/20250212021311.13257-1-ritvikfoss@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../device_drivers/ethernet/freescale/dpaa2/switch-driver.rst   | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/switch-driver.rst b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/switch-driver.rst
index 8bf411b857d43..5f3885e56f582 100644
--- a/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/switch-driver.rst
+++ b/Documentation/networking/device_drivers/ethernet/freescale/dpaa2/switch-driver.rst
@@ -70,7 +70,7 @@ the DPSW object that it will probe:
 Besides the configuration of the actual DPSW object, the dpaa2-switch driver
 will need the following DPAA2 objects:
 
- * 1 DPMCP - A Management Command Portal object is needed for any interraction
+ * 1 DPMCP - A Management Command Portal object is needed for any interaction
    with the MC firmware.
 
  * 1 DPBP - A Buffer Pool is used for seeding buffers intended for the Rx path

From 34dba73b231f2a46af88519d573052cc57a84952 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 11 Feb 2025 11:20:56 +0100
Subject: [PATCH 0512/2753] sctp: Remove commented out code

Remove commented out code.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250211102057.587182-1-thorsten.blum@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/sctp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 836a7e200f395..812011d8b67e7 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -222,7 +222,6 @@ struct sctp_datahdr {
 	__be16 stream;
 	__be16 ssn;
 	__u32 ppid;
-	/* __u8  payload[]; */
 };
 
 struct sctp_data_chunk {

From 5077bc7af28f649d669f9cda6b5fedecedfaef2d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 12 Feb 2025 07:32:52 +0100
Subject: [PATCH 0513/2753] ixgene-v2: prepare for phylib stop exporting
 phy_10_100_features_array

As part of phylib cleanup we plan to stop exporting the feature arrays.
So explicitly remove the modes not supported by the MAC. The media type
bits don't have any impact on kernel behavior, so don't touch them.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/be356a21-5a1a-45b3-9407-3a97f3af4600@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/apm/xgene-v2/mdio.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/apm/xgene-v2/mdio.c b/drivers/net/ethernet/apm/xgene-v2/mdio.c
index eba06831aec2d..6a17045a5f626 100644
--- a/drivers/net/ethernet/apm/xgene-v2/mdio.c
+++ b/drivers/net/ethernet/apm/xgene-v2/mdio.c
@@ -97,7 +97,6 @@ void xge_mdio_remove(struct net_device *ndev)
 
 int xge_mdio_config(struct net_device *ndev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
 	struct xge_pdata *pdata = netdev_priv(ndev);
 	struct device *dev = &pdata->pdev->dev;
 	struct mii_bus *mdio_bus;
@@ -137,17 +136,12 @@ int xge_mdio_config(struct net_device *ndev)
 		goto err;
 	}
 
-	linkmode_set_bit_array(phy_10_100_features_array,
-			       ARRAY_SIZE(phy_10_100_features_array),
-			       mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_AUI_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_FIBRE_BIT, mask);
-	linkmode_set_bit(ETHTOOL_LINK_MODE_BNC_BIT, mask);
-
-	linkmode_andnot(phydev->supported, phydev->supported, mask);
-	linkmode_copy(phydev->advertising, phydev->supported);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_10baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Half_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_100baseT_Full_BIT);
+	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
+
 	pdata->phy_speed = SPEED_UNKNOWN;
 
 	return 0;

From d30460f42675fef5cd4b44ffbc49b545524555e3 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 12 Feb 2025 08:03:56 +0100
Subject: [PATCH 0514/2753] r8169: add support for Intel Killer E5000

This adds support for the Intel Killer E5000 which seems to be a
rebranded RTL8126. Copied from r8126 vendor driver.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/9db73e9b-e2e8-45de-97a5-041c5f71d774@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 32eb4a4482f9f..9fe53322d7bbc 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -169,6 +169,7 @@ static const struct pci_device_id rtl8169_pci_tbl[] = {
 	{ PCI_VDEVICE(REALTEK,	0x8125) },
 	{ PCI_VDEVICE(REALTEK,	0x8126) },
 	{ PCI_VDEVICE(REALTEK,	0x3000) },
+	{ PCI_VDEVICE(REALTEK,	0x5000) },
 	{}
 };
 

From 4079918ae720e842ed7dff65fedeb9980b374995 Mon Sep 17 00:00:00 2001
From: Max Schulze <max.schulze@online.de>
Date: Wed, 12 Feb 2025 16:09:51 +0100
Subject: [PATCH 0515/2753] net: usb: asix_devices: add FiberGecko DeviceID

The FiberGecko is a small USB module that connects a 100 Mbit/s SFP

Signed-off-by: Max Schulze <max.schulze@online.de>
Tested-by: Max Schulze <max.schulze@online.de>
Suggested-by: David Hollis <dhollis@davehollis.com>
Reported-by: Sven Kreiensen <s.kreiensen@lyconsys.com>
Link: https://patch.msgid.link/20250212150957.43900-2-max.schulze@online.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/asix_devices.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/usb/asix_devices.c b/drivers/net/usb/asix_devices.c
index 57d6e5abc30e8..da24941a6e444 100644
--- a/drivers/net/usb/asix_devices.c
+++ b/drivers/net/usb/asix_devices.c
@@ -1421,6 +1421,19 @@ static const struct driver_info hg20f9_info = {
 	.data = FLAG_EEPROM_MAC,
 };
 
+static const struct driver_info lyconsys_fibergecko100_info = {
+	.description = "LyconSys FiberGecko 100 USB 2.0 to SFP Adapter",
+	.bind = ax88178_bind,
+	.status = asix_status,
+	.link_reset = ax88178_link_reset,
+	.reset = ax88178_link_reset,
+	.flags = FLAG_ETHER | FLAG_FRAMING_AX | FLAG_LINK_INTR |
+		 FLAG_MULTI_PACKET,
+	.rx_fixup = asix_rx_fixup_common,
+	.tx_fixup = asix_tx_fixup,
+	.data = 0x20061201,
+};
+
 static const struct usb_device_id	products [] = {
 {
 	// Linksys USB200M
@@ -1578,6 +1591,10 @@ static const struct usb_device_id	products [] = {
 	// Linux Automation GmbH USB 10Base-T1L
 	USB_DEVICE(0x33f7, 0x0004),
 	.driver_info = (unsigned long) &lxausb_t1l_info,
+}, {
+	/* LyconSys FiberGecko 100 */
+	USB_DEVICE(0x1d2a, 0x0801),
+	.driver_info = (unsigned long) &lyconsys_fibergecko100_info,
 },
 	{ },		// END
 };

From a8972d5a49b408248294b5ecbdd0a085e4726349 Mon Sep 17 00:00:00 2001
From: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Date: Fri, 27 Sep 2024 09:53:05 -0400
Subject: [PATCH 0516/2753] drm: panel: jd9365da-h3: fix reset signal polarity

In jadard_prepare() a reset pulse is generated with the following
statements (delays ommited for clarity):

    gpiod_set_value(jadard->reset, 1); --> Deassert reset
    gpiod_set_value(jadard->reset, 0); --> Assert reset for 10ms
    gpiod_set_value(jadard->reset, 1); --> Deassert reset

However, specifying second argument of "0" to gpiod_set_value() means to
deassert the GPIO, and "1" means to assert it. If the reset signal is
defined as GPIO_ACTIVE_LOW in the DTS, the above statements will
incorrectly generate the reset pulse (inverted) and leave it asserted
(LOW) at the end of jadard_prepare().

Fix reset behavior by inverting gpiod_set_value() second argument
in jadard_prepare(). Also modify second argument to devm_gpiod_get()
in jadard_dsi_probe() to assert the reset when probing.

Do not modify it in jadard_unprepare() as it is already properly
asserted with "1", which seems to be the intended behavior.

Fixes: 6b818c533dd8 ("drm: panel: Add Jadard JD9365DA-H3 DSI panel")
Cc: stable@vger.kernel.org
Signed-off-by: Hugo Villeneuve <hvilleneuve@dimonoff.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20240927135306.857617-1-hugo@hugovil.com
Signed-off-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20240927135306.857617-1-hugo@hugovil.com
---
 drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
index 45d09e6fa667f..7d68a8acfe2ea 100644
--- a/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+++ b/drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
@@ -109,13 +109,13 @@ static int jadard_prepare(struct drm_panel *panel)
 	if (jadard->desc->lp11_to_reset_delay_ms)
 		msleep(jadard->desc->lp11_to_reset_delay_ms);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(5);
 
-	gpiod_set_value(jadard->reset, 0);
+	gpiod_set_value(jadard->reset, 1);
 	msleep(10);
 
-	gpiod_set_value(jadard->reset, 1);
+	gpiod_set_value(jadard->reset, 0);
 	msleep(130);
 
 	ret = jadard->desc->init(jadard);
@@ -1130,7 +1130,7 @@ static int jadard_dsi_probe(struct mipi_dsi_device *dsi)
 	dsi->format = desc->format;
 	dsi->lanes = desc->lanes;
 
-	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	jadard->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(jadard->reset)) {
 		DRM_DEV_ERROR(&dsi->dev, "failed to get our reset GPIO\n");
 		return PTR_ERR(jadard->reset);

From fbe8f2fa971c537571994a0df532c511c4fb5537 Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Wed, 12 Feb 2025 09:11:07 -0800
Subject: [PATCH 0517/2753] md/raid*: Fix the set_queue_limits implementations

queue_limits_cancel_update() must only be called if
queue_limits_start_update() is called first. Remove the
queue_limits_cancel_update() calls from the raid*_set_limits() functions
because there is no corresponding queue_limits_start_update() call.

Cc: Christoph Hellwig <hch@lst.de>
Fixes: c6e56cf6b2e7 ("block: move integrity information into queue_limits")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/linux-raid/20250212171108.3483150-1-bvanassche@acm.org/
Signed-off-by: Yu Kuai <yukuai@kernel.org>
---
 drivers/md/raid0.c  | 4 +---
 drivers/md/raid1.c  | 4 +---
 drivers/md/raid10.c | 4 +---
 3 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index 8fc9339b00c72..70bcc3cdf2cd1 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -386,10 +386,8 @@ static int raid0_set_limits(struct mddev *mddev)
 	lim.io_opt = lim.io_min * mddev->raid_disks;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 9d57a88dbd261..10ea3af40991d 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -3219,10 +3219,8 @@ static int raid1_set_limits(struct mddev *mddev)
 	lim.max_write_zeroes_sectors = 0;
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index efe93b9791677..15b9ae5bf84d8 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -4020,10 +4020,8 @@ static int raid10_set_queue_limits(struct mddev *mddev)
 	lim.io_opt = lim.io_min * raid10_nr_stripes(conf);
 	lim.features |= BLK_FEAT_ATOMIC_WRITES;
 	err = mddev_stack_rdev_limits(mddev, &lim, MDDEV_STACK_INTEGRITY);
-	if (err) {
-		queue_limits_cancel_update(mddev->gendisk->queue);
+	if (err)
 		return err;
-	}
 	return queue_limits_set(mddev->gendisk->queue, &lim);
 }
 

From cd57e4327707126dca3f9517b84274c001d4c184 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Tue, 11 Feb 2025 10:29:48 +0800
Subject: [PATCH 0518/2753] phy: freescale: fsl-samsung-hdmi: Limit PLL lock
 detection clock divider to valid range
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

FIELD_PREP() checks that a value fits into the available bitfield,
but the index div equals to 4,is out of range.

which gcc complains about:
In function ‘fsl_samsung_hdmi_phy_configure_pll_lock_det’,
inlined from ‘fsl_samsung_hdmi_phy_configure’ at
drivers/phy/freescale/phy-fsl-samsung-hdmi.c :470:2:
././include/linux/compiler_types.h:542:38: error: call to ‘__compiletime_assert_538’
declared with attribute error: FIELD_PREP: value too large for the field
  542 |  _compiletime_assert(condition, msg, __compiletime_assert_,
__COUNTER__)
      |                                      ^
././include/linux/compiler_types.h:523:4: note: in definition of
macro ‘__compiletime_assert’ 523 |    prefix ## suffix();
      |    ^~~~~~
././include/linux/compiler_types.h:542:2: note: in expansion of macro
‘_compiletime_assert’
  542 |  _compiletime_assert(condition, msg, __compiletime_assert_,
 __COUNTER__)

REG12_CK_DIV_MASK only two bit, limit div to range 0~3,
so build error will fix.

Fixes: d567679f2b6a ("phy: freescale: fsl-samsung-hdmi: Clean up fld_tg_code calculation")
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>

Changlog:

Reviewed-by: Adam Ford <aford173@gmail.com>
Link: https://lore.kernel.org/r/tencent_6F503D43467AA99DD8CC59B8F645F0725B0A@qq.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/freescale/phy-fsl-samsung-hdmi.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
index 45004f598e4dc..e4c0a82d16d9e 100644
--- a/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
+++ b/drivers/phy/freescale/phy-fsl-samsung-hdmi.c
@@ -325,7 +325,7 @@ to_fsl_samsung_hdmi_phy(struct clk_hw *hw)
 	return container_of(hw, struct fsl_samsung_hdmi_phy, hw);
 }
 
-static void
+static int
 fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 					    const struct phy_config *cfg)
 {
@@ -341,6 +341,9 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 			break;
 	}
 
+	if (unlikely(div == 4))
+		return -EINVAL;
+
 	writeb(FIELD_PREP(REG12_CK_DIV_MASK, div), phy->regs + PHY_REG(12));
 
 	/*
@@ -364,6 +367,8 @@ fsl_samsung_hdmi_phy_configure_pll_lock_det(struct fsl_samsung_hdmi_phy *phy,
 	       FIELD_PREP(REG14_RP_CODE_MASK, 2) |
 	       FIELD_PREP(REG14_TG_CODE_HIGH_MASK, fld_tg_code >> 8),
 	       phy->regs + PHY_REG(14));
+
+	return 0;
 }
 
 static unsigned long fsl_samsung_hdmi_phy_find_pms(unsigned long fout, u8 *p, u16 *m, u8 *s)
@@ -466,7 +471,11 @@ static int fsl_samsung_hdmi_phy_configure(struct fsl_samsung_hdmi_phy *phy,
 	writeb(REG21_SEL_TX_CK_INV | FIELD_PREP(REG21_PMS_S_MASK,
 	       cfg->pll_div_regs[2] >> 4), phy->regs + PHY_REG(21));
 
-	fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
+	ret = fsl_samsung_hdmi_phy_configure_pll_lock_det(phy, cfg);
+	if (ret) {
+		dev_err(phy->dev, "pixclock too large\n");
+		return ret;
+	}
 
 	writeb(REG33_FIX_DA | REG33_MODE_SET_DONE, phy->regs + PHY_REG(33));
 

From 89cb121e94612cd3bb3c74b0e772ead5b40b7a5d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Micka=C3=ABl=20Sala=C3=BCn?= <mic@digikod.net>
Date: Tue, 11 Feb 2025 14:25:28 +0100
Subject: [PATCH 0519/2753] selftests/landlock: Enable the new
 CONFIG_AF_UNIX_OOB
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since commit 5155cbcdbf03 ("af_unix: Add a prompt to
CONFIG_AF_UNIX_OOB"), the Landlock selftests's configuration is not
enough to build a minimal kernel.  Because scoped_signal_test checks
with the MSG_OOB flag, we need to enable CONFIG_AF_UNIX_OOB for tests:

 #  RUN           fown.no_sandbox.sigurg_socket ...
 # scoped_signal_test.c:420:sigurg_socket:Expected 1 (1) == send(client_socket, ".", 1, MSG_OOB) (-1)
 # sigurg_socket: Test terminated by assertion
 #          FAIL  fown.no_sandbox.sigurg_socket
 ...

Cc: Günther Noack <gnoack@google.com>
Acked-by: Florent Revest <revest@chromium.org>
Link: https://lore.kernel.org/r/20250211132531.1625566-1-mic@digikod.net
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/config | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 29af19c4e9f98..361f94f8cb0d4 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -1,3 +1,4 @@
+CONFIG_AF_UNIX_OOB=y
 CONFIG_CGROUPS=y
 CONFIG_CGROUP_SCHED=y
 CONFIG_INET=y

From 143c9aae043a1dc174a75be52521192a0caa224b Mon Sep 17 00:00:00 2001
From: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Date: Fri, 24 Jan 2025 01:12:10 +0530
Subject: [PATCH 0520/2753] landlock: Fix grammar error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix grammar error in comments that were identified using the codespell
tool.

Signed-off-by: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Reviewed-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20250123194208.2660-1-tanyaagarwal25699@gmail.com
[mic: Simplify commit message]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/ruleset.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/security/landlock/ruleset.c b/security/landlock/ruleset.c
index 241ce44375b6a..bff4e40a3093c 100644
--- a/security/landlock/ruleset.c
+++ b/security/landlock/ruleset.c
@@ -124,7 +124,7 @@ create_rule(const struct landlock_id id,
 		return ERR_PTR(-ENOMEM);
 	RB_CLEAR_NODE(&new_rule->node);
 	if (is_object_pointer(id.type)) {
-		/* This should be catched by insert_rule(). */
+		/* This should have been caught by insert_rule(). */
 		WARN_ON_ONCE(!id.key.object);
 		landlock_get_object(id.key.object);
 	}

From 192b7ff29b1fb0335a9b9107991e6286f462f361 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?G=C3=BCnther=20Noack?= <gnoack@google.com>
Date: Fri, 24 Jan 2025 15:44:44 +0000
Subject: [PATCH 0521/2753] landlock: Minor typo and grammar fixes in IPC
 scoping documentation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

* Fix some whitespace, punctuation and minor grammar.
* Add a missing sentence about the minimum ABI version,
  to stay in line with the section next to it.

Cc: Tahera Fahimi <fahimitahera@gmail.com>
Cc: Tanya Agarwal <tanyaagarwal25699@gmail.com>
Signed-off-by: Günther Noack <gnoack@google.com>
Link: https://lore.kernel.org/r/20250124154445.162841-1-gnoack@google.com
[mic: Add newlines, update doc date]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 Documentation/userspace-api/landlock.rst | 6 +++---
 include/uapi/linux/landlock.h            | 8 ++++++--
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/Documentation/userspace-api/landlock.rst b/Documentation/userspace-api/landlock.rst
index d639c61cb472a..ad587f53fe417 100644
--- a/Documentation/userspace-api/landlock.rst
+++ b/Documentation/userspace-api/landlock.rst
@@ -8,7 +8,7 @@ Landlock: unprivileged access control
 =====================================
 
 :Author: Mickaël Salaün
-:Date: October 2024
+:Date: January 2025
 
 The goal of Landlock is to enable restriction of ambient rights (e.g. global
 filesystem or network access) for a set of processes.  Because Landlock
@@ -329,11 +329,11 @@ non-sandboxed process, we can specify this restriction with
 A sandboxed process can connect to a non-sandboxed process when its domain is
 not scoped. If a process's domain is scoped, it can only connect to sockets
 created by processes in the same scope.
-Moreover, If a process is scoped to send signal to a non-scoped process, it can
+Moreover, if a process is scoped to send signal to a non-scoped process, it can
 only send signals to processes in the same scope.
 
 A connected datagram socket behaves like a stream socket when its domain is
-scoped, meaning if the domain is scoped after the socket is connected , it can
+scoped, meaning if the domain is scoped after the socket is connected, it can
 still :manpage:`send(2)` data just like a stream socket.  However, in the same
 scenario, a non-connected datagram socket cannot send data (with
 :manpage:`sendto(2)`) outside its scope.
diff --git a/include/uapi/linux/landlock.h b/include/uapi/linux/landlock.h
index 33745642f7875..e1d2c27533b49 100644
--- a/include/uapi/linux/landlock.h
+++ b/include/uapi/linux/landlock.h
@@ -268,7 +268,9 @@ struct landlock_net_port_attr {
  * ~~~~~~~~~~~~~~~~
  *
  * These flags enable to restrict a sandboxed process to a set of network
- * actions. This is supported since the Landlock ABI version 4.
+ * actions.
+ *
+ * This is supported since Landlock ABI version 4.
  *
  * The following access rights apply to TCP port numbers:
  *
@@ -291,11 +293,13 @@ struct landlock_net_port_attr {
  * Setting a flag for a ruleset will isolate the Landlock domain to forbid
  * connections to resources outside the domain.
  *
+ * This is supported since Landlock ABI version 6.
+ *
  * Scopes:
  *
  * - %LANDLOCK_SCOPE_ABSTRACT_UNIX_SOCKET: Restrict a sandboxed process from
  *   connecting to an abstract UNIX socket created by a process outside the
- *   related Landlock domain (e.g. a parent domain or a non-sandboxed process).
+ *   related Landlock domain (e.g., a parent domain or a non-sandboxed process).
  * - %LANDLOCK_SCOPE_SIGNAL: Restrict a sandboxed process from sending a signal
  *   to another process outside the domain.
  */

From 854277e2cc8c75dc3c216c82e72523258fcf65b9 Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:49 +0800
Subject: [PATCH 0522/2753] landlock: Fix non-TCP sockets restriction
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use sk_is_tcp() to check if socket is TCP in bind(2) and connect(2)
hooks.

SMC, MPTCP, SCTP protocols are currently restricted by TCP access
rights.  The purpose of TCP access rights is to provide control over
ports that can be used by userland to establish a TCP connection.
Therefore, it is incorrect to deny bind(2) and connect(2) requests for a
socket of another protocol.

However, SMC, MPTCP and RDS implementations use TCP internal sockets to
establish communication or even to exchange packets over a TCP
connection [1]. Landlock rules that configure bind(2) and connect(2)
usage for TCP sockets should not cover requests for sockets of such
protocols. These protocols have different set of security issues and
security properties, therefore, it is necessary to provide the userland
with the ability to distinguish between them (eg. [2]).

Control over TCP connection used by other protocols can be achieved with
upcoming support of socket creation control [3].

[1] https://lore.kernel.org/all/62336067-18c2-3493-d0ec-6dd6a6d3a1b5@huawei-partners.com/
[2] https://lore.kernel.org/all/20241204.fahVio7eicim@digikod.net/
[3] https://lore.kernel.org/all/20240904104824.1844082-1-ivanov.mikhail1@huawei-partners.com/

Closes: https://github.com/landlock-lsm/linux/issues/40
Fixes: fff69fb03dde ("landlock: Support network rules with TCP bind and connect")
Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-2-ivanov.mikhail1@huawei-partners.com
[mic: Format commit message to 72 columns]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 security/landlock/net.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/security/landlock/net.c b/security/landlock/net.c
index d5dcc4407a197..104b6c01fe503 100644
--- a/security/landlock/net.c
+++ b/security/landlock/net.c
@@ -63,8 +63,7 @@ static int current_check_access_socket(struct socket *const sock,
 	if (WARN_ON_ONCE(dom->num_layers < 1))
 		return -EACCES;
 
-	/* Checks if it's a (potential) TCP socket. */
-	if (sock->type != SOCK_STREAM)
+	if (!sk_is_tcp(sock->sk))
 		return 0;
 
 	/* Checks for minimal header length to safely read sa_family. */

From f5534d511bcd273720f168386de74af76e148a9b Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:50 +0800
Subject: [PATCH 0523/2753] selftests/landlock: Test TCP accesses with
 protocol=IPPROTO_TCP
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend protocol_variant structure with protocol field (Cf. socket(2)).

Extend protocol fixture with TCP test suits with protocol=IPPROTO_TCP
which can be used as an alias for IPPROTO_IP (=0) in socket(2).

Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-3-ivanov.mikhail1@huawei-partners.com
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/common.h   |  1 +
 tools/testing/selftests/landlock/net_test.c | 80 +++++++++++++++++----
 2 files changed, 67 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/landlock/common.h b/tools/testing/selftests/landlock/common.h
index a604ea5d8297c..6064c9ac05329 100644
--- a/tools/testing/selftests/landlock/common.h
+++ b/tools/testing/selftests/landlock/common.h
@@ -207,6 +207,7 @@ enforce_ruleset(struct __test_metadata *const _metadata, const int ruleset_fd)
 struct protocol_variant {
 	int domain;
 	int type;
+	int protocol;
 };
 
 struct service_fixture {
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index 4e0aeb53b225a..333263780fae4 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -85,18 +85,18 @@ static void setup_loopback(struct __test_metadata *const _metadata)
 	clear_ambient_cap(_metadata, CAP_NET_ADMIN);
 }
 
+static bool prot_is_tcp(const struct protocol_variant *const prot)
+{
+	return (prot->domain == AF_INET || prot->domain == AF_INET6) &&
+	       prot->type == SOCK_STREAM &&
+	       (prot->protocol == IPPROTO_TCP || prot->protocol == IPPROTO_IP);
+}
+
 static bool is_restricted(const struct protocol_variant *const prot,
 			  const enum sandbox_type sandbox)
 {
-	switch (prot->domain) {
-	case AF_INET:
-	case AF_INET6:
-		switch (prot->type) {
-		case SOCK_STREAM:
-			return sandbox == TCP_SANDBOX;
-		}
-		break;
-	}
+	if (sandbox == TCP_SANDBOX)
+		return prot_is_tcp(prot);
 	return false;
 }
 
@@ -105,7 +105,7 @@ static int socket_variant(const struct service_fixture *const srv)
 	int ret;
 
 	ret = socket(srv->protocol.domain, srv->protocol.type | SOCK_CLOEXEC,
-		     0);
+		     srv->protocol.protocol);
 	if (ret < 0)
 		return -errno;
 	return ret;
@@ -290,22 +290,48 @@ FIXTURE_TEARDOWN(protocol)
 }
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp) {
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp1) {
 	/* clang-format on */
 	.sandbox = NO_SANDBOX,
 	.prot = {
 		.domain = AF_INET,
 		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
 	},
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp) {
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp2) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
 	.sandbox = NO_SANDBOX,
 	.prot = {
 		.domain = AF_INET6,
 		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp2) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
 	},
 };
 
@@ -350,22 +376,48 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_unix_datagram) {
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp) {
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp1) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp2) {
 	/* clang-format on */
 	.sandbox = TCP_SANDBOX,
 	.prot = {
 		.domain = AF_INET,
 		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
+	},
+};
+
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp1) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		/* IPPROTO_IP == 0 */
+		.protocol = IPPROTO_IP,
 	},
 };
 
 /* clang-format off */
-FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp) {
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp2) {
 	/* clang-format on */
 	.sandbox = TCP_SANDBOX,
 	.prot = {
 		.domain = AF_INET6,
 		.type = SOCK_STREAM,
+		.protocol = IPPROTO_TCP,
 	},
 };
 

From 3d4033985ff508ef587ca11f1c8361ba57c7e09f Mon Sep 17 00:00:00 2001
From: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Date: Wed, 5 Feb 2025 17:36:51 +0800
Subject: [PATCH 0524/2753] selftests/landlock: Test that MPTCP actions are not
 restricted
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Extend protocol fixture with test suits for MPTCP protocol.
Add CONFIG_MPTCP and CONFIG_MPTCP_IPV6 options in config.

Signed-off-by: Mikhail Ivanov <ivanov.mikhail1@huawei-partners.com>
Link: https://lore.kernel.org/r/20250205093651.1424339-4-ivanov.mikhail1@huawei-partners.com
Cc: <stable@vger.kernel.org> # 6.7.x
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/config     |  2 +
 tools/testing/selftests/landlock/net_test.c | 44 +++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
index 361f94f8cb0d4..425de4c20271c 100644
--- a/tools/testing/selftests/landlock/config
+++ b/tools/testing/selftests/landlock/config
@@ -4,6 +4,8 @@ CONFIG_CGROUP_SCHED=y
 CONFIG_INET=y
 CONFIG_IPV6=y
 CONFIG_KEYS=y
+CONFIG_MPTCP=y
+CONFIG_MPTCP_IPV6=y
 CONFIG_NET=y
 CONFIG_NET_NS=y
 CONFIG_OVERLAY_FS=y
diff --git a/tools/testing/selftests/landlock/net_test.c b/tools/testing/selftests/landlock/net_test.c
index 333263780fae4..d9de0ee49ebc2 100644
--- a/tools/testing/selftests/landlock/net_test.c
+++ b/tools/testing/selftests/landlock/net_test.c
@@ -312,6 +312,17 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_mptcp) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
@@ -335,6 +346,17 @@ FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv6_mptcp) {
+	/* clang-format on */
+	.sandbox = NO_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, no_sandbox_with_ipv4_udp) {
 	/* clang-format on */
@@ -398,6 +420,17 @@ FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_mptcp) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp1) {
 	/* clang-format on */
@@ -421,6 +454,17 @@ FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_tcp2) {
 	},
 };
 
+/* clang-format off */
+FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv6_mptcp) {
+	/* clang-format on */
+	.sandbox = TCP_SANDBOX,
+	.prot = {
+		.domain = AF_INET6,
+		.type = SOCK_STREAM,
+		.protocol = IPPROTO_MPTCP,
+	},
+};
+
 /* clang-format off */
 FIXTURE_VARIANT_ADD(protocol, tcp_sandbox_with_ipv4_udp) {
 	/* clang-format on */

From 78332fdb956f18accfbca5993b10c5ed69f00a2c Mon Sep 17 00:00:00 2001
From: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Date: Mon, 10 Feb 2025 21:40:57 +0530
Subject: [PATCH 0525/2753] selftests/landlock: Add binaries to .gitignore
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Building the test creates binaries 'wait-pipe' and
'sandbox-and-launch' which need to be gitignore'd.

Signed-off-by: Bharadwaj Raju <bharadwaj.raju777@gmail.com>
Link: https://lore.kernel.org/r/20250210161101.6024-1-bharadwaj.raju777@gmail.com
[mic: Sort entries]
Signed-off-by: Mickaël Salaün <mic@digikod.net>
---
 tools/testing/selftests/landlock/.gitignore | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/landlock/.gitignore b/tools/testing/selftests/landlock/.gitignore
index 470203a7cd737..335b2b1a3463a 100644
--- a/tools/testing/selftests/landlock/.gitignore
+++ b/tools/testing/selftests/landlock/.gitignore
@@ -1,2 +1,4 @@
 /*_test
+/sandbox-and-launch
 /true
+/wait-pipe

From 0c67c37e1710b2a8f61c8a02db95a51fe577e2c1 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 11 Feb 2025 13:47:50 -0800
Subject: [PATCH 0526/2753] fuse: revert back to __readahead_folio() for
 readahead
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In commit 3eab9d7bc2f4 ("fuse: convert readahead to use folios"), the
logic was converted to using the new folio readahead code, which drops
the reference on the folio once it is locked, using an inferred
reference on the folio. Previously we held a reference on the folio for
the entire duration of the readpages call.

This is fine, however for the case for splice pipe responses where we
will remove the old folio and splice in the new folio (see
fuse_try_move_page()), we assume that there is a reference held on the
folio for ap->folios, which is no longer the case.

To fix this, revert back to __readahead_folio() which allows us to hold
the reference on the folio for the duration of readpages until either we
drop the reference ourselves in fuse_readpages_end() or the reference is
dropped after it's replaced in the page cache in the splice case.
This will fix the UAF bug that was reported.

Link: https://lore.kernel.org/linux-fsdevel/2f681f48-00f5-4e09-8431-2b3dbfaa881e@heusel.eu/
Fixes: 3eab9d7bc2f4 ("fuse: convert readahead to use folios")
Reported-by: Christian Heusel <christian@heusel.eu>
Closes: https://lore.kernel.org/all/2f681f48-00f5-4e09-8431-2b3dbfaa881e@heusel.eu/
Closes: https://gitlab.archlinux.org/archlinux/packaging/packages/linux/-/issues/110
Reported-by: Mantas Mikulėnas <grawity@gmail.com>
Closes: https://lore.kernel.org/all/34feb867-09e2-46e4-aa31-d9660a806d1a@gmail.com/
Closes: https://bugzilla.opensuse.org/show_bug.cgi?id=1236660
Cc: <stable@vger.kernel.org> # v6.13
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
---
 fs/fuse/dev.c  |  6 ++++++
 fs/fuse/file.c | 13 +++++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 5b5f789b37eb6..2b2d1b7555444 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -838,6 +838,12 @@ static int fuse_check_folio(struct folio *folio)
 	return 0;
 }
 
+/*
+ * Attempt to steal a page from the splice() pipe and move it into the
+ * pagecache. If successful, the pointer in @pagep will be updated. The
+ * folio that was originally in @pagep will lose a reference and the new
+ * folio returned in @pagep will carry a reference.
+ */
 static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
 {
 	int err;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 7d92a54799985..d63e56fd3dd20 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -955,8 +955,10 @@ static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
 		fuse_invalidate_atime(inode);
 	}
 
-	for (i = 0; i < ap->num_folios; i++)
+	for (i = 0; i < ap->num_folios; i++) {
 		folio_end_read(ap->folios[i], !err);
+		folio_put(ap->folios[i]);
+	}
 	if (ia->ff)
 		fuse_file_put(ia->ff, false);
 
@@ -1048,7 +1050,14 @@ static void fuse_readahead(struct readahead_control *rac)
 		ap = &ia->ap;
 
 		while (ap->num_folios < cur_pages) {
-			folio = readahead_folio(rac);
+			/*
+			 * This returns a folio with a ref held on it.
+			 * The ref needs to be held until the request is
+			 * completed, since the splice case (see
+			 * fuse_try_move_page()) drops the ref after it's
+			 * replaced in the page cache.
+			 */
+			folio = __readahead_folio(rac);
 			ap->folios[ap->num_folios] = folio;
 			ap->descs[ap->num_folios].length = folio_size(folio);
 			ap->num_folios++;

From 8789b4296aa796f658a19cac7d27365012893de1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Andr=C3=A9=20Draszik?= <andre.draszik@linaro.org>
Date: Thu, 5 Dec 2024 10:22:00 +0000
Subject: [PATCH 0527/2753] phy: exynos5-usbdrd: gs101: ensure power is gated
 to SS phy in phy_exit()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We currently don't gate the power to the SS phy in phy_exit().

Shuffle the code slightly to ensure the power is gated to the SS phy as
well.

Fixes: 32267c29bc7d ("phy: exynos5-usbdrd: support Exynos USBDRD 3.1 combo phy (HS & SS)")
CC: stable@vger.kernel.org # 6.11+
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Peter Griffin <peter.griffin@linaro.org>
Signed-off-by: André Draszik <andre.draszik@linaro.org>
Link: https://lore.kernel.org/r/20241205-gs101-usb-phy-fix-v4-1-0278809fb810@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos5-usbdrd.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 4a108fdab118c..46b8f6987c62c 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -1296,14 +1296,17 @@ static int exynos5_usbdrd_gs101_phy_exit(struct phy *phy)
 	struct exynos5_usbdrd_phy *phy_drd = to_usbdrd_phy(inst);
 	int ret;
 
+	if (inst->phy_cfg->id == EXYNOS5_DRDPHY_UTMI) {
+		ret = exynos850_usbdrd_phy_exit(phy);
+		if (ret)
+			return ret;
+	}
+
+	exynos5_usbdrd_phy_isol(inst, true);
+
 	if (inst->phy_cfg->id != EXYNOS5_DRDPHY_UTMI)
 		return 0;
 
-	ret = exynos850_usbdrd_phy_exit(phy);
-	if (ret)
-		return ret;
-
-	exynos5_usbdrd_phy_isol(inst, true);
 	return regulator_bulk_disable(phy_drd->drv_data->n_regulators,
 				      phy_drd->regulators);
 }

From 5ab90f40121a9f6a9b368274cd92d0f435dc7cfa Mon Sep 17 00:00:00 2001
From: Andrew Davis <afd@ti.com>
Date: Thu, 23 Jan 2025 12:22:34 -0600
Subject: [PATCH 0528/2753] phy: ti: gmii-sel: Do not use syscon helper to
 build regmap

The syscon helper device_node_to_regmap() is used to fetch a regmap
registered to a device node. It also currently creates this regmap
if the node did not already have a regmap associated with it. This
should only be used on "syscon" nodes. This driver is not such a
device and instead uses device_node_to_regmap() on its own node as
a hacky way to create a regmap for itself.

This will not work going forward and so we should create our regmap
the normal way by defining our regmap_config, fetching our memory
resource, then using the normal regmap_init_mmio() function.

Signed-off-by: Andrew Davis <afd@ti.com>
Tested-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20250123182234.597665-1-afd@ti.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/ti/phy-gmii-sel.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/phy/ti/phy-gmii-sel.c b/drivers/phy/ti/phy-gmii-sel.c
index e0ca59ae31531..ff5d5e29629fa 100644
--- a/drivers/phy/ti/phy-gmii-sel.c
+++ b/drivers/phy/ti/phy-gmii-sel.c
@@ -424,6 +424,12 @@ static int phy_gmii_sel_init_ports(struct phy_gmii_sel_priv *priv)
 	return 0;
 }
 
+static const struct regmap_config phy_gmii_sel_regmap_cfg = {
+	.reg_bits = 32,
+	.val_bits = 32,
+	.reg_stride = 4,
+};
+
 static int phy_gmii_sel_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -468,7 +474,14 @@ static int phy_gmii_sel_probe(struct platform_device *pdev)
 
 	priv->regmap = syscon_node_to_regmap(node->parent);
 	if (IS_ERR(priv->regmap)) {
-		priv->regmap = device_node_to_regmap(node);
+		void __iomem *base;
+
+		base = devm_platform_ioremap_resource(pdev, 0);
+		if (IS_ERR(base))
+			return dev_err_probe(dev, PTR_ERR(base),
+					     "failed to get base memory resource\n");
+
+		priv->regmap = regmap_init_mmio(dev, base, &phy_gmii_sel_regmap_cfg);
 		if (IS_ERR(priv->regmap))
 			return dev_err_probe(dev, PTR_ERR(priv->regmap),
 					     "Failed to get syscon\n");

From 55f1a5f7c97c3c92ba469e16991a09274410ceb7 Mon Sep 17 00:00:00 2001
From: BH Hsieh <bhsieh@nvidia.com>
Date: Wed, 22 Jan 2025 18:59:43 +0800
Subject: [PATCH 0529/2753] phy: tegra: xusb: reset VBUS & ID OVERRIDE

Observed VBUS_OVERRIDE & ID_OVERRIDE might be programmed
with unexpected value prior to XUSB PADCTL driver, this
could also occur in virtualization scenario.

For example, UEFI firmware programs ID_OVERRIDE=GROUNDED to set
a type-c port to host mode and keeps the value to kernel.
If the type-c port is connected a usb host, below errors can be
observed right after usb host mode driver gets probed. The errors
would keep until usb role class driver detects the type-c port
as device mode and notifies usb device mode driver to set both
ID_OVERRIDE and VBUS_OVERRIDE to correct value by XUSB PADCTL
driver.

[  173.765814] usb usb3-port2: Cannot enable. Maybe the USB cable is bad?
[  173.765837] usb usb3-port2: config error

Taking virtualization into account, asserting XUSB PADCTL
reset would break XUSB functions used by other guest OS,
hence only reset VBUS & ID OVERRIDE of the port in
utmi_phy_init.

Fixes: bbf711682cd5 ("phy: tegra: xusb: Add Tegra186 support")
Cc: stable@vger.kernel.org
Change-Id: Ic63058d4d49b4a1f8f9ab313196e20ad131cc591
Signed-off-by: BH Hsieh <bhsieh@nvidia.com>
Signed-off-by: Henry Lin <henryl@nvidia.com>
Link: https://lore.kernel.org/r/20250122105943.8057-1-henryl@nvidia.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/tegra/xusb-tegra186.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/phy/tegra/xusb-tegra186.c b/drivers/phy/tegra/xusb-tegra186.c
index 0f60d5d1c1678..fae6242aa730e 100644
--- a/drivers/phy/tegra/xusb-tegra186.c
+++ b/drivers/phy/tegra/xusb-tegra186.c
@@ -928,6 +928,7 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 	unsigned int index = lane->index;
 	struct device *dev = padctl->dev;
 	int err;
+	u32 reg;
 
 	port = tegra_xusb_find_usb2_port(padctl, index);
 	if (!port) {
@@ -935,6 +936,16 @@ static int tegra186_utmi_phy_init(struct phy *phy)
 		return -ENODEV;
 	}
 
+	if (port->mode == USB_DR_MODE_OTG ||
+	    port->mode == USB_DR_MODE_PERIPHERAL) {
+		/* reset VBUS&ID OVERRIDE */
+		reg = padctl_readl(padctl, USB2_VBUS_ID);
+		reg &= ~VBUS_OVERRIDE;
+		reg &= ~ID_OVERRIDE(~0);
+		reg |= ID_OVERRIDE_FLOATING;
+		padctl_writel(padctl, reg, USB2_VBUS_ID);
+	}
+
 	if (port->supply && port->mode == USB_DR_MODE_HOST) {
 		err = regulator_enable(port->supply);
 		if (err) {

From 5755eb0a8168493fddf63d72e0133de54b3a17dd Mon Sep 17 00:00:00 2001
From: Andrew Jeffery <andrew@codeconstruct.com.au>
Date: Mon, 3 Feb 2025 13:26:31 +1030
Subject: [PATCH 0530/2753] MAINTAINERS: Mark Andrew as M: for ASPEED MACHINE
 SUPPORT

From discussion in [1] and in-person with Joel, flip my entry from R:
to M:.

Link: https://lore.kernel.org/all/CACPK8Xe8yZLXzEQPp=1D2f0TsKA7hBZG=pHHW6U51FMpp_BiRQ@mail.gmail.com/ [1]
Cc: Joel Stanley <joel@jms.id.au>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: soc@lists.linux.dev
Cc: linux-aspeed@lists.ozlabs.org
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Andrew Jeffery <andrew@codeconstruct.com.au>
Acked-by: Joel Stanley <joel@jms.id.au>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 25c86f47353de..e3920abb7794f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2284,7 +2284,7 @@ F:	drivers/irqchip/irq-aspeed-i2c-ic.c
 
 ARM/ASPEED MACHINE SUPPORT
 M:	Joel Stanley <joel@jms.id.au>
-R:	Andrew Jeffery <andrew@codeconstruct.com.au>
+M:	Andrew Jeffery <andrew@codeconstruct.com.au>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 L:	linux-aspeed@lists.ozlabs.org (moderated for non-subscribers)
 S:	Supported

From f0570fdc8f72fb1a22bfd2bbf030b34a06da21ff Mon Sep 17 00:00:00 2001
From: Janne Grunau <j@jannau.net>
Date: Sat, 8 Feb 2025 10:22:01 +0100
Subject: [PATCH 0531/2753] MAINTAINERS: arm: apple: Add Janne as maintainer

Sven and I have agreed to share the maintainership for the ARM/APPLE
platform after Marcan's step down. I'm handling the downstream Asahi
Linux tree since April 2024 and worked on or wrote several drivers for
the platform.

Signed-off-by: Janne Grunau <j@jannau.net>
Acked-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Hector Martin <marcan@marcan.st>
Acked-by: Neal Gompa <neal@gompa.dev>
Link: https://lore.kernel.org/r/20250208-maint-soc-apple-v1-1-a7f7337baec0@jannau.net
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index e3920abb7794f..04c90ecf616a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2210,6 +2210,7 @@ F:	sound/soc/codecs/ssm3515.c
 
 ARM/APPLE MACHINE SUPPORT
 M:	Sven Peter <sven@svenpeter.dev>
+M:	Janne Grunau <j@jannau.net>
 R:	Alyssa Rosenzweig <alyssa@rosenzweig.io>
 L:	asahi@lists.linux.dev
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)

From be6686b823b30a69b1f71bde228ce042c78a1941 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Wed, 5 Feb 2025 15:41:43 +0100
Subject: [PATCH 0532/2753] firmware: imx: IMX_SCMI_MISC_DRV should depend on
 ARCH_MXC

The i.MX System Controller Management Interface firmware is only present
on Freescale i.MX SoCs.  Hence add a dependency on ARCH_MXC, to prevent
asking the user about this driver when configuring a kernel without
Freescale i.MX platform support.

Fixes: 514b2262ade48a05 ("firmware: arm_scmi: Fix i.MX build dependency")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Fabio Estevam <festevam@gmail.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/firmware/imx/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/imx/Kconfig b/drivers/firmware/imx/Kconfig
index 907cd149c40a8..c964f4924359f 100644
--- a/drivers/firmware/imx/Kconfig
+++ b/drivers/firmware/imx/Kconfig
@@ -25,6 +25,7 @@ config IMX_SCU
 
 config IMX_SCMI_MISC_DRV
 	tristate "IMX SCMI MISC Protocol driver"
+	depends on ARCH_MXC || COMPILE_TEST
 	default y if ARCH_MXC
 	help
 	  The System Controller Management Interface firmware (SCMI FW) is

From dd0f05b98925111f4530d7dab774398cdb32e9e3 Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Fri, 14 Feb 2025 09:31:29 +0100
Subject: [PATCH 0533/2753] platform: cznic: CZNIC_PLATFORMS should depend on
 ARCH_MVEBU

CZ.NIC's Turris devices are based on Marvell EBU SoCs.  Hence add a
dependency on ARCH_MVEBU, to prevent asking the user about these drivers
when configuring a kernel that cannot run on an affected CZ.NIC Turris
system.

Fixes: 992f1a3d4e88498d ("platform: cznic: Add preliminary support for Turris Omnia MCU")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/platform/cznic/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/cznic/Kconfig b/drivers/platform/cznic/Kconfig
index 49c383eb67854..13e37b49d9d01 100644
--- a/drivers/platform/cznic/Kconfig
+++ b/drivers/platform/cznic/Kconfig
@@ -6,6 +6,7 @@
 
 menuconfig CZNIC_PLATFORMS
 	bool "Platform support for CZ.NIC's Turris hardware"
+	depends on ARCH_MVEBU || COMPILE_TEST
 	help
 	  Say Y here to be able to choose driver support for CZ.NIC's Turris
 	  devices. This option alone does not add any kernel code.

From 70b0d6b0a199c5a3ee6c72f5e61681ed6f759612 Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Tue, 4 Feb 2025 13:04:18 +0530
Subject: [PATCH 0534/2753] tee: optee: Fix supplicant wait loop

OP-TEE supplicant is a user-space daemon and it's possible for it
be hung or crashed or killed in the middle of processing an OP-TEE
RPC call. It becomes more complicated when there is incorrect shutdown
ordering of the supplicant process vs the OP-TEE client application which
can eventually lead to system hang-up waiting for the closure of the
client application.

Allow the client process waiting in kernel for supplicant response to
be killed rather than indefinitely waiting in an unkillable state. Also,
a normal uninterruptible wait should not have resulted in the hung-task
watchdog getting triggered, but the endless loop would.

This fixes issues observed during system reboot/shutdown when supplicant
got hung for some reason or gets crashed/killed which lead to client
getting hung in an unkillable state. It in turn lead to system being in
hung up state requiring hard power off/on to recover.

Fixes: 4fb0a5eb364d ("tee: add OP-TEE driver")
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/tee/optee/supp.c | 35 ++++++++---------------------------
 1 file changed, 8 insertions(+), 27 deletions(-)

diff --git a/drivers/tee/optee/supp.c b/drivers/tee/optee/supp.c
index 322a543b8c278..d0f397c902420 100644
--- a/drivers/tee/optee/supp.c
+++ b/drivers/tee/optee/supp.c
@@ -80,7 +80,6 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	struct optee *optee = tee_get_drvdata(ctx->teedev);
 	struct optee_supp *supp = &optee->supp;
 	struct optee_supp_req *req;
-	bool interruptable;
 	u32 ret;
 
 	/*
@@ -111,36 +110,18 @@ u32 optee_supp_thrd_req(struct tee_context *ctx, u32 func, size_t num_params,
 	/*
 	 * Wait for supplicant to process and return result, once we've
 	 * returned from wait_for_completion(&req->c) successfully we have
-	 * exclusive access again.
+	 * exclusive access again. Allow the wait to be killable such that
+	 * the wait doesn't turn into an indefinite state if the supplicant
+	 * gets hung for some reason.
 	 */
-	while (wait_for_completion_interruptible(&req->c)) {
+	if (wait_for_completion_killable(&req->c)) {
 		mutex_lock(&supp->mutex);
-		interruptable = !supp->ctx;
-		if (interruptable) {
-			/*
-			 * There's no supplicant available and since the
-			 * supp->mutex currently is held none can
-			 * become available until the mutex released
-			 * again.
-			 *
-			 * Interrupting an RPC to supplicant is only
-			 * allowed as a way of slightly improving the user
-			 * experience in case the supplicant hasn't been
-			 * started yet. During normal operation the supplicant
-			 * will serve all requests in a timely manner and
-			 * interrupting then wouldn't make sense.
-			 */
-			if (req->in_queue) {
-				list_del(&req->link);
-				req->in_queue = false;
-			}
+		if (req->in_queue) {
+			list_del(&req->link);
+			req->in_queue = false;
 		}
 		mutex_unlock(&supp->mutex);
-
-		if (interruptable) {
-			req->ret = TEEC_ERROR_COMMUNICATION;
-			break;
-		}
+		req->ret = TEEC_ERROR_COMMUNICATION;
 	}
 
 	ret = req->ret;

From b3fefbb30a1691533cb905006b69b2a474660744 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 24 Jan 2025 19:15:23 +0100
Subject: [PATCH 0535/2753] nouveau/svm: fix missing folio unlock + put after
 make_device_exclusive_range()

In case we have to retry the loop, we are missing to unlock+put the
folio. In that case, we will keep failing make_device_exclusive_range()
because we cannot grab the folio lock, and even return from the function
with the folio locked and referenced, effectively never succeeding the
make_device_exclusive_range().

While at it, convert the other unlock+put to use a folio as well.

This was found by code inspection.

Fixes: 8f187163eb89 ("nouveau/svm: implement atomic SVM access")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Tested-by: Alistair Popple <apopple@nvidia.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250124181524.3584236-2-david@redhat.com
---
 drivers/gpu/drm/nouveau/nouveau_svm.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c
index b4da82ddbb6b2..8ea98f06d39af 100644
--- a/drivers/gpu/drm/nouveau/nouveau_svm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_svm.c
@@ -590,6 +590,7 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
 	struct mm_struct *mm = svmm->notifier.mm;
+	struct folio *folio;
 	struct page *page;
 	unsigned long start = args->p.addr;
 	unsigned long notifier_seq;
@@ -616,12 +617,16 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 			ret = -EINVAL;
 			goto out;
 		}
+		folio = page_folio(page);
 
 		mutex_lock(&svmm->mutex);
 		if (!mmu_interval_read_retry(&notifier->notifier,
 					     notifier_seq))
 			break;
 		mutex_unlock(&svmm->mutex);
+
+		folio_unlock(folio);
+		folio_put(folio);
 	}
 
 	/* Map the page on the GPU. */
@@ -637,8 +642,8 @@ static int nouveau_atomic_range_fault(struct nouveau_svmm *svmm,
 	ret = nvif_object_ioctl(&svmm->vmm->vmm.object, args, size, NULL);
 	mutex_unlock(&svmm->mutex);
 
-	unlock_page(page);
-	put_page(page);
+	folio_unlock(folio);
+	folio_put(folio);
 
 out:
 	mmu_interval_notifier_remove(&notifier->notifier);

From 2eeb03ad9f42dfece63051be2400af487ddb96d2 Mon Sep 17 00:00:00 2001
From: Saranya R <quic_sarar@quicinc.com>
Date: Wed, 12 Feb 2025 22:07:20 +0530
Subject: [PATCH 0536/2753] soc: qcom: pdr: Fix the potential deadlock

When some client process A call pdr_add_lookup() to add the look up for
the service and does schedule locator work, later a process B got a new
server packet indicating locator is up and call pdr_locator_new_server()
which eventually sets pdr->locator_init_complete to true which process A
sees and takes list lock and queries domain list but it will timeout due
to deadlock as the response will queued to the same qmi->wq and it is
ordered workqueue and process B is not able to complete new server
request work due to deadlock on list lock.

Fix it by removing the unnecessary list iteration as the list iteration
is already being done inside locator work, so avoid it here and just
call schedule_work() here.

       Process A                        Process B

                                     process_scheduled_works()
pdr_add_lookup()                      qmi_data_ready_work()
 process_scheduled_works()             pdr_locator_new_server()
                                         pdr->locator_init_complete=true;
   pdr_locator_work()
    mutex_lock(&pdr->list_lock);

     pdr_locate_service()                  mutex_lock(&pdr->list_lock);

      pdr_get_domain_list()
       pr_err("PDR: %s get domain list
               txn wait failed: %d\n",
               req->service_name,
               ret);

Timeout error log due to deadlock:

"
 PDR: tms/servreg get domain list txn wait failed: -110
 PDR: service lookup for msm/adsp/sensor_pd:tms/servreg failed: -110
"

Thanks to Bjorn and Johan for letting me know that this commit also fixes
an audio regression when using the in-kernel pd-mapper as that makes it
easier to hit this race. [1]

Link: https://lore.kernel.org/lkml/Zqet8iInnDhnxkT9@hovoldconsulting.com/ # [1]
Fixes: fbe639b44a82 ("soc: qcom: Introduce Protection Domain Restart helpers")
CC: stable@vger.kernel.org
Reviewed-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Tested-by: Bjorn Andersson <bjorn.andersson@oss.qualcomm.com>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Saranya R <quic_sarar@quicinc.com>
Co-developed-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com>
Signed-off-by: Mukesh Ojha <mukesh.ojha@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250212163720.1577876-1-mukesh.ojha@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/pdr_interface.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c
index 328b6153b2be6..71be378d2e43a 100644
--- a/drivers/soc/qcom/pdr_interface.c
+++ b/drivers/soc/qcom/pdr_interface.c
@@ -75,7 +75,6 @@ static int pdr_locator_new_server(struct qmi_handle *qmi,
 {
 	struct pdr_handle *pdr = container_of(qmi, struct pdr_handle,
 					      locator_hdl);
-	struct pdr_service *pds;
 
 	mutex_lock(&pdr->lock);
 	/* Create a local client port for QMI communication */
@@ -87,12 +86,7 @@ static int pdr_locator_new_server(struct qmi_handle *qmi,
 	mutex_unlock(&pdr->lock);
 
 	/* Service pending lookup requests */
-	mutex_lock(&pdr->list_lock);
-	list_for_each_entry(pds, &pdr->lookups, node) {
-		if (pds->need_locator_lookup)
-			schedule_work(&pdr->locator_work);
-	}
-	mutex_unlock(&pdr->list_lock);
+	schedule_work(&pdr->locator_work);
 
 	return 0;
 }

From 8221fd1a73044adef712a5c9346a23c2447f629c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 14 Feb 2025 16:43:49 +0000
Subject: [PATCH 0537/2753] workqueue: Log additional details when rejecting
 work

Syzbot regularly runs into the following warning on arm64:

  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 current_wq_worker kernel/workqueue_internal.h:69 [inline]
  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 is_chained_work kernel/workqueue.c:2199 [inline]
  | WARNING: CPU: 1 PID: 6023 at kernel/workqueue.c:2257 __queue_work+0xe50/0x1308 kernel/workqueue.c:2256
  | Modules linked in:
  | CPU: 1 UID: 0 PID: 6023 Comm: klogd Not tainted 6.13.0-rc2-syzkaller-g2e7aff49b5da #0
  | Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
  | pstate: 404000c5 (nZcv daIF +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  | pc : __queue_work+0xe50/0x1308 kernel/workqueue_internal.h:69
  | lr : current_wq_worker kernel/workqueue_internal.h:69 [inline]
  | lr : is_chained_work kernel/workqueue.c:2199 [inline]
  | lr : __queue_work+0xe50/0x1308 kernel/workqueue.c:2256

  [...]

  |    __queue_work+0xe50/0x1308 kernel/workqueue.c:2256 (L)
  |  delayed_work_timer_fn+0x74/0x90 kernel/workqueue.c:2485
  |  call_timer_fn+0x1b4/0x8b8 kernel/time/timer.c:1793
  |  expire_timers kernel/time/timer.c:1839 [inline]
  |  __run_timers kernel/time/timer.c:2418 [inline]
  |  __run_timer_base+0x59c/0x7b4 kernel/time/timer.c:2430
  |  run_timer_base kernel/time/timer.c:2439 [inline]
  |  run_timer_softirq+0xcc/0x194 kernel/time/timer.c:2449

The warning is probably because we are trying to queue work into a
destroyed workqueue, but the softirq context makes it hard to pinpoint
the problematic caller.

Extend the warning diagnostics to print both the function we are trying
to queue as well as the name of the workqueue.

Cc: Tejun Heo <tj@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Link: https://syzkaller.appspot.com/bug?extid=e13e654d315d4da1277c
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/workqueue.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index ccad33001c58c..902df3253598c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2254,8 +2254,10 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
 	 * queues a new work item to a wq after destroy_workqueue(wq).
 	 */
 	if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) &&
-		     WARN_ON_ONCE(!is_chained_work(wq))))
+		     WARN_ONCE(!is_chained_work(wq), "workqueue: cannot queue %ps on wq %s\n",
+			       work->func, wq->name))) {
 		return;
+	}
 	rcu_read_lock();
 retry:
 	/* pwq which will be used unless @work is executing elsewhere */

From 27ebd8bf9e4b53388cef2d9cdb2947bc456b0b33 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:18 -0500
Subject: [PATCH 0538/2753] virtchnl: add support for enabling PTP on iAVF

Add support for allowing a VF to enable PTP feature - Rx timestamps

The new capability is gated by VIRTCHNL_VF_CAP_PTP, which must be
set by the VF to request access to the new operations. In addition, the
VIRTCHNL_OP_1588_PTP_CAPS command is used to determine the specific
capabilities available to the VF.

This support includes the following additional capabilities:

* Rx timestamps enabled in the Rx queues (when using flexible advanced
  descriptors)
* Read access to PHC time over virtchnl using
  VIRTCHNL_OP_1588_PTP_GET_TIME

Extra space is reserved in most structures to allow for future
extension (like set clock, Tx timestamps).  Additional opcode numbers
are reserved and space in the virtchnl_ptp_caps structure is
specifically set aside for this.
Additionally, each structure has some space reserved for future
extensions to allow some flexibility.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/avf/virtchnl.h | 67 +++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 13a11f3c09b87..92866e449b21a 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -154,7 +154,10 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55,
 	VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56,
 	VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57,
-	/* opcode 57 - 65 are reserved */
+	/* opcode 58 and 59 are reserved */
+	VIRTCHNL_OP_1588_PTP_GET_CAPS = 60,
+	VIRTCHNL_OP_1588_PTP_GET_TIME = 61,
+	/* opcode 62 - 65 are reserved */
 	VIRTCHNL_OP_GET_QOS_CAPS = 66,
 	/* opcode 68 through 111 are reserved */
 	VIRTCHNL_OP_CONFIG_QUEUE_BW = 112,
@@ -270,6 +273,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF		BIT(27)
 #define VIRTCHNL_VF_OFFLOAD_FDIR_PF		BIT(28)
 #define VIRTCHNL_VF_OFFLOAD_QOS			BIT(29)
+#define VIRTCHNL_VF_CAP_PTP			BIT(31)
 
 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \
 			       VIRTCHNL_VF_OFFLOAD_VLAN | \
@@ -1425,6 +1429,61 @@ struct virtchnl_fdir_del {
 
 VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 
+#define VIRTCHNL_1588_PTP_CAP_RX_TSTAMP		BIT(1)
+#define VIRTCHNL_1588_PTP_CAP_READ_PHC		BIT(2)
+
+/**
+ * struct virtchnl_ptp_caps - Defines the PTP caps available to the VF.
+ * @caps: On send, VF sets what capabilities it requests. On reply, PF
+ *        indicates what has been enabled for this VF. The PF shall not set
+ *        bits which were not requested by the VF.
+ * @rsvd: Reserved bits for future extension.
+ *
+ * Structure that defines the PTP capabilities available to the VF. The VF
+ * sends VIRTCHNL_OP_1588_PTP_GET_CAPS, and must fill in the ptp_caps field
+ * indicating what capabilities it is requesting. The PF will respond with the
+ * same message with the virtchnl_ptp_caps structure indicating what is
+ * enabled for the VF.
+ *
+ * VIRTCHNL_1588_PTP_CAP_RX_TSTAMP indicates that the VF receive queues have
+ * receive timestamps enabled in the flexible descriptors. Note that this
+ * requires a VF to also negotiate to enable advanced flexible descriptors in
+ * the receive path instead of the default legacy descriptor format.
+ *
+ * VIRTCHNL_1588_PTP_CAP_READ_PHC indicates that the VF may read the PHC time
+ * via the VIRTCHNL_OP_1588_PTP_GET_TIME command.
+ *
+ * Note that in the future, additional capability flags may be added which
+ * indicate additional extended support. All fields marked as reserved by this
+ * header will be set to zero. VF implementations should verify this to ensure
+ * that future extensions do not break compatibility.
+ */
+struct virtchnl_ptp_caps {
+	u32 caps;
+	u8 rsvd[44];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(48, virtchnl_ptp_caps);
+
+/**
+ * struct virtchnl_phc_time - Contains the 64bits of PHC clock time in ns.
+ * @time: PHC time in nanoseconds
+ * @rsvd: Reserved for future extension
+ *
+ * Structure received with VIRTCHNL_OP_1588_PTP_GET_TIME. Contains the 64bits
+ * of PHC clock time in nanoseconds.
+ *
+ * VIRTCHNL_OP_1588_PTP_GET_TIME may be sent to request the current time of
+ * the PHC. This op is available in case direct access via the PHC registers
+ * is not available.
+ */
+struct virtchnl_phc_time {
+	u64 time;
+	u8 rsvd[8];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_phc_time);
+
 struct virtchnl_shaper_bw {
 	/* Unit is Kbps */
 	u32 committed;
@@ -1757,6 +1816,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 			}
 		}
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		valid_len = sizeof(struct virtchnl_ptp_caps);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		valid_len = sizeof(struct virtchnl_phc_time);
+		break;
 	/* These are always errors coming from the VF. */
 	case VIRTCHNL_OP_EVENT:
 	case VIRTCHNL_OP_UNKNOWN:

From 41758630dd7ea9dce3eb152168c979534b415ab0 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Wed, 12 Feb 2025 19:25:34 +0800
Subject: [PATCH 0539/2753] dt-bindings: mtd: cadence: document required
 clock-names

The clock-names property is required because the driver requests
the clock by name and not the index.
Update the example to use &clk instead of &nf_clk for the clocks
property to avoid confusion with the clock-names property "nf_clk".

Fixes: 1f05f823a16c (dt-bindings: mtd: cadence: convert cadence-nand-controller.txt to yaml)
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
index 0bed37a994c38..e1f4d7c35a885 100644
--- a/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
+++ b/Documentation/devicetree/bindings/mtd/cdns,hp-nfc.yaml
@@ -33,6 +33,10 @@ properties:
   clocks:
     maxItems: 1
 
+  clock-names:
+    items:
+      - const: nf_clk
+
   dmas:
     maxItems: 1
 
@@ -51,6 +55,7 @@ required:
   - reg-names
   - interrupts
   - clocks
+  - clock-names
 
 unevaluatedProperties: false
 
@@ -66,7 +71,8 @@ examples:
         #address-cells = <1>;
         #size-cells = <0>;
         interrupts = <GIC_SPI 97 IRQ_TYPE_LEVEL_HIGH>;
-        clocks = <&nf_clk>;
+        clocks = <&clk>;
+        clock-names = "nf_clk";
         cdns,board-delay-ps = <4830>;
 
         nand@0 {

From 7c1178a9df583454fc76be2ca8a6f0bef6613fba Mon Sep 17 00:00:00 2001
From: Simei Su <simei.su@intel.com>
Date: Wed, 6 Nov 2024 12:37:19 -0500
Subject: [PATCH 0540/2753] ice: support Rx timestamp on flex descriptor

To support Rx timestamp offload, VIRTCHNL_OP_1588_PTP_CAPS is sent by
the VF to request PTP capability and responded by the PF what capability
is enabled for that VF.

Hardware captures timestamps which contain only 32 bits of nominal
nanoseconds, as opposed to the 64bit timestamps that the stack expects.
To convert 32b to 64b, we need a current PHC time.
VIRTCHNL_OP_1588_PTP_GET_TIME is sent by the VF and responded by the
PF with the current PHC time.

Signed-off-by: Simei Su <simei.su@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c     |  3 -
 drivers/net/ethernet/intel/ice/ice_lib.c      |  5 +-
 drivers/net/ethernet/intel/ice/ice_ptp.c      |  4 +-
 drivers/net/ethernet/intel/ice/ice_ptp.h      |  8 ++
 drivers/net/ethernet/intel/ice/ice_vf_lib.h   |  3 +
 drivers/net/ethernet/intel/ice/ice_virtchnl.c | 76 ++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_virtchnl.h |  6 ++
 .../intel/ice/ice_virtchnl_allowlist.c        |  7 ++
 include/linux/avf/virtchnl.h                  | 15 +++-
 9 files changed, 116 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 0e862f20427ab..b3234a55a2532 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -473,9 +473,6 @@ static int ice_setup_rx_ctx(struct ice_rx_ring *ring)
 	 */
 	if (vsi->type != ICE_VSI_VF)
 		ice_write_qrxflxp_cntxt(hw, pf_q, rxdid, 0x3, true);
-	else
-		ice_write_qrxflxp_cntxt(hw, pf_q, ICE_RXDID_LEGACY_1, 0x3,
-					false);
 
 	/* Absolute queue number out of 2K needs to be passed */
 	err = ice_write_rxq_ctx(hw, &rlan_ctx, pf_q);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 978f308d3b1b9..7f5b229cab059 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1775,9 +1775,8 @@ void ice_update_eth_stats(struct ice_vsi *vsi)
  * @prio: priority for the RXDID for this queue
  * @ena_ts: true to enable timestamp and false to disable timestamp
  */
-void
-ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
-			bool ena_ts)
+void ice_write_qrxflxp_cntxt(struct ice_hw *hw, u16 pf_q, u32 rxdid, u32 prio,
+			     bool ena_ts)
 {
 	int regval = rd32(hw, QRXFLXP_CNTXT(pf_q));
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index b65114ff487b1..1bb0033347c76 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -298,8 +298,8 @@ void ice_ptp_restore_timestamp_mode(struct ice_pf *pf)
  * @sts: Optional parameter for holding a pair of system timestamps from
  *       the system clock. Will be ignored if NULL is given.
  */
-static u64
-ice_ptp_read_src_clk_reg(struct ice_pf *pf, struct ptp_system_timestamp *sts)
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts)
 {
 	struct ice_hw *hw = &pf->hw;
 	u32 hi, lo, lo2;
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.h b/drivers/net/ethernet/intel/ice/ice_ptp.h
index 783139de7f741..3b769a0cad00d 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.h
@@ -304,6 +304,8 @@ void ice_ptp_req_tx_single_tstamp(struct ice_ptp_tx *tx, u8 idx);
 void ice_ptp_complete_tx_single_tstamp(struct ice_ptp_tx *tx);
 enum ice_tx_tstamp_work ice_ptp_process_ts(struct ice_pf *pf);
 irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf);
+u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+			     struct ptp_system_timestamp *sts);
 
 u64 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 			const struct ice_pkt_ctx *pkt_ctx);
@@ -347,6 +349,12 @@ static inline irqreturn_t ice_ptp_ts_irq(struct ice_pf *pf)
 	return IRQ_HANDLED;
 }
 
+static inline u64 ice_ptp_read_src_clk_reg(struct ice_pf *pf,
+					   struct ptp_system_timestamp *sts)
+{
+	return 0;
+}
+
 static inline u64
 ice_ptp_get_rx_hwts(const union ice_32b_rx_flex_desc *rx_desc,
 		    const struct ice_pkt_ctx *pkt_ctx)
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.h b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
index 4261fe1c2bcd7..799b2c1f11844 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.h
@@ -124,6 +124,9 @@ struct ice_vf {
 	u8 spoofchk:1;
 	u8 link_forced:1;
 	u8 link_up:1;			/* only valid if VF link is forced */
+
+	u32 ptp_caps;
+
 	unsigned int min_tx_rate;	/* Minimum Tx bandwidth limit in Mbps */
 	unsigned int max_tx_rate;	/* Maximum Tx bandwidth limit in Mbps */
 	DECLARE_BITMAP(vf_states, ICE_VF_STATES_NBITS);	/* VF runtime states */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index ff4ad788d96ac..629f04d1c3ff1 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -498,6 +498,9 @@ static int ice_vc_get_vf_res_msg(struct ice_vf *vf, u8 *msg)
 	if (vf->driver_caps & VIRTCHNL_VF_OFFLOAD_QOS)
 		vfres->vf_cap_flags |= VIRTCHNL_VF_OFFLOAD_QOS;
 
+	if (vf->driver_caps & VIRTCHNL_VF_CAP_PTP)
+		vfres->vf_cap_flags |= VIRTCHNL_VF_CAP_PTP;
+
 	vfres->num_vsis = 1;
 	/* Tx and Rx queue are equal for VF */
 	vfres->num_queue_pairs = vsi->num_txq;
@@ -1975,6 +1978,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 	struct ice_vsi *vsi;
 	u8 act_prt, pri_prt;
 	int i = -1, q_idx;
+	bool ena_ts;
 
 	lag = pf->lag;
 	mutex_lock(&pf->lag_mutex);
@@ -2104,9 +2108,14 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg)
 				rxdid = ICE_RXDID_LEGACY_1;
 			}
 
+			ena_ts = ((vf->driver_caps &
+				  VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC) &&
+				  (vf->driver_caps & VIRTCHNL_VF_CAP_PTP) &&
+				  (qpi->rxq.flags & VIRTCHNL_PTP_RX_TSTAMP));
+
 			ice_write_qrxflxp_cntxt(&vsi->back->hw,
-						vsi->rxq_map[q_idx],
-						rxdid, 0x03, false);
+						vsi->rxq_map[q_idx], rxdid,
+						ICE_RXDID_PRIO, ena_ts);
 		}
 	}
 
@@ -4092,6 +4101,59 @@ static int ice_vc_dis_vlan_insertion_v2_msg(struct ice_vf *vf, u8 *msg)
 				     v_ret, NULL, 0);
 }
 
+static int ice_vc_get_ptp_cap(struct ice_vf *vf,
+			      const struct virtchnl_ptp_caps *msg)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	u32 caps = VIRTCHNL_1588_PTP_CAP_RX_TSTAMP |
+		   VIRTCHNL_1588_PTP_CAP_READ_PHC;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	if (msg->caps & caps)
+		vf->ptp_caps = caps;
+
+err:
+	/* send the response back to the VF */
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_CAPS, v_ret,
+				     (u8 *)&vf->ptp_caps,
+				     sizeof(struct virtchnl_ptp_caps));
+}
+
+static int ice_vc_get_phc_time(struct ice_vf *vf)
+{
+	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+	struct virtchnl_phc_time *phc_time = NULL;
+	struct ice_pf *pf = vf->pf;
+	u32 len = 0;
+	int ret;
+
+	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states))
+		goto err;
+
+	v_ret = VIRTCHNL_STATUS_SUCCESS;
+
+	phc_time = kzalloc(sizeof(*phc_time), GFP_KERNEL);
+	if (!phc_time) {
+		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
+		goto err;
+	}
+
+	len = sizeof(*phc_time);
+
+	phc_time->time = ice_ptp_read_src_clk_reg(pf, NULL);
+
+err:
+	/* send the response back to the VF */
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_1588_PTP_GET_TIME, v_ret,
+				    (u8 *)phc_time, len);
+	kfree(phc_time);
+	return ret;
+}
+
 static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_ver_msg = ice_vc_get_ver_msg,
 	.get_vf_res_msg = ice_vc_get_vf_res_msg,
@@ -4128,6 +4190,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 	/* If you add a new op here please make sure to add it to
 	 * ice_virtchnl_repr_ops as well.
 	 */
@@ -4264,6 +4328,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.get_qos_caps = ice_vc_get_qos_caps,
 	.cfg_q_bw = ice_vc_cfg_q_bw,
 	.cfg_q_quanta = ice_vc_cfg_q_quanta,
+	.get_ptp_cap = ice_vc_get_ptp_cap,
+	.get_phc_time = ice_vc_get_phc_time,
 };
 
 /**
@@ -4501,6 +4567,12 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event,
 	case VIRTCHNL_OP_CONFIG_QUANTA:
 		err = ops->cfg_q_quanta(vf, msg);
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		err = ops->get_ptp_cap(vf, (const void *)msg);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		err = ops->get_phc_time(vf);
+		break;
 	case VIRTCHNL_OP_UNKNOWN:
 	default:
 		dev_err(dev, "Unsupported opcode %d from VF %d\n", v_opcode,
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index 0c629aef9baf1..222990f229d5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -26,6 +26,9 @@
 #define ICE_MAX_MACADDR_PER_VF		18
 #define ICE_FLEX_DESC_RXDID_MAX_NUM	64
 
+/* Priority to be compared against previous priority from the pipe */
+#define ICE_RXDID_PRIO			0x03
+
 /* VFs only get a single VSI. For ice hardware, the VF does not need to know
  * its VSI index. However, the virtchnl interface requires a VSI number,
  * mainly due to legacy hardware.
@@ -72,6 +75,9 @@ struct ice_virtchnl_ops {
 	int (*cfg_q_tc_map)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_bw)(struct ice_vf *vf, u8 *msg);
 	int (*cfg_q_quanta)(struct ice_vf *vf, u8 *msg);
+	int (*get_ptp_cap)(struct ice_vf *vf,
+			   const struct virtchnl_ptp_caps *msg);
+	int (*get_phc_time)(struct ice_vf *vf);
 };
 
 #ifdef CONFIG_PCI_IOV
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index c105a82ee1364..a3d1579a619a5 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -84,6 +84,12 @@ static const u32 fdir_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_ADD_FDIR_FILTER, VIRTCHNL_OP_DEL_FDIR_FILTER,
 };
 
+/* VIRTCHNL_VF_CAP_PTP */
+static const u32 ptp_allowlist_opcodes[] = {
+	VIRTCHNL_OP_1588_PTP_GET_CAPS,
+	VIRTCHNL_OP_1588_PTP_GET_TIME,
+};
+
 static const u32 tc_allowlist_opcodes[] = {
 	VIRTCHNL_OP_GET_QOS_CAPS, VIRTCHNL_OP_CONFIG_QUEUE_BW,
 	VIRTCHNL_OP_CONFIG_QUANTA,
@@ -110,6 +116,7 @@ static const struct allowlist_opcode_info allowlist_opcodes[] = {
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_FDIR_PF, fdir_pf_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_VLAN_V2, vlan_v2_allowlist_opcodes),
 	ALLOW_ITEM(VIRTCHNL_VF_OFFLOAD_QOS, tc_allowlist_opcodes),
+	ALLOW_ITEM(VIRTCHNL_VF_CAP_PTP, ptp_allowlist_opcodes),
 };
 
 /**
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 92866e449b21a..56baf97c44d02 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -313,6 +313,18 @@ struct virtchnl_txq_info {
 
 VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info);
 
+/* virtchnl_rxq_info_flags - definition of bits in the flags field of the
+ *			     virtchnl_rxq_info structure.
+ *
+ * @VIRTCHNL_PTP_RX_TSTAMP: request to enable Rx timestamping
+ *
+ * Other flag bits are currently reserved and they may be extended in the
+ * future.
+ */
+enum virtchnl_rxq_info_flags {
+	VIRTCHNL_PTP_RX_TSTAMP = BIT(0),
+};
+
 /* VIRTCHNL_OP_CONFIG_RX_QUEUE
  * VF sends this message to set up parameters for one RX queue.
  * External data buffer contains one instance of virtchnl_rxq_info.
@@ -336,7 +348,8 @@ struct virtchnl_rxq_info {
 	u32 max_pkt_size;
 	u8 crc_disable;
 	u8 rxdid;
-	u8 pad1[2];
+	enum virtchnl_rxq_info_flags flags:8; /* see virtchnl_rxq_info_flags */
+	u8 pad1;
 	u64 dma_ring_addr;
 
 	/* see enum virtchnl_rx_hsplit; deprecated with AVF 1.0 */

From 6a88c797ab4005cd5dd02575c1b3d1e7b53fe715 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:20 -0500
Subject: [PATCH 0541/2753] virtchnl: add enumeration for the rxdid format

Support for allowing VF to negotiate the descriptor format requires that
the VF specify which descriptor format to use when requesting Rx queues.
The VF is supposed to request the set of supported formats via the new
VIRTCHNL_OP_GET_SUPPORTED_RXDIDS, and then set one of the supported
formats in the rxdid field of the virtchnl_rxq_info structure.

The virtchnl.h header does not provide an enumeration of the format
values. The existing implementations in the PF directly use the values
from the DDP package.

Make the formats explicit by defining an enumeration of the RXDIDs.
Provide an enumeration for the values as well as the bit positions as
returned by the supported_rxdids data from the
VIRTCHNL_OP_GET_SUPPORTED_RXDIDS.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 include/linux/avf/virtchnl.h | 50 +++++++++++++++++++++++++++++++++++-
 1 file changed, 49 insertions(+), 1 deletion(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 56baf97c44d02..bc10e6ffa50b6 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -313,6 +313,48 @@ struct virtchnl_txq_info {
 
 VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info);
 
+/* RX descriptor IDs (range from 0 to 63) */
+enum virtchnl_rx_desc_ids {
+	VIRTCHNL_RXDID_0_16B_BASE		= 0,
+	VIRTCHNL_RXDID_1_32B_BASE		= 1,
+	VIRTCHNL_RXDID_2_FLEX_SQ_NIC		= 2,
+	VIRTCHNL_RXDID_3_FLEX_SQ_SW		= 3,
+	VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB	= 4,
+	VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL	= 5,
+	VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2		= 6,
+	VIRTCHNL_RXDID_7_HW_RSVD		= 7,
+	/* 8 through 15 are reserved */
+	VIRTCHNL_RXDID_16_COMMS_GENERIC		= 16,
+	VIRTCHNL_RXDID_17_COMMS_AUX_VLAN	= 17,
+	VIRTCHNL_RXDID_18_COMMS_AUX_IPV4	= 18,
+	VIRTCHNL_RXDID_19_COMMS_AUX_IPV6	= 19,
+	VIRTCHNL_RXDID_20_COMMS_AUX_FLOW	= 20,
+	VIRTCHNL_RXDID_21_COMMS_AUX_TCP		= 21,
+	/* 22 through 63 are reserved */
+};
+
+#define VIRTCHNL_RXDID_BIT(x)			BIT_ULL(VIRTCHNL_RXDID_##x)
+
+/* RX descriptor ID bitmasks */
+enum virtchnl_rx_desc_id_bitmasks {
+	VIRTCHNL_RXDID_0_16B_BASE_M		= VIRTCHNL_RXDID_BIT(0_16B_BASE),
+	VIRTCHNL_RXDID_1_32B_BASE_M		= VIRTCHNL_RXDID_BIT(1_32B_BASE),
+	VIRTCHNL_RXDID_2_FLEX_SQ_NIC_M		= VIRTCHNL_RXDID_BIT(2_FLEX_SQ_NIC),
+	VIRTCHNL_RXDID_3_FLEX_SQ_SW_M		= VIRTCHNL_RXDID_BIT(3_FLEX_SQ_SW),
+	VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB_M	= VIRTCHNL_RXDID_BIT(4_FLEX_SQ_NIC_VEB),
+	VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL_M	= VIRTCHNL_RXDID_BIT(5_FLEX_SQ_NIC_ACL),
+	VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2_M	= VIRTCHNL_RXDID_BIT(6_FLEX_SQ_NIC_2),
+	VIRTCHNL_RXDID_7_HW_RSVD_M		= VIRTCHNL_RXDID_BIT(7_HW_RSVD),
+	/* 8 through 15 are reserved */
+	VIRTCHNL_RXDID_16_COMMS_GENERIC_M	= VIRTCHNL_RXDID_BIT(16_COMMS_GENERIC),
+	VIRTCHNL_RXDID_17_COMMS_AUX_VLAN_M	= VIRTCHNL_RXDID_BIT(17_COMMS_AUX_VLAN),
+	VIRTCHNL_RXDID_18_COMMS_AUX_IPV4_M	= VIRTCHNL_RXDID_BIT(18_COMMS_AUX_IPV4),
+	VIRTCHNL_RXDID_19_COMMS_AUX_IPV6_M	= VIRTCHNL_RXDID_BIT(19_COMMS_AUX_IPV6),
+	VIRTCHNL_RXDID_20_COMMS_AUX_FLOW_M	= VIRTCHNL_RXDID_BIT(20_COMMS_AUX_FLOW),
+	VIRTCHNL_RXDID_21_COMMS_AUX_TCP_M	= VIRTCHNL_RXDID_BIT(21_COMMS_AUX_TCP),
+	/* 22 through 63 are reserved */
+};
+
 /* virtchnl_rxq_info_flags - definition of bits in the flags field of the
  *			     virtchnl_rxq_info structure.
  *
@@ -347,7 +389,12 @@ struct virtchnl_rxq_info {
 	u32 databuffer_size;
 	u32 max_pkt_size;
 	u8 crc_disable;
-	u8 rxdid;
+	/* see enum virtchnl_rx_desc_ids;
+	 * only used when VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is supported. Note
+	 * that when the offload is not supported, the descriptor format aligns
+	 * with VIRTCHNL_RXDID_1_32B_BASE.
+	 */
+	enum virtchnl_rx_desc_ids rxdid:8;
 	enum virtchnl_rxq_info_flags flags:8; /* see virtchnl_rxq_info_flags */
 	u8 pad1;
 	u64 dma_ring_addr;
@@ -1050,6 +1097,7 @@ struct virtchnl_filter {
 VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter);
 
 struct virtchnl_supported_rxdids {
+	/* see enum virtchnl_rx_desc_id_bitmasks */
 	u64 supported_rxdids;
 };
 

From 2a86e210f1a102614116e347efda59896f780417 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:21 -0500
Subject: [PATCH 0542/2753] iavf: add support for negotiating flexible RXDID
 format

Enable support for VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, to enable the VF
driver the ability to determine what Rx descriptor formats are
available. This requires sending an additional message during
initialization and reset, the VIRTCHNL_OP_GET_SUPPORTED_RXDIDS. This
operation requests the supported Rx descriptor IDs available from the
PF.

This is treated the same way that VLAN V2 capabilities are handled. Add
a new set of extended capability flags, used to process send and receipt
of the VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message.

This ensures we finish negotiating for the supported descriptor formats
prior to beginning configuration of receive queues.

This change stores the supported format bitmap into the iavf_adapter
structure. Additionally, if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is enabled
by the PF, we need to make sure that the Rx queue configuration
specifies the format.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h        |  20 ++-
 drivers/net/ethernet/intel/iavf/iavf_main.c   | 123 ++++++++++++++++--
 drivers/net/ethernet/intel/iavf/iavf_txrx.h   |   2 +
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |  40 ++++++
 drivers/net/ethernet/intel/ice/ice_virtchnl.c |   4 +-
 include/linux/avf/virtchnl.h                  |   5 -
 6 files changed, 178 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index 532a0a595fe8e..a520374c52285 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -271,6 +271,7 @@ struct iavf_adapter {
 	/* Lock to protect accesses to MAC and VLAN lists */
 	spinlock_t mac_vlan_list_lock;
 	char misc_vector_name[IFNAMSIZ + 9];
+	u8 rxdid;
 	int num_active_queues;
 	int num_req_queues;
 
@@ -343,6 +344,14 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CONFIGURE_QUEUES_BW		BIT_ULL(39)
 #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
 #define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
+#define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS		BIT_ULL(42)
+
+	/* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in
+	 * order to negotiated extended capabilities.
+	 */
+#define IAVF_FLAG_AQ_EXTENDED_CAPS			\
+	(IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS |	\
+	 IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -354,10 +363,14 @@ struct iavf_adapter {
 	u64 extended_caps;
 #define IAVF_EXTENDED_CAP_SEND_VLAN_V2			BIT_ULL(0)
 #define IAVF_EXTENDED_CAP_RECV_VLAN_V2			BIT_ULL(1)
+#define IAVF_EXTENDED_CAP_SEND_RXDID			BIT_ULL(2)
+#define IAVF_EXTENDED_CAP_RECV_RXDID			BIT_ULL(3)
 
 #define IAVF_EXTENDED_CAPS				\
 	(IAVF_EXTENDED_CAP_SEND_VLAN_V2 |		\
-	 IAVF_EXTENDED_CAP_RECV_VLAN_V2)
+	 IAVF_EXTENDED_CAP_RECV_VLAN_V2 |		\
+	 IAVF_EXTENDED_CAP_SEND_RXDID |			\
+	 IAVF_EXTENDED_CAP_RECV_RXDID)
 
 	/* Lock to prevent possible clobbering of
 	 * current_netdev_promisc_flags
@@ -417,12 +430,15 @@ struct iavf_adapter {
 			     VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF)
 #define QOS_ALLOWED(_a) ((_a)->vf_res->vf_cap_flags & \
 			 VIRTCHNL_VF_OFFLOAD_QOS)
+#define IAVF_RXDID_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;
 #define PF_IS_V11(_a) (((_a)->pf_version.major == 1) && \
 		       ((_a)->pf_version.minor == 1))
 	struct virtchnl_vlan_caps vlan_v2_caps;
+	u64 supp_rxdids;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
 	struct virtchnl_qos_cap_list *qos_caps;
@@ -555,6 +571,8 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter);
 int iavf_get_vf_config(struct iavf_adapter *adapter);
 int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter);
 int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter);
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter);
 void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter);
 u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter);
 void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 852e5b62f0a5d..938155656a518 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -709,6 +709,38 @@ static void iavf_configure_tx(struct iavf_adapter *adapter)
 		adapter->tx_rings[i].tail = hw->hw_addr + IAVF_QTX_TAIL1(i);
 }
 
+/**
+ * iavf_select_rx_desc_format - Select Rx descriptor format
+ * @adapter: adapter private structure
+ *
+ * Select what Rx descriptor format based on availability and enabled
+ * features.
+ *
+ * Return: the desired RXDID to select for a given Rx queue, as defined by
+ *         enum virtchnl_rxdid_format.
+ */
+static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter)
+{
+	u64 rxdids = adapter->supp_rxdids;
+
+	/* If we did not negotiate VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC, we must
+	 * stick with the default value of the legacy 32 byte format.
+	 */
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return VIRTCHNL_RXDID_1_32B_BASE;
+
+	/* Warn if the PF does not list support for the default legacy
+	 * descriptor format. This shouldn't happen, as this is the format
+	 * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is
+	 * likely caused by a bug in the PF implementation failing to indicate
+	 * support for the format.
+	 */
+	if (!(rxdids & VIRTCHNL_RXDID_1_32B_BASE_M))
+		netdev_warn(adapter->netdev, "PF does not list support for default Rx descriptor format\n");
+
+	return VIRTCHNL_RXDID_1_32B_BASE;
+}
+
 /**
  * iavf_configure_rx - Configure Receive Unit after Reset
  * @adapter: board private structure
@@ -719,8 +751,12 @@ static void iavf_configure_rx(struct iavf_adapter *adapter)
 {
 	struct iavf_hw *hw = &adapter->hw;
 
-	for (u32 i = 0; i < adapter->num_active_queues; i++)
+	adapter->rxdid = iavf_select_rx_desc_format(adapter);
+
+	for (u32 i = 0; i < adapter->num_active_queues; i++) {
 		adapter->rx_rings[i].tail = hw->hw_addr + IAVF_QRX_TAIL1(i);
+		adapter->rx_rings[i].rxdid = adapter->rxdid;
+	}
 }
 
 /**
@@ -2071,6 +2107,8 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return iavf_send_vf_config_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS)
 		return iavf_send_vf_offload_vlan_v2_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
+		return iavf_send_vf_supported_rxdids_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
 		iavf_disable_queues(adapter);
 		return 0;
@@ -2599,6 +2637,63 @@ static void iavf_init_recv_offload_vlan_v2_caps(struct iavf_adapter *adapter)
 	iavf_change_state(adapter, __IAVF_INIT_FAILED);
 }
 
+/**
+ * iavf_init_send_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for supported RXDIDs to the PF.
+ * Must clear IAVF_EXTENDED_CAP_RECV_RXDID if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC.
+ */
+static void iavf_init_send_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	ret = iavf_send_vf_supported_rxdids_msg(adapter);
+	if (ret == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC. In this
+		 * case, we did not send the capability exchange message and
+		 * do not expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_RXDID;
+}
+
+/**
+ * iavf_init_recv_supported_rxdids - part of querying for supported RXDID
+ * formats
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the supported RXDIDs message from the PF.
+ **/
+static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter)
+{
+	int ret;
+
+	memset(&adapter->supp_rxdids, 0, sizeof(adapter->supp_rxdids));
+
+	ret = iavf_get_vf_supported_rxdids(adapter);
+	if (ret)
+		goto err;
+
+	/* We've processed the PF response to the
+	 * VIRTCHNL_OP_GET_SUPPORTED_RXDIDS message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_RXDID;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_RXDID;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
 /**
  * iavf_init_process_extended_caps - Part of driver startup
  * @adapter: board private structure
@@ -2623,6 +2718,15 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter)
 		return;
 	}
 
+	/* Process capability exchange for RXDID formats */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_RXDID) {
+		iavf_init_send_supported_rxdids(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_RXDID) {
+		iavf_init_recv_supported_rxdids(adapter);
+		return;
+	}
+
 	/* When we reach here, no further extended capabilities exchanges are
 	 * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER
 	 */
@@ -3139,15 +3243,18 @@ static void iavf_reset_task(struct work_struct *work)
 	}
 
 	adapter->aq_required |= IAVF_FLAG_AQ_GET_CONFIG;
-	/* always set since VIRTCHNL_OP_GET_VF_RESOURCES has not been
-	 * sent/received yet, so VLAN_V2_ALLOWED() cannot is not reliable here,
-	 * however the VIRTCHNL_OP_GET_OFFLOAD_VLAN_V2_CAPS won't be sent until
-	 * VIRTCHNL_OP_GET_VF_RESOURCES and VIRTCHNL_VF_OFFLOAD_VLAN_V2 have
-	 * been successfully sent and negotiated
-	 */
-	adapter->aq_required |= IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS;
 	adapter->aq_required |= IAVF_FLAG_AQ_MAP_VECTORS;
 
+	/* Certain capabilities require an extended negotiation process using
+	 * extra messages that must be processed after getting the VF
+	 * configuration. The related checks such as VLAN_V2_ALLOWED() are not
+	 * reliable here, since the configuration has not yet been negotiated.
+	 *
+	 * Always set these flags, since them related VIRTCHNL messages won't
+	 * be sent until after VIRTCHNL_OP_GET_VF_RESOURCES.
+	 */
+	adapter->aq_required |= IAVF_FLAG_AQ_EXTENDED_CAPS;
+
 	spin_lock_bh(&adapter->mac_vlan_list_lock);
 
 	/* Delete filter for the current MAC address, it could have
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index f97c702c0802d..15a05e30434de 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -262,6 +262,8 @@ struct iavf_ring {
 	u16 next_to_use;
 	u16 next_to_clean;
 
+	u16 rxdid;		/* Rx descriptor format */
+
 	u16 flags;
 #define IAVF_TXR_FLAGS_WB_ON_ITR		BIT(0)
 #define IAVF_TXR_FLAGS_ARM_WB			BIT(1)
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 15d388b431c51..42e906941811b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -144,6 +144,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_ENCAP |
 	       VIRTCHNL_VF_OFFLOAD_TC_U32 |
 	       VIRTCHNL_VF_OFFLOAD_VLAN_V2 |
+	       VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC |
 	       VIRTCHNL_VF_OFFLOAD_CRC |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
 	       VIRTCHNL_VF_OFFLOAD_REQ_QUEUES |
@@ -177,6 +178,19 @@ int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter)
 				NULL, 0);
 }
 
+int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter)
+{
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS;
+
+	if (!IAVF_RXDID_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_GET_SUPPORTED_RXDIDS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
+				NULL, 0);
+}
+
 /**
  * iavf_validate_num_queues
  * @adapter: adapter structure
@@ -263,6 +277,23 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter)
 	return err;
 }
 
+int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter)
+{
+	struct iavf_arq_event_info event;
+	u64 rxdids;
+	int err;
+
+	event.msg_buf = (u8 *)&rxdids;
+	event.buf_len = sizeof(rxdids);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_GET_SUPPORTED_RXDIDS);
+	if (!err)
+		adapter->supp_rxdids = rxdids;
+
+	return err;
+}
+
 /**
  * iavf_configure_queues
  * @adapter: adapter structure
@@ -309,6 +340,8 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		vqpi->rxq.dma_ring_addr = adapter->rx_rings[i].dma;
 		vqpi->rxq.max_pkt_size = max_frame;
 		vqpi->rxq.databuffer_size = adapter->rx_rings[i].rx_buf_len;
+		if (IAVF_RXDID_ALLOWED(adapter))
+			vqpi->rxq.rxdid = adapter->rxdid;
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
@@ -2508,6 +2541,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_MAC_FILTER |
 			aq_required;
 		}
+		break;
+	case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
+		if (msglen != sizeof(u64))
+			return;
+
+		adapter->supp_rxdids = *(u64 *)msg;
+
 		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 629f04d1c3ff1..674767781fe42 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -3040,8 +3040,8 @@ static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
 static int ice_vc_query_rxdid(struct ice_vf *vf)
 {
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_supported_rxdids rxdid = {};
 	struct ice_pf *pf = vf->pf;
+	u64 rxdid;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
@@ -3053,7 +3053,7 @@ static int ice_vc_query_rxdid(struct ice_vf *vf)
 		goto err;
 	}
 
-	rxdid.supported_rxdids = pf->supported_rxdids;
+	rxdid = pf->supported_rxdids;
 
 err:
 	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_SUPPORTED_RXDIDS,
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index bc10e6ffa50b6..4811b9a146048 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -1096,11 +1096,6 @@ struct virtchnl_filter {
 
 VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter);
 
-struct virtchnl_supported_rxdids {
-	/* see enum virtchnl_rx_desc_id_bitmasks */
-	u64 supported_rxdids;
-};
-
 /* VIRTCHNL_OP_EVENT
  * PF sends this message to inform the VF driver of events that may affect it.
  * No direct response is expected from the VF, though it may generate other

From 3247d65ad9de39ae11261274899ac6a9fc04b7a9 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:22 -0500
Subject: [PATCH 0543/2753] iavf: negotiate PTP capabilities

Add a new extended capabilities negotiation to exchange information from
the PF about what PTP capabilities are supported by this VF. This
requires sending a VIRTCHNL_OP_1588_PTP_GET_CAPS message, and waiting
for the response from the PF. Handle this early on during the VF
initialization.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h        | 17 +++++-
 drivers/net/ethernet/intel/iavf/iavf_main.c   | 60 +++++++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.h    |  9 +++
 drivers/net/ethernet/intel/iavf/iavf_types.h  | 34 +++++++++++
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   | 60 +++++++++++++++++++
 5 files changed, 178 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/intel/iavf/iavf_ptp.h
 create mode 100644 drivers/net/ethernet/intel/iavf/iavf_types.h

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index a520374c52285..b6e52992e2702 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -41,6 +41,7 @@
 #include "iavf_txrx.h"
 #include "iavf_fdir.h"
 #include "iavf_adv_rss.h"
+#include "iavf_types.h"
 #include <linux/bitmap.h>
 
 #define DEFAULT_DEBUG_LEVEL_SHIFT 3
@@ -345,13 +346,16 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CFG_QUEUES_QUANTA_SIZE		BIT_ULL(40)
 #define IAVF_FLAG_AQ_GET_QOS_CAPS			BIT_ULL(41)
 #define IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS		BIT_ULL(42)
+#define IAVF_FLAG_AQ_GET_PTP_CAPS			BIT_ULL(43)
+#define IAVF_FLAG_AQ_SEND_PTP_CMD			BIT_ULL(44)
 
 	/* AQ messages that must be sent after IAVF_FLAG_AQ_GET_CONFIG, in
 	 * order to negotiated extended capabilities.
 	 */
 #define IAVF_FLAG_AQ_EXTENDED_CAPS			\
 	(IAVF_FLAG_AQ_GET_OFFLOAD_VLAN_V2_CAPS |	\
-	 IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
+	 IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS |		\
+	 IAVF_FLAG_AQ_GET_PTP_CAPS)
 
 	/* flags for processing extended capability messages during
 	 * __IAVF_INIT_EXTENDED_CAPS. Each capability exchange requires
@@ -365,12 +369,16 @@ struct iavf_adapter {
 #define IAVF_EXTENDED_CAP_RECV_VLAN_V2			BIT_ULL(1)
 #define IAVF_EXTENDED_CAP_SEND_RXDID			BIT_ULL(2)
 #define IAVF_EXTENDED_CAP_RECV_RXDID			BIT_ULL(3)
+#define IAVF_EXTENDED_CAP_SEND_PTP			BIT_ULL(4)
+#define IAVF_EXTENDED_CAP_RECV_PTP			BIT_ULL(5)
 
 #define IAVF_EXTENDED_CAPS				\
 	(IAVF_EXTENDED_CAP_SEND_VLAN_V2 |		\
 	 IAVF_EXTENDED_CAP_RECV_VLAN_V2 |		\
 	 IAVF_EXTENDED_CAP_SEND_RXDID |			\
-	 IAVF_EXTENDED_CAP_RECV_RXDID)
+	 IAVF_EXTENDED_CAP_RECV_RXDID |			\
+	 IAVF_EXTENDED_CAP_SEND_PTP |			\
+	 IAVF_EXTENDED_CAP_RECV_PTP)
 
 	/* Lock to prevent possible clobbering of
 	 * current_netdev_promisc_flags
@@ -432,6 +440,8 @@ struct iavf_adapter {
 			 VIRTCHNL_VF_OFFLOAD_QOS)
 #define IAVF_RXDID_ALLOWED(a)						\
 	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC)
+#define IAVF_PTP_ALLOWED(a)						\
+	((a)->vf_res->vf_cap_flags & VIRTCHNL_VF_CAP_PTP)
 	struct virtchnl_vf_resource *vf_res; /* incl. all VSIs */
 	struct virtchnl_vsi_resource *vsi_res; /* our LAN VSI */
 	struct virtchnl_version_info pf_version;
@@ -439,6 +449,7 @@ struct iavf_adapter {
 		       ((_a)->pf_version.minor == 1))
 	struct virtchnl_vlan_caps vlan_v2_caps;
 	u64 supp_rxdids;
+	struct iavf_ptp ptp;
 	u16 msg_enable;
 	struct iavf_eth_stats current_stats;
 	struct virtchnl_qos_cap_list *qos_caps;
@@ -573,6 +584,8 @@ int iavf_get_vf_vlan_v2_caps(struct iavf_adapter *adapter);
 int iavf_send_vf_offload_vlan_v2_msg(struct iavf_adapter *adapter);
 int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter);
 int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter);
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter);
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter);
 void iavf_set_queue_vlan_tag_loc(struct iavf_adapter *adapter);
 u16 iavf_get_num_vlans_added(struct iavf_adapter *adapter);
 void iavf_irq_enable(struct iavf_adapter *adapter, bool flush);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 938155656a518..edb9679cbad47 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2109,6 +2109,8 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		return iavf_send_vf_offload_vlan_v2_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_GET_SUPPORTED_RXDIDS)
 		return iavf_send_vf_supported_rxdids_msg(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_PTP_CAPS)
+		return iavf_send_vf_ptp_caps_msg(adapter);
 	if (adapter->aq_required & IAVF_FLAG_AQ_DISABLE_QUEUES) {
 		iavf_disable_queues(adapter);
 		return 0;
@@ -2694,6 +2696,55 @@ static void iavf_init_recv_supported_rxdids(struct iavf_adapter *adapter)
 	iavf_change_state(adapter, __IAVF_INIT_FAILED);
 }
 
+/**
+ * iavf_init_send_ptp_caps - part of querying for extended PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes send of the request for 1588 PTP capabilities to the PF.
+ * Must clear IAVF_EXTENDED_CAP_SEND_PTP if the message is not sent, e.g.
+ * due to the PF not negotiating VIRTCHNL_VF_PTP_CAP
+ */
+static void iavf_init_send_ptp_caps(struct iavf_adapter *adapter)
+{
+	if (iavf_send_vf_ptp_caps_msg(adapter) == -EOPNOTSUPP) {
+		/* PF does not support VIRTCHNL_VF_PTP_CAP. In this case, we
+		 * did not send the capability exchange message and do not
+		 * expect a response.
+		 */
+		adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	}
+
+	/* We sent the message, so move on to the next step */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_SEND_PTP;
+}
+
+/**
+ * iavf_init_recv_ptp_caps - part of querying for supported PTP capabilities
+ * @adapter: board private structure
+ *
+ * Function processes receipt of the PTP capabilities supported on this VF.
+ **/
+static void iavf_init_recv_ptp_caps(struct iavf_adapter *adapter)
+{
+	memset(&adapter->ptp.hw_caps, 0, sizeof(adapter->ptp.hw_caps));
+
+	if (iavf_get_vf_ptp_caps(adapter))
+		goto err;
+
+	/* We've processed the PF response to the VIRTCHNL_OP_1588_PTP_GET_CAPS
+	 * message we sent previously.
+	 */
+	adapter->extended_caps &= ~IAVF_EXTENDED_CAP_RECV_PTP;
+	return;
+
+err:
+	/* We didn't receive a reply. Make sure we try sending again when
+	 * __IAVF_INIT_FAILED attempts to recover.
+	 */
+	adapter->extended_caps |= IAVF_EXTENDED_CAP_SEND_PTP;
+	iavf_change_state(adapter, __IAVF_INIT_FAILED);
+}
+
 /**
  * iavf_init_process_extended_caps - Part of driver startup
  * @adapter: board private structure
@@ -2727,6 +2778,15 @@ static void iavf_init_process_extended_caps(struct iavf_adapter *adapter)
 		return;
 	}
 
+	/* Process capability exchange for PTP features */
+	if (adapter->extended_caps & IAVF_EXTENDED_CAP_SEND_PTP) {
+		iavf_init_send_ptp_caps(adapter);
+		return;
+	} else if (adapter->extended_caps & IAVF_EXTENDED_CAP_RECV_PTP) {
+		iavf_init_recv_ptp_caps(adapter);
+		return;
+	}
+
 	/* When we reach here, no further extended capabilities exchanges are
 	 * necessary, so we finally transition into __IAVF_INIT_CONFIG_ADAPTER
 	 */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
new file mode 100644
index 0000000000000..65678e76c34f0
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_PTP_H_
+#define _IAVF_PTP_H_
+
+#include "iavf_types.h"
+
+#endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_types.h b/drivers/net/ethernet/intel/iavf/iavf_types.h
new file mode 100644
index 0000000000000..a095855122bf2
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_types.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright(c) 2024 Intel Corporation. */
+
+#ifndef _IAVF_TYPES_H_
+#define _IAVF_TYPES_H_
+
+#include "iavf_types.h"
+
+#include <linux/avf/virtchnl.h>
+#include <linux/ptp_clock_kernel.h>
+
+/* structure used to queue PTP commands for processing */
+struct iavf_ptp_aq_cmd {
+	struct list_head list;
+	enum virtchnl_ops v_opcode:16;
+	u16 msglen;
+	u8 msg[] __counted_by(msglen);
+};
+
+struct iavf_ptp {
+	wait_queue_head_t phc_time_waitqueue;
+	struct virtchnl_ptp_caps hw_caps;
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct list_head aq_cmds;
+	u64 cached_phc_time;
+	unsigned long cached_phc_updated;
+	/* Lock protecting access to the AQ command list */
+	struct mutex aq_cmd_lock;
+	struct kernel_hwtstamp_config hwtstamp_config;
+	bool phc_time_ready:1;
+};
+
+#endif /* _IAVF_TYPES_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 42e906941811b..65b0028bb968b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -148,6 +148,7 @@ int iavf_send_vf_config_msg(struct iavf_adapter *adapter)
 	       VIRTCHNL_VF_OFFLOAD_CRC |
 	       VIRTCHNL_VF_OFFLOAD_ENCAP_CSUM |
 	       VIRTCHNL_VF_OFFLOAD_REQ_QUEUES |
+	       VIRTCHNL_VF_CAP_PTP |
 	       VIRTCHNL_VF_OFFLOAD_ADQ |
 	       VIRTCHNL_VF_OFFLOAD_USO |
 	       VIRTCHNL_VF_OFFLOAD_FDIR_PF |
@@ -191,6 +192,41 @@ int iavf_send_vf_supported_rxdids_msg(struct iavf_adapter *adapter)
 				NULL, 0);
 }
 
+/**
+ * iavf_send_vf_ptp_caps_msg - Send request for PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Send the VIRTCHNL_OP_1588_PTP_GET_CAPS command to the PF to request the PTP
+ * capabilities available to this device. This includes the following
+ * potential access:
+ *
+ * * READ_PHC - access to read the PTP hardware clock time
+ * * RX_TSTAMP - access to request Rx timestamps on all received packets
+ *
+ * The PF will reply with the same opcode a filled out copy of the
+ * virtchnl_ptp_caps structure which defines the specifics of which features
+ * are accessible to this device.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+int iavf_send_vf_ptp_caps_msg(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps hw_caps = {
+		.caps = VIRTCHNL_1588_PTP_CAP_READ_PHC |
+			VIRTCHNL_1588_PTP_CAP_RX_TSTAMP
+	};
+
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_PTP_CAPS;
+
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return -EOPNOTSUPP;
+
+	adapter->current_op = VIRTCHNL_OP_1588_PTP_GET_CAPS;
+
+	return iavf_send_pf_msg(adapter, VIRTCHNL_OP_1588_PTP_GET_CAPS,
+				(u8 *)&hw_caps, sizeof(hw_caps));
+}
+
 /**
  * iavf_validate_num_queues
  * @adapter: adapter structure
@@ -294,6 +330,23 @@ int iavf_get_vf_supported_rxdids(struct iavf_adapter *adapter)
 	return err;
 }
 
+int iavf_get_vf_ptp_caps(struct iavf_adapter *adapter)
+{
+	struct virtchnl_ptp_caps caps = {};
+	struct iavf_arq_event_info event;
+	int err;
+
+	event.msg_buf = (u8 *)&caps;
+	event.buf_len = sizeof(caps);
+
+	err = iavf_poll_virtchnl_msg(&adapter->hw, &event,
+				     VIRTCHNL_OP_1588_PTP_GET_CAPS);
+	if (!err)
+		adapter->ptp.hw_caps = caps;
+
+	return err;
+}
+
 /**
  * iavf_configure_queues
  * @adapter: adapter structure
@@ -2548,6 +2601,13 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		adapter->supp_rxdids = *(u64 *)msg;
 
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		if (msglen != sizeof(adapter->ptp.hw_caps))
+			return;
+
+		adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg;
+
 		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */

From d734223b2f0dc4f5826204ee628ad6273148223d Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:23 -0500
Subject: [PATCH 0544/2753] iavf: add initial framework for registering PTP
 clock

Add the iavf_ptp.c file and fill it in with a skeleton framework to
allow registering the PTP clock device.
Add implementation of helper functions to check if a PTP capability
is supported and handle change in PTP capabilities.
Enabling virtual clock would be possible, though it would probably
perform poorly due to the lack of direct time access.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Sai Krishna <saikrishnag@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Co-developed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/Kconfig            |   1 +
 drivers/net/ethernet/intel/iavf/Makefile      |   2 +
 drivers/net/ethernet/intel/iavf/iavf_main.c   |   6 +
 drivers/net/ethernet/intel/iavf/iavf_ptp.c    | 122 ++++++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.h    |  14 ++
 drivers/net/ethernet/intel/iavf/iavf_txrx.h   |   2 +
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |   8 ++
 7 files changed, 155 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/iavf/iavf_ptp.c

diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig
index 26b9938bc38d6..1640d2f278330 100644
--- a/drivers/net/ethernet/intel/Kconfig
+++ b/drivers/net/ethernet/intel/Kconfig
@@ -264,6 +264,7 @@ config I40EVF
 	tristate "Intel(R) Ethernet Adaptive Virtual Function support"
 	select IAVF
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	help
 	  This driver supports virtual functions for Intel XL710,
 	  X710, X722, XXV710, and all devices advertising support for
diff --git a/drivers/net/ethernet/intel/iavf/Makefile b/drivers/net/ethernet/intel/iavf/Makefile
index 356ac9faa5bf9..e13720a728ff3 100644
--- a/drivers/net/ethernet/intel/iavf/Makefile
+++ b/drivers/net/ethernet/intel/iavf/Makefile
@@ -13,3 +13,5 @@ obj-$(CONFIG_IAVF) += iavf.o
 
 iavf-y := iavf_main.o iavf_ethtool.o iavf_virtchnl.o iavf_fdir.o \
 	  iavf_adv_rss.o iavf_txrx.o iavf_common.o iavf_adminq.o
+
+iavf-$(CONFIG_PTP_1588_CLOCK) += iavf_ptp.o
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index edb9679cbad47..8d652ab72e195 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -4,6 +4,7 @@
 #include <linux/net/intel/libie/rx.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 /* All iavf tracepoints are defined by the include below, which must
  * be included exactly once across the whole kernel with
@@ -2878,6 +2879,9 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter)
 	if (QOS_ALLOWED(adapter))
 		adapter->aq_required |= IAVF_FLAG_AQ_GET_QOS_CAPS;
 
+	/* Setup initial PTP configuration */
+	iavf_ptp_init(adapter);
+
 	iavf_schedule_finish_config(adapter);
 	return;
 
@@ -5681,6 +5685,8 @@ static void iavf_remove(struct pci_dev *pdev)
 		msleep(50);
 	}
 
+	iavf_ptp_release(adapter);
+
 	iavf_misc_irq_disable(adapter);
 	/* Shut down all the garbage mashers on the detention level */
 	cancel_work_sync(&adapter->reset_task);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
new file mode 100644
index 0000000000000..5a1b5f8b87e5f
--- /dev/null
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -0,0 +1,122 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright(c) 2024 Intel Corporation. */
+
+#include "iavf.h"
+#include "iavf_ptp.h"
+
+/**
+ * iavf_ptp_cap_supported - Check if a PTP capability is supported
+ * @adapter: private adapter structure
+ * @cap: the capability bitmask to check
+ *
+ * Return: true if every capability set in cap is also set in the enabled
+ *         capabilities reported by the PF, false otherwise.
+ */
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap)
+{
+	if (!IAVF_PTP_ALLOWED(adapter))
+		return false;
+
+	/* Only return true if every bit in cap is set in hw_caps.caps */
+	return (adapter->ptp.hw_caps.caps & cap) == cap;
+}
+
+/**
+ * iavf_ptp_register_clock - Register a new PTP for userspace
+ * @adapter: private adapter structure
+ *
+ * Allocate and register a new PTP clock device if necessary.
+ *
+ * Return: 0 if success, error otherwise.
+ */
+static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
+{
+	struct ptp_clock_info *ptp_info = &adapter->ptp.info;
+	struct device *dev = &adapter->pdev->dev;
+	struct ptp_clock *clock;
+
+	snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, dev_name(dev));
+	ptp_info->owner = THIS_MODULE;
+
+	clock = ptp_clock_register(ptp_info, dev);
+	if (IS_ERR(clock))
+		return PTR_ERR(clock);
+
+	adapter->ptp.clock = clock;
+
+	dev_dbg(&adapter->pdev->dev, "PTP clock %s registered\n",
+		adapter->ptp.info.name);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_init - Initialize PTP support if capability was negotiated
+ * @adapter: private adapter structure
+ *
+ * Initialize PTP functionality, based on the capabilities that the PF has
+ * enabled for this VF.
+ */
+void iavf_ptp_init(struct iavf_adapter *adapter)
+{
+	int err;
+
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC)) {
+		pci_notice(adapter->pdev,
+			   "Device does not have PTP clock support\n");
+		return;
+	}
+
+	err = iavf_ptp_register_clock(adapter);
+	if (err) {
+		pci_err(adapter->pdev,
+			"Failed to register PTP clock device (%p)\n",
+			ERR_PTR(err));
+		return;
+	}
+
+	for (int i = 0; i < adapter->num_active_queues; i++) {
+		struct iavf_ring *rx_ring = &adapter->rx_rings[i];
+
+		rx_ring->ptp = &adapter->ptp;
+	}
+}
+
+/**
+ * iavf_ptp_release - Disable PTP support
+ * @adapter: private adapter structure
+ *
+ * Release all PTP resources that were previously initialized.
+ */
+void iavf_ptp_release(struct iavf_adapter *adapter)
+{
+	if (!adapter->ptp.clock)
+		return;
+
+	pci_dbg(adapter->pdev, "removing PTP clock %s\n",
+		adapter->ptp.info.name);
+	ptp_clock_unregister(adapter->ptp.clock);
+	adapter->ptp.clock = NULL;
+}
+
+/**
+ * iavf_ptp_process_caps - Handle change in PTP capabilities
+ * @adapter: private adapter structure
+ *
+ * Handle any state changes necessary due to change in PTP capabilities, such
+ * as after a device reset or change in configuration from the PF.
+ */
+void iavf_ptp_process_caps(struct iavf_adapter *adapter)
+{
+	bool phc = iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_READ_PHC);
+
+	/* Check if the device gained or lost necessary access to support the
+	 * PTP hardware clock. If so, driver must respond appropriately by
+	 * creating or destroying the PTP clock device.
+	 */
+	if (adapter->ptp.clock && !phc)
+		iavf_ptp_release(adapter);
+	else if (!adapter->ptp.clock && phc)
+		iavf_ptp_init(adapter);
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
index 65678e76c34f0..b63aea323f86a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -6,4 +6,18 @@
 
 #include "iavf_types.h"
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+void iavf_ptp_init(struct iavf_adapter *adapter);
+void iavf_ptp_release(struct iavf_adapter *adapter);
+void iavf_ptp_process_caps(struct iavf_adapter *adapter);
+bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
+#else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
+static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { }
+static inline bool iavf_ptp_cap_supported(struct iavf_adapter *adapter, u32 cap)
+{
+	return false;
+}
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 #endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 15a05e30434de..c38b4ec2eaea1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -297,6 +297,8 @@ struct iavf_ring {
 					 * for this ring.
 					 */
 
+	struct iavf_ptp *ptp;
+
 	u32 rx_buf_len;
 	struct net_shaper q_shaper;
 	bool q_shaper_update;
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index 65b0028bb968b..d009171e5f8a3 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -4,6 +4,7 @@
 #include <linux/net/intel/libie/rx.h>
 
 #include "iavf.h"
+#include "iavf_ptp.h"
 #include "iavf_prototype.h"
 
 /**
@@ -359,6 +360,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	int pairs = adapter->num_active_queues;
 	struct virtchnl_queue_pair_info *vqpi;
 	u32 i, max_frame;
+	u8 rx_flags = 0;
 	size_t len;
 
 	max_frame = LIBIE_MAX_RX_FRM_LEN(adapter->rx_rings->pp->p.offset);
@@ -376,6 +378,9 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 	if (!vqci)
 		return;
 
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))
+		rx_flags |= VIRTCHNL_PTP_RX_TSTAMP;
+
 	vqci->vsi_id = adapter->vsi_res->vsi_id;
 	vqci->num_queue_pairs = pairs;
 	vqpi = vqci->qpair;
@@ -398,6 +403,7 @@ void iavf_configure_queues(struct iavf_adapter *adapter)
 		if (CRC_OFFLOAD_ALLOWED(adapter))
 			vqpi->rxq.crc_disable = !!(adapter->netdev->features &
 						   NETIF_F_RXFCS);
+		vqpi->rxq.flags = rx_flags;
 		vqpi++;
 	}
 
@@ -2608,6 +2614,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 
 		adapter->ptp.hw_caps = *(struct virtchnl_ptp_caps *)msg;
 
+		/* process any state change needed due to new capabilities */
+		iavf_ptp_process_caps(adapter);
 		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */

From 52e3beac764def6ee1cb20ead8161d81b3113955 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:24 -0500
Subject: [PATCH 0545/2753] iavf: add support for indirect access to PHC time

Implement support for reading the PHC time indirectly via the
VIRTCHNL_OP_1588_PTP_GET_TIME operation.

Based on some simple tests with ftrace, the latency of the indirect
clock access appears to be about ~110 microseconds. This is due to the
cost of preparing a message to send over the virtchnl queue.

This is expected, due to the increased jitter caused by sending messages
over virtchnl. It is not easy to control the precise time that the
message is sent by the VF, or the time that the message is responded to
by the PF, or the time that the message sent from the PF is received by
the VF.

For sending the request, note that many PTP related operations will
require sending of VIRTCHNL messages. Instead of adding a separate AQ
flag and storage for each operation, setup a simple queue mechanism for
queuing up virtchnl messages.

Each message will be converted to a iavf_ptp_aq_cmd structure which ends
with a flexible array member. A single AQ flag is added for processing
messages from this queue. In principle this could be extended to handle
arbitrary virtchnl messages. For now it is kept to PTP-specific as the
need is primarily for handling PTP-related commands.

Use this to implement .gettimex64 using the indirect method via the
virtchnl command. The response from the PF is processed and stored into
the cached_phc_time. A wait queue is used to allow the PTP clock gettime
request to sleep until the message is sent from the PF.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c   |   9 +-
 drivers/net/ethernet/intel/iavf/iavf_ptp.c    | 149 ++++++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.h    |   6 +-
 .../net/ethernet/intel/iavf/iavf_virtchnl.c   |  95 +++++++++++
 4 files changed, 257 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 8d652ab72e195..d545b34496e73 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2276,7 +2276,10 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		iavf_enable_vlan_insertion_v2(adapter, ETH_P_8021AD);
 		return 0;
 	}
-
+	if (adapter->aq_required & IAVF_FLAG_AQ_SEND_PTP_CMD) {
+		iavf_virtchnl_send_ptp_cmd(adapter);
+		return IAVF_SUCCESS;
+	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_REQUEST_STATS) {
 		iavf_request_stats(adapter);
 		return 0;
@@ -5529,6 +5532,10 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Setup the wait queue for indicating virtchannel events */
 	init_waitqueue_head(&adapter->vc_waitqueue);
 
+	INIT_LIST_HEAD(&adapter->ptp.aq_cmds);
+	init_waitqueue_head(&adapter->ptp.phc_time_waitqueue);
+	mutex_init(&adapter->ptp.aq_cmd_lock);
+
 	queue_delayed_work(adapter->wq, &adapter->watchdog_task,
 			   msecs_to_jiffies(5 * (pdev->devfn & 0x07)));
 	/* Initialization goes on in the work. Do not add more of it below. */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
index 5a1b5f8b87e5f..b9a341e98a980 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -4,6 +4,9 @@
 #include "iavf.h"
 #include "iavf_ptp.h"
 
+#define iavf_clock_to_adapter(info)				\
+	container_of_const(info, struct iavf_adapter, ptp.info)
+
 /**
  * iavf_ptp_cap_supported - Check if a PTP capability is supported
  * @adapter: private adapter structure
@@ -21,6 +24,140 @@ bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap)
 	return (adapter->ptp.hw_caps.caps & cap) == cap;
 }
 
+/**
+ * iavf_allocate_ptp_cmd - Allocate a PTP command message structure
+ * @v_opcode: the virtchnl opcode
+ * @msglen: length in bytes of the associated virtchnl structure
+ *
+ * Allocates a PTP command message and pre-fills it with the provided message
+ * length and opcode.
+ *
+ * Return: allocated PTP command.
+ */
+static struct iavf_ptp_aq_cmd *iavf_allocate_ptp_cmd(enum virtchnl_ops v_opcode,
+						     u16 msglen)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	cmd = kzalloc(struct_size(cmd, msg, msglen), GFP_KERNEL);
+	if (!cmd)
+		return NULL;
+
+	cmd->v_opcode = v_opcode;
+	cmd->msglen = msglen;
+
+	return cmd;
+}
+
+/**
+ * iavf_queue_ptp_cmd - Queue PTP command for sending over virtchnl
+ * @adapter: private adapter structure
+ * @cmd: the command structure to send
+ *
+ * Queue the given command structure into the PTP virtchnl command queue tos
+ * end to the PF.
+ */
+static void iavf_queue_ptp_cmd(struct iavf_adapter *adapter,
+			       struct iavf_ptp_aq_cmd *cmd)
+{
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_add_tail(&cmd->list, &adapter->ptp.aq_cmds);
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->aq_required |= IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mod_delayed_work(adapter->wq, &adapter->watchdog_task, 0);
+}
+
+/**
+ * iavf_send_phc_read - Send request to read PHC time
+ * @adapter: private adapter structure
+ *
+ * Send a request to obtain the PTP hardware clock time. This allocates the
+ * VIRTCHNL_OP_1588_PTP_GET_TIME message and queues it up to send to
+ * indirectly read the PHC time.
+ *
+ * This function does not wait for the reply from the PF.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_send_phc_read(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	cmd = iavf_allocate_ptp_cmd(VIRTCHNL_OP_1588_PTP_GET_TIME,
+				    sizeof(struct virtchnl_phc_time));
+	if (!cmd)
+		return -ENOMEM;
+
+	iavf_queue_ptp_cmd(adapter, cmd);
+
+	return 0;
+}
+
+/**
+ * iavf_read_phc_indirect - Indirectly read the PHC time via virtchnl
+ * @adapter: private adapter structure
+ * @ts: storage for the timestamp value
+ * @sts: system timestamp values before and after the read
+ *
+ * Used when the device does not have direct register access to the PHC time.
+ * Indirectly reads the time via the VIRTCHNL_OP_1588_PTP_GET_TIME, and waits
+ * for the reply from the PF.
+ *
+ * Based on some simple measurements using ftrace and phc2sys, this clock
+ * access method has about a ~110 usec latency even when the system is not
+ * under load. In order to achieve acceptable results when using phc2sys with
+ * the indirect clock access method, it is recommended to use more
+ * conservative proportional and integration constants with the P/I servo.
+ *
+ * Return: 0 if success, error code otherwise.
+ */
+static int iavf_read_phc_indirect(struct iavf_adapter *adapter,
+				  struct timespec64 *ts,
+				  struct ptp_system_timestamp *sts)
+{
+	long ret;
+	int err;
+
+	adapter->ptp.phc_time_ready = false;
+
+	ptp_read_system_prets(sts);
+
+	err = iavf_send_phc_read(adapter);
+	if (err)
+		return err;
+
+	ret = wait_event_interruptible_timeout(adapter->ptp.phc_time_waitqueue,
+					       adapter->ptp.phc_time_ready,
+					       HZ);
+
+	ptp_read_system_postts(sts);
+
+	if (ret < 0)
+		return ret;
+	else if (!ret)
+		return -EBUSY;
+
+	*ts = ns_to_timespec64(adapter->ptp.cached_phc_time);
+
+	return 0;
+}
+
+static int iavf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	if (!adapter->ptp.clock)
+		return -EOPNOTSUPP;
+
+	return iavf_read_phc_indirect(adapter, ts, sts);
+}
+
 /**
  * iavf_ptp_register_clock - Register a new PTP for userspace
  * @adapter: private adapter structure
@@ -38,6 +175,7 @@ static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
 	snprintf(ptp_info->name, sizeof(ptp_info->name), "%s-%s-clk",
 		 KBUILD_MODNAME, dev_name(dev));
 	ptp_info->owner = THIS_MODULE;
+	ptp_info->gettimex64 = iavf_ptp_gettimex64;
 
 	clock = ptp_clock_register(ptp_info, dev);
 	if (IS_ERR(clock))
@@ -91,6 +229,8 @@ void iavf_ptp_init(struct iavf_adapter *adapter)
  */
 void iavf_ptp_release(struct iavf_adapter *adapter)
 {
+	struct iavf_ptp_aq_cmd *cmd, *tmp;
+
 	if (!adapter->ptp.clock)
 		return;
 
@@ -98,6 +238,15 @@ void iavf_ptp_release(struct iavf_adapter *adapter)
 		adapter->ptp.info.name);
 	ptp_clock_unregister(adapter->ptp.clock);
 	adapter->ptp.clock = NULL;
+
+	/* Cancel any remaining uncompleted PTP clock commands */
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &adapter->ptp.aq_cmds, list) {
+		list_del(&cmd->list);
+		kfree(cmd);
+	}
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
index b63aea323f86a..8e2f1ed18b868 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -11,13 +11,17 @@ void iavf_ptp_init(struct iavf_adapter *adapter);
 void iavf_ptp_release(struct iavf_adapter *adapter);
 void iavf_ptp_process_caps(struct iavf_adapter *adapter);
 bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
 static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
 static inline void iavf_ptp_process_caps(struct iavf_adapter *adapter) { }
-static inline bool iavf_ptp_cap_supported(struct iavf_adapter *adapter, u32 cap)
+static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter,
+					  u32 cap)
 {
 	return false;
 }
+
+static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { }
 #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 #endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index d009171e5f8a3..a6f0e5990be25 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1494,6 +1494,67 @@ void iavf_disable_vlan_insertion_v2(struct iavf_adapter *adapter, u16 tpid)
 				  VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2);
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * iavf_virtchnl_send_ptp_cmd - Send one queued PTP command
+ * @adapter: adapter private structure
+ *
+ * De-queue one PTP command request and send the command message to the PF.
+ * Clear IAVF_FLAG_AQ_SEND_PTP_CMD if no more messages are left to send.
+ */
+void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter)
+{
+	struct iavf_ptp_aq_cmd *cmd;
+	int err;
+
+	if (!adapter->ptp.clock) {
+		/* This shouldn't be possible to hit, since no messages should
+		 * be queued if PTP is not initialized.
+		 */
+		pci_err(adapter->pdev, "PTP is not initialized\n");
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		return;
+	}
+
+	mutex_lock(&adapter->ptp.aq_cmd_lock);
+	cmd = list_first_entry_or_null(&adapter->ptp.aq_cmds,
+				       struct iavf_ptp_aq_cmd, list);
+	if (!cmd) {
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+		goto out_unlock;
+	}
+
+	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
+		/* bail because we already have a command pending */
+		pci_err(adapter->pdev,
+			"Cannot send PTP command %d, command %d pending\n",
+			cmd->v_opcode, adapter->current_op);
+		goto out_unlock;
+	}
+
+	err = iavf_send_pf_msg(adapter, cmd->v_opcode, cmd->msg, cmd->msglen);
+	if (!err) {
+		/* Command was sent without errors, so we can remove it from
+		 * the list and discard it.
+		 */
+		list_del(&cmd->list);
+		kfree(cmd);
+	} else {
+		/* We failed to send the command, try again next cycle */
+		pci_err(adapter->pdev, "Failed to send PTP command %d\n",
+			cmd->v_opcode);
+	}
+
+	if (list_empty(&adapter->ptp.aq_cmds))
+		/* no further PTP messages to send */
+		adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
+
+out_unlock:
+	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+}
+#endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
+
 /**
  * iavf_print_link_message - print link up or down
  * @adapter: adapter structure
@@ -2189,6 +2250,37 @@ static void iavf_activate_fdir_filters(struct iavf_adapter *adapter)
 		adapter->aq_required |= IAVF_FLAG_AQ_ADD_FDIR_FILTER;
 }
 
+/**
+ * iavf_virtchnl_ptp_get_time - Respond to VIRTCHNL_OP_1588_PTP_GET_TIME
+ * @adapter: private adapter structure
+ * @data: the message from the PF
+ * @len: length of the message from the PF
+ *
+ * Handle the VIRTCHNL_OP_1588_PTP_GET_TIME message from the PF. This message
+ * is sent by the PF in response to the same op as a request from the VF.
+ * Extract the 64bit nanoseconds time from the message and store it in
+ * cached_phc_time. Then, notify any thread that is waiting for the update via
+ * the wait queue.
+ */
+static void iavf_virtchnl_ptp_get_time(struct iavf_adapter *adapter,
+				       void *data, u16 len)
+{
+	struct virtchnl_phc_time *msg = data;
+
+	if (len != sizeof(*msg)) {
+		dev_err_once(&adapter->pdev->dev,
+			     "Invalid VIRTCHNL_OP_1588_PTP_GET_TIME from PF. Got size %u, expected %zu\n",
+			     len, sizeof(*msg));
+		return;
+	}
+
+	adapter->ptp.cached_phc_time = msg->time;
+	adapter->ptp.cached_phc_updated = jiffies;
+	adapter->ptp.phc_time_ready = true;
+
+	wake_up(&adapter->ptp.phc_time_waitqueue);
+}
+
 /**
  * iavf_virtchnl_completion
  * @adapter: adapter structure
@@ -2617,6 +2709,9 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		/* process any state change needed due to new capabilities */
 		iavf_ptp_process_caps(adapter);
 		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		iavf_virtchnl_ptp_get_time(adapter, msg, msglen);
+		break;
 	case VIRTCHNL_OP_ENABLE_QUEUES:
 		/* enable transmits */
 		iavf_irq_enable(adapter, true);

From 7c01dbfc8a1c5f8b8e4a7907ab06db1449d478d0 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:25 -0500
Subject: [PATCH 0546/2753] iavf: periodically cache PHC time

The Rx timestamps reported by hardware may only have 32 bits of storage
for nanosecond time. These timestamps cannot be directly reported to the
Linux stack, as it expects 64bits of time.

To handle this, the timestamps must be extended using an algorithm that
calculates the corrected 64bit timestamp by comparison between the PHC
time and the timestamp. This algorithm requires the PHC time to be
captured within ~2 seconds of when the timestamp was captured.

Instead of trying to read the PHC time in the Rx hotpath, the algorithm
relies on a cached value that is periodically updated.

Keep this cached time up to date by using the PTP .do_aux_work kthread
function.

The iavf_ptp_do_aux_work will reschedule itself about twice a second,
and will check whether or not the cached PTP time needs to be updated.
If so, it issues a VIRTCHNL_OP_1588_PTP_GET_TIME to request the time
from the PF. The jitter and latency involved with this command aren't
important, because the cached time just needs to be kept up to date
within about ~2 seconds.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_ptp.c | 53 ++++++++++++++++++++++
 1 file changed, 53 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
index b9a341e98a980..c2e0d27552b00 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -158,6 +158,56 @@ static int iavf_ptp_gettimex64(struct ptp_clock_info *info,
 	return iavf_read_phc_indirect(adapter, ts, sts);
 }
 
+/**
+ * iavf_ptp_cache_phc_time - Cache PHC time for performing timestamp extension
+ * @adapter: private adapter structure
+ *
+ * Periodically cache the PHC time in order to allow for timestamp extension.
+ * This is required because the Tx and Rx timestamps only contain 32bits of
+ * nanoseconds. Timestamp extension allows calculating the corrected 64bit
+ * timestamp. This algorithm relies on the cached time being within ~1 second
+ * of the timestamp.
+ */
+static void iavf_ptp_cache_phc_time(struct iavf_adapter *adapter)
+{
+	if (!time_is_before_jiffies(adapter->ptp.cached_phc_updated + HZ))
+		return;
+
+	/* The response from virtchnl will store the time into
+	 * cached_phc_time.
+	 */
+	iavf_send_phc_read(adapter);
+}
+
+/**
+ * iavf_ptp_do_aux_work - Perform periodic work required for PTP support
+ * @info: PTP clock info structure
+ *
+ * Handler to take care of periodic work required for PTP operation. This
+ * includes the following tasks:
+ *
+ *   1) updating cached_phc_time
+ *
+ *      cached_phc_time is used by the Tx and Rx timestamp flows in order to
+ *      perform timestamp extension, by carefully comparing the timestamp
+ *      32bit nanosecond timestamps and determining the corrected 64bit
+ *      timestamp value to report to userspace. This algorithm only works if
+ *      the cached_phc_time is within ~1 second of the Tx or Rx timestamp
+ *      event. This task periodically reads the PHC time and stores it, to
+ *      ensure that timestamp extension operates correctly.
+ *
+ * Returns: time in jiffies until the periodic task should be re-scheduled.
+ */
+static long iavf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct iavf_adapter *adapter = iavf_clock_to_adapter(info);
+
+	iavf_ptp_cache_phc_time(adapter);
+
+	/* Check work about twice a second */
+	return msecs_to_jiffies(500);
+}
+
 /**
  * iavf_ptp_register_clock - Register a new PTP for userspace
  * @adapter: private adapter structure
@@ -176,6 +226,7 @@ static int iavf_ptp_register_clock(struct iavf_adapter *adapter)
 		 KBUILD_MODNAME, dev_name(dev));
 	ptp_info->owner = THIS_MODULE;
 	ptp_info->gettimex64 = iavf_ptp_gettimex64;
+	ptp_info->do_aux_work = iavf_ptp_do_aux_work;
 
 	clock = ptp_clock_register(ptp_info, dev);
 	if (IS_ERR(clock))
@@ -219,6 +270,8 @@ void iavf_ptp_init(struct iavf_adapter *adapter)
 
 		rx_ring->ptp = &adapter->ptp;
 	}
+
+	ptp_schedule_worker(adapter->ptp.clock, 0);
 }
 
 /**

From ce5cf4af7ceb6c1350c7ae788659c1f0696b2267 Mon Sep 17 00:00:00 2001
From: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Date: Wed, 6 Nov 2024 12:37:26 -0500
Subject: [PATCH 0547/2753] libeth: move idpf_rx_csum_decoded and
 idpf_rx_extracted

Structs idpf_rx_csum_decoded and idpf_rx_extracted are used both in
idpf and iavf Intel drivers. Change the prefix from idpf_* to libeth_*
and move mentioned structs to libeth's rx.h header file.

Adjust usage in idpf driver.

Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 .../ethernet/intel/idpf/idpf_singleq_txrx.c   | 51 ++++++++++---------
 drivers/net/ethernet/intel/idpf/idpf_txrx.c   | 16 +++---
 drivers/net/ethernet/intel/idpf/idpf_txrx.h   | 19 -------
 include/net/libeth/rx.h                       | 47 +++++++++++++++++
 4 files changed, 82 insertions(+), 51 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
index dfd7cf1d9aa0a..eae1b6f474e62 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
@@ -595,7 +595,7 @@ static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc)
  */
 static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq,
 				 struct sk_buff *skb,
-				 struct idpf_rx_csum_decoded csum_bits,
+				 struct libeth_rx_csum csum_bits,
 				 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
@@ -661,10 +661,10 @@ static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq,
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u32 rx_error, rx_status;
 	u64 qword;
 
@@ -696,10 +696,10 @@ idpf_rx_singleq_base_csum(const union virtchnl2_rx_desc *rx_desc)
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_singleq_flex_csum(const union virtchnl2_rx_desc *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits = { };
+	struct libeth_rx_csum csum_bits = { };
 	u16 rx_status0, rx_status1;
 
 	rx_status0 = le16_to_cpu(rx_desc->flex_nic_wb.status_error0);
@@ -798,7 +798,7 @@ idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
 				   u16 ptype)
 {
 	struct libeth_rx_pt decoded = rx_q->rx_ptype_lkup[ptype];
-	struct idpf_rx_csum_decoded csum_bits;
+	struct libeth_rx_csum csum_bits;
 
 	/* modifies the skb - consumes the enet header */
 	skb->protocol = eth_type_trans(skb, rx_q->netdev);
@@ -891,6 +891,7 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
+ * @ptype: pointer that will store packet type
  *
  * Decode the Rx descriptor and extract relevant information including the
  * size and Rx packet type.
@@ -900,20 +901,21 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
  */
 static void
 idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields, u32 *ptype)
 {
 	u64 qword;
 
 	qword = le64_to_cpu(rx_desc->base_wb.qword1.status_error_ptype_len);
 
-	fields->size = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
+	fields->len = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_LEN_PBUF_M, qword);
+	*ptype = FIELD_GET(VIRTCHNL2_RX_BASE_DESC_QW1_PTYPE_M, qword);
 }
 
 /**
  * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
+ * @ptype: pointer that will store packet type
  *
  * Decode the Rx descriptor and extract relevant information including the
  * size and Rx packet type.
@@ -923,12 +925,12 @@ idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
  */
 static void
 idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
-				    struct idpf_rx_extracted *fields)
+				    struct libeth_rqe_info *fields, u32 *ptype)
 {
-	fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
-				 le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
-	fields->rx_ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
-				     le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
+	fields->len = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
+				le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
+	*ptype = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PTYPE_M,
+			   le16_to_cpu(rx_desc->flex_nic_wb.ptype_flex_flags0));
 }
 
 /**
@@ -936,17 +938,18 @@ idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
  * @rx_q: Rx descriptor queue
  * @rx_desc: the descriptor to process
  * @fields: storage for extracted values
+ * @ptype: pointer that will store packet type
  *
  */
 static void
 idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
 			       const union virtchnl2_rx_desc *rx_desc,
-			       struct idpf_rx_extracted *fields)
+			       struct libeth_rqe_info *fields, u32 *ptype)
 {
 	if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M)
-		idpf_rx_singleq_extract_base_fields(rx_desc, fields);
+		idpf_rx_singleq_extract_base_fields(rx_desc, fields, ptype);
 	else
-		idpf_rx_singleq_extract_flex_fields(rx_desc, fields);
+		idpf_rx_singleq_extract_flex_fields(rx_desc, fields, ptype);
 }
 
 /**
@@ -966,9 +969,10 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 
 	/* Process Rx packets bounded by budget */
 	while (likely(total_rx_pkts < (unsigned int)budget)) {
-		struct idpf_rx_extracted fields = { };
+		struct libeth_rqe_info fields = { };
 		union virtchnl2_rx_desc *rx_desc;
 		struct idpf_rx_buf *rx_buf;
+		u32 ptype;
 
 		/* get the Rx desc from Rx queue based on 'next_to_clean' */
 		rx_desc = &rx_q->rx[ntc];
@@ -989,16 +993,16 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		 */
 		dma_rmb();
 
-		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields);
+		idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields, &ptype);
 
 		rx_buf = &rx_q->rx_buf[ntc];
-		if (!libeth_rx_sync_for_cpu(rx_buf, fields.size))
+		if (!libeth_rx_sync_for_cpu(rx_buf, fields.len))
 			goto skip_data;
 
 		if (skb)
-			idpf_rx_add_frag(rx_buf, skb, fields.size);
+			idpf_rx_add_frag(rx_buf, skb, fields.len);
 		else
-			skb = idpf_rx_build_skb(rx_buf, fields.size);
+			skb = idpf_rx_build_skb(rx_buf, fields.len);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb)
@@ -1033,8 +1037,7 @@ static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
 		total_rx_bytes += skb->len;
 
 		/* protocol */
-		idpf_rx_singleq_process_skb_fields(rx_q, skb,
-						   rx_desc, fields.rx_ptype);
+		idpf_rx_singleq_process_skb_fields(rx_q, skb, rx_desc, ptype);
 
 		/* send completed skb up the stack */
 		napi_gro_receive(rx_q->pp->p.napi, skb);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 9be6a6b59c4e1..2747dc69999aa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -2895,7 +2895,7 @@ idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb,
  * skb->protocol must be set before this function is called
  */
 static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
-			 struct idpf_rx_csum_decoded csum_bits,
+			 struct libeth_rx_csum csum_bits,
 			 struct libeth_rx_pt decoded)
 {
 	bool ipv4, ipv6;
@@ -2923,7 +2923,7 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
-	if (csum_bits.raw_csum_inv ||
+	if (!csum_bits.raw_csum_valid ||
 	    decoded.inner_prot == LIBETH_RX_PT_INNER_SCTP) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		return;
@@ -2946,10 +2946,10 @@ static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
  *
  * Return: parsed checksum status.
  **/
-static struct idpf_rx_csum_decoded
+static struct libeth_rx_csum
 idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum = { };
+	struct libeth_rx_csum csum = { };
 	u8 qword0, qword1;
 
 	qword0 = rx_desc->status_err0_qw0;
@@ -2965,9 +2965,9 @@ idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *
 			       qword1);
 	csum.ipv6exadd = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_IPV6EXADD_M,
 				   qword0);
-	csum.raw_csum_inv =
-		le16_get_bits(rx_desc->ptype_err_fflags0,
-			      VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
+	csum.raw_csum_valid =
+		!le16_get_bits(rx_desc->ptype_err_fflags0,
+			       VIRTCHNL2_RX_FLEX_DESC_ADV_RAW_CSUM_INV_M);
 	csum.raw_csum = le16_to_cpu(rx_desc->misc.raw_cs);
 
 	return csum;
@@ -3058,7 +3058,7 @@ static int
 idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 			   const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
 {
-	struct idpf_rx_csum_decoded csum_bits;
+	struct libeth_rx_csum csum_bits;
 	struct libeth_rx_pt decoded;
 	u16 rx_ptype;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 0f71a6f5557b9..cd9a20c9cc7fb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -213,25 +213,6 @@ enum idpf_tx_ctx_desc_eipt_offload {
 	IDPF_TX_CTX_EXT_IP_IPV4         = 0x3
 };
 
-/* Checksum offload bits decoded from the receive descriptor. */
-struct idpf_rx_csum_decoded {
-	u32 l3l4p : 1;
-	u32 ipe : 1;
-	u32 eipe : 1;
-	u32 eudpe : 1;
-	u32 ipv6exadd : 1;
-	u32 l4e : 1;
-	u32 pprs : 1;
-	u32 nat : 1;
-	u32 raw_csum_inv : 1;
-	u32 raw_csum : 16;
-};
-
-struct idpf_rx_extracted {
-	unsigned int size;
-	u16 rx_ptype;
-};
-
 #define IDPF_TX_COMPLQ_CLEAN_BUDGET	256
 #define IDPF_TX_MIN_PKT_LEN		17
 #define IDPF_TX_DESCS_FOR_SKB_DATA_PTR	1
diff --git a/include/net/libeth/rx.h b/include/net/libeth/rx.h
index 43574bd6612f0..ab05024be5186 100644
--- a/include/net/libeth/rx.h
+++ b/include/net/libeth/rx.h
@@ -198,6 +198,53 @@ struct libeth_rx_pt {
 	enum xdp_rss_hash_type			hash_type:16;
 };
 
+/**
+ * struct libeth_rx_csum - checksum offload bits decoded from the Rx descriptor
+ * @l3l4p: detectable L3 and L4 integrity check is processed by the hardware
+ * @ipe: IP checksum error
+ * @eipe: external (outermost) IP header (only for tunels)
+ * @eudpe: external (outermost) UDP checksum error (only for tunels)
+ * @ipv6exadd: IPv6 header with extension headers
+ * @l4e: L4 integrity error
+ * @pprs: set for packets that skip checksum calculation in the HW pre parser
+ * @nat: the packet is a UDP tunneled packet
+ * @raw_csum_valid: set if raw checksum is valid
+ * @pad: padding to naturally align raw_csum field
+ * @raw_csum: raw checksum
+ */
+struct libeth_rx_csum {
+	u32					l3l4p:1;
+	u32					ipe:1;
+	u32					eipe:1;
+	u32					eudpe:1;
+	u32					ipv6exadd:1;
+	u32					l4e:1;
+	u32					pprs:1;
+	u32					nat:1;
+
+	u32					raw_csum_valid:1;
+	u32					pad:7;
+	u32					raw_csum:16;
+};
+
+/**
+ * struct libeth_rqe_info - receive queue element info
+ * @len: packet length
+ * @ptype: packet type based on types programmed into the device
+ * @eop: whether it's the last fragment of the packet
+ * @rxe: MAC errors: CRC, Alignment, Oversize, Undersizes, Length error
+ * @vlan: C-VLAN or S-VLAN tag depending on the VLAN offload configuration
+ */
+struct libeth_rqe_info {
+	u32					len;
+
+	u32					ptype:14;
+	u32					eop:1;
+	u32					rxe:1;
+
+	u32					vlan:16;
+};
+
 void libeth_rx_pt_gen_hash_type(struct libeth_rx_pt *pt);
 
 /**

From e9f476d7b39ce1aecc4913eda1562e87113df185 Mon Sep 17 00:00:00 2001
From: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Date: Wed, 6 Nov 2024 12:37:27 -0500
Subject: [PATCH 0548/2753] iavf: define Rx descriptors as qwords

The union iavf_32byte_rx_desc consists of two unnamed structs defined
inside. One of them represents legacy 32 byte descriptor and second the
16 byte descriptor (extended to 32 byte). Each of them consists of
bunch of unions, structs and __le fields that represent specific fields
in descriptor.

This commit changes the representation of iavf_32byte_rx_desc union
to store four __le64 fields (qw0, qw1, qw2, qw3) that represent
quad-words. Those quad-words will be then accessed by calling
leXY_get_bits macros in upcoming commits.

Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf.h       |   2 +-
 drivers/net/ethernet/intel/iavf/iavf_trace.h |   6 +-
 drivers/net/ethernet/intel/iavf/iavf_txrx.c  |  56 ++++-----
 drivers/net/ethernet/intel/iavf/iavf_txrx.h  |   7 +-
 drivers/net/ethernet/intel/iavf/iavf_type.h  | 117 +++++++------------
 5 files changed, 77 insertions(+), 111 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index b6e52992e2702..9de3e0ba37316 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -83,7 +83,7 @@ struct iavf_vsi {
 
 #define MAXIMUM_ETHERNET_VLAN_SIZE (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)
 
-#define IAVF_RX_DESC(R, i) (&(((union iavf_32byte_rx_desc *)((R)->desc))[i]))
+#define IAVF_RX_DESC(R, i) (&(((struct iavf_rx_desc *)((R)->desc))[i]))
 #define IAVF_TX_DESC(R, i) (&(((struct iavf_tx_desc *)((R)->desc))[i]))
 #define IAVF_TX_CTXTDESC(R, i) \
 	(&(((struct iavf_tx_context_desc *)((R)->desc))[i]))
diff --git a/drivers/net/ethernet/intel/iavf/iavf_trace.h b/drivers/net/ethernet/intel/iavf/iavf_trace.h
index 62212011c8070..c5e4d18238866 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_trace.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_trace.h
@@ -112,7 +112,7 @@ DECLARE_EVENT_CLASS(
 	iavf_rx_template,
 
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb),
@@ -140,7 +140,7 @@ DECLARE_EVENT_CLASS(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
@@ -148,7 +148,7 @@ DEFINE_EVENT(
 DEFINE_EVENT(
 	iavf_rx_template, iavf_clean_rx_irq_rx,
 	TP_PROTO(struct iavf_ring *ring,
-		 union iavf_32byte_rx_desc *desc,
+		 struct iavf_rx_desc *desc,
 		 struct sk_buff *skb),
 
 	TP_ARGS(ring, desc, skb));
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 26b424fd67183..46745ebc9c1fd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -766,7 +766,7 @@ int iavf_setup_rx_descriptors(struct iavf_ring *rx_ring)
 	u64_stats_init(&rx_ring->syncp);
 
 	/* Round up to nearest 4K */
-	rx_ring->size = rx_ring->count * sizeof(union iavf_32byte_rx_desc);
+	rx_ring->size = rx_ring->count * sizeof(struct iavf_rx_desc);
 	rx_ring->size = ALIGN(rx_ring->size, 4096);
 	rx_ring->desc = dma_alloc_coherent(fq.pp->p.dev, rx_ring->size,
 					   &rx_ring->dma, GFP_KERNEL);
@@ -845,7 +845,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		.count		= rx_ring->count,
 	};
 	u16 ntu = rx_ring->next_to_use;
-	union iavf_rx_desc *rx_desc;
+	struct iavf_rx_desc *rx_desc;
 
 	/* do nothing if no valid netdev defined */
 	if (!rx_ring->netdev || !cleaned_count)
@@ -863,7 +863,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		/* Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(addr);
+		rx_desc->qw0 = cpu_to_le64(addr);
 
 		rx_desc++;
 		ntu++;
@@ -873,7 +873,7 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 		}
 
 		/* clear the status bits for the next_to_use descriptor */
-		rx_desc->wb.qword1.status_error_len = 0;
+		rx_desc->qw1 = 0;
 
 		cleaned_count--;
 	} while (cleaned_count);
@@ -901,19 +901,18 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
  * @skb: skb currently being received and modified
  * @rx_desc: the receive descriptor
  **/
-static void iavf_rx_checksum(struct iavf_vsi *vsi,
-			     struct sk_buff *skb,
-			     union iavf_rx_desc *rx_desc)
+static void iavf_rx_checksum(struct iavf_vsi *vsi, struct sk_buff *skb,
+			     struct iavf_rx_desc *rx_desc)
 {
 	struct libeth_rx_pt decoded;
 	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
-	u8 ptype;
 	u64 qword;
+	u32 ptype;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+	qword = le64_to_cpu(rx_desc->qw1);
 	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
 
 	decoded = libie_rx_pt_parse(ptype);
@@ -967,7 +966,7 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi,
  * @rx_ptype: Rx packet type
  **/
 static void iavf_rx_hash(struct iavf_ring *ring,
-			 union iavf_rx_desc *rx_desc,
+			 struct iavf_rx_desc *rx_desc,
 			 struct sk_buff *skb,
 			 u8 rx_ptype)
 {
@@ -981,8 +980,8 @@ static void iavf_rx_hash(struct iavf_ring *ring,
 	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
 		return;
 
-	if ((rx_desc->wb.qword1.status_error_len & rss_mask) == rss_mask) {
-		hash = le32_to_cpu(rx_desc->wb.qword0.hi_dword.rss);
+	if ((rx_desc->qw1 & rss_mask) == rss_mask) {
+		hash = le64_get_bits(rx_desc->qw0, IAVF_RXD_LEGACY_RSS_M);
 		libeth_rx_pt_set_hash(skb, hash, decoded);
 	}
 }
@@ -1000,7 +999,7 @@ static void iavf_rx_hash(struct iavf_ring *ring,
  **/
 static void
 iavf_process_skb_fields(struct iavf_ring *rx_ring,
-			union iavf_rx_desc *rx_desc, struct sk_buff *skb,
+			struct iavf_rx_desc *rx_desc, struct sk_buff *skb,
 			u8 rx_ptype)
 {
 	iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
@@ -1101,7 +1100,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
  * that this is in fact a non-EOP buffer.
  **/
 static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
-			    union iavf_rx_desc *rx_desc,
+			    struct iavf_rx_desc *rx_desc,
 			    struct sk_buff *skb)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
@@ -1143,11 +1142,12 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
 		struct libeth_fqe *rx_buffer;
-		union iavf_rx_desc *rx_desc;
+		struct iavf_rx_desc *rx_desc;
+		u16 ext_status = 0;
 		unsigned int size;
 		u16 vlan_tag = 0;
 		u8 rx_ptype;
-		u64 qword;
+		u64 qw1;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1163,7 +1163,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		 * which is always zero because packet split isn't used, if the
 		 * hardware wrote DD then the length will be non-zero
 		 */
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
+		qw1 = le64_to_cpu(rx_desc->qw1);
 
 		/* This memory barrier is needed to keep us from reading
 		 * any other fields out of the rx_desc until we have
@@ -1174,7 +1174,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
 			break;
 
-		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qword);
+		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qw1);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 
@@ -1219,19 +1219,23 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
-		qword = le64_to_cpu(rx_desc->wb.qword1.status_error_len);
-		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
+		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qw1);
 
 		/* populate checksum, VLAN, and protocol */
 		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
 
-		if (qword & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
+		if (qw1 & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
 		    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword0.lo_dword.l2tag1);
-		if (rx_desc->wb.qword2.ext_status &
-		    cpu_to_le16(BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)) &&
-		    rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2)
-			vlan_tag = le16_to_cpu(rx_desc->wb.qword2.l2tag2_2);
+			vlan_tag = le64_get_bits(rx_desc->qw0,
+						 IAVF_RXD_LEGACY_L2TAG1_M);
+
+		ext_status = le64_get_bits(rx_desc->qw2,
+					   IAVF_RXD_LEGACY_EXT_STATUS_M);
+
+		if ((ext_status & IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M) &&
+		    (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2))
+			vlan_tag = le64_get_bits(rx_desc->qw2,
+						 IAVF_RXD_LEGACY_L2TAG2_2_M);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		iavf_receive_skb(rx_ring, skb, vlan_tag);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index c38b4ec2eaea1..3a1a39ee3615b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -80,8 +80,6 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-#define iavf_rx_desc iavf_32byte_rx_desc
-
 /**
  * iavf_test_staterr - tests bits in Rx descriptor status and error fields
  * @rx_desc: pointer to receive descriptor (in le64 format)
@@ -92,11 +90,10 @@ enum iavf_dyn_idx_t {
  * The status_error_len doesn't need to be shifted because it begins
  * at offset zero.
  */
-static inline bool iavf_test_staterr(union iavf_rx_desc *rx_desc,
+static inline bool iavf_test_staterr(struct iavf_rx_desc *rx_desc,
 				     const u64 stat_err_bits)
 {
-	return !!(rx_desc->wb.qword1.status_error_len &
-		  cpu_to_le64(stat_err_bits));
+	return !!(rx_desc->qw1 & cpu_to_le64(stat_err_bits));
 }
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index f6b09e57abcef..e000971e3c013 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -178,82 +178,45 @@ struct iavf_hw {
 	char err_str[16];
 };
 
-/* RX Descriptors */
-union iavf_16byte_rx_desc {
-	struct {
-		__le64 pkt_addr; /* Packet buffer address */
-		__le64 hdr_addr; /* Header buffer address */
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fd_id; /* Flow director filter id */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-			} hi_dword;
-		} qword0;
-		struct {
-			/* ext status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-	} wb;  /* writeback */
-};
-
-union iavf_32byte_rx_desc {
-	struct {
-		__le64  pkt_addr; /* Packet buffer address */
-		__le64  hdr_addr; /* Header buffer address */
-			/* bit 0 of hdr_buffer_addr is DD bit */
-		__le64  rsvd1;
-		__le64  rsvd2;
-	} read;
-	struct {
-		struct {
-			struct {
-				union {
-					__le16 mirroring_status;
-					__le16 fcoe_ctx_id;
-				} mirr_fcoe;
-				__le16 l2tag1;
-			} lo_dword;
-			union {
-				__le32 rss; /* RSS Hash */
-				__le32 fcoe_param; /* FCoE DDP Context id */
-				/* Flow director filter id in case of
-				 * Programming status desc WB
-				 */
-				__le32 fd_id;
-			} hi_dword;
-		} qword0;
-		struct {
-			/* status/error/pktype/length */
-			__le64 status_error_len;
-		} qword1;
-		struct {
-			__le16 ext_status; /* extended status */
-			__le16 rsvd;
-			__le16 l2tag2_1;
-			__le16 l2tag2_2;
-		} qword2;
-		struct {
-			union {
-				__le32 flex_bytes_lo;
-				__le32 pe_status;
-			} lo_dword;
-			union {
-				__le32 flex_bytes_hi;
-				__le32 fd_id;
-			} hi_dword;
-		} qword3;
-	} wb;  /* writeback */
-};
+/**
+ * struct iavf_rx_desc - Receive descriptor (both legacy and flexible)
+ * @qw0: quad word 0 fields:
+ *	 Legacy: Descriptor Type; Mirror ID; L2TAG1P (S-TAG); Filter Status
+ *	 Flex: Descriptor Type; Mirror ID; UMBCAST; Packet Type; Flexible Flags
+ *	       Section 0; Packet Length; Header Length; Split Header Flag;
+ *	       Flexible Flags section 1 / Extended Status
+ * @qw1: quad word 1 fields:
+ *	 Legacy: Status Field; Error Field; Packet Type; Packet Length (packet,
+ *		 header, Split Header Flag)
+ *	 Flex: Status / Error 0 Field; L2TAG1P (S-TAG); Flexible Metadata
+ *	       Container #0; Flexible Metadata Container #1
+ * @qw2: quad word 2 fields:
+ *	 Legacy: Extended Status; 1st L2TAG2P (C-TAG); 2nd L2TAG2P (C-TAG)
+ *	 Flex: Status / Error 1 Field; Flexible Flags section 2; Timestamp Low;
+ *	       1st L2TAG2 (C-TAG); 2nd L2TAG2 (C-TAG)
+ * @qw3: quad word 3 fields:
+ *	 Legacy: FD Filter ID / Flexible Bytes
+ *	 Flex: Flexible Metadata Container #2; Flexible Metadata Container #3;
+ *	       Flexible Metadata Container #4 / Timestamp High 0; Flexible
+ *	       Metadata Container #5 / Timestamp High 1;
+ */
+struct iavf_rx_desc {
+	aligned_le64 qw0;
+/* The hash signature (RSS) */
+#define IAVF_RXD_LEGACY_RSS_M			GENMASK_ULL(63, 32)
+/* Stripped C-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG1_M		GENMASK_ULL(33, 16)
+
+	aligned_le64 qw1;
+	aligned_le64 qw2;
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_LEGACY_L2TAG2_2_M		GENMASK_ULL(63, 48)
+/* Extended status bits */
+#define IAVF_RXD_LEGACY_EXT_STATUS_M		GENMASK_ULL(11, 0)
+
+	aligned_le64 qw3;
+} __aligned(4 * sizeof(__le64));
+static_assert(sizeof(struct iavf_rx_desc) == 32);
 
 enum iavf_rx_desc_status_bits {
 	/* Note: These are predefined bit offsets */
@@ -347,6 +310,8 @@ enum iavf_rx_desc_ext_status_bits {
 	IAVF_RX_DESC_EXT_STATUS_PELONGB_SHIFT	= 11,
 };
 
+#define IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M	BIT(IAVF_RX_DESC_EXT_STATUS_L2TAG2P_SHIFT)
+
 enum iavf_rx_desc_pe_status_bits {
 	/* Note: These are predefined bit offsets */
 	IAVF_RX_DESC_PE_STATUS_QPID_SHIFT	= 0, /* 18 BITS */

From 2dc8e7c36d805084756e170527423e64eb04aba8 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:28 -0500
Subject: [PATCH 0549/2753] iavf: refactor iavf_clean_rx_irq to support legacy
 and flex descriptors

Using VIRTCHNL_VF_OFFLOAD_FLEX_DESC, the iAVF driver is capable of
negotiating to enable the advanced flexible descriptor layout. Add the
flexible NIC layout (RXDID=2) as a member of the Rx descriptor union.

Also add bit position definitions for the status and error indications
that are needed.

The iavf_clean_rx_irq function needs to extract a few fields from the Rx
descriptor, including the size, rx_ptype, and vlan_tag.
Move the extraction to a separate function that decodes the fields into
a structure. This will reduce the burden for handling multiple
descriptor types by keeping the relevant extraction logic in one place.

To support handling an additional descriptor format with minimal code
duplication, refactor Rx checksum handling so that the general logic
is separated from the bit calculations. Introduce an iavf_rx_desc_decoded
structure which holds the relevant bits decoded from the Rx descriptor.
This will enable implementing flexible descriptor handling without
duplicating the general logic twice.

Introduce an iavf_extract_flex_rx_fields, iavf_flex_rx_hash, and
iavf_flex_rx_csum functions which operate on the flexible NIC descriptor
format instead of the legacy 32 byte format. Based on the negotiated
RXDID, select the correct function for processing the Rx descriptors.

With this change, the Rx hot path should be functional when using either
the default legacy 32byte format or when we switch to the flexible NIC
layout.

Modify the Rx hot path to add support for the flexible descriptor
format and add request enabling Rx timestamps for all queues.

As in ice, make sure we bump the checksum level if the hardware detected
a packet type which could have an outer checksum. This is important
because hardware only verifies the inner checksum.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_txrx.c | 354 ++++++++++++++------
 drivers/net/ethernet/intel/iavf/iavf_type.h | 127 ++++---
 2 files changed, 327 insertions(+), 154 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 46745ebc9c1fd..89b71509e521d 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -896,59 +896,43 @@ bool iavf_alloc_rx_buffers(struct iavf_ring *rx_ring, u16 cleaned_count)
 }
 
 /**
- * iavf_rx_checksum - Indicate in skb if hw indicated a good cksum
+ * iavf_rx_csum - Indicate in skb if hw indicated a good checksum
  * @vsi: the VSI we care about
  * @skb: skb currently being received and modified
- * @rx_desc: the receive descriptor
+ * @decoded_pt: decoded ptype information
+ * @csum_bits: decoded Rx descriptor information
  **/
-static void iavf_rx_checksum(struct iavf_vsi *vsi, struct sk_buff *skb,
-			     struct iavf_rx_desc *rx_desc)
+static void iavf_rx_csum(const struct iavf_vsi *vsi, struct sk_buff *skb,
+			 struct libeth_rx_pt decoded_pt,
+			 struct libeth_rx_csum csum_bits)
 {
-	struct libeth_rx_pt decoded;
-	u32 rx_error, rx_status;
 	bool ipv4, ipv6;
-	u64 qword;
-	u32 ptype;
 
 	skb->ip_summed = CHECKSUM_NONE;
 
-	qword = le64_to_cpu(rx_desc->qw1);
-	ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qword);
-
-	decoded = libie_rx_pt_parse(ptype);
-	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded))
-		return;
-
-	rx_error = FIELD_GET(IAVF_RXD_QW1_ERROR_MASK, qword);
-	rx_status = FIELD_GET(IAVF_RXD_QW1_STATUS_MASK, qword);
-
 	/* did the hardware decode the packet and checksum? */
-	if (!(rx_status & BIT(IAVF_RX_DESC_STATUS_L3L4P_SHIFT)))
+	if (unlikely(!csum_bits.l3l4p))
 		return;
 
-	ipv4 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV4;
-	ipv6 = libeth_rx_pt_get_ip_ver(decoded) == LIBETH_RX_PT_OUTER_IPV6;
+	ipv4 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV4;
+	ipv6 = libeth_rx_pt_get_ip_ver(decoded_pt) == LIBETH_RX_PT_OUTER_IPV6;
 
-	if (ipv4 &&
-	    (rx_error & (BIT(IAVF_RX_DESC_ERROR_IPE_SHIFT) |
-			 BIT(IAVF_RX_DESC_ERROR_EIPE_SHIFT))))
+	if (unlikely(ipv4 && (csum_bits.ipe || csum_bits.eipe)))
 		goto checksum_fail;
 
 	/* likely incorrect csum if alternate IP extension headers found */
-	if (ipv6 &&
-	    rx_status & BIT(IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT))
-		/* don't increment checksum err here, non-fatal err */
+	if (unlikely(ipv6 && csum_bits.ipv6exadd))
 		return;
 
 	/* there was some L4 error, count error and punt packet to the stack */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_L4E_SHIFT))
+	if (unlikely(csum_bits.l4e))
 		goto checksum_fail;
 
 	/* handle packets that were not able to be checksummed due
 	 * to arrival speed, in this case the stack can compute
 	 * the csum.
 	 */
-	if (rx_error & BIT(IAVF_RX_DESC_ERROR_PPRS_SHIFT))
+	if (unlikely(csum_bits.pprs))
 		return;
 
 	skb->ip_summed = CHECKSUM_UNNECESSARY;
@@ -959,30 +943,117 @@ static void iavf_rx_checksum(struct iavf_vsi *vsi, struct sk_buff *skb,
 }
 
 /**
- * iavf_rx_hash - set the hash value in the skb
+ * iavf_legacy_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_legacy_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		    const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_LEGACY_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_LEGACY_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_LEGACY_L4E_M, qw1);
+	csum_bits.pprs = FIELD_GET(IAVF_RXD_LEGACY_PPRS_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_LEGACY_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_LEGACY_IPV6EXADD_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_flex_rx_csum - Indicate in skb if hw indicated a good checksum
+ * @vsi: the VSI we care about
+ * @qw1: quad word 1
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: decoded checksum bits.
+ **/
+static struct libeth_rx_csum
+iavf_flex_rx_csum(const struct iavf_vsi *vsi, u64 qw1,
+		  const struct libeth_rx_pt decoded_pt)
+{
+	struct libeth_rx_csum csum_bits = {};
+
+	if (!libeth_rx_pt_has_checksum(vsi->netdev, decoded_pt))
+		return csum_bits;
+
+	csum_bits.ipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_IPE_M, qw1);
+	csum_bits.eipe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EIPE_M, qw1);
+	csum_bits.l4e = FIELD_GET(IAVF_RXD_FLEX_XSUM_L4E_M, qw1);
+	csum_bits.eudpe = FIELD_GET(IAVF_RXD_FLEX_XSUM_EUDPE_M, qw1);
+	csum_bits.l3l4p = FIELD_GET(IAVF_RXD_FLEX_L3L4P_M, qw1);
+	csum_bits.ipv6exadd = FIELD_GET(IAVF_RXD_FLEX_IPV6EXADD_M, qw1);
+	csum_bits.nat = FIELD_GET(IAVF_RXD_FLEX_NAT_M, qw1);
+
+	return csum_bits;
+}
+
+/**
+ * iavf_legacy_rx_hash - set the hash value in the skb
+ * @ring: descriptor ring
+ * @qw0: quad word 0
+ * @qw1: quad word 1
+ * @skb: skb currently being received and modified
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ **/
+static void iavf_legacy_rx_hash(const struct iavf_ring *ring, __le64 qw0,
+				__le64 qw1, struct sk_buff *skb,
+				const struct libeth_rx_pt decoded_pt)
+{
+	const __le64 rss_mask = cpu_to_le64(IAVF_RXD_LEGACY_FLTSTAT_M);
+	u32 hash;
+
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
+		return;
+
+	if ((qw1 & rss_mask) == rss_mask) {
+		hash = le64_get_bits(qw0, IAVF_RXD_LEGACY_RSS_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
+	}
+}
+
+/**
+ * iavf_flex_rx_hash - set the hash value in the skb
  * @ring: descriptor ring
- * @rx_desc: specific descriptor
+ * @qw1: quad word 1
  * @skb: skb currently being received and modified
- * @rx_ptype: Rx packet type
+ * @decoded_pt: decoded packet type
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
  **/
-static void iavf_rx_hash(struct iavf_ring *ring,
-			 struct iavf_rx_desc *rx_desc,
-			 struct sk_buff *skb,
-			 u8 rx_ptype)
+static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
+			      struct sk_buff *skb,
+			      const struct libeth_rx_pt decoded_pt)
 {
-	struct libeth_rx_pt decoded;
+	bool rss_valid;
 	u32 hash;
-	const __le64 rss_mask =
-		cpu_to_le64((u64)IAVF_RX_DESC_FLTSTAT_RSS_HASH <<
-			    IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT);
 
-	decoded = libie_rx_pt_parse(rx_ptype);
-	if (!libeth_rx_pt_has_hash(ring->netdev, decoded))
+	if (!libeth_rx_pt_has_hash(ring->netdev, decoded_pt))
 		return;
 
-	if ((rx_desc->qw1 & rss_mask) == rss_mask) {
-		hash = le64_get_bits(rx_desc->qw0, IAVF_RXD_LEGACY_RSS_M);
-		libeth_rx_pt_set_hash(skb, hash, decoded);
+	rss_valid = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_VALID_M);
+	if (rss_valid) {
+		hash = le64_get_bits(qw1, IAVF_RXD_FLEX_RSS_HASH_M);
+		libeth_rx_pt_set_hash(skb, hash, decoded_pt);
 	}
 }
 
@@ -991,20 +1062,33 @@ static void iavf_rx_hash(struct iavf_ring *ring,
  * @rx_ring: rx descriptor ring packet is being transacted on
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
- * @rx_ptype: the packet type decoded by hardware
+ * @ptype: the packet type decoded by hardware
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
  * other fields within the skb.
  **/
-static void
-iavf_process_skb_fields(struct iavf_ring *rx_ring,
-			struct iavf_rx_desc *rx_desc, struct sk_buff *skb,
-			u8 rx_ptype)
+static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
+				    const struct iavf_rx_desc *rx_desc,
+				    struct sk_buff *skb, u32 ptype)
 {
-	iavf_rx_hash(rx_ring, rx_desc, skb, rx_ptype);
+	struct libeth_rx_csum csum_bits;
+	struct libeth_rx_pt decoded_pt;
+	__le64 qw0 = rx_desc->qw0;
+	__le64 qw1 = rx_desc->qw1;
 
-	iavf_rx_checksum(rx_ring->vsi, skb, rx_desc);
+	decoded_pt = libie_rx_pt_parse(ptype);
+
+	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE) {
+		iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
+		csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+						decoded_pt);
+	} else {
+		iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
+		csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+					      decoded_pt);
+	}
+	iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits);
 
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 
@@ -1091,8 +1175,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
 /**
  * iavf_is_non_eop - process handling of non-EOP buffers
  * @rx_ring: Rx ring being processed
- * @rx_desc: Rx descriptor for current buffer
- * @skb: Current socket buffer containing buffer in progress
+ * @fields: Rx descriptor extracted fields
  *
  * This function updates next to clean.  If the buffer is an EOP buffer
  * this function exits returning false, otherwise it will place the
@@ -1100,8 +1183,7 @@ static struct sk_buff *iavf_build_skb(const struct libeth_fqe *rx_buffer,
  * that this is in fact a non-EOP buffer.
  **/
 static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
-			    struct iavf_rx_desc *rx_desc,
-			    struct sk_buff *skb)
+			    struct libeth_rqe_info fields)
 {
 	u32 ntc = rx_ring->next_to_clean + 1;
 
@@ -1112,8 +1194,7 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	prefetch(IAVF_RX_DESC(rx_ring, ntc));
 
 	/* if we are the last buffer then there is nothing else to do */
-#define IAVF_RXD_EOF BIT(IAVF_RX_DESC_STATUS_EOF_SHIFT)
-	if (likely(iavf_test_staterr(rx_desc, IAVF_RXD_EOF)))
+	if (likely(fields.eop))
 		return false;
 
 	rx_ring->rx_stats.non_eop_descs++;
@@ -1121,6 +1202,108 @@ static bool iavf_is_non_eop(struct iavf_ring *rx_ring,
 	return true;
 }
 
+/**
+ * iavf_extract_legacy_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_1_32B_BASE legacy 32byte
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_legacy_rx_fields(const struct iavf_ring *rx_ring,
+			      const struct iavf_rx_desc *rx_desc)
+{
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	struct libeth_rqe_info fields;
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_LEGACY_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_LEGACY_LENGTH_M, qw1);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_LEGACY_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_LEGACY_PTYPE_M, qw1);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG1_M, qw0);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_LEGACY_L2TAG2_M, qw2);
+	}
+
+	return fields;
+}
+
+/**
+ * iavf_extract_flex_rx_fields - Extract fields from the Rx descriptor
+ * @rx_ring: rx descriptor ring
+ * @rx_desc: the descriptor to process
+ *
+ * Decode the Rx descriptor and extract relevant information including the
+ * size, VLAN tag, Rx packet type, end of packet field and RXE field value.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ *
+ * Return: fields extracted from the Rx descriptor.
+ */
+static struct libeth_rqe_info
+iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring,
+			    const struct iavf_rx_desc *rx_desc)
+{
+	struct libeth_rqe_info fields = {};
+	u64 qw0 = le64_to_cpu(rx_desc->qw0);
+	u64 qw1 = le64_to_cpu(rx_desc->qw1);
+	u64 qw2 = le64_to_cpu(rx_desc->qw2);
+	bool l2tag1p, l2tag2p;
+
+	fields.eop = FIELD_GET(IAVF_RXD_FLEX_EOP_M, qw1);
+	fields.len = FIELD_GET(IAVF_RXD_FLEX_PKT_LEN_M, qw0);
+
+	if (!fields.eop)
+		return fields;
+
+	fields.rxe = FIELD_GET(IAVF_RXD_FLEX_RXE_M, qw1);
+	fields.ptype = FIELD_GET(IAVF_RXD_FLEX_PTYPE_M, qw0);
+	fields.vlan = 0;
+
+	if (rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1) {
+		l2tag1p = FIELD_GET(IAVF_RXD_FLEX_L2TAG1P_M, qw1);
+		if (l2tag1p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG1_M, qw1);
+	} else if (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2) {
+		l2tag2p = FIELD_GET(IAVF_RXD_FLEX_L2TAG2P_M, qw2);
+		if (l2tag2p)
+			fields.vlan = FIELD_GET(IAVF_RXD_FLEX_L2TAG2_2_M, qw2);
+	}
+
+	return fields;
+}
+
+static struct libeth_rqe_info
+iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
+		       const struct iavf_rx_desc *rx_desc)
+{
+	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE)
+		return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
+	else
+		return iavf_extract_flex_rx_fields(rx_ring, rx_desc);
+}
+
 /**
  * iavf_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf
  * @rx_ring: rx descriptor ring to transact packets on
@@ -1141,13 +1324,9 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 	bool failure = false;
 
 	while (likely(total_rx_packets < (unsigned int)budget)) {
+		struct libeth_rqe_info fields;
 		struct libeth_fqe *rx_buffer;
 		struct iavf_rx_desc *rx_desc;
-		u16 ext_status = 0;
-		unsigned int size;
-		u16 vlan_tag = 0;
-		u8 rx_ptype;
-		u64 qw1;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1158,35 +1337,28 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 
 		rx_desc = IAVF_RX_DESC(rx_ring, rx_ring->next_to_clean);
 
-		/* status_error_len will always be zero for unused descriptors
-		 * because it's cleared in cleanup, and overlaps with hdr_addr
-		 * which is always zero because packet split isn't used, if the
-		 * hardware wrote DD then the length will be non-zero
-		 */
-		qw1 = le64_to_cpu(rx_desc->qw1);
-
 		/* This memory barrier is needed to keep us from reading
 		 * any other fields out of the rx_desc until we have
 		 * verified the descriptor has been written back.
 		 */
 		dma_rmb();
-#define IAVF_RXD_DD BIT(IAVF_RX_DESC_STATUS_DD_SHIFT)
-		if (!iavf_test_staterr(rx_desc, IAVF_RXD_DD))
+
+		if (!iavf_test_staterr(rx_desc, IAVF_RXD_FLEX_DD_M))
 			break;
 
-		size = FIELD_GET(IAVF_RXD_QW1_LENGTH_PBUF_MASK, qw1);
+		fields = iavf_extract_rx_fields(rx_ring, rx_desc);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 
 		rx_buffer = &rx_ring->rx_fqes[rx_ring->next_to_clean];
-		if (!libeth_rx_sync_for_cpu(rx_buffer, size))
+		if (!libeth_rx_sync_for_cpu(rx_buffer, fields.len))
 			goto skip_data;
 
 		/* retrieve a buffer from the ring */
 		if (skb)
-			iavf_add_rx_frag(skb, rx_buffer, size);
+			iavf_add_rx_frag(skb, rx_buffer, fields.len);
 		else
-			skb = iavf_build_skb(rx_buffer, size);
+			skb = iavf_build_skb(rx_buffer, fields.len);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb) {
@@ -1197,15 +1369,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 skip_data:
 		cleaned_count++;
 
-		if (iavf_is_non_eop(rx_ring, rx_desc, skb) || unlikely(!skb))
+		if (iavf_is_non_eop(rx_ring, fields) || unlikely(!skb))
 			continue;
 
-		/* ERR_MASK will only have valid bits if EOP set, and
-		 * what we are doing here is actually checking
-		 * IAVF_RX_DESC_ERROR_RXE_SHIFT, since it is the zeroth bit in
-		 * the error field
+		/* RXE field in descriptor is an indication of the MAC errors
+		 * (like CRC, alignment, oversize etc). If it is set then iavf
+		 * should finish.
 		 */
-		if (unlikely(iavf_test_staterr(rx_desc, BIT(IAVF_RXD_QW1_ERROR_SHIFT)))) {
+		if (unlikely(fields.rxe)) {
 			dev_kfree_skb_any(skb);
 			skb = NULL;
 			continue;
@@ -1219,26 +1390,11 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		/* probably a little skewed due to removing CRC */
 		total_rx_bytes += skb->len;
 
-		rx_ptype = FIELD_GET(IAVF_RXD_QW1_PTYPE_MASK, qw1);
-
 		/* populate checksum, VLAN, and protocol */
-		iavf_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype);
-
-		if (qw1 & BIT(IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT) &&
-		    rx_ring->flags & IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1)
-			vlan_tag = le64_get_bits(rx_desc->qw0,
-						 IAVF_RXD_LEGACY_L2TAG1_M);
-
-		ext_status = le64_get_bits(rx_desc->qw2,
-					   IAVF_RXD_LEGACY_EXT_STATUS_M);
-
-		if ((ext_status & IAVF_RX_DESC_EXT_STATUS_L2TAG2P_M) &&
-		    (rx_ring->flags & IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2))
-			vlan_tag = le64_get_bits(rx_desc->qw2,
-						 IAVF_RXD_LEGACY_L2TAG2_2_M);
+		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
-		iavf_receive_skb(rx_ring, skb, vlan_tag);
+		iavf_receive_skb(rx_ring, skb, fields.vlan);
 		skb = NULL;
 
 		/* update budget accounting */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index e000971e3c013..3dc0907bf70d7 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -206,46 +206,86 @@ struct iavf_rx_desc {
 #define IAVF_RXD_LEGACY_RSS_M			GENMASK_ULL(63, 32)
 /* Stripped C-TAG VLAN from the receive packet */
 #define IAVF_RXD_LEGACY_L2TAG1_M		GENMASK_ULL(33, 16)
+/* Packet type */
+#define IAVF_RXD_FLEX_PTYPE_M			GENMASK_ULL(25, 16)
+/* Packet length */
+#define IAVF_RXD_FLEX_PKT_LEN_M			GENMASK_ULL(45, 32)
 
 	aligned_le64 qw1;
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_LEGACY_EOP_M			BIT(1)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_LEGACY_L2TAG1P_M		BIT(2)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_LEGACY_L3L4P_M			BIT(3)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_LEGACY_IPV6EXADD_M		BIT(15)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_LEGACY_RXE_M			BIT(19)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ */
+#define IAVF_RXD_LEGACY_IPE_M			BIT(22)
+#define IAVF_RXD_LEGACY_L4E_M			BIT(23)
+#define IAVF_RXD_LEGACY_EIPE_M			BIT(24)
+/* Set for packets that skip checksum calculation in pre-parser */
+#define IAVF_RXD_LEGACY_PPRS_M			BIT(26)
+/* Indicates the content in the Filter Status field */
+#define IAVF_RXD_LEGACY_FLTSTAT_M		GENMASK_ULL(13, 12)
+/* Packet type */
+#define IAVF_RXD_LEGACY_PTYPE_M			GENMASK_ULL(37, 30)
+/* Packet length */
+#define IAVF_RXD_LEGACY_LENGTH_M		GENMASK_ULL(51, 38)
+/* Descriptor done indication flag */
+#define IAVF_RXD_FLEX_DD_M			BIT(0)
+/* End of packet. Set to 1 if this descriptor is the last one of the packet */
+#define IAVF_RXD_FLEX_EOP_M			BIT(1)
+/* Detectable L3 and L4 integrity check is processed by the HW */
+#define IAVF_RXD_FLEX_L3L4P_M			BIT(3)
+/* Checksum reports:
+ * - IPE: IP checksum error
+ * - L4E: L4 integrity error
+ * - EIPE: External IP header (tunneled packets)
+ * - EUDPE: External UDP checksum error (tunneled packets)
+ */
+#define IAVF_RXD_FLEX_XSUM_IPE_M		BIT(4)
+#define IAVF_RXD_FLEX_XSUM_L4E_M		BIT(5)
+#define IAVF_RXD_FLEX_XSUM_EIPE_M		BIT(6)
+#define IAVF_RXD_FLEX_XSUM_EUDPE_M		BIT(7)
+/* Set when an IPv6 packet contains a Destination Options Header or a Routing
+ * Header.
+ */
+#define IAVF_RXD_FLEX_IPV6EXADD_M		BIT(9)
+/* Receive MAC Errors: CRC; Alignment; Oversize; Undersizes; Length error */
+#define IAVF_RXD_FLEX_RXE_M			BIT(10)
+/* Indicates that the RSS/HASH result is valid */
+#define IAVF_RXD_FLEX_RSS_VALID_M		BIT(12)
+/* L2 TAG 1 presence indication */
+#define IAVF_RXD_FLEX_L2TAG1P_M			BIT(13)
+/* Stripped L2 Tag from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG1_M			GENMASK_ULL(31, 16)
+/* The hash signature (RSS) */
+#define IAVF_RXD_FLEX_RSS_HASH_M		GENMASK_ULL(63, 32)
+
 	aligned_le64 qw2;
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_LEGACY_L2TAG2P_M		BIT(0)
 /* Stripped S-TAG VLAN from the receive packet */
-#define IAVF_RXD_LEGACY_L2TAG2_2_M		GENMASK_ULL(63, 48)
-/* Extended status bits */
-#define IAVF_RXD_LEGACY_EXT_STATUS_M		GENMASK_ULL(11, 0)
-
+#define IAVF_RXD_LEGACY_L2TAG2_M		GENMASK_ULL(63, 32)
+/* Stripped S-TAG VLAN from the receive packet */
+#define IAVF_RXD_FLEX_L2TAG2_2_M		GENMASK_ULL(63, 48)
+/* The packet is a UDP tunneled packet */
+#define IAVF_RXD_FLEX_NAT_M			BIT(4)
+/* L2 Tag 2 Presence */
+#define IAVF_RXD_FLEX_L2TAG2P_M			BIT(11)
 	aligned_le64 qw3;
 } __aligned(4 * sizeof(__le64));
 static_assert(sizeof(struct iavf_rx_desc) == 32);
 
-enum iavf_rx_desc_status_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_STATUS_DD_SHIFT		= 0,
-	IAVF_RX_DESC_STATUS_EOF_SHIFT		= 1,
-	IAVF_RX_DESC_STATUS_L2TAG1P_SHIFT	= 2,
-	IAVF_RX_DESC_STATUS_L3L4P_SHIFT		= 3,
-	IAVF_RX_DESC_STATUS_CRCP_SHIFT		= 4,
-	IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT	= 5, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_TSYNVALID_SHIFT	= 7,
-	/* Note: Bit 8 is reserved in X710 and XL710 */
-	IAVF_RX_DESC_STATUS_EXT_UDP_0_SHIFT	= 8,
-	IAVF_RX_DESC_STATUS_UMBCAST_SHIFT	= 9, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_FLM_SHIFT		= 11,
-	IAVF_RX_DESC_STATUS_FLTSTAT_SHIFT	= 12, /* 2 BITS */
-	IAVF_RX_DESC_STATUS_LPBK_SHIFT		= 14,
-	IAVF_RX_DESC_STATUS_IPV6EXADD_SHIFT	= 15,
-	IAVF_RX_DESC_STATUS_RESERVED_SHIFT	= 16, /* 2 BITS */
-	/* Note: For non-tunnel packets INT_UDP_0 is the right status for
-	 * UDP header
-	 */
-	IAVF_RX_DESC_STATUS_INT_UDP_0_SHIFT	= 18,
-	IAVF_RX_DESC_STATUS_LAST /* this entry must be last!!! */
-};
-
-#define IAVF_RXD_QW1_STATUS_SHIFT	0
-#define IAVF_RXD_QW1_STATUS_MASK	((BIT(IAVF_RX_DESC_STATUS_LAST) - 1) \
-					 << IAVF_RXD_QW1_STATUS_SHIFT)
-
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT IAVF_RX_DESC_STATUS_TSYNINDX_SHIFT
 #define IAVF_RXD_QW1_STATUS_TSYNINDX_MASK  (0x3UL << \
 					    IAVF_RXD_QW1_STATUS_TSYNINDX_SHIFT)
@@ -261,22 +301,6 @@ enum iavf_rx_desc_fltstat_values {
 	IAVF_RX_DESC_FLTSTAT_RSS_HASH	= 3,
 };
 
-#define IAVF_RXD_QW1_ERROR_SHIFT	19
-#define IAVF_RXD_QW1_ERROR_MASK		(0xFFUL << IAVF_RXD_QW1_ERROR_SHIFT)
-
-enum iavf_rx_desc_error_bits {
-	/* Note: These are predefined bit offsets */
-	IAVF_RX_DESC_ERROR_RXE_SHIFT		= 0,
-	IAVF_RX_DESC_ERROR_RECIPE_SHIFT		= 1,
-	IAVF_RX_DESC_ERROR_HBO_SHIFT		= 2,
-	IAVF_RX_DESC_ERROR_L3L4E_SHIFT		= 3, /* 3 BITS */
-	IAVF_RX_DESC_ERROR_IPE_SHIFT		= 3,
-	IAVF_RX_DESC_ERROR_L4E_SHIFT		= 4,
-	IAVF_RX_DESC_ERROR_EIPE_SHIFT		= 5,
-	IAVF_RX_DESC_ERROR_OVERSIZE_SHIFT	= 6,
-	IAVF_RX_DESC_ERROR_PPRS_SHIFT		= 7
-};
-
 enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_NONE		= 0,
 	IAVF_RX_DESC_ERROR_L3L4E_PROT		= 1,
@@ -285,13 +309,6 @@ enum iavf_rx_desc_error_l3l4e_fcoe_masks {
 	IAVF_RX_DESC_ERROR_L3L4E_DMAC_WARN	= 4
 };
 
-#define IAVF_RXD_QW1_PTYPE_SHIFT	30
-#define IAVF_RXD_QW1_PTYPE_MASK		(0xFFULL << IAVF_RXD_QW1_PTYPE_SHIFT)
-
-#define IAVF_RXD_QW1_LENGTH_PBUF_SHIFT	38
-#define IAVF_RXD_QW1_LENGTH_PBUF_MASK	(0x3FFFULL << \
-					 IAVF_RXD_QW1_LENGTH_PBUF_SHIFT)
-
 #define IAVF_RXD_QW1_LENGTH_HBUF_SHIFT	52
 #define IAVF_RXD_QW1_LENGTH_HBUF_MASK	(0x7FFULL << \
 					 IAVF_RXD_QW1_LENGTH_HBUF_SHIFT)

From 8447357e7b04d09dde4ad04d93672b9f0f47a66c Mon Sep 17 00:00:00 2001
From: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Date: Wed, 6 Nov 2024 12:37:29 -0500
Subject: [PATCH 0550/2753] iavf: Implement checking DD desc field

Rx timestamping introduced in PF driver caused the need of refactoring
the VF driver mechanism to check packet fields.

The function to check errors in descriptor has been removed and from
now only previously set struct fields are being checked. The field DD
(descriptor done) needs to be checked at the very beginning, before
extracting other fields.

Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_txrx.c | 54 ++++++++++++++++-----
 drivers/net/ethernet/intel/iavf/iavf_txrx.h | 16 ------
 drivers/net/ethernet/intel/iavf/iavf_type.h |  2 +
 3 files changed, 43 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 89b71509e521d..283997b8a7772 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -9,6 +9,25 @@
 #include "iavf_trace.h"
 #include "iavf_prototype.h"
 
+/**
+ * iavf_is_descriptor_done - tests DD bit in Rx descriptor
+ * @qw1: quad word 1 from descriptor to get Descriptor Done field from
+ * @flex: is the descriptor flex or legacy
+ *
+ * This function tests the descriptor done bit in specified descriptor. Because
+ * there are two types of descriptors (legacy and flex) the parameter rx_ring
+ * is used to distinguish.
+ *
+ * Return: true or false based on the state of DD bit in Rx descriptor.
+ */
+static bool iavf_is_descriptor_done(u64 qw1, bool flex)
+{
+	if (flex)
+		return FIELD_GET(IAVF_RXD_FLEX_DD_M, qw1);
+	else
+		return FIELD_GET(IAVF_RXD_LEGACY_DD_M, qw1);
+}
+
 static __le64 build_ctob(u32 td_cmd, u32 td_offset, unsigned int size,
 			 u32 td_tag)
 {
@@ -1063,6 +1082,7 @@ static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
  * @rx_desc: pointer to the EOP Rx descriptor
  * @skb: pointer to current skb being populated
  * @ptype: the packet type decoded by hardware
+ * @flex: is the descriptor flex or legacy
  *
  * This function checks the ring, descriptor, and packet information in
  * order to populate the hash, checksum, VLAN, protocol, and
@@ -1070,7 +1090,8 @@ static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
  **/
 static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
 				    const struct iavf_rx_desc *rx_desc,
-				    struct sk_buff *skb, u32 ptype)
+				    struct sk_buff *skb, u32 ptype,
+				    bool flex)
 {
 	struct libeth_rx_csum csum_bits;
 	struct libeth_rx_pt decoded_pt;
@@ -1079,14 +1100,14 @@ static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
 
 	decoded_pt = libie_rx_pt_parse(ptype);
 
-	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE) {
-		iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
-		csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
-						decoded_pt);
-	} else {
+	if (flex) {
 		iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
 		csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
 					      decoded_pt);
+	} else {
+		iavf_legacy_rx_hash(rx_ring, qw0, qw1, skb, decoded_pt);
+		csum_bits = iavf_legacy_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
+						decoded_pt);
 	}
 	iavf_rx_csum(rx_ring->vsi, skb, decoded_pt, csum_bits);
 
@@ -1296,12 +1317,13 @@ iavf_extract_flex_rx_fields(const struct iavf_ring *rx_ring,
 
 static struct libeth_rqe_info
 iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
-		       const struct iavf_rx_desc *rx_desc)
+		       const struct iavf_rx_desc *rx_desc,
+		       bool flex)
 {
-	if (rx_ring->rxdid == VIRTCHNL_RXDID_1_32B_BASE)
-		return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
-	else
+	if (flex)
 		return iavf_extract_flex_rx_fields(rx_ring, rx_desc);
+	else
+		return iavf_extract_legacy_rx_fields(rx_ring, rx_desc);
 }
 
 /**
@@ -1318,6 +1340,7 @@ iavf_extract_rx_fields(const struct iavf_ring *rx_ring,
  **/
 static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 {
+	bool flex = rx_ring->rxdid == VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
 	unsigned int total_rx_bytes = 0, total_rx_packets = 0;
 	struct sk_buff *skb = rx_ring->skb;
 	u16 cleaned_count = IAVF_DESC_UNUSED(rx_ring);
@@ -1327,6 +1350,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		struct libeth_rqe_info fields;
 		struct libeth_fqe *rx_buffer;
 		struct iavf_rx_desc *rx_desc;
+		u64 qw1;
 
 		/* return some buffers to hardware, one at a time is too slow */
 		if (cleaned_count >= IAVF_RX_BUFFER_WRITE) {
@@ -1343,10 +1367,14 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		 */
 		dma_rmb();
 
-		if (!iavf_test_staterr(rx_desc, IAVF_RXD_FLEX_DD_M))
+		qw1 = le64_to_cpu(rx_desc->qw1);
+		/* If DD field (descriptor done) is unset then other fields are
+		 * not valid
+		 */
+		if (!iavf_is_descriptor_done(qw1, flex))
 			break;
 
-		fields = iavf_extract_rx_fields(rx_ring, rx_desc);
+		fields = iavf_extract_rx_fields(rx_ring, rx_desc, flex);
 
 		iavf_trace(clean_rx_irq, rx_ring, rx_desc, skb);
 
@@ -1391,7 +1419,7 @@ static int iavf_clean_rx_irq(struct iavf_ring *rx_ring, int budget)
 		total_rx_bytes += skb->len;
 
 		/* populate checksum, VLAN, and protocol */
-		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype);
+		iavf_process_skb_fields(rx_ring, rx_desc, skb, fields.ptype, flex);
 
 		iavf_trace(clean_rx_irq_rx, rx_ring, rx_desc, skb);
 		iavf_receive_skb(rx_ring, skb, fields.vlan);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 3a1a39ee3615b..dff5c8cd27ab8 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -80,22 +80,6 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-/**
- * iavf_test_staterr - tests bits in Rx descriptor status and error fields
- * @rx_desc: pointer to receive descriptor (in le64 format)
- * @stat_err_bits: value to mask
- *
- * This function does some fast chicanery in order to return the
- * value of the mask which is really only used for boolean tests.
- * The status_error_len doesn't need to be shifted because it begins
- * at offset zero.
- */
-static inline bool iavf_test_staterr(struct iavf_rx_desc *rx_desc,
-				     const u64 stat_err_bits)
-{
-	return !!(rx_desc->qw1 & cpu_to_le64(stat_err_bits));
-}
-
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IAVF_RX_INCREMENT(r, i) \
 	do {					\
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index 3dc0907bf70d7..e62a8a0067ea0 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -212,6 +212,8 @@ struct iavf_rx_desc {
 #define IAVF_RXD_FLEX_PKT_LEN_M			GENMASK_ULL(45, 32)
 
 	aligned_le64 qw1;
+/* Descriptor done indication flag. */
+#define IAVF_RXD_LEGACY_DD_M			BIT(0)
 /* End of packet. Set to 1 if this descriptor is the last one of the packet */
 #define IAVF_RXD_LEGACY_EOP_M			BIT(1)
 /* L2 TAG 1 presence indication */

From 51534239ef132afbc8cc65cf430aeaeec244a6ad Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:30 -0500
Subject: [PATCH 0551/2753] iavf: handle set and get timestamps ops

Add handlers for the .ndo_hwtstamp_get and .ndo_hwtstamp_set ops which
allow userspace to request timestamp enablement for the device. This
support allows standard Linux applications to request the timestamping
desired.

As with other devices that support timestamping all packets, the driver
will upgrade any request for timestamping of a specific type of packet
to HWTSTAMP_FILTER_ALL.

The current configuration is stored, so that it can be retrieved by
calling .ndo_hwtstamp_get

The Tx timestamps are not implemented yet so calling set ops for
Tx path will end with EOPNOTSUPP error code.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Co-developed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c |  21 ++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.c  | 100 ++++++++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.h  |   9 ++
 drivers/net/ethernet/intel/iavf/iavf_txrx.h |   1 +
 4 files changed, 131 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index d545b34496e73..2d908ff0152ca 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -5170,6 +5170,25 @@ static netdev_features_t iavf_fix_features(struct net_device *netdev,
 	return iavf_fix_strip_features(adapter, features);
 }
 
+static int iavf_hwstamp_get(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	*config = adapter->ptp.hwtstamp_config;
+
+	return 0;
+}
+
+static int iavf_hwstamp_set(struct net_device *netdev,
+			    struct kernel_hwtstamp_config *config,
+			    struct netlink_ext_ack *extack)
+{
+	struct iavf_adapter *adapter = netdev_priv(netdev);
+
+	return iavf_ptp_set_ts_config(adapter, config, extack);
+}
+
 static int
 iavf_verify_shaper(struct net_shaper_binding *binding,
 		   const struct net_shaper *shaper,
@@ -5278,6 +5297,8 @@ static const struct net_device_ops iavf_netdev_ops = {
 	.ndo_set_features	= iavf_set_features,
 	.ndo_setup_tc		= iavf_setup_tc,
 	.net_shaper_ops		= &iavf_shaper_ops,
+	.ndo_hwtstamp_get	= iavf_hwstamp_get,
+	.ndo_hwtstamp_set	= iavf_hwstamp_set,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
index c2e0d27552b00..4246ddfa6f0d2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -7,6 +7,100 @@
 #define iavf_clock_to_adapter(info)				\
 	container_of_const(info, struct iavf_adapter, ptp.info)
 
+/**
+ * iavf_ptp_disable_rx_tstamp - Disable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Disable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_disable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags &= ~IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_enable_rx_tstamp - Enable timestamping in Rx rings
+ * @adapter: private adapter structure
+ *
+ * Enable timestamp reporting for all Rx rings.
+ */
+static void iavf_ptp_enable_rx_tstamp(struct iavf_adapter *adapter)
+{
+	for (u32 i = 0; i < adapter->num_active_queues; i++)
+		adapter->rx_rings[i].flags |= IAVF_TXRX_FLAGS_HW_TSTAMP;
+}
+
+/**
+ * iavf_ptp_set_timestamp_mode - Set device timestamping mode
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config
+ *
+ * Set the timestamping mode requested from the userspace.
+ *
+ * Note: this function always translates Rx timestamp requests for any packet
+ * category into HWTSTAMP_FILTER_ALL.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+static int iavf_ptp_set_timestamp_mode(struct iavf_adapter *adapter,
+				       struct kernel_hwtstamp_config *config)
+{
+	/* Reserved for future extensions. */
+	if (config->flags)
+		return -EINVAL;
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		return -EOPNOTSUPP;
+	default:
+		return -ERANGE;
+	}
+
+	if (config->rx_filter == HWTSTAMP_FILTER_NONE) {
+		iavf_ptp_disable_rx_tstamp(adapter);
+		return 0;
+	} else if (config->rx_filter > HWTSTAMP_FILTER_NTP_ALL) {
+		return -ERANGE;
+	} else if (!(iavf_ptp_cap_supported(adapter,
+					    VIRTCHNL_1588_PTP_CAP_RX_TSTAMP))) {
+		return -EOPNOTSUPP;
+	}
+
+	config->rx_filter = HWTSTAMP_FILTER_ALL;
+	iavf_ptp_enable_rx_tstamp(adapter);
+
+	return 0;
+}
+
+/**
+ * iavf_ptp_set_ts_config - Set timestamping configuration
+ * @adapter: private adapter structure
+ * @config: pointer to kernel_hwtstamp_config structure
+ * @extack: pointer to netlink_ext_ack structure
+ *
+ * Program the requested timestamping configuration to the device.
+ *
+ * Return: 0 on success, negative error code otherwise.
+ */
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack)
+{
+	int err;
+
+	err = iavf_ptp_set_timestamp_mode(adapter, config);
+	if (err)
+		return err;
+
+	/* Save successful settings for future reference */
+	adapter->ptp.hwtstamp_config = *config;
+
+	return 0;
+}
+
 /**
  * iavf_ptp_cap_supported - Check if a PTP capability is supported
  * @adapter: private adapter structure
@@ -321,4 +415,10 @@ void iavf_ptp_process_caps(struct iavf_adapter *adapter)
 		iavf_ptp_release(adapter);
 	else if (!adapter->ptp.clock && phc)
 		iavf_ptp_init(adapter);
+
+	/* Check if the device lost access to Rx timestamp incoming packets */
+	if (!iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+		iavf_ptp_disable_rx_tstamp(adapter);
+	}
 }
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
index 8e2f1ed18b868..0801e3ff5a596 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -12,6 +12,9 @@ void iavf_ptp_release(struct iavf_adapter *adapter);
 void iavf_ptp_process_caps(struct iavf_adapter *adapter);
 bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter, u32 cap);
 void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
+int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+			   struct kernel_hwtstamp_config *config,
+			   struct netlink_ext_ack *extack);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
 static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
@@ -23,5 +26,11 @@ static inline bool iavf_ptp_cap_supported(const struct iavf_adapter *adapter,
 }
 
 static inline void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter) { }
+static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
+					 struct kernel_hwtstamp_config *config,
+					 struct netlink_ext_ack *extack)
+{
+	return -1;
+}
 #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 #endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index dff5c8cd27ab8..79ad554f2d53b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -252,6 +252,7 @@ struct iavf_ring {
 #define IAVF_TXRX_FLAGS_VLAN_TAG_LOC_L2TAG1	BIT(3)
 #define IAVF_TXR_FLAGS_VLAN_TAG_LOC_L2TAG2	BIT(4)
 #define IAVF_RXR_FLAGS_VLAN_TAG_LOC_L2TAG2_2	BIT(5)
+#define IAVF_TXRX_FLAGS_HW_TSTAMP		BIT(6)
 
 	/* stats structs */
 	struct iavf_queue_stats	stats;

From 48ccdcd87e0d2d4c82eb50eaff53c6aeb9a8372b Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 6 Nov 2024 12:37:31 -0500
Subject: [PATCH 0552/2753] iavf: add support for Rx timestamps to hotpath

Add support for receive timestamps to the Rx hotpath. This support only
works when using the flexible descriptor format, so make sure that we
request this format by default if we have receive timestamp support
available in the PTP capabilities.

In order to report the timestamps to userspace, we need to perform
timestamp extension. The Rx descriptor does actually contain the "40
bit" timestamp. However, upper 32 bits which contain nanoseconds are
conveniently stored separately in the descriptor. We could extract the
32bits and lower 8 bits, then perform a bitwise OR to calculate the
40bit value. This makes no sense, because the timestamp extension
algorithm would simply discard the lower 8 bits anyways.

Thus, implement timestamp extension as iavf_ptp_extend_32b_timestamp(),
and extract and forward only the 32bits of nominal nanoseconds.

Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Rahul Rameshbabu <rrameshbabu@nvidia.com>
Reviewed-by: Sunil Goutham <sgoutham@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c |  9 +++
 drivers/net/ethernet/intel/iavf/iavf_ptp.c  | 61 +++++++++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_ptp.h  | 11 ++++
 drivers/net/ethernet/intel/iavf/iavf_txrx.c | 43 +++++++++++++++
 drivers/net/ethernet/intel/iavf/iavf_type.h |  1 +
 5 files changed, 125 insertions(+)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2d908ff0152ca..4c29739780bda 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -730,6 +730,15 @@ static u8 iavf_select_rx_desc_format(const struct iavf_adapter *adapter)
 	if (!IAVF_RXDID_ALLOWED(adapter))
 		return VIRTCHNL_RXDID_1_32B_BASE;
 
+	/* Rx timestamping requires the use of flexible NIC descriptors */
+	if (iavf_ptp_cap_supported(adapter, VIRTCHNL_1588_PTP_CAP_RX_TSTAMP)) {
+		if (rxdids & BIT(VIRTCHNL_RXDID_2_FLEX_SQ_NIC))
+			return VIRTCHNL_RXDID_2_FLEX_SQ_NIC;
+
+		pci_warn(adapter->pdev,
+			 "Unable to negotiate flexible descriptor format\n");
+	}
+
 	/* Warn if the PF does not list support for the default legacy
 	 * descriptor format. This shouldn't happen, as this is the format
 	 * used if VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is not supported. It is
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.c b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
index 4246ddfa6f0d2..b4d5eda2e84fc 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.c
@@ -394,6 +394,9 @@ void iavf_ptp_release(struct iavf_adapter *adapter)
 	}
 	adapter->aq_required &= ~IAVF_FLAG_AQ_SEND_PTP_CMD;
 	mutex_unlock(&adapter->ptp.aq_cmd_lock);
+
+	adapter->ptp.hwtstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	iavf_ptp_disable_rx_tstamp(adapter);
 }
 
 /**
@@ -422,3 +425,61 @@ void iavf_ptp_process_caps(struct iavf_adapter *adapter)
 		iavf_ptp_disable_rx_tstamp(adapter);
 	}
 }
+
+/**
+ * iavf_ptp_extend_32b_timestamp - Convert a 32b nanoseconds timestamp to 64b
+ * nanoseconds
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_tstamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Extend the 32bit nanosecond timestamp using the following algorithm and
+ * assumptions:
+ *
+ * 1) have a recently cached copy of the PHC time
+ * 2) assume that the in_tstamp was captured 2^31 nanoseconds (~2.1
+ *    seconds) before or after the PHC time was captured.
+ * 3) calculate the delta between the cached time and the timestamp
+ * 4) if the delta is smaller than 2^31 nanoseconds, then the timestamp was
+ *    captured after the PHC time. In this case, the full timestamp is just
+ *    the cached PHC time plus the delta.
+ * 5) otherwise, if the delta is larger than 2^31 nanoseconds, then the
+ *    timestamp was captured *before* the PHC time, i.e. because the PHC
+ *    cache was updated after the timestamp was captured by hardware. In this
+ *    case, the full timestamp is the cached time minus the inverse delta.
+ *
+ * This algorithm works even if the PHC time was updated after a Tx timestamp
+ * was requested, but before the Tx timestamp event was reported from
+ * hardware.
+ *
+ * This calculation primarily relies on keeping the cached PHC time up to
+ * date. If the timestamp was captured more than 2^31 nanoseconds after the
+ * PHC time, it is possible that the lower 32bits of PHC time have
+ * overflowed more than once, and we might generate an incorrect timestamp.
+ *
+ * This is prevented by (a) periodically updating the cached PHC time once
+ * a second, and (b) discarding any Tx timestamp packet if it has waited for
+ * a timestamp for more than one second.
+ *
+ * Return: extended timestamp (to 64b).
+ */
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp)
+{
+	u32 low = lower_32_bits(cached_phc_time);
+	u32 delta = in_tstamp - low;
+	u64 ns;
+
+	/* Do not assume that the in_tstamp is always more recent than the
+	 * cached PHC time. If the delta is large, it indicates that the
+	 * in_tstamp was taken in the past, and should be converted
+	 * forward.
+	 */
+	if (delta > S32_MAX)
+		ns = cached_phc_time - (low - in_tstamp);
+	else
+		ns = cached_phc_time + delta;
+
+	return ns;
+}
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ptp.h b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
index 0801e3ff5a596..783b8f287cd95 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ptp.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_ptp.h
@@ -6,6 +6,9 @@
 
 #include "iavf_types.h"
 
+/* bit indicating whether a 40bit timestamp is valid */
+#define IAVF_PTP_40B_TSTAMP_VALID	BIT(24)
+
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 void iavf_ptp_init(struct iavf_adapter *adapter);
 void iavf_ptp_release(struct iavf_adapter *adapter);
@@ -15,6 +18,7 @@ void iavf_virtchnl_send_ptp_cmd(struct iavf_adapter *adapter);
 int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
 			   struct kernel_hwtstamp_config *config,
 			   struct netlink_ext_ack *extack);
+u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time, u32 in_tstamp);
 #else /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 static inline void iavf_ptp_init(struct iavf_adapter *adapter) { }
 static inline void iavf_ptp_release(struct iavf_adapter *adapter) { }
@@ -32,5 +36,12 @@ static inline int iavf_ptp_set_ts_config(struct iavf_adapter *adapter,
 {
 	return -1;
 }
+
+static inline u64 iavf_ptp_extend_32b_timestamp(u64 cached_phc_time,
+						u32 in_tstamp)
+{
+	return 0;
+}
+
 #endif /* IS_ENABLED(CONFIG_PTP_1588_CLOCK) */
 #endif /* _IAVF_PTP_H_ */
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
index 283997b8a7772..422312b8b54a1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c
@@ -8,6 +8,7 @@
 #include "iavf.h"
 #include "iavf_trace.h"
 #include "iavf_prototype.h"
+#include "iavf_ptp.h"
 
 /**
  * iavf_is_descriptor_done - tests DD bit in Rx descriptor
@@ -1076,6 +1077,45 @@ static void iavf_flex_rx_hash(const struct iavf_ring *ring, __le64 qw1,
 	}
 }
 
+/**
+ * iavf_flex_rx_tstamp - Capture Rx timestamp from the descriptor
+ * @rx_ring: descriptor ring
+ * @qw2: quad word 2 of descriptor
+ * @qw3: quad word 3 of descriptor
+ * @skb: skb currently being received
+ *
+ * Read the Rx timestamp value from the descriptor and pass it to the stack.
+ *
+ * This function only operates on the VIRTCHNL_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+static void iavf_flex_rx_tstamp(const struct iavf_ring *rx_ring, __le64 qw2,
+				__le64 qw3, struct sk_buff *skb)
+{
+	u32 tstamp;
+	u64 ns;
+
+	/* Skip processing if timestamps aren't enabled */
+	if (!(rx_ring->flags & IAVF_TXRX_FLAGS_HW_TSTAMP))
+		return;
+
+	/* Check if this Rx descriptor has a valid timestamp */
+	if (!le64_get_bits(qw2, IAVF_PTP_40B_TSTAMP_VALID))
+		return;
+
+	/* the ts_low field only contains the valid bit and sub-nanosecond
+	 * precision, so we don't need to extract it.
+	 */
+	tstamp = le64_get_bits(qw3, IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M);
+
+	ns = iavf_ptp_extend_32b_timestamp(rx_ring->ptp->cached_phc_time,
+					   tstamp);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ns),
+	};
+}
+
 /**
  * iavf_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rx_ring: rx descriptor ring packet is being transacted on
@@ -1097,11 +1137,14 @@ static void iavf_process_skb_fields(const struct iavf_ring *rx_ring,
 	struct libeth_rx_pt decoded_pt;
 	__le64 qw0 = rx_desc->qw0;
 	__le64 qw1 = rx_desc->qw1;
+	__le64 qw2 = rx_desc->qw2;
+	__le64 qw3 = rx_desc->qw3;
 
 	decoded_pt = libie_rx_pt_parse(ptype);
 
 	if (flex) {
 		iavf_flex_rx_hash(rx_ring, qw1, skb, decoded_pt);
+		iavf_flex_rx_tstamp(rx_ring, qw2, qw3, skb);
 		csum_bits = iavf_flex_rx_csum(rx_ring->vsi, le64_to_cpu(qw1),
 					      decoded_pt);
 	} else {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index e62a8a0067ea0..f9e1319620f45 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -285,6 +285,7 @@ struct iavf_rx_desc {
 /* L2 Tag 2 Presence */
 #define IAVF_RXD_FLEX_L2TAG2P_M			BIT(11)
 	aligned_le64 qw3;
+#define IAVF_RXD_FLEX_QW3_TSTAMP_HIGH_M		GENMASK_ULL(63, 32)
 } __aligned(4 * sizeof(__le64));
 static_assert(sizeof(struct iavf_rx_desc) == 32);
 

From c158647c107358bf1be579f98e4bb705c1953292 Mon Sep 17 00:00:00 2001
From: Komal Bajaj <quic_kbajaj@quicinc.com>
Date: Tue, 19 Nov 2024 12:16:08 +0530
Subject: [PATCH 0553/2753] EDAC/qcom: Correct interrupt enable register
 configuration

The previous implementation incorrectly configured the cmn_interrupt_2_enable
register for interrupt handling. Using cmn_interrupt_2_enable to configure
Tag, Data RAM ECC interrupts would lead to issues like double handling of the
interrupts (EL1 and EL3) as cmn_interrupt_2_enable is meant to be configured
for interrupts which needs to be handled by EL3.

EL1 LLCC EDAC driver needs to use cmn_interrupt_0_enable register to configure
Tag, Data RAM ECC interrupts instead of cmn_interrupt_2_enable.

Fixes: 27450653f1db ("drivers: edac: Add EDAC driver support for QCOM SoCs")
Signed-off-by: Komal Bajaj <quic_kbajaj@quicinc.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Cc: <stable@kernel.org>
Link: https://lore.kernel.org/r/20241119064608.12326-1-quic_kbajaj@quicinc.com
---
 drivers/edac/qcom_edac.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/edac/qcom_edac.c b/drivers/edac/qcom_edac.c
index 04c42c83a2bad..f3da9385ca0d8 100644
--- a/drivers/edac/qcom_edac.c
+++ b/drivers/edac/qcom_edac.c
@@ -95,7 +95,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	 * Configure interrupt enable registers such that Tag, Data RAM related
 	 * interrupts are propagated to interrupt controller for servicing
 	 */
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 TRP0_INTERRUPT_ENABLE,
 				 TRP0_INTERRUPT_ENABLE);
 	if (ret)
@@ -113,7 +113,7 @@ static int qcom_llcc_core_setup(struct llcc_drv_data *drv, struct regmap *llcc_b
 	if (ret)
 		return ret;
 
-	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_2_enable,
+	ret = regmap_update_bits(llcc_bcast_regmap, drv->edac_reg_offset->cmn_interrupt_0_enable,
 				 DRP0_INTERRUPT_ENABLE,
 				 DRP0_INTERRUPT_ENABLE);
 	if (ret)

From fb8179ce2996bffaa36a04e2b6262843b01b7565 Mon Sep 17 00:00:00 2001
From: Rob Herring <robh@kernel.org>
Date: Mon, 4 Nov 2024 13:03:13 -0600
Subject: [PATCH 0554/2753] riscv: cacheinfo: Use of_property_present() for
 non-boolean properties
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The use of of_property_read_bool() for non-boolean properties is
deprecated in favor of of_property_present() when testing for property
presence.

Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Clément Léger <cleger@rivosinc.com>
Cc: stable@vger.kernel.org
Fixes: 76d2a0493a17 ("RISC-V: Init and Halt Code")
Link: https://lore.kernel.org/r/20241104190314.270095-1-robh@kernel.org
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cacheinfo.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/riscv/kernel/cacheinfo.c b/arch/riscv/kernel/cacheinfo.c
index 2d40736fc37ce..26b085dbdd073 100644
--- a/arch/riscv/kernel/cacheinfo.c
+++ b/arch/riscv/kernel/cacheinfo.c
@@ -108,11 +108,11 @@ int populate_cache_leaves(unsigned int cpu)
 	if (!np)
 		return -ENOENT;
 
-	if (of_property_read_bool(np, "cache-size"))
+	if (of_property_present(np, "cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-	if (of_property_read_bool(np, "i-cache-size"))
+	if (of_property_present(np, "i-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-	if (of_property_read_bool(np, "d-cache-size"))
+	if (of_property_present(np, "d-cache-size"))
 		ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 
 	prev = np;
@@ -125,11 +125,11 @@ int populate_cache_leaves(unsigned int cpu)
 			break;
 		if (level <= levels)
 			break;
-		if (of_property_read_bool(np, "cache-size"))
+		if (of_property_present(np, "cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_UNIFIED, level);
-		if (of_property_read_bool(np, "i-cache-size"))
+		if (of_property_present(np, "i-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_INST, level);
-		if (of_property_read_bool(np, "d-cache-size"))
+		if (of_property_present(np, "d-cache-size"))
 			ci_leaf_init(this_leaf++, CACHE_TYPE_DATA, level);
 		levels = level;
 	}

From c6ec1e1b078d8e2ecd075e46db6197a14930a3fc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cl=C3=A9ment=20L=C3=A9ger?= <cleger@rivosinc.com>
Date: Mon, 10 Feb 2025 16:56:14 +0100
Subject: [PATCH 0555/2753] riscv: cpufeature: use bitmap_equal() instead of
 memcmp()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Comparison of bitmaps should be done using bitmap_equal(), not memcmp(),
use the former one to compare isa bitmaps.

Signed-off-by: Clément Léger <cleger@rivosinc.com>
Fixes: 625034abd52a8c ("riscv: add ISA extensions validation callback")
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250210155615.1545738-1-cleger@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/cpufeature.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c
index c6ba750536c32..40ac72e407b68 100644
--- a/arch/riscv/kernel/cpufeature.c
+++ b/arch/riscv/kernel/cpufeature.c
@@ -479,7 +479,7 @@ static void __init riscv_resolve_isa(unsigned long *source_isa,
 			if (bit < RISCV_ISA_EXT_BASE)
 				*this_hwcap |= isa2hwcap[bit];
 		}
-	} while (loop && memcmp(prev_resolved_isa, resolved_isa, sizeof(prev_resolved_isa)));
+	} while (loop && !bitmap_equal(prev_resolved_isa, resolved_isa, RISCV_ISA_EXT_MAX));
 }
 
 static void __init match_isa_ext(const char *name, const char *name_end, unsigned long *bitmap)

From 1898300abf3508bca152e65b36cce5bf93d7e63e Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Thu, 30 Jan 2025 10:25:38 +0100
Subject: [PATCH 0556/2753] riscv/atomic: Do proper sign extension also for
 unsigned in arch_cmpxchg

Sign extend also an unsigned compare value to match what lr.w is doing.
Otherwise try_cmpxchg may spuriously return true when used on a u32 value
that has the sign bit set, as it happens often in inode_set_ctime_current.

Do this in three conversion steps.  The first conversion to long is needed
to avoid a -Wpointer-to-int-cast warning when arch_cmpxchg is used with a
pointer type.  Then convert to int and back to long to always sign extend
the 32-bit value to 64-bit.

Fixes: 6c58f25e6938 ("riscv/atomic: Fix sign extension for RV64I")
Signed-off-by: Andreas Schwab <schwab@suse.de>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Tested-by: Xi Ruoyao <xry111@xry111.site>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/mvmed0k4prh.fsf@suse.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/cmpxchg.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4cadc56220fea..427c41dde6431 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -231,7 +231,7 @@
 		__arch_cmpxchg(".w", ".w" sc_sfx, ".w" cas_sfx,		\
 			       sc_prepend, sc_append,			\
 			       cas_prepend, cas_append,			\
-			       __ret, __ptr, (long), __old, __new);	\
+			       __ret, __ptr, (long)(int)(long), __old, __new);	\
 		break;							\
 	case 8:								\
 		__arch_cmpxchg(".d", ".d" sc_sfx, ".d" cas_sfx,		\

From 599c44cd21f4967774e0acf58f734009be4aea9a Mon Sep 17 00:00:00 2001
From: Andreas Schwab <schwab@suse.de>
Date: Mon, 3 Feb 2025 11:06:00 +0100
Subject: [PATCH 0557/2753] riscv/futex: sign extend compare value in atomic
 cmpxchg
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make sure the compare value in the lr/sc loop is sign extended to match
what lr.w does.  Fortunately, due to the compiler keeping the register
contents sign extended anyway the lack of the explicit extension didn't
result in wrong code so far, but this cannot be relied upon.

Fixes: b90edb33010b ("RISC-V: Add futex support.")
Signed-off-by: Andreas Schwab <schwab@suse.de>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/mvmfrkv2vhz.fsf@suse.de
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/include/asm/futex.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/include/asm/futex.h b/arch/riscv/include/asm/futex.h
index 72be100afa236..90c86b115e008 100644
--- a/arch/riscv/include/asm/futex.h
+++ b/arch/riscv/include/asm/futex.h
@@ -93,7 +93,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		_ASM_EXTABLE_UACCESS_ERR(1b, 3b, %[r])	\
 		_ASM_EXTABLE_UACCESS_ERR(2b, 3b, %[r])	\
 	: [r] "+r" (ret), [v] "=&r" (val), [u] "+m" (*uaddr), [t] "=&r" (tmp)
-	: [ov] "Jr" (oldval), [nv] "Jr" (newval)
+	: [ov] "Jr" ((long)(int)oldval), [nv] "Jr" (newval)
 	: "memory");
 	__disable_user_access();
 

From 713e788c0e07e185fd44dd581f74855ef149722f Mon Sep 17 00:00:00 2001
From: Stafford Horne <shorne@gmail.com>
Date: Tue, 14 Jan 2025 17:07:21 +0000
Subject: [PATCH 0558/2753] rseq/selftests: Fix riscv rseq_offset_deref_addv
 inline asm

When working on OpenRISC support for restartable sequences I noticed
and fixed these two issues with the riscv support bits.

 1 The 'inc' argument to RSEQ_ASM_OP_R_DEREF_ADDV was being implicitly
   passed to the macro.  Fix this by adding 'inc' to the list of macro
   arguments.
 2 The inline asm input constraints for 'inc' and 'off' use "er",  The
   riscv gcc port does not have an "e" constraint, this looks to be
   copied from the x86 port.  Fix this by just using an "r" constraint.

I have compile tested this only for riscv.  However, the same fixes I
use in the OpenRISC rseq selftests and everything passes with no issues.

Fixes: 171586a6ab66 ("selftests/rseq: riscv: Template memory ordering and percpu access mode")
Signed-off-by: Stafford Horne <shorne@gmail.com>
Tested-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Charlie Jenkins <charlie@rivosinc.com>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250114170721.3613280-1-shorne@gmail.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 tools/testing/selftests/rseq/rseq-riscv-bits.h | 6 +++---
 tools/testing/selftests/rseq/rseq-riscv.h      | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/rseq/rseq-riscv-bits.h b/tools/testing/selftests/rseq/rseq-riscv-bits.h
index de31a0143139b..f02f411d550d1 100644
--- a/tools/testing/selftests/rseq/rseq-riscv-bits.h
+++ b/tools/testing/selftests/rseq/rseq-riscv-bits.h
@@ -243,7 +243,7 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
 #ifdef RSEQ_COMPARE_TWICE
 				  RSEQ_ASM_CMP_CPU_ID(cpu_id, current_cpu_id, "%l[error1]")
 #endif
-				  RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, 3)
+				  RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, 3)
 				  RSEQ_INJECT_ASM(4)
 				  RSEQ_ASM_DEFINE_ABORT(4, abort)
 				  : /* gcc asm goto does not allow outputs */
@@ -251,8 +251,8 @@ int RSEQ_TEMPLATE_IDENTIFIER(rseq_offset_deref_addv)(intptr_t *ptr, off_t off, i
 				    [current_cpu_id]		"m" (rseq_get_abi()->RSEQ_TEMPLATE_CPU_ID_FIELD),
 				    [rseq_cs]			"m" (rseq_get_abi()->rseq_cs.arch.ptr),
 				    [ptr]			"r" (ptr),
-				    [off]			"er" (off),
-				    [inc]			"er" (inc)
+				    [off]			"r" (off),
+				    [inc]			"r" (inc)
 				    RSEQ_INJECT_INPUT
 				  : "memory", RSEQ_ASM_TMP_REG_1
 				    RSEQ_INJECT_CLOBBER
diff --git a/tools/testing/selftests/rseq/rseq-riscv.h b/tools/testing/selftests/rseq/rseq-riscv.h
index 37e598d0a365e..67d544aaa9a3b 100644
--- a/tools/testing/selftests/rseq/rseq-riscv.h
+++ b/tools/testing/selftests/rseq/rseq-riscv.h
@@ -158,7 +158,7 @@ do {									\
 	"bnez	" RSEQ_ASM_TMP_REG_1 ", 222b\n"				\
 	"333:\n"
 
-#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, post_commit_label)		\
+#define RSEQ_ASM_OP_R_DEREF_ADDV(ptr, off, inc, post_commit_label)	\
 	"mv	" RSEQ_ASM_TMP_REG_1 ", %[" __rseq_str(ptr) "]\n"	\
 	RSEQ_ASM_OP_R_ADD(off)						\
 	REG_L	  RSEQ_ASM_TMP_REG_1 ", 0(" RSEQ_ASM_TMP_REG_1 ")\n"	\

From aa49bc2ca8524186ceb0811c23a7f00c3dea6987 Mon Sep 17 00:00:00 2001
From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Date: Fri, 20 Dec 2024 16:39:23 +0800
Subject: [PATCH 0559/2753] riscv: signal: fix signal frame size

The signal context of certain RISC-V extensions will be appended after
struct __riscv_extra_ext_header, which already includes an empty context
header. Therefore, there is no need to preserve a separate hdr for the
END of signal context.

Fixes: 8ee0b41898fa ("riscv: signal: Add sigcontext save/restore for vector")
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Zong Li <zong.li@sifive.com>
Reviewed-by: Andy Chiu <AndybnAC@gmail.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241220083926.19453-2-yongxuan.wang@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/signal.c | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/arch/riscv/kernel/signal.c b/arch/riscv/kernel/signal.c
index 94e905eea1dee..08378fea3a111 100644
--- a/arch/riscv/kernel/signal.c
+++ b/arch/riscv/kernel/signal.c
@@ -215,12 +215,6 @@ static size_t get_rt_frame_size(bool cal_all)
 		if (cal_all || riscv_v_vstate_query(task_pt_regs(current)))
 			total_context_size += riscv_v_sc_size;
 	}
-	/*
-	 * Preserved a __riscv_ctx_hdr for END signal context header if an
-	 * extension uses __riscv_extra_ext_header
-	 */
-	if (total_context_size)
-		total_context_size += sizeof(struct __riscv_ctx_hdr);
 
 	frame_size += total_context_size;
 

From 564fc8eb6f78e01292ff10801f318feae6153fdd Mon Sep 17 00:00:00 2001
From: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Date: Fri, 20 Dec 2024 16:39:24 +0800
Subject: [PATCH 0560/2753] riscv: signal: fix signal_minsigstksz

The init_rt_signal_env() funciton is called before the alternative patch
is applied, so using the alternative-related API to check the availability
of an extension within this function doesn't have the intended effect.
This patch reorders the init_rt_signal_env() and apply_boot_alternatives()
to get the correct signal_minsigstksz.

Fixes: e92f469b0771 ("riscv: signal: Report signal frame size to userspace via auxv")
Signed-off-by: Yong-Xuan Wang <yongxuan.wang@sifive.com>
Reviewed-by: Zong Li <zong.li@sifive.com>
Reviewed-by: Andy Chiu <andybnac@gmail.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241220083926.19453-3-yongxuan.wang@sifive.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/kernel/setup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index f1793630fc518..4fe45daa6281e 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -322,8 +322,8 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_init_cbo_blocksizes();
 	riscv_fill_hwcap();
-	init_rt_signal_env();
 	apply_boot_alternatives();
+	init_rt_signal_env();
 
 	if (IS_ENABLED(CONFIG_RISCV_ISA_ZICBOM) &&
 	    riscv_isa_extension_available(NULL, ZICBOM))

From 245aece3750d3692ae7a44516c1096936bded7ab Mon Sep 17 00:00:00 2001
From: Alexandre Ghiti <alexghiti@rivosinc.com>
Date: Thu, 12 Dec 2024 14:11:34 +0100
Subject: [PATCH 0561/2753] MAINTAINERS: Add myself as a riscv reviewer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The goal is for me to get a kernel.org account and then send pull requests
in order to relieve some pressure from Palmer and make our workflow
smoother.

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
Enthusiastically-Supported-by: Björn Töpel <bjorn@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20241212131134.288819-1-alexghiti@rivosinc.com
Signed-off-by: Palmer Dabbelt <palmer@rivosinc.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa0654..ebc3e39dbcaab 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -20280,6 +20280,7 @@ RISC-V ARCHITECTURE
 M:	Paul Walmsley <paul.walmsley@sifive.com>
 M:	Palmer Dabbelt <palmer@dabbelt.com>
 M:	Albert Ou <aou@eecs.berkeley.edu>
+R:	Alexandre Ghiti <alex@ghiti.fr>
 L:	linux-riscv@lists.infradead.org
 S:	Supported
 Q:	https://patchwork.kernel.org/project/linux-riscv/list/

From 54568a84c95bdea20227cf48d41f198d083e78dd Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:24:15 +0000
Subject: [PATCH 0562/2753] net: introduce EXPORT_IPV6_MOD() and
 EXPORT_IPV6_MOD_GPL()

We have many EXPORT_SYMBOL(x) in networking tree because IPv6
can be built as a module.

CONFIG_IPV6=y is becoming the norm.

Define a EXPORT_IPV6_MOD(x) which only exports x
for modular IPv6.

Same principle applies to EXPORT_IPV6_MOD_GPL()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250212132418.1524422-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/net/ip.h b/include/net/ip.h
index ba7b43447775e..305eccdf4ff76 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -673,6 +673,14 @@ static inline void ip_ipgre_mc_map(__be32 naddr, const unsigned char *broadcast,
 		memcpy(buf, &naddr, sizeof(naddr));
 }
 
+#if IS_MODULE(CONFIG_IPV6)
+#define EXPORT_IPV6_MOD(X) EXPORT_SYMBOL(X)
+#define EXPORT_IPV6_MOD_GPL(X) EXPORT_SYMBOL_GPL(X)
+#else
+#define EXPORT_IPV6_MOD(X)
+#define EXPORT_IPV6_MOD_GPL(X)
+#endif
+
 #if IS_ENABLED(CONFIG_IPV6)
 #include <linux/ipv6.h>
 #endif

From 95a3c96c746008a2abed2882e0da48a78f941c49 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:24:16 +0000
Subject: [PATCH 0563/2753] inetpeer: use EXPORT_IPV6_MOD[_GPL]()

Use EXPORT_IPV6_MOD[_GPL]() for symbols that do not need to
to be exported unless CONFIG_IPV6=m

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250212132418.1524422-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inetpeer.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index b8b23a77ceb4f..7b1e0a2d69066 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -60,7 +60,7 @@ void inet_peer_base_init(struct inet_peer_base *bp)
 	seqlock_init(&bp->lock);
 	bp->total = 0;
 }
-EXPORT_SYMBOL_GPL(inet_peer_base_init);
+EXPORT_IPV6_MOD_GPL(inet_peer_base_init);
 
 #define PEER_MAX_GC 32
 
@@ -218,7 +218,7 @@ struct inet_peer *inet_getpeer(struct inet_peer_base *base,
 
 	return p;
 }
-EXPORT_SYMBOL_GPL(inet_getpeer);
+EXPORT_IPV6_MOD_GPL(inet_getpeer);
 
 void inet_putpeer(struct inet_peer *p)
 {
@@ -269,7 +269,7 @@ bool inet_peer_xrlim_allow(struct inet_peer *peer, int timeout)
 		WRITE_ONCE(peer->rate_tokens, token);
 	return rc;
 }
-EXPORT_SYMBOL(inet_peer_xrlim_allow);
+EXPORT_IPV6_MOD(inet_peer_xrlim_allow);
 
 void inetpeer_invalidate_tree(struct inet_peer_base *base)
 {
@@ -286,4 +286,4 @@ void inetpeer_invalidate_tree(struct inet_peer_base *base)
 
 	base->total = 0;
 }
-EXPORT_SYMBOL(inetpeer_invalidate_tree);
+EXPORT_IPV6_MOD(inetpeer_invalidate_tree);

From 6dc4c2526f6d11f36c4e26d0231b345eabab584c Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:24:17 +0000
Subject: [PATCH 0564/2753] tcp: use EXPORT_IPV6_MOD[_GPL]()

Use EXPORT_IPV6_MOD[_GPL]() for symbols that don't need
to be exported unless CONFIG_IPV6=m

tcp_hashinfo and tcp_openreq_init_rwin() are no longer
used from any module anyway.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250212132418.1524422-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/secure_seq.c    |  2 +-
 net/ipv4/syncookies.c    |  8 +++----
 net/ipv4/tcp.c           | 44 ++++++++++++++++++-------------------
 net/ipv4/tcp_fastopen.c  |  2 +-
 net/ipv4/tcp_input.c     | 14 ++++++------
 net/ipv4/tcp_ipv4.c      | 47 ++++++++++++++++++++--------------------
 net/ipv4/tcp_minisocks.c | 11 +++++-----
 net/ipv4/tcp_output.c    | 12 +++++-----
 net/ipv4/tcp_timer.c     |  4 ++--
 9 files changed, 71 insertions(+), 73 deletions(-)

diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index b0ff6153be623..568779d5a0efa 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -71,7 +71,7 @@ u32 secure_tcpv6_ts_off(const struct net *net,
 	return siphash(&combined, offsetofend(typeof(combined), daddr),
 		       &ts_secret);
 }
-EXPORT_SYMBOL(secure_tcpv6_ts_off);
+EXPORT_IPV6_MOD(secure_tcpv6_ts_off);
 
 u32 secure_tcpv6_seq(const __be32 *saddr, const __be32 *daddr,
 		     __be16 sport, __be16 dport)
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 1948d15f1f281..26816b876dd8b 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -222,7 +222,7 @@ struct sock *tcp_get_cookie_sock(struct sock *sk, struct sk_buff *skb,
 
 	return NULL;
 }
-EXPORT_SYMBOL(tcp_get_cookie_sock);
+EXPORT_IPV6_MOD(tcp_get_cookie_sock);
 
 /*
  * when syncookies are in effect and tcp timestamps are enabled we stored
@@ -259,7 +259,7 @@ bool cookie_timestamp_decode(const struct net *net,
 
 	return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0;
 }
-EXPORT_SYMBOL(cookie_timestamp_decode);
+EXPORT_IPV6_MOD(cookie_timestamp_decode);
 
 static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 				 struct request_sock *req)
@@ -310,7 +310,7 @@ struct request_sock *cookie_bpf_check(struct sock *sk, struct sk_buff *skb)
 
 	return req;
 }
-EXPORT_SYMBOL_GPL(cookie_bpf_check);
+EXPORT_IPV6_MOD_GPL(cookie_bpf_check);
 #endif
 
 struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
@@ -351,7 +351,7 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
 
 	return req;
 }
-EXPORT_SYMBOL_GPL(cookie_tcp_reqsk_alloc);
+EXPORT_IPV6_MOD_GPL(cookie_tcp_reqsk_alloc);
 
 static struct request_sock *cookie_tcp_check(struct net *net, struct sock *sk,
 					     struct sk_buff *skb)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 992d5c9b2487c..5d78ab3b416e2 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -300,10 +300,10 @@ DEFINE_PER_CPU(u32, tcp_tw_isn);
 EXPORT_PER_CPU_SYMBOL_GPL(tcp_tw_isn);
 
 long sysctl_tcp_mem[3] __read_mostly;
-EXPORT_SYMBOL(sysctl_tcp_mem);
+EXPORT_IPV6_MOD(sysctl_tcp_mem);
 
 atomic_long_t tcp_memory_allocated ____cacheline_aligned_in_smp;	/* Current allocated memory. */
-EXPORT_SYMBOL(tcp_memory_allocated);
+EXPORT_IPV6_MOD(tcp_memory_allocated);
 DEFINE_PER_CPU(int, tcp_memory_per_cpu_fw_alloc);
 EXPORT_PER_CPU_SYMBOL_GPL(tcp_memory_per_cpu_fw_alloc);
 
@@ -316,7 +316,7 @@ EXPORT_SYMBOL(tcp_have_smc);
  * Current number of TCP sockets.
  */
 struct percpu_counter tcp_sockets_allocated ____cacheline_aligned_in_smp;
-EXPORT_SYMBOL(tcp_sockets_allocated);
+EXPORT_IPV6_MOD(tcp_sockets_allocated);
 
 /*
  * TCP splice context
@@ -349,7 +349,7 @@ void tcp_enter_memory_pressure(struct sock *sk)
 	if (!cmpxchg(&tcp_memory_pressure, 0, val))
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURES);
 }
-EXPORT_SYMBOL_GPL(tcp_enter_memory_pressure);
+EXPORT_IPV6_MOD_GPL(tcp_enter_memory_pressure);
 
 void tcp_leave_memory_pressure(struct sock *sk)
 {
@@ -362,7 +362,7 @@ void tcp_leave_memory_pressure(struct sock *sk)
 		NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPMEMORYPRESSURESCHRONO,
 			      jiffies_to_msecs(jiffies - val));
 }
-EXPORT_SYMBOL_GPL(tcp_leave_memory_pressure);
+EXPORT_IPV6_MOD_GPL(tcp_leave_memory_pressure);
 
 /* Convert seconds to retransmits based on initial and max timeout */
 static u8 secs_to_retrans(int seconds, int timeout, int rto_max)
@@ -479,7 +479,7 @@ void tcp_init_sock(struct sock *sk)
 	sk_sockets_allocated_inc(sk);
 	xa_init_flags(&sk->sk_user_frags, XA_FLAGS_ALLOC1);
 }
-EXPORT_SYMBOL(tcp_init_sock);
+EXPORT_IPV6_MOD(tcp_init_sock);
 
 static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
 {
@@ -664,7 +664,7 @@ int tcp_ioctl(struct sock *sk, int cmd, int *karg)
 	*karg = answ;
 	return 0;
 }
-EXPORT_SYMBOL(tcp_ioctl);
+EXPORT_IPV6_MOD(tcp_ioctl);
 
 void tcp_mark_push(struct tcp_sock *tp, struct sk_buff *skb)
 {
@@ -880,7 +880,7 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 
 	return ret;
 }
-EXPORT_SYMBOL(tcp_splice_read);
+EXPORT_IPV6_MOD(tcp_splice_read);
 
 struct sk_buff *tcp_stream_alloc_skb(struct sock *sk, gfp_t gfp,
 				     bool force_schedule)
@@ -1380,7 +1380,7 @@ void tcp_splice_eof(struct socket *sock)
 	tcp_push(sk, 0, mss_now, tp->nonagle, size_goal);
 	release_sock(sk);
 }
-EXPORT_SYMBOL_GPL(tcp_splice_eof);
+EXPORT_IPV6_MOD_GPL(tcp_splice_eof);
 
 /*
  *	Handle reading urgent data. BSD has very simple semantics for
@@ -1671,7 +1671,7 @@ int tcp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 	}
 	return copied;
 }
-EXPORT_SYMBOL(tcp_read_skb);
+EXPORT_IPV6_MOD(tcp_read_skb);
 
 void tcp_read_done(struct sock *sk, size_t len)
 {
@@ -1716,7 +1716,7 @@ int tcp_peek_len(struct socket *sock)
 {
 	return tcp_inq(sock->sk);
 }
-EXPORT_SYMBOL(tcp_peek_len);
+EXPORT_IPV6_MOD(tcp_peek_len);
 
 /* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */
 int tcp_set_rcvlowat(struct sock *sk, int val)
@@ -1743,7 +1743,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val)
 	}
 	return 0;
 }
-EXPORT_SYMBOL(tcp_set_rcvlowat);
+EXPORT_IPV6_MOD(tcp_set_rcvlowat);
 
 void tcp_update_recv_tstamps(struct sk_buff *skb,
 			     struct scm_timestamping_internal *tss)
@@ -1776,7 +1776,7 @@ int tcp_mmap(struct file *file, struct socket *sock,
 	vma->vm_ops = &tcp_vm_ops;
 	return 0;
 }
-EXPORT_SYMBOL(tcp_mmap);
+EXPORT_IPV6_MOD(tcp_mmap);
 
 static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 				       u32 *offset_frag)
@@ -2873,7 +2873,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 	}
 	return ret;
 }
-EXPORT_SYMBOL(tcp_recvmsg);
+EXPORT_IPV6_MOD(tcp_recvmsg);
 
 void tcp_set_state(struct sock *sk, int state)
 {
@@ -3003,7 +3003,7 @@ void tcp_shutdown(struct sock *sk, int how)
 			tcp_send_fin(sk);
 	}
 }
-EXPORT_SYMBOL(tcp_shutdown);
+EXPORT_IPV6_MOD(tcp_shutdown);
 
 int tcp_orphan_count_sum(void)
 {
@@ -3502,7 +3502,7 @@ static int tcp_repair_options_est(struct sock *sk, sockptr_t optbuf,
 }
 
 DEFINE_STATIC_KEY_FALSE(tcp_tx_delay_enabled);
-EXPORT_SYMBOL(tcp_tx_delay_enabled);
+EXPORT_IPV6_MOD(tcp_tx_delay_enabled);
 
 static void tcp_enable_tx_delay(void)
 {
@@ -4045,7 +4045,7 @@ int tcp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 								optval, optlen);
 	return do_tcp_setsockopt(sk, level, optname, optval, optlen);
 }
-EXPORT_SYMBOL(tcp_setsockopt);
+EXPORT_IPV6_MOD(tcp_setsockopt);
 
 static void tcp_get_info_chrono_stats(const struct tcp_sock *tp,
 				      struct tcp_info *info)
@@ -4676,7 +4676,7 @@ bool tcp_bpf_bypass_getsockopt(int level, int optname)
 
 	return false;
 }
-EXPORT_SYMBOL(tcp_bpf_bypass_getsockopt);
+EXPORT_IPV6_MOD(tcp_bpf_bypass_getsockopt);
 
 int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 		   int __user *optlen)
@@ -4690,11 +4690,11 @@ int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval,
 	return do_tcp_getsockopt(sk, level, optname, USER_SOCKPTR(optval),
 				 USER_SOCKPTR(optlen));
 }
-EXPORT_SYMBOL(tcp_getsockopt);
+EXPORT_IPV6_MOD(tcp_getsockopt);
 
 #ifdef CONFIG_TCP_MD5SIG
 int tcp_md5_sigpool_id = -1;
-EXPORT_SYMBOL_GPL(tcp_md5_sigpool_id);
+EXPORT_IPV6_MOD_GPL(tcp_md5_sigpool_id);
 
 int tcp_md5_alloc_sigpool(void)
 {
@@ -4740,7 +4740,7 @@ int tcp_md5_hash_key(struct tcp_sigpool *hp,
 	 */
 	return data_race(crypto_ahash_update(hp->req));
 }
-EXPORT_SYMBOL(tcp_md5_hash_key);
+EXPORT_IPV6_MOD(tcp_md5_hash_key);
 
 /* Called with rcu_read_lock() */
 static enum skb_drop_reason
@@ -4860,7 +4860,7 @@ tcp_inbound_hash(struct sock *sk, const struct request_sock *req,
 	return tcp_inbound_md5_hash(sk, skb, saddr, daddr, family,
 				    l3index, md5_location);
 }
-EXPORT_SYMBOL_GPL(tcp_inbound_hash);
+EXPORT_IPV6_MOD_GPL(tcp_inbound_hash);
 
 void tcp_done(struct sock *sk)
 {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index e4c95238df58f..3a352c40a4865 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -468,7 +468,7 @@ bool tcp_fastopen_defer_connect(struct sock *sk, int *err)
 	}
 	return false;
 }
-EXPORT_SYMBOL(tcp_fastopen_defer_connect);
+EXPORT_IPV6_MOD(tcp_fastopen_defer_connect);
 
 /*
  * The following code block is to deal with middle box issues with TFO:
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4686783b70def..074406890552a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -630,7 +630,7 @@ void tcp_initialize_rcv_mss(struct sock *sk)
 
 	inet_csk(sk)->icsk_ack.rcv_mss = hint;
 }
-EXPORT_SYMBOL(tcp_initialize_rcv_mss);
+EXPORT_IPV6_MOD(tcp_initialize_rcv_mss);
 
 /* Receiver "autotuning" code.
  *
@@ -2891,7 +2891,7 @@ void tcp_simple_retransmit(struct sock *sk)
 	 */
 	tcp_non_congestion_loss_retransmit(sk);
 }
-EXPORT_SYMBOL(tcp_simple_retransmit);
+EXPORT_IPV6_MOD(tcp_simple_retransmit);
 
 void tcp_enter_recovery(struct sock *sk, bool ece_ack)
 {
@@ -4521,7 +4521,7 @@ void tcp_done_with_error(struct sock *sk, int err)
 	if (!sock_flag(sk, SOCK_DEAD))
 		sk_error_report(sk);
 }
-EXPORT_SYMBOL(tcp_done_with_error);
+EXPORT_IPV6_MOD(tcp_done_with_error);
 
 /* When we get a reset we do this. */
 void tcp_reset(struct sock *sk, struct sk_buff *skb)
@@ -6291,7 +6291,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 discard:
 	tcp_drop_reason(sk, skb, reason);
 }
-EXPORT_SYMBOL(tcp_rcv_established);
+EXPORT_IPV6_MOD(tcp_rcv_established);
 
 void tcp_init_transfer(struct sock *sk, int bpf_op, struct sk_buff *skb)
 {
@@ -7004,7 +7004,7 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	__kfree_skb(skb);
 	return 0;
 }
-EXPORT_SYMBOL(tcp_rcv_state_process);
+EXPORT_IPV6_MOD(tcp_rcv_state_process);
 
 static inline void pr_drop_req(struct request_sock *req, __u16 port, int family)
 {
@@ -7186,7 +7186,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
 
 	return mss;
 }
-EXPORT_SYMBOL_GPL(tcp_get_syncookie_mss);
+EXPORT_IPV6_MOD_GPL(tcp_get_syncookie_mss);
 
 int tcp_conn_request(struct request_sock_ops *rsk_ops,
 		     const struct tcp_request_sock_ops *af_ops,
@@ -7367,4 +7367,4 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
 	tcp_listendrop(sk);
 	return 0;
 }
-EXPORT_SYMBOL(tcp_conn_request);
+EXPORT_IPV6_MOD(tcp_conn_request);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d1fd2128ac6cc..6245e24fcbf3f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -92,7 +92,6 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 #endif
 
 struct inet_hashinfo tcp_hashinfo;
-EXPORT_SYMBOL(tcp_hashinfo);
 
 static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
 	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
@@ -199,7 +198,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(tcp_twsk_unique);
+EXPORT_IPV6_MOD_GPL(tcp_twsk_unique);
 
 static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr,
 			      int addr_len)
@@ -359,7 +358,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	inet->inet_dport = 0;
 	return err;
 }
-EXPORT_SYMBOL(tcp_v4_connect);
+EXPORT_IPV6_MOD(tcp_v4_connect);
 
 /*
  * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191.
@@ -400,7 +399,7 @@ void tcp_v4_mtu_reduced(struct sock *sk)
 		tcp_simple_retransmit(sk);
 	} /* else let the usual retransmit timer handle it */
 }
-EXPORT_SYMBOL(tcp_v4_mtu_reduced);
+EXPORT_IPV6_MOD(tcp_v4_mtu_reduced);
 
 static void do_redirect(struct sk_buff *skb, struct sock *sk)
 {
@@ -434,7 +433,7 @@ void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 	}
 	reqsk_put(req);
 }
-EXPORT_SYMBOL(tcp_req_err);
+EXPORT_IPV6_MOD(tcp_req_err);
 
 /* TCP-LD (RFC 6069) logic */
 void tcp_ld_RTO_revert(struct sock *sk, u32 seq)
@@ -473,7 +472,7 @@ void tcp_ld_RTO_revert(struct sock *sk, u32 seq)
 		tcp_retransmit_timer(sk);
 	}
 }
-EXPORT_SYMBOL(tcp_ld_RTO_revert);
+EXPORT_IPV6_MOD(tcp_ld_RTO_revert);
 
 /*
  * This routine is called by the ICMP module when it gets some
@@ -675,7 +674,7 @@ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb)
 
 	__tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr);
 }
-EXPORT_SYMBOL(tcp_v4_send_check);
+EXPORT_IPV6_MOD(tcp_v4_send_check);
 
 #define REPLY_OPTIONS_LEN      (MAX_TCP_OPTION_SPACE / sizeof(__be32))
 
@@ -1230,7 +1229,7 @@ static void tcp_v4_reqsk_destructor(struct request_sock *req)
  */
 
 DEFINE_STATIC_KEY_DEFERRED_FALSE(tcp_md5_needed, HZ);
-EXPORT_SYMBOL(tcp_md5_needed);
+EXPORT_IPV6_MOD(tcp_md5_needed);
 
 static bool better_md5_match(struct tcp_md5sig_key *old, struct tcp_md5sig_key *new)
 {
@@ -1289,7 +1288,7 @@ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, int l3index,
 	}
 	return best_match;
 }
-EXPORT_SYMBOL(__tcp_md5_do_lookup);
+EXPORT_IPV6_MOD(__tcp_md5_do_lookup);
 
 static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk,
 						      const union tcp_md5_addr *addr,
@@ -1336,7 +1335,7 @@ struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk,
 	addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr;
 	return tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
 }
-EXPORT_SYMBOL(tcp_v4_md5_lookup);
+EXPORT_IPV6_MOD(tcp_v4_md5_lookup);
 
 static int tcp_md5sig_info_add(struct sock *sk, gfp_t gfp)
 {
@@ -1432,7 +1431,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
 	return __tcp_md5_do_add(sk, addr, family, prefixlen, l3index, flags,
 				newkey, newkeylen, GFP_KERNEL);
 }
-EXPORT_SYMBOL(tcp_md5_do_add);
+EXPORT_IPV6_MOD(tcp_md5_do_add);
 
 int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr,
 		     int family, u8 prefixlen, int l3index,
@@ -1464,7 +1463,7 @@ int tcp_md5_key_copy(struct sock *sk, const union tcp_md5_addr *addr,
 				key->flags, key->key, key->keylen,
 				sk_gfp_mask(sk, GFP_ATOMIC));
 }
-EXPORT_SYMBOL(tcp_md5_key_copy);
+EXPORT_IPV6_MOD(tcp_md5_key_copy);
 
 int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
 		   u8 prefixlen, int l3index, u8 flags)
@@ -1479,7 +1478,7 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family,
 	kfree_rcu(key, rcu);
 	return 0;
 }
-EXPORT_SYMBOL(tcp_md5_do_del);
+EXPORT_IPV6_MOD(tcp_md5_do_del);
 
 void tcp_clear_md5_list(struct sock *sk)
 {
@@ -1658,7 +1657,7 @@ int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key,
 	memset(md5_hash, 0, 16);
 	return 1;
 }
-EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
+EXPORT_IPV6_MOD(tcp_v4_md5_hash_skb);
 
 #endif
 
@@ -1731,7 +1730,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
 	tcp_listendrop(sk);
 	return 0;
 }
-EXPORT_SYMBOL(tcp_v4_conn_request);
+EXPORT_IPV6_MOD(tcp_v4_conn_request);
 
 
 /*
@@ -1855,7 +1854,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	tcp_done(newsk);
 	goto exit;
 }
-EXPORT_SYMBOL(tcp_v4_syn_recv_sock);
+EXPORT_IPV6_MOD(tcp_v4_syn_recv_sock);
 
 static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb)
 {
@@ -2134,7 +2133,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	}
 	return false;
 }
-EXPORT_SYMBOL(tcp_add_backlog);
+EXPORT_IPV6_MOD(tcp_add_backlog);
 
 int tcp_filter(struct sock *sk, struct sk_buff *skb)
 {
@@ -2142,7 +2141,7 @@ int tcp_filter(struct sock *sk, struct sk_buff *skb)
 
 	return sk_filter_trim_cap(sk, skb, th->doff * 4);
 }
-EXPORT_SYMBOL(tcp_filter);
+EXPORT_IPV6_MOD(tcp_filter);
 
 static void tcp_v4_restore_cb(struct sk_buff *skb)
 {
@@ -2451,7 +2450,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
 		sk->sk_rx_dst_ifindex = skb->skb_iif;
 	}
 }
-EXPORT_SYMBOL(inet_sk_rx_dst_set);
+EXPORT_IPV6_MOD(inet_sk_rx_dst_set);
 
 const struct inet_connection_sock_af_ops ipv4_specific = {
 	.queue_xmit	   = ip_queue_xmit,
@@ -2467,7 +2466,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.sockaddr_len	   = sizeof(struct sockaddr_in),
 	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
-EXPORT_SYMBOL(ipv4_specific);
+EXPORT_IPV6_MOD(ipv4_specific);
 
 #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
 static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
@@ -2577,7 +2576,7 @@ void tcp_v4_destroy_sock(struct sock *sk)
 
 	sk_sockets_allocated_dec(sk);
 }
-EXPORT_SYMBOL(tcp_v4_destroy_sock);
+EXPORT_IPV6_MOD(tcp_v4_destroy_sock);
 
 #ifdef CONFIG_PROC_FS
 /* Proc filesystem TCP sock list dumping. */
@@ -2813,7 +2812,7 @@ void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
 	st->last_pos = *pos;
 	return rc;
 }
-EXPORT_SYMBOL(tcp_seq_start);
+EXPORT_IPV6_MOD(tcp_seq_start);
 
 void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
@@ -2844,7 +2843,7 @@ void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	st->last_pos = *pos;
 	return rc;
 }
-EXPORT_SYMBOL(tcp_seq_next);
+EXPORT_IPV6_MOD(tcp_seq_next);
 
 void tcp_seq_stop(struct seq_file *seq, void *v)
 {
@@ -2862,7 +2861,7 @@ void tcp_seq_stop(struct seq_file *seq, void *v)
 		break;
 	}
 }
-EXPORT_SYMBOL(tcp_seq_stop);
+EXPORT_IPV6_MOD(tcp_seq_stop);
 
 static void get_openreq4(const struct request_sock *req,
 			 struct seq_file *f, int i)
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0deb2ac85acf7..1eccc518b957e 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -264,7 +264,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
 	inet_twsk_put(tw);
 	return TCP_TW_SUCCESS;
 }
-EXPORT_SYMBOL(tcp_timewait_state_process);
+EXPORT_IPV6_MOD(tcp_timewait_state_process);
 
 static void tcp_time_wait_init(struct sock *sk, struct tcp_timewait_sock *tcptw)
 {
@@ -398,7 +398,7 @@ void tcp_twsk_destructor(struct sock *sk)
 #endif
 	tcp_ao_destroy_sock(sk, true);
 }
-EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
+EXPORT_IPV6_MOD_GPL(tcp_twsk_destructor);
 
 void tcp_twsk_purge(struct list_head *net_exit_list)
 {
@@ -457,7 +457,6 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 		rcv_wnd);
 	ireq->rcv_wscale = rcv_wscale;
 }
-EXPORT_SYMBOL(tcp_openreq_init_rwin);
 
 static void tcp_ecn_openreq_child(struct tcp_sock *tp,
 				  const struct request_sock *req)
@@ -492,7 +491,7 @@ void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
 
 	tcp_set_ca_state(sk, TCP_CA_Open);
 }
-EXPORT_SYMBOL_GPL(tcp_ca_openreq_child);
+EXPORT_IPV6_MOD_GPL(tcp_ca_openreq_child);
 
 static void smc_check_reset_syn_req(const struct tcp_sock *oldtp,
 				    struct request_sock *req,
@@ -909,7 +908,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	}
 	return NULL;
 }
-EXPORT_SYMBOL(tcp_check_req);
+EXPORT_IPV6_MOD(tcp_check_req);
 
 /*
  * Queue segment on the new socket if the new socket is active,
@@ -951,4 +950,4 @@ enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 	sock_put(child);
 	return reason;
 }
-EXPORT_SYMBOL(tcp_child_process);
+EXPORT_IPV6_MOD(tcp_child_process);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 464232a0d6379..b4b40f1354323 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -250,7 +250,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	WRITE_ONCE(*__window_clamp,
 		   min_t(__u32, U16_MAX << (*rcv_wscale), window_clamp));
 }
-EXPORT_SYMBOL(tcp_select_initial_window);
+EXPORT_IPV6_MOD(tcp_select_initial_window);
 
 /* Chose a new window to advertise, update state in tcp_sock for the
  * socket, and return result with RFC1323 scaling applied.  The return
@@ -1171,7 +1171,7 @@ void tcp_release_cb(struct sock *sk)
 	if ((flags & TCPF_ACK_DEFERRED) && inet_csk_ack_scheduled(sk))
 		tcp_send_ack(sk);
 }
-EXPORT_SYMBOL(tcp_release_cb);
+EXPORT_IPV6_MOD(tcp_release_cb);
 
 void __init tcp_tasklet_init(void)
 {
@@ -1783,7 +1783,7 @@ int tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	return __tcp_mtu_to_mss(sk, pmtu) -
 	       (tcp_sk(sk)->tcp_header_len - sizeof(struct tcphdr));
 }
-EXPORT_SYMBOL(tcp_mtu_to_mss);
+EXPORT_IPV6_MOD(tcp_mtu_to_mss);
 
 /* Inverse of above */
 int tcp_mss_to_mtu(struct sock *sk, int mss)
@@ -1856,7 +1856,7 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu)
 
 	return mss_now;
 }
-EXPORT_SYMBOL(tcp_sync_mss);
+EXPORT_IPV6_MOD(tcp_sync_mss);
 
 /* Compute the current effective MSS, taking SACKs and IP options,
  * and even PMTU discovery events into account.
@@ -3851,7 +3851,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
 
 	return skb;
 }
-EXPORT_SYMBOL(tcp_make_synack);
+EXPORT_IPV6_MOD(tcp_make_synack);
 
 static void tcp_ca_dst_init(struct sock *sk, const struct dst_entry *dst)
 {
@@ -4428,4 +4428,4 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)
 	}
 	return res;
 }
-EXPORT_SYMBOL(tcp_rtx_synack);
+EXPORT_IPV6_MOD(tcp_rtx_synack);
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c0e601e4f39c1..728bce01ccd3d 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -750,7 +750,7 @@ void tcp_syn_ack_timeout(const struct request_sock *req)
 
 	__NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS);
 }
-EXPORT_SYMBOL(tcp_syn_ack_timeout);
+EXPORT_IPV6_MOD(tcp_syn_ack_timeout);
 
 void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len)
 {
@@ -772,7 +772,7 @@ void tcp_set_keepalive(struct sock *sk, int val)
 	else if (!val)
 		tcp_delete_keepalive_timer(sk);
 }
-EXPORT_SYMBOL_GPL(tcp_set_keepalive);
+EXPORT_IPV6_MOD_GPL(tcp_set_keepalive);
 
 static void tcp_keepalive_timer(struct timer_list *t)
 {

From 2f8f4f22452a744dcd5cc865bbcfba40b3c13add Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:24:18 +0000
Subject: [PATCH 0565/2753] udp: use EXPORT_IPV6_MOD[_GPL]()

Use EXPORT_IPV6_MOD[_GPL]() for symbols that don't need
to be exported unless CONFIG_IPV6=m

udp_table is no longer used from any modules, and does not
need to be exported anyway.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250212132418.1524422-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 63 +++++++++++++++++++++++++-------------------------
 1 file changed, 31 insertions(+), 32 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index a9bb9ce5438ea..3485989cd4bde 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -121,13 +121,12 @@
 #endif
 
 struct udp_table udp_table __read_mostly;
-EXPORT_SYMBOL(udp_table);
 
 long sysctl_udp_mem[3] __read_mostly;
-EXPORT_SYMBOL(sysctl_udp_mem);
+EXPORT_IPV6_MOD(sysctl_udp_mem);
 
 atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp;
-EXPORT_SYMBOL(udp_memory_allocated);
+EXPORT_IPV6_MOD(udp_memory_allocated);
 DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc);
 EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc);
 
@@ -352,7 +351,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 fail:
 	return error;
 }
-EXPORT_SYMBOL(udp_lib_get_port);
+EXPORT_IPV6_MOD(udp_lib_get_port);
 
 int udp_v4_get_port(struct sock *sk, unsigned short snum)
 {
@@ -418,7 +417,7 @@ u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
 	return __inet_ehashfn(laddr, lport, faddr, fport,
 			      udp_ehash_secret + net_hash_mix(net));
 }
-EXPORT_SYMBOL(udp_ehashfn);
+EXPORT_IPV6_MOD(udp_ehashfn);
 
 /**
  * udp4_lib_lookup1() - Simplified lookup using primary hash (destination port)
@@ -653,7 +652,7 @@ void udp_lib_hash4(struct sock *sk, u16 hash)
 
 	spin_unlock_bh(&hslot->lock);
 }
-EXPORT_SYMBOL(udp_lib_hash4);
+EXPORT_IPV6_MOD(udp_lib_hash4);
 
 /* call with sock lock */
 void udp4_hash4(struct sock *sk)
@@ -669,7 +668,7 @@ void udp4_hash4(struct sock *sk)
 
 	udp_lib_hash4(sk, hash);
 }
-EXPORT_SYMBOL(udp4_hash4);
+EXPORT_IPV6_MOD(udp4_hash4);
 #endif /* CONFIG_BASE_SMALL */
 
 /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
@@ -809,11 +808,11 @@ static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk,
 }
 
 DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
-EXPORT_SYMBOL(udp_encap_needed_key);
+EXPORT_IPV6_MOD(udp_encap_needed_key);
 
 #if IS_ENABLED(CONFIG_IPV6)
 DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
-EXPORT_SYMBOL(udpv6_encap_needed_key);
+EXPORT_IPV6_MOD(udpv6_encap_needed_key);
 #endif
 
 void udp_encap_enable(void)
@@ -1041,7 +1040,7 @@ void udp_flush_pending_frames(struct sock *sk)
 		ip_flush_pending_frames(sk);
 	}
 }
-EXPORT_SYMBOL(udp_flush_pending_frames);
+EXPORT_IPV6_MOD(udp_flush_pending_frames);
 
 /**
  * 	udp4_hwcsum  -  handle outgoing HW checksumming
@@ -1229,7 +1228,7 @@ int udp_push_pending_frames(struct sock *sk)
 	WRITE_ONCE(up->pending, 0);
 	return err;
 }
-EXPORT_SYMBOL(udp_push_pending_frames);
+EXPORT_IPV6_MOD(udp_push_pending_frames);
 
 static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size)
 {
@@ -1266,7 +1265,7 @@ int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size)
 
 	return need_ip;
 }
-EXPORT_SYMBOL_GPL(udp_cmsg_send);
+EXPORT_IPV6_MOD_GPL(udp_cmsg_send);
 
 int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 {
@@ -1561,7 +1560,7 @@ void udp_splice_eof(struct socket *sock)
 		udp_push_pending_frames(sk);
 	release_sock(sk);
 }
-EXPORT_SYMBOL_GPL(udp_splice_eof);
+EXPORT_IPV6_MOD_GPL(udp_splice_eof);
 
 #define UDP_SKB_IS_STATELESS 0x80000000
 
@@ -1678,7 +1677,7 @@ void udp_skb_destructor(struct sock *sk, struct sk_buff *skb)
 	prefetch(&skb->data);
 	udp_rmem_release(sk, udp_skb_truesize(skb), 1, false);
 }
-EXPORT_SYMBOL(udp_skb_destructor);
+EXPORT_IPV6_MOD(udp_skb_destructor);
 
 /* as above, but the caller held the rx queue lock, too */
 static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb)
@@ -1785,7 +1784,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
 	busylock_release(busy);
 	return err;
 }
-EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
+EXPORT_IPV6_MOD_GPL(__udp_enqueue_schedule_skb);
 
 void udp_destruct_common(struct sock *sk)
 {
@@ -1801,7 +1800,7 @@ void udp_destruct_common(struct sock *sk)
 	}
 	udp_rmem_release(sk, total, 0, true);
 }
-EXPORT_SYMBOL_GPL(udp_destruct_common);
+EXPORT_IPV6_MOD_GPL(udp_destruct_common);
 
 static void udp_destruct_sock(struct sock *sk)
 {
@@ -1832,7 +1831,7 @@ void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
 		skb_release_head_state(skb);
 	__consume_stateless_skb(skb);
 }
-EXPORT_SYMBOL_GPL(skb_consume_udp);
+EXPORT_IPV6_MOD_GPL(skb_consume_udp);
 
 static struct sk_buff *__first_packet_length(struct sock *sk,
 					     struct sk_buff_head *rcvq,
@@ -1914,7 +1913,7 @@ int udp_ioctl(struct sock *sk, int cmd, int *karg)
 
 	return 0;
 }
-EXPORT_SYMBOL(udp_ioctl);
+EXPORT_IPV6_MOD(udp_ioctl);
 
 struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
 			       int *off, int *err)
@@ -2010,7 +2009,7 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 	WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk));
 	return recv_actor(sk, skb);
 }
-EXPORT_SYMBOL(udp_read_skb);
+EXPORT_IPV6_MOD(udp_read_skb);
 
 /*
  * 	This should be easy, if there is something there we
@@ -2137,7 +2136,7 @@ int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 
 	return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len);
 }
-EXPORT_SYMBOL(udp_pre_connect);
+EXPORT_IPV6_MOD(udp_pre_connect);
 
 static int udp_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 {
@@ -2186,7 +2185,7 @@ int udp_disconnect(struct sock *sk, int flags)
 	release_sock(sk);
 	return 0;
 }
-EXPORT_SYMBOL(udp_disconnect);
+EXPORT_IPV6_MOD(udp_disconnect);
 
 void udp_lib_unhash(struct sock *sk)
 {
@@ -2216,7 +2215,7 @@ void udp_lib_unhash(struct sock *sk)
 		spin_unlock_bh(&hslot->lock);
 	}
 }
-EXPORT_SYMBOL(udp_lib_unhash);
+EXPORT_IPV6_MOD(udp_lib_unhash);
 
 /*
  * inet_rcv_saddr was changed, we must rehash secondary hash
@@ -2280,7 +2279,7 @@ void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4)
 		}
 	}
 }
-EXPORT_SYMBOL(udp_lib_rehash);
+EXPORT_IPV6_MOD(udp_lib_rehash);
 
 void udp_v4_rehash(struct sock *sk)
 {
@@ -2485,7 +2484,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
 	}
 	return false;
 }
-EXPORT_SYMBOL(udp_sk_rx_dst_set);
+EXPORT_IPV6_MOD(udp_sk_rx_dst_set);
 
 /*
  *	Multicasts and broadcasts go to each listener.
@@ -3041,7 +3040,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 
 	return err;
 }
-EXPORT_SYMBOL(udp_lib_setsockopt);
+EXPORT_IPV6_MOD(udp_lib_setsockopt);
 
 int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen)
@@ -3112,7 +3111,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 		return -EFAULT;
 	return 0;
 }
-EXPORT_SYMBOL(udp_lib_getsockopt);
+EXPORT_IPV6_MOD(udp_lib_getsockopt);
 
 int udp_getsockopt(struct sock *sk, int level, int optname,
 		   char __user *optval, int __user *optlen)
@@ -3154,7 +3153,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait)
 	return mask;
 
 }
-EXPORT_SYMBOL(udp_poll);
+EXPORT_IPV6_MOD(udp_poll);
 
 int udp_abort(struct sock *sk, int err)
 {
@@ -3177,7 +3176,7 @@ int udp_abort(struct sock *sk, int err)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(udp_abort);
+EXPORT_IPV6_MOD_GPL(udp_abort);
 
 struct proto udp_prot = {
 	.name			= "UDP",
@@ -3311,7 +3310,7 @@ void *udp_seq_start(struct seq_file *seq, loff_t *pos)
 
 	return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
 }
-EXPORT_SYMBOL(udp_seq_start);
+EXPORT_IPV6_MOD(udp_seq_start);
 
 void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
@@ -3325,7 +3324,7 @@ void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	++*pos;
 	return sk;
 }
-EXPORT_SYMBOL(udp_seq_next);
+EXPORT_IPV6_MOD(udp_seq_next);
 
 void udp_seq_stop(struct seq_file *seq, void *v)
 {
@@ -3337,7 +3336,7 @@ void udp_seq_stop(struct seq_file *seq, void *v)
 	if (state->bucket <= udptable->mask)
 		spin_unlock_bh(&udptable->hash[state->bucket].lock);
 }
-EXPORT_SYMBOL(udp_seq_stop);
+EXPORT_IPV6_MOD(udp_seq_stop);
 
 /* ------------------------------------------------------------------------ */
 static void udp4_format_sock(struct sock *sp, struct seq_file *f,
@@ -3616,7 +3615,7 @@ const struct seq_operations udp_seq_ops = {
 	.stop		= udp_seq_stop,
 	.show		= udp4_seq_show,
 };
-EXPORT_SYMBOL(udp_seq_ops);
+EXPORT_IPV6_MOD(udp_seq_ops);
 
 static struct udp_seq_afinfo udp4_seq_afinfo = {
 	.family		= AF_INET,

From c6287e1a858e336cc202b484c6138a0fe252c6b3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 13 Feb 2025 16:34:20 +0100
Subject: [PATCH 0566/2753] net: airoha: Fix TSO support for header cloned skbs

For GSO packets, skb_cow_head() will reallocate the skb for TSO header
cloned skbs in airoha_dev_xmit(). For this reason, sinfo pointer can be
no more valid. Fix the issue relying on skb_shinfo() macro directly in
airoha_dev_xmit().

The problem exists since
commit 23020f049327 ("net: airoha: Introduce ethernet support for EN7581 SoC")
but it is not a user visible, since we can't currently enable TSO
for DSA user ports since we are missing to initialize net_device
vlan_features field.

Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250213-airoha-en7581-flowtable-offload-v4-1-b69ca16d74db@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/airoha_eth.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/mediatek/airoha_eth.c
index 09f448f291240..aa5f220ddbcf9 100644
--- a/drivers/net/ethernet/mediatek/airoha_eth.c
+++ b/drivers/net/ethernet/mediatek/airoha_eth.c
@@ -2556,11 +2556,10 @@ static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
 static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
-	struct skb_shared_info *sinfo = skb_shinfo(skb);
 	struct airoha_gdm_port *port = netdev_priv(dev);
+	u32 nr_frags = 1 + skb_shinfo(skb)->nr_frags;
 	u32 msg0, msg1, len = skb_headlen(skb);
 	struct airoha_qdma *qdma = port->qdma;
-	u32 nr_frags = 1 + sinfo->nr_frags;
 	struct netdev_queue *txq;
 	struct airoha_queue *q;
 	void *data = skb->data;
@@ -2583,8 +2582,9 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		if (skb_cow_head(skb, 0))
 			goto error;
 
-		if (sinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
-			__be16 csum = cpu_to_be16(sinfo->gso_size);
+		if (skb_shinfo(skb)->gso_type & (SKB_GSO_TCPV4 |
+						 SKB_GSO_TCPV6)) {
+			__be16 csum = cpu_to_be16(skb_shinfo(skb)->gso_size);
 
 			tcp_hdr(skb)->check = (__force __sum16)csum;
 			msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TSO_MASK, 1);
@@ -2613,7 +2613,7 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	for (i = 0; i < nr_frags; i++) {
 		struct airoha_qdma_desc *desc = &q->desc[index];
 		struct airoha_queue_entry *e = &q->entry[index];
-		skb_frag_t *frag = &sinfo->frags[i];
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		dma_addr_t addr;
 		u32 val;
 

From a045e40645dfa02a68c17ad8a3c92a8ef62375b0 Mon Sep 17 00:00:00 2001
From: Swathi K S <swathi.ks@samsung.com>
Date: Thu, 13 Feb 2025 09:45:59 +0530
Subject: [PATCH 0567/2753] net: stmmac: refactor clock management in EQoS
 driver

Refactor clock management in EQoS driver for code reuse and to avoid
redundancy. This way, only minimal changes are required when a new platform
is added.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Swathi K S <swathi.ks@samsung.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213041559.106111-1-swathi.ks@samsung.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-dwc-qos-eth.c        | 131 +++++-------------
 include/linux/stmmac.h                        |   2 +
 2 files changed, 34 insertions(+), 99 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index bd4eb187f8c64..1fadb8ba1d2ff 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -29,10 +29,8 @@ struct tegra_eqos {
 	void __iomem *regs;
 
 	struct reset_control *rst;
-	struct clk *clk_master;
 	struct clk *clk_slave;
 	struct clk *clk_tx;
-	struct clk *clk_rx;
 
 	struct gpio_desc *reset;
 };
@@ -123,49 +121,14 @@ static int dwc_qos_probe(struct platform_device *pdev,
 			 struct plat_stmmacenet_data *plat_dat,
 			 struct stmmac_resources *stmmac_res)
 {
-	int err;
-
-	plat_dat->stmmac_clk = devm_clk_get(&pdev->dev, "apb_pclk");
-	if (IS_ERR(plat_dat->stmmac_clk)) {
-		dev_err(&pdev->dev, "apb_pclk clock not found.\n");
-		return PTR_ERR(plat_dat->stmmac_clk);
-	}
-
-	err = clk_prepare_enable(plat_dat->stmmac_clk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable apb_pclk clock: %d\n",
-			err);
-		return err;
-	}
-
-	plat_dat->pclk = devm_clk_get(&pdev->dev, "phy_ref_clk");
-	if (IS_ERR(plat_dat->pclk)) {
-		dev_err(&pdev->dev, "phy_ref_clk clock not found.\n");
-		err = PTR_ERR(plat_dat->pclk);
-		goto disable;
-	}
-
-	err = clk_prepare_enable(plat_dat->pclk);
-	if (err < 0) {
-		dev_err(&pdev->dev, "failed to enable phy_ref clock: %d\n",
-			err);
-		goto disable;
+	for (int i = 0; i < plat_dat->num_clks; i++) {
+		if (strcmp(plat_dat->clks[i].id, "apb_pclk") == 0)
+			plat_dat->stmmac_clk = plat_dat->clks[i].clk;
+		else if (strcmp(plat_dat->clks[i].id, "phy_ref_clk") == 0)
+			plat_dat->pclk = plat_dat->clks[i].clk;
 	}
 
 	return 0;
-
-disable:
-	clk_disable_unprepare(plat_dat->stmmac_clk);
-	return err;
-}
-
-static void dwc_qos_remove(struct platform_device *pdev)
-{
-	struct net_device *ndev = platform_get_drvdata(pdev);
-	struct stmmac_priv *priv = netdev_priv(ndev);
-
-	clk_disable_unprepare(priv->plat->pclk);
-	clk_disable_unprepare(priv->plat->stmmac_clk);
 }
 
 #define SDMEMCOMPPADCTRL 0x8800
@@ -278,52 +241,19 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
 
-	eqos->clk_master = devm_clk_get(&pdev->dev, "master_bus");
-	if (IS_ERR(eqos->clk_master)) {
-		err = PTR_ERR(eqos->clk_master);
-		goto error;
-	}
-
-	err = clk_prepare_enable(eqos->clk_master);
-	if (err < 0)
-		goto error;
-
-	eqos->clk_slave = devm_clk_get(&pdev->dev, "slave_bus");
-	if (IS_ERR(eqos->clk_slave)) {
-		err = PTR_ERR(eqos->clk_slave);
-		goto disable_master;
-	}
-
-	data->stmmac_clk = eqos->clk_slave;
-
-	err = clk_prepare_enable(eqos->clk_slave);
-	if (err < 0)
-		goto disable_master;
-
-	eqos->clk_rx = devm_clk_get(&pdev->dev, "rx");
-	if (IS_ERR(eqos->clk_rx)) {
-		err = PTR_ERR(eqos->clk_rx);
-		goto disable_slave;
-	}
-
-	err = clk_prepare_enable(eqos->clk_rx);
-	if (err < 0)
-		goto disable_slave;
-
-	eqos->clk_tx = devm_clk_get(&pdev->dev, "tx");
-	if (IS_ERR(eqos->clk_tx)) {
-		err = PTR_ERR(eqos->clk_tx);
-		goto disable_rx;
+	for (int i = 0; i < data->num_clks; i++) {
+		if (strcmp(data->clks[i].id, "slave_bus") == 0) {
+			eqos->clk_slave = data->clks[i].clk;
+			data->stmmac_clk = eqos->clk_slave;
+		} else if (strcmp(data->clks[i].id, "tx") == 0) {
+			eqos->clk_tx = data->clks[i].clk;
+		}
 	}
 
-	err = clk_prepare_enable(eqos->clk_tx);
-	if (err < 0)
-		goto disable_rx;
-
 	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(eqos->reset)) {
 		err = PTR_ERR(eqos->reset);
-		goto disable_tx;
+		return err;
 	}
 
 	usleep_range(2000, 4000);
@@ -365,15 +295,7 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	reset_control_assert(eqos->rst);
 reset_phy:
 	gpiod_set_value(eqos->reset, 1);
-disable_tx:
-	clk_disable_unprepare(eqos->clk_tx);
-disable_rx:
-	clk_disable_unprepare(eqos->clk_rx);
-disable_slave:
-	clk_disable_unprepare(eqos->clk_slave);
-disable_master:
-	clk_disable_unprepare(eqos->clk_master);
-error:
+
 	return err;
 }
 
@@ -383,10 +305,6 @@ static void tegra_eqos_remove(struct platform_device *pdev)
 
 	reset_control_assert(eqos->rst);
 	gpiod_set_value(eqos->reset, 1);
-	clk_disable_unprepare(eqos->clk_tx);
-	clk_disable_unprepare(eqos->clk_rx);
-	clk_disable_unprepare(eqos->clk_slave);
-	clk_disable_unprepare(eqos->clk_master);
 }
 
 struct dwc_eth_dwmac_data {
@@ -398,7 +316,6 @@ struct dwc_eth_dwmac_data {
 
 static const struct dwc_eth_dwmac_data dwc_qos_data = {
 	.probe = dwc_qos_probe,
-	.remove = dwc_qos_remove,
 };
 
 static const struct dwc_eth_dwmac_data tegra_eqos_data = {
@@ -434,9 +351,19 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
+	ret = devm_clk_bulk_get_all(&pdev->dev, &plat_dat->clks);
+	if (ret < 0)
+		return dev_err_probe(&pdev->dev, ret, "Failed to retrieve all required clocks\n");
+	plat_dat->num_clks = ret;
+
+	ret = clk_bulk_prepare_enable(plat_dat->num_clks, plat_dat->clks);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n");
+
 	ret = data->probe(pdev, plat_dat, &stmmac_res);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n");
+		clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
 		return ret;
 	}
 
@@ -451,7 +378,8 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	return ret;
 
 remove:
-	data->remove(pdev);
+	if (data->remove)
+		data->remove(pdev);
 
 	return ret;
 }
@@ -459,10 +387,15 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 static void dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
 	const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev);
+	struct plat_stmmacenet_data *plat_data = dev_get_platdata(&pdev->dev);
 
 	stmmac_dvr_remove(&pdev->dev);
 
-	data->remove(pdev);
+	if (data->remove)
+		data->remove(pdev);
+
+	if (plat_data)
+		clk_bulk_disable_unprepare(plat_data->num_clks, plat_data->clks);
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index c9878a612e532..24422ac4e4179 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -254,6 +254,8 @@ struct plat_stmmacenet_data {
 	struct clk *clk_ptp_ref;
 	unsigned long clk_ptp_rate;
 	unsigned long clk_ref_rate;
+	struct clk_bulk_data *clks;
+	int num_clks;
 	unsigned int mult_fact_100ns;
 	s32 ptp_max_adj;
 	u32 cdc_error_adj;

From 55250b83b02aa5ffe602987adb2c05178c87ac63 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:13:27 +0000
Subject: [PATCH 0568/2753] inet: reduce inet_csk_clone_lock() indent level

Return early from inet_csk_clone_lock() if the socket
allocation failed, to reduce the indentation level.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250212131328.1514243-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_connection_sock.c | 50 ++++++++++++++++++---------------
 1 file changed, 27 insertions(+), 23 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 2b7775b90a090..1c00069552ccf 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1237,39 +1237,43 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 				 const gfp_t priority)
 {
 	struct sock *newsk = sk_clone_lock(sk, priority);
+	struct inet_connection_sock *newicsk;
 
-	if (newsk) {
-		struct inet_connection_sock *newicsk = inet_csk(newsk);
+	if (!newsk)
+		return NULL;
 
-		inet_sk_set_state(newsk, TCP_SYN_RECV);
-		newicsk->icsk_bind_hash = NULL;
-		newicsk->icsk_bind2_hash = NULL;
+	newicsk = inet_csk(newsk);
 
-		inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
-		inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
-		inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
+	inet_sk_set_state(newsk, TCP_SYN_RECV);
+	newicsk->icsk_bind_hash = NULL;
+	newicsk->icsk_bind2_hash = NULL;
 
-		/* listeners have SOCK_RCU_FREE, not the children */
-		sock_reset_flag(newsk, SOCK_RCU_FREE);
+	inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
+	inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
+	inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
 
-		inet_sk(newsk)->mc_list = NULL;
+	/* listeners have SOCK_RCU_FREE, not the children */
+	sock_reset_flag(newsk, SOCK_RCU_FREE);
 
-		newsk->sk_mark = inet_rsk(req)->ir_mark;
-		atomic64_set(&newsk->sk_cookie,
-			     atomic64_read(&inet_rsk(req)->ir_cookie));
+	inet_sk(newsk)->mc_list = NULL;
 
-		newicsk->icsk_retransmits = 0;
-		newicsk->icsk_backoff	  = 0;
-		newicsk->icsk_probes_out  = 0;
-		newicsk->icsk_probes_tstamp = 0;
+	newsk->sk_mark = inet_rsk(req)->ir_mark;
+	atomic64_set(&newsk->sk_cookie,
+		     atomic64_read(&inet_rsk(req)->ir_cookie));
 
-		/* Deinitialize accept_queue to trap illegal accesses. */
-		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
+	newicsk->icsk_retransmits = 0;
+	newicsk->icsk_backoff	  = 0;
+	newicsk->icsk_probes_out  = 0;
+	newicsk->icsk_probes_tstamp = 0;
 
-		inet_clone_ulp(req, newsk, priority);
+	/* Deinitialize accept_queue to trap illegal accesses. */
+	memset(&newicsk->icsk_accept_queue, 0,
+	       sizeof(newicsk->icsk_accept_queue));
+
+	inet_clone_ulp(req, newsk, priority);
+
+	security_inet_csk_clone(newsk, req);
 
-		security_inet_csk_clone(newsk, req);
-	}
 	return newsk;
 }
 EXPORT_SYMBOL_GPL(inet_csk_clone_lock);

From a3a128f611a965fddf8a02dd45716f96e0738e00 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Feb 2025 13:13:28 +0000
Subject: [PATCH 0569/2753] inet: consolidate inet_csk_clone_lock()

Current inet_sock_set_state trace from inet_csk_clone_lock() is missing
many details :

... sock:inet_sock_set_state: family=AF_INET6 protocol=IPPROTO_TCP \
    sport=4901 dport=0 \
    saddr=127.0.0.6 daddr=0.0.0.0 \
    saddrv6=:: daddrv6=:: \
    oldstate=TCP_LISTEN newstate=TCP_SYN_RECV

Only the sport gives the listener port, no other parts of the n-tuple are correct.

In this patch, I initialize relevant fields of the new socket before
calling inet_sk_set_state(newsk, TCP_SYN_RECV).

We now have a trace including all the source/destination bits.

... sock:inet_sock_set_state: family=AF_INET6 protocol=IPPROTO_TCP \
    sport=4901 dport=47648 \
    saddr=127.0.0.6 daddr=127.0.0.6 \
    saddrv6=2002:a05:6830:1f85:: daddrv6=2001:4860:f803:65::3 \
    oldstate=TCP_LISTEN newstate=TCP_SYN_RECV

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250212131328.1514243-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/dccp/ipv4.c                 |  3 ---
 net/dccp/ipv6.c                 |  9 +++------
 net/ipv4/inet_connection_sock.c | 24 ++++++++++++++++++++----
 net/ipv4/tcp_ipv4.c             |  4 ----
 net/ipv6/tcp_ipv6.c             |  8 ++------
 5 files changed, 25 insertions(+), 23 deletions(-)

diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index be515ba821e2d..bfa529a54acab 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -426,9 +426,6 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk,
 
 	newinet		   = inet_sk(newsk);
 	ireq		   = inet_rsk(req);
-	sk_daddr_set(newsk, ireq->ir_rmt_addr);
-	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
-	newinet->inet_saddr	= ireq->ir_loc_addr;
 	RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt));
 	newinet->mc_index  = inet_iif(skb);
 	newinet->mc_ttl	   = ip_hdr(skb)->ttl;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d6649246188d7..39ae9d89d7d43 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -365,6 +365,9 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
 	ireq = inet_rsk(req);
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+	ireq->ir_rmt_addr = LOOPBACK4_IPV6;
+	ireq->ir_loc_addr = LOOPBACK4_IPV6;
+
 	ireq->ireq_family = AF_INET6;
 	ireq->ir_mark = inet_request_mark(sk, skb);
 
@@ -504,10 +507,7 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 
 	memcpy(newnp, np, sizeof(struct ipv6_pinfo));
 
-	newsk->sk_v6_daddr	= ireq->ir_v6_rmt_addr;
 	newnp->saddr		= ireq->ir_v6_loc_addr;
-	newsk->sk_v6_rcv_saddr	= ireq->ir_v6_loc_addr;
-	newsk->sk_bound_dev_if	= ireq->ir_iif;
 
 	/* Now IPv6 options...
 
@@ -546,9 +546,6 @@ static struct sock *dccp_v6_request_recv_sock(const struct sock *sk,
 
 	dccp_sync_mss(newsk, dst_mtu(dst));
 
-	newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
-	newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
-
 	if (__inet_inherit_port(sk, newsk) < 0) {
 		inet_csk_prepare_forced_close(newsk);
 		dccp_done(newsk);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 1c00069552ccf..bf9ce0c196575 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1238,19 +1238,33 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 {
 	struct sock *newsk = sk_clone_lock(sk, priority);
 	struct inet_connection_sock *newicsk;
+	struct inet_request_sock *ireq;
+	struct inet_sock *newinet;
 
 	if (!newsk)
 		return NULL;
 
 	newicsk = inet_csk(newsk);
+	newinet = inet_sk(newsk);
+	ireq = inet_rsk(req);
 
-	inet_sk_set_state(newsk, TCP_SYN_RECV);
 	newicsk->icsk_bind_hash = NULL;
 	newicsk->icsk_bind2_hash = NULL;
 
-	inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port;
-	inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num;
-	inet_sk(newsk)->inet_sport = htons(inet_rsk(req)->ir_num);
+	newinet->inet_dport = ireq->ir_rmt_port;
+	newinet->inet_num = ireq->ir_num;
+	newinet->inet_sport = htons(ireq->ir_num);
+
+	newsk->sk_bound_dev_if = ireq->ir_iif;
+
+	newsk->sk_daddr = ireq->ir_rmt_addr;
+	newsk->sk_rcv_saddr = ireq->ir_loc_addr;
+	newinet->inet_saddr = ireq->ir_loc_addr;
+
+#if IS_ENABLED(CONFIG_IPV6)
+	newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
+	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
+#endif
 
 	/* listeners have SOCK_RCU_FREE, not the children */
 	sock_reset_flag(newsk, SOCK_RCU_FREE);
@@ -1270,6 +1284,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 	memset(&newicsk->icsk_accept_queue, 0,
 	       sizeof(newicsk->icsk_accept_queue));
 
+	inet_sk_set_state(newsk, TCP_SYN_RECV);
+
 	inet_clone_ulp(req, newsk, priority);
 
 	security_inet_csk_clone(newsk, req);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 6245e24fcbf3f..f4a5e963a6077 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1768,10 +1768,6 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb,
 	newtp		      = tcp_sk(newsk);
 	newinet		      = inet_sk(newsk);
 	ireq		      = inet_rsk(req);
-	sk_daddr_set(newsk, ireq->ir_rmt_addr);
-	sk_rcv_saddr_set(newsk, ireq->ir_loc_addr);
-	newsk->sk_bound_dev_if = ireq->ir_iif;
-	newinet->inet_saddr   = ireq->ir_loc_addr;
 	inet_opt	      = rcu_dereference(ireq->ireq_opt);
 	RCU_INIT_POINTER(newinet->inet_opt, inet_opt);
 	newinet->mc_index     = inet_iif(skb);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 2debdf085a3b4..a806082602985 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -798,6 +798,8 @@ static void tcp_v6_init_req(struct request_sock *req,
 
 	ireq->ir_v6_rmt_addr = ipv6_hdr(skb)->saddr;
 	ireq->ir_v6_loc_addr = ipv6_hdr(skb)->daddr;
+	ireq->ir_rmt_addr = LOOPBACK4_IPV6;
+	ireq->ir_loc_addr = LOOPBACK4_IPV6;
 
 	/* So that link locals have meaning */
 	if ((!sk_listener->sk_bound_dev_if || l3_slave) &&
@@ -1451,10 +1453,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	ip6_dst_store(newsk, dst, NULL, NULL);
 
-	newsk->sk_v6_daddr = ireq->ir_v6_rmt_addr;
 	newnp->saddr = ireq->ir_v6_loc_addr;
-	newsk->sk_v6_rcv_saddr = ireq->ir_v6_loc_addr;
-	newsk->sk_bound_dev_if = ireq->ir_iif;
 
 	/* Now IPv6 options...
 
@@ -1507,9 +1506,6 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff *
 
 	tcp_initialize_rcv_mss(newsk);
 
-	newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6;
-	newinet->inet_rcv_saddr = LOOPBACK4_IPV6;
-
 #ifdef CONFIG_TCP_MD5SIG
 	l3index = l3mdev_master_ifindex_by_index(sock_net(sk), ireq->ir_iif);
 

From e9f03a6a879bffea0ee51af87ac7a0c77716dda6 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:53:39 +0000
Subject: [PATCH 0570/2753] net: phylink: add support for notifying PCS about
 EEE

There are hooks in the stmmac driver into XPCS to control the EEE
settings when LPI is configured at the MAC. This bypasses the layering.
To allow this to be removed from the stmmac driver, add two new
methods for PCS to inform them when the LPI/EEE enablement state
changes at the MAC.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQ3-003w6u-RH@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 25 ++++++++++++++++++++++---
 include/linux/phylink.h   | 22 ++++++++++++++++++++++
 2 files changed, 44 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 74693307dfbf9..046ec8dda1598 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1073,6 +1073,18 @@ static void phylink_pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 		pcs->ops->pcs_link_up(pcs, neg_mode, interface, speed, duplex);
 }
 
+static void phylink_pcs_disable_eee(struct phylink_pcs *pcs)
+{
+	if (pcs && pcs->ops->pcs_disable_eee)
+		pcs->ops->pcs_disable_eee(pcs);
+}
+
+static void phylink_pcs_enable_eee(struct phylink_pcs *pcs)
+{
+	if (pcs && pcs->ops->pcs_enable_eee)
+		pcs->ops->pcs_enable_eee(pcs);
+}
+
 /* Query inband for a specific interface mode, asking the MAC for the
  * PCS which will be used to handle the interface mode.
  */
@@ -1601,6 +1613,8 @@ static void phylink_deactivate_lpi(struct phylink *pl)
 		phylink_dbg(pl, "disabling LPI\n");
 
 		pl->mac_ops->mac_disable_tx_lpi(pl->config);
+
+		phylink_pcs_disable_eee(pl->pcs);
 	}
 }
 
@@ -1617,13 +1631,18 @@ static void phylink_activate_lpi(struct phylink *pl)
 	phylink_dbg(pl, "LPI timer %uus, tx clock stop %u\n",
 		    pl->mac_tx_lpi_timer, pl->mac_tx_clk_stop);
 
+	phylink_pcs_enable_eee(pl->pcs);
+
 	err = pl->mac_ops->mac_enable_tx_lpi(pl->config, pl->mac_tx_lpi_timer,
 					     pl->mac_tx_clk_stop);
-	if (!err)
-		pl->mac_enable_tx_lpi = true;
-	else
+	if (err) {
+		phylink_pcs_disable_eee(pl->pcs);
 		phylink_err(pl, "%ps() failed: %pe\n",
 			    pl->mac_ops->mac_enable_tx_lpi, ERR_PTR(err));
+		return;
+	}
+
+	pl->mac_enable_tx_lpi = true;
 }
 
 static void phylink_link_up(struct phylink *pl,
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 0de78673172de..41ab85e591ad6 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -477,6 +477,10 @@ struct phylink_pcs {
  * @pcs_an_restart: restart 802.3z BaseX autonegotiation.
  * @pcs_link_up: program the PCS for the resolved link configuration
  *               (where necessary).
+ * @pcs_disable_eee: optional notification to PCS that EEE has been disabled
+ *		     at the MAC.
+ * @pcs_enable_eee: optional notification to PCS that EEE will be enabled at
+ *		    the MAC.
  * @pcs_pre_init: configure PCS components necessary for MAC hardware
  *                initialization e.g. RX clock for stmmac.
  */
@@ -500,6 +504,8 @@ struct phylink_pcs_ops {
 	void (*pcs_an_restart)(struct phylink_pcs *pcs);
 	void (*pcs_link_up)(struct phylink_pcs *pcs, unsigned int neg_mode,
 			    phy_interface_t interface, int speed, int duplex);
+	void (*pcs_disable_eee)(struct phylink_pcs *pcs);
+	void (*pcs_enable_eee)(struct phylink_pcs *pcs);
 	int (*pcs_pre_init)(struct phylink_pcs *pcs);
 };
 
@@ -625,6 +631,22 @@ void pcs_an_restart(struct phylink_pcs *pcs);
 void pcs_link_up(struct phylink_pcs *pcs, unsigned int neg_mode,
 		 phy_interface_t interface, int speed, int duplex);
 
+/**
+ * pcs_disable_eee() - Disable EEE at the PCS
+ * @pcs: a pointer to a &struct phylink_pcs
+ *
+ * Optional method informing the PCS that EEE has been disabled at the MAC.
+ */
+void pcs_disable_eee(struct phylink_pcs *pcs);
+
+/**
+ * pcs_enable_eee() - Enable EEE at the PCS
+ * @pcs: a pointer to a &struct phylink_pcs
+ *
+ * Optional method informing the PCS that EEE is about to be enabled at the MAC.
+ */
+void pcs_enable_eee(struct phylink_pcs *pcs);
+
 /**
  * pcs_pre_init() - Configure PCS components necessary for MAC initialization
  * @pcs: a pointer to a &struct phylink_pcs.

From 8c841486674a43df9db08210232987cf039b8942 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:53:44 +0000
Subject: [PATCH 0571/2753] net: xpcs: add function to configure EEE clock
 multiplying factor

Add a function to separate out the EEE clock multiplying factor. This
will be called by the stmmac driver to configure this value.

It would have been better had the driver used the CLK API to retrieve
this clock, get its rate and calculate the appropriate multiplier, but
that door has closed.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQ8-003w70-VT@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c   | 14 ++++++++++++++
 drivers/net/pcs/pcs-xpcs.h   |  1 +
 include/linux/pcs/pcs-xpcs.h |  1 +
 3 files changed, 16 insertions(+)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 1faa37f0e7b94..91ce4b13df327 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -1193,6 +1193,20 @@ static void xpcs_an_restart(struct phylink_pcs *pcs)
 		    BMCR_ANRESTART);
 }
 
+/**
+ * xpcs_config_eee_mult_fact() - set the EEE clock multiplying factor
+ * @xpcs: pointer to a &struct dw_xpcs instance
+ * @mult_fact: the multiplying factor
+ *
+ * Configure the EEE clock multiplying factor. This value should be such that
+ * clk_eee_time_period * (mult_fact + 1) is within the range 80 to 120ns.
+ */
+void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact)
+{
+	xpcs->eee_mult_fact = mult_fact;
+}
+EXPORT_SYMBOL_GPL(xpcs_config_eee_mult_fact);
+
 static int xpcs_read_ids(struct dw_xpcs *xpcs)
 {
 	int ret;
diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
index adc5a0b3c8831..39d3f517b557b 100644
--- a/drivers/net/pcs/pcs-xpcs.h
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -122,6 +122,7 @@ struct dw_xpcs {
 	struct phylink_pcs pcs;
 	phy_interface_t interface;
 	bool need_reset;
+	u8 eee_mult_fact;
 };
 
 int xpcs_read(struct dw_xpcs *xpcs, int dev, u32 reg);
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index 733f4ddd2ef15..749d40a9a0867 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -52,6 +52,7 @@ struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs);
 int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
 int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
 		    int enable);
+void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact);
 struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr);
 struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode);
 void xpcs_destroy(struct dw_xpcs *xpcs);

From 060fb27060e89c7d31c1c9542a6d1fb058573ff5 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:53:50 +0000
Subject: [PATCH 0572/2753] net: stmmac: call xpcs_config_eee_mult_fact()

Arrange for stmmac to call the new xpcs_config_eee_mult_fact() function
to configure the EEE clock multiplying factor. This will allow the
removal of the xpcs_config_eee() calls in the next patch.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQE-003w76-3C@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 0c7d81ddd4406..7c0a4046bbe35 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -524,6 +524,8 @@ int stmmac_pcs_setup(struct net_device *ndev)
 	if (ret)
 		return dev_err_probe(priv->device, ret, "No xPCS found\n");
 
+	xpcs_config_eee_mult_fact(xpcs, priv->plat->mult_fact_100ns);
+
 	priv->hw->xpcs = xpcs;
 
 	return 0;

From 5a12b2cf29c12d9d1467ec3e03746cd43dbb6251 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:53:55 +0000
Subject: [PATCH 0573/2753] net: xpcs: convert to phylink managed EEE

Convert XPCS to use the new pcs_disable_eee() and pcs_enable_eee()
methods. Since stmmac is the only user of xpcs_config_eee(), we can
make this a no-op along with this change.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQJ-003w7C-6v@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c | 24 +++++++++++++++++++++++-
 1 file changed, 23 insertions(+), 1 deletion(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 91ce4b13df327..1f312b5589a39 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -602,7 +602,8 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
 		__set_bit(compat->interface, interfaces);
 }
 
-int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
+static int __xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
+			     int enable)
 {
 	u16 mask, val;
 	int ret;
@@ -630,6 +631,11 @@ int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
 			   DW_VR_MII_EEE_TRN_LPI,
 			   enable ? DW_VR_MII_EEE_TRN_LPI : 0);
 }
+
+int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
+{
+	return 0;
+}
 EXPORT_SYMBOL_GPL(xpcs_config_eee);
 
 static void xpcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface)
@@ -1193,6 +1199,20 @@ static void xpcs_an_restart(struct phylink_pcs *pcs)
 		    BMCR_ANRESTART);
 }
 
+static void xpcs_disable_eee(struct phylink_pcs *pcs)
+{
+	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
+
+	__xpcs_config_eee(xpcs, 0, false);
+}
+
+static void xpcs_enable_eee(struct phylink_pcs *pcs)
+{
+	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
+
+	__xpcs_config_eee(xpcs, xpcs->eee_mult_fact, true);
+}
+
 /**
  * xpcs_config_eee_mult_fact() - set the EEE clock multiplying factor
  * @xpcs: pointer to a &struct dw_xpcs instance
@@ -1355,6 +1375,8 @@ static const struct phylink_pcs_ops xpcs_phylink_ops = {
 	.pcs_get_state = xpcs_get_state,
 	.pcs_an_restart = xpcs_an_restart,
 	.pcs_link_up = xpcs_link_up,
+	.pcs_disable_eee = xpcs_disable_eee,
+	.pcs_enable_eee = xpcs_enable_eee,
 };
 
 static int xpcs_identify(struct dw_xpcs *xpcs)

From dba7441b3916d145e24329fbef761b7349ba631c Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:54:00 +0000
Subject: [PATCH 0574/2753] net: stmmac: remove calls to xpcs_config_eee()

Remove the explicit calls to xpcs_config_eee() from the stmmac driver,
preferring instead for phylink to manage the EEE configuration at the
PCS.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQO-003w7I-Ap@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d99ff4146512d..fd8ca1524e43b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1046,10 +1046,6 @@ static void stmmac_mac_disable_tx_lpi(struct phylink_config *config)
 	priv->tx_path_in_lpi_mode = false;
 
 	stmmac_set_eee_timer(priv, priv->hw, 0, STMMAC_DEFAULT_TWT_LS);
-	if (priv->hw->xpcs)
-		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,
-				false);
-
 	mutex_unlock(&priv->lock);
 }
 
@@ -1068,9 +1064,6 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 
 	stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
 			     STMMAC_DEFAULT_TWT_LS);
-	if (priv->hw->xpcs)
-		xpcs_config_eee(priv->hw->xpcs, priv->plat->mult_fact_100ns,
-				true);
 
 	/* Try to cnfigure the hardware timer. */
 	ret = stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_TIMER,

From 55faeb89968aab5a32f0de93cd97fc1c4169d0f7 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:54:05 +0000
Subject: [PATCH 0575/2753] net: xpcs: remove xpcs_config_eee() from global
 scope

Make xpcs_config_eee() private to the XPCS driver, called only from
the phylink pcs_disable_eee() and pcs_enable_eee() methods.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQT-003w7O-Ec@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c   | 14 ++++----------
 include/linux/pcs/pcs-xpcs.h |  2 --
 2 files changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 1f312b5589a39..6a28a4eae21cf 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -602,8 +602,8 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
 		__set_bit(compat->interface, interfaces);
 }
 
-static int __xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
-			     int enable)
+static int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
+			   int enable)
 {
 	u16 mask, val;
 	int ret;
@@ -632,12 +632,6 @@ static int __xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
 			   enable ? DW_VR_MII_EEE_TRN_LPI : 0);
 }
 
-int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns, int enable)
-{
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xpcs_config_eee);
-
 static void xpcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
@@ -1203,14 +1197,14 @@ static void xpcs_disable_eee(struct phylink_pcs *pcs)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 
-	__xpcs_config_eee(xpcs, 0, false);
+	xpcs_config_eee(xpcs, 0, false);
 }
 
 static void xpcs_enable_eee(struct phylink_pcs *pcs)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 
-	__xpcs_config_eee(xpcs, xpcs->eee_mult_fact, true);
+	xpcs_config_eee(xpcs, xpcs->eee_mult_fact, true);
 }
 
 /**
diff --git a/include/linux/pcs/pcs-xpcs.h b/include/linux/pcs/pcs-xpcs.h
index 749d40a9a0867..e40f554ff717a 100644
--- a/include/linux/pcs/pcs-xpcs.h
+++ b/include/linux/pcs/pcs-xpcs.h
@@ -50,8 +50,6 @@ struct dw_xpcs;
 
 struct phylink_pcs *xpcs_to_phylink_pcs(struct dw_xpcs *xpcs);
 int xpcs_get_an_mode(struct dw_xpcs *xpcs, phy_interface_t interface);
-int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
-		    int enable);
 void xpcs_config_eee_mult_fact(struct dw_xpcs *xpcs, u8 mult_fact);
 struct dw_xpcs *xpcs_create_mdiodev(struct mii_bus *bus, int addr);
 struct dw_xpcs *xpcs_create_fwnode(struct fwnode_handle *fwnode);

From 760320145a5acb5186b5500e396bd0ea434c8040 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:54:10 +0000
Subject: [PATCH 0576/2753] net: xpcs: clean up xpcs_config_eee()

There is now no need to pass the mult_fact into xpcs_config_eee(), so
let's remove that argument and use xpcs->eee_mult_fact directly. While
changing the function signature, as we pass true/false for enable, use
"bool" instead of "int" for this.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQY-003w7U-IG@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index 6a28a4eae21cf..cae6e83771913 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -602,8 +602,7 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
 		__set_bit(compat->interface, interfaces);
 }
 
-static int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
-			   int enable)
+static int xpcs_config_eee(struct dw_xpcs *xpcs, bool enable)
 {
 	u16 mask, val;
 	int ret;
@@ -618,7 +617,7 @@ static int xpcs_config_eee(struct dw_xpcs *xpcs, int mult_fact_100ns,
 		      DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
 		      DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
 		      FIELD_PREP(DW_VR_MII_EEE_MULT_FACT_100NS,
-				 mult_fact_100ns);
+				 xpcs->eee_mult_fact);
 	else
 		val = 0;
 
@@ -1197,14 +1196,14 @@ static void xpcs_disable_eee(struct phylink_pcs *pcs)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 
-	xpcs_config_eee(xpcs, 0, false);
+	xpcs_config_eee(xpcs, false);
 }
 
 static void xpcs_enable_eee(struct phylink_pcs *pcs)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 
-	xpcs_config_eee(xpcs, xpcs->eee_mult_fact, true);
+	xpcs_config_eee(xpcs, true);
 }
 
 /**

From 1d4c99a1ac126b73780b0caec3ab9fbd7fc85adc Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Feb 2025 10:54:15 +0000
Subject: [PATCH 0577/2753] net: xpcs: group EEE code together

Move xpcs_config_eee() with the other EEE-related functions.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1thRQd-003w7a-MM@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c | 58 +++++++++++++++++++-------------------
 1 file changed, 29 insertions(+), 29 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index cae6e83771913..ee0c1a27f06ce 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -602,35 +602,6 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
 		__set_bit(compat->interface, interfaces);
 }
 
-static int xpcs_config_eee(struct dw_xpcs *xpcs, bool enable)
-{
-	u16 mask, val;
-	int ret;
-
-	mask = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
-	       DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
-	       DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
-	       DW_VR_MII_EEE_MULT_FACT_100NS;
-
-	if (enable)
-		val = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
-		      DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
-		      DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
-		      FIELD_PREP(DW_VR_MII_EEE_MULT_FACT_100NS,
-				 xpcs->eee_mult_fact);
-	else
-		val = 0;
-
-	ret = xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, mask,
-			  val);
-	if (ret < 0)
-		return ret;
-
-	return xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1,
-			   DW_VR_MII_EEE_TRN_LPI,
-			   enable ? DW_VR_MII_EEE_TRN_LPI : 0);
-}
-
 static void xpcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
@@ -1192,6 +1163,35 @@ static void xpcs_an_restart(struct phylink_pcs *pcs)
 		    BMCR_ANRESTART);
 }
 
+static int xpcs_config_eee(struct dw_xpcs *xpcs, bool enable)
+{
+	u16 mask, val;
+	int ret;
+
+	mask = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
+	       DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
+	       DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
+	       DW_VR_MII_EEE_MULT_FACT_100NS;
+
+	if (enable)
+		val = DW_VR_MII_EEE_LTX_EN | DW_VR_MII_EEE_LRX_EN |
+		      DW_VR_MII_EEE_TX_QUIET_EN | DW_VR_MII_EEE_RX_QUIET_EN |
+		      DW_VR_MII_EEE_TX_EN_CTRL | DW_VR_MII_EEE_RX_EN_CTRL |
+		      FIELD_PREP(DW_VR_MII_EEE_MULT_FACT_100NS,
+				 xpcs->eee_mult_fact);
+	else
+		val = 0;
+
+	ret = xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL0, mask,
+			  val);
+	if (ret < 0)
+		return ret;
+
+	return xpcs_modify(xpcs, MDIO_MMD_VEND2, DW_VR_MII_EEE_MCTRL1,
+			   DW_VR_MII_EEE_TRN_LPI,
+			   enable ? DW_VR_MII_EEE_TRN_LPI : 0);
+}
+
 static void xpcs_disable_eee(struct phylink_pcs *pcs)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);

From 13918315c5dc5a515926c8799042ea6885c2b734 Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Sat, 8 Feb 2025 13:42:13 -0700
Subject: [PATCH 0578/2753] io-wq: backoff when retrying worker creation

When io_uring submission goes async for the first time on a given task,
we'll try to create a worker thread to handle the submission. Creating
this worker thread can fail due to various transient conditions, such as
an outstanding signal in the forking thread, so we have retry logic with
a limit of 3 retries. However, this retry logic appears to be too
aggressive/fast - we've observed a thread blowing through the retry
limit while having the same outstanding signal the whole time. Here's an
excerpt of some tracing that demonstrates the issue:

First, signal 26 is generated for the process. It ends up getting routed
to thread 92942.

 0)   cbd-92284    /* signal_generate: sig=26 errno=0 code=-2 comm=psblkdASD pid=92934 grp=1 res=0 */

This causes create_io_thread in the signalled thread to fail with
ERESTARTNOINTR, and thus a retry is queued.

13) task_th-92942  /* io_uring_queue_async_work: ring 000000007325c9ae, request 0000000080c96d8e, user_data 0x0, opcode URING_CMD, flags 0x8240001, normal queue, work 000000006e96dd3f */
13) task_th-92942  io_wq_enqueue() {
13) task_th-92942    _raw_spin_lock();
13) task_th-92942    io_wq_activate_free_worker();
13) task_th-92942    _raw_spin_lock();
13) task_th-92942    create_io_worker() {
13) task_th-92942      __kmalloc_cache_noprof();
13) task_th-92942      __init_swait_queue_head();
13) task_th-92942      kprobe_ftrace_handler() {
13) task_th-92942        get_kprobe();
13) task_th-92942        aggr_pre_handler() {
13) task_th-92942          pre_handler_kretprobe();
13) task_th-92942          /* create_enter: (create_io_thread+0x0/0x50) fn=0xffffffff8172c0e0 arg=0xffff888996bb69c0 node=-1 */
13) task_th-92942        } /* aggr_pre_handler */
...
13) task_th-92942        } /* copy_process */
13) task_th-92942      } /* create_io_thread */
13) task_th-92942      kretprobe_rethook_handler() {
13) task_th-92942        /* create_exit: (create_io_worker+0x8a/0x1a0 <- create_io_thread) arg1=0xfffffffffffffdff */
13) task_th-92942      } /* kretprobe_rethook_handler */
13) task_th-92942    queue_work_on() {
...

The CPU is then handed to a kworker to process the queued retry:

------------------------------------------
 13) task_th-92942  => kworker-54154
------------------------------------------
13) kworker-54154  io_workqueue_create() {
13) kworker-54154    io_queue_worker_create() {
13) kworker-54154      task_work_add() {
13) kworker-54154        wake_up_state() {
13) kworker-54154          try_to_wake_up() {
13) kworker-54154            _raw_spin_lock_irqsave();
13) kworker-54154            _raw_spin_unlock_irqrestore();
13) kworker-54154          } /* try_to_wake_up */
13) kworker-54154        } /* wake_up_state */
13) kworker-54154        kick_process();
13) kworker-54154      } /* task_work_add */
13) kworker-54154    } /* io_queue_worker_create */
13) kworker-54154  } /* io_workqueue_create */

And then we immediately switch back to the original task to try creating
a worker again. This fails, because the original task still hasn't
handled its signal.

-----------------------------------------
 13) kworker-54154  => task_th-92942
------------------------------------------
13) task_th-92942  create_worker_cont() {
13) task_th-92942    kprobe_ftrace_handler() {
13) task_th-92942      get_kprobe();
13) task_th-92942      aggr_pre_handler() {
13) task_th-92942        pre_handler_kretprobe();
13) task_th-92942        /* create_enter: (create_io_thread+0x0/0x50) fn=0xffffffff8172c0e0 arg=0xffff888996bb69c0 node=-1 */
13) task_th-92942      } /* aggr_pre_handler */
13) task_th-92942    } /* kprobe_ftrace_handler */
13) task_th-92942    create_io_thread() {
13) task_th-92942      copy_process() {
13) task_th-92942        task_active_pid_ns();
13) task_th-92942        _raw_spin_lock_irq();
13) task_th-92942        recalc_sigpending();
13) task_th-92942        _raw_spin_lock_irq();
13) task_th-92942      } /* copy_process */
13) task_th-92942    } /* create_io_thread */
13) task_th-92942    kretprobe_rethook_handler() {
13) task_th-92942      /* create_exit: (create_worker_cont+0x35/0x1b0 <- create_io_thread) arg1=0xfffffffffffffdff */
13) task_th-92942    } /* kretprobe_rethook_handler */
13) task_th-92942    io_worker_release();
13) task_th-92942    queue_work_on() {
13) task_th-92942      clear_pending_if_disabled();
13) task_th-92942      __queue_work() {
13) task_th-92942      } /* __queue_work */
13) task_th-92942    } /* queue_work_on */
13) task_th-92942  } /* create_worker_cont */

The pattern repeats another couple times until we blow through the retry
counter, at which point we give up. All outstanding work is canceled,
and the io_uring command which triggered all this is failed with
ECANCELED:

13) task_th-92942  io_acct_cancel_pending_work() {
...
13) task_th-92942  /* io_uring_complete: ring 000000007325c9ae, req 0000000080c96d8e, user_data 0x0, result -125, cflags 0x0 extra1 0 extra2 0  */

Finally, the task gets around to processing its outstanding signal 26,
but it's too late.

13) task_th-92942  /* signal_deliver: sig=26 errno=0 code=-2 sa_handler=59566a0 sa_flags=14000000 */

Try to address this issue by adding a small scaling delay when retrying
worker creation. This should give the forking thread time to handle its
signal in the above case. This isn't a particularly satisfying solution,
as sufficiently paradoxical scheduling would still have us hitting the
same issue, and I'm open to suggestions for something better. But this
is likely to prevent this (already rare) issue from hitting in practice.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Link: https://lore.kernel.org/r/20250208-wq_retry-v2-1-4f6f5041d303@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io-wq.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index 5d0928f37471e..91019b4d03088 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -64,7 +64,7 @@ struct io_worker {
 
 	union {
 		struct rcu_head rcu;
-		struct work_struct work;
+		struct delayed_work work;
 	};
 };
 
@@ -770,6 +770,18 @@ static inline bool io_should_retry_thread(struct io_worker *worker, long err)
 	}
 }
 
+static void queue_create_worker_retry(struct io_worker *worker)
+{
+	/*
+	 * We only bother retrying because there's a chance that the
+	 * failure to create a worker is due to some temporary condition
+	 * in the forking task (e.g. outstanding signal); give the task
+	 * some time to clear that condition.
+	 */
+	schedule_delayed_work(&worker->work,
+			      msecs_to_jiffies(worker->init_retries * 5));
+}
+
 static void create_worker_cont(struct callback_head *cb)
 {
 	struct io_worker *worker;
@@ -809,12 +821,13 @@ static void create_worker_cont(struct callback_head *cb)
 
 	/* re-create attempts grab a new worker ref, drop the existing one */
 	io_worker_release(worker);
-	schedule_work(&worker->work);
+	queue_create_worker_retry(worker);
 }
 
 static void io_workqueue_create(struct work_struct *work)
 {
-	struct io_worker *worker = container_of(work, struct io_worker, work);
+	struct io_worker *worker = container_of(work, struct io_worker,
+						work.work);
 	struct io_wq_acct *acct = io_wq_get_acct(worker);
 
 	if (!io_queue_worker_create(worker, acct, create_worker_cont))
@@ -855,8 +868,8 @@ static bool create_io_worker(struct io_wq *wq, int index)
 		kfree(worker);
 		goto fail;
 	} else {
-		INIT_WORK(&worker->work, io_workqueue_create);
-		schedule_work(&worker->work);
+		INIT_DELAYED_WORK(&worker->work, io_workqueue_create);
+		queue_create_worker_retry(worker);
 	}
 
 	return true;

From 43c70b104093c324b1a000762ce943d16ce788f9 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Fri, 14 Feb 2025 12:36:36 -0700
Subject: [PATCH 0579/2753] block/merge: remove unnecessary min() with UINT_MAX

In bvec_split_segs(), max_bytes is an unsigned, so it must be less than
or equal to UINT_MAX. Remove the unnecessary min().

Prior to commit 67927d220150 ("block/merge: count bytes instead of
sectors"), the min() was with UINT_MAX >> 9, so it did have an effect.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Link: https://lore.kernel.org/r/20250214193637.234702-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 15cd231d560cb..39b738c0e4c9a 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -270,7 +270,7 @@ static bool bvec_split_segs(const struct queue_limits *lim,
 		const struct bio_vec *bv, unsigned *nsegs, unsigned *bytes,
 		unsigned max_segs, unsigned max_bytes)
 {
-	unsigned max_len = min(max_bytes, UINT_MAX) - *bytes;
+	unsigned max_len = max_bytes - *bytes;
 	unsigned len = min(bv->bv_len, max_len);
 	unsigned total_len = 0;
 	unsigned seg_size = 0;

From 853e80369cfceb2331bf34f251ba11c6602cc67f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 20:15:42 +0100
Subject: [PATCH 0580/2753] r8169: add PHY c45 ops for MDIO_MMD_VENDOR2
 registers

The integrated PHYs on chip versions from RTL8168g allow to address
MDIO_MMD_VEND2 registers. All c22 standard registers are mapped to
MDIO_MMD_VEND2 registers. So far the paging mechanism is used to
address PHY registers. Add support for c45 ops to address MDIO_MMD_VEND2
registers directly, w/o the paging.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/d6f97eaa-0f13-468f-89cb-75a41087bc4a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 32 +++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 9fe53322d7bbc..fa339bd8c775b 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5200,6 +5200,33 @@ static int r8169_mdio_write_reg(struct mii_bus *mii_bus, int phyaddr,
 	return 0;
 }
 
+static int r8169_mdio_read_reg_c45(struct mii_bus *mii_bus, int addr,
+				   int devnum, int regnum)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (addr > 0)
+		return -ENODEV;
+
+	if (devnum == MDIO_MMD_VEND2 && regnum > MDIO_STAT2)
+		return r8168_phy_ocp_read(tp, regnum);
+
+	return 0;
+}
+
+static int r8169_mdio_write_reg_c45(struct mii_bus *mii_bus, int addr,
+				    int devnum, int regnum, u16 val)
+{
+	struct rtl8169_private *tp = mii_bus->priv;
+
+	if (addr > 0 || devnum != MDIO_MMD_VEND2 || regnum <= MDIO_STAT2)
+		return -ENODEV;
+
+	r8168_phy_ocp_write(tp, regnum, val);
+
+	return 0;
+}
+
 static int r8169_mdio_register(struct rtl8169_private *tp)
 {
 	struct pci_dev *pdev = tp->pci_dev;
@@ -5230,6 +5257,11 @@ static int r8169_mdio_register(struct rtl8169_private *tp)
 	new_bus->read = r8169_mdio_read_reg;
 	new_bus->write = r8169_mdio_write_reg;
 
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_40) {
+		new_bus->read_c45 = r8169_mdio_read_reg_c45;
+		new_bus->write_c45 = r8169_mdio_write_reg_c45;
+	}
+
 	ret = devm_mdiobus_register(&pdev->dev, new_bus);
 	if (ret)
 		return ret;

From da681ed73fb980286fc29de707b35d76bb33e123 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 20:18:17 +0100
Subject: [PATCH 0581/2753] net: phy: realtek: improve mmd register access for
 internal PHY's

r8169 provides the MDIO bus for the internal PHY's. It has been extended
with c45 access functions for addressing MDIO_MMD_VEND2 registers.
So we can switch from paged access to directly addressing the
MDIO_MMD_VEND2 registers.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/a5f2333c-dda9-48ad-9801-77049766e632@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/realtek_main.c | 79 +++++++++++---------------
 1 file changed, 33 insertions(+), 46 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 210fefac44d47..2e2c5353c5afd 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -735,29 +735,31 @@ static int rtlgen_read_status(struct phy_device *phydev)
 	return 0;
 }
 
+static int rtlgen_read_vend2(struct phy_device *phydev, int regnum)
+{
+	return __mdiobus_c45_read(phydev->mdio.bus, 0, MDIO_MMD_VEND2, regnum);
+}
+
+static int rtlgen_write_vend2(struct phy_device *phydev, int regnum, u16 val)
+{
+	return __mdiobus_c45_write(phydev->mdio.bus, 0, MDIO_MMD_VEND2, regnum,
+				   val);
+}
+
 static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 {
 	int ret;
 
-	if (devnum == MDIO_MMD_VEND2) {
-		rtl821x_write_page(phydev, regnum >> 4);
-		ret = __phy_read(phydev, 0x10 + ((regnum & 0xf) >> 1));
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE) {
-		rtl821x_write_page(phydev, 0xa5c);
-		ret = __phy_read(phydev, 0x12);
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) {
-		rtl821x_write_page(phydev, 0xa5d);
-		ret = __phy_read(phydev, 0x10);
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE) {
-		rtl821x_write_page(phydev, 0xa5d);
-		ret = __phy_read(phydev, 0x11);
-		rtl821x_write_page(phydev, 0);
-	} else {
+	if (devnum == MDIO_MMD_VEND2)
+		ret = rtlgen_read_vend2(phydev, regnum);
+	else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE)
+		ret = rtlgen_read_vend2(phydev, 0xa5c4);
+	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV)
+		ret = rtlgen_read_vend2(phydev, 0xa5d0);
+	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE)
+		ret = rtlgen_read_vend2(phydev, 0xa5d2);
+	else
 		ret = -EOPNOTSUPP;
-	}
 
 	return ret;
 }
@@ -767,17 +769,12 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 {
 	int ret;
 
-	if (devnum == MDIO_MMD_VEND2) {
-		rtl821x_write_page(phydev, regnum >> 4);
-		ret = __phy_write(phydev, 0x10 + ((regnum & 0xf) >> 1), val);
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV) {
-		rtl821x_write_page(phydev, 0xa5d);
-		ret = __phy_write(phydev, 0x10, val);
-		rtl821x_write_page(phydev, 0);
-	} else {
+	if (devnum == MDIO_MMD_VEND2)
+		ret = rtlgen_write_vend2(phydev, regnum, val);
+	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV)
+		ret = rtlgen_write_vend2(phydev, regnum, 0xa5d0);
+	else
 		ret = -EOPNOTSUPP;
-	}
 
 	return ret;
 }
@@ -789,19 +786,12 @@ static int rtl822x_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 	if (ret != -EOPNOTSUPP)
 		return ret;
 
-	if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE2) {
-		rtl821x_write_page(phydev, 0xa6e);
-		ret = __phy_read(phydev, 0x16);
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) {
-		rtl821x_write_page(phydev, 0xa6d);
-		ret = __phy_read(phydev, 0x12);
-		rtl821x_write_page(phydev, 0);
-	} else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE2) {
-		rtl821x_write_page(phydev, 0xa6d);
-		ret = __phy_read(phydev, 0x10);
-		rtl821x_write_page(phydev, 0);
-	}
+	if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE2)
+		ret = rtlgen_read_vend2(phydev, 0xa6ec);
+	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2)
+		ret = rtlgen_read_vend2(phydev, 0xa6d4);
+	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE2)
+		ret = rtlgen_read_vend2(phydev, 0xa6d0);
 
 	return ret;
 }
@@ -814,11 +804,8 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 	if (ret != -EOPNOTSUPP)
 		return ret;
 
-	if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2) {
-		rtl821x_write_page(phydev, 0xa6d);
-		ret = __phy_write(phydev, 0x12, val);
-		rtl821x_write_page(phydev, 0);
-	}
+	if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2)
+		ret = rtlgen_write_vend2(phydev, 0xa6d4, val);
 
 	return ret;
 }

From 02d3b306ac2f0b174753d1c5b9e4e5fb8ec5057e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 20:19:14 +0100
Subject: [PATCH 0582/2753] net: phy: realtek: switch from paged to MMD ops in
 rtl822x functions

The MDIO bus provided by r8169 for the internal PHY's now supports
c45 ops for the MDIO_MMD_VEND2 device. So we can switch to standard
MMD ops here.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/81416f95-0fac-4225-87b4-828e3738b8ed@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/realtek_main.c | 11 +++++------
 1 file changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 2e2c5353c5afd..34be1d752ef82 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -901,7 +901,7 @@ static int rtl822x_get_features(struct phy_device *phydev)
 {
 	int val;
 
-	val = phy_read_paged(phydev, 0xa61, 0x13);
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND2, 0xa616);
 	if (val < 0)
 		return val;
 
@@ -922,10 +922,9 @@ static int rtl822x_config_aneg(struct phy_device *phydev)
 	if (phydev->autoneg == AUTONEG_ENABLE) {
 		u16 adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising);
 
-		ret = phy_modify_paged_changed(phydev, 0xa5d, 0x12,
-					       MDIO_AN_10GBT_CTRL_ADV2_5G |
-					       MDIO_AN_10GBT_CTRL_ADV5G,
-					       adv);
+		ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, 0xa5d4,
+					     MDIO_AN_10GBT_CTRL_ADV2_5G |
+					     MDIO_AN_10GBT_CTRL_ADV5G, adv);
 		if (ret < 0)
 			return ret;
 	}
@@ -969,7 +968,7 @@ static int rtl822x_read_status(struct phy_device *phydev)
 	    !phydev->autoneg_complete)
 		return 0;
 
-	lpadv = phy_read_paged(phydev, 0xa5d, 0x13);
+	lpadv = phy_read_mmd(phydev, MDIO_MMD_VEND2, 0xa5d6);
 	if (lpadv < 0)
 		return lpadv;
 

From ea47e70e476ffb3fc8969c842d95609da24266b1 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 22:48:11 +0100
Subject: [PATCH 0583/2753] net: phy: remove fixup-related definitions from
 phy.h which are not used outside phylib

Certain fixup-related definitions aren't used outside phy_device.c.
So make them private and remove them from phy.h.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/ea6fde13-9183-4c7c-8434-6c0eb64fc72c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 16 +++++++++++++---
 include/linux/phy.h          | 14 --------------
 2 files changed, 13 insertions(+), 17 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 9b06ba92f2ed2..14c312ad2c03e 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -45,6 +45,17 @@ MODULE_DESCRIPTION("PHY library");
 MODULE_AUTHOR("Andy Fleming");
 MODULE_LICENSE("GPL");
 
+#define	PHY_ANY_ID	"MATCH ANY PHY"
+#define	PHY_ANY_UID	0xffffffff
+
+struct phy_fixup {
+	struct list_head list;
+	char bus_id[MII_BUS_ID_SIZE + 3];
+	u32 phy_uid;
+	u32 phy_uid_mask;
+	int (*run)(struct phy_device *phydev);
+};
+
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_basic_features);
 
@@ -378,8 +389,8 @@ static SIMPLE_DEV_PM_OPS(mdio_bus_phy_pm_ops, mdio_bus_phy_suspend,
  *	comparison
  * @run: The actual code to be run when a matching PHY is found
  */
-int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
-		       int (*run)(struct phy_device *))
+static int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
+			      int (*run)(struct phy_device *))
 {
 	struct phy_fixup *fixup = kzalloc(sizeof(*fixup), GFP_KERNEL);
 
@@ -397,7 +408,6 @@ int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
 
 	return 0;
 }
-EXPORT_SYMBOL(phy_register_fixup);
 
 /* Registers a fixup to be run on any PHY with the UID in phy_uid */
 int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 64982eba71d1e..245578ed710e1 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1287,9 +1287,6 @@ struct phy_driver {
 #define to_phy_driver(d) container_of_const(to_mdio_common_driver(d),		\
 				      struct phy_driver, mdiodrv)
 
-#define PHY_ANY_ID "MATCH ANY PHY"
-#define PHY_ANY_UID 0xffffffff
-
 #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0)
 #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4)
 #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10)
@@ -1322,15 +1319,6 @@ static inline bool phydev_id_compare(struct phy_device *phydev, u32 id)
 	return phy_id_compare(id, phydev->phy_id, phydev->drv->phy_id_mask);
 }
 
-/* A Structure for boards to register fixups with the PHY Lib */
-struct phy_fixup {
-	struct list_head list;
-	char bus_id[MII_BUS_ID_SIZE + 3];
-	u32 phy_uid;
-	u32 phy_uid_mask;
-	int (*run)(struct phy_device *phydev);
-};
-
 const char *phy_speed_to_str(int speed);
 const char *phy_duplex_to_str(unsigned int duplex);
 const char *phy_rate_matching_to_str(int rate_matching);
@@ -2127,8 +2115,6 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv,
 		       bool *tx_pause, bool *rx_pause);
 
-int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask,
-		       int (*run)(struct phy_device *));
 int phy_register_fixup_for_id(const char *bus_id,
 			      int (*run)(struct phy_device *));
 int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask,

From d3a0e217f850a768851974a6efbd70f5673bb584 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 22:49:19 +0100
Subject: [PATCH 0584/2753] net: phy: stop exporting feature arrays which
 aren't used outside phylib

Stop exporting feature arrays which aren't used outside phylib.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/01886672-4880-4ca8-b7b0-94d40f6e0ec5@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 22 ++++++----------------
 include/linux/phy.h          |  5 -----
 2 files changed, 6 insertions(+), 21 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 14c312ad2c03e..1c10c774b9085 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -91,37 +91,28 @@ static const int phy_all_ports_features_array[7] = {
 	ETHTOOL_LINK_MODE_Backplane_BIT,
 };
 
-const int phy_10_100_features_array[4] = {
+static const int phy_10_100_features_array[4] = {
 	ETHTOOL_LINK_MODE_10baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_10baseT_Full_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 };
-EXPORT_SYMBOL_GPL(phy_10_100_features_array);
 
-const int phy_basic_t1_features_array[3] = {
+static const int phy_basic_t1_features_array[3] = {
 	ETHTOOL_LINK_MODE_TP_BIT,
 	ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
 	ETHTOOL_LINK_MODE_100baseT1_Full_BIT,
 };
-EXPORT_SYMBOL_GPL(phy_basic_t1_features_array);
 
-const int phy_basic_t1s_p2mp_features_array[2] = {
+static const int phy_basic_t1s_p2mp_features_array[2] = {
 	ETHTOOL_LINK_MODE_TP_BIT,
 	ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT,
 };
-EXPORT_SYMBOL_GPL(phy_basic_t1s_p2mp_features_array);
 
-const int phy_gbit_features_array[2] = {
+static const int phy_gbit_features_array[2] = {
 	ETHTOOL_LINK_MODE_1000baseT_Half_BIT,
 	ETHTOOL_LINK_MODE_1000baseT_Full_BIT,
 };
-EXPORT_SYMBOL_GPL(phy_gbit_features_array);
-
-const int phy_10gbit_features_array[1] = {
-	ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
-};
-EXPORT_SYMBOL_GPL(phy_10gbit_features_array);
 
 static const int phy_eee_cap1_features_array[] = {
 	ETHTOOL_LINK_MODE_100baseT_Full_BIT,
@@ -196,9 +187,8 @@ static void features_init(void)
 	linkmode_set_bit_array(phy_gbit_features_array,
 			       ARRAY_SIZE(phy_gbit_features_array),
 			       phy_10gbit_features);
-	linkmode_set_bit_array(phy_10gbit_features_array,
-			       ARRAY_SIZE(phy_10gbit_features_array),
-			       phy_10gbit_features);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT,
+			 phy_10gbit_features);
 
 	linkmode_set_bit_array(phy_eee_cap1_features_array,
 			       ARRAY_SIZE(phy_eee_cap1_features_array),
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 245578ed710e1..104c0b4899919 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -54,11 +54,6 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init;
 #define PHY_EEE_CAP2_FEATURES ((unsigned long *)&phy_eee_cap2_features)
 
 extern const int phy_basic_ports_array[3];
-extern const int phy_10_100_features_array[4];
-extern const int phy_basic_t1_features_array[3];
-extern const int phy_basic_t1s_p2mp_features_array[2];
-extern const int phy_gbit_features_array[2];
-extern const int phy_10gbit_features_array[1];
 
 /*
  * Set phydev->irq to PHY_POLL if interrupts are not supported,

From ef6249e37df5eac72bacdfe0a3000b08ae153146 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 22:50:02 +0100
Subject: [PATCH 0585/2753] net: phy: stop exporting phy_queue_state_machine

phy_queue_state_machine() isn't used outside phy.c,
so stop exporting it.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/16986d3d-7baf-4b02-a641-e2916d491264@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c | 4 ++--
 include/linux/phy.h   | 1 -
 2 files changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 347ad1b644978..29fb19bb712b0 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -520,12 +520,12 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
  * @phydev: the phy_device struct
  * @jiffies: Run the state machine after these jiffies
  */
-void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies)
+static void phy_queue_state_machine(struct phy_device *phydev,
+				    unsigned long jiffies)
 {
 	mod_delayed_work(system_power_efficient_wq, &phydev->state_queue,
 			 jiffies);
 }
-EXPORT_SYMBOL(phy_queue_state_machine);
 
 /**
  * phy_trigger_machine - Trigger the state machine to run now
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 104c0b4899919..2ab83d24a5733 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2071,7 +2071,6 @@ int phy_drivers_register(struct phy_driver *new_driver, int n,
 			 struct module *owner);
 void phy_error(struct phy_device *phydev);
 void phy_state_machine(struct work_struct *work);
-void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies);
 void phy_trigger_machine(struct phy_device *phydev);
 void phy_mac_interrupt(struct phy_device *phydev);
 void phy_start_machine(struct phy_device *phydev);

From 6b2edfba74696e0defd181989c9effe911e6f54f Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Feb 2025 22:51:53 +0100
Subject: [PATCH 0586/2753] net: phy: remove helper phy_is_internal

Helper phy_is_internal() is just used in two places phylib-internally.
So let's remove it from the API.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/f3f35265-80a9-4ed7-ad78-ae22c21e288b@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy.c        | 2 +-
 drivers/net/phy/phy_device.c | 2 +-
 include/linux/phy.h          | 9 ---------
 3 files changed, 2 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 29fb19bb712b0..f2086b0b7b76e 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -302,7 +302,7 @@ void phy_ethtool_ksettings_get(struct phy_device *phydev,
 		cmd->base.port = PORT_BNC;
 	else
 		cmd->base.port = phydev->port;
-	cmd->base.transceiver = phy_is_internal(phydev) ?
+	cmd->base.transceiver = phydev->is_internal ?
 				XCVR_INTERNAL : XCVR_EXTERNAL;
 	cmd->base.phy_address = phydev->mdio.addr;
 	cmd->base.autoneg = phydev->autoneg;
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 1c10c774b9085..35ec99b4dc510 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -544,7 +544,7 @@ phy_interface_show(struct device *dev, struct device_attribute *attr, char *buf)
 	struct phy_device *phydev = to_phy_device(dev);
 	const char *mode = NULL;
 
-	if (phy_is_internal(phydev))
+	if (phydev->is_internal)
 		mode = "internal";
 	else
 		mode = phy_modes(phydev->interface);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 2ab83d24a5733..3665cdd610a3d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1739,15 +1739,6 @@ static inline bool phy_is_default_hwtstamp(struct phy_device *phydev)
 	return phy_has_hwtstamp(phydev) && phydev->default_timestamp;
 }
 
-/**
- * phy_is_internal - Convenience function for testing if a PHY is internal
- * @phydev: the phy_device struct
- */
-static inline bool phy_is_internal(struct phy_device *phydev)
-{
-	return phydev->is_internal;
-}
-
 /**
  * phy_on_sfp - Convenience function for testing if a PHY is on an SFP module
  * @phydev: the phy_device struct

From bf1b8e0abc39b01091995e10163c0592b4d8a296 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Thu, 13 Feb 2025 19:15:34 +0000
Subject: [PATCH 0587/2753] documentation: networking: Add NAPI config

Document the existence of persistent per-NAPI configuration space and
the API that drivers can opt into.

Update stale documentation which suggested that NAPI IDs cannot be
queried from userspace.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Link: https://patch.msgid.link/20250213191535.38792-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/napi.rst | 33 ++++++++++++++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index f970a2be271a0..d0e3953cae6ab 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -171,12 +171,43 @@ a channel as an IRQ/NAPI which services queues of a given type. For example,
 a configuration of 1 ``rx``, 1 ``tx`` and 1 ``combined`` channel is expected
 to utilize 3 interrupts, 2 Rx and 2 Tx queues.
 
+Persistent NAPI config
+----------------------
+
+Drivers often allocate and free NAPI instances dynamically. This leads to loss
+of NAPI-related user configuration each time NAPI instances are reallocated.
+The netif_napi_add_config() API prevents this loss of configuration by
+associating each NAPI instance with a persistent NAPI configuration based on
+a driver defined index value, like a queue number.
+
+Using this API allows for persistent NAPI IDs (among other settings), which can
+be beneficial to userspace programs using ``SO_INCOMING_NAPI_ID``. See the
+sections below for other NAPI configuration settings.
+
+Drivers should try to use netif_napi_add_config() whenever possible.
+
 User API
 ========
 
 User interactions with NAPI depend on NAPI instance ID. The instance IDs
 are only visible to the user thru the ``SO_INCOMING_NAPI_ID`` socket option.
-It's not currently possible to query IDs used by a given device.
+
+Users can query NAPI IDs for a device or device queue using netlink. This can
+be done programmatically in a user application or by using a script included in
+the kernel source tree: ``tools/net/ynl/pyynl/cli.py``.
+
+For example, using the script to dump all of the queues for a device (which
+will reveal each queue's NAPI ID):
+
+.. code-block:: bash
+
+   $ kernel-source/tools/net/ynl/pyynl/cli.py \
+             --spec Documentation/netlink/specs/netdev.yaml \
+             --dump queue-get \
+             --json='{"ifindex": 2}'
+
+See ``Documentation/netlink/specs/netdev.yaml`` for more details on
+available operations and attributes.
 
 Software IRQ coalescing
 -----------------------

From de38503b74e28c47e28ed800d2a8d12c713b2c63 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 13 Feb 2025 17:54:19 +0000
Subject: [PATCH 0588/2753] net: remove phylink_pcs .neg_mode boolean

As all PCS are using the neg_mode parameter rather than the legacy
an_mode, remove the ability to use the legacy an_mode. We remove the
tests in the phylink code, unconditionally passing the PCS neg_mode
parameter to PCS methods, and remove setting the flag from drivers.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tidPn-0040hd-2R@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_serdes.c              |  1 -
 drivers/net/dsa/mt7530.c                      |  1 -
 drivers/net/dsa/mv88e6xxx/pcs-6185.c          |  1 -
 drivers/net/dsa/mv88e6xxx/pcs-6352.c          |  1 -
 drivers/net/dsa/mv88e6xxx/pcs-639x.c          |  4 ---
 drivers/net/dsa/qca/qca8k-8xxx.c              |  1 -
 drivers/net/ethernet/cadence/macb_main.c      |  2 --
 .../net/ethernet/freescale/fman/fman_dtsec.c  |  1 -
 drivers/net/ethernet/marvell/mvneta.c         |  1 -
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   |  2 --
 .../ethernet/marvell/prestera/prestera_main.c |  1 -
 .../net/ethernet/meta/fbnic/fbnic_phylink.c   |  1 -
 .../ethernet/microchip/lan966x/lan966x_main.c |  1 -
 .../ethernet/microchip/sparx5/sparx5_main.c   |  1 -
 .../net/ethernet/xilinx/xilinx_axienet_main.c |  1 -
 drivers/net/pcs/pcs-lynx.c                    |  1 -
 drivers/net/pcs/pcs-mtk-lynxi.c               |  1 -
 drivers/net/pcs/pcs-rzn1-miic.c               |  1 -
 drivers/net/pcs/pcs-xpcs.c                    |  1 -
 drivers/net/phy/phylink.c                     | 30 ++++---------------
 include/linux/phylink.h                       |  2 --
 21 files changed, 5 insertions(+), 51 deletions(-)

diff --git a/drivers/net/dsa/b53/b53_serdes.c b/drivers/net/dsa/b53/b53_serdes.c
index 4730982b68400..7460122f6abca 100644
--- a/drivers/net/dsa/b53/b53_serdes.c
+++ b/drivers/net/dsa/b53/b53_serdes.c
@@ -239,7 +239,6 @@ int b53_serdes_init(struct b53_device *dev, int port)
 	pcs->dev = dev;
 	pcs->lane = lane;
 	pcs->pcs.ops = &b53_pcs_ops;
-	pcs->pcs.neg_mode = true;
 
 	return 0;
 }
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 9fd44e55d5196..8422262febaf7 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -3104,7 +3104,6 @@ mt753x_setup(struct dsa_switch *ds)
 	/* Initialise the PCS devices */
 	for (i = 0; i < priv->ds->num_ports; i++) {
 		priv->pcs[i].pcs.ops = priv->info->pcs_ops;
-		priv->pcs[i].pcs.neg_mode = true;
 		priv->pcs[i].priv = priv;
 		priv->pcs[i].port = i;
 	}
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6185.c b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
index 75ed1fa500a5c..af7e06d265f7b 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-6185.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6185.c
@@ -138,7 +138,6 @@ static int mv88e6185_pcs_init(struct mv88e6xxx_chip *chip, int port)
 	mpcs->chip = chip;
 	mpcs->port = port;
 	mpcs->phylink_pcs.ops = &mv88e6185_phylink_pcs_ops;
-	mpcs->phylink_pcs.neg_mode = true;
 
 	irq = mv88e6xxx_serdes_irq_mapping(chip, port);
 	if (irq) {
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-6352.c b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
index 143fe21d18349..36993400837ea 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-6352.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-6352.c
@@ -275,7 +275,6 @@ static struct marvell_c22_pcs *marvell_c22_pcs_alloc(struct device *dev,
 	mpcs->mdio.bus = bus;
 	mpcs->mdio.addr = addr;
 	mpcs->phylink_pcs.ops = &marvell_c22_pcs_ops;
-	mpcs->phylink_pcs.neg_mode = true;
 
 	return mpcs;
 }
diff --git a/drivers/net/dsa/mv88e6xxx/pcs-639x.c b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
index 59f63d6beec85..5db17c0b77f5b 100644
--- a/drivers/net/dsa/mv88e6xxx/pcs-639x.c
+++ b/drivers/net/dsa/mv88e6xxx/pcs-639x.c
@@ -565,9 +565,7 @@ static int mv88e6390_pcs_init(struct mv88e6xxx_chip *chip, int port)
 		return -ENOMEM;
 
 	mpcs->sgmii_pcs.ops = &mv88e639x_sgmii_pcs_ops;
-	mpcs->sgmii_pcs.neg_mode = true;
 	mpcs->xg_pcs.ops = &mv88e6390_xg_pcs_ops;
-	mpcs->xg_pcs.neg_mode = true;
 
 	if (chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6190X ||
 	    chip->info->prod_num == MV88E6XXX_PORT_SWITCH_ID_PROD_6390X)
@@ -945,9 +943,7 @@ static int mv88e6393x_pcs_init(struct mv88e6xxx_chip *chip, int port)
 		return -ENOMEM;
 
 	mpcs->sgmii_pcs.ops = &mv88e6393x_sgmii_pcs_ops;
-	mpcs->sgmii_pcs.neg_mode = true;
 	mpcs->xg_pcs.ops = &mv88e6393x_xg_pcs_ops;
-	mpcs->xg_pcs.neg_mode = true;
 	mpcs->supports_5g = true;
 
 	err = mv88e6393x_erratum_4_6(mpcs);
diff --git a/drivers/net/dsa/qca/qca8k-8xxx.c b/drivers/net/dsa/qca/qca8k-8xxx.c
index e8cb4da15dbe4..a36b8b07030e3 100644
--- a/drivers/net/dsa/qca/qca8k-8xxx.c
+++ b/drivers/net/dsa/qca/qca8k-8xxx.c
@@ -1634,7 +1634,6 @@ static void qca8k_setup_pcs(struct qca8k_priv *priv, struct qca8k_pcs *qpcs,
 			    int port)
 {
 	qpcs->pcs.ops = &qca8k_pcs_ops;
-	qpcs->pcs.neg_mode = true;
 
 	/* We don't have interrupts for link changes, so we need to poll */
 	qpcs->pcs.poll = true;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 48496209fb164..4db61372a78e5 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -853,9 +853,7 @@ static int macb_mii_probe(struct net_device *dev)
 	struct macb *bp = netdev_priv(dev);
 
 	bp->phylink_sgmii_pcs.ops = &macb_phylink_pcs_ops;
-	bp->phylink_sgmii_pcs.neg_mode = true;
 	bp->phylink_usx_pcs.ops = &macb_phylink_usx_pcs_ops;
-	bp->phylink_usx_pcs.neg_mode = true;
 
 	bp->phylink_config.dev = &dev->dev;
 	bp->phylink_config.type = PHYLINK_NETDEV;
diff --git a/drivers/net/ethernet/freescale/fman/fman_dtsec.c b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
index b3e2a596ad2c8..51402dff72c5f 100644
--- a/drivers/net/ethernet/freescale/fman/fman_dtsec.c
+++ b/drivers/net/ethernet/freescale/fman/fman_dtsec.c
@@ -1446,7 +1446,6 @@ int dtsec_initialization(struct mac_device *mac_dev,
 		goto _return_fm_mac_free;
 	}
 	dtsec->pcs.ops = &dtsec_pcs_ops;
-	dtsec->pcs.neg_mode = true;
 	dtsec->pcs.poll = true;
 
 	supported = mac_dev->phylink_config.supported_interfaces;
diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 4fe121b9f94b6..44b18c5739092 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -5557,7 +5557,6 @@ static int mvneta_probe(struct platform_device *pdev)
 		clk_prepare_enable(pp->clk_bus);
 
 	pp->phylink_pcs.ops = &mvneta_phylink_pcs_ops;
-	pp->phylink_pcs.neg_mode = true;
 
 	pp->phylink_config.dev = &dev->dev;
 	pp->phylink_config.type = PHYLINK_NETDEV;
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index dd76c1b7ed3a1..f166dc4e65037 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7024,9 +7024,7 @@ static int mvpp2_port_probe(struct platform_device *pdev,
 	dev->dev_port = port->id;
 
 	port->pcs_gmac.ops = &mvpp2_phylink_gmac_pcs_ops;
-	port->pcs_gmac.neg_mode = true;
 	port->pcs_xlg.ops = &mvpp2_phylink_xlg_pcs_ops;
-	port->pcs_xlg.neg_mode = true;
 
 	if (!mvpp2_use_acpi_compat_mode(port_fwnode)) {
 		port->phylink_config.dev = &dev->dev;
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 440a4c42b405f..8cdecf61253cc 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -396,7 +396,6 @@ static int prestera_port_sfp_bind(struct prestera_port *port)
 			continue;
 
 		port->phylink_pcs.ops = &prestera_pcs_ops;
-		port->phylink_pcs.neg_mode = true;
 
 		port->phy_config.dev = &port->dev->dev;
 		port->phy_config.type = PHYLINK_NETDEV;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
index bb11fc83367d8..860b02b22c15e 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_phylink.c
@@ -133,7 +133,6 @@ int fbnic_phylink_init(struct net_device *netdev)
 	struct fbnic_net *fbn = netdev_priv(netdev);
 	struct phylink *phylink;
 
-	fbn->phylink_pcs.neg_mode = true;
 	fbn->phylink_pcs.ops = &fbnic_phylink_pcs_ops;
 
 	fbn->phylink_config.dev = &netdev->dev;
diff --git a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
index 3234a960fcc30..0af143ec0f869 100644
--- a/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
+++ b/drivers/net/ethernet/microchip/lan966x/lan966x_main.c
@@ -828,7 +828,6 @@ static int lan966x_probe_port(struct lan966x *lan966x, u32 p,
 	port->phylink_config.type = PHYLINK_NETDEV;
 	port->phylink_pcs.poll = true;
 	port->phylink_pcs.ops = &lan966x_phylink_pcs_ops;
-	port->phylink_pcs.neg_mode = true;
 
 	port->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000FD | MAC_2500FD;
diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
index 6a0e5b83ecd07..74ad1d73b4652 100644
--- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
+++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c
@@ -338,7 +338,6 @@ static int sparx5_create_port(struct sparx5 *sparx5,
 	spx5_port->custom_etype = 0x8880; /* Vitesse */
 	spx5_port->phylink_pcs.poll = true;
 	spx5_port->phylink_pcs.ops = &sparx5_phylink_pcs_ops;
-	spx5_port->phylink_pcs.neg_mode = true;
 	spx5_port->is_mrouter = false;
 	INIT_LIST_HEAD(&spx5_port->tc_templates);
 	sparx5->ports[config->portno] = spx5_port;
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 0673b2694e4cb..2ffaad0b0477f 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -3073,7 +3073,6 @@ static int axienet_probe(struct platform_device *pdev)
 		}
 		of_node_put(np);
 		lp->pcs.ops = &axienet_pcs_ops;
-		lp->pcs.neg_mode = true;
 		lp->pcs.poll = true;
 	}
 
diff --git a/drivers/net/pcs/pcs-lynx.c b/drivers/net/pcs/pcs-lynx.c
index e46f588cae7d3..23b40e9eacbbc 100644
--- a/drivers/net/pcs/pcs-lynx.c
+++ b/drivers/net/pcs/pcs-lynx.c
@@ -355,7 +355,6 @@ static struct phylink_pcs *lynx_pcs_create(struct mdio_device *mdio)
 	mdio_device_get(mdio);
 	lynx->mdio = mdio;
 	lynx->pcs.ops = &lynx_pcs_phylink_ops;
-	lynx->pcs.neg_mode = true;
 	lynx->pcs.poll = true;
 
 	for (i = 0; i < ARRAY_SIZE(lynx_interfaces); i++)
diff --git a/drivers/net/pcs/pcs-mtk-lynxi.c b/drivers/net/pcs/pcs-mtk-lynxi.c
index 7d6261dee5340..149ddf51d7856 100644
--- a/drivers/net/pcs/pcs-mtk-lynxi.c
+++ b/drivers/net/pcs/pcs-mtk-lynxi.c
@@ -305,7 +305,6 @@ struct phylink_pcs *mtk_pcs_lynxi_create(struct device *dev,
 	mpcs->regmap = regmap;
 	mpcs->flags = flags;
 	mpcs->pcs.ops = &mtk_pcs_lynxi_ops;
-	mpcs->pcs.neg_mode = true;
 	mpcs->pcs.poll = true;
 	mpcs->interface = PHY_INTERFACE_MODE_NA;
 
diff --git a/drivers/net/pcs/pcs-rzn1-miic.c b/drivers/net/pcs/pcs-rzn1-miic.c
index a808ac7375f5d..d79bb9b06cd22 100644
--- a/drivers/net/pcs/pcs-rzn1-miic.c
+++ b/drivers/net/pcs/pcs-rzn1-miic.c
@@ -349,7 +349,6 @@ struct phylink_pcs *miic_create(struct device *dev, struct device_node *np)
 	miic_port->miic = miic;
 	miic_port->port = port - 1;
 	miic_port->pcs.ops = &miic_phylink_ops;
-	miic_port->pcs.neg_mode = true;
 
 	phy_interface_set_rgmii(miic_port->pcs.supported_interfaces);
 	__set_bit(PHY_INTERFACE_MODE_RMII, miic_port->pcs.supported_interfaces);
diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index ee0c1a27f06ce..e32dec4b812ec 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -1403,7 +1403,6 @@ static struct dw_xpcs *xpcs_create_data(struct mdio_device *mdiodev)
 	mdio_device_get(mdiodev);
 	xpcs->mdiodev = mdiodev;
 	xpcs->pcs.ops = &xpcs_phylink_ops;
-	xpcs->pcs.neg_mode = true;
 	xpcs->pcs.poll = true;
 
 	return xpcs;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 046ec8dda1598..a3b186ab38546 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -1365,7 +1365,6 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 	struct phylink_pcs *pcs = NULL;
 	bool pcs_changed = false;
 	unsigned int rate_kbd;
-	unsigned int neg_mode;
 	int err;
 
 	phylink_dbg(pl, "major config, requested %s/%s\n",
@@ -1428,11 +1427,7 @@ static void phylink_major_config(struct phylink *pl, bool restart,
 	if (pl->pcs_state == PCS_STATE_STARTING || pcs_changed)
 		phylink_pcs_enable(pl->pcs);
 
-	neg_mode = pl->act_link_an_mode;
-	if (pl->pcs && pl->pcs->neg_mode)
-		neg_mode = pl->pcs_neg_mode;
-
-	err = phylink_pcs_config(pl->pcs, neg_mode, state,
+	err = phylink_pcs_config(pl->pcs, pl->pcs_neg_mode, state,
 				 !!(pl->link_config.pause & MLO_PAUSE_AN));
 	if (err < 0)
 		phylink_err(pl, "pcs_config failed: %pe\n",
@@ -1475,7 +1470,6 @@ static void phylink_major_config(struct phylink *pl, bool restart,
  */
 static int phylink_change_inband_advert(struct phylink *pl)
 {
-	unsigned int neg_mode;
 	int ret;
 
 	if (test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state))
@@ -1491,15 +1485,11 @@ static int phylink_change_inband_advert(struct phylink *pl)
 	phylink_pcs_neg_mode(pl, pl->pcs, pl->link_config.interface,
 			     pl->link_config.advertising);
 
-	neg_mode = pl->act_link_an_mode;
-	if (pl->pcs->neg_mode)
-		neg_mode = pl->pcs_neg_mode;
-
 	/* Modern PCS-based method; update the advert at the PCS, and
 	 * restart negotiation if the pcs_config() helper indicates that
 	 * the programmed advertisement has changed.
 	 */
-	ret = phylink_pcs_config(pl->pcs, neg_mode, &pl->link_config,
+	ret = phylink_pcs_config(pl->pcs, pl->pcs_neg_mode, &pl->link_config,
 				 !!(pl->link_config.pause & MLO_PAUSE_AN));
 	if (ret < 0)
 		return ret;
@@ -1523,13 +1513,7 @@ static void phylink_mac_pcs_get_state(struct phylink *pl,
 	state->an_complete = 0;
 	state->link = 1;
 
-	pcs = pl->pcs;
-	if (!pcs || pcs->neg_mode)
-		autoneg = pl->pcs_neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED;
-	else
-		autoneg = linkmode_test_bit(ETHTOOL_LINK_MODE_Autoneg_BIT,
-					    state->advertising);
-
+	autoneg = pl->pcs_neg_mode == PHYLINK_PCS_NEG_INBAND_ENABLED;
 	if (autoneg) {
 		state->speed = SPEED_UNKNOWN;
 		state->duplex = DUPLEX_UNKNOWN;
@@ -1540,6 +1524,7 @@ static void phylink_mac_pcs_get_state(struct phylink *pl,
 		state->pause = pl->link_config.pause;
 	}
 
+	pcs = pl->pcs;
 	if (pcs)
 		pcs->ops->pcs_get_state(pcs, pl->pcs_neg_mode, state);
 	else
@@ -1649,7 +1634,6 @@ static void phylink_link_up(struct phylink *pl,
 			    struct phylink_link_state link_state)
 {
 	struct net_device *ndev = pl->netdev;
-	unsigned int neg_mode;
 	int speed, duplex;
 	bool rx_pause;
 
@@ -1680,11 +1664,7 @@ static void phylink_link_up(struct phylink *pl,
 
 	pl->cur_interface = link_state.interface;
 
-	neg_mode = pl->act_link_an_mode;
-	if (pl->pcs && pl->pcs->neg_mode)
-		neg_mode = pl->pcs_neg_mode;
-
-	phylink_pcs_link_up(pl->pcs, neg_mode, pl->cur_interface, speed,
+	phylink_pcs_link_up(pl->pcs, pl->pcs_neg_mode, pl->cur_interface, speed,
 			    duplex);
 
 	pl->mac_ops->mac_link_up(pl->config, pl->phydev, pl->act_link_an_mode,
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 41ab85e591ad6..08df65f6867a6 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -442,7 +442,6 @@ struct phylink_pcs_ops;
  *                        are supported by this PCS.
  * @ops: a pointer to the &struct phylink_pcs_ops structure
  * @phylink: pointer to &struct phylink_config
- * @neg_mode: provide PCS neg mode via "mode" argument
  * @poll: poll the PCS for link changes
  * @rxc_always_on: The MAC driver requires the reference clock
  *                 to always be on. Standalone PCS drivers which
@@ -459,7 +458,6 @@ struct phylink_pcs {
 	DECLARE_PHY_INTERFACE_MASK(supported_interfaces);
 	const struct phylink_pcs_ops *ops;
 	struct phylink *phylink;
-	bool neg_mode;
 	bool poll;
 	bool rxc_always_on;
 };

From c2ddb619fa8d535af968965181656c20a6de3f81 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Thu, 13 Feb 2025 09:31:41 +0300
Subject: [PATCH 0589/2753] ice: Fix signedness bug in
 ice_init_interrupt_scheme()

If pci_alloc_irq_vectors() can't allocate the minimum number of vectors
then it returns -ENOSPC so there is no need to check for that in the
caller.  In fact, because pf->msix.min is an unsigned int, it means that
any negative error codes are type promoted to high positive values and
treated as success.  So here, the "return -ENOMEM;" is unreachable code.
Check for negatives instead.

Now that we're only dealing with error codes, it's easier to propagate
the error code from pci_alloc_irq_vectors() instead of hardcoding
-ENOMEM.

Fixes: 79d97b8cf9a8 ("ice: remove splitting MSI-X between features")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/b16e4f01-4c85-46e2-b602-fce529293559@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_irq.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_irq.c b/drivers/net/ethernet/intel/ice/ice_irq.c
index cbae3d81f0f1d..30801fd375f01 100644
--- a/drivers/net/ethernet/intel/ice/ice_irq.c
+++ b/drivers/net/ethernet/intel/ice/ice_irq.c
@@ -149,8 +149,8 @@ int ice_init_interrupt_scheme(struct ice_pf *pf)
 
 	vectors = pci_alloc_irq_vectors(pf->pdev, pf->msix.min, vectors,
 					PCI_IRQ_MSIX);
-	if (vectors < pf->msix.min)
-		return -ENOMEM;
+	if (vectors < 0)
+		return vectors;
 
 	ice_init_irq_tracker(pf, pf->msix.max, vectors);
 

From 0025fa45253c266eb3424d0f21e240c8c420894a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 12 Feb 2025 21:01:42 +0100
Subject: [PATCH 0590/2753] net: phy: c45: improve handling of disabled EEE
 modes in generic ethtool functions

Currently disabled EEE modes are shown as supported in ethtool.
Change this by filtering them out when populating data->supported
in genphy_c45_ethtool_get_eee.
Disabled EEE modes are silently filtered out by genphy_c45_write_eee_adv.
This is planned to be removed, therefore ensure in
genphy_c45_ethtool_set_eee that disabled EEE modes are removed from the
user space provided EEE advertisement. For now keep the current behavior
to do this silently.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/5187c86d-9a5a-482c-974f-cc103ce9738c@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 468d246113a4b..dedbdcab83a59 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1525,8 +1525,8 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 		return ret;
 
 	data->eee_active = phydev->eee_active;
-	linkmode_copy(data->supported, phydev->supported_eee);
-
+	linkmode_andnot(data->supported, phydev->supported_eee,
+			phydev->eee_disabled_modes);
 	return 0;
 }
 EXPORT_SYMBOL(genphy_c45_ethtool_get_eee);
@@ -1559,7 +1559,9 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 				phydev_warn(phydev, "At least some EEE link modes are not supported.\n");
 				return -EINVAL;
 			}
-			linkmode_copy(phydev->advertising_eee, adv);
+
+			linkmode_andnot(phydev->advertising_eee, adv,
+					phydev->eee_disabled_modes);
 		} else if (linkmode_empty(phydev->advertising_eee)) {
 			phy_advertise_eee_all(phydev);
 		}

From 4a6f18f28627e121bd1f74b5fcc9f945d6dbeb1e Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 10 Feb 2025 09:45:05 -0800
Subject: [PATCH 0591/2753] net/mlx4_core: Avoid impossible mlx4_db_alloc()
 order value

GCC can see that the value range for "order" is capped, but this leads
it to consider that it might be negative, leading to a false positive
warning (with GCC 15 with -Warray-bounds -fdiagnostics-details):

../drivers/net/ethernet/mellanox/mlx4/alloc.c:691:47: error: array subscript -1 is below array bounds of 'long unsigned int *[2]' [-Werror=array-bounds=]
  691 |                 i = find_first_bit(pgdir->bits[o], MLX4_DB_PER_PAGE >> o);
      |                                    ~~~~~~~~~~~^~~
  'mlx4_alloc_db_from_pgdir': events 1-2
  691 |                 i = find_first_bit(pgdir->bits[o], MLX4_DB_PER_PAGE >> o);                        |                     ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
      |                     |                         |                                                   |                     |                         (2) out of array bounds here
      |                     (1) when the condition is evaluated to true                             In file included from ../drivers/net/ethernet/mellanox/mlx4/mlx4.h:53,
                 from ../drivers/net/ethernet/mellanox/mlx4/alloc.c:42:
../include/linux/mlx4/device.h:664:33: note: while referencing 'bits'
  664 |         unsigned long          *bits[2];
      |                                 ^~~~

Switch the argument to unsigned int, which removes the compiler needing
to consider negative values.

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250210174504.work.075-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/alloc.c | 6 +++---
 include/linux/mlx4/device.h                | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/alloc.c b/drivers/net/ethernet/mellanox/mlx4/alloc.c
index 598df63518c55..07b061a97a6ed 100644
--- a/drivers/net/ethernet/mellanox/mlx4/alloc.c
+++ b/drivers/net/ethernet/mellanox/mlx4/alloc.c
@@ -660,9 +660,9 @@ static struct mlx4_db_pgdir *mlx4_alloc_db_pgdir(struct device *dma_device)
 }
 
 static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
-				    struct mlx4_db *db, int order)
+				    struct mlx4_db *db, unsigned int order)
 {
-	int o;
+	unsigned int o;
 	int i;
 
 	for (o = order; o <= 1; ++o) {
@@ -690,7 +690,7 @@ static int mlx4_alloc_db_from_pgdir(struct mlx4_db_pgdir *pgdir,
 	return 0;
 }
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order)
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_db_pgdir *pgdir;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 87edb7a8173b1..f016263e1fcf0 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -1135,7 +1135,7 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		       struct mlx4_buf *buf);
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,

From ebdf7fe488c512b18add66b6c26e11e4d3830213 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:29 -0800
Subject: [PATCH 0592/2753] bnxt_en: Set NPAR 1.2 support when registering with
 firmware

NPAR (Network interface card partitioning)[1] 1.2 adds a transparent
VLAN tag for all packets between the NIC and the switch.  Because of
that, RX VLAN acceleration cannot be supported for any additional
host configured VLANs.  The driver has to acknowledge that it can
support no RX VLAN acceleration and set the NPAR 1.2 supported flag
when registering with the FW.  Otherwise, the FW call will fail and
the driver will abort on these NPAR 1.2 NICs with this error:

bnxt_en 0000:26:00.0 (unnamed net_device) (uninitialized): hwrm req_type 0x1d seq id 0xb error 0x2

[1] https://techdocs.broadcom.com/us/en/storage-and-ethernet-connectivity/ethernet-nic-controllers/bcm957xxx/adapters/introduction/features/network-partitioning-npar.html

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 5 +++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7b8b5b39c7bbe..fc870c104c560 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5565,6 +5565,8 @@ int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap, int bmap_size,
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT |
 			 FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT;
+	if (bp->fw_cap & BNXT_FW_CAP_NPAR_1_2)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT;
 	req->flags = cpu_to_le32(flags);
 	req->ver_maj_8b = DRV_VER_MAJ;
 	req->ver_min_8b = DRV_VER_MIN;
@@ -8365,6 +8367,7 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp)
 
 	switch (resp->port_partition_type) {
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0:
+	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5:
 	case FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0:
 		bp->port_partition_type = resp->port_partition_type;
@@ -9529,6 +9532,8 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp)
 		bp->fw_cap |= BNXT_FW_CAP_HOT_RESET_IF;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_LIVEPATCH;
+	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED)
+		bp->fw_cap |= BNXT_FW_CAP_NPAR_1_2;
 	if (BNXT_PF(bp) && (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED))
 		bp->fw_cap |= BNXT_FW_CAP_DFLT_VLAN_TPID_PCP;
 	if (flags_ext & FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 2373f423a523e..db0be469a3dbd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2492,6 +2492,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX_V3	BIT_ULL(39)
 	#define BNXT_FW_CAP_VNIC_RE_FLUSH		BIT_ULL(40)
 	#define BNXT_FW_CAP_SW_MAX_RESOURCE_LIMITS	BIT_ULL(41)
+	#define BNXT_FW_CAP_NPAR_1_2			BIT_ULL(42)
 
 	u32			fw_dbg_cap;
 

From 0fed290525d511348593ff91a7a361ced388912a Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:30 -0800
Subject: [PATCH 0593/2753] bnxt_en: Refactor completion ring allocation logic
 for P5_PLUS chips

Add a new bnxt_hwrm_cp_ring_alloc_p5() function to handle allocating
one completion ring on P5_PLUS chips.  This simplifies the existing code
and will be useful later in the series.

Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 44 +++++++++++------------
 1 file changed, 21 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index fc870c104c560..0e16ea823fbdb 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7199,6 +7199,25 @@ static int bnxt_hwrm_rx_agg_ring_alloc(struct bnxt *bp,
 	return 0;
 }
 
+static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp,
+				      struct bnxt_cp_ring_info *cpr)
+{
+	const u32 type = HWRM_RING_ALLOC_CMPL;
+	struct bnxt_napi *bnapi = cpr->bnapi;
+	struct bnxt_ring_struct *ring;
+	u32 map_idx = bnapi->index;
+	int rc;
+
+	ring = &cpr->cp_ring_struct;
+	ring->handle = BNXT_SET_NQ_HDL(cpr);
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &cpr->cp_db, type, map_idx, ring->fw_ring_id);
+	bnxt_db_cq(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	return 0;
+}
+
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
 	bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
@@ -7242,19 +7261,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		u32 map_idx;
 
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = txr->tx_cpr;
-			struct bnxt_napi *bnapi = txr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			map_idx = bnapi->index;
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
 		ring = &txr->tx_ring_struct;
 		map_idx = i;
@@ -7274,20 +7283,9 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		if (!agg_rings)
 			bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			struct bnxt_cp_ring_info *cpr2 = rxr->rx_cpr;
-			struct bnxt_napi *bnapi = rxr->bnapi;
-			u32 type2 = HWRM_RING_ALLOC_CMPL;
-			struct bnxt_ring_struct *ring;
-			u32 map_idx = bnapi->index;
-
-			ring = &cpr2->cp_ring_struct;
-			ring->handle = BNXT_SET_NQ_HDL(cpr2);
-			rc = hwrm_ring_alloc_send_msg(bp, ring, type2, map_idx);
+			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
 			if (rc)
 				goto err_out;
-			bnxt_set_db(bp, &cpr2->cp_db, type2, map_idx,
-				    ring->fw_ring_id);
-			bnxt_db_cq(bp, &cpr2->cp_db, cpr2->cp_raw_cons);
 		}
 	}
 

From e6ec5048565948fac968d8907616f5fd284e8ac3 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:31 -0800
Subject: [PATCH 0594/2753] bnxt_en: Refactor TX ring allocation logic

Add a new bnxt_hwrm_tx_ring_alloc() function to handle allocating
a transmit ring.  This will be useful later in the series.

Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-4-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 22 +++++++++++++++-------
 1 file changed, 15 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 0e16ea823fbdb..8ab7345acb0ac 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7218,6 +7218,20 @@ static int bnxt_hwrm_cp_ring_alloc_p5(struct bnxt *bp,
 	return 0;
 }
 
+static int bnxt_hwrm_tx_ring_alloc(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr, u32 tx_idx)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	const u32 type = HWRM_RING_ALLOC_TX;
+	int rc;
+
+	rc = hwrm_ring_alloc_send_msg(bp, ring, type, tx_idx);
+	if (rc)
+		return rc;
+	bnxt_set_db(bp, &txr->tx_db, type, tx_idx, ring->fw_ring_id);
+	return 0;
+}
+
 static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 {
 	bool agg_rings = !!(bp->flags & BNXT_FLAG_AGG_RINGS);
@@ -7254,23 +7268,17 @@ static int bnxt_hwrm_ring_alloc(struct bnxt *bp)
 		}
 	}
 
-	type = HWRM_RING_ALLOC_TX;
 	for (i = 0; i < bp->tx_nr_rings; i++) {
 		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring;
-		u32 map_idx;
 
 		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
 			rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
 			if (rc)
 				goto err_out;
 		}
-		ring = &txr->tx_ring_struct;
-		map_idx = i;
-		rc = hwrm_ring_alloc_send_msg(bp, ring, type, map_idx);
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, i);
 		if (rc)
 			goto err_out;
-		bnxt_set_db(bp, &txr->tx_db, type, map_idx, ring->fw_ring_id);
 	}
 
 	for (i = 0; i < bp->rx_nr_rings; i++) {

From f33a508c23a48b8b94a6bb9e3ffd2432bbfa3d50 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:32 -0800
Subject: [PATCH 0595/2753] bnxt_en: Refactor completion ring free routine

Add a wrapper routine to free L2 completion rings.  This will be
useful later in the series.

Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-5-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 26 ++++++++++++++---------
 1 file changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 8ab7345acb0ac..52d4dc2227592 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7405,6 +7405,20 @@ static void bnxt_hwrm_rx_agg_ring_free(struct bnxt *bp,
 	bp->grp_info[grp_idx].agg_fw_ring_id = INVALID_HW_RING_ID;
 }
 
+static void bnxt_hwrm_cp_ring_free(struct bnxt *bp,
+				   struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring;
+
+	ring = &cpr->cp_ring_struct;
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_L2_CMPL,
+				INVALID_HW_RING_ID);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
 static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 {
 	u32 type;
@@ -7450,17 +7464,9 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		struct bnxt_ring_struct *ring;
 		int j;
 
-		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++) {
-			struct bnxt_cp_ring_info *cpr2 = &cpr->cp_ring_arr[j];
+		for (j = 0; j < cpr->cp_ring_count && cpr->cp_ring_arr; j++)
+			bnxt_hwrm_cp_ring_free(bp, &cpr->cp_ring_arr[j]);
 
-			ring = &cpr2->cp_ring_struct;
-			if (ring->fw_ring_id == INVALID_HW_RING_ID)
-				continue;
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_L2_CMPL,
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
 		ring = &cpr->cp_ring_struct;
 		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
 			hwrm_ring_free_send_msg(bp, ring, type,

From 09cc58d5944155d6e12a4e02e44c87dd667f43af Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:33 -0800
Subject: [PATCH 0596/2753] bnxt_en: Refactor bnxt_free_tx_rings() to free per
 TX ring

Modify bnxt_free_tx_rings() to free the skbs per TX ring.
This will be useful later in the series.

Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-6-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 115 ++++++++++++----------
 1 file changed, 61 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 52d4dc2227592..453f526481452 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -3314,74 +3314,81 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 	return work_done;
 }
 
-static void bnxt_free_tx_skbs(struct bnxt *bp)
+static void bnxt_free_one_tx_ring_skbs(struct bnxt *bp,
+				       struct bnxt_tx_ring_info *txr, int idx)
 {
 	int i, max_idx;
 	struct pci_dev *pdev = bp->pdev;
 
-	if (!bp->tx_ring)
-		return;
-
 	max_idx = bp->tx_nr_pages * TX_DESC_CNT;
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		int j;
 
-		if (!txr->tx_buf_ring)
+	for (i = 0; i < max_idx;) {
+		struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[i];
+		struct sk_buff *skb;
+		int j, last;
+
+		if (idx  < bp->tx_nr_rings_xdp &&
+		    tx_buf->action == XDP_REDIRECT) {
+			dma_unmap_single(&pdev->dev,
+					 dma_unmap_addr(tx_buf, mapping),
+					 dma_unmap_len(tx_buf, len),
+					 DMA_TO_DEVICE);
+			xdp_return_frame(tx_buf->xdpf);
+			tx_buf->action = 0;
+			tx_buf->xdpf = NULL;
+			i++;
 			continue;
+		}
 
-		for (j = 0; j < max_idx;) {
-			struct bnxt_sw_tx_bd *tx_buf = &txr->tx_buf_ring[j];
-			struct sk_buff *skb;
-			int k, last;
-
-			if (i < bp->tx_nr_rings_xdp &&
-			    tx_buf->action == XDP_REDIRECT) {
-				dma_unmap_single(&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					dma_unmap_len(tx_buf, len),
-					DMA_TO_DEVICE);
-				xdp_return_frame(tx_buf->xdpf);
-				tx_buf->action = 0;
-				tx_buf->xdpf = NULL;
-				j++;
-				continue;
-			}
+		skb = tx_buf->skb;
+		if (!skb) {
+			i++;
+			continue;
+		}
 
-			skb = tx_buf->skb;
-			if (!skb) {
-				j++;
-				continue;
-			}
+		tx_buf->skb = NULL;
 
-			tx_buf->skb = NULL;
+		if (tx_buf->is_push) {
+			dev_kfree_skb(skb);
+			i += 2;
+			continue;
+		}
 
-			if (tx_buf->is_push) {
-				dev_kfree_skb(skb);
-				j += 2;
-				continue;
-			}
+		dma_unmap_single(&pdev->dev,
+				 dma_unmap_addr(tx_buf, mapping),
+				 skb_headlen(skb),
+				 DMA_TO_DEVICE);
 
-			dma_unmap_single(&pdev->dev,
-					 dma_unmap_addr(tx_buf, mapping),
-					 skb_headlen(skb),
-					 DMA_TO_DEVICE);
+		last = tx_buf->nr_frags;
+		i += 2;
+		for (j = 0; j < last; j++, i++) {
+			int ring_idx = i & bp->tx_ring_mask;
+			skb_frag_t *frag = &skb_shinfo(skb)->frags[j];
 
-			last = tx_buf->nr_frags;
-			j += 2;
-			for (k = 0; k < last; k++, j++) {
-				int ring_idx = j & bp->tx_ring_mask;
-				skb_frag_t *frag = &skb_shinfo(skb)->frags[k];
-
-				tx_buf = &txr->tx_buf_ring[ring_idx];
-				dma_unmap_page(
-					&pdev->dev,
-					dma_unmap_addr(tx_buf, mapping),
-					skb_frag_size(frag), DMA_TO_DEVICE);
-			}
-			dev_kfree_skb(skb);
+			tx_buf = &txr->tx_buf_ring[ring_idx];
+			dma_unmap_page(&pdev->dev,
+				       dma_unmap_addr(tx_buf, mapping),
+				       skb_frag_size(frag), DMA_TO_DEVICE);
 		}
-		netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, i));
+		dev_kfree_skb(skb);
+	}
+	netdev_tx_reset_queue(netdev_get_tx_queue(bp->dev, idx));
+}
+
+static void bnxt_free_tx_skbs(struct bnxt *bp)
+{
+	int i;
+
+	if (!bp->tx_ring)
+		return;
+
+	for (i = 0; i < bp->tx_nr_rings; i++) {
+		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
+
+		if (!txr->tx_buf_ring)
+			continue;
+
+		bnxt_free_one_tx_ring_skbs(bp, txr, i);
 	}
 }
 

From e1714de53218796087d7182b429b047392d6ba94 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:34 -0800
Subject: [PATCH 0597/2753] bnxt_en: Refactor RX/RX AGG ring parameters setup
 for P5_PLUS

There is some common code for setting up RX and RX AGG ring allocation
parameters for P5_PLUS chips.  Refactor the logic into a new function.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-7-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 58 +++++++++++------------
 1 file changed, 28 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 453f526481452..ac63d3feaa1d2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6944,6 +6944,28 @@ static void bnxt_hwrm_ring_grp_free(struct bnxt *bp)
 	hwrm_req_drop(bp, req);
 }
 
+static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
+				       struct hwrm_ring_alloc_input *req,
+				       struct bnxt_ring_struct *ring)
+{
+	struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx];
+	u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID;
+
+	if (ring_type == HWRM_RING_ALLOC_AGG) {
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
+		req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
+		req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
+		enables |= RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID;
+	} else {
+		req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
+		if (NET_IP_ALIGN == 2)
+			req->flags =
+				cpu_to_le16(RING_ALLOC_REQ_FLAGS_RX_SOP_PAD);
+	}
+	req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+	req->enables |= cpu_to_le32(enables);
+}
+
 static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 				    struct bnxt_ring_struct *ring,
 				    u32 ring_type, u32 map_index)
@@ -6995,37 +7017,13 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp,
 		break;
 	}
 	case HWRM_RING_ALLOC_RX:
-		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		req->length = cpu_to_le32(bp->rx_ring_mask + 1);
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			u16 flags = 0;
-
-			/* Association of rx ring with stats context */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_buf_size = cpu_to_le16(bp->rx_buf_use_size);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-			if (NET_IP_ALIGN == 2)
-				flags = RING_ALLOC_REQ_FLAGS_RX_SOP_PAD;
-			req->flags = cpu_to_le16(flags);
-		}
-		break;
 	case HWRM_RING_ALLOC_AGG:
-		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS) {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
-			/* Association of agg ring with rx ring */
-			grp_info = &bp->grp_info[ring->grp_idx];
-			req->rx_ring_id = cpu_to_le16(grp_info->rx_fw_ring_id);
-			req->rx_buf_size = cpu_to_le16(BNXT_RX_PAGE_SIZE);
-			req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
-			req->enables |= cpu_to_le32(
-				RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID |
-				RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID);
-		} else {
-			req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
-		}
-		req->length = cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX;
+		req->length = (ring_type == HWRM_RING_ALLOC_RX) ?
+			      cpu_to_le32(bp->rx_ring_mask + 1) :
+			      cpu_to_le32(bp->rx_agg_ring_mask + 1);
+		if (bp->flags & BNXT_FLAG_CHIP_P5_PLUS)
+			bnxt_set_rx_ring_params_p5(bp, ring_type, req, ring);
 		break;
 	case HWRM_RING_ALLOC_CMPL:
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_L2_CMPL;

From 4c8e612c9a36721e873d7ba56019706b294fa860 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:35 -0800
Subject: [PATCH 0598/2753] bnxt_en: Pass NQ ID to the FW when allocating RX/RX
 AGG rings

Newer firmware can use the NQ ring ID associated with each RX/RX AGG
ring to enable PCIe Steering Tags on P5_PLUS chips.  When allocating
RX/RX AGG rings, pass along NQ ring ID for the firmware to use.  This
information helps optimize DMA writes by directing them to the cache
closer to the CPU consuming the data, potentially improving the
processing speed.  This change is backward-compatible with older
firmware, which will simply disregard the information.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-8-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ac63d3feaa1d2..c6cf575af53f9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -6949,7 +6949,8 @@ static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
 				       struct bnxt_ring_struct *ring)
 {
 	struct bnxt_ring_grp_info *grp_info = &bp->grp_info[ring->grp_idx];
-	u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID;
+	u32 enables = RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID |
+		      RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID;
 
 	if (ring_type == HWRM_RING_ALLOC_AGG) {
 		req->ring_type = RING_ALLOC_REQ_RING_TYPE_RX_AGG;
@@ -6963,6 +6964,7 @@ static void bnxt_set_rx_ring_params_p5(struct bnxt *bp, u32 ring_type,
 				cpu_to_le16(RING_ALLOC_REQ_FLAGS_RX_SOP_PAD);
 	}
 	req->stat_ctx_id = cpu_to_le32(grp_info->fw_stats_ctx);
+	req->nq_ring_id = cpu_to_le16(grp_info->cp_fw_ring_id);
 	req->enables |= cpu_to_le32(enables);
 }
 

From 6b6bf60fc95f908b5a3b45137436eb495af414cc Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:36 -0800
Subject: [PATCH 0599/2753] bnxt_en: Reallocate RX completion ring for TPH
 support

In order to program the correct Steering Tag during an IRQ affinity
change, we need to free/re-allocate the RX completion ring during
queue_restart.  If TPH is enabled, call FW to free the Rx completion
ring and clear the ring entries in queue_stop().  Re-allocate it in
queue_start() if TPH is enabled.  Note that TPH mode is not enabled
in this patch and will be enabled later in the patch series.

While modifying bnxt_queue_start(), remove the unnecessary zeroing of
rxr->rx_next_cons.  It gets overwritten by the clone in
bnxt_queue_start().  Remove the rx_reset counter increment since
restart is not reset.  Add comment to clarify that the ring
allocations in queue_start should never fail.

Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-9-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 38 +++++++++++++++++++----
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |  2 ++
 2 files changed, 34 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index c6cf575af53f9..04980718c2871 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7426,6 +7426,19 @@ static void bnxt_hwrm_cp_ring_free(struct bnxt *bp,
 	ring->fw_ring_id = INVALID_HW_RING_ID;
 }
 
+static void bnxt_clear_one_cp_ring(struct bnxt *bp, struct bnxt_cp_ring_info *cpr)
+{
+	struct bnxt_ring_struct *ring = &cpr->cp_ring_struct;
+	int i, size = ring->ring_mem.page_size;
+
+	cpr->cp_raw_cons = 0;
+	cpr->toggle = 0;
+
+	for (i = 0; i < bp->cp_nr_pages; i++)
+		if (cpr->cp_desc_ring[i])
+			memset(cpr->cp_desc_ring[i], 0, size);
+}
+
 static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 {
 	u32 type;
@@ -15623,7 +15636,6 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr, *clone;
-	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
 	int i, rc;
 
@@ -15642,20 +15654,27 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
 	rc = bnxt_hwrm_rx_ring_alloc(bp, rxr);
 	if (rc)
 		return rc;
+
+	if (bp->tph_mode) {
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
+		if (rc)
+			goto err_free_hwrm_rx_ring;
+	}
+
 	rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr);
 	if (rc)
-		goto err_free_hwrm_rx_ring;
+		goto err_free_hwrm_cp_ring;
 
 	bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 
-	cpr = &rxr->bnapi->cp_ring;
-	cpr->sw_stats->rx.rx_resets++;
-
 	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
 		vnic = &bp->vnic_info[i];
 
@@ -15672,6 +15691,9 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	return 0;
 
+err_free_hwrm_cp_ring:
+	if (bp->tph_mode)
+		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
 err_free_hwrm_rx_ring:
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	return rc;
@@ -15696,11 +15718,15 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	cancel_work_sync(&rxr->bnapi->cp_ring.dim.work);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
-	rxr->rx_next_cons = 0;
 	page_pool_disable_direct_recycling(rxr->page_pool);
 	if (bnxt_separate_head_pool())
 		page_pool_disable_direct_recycling(rxr->head_pool);
 
+	if (bp->tph_mode) {
+		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
+		bnxt_clear_one_cp_ring(bp, rxr->rx_cpr);
+	}
+
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index db0be469a3dbd..4e20878e77149 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2410,6 +2410,8 @@ struct bnxt {
 	u8			max_q;
 	u8			num_tc;
 
+	u8			tph_mode;
+
 	unsigned int		current_interval;
 #define BNXT_TIMER_INTERVAL	HZ
 

From c8a0f7652d61dba8d7b0fee0539a0546ba78deda Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:37 -0800
Subject: [PATCH 0600/2753] bnxt_en: Refactor TX ring free logic

Add a new bnxt_hwrm_tx_ring_free() function to handle freeing a HW
transmit ring.  The new function will also be used in the next patch
to free the TX ring in queue_stop.

Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-10-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 33 +++++++++++++----------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 04980718c2871..2d0d9ac8e2c44 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -7368,6 +7368,23 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp,
 	return 0;
 }
 
+static void bnxt_hwrm_tx_ring_free(struct bnxt *bp,
+				   struct bnxt_tx_ring_info *txr,
+				   bool close_path)
+{
+	struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
+	u32 cmpl_ring_id;
+
+	if (ring->fw_ring_id == INVALID_HW_RING_ID)
+		return;
+
+	cmpl_ring_id = close_path ? bnxt_cp_ring_for_tx(bp, txr) :
+		       INVALID_HW_RING_ID;
+	hwrm_ring_free_send_msg(bp, ring, RING_FREE_REQ_RING_TYPE_TX,
+				cmpl_ring_id);
+	ring->fw_ring_id = INVALID_HW_RING_ID;
+}
+
 static void bnxt_hwrm_rx_ring_free(struct bnxt *bp,
 				   struct bnxt_rx_ring_info *rxr,
 				   bool close_path)
@@ -7447,20 +7464,8 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 	if (!bp->bnapi)
 		return;
 
-	for (i = 0; i < bp->tx_nr_rings; i++) {
-		struct bnxt_tx_ring_info *txr = &bp->tx_ring[i];
-		struct bnxt_ring_struct *ring = &txr->tx_ring_struct;
-
-		if (ring->fw_ring_id != INVALID_HW_RING_ID) {
-			u32 cmpl_ring_id = bnxt_cp_ring_for_tx(bp, txr);
-
-			hwrm_ring_free_send_msg(bp, ring,
-						RING_FREE_REQ_RING_TYPE_TX,
-						close_path ? cmpl_ring_id :
-						INVALID_HW_RING_ID);
-			ring->fw_ring_id = INVALID_HW_RING_ID;
-		}
-	}
+	for (i = 0; i < bp->tx_nr_rings; i++)
+		bnxt_hwrm_tx_ring_free(bp, &bp->tx_ring[i], close_path);
 
 	bnxt_cancel_dim(bp);
 	for (i = 0; i < bp->rx_nr_rings; i++) {

From fe96d717d38ecd8e6e8d710ebf88e82ac35a0032 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Wed, 12 Feb 2025 17:12:38 -0800
Subject: [PATCH 0601/2753] bnxt_en: Extend queue stop/start for TX rings

In order to use queue_stop/queue_start to support the new Steering
Tags, we need to free the TX ring and TX completion ring if it is a
combined channel with TX/RX sharing the same NAPI.  Otherwise
TX completions will not have the updated Steering Tag.  If TPH is
not enabled, we just stop the TX ring without freeing the TX/TX cmpl
rings.  With that we can now add napi_disable() and napi_enable()
during queue_stop()/ queue_start().  This will guarantee that NAPI
will stop processing the completion entries in case there are
additional pending entries in the completion rings after queue_stop().

There could be some NQEs sitting unprocessed while NAPI is disabled
thereby leaving the NQ unarmed.  Explicitly re-arm the NQ after
napi_enable() in queue start so that NAPI will resume properly.

Error handling in bnxt_queue_start() requires a reset.  If a TX
ring cannot be allocated or initialized properly, it will cause
TX timeout.  The reset will also free any partially allocated
rings.  We don't expect to hit this error path because re-allocating
previously reserved and allocated rings with the same parameters
should never fail.

Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-11-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 119 ++++++++++++++++++++--
 1 file changed, 110 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 2d0d9ac8e2c44..1997cdbd58018 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11279,6 +11279,78 @@ int bnxt_reserve_rings(struct bnxt *bp, bool irq_re_init)
 	return 0;
 }
 
+static void bnxt_tx_queue_stop(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int i;
+
+	bnapi = bp->bnapi[idx];
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		WRITE_ONCE(txr->dev_state, BNXT_DEV_STATE_CLOSING);
+		synchronize_net();
+
+		if (!(bnapi->flags & BNXT_NAPI_FLAG_XDP)) {
+			txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+			if (txq) {
+				__netif_tx_lock_bh(txq);
+				netif_tx_stop_queue(txq);
+				__netif_tx_unlock_bh(txq);
+			}
+		}
+
+		if (!bp->tph_mode)
+			continue;
+
+		bnxt_hwrm_tx_ring_free(bp, txr, true);
+		bnxt_hwrm_cp_ring_free(bp, txr->tx_cpr);
+		bnxt_free_one_tx_ring_skbs(bp, txr, txr->txq_index);
+		bnxt_clear_one_cp_ring(bp, txr->tx_cpr);
+	}
+}
+
+static int bnxt_tx_queue_start(struct bnxt *bp, int idx)
+{
+	struct bnxt_tx_ring_info *txr;
+	struct netdev_queue *txq;
+	struct bnxt_napi *bnapi;
+	int rc, i;
+
+	bnapi = bp->bnapi[idx];
+	/* All rings have been reserved and previously allocated.
+	 * Reallocating with the same parameters should never fail.
+	 */
+	bnxt_for_each_napi_tx(i, bnapi, txr) {
+		if (!bp->tph_mode)
+			goto start_tx;
+
+		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, txr->tx_cpr);
+		if (rc)
+			return rc;
+
+		rc = bnxt_hwrm_tx_ring_alloc(bp, txr, false);
+		if (rc)
+			return rc;
+
+		txr->tx_prod = 0;
+		txr->tx_cons = 0;
+		txr->tx_hw_cons = 0;
+start_tx:
+		WRITE_ONCE(txr->dev_state, 0);
+		synchronize_net();
+
+		if (bnapi->flags & BNXT_NAPI_FLAG_XDP)
+			continue;
+
+		txq = netdev_get_tx_queue(bp->dev, txr->txq_index);
+		if (txq)
+			netif_tx_start_queue(txq);
+	}
+
+	return 0;
+}
+
 static void bnxt_free_irq(struct bnxt *bp)
 {
 	struct bnxt_irq *irq;
@@ -15641,7 +15713,9 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr, *clone;
+	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i, rc;
 
 	rxr = &bp->rx_ring[idx];
@@ -15659,27 +15733,39 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	bnxt_copy_rx_ring(bp, rxr, clone);
 
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+
 	/* All rings have been reserved and previously allocated.
 	 * Reallocating with the same parameters should never fail.
 	 */
 	rc = bnxt_hwrm_rx_ring_alloc(bp, rxr);
 	if (rc)
-		return rc;
+		goto err_reset;
 
 	if (bp->tph_mode) {
 		rc = bnxt_hwrm_cp_ring_alloc_p5(bp, rxr->rx_cpr);
 		if (rc)
-			goto err_free_hwrm_rx_ring;
+			goto err_reset;
 	}
 
 	rc = bnxt_hwrm_rx_agg_ring_alloc(bp, rxr);
 	if (rc)
-		goto err_free_hwrm_cp_ring;
+		goto err_reset;
 
 	bnxt_db_write(bp, &rxr->rx_db, rxr->rx_prod);
 	if (bp->flags & BNXT_FLAG_AGG_RINGS)
 		bnxt_db_write(bp, &rxr->rx_agg_db, rxr->rx_agg_prod);
 
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS) {
+		rc = bnxt_tx_queue_start(bp, idx);
+		if (rc)
+			goto err_reset;
+	}
+
+	napi_enable(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
+
 	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
 		vnic = &bp->vnic_info[i];
 
@@ -15696,11 +15782,12 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 
 	return 0;
 
-err_free_hwrm_cp_ring:
-	if (bp->tph_mode)
-		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
-err_free_hwrm_rx_ring:
-	bnxt_hwrm_rx_ring_free(bp, rxr, false);
+err_reset:
+	netdev_err(bp->dev, "Unexpected HWRM error during queue start rc: %d\n",
+		   rc);
+	napi_enable(&bnapi->napi);
+	bnxt_db_nq_arm(bp, &cpr->cp_db, cpr->cp_raw_cons);
+	bnxt_reset_task(bp, true);
 	return rc;
 }
 
@@ -15708,7 +15795,9 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 {
 	struct bnxt *bp = netdev_priv(dev);
 	struct bnxt_rx_ring_info *rxr;
+	struct bnxt_cp_ring_info *cpr;
 	struct bnxt_vnic_info *vnic;
+	struct bnxt_napi *bnapi;
 	int i;
 
 	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
@@ -15720,17 +15809,29 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	/* Make sure NAPI sees that the VNIC is disabled */
 	synchronize_net();
 	rxr = &bp->rx_ring[idx];
-	cancel_work_sync(&rxr->bnapi->cp_ring.dim.work);
+	bnapi = rxr->bnapi;
+	cpr = &bnapi->cp_ring;
+	cancel_work_sync(&cpr->dim.work);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	page_pool_disable_direct_recycling(rxr->page_pool);
 	if (bnxt_separate_head_pool())
 		page_pool_disable_direct_recycling(rxr->head_pool);
 
+	if (bp->flags & BNXT_FLAG_SHARED_RINGS)
+		bnxt_tx_queue_stop(bp, idx);
+
+	/* Disable NAPI now after freeing the rings because HWRM_RING_FREE
+	 * completion is handled in NAPI to guarantee no more DMA on that ring
+	 * after seeing the completion.
+	 */
+	napi_disable(&bnapi->napi);
+
 	if (bp->tph_mode) {
 		bnxt_hwrm_cp_ring_free(bp, rxr->rx_cpr);
 		bnxt_clear_one_cp_ring(bp, rxr->rx_cpr);
 	}
+	bnxt_db_nq(bp, &cpr->cp_db, cpr->cp_raw_cons);
 
 	memcpy(qmem, rxr, sizeof(*rxr));
 	bnxt_init_rx_ring_struct(bp, qmem);

From c214410c47d6ec3128143370747d9e388bab21d7 Mon Sep 17 00:00:00 2001
From: Manoj Panicker <manoj.panicker2@amd.com>
Date: Wed, 12 Feb 2025 17:12:39 -0800
Subject: [PATCH 0602/2753] bnxt_en: Add TPH support in BNXT driver

Add TPH support to the Broadcom BNXT device driver. This allows the
driver to utilize TPH functions for retrieving and configuring Steering
Tags when changing interrupt affinity. With compatible NIC firmware,
network traffic will be tagged correctly with Steering Tags, resulting
in significant memory bandwidth savings and other advantages as
demonstrated by real network benchmarks on TPH-capable platforms.

Co-developed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Co-developed-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Wei Huang <wei.huang2@amd.com>
Signed-off-by: Manoj Panicker <manoj.panicker2@amd.com>
Reviewed-by: Ajit Khaparde <ajit.khaparde@broadcom.com>
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250213011240.1640031-12-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 106 ++++++++++++++++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt.h |   5 +
 2 files changed, 111 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1997cdbd58018..15c57a06ecaf4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -55,6 +55,8 @@
 #include <net/page_pool/helpers.h>
 #include <linux/align.h>
 #include <net/netdev_queues.h>
+#include <net/netdev_rx_queue.h>
+#include <linux/pci-tph.h>
 
 #include "bnxt_hsi.h"
 #include "bnxt.h"
@@ -76,6 +78,7 @@
 #define BNXT_DEF_MSG_ENABLE	(NETIF_MSG_DRV | NETIF_MSG_HW | \
 				 NETIF_MSG_TX_ERR)
 
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Broadcom NetXtreme network driver");
 
@@ -11351,6 +11354,83 @@ static int bnxt_tx_queue_start(struct bnxt *bp, int idx)
 	return 0;
 }
 
+static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify,
+				     const cpumask_t *mask)
+{
+	struct bnxt_irq *irq;
+	u16 tag;
+	int err;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	cpumask_copy(irq->cpu_mask, mask);
+
+	if (irq->ring_nr >= irq->bp->rx_nr_rings)
+		return;
+
+	if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+				cpumask_first(irq->cpu_mask), &tag))
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag))
+		return;
+
+	rtnl_lock();
+	if (netif_running(irq->bp->dev)) {
+		err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr);
+		if (err)
+			netdev_err(irq->bp->dev,
+				   "RX queue restart failed: err=%d\n", err);
+	}
+	rtnl_unlock();
+}
+
+static void bnxt_irq_affinity_release(struct kref *ref)
+{
+	struct irq_affinity_notify *notify =
+		container_of(ref, struct irq_affinity_notify, kref);
+	struct bnxt_irq *irq;
+
+	irq = container_of(notify, struct bnxt_irq, affinity_notify);
+
+	if (!irq->bp->tph_mode)
+		return;
+
+	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, 0)) {
+		netdev_err(irq->bp->dev,
+			   "Setting ST=0 for MSIX entry %d failed\n",
+			   irq->msix_nr);
+		return;
+	}
+}
+
+static void bnxt_release_irq_notifier(struct bnxt_irq *irq)
+{
+	irq_set_affinity_notifier(irq->vector, NULL);
+}
+
+static void bnxt_register_irq_notifier(struct bnxt *bp, struct bnxt_irq *irq)
+{
+	struct irq_affinity_notify *notify;
+
+	irq->bp = bp;
+
+	/* Nothing to do if TPH is not enabled */
+	if (!bp->tph_mode)
+		return;
+
+	/* Register IRQ affinity notifier */
+	notify = &irq->affinity_notify;
+	notify->irq = irq->vector;
+	notify->notify = bnxt_irq_affinity_notify;
+	notify->release = bnxt_irq_affinity_release;
+
+	irq_set_affinity_notifier(irq->vector, notify);
+}
+
 static void bnxt_free_irq(struct bnxt *bp)
 {
 	struct bnxt_irq *irq;
@@ -11373,11 +11453,18 @@ static void bnxt_free_irq(struct bnxt *bp)
 				free_cpumask_var(irq->cpu_mask);
 				irq->have_cpumask = 0;
 			}
+
+			bnxt_release_irq_notifier(irq);
+
 			free_irq(irq->vector, bp->bnapi[i]);
 		}
 
 		irq->requested = 0;
 	}
+
+	/* Disable TPH support */
+	pcie_disable_tph(bp->pdev);
+	bp->tph_mode = 0;
 }
 
 static int bnxt_request_irq(struct bnxt *bp)
@@ -11397,6 +11484,12 @@ static int bnxt_request_irq(struct bnxt *bp)
 #ifdef CONFIG_RFS_ACCEL
 	rmap = bp->dev->rx_cpu_rmap;
 #endif
+
+	/* Enable TPH support as part of IRQ request */
+	rc = pcie_enable_tph(bp->pdev, PCI_TPH_ST_IV_MODE);
+	if (!rc)
+		bp->tph_mode = PCI_TPH_ST_IV_MODE;
+
 	for (i = 0, j = 0; i < bp->cp_nr_rings; i++) {
 		int map_idx = bnxt_cp_num_to_irq_num(bp, i);
 		struct bnxt_irq *irq = &bp->irq_tbl[map_idx];
@@ -11420,8 +11513,11 @@ static int bnxt_request_irq(struct bnxt *bp)
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
 			int numa_node = dev_to_node(&bp->pdev->dev);
+			u16 tag;
 
 			irq->have_cpumask = 1;
+			irq->msix_nr = map_idx;
+			irq->ring_nr = i;
 			cpumask_set_cpu(cpumask_local_spread(i, numa_node),
 					irq->cpu_mask);
 			rc = irq_update_affinity_hint(irq->vector, irq->cpu_mask);
@@ -11431,6 +11527,16 @@ static int bnxt_request_irq(struct bnxt *bp)
 					    irq->vector);
 				break;
 			}
+
+			bnxt_register_irq_notifier(bp, irq);
+
+			/* Init ST table entry */
+			if (pcie_tph_get_cpu_st(irq->bp->pdev, TPH_MEM_TYPE_VM,
+						cpumask_first(irq->cpu_mask),
+						&tag))
+				continue;
+
+			pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag);
 		}
 	}
 	return rc;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 4e20878e77149..e85b5ce94f587 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -1234,6 +1234,11 @@ struct bnxt_irq {
 	u8		have_cpumask:1;
 	char		name[IFNAMSIZ + BNXT_IRQ_NAME_EXTRA];
 	cpumask_var_t	cpu_mask;
+
+	struct bnxt	*bp;
+	int		msix_nr;
+	int		ring_nr;
+	struct irq_affinity_notify affinity_notify;
 };
 
 #define HWRM_RING_ALLOC_TX	0x1

From 1e988c3fe1264708f4f92109203ac5b1d65de50b Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Fri, 14 Feb 2025 22:48:15 +0000
Subject: [PATCH 0603/2753] io_uring: prevent opcode speculation

sqe->opcode is used for different tables, make sure we santitise it
against speculations.

Cc: stable@vger.kernel.org
Fixes: d3656344fea03 ("io_uring: add lookup table for various opcode needs")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Link: https://lore.kernel.org/r/7eddbf31c8ca0a3947f8ed98271acc2b4349c016.1739568408.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/io_uring.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 263e504be4a8b..29a42365a4816 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -2045,6 +2045,8 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req,
 		req->opcode = 0;
 		return io_init_fail_req(req, -EINVAL);
 	}
+	opcode = array_index_nospec(opcode, IORING_OP_LAST);
+
 	def = &io_issue_defs[opcode];
 	if (unlikely(sqe_flags & ~SQE_COMMON_FLAGS)) {
 		/* enforce forwards compatibility on users */

From 0784d83df3bfc977c13252a0599be924f0afa68d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 14 Feb 2025 14:07:05 +0000
Subject: [PATCH 0604/2753] ndisc: ndisc_send_redirect() cleanup

ndisc_send_redirect() is always called under rcu_read_lock().

It can use dev_net_rcu() and avoid one redundant
rcu_read_lock()/rcu_read_unlock() pair.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214140705.2105890-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ndisc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 8699d1a188dc4..ecb5c4b8518fd 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1680,7 +1680,7 @@ static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
 void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 {
 	struct net_device *dev = skb->dev;
-	struct net *net = dev_net(dev);
+	struct net *net = dev_net_rcu(dev);
 	struct sock *sk = net->ipv6.ndisc_sk;
 	int optlen = 0;
 	struct inet_peer *peer;
@@ -1695,8 +1695,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 	   ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
 	bool ret;
 
-	if (netif_is_l3_master(skb->dev)) {
-		dev = dev_get_by_index_rcu(dev_net(skb->dev), IPCB(skb)->iif);
+	if (netif_is_l3_master(dev)) {
+		dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
 		if (!dev)
 			return;
 	}
@@ -1734,10 +1734,8 @@ void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
 		goto release;
 	}
 
-	rcu_read_lock();
 	peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr);
 	ret = inet_peer_xrlim_allow(peer, 1*HZ);
-	rcu_read_unlock();
 
 	if (!ret)
 		goto release;

From ef24989a62eefa6293a6c1c59dbb8b7e646e76dd Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 13 Feb 2025 17:44:43 +0100
Subject: [PATCH 0605/2753] drm/msm/a6xx: Only print the GMU firmware version
 once

We only fetch it once from userland, so let's also only notify the
user once and not on every runtime resume.

As you can notice by the tags chain, more than one user found this
annoying.

Reported-by: Jens Glathe <jens.glathe@oldschoolsolutions.biz>
Suggested-by: Abel Vesa <abel.vesa@linaro.org>
Suggested-by: Rob Clark <robdclark@chromium.org>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/637062/
Signed-off-by: Rob Clark <robdclark@chromium.org>
---
 drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
index 65d38b25c0707..699b0dd34b18f 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gmu.c
@@ -813,10 +813,10 @@ static int a6xx_gmu_fw_load(struct a6xx_gmu *gmu)
 	}
 
 	ver = gmu_read(gmu, REG_A6XX_GMU_CORE_FW_VERSION);
-	DRM_INFO("Loaded GMU firmware v%u.%u.%u\n",
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
-		 FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
+	DRM_INFO_ONCE("Loaded GMU firmware v%u.%u.%u\n",
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MAJOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_MINOR__MASK, ver),
+		      FIELD_GET(A6XX_GMU_CORE_FW_VERSION_STEP__MASK, ver));
 
 	return 0;
 }

From 669c285620231786fffe9d87ab432e08a6ed922b Mon Sep 17 00:00:00 2001
From: Rob Clark <robdclark@chromium.org>
Date: Mon, 13 Jan 2025 07:48:41 -0800
Subject: [PATCH 0606/2753] drm/msm: Avoid rounding up to one jiffy

If userspace is trying to achieve a timeout of zero, let 'em have it.
Only round up if the timeout is greater than zero.

Fixes: 4969bccd5f4e ("drm/msm: Avoid rounding down to zero jiffies")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Reviewed-by: Akhil P Oommen <quic_akhilpo@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/632264/
---
 drivers/gpu/drm/msm/msm_drv.h | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index fee31680a6d54..a650778552017 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -537,15 +537,12 @@ static inline int align_pitch(int width, int bpp)
 static inline unsigned long timeout_to_jiffies(const ktime_t *timeout)
 {
 	ktime_t now = ktime_get();
-	s64 remaining_jiffies;
 
-	if (ktime_compare(*timeout, now) < 0) {
-		remaining_jiffies = 0;
-	} else {
-		ktime_t rem = ktime_sub(*timeout, now);
-		remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
-	}
+	if (ktime_compare(*timeout, now) <= 0)
+		return 0;
 
+	ktime_t rem = ktime_sub(*timeout, now);
+	s64 remaining_jiffies = ktime_divns(rem, NSEC_PER_SEC / HZ);
 	return clamp(remaining_jiffies, 1LL, (s64)INT_MAX);
 }
 

From 2f69e54584475ac85ea0e3407c9198ac7c6ea8ad Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 14 Dec 2024 00:14:17 +0200
Subject: [PATCH 0607/2753] drm/msm/dpu: skip watchdog timer programming
 through TOP on >= SM8450

The SM8450 and later chips have DPU_MDP_PERIPH_0_REMOVED feature bit
set, which means that those platforms have dropped some of the
registers, including the WD TIMER-related ones. Stop providing the
callback to program WD timer on those platforms.

Fixes: 100d7ef6995d ("drm/msm/dpu: add support for SM8450")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/628874/
Link: https://lore.kernel.org/r/20241214-dpu-drop-features-v1-1-988f0662cb7e@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
index ad19330de61ab..562a3f4c5238a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_top.c
@@ -272,7 +272,7 @@ static void _setup_mdp_ops(struct dpu_hw_mdp_ops *ops,
 
 	if (cap & BIT(DPU_MDP_VSYNC_SEL))
 		ops->setup_vsync_source = dpu_hw_setup_vsync_sel;
-	else
+	else if (!(cap & BIT(DPU_MDP_PERIPH_0_REMOVED)))
 		ops->setup_vsync_source = dpu_hw_setup_wd_timer;
 
 	ops->get_safe_status = dpu_hw_get_safe_status;

From af0a4a2090cce732c70ad6c5f4145b43f39e3fe9 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Sat, 14 Dec 2024 00:14:18 +0200
Subject: [PATCH 0608/2753] drm/msm/dpu: enable DPU_WB_INPUT_CTRL for DPU 5.x

Several DPU 5.x platforms are supposed to be using DPU_WB_INPUT_CTRL,
to bind WB and PINGPONG blocks, but they do not. Change those platforms
to use WB_SM8250_MASK, which includes that bit.

Fixes: 1f5bcc4316b3 ("drm/msm/dpu: enable writeback on SC8108X")
Fixes: ab2b03d73a66 ("drm/msm/dpu: enable writeback on SM6125")
Fixes: 47cebb740a83 ("drm/msm/dpu: enable writeback on SM8150")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/628876/
Link: https://lore.kernel.org/r/20241214-dpu-drop-features-v1-2-988f0662cb7e@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h  | 2 +-
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h | 2 +-
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h  | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
index 421afacb72480..36cc9dbc00b5c 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_0_sm8150.h
@@ -297,7 +297,7 @@ static const struct dpu_wb_cfg sm8150_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
index 641023b102bf5..e8eacdb47967a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_1_sc8180x.h
@@ -304,7 +304,7 @@ static const struct dpu_wb_cfg sc8180x_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
index d039b96beb97c..76f60a2df7a89 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_4_sm6125.h
@@ -144,7 +144,7 @@ static const struct dpu_wb_cfg sm6125_wb[] = {
 	{
 		.name = "wb_2", .id = WB_2,
 		.base = 0x65000, .len = 0x2c8,
-		.features = WB_SDM845_MASK,
+		.features = WB_SM8250_MASK,
 		.format_list = wb2_formats_rgb,
 		.num_formats = ARRAY_SIZE(wb2_formats_rgb),
 		.clk_ctrl = DPU_CLK_CTRL_WB2,

From 24b50b7340ab7e7b004ee6db43d625caa68498b0 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Tue, 17 Dec 2024 14:35:40 +0200
Subject: [PATCH 0609/2753] drm/msm/dpu: correct LM pairing for SM6150

The SM6150 platform doesn't have 3DMux (MERGE_3D) block, so it can not
split the screen between two LMs. Drop lm_pair fields as they don't make
sense for this platform.

Suggested-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Fixes: cb2f9144693b ("drm/msm/dpu: Add SM6150 support")
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/629377/
Link: https://lore.kernel.org/r/20241217-dpu-fix-sm6150-v2-1-9acc8f5addf3@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
index 621a2140f675f..d761ed705bac3 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/catalog/dpu_5_3_sm6150.h
@@ -116,14 +116,12 @@ static const struct dpu_lm_cfg sm6150_lm[] = {
 		.sblk = &sdm845_lm_sblk,
 		.pingpong = PINGPONG_0,
 		.dspp = DSPP_0,
-		.lm_pair = LM_1,
 	}, {
 		.name = "lm_1", .id = LM_1,
 		.base = 0x45000, .len = 0x320,
 		.features = MIXER_QCM2290_MASK,
 		.sblk = &sdm845_lm_sblk,
 		.pingpong = PINGPONG_1,
-		.lm_pair = LM_0,
 	}, {
 		.name = "lm_2", .id = LM_2,
 		.base = 0x46000, .len = 0x320,

From df9cf852ca3099feb8fed781bdd5d3863af001c8 Mon Sep 17 00:00:00 2001
From: Abhinav Kumar <quic_abhinavk@quicinc.com>
Date: Thu, 6 Feb 2025 11:46:36 -0800
Subject: [PATCH 0610/2753] drm/msm/dp: account for widebus and yuv420 during
 mode validation

Widebus allows the DP controller to operate in 2 pixel per clock mode.
The mode validation logic validates the mode->clock against the max
DP pixel clock. However the max DP pixel clock limit assumes widebus
is already enabled. Adjust the mode validation logic to only compare
the adjusted pixel clock which accounts for widebus against the max DP
pixel clock. Also fix the mode validation logic for YUV420 modes as in
that case as well, only half the pixel clock is needed.

Cc: stable@vger.kernel.org
Fixes: 757a2f36ab09 ("drm/msm/dp: enable widebus feature for display port")
Fixes: 6db6e5606576 ("drm/msm/dp: change clock related programming for YUV420 over DP")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Tested-by: Dale Whinham <daleyo@gmail.com>
Patchwork: https://patchwork.freedesktop.org/patch/635789/
Link: https://lore.kernel.org/r/20250206-dp-widebus-fix-v2-1-cb89a0313286@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dp/dp_display.c | 11 ++++++-----
 drivers/gpu/drm/msm/dp/dp_drm.c     |  5 ++++-
 2 files changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
index d852e7a853348..a129e26c3ddb3 100644
--- a/drivers/gpu/drm/msm/dp/dp_display.c
+++ b/drivers/gpu/drm/msm/dp/dp_display.c
@@ -930,16 +930,17 @@ enum drm_mode_status msm_dp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
-		return MODE_CLOCK_HIGH;
-
 	msm_dp_display = container_of(dp, struct msm_dp_display_private, msm_dp_display);
 	link_info = &msm_dp_display->panel->link_info;
 
-	if (drm_mode_is_420_only(&dp->connector->display_info, mode) &&
-	    msm_dp_display->panel->vsc_sdp_supported)
+	if ((drm_mode_is_420_only(&dp->connector->display_info, mode) &&
+	     msm_dp_display->panel->vsc_sdp_supported) ||
+	     msm_dp_wide_bus_available(dp))
 		mode_pclk_khz /= 2;
 
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
+		return MODE_CLOCK_HIGH;
+
 	mode_bpp = dp->connector->display_info.bpc * num_components;
 	if (!mode_bpp)
 		mode_bpp = default_bpp;
diff --git a/drivers/gpu/drm/msm/dp/dp_drm.c b/drivers/gpu/drm/msm/dp/dp_drm.c
index d3e241ea69416..16b7913d1eefa 100644
--- a/drivers/gpu/drm/msm/dp/dp_drm.c
+++ b/drivers/gpu/drm/msm/dp/dp_drm.c
@@ -257,7 +257,10 @@ static enum drm_mode_status msm_edp_bridge_mode_valid(struct drm_bridge *bridge,
 		return -EINVAL;
 	}
 
-	if (mode->clock > DP_MAX_PIXEL_CLK_KHZ)
+	if (msm_dp_wide_bus_available(dp))
+		mode_pclk_khz /= 2;
+
+	if (mode_pclk_khz > DP_MAX_PIXEL_CLK_KHZ)
 		return MODE_CLOCK_HIGH;
 
 	/*

From 978ca99d6bd87b84ff7788eea4d2c328a70530f6 Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Sun, 9 Feb 2025 22:51:54 -0500
Subject: [PATCH 0611/2753] drm/msm/dpu: Fix uninitialized variable

There is a possibility for an uninitialized *ret* variable to be
returned in some code paths.

Fix this by initializing *ret* to 0.

Addresses-Coverity-ID: 1642546 ("Uninitialized scalar variable")
Fixes: 774bcfb73176 ("drm/msm/dpu: add support for virtual planes")
Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/636201/
Link: https://lore.kernel.org/r/20250209-dpu-v2-1-114dfd4ebefd@ethancedwards.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 098abc2c0003c..af3e541f60c30 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -1164,7 +1164,6 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state,
 			       unsigned int num_planes)
 {
 	unsigned int i;
-	int ret;
 
 	for (i = 0; i < num_planes; i++) {
 		struct drm_plane_state *plane_state = states[i];
@@ -1173,13 +1172,13 @@ int dpu_assign_plane_resources(struct dpu_global_state *global_state,
 		    !plane_state->visible)
 			continue;
 
-		ret = dpu_plane_virtual_assign_resources(crtc, global_state,
+		int ret = dpu_plane_virtual_assign_resources(crtc, global_state,
 							 state, plane_state);
 		if (ret)
-			break;
+			return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static void dpu_plane_flush_csc(struct dpu_plane *pdpu, struct dpu_sw_pipe *pipe)

From f063ac6b55df03ed25996bdc84d9e1c50147cfa1 Mon Sep 17 00:00:00 2001
From: Jessica Zhang <quic_jesszhan@quicinc.com>
Date: Tue, 11 Feb 2025 19:59:19 -0800
Subject: [PATCH 0612/2753] drm/msm/dpu: Disable dither in phys encoder cleanup

Disable pingpong dither in dpu_encoder_helper_phys_cleanup().

This avoids the issue where an encoder unknowingly uses dither after
reserving a pingpong block that was previously bound to an encoder that
had enabled dither.

Cc: stable@vger.kernel.org
Reported-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Closes: https://lore.kernel.org/all/jr7zbj5w7iq4apg3gofuvcwf4r2swzqjk7sshwcdjll4mn6ctt@l2n3qfpujg3q/
Signed-off-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Fixes: 3c128638a07d ("drm/msm/dpu: add support for dither block in display")
Patchwork: https://patchwork.freedesktop.org/patch/636517/
Link: https://lore.kernel.org/r/20250211-dither-disable-v1-1-ac2cb455f6b9@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
index 5172ab4dea995..48e6e8d74c855 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
@@ -2281,6 +2281,9 @@ void dpu_encoder_helper_phys_cleanup(struct dpu_encoder_phys *phys_enc)
 		}
 	}
 
+	if (phys_enc->hw_pp && phys_enc->hw_pp->ops.setup_dither)
+		phys_enc->hw_pp->ops.setup_dither(phys_enc->hw_pp, NULL);
+
 	/* reset the merge 3D HW block */
 	if (phys_enc->hw_pp && phys_enc->hw_pp->merge_3d) {
 		phys_enc->hw_pp->merge_3d->ops.setup_3d_mode(phys_enc->hw_pp->merge_3d,

From 144429831f447223253a0e4376489f84ff37d1a7 Mon Sep 17 00:00:00 2001
From: Marijn Suijten <marijn.suijten@somainline.org>
Date: Tue, 11 Feb 2025 00:19:32 +0100
Subject: [PATCH 0613/2753] drm/msm/dpu: Don't leak bits_per_component into
 random DSC_ENC fields

What used to be the input_10_bits boolean - feeding into the lowest
bit of DSC_ENC - on MSM downstream turned into an accidental OR with
the full bits_per_component number when it was ported to the upstream
kernel.

On typical bpc=8 setups we don't notice this because line_buf_depth is
always an odd value (it contains bpc+1) and will also set the 4th bit
after left-shifting by 3 (hence this |= bits_per_component is a no-op).

Now that guards are being removed to allow more bits_per_component
values besides 8 (possible since commit 49fd30a7153b ("drm/msm/dsi: use
DRM DSC helpers for DSC setup")), a bpc of 10 will instead clash with
the 5th bit which is convert_rgb.  This is "fortunately" also always set
to true by MSM's dsi_populate_dsc_params() already, but once a bpc of 12
starts being used it'll write into simple_422 which is normally false.

To solve all these overlaps, simply replicate downstream code and only
set this lowest bit if bits_per_component is equal to 10.  It is unclear
why DSC requires this only for bpc=10 but not bpc=12, and also notice
that this lowest bit wasn't set previously despite having a panel and
patch on the list using it without any mentioned issues.

Fixes: c110cfd1753e ("drm/msm/disp/dpu1: Add support for DSC")
Signed-off-by: Marijn Suijten <marijn.suijten@somainline.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/636311/
Link: https://lore.kernel.org/r/20250211-dsc-10-bit-v1-1-1c85a9430d9a@somainline.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
index 657200401f576..cec6d4e8baec4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_dsc.c
@@ -52,6 +52,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	u32 slice_last_group_size;
 	u32 det_thresh_flatness;
 	bool is_cmd_mode = !(mode & DSC_MODE_VIDEO);
+	bool input_10_bits = dsc->bits_per_component == 10;
 
 	DPU_REG_WRITE(c, DSC_COMMON_MODE, mode);
 
@@ -68,7 +69,7 @@ static void dpu_hw_dsc_config(struct dpu_hw_dsc *hw_dsc,
 	data |= (dsc->line_buf_depth << 3);
 	data |= (dsc->simple_422 << 2);
 	data |= (dsc->convert_rgb << 1);
-	data |= dsc->bits_per_component;
+	data |= input_10_bits;
 
 	DPU_REG_WRITE(c, DSC_ENC, data);
 

From 5e192eefebaab5bdcf716add8910d7f8a2e30e3c Mon Sep 17 00:00:00 2001
From: Jessica Zhang <quic_jesszhan@quicinc.com>
Date: Wed, 8 Jan 2025 14:40:48 -0800
Subject: [PATCH 0614/2753] drm/msm/dpu: Drop extraneous return in
 dpu_crtc_reassign_planes()

Drop extra return at the end of dpu_crtc_reassign_planes()

Fixes: 774bcfb73176 ("drm/msm/dpu: add support for virtual planes")
Signed-off-by: Jessica Zhang <quic_jesszhan@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/631565/
Link: https://lore.kernel.org/r/20250108-virtual-planes-fixes-v1-2-420cb36df94a@quicinc.com
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index 7191b1a6d41b3..e5dcd41a361f4 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -1228,8 +1228,6 @@ static int dpu_crtc_reassign_planes(struct drm_crtc *crtc, struct drm_crtc_state
 done:
 	kfree(states);
 	return ret;
-
-	return 0;
 }
 
 static int dpu_crtc_atomic_check(struct drm_crtc *crtc,

From 588257897058a0b1aa47912db4fe93c6ff5e3887 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:41 +0100
Subject: [PATCH 0615/2753] drm/msm/dsi/phy: Protect PHY_CMN_CLK_CFG0 updated
 from driver side

PHY_CMN_CLK_CFG0 register is updated by the PHY driver and by two
divider clocks from Common Clock Framework:
devm_clk_hw_register_divider_parent_hw().  Concurrent access by the
clocks side is protected with spinlock, however driver's side in
restoring state is not.  Restoring state is called from
msm_dsi_phy_enable(), so there could be a path leading to concurrent and
conflicting updates with clock framework.

Add missing lock usage on the PHY driver side, encapsulated in its own
function so the code will be still readable.

While shuffling the code, define and use PHY_CMN_CLK_CFG0 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Patchwork: https://patchwork.freedesktop.org/patch/637376/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-1-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c          | 14 ++++++++++++--
 .../gpu/drm/msm/registers/display/dsi_phy_7nm.xml  |  5 ++++-
 2 files changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 031446c87daec..25ca649de717e 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -372,6 +372,15 @@ static void dsi_pll_enable_pll_bias(struct dsi_pll_7nm *pll)
 	ndelay(250);
 }
 
+static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pll->postdiv_lock, flags);
+	writel(val, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
+	spin_unlock_irqrestore(&pll->postdiv_lock, flags);
+}
+
 static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
 {
 	u32 data;
@@ -574,8 +583,9 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 	val |= cached->pll_out_div;
 	writel(val, pll_7nm->phy->pll_base + REG_DSI_7nm_PHY_PLL_PLL_OUTDIV_RATE);
 
-	writel(cached->bit_clk_div | (cached->pix_clk_div << 4),
-	       phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG0);
+	dsi_pll_cmn_clk_cfg0_write(pll_7nm,
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) |
+				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div));
 
 	val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
 	val &= ~0x3;
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index d54b72f924493..e0bf6e016b4ce 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -9,7 +9,10 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x00004" name="REVISION_ID1"/>
 	<reg32 offset="0x00008" name="REVISION_ID2"/>
 	<reg32 offset="0x0000c" name="REVISION_ID3"/>
-	<reg32 offset="0x00010" name="CLK_CFG0"/>
+	<reg32 offset="0x00010" name="CLK_CFG0">
+		<bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/>
+		<bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/>
+	</reg32>
 	<reg32 offset="0x00014" name="CLK_CFG1"/>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>

From 5a97bc924ae0804b8dbf627e357acaa5ef761483 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:42 +0100
Subject: [PATCH 0616/2753] drm/msm/dsi/phy: Protect PHY_CMN_CLK_CFG1 against
 clock driver

PHY_CMN_CLK_CFG1 register is updated by the PHY driver and by a mux
clock from Common Clock Framework:
devm_clk_hw_register_mux_parent_hws().  There could be a path leading to
concurrent and conflicting updates between PHY driver and clock
framework, e.g. changing the mux and enabling PLL clocks.

Add dedicated spinlock to be sure all PHY_CMN_CLK_CFG1 updates are
synchronized.

While shuffling the code, define and use PHY_CMN_CLK_CFG1 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/637378/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-2-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c     | 35 ++++++++++++-------
 .../drm/msm/registers/display/dsi_phy_7nm.xml |  5 ++-
 2 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 25ca649de717e..388017db45d80 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -83,6 +83,9 @@ struct dsi_pll_7nm {
 	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG0 register */
 	spinlock_t postdiv_lock;
 
+	/* protects REG_DSI_7nm_PHY_CMN_CLK_CFG1 register */
+	spinlock_t pclk_mux_lock;
+
 	struct pll_7nm_cached_state cached_state;
 
 	struct dsi_pll_7nm *slave;
@@ -381,22 +384,32 @@ static void dsi_pll_cmn_clk_cfg0_write(struct dsi_pll_7nm *pll, u32 val)
 	spin_unlock_irqrestore(&pll->postdiv_lock, flags);
 }
 
-static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+static void dsi_pll_cmn_clk_cfg1_update(struct dsi_pll_7nm *pll, u32 mask,
+					u32 val)
 {
+	unsigned long flags;
 	u32 data;
 
+	spin_lock_irqsave(&pll->pclk_mux_lock, flags);
 	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data & ~BIT(5), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	data &= ~mask;
+	data |= val & mask;
+
+	writel(data, pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	spin_unlock_irqrestore(&pll->pclk_mux_lock, flags);
+}
+
+static void dsi_pll_disable_global_clk(struct dsi_pll_7nm *pll)
+{
+	dsi_pll_cmn_clk_cfg1_update(pll, DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN, 0);
 }
 
 static void dsi_pll_enable_global_clk(struct dsi_pll_7nm *pll)
 {
-	u32 data;
+	u32 cfg_1 = DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN | DSI_7nm_PHY_CMN_CLK_CFG1_CLK_EN_SEL;
 
 	writel(0x04, pll->phy->base + REG_DSI_7nm_PHY_CMN_CTRL_3);
-
-	data = readl(pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	writel(data | BIT(5) | BIT(4), pll->phy->base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll, cfg_1, cfg_1);
 }
 
 static void dsi_pll_phy_dig_reset(struct dsi_pll_7nm *pll)
@@ -574,7 +587,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
 	struct pll_7nm_cached_state *cached = &pll_7nm->cached_state;
-	void __iomem *phy_base = pll_7nm->phy->base;
 	u32 val;
 	int ret;
 
@@ -586,11 +598,7 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 	dsi_pll_cmn_clk_cfg0_write(pll_7nm,
 				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_3_0(cached->bit_clk_div) |
 				   DSI_7nm_PHY_CMN_CLK_CFG0_DIV_CTRL_7_4(cached->pix_clk_div));
-
-	val = readl(phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
-	val &= ~0x3;
-	val |= cached->pll_mux;
-	writel(val, phy_base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, 0x3, cached->pll_mux);
 
 	ret = dsi_pll_7nm_vco_set_rate(phy->vco_hw,
 			pll_7nm->vco_current_rate,
@@ -743,7 +751,7 @@ static int pll_7nm_register(struct dsi_pll_7nm *pll_7nm, struct clk_hw **provide
 					pll_by_2_bit,
 				}), 2, 0, pll_7nm->phy->base +
 					REG_DSI_7nm_PHY_CMN_CLK_CFG1,
-				0, 1, 0, NULL);
+				0, 1, 0, &pll_7nm->pclk_mux_lock);
 		if (IS_ERR(hw)) {
 			ret = PTR_ERR(hw);
 			goto fail;
@@ -788,6 +796,7 @@ static int dsi_pll_7nm_init(struct msm_dsi_phy *phy)
 	pll_7nm_list[phy->id] = pll_7nm;
 
 	spin_lock_init(&pll_7nm->postdiv_lock);
+	spin_lock_init(&pll_7nm->pclk_mux_lock);
 
 	pll_7nm->phy = phy;
 
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index e0bf6e016b4ce..cfaf78c028b13 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -13,7 +13,10 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 		<bitfield name="DIV_CTRL_3_0" low="0" high="3" type="uint"/>
 		<bitfield name="DIV_CTRL_7_4" low="4" high="7" type="uint"/>
 	</reg32>
-	<reg32 offset="0x00014" name="CLK_CFG1"/>
+	<reg32 offset="0x00014" name="CLK_CFG1">
+		<bitfield name="CLK_EN" pos="5" type="boolean"/>
+		<bitfield name="CLK_EN_SEL" pos="4" type="boolean"/>
+	</reg32>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>
 	<reg32 offset="0x00020" name="VREG_CTRL_0"/>

From 73f69c6be2a9f22c31c775ec03c6c286bfe12cfa Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Fri, 14 Feb 2025 16:08:43 +0100
Subject: [PATCH 0617/2753] drm/msm/dsi/phy: Do not overwite PHY_CMN_CLK_CFG1
 when choosing bitclk source

PHY_CMN_CLK_CFG1 register has four fields being used in the driver: DSI
clock divider, source of bitclk and two for enabling the DSI PHY PLL
clocks.

dsi_7nm_set_usecase() sets only the source of bitclk, so should leave
all other bits untouched.  Use newly introduced
dsi_pll_cmn_clk_cfg1_update() to update respective bits without
overwriting the rest.

While shuffling the code, define and use PHY_CMN_CLK_CFG1 bitfields to
make the code more readable and obvious.

Fixes: 1ef7c99d145c ("drm/msm/dsi: add support for 7nm DSI PHY/PLL")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Patchwork: https://patchwork.freedesktop.org/patch/637380/
Link: https://lore.kernel.org/r/20250214-drm-msm-phy-pll-cfg-reg-v3-3-0943b850722c@linaro.org
Signed-off-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
---
 drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c             | 4 ++--
 drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
index 388017db45d80..798168180c1ab 100644
--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
@@ -617,7 +617,6 @@ static int dsi_7nm_pll_restore_state(struct msm_dsi_phy *phy)
 static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 {
 	struct dsi_pll_7nm *pll_7nm = to_pll_7nm(phy->vco_hw);
-	void __iomem *base = phy->base;
 	u32 data = 0x0;	/* internal PLL */
 
 	DBG("DSI PLL%d", pll_7nm->phy->id);
@@ -636,7 +635,8 @@ static int dsi_7nm_set_usecase(struct msm_dsi_phy *phy)
 	}
 
 	/* set PLL src */
-	writel(data << 2, base + REG_DSI_7nm_PHY_CMN_CLK_CFG1);
+	dsi_pll_cmn_clk_cfg1_update(pll_7nm, DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL__MASK,
+				    DSI_7nm_PHY_CMN_CLK_CFG1_BITCLK_SEL(data));
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
index cfaf78c028b13..35f7f40e405b7 100644
--- a/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
+++ b/drivers/gpu/drm/msm/registers/display/dsi_phy_7nm.xml
@@ -16,6 +16,7 @@ xsi:schemaLocation="https://gitlab.freedesktop.org/freedreno/ rules-fd.xsd">
 	<reg32 offset="0x00014" name="CLK_CFG1">
 		<bitfield name="CLK_EN" pos="5" type="boolean"/>
 		<bitfield name="CLK_EN_SEL" pos="4" type="boolean"/>
+		<bitfield name="BITCLK_SEL" low="2" high="3" type="uint"/>
 	</reg32>
 	<reg32 offset="0x00018" name="GLBL_CTRL"/>
 	<reg32 offset="0x0001c" name="RBUF_CTRL"/>

From 579cd64b9df8a60284ec3422be919c362de40e41 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Sat, 8 Feb 2025 00:54:35 +0000
Subject: [PATCH 0618/2753] ASoC: tas2770: Fix volume scale

The scale starts at -100dB, not -128dB.

Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20250208-asoc-tas2770-v1-1-cf50ff1d59a3@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2770.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2770.c b/sound/soc/codecs/tas2770.c
index 9f93b230652a5..863c3f672ba98 100644
--- a/sound/soc/codecs/tas2770.c
+++ b/sound/soc/codecs/tas2770.c
@@ -506,7 +506,7 @@ static int tas2770_codec_probe(struct snd_soc_component *component)
 }
 
 static DECLARE_TLV_DB_SCALE(tas2770_digital_tlv, 1100, 50, 0);
-static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -12750, 50, 0);
+static DECLARE_TLV_DB_SCALE(tas2770_playback_volume, -10050, 50, 0);
 
 static const struct snd_kcontrol_new tas2770_snd_controls[] = {
 	SOC_SINGLE_TLV("Speaker Playback Volume", TAS2770_PLAY_CFG_REG2,

From 99e6ea912340d6a262a60d5dd0c87c5e7b2d6ff2 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea@microchip.com>
Date: Fri, 7 Feb 2025 13:21:45 +0100
Subject: [PATCH 0619/2753] spi: atmel-quadspi: remove references to runtime PM
 on error path
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is no need to call runtime PM put APIs on error path of
`atmel_qspi_sama7g5_transfer()` as the caller (`atmel_qspi_exec_op()`)
of it will take care of this if needed.

Fixes: 5af42209a4d2 ("spi: atmel-quadspi: Add support for sama7g5 QSPI")
Signed-off-by: Claudiu Beznea <claudiu.beznea@microchip.com>
Signed-off-by: Durai Manickam KR <durai.manickamkr@microchip.com>
Reported-by: Alexander Dahl <ada@thorsis.com>
Closes: https://lore.kernel.org/linux-spi/20250109-carat-festivity-5f088e1add3c@thorsis.com/
[ csokas.bence: Rebase and clarify msg, fix/add tags ]
Signed-off-by: Bence Csókás <csokas.bence@prolan.hu>
Link: https://patch.msgid.link/20250207122145.162183-2-csokas.bence@prolan.hu
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/atmel-quadspi.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
index d8c9be64d006a..244ac01068629 100644
--- a/drivers/spi/atmel-quadspi.c
+++ b/drivers/spi/atmel-quadspi.c
@@ -930,11 +930,8 @@ static int atmel_qspi_sama7g5_transfer(struct spi_mem *mem,
 
 	/* Release the chip-select. */
 	ret = atmel_qspi_reg_sync(aq);
-	if (ret) {
-		pm_runtime_mark_last_busy(&aq->pdev->dev);
-		pm_runtime_put_autosuspend(&aq->pdev->dev);
+	if (ret)
 		return ret;
-	}
 	atmel_qspi_write(QSPI_CR_LASTXFER, aq, QSPI_CR);
 
 	return atmel_qspi_wait_for_completion(aq, QSPI_SR_CSRA);

From 3d7a20f9ba7b09a35df4bdb5f0ddb2a0c8a4f39e Mon Sep 17 00:00:00 2001
From: Tudor Ambarus <tudor.ambarus@linaro.org>
Date: Thu, 13 Feb 2025 08:03:41 +0000
Subject: [PATCH 0620/2753] MAINTAINERS: add tambarus as R for Samsung SPI

I'm currently working on a Samsung SoC which includes SPI.
I'd like to be Cc'ed to further contributions and help on reviewing
them. Add me as reviewer.

Signed-off-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Acked-by: Andi Shyti <andi.shyti@kernel.org>
Reviewed-by: Sam Protsenko <semen.protsenko@linaro.org>
Link: https://patch.msgid.link/20250213-gs101-spi-r-v1-1-1e3ab8096873@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index efee40ea589f7..3a5d1d5891e74 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21075,6 +21075,7 @@ F:	include/linux/clk/samsung.h
 
 SAMSUNG SPI DRIVERS
 M:	Andi Shyti <andi.shyti@kernel.org>
+R:	Tudor Ambarus <tudor.ambarus@linaro.org>
 L:	linux-spi@vger.kernel.org
 L:	linux-samsung-soc@vger.kernel.org
 S:	Maintained

From 7103f0589ac220eac3d2b1e8411494b31b883d06 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 13:14:34 +0100
Subject: [PATCH 0621/2753] x86/microcode/AMD: Remove ugly linebreak in
 __verify_patch_section() signature

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-2-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index a5dac7f3c0a07..4a62625c311a6 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -246,8 +246,7 @@ static bool verify_equivalence_table(const u8 *buf, size_t buf_size)
  * On success, @sh_psize returns the patch size according to the section header,
  * to the caller.
  */
-static bool
-__verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
+static bool __verify_patch_section(const u8 *buf, size_t buf_size, u32 *sh_psize)
 {
 	u32 p_type, p_size;
 	const u32 *hdr;

From 3ef0740d10b005a45e8ae5b4b7b5d37bfddf63c0 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:23:47 +0100
Subject: [PATCH 0622/2753] x86/microcode/AMD: Remove unused
 save_microcode_in_initrd_amd() declarations

Commit

  a7939f016720 ("x86/microcode/amd: Cache builtin/initrd microcode early")

renamed it to save_microcode_in_initrd() and made it static. Zap the
forgotten declarations.

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-3-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c      | 2 +-
 arch/x86/kernel/cpu/microcode/internal.h | 2 --
 2 files changed, 1 insertion(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 4a62625c311a6..f831c06029948 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -517,7 +517,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
  * patch container file in initrd, traverse equivalent cpu table, look for a
  * matching microcode patch, and update, all in initrd memory in place.
  * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd_amd() -- we can call
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
  * load_microcode_amd() to save equivalent cpu table and microcode patches in
  * kernel heap memory.
  *
diff --git a/arch/x86/kernel/cpu/microcode/internal.h b/arch/x86/kernel/cpu/microcode/internal.h
index 21776c529fa97..5df621752fefa 100644
--- a/arch/x86/kernel/cpu/microcode/internal.h
+++ b/arch/x86/kernel/cpu/microcode/internal.h
@@ -100,14 +100,12 @@ extern bool force_minrev;
 #ifdef CONFIG_CPU_SUP_AMD
 void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family);
 void load_ucode_amd_ap(unsigned int family);
-int save_microcode_in_initrd_amd(unsigned int family);
 void reload_ucode_amd(unsigned int cpu);
 struct microcode_ops *init_amd_microcode(void);
 void exit_amd_microcode(void);
 #else /* CONFIG_CPU_SUP_AMD */
 static inline void load_ucode_amd_bsp(struct early_load_data *ed, unsigned int family) { }
 static inline void load_ucode_amd_ap(unsigned int family) { }
-static inline int save_microcode_in_initrd_amd(unsigned int family) { return -EINVAL; }
 static inline void reload_ucode_amd(unsigned int cpu) { }
 static inline struct microcode_ops *init_amd_microcode(void) { return NULL; }
 static inline void exit_amd_microcode(void) { }

From dc15675074dcfd79a2f10a6e39f96b0244961a01 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:46:45 +0100
Subject: [PATCH 0623/2753] x86/microcode/AMD: Merge early_apply_microcode()
 into its single callsite

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-4-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 60 +++++++++++++----------------
 1 file changed, 26 insertions(+), 34 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index f831c06029948..90f93b3ca9dbb 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -512,39 +512,6 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	return true;
 }
 
-/*
- * Early load occurs before we can vmalloc(). So we look for the microcode
- * patch container file in initrd, traverse equivalent cpu table, look for a
- * matching microcode patch, and update, all in initrd memory in place.
- * When vmalloc() is available for use later -- on 64-bit during first AP load,
- * and on 32-bit during save_microcode_in_initrd() -- we can call
- * load_microcode_amd() to save equivalent cpu table and microcode patches in
- * kernel heap memory.
- *
- * Returns true if container found (sets @desc), false otherwise.
- */
-static bool early_apply_microcode(u32 old_rev, void *ucode, size_t size)
-{
-	struct cont_desc desc = { 0 };
-	struct microcode_amd *mc;
-
-	scan_containers(ucode, size, &desc);
-
-	mc = desc.mc;
-	if (!mc)
-		return false;
-
-	/*
-	 * Allow application of the same revision to pick up SMT-specific
-	 * changes even if the revision of the other SMT thread is already
-	 * up-to-date.
-	 */
-	if (old_rev > mc->hdr.patch_id)
-		return false;
-
-	return __apply_microcode_amd(mc, desc.psize);
-}
-
 static bool get_builtin_microcode(struct cpio_data *cp)
 {
 	char fw_name[36] = "amd-ucode/microcode_amd.bin";
@@ -582,8 +549,19 @@ static bool __init find_blobs_in_containers(struct cpio_data *ret)
 	return found;
 }
 
+/*
+ * Early load occurs before we can vmalloc(). So we look for the microcode
+ * patch container file in initrd, traverse equivalent cpu table, look for a
+ * matching microcode patch, and update, all in initrd memory in place.
+ * When vmalloc() is available for use later -- on 64-bit during first AP load,
+ * and on 32-bit during save_microcode_in_initrd() -- we can call
+ * load_microcode_amd() to save equivalent cpu table and microcode patches in
+ * kernel heap memory.
+ */
 void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_eax)
 {
+	struct cont_desc desc = { };
+	struct microcode_amd *mc;
 	struct cpio_data cp = { };
 	u32 dummy;
 
@@ -597,7 +575,21 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (!find_blobs_in_containers(&cp))
 		return;
 
-	if (early_apply_microcode(ed->old_rev, cp.data, cp.size))
+	scan_containers(cp.data, cp.size, &desc);
+
+	mc = desc.mc;
+	if (!mc)
+		return;
+
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (ed->old_rev > mc->hdr.patch_id)
+		return;
+
+	if (__apply_microcode_amd(mc, desc.psize))
 		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 

From b39c387164879eef71886fc93cee5ca7dd7bf500 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 12:51:37 +0100
Subject: [PATCH 0624/2753] x86/microcode/AMD: Get rid of the
 _load_microcode_amd() forward declaration

Simply move save_microcode_in_initrd() down.

No functional changes.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-5-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 54 ++++++++++++++---------------
 1 file changed, 26 insertions(+), 28 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 90f93b3ca9dbb..adfea4d0d1297 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -593,34 +593,6 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
 }
 
-static enum ucode_state _load_microcode_amd(u8 family, const u8 *data, size_t size);
-
-static int __init save_microcode_in_initrd(void)
-{
-	unsigned int cpuid_1_eax = native_cpuid_eax(1);
-	struct cpuinfo_x86 *c = &boot_cpu_data;
-	struct cont_desc desc = { 0 };
-	enum ucode_state ret;
-	struct cpio_data cp;
-
-	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
-		return 0;
-
-	if (!find_blobs_in_containers(&cp))
-		return -EINVAL;
-
-	scan_containers(cp.data, cp.size, &desc);
-	if (!desc.mc)
-		return -EINVAL;
-
-	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
-	if (ret > UCODE_UPDATED)
-		return -EINVAL;
-
-	return 0;
-}
-early_initcall(save_microcode_in_initrd);
-
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
 					 struct ucode_patch *n,
 					 bool ignore_stepping)
@@ -1004,6 +976,32 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	return ret;
 }
 
+static int __init save_microcode_in_initrd(void)
+{
+	unsigned int cpuid_1_eax = native_cpuid_eax(1);
+	struct cpuinfo_x86 *c = &boot_cpu_data;
+	struct cont_desc desc = { 0 };
+	enum ucode_state ret;
+	struct cpio_data cp;
+
+	if (dis_ucode_ldr || c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10)
+		return 0;
+
+	if (!find_blobs_in_containers(&cp))
+		return -EINVAL;
+
+	scan_containers(cp.data, cp.size, &desc);
+	if (!desc.mc)
+		return -EINVAL;
+
+	ret = _load_microcode_amd(x86_family(cpuid_1_eax), desc.data, desc.size);
+	if (ret > UCODE_UPDATED)
+		return -EINVAL;
+
+	return 0;
+}
+early_initcall(save_microcode_in_initrd);
+
 /*
  * AMD microcode firmware naming convention, up to family 15h they are in
  * the legacy file:

From 037e81fb9d2dfe7b31fd97e5f578854e38f09887 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 13:02:32 +0100
Subject: [PATCH 0625/2753] x86/microcode/AMD: Add get_patch_level()

Put the MSR_AMD64_PATCH_LEVEL reading of the current microcode revision
the hw has, into a separate function.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20250211163648.30531-6-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 46 +++++++++++++++--------------
 1 file changed, 24 insertions(+), 22 deletions(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index adfea4d0d1297..31f90e129b083 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -145,6 +145,15 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static u32 get_patch_level(void)
+{
+	u32 rev, dummy __always_unused;
+
+	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
+
+	return rev;
+}
+
 static union cpuid_1_eax ucode_rev_to_cpuid(unsigned int val)
 {
 	union zen_patch_rev p;
@@ -483,10 +492,10 @@ static void scan_containers(u8 *ucode, size_t size, struct cont_desc *desc)
 	}
 }
 
-static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
+static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
+				  unsigned int psize)
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
-	u32 rev, dummy;
 
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
@@ -504,9 +513,8 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, unsigned int psize)
 	}
 
 	/* verify patch application was successful */
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
-	if (rev != mc->hdr.patch_id)
+	*cur_rev = get_patch_level();
+	if (*cur_rev != mc->hdr.patch_id)
 		return false;
 
 	return true;
@@ -563,11 +571,12 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	struct cont_desc desc = { };
 	struct microcode_amd *mc;
 	struct cpio_data cp = { };
-	u32 dummy;
+	u32 rev;
 
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
-	native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->old_rev, dummy);
+	rev = get_patch_level();
+	ed->old_rev = rev;
 
 	/* Needed in load_microcode_amd() */
 	ucode_cpu_info[0].cpu_sig.sig = cpuid_1_eax;
@@ -589,8 +598,8 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	if (ed->old_rev > mc->hdr.patch_id)
 		return;
 
-	if (__apply_microcode_amd(mc, desc.psize))
-		native_rdmsr(MSR_AMD64_PATCH_LEVEL, ed->new_rev, dummy);
+	if (__apply_microcode_amd(mc, &rev, desc.psize))
+		ed->new_rev = rev;
 }
 
 static inline bool patch_cpus_equivalent(struct ucode_patch *p,
@@ -692,14 +701,9 @@ static void free_cache(void)
 static struct ucode_patch *find_patch(unsigned int cpu)
 {
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	u32 rev, dummy __always_unused;
 	u16 equiv_id = 0;
 
-	/* fetch rev if not populated yet: */
-	if (!uci->cpu_sig.rev) {
-		rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-		uci->cpu_sig.rev = rev;
-	}
+	uci->cpu_sig.rev = get_patch_level();
 
 	if (x86_family(bsp_cpuid_1_eax) < 0x17) {
 		equiv_id = find_equiv_id(&equiv_table, uci->cpu_sig.sig);
@@ -722,22 +726,20 @@ void reload_ucode_amd(unsigned int cpu)
 
 	mc = p->data;
 
-	rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-
+	rev = get_patch_level();
 	if (rev < mc->hdr.patch_id) {
-		if (__apply_microcode_amd(mc, p->size))
-			pr_info_once("reload revision: 0x%08x\n", mc->hdr.patch_id);
+		if (__apply_microcode_amd(mc, &rev, p->size))
+			pr_info_once("reload revision: 0x%08x\n", rev);
 	}
 }
 
 static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
-	struct cpuinfo_x86 *c = &cpu_data(cpu);
 	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 	struct ucode_patch *p;
 
 	csig->sig = cpuid_eax(0x00000001);
-	csig->rev = c->microcode;
+	csig->rev = get_patch_level();
 
 	/*
 	 * a patch could have been loaded early, set uci->mc so that
@@ -778,7 +780,7 @@ static enum ucode_state apply_microcode_amd(int cpu)
 		goto out;
 	}
 
-	if (!__apply_microcode_amd(mc_amd, p->size)) {
+	if (!__apply_microcode_amd(mc_amd, &rev, p->size)) {
 		pr_err("CPU%d: update failed for patch_level=0x%08x\n",
 			cpu, mc_amd->hdr.patch_id);
 		return UCODE_ERROR;

From 7fb39882b20c98a9a393c244c86b56ef6933cff8 Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@gmail.com>
Date: Sun, 16 Feb 2025 11:42:09 +0100
Subject: [PATCH 0626/2753] dm-integrity: Avoid divide by zero in table status
 in Inline mode

In Inline mode, the journal is unused, and journal_sectors is zero.

Calculating the journal watermark requires dividing by journal_sectors,
which should be done only if the journal is configured.

Otherwise, a simple table query (dmsetup table) can cause OOPS.

This bug did not show on some systems, perhaps only due to
compiler optimization.

On my 32-bit testing machine, this reliably crashes with the following:

 : Oops: divide error: 0000 [#1] PREEMPT SMP
 : CPU: 0 UID: 0 PID: 2450 Comm: dmsetup Not tainted 6.14.0-rc2+ #959
 : EIP: dm_integrity_status+0x2f8/0xab0 [dm_integrity]
 ...

Signed-off-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Fixes: fb0987682c62 ("dm-integrity: introduce the Inline mode")
Cc: stable@vger.kernel.org # 6.11+
---
 drivers/md/dm-integrity.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index ee9f7cecd78e0..555dc06b94228 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3790,10 +3790,6 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE: {
-		__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
-
-		watermark_percentage += ic->journal_entries / 2;
-		do_div(watermark_percentage, ic->journal_entries);
 		arg_count = 3;
 		arg_count += !!ic->meta_dev;
 		arg_count += ic->sectors_per_block != 1;
@@ -3826,6 +3822,10 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
 		DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
 		if (ic->mode == 'J') {
+			__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
+
+			watermark_percentage += ic->journal_entries / 2;
+			do_div(watermark_percentage, ic->journal_entries);
 			DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage);
 			DMEMIT(" commit_time:%u", ic->autocommit_msec);
 		}

From c19525b5fb71a355079063bb14adcddae60cf922 Mon Sep 17 00:00:00 2001
From: Milan Broz <gmazyland@gmail.com>
Date: Sun, 16 Feb 2025 11:42:10 +0100
Subject: [PATCH 0627/2753] dm-integrity: Do not emit journal configuration in
 DM table for Inline mode

The Inline mode does not use a journal; it makes no sense to print
journal information in DM table. Print it only if the journal is used.

The same applies to interleave_sectors (unused for Inline mode).

Also, add comments for arg_count, as the current calculation
is quite obscure.

Signed-off-by: Milan Broz <gmazyland@gmail.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
---
 drivers/md/dm-integrity.c | 17 ++++++++++-------
 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 555dc06b94228..c45464b6576aa 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3790,16 +3790,18 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 		break;
 
 	case STATUSTYPE_TABLE: {
-		arg_count = 3;
+		arg_count = 1; /* buffer_sectors */
 		arg_count += !!ic->meta_dev;
 		arg_count += ic->sectors_per_block != 1;
 		arg_count += !!(ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING));
 		arg_count += ic->reset_recalculate_flag;
 		arg_count += ic->discard;
-		arg_count += ic->mode == 'J';
-		arg_count += ic->mode == 'J';
-		arg_count += ic->mode == 'B';
-		arg_count += ic->mode == 'B';
+		arg_count += ic->mode != 'I'; /* interleave_sectors */
+		arg_count += ic->mode == 'J'; /* journal_sectors */
+		arg_count += ic->mode == 'J'; /* journal_watermark */
+		arg_count += ic->mode == 'J'; /* commit_time */
+		arg_count += ic->mode == 'B'; /* sectors_per_bit */
+		arg_count += ic->mode == 'B'; /* bitmap_flush_interval */
 		arg_count += !!ic->internal_hash_alg.alg_string;
 		arg_count += !!ic->journal_crypt_alg.alg_string;
 		arg_count += !!ic->journal_mac_alg.alg_string;
@@ -3818,14 +3820,15 @@ static void dm_integrity_status(struct dm_target *ti, status_type_t type,
 			DMEMIT(" reset_recalculate");
 		if (ic->discard)
 			DMEMIT(" allow_discards");
-		DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
-		DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
+		if (ic->mode != 'I')
+			DMEMIT(" interleave_sectors:%u", 1U << ic->sb->log2_interleave_sectors);
 		DMEMIT(" buffer_sectors:%u", 1U << ic->log2_buffer_sectors);
 		if (ic->mode == 'J') {
 			__u64 watermark_percentage = (__u64)(ic->journal_entries - ic->free_sectors_threshold) * 100;
 
 			watermark_percentage += ic->journal_entries / 2;
 			do_div(watermark_percentage, ic->journal_entries);
+			DMEMIT(" journal_sectors:%u", ic->initial_sectors - SB_SECTORS);
 			DMEMIT(" journal_watermark:%u", (unsigned int)watermark_percentage);
 			DMEMIT(" commit_time:%u", ic->autocommit_msec);
 		}

From 9d846b1aebbe488f245f1aa463802ff9c34cc078 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 10 Feb 2025 11:51:55 +0100
Subject: [PATCH 0628/2753] gpiolib: check the return value of
 gpio_chip::get_direction()

As per the API contract - gpio_chip::get_direction() may fail and return
a negative error number. However, we treat it as if it always returned 0
or 1. Check the return value of the callback and propagate the error
number up the stack.

Cc: stable@vger.kernel.org
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250210-gpio-sanitize-retvals-v1-1-12ea88506cb2@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 44 ++++++++++++++++++++++++++++--------------
 1 file changed, 29 insertions(+), 15 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index ca2f58a2cd45e..29110dc436f15 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1057,8 +1057,11 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		desc->gdev = gdev;
 
 		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) {
-			assign_bit(FLAG_IS_OUT,
-				   &desc->flags, !gc->get_direction(gc, desc_index));
+			ret = gc->get_direction(gc, desc_index);
+			if (ret < 0)
+				goto err_cleanup_desc_srcu;
+
+			assign_bit(FLAG_IS_OUT, &desc->flags, !ret);
 		} else {
 			assign_bit(FLAG_IS_OUT,
 				   &desc->flags, !gc->direction_input);
@@ -2728,13 +2731,18 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 	if (guard.gc->direction_input) {
 		ret = guard.gc->direction_input(guard.gc,
 						gpio_chip_hwgpio(desc));
-	} else if (guard.gc->get_direction &&
-		  (guard.gc->get_direction(guard.gc,
-					   gpio_chip_hwgpio(desc)) != 1)) {
-		gpiod_warn(desc,
-			   "%s: missing direction_input() operation and line is output\n",
-			   __func__);
-		return -EIO;
+	} else if (guard.gc->get_direction) {
+		ret = guard.gc->get_direction(guard.gc,
+					      gpio_chip_hwgpio(desc));
+		if (ret < 0)
+			return ret;
+
+		if (ret != GPIO_LINE_DIRECTION_IN) {
+			gpiod_warn(desc,
+				   "%s: missing direction_input() operation and line is output\n",
+				    __func__);
+			return -EIO;
+		}
 	}
 	if (ret == 0) {
 		clear_bit(FLAG_IS_OUT, &desc->flags);
@@ -2771,12 +2779,18 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 						 gpio_chip_hwgpio(desc), val);
 	} else {
 		/* Check that we are in output mode if we can */
-		if (guard.gc->get_direction &&
-		    guard.gc->get_direction(guard.gc, gpio_chip_hwgpio(desc))) {
-			gpiod_warn(desc,
-				"%s: missing direction_output() operation\n",
-				__func__);
-			return -EIO;
+		if (guard.gc->get_direction) {
+			ret = guard.gc->get_direction(guard.gc,
+						      gpio_chip_hwgpio(desc));
+			if (ret < 0)
+				return ret;
+
+			if (ret != GPIO_LINE_DIRECTION_OUT) {
+				gpiod_warn(desc,
+					   "%s: missing direction_output() operation\n",
+					   __func__);
+				return -EIO;
+			}
 		}
 		/*
 		 * If we can't actively set the direction, we are some

From 4e667a1968099c6deadee2313ecd648f8f0a8956 Mon Sep 17 00:00:00 2001
From: Johan Korsnes <johan.korsnes@remarkable.no>
Date: Mon, 17 Feb 2025 10:16:43 +0100
Subject: [PATCH 0629/2753] gpio: vf610: add locking to gpio direction
 functions

Add locking to `vf610_gpio_direction_input|output()` functions. Without
this locking, a race condition exists between concurrent calls to these
functions, potentially leading to incorrect GPIO direction settings.

To verify the correctness of this fix, a `trylock` patch was applied,
where after a couple of reboots the race was confirmed. I.e., one user
had to wait before acquiring the lock. With this patch the race has not
been encountered. It's worth mentioning that any type of debugging
(printing, tracing, etc.) would "resolve"/hide the issue.

Fixes: 659d8a62311f ("gpio: vf610: add imx7ulp support")
Signed-off-by: Johan Korsnes <johan.korsnes@remarkable.no>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Haibo Chen <haibo.chen@nxp.com>
Cc: Bartosz Golaszewski <brgl@bgdev.pl>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250217091643.679644-1-johan.korsnes@remarkable.no
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-vf610.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c
index c4f34a347cb6e..c36a9dbccd4dd 100644
--- a/drivers/gpio/gpio-vf610.c
+++ b/drivers/gpio/gpio-vf610.c
@@ -36,6 +36,7 @@ struct vf610_gpio_port {
 	struct clk *clk_port;
 	struct clk *clk_gpio;
 	int irq;
+	spinlock_t lock; /* protect gpio direction registers */
 };
 
 #define GPIO_PDOR		0x00
@@ -124,6 +125,7 @@ static int vf610_gpio_direction_input(struct gpio_chip *chip, unsigned int gpio)
 	u32 val;
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val &= ~mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -142,6 +144,7 @@ static int vf610_gpio_direction_output(struct gpio_chip *chip, unsigned int gpio
 	vf610_gpio_set(chip, gpio, value);
 
 	if (port->sdata->have_paddr) {
+		guard(spinlock_irqsave)(&port->lock);
 		val = vf610_gpio_readl(port->gpio_base + GPIO_PDDR);
 		val |= mask;
 		vf610_gpio_writel(val, port->gpio_base + GPIO_PDDR);
@@ -297,6 +300,7 @@ static int vf610_gpio_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	port->sdata = device_get_match_data(dev);
+	spin_lock_init(&port->lock);
 
 	dual_base = port->sdata->have_dual_base;
 

From c7db342e3b4744688be1e27e31254c1d31a35274 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:08 +0100
Subject: [PATCH 0630/2753] riscv: KVM: Fix hart suspend status check

"Not stopped" means started or suspended so we need to check for
a single state in order to have a chance to check for each state.
Also, we need to use target_vcpu when checking for the suspend
state.

Fixes: 763c8bed8c05 ("RISC-V: KVM: Implement SBI HSM suspend call")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-8-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_hsm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index dce667f4b6ab0..13a35eb77e8e3 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -79,12 +79,12 @@ static int kvm_sbi_hsm_vcpu_get_status(struct kvm_vcpu *vcpu)
 	target_vcpu = kvm_get_vcpu_by_id(vcpu->kvm, target_vcpuid);
 	if (!target_vcpu)
 		return SBI_ERR_INVALID_PARAM;
-	if (!kvm_riscv_vcpu_stopped(target_vcpu))
-		return SBI_HSM_STATE_STARTED;
-	else if (vcpu->stat.generic.blocking)
+	if (kvm_riscv_vcpu_stopped(target_vcpu))
+		return SBI_HSM_STATE_STOPPED;
+	else if (target_vcpu->stat.generic.blocking)
 		return SBI_HSM_STATE_SUSPENDED;
 	else
-		return SBI_HSM_STATE_STOPPED;
+		return SBI_HSM_STATE_STARTED;
 }
 
 static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,

From e3219b0c491f2aa0e0b200a39d3352ab05cdda96 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:09 +0100
Subject: [PATCH 0631/2753] riscv: KVM: Fix hart suspend_type use

The spec says suspend_type is 32 bits wide and "In case the data is
defined as 32bit wide, higher privilege software must ensure that it
only uses 32 bit data." Mask off upper bits of suspend_type before
using it.

Fixes: 763c8bed8c05 ("RISC-V: KVM: Implement SBI HSM suspend call")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-9-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_hsm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index 13a35eb77e8e3..3070bb31745de 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -9,6 +9,7 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 #include <asm/sbi.h>
 #include <asm/kvm_vcpu_sbi.h>
 
@@ -109,7 +110,7 @@ static int kvm_sbi_ext_hsm_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		}
 		return 0;
 	case SBI_EXT_HSM_HART_SUSPEND:
-		switch (cp->a0) {
+		switch (lower_32_bits(cp->a0)) {
 		case SBI_HSM_SUSPEND_RET_DEFAULT:
 			kvm_riscv_vcpu_wfi(vcpu);
 			break;

From 0611f78f83c93c000029ab01daa28166d03590ed Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:10 +0100
Subject: [PATCH 0632/2753] riscv: KVM: Fix SBI IPI error generation

When an invalid function ID of an SBI extension is used we should
return not-supported, not invalid-param. Also, when we see that at
least one hartid constructed from the base and mask parameters is
invalid, then we should return invalid-param. Finally, rather than
relying on overflowing a left shift to result in zero and then using
that zero in a condition which [correctly] skips sending an IPI (but
loops unnecessarily), explicitly check for overflow and exit the loop
immediately.

Fixes: 5f862df5585c ("RISC-V: KVM: Add v0.1 replacement SBI extensions defined in v0.2")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-10-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 9c2ab3dfa93aa..74e3a38c6a29e 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -51,9 +51,10 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	unsigned long hmask = cp->a0;
 	unsigned long hbase = cp->a1;
+	unsigned long hart_bit = 0, sentmask = 0;
 
 	if (cp->a6 != SBI_EXT_IPI_SEND_IPI) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 
@@ -62,15 +63,23 @@ static int kvm_sbi_ext_ipi_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 		if (hbase != -1UL) {
 			if (tmp->vcpu_id < hbase)
 				continue;
-			if (!(hmask & (1UL << (tmp->vcpu_id - hbase))))
+			hart_bit = tmp->vcpu_id - hbase;
+			if (hart_bit >= __riscv_xlen)
+				goto done;
+			if (!(hmask & (1UL << hart_bit)))
 				continue;
 		}
 		ret = kvm_riscv_vcpu_set_interrupt(tmp, IRQ_VS_SOFT);
 		if (ret < 0)
 			break;
+		sentmask |= 1UL << hart_bit;
 		kvm_riscv_vcpu_pmu_incr_fw(tmp, SBI_PMU_FW_IPI_RCVD);
 	}
 
+done:
+	if (hbase != -1UL && (hmask ^ sentmask))
+		retdata->err_val = SBI_ERR_INVALID_PARAM;
+
 	return ret;
 }
 

From b901484852992cf3d162a5eab72251cc813ca624 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:11 +0100
Subject: [PATCH 0633/2753] riscv: KVM: Fix SBI TIME error generation

When an invalid function ID of an SBI extension is used we should
return not-supported, not invalid-param.

Fixes: 5f862df5585c ("RISC-V: KVM: Add v0.1 replacement SBI extensions defined in v0.2")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-11-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_replace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_replace.c b/arch/riscv/kvm/vcpu_sbi_replace.c
index 74e3a38c6a29e..5fbf3f94f1e85 100644
--- a/arch/riscv/kvm/vcpu_sbi_replace.c
+++ b/arch/riscv/kvm/vcpu_sbi_replace.c
@@ -21,7 +21,7 @@ static int kvm_sbi_ext_time_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 	u64 next_cycle;
 
 	if (cp->a6 != SBI_EXT_TIME_SET_TIMER) {
-		retdata->err_val = SBI_ERR_INVALID_PARAM;
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
 		return 0;
 	}
 

From 351e02b1733b057e33fe13fc03ca93ec799e4f78 Mon Sep 17 00:00:00 2001
From: Andrew Jones <ajones@ventanamicro.com>
Date: Mon, 17 Feb 2025 09:45:12 +0100
Subject: [PATCH 0634/2753] riscv: KVM: Fix SBI sleep_type use

The spec says sleep_type is 32 bits wide and "In case the data is
defined as 32bit wide, higher privilege software must ensure that it
only uses 32 bit data." Mask off upper bits of sleep_type before
using it.

Fixes: 023c15151fbb ("RISC-V: KVM: Add SBI system suspend support")
Signed-off-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Anup Patel <anup@brainfault.org>
Link: https://lore.kernel.org/r/20250217084506.18763-12-ajones@ventanamicro.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/vcpu_sbi_system.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index 5d55e08791fa1..bc0ebba890037 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/kvm_host.h>
+#include <linux/wordpart.h>
 
 #include <asm/kvm_vcpu_sbi.h>
 #include <asm/sbi.h>
@@ -19,7 +20,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 
 	switch (funcid) {
 	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
-		if (cp->a0 != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
 			retdata->err_val = SBI_ERR_INVALID_PARAM;
 			return 0;
 		}

From 539bd20352832b9244238a055eb169ccf1c41ff6 Mon Sep 17 00:00:00 2001
From: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Date: Thu, 13 Feb 2025 11:15:46 +0530
Subject: [PATCH 0635/2753] mtd: spi-nor: sst: Fix SST write failure
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

'commit 18bcb4aa54ea ("mtd: spi-nor: sst: Factor out common write operation
to `sst_nor_write_data()`")' introduced a bug where only one byte of data
is written, regardless of the number of bytes passed to
sst_nor_write_data(), causing a kernel crash during the write operation.
Ensure the correct number of bytes are written as passed to
sst_nor_write_data().

Call trace:
[   57.400180] ------------[ cut here ]------------
[   57.404842] While writing 2 byte written 1 bytes
[   57.409493] WARNING: CPU: 0 PID: 737 at drivers/mtd/spi-nor/sst.c:187 sst_nor_write_data+0x6c/0x74
[   57.418464] Modules linked in:
[   57.421517] CPU: 0 UID: 0 PID: 737 Comm: mtd_debug Not tainted 6.12.0-g5ad04afd91f9 #30
[   57.429517] Hardware name: Xilinx Versal A2197 Processor board revA - x-prc-02 revA (DT)
[   57.437600] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   57.444557] pc : sst_nor_write_data+0x6c/0x74
[   57.448911] lr : sst_nor_write_data+0x6c/0x74
[   57.453264] sp : ffff80008232bb40
[   57.456570] x29: ffff80008232bb40 x28: 0000000000010000 x27: 0000000000000001
[   57.463708] x26: 000000000000ffff x25: 0000000000000000 x24: 0000000000000000
[   57.470843] x23: 0000000000010000 x22: ffff80008232bbf0 x21: ffff000816230000
[   57.477978] x20: ffff0008056c0080 x19: 0000000000000002 x18: 0000000000000006
[   57.485112] x17: 0000000000000000 x16: 0000000000000000 x15: ffff80008232b580
[   57.492246] x14: 0000000000000000 x13: ffff8000816d1530 x12: 00000000000004a4
[   57.499380] x11: 000000000000018c x10: ffff8000816fd530 x9 : ffff8000816d1530
[   57.506515] x8 : 00000000fffff7ff x7 : ffff8000816fd530 x6 : 0000000000000001
[   57.513649] x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000
[   57.520782] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff0008049b0000
[   57.527916] Call trace:
[   57.530354]  sst_nor_write_data+0x6c/0x74
[   57.534361]  sst_nor_write+0xb4/0x18c
[   57.538019]  mtd_write_oob_std+0x7c/0x88
[   57.541941]  mtd_write_oob+0x70/0xbc
[   57.545511]  mtd_write+0x68/0xa8
[   57.548733]  mtdchar_write+0x10c/0x290
[   57.552477]  vfs_write+0xb4/0x3a8
[   57.555791]  ksys_write+0x74/0x10c
[   57.559189]  __arm64_sys_write+0x1c/0x28
[   57.563109]  invoke_syscall+0x54/0x11c
[   57.566856]  el0_svc_common.constprop.0+0xc0/0xe0
[   57.571557]  do_el0_svc+0x1c/0x28
[   57.574868]  el0_svc+0x30/0xcc
[   57.577921]  el0t_64_sync_handler+0x120/0x12c
[   57.582276]  el0t_64_sync+0x190/0x194
[   57.585933] ---[ end trace 0000000000000000 ]---

Cc: stable@vger.kernel.org
Fixes: 18bcb4aa54ea ("mtd: spi-nor: sst: Factor out common write operation to `sst_nor_write_data()`")
Signed-off-by: Amit Kumar Mahapatra <amit.kumar-mahapatra@amd.com>
Reviewed-by: Pratyush Yadav <pratyush@kernel.org>
Reviewed-by: Tudor Ambarus <tudor.ambarus@linaro.org>
Reviewed-by: Bence Csókás <csokas.bence@prolan.hu>
[pratyush@kernel.org: add Cc stable tag]
Signed-off-by: Pratyush Yadav <pratyush@kernel.org>
Link: https://lore.kernel.org/r/20250213054546.2078121-1-amit.kumar-mahapatra@amd.com
---
 drivers/mtd/spi-nor/sst.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/mtd/spi-nor/sst.c b/drivers/mtd/spi-nor/sst.c
index b5ad7118c49a2..175211fe6a5ed 100644
--- a/drivers/mtd/spi-nor/sst.c
+++ b/drivers/mtd/spi-nor/sst.c
@@ -174,7 +174,7 @@ static int sst_nor_write_data(struct spi_nor *nor, loff_t to, size_t len,
 	int ret;
 
 	nor->program_opcode = op;
-	ret = spi_nor_write_data(nor, to, 1, buf);
+	ret = spi_nor_write_data(nor, to, len, buf);
 	if (ret < 0)
 		return ret;
 	WARN(ret != len, "While writing %zu byte written %i bytes\n", len, ret);

From e49477f7f78598295551d486ecc7f020d796432e Mon Sep 17 00:00:00 2001
From: Krzysztof Karas <krzysztof.karas@intel.com>
Date: Thu, 16 Jan 2025 10:40:46 +0000
Subject: [PATCH 0636/2753] drm/i915/gt: Use spin_lock_irqsave() in
 interruptible context

spin_lock/unlock() functions used in interrupt contexts could
result in a deadlock, as seen in GitLab issue #13399,
which occurs when interrupt comes in while holding a lock.

Try to remedy the problem by saving irq state before spin lock
acquisition.

v2: add irqs' state save/restore calls to all locks/unlocks in
 signal_irq_work() execution (Maciej)

v3: use with spin_lock_irqsave() in guc_lrc_desc_unpin() instead
 of other lock/unlock calls and add Fixes and Cc tags (Tvrtko);
 change title and commit message

Fixes: 2f2cc53b5fe7 ("drm/i915/guc: Close deregister-context race against CT-loss")
Closes: https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13399
Signed-off-by: Krzysztof Karas <krzysztof.karas@intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Reviewed-by: Maciej Patelczyk <maciej.patelczyk@intel.com>
Reviewed-by: Andi Shyti <andi.shyti@linux.intel.com>
Signed-off-by: Andi Shyti <andi.shyti@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/pusppq5ybyszau2oocboj3mtj5x574gwij323jlclm5zxvimmu@mnfg6odxbpsv
(cherry picked from commit c088387ddd6482b40f21ccf23db1125e8fa4af7e)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index cc05bd9e43b49..3fce5c0001444 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -3449,10 +3449,10 @@ static inline int guc_lrc_desc_unpin(struct intel_context *ce)
 	 */
 	ret = deregister_context(ce, ce->guc_id.id);
 	if (ret) {
-		spin_lock(&ce->guc_state.lock);
+		spin_lock_irqsave(&ce->guc_state.lock, flags);
 		set_context_registered(ce);
 		clr_context_destroyed(ce);
-		spin_unlock(&ce->guc_state.lock);
+		spin_unlock_irqrestore(&ce->guc_state.lock, flags);
 		/*
 		 * As gt-pm is awake at function entry, intel_wakeref_put_async merely decrements
 		 * the wakeref immediately but per function spec usage call this after unlock.

From 0c455f3a12298e9c89a78d2f3327e15e52c0adc5 Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Thu, 13 Feb 2025 11:28:59 -0800
Subject: [PATCH 0637/2753] drm/xe: Fix error handling in xe_irq_install()

When devm_add_action_or_reset() fails, it already calls the function
passed as parameter and that function is already free'ing the irqs.
Drop the goto and just return.

The caller, xe_device_probe(), should also do the same thing instead of
wrongly doing `goto err` and calling the unrelated xe_display_fini()
function.

Fixes: 14d25d8d684d ("drm/xe: change old msi irq api to a new one")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Reviewed-by: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250213192909.996148-3-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 121b214cdf10d4129b64f2b1f31807154c74ae55)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_irq.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index 32f5a67a917b5..08552ee3fb94b 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -757,19 +757,7 @@ int xe_irq_install(struct xe_device *xe)
 
 	xe_irq_postinstall(xe);
 
-	err = devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe);
-	if (err)
-		goto free_irq_handler;
-
-	return 0;
-
-free_irq_handler:
-	if (xe_device_has_msix(xe))
-		xe_irq_msix_free(xe);
-	else
-		xe_irq_msi_free(xe);
-
-	return err;
+	return devm_add_action_or_reset(xe->drm.dev, irq_uninstall, xe);
 }
 
 static void xe_irq_msi_synchronize_irq(struct xe_device *xe)

From 879f70382ff3e92fc854589ada3453e3f5f5b601 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 14 Feb 2025 16:19:51 +0200
Subject: [PATCH 0638/2753] drm/i915/dsi: Use TRANS_DDI_FUNC_CTL's own port
 width macro

The format of the port width field in the DDI_BUF_CTL and the
TRANS_DDI_FUNC_CTL registers are different starting with MTL, where the
x3 lane mode for HDMI FRL has a different encoding in the two registers.
To account for this use the TRANS_DDI_FUNC_CTL's own port width macro.

Cc: <stable@vger.kernel.org> # v6.5+
Fixes: b66a8abaa48a ("drm/i915/display/mtl: Fill port width in DDI_BUF_/TRANS_DDI_FUNC_/PORT_BUF_CTL for HDMI")
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250214142001.552916-2-imre.deak@intel.com
(cherry picked from commit 76120b3a304aec28fef4910204b81a12db8974da)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/icl_dsi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c
index c977b74f82f0b..82bf6c654de25 100644
--- a/drivers/gpu/drm/i915/display/icl_dsi.c
+++ b/drivers/gpu/drm/i915/display/icl_dsi.c
@@ -809,8 +809,8 @@ gen11_dsi_configure_transcoder(struct intel_encoder *encoder,
 		/* select data lane width */
 		tmp = intel_de_read(display,
 				    TRANS_DDI_FUNC_CTL(display, dsi_trans));
-		tmp &= ~DDI_PORT_WIDTH_MASK;
-		tmp |= DDI_PORT_WIDTH(intel_dsi->lane_count);
+		tmp &= ~TRANS_DDI_PORT_WIDTH_MASK;
+		tmp |= TRANS_DDI_PORT_WIDTH(intel_dsi->lane_count);
 
 		/* select input pipe */
 		tmp &= ~TRANS_DDI_EDP_INPUT_MASK;

From 166ce267ae3f96e439d8ccc838e8ec4d8b4dab73 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 14 Feb 2025 16:19:52 +0200
Subject: [PATCH 0639/2753] drm/i915/ddi: Fix HDMI port width programming in
 DDI_BUF_CTL

Fix the port width programming in the DDI_BUF_CTL register on MTLP+,
where this had an off-by-one error.

Cc: <stable@vger.kernel.org> # v6.5+
Fixes: b66a8abaa48a ("drm/i915/display/mtl: Fill port width in DDI_BUF_/TRANS_DDI_FUNC_/PORT_BUF_CTL for HDMI")
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250214142001.552916-3-imre.deak@intel.com
(cherry picked from commit b2ecdabe46d23db275f94cd7c46ca414a144818b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 2 +-
 drivers/gpu/drm/i915/i915_reg.h          | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index acb986bc1f33a..2b9240ab547d8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -3487,7 +3487,7 @@ static void intel_ddi_enable_hdmi(struct intel_atomic_state *state,
 		intel_de_rmw(dev_priv, XELPDP_PORT_BUF_CTL1(dev_priv, port),
 			     XELPDP_PORT_WIDTH_MASK | XELPDP_PORT_REVERSAL, port_buf);
 
-		buf_ctl |= DDI_PORT_WIDTH(lane_count);
+		buf_ctl |= DDI_PORT_WIDTH(crtc_state->lane_count);
 
 		if (DISPLAY_VER(dev_priv) >= 20)
 			buf_ctl |= XE2LPD_DDI_BUF_D2D_LINK_ENABLE;
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 765e6c0528fb0..786c727aea454 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -3633,7 +3633,7 @@ enum skl_power_gate {
 #define  DDI_BUF_IS_IDLE			(1 << 7)
 #define  DDI_BUF_CTL_TC_PHY_OWNERSHIP		REG_BIT(6)
 #define  DDI_A_4_LANES				(1 << 4)
-#define  DDI_PORT_WIDTH(width)			(((width) - 1) << 1)
+#define  DDI_PORT_WIDTH(width)			(((width) == 3 ? 4 : ((width) - 1)) << 1)
 #define  DDI_PORT_WIDTH_MASK			(7 << 1)
 #define  DDI_PORT_WIDTH_SHIFT			1
 #define  DDI_INIT_DISPLAY_DETECTED		(1 << 0)

From 07fb70d82e0df085980246bf17bc12537588795f Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Wed, 12 Feb 2025 18:43:21 +0200
Subject: [PATCH 0640/2753] drm/i915: Make sure all planes in use by the joiner
 have their crtc included
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Any active plane needs to have its crtc included in the atomic
state. For planes enabled via uapi that is all handler in the core.
But when we use a plane for joiner the uapi code things the plane
is disabled and therefore doesn't have a crtc. So we need to pull
those in by hand. We do it first thing in
intel_joiner_add_affected_crtcs() so that any newly added crtc will
subsequently pull in all of its joined crtcs as well.

The symptoms from failing to do this are:
- duct tape in the form of commit 1d5b09f8daf8 ("drm/i915: Fix NULL
  ptr deref by checking new_crtc_state")
- the plane's hw state will get overwritten by the disabled
  uapi state if it can't find the uapi counterpart plane in
  the atomic state from where it should copy the correct state

Cc: stable@vger.kernel.org
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250212164330.16891-2-ville.syrjala@linux.intel.com
(cherry picked from commit 91077d1deb5374eb8be00fb391710f00e751dc4b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 4271da219b410..41128469f12a2 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -6628,12 +6628,30 @@ static int intel_async_flip_check_hw(struct intel_atomic_state *state, struct in
 static int intel_joiner_add_affected_crtcs(struct intel_atomic_state *state)
 {
 	struct drm_i915_private *i915 = to_i915(state->base.dev);
+	const struct intel_plane_state *plane_state;
 	struct intel_crtc_state *crtc_state;
+	struct intel_plane *plane;
 	struct intel_crtc *crtc;
 	u8 affected_pipes = 0;
 	u8 modeset_pipes = 0;
 	int i;
 
+	/*
+	 * Any plane which is in use by the joiner needs its crtc.
+	 * Pull those in first as this will not have happened yet
+	 * if the plane remains disabled according to uapi.
+	 */
+	for_each_new_intel_plane_in_state(state, plane, plane_state, i) {
+		crtc = to_intel_crtc(plane_state->hw.crtc);
+		if (!crtc)
+			continue;
+
+		crtc_state = intel_atomic_get_crtc_state(&state->base, crtc);
+		if (IS_ERR(crtc_state))
+			return PTR_ERR(crtc_state);
+	}
+
+	/* Now pull in all joined crtcs */
 	for_each_new_intel_crtc_in_state(state, crtc, crtc_state, i) {
 		affected_pipes |= crtc_state->joiner_pipes;
 		if (intel_crtc_needs_modeset(crtc_state))

From dd8b0582e25e36bba483c60338741c0ba5bc426c Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Mon, 17 Feb 2025 11:16:26 +0800
Subject: [PATCH 0641/2753] block: fix NULL pointer dereferenced within
 __blk_rq_map_sg

The block layer internal flush request may not have bio attached, so the
request iterator has to be initialized from valid req->bio, otherwise NULL
pointer dereferenced is triggered.

Cc: Christoph Hellwig <hch@lst.de>
Reported-and-tested-by: Cheyenne Wills <cheyenne.wills@gmail.com>
Fixes: b7175e24d6ac ("block: add a dma mapping iterator")
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250217031626.461977-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index 39b738c0e4c9a..c7c85e10cf9cb 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -556,11 +556,14 @@ int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
 {
 	struct req_iterator iter = {
 		.bio	= rq->bio,
-		.iter	= rq->bio->bi_iter,
 	};
 	struct phys_vec vec;
 	int nsegs = 0;
 
+	/* the internal flush request may not have bio attached */
+	if (iter.bio)
+		iter.iter = iter.bio->bi_iter;
+
 	while (blk_map_iter_next(rq, &iter, &vec)) {
 		*last_sg = blk_next_sg(last_sg, sglist);
 		sg_set_page(*last_sg, phys_to_page(vec.paddr), vec.len,

From 290237fde9491ca26cf4020bbf5a2b330452e7db Mon Sep 17 00:00:00 2001
From: David Disseldorp <ddiss@suse.de>
Date: Mon, 10 Feb 2025 22:17:29 +1100
Subject: [PATCH 0642/2753] btrfs: selftests: fix btrfs_test_delayed_refs()
 leak of transaction

The btrfs_transaction struct leaks, which can cause sporadic fstests
failures when kmemleak checking is enabled:

kmemleak: 5 new suspected memory leaks (see /sys/kernel/debug/kmemleak)
> cat /sys/kernel/debug/kmemleak
unreferenced object 0xffff88810fdc6c00 (size 512):
  comm "modprobe", pid 203, jiffies 4294892552
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 6736050f):
    __kmalloc_cache_noprof+0x133/0x2c0
    btrfs_test_delayed_refs+0x6f/0xbb0 [btrfs]
    btrfs_run_sanity_tests.cold+0x91/0xf9 [btrfs]
    0xffffffffa02fd055
    do_one_initcall+0x49/0x1c0
    do_init_module+0x5b/0x1f0
    init_module_from_file+0x70/0x90
    idempotent_init_module+0xe8/0x2c0
    __x64_sys_finit_module+0x6b/0xd0
    do_syscall_64+0x54/0x110
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

The transaction struct was initially stack-allocated but switched to
heap following frame size compiler warnings.

Fixes: 2b34879d97e27 ("btrfs: selftests: add delayed ref self test cases")
Signed-off-by: David Disseldorp <ddiss@suse.de>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/tests/delayed-refs-tests.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/tests/delayed-refs-tests.c b/fs/btrfs/tests/delayed-refs-tests.c
index 6558508c2ddf5..265370e79a546 100644
--- a/fs/btrfs/tests/delayed-refs-tests.c
+++ b/fs/btrfs/tests/delayed-refs-tests.c
@@ -1009,6 +1009,7 @@ int btrfs_test_delayed_refs(u32 sectorsize, u32 nodesize)
 	if (!ret)
 		ret = select_delayed_refs_test(&trans);
 
+	kfree(transaction);
 out_free_fs_info:
 	btrfs_free_dummy_fs_info(fs_info);
 	return ret;

From 4cb77793842a351b39a030f77caebace3524840e Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Sat, 15 Feb 2025 18:52:41 +0000
Subject: [PATCH 0643/2753] irqchip/gic-v3: Fix rk3399 workaround when secure
 interrupts are enabled

Christoph reports that their rk3399 system dies since commit 773c05f417fa1
("irqchip/gic-v3: Work around insecure GIC integrations").

It appears that some rk3399 have secure payloads, and that the firmware
sets SCR_EL3.FIQ==1. Obivously, disabling security in that configuration
leads to even more problems.

Revisit the workaround by:

  - making it rk3399 specific
  - checking whether Group-0 is available, which is a good proxy
    for SCR_EL3.FIQ being 0
  - either apply the workaround if Group-0 is available, or disable
    pseudo-NMIs if not

Note that this doesn't mean that the secure side is able to receive
interrupts, as all interrupts are made non-secure anyway.

Clearly, nobody ever tested secure interrupts on this platform.

Fixes: 773c05f417fa1 ("irqchip/gic-v3: Work around insecure GIC integrations")
Reported-by: Christoph Fritz <chf.fritz@googlemail.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Christoph Fritz <chf.fritz@googlemail.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/all/20250215185241.3768218-1-maz@kernel.org
Closes: https://lore.kernel.org/r/b1266652fb64857246e8babdf268d0df8f0c36d9.camel@googlemail.com
---
 drivers/irqchip/irq-gic-v3.c | 53 +++++++++++++++++++++++++++---------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 76dce0aac2465..270d7a4d85a6d 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -44,6 +44,7 @@ static u8 dist_prio_nmi __ro_after_init = GICV3_PRIO_NMI;
 #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996	(1ULL << 0)
 #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539	(1ULL << 1)
 #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001	(1ULL << 2)
+#define FLAGS_WORKAROUND_INSECURE		(1ULL << 3)
 
 #define GIC_IRQ_TYPE_PARTITION	(GIC_IRQ_TYPE_LPI + 1)
 
@@ -83,6 +84,8 @@ static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key);
 #define GIC_LINE_NR	min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U)
 #define GIC_ESPI_NR	GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer)
 
+static bool nmi_support_forbidden;
+
 /*
  * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs
  * are potentially stolen by the secure side. Some code, especially code dealing
@@ -163,21 +166,27 @@ static void __init gic_prio_init(void)
 {
 	bool ds;
 
-	ds = gic_dist_security_disabled();
-	if (!ds) {
-		u32 val;
-
-		val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
-		val |= GICD_CTLR_DS;
-		writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+	cpus_have_group0 = gic_has_group0();
 
-		ds = gic_dist_security_disabled();
-		if (ds)
-			pr_warn("Broken GIC integration, security disabled");
+	ds = gic_dist_security_disabled();
+	if ((gic_data.flags & FLAGS_WORKAROUND_INSECURE) && !ds) {
+		if (cpus_have_group0) {
+			u32 val;
+
+			val = readl_relaxed(gic_data.dist_base + GICD_CTLR);
+			val |= GICD_CTLR_DS;
+			writel_relaxed(val, gic_data.dist_base + GICD_CTLR);
+
+			ds = gic_dist_security_disabled();
+			if (ds)
+				pr_warn("Broken GIC integration, security disabled\n");
+		} else {
+			pr_warn("Broken GIC integration, pNMI forbidden\n");
+			nmi_support_forbidden = true;
+		}
 	}
 
 	cpus_have_security_disabled = ds;
-	cpus_have_group0 = gic_has_group0();
 
 	/*
 	 * How priority values are used by the GIC depends on two things:
@@ -209,7 +218,7 @@ static void __init gic_prio_init(void)
 	 * be in the non-secure range, we program the non-secure values into
 	 * the distributor to match the PMR values we want.
 	 */
-	if (cpus_have_group0 & !cpus_have_security_disabled) {
+	if (cpus_have_group0 && !cpus_have_security_disabled) {
 		dist_prio_irq = __gicv3_prio_to_ns(dist_prio_irq);
 		dist_prio_nmi = __gicv3_prio_to_ns(dist_prio_nmi);
 	}
@@ -1922,6 +1931,18 @@ static bool gic_enable_quirk_arm64_2941627(void *data)
 	return true;
 }
 
+static bool gic_enable_quirk_rk3399(void *data)
+{
+	struct gic_chip_data *d = data;
+
+	if (of_machine_is_compatible("rockchip,rk3399")) {
+		d->flags |= FLAGS_WORKAROUND_INSECURE;
+		return true;
+	}
+
+	return false;
+}
+
 static bool rd_set_non_coherent(void *data)
 {
 	struct gic_chip_data *d = data;
@@ -1996,6 +2017,12 @@ static const struct gic_quirk gic_quirks[] = {
 		.property = "dma-noncoherent",
 		.init   = rd_set_non_coherent,
 	},
+	{
+		.desc	= "GICv3: Insecure RK3399 integration",
+		.iidr	= 0x0000043b,
+		.mask	= 0xff000fff,
+		.init	= gic_enable_quirk_rk3399,
+	},
 	{
 	}
 };
@@ -2004,7 +2031,7 @@ static void gic_enable_nmi_support(void)
 {
 	int i;
 
-	if (!gic_prio_masking_enabled())
+	if (!gic_prio_masking_enabled() || nmi_support_forbidden)
 		return;
 
 	rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR,

From d7e3fd658248f257006227285095d190e70ee73a Mon Sep 17 00:00:00 2001
From: Artur Rojek <contact@artur-rojek.eu>
Date: Sun, 16 Feb 2025 18:55:45 +0100
Subject: [PATCH 0644/2753] irqchip/jcore-aic, clocksource/drivers/jcore: Fix
 jcore-pit interrupt request

The jcore-aic irqchip does not have separate interrupt numbers reserved for
cpu-local vs global interrupts. Therefore the device drivers need to
request the given interrupt as per CPU interrupt.

69a9dcbd2d65 ("clocksource/drivers/jcore: Use request_percpu_irq()")
converted the clocksource driver over to request_percpu_irq(), but failed
to do add all the required changes, resulting in a failure to register PIT
interrupts.

Fix this by:

 1) Explicitly mark the interrupt via irq_set_percpu_devid() in
    jcore_pit_init().

 2) Enable and disable the per CPU interrupt in the CPU hotplug callbacks.

 3) Pass the correct per-cpu cookie to the irq handler by using
    handle_percpu_devid_irq() instead of handle_percpu_irq() in
    handle_jcore_irq().

[ tglx: Massage change log ]

Fixes: 69a9dcbd2d65 ("clocksource/drivers/jcore: Use request_percpu_irq()")
Signed-off-by: Artur Rojek <contact@artur-rojek.eu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Uros Bizjak <ubizjak@gmail.com>
Link: https://lore.kernel.org/all/20250216175545.35079-3-contact@artur-rojek.eu
---
 drivers/clocksource/jcore-pit.c | 15 ++++++++++++++-
 drivers/irqchip/irq-jcore-aic.c |  2 +-
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/clocksource/jcore-pit.c b/drivers/clocksource/jcore-pit.c
index a3fe98cd38382..82815428f8f92 100644
--- a/drivers/clocksource/jcore-pit.c
+++ b/drivers/clocksource/jcore-pit.c
@@ -114,6 +114,18 @@ static int jcore_pit_local_init(unsigned cpu)
 	pit->periodic_delta = DIV_ROUND_CLOSEST(NSEC_PER_SEC, HZ * buspd);
 
 	clockevents_config_and_register(&pit->ced, freq, 1, ULONG_MAX);
+	enable_percpu_irq(pit->ced.irq, IRQ_TYPE_NONE);
+
+	return 0;
+}
+
+static int jcore_pit_local_teardown(unsigned cpu)
+{
+	struct jcore_pit *pit = this_cpu_ptr(jcore_pit_percpu);
+
+	pr_info("Local J-Core PIT teardown on cpu %u\n", cpu);
+
+	disable_percpu_irq(pit->ced.irq);
 
 	return 0;
 }
@@ -168,6 +180,7 @@ static int __init jcore_pit_init(struct device_node *node)
 		return -ENOMEM;
 	}
 
+	irq_set_percpu_devid(pit_irq);
 	err = request_percpu_irq(pit_irq, jcore_timer_interrupt,
 				 "jcore_pit", jcore_pit_percpu);
 	if (err) {
@@ -237,7 +250,7 @@ static int __init jcore_pit_init(struct device_node *node)
 
 	cpuhp_setup_state(CPUHP_AP_JCORE_TIMER_STARTING,
 			  "clockevents/jcore:starting",
-			  jcore_pit_local_init, NULL);
+			  jcore_pit_local_init, jcore_pit_local_teardown);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-jcore-aic.c b/drivers/irqchip/irq-jcore-aic.c
index b9dcc8e78c750..1f613eb7b7f03 100644
--- a/drivers/irqchip/irq-jcore-aic.c
+++ b/drivers/irqchip/irq-jcore-aic.c
@@ -38,7 +38,7 @@ static struct irq_chip jcore_aic;
 static void handle_jcore_irq(struct irq_desc *desc)
 {
 	if (irqd_is_per_cpu(irq_desc_get_irq_data(desc)))
-		handle_percpu_irq(desc);
+		handle_percpu_devid_irq(desc);
 	else
 		handle_simple_irq(desc);
 }

From 1dd1bf505c0916ff3ad62152b0f4da71ffe5708f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 16 Feb 2025 10:20:42 +0000
Subject: [PATCH 0645/2753] net: xpcs: rearrange register definitions

Place register number definitions immediately above their field
definitions and order by register number.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tjblS-00448F-8v@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.h | 25 ++++++++-----------------
 1 file changed, 8 insertions(+), 17 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.h b/drivers/net/pcs/pcs-xpcs.h
index 39d3f517b557b..929fa238445ed 100644
--- a/drivers/net/pcs/pcs-xpcs.h
+++ b/drivers/net/pcs/pcs-xpcs.h
@@ -55,23 +55,11 @@
 /* Clause 37 Defines */
 /* VR MII MMD registers offsets */
 #define DW_VR_MII_DIG_CTRL1		0x8000
-#define DW_VR_MII_AN_CTRL		0x8001
-#define DW_VR_MII_AN_INTR_STS		0x8002
-/* EEE Mode Control Register */
-#define DW_VR_MII_EEE_MCTRL0		0x8006
-#define DW_VR_MII_EEE_MCTRL1		0x800b
-#define DW_VR_MII_DIG_CTRL2		0x80e1
-
-/* VR_MII_DIG_CTRL1 */
 #define DW_VR_MII_DIG_CTRL1_MAC_AUTO_SW		BIT(9)
 #define DW_VR_MII_DIG_CTRL1_2G5_EN		BIT(2)
 #define DW_VR_MII_DIG_CTRL1_PHY_MODE_CTRL	BIT(0)
 
-/* VR_MII_DIG_CTRL2 */
-#define DW_VR_MII_DIG_CTRL2_TX_POL_INV		BIT(4)
-#define DW_VR_MII_DIG_CTRL2_RX_POL_INV		BIT(0)
-
-/* VR_MII_AN_CTRL */
+#define DW_VR_MII_AN_CTRL		0x8001
 #define DW_VR_MII_AN_CTRL_8BIT			BIT(8)
 #define DW_VR_MII_TX_CONFIG_MASK		BIT(3)
 #define DW_VR_MII_TX_CONFIG_PHY_SIDE_SGMII	0x1
@@ -81,7 +69,7 @@
 #define DW_VR_MII_PCS_MODE_C37_SGMII		0x2
 #define DW_VR_MII_AN_INTR_EN			BIT(0)
 
-/* VR_MII_AN_INTR_STS */
+#define DW_VR_MII_AN_INTR_STS		0x8002
 #define DW_VR_MII_AN_STS_C37_ANCMPLT_INTR	BIT(0)
 #define DW_VR_MII_AN_STS_C37_ANSGM_FD		BIT(1)
 #define DW_VR_MII_AN_STS_C37_ANSGM_SP		GENMASK(3, 2)
@@ -90,19 +78,22 @@
 #define DW_VR_MII_C37_ANSGM_SP_1000		0x2
 #define DW_VR_MII_C37_ANSGM_SP_LNKSTS		BIT(4)
 
-/* VR MII EEE Control 0 defines */
+#define DW_VR_MII_EEE_MCTRL0		0x8006
 #define DW_VR_MII_EEE_LTX_EN			BIT(0)  /* LPI Tx Enable */
 #define DW_VR_MII_EEE_LRX_EN			BIT(1)  /* LPI Rx Enable */
 #define DW_VR_MII_EEE_TX_QUIET_EN		BIT(2)  /* Tx Quiet Enable */
 #define DW_VR_MII_EEE_RX_QUIET_EN		BIT(3)  /* Rx Quiet Enable */
 #define DW_VR_MII_EEE_TX_EN_CTRL		BIT(4)  /* Tx Control Enable */
 #define DW_VR_MII_EEE_RX_EN_CTRL		BIT(7)  /* Rx Control Enable */
-
 #define DW_VR_MII_EEE_MULT_FACT_100NS		GENMASK(11, 8)
 
-/* VR MII EEE Control 1 defines */
+#define DW_VR_MII_EEE_MCTRL1		0x800b
 #define DW_VR_MII_EEE_TRN_LPI		BIT(0)	/* Transparent Mode Enable */
 
+#define DW_VR_MII_DIG_CTRL2		0x80e1
+#define DW_VR_MII_DIG_CTRL2_TX_POL_INV		BIT(4)
+#define DW_VR_MII_DIG_CTRL2_RX_POL_INV		BIT(0)
+
 #define DW_XPCS_INFO_DECLARE(_name, _pcs, _pma)				\
 	static const struct dw_xpcs_info _name = { .pcs = _pcs, .pma = _pma }
 

From 2f435137a0484f11b47554281091ef4908f8cb31 Mon Sep 17 00:00:00 2001
From: Sky Huang <skylake.huang@mediatek.com>
Date: Thu, 13 Feb 2025 16:05:49 +0800
Subject: [PATCH 0646/2753] net: phy: mediatek: Change to more meaningful
 macros

Replace magic number with more meaningful macros in mtk-ge.c.
Also, move some common macros into mtk-phy-lib.c.

Signed-off-by: Sky Huang <skylake.huang@mediatek.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213080553.921434-2-SkyLake.Huang@mediatek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge-soc.c |  1 -
 drivers/net/phy/mediatek/mtk-ge.c     | 71 +++++++++++++++++++++------
 drivers/net/phy/mediatek/mtk.h        |  2 +
 3 files changed, 57 insertions(+), 17 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index bdf99b3270293..69cd6a1cbad41 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -24,7 +24,6 @@
 #define MTK_PHY_SMI_DET_ON_THRESH_MASK		GENMASK(13, 8)
 
 #define MTK_PHY_PAGE_EXTENDED_2A30		0x2a30
-#define MTK_PHY_PAGE_EXTENDED_52B5		0x52b5
 
 #define ANALOG_INTERNAL_OPERATION_MAX_US	20
 #define TXRESERVE_MIN				0
diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c
index b517ca8573e76..75e1b03877104 100644
--- a/drivers/net/phy/mediatek/mtk-ge.c
+++ b/drivers/net/phy/mediatek/mtk-ge.c
@@ -8,18 +8,38 @@
 #define MTK_GPHY_ID_MT7530		0x03a29412
 #define MTK_GPHY_ID_MT7531		0x03a29441
 
-#define MTK_EXT_PAGE_ACCESS		0x1f
-#define MTK_PHY_PAGE_STANDARD		0x0000
-#define MTK_PHY_PAGE_EXTENDED		0x0001
-#define MTK_PHY_PAGE_EXTENDED_2		0x0002
-#define MTK_PHY_PAGE_EXTENDED_3		0x0003
-#define MTK_PHY_PAGE_EXTENDED_2A30	0x2a30
-#define MTK_PHY_PAGE_EXTENDED_52B5	0x52b5
+#define MTK_PHY_PAGE_EXTENDED_1			0x0001
+#define MTK_PHY_AUX_CTRL_AND_STATUS		0x14
+#define   MTK_PHY_ENABLE_DOWNSHIFT		BIT(4)
+
+#define MTK_PHY_PAGE_EXTENDED_2			0x0002
+#define MTK_PHY_PAGE_EXTENDED_3			0x0003
+#define MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11	0x11
+
+#define MTK_PHY_PAGE_EXTENDED_2A30		0x2a30
+
+/* Registers on MDIO_MMD_VEND1 */
+#define MTK_PHY_GBE_MODE_TX_DELAY_SEL		0x13
+#define MTK_PHY_TEST_MODE_TX_DELAY_SEL		0x14
+#define   MTK_TX_DELAY_PAIR_B_MASK		GENMASK(10, 8)
+#define   MTK_TX_DELAY_PAIR_D_MASK		GENMASK(2, 0)
+
+#define MTK_PHY_MCC_CTRL_AND_TX_POWER_CTRL	0xa6
+#define   MTK_MCC_NEARECHO_OFFSET_MASK		GENMASK(15, 8)
+
+#define MTK_PHY_RXADC_CTRL_RG7			0xc6
+#define   MTK_PHY_DA_AD_BUF_BIAS_LP_MASK	GENMASK(9, 8)
+
+#define MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG123	0x123
+#define   MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK	GENMASK(15, 8)
+#define   MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK	GENMASK(7, 0)
 
 static void mtk_gephy_config_init(struct phy_device *phydev)
 {
 	/* Enable HW auto downshift */
-	phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED, 0x14, 0, BIT(4));
+	phy_modify_paged(phydev, MTK_PHY_PAGE_EXTENDED_1,
+			 MTK_PHY_AUX_CTRL_AND_STATUS,
+			 0, MTK_PHY_ENABLE_DOWNSHIFT);
 
 	/* Increase SlvDPSready time */
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
@@ -29,10 +49,20 @@ static void mtk_gephy_config_init(struct phy_device *phydev)
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
 	/* Adjust 100_mse_threshold */
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x123, 0xffff);
-
-	/* Disable mcc */
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0xa6, 0x300);
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+		       MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG123,
+		       MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK |
+		       MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK,
+		       FIELD_PREP(MTK_PHY_LPI_NORM_MSE_LO_THRESH100_MASK,
+				  0xff) |
+		       FIELD_PREP(MTK_PHY_LPI_NORM_MSE_HI_THRESH100_MASK,
+				  0xff));
+
+	/* If echo time is narrower than 0x3, it will be regarded as noise */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1,
+		       MTK_PHY_MCC_CTRL_AND_TX_POWER_CTRL,
+		       MTK_MCC_NEARECHO_OFFSET_MASK,
+		       FIELD_PREP(MTK_MCC_NEARECHO_OFFSET_MASK, 0x3));
 }
 
 static int mt7530_phy_config_init(struct phy_device *phydev)
@@ -40,7 +70,8 @@ static int mt7530_phy_config_init(struct phy_device *phydev)
 	mtk_gephy_config_init(phydev);
 
 	/* Increase post_update_timer */
-	phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3, 0x11, 0x4b);
+	phy_write_paged(phydev, MTK_PHY_PAGE_EXTENDED_3,
+			MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11, 0x4b);
 
 	return 0;
 }
@@ -51,11 +82,19 @@ static int mt7531_phy_config_init(struct phy_device *phydev)
 
 	/* PHY link down power saving enable */
 	phy_set_bits(phydev, 0x17, BIT(4));
-	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, 0xc6, 0x300);
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
+		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK,
+		       FIELD_PREP(MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3));
 
 	/* Set TX Pair delay selection */
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x13, 0x404);
-	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x14, 0x404);
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_GBE_MODE_TX_DELAY_SEL,
+		       MTK_TX_DELAY_PAIR_B_MASK | MTK_TX_DELAY_PAIR_D_MASK,
+		       FIELD_PREP(MTK_TX_DELAY_PAIR_B_MASK, 0x4) |
+		       FIELD_PREP(MTK_TX_DELAY_PAIR_D_MASK, 0x4));
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_TEST_MODE_TX_DELAY_SEL,
+		       MTK_TX_DELAY_PAIR_B_MASK | MTK_TX_DELAY_PAIR_D_MASK,
+		       FIELD_PREP(MTK_TX_DELAY_PAIR_B_MASK, 0x4) |
+		       FIELD_PREP(MTK_TX_DELAY_PAIR_D_MASK, 0x4));
 
 	return 0;
 }
diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h
index 63d9fe179b8fd..a888e2e1dd6b6 100644
--- a/drivers/net/phy/mediatek/mtk.h
+++ b/drivers/net/phy/mediatek/mtk.h
@@ -9,6 +9,8 @@
 #define _MTK_EPHY_H_
 
 #define MTK_EXT_PAGE_ACCESS			0x1f
+#define MTK_PHY_PAGE_STANDARD			0x0000
+#define MTK_PHY_PAGE_EXTENDED_52B5		0x52b5
 
 /* Registers on MDIO_MMD_VEND2 */
 #define MTK_PHY_LED0_ON_CTRL			0x24

From afa08fde7c4780ea5556d9d4df6c1daa38ba0d6b Mon Sep 17 00:00:00 2001
From: Sky Huang <skylake.huang@mediatek.com>
Date: Thu, 13 Feb 2025 16:05:50 +0800
Subject: [PATCH 0647/2753] net: phy: mediatek: Add token ring access helper
 functions in mtk-phy-lib

This patch adds TR(token ring) manipulations and adds correct
macro names for those magic numbers. TR is a way to access
proprietary registers on page 52b5. Use these helper functions
so we can see which fields we're going to modify/set/clear.

TR functions with __* prefix mean that the operations inside
aren't wrapped by page select/restore functions.

This patch doesn't really change registers' settings but just
enhances readability and maintainability.

Signed-off-by: Sky Huang <skylake.huang@mediatek.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213080553.921434-3-SkyLake.Huang@mediatek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge-soc.c  | 231 +++++++++++++++++--------
 drivers/net/phy/mediatek/mtk-ge.c      |  11 +-
 drivers/net/phy/mediatek/mtk-phy-lib.c |  63 +++++++
 drivers/net/phy/mediatek/mtk.h         |   5 +
 4 files changed, 230 insertions(+), 80 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index 69cd6a1cbad41..5d73737936595 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -25,6 +25,90 @@
 
 #define MTK_PHY_PAGE_EXTENDED_2A30		0x2a30
 
+/* Registers on Token Ring debug nodes */
+/* ch_addr = 0x0, node_addr = 0x7, data_addr = 0x15 */
+/* NormMseLoThresh */
+#define NORMAL_MSE_LO_THRESH_MASK		GENMASK(15, 8)
+
+/* ch_addr = 0x0, node_addr = 0xf, data_addr = 0x3c */
+/* RemAckCntLimitCtrl */
+#define REMOTE_ACK_COUNT_LIMIT_CTRL_MASK	GENMASK(2, 1)
+
+/* ch_addr = 0x1, node_addr = 0xd, data_addr = 0x20 */
+/* VcoSlicerThreshBitsHigh */
+#define VCO_SLICER_THRESH_HIGH_MASK		GENMASK(23, 0)
+
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x0 */
+/* DfeTailEnableVgaThresh1000 */
+#define DFE_TAIL_EANBLE_VGA_TRHESH_1000		GENMASK(5, 1)
+
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x1 */
+/* MrvlTrFix100Kp */
+#define MRVL_TR_FIX_100KP_MASK			GENMASK(22, 20)
+/* MrvlTrFix100Kf */
+#define MRVL_TR_FIX_100KF_MASK			GENMASK(19, 17)
+/* MrvlTrFix1000Kp */
+#define MRVL_TR_FIX_1000KP_MASK			GENMASK(16, 14)
+/* MrvlTrFix1000Kf */
+#define MRVL_TR_FIX_1000KF_MASK			GENMASK(13, 11)
+
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x12 */
+/* VgaDecRate */
+#define VGA_DECIMATION_RATE_MASK		GENMASK(8, 5)
+
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x17 */
+/* SlvDSPreadyTime */
+#define SLAVE_DSP_READY_TIME_MASK		GENMASK(22, 15)
+/* MasDSPreadyTime */
+#define MASTER_DSP_READY_TIME_MASK		GENMASK(14, 7)
+
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x20 */
+/* ResetSyncOffset */
+#define RESET_SYNC_OFFSET_MASK			GENMASK(11, 8)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x0 */
+/* FfeUpdGainForceVal */
+#define FFE_UPDATE_GAIN_FORCE_VAL_MASK		GENMASK(9, 7)
+/* FfeUpdGainForce */
+#define FFE_UPDATE_GAIN_FORCE			BIT(6)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x6 */
+/* SS: Steady-state, KP: Proportional Gain */
+/* SSTrKp100 */
+#define SS_TR_KP100_MASK			GENMASK(21, 19)
+/* SSTrKf100 */
+#define SS_TR_KF100_MASK			GENMASK(18, 16)
+/* SSTrKp1000Mas */
+#define SS_TR_KP1000_MASTER_MASK		GENMASK(15, 13)
+/* SSTrKf1000Mas */
+#define SS_TR_KF1000_MASTER_MASK		GENMASK(12, 10)
+/* SSTrKp1000Slv */
+#define SS_TR_KP1000_SLAVE_MASK			GENMASK(9, 7)
+/* SSTrKf1000Slv */
+#define SS_TR_KF1000_SLAVE_MASK			GENMASK(6, 4)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0xd */
+/* RegEEE_st2TrKf1000 */
+#define EEE1000_STAGE2_TR_KF_MASK		GENMASK(13, 11)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0xf */
+/* RegEEE_slv_waketr_timer_tar */
+#define SLAVE_WAKETR_TIMER_MASK			GENMASK(20, 11)
+/* RegEEE_slv_remtx_timer_tar */
+#define SLAVE_REMTX_TIMER_MASK			GENMASK(10, 1)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x10 */
+/* RegEEE_slv_wake_int_timer_tar */
+#define SLAVE_WAKEINT_TIMER_MASK		GENMASK(10, 1)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x14 */
+/* RegEEE_trfreeze_timer2 */
+#define TR_FREEZE_TIMER2_MASK			GENMASK(9, 0)
+
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x1c */
+/* RegEEE100Stg1_tar */
+#define EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK	GENMASK(8, 0)
+
 #define ANALOG_INTERNAL_OPERATION_MAX_US	20
 #define TXRESERVE_MIN				0
 #define TXRESERVE_MAX				7
@@ -700,40 +784,41 @@ static int tx_vcm_cal_sw(struct phy_device *phydev, u8 rg_txreserve_x)
 static void mt798x_phy_common_finetune(struct phy_device *phydev)
 {
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
-	__phy_write(phydev, 0x11, 0xc71);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x17,
+			SLAVE_DSP_READY_TIME_MASK | MASTER_DSP_READY_TIME_MASK,
+			FIELD_PREP(SLAVE_DSP_READY_TIME_MASK, 0x18) |
+			FIELD_PREP(MASTER_DSP_READY_TIME_MASK, 0x18));
 
 	/* EnabRandUpdTrig = 1 */
 	__phy_write(phydev, 0x11, 0x2f00);
 	__phy_write(phydev, 0x12, 0xe);
 	__phy_write(phydev, 0x10, 0x8fb0);
 
-	/* NormMseLoThresh = 85 */
-	__phy_write(phydev, 0x11, 0x55a0);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x83aa);
+	__mtk_tr_modify(phydev, 0x0, 0x7, 0x15,
+			NORMAL_MSE_LO_THRESH_MASK,
+			FIELD_PREP(NORMAL_MSE_LO_THRESH_MASK, 0x55));
 
-	/* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */
-	__phy_write(phydev, 0x11, 0x240);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9680);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0x0,
+			FFE_UPDATE_GAIN_FORCE_VAL_MASK,
+			FIELD_PREP(FFE_UPDATE_GAIN_FORCE_VAL_MASK, 0x4) |
+				   FFE_UPDATE_GAIN_FORCE);
 
 	/* TrFreeze = 0 (mt7988 default) */
 	__phy_write(phydev, 0x11, 0x0);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9686);
 
-	/* SSTrKp100 = 5 */
-	/* SSTrKf100 = 6 */
-	/* SSTrKp1000Mas = 5 */
-	/* SSTrKf1000Mas = 6 */
-	/* SSTrKp1000Slv = 5 */
-	/* SSTrKf1000Slv = 6 */
-	__phy_write(phydev, 0x11, 0xbaef);
-	__phy_write(phydev, 0x12, 0x2e);
-	__phy_write(phydev, 0x10, 0x968c);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0x6,
+			SS_TR_KP100_MASK | SS_TR_KF100_MASK |
+			SS_TR_KP1000_MASTER_MASK | SS_TR_KF1000_MASTER_MASK |
+			SS_TR_KP1000_SLAVE_MASK | SS_TR_KF1000_SLAVE_MASK,
+			FIELD_PREP(SS_TR_KP100_MASK, 0x5) |
+			FIELD_PREP(SS_TR_KF100_MASK, 0x6) |
+			FIELD_PREP(SS_TR_KP1000_MASTER_MASK, 0x5) |
+			FIELD_PREP(SS_TR_KF1000_MASTER_MASK, 0x6) |
+			FIELD_PREP(SS_TR_KP1000_SLAVE_MASK, 0x5) |
+			FIELD_PREP(SS_TR_KF1000_SLAVE_MASK, 0x6));
+
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 }
 
@@ -756,27 +841,29 @@ static void mt7981_phy_finetune(struct phy_device *phydev)
 	}
 
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* ResetSyncOffset = 6 */
-	__phy_write(phydev, 0x11, 0x600);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x20,
+			RESET_SYNC_OFFSET_MASK,
+			FIELD_PREP(RESET_SYNC_OFFSET_MASK, 0x6));
 
-	/* VgaDecRate = 1 */
-	__phy_write(phydev, 0x11, 0x4c2a);
-	__phy_write(phydev, 0x12, 0x3e);
-	__phy_write(phydev, 0x10, 0x8fa4);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x12,
+			VGA_DECIMATION_RATE_MASK,
+			FIELD_PREP(VGA_DECIMATION_RATE_MASK, 0x1));
 
 	/* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2,
 	 * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2
 	 */
-	__phy_write(phydev, 0x11, 0xd10a);
-	__phy_write(phydev, 0x12, 0x34);
-	__phy_write(phydev, 0x10, 0x8f82);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x1,
+			MRVL_TR_FIX_100KP_MASK | MRVL_TR_FIX_100KF_MASK |
+			MRVL_TR_FIX_1000KP_MASK | MRVL_TR_FIX_1000KF_MASK,
+			FIELD_PREP(MRVL_TR_FIX_100KP_MASK, 0x3) |
+			FIELD_PREP(MRVL_TR_FIX_100KF_MASK, 0x2) |
+			FIELD_PREP(MRVL_TR_FIX_1000KP_MASK, 0x3) |
+			FIELD_PREP(MRVL_TR_FIX_1000KF_MASK, 0x2));
 
 	/* VcoSlicerThreshBitsHigh */
-	__phy_write(phydev, 0x11, 0x5555);
-	__phy_write(phydev, 0x12, 0x55);
-	__phy_write(phydev, 0x10, 0x8ec0);
+	__mtk_tr_modify(phydev, 0x1, 0xd, 0x20,
+			VCO_SLICER_THRESH_HIGH_MASK,
+			FIELD_PREP(VCO_SLICER_THRESH_HIGH_MASK, 0x555555));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
 	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */
@@ -828,25 +915,23 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5);
 
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* ResetSyncOffset = 5 */
-	__phy_write(phydev, 0x11, 0x500);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x20,
+			RESET_SYNC_OFFSET_MASK,
+			FIELD_PREP(RESET_SYNC_OFFSET_MASK, 0x5));
 
 	/* VgaDecRate is 1 at default on mt7988 */
 
-	/* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7,
-	 * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7
-	 */
-	__phy_write(phydev, 0x11, 0xb90a);
-	__phy_write(phydev, 0x12, 0x6f);
-	__phy_write(phydev, 0x10, 0x8f82);
-
-	/* RemAckCntLimitCtrl = 1 */
-	__phy_write(phydev, 0x11, 0xfbba);
-	__phy_write(phydev, 0x12, 0xc3);
-	__phy_write(phydev, 0x10, 0x87f8);
-
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x1,
+			MRVL_TR_FIX_100KP_MASK | MRVL_TR_FIX_100KF_MASK |
+			MRVL_TR_FIX_1000KP_MASK | MRVL_TR_FIX_1000KF_MASK,
+			FIELD_PREP(MRVL_TR_FIX_100KP_MASK, 0x6) |
+			FIELD_PREP(MRVL_TR_FIX_100KF_MASK, 0x7) |
+			FIELD_PREP(MRVL_TR_FIX_1000KP_MASK, 0x6) |
+			FIELD_PREP(MRVL_TR_FIX_1000KF_MASK, 0x7));
+
+	__mtk_tr_modify(phydev, 0x0, 0xf, 0x3c,
+			REMOTE_ACK_COUNT_LIMIT_CTRL_MASK,
+			FIELD_PREP(REMOTE_ACK_COUNT_LIMIT_CTRL_MASK, 0x1));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
 	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */
@@ -927,40 +1012,36 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9690);
 
-	/* REG_EEE_st2TrKf1000 = 2 */
-	__phy_write(phydev, 0x11, 0x114f);
-	__phy_write(phydev, 0x12, 0x2);
-	__phy_write(phydev, 0x10, 0x969a);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0xd,
+			EEE1000_STAGE2_TR_KF_MASK,
+			FIELD_PREP(EEE1000_STAGE2_TR_KF_MASK, 0x2));
 
-	/* RegEEE_slv_wake_tr_timer_tar = 6, RegEEE_slv_remtx_timer_tar = 20 */
-	__phy_write(phydev, 0x11, 0x3028);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x969e);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0xf,
+			SLAVE_WAKETR_TIMER_MASK | SLAVE_REMTX_TIMER_MASK,
+			FIELD_PREP(SLAVE_WAKETR_TIMER_MASK, 0x6) |
+			FIELD_PREP(SLAVE_REMTX_TIMER_MASK, 0x14));
 
-	/* RegEEE_slv_wake_int_timer_tar = 8 */
-	__phy_write(phydev, 0x11, 0x5010);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x96a0);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0x10,
+			SLAVE_WAKEINT_TIMER_MASK,
+			FIELD_PREP(SLAVE_WAKEINT_TIMER_MASK, 0x8));
 
-	/* RegEEE_trfreeze_timer2 = 586 */
-	__phy_write(phydev, 0x11, 0x24a);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x96a8);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0x14,
+			TR_FREEZE_TIMER2_MASK,
+			FIELD_PREP(TR_FREEZE_TIMER2_MASK, 0x24a));
 
-	/* RegEEE100Stg1_tar = 16 */
-	__phy_write(phydev, 0x11, 0x3210);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x96b8);
+	__mtk_tr_modify(phydev, 0x2, 0xd, 0x1c,
+			EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK,
+			FIELD_PREP(EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK,
+				   0x10));
 
 	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
 	__phy_write(phydev, 0x11, 0x1463);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96ca);
 
-	/* DfeTailEnableVgaThresh1000 = 27 */
-	__phy_write(phydev, 0x11, 0x36);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8f80);
+	__mtk_tr_modify(phydev, 0x1, 0xf, 0x0,
+			DFE_TAIL_EANBLE_VGA_TRHESH_1000,
+			FIELD_PREP(DFE_TAIL_EANBLE_VGA_TRHESH_1000, 0x1b));
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_3);
diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c
index 75e1b03877104..a24c5ba469bad 100644
--- a/drivers/net/phy/mediatek/mtk-ge.c
+++ b/drivers/net/phy/mediatek/mtk-ge.c
@@ -18,6 +18,10 @@
 
 #define MTK_PHY_PAGE_EXTENDED_2A30		0x2a30
 
+/* Registers on Token Ring debug nodes */
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x17 */
+#define SLAVE_DSP_READY_TIME_MASK		GENMASK(22, 15)
+
 /* Registers on MDIO_MMD_VEND1 */
 #define MTK_PHY_GBE_MODE_TX_DELAY_SEL		0x13
 #define MTK_PHY_TEST_MODE_TX_DELAY_SEL		0x14
@@ -42,11 +46,8 @@ static void mtk_gephy_config_init(struct phy_device *phydev)
 			 0, MTK_PHY_ENABLE_DOWNSHIFT);
 
 	/* Increase SlvDPSready time */
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	__phy_write(phydev, 0x10, 0xafae);
-	__phy_write(phydev, 0x12, 0x2f);
-	__phy_write(phydev, 0x10, 0x8fae);
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+	mtk_tr_modify(phydev, 0x1, 0xf, 0x17, SLAVE_DSP_READY_TIME_MASK,
+		      FIELD_PREP(SLAVE_DSP_READY_TIME_MASK, 0x5e));
 
 	/* Adjust 100_mse_threshold */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1,
diff --git a/drivers/net/phy/mediatek/mtk-phy-lib.c b/drivers/net/phy/mediatek/mtk-phy-lib.c
index 98a09d670e9ca..7275e4ee22981 100644
--- a/drivers/net/phy/mediatek/mtk-phy-lib.c
+++ b/drivers/net/phy/mediatek/mtk-phy-lib.c
@@ -6,6 +6,69 @@
 
 #include "mtk.h"
 
+/* Difference between functions with mtk_tr* and __mtk_tr* prefixes is
+ * mtk_tr* functions: wrapped by page switching operations
+ * __mtk_tr* functions: no page switching operations
+ */
+
+static void __mtk_tr_access(struct phy_device *phydev, bool read, u8 ch_addr,
+			    u8 node_addr, u8 data_addr)
+{
+	u16 tr_cmd = BIT(15); /* bit 14 & 0 are reserved */
+
+	if (read)
+		tr_cmd |= BIT(13);
+
+	tr_cmd |= (((ch_addr & 0x3) << 11) |
+		   ((node_addr & 0xf) << 7) |
+		   ((data_addr & 0x3f) << 1));
+	dev_dbg(&phydev->mdio.dev, "tr_cmd: 0x%x\n", tr_cmd);
+	__phy_write(phydev, 0x10, tr_cmd);
+}
+
+static void __mtk_tr_read(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+			  u8 data_addr, u16 *tr_high, u16 *tr_low)
+{
+	__mtk_tr_access(phydev, true, ch_addr, node_addr, data_addr);
+	*tr_low = __phy_read(phydev, 0x11);
+	*tr_high = __phy_read(phydev, 0x12);
+	dev_dbg(&phydev->mdio.dev, "tr_high read: 0x%x, tr_low read: 0x%x\n",
+		*tr_high, *tr_low);
+}
+
+static void __mtk_tr_write(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+			   u8 data_addr, u32 tr_data)
+{
+	__phy_write(phydev, 0x11, tr_data & 0xffff);
+	__phy_write(phydev, 0x12, tr_data >> 16);
+	dev_dbg(&phydev->mdio.dev, "tr_high write: 0x%x, tr_low write: 0x%x\n",
+		tr_data >> 16, tr_data & 0xffff);
+	__mtk_tr_access(phydev, false, ch_addr, node_addr, data_addr);
+}
+
+void __mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		     u8 data_addr, u32 mask, u32 set)
+{
+	u32 tr_data;
+	u16 tr_high;
+	u16 tr_low;
+
+	__mtk_tr_read(phydev, ch_addr, node_addr, data_addr, &tr_high, &tr_low);
+	tr_data = (tr_high << 16) | tr_low;
+	tr_data = (tr_data & ~mask) | set;
+	__mtk_tr_write(phydev, ch_addr, node_addr, data_addr, tr_data);
+}
+EXPORT_SYMBOL_GPL(__mtk_tr_modify);
+
+void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		   u8 data_addr, u32 mask, u32 set)
+{
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	__mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, mask, set);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+}
+EXPORT_SYMBOL_GPL(mtk_tr_modify);
+
 int mtk_phy_read_page(struct phy_device *phydev)
 {
 	return __phy_read(phydev, MTK_EXT_PAGE_ACCESS);
diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h
index a888e2e1dd6b6..af44d1ad8c9ed 100644
--- a/drivers/net/phy/mediatek/mtk.h
+++ b/drivers/net/phy/mediatek/mtk.h
@@ -68,6 +68,11 @@ struct mtk_socphy_priv {
 	unsigned long		led_state;
 };
 
+void __mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		     u8 data_addr, u32 mask, u32 set);
+void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		   u8 data_addr, u32 mask, u32 set);
+
 int mtk_phy_read_page(struct phy_device *phydev);
 int mtk_phy_write_page(struct phy_device *phydev, int page);
 

From 40d33d6d3c90eb104c66e05cdc00db61268c93f9 Mon Sep 17 00:00:00 2001
From: Sky Huang <skylake.huang@mediatek.com>
Date: Thu, 13 Feb 2025 16:05:51 +0800
Subject: [PATCH 0648/2753] net: phy: mediatek: Add token ring set bit
 operation support

Previously in mtk-ge-soc.c, we set some register bits via token
ring, which were implemented in three __phy_write().
Now we can do the same thing via __mtk_tr_set_bits() helper.

Signed-off-by: Sky Huang <skylake.huang@mediatek.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213080553.921434-4-SkyLake.Huang@mediatek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge-soc.c  | 10 ++++++----
 drivers/net/phy/mediatek/mtk-phy-lib.c |  7 +++++++
 drivers/net/phy/mediatek/mtk.h         |  2 ++
 3 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index 5d73737936595..37777ad104d87 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -62,6 +62,10 @@
 /* MasDSPreadyTime */
 #define MASTER_DSP_READY_TIME_MASK		GENMASK(14, 7)
 
+/* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x18 */
+/* EnabRandUpdTrig */
+#define ENABLE_RANDOM_UPDOWN_COUNTER_TRIGGER	BIT(8)
+
 /* ch_addr = 0x1, node_addr = 0xf, data_addr = 0x20 */
 /* ResetSyncOffset */
 #define RESET_SYNC_OFFSET_MASK			GENMASK(11, 8)
@@ -789,10 +793,8 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 			FIELD_PREP(SLAVE_DSP_READY_TIME_MASK, 0x18) |
 			FIELD_PREP(MASTER_DSP_READY_TIME_MASK, 0x18));
 
-	/* EnabRandUpdTrig = 1 */
-	__phy_write(phydev, 0x11, 0x2f00);
-	__phy_write(phydev, 0x12, 0xe);
-	__phy_write(phydev, 0x10, 0x8fb0);
+	__mtk_tr_set_bits(phydev, 0x1, 0xf, 0x18,
+			  ENABLE_RANDOM_UPDOWN_COUNTER_TRIGGER);
 
 	__mtk_tr_modify(phydev, 0x0, 0x7, 0x15,
 			NORMAL_MSE_LO_THRESH_MASK,
diff --git a/drivers/net/phy/mediatek/mtk-phy-lib.c b/drivers/net/phy/mediatek/mtk-phy-lib.c
index 7275e4ee22981..df8fdadcc0f45 100644
--- a/drivers/net/phy/mediatek/mtk-phy-lib.c
+++ b/drivers/net/phy/mediatek/mtk-phy-lib.c
@@ -69,6 +69,13 @@ void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 }
 EXPORT_SYMBOL_GPL(mtk_tr_modify);
 
+void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		       u8 data_addr, u32 set)
+{
+	__mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, 0, set);
+}
+EXPORT_SYMBOL_GPL(__mtk_tr_set_bits);
+
 int mtk_phy_read_page(struct phy_device *phydev)
 {
 	return __phy_read(phydev, MTK_EXT_PAGE_ACCESS);
diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h
index af44d1ad8c9ed..2d8e5b934a024 100644
--- a/drivers/net/phy/mediatek/mtk.h
+++ b/drivers/net/phy/mediatek/mtk.h
@@ -72,6 +72,8 @@ void __mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 		     u8 data_addr, u32 mask, u32 set);
 void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 		   u8 data_addr, u32 mask, u32 set);
+void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		       u8 data_addr, u32 set);
 
 int mtk_phy_read_page(struct phy_device *phydev);
 int mtk_phy_write_page(struct phy_device *phydev, int page);

From 4786eff288bcc77a5dbc2be2308f46f70e58600d Mon Sep 17 00:00:00 2001
From: Sky Huang <skylake.huang@mediatek.com>
Date: Thu, 13 Feb 2025 16:05:52 +0800
Subject: [PATCH 0649/2753] net: phy: mediatek: Add token ring clear bit
 operation support

Similar to __mtk_tr_set_bits() support. Previously in mtk-ge-soc.c,
we clear some register bits via token ring, which were also implemented
in three __phy_write(). Now we can do the same thing via
__mtk_tr_clr_bits() helper.

Signed-off-by: Sky Huang <skylake.huang@mediatek.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213080553.921434-5-SkyLake.Huang@mediatek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge-soc.c  | 30 +++++++++++++++-----------
 drivers/net/phy/mediatek/mtk-phy-lib.c |  7 ++++++
 drivers/net/phy/mediatek/mtk.h         |  2 ++
 3 files changed, 27 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index 37777ad104d87..9de6fbb45564e 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -76,6 +76,10 @@
 /* FfeUpdGainForce */
 #define FFE_UPDATE_GAIN_FORCE			BIT(6)
 
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x3 */
+/* TrFreeze */
+#define TR_FREEZE_MASK				GENMASK(11, 0)
+
 /* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x6 */
 /* SS: Steady-state, KP: Proportional Gain */
 /* SSTrKp100 */
@@ -91,6 +95,11 @@
 /* SSTrKf1000Slv */
 #define SS_TR_KF1000_SLAVE_MASK			GENMASK(6, 4)
 
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x8 */
+/* clear this bit if wanna select from AFE */
+/* Regsigdet_sel_1000 */
+#define EEE1000_SELECT_SIGNAL_DETECTION_FROM_DFE	BIT(4)
+
 /* ch_addr = 0x2, node_addr = 0xd, data_addr = 0xd */
 /* RegEEE_st2TrKf1000 */
 #define EEE1000_STAGE2_TR_KF_MASK		GENMASK(13, 11)
@@ -113,6 +122,10 @@
 /* RegEEE100Stg1_tar */
 #define EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK	GENMASK(8, 0)
 
+/* ch_addr = 0x2, node_addr = 0xd, data_addr = 0x25 */
+/* REGEEE_wake_slv_tr_wait_dfesigdet_en */
+#define WAKE_SLAVE_TR_WAIT_DFE_DETECTION_EN	BIT(11)
+
 #define ANALOG_INTERNAL_OPERATION_MAX_US	20
 #define TXRESERVE_MIN				0
 #define TXRESERVE_MAX				7
@@ -805,10 +818,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 			FIELD_PREP(FFE_UPDATE_GAIN_FORCE_VAL_MASK, 0x4) |
 				   FFE_UPDATE_GAIN_FORCE);
 
-	/* TrFreeze = 0 (mt7988 default) */
-	__phy_write(phydev, 0x11, 0x0);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9686);
+	__mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x3, TR_FREEZE_MASK);
 
 	__mtk_tr_modify(phydev, 0x2, 0xd, 0x6,
 			SS_TR_KP100_MASK | SS_TR_KF100_MASK |
@@ -1009,10 +1019,8 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 			 MTK_PHY_TR_READY_SKIP_AFE_WAKEUP);
 
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* Regsigdet_sel_1000 = 0 */
-	__phy_write(phydev, 0x11, 0xb);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9690);
+	__mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x8,
+			  EEE1000_SELECT_SIGNAL_DETECTION_FROM_DFE);
 
 	__mtk_tr_modify(phydev, 0x2, 0xd, 0xd,
 			EEE1000_STAGE2_TR_KF_MASK,
@@ -1036,10 +1044,8 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 			FIELD_PREP(EEE100_LPSYNC_STAGE1_UPDATE_TIMER_MASK,
 				   0x10));
 
-	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
-	__phy_write(phydev, 0x11, 0x1463);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x96ca);
+	__mtk_tr_clr_bits(phydev, 0x2, 0xd, 0x25,
+			  WAKE_SLAVE_TR_WAIT_DFE_DETECTION_EN);
 
 	__mtk_tr_modify(phydev, 0x1, 0xf, 0x0,
 			DFE_TAIL_EANBLE_VGA_TRHESH_1000,
diff --git a/drivers/net/phy/mediatek/mtk-phy-lib.c b/drivers/net/phy/mediatek/mtk-phy-lib.c
index df8fdadcc0f45..dfd0f4e439a21 100644
--- a/drivers/net/phy/mediatek/mtk-phy-lib.c
+++ b/drivers/net/phy/mediatek/mtk-phy-lib.c
@@ -76,6 +76,13 @@ void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 }
 EXPORT_SYMBOL_GPL(__mtk_tr_set_bits);
 
+void __mtk_tr_clr_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		       u8 data_addr, u32 clr)
+{
+	__mtk_tr_modify(phydev, ch_addr, node_addr, data_addr, clr, 0);
+}
+EXPORT_SYMBOL_GPL(__mtk_tr_clr_bits);
+
 int mtk_phy_read_page(struct phy_device *phydev)
 {
 	return __phy_read(phydev, MTK_EXT_PAGE_ACCESS);
diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h
index 2d8e5b934a024..4e4468dc02344 100644
--- a/drivers/net/phy/mediatek/mtk.h
+++ b/drivers/net/phy/mediatek/mtk.h
@@ -74,6 +74,8 @@ void mtk_tr_modify(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 		   u8 data_addr, u32 mask, u32 set);
 void __mtk_tr_set_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
 		       u8 data_addr, u32 set);
+void __mtk_tr_clr_bits(struct phy_device *phydev, u8 ch_addr, u8 node_addr,
+		       u8 data_addr, u32 clr);
 
 int mtk_phy_read_page(struct phy_device *phydev);
 int mtk_phy_write_page(struct phy_device *phydev, int page);

From be378ebd6cfb8e369d4aa03a551e594d00debda5 Mon Sep 17 00:00:00 2001
From: Sky Huang <skylake.huang@mediatek.com>
Date: Thu, 13 Feb 2025 16:05:53 +0800
Subject: [PATCH 0650/2753] net: phy: mediatek: Move some macros to phy-lib for
 later use

Move some macros to phy-lib because MediaTek's 2.5G built-in
ethernet PHY will also use them.

Signed-off-by: Sky Huang <skylake.huang@mediatek.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250213080553.921434-6-SkyLake.Huang@mediatek.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge.c | 4 ----
 drivers/net/phy/mediatek/mtk.h    | 4 ++++
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge.c b/drivers/net/phy/mediatek/mtk-ge.c
index a24c5ba469bad..73d9b72f9d9e2 100644
--- a/drivers/net/phy/mediatek/mtk-ge.c
+++ b/drivers/net/phy/mediatek/mtk-ge.c
@@ -8,10 +8,6 @@
 #define MTK_GPHY_ID_MT7530		0x03a29412
 #define MTK_GPHY_ID_MT7531		0x03a29441
 
-#define MTK_PHY_PAGE_EXTENDED_1			0x0001
-#define MTK_PHY_AUX_CTRL_AND_STATUS		0x14
-#define   MTK_PHY_ENABLE_DOWNSHIFT		BIT(4)
-
 #define MTK_PHY_PAGE_EXTENDED_2			0x0002
 #define MTK_PHY_PAGE_EXTENDED_3			0x0003
 #define MTK_PHY_RG_LPI_PCS_DSP_CTRL_REG11	0x11
diff --git a/drivers/net/phy/mediatek/mtk.h b/drivers/net/phy/mediatek/mtk.h
index 4e4468dc02344..320f76ffa81fa 100644
--- a/drivers/net/phy/mediatek/mtk.h
+++ b/drivers/net/phy/mediatek/mtk.h
@@ -8,7 +8,11 @@
 #ifndef _MTK_EPHY_H_
 #define _MTK_EPHY_H_
 
+#define MTK_PHY_AUX_CTRL_AND_STATUS		0x14
+#define   MTK_PHY_ENABLE_DOWNSHIFT		BIT(4)
+
 #define MTK_EXT_PAGE_ACCESS			0x1f
+#define MTK_PHY_PAGE_EXTENDED_1			0x0001
 #define MTK_PHY_PAGE_STANDARD			0x0000
 #define MTK_PHY_PAGE_EXTENDED_52B5		0x52b5
 

From 9dd3d5d258aceb37bdf09c8b91fa448f58ea81f0 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Thu, 13 Feb 2025 11:46:38 +0200
Subject: [PATCH 0651/2753] net/mlx5: Apply rate-limiting to high temperature
 warning

Wrap the high temperature warning in a temperature event with
a call to net_ratelimit() to prevent flooding the kernel log
with repeated warning messages when temperature exceeds the
threshold multiple times within a short duration.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250213094641.226501-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index d91ea53eb394d..e8beb6289d018 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -165,9 +165,10 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	mlx5_core_warn(events->dev,
-		       "High temperature on sensors with bit set %llx %llx",
-		       value_msb, value_lsb);
+	if (net_ratelimit())
+		mlx5_core_warn(events->dev,
+			       "High temperature on sensors with bit set %llx %llx",
+			       value_msb, value_lsb);
 
 	return NOTIFY_OK;
 }

From b9b72ce0f5f4679fc878ad010658a72f30595118 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Thu, 13 Feb 2025 11:46:39 +0200
Subject: [PATCH 0652/2753] net/mlx5: Prefix temperature event bitmap with '0x'
 for clarity

Prepend '0x' to the sensor bitmap in the warning message to clearly
indicate that the bitmap is in hexadecimal format.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250213094641.226501-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index e8beb6289d018..a661aa522a9ad 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -167,7 +167,7 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 
 	if (net_ratelimit())
 		mlx5_core_warn(events->dev,
-			       "High temperature on sensors with bit set %llx %llx",
+			       "High temperature on sensors with bit set %#llx %#llx",
 			       value_msb, value_lsb);
 
 	return NOTIFY_OK;

From 633f16d7e07c129a36b882c05379e01ce5bdb542 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Thu, 13 Feb 2025 11:46:40 +0200
Subject: [PATCH 0653/2753] net/mlx5: Modify LSB bitmask in temperature event
 to include only the first bit

In the sensor_count field of the MTEWE register, bits 1-62 are
supported only for unmanaged switches, not for NICs, and bit 63
is reserved for internal use.

To prevent confusing output that may include set bits that are
not relevant to NIC sensors, we update the bitmask to retain only
the first bit, which corresponds to the sensor ASIC.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250213094641.226501-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/events.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index a661aa522a9ad..e85a9042e3c24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -163,6 +163,10 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 	u64 value_msb;
 
 	value_lsb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_lsb);
+	/* bit 1-63 are not supported for NICs,
+	 * hence read only bit 0 (asic) from lsb.
+	 */
+	value_lsb &= 0x1;
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
 	if (net_ratelimit())

From 46fd50cfcc12368bed9ae5257cc3beaea5b3c193 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Thu, 13 Feb 2025 11:46:41 +0200
Subject: [PATCH 0654/2753] net/mlx5: Add sensor name to temperature event
 message

Previously, a temperature event message included a bitmap indicating
which sensors detect high temperatures.

To enhance clarity, we modify the message format to explicitly list
the names of the overheating sensors, alongside the sensors bitmap.
If HWMON is not configured, the event message remains unchanged.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250213094641.226501-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/events.c  | 31 +++++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/hwmon.c   |  5 +++
 .../net/ethernet/mellanox/mlx5/core/hwmon.h   |  1 +
 3 files changed, 34 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/events.c b/drivers/net/ethernet/mellanox/mlx5/core/events.c
index e85a9042e3c24..01c5f5990f9ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/events.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/events.c
@@ -6,6 +6,7 @@
 #include "mlx5_core.h"
 #include "lib/eq.h"
 #include "lib/events.h"
+#include "hwmon.h"
 
 struct mlx5_event_nb {
 	struct mlx5_nb  nb;
@@ -153,11 +154,28 @@ static int any_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+#if IS_ENABLED(CONFIG_HWMON)
+static void print_sensor_names_in_bit_set(struct mlx5_core_dev *dev, struct mlx5_hwmon *hwmon,
+					  u64 bit_set, int bit_set_offset)
+{
+	unsigned long *bit_set_ptr = (unsigned long *)&bit_set;
+	int num_bits = sizeof(bit_set) * BITS_PER_BYTE;
+	int i;
+
+	for_each_set_bit(i, bit_set_ptr, num_bits) {
+		const char *sensor_name = hwmon_get_sensor_name(hwmon, i + bit_set_offset);
+
+		mlx5_core_warn(dev, "Sensor name[%d]: %s\n", i + bit_set_offset, sensor_name);
+	}
+}
+#endif /* CONFIG_HWMON */
+
 /* type == MLX5_EVENT_TYPE_TEMP_WARN_EVENT */
 static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 {
 	struct mlx5_event_nb *event_nb = mlx5_nb_cof(nb, struct mlx5_event_nb, nb);
 	struct mlx5_events   *events   = event_nb->ctx;
+	struct mlx5_core_dev *dev      = events->dev;
 	struct mlx5_eqe      *eqe      = data;
 	u64 value_lsb;
 	u64 value_msb;
@@ -169,10 +187,17 @@ static int temp_warn(struct notifier_block *nb, unsigned long type, void *data)
 	value_lsb &= 0x1;
 	value_msb = be64_to_cpu(eqe->data.temp_warning.sensor_warning_msb);
 
-	if (net_ratelimit())
-		mlx5_core_warn(events->dev,
-			       "High temperature on sensors with bit set %#llx %#llx",
+	if (net_ratelimit()) {
+		mlx5_core_warn(dev, "High temperature on sensors with bit set %#llx %#llx.\n",
 			       value_msb, value_lsb);
+#if IS_ENABLED(CONFIG_HWMON)
+		if (dev->hwmon) {
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_lsb, 0);
+			print_sensor_names_in_bit_set(dev, dev->hwmon, value_msb,
+						      sizeof(value_lsb) * BITS_PER_BYTE);
+		}
+#endif
+	}
 
 	return NOTIFY_OK;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
index 353f81dccd1ce..4ba2636d7fb6c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.c
@@ -416,3 +416,8 @@ void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev)
 	mlx5_hwmon_free(hwmon);
 	mdev->hwmon = NULL;
 }
+
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel)
+{
+	return hwmon->temp_channel_desc[channel].sensor_name;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
index 999654a9b9da5..f38271c22c105 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/hwmon.h
@@ -10,6 +10,7 @@
 
 int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev);
 void mlx5_hwmon_dev_unregister(struct mlx5_core_dev *mdev);
+const char *hwmon_get_sensor_name(struct mlx5_hwmon *hwmon, int channel);
 
 #else
 static inline int mlx5_hwmon_dev_register(struct mlx5_core_dev *mdev)

From dbcbec81c9b8899cf92f6a763a4119aff61ba778 Mon Sep 17 00:00:00 2001
From: Pranav Tyagi <pranav.tyagi03@gmail.com>
Date: Thu, 13 Feb 2025 20:56:11 +0530
Subject: [PATCH 0655/2753] selftests: net: fix grammar in
 reuseaddr_ports_exhausted.c log message

This patch fixes a grammatical error in a test log message
in reuseaddr_ports_exhausted.c for better clarity.

Signed-off-by: Pranav Tyagi <pranav.tyagi03@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250213152612.4434-1-pranav.tyagi03@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/reuseaddr_ports_exhausted.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
index 066efd30e2946..7b9bf8a7bbe1c 100644
--- a/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
+++ b/tools/testing/selftests/net/reuseaddr_ports_exhausted.c
@@ -112,7 +112,7 @@ TEST(reuseaddr_ports_exhausted_reusable_same_euid)
 		ASSERT_NE(-1, fd[0]) TH_LOG("failed to bind.");
 
 		if (opts->reuseport[0] && opts->reuseport[1]) {
-			EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets succeed to be listened.");
+			EXPECT_EQ(-1, fd[1]) TH_LOG("should fail to bind because both sockets successfully listened.");
 		} else {
 			EXPECT_NE(-1, fd[1]) TH_LOG("should succeed to bind to connect to different destinations.");
 		}

From 7fff5d958648eadec1b164dc5a61a5644117d329 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Fri, 14 Feb 2025 15:14:09 +0100
Subject: [PATCH 0656/2753] dt-bindings: net: ethernet-phy: add property
 tx-amplitude-100base-tx-percent

Add property tx-amplitude-100base-tx-percent in the device tree bindings
for configuring the tx amplitude of 100BASE-TX PHYs. Modifying it can be
necessary to compensate losses on the PCB and connector, so the voltages
measured on the RJ45 pins are conforming.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250214-dp83822-tx-swing-v5-1-02ca72620599@liebherr.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/ethernet-phy.yaml | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/ethernet-phy.yaml b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
index 2c71454ae8e36..824bbe4333b7e 100644
--- a/Documentation/devicetree/bindings/net/ethernet-phy.yaml
+++ b/Documentation/devicetree/bindings/net/ethernet-phy.yaml
@@ -232,6 +232,12 @@ properties:
       PHY's that have configurable TX internal delays. If this property is
       present then the PHY applies the TX delay.
 
+  tx-amplitude-100base-tx-percent:
+    description:
+      Transmit amplitude gain applied for 100BASE-TX. 100% matches 2V
+      peak-to-peak specified in ANSI X3.263. When omitted, the PHYs default
+      will be left as is.
+
   leds:
     type: object
 

From 961ee5aeea048aa292f28d61f3a96a48554e91af Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Fri, 14 Feb 2025 15:14:10 +0100
Subject: [PATCH 0657/2753] net: phy: Add helper for getting tx amplitude gain

Add helper which returns the tx amplitude gain defined in device tree.
Modifying it can be necessary to compensate losses on the PCB and
connector, so the voltages measured on the RJ45 pins are conforming.

Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250214-dp83822-tx-swing-v5-2-02ca72620599@liebherr.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 53 ++++++++++++++++++++++++------------
 include/linux/phy.h          |  4 +++
 2 files changed, 39 insertions(+), 18 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 35ec99b4dc510..0d56e7c7f98cd 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3096,19 +3096,12 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause)
 EXPORT_SYMBOL(phy_get_pause);
 
 #if IS_ENABLED(CONFIG_OF_MDIO)
-static int phy_get_int_delay_property(struct device *dev, const char *name)
+static int phy_get_u32_property(struct device *dev, const char *name, u32 *val)
 {
-	s32 int_delay;
-	int ret;
-
-	ret = device_property_read_u32(dev, name, &int_delay);
-	if (ret)
-		return ret;
-
-	return int_delay;
+	return device_property_read_u32(dev, name, val);
 }
 #else
-static int phy_get_int_delay_property(struct device *dev, const char *name)
+static int phy_get_u32_property(struct device *dev, const char *name, u32 *val)
 {
 	return -EINVAL;
 }
@@ -3133,12 +3126,12 @@ static int phy_get_int_delay_property(struct device *dev, const char *name)
 s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 			   const int *delay_values, int size, bool is_rx)
 {
-	s32 delay;
-	int i;
+	int i, ret;
+	u32 delay;
 
 	if (is_rx) {
-		delay = phy_get_int_delay_property(dev, "rx-internal-delay-ps");
-		if (delay < 0 && size == 0) {
+		ret = phy_get_u32_property(dev, "rx-internal-delay-ps", &delay);
+		if (ret < 0 && size == 0) {
 			if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
 			    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID)
 				return 1;
@@ -3147,8 +3140,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 		}
 
 	} else {
-		delay = phy_get_int_delay_property(dev, "tx-internal-delay-ps");
-		if (delay < 0 && size == 0) {
+		ret = phy_get_u32_property(dev, "tx-internal-delay-ps", &delay);
+		if (ret < 0 && size == 0) {
 			if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
 			    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID)
 				return 1;
@@ -3157,8 +3150,8 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 		}
 	}
 
-	if (delay < 0)
-		return delay;
+	if (ret < 0)
+		return ret;
 
 	if (size == 0)
 		return delay;
@@ -3193,6 +3186,30 @@ s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 }
 EXPORT_SYMBOL(phy_get_internal_delay);
 
+/**
+ * phy_get_tx_amplitude_gain - stores tx amplitude gain in @val
+ * @phydev: phy_device struct
+ * @dev: pointer to the devices device struct
+ * @linkmode: linkmode for which the tx amplitude gain should be retrieved
+ * @val: tx amplitude gain
+ *
+ * Returns: 0 on success, < 0 on failure
+ */
+int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev,
+			      enum ethtool_link_mode_bit_indices linkmode,
+			      u32 *val)
+{
+	switch (linkmode) {
+	case ETHTOOL_LINK_MODE_100baseT_Full_BIT:
+		return phy_get_u32_property(dev,
+					    "tx-amplitude-100base-tx-percent",
+					    val);
+	default:
+		return -EINVAL;
+	}
+}
+EXPORT_SYMBOL_GPL(phy_get_tx_amplitude_gain);
+
 static int phy_led_set_brightness(struct led_classdev *led_cdev,
 				  enum led_brightness value)
 {
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 3665cdd610a3d..70c632799082e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2097,6 +2097,10 @@ void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause);
 s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
 			   const int *delay_values, int size, bool is_rx);
 
+int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev,
+			      enum ethtool_link_mode_bit_indices linkmode,
+			      u32 *val);
+
 void phy_resolve_pause(unsigned long *local_adv, unsigned long *partner_adv,
 		       bool *tx_pause, bool *rx_pause);
 

From 4f3735e82d8a2e80ee39731832536b1e34697c71 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Fri, 14 Feb 2025 15:14:11 +0100
Subject: [PATCH 0658/2753] net: phy: dp83822: Add support for changing the
 transmit amplitude voltage

Add support for changing the transmit amplitude voltage in 100BASE-TX mode.
Modifying it can be necessary to compensate losses on the PCB and
connector, so the voltages measured on the RJ45 pins are conforming.

Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250214-dp83822-tx-swing-v5-3-02ca72620599@liebherr.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83822.c | 38 ++++++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 6599feca1967d..3662f3905d5ad 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -31,6 +31,7 @@
 #define MII_DP83822_RCSR	0x17
 #define MII_DP83822_RESET_CTRL	0x1f
 #define MII_DP83822_MLEDCR	0x25
+#define MII_DP83822_LDCTRL	0x403
 #define MII_DP83822_LEDCFG1	0x460
 #define MII_DP83822_IOCTRL1	0x462
 #define MII_DP83822_IOCTRL2	0x463
@@ -123,6 +124,9 @@
 #define DP83822_IOCTRL1_GPIO1_CTRL		GENMASK(2, 0)
 #define DP83822_IOCTRL1_GPIO1_CTRL_LED_1	BIT(0)
 
+/* LDCTRL bits */
+#define DP83822_100BASE_TX_LINE_DRIVER_SWING	GENMASK(7, 4)
+
 /* IOCTRL2 bits */
 #define DP83822_IOCTRL2_GPIO2_CLK_SRC		GENMASK(6, 4)
 #define DP83822_IOCTRL2_GPIO2_CTRL		GENMASK(2, 0)
@@ -197,6 +201,7 @@ struct dp83822_private {
 	bool set_gpio2_clk_out;
 	u32 gpio2_clk_out;
 	bool led_pin_enable[DP83822_MAX_LED_PINS];
+	int tx_amplitude_100base_tx_index;
 };
 
 static int dp83822_config_wol(struct phy_device *phydev,
@@ -522,6 +527,12 @@ static int dp83822_config_init(struct phy_device *phydev)
 			       FIELD_PREP(DP83822_IOCTRL2_GPIO2_CLK_SRC,
 					  dp83822->gpio2_clk_out));
 
+	if (dp83822->tx_amplitude_100base_tx_index >= 0)
+		phy_modify_mmd(phydev, MDIO_MMD_VEND2, MII_DP83822_LDCTRL,
+			       DP83822_100BASE_TX_LINE_DRIVER_SWING,
+			       FIELD_PREP(DP83822_100BASE_TX_LINE_DRIVER_SWING,
+					  dp83822->tx_amplitude_100base_tx_index));
+
 	err = dp83822_config_init_leds(phydev);
 	if (err)
 		return err;
@@ -720,6 +731,11 @@ static int dp83822_phy_reset(struct phy_device *phydev)
 }
 
 #ifdef CONFIG_OF_MDIO
+static const u32 tx_amplitude_100base_tx_gain[] = {
+	80, 82, 83, 85, 87, 88, 90, 92,
+	93, 95, 97, 98, 100, 102, 103, 105,
+};
+
 static int dp83822_of_init_leds(struct phy_device *phydev)
 {
 	struct device_node *node = phydev->mdio.dev.of_node;
@@ -780,6 +796,8 @@ static int dp83822_of_init(struct phy_device *phydev)
 	struct dp83822_private *dp83822 = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	const char *of_val;
+	int i, ret;
+	u32 val;
 
 	/* Signal detection for the PHY is only enabled if the FX_EN and the
 	 * SD_EN pins are strapped. Signal detection can only enabled if FX_EN
@@ -815,6 +833,26 @@ static int dp83822_of_init(struct phy_device *phydev)
 		dp83822->set_gpio2_clk_out = true;
 	}
 
+	dp83822->tx_amplitude_100base_tx_index = -1;
+	ret = phy_get_tx_amplitude_gain(phydev, dev,
+					ETHTOOL_LINK_MODE_100baseT_Full_BIT,
+					&val);
+	if (!ret) {
+		for (i = 0; i < ARRAY_SIZE(tx_amplitude_100base_tx_gain); i++) {
+			if (tx_amplitude_100base_tx_gain[i] == val) {
+				dp83822->tx_amplitude_100base_tx_index = i;
+				break;
+			}
+		}
+
+		if (dp83822->tx_amplitude_100base_tx_index < 0) {
+			phydev_err(phydev,
+				   "Invalid value for tx-amplitude-100base-tx-percent property (%u)\n",
+				   val);
+			return -EINVAL;
+		}
+	}
+
 	return dp83822_of_init_leds(phydev);
 }
 

From b9d752105e5fdcbd9d0126d61da2f6df4a18560f Mon Sep 17 00:00:00 2001
From: Stefano Jordhani <sjordhani@gmail.com>
Date: Fri, 14 Feb 2025 18:17:51 +0000
Subject: [PATCH 0659/2753] net: use napi_id_valid helper

In commit 6597e8d35851 ("netdev-genl: Elide napi_id when not present"),
napi_id_valid function was added. Use the helper to refactor open-coded
checks in the source.

Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Stefano Jordhani <sjordhani@gmail.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk> # for iouring
Link: https://patch.msgid.link/20250214181801.931-1-sjordhani@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/eventpoll.c            | 8 ++++----
 include/net/busy_poll.h   | 4 ++--
 io_uring/napi.c           | 4 ++--
 net/core/dev.c            | 6 +++---
 net/core/netdev-genl.c    | 2 +-
 net/core/page_pool_user.c | 2 +-
 net/core/sock.c           | 2 +-
 net/xdp/xsk.c             | 2 +-
 8 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index 7c0980db77b31..2fecf66661e9a 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -447,7 +447,7 @@ static bool ep_busy_loop(struct eventpoll *ep, int nonblock)
 	if (!budget)
 		budget = BUSY_POLL_BUDGET;
 
-	if (napi_id >= MIN_NAPI_ID && ep_busy_loop_on(ep)) {
+	if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) {
 		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end,
 			       ep, prefer_busy_poll, budget);
 		if (ep_events_available(ep))
@@ -492,7 +492,7 @@ static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
 	 *	or
 	 * Nothing to do if we already have this ID
 	 */
-	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+	if (!napi_id_valid(napi_id) || napi_id == ep->napi_id)
 		return;
 
 	/* record NAPI ID for use in next busy poll */
@@ -546,7 +546,7 @@ static void ep_suspend_napi_irqs(struct eventpoll *ep)
 {
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 
-	if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll))
+	if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll))
 		napi_suspend_irqs(napi_id);
 }
 
@@ -554,7 +554,7 @@ static void ep_resume_napi_irqs(struct eventpoll *ep)
 {
 	unsigned int napi_id = READ_ONCE(ep->napi_id);
 
-	if (napi_id >= MIN_NAPI_ID && READ_ONCE(ep->prefer_busy_poll))
+	if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll))
 		napi_resume_irqs(napi_id);
 }
 
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 741fa77547001..cab6146a510a1 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -119,7 +119,7 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	unsigned int napi_id = READ_ONCE(sk->sk_napi_id);
 
-	if (napi_id >= MIN_NAPI_ID)
+	if (napi_id_valid(napi_id))
 		napi_busy_loop(napi_id, nonblock ? NULL : sk_busy_loop_end, sk,
 			       READ_ONCE(sk->sk_prefer_busy_poll),
 			       READ_ONCE(sk->sk_busy_poll_budget) ?: BUSY_POLL_BUDGET);
@@ -134,7 +134,7 @@ static inline void skb_mark_napi_id(struct sk_buff *skb,
 	/* If the skb was already marked with a valid NAPI ID, avoid overwriting
 	 * it.
 	 */
-	if (skb->napi_id < MIN_NAPI_ID)
+	if (!napi_id_valid(skb->napi_id))
 		skb->napi_id = napi->napi_id;
 #endif
 }
diff --git a/io_uring/napi.c b/io_uring/napi.c
index b1ade3fda30f3..4a10de03e4269 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -44,7 +44,7 @@ int __io_napi_add_id(struct io_ring_ctx *ctx, unsigned int napi_id)
 	struct io_napi_entry *e;
 
 	/* Non-NAPI IDs can be rejected. */
-	if (napi_id < MIN_NAPI_ID)
+	if (!napi_id_valid(napi_id))
 		return -EINVAL;
 
 	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
@@ -87,7 +87,7 @@ static int __io_napi_del_id(struct io_ring_ctx *ctx, unsigned int napi_id)
 	struct io_napi_entry *e;
 
 	/* Non-NAPI IDs can be rejected. */
-	if (napi_id < MIN_NAPI_ID)
+	if (!napi_id_valid(napi_id))
 		return -EINVAL;
 
 	hash_list = &ctx->napi_ht[hash_min(napi_id, HASH_BITS(ctx->napi_ht))];
diff --git a/net/core/dev.c b/net/core/dev.c
index d5ab9a4b318ea..bcb266ab29126 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1008,7 +1008,7 @@ struct net_device *dev_get_by_napi_id(unsigned int napi_id)
 
 	WARN_ON_ONCE(!rcu_read_lock_held());
 
-	if (napi_id < MIN_NAPI_ID)
+	if (!napi_id_valid(napi_id))
 		return NULL;
 
 	napi = napi_by_id(napi_id);
@@ -6740,7 +6740,7 @@ static void napi_hash_add(struct napi_struct *napi)
 
 	/* 0..NR_CPUS range is reserved for sender_cpu use */
 	do {
-		if (unlikely(++napi_gen_id < MIN_NAPI_ID))
+		if (unlikely(!napi_id_valid(++napi_gen_id)))
 			napi_gen_id = MIN_NAPI_ID;
 	} while (napi_by_id(napi_gen_id));
 
@@ -6911,7 +6911,7 @@ netif_napi_dev_list_add(struct net_device *dev, struct napi_struct *napi)
 
 	higher = &dev->napi_list;
 	list_for_each_entry(pos, &dev->napi_list, dev_list) {
-		if (pos->napi_id >= MIN_NAPI_ID)
+		if (napi_id_valid(pos->napi_id))
 			pos_id = pos->napi_id;
 		else if (pos->config)
 			pos_id = pos->config->napi_id;
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index c18bb53d13fd8..22ac51356d9f6 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -267,7 +267,7 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
 
 	prev_id = UINT_MAX;
 	list_for_each_entry(napi, &netdev->napi_list, dev_list) {
-		if (napi->napi_id < MIN_NAPI_ID)
+		if (!napi_id_valid(napi->napi_id))
 			continue;
 
 		/* Dump continuation below depends on the list being sorted */
diff --git a/net/core/page_pool_user.c b/net/core/page_pool_user.c
index 9d8a3d8597fa8..c82a95beceff8 100644
--- a/net/core/page_pool_user.c
+++ b/net/core/page_pool_user.c
@@ -233,7 +233,7 @@ page_pool_nl_fill(struct sk_buff *rsp, const struct page_pool *pool,
 		goto err_cancel;
 
 	napi_id = pool->p.napi ? READ_ONCE(pool->p.napi->napi_id) : 0;
-	if (napi_id >= MIN_NAPI_ID &&
+	if (napi_id_valid(napi_id) &&
 	    nla_put_uint(rsp, NETDEV_A_PAGE_POOL_NAPI_ID, napi_id))
 		goto err_cancel;
 
diff --git a/net/core/sock.c b/net/core/sock.c
index a197f0a0b8788..53c7af0038c4f 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2042,7 +2042,7 @@ int sk_getsockopt(struct sock *sk, int level, int optname,
 		v.val = READ_ONCE(sk->sk_napi_id);
 
 		/* aggregate non-NAPI IDs down to 0 */
-		if (v.val < MIN_NAPI_ID)
+		if (!napi_id_valid(v.val))
 			v.val = 0;
 
 		break;
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 89d2bef964698..0edf259730726 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -875,7 +875,7 @@ static bool xsk_no_wakeup(struct sock *sk)
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* Prefer busy-polling, skip the wakeup. */
 	return READ_ONCE(sk->sk_prefer_busy_poll) && READ_ONCE(sk->sk_ll_usec) &&
-		READ_ONCE(sk->sk_napi_id) >= MIN_NAPI_ID;
+		napi_id_valid(READ_ONCE(sk->sk_napi_id));
 #else
 	return false;
 #endif

From c935af429ec2344ffe716f869ddde43f5f1b20dc Mon Sep 17 00:00:00 2001
From: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Date: Fri, 14 Feb 2025 21:58:28 +0100
Subject: [PATCH 0660/2753] selftests: net: add support for testing SO_RCVMARK
 and SO_RCVPRIORITY

Introduce tests to verify the correct functionality of the SO_RCVMARK and
SO_RCVPRIORITY socket options.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Suggested-by: Ferenc Fejes <fejes@inf.elte.hu>
Signed-off-by: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/20250214205828.48503-1-annaemesenyiri@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/.gitignore        |   1 +
 tools/testing/selftests/net/Makefile          |   2 +
 tools/testing/selftests/net/so_rcv_listener.c | 168 ++++++++++++++++++
 tools/testing/selftests/net/test_so_rcv.sh    |  73 ++++++++
 4 files changed, 244 insertions(+)
 create mode 100644 tools/testing/selftests/net/so_rcv_listener.c
 create mode 100755 tools/testing/selftests/net/test_so_rcv.sh

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 28a715a8ef2b1..80dcae53ef55e 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -42,6 +42,7 @@ socket
 so_incoming_cpu
 so_netns_cookie
 so_txtime
+so_rcv_listener
 stress_reuseport_listen
 tap
 tcp_fastopen_backup_key
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index b6271714504d9..8d6116b80cf1a 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -33,6 +33,7 @@ TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
+TEST_PROGS += test_so_rcv.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
 TEST_PROGS += netns-name.sh
 TEST_PROGS += nl_netdev.py
@@ -76,6 +77,7 @@ TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict tls tun tap epoll_busy_
 TEST_GEN_FILES += toeplitz
 TEST_GEN_FILES += cmsg_sender
 TEST_GEN_FILES += stress_reuseport_listen
+TEST_GEN_FILES += so_rcv_listener
 TEST_PROGS += test_vxlan_vnifiltering.sh
 TEST_GEN_FILES += io_uring_zerocopy_tx
 TEST_PROGS += io_uring_zerocopy_tx.sh
diff --git a/tools/testing/selftests/net/so_rcv_listener.c b/tools/testing/selftests/net/so_rcv_listener.c
new file mode 100644
index 0000000000000..bc5841192aa6b
--- /dev/null
+++ b/tools/testing/selftests/net/so_rcv_listener.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <errno.h>
+#include <netdb.h>
+#include <stdbool.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <linux/types.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <arpa/inet.h>
+
+#ifndef SO_RCVPRIORITY
+#define SO_RCVPRIORITY 82
+#endif
+
+struct options {
+	__u32 val;
+	int name;
+	int rcvname;
+	const char *host;
+	const char *service;
+} opt;
+
+static void __attribute__((noreturn)) usage(const char *bin)
+{
+	printf("Usage: %s [opts] <dst host> <dst port / service>\n", bin);
+	printf("Options:\n"
+		"\t\t-M val  Test SO_RCVMARK\n"
+		"\t\t-P val  Test SO_RCVPRIORITY\n"
+		"");
+	exit(EXIT_FAILURE);
+}
+
+static void parse_args(int argc, char *argv[])
+{
+	int o;
+
+	while ((o = getopt(argc, argv, "M:P:")) != -1) {
+		switch (o) {
+		case 'M':
+			opt.val = atoi(optarg);
+			opt.name = SO_MARK;
+			opt.rcvname = SO_RCVMARK;
+			break;
+		case 'P':
+			opt.val = atoi(optarg);
+			opt.name = SO_PRIORITY;
+			opt.rcvname = SO_RCVPRIORITY;
+			break;
+		default:
+			usage(argv[0]);
+			break;
+		}
+	}
+
+	if (optind != argc - 2)
+		usage(argv[0]);
+
+	opt.host = argv[optind];
+	opt.service = argv[optind + 1];
+}
+
+int main(int argc, char *argv[])
+{
+	int err = 0;
+	int recv_fd = -1;
+	int ret_value = 0;
+	__u32 recv_val;
+	struct cmsghdr *cmsg;
+	char cbuf[CMSG_SPACE(sizeof(__u32))];
+	char recv_buf[CMSG_SPACE(sizeof(__u32))];
+	struct iovec iov[1];
+	struct msghdr msg;
+	struct sockaddr_in recv_addr4;
+	struct sockaddr_in6 recv_addr6;
+
+	parse_args(argc, argv);
+
+	int family = strchr(opt.host, ':') ? AF_INET6 : AF_INET;
+
+	recv_fd = socket(family, SOCK_DGRAM, IPPROTO_UDP);
+	if (recv_fd < 0) {
+		perror("Can't open recv socket");
+		ret_value = -errno;
+		goto cleanup;
+	}
+
+	err = setsockopt(recv_fd, SOL_SOCKET, opt.rcvname, &opt.val, sizeof(opt.val));
+	if (err < 0) {
+		perror("Recv setsockopt error");
+		ret_value = -errno;
+		goto cleanup;
+	}
+
+	if (family == AF_INET) {
+		memset(&recv_addr4, 0, sizeof(recv_addr4));
+		recv_addr4.sin_family = family;
+		recv_addr4.sin_port = htons(atoi(opt.service));
+
+		if (inet_pton(family, opt.host, &recv_addr4.sin_addr) <= 0) {
+			perror("Invalid IPV4 address");
+			ret_value = -errno;
+			goto cleanup;
+		}
+
+		err = bind(recv_fd, (struct sockaddr *)&recv_addr4, sizeof(recv_addr4));
+	} else {
+		memset(&recv_addr6, 0, sizeof(recv_addr6));
+		recv_addr6.sin6_family = family;
+		recv_addr6.sin6_port = htons(atoi(opt.service));
+
+		if (inet_pton(family, opt.host, &recv_addr6.sin6_addr) <= 0) {
+			perror("Invalid IPV6 address");
+			ret_value = -errno;
+			goto cleanup;
+		}
+
+		err = bind(recv_fd, (struct sockaddr *)&recv_addr6, sizeof(recv_addr6));
+	}
+
+	if (err < 0) {
+		perror("Recv bind error");
+		ret_value = -errno;
+		goto cleanup;
+	}
+
+	iov[0].iov_base = recv_buf;
+	iov[0].iov_len = sizeof(recv_buf);
+
+	memset(&msg, 0, sizeof(msg));
+	msg.msg_iov = iov;
+	msg.msg_iovlen = 1;
+	msg.msg_control = cbuf;
+	msg.msg_controllen = sizeof(cbuf);
+
+	err = recvmsg(recv_fd, &msg, 0);
+	if (err < 0) {
+		perror("Message receive error");
+		ret_value = -errno;
+		goto cleanup;
+	}
+
+	for (cmsg = CMSG_FIRSTHDR(&msg); cmsg != NULL; cmsg = CMSG_NXTHDR(&msg, cmsg)) {
+		if (cmsg->cmsg_level == SOL_SOCKET && cmsg->cmsg_type == opt.name) {
+			recv_val = *(__u32 *)CMSG_DATA(cmsg);
+			printf("Received value: %u\n", recv_val);
+
+			if (recv_val != opt.val) {
+				fprintf(stderr, "Error: expected value: %u, got: %u\n",
+					opt.val, recv_val);
+				ret_value = -EINVAL;
+			}
+			goto cleanup;
+		}
+	}
+
+	fprintf(stderr, "Error: No matching cmsg received\n");
+	ret_value = -ENOMSG;
+
+cleanup:
+	if (recv_fd >= 0)
+		close(recv_fd);
+
+	return ret_value;
+}
diff --git a/tools/testing/selftests/net/test_so_rcv.sh b/tools/testing/selftests/net/test_so_rcv.sh
new file mode 100755
index 0000000000000..d8aa4362879da
--- /dev/null
+++ b/tools/testing/selftests/net/test_so_rcv.sh
@@ -0,0 +1,73 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source lib.sh
+
+HOSTS=("127.0.0.1" "::1")
+PORT=1234
+TOTAL_TESTS=0
+FAILED_TESTS=0
+
+declare -A TESTS=(
+	["SO_RCVPRIORITY"]="-P 2"
+	["SO_RCVMARK"]="-M 3"
+)
+
+check_result() {
+	((TOTAL_TESTS++))
+	if [ "$1" -ne 0 ]; then
+		((FAILED_TESTS++))
+	fi
+}
+
+cleanup()
+{
+	cleanup_ns $NS
+}
+
+trap cleanup EXIT
+
+setup_ns NS
+
+for HOST in "${HOSTS[@]}"; do
+	PROTOCOL="IPv4"
+	if [[ "$HOST" == "::1" ]]; then
+		PROTOCOL="IPv6"
+	fi
+	for test_name in "${!TESTS[@]}"; do
+		echo "Running $test_name test, $PROTOCOL"
+		arg=${TESTS[$test_name]}
+
+		ip netns exec $NS ./so_rcv_listener $arg $HOST $PORT &
+		LISTENER_PID=$!
+
+		sleep 0.5
+
+		if ! ip netns exec $NS ./cmsg_sender $arg $HOST $PORT; then
+			echo "Sender failed for $test_name, $PROTOCOL"
+			kill "$LISTENER_PID" 2>/dev/null
+			wait "$LISTENER_PID"
+			check_result 1
+			continue
+		fi
+
+		wait "$LISTENER_PID"
+		LISTENER_EXIT_CODE=$?
+
+		if [ "$LISTENER_EXIT_CODE" -eq 0 ]; then
+			echo "Rcv test OK for $test_name, $PROTOCOL"
+			check_result 0
+		else
+			echo "Rcv test FAILED for $test_name, $PROTOCOL"
+			check_result 1
+		fi
+	done
+done
+
+if [ "$FAILED_TESTS" -ne 0 ]; then
+	echo "FAIL - $FAILED_TESTS/$TOTAL_TESTS tests failed"
+	exit ${KSFT_FAIL}
+else
+	echo "OK - All $TOTAL_TESTS tests passed"
+	exit ${KSFT_PASS}
+fi

From a127c18462ea619a1ace1f00540807e009dbf225 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 14 Feb 2025 21:12:29 +0000
Subject: [PATCH 0661/2753] netlink: Add nla_put_empty_nest helper

Creating empty nests is helpful when the exact attributes to be exposed
in the future are not known. Encapsulate the logic in a helper.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250214211255.14194-2-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netlink.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/include/net/netlink.h b/include/net/netlink.h
index e015ffbed819c..29e0db9403820 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -118,6 +118,7 @@
  *   nla_nest_start(skb, type)		start a nested attribute
  *   nla_nest_end(skb, nla)		finalize a nested attribute
  *   nla_nest_cancel(skb, nla)		cancel nested attribute construction
+ *   nla_put_empty_nest(skb, type)	create an empty nest
  *
  * Attribute Length Calculations:
  *   nla_attr_size(payload)		length of attribute w/o padding
@@ -2240,6 +2241,20 @@ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start)
 	nlmsg_trim(skb, start);
 }
 
+/**
+ * nla_put_empty_nest - Create an empty nest
+ * @skb: socket buffer the message is stored in
+ * @attrtype: attribute type of the container
+ *
+ * This function is a helper for creating empty nests.
+ *
+ * Returns: 0 when successful or -EMSGSIZE on failure.
+ */
+static inline int nla_put_empty_nest(struct sk_buff *skb, int attrtype)
+{
+	return nla_nest_start(skb, attrtype) ? 0 : -EMSGSIZE;
+}
+
 /**
  * __nla_validate_nested - Validate a stream of nested attributes
  * @start: container attribute

From df524c8f57711a3fe54abb087794819840005fd0 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 14 Feb 2025 21:12:30 +0000
Subject: [PATCH 0662/2753] netdev-genl: Add an XSK attribute to queues

Expose a new per-queue nest attribute, xsk, which will be present for
queues that are being used for AF_XDP. If the queue is not being used for
AF_XDP, the nest will not be present.

In the future, this attribute can be extended to include more data about
XSK as it is needed.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250214211255.14194-3-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 13 ++++++++++++-
 include/uapi/linux/netdev.h             |  6 ++++++
 net/core/netdev-genl.c                  | 12 ++++++++++++
 tools/include/uapi/linux/netdev.h       |  6 ++++++
 4 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 288923e965aed..85402a2e289c4 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -276,6 +276,9 @@ attribute-sets:
         doc: The timeout, in nanoseconds, of how long to suspend irq
              processing, if event polling finds events
         type: uint
+  -
+    name: xsk-info
+    attributes: []
   -
     name: queue
     attributes:
@@ -294,6 +297,9 @@ attribute-sets:
       -
         name: type
         doc: Queue type as rx, tx. Each queue type defines a separate ID space.
+             XDP TX queues allocated in the kernel are not linked to NAPIs and
+             thus not listed. AF_XDP queues will have more information set in
+             the xsk attribute.
         type: u32
         enum: queue-type
       -
@@ -309,7 +315,11 @@ attribute-sets:
         doc: io_uring memory provider information.
         type: nest
         nested-attributes: io-uring-provider-info
-
+      -
+        name: xsk
+        doc: XSK information for this queue, if any.
+        type: nest
+        nested-attributes: xsk-info
   -
     name: qstats
     doc: |
@@ -652,6 +662,7 @@ operations:
             - ifindex
             - dmabuf
             - io-uring
+            - xsk
       dump:
         request:
           attributes:
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6c6ee183802d3..4e82f3871473b 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -136,6 +136,11 @@ enum {
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_XSK_INFO_MAX,
+	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -143,6 +148,7 @@ enum {
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
+	NETDEV_A_QUEUE_XSK,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 22ac51356d9f6..c92fba65b20d1 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -400,11 +400,23 @@ netdev_nl_queue_fill_one(struct sk_buff *rsp, struct net_device *netdev,
 		if (params->mp_ops &&
 		    params->mp_ops->nl_fill(params->mp_priv, rsp, rxq))
 			goto nla_put_failure;
+#ifdef CONFIG_XDP_SOCKETS
+		if (rxq->pool)
+			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
+				goto nla_put_failure;
+#endif
+
 		break;
 	case NETDEV_QUEUE_TYPE_TX:
 		txq = netdev_get_tx_queue(netdev, q_idx);
 		if (nla_put_napi_id(rsp, txq->napi))
 			goto nla_put_failure;
+#ifdef CONFIG_XDP_SOCKETS
+		if (txq->pool)
+			if (nla_put_empty_nest(rsp, NETDEV_A_QUEUE_XSK))
+				goto nla_put_failure;
+#endif
+		break;
 	}
 
 	genlmsg_end(rsp, hdr);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6c6ee183802d3..4e82f3871473b 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -136,6 +136,11 @@ enum {
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
 };
 
+enum {
+	__NETDEV_A_XSK_INFO_MAX,
+	NETDEV_A_XSK_INFO_MAX = (__NETDEV_A_XSK_INFO_MAX - 1)
+};
+
 enum {
 	NETDEV_A_QUEUE_ID = 1,
 	NETDEV_A_QUEUE_IFINDEX,
@@ -143,6 +148,7 @@ enum {
 	NETDEV_A_QUEUE_NAPI_ID,
 	NETDEV_A_QUEUE_DMABUF,
 	NETDEV_A_QUEUE_IO_URING,
+	NETDEV_A_QUEUE_XSK,
 
 	__NETDEV_A_QUEUE_MAX,
 	NETDEV_A_QUEUE_MAX = (__NETDEV_A_QUEUE_MAX - 1)

From 788e52e2b66844301fe09f3372d46d8c62f6ebe4 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 14 Feb 2025 21:12:31 +0000
Subject: [PATCH 0663/2753] selftests: drv-net: Test queue xsk attribute

Test that queues which are used for AF_XDP have the xsk nest attribute.
The attribute is currently empty, but its existence means the AF_XDP is
being used for the queue. Enable CONFIG_XDP_SOCKETS for
selftests/drivers/net tests, as well.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250214211255.14194-4-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/.gitignore  |  2 +
 tools/testing/selftests/drivers/net/Makefile  |  3 +
 tools/testing/selftests/drivers/net/config    |  1 +
 tools/testing/selftests/drivers/net/queues.py | 42 +++++++-
 .../selftests/drivers/net/xdp_helper.c        | 98 +++++++++++++++++++
 5 files changed, 143 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/drivers/net/.gitignore
 create mode 100644 tools/testing/selftests/drivers/net/xdp_helper.c

diff --git a/tools/testing/selftests/drivers/net/.gitignore b/tools/testing/selftests/drivers/net/.gitignore
new file mode 100644
index 0000000000000..ec746f374e858
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+xdp_helper
diff --git a/tools/testing/selftests/drivers/net/Makefile b/tools/testing/selftests/drivers/net/Makefile
index 28b6d47f812dd..0c95bd944d56d 100644
--- a/tools/testing/selftests/drivers/net/Makefile
+++ b/tools/testing/selftests/drivers/net/Makefile
@@ -1,10 +1,13 @@
 # SPDX-License-Identifier: GPL-2.0
+CFLAGS += $(KHDR_INCLUDES)
 
 TEST_INCLUDES := $(wildcard lib/py/*.py) \
 		 $(wildcard lib/sh/*.sh) \
 		 ../../net/net_helper.sh \
 		 ../../net/lib.sh \
 
+TEST_GEN_FILES := xdp_helper
+
 TEST_PROGS := \
 	netcons_basic.sh \
 	netcons_fragmented_msg.sh \
diff --git a/tools/testing/selftests/drivers/net/config b/tools/testing/selftests/drivers/net/config
index a2d8af60876df..f27172ddee0a1 100644
--- a/tools/testing/selftests/drivers/net/config
+++ b/tools/testing/selftests/drivers/net/config
@@ -4,3 +4,4 @@ CONFIG_CONFIGFS_FS=y
 CONFIG_NETCONSOLE=m
 CONFIG_NETCONSOLE_DYNAMIC=y
 CONFIG_NETCONSOLE_EXTENDED_LOG=y
+CONFIG_XDP_SOCKETS=y
diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 38303da957ee5..5fdfebc6415f4 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -2,13 +2,16 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from lib.py import ksft_disruptive, ksft_exit, ksft_run
-from lib.py import ksft_eq, ksft_raises, KsftSkipEx
+from lib.py import ksft_eq, ksft_raises, KsftSkipEx, KsftFailEx
 from lib.py import EthtoolFamily, NetdevFamily, NlError
 from lib.py import NetDrvEnv
 from lib.py import cmd, defer, ip
 import errno
 import glob
-
+import os
+import socket
+import struct
+import subprocess
 
 def sys_get_queues(ifname, qtype='rx') -> int:
     folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
@@ -21,6 +24,39 @@ def nl_get_queues(cfg, nl, qtype='rx'):
         return len([q for q in queues if q['type'] == qtype])
     return None
 
+def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    xdp = subprocess.Popen([f"{test_dir}/xdp_helper", f"{cfg.ifindex}", f"{xdp_queue_id}"],
+                           stdin=subprocess.PIPE, stdout=subprocess.PIPE, bufsize=1,
+                           text=True)
+    defer(xdp.kill)
+
+    stdout, stderr = xdp.communicate(timeout=10)
+    rx = tx = False
+
+    if xdp.returncode == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.returncode > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
+    queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+    if not queues:
+        raise KsftSkipEx("Netlink reports no queues")
+
+    for q in queues:
+        if q['id'] == 0:
+            if q['type'] == 'rx':
+                rx = True
+            if q['type'] == 'tx':
+                tx = True
+
+            ksft_eq(q['xsk'], {})
+        else:
+            if 'xsk' in q:
+                _fail("Check failed: xsk attribute set.")
+
+    ksft_eq(rx, True)
+    ksft_eq(tx, True)
 
 def get_queues(cfg, nl) -> None:
     snl = NetdevFamily(recv_size=4096)
@@ -81,7 +117,7 @@ def check_down(cfg, nl) -> None:
 
 def main() -> None:
     with NetDrvEnv(__file__, queue_count=100) as cfg:
-        ksft_run([get_queues, addremove_queues, check_down], args=(cfg, NetdevFamily()))
+        ksft_run([get_queues, addremove_queues, check_down, check_xdp], args=(cfg, NetdevFamily()))
     ksft_exit()
 
 
diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c
new file mode 100644
index 0000000000000..cf06a88b830b8
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/xdp_helper.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <sys/mman.h>
+#include <sys/socket.h>
+#include <linux/if_xdp.h>
+#include <linux/if_link.h>
+#include <net/if.h>
+#include <inttypes.h>
+
+#define UMEM_SZ (1U << 16)
+#define NUM_DESC (UMEM_SZ / 2048)
+
+/* this is a simple helper program that creates an XDP socket and does the
+ * minimum necessary to get bind() to succeed.
+ *
+ * this test program is not intended to actually process packets, but could be
+ * extended in the future if that is actually needed.
+ *
+ * it is used by queues.py to ensure the xsk netlinux attribute is set
+ * correctly.
+ */
+int main(int argc, char **argv)
+{
+	struct xdp_umem_reg umem_reg = { 0 };
+	struct sockaddr_xdp sxdp = { 0 };
+	int num_desc = NUM_DESC;
+	void *umem_area;
+	int ifindex;
+	int sock_fd;
+	int queue;
+	char byte;
+
+	if (argc != 3) {
+		fprintf(stderr, "Usage: %s ifindex queue_id", argv[0]);
+		return 1;
+	}
+
+	sock_fd = socket(AF_XDP, SOCK_RAW, 0);
+	if (sock_fd < 0) {
+		perror("socket creation failed");
+		/* if the kernel doesn't support AF_XDP, let the test program
+		 * know with -1. All other error paths return 1.
+		 */
+		if (errno == EAFNOSUPPORT)
+			return -1;
+		return 1;
+	}
+
+	ifindex = atoi(argv[1]);
+	queue = atoi(argv[2]);
+
+	umem_area = mmap(NULL, UMEM_SZ, PROT_READ | PROT_WRITE, MAP_PRIVATE |
+			MAP_ANONYMOUS, -1, 0);
+	if (umem_area == MAP_FAILED) {
+		perror("mmap failed");
+		return 1;
+	}
+
+	umem_reg.addr = (uintptr_t)umem_area;
+	umem_reg.len = UMEM_SZ;
+	umem_reg.chunk_size = 2048;
+	umem_reg.headroom = 0;
+
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_REG, &umem_reg,
+		   sizeof(umem_reg));
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_FILL_RING, &num_desc,
+		   sizeof(num_desc));
+	setsockopt(sock_fd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &num_desc,
+		   sizeof(num_desc));
+	setsockopt(sock_fd, SOL_XDP, XDP_RX_RING, &num_desc, sizeof(num_desc));
+
+	sxdp.sxdp_family = AF_XDP;
+	sxdp.sxdp_ifindex = ifindex;
+	sxdp.sxdp_queue_id = queue;
+	sxdp.sxdp_flags = 0;
+
+	if (bind(sock_fd, (struct sockaddr *)&sxdp, sizeof(sxdp)) != 0) {
+		munmap(umem_area, UMEM_SZ);
+		perror("bind failed");
+		close(sock_fd);
+		return 1;
+	}
+
+	/* give the parent program some data when the socket is ready*/
+	fprintf(stdout, "%d\n", sock_fd);
+
+	/* parent program will write a byte to stdin when its ready for this
+	 * helper to exit
+	 */
+	read(STDIN_FILENO, &byte, 1);
+
+	close(sock_fd);
+	return 0;
+}

From 637026e591fae3b91986c01e3beab9bb664bda2d Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 14 Feb 2025 14:43:40 -0800
Subject: [PATCH 0664/2753] net: move stale comment about ntuple validation

Gal points out that the comment now belongs further down, since
the original if condition was split into two in
commit de7f7582dff2 ("net: ethtool: prevent flow steering to RSS contexts which don't exist")

Link: https://lore.kernel.org/de4a2a8a-1eb9-4fa8-af87-7526e58218e9@nvidia.com
Reviewed-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250214224340.2268691-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/ioctl.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 98b7dcea207a6..271c7cef9ef3e 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -992,8 +992,10 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 	if (rc)
 		return rc;
 
-	/* Nonzero ring with RSS only makes sense if NIC adds them together */
 	if (cmd == ETHTOOL_SRXCLSRLINS && info.fs.flow_type & FLOW_RSS) {
+		/* Nonzero ring with RSS only makes sense
+		 * if NIC adds them together
+		 */
 		if (!ops->cap_rss_rxnfc_adds &&
 		    ethtool_get_flow_spec_ring(info.fs.ring_cookie))
 			return -EINVAL;

From b5e489003abcff4b65088d49fce78dcb3cc1ae06 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 14 Feb 2025 14:46:01 -0800
Subject: [PATCH 0665/2753] netdev: clarify GSO vs csum in qstats

Could be just me, but I had to pause and double check that the Tx csum
counter in qstat should include GSO'd packets. GSO pretty much implies
csum so one could possibly interpret the csum counter as pure csum offload.

But the counters are based on virtio:

  [tx_needs_csum]
      The number of packets which require checksum calculation by the device.

  [rx_needs_csum]
      The number of packets with VIRTIO_NET_HDR_F_NEEDS_CSUM.

and VIRTIO_NET_HDR_F_NEEDS_CSUM gets set on GSO packets virtio sends.

Clarify this in the spec to avoid any confusion.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250214224601.2271201-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 85402a2e289c4..766b82005d184 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -467,6 +467,8 @@ attribute-sets:
         name: tx-needs-csum
         doc: |
           Number of packets that required the device to calculate the checksum.
+          This counter includes the number of GSO wire packets for which device
+          calculated the L4 checksum.
         type: uint
       -
         name: tx-hw-gso-packets

From b0b0f52042acb324cd39fbefb2b1ae83af8f8ae1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 16 Feb 2025 09:41:09 -0800
Subject: [PATCH 0666/2753] eth: fbnic: support TCP segmentation offload

Add TSO support to the driver. Device can handle unencapsulated or
IPv6-in-IPv6 packets. Any other tunnel stacks are handled with
GSO partial.

Validate that the packet can be offloaded in ndo_features_check.
Main thing we need to check for is that the header geometry can
be expressed in the decriptor fields (offsets aren't too large).

Report number of TSO super-packets via the qstat API.

Link: https://patch.msgid.link/20250216174109.2808351-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    |  25 ++-
 .../net/ethernet/meta/fbnic/fbnic_netdev.h    |   3 +
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c  | 146 +++++++++++++++++-
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h  |   1 +
 4 files changed, 163 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index b12672d1607e9..c59f1ce8de324 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -517,7 +517,7 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 	struct fbnic_net *fbn = netdev_priv(dev);
 	struct fbnic_ring *txr = fbn->tx[idx];
 	struct fbnic_queue_stats *stats;
-	u64 stop, wake, csum;
+	u64 stop, wake, csum, lso;
 	unsigned int start;
 	u64 bytes, packets;
 
@@ -530,13 +530,15 @@ static void fbnic_get_queue_stats_tx(struct net_device *dev, int idx,
 		bytes = stats->bytes;
 		packets = stats->packets;
 		csum = stats->twq.csum_partial;
+		lso = stats->twq.lso;
 		stop = stats->twq.stop;
 		wake = stats->twq.wake;
 	} while (u64_stats_fetch_retry(&stats->syncp, start));
 
 	tx->bytes = bytes;
 	tx->packets = packets;
-	tx->needs_csum = csum;
+	tx->needs_csum = csum + lso;
+	tx->hw_gso_wire_packets = lso;
 	tx->stop = stop;
 	tx->wake = wake;
 }
@@ -549,7 +551,8 @@ static void fbnic_get_base_stats(struct net_device *dev,
 
 	tx->bytes = fbn->tx_stats.bytes;
 	tx->packets = fbn->tx_stats.packets;
-	tx->needs_csum = fbn->tx_stats.twq.csum_partial;
+	tx->needs_csum = fbn->tx_stats.twq.csum_partial + fbn->tx_stats.twq.lso;
+	tx->hw_gso_wire_packets = fbn->tx_stats.twq.lso;
 	tx->stop = fbn->tx_stats.twq.stop;
 	tx->wake = fbn->tx_stats.twq.wake;
 
@@ -650,11 +653,25 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
+	netdev->gso_partial_features =
+		NETIF_F_GSO_GRE |
+		NETIF_F_GSO_GRE_CSUM |
+		NETIF_F_GSO_IPXIP4 |
+		NETIF_F_GSO_UDP_TUNNEL |
+		NETIF_F_GSO_UDP_TUNNEL_CSUM;
+
 	netdev->features |=
+		netdev->gso_partial_features |
+		FBNIC_TUN_GSO_FEATURES |
 		NETIF_F_RXHASH |
 		NETIF_F_SG |
 		NETIF_F_HW_CSUM |
-		NETIF_F_RXCSUM;
+		NETIF_F_RXCSUM |
+		NETIF_F_TSO |
+		NETIF_F_TSO_ECN |
+		NETIF_F_TSO6 |
+		NETIF_F_GSO_PARTIAL |
+		NETIF_F_GSO_UDP_L4;
 
 	netdev->hw_features |= netdev->features;
 	netdev->vlan_features |= netdev->features;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
index a392ac1cc4f2f..b84b447a8d8ad 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
@@ -13,6 +13,9 @@
 
 #define FBNIC_MAX_NAPI_VECTORS		128u
 
+/* Natively supported tunnel GSO features (not thru GSO_PARTIAL) */
+#define FBNIC_TUN_GSO_FEATURES		NETIF_F_GSO_IPXIP6
+
 struct fbnic_net {
 	struct fbnic_ring *tx[FBNIC_MAX_TXQS];
 	struct fbnic_ring *rx[FBNIC_MAX_RXQS];
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 24d2b528b66c0..b2e544a66de32 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -6,6 +6,7 @@
 #include <linux/pci.h>
 #include <net/netdev_queues.h>
 #include <net/page_pool/helpers.h>
+#include <net/tcp.h>
 
 #include "fbnic.h"
 #include "fbnic_csr.h"
@@ -18,6 +19,7 @@ enum {
 
 struct fbnic_xmit_cb {
 	u32 bytecount;
+	u16 gso_segs;
 	u8 desc_count;
 	u8 flags;
 	int hw_head;
@@ -178,9 +180,73 @@ static bool fbnic_tx_tstamp(struct sk_buff *skb)
 	return true;
 }
 
+static bool
+fbnic_tx_lso(struct fbnic_ring *ring, struct sk_buff *skb,
+	     struct skb_shared_info *shinfo, __le64 *meta,
+	     unsigned int *l2len, unsigned int *i3len)
+{
+	unsigned int l3_type, l4_type, l4len, hdrlen;
+	unsigned char *l4hdr;
+	__be16 payload_len;
+
+	if (unlikely(skb_cow_head(skb, 0)))
+		return true;
+
+	if (shinfo->gso_type & SKB_GSO_PARTIAL) {
+		l3_type = FBNIC_TWD_L3_TYPE_OTHER;
+	} else if (!skb->encapsulation) {
+		if (ip_hdr(skb)->version == 4)
+			l3_type = FBNIC_TWD_L3_TYPE_IPV4;
+		else
+			l3_type = FBNIC_TWD_L3_TYPE_IPV6;
+	} else {
+		unsigned int o3len;
+
+		o3len = skb_inner_network_header(skb) - skb_network_header(skb);
+		*i3len -= o3len;
+		*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_OHLEN_MASK,
+						o3len / 2));
+		l3_type = FBNIC_TWD_L3_TYPE_V6V6;
+	}
+
+	l4hdr = skb_checksum_start(skb);
+	payload_len = cpu_to_be16(skb->len - (l4hdr - skb->data));
+
+	if (shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+		struct tcphdr *tcph = (struct tcphdr *)l4hdr;
+
+		l4_type = FBNIC_TWD_L4_TYPE_TCP;
+		l4len = __tcp_hdrlen((struct tcphdr *)l4hdr);
+		csum_replace_by_diff(&tcph->check, (__force __wsum)payload_len);
+	} else {
+		struct udphdr *udph = (struct udphdr *)l4hdr;
+
+		l4_type = FBNIC_TWD_L4_TYPE_UDP;
+		l4len = sizeof(struct udphdr);
+		csum_replace_by_diff(&udph->check, (__force __wsum)payload_len);
+	}
+
+	hdrlen = (l4hdr - skb->data) + l4len;
+	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L3_TYPE_MASK, l3_type) |
+			     FIELD_PREP(FBNIC_TWD_L4_TYPE_MASK, l4_type) |
+			     FIELD_PREP(FBNIC_TWD_L4_HLEN_MASK, l4len / 4) |
+			     FIELD_PREP(FBNIC_TWD_MSS_MASK, shinfo->gso_size) |
+			     FBNIC_TWD_FLAG_REQ_LSO);
+
+	FBNIC_XMIT_CB(skb)->bytecount += (shinfo->gso_segs - 1) * hdrlen;
+	FBNIC_XMIT_CB(skb)->gso_segs = shinfo->gso_segs;
+
+	u64_stats_update_begin(&ring->stats.syncp);
+	ring->stats.twq.lso += shinfo->gso_segs;
+	u64_stats_update_end(&ring->stats.syncp);
+
+	return false;
+}
+
 static bool
 fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 {
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
 	unsigned int l2len, i3len;
 
 	if (fbnic_tx_tstamp(skb))
@@ -195,10 +261,15 @@ fbnic_tx_offloads(struct fbnic_ring *ring, struct sk_buff *skb, __le64 *meta)
 	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_CSUM_OFFSET_MASK,
 					skb->csum_offset / 2));
 
-	*meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO);
-	u64_stats_update_begin(&ring->stats.syncp);
-	ring->stats.twq.csum_partial++;
-	u64_stats_update_end(&ring->stats.syncp);
+	if (shinfo->gso_size) {
+		if (fbnic_tx_lso(ring, skb, shinfo, meta, &l2len, &i3len))
+			return true;
+	} else {
+		*meta |= cpu_to_le64(FBNIC_TWD_FLAG_REQ_CSO);
+		u64_stats_update_begin(&ring->stats.syncp);
+		ring->stats.twq.csum_partial++;
+		u64_stats_update_end(&ring->stats.syncp);
+	}
 
 	*meta |= cpu_to_le64(FIELD_PREP(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) |
 			     FIELD_PREP(FBNIC_TWD_L3_IHLEN_MASK, i3len / 2));
@@ -341,7 +412,9 @@ fbnic_xmit_frame_ring(struct sk_buff *skb, struct fbnic_ring *ring)
 
 	/* Write all members within DWORD to condense this into 2 4B writes */
 	FBNIC_XMIT_CB(skb)->bytecount = skb->len;
+	FBNIC_XMIT_CB(skb)->gso_segs = 1;
 	FBNIC_XMIT_CB(skb)->desc_count = 0;
+	FBNIC_XMIT_CB(skb)->flags = 0;
 
 	if (fbnic_tx_offloads(ring, skb, meta))
 		goto err_free;
@@ -368,6 +441,59 @@ netdev_tx_t fbnic_xmit_frame(struct sk_buff *skb, struct net_device *dev)
 	return fbnic_xmit_frame_ring(skb, fbn->tx[q_map]);
 }
 
+static netdev_features_t
+fbnic_features_check_encap_gso(struct sk_buff *skb, struct net_device *dev,
+			       netdev_features_t features, unsigned int l3len)
+{
+	netdev_features_t skb_gso_features;
+	struct ipv6hdr *ip6_hdr;
+	unsigned char l4_hdr;
+	unsigned int start;
+	__be16 frag_off;
+
+	/* Require MANGLEID for GSO_PARTIAL of IPv4.
+	 * In theory we could support TSO with single, innermost v4 header
+	 * by pretending everything before it is L2, but that needs to be
+	 * parsed case by case.. so leaving it for when the need arises.
+	 */
+	if (!(features & NETIF_F_TSO_MANGLEID))
+		features &= ~NETIF_F_TSO;
+
+	skb_gso_features = skb_shinfo(skb)->gso_type;
+	skb_gso_features <<= NETIF_F_GSO_SHIFT;
+
+	/* We'd only clear the native GSO features, so don't bother validating
+	 * if the match can only be on those supported thru GSO_PARTIAL.
+	 */
+	if (!(skb_gso_features & FBNIC_TUN_GSO_FEATURES))
+		return features;
+
+	/* We can only do IPv6-in-IPv6, not v4-in-v6. It'd be nice
+	 * to fall back to partial for this, or any failure below.
+	 * This is just an optimization, UDPv4 will be caught later on.
+	 */
+	if (skb_gso_features & NETIF_F_TSO)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	/* Inner headers multiple of 2 */
+	if ((skb_inner_network_header(skb) - skb_network_header(skb)) % 2)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	/* Encapsulated GSO packet, make 100% sure it's IPv6-in-IPv6. */
+	ip6_hdr = ipv6_hdr(skb);
+	if (ip6_hdr->version != 6)
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	l4_hdr = ip6_hdr->nexthdr;
+	start = (unsigned char *)ip6_hdr - skb->data + sizeof(struct ipv6hdr);
+	start = ipv6_skip_exthdr(skb, start, &l4_hdr, &frag_off);
+	if (frag_off || l4_hdr != IPPROTO_IPV6 ||
+	    skb->data + start != skb_inner_network_header(skb))
+		return features & ~FBNIC_TUN_GSO_FEATURES;
+
+	return features;
+}
+
 netdev_features_t
 fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
 		     netdev_features_t features)
@@ -388,9 +514,12 @@ fbnic_features_check(struct sk_buff *skb, struct net_device *dev,
 	    !FIELD_FIT(FBNIC_TWD_L2_HLEN_MASK, l2len / 2) ||
 	    !FIELD_FIT(FBNIC_TWD_L3_IHLEN_MASK, l3len / 2) ||
 	    !FIELD_FIT(FBNIC_TWD_CSUM_OFFSET_MASK, skb->csum_offset / 2))
-		return features & ~NETIF_F_CSUM_MASK;
+		return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK);
 
-	return features;
+	if (likely(!skb->encapsulation) || !skb_is_gso(skb))
+		return features;
+
+	return fbnic_features_check_encap_gso(skb, dev, features, l3len);
 }
 
 static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
@@ -441,7 +570,7 @@ static void fbnic_clean_twq0(struct fbnic_napi_vector *nv, int napi_budget,
 		}
 
 		total_bytes += FBNIC_XMIT_CB(skb)->bytecount;
-		total_packets += 1;
+		total_packets += FBNIC_XMIT_CB(skb)->gso_segs;
 
 		napi_consume_skb(skb, napi_budget);
 	}
@@ -1105,12 +1234,13 @@ void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,
 	fbn->tx_stats.packets += stats->packets;
 	fbn->tx_stats.dropped += stats->dropped;
 	fbn->tx_stats.twq.csum_partial += stats->twq.csum_partial;
+	fbn->tx_stats.twq.lso += stats->twq.lso;
 	fbn->tx_stats.twq.ts_lost += stats->twq.ts_lost;
 	fbn->tx_stats.twq.ts_packets += stats->twq.ts_packets;
 	fbn->tx_stats.twq.stop += stats->twq.stop;
 	fbn->tx_stats.twq.wake += stats->twq.wake;
 	/* Remember to add new stats here */
-	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 5);
+	BUILD_BUG_ON(sizeof(fbn->tx_stats.twq) / 8 != 6);
 }
 
 static void fbnic_remove_tx_ring(struct fbnic_net *fbn,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index b53a7d28ecd36..89a5c394f8463 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -59,6 +59,7 @@ struct fbnic_queue_stats {
 	union {
 		struct {
 			u64 csum_partial;
+			u64 lso;
 			u64 ts_packets;
 			u64 ts_lost;
 			u64 stop;

From fbf10b86f6057cf79300720da4ea4b77e6708b0d Mon Sep 17 00:00:00 2001
From: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Date: Tue, 24 Dec 2024 12:34:56 +0900
Subject: [PATCH 0667/2753] firmware: imx-scu: fix OF node leak in .probe()

imx_scu_probe() calls of_parse_phandle_with_args(), but does not
release the OF node reference obtained by it. Add a of_node_put() call
after done with the node.

Fixes: f25a066d1a07 ("firmware: imx-scu: Support one TX and one RX")
Signed-off-by: Joe Hattori <joe@pf.is.s.u-tokyo.ac.jp>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/firmware/imx/imx-scu.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/firmware/imx/imx-scu.c b/drivers/firmware/imx/imx-scu.c
index 1dd4362ef9a3f..8c28e25ddc8a6 100644
--- a/drivers/firmware/imx/imx-scu.c
+++ b/drivers/firmware/imx/imx-scu.c
@@ -280,6 +280,7 @@ static int imx_scu_probe(struct platform_device *pdev)
 		return ret;
 
 	sc_ipc->fast_ipc = of_device_is_compatible(args.np, "fsl,imx8-mu-scu");
+	of_node_put(args.np);
 
 	num_channel = sc_ipc->fast_ipc ? 2 : SCU_MU_CHAN_NUM;
 	for (i = 0; i < num_channel; i++) {

From 38f59e0e8bd2b3e1319716e4aeaeb9a6223b006d Mon Sep 17 00:00:00 2001
From: Alexander Stein <alexander.stein@ew.tq-group.com>
Date: Tue, 7 Jan 2025 16:03:09 +0100
Subject: [PATCH 0668/2753] arm64: dts: freescale: tqma8mpql: Fix vqmmc-supply

eMMC is supplied by BUCK5 rail. Use the actual regulator instead of
a virtual fixed regulator.

Fixes: 418d1d840e421 ("arm64: dts: freescale: add initial device tree for TQMa8MPQL with i.MX8MP")
Signed-off-by: Alexander Stein <alexander.stein@ew.tq-group.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 .../boot/dts/freescale/imx8mp-tqma8mpql.dtsi     | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
index 336785a9fba89..3ddc5aaa7c5f0 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-tqma8mpql.dtsi
@@ -1,7 +1,8 @@
 // SPDX-License-Identifier: GPL-2.0-or-later OR MIT
 /*
- * Copyright 2021-2022 TQ-Systems GmbH
- * Author: Alexander Stein <alexander.stein@tq-group.com>
+ * Copyright 2021-2025 TQ-Systems GmbH <linux@ew.tq-group.com>,
+ * D-82229 Seefeld, Germany.
+ * Author: Alexander Stein
  */
 
 #include "imx8mp.dtsi"
@@ -23,15 +24,6 @@
 		regulator-max-microvolt = <3300000>;
 		regulator-always-on;
 	};
-
-	/* e-MMC IO, needed for HS modes */
-	reg_vcc1v8: regulator-vcc1v8 {
-		compatible = "regulator-fixed";
-		regulator-name = "VCC1V8";
-		regulator-min-microvolt = <1800000>;
-		regulator-max-microvolt = <1800000>;
-		regulator-always-on;
-	};
 };
 
 &A53_0 {
@@ -197,7 +189,7 @@
 	no-sd;
 	no-sdio;
 	vmmc-supply = <&reg_vcc3v3>;
-	vqmmc-supply = <&reg_vcc1v8>;
+	vqmmc-supply = <&buck5_reg>;
 	status = "okay";
 };
 

From 02d954c0fdf91845169cdacc7405b120f90afe01 Mon Sep 17 00:00:00 2001
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Date: Mon, 10 Feb 2025 16:32:50 +0100
Subject: [PATCH 0669/2753] sched: Compact RSEQ concurrency IDs with reduced
 threads and affinity

When a process reduces its number of threads or clears bits in its CPU
affinity mask, the mm_cid allocation should eventually converge towards
smaller values.

However, the change introduced by:

commit 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency
IDs for intermittent workloads")

adds a per-mm/CPU recent_cid which is never unset unless a thread
migrates.

This is a tradeoff between:

A) Preserving cache locality after a transition from many threads to few
   threads, or after reducing the hamming weight of the allowed CPU mask.

B) Making the mm_cid upper bounds wrt nr threads and allowed CPU mask
   easy to document and understand.

C) Allowing applications to eventually react to mm_cid compaction after
   reduction of the nr threads or allowed CPU mask, making the tracking
   of mm_cid compaction easier by shrinking it back towards 0 or not.

D) Making sure applications that periodically reduce and then increase
   again the nr threads or allowed CPU mask still benefit from good
   cache locality with mm_cid.

Introduce the following changes:

* After shrinking the number of threads or reducing the number of
  allowed CPUs, reduce the value of max_nr_cid so expansion of CID
  allocation will preserve cache locality if the number of threads or
  allowed CPUs increase again.

* Only re-use a recent_cid if it is within the max_nr_cid upper bound,
  else find the first available CID.

Fixes: 7e019dcc470f ("sched: Improve cache locality of RSEQ concurrency IDs for intermittent workloads")
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lkml.kernel.org/r/20250210153253.460471-2-gmonaco@redhat.com
---
 include/linux/mm_types.h |  7 ++++---
 kernel/sched/sched.h     | 25 ++++++++++++++++++++++---
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6b27db7f94963..0234f14f2aa6b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -875,10 +875,11 @@ struct mm_struct {
 		 */
 		unsigned int nr_cpus_allowed;
 		/**
-		 * @max_nr_cid: Maximum number of concurrency IDs allocated.
+		 * @max_nr_cid: Maximum number of allowed concurrency
+		 *              IDs allocated.
 		 *
-		 * Track the highest number of concurrency IDs allocated for the
-		 * mm.
+		 * Track the highest number of allowed concurrency IDs
+		 * allocated for the mm.
 		 */
 		atomic_t max_nr_cid;
 		/**
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b93c8c3dc05a5..c8512a9fb0229 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
 {
 	struct cpumask *cidmask = mm_cidmask(mm);
 	struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-	int cid = __this_cpu_read(pcpu_cid->recent_cid);
+	int cid, max_nr_cid, allowed_max_nr_cid;
 
+	/*
+	 * After shrinking the number of threads or reducing the number
+	 * of allowed cpus, reduce the value of max_nr_cid so expansion
+	 * of cid allocation will preserve cache locality if the number
+	 * of threads or allowed cpus increase again.
+	 */
+	max_nr_cid = atomic_read(&mm->max_nr_cid);
+	while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed),
+					   atomic_read(&mm->mm_users))),
+	       max_nr_cid > allowed_max_nr_cid) {
+		/* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */
+		if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) {
+			max_nr_cid = allowed_max_nr_cid;
+			break;
+		}
+	}
 	/* Try to re-use recent cid. This improves cache locality. */
-	if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask))
+	cid = __this_cpu_read(pcpu_cid->recent_cid);
+	if (!mm_cid_is_unset(cid) && cid < max_nr_cid &&
+	    !cpumask_test_and_set_cpu(cid, cidmask))
 		return cid;
 	/*
 	 * Expand cid allocation if the maximum number of concurrency
@@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
 	 * and number of threads. Expanding cid allocation as much as
 	 * possible improves cache locality.
 	 */
-	cid = atomic_read(&mm->max_nr_cid);
+	cid = max_nr_cid;
 	while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) {
+		/* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */
 		if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1))
 			continue;
 		if (!cpumask_test_and_set_cpu(cid, cidmask))

From ec5fd50aeff9c9156304853c6d75eda852d4a2c8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 08:43:35 +0100
Subject: [PATCH 0670/2753] uprobes: Don't use %pK through printk
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Restricted pointers ("%pK") are not meant to be used through printk().
It can unintentionally expose security sensitive, raw pointer values.

Use regular pointer formatting instead.

For more background, see:

  https://lore.kernel.org/lkml/20250113171731-dc10e3c1-da64-4af0-b767-7c7070468023@linutronix.de/

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250217-restricted-pointers-uprobes-v1-1-e8cbe5bb22a7@linutronix.de
---
 kernel/events/uprobes.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index 2ca797cbe465f..bf2a87a0a3787 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -417,7 +417,7 @@ static void update_ref_ctr_warn(struct uprobe *uprobe,
 				struct mm_struct *mm, short d)
 {
 	pr_warn("ref_ctr %s failed for inode: 0x%lx offset: "
-		"0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n",
+		"0x%llx ref_ctr_offset: 0x%llx of mm: 0x%p\n",
 		d > 0 ? "increment" : "decrement", uprobe->inode->i_ino,
 		(unsigned long long) uprobe->offset,
 		(unsigned long long) uprobe->ref_ctr_offset, mm);

From 83964a29379cb08929a39172780a4c2992bc7c93 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Fri, 10 Jan 2025 16:18:29 +0100
Subject: [PATCH 0671/2753] ARM: dts: imx6qdl-apalis: Fix poweroff on Apalis
 iMX6

The current solution for powering off the Apalis iMX6 is not functioning
as intended. To resolve this, it is necessary to power off the
vgen2_reg, which will also set the POWER_ENABLE_MOCI signal to a low
state. This ensures the carrier board is properly informed to initiate
its power-off sequence.

The new solution uses the regulator-poweroff driver, which will power
off the regulator during a system shutdown.

Cc: <stable@vger.kernel.org>
Fixes: 4eb56e26f92e ("ARM: dts: imx6q-apalis: Command pmic to standby for poweroff")
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
index dffab5aa8b9ca..88be29166c1ae 100644
--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
+++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-apalis.dtsi
@@ -108,6 +108,11 @@
 		};
 	};
 
+	poweroff {
+		compatible = "regulator-poweroff";
+		cpu-supply = <&vgen2_reg>;
+	};
+
 	reg_module_3v3: regulator-module-3v3 {
 		compatible = "regulator-fixed";
 		regulator-always-on;
@@ -236,10 +241,6 @@
 	status = "disabled";
 };
 
-&clks {
-	fsl,pmic-stby-poweroff;
-};
-
 /* Apalis SPI1 */
 &ecspi1 {
 	cs-gpios = <&gpio5 25 GPIO_ACTIVE_LOW>;
@@ -527,7 +528,6 @@
 
 	pmic: pmic@8 {
 		compatible = "fsl,pfuze100";
-		fsl,pmic-stby-poweroff;
 		reg = <0x08>;
 
 		regulators {

From 81570d6a7ad37033c7895811551a5a9023706eda Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Sat, 15 Feb 2025 10:56:55 +0100
Subject: [PATCH 0672/2753] gpiolib: protect gpio_chip with SRCU in array_info
 paths in multi get/set

During the locking rework in GPIOLIB, we omitted one important use-case,
namely: setting and getting values for GPIO descriptor arrays with
array_info present.

This patch does two things: first it makes struct gpio_array store the
address of the underlying GPIO device and not chip. Next: it protects
the chip with SRCU from removal in gpiod_get_array_value_complex() and
gpiod_set_array_value_complex().

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250215095655.23152-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 48 +++++++++++++++++++++++++++++-------------
 drivers/gpio/gpiolib.h |  4 ++--
 2 files changed, 35 insertions(+), 17 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 29110dc436f15..5529d8b65f6fb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -3143,6 +3143,8 @@ static int gpiod_get_raw_value_commit(const struct gpio_desc *desc)
 static int gpio_chip_get_multiple(struct gpio_chip *gc,
 				  unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->get_multiple)
 		return gc->get_multiple(gc, mask, bits);
 	if (gc->get) {
@@ -3173,6 +3175,7 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int ret, i = 0;
 
 	/*
@@ -3184,10 +3187,15 @@ int gpiod_get_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
-		ret = gpio_chip_get_multiple(array_info->chip,
-					     array_info->get_mask,
+		ret = gpio_chip_get_multiple(gc, array_info->get_mask,
 					     value_bitmap);
 		if (ret)
 			return ret;
@@ -3468,6 +3476,8 @@ static void gpiod_set_raw_value_commit(struct gpio_desc *desc, bool value)
 static void gpio_chip_set_multiple(struct gpio_chip *gc,
 				   unsigned long *mask, unsigned long *bits)
 {
+	lockdep_assert_held(&gc->gpiodev->srcu);
+
 	if (gc->set_multiple) {
 		gc->set_multiple(gc, mask, bits);
 	} else {
@@ -3485,6 +3495,7 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 				  struct gpio_array *array_info,
 				  unsigned long *value_bitmap)
 {
+	struct gpio_chip *gc;
 	int i = 0;
 
 	/*
@@ -3496,14 +3507,19 @@ int gpiod_set_array_value_complex(bool raw, bool can_sleep,
 	    array_size <= array_info->size &&
 	    (void *)array_info == desc_array + array_info->size) {
 		if (!can_sleep)
-			WARN_ON(array_info->chip->can_sleep);
+			WARN_ON(array_info->gdev->can_sleep);
+
+		guard(srcu)(&array_info->gdev->srcu);
+		gc = srcu_dereference(array_info->gdev->chip,
+				      &array_info->gdev->srcu);
+		if (!gc)
+			return -ENODEV;
 
 		if (!raw && !bitmap_empty(array_info->invert_mask, array_size))
 			bitmap_xor(value_bitmap, value_bitmap,
 				   array_info->invert_mask, array_size);
 
-		gpio_chip_set_multiple(array_info->chip, array_info->set_mask,
-				       value_bitmap);
+		gpio_chip_set_multiple(gc, array_info->set_mask, value_bitmap);
 
 		i = find_first_zero_bit(array_info->set_mask, array_size);
 		if (i == array_size)
@@ -4765,9 +4781,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 {
 	struct gpio_desc *desc;
 	struct gpio_descs *descs;
+	struct gpio_device *gdev;
 	struct gpio_array *array_info = NULL;
-	struct gpio_chip *gc;
 	int count, bitmap_size;
+	unsigned long dflags;
 	size_t descs_size;
 
 	count = gpiod_count(dev, con_id);
@@ -4788,7 +4805,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 		descs->desc[descs->ndescs] = desc;
 
-		gc = gpiod_to_chip(desc);
+		gdev = gpiod_to_gpio_device(desc);
 		/*
 		 * If pin hardware number of array member 0 is also 0, select
 		 * its chip as a candidate for fast bitmap processing path.
@@ -4796,8 +4813,8 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 		if (descs->ndescs == 0 && gpio_chip_hwgpio(desc) == 0) {
 			struct gpio_descs *array;
 
-			bitmap_size = BITS_TO_LONGS(gc->ngpio > count ?
-						    gc->ngpio : count);
+			bitmap_size = BITS_TO_LONGS(gdev->ngpio > count ?
+						    gdev->ngpio : count);
 
 			array = krealloc(descs, descs_size +
 					 struct_size(array_info, invert_mask, 3 * bitmap_size),
@@ -4817,7 +4834,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 
 			array_info->desc = descs->desc;
 			array_info->size = count;
-			array_info->chip = gc;
+			array_info->gdev = gdev;
 			bitmap_set(array_info->get_mask, descs->ndescs,
 				   count - descs->ndescs);
 			bitmap_set(array_info->set_mask, descs->ndescs,
@@ -4830,7 +4847,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 			continue;
 
 		/* Unmark array members which don't belong to the 'fast' chip */
-		if (array_info->chip != gc) {
+		if (array_info->gdev != gdev) {
 			__clear_bit(descs->ndescs, array_info->get_mask);
 			__clear_bit(descs->ndescs, array_info->set_mask);
 		}
@@ -4853,9 +4870,10 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 					    array_info->set_mask);
 			}
 		} else {
+			dflags = READ_ONCE(desc->flags);
 			/* Exclude open drain or open source from fast output */
-			if (gpiochip_line_is_open_drain(gc, descs->ndescs) ||
-			    gpiochip_line_is_open_source(gc, descs->ndescs))
+			if (test_bit(FLAG_OPEN_DRAIN, &dflags) ||
+			    test_bit(FLAG_OPEN_SOURCE, &dflags))
 				__clear_bit(descs->ndescs,
 					    array_info->set_mask);
 			/* Identify 'fast' pins which require invertion */
@@ -4867,7 +4885,7 @@ struct gpio_descs *__must_check gpiod_get_array(struct device *dev,
 	if (array_info)
 		dev_dbg(dev,
 			"GPIO array info: chip=%s, size=%d, get_mask=%lx, set_mask=%lx, invert_mask=%lx\n",
-			array_info->chip->label, array_info->size,
+			array_info->gdev->label, array_info->size,
 			*array_info->get_mask, *array_info->set_mask,
 			*array_info->invert_mask);
 	return descs;
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 83690f72f7e5c..147156ec502b2 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -114,7 +114,7 @@ extern const char *const gpio_suffixes[];
  *
  * @desc:		Array of pointers to the GPIO descriptors
  * @size:		Number of elements in desc
- * @chip:		Parent GPIO chip
+ * @gdev:		Parent GPIO device
  * @get_mask:		Get mask used in fastpath
  * @set_mask:		Set mask used in fastpath
  * @invert_mask:	Invert mask used in fastpath
@@ -126,7 +126,7 @@ extern const char *const gpio_suffixes[];
 struct gpio_array {
 	struct gpio_desc	**desc;
 	unsigned int		size;
-	struct gpio_chip	*chip;
+	struct gpio_device	*gdev;
 	unsigned long		*get_mask;
 	unsigned long		*set_mask;
 	unsigned long		invert_mask[];

From 94c80f748873514af27b9fac3f72acafcde3bcd6 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:36 +0530
Subject: [PATCH 0673/2753] octeontx2-pf: use xdp_return_frame() to free xdp
 buffers

xdp_return_frames() will help to free the xdp frames and their
associated pages back to page pool.

Signed-off-by: Geetha sowjanya <gakula@marvell.com>
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../marvell/octeontx2/nic/otx2_common.h       |  4 +-
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |  7 ++-
 .../marvell/octeontx2/nic/otx2_txrx.c         | 53 +++++++++++--------
 .../marvell/octeontx2/nic/otx2_txrx.h         |  1 +
 4 files changed, 38 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 65814e3dc93f5..d5fbccb289df8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -21,6 +21,7 @@
 #include <linux/time64.h>
 #include <linux/dim.h>
 #include <uapi/linux/if_macsec.h>
+#include <net/page_pool/helpers.h>
 
 #include <mbox.h>
 #include <npc.h>
@@ -1094,7 +1095,8 @@ int otx2_del_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_add_macfilter(struct net_device *netdev, const u8 *mac);
 int otx2_enable_rxvlan(struct otx2_nic *pf, bool enable);
 int otx2_install_rxvlan_offload_flow(struct otx2_nic *pfvf);
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx);
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags);
 u16 otx2_get_max_mtu(struct otx2_nic *pfvf);
 int otx2_handle_ntuple_tc_features(struct net_device *netdev,
 				   netdev_features_t features);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index e1dde93e8af82..4347a3c95350f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2691,7 +2691,6 @@ static int otx2_get_vf_config(struct net_device *netdev, int vf,
 static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 			    int qidx)
 {
-	struct page *page;
 	u64 dma_addr;
 	int err = 0;
 
@@ -2701,11 +2700,11 @@ static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 	if (dma_mapping_error(pf->dev, dma_addr))
 		return -ENOMEM;
 
-	err = otx2_xdp_sq_append_pkt(pf, dma_addr, xdpf->len, qidx);
+	err = otx2_xdp_sq_append_pkt(pf, xdpf, dma_addr, xdpf->len,
+				     qidx, XDP_REDIRECT);
 	if (!err) {
 		otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE);
-		page = virt_to_page(xdpf->data);
-		put_page(page);
+		xdp_return_frame(xdpf);
 		return -ENOMEM;
 	}
 	return 0;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 224cef9389274..4a72750431036 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -96,20 +96,16 @@ static unsigned int frag_num(unsigned int i)
 
 static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_snd_queue *sq,
-				 struct nix_cqe_tx_s *cqe)
+				     struct nix_cqe_tx_s *cqe)
 {
 	struct nix_send_comp_s *snd_comp = &cqe->comp;
 	struct sg_list *sg;
-	struct page *page;
-	u64 pa;
 
 	sg = &sq->sg[snd_comp->sqe_id];
-
-	pa = otx2_iova_to_phys(pfvf->iommu_domain, sg->dma_addr[0]);
-	otx2_dma_unmap_page(pfvf, sg->dma_addr[0],
-			    sg->size[0], DMA_TO_DEVICE);
-	page = virt_to_page(phys_to_virt(pa));
-	put_page(page);
+	if (sg->flags & XDP_REDIRECT)
+		otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE);
+	xdp_return_frame((struct xdp_frame *)sg->skb);
+	sg->skb = (u64)NULL;
 }
 
 static void otx2_snd_pkt_handler(struct otx2_nic *pfvf,
@@ -1359,8 +1355,9 @@ void otx2_free_pending_sqe(struct otx2_nic *pfvf)
 	}
 }
 
-static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
-				int len, int *offset)
+static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq,
+				struct xdp_frame *xdpf,
+				u64 dma_addr, int len, int *offset, u16 flags)
 {
 	struct nix_sqe_sg_s *sg = NULL;
 	u64 *iova = NULL;
@@ -1377,9 +1374,12 @@ static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq, u64 dma_addr,
 	sq->sg[sq->head].dma_addr[0] = dma_addr;
 	sq->sg[sq->head].size[0] = len;
 	sq->sg[sq->head].num_segs = 1;
+	sq->sg[sq->head].flags = flags;
+	sq->sg[sq->head].skb = (u64)xdpf;
 }
 
-bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
+bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
+			    u64 iova, int len, u16 qidx, u16 flags)
 {
 	struct nix_sqe_hdr_s *sqe_hdr;
 	struct otx2_snd_queue *sq;
@@ -1405,7 +1405,7 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, u64 iova, int len, u16 qidx)
 
 	offset = sizeof(*sqe_hdr);
 
-	otx2_xdp_sqe_add_sg(sq, iova, len, &offset);
+	otx2_xdp_sqe_add_sg(sq, xdpf, iova, len, &offset, flags);
 	sqe_hdr->sizem1 = (offset / 16) - 1;
 	pfvf->hw_ops->sqe_flush(pfvf, sq, offset, qidx);
 
@@ -1419,6 +1419,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     bool *need_xdp_flush)
 {
 	unsigned char *hard_start;
+	struct otx2_pool *pool;
+	struct xdp_frame *xdpf;
 	int qidx = cq->cq_idx;
 	struct xdp_buff xdp;
 	struct page *page;
@@ -1426,6 +1428,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 	u32 act;
 	int err;
 
+	pool = &pfvf->qset.pool[qidx];
 	iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM;
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_page(phys_to_virt(pa));
@@ -1444,19 +1447,21 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 	case XDP_TX:
 		qidx += pfvf->hw.tx_queues;
 		cq->pool_ptrs++;
-		return otx2_xdp_sq_append_pkt(pfvf, iova,
-					      cqe->sg.seg_size, qidx);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		return otx2_xdp_sq_append_pkt(pfvf, xdpf, cqe->sg.seg_addr,
+					      cqe->sg.seg_size, qidx, XDP_TX);
 	case XDP_REDIRECT:
 		cq->pool_ptrs++;
 		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
-
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
 		if (!err) {
 			*need_xdp_flush = true;
 			return true;
 		}
-		put_page(page);
+
+		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+				    DMA_FROM_DEVICE);
+		xdpf = xdp_convert_buff_to_frame(&xdp);
+		xdp_return_frame(xdpf);
 		break;
 	default:
 		bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act);
@@ -1465,10 +1470,14 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 		trace_xdp_exception(pfvf->netdev, prog, act);
 		break;
 	case XDP_DROP:
-		otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
-				    DMA_FROM_DEVICE);
-		put_page(page);
 		cq->pool_ptrs++;
+		if (page->pp) {
+			page_pool_recycle_direct(pool->page_pool, page);
+		} else {
+			otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
+					    DMA_FROM_DEVICE);
+			put_page(page);
+		}
 		return true;
 	}
 	return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index d23810963fdbd..92e1e84cad75c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -76,6 +76,7 @@ struct otx2_rcv_queue {
 
 struct sg_list {
 	u16	num_segs;
+	u16	flags;
 	u64	skb;
 	u64	size[OTX2_MAX_FRAGS_IN_SQE];
 	u64	dma_addr[OTX2_MAX_FRAGS_IN_SQE];

From b4164de5041b51cda3438e75bce668e2556057c3 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:37 +0530
Subject: [PATCH 0674/2753] octeontx2-pf: Add AF_XDP non-zero copy support

Set xdp rx ring memory type as MEM_TYPE_PAGE_POOL for
af-xdp to work. This is needed since xdp_return_frame
internally will use page pools.

Fixes: 06059a1a9a4a ("octeontx2-pf: Add XDP support to netdev PF")
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 2b49bfec78692..161cf33ef89ed 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1047,6 +1047,7 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 	int err, pool_id, non_xdp_queues;
 	struct nix_aq_enq_req *aq;
 	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
 
 	cq = &qset->cq[qidx];
 	cq->cq_idx = qidx;
@@ -1055,8 +1056,13 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cq_type = CQ_RX;
 		cq->cint_idx = qidx;
 		cq->cqe_cnt = qset->rqe_cnt;
-		if (pfvf->xdp_prog)
+		if (pfvf->xdp_prog) {
+			pool = &qset->pool[qidx];
 			xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0);
+			xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+						   MEM_TYPE_PAGE_POOL,
+						   pool->page_pool);
+		}
 	} else if (qidx < non_xdp_queues) {
 		cq->cq_type = CQ_TX;
 		cq->cint_idx = qidx - pfvf->hw.rx_queues;

From efabce29015189cb5cd8066cf29eb1d754de6c3c Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:38 +0530
Subject: [PATCH 0675/2753] octeontx2-pf: AF_XDP zero copy receive support

This patch adds support to AF_XDP zero copy for CN10K.
This patch specifically adds receive side support. In this approach once
a xdp program with zero copy support on a specific rx queue is enabled,
then that receive quse is disabled/detached from the existing kernel
queue and re-assigned to the umem memory.

Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeontx2/nic/Makefile   |   2 +-
 .../ethernet/marvell/octeontx2/nic/cn10k.c    |   7 +-
 .../marvell/octeontx2/nic/otx2_common.c       | 114 ++++++++---
 .../marvell/octeontx2/nic/otx2_common.h       |   6 +-
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |  25 ++-
 .../marvell/octeontx2/nic/otx2_txrx.c         |  73 +++++--
 .../marvell/octeontx2/nic/otx2_txrx.h         |   6 +
 .../ethernet/marvell/octeontx2/nic/otx2_vf.c  |  12 +-
 .../ethernet/marvell/octeontx2/nic/otx2_xsk.c | 182 ++++++++++++++++++
 .../ethernet/marvell/octeontx2/nic/otx2_xsk.h |  21 ++
 .../ethernet/marvell/octeontx2/nic/qos_sq.c   |   2 +-
 11 files changed, 389 insertions(+), 61 deletions(-)
 create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
 create mode 100644 drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
index cb6513ab35e74..69e0778f9ac10 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/Makefile
@@ -9,7 +9,7 @@ obj-$(CONFIG_RVU_ESWITCH) += rvu_rep.o
 
 rvu_nicpf-y := otx2_pf.o otx2_common.o otx2_txrx.o otx2_ethtool.o \
                otx2_flows.o otx2_tc.o cn10k.o otx2_dmac_flt.o \
-               otx2_devlink.o qos_sq.o qos.o
+               otx2_devlink.o qos_sq.o qos.o otx2_xsk.o
 rvu_nicvf-y := otx2_vf.o
 rvu_rep-y := rep.o
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
index a15cc86635d66..c3b6e0f60a799 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k.c
@@ -112,9 +112,12 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	struct otx2_nic *pfvf = dev;
 	int cnt = cq->pool_ptrs;
 	u64 ptrs[NPA_MAX_BURST];
+	struct otx2_pool *pool;
 	dma_addr_t bufptr;
 	int num_ptrs = 1;
 
+	pool = &pfvf->qset.pool[cq->cq_idx];
+
 	/* Refill pool with new buffers */
 	while (cq->pool_ptrs) {
 		if (otx2_alloc_buffer(pfvf, cq, &bufptr)) {
@@ -124,7 +127,9 @@ int cn10k_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 			break;
 		}
 		cq->pool_ptrs--;
-		ptrs[num_ptrs] = (u64)bufptr + OTX2_HEAD_ROOM;
+		ptrs[num_ptrs] = pool->xsk_pool ?
+				 (u64)bufptr : (u64)bufptr + OTX2_HEAD_ROOM;
+
 		num_ptrs++;
 		if (num_ptrs == NPA_MAX_BURST || cq->pool_ptrs == 0) {
 			__cn10k_aura_freeptr(pfvf, cq->cq_idx, ptrs,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 161cf33ef89ed..92b0dba07853a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -17,6 +17,7 @@
 #include "otx2_common.h"
 #include "otx2_struct.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
 
 static bool otx2_is_pfc_enabled(struct otx2_nic *pfvf)
 {
@@ -549,10 +550,13 @@ static int otx2_alloc_pool_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-			     dma_addr_t *dma)
+			     dma_addr_t *dma, int qidx, int idx)
 {
 	u8 *buf;
 
+	if (pool->xsk_pool)
+		return otx2_xsk_pool_alloc_buf(pfvf, pool, dma, idx);
+
 	if (pool->page_pool)
 		return otx2_alloc_pool_buf(pfvf, pool, dma);
 
@@ -571,12 +575,12 @@ static int __otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 }
 
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma)
+		    dma_addr_t *dma, int qidx, int idx)
 {
 	int ret;
 
 	local_bh_disable();
-	ret = __otx2_alloc_rbuf(pfvf, pool, dma);
+	ret = __otx2_alloc_rbuf(pfvf, pool, dma, qidx, idx);
 	local_bh_enable();
 	return ret;
 }
@@ -584,7 +588,8 @@ int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 int otx2_alloc_buffer(struct otx2_nic *pfvf, struct otx2_cq_queue *cq,
 		      dma_addr_t *dma)
 {
-	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma)))
+	if (unlikely(__otx2_alloc_rbuf(pfvf, cq->rbpool, dma,
+				       cq->cq_idx, cq->pool_ptrs - 1)))
 		return -ENOMEM;
 	return 0;
 }
@@ -884,7 +889,7 @@ void otx2_sqb_flush(struct otx2_nic *pfvf)
 #define RQ_PASS_LVL_AURA (255 - ((95 * 256) / 100)) /* RED when 95% is full */
 #define RQ_DROP_LVL_AURA (255 - ((99 * 256) / 100)) /* Drop when 99% is full */
 
-static int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	struct nix_aq_enq_req *aq;
@@ -1041,7 +1046,7 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 }
 
-static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 {
 	struct otx2_qset *qset = &pfvf->qset;
 	int err, pool_id, non_xdp_queues;
@@ -1057,11 +1062,18 @@ static int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx)
 		cq->cint_idx = qidx;
 		cq->cqe_cnt = qset->rqe_cnt;
 		if (pfvf->xdp_prog) {
-			pool = &qset->pool[qidx];
 			xdp_rxq_info_reg(&cq->xdp_rxq, pfvf->netdev, qidx, 0);
-			xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
-						   MEM_TYPE_PAGE_POOL,
-						   pool->page_pool);
+			pool = &qset->pool[qidx];
+			if (pool->xsk_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_XSK_BUFF_POOL,
+							   NULL);
+				xsk_pool_set_rxq_info(pool->xsk_pool, &cq->xdp_rxq);
+			} else if (pool->page_pool) {
+				xdp_rxq_info_reg_mem_model(&cq->xdp_rxq,
+							   MEM_TYPE_PAGE_POOL,
+							   pool->page_pool);
+			}
 		}
 	} else if (qidx < non_xdp_queues) {
 		cq->cq_type = CQ_TX;
@@ -1281,9 +1293,10 @@ void otx2_free_bufs(struct otx2_nic *pfvf, struct otx2_pool *pool,
 
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_head_page(phys_to_virt(pa));
-
 	if (pool->page_pool) {
 		page_pool_put_full_page(pool->page_pool, page, true);
+	} else if (pool->xsk_pool) {
+		/* Note: No way of identifying xdp_buff */
 	} else {
 		dma_unmap_page_attrs(pfvf->dev, iova, size,
 				     DMA_FROM_DEVICE,
@@ -1298,6 +1311,7 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 	int pool_id, pool_start = 0, pool_end = 0, size = 0;
 	struct otx2_pool *pool;
 	u64 iova;
+	int idx;
 
 	if (type == AURA_NIX_SQ) {
 		pool_start = otx2_get_pool_idx(pfvf, type, 0);
@@ -1312,16 +1326,21 @@ void otx2_free_aura_ptr(struct otx2_nic *pfvf, int type)
 
 	/* Free SQB and RQB pointers from the aura pool */
 	for (pool_id = pool_start; pool_id < pool_end; pool_id++) {
-		iova = otx2_aura_allocptr(pfvf, pool_id);
 		pool = &pfvf->qset.pool[pool_id];
+		iova = otx2_aura_allocptr(pfvf, pool_id);
 		while (iova) {
 			if (type == AURA_NIX_RQ)
 				iova -= OTX2_HEAD_ROOM;
-
 			otx2_free_bufs(pfvf, pool, iova, size);
-
 			iova = otx2_aura_allocptr(pfvf, pool_id);
 		}
+
+		for (idx = 0 ; idx < pool->xdp_cnt; idx++) {
+			if (!pool->xdp[idx])
+				continue;
+
+			xsk_buff_free(pool->xdp[idx]);
+		}
 	}
 }
 
@@ -1338,7 +1357,8 @@ void otx2_aura_pool_free(struct otx2_nic *pfvf)
 		qmem_free(pfvf->dev, pool->stack);
 		qmem_free(pfvf->dev, pool->fc_addr);
 		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
+		devm_kfree(pfvf->dev, pool->xdp);
+		pool->xsk_pool = NULL;
 	}
 	devm_kfree(pfvf->dev, pfvf->qset.pool);
 	pfvf->qset.pool = NULL;
@@ -1425,6 +1445,7 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 		   int stack_pages, int numptrs, int buf_size, int type)
 {
 	struct page_pool_params pp_params = { 0 };
+	struct xsk_buff_pool *xsk_pool;
 	struct npa_aq_enq_req *aq;
 	struct otx2_pool *pool;
 	int err;
@@ -1468,21 +1489,35 @@ int otx2_pool_init(struct otx2_nic *pfvf, u16 pool_id,
 	aq->ctype = NPA_AQ_CTYPE_POOL;
 	aq->op = NPA_AQ_INSTOP_INIT;
 
-	if (type != AURA_NIX_RQ) {
-		pool->page_pool = NULL;
+	if (type != AURA_NIX_RQ)
+		return 0;
+
+	if (!test_bit(pool_id, pfvf->af_xdp_zc_qidx)) {
+		pp_params.order = get_order(buf_size);
+		pp_params.flags = PP_FLAG_DMA_MAP;
+		pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
+		pp_params.nid = NUMA_NO_NODE;
+		pp_params.dev = pfvf->dev;
+		pp_params.dma_dir = DMA_FROM_DEVICE;
+		pool->page_pool = page_pool_create(&pp_params);
+		if (IS_ERR(pool->page_pool)) {
+			netdev_err(pfvf->netdev, "Creation of page pool failed\n");
+			return PTR_ERR(pool->page_pool);
+		}
 		return 0;
 	}
 
-	pp_params.order = get_order(buf_size);
-	pp_params.flags = PP_FLAG_DMA_MAP;
-	pp_params.pool_size = min(OTX2_PAGE_POOL_SZ, numptrs);
-	pp_params.nid = NUMA_NO_NODE;
-	pp_params.dev = pfvf->dev;
-	pp_params.dma_dir = DMA_FROM_DEVICE;
-	pool->page_pool = page_pool_create(&pp_params);
-	if (IS_ERR(pool->page_pool)) {
-		netdev_err(pfvf->netdev, "Creation of page pool failed\n");
-		return PTR_ERR(pool->page_pool);
+	/* Set XSK pool to support AF_XDP zero-copy */
+	xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, pool_id);
+	if (xsk_pool) {
+		pool->xsk_pool = xsk_pool;
+		pool->xdp_cnt = numptrs;
+		pool->xdp = devm_kcalloc(pfvf->dev,
+					 numptrs, sizeof(struct xdp_buff *), GFP_KERNEL);
+		if (IS_ERR(pool->xdp)) {
+			netdev_err(pfvf->netdev, "Creation of xsk pool failed\n");
+			return PTR_ERR(pool->xdp);
+		}
 	}
 
 	return 0;
@@ -1543,9 +1578,18 @@ int otx2_sq_aura_pool_init(struct otx2_nic *pfvf)
 		}
 
 		for (ptr = 0; ptr < num_sqbs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					ptr--;
+					while (ptr >= 0) {
+						xsk_buff_free(pool->xdp[ptr]);
+						ptr--;
+					}
+				}
 				goto err_mem;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);
 			sq->sqb_ptrs[sq->sqb_count++] = (u64)bufptr;
 		}
@@ -1595,11 +1639,19 @@ int otx2_rq_aura_pool_init(struct otx2_nic *pfvf)
 	/* Allocate pointers and free them to aura/pool */
 	for (pool_id = 0; pool_id < hw->rqpool_cnt; pool_id++) {
 		pool = &pfvf->qset.pool[pool_id];
+
 		for (ptr = 0; ptr < num_ptrs; ptr++) {
-			err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
-			if (err)
+			err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
+			if (err) {
+				if (pool->xsk_pool) {
+					while (ptr)
+						xsk_buff_free(pool->xdp[--ptr]);
+				}
 				return -ENOMEM;
+			}
+
 			pfvf->hw_ops->aura_freeptr(pfvf, pool_id,
+						   pool->xsk_pool ? bufptr :
 						   bufptr + OTX2_HEAD_ROOM);
 		}
 	}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index d5fbccb289df8..60508971b62f1 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -532,6 +532,8 @@ struct otx2_nic {
 
 	/* Inline ipsec */
 	struct cn10k_ipsec	ipsec;
+	/* af_xdp zero-copy */
+	unsigned long		*af_xdp_zc_qidx;
 };
 
 static inline bool is_otx2_lbkvf(struct pci_dev *pdev)
@@ -1003,7 +1005,7 @@ void otx2_txschq_free_one(struct otx2_nic *pfvf, u16 lvl, u16 schq);
 void otx2_free_pending_sqe(struct otx2_nic *pfvf);
 void otx2_sqb_flush(struct otx2_nic *pfvf);
 int otx2_alloc_rbuf(struct otx2_nic *pfvf, struct otx2_pool *pool,
-		    dma_addr_t *dma);
+		    dma_addr_t *dma, int qidx, int idx);
 int otx2_rxtx_enable(struct otx2_nic *pfvf, bool enable);
 void otx2_ctx_disable(struct mbox *mbox, int type, bool npa);
 int otx2_nix_config_bp(struct otx2_nic *pfvf, bool enable);
@@ -1033,6 +1035,8 @@ void otx2_pfaf_mbox_destroy(struct otx2_nic *pf);
 void otx2_disable_mbox_intr(struct otx2_nic *pf);
 void otx2_disable_napi(struct otx2_nic *pf);
 irqreturn_t otx2_cq_intr_handler(int irq, void *cq_irq);
+int otx2_rq_init(struct otx2_nic *pfvf, u16 qidx, u16 lpb_aura);
+int otx2_cq_init(struct otx2_nic *pfvf, u16 qidx);
 
 /* RSS configuration APIs*/
 int otx2_rss_init(struct otx2_nic *pfvf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 4347a3c95350f..50a42cd5d50a2 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -27,6 +27,7 @@
 #include "qos.h"
 #include <rvu_trace.h>
 #include "cn10k_ipsec.h"
+#include "otx2_xsk.h"
 
 #define DRV_NAME	"rvu_nicpf"
 #define DRV_STRING	"Marvell RVU NIC Physical Function Driver"
@@ -1662,9 +1663,7 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	struct nix_lf_free_req *free_req;
 	struct mbox *mbox = &pf->mbox;
 	struct otx2_cq_queue *cq;
-	struct otx2_pool *pool;
 	struct msg_req *req;
-	int pool_id;
 	int qidx;
 
 	/* Ensure all SQE are processed */
@@ -1705,13 +1704,6 @@ void otx2_free_hw_resources(struct otx2_nic *pf)
 	/* Free RQ buffer pointers*/
 	otx2_free_aura_ptr(pf, AURA_NIX_RQ);
 
-	for (qidx = 0; qidx < pf->hw.rx_queues; qidx++) {
-		pool_id = otx2_get_pool_idx(pf, AURA_NIX_RQ, qidx);
-		pool = &pf->qset.pool[pool_id];
-		page_pool_destroy(pool->page_pool);
-		pool->page_pool = NULL;
-	}
-
 	otx2_free_cq_res(pf);
 
 	/* Free all ingress bandwidth profiles allocated */
@@ -2788,6 +2780,8 @@ static int otx2_xdp(struct net_device *netdev, struct netdev_bpf *xdp)
 	switch (xdp->command) {
 	case XDP_SETUP_PROG:
 		return otx2_xdp_setup(pf, xdp->prog);
+	case XDP_SETUP_XSK_POOL:
+		return otx2_xsk_pool_setup(pf, xdp->xsk.pool, xdp->xsk.queue_id);
 	default:
 		return -EINVAL;
 	}
@@ -2865,6 +2859,7 @@ static const struct net_device_ops otx2_netdev_ops = {
 	.ndo_set_vf_vlan	= otx2_set_vf_vlan,
 	.ndo_get_vf_config	= otx2_get_vf_config,
 	.ndo_bpf		= otx2_xdp,
+	.ndo_xsk_wakeup		= otx2_xsk_wakeup,
 	.ndo_xdp_xmit           = otx2_xdp_xmit,
 	.ndo_setup_tc		= otx2_setup_tc,
 	.ndo_set_vf_trust	= otx2_ndo_set_vf_trust,
@@ -3203,16 +3198,26 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	/* Enable link notifications */
 	otx2_cgx_config_linkevents(pf, true);
 
+	pf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!pf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_sriov_cleannup;
+	}
+
 #ifdef CONFIG_DCB
 	err = otx2_dcbnl_set_ops(netdev);
 	if (err)
-		goto err_pf_sriov_init;
+		goto err_free_zc_bmap;
 #endif
 
 	otx2_qos_init(pf, qos_txqs);
 
 	return 0;
 
+err_free_zc_bmap:
+	bitmap_free(pf->af_xdp_zc_qidx);
+err_sriov_cleannup:
+	otx2_sriov_vfcfg_cleanup(pf);
 err_pf_sriov_init:
 	otx2_shutdown_tc(pf);
 err_mcam_flow_del:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 4a72750431036..00b6903ba250c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -12,6 +12,7 @@
 #include <linux/bpf_trace.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
+#include <net/xdp.h>
 
 #include "otx2_reg.h"
 #include "otx2_common.h"
@@ -523,9 +524,10 @@ static void otx2_adjust_adaptive_coalese(struct otx2_nic *pfvf, struct otx2_cq_p
 int otx2_napi_handler(struct napi_struct *napi, int budget)
 {
 	struct otx2_cq_queue *rx_cq = NULL;
+	struct otx2_cq_queue *cq = NULL;
+	struct otx2_pool *pool = NULL;
 	struct otx2_cq_poll *cq_poll;
 	int workdone = 0, cq_idx, i;
-	struct otx2_cq_queue *cq;
 	struct otx2_qset *qset;
 	struct otx2_nic *pfvf;
 	int filled_cnt = -1;
@@ -550,6 +552,7 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 
 	if (rx_cq && rx_cq->pool_ptrs)
 		filled_cnt = pfvf->hw_ops->refill_pool_ptrs(pfvf, rx_cq);
+
 	/* Clear the IRQ */
 	otx2_write64(pfvf, NIX_LF_CINTX_INT(cq_poll->cint_idx), BIT_ULL(0));
 
@@ -562,20 +565,31 @@ int otx2_napi_handler(struct napi_struct *napi, int budget)
 		if (pfvf->flags & OTX2_FLAG_ADPTV_INT_COAL_ENABLED)
 			otx2_adjust_adaptive_coalese(pfvf, cq_poll);
 
+		if (likely(cq))
+			pool = &pfvf->qset.pool[cq->cq_idx];
+
 		if (unlikely(!filled_cnt)) {
 			struct refill_work *work;
 			struct delayed_work *dwork;
 
-			work = &pfvf->refill_wrk[cq->cq_idx];
-			dwork = &work->pool_refill_work;
-			/* Schedule a task if no other task is running */
-			if (!cq->refill_task_sched) {
-				work->napi = napi;
-				cq->refill_task_sched = true;
-				schedule_delayed_work(dwork,
-						      msecs_to_jiffies(100));
+			if (likely(cq)) {
+				work = &pfvf->refill_wrk[cq->cq_idx];
+				dwork = &work->pool_refill_work;
+				/* Schedule a task if no other task is running */
+				if (!cq->refill_task_sched) {
+					work->napi = napi;
+					cq->refill_task_sched = true;
+					schedule_delayed_work(dwork,
+							      msecs_to_jiffies(100));
+				}
+				/* Call wake-up for not able to fill buffers */
+				if (pool->xsk_pool)
+					xsk_set_rx_need_wakeup(pool->xsk_pool);
 			}
 		} else {
+			/* Clear wake-up, since buffers are filled successfully */
+			if (pool && pool->xsk_pool)
+				xsk_clear_rx_need_wakeup(pool->xsk_pool);
 			/* Re-enable interrupts */
 			otx2_write64(pfvf,
 				     NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx),
@@ -1226,15 +1240,19 @@ void otx2_cleanup_rx_cqes(struct otx2_nic *pfvf, struct otx2_cq_queue *cq, int q
 	u16 pool_id;
 	u64 iova;
 
-	if (pfvf->xdp_prog)
+	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
+	pool = &pfvf->qset.pool[pool_id];
+
+	if (pfvf->xdp_prog) {
+		if (pool->page_pool)
+			xdp_rxq_info_unreg_mem_model(&cq->xdp_rxq);
+
 		xdp_rxq_info_unreg(&cq->xdp_rxq);
+	}
 
 	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
 		return;
 
-	pool_id = otx2_get_pool_idx(pfvf, AURA_NIX_RQ, qidx);
-	pool = &pfvf->qset.pool[pool_id];
-
 	while (cq->pend_cqe) {
 		cqe = (struct nix_cqe_rx_s *)otx2_get_next_cqe(cq);
 		processed_cqe++;
@@ -1418,17 +1436,28 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_cq_queue *cq,
 				     bool *need_xdp_flush)
 {
+	struct xdp_buff xdp, *xsk_buff = NULL;
 	unsigned char *hard_start;
 	struct otx2_pool *pool;
 	struct xdp_frame *xdpf;
 	int qidx = cq->cq_idx;
-	struct xdp_buff xdp;
 	struct page *page;
 	u64 iova, pa;
 	u32 act;
 	int err;
 
 	pool = &pfvf->qset.pool[qidx];
+
+	if (pool->xsk_pool) {
+		xsk_buff = pool->xdp[--cq->rbpool->xdp_top];
+		if (!xsk_buff)
+			return false;
+
+		xsk_buff->data_end = xsk_buff->data + cqe->sg.seg_size;
+		act = bpf_prog_run_xdp(prog, xsk_buff);
+		goto handle_xdp_verdict;
+	}
+
 	iova = cqe->sg.seg_addr - OTX2_HEAD_ROOM;
 	pa = otx2_iova_to_phys(pfvf->iommu_domain, iova);
 	page = virt_to_page(phys_to_virt(pa));
@@ -1441,6 +1470,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 
+handle_xdp_verdict:
 	switch (act) {
 	case XDP_PASS:
 		break;
@@ -1452,6 +1482,15 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 					      cqe->sg.seg_size, qidx, XDP_TX);
 	case XDP_REDIRECT:
 		cq->pool_ptrs++;
+		if (xsk_buff) {
+			err = xdp_do_redirect(pfvf->netdev, xsk_buff, prog);
+			if (!err) {
+				*need_xdp_flush = true;
+				return true;
+			}
+			return false;
+		}
+
 		err = xdp_do_redirect(pfvf->netdev, &xdp, prog);
 		if (!err) {
 			*need_xdp_flush = true;
@@ -1467,11 +1506,15 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 		bpf_warn_invalid_xdp_action(pfvf->netdev, prog, act);
 		break;
 	case XDP_ABORTED:
+		if (xsk_buff)
+			xsk_buff_free(xsk_buff);
 		trace_xdp_exception(pfvf->netdev, prog, act);
 		break;
 	case XDP_DROP:
 		cq->pool_ptrs++;
-		if (page->pp) {
+		if (xsk_buff) {
+			xsk_buff_free(xsk_buff);
+		} else if (page->pp) {
 			page_pool_recycle_direct(pool->page_pool, page);
 		} else {
 			otx2_dma_unmap_page(pfvf, iova, pfvf->rbsize,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 92e1e84cad75c..8f346fbc8221f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -12,6 +12,7 @@
 #include <linux/iommu.h>
 #include <linux/if_vlan.h>
 #include <net/xdp.h>
+#include <net/xdp_sock_drv.h>
 
 #define LBK_CHAN_BASE	0x000
 #define SDP_CHAN_BASE	0x700
@@ -128,7 +129,11 @@ struct otx2_pool {
 	struct qmem		*stack;
 	struct qmem		*fc_addr;
 	struct page_pool	*page_pool;
+	struct xsk_buff_pool	*xsk_pool;
+	struct xdp_buff		**xdp;
+	u16			xdp_cnt;
 	u16			rbsize;
+	u16			xdp_top;
 };
 
 struct otx2_cq_queue {
@@ -145,6 +150,7 @@ struct otx2_cq_queue {
 	void			*cqe_base;
 	struct qmem		*cqe;
 	struct otx2_pool	*rbpool;
+	bool			xsk_zc_en;
 	struct xdp_rxq_info xdp_rxq;
 } ____cacheline_aligned_in_smp;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index e926c6ce96cff..63ddd262d1229 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -722,15 +722,25 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	if (err)
 		goto err_shutdown_tc;
 
+	vf->af_xdp_zc_qidx = bitmap_zalloc(qcount, GFP_KERNEL);
+	if (!vf->af_xdp_zc_qidx) {
+		err = -ENOMEM;
+		goto err_unreg_devlink;
+	}
+
 #ifdef CONFIG_DCB
 	err = otx2_dcbnl_set_ops(netdev);
 	if (err)
-		goto err_shutdown_tc;
+		goto err_free_zc_bmap;
 #endif
 	otx2_qos_init(vf, qos_txqs);
 
 	return 0;
 
+err_free_zc_bmap:
+	bitmap_free(vf->af_xdp_zc_qidx);
+err_unreg_devlink:
+	otx2_unregister_dl(vf);
 err_shutdown_tc:
 	otx2_shutdown_tc(vf);
 err_unreg_netdev:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
new file mode 100644
index 0000000000000..894c1e0aea6f1
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -0,0 +1,182 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Marvell RVU Ethernet driver
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#include <linux/bpf_trace.h>
+#include <linux/stringify.h>
+#include <net/xdp_sock_drv.h>
+#include <net/xdp.h>
+
+#include "otx2_common.h"
+#include "otx2_xsk.h"
+
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx)
+{
+	struct xdp_buff *xdp;
+	int delta;
+
+	xdp = xsk_buff_alloc(pool->xsk_pool);
+	if (!xdp)
+		return -ENOMEM;
+
+	pool->xdp[pool->xdp_top++] = xdp;
+	*dma = OTX2_DATA_ALIGN(xsk_buff_xdp_get_dma(xdp));
+	/* Adjust xdp->data for unaligned addresses */
+	delta = *dma - xsk_buff_xdp_get_dma(xdp);
+	xdp->data += delta;
+
+	return 0;
+}
+
+static int otx2_xsk_ctx_disable(struct otx2_nic *pfvf, u16 qidx, int aura_id)
+{
+	struct nix_cn10k_aq_enq_req *cn10k_rq_aq;
+	struct npa_aq_enq_req *aura_aq;
+	struct npa_aq_enq_req *pool_aq;
+	struct nix_aq_enq_req *rq_aq;
+
+	if (test_bit(CN10K_LMTST, &pfvf->hw.cap_flag)) {
+		cn10k_rq_aq = otx2_mbox_alloc_msg_nix_cn10k_aq_enq(&pfvf->mbox);
+		if (!cn10k_rq_aq)
+			return -ENOMEM;
+		cn10k_rq_aq->qidx = qidx;
+		cn10k_rq_aq->rq.ena = 0;
+		cn10k_rq_aq->rq_mask.ena = 1;
+		cn10k_rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		cn10k_rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	} else {
+		rq_aq = otx2_mbox_alloc_msg_nix_aq_enq(&pfvf->mbox);
+		if (!rq_aq)
+			return -ENOMEM;
+		rq_aq->qidx = qidx;
+		rq_aq->sq.ena = 0;
+		rq_aq->sq_mask.ena = 1;
+		rq_aq->ctype = NIX_AQ_CTYPE_RQ;
+		rq_aq->op = NIX_AQ_INSTOP_WRITE;
+	}
+
+	aura_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!aura_aq)
+		goto fail;
+
+	aura_aq->aura_id = aura_id;
+	aura_aq->aura.ena = 0;
+	aura_aq->aura_mask.ena = 1;
+	aura_aq->ctype = NPA_AQ_CTYPE_AURA;
+	aura_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	pool_aq = otx2_mbox_alloc_msg_npa_aq_enq(&pfvf->mbox);
+	if (!pool_aq)
+		goto fail;
+
+	pool_aq->aura_id = aura_id;
+	pool_aq->pool.ena = 0;
+	pool_aq->pool_mask.ena = 1;
+
+	pool_aq->ctype = NPA_AQ_CTYPE_POOL;
+	pool_aq->op = NPA_AQ_INSTOP_WRITE;
+
+	return otx2_sync_mbox_msg(&pfvf->mbox);
+
+fail:
+	otx2_mbox_reset(&pfvf->mbox.mbox, 0);
+	return -ENOMEM;
+}
+
+static void otx2_clean_up_rq(struct otx2_nic *pfvf, int qidx)
+{
+	struct otx2_qset *qset = &pfvf->qset;
+	struct otx2_cq_queue *cq;
+	struct otx2_pool *pool;
+	u64 iova;
+
+	/* If the DOWN flag is set SQs are already freed */
+	if (pfvf->flags & OTX2_FLAG_INTF_DOWN)
+		return;
+
+	cq = &qset->cq[qidx];
+	if (cq)
+		otx2_cleanup_rx_cqes(pfvf, cq, qidx);
+
+	pool = &pfvf->qset.pool[qidx];
+	iova = otx2_aura_allocptr(pfvf, qidx);
+	while (iova) {
+		iova -= OTX2_HEAD_ROOM;
+		otx2_free_bufs(pfvf, pool, iova, pfvf->rbsize);
+		iova = otx2_aura_allocptr(pfvf, qidx);
+	}
+
+	mutex_lock(&pfvf->mbox.lock);
+	otx2_xsk_ctx_disable(pfvf, qidx, qidx);
+	mutex_unlock(&pfvf->mbox.lock);
+}
+
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	u16 rx_queues = pf->hw.rx_queues;
+	u16 tx_queues = pf->hw.tx_queues;
+	int err;
+
+	if (qidx >= rx_queues || qidx >= tx_queues)
+		return -EINVAL;
+
+	err = xsk_pool_dma_map(pool, pf->dev, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	if (err)
+		return err;
+
+	set_bit(qidx, pf->af_xdp_zc_qidx);
+	otx2_clean_up_rq(pf, qidx);
+	/* Kick start the NAPI context so that receiving will start */
+	return otx2_xsk_wakeup(pf->netdev, qidx, XDP_WAKEUP_RX);
+}
+
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx)
+{
+	struct net_device *netdev = pf->netdev;
+	struct xsk_buff_pool *pool;
+
+	pool = xsk_get_pool_from_qid(netdev, qidx);
+	if (!pool)
+		return -EINVAL;
+
+	otx2_clean_up_rq(pf, qidx);
+	clear_bit(qidx, pf->af_xdp_zc_qidx);
+	xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+
+	return 0;
+}
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qidx)
+{
+	if (pool)
+		return otx2_xsk_pool_enable(pf, pool, qidx);
+
+	return otx2_xsk_pool_disable(pf, qidx);
+}
+
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
+{
+	struct otx2_nic *pf = netdev_priv(dev);
+	struct otx2_cq_poll *cq_poll = NULL;
+	struct otx2_qset *qset = &pf->qset;
+
+	if (pf->flags & OTX2_FLAG_INTF_DOWN)
+		return -ENETDOWN;
+
+	if (queue_id >= pf->hw.rx_queues)
+		return -EINVAL;
+
+	cq_poll = &qset->napi[queue_id];
+	if (!cq_poll)
+		return -EINVAL;
+
+	/* Trigger interrupt */
+	if (!napi_if_scheduled_mark_missed(&cq_poll->napi))
+		otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), BIT_ULL(0));
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
new file mode 100644
index 0000000000000..022b3433edbbb
--- /dev/null
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Marvell RVU PF/VF Netdev Devlink
+ *
+ * Copyright (C) 2024 Marvell.
+ *
+ */
+
+#ifndef	OTX2_XSK_H
+#define	OTX2_XSK_H
+
+struct otx2_nic;
+struct xsk_buff_pool;
+
+int otx2_xsk_pool_setup(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qid);
+int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qid);
+int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
+			    dma_addr_t *dma, int idx);
+int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+
+#endif /* OTX2_XSK_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
index 9d887bfc31089..c5dbae0e513b6 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/qos_sq.c
@@ -82,7 +82,7 @@ static int otx2_qos_sq_aura_pool_init(struct otx2_nic *pfvf, int qidx)
 	}
 
 	for (ptr = 0; ptr < num_sqbs; ptr++) {
-		err = otx2_alloc_rbuf(pfvf, pool, &bufptr);
+		err = otx2_alloc_rbuf(pfvf, pool, &bufptr, pool_id, ptr);
 		if (err)
 			goto sqb_free;
 		pfvf->hw_ops->aura_freeptr(pfvf, pool_id, bufptr);

From 25b07c1a869457fb1fcbbb744123d4ab05666709 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:39 +0530
Subject: [PATCH 0676/2753] octeontx2-pf: Reconfigure RSS table after enabling
 AF_XDP zerocopy on rx queue

RSS table needs to be reconfigured once a rx queue is enabled or
disabled for AF_XDP zerocopy support. After enabling UMEM on a rx queue,
that queue should not be part of RSS queue selection algorithm.
Similarly the queue should be considered again after UMEM is disabled.

Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c  | 4 ++++
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c | 6 +++++-
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c     | 4 ++++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 92b0dba07853a..6f7c11d59942f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -331,6 +331,10 @@ int otx2_set_rss_table(struct otx2_nic *pfvf, int ctx_id)
 	rss_ctx = rss->rss_ctx[ctx_id];
 	/* Get memory to put this msg */
 	for (idx = 0; idx < rss->rss_size; idx++) {
+		/* Ignore the queue if AF_XDP zero copy is enabled */
+		if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+			continue;
+
 		aq = otx2_mbox_alloc_msg_nix_aq_enq(mbox);
 		if (!aq) {
 			/* The shared memory buffer can be full.
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
index 2d53dc77ef1ef..010385b299886 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c
@@ -910,8 +910,12 @@ static int otx2_get_rxfh(struct net_device *dev,
 		return -ENOENT;
 
 	if (indir) {
-		for (idx = 0; idx < rss->rss_size; idx++)
+		for (idx = 0; idx < rss->rss_size; idx++) {
+			/* Ignore if the rx queue is AF_XDP zero copy enabled */
+			if (test_bit(rss_ctx->ind_tbl[idx], pfvf->af_xdp_zc_qidx))
+				continue;
 			indir[idx] = rss_ctx->ind_tbl[idx];
+		}
 	}
 	if (rxfh->key)
 		memcpy(rxfh->key, rss->key, sizeof(rss->key));
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
index 894c1e0aea6f1..3bdee1603facc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -130,6 +130,8 @@ int otx2_xsk_pool_enable(struct otx2_nic *pf, struct xsk_buff_pool *pool, u16 qi
 
 	set_bit(qidx, pf->af_xdp_zc_qidx);
 	otx2_clean_up_rq(pf, qidx);
+	/* Reconfigure RSS table as 'qidx' cannot be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP);
 	/* Kick start the NAPI context so that receiving will start */
 	return otx2_xsk_wakeup(pf->netdev, qidx, XDP_WAKEUP_RX);
 }
@@ -146,6 +148,8 @@ int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx)
 	otx2_clean_up_rq(pf, qidx);
 	clear_bit(qidx, pf->af_xdp_zc_qidx);
 	xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+	/* Reconfigure RSS table as 'qidx' now need to be part of RSS now */
+	otx2_set_rss_table(pf, DEFAULT_RSS_CONTEXT_GROUP);
 
 	return 0;
 }

From c5c2398eb88b314918a30ce4e2b0e088c3741f33 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:40 +0530
Subject: [PATCH 0677/2753] octeontx2-pf: Prepare for AF_XDP

Implement necessary APIs required for AF_XDP transmit.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../marvell/octeontx2/nic/otx2_common.h       |  1 +
 .../marvell/octeontx2/nic/otx2_txrx.c         | 25 +++++++++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 60508971b62f1..19e9e2e722333 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -1181,4 +1181,5 @@ static inline int mcam_entry_cmp(const void *a, const void *b)
 dma_addr_t otx2_dma_map_skb_frag(struct otx2_nic *pfvf,
 				 struct sk_buff *skb, int seg, int *len);
 void otx2_dma_unmap_skb_frags(struct otx2_nic *pfvf, struct sg_list *sg);
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx);
 #endif /* OTX2_COMMON_H */
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 00b6903ba250c..9a6c1f1a3ee0a 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -30,6 +30,12 @@
 
 DEFINE_STATIC_KEY_FALSE(cn10k_ipsec_sa_enabled);
 
+static int otx2_get_free_sqe(struct otx2_snd_queue *sq)
+{
+	return (sq->cons_head - sq->head - 1 + sq->sqe_cnt)
+		& (sq->sqe_cnt - 1);
+}
+
 static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
@@ -1157,7 +1163,7 @@ bool otx2_sq_append_skb(void *dev, struct netdev_queue *txq,
 	/* Check if there is enough room between producer
 	 * and consumer index.
 	 */
-	free_desc = (sq->cons_head - sq->head - 1 + sq->sqe_cnt) & (sq->sqe_cnt - 1);
+	free_desc = otx2_get_free_sqe(sq);
 	if (free_desc < sq->sqe_thresh)
 		return false;
 
@@ -1396,6 +1402,21 @@ static void otx2_xdp_sqe_add_sg(struct otx2_snd_queue *sq,
 	sq->sg[sq->head].skb = (u64)xdpf;
 }
 
+int otx2_read_free_sqe(struct otx2_nic *pfvf, u16 qidx)
+{
+	struct otx2_snd_queue *sq;
+	int free_sqe;
+
+	sq = &pfvf->qset.sq[qidx];
+	free_sqe = otx2_get_free_sqe(sq);
+	if (free_sqe < sq->sqe_thresh) {
+		netdev_warn(pfvf->netdev, "No free sqe for Send queue%d\n", qidx);
+		return 0;
+	}
+
+	return free_sqe - sq->sqe_thresh;
+}
+
 bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
 			    u64 iova, int len, u16 qidx, u16 flags)
 {
@@ -1404,7 +1425,7 @@ bool otx2_xdp_sq_append_pkt(struct otx2_nic *pfvf, struct xdp_frame *xdpf,
 	int offset, free_sqe;
 
 	sq = &pfvf->qset.sq[qidx];
-	free_sqe = (sq->num_sqbs - *sq->aura_fc_addr) * sq->sqe_per_sqb;
+	free_sqe = otx2_get_free_sqe(sq);
 	if (free_sqe < sq->sqe_thresh)
 		return false;
 

From 53616af09b5a55174e470b456461fa45d8abeb35 Mon Sep 17 00:00:00 2001
From: Suman Ghosh <sumang@marvell.com>
Date: Thu, 13 Feb 2025 11:01:41 +0530
Subject: [PATCH 0678/2753] octeontx2-pf: AF_XDP zero copy transmit support

This patch implements below changes,

1. To avoid concurrency with normal traffic uses
   XDP queues.
2. Since there are chances that XDP and AF_XDP can
   fall under same queue uses separate flags to handle
   dma buffers.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Signed-off-by: Suman Ghosh <sumang@marvell.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../marvell/octeontx2/nic/otx2_common.c       |  4 ++
 .../marvell/octeontx2/nic/otx2_common.h       |  6 +++
 .../ethernet/marvell/octeontx2/nic/otx2_pf.c  |  2 +-
 .../marvell/octeontx2/nic/otx2_txrx.c         | 49 +++++++++++++++----
 .../marvell/octeontx2/nic/otx2_txrx.h         |  2 +
 .../ethernet/marvell/octeontx2/nic/otx2_xsk.c | 43 +++++++++++++++-
 .../ethernet/marvell/octeontx2/nic/otx2_xsk.h |  3 ++
 7 files changed, 96 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
index 6f7c11d59942f..84cd029a85aab 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.c
@@ -1037,6 +1037,10 @@ int otx2_sq_init(struct otx2_nic *pfvf, u16 qidx, u16 sqb_aura)
 
 	sq->stats.bytes = 0;
 	sq->stats.pkts = 0;
+	/* Attach XSK_BUFF_POOL to XDP queue */
+	if (qidx > pfvf->hw.xdp_queues)
+		otx2_attach_xsk_buff(pfvf, sq, (qidx - pfvf->hw.xdp_queues));
+
 
 	chan_offset = qidx % pfvf->hw.tx_chan_cnt;
 	err = pfvf->hw_ops->sq_aq_init(pfvf, qidx, chan_offset, sqb_aura);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index 19e9e2e722333..1e88422825be7 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -129,6 +129,12 @@ enum otx2_errcodes_re {
 	ERRCODE_IL4_CSUM = 0x22,
 };
 
+enum otx2_xdp_action {
+	OTX2_XDP_TX	  = BIT(0),
+	OTX2_XDP_REDIRECT = BIT(1),
+	OTX2_AF_XDP_FRAME = BIT(2),
+};
+
 struct otx2_dev_stats {
 	u64 rx_bytes;
 	u64 rx_frames;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 50a42cd5d50a2..c7c562f0f5e5c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -2693,7 +2693,7 @@ static int otx2_xdp_xmit_tx(struct otx2_nic *pf, struct xdp_frame *xdpf,
 		return -ENOMEM;
 
 	err = otx2_xdp_sq_append_pkt(pf, xdpf, dma_addr, xdpf->len,
-				     qidx, XDP_REDIRECT);
+				     qidx, OTX2_XDP_REDIRECT);
 	if (!err) {
 		otx2_dma_unmap_page(pf, dma_addr, xdpf->len, DMA_TO_DEVICE);
 		xdp_return_frame(xdpf);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 9a6c1f1a3ee0a..6bc5ce5a9f61c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -20,6 +20,7 @@
 #include "otx2_txrx.h"
 #include "otx2_ptp.h"
 #include "cn10k.h"
+#include "otx2_xsk.h"
 
 #define CQE_ADDR(CQ, idx) ((CQ)->cqe_base + ((CQ)->cqe_size * (idx)))
 #define PTP_PORT	        0x13F
@@ -103,13 +104,19 @@ static unsigned int frag_num(unsigned int i)
 
 static void otx2_xdp_snd_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_snd_queue *sq,
-				     struct nix_cqe_tx_s *cqe)
+				     struct nix_cqe_tx_s *cqe,
+				     int *xsk_frames)
 {
 	struct nix_send_comp_s *snd_comp = &cqe->comp;
 	struct sg_list *sg;
 
 	sg = &sq->sg[snd_comp->sqe_id];
-	if (sg->flags & XDP_REDIRECT)
+	if (sg->flags & OTX2_AF_XDP_FRAME) {
+		(*xsk_frames)++;
+		return;
+	}
+
+	if (sg->flags & OTX2_XDP_REDIRECT)
 		otx2_dma_unmap_page(pfvf, sg->dma_addr[0], sg->size[0], DMA_TO_DEVICE);
 	xdp_return_frame((struct xdp_frame *)sg->skb);
 	sg->skb = (u64)NULL;
@@ -434,6 +441,18 @@ int otx2_refill_pool_ptrs(void *dev, struct otx2_cq_queue *cq)
 	return cnt - cq->pool_ptrs;
 }
 
+static void otx2_zc_submit_pkts(struct otx2_nic *pfvf, struct xsk_buff_pool *xsk_pool,
+				int *xsk_frames, int qidx, int budget)
+{
+	if (*xsk_frames)
+		xsk_tx_completed(xsk_pool, *xsk_frames);
+
+	if (xsk_uses_need_wakeup(xsk_pool))
+		xsk_set_tx_need_wakeup(xsk_pool);
+
+	otx2_zc_napi_handler(pfvf, xsk_pool, qidx, budget);
+}
+
 static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 				struct otx2_cq_queue *cq, int budget)
 {
@@ -442,16 +461,22 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 	struct nix_cqe_tx_s *cqe;
 	struct net_device *ndev;
 	int processed_cqe = 0;
+	int xsk_frames = 0;
+
+	qidx = cq->cq_idx - pfvf->hw.rx_queues;
+	sq = &pfvf->qset.sq[qidx];
 
 	if (cq->pend_cqe >= budget)
 		goto process_cqe;
 
-	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe)
+	if (otx2_nix_cq_op_status(pfvf, cq) || !cq->pend_cqe) {
+		if (sq->xsk_pool)
+			otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames,
+					    qidx, budget);
 		return 0;
+	}
 
 process_cqe:
-	qidx = cq->cq_idx - pfvf->hw.rx_queues;
-	sq = &pfvf->qset.sq[qidx];
 
 	while (likely(processed_cqe < budget) && cq->pend_cqe) {
 		cqe = (struct nix_cqe_tx_s *)otx2_get_next_cqe(cq);
@@ -461,10 +486,8 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 			break;
 		}
 
-		qidx = cq->cq_idx - pfvf->hw.rx_queues;
-
 		if (cq->cq_type == CQ_XDP)
-			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe);
+			otx2_xdp_snd_pkt_handler(pfvf, sq, cqe, &xsk_frames);
 		else
 			otx2_snd_pkt_handler(pfvf, cq, &pfvf->qset.sq[qidx],
 					     cqe, budget, &tx_pkts, &tx_bytes);
@@ -505,6 +528,10 @@ static int otx2_tx_napi_handler(struct otx2_nic *pfvf,
 		    netif_carrier_ok(ndev))
 			netif_tx_wake_queue(txq);
 	}
+
+	if (sq->xsk_pool)
+		otx2_zc_submit_pkts(pfvf, sq->xsk_pool, &xsk_frames, qidx, budget);
+
 	return 0;
 }
 
@@ -1499,8 +1526,10 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 		qidx += pfvf->hw.tx_queues;
 		cq->pool_ptrs++;
 		xdpf = xdp_convert_buff_to_frame(&xdp);
-		return otx2_xdp_sq_append_pkt(pfvf, xdpf, cqe->sg.seg_addr,
-					      cqe->sg.seg_size, qidx, XDP_TX);
+		return otx2_xdp_sq_append_pkt(pfvf, xdpf,
+					      cqe->sg.seg_addr,
+					      cqe->sg.seg_size,
+					      qidx, OTX2_XDP_TX);
 	case XDP_REDIRECT:
 		cq->pool_ptrs++;
 		if (xsk_buff) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
index 8f346fbc8221f..acf259d720088 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.h
@@ -106,6 +106,8 @@ struct otx2_snd_queue {
 	/* SQE ring and CPT response queue for Inline IPSEC */
 	struct qmem		*sqe_ring;
 	struct qmem		*cpt_resp;
+	/* Buffer pool for af_xdp zero-copy */
+	struct xsk_buff_pool    *xsk_pool;
 } ____cacheline_aligned_in_smp;
 
 enum cq_type {
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
index 3bdee1603facc..ce10caea8511d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.c
@@ -140,11 +140,14 @@ int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qidx)
 {
 	struct net_device *netdev = pf->netdev;
 	struct xsk_buff_pool *pool;
+	struct otx2_snd_queue *sq;
 
 	pool = xsk_get_pool_from_qid(netdev, qidx);
 	if (!pool)
 		return -EINVAL;
 
+	sq = &pf->qset.sq[qidx + pf->hw.tx_queues];
+	sq->xsk_pool = NULL;
 	otx2_clean_up_rq(pf, qidx);
 	clear_bit(qidx, pf->af_xdp_zc_qidx);
 	xsk_pool_dma_unmap(pool, DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -171,7 +174,7 @@ int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 	if (pf->flags & OTX2_FLAG_INTF_DOWN)
 		return -ENETDOWN;
 
-	if (queue_id >= pf->hw.rx_queues)
+	if (queue_id >= pf->hw.rx_queues || queue_id >= pf->hw.tx_queues)
 		return -EINVAL;
 
 	cq_poll = &qset->napi[queue_id];
@@ -179,8 +182,44 @@ int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 		return -EINVAL;
 
 	/* Trigger interrupt */
-	if (!napi_if_scheduled_mark_missed(&cq_poll->napi))
+	if (!napi_if_scheduled_mark_missed(&cq_poll->napi)) {
 		otx2_write64(pf, NIX_LF_CINTX_ENA_W1S(cq_poll->cint_idx), BIT_ULL(0));
+		otx2_write64(pf, NIX_LF_CINTX_INT_W1S(cq_poll->cint_idx), BIT_ULL(0));
+	}
 
 	return 0;
 }
+
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx)
+{
+	if (test_bit(qidx, pfvf->af_xdp_zc_qidx))
+		sq->xsk_pool = xsk_get_pool_from_qid(pfvf->netdev, qidx);
+}
+
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget)
+{
+	struct xdp_desc *xdp_desc = pool->tx_descs;
+	int err, i, work_done = 0, batch;
+
+	budget = min(budget, otx2_read_free_sqe(pfvf, queue));
+	batch = xsk_tx_peek_release_desc_batch(pool, budget);
+	if (!batch)
+		return;
+
+	for (i = 0; i < batch; i++) {
+		dma_addr_t dma_addr;
+
+		dma_addr = xsk_buff_raw_get_dma(pool, xdp_desc[i].addr);
+		err = otx2_xdp_sq_append_pkt(pfvf, NULL, dma_addr, xdp_desc[i].len,
+					     queue, OTX2_AF_XDP_FRAME);
+		if (!err) {
+			netdev_err(pfvf->netdev, "AF_XDP: Unable to transfer packet err%d\n", err);
+			break;
+		}
+		work_done++;
+	}
+
+	if (work_done)
+		xsk_tx_release(pool);
+}
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
index 022b3433edbbb..8047fafee8feb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_xsk.h
@@ -17,5 +17,8 @@ int otx2_xsk_pool_disable(struct otx2_nic *pf, u16 qid);
 int otx2_xsk_pool_alloc_buf(struct otx2_nic *pfvf, struct otx2_pool *pool,
 			    dma_addr_t *dma, int idx);
 int otx2_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags);
+void otx2_zc_napi_handler(struct otx2_nic *pfvf, struct xsk_buff_pool *pool,
+			  int queue, int budget);
+void otx2_attach_xsk_buff(struct otx2_nic *pfvf, struct otx2_snd_queue *sq, int qidx);
 
 #endif /* OTX2_XSK_H */

From 43130d02baa137033c25297aaae95fd0edc41654 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Fri, 14 Feb 2025 14:42:50 +0800
Subject: [PATCH 0679/2753] page_pool: avoid infinite loop to schedule delayed
 worker

We noticed the kworker in page_pool_release_retry() was waken
up repeatedly and infinitely in production because of the
buggy driver causing the inflight less than 0 and warning
us in page_pool_inflight()[1].

Since the inflight value goes negative, it means we should
not expect the whole page_pool to get back to work normally.

This patch mitigates the adverse effect by not rescheduling
the kworker when detecting the inflight negative in
page_pool_release_retry().

[1]
[Mon Feb 10 20:36:11 2025] ------------[ cut here ]------------
[Mon Feb 10 20:36:11 2025] Negative(-51446) inflight packet-pages
...
[Mon Feb 10 20:36:11 2025] Call Trace:
[Mon Feb 10 20:36:11 2025]  page_pool_release_retry+0x23/0x70
[Mon Feb 10 20:36:11 2025]  process_one_work+0x1b1/0x370
[Mon Feb 10 20:36:11 2025]  worker_thread+0x37/0x3a0
[Mon Feb 10 20:36:11 2025]  kthread+0x11a/0x140
[Mon Feb 10 20:36:11 2025]  ? process_one_work+0x370/0x370
[Mon Feb 10 20:36:11 2025]  ? __kthread_cancel_work+0x40/0x40
[Mon Feb 10 20:36:11 2025]  ret_from_fork+0x35/0x40
[Mon Feb 10 20:36:11 2025] ---[ end trace ebffe800f33e7e34 ]---
Note: before this patch, the above calltrace would flood the
dmesg due to repeated reschedule of release_dw kworker.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250214064250.85987-1-kerneljasonxing@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/page_pool.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 1c6fec08bc434..acef1fcd8ddcf 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -1112,7 +1112,13 @@ static void page_pool_release_retry(struct work_struct *wq)
 	int inflight;
 
 	inflight = page_pool_release(pool);
-	if (!inflight)
+	/* In rare cases, a driver bug may cause inflight to go negative.
+	 * Don't reschedule release if inflight is 0 or negative.
+	 * - If 0, the page_pool has been destroyed
+	 * - if negative, we will never recover
+	 * in both cases no reschedule is necessary.
+	 */
+	if (inflight <= 0)
 		return;
 
 	/* Periodic warning for page pools the user can't see */

From 5afb1596b90c0055bad56c97a4ed3a92a0b9595a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 14 Feb 2025 17:18:20 +0100
Subject: [PATCH 0680/2753] vxlan: Drop 'changelink' parameter from
 vxlan_dev_configure()

vxlan_dev_configure() only has a single caller that passes false
for the changelink parameter. Drop the parameter and inline the
sole value.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/vxlan/vxlan_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index ac5bc78edfd7b..9d3919265a52b 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -3936,7 +3936,7 @@ static void vxlan_config_apply(struct net_device *dev,
 }
 
 static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
-			       struct vxlan_config *conf, bool changelink,
+			       struct vxlan_config *conf,
 			       struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
@@ -3947,7 +3947,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
 	if (ret)
 		return ret;
 
-	vxlan_config_apply(dev, conf, lowerdev, src_net, changelink);
+	vxlan_config_apply(dev, conf, lowerdev, src_net, false);
 
 	return 0;
 }
@@ -3965,7 +3965,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev,
 	int err;
 
 	dst = &vxlan->default_dst;
-	err = vxlan_dev_configure(net, dev, conf, false, extack);
+	err = vxlan_dev_configure(net, dev, conf, extack);
 	if (err)
 		return err;
 

From d42d543368343c0449a4e433b5f02e063a86209c Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 14 Feb 2025 17:18:21 +0100
Subject: [PATCH 0681/2753] vxlan: Join / leave MC group after remote changes

When a vxlan netdevice is brought up, if its default remote is a multicast
address, the device joins the indicated group.

Therefore when the multicast remote address changes, the device should
leave the current group and subscribe to the new one. Similarly when the
interface used for endpoint communication is changed in a situation when
multicast remote is configured. This is currently not done.

Both vxlan_igmp_join() and vxlan_igmp_leave() can however fail. So it is
possible that with such fix, the netdevice will end up in an inconsistent
situation where the old group is not joined anymore, but joining the new
group fails. Should we join the new group first, and leave the old one
second, we might end up in the opposite situation, where both groups are
joined. Undoing any of this during rollback is going to be similarly
problematic.

One solution would be to just forbid the change when the netdevice is up.
However in vnifilter mode, changing the group address is allowed, and these
problems are simply ignored (see vxlan_vni_update_group()):

 # ip link add name br up type bridge vlan_filtering 1
 # ip link add vx1 up master br type vxlan external vnifilter local 192.0.2.1 dev lo dstport 4789
 # bridge vni add dev vx1 vni 200 group 224.0.0.1
 # tcpdump -i lo &
 # bridge vni add dev vx1 vni 200 group 224.0.0.2
 18:55:46.523438 IP 0.0.0.0 > 224.0.0.22: igmp v3 report, 1 group record(s)
 18:55:46.943447 IP 0.0.0.0 > 224.0.0.22: igmp v3 report, 1 group record(s)
 # bridge vni
 dev               vni                group/remote
 vx1               200                224.0.0.2

Having two different modes of operation for conceptually the same interface
is silly, so in this patch, just do what the vnifilter code does and deal
with the errors by crossing fingers real hard.

The vnifilter code leaves old before joining new, and in case of join /
leave failures does not roll back the configuration changes that have
already been applied, but bails out of joining if it could not leave. Do
the same here: leave before join, apply changes unconditionally and do not
attempt to join if we couldn't leave.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/vxlan/vxlan_core.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 9d3919265a52b..e2354c02def0e 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -4419,6 +4419,7 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 			    struct netlink_ext_ack *extack)
 {
 	struct vxlan_dev *vxlan = netdev_priv(dev);
+	bool rem_ip_changed, change_igmp;
 	struct net_device *lowerdev;
 	struct vxlan_config conf;
 	struct vxlan_rdst *dst;
@@ -4442,8 +4443,13 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (err)
 		return err;
 
+	rem_ip_changed = !vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip);
+	change_igmp = vxlan->dev->flags & IFF_UP &&
+		      (rem_ip_changed ||
+		       dst->remote_ifindex != conf.remote_ifindex);
+
 	/* handle default dst entry */
-	if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) {
+	if (rem_ip_changed) {
 		u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni);
 
 		spin_lock_bh(&vxlan->hash_lock[hash_index]);
@@ -4487,6 +4493,9 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 		}
 	}
 
+	if (change_igmp && vxlan_addr_multicast(&dst->remote_ip))
+		err = vxlan_multicast_leave(vxlan);
+
 	if (conf.age_interval != vxlan->cfg.age_interval)
 		mod_timer(&vxlan->age_timer, jiffies);
 
@@ -4494,7 +4503,12 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	if (lowerdev && lowerdev != dst->remote_dev)
 		dst->remote_dev = lowerdev;
 	vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true);
-	return 0;
+
+	if (!err && change_igmp &&
+	    vxlan_addr_multicast(&dst->remote_ip))
+		err = vxlan_multicast_join(vxlan);
+
+	return err;
 }
 
 static void vxlan_dellink(struct net_device *dev, struct list_head *head)

From f802f172d78b8b96dcd1832dc7c8da8ee9dcbc29 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 14 Feb 2025 17:18:22 +0100
Subject: [PATCH 0682/2753] selftests: forwarding: lib: Move require_command to
 net, generalize

This helper could be useful to more than just forwarding tests.
Move it upstairs and port over to log_test_skip().

Split the function into two parts: the bit that actually checks and
reports skip, which is in a new function check_command(). And a bit
that exits the test script if the check fails. This allows users
consistent checking behavior while giving an option to bail out from
a single test without bailing out of the whole script.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/forwarding/lib.sh | 10 ----------
 tools/testing/selftests/net/lib.sh            | 19 +++++++++++++++++++
 2 files changed, 19 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index 8de80acf249ea..508f3c700d719 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -291,16 +291,6 @@ if [[ "$CHECK_TC" = "yes" ]]; then
 	check_tc_version
 fi
 
-require_command()
-{
-	local cmd=$1; shift
-
-	if [[ ! -x "$(command -v "$cmd")" ]]; then
-		echo "SKIP: $cmd not installed"
-		exit $ksft_skip
-	fi
-}
-
 # IPv6 support was added in v3.0
 check_mtools_version()
 {
diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
index 0bd9a038a1f0e..975be4fdbcdbe 100644
--- a/tools/testing/selftests/net/lib.sh
+++ b/tools/testing/selftests/net/lib.sh
@@ -450,6 +450,25 @@ kill_process()
 	{ kill $pid && wait $pid; } 2>/dev/null
 }
 
+check_command()
+{
+	local cmd=$1; shift
+
+	if [[ ! -x "$(command -v "$cmd")" ]]; then
+		log_test_skip "$cmd not installed"
+		return $EXIT_STATUS
+	fi
+}
+
+require_command()
+{
+	local cmd=$1; shift
+
+	if ! check_command "$cmd"; then
+		exit $EXIT_STATUS
+	fi
+}
+
 ip_link_add()
 {
 	local name=$1; shift

From 24adf47ea9acfb15d425e5b363c3f25dc6622a45 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 14 Feb 2025 17:18:23 +0100
Subject: [PATCH 0683/2753] selftests: test_vxlan_fdb_changelink: Convert to
 lib.sh

Instead of inlining equivalents, use lib.sh-provided primitives.
Use defer to manage vx lifetime.

This will make it easier to extend the test in the next patch.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/test_vxlan_fdb_changelink.sh          | 39 ++++++++++++-------
 1 file changed, 24 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
index 2d442cdab11e1..6f2bca4b346c8 100755
--- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
+++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
@@ -1,29 +1,38 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-# Check FDB default-remote handling across "ip link set".
+ALL_TESTS="
+	test_set_remote
+"
+source lib.sh
 
 check_remotes()
 {
 	local what=$1; shift
 	local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l)
 
-	echo -ne "expected two remotes after $what\t"
-	if [[ $N != 2 ]]; then
-		echo "[FAIL]"
-		EXIT_STATUS=1
-	else
-		echo "[ OK ]"
-	fi
+	((N == 2))
+	check_err $? "expected 2 remotes after $what, got $N"
+}
+
+# Check FDB default-remote handling across "ip link set".
+test_set_remote()
+{
+	RET=0
+
+	ip_link_add vx up type vxlan id 2000 dstport 4789
+	bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent
+	bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent
+	check_remotes "fdb append"
+
+	ip link set dev vx type vxlan remote 192.0.2.30
+	check_remotes "link set"
+
+	log_test 'FDB default-remote handling across "ip link set"'
 }
 
-ip link add name vx up type vxlan id 2000 dstport 4789
-bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent
-bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent
-check_remotes "fdb append"
+trap defer_scopes_cleanup EXIT
 
-ip link set dev vx type vxlan remote 192.0.2.30
-check_remotes "link set"
+tests_run
 
-ip link del dev vx
 exit $EXIT_STATUS

From eae1e92a1d414c4485c865c9f4e430b398cb8e8a Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Fri, 14 Feb 2025 17:18:24 +0100
Subject: [PATCH 0684/2753] selftests: test_vxlan_fdb_changelink: Add a test
 for MC remote change

Changes to MC remote need to be reflected in actual group memberships.
Add a test to verify that it is the case.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/test_vxlan_fdb_changelink.sh          | 76 +++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
index 6f2bca4b346c8..062f957950af3 100755
--- a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
+++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh
@@ -3,6 +3,7 @@
 
 ALL_TESTS="
 	test_set_remote
+	test_change_mc_remote
 "
 source lib.sh
 
@@ -31,6 +32,81 @@ test_set_remote()
 	log_test 'FDB default-remote handling across "ip link set"'
 }
 
+fmt_remote()
+{
+	local addr=$1; shift
+
+	if [[ $addr == 224.* ]]; then
+		echo "group $addr"
+	else
+		echo "remote $addr"
+	fi
+}
+
+change_remote()
+{
+	local remote=$1; shift
+
+	ip link set dev vx type vxlan $(fmt_remote $remote) dev v1
+}
+
+check_membership()
+{
+	local check_vec=("$@")
+
+	local memberships
+	memberships=$(
+	    netstat -n --groups |
+		sed -n '/^v1\b/p' |
+		grep -o '[^ ]*$'
+	)
+	check_err $? "Couldn't obtain group memberships"
+
+	local item
+	for item in "${check_vec[@]}"; do
+		eval "local $item"
+		echo "$memberships" | grep -q "\b$group\b"
+		check_err_fail $fail $? "$group is_ex reported in IGMP query response"
+	done
+}
+
+test_change_mc_remote()
+{
+	check_command netstat || return
+
+	ip_link_add v1 up type veth peer name v2
+	ip_link_set_up v2
+
+	RET=0
+
+	ip_link_add vx up type vxlan dstport 4789 \
+		local 192.0.2.1 $(fmt_remote 224.1.1.1) dev v1 vni 1000
+
+	check_membership "group=224.1.1.1 fail=0" \
+			 "group=224.1.1.2 fail=1" \
+			 "group=224.1.1.3 fail=1"
+
+	log_test "MC group report after VXLAN creation"
+
+	RET=0
+
+	change_remote 224.1.1.2
+	check_membership "group=224.1.1.1 fail=1" \
+			 "group=224.1.1.2 fail=0" \
+			 "group=224.1.1.3 fail=1"
+
+	log_test "MC group report after changing VXLAN remote MC->MC"
+
+	RET=0
+
+	change_remote 192.0.2.2
+	check_membership "group=224.1.1.1 fail=1" \
+			 "group=224.1.1.2 fail=1" \
+			 "group=224.1.1.3 fail=1"
+
+	log_test "MC group report after changing VXLAN remote MC->UC"
+}
+
 trap defer_scopes_cleanup EXIT
 
 tests_run

From a3bdd8f5c2217e1cb35db02c2eed36ea20fb50f5 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 18 Feb 2025 12:40:24 +0100
Subject: [PATCH 0685/2753] ALSA: usb-audio: Avoid dropping MIDI events at
 closing multiple ports

We fixed the UAF issue in USB MIDI code by canceling the pending work
at closing each MIDI output device in the commit below.  However, this
assumed that it's the only one that is tied with the endpoint, and it
resulted in unexpected data truncations when multiple devices are
assigned to a single endpoint and opened simultaneously.

For addressing the unexpected MIDI message drops, simply replace
cancel_work_sync() with flush_work().  The drain callback should have
been already invoked before the close callback, hence the port->active
flag must be already cleared.  So this just assures that the pending
work is finished before freeing the resources.

Fixes: 0125de38122f ("ALSA: usb-audio: Cancel pending work at closing a MIDI substream")
Reported-and-tested-by: John Keeping <jkeeping@inmusicbrands.com>
Closes: https://lore.kernel.org/20250217111647.3368132-1-jkeeping@inmusicbrands.com
Link: https://patch.msgid.link/20250218114024.23125-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/midi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/usb/midi.c b/sound/usb/midi.c
index 737dd00e97b14..779d97d31f170 100644
--- a/sound/usb/midi.c
+++ b/sound/usb/midi.c
@@ -1145,7 +1145,7 @@ static int snd_usbmidi_output_close(struct snd_rawmidi_substream *substream)
 {
 	struct usbmidi_out_port *port = substream->runtime->private_data;
 
-	cancel_work_sync(&port->ep->work);
+	flush_work(&port->ep->work);
 	return substream_open(substream, 0, 0);
 }
 

From 8dcaed624f6af020023a09f7d14decc7ec730355 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dima.fedrau@gmail.com>
Date: Fri, 14 Feb 2025 17:32:03 +0100
Subject: [PATCH 0686/2753] net: phy: marvell-88q2xxx: align defines
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Align some defines.

Signed-off-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell-88q2xxx.c | 62 +++++++++++++++----------------
 1 file changed, 31 insertions(+), 31 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index bad5e7b2357da..6e95de080bc65 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -12,29 +12,29 @@
 #include <linux/phy.h>
 #include <linux/hwmon.h>
 
-#define PHY_ID_88Q2220_REVB0	(MARVELL_PHY_ID_88Q2220 | 0x1)
-#define PHY_ID_88Q2220_REVB1	(MARVELL_PHY_ID_88Q2220 | 0x2)
-#define PHY_ID_88Q2220_REVB2	(MARVELL_PHY_ID_88Q2220 | 0x3)
-
-#define MDIO_MMD_AN_MV_STAT			32769
-#define MDIO_MMD_AN_MV_STAT_ANEG		0x0100
-#define MDIO_MMD_AN_MV_STAT_LOCAL_RX		0x1000
-#define MDIO_MMD_AN_MV_STAT_REMOTE_RX		0x2000
-#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER	0x4000
-#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT	0x8000
-
-#define MDIO_MMD_AN_MV_STAT2			32794
-#define MDIO_MMD_AN_MV_STAT2_AN_RESOLVED	0x0800
-#define MDIO_MMD_AN_MV_STAT2_100BT1		0x2000
-#define MDIO_MMD_AN_MV_STAT2_1000BT1		0x4000
-
-#define MDIO_MMD_PCS_MV_RESET_CTRL		32768
-#define MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE	0x8
-
-#define MDIO_MMD_PCS_MV_INT_EN			32784
-#define MDIO_MMD_PCS_MV_INT_EN_LINK_UP		0x0040
-#define MDIO_MMD_PCS_MV_INT_EN_LINK_DOWN	0x0080
-#define MDIO_MMD_PCS_MV_INT_EN_100BT1		0x1000
+#define PHY_ID_88Q2220_REVB0				(MARVELL_PHY_ID_88Q2220 | 0x1)
+#define PHY_ID_88Q2220_REVB1				(MARVELL_PHY_ID_88Q2220 | 0x2)
+#define PHY_ID_88Q2220_REVB2				(MARVELL_PHY_ID_88Q2220 | 0x3)
+
+#define MDIO_MMD_AN_MV_STAT				32769
+#define MDIO_MMD_AN_MV_STAT_ANEG			0x0100
+#define MDIO_MMD_AN_MV_STAT_LOCAL_RX			0x1000
+#define MDIO_MMD_AN_MV_STAT_REMOTE_RX			0x2000
+#define MDIO_MMD_AN_MV_STAT_LOCAL_MASTER		0x4000
+#define MDIO_MMD_AN_MV_STAT_MS_CONF_FAULT		0x8000
+
+#define MDIO_MMD_AN_MV_STAT2				32794
+#define MDIO_MMD_AN_MV_STAT2_AN_RESOLVED		0x0800
+#define MDIO_MMD_AN_MV_STAT2_100BT1			0x2000
+#define MDIO_MMD_AN_MV_STAT2_1000BT1			0x4000
+
+#define MDIO_MMD_PCS_MV_RESET_CTRL			32768
+#define MDIO_MMD_PCS_MV_RESET_CTRL_TX_DISABLE		0x8
+
+#define MDIO_MMD_PCS_MV_INT_EN				32784
+#define MDIO_MMD_PCS_MV_INT_EN_LINK_UP			0x0040
+#define MDIO_MMD_PCS_MV_INT_EN_LINK_DOWN		0x0080
+#define MDIO_MMD_PCS_MV_INT_EN_100BT1			0x1000
 
 #define MDIO_MMD_PCS_MV_GPIO_INT_STAT			32785
 #define MDIO_MMD_PCS_MV_GPIO_INT_STAT_LINK_UP		0x0040
@@ -80,11 +80,11 @@
 #define MDIO_MMD_PCS_MV_100BT1_STAT1_REMOTE_RX		0x2000
 #define MDIO_MMD_PCS_MV_100BT1_STAT1_LOCAL_MASTER	0x4000
 
-#define MDIO_MMD_PCS_MV_100BT1_STAT2		33033
-#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER	0x0001
-#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL	0x0002
-#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK	0x0004
-#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE	0x0008
+#define MDIO_MMD_PCS_MV_100BT1_STAT2			33033
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_JABBER		0x0001
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_POL		0x0002
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_LINK		0x0004
+#define MDIO_MMD_PCS_MV_100BT1_STAT2_ANGE		0x0008
 
 #define MDIO_MMD_PCS_MV_100BT1_INT_EN			33042
 #define MDIO_MMD_PCS_MV_100BT1_INT_EN_LINKEVENT		0x0400
@@ -92,7 +92,7 @@
 #define MDIO_MMD_PCS_MV_COPPER_INT_STAT			33043
 #define MDIO_MMD_PCS_MV_COPPER_INT_STAT_LINKEVENT	0x0400
 
-#define MDIO_MMD_PCS_MV_RX_STAT			33328
+#define MDIO_MMD_PCS_MV_RX_STAT				33328
 
 #define MDIO_MMD_PCS_MV_TDR_RESET			65226
 #define MDIO_MMD_PCS_MV_TDR_RESET_TDR_RST		0x1000
@@ -115,8 +115,8 @@
 
 #define MDIO_MMD_PCS_MV_TDR_OFF_CUTOFF			65246
 
-#define MV88Q2XXX_LED_INDEX_TX_ENABLE	0
-#define MV88Q2XXX_LED_INDEX_GPIO	1
+#define MV88Q2XXX_LED_INDEX_TX_ENABLE			0
+#define MV88Q2XXX_LED_INDEX_GPIO			1
 
 struct mv88q2xxx_priv {
 	bool enable_temp;

From cbe0449e8f9f306a022e99b051e263769ba6e599 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dima.fedrau@gmail.com>
Date: Fri, 14 Feb 2025 17:32:04 +0100
Subject: [PATCH 0687/2753] net: phy: marvell-88q2xxx: order includes
 alphabetically
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Order includes alphabetically.

Signed-off-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell-88q2xxx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 6e95de080bc65..7b0913968bb40 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -7,10 +7,10 @@
  * Copyright (C) 2024 Liebherr-Electronics and Drives GmbH
  */
 #include <linux/ethtool_netlink.h>
+#include <linux/hwmon.h>
 #include <linux/marvell_phy.h>
 #include <linux/of.h>
 #include <linux/phy.h>
-#include <linux/hwmon.h>
 
 #define PHY_ID_88Q2220_REVB0				(MARVELL_PHY_ID_88Q2220 | 0x1)
 #define PHY_ID_88Q2220_REVB1				(MARVELL_PHY_ID_88Q2220 | 0x2)

From 6c806720bafe3ae9c43eb2dc942a1849d5453736 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dima.fedrau@gmail.com>
Date: Fri, 14 Feb 2025 17:32:05 +0100
Subject: [PATCH 0688/2753] net: phy: marvell-88q2xxx: enable temperature
 sensor in mv88q2xxx_config_init
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Temperature sensor gets enabled for 88Q222X devices in
mv88q222x_config_init. Move enabling to mv88q2xxx_config_init because
all 88Q2XXX devices support the temperature sensor.

Signed-off-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Tested-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell-88q2xxx.c | 21 +++++++++------------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 7b0913968bb40..1859db10b3914 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -513,6 +513,15 @@ static int mv88q2xxx_config_init(struct phy_device *phydev)
 			return ret;
 	}
 
+	/* Enable temperature sense */
+	if (priv->enable_temp) {
+		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2,
+				     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
+		if (ret < 0)
+			return ret;
+	}
+
 	return 0;
 }
 
@@ -903,18 +912,6 @@ static int mv88q222x_revb1_revb2_config_init(struct phy_device *phydev)
 
 static int mv88q222x_config_init(struct phy_device *phydev)
 {
-	struct mv88q2xxx_priv *priv = phydev->priv;
-	int ret;
-
-	/* Enable temperature sense */
-	if (priv->enable_temp) {
-		ret = phy_modify_mmd(phydev, MDIO_MMD_PCS,
-				     MDIO_MMD_PCS_MV_TEMP_SENSOR2,
-				     MDIO_MMD_PCS_MV_TEMP_SENSOR2_DIS_MASK, 0);
-		if (ret < 0)
-			return ret;
-	}
-
 	if (phydev->c45_ids.device_ids[MDIO_MMD_PMAPMD] == PHY_ID_88Q2220_REVB0)
 		return mv88q222x_revb0_config_init(phydev);
 	else

From 8e677a466145174e6899ceaf189e7cb7fbd6ad3f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Feb 2025 09:07:11 -0800
Subject: [PATCH 0689/2753] trace: tcp: Add tracepoint for tcp_cwnd_reduction()

Add a lightweight tracepoint to monitor TCP congestion window
adjustments via tcp_cwnd_reduction(). This tracepoint enables tracking
of:
- TCP window size fluctuations
- Active socket behavior
- Congestion window reduction events

Meta has been using BPF programs to monitor this function for years.
Adding a proper tracepoint provides a stable API for all users who need
to monitor TCP congestion window behavior.

Use DECLARE_TRACE instead of TRACE_EVENT to avoid creating trace event
infrastructure and exporting to tracefs, keeping the implementation
minimal. (Thanks Steven Rostedt)

Given that this patch creates a rawtracepoint, you could hook into it
using regular tooling, like bpftrace, using regular rawtracepoint
infrastructure, such as:

	rawtracepoint:tcp_cwnd_reduction_tp {
		....
	}

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250214-cwnd_tracepoint-v2-1-ef8d15162d95@debian.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/trace/events/tcp.h | 6 ++++++
 net/ipv4/tcp_input.c       | 2 ++
 2 files changed, 8 insertions(+)

diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h
index a27c4b619dffd..1a40c41ff8c30 100644
--- a/include/trace/events/tcp.h
+++ b/include/trace/events/tcp.h
@@ -259,6 +259,12 @@ TRACE_EVENT(tcp_retransmit_synack,
 		  __entry->saddr_v6, __entry->daddr_v6)
 );
 
+DECLARE_TRACE(tcp_cwnd_reduction_tp,
+	TP_PROTO(const struct sock *sk, int newly_acked_sacked,
+		 int newly_lost, int flag),
+	TP_ARGS(sk, newly_acked_sacked, newly_lost, flag)
+);
+
 #include <trace/events/net_probe_common.h>
 
 TRACE_EVENT(tcp_probe,
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 074406890552a..fbb67a098543b 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2709,6 +2709,8 @@ void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked, int newly_lost,
 	if (newly_acked_sacked <= 0 || WARN_ON_ONCE(!tp->prior_cwnd))
 		return;
 
+	trace_tcp_cwnd_reduction_tp(sk, newly_acked_sacked, newly_lost, flag);
+
 	tp->prr_delivered += newly_acked_sacked;
 	if (delta < 0) {
 		u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered +

From 4991b88c2514e62bd8410e0a96999ef662765d9d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Niklas=20S=C3=B6derlund?=
 <niklas.soderlund+renesas@ragnatech.se>
Date: Fri, 14 Feb 2025 18:46:50 +0100
Subject: [PATCH 0690/2753] net: phy: marvell-88q2xxx: Init PHY private
 structure for mv88q211x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When adding LED support for mv88q222x devices the PHY private data
structure was added to the mv88q211x code path, the data structure is
however only allocated during mv88q222x probe. This results in a nullptr
deference for mv88q2110 devices.

	Unable to handle kernel NULL pointer dereference at virtual address 0000000000000001
	Mem abort info:
	  ESR = 0x0000000096000004
	  EC = 0x25: DABT (current EL), IL = 32 bits
	  SET = 0, FnV = 0
	  EA = 0, S1PTW = 0
	  FSC = 0x04: level 0 translation fault
	Data abort info:
	  ISV = 0, ISS = 0x00000004, ISS2 = 0x00000000
	  CM = 0, WnR = 0, TnD = 0, TagAccess = 0
	  GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
	[0000000000000001] user address but active_mm is swapper
	Internal error: Oops: 0000000096000004 [#1] PREEMPT SMP
	CPU: 3 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.14.0-rc1-arm64-renesas-00342-ga3783dbf2574 #7
	Hardware name: Renesas White Hawk Single board based on r8a779g2 (DT)
	pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
	pc : mv88q2xxx_config_init+0x28/0x84
	lr : mv88q2110_config_init+0x98/0xb0
	sp : ffff8000823eb9d0
	x29: ffff8000823eb9d0 x28: ffff000440942000 x27: ffff80008144e400
	x26: 0000000000001002 x25: 0000000000000000 x24: 0000000000000000
	x23: 0000000000000009 x22: ffff8000810534f0 x21: ffff800081053550
	x20: 0000000000000000 x19: ffff0004437d6800 x18: 0000000000000018
	x17: 00000000000961c8 x16: ffff0006bef75ec0 x15: 0000000000000001
	x14: 0000000000000001 x13: ffff000440218080 x12: 071c71c71c71c71c
	x11: ffff000440218080 x10: 0000000000001420 x9 : ffff8000823eb770
	x8 : ffff8000823eb650 x7 : ffff8000823eb750 x6 : ffff8000823eb710
	x5 : 0000000000000000 x4 : 0000000000000800 x3 : 0000000000000001
	x2 : 0000000000000000 x1 : 00000000ffffffff x0 : ffff0004437d6800
	Call trace:
	 mv88q2xxx_config_init+0x28/0x84 (P)
	 mv88q2110_config_init+0x98/0xb0
	 phy_init_hw+0x64/0x9c
	 phy_attach_direct+0x118/0x320
	 phy_connect_direct+0x24/0x80
	 of_phy_connect+0x5c/0xa0
	 rtsn_open+0x5bc/0x78c
	 __dev_open+0xf8/0x1fc
	 __dev_change_flags+0x198/0x220
	 dev_change_flags+0x20/0x64
	 ip_auto_config+0x270/0xefc
	 do_one_initcall+0xe4/0x22c
	 kernel_init_freeable+0x2a8/0x308
	 kernel_init+0x20/0x130
	 ret_from_fork+0x10/0x20
	Code: b907e404 f9432814 3100083f 540000e3 (39400680)
	---[ end trace 0000000000000000 ]---
	Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b
	SMP: stopping secondary CPUs
	Kernel Offset: disabled
	CPU features: 0x000,00000070,00801250,8200700b
	Memory Limit: none
	---[ end Kernel panic - not syncing: Attempted to kill init! exitcode=0x0000000b ]---

Fix this by using a generic probe function for both mv88q211x and
mv88q222x devices that allocates the PHY private data structure, while
only the mv88q222x probes for LED support.

Fixes: a3783dbf2574 ("net: phy: marvell-88q2xxx: Add support for PHY LEDs on 88q2xxx")
Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250214174650.2056949-1-niklas.soderlund+renesas@ragnatech.se
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell-88q2xxx.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 1859db10b3914..15c0f8adc2f53 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -834,13 +834,24 @@ static int mv88q2xxx_leds_probe(struct phy_device *phydev)
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
 	struct mv88q2xxx_priv *priv;
-	int ret;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
 
 	phydev->priv = priv;
+
+	return 0;
+}
+
+static int mv88q222x_probe(struct phy_device *phydev)
+{
+	int ret;
+
+	ret = mv88q2xxx_probe(phydev);
+	if (ret)
+		return ret;
+
 	ret = mv88q2xxx_leds_probe(phydev);
 	if (ret)
 		return ret;
@@ -1098,6 +1109,7 @@ static struct phy_driver mv88q2xxx_driver[] = {
 		.phy_id			= MARVELL_PHY_ID_88Q2110,
 		.phy_id_mask		= MARVELL_PHY_ID_MASK,
 		.name			= "mv88q2110",
+		.probe			= mv88q2xxx_probe,
 		.get_features		= mv88q2xxx_get_features,
 		.config_aneg		= mv88q2xxx_config_aneg,
 		.config_init		= mv88q2110_config_init,
@@ -1112,7 +1124,7 @@ static struct phy_driver mv88q2xxx_driver[] = {
 		.phy_id_mask		= MARVELL_PHY_ID_MASK,
 		.name			= "mv88q2220",
 		.flags			= PHY_POLL_CABLE_TEST,
-		.probe			= mv88q2xxx_probe,
+		.probe			= mv88q222x_probe,
 		.get_features		= mv88q2xxx_get_features,
 		.config_aneg		= mv88q2xxx_config_aneg,
 		.aneg_done		= genphy_c45_aneg_done,

From fcd875445866a5219cf2be3101e276b21fc843f3 Mon Sep 17 00:00:00 2001
From: Christopher Lentocha <christopherericlentocha@gmail.com>
Date: Tue, 18 Feb 2025 08:59:29 -0500
Subject: [PATCH 0691/2753] nvme-pci: quirk Acer FA100 for non-uniqueue
 identifiers

In order for two Acer FA100 SSDs to work in one PC (in the case of
myself, a Lenovo Legion T5 28IMB05), and not show one drive and not
the other, and sometimes mix up what drive shows up (randomly), these
two lines of code need to be added, and then both of the SSDs will
show up and not conflict when booting off of one of them. If you boot
up your computer with both SSDs installed without this patch, you may
also randomly get into a kernel panic (if the initrd is not set up) or
stuck in the initrd "/init" process, it is set up, however, if you do
apply this patch, there should not be problems with booting or seeing
both contents of the drive. Tested with the btrfs filesystem with a
RAID configuration of having the root drive '/' combined to make two
256GB Acer FA100 SSDs become 512GB in total storage.

Kernel Logs with patch applied (`dmesg -t | grep -i nvm`):

```
...
nvme 0000:04:00.0: platform quirk: setting simple suspend
nvme nvme0: pci function 0000:04:00.0
nvme 0000:05:00.0: platform quirk: setting simple suspend
nvme nvme1: pci function 0000:05:00.0
nvme nvme1: missing or invalid SUBNQN field.
nvme nvme1: allocated 64 MiB host memory buffer.
nvme nvme0: missing or invalid SUBNQN field.
nvme nvme0: allocated 64 MiB host memory buffer.
nvme nvme1: 8/0/0 default/read/poll queues
nvme nvme1: Ignoring bogus Namespace Identifiers
nvme nvme0: 8/0/0 default/read/poll queues
nvme nvme0: Ignoring bogus Namespace Identifiers
nvme0n1: p1 p2
...
```

Kernel Logs with patch not applied (`dmesg -t | grep -i nvm`):

```
...
nvme 0000:04:00.0: platform quirk: setting simple suspend
nvme nvme0: pci function 0000:04:00.0
nvme 0000:05:00.0: platform quirk: setting simple suspend
nvme nvme1: pci function 0000:05:00.0
nvme nvme0: missing or invalid SUBNQN field.
nvme nvme1: missing or invalid SUBNQN field.
nvme nvme0: allocated 64 MiB host memory buffer.
nvme nvme1: allocated 64 MiB host memory buffer.
nvme nvme0: 8/0/0 default/read/poll queues
nvme nvme1: 8/0/0 default/read/poll queues
nvme nvme1: globally duplicate IDs for nsid 1
nvme nvme1: VID:DID 1dbe:5216 model:Acer SSD FA100 256GB firmware:1.Z.J.2X
nvme0n1: p1 p2
...
```

Signed-off-by: Christopher Lentocha <christopherericlentocha@gmail.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9197a5b173fdf..950289405ef28 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -3706,6 +3706,8 @@ static const struct pci_device_id nvme_id_table[] = {
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1cc1, 0x5350),   /* ADATA XPG GAMMIX S50 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
+	{ PCI_DEVICE(0x1dbe, 0x5216),   /* Acer/INNOGRIT FA100/5216 NVMe SSD */
+		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1dbe, 0x5236),   /* ADATA XPG GAMMIX S70 */
 		.driver_data = NVME_QUIRK_BOGUS_NID, },
 	{ PCI_DEVICE(0x1e49, 0x0021),   /* ZHITAI TiPro5000 NVMe SSD */

From 84e009042d0f3dfe91bec60bcd208ee3f866cbcd Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 17 Feb 2025 17:08:27 +0100
Subject: [PATCH 0692/2753] nvme-tcp: add basic support for the C2HTermReq PDU

Previously, the NVMe/TCP host driver did not handle the C2HTermReq PDU,
instead printing "unsupported pdu type (3)" when received. This patch adds
support for processing the C2HTermReq PDU, allowing the driver
to print the Fatal Error Status field.

Example of output:
nvme nvme4: Received C2HTermReq (FES = Invalid PDU Header Field)

Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c  | 43 ++++++++++++++++++++++++++++++++++++++++
 include/linux/nvme-tcp.h |  2 ++
 2 files changed, 45 insertions(+)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 841238f38fdda..038b35238c26d 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -763,6 +763,40 @@ static int nvme_tcp_handle_r2t(struct nvme_tcp_queue *queue,
 	return 0;
 }
 
+static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
+		struct nvme_tcp_term_pdu *pdu)
+{
+	u16 fes;
+	const char *msg;
+	u32 plen = le32_to_cpu(pdu->hdr.plen);
+
+	static const char * const msg_table[] = {
+		[NVME_TCP_FES_INVALID_PDU_HDR] = "Invalid PDU Header Field",
+		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
+		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
+		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
+		[NVME_TCP_FES_R2T_LIMIT_EXCEEDED] = "R2T Limit Exceeded",
+		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
+	};
+
+	if (plen < NVME_TCP_MIN_C2HTERM_PLEN ||
+	    plen > NVME_TCP_MAX_C2HTERM_PLEN) {
+		dev_err(queue->ctrl->ctrl.device,
+			"Received a malformed C2HTermReq PDU (plen = %u)\n",
+			plen);
+		return;
+	}
+
+	fes = le16_to_cpu(pdu->fes);
+	if (fes && fes < ARRAY_SIZE(msg_table))
+		msg = msg_table[fes];
+	else
+		msg = "Unknown";
+
+	dev_err(queue->ctrl->ctrl.device,
+		"Received C2HTermReq (FES = %s)\n", msg);
+}
+
 static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		unsigned int *offset, size_t *len)
 {
@@ -784,6 +818,15 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
+		/*
+		 * C2HTermReq never includes Header or Data digests.
+		 * Skip the checks.
+		 */
+		nvme_tcp_handle_c2h_term(queue, (void *)queue->pdu);
+		return -EINVAL;
+	}
+
 	if (queue->hdr_digest) {
 		ret = nvme_tcp_verify_hdgst(queue, queue->pdu, hdr->hlen);
 		if (unlikely(ret))
diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h
index e07e8978d691b..e435250fcb4d0 100644
--- a/include/linux/nvme-tcp.h
+++ b/include/linux/nvme-tcp.h
@@ -13,6 +13,8 @@
 #define NVME_TCP_ADMIN_CCSZ	SZ_8K
 #define NVME_TCP_DIGEST_LENGTH	4
 #define NVME_TCP_MIN_MAXH2CDATA 4096
+#define NVME_TCP_MIN_C2HTERM_PLEN	24
+#define NVME_TCP_MAX_C2HTERM_PLEN	152
 
 enum nvme_tcp_pfv {
 	NVME_TCP_PFV_1_0 = 0x0,

From 4082326807072b71496501b6a0c55ffe8d5092a5 Mon Sep 17 00:00:00 2001
From: Hannes Reinecke <hare@kernel.org>
Date: Fri, 7 Feb 2025 13:41:34 +0100
Subject: [PATCH 0693/2753] nvmet: Fix crash when a namespace is disabled

The namespace percpu counter protects pending I/O, and we can
only safely diable the namespace once the counter drop to zero.
Otherwise we end up with a crash when running blktests/nvme/058
(eg for loop transport):

[ 2352.930426] [  T53909] Oops: general protection fault, probably for non-canonical address 0xdffffc0000000005: 0000 [#1] PREEMPT SMP KASAN PTI
[ 2352.930431] [  T53909] KASAN: null-ptr-deref in range [0x0000000000000028-0x000000000000002f]
[ 2352.930434] [  T53909] CPU: 3 UID: 0 PID: 53909 Comm: kworker/u16:5 Tainted: G        W          6.13.0-rc6 #232
[ 2352.930438] [  T53909] Tainted: [W]=WARN
[ 2352.930440] [  T53909] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.3-3.fc41 04/01/2014
[ 2352.930443] [  T53909] Workqueue: nvmet-wq nvme_loop_execute_work [nvme_loop]
[ 2352.930449] [  T53909] RIP: 0010:blkcg_set_ioprio+0x44/0x180

as the queue is already torn down when calling submit_bio();

So we need to init the percpu counter in nvmet_ns_enable(), and
wait for it to drop to zero in nvmet_ns_disable() to avoid having
I/O pending after the namespace has been disabled.

Fixes: 74d16965d7ac ("nvmet-loop: avoid using mutex in IO hotpath")

Signed-off-by: Hannes Reinecke <hare@kernel.org>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/core.c | 40 ++++++++++++++++++--------------------
 1 file changed, 19 insertions(+), 21 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index cdc4a09a6e8a4..2e741696f3712 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -606,6 +606,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 			goto out_dev_put;
 	}
 
+	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
+		goto out_pr_exit;
+
 	nvmet_ns_changed(subsys, ns->nsid);
 	ns->enabled = true;
 	xa_set_mark(&subsys->namespaces, ns->nsid, NVMET_NS_ENABLED);
@@ -613,6 +616,9 @@ int nvmet_ns_enable(struct nvmet_ns *ns)
 out_unlock:
 	mutex_unlock(&subsys->lock);
 	return ret;
+out_pr_exit:
+	if (ns->pr.enable)
+		nvmet_pr_exit_ns(ns);
 out_dev_put:
 	list_for_each_entry(ctrl, &subsys->ctrls, subsys_entry)
 		pci_dev_put(radix_tree_delete(&ctrl->p2p_ns_map, ns->nsid));
@@ -638,6 +644,19 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 
 	mutex_unlock(&subsys->lock);
 
+	/*
+	 * Now that we removed the namespaces from the lookup list, we
+	 * can kill the per_cpu ref and wait for any remaining references
+	 * to be dropped, as well as a RCU grace period for anyone only
+	 * using the namepace under rcu_read_lock().  Note that we can't
+	 * use call_rcu here as we need to ensure the namespaces have
+	 * been fully destroyed before unloading the module.
+	 */
+	percpu_ref_kill(&ns->ref);
+	synchronize_rcu();
+	wait_for_completion(&ns->disable_done);
+	percpu_ref_exit(&ns->ref);
+
 	if (ns->pr.enable)
 		nvmet_pr_exit_ns(ns);
 
@@ -660,22 +679,6 @@ void nvmet_ns_free(struct nvmet_ns *ns)
 	if (ns->nsid == subsys->max_nsid)
 		subsys->max_nsid = nvmet_max_nsid(subsys);
 
-	mutex_unlock(&subsys->lock);
-
-	/*
-	 * Now that we removed the namespaces from the lookup list, we
-	 * can kill the per_cpu ref and wait for any remaining references
-	 * to be dropped, as well as a RCU grace period for anyone only
-	 * using the namepace under rcu_read_lock().  Note that we can't
-	 * use call_rcu here as we need to ensure the namespaces have
-	 * been fully destroyed before unloading the module.
-	 */
-	percpu_ref_kill(&ns->ref);
-	synchronize_rcu();
-	wait_for_completion(&ns->disable_done);
-	percpu_ref_exit(&ns->ref);
-
-	mutex_lock(&subsys->lock);
 	subsys->nr_namespaces--;
 	mutex_unlock(&subsys->lock);
 
@@ -705,9 +708,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	ns->nsid = nsid;
 	ns->subsys = subsys;
 
-	if (percpu_ref_init(&ns->ref, nvmet_destroy_namespace, 0, GFP_KERNEL))
-		goto out_free;
-
 	if (ns->nsid > subsys->max_nsid)
 		subsys->max_nsid = nsid;
 
@@ -730,8 +730,6 @@ struct nvmet_ns *nvmet_ns_alloc(struct nvmet_subsys *subsys, u32 nsid)
 	return ns;
 out_exit:
 	subsys->max_nsid = nvmet_max_nsid(subsys);
-	percpu_ref_exit(&ns->ref);
-out_free:
 	kfree(ns);
 out_unlock:
 	mutex_unlock(&subsys->lock);

From 3988ac1c67e6e84d2feb987d7b36d5791174b3da Mon Sep 17 00:00:00 2001
From: Ruozhu Li <david.li@jaguarmicro.com>
Date: Sun, 16 Feb 2025 20:49:56 +0800
Subject: [PATCH 0694/2753] nvmet-rdma: recheck queue state is LIVE in state
 lock in recv done

The queue state checking in nvmet_rdma_recv_done is not in queue state
lock.Queue state can transfer to LIVE in cm establish handler between
state checking and state lock here, cause a silent drop of nvme connect
cmd.
Recheck queue state whether in LIVE state in state lock to prevent this
issue.

Signed-off-by: Ruozhu Li <david.li@jaguarmicro.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/rdma.c | 33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1afd93026f9bf..2a4536ef61848 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -996,6 +996,27 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 	nvmet_req_complete(&cmd->req, status);
 }
 
+static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue,
+		struct nvmet_rdma_rsp *rsp)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	/*
+	 * recheck queue state is not live to prevent a race condition
+	 * with RDMA_CM_EVENT_ESTABLISHED handler.
+	 */
+	if (queue->state == NVMET_RDMA_Q_LIVE)
+		ret = false;
+	else if (queue->state == NVMET_RDMA_Q_CONNECTING)
+		list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+	else
+		nvmet_rdma_put_rsp(rsp);
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+	return ret;
+}
+
 static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvmet_rdma_cmd *cmd =
@@ -1038,17 +1059,9 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rsp->n_rdma = 0;
 	rsp->invalidate_rkey = 0;
 
-	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&queue->state_lock, flags);
-		if (queue->state == NVMET_RDMA_Q_CONNECTING)
-			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
-		else
-			nvmet_rdma_put_rsp(rsp);
-		spin_unlock_irqrestore(&queue->state_lock, flags);
+	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) &&
+	    nvmet_rdma_recv_not_live(queue, rsp))
 		return;
-	}
 
 	nvmet_rdma_handle_command(queue, rsp);
 }

From 68a5c91f01fc9f086567b260cced003ed9fdff3f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:28 +0900
Subject: [PATCH 0695/2753] nvmet: pci-epf: Correctly initialize CSTS when
 enabling the controller

The function nvmet_pci_epf_poll_cc_work() sets the NVME_CSTS_RDY bit of
the controller status register (CSTS) when nvmet_pci_epf_enable_ctrl()
returns success. However, since this function can be called several
times (e.g. if the host reboots), instead of setting the bit in
ctrl->csts, initialize this field to only have NVME_CSTS_RDY set.
Conversely, if nvmet_pci_epf_enable_ctrl() fails, make sure to clear all
bits from ctrl->csts.

To simplify nvmet_pci_epf_poll_cc_work(), initialize ctrl->csts to
NVME_CSTS_RDY directly inside nvmet_pci_epf_enable_ctrl() and clear this
field in that function as well in case of a failure. To be consistent,
move clearing the NVME_CSTS_RDY bit from ctrl->csts when the controller
is being disabled from nvmet_pci_epf_poll_cc_work() into
nvmet_pci_epf_disable_ctrl().

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index ac30b42cc6221..efd4623fb0022 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1822,14 +1822,14 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	if (ctrl->io_sqes < sizeof(struct nvme_command)) {
 		dev_err(ctrl->dev, "Unsupported I/O SQES %zu (need %zu)\n",
 			ctrl->io_sqes, sizeof(struct nvme_command));
-		return -EINVAL;
+		goto err;
 	}
 
 	ctrl->io_cqes = 1UL << nvmet_cc_iocqes(ctrl->cc);
 	if (ctrl->io_cqes < sizeof(struct nvme_completion)) {
 		dev_err(ctrl->dev, "Unsupported I/O CQES %zu (need %zu)\n",
 			ctrl->io_sqes, sizeof(struct nvme_completion));
-		return -EINVAL;
+		goto err;
 	}
 
 	/* Create the admin queue. */
@@ -1844,7 +1844,7 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 				qsize, pci_addr, 0);
 	if (status != NVME_SC_SUCCESS) {
 		dev_err(ctrl->dev, "Failed to create admin completion queue\n");
-		return -EINVAL;
+		goto err;
 	}
 
 	qsize = aqa & 0x00000fff;
@@ -1854,17 +1854,22 @@ static int nvmet_pci_epf_enable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	if (status != NVME_SC_SUCCESS) {
 		dev_err(ctrl->dev, "Failed to create admin submission queue\n");
 		nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
-		return -EINVAL;
+		goto err;
 	}
 
 	ctrl->sq_ab = NVMET_PCI_EPF_SQ_AB;
 	ctrl->irq_vector_threshold = NVMET_PCI_EPF_IV_THRESHOLD;
 	ctrl->enabled = true;
+	ctrl->csts = NVME_CSTS_RDY;
 
 	/* Start polling the controller SQs. */
 	schedule_delayed_work(&ctrl->poll_sqs, 0);
 
 	return 0;
+
+err:
+	ctrl->csts = 0;
+	return -EINVAL;
 }
 
 static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
@@ -1889,6 +1894,8 @@ static void nvmet_pci_epf_disable_ctrl(struct nvmet_pci_epf_ctrl *ctrl)
 	/* Delete the admin queue last. */
 	nvmet_pci_epf_delete_sq(ctrl->tctrl, 0);
 	nvmet_pci_epf_delete_cq(ctrl->tctrl, 0);
+
+	ctrl->csts &= ~NVME_CSTS_RDY;
 }
 
 static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
@@ -1909,13 +1916,10 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 		ret = nvmet_pci_epf_enable_ctrl(ctrl);
 		if (ret)
 			return;
-		ctrl->csts |= NVME_CSTS_RDY;
 	}
 
-	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc)) {
+	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
 		nvmet_pci_epf_disable_ctrl(ctrl);
-		ctrl->csts &= ~NVME_CSTS_RDY;
-	}
 
 	if (nvmet_cc_shn(new_cc) && !nvmet_cc_shn(old_cc)) {
 		nvmet_pci_epf_disable_ctrl(ctrl);

From ffa35567632c0059e7f380ed155e26a07ec4153f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:29 +0900
Subject: [PATCH 0696/2753] nvmet: pci-epf: Do not uselessly write the CSTS
 register

The function nvmet_pci_epf_poll_cc_work() will do nothing if there are
no changes to the controller configuration (CC) register. However, even
for such case, this function still calls nvmet_update_cc() and uselessly
writes the CSTS register. Avoid this by simply rescheduling the poll_cc
work if the CC register has not changed.

Also reschedule the poll_cc work if the function
nvmet_pci_epf_enable_ctrl() fails to allow the host the chance to try
again enabling the controller.

While at it, since there is no point in trying to handle the CC register
as quickly as possible, change the poll_cc work scheduling interval to
10 ms (from 5ms), to avoid excessive read accesses to that register.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index efd4623fb0022..b646a8f468ea9 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -46,7 +46,7 @@ static DEFINE_MUTEX(nvmet_pci_epf_ports_mutex);
 /*
  * BAR CC register and SQ polling intervals.
  */
-#define NVMET_PCI_EPF_CC_POLL_INTERVAL	msecs_to_jiffies(5)
+#define NVMET_PCI_EPF_CC_POLL_INTERVAL	msecs_to_jiffies(10)
 #define NVMET_PCI_EPF_SQ_POLL_INTERVAL	msecs_to_jiffies(5)
 #define NVMET_PCI_EPF_SQ_POLL_IDLE	msecs_to_jiffies(5000)
 
@@ -1910,12 +1910,15 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 
 	old_cc = ctrl->cc;
 	new_cc = nvmet_pci_epf_bar_read32(ctrl, NVME_REG_CC);
+	if (new_cc == old_cc)
+		goto reschedule_work;
+
 	ctrl->cc = new_cc;
 
 	if (nvmet_cc_en(new_cc) && !nvmet_cc_en(old_cc)) {
 		ret = nvmet_pci_epf_enable_ctrl(ctrl);
 		if (ret)
-			return;
+			goto reschedule_work;
 	}
 
 	if (!nvmet_cc_en(new_cc) && nvmet_cc_en(old_cc))
@@ -1932,6 +1935,7 @@ static void nvmet_pci_epf_poll_cc_work(struct work_struct *work)
 	nvmet_update_cc(ctrl->tctrl, ctrl->cc);
 	nvmet_pci_epf_bar_write32(ctrl, NVME_REG_CSTS, ctrl->csts);
 
+reschedule_work:
 	schedule_delayed_work(&ctrl->poll_cc, NVMET_PCI_EPF_CC_POLL_INTERVAL);
 }
 

From 01ef7ff7dd3cd8cc71af8d1d1496be853281a948 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:30 +0900
Subject: [PATCH 0697/2753] nvmet: pci-epf: Avoid RCU stalls under heavy
 workload

The delayed work item function nvmet_pci_epf_poll_sqs_work() polls all
submission queues and keeps running in a loop as long as commands are
being submitted by the host. Depending on the preemption configuration
of the kernel, under heavy command workload, this function can thus run
for more than RCU_CPU_STALL_TIMEOUT seconds, leading to a RCU stall:

 rcu: INFO: rcu_sched self-detected stall on CPU
 rcu:   5-....: (20998 ticks this GP) idle=4244/1/0x4000000000000000 softirq=301/301 fqs=5132
 rcu:   (t=21000 jiffies g=-443 q=12 ncpus=8)
 CPU: 5 UID: 0 PID: 82 Comm: kworker/5:1 Not tainted 6.14.0-rc2 #1
 Hardware name: Radxa ROCK 5B (DT)
 Workqueue: events nvmet_pci_epf_poll_sqs_work [nvmet_pci_epf]
 pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
 pc : dw_edma_device_tx_status+0xb8/0x130
 lr : dw_edma_device_tx_status+0x9c/0x130
 sp : ffff800080b5bbb0
 x29: ffff800080b5bbb0 x28: ffff0331c5c78400 x27: ffff0331c1cd1960
 x26: ffff0331c0e39010 x25: ffff0331c20e4000 x24: ffff0331c20e4a90
 x23: 0000000000000000 x22: 0000000000000001 x21: 00000000005aca33
 x20: ffff800080b5bc30 x19: ffff0331c123e370 x18: 000000000ab29e62
 x17: ffffb2a878c9c118 x16: ffff0335bde82040 x15: 0000000000000000
 x14: 000000000000017b x13: 00000000ee601780 x12: 0000000000000018
 x11: 0000000000000000 x10: 0000000000000001 x9 : 0000000000000040
 x8 : 00000000ee601780 x7 : 0000000105c785c0 x6 : ffff0331c1027d80
 x5 : 0000000001ee7ad6 x4 : ffff0335bdea16c0 x3 : ffff0331c123e438
 x2 : 00000000005aca33 x1 : 0000000000000000 x0 : ffff0331c123e410
 Call trace:
  dw_edma_device_tx_status+0xb8/0x130 (P)
  dma_sync_wait+0x60/0xbc
  nvmet_pci_epf_dma_transfer+0x128/0x264 [nvmet_pci_epf]
  nvmet_pci_epf_poll_sqs_work+0x2a0/0x2e0 [nvmet_pci_epf]
  process_one_work+0x144/0x390
  worker_thread+0x27c/0x458
  kthread+0xe8/0x19c
  ret_from_fork+0x10/0x20

The solution for this is simply to explicitly allow rescheduling using
cond_resched(). However, since doing so for every loop of
nvmet_pci_epf_poll_sqs_work() significantly degrades performance
(for 4K random reads using 4 I/O queues, the maximum IOPS goes down from
137 KIOPS to 110 KIOPS), call cond_resched() every second to avoid the
RCU stalls.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index b646a8f468ea9..565d2bd36dcde 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1694,6 +1694,7 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
 	struct nvmet_pci_epf_ctrl *ctrl =
 		container_of(work, struct nvmet_pci_epf_ctrl, poll_sqs.work);
 	struct nvmet_pci_epf_queue *sq;
+	unsigned long limit = jiffies;
 	unsigned long last = 0;
 	int i, nr_sqs;
 
@@ -1708,6 +1709,16 @@ static void nvmet_pci_epf_poll_sqs_work(struct work_struct *work)
 				nr_sqs++;
 		}
 
+		/*
+		 * If we have been running for a while, reschedule to let other
+		 * tasks run and to avoid RCU stalls.
+		 */
+		if (time_is_before_jiffies(limit + secs_to_jiffies(1))) {
+			cond_resched();
+			limit = jiffies;
+			continue;
+		}
+
 		if (nr_sqs) {
 			last = jiffies;
 			continue;

From cd513e0434c3e736c549bc99bf7982658b25114d Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:52:31 +0900
Subject: [PATCH 0698/2753] nvme: tcp: Fix compilation warning with W=1

When compiling with W=1, a warning result for the function
nvme_tcp_set_queue_io_cpu():

host/tcp.c:1578: warning: Function parameter or struct member 'queue'
not described in 'nvme_tcp_set_queue_io_cpu'
host/tcp.c:1578: warning: expecting prototype for Track the number of
queues assigned to each cpu using a global per(). Prototype was for
nvme_tcp_set_queue_io_cpu() instead

Avoid this warning by using the regular comment format for the function
nvme_tcp_set_queue_io_cpu() instead of the kdoc comment format.

Fixes: 32193789878c ("nvme-tcp: Fix I/O queue cpu spreading for multiple controllers")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 038b35238c26d..a7398e9e5f71c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1608,7 +1608,7 @@ static bool nvme_tcp_poll_queue(struct nvme_tcp_queue *queue)
 			  ctrl->io_queues[HCTX_TYPE_POLL];
 }
 
-/**
+/*
  * Track the number of queues assigned to each cpu using a global per-cpu
  * counter and select the least used cpu from the mq_map. Our goal is to spread
  * different controllers I/O threads across different cpu cores.

From 578539e0969028f711c34d9a4565931edfe1d730 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Fri, 24 Jan 2025 11:43:10 -0700
Subject: [PATCH 0699/2753] nvme-tcp: fix connect failure on receiving partial
 ICResp PDU

nvme_tcp_init_connection() attempts to receive an ICResp PDU but only
checks that the return value from recvmsg() is non-negative. If the
sender closes the TCP connection or sends fewer than 128 bytes, this
check will pass even though the full PDU wasn't received.

Ensure the full ICResp PDU is received by checking that recvmsg()
returns the expected 128 bytes.

Additionally set the MSG_WAITALL flag for recvmsg(), as a sender could
split the ICResp over multiple TCP frames. Without MSG_WAITALL,
recvmsg() could return prematurely with only part of the PDU.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index a7398e9e5f71c..8a9131c95a3da 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1492,11 +1492,14 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 		msg.msg_control = cbuf;
 		msg.msg_controllen = sizeof(cbuf);
 	}
+	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < 0) {
+	if (ret < sizeof(*icresp)) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
+		if (ret >= 0)
+			ret = -ECONNRESET;
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;

From 487a3ea7b1b8ba2ca7d2c2bb3c3594dc360d6261 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Thu, 13 Feb 2025 10:05:14 -0700
Subject: [PATCH 0700/2753] nvme/ioctl: add missing space in err message

nvme_validate_passthru_nsid() logs an err message whose format string is
split over 2 lines. There is a missing space between the two pieces,
resulting in log lines like "... does not match nsid (1)of namespace".
Add the missing space between ")" and "of". Also combine the format
string pieces onto a single line to make the err message easier to grep.

Fixes: e7d4b5493a2d ("nvme: factor out a nvme_validate_passthru_nsid helper")
Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/ioctl.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index e8930146847af..b1b46c2713e1c 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -283,8 +283,7 @@ static bool nvme_validate_passthru_nsid(struct nvme_ctrl *ctrl,
 {
 	if (ns && nsid != ns->head->ns_id) {
 		dev_err(ctrl->device,
-			"%s: nsid (%u) in cmd does not match nsid (%u)"
-			"of namespace\n",
+			"%s: nsid (%u) in cmd does not match nsid (%u) of namespace\n",
 			current->comm, nsid, ns->head->ns_id);
 		return false;
 	}

From d422247d14a53fe825b1778edf104167d8fd8f3f Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:49:59 +0900
Subject: [PATCH 0701/2753] nvme: Cleanup the definition of the controller
 config register fields

Reorganized the enum used to define the fields of the contrller
configuration (CC) register in include/linux/nvme.h to:
1) Group together all the values defined for each field.
2) Add the missing field masks definitions.
3) Add comments to describe the enum and each field.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 include/linux/nvme.h | 40 +++++++++++++++++++++++++++++++++-------
 1 file changed, 33 insertions(+), 7 deletions(-)

diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index fe3b60818fdcf..2dc05b1c3283d 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -199,28 +199,54 @@ enum {
 #define NVME_NVM_IOSQES		6
 #define NVME_NVM_IOCQES		4
 
+/*
+ * Controller Configuration (CC) register (Offset 14h)
+ */
 enum {
+	/* Enable (EN): bit 0 */
 	NVME_CC_ENABLE		= 1 << 0,
 	NVME_CC_EN_SHIFT	= 0,
+
+	/* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */
+
+	/* I/O Command Set Selected (CSS): bits 06:04 */
 	NVME_CC_CSS_SHIFT	= 4,
-	NVME_CC_MPS_SHIFT	= 7,
-	NVME_CC_AMS_SHIFT	= 11,
-	NVME_CC_SHN_SHIFT	= 14,
-	NVME_CC_IOSQES_SHIFT	= 16,
-	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
-	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
+
+	/* Memory Page Size (MPS): bits 10:07 */
+	NVME_CC_MPS_SHIFT	= 7,
+	NVME_CC_MPS_MASK	= 0xf << NVME_CC_MPS_SHIFT,
+
+	/* Arbitration Mechanism Selected (AMS): bits 13:11 */
+	NVME_CC_AMS_SHIFT	= 11,
+	NVME_CC_AMS_MASK	= 7 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
+
+	/* Shutdown Notification (SHN): bits 15:14 */
+	NVME_CC_SHN_SHIFT	= 14,
+	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NONE	= 0 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NORMAL	= 1 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_ABRUPT	= 2 << NVME_CC_SHN_SHIFT,
-	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
+
+	/* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */
+	NVME_CC_IOSQES_SHIFT	= 16,
+	NVME_CC_IOSQES_MASK	= 0xf << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
+
+	/* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */
+	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_IOCQES_MASK	= 0xf << NVME_CC_IOCQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+
+	/* Controller Ready Independent of Media Enable (CRIME): bit 24 */
 	NVME_CC_CRIME		= 1 << 24,
+
+	/* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */
 };
 
 enum {

From 2ba8cf918f0d1873cd5430ae2cc3c41711a144d7 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 13 Feb 2025 15:50:00 +0900
Subject: [PATCH 0702/2753] nvmet: Use enum definitions instead of hardcoded
 values

Change the definition of the inline functions nvmet_cc_en(),
nvmet_cc_css(), nvmet_cc_mps(), nvmet_cc_ams(), nvmet_cc_shn(),
nvmet_cc_iosqes(), and nvmet_cc_iocqes() to use the enum difinitions in
include/linux/nvme.h instead of hardcoded values.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/nvmet.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index 4be8d22d2d8d4..d2c1233981e1a 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -784,37 +784,37 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req);
 
 static inline bool nvmet_cc_en(u32 cc)
 {
-	return (cc >> NVME_CC_EN_SHIFT) & 0x1;
+	return (cc & NVME_CC_ENABLE) >> NVME_CC_EN_SHIFT;
 }
 
 static inline u8 nvmet_cc_css(u32 cc)
 {
-	return (cc >> NVME_CC_CSS_SHIFT) & 0x7;
+	return (cc & NVME_CC_CSS_MASK) >> NVME_CC_CSS_SHIFT;
 }
 
 static inline u8 nvmet_cc_mps(u32 cc)
 {
-	return (cc >> NVME_CC_MPS_SHIFT) & 0xf;
+	return (cc & NVME_CC_MPS_MASK) >> NVME_CC_MPS_SHIFT;
 }
 
 static inline u8 nvmet_cc_ams(u32 cc)
 {
-	return (cc >> NVME_CC_AMS_SHIFT) & 0x7;
+	return (cc & NVME_CC_AMS_MASK) >> NVME_CC_AMS_SHIFT;
 }
 
 static inline u8 nvmet_cc_shn(u32 cc)
 {
-	return (cc >> NVME_CC_SHN_SHIFT) & 0x3;
+	return (cc & NVME_CC_SHN_MASK) >> NVME_CC_SHN_SHIFT;
 }
 
 static inline u8 nvmet_cc_iosqes(u32 cc)
 {
-	return (cc >> NVME_CC_IOSQES_SHIFT) & 0xf;
+	return (cc & NVME_CC_IOSQES_MASK) >> NVME_CC_IOSQES_SHIFT;
 }
 
 static inline u8 nvmet_cc_iocqes(u32 cc)
 {
-	return (cc >> NVME_CC_IOCQES_SHIFT) & 0xf;
+	return (cc & NVME_CC_IOCQES_MASK) >> NVME_CC_IOCQES_SHIFT;
 }
 
 /* Convert a 32-bit number to a 16-bit 0's based number */

From eefa72a15ea03fd009333aaa9f0e360b2578e434 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Thu, 13 Feb 2025 11:12:59 -0500
Subject: [PATCH 0703/2753] apple-nvme: Release power domains when probe fails

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/apple.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 1de11b722f049..7995f0776bc06 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1516,6 +1516,7 @@ static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
 
 	return anv;
 put_dev:
+	apple_nvme_detach_genpd(anv);
 	put_device(anv->dev);
 	return ERR_PTR(ret);
 }
@@ -1549,6 +1550,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
 	nvme_uninit_ctrl(&anv->ctrl);
 out_put_ctrl:
 	nvme_put_ctrl(&anv->ctrl);
+	apple_nvme_detach_genpd(anv);
 	return ret;
 }
 

From 3f22421f6a240b33ab8ffbf662bf0a8f336f405b Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Thu, 13 Feb 2025 11:12:58 -0500
Subject: [PATCH 0704/2753] apple-nvme: Support coprocessors left idle

iBoot on at least some firmwares/machines leaves ANS2 running, requiring
a wake command instead of a CPU boot (and if we reset ANS2 in that
state, everything breaks).

Only stop the CPU if RTKit was running, and only do the reset dance if
the CPU is stopped.

Normal shutdown handoff:
- RTKit not yet running
- CPU detected not running
- Reset
- CPU powerup
- RTKit boot wait

ANS2 left running/idle:
- RTKit not yet running
- CPU detected running
- RTKit wake message

Sleep/resume cycle:
- RTKit shutdown
- CPU stopped
- (sleep here)
- CPU detected not running
- Reset
- CPU powerup
- RTKit boot wait

Shutdown or device removal:
- RTKit shutdown
- CPU stopped

Therefore, the CPU running bit serves as a consistent flag of whether
the coprocessor is fully stopped or just idle.

Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Reviewed-by: Sven Peter <sven@svenpeter.dev>
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/apple.c | 53 ++++++++++++++++++++++++++-------------
 1 file changed, 36 insertions(+), 17 deletions(-)

diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index 7995f0776bc06..a060f69558e76 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -1011,25 +1011,37 @@ static void apple_nvme_reset_work(struct work_struct *work)
 		ret = apple_rtkit_shutdown(anv->rtk);
 		if (ret)
 			goto out;
+
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
 	}
 
-	writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	/*
+	 * Only do the soft-reset if the CPU is not running, which means either we
+	 * or the previous stage shut it down cleanly.
+	 */
+	if (!(readl(anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL) &
+		APPLE_ANS_COPROC_CPU_CONTROL_RUN)) {
 
-	ret = reset_control_assert(anv->reset);
-	if (ret)
-		goto out;
+		ret = reset_control_assert(anv->reset);
+		if (ret)
+			goto out;
 
-	ret = apple_rtkit_reinit(anv->rtk);
-	if (ret)
-		goto out;
+		ret = apple_rtkit_reinit(anv->rtk);
+		if (ret)
+			goto out;
 
-	ret = reset_control_deassert(anv->reset);
-	if (ret)
-		goto out;
+		ret = reset_control_deassert(anv->reset);
+		if (ret)
+			goto out;
+
+		writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
+		       anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+
+		ret = apple_rtkit_boot(anv->rtk);
+	} else {
+		ret = apple_rtkit_wake(anv->rtk);
+	}
 
-	writel(APPLE_ANS_COPROC_CPU_CONTROL_RUN,
-	       anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
-	ret = apple_rtkit_boot(anv->rtk);
 	if (ret) {
 		dev_err(anv->dev, "ANS did not boot");
 		goto out;
@@ -1565,9 +1577,12 @@ static void apple_nvme_remove(struct platform_device *pdev)
 	apple_nvme_disable(anv, true);
 	nvme_uninit_ctrl(&anv->ctrl);
 
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		apple_rtkit_shutdown(anv->rtk);
 
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
+
 	apple_nvme_detach_genpd(anv);
 }
 
@@ -1576,8 +1591,11 @@ static void apple_nvme_shutdown(struct platform_device *pdev)
 	struct apple_nvme *anv = platform_get_drvdata(pdev);
 
 	apple_nvme_disable(anv, true);
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		apple_rtkit_shutdown(anv->rtk);
+
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
 }
 
 static int apple_nvme_resume(struct device *dev)
@@ -1594,10 +1612,11 @@ static int apple_nvme_suspend(struct device *dev)
 
 	apple_nvme_disable(anv, true);
 
-	if (apple_rtkit_is_running(anv->rtk))
+	if (apple_rtkit_is_running(anv->rtk)) {
 		ret = apple_rtkit_shutdown(anv->rtk);
 
-	writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+		writel(0, anv->mmio_coproc + APPLE_ANS_COPROC_CPU_CONTROL);
+	}
 
 	return ret;
 }

From ed83aff5a94e1d623c007159a6a7f1c3ef202c6c Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 12 Feb 2025 12:01:15 +0100
Subject: [PATCH 0705/2753] s390: Update defconfigs

Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/configs/debug_defconfig | 2 ++
 arch/s390/configs/defconfig       | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 44f01a4bc810f..80bdfbae6e5b4 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -469,6 +469,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -874,6 +875,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=300
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index 8bcd37edd3c97..449a0e996b963 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -459,6 +459,7 @@ CONFIG_SCSI_DH_ALUA=m
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=y
 # CONFIG_MD_BITMAP_FILE is not set
+CONFIG_MD_LINEAR=m
 CONFIG_MD_CLUSTER=m
 CONFIG_BCACHE=m
 CONFIG_BLK_DEV_DM=y
@@ -825,6 +826,7 @@ CONFIG_RCU_CPU_STALL_TIMEOUT=60
 CONFIG_LATENCYTOP=y
 CONFIG_BOOTTIME_TRACING=y
 CONFIG_FUNCTION_GRAPH_RETVAL=y
+CONFIG_FUNCTION_GRAPH_RETADDR=y
 CONFIG_FPROBE=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_STACK_TRACER=y

From 173767c218cc1da74704e7863f165ac8a9796f3e Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Thu, 13 Feb 2025 21:16:14 +0000
Subject: [PATCH 0706/2753] s390/purgatory: Use -D__DISABLE_EXPORTS

The object files in purgatory do not export symbols, so disable exports
for all the object files, not only sha256.o, with -D__DISABLE_EXPORTS.

This fixes a build failure with CONFIG_GENDWARFKSYMS, where we would
otherwise attempt to calculate symbol versions for purgatory objects and
fail because they're not built with debugging information:

error: gendwarfksyms: process_module: dwarf_get_units failed: no debugging information?
make[5]: *** [../scripts/Makefile.build:207: arch/s390/purgatory/string.o] Error 1
make[5]: *** Deleting file 'arch/s390/purgatory/string.o'

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502120752.U3fOKScQ-lkp@intel.com/
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250213211614.3537605-2-samitolvanen@google.com
Acked-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/purgatory/Makefile | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/arch/s390/purgatory/Makefile b/arch/s390/purgatory/Makefile
index bdcf2a3b6c41b..bd39b36e7bd68 100644
--- a/arch/s390/purgatory/Makefile
+++ b/arch/s390/purgatory/Makefile
@@ -8,7 +8,7 @@ PURGATORY_OBJS = $(addprefix $(obj)/,$(purgatory-y))
 $(obj)/sha256.o: $(srctree)/lib/crypto/sha256.c FORCE
 	$(call if_changed_rule,cc_o_c)
 
-CFLAGS_sha256.o := -D__DISABLE_EXPORTS -D__NO_FORTIFY
+CFLAGS_sha256.o := -D__NO_FORTIFY
 
 $(obj)/mem.o: $(srctree)/arch/s390/lib/mem.S FORCE
 	$(call if_changed_rule,as_o_S)
@@ -19,9 +19,11 @@ KBUILD_CFLAGS += -fno-zero-initialized-in-bss -fno-builtin -ffreestanding
 KBUILD_CFLAGS += -Os -m64 -msoft-float -fno-common
 KBUILD_CFLAGS += -fno-stack-protector
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS
 KBUILD_CFLAGS += $(CLANG_FLAGS)
 KBUILD_CFLAGS += $(call cc-option,-fno-PIE)
 KBUILD_AFLAGS := $(filter-out -DCC_USING_EXPOLINE,$(KBUILD_AFLAGS))
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
 
 # Since we link purgatory with -r unresolved symbols are not checked, so we
 # also link a purgatory.chk binary without -r to check for unresolved symbols.

From c3a589fd9fcbf295a7402a4b188dc9277d505f4f Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 18 Feb 2025 12:11:34 +0100
Subject: [PATCH 0707/2753] s390/boot: Fix ESSA detection

The cmma_test_essa() inline assembly uses tmp as input and output, however
tmp is specified as output only, which allows the compiler to optimize the
initialization of tmp away.

Therefore the ESSA detection may or may not work depending on previous
contents of the register that the compiler selected for tmp.

Fix this by using the correct constraint modifier.

Fixes: 468a3bc2b7b9 ("s390/cmma: move parsing of cmma kernel parameter to early boot code")
Cc: stable@vger.kernel.org
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/boot/startup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
index 885bd1dd2c82f..9276e0576d0ab 100644
--- a/arch/s390/boot/startup.c
+++ b/arch/s390/boot/startup.c
@@ -86,7 +86,7 @@ static int cmma_test_essa(void)
 		: [reg1] "=&d" (reg1),
 		  [reg2] "=&a" (reg2),
 		  [rc] "+&d" (rc),
-		  [tmp] "=&d" (tmp),
+		  [tmp] "+&d" (tmp),
 		  "+Q" (get_lowcore()->program_new_psw),
 		  "=Q" (old)
 		: [psw_old] "a" (&old),

From 9ee2578c343a2c8b6cf6c43f2f385cdb56a25250 Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <quic_miaoqing@quicinc.com>
Date: Tue, 13 Aug 2024 09:30:27 +0800
Subject: [PATCH 0708/2753] wifi: ath11k: use union for vaddr and iaddr in
 target_mem_chunk

The value of 'ab->hw_params.fixed_mem_region' determines that
only one variable 'vaddr' or 'iaddr' is used in target_mem_chunk.
So use an anonymous union instead, easy to check whether the
memory is set or not.

Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-04358-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1

Signed-off-by: Miaoqing Pan <quic_miaoqing@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20240813013028.2708111-1-quic_miaoqing@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/qmi.c | 17 ++++++++++-------
 drivers/net/wireless/ath/ath11k/qmi.h |  9 ++++++---
 2 files changed, 16 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
index 5759fc5213162..4f8b08ed1bbc6 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.c
+++ b/drivers/net/wireless/ath/ath11k/qmi.c
@@ -1957,13 +1957,15 @@ static void ath11k_qmi_free_target_mem_chunk(struct ath11k_base *ab)
 	int i;
 
 	for (i = 0; i < ab->qmi.mem_seg_count; i++) {
-		if ((ab->hw_params.fixed_mem_region ||
-		     test_bit(ATH11K_FLAG_FIXED_MEM_RGN, &ab->dev_flags)) &&
-		     ab->qmi.target_mem[i].iaddr)
-			iounmap(ab->qmi.target_mem[i].iaddr);
+		if (!ab->qmi.target_mem[i].anyaddr)
+			continue;
 
-		if (!ab->qmi.target_mem[i].vaddr)
+		if (ab->hw_params.fixed_mem_region ||
+		    test_bit(ATH11K_FLAG_FIXED_MEM_RGN, &ab->dev_flags)) {
+			iounmap(ab->qmi.target_mem[i].iaddr);
+			ab->qmi.target_mem[i].iaddr = NULL;
 			continue;
+		}
 
 		dma_free_coherent(ab->dev,
 				  ab->qmi.target_mem[i].prev_size,
@@ -2070,7 +2072,7 @@ static int ath11k_qmi_assign_target_mem_chunk(struct ath11k_base *ab)
 			break;
 		case BDF_MEM_REGION_TYPE:
 			ab->qmi.target_mem[idx].paddr = ab->hw_params.bdf_addr;
-			ab->qmi.target_mem[idx].vaddr = NULL;
+			ab->qmi.target_mem[idx].iaddr = NULL;
 			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
 			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
 			idx++;
@@ -2093,10 +2095,11 @@ static int ath11k_qmi_assign_target_mem_chunk(struct ath11k_base *ab)
 				} else {
 					ab->qmi.target_mem[idx].paddr =
 						ATH11K_QMI_CALDB_ADDRESS;
+					ab->qmi.target_mem[idx].iaddr = NULL;
 				}
 			} else {
 				ab->qmi.target_mem[idx].paddr = 0;
-				ab->qmi.target_mem[idx].vaddr = NULL;
+				ab->qmi.target_mem[idx].iaddr = NULL;
 			}
 			ab->qmi.target_mem[idx].size = ab->qmi.target_mem[i].size;
 			ab->qmi.target_mem[idx].type = ab->qmi.target_mem[i].type;
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index 7e06d100af575..fdf9b5f8c19f1 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: BSD-3-Clause-Clear */
 /*
  * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
- * Copyright (c) 2021-2023 Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2021-2024 Qualcomm Innovation Center, Inc. All rights reserved.
  */
 
 #ifndef ATH11K_QMI_H
@@ -102,8 +102,11 @@ struct target_mem_chunk {
 	u32 prev_size;
 	u32 prev_type;
 	dma_addr_t paddr;
-	u32 *vaddr;
-	void __iomem *iaddr;
+	union {
+		u32 *vaddr;
+		void __iomem *iaddr;
+		void *anyaddr;
+	};
 };
 
 struct target_info {

From 5edbb148bc57295a6abbb31b832878c0725ed10a Mon Sep 17 00:00:00 2001
From: Miaoqing Pan <quic_miaoqing@quicinc.com>
Date: Tue, 13 Aug 2024 09:30:28 +0800
Subject: [PATCH 0709/2753] wifi: ath11k: Add firmware coredump collection
 support

In case of firmware assert snapshot of firmware memory is essential for
debugging. Add firmware coredump collection support for PCI bus.
Collect RDDM and firmware paging dumps from MHI and pack them in TLV
format and also pack various memory shared during QMI phase in separate
TLVs.  Add necessary header and share the dumps to user space using dev
coredump framework. Coredump collection is controlled by
CONFIG_DEV_COREDUMP. Dump collected for a radio is 55 MB approximately.

The changeset is mostly copied from:
https://lore.kernel.org/all/20240325183414.4016663-1-quic_ssreeela@quicinc.com/.

Tested-on: WCN6855 hw2.1 PCI WLAN.HSP.1.1-04358-QCAHSPSWPL_V1_V2_SILICONZ_LITE-1

Signed-off-by: Miaoqing Pan <quic_miaoqing@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20240813013028.2708111-2-quic_miaoqing@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/Makefile   |   1 +
 drivers/net/wireless/ath/ath11k/core.c     |   2 +
 drivers/net/wireless/ath/ath11k/core.h     |   5 +
 drivers/net/wireless/ath/ath11k/coredump.c |  52 ++++++
 drivers/net/wireless/ath/ath11k/coredump.h |  79 +++++++++
 drivers/net/wireless/ath/ath11k/hif.h      |   7 +
 drivers/net/wireless/ath/ath11k/mhi.c      |   5 +
 drivers/net/wireless/ath/ath11k/mhi.h      |   1 +
 drivers/net/wireless/ath/ath11k/pci.c      | 188 +++++++++++++++++++++
 drivers/net/wireless/ath/ath11k/qmi.h      |   1 +
 10 files changed, 341 insertions(+)
 create mode 100644 drivers/net/wireless/ath/ath11k/coredump.c
 create mode 100644 drivers/net/wireless/ath/ath11k/coredump.h

diff --git a/drivers/net/wireless/ath/ath11k/Makefile b/drivers/net/wireless/ath/ath11k/Makefile
index 43d2d8ddcdc05..d9092414b362d 100644
--- a/drivers/net/wireless/ath/ath11k/Makefile
+++ b/drivers/net/wireless/ath/ath11k/Makefile
@@ -27,6 +27,7 @@ ath11k-$(CONFIG_ATH11K_TRACING) += trace.o
 ath11k-$(CONFIG_THERMAL) += thermal.o
 ath11k-$(CONFIG_ATH11K_SPECTRAL) += spectral.o
 ath11k-$(CONFIG_PM) += wow.o
+ath11k-$(CONFIG_DEV_COREDUMP) += coredump.o
 
 obj-$(CONFIG_ATH11K_AHB) += ath11k_ahb.o
 ath11k_ahb-y += ahb.o
diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 12dd37c2e9044..65bba0ae69a9a 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -2258,6 +2258,7 @@ static void ath11k_core_reset(struct work_struct *work)
 	reinit_completion(&ab->recovery_start);
 	atomic_set(&ab->recovery_start_count, 0);
 
+	ath11k_coredump_collect(ab);
 	ath11k_core_pre_reconfigure_recovery(ab);
 
 	reinit_completion(&ab->reconfigure_complete);
@@ -2393,6 +2394,7 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
 	INIT_WORK(&ab->restart_work, ath11k_core_restart);
 	INIT_WORK(&ab->update_11d_work, ath11k_update_11d);
 	INIT_WORK(&ab->reset_work, ath11k_core_reset);
+	INIT_WORK(&ab->dump_work, ath11k_coredump_upload);
 	timer_setup(&ab->rx_replenish_retry, ath11k_ce_rx_replenish_retry, 0);
 	init_completion(&ab->htc_suspend);
 	init_completion(&ab->wow.wakeup_completed);
diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
index 9842a4d65c7b9..1a3d0de4afde8 100644
--- a/drivers/net/wireless/ath/ath11k/core.h
+++ b/drivers/net/wireless/ath/ath11k/core.h
@@ -32,6 +32,7 @@
 #include "spectral.h"
 #include "wow.h"
 #include "fw.h"
+#include "coredump.h"
 
 #define SM(_v, _f) (((_v) << _f##_LSB) & _f##_MASK)
 
@@ -904,6 +905,10 @@ struct ath11k_base {
 	/* HW channel counters frequency value in hertz common to all MACs */
 	u32 cc_freq_hz;
 
+	struct ath11k_dump_file_data *dump_data;
+	size_t ath11k_coredump_len;
+	struct work_struct dump_work;
+
 	struct ath11k_htc htc;
 
 	struct ath11k_dp dp;
diff --git a/drivers/net/wireless/ath/ath11k/coredump.c b/drivers/net/wireless/ath/ath11k/coredump.c
new file mode 100644
index 0000000000000..b8bad358cebec
--- /dev/null
+++ b/drivers/net/wireless/ath/ath11k/coredump.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: BSD-3-Clause-Clear
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+#include <linux/devcoredump.h>
+#include "hif.h"
+#include "coredump.h"
+#include "debug.h"
+
+enum
+ath11k_fw_crash_dump_type ath11k_coredump_get_dump_type(int type)
+{
+	enum ath11k_fw_crash_dump_type dump_type;
+
+	switch (type) {
+	case HOST_DDR_REGION_TYPE:
+		dump_type = FW_CRASH_DUMP_REMOTE_MEM_DATA;
+		break;
+	case M3_DUMP_REGION_TYPE:
+		dump_type = FW_CRASH_DUMP_M3_DUMP;
+		break;
+	case PAGEABLE_MEM_REGION_TYPE:
+		dump_type = FW_CRASH_DUMP_PAGEABLE_DATA;
+		break;
+	case BDF_MEM_REGION_TYPE:
+	case CALDB_MEM_REGION_TYPE:
+		dump_type = FW_CRASH_DUMP_NONE;
+		break;
+	default:
+		dump_type = FW_CRASH_DUMP_TYPE_MAX;
+		break;
+	}
+
+	return dump_type;
+}
+EXPORT_SYMBOL(ath11k_coredump_get_dump_type);
+
+void ath11k_coredump_upload(struct work_struct *work)
+{
+	struct ath11k_base *ab = container_of(work, struct ath11k_base, dump_work);
+
+	ath11k_info(ab, "Uploading coredump\n");
+	/* dev_coredumpv() takes ownership of the buffer */
+	dev_coredumpv(ab->dev, ab->dump_data, ab->ath11k_coredump_len, GFP_KERNEL);
+	ab->dump_data = NULL;
+}
+
+void ath11k_coredump_collect(struct ath11k_base *ab)
+{
+	ath11k_hif_coredump_download(ab);
+}
diff --git a/drivers/net/wireless/ath/ath11k/coredump.h b/drivers/net/wireless/ath/ath11k/coredump.h
new file mode 100644
index 0000000000000..3960d93852617
--- /dev/null
+++ b/drivers/net/wireless/ath/ath11k/coredump.h
@@ -0,0 +1,79 @@
+/* SPDX-License-Identifier: BSD-3-Clause-Clear */
+/*
+ * Copyright (c) 2020 The Linux Foundation. All rights reserved.
+ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+#ifndef _ATH11K_COREDUMP_H_
+#define _ATH11K_COREDUMP_H_
+
+#define ATH11K_FW_CRASH_DUMP_V2      2
+
+enum ath11k_fw_crash_dump_type {
+	FW_CRASH_DUMP_PAGING_DATA,
+	FW_CRASH_DUMP_RDDM_DATA,
+	FW_CRASH_DUMP_REMOTE_MEM_DATA,
+	FW_CRASH_DUMP_PAGEABLE_DATA,
+	FW_CRASH_DUMP_M3_DUMP,
+	FW_CRASH_DUMP_NONE,
+
+	/* keep last */
+	FW_CRASH_DUMP_TYPE_MAX,
+};
+
+#define COREDUMP_TLV_HDR_SIZE 8
+
+struct ath11k_tlv_dump_data {
+	/* see ath11k_fw_crash_dump_type above */
+	__le32 type;
+
+	/* in bytes */
+	__le32 tlv_len;
+
+	/* pad to 32-bit boundaries as needed */
+	u8 tlv_data[];
+} __packed;
+
+struct ath11k_dump_file_data {
+	/* "ATH11K-FW-DUMP" */
+	char df_magic[16];
+	/* total dump len in bytes */
+	__le32 len;
+	/* file dump version */
+	__le32 version;
+	/* pci device id */
+	__le32 chip_id;
+	/* qrtr instance id */
+	__le32 qrtr_id;
+	/* pci domain id */
+	__le32 bus_id;
+	guid_t guid;
+	/* time-of-day stamp */
+	__le64 tv_sec;
+	/* time-of-day stamp, nano-seconds */
+	__le64 tv_nsec;
+	/* room for growth w/out changing binary format */
+	u8 unused[128];
+	u8 data[];
+} __packed;
+
+#ifdef CONFIG_DEV_COREDUMP
+enum ath11k_fw_crash_dump_type ath11k_coredump_get_dump_type(int type);
+void ath11k_coredump_upload(struct work_struct *work);
+void ath11k_coredump_collect(struct ath11k_base *ab);
+#else
+static inline enum
+ath11k_fw_crash_dump_type ath11k_coredump_get_dump_type(int type)
+{
+	return FW_CRASH_DUMP_TYPE_MAX;
+}
+
+static inline void ath11k_coredump_upload(struct work_struct *work)
+{
+}
+
+static inline void ath11k_coredump_collect(struct ath11k_base *ab)
+{
+}
+#endif
+
+#endif
diff --git a/drivers/net/wireless/ath/ath11k/hif.h b/drivers/net/wireless/ath/ath11k/hif.h
index 674ff772b181b..770c39ff99b45 100644
--- a/drivers/net/wireless/ath/ath11k/hif.h
+++ b/drivers/net/wireless/ath/ath11k/hif.h
@@ -31,6 +31,7 @@ struct ath11k_hif_ops {
 	void (*ce_irq_enable)(struct ath11k_base *ab);
 	void (*ce_irq_disable)(struct ath11k_base *ab);
 	void (*get_ce_msi_idx)(struct ath11k_base *ab, u32 ce_id, u32 *msi_idx);
+	void (*coredump_download)(struct ath11k_base *ab);
 };
 
 static inline void ath11k_hif_ce_irq_enable(struct ath11k_base *ab)
@@ -146,4 +147,10 @@ static inline void ath11k_get_ce_msi_idx(struct ath11k_base *ab, u32 ce_id,
 		*msi_data_idx = ce_id;
 }
 
+static inline void ath11k_hif_coredump_download(struct ath11k_base *ab)
+{
+	if (ab->hif.ops->coredump_download)
+		ab->hif.ops->coredump_download(ab);
+}
+
 #endif /* _HIF_H_ */
diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
index 6e45f464a429b..fc77eac83e953 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.c
+++ b/drivers/net/wireless/ath/ath11k/mhi.c
@@ -491,3 +491,8 @@ int ath11k_mhi_resume(struct ath11k_pci *ab_pci)
 
 	return 0;
 }
+
+void ath11k_mhi_coredump(struct mhi_controller *mhi_ctrl, bool in_panic)
+{
+	mhi_download_rddm_image(mhi_ctrl, in_panic);
+}
diff --git a/drivers/net/wireless/ath/ath11k/mhi.h b/drivers/net/wireless/ath/ath11k/mhi.h
index a682aad52fc51..651470091bd5a 100644
--- a/drivers/net/wireless/ath/ath11k/mhi.h
+++ b/drivers/net/wireless/ath/ath11k/mhi.h
@@ -26,5 +26,6 @@ void ath11k_mhi_clear_vector(struct ath11k_base *ab);
 
 int ath11k_mhi_suspend(struct ath11k_pci *ar_pci);
 int ath11k_mhi_resume(struct ath11k_pci *ar_pci);
+void ath11k_mhi_coredump(struct mhi_controller *mhi_ctrl, bool in_panic);
 
 #endif
diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index f1121e3317194..6565ac1917b79 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -8,6 +8,8 @@
 #include <linux/msi.h>
 #include <linux/pci.h>
 #include <linux/of.h>
+#include <linux/time.h>
+#include <linux/vmalloc.h>
 
 #include "pci.h"
 #include "core.h"
@@ -610,6 +612,187 @@ static void ath11k_pci_aspm_restore(struct ath11k_pci *ab_pci)
 						   PCI_EXP_LNKCTL_ASPMC);
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static int ath11k_pci_coredump_calculate_size(struct ath11k_base *ab, u32 *dump_seg_sz)
+{
+	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+	struct mhi_controller *mhi_ctrl = ab_pci->mhi_ctrl;
+	struct image_info *rddm_img, *fw_img;
+	struct ath11k_tlv_dump_data *dump_tlv;
+	enum ath11k_fw_crash_dump_type mem_type;
+	u32 len = 0, rddm_tlv_sz = 0, paging_tlv_sz = 0;
+	struct ath11k_dump_file_data *file_data;
+	int i;
+
+	rddm_img = mhi_ctrl->rddm_image;
+	if (!rddm_img) {
+		ath11k_err(ab, "No RDDM dump found\n");
+		return 0;
+	}
+
+	fw_img = mhi_ctrl->fbc_image;
+
+	for (i = 0; i < fw_img->entries ; i++) {
+		if (!fw_img->mhi_buf[i].buf)
+			continue;
+
+		paging_tlv_sz += fw_img->mhi_buf[i].len;
+	}
+	dump_seg_sz[FW_CRASH_DUMP_PAGING_DATA] = paging_tlv_sz;
+
+	for (i = 0; i < rddm_img->entries; i++) {
+		if (!rddm_img->mhi_buf[i].buf)
+			continue;
+
+		rddm_tlv_sz += rddm_img->mhi_buf[i].len;
+	}
+	dump_seg_sz[FW_CRASH_DUMP_RDDM_DATA] = rddm_tlv_sz;
+
+	for (i = 0; i < ab->qmi.mem_seg_count; i++) {
+		mem_type = ath11k_coredump_get_dump_type(ab->qmi.target_mem[i].type);
+
+		if (mem_type == FW_CRASH_DUMP_NONE)
+			continue;
+
+		if (mem_type == FW_CRASH_DUMP_TYPE_MAX) {
+			ath11k_dbg(ab, ATH11K_DBG_PCI,
+				   "target mem region type %d not supported",
+				   ab->qmi.target_mem[i].type);
+			continue;
+		}
+
+		if (!ab->qmi.target_mem[i].anyaddr)
+			continue;
+
+		dump_seg_sz[mem_type] += ab->qmi.target_mem[i].size;
+	}
+
+	for (i = 0; i < FW_CRASH_DUMP_TYPE_MAX; i++) {
+		if (!dump_seg_sz[i])
+			continue;
+
+		len += sizeof(*dump_tlv) + dump_seg_sz[i];
+	}
+
+	if (len)
+		len += sizeof(*file_data);
+
+	return len;
+}
+
+static void ath11k_pci_coredump_download(struct ath11k_base *ab)
+{
+	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+	struct mhi_controller *mhi_ctrl = ab_pci->mhi_ctrl;
+	struct image_info *rddm_img, *fw_img;
+	struct timespec64 timestamp;
+	int i, len, mem_idx;
+	enum ath11k_fw_crash_dump_type mem_type;
+	struct ath11k_dump_file_data *file_data;
+	struct ath11k_tlv_dump_data *dump_tlv;
+	size_t hdr_len = sizeof(*file_data);
+	void *buf;
+	u32 dump_seg_sz[FW_CRASH_DUMP_TYPE_MAX] = { 0 };
+
+	ath11k_mhi_coredump(mhi_ctrl, false);
+
+	len = ath11k_pci_coredump_calculate_size(ab, dump_seg_sz);
+	if (!len) {
+		ath11k_warn(ab, "No crash dump data found for devcoredump");
+		return;
+	}
+
+	rddm_img = mhi_ctrl->rddm_image;
+	fw_img = mhi_ctrl->fbc_image;
+
+	/* dev_coredumpv() requires vmalloc data */
+	buf = vzalloc(len);
+	if (!buf)
+		return;
+
+	ab->dump_data = buf;
+	ab->ath11k_coredump_len = len;
+	file_data = ab->dump_data;
+	strscpy(file_data->df_magic, "ATH11K-FW-DUMP", sizeof(file_data->df_magic));
+	file_data->len = cpu_to_le32(len);
+	file_data->version = cpu_to_le32(ATH11K_FW_CRASH_DUMP_V2);
+	file_data->chip_id = cpu_to_le32(ab_pci->dev_id);
+	file_data->qrtr_id = cpu_to_le32(ab_pci->ab->qmi.service_ins_id);
+	file_data->bus_id = cpu_to_le32(pci_domain_nr(ab_pci->pdev->bus));
+	guid_gen(&file_data->guid);
+	ktime_get_real_ts64(&timestamp);
+	file_data->tv_sec = cpu_to_le64(timestamp.tv_sec);
+	file_data->tv_nsec = cpu_to_le64(timestamp.tv_nsec);
+	buf += hdr_len;
+	dump_tlv = buf;
+	dump_tlv->type = cpu_to_le32(FW_CRASH_DUMP_PAGING_DATA);
+	dump_tlv->tlv_len = cpu_to_le32(dump_seg_sz[FW_CRASH_DUMP_PAGING_DATA]);
+	buf += COREDUMP_TLV_HDR_SIZE;
+
+	/* append all segments together as they are all part of a single contiguous
+	 * block of memory
+	 */
+	for (i = 0; i < fw_img->entries ; i++) {
+		if (!fw_img->mhi_buf[i].buf)
+			continue;
+
+		memcpy_fromio(buf, (void const __iomem *)fw_img->mhi_buf[i].buf,
+			      fw_img->mhi_buf[i].len);
+		buf += fw_img->mhi_buf[i].len;
+	}
+
+	dump_tlv = buf;
+	dump_tlv->type = cpu_to_le32(FW_CRASH_DUMP_RDDM_DATA);
+	dump_tlv->tlv_len = cpu_to_le32(dump_seg_sz[FW_CRASH_DUMP_RDDM_DATA]);
+	buf += COREDUMP_TLV_HDR_SIZE;
+
+	/* append all segments together as they are all part of a single contiguous
+	 * block of memory
+	 */
+	for (i = 0; i < rddm_img->entries; i++) {
+		if (!rddm_img->mhi_buf[i].buf)
+			continue;
+
+		memcpy_fromio(buf, (void const __iomem *)rddm_img->mhi_buf[i].buf,
+			      rddm_img->mhi_buf[i].len);
+		buf += rddm_img->mhi_buf[i].len;
+	}
+
+	mem_idx = FW_CRASH_DUMP_REMOTE_MEM_DATA;
+	for (; mem_idx < FW_CRASH_DUMP_TYPE_MAX; mem_idx++) {
+		if (mem_idx == FW_CRASH_DUMP_NONE)
+			continue;
+
+		for (i = 0; i < ab->qmi.mem_seg_count; i++) {
+			mem_type = ath11k_coredump_get_dump_type
+						(ab->qmi.target_mem[i].type);
+
+			if (mem_type != mem_idx)
+				continue;
+
+			if (!ab->qmi.target_mem[i].anyaddr) {
+				ath11k_dbg(ab, ATH11K_DBG_PCI,
+					   "Skipping mem region type %d",
+					   ab->qmi.target_mem[i].type);
+				continue;
+			}
+
+			dump_tlv = buf;
+			dump_tlv->type = cpu_to_le32(mem_idx);
+			dump_tlv->tlv_len = cpu_to_le32(dump_seg_sz[mem_idx]);
+			buf += COREDUMP_TLV_HDR_SIZE;
+
+			memcpy_fromio(buf, ab->qmi.target_mem[i].iaddr,
+				      ab->qmi.target_mem[i].size);
+
+			buf += ab->qmi.target_mem[i].size;
+		}
+	}
+
+	queue_work(ab->workqueue, &ab->dump_work);
+}
+#endif
+
 static int ath11k_pci_power_up(struct ath11k_base *ab)
 {
 	struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
@@ -713,6 +896,9 @@ static const struct ath11k_hif_ops ath11k_pci_hif_ops = {
 	.ce_irq_enable = ath11k_pci_hif_ce_irq_enable,
 	.ce_irq_disable = ath11k_pci_hif_ce_irq_disable,
 	.get_ce_msi_idx = ath11k_pcic_get_ce_msi_idx,
+#ifdef CONFIG_DEV_COREDUMP
+	.coredump_download = ath11k_pci_coredump_download,
+#endif
 };
 
 static void ath11k_pci_read_hw_version(struct ath11k_base *ab, u32 *major, u32 *minor)
@@ -981,6 +1167,8 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
 
 	set_bit(ATH11K_FLAG_UNREGISTERING, &ab->dev_flags);
 
+	cancel_work_sync(&ab->reset_work);
+	cancel_work_sync(&ab->dump_work);
 	ath11k_core_deinit(ab);
 
 qmi_fail:
diff --git a/drivers/net/wireless/ath/ath11k/qmi.h b/drivers/net/wireless/ath/ath11k/qmi.h
index fdf9b5f8c19f1..7968ab122b65d 100644
--- a/drivers/net/wireless/ath/ath11k/qmi.h
+++ b/drivers/net/wireless/ath/ath11k/qmi.h
@@ -157,6 +157,7 @@ struct ath11k_qmi {
 #define BDF_MEM_REGION_TYPE				0x2
 #define M3_DUMP_REGION_TYPE				0x3
 #define CALDB_MEM_REGION_TYPE				0x4
+#define PAGEABLE_MEM_REGION_TYPE			0x9
 
 struct qmi_wlanfw_host_cap_req_msg_v01 {
 	u8 num_clients_valid;

From ceb3b35f5ef4a0c490f54eb8b53075fd83a97d11 Mon Sep 17 00:00:00 2001
From: Ethan Carter Edwards <ethan@ethancedwards.com>
Date: Mon, 10 Feb 2025 21:49:41 -0500
Subject: [PATCH 0710/2753] wifi: ath12k: cleanup ath12k_mac_mlo_ready()

There is a possibility for an uninitialized *ret* variable to be
returned in some code paths.

This explicitly returns 0 without an error. Also removes goto that
returned *ret* and simply returns in place.

Closes: https://scan5.scan.coverity.com/#/project-view/63541/10063?selectedIssue=1642337
Fixes: b716a10d99a2 ("wifi: ath12k: enable MLO setup and teardown from core")
Signed-off-by: Ethan Carter Edwards <ethan@ethancedwards.com>
Reviewed-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210-ath12k-uninit-v2-1-3596f28dd380@ethancedwards.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/core.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
index 0c556023141b0..0b2dec081c6ee 100644
--- a/drivers/net/wireless/ath/ath12k/core.c
+++ b/drivers/net/wireless/ath/ath12k/core.c
@@ -961,12 +961,11 @@ int ath12k_mac_mlo_ready(struct ath12k_hw_group *ag)
 			ar = &ah->radio[j];
 			ret = __ath12k_mac_mlo_ready(ar);
 			if (ret)
-				goto out;
+				return ret;
 		}
 	}
 
-out:
-	return ret;
+	return 0;
 }
 
 static int ath12k_core_mlo_setup(struct ath12k_hw_group *ag)

From 293f324ce96d700112c726682b14094d1b54e09c Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 13 Feb 2025 13:06:21 -0800
Subject: [PATCH 0711/2753] tools: Unify top-level quiet infrastructure

Commit f2868b1a66d4f40f ("perf tools: Expose quiet/verbose variables in
Makefile.perf") moved the quiet infrastructure out of
tools/build/Makefile.build and into the top-level Makefile.perf file so
that the quiet infrastructure could be used throughout perf and not just
in Makefile.build.

Extract out the quiet infrastructure into Makefile.include so that it
can be leveraged outside of perf.

Fixes: f2868b1a66d4f40f ("perf tools: Expose quiet/verbose variables in Makefile.perf")
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Lukasz Luba <lukasz.luba@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Mykola Lysenko <mykolal@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Quentin Monnet <qmo@kernel.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20250213-quiet_tools-v3-1-07de4482a581@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/build/Makefile           |  8 +------
 tools/perf/Makefile.perf       | 41 ----------------------------------
 tools/scripts/Makefile.include | 30 +++++++++++++++++++++++++
 3 files changed, 31 insertions(+), 48 deletions(-)

diff --git a/tools/build/Makefile b/tools/build/Makefile
index 18ad131f6ea74..63ef218787616 100644
--- a/tools/build/Makefile
+++ b/tools/build/Makefile
@@ -17,13 +17,7 @@ $(call allow-override,LD,$(CROSS_COMPILE)ld)
 
 export HOSTCC HOSTLD HOSTAR
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
-export Q srctree CC LD
+export srctree CC LD
 
 MAKEFLAGS := --no-print-directory
 build     := -f $(srctree)/tools/build/Makefile.build dir=. obj
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 55d6ce9ea52fb..05c083bb11220 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -161,47 +161,6 @@ export VPATH
 SOURCE := $(shell ln -sf $(srctree)/tools/perf $(OUTPUT)/source)
 endif
 
-# Beautify output
-# ---------------------------------------------------------------------------
-#
-# Most of build commands in Kbuild start with "cmd_". You can optionally define
-# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from
-# that command is printed by default.
-#
-# e.g.)
-#    quiet_cmd_depmod = DEPMOD  $(MODLIB)
-#          cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE)
-#
-# A simple variant is to prefix commands with $(Q) - that's useful
-# for commands that shall be hidden in non-verbose mode.
-#
-#    $(Q)$(MAKE) $(build)=scripts/basic
-#
-# To put more focus on warnings, be less verbose as default
-# Use 'make V=1' to see the full commands
-
-ifeq ($(V),1)
-  quiet =
-  Q =
-else
-  quiet=quiet_
-  Q=@
-endif
-
-# If the user is running make -s (silent mode), suppress echoing of commands
-# make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
-ifeq ($(filter 3.%,$(MAKE_VERSION)),)
-short-opts := $(firstword -$(MAKEFLAGS))
-else
-short-opts := $(filter-out --%,$(MAKEFLAGS))
-endif
-
-ifneq ($(findstring s,$(short-opts)),)
-  quiet=silent_
-endif
-
-export quiet Q
-
 # Do not use make's built-in rules
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index 0aa4005017c72..45f4abef70640 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -136,6 +136,33 @@ else
 NO_SUBDIR = :
 endif
 
+# Beautify output
+# ---------------------------------------------------------------------------
+#
+# Most of build commands in Kbuild start with "cmd_". You can optionally define
+# "quiet_cmd_*". If defined, the short log is printed. Otherwise, no log from
+# that command is printed by default.
+#
+# e.g.)
+#    quiet_cmd_depmod = DEPMOD  $(MODLIB)
+#          cmd_depmod = $(srctree)/scripts/depmod.sh $(DEPMOD) $(KERNELRELEASE)
+#
+# A simple variant is to prefix commands with $(Q) - that's useful
+# for commands that shall be hidden in non-verbose mode.
+#
+#    $(Q)$(MAKE) $(build)=scripts/basic
+#
+# To put more focus on warnings, be less verbose as default
+# Use 'make V=1' to see the full commands
+
+ifeq ($(V),1)
+  quiet =
+  Q =
+else
+  quiet = quiet_
+  Q = @
+endif
+
 # If the user is running make -s (silent mode), suppress echoing of commands
 # make-4.0 (and later) keep single letter options in the 1st word of MAKEFLAGS.
 ifeq ($(filter 3.%,$(MAKE_VERSION)),)
@@ -146,8 +173,11 @@ endif
 
 ifneq ($(findstring s,$(short-opts)),)
   silent=1
+  quiet=silent_
 endif
 
+export quiet Q
+
 #
 # Define a callable command for descending to a new directory
 #

From d403120cb9d4787b283ea202b2162f459d18fe9d Mon Sep 17 00:00:00 2001
From: Kurt Borja <kuurtb@gmail.com>
Date: Wed, 12 Feb 2025 14:30:58 -0500
Subject: [PATCH 0712/2753] ACPI: platform_profile: Fix memory leak in
 profile_class_is_visible()

If class_find_device() finds a device, it's reference count is
incremented.

Call put_device() to drop this reference before returning.

Fixes: 77be5cacb2c2 ("ACPI: platform_profile: Create class for ACPI platform profile")
Signed-off-by: Kurt Borja <kuurtb@gmail.com>
Reviewed-by: Mark Pearson <mpearson-lenovo@squebb.ca>
Link: https://patch.msgid.link/20250212193058.32110-1-kuurtb@gmail.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/platform_profile.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index fc92e43d0fe93..2ad53cc6aae53 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -417,8 +417,14 @@ static int profile_class_registered(struct device *dev, const void *data)
 
 static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx)
 {
-	if (!class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered))
+	struct device *dev;
+
+	dev = class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered);
+	if (!dev)
 		return 0;
+
+	put_device(dev);
+
 	return attr->mode;
 }
 

From 643f209ba3fdd4099416aaf9efa8266f7366d6fb Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Thu, 23 Jan 2025 12:22:04 -0800
Subject: [PATCH 0713/2753] drm/xe: Make GUC binaries dump consistent with
 other binaries in devcoredump
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All other(hwsp, hwctx and vmas) binaries follow this format:
[name].length: 0x1000
[name].data: xxxxxxx
[name].error: errno

The error one is just in case by some reason it was not able to
capture the binary.

So this GuC binaries should follow the same patern.

v2:
- renamed GUC binary to LOG

Cc: John Harrison <John.C.Harrison@Intel.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250123202307.95103-3-jose.souza@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit cb1f868ca13756c0c18ba54d1591332476760d07)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c  | 6 ++++--
 drivers/gpu/drm/xe/xe_guc_log.c | 3 ++-
 2 files changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 50c8076b51585..497036675a38c 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1723,9 +1723,11 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 		drm_printf(p, "\tg2h outstanding: %d\n",
 			   snapshot->g2h_outstanding);
 
-		if (snapshot->ctb)
-			xe_print_blob_ascii85(p, "CTB data", '\n',
+		if (snapshot->ctb) {
+			drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
+			xe_print_blob_ascii85(p, "[CTB].data", '\n',
 					      snapshot->ctb, 0, snapshot->ctb_size);
+		}
 	} else {
 		drm_puts(p, "CT disabled\n");
 	}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 2baa4d95571fb..2457572ed86ad 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -208,10 +208,11 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	drm_printf(p, "GuC timestamp: 0x%08llX [%llu]\n", snapshot->stamp, snapshot->stamp);
 	drm_printf(p, "Log level: %u\n", snapshot->level);
 
+	drm_printf(p, "[LOG].length: 0x%lx\n", snapshot->size);
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);
-		const char *prefix = i ? NULL : "Log data";
+		const char *prefix = i ? NULL : "[LOG].data";
 		char suffix = i == snapshot->num_chunks - 1 ? '\n' : 0;
 
 		xe_print_blob_ascii85(p, prefix, suffix, snapshot->copy[i], 0, size);

From 42367eca7604e16e170bd6bd94ef61ffdd335f4a Mon Sep 17 00:00:00 2001
From: Charlie Jenkins <charlie@rivosinc.com>
Date: Thu, 13 Feb 2025 13:06:22 -0800
Subject: [PATCH 0714/2753] tools: Remove redundant quiet setup

Q is exported from Makefile.include so it is not necessary to manually
set it.

Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Charlie Jenkins <charlie@rivosinc.com>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Quentin Monnet <qmo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Benjamin Tissoires <bentiss@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Hao Luo <haoluo@google.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: KP Singh <kpsingh@kernel.org>
Cc: Lukasz Luba <lukasz.luba@arm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Mykola Lysenko <mykolal@fb.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J. Wysocki <rafael@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Song Liu <song@kernel.org>
Cc: Stanislav Fomichev <sdf@google.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Yonghong Song <yonghong.song@linux.dev>
Cc: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20250213-quiet_tools-v3-2-07de4482a581@rivosinc.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/arch/arm64/tools/Makefile           |  6 ------
 tools/bpf/Makefile                        |  6 ------
 tools/bpf/bpftool/Documentation/Makefile  |  6 ------
 tools/bpf/bpftool/Makefile                |  6 ------
 tools/bpf/resolve_btfids/Makefile         |  2 --
 tools/bpf/runqslower/Makefile             |  5 +----
 tools/lib/bpf/Makefile                    | 13 -------------
 tools/lib/perf/Makefile                   | 13 -------------
 tools/lib/thermal/Makefile                | 13 -------------
 tools/objtool/Makefile                    |  6 ------
 tools/testing/selftests/bpf/Makefile.docs |  6 ------
 tools/testing/selftests/hid/Makefile      |  2 --
 tools/thermal/lib/Makefile                | 13 -------------
 tools/tracing/latency/Makefile            |  6 ------
 tools/tracing/rtla/Makefile               |  6 ------
 tools/verification/rv/Makefile            |  6 ------
 16 files changed, 1 insertion(+), 114 deletions(-)

diff --git a/tools/arch/arm64/tools/Makefile b/tools/arch/arm64/tools/Makefile
index 7b42feedf6471..de4f1b66ef014 100644
--- a/tools/arch/arm64/tools/Makefile
+++ b/tools/arch/arm64/tools/Makefile
@@ -13,12 +13,6 @@ AWK	?= awk
 MKDIR	?= mkdir
 RM	?= rm
 
-ifeq ($(V),1)
-Q =
-else
-Q = @
-endif
-
 arm64_tools_dir = $(top_srcdir)/arch/arm64/tools
 arm64_sysreg_tbl = $(arm64_tools_dir)/sysreg
 arm64_gen_sysreg = $(arm64_tools_dir)/gen-sysreg.awk
diff --git a/tools/bpf/Makefile b/tools/bpf/Makefile
index 243b79f2b451e..062bbd6cd048e 100644
--- a/tools/bpf/Makefile
+++ b/tools/bpf/Makefile
@@ -27,12 +27,6 @@ srctree := $(patsubst %/,%,$(dir $(CURDIR)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 FEATURE_USER = .bpf
 FEATURE_TESTS = libbfd disassembler-four-args disassembler-init-styled
 FEATURE_DISPLAY = libbfd
diff --git a/tools/bpf/bpftool/Documentation/Makefile b/tools/bpf/bpftool/Documentation/Makefile
index 4315652678b9f..bf843f328812e 100644
--- a/tools/bpf/bpftool/Documentation/Makefile
+++ b/tools/bpf/bpftool/Documentation/Makefile
@@ -5,12 +5,6 @@ INSTALL ?= install
 RM ?= rm -f
 RMDIR ?= rmdir --ignore-fail-on-non-empty
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man8dir = $(mandir)/man8
diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile
index dd9f3ec842017..6ea4823b770cb 100644
--- a/tools/bpf/bpftool/Makefile
+++ b/tools/bpf/bpftool/Makefile
@@ -7,12 +7,6 @@ srctree := $(patsubst %/,%,$(dir $(srctree)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))
 endif
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 BPF_DIR = $(srctree)/tools/lib/bpf
 
 ifneq ($(OUTPUT),)
diff --git a/tools/bpf/resolve_btfids/Makefile b/tools/bpf/resolve_btfids/Makefile
index 4b8079f294f65..afbddea3a39c6 100644
--- a/tools/bpf/resolve_btfids/Makefile
+++ b/tools/bpf/resolve_btfids/Makefile
@@ -5,10 +5,8 @@ include ../../scripts/Makefile.arch
 srctree := $(abspath $(CURDIR)/../../../)
 
 ifeq ($(V),1)
-  Q =
   msg =
 else
-  Q = @
   ifeq ($(silent),1)
     msg =
   else
diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
index c4f1f1735af65..e49203ebd48c1 100644
--- a/tools/bpf/runqslower/Makefile
+++ b/tools/bpf/runqslower/Makefile
@@ -26,10 +26,7 @@ VMLINUX_BTF_PATHS := $(if $(O),$(O)/vmlinux)		\
 VMLINUX_BTF_PATH := $(or $(VMLINUX_BTF),$(firstword			       \
 					  $(wildcard $(VMLINUX_BTF_PATHS))))
 
-ifeq ($(V),1)
-Q =
-else
-Q = @
+ifneq ($(V),1)
 MAKEFLAGS += --no-print-directory
 submake_extras := feature_display=0
 endif
diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile
index 857a5f7b413d6..168140f8e6461 100644
--- a/tools/lib/bpf/Makefile
+++ b/tools/lib/bpf/Makefile
@@ -53,13 +53,6 @@ include $(srctree)/tools/scripts/Makefile.include
 
 # copy a bit from Linux kbuild
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
 INCLUDES = -I$(or $(OUTPUT),.) \
 	   -I$(srctree)/tools/include -I$(srctree)/tools/include/uapi \
 	   -I$(srctree)/tools/arch/$(SRCARCH)/include
@@ -96,12 +89,6 @@ override CFLAGS += $(CLANG_CROSS_FLAGS)
 # flags specific for shared library
 SHLIB_FLAGS := -DSHARED -fPIC
 
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Disable command line variables (CFLAGS) override from top
 # level Makefile (perf), otherwise build Makefile will get
 # the same command line setup.
diff --git a/tools/lib/perf/Makefile b/tools/lib/perf/Makefile
index 3a9b2140aa048..e9a7ac2c062e2 100644
--- a/tools/lib/perf/Makefile
+++ b/tools/lib/perf/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 TEST_ARGS := $(if $(V),-v)
 
 # Set compile option CFLAGS
diff --git a/tools/lib/thermal/Makefile b/tools/lib/thermal/Makefile
index 8890fd57b110c..a1f5e388644d3 100644
--- a/tools/lib/thermal/Makefile
+++ b/tools/lib/thermal/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index f56e277275341..7a65948892e56 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -46,12 +46,6 @@ HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)"
 AWK = awk
 MKDIR = mkdir
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 BUILD_ORC := n
 
 ifeq ($(SRCARCH),x86)
diff --git a/tools/testing/selftests/bpf/Makefile.docs b/tools/testing/selftests/bpf/Makefile.docs
index eb6a4fea8c794..f7f9e7088bb38 100644
--- a/tools/testing/selftests/bpf/Makefile.docs
+++ b/tools/testing/selftests/bpf/Makefile.docs
@@ -7,12 +7,6 @@ INSTALL ?= install
 RM ?= rm -f
 RMDIR ?= rmdir --ignore-fail-on-non-empty
 
-ifeq ($(V),1)
-  Q =
-else
-  Q = @
-endif
-
 prefix ?= /usr/local
 mandir ?= $(prefix)/man
 man2dir = $(mandir)/man2
diff --git a/tools/testing/selftests/hid/Makefile b/tools/testing/selftests/hid/Makefile
index 0336353bd15f0..2839d2612ce3a 100644
--- a/tools/testing/selftests/hid/Makefile
+++ b/tools/testing/selftests/hid/Makefile
@@ -43,10 +43,8 @@ TEST_GEN_PROGS = hid_bpf hidraw
 # $3 - target (assumed to be file); only file name will be emitted;
 # $4 - optional extra arg, emitted as-is, if provided.
 ifeq ($(V),1)
-Q =
 msg =
 else
-Q = @
 msg = @printf '  %-8s%s %s%s\n' "$(1)" "$(if $(2), [$(2)])" "$(notdir $(3))" "$(if $(4), $(4))";
 MAKEFLAGS += --no-print-directory
 submake_extras := feature_display=0
diff --git a/tools/thermal/lib/Makefile b/tools/thermal/lib/Makefile
index f2552f73a64c7..056d212f25cf5 100644
--- a/tools/thermal/lib/Makefile
+++ b/tools/thermal/lib/Makefile
@@ -39,19 +39,6 @@ libdir = $(prefix)/$(libdir_relative)
 libdir_SQ = $(subst ','\'',$(libdir))
 libdir_relative_SQ = $(subst ','\'',$(libdir_relative))
 
-ifeq ("$(origin V)", "command line")
-  VERBOSE = $(V)
-endif
-ifndef VERBOSE
-  VERBOSE = 0
-endif
-
-ifeq ($(VERBOSE),1)
-  Q =
-else
-  Q = @
-endif
-
 # Set compile option CFLAGS
 ifdef EXTRA_CFLAGS
   CFLAGS := $(EXTRA_CFLAGS)
diff --git a/tools/tracing/latency/Makefile b/tools/tracing/latency/Makefile
index 6518b03e05c71..257a56b1899f2 100644
--- a/tools/tracing/latency/Makefile
+++ b/tools/tracing/latency/Makefile
@@ -37,12 +37,6 @@ FEATURE_TESTS	+= libtracefs
 FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 
-ifeq ($(V),1)
-  Q 		=
-else
-  Q 		= @
-endif
-
 all: $(LATENCY-COLLECTOR)
 
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/tracing/rtla/Makefile b/tools/tracing/rtla/Makefile
index a6a7dee16622d..a1727c414e44b 100644
--- a/tools/tracing/rtla/Makefile
+++ b/tools/tracing/rtla/Makefile
@@ -37,12 +37,6 @@ FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 FEATURE_DISPLAY	+= libcpupower
 
-ifeq ($(V),1)
-  Q		=
-else
-  Q		= @
-endif
-
 all: $(RTLA)
 
 include $(srctree)/tools/build/Makefile.include
diff --git a/tools/verification/rv/Makefile b/tools/verification/rv/Makefile
index 411d62b3d8eb9..5b898360ba481 100644
--- a/tools/verification/rv/Makefile
+++ b/tools/verification/rv/Makefile
@@ -35,12 +35,6 @@ FEATURE_TESTS	+= libtracefs
 FEATURE_DISPLAY	:= libtraceevent
 FEATURE_DISPLAY	+= libtracefs
 
-ifeq ($(V),1)
-  Q		=
-else
-  Q		= @
-endif
-
 all: $(RV)
 
 include $(srctree)/tools/build/Makefile.include

From a3f172359e22b2c11b750d23560481a55bf86af1 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Tue, 18 Feb 2025 18:35:35 +1000
Subject: [PATCH 0715/2753] ASoC: tas2764: Fix power control mask

Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: James Calligeros <jcalligeros99@gmail.com>
Link: https://patch.msgid.link/20250218-apple-codec-changes-v2-1-932760fd7e07@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2764.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h
index 168af772a898f..d13ecae9c9c2f 100644
--- a/sound/soc/codecs/tas2764.h
+++ b/sound/soc/codecs/tas2764.h
@@ -25,7 +25,7 @@
 
 /* Power Control */
 #define TAS2764_PWR_CTRL		TAS2764_REG(0X0, 0x02)
-#define TAS2764_PWR_CTRL_MASK		GENMASK(1, 0)
+#define TAS2764_PWR_CTRL_MASK		GENMASK(2, 0)
 #define TAS2764_PWR_CTRL_ACTIVE		0x0
 #define TAS2764_PWR_CTRL_MUTE		BIT(0)
 #define TAS2764_PWR_CTRL_SHUTDOWN	BIT(1)

From f5468beeab1b1adfc63c2717b1f29ef3f49a5fab Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Tue, 18 Feb 2025 18:36:02 +1000
Subject: [PATCH 0716/2753] ASoC: tas2764: Set the SDOUT polarity correctly

TX launch polarity needs to be the opposite of RX capture polarity, to
generate the right bit slot alignment.

Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: James Calligeros <jcalligeros99@gmail.com>
Link: https://patch.msgid.link/20250218-apple-codec-changes-v2-28-932760fd7e07@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/tas2764.c | 10 +++++++++-
 sound/soc/codecs/tas2764.h |  6 ++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/tas2764.c b/sound/soc/codecs/tas2764.c
index d482cd194c08c..58315eab492a1 100644
--- a/sound/soc/codecs/tas2764.c
+++ b/sound/soc/codecs/tas2764.c
@@ -365,7 +365,7 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 {
 	struct snd_soc_component *component = dai->component;
 	struct tas2764_priv *tas2764 = snd_soc_component_get_drvdata(component);
-	u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0;
+	u8 tdm_rx_start_slot = 0, asi_cfg_0 = 0, asi_cfg_1 = 0, asi_cfg_4 = 0;
 	int ret;
 
 	switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
@@ -374,12 +374,14 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 		fallthrough;
 	case SND_SOC_DAIFMT_NB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_RISING;
+		asi_cfg_4 = TAS2764_TDM_CFG4_TX_FALLING;
 		break;
 	case SND_SOC_DAIFMT_IB_IF:
 		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
 		fallthrough;
 	case SND_SOC_DAIFMT_IB_NF:
 		asi_cfg_1 = TAS2764_TDM_CFG1_RX_FALLING;
+		asi_cfg_4 = TAS2764_TDM_CFG4_TX_RISING;
 		break;
 	}
 
@@ -389,6 +391,12 @@ static int tas2764_set_fmt(struct snd_soc_dai *dai, unsigned int fmt)
 	if (ret < 0)
 		return ret;
 
+	ret = snd_soc_component_update_bits(component, TAS2764_TDM_CFG4,
+					    TAS2764_TDM_CFG4_TX_MASK,
+					    asi_cfg_4);
+	if (ret < 0)
+		return ret;
+
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_I2S:
 		asi_cfg_0 ^= TAS2764_TDM_CFG0_FRAME_START;
diff --git a/sound/soc/codecs/tas2764.h b/sound/soc/codecs/tas2764.h
index d13ecae9c9c2f..9490f2686e389 100644
--- a/sound/soc/codecs/tas2764.h
+++ b/sound/soc/codecs/tas2764.h
@@ -79,6 +79,12 @@
 #define TAS2764_TDM_CFG3_RXS_SHIFT	0x4
 #define TAS2764_TDM_CFG3_MASK		GENMASK(3, 0)
 
+/* TDM Configuration Reg4 */
+#define TAS2764_TDM_CFG4		TAS2764_REG(0X0, 0x0d)
+#define TAS2764_TDM_CFG4_TX_MASK	BIT(0)
+#define TAS2764_TDM_CFG4_TX_RISING	0x0
+#define TAS2764_TDM_CFG4_TX_FALLING	BIT(0)
+
 /* TDM Configuration Reg5 */
 #define TAS2764_TDM_CFG5		TAS2764_REG(0X0, 0x0e)
 #define TAS2764_TDM_CFG5_VSNS_MASK	BIT(6)

From 0c28e4d1e10d2aae608094620bb386e6fd73d55e Mon Sep 17 00:00:00 2001
From: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Date: Thu, 13 Feb 2025 13:38:49 +0000
Subject: [PATCH 0717/2753] HID: corsair-void: Update power supply values with
 a unified work handler

corsair_void_process_receiver can be called from an interrupt context,
locking battery_mutex in it was causing a kernel panic.
Fix it by moving the critical section into its own work, sharing this
work with battery_add_work and battery_remove_work to remove the need
for any locking

Closes: https://bugzilla.suse.com/show_bug.cgi?id=1236843
Fixes: 6ea2a6fd3872 ("HID: corsair-void: Add Corsair Void headset family driver")
Cc: stable@vger.kernel.org
Signed-off-by: Stuart Hayhurst <stuart.a.hayhurst@gmail.com>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-corsair-void.c | 83 ++++++++++++++++++----------------
 1 file changed, 43 insertions(+), 40 deletions(-)

diff --git a/drivers/hid/hid-corsair-void.c b/drivers/hid/hid-corsair-void.c
index 56e858066c3c3..afbd67aa97192 100644
--- a/drivers/hid/hid-corsair-void.c
+++ b/drivers/hid/hid-corsair-void.c
@@ -71,11 +71,9 @@
 
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
-#include <linux/cleanup.h>
 #include <linux/device.h>
 #include <linux/hid.h>
 #include <linux/module.h>
-#include <linux/mutex.h>
 #include <linux/power_supply.h>
 #include <linux/usb.h>
 #include <linux/workqueue.h>
@@ -120,6 +118,12 @@ enum {
 	CORSAIR_VOID_BATTERY_CHARGING	= 5,
 };
 
+enum {
+	CORSAIR_VOID_ADD_BATTERY	= 0,
+	CORSAIR_VOID_REMOVE_BATTERY	= 1,
+	CORSAIR_VOID_UPDATE_BATTERY	= 2,
+};
+
 static enum power_supply_property corsair_void_battery_props[] = {
 	POWER_SUPPLY_PROP_STATUS,
 	POWER_SUPPLY_PROP_PRESENT,
@@ -155,12 +159,12 @@ struct corsair_void_drvdata {
 
 	struct power_supply *battery;
 	struct power_supply_desc battery_desc;
-	struct mutex battery_mutex;
 
 	struct delayed_work delayed_status_work;
 	struct delayed_work delayed_firmware_work;
-	struct work_struct battery_remove_work;
-	struct work_struct battery_add_work;
+
+	unsigned long battery_work_flags;
+	struct work_struct battery_work;
 };
 
 /*
@@ -260,11 +264,9 @@ static void corsair_void_process_receiver(struct corsair_void_drvdata *drvdata,
 
 	/* Inform power supply if battery values changed */
 	if (memcmp(&orig_battery_data, battery_data, sizeof(*battery_data))) {
-		scoped_guard(mutex, &drvdata->battery_mutex) {
-			if (drvdata->battery) {
-				power_supply_changed(drvdata->battery);
-			}
-		}
+		set_bit(CORSAIR_VOID_UPDATE_BATTERY,
+			&drvdata->battery_work_flags);
+		schedule_work(&drvdata->battery_work);
 	}
 }
 
@@ -536,29 +538,11 @@ static void corsair_void_firmware_work_handler(struct work_struct *work)
 
 }
 
-static void corsair_void_battery_remove_work_handler(struct work_struct *work)
-{
-	struct corsair_void_drvdata *drvdata;
-
-	drvdata = container_of(work, struct corsair_void_drvdata,
-			       battery_remove_work);
-	scoped_guard(mutex, &drvdata->battery_mutex) {
-		if (drvdata->battery) {
-			power_supply_unregister(drvdata->battery);
-			drvdata->battery = NULL;
-		}
-	}
-}
-
-static void corsair_void_battery_add_work_handler(struct work_struct *work)
+static void corsair_void_add_battery(struct corsair_void_drvdata *drvdata)
 {
-	struct corsair_void_drvdata *drvdata;
 	struct power_supply_config psy_cfg = {};
 	struct power_supply *new_supply;
 
-	drvdata = container_of(work, struct corsair_void_drvdata,
-			       battery_add_work);
-	guard(mutex)(&drvdata->battery_mutex);
 	if (drvdata->battery)
 		return;
 
@@ -583,16 +567,42 @@ static void corsair_void_battery_add_work_handler(struct work_struct *work)
 	drvdata->battery = new_supply;
 }
 
+static void corsair_void_battery_work_handler(struct work_struct *work)
+{
+	struct corsair_void_drvdata *drvdata = container_of(work,
+		struct corsair_void_drvdata, battery_work);
+
+	bool add_battery = test_and_clear_bit(CORSAIR_VOID_ADD_BATTERY,
+					      &drvdata->battery_work_flags);
+	bool remove_battery = test_and_clear_bit(CORSAIR_VOID_REMOVE_BATTERY,
+						 &drvdata->battery_work_flags);
+	bool update_battery = test_and_clear_bit(CORSAIR_VOID_UPDATE_BATTERY,
+						 &drvdata->battery_work_flags);
+
+	if (add_battery && !remove_battery) {
+		corsair_void_add_battery(drvdata);
+	} else if (remove_battery && !add_battery && drvdata->battery) {
+		power_supply_unregister(drvdata->battery);
+		drvdata->battery = NULL;
+	}
+
+	if (update_battery && drvdata->battery)
+		power_supply_changed(drvdata->battery);
+
+}
+
 static void corsair_void_headset_connected(struct corsair_void_drvdata *drvdata)
 {
-	schedule_work(&drvdata->battery_add_work);
+	set_bit(CORSAIR_VOID_ADD_BATTERY, &drvdata->battery_work_flags);
+	schedule_work(&drvdata->battery_work);
 	schedule_delayed_work(&drvdata->delayed_firmware_work,
 			      msecs_to_jiffies(100));
 }
 
 static void corsair_void_headset_disconnected(struct corsair_void_drvdata *drvdata)
 {
-	schedule_work(&drvdata->battery_remove_work);
+	set_bit(CORSAIR_VOID_REMOVE_BATTERY, &drvdata->battery_work_flags);
+	schedule_work(&drvdata->battery_work);
 
 	corsair_void_set_unknown_wireless_data(drvdata);
 	corsair_void_set_unknown_batt(drvdata);
@@ -678,13 +688,7 @@ static int corsair_void_probe(struct hid_device *hid_dev,
 	drvdata->battery_desc.get_property = corsair_void_battery_get_property;
 
 	drvdata->battery = NULL;
-	INIT_WORK(&drvdata->battery_remove_work,
-		  corsair_void_battery_remove_work_handler);
-	INIT_WORK(&drvdata->battery_add_work,
-		  corsair_void_battery_add_work_handler);
-	ret = devm_mutex_init(drvdata->dev, &drvdata->battery_mutex);
-	if (ret)
-		return ret;
+	INIT_WORK(&drvdata->battery_work, corsair_void_battery_work_handler);
 
 	ret = sysfs_create_group(&hid_dev->dev.kobj, &corsair_void_attr_group);
 	if (ret)
@@ -721,8 +725,7 @@ static void corsair_void_remove(struct hid_device *hid_dev)
 	struct corsair_void_drvdata *drvdata = hid_get_drvdata(hid_dev);
 
 	hid_hw_stop(hid_dev);
-	cancel_work_sync(&drvdata->battery_remove_work);
-	cancel_work_sync(&drvdata->battery_add_work);
+	cancel_work_sync(&drvdata->battery_work);
 	if (drvdata->battery)
 		power_supply_unregister(drvdata->battery);
 

From 213e24250feed3bcf58d7594298df2d7e78a88ab Mon Sep 17 00:00:00 2001
From: Lucas De Marchi <lucas.demarchi@intel.com>
Date: Tue, 28 Jan 2025 07:42:42 -0800
Subject: [PATCH 0718/2753] drm/xe/guc: Fix size_t print format
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use %zx format to print size_t to remove the following warning when
building for i386:

>> drivers/gpu/drm/xe/xe_guc_ct.c:1727:43: warning: format specifies type 'unsigned long' but the argument has type 'size_t' (aka 'unsigned int') [-Wformat]
    1727 |                         drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
         |                                                        ~~~     ^~~~~~~~~~~~~~~~~~
         |                                                        %zx

Cc: José Roberto de Souza <jose.souza@intel.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501281627.H6nj184e-lkp@intel.com/
Fixes: 643f209ba3fd ("drm/xe: Make GUC binaries dump consistent with other binaries in devcoredump")
Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250128154242.3371687-1-lucas.demarchi@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 7748289df510638ba61fed86b59ce7d2fb4a194c)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_ct.c  | 2 +-
 drivers/gpu/drm/xe/xe_guc_log.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
index 497036675a38c..72ad576fc18eb 100644
--- a/drivers/gpu/drm/xe/xe_guc_ct.c
+++ b/drivers/gpu/drm/xe/xe_guc_ct.c
@@ -1724,7 +1724,7 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
 			   snapshot->g2h_outstanding);
 
 		if (snapshot->ctb) {
-			drm_printf(p, "[CTB].length: 0x%lx\n", snapshot->ctb_size);
+			drm_printf(p, "[CTB].length: 0x%zx\n", snapshot->ctb_size);
 			xe_print_blob_ascii85(p, "[CTB].data", '\n',
 					      snapshot->ctb, 0, snapshot->ctb_size);
 		}
diff --git a/drivers/gpu/drm/xe/xe_guc_log.c b/drivers/gpu/drm/xe/xe_guc_log.c
index 2457572ed86ad..0ca3056d8bd3f 100644
--- a/drivers/gpu/drm/xe/xe_guc_log.c
+++ b/drivers/gpu/drm/xe/xe_guc_log.c
@@ -208,7 +208,7 @@ void xe_guc_log_snapshot_print(struct xe_guc_log_snapshot *snapshot, struct drm_
 	drm_printf(p, "GuC timestamp: 0x%08llX [%llu]\n", snapshot->stamp, snapshot->stamp);
 	drm_printf(p, "Log level: %u\n", snapshot->level);
 
-	drm_printf(p, "[LOG].length: 0x%lx\n", snapshot->size);
+	drm_printf(p, "[LOG].length: 0x%zx\n", snapshot->size);
 	remain = snapshot->size;
 	for (i = 0; i < snapshot->num_chunks; i++) {
 		size_t size = min(GUC_LOG_CHUNK_SIZE, remain);

From 8533b14b3d65ee666ba31254787c1bdaee56d95a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 12 Feb 2025 17:06:32 -0800
Subject: [PATCH 0719/2753] eth: mlx4: create a page pool for Rx

Create a pool per rx queue. Subsequent patches will make use of it.

Move fcs_del to a hole to make space for the pointer.

Per common "wisdom" base the page pool size on the ring size.
Note that the page pool cache size is in full pages, so just
round up the effective buffer size to pages.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250213010635.1354034-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 24 +++++++++++++++++++-
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  3 ++-
 2 files changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 15c57e9517e9a..a8c0cf5d0d083 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -48,6 +48,7 @@
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/ip6_checksum.h>
 #endif
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
@@ -268,6 +269,7 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 			   u32 size, u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
+	struct page_pool_params pp = {};
 	struct mlx4_en_rx_ring *ring;
 	int err = -ENOMEM;
 	int tmp;
@@ -286,9 +288,26 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->log_stride = ffs(ring->stride) - 1;
 	ring->buf_size = ring->size * ring->stride + TXBB_SIZE;
 
-	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+	pp.flags = PP_FLAG_DMA_MAP;
+	pp.pool_size = size * DIV_ROUND_UP(priv->rx_skb_size, PAGE_SIZE);
+	pp.nid = node;
+	pp.napi = &priv->rx_cq[queue_index]->napi;
+	pp.netdev = priv->dev;
+	pp.dev = &mdev->dev->persist->pdev->dev;
+	pp.dma_dir = priv->dma_dir;
+
+	ring->pp = page_pool_create(&pp);
+	if (!ring->pp)
 		goto err_ring;
 
+	if (xdp_rxq_info_reg(&ring->xdp_rxq, priv->dev, queue_index, 0) < 0)
+		goto err_pp;
+
+	err = xdp_rxq_info_reg_mem_model(&ring->xdp_rxq, MEM_TYPE_PAGE_POOL,
+					 ring->pp);
+	if (err)
+		goto err_xdp_info;
+
 	tmp = size * roundup_pow_of_two(MLX4_EN_MAX_RX_FRAGS *
 					sizeof(struct mlx4_en_rx_alloc));
 	ring->rx_info = kvzalloc_node(tmp, GFP_KERNEL, node);
@@ -319,6 +338,8 @@ int mlx4_en_create_rx_ring(struct mlx4_en_priv *priv,
 	ring->rx_info = NULL;
 err_xdp_info:
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
+err_pp:
+	page_pool_destroy(ring->pp);
 err_ring:
 	kfree(ring);
 	*pring = NULL;
@@ -445,6 +466,7 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 	xdp_rxq_info_unreg(&ring->xdp_rxq);
 	mlx4_free_hwq_res(mdev->dev, &ring->wqres, size * stride + TXBB_SIZE);
 	kvfree(ring->rx_info);
+	page_pool_destroy(ring->pp);
 	ring->rx_info = NULL;
 	kfree(ring);
 	*pring = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 28b70dcc652e6..29f48e63081b6 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -335,10 +335,11 @@ struct mlx4_en_rx_ring {
 	u16 stride;
 	u16 log_stride;
 	u16 cqn;	/* index of port CQ associated with this ring */
+	u8  fcs_del;
 	u32 prod;
 	u32 cons;
 	u32 buf_size;
-	u8  fcs_del;
+	struct page_pool *pp;
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;

From 8fdeafd66edaf420ea0063a1f13442fe3470fe70 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 12 Feb 2025 17:06:33 -0800
Subject: [PATCH 0720/2753] eth: mlx4: don't try to complete XDP frames in
 netpoll

mlx4 doesn't support ndo_xdp_xmit / XDP_REDIRECT and wasn't
using page pool until now, so it could run XDP completions
in netpoll (NAPI budget == 0) just fine. Page pool has calling
context requirements, make sure we don't try to call it from
what is potentially HW IRQ context.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250213010635.1354034-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_tx.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 1ddb11cb25f91..6e077d202827a 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -450,6 +450,8 @@ int mlx4_en_process_tx_cq(struct net_device *dev,
 
 	if (unlikely(!priv->port_up))
 		return 0;
+	if (unlikely(!napi_budget) && cq->type == TX_XDP)
+		return 0;
 
 	netdev_txq_bql_complete_prefetchw(ring->tx_queue);
 

From d17fb2c0555a429507419a9e23b84188021a801a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 12 Feb 2025 17:06:34 -0800
Subject: [PATCH 0721/2753] eth: mlx4: remove the local XDP fast-recycling ring

It will be replaced with page pool's built-in recycling.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250213010635.1354034-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 40 --------------------
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   | 13 ++-----
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 11 ------
 3 files changed, 3 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index a8c0cf5d0d083..d2cfbf2e38d96 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -142,18 +142,6 @@ static int mlx4_en_prepare_rx_desc(struct mlx4_en_priv *priv,
 		(index << ring->log_stride);
 	struct mlx4_en_rx_alloc *frags = ring->rx_info +
 					(index << priv->log_rx_info);
-	if (likely(ring->page_cache.index > 0)) {
-		/* XDP uses a single page per frame */
-		if (!frags->page) {
-			ring->page_cache.index--;
-			frags->page = ring->page_cache.buf[ring->page_cache.index].page;
-			frags->dma  = ring->page_cache.buf[ring->page_cache.index].dma;
-		}
-		frags->page_offset = XDP_PACKET_HEADROOM;
-		rx_desc->data[0].addr = cpu_to_be64(frags->dma +
-						    XDP_PACKET_HEADROOM);
-		return 0;
-	}
 
 	return mlx4_en_alloc_frags(priv, ring, rx_desc, frags, gfp);
 }
@@ -430,26 +418,6 @@ void mlx4_en_recover_from_oom(struct mlx4_en_priv *priv)
 	}
 }
 
-/* When the rx ring is running in page-per-packet mode, a released frame can go
- * directly into a small cache, to avoid unmapping or touching the page
- * allocator. In bpf prog performance scenarios, buffers are either forwarded
- * or dropped, never converted to skbs, so every page can come directly from
- * this cache when it is sized to be a multiple of the napi budget.
- */
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame)
-{
-	struct mlx4_en_page_cache *cache = &ring->page_cache;
-
-	if (cache->index >= MLX4_EN_CACHE_SIZE)
-		return false;
-
-	cache->buf[cache->index].page = frame->page;
-	cache->buf[cache->index].dma = frame->dma;
-	cache->index++;
-	return true;
-}
-
 void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_rx_ring **pring,
 			     u32 size, u16 stride)
@@ -475,14 +443,6 @@ void mlx4_en_destroy_rx_ring(struct mlx4_en_priv *priv,
 void mlx4_en_deactivate_rx_ring(struct mlx4_en_priv *priv,
 				struct mlx4_en_rx_ring *ring)
 {
-	int i;
-
-	for (i = 0; i < ring->page_cache.index; i++) {
-		dma_unmap_page(priv->ddev, ring->page_cache.buf[i].dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(ring->page_cache.buf[i].page);
-	}
-	ring->page_cache.index = 0;
 	mlx4_en_free_rx_buf(priv, ring);
 	if (ring->stride <= TXBB_SIZE)
 		ring->buf -= TXBB_SIZE;
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index 6e077d202827a..fe1378a689a10 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -350,16 +350,9 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
-	struct mlx4_en_rx_alloc frame = {
-		.page = tx_info->page,
-		.dma = tx_info->map0_dma,
-	};
-
-	if (!napi_mode || !mlx4_en_rx_recycle(ring->recycle_ring, &frame)) {
-		dma_unmap_page(priv->ddev, tx_info->map0_dma,
-			       PAGE_SIZE, priv->dma_dir);
-		put_page(tx_info->page);
-	}
+
+	dma_unmap_page(priv->ddev, tx_info->map0_dma, PAGE_SIZE, priv->dma_dir);
+	put_page(tx_info->page);
 
 	return tx_info->nr_txbb;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 29f48e63081b6..97311c98569f5 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -253,14 +253,6 @@ struct mlx4_en_rx_alloc {
 
 #define MLX4_EN_CACHE_SIZE (2 * NAPI_POLL_WEIGHT)
 
-struct mlx4_en_page_cache {
-	u32 index;
-	struct {
-		struct page	*page;
-		dma_addr_t	dma;
-	} buf[MLX4_EN_CACHE_SIZE];
-};
-
 enum {
 	MLX4_EN_TX_RING_STATE_RECOVERING,
 };
@@ -343,7 +335,6 @@ struct mlx4_en_rx_ring {
 	void *buf;
 	void *rx_info;
 	struct bpf_prog __rcu *xdp_prog;
-	struct mlx4_en_page_cache page_cache;
 	unsigned long bytes;
 	unsigned long packets;
 	unsigned long csum_ok;
@@ -708,8 +699,6 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 			       struct mlx4_en_priv *priv, unsigned int length,
 			       int tx_ind, bool *doorbell_pending);
 void mlx4_en_xmit_doorbell(struct mlx4_en_tx_ring *ring);
-bool mlx4_en_rx_recycle(struct mlx4_en_rx_ring *ring,
-			struct mlx4_en_rx_alloc *frame);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,

From 82b023c97f602970af6e1f77914cbba5f63b3936 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 12 Feb 2025 17:06:35 -0800
Subject: [PATCH 0722/2753] eth: mlx4: use the page pool for Rx buffers

Simple conversion to page pool. Preserve the current fragmentation
logic / page splitting. Each page starts with a single frag reference,
and then we bump that when attaching to skbs. This can likely be
optimized further.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250213010635.1354034-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c   | 55 +++++++-------------
 drivers/net/ethernet/mellanox/mlx4/en_tx.c   |  8 +--
 drivers/net/ethernet/mellanox/mlx4/mlx4_en.h |  1 -
 3 files changed, 25 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index d2cfbf2e38d96..b33285d755b90 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -52,57 +52,39 @@
 
 #include "mlx4_en.h"
 
-static int mlx4_alloc_page(struct mlx4_en_priv *priv,
-			   struct mlx4_en_rx_alloc *frag,
-			   gfp_t gfp)
-{
-	struct page *page;
-	dma_addr_t dma;
-
-	page = alloc_page(gfp);
-	if (unlikely(!page))
-		return -ENOMEM;
-	dma = dma_map_page(priv->ddev, page, 0, PAGE_SIZE, priv->dma_dir);
-	if (unlikely(dma_mapping_error(priv->ddev, dma))) {
-		__free_page(page);
-		return -ENOMEM;
-	}
-	frag->page = page;
-	frag->dma = dma;
-	frag->page_offset = priv->rx_headroom;
-	return 0;
-}
-
 static int mlx4_en_alloc_frags(struct mlx4_en_priv *priv,
 			       struct mlx4_en_rx_ring *ring,
 			       struct mlx4_en_rx_desc *rx_desc,
 			       struct mlx4_en_rx_alloc *frags,
 			       gfp_t gfp)
 {
+	dma_addr_t dma;
 	int i;
 
 	for (i = 0; i < priv->num_frags; i++, frags++) {
 		if (!frags->page) {
-			if (mlx4_alloc_page(priv, frags, gfp)) {
+			frags->page = page_pool_alloc_pages(ring->pp, gfp);
+			if (!frags->page) {
 				ring->alloc_fail++;
 				return -ENOMEM;
 			}
+			page_pool_fragment_page(frags->page, 1);
+			frags->page_offset = priv->rx_headroom;
+
 			ring->rx_alloc_pages++;
 		}
-		rx_desc->data[i].addr = cpu_to_be64(frags->dma +
-						    frags->page_offset);
+		dma = page_pool_get_dma_addr(frags->page);
+		rx_desc->data[i].addr = cpu_to_be64(dma + frags->page_offset);
 	}
 	return 0;
 }
 
 static void mlx4_en_free_frag(const struct mlx4_en_priv *priv,
+			      struct mlx4_en_rx_ring *ring,
 			      struct mlx4_en_rx_alloc *frag)
 {
-	if (frag->page) {
-		dma_unmap_page(priv->ddev, frag->dma,
-			       PAGE_SIZE, priv->dma_dir);
-		__free_page(frag->page);
-	}
+	if (frag->page)
+		page_pool_put_full_page(ring->pp, frag->page, false);
 	/* We need to clear all fields, otherwise a change of priv->log_rx_info
 	 * could lead to see garbage later in frag->page.
 	 */
@@ -167,7 +149,7 @@ static void mlx4_en_free_rx_desc(const struct mlx4_en_priv *priv,
 	frags = ring->rx_info + (index << priv->log_rx_info);
 	for (nr = 0; nr < priv->num_frags; nr++) {
 		en_dbg(DRV, priv, "Freeing fragment:%d\n", nr);
-		mlx4_en_free_frag(priv, frags + nr);
+		mlx4_en_free_frag(priv, ring, frags + nr);
 	}
 }
 
@@ -469,7 +451,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		if (unlikely(!page))
 			goto fail;
 
-		dma = frags->dma;
+		dma = page_pool_get_dma_addr(page);
 		dma_sync_single_range_for_cpu(priv->ddev, dma, frags->page_offset,
 					      frag_size, priv->dma_dir);
 
@@ -480,6 +462,7 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 		if (frag_info->frag_stride == PAGE_SIZE / 2) {
 			frags->page_offset ^= PAGE_SIZE / 2;
 			release = page_count(page) != 1 ||
+				  atomic_long_read(&page->pp_ref_count) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
 		} else if (!priv->rx_headroom) {
@@ -493,10 +476,9 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 			release = frags->page_offset + frag_info->frag_size > PAGE_SIZE;
 		}
 		if (release) {
-			dma_unmap_page(priv->ddev, dma, PAGE_SIZE, priv->dma_dir);
 			frags->page = NULL;
 		} else {
-			page_ref_inc(page);
+			page_pool_ref_page(page);
 		}
 
 		nr++;
@@ -766,7 +748,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			/* Get pointer to first fragment since we haven't
 			 * skb yet and cast it to ethhdr struct
 			 */
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma, sizeof(*ethh),
 						DMA_FROM_DEVICE);
 
@@ -805,7 +788,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			void *orig_data;
 			u32 act;
 
-			dma = frags[0].dma + frags[0].page_offset;
+			dma = page_pool_get_dma_addr(frags[0].page);
+			dma += frags[0].page_offset;
 			dma_sync_single_for_cpu(priv->ddev, dma,
 						priv->frag_info[0].frag_size,
 						DMA_FROM_DEVICE);
@@ -868,6 +852,7 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 		skb = napi_get_frags(&cq->napi);
 		if (unlikely(!skb))
 			goto next;
+		skb_mark_for_recycle(skb);
 
 		if (unlikely(ring->hwtstamp_rx_filter == HWTSTAMP_FILTER_ALL)) {
 			u64 timestamp = mlx4_en_get_cqe_ts(cqe);
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
index fe1378a689a10..87f35bcbeff8f 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c
@@ -44,6 +44,7 @@
 #include <linux/ipv6.h>
 #include <linux/indirect_call_wrapper.h>
 #include <net/ipv6.h>
+#include <net/page_pool/helpers.h>
 
 #include "mlx4_en.h"
 
@@ -350,9 +351,10 @@ u32 mlx4_en_recycle_tx_desc(struct mlx4_en_priv *priv,
 			    int napi_mode)
 {
 	struct mlx4_en_tx_info *tx_info = &ring->tx_info[index];
+	struct page_pool *pool = ring->recycle_ring->pp;
 
-	dma_unmap_page(priv->ddev, tx_info->map0_dma, PAGE_SIZE, priv->dma_dir);
-	put_page(tx_info->page);
+	/* Note that napi_mode = 0 means ndo_close() path, not budget = 0 */
+	page_pool_put_full_page(pool, tx_info->page, !!napi_mode);
 
 	return tx_info->nr_txbb;
 }
@@ -1189,7 +1191,7 @@ netdev_tx_t mlx4_en_xmit_frame(struct mlx4_en_rx_ring *rx_ring,
 	tx_desc = ring->buf + (index << LOG_TXBB_SIZE);
 	data = &tx_desc->data;
 
-	dma = frame->dma;
+	dma = page_pool_get_dma_addr(frame->page);
 
 	tx_info->page = frame->page;
 	frame->page = NULL;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
index 97311c98569f5..ad0d91a751848 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h
@@ -247,7 +247,6 @@ struct mlx4_en_tx_desc {
 
 struct mlx4_en_rx_alloc {
 	struct page	*page;
-	dma_addr_t	dma;
 	u32		page_offset;
 };
 

From 8af2136e77989a64fae0284bf76fd584e32edd3a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 14 Feb 2025 21:31:14 +0100
Subject: [PATCH 0723/2753] net: phy: realtek: add helper RTL822X_VND2_C22_REG

C22 register space is mapped to 0xa400 in MMD VEND2 register space.
Add a helper to access mapped C22 registers.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/6344277b-c5c7-449b-ac89-d5425306ca76@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/realtek_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 34be1d752ef82..b877057348d55 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -79,9 +79,7 @@
 /* RTL822X_VND2_XXXXX registers are only accessible when phydev->is_c45
  * is set, they cannot be accessed by C45-over-C22.
  */
-#define RTL822X_VND2_GBCR				0xa412
-
-#define RTL822X_VND2_GANLPAR				0xa414
+#define RTL822X_VND2_C22_REG(reg)		(0xa400 + 2 * (reg))
 
 #define RTL8366RB_POWER_SAVE			0x15
 #define RTL8366RB_POWER_SAVE_ON			BIT(12)
@@ -1015,7 +1013,8 @@ static int rtl822x_c45_config_aneg(struct phy_device *phydev)
 	val = linkmode_adv_to_mii_ctrl1000_t(phydev->advertising);
 
 	/* Vendor register as C45 has no standardized support for 1000BaseT */
-	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, RTL822X_VND2_GBCR,
+	ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2,
+				     RTL822X_VND2_C22_REG(MII_CTRL1000),
 				     ADVERTISE_1000FULL, val);
 	if (ret < 0)
 		return ret;
@@ -1032,7 +1031,7 @@ static int rtl822x_c45_read_status(struct phy_device *phydev)
 	/* Vendor register as C45 has no standardized support for 1000BaseT */
 	if (phydev->autoneg == AUTONEG_ENABLE && genphy_c45_aneg_done(phydev)) {
 		val = phy_read_mmd(phydev, MDIO_MMD_VEND2,
-				   RTL822X_VND2_GANLPAR);
+				   RTL822X_VND2_C22_REG(MII_STAT1000));
 		if (val < 0)
 			return val;
 	} else {

From 1fc61eeefe10d9996d2b875214d89f0909d03417 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 18 Feb 2025 16:47:40 -0700
Subject: [PATCH 0724/2753] io_uring: fix spelling error in uapi io_uring.h

This is obviously not that important, but when changes are synced back
from the kernel to liburing, the codespell CI ends up erroring because
of this misspelling. Let's just correct it and avoid this biting us
again on an import.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/uapi/linux/io_uring.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index e11c826385277..050fa8eb2e8f8 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -380,7 +380,7 @@ enum io_uring_op {
  *				result 	will be the number of buffers send, with
  *				the starting buffer ID in cqe->flags as per
  *				usual for provided buffer usage. The buffers
- *				will be	contigious from the starting buffer ID.
+ *				will be	contiguous from the starting buffer ID.
  */
 #define IORING_RECVSEND_POLL_FIRST	(1U << 0)
 #define IORING_RECV_MULTISHOT		(1U << 1)

From 4fa382be430421e1445f9c95c4dc9b7e0949ae8a Mon Sep 17 00:00:00 2001
From: Bart Van Assche <bvanassche@acm.org>
Date: Fri, 14 Feb 2025 14:43:44 -0800
Subject: [PATCH 0725/2753] scsi: ufs: core: Fix ufshcd_is_ufs_dev_busy() and
 ufshcd_eh_timed_out()

ufshcd_is_ufs_dev_busy(), ufshcd_print_host_state() and
ufshcd_eh_timed_out() are used in both modes (legacy mode and MCQ mode).
hba->outstanding_reqs only represents the outstanding requests in legacy
mode. Hence, change hba->outstanding_reqs into scsi_host_busy(hba->host) in
these functions.

Fixes: eacb139b77ff ("scsi: ufs: core: mcq: Enable multi-circular queue")
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250214224352.3025151-1-bvanassche@acm.org
Reviewed-by: Peter Wang <peter.wang@mediatek.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 1893a7ad95316..f9303e66bb798 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -266,7 +266,7 @@ static bool ufshcd_has_pending_tasks(struct ufs_hba *hba)
 
 static bool ufshcd_is_ufs_dev_busy(struct ufs_hba *hba)
 {
-	return hba->outstanding_reqs || ufshcd_has_pending_tasks(hba);
+	return scsi_host_busy(hba->host) || ufshcd_has_pending_tasks(hba);
 }
 
 static const struct ufs_dev_quirk ufs_fixups[] = {
@@ -628,8 +628,8 @@ static void ufshcd_print_host_state(struct ufs_hba *hba)
 	const struct scsi_device *sdev_ufs = hba->ufs_device_wlun;
 
 	dev_err(hba->dev, "UFS Host state=%d\n", hba->ufshcd_state);
-	dev_err(hba->dev, "outstanding reqs=0x%lx tasks=0x%lx\n",
-		hba->outstanding_reqs, hba->outstanding_tasks);
+	dev_err(hba->dev, "%d outstanding reqs, tasks=0x%lx\n",
+		scsi_host_busy(hba->host), hba->outstanding_tasks);
 	dev_err(hba->dev, "saved_err=0x%x, saved_uic_err=0x%x\n",
 		hba->saved_err, hba->saved_uic_err);
 	dev_err(hba->dev, "Device power mode=%d, UIC link state=%d\n",
@@ -8882,7 +8882,7 @@ static enum scsi_timeout_action ufshcd_eh_timed_out(struct scsi_cmnd *scmd)
 	dev_info(hba->dev, "%s() finished; outstanding_tasks = %#lx.\n",
 		 __func__, hba->outstanding_tasks);
 
-	return hba->outstanding_reqs ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
+	return scsi_host_busy(hba->host) ? SCSI_EH_RESET_TIMER : SCSI_EH_DONE;
 }
 
 static const struct attribute_group *ufshcd_driver_groups[] = {

From c900e49d58eb32b192b6d200ace4ae3ab89779d4 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Fri, 14 Feb 2025 16:12:52 -0500
Subject: [PATCH 0726/2753] net: xilinx: axienet: Implement BQL

Implement byte queue limits to allow queueing disciplines to account for
packets enqueued in the ring buffers but not yet transmitted.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250214211252.2615573-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 2ffaad0b0477f..60a5bceb01174 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -1002,6 +1002,7 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
 					&size, budget);
 
 	if (packets) {
+		netdev_completed_queue(ndev, packets, size);
 		u64_stats_update_begin(&lp->tx_stat_sync);
 		u64_stats_add(&lp->tx_packets, packets);
 		u64_stats_add(&lp->tx_bytes, size);
@@ -1125,6 +1126,7 @@ axienet_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (++new_tail_ptr >= lp->tx_bd_num)
 		new_tail_ptr = 0;
 	WRITE_ONCE(lp->tx_bd_tail, new_tail_ptr);
+	netdev_sent_queue(ndev, skb->len);
 
 	/* Start the transfer */
 	axienet_dma_out_addr(lp, XAXIDMA_TX_TDESC_OFFSET, tail_p);
@@ -1751,6 +1753,7 @@ static int axienet_stop(struct net_device *ndev)
 		dma_release_channel(lp->tx_chan);
 	}
 
+	netdev_reset_queue(ndev);
 	axienet_iow(lp, XAE_IE_OFFSET, 0);
 
 	if (lp->eth_irq > 0)
@@ -2676,6 +2679,7 @@ static void axienet_dma_err_handler(struct work_struct *work)
 			   ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
 
 	axienet_dma_stop(lp);
+	netdev_reset_queue(ndev);
 
 	for (i = 0; i < lp->tx_bd_num; i++) {
 		cur_p = &lp->tx_bd_v[i];

From 75696dd0fd721f2148e7fabe8d544600f176bc13 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Fri, 14 Feb 2025 16:27:02 -0500
Subject: [PATCH 0727/2753] net: cadence: macb: Convert to get_stats64

Convert the existing get_stats implementation to get_stats64. Since we
now report 64-bit values, increase the counters to 64-bits as well.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250214212703.2618652-2-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb.h      | 132 +++++++++++------------
 drivers/net/ethernet/cadence/macb_main.c |  34 +++---
 2 files changed, 81 insertions(+), 85 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f0..b4aa2b165bf38 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -951,75 +951,75 @@ struct macb_tx_skb {
  * device stats by a periodic timer.
  */
 struct macb_stats {
-	u32	rx_pause_frames;
-	u32	tx_ok;
-	u32	tx_single_cols;
-	u32	tx_multiple_cols;
-	u32	rx_ok;
-	u32	rx_fcs_errors;
-	u32	rx_align_errors;
-	u32	tx_deferred;
-	u32	tx_late_cols;
-	u32	tx_excessive_cols;
-	u32	tx_underruns;
-	u32	tx_carrier_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_symbol_errors;
-	u32	rx_oversize_pkts;
-	u32	rx_jabbers;
-	u32	rx_undersize_pkts;
-	u32	sqe_test_errors;
-	u32	rx_length_mismatch;
-	u32	tx_pause_frames;
+	u64	rx_pause_frames;
+	u64	tx_ok;
+	u64	tx_single_cols;
+	u64	tx_multiple_cols;
+	u64	rx_ok;
+	u64	rx_fcs_errors;
+	u64	rx_align_errors;
+	u64	tx_deferred;
+	u64	tx_late_cols;
+	u64	tx_excessive_cols;
+	u64	tx_underruns;
+	u64	tx_carrier_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_symbol_errors;
+	u64	rx_oversize_pkts;
+	u64	rx_jabbers;
+	u64	rx_undersize_pkts;
+	u64	sqe_test_errors;
+	u64	rx_length_mismatch;
+	u64	tx_pause_frames;
 };
 
 struct gem_stats {
-	u32	tx_octets_31_0;
-	u32	tx_octets_47_32;
-	u32	tx_frames;
-	u32	tx_broadcast_frames;
-	u32	tx_multicast_frames;
-	u32	tx_pause_frames;
-	u32	tx_64_byte_frames;
-	u32	tx_65_127_byte_frames;
-	u32	tx_128_255_byte_frames;
-	u32	tx_256_511_byte_frames;
-	u32	tx_512_1023_byte_frames;
-	u32	tx_1024_1518_byte_frames;
-	u32	tx_greater_than_1518_byte_frames;
-	u32	tx_underrun;
-	u32	tx_single_collision_frames;
-	u32	tx_multiple_collision_frames;
-	u32	tx_excessive_collisions;
-	u32	tx_late_collisions;
-	u32	tx_deferred_frames;
-	u32	tx_carrier_sense_errors;
-	u32	rx_octets_31_0;
-	u32	rx_octets_47_32;
-	u32	rx_frames;
-	u32	rx_broadcast_frames;
-	u32	rx_multicast_frames;
-	u32	rx_pause_frames;
-	u32	rx_64_byte_frames;
-	u32	rx_65_127_byte_frames;
-	u32	rx_128_255_byte_frames;
-	u32	rx_256_511_byte_frames;
-	u32	rx_512_1023_byte_frames;
-	u32	rx_1024_1518_byte_frames;
-	u32	rx_greater_than_1518_byte_frames;
-	u32	rx_undersized_frames;
-	u32	rx_oversize_frames;
-	u32	rx_jabbers;
-	u32	rx_frame_check_sequence_errors;
-	u32	rx_length_field_frame_errors;
-	u32	rx_symbol_errors;
-	u32	rx_alignment_errors;
-	u32	rx_resource_errors;
-	u32	rx_overruns;
-	u32	rx_ip_header_checksum_errors;
-	u32	rx_tcp_checksum_errors;
-	u32	rx_udp_checksum_errors;
+	u64	tx_octets_31_0;
+	u64	tx_octets_47_32;
+	u64	tx_frames;
+	u64	tx_broadcast_frames;
+	u64	tx_multicast_frames;
+	u64	tx_pause_frames;
+	u64	tx_64_byte_frames;
+	u64	tx_65_127_byte_frames;
+	u64	tx_128_255_byte_frames;
+	u64	tx_256_511_byte_frames;
+	u64	tx_512_1023_byte_frames;
+	u64	tx_1024_1518_byte_frames;
+	u64	tx_greater_than_1518_byte_frames;
+	u64	tx_underrun;
+	u64	tx_single_collision_frames;
+	u64	tx_multiple_collision_frames;
+	u64	tx_excessive_collisions;
+	u64	tx_late_collisions;
+	u64	tx_deferred_frames;
+	u64	tx_carrier_sense_errors;
+	u64	rx_octets_31_0;
+	u64	rx_octets_47_32;
+	u64	rx_frames;
+	u64	rx_broadcast_frames;
+	u64	rx_multicast_frames;
+	u64	rx_pause_frames;
+	u64	rx_64_byte_frames;
+	u64	rx_65_127_byte_frames;
+	u64	rx_128_255_byte_frames;
+	u64	rx_256_511_byte_frames;
+	u64	rx_512_1023_byte_frames;
+	u64	rx_1024_1518_byte_frames;
+	u64	rx_greater_than_1518_byte_frames;
+	u64	rx_undersized_frames;
+	u64	rx_oversize_frames;
+	u64	rx_jabbers;
+	u64	rx_frame_check_sequence_errors;
+	u64	rx_length_field_frame_errors;
+	u64	rx_symbol_errors;
+	u64	rx_alignment_errors;
+	u64	rx_resource_errors;
+	u64	rx_overruns;
+	u64	rx_ip_header_checksum_errors;
+	u64	rx_tcp_checksum_errors;
+	u64	rx_udp_checksum_errors;
 };
 
 /* Describes the name and offset of an individual statistic register, as
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 4db61372a78e5..2dc5490606b1c 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -988,8 +988,8 @@ static int macb_mii_init(struct macb *bp)
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
-	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	u64 *p = &bp->hw_stats.macb.rx_pause_frames;
+	u64 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
 	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
@@ -3069,7 +3069,7 @@ static void gem_update_stats(struct macb *bp)
 	unsigned int i, q, idx;
 	unsigned long *stat;
 
-	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
+	u64 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
@@ -3092,15 +3092,12 @@ static void gem_update_stats(struct macb *bp)
 			bp->ethtool_stats[idx++] = *stat;
 }
 
-static struct net_device_stats *gem_get_stats(struct macb *bp)
+static void gem_get_stats(struct macb *bp, struct rtnl_link_stats64 *nstat)
 {
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
-	struct net_device_stats *nstat = &bp->dev->stats;
 
-	if (!netif_running(bp->dev))
-		return nstat;
-
-	gem_update_stats(bp);
+	if (netif_running(bp->dev))
+		gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
 			    hwstat->rx_alignment_errors +
@@ -3129,8 +3126,6 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
-
-	return nstat;
 }
 
 static void gem_get_ethtool_stats(struct net_device *dev,
@@ -3181,14 +3176,17 @@ static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 	}
 }
 
-static struct net_device_stats *macb_get_stats(struct net_device *dev)
+static void macb_get_stats(struct net_device *dev,
+			   struct rtnl_link_stats64 *nstat)
 {
 	struct macb *bp = netdev_priv(dev);
-	struct net_device_stats *nstat = &bp->dev->stats;
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
-	if (macb_is_gem(bp))
-		return gem_get_stats(bp);
+	netdev_stats_to_stats64(nstat, &bp->dev->stats);
+	if (macb_is_gem(bp)) {
+		gem_get_stats(bp, nstat);
+		return;
+	}
 
 	/* read stats from hardware */
 	macb_update_stats(bp);
@@ -3224,8 +3222,6 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
-
-	return nstat;
 }
 
 static int macb_get_regs_len(struct net_device *netdev)
@@ -3908,7 +3904,7 @@ static const struct net_device_ops macb_netdev_ops = {
 	.ndo_stop		= macb_close,
 	.ndo_start_xmit		= macb_start_xmit,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_eth_ioctl		= macb_ioctl,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_change_mtu		= macb_change_mtu,
@@ -4569,7 +4565,7 @@ static const struct net_device_ops at91ether_netdev_ops = {
 	.ndo_open		= at91ether_open,
 	.ndo_stop		= at91ether_close,
 	.ndo_start_xmit		= at91ether_start_xmit,
-	.ndo_get_stats		= macb_get_stats,
+	.ndo_get_stats64	= macb_get_stats,
 	.ndo_set_rx_mode	= macb_set_rx_mode,
 	.ndo_set_mac_address	= eth_mac_addr,
 	.ndo_eth_ioctl		= macb_ioctl,

From f6af690a295a106cca1849be6de5bf2d41ead8a8 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Fri, 14 Feb 2025 16:27:03 -0500
Subject: [PATCH 0728/2753] net: cadence: macb: Report standard stats

Report standard statistics using the dedicated callbacks instead of
get_ethtool_stats.

OCTTX is split over two registers. Accumulating these registers
separately in gem_stats just means we need to combine them again later.
Instead, combine these stats before saving them, like is done for
ethtool_stats.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250214212703.2618652-3-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb.h      |   6 +-
 drivers/net/ethernet/cadence/macb_main.c | 160 ++++++++++++++++++++++-
 2 files changed, 160 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index b4aa2b165bf38..f69b2b7c88027 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -975,8 +975,7 @@ struct macb_stats {
 };
 
 struct gem_stats {
-	u64	tx_octets_31_0;
-	u64	tx_octets_47_32;
+	u64	tx_octets;
 	u64	tx_frames;
 	u64	tx_broadcast_frames;
 	u64	tx_multicast_frames;
@@ -995,8 +994,7 @@ struct gem_stats {
 	u64	tx_late_collisions;
 	u64	tx_deferred_frames;
 	u64	tx_carrier_sense_errors;
-	u64	rx_octets_31_0;
-	u64	rx_octets_47_32;
+	u64	rx_octets;
 	u64	rx_frames;
 	u64	rx_broadcast_frames;
 	u64	rx_multicast_frames;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 2dc5490606b1c..2112a9701e05f 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3069,7 +3069,7 @@ static void gem_update_stats(struct macb *bp)
 	unsigned int i, q, idx;
 	unsigned long *stat;
 
-	u64 *p = &bp->hw_stats.gem.tx_octets_31_0;
+	u64 *p = &bp->hw_stats.gem.tx_octets;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
@@ -3082,7 +3082,7 @@ static void gem_update_stats(struct macb *bp)
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
 			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
-			*(++p) += val;
+			*(p++) += ((u64)val) << 32;
 		}
 	}
 
@@ -3224,6 +3224,154 @@ static void macb_get_stats(struct net_device *dev,
 	/* Don't know about heartbeat or window errors... */
 }
 
+static void macb_get_pause_stats(struct net_device *dev,
+				 struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	macb_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+}
+
+static void gem_get_pause_stats(struct net_device *dev,
+				struct ethtool_pause_stats *pause_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	gem_update_stats(bp);
+	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
+	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+}
+
+static void macb_get_eth_mac_stats(struct net_device *dev,
+				   struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	macb_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_ok;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_cols;
+	mac_stats->MultipleCollisionFrames = hwstat->tx_multiple_cols;
+	mac_stats->FramesReceivedOK = hwstat->rx_ok;
+	mac_stats->FrameCheckSequenceErrors = hwstat->rx_fcs_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_align_errors;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred;
+	mac_stats->LateCollisions = hwstat->tx_late_cols;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_cols;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underruns;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_errors;
+	mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts;
+}
+
+static void gem_get_eth_mac_stats(struct net_device *dev,
+				  struct ethtool_eth_mac_stats *mac_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	gem_update_stats(bp);
+	mac_stats->FramesTransmittedOK = hwstat->tx_frames;
+	mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames;
+	mac_stats->MultipleCollisionFrames =
+		hwstat->tx_multiple_collision_frames;
+	mac_stats->FramesReceivedOK = hwstat->rx_frames;
+	mac_stats->FrameCheckSequenceErrors =
+		hwstat->rx_frame_check_sequence_errors;
+	mac_stats->AlignmentErrors = hwstat->rx_alignment_errors;
+	mac_stats->OctetsTransmittedOK = hwstat->tx_octets;
+	mac_stats->FramesWithDeferredXmissions = hwstat->tx_deferred_frames;
+	mac_stats->LateCollisions = hwstat->tx_late_collisions;
+	mac_stats->FramesAbortedDueToXSColls = hwstat->tx_excessive_collisions;
+	mac_stats->FramesLostDueToIntMACXmitError = hwstat->tx_underrun;
+	mac_stats->CarrierSenseErrors = hwstat->tx_carrier_sense_errors;
+	mac_stats->OctetsReceivedOK = hwstat->rx_octets;
+	mac_stats->MulticastFramesXmittedOK = hwstat->tx_multicast_frames;
+	mac_stats->BroadcastFramesXmittedOK = hwstat->tx_broadcast_frames;
+	mac_stats->MulticastFramesReceivedOK = hwstat->rx_multicast_frames;
+	mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames;
+	mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors;
+	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames;
+}
+
+/* TODO: Report SQE test errors when added to phy_stats */
+static void macb_get_eth_phy_stats(struct net_device *dev,
+				   struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	macb_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+}
+
+static void gem_get_eth_phy_stats(struct net_device *dev,
+				  struct ethtool_eth_phy_stats *phy_stats)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	gem_update_stats(bp);
+	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+}
+
+static void macb_get_rmon_stats(struct net_device *dev,
+				struct ethtool_rmon_stats *rmon_stats,
+				const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct macb_stats *hwstat = &bp->hw_stats.macb;
+
+	macb_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+}
+
+static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = {
+	{   64,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519, 16384 },
+	{ },
+};
+
+static void gem_get_rmon_stats(struct net_device *dev,
+			       struct ethtool_rmon_stats *rmon_stats,
+			       const struct ethtool_rmon_hist_range **ranges)
+{
+	struct macb *bp = netdev_priv(dev);
+	struct gem_stats *hwstat = &bp->hw_stats.gem;
+
+	gem_update_stats(bp);
+	rmon_stats->undersize_pkts = hwstat->rx_undersized_frames;
+	rmon_stats->oversize_pkts = hwstat->rx_oversize_frames;
+	rmon_stats->jabbers = hwstat->rx_jabbers;
+	rmon_stats->hist[0] = hwstat->rx_64_byte_frames;
+	rmon_stats->hist[1] = hwstat->rx_65_127_byte_frames;
+	rmon_stats->hist[2] = hwstat->rx_128_255_byte_frames;
+	rmon_stats->hist[3] = hwstat->rx_256_511_byte_frames;
+	rmon_stats->hist[4] = hwstat->rx_512_1023_byte_frames;
+	rmon_stats->hist[5] = hwstat->rx_1024_1518_byte_frames;
+	rmon_stats->hist[6] = hwstat->rx_greater_than_1518_byte_frames;
+	rmon_stats->hist_tx[0] = hwstat->tx_64_byte_frames;
+	rmon_stats->hist_tx[1] = hwstat->tx_65_127_byte_frames;
+	rmon_stats->hist_tx[2] = hwstat->tx_128_255_byte_frames;
+	rmon_stats->hist_tx[3] = hwstat->tx_256_511_byte_frames;
+	rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames;
+	rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames;
+	rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames;
+	*ranges = gem_rmon_ranges;
+}
+
 static int macb_get_regs_len(struct net_device *netdev)
 {
 	return MACB_GREGS_NBR * sizeof(u32);
@@ -3750,6 +3898,10 @@ static const struct ethtool_ops macb_ethtool_ops = {
 	.get_regs		= macb_get_regs,
 	.get_link		= ethtool_op_get_link,
 	.get_ts_info		= ethtool_op_get_ts_info,
+	.get_pause_stats	= macb_get_pause_stats,
+	.get_eth_mac_stats	= macb_get_eth_mac_stats,
+	.get_eth_phy_stats	= macb_get_eth_phy_stats,
+	.get_rmon_stats		= macb_get_rmon_stats,
 	.get_wol		= macb_get_wol,
 	.set_wol		= macb_set_wol,
 	.get_link_ksettings     = macb_get_link_ksettings,
@@ -3768,6 +3920,10 @@ static const struct ethtool_ops gem_ethtool_ops = {
 	.get_ethtool_stats	= gem_get_ethtool_stats,
 	.get_strings		= gem_get_ethtool_strings,
 	.get_sset_count		= gem_get_sset_count,
+	.get_pause_stats	= gem_get_pause_stats,
+	.get_eth_mac_stats	= gem_get_eth_mac_stats,
+	.get_eth_phy_stats	= gem_get_eth_phy_stats,
+	.get_rmon_stats		= gem_get_rmon_stats,
 	.get_link_ksettings     = macb_get_link_ksettings,
 	.set_link_ksettings     = macb_set_link_ksettings,
 	.get_ringparam		= macb_get_ringparam,

From 438989137acd6c620e9990c24dead5ffdd8e77c1 Mon Sep 17 00:00:00 2001
From: Siddh Raman Pant <siddh.raman.pant@oracle.com>
Date: Sat, 15 Feb 2025 09:40:51 +0000
Subject: [PATCH 0729/2753] netlink: Unset cb_running when terminating dump on
 release

When we terminated the dump, the callback isn't running, so cb_running
should be set to false to be logically consistent.

cb_running signifies whether a dump is ongoing. It is set to true in
cb->start(), and is checked in netlink_dump() to be true initially.
After the dump, it is set to false in the same function.

This is just a cleanup, no path should access this field on a closed
socket.

Signed-off-by: Siddh Raman Pant <siddh.raman.pant@oracle.com>
Link: https://patch.msgid.link/aff028e3eb2b768b9895fa6349fa1981ae22f098.camel@oracle.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/netlink/af_netlink.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 85311226183a2..f8f13058a46ed 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -771,6 +771,7 @@ static int netlink_release(struct socket *sock)
 			nlk->cb.done(&nlk->cb);
 		module_put(nlk->cb.module);
 		kfree_skb(nlk->cb.skb);
+		WRITE_ONCE(nlk->cb_running, false);
 	}
 
 	module_put(nlk->module);

From fabcfd6d10999024a721ae1b965b57eb8a305ace Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 15 Feb 2025 14:29:15 +0100
Subject: [PATCH 0730/2753] net: phy: realtek: add defines for shadowed c45
 standard registers

Realtek shadows standard c45 registers in VEND2 device register space.
Add defines for these VEND2 registers, based on the names of the
standard c45 registers.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/c90bdf76-f8b8-4d06-9656-7a52d5658ee6@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/realtek/realtek_main.c | 33 +++++++++++++++++---------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index b877057348d55..7a0b19d66acac 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -94,6 +94,16 @@
 #define RTL_VND2_PHYSR_MASTER			BIT(11)
 #define RTL_VND2_PHYSR_SPEED_MASK		(RTL_VND2_PHYSR_SPEEDL | RTL_VND2_PHYSR_SPEEDH)
 
+#define	RTL_MDIO_PCS_EEE_ABLE			0xa5c4
+#define	RTL_MDIO_AN_EEE_ADV			0xa5d0
+#define	RTL_MDIO_AN_EEE_LPABLE			0xa5d2
+#define	RTL_MDIO_AN_10GBT_CTRL			0xa5d4
+#define	RTL_MDIO_AN_10GBT_STAT			0xa5d6
+#define	RTL_MDIO_PMA_SPEED			0xa616
+#define	RTL_MDIO_AN_EEE_LPABLE2			0xa6d0
+#define	RTL_MDIO_AN_EEE_ADV2			0xa6d4
+#define	RTL_MDIO_PCS_EEE_ABLE2			0xa6ec
+
 #define RTL_GENERIC_PHYID			0x001cc800
 #define RTL_8211FVD_PHYID			0x001cc878
 #define RTL_8221B				0x001cc840
@@ -751,11 +761,11 @@ static int rtlgen_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 	if (devnum == MDIO_MMD_VEND2)
 		ret = rtlgen_read_vend2(phydev, regnum);
 	else if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE)
-		ret = rtlgen_read_vend2(phydev, 0xa5c4);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_PCS_EEE_ABLE);
 	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV)
-		ret = rtlgen_read_vend2(phydev, 0xa5d0);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_ADV);
 	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE)
-		ret = rtlgen_read_vend2(phydev, 0xa5d2);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_LPABLE);
 	else
 		ret = -EOPNOTSUPP;
 
@@ -770,7 +780,7 @@ static int rtlgen_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 	if (devnum == MDIO_MMD_VEND2)
 		ret = rtlgen_write_vend2(phydev, regnum, val);
 	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV)
-		ret = rtlgen_write_vend2(phydev, regnum, 0xa5d0);
+		ret = rtlgen_write_vend2(phydev, regnum, RTL_MDIO_AN_EEE_ADV);
 	else
 		ret = -EOPNOTSUPP;
 
@@ -785,11 +795,11 @@ static int rtl822x_read_mmd(struct phy_device *phydev, int devnum, u16 regnum)
 		return ret;
 
 	if (devnum == MDIO_MMD_PCS && regnum == MDIO_PCS_EEE_ABLE2)
-		ret = rtlgen_read_vend2(phydev, 0xa6ec);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_PCS_EEE_ABLE2);
 	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2)
-		ret = rtlgen_read_vend2(phydev, 0xa6d4);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_ADV2);
 	else if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_LPABLE2)
-		ret = rtlgen_read_vend2(phydev, 0xa6d0);
+		ret = rtlgen_read_vend2(phydev, RTL_MDIO_AN_EEE_LPABLE2);
 
 	return ret;
 }
@@ -803,7 +813,7 @@ static int rtl822x_write_mmd(struct phy_device *phydev, int devnum, u16 regnum,
 		return ret;
 
 	if (devnum == MDIO_MMD_AN && regnum == MDIO_AN_EEE_ADV2)
-		ret = rtlgen_write_vend2(phydev, 0xa6d4, val);
+		ret = rtlgen_write_vend2(phydev, RTL_MDIO_AN_EEE_ADV2, val);
 
 	return ret;
 }
@@ -899,7 +909,7 @@ static int rtl822x_get_features(struct phy_device *phydev)
 {
 	int val;
 
-	val = phy_read_mmd(phydev, MDIO_MMD_VEND2, 0xa616);
+	val = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL_MDIO_PMA_SPEED);
 	if (val < 0)
 		return val;
 
@@ -920,7 +930,8 @@ static int rtl822x_config_aneg(struct phy_device *phydev)
 	if (phydev->autoneg == AUTONEG_ENABLE) {
 		u16 adv = linkmode_adv_to_mii_10gbt_adv_t(phydev->advertising);
 
-		ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2, 0xa5d4,
+		ret = phy_modify_mmd_changed(phydev, MDIO_MMD_VEND2,
+					     RTL_MDIO_AN_10GBT_CTRL,
 					     MDIO_AN_10GBT_CTRL_ADV2_5G |
 					     MDIO_AN_10GBT_CTRL_ADV5G, adv);
 		if (ret < 0)
@@ -966,7 +977,7 @@ static int rtl822x_read_status(struct phy_device *phydev)
 	    !phydev->autoneg_complete)
 		return 0;
 
-	lpadv = phy_read_mmd(phydev, MDIO_MMD_VEND2, 0xa5d6);
+	lpadv = phy_read_mmd(phydev, MDIO_MMD_VEND2, RTL_MDIO_AN_10GBT_STAT);
 	if (lpadv < 0)
 		return lpadv;
 

From 8a6a77bb5a41d5a91c6155e1b902d9f75b5bf9a6 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:15:42 +0100
Subject: [PATCH 0731/2753] net: phy: move definition of phy_is_started before
 phy_disable_eee_mode

In preparation of a follow-up patch, move phy_is_started() to before
phy_disable_eee_mode().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/04d1e7a5-f4c0-42ab-8fa4-88ad26b74813@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 70c632799082e..96ea56de71b28 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1340,22 +1340,22 @@ void of_set_phy_timing_role(struct phy_device *phydev);
 int phy_speed_down_core(struct phy_device *phydev);
 
 /**
- * phy_disable_eee_mode - Don't advertise an EEE mode.
+ * phy_is_started - Convenience function to check whether PHY is started
  * @phydev: The phy_device struct
- * @link_mode: The EEE mode to be disabled
  */
-static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode)
+static inline bool phy_is_started(struct phy_device *phydev)
 {
-	linkmode_set_bit(link_mode, phydev->eee_disabled_modes);
+	return phydev->state >= PHY_UP;
 }
 
 /**
- * phy_is_started - Convenience function to check whether PHY is started
+ * phy_disable_eee_mode - Don't advertise an EEE mode.
  * @phydev: The phy_device struct
+ * @link_mode: The EEE mode to be disabled
  */
-static inline bool phy_is_started(struct phy_device *phydev)
+static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode)
 {
-	return phydev->state >= PHY_UP;
+	linkmode_set_bit(link_mode, phydev->eee_disabled_modes);
 }
 
 void phy_resolve_aneg_pause(struct phy_device *phydev);

From a9b6a860d7789d8183530aedbb46cf70f843e40d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:16:34 +0100
Subject: [PATCH 0732/2753] net: phy: improve phy_disable_eee_mode

If a mode is to be disabled, remove it from advertising_eee.
Disabling EEE modes shall be done before calling phy_start(),
warn if that's not the case.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/92164896-38ff-4474-b98b-e83fc05b9509@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 96ea56de71b28..0d5da01d275c4 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1355,7 +1355,10 @@ static inline bool phy_is_started(struct phy_device *phydev)
  */
 static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode)
 {
+	WARN_ON(phy_is_started(phydev));
+
 	linkmode_set_bit(link_mode, phydev->eee_disabled_modes);
+	linkmode_clear_bit(link_mode, phydev->advertising_eee);
 }
 
 void phy_resolve_aneg_pause(struct phy_device *phydev);

From 7f33fea6bb53d4dcc927a7aca81eb08b5c1fe63a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:17:48 +0100
Subject: [PATCH 0733/2753] net: phy: remove disabled EEE modes from
 advertising_eee in phy_probe

A PHY driver may populate eee_disabled_modes in its probe or get_features
callback, therefore filter the EEE advertisement read from the PHY.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/493f3e2e-9cfc-445d-adbe-58d9c117a489@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 0d56e7c7f98cd..7c4e1ad1864c7 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -3580,22 +3580,21 @@ static int phy_probe(struct device *dev)
 	if (err)
 		goto out;
 
-	/* There is no "enabled" flag. If PHY is advertising, assume it is
-	 * kind of enabled.
-	 */
-	phydev->eee_cfg.eee_enabled = !linkmode_empty(phydev->advertising_eee);
+	/* Get the EEE modes we want to prohibit. */
+	of_set_phy_eee_broken(phydev);
 
 	/* Some PHYs may advertise, by default, not support EEE modes. So,
-	 * we need to clean them.
+	 * we need to clean them. In addition remove all disabled EEE modes.
 	 */
-	if (phydev->eee_cfg.eee_enabled)
-		linkmode_and(phydev->advertising_eee, phydev->supported_eee,
-			     phydev->advertising_eee);
+	linkmode_and(phydev->advertising_eee, phydev->supported_eee,
+		     phydev->advertising_eee);
+	linkmode_andnot(phydev->advertising_eee, phydev->advertising_eee,
+			phydev->eee_disabled_modes);
 
-	/* Get the EEE modes we want to prohibit. We will ask
-	 * the PHY stop advertising these mode later on
+	/* There is no "enabled" flag. If PHY is advertising, assume it is
+	 * kind of enabled.
 	 */
-	of_set_phy_eee_broken(phydev);
+	phydev->eee_cfg.eee_enabled = !linkmode_empty(phydev->advertising_eee);
 
 	/* Get master/slave strap overrides */
 	of_set_phy_timing_role(phydev);

From aa951feb542662342223c8db582897969b64fb59 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:18:42 +0100
Subject: [PATCH 0734/2753] net: phy: c45: Don't silently remove disabled EEE
 modes any longer when writing advertisement register

advertising_eee is adjusted now whenever an EEE mode gets disabled.
Therefore we can remove the silent removal of disabled EEE modes here.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/e95b9dad-24a7-4e3e-9af9-6f0770cf1520@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index dedbdcab83a59..b19055cfced04 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -683,13 +683,10 @@ EXPORT_SYMBOL_GPL(genphy_c45_read_mdix);
 static int genphy_c45_write_eee_adv(struct phy_device *phydev,
 				    unsigned long *adv)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(tmp);
 	int val, changed = 0;
 
-	linkmode_andnot(tmp, adv, phydev->eee_disabled_modes);
-
 	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP1_FEATURES)) {
-		val = linkmode_to_mii_eee_cap1_t(tmp);
+		val = linkmode_to_mii_eee_cap1_t(adv);
 
 		/* IEEE 802.3-2018 45.2.7.13 EEE advertisement 1
 		 * (Register 7.60)
@@ -707,7 +704,7 @@ static int genphy_c45_write_eee_adv(struct phy_device *phydev,
 	}
 
 	if (linkmode_intersects(phydev->supported_eee, PHY_EEE_CAP2_FEATURES)) {
-		val = linkmode_to_mii_eee_cap2_t(tmp);
+		val = linkmode_to_mii_eee_cap2_t(adv);
 
 		/* IEEE 802.3-2022 45.2.7.16 EEE advertisement 2
 		 * (Register 7.62)

From 199d0ce385adbbf5b8532752a26e12413100c4ea Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:19:23 +0100
Subject: [PATCH 0735/2753] net: phy: c45: use cached EEE advertisement in
 genphy_c45_ethtool_get_eee

Now that disabled EEE modes are considered when populating
advertising_eee, we can use this bitmap here instead of reading
the PHY register.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/e57ed3d4-d0bc-4f91-83f6-8f48dfb6d7d7@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index b19055cfced04..fed5fb0ef321e 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1516,14 +1516,14 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 {
 	int ret;
 
-	ret = genphy_c45_eee_is_active(phydev, data->advertised,
-				       data->lp_advertised);
+	ret = genphy_c45_eee_is_active(phydev, NULL, data->lp_advertised);
 	if (ret < 0)
 		return ret;
 
 	data->eee_active = phydev->eee_active;
 	linkmode_andnot(data->supported, phydev->supported_eee,
 			phydev->eee_disabled_modes);
+	linkmode_copy(data->advertised, phydev->advertising_eee);
 	return 0;
 }
 EXPORT_SYMBOL(genphy_c45_ethtool_get_eee);

From 809265fe96fe3eb7a85a9260356767587c482cb7 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 16 Feb 2025 22:20:07 +0100
Subject: [PATCH 0736/2753] net: phy: c45: remove local advertisement parameter
 from genphy_c45_eee_is_active

After the last user has gone, we can remove the local advertisement
parameter from genphy_c45_eee_is_active.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/bd121330-9e28-4bc8-8422-794bd54d561f@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c | 31 +++++++++----------------------
 drivers/net/phy/phy.c     |  4 ++--
 include/linux/phy.h       |  3 +--
 3 files changed, 12 insertions(+), 26 deletions(-)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index fed5fb0ef321e..37c9a344bf4a3 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1464,42 +1464,29 @@ EXPORT_SYMBOL_GPL(genphy_c45_plca_get_status);
 /**
  * genphy_c45_eee_is_active - get EEE status
  * @phydev: target phy_device struct
- * @adv: variable to store advertised linkmodes
  * @lp: variable to store LP advertised linkmodes
  *
- * Description: this function will read local and link partner PHY
- * advertisements. Compare them return current EEE state.
+ * Description: this function will read link partner PHY advertisement
+ * and compare it to local advertisement to return current EEE state.
  */
-int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv,
-			     unsigned long *lp)
+int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_adv) = {};
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(tmp_lp) = {};
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
-	bool eee_active;
 	int ret;
 
-	ret = genphy_c45_read_eee_adv(phydev, tmp_adv);
-	if (ret)
-		return ret;
-
 	ret = genphy_c45_read_eee_lpa(phydev, tmp_lp);
 	if (ret)
 		return ret;
 
-	linkmode_and(common, tmp_adv, tmp_lp);
-	if (!linkmode_empty(tmp_adv) && !linkmode_empty(common))
-		eee_active = phy_check_valid(phydev->speed, phydev->duplex,
-					     common);
-	else
-		eee_active = false;
-
-	if (adv)
-		linkmode_copy(adv, tmp_adv);
 	if (lp)
 		linkmode_copy(lp, tmp_lp);
 
-	return eee_active;
+	linkmode_and(common, phydev->advertising_eee, tmp_lp);
+	if (linkmode_empty(common))
+		return 0;
+
+	return phy_check_valid(phydev->speed, phydev->duplex, common);
 }
 EXPORT_SYMBOL(genphy_c45_eee_is_active);
 
@@ -1516,7 +1503,7 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 {
 	int ret;
 
-	ret = genphy_c45_eee_is_active(phydev, NULL, data->lp_advertised);
+	ret = genphy_c45_eee_is_active(phydev, data->lp_advertised);
 	if (ret < 0)
 		return ret;
 
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index f2086b0b7b76e..831b368396277 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1031,7 +1031,7 @@ static int phy_check_link_status(struct phy_device *phydev)
 	if (phydev->link && phydev->state != PHY_RUNNING) {
 		phy_check_downshift(phydev);
 		phydev->state = PHY_RUNNING;
-		err = genphy_c45_eee_is_active(phydev, NULL, NULL);
+		err = genphy_c45_eee_is_active(phydev, NULL);
 		phydev->eee_active = err > 0;
 		phydev->enable_tx_lpi = phydev->eee_cfg.tx_lpi_enabled &&
 					phydev->eee_active;
@@ -1780,7 +1780,7 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable)
 	if (!phydev->drv)
 		return -EIO;
 
-	ret = genphy_c45_eee_is_active(phydev, NULL, NULL);
+	ret = genphy_c45_eee_is_active(phydev, NULL);
 	if (ret < 0)
 		return ret;
 	if (!ret)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 0d5da01d275c4..584710e084eb6 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2032,8 +2032,7 @@ int genphy_c45_plca_set_cfg(struct phy_device *phydev,
 			    const struct phy_plca_cfg *plca_cfg);
 int genphy_c45_plca_get_status(struct phy_device *phydev,
 			       struct phy_plca_status *plca_st);
-int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *adv,
-			     unsigned long *lp);
+int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp);
 int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 			       struct ethtool_keee *data);
 int genphy_c45_ethtool_set_eee(struct phy_device *phydev,

From 9faaaef27c5df617223ad725f3fac9a21d333e81 Mon Sep 17 00:00:00 2001
From: Pei Xiao <xiaopei01@kylinos.cn>
Date: Mon, 17 Feb 2025 09:29:30 +0800
Subject: [PATCH 0737/2753] net: freescale: ucc_geth: make ugeth_mac_ops be
 static const

sparse warning:
    sparse: symbol 'ugeth_mac_ops' was not declared. Should it be
static.

Add static to fix sparse warnings and add const. phylink_create() will
accept a const struct.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/202502141128.9HfxcdIE-lkp@intel.com
Signed-off-by: Pei Xiao <xiaopei01@kylinos.cn>
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/ucc_geth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/ucc_geth.c b/drivers/net/ethernet/freescale/ucc_geth.c
index 88510f8227596..affd5a6c44e7b 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -3408,7 +3408,7 @@ static int ucc_geth_parse_clock(struct device_node *np, const char *which,
 	return 0;
 }
 
-struct phylink_mac_ops ugeth_mac_ops = {
+static const struct phylink_mac_ops ugeth_mac_ops = {
 	.mac_link_up = ugeth_mac_link_up,
 	.mac_link_down = ugeth_mac_link_down,
 	.mac_config = ugeth_mac_config,

From 952d7325362ffbefa6ce5619fb4e53c2159ec7a7 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Mon, 17 Feb 2025 17:40:21 +0800
Subject: [PATCH 0738/2753] net: ethernet: mediatek: add EEE support

Add EEE support to MediaTek SoC Ethernet. The register fields are
similar to the ones in MT7531, except that the LPI threshold is in
milliseconds.

Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250217094022.1065436-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 67 +++++++++++++++++++++
 drivers/net/ethernet/mediatek/mtk_eth_soc.h | 11 ++++
 2 files changed, 78 insertions(+)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 0ad965ced5ef8..922330b3f4d70 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -815,12 +815,60 @@ static void mtk_mac_link_up(struct phylink_config *config,
 	mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id));
 }
 
+static void mtk_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+
+	mtk_m32(eth, MAC_MCR_EEE100M | MAC_MCR_EEE1G, 0, MTK_MAC_MCR(mac->id));
+}
+
+static int mtk_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				 bool tx_clk_stop)
+{
+	struct mtk_mac *mac = container_of(config, struct mtk_mac,
+					   phylink_config);
+	struct mtk_eth *eth = mac->hw;
+	u32 val;
+
+	/* Tx idle timer in ms */
+	timer = DIV_ROUND_UP(timer, 1000);
+
+	/* If the timer is zero, then set LPI_MODE, which allows the
+	 * system to enter LPI mode immediately rather than waiting for
+	 * the LPI threshold.
+	 */
+	if (!timer)
+		val = MAC_EEE_LPI_MODE;
+	else if (FIELD_FIT(MAC_EEE_LPI_TXIDLE_THD, timer))
+		val = FIELD_PREP(MAC_EEE_LPI_TXIDLE_THD, timer);
+	else
+		val = MAC_EEE_LPI_TXIDLE_THD;
+
+	if (tx_clk_stop)
+		val |= MAC_EEE_CKG_TXIDLE;
+
+	/* PHY Wake-up time, this field does not have a reset value, so use the
+	 * reset value from MT7531 (36us for 100M and 17us for 1000M).
+	 */
+	val |= FIELD_PREP(MAC_EEE_WAKEUP_TIME_1000, 17) |
+	       FIELD_PREP(MAC_EEE_WAKEUP_TIME_100, 36);
+
+	mtk_w32(eth, val, MTK_MAC_EEECR(mac->id));
+	mtk_m32(eth, 0, MAC_MCR_EEE100M | MAC_MCR_EEE1G, MTK_MAC_MCR(mac->id));
+
+	return 0;
+}
+
 static const struct phylink_mac_ops mtk_phylink_ops = {
 	.mac_select_pcs = mtk_mac_select_pcs,
 	.mac_config = mtk_mac_config,
 	.mac_finish = mtk_mac_finish,
 	.mac_link_down = mtk_mac_link_down,
 	.mac_link_up = mtk_mac_link_up,
+	.mac_disable_tx_lpi = mtk_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = mtk_mac_enable_tx_lpi,
 };
 
 static int mtk_mdio_init(struct mtk_eth *eth)
@@ -4469,6 +4517,20 @@ static int mtk_set_pauseparam(struct net_device *dev, struct ethtool_pauseparam
 	return phylink_ethtool_set_pauseparam(mac->phylink, pause);
 }
 
+static int mtk_get_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_get_eee(mac->phylink, eee);
+}
+
+static int mtk_set_eee(struct net_device *dev, struct ethtool_keee *eee)
+{
+	struct mtk_mac *mac = netdev_priv(dev);
+
+	return phylink_ethtool_set_eee(mac->phylink, eee);
+}
+
 static u16 mtk_select_queue(struct net_device *dev, struct sk_buff *skb,
 			    struct net_device *sb_dev)
 {
@@ -4501,6 +4563,8 @@ static const struct ethtool_ops mtk_ethtool_ops = {
 	.set_pauseparam		= mtk_set_pauseparam,
 	.get_rxnfc		= mtk_get_rxnfc,
 	.set_rxnfc		= mtk_set_rxnfc,
+	.get_eee		= mtk_get_eee,
+	.set_eee		= mtk_set_eee,
 };
 
 static const struct net_device_ops mtk_netdev_ops = {
@@ -4610,6 +4674,9 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np)
 	mac->phylink_config.type = PHYLINK_NETDEV;
 	mac->phylink_config.mac_capabilities = MAC_ASYM_PAUSE | MAC_SYM_PAUSE |
 		MAC_10 | MAC_100 | MAC_1000 | MAC_2500FD;
+	mac->phylink_config.lpi_capabilities = MAC_100FD | MAC_1000FD |
+		MAC_2500FD;
+	mac->phylink_config.lpi_timer_default = 1000;
 
 	/* MT7623 gmac0 is now missing its speed-specific PLL configuration
 	 * in its .mac_config method (since state->speed is not valid there.
diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
index 0d5225f1d3eef..90a377ab4359e 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h
@@ -453,6 +453,8 @@
 #define MAC_MCR_RX_FIFO_CLR_DIS	BIT(12)
 #define MAC_MCR_BACKOFF_EN	BIT(9)
 #define MAC_MCR_BACKPR_EN	BIT(8)
+#define MAC_MCR_EEE1G		BIT(7)
+#define MAC_MCR_EEE100M		BIT(6)
 #define MAC_MCR_FORCE_RX_FC	BIT(5)
 #define MAC_MCR_FORCE_TX_FC	BIT(4)
 #define MAC_MCR_SPEED_1000	BIT(3)
@@ -461,6 +463,15 @@
 #define MAC_MCR_FORCE_LINK	BIT(0)
 #define MAC_MCR_FORCE_LINK_DOWN	(MAC_MCR_FORCE_MODE)
 
+/* Mac EEE control registers */
+#define MTK_MAC_EEECR(x)		(0x10104 + (x * 0x100))
+#define MAC_EEE_WAKEUP_TIME_1000	GENMASK(31, 24)
+#define MAC_EEE_WAKEUP_TIME_100		GENMASK(23, 16)
+#define MAC_EEE_LPI_TXIDLE_THD		GENMASK(15, 8)
+#define MAC_EEE_CKG_TXIDLE		BIT(3)
+#define MAC_EEE_CKG_RXLPI		BIT(2)
+#define MAC_EEE_LPI_MODE		BIT(0)
+
 /* Mac status registers */
 #define MTK_MAC_MSR(x)		(0x10108 + (x * 0x100))
 #define MAC_MSR_EEE1G		BIT(7)

From f29e41454b94e6e4f3cdf340947b61fd22950c96 Mon Sep 17 00:00:00 2001
From: Chandra Mohan Sundar <chandru.dav@gmail.com>
Date: Mon, 17 Feb 2025 19:45:16 +0530
Subject: [PATCH 0739/2753] selftests: net: Fix few spelling mistakes

Fix few spelling mistakes in net selftests

Signed-off-by: Chandra Mohan Sundar <chandru.dav@gmail.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250217141520.81033-1-chandru.dav@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fcnal-test.sh   | 4 ++--
 tools/testing/selftests/net/fdb_flush.sh    | 2 +-
 tools/testing/selftests/net/fib_nexthops.sh | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/fcnal-test.sh b/tools/testing/selftests/net/fcnal-test.sh
index 899dbad0104bf..4fcc38907e48e 100755
--- a/tools/testing/selftests/net/fcnal-test.sh
+++ b/tools/testing/selftests/net/fcnal-test.sh
@@ -3667,7 +3667,7 @@ ipv6_addr_bind_novrf()
 	# when it really should not
 	a=${NSA_LO_IP6}
 	log_start
-	show_hint "Tecnically should fail since address is not on device but kernel allows"
+	show_hint "Technically should fail since address is not on device but kernel allows"
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
 	log_test_addr ${a} $? 0 "TCP socket bind to out of scope local address"
 }
@@ -3724,7 +3724,7 @@ ipv6_addr_bind_vrf()
 	# passes when it really should not
 	a=${VRF_IP6}
 	log_start
-	show_hint "Tecnically should fail since address is not on device but kernel allows"
+	show_hint "Technically should fail since address is not on device but kernel allows"
 	run_cmd nettest -6 -s -l ${a} -I ${NSA_DEV} -t1 -b
 	log_test_addr ${a} $? 0 "TCP socket bind to VRF address with device bind"
 
diff --git a/tools/testing/selftests/net/fdb_flush.sh b/tools/testing/selftests/net/fdb_flush.sh
index d5e3abb8658c3..9931a1e36e3db 100755
--- a/tools/testing/selftests/net/fdb_flush.sh
+++ b/tools/testing/selftests/net/fdb_flush.sh
@@ -583,7 +583,7 @@ vxlan_test_flush_by_remote_attributes()
 	$IP link del dev vx10
 	$IP link add name vx10 type vxlan dstport "$VXPORT" external
 
-	# For multicat FDB entries, the VXLAN driver stores a linked list of
+	# For multicast FDB entries, the VXLAN driver stores a linked list of
 	# remotes for a given key. Verify that only the expected remotes are
 	# flushed.
 	multicast_fdb_entries_add
diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index 77c83d9508d3b..bea1282e02819 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -741,7 +741,7 @@ ipv6_fcnal()
 	run_cmd "$IP nexthop add id 52 via 2001:db8:92::3"
 	log_test $? 2 "Create nexthop - gw only"
 
-	# gw is not reachable throught given dev
+	# gw is not reachable through given dev
 	run_cmd "$IP nexthop add id 53 via 2001:db8:3::3 dev veth1"
 	log_test $? 2 "Create nexthop - invalid gw+dev combination"
 

From 8f02c48f8f623eedc3c0a26a64c7ef155c35bfb9 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Mon, 17 Feb 2025 07:48:13 -0800
Subject: [PATCH 0740/2753] net: Remove redundant variable declaration in
 __dev_change_flags()

The old_flags variable is declared twice in __dev_change_flags(),
causing a shadow variable warning. This patch fixes the issue by
removing the redundant declaration, reusing the existing old_flags
variable instead.

	net/core/dev.c:9225:16: warning: declaration shadows a local variable [-Wshadow]
	9225 |                 unsigned int old_flags = dev->flags;
	|                              ^
	net/core/dev.c:9185:15: note: previous declaration is here
	9185 |         unsigned int old_flags = dev->flags;
	|                      ^
	1 warning generated.

Remove the redundant inner declaration and reuse the existing old_flags
variable since its value is not needed outside the if block, and it is
safe to reuse the variable. This eliminates the warning while
maintaining the same functionality.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250217-old_flags-v2-1-4cda3b43a35f@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index bcb266ab29126..ebc000b568283 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9182,7 +9182,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 
 	if ((flags ^ dev->gflags) & IFF_PROMISC) {
 		int inc = (flags & IFF_PROMISC) ? 1 : -1;
-		unsigned int old_flags = dev->flags;
+		old_flags = dev->flags;
 
 		dev->gflags ^= IFF_PROMISC;
 

From 3a03f9ec5d333b9998fbc63fd3e075b9d1991b89 Mon Sep 17 00:00:00 2001
From: Yu-Chun Lin <eleanor15x@gmail.com>
Date: Mon, 17 Feb 2025 23:58:33 +0800
Subject: [PATCH 0741/2753] net: stmmac: Use str_enabled_disabled() helper

As kernel test robot reported, the following warning occurs:

cocci warnings: (new ones prefixed by >>)
>> drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c:582:6-8: opportunity for str_enabled_disabled(on)

Replace ternary (condition ? "enabled" : "disabled") with
str_enabled_disabled() from string_choices.h to improve readability,
maintain uniform string usage, and reduce binary size through linker
deduplication.

Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Link: https://patch.msgid.link/20250217155833.3105775-1-eleanor15x@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
index 7900bf3effa71..a8b901cdf5cbb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c
@@ -16,6 +16,7 @@
 #include <linux/slab.h>
 #include <linux/ethtool.h>
 #include <linux/io.h>
+#include <linux/string_choices.h>
 #include "stmmac.h"
 #include "stmmac_pcs.h"
 #include "stmmac_ptp.h"
@@ -625,7 +626,7 @@ int dwmac1000_ptp_enable(struct ptp_clock_info *ptp,
 		}
 
 		netdev_dbg(priv->dev, "Auxiliary Snapshot %s.\n",
-			   on ? "enabled" : "disabled");
+			   str_enabled_disabled(on));
 		writel(tcr_val, ptpaddr + PTP_TCR);
 
 		/* wait for auxts fifo clear to finish */

From aaf6532d119d8ad4c75420b021d2649864133583 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:26:58 -0500
Subject: [PATCH 0742/2753] tcp: only initialize sockcm tsflags field

TCP only reads the tsflags field. Don't bother initializing others.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-2-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 5d78ab3b416e2..6a8f19a10911a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1127,7 +1127,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size)
 		/* 'common' sending to sendq */
 	}
 
-	sockcm_init(&sockc, sk);
+	sockc = (struct sockcm_cookie) { .tsflags = READ_ONCE(sk->sk_tsflags)};
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
 		if (unlikely(err)) {

From 6ad861519a69ecf3cf032c579e18569f62b81263 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:26:59 -0500
Subject: [PATCH 0743/2753] net: initialize mark in sockcm_init

Avoid open coding initialization of sockcm fields.
Avoid reading the sk_priority field twice.

This ensures all callers, existing and future, will correctly try a
cmsg passed mark before sk_mark.

This patch extends support for cmsg mark to:
packet_spkt and packet_tpacket and net/can/raw.c.

This patch extends support for cmsg priority to:
packet_spkt and packet_tpacket.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h     | 1 +
 net/can/raw.c          | 2 +-
 net/packet/af_packet.c | 9 ++++-----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 60ebf3c7b229e..fac65ed30983d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1829,6 +1829,7 @@ static inline void sockcm_init(struct sockcm_cookie *sockc,
 			       const struct sock *sk)
 {
 	*sockc = (struct sockcm_cookie) {
+		.mark = READ_ONCE(sk->sk_mark),
 		.tsflags = READ_ONCE(sk->sk_tsflags),
 		.priority = READ_ONCE(sk->sk_priority),
 	};
diff --git a/net/can/raw.c b/net/can/raw.c
index 46e8ed9d64da3..9b1d5f036f579 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -963,7 +963,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size)
 
 	skb->dev = dev;
 	skb->priority = sockc.priority;
-	skb->mark = READ_ONCE(sk->sk_mark);
+	skb->mark = sockc.mark;
 	skb->tstamp = sockc.transmit_time;
 
 	skb_setup_tx_timestamp(skb, &sockc);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index c131e5ceea374..3e9ddf72cd031 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2102,8 +2102,8 @@ static int packet_sendmsg_spkt(struct socket *sock, struct msghdr *msg,
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = READ_ONCE(sk->sk_priority);
-	skb->mark = READ_ONCE(sk->sk_mark);
+	skb->priority = sockc.priority;
+	skb->mark = sockc.mark;
 	skb_set_delivery_type_by_clockid(skb, sockc.transmit_time, sk->sk_clockid);
 	skb_setup_tx_timestamp(skb, &sockc);
 
@@ -2634,8 +2634,8 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb,
 
 	skb->protocol = proto;
 	skb->dev = dev;
-	skb->priority = READ_ONCE(po->sk.sk_priority);
-	skb->mark = READ_ONCE(po->sk.sk_mark);
+	skb->priority = sockc->priority;
+	skb->mark = sockc->mark;
 	skb_set_delivery_type_by_clockid(skb, sockc->transmit_time, po->sk.sk_clockid);
 	skb_setup_tx_timestamp(skb, sockc);
 	skb_zcopy_set_nouarg(skb, ph.raw);
@@ -3039,7 +3039,6 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len)
 		goto out_unlock;
 
 	sockcm_init(&sockc, sk);
-	sockc.mark = READ_ONCE(sk->sk_mark);
 	if (msg->msg_controllen) {
 		err = sock_cmsg_send(sk, msg, &sockc);
 		if (unlikely(err))

From 94788792f37902f1f4d417f6f9663831cf7e91fc Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:27:00 -0500
Subject: [PATCH 0744/2753] ipv4: initialize inet socket cookies with
 sockcm_init

Avoid open coding the same logic.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-4-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 305eccdf4ff76..3c4ef5ddad83a 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -94,9 +94,8 @@ static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 {
 	ipcm_init(ipcm);
 
-	ipcm->sockc.mark = READ_ONCE(inet->sk.sk_mark);
-	ipcm->sockc.priority = READ_ONCE(inet->sk.sk_priority);
-	ipcm->sockc.tsflags = READ_ONCE(inet->sk.sk_tsflags);
+	sockcm_init(&ipcm->sockc, &inet->sk);
+
 	ipcm->oif = READ_ONCE(inet->sk.sk_bound_dev_if);
 	ipcm->addr = inet->inet_saddr;
 	ipcm->protocol = inet->inet_num;

From 9329b58395e51bba9c847419cc4ba176df3dd2b7 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:27:01 -0500
Subject: [PATCH 0745/2753] ipv4: remove get_rttos

Initialize the ip cookie tos field when initializing the cookie, in
ipcm_init_sk.

The existing code inverts the standard pattern for initializing cookie
fields. Default is to initialize the field from the sk, then possibly
overwrite that when parsing cmsgs (the unlikely case).

This field inverts that, setting the field to an illegal value and
after cmsg parsing checking whether the value is still illegal and
thus should be overridden.

Be careful to always apply mask INET_DSCP_MASK, as before.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-5-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip.h | 11 +++--------
 net/ipv4/ping.c  |  6 +++---
 net/ipv4/raw.c   |  6 +++---
 net/ipv4/udp.c   |  6 +++---
 4 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/include/net/ip.h b/include/net/ip.h
index 3c4ef5ddad83a..ce5e59957dd55 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -92,7 +92,9 @@ static inline void ipcm_init(struct ipcm_cookie *ipcm)
 static inline void ipcm_init_sk(struct ipcm_cookie *ipcm,
 				const struct inet_sock *inet)
 {
-	ipcm_init(ipcm);
+	*ipcm = (struct ipcm_cookie) {
+		.tos = READ_ONCE(inet->tos),
+	};
 
 	sockcm_init(&ipcm->sockc, &inet->sk);
 
@@ -256,13 +258,6 @@ static inline u8 ip_sendmsg_scope(const struct inet_sock *inet,
 	return RT_SCOPE_UNIVERSE;
 }
 
-static inline __u8 get_rttos(struct ipcm_cookie* ipc, struct inet_sock *inet)
-{
-	u8 dsfield = ipc->tos != -1 ? ipc->tos : READ_ONCE(inet->tos);
-
-	return dsfield & INET_DSCP_MASK;
-}
-
 /* datagram.c */
 int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 619ddc087957f..85d09f2ecadcb 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -705,7 +705,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ip_options_data opt_copy;
 	int free = 0;
 	__be32 saddr, daddr, faddr;
-	u8 tos, scope;
+	u8 scope;
 	int err;
 
 	pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
@@ -768,7 +768,6 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 		faddr = ipc.opt->opt.faddr;
 	}
-	tos = get_rttos(&ipc, inet);
 	scope = ip_sendmsg_scope(inet, &ipc, msg);
 
 	if (ipv4_is_multicast(daddr)) {
@@ -779,7 +778,8 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	} else if (!ipc.oif)
 		ipc.oif = READ_ONCE(inet->uc_index);
 
-	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
+			   ipc.tos & INET_DSCP_MASK, scope,
 			   sk->sk_protocol, inet_sk_flowi_flags(sk), faddr,
 			   saddr, 0, 0, sk->sk_uid);
 
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 4304a68d1db05..6aace4d55733e 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -486,7 +486,7 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	struct ipcm_cookie ipc;
 	struct rtable *rt = NULL;
 	struct flowi4 fl4;
-	u8 tos, scope;
+	u8 scope;
 	int free = 0;
 	__be32 daddr;
 	__be32 saddr;
@@ -581,7 +581,6 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 			daddr = ipc.opt->opt.faddr;
 		}
 	}
-	tos = get_rttos(&ipc, inet);
 	scope = ip_sendmsg_scope(inet, &ipc, msg);
 
 	uc_index = READ_ONCE(inet->uc_index);
@@ -606,7 +605,8 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		}
 	}
 
-	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark,
+			   ipc.tos & INET_DSCP_MASK, scope,
 			   hdrincl ? ipc.protocol : sk->sk_protocol,
 			   inet_sk_flowi_flags(sk) |
 			    (hdrincl ? FLOWI_FLAG_KNOWN_NH : 0),
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 3485989cd4bde..17c7736d83494 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1280,7 +1280,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int free = 0;
 	int connected = 0;
 	__be32 daddr, faddr, saddr;
-	u8 tos, scope;
+	u8 scope;
 	__be16 dport;
 	int err, is_udplite = IS_UDPLITE(sk);
 	int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
@@ -1404,7 +1404,6 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		faddr = ipc.opt->opt.faddr;
 		connected = 0;
 	}
-	tos = get_rttos(&ipc, inet);
 	scope = ip_sendmsg_scope(inet, &ipc, msg);
 	if (scope == RT_SCOPE_LINK)
 		connected = 0;
@@ -1441,7 +1440,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 		fl4 = &fl4_stack;
 
-		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos, scope,
+		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark,
+				   ipc.tos & INET_DSCP_MASK, scope,
 				   sk->sk_protocol, flow_flags, faddr, saddr,
 				   dport, inet->inet_sport, sk->sk_uid);
 

From e8485911050a60091d1bf51a162f0a2654729fad Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:27:02 -0500
Subject: [PATCH 0746/2753] icmp: reflect tos through ip cookie rather than
 updating inet_sk

Do not modify socket fields if it can be avoided.

The current code predates the introduction of ip cookies in commit
aa6615814533 ("ipv4: processing ancillary IP_TOS or IP_TTL"). Now that
cookies exist and support tos, update that field directly.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-6-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 5482edb5aade2..799775ba97d4f 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -405,7 +405,6 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct sock *sk;
-	struct inet_sock *inet;
 	__be32 daddr, saddr;
 	u32 mark = IP4_REPLY_MARK(net, skb->mark);
 	int type = icmp_param->data.icmph.type;
@@ -424,12 +423,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
 	sk = icmp_xmit_lock(net);
 	if (!sk)
 		goto out_bh_enable;
-	inet = inet_sk(sk);
 
 	icmp_param->data.icmph.checksum = 0;
 
 	ipcm_init(&ipc);
-	inet->tos = ip_hdr(skb)->tos;
+	ipc.tos = ip_hdr(skb)->tos;
 	ipc.sockc.mark = mark;
 	daddr = ipc.addr = ip_hdr(skb)->saddr;
 	saddr = fib_compute_spec_dst(skb);
@@ -737,8 +735,8 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 	icmp_param.data.icmph.checksum	 = 0;
 	icmp_param.skb	  = skb_in;
 	icmp_param.offset = skb_network_offset(skb_in);
-	inet_sk(sk)->tos = tos;
 	ipcm_init(&ipc);
+	ipc.tos = tos;
 	ipc.addr = iph->saddr;
 	ipc.opt = &icmp_param.replyopts.opt;
 	ipc.sockc.mark = mark;

From 096208592b09c2f5fc0c1a174694efa41c04209d Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:27:03 -0500
Subject: [PATCH 0747/2753] ipv6: replace ipcm6_init calls with ipcm6_init_sk

This initializes tclass and dontfrag before cmsg parsing, removing the
need for explicit checks against -1 in each caller.

Leave hlimit set to -1, because its full initialization
(in ip6_sk_dst_hoplimit) requires more state (dst, flowi6, ..).

This also prepares for calling sockcm_init in a follow-on patch.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-7-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ipv6.h  | 9 ---------
 net/ipv6/raw.c      | 8 +-------
 net/ipv6/udp.c      | 7 +------
 net/l2tp/l2tp_ip6.c | 8 +-------
 4 files changed, 3 insertions(+), 29 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index f5c43ad1565e2..46a679d9b3348 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -363,15 +363,6 @@ struct ipcm6_cookie {
 	struct ipv6_txoptions *opt;
 };
 
-static inline void ipcm6_init(struct ipcm6_cookie *ipc6)
-{
-	*ipc6 = (struct ipcm6_cookie) {
-		.hlimit = -1,
-		.tclass = -1,
-		.dontfrag = -1,
-	};
-}
-
 static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6,
 				 const struct sock *sk)
 {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index a45aba090aa41..ae68d3f7dd321 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -777,7 +777,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
 	fl6.flowi6_uid = sk->sk_uid;
 
-	ipcm6_init(&ipc6);
+	ipcm6_init_sk(&ipc6, sk);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = fl6.flowi6_mark;
 	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
@@ -891,9 +891,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (hdrincl)
 		fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH;
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
@@ -904,9 +901,6 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
-
 	if (msg->msg_flags&MSG_CONFIRM)
 		goto do_confirm;
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index c6ea438b5c758..7096b7e84c106 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1494,7 +1494,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	int is_udplite = IS_UDPLITE(sk);
 	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);
 
-	ipcm6_init(&ipc6);
+	ipcm6_init_sk(&ipc6, sk);
 	ipc6.gso_size = READ_ONCE(up->gso_size);
 	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
 	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
@@ -1704,9 +1704,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);
 
 	dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
@@ -1752,8 +1749,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	WRITE_ONCE(up->pending, AF_INET6);
 
 do_append_data:
-	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
 	up->len += ulen;
 	err = ip6_append_data(sk, getfrag, msg, ulen, sizeof(struct udphdr),
 			      &ipc6, fl6, dst_rt6_info(dst),
diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c
index f4c1da0708269..b98d13584c81f 100644
--- a/net/l2tp/l2tp_ip6.c
+++ b/net/l2tp/l2tp_ip6.c
@@ -547,7 +547,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
 	fl6.flowi6_uid = sk->sk_uid;
 
-	ipcm6_init(&ipc6);
+	ipcm6_init_sk(&ipc6, sk);
 
 	if (lsa) {
 		if (addr_len < SIN6_LEN_RFC2133)
@@ -634,9 +634,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	security_sk_classify_flow(sk, flowi6_to_flowi_common(&fl6));
 
-	if (ipc6.tclass < 0)
-		ipc6.tclass = np->tclass;
-
 	fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
 
 	dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p);
@@ -648,9 +645,6 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (ipc6.hlimit < 0)
 		ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
 
-	if (ipc6.dontfrag < 0)
-		ipc6.dontfrag = inet6_test_bit(DONTFRAG, sk);
-
 	if (msg->msg_flags & MSG_CONFIRM)
 		goto do_confirm;
 

From 5cd2f78886dd86de1b13d6502808a149f1b77959 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Fri, 14 Feb 2025 17:27:04 -0500
Subject: [PATCH 0748/2753] ipv6: initialize inet socket cookies with
 sockcm_init

Avoid open coding the same logic.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250214222720.3205500-8-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ipv6.h | 2 ++
 net/ipv6/ping.c    | 3 ---
 net/ipv6/raw.c     | 9 +++------
 net/ipv6/udp.c     | 3 ---
 4 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 46a679d9b3348..9614006f483c9 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -371,6 +371,8 @@ static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6,
 		.tclass = inet6_sk(sk)->tclass,
 		.dontfrag = inet6_test_bit(DONTFRAG, sk),
 	};
+
+	sockcm_init(&ipc6->sockc, sk);
 }
 
 static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np)
diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c
index 46b8adf6e7f8e..84d90dd8b3f0f 100644
--- a/net/ipv6/ping.c
+++ b/net/ipv6/ping.c
@@ -119,9 +119,6 @@ static int ping_v6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		return -EINVAL;
 
 	ipcm6_init_sk(&ipc6, sk);
-	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
-	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
-	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
 
 	fl6.flowi6_oif = oif;
 
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index ae68d3f7dd321..fda640ebd53f8 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -769,19 +769,16 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	hdrincl = inet_test_bit(HDRINCL, sk);
 
+	ipcm6_init_sk(&ipc6, sk);
+
 	/*
 	 *	Get and verify the address.
 	 */
 	memset(&fl6, 0, sizeof(fl6));
 
-	fl6.flowi6_mark = READ_ONCE(sk->sk_mark);
+	fl6.flowi6_mark = ipc6.sockc.mark;
 	fl6.flowi6_uid = sk->sk_uid;
 
-	ipcm6_init_sk(&ipc6, sk);
-	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
-	ipc6.sockc.mark = fl6.flowi6_mark;
-	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
-
 	if (sin6) {
 		if (addr_len < SIN6_LEN_RFC2133)
 			return -EINVAL;
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7096b7e84c106..3a0d6c5a8286b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1496,9 +1496,6 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	ipcm6_init_sk(&ipc6, sk);
 	ipc6.gso_size = READ_ONCE(up->gso_size);
-	ipc6.sockc.tsflags = READ_ONCE(sk->sk_tsflags);
-	ipc6.sockc.mark = READ_ONCE(sk->sk_mark);
-	ipc6.sockc.priority = READ_ONCE(sk->sk_priority);
 
 	/* destination address check */
 	if (sin6) {

From eff2eb592efd73f00590d578c3d6021f604df62c Mon Sep 17 00:00:00 2001
From: Andrew Donnellan <ajd@linux.ibm.com>
Date: Wed, 19 Feb 2025 17:48:07 +1100
Subject: [PATCH 0749/2753] cxl: Fix cross-reference in documentation and add
 deprecation warning

commit 5731d41af924 ("cxl: Deprecate driver") labelled the cxl driver as
deprecated and moved the ABI documentation to the obsolete/ subdirectory,
but didn't update cxl.rst, causing a warning once ff7ff6eb4f809 ("docs:
media: Allow creating cross-references for RC ABI") was merged.

Fix the cross-reference, and also add a deprecation warning.

Fixes: 5731d41af924 ("cxl: Deprecate driver")
Reported-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
Acked-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Link: https://patch.msgid.link/20250219064807.175107-1-ajd@linux.ibm.com
---
 Documentation/arch/powerpc/cxl.rst | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/Documentation/arch/powerpc/cxl.rst b/Documentation/arch/powerpc/cxl.rst
index d2d77057610e4..778adda740d24 100644
--- a/Documentation/arch/powerpc/cxl.rst
+++ b/Documentation/arch/powerpc/cxl.rst
@@ -18,6 +18,7 @@ Introduction
     both access system memory directly and with the same effective
     addresses.
 
+    **This driver is deprecated and will be removed in a future release.**
 
 Hardware overview
 =================
@@ -453,7 +454,7 @@ Sysfs Class
 
     A cxl sysfs class is added under /sys/class/cxl to facilitate
     enumeration and tuning of the accelerators. Its layout is
-    described in Documentation/ABI/testing/sysfs-class-cxl
+    described in Documentation/ABI/obsolete/sysfs-class-cxl
 
 
 Udev rules

From 8821f36333e27c8355d4a730649923f938e1e4b9 Mon Sep 17 00:00:00 2001
From: Friedrich Vock <friedrich.vock@gmx.de>
Date: Mon, 27 Jan 2025 16:27:52 +0100
Subject: [PATCH 0750/2753] cgroup/dmem: Don't open-code
 css_for_each_descendant_pre

The current implementation has a bug: If the current css doesn't
contain any pool that is a descendant of the "pool" (i.e. when
found_descendant == false), then "pool" will point to some unrelated
pool. If the current css has a child, we'll overwrite parent_pool with
this unrelated pool on the next iteration.

Since we can just check whether a pool refers to the same region to
determine whether or not it's related, all the additional pool tracking
is unnecessary, so just switch to using css_for_each_descendant_pre for
traversal.

Fixes: b168ed458dde ("kernel/cgroup: Add "dmem" memory accounting cgroup")
Signed-off-by: Friedrich Vock <friedrich.vock@gmx.de>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250127152754.21325-1-friedrich.vock@gmx.de
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 kernel/cgroup/dmem.c | 50 ++++++++++----------------------------------
 1 file changed, 11 insertions(+), 39 deletions(-)

diff --git a/kernel/cgroup/dmem.c b/kernel/cgroup/dmem.c
index fbe34299673d3..10b63433f0573 100644
--- a/kernel/cgroup/dmem.c
+++ b/kernel/cgroup/dmem.c
@@ -220,60 +220,32 @@ dmem_cgroup_calculate_protection(struct dmem_cgroup_pool_state *limit_pool,
 				 struct dmem_cgroup_pool_state *test_pool)
 {
 	struct page_counter *climit;
-	struct cgroup_subsys_state *css, *next_css;
+	struct cgroup_subsys_state *css;
 	struct dmemcg_state *dmemcg_iter;
-	struct dmem_cgroup_pool_state *pool, *parent_pool;
-	bool found_descendant;
+	struct dmem_cgroup_pool_state *pool, *found_pool;
 
 	climit = &limit_pool->cnt;
 
 	rcu_read_lock();
-	parent_pool = pool = limit_pool;
-	css = &limit_pool->cs->css;
 
-	/*
-	 * This logic is roughly equivalent to css_foreach_descendant_pre,
-	 * except we also track the parent pool to find out which pool we need
-	 * to calculate protection values for.
-	 *
-	 * We can stop the traversal once we find test_pool among the
-	 * descendants since we don't really care about any others.
-	 */
-	while (pool != test_pool) {
-		next_css = css_next_child(NULL, css);
-		if (next_css) {
-			parent_pool = pool;
-		} else {
-			while (css != &limit_pool->cs->css) {
-				next_css = css_next_child(css, css->parent);
-				if (next_css)
-					break;
-				css = css->parent;
-				parent_pool = pool_parent(parent_pool);
-			}
-			/*
-			 * We can only hit this when test_pool is not a
-			 * descendant of limit_pool.
-			 */
-			if (WARN_ON_ONCE(css == &limit_pool->cs->css))
-				break;
-		}
-		css = next_css;
-
-		found_descendant = false;
+	css_for_each_descendant_pre(css, &limit_pool->cs->css) {
 		dmemcg_iter = container_of(css, struct dmemcg_state, css);
+		found_pool = NULL;
 
 		list_for_each_entry_rcu(pool, &dmemcg_iter->pools, css_node) {
-			if (pool_parent(pool) == parent_pool) {
-				found_descendant = true;
+			if (pool->region == limit_pool->region) {
+				found_pool = pool;
 				break;
 			}
 		}
-		if (!found_descendant)
+		if (!found_pool)
 			continue;
 
 		page_counter_calculate_protection(
-			climit, &pool->cnt, true);
+			climit, &found_pool->cnt, true);
+
+		if (found_pool == test_pool)
+			break;
 	}
 	rcu_read_unlock();
 }

From 44afc10d4678d5a3a4ab8c25750be00f037298cf Mon Sep 17 00:00:00 2001
From: Ryan McClelland <rymcclel@gmail.com>
Date: Thu, 16 Jan 2025 22:49:24 -0800
Subject: [PATCH 0751/2753] HID: nintendo: fix gencon button events map

This fixes the button event map to match the 3-button recommendation
as well as the redundant 'z' in the button map events for the Sega
MD/Gen 6 Button.

Signed-off-by: Ryan McClelland <rymcclel@gmail.com>
Reviewed-by: Daniel J. Ogorchock <djogorchock@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-nintendo.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/hid/hid-nintendo.c b/drivers/hid/hid-nintendo.c
index 11ac246176ae1..839d5bcd72b1e 100644
--- a/drivers/hid/hid-nintendo.c
+++ b/drivers/hid/hid-nintendo.c
@@ -457,13 +457,13 @@ static const struct joycon_ctlr_button_mapping snescon_button_mappings[] = {
 };
 
 static const struct joycon_ctlr_button_mapping gencon_button_mappings[] = {
-	{ BTN_A,	JC_BTN_A,	},
-	{ BTN_B,	JC_BTN_B,	},
-	{ BTN_C,	JC_BTN_R,	},
-	{ BTN_X,	JC_BTN_X,	}, /* MD/GEN 6B Only */
-	{ BTN_Y,	JC_BTN_Y,	}, /* MD/GEN 6B Only */
-	{ BTN_Z,	JC_BTN_L,	}, /* MD/GEN 6B Only */
-	{ BTN_SELECT,	JC_BTN_ZR,	},
+	{ BTN_WEST,	JC_BTN_A,	}, /* A */
+	{ BTN_SOUTH,	JC_BTN_B,	}, /* B */
+	{ BTN_EAST,	JC_BTN_R,	}, /* C */
+	{ BTN_TL,	JC_BTN_X,	}, /* X MD/GEN 6B Only */
+	{ BTN_NORTH,	JC_BTN_Y,	}, /* Y MD/GEN 6B Only */
+	{ BTN_TR,	JC_BTN_L,	}, /* Z MD/GEN 6B Only */
+	{ BTN_SELECT,	JC_BTN_ZR,	}, /* Mode */
 	{ BTN_START,	JC_BTN_PLUS,	},
 	{ BTN_MODE,	JC_BTN_HOME,	},
 	{ BTN_Z,	JC_BTN_CAP,	},

From 4bd0725c09f377ffaf22b834241f6c050742e4fc Mon Sep 17 00:00:00 2001
From: Yu-Chun Lin <eleanor15x@gmail.com>
Date: Tue, 18 Feb 2025 00:50:13 +0800
Subject: [PATCH 0752/2753] HID: google: fix unused variable warning under
 !CONFIG_ACPI

As reported by the kernel test robot, the following warning occurs:

>> drivers/hid/hid-google-hammer.c:261:36: warning: 'cbas_ec_acpi_ids' defined but not used [-Wunused-const-variable=]
     261 | static const struct acpi_device_id cbas_ec_acpi_ids[] = {
         |                                    ^~~~~~~~~~~~~~~~

The 'cbas_ec_acpi_ids' array is only used when CONFIG_ACPI is enabled.
Wrapping its definition and 'MODULE_DEVICE_TABLE' in '#ifdef CONFIG_ACPI'
prevents a compiler warning when ACPI is disabled.

Fixes: eb1aac4c8744f75 ("HID: google: add support tablet mode switch for Whiskers")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501201141.jctFH5eB-lkp@intel.com/
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-google-hammer.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/hid-google-hammer.c b/drivers/hid/hid-google-hammer.c
index 0f292b5d3e26d..eb6fd2dc75d0a 100644
--- a/drivers/hid/hid-google-hammer.c
+++ b/drivers/hid/hid-google-hammer.c
@@ -268,11 +268,13 @@ static void cbas_ec_remove(struct platform_device *pdev)
 	mutex_unlock(&cbas_ec_reglock);
 }
 
+#ifdef CONFIG_ACPI
 static const struct acpi_device_id cbas_ec_acpi_ids[] = {
 	{ "GOOG000B", 0 },
 	{ }
 };
 MODULE_DEVICE_TABLE(acpi, cbas_ec_acpi_ids);
+#endif
 
 #ifdef CONFIG_OF
 static const struct of_device_id cbas_ec_of_match[] = {

From 823987841424289339fdb4ba90e6d2c3792836db Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 18 Feb 2025 14:37:29 +0800
Subject: [PATCH 0753/2753] HID: intel-ish-hid: Fix use-after-free issue in
 hid_ishtp_cl_remove()

During the `rmmod` operation for the `intel_ishtp_hid` driver, a
use-after-free issue can occur in the hid_ishtp_cl_remove() function.
The function hid_ishtp_cl_deinit() is called before ishtp_hid_remove(),
which can lead to accessing freed memory or resources during the
removal process.

Call Trace:
 ? ishtp_cl_send+0x168/0x220 [intel_ishtp]
 ? hid_output_report+0xe3/0x150 [hid]
 hid_ishtp_set_feature+0xb5/0x120 [intel_ishtp_hid]
 ishtp_hid_request+0x7b/0xb0 [intel_ishtp_hid]
 hid_hw_request+0x1f/0x40 [hid]
 sensor_hub_set_feature+0x11f/0x190 [hid_sensor_hub]
 _hid_sensor_power_state+0x147/0x1e0 [hid_sensor_trigger]
 hid_sensor_runtime_resume+0x22/0x30 [hid_sensor_trigger]
 sensor_hub_remove+0xa8/0xe0 [hid_sensor_hub]
 hid_device_remove+0x49/0xb0 [hid]
 hid_destroy_device+0x6f/0x90 [hid]
 ishtp_hid_remove+0x42/0x70 [intel_ishtp_hid]
 hid_ishtp_cl_remove+0x6b/0xb0 [intel_ishtp_hid]
 ishtp_cl_device_remove+0x4a/0x60 [intel_ishtp]
 ...

Additionally, ishtp_hid_remove() is a HID level power off, which should
occur before the ISHTP level disconnect.

This patch resolves the issue by reordering the calls in
hid_ishtp_cl_remove(). The function ishtp_hid_remove() is now
called before hid_ishtp_cl_deinit().

Fixes: f645a90e8ff7 ("HID: intel-ish-hid: ishtp-hid-client: use helper functions for connection")
Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ishtp-hid-client.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/intel-ish-hid/ishtp-hid-client.c b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
index cb04cd1d980bd..6550ad5bfbb53 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid-client.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid-client.c
@@ -832,9 +832,9 @@ static void hid_ishtp_cl_remove(struct ishtp_cl_device *cl_device)
 			hid_ishtp_cl);
 
 	dev_dbg(ishtp_device(cl_device), "%s\n", __func__);
-	hid_ishtp_cl_deinit(hid_ishtp_cl);
 	ishtp_put_device(cl_device);
 	ishtp_hid_remove(client_data);
+	hid_ishtp_cl_deinit(hid_ishtp_cl);
 
 	hid_ishtp_cl = NULL;
 

From 07583a0010696a17fb0942e0b499a62785c5fc9f Mon Sep 17 00:00:00 2001
From: Zhang Lixu <lixu.zhang@intel.com>
Date: Tue, 18 Feb 2025 14:37:30 +0800
Subject: [PATCH 0754/2753] HID: intel-ish-hid: Fix use-after-free issue in
 ishtp_hid_remove()

The system can experience a random crash a few minutes after the driver is
removed. This issue occurs due to improper handling of memory freeing in
the ishtp_hid_remove() function.

The function currently frees the `driver_data` directly within the loop
that destroys the HID devices, which can lead to accessing freed memory.
Specifically, `hid_destroy_device()` uses `driver_data` when it calls
`hid_ishtp_set_feature()` to power off the sensor, so freeing
`driver_data` beforehand can result in accessing invalid memory.

This patch resolves the issue by storing the `driver_data` in a temporary
variable before calling `hid_destroy_device()`, and then freeing the
`driver_data` after the device is destroyed.

Fixes: 0b28cb4bcb17 ("HID: intel-ish-hid: ISH HID client driver")
Signed-off-by: Zhang Lixu <lixu.zhang@intel.com>
Acked-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-ish-hid/ishtp-hid.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hid/intel-ish-hid/ishtp-hid.c b/drivers/hid/intel-ish-hid/ishtp-hid.c
index 00c6f0ebf3563..be2c62fc8251d 100644
--- a/drivers/hid/intel-ish-hid/ishtp-hid.c
+++ b/drivers/hid/intel-ish-hid/ishtp-hid.c
@@ -261,12 +261,14 @@ int ishtp_hid_probe(unsigned int cur_hid_dev,
  */
 void ishtp_hid_remove(struct ishtp_cl_data *client_data)
 {
+	void *data;
 	int i;
 
 	for (i = 0; i < client_data->num_hid_devices; ++i) {
 		if (client_data->hid_sensor_hubs[i]) {
-			kfree(client_data->hid_sensor_hubs[i]->driver_data);
+			data = client_data->hid_sensor_hubs[i]->driver_data;
 			hid_destroy_device(client_data->hid_sensor_hubs[i]);
+			kfree(data);
 			client_data->hid_sensor_hubs[i] = NULL;
 		}
 	}

From 27315836f4bcc8e4879d50dfc1fa6eb41e7952ef Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Sun, 16 Feb 2025 19:42:26 -0800
Subject: [PATCH 0755/2753] net: mana: Allow tso_max_size to go up-to
 GSO_MAX_SIZE

Allow the max aggregated pkt size to go up-to GSO_MAX_SIZE for MANA NIC.
This patch only increases the max allowable gso/gro pkt size for MANA
devices and does not change the defaults.
Following are the perf benefits by increasing the pkt aggregate size from
legacy gso_max_size value(64K) to newer one(up-to 511K

IPv4 tests
for i in {1..10}; do netperf -t TCP_RR  -H 10.0.0.5 -p50000 -- -r80000,80000
-O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done

min	p90	p99	Throughput		gso_max_size
93	171	194	6594.25
97	154	180	7183.74
95	165	189	6927.86
96	165	188	6976.04
93	154	185	7338.05			64K
93	168	189	6938.03
94	169	189	6784.93
92	166	189	7117.56
94	179	191	6678.44
95	157	183	7277.81

min	p90	p99	Throughput
93	134	146	8448.75
95	134	140	8396.54
94	137	148	8204.12
94	137	148	8244.41
94	128	139	8666.52			80K
94	141	153	8116.86
94	138	149	8163.92
92	135	142	8362.72
92	134	142	8497.57
93	136	148	8393.23

IPv6 Tests
for i in {1..10}; do netperf -t TCP_RR  -H fd00:9013:cadd::4 -p50000 --
-r80000,80000 -O MIN_LATENCY,P90_LATENCY,P99_LATENCY,THROUGHPUT|tail -1; done

min	p90	p99	Throughput		gso_max_size
108	165	170	6673.2
101	169	189	6451.69
101	165	169	6737.65
102	167	175	6614.64
101	178	189	6247.13			64K
107	163	169	6678.63
106	176	187	6350.86
100	164	169	6617.36
102	163	170	6849.21
102	168	175	6605.7

min	p90	p99	Throughput
108	155	166	7183
110	154	163	7268.87
109	152	159	7434.35
107	145	157	7569.15
107	149	164	7496.17			80K
110	154	159	7245.85
108	156	162	7266.24
109	145	158	7526.66
106	145	151	7785.75
111	148	157	7246.65

Tested on azure env with Accelerated Networking enabled and disabled.

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index aa1e47233fe50..3b0fb4d95cf71 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -256,6 +256,9 @@ netdev_tx_t mana_start_xmit(struct sk_buff *skb, struct net_device *ndev)
 	if (skb_cow_head(skb, MANA_HEADROOM))
 		goto tx_drop_count;
 
+	if (unlikely(ipv6_hopopt_jumbo_remove(skb)))
+		goto tx_drop_count;
+
 	txq = &apc->tx_qp[txq_idx].txq;
 	gdma_sq = txq->gdma_sq;
 	cq = &apc->tx_qp[txq_idx].tx_cq;
@@ -2873,6 +2876,8 @@ static int mana_probe_port(struct mana_context *ac, int port_idx,
 	ndev->dev_port = port_idx;
 	SET_NETDEV_DEV(ndev, gc->dev);
 
+	netif_set_tso_max_size(ndev, GSO_MAX_SIZE);
+
 	netif_carrier_off(ndev);
 
 	netdev_rss_key_fill(apc->hashkey, MANA_HASH_KEY_SIZE);

From 685920920e3d5f68a8c50107b97747b0f8ce050f Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Sun, 16 Feb 2025 19:42:42 -0800
Subject: [PATCH 0756/2753] hv_netvsc: Use VF's tso_max_size value when data
 path is VF

On Azure, increasing VF's gso/gro packet size to up-to GSO_MAX_SIZE
is not possible without allowing the same for netvsc NIC
(as the NICs are bonded together). For bonded NICs, the min of the max
aggregated pkt size of the members is propagated in the stack.

Therefore, we use netif_set_tso_max_size() to set max aggregated pkt size
to VF's packet size for netvsc too, when the data path is switched over
to the VF
Tested on azure env with Accelerated Networking enabled and disabled.

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/hyperv/hyperv_net.h   |  2 ++
 drivers/net/hyperv/netvsc_drv.c   | 15 +++++++++++++++
 drivers/net/hyperv/rndis_filter.c | 13 +++++++------
 3 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h
index 234db693cefa4..70f7cb383228e 100644
--- a/drivers/net/hyperv/hyperv_net.h
+++ b/drivers/net/hyperv/hyperv_net.h
@@ -1166,6 +1166,8 @@ struct netvsc_device {
 	u32 max_chn;
 	u32 num_chn;
 
+	u32 netvsc_gso_max_size;
+
 	atomic_t open_chn;
 	struct work_struct subchan_work;
 	wait_queue_head_t subchan_open;
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index d6c4abfc3a28b..9c6501bf27bde 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -2461,6 +2461,21 @@ static int netvsc_vf_changed(struct net_device *vf_netdev, unsigned long event)
 	} else {
 		netdev_info(ndev, "Data path switched %s VF: %s\n",
 			    vf_is_up ? "to" : "from", vf_netdev->name);
+
+		/* In Azure, when accelerated networking in enabled, other NICs
+		 * like MANA, MLX, are configured as a bonded nic with
+		 * Netvsc(failover) NIC. For bonded NICs, the min of the max
+		 * pkt aggregate size of the members is propagated in the stack.
+		 * In order to allow these NICs (MANA/MLX) to use up to
+		 * GSO_MAX_SIZE gso packet size, we need to allow Netvsc NIC to
+		 * also support this in the guest.
+		 * This value is only increased for netvsc NIC when datapath is
+		 * switched over to the VF
+		 */
+		if (vf_is_up)
+			netif_set_tso_max_size(ndev, vf_netdev->tso_max_size);
+		else
+			netif_set_tso_max_size(ndev, netvsc_dev->netvsc_gso_max_size);
 	}
 
 	return NOTIFY_OK;
diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c
index c0ceeef4fcd81..82747dfacd70f 100644
--- a/drivers/net/hyperv/rndis_filter.c
+++ b/drivers/net/hyperv/rndis_filter.c
@@ -1356,9 +1356,10 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
 	struct net_device_context *net_device_ctx = netdev_priv(net);
 	struct ndis_offload hwcaps;
 	struct ndis_offload_params offloads;
-	unsigned int gso_max_size = GSO_LEGACY_MAX_SIZE;
 	int ret;
 
+	nvdev->netvsc_gso_max_size = GSO_LEGACY_MAX_SIZE;
+
 	/* Find HW offload capabilities */
 	ret = rndis_query_hwcaps(rndis_device, nvdev, &hwcaps);
 	if (ret != 0)
@@ -1390,8 +1391,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
 			offloads.lso_v2_ipv4 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED;
 			net->hw_features |= NETIF_F_TSO;
 
-			if (hwcaps.lsov2.ip4_maxsz < gso_max_size)
-				gso_max_size = hwcaps.lsov2.ip4_maxsz;
+			if (hwcaps.lsov2.ip4_maxsz < nvdev->netvsc_gso_max_size)
+				nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip4_maxsz;
 		}
 
 		if (hwcaps.csum.ip4_txcsum & NDIS_TXCSUM_CAP_UDP4) {
@@ -1411,8 +1412,8 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
 			offloads.lso_v2_ipv6 = NDIS_OFFLOAD_PARAMETERS_LSOV2_ENABLED;
 			net->hw_features |= NETIF_F_TSO6;
 
-			if (hwcaps.lsov2.ip6_maxsz < gso_max_size)
-				gso_max_size = hwcaps.lsov2.ip6_maxsz;
+			if (hwcaps.lsov2.ip6_maxsz < nvdev->netvsc_gso_max_size)
+				nvdev->netvsc_gso_max_size = hwcaps.lsov2.ip6_maxsz;
 		}
 
 		if (hwcaps.csum.ip6_txcsum & NDIS_TXCSUM_CAP_UDP6) {
@@ -1438,7 +1439,7 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device,
 	 */
 	net->features &= ~NETVSC_SUPPORTED_HW_FEATURES | net->hw_features;
 
-	netif_set_tso_max_size(net, gso_max_size);
+	netif_set_tso_max_size(net, nvdev->netvsc_gso_max_size);
 
 	ret = rndis_filter_set_offload_params(net, nvdev, &offloads);
 

From fd2a0c47fbae257bc7ff9c8d66aa7f039eb367b1 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 12 Feb 2025 21:23:12 +0100
Subject: [PATCH 0757/2753] can: c_can: Drop useless final probe failure
 message

Generic probe failure message is useless: does not give information what
failed and it duplicates messages provided by the core, e.g. from memory
allocation or platform_get_irq().  It also floods dmesg in case of
deferred probe, e.g. resulting from devm_clk_get().

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250212-syscon-phandle-args-can-v2-1-ac9a1253396b@linaro.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_platform.c | 26 ++++++++------------------
 1 file changed, 8 insertions(+), 18 deletions(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 399844809bbea..8968b6288ac7a 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -269,30 +269,22 @@ static int c_can_plat_probe(struct platform_device *pdev)
 
 	/* get the appropriate clk */
 	clk = devm_clk_get(&pdev->dev, NULL);
-	if (IS_ERR(clk)) {
-		ret = PTR_ERR(clk);
-		goto exit;
-	}
+	if (IS_ERR(clk))
+		return PTR_ERR(clk);
 
 	/* get the platform data */
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		ret = irq;
-		goto exit;
-	}
+	if (irq < 0)
+		return irq;
 
 	addr = devm_platform_get_and_ioremap_resource(pdev, 0, &mem);
-	if (IS_ERR(addr)) {
-		ret =  PTR_ERR(addr);
-		goto exit;
-	}
+	if (IS_ERR(addr))
+		return PTR_ERR(addr);
 
 	/* allocate the c_can device */
 	dev = alloc_c_can_dev(drvdata->msg_obj_num);
-	if (!dev) {
-		ret = -ENOMEM;
-		goto exit;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	priv = netdev_priv(dev);
 	switch (drvdata->id) {
@@ -396,8 +388,6 @@ static int c_can_plat_probe(struct platform_device *pdev)
 	pm_runtime_disable(priv->device);
 exit_free_device:
 	free_c_can_dev(dev);
-exit:
-	dev_err(&pdev->dev, "probe failed\n");
 
 	return ret;
 }

From 6c00b580d1c95ba9fe76c99307a16e5f47a214ba Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 12 Feb 2025 21:23:13 +0100
Subject: [PATCH 0758/2753] can: c_can: Simplify handling syscon error path

Use error handling block instead of open-coding it in one of probe
failure cases.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250212-syscon-phandle-args-can-v2-2-ac9a1253396b@linaro.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_platform.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 8968b6288ac7a..96d1225c41d0a 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -324,10 +324,8 @@ static int c_can_plat_probe(struct platform_device *pdev)
 			raminit->syscon = syscon_regmap_lookup_by_phandle(np,
 									  "syscon-raminit");
 			if (IS_ERR(raminit->syscon)) {
-				/* can fail with -EPROBE_DEFER */
 				ret = PTR_ERR(raminit->syscon);
-				free_c_can_dev(dev);
-				return ret;
+				goto exit_free_device;
 			}
 
 			if (of_property_read_u32_index(np, "syscon-raminit", 1,

From ab1bc2290fd8311d49b87c29f1eb123fcb581bee Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 12 Feb 2025 21:23:14 +0100
Subject: [PATCH 0759/2753] can: c_can: Use of_property_present() to test
 existence of DT property

of_property_read_bool() should be used only on boolean properties.

Cc: Rob Herring <robh@kernel.org>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250212-syscon-phandle-args-can-v2-3-ac9a1253396b@linaro.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_platform.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 96d1225c41d0a..1acceb097c17f 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -316,7 +316,7 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		/* Check if we need custom RAMINIT via syscon. Mostly for TI
 		 * platforms. Only supported with DT boot.
 		 */
-		if (np && of_property_read_bool(np, "syscon-raminit")) {
+		if (np && of_property_present(np, "syscon-raminit")) {
 			u32 id;
 			struct c_can_raminit *raminit = &priv->raminit_sys;
 

From 9f0f0345d0406cc17a764be4ce56e6c727cdf720 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 12 Feb 2025 21:23:15 +0100
Subject: [PATCH 0760/2753] can: c_can: Use
 syscon_regmap_lookup_by_phandle_args

Use syscon_regmap_lookup_by_phandle_args() which is a wrapper over
syscon_regmap_lookup_by_phandle() combined with getting the syscon
argument.  Except simpler code this annotates within one line that given
phandle has arguments, so grepping for code would be easier.

There is also no real benefit in printing errors on missing syscon
argument, because this is done just too late: runtime check on
static/build-time data.  Dtschema and Devicetree bindings offer the
static/build-time check for this already.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250212-syscon-phandle-args-can-v2-4-ac9a1253396b@linaro.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/c_can/c_can_platform.c | 21 ++++++---------------
 1 file changed, 6 insertions(+), 15 deletions(-)

diff --git a/drivers/net/can/c_can/c_can_platform.c b/drivers/net/can/c_can/c_can_platform.c
index 1acceb097c17f..19c86b94a40e4 100644
--- a/drivers/net/can/c_can/c_can_platform.c
+++ b/drivers/net/can/c_can/c_can_platform.c
@@ -317,30 +317,21 @@ static int c_can_plat_probe(struct platform_device *pdev)
 		 * platforms. Only supported with DT boot.
 		 */
 		if (np && of_property_present(np, "syscon-raminit")) {
+			unsigned int args[2];
 			u32 id;
 			struct c_can_raminit *raminit = &priv->raminit_sys;
 
 			ret = -EINVAL;
-			raminit->syscon = syscon_regmap_lookup_by_phandle(np,
-									  "syscon-raminit");
+			raminit->syscon = syscon_regmap_lookup_by_phandle_args(np,
+									       "syscon-raminit",
+									       2, args);
 			if (IS_ERR(raminit->syscon)) {
 				ret = PTR_ERR(raminit->syscon);
 				goto exit_free_device;
 			}
 
-			if (of_property_read_u32_index(np, "syscon-raminit", 1,
-						       &raminit->reg)) {
-				dev_err(&pdev->dev,
-					"couldn't get the RAMINIT reg. offset!\n");
-				goto exit_free_device;
-			}
-
-			if (of_property_read_u32_index(np, "syscon-raminit", 2,
-						       &id)) {
-				dev_err(&pdev->dev,
-					"couldn't get the CAN instance ID\n");
-				goto exit_free_device;
-			}
+			raminit->reg = args[0];
+			id = args[1];
 
 			if (id >= drvdata->raminit_num) {
 				dev_err(&pdev->dev,

From 51723790b718800014dc905ace0f8ffacd07f31e Mon Sep 17 00:00:00 2001
From: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Date: Mon, 13 Jan 2025 14:07:02 +0200
Subject: [PATCH 0761/2753] dt-bindings: can: fsl,flexcan: add S32G2/S32G3 SoC
 support

Add S32G2/S32G3 SoCs compatible strings.

A particularity for these SoCs is the presence of separate interrupts for
state change, bus errors, MBs 0-7 and MBs 8-127 respectively.

Increase maxItems of 'interrupts' to 4 for S32G based SoCs and keep the
same restriction for other SoCs.

Also, as part of this commit, move the 'allOf' after the required
properties to make the documentation easier to read.

Signed-off-by: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://patch.msgid.link/20250113120704.522307-2-ciprianmarian.costea@oss.nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../bindings/net/can/fsl,flexcan.yaml         | 44 +++++++++++++++++--
 1 file changed, 40 insertions(+), 4 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
index 97dd1a7c5ed26..73252fe56fe6c 100644
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -10,9 +10,6 @@ title:
 maintainers:
   - Marc Kleine-Budde <mkl@pengutronix.de>
 
-allOf:
-  - $ref: can-controller.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -28,6 +25,7 @@ properties:
           - fsl,vf610-flexcan
           - fsl,ls1021ar2-flexcan
           - fsl,lx2160ar1-flexcan
+          - nxp,s32g2-flexcan
       - items:
           - enum:
               - fsl,imx53-flexcan
@@ -43,12 +41,21 @@ properties:
           - enum:
               - fsl,ls1028ar1-flexcan
           - const: fsl,lx2160ar1-flexcan
+      - items:
+          - enum:
+              - nxp,s32g3-flexcan
+          - const: nxp,s32g2-flexcan
 
   reg:
     maxItems: 1
 
   interrupts:
-    maxItems: 1
+    minItems: 1
+    maxItems: 4
+
+  interrupt-names:
+    minItems: 1
+    maxItems: 4
 
   clocks:
     maxItems: 2
@@ -136,6 +143,35 @@ required:
   - reg
   - interrupts
 
+allOf:
+  - $ref: can-controller.yaml#
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: nxp,s32g2-flexcan
+    then:
+      properties:
+        interrupts:
+          items:
+            - description: Message Buffer interrupt for mailboxes 0-7 and Enhanced RX FIFO
+            - description: Device state change
+            - description: Bus Error detection
+            - description: Message Buffer interrupt for mailboxes 8-127
+        interrupt-names:
+          items:
+            - const: mb-0
+            - const: state
+            - const: berr
+            - const: mb-1
+      required:
+        - interrupt-names
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+        interrupt-names: false
+
 additionalProperties: false
 
 examples:

From 8c652cf030a769fbfc73cfc280ed3f1656343c35 Mon Sep 17 00:00:00 2001
From: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Date: Mon, 13 Jan 2025 14:07:03 +0200
Subject: [PATCH 0762/2753] can: flexcan: Add quirk to handle separate
 interrupt lines for mailboxes

Introduce 'FLEXCAN_QUIRK_SECONDARY_MB_IRQ' quirk to handle a FlexCAN
hardware module integration particularity where two ranges of mailboxes
are controlled by separate hardware interrupt lines.
The same 'flexcan_irq' handler is used for both separate mailbox interrupt
lines, with no other changes.

Signed-off-by: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250113120704.522307-3-ciprianmarian.costea@oss.nxp.com
[mkl: flexcan_open(): change order and free irq_secondary_mb first]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 24 +++++++++++++++++++++++-
 drivers/net/can/flexcan/flexcan.h      |  5 +++++
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index ac1a860986df6..a8a4cc4c064d9 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -1762,14 +1762,25 @@ static int flexcan_open(struct net_device *dev)
 			goto out_free_irq_boff;
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		err = request_irq(priv->irq_secondary_mb,
+				  flexcan_irq, IRQF_SHARED, dev->name, dev);
+		if (err)
+			goto out_free_irq_err;
+	}
+
 	flexcan_chip_interrupts_enable(dev);
 
 	netif_start_queue(dev);
 
 	return 0;
 
+ out_free_irq_err:
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_err, dev);
  out_free_irq_boff:
-	free_irq(priv->irq_boff, dev);
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3)
+		free_irq(priv->irq_boff, dev);
  out_free_irq:
 	free_irq(dev->irq, dev);
  out_can_rx_offload_disable:
@@ -1794,6 +1805,9 @@ static int flexcan_close(struct net_device *dev)
 	netif_stop_queue(dev);
 	flexcan_chip_interrupts_disable(dev);
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ)
+		free_irq(priv->irq_secondary_mb, dev);
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		free_irq(priv->irq_err, dev);
 		free_irq(priv->irq_boff, dev);
@@ -2187,6 +2201,14 @@ static int flexcan_probe(struct platform_device *pdev)
 		}
 	}
 
+	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SECONDARY_MB_IRQ) {
+		priv->irq_secondary_mb = platform_get_irq_byname(pdev, "mb-1");
+		if (priv->irq_secondary_mb < 0) {
+			err = priv->irq_secondary_mb;
+			goto failed_platform_get_irq;
+		}
+	}
+
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_SUPPORT_FD) {
 		priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD |
 			CAN_CTRLMODE_FD_NON_ISO;
diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h
index 4933d8c7439e6..2cf886618c962 100644
--- a/drivers/net/can/flexcan/flexcan.h
+++ b/drivers/net/can/flexcan/flexcan.h
@@ -70,6 +70,10 @@
 #define FLEXCAN_QUIRK_SUPPORT_RX_FIFO BIT(16)
 /* Setup stop mode with ATF SCMI protocol to support wakeup */
 #define FLEXCAN_QUIRK_SETUP_STOP_MODE_SCMI BIT(17)
+/* Device has two separate interrupt lines for two mailbox ranges, which
+ * both need to have an interrupt handler registered.
+ */
+#define FLEXCAN_QUIRK_SECONDARY_MB_IRQ	BIT(18)
 
 struct flexcan_devtype_data {
 	u32 quirks;		/* quirks needed for different IP cores */
@@ -107,6 +111,7 @@ struct flexcan_priv {
 
 	int irq_boff;
 	int irq_err;
+	int irq_secondary_mb;
 
 	/* IPC handle when setup stop mode by System Controller firmware(scfw) */
 	struct imx_sc_ipc *sc_ipc_handle;

From 8503a4b1a24d32e95f3a233062e8f1dc0b2052bd Mon Sep 17 00:00:00 2001
From: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Date: Mon, 13 Jan 2025 14:07:04 +0200
Subject: [PATCH 0763/2753] can: flexcan: add NXP S32G2/S32G3 SoC support

Add device type data for S32G2/S32G3 SoC.

FlexCAN module from S32G2/S32G3 is similar with i.MX SoCs, but interrupt
management is different.

On S32G2/S32G3 SoC, there are separate interrupts for state change, bus
errors, Mailboxes 0-7 and Mailboxes 8-127 respectively.
In order to handle this FlexCAN hardware particularity, first reuse the
'FLEXCAN_QUIRK_NR_IRQ_3' quirk provided by mcf5441x's irq handling
support. Secondly, use the newly introduced
'FLEXCAN_QUIRK_SECONDARY_MB_IRQ' quirk which handles the case where two
separate mailbox ranges are controlled by independent hardware interrupt
lines.

Signed-off-by: Ciprian Marian Costea <ciprianmarian.costea@oss.nxp.com>
Link: https://patch.msgid.link/20250113120704.522307-4-ciprianmarian.costea@oss.nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index a8a4cc4c064d9..b347a1c93536d 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -386,6 +386,16 @@ static const struct flexcan_devtype_data fsl_lx2160a_r1_devtype_data = {
 		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR,
 };
 
+static const struct flexcan_devtype_data nxp_s32g2_devtype_data = {
+	.quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS |
+		FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE |
+		FLEXCAN_QUIRK_USE_RX_MAILBOX | FLEXCAN_QUIRK_SUPPORT_FD |
+		FLEXCAN_QUIRK_SUPPORT_ECC | FLEXCAN_QUIRK_NR_IRQ_3 |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX |
+		FLEXCAN_QUIRK_SUPPORT_RX_MAILBOX_RTR |
+		FLEXCAN_QUIRK_SECONDARY_MB_IRQ,
+};
+
 static const struct can_bittiming_const flexcan_bittiming_const = {
 	.name = DRV_NAME,
 	.tseg1_min = 4,
@@ -2055,6 +2065,7 @@ static const struct of_device_id flexcan_of_match[] = {
 	{ .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, },
 	{ .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, },
 	{ .compatible = "fsl,lx2160ar1-flexcan", .data = &fsl_lx2160a_r1_devtype_data, },
+	{ .compatible = "nxp,s32g2-flexcan", .data = &nxp_s32g2_devtype_data, },
 	{ /* sentinel */ },
 };
 MODULE_DEVICE_TABLE(of, flexcan_of_match);

From bcb13d33221d8ac340346c77a6fa8770495a5809 Mon Sep 17 00:00:00 2001
From: Ruffalo Lavoisier <ruffalolavoisier@gmail.com>
Date: Wed, 20 Nov 2024 13:40:13 +0900
Subject: [PATCH 0764/2753] dt-binding: can: mcp251xfd: remove duplicate word

Remove duplicate word 'to' from microchip,rx-int-gpios description.

Signed-off-by: Ruffalo Lavoisier <ruffalolavoisier@gmail.com>
Acked-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20241120044014.92375-1-RuffaloLavoisier@gmail.com
[mkl: rephrase subject and patch description]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../devicetree/bindings/net/can/microchip,mcp251xfd.yaml        | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
index 2a98b26630cb1..c155c9c6db392 100644
--- a/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
+++ b/Documentation/devicetree/bindings/net/can/microchip,mcp251xfd.yaml
@@ -40,7 +40,7 @@ properties:
 
   microchip,rx-int-gpios:
     description:
-      GPIO phandle of GPIO connected to to INT1 pin of the MCP251XFD, which
+      GPIO phandle of GPIO connected to INT1 pin of the MCP251XFD, which
       signals a pending RX interrupt.
     maxItems: 1
 

From 6b89d89f2147dddd0da4e08e88840553c2d3c5a6 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Sun, 13 Oct 2024 20:17:15 +0200
Subject: [PATCH 0765/2753] can: j1939: Extend stack documentation with buffer
 size behavior

Extend the J1939 stack documentation to include information about how
buffer sizes influence stack behavior, detailing handling of simple
sessions, TP, and ETP transfers.

Additionally, describe various setsockopt(2) options, including their
usage  and potential error values that can be returned by the stack.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20241013181715.3488980-1-o.rempel@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/networking/j1939.rst | 675 +++++++++++++++++++++++++++++
 1 file changed, 675 insertions(+)

diff --git a/Documentation/networking/j1939.rst b/Documentation/networking/j1939.rst
index 544bad175aae2..45f02efe3df5f 100644
--- a/Documentation/networking/j1939.rst
+++ b/Documentation/networking/j1939.rst
@@ -66,6 +66,90 @@ the library exclusively, or by the in-kernel system exclusively.
 J1939 concepts
 ==============
 
+Data Sent to the J1939 Stack
+----------------------------
+
+The data buffers sent to the J1939 stack from user space are not CAN frames
+themselves. Instead, they are payloads that the J1939 stack converts into
+proper CAN frames based on the size of the buffer and the type of transfer. The
+size of the buffer influences how the stack processes the data and determines
+the internal code path used for the transfer.
+
+**Handling of Different Buffer Sizes:**
+
+- **Buffers with a size of 8 bytes or less:**
+
+  - These are handled as simple sessions internally within the stack.
+
+  - The stack converts the buffer directly into a single CAN frame without
+    fragmentation.
+
+  - This type of transfer does not require an actual client (receiver) on the
+    receiving side.
+
+- **Buffers up to 1785 bytes:**
+
+  - These are automatically handled as J1939 Transport Protocol (TP) transfers.
+
+  - Internally, the stack splits the buffer into multiple 8-byte CAN frames.
+
+  - TP transfers can be unicast or broadcast.
+
+  - **Broadcast TP:** Does not require a receiver on the other side and can be
+    used in broadcast scenarios.
+
+  - **Unicast TP:** Requires an active receiver (client) on the other side to
+    acknowledge the transfer.
+
+- **Buffers from 1786 bytes up to 111 MiB:**
+
+  - These are handled as ISO 11783 Extended Transport Protocol (ETP) transfers.
+
+  - ETP transfers are used for larger payloads and are split into multiple CAN
+    frames internally.
+
+  - **ETP transfers (unicast):** Require a receiver on the other side to
+    process the incoming data and acknowledge each step of the transfer.
+
+  - ETP transfers cannot be broadcast like TP transfers, and always require a
+    receiver for operation.
+
+**Non-Blocking Operation with `MSG_DONTWAIT`:**
+
+The J1939 stack supports non-blocking operation when used in combination with
+the `MSG_DONTWAIT` flag. In this mode, the stack attempts to take as much data
+as the available memory for the socket allows. It returns the amount of data
+that was successfully taken, and it is the responsibility of user space to
+monitor this value and handle partial transfers.
+
+- If the stack cannot take the entire buffer, it returns the number of bytes
+  successfully taken, and user space should handle the remainder.
+
+- **Error handling:** When using `MSG_DONTWAIT`, the user must rely on the
+  error queue to detect transfer errors. See the **SO_J1939_ERRQUEUE** section
+  for details on how to subscribe to error notifications. Without the error
+  queue, there is no other way for user space to be notified of transfer errors
+  during non-blocking operations.
+
+**Behavior and Requirements:**
+
+- **Simple transfers (<= 8 bytes):** Do not require a receiver on the other
+  side, making them easy to send without needing address claiming or
+  coordination with a destination.
+
+- **Unicast TP/ETP:** Requires a receiver on the other side to complete the
+  transfer. The receiver must acknowledge the transfer for the session to
+  proceed successfully.
+
+- **Broadcast TP:** Allows sending data without a receiver, but only works for
+  TP transfers. ETP cannot be broadcast and always needs a receiving client.
+
+These different behaviors depend heavily on the size of the buffer provided to
+the stack, and the appropriate transport mechanism (TP or ETP) is selected
+based on the payload size. The stack automatically manages the fragmentation
+and reassembly of large payloads and ensures that the correct CAN frames are
+generated and transmitted for each session.
+
 PGN
 ---
 
@@ -338,6 +422,459 @@ with ``cmsg_level == SOL_J1939 && cmsg_type == SCM_J1939_DEST_ADDR``,
 		}
 	}
 
+setsockopt(2)
+^^^^^^^^^^^^^
+
+The ``setsockopt(2)`` function is used to configure various socket-level
+options for J1939 communication. The following options are supported:
+
+``SO_J1939_FILTER``
+~~~~~~~~~~~~~~~~~~~
+
+The ``SO_J1939_FILTER`` option is essential when the default behavior of
+``bind(2)`` and ``connect(2)`` is insufficient for specific use cases. By
+default, ``bind(2)`` and ``connect(2)`` allow a socket to be associated with a
+single unicast or broadcast address. However, there are scenarios where finer
+control over the incoming messages is required, such as filtering by Parameter
+Group Number (PGN) rather than by addresses.
+
+For example, in a system where multiple types of J1939 messages are being
+transmitted, a process might only be interested in a subset of those messages,
+such as specific PGNs, and not want to receive all messages destined for its
+address or broadcast to the bus.
+
+By applying the ``SO_J1939_FILTER`` option, you can filter messages based on:
+
+- **Source Address (SA)**: Filter messages coming from specific source
+  addresses.
+
+- **Source Name**: Filter messages coming from ECUs with specific NAME
+  identifiers.
+
+- **Parameter Group Number (PGN)**: Focus on receiving messages with specific
+  PGNs, filtering out irrelevant ones.
+
+This filtering mechanism is particularly useful when:
+
+- You want to receive a subset of messages based on their PGNs, even if the
+  address is the same.
+
+- You need to handle both broadcast and unicast messages but only care about
+  certain message types or parameters.
+
+- The ``bind(2)`` and ``connect(2)`` functions only allow binding to a single
+  address, which might not be sufficient if the process needs to handle multiple
+  PGNs but does not want to open multiple sockets.
+
+To remove existing filters, you can pass ``optval == NULL`` or ``optlen == 0``
+to ``setsockopt(2)``. This will clear all currently set filters. If you want to
+**update** the set of filters, you must pass the updated filter set to
+``setsockopt(2)``, as the new filter set will **replace** the old one entirely.
+This behavior ensures that any previous filter configuration is discarded and
+only the new set is applied.
+
+Example of removing all filters:
+
+.. code-block:: c
+
+    setsockopt(sock, SOL_CAN_J1939, SO_J1939_FILTER, NULL, 0);
+
+**Maximum number of filters:** The maximum amount of filters that can be
+applied using ``SO_J1939_FILTER`` is defined by ``J1939_FILTER_MAX``, which is
+set to 512. This means you can configure up to 512 individual filters to match
+your specific filtering needs.
+
+Practical use case: **Monitoring Address Claiming**
+
+One practical use case is monitoring the J1939 address claiming process by
+filtering for specific PGNs related to address claiming. This allows a process
+to monitor and handle address claims without processing unrelated messages.
+
+Example:
+
+.. code-block:: c
+
+    struct j1939_filter filt[] = {
+        {
+            .pgn = J1939_PGN_ADDRESS_CLAIMED,
+            .pgn_mask = J1939_PGN_PDU1_MAX,
+        }, {
+            .pgn = J1939_PGN_REQUEST,
+            .pgn_mask = J1939_PGN_PDU1_MAX,
+        }, {
+            .pgn = J1939_PGN_ADDRESS_COMMANDED,
+            .pgn_mask = J1939_PGN_MAX,
+        },
+    };
+    setsockopt(sock, SOL_CAN_J1939, SO_J1939_FILTER, &filt, sizeof(filt));
+
+In this example, the socket will only receive messages with the PGNs related to
+address claiming: ``J1939_PGN_ADDRESS_CLAIMED``, ``J1939_PGN_REQUEST``, and
+``J1939_PGN_ADDRESS_COMMANDED``. This is particularly useful in scenarios where
+you want to monitor and process address claims without being overwhelmed by
+other traffic on the J1939 network.
+
+``SO_J1939_PROMISC``
+~~~~~~~~~~~~~~~~~~~~
+
+The ``SO_J1939_PROMISC`` option enables socket-level promiscuous mode. When
+this option is enabled, the socket will receive all J1939 traffic, regardless
+of any filters set by ``bind()`` or ``connect()``. This is analogous to
+enabling promiscuous mode for an Ethernet interface, where all traffic on the
+network segment is captured.
+
+However, **`SO_J1939_FILTER` has a higher priority** compared to
+``SO_J1939_PROMISC``. This means that even in promiscuous mode, you can reduce
+the number of packets received by applying specific filters with
+`SO_J1939_FILTER`. The filters will limit which packets are passed to the
+socket, allowing for more refined traffic selection while promiscuous mode is
+active.
+
+The acceptable value size for this option is ``sizeof(int)``, and the value is
+only differentiated between `0` and non-zero. A value of `0` disables
+promiscuous mode, while any non-zero value enables it.
+
+This combination can be useful for debugging or monitoring specific types of
+traffic while still capturing a broad set of messages.
+
+Example:
+
+.. code-block:: c
+
+    int value = 1;
+    setsockopt(sock, SOL_CAN_J1939, SO_J1939_PROMISC, &value, sizeof(value));
+
+In this example, setting ``value`` to any non-zero value (e.g., `1`) enables
+promiscuous mode, allowing the socket to receive all J1939 traffic on the
+network.
+
+``SO_BROADCAST``
+~~~~~~~~~~~~~~~~
+
+The ``SO_BROADCAST`` option enables the sending and receiving of broadcast
+messages. By default, broadcast messages are disabled for J1939 sockets. When
+this option is enabled, the socket will be allowed to send and receive
+broadcast packets on the J1939 network.
+
+Due to the nature of the CAN bus as a shared medium, all messages transmitted
+on the bus are visible to all participants. In the context of J1939,
+broadcasting refers to using a specific destination address field, where the
+destination address is set to a value that indicates the message is intended
+for all participants (usually a global address such as 0xFF). Enabling the
+broadcast option allows the socket to send and receive such broadcast messages.
+
+The acceptable value size for this option is ``sizeof(int)``, and the value is
+only differentiated between `0` and non-zero. A value of `0` disables the
+ability to send and receive broadcast messages, while any non-zero value
+enables it.
+
+Example:
+
+.. code-block:: c
+
+    int value = 1;
+    setsockopt(sock, SOL_SOCKET, SO_BROADCAST, &value, sizeof(value));
+
+In this example, setting ``value`` to any non-zero value (e.g., `1`) enables
+the socket to send and receive broadcast messages.
+
+``SO_J1939_SEND_PRIO``
+~~~~~~~~~~~~~~~~~~~~~~
+
+The ``SO_J1939_SEND_PRIO`` option sets the priority of outgoing J1939 messages
+for the socket. In J1939, messages can have different priorities, and lower
+numerical values indicate higher priority. This option allows the user to
+control the priority of messages sent from the socket by adjusting the priority
+bits in the CAN identifier.
+
+The acceptable value **size** for this option is ``sizeof(int)``, and the value
+is expected to be in the range of 0 to 7, where `0` is the highest priority,
+and `7` is the lowest. By default, the priority is set to `6` if this option is
+not explicitly configured.
+
+Note that the priority values `0` and `1` can only be set if the process has
+the `CAP_NET_ADMIN` capability. These are reserved for high-priority traffic
+and require administrative privileges.
+
+Example:
+
+.. code-block:: c
+
+    int prio = 3;  // Priority value between 0 (highest) and 7 (lowest)
+    setsockopt(sock, SOL_CAN_J1939, SO_J1939_SEND_PRIO, &prio, sizeof(prio));
+
+In this example, the priority is set to `3`, meaning the outgoing messages will
+be sent with a moderate priority level.
+
+``SO_J1939_ERRQUEUE``
+~~~~~~~~~~~~~~~~~~~~~
+
+The ``SO_J1939_ERRQUEUE`` option enables the socket to receive error messages
+from the error queue, providing diagnostic information about transmission
+failures, protocol violations, or other issues that occur during J1939
+communication. Once this option is set, user space is required to handle
+``MSG_ERRQUEUE`` messages.
+
+Setting ``SO_J1939_ERRQUEUE`` to ``0`` will purge any currently present error
+messages in the error queue. When enabled, error messages can be retrieved
+using the ``recvmsg(2)`` system call.
+
+When subscribing to the error queue, the following error events can be
+accessed:
+
+- **``J1939_EE_INFO_TX_ABORT``**: Transmission abort errors.
+- **``J1939_EE_INFO_RX_RTS``**: Reception of RTS (Request to Send) control
+  frames.
+- **``J1939_EE_INFO_RX_DPO``**: Reception of data packets with Data Page Offset
+  (DPO).
+- **``J1939_EE_INFO_RX_ABORT``**: Reception abort errors.
+
+The error queue can be used to correlate errors with specific message transfer
+sessions using the session ID (``tskey``). The session ID is assigned via the
+``SOF_TIMESTAMPING_OPT_ID`` flag, which is set by enabling the
+``SO_TIMESTAMPING`` option.
+
+If ``SO_J1939_ERRQUEUE`` is activated, the user is required to pull messages
+from the error queue, meaning that using plain ``recv(2)`` is not sufficient
+anymore. The user must use ``recvmsg(2)`` with appropriate flags to handle
+error messages. Failure to do so can result in the socket becoming blocked with
+unprocessed error messages in the queue.
+
+It is **recommended** that ``SO_J1939_ERRQUEUE`` be used in combination with
+``SO_TIMESTAMPING`` in most cases. This enables proper error handling along
+with session tracking and timestamping, providing a more detailed analysis of
+message transfers and errors.
+
+The acceptable value **size** for this option is ``sizeof(int)``, and the value
+is only differentiated between ``0`` and non-zero. A value of ``0`` disables
+error queue reception and purges any existing error messages, while any
+non-zero value enables it.
+
+Example:
+
+.. code-block:: c
+
+    int enable = 1;  // Enable error queue reception
+    setsockopt(sock, SOL_CAN_J1939, SO_J1939_ERRQUEUE, &enable, sizeof(enable));
+
+    // Enable timestamping with session tracking via tskey
+    int timestamping = SOF_TIMESTAMPING_OPT_ID | SOF_TIMESTAMPING_TX_ACK |
+                       SOF_TIMESTAMPING_TX_SCHED |
+                       SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_OPT_CMSG;
+    setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &timestamping,
+               sizeof(timestamping));
+
+When enabled, error messages can be retrieved using ``recvmsg(2)``. By
+combining ``SO_J1939_ERRQUEUE`` with ``SO_TIMESTAMPING`` (with
+``SOF_TIMESTAMPING_OPT_ID`` and ``SOF_TIMESTAMPING_OPT_CMSG`` enabled), the
+user can track message transfers, retrieve precise timestamps, and correlate
+errors with specific sessions.
+
+For more information on enabling timestamps and session tracking, refer to the
+`SO_TIMESTAMPING` section.
+
+``SO_TIMESTAMPING``
+~~~~~~~~~~~~~~~~~~~
+
+The ``SO_TIMESTAMPING`` option allows the socket to receive timestamps for
+various events related to message transmissions and receptions in J1939. This
+option is often used in combination with ``SO_J1939_ERRQUEUE`` to provide
+detailed diagnostic information, session tracking, and precise timing data for
+message transfers.
+
+In J1939, all payloads provided by user space, regardless of size, are
+processed by the kernel as **sessions**. This includes both single-frame
+messages (up to 8 bytes) and multi-frame protocols such as the Transport
+Protocol (TP) and Extended Transport Protocol (ETP). Even for small,
+single-frame messages, the kernel creates a session to manage the transmission
+and reception. The concept of sessions allows the kernel to manage various
+aspects of the protocol, such as reassembling multi-frame messages and tracking
+the status of transmissions.
+
+When receiving extended error messages from the error queue, the error
+information is delivered through a `struct sock_extended_err`, accessible via
+the control message (``cmsg``) retrieved using the ``recvmsg(2)`` system call.
+
+There are two typical origins for the extended error messages in J1939:
+
+1. ``serr->ee_origin == SO_EE_ORIGIN_TIMESTAMPING``:
+
+   In this case, the `serr->ee_info` field will contain one of the following
+   timestamp types:
+
+   - ``SCM_TSTAMP_SCHED``: This timestamp is valid for Extended Transport
+     Protocol (ETP) transfers and simple transfers (8 bytes or less). It
+     indicates when a message or set of frames has been scheduled for
+     transmission.
+
+     - For simple transfers (8 bytes or less), it marks the point when the
+       message is queued and ready to be sent onto the CAN bus.
+
+     - For ETP transfers, it is sent after receiving a CTS (Clear to Send)
+       frame on the sender side, indicating that a new set of frames has been
+       scheduled for transmission.
+
+     - The Transport Protocol (TP) case is currently not implemented for this
+       timestamp.
+
+     - On the receiver side, the counterpart to this event for ETP is
+       represented by the ``J1939_EE_INFO_RX_DPO`` message, which indicates the
+       reception of a Data Page Offset (DPO) control frame.
+
+   - ``SCM_TSTAMP_ACK``: This timestamp indicates the acknowledgment of the
+     message or session.
+
+     - For simple transfers (8 bytes or less), it marks when the message has
+       been sent and an echo confirmation has been received from the CAN
+       controller, indicating that the frame was transmitted onto the bus.
+
+     - For multi-frame transfers (TP or ETP), it signifies that the entire
+       session has been acknowledged, typically after receiving the End of
+       Message Acknowledgment (EOMA) packet.
+
+2. ``serr->ee_origin == SO_EE_ORIGIN_LOCAL``:
+
+   In this case, the `serr->ee_info` field will contain one of the following
+   J1939 stack-specific message types:
+
+   - ``J1939_EE_INFO_TX_ABORT``: This message indicates that the transmission
+     of a message or session was aborted. The cause of the abort can come from
+     various sources:
+
+     - **CAN stack failure**: The J1939 stack was unable to pass the frame to
+       the CAN framework for transmission.
+
+     - **Echo failure**: The J1939 stack did not receive an echo confirmation
+       from the CAN controller, meaning the frame may not have been successfully
+       transmitted to the CAN bus.
+
+     - **Protocol-level issues**: For multi-frame transfers (TP/ETP), this
+       could include protocol-related errors, such as an abort signaled by the
+       receiver or a timeout at the protocol level, which causes the session to
+       terminate prematurely.
+
+     - The corresponding error code is stored in ``serr->ee_data``
+       (``session->err`` on kernel side), providing additional details about
+       the specific reason for the abort.
+
+   - ``J1939_EE_INFO_RX_RTS``: This message indicates that the J1939 stack has
+     received a Request to Send (RTS) control frame, signaling the start of a
+     multi-frame transfer using the Transport Protocol (TP) or Extended
+     Transport Protocol (ETP).
+
+     - It informs the receiver that the sender is ready to transmit a
+       multi-frame message and includes details about the total message size
+       and the number of frames to be sent.
+
+     - Statistics such as ``J1939_NLA_TOTAL_SIZE``, ``J1939_NLA_PGN``,
+       ``J1939_NLA_SRC_NAME``, and ``J1939_NLA_DEST_NAME`` are provided along
+       with the ``J1939_EE_INFO_RX_RTS`` message, giving detailed information
+       about the incoming transfer.
+
+   - ``J1939_EE_INFO_RX_DPO``: This message indicates that the J1939 stack has
+     received a Data Page Offset (DPO) control frame, which is part of the
+     Extended Transport Protocol (ETP).
+
+     - The DPO frame signals the continuation of an ETP multi-frame message by
+       indicating the offset position in the data being transferred. It helps
+       the receiver manage large data sets by identifying which portion of the
+       message is being received.
+
+     - It is typically paired with a corresponding ``SCM_TSTAMP_SCHED`` event
+       on the sender side, which indicates when the next set of frames is
+       scheduled for transmission.
+
+     - This event includes statistics such as ``J1939_NLA_BYTES_ACKED``, which
+       tracks the number of bytes acknowledged up to that point in the session.
+
+   - ``J1939_EE_INFO_RX_ABORT``: This message indicates that the reception of a
+     multi-frame message (Transport Protocol or Extended Transport Protocol) has
+     been aborted.
+
+     - The abort can be triggered by protocol-level errors such as timeouts, an
+       unexpected frame, or a specific abort request from the sender.
+
+     - This message signals that the receiver cannot continue processing the
+       transfer, and the session is terminated.
+
+     - The corresponding error code is stored in ``serr->ee_data``
+       (``session->err`` on kernel side ), providing further details about the
+       reason for the abort, such as protocol violations or timeouts.
+
+     - After receiving this message, the receiver discards the partially received
+       frames, and the multi-frame session is considered incomplete.
+
+In both cases, if ``SOF_TIMESTAMPING_OPT_ID`` is enabled, ``serr->ee_data``
+will be set to the session’s unique identifier (``session->tskey``). This
+allows user space to track message transfers by their session identifier across
+multiple frames or stages.
+
+In all other cases, ``serr->ee_errno`` will be set to ``ENOMSG``, except for
+the ``J1939_EE_INFO_TX_ABORT`` and ``J1939_EE_INFO_RX_ABORT`` cases, where the
+kernel sets ``serr->ee_data`` to the error stored in ``session->err``.  All
+protocol-specific errors are converted to standard kernel error values and
+stored in ``session->err``. These error values are unified across system calls
+and ``serr->ee_errno``.  Some of the known error values are described in the
+`Error Codes in the J1939 Stack` section.
+
+When the `J1939_EE_INFO_RX_RTS` message is provided, it will include the
+following statistics for multi-frame messages (TP and ETP):
+
+  - ``J1939_NLA_TOTAL_SIZE``: Total size of the message in the session.
+  - ``J1939_NLA_PGN``: Parameter Group Number (PGN) identifying the message type.
+  - ``J1939_NLA_SRC_NAME``: 64-bit name of the source ECU.
+  - ``J1939_NLA_DEST_NAME``: 64-bit name of the destination ECU.
+  - ``J1939_NLA_SRC_ADDR``: 8-bit source address of the sending ECU.
+  - ``J1939_NLA_DEST_ADDR``: 8-bit destination address of the receiving ECU.
+
+- For other messages (including single-frame messages), only the following
+  statistic is included:
+
+  - ``J1939_NLA_BYTES_ACKED``: Number of bytes successfully acknowledged in the
+    session.
+
+The key flags for ``SO_TIMESTAMPING`` include:
+
+- ``SOF_TIMESTAMPING_OPT_ID``: Enables the use of a unique session identifier
+  (``tskey``) for each transfer. This identifier helps track message transfers
+  and errors as distinct sessions in user space. When this option is enabled,
+  ``serr->ee_data`` will be set to ``session->tskey``.
+
+- ``SOF_TIMESTAMPING_OPT_CMSG``: Sends timestamp information through control
+  messages (``struct scm_timestamping``), allowing the application to retrieve
+  timestamps alongside the data.
+
+- ``SOF_TIMESTAMPING_TX_SCHED``: Provides the timestamp for when a message is
+  scheduled for transmission (``SCM_TSTAMP_SCHED``).
+
+- ``SOF_TIMESTAMPING_TX_ACK``: Provides the timestamp for when a message
+  transmission is fully acknowledged (``SCM_TSTAMP_ACK``).
+
+- ``SOF_TIMESTAMPING_RX_SOFTWARE``: Provides timestamps for reception-related
+  events (e.g., ``J1939_EE_INFO_RX_RTS``, ``J1939_EE_INFO_RX_DPO``,
+  ``J1939_EE_INFO_RX_ABORT``).
+
+These flags enable detailed monitoring of message lifecycles, including
+transmission scheduling, acknowledgments, reception timestamps, and gathering
+detailed statistics about the communication session, especially for multi-frame
+payloads like TP and ETP.
+
+Example:
+
+.. code-block:: c
+
+    // Enable timestamping with various options, including session tracking and
+    // statistics
+    int sock_opt = SOF_TIMESTAMPING_OPT_CMSG |
+                   SOF_TIMESTAMPING_TX_ACK |
+                   SOF_TIMESTAMPING_TX_SCHED |
+                   SOF_TIMESTAMPING_OPT_ID |
+                   SOF_TIMESTAMPING_RX_SOFTWARE;
+
+    setsockopt(sock, SOL_SOCKET, SO_TIMESTAMPING, &sock_opt, sizeof(sock_opt));
+
+
+
 Dynamic Addressing
 ------------------
 
@@ -458,3 +995,141 @@ Send:
 	};
 
 	sendto(sock, dat, sizeof(dat), 0, (const struct sockaddr *)&saddr, sizeof(saddr));
+
+
+Error Codes in the J1939 Stack
+------------------------------
+
+This section lists all potential kernel error codes that can be exposed to user
+space when interacting with the J1939 stack. It includes both standard error
+codes and those derived from protocol-specific abort codes.
+
+- ``EAGAIN``: Operation would block; retry may succeed. One common reason is
+  that an active TP or ETP session exists, and an attempt was made to start a
+  new overlapping TP or ETP session between the same peers.
+
+- ``ENETDOWN``: Network is down. This occurs when the CAN interface is switched
+  to the "down" state.
+
+- ``ENOBUFS``: No buffer space available. This error occurs when the CAN
+  interface's transmit (TX) queue is full, and no more messages can be queued.
+
+- ``EOVERFLOW``: Value too large for defined data type. In J1939, this can
+  happen if the requested data lies outside of the queued buffer. For example,
+  if a CTS (Clear to Send) requests an offset not available in the kernel buffer
+  because user space did not provide enough data.
+
+- ``EBUSY``: Device or resource is busy. For example, this occurs if an
+  identical session is already active and the stack is unable to recover from
+  the condition.
+
+- ``EACCES``: Permission denied. This error can occur, for example, when
+  attempting to send broadcast messages, but the socket is not configured with
+  ``SO_BROADCAST``.
+
+- ``EADDRNOTAVAIL``: Address not available. This error occurs in cases such as:
+
+  - When attempting to use ``getsockname(2)`` to retrieve the peer's address,
+    but the socket is not connected.
+
+  - When trying to send data to or from a NAME, but address claiming for the
+    NAME was not performed or detected by the stack.
+
+- ``EBADFD``: File descriptor in bad state. This error can occur if:
+
+  - Attempting to send data to an unbound socket.
+
+  - The socket is bound but has no source name, and the source address is
+    ``J1939_NO_ADDR``.
+
+  - The ``can_ifindex`` is incorrect.
+
+- ``EFAULT``: Bad address. Occurs mostly when the stack can't copy from or to a
+  sockptr, when there is insufficient data from user space, or when the buffer
+  provided by user space is not large enough for the requested data.
+
+- ``EINTR``: A signal occurred before any data was transmitted; see ``signal(7)``.
+
+- ``EINVAL``: Invalid argument passed. For example:
+
+  - ``msg->msg_namelen`` is less than ``J1939_MIN_NAMELEN``.
+
+  - ``addr->can_family`` is not equal to ``AF_CAN``.
+
+  - An incorrect PGN was provided.
+
+- ``ENODEV``: No such device. This happens when the CAN network device cannot
+  be found for the provided ``can_ifindex`` or if ``can_ifindex`` is 0.
+
+- ``ENOMEM``: Out of memory. Typically related to issues with memory allocation
+  in the stack.
+
+- ``ENOPROTOOPT``: Protocol not available. This can occur when using
+  ``getsockopt(2)`` or ``setsockopt(2)`` if the requested socket option is not
+  available.
+
+- ``EDESTADDRREQ``: Destination address required. This error occurs:
+
+  - In the case of ``connect(2)``, if the ``struct sockaddr *uaddr`` is ``NULL``.
+
+  - In the case of ``send*(2)``, if there is an attempt to send an ETP message
+    to a broadcast address.
+
+- ``EDOM``: Argument out of domain. This error may happen if attempting to send
+  a TP or ETP message to a PGN that is reserved for control PGNs for TP or ETP
+  operations.
+
+- ``EIO``: I/O error. This can occur if the amount of data provided to the
+  socket for a TP or ETP session does not match the announced amount of data for
+  the session.
+
+- ``ENOENT``: No such file or directory. This can happen when the stack
+  attempts to transfer CTS or EOMA but cannot find a matching receiving socket
+  anymore.
+
+- ``ENOIOCTLCMD``: No ioctls are available for the socket layer.
+
+- ``EPERM``: Operation not permitted. For example, this can occur if a
+  requested action requires ``CAP_NET_ADMIN`` privileges.
+
+- ``ENETUNREACH``: Network unreachable. Most likely, this occurs when frames
+  cannot be transmitted to the CAN bus.
+
+- ``ETIME``: Timer expired. This can happen if a timeout occurs while
+  attempting to send a simple message, for example, when an echo message from
+  the controller is not received.
+
+- ``EPROTO``: Protocol error.
+
+  - Used for various protocol-level errors in J1939, including:
+
+    - Duplicate sequence number.
+
+    - Unexpected EDPO or ECTS packet.
+
+    - Invalid PGN or offset in EDPO/ECTS.
+
+    - Number of EDPO packets exceeded CTS allowance.
+
+    - Any other protocol-level error.
+
+- ``EMSGSIZE``: Message too long.
+
+- ``ENOMSG``: No message available.
+
+- ``EALREADY``: The ECU is already engaged in one or more connection-managed
+  sessions and cannot support another.
+
+- ``EHOSTUNREACH``: A timeout occurred, and the session was aborted.
+
+- ``EBADMSG``: CTS (Clear to Send) messages were received during an active data
+  transfer, causing an abort.
+
+- ``ENOTRECOVERABLE``: The maximum retransmission request limit was reached,
+  and the session cannot recover.
+
+- ``ENOTCONN``: An unexpected data transfer packet was received.
+
+- ``EILSEQ``: A bad sequence number was received, and the software could not
+  recover.
+

From e1b2c7e902f7254b5ec90b02b012852911f8b740 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Fri, 24 Jan 2025 15:23:47 +0100
Subject: [PATCH 0766/2753] can: canxl: support Remote Request Substitution bit
 access

The Remote Request Substitution bit is a dominant bit ("0") in the CAN
XL frame. As some CAN XL controllers support to access this bit a new
CANXL_RRS value has been defined for the canxl_frame.flags element.

Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Link: https://patch.msgid.link/20250124142347.7444-1-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 include/uapi/linux/can.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/include/uapi/linux/can.h b/include/uapi/linux/can.h
index e78cbd85ce7c7..42abf0679fb48 100644
--- a/include/uapi/linux/can.h
+++ b/include/uapi/linux/can.h
@@ -182,7 +182,7 @@ struct canfd_frame {
 /*
  * defined bits for canxl_frame.flags
  *
- * The canxl_frame.flags element contains two bits CANXL_XLF and CANXL_SEC
+ * The canxl_frame.flags element contains three bits CANXL_[XLF|SEC|RRS]
  * and shares the relative position of the struct can[fd]_frame.len element.
  * The CANXL_XLF bit ALWAYS needs to be set to indicate a valid CAN XL frame.
  * As a side effect setting this bit intentionally breaks the length checks
@@ -192,6 +192,7 @@ struct canfd_frame {
  */
 #define CANXL_XLF 0x80 /* mandatory CAN XL frame flag (must always be set!) */
 #define CANXL_SEC 0x01 /* Simple Extended Content (security/segmentation) */
+#define CANXL_RRS 0x02 /* Remote Request Substitution */
 
 /* the 8-bit VCID is optionally placed in the canxl_frame.prio element */
 #define CANXL_VCID_OFFSET 16 /* bit offset of VCID in prio element */

From 32f08b22f3b88b7ba43fa8f4090dfd9575343256 Mon Sep 17 00:00:00 2001
From: Henrik Brix Andersen <henrik@brixandersen.dk>
Date: Mon, 20 Jan 2025 13:37:59 +0000
Subject: [PATCH 0767/2753] can: gs_usb: add VID/PID for the CANnectivity
 firmware

Add USB VID/PID for the CANnectivity USB to CAN adapter firmware.

Signed-off-by: Henrik Brix Andersen <henrik@brixandersen.dk>
Tested-by: Sean Nyekjaer <sean@geanix.com>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250120133827.668977-1-henrik@brixandersen.dk
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/gs_usb.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index b6f4de375df75..3ccac6781b983 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -43,6 +43,9 @@
 #define USB_XYLANTA_SAINT3_VENDOR_ID 0x16d0
 #define USB_XYLANTA_SAINT3_PRODUCT_ID 0x0f30
 
+#define USB_CANNECTIVITY_VENDOR_ID 0x1209
+#define USB_CANNECTIVITY_PRODUCT_ID 0xca01
+
 /* Timestamp 32 bit timer runs at 1 MHz (1 µs tick). Worker accounts
  * for timer overflow (will be after ~71 minutes)
  */
@@ -1546,6 +1549,8 @@ static const struct usb_device_id gs_usb_table[] = {
 				      USB_ABE_CANDEBUGGER_FD_PRODUCT_ID, 0) },
 	{ USB_DEVICE_INTERFACE_NUMBER(USB_XYLANTA_SAINT3_VENDOR_ID,
 				      USB_XYLANTA_SAINT3_PRODUCT_ID, 0) },
+	{ USB_DEVICE_INTERFACE_NUMBER(USB_CANNECTIVITY_VENDOR_ID,
+				      USB_CANNECTIVITY_PRODUCT_ID, 0) },
 	{} /* Terminating entry */
 };
 

From d9e1cc087a55286fe028e0f078159b30d7da90bd Mon Sep 17 00:00:00 2001
From: Robin van der Gracht <robin@protonic.nl>
Date: Mon, 27 Jan 2025 13:16:44 +0100
Subject: [PATCH 0768/2753] can: rockchip_canfd: rkcanfd_chip_fifo_setup():
 remove duplicated setup of RX FIFO

The rockchip_canfd driver doesn't make use of the TXE FIFO.

Although the comment states that the TXE FIFO is setup, it's actually
a setup of the RX FIFO. The regular setup of the RX FIFO follows.

Remove the duplicated setup of the RX FIFO.

Fixes: ff60bfbaf67f ("can: rockchip_canfd: add driver for Rockchip CAN-FD controller")
Signed-off-by: Robin van der Gracht <robin@protonic.nl>
Link: https://patch.msgid.link/20250219-rk3568-canfd-v1-1-453869358c72@pengutronix.de
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rockchip/rockchip_canfd-core.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/can/rockchip/rockchip_canfd-core.c b/drivers/net/can/rockchip/rockchip_canfd-core.c
index d9a937ba126c3..46201c126703c 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-core.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-core.c
@@ -236,11 +236,6 @@ static void rkcanfd_chip_fifo_setup(struct rkcanfd_priv *priv)
 {
 	u32 reg;
 
-	/* TXE FIFO */
-	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
-	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;
-	rkcanfd_write(priv, RKCANFD_REG_RX_FIFO_CTRL, reg);
-
 	/* RX FIFO */
 	reg = rkcanfd_read(priv, RKCANFD_REG_RX_FIFO_CTRL);
 	reg |= RKCANFD_REG_RX_FIFO_CTRL_RX_FIFO_ENABLE;

From 9a369ae3d1431a83589dde57323a04692dd7fc12 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 17 Feb 2025 09:31:46 +0200
Subject: [PATCH 0769/2753] net: ethernet: ti: am65-cpsw: remove
 am65_cpsw_nuss_tx_compl_packets_2g()

The only difference between am65_cpsw_nuss_tx_compl_packets_2g() and
am65_cpsw_nuss_tx_compl_packets() is the usage of spin_lock() and
netdev_tx_completed_queue() + am65_cpsw_nuss_tx_wake at every packet
in the latter.

Insted of having 2 separate functions for TX completion, merge them
into one. This will reduce code duplication and make maintenance easier.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 98 ++++++------------------
 1 file changed, 25 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 2806238629f82..0ccb8dbcbba44 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1504,6 +1504,7 @@ static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_d
 static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 					   int chn, unsigned int budget, bool *tdown)
 {
+	bool single_port = AM65_CPSW_IS_CPSW2G(common);
 	enum am65_cpsw_tx_buf_type buf_type;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
@@ -1511,6 +1512,7 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	unsigned int total_bytes = 0;
 	struct net_device *ndev;
 	struct xdp_frame *xdpf;
+	unsigned int pkt_len;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
@@ -1518,9 +1520,12 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	tx_chn = &common->tx_chns[chn];
 
 	while (true) {
-		spin_lock(&tx_chn->lock);
+		if (!single_port)
+			spin_lock(&tx_chn->lock);
 		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
-		spin_unlock(&tx_chn->lock);
+		if (!single_port)
+			spin_unlock(&tx_chn->lock);
+
 		if (res == -ENODATA)
 			break;
 
@@ -1535,23 +1540,35 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
 			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
 			ndev = skb->dev;
-			total_bytes = skb->len;
+			pkt_len = skb->len;
 			napi_consume_skb(skb, budget);
 		} else {
 			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
 								  desc_dma, &ndev);
-			total_bytes = xdpf->len;
+			pkt_len = xdpf->len;
 			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
 				xdp_return_frame_rx_napi(xdpf);
 			else
 				xdp_return_frame(xdpf);
 		}
+
+		total_bytes += pkt_len;
 		num_tx++;
 
-		netif_txq = netdev_get_tx_queue(ndev, chn);
+		if (!single_port) {
+			/* as packets from multi ports can be interleaved
+			 * on the same channel, we have to figure out the
+			 * port/queue at every packet and report it/wake queue.
+			 */
+			netif_txq = netdev_get_tx_queue(ndev, chn);
+			netdev_tx_completed_queue(netif_txq, 1, pkt_len);
+			am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
+		}
+	}
 
+	if (single_port) {
+		netif_txq = netdev_get_tx_queue(ndev, chn);
 		netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
-
 		am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
 	}
 
@@ -1560,66 +1577,6 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 	return num_tx;
 }
 
-static int am65_cpsw_nuss_tx_compl_packets_2g(struct am65_cpsw_common *common,
-					      int chn, unsigned int budget, bool *tdown)
-{
-	enum am65_cpsw_tx_buf_type buf_type;
-	struct device *dev = common->dev;
-	struct am65_cpsw_tx_chn *tx_chn;
-	struct netdev_queue *netif_txq;
-	unsigned int total_bytes = 0;
-	struct net_device *ndev;
-	struct xdp_frame *xdpf;
-	struct sk_buff *skb;
-	dma_addr_t desc_dma;
-	int res, num_tx = 0;
-
-	tx_chn = &common->tx_chns[chn];
-
-	while (true) {
-		res = k3_udma_glue_pop_tx_chn(tx_chn->tx_chn, &desc_dma);
-		if (res == -ENODATA)
-			break;
-
-		if (cppi5_desc_is_tdcm(desc_dma)) {
-			if (atomic_dec_and_test(&common->tdown_cnt))
-				complete(&common->tdown_complete);
-			*tdown = true;
-			break;
-		}
-
-		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
-		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
-			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
-			ndev = skb->dev;
-			total_bytes += skb->len;
-			napi_consume_skb(skb, budget);
-		} else {
-			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
-								  desc_dma, &ndev);
-			total_bytes += xdpf->len;
-			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
-				xdp_return_frame_rx_napi(xdpf);
-			else
-				xdp_return_frame(xdpf);
-		}
-		num_tx++;
-	}
-
-	if (!num_tx)
-		return 0;
-
-	netif_txq = netdev_get_tx_queue(ndev, chn);
-
-	netdev_tx_completed_queue(netif_txq, num_tx, total_bytes);
-
-	am65_cpsw_nuss_tx_wake(tx_chn, ndev, netif_txq);
-
-	dev_dbg(dev, "%s:%u pkt:%d\n", __func__, chn, num_tx);
-
-	return num_tx;
-}
-
 static enum hrtimer_restart am65_cpsw_nuss_tx_timer_callback(struct hrtimer *timer)
 {
 	struct am65_cpsw_tx_chn *tx_chns =
@@ -1635,13 +1592,8 @@ static int am65_cpsw_nuss_tx_poll(struct napi_struct *napi_tx, int budget)
 	bool tdown = false;
 	int num_tx;
 
-	if (AM65_CPSW_IS_CPSW2G(tx_chn->common))
-		num_tx = am65_cpsw_nuss_tx_compl_packets_2g(tx_chn->common, tx_chn->id,
-							    budget, &tdown);
-	else
-		num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common,
-							 tx_chn->id, budget, &tdown);
-
+	num_tx = am65_cpsw_nuss_tx_compl_packets(tx_chn->common,
+						 tx_chn->id, budget, &tdown);
 	if (num_tx >= budget)
 		return budget;
 

From 1ae26bf6151706477fe2b4567be516f0173162fd Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 17 Feb 2025 09:31:47 +0200
Subject: [PATCH 0770/2753] net: ethernet: ti: am65_cpsw: remove cpu argument
 am65_cpsw_run_xdp

am65_cpsw_run_xdp() can figure out the cpu id itself.
No need to pass it around 2 functions so drop it.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 0ccb8dbcbba44..134802007c937 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1167,14 +1167,14 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
 
 static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 			     struct am65_cpsw_port *port,
-			     struct xdp_buff *xdp,
-			     int cpu, int *len)
+			     struct xdp_buff *xdp, int *len)
 {
 	struct am65_cpsw_common *common = flow->common;
 	struct net_device *ndev = port->ndev;
 	int ret = AM65_CPSW_XDP_CONSUMED;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
+	int cpu = smp_processor_id();
 	struct xdp_frame *xdpf;
 	struct bpf_prog *prog;
 	struct page *page;
@@ -1274,7 +1274,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info)
 }
 
 static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
-				     int cpu, int *xdp_state)
+				     int *xdp_state)
 {
 	struct am65_cpsw_rx_chn *rx_chn = &flow->common->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0, csum_info;
@@ -1334,8 +1334,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 		xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq[flow->id]);
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
 				 pkt_len, false);
-		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp,
-					       cpu, &pkt_len);
+		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, &pkt_len);
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
 
@@ -1401,7 +1400,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 {
 	struct am65_cpsw_rx_flow *flow = am65_cpsw_napi_to_rx_flow(napi_rx);
 	struct am65_cpsw_common *common = flow->common;
-	int cpu = smp_processor_id();
 	int xdp_state_or = 0;
 	int cur_budget, ret;
 	int xdp_state;
@@ -1410,7 +1408,7 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	/* process only this flow */
 	cur_budget = budget;
 	while (cur_budget--) {
-		ret = am65_cpsw_nuss_rx_packets(flow, cpu, &xdp_state);
+		ret = am65_cpsw_nuss_rx_packets(flow, &xdp_state);
 		xdp_state_or |= xdp_state;
 		if (ret)
 			break;

From 09057ce3774ec42d8463548cb5125a5ac61b89ff Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 17 Feb 2025 09:31:48 +0200
Subject: [PATCH 0771/2753] net: ethernet: ti: am65-cpsw: use return instead of
 goto in am65_cpsw_run_xdp()

In am65_cpsw_run_xdp() instead of goto followed by return, simply return.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 134802007c937..e1d7c3bf16e2d 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -1193,8 +1193,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 
 	switch (act) {
 	case XDP_PASS:
-		ret = AM65_CPSW_XDP_PASS;
-		goto out;
+		return AM65_CPSW_XDP_PASS;
 	case XDP_TX:
 		tx_chn = &common->tx_chns[cpu % AM65_CPSW_MAX_QUEUES];
 		netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
@@ -1213,15 +1212,13 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 			goto drop;
 
 		dev_sw_netstats_rx_add(ndev, pkt_len);
-		ret = AM65_CPSW_XDP_CONSUMED;
-		goto out;
+		return AM65_CPSW_XDP_CONSUMED;
 	case XDP_REDIRECT:
 		if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
 			goto drop;
 
 		dev_sw_netstats_rx_add(ndev, pkt_len);
-		ret = AM65_CPSW_XDP_REDIRECT;
-		goto out;
+		return AM65_CPSW_XDP_REDIRECT;
 	default:
 		bpf_warn_invalid_xdp_action(ndev, prog, act);
 		fallthrough;
@@ -1236,7 +1233,6 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 	page = virt_to_head_page(xdp->data);
 	am65_cpsw_put_page(flow, page, true);
 
-out:
 	return ret;
 }
 

From 6d6c7933cea6e51a07be52cf5aba97cd656e0e54 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 17 Feb 2025 09:31:49 +0200
Subject: [PATCH 0772/2753] net: ethernet: ti: am65_cpsw: move
 am65_cpsw_put_page() out of am65_cpsw_run_xdp()

This allows us to re-use am65_cpsw_run_xdp() for zero copy
case. Add AM65_CPSW_XDP_TX case for successful XDP_TX so we don't
free the page while in flight.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index e1d7c3bf16e2d..20a4fc3e579fd 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -164,6 +164,7 @@
 #define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7
 
 /* XDP */
+#define AM65_CPSW_XDP_TX       BIT(2)
 #define AM65_CPSW_XDP_CONSUMED BIT(1)
 #define AM65_CPSW_XDP_REDIRECT BIT(0)
 #define AM65_CPSW_XDP_PASS     0
@@ -1177,7 +1178,6 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 	int cpu = smp_processor_id();
 	struct xdp_frame *xdpf;
 	struct bpf_prog *prog;
-	struct page *page;
 	int pkt_len;
 	u32 act;
 	int err;
@@ -1212,7 +1212,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 			goto drop;
 
 		dev_sw_netstats_rx_add(ndev, pkt_len);
-		return AM65_CPSW_XDP_CONSUMED;
+		return AM65_CPSW_XDP_TX;
 	case XDP_REDIRECT:
 		if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
 			goto drop;
@@ -1230,9 +1230,6 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_rx_flow *flow,
 		ndev->stats.rx_dropped++;
 	}
 
-	page = virt_to_head_page(xdp->data);
-	am65_cpsw_put_page(flow, page, true);
-
 	return ret;
 }
 
@@ -1331,6 +1328,12 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_rx_flow *flow,
 		xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
 				 pkt_len, false);
 		*xdp_state = am65_cpsw_run_xdp(flow, port, &xdp, &pkt_len);
+		if (*xdp_state == AM65_CPSW_XDP_CONSUMED) {
+			page = virt_to_head_page(xdp.data);
+			am65_cpsw_put_page(flow, page, true);
+			goto allocate;
+		}
+
 		if (*xdp_state != AM65_CPSW_XDP_PASS)
 			goto allocate;
 

From ce643fa62a70f0bb1c33d9fc98ed4d0300b00ff4 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 17 Feb 2025 09:31:50 +0200
Subject: [PATCH 0773/2753] net: ethernet: ti am65_cpsw: Drop separate TX
 completion functions

Drop separate TX completion functions for SKB and XDP. To do that
use the SW_DATA mechanism to store ndev and skb/xdpf for TX packets.

Use BUILD_BUG_ON_MSG() to fail build if SW_DATA size exceeds whats
available. i.e. AM65_CPSW_NAV_SW_DATA_SIZE.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 82 +++++++-----------------
 drivers/net/ethernet/ti/am65-cpsw-nuss.h |  8 +++
 2 files changed, 32 insertions(+), 58 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 20a4fc3e579fd..3e671be95d6f6 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -830,19 +830,19 @@ static void am65_cpsw_nuss_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct am65_cpsw_tx_chn *tx_chn = data;
 	enum am65_cpsw_tx_buf_type buf_type;
+	struct am65_cpsw_tx_swdata *swdata;
 	struct cppi5_host_desc_t *desc_tx;
 	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
-	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
 	buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
 	if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
-		skb = *(swdata);
+		skb = swdata->skb;
 		dev_kfree_skb_any(skb);
 	} else {
-		xdpf = *(swdata);
+		xdpf = swdata->xdpf;
 		xdp_return_frame(xdpf);
 	}
 
@@ -1099,10 +1099,10 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
 	struct cppi5_host_desc_t *host_desc;
+	struct am65_cpsw_tx_swdata *swdata;
 	struct netdev_queue *netif_txq;
 	dma_addr_t dma_desc, dma_buf;
 	u32 pkt_len = xdpf->len;
-	void **swdata;
 	int ret;
 
 	host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
@@ -1132,7 +1132,8 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
 	cppi5_hdesc_attach_buf(host_desc, dma_buf, pkt_len, dma_buf, pkt_len);
 
 	swdata = cppi5_hdesc_get_swdata(host_desc);
-	*(swdata) = xdpf;
+	swdata->ndev = ndev;
+	swdata->xdpf = xdpf;
 
 	/* Report BQL before sending the packet */
 	netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
@@ -1435,52 +1436,6 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
 	return num_rx;
 }
 
-static struct sk_buff *
-am65_cpsw_nuss_tx_compl_packet_skb(struct am65_cpsw_tx_chn *tx_chn,
-				   dma_addr_t desc_dma)
-{
-	struct cppi5_host_desc_t *desc_tx;
-	struct sk_buff *skb;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
-					     desc_dma);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
-
-	am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
-
-	dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
-
-	return skb;
-}
-
-static struct xdp_frame *
-am65_cpsw_nuss_tx_compl_packet_xdp(struct am65_cpsw_common *common,
-				   struct am65_cpsw_tx_chn *tx_chn,
-				   dma_addr_t desc_dma,
-				   struct net_device **ndev)
-{
-	struct cppi5_host_desc_t *desc_tx;
-	struct am65_cpsw_port *port;
-	struct xdp_frame *xdpf;
-	u32 port_id = 0;
-	void **swdata;
-
-	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
-	cppi5_desc_get_tags_ids(&desc_tx->hdr, NULL, &port_id);
-	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	xdpf = *(swdata);
-	am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
-
-	port = am65_common_get_port(common, port_id);
-	dev_sw_netstats_tx_add(port->ndev, 1, xdpf->len);
-	*ndev = port->ndev;
-
-	return xdpf;
-}
-
 static void am65_cpsw_nuss_tx_wake(struct am65_cpsw_tx_chn *tx_chn, struct net_device *ndev,
 				   struct netdev_queue *netif_txq)
 {
@@ -1503,6 +1458,8 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 {
 	bool single_port = AM65_CPSW_IS_CPSW2G(common);
 	enum am65_cpsw_tx_buf_type buf_type;
+	struct am65_cpsw_tx_swdata *swdata;
+	struct cppi5_host_desc_t *desc_tx;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
@@ -1533,15 +1490,18 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 			break;
 		}
 
+		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
+						     desc_dma);
+		swdata = cppi5_hdesc_get_swdata(desc_tx);
+		ndev = swdata->ndev;
 		buf_type = am65_cpsw_nuss_buf_type(tx_chn, desc_dma);
 		if (buf_type == AM65_CPSW_TX_BUF_TYPE_SKB) {
-			skb = am65_cpsw_nuss_tx_compl_packet_skb(tx_chn, desc_dma);
-			ndev = skb->dev;
+			skb = swdata->skb;
+			am65_cpts_tx_timestamp(tx_chn->common->cpts, skb);
 			pkt_len = skb->len;
 			napi_consume_skb(skb, budget);
 		} else {
-			xdpf = am65_cpsw_nuss_tx_compl_packet_xdp(common, tx_chn,
-								  desc_dma, &ndev);
+			xdpf = swdata->xdpf;
 			pkt_len = xdpf->len;
 			if (buf_type == AM65_CPSW_TX_BUF_TYPE_XDP_TX)
 				xdp_return_frame_rx_napi(xdpf);
@@ -1551,7 +1511,8 @@ static int am65_cpsw_nuss_tx_compl_packets(struct am65_cpsw_common *common,
 
 		total_bytes += pkt_len;
 		num_tx++;
-
+		am65_cpsw_nuss_xmit_free(tx_chn, desc_tx);
+		dev_sw_netstats_tx_add(ndev, 1, pkt_len);
 		if (!single_port) {
 			/* as packets from multi ports can be interleaved
 			 * on the same channel, we have to figure out the
@@ -1634,12 +1595,12 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
 	struct cppi5_host_desc_t *first_desc, *next_desc, *cur_desc;
 	struct am65_cpsw_port *port = am65_ndev_to_port(ndev);
+	struct am65_cpsw_tx_swdata *swdata;
 	struct device *dev = common->dev;
 	struct am65_cpsw_tx_chn *tx_chn;
 	struct netdev_queue *netif_txq;
 	dma_addr_t desc_dma, buf_dma;
 	int ret, q_idx, i;
-	void **swdata;
 	u32 *psdata;
 	u32 pkt_len;
 
@@ -1685,7 +1646,8 @@ static netdev_tx_t am65_cpsw_nuss_ndo_slave_xmit(struct sk_buff *skb,
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*(swdata) = skb;
+	swdata->ndev = ndev;
+	swdata->skb = skb;
 	psdata = cppi5_hdesc_get_psdata(first_desc);
 
 	/* HW csum offload if enabled */
@@ -3527,6 +3489,10 @@ static int am65_cpsw_nuss_probe(struct platform_device *pdev)
 	__be64 id_temp;
 	int ret, i;
 
+	BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_tx_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE,
+			 "TX SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE");
+	BUILD_BUG_ON_MSG(sizeof(struct am65_cpsw_swdata) > AM65_CPSW_NAV_SW_DATA_SIZE,
+			 "SW_DATA size exceeds AM65_CPSW_NAV_SW_DATA_SIZE");
 	common = devm_kzalloc(dev, sizeof(struct am65_cpsw_common), GFP_KERNEL);
 	if (!common)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.h b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
index e7832a5cf3ccd..917c37e4e89bd 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.h
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.h
@@ -104,6 +104,14 @@ struct am65_cpsw_rx_flow {
 	char name[32];
 };
 
+struct am65_cpsw_tx_swdata {
+	struct net_device *ndev;
+	union {
+		struct sk_buff *skb;
+		struct xdp_frame *xdpf;
+	};
+};
+
 struct am65_cpsw_swdata {
 	u32 flow_id;
 	struct page *page;

From 3dbc0215e3c502a9f3221576da0fdc9847fb9721 Mon Sep 17 00:00:00 2001
From: Aaron Kling <webgeek1234@gmail.com>
Date: Tue, 18 Feb 2025 03:28:03 -0600
Subject: [PATCH 0774/2753] drm/nouveau/pmu: Fix gp10b firmware guard

Most kernel configs enable multiple Tegra SoC generations, causing this
typo to go unnoticed. But in the case where a kernel config is strictly
for Tegra186, this is a problem.

Fixes: 989863d7cbe5 ("drm/nouveau/pmu: select implementation based on available firmware")
Signed-off-by: Aaron Kling <webgeek1234@gmail.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250218-nouveau-gm10b-guard-v2-1-a4de71500d48@gmail.com
---
 drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
index a6f410ba60bc9..d393bc540f862 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/pmu/gp10b.c
@@ -75,7 +75,7 @@ gp10b_pmu_acr = {
 	.bootstrap_multiple_falcons = gp10b_pmu_acr_bootstrap_multiple_falcons,
 };
 
-#if IS_ENABLED(CONFIG_ARCH_TEGRA_210_SOC)
+#if IS_ENABLED(CONFIG_ARCH_TEGRA_186_SOC)
 MODULE_FIRMWARE("nvidia/gp10b/pmu/desc.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/image.bin");
 MODULE_FIRMWARE("nvidia/gp10b/pmu/sig.bin");

From 6586788f0a8d0f3b33b1383885575f5b5f7b9dad Mon Sep 17 00:00:00 2001
From: Karol Herbst <kherbst@redhat.com>
Date: Sat, 15 Feb 2025 08:37:53 +0100
Subject: [PATCH 0775/2753] MAINTAINERS: Remove myself

I was pondering with myself for a while if I should just make it official
that I'm not really involved in the kernel community anymore, neither as a
reviewer, nor as a maintainer.

Most of the time I simply excused myself with "if something urgent comes
up, I can chime in and help out". Lyude and Danilo are doing a wonderful
job and I've put all my trust into them.

However, there is one thing I can't stand and it's hurting me the most.
I'm convinced, no, my core believe is, that inclusivity and respect,
working with others as equals, no power plays involved, is how we should
work together within the Free and Open Source community.

I can understand maintainers needing to learn, being concerned on
technical points. Everybody deserves the time to understand and learn. It
is my true belief that most people are capable of change eventually. I
truly believe this community can change from within, however this doesn't
mean it's going to be a smooth process.

The moment I made up my mind about this was reading the following words
written by a maintainer within the kernel community:

	"we are the thin blue line"

This isn't okay. This isn't creating an inclusive environment. This isn't
okay with the current political situation especially in the US. A
maintainer speaking those words can't be kept. No matter how important
or critical or relevant they are. They need to be removed until they
learn. Learn what those words mean for a lot of marginalized people. Learn
about what horrors it evokes in their minds.

I can't in good faith remain to be part of a project and its community
where those words are tolerated. Those words are not technical, they are
a political statement. Even if unintentionally, such words carry power,
they carry meanings one needs to be aware of. They do cause an immense
amount of harm.

I wish the best of luck for everybody to continue to try to work from
within. You got my full support and I won't hold it against anybody trying
to improve the community, it's a thankless job, it's a lot of work. People
will continue to burn out.

I got burned out enough by myself caring about the bits I maintained, but
eventually I had to realize my limits. The obligation I felt was eating me
from inside. It stopped being fun at some point and I reached a point
where I simply couldn't continue the work I was so motivated doing as I've
did in the early days.

Please respect my wishes and put this statement as is into the tree.
Leaving anything out destroys its entire meaning.

Respectfully

Karol

Signed-off-by: Karol Herbst <kherbst@redhat.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250215073753.1217002-2-kherbst@redhat.com
---
 MAINTAINERS | 2 --
 1 file changed, 2 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index fd4f528bc4145..18ade2ea4f3c4 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -7354,7 +7354,6 @@ F:	Documentation/devicetree/bindings/display/panel/novatek,nt36672a.yaml
 F:	drivers/gpu/drm/panel/panel-novatek-nt36672a.c
 
 DRM DRIVER FOR NVIDIA GEFORCE/QUADRO GPUS
-M:	Karol Herbst <kherbst@redhat.com>
 M:	Lyude Paul <lyude@redhat.com>
 M:	Danilo Krummrich <dakr@kernel.org>
 L:	dri-devel@lists.freedesktop.org
@@ -23819,7 +23818,6 @@ F:	tools/testing/selftests/ftrace/
 TRACING MMIO ACCESSES (MMIOTRACE)
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Masami Hiramatsu <mhiramat@kernel.org>
-R:	Karol Herbst <karolherbst@gmail.com>
 R:	Pekka Paalanen <ppaalanen@gmail.com>
 L:	linux-kernel@vger.kernel.org
 L:	nouveau@lists.freedesktop.org

From 60255f3704fde70ed3c4d62f919aa4b46f841f70 Mon Sep 17 00:00:00 2001
From: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Date: Sun, 16 Feb 2025 11:15:36 +0800
Subject: [PATCH 0776/2753] mtd: rawnand: cadence: fix unchecked dereference

Add NULL check before variable dereference to fix static checker warning.

Fixes: d76d22b5096c ("mtd: rawnand: cadence: use dma_map_resource for sdma address")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/e448a22c-bada-448d-9167-7af71305130d@stanley.mountain/
Signed-off-by: Niravkumar L Rabara <niravkumar.l.rabara@intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/raw/cadence-nand-controller.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/mtd/nand/raw/cadence-nand-controller.c b/drivers/mtd/nand/raw/cadence-nand-controller.c
index 0b2db4173e723..6667eea955977 100644
--- a/drivers/mtd/nand/raw/cadence-nand-controller.c
+++ b/drivers/mtd/nand/raw/cadence-nand-controller.c
@@ -2972,8 +2972,10 @@ static int cadence_nand_init(struct cdns_nand_ctrl *cdns_ctrl)
 static void cadence_nand_remove(struct cdns_nand_ctrl *cdns_ctrl)
 {
 	cadence_nand_chips_cleanup(cdns_ctrl);
-	dma_unmap_resource(cdns_ctrl->dmac->device->dev, cdns_ctrl->io.iova_dma,
-			   cdns_ctrl->io.size, DMA_BIDIRECTIONAL, 0);
+	if (cdns_ctrl->dmac)
+		dma_unmap_resource(cdns_ctrl->dmac->device->dev,
+				   cdns_ctrl->io.iova_dma, cdns_ctrl->io.size,
+				   DMA_BIDIRECTIONAL, 0);
 	cadence_nand_irq_cleanup(cdns_ctrl->irq, cdns_ctrl);
 	kfree(cdns_ctrl->buf);
 	dma_free_coherent(cdns_ctrl->dev, sizeof(struct cadence_nand_cdma_desc),

From a8e8ffcc3afce2ee5fb70162aeaef3f03573ee1e Mon Sep 17 00:00:00 2001
From: Alexander Usyskin <alexander.usyskin@intel.com>
Date: Sun, 9 Feb 2025 13:05:50 +0200
Subject: [PATCH 0777/2753] mei: me: add panther lake P DID

Add Panther Lake P device id.

Cc: stable <stable@kernel.org>
Co-developed-by: Tomas Winkler <tomasw@gmail.com>
Signed-off-by: Tomas Winkler <tomasw@gmail.com>
Signed-off-by: Alexander Usyskin <alexander.usyskin@intel.com>
Link: https://lore.kernel.org/r/20250209110550.1582982-1-alexander.usyskin@intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/hw-me-regs.h | 2 ++
 drivers/misc/mei/pci-me.c     | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/misc/mei/hw-me-regs.h b/drivers/misc/mei/hw-me-regs.h
index c3a6657dcd4a2..a5f88ec97df75 100644
--- a/drivers/misc/mei/hw-me-regs.h
+++ b/drivers/misc/mei/hw-me-regs.h
@@ -117,6 +117,8 @@
 
 #define MEI_DEV_ID_LNL_M      0xA870  /* Lunar Lake Point M */
 
+#define MEI_DEV_ID_PTL_P      0xE470  /* Panther Lake P */
+
 /*
  * MEI HW Section
  */
diff --git a/drivers/misc/mei/pci-me.c b/drivers/misc/mei/pci-me.c
index 6589635f8ba32..d6ff9d82ae94b 100644
--- a/drivers/misc/mei/pci-me.c
+++ b/drivers/misc/mei/pci-me.c
@@ -124,6 +124,8 @@ static const struct pci_device_id mei_me_pci_tbl[] = {
 
 	{MEI_PCI_DEVICE(MEI_DEV_ID_LNL_M, MEI_ME_PCH15_CFG)},
 
+	{MEI_PCI_DEVICE(MEI_DEV_ID_PTL_P, MEI_ME_PCH15_CFG)},
+
 	/* required last entry */
 	{0, }
 };

From fdb1ada57cf8b8752cdf54f08709d76d74999544 Mon Sep 17 00:00:00 2001
From: Hans de Goede <hdegoede@redhat.com>
Date: Fri, 14 Feb 2025 22:24:25 +0100
Subject: [PATCH 0778/2753] mei: vsc: Use "wakeuphostint" when getting the host
 wakeup GPIO

The _CRS ACPI resources table has 2 entries for the host wakeup GPIO,
the first one being a regular GpioIo () resource while the second one
is a GpioInt () resource for the same pin.

The acpi_gpio_mapping table used by vsc-tp.c maps the first Gpio ()
resource to "wakeuphost-gpios" where as the second GpioInt () entry
is mapped to "wakeuphostint-gpios".

Using "wakeuphost" to request the GPIO as was done until now, means
that the gpiolib-acpi code does not know that the GPIO is active-low
as that info is only available in the GpioInt () entry.

Things were still working before due to the following happening:

1. Since the 2 entries point to the same pin they share a struct gpio_desc
2. The SPI core creates the SPI device vsc-tp.c binds to and calls
   acpi_dev_gpio_irq_get(). This does use the second entry and sets
   FLAG_ACTIVE_LOW in gpio_desc.flags .
3. vsc_tp_probe() requests the "wakeuphost" GPIO and inherits the
   active-low flag set by acpi_dev_gpio_irq_get()

But there is a possible scenario where things do not work:

1. - 3. happen as above
4. After requesting the "wakeuphost" GPIO, the "resetfw" GPIO is requested
   next, but its USB GPIO controller is not available yet, so this call
   returns -EPROBE_DEFER.
5. The gpio_desc for "wakeuphost" is put() and during this the active-low
   flag is cleared from gpio_desc.flags .
6. Later on vsc_tp_probe() requests the "wakeuphost" GPIO again, but now it
   is not marked active-low.

The difference can also be seen in /sys/kernel/debug/gpio, which contains
the following line for this GPIO:

 gpio-535 (                    |wakeuphost          ) in  hi IRQ ACTIVE LOW

If the second scenario is hit the "ACTIVE LOW" at the end disappears and
things do not work.

Fix this by requesting the GPIO through the "wakeuphostint" mapping instead
which provides active-low info without relying on acpi_dev_gpio_irq_get()
pre-populating this info in the gpio_desc.

Link: https://bugzilla.redhat.com/show_bug.cgi?id=2316918
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Stanislaw Gruszka <stanislaw.gruszka@linux.intel.com>
Tested-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Fixes: 566f5ca97680 ("mei: Add transport driver for IVSC device")
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250214212425.84021-1-hdegoede@redhat.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/mei/vsc-tp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/mei/vsc-tp.c b/drivers/misc/mei/vsc-tp.c
index 35d349fee7698..7be1649b19725 100644
--- a/drivers/misc/mei/vsc-tp.c
+++ b/drivers/misc/mei/vsc-tp.c
@@ -502,7 +502,7 @@ static int vsc_tp_probe(struct spi_device *spi)
 	if (ret)
 		return ret;
 
-	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphost", GPIOD_IN);
+	tp->wakeuphost = devm_gpiod_get(dev, "wakeuphostint", GPIOD_IN);
 	if (IS_ERR(tp->wakeuphost))
 		return PTR_ERR(tp->wakeuphost);
 

From c90aad369899a607cfbc002bebeafd51e31900cd Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Thu, 13 Feb 2025 15:22:57 +0300
Subject: [PATCH 0779/2753] usb: atm: cxacru: fix a flaw in existing endpoint
 checks

Syzbot once again identified a flaw in usb endpoint checking, see [1].
This time the issue stems from a commit authored by me (2eabb655a968
("usb: atm: cxacru: fix endpoint checking in cxacru_bind()")).

While using usb_find_common_endpoints() may usually be enough to
discard devices with wrong endpoints, in this case one needs more
than just finding and identifying the sufficient number of endpoints
of correct types - one needs to check the endpoint's address as well.

Since cxacru_bind() fills URBs with CXACRU_EP_CMD address in mind,
switch the endpoint verification approach to usb_check_XXX_endpoints()
instead to fix incomplete ep testing.

[1] Syzbot report:
usb 5-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 0 PID: 1378 at drivers/usb/core/urb.c:504 usb_submit_urb+0xc4e/0x18c0 drivers/usb/core/urb.c:503
...
RIP: 0010:usb_submit_urb+0xc4e/0x18c0 drivers/usb/core/urb.c:503
...
Call Trace:
 <TASK>
 cxacru_cm+0x3c8/0xe50 drivers/usb/atm/cxacru.c:649
 cxacru_card_status drivers/usb/atm/cxacru.c:760 [inline]
 cxacru_bind+0xcf9/0x1150 drivers/usb/atm/cxacru.c:1223
 usbatm_usb_probe+0x314/0x1d30 drivers/usb/atm/usbatm.c:1058
 cxacru_usb_probe+0x184/0x220 drivers/usb/atm/cxacru.c:1377
 usb_probe_interface+0x641/0xbb0 drivers/usb/core/driver.c:396
 really_probe+0x2b9/0xad0 drivers/base/dd.c:658
 __driver_probe_device+0x1a2/0x390 drivers/base/dd.c:800
 driver_probe_device+0x50/0x430 drivers/base/dd.c:830
...

Reported-and-tested-by: syzbot+ccbbc229a024fa3e13b5@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=ccbbc229a024fa3e13b5
Fixes: 2eabb655a968 ("usb: atm: cxacru: fix endpoint checking in cxacru_bind()")
Cc: stable@kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://lore.kernel.org/r/20250213122259.730772-1-n.zhandarovich@fintech.ru
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/atm/cxacru.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/atm/cxacru.c b/drivers/usb/atm/cxacru.c
index 0dd85d2635b99..47d06af33747d 100644
--- a/drivers/usb/atm/cxacru.c
+++ b/drivers/usb/atm/cxacru.c
@@ -1131,7 +1131,10 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	struct cxacru_data *instance;
 	struct usb_device *usb_dev = interface_to_usbdev(intf);
 	struct usb_host_endpoint *cmd_ep = usb_dev->ep_in[CXACRU_EP_CMD];
-	struct usb_endpoint_descriptor *in, *out;
+	static const u8 ep_addrs[] = {
+		CXACRU_EP_CMD + USB_DIR_IN,
+		CXACRU_EP_CMD + USB_DIR_OUT,
+		0};
 	int ret;
 
 	/* instance init */
@@ -1179,13 +1182,11 @@ static int cxacru_bind(struct usbatm_data *usbatm_instance,
 	}
 
 	if (usb_endpoint_xfer_int(&cmd_ep->desc))
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						NULL, NULL, &in, &out);
+		ret = usb_check_int_endpoints(intf, ep_addrs);
 	else
-		ret = usb_find_common_endpoints(intf->cur_altsetting,
-						&in, &out, NULL, NULL);
+		ret = usb_check_bulk_endpoints(intf, ep_addrs);
 
-	if (ret) {
+	if (!ret) {
 		usb_err(usbatm_instance, "cxacru_bind: interface has incorrect endpoints\n");
 		ret = -ENODEV;
 		goto fail;

From 17c2c87c37862c3e95b55f660681cc6e8d66660e Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Wed, 12 Feb 2025 15:38:40 +0530
Subject: [PATCH 0780/2753] usb: gadget: u_ether: Set is_suspend flag if remote
 wakeup fails

Currently while UDC suspends, u_ether attempts to remote wakeup
the host if there are any pending transfers. However, if remote
wakeup fails, the UDC remains suspended but the is_suspend flag
is not set. And since is_suspend flag isn't set, the subsequent
eth_start_xmit() would queue USB requests to suspended UDC.

To fix this, bail out from gether_suspend() only if remote wakeup
operation is successful.

Cc: stable <stable@kernel.org>
Fixes: 0a1af6dfa077 ("usb: gadget: f_ecm: Add suspend/resume and remote wakeup support")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250212100840.3812153-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/function/u_ether.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/usb/gadget/function/u_ether.c b/drivers/usb/gadget/function/u_ether.c
index 09e2838917e29..f58590bf5e02f 100644
--- a/drivers/usb/gadget/function/u_ether.c
+++ b/drivers/usb/gadget/function/u_ether.c
@@ -1052,8 +1052,8 @@ void gether_suspend(struct gether *link)
 		 * There is a transfer in progress. So we trigger a remote
 		 * wakeup to inform the host.
 		 */
-		ether_wakeup_host(dev->port_usb);
-		return;
+		if (!ether_wakeup_host(dev->port_usb))
+			return;
 	}
 	spin_lock_irqsave(&dev->lock, flags);
 	link->is_suspend = true;

From 40e89ff5750fca2c1d6da93f98a2038716bba86c Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Mon, 17 Feb 2025 17:33:28 +0530
Subject: [PATCH 0781/2753] usb: gadget: Set self-powered based on MaxPower and
 bmAttributes

Currently the USB gadget will be set as bus-powered based solely
on whether its bMaxPower is greater than 100mA, but this may miss
devices that may legitimately draw less than 100mA but still want
to report as bus-powered. Similarly during suspend & resume, USB
gadget is incorrectly marked as bus/self powered without checking
the bmAttributes field. Fix these by configuring the USB gadget
as self or bus powered based on bmAttributes, and explicitly set
it as bus-powered if it draws more than 100mA.

Cc: stable <stable@kernel.org>
Fixes: 5e5caf4fa8d3 ("usb: gadget: composite: Inform controller driver of self-powered")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250217120328.2446639-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index bdda8c74602de..1fb28bbf6c458 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1050,10 +1050,11 @@ static int set_config(struct usb_composite_dev *cdev,
 	else
 		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
-	if (power <= USB_SELF_POWER_VBUS_MAX_DRAW)
-		usb_gadget_set_selfpowered(gadget);
-	else
+	if (power > USB_SELF_POWER_VBUS_MAX_DRAW ||
+	    !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
 		usb_gadget_clear_selfpowered(gadget);
+	else
+		usb_gadget_set_selfpowered(gadget);
 
 	usb_gadget_vbus_draw(gadget, power);
 	if (result >= 0 && cdev->delayed_status)
@@ -2615,7 +2616,9 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
-	usb_gadget_set_selfpowered(gadget);
+	if (cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
+		usb_gadget_set_selfpowered(gadget);
+
 	usb_gadget_vbus_draw(gadget, 2);
 }
 
@@ -2649,8 +2652,11 @@ void composite_resume(struct usb_gadget *gadget)
 		else
 			maxpower = min(maxpower, 900U);
 
-		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW)
+		if (maxpower > USB_SELF_POWER_VBUS_MAX_DRAW ||
+		    !(cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
 			usb_gadget_clear_selfpowered(gadget);
+		else
+			usb_gadget_set_selfpowered(gadget);
 
 		usb_gadget_vbus_draw(gadget, maxpower);
 	} else {

From d6b82dafd17db0658f089b9cdec573982ca82bc5 Mon Sep 17 00:00:00 2001
From: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Date: Wed, 19 Feb 2025 12:47:00 +0100
Subject: [PATCH 0782/2753] usb: typec: tcpci_rt1711h: Unmask alert interrupts
 to fix functionality

During probe, the TCPC alert interrupts are getting masked to
avoid unwanted interrupts during chip setup: this is ok to do
but there is no unmasking happening at any later time, which
means that the chip will not raise any interrupt, essentially
making it not functional as, while internally it does perform
all of the intended functions, it won't signal anything to the
outside.

Unmask the alert interrupts to fix functionality.

Fixes: ce08eaeb6388 ("staging: typec: rt1711h typec chip driver")
Cc: stable <stable@kernel.org>
Signed-off-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://lore.kernel.org/r/20250219114700.41700-1-angelogioacchino.delregno@collabora.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpci_rt1711h.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/usb/typec/tcpm/tcpci_rt1711h.c b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
index 64f6dd0dc6609..88c50b984e8a3 100644
--- a/drivers/usb/typec/tcpm/tcpci_rt1711h.c
+++ b/drivers/usb/typec/tcpm/tcpci_rt1711h.c
@@ -334,6 +334,11 @@ static int rt1711h_probe(struct i2c_client *client)
 {
 	int ret;
 	struct rt1711h_chip *chip;
+	const u16 alert_mask = TCPC_ALERT_TX_SUCCESS | TCPC_ALERT_TX_DISCARDED |
+			       TCPC_ALERT_TX_FAILED | TCPC_ALERT_RX_HARD_RST |
+			       TCPC_ALERT_RX_STATUS | TCPC_ALERT_POWER_STATUS |
+			       TCPC_ALERT_CC_STATUS | TCPC_ALERT_RX_BUF_OVF |
+			       TCPC_ALERT_FAULT;
 
 	chip = devm_kzalloc(&client->dev, sizeof(*chip), GFP_KERNEL);
 	if (!chip)
@@ -382,6 +387,12 @@ static int rt1711h_probe(struct i2c_client *client)
 					dev_name(chip->dev), chip);
 	if (ret < 0)
 		return ret;
+
+	/* Enable alert interrupts */
+	ret = rt1711h_write16(chip, TCPC_ALERT_MASK, alert_mask);
+	if (ret < 0)
+		return ret;
+
 	enable_irq_wake(client->irq);
 
 	return 0;

From 976e7e9bdc7719a023a4ecccd2e3daec9ab20a40 Mon Sep 17 00:00:00 2001
From: "Christian A. Ehrhardt" <lk@c--e.de>
Date: Mon, 17 Feb 2025 13:54:39 +0300
Subject: [PATCH 0783/2753] acpi: typec: ucsi: Introduce a ->poll_cci method

For the ACPI backend of UCSI the UCSI "registers" are just a memory copy
of the register values in an opregion. The ACPI implementation in the
BIOS ensures that the opregion contents are synced to the embedded
controller and it ensures that the registers (in particular CCI) are
synced back to the opregion on notifications. While there is an ACPI call
that syncs the actual registers to the opregion there is rarely a need to
do this and on some ACPI implementations it actually breaks in various
interesting ways.

The only reason to force a sync from the embedded controller is to poll
CCI while notifications are disabled. Only the ucsi core knows if this
is the case and guessing based on the current command is suboptimal, i.e.
leading to the following spurious assertion splat:

WARNING: CPU: 3 PID: 76 at drivers/usb/typec/ucsi/ucsi.c:1388 ucsi_reset_ppm+0x1b4/0x1c0 [typec_ucsi]
CPU: 3 UID: 0 PID: 76 Comm: kworker/3:0 Not tainted 6.12.11-200.fc41.x86_64 #1
Hardware name: LENOVO 21D0/LNVNB161216, BIOS J6CN45WW 03/17/2023
Workqueue: events_long ucsi_init_work [typec_ucsi]
RIP: 0010:ucsi_reset_ppm+0x1b4/0x1c0 [typec_ucsi]
Call Trace:
 <TASK>
 ucsi_init_work+0x3c/0xac0 [typec_ucsi]
 process_one_work+0x179/0x330
 worker_thread+0x252/0x390
 kthread+0xd2/0x100
 ret_from_fork+0x34/0x50
 ret_from_fork_asm+0x1a/0x30
 </TASK>

Thus introduce a ->poll_cci() method that works like ->read_cci() with an
additional forced sync and document that this should be used when polling
with notifications disabled. For all other backends that presumably don't
have this issue use the same implementation for both methods.

Fixes: fa48d7e81624 ("usb: typec: ucsi: Do not call ACPI _DSM method for UCSI read operations")
Cc: stable <stable@kernel.org>
Signed-off-by: Christian A. Ehrhardt <lk@c--e.de>
Tested-by: Fedor Pchelkin <boddah8794@gmail.com>
Signed-off-by: Fedor Pchelkin <boddah8794@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250217105442.113486-2-boddah8794@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c           | 10 +++++-----
 drivers/usb/typec/ucsi/ucsi.h           |  2 ++
 drivers/usb/typec/ucsi/ucsi_acpi.c      | 21 ++++++++++++++-------
 drivers/usb/typec/ucsi/ucsi_ccg.c       |  1 +
 drivers/usb/typec/ucsi/ucsi_glink.c     |  1 +
 drivers/usb/typec/ucsi/ucsi_stm32g0.c   |  1 +
 drivers/usb/typec/ucsi/ucsi_yoga_c630.c |  1 +
 7 files changed, 25 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index fcf499cc9458c..0fe1476f4c297 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1346,7 +1346,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 	mutex_lock(&ucsi->ppm_lock);
 
-	ret = ucsi->ops->read_cci(ucsi, &cci);
+	ret = ucsi->ops->poll_cci(ucsi, &cci);
 	if (ret < 0)
 		goto out;
 
@@ -1364,7 +1364,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 
 		tmo = jiffies + msecs_to_jiffies(UCSI_TIMEOUT_MS);
 		do {
-			ret = ucsi->ops->read_cci(ucsi, &cci);
+			ret = ucsi->ops->poll_cci(ucsi, &cci);
 			if (ret < 0)
 				goto out;
 			if (cci & UCSI_CCI_COMMAND_COMPLETE)
@@ -1393,7 +1393,7 @@ static int ucsi_reset_ppm(struct ucsi *ucsi)
 		/* Give the PPM time to process a reset before reading CCI */
 		msleep(20);
 
-		ret = ucsi->ops->read_cci(ucsi, &cci);
+		ret = ucsi->ops->poll_cci(ucsi, &cci);
 		if (ret)
 			goto out;
 
@@ -1929,8 +1929,8 @@ struct ucsi *ucsi_create(struct device *dev, const struct ucsi_operations *ops)
 	struct ucsi *ucsi;
 
 	if (!ops ||
-	    !ops->read_version || !ops->read_cci || !ops->read_message_in ||
-	    !ops->sync_control || !ops->async_control)
+	    !ops->read_version || !ops->read_cci || !ops->poll_cci ||
+	    !ops->read_message_in || !ops->sync_control || !ops->async_control)
 		return ERR_PTR(-EINVAL);
 
 	ucsi = kzalloc(sizeof(*ucsi), GFP_KERNEL);
diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
index 82735eb34f0e3..28780acc4af2e 100644
--- a/drivers/usb/typec/ucsi/ucsi.h
+++ b/drivers/usb/typec/ucsi/ucsi.h
@@ -62,6 +62,7 @@ struct dentry;
  * struct ucsi_operations - UCSI I/O operations
  * @read_version: Read implemented UCSI version
  * @read_cci: Read CCI register
+ * @poll_cci: Read CCI register while polling with notifications disabled
  * @read_message_in: Read message data from UCSI
  * @sync_control: Blocking control operation
  * @async_control: Non-blocking control operation
@@ -76,6 +77,7 @@ struct dentry;
 struct ucsi_operations {
 	int (*read_version)(struct ucsi *ucsi, u16 *version);
 	int (*read_cci)(struct ucsi *ucsi, u32 *cci);
+	int (*poll_cci)(struct ucsi *ucsi, u32 *cci);
 	int (*read_message_in)(struct ucsi *ucsi, void *val, size_t val_len);
 	int (*sync_control)(struct ucsi *ucsi, u64 command);
 	int (*async_control)(struct ucsi *ucsi, u64 command);
diff --git a/drivers/usb/typec/ucsi/ucsi_acpi.c b/drivers/usb/typec/ucsi/ucsi_acpi.c
index 5c55155519634..ac1ebb5d95272 100644
--- a/drivers/usb/typec/ucsi/ucsi_acpi.c
+++ b/drivers/usb/typec/ucsi/ucsi_acpi.c
@@ -59,19 +59,24 @@ static int ucsi_acpi_read_version(struct ucsi *ucsi, u16 *version)
 static int ucsi_acpi_read_cci(struct ucsi *ucsi, u32 *cci)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
-	int ret;
-
-	if (UCSI_COMMAND(ua->cmd) == UCSI_PPM_RESET) {
-		ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
-		if (ret)
-			return ret;
-	}
 
 	memcpy(cci, ua->base + UCSI_CCI, sizeof(*cci));
 
 	return 0;
 }
 
+static int ucsi_acpi_poll_cci(struct ucsi *ucsi, u32 *cci)
+{
+	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
+	int ret;
+
+	ret = ucsi_acpi_dsm(ua, UCSI_DSM_FUNC_READ);
+	if (ret)
+		return ret;
+
+	return ucsi_acpi_read_cci(ucsi, cci);
+}
+
 static int ucsi_acpi_read_message_in(struct ucsi *ucsi, void *val, size_t val_len)
 {
 	struct ucsi_acpi *ua = ucsi_get_drvdata(ucsi);
@@ -94,6 +99,7 @@ static int ucsi_acpi_async_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_acpi_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_acpi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_acpi_async_control
@@ -142,6 +148,7 @@ static int ucsi_gram_sync_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_gram_ops = {
 	.read_version = ucsi_acpi_read_version,
 	.read_cci = ucsi_acpi_read_cci,
+	.poll_cci = ucsi_acpi_poll_cci,
 	.read_message_in = ucsi_gram_read_message_in,
 	.sync_control = ucsi_gram_sync_control,
 	.async_control = ucsi_acpi_async_control
diff --git a/drivers/usb/typec/ucsi/ucsi_ccg.c b/drivers/usb/typec/ucsi/ucsi_ccg.c
index 740171f24ef9f..4b1668733a4be 100644
--- a/drivers/usb/typec/ucsi/ucsi_ccg.c
+++ b/drivers/usb/typec/ucsi/ucsi_ccg.c
@@ -664,6 +664,7 @@ static int ucsi_ccg_sync_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations ucsi_ccg_ops = {
 	.read_version = ucsi_ccg_read_version,
 	.read_cci = ucsi_ccg_read_cci,
+	.poll_cci = ucsi_ccg_read_cci,
 	.read_message_in = ucsi_ccg_read_message_in,
 	.sync_control = ucsi_ccg_sync_control,
 	.async_control = ucsi_ccg_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
index fed39d4580905..8af79101a2fc7 100644
--- a/drivers/usb/typec/ucsi/ucsi_glink.c
+++ b/drivers/usb/typec/ucsi/ucsi_glink.c
@@ -206,6 +206,7 @@ static void pmic_glink_ucsi_connector_status(struct ucsi_connector *con)
 static const struct ucsi_operations pmic_glink_ucsi_ops = {
 	.read_version = pmic_glink_ucsi_read_version,
 	.read_cci = pmic_glink_ucsi_read_cci,
+	.poll_cci = pmic_glink_ucsi_read_cci,
 	.read_message_in = pmic_glink_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = pmic_glink_ucsi_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_stm32g0.c b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
index 6923fad31d795..57ef7d83a4121 100644
--- a/drivers/usb/typec/ucsi/ucsi_stm32g0.c
+++ b/drivers/usb/typec/ucsi/ucsi_stm32g0.c
@@ -424,6 +424,7 @@ static irqreturn_t ucsi_stm32g0_irq_handler(int irq, void *data)
 static const struct ucsi_operations ucsi_stm32g0_ops = {
 	.read_version = ucsi_stm32g0_read_version,
 	.read_cci = ucsi_stm32g0_read_cci,
+	.poll_cci = ucsi_stm32g0_read_cci,
 	.read_message_in = ucsi_stm32g0_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = ucsi_stm32g0_async_control,
diff --git a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
index 4cae85c0dc12a..d33e3f2dd1d80 100644
--- a/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
+++ b/drivers/usb/typec/ucsi/ucsi_yoga_c630.c
@@ -74,6 +74,7 @@ static int yoga_c630_ucsi_async_control(struct ucsi *ucsi, u64 command)
 static const struct ucsi_operations yoga_c630_ucsi_ops = {
 	.read_version = yoga_c630_ucsi_read_version,
 	.read_cci = yoga_c630_ucsi_read_cci,
+	.poll_cci = yoga_c630_ucsi_read_cci,
 	.read_message_in = yoga_c630_ucsi_read_message_in,
 	.sync_control = ucsi_sync_control_common,
 	.async_control = yoga_c630_ucsi_async_control,

From bf4f9ae1cb08ccaafbe6874be6c46f59b83ae778 Mon Sep 17 00:00:00 2001
From: Fedor Pchelkin <boddah8794@gmail.com>
Date: Mon, 17 Feb 2025 13:54:40 +0300
Subject: [PATCH 0784/2753] usb: typec: ucsi: increase timeout for PPM reset
 operations

It is observed that on some systems an initial PPM reset during the boot
phase can trigger a timeout:

[    6.482546] ucsi_acpi USBC000:00: failed to reset PPM!
[    6.482551] ucsi_acpi USBC000:00: error -ETIMEDOUT: PPM init failed

Still, increasing the timeout value, albeit being the most straightforward
solution, eliminates the problem: the initial PPM reset may take up to
~8000-10000ms on some Lenovo laptops. When it is reset after the above
period of time (or even if ucsi_reset_ppm() is not called overall), UCSI
works as expected.

Moreover, if the ucsi_acpi module is loaded/unloaded manually after the
system has booted, reading the CCI values and resetting the PPM works
perfectly, without any timeout. Thus it's only a boot-time issue.

The reason for this behavior is not clear but it may be the consequence
of some tricks that the firmware performs or be an actual firmware bug.
As a workaround, increase the timeout to avoid failing the UCSI
initialization prematurely.

Fixes: b1b59e16075f ("usb: typec: ucsi: Increase command completion timeout value")
Cc: stable <stable@kernel.org>
Signed-off-by: Fedor Pchelkin <boddah8794@gmail.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250217105442.113486-3-boddah8794@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 0fe1476f4c297..7a56d3f840d75 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -25,7 +25,7 @@
  * difficult to estimate the time it takes for the system to process the command
  * before it is actually passed to the PPM.
  */
-#define UCSI_TIMEOUT_MS		5000
+#define UCSI_TIMEOUT_MS		10000
 
 /*
  * UCSI_SWAP_TIMEOUT_MS - Timeout for role swap requests

From a321d163de3d8aa38a6449ab2becf4b1581aed96 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 8 Jan 2025 19:09:27 +0530
Subject: [PATCH 0785/2753] bus: mhi: host: pci_generic: Use
 pci_try_reset_function() to avoid deadlock

There are multiple places from where the recovery work gets scheduled
asynchronously. Also, there are multiple places where the caller waits
synchronously for the recovery to be completed. One such place is during
the PM shutdown() callback.

If the device is not alive during recovery_work, it will try to reset the
device using pci_reset_function(). This function internally will take the
device_lock() first before resetting the device. By this time, if the lock
has already been acquired, then recovery_work will get stalled while
waiting for the lock. And if the lock was already acquired by the caller
which waits for the recovery_work to be completed, it will lead to
deadlock.

This is what happened on the X1E80100 CRD device when the device died
before shutdown() callback. Driver core calls the driver's shutdown()
callback while holding the device_lock() leading to deadlock.

And this deadlock scenario can occur on other paths as well, like during
the PM suspend() callback, where the driver core would hold the
device_lock() before calling driver's suspend() callback. And if the
recovery_work was already started, it could lead to deadlock. This is also
observed on the X1E80100 CRD.

So to fix both issues, use pci_try_reset_function() in recovery_work. This
function first checks for the availability of the device_lock() before
trying to reset the device. If the lock is available, it will acquire it
and reset the device. Otherwise, it will return -EAGAIN. If that happens,
recovery_work will fail with the error message "Recovery failed" as not
much could be done.

Cc: stable@vger.kernel.org # 5.12
Reported-by: Johan Hovold <johan@kernel.org>
Closes: https://lore.kernel.org/mhi/Z1me8iaK7cwgjL92@hovoldconsulting.com
Fixes: 7389337f0a78 ("mhi: pci_generic: Add suspend/resume/recovery procedure")
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Analyzed-by: Johan Hovold <johan@kernel.org>
Link: https://lore.kernel.org/mhi/Z2KKjWY2mPen6GPL@hovoldconsulting.com/
Reviewed-by: Loic Poulain <loic.poulain@linaro.org>
Link: https://lore.kernel.org/r/20250108-mhi_recovery_fix-v1-1-a0a00a17da46@linaro.org
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
---
 drivers/bus/mhi/host/pci_generic.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
index c41119b9079f0..7ffea0f981628 100644
--- a/drivers/bus/mhi/host/pci_generic.c
+++ b/drivers/bus/mhi/host/pci_generic.c
@@ -1095,8 +1095,9 @@ static void mhi_pci_recovery_work(struct work_struct *work)
 err_unprepare:
 	mhi_unprepare_after_power_down(mhi_cntrl);
 err_try_reset:
-	if (pci_reset_function(pdev))
-		dev_err(&pdev->dev, "Recovery failed\n");
+	err = pci_try_reset_function(pdev);
+	if (err)
+		dev_err(&pdev->dev, "Recovery failed: %d\n", err);
 }
 
 static void health_check(struct timer_list *t)

From fa2e55811ae25020a5e9b23a8932e67e6d6261a4 Mon Sep 17 00:00:00 2001
From: Mike Lothian <mike@fireburn.co.uk>
Date: Fri, 14 Feb 2025 12:28:00 +0000
Subject: [PATCH 0786/2753] ntsync: Set the permissions to be 0666

This allows ntsync to be usuable by non-root processes out of the box

Signed-off-by: Mike Lothian <mike@fireburn.co.uk>
Reviewed-by: Elizabeth Figura <zfigura@codeweavers.com>
Link: https://lore.kernel.org/r/20250214122759.2629-2-mike@fireburn.co.uk
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ntsync.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 055395cde42b6..0b4e56d59b3da 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -1208,6 +1208,7 @@ static struct miscdevice ntsync_misc = {
 	.minor		= MISC_DYNAMIC_MINOR,
 	.name		= NTSYNC_NAME,
 	.fops		= &ntsync_fops,
+	.mode		= 0666,
 };
 
 module_misc_device(ntsync_misc);

From fb3331f53e3cb1f1505f918f4f33bb0a3a231e4f Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Tue, 18 Feb 2025 20:34:43 -0700
Subject: [PATCH 0787/2753] io_uring/rsrc: remove unused constants

IO_NODE_ALLOC_CACHE_MAX has been unused since commit fbbb8e991d86
("io_uring/rsrc: get rid of io_rsrc_node allocation cache") removed the
rsrc_node_cache.

IO_RSRC_TAG_TABLE_SHIFT and IO_RSRC_TAG_TABLE_MASK have been unused
since commit 7029acd8a950 ("io_uring/rsrc: get rid of per-ring
io_rsrc_node list") removed the separate tag table for registered nodes.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Li Zetao <lizetao1@huawei.com>
Link: https://lore.kernel.org/r/20250219033444.2020136-1-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rsrc.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/io_uring/rsrc.h b/io_uring/rsrc.h
index 190f7ee45de93..89ea0135a1a0d 100644
--- a/io_uring/rsrc.h
+++ b/io_uring/rsrc.h
@@ -4,12 +4,6 @@
 
 #include <linux/lockdep.h>
 
-#define IO_NODE_ALLOC_CACHE_MAX 32
-
-#define IO_RSRC_TAG_TABLE_SHIFT	(PAGE_SHIFT - 3)
-#define IO_RSRC_TAG_TABLE_MAX	(1U << IO_RSRC_TAG_TABLE_SHIFT)
-#define IO_RSRC_TAG_TABLE_MASK	(IO_RSRC_TAG_TABLE_MAX - 1)
-
 enum {
 	IORING_RSRC_FILE		= 0,
 	IORING_RSRC_BUFFER		= 1,

From 954b8915ff86353037d4246c7129d807a75f898b Mon Sep 17 00:00:00 2001
From: Eddie James <eajames@linux.ibm.com>
Date: Thu, 13 Feb 2025 16:57:46 -0600
Subject: [PATCH 0788/2753] MAINTAINERS: change maintainer for FSI

Due to job transitions, both Joel and Jeremy can no longer maintain
the FSI subsystem. I will take over.
I also replaced Alistair with Ninad as a reviewer, as Alistair doesn't
have access to hardware and hasn't been active.
I also removed the link to Joel's FSI tree as he won't be maintaining
it.

Signed-off-by: Eddie James <eajames@linux.ibm.com>
Acked-by: Jeremy Kerr <jk@ozlabs.org>
Link: https://lore.kernel.org/r/20250213225746.2159118-1-eajames@linux.ibm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 MAINTAINERS | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 25c86f47353de..f6026443526b5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9439,14 +9439,11 @@ F:	include/linux/fscrypt.h
 F:	include/uapi/linux/fscrypt.h
 
 FSI SUBSYSTEM
-M:	Jeremy Kerr <jk@ozlabs.org>
-M:	Joel Stanley <joel@jms.id.au>
-R:	Alistar Popple <alistair@popple.id.au>
-R:	Eddie James <eajames@linux.ibm.com>
+M:	Eddie James <eajames@linux.ibm.com>
+R:	Ninad Palsule <ninad@linux.ibm.com>
 L:	linux-fsi@lists.ozlabs.org
 S:	Supported
 Q:	http://patchwork.ozlabs.org/project/linux-fsi/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/joel/fsi.git
 F:	drivers/fsi/
 F:	include/linux/fsi*.h
 F:	include/trace/events/fsi*.h

From c84e125fff2615b4d9c259e762596134eddd2f27 Mon Sep 17 00:00:00 2001
From: Vasiliy Kovalev <kovalev@altlinux.org>
Date: Sat, 15 Feb 2025 00:51:48 +0300
Subject: [PATCH 0789/2753] ovl: fix UAF in ovl_dentry_update_reval by moving
 dput() in ovl_link_up

The issue was caused by dput(upper) being called before
ovl_dentry_update_reval(), while upper->d_flags was still
accessed in ovl_dentry_remote().

Move dput(upper) after its last use to prevent use-after-free.

BUG: KASAN: slab-use-after-free in ovl_dentry_remote fs/overlayfs/util.c:162 [inline]
BUG: KASAN: slab-use-after-free in ovl_dentry_update_reval+0xd2/0xf0 fs/overlayfs/util.c:167

Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:114
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0xc3/0x620 mm/kasan/report.c:488
 kasan_report+0xd9/0x110 mm/kasan/report.c:601
 ovl_dentry_remote fs/overlayfs/util.c:162 [inline]
 ovl_dentry_update_reval+0xd2/0xf0 fs/overlayfs/util.c:167
 ovl_link_up fs/overlayfs/copy_up.c:610 [inline]
 ovl_copy_up_one+0x2105/0x3490 fs/overlayfs/copy_up.c:1170
 ovl_copy_up_flags+0x18d/0x200 fs/overlayfs/copy_up.c:1223
 ovl_rename+0x39e/0x18c0 fs/overlayfs/dir.c:1136
 vfs_rename+0xf84/0x20a0 fs/namei.c:4893
...
 </TASK>

Fixes: b07d5cc93e1b ("ovl: update of dentry revalidate flags after copy up")
Reported-by: syzbot+316db8a1191938280eb6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=316db8a1191938280eb6
Signed-off-by: Vasiliy Kovalev <kovalev@altlinux.org>
Link: https://lore.kernel.org/r/20250214215148.761147-1-kovalev@altlinux.org
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/overlayfs/copy_up.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 0c28e5fa34077..d7310fcf38881 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -618,7 +618,6 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 	err = PTR_ERR(upper);
 	if (!IS_ERR(upper)) {
 		err = ovl_do_link(ofs, ovl_dentry_upper(c->dentry), udir, upper);
-		dput(upper);
 
 		if (!err) {
 			/* Restore timestamps on parent (best effort) */
@@ -626,6 +625,7 @@ static int ovl_link_up(struct ovl_copy_up_ctx *c)
 			ovl_dentry_set_upper_alias(c->dentry);
 			ovl_dentry_update_reval(c->dentry, upper);
 		}
+		dput(upper);
 	}
 	inode_unlock(udir);
 	if (err)

From 838c17fd077e611b12c78feb0feee1b30ed09b63 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Tue, 11 Feb 2025 09:53:55 +0800
Subject: [PATCH 0790/2753] accel/amdxdna: Add missing include linux/slab.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When compiling without CONFIG_IA32_EMULATION, there can be some errors:

drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘mailbox_release_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:197:2: error: implicit declaration
of function ‘kfree’.
  197 |  kfree(mb_msg);
      |  ^~~~~
drivers/accel/amdxdna/amdxdna_mailbox.c: In function ‘xdna_mailbox_send_msg’:
drivers/accel/amdxdna/amdxdna_mailbox.c:418:11: error:implicit declaration
of function ‘kzalloc’.
  418 |  mb_msg = kzalloc(sizeof(*mb_msg) + pkg_size, GFP_KERNEL);
      |           ^~~~~~~

Add the missing include.

Fixes: b87f920b9344 ("accel/amdxdna: Support hardware mailbox")
Signed-off-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Lizhi Hou <lizhi.hou@amd.com>
Reviewed-by: Jeffrey Hugo <quic_jhugo@quicinc.com>
Signed-off-by: Lizhi Hou <lizhi.hou@amd.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250211015354.3388171-1-suhui@nfschina.com
---
 drivers/accel/amdxdna/amdxdna_mailbox.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/accel/amdxdna/amdxdna_mailbox.c b/drivers/accel/amdxdna/amdxdna_mailbox.c
index 814b16bb1953f..e5301fac13971 100644
--- a/drivers/accel/amdxdna/amdxdna_mailbox.c
+++ b/drivers/accel/amdxdna/amdxdna_mailbox.c
@@ -8,6 +8,7 @@
 #include <linux/bitfield.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
+#include <linux/slab.h>
 #include <linux/xarray.h>
 
 #define CREATE_TRACE_POINTS

From b9275eabe31e6679ae12c46a4a0a18d622db4570 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 18 Feb 2025 00:38:27 +0200
Subject: [PATCH 0791/2753] drm/i915/dp: Fix error handling during 128b/132b
 link training

At the end of a 128b/132b link training sequence, the HW expects the
transcoder training pattern to be set to TPS2 and from that to normal
mode (disabling the training pattern). Transitioning from TPS1 directly
to normal mode leaves the transcoder in a stuck state, resulting in
page-flip timeouts later in the modeset sequence.

Atm, in case of a failure during link training, the transcoder may be
still set to output the TPS1 pattern. Later the transcoder is then set
from TPS1 directly to normal mode in intel_dp_stop_link_train(), leading
to modeset failures later as described above. Fix this by setting the
training patter to TPS2, if the link training failed at any point.

The clue in the specification about the above HW behavior is the
explicit mention that TPS2 must be set after the link training sequence
(and there isn't a similar requirement specified for the 8b/10b link
training), see the Bspec links below.

v2: Add bspec aspect/link to the commit log. (Jani)

Bspec: 54128, 65448, 68849
Cc: stable@vger.kernel.org # v5.18+
Cc: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Acked-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217223828.1166093-2-imre.deak@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 8b4bbaf8ddc1f68f3ee96a706f65fdb1bcd9d355)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 .../gpu/drm/i915/display/intel_dp_link_training.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
index 8b1977cfec503..6696a32cdd3e6 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
@@ -1563,7 +1563,7 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 
 	if (wait_for(intel_dp_128b132b_intra_hop(intel_dp, crtc_state) == 0, 500)) {
 		lt_err(intel_dp, DP_PHY_DPRX, "128b/132b intra-hop not clear\n");
-		return false;
+		goto out;
 	}
 
 	if (intel_dp_128b132b_lane_eq(intel_dp, crtc_state) &&
@@ -1575,6 +1575,19 @@ intel_dp_128b132b_link_train(struct intel_dp *intel_dp,
 	       passed ? "passed" : "failed",
 	       crtc_state->port_clock, crtc_state->lane_count);
 
+out:
+	/*
+	 * Ensure that the training pattern does get set to TPS2 even in case
+	 * of a failure, as is the case at the end of a passing link training
+	 * and what is expected by the transcoder. Leaving TPS1 set (and
+	 * disabling the link train mode in DP_TP_CTL later from TPS1 directly)
+	 * would result in a stuck transcoder HW state and flip-done timeouts
+	 * later in the modeset sequence.
+	 */
+	if (!passed)
+		intel_dp_program_link_training_pattern(intel_dp, crtc_state,
+						       DP_PHY_DPRX, DP_TRAINING_PATTERN_2);
+
 	return passed;
 }
 

From 8058b49bf6fff777bf3f47309c7b15dbef2191af Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Tue, 18 Feb 2025 00:38:28 +0200
Subject: [PATCH 0792/2753] drm/i915/dp: Fix disabling the transcoder function
 in 128b/132b mode

During disabling the transcoder in DP 128b/132b mode (both in case of an
MST master transcoder and in case of SST) the transcoder function must
be first disabled without changing any other field in the register (in
particular leaving the DDI port and mode select fields unchanged) and
clearing the DDI port and mode select fields separately, later during
the disabling sequences. Fix the sequence accordingly.

Bspec: 54128, 65448, 68849
Cc: Jani Nikula <jani.nikula@intel.com>
Fixes: 79a6734cd56e ("drm/i915/ddi: disable trancoder port select for 128b/132b SST")
Signed-off-by: Imre Deak <imre.deak@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250217223828.1166093-3-imre.deak@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 2ed653c7b843db0670136330480842d76cb65cd8)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 2b9240ab547d8..18c66992aa1d8 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -658,7 +658,6 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state
 	struct intel_crtc *crtc = to_intel_crtc(crtc_state->uapi.crtc);
 	struct drm_i915_private *dev_priv = to_i915(crtc->base.dev);
 	enum transcoder cpu_transcoder = crtc_state->cpu_transcoder;
-	bool is_mst = intel_crtc_has_type(crtc_state, INTEL_OUTPUT_DP_MST);
 	u32 ctl;
 
 	if (DISPLAY_VER(dev_priv) >= 11)
@@ -678,8 +677,7 @@ void intel_ddi_disable_transcoder_func(const struct intel_crtc_state *crtc_state
 			 TRANS_DDI_PORT_SYNC_MASTER_SELECT_MASK);
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (!intel_dp_mst_is_master_trans(crtc_state) ||
-		    (!is_mst && intel_dp_is_uhbr(crtc_state))) {
+		if (!intel_dp_mst_is_master_trans(crtc_state)) {
 			ctl &= ~(TGL_TRANS_DDI_PORT_MASK |
 				 TRANS_DDI_MODE_SELECT_MASK);
 		}
@@ -3134,7 +3132,7 @@ static void intel_ddi_post_disable_dp(struct intel_atomic_state *state,
 	intel_dp_set_power(intel_dp, DP_SET_POWER_D3);
 
 	if (DISPLAY_VER(dev_priv) >= 12) {
-		if (is_mst) {
+		if (is_mst || intel_dp_is_uhbr(old_crtc_state)) {
 			enum transcoder cpu_transcoder = old_crtc_state->cpu_transcoder;
 
 			intel_de_rmw(dev_priv,

From 6810c771d3165e6320f991220f0c92519e6bace7 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 19 Feb 2025 16:13:31 +0800
Subject: [PATCH 0793/2753] bpf: Support TCP_RTO_MAX_MS for bpf_setsockopt

Some applications don't want to wait for too long because the
time of retransmission increases exponentially and can reach more
than 10 seconds, for example. Eric implements the core logic
on supporting rto max feature in the stack previously. Based on that,
we can support it for BPF use.

This patch reuses the same logic of TCP_RTO_MAX_MS in do_tcp_setsockopt()
and do_tcp_getsockopt(). BPF program can call bpf_{set/get}sockopt()
to set/get the maximum value of RTO.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219081333.56378-2-kerneljasonxing@gmail.com
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 2ec162dd83c46..ffec7b4357f9f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5382,6 +5382,7 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 	case TCP_USER_TIMEOUT:
 	case TCP_NOTSENT_LOWAT:
 	case TCP_SAVE_SYN:
+	case TCP_RTO_MAX_MS:
 		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;

From 7a93ba804847c3257a2f116b7a0c978835813333 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 19 Feb 2025 16:13:32 +0800
Subject: [PATCH 0794/2753] selftests/bpf: Add rto max for bpf_setsockopt test

Test the TCP_RTO_MAX_MS optname in the existing setget_sockopt test.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250219081333.56378-3-kerneljasonxing@gmail.com
---
 tools/testing/selftests/bpf/progs/bpf_tracing_net.h | 1 +
 tools/testing/selftests/bpf/progs/setget_sockopt.c  | 1 +
 2 files changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
index 59843b430f76a..eb6ed1b7b2efe 100644
--- a/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
+++ b/tools/testing/selftests/bpf/progs/bpf_tracing_net.h
@@ -49,6 +49,7 @@
 #define TCP_SAVED_SYN		28
 #define TCP_CA_NAME_MAX		16
 #define TCP_NAGLE_OFF		1
+#define TCP_RTO_MAX_MS		44
 
 #define TCP_ECN_OK              1
 #define TCP_ECN_QUEUE_CWR       2
diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 6dd4318debbfb..106fe430f41b9 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -61,6 +61,7 @@ static const struct sockopt_test sol_tcp_tests[] = {
 	{ .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, },
 	{ .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS,
 	  .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, },
+	{ .opt = TCP_RTO_MAX_MS, .new = 2000, .expected = 2000, },
 	{ .opt = 0, },
 };
 

From 67b0025d19f99fb9fbb8b62e6975553c183f3a16 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:37 +0000
Subject: [PATCH 0795/2753] io_uring/rw: forbid multishot async reads

At the moment we can't sanely handle queuing an async request from a
multishot context, so disable them. It shouldn't matter as pollable
files / socekts don't normally do async.

Patching it in __io_read() is not the cleanest way, but it's simpler
than other options, so let's fix it there and clean up on top.

Cc: stable@vger.kernel.org
Reported-by: chase xd <sl1589472800@gmail.com>
Fixes: fc68fcda04910 ("io_uring/rw: add support for IORING_OP_READ_MULTISHOT")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/7d51732c125159d17db4fe16f51ec41b936973f8.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 7aa1e4c9f64a3..e8efd97fdee5b 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -880,7 +880,15 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 
-	ret = io_iter_do_read(rw, &io->iter);
+	if (unlikely(req->opcode == IORING_OP_READ_MULTISHOT)) {
+		void *cb_copy = rw->kiocb.ki_complete;
+
+		rw->kiocb.ki_complete = NULL;
+		ret = io_iter_do_read(rw, &io->iter);
+		rw->kiocb.ki_complete = cb_copy;
+	} else {
+		ret = io_iter_do_read(rw, &io->iter);
+	}
 
 	/*
 	 * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
@@ -904,7 +912,8 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	} else if (ret == -EIOCBQUEUED) {
 		return IOU_ISSUE_SKIP_COMPLETE;
 	} else if (ret == req->cqe.res || ret <= 0 || !force_nonblock ||
-		   (req->flags & REQ_F_NOWAIT) || !need_complete_io(req)) {
+		   (req->flags & REQ_F_NOWAIT) || !need_complete_io(req) ||
+		   (issue_flags & IO_URING_F_MULTISHOT)) {
 		/* read all, failed, already did sync or don't want to retry */
 		goto done;
 	}

From 4e43133c6f2319d3e205ea986c507b25d9b41e64 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:38 +0000
Subject: [PATCH 0796/2753] io_uring/rw: don't directly use ki_complete

We want to avoid checking ->ki_complete directly in the io_uring
completion path. Fortunately we have only two callback the selection
of which depend on the ring constant flags, i.e. IOPOLL, so use that
to infer the function.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4eb4bdab8cbcf5bc87083f7047edc81e920ab83c.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index e8efd97fdee5b..27ccc82d78436 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -563,8 +563,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	smp_store_release(&req->iopoll_completed, 1);
 }
 
-static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
+static inline void io_rw_done(struct io_kiocb *req, ssize_t ret)
 {
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
+
 	/* IO was queued async, completion will happen later */
 	if (ret == -EIOCBQUEUED)
 		return;
@@ -586,8 +588,10 @@ static inline void io_rw_done(struct kiocb *kiocb, ssize_t ret)
 		}
 	}
 
-	INDIRECT_CALL_2(kiocb->ki_complete, io_complete_rw_iopoll,
-			io_complete_rw, kiocb, ret);
+	if (req->ctx->flags & IORING_SETUP_IOPOLL)
+		io_complete_rw_iopoll(&rw->kiocb, ret);
+	else
+		io_complete_rw(&rw->kiocb, ret);
 }
 
 static int kiocb_done(struct io_kiocb *req, ssize_t ret,
@@ -598,7 +602,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 
 	if (ret >= 0 && req->flags & REQ_F_CUR_POS)
 		req->file->f_pos = rw->kiocb.ki_pos;
-	if (ret >= 0 && (rw->kiocb.ki_complete == io_complete_rw)) {
+	if (ret >= 0 && !(req->ctx->flags & IORING_SETUP_IOPOLL)) {
 		__io_complete_rw_common(req, ret);
 		/*
 		 * Safe to call io_end from here as we're inline
@@ -609,7 +613,7 @@ static int kiocb_done(struct io_kiocb *req, ssize_t ret,
 		io_req_rw_cleanup(req, issue_flags);
 		return IOU_OK;
 	} else {
-		io_rw_done(&rw->kiocb, ret);
+		io_rw_done(req, ret);
 	}
 
 	return IOU_ISSUE_SKIP_COMPLETE;

From 74f3e875268f1ce2dd01029c29560263212077df Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:39 +0000
Subject: [PATCH 0797/2753] io_uring/rw: move ki_complete init into prep

Initialise ki_complete during request prep stage, we'll depend on it not
being reset during issue in the following patch.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/817624086bd5f0448b08c80623399919fda82f34.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 27ccc82d78436..d162565053892 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -23,6 +23,9 @@
 #include "poll.h"
 #include "rw.h"
 
+static void io_complete_rw(struct kiocb *kiocb, long res);
+static void io_complete_rw_iopoll(struct kiocb *kiocb, long res);
+
 struct io_rw {
 	/* NOTE: kiocb has the file as the first member, so don't do it here */
 	struct kiocb			kiocb;
@@ -289,6 +292,11 @@ static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 	rw->kiocb.dio_complete = NULL;
 	rw->kiocb.ki_flags = 0;
 
+	if (req->ctx->flags & IORING_SETUP_IOPOLL)
+		rw->kiocb.ki_complete = io_complete_rw_iopoll;
+	else
+		rw->kiocb.ki_complete = io_complete_rw;
+
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
@@ -817,10 +825,8 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (ctx->flags & IORING_SETUP_IOPOLL) {
 		if (!(kiocb->ki_flags & IOCB_DIRECT) || !file->f_op->iopoll)
 			return -EOPNOTSUPP;
-
 		kiocb->private = NULL;
 		kiocb->ki_flags |= IOCB_HIPRI;
-		kiocb->ki_complete = io_complete_rw_iopoll;
 		req->iopoll_completed = 0;
 		if (ctx->flags & IORING_SETUP_HYBRID_IOPOLL) {
 			/* make sure every req only blocks once*/
@@ -830,7 +836,6 @@ static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	} else {
 		if (kiocb->ki_flags & IOCB_HIPRI)
 			return -EINVAL;
-		kiocb->ki_complete = io_complete_rw;
 	}
 
 	if (req->flags & REQ_F_HAS_METADATA) {

From 4614de748e78a295ee9b1f54ca87280b101fbdf0 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Wed, 19 Feb 2025 01:33:40 +0000
Subject: [PATCH 0798/2753] io_uring/rw: clean up mshot forced sync mode

Move code forcing synchronous execution of multishot read requests out
a more generic __io_read().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/4ad7b928c776d1ad59addb9fff64ef2d1fc474d5.1739919038.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index d162565053892..9edc6baebd01c 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -889,15 +889,7 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	if (unlikely(ret))
 		return ret;
 
-	if (unlikely(req->opcode == IORING_OP_READ_MULTISHOT)) {
-		void *cb_copy = rw->kiocb.ki_complete;
-
-		rw->kiocb.ki_complete = NULL;
-		ret = io_iter_do_read(rw, &io->iter);
-		rw->kiocb.ki_complete = cb_copy;
-	} else {
-		ret = io_iter_do_read(rw, &io->iter);
-	}
+	ret = io_iter_do_read(rw, &io->iter);
 
 	/*
 	 * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
@@ -995,6 +987,8 @@ int io_read_mshot(struct io_kiocb *req, unsigned int issue_flags)
 	if (!io_file_can_poll(req))
 		return -EBADFD;
 
+	/* make it sync, multishot doesn't support async execution */
+	rw->kiocb.ki_complete = NULL;
 	ret = __io_read(req, issue_flags);
 
 	/*

From fcf857ee1958e9247298251f7615d0c76f1e9b38 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 14:59:02 -0500
Subject: [PATCH 0799/2753] NFS: O_DIRECT writes must check and adjust the file
 length

While it is uncommon for delegations to be held while O_DIRECT writes
are in progress, it is possible. The xfstests generic/647 and
generic/729 both end up triggering that state, and end up failing due to
the fact that the file size is not adjusted.

Reported-by: Chuck Lever <chuck.lever@oracle.com>
Link: https://bugzilla.kernel.org/show_bug.cgi?id=219738
Cc: stable@vger.kernel.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/direct.c | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index f45beea92d034..40e13c9a2873f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -130,6 +130,20 @@ static void nfs_direct_truncate_request(struct nfs_direct_req *dreq,
 		dreq->count = req_start;
 }
 
+static void nfs_direct_file_adjust_size_locked(struct inode *inode,
+					       loff_t offset, size_t count)
+{
+	loff_t newsize = offset + (loff_t)count;
+	loff_t oldsize = i_size_read(inode);
+
+	if (newsize > oldsize) {
+		i_size_write(inode, newsize);
+		NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_SIZE;
+		trace_nfs_size_grow(inode, newsize);
+		nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
+	}
+}
+
 /**
  * nfs_swap_rw - NFS address space operation for swap I/O
  * @iocb: target I/O control block
@@ -741,6 +755,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	struct nfs_direct_req *dreq = hdr->dreq;
 	struct nfs_commit_info cinfo;
 	struct nfs_page *req = nfs_list_entry(hdr->pages.next);
+	struct inode *inode = dreq->inode;
 	int flags = NFS_ODIRECT_DONE;
 
 	trace_nfs_direct_write_completion(dreq);
@@ -762,6 +777,10 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 	}
 	spin_unlock(&dreq->lock);
 
+	spin_lock(&inode->i_lock);
+	nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count);
+	spin_unlock(&inode->i_lock);
+
 	while (!list_empty(&hdr->pages)) {
 
 		req = nfs_list_entry(hdr->pages.next);

From 88025c67fe3c025a0123bc7af50535b97f7af89a Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 14:59:03 -0500
Subject: [PATCH 0800/2753] NFS: Adjust delegated timestamps for O_DIRECT reads
 and writes

Adjust the timestamps if O_DIRECT is being combined with attribute
delegations.

Fixes: e12912d94137 ("NFSv4: Add support for delegated atime and mtime attributes")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/direct.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 40e13c9a2873f..f32f8d7c9122b 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -56,6 +56,7 @@
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 
+#include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
 #include "pnfs.h"
@@ -286,6 +287,8 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 	nfs_direct_count_bytes(dreq, hdr);
 	spin_unlock(&dreq->lock);
 
+	nfs_update_delegated_atime(dreq->inode);
+
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
 		struct page *page = req->wb_page;
@@ -779,6 +782,7 @@ static void nfs_direct_write_completion(struct nfs_pgio_header *hdr)
 
 	spin_lock(&inode->i_lock);
 	nfs_direct_file_adjust_size_locked(inode, dreq->io_start, dreq->count);
+	nfs_update_delegated_mtime_locked(dreq->inode);
 	spin_unlock(&inode->i_lock);
 
 	while (!list_empty(&hdr->pages)) {

From 5bbd6e863b15a85221e49b9bdb2d5d8f0bb91f3d Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 15:00:02 -0500
Subject: [PATCH 0801/2753] SUNRPC: Prevent looping due to rpc_signal_task()
 races

If rpc_signal_task() is called while a task is in an rpc_call_done()
callback function, and the latter calls rpc_restart_call(), the task can
end up looping due to the RPC_TASK_SIGNALLED flag being set without the
tk_rpc_status being set.
Removing the redundant mechanism for signalling the task fixes the
looping behaviour.

Reported-by: Li Lingfeng <lilingfeng3@huawei.com>
Fixes: 39494194f93b ("SUNRPC: Fix races with rpc_killall_tasks()")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 include/linux/sunrpc/sched.h  | 3 +--
 include/trace/events/sunrpc.h | 3 +--
 net/sunrpc/sched.c            | 2 --
 3 files changed, 2 insertions(+), 6 deletions(-)

diff --git a/include/linux/sunrpc/sched.h b/include/linux/sunrpc/sched.h
index fec1e8a1570c3..eac57914dcf32 100644
--- a/include/linux/sunrpc/sched.h
+++ b/include/linux/sunrpc/sched.h
@@ -158,7 +158,6 @@ enum {
 	RPC_TASK_NEED_XMIT,
 	RPC_TASK_NEED_RECV,
 	RPC_TASK_MSG_PIN_WAIT,
-	RPC_TASK_SIGNALLED,
 };
 
 #define rpc_test_and_set_running(t) \
@@ -171,7 +170,7 @@ enum {
 
 #define RPC_IS_ACTIVATED(t)	test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)
 
-#define RPC_SIGNALLED(t)	test_bit(RPC_TASK_SIGNALLED, &(t)->tk_runstate)
+#define RPC_SIGNALLED(t)	(READ_ONCE(task->tk_rpc_status) == -ERESTARTSYS)
 
 /*
  * Task priorities.
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index b13dc275ef4a7..851841336ee65 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -360,8 +360,7 @@ TRACE_EVENT(rpc_request,
 		{ (1UL << RPC_TASK_ACTIVE), "ACTIVE" },			\
 		{ (1UL << RPC_TASK_NEED_XMIT), "NEED_XMIT" },		\
 		{ (1UL << RPC_TASK_NEED_RECV), "NEED_RECV" },		\
-		{ (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" },	\
-		{ (1UL << RPC_TASK_SIGNALLED), "SIGNALLED" })
+		{ (1UL << RPC_TASK_MSG_PIN_WAIT), "MSG_PIN_WAIT" })
 
 DECLARE_EVENT_CLASS(rpc_task_running,
 
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index cef623ea15060..9b45fbdc90cab 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -864,8 +864,6 @@ void rpc_signal_task(struct rpc_task *task)
 	if (!rpc_task_set_rpc_status(task, -ERESTARTSYS))
 		return;
 	trace_rpc_task_signalled(task, task->tk_action);
-	set_bit(RPC_TASK_SIGNALLED, &task->tk_runstate);
-	smp_mb__after_atomic();
 	queue = READ_ONCE(task->tk_waitqueue);
 	if (queue)
 		rpc_wake_up_queued_task(queue, task);

From 8f8df955f078e1a023ee55161935000a67651f38 Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@hammerspace.com>
Date: Sat, 1 Feb 2025 15:00:09 -0500
Subject: [PATCH 0802/2753] NFSv4: Fix a deadlock when recovering state on a
 sillyrenamed file

If the file is sillyrenamed, and slated for delete on close, it is
possible for a server reboot to triggeer an open reclaim, with can again
race with the application call to close(). When that happens, the call
to put_nfs_open_context() can trigger a synchronous delegreturn call
which deadlocks because it is not marked as privileged.

Instead, ensure that the call to nfs4_inode_return_delegation_on_close()
catches the delegreturn, and schedules it asynchronously.

Reported-by: Li Lingfeng <lilingfeng3@huawei.com>
Fixes: adb4b42d19ae ("Return the delegation when deleting sillyrenamed files")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/delegation.c | 37 +++++++++++++++++++++++++++++++++++++
 fs/nfs/delegation.h |  1 +
 fs/nfs/nfs4proc.c   |  3 +++
 3 files changed, 41 insertions(+)

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 035ba52742a50..4db912f562305 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -780,6 +780,43 @@ int nfs4_inode_return_delegation(struct inode *inode)
 	return 0;
 }
 
+/**
+ * nfs4_inode_set_return_delegation_on_close - asynchronously return a delegation
+ * @inode: inode to process
+ *
+ * This routine is called to request that the delegation be returned as soon
+ * as the file is closed. If the file is already closed, the delegation is
+ * immediately returned.
+ */
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode)
+{
+	struct nfs_delegation *delegation;
+	struct nfs_delegation *ret = NULL;
+
+	if (!inode)
+		return;
+	rcu_read_lock();
+	delegation = nfs4_get_valid_delegation(inode);
+	if (!delegation)
+		goto out;
+	spin_lock(&delegation->lock);
+	if (!delegation->inode)
+		goto out_unlock;
+	if (list_empty(&NFS_I(inode)->open_files) &&
+	    !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) {
+		/* Refcount matched in nfs_end_delegation_return() */
+		ret = nfs_get_delegation(delegation);
+	} else
+		set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags);
+out_unlock:
+	spin_unlock(&delegation->lock);
+	if (ret)
+		nfs_clear_verifier_delegated(inode);
+out:
+	rcu_read_unlock();
+	nfs_end_delegation_return(inode, ret, 0);
+}
+
 /**
  * nfs4_inode_return_delegation_on_close - asynchronously return a delegation
  * @inode: inode to process
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 71524d34ed207..8ff5ab9c5c256 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -49,6 +49,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 				  unsigned long pagemod_limit, u32 deleg_type);
 int nfs4_inode_return_delegation(struct inode *inode);
 void nfs4_inode_return_delegation_on_close(struct inode *inode);
+void nfs4_inode_set_return_delegation_on_close(struct inode *inode);
 int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid);
 void nfs_inode_evict_delegation(struct inode *inode);
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index df9669d4ded7f..c25ecdb76d304 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -3906,8 +3906,11 @@ nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx,
 
 static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync)
 {
+	struct dentry *dentry = ctx->dentry;
 	if (ctx->state == NULL)
 		return;
+	if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
+		nfs4_inode_set_return_delegation_on_close(d_inode(dentry));
 	if (is_sync)
 		nfs4_close_sync(ctx->state, _nfs4_ctx_to_openmode(ctx));
 	else

From 7a2f6f7687c5f7083a35317cddec5ad9fa491443 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Tue, 11 Feb 2025 12:31:57 -0500
Subject: [PATCH 0803/2753] SUNRPC: Handle -ETIMEDOUT return from tlshd

If the TLS handshake attempt returns -ETIMEDOUT, we currently translate
that error into -EACCES.  This becomes problematic for cases where the RPC
layer is attempting to re-connect in paths that don't resonably handle
-EACCES, for example: writeback.  The RPC layer can handle -ETIMEDOUT quite
well, however - so if the handshake returns this error let's just pass it
along.

Fixes: 75eb6af7acdf ("SUNRPC: Add a TCP-with-TLS RPC transport class")
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/xprtsock.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c60936d8cef71..6b80b2aaf7639 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2581,7 +2581,15 @@ static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid)
 	struct sock_xprt *lower_transport =
 				container_of(lower_xprt, struct sock_xprt, xprt);
 
-	lower_transport->xprt_err = status ? -EACCES : 0;
+	switch (status) {
+	case 0:
+	case -EACCES:
+	case -ETIMEDOUT:
+		lower_transport->xprt_err = status;
+		break;
+	default:
+		lower_transport->xprt_err = -EACCES;
+	}
 	complete(&lower_transport->handshake_done);
 	xprt_put(lower_xprt);
 }

From 102c51c50db88aedd00a318b7708ad60dbec2e95 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Fri, 14 Feb 2025 13:37:24 +0000
Subject: [PATCH 0804/2753] KVM: arm64: Fix tcr_el2 initialisation in hVHE mode

When not running in VHE mode, cpu_prepare_hyp_mode() computes the value
of TCR_EL2 using the host's TCR_EL1 settings as a starting point. For
nVHE, this amounts to masking out everything apart from the TG0, SH0,
ORGN0, IRGN0 and T0SZ fields before setting the RES1 bits, shifting the
IPS field down to the PS field and setting DS if LPA2 is enabled.

Unfortunately, for hVHE, things go slightly wonky: EPD1 is correctly set
to disable walks via TTBR1_EL2 but then the T1SZ and IPS fields are
corrupted when we mistakenly attempt to initialise the PS and DS fields
in their E2H=0 positions. Furthermore, many fields are retained from
TCR_EL1 which should not be propagated to TCR_EL2. Notably, this means
we can end up with A1 set despite not initialising TTBR1_EL2 at all.
This has been shown to cause unexpected translation faults at EL2 with
pKVM due to TLB invalidation not taking effect when running with a
non-zero ASID.

Fix the TCR_EL2 initialisation code to set PS and DS only when E2H=0,
masking out HD, HA and A1 when E2H=1.

Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Fixes: ad744e8cb346 ("arm64: Allow arm64_sw.hvhe on command line")
Signed-off-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250214133724.13179-1-will@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_arm.h |  2 +-
 arch/arm64/kvm/arm.c             | 15 +++++++--------
 2 files changed, 8 insertions(+), 9 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 8d94a6c0ed5c4..c2417a424b98d 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -119,7 +119,7 @@
 #define TCR_EL2_IRGN0_MASK	TCR_IRGN0_MASK
 #define TCR_EL2_T0SZ_MASK	0x3f
 #define TCR_EL2_MASK	(TCR_EL2_TG0_MASK | TCR_EL2_SH0_MASK | \
-			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK | TCR_EL2_T0SZ_MASK)
+			 TCR_EL2_ORGN0_MASK | TCR_EL2_IRGN0_MASK)
 
 /* VTCR_EL2 Registers bits */
 #define VTCR_EL2_DS		TCR_EL2_DS
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index b8e55a441282f..bc7a37cea2420 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -1980,7 +1980,7 @@ static int kvm_init_vector_slots(void)
 static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 {
 	struct kvm_nvhe_init_params *params = per_cpu_ptr_nvhe_sym(kvm_init_params, cpu);
-	unsigned long tcr, ips;
+	unsigned long tcr;
 
 	/*
 	 * Calculate the raw per-cpu offset without a translation from the
@@ -1994,19 +1994,18 @@ static void __init cpu_prepare_hyp_mode(int cpu, u32 hyp_va_bits)
 	params->mair_el2 = read_sysreg(mair_el1);
 
 	tcr = read_sysreg(tcr_el1);
-	ips = FIELD_GET(TCR_IPS_MASK, tcr);
 	if (cpus_have_final_cap(ARM64_KVM_HVHE)) {
+		tcr &= ~(TCR_HD | TCR_HA | TCR_A1 | TCR_T0SZ_MASK);
 		tcr |= TCR_EPD1_MASK;
 	} else {
+		unsigned long ips = FIELD_GET(TCR_IPS_MASK, tcr);
+
 		tcr &= TCR_EL2_MASK;
-		tcr |= TCR_EL2_RES1;
+		tcr |= TCR_EL2_RES1 | FIELD_PREP(TCR_EL2_PS_MASK, ips);
+		if (lpa2_is_enabled())
+			tcr |= TCR_EL2_DS;
 	}
-	tcr &= ~TCR_T0SZ_MASK;
 	tcr |= TCR_T0SZ(hyp_va_bits);
-	tcr &= ~TCR_EL2_PS_MASK;
-	tcr |= FIELD_PREP(TCR_EL2_PS_MASK, ips);
-	if (lpa2_is_enabled())
-		tcr |= TCR_EL2_DS;
 	params->tcr_el2 = tcr;
 
 	params->pgd_pa = kvm_mmu_get_httbr();

From c4f873c2b65c839ff5e7c996bd9ef5a1e7eae11a Mon Sep 17 00:00:00 2001
From: Torben Nielsen <torben.nielsen@prevas.dk>
Date: Mon, 17 Feb 2025 09:05:01 +0100
Subject: [PATCH 0805/2753] net: dsa: b53: mdio: add support for BCM53101

BCM53101 is a ethernet switch, very similar to the BCM53115.
Enable support for it, in the existing b53 dsa driver.

Signed-off-by: Torben Nielsen <torben.nielsen@prevas.dk>
Signed-off-by: Claus Stovgaard <claus.stovgaard@prevas.dk>
Link: https://patch.msgid.link/20250217080503.1390282-1-claus.stovgaard@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/b53/b53_common.c | 14 ++++++++++++++
 drivers/net/dsa/b53/b53_mdio.c   |  1 +
 drivers/net/dsa/b53/b53_priv.h   |  2 ++
 3 files changed, 17 insertions(+)

diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
index 79dc77835681c..61d164ffb3ae9 100644
--- a/drivers/net/dsa/b53/b53_common.c
+++ b/drivers/net/dsa/b53/b53_common.c
@@ -2409,6 +2409,19 @@ static const struct b53_chip_data b53_switch_chips[] = {
 		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
 		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
 	},
+	{
+		.chip_id = BCM53101_DEVICE_ID,
+		.dev_name = "BCM53101",
+		.vlans = 4096,
+		.enabled_ports = 0x11f,
+		.arl_bins = 4,
+		.arl_buckets = 512,
+		.vta_regs = B53_VTA_REGS,
+		.imp_port = 8,
+		.duplex_reg = B53_DUPLEX_STAT_GE,
+		.jumbo_pm_reg = B53_JUMBO_PORT_MASK,
+		.jumbo_size_reg = B53_JUMBO_MAX_SIZE,
+	},
 	{
 		.chip_id = BCM53115_DEVICE_ID,
 		.dev_name = "BCM53115",
@@ -2789,6 +2802,7 @@ int b53_switch_detect(struct b53_device *dev)
 			return ret;
 
 		switch (id32) {
+		case BCM53101_DEVICE_ID:
 		case BCM53115_DEVICE_ID:
 		case BCM53125_DEVICE_ID:
 		case BCM53128_DEVICE_ID:
diff --git a/drivers/net/dsa/b53/b53_mdio.c b/drivers/net/dsa/b53/b53_mdio.c
index 31d070bf161a3..43a3b37b731bf 100644
--- a/drivers/net/dsa/b53/b53_mdio.c
+++ b/drivers/net/dsa/b53/b53_mdio.c
@@ -374,6 +374,7 @@ static void b53_mdio_shutdown(struct mdio_device *mdiodev)
 
 static const struct of_device_id b53_of_match[] = {
 	{ .compatible = "brcm,bcm5325" },
+	{ .compatible = "brcm,bcm53101" },
 	{ .compatible = "brcm,bcm53115" },
 	{ .compatible = "brcm,bcm53125" },
 	{ .compatible = "brcm,bcm53128" },
diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h
index 9e9b5bc0c5d6a..0166c37a13a7f 100644
--- a/drivers/net/dsa/b53/b53_priv.h
+++ b/drivers/net/dsa/b53/b53_priv.h
@@ -66,6 +66,7 @@ enum {
 	BCM5395_DEVICE_ID = 0x95,
 	BCM5397_DEVICE_ID = 0x97,
 	BCM5398_DEVICE_ID = 0x98,
+	BCM53101_DEVICE_ID = 0x53101,
 	BCM53115_DEVICE_ID = 0x53115,
 	BCM53125_DEVICE_ID = 0x53125,
 	BCM53128_DEVICE_ID = 0x53128,
@@ -188,6 +189,7 @@ static inline int is531x5(struct b53_device *dev)
 {
 	return dev->chip_id == BCM53115_DEVICE_ID ||
 		dev->chip_id == BCM53125_DEVICE_ID ||
+		dev->chip_id == BCM53101_DEVICE_ID ||
 		dev->chip_id == BCM53128_DEVICE_ID ||
 		dev->chip_id == BCM53134_DEVICE_ID;
 }

From dfc4b67db06ce272d670cd704c13c741f38d246e Mon Sep 17 00:00:00 2001
From: Claus Stovgaard <claus.stovgaard@prevas.dk>
Date: Mon, 17 Feb 2025 09:05:02 +0100
Subject: [PATCH 0806/2753] dt-bindings: net: dsa: b53: add BCM53101 support

BCM53101 is a ethernet switch, very similar to the BCM53115.

Signed-off-by: Claus Stovgaard <claus.stovgaard@prevas.dk>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250217080503.1390282-2-claus.stovgaard@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml
index 4c78c546343f5..d6c957a33b482 100644
--- a/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml
+++ b/Documentation/devicetree/bindings/net/dsa/brcm,b53.yaml
@@ -16,6 +16,7 @@ properties:
   compatible:
     oneOf:
       - const: brcm,bcm5325
+      - const: brcm,bcm53101
       - const: brcm,bcm53115
       - const: brcm,bcm53125
       - const: brcm,bcm53128
@@ -77,6 +78,7 @@ allOf:
           contains:
             enum:
               - brcm,bcm5325
+              - brcm,bcm53101
               - brcm,bcm53115
               - brcm,bcm53125
               - brcm,bcm53128

From 39f970aead3c5afd81d7f4e866a8f3f8fec3dabc Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:02 +0200
Subject: [PATCH 0807/2753] net: fib_rules: Add port mask attributes

Add attributes that allow matching on source and destination ports with
a mask. Matching on the source port with a mask is needed in deployments
where users encode path information into certain bits of the UDP source
port.

Temporarily set the type of the attributes to 'NLA_REJECT' while support
is being added.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/fib_rules.h | 2 ++
 net/core/fib_rules.c           | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 00e9890ca3c05..95ec01b15c654 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -70,6 +70,8 @@ enum {
 	FRA_DSCP,	/* dscp */
 	FRA_FLOWLABEL,	/* flowlabel */
 	FRA_FLOWLABEL_MASK,	/* flowlabel mask */
+	FRA_SPORT_MASK,	/* sport mask */
+	FRA_DPORT_MASK,	/* dport mask */
 	__FRA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 424b4cd4e9e5d..f5b1900770ec6 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -784,6 +784,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_DSCP]	= NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2),
 	[FRA_FLOWLABEL] = { .type = NLA_BE32 },
 	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
+	[FRA_SPORT_MASK] = { .type = NLA_REJECT },
+	[FRA_DPORT_MASK] = { .type = NLA_REJECT },
 };
 
 int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,

From da7665947b668ef7882b40888171e941db11f06a Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:03 +0200
Subject: [PATCH 0808/2753] net: fib_rules: Add port mask support

Add support for configuring and deleting rules that match on source and
destination ports using a mask as well as support for dumping such rules
to user space.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/fib_rules.h |  8 +++++
 net/core/fib_rules.c    | 67 ++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 74 insertions(+), 1 deletion(-)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index 710caacad9da1..cfeb2fd0f5db5 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -43,6 +43,8 @@ struct fib_rule {
 	struct fib_kuid_range	uid_range;
 	struct fib_rule_port_range	sport_range;
 	struct fib_rule_port_range	dport_range;
+	u16			sport_mask;
+	u16			dport_mask;
 	struct rcu_head		rcu;
 };
 
@@ -159,6 +161,12 @@ static inline bool fib_rule_port_range_compare(struct fib_rule_port_range *a,
 		a->end == b->end;
 }
 
+static inline bool
+fib_rule_port_is_range(const struct fib_rule_port_range *range)
+{
+	return range->start != range->end;
+}
+
 static inline bool fib_rule_requires_fldissect(struct fib_rule *rule)
 {
 	return rule->iifindex != LOOPBACK_IFINDEX && (rule->ip_proto ||
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index f5b1900770ec6..ba6beaa63f44e 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -481,11 +481,17 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops,
 						 &rule->sport_range))
 			continue;
 
+		if (rule->sport_mask && r->sport_mask != rule->sport_mask)
+			continue;
+
 		if (fib_rule_port_range_set(&rule->dport_range) &&
 		    !fib_rule_port_range_compare(&r->dport_range,
 						 &rule->dport_range))
 			continue;
 
+		if (rule->dport_mask && r->dport_mask != rule->dport_mask)
+			continue;
+
 		if (!ops->compare(r, frh, tb))
 			continue;
 		return r;
@@ -515,6 +521,33 @@ static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule,
 }
 #endif
 
+static int fib_nl2rule_port_mask(const struct nlattr *mask_attr,
+				 const struct fib_rule_port_range *range,
+				 u16 *port_mask,
+				 struct netlink_ext_ack *extack)
+{
+	if (!fib_rule_port_range_valid(range)) {
+		NL_SET_ERR_MSG_ATTR(extack, mask_attr,
+				    "Cannot specify port mask without port value");
+		return -EINVAL;
+	}
+
+	if (fib_rule_port_is_range(range)) {
+		NL_SET_ERR_MSG_ATTR(extack, mask_attr,
+				    "Cannot specify port mask for port range");
+		return -EINVAL;
+	}
+
+	if (range->start & ~nla_get_u16(mask_attr)) {
+		NL_SET_ERR_MSG_ATTR(extack, mask_attr, "Invalid port mask");
+		return -EINVAL;
+	}
+
+	*port_mask = nla_get_u16(mask_attr);
+
+	return 0;
+}
+
 static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 		       struct netlink_ext_ack *extack,
 		       struct fib_rules_ops *ops,
@@ -644,6 +677,16 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 			NL_SET_ERR_MSG(extack, "Invalid sport range");
 			goto errout_free;
 		}
+		if (!fib_rule_port_is_range(&nlrule->sport_range))
+			nlrule->sport_mask = U16_MAX;
+	}
+
+	if (tb[FRA_SPORT_MASK]) {
+		err = fib_nl2rule_port_mask(tb[FRA_SPORT_MASK],
+					    &nlrule->sport_range,
+					    &nlrule->sport_mask, extack);
+		if (err)
+			goto errout_free;
 	}
 
 	if (tb[FRA_DPORT_RANGE]) {
@@ -653,6 +696,16 @@ static int fib_nl2rule(struct net *net, struct nlmsghdr *nlh,
 			NL_SET_ERR_MSG(extack, "Invalid dport range");
 			goto errout_free;
 		}
+		if (!fib_rule_port_is_range(&nlrule->dport_range))
+			nlrule->dport_mask = U16_MAX;
+	}
+
+	if (tb[FRA_DPORT_MASK]) {
+		err = fib_nl2rule_port_mask(tb[FRA_DPORT_MASK],
+					    &nlrule->dport_range,
+					    &nlrule->dport_mask, extack);
+		if (err)
+			goto errout_free;
 	}
 
 	*rule = nlrule;
@@ -751,10 +804,16 @@ static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh,
 						 &rule->sport_range))
 			continue;
 
+		if (r->sport_mask != rule->sport_mask)
+			continue;
+
 		if (!fib_rule_port_range_compare(&r->dport_range,
 						 &rule->dport_range))
 			continue;
 
+		if (r->dport_mask != rule->dport_mask)
+			continue;
+
 		if (!ops->compare(r, frh, tb))
 			continue;
 		return 1;
@@ -1051,7 +1110,9 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 			 + nla_total_size(1) /* FRA_PROTOCOL */
 			 + nla_total_size(1) /* FRA_IP_PROTO */
 			 + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_SPORT_RANGE */
-			 + nla_total_size(sizeof(struct fib_rule_port_range)); /* FRA_DPORT_RANGE */
+			 + nla_total_size(sizeof(struct fib_rule_port_range)) /* FRA_DPORT_RANGE */
+			 + nla_total_size(2) /* FRA_SPORT_MASK */
+			 + nla_total_size(2); /* FRA_DPORT_MASK */
 
 	if (ops->nlmsg_payload)
 		payload += ops->nlmsg_payload(rule);
@@ -1119,8 +1180,12 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 	     nla_put_uid_range(skb, &rule->uid_range)) ||
 	    (fib_rule_port_range_set(&rule->sport_range) &&
 	     nla_put_port_range(skb, FRA_SPORT_RANGE, &rule->sport_range)) ||
+	    (rule->sport_mask && nla_put_u16(skb, FRA_SPORT_MASK,
+					     rule->sport_mask)) ||
 	    (fib_rule_port_range_set(&rule->dport_range) &&
 	     nla_put_port_range(skb, FRA_DPORT_RANGE, &rule->dport_range)) ||
+	    (rule->dport_mask && nla_put_u16(skb, FRA_DPORT_MASK,
+					     rule->dport_mask)) ||
 	    (rule->ip_proto && nla_put_u8(skb, FRA_IP_PROTO, rule->ip_proto)))
 		goto nla_put_failure;
 

From 79a4e21584b7d36df51d452f4dc43221b463a26f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:04 +0200
Subject: [PATCH 0809/2753] ipv4: fib_rules: Add port mask matching

Extend IPv4 FIB rules to match on source and destination ports using a
mask. Note that the mask is only set when not matching on a range.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/fib_rules.h | 11 +++++++++++
 net/ipv4/fib_rules.c    |  8 ++++----
 2 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h
index cfeb2fd0f5db5..5927910ec06e5 100644
--- a/include/net/fib_rules.h
+++ b/include/net/fib_rules.h
@@ -148,6 +148,17 @@ static inline bool fib_rule_port_inrange(const struct fib_rule_port_range *a,
 		ntohs(port) <= a->end;
 }
 
+static inline bool fib_rule_port_match(const struct fib_rule_port_range *range,
+				       u16 port_mask, __be16 port)
+{
+	if ((range->start ^ ntohs(port)) & port_mask)
+		return false;
+	if (!port_mask && fib_rule_port_range_set(range) &&
+	    !fib_rule_port_inrange(range, port))
+		return false;
+	return true;
+}
+
 static inline bool fib_rule_port_range_valid(const struct fib_rule_port_range *a)
 {
 	return a->start != 0 && a->end != 0 && a->end < 0xffff &&
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 041c46787d941..6b3d6a957822b 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -201,12 +201,12 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
 	if (rule->ip_proto && (rule->ip_proto != fl4->flowi4_proto))
 		return 0;
 
-	if (fib_rule_port_range_set(&rule->sport_range) &&
-	    !fib_rule_port_inrange(&rule->sport_range, fl4->fl4_sport))
+	if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask,
+				 fl4->fl4_sport))
 		return 0;
 
-	if (fib_rule_port_range_set(&rule->dport_range) &&
-	    !fib_rule_port_inrange(&rule->dport_range, fl4->fl4_dport))
+	if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask,
+				 fl4->fl4_dport))
 		return 0;
 
 	return 1;

From fc1266a061641ee10feb68ba2c33b85904413606 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:05 +0200
Subject: [PATCH 0810/2753] ipv6: fib_rules: Add port mask matching

Extend IPv6 FIB rules to match on source and destination ports using a
mask. Note that the mask is only set when not matching on a range.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/fib6_rules.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 40af8fd6efa70..0144d01417d9e 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -340,12 +340,12 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
 	if (rule->ip_proto && (rule->ip_proto != fl6->flowi6_proto))
 		return 0;
 
-	if (fib_rule_port_range_set(&rule->sport_range) &&
-	    !fib_rule_port_inrange(&rule->sport_range, fl6->fl6_sport))
+	if (!fib_rule_port_match(&rule->sport_range, rule->sport_mask,
+				 fl6->fl6_sport))
 		return 0;
 
-	if (fib_rule_port_range_set(&rule->dport_range) &&
-	    !fib_rule_port_inrange(&rule->dport_range, fl6->fl6_dport))
+	if (!fib_rule_port_match(&rule->dport_range, rule->dport_mask,
+				 fl6->fl6_dport))
 		return 0;
 
 	return 1;

From 34e406a8492832d30491905a878a2ac853e9ef0f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:06 +0200
Subject: [PATCH 0811/2753] net: fib_rules: Enable port mask usage

Allow user space to configure FIB rules that match on the source and
destination ports with a mask, now that support has been added to the
FIB rule core and the IPv4 and IPv6 address families.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index ba6beaa63f44e..5ddd34cbe7f6d 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -843,8 +843,8 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_DSCP]	= NLA_POLICY_MAX(NLA_U8, INET_DSCP_MASK >> 2),
 	[FRA_FLOWLABEL] = { .type = NLA_BE32 },
 	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
-	[FRA_SPORT_MASK] = { .type = NLA_REJECT },
-	[FRA_DPORT_MASK] = { .type = NLA_REJECT },
+	[FRA_SPORT_MASK] = { .type = NLA_U16 },
+	[FRA_DPORT_MASK] = { .type = NLA_U16 },
 };
 
 int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,

From ab35ebfabb530409d608a1e53138831e346243f0 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:07 +0200
Subject: [PATCH 0812/2753] netlink: specs: Add FIB rule port mask attributes

Add new port mask attributes to the spec. Example:

 # ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_rule.yaml \
	--do newrule \
	--json '{"family": 2, "sport-range": { "start": 12345, "end": 12345 }, "sport-mask": 65535, "action": 1, "table": 1}'
 None
 # ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_rule.yaml \
	--do newrule \
	--json '{"family": 2, "dport-range": { "start": 54321, "end": 54321 }, "dport-mask": 65535, "action": 1, "table": 2}'
 None
 $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_rule.yaml \
	--dump getrule --json '{"family": 2}' --output-json | jq '.[]'
 [...]
 {
   "table": 2,
   "suppress-prefixlen": "0xffffffff",
   "protocol": 0,
   "priority": 32764,
   "dport-range": {
     "start": 54321,
     "end": 54321
   },
   "dport-mask": "0xffff",
   "family": 2,
   "dst-len": 0,
   "src-len": 0,
   "tos": 0,
   "action": "to-tbl",
   "flags": 0
 }
 {
   "table": 1,
   "suppress-prefixlen": "0xffffffff",
   "protocol": 0,
   "priority": 32765,
   "sport-range": {
     "start": 12345,
     "end": 12345
   },
   "sport-mask": "0xffff",
   "family": 2,
   "dst-len": 0,
   "src-len": 0,
   "tos": 0,
   "action": "to-tbl",
   "flags": 0
 }
 [...]

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-7-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_rule.yaml | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/netlink/specs/rt_rule.yaml b/Documentation/netlink/specs/rt_rule.yaml
index a9debac3058a0..b30c924087fa8 100644
--- a/Documentation/netlink/specs/rt_rule.yaml
+++ b/Documentation/netlink/specs/rt_rule.yaml
@@ -182,6 +182,14 @@ attribute-sets:
         type: u32
         byte-order: big-endian
         display-hint: hex
+      -
+        name: sport-mask
+        type: u16
+        display-hint: hex
+      -
+        name: dport-mask
+        type: u16
+        display-hint: hex
 
 operations:
   enum-model: directional
@@ -215,6 +223,8 @@ operations:
             - dscp
             - flowlabel
             - flowlabel-mask
+            - sport-mask
+            - dport-mask
     -
       name: newrule-ntf
       doc: Notify a rule creation

From 94694aa64100dc5521477828f5dfd367af158674 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:08 +0200
Subject: [PATCH 0813/2753] selftests: fib_rule_tests: Add port range match
 tests

Currently, only matching on specific ports is tested. Add port range
testing to make sure this use case does not regress.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-8-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 847936363a12b..12a6e219d683f 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -256,6 +256,14 @@ fib_rule6_test()
 		fib_rule6_test_match_n_redirect "$match" "$match" \
 			"$getnomatch" "sport and dport redirect to table" \
 			"sport and dport no redirect to table"
+
+		match="sport 100-200 dport 300-400"
+		getmatch="sport 100 dport 400"
+		getnomatch="sport 100 dport 401"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" \
+			"sport and dport range redirect to table" \
+			"sport and dport range no redirect to table"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"
@@ -525,6 +533,14 @@ fib_rule4_test()
 		fib_rule4_test_match_n_redirect "$match" "$match" \
 			"$getnomatch" "sport and dport redirect to table" \
 			"sport and dport no redirect to table"
+
+		match="sport 100-200 dport 300-400"
+		getmatch="sport 100 dport 400"
+		getnomatch="sport 100 dport 401"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" \
+			"sport and dport range redirect to table" \
+			"sport and dport range no redirect to table"
 	fi
 
 	fib_check_iproute_support "ipproto" "ipproto"

From f5d783c088754eb3dc32b3d927229d6e6c6c0f4e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Mon, 17 Feb 2025 15:41:09 +0200
Subject: [PATCH 0814/2753] selftests: fib_rule_tests: Add port mask match
 tests

Add tests for FIB rules that match on source and destination ports with
a mask. Test both good and bad flows.

 # ./fib_rule_tests.sh
 IPv6 FIB rule tests
 [...]
    TEST: rule6 check: sport and dport redirect to table                [ OK ]
    TEST: rule6 check: sport and dport no redirect to table             [ OK ]
    TEST: rule6 del by pref: sport and dport redirect to table          [ OK ]
    TEST: rule6 check: sport and dport range redirect to table          [ OK ]
    TEST: rule6 check: sport and dport range no redirect to table       [ OK ]
    TEST: rule6 del by pref: sport and dport range redirect to table    [ OK ]
    TEST: rule6 check: sport and dport masked redirect to table         [ OK ]
    TEST: rule6 check: sport and dport masked no redirect to table      [ OK ]
    TEST: rule6 del by pref: sport and dport masked redirect to table   [ OK ]
 [...]

 Tests passed: 292
 Tests failed:   0

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250217134109.311176-9-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 20 +++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 12a6e219d683f..06c51d7ceb4a1 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -266,6 +266,16 @@ fib_rule6_test()
 			"sport and dport range no redirect to table"
 	fi
 
+	ip rule help 2>&1 | grep sport | grep -q MASK
+	if [ $? -eq 0 ]; then
+		match="sport 0x0f00/0xff00 dport 0x000f/0x00ff"
+		getmatch="sport 0x0f11 dport 0x220f"
+		getnomatch="sport 0x1f11 dport 0x221f"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "sport and dport masked redirect to table" \
+			"sport and dport masked no redirect to table"
+	fi
+
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto tcp"
@@ -543,6 +553,16 @@ fib_rule4_test()
 			"sport and dport range no redirect to table"
 	fi
 
+	ip rule help 2>&1 | grep sport | grep -q MASK
+	if [ $? -eq 0 ]; then
+		match="sport 0x0f00/0xff00 dport 0x000f/0x00ff"
+		getmatch="sport 0x0f11 dport 0x220f"
+		getnomatch="sport 0x1f11 dport 0x221f"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "sport and dport masked redirect to table" \
+			"sport and dport masked no redirect to table"
+	fi
+
 	fib_check_iproute_support "ipproto" "ipproto"
 	if [ $? -eq 0 ]; then
 		match="ipproto tcp"

From 47dfd7a72257e91171d56e220ea484a04df89847 Mon Sep 17 00:00:00 2001
From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Date: Mon, 17 Feb 2025 17:34:15 -0800
Subject: [PATCH 0815/2753] net: mana: Add debug logs in MANA network driver

Add more logs to assist in debugging and monitoring
driver behaviour, making it easier to identify potential
issues  during development and testing.

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Link: https://patch.msgid.link/1739842455-23899-1-git-send-email-ernis@linux.microsoft.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/microsoft/mana/gdma_main.c   | 50 +++++++++++++---
 .../net/ethernet/microsoft/mana/hw_channel.c  |  6 +-
 drivers/net/ethernet/microsoft/mana/mana_en.c | 58 +++++++++++++++----
 3 files changed, 94 insertions(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index be95336ce089a..c15a5ef4674e8 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -666,8 +666,11 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	queue->head = 0;
 	queue->tail = 0;
@@ -688,6 +691,8 @@ int mana_gd_create_hwc_queue(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
@@ -770,7 +775,13 @@ static int mana_gd_create_dma_region(struct gdma_dev *gd,
 	}
 
 	gmi->dma_region_handle = resp.dma_region_handle;
+	dev_dbg(gc->dev, "Created DMA region handle 0x%llx\n",
+		gmi->dma_region_handle);
 out:
+	if (err)
+		dev_dbg(gc->dev,
+			"Failed to create DMA region of length: %u, page_type: %d, status: 0x%x, err: %d\n",
+			length, req->gdma_page_type, resp.hdr.status, err);
 	kfree(req);
 	return err;
 }
@@ -793,8 +804,11 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, gdma memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	err = mana_gd_create_dma_region(gd, gmi);
 	if (err)
@@ -815,6 +829,8 @@ int mana_gd_create_mana_eq(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
@@ -841,8 +857,11 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 
 	gmi = &queue->mem_info;
 	err = mana_gd_alloc_memory(gc, spec->queue_size, gmi);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "GDMA queue type: %d, size: %u, memory allocation err: %d\n",
+			spec->type, spec->queue_size, err);
 		goto free_q;
+	}
 
 	err = mana_gd_create_dma_region(gd, gmi);
 	if (err)
@@ -862,6 +881,8 @@ int mana_gd_create_mana_wq_cq(struct gdma_dev *gd,
 	*queue_ptr = queue;
 	return 0;
 out:
+	dev_err(gc->dev, "Failed to create queue type %d of size: %u, err: %d\n",
+		spec->type, spec->queue_size, err);
 	mana_gd_free_memory(gmi);
 free_q:
 	kfree(queue);
@@ -1157,8 +1178,11 @@ int mana_gd_post_and_ring(struct gdma_queue *queue,
 	int err;
 
 	err = mana_gd_post_work_request(queue, wqe_req, wqe_info);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "Failed to post work req from queue type %d of size %u (err=%d)\n",
+			queue->type, queue->queue_size, err);
 		return err;
+	}
 
 	mana_gd_wq_ring_doorbell(gc, queue);
 
@@ -1435,8 +1459,10 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	mana_smc_init(&gc->shm_channel, gc->dev, gc->shm_base);
 
 	err = mana_gd_setup_irqs(pdev);
-	if (err)
+	if (err) {
+		dev_err(gc->dev, "Failed to setup IRQs: %d\n", err);
 		return err;
+	}
 
 	err = mana_hwc_create_channel(gc);
 	if (err)
@@ -1454,12 +1480,14 @@ static int mana_gd_setup(struct pci_dev *pdev)
 	if (err)
 		goto destroy_hwc;
 
+	dev_dbg(&pdev->dev, "mana gdma setup successful\n");
 	return 0;
 
 destroy_hwc:
 	mana_hwc_destroy_channel(gc);
 remove_irq:
 	mana_gd_remove_irqs(pdev);
+	dev_err(&pdev->dev, "%s failed (error %d)\n", __func__, err);
 	return err;
 }
 
@@ -1470,6 +1498,7 @@ static void mana_gd_cleanup(struct pci_dev *pdev)
 	mana_hwc_destroy_channel(gc);
 
 	mana_gd_remove_irqs(pdev);
+	dev_dbg(&pdev->dev, "mana gdma cleanup successful\n");
 }
 
 static bool mana_is_pf(unsigned short dev_id)
@@ -1488,8 +1517,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	BUILD_BUG_ON(2 * MAX_PORTS_IN_MANA_DEV * GDMA_EQE_SIZE > EQ_SIZE);
 
 	err = pci_enable_device(pdev);
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable pci device (err=%d)\n", err);
 		return -ENXIO;
+	}
 
 	pci_set_master(pdev);
 
@@ -1498,9 +1529,10 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto disable_dev;
 
 	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
-	if (err)
+	if (err) {
+		dev_err(&pdev->dev, "DMA set mask failed: %d\n", err);
 		goto release_region;
-
+	}
 	dma_set_max_seg_size(&pdev->dev, UINT_MAX);
 
 	err = -ENOMEM;
@@ -1575,6 +1607,8 @@ static void mana_gd_remove(struct pci_dev *pdev)
 
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
+
+	dev_dbg(&pdev->dev, "mana gdma remove successful\n");
 }
 
 /* The 'state' parameter is not used. */
diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index a00f915c51881..1ba49602089bb 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -440,7 +440,8 @@ static int mana_hwc_alloc_dma_buf(struct hw_channel_context *hwc, u16 q_depth,
 	gmi = &dma_buf->mem_info;
 	err = mana_gd_alloc_memory(gc, buf_size, gmi);
 	if (err) {
-		dev_err(hwc->dev, "Failed to allocate DMA buffer: %d\n", err);
+		dev_err(hwc->dev, "Failed to allocate DMA buffer size: %u, err %d\n",
+			buf_size, err);
 		goto out;
 	}
 
@@ -529,6 +530,9 @@ static int mana_hwc_create_wq(struct hw_channel_context *hwc,
 out:
 	if (err)
 		mana_hwc_destroy_wq(hwc, hwc_wq);
+
+	dev_err(hwc->dev, "Failed to create HWC queue size= %u type= %d err= %d\n",
+		queue_size, q_type, err);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 3b0fb4d95cf71..0411a1897f573 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -52,10 +52,12 @@ static int mana_open(struct net_device *ndev)
 {
 	struct mana_port_context *apc = netdev_priv(ndev);
 	int err;
-
 	err = mana_alloc_queues(ndev);
-	if (err)
+
+	if (err) {
+		netdev_err(ndev, "%s failed to allocate queues: %d\n", __func__, err);
 		return err;
+	}
 
 	apc->port_is_up = true;
 
@@ -64,7 +66,7 @@ static int mana_open(struct net_device *ndev)
 
 	netif_carrier_on(ndev);
 	netif_tx_wake_all_queues(ndev);
-
+	netdev_dbg(ndev, "%s successful\n", __func__);
 	return 0;
 }
 
@@ -176,6 +178,9 @@ static int mana_map_skb(struct sk_buff *skb, struct mana_port_context *apc,
 	return 0;
 
 frag_err:
+	if (net_ratelimit())
+		netdev_err(apc->ndev, "Failed to map skb of size %u to DMA\n",
+			   skb->len);
 	for (i = sg_i - 1; i >= hsg; i--)
 		dma_unmap_page(dev, ash->dma_handle[i], ash->size[i],
 			       DMA_TO_DEVICE);
@@ -690,6 +695,7 @@ int mana_pre_alloc_rxbufs(struct mana_port_context *mpc, int new_mtu, int num_qu
 	return 0;
 
 error:
+	netdev_err(mpc->ndev, "Failed to pre-allocate RX buffers for %d queues\n", num_queues);
 	mana_pre_dealloc_rxbufs(mpc);
 	return -ENOMEM;
 }
@@ -1307,8 +1313,10 @@ static int mana_create_eq(struct mana_context *ac)
 	for (i = 0; i < gc->max_num_queues; i++) {
 		spec.eq.msix_index = (i + 1) % gc->num_msix_usable;
 		err = mana_gd_create_mana_eq(gd, &spec, &ac->eqs[i].eq);
-		if (err)
+		if (err) {
+			dev_err(gc->dev, "Failed to create EQ %d : %d\n", i, err);
 			goto out;
+		}
 		mana_create_eq_debugfs(ac, i);
 	}
 
@@ -2083,6 +2091,8 @@ static int mana_create_txq(struct mana_port_context *apc,
 
 	return 0;
 out:
+	netdev_err(net, "Failed to create %d TX queues, %d\n",
+		   apc->num_queues, err);
 	mana_destroy_txq(apc);
 	return err;
 }
@@ -2418,6 +2428,7 @@ static int mana_add_rx_queues(struct mana_port_context *apc,
 		rxq = mana_create_rxq(apc, i, &ac->eqs[i], ndev);
 		if (!rxq) {
 			err = -ENOMEM;
+			netdev_err(ndev, "Failed to create rxq %d : %d\n", i, err);
 			goto out;
 		}
 
@@ -2664,12 +2675,18 @@ int mana_alloc_queues(struct net_device *ndev)
 	int err;
 
 	err = mana_create_vport(apc, ndev);
-	if (err)
+	if (err) {
+		netdev_err(ndev, "Failed to create vPort %u : %d\n", apc->port_idx, err);
 		return err;
+	}
 
 	err = netif_set_real_num_tx_queues(ndev, apc->num_queues);
-	if (err)
+	if (err) {
+		netdev_err(ndev,
+			   "netif_set_real_num_tx_queues () failed for ndev with num_queues %u : %d\n",
+			   apc->num_queues, err);
 		goto destroy_vport;
+	}
 
 	err = mana_add_rx_queues(apc, ndev);
 	if (err)
@@ -2678,14 +2695,20 @@ int mana_alloc_queues(struct net_device *ndev)
 	apc->rss_state = apc->num_queues > 1 ? TRI_STATE_TRUE : TRI_STATE_FALSE;
 
 	err = netif_set_real_num_rx_queues(ndev, apc->num_queues);
-	if (err)
+	if (err) {
+		netdev_err(ndev,
+			   "netif_set_real_num_rx_queues () failed for ndev with num_queues %u : %d\n",
+			   apc->num_queues, err);
 		goto destroy_vport;
+	}
 
 	mana_rss_table_init(apc);
 
 	err = mana_config_rss(apc, TRI_STATE_TRUE, true, true);
-	if (err)
+	if (err) {
+		netdev_err(ndev, "Failed to configure RSS table: %d\n", err);
 		goto destroy_vport;
+	}
 
 	if (gd->gdma_context->is_pf) {
 		err = mana_pf_register_filter(apc);
@@ -2826,8 +2849,10 @@ int mana_detach(struct net_device *ndev, bool from_close)
 
 	if (apc->port_st_save) {
 		err = mana_dealloc_queues(ndev);
-		if (err)
+		if (err) {
+			netdev_err(ndev, "%s failed to deallocate queues: %d\n", __func__, err);
 			return err;
+		}
 	}
 
 	if (!from_close) {
@@ -2973,6 +2998,8 @@ static int add_adev(struct gdma_dev *gd)
 		goto add_fail;
 
 	gd->adev = adev;
+	dev_dbg(gd->gdma_context->dev,
+		"Auxiliary device added successfully\n");
 	return 0;
 
 add_fail:
@@ -3014,8 +3041,10 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 	}
 
 	err = mana_create_eq(ac);
-	if (err)
+	if (err) {
+		dev_err(dev, "Failed to create EQs: %d\n", err);
 		goto out;
+	}
 
 	err = mana_query_device_cfg(ac, MANA_MAJOR_VERSION, MANA_MINOR_VERSION,
 				    MANA_MICRO_VERSION, &num_ports);
@@ -3071,8 +3100,14 @@ int mana_probe(struct gdma_dev *gd, bool resuming)
 
 	err = add_adev(gd);
 out:
-	if (err)
+	if (err) {
 		mana_remove(gd, false);
+	} else {
+		dev_dbg(dev, "gd=%p, id=%u, num_ports=%d, type=%u, instance=%u\n",
+			gd, gd->dev_id.as_uint32, ac->num_ports,
+			gd->dev_id.type, gd->dev_id.instance);
+		dev_dbg(dev, "%s succeeded\n", __func__);
+	}
 
 	return err;
 }
@@ -3134,6 +3169,7 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
 	gd->driver_data = NULL;
 	gd->gdma_context = NULL;
 	kfree(ac);
+	dev_dbg(dev, "%s succeeded\n", __func__);
 }
 
 struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index)

From ff1a9b2e311f6894afe39b0000dc7482498eb2d1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 18 Feb 2025 10:24:29 +0000
Subject: [PATCH 0816/2753] net: stmmac: clarify priv->pause and pause module
 parameter

priv->pause corresponds with "pause_time" in the 802.3 specification,
and is also called "pause_time" in the various MAC backends. For
consistency, use the same name in the core stmmac code.

Clarify the units of the "pause" module parameter which sets up this
struct member to indicate that it's in units of the pause_quanta
defined by 802.3, which is 512 bit times.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/E1tkKmD-004ObA-9K@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      | 2 +-
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index f05cae103d836..c602ace572b28 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -283,7 +283,7 @@ struct stmmac_priv {
 
 	int speed;
 	unsigned int flow_ctrl;
-	unsigned int pause;
+	unsigned int pause_time;
 	struct mii_bus *mii;
 
 	struct phylink_config phylink_config;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fd8ca1524e43b..c3a13bd8c9b30 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -94,7 +94,7 @@ MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]");
 
 static int pause = PAUSE_TIME;
 module_param(pause, int, 0644);
-MODULE_PARM_DESC(pause, "Flow Control Pause Time");
+MODULE_PARM_DESC(pause, "Flow Control Pause Time (units of 512 bit times)");
 
 #define TC_DEFAULT 64
 static int tc = TC_DEFAULT;
@@ -865,7 +865,7 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 
 	stmmac_flow_ctrl(priv, priv->hw, duplex, priv->flow_ctrl,
-			priv->pause, tx_cnt);
+			 priv->pause_time, tx_cnt);
 }
 
 static unsigned long stmmac_mac_get_caps(struct phylink_config *config,
@@ -7404,7 +7404,7 @@ int stmmac_dvr_probe(struct device *device,
 		return -ENOMEM;
 
 	stmmac_set_ethtool_ops(ndev);
-	priv->pause = pause;
+	priv->pause_time = pause;
 	priv->plat = plat_dat;
 	priv->ioaddr = res->addr;
 	priv->dev->base_addr = (unsigned long)res->addr;

From bc9d75b0aaed795dcd6009336500fd6094e0c944 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 18 Feb 2025 10:24:34 +0000
Subject: [PATCH 0817/2753] net: stmmac: remove useless priv->flow_ctrl

priv->flow_ctrl is only accessed by stmmac_main.c, and the only place
that it is read is in stmmac_mac_flow_ctrl(). This function is only
called from stmmac_mac_link_up() which always sets priv->flow_ctrl
immediately before calling this function.

Therefore, initialising this at probe time is ineffectual because it
will always be overwritten before it's read. As such, the "flow_ctrl"
module parameter has been useless for some time. Rather than remove
the module parameter, which would risk module load failure, change the
description to indicate that it is obsolete, and warn if it is set by
userspace.

Moreover, storing the value in the stmmac_priv has no benefit as it's
set and then immediately read stmmac_mac_flow_ctrl(). Instead, pass it
as a parameter to this function..

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Link: https://patch.msgid.link/E1tkKmI-004ObG-DL@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |  1 -
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 33 +++++++++----------
 2 files changed, 16 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index c602ace572b28..3395188c198aa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -282,7 +282,6 @@ struct stmmac_priv {
 	struct stmmac_channel channel[STMMAC_CH_MAX];
 
 	int speed;
-	unsigned int flow_ctrl;
 	unsigned int pause_time;
 	struct mii_bus *mii;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c3a13bd8c9b30..4d542f482ecbb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -88,9 +88,9 @@ MODULE_PARM_DESC(phyaddr, "Physical device address");
 #define STMMAC_XDP_TX		BIT(1)
 #define STMMAC_XDP_REDIRECT	BIT(2)
 
-static int flow_ctrl = FLOW_AUTO;
+static int flow_ctrl = 0xdead;
 module_param(flow_ctrl, int, 0644);
-MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off]");
+MODULE_PARM_DESC(flow_ctrl, "Flow control ability [on/off] (obsolete)");
 
 static int pause = PAUSE_TIME;
 module_param(pause, int, 0644);
@@ -188,12 +188,11 @@ static void stmmac_verify_args(void)
 		watchdog = TX_TIMEO;
 	if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
 		buf_sz = DEFAULT_BUFSIZE;
-	if (unlikely(flow_ctrl > 1))
-		flow_ctrl = FLOW_AUTO;
-	else if (likely(flow_ctrl < 0))
-		flow_ctrl = FLOW_OFF;
 	if (unlikely((pause < 0) || (pause > 0xffff)))
 		pause = PAUSE_TIME;
+
+	if (flow_ctrl != 0xdead)
+		pr_warn("stmmac: module parameter 'flow_ctrl' is obsolete - please remove from your module configuration\n");
 }
 
 static void __stmmac_disable_all_queues(struct stmmac_priv *priv)
@@ -858,14 +857,16 @@ static void stmmac_release_ptp(struct stmmac_priv *priv)
  *  stmmac_mac_flow_ctrl - Configure flow control in all queues
  *  @priv: driver private structure
  *  @duplex: duplex passed to the next function
+ *  @flow_ctrl: desired flow control modes
  *  Description: It is used for configuring the flow control in all queues
  */
-static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex)
+static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex,
+				 unsigned int flow_ctrl)
 {
 	u32 tx_cnt = priv->plat->tx_queues_to_use;
 
-	stmmac_flow_ctrl(priv, priv->hw, duplex, priv->flow_ctrl,
-			 priv->pause_time, tx_cnt);
+	stmmac_flow_ctrl(priv, priv->hw, duplex, flow_ctrl, priv->pause_time,
+			 tx_cnt);
 }
 
 static unsigned long stmmac_mac_get_caps(struct phylink_config *config,
@@ -925,6 +926,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 			       bool tx_pause, bool rx_pause)
 {
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
+	unsigned int flow_ctrl;
 	u32 old_ctrl, ctrl;
 
 	if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
@@ -1005,15 +1007,15 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 
 	/* Flow Control operation */
 	if (rx_pause && tx_pause)
-		priv->flow_ctrl = FLOW_AUTO;
+		flow_ctrl = FLOW_AUTO;
 	else if (rx_pause && !tx_pause)
-		priv->flow_ctrl = FLOW_RX;
+		flow_ctrl = FLOW_RX;
 	else if (!rx_pause && tx_pause)
-		priv->flow_ctrl = FLOW_TX;
+		flow_ctrl = FLOW_TX;
 	else
-		priv->flow_ctrl = FLOW_OFF;
+		flow_ctrl = FLOW_OFF;
 
-	stmmac_mac_flow_ctrl(priv, duplex);
+	stmmac_mac_flow_ctrl(priv, duplex, flow_ctrl);
 
 	if (ctrl != old_ctrl)
 		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
@@ -7600,9 +7602,6 @@ int stmmac_dvr_probe(struct device *device,
 			 "%s: warning: maxmtu having invalid value (%d)\n",
 			 __func__, priv->plat->maxmtu);
 
-	if (flow_ctrl)
-		priv->flow_ctrl = FLOW_AUTO;	/* RX/TX pause on */
-
 	ndev->priv_flags |= IFF_LIVE_ADDR_CHANGE;
 
 	/* Setup channels NAPI */

From ac9a8587edc78f3a66fdf6a99973ef151cbff72a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 18 Feb 2025 10:24:39 +0000
Subject: [PATCH 0818/2753] net: stmmac: "speed" passed to fix_mac_speed is an
 int

priv->plat->fix_mac_speed() is called from stmmac_mac_link_up(), which
is passed the speed as an "int". However, fix_mac_speed() implicitly
casts this to an unsigned int. Some platform glue code print this value
using %u, others with %d. Some implicitly cast it back to an int, and
others to u32.

Good practice is to use one type and only one type to represent a value
being passed around a driver.

Switch all of these over to consistently use "int" when dealing with a
speed passed from stmmac_mac_link_up(), even though the speed will
always be positive.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Acked-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Link: https://patch.msgid.link/E1tkKmN-004ObM-Ge@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c         | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c  | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c     | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c    | 3 +--
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 6 +++---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c          | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c         | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c     | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c    | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c         | 8 ++++----
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c       | 2 +-
 drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c       | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c    | 2 +-
 include/linux/stmmac.h                                  | 2 +-
 16 files changed, 31 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 1fadb8ba1d2ff..392574bdd4a47 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -141,7 +141,7 @@ static int dwc_qos_probe(struct platform_device *pdev,
 #define AUTO_CAL_STATUS 0x880c
 #define  AUTO_CAL_STATUS_ACTIVE BIT(31)
 
-static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct tegra_eqos *eqos = priv;
 	bool needs_calibration = false;
@@ -160,7 +160,7 @@ static void tegra_eqos_fix_speed(void *priv, unsigned int speed, unsigned int mo
 		break;
 
 	default:
-		dev_err(eqos->dev, "invalid speed %u\n", speed);
+		dev_err(eqos->dev, "invalid speed %d\n", speed);
 		break;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 20d3a202bb8d1..610204b51e3fe 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -51,7 +51,7 @@ struct imx_dwmac_ops {
 
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*set_intf_mode)(struct plat_stmmacenet_data *plat_dat);
-	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 };
 
 struct imx_priv_data {
@@ -192,7 +192,7 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv)
 	/* nothing to do now */
 }
 
-static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void imx_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct plat_stmmacenet_data *plat_dat;
 	struct imx_priv_data *dwmac = priv;
@@ -208,7 +208,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 
 	rate = rgmii_clock(speed);
 	if (rate < 0) {
-		dev_err(dwmac->dev, "invalid speed %u\n", speed);
+		dev_err(dwmac->dev, "invalid speed %d\n", speed);
 		return;
 	}
 
@@ -217,7 +217,7 @@ static void imx_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mod
 		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
 }
 
-static void imx93_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void imx93_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct imx_priv_data *dwmac = priv;
 	unsigned int iface;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index ddee6154d40bc..0591756a2100e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -22,13 +22,13 @@ struct intel_dwmac {
 };
 
 struct intel_dwmac_data {
-	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 	unsigned long ptp_ref_clk_rate;
 	unsigned long tx_clk_rate;
 	bool tx_clk_en;
 };
 
-static void kmb_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void kmb_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct intel_dwmac *dwmac = priv;
 	long rate;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 61227dcf56dc6..7f4b9c1cc32b7 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -112,7 +112,7 @@ struct ipq806x_gmac {
 	phy_interface_t phy_mode;
 };
 
-static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, int speed)
 {
 	struct device *dev = &gmac->pdev->dev;
 	int div;
@@ -138,7 +138,7 @@ static int get_clk_div_sgmii(struct ipq806x_gmac *gmac, unsigned int speed)
 	return div;
 }
 
-static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed)
+static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, int speed)
 {
 	struct device *dev = &gmac->pdev->dev;
 	int div;
@@ -164,7 +164,7 @@ static int get_clk_div_rgmii(struct ipq806x_gmac *gmac, unsigned int speed)
 	return div;
 }
 
-static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, unsigned int speed)
+static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, int speed)
 {
 	uint32_t clk_bits, val;
 	int div;
@@ -260,7 +260,7 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
 	return PTR_ERR_OR_ZERO(gmac->qsgmii_csr);
 }
 
-static void ipq806x_gmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void ipq806x_gmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct ipq806x_gmac *gmac = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index 79acdf38c5254..60a4e3330ccd0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -149,8 +149,7 @@ static struct stmmac_pci_info loongson_gmac_pci_info = {
 	.setup = loongson_gmac_data,
 };
 
-static void loongson_gnet_fix_speed(void *priv, unsigned int speed,
-				    unsigned int mode)
+static void loongson_gnet_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct loongson_data *ld = (struct loongson_data *)priv;
 	struct net_device *ndev = dev_get_drvdata(ld->dev);
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index 5469fa1b429e3..b115b7873cefa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -22,7 +22,7 @@ struct meson_dwmac {
 	void __iomem	*reg;
 };
 
-static void meson6_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void meson6_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct meson_dwmac *dwmac = priv;
 	unsigned int val;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 2a5b38723635b..192f270197c8d 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -111,7 +111,7 @@ struct qcom_ethqos {
 	unsigned int link_clk_rate;
 	struct clk *link_clk;
 	struct phy *serdes_phy;
-	unsigned int speed;
+	int speed;
 	int serdes_speed;
 	phy_interface_t phy_mode;
 
@@ -175,7 +175,7 @@ static void rgmii_dump(void *priv)
 #define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ	  (5 * 1000 * 1000UL)
 
 static void
-ethqos_update_link_clk(struct qcom_ethqos *ethqos, unsigned int speed)
+ethqos_update_link_clk(struct qcom_ethqos *ethqos, int speed)
 {
 	if (!phy_interface_mode_is_rgmii(ethqos->phy_mode))
 		return;
@@ -699,7 +699,7 @@ static int ethqos_configure(struct qcom_ethqos *ethqos)
 	return ethqos->configure_func(ethqos);
 }
 
-static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void ethqos_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct qcom_ethqos *ethqos = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index a4dc89e23a68e..83d104a274c50 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1920,7 +1920,7 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 	gmac_clk_enable(gmac, false);
 }
 
-static void rk_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void rk_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct rk_priv_data *bsp_priv = priv;
 	struct device *dev = &bsp_priv->pdev->dev;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
index 9cc0e5817416e..6a498833b8ed0 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
@@ -100,7 +100,7 @@ static void s32_gmac_exit(struct platform_device *pdev, void *priv)
 	clk_disable_unprepare(gmac->rx_clk);
 }
 
-static void s32_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void s32_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct s32_priv_data *gmac = priv;
 	long tx_clk_rate;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 16020b72dec83..6b78ae7304669 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -61,7 +61,7 @@ struct socfpga_dwmac {
 	struct mdio_device *pcs_mdiodev;
 };
 
-static void socfpga_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void socfpga_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct socfpga_dwmac *dwmac = (struct socfpga_dwmac *)priv;
 	void __iomem *splitter_base = dwmac->splitter_base;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 0a0a363d37309..282c846dad0b2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -31,7 +31,7 @@ struct starfive_dwmac {
 	const struct starfive_dwmac_data *data;
 };
 
-static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void starfive_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct starfive_dwmac *dwmac = priv;
 	long rate;
@@ -39,7 +39,7 @@ static void starfive_dwmac_fix_mac_speed(void *priv, unsigned int speed, unsigne
 
 	rate = rgmii_clock(speed);
 	if (rate < 0) {
-		dev_err(dwmac->dev, "invalid speed %u\n", speed);
+		dev_err(dwmac->dev, "invalid speed %d\n", speed);
 		return;
 	}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index f25461c292fec..13b9c2a51fce4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -99,12 +99,12 @@ struct sti_dwmac {
 	int clk_sel_reg;	/* GMAC ext clk selection register */
 	struct regmap *regmap;
 	bool gmac_en;
-	u32 speed;
-	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
+	int speed;
+	void (*fix_retime_src)(void *priv, int speed, unsigned int mode);
 };
 
 struct sti_dwmac_of_data {
-	void (*fix_retime_src)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_retime_src)(void *priv, int speed, unsigned int mode);
 };
 
 static u32 phy_intf_sels[] = {
@@ -132,7 +132,7 @@ static u32 stih4xx_tx_retime_val[] = {
 				 | STIH4XX_ETH_SEL_INTERNAL_NOTEXT_PHYCLK,
 };
 
-static void stih4xx_fix_retime_src(void *priv, u32 spd, unsigned int mode)
+static void stih4xx_fix_retime_src(void *priv, int spd, unsigned int mode)
 {
 	struct sti_dwmac *dwmac = priv;
 	u32 src = dwmac->tx_retime_src;
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 9ae318436c4a7..1b1ce2888b2eb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -72,7 +72,7 @@ static void sun7i_gmac_exit(struct platform_device *pdev, void *priv)
 		regulator_disable(gmac->regulator);
 }
 
-static void sun7i_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void sun7i_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct sunxi_priv_data *gmac = priv;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index dce84ed184e9a..ddb1d8aba3215 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -104,7 +104,7 @@ static int thead_dwmac_set_txclk_dir(struct plat_stmmacenet_data *plat)
 	return 0;
 }
 
-static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int mode)
+static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct plat_stmmacenet_data *plat;
 	struct thead_dwmac *dwmac = priv;
@@ -142,7 +142,7 @@ static void thead_dwmac_fix_speed(void *priv, unsigned int speed, unsigned int m
 			div = rate * 10 / GMAC_MII_RATE;
 			break;
 		default:
-			dev_err(dwmac->dev, "invalid speed %u\n", speed);
+			dev_err(dwmac->dev, "invalid speed %d\n", speed);
 			return;
 		}
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
index eccf7f5374678..33cf99797df53 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-visconti.c
@@ -54,7 +54,7 @@ struct visconti_eth {
 	spinlock_t lock; /* lock to protect register update */
 };
 
-static void visconti_eth_fix_mac_speed(void *priv, unsigned int speed, unsigned int mode)
+static void visconti_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
 {
 	struct visconti_eth *dwmac = priv;
 	struct net_device *netdev = dev_get_drvdata(dwmac->dev);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 24422ac4e4179..6d2aa77ea9635 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -231,7 +231,7 @@ struct plat_stmmacenet_data {
 	u8 tx_sched_algorithm;
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
 	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
-	void (*fix_mac_speed)(void *priv, unsigned int speed, unsigned int mode);
+	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);

From 23dcacff2d111fb35042edc44d4ce07e85598cce Mon Sep 17 00:00:00 2001
From: Suchit <suchitkarunakaran@gmail.com>
Date: Tue, 18 Feb 2025 22:29:23 +0530
Subject: [PATCH 0819/2753] selftests: net: Fix minor typos in MPTCP and psock
 tests

Fixes minor spelling errors:
- `simult_flows.sh`: "al testcases" -> "all testcases"
- `psock_tpacket.c`: "accross" -> "across"

Signed-off-by: Suchit Karunakaran <suchitkarunakaran@gmail.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218165923.20740-1-suchitkarunakaran@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/simult_flows.sh | 2 +-
 tools/testing/selftests/net/psock_tpacket.c       | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh
index 9c2a415976cbf..2329c2f8519b7 100755
--- a/tools/testing/selftests/net/mptcp/simult_flows.sh
+++ b/tools/testing/selftests/net/mptcp/simult_flows.sh
@@ -28,7 +28,7 @@ size=0
 
 usage() {
 	echo "Usage: $0 [ -b ] [ -c ] [ -d ] [ -i]"
-	echo -e "\t-b: bail out after first error, otherwise runs al testcases"
+	echo -e "\t-b: bail out after first error, otherwise runs all testcases"
 	echo -e "\t-c: capture packets for each test using tcpdump (default: no capture)"
 	echo -e "\t-d: debug this script"
 	echo -e "\t-i: use 'ip mptcp' instead of 'pm_nl_ctl'"
diff --git a/tools/testing/selftests/net/psock_tpacket.c b/tools/testing/selftests/net/psock_tpacket.c
index 404a2ce759ab6..221270cee3eaa 100644
--- a/tools/testing/selftests/net/psock_tpacket.c
+++ b/tools/testing/selftests/net/psock_tpacket.c
@@ -12,7 +12,7 @@
  *
  * Datapath:
  *   Open a pair of packet sockets and send resp. receive an a priori known
- *   packet pattern accross the sockets and check if it was received resp.
+ *   packet pattern across the sockets and check if it was received resp.
  *   sent correctly. Fanout in combination with RX_RING is currently not
  *   tested here.
  *

From 9a6c2b2bdd5ed46f3ab364c975ea7b772b29aec2 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Wed, 19 Feb 2025 02:02:58 +0000
Subject: [PATCH 0820/2753] nfc: hci: Remove unused nfc_llc_unregister

nfc_llc_unregister() has been unused since it was added in 2012's
commit 67cccfe17d1b ("NFC: Add an LLC Core layer to HCI")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250219020258.297995-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/nfc/hci/llc.c | 11 -----------
 net/nfc/hci/llc.h |  1 -
 2 files changed, 12 deletions(-)

diff --git a/net/nfc/hci/llc.c b/net/nfc/hci/llc.c
index ba91284f4086e..e6cf4eb06b46c 100644
--- a/net/nfc/hci/llc.c
+++ b/net/nfc/hci/llc.c
@@ -78,17 +78,6 @@ static struct nfc_llc_engine *nfc_llc_name_to_engine(const char *name)
 	return NULL;
 }
 
-void nfc_llc_unregister(const char *name)
-{
-	struct nfc_llc_engine *llc_engine;
-
-	llc_engine = nfc_llc_name_to_engine(name);
-	if (llc_engine == NULL)
-		return;
-
-	nfc_llc_del_engine(llc_engine);
-}
-
 struct nfc_llc *nfc_llc_allocate(const char *name, struct nfc_hci_dev *hdev,
 				 xmit_to_drv_t xmit_to_drv,
 				 rcv_to_hci_t rcv_to_hci, int tx_headroom,
diff --git a/net/nfc/hci/llc.h b/net/nfc/hci/llc.h
index d66271d211a51..09914608ec43e 100644
--- a/net/nfc/hci/llc.h
+++ b/net/nfc/hci/llc.h
@@ -40,7 +40,6 @@ struct nfc_llc {
 void *nfc_llc_get_data(struct nfc_llc *llc);
 
 int nfc_llc_register(const char *name, const struct nfc_llc_ops *ops);
-void nfc_llc_unregister(const char *name);
 
 int nfc_llc_nop_register(void);
 

From c3349a22c2002947d29a98a77bfb36d97cfbfac1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:12 +0100
Subject: [PATCH 0821/2753] mptcp: consolidate subflow cleanup

Consolidate all the cleanup actions requiring the worker in a single
helper and ensure the dummy data fin creation for fallback socket is
performed only when the tcp rx queue is empty.

There are no functional changes intended, but this will simplify the
next patch, when the tcp rx queue spooling could be delayed at release_cb
time.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-1-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index fd021cf8286ef..2926bdf88e42c 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1271,7 +1271,12 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
 		subflow->map_valid = 0;
 }
 
-/* sched mptcp worker to remove the subflow if no more data is pending */
+static bool subflow_is_done(const struct sock *sk)
+{
+	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
+}
+
+/* sched mptcp worker for subflow cleanup if no more data is pending */
 static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
@@ -1281,8 +1286,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		    inet_sk_state_load(sk) != TCP_ESTABLISHED)))
 		return;
 
-	if (skb_queue_empty(&ssk->sk_receive_queue) &&
-	    !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+	if (!skb_queue_empty(&ssk->sk_receive_queue))
+		return;
+
+	if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+		mptcp_schedule_work(sk);
+
+	/* when the fallback subflow closes the rx side, trigger a 'dummy'
+	 * ingress data fin, so that the msk state will follow along
+	 */
+	if (__mptcp_check_fallback(msk) && subflow_is_done(ssk) &&
+	    msk->first == ssk &&
+	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
 		mptcp_schedule_work(sk);
 }
 
@@ -1842,11 +1857,6 @@ static void __subflow_state_change(struct sock *sk)
 	rcu_read_unlock();
 }
 
-static bool subflow_is_done(const struct sock *sk)
-{
-	return sk->sk_shutdown & RCV_SHUTDOWN || sk->sk_state == TCP_CLOSE;
-}
-
 static void subflow_state_change(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
@@ -1873,13 +1883,6 @@ static void subflow_state_change(struct sock *sk)
 		subflow_error_report(sk);
 
 	subflow_sched_work_if_closed(mptcp_sk(parent), sk);
-
-	/* when the fallback subflow closes the rx side, trigger a 'dummy'
-	 * ingress data fin, so that the msk state will follow along
-	 */
-	if (__mptcp_check_fallback(msk) && subflow_is_done(sk) && msk->first == sk &&
-	    mptcp_update_rcv_data_fin(msk, READ_ONCE(msk->ack_seq), true))
-		mptcp_schedule_work(parent);
 }
 
 void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk)

From f03afb3aeb9d81f6c5ab728a61a040012923e3b3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:13 +0100
Subject: [PATCH 0822/2753] mptcp: drop __mptcp_fastopen_gen_msk_ackseq()

When we will move the whole RX path under the msk socket lock, updating
the already queued skb for passive fastopen socket at 3rd ack time will
be extremely painful and race prone

The map_seq for already enqueued skbs is used only to allow correct
coalescing with later data; preventing collapsing to the first skb of
a fastopen connect we can completely remove the
__mptcp_fastopen_gen_msk_ackseq() helper.

Before dropping this helper, a new item had to be added to the
mptcp_skb_cb structure. Because this item will be frequently tested in
the fast path -- almost on every packet -- and because there is free
space there, a single byte is used instead of a bitfield. This micro
optimisation slightly reduces the number of CPU operations to do the
associated check.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-2-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/fastopen.c | 24 ++----------------------
 net/mptcp/protocol.c |  4 +++-
 net/mptcp/protocol.h |  5 ++---
 net/mptcp/subflow.c  |  3 ---
 4 files changed, 7 insertions(+), 29 deletions(-)

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index a29ff901df758..7777f5a2d1437 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -40,13 +40,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	tp->copied_seq += skb->len;
 	subflow->ssn_offset += skb->len;
 
-	/* initialize a dummy sequence number, we will update it at MPC
-	 * completion, if needed
-	 */
+	/* Only the sequence delta is relevant */
 	MPTCP_SKB_CB(skb)->map_seq = -skb->len;
 	MPTCP_SKB_CB(skb)->end_seq = 0;
 	MPTCP_SKB_CB(skb)->offset = 0;
 	MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+	MPTCP_SKB_CB(skb)->cant_coalesce = 1;
 
 	mptcp_data_lock(sk);
 
@@ -58,22 +57,3 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 
 	mptcp_data_unlock(sk);
 }
-
-void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt)
-{
-	struct sock *sk = (struct sock *)msk;
-	struct sk_buff *skb;
-
-	skb = skb_peek_tail(&sk->sk_receive_queue);
-	if (skb) {
-		WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
-		pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk,
-			 MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
-			 MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
-		MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
-		MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
-	}
-
-	pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq);
-}
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6bd8190474706..55f9698f3c22f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -135,7 +135,8 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	bool fragstolen;
 	int delta;
 
-	if (MPTCP_SKB_CB(from)->offset ||
+	if (unlikely(MPTCP_SKB_CB(to)->cant_coalesce) ||
+	    MPTCP_SKB_CB(from)->offset ||
 	    ((to->len + from->len) > (sk->sk_rcvbuf >> 3)) ||
 	    !skb_try_coalesce(to, from, &fragstolen, &delta))
 		return false;
@@ -366,6 +367,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
 	MPTCP_SKB_CB(skb)->offset = offset;
 	MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
+	MPTCP_SKB_CB(skb)->cant_coalesce = 0;
 
 	if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) {
 		/* in sequence */
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 37226cdd9e371..3c3e9b185ae35 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -129,7 +129,8 @@ struct mptcp_skb_cb {
 	u64 map_seq;
 	u64 end_seq;
 	u32 offset;
-	u8  has_rxtstamp:1;
+	u8  has_rxtstamp;
+	u8  cant_coalesce;
 };
 
 #define MPTCP_SKB_CB(__skb)	((struct mptcp_skb_cb *)&((__skb)->cb[0]))
@@ -1059,8 +1060,6 @@ void mptcp_event_pm_listener(const struct sock *ssk,
 			     enum mptcp_event_type event);
 bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
-void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				     const struct mptcp_options_received *mp_opt);
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
 					      struct request_sock *req);
 int mptcp_nl_fill_addr(struct sk_buff *skb,
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 2926bdf88e42c..d2caffa56bdd9 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -802,9 +802,6 @@ void __mptcp_subflow_fully_established(struct mptcp_sock *msk,
 	subflow_set_remote_key(msk, subflow, mp_opt);
 	WRITE_ONCE(subflow->fully_established, true);
 	WRITE_ONCE(msk->fully_established, true);
-
-	if (subflow->is_mptfo)
-		__mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt);
 }
 
 static struct sock *subflow_syn_recv_sock(const struct sock *sk,

From bc68b0efa1bf923cef1294a631d8e7416c7e06e4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:14 +0100
Subject: [PATCH 0823/2753] mptcp: move the whole rx path under msk socket lock
 protection

After commit c2e6048fa1cf ("mptcp: fix race in release_cb") we can
move the whole MPTCP rx path under the socket lock leveraging the
release_cb.

We can drop a bunch of spin_lock pairs in the receive functions, use
a single receive queue and invoke __mptcp_move_skbs only when subflows
ask for it.

This will allow more cleanup in the next patch.

Some changes are worth specific mention:

The msk rcvbuf update now always happens under both the msk and the
subflow socket lock: we can drop a bunch of ONCE annotation and
consolidate the checks.

When the skbs move is delayed at msk release callback time, even the
msk rcvbuf update is delayed; additionally take care of such action in
__mptcp_move_skbs().

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-3-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/fastopen.c |   1 +
 net/mptcp/protocol.c | 123 ++++++++++++++++++++-----------------------
 net/mptcp/protocol.h |   2 +-
 3 files changed, 60 insertions(+), 66 deletions(-)

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 7777f5a2d1437..f85ad19f3dd6c 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -48,6 +48,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	MPTCP_SKB_CB(skb)->cant_coalesce = 1;
 
 	mptcp_data_lock(sk);
+	DEBUG_NET_WARN_ON_ONCE(sock_owned_by_user_nocheck(sk));
 
 	mptcp_set_owner_r(skb, sk);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 55f9698f3c22f..8bdc7a7a58f31 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -645,18 +645,6 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 	bool more_data_avail;
 	struct tcp_sock *tp;
 	bool done = false;
-	int sk_rbuf;
-
-	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
-
-	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
-		int ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
-
-		if (unlikely(ssk_rbuf > sk_rbuf)) {
-			WRITE_ONCE(sk->sk_rcvbuf, ssk_rbuf);
-			sk_rbuf = ssk_rbuf;
-		}
-	}
 
 	pr_debug("msk=%p ssk=%p\n", msk, ssk);
 	tp = tcp_sk(ssk);
@@ -724,7 +712,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		WRITE_ONCE(tp->copied_seq, seq);
 		more_data_avail = mptcp_subflow_data_available(ssk);
 
-		if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) {
+		if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
 			done = true;
 			break;
 		}
@@ -848,11 +836,30 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 	return moved > 0;
 }
 
+static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk)
+{
+	if (unlikely(ssk->sk_rcvbuf > sk->sk_rcvbuf))
+		WRITE_ONCE(sk->sk_rcvbuf, ssk->sk_rcvbuf);
+}
+
+static void __mptcp_data_ready(struct sock *sk, struct sock *ssk)
+{
+	struct mptcp_sock *msk = mptcp_sk(sk);
+
+	__mptcp_rcvbuf_update(sk, ssk);
+
+	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
+	if (__mptcp_rmem(sk) > sk->sk_rcvbuf)
+		return;
+
+	/* Wake-up the reader only for in-sequence data */
+	if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
+		sk->sk_data_ready(sk);
+}
+
 void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	int sk_rbuf, ssk_rbuf;
 
 	/* The peer can send data while we are shutting down this
 	 * subflow at msk destruction time, but we must avoid enqueuing
@@ -861,19 +868,11 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	if (unlikely(subflow->disposable))
 		return;
 
-	ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf);
-	sk_rbuf = READ_ONCE(sk->sk_rcvbuf);
-	if (unlikely(ssk_rbuf > sk_rbuf))
-		sk_rbuf = ssk_rbuf;
-
-	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (__mptcp_rmem(sk) > sk_rbuf)
-		return;
-
-	/* Wake-up the reader only for in-sequence data */
 	mptcp_data_lock(sk);
-	if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
-		sk->sk_data_ready(sk);
+	if (!sock_owned_by_user(sk))
+		__mptcp_data_ready(sk, ssk);
+	else
+		__set_bit(MPTCP_DEQUEUE, &mptcp_sk(sk)->cb_flags);
 	mptcp_data_unlock(sk);
 }
 
@@ -1946,16 +1945,17 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied);
 
-static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
+static int __mptcp_recvmsg_mskq(struct sock *sk,
 				struct msghdr *msg,
 				size_t len, int flags,
 				struct scm_timestamping_internal *tss,
 				int *cmsg_flags)
 {
+	struct mptcp_sock *msk = mptcp_sk(sk);
 	struct sk_buff *skb, *tmp;
 	int copied = 0;
 
-	skb_queue_walk_safe(&msk->receive_queue, skb, tmp) {
+	skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
 		u32 offset = MPTCP_SKB_CB(skb)->offset;
 		u32 data_len = skb->len - offset;
 		u32 count = min_t(size_t, len - copied, data_len);
@@ -1990,7 +1990,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk,
 			/* we will bulk release the skb memory later */
 			skb->destructor = NULL;
 			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
-			__skb_unlink(skb, &msk->receive_queue);
+			__skb_unlink(skb, &sk->sk_receive_queue);
 			__kfree_skb(skb);
 			msk->bytes_consumed += count;
 		}
@@ -2115,54 +2115,46 @@ static void __mptcp_update_rmem(struct sock *sk)
 	WRITE_ONCE(msk->rmem_released, 0);
 }
 
-static void __mptcp_splice_receive_queue(struct sock *sk)
+static bool __mptcp_move_skbs(struct sock *sk)
 {
+	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue);
-}
-
-static bool __mptcp_move_skbs(struct mptcp_sock *msk)
-{
-	struct sock *sk = (struct sock *)msk;
 	unsigned int moved = 0;
 	bool ret, done;
 
+	/* verify we can move any data from the subflow, eventually updating */
+	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
+		mptcp_for_each_subflow(msk, subflow)
+			__mptcp_rcvbuf_update(sk, subflow->tcp_sock);
+
+	if (__mptcp_rmem(sk) > sk->sk_rcvbuf)
+		return false;
+
 	do {
 		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
 		bool slowpath;
 
-		/* we can have data pending in the subflows only if the msk
-		 * receive buffer was full at subflow_data_ready() time,
-		 * that is an unlikely slow path.
-		 */
-		if (likely(!ssk))
+		if (unlikely(!ssk))
 			break;
 
 		slowpath = lock_sock_fast(ssk);
-		mptcp_data_lock(sk);
 		__mptcp_update_rmem(sk);
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
-		mptcp_data_unlock(sk);
 
 		if (unlikely(ssk->sk_err))
 			__mptcp_error_report(sk);
 		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
-	/* acquire the data lock only if some input data is pending */
 	ret = moved > 0;
 	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
-	    !skb_queue_empty_lockless(&sk->sk_receive_queue)) {
-		mptcp_data_lock(sk);
+	    !skb_queue_empty(&sk->sk_receive_queue)) {
 		__mptcp_update_rmem(sk);
 		ret |= __mptcp_ofo_queue(msk);
-		__mptcp_splice_receive_queue(sk);
-		mptcp_data_unlock(sk);
 	}
 	if (ret)
 		mptcp_check_data_fin((struct sock *)msk);
-	return !skb_queue_empty(&msk->receive_queue);
+	return ret;
 }
 
 static unsigned int mptcp_inq_hint(const struct sock *sk)
@@ -2170,7 +2162,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk)
 	const struct mptcp_sock *msk = mptcp_sk(sk);
 	const struct sk_buff *skb;
 
-	skb = skb_peek(&msk->receive_queue);
+	skb = skb_peek(&sk->sk_receive_queue);
 	if (skb) {
 		u64 hint_val = READ_ONCE(msk->ack_seq) - MPTCP_SKB_CB(skb)->map_seq;
 
@@ -2216,7 +2208,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 	while (copied < len) {
 		int err, bytes_read;
 
-		bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags);
+		bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags);
 		if (unlikely(bytes_read < 0)) {
 			if (!copied)
 				copied = bytes_read;
@@ -2225,7 +2217,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 
 		copied += bytes_read;
 
-		if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk))
+		if (skb_queue_empty(&sk->sk_receive_queue) && __mptcp_move_skbs(sk))
 			continue;
 
 		/* only the MPTCP socket status is relevant here. The exit
@@ -2251,7 +2243,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 				/* race breaker: the shutdown could be after the
 				 * previous receive queue check
 				 */
-				if (__mptcp_move_skbs(msk))
+				if (__mptcp_move_skbs(sk))
 					continue;
 				break;
 			}
@@ -2295,9 +2287,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		}
 	}
 
-	pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
-		 msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
-		 skb_queue_empty(&msk->receive_queue), copied);
+	pr_debug("msk=%p rx queue empty=%d copied=%d\n",
+		 msk, skb_queue_empty(&sk->sk_receive_queue), copied);
 
 	release_sock(sk);
 	return copied;
@@ -2824,7 +2815,6 @@ static void __mptcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&msk->join_list);
 	INIT_LIST_HEAD(&msk->rtx_queue);
 	INIT_WORK(&msk->work, mptcp_worker);
-	__skb_queue_head_init(&msk->receive_queue);
 	msk->out_of_order_queue = RB_ROOT;
 	msk->first_pending = NULL;
 	WRITE_ONCE(msk->rmem_fwd_alloc, 0);
@@ -3407,12 +3397,8 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	mptcp_for_each_subflow_safe(msk, subflow, tmp)
 		__mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags);
 
-	/* move to sk_receive_queue, sk_stream_kill_queues will purge it */
-	mptcp_data_lock(sk);
-	skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue);
 	__skb_queue_purge(&sk->sk_receive_queue);
 	skb_rbtree_purge(&msk->out_of_order_queue);
-	mptcp_data_unlock(sk);
 
 	/* move all the rx fwd alloc into the sk_mem_reclaim_final in
 	 * inet_sock_destruct() will dispose it
@@ -3455,7 +3441,8 @@ void __mptcp_check_push(struct sock *sk, struct sock *ssk)
 
 #define MPTCP_FLAGS_PROCESS_CTX_NEED (BIT(MPTCP_PUSH_PENDING) | \
 				      BIT(MPTCP_RETRANSMIT) | \
-				      BIT(MPTCP_FLUSH_JOIN_LIST))
+				      BIT(MPTCP_FLUSH_JOIN_LIST) | \
+				      BIT(MPTCP_DEQUEUE))
 
 /* processes deferred events and flush wmem */
 static void mptcp_release_cb(struct sock *sk)
@@ -3489,6 +3476,11 @@ static void mptcp_release_cb(struct sock *sk)
 			__mptcp_push_pending(sk, 0);
 		if (flags & BIT(MPTCP_RETRANSMIT))
 			__mptcp_retrans(sk);
+		if ((flags & BIT(MPTCP_DEQUEUE)) && __mptcp_move_skbs(sk)) {
+			/* notify ack seq update */
+			mptcp_cleanup_rbuf(msk, 0);
+			sk->sk_data_ready(sk);
+		}
 
 		cond_resched();
 		spin_lock_bh(&sk->sk_lock.slock);
@@ -3726,7 +3718,8 @@ static int mptcp_ioctl(struct sock *sk, int cmd, int *karg)
 			return -EINVAL;
 
 		lock_sock(sk);
-		__mptcp_move_skbs(msk);
+		if (__mptcp_move_skbs(sk))
+			mptcp_cleanup_rbuf(msk, 0);
 		*karg = mptcp_inq_hint(sk);
 		release_sock(sk);
 		break;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 3c3e9b185ae35..753456b73f908 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -124,6 +124,7 @@
 #define MPTCP_FLUSH_JOIN_LIST	5
 #define MPTCP_SYNC_STATE	6
 #define MPTCP_SYNC_SNDBUF	7
+#define MPTCP_DEQUEUE		8
 
 struct mptcp_skb_cb {
 	u64 map_seq;
@@ -325,7 +326,6 @@ struct mptcp_sock {
 	struct work_struct work;
 	struct sk_buff  *ooo_last_skb;
 	struct rb_root  out_of_order_queue;
-	struct sk_buff_head receive_queue;
 	struct list_head conn_list;
 	struct list_head rtx_queue;
 	struct mptcp_data_frag *first_pending;

From 6639498ed85fdb135dfb0dfbcc0f540b2d4ad6a6 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:15 +0100
Subject: [PATCH 0824/2753] mptcp: cleanup mem accounting

After the previous patch, updating sk_forward_memory is cheap and
we can drop a lot of complexity from the MPTCP memory accounting,
removing the custom fwd mem allocations for rmem.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-4-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/fastopen.c |   2 +-
 net/mptcp/protocol.c | 115 +++----------------------------------------
 net/mptcp/protocol.h |   4 +-
 3 files changed, 10 insertions(+), 111 deletions(-)

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index f85ad19f3dd6c..b9e4511979028 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -50,7 +50,7 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	mptcp_data_lock(sk);
 	DEBUG_NET_WARN_ON_ONCE(sock_owned_by_user_nocheck(sk));
 
-	mptcp_set_owner_r(skb, sk);
+	skb_set_owner_r(skb, sk);
 	__skb_queue_tail(&sk->sk_receive_queue, skb);
 	mptcp_sk(sk)->bytes_received += skb->len;
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 8bdc7a7a58f31..080877f8daf7e 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -118,17 +118,6 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
-static void mptcp_rmem_fwd_alloc_add(struct sock *sk, int size)
-{
-	WRITE_ONCE(mptcp_sk(sk)->rmem_fwd_alloc,
-		   mptcp_sk(sk)->rmem_fwd_alloc + size);
-}
-
-static void mptcp_rmem_charge(struct sock *sk, int size)
-{
-	mptcp_rmem_fwd_alloc_add(sk, -size);
-}
-
 static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 			       struct sk_buff *from)
 {
@@ -151,7 +140,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 	 * negative one
 	 */
 	atomic_add(delta, &sk->sk_rmem_alloc);
-	mptcp_rmem_charge(sk, delta);
+	sk_mem_charge(sk, delta);
 	kfree_skb_partial(from, fragstolen);
 
 	return true;
@@ -166,44 +155,6 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to,
 	return mptcp_try_coalesce((struct sock *)msk, to, from);
 }
 
-static void __mptcp_rmem_reclaim(struct sock *sk, int amount)
-{
-	amount >>= PAGE_SHIFT;
-	mptcp_rmem_charge(sk, amount << PAGE_SHIFT);
-	__sk_mem_reduce_allocated(sk, amount);
-}
-
-static void mptcp_rmem_uncharge(struct sock *sk, int size)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	int reclaimable;
-
-	mptcp_rmem_fwd_alloc_add(sk, size);
-	reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk);
-
-	/* see sk_mem_uncharge() for the rationale behind the following schema */
-	if (unlikely(reclaimable >= PAGE_SIZE))
-		__mptcp_rmem_reclaim(sk, reclaimable);
-}
-
-static void mptcp_rfree(struct sk_buff *skb)
-{
-	unsigned int len = skb->truesize;
-	struct sock *sk = skb->sk;
-
-	atomic_sub(len, &sk->sk_rmem_alloc);
-	mptcp_rmem_uncharge(sk, len);
-}
-
-void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk)
-{
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = mptcp_rfree;
-	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
-	mptcp_rmem_charge(sk, skb->truesize);
-}
-
 /* "inspired" by tcp_data_queue_ofo(), main differences:
  * - use mptcp seqs
  * - don't cope with sacks
@@ -316,25 +267,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 
 end:
 	skb_condense(skb);
-	mptcp_set_owner_r(skb, sk);
-}
-
-static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-	int amt, amount;
-
-	if (size <= msk->rmem_fwd_alloc)
-		return true;
-
-	size -= msk->rmem_fwd_alloc;
-	amt = sk_mem_pages(size);
-	amount = amt << PAGE_SHIFT;
-	if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV))
-		return false;
-
-	mptcp_rmem_fwd_alloc_add(sk, amount);
-	return true;
+	skb_set_owner_r(skb, sk);
 }
 
 static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
@@ -352,7 +285,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 	skb_orphan(skb);
 
 	/* try to fetch required memory from subflow */
-	if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
+	if (!sk_rmem_schedule(sk, skb, skb->truesize)) {
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
 		goto drop;
 	}
@@ -377,7 +310,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
 		if (tail && mptcp_try_coalesce(sk, tail, skb))
 			return true;
 
-		mptcp_set_owner_r(skb, sk);
+		skb_set_owner_r(skb, sk);
 		__skb_queue_tail(&sk->sk_receive_queue, skb);
 		return true;
 	} else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) {
@@ -1987,9 +1920,10 @@ static int __mptcp_recvmsg_mskq(struct sock *sk,
 		}
 
 		if (!(flags & MSG_PEEK)) {
-			/* we will bulk release the skb memory later */
+			/* avoid the indirect call, we know the destructor is sock_wfree */
 			skb->destructor = NULL;
-			WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize);
+			atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+			sk_mem_uncharge(sk, skb->truesize);
 			__skb_unlink(skb, &sk->sk_receive_queue);
 			__kfree_skb(skb);
 			msk->bytes_consumed += count;
@@ -2103,18 +2037,6 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	msk->rcvq_space.time = mstamp;
 }
 
-static void __mptcp_update_rmem(struct sock *sk)
-{
-	struct mptcp_sock *msk = mptcp_sk(sk);
-
-	if (!msk->rmem_released)
-		return;
-
-	atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc);
-	mptcp_rmem_uncharge(sk, msk->rmem_released);
-	WRITE_ONCE(msk->rmem_released, 0);
-}
-
 static bool __mptcp_move_skbs(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
@@ -2138,7 +2060,6 @@ static bool __mptcp_move_skbs(struct sock *sk)
 			break;
 
 		slowpath = lock_sock_fast(ssk);
-		__mptcp_update_rmem(sk);
 		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
 
 		if (unlikely(ssk->sk_err))
@@ -2146,12 +2067,7 @@ static bool __mptcp_move_skbs(struct sock *sk)
 		unlock_sock_fast(ssk, slowpath);
 	} while (!done);
 
-	ret = moved > 0;
-	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) ||
-	    !skb_queue_empty(&sk->sk_receive_queue)) {
-		__mptcp_update_rmem(sk);
-		ret |= __mptcp_ofo_queue(msk);
-	}
+	ret = moved > 0 || __mptcp_ofo_queue(msk);
 	if (ret)
 		mptcp_check_data_fin((struct sock *)msk);
 	return ret;
@@ -2817,8 +2733,6 @@ static void __mptcp_init_sock(struct sock *sk)
 	INIT_WORK(&msk->work, mptcp_worker);
 	msk->out_of_order_queue = RB_ROOT;
 	msk->first_pending = NULL;
-	WRITE_ONCE(msk->rmem_fwd_alloc, 0);
-	WRITE_ONCE(msk->rmem_released, 0);
 	msk->timer_ival = TCP_RTO_MIN;
 	msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO;
 
@@ -3044,8 +2958,6 @@ static void __mptcp_destroy_sock(struct sock *sk)
 
 	sk->sk_prot->destroy(sk);
 
-	WARN_ON_ONCE(READ_ONCE(msk->rmem_fwd_alloc));
-	WARN_ON_ONCE(msk->rmem_released);
 	sk_stream_kill_queues(sk);
 	xfrm_sk_free_policy(sk);
 
@@ -3403,8 +3315,6 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	/* move all the rx fwd alloc into the sk_mem_reclaim_final in
 	 * inet_sock_destruct() will dispose it
 	 */
-	sk_forward_alloc_add(sk, msk->rmem_fwd_alloc);
-	WRITE_ONCE(msk->rmem_fwd_alloc, 0);
 	mptcp_token_destroy(msk);
 	mptcp_pm_free_anno_list(msk);
 	mptcp_free_local_addr_list(msk);
@@ -3500,8 +3410,6 @@ static void mptcp_release_cb(struct sock *sk)
 		if (__test_and_clear_bit(MPTCP_SYNC_SNDBUF, &msk->cb_flags))
 			__mptcp_sync_sndbuf(sk);
 	}
-
-	__mptcp_update_rmem(sk);
 }
 
 /* MP_JOIN client subflow must wait for 4th ack before sending any data:
@@ -3672,12 +3580,6 @@ static void mptcp_shutdown(struct sock *sk, int how)
 		__mptcp_wr_shutdown(sk);
 }
 
-static int mptcp_forward_alloc_get(const struct sock *sk)
-{
-	return READ_ONCE(sk->sk_forward_alloc) +
-	       READ_ONCE(mptcp_sk(sk)->rmem_fwd_alloc);
-}
-
 static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v)
 {
 	const struct sock *sk = (void *)msk;
@@ -3836,7 +3738,6 @@ static struct proto mptcp_prot = {
 	.hash		= mptcp_hash,
 	.unhash		= mptcp_unhash,
 	.get_port	= mptcp_get_port,
-	.forward_alloc_get	= mptcp_forward_alloc_get,
 	.stream_memory_free	= mptcp_stream_memory_free,
 	.sockets_allocated	= &mptcp_sockets_allocated,
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 753456b73f908..613d556ed938a 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -281,7 +281,6 @@ struct mptcp_sock {
 	u64		rcv_data_fin_seq;
 	u64		bytes_retrans;
 	u64		bytes_consumed;
-	int		rmem_fwd_alloc;
 	int		snd_burst;
 	int		old_wspace;
 	u64		recovery_snd_nxt;	/* in recovery mode accept up to this seq;
@@ -296,7 +295,6 @@ struct mptcp_sock {
 	u32		last_ack_recv;
 	unsigned long	timer_ival;
 	u32		token;
-	int		rmem_released;
 	unsigned long	flags;
 	unsigned long	cb_flags;
 	bool		recovery;		/* closing subflow write queue reinjected */
@@ -387,7 +385,7 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk)
  */
 static inline int __mptcp_rmem(const struct sock *sk)
 {
-	return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released);
+	return atomic_read(&sk->sk_rmem_alloc);
 }
 
 static inline int mptcp_win_from_space(const struct sock *sk, int space)

From c8802ded46589fcd054a0497159ab4704c9dc89f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:16 +0100
Subject: [PATCH 0825/2753] net: dismiss sk_forward_alloc_get()

After the previous patch we can remove the forward_alloc_get
proto callback, basically reverting commit 292e6077b040 ("net: introduce
sk_forward_alloc_get()") and commit 66d58f046c9d ("net: use
sk_forward_alloc_get() in sk_get_meminfo()").

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-5-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h   | 13 -------------
 net/core/sock.c      |  2 +-
 net/ipv4/af_inet.c   |  2 +-
 net/ipv4/inet_diag.c |  2 +-
 net/sched/em_meta.c  |  2 +-
 5 files changed, 4 insertions(+), 17 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index fac65ed30983d..edbb870e3f864 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1285,10 +1285,6 @@ struct proto {
 	unsigned int		inuse_idx;
 #endif
 
-#if IS_ENABLED(CONFIG_MPTCP)
-	int			(*forward_alloc_get)(const struct sock *sk);
-#endif
-
 	bool			(*stream_memory_free)(const struct sock *sk, int wake);
 	bool			(*sock_is_readable)(struct sock *sk);
 	/* Memory pressure */
@@ -1349,15 +1345,6 @@ int sock_load_diag_module(int family, int protocol);
 
 INDIRECT_CALLABLE_DECLARE(bool tcp_stream_memory_free(const struct sock *sk, int wake));
 
-static inline int sk_forward_alloc_get(const struct sock *sk)
-{
-#if IS_ENABLED(CONFIG_MPTCP)
-	if (sk->sk_prot->forward_alloc_get)
-		return sk->sk_prot->forward_alloc_get(sk);
-#endif
-	return READ_ONCE(sk->sk_forward_alloc);
-}
-
 static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
 	if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf))
diff --git a/net/core/sock.c b/net/core/sock.c
index 53c7af0038c4f..0d385bf27b38d 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -3882,7 +3882,7 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem)
 	mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf);
 	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
 	mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf);
-	mem[SK_MEMINFO_FWD_ALLOC] = sk_forward_alloc_get(sk);
+	mem[SK_MEMINFO_FWD_ALLOC] = READ_ONCE(sk->sk_forward_alloc);
 	mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued);
 	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
 	mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len);
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 21f46ee7b6e95..5df1f1325259d 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -153,7 +153,7 @@ void inet_sock_destruct(struct sock *sk)
 	WARN_ON_ONCE(atomic_read(&sk->sk_rmem_alloc));
 	WARN_ON_ONCE(refcount_read(&sk->sk_wmem_alloc));
 	WARN_ON_ONCE(sk->sk_wmem_queued);
-	WARN_ON_ONCE(sk_forward_alloc_get(sk));
+	WARN_ON_ONCE(sk->sk_forward_alloc);
 
 	kfree(rcu_dereference_protected(inet->inet_opt, 1));
 	dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 321acc8abf17e..efe2a085cf68e 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -282,7 +282,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		struct inet_diag_meminfo minfo = {
 			.idiag_rmem = sk_rmem_alloc_get(sk),
 			.idiag_wmem = READ_ONCE(sk->sk_wmem_queued),
-			.idiag_fmem = sk_forward_alloc_get(sk),
+			.idiag_fmem = READ_ONCE(sk->sk_forward_alloc),
 			.idiag_tmem = sk_wmem_alloc_get(sk),
 		};
 
diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c
index 8996c73c9779b..3f2e707a11d18 100644
--- a/net/sched/em_meta.c
+++ b/net/sched/em_meta.c
@@ -460,7 +460,7 @@ META_COLLECTOR(int_sk_fwd_alloc)
 		*err = -1;
 		return;
 	}
-	dst->value = sk_forward_alloc_get(sk);
+	dst->value = READ_ONCE(sk->sk_forward_alloc);
 }
 
 META_COLLECTOR(int_sk_sndbuf)

From 51fe9cb9213e18c4968385482c7ed20c0b1b21d3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:17 +0100
Subject: [PATCH 0826/2753] mptcp: dismiss __mptcp_rmem()

After the RX path refactor, it become a wrapper for sk_rmem_alloc
access, with a slightly misleading name. Just drop it.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-6-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c |  8 ++++----
 net/mptcp/protocol.h | 11 ++---------
 2 files changed, 6 insertions(+), 13 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 080877f8daf7e..c709f654cd5a4 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -496,7 +496,7 @@ static void mptcp_cleanup_rbuf(struct mptcp_sock *msk, int copied)
 	bool cleanup, rx_empty;
 
 	cleanup = (space > 0) && (space >= (old_space << 1)) && copied;
-	rx_empty = !__mptcp_rmem(sk) && copied;
+	rx_empty = !sk_rmem_alloc_get(sk) && copied;
 
 	mptcp_for_each_subflow(msk, subflow) {
 		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
@@ -645,7 +645,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		WRITE_ONCE(tp->copied_seq, seq);
 		more_data_avail = mptcp_subflow_data_available(ssk);
 
-		if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) {
+		if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) {
 			done = true;
 			break;
 		}
@@ -782,7 +782,7 @@ static void __mptcp_data_ready(struct sock *sk, struct sock *ssk)
 	__mptcp_rcvbuf_update(sk, ssk);
 
 	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (__mptcp_rmem(sk) > sk->sk_rcvbuf)
+	if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
 		return;
 
 	/* Wake-up the reader only for in-sequence data */
@@ -2049,7 +2049,7 @@ static bool __mptcp_move_skbs(struct sock *sk)
 		mptcp_for_each_subflow(msk, subflow)
 			__mptcp_rcvbuf_update(sk, subflow->tcp_sock);
 
-	if (__mptcp_rmem(sk) > sk->sk_rcvbuf)
+	if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
 		return false;
 
 	do {
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 613d556ed938a..a1a077bae7b6e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -380,14 +380,6 @@ static inline void msk_owned_by_me(const struct mptcp_sock *msk)
 #define mptcp_sk(ptr) container_of_const(ptr, struct mptcp_sock, sk.icsk_inet.sk)
 #endif
 
-/* the msk socket don't use the backlog, also account for the bulk
- * free memory
- */
-static inline int __mptcp_rmem(const struct sock *sk)
-{
-	return atomic_read(&sk->sk_rmem_alloc);
-}
-
 static inline int mptcp_win_from_space(const struct sock *sk, int space)
 {
 	return __tcp_win_from_space(mptcp_sk(sk)->scaling_ratio, space);
@@ -400,7 +392,8 @@ static inline int mptcp_space_from_win(const struct sock *sk, int win)
 
 static inline int __mptcp_space(const struct sock *sk)
 {
-	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk));
+	return mptcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) -
+				    sk_rmem_alloc_get(sk));
 }
 
 static inline struct mptcp_data_frag *mptcp_send_head(const struct sock *sk)

From e0ca4057e0ecd4b10f27892fe6f1ac2a7fd25ab4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 18 Feb 2025 19:36:18 +0100
Subject: [PATCH 0827/2753] mptcp: micro-optimize __mptcp_move_skb()

After the RX path refactor the mentioned function is expected to run
frequently, let's optimize it a bit.

Scan for ready subflow from the last processed one, and stop after
traversing the list once or reaching the msk memory limit - instead of
looking for dubious per-subflow conditions.
Also re-order the memory limit checks, to avoid duplicate tests.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250218-net-next-mptcp-rx-path-refactor-v1-7-4a47d90d7998@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.c | 111 +++++++++++++++++++------------------------
 net/mptcp/protocol.h |   2 +
 2 files changed, 52 insertions(+), 61 deletions(-)

diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index c709f654cd5a4..6b61b7dee33be 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -569,15 +569,13 @@ static void mptcp_dss_corruption(struct mptcp_sock *msk, struct sock *ssk)
 }
 
 static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
-					   struct sock *ssk,
-					   unsigned int *bytes)
+					   struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
-	unsigned int moved = 0;
 	bool more_data_avail;
 	struct tcp_sock *tp;
-	bool done = false;
+	bool ret = false;
 
 	pr_debug("msk=%p ssk=%p\n", msk, ssk);
 	tp = tcp_sk(ssk);
@@ -587,20 +585,16 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		struct sk_buff *skb;
 		bool fin;
 
+		if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
+			break;
+
 		/* try to move as much data as available */
 		map_remaining = subflow->map_data_len -
 				mptcp_subflow_get_map_offset(subflow);
 
 		skb = skb_peek(&ssk->sk_receive_queue);
-		if (!skb) {
-			/* With racing move_skbs_to_msk() and __mptcp_move_skbs(),
-			 * a different CPU can have already processed the pending
-			 * data, stop here or we can enter an infinite loop
-			 */
-			if (!moved)
-				done = true;
+		if (unlikely(!skb))
 			break;
-		}
 
 		if (__mptcp_check_fallback(msk)) {
 			/* Under fallback skbs have no MPTCP extension and TCP could
@@ -613,19 +607,13 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 
 		offset = seq - TCP_SKB_CB(skb)->seq;
 		fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
-		if (fin) {
-			done = true;
+		if (fin)
 			seq++;
-		}
 
 		if (offset < skb->len) {
 			size_t len = skb->len - offset;
 
-			if (tp->urg_data)
-				done = true;
-
-			if (__mptcp_move_skb(msk, ssk, skb, offset, len))
-				moved += len;
+			ret = __mptcp_move_skb(msk, ssk, skb, offset, len) || ret;
 			seq += len;
 
 			if (unlikely(map_remaining < len)) {
@@ -639,22 +627,16 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 			}
 
 			sk_eat_skb(ssk, skb);
-			done = true;
 		}
 
 		WRITE_ONCE(tp->copied_seq, seq);
 		more_data_avail = mptcp_subflow_data_available(ssk);
 
-		if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf) {
-			done = true;
-			break;
-		}
 	} while (more_data_avail);
 
-	if (moved > 0)
+	if (ret)
 		msk->last_data_recv = tcp_jiffies32;
-	*bytes += moved;
-	return done;
+	return ret;
 }
 
 static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
@@ -748,9 +730,9 @@ void __mptcp_error_report(struct sock *sk)
 static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct sock *sk = (struct sock *)msk;
-	unsigned int moved = 0;
+	bool moved;
 
-	__mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+	moved = __mptcp_move_skbs_from_subflow(msk, ssk);
 	__mptcp_ofo_queue(msk);
 	if (unlikely(ssk->sk_err)) {
 		if (!sock_owned_by_user(sk))
@@ -766,7 +748,7 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk)
 	 */
 	if (mptcp_pending_data_fin(sk, NULL))
 		mptcp_schedule_work(sk);
-	return moved > 0;
+	return moved;
 }
 
 static void __mptcp_rcvbuf_update(struct sock *sk, struct sock *ssk)
@@ -781,10 +763,6 @@ static void __mptcp_data_ready(struct sock *sk, struct sock *ssk)
 
 	__mptcp_rcvbuf_update(sk, ssk);
 
-	/* over limit? can't append more skbs to msk, Also, no need to wake-up*/
-	if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
-		return;
-
 	/* Wake-up the reader only for in-sequence data */
 	if (move_skbs_to_msk(msk, ssk) && mptcp_epollin_ready(sk))
 		sk->sk_data_ready(sk);
@@ -884,20 +862,6 @@ bool mptcp_schedule_work(struct sock *sk)
 	return false;
 }
 
-static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow;
-
-	msk_owned_by_me(msk);
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (READ_ONCE(subflow->data_avail))
-			return mptcp_subflow_tcp_sock(subflow);
-	}
-
-	return NULL;
-}
-
 static bool mptcp_skb_can_collapse_to(u64 write_seq,
 				      const struct sk_buff *skb,
 				      const struct mptcp_ext *mpext)
@@ -2037,37 +2001,62 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied)
 	msk->rcvq_space.time = mstamp;
 }
 
+static struct mptcp_subflow_context *
+__mptcp_first_ready_from(struct mptcp_sock *msk,
+			 struct mptcp_subflow_context *subflow)
+{
+	struct mptcp_subflow_context *start_subflow = subflow;
+
+	while (!READ_ONCE(subflow->data_avail)) {
+		subflow = mptcp_next_subflow(msk, subflow);
+		if (subflow == start_subflow)
+			return NULL;
+	}
+	return subflow;
+}
+
 static bool __mptcp_move_skbs(struct sock *sk)
 {
 	struct mptcp_subflow_context *subflow;
 	struct mptcp_sock *msk = mptcp_sk(sk);
-	unsigned int moved = 0;
-	bool ret, done;
+	bool ret = false;
+
+	if (list_empty(&msk->conn_list))
+		return false;
 
 	/* verify we can move any data from the subflow, eventually updating */
 	if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK))
 		mptcp_for_each_subflow(msk, subflow)
 			__mptcp_rcvbuf_update(sk, subflow->tcp_sock);
 
-	if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
-		return false;
-
-	do {
-		struct sock *ssk = mptcp_subflow_recv_lookup(msk);
+	subflow = list_first_entry(&msk->conn_list,
+				   struct mptcp_subflow_context, node);
+	for (;;) {
+		struct sock *ssk;
 		bool slowpath;
 
-		if (unlikely(!ssk))
+		/*
+		 * As an optimization avoid traversing the subflows list
+		 * and ev. acquiring the subflow socket lock before baling out
+		 */
+		if (sk_rmem_alloc_get(sk) > sk->sk_rcvbuf)
 			break;
 
-		slowpath = lock_sock_fast(ssk);
-		done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved);
+		subflow = __mptcp_first_ready_from(msk, subflow);
+		if (!subflow)
+			break;
 
+		ssk = mptcp_subflow_tcp_sock(subflow);
+		slowpath = lock_sock_fast(ssk);
+		ret = __mptcp_move_skbs_from_subflow(msk, ssk) || ret;
 		if (unlikely(ssk->sk_err))
 			__mptcp_error_report(sk);
 		unlock_sock_fast(ssk, slowpath);
-	} while (!done);
 
-	ret = moved > 0 || __mptcp_ofo_queue(msk);
+		subflow = mptcp_next_subflow(msk, subflow);
+	}
+
+	__mptcp_ofo_queue(msk);
 	if (ret)
 		mptcp_check_data_fin((struct sock *)msk);
 	return ret;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a1a077bae7b6e..ca65f8bff632f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -354,6 +354,8 @@ struct mptcp_sock {
 	list_for_each_entry(__subflow, &((__msk)->conn_list), node)
 #define mptcp_for_each_subflow_safe(__msk, __subflow, __tmp)			\
 	list_for_each_entry_safe(__subflow, __tmp, &((__msk)->conn_list), node)
+#define mptcp_next_subflow(__msk, __subflow)				\
+	list_next_entry_circular(__subflow, &((__msk)->conn_list), node)
 
 extern struct genl_family mptcp_genl_family;
 

From 2217bcb4914920f9b50175da583bd727caf6d927 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 18 Feb 2025 14:54:23 -0800
Subject: [PATCH 0828/2753] selftests: drv-net: resolve remote interface name

Find out and record in env the name of the interface which remote host
will use for the IP address provided via config.

Interface name is useful for mausezahn and for setting up tunnels.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250218225426.77726-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/lib/py/env.py | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 886b4904613c3..55d6b3d992b68 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -154,6 +154,9 @@ def __init__(self, src_path, nsim_test=None):
         self.ifname = self.dev['ifname']
         self.ifindex = self.dev['ifindex']
 
+        # resolve remote interface name
+        self.remote_ifname = self.resolve_remote_ifc()
+
         self._required_cmd = {}
 
     def create_local(self):
@@ -200,6 +203,18 @@ def _check_env(self):
             raise Exception("Invalid environment, missing configuration:", missing,
                             "Please see tools/testing/selftests/drivers/net/README.rst")
 
+    def resolve_remote_ifc(self):
+        v4 = v6 = None
+        if self.remote_v4:
+            v4 = ip("addr show to " + self.remote_v4, json=True, host=self.remote)
+        if self.remote_v6:
+            v6 = ip("addr show to " + self.remote_v6, json=True, host=self.remote)
+        if v4 and v6 and v4[0]["ifname"] != v6[0]["ifname"]:
+            raise Exception("Can't resolve remote interface name, v4 and v6 don't match")
+        if (v4 and len(v4) > 1) or (v6 and len(v6) > 1):
+            raise Exception("Can't resolve remote interface name, multiple interfaces match")
+        return v6[0]["ifname"] if v6 else v4[0]["ifname"]
+
     def __enter__(self):
         return self
 

From 2aefca8e1fa8a67be56e8c2f13e8c1c2e6a4c4b3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 18 Feb 2025 14:54:24 -0800
Subject: [PATCH 0829/2753] selftests: drv-net: get detailed interface info

We already record output of ip link for NETIF in env for easy access.
Record the detailed version. TSO test will want to know the max tso size.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/20250218225426.77726-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/lib/py/env.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 55d6b3d992b68..128acff4f7532 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -64,7 +64,7 @@ def __init__(self, src_path, **kwargs):
         self._ns = None
 
         if 'NETIF' in self.env:
-            self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0]
+            self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
         else:
             self._ns = NetdevSimDev(**kwargs)
             self.dev = self._ns.nsims[0].dev
@@ -118,7 +118,7 @@ def __init__(self, src_path, nsim_test=None):
                 raise KsftXfailEx("Test only works on netdevsim")
             self._check_env()
 
-            self.dev = ip("link show dev " + self.env['NETIF'], json=True)[0]
+            self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
 
             self.v4 = self.env.get("LOCAL_V4")
             self.v6 = self.env.get("LOCAL_V6")

From de94e8697405112b48c2cb8ee6ebe7c873e48f50 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 18 Feb 2025 14:54:25 -0800
Subject: [PATCH 0830/2753] selftests: drv-net: store addresses in dict indexed
 by ipver

Looks like more and more tests want to iterate over IP version,
run the same test over ipv4 and ipv6. The current naming of
members in the env class makes it a bit awkward, we have
separate members for ipv4 and ipv6 parameters.

Store the parameters inside dicts, so that tests can easily
index them with ip version.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250218225426.77726-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/hw/csum.py  | 48 +++++++------------
 .../selftests/drivers/net/hw/devmem.py        |  6 +--
 .../selftests/drivers/net/lib/py/env.py       | 47 +++++++++---------
 tools/testing/selftests/drivers/net/ping.py   | 12 ++---
 4 files changed, 50 insertions(+), 63 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hw/csum.py b/tools/testing/selftests/drivers/net/hw/csum.py
index cd477f3440caf..701aca1361e0e 100755
--- a/tools/testing/selftests/drivers/net/hw/csum.py
+++ b/tools/testing/selftests/drivers/net/hw/csum.py
@@ -9,15 +9,12 @@
 from lib.py import EthtoolFamily, NetDrvEpEnv
 from lib.py import bkg, cmd, wait_port_listen
 
-def test_receive(cfg, ipv4=False, extra_args=None):
+def test_receive(cfg, ipver="6", extra_args=None):
     """Test local nic checksum receive. Remote host sends crafted packets."""
     if not cfg.have_rx_csum:
         raise KsftSkipEx(f"Test requires rx checksum offload on {cfg.ifname}")
 
-    if ipv4:
-        ip_args = f"-4 -S {cfg.remote_v4} -D {cfg.v4}"
-    else:
-        ip_args = f"-6 -S {cfg.remote_v6} -D {cfg.v6}"
+    ip_args = f"-{ipver} -S {cfg.remote_addr_v[ipver]} -D {cfg.addr_v[ipver]}"
 
     rx_cmd = f"{cfg.bin_local} -i {cfg.ifname} -n 100 {ip_args} -r 1 -R {extra_args}"
     tx_cmd = f"{cfg.bin_remote} -i {cfg.ifname} -n 100 {ip_args} -r 1 -T {extra_args}"
@@ -27,17 +24,14 @@ def test_receive(cfg, ipv4=False, extra_args=None):
         cmd(tx_cmd, host=cfg.remote)
 
 
-def test_transmit(cfg, ipv4=False, extra_args=None):
+def test_transmit(cfg, ipver="6", extra_args=None):
     """Test local nic checksum transmit. Remote host verifies packets."""
     if (not cfg.have_tx_csum_generic and
-        not (cfg.have_tx_csum_ipv4 and ipv4) and
-        not (cfg.have_tx_csum_ipv6 and not ipv4)):
+        not (cfg.have_tx_csum_ipv4 and ipver == "4") and
+        not (cfg.have_tx_csum_ipv6 and ipver == "6")):
         raise KsftSkipEx(f"Test requires tx checksum offload on {cfg.ifname}")
 
-    if ipv4:
-        ip_args = f"-4 -S {cfg.v4} -D {cfg.remote_v4}"
-    else:
-        ip_args = f"-6 -S {cfg.v6} -D {cfg.remote_v6}"
+    ip_args = f"-{ipver} -S {cfg.addr_v[ipver]} -D {cfg.remote_addr_v[ipver]}"
 
     # Cannot randomize input when calculating zero checksum
     if extra_args != "-U -Z":
@@ -51,26 +45,20 @@ def test_transmit(cfg, ipv4=False, extra_args=None):
         cmd(tx_cmd)
 
 
-def test_builder(name, cfg, ipv4=False, tx=False, extra_args=""):
+def test_builder(name, cfg, ipver="6", tx=False, extra_args=""):
     """Construct specific tests from the common template.
 
        Most tests follow the same basic pattern, differing only in
        Direction of the test and optional flags passed to csum."""
     def f(cfg):
-        if ipv4:
-            cfg.require_v4()
-        else:
-            cfg.require_v6()
+        cfg.require_ipver(ipver)
 
         if tx:
-            test_transmit(cfg, ipv4, extra_args)
+            test_transmit(cfg, ipver, extra_args)
         else:
-            test_receive(cfg, ipv4, extra_args)
+            test_receive(cfg, ipver, extra_args)
 
-    if ipv4:
-        f.__name__ = "ipv4_" + name
-    else:
-        f.__name__ = "ipv6_" + name
+    f.__name__ = f"ipv{ipver}_" + name
     return f
 
 
@@ -104,15 +92,15 @@ def main() -> None:
         cfg.bin_remote = cfg.remote.deploy(cfg.bin_local)
 
         cases = []
-        for ipv4 in [True, False]:
-            cases.append(test_builder("rx_tcp", cfg, ipv4, False, "-t"))
-            cases.append(test_builder("rx_tcp_invalid", cfg, ipv4, False, "-t -E"))
+        for ipver in ["4", "6"]:
+            cases.append(test_builder("rx_tcp", cfg, ipver, False, "-t"))
+            cases.append(test_builder("rx_tcp_invalid", cfg, ipver, False, "-t -E"))
 
-            cases.append(test_builder("rx_udp", cfg, ipv4, False, ""))
-            cases.append(test_builder("rx_udp_invalid", cfg, ipv4, False, "-E"))
+            cases.append(test_builder("rx_udp", cfg, ipver, False, ""))
+            cases.append(test_builder("rx_udp_invalid", cfg, ipver, False, "-E"))
 
-            cases.append(test_builder("tx_udp_csum_offload", cfg, ipv4, True, "-U"))
-            cases.append(test_builder("tx_udp_zero_checksum", cfg, ipv4, True, "-U -Z"))
+            cases.append(test_builder("tx_udp_csum_offload", cfg, ipver, True, "-U"))
+            cases.append(test_builder("tx_udp_zero_checksum", cfg, ipver, True, "-U -Z"))
 
         ksft_run(cases=cases, args=(cfg, ))
     ksft_exit()
diff --git a/tools/testing/selftests/drivers/net/hw/devmem.py b/tools/testing/selftests/drivers/net/hw/devmem.py
index 1223f0f5c10c3..3947e91571159 100755
--- a/tools/testing/selftests/drivers/net/hw/devmem.py
+++ b/tools/testing/selftests/drivers/net/hw/devmem.py
@@ -21,15 +21,15 @@ def require_devmem(cfg):
 
 @ksft_disruptive
 def check_rx(cfg) -> None:
-    cfg.require_v6()
+    cfg.require_ipver("6")
     require_devmem(cfg)
 
     port = rand_port()
-    listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.v6} -p {port}"
+    listen_cmd = f"./ncdevmem -l -f {cfg.ifname} -s {cfg.addr_v['6']} -p {port}"
 
     with bkg(listen_cmd) as socat:
         wait_port_listen(port)
-        cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.v6}]:{port}", host=cfg.remote, shell=True)
+        cmd(f"echo -e \"hello\\nworld\"| socat -u - TCP6:[{cfg.addr_v['6']}]:{port}", host=cfg.remote, shell=True)
 
     ksft_eq(socat.stdout.strip(), "hello\nworld")
 
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 128acff4f7532..96b33b5ef9dd4 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -113,6 +113,9 @@ def __init__(self, src_path, nsim_test=None):
         self._ns = None
         self._ns_peer = None
 
+        self.addr_v        = { "4": None, "6": None }
+        self.remote_addr_v = { "4": None, "6": None }
+
         if "NETIF" in self.env:
             if nsim_test is True:
                 raise KsftXfailEx("Test only works on netdevsim")
@@ -120,10 +123,10 @@ def __init__(self, src_path, nsim_test=None):
 
             self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
 
-            self.v4 = self.env.get("LOCAL_V4")
-            self.v6 = self.env.get("LOCAL_V6")
-            self.remote_v4 = self.env.get("REMOTE_V4")
-            self.remote_v6 = self.env.get("REMOTE_V6")
+            self.addr_v["4"] = self.env.get("LOCAL_V4")
+            self.addr_v["6"] = self.env.get("LOCAL_V6")
+            self.remote_addr_v["4"] = self.env.get("REMOTE_V4")
+            self.remote_addr_v["6"] = self.env.get("REMOTE_V6")
             kind = self.env["REMOTE_TYPE"]
             args = self.env["REMOTE_ARGS"]
         else:
@@ -134,22 +137,22 @@ def __init__(self, src_path, nsim_test=None):
 
             self.dev = self._ns.nsims[0].dev
 
-            self.v4 = self.nsim_v4_pfx + "1"
-            self.v6 = self.nsim_v6_pfx + "1"
-            self.remote_v4 = self.nsim_v4_pfx + "2"
-            self.remote_v6 = self.nsim_v6_pfx + "2"
+            self.addr_v["4"] = self.nsim_v4_pfx + "1"
+            self.addr_v["6"] = self.nsim_v6_pfx + "1"
+            self.remote_addr_v["4"] = self.nsim_v4_pfx + "2"
+            self.remote_addr_v["6"] = self.nsim_v6_pfx + "2"
             kind = "netns"
             args = self._netns.name
 
         self.remote = Remote(kind, args, src_path)
 
-        self.addr = self.v6 if self.v6 else self.v4
-        self.remote_addr = self.remote_v6 if self.remote_v6 else self.remote_v4
+        self.addr_ipver = "6" if self.addr_v["6"] else "4"
+        self.addr = self.addr_v[self.addr_ipver]
+        self.remote_addr = self.remote_addr_v[self.addr_ipver]
 
-        self.addr_ipver = "6" if self.v6 else "4"
         # Bracketed addresses, some commands need IPv6 to be inside []
-        self.baddr = f"[{self.v6}]" if self.v6 else self.v4
-        self.remote_baddr = f"[{self.remote_v6}]" if self.remote_v6 else self.remote_v4
+        self.baddr = f"[{self.addr_v['6']}]" if self.addr_v["6"] else self.addr_v["4"]
+        self.remote_baddr = f"[{self.remote_addr_v['6']}]" if self.remote_addr_v["6"] else self.remote_addr_v["4"]
 
         self.ifname = self.dev['ifname']
         self.ifindex = self.dev['ifindex']
@@ -205,10 +208,10 @@ def _check_env(self):
 
     def resolve_remote_ifc(self):
         v4 = v6 = None
-        if self.remote_v4:
-            v4 = ip("addr show to " + self.remote_v4, json=True, host=self.remote)
-        if self.remote_v6:
-            v6 = ip("addr show to " + self.remote_v6, json=True, host=self.remote)
+        if self.remote_addr_v["4"]:
+            v4 = ip("addr show to " + self.remote_addr_v["4"], json=True, host=self.remote)
+        if self.remote_addr_v["6"]:
+            v6 = ip("addr show to " + self.remote_addr_v["6"], json=True, host=self.remote)
         if v4 and v6 and v4[0]["ifname"] != v6[0]["ifname"]:
             raise Exception("Can't resolve remote interface name, v4 and v6 don't match")
         if (v4 and len(v4) > 1) or (v6 and len(v6) > 1):
@@ -238,13 +241,9 @@ def __del__(self):
             del self.remote
             self.remote = None
 
-    def require_v4(self):
-        if not self.v4 or not self.remote_v4:
-            raise KsftSkipEx("Test requires IPv4 connectivity")
-
-    def require_v6(self):
-        if not self.v6 or not self.remote_v6:
-            raise KsftSkipEx("Test requires IPv6 connectivity")
+    def require_ipver(self, ipver):
+        if not self.addr_v[ipver] or not self.remote_addr_v[ipver]:
+            raise KsftSkipEx(f"Test requires IPv{ipver} connectivity")
 
     def _require_cmd(self, comm, key, host=None):
         cached = self._required_cmd.get(comm, {})
diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index eb83e7b487978..17dc11e9b6dd6 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -8,17 +8,17 @@
 
 
 def test_v4(cfg) -> None:
-    cfg.require_v4()
+    cfg.require_ipver("4")
 
-    cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}")
-    cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote)
+    cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
+    cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
 
 
 def test_v6(cfg) -> None:
-    cfg.require_v6()
+    cfg.require_ipver("6")
 
-    cmd(f"ping -c 1 -W0.5 {cfg.remote_v6}")
-    cmd(f"ping -c 1 -W0.5 {cfg.v6}", host=cfg.remote)
+    cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["6"])
+    cmd("ping -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote)
 
 
 def test_tcp(cfg) -> None:

From 0d0f4174f6c87be7d0b992c008cc6f464edea2fa Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 18 Feb 2025 14:54:26 -0800
Subject: [PATCH 0831/2753] selftests: drv-net: add a simple TSO test

Add a simple test for TSO. Send a few MB of data and check device
stats to verify that the device was performing segmentation.
Do the same thing over a few tunnel types.

Injecting GSO packets directly would give us more ability to test
corner cases, but perhaps starting simple is good enough?

  # ./ksft-net-drv/drivers/net/hw/tso.py
  # Detected qstat for LSO wire-packets
  KTAP version 1
  1..14
  ok 1 tso.ipv4 # SKIP Test requires IPv4 connectivity
  ok 2 tso.vxlan4_ipv4 # SKIP Test requires IPv4 connectivity
  ok 3 tso.vxlan6_ipv4 # SKIP Test requires IPv4 connectivity
  ok 4 tso.vxlan_csum4_ipv4 # SKIP Test requires IPv4 connectivity
  ok 5 tso.vxlan_csum6_ipv4 # SKIP Test requires IPv4 connectivity
  ok 6 tso.gre4_ipv4 # SKIP Test requires IPv4 connectivity
  ok 7 tso.gre6_ipv4 # SKIP Test requires IPv4 connectivity
  ok 8 tso.ipv6
  ok 9 tso.vxlan4_ipv6
  ok 10 tso.vxlan6_ipv6
  ok 11 tso.vxlan_csum4_ipv6
  ok 12 tso.vxlan_csum6_ipv6
  # Testing with mangleid enabled
  ok 13 tso.gre4_ipv6
  ok 14 tso.gre6_ipv6
  # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:7 error:0

Note that the test currently depends on the driver reporting
the LSO count via qstat, which appears to be relatively rare
(virtio, cisco/enic, sfc/efc; but virtio needs host support).

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250218225426.77726-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/hw/Makefile |   1 +
 tools/testing/selftests/drivers/net/hw/tso.py | 241 ++++++++++++++++++
 2 files changed, 242 insertions(+)
 create mode 100755 tools/testing/selftests/drivers/net/hw/tso.py

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index 21ba64ce1e34b..ae783e18be83b 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,6 +15,7 @@ TEST_PROGS = \
 	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
+	tso.py \
 	#
 
 TEST_FILES := \
diff --git a/tools/testing/selftests/drivers/net/hw/tso.py b/tools/testing/selftests/drivers/net/hw/tso.py
new file mode 100755
index 0000000000000..e1ecb92f79d9b
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/tso.py
@@ -0,0 +1,241 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+"""Run the tools/testing/selftests/net/csum testsuite."""
+
+import fcntl
+import socket
+import struct
+import termios
+import time
+
+from lib.py import ksft_pr, ksft_run, ksft_exit, KsftSkipEx, KsftXfailEx
+from lib.py import ksft_eq, ksft_ge, ksft_lt
+from lib.py import EthtoolFamily, NetdevFamily, NetDrvEpEnv
+from lib.py import bkg, cmd, defer, ethtool, ip, rand_port, wait_port_listen
+
+
+def sock_wait_drain(sock, max_wait=1000):
+    """Wait for all pending write data on the socket to get ACKed."""
+    for _ in range(max_wait):
+        one = b'\0' * 4
+        outq = fcntl.ioctl(sock.fileno(), termios.TIOCOUTQ, one)
+        outq = struct.unpack("I", outq)[0]
+        if outq == 0:
+            break
+        time.sleep(0.01)
+    ksft_eq(outq, 0)
+
+
+def tcp_sock_get_retrans(sock):
+    """Get the number of retransmissions for the TCP socket."""
+    info = sock.getsockopt(socket.SOL_TCP, socket.TCP_INFO, 512)
+    return struct.unpack("I", info[100:104])[0]
+
+
+def run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso):
+    cfg.require_cmd("socat", remote=True)
+
+    port = rand_port()
+    listen_cmd = f"socat -{ipver} -t 2 -u TCP-LISTEN:{port},reuseport /dev/null,ignoreeof"
+
+    with bkg(listen_cmd, host=cfg.remote) as nc:
+        wait_port_listen(port, host=cfg.remote)
+
+        if ipver == "4":
+            sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+            sock.connect((remote_v4, port))
+        else:
+            sock = socket.socket(socket.AF_INET6, socket.SOCK_STREAM)
+            sock.connect((remote_v6, port))
+
+        # Small send to make sure the connection is working.
+        sock.send("ping".encode())
+        sock_wait_drain(sock)
+
+        # Send 4MB of data, record the LSO packet count.
+        qstat_old = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+        buf = b"0" * 1024 * 1024 * 4
+        sock.send(buf)
+        sock_wait_drain(sock)
+        qstat_new = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)[0]
+
+        # No math behind the 10 here, but try to catch cases where
+        # TCP falls back to non-LSO.
+        ksft_lt(tcp_sock_get_retrans(sock), 10)
+        sock.close()
+
+        # Check that at least 90% of the data was sent as LSO packets.
+        # System noise may cause false negatives. Also header overheads
+        # will add up to 5% of extra packes... The check is best effort.
+        total_lso_wire  = len(buf) * 0.90 // cfg.dev["mtu"]
+        total_lso_super = len(buf) * 0.90 // cfg.dev["tso_max_size"]
+        if should_lso:
+            if cfg.have_stat_super_count:
+                ksft_ge(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        total_lso_super,
+                        comment="Number of LSO super-packets with LSO enabled")
+            if cfg.have_stat_wire_count:
+                ksft_ge(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        total_lso_wire,
+                        comment="Number of LSO wire-packets with LSO enabled")
+        else:
+            if cfg.have_stat_super_count:
+                ksft_lt(qstat_new['tx-hw-gso-packets'] -
+                        qstat_old['tx-hw-gso-packets'],
+                        15, comment="Number of LSO super-packets with LSO disabled")
+            if cfg.have_stat_wire_count:
+                ksft_lt(qstat_new['tx-hw-gso-wire-packets'] -
+                        qstat_old['tx-hw-gso-wire-packets'],
+                        500, comment="Number of LSO wire-packets with LSO disabled")
+
+
+def build_tunnel(cfg, outer_ipver, tun_info):
+    local_v4  = NetDrvEpEnv.nsim_v4_pfx + "1"
+    local_v6  = NetDrvEpEnv.nsim_v6_pfx + "1"
+    remote_v4 = NetDrvEpEnv.nsim_v4_pfx + "2"
+    remote_v6 = NetDrvEpEnv.nsim_v6_pfx + "2"
+
+    local_addr  = cfg.addr_v[outer_ipver]
+    remote_addr = cfg.remote_addr_v[outer_ipver]
+
+    tun_type = tun_info[0]
+    tun_arg  = tun_info[2]
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {local_addr} remote {remote_addr} dev {cfg.ifname}")
+    defer(ip, f"link del {tun_type}-ksft")
+    ip(f"link set dev {tun_type}-ksft up")
+    ip(f"addr add {local_v4}/24 dev {tun_type}-ksft")
+    ip(f"addr add {local_v6}/64 dev {tun_type}-ksft")
+
+    ip(f"link add {tun_type}-ksft type {tun_type} {tun_arg} local {remote_addr} remote {local_addr} dev {cfg.remote_ifname}",
+        host=cfg.remote)
+    defer(ip, f"link del {tun_type}-ksft", host=cfg.remote)
+    ip(f"link set dev {tun_type}-ksft up", host=cfg.remote)
+    ip(f"addr add {remote_v4}/24 dev {tun_type}-ksft", host=cfg.remote)
+    ip(f"addr add {remote_v6}/64 dev {tun_type}-ksft", host=cfg.remote)
+
+    return remote_v4, remote_v6
+
+
+def test_builder(name, cfg, outer_ipver, feature, tun=None, inner_ipver=None):
+    """Construct specific tests from the common template."""
+    def f(cfg):
+        cfg.require_ipver(outer_ipver)
+
+        if not cfg.have_stat_super_count and \
+           not cfg.have_stat_wire_count:
+            raise KsftSkipEx(f"Device does not support LSO queue stats")
+
+        ipver = outer_ipver
+        if tun:
+            remote_v4, remote_v6 = build_tunnel(cfg, ipver, tun)
+            ipver = inner_ipver
+        else:
+            remote_v4 = cfg.remote_addr_v["4"]
+            remote_v6 = cfg.remote_addr_v["6"]
+
+        tun_partial = tun and tun[1]
+        # Tunnel which can silently fall back to gso-partial
+        has_gso_partial = tun and 'tx-gso-partial' in cfg.features
+
+        # For TSO4 via partial we need mangleid
+        if ipver == "4" and feature in cfg.partial_features:
+            ksft_pr("Testing with mangleid enabled")
+            if 'tx-tcp-mangleid-segmentation' not in cfg.features:
+                ethtool(f"-K {cfg.ifname} tx-tcp-mangleid-segmentation on")
+                defer(ethtool, f"-K {cfg.ifname} tx-tcp-mangleid-segmentation off")
+
+        # First test without the feature enabled.
+        ethtool(f"-K {cfg.ifname} {feature} off")
+        if has_gso_partial:
+            ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+        run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=False)
+
+        # Now test with the feature enabled.
+        # For compatible tunnels only - just GSO partial, not specific feature.
+        if has_gso_partial:
+            ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+            run_one_stream(cfg, ipver, remote_v4, remote_v6,
+                           should_lso=tun_partial)
+
+        # Full feature enabled.
+        if feature in cfg.features:
+            ethtool(f"-K {cfg.ifname} {feature} on")
+            run_one_stream(cfg, ipver, remote_v4, remote_v6, should_lso=True)
+        else:
+            raise KsftXfailEx(f"Device does not support {feature}")
+
+    f.__name__ = name + ((outer_ipver + "_") if tun else "") + "ipv" + inner_ipver
+    return f
+
+
+def query_nic_features(cfg) -> None:
+    """Query and cache the NIC features."""
+    cfg.have_stat_super_count = False
+    cfg.have_stat_wire_count = False
+
+    cfg.features = set()
+    features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+    for f in features["active"]["bits"]["bit"]:
+        cfg.features.add(f["name"])
+
+    # Check which features are supported via GSO partial
+    cfg.partial_features = set()
+    if 'tx-gso-partial' in cfg.features:
+        ethtool(f"-K {cfg.ifname} tx-gso-partial off")
+
+        no_partial = set()
+        features = cfg.ethnl.features_get({"header": {"dev-index": cfg.ifindex}})
+        for f in features["active"]["bits"]["bit"]:
+            no_partial.add(f["name"])
+        cfg.partial_features = cfg.features - no_partial
+        ethtool(f"-K {cfg.ifname} tx-gso-partial on")
+
+    stats = cfg.netnl.qstats_get({"ifindex": cfg.ifindex}, dump=True)
+    if stats:
+        if 'tx-hw-gso-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO super-packets")
+            cfg.have_stat_super_count = True
+        if 'tx-hw-gso-wire-packets' in stats[0]:
+            ksft_pr("Detected qstat for LSO wire-packets")
+            cfg.have_stat_wire_count = True
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        query_nic_features(cfg)
+
+        test_info = (
+            # name,       v4/v6  ethtool_feature              tun:(type,    partial, args)
+            ("",            "4", "tx-tcp-segmentation",           None),
+            ("",            "6", "tx-tcp6-segmentation",          None),
+            ("vxlan",        "", "tx-udp_tnl-segmentation",       ("vxlan",  True,  "id 100 dstport 4789 noudpcsum")),
+            ("vxlan_csum",   "", "tx-udp_tnl-csum-segmentation",  ("vxlan",  False, "id 100 dstport 4789 udpcsum")),
+            ("gre",         "4", "tx-gre-segmentation",           ("ipgre",  False,  "")),
+            ("gre",         "6", "tx-gre-segmentation",           ("ip6gre", False,  "")),
+        )
+
+        cases = []
+        for outer_ipver in ["4", "6"]:
+            for info in test_info:
+                # Skip if test which only works for a specific IP version
+                if info[1] and outer_ipver != info[1]:
+                    continue
+
+                cases.append(test_builder(info[0], cfg, outer_ipver, info[2],
+                                          tun=info[3], inner_ipver="4"))
+                if info[3]:
+                    cases.append(test_builder(info[0], cfg, outer_ipver, info[2],
+                                              tun=info[3], inner_ipver="6"))
+
+        ksft_run(cases=cases, args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()

From 3d8c6f26893d55fab218ad086719de1fc9bb86ba Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Mon, 10 Feb 2025 13:31:11 +0200
Subject: [PATCH 0832/2753] RDMA/mlx5: Fix implicit ODP hang on parent
 deregistration

Fix the destroy_unused_implicit_child_mr() to prevent hanging during
parent deregistration as of below [1].

Upon entering destroy_unused_implicit_child_mr(), the reference count
for the implicit MR parent is incremented using:
refcount_inc_not_zero().

A corresponding decrement must be performed if
free_implicit_child_mr_work() is not called.

The code has been updated to properly manage the reference count that
was incremented.

[1]
INFO: task python3:2157 blocked for more than 120 seconds.
Not tainted 6.12.0-rc7+ #1633
"echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
task:python3         state:D stack:0     pid:2157 tgid:2157  ppid:1685   flags:0x00000000
Call Trace:
<TASK>
__schedule+0x420/0xd30
schedule+0x47/0x130
__mlx5_ib_dereg_mr+0x379/0x5d0 [mlx5_ib]
? __pfx_autoremove_wake_function+0x10/0x10
ib_dereg_mr_user+0x5f/0x120 [ib_core]
? lock_release+0xc6/0x280
destroy_hw_idr_uobject+0x1d/0x60 [ib_uverbs]
uverbs_destroy_uobject+0x58/0x1d0 [ib_uverbs]
uobj_destroy+0x3f/0x70 [ib_uverbs]
ib_uverbs_cmd_verbs+0x3e4/0xbb0 [ib_uverbs]
? __pfx_uverbs_destroy_def_handler+0x10/0x10 [ib_uverbs]
? lock_acquire+0xc1/0x2f0
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0x116/0x170 [ib_uverbs]
? lock_release+0xc6/0x280
ib_uverbs_ioctl+0xe7/0x170 [ib_uverbs]
? ib_uverbs_ioctl+0xcb/0x170 [ib_uverbs]
 __x64_sys_ioctl+0x1b0/0xa70
? kmem_cache_free+0x221/0x400
do_syscall_64+0x6b/0x140
entry_SYSCALL_64_after_hwframe+0x76/0x7e
RIP: 0033:0x7f20f21f017b
RSP: 002b:00007ffcfc4a77c8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007ffcfc4a78d8 RCX: 00007f20f21f017b
RDX: 00007ffcfc4a78c0 RSI: 00000000c0181b01 RDI: 0000000000000003
RBP: 00007ffcfc4a78a0 R08: 000056147d125190 R09: 00007f20f1f14c60
R10: 0000000000000001 R11: 0000000000000246 R12: 00007ffcfc4a7890
R13: 000000000000001c R14: 000056147d100fc0 R15: 00007f20e365c9d0
</TASK>

Fixes: d3d930411ce3 ("RDMA/mlx5: Fix implicit ODP use after free")
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Artemy Kovalyov <artemyko@nvidia.com>
Link: https://patch.msgid.link/80f2fcd19952dfa7d9981d93fd6359b4471f8278.1739186929.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/odp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
index f1e23583e6c08..e77c9280c07e4 100644
--- a/drivers/infiniband/hw/mlx5/odp.c
+++ b/drivers/infiniband/hw/mlx5/odp.c
@@ -242,6 +242,7 @@ static void destroy_unused_implicit_child_mr(struct mlx5_ib_mr *mr)
 	if (__xa_cmpxchg(&imr->implicit_children, idx, mr, NULL, GFP_KERNEL) !=
 	    mr) {
 		xa_unlock(&imr->implicit_children);
+		mlx5r_deref_odp_mkey(&imr->mmkey);
 		return;
 	}
 

From c534ffda781f44a1c6ac25ef6e0e444da38ca8af Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Mon, 10 Feb 2025 13:32:39 +0200
Subject: [PATCH 0833/2753] RDMA/mlx5: Fix AH static rate parsing

Previously static rate wasn't translated according to our PRM but simply
used the 4 lower bytes.

Correctly translate static rate value passed in AH creation attribute
according to our PRM expected values.

In addition change 800GB mapping to zero, which is the PRM
specified value.

Fixes: e126ba97dba9 ("mlx5: Add driver for Mellanox Connect-IB adapters")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Link: https://patch.msgid.link/18ef4cc5396caf80728341eb74738cd777596f60.1739187089.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/ah.c | 3 ++-
 drivers/infiniband/hw/mlx5/qp.c | 6 +++---
 drivers/infiniband/hw/mlx5/qp.h | 1 +
 3 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 505bc47fd575d..99036afb3aef0 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -67,7 +67,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.tclass = grh->traffic_class;
 	}
 
-	ah->av.stat_rate_sl = (rdma_ah_get_static_rate(ah_attr) << 4);
+	ah->av.stat_rate_sl =
+		(mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr)) << 4);
 
 	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		if (init_attr->xmit_slave)
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 08d22db8dca91..88724d15705d4 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -3447,11 +3447,11 @@ static int ib_to_mlx5_rate_map(u8 rate)
 	return 0;
 }
 
-static int ib_rate_to_mlx5(struct mlx5_ib_dev *dev, u8 rate)
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate)
 {
 	u32 stat_rate_support;
 
-	if (rate == IB_RATE_PORT_CURRENT)
+	if (rate == IB_RATE_PORT_CURRENT || rate == IB_RATE_800_GBPS)
 		return 0;
 
 	if (rate < IB_RATE_2_5_GBPS || rate > IB_RATE_800_GBPS)
@@ -3596,7 +3596,7 @@ static int mlx5_set_path(struct mlx5_ib_dev *dev, struct mlx5_ib_qp *qp,
 		       sizeof(grh->dgid.raw));
 	}
 
-	err = ib_rate_to_mlx5(dev, rdma_ah_get_static_rate(ah));
+	err = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah));
 	if (err < 0)
 		return err;
 	MLX5_SET(ads, path, stat_rate, err);
diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h
index b6ee7c3ee1ca1..2530e7730635f 100644
--- a/drivers/infiniband/hw/mlx5/qp.h
+++ b/drivers/infiniband/hw/mlx5/qp.h
@@ -56,4 +56,5 @@ int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn);
 int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter);
 int mlx5_ib_qp_event_init(void);
 void mlx5_ib_qp_event_cleanup(void);
+int mlx5r_ib_rate(struct mlx5_ib_dev *dev, u8 rate);
 #endif /* _MLX5_IB_QP_H */

From 4738d3d3e12d70a5067baba147daf57e57b77548 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:13 +0200
Subject: [PATCH 0834/2753] intel_th: msu: Fix kernel-doc warnings

Correct function comments to prevent kernel-doc warnings
found when using "W=1".

msu.c:162: warning: Function parameter or struct member 'mbuf_priv' not described in 'msc'
msu.c:164: warning: Function parameter or struct member 'orig_addr' not described in 'msc'
msu.c:164: warning: Function parameter or struct member 'orig_sz' not described in 'msc'

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Link: https://lore.kernel.org/r/20250211185017.1759193-2-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/msu.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 66123d684ac9e..492d8eba37ebc 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -108,7 +108,7 @@ struct msc_iter {
  * @reg_base:		register window base address
  * @thdev:		intel_th_device pointer
  * @mbuf:		MSU buffer, if assigned
- * @mbuf_priv		MSU buffer's private data, if @mbuf
+ * @mbuf_priv:		MSU buffer's private data, if @mbuf
  * @win_list:		list of windows in multiblock mode
  * @single_sgt:		single mode buffer
  * @cur_win:		current window
@@ -117,6 +117,8 @@ struct msc_iter {
  * @single_wrap:	single mode wrap occurred
  * @base:		buffer's base pointer
  * @base_addr:		buffer's base address
+ * @orig_addr:		MSC0 buffer's base address
+ * @orig_sz:		MSC0 buffer's size
  * @user_count:		number of users of the buffer
  * @mmap_count:		number of mappings
  * @buf_mutex:		mutex to serialize access to buffer-related bits

From 04190ec6d02aa8fee0f03189bb7762b44739c253 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:14 +0200
Subject: [PATCH 0835/2753] intel_th: msu: Fix less trivial kernel-doc warnings

Correct function comments to prevent kernel-doc warnings found when using
"W=1" that the drive-by fixers had trouble documenting and skipped over.

msu.c:168: warning: Function parameter or struct member 'msu_base' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'work' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'switch_on_unlock' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'iter_list' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'stop_on_full' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'do_irq' not described in 'msc'
msu.c:168: warning: Function parameter or struct member 'multi_is_broken' not described in 'msc'

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250211185017.1759193-3-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/msu.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 492d8eba37ebc..bf99d79a41920 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -105,13 +105,16 @@ struct msc_iter {
 
 /**
  * struct msc - MSC device representation
- * @reg_base:		register window base address
+ * @reg_base:		register window base address for the entire MSU
+ * @msu_base:		register window base address for this MSC
  * @thdev:		intel_th_device pointer
  * @mbuf:		MSU buffer, if assigned
  * @mbuf_priv:		MSU buffer's private data, if @mbuf
+ * @work:		a work to stop the trace when the buffer is full
  * @win_list:		list of windows in multiblock mode
  * @single_sgt:		single mode buffer
  * @cur_win:		current window
+ * @switch_on_unlock:	window to switch to when it becomes available
  * @nr_pages:		total number of pages allocated for this buffer
  * @single_sz:		amount of data in single mode
  * @single_wrap:	single mode wrap occurred
@@ -122,8 +125,12 @@ struct msc_iter {
  * @user_count:		number of users of the buffer
  * @mmap_count:		number of mappings
  * @buf_mutex:		mutex to serialize access to buffer-related bits
+ * @iter_list:		list of open file descriptor iterators
+ * @stop_on_full:	stop the trace if the current window is full
  * @enabled:		MSC is enabled
  * @wrap:		wrapping is enabled
+ * @do_irq:		IRQ resource is available, handle interrupts
+ * @multi_is_broken:	multiblock mode enabled (not disabled by PCI drvdata)
  * @mode:		MSC operating mode
  * @burst_len:		write burst length
  * @index:		number of this MSC in the MSU

From b5edccae9f447a92d475267d94c33f4926963eec Mon Sep 17 00:00:00 2001
From: Pawel Chmielewski <pawel.chmielewski@intel.com>
Date: Tue, 11 Feb 2025 20:50:15 +0200
Subject: [PATCH 0836/2753] intel_th: pci: Add Arrow Lake support

Add support for the Trace Hub in Arrow Lake.

Signed-off-by: Pawel Chmielewski <pawel.chmielewski@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-4-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index e9d8d28e055f3..3e03ee788bb94 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -334,6 +334,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa824),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Arrow Lake */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From a70034d6c0d5f3cdee40bb00a578e17fd2ebe426 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:16 +0200
Subject: [PATCH 0837/2753] intel_th: pci: Add Panther Lake-H support

Add support for the Trace Hub in Panther Lake-H.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-5-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 3e03ee788bb94..004e68286fd43 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -339,6 +339,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7724),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Panther Lake-H */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From 49114ff05770264ae233f50023fc64a719a9dcf9 Mon Sep 17 00:00:00 2001
From: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Date: Tue, 11 Feb 2025 20:50:17 +0200
Subject: [PATCH 0838/2753] intel_th: pci: Add Panther Lake-P/U support

Add support for the Trace Hub in Panther Lake-P/U.

Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: stable@kernel.org
Link: https://lore.kernel.org/r/20250211185017.1759193-6-alexander.shishkin@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/hwtracing/intel_th/pci.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/hwtracing/intel_th/pci.c b/drivers/hwtracing/intel_th/pci.c
index 004e68286fd43..e3def163d5cf7 100644
--- a/drivers/hwtracing/intel_th/pci.c
+++ b/drivers/hwtracing/intel_th/pci.c
@@ -344,6 +344,11 @@ static const struct pci_device_id intel_th_pci_id_table[] = {
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe324),
 		.driver_data = (kernel_ulong_t)&intel_th_2x,
 	},
+	{
+		/* Panther Lake-P/U */
+		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe424),
+		.driver_data = (kernel_ulong_t)&intel_th_2x,
+	},
 	{
 		/* Alder Lake CPU */
 		PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x466f),

From 304b0a60d38dc24bfbfc9adc7d254d1cf8f98317 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@cherry.de>
Date: Wed, 19 Feb 2025 10:33:02 +0100
Subject: [PATCH 0839/2753] arm64: dts: rockchip: remove supports-cqe from
 rk3588 jaguar

The sdhci controller supports cqe it seems and necessary code also is in
place - in theory.

At this point Jaguar and Tiger are the only boards enabling cqe support
on the rk3588 and we are seeing reliability issues under load.

This can be caused by either a controller-, hw- or driver-issue and
definitly needs more investigation to work properly it seems.

So disable cqe support on Jaguar for now.

Fixes: d1b8b36a2cc5 ("arm64: dts: rockchip: add Theobroma Jaguar SBC")
Signed-off-by: Heiko Stuebner <heiko.stuebner@cherry.de>
Reviewed-by: Quentin Schulz <quentin.schulz@cherry.de>
Link: https://lore.kernel.org/r/20250219093303.2320517-1-heiko@sntech.de
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
index 90f823b2c2191..7f457ab78015a 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-jaguar.dts
@@ -503,7 +503,6 @@
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
-	supports-cqe;
 	vmmc-supply = <&vcc_3v3_s3>;
 	vqmmc-supply = <&vcc_1v8_s3>;
 	status = "okay";

From 3e0711f89e5e7b0c7b2ab4843dc92dcbbdbba777 Mon Sep 17 00:00:00 2001
From: Heiko Stuebner <heiko.stuebner@cherry.de>
Date: Wed, 19 Feb 2025 10:33:03 +0100
Subject: [PATCH 0840/2753] arm64: dts: rockchip: remove supports-cqe from
 rk3588 tiger

The sdhci controller supports cqe it seems and necessary code also is in
place - in theory.

At this point Jaguar and Tiger are the only boards enabling cqe support
on the rk3588 and we are seeing reliability issues under load.

This can be caused by either a controller-, hw- or driver-issue and
definitly needs more investigation to work properly it seems.

So disable cqe support on Tiger for now.

Fixes: 6173ef24b35b ("arm64: dts: rockchip: add RK3588-Q7 (Tiger) SoM")
Signed-off-by: Heiko Stuebner <heiko.stuebner@cherry.de>
Reviewed-by: Quentin Schulz <quentin.schulz@cherry.de>
Link: https://lore.kernel.org/r/20250219093303.2320517-2-heiko@sntech.de
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
index 81a6a05ce13b6..e8fa449517c27 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3588-tiger.dtsi
@@ -386,7 +386,6 @@
 	non-removable;
 	pinctrl-names = "default";
 	pinctrl-0 = <&emmc_bus8 &emmc_cmd &emmc_clk &emmc_data_strobe>;
-	supports-cqe;
 	vmmc-supply = <&vcc_3v3_s3>;
 	vqmmc-supply = <&vcc_1v8_s3>;
 	status = "okay";

From 78eb41f518f414378643ab022241df2a9dcd008b Mon Sep 17 00:00:00 2001
From: Luca Ceresoli <luca.ceresoli@bootlin.com>
Date: Thu, 13 Feb 2025 15:05:13 +0100
Subject: [PATCH 0841/2753] drivers: core: fix device leak in
 __fw_devlink_relax_cycles()

Commit bac3b10b78e5 ("driver core: fw_devlink: Stop trying to optimize
cycle detection logic") introduced a new struct device *con_dev and a
get_dev_from_fwnode() call to get it, but without adding a corresponding
put_device().

Closes: https://lore.kernel.org/all/20241204124826.2e055091@booty/
Fixes: bac3b10b78e5 ("driver core: fw_devlink: Stop trying to optimize cycle detection logic")
Cc: stable@vger.kernel.org
Reviewed-by: Saravana Kannan <saravanak@google.com>
Signed-off-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://lore.kernel.org/r/20250213-fix__fw_devlink_relax_cycles_missing_device_put-v2-1-8cd3b03e6a3f@bootlin.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 5a1f051981149..2fde698430dff 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2079,6 +2079,7 @@ static bool __fw_devlink_relax_cycles(struct fwnode_handle *con_handle,
 out:
 	sup_handle->flags &= ~FWNODE_FLAG_VISITED;
 	put_device(sup_dev);
+	put_device(con_dev);
 	put_device(par_dev);
 	return ret;
 }

From c783e1258f29c5caac9eea0aea6b172870f1baf8 Mon Sep 17 00:00:00 2001
From: Marek Szyprowski <m.szyprowski@samsung.com>
Date: Thu, 20 Feb 2025 13:03:14 +0100
Subject: [PATCH 0842/2753] usb: gadget: Fix setting self-powered state on
 suspend

cdev->config might be NULL, so check it before dereferencing.

CC: stable <stable@kernel.org>
Fixes: 40e89ff5750f ("usb: gadget: Set self-powered based on MaxPower and bmAttributes")
Signed-off-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250220120314.3614330-1-m.szyprowski@samsung.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 1fb28bbf6c458..4bcf73bae7610 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -2616,7 +2616,8 @@ void composite_suspend(struct usb_gadget *gadget)
 
 	cdev->suspended = 1;
 
-	if (cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
+	if (cdev->config &&
+	    cdev->config->bmAttributes & USB_CONFIG_ATT_SELFPOWER)
 		usb_gadget_set_selfpowered(gadget);
 
 	usb_gadget_vbus_draw(gadget, 2);

From 96fa9ec477ff60bed87e1441fd43e003179f3253 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 19 Feb 2025 15:43:56 +0100
Subject: [PATCH 0843/2753] gpiolib: don't bail out if get_direction() fails in
 gpiochip_add_data()

Since commit 9d846b1aebbe ("gpiolib: check the return value of
gpio_chip::get_direction()") we check the return value of the
get_direction() callback as per its API contract. Some drivers have been
observed to fail to register now as they may call get_direction() in
gpiochip_add_data() in contexts where it has always silently failed.
Until we audit all drivers, replace the bail-out to a kernel log
warning.

Fixes: 9d846b1aebbe ("gpiolib: check the return value of gpio_chip::get_direction()")
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/Z7VFB1nST6lbmBIo@finisterre.sirena.org.uk/
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/all/dfe03f88-407e-4ef1-ad30-42db53bbd4e4@samsung.com/
Tested-by: Mark Brown <broonie@kernel.org>
Reviewed-by: Mark Brown <broonie@kernel.org>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250219144356.258635-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5529d8b65f6fb..fc19df5a64c2b 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1059,7 +1059,15 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) {
 			ret = gc->get_direction(gc, desc_index);
 			if (ret < 0)
-				goto err_cleanup_desc_srcu;
+				/*
+				 * FIXME: Bail-out here once all GPIO drivers
+				 * are updated to not return errors in
+				 * situations that can be considered normal
+				 * operation.
+				 */
+				dev_warn(&gdev->dev,
+					 "%s: get_direction failed: %d\n",
+					 __func__, ret);
 
 			assign_bit(FLAG_IS_OUT, &desc->flags, !ret);
 		} else {

From 91d44c1afc61a2fec37a9c7a3485368309391e0b Mon Sep 17 00:00:00 2001
From: Qiu-ji Chen <chenqiuji666@gmail.com>
Date: Sat, 18 Jan 2025 15:08:33 +0800
Subject: [PATCH 0844/2753] cdx: Fix possible UAF error in
 driver_override_show()

Fixed a possible UAF problem in driver_override_show() in drivers/cdx/cdx.c

This function driver_override_show() is part of DEVICE_ATTR_RW, which
includes both driver_override_show() and driver_override_store().
These functions can be executed concurrently in sysfs.

The driver_override_store() function uses driver_set_override() to
update the driver_override value, and driver_set_override() internally
locks the device (device_lock(dev)). If driver_override_show() reads
cdx_dev->driver_override without locking, it could potentially access
a freed pointer if driver_override_store() frees the string
concurrently. This could lead to printing a kernel address, which is a
security risk since DEVICE_ATTR can be read by all users.

Additionally, a similar pattern is used in drivers/amba/bus.c, as well
as many other bus drivers, where device_lock() is taken in the show
function, and it has been working without issues.

This potential bug was detected by our experimental static analysis
tool, which analyzes locking APIs and paired functions to identify
data races and atomicity violations.

Fixes: 1f86a00c1159 ("bus/fsl-mc: add support for 'driver_override' in the mc-bus")
Cc: stable <stable@kernel.org>
Signed-off-by: Qiu-ji Chen <chenqiuji666@gmail.com>
Link: https://lore.kernel.org/r/20250118070833.27201-1-chenqiuji666@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/cdx/cdx.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/cdx/cdx.c b/drivers/cdx/cdx.c
index c573ed2ee71a8..7811aa7340537 100644
--- a/drivers/cdx/cdx.c
+++ b/drivers/cdx/cdx.c
@@ -473,8 +473,12 @@ static ssize_t driver_override_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
 	struct cdx_device *cdx_dev = to_cdx_device(dev);
+	ssize_t len;
 
-	return sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_lock(dev);
+	len = sysfs_emit(buf, "%s\n", cdx_dev->driver_override);
+	device_unlock(dev);
+	return len;
 }
 static DEVICE_ATTR_RW(driver_override);
 

From c99e1e1d0850ff157f1bc16871acd2dff5a9bcc3 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 22 Jan 2025 07:54:33 +0100
Subject: [PATCH 0845/2753] vbox: add HAS_IOPORT dependency

The vboxguest driver depends on port I/O for debug output:

include/asm-generic/io.h:626:15: error: call to '_outl' declared with attribute error: outl() requires CONFIG_HAS_IOPORT
  626 | #define _outl _outl
include/asm-generic/io.h:663:14: note: in expansion of macro '_outl'
  663 | #define outl _outl
      |              ^~~~~
drivers/virt/vboxguest/vboxguest_utils.c:102:9: note: in expansion of macro 'outl'
  102 |         outl(phys_req, gdev->io_port + VMMDEV_PORT_OFF_REQUEST);
      |         ^~~~

Most arm64 platforms don't actually support port I/O, though it is
currently enabled unconditionally. Refine the vbox dependency to allow
turning HAS_IOPORT off in the future when building for platforms without
port I/O and allow compile-testing on all architectures.

Fixes: 5cf8f938bf5c ("vbox: Enable VBOXGUEST and VBOXSF_FS on ARM64")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20250122065445.1469218-1-arnd@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/vboxguest/Kconfig | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/virt/vboxguest/Kconfig b/drivers/virt/vboxguest/Kconfig
index 11b153e7454e4..eaba28c95e733 100644
--- a/drivers/virt/vboxguest/Kconfig
+++ b/drivers/virt/vboxguest/Kconfig
@@ -1,7 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 config VBOXGUEST
 	tristate "Virtual Box Guest integration support"
-	depends on (ARM64 || X86) && PCI && INPUT
+	depends on (ARM64 || X86 || COMPILE_TEST) && PCI && INPUT
+	depends on HAS_IOPORT
 	help
 	  This is a driver for the Virtual Box Guest PCI device used in
 	  Virtual Box virtual machines. Enabling this driver will add

From dcb0d43ba8eb9517e70b1a0e4b0ae0ab657a0e5a Mon Sep 17 00:00:00 2001
From: Visweswara Tanuku <quic_vtanuku@quicinc.com>
Date: Fri, 24 Jan 2025 04:57:40 -0800
Subject: [PATCH 0846/2753] slimbus: messaging: Free transaction ID in delayed
 interrupt scenario

In case of interrupt delay for any reason, slim_do_transfer()
returns timeout error but the transaction ID (TID) is not freed.
This results into invalid memory access inside
qcom_slim_ngd_rx_msgq_cb() due to invalid TID.

Fix the issue by freeing the TID in slim_do_transfer() before
returning timeout error to avoid invalid memory access.

Call trace:
__memcpy_fromio+0x20/0x190
qcom_slim_ngd_rx_msgq_cb+0x130/0x290 [slim_qcom_ngd_ctrl]
vchan_complete+0x2a0/0x4a0
tasklet_action_common+0x274/0x700
tasklet_action+0x28/0x3c
_stext+0x188/0x620
run_ksoftirqd+0x34/0x74
smpboot_thread_fn+0x1d8/0x464
kthread+0x178/0x238
ret_from_fork+0x10/0x20
Code: aa0003e8 91000429 f100044a 3940002b (3800150b)
---[ end trace 0fe00bec2b975c99 ]---
Kernel panic - not syncing: Oops: Fatal exception in interrupt.

Fixes: afbdcc7c384b ("slimbus: Add messaging APIs to slimbus framework")
Cc: stable <stable@kernel.org>
Signed-off-by: Visweswara Tanuku <quic_vtanuku@quicinc.com>
Link: https://lore.kernel.org/r/20250124125740.16897-1-quic_vtanuku@quicinc.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/slimbus/messaging.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/slimbus/messaging.c b/drivers/slimbus/messaging.c
index e7aa9bd4b44b8..6f01d944f9c65 100644
--- a/drivers/slimbus/messaging.c
+++ b/drivers/slimbus/messaging.c
@@ -148,8 +148,9 @@ int slim_do_transfer(struct slim_controller *ctrl, struct slim_msg_txn *txn)
 	}
 
 	ret = ctrl->xfer_msg(ctrl, txn);
-
-	if (!ret && need_tid && !txn->msg->comp) {
+	if (ret == -ETIMEDOUT) {
+		slim_free_txn_tid(ctrl, txn);
+	} else if (!ret && need_tid && !txn->msg->comp) {
 		unsigned long ms = txn->rl + HZ;
 
 		time_left = wait_for_completion_timeout(txn->comp,

From e77aff5528a183462714f750e45add6cc71e276a Mon Sep 17 00:00:00 2001
From: Carlos Llamas <cmllamas@google.com>
Date: Thu, 30 Jan 2025 21:58:22 +0000
Subject: [PATCH 0847/2753] binderfs: fix use-after-free in binder_devices

Devices created through binderfs are added to the global binder_devices
list but are not removed before being destroyed. This leads to dangling
pointers in the list and subsequent use-after-free errors:

  ==================================================================
  BUG: KASAN: slab-use-after-free in binder_add_device+0x5c/0x9c
  Write of size 8 at addr ffff0000c258d708 by task mount/653

  CPU: 7 UID: 0 PID: 653 Comm: mount Not tainted 6.13.0-09030-g6d61a53dd6f5 #1
  Hardware name: linux,dummy-virt (DT)
  Call trace:
   binder_add_device+0x5c/0x9c
   binderfs_binder_device_create+0x690/0x84c
   [...]
   __arm64_sys_mount+0x324/0x3bc

  Allocated by task 632:
   binderfs_binder_device_create+0x168/0x84c
   binder_ctl_ioctl+0xfc/0x184
   [...]
   __arm64_sys_ioctl+0x110/0x150

  Freed by task 649:
   kfree+0xe0/0x338
   binderfs_evict_inode+0x138/0x1dc
   [...]
  ==================================================================

Remove devices from binder_devices before destroying them.

Cc: Li Li <dualli@google.com>
Reported-by: syzbot+7015dcf45953112c8b45@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=7015dcf45953112c8b45
Fixes: 12d909cac1e1 ("binderfs: add new binder devices to binder_devices")
Signed-off-by: Carlos Llamas <cmllamas@google.com>
Tested-by: syzbot+7015dcf45953112c8b45@syzkaller.appspotmail.com
Link: https://lore.kernel.org/r/20250130215823.1518990-1-cmllamas@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/android/binderfs.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/android/binderfs.c b/drivers/android/binderfs.c
index bc6bae76ccaf1..94c6446604fc9 100644
--- a/drivers/android/binderfs.c
+++ b/drivers/android/binderfs.c
@@ -274,6 +274,7 @@ static void binderfs_evict_inode(struct inode *inode)
 	mutex_unlock(&binderfs_minors_mutex);
 
 	if (refcount_dec_and_test(&device->ref)) {
+		hlist_del_init(&device->hlist);
 		kfree(device->context.name);
 		kfree(device);
 	}

From 819cec1dc47cdeac8f5dd6ba81c1dbee2a68c3bb Mon Sep 17 00:00:00 2001
From: Haoyu Li <lihaoyu499@gmail.com>
Date: Thu, 30 Jan 2025 19:58:11 +0800
Subject: [PATCH 0848/2753] drivers: virt: acrn: hsm: Use kzalloc to avoid info
 leak in pmcmd_ioctl

In the "pmcmd_ioctl" function, three memory objects allocated by
kmalloc are initialized by "hcall_get_cpu_state", which are then
copied to user space. The initializer is indeed implemented in
"acrn_hypercall2" (arch/x86/include/asm/acrn.h). There is a risk of
information leakage due to uninitialized bytes.

Fixes: 3d679d5aec64 ("virt: acrn: Introduce interfaces to query C-states and P-states allowed by hypervisor")
Signed-off-by: Haoyu Li <lihaoyu499@gmail.com>
Cc: stable <stable@kernel.org>
Acked-by: Fei Li <fei1.li@intel.com>
Link: https://lore.kernel.org/r/20250130115811.92424-1-lihaoyu499@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/virt/acrn/hsm.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/virt/acrn/hsm.c b/drivers/virt/acrn/hsm.c
index c24036c4e51ec..e4e196abdaac9 100644
--- a/drivers/virt/acrn/hsm.c
+++ b/drivers/virt/acrn/hsm.c
@@ -49,7 +49,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 	switch (cmd & PMCMD_TYPE_MASK) {
 	case ACRN_PMCMD_GET_PX_CNT:
 	case ACRN_PMCMD_GET_CX_CNT:
-		pm_info = kmalloc(sizeof(u64), GFP_KERNEL);
+		pm_info = kzalloc(sizeof(u64), GFP_KERNEL);
 		if (!pm_info)
 			return -ENOMEM;
 
@@ -64,7 +64,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(pm_info);
 		break;
 	case ACRN_PMCMD_GET_PX_DATA:
-		px_data = kmalloc(sizeof(*px_data), GFP_KERNEL);
+		px_data = kzalloc(sizeof(*px_data), GFP_KERNEL);
 		if (!px_data)
 			return -ENOMEM;
 
@@ -79,7 +79,7 @@ static int pmcmd_ioctl(u64 cmd, void __user *uptr)
 		kfree(px_data);
 		break;
 	case ACRN_PMCMD_GET_CX_DATA:
-		cx_data = kmalloc(sizeof(*cx_data), GFP_KERNEL);
+		cx_data = kzalloc(sizeof(*cx_data), GFP_KERNEL);
 		if (!cx_data)
 			return -ENOMEM;
 

From 038ef0754aae76f79b147b8867f9250e6a976872 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 7 Feb 2025 00:03:11 +0200
Subject: [PATCH 0849/2753] eeprom: digsy_mtc: Make GPIO lookup table match the
 device

The dev_id value in the GPIO lookup table must match to
the device instance name, which in this case is combined
of name and platform device ID, i.e. "spi_gpio.1". But
the table assumed that there was no platform device ID
defined, which is wrong. Fix the dev_id value accordingly.

Fixes: 9b00bc7b901f ("spi: spi-gpio: Rewrite to use GPIO descriptors")
Cc: stable <stable@kernel.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250206220311.1554075-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/eeprom/digsy_mtc_eeprom.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/misc/eeprom/digsy_mtc_eeprom.c b/drivers/misc/eeprom/digsy_mtc_eeprom.c
index 88888485e6f8e..ee58f7ce5bfa9 100644
--- a/drivers/misc/eeprom/digsy_mtc_eeprom.c
+++ b/drivers/misc/eeprom/digsy_mtc_eeprom.c
@@ -50,7 +50,7 @@ static struct platform_device digsy_mtc_eeprom = {
 };
 
 static struct gpiod_lookup_table eeprom_spi_gpiod_table = {
-	.dev_id         = "spi_gpio",
+	.dev_id         = "spi_gpio.1",
 	.table          = {
 		GPIO_LOOKUP("gpio@b00", GPIO_EEPROM_CLK,
 			    "sck", GPIO_ACTIVE_HIGH),

From 6d991f569c5ef6eaeadf1238df2c36e3975233ad Mon Sep 17 00:00:00 2001
From: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Date: Thu, 23 Jan 2025 09:32:49 -0300
Subject: [PATCH 0850/2753] char: misc: deallocate static minor in error path

When creating sysfs files fail, the allocated minor must be freed such that
it can be later reused. That is specially harmful for static minor numbers,
since those would always fail to register later on.

Fixes: 6d04d2b554b1 ("misc: misc_minor_alloc to use ida for all dynamic/misc dynamic minors")
Cc: stable <stable@kernel.org>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@igalia.com>
Link: https://lore.kernel.org/r/20250123123249.4081674-5-cascardo@igalia.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/char/misc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/char/misc.c b/drivers/char/misc.c
index 2cf595d2e10b8..f7dd455dd0dd3 100644
--- a/drivers/char/misc.c
+++ b/drivers/char/misc.c
@@ -264,8 +264,8 @@ int misc_register(struct miscdevice *misc)
 		device_create_with_groups(&misc_class, misc->parent, dev,
 					  misc, misc->groups, "%s", misc->name);
 	if (IS_ERR(misc->this_device)) {
+		misc_minor_free(misc->minor);
 		if (is_dynamic) {
-			misc_minor_free(misc->minor);
 			misc->minor = MISC_DYNAMIC_MINOR;
 		}
 		err = PTR_ERR(misc->this_device);

From 32ce5d87d52213a50a513750f01a56f4d01f50cb Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan+linaro@kernel.org>
Date: Fri, 14 Feb 2025 11:21:30 +0100
Subject: [PATCH 0851/2753] bus: simple-pm-bus: fix forced runtime PM use

The simple-pm-bus driver only enables runtime PM for some buses
('simple-pm-bus') yet has started calling pm_runtime_force_suspend() and
pm_runtime_force_resume() during system suspend unconditionally.

This currently works, but that is not obvious and depends on
implementation details which may change at some point.

Add dedicated system sleep ops and only call pm_runtime_force_suspend()
and pm_runtime_force_resume() for buses that use runtime PM to avoid any
future surprises.

Fixes: c45839309c3d ("drivers: bus: simple-pm-bus: Use clocks")
Cc: Liu Ying <victor.liu@nxp.com>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Acked-by: Liu Ying <victor.liu@nxp.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20250214102130.3000-1-johan+linaro@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/bus/simple-pm-bus.c | 22 +++++++++++++++++++++-
 1 file changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/bus/simple-pm-bus.c b/drivers/bus/simple-pm-bus.c
index 5dea31769f9a8..d8e029e7e53f7 100644
--- a/drivers/bus/simple-pm-bus.c
+++ b/drivers/bus/simple-pm-bus.c
@@ -109,9 +109,29 @@ static int simple_pm_bus_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static int simple_pm_bus_suspend(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_suspend(dev);
+}
+
+static int simple_pm_bus_resume(struct device *dev)
+{
+	struct simple_pm_bus *bus = dev_get_drvdata(dev);
+
+	if (!bus)
+		return 0;
+
+	return pm_runtime_force_resume(dev);
+}
+
 static const struct dev_pm_ops simple_pm_bus_pm_ops = {
 	RUNTIME_PM_OPS(simple_pm_bus_runtime_suspend, simple_pm_bus_runtime_resume, NULL)
-	NOIRQ_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(simple_pm_bus_suspend, simple_pm_bus_resume)
 };
 
 #define ONLY_BUS	((void *) 1) /* Match if the device is only a bus. */

From b4c173dfbb6c78568578ff18f9e8822d7bd0e31b Mon Sep 17 00:00:00 2001
From: Miklos Szeredi <mszeredi@redhat.com>
Date: Thu, 20 Feb 2025 11:02:58 +0100
Subject: [PATCH 0852/2753] fuse: don't truncate cached, mutated symlink

Fuse allows the value of a symlink to change and this property is exploited
by some filesystems (e.g. CVMFS).

It has been observed, that sometimes after changing the symlink contents,
the value is truncated to the old size.

This is caused by fuse_getattr() racing with fuse_reverse_inval_inode().
fuse_reverse_inval_inode() updates the fuse_inode's attr_version, which
results in fuse_change_attributes() exiting before updating the cached
attributes

This is okay, as the cached attributes remain invalid and the next call to
fuse_change_attributes() will likely update the inode with the correct
values.

The reason this causes problems is that cached symlinks will be
returned through page_get_link(), which truncates the symlink to
inode->i_size.  This is correct for filesystems that don't mutate
symlinks, but in this case it causes bad behavior.

The solution is to just remove this truncation.  This can cause a
regression in a filesystem that relies on supplying a symlink larger than
the file size, but this is unlikely.  If that happens we'd need to make
this behavior conditional.

Reported-by: Laura Promberger <laura.promberger@cern.ch>
Tested-by: Sam Lewis <samclewis@google.com>
Signed-off-by: Miklos Szeredi <mszeredi@redhat.com>
Link: https://lore.kernel.org/r/20250220100258.793363-1-mszeredi@redhat.com
Reviewed-by: Bernd Schubert <bschubert@ddn.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/fuse/dir.c      |  2 +-
 fs/namei.c         | 24 +++++++++++++++++++-----
 include/linux/fs.h |  2 ++
 3 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 198862b086ff7..3805f9b06c9d2 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1636,7 +1636,7 @@ static const char *fuse_get_link(struct dentry *dentry, struct inode *inode,
 		goto out_err;
 
 	if (fc->cache_symlinks)
-		return page_get_link(dentry, inode, callback);
+		return page_get_link_raw(dentry, inode, callback);
 
 	err = -ECHILD;
 	if (!dentry)
diff --git a/fs/namei.c b/fs/namei.c
index 3ab9440c5b931..ecb7b95c2ca33 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -5356,10 +5356,9 @@ const char *vfs_get_link(struct dentry *dentry, struct delayed_call *done)
 EXPORT_SYMBOL(vfs_get_link);
 
 /* get the link contents into pagecache */
-const char *page_get_link(struct dentry *dentry, struct inode *inode,
-			  struct delayed_call *callback)
+static char *__page_get_link(struct dentry *dentry, struct inode *inode,
+			     struct delayed_call *callback)
 {
-	char *kaddr;
 	struct page *page;
 	struct address_space *mapping = inode->i_mapping;
 
@@ -5378,8 +5377,23 @@ const char *page_get_link(struct dentry *dentry, struct inode *inode,
 	}
 	set_delayed_call(callback, page_put_link, page);
 	BUG_ON(mapping_gfp_mask(mapping) & __GFP_HIGHMEM);
-	kaddr = page_address(page);
-	nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
+	return page_address(page);
+}
+
+const char *page_get_link_raw(struct dentry *dentry, struct inode *inode,
+			      struct delayed_call *callback)
+{
+	return __page_get_link(dentry, inode, callback);
+}
+EXPORT_SYMBOL_GPL(page_get_link_raw);
+
+const char *page_get_link(struct dentry *dentry, struct inode *inode,
+					struct delayed_call *callback)
+{
+	char *kaddr = __page_get_link(dentry, inode, callback);
+
+	if (!IS_ERR(kaddr))
+		nd_terminate_link(kaddr, inode->i_size, PAGE_SIZE - 1);
 	return kaddr;
 }
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 2c3b2f8a621f7..9346adf28f7bc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3452,6 +3452,8 @@ extern const struct file_operations generic_ro_fops;
 
 extern int readlink_copy(char __user *, int, const char *, int);
 extern int page_readlink(struct dentry *, char __user *, int);
+extern const char *page_get_link_raw(struct dentry *, struct inode *,
+				     struct delayed_call *);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
 extern void page_put_link(void *);

From 782cffeec9ad96daa64ffb2d527b2a052fb02552 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Wed, 19 Feb 2025 06:10:05 -0800
Subject: [PATCH 0853/2753] perf/x86/intel: Fix event constraints for LNC

According to the latest event list, update the event constraint tables
for Lion Cove core.

The general rule (the event codes < 0x90 are restricted to counters
0-3.) has been removed. There is no restriction for most of the
performance monitoring events.

Fixes: a932aa0e868f ("perf/x86: Add Lunar Lake and Arrow Lake support")
Reported-by: Amiri Khalil <amiri.khalil@intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250219141005.2446823-1-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 20 +++++++-------------
 arch/x86/events/intel/ds.c   |  2 +-
 2 files changed, 8 insertions(+), 14 deletions(-)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index e86333eee2668..cdcebf30468a0 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -397,34 +397,28 @@ static struct event_constraint intel_lnc_event_constraints[] = {
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_FETCH_LAT, 6),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_MEM_BOUND, 7),
 
+	INTEL_EVENT_CONSTRAINT(0x20, 0xf),
+
+	INTEL_UEVENT_CONSTRAINT(0x012a, 0xf),
+	INTEL_UEVENT_CONSTRAINT(0x012b, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x0148, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0175, 0x4),
 
 	INTEL_EVENT_CONSTRAINT(0x2e, 0x3ff),
 	INTEL_EVENT_CONSTRAINT(0x3c, 0x3ff),
-	/*
-	 * Generally event codes < 0x90 are restricted to counters 0-3.
-	 * The 0x2E and 0x3C are exception, which has no restriction.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x01, 0x8f, 0xf),
 
-	INTEL_UEVENT_CONSTRAINT(0x01a3, 0xf),
-	INTEL_UEVENT_CONSTRAINT(0x02a3, 0xf),
 	INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4),
 	INTEL_UEVENT_CONSTRAINT(0x04a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x08a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x10a4, 0x1),
 	INTEL_UEVENT_CONSTRAINT(0x01b1, 0x8),
+	INTEL_UEVENT_CONSTRAINT(0x01cd, 0x3fc),
 	INTEL_UEVENT_CONSTRAINT(0x02cd, 0x3),
-	INTEL_EVENT_CONSTRAINT(0xce, 0x1),
 
 	INTEL_EVENT_CONSTRAINT_RANGE(0xd0, 0xdf, 0xf),
-	/*
-	 * Generally event codes >= 0x90 are likely to have no restrictions.
-	 * The exception are defined as above.
-	 */
-	INTEL_EVENT_CONSTRAINT_RANGE(0x90, 0xfe, 0x3ff),
+
+	INTEL_UEVENT_CONSTRAINT(0x00e0, 0xf),
 
 	EVENT_CONSTRAINT_END
 };
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c2e2eae7309c3..f122882ef278f 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -1199,7 +1199,7 @@ struct event_constraint intel_lnc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
-	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3ff),
+	INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc),
 	INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3),
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_LOADS */
 	INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf),	/* MEM_INST_RETIRED.STLB_MISS_STORES */

From fa808ed4e199ed17d878eb75b110bda30dd52434 Mon Sep 17 00:00:00 2001
From: Oliver Upton <oliver.upton@linux.dev>
Date: Wed, 19 Feb 2025 14:07:37 -0800
Subject: [PATCH 0854/2753] KVM: arm64: Ensure a VMID is allocated before
 programming VTTBR_EL2

Vladimir reports that a race condition to attach a VMID to a stage-2 MMU
sometimes results in a vCPU entering the guest with a VMID of 0:

| CPU1                                            |   CPU2
|                                                 |
|                                                 | kvm_arch_vcpu_ioctl_run
|                                                 |   vcpu_load             <= load VTTBR_EL2
|                                                 |                            kvm_vmid->id = 0
|                                                 |
| kvm_arch_vcpu_ioctl_run                         |
|   vcpu_load             <= load VTTBR_EL2       |
|                            with kvm_vmid->id = 0|
|   kvm_arm_vmid_update   <= allocates fresh      |
|                            kvm_vmid->id and     |
|                            reload VTTBR_EL2     |
|                                                 |
|                                                 |   kvm_arm_vmid_update <= observes that kvm_vmid->id
|                                                 |                          already allocated,
|                                                 |                          skips reload VTTBR_EL2

Oh yeah, it's as bad as it looks. Remember that VHE loads the stage-2
MMU eagerly but a VMID only gets attached to the MMU later on in the
KVM_RUN loop.

Even in the "best case" where VTTBR_EL2 correctly gets reprogrammed
before entering the EL1&0 regime, there is a period of time where
hardware is configured with VMID 0. That's completely insane. So, rather
than decorating the 'late' binding with another hack, just allocate the
damn thing up front.

Attaching a VMID from vcpu_load() is still rollover safe since
(surprise!) it'll always get called after a vCPU was preempted.

Excuse me while I go find a brown paper bag.

Cc: stable@vger.kernel.org
Fixes: 934bf871f011 ("KVM: arm64: Load the stage-2 MMU context in kvm_vcpu_load_vhe()")
Reported-by: Vladimir Murzin <vladimir.murzin@arm.com>
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250219220737.130842-1-oliver.upton@linux.dev
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/kvm_host.h |  2 +-
 arch/arm64/kvm/arm.c              | 22 ++++++++++------------
 arch/arm64/kvm/vmid.c             | 11 +++--------
 3 files changed, 14 insertions(+), 21 deletions(-)

diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 3a7ec98ef1238..d919557af5e50 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -1259,7 +1259,7 @@ int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu,
 extern unsigned int __ro_after_init kvm_arm_vmid_bits;
 int __init kvm_arm_vmid_alloc_init(void);
 void __init kvm_arm_vmid_alloc_free(void);
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid);
 void kvm_arm_vmid_clear_active(void);
 
 static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index bc7a37cea2420..0160b49243511 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -559,6 +559,16 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	mmu = vcpu->arch.hw_mmu;
 	last_ran = this_cpu_ptr(mmu->last_vcpu_ran);
 
+	/*
+	 * Ensure a VMID is allocated for the MMU before programming VTTBR_EL2,
+	 * which happens eagerly in VHE.
+	 *
+	 * Also, the VMID allocator only preserves VMIDs that are active at the
+	 * time of rollover, so KVM might need to grab a new VMID for the MMU if
+	 * this is called from kvm_sched_in().
+	 */
+	kvm_arm_vmid_update(&mmu->vmid);
+
 	/*
 	 * We guarantee that both TLBs and I-cache are private to each
 	 * vcpu. If detecting that a vcpu from the same VM has
@@ -1138,18 +1148,6 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		 */
 		preempt_disable();
 
-		/*
-		 * The VMID allocator only tracks active VMIDs per
-		 * physical CPU, and therefore the VMID allocated may not be
-		 * preserved on VMID roll-over if the task was preempted,
-		 * making a thread's VMID inactive. So we need to call
-		 * kvm_arm_vmid_update() in non-premptible context.
-		 */
-		if (kvm_arm_vmid_update(&vcpu->arch.hw_mmu->vmid) &&
-		    has_vhe())
-			__load_stage2(vcpu->arch.hw_mmu,
-				      vcpu->arch.hw_mmu->arch);
-
 		kvm_pmu_flush_hwstate(vcpu);
 
 		local_irq_disable();
diff --git a/arch/arm64/kvm/vmid.c b/arch/arm64/kvm/vmid.c
index 806223b7022af..7fe8ba1a2851c 100644
--- a/arch/arm64/kvm/vmid.c
+++ b/arch/arm64/kvm/vmid.c
@@ -135,11 +135,10 @@ void kvm_arm_vmid_clear_active(void)
 	atomic64_set(this_cpu_ptr(&active_vmids), VMID_ACTIVE_INVALID);
 }
 
-bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
+void kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 {
 	unsigned long flags;
 	u64 vmid, old_active_vmid;
-	bool updated = false;
 
 	vmid = atomic64_read(&kvm_vmid->id);
 
@@ -157,21 +156,17 @@ bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid)
 	if (old_active_vmid != 0 && vmid_gen_match(vmid) &&
 	    0 != atomic64_cmpxchg_relaxed(this_cpu_ptr(&active_vmids),
 					  old_active_vmid, vmid))
-		return false;
+		return;
 
 	raw_spin_lock_irqsave(&cpu_vmid_lock, flags);
 
 	/* Check that our VMID belongs to the current generation. */
 	vmid = atomic64_read(&kvm_vmid->id);
-	if (!vmid_gen_match(vmid)) {
+	if (!vmid_gen_match(vmid))
 		vmid = new_vmid(kvm_vmid);
-		updated = true;
-	}
 
 	atomic64_set(this_cpu_ptr(&active_vmids), vmid);
 	raw_spin_unlock_irqrestore(&cpu_vmid_lock, flags);
-
-	return updated;
 }
 
 /*

From 9af3b4f2d879da01192d6168e6c651e7fb5b652d Mon Sep 17 00:00:00 2001
From: Dmitry Panchenko <dmitry@d-systems.ee>
Date: Thu, 20 Feb 2025 18:15:37 +0200
Subject: [PATCH 0855/2753] ALSA: usb-audio: Re-add sample rate quirk for
 Pioneer DJM-900NXS2

Re-add the sample-rate quirk for the Pioneer DJM-900NXS2. This
device does not work without setting sample-rate.

Signed-off-by: Dmitry Panchenko <dmitry@d-systems.ee>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250220161540.3624660-1-dmitry@d-systems.ee
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/quirks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index a97efb7b131ea..09210fb4ac60c 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -1868,6 +1868,7 @@ void snd_usb_set_format_quirk(struct snd_usb_substream *subs,
 	case USB_ID(0x534d, 0x2109): /* MacroSilicon MS2109 */
 		subs->stream_offset_adj = 2;
 		break;
+	case USB_ID(0x2b73, 0x000a): /* Pioneer DJM-900NXS2 */
 	case USB_ID(0x2b73, 0x0013): /* Pioneer DJM-450 */
 		pioneer_djm_set_format_quirk(subs, 0x0082);
 		break;

From f13409bb3f9140dad7256febcb478f0c9600312c Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Fri, 14 Feb 2025 09:02:04 +0100
Subject: [PATCH 0856/2753] nvme-fc: rely on state transitions to handle
 connectivity loss

It's not possible to call nvme_state_ctrl_state with holding a spin
lock, because nvme_state_ctrl_state calls cancel_delayed_work_sync
when fastfail is enabled.

Instead syncing the ASSOC_FLAG and state transitions using a lock, it's
possible to only rely on the state machine transitions. That means
nvme_fc_ctrl_connectivity_loss should unconditionally call
nvme_reset_ctrl which avoids the read race on the ctrl state variable.
Actually, it's not necessary to test in which state the ctrl is, the
reset work will only scheduled when the state machine is in LIVE state.

In nvme_fc_create_association, the LIVE state can only be entered if it
was previously CONNECTING. If this is not possible then the reset
handler got triggered. Thus just error out here.

Fixes: ee59e3820ca9 ("nvme-fc: do not ignore connectivity loss during connecting")
Closes: https://lore.kernel.org/all/denqwui6sl5erqmz2gvrwueyxakl5txzbbiu3fgebryzrfxunm@iwxuthct377m/
Reported-by: Shinichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/fc.c | 67 ++++--------------------------------------
 1 file changed, 6 insertions(+), 61 deletions(-)

diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
index f4f1866fbd5b8..b9929a5a7f4e3 100644
--- a/drivers/nvme/host/fc.c
+++ b/drivers/nvme/host/fc.c
@@ -781,61 +781,12 @@ nvme_fc_abort_lsops(struct nvme_fc_rport *rport)
 static void
 nvme_fc_ctrl_connectivity_loss(struct nvme_fc_ctrl *ctrl)
 {
-	enum nvme_ctrl_state state;
-	unsigned long flags;
-
 	dev_info(ctrl->ctrl.device,
 		"NVME-FC{%d}: controller connectivity lost. Awaiting "
 		"Reconnect", ctrl->cnum);
 
-	spin_lock_irqsave(&ctrl->lock, flags);
 	set_bit(ASSOC_FAILED, &ctrl->flags);
-	state = nvme_ctrl_state(&ctrl->ctrl);
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	switch (state) {
-	case NVME_CTRL_NEW:
-	case NVME_CTRL_LIVE:
-		/*
-		 * Schedule a controller reset. The reset will terminate the
-		 * association and schedule the reconnect timer.  Reconnects
-		 * will be attempted until either the ctlr_loss_tmo
-		 * (max_retries * connect_delay) expires or the remoteport's
-		 * dev_loss_tmo expires.
-		 */
-		if (nvme_reset_ctrl(&ctrl->ctrl)) {
-			dev_warn(ctrl->ctrl.device,
-				"NVME-FC{%d}: Couldn't schedule reset.\n",
-				ctrl->cnum);
-			nvme_delete_ctrl(&ctrl->ctrl);
-		}
-		break;
-
-	case NVME_CTRL_CONNECTING:
-		/*
-		 * The association has already been terminated and the
-		 * controller is attempting reconnects.  No need to do anything
-		 * futher.  Reconnects will be attempted until either the
-		 * ctlr_loss_tmo (max_retries * connect_delay) expires or the
-		 * remoteport's dev_loss_tmo expires.
-		 */
-		break;
-
-	case NVME_CTRL_RESETTING:
-		/*
-		 * Controller is already in the process of terminating the
-		 * association.  No need to do anything further. The reconnect
-		 * step will kick in naturally after the association is
-		 * terminated.
-		 */
-		break;
-
-	case NVME_CTRL_DELETING:
-	case NVME_CTRL_DELETING_NOIO:
-	default:
-		/* no action to take - let it delete */
-		break;
-	}
+	nvme_reset_ctrl(&ctrl->ctrl);
 }
 
 /**
@@ -3071,7 +3022,6 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 	struct nvmefc_ls_rcv_op *disls = NULL;
 	unsigned long flags;
 	int ret;
-	bool changed;
 
 	++ctrl->ctrl.nr_reconnects;
 
@@ -3177,23 +3127,18 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
 		else
 			ret = nvme_fc_recreate_io_queues(ctrl);
 	}
+	if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags))
+		ret = -EIO;
 	if (ret)
 		goto out_term_aen_ops;
 
-	spin_lock_irqsave(&ctrl->lock, flags);
-	if (!test_bit(ASSOC_FAILED, &ctrl->flags))
-		changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE);
-	else
+	if (!nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE)) {
 		ret = -EIO;
-	spin_unlock_irqrestore(&ctrl->lock, flags);
-
-	if (ret)
 		goto out_term_aen_ops;
+	}
 
 	ctrl->ctrl.nr_reconnects = 0;
-
-	if (changed)
-		nvme_start_ctrl(&ctrl->ctrl);
+	nvme_start_ctrl(&ctrl->ctrl);
 
 	return 0;	/* Success */
 

From d2fe192348f93fe3a0cb1e33e4aba58e646397f4 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Fri, 14 Feb 2025 09:02:03 +0100
Subject: [PATCH 0857/2753] nvme: only allow entering LIVE from CONNECTING
 state

The fabric transports and also the PCI transport are not entering the
LIVE state from NEW or RESETTING. This makes the state machine more
restrictive and allows to catch not supported state transitions, e.g.
directly switching from RESETTING to LIVE.

Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/core.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 818d4e49aab51..f028913e2e622 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -564,8 +564,6 @@ bool nvme_change_ctrl_state(struct nvme_ctrl *ctrl,
 	switch (new_state) {
 	case NVME_CTRL_LIVE:
 		switch (old_state) {
-		case NVME_CTRL_NEW:
-		case NVME_CTRL_RESETTING:
 		case NVME_CTRL_CONNECTING:
 			changed = true;
 			fallthrough;

From 860ca5e50f73c2a1cef7eefc9d39d04e275417f7 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Mon, 17 Feb 2025 15:20:38 +0800
Subject: [PATCH 0858/2753] smb: client: Add check for next_buffer in
 receive_encrypted_standard()

Add check for the return value of cifs_buf_get() and cifs_small_buf_get()
in receive_encrypted_standard() to prevent null pointer dereference.

Fixes: eec04ea11969 ("smb: client: fix OOB in receive_encrypted_standard()")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/smb2ops.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
index 23e0c8be7fb52..4dd11eafb69d9 100644
--- a/fs/smb/client/smb2ops.c
+++ b/fs/smb/client/smb2ops.c
@@ -4965,6 +4965,10 @@ receive_encrypted_standard(struct TCP_Server_Info *server,
 			next_buffer = (char *)cifs_buf_get();
 		else
 			next_buffer = (char *)cifs_small_buf_get();
+		if (!next_buffer) {
+			cifs_server_dbg(VFS, "No memory for (large) SMB response\n");
+			return -1;
+		}
 		memcpy(next_buffer, buf + next_cmd, pdu_length - next_cmd);
 	}
 

From bd30e8d7bfa6e528f9e746c940e6f7246c7899d6 Mon Sep 17 00:00:00 2001
From: Hsin-chen Chuang <chharry@chromium.org>
Date: Fri, 14 Feb 2025 19:17:09 +0800
Subject: [PATCH 0859/2753] Bluetooth: Always allow SCO packets for user
 channel

The SCO packets from Bluetooth raw socket are now rejected because
hci_conn_num is left 0. This patch allows such the usecase to enable
the userspace SCO support.

Fixes: b16b327edb4d ("Bluetooth: btusb: add sysfs attribute to control USB alt setting")
Signed-off-by: Hsin-chen Chuang <chharry@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 90966dfbd2781..8149e53fd0a76 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2102,7 +2102,8 @@ static int btusb_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 		return submit_or_queue_tx_urb(hdev, urb);
 
 	case HCI_SCODATA_PKT:
-		if (hci_conn_num(hdev, SCO_LINK) < 1)
+		if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+		    hci_conn_num(hdev, SCO_LINK) < 1)
 			return -ENODEV;
 
 		urb = alloc_isoc_urb(hdev, skb);
@@ -2576,7 +2577,8 @@ static int btusb_send_frame_intel(struct hci_dev *hdev, struct sk_buff *skb)
 		return submit_or_queue_tx_urb(hdev, urb);
 
 	case HCI_SCODATA_PKT:
-		if (hci_conn_num(hdev, SCO_LINK) < 1)
+		if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL) &&
+		    hci_conn_num(hdev, SCO_LINK) < 1)
 			return -ENODEV;
 
 		urb = alloc_isoc_urb(hdev, skb);

From b25120e1d5f2ebb3db00af557709041f47f7f3d0 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 14 Feb 2025 10:30:25 -0500
Subject: [PATCH 0860/2753] Bluetooth: L2CAP: Fix L2CAP_ECRED_CONN_RSP response

L2CAP_ECRED_CONN_RSP needs to respond DCID in the same order received as
SCID but the order is reversed due to use of list_add which actually
prepend channels to the list so the response is reversed:

> ACL Data RX: Handle 16 flags 0x02 dlen 26
      LE L2CAP: Enhanced Credit Connection Request (0x17) ident 2 len 18
        PSM: 39 (0x0027)
        MTU: 256
        MPS: 251
        Credits: 65535
        Source CID: 116
        Source CID: 117
        Source CID: 118
        Source CID: 119
        Source CID: 120
< ACL Data TX: Handle 16 flags 0x00 dlen 26
      LE L2CAP: Enhanced Credit Connection Response (0x18) ident 2 len 18
        MTU: 517
        MPS: 247
        Credits: 3
        Result: Connection successful (0x0000)
        Destination CID: 68
        Destination CID: 67
        Destination CID: 66
        Destination CID: 65
        Destination CID: 64

Also make sure the response don't include channels that are not on
BT_CONNECT2 since the chan->ident can be set to the same value as in the
following trace:

< ACL Data TX: Handle 16 flags 0x00 dlen 12
      LE L2CAP: LE Flow Control Credit (0x16) ident 6 len 4
        Source CID: 64
        Credits: 1
...
> ACL Data RX: Handle 16 flags 0x02 dlen 18
      LE L2CAP: Enhanced Credit Connection Request (0x17) ident 6 len 10
        PSM: 39 (0x0027)
        MTU: 517
        MPS: 251
        Credits: 255
        Source CID: 70
< ACL Data TX: Handle 16 flags 0x00 dlen 20
      LE L2CAP: Enhanced Credit Connection Response (0x18) ident 6 len 12
        MTU: 517
        MPS: 247
        Credits: 3
        Result: Connection successful (0x0000)
        Destination CID: 64
        Destination CID: 68

Closes: https://github.com/bluez/bluez/issues/1094
Fixes: 9aa9d9473f15 ("Bluetooth: L2CAP: Fix responding with wrong PDU type")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/l2cap_core.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index fec11e576f310..b22078b679726 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -632,7 +632,8 @@ void __l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
 	    test_bit(FLAG_HOLD_HCI_CONN, &chan->flags))
 		hci_conn_hold(conn->hcon);
 
-	list_add(&chan->list, &conn->chan_l);
+	/* Append to the list since the order matters for ECRED */
+	list_add_tail(&chan->list, &conn->chan_l);
 }
 
 void l2cap_chan_add(struct l2cap_conn *conn, struct l2cap_chan *chan)
@@ -3771,7 +3772,11 @@ static void l2cap_ecred_rsp_defer(struct l2cap_chan *chan, void *data)
 	struct l2cap_ecred_conn_rsp *rsp_flex =
 		container_of(&rsp->pdu.rsp, struct l2cap_ecred_conn_rsp, hdr);
 
-	if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags))
+	/* Check if channel for outgoing connection or if it wasn't deferred
+	 * since in those cases it must be skipped.
+	 */
+	if (test_bit(FLAG_ECRED_CONN_REQ_SENT, &chan->flags) ||
+	    !test_and_clear_bit(FLAG_DEFER_SETUP, &chan->flags))
 		return;
 
 	/* Reset ident so only one response is sent */

From 511a3444f72efdc51fa923c4b1f5f0abd545fb20 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Thu, 20 Feb 2025 15:07:57 +0100
Subject: [PATCH 0861/2753] MAINTAINERS: Add entry for DMEM cgroup controller
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The cgroups controller is currently maintained through the
drm-misc tree, so lets add Maxime Ripard, Natalie Vock
and me as specific maintainers for dmem.

We keep the cgroup mailing list CC'd on all cgroup specific patches.

Acked-by: Maxime Ripard <mripard@kernel.org>
Acked-by: Natalie Vock <natalie.vock@gmx.de>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Michal Koutný <mkoutny@suse.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250220140757.16823-1-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
---
 .mailmap    |  1 +
 MAINTAINERS | 11 +++++++++++
 2 files changed, 12 insertions(+)

diff --git a/.mailmap b/.mailmap
index 399322897938d..b71ee37f805d3 100644
--- a/.mailmap
+++ b/.mailmap
@@ -502,6 +502,7 @@ Nadav Amit <nadav.amit@gmail.com> <namit@cs.technion.ac.il>
 Nadia Yvette Chambers <nyc@holomorphy.com> William Lee Irwin III <wli@holomorphy.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <n-horiguchi@ah.jp.nec.com>
 Naoya Horiguchi <nao.horiguchi@gmail.com> <naoya.horiguchi@nec.com>
+Natalie Vock <natalie.vock@gmx.de> <friedrich.vock@gmx.de>
 Nathan Chancellor <nathan@kernel.org> <natechancellor@gmail.com>
 Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.ibm.com>
 Naveen N Rao <naveen@kernel.org> <naveen.n.rao@linux.vnet.ibm.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 18ade2ea4f3c4..473e7814a2925 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5878,6 +5878,17 @@ F:	tools/testing/selftests/cgroup/test_cpuset.c
 F:	tools/testing/selftests/cgroup/test_cpuset_prs.sh
 F:	tools/testing/selftests/cgroup/test_cpuset_v1_base.sh
 
+CONTROL GROUP - DEVICE MEMORY CONTROLLER (DMEM)
+M:	Maarten Lankhorst <dev@lankhorst.se>
+M:	Maxime Ripard <mripard@kernel.org>
+M:	Natalie Vock <natalie.vock@gmx.de>
+L:	cgroups@vger.kernel.org
+L:	dri-devel@lists.freedesktop.org
+S:	Maintained
+T:	git https://gitlab.freedesktop.org/drm/misc/kernel.git
+F:	include/linux/cgroup_dmem.h
+F:	kernel/cgroup/dmem.c
+
 CONTROL GROUP - MEMORY RESOURCE CONTROLLER (MEMCG)
 M:	Johannes Weiner <hannes@cmpxchg.org>
 M:	Michal Hocko <mhocko@kernel.org>

From ba3fa6e8c1eb4e40719451710263c87fb5f22221 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 19 Feb 2025 16:32:55 +0200
Subject: [PATCH 0862/2753] ip_tunnel: Use ip_tunnel_info() helper instead of
 'info + 1'

Tunnel options should not be accessed directly, use the ip_tunnel_info()
accessor instead.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250219143256.370277-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h   | 2 +-
 net/sched/act_tunnel_key.c | 8 ++++----
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 1aa31bdb2b31e..7b54cea5de270 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -650,7 +650,7 @@ static inline void iptunnel_xmit_stats(struct net_device *dev, int pkt_len)
 static inline void ip_tunnel_info_opts_get(void *to,
 					   const struct ip_tunnel_info *info)
 {
-	memcpy(to, info + 1, info->options_len);
+	memcpy(to, ip_tunnel_info_opts(info), info->options_len);
 }
 
 static inline void ip_tunnel_info_opts_set(struct ip_tunnel_info *info,
diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c
index af7c998459488..ae5dea7c48a82 100644
--- a/net/sched/act_tunnel_key.c
+++ b/net/sched/act_tunnel_key.c
@@ -571,8 +571,8 @@ static void tunnel_key_release(struct tc_action *a)
 static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 				       const struct ip_tunnel_info *info)
 {
+	const u8 *src = ip_tunnel_info_opts(info);
 	int len = info->options_len;
-	u8 *src = (u8 *)(info + 1);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_GENEVE);
@@ -580,7 +580,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 		return -EMSGSIZE;
 
 	while (len > 0) {
-		struct geneve_opt *opt = (struct geneve_opt *)src;
+		const struct geneve_opt *opt = (const struct geneve_opt *)src;
 
 		if (nla_put_be16(skb, TCA_TUNNEL_KEY_ENC_OPT_GENEVE_CLASS,
 				 opt->opt_class) ||
@@ -603,7 +603,7 @@ static int tunnel_key_geneve_opts_dump(struct sk_buff *skb,
 static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
 				      const struct ip_tunnel_info *info)
 {
-	struct vxlan_metadata *md = (struct vxlan_metadata *)(info + 1);
+	const struct vxlan_metadata *md = ip_tunnel_info_opts(info);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_VXLAN);
@@ -622,7 +622,7 @@ static int tunnel_key_vxlan_opts_dump(struct sk_buff *skb,
 static int tunnel_key_erspan_opts_dump(struct sk_buff *skb,
 				       const struct ip_tunnel_info *info)
 {
-	struct erspan_metadata *md = (struct erspan_metadata *)(info + 1);
+	const struct erspan_metadata *md = ip_tunnel_info_opts(info);
 	struct nlattr *start;
 
 	start = nla_nest_start_noflag(skb, TCA_TUNNEL_KEY_ENC_OPTS_ERSPAN);

From bb5e62f2d547c4de6d1b144cbce2373a76c33f18 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 19 Feb 2025 16:32:56 +0200
Subject: [PATCH 0863/2753] net: Add options as a flexible array to struct
 ip_tunnel_info

Remove the hidden assumption that options are allocated at the end of
the struct, and teach the compiler about them using a flexible array.

With this, we can revert the unsafe_memcpy() call we have in
tun_dst_unclone() [1], and resolve the false field-spanning write
warning caused by the memcpy() in ip_tunnel_info_opts_set().

The layout of struct ip_tunnel_info remains the same with this patch.
Before this patch, there was an implicit padding at the end of the
struct, options would be written at 'info + 1' which is after the
padding.
This will remain the same as this patch explicitly aligns 'options'.
The alignment is needed as the options are later casted to different
structs, and might result in unaligned memory access.

Pahole output before this patch:
struct ip_tunnel_info {
    struct ip_tunnel_key       key;                  /*     0    64 */

    /* XXX last struct has 1 byte of padding */

    /* --- cacheline 1 boundary (64 bytes) --- */
    struct ip_tunnel_encap     encap;                /*    64     8 */
    struct dst_cache           dst_cache;            /*    72    16 */
    u8                         options_len;          /*    88     1 */
    u8                         mode;                 /*    89     1 */

    /* size: 96, cachelines: 2, members: 5 */
    /* padding: 6 */
    /* paddings: 1, sum paddings: 1 */
    /* last cacheline: 32 bytes */
};

Pahole output after this patch:
struct ip_tunnel_info {
    struct ip_tunnel_key       key;                  /*     0    64 */

    /* XXX last struct has 1 byte of padding */

    /* --- cacheline 1 boundary (64 bytes) --- */
    struct ip_tunnel_encap     encap;                /*    64     8 */
    struct dst_cache           dst_cache;            /*    72    16 */
    u8                         options_len;          /*    88     1 */
    u8                         mode;                 /*    89     1 */

    /* XXX 6 bytes hole, try to pack */

    u8                         options[] __attribute__((__aligned__(16))); /*    96     0 */

    /* size: 96, cachelines: 2, members: 6 */
    /* sum members: 90, holes: 1, sum holes: 6 */
    /* paddings: 1, sum paddings: 1 */
    /* forced alignments: 1, forced holes: 1, sum forced holes: 6 */
    /* last cacheline: 32 bytes */
} __attribute__((__aligned__(16)));

[1] Commit 13cfd6a6d7ac ("net: Silence false field-spanning write warning in metadata_dst memcpy")

Link: https://lore.kernel.org/all/53D1D353-B8F6-4ADC-8F29-8C48A7C9C6F1@kernel.org/
Suggested-by: Kees Cook <kees@kernel.org>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250219143256.370277-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dst_metadata.h | 7 ++-----
 include/net/ip_tunnels.h   | 5 +++--
 net/core/dst.c             | 6 ++++--
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/include/net/dst_metadata.h b/include/net/dst_metadata.h
index 84c15402931cd..4160731dcb6e3 100644
--- a/include/net/dst_metadata.h
+++ b/include/net/dst_metadata.h
@@ -163,11 +163,8 @@ static inline struct metadata_dst *tun_dst_unclone(struct sk_buff *skb)
 	if (!new_md)
 		return ERR_PTR(-ENOMEM);
 
-	unsafe_memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
-		      sizeof(struct ip_tunnel_info) + md_size,
-		      /* metadata_dst_alloc() reserves room (md_size bytes) for
-		       * options right after the ip_tunnel_info struct.
-		       */);
+	memcpy(&new_md->u.tun_info, &md_dst->u.tun_info,
+	       sizeof(struct ip_tunnel_info) + md_size);
 #ifdef CONFIG_DST_CACHE
 	/* Unclone the dst cache if there is one */
 	if (new_md->u.tun_info.dst_cache.cache) {
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 7b54cea5de270..e041e4865373e 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -95,8 +95,8 @@ struct ip_tunnel_encap {
 
 #define ip_tunnel_info_opts(info)				\
 	_Generic(info,						\
-		 const struct ip_tunnel_info * : ((const void *)((info) + 1)),\
-		 struct ip_tunnel_info * : ((void *)((info) + 1))\
+		 const struct ip_tunnel_info * : ((const void *)(info)->options),\
+		 struct ip_tunnel_info * : ((void *)(info)->options)\
 	)
 
 struct ip_tunnel_info {
@@ -107,6 +107,7 @@ struct ip_tunnel_info {
 #endif
 	u8			options_len;
 	u8			mode;
+	u8			options[] __aligned_largest __counted_by(options_len);
 };
 
 /* 6rd prefix/relay information */
diff --git a/net/core/dst.c b/net/core/dst.c
index 9552a90d4772d..c99b95cf9cbb1 100644
--- a/net/core/dst.c
+++ b/net/core/dst.c
@@ -286,7 +286,8 @@ struct metadata_dst *metadata_dst_alloc(u8 optslen, enum metadata_type type,
 {
 	struct metadata_dst *md_dst;
 
-	md_dst = kmalloc(sizeof(*md_dst) + optslen, flags);
+	md_dst = kmalloc(struct_size(md_dst, u.tun_info.options, optslen),
+			 flags);
 	if (!md_dst)
 		return NULL;
 
@@ -314,7 +315,8 @@ metadata_dst_alloc_percpu(u8 optslen, enum metadata_type type, gfp_t flags)
 	int cpu;
 	struct metadata_dst __percpu *md_dst;
 
-	md_dst = __alloc_percpu_gfp(sizeof(struct metadata_dst) + optslen,
+	md_dst = __alloc_percpu_gfp(struct_size(md_dst, u.tun_info.options,
+						optslen),
 				    __alignof__(struct metadata_dst), flags);
 	if (!md_dst)
 		return NULL;

From bf3624cf1c3708284c53ed99a1c43f2e104dc2dd Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 19 Feb 2025 08:41:20 -0800
Subject: [PATCH 0864/2753] netdevsim: call napi_schedule from a timer context

The netdevsim driver was experiencing NOHZ tick-stop errors during packet
transmission due to pending softirq work when calling napi_schedule().
This issue was observed when running the netconsole selftest, which
triggered the following error message:

  NOHZ tick-stop error: local softirq work is pending, handler #08!!!

To fix this issue, introduce a timer that schedules napi_schedule()
from a timer context instead of calling it directly from the TX path.

Create an hrtimer for each queue and kick it from the TX path,
which then schedules napi_schedule() from the timer context.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250219-netdevsim-v3-1-811e2b8abc4c@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/netdev.c    | 21 ++++++++++++++++++++-
 drivers/net/netdevsim/netdevsim.h |  1 +
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 9b394ddc5206a..a41dc79e9c2e0 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -87,7 +87,8 @@ static netdev_tx_t nsim_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	if (unlikely(nsim_forward_skb(peer_dev, skb, rq) == NET_RX_DROP))
 		goto out_drop_cnt;
 
-	napi_schedule(&rq->napi);
+	if (!hrtimer_active(&rq->napi_timer))
+		hrtimer_start(&rq->napi_timer, us_to_ktime(5), HRTIMER_MODE_REL);
 
 	rcu_read_unlock();
 	u64_stats_update_begin(&ns->syncp);
@@ -426,6 +427,22 @@ static int nsim_init_napi(struct netdevsim *ns)
 	return err;
 }
 
+static enum hrtimer_restart nsim_napi_schedule(struct hrtimer *timer)
+{
+	struct nsim_rq *rq;
+
+	rq = container_of(timer, struct nsim_rq, napi_timer);
+	napi_schedule(&rq->napi);
+
+	return HRTIMER_NORESTART;
+}
+
+static void nsim_rq_timer_init(struct nsim_rq *rq)
+{
+	hrtimer_init(&rq->napi_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	rq->napi_timer.function = nsim_napi_schedule;
+}
+
 static void nsim_enable_napi(struct netdevsim *ns)
 {
 	struct net_device *dev = ns->netdev;
@@ -615,11 +632,13 @@ static struct nsim_rq *nsim_queue_alloc(void)
 		return NULL;
 
 	skb_queue_head_init(&rq->skb_queue);
+	nsim_rq_timer_init(rq);
 	return rq;
 }
 
 static void nsim_queue_free(struct nsim_rq *rq)
 {
+	hrtimer_cancel(&rq->napi_timer);
 	skb_queue_purge_reason(&rq->skb_queue, SKB_DROP_REASON_QUEUE_PURGE);
 	kfree(rq);
 }
diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h
index 96d54c08043d3..e757f85ed8617 100644
--- a/drivers/net/netdevsim/netdevsim.h
+++ b/drivers/net/netdevsim/netdevsim.h
@@ -97,6 +97,7 @@ struct nsim_rq {
 	struct napi_struct napi;
 	struct sk_buff_head skb_queue;
 	struct page_pool *page_pool;
+	struct hrtimer napi_timer;
 };
 
 struct netdevsim {

From 992ee3ed6e9fdd0be83a7daa5ff738e3cf86047f Mon Sep 17 00:00:00 2001
From: George Moussalem <george.moussalem@outlook.com>
Date: Wed, 19 Feb 2025 14:09:21 +0100
Subject: [PATCH 0865/2753] net: phy: qcom: qca807x fix condition for
 DAC_DSP_BIAS_CURRENT

While setting the DAC value, the wrong boolean value is evaluated to set
the DSP bias current. So let's correct the conditional statement and use
the right boolean value read from the DTS set in the priv.

Cc: stable@vger.kernel.org
Fixes: d1cb613efbd3 ("net: phy: qcom: add support for QCA807x PHY Family")
Signed-off-by: George Moussalem <george.moussalem@outlook.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250219130923.7216-1-ansuelsmth@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index 3279de857b474..2ad8c2586d643 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -774,7 +774,7 @@ static int qca807x_config_init(struct phy_device *phydev)
 	control_dac &= ~QCA807X_CONTROL_DAC_MASK;
 	if (!priv->dac_full_amplitude)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_AMPLITUDE;
-	if (!priv->dac_full_amplitude)
+	if (!priv->dac_full_bias_current)
 		control_dac |= QCA807X_CONTROL_DAC_DSP_BIAS_CURRENT;
 	if (!priv->dac_disable_bias_current_tweak)
 		control_dac |= QCA807X_CONTROL_DAC_BIAS_CURRENT_TWEAK;

From e31e3f6c0ce473f7ce1e70d54ac8e3ed190509f8 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 20 Feb 2025 16:17:14 +0800
Subject: [PATCH 0866/2753] soc: loongson: loongson2_guts: Add check for
 devm_kstrdup()

Add check for the return value of devm_kstrdup() in
loongson2_guts_probe() to catch potential exception.

Fixes: b82621ac8450 ("soc: loongson: add GUTS driver for loongson-2 platforms")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Link: https://lore.kernel.org/r/20250220081714.2676828-1-haoxiang_li2024@163.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/soc/loongson/loongson2_guts.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/soc/loongson/loongson2_guts.c b/drivers/soc/loongson/loongson2_guts.c
index ae42e3a9127fc..16913c3ef65ca 100644
--- a/drivers/soc/loongson/loongson2_guts.c
+++ b/drivers/soc/loongson/loongson2_guts.c
@@ -114,8 +114,11 @@ static int loongson2_guts_probe(struct platform_device *pdev)
 	if (of_property_read_string(root, "model", &machine))
 		of_property_read_string_index(root, "compatible", 0, &machine);
 	of_node_put(root);
-	if (machine)
+	if (machine) {
 		soc_dev_attr.machine = devm_kstrdup(dev, machine, GFP_KERNEL);
+		if (!soc_dev_attr.machine)
+			return -ENOMEM;
+	}
 
 	svr = loongson2_guts_get_svr();
 	soc_die = loongson2_soc_die_match(svr, loongson2_soc_die);

From cb9a978a20a4481dd59c3ea8c6fee36b3dac2b47 Mon Sep 17 00:00:00 2001
From: P Praneesh <praneesh.p@oss.qualcomm.com>
Date: Wed, 19 Feb 2025 11:06:40 +0530
Subject: [PATCH 0867/2753] wifi: ath12k: remove redundant declaration of
 ath12k_dp_rx_h_find_peer()

The current code in dp_rx.h declares the ath12k_dp_rx_h_find_peer() twice.
Fix this by removing one of the redundant declarations of
ath12k_dp_rx_h_find_peer() to ensure that the function is declared only
once.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1
Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0.c5-00481-QCAHMTSWPL_V1.0_V2.0_SILICONZ-3

Signed-off-by: P Praneesh <praneesh.p@oss.qualcomm.com>
Link: https://patch.msgid.link/20250219053640.223734-1-praneesh.p@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_rx.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.h b/drivers/net/wireless/ath/ath12k/dp_rx.h
index c0aa965f47e77..88e42365a9d8b 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.h
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.h
@@ -138,9 +138,6 @@ u32 ath12k_dp_rx_h_mpdu_err(struct ath12k_base *ab,
 			    struct hal_rx_desc *desc);
 void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
 			 struct ieee80211_rx_status *rx_status);
-struct ath12k_peer *
-ath12k_dp_rx_h_find_peer(struct ath12k_base *ab, struct sk_buff *msdu);
-
 int ath12k_dp_rxdma_ring_sel_config_qcn9274(struct ath12k_base *ab);
 int ath12k_dp_rxdma_ring_sel_config_wcn7850(struct ath12k_base *ab);
 

From af1c6007a64e78b729eb5a8d149637a820077bee Mon Sep 17 00:00:00 2001
From: Nicolas Escande <nico.escande@gmail.com>
Date: Fri, 24 Jan 2025 12:33:31 +0100
Subject: [PATCH 0868/2753] wifi: ath12k: Add missing htt_metadata flag in
 ath12k_dp_tx()

When AP-VLAN support was added, the HTT_TCL_META_DATA_VALID_HTT flag
was not added to the tx_info's meta_data_flags. Without this flag the
firmware seems to reject all the broadcast (ap-vlan) frames. So add
the flag, just as ath11k did it in the downstream QSDK project[1].

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Fixes: 26dd8ccdba4d ("wifi: ath12k: dynamic VLAN support")
Signed-off-by: Nicolas Escande <nico.escande@gmail.com>
Link: https://git.codelinaro.org/clo/qsdk/oss/system/feeds/wlan-open/-/blob/win.wlan_host_opensource.3.0.r24/patches/ath11k/207-ath11k-Add-support-for-dynamic-vlan.patch # [1]
Link: https://patch.msgid.link/20250124113331.93476-1-nico.escande@gmail.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 4e11b7b61b823..46a55554c19c8 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -384,6 +384,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_link_vif *arvif,
 		add_htt_metadata = true;
 		msdu_ext_desc = true;
 		ti.flags0 |= u32_encode_bits(1, HAL_TCL_DATA_CMD_INFO2_TO_FW);
+		ti.meta_data_flags |= HTT_TCL_META_DATA_VALID_HTT;
 		ti.encap_type = HAL_TCL_ENCAP_TYPE_RAW;
 		ti.encrypt_type = HAL_ENCRYPT_TYPE_OPEN;
 	}

From 68aaa637162787dc3374080efe03366f70b344f1 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 20 Feb 2025 09:17:17 -0500
Subject: [PATCH 0869/2753] bcachefs: print op->nonce on data update
 inconsistency

"nonce inconstancy" is popping up again, causing us to go emergency
read-only.

This one looks less serious, i.e. specific to the encryption path and
not indicative of a data corruption bug. But we'll need more info to
track it down.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/data_update.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/data_update.c b/fs/bcachefs/data_update.c
index 337494facac64..642fbc60ecab1 100644
--- a/fs/bcachefs/data_update.c
+++ b/fs/bcachefs/data_update.c
@@ -340,6 +340,7 @@ static int __bch2_data_update_index_update(struct btree_trans *trans,
 			struct printbuf buf = PRINTBUF;
 
 			prt_str(&buf, "about to insert invalid key in data update path");
+			prt_printf(&buf, "\nop.nonce: %u", m->op.nonce);
 			prt_str(&buf, "\nold: ");
 			bch2_bkey_val_to_text(&buf, c, old);
 			prt_str(&buf, "\nk:   ");

From c522093b02835f2e897b83e9764e7919edac5d08 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Thu, 20 Feb 2025 18:56:08 +0800
Subject: [PATCH 0870/2753] bcachefs: Fix memmove when move keys down

The fix alone doesn't fix [1], but should be applied before debugging
that.

[1] https://syzkaller.appspot.com/bug?extid=38a0cbd267eff2d286ff

Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index e371e60e3133e..dece27d9db04e 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -996,7 +996,7 @@ static int validate_bset_keys(struct bch_fs *c, struct btree *b,
 		}
 got_good_key:
 		le16_add_cpu(&i->u64s, -next_good_key);
-		memmove_u64s_down(k, bkey_p_next(k), (u64 *) vstruct_end(i) - (u64 *) k);
+		memmove_u64s_down(k, (u64 *) k + next_good_key, (u64 *) vstruct_end(i) - (u64 *) k);
 		set_btree_node_need_rewrite(b);
 	}
 fsck_err:

From 4adf74971018ad9375aefabee2c702e367930fea Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Sat, 15 Feb 2025 15:04:50 +0900
Subject: [PATCH 0871/2753] tun: Pad virtio headers

tun simply advances iov_iter when it needs to pad virtio header,
which leaves the garbage in the buffer as is. This will become
especially problematic when tun starts to allow enabling the hash
reporting feature; even if the feature is enabled, the packet may lack a
hash value and may contain a hole in the virtio header because the
packet arrived before the feature gets enabled or does not contain the
header fields to be hashed. If the hole is not filled with zero, it is
impossible to tell if the packet lacks a hash value.

In theory, a user of tun can fill the buffer with zero before calling
read() to avoid such a problem, but leaving the garbage in the buffer is
awkward anyway so replace advancing the iterator with writing zeros.

A user might have initialized the buffer to some non-zero value,
expecting tun to skip writing it. As this was never a documented
feature, this seems unlikely.

The overhead of filling the hole in the header is negligible when the
header size is specified according to the specification as doing so will
not make another cache line dirty under a reasonable assumption. Below
is a proof of this statement:

The first 10 bytes of the header is always written and tun also writes
the packet itself immediately after the packet unless the packet is
empty. This makes a hole between these writes whose size is: sz - 10
where sz is the specified header size.

Therefore, we will never make another cache line dirty when:
sz < L1_CACHE_BYTES + 10
where L1_CACHE_BYTES is the cache line size. Assuming
L1_CACHE_BYTES >= 16, this inequation holds when: sz < 26.

sz <= 20 according to the current specification so we even have a
margin of 5 bytes in case that the header size grows in a future version
of the specification.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Link: https://patch.msgid.link/20250215-buffers-v2-1-1fbc6aaf8ad6@daynix.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun_vnet.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index fd7411c4447ff..58b9ac7a5fc40 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -143,7 +143,8 @@ static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
 	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
 		return -EFAULT;
 
-	iov_iter_advance(iter, sz - sizeof(*hdr));
+	if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr))
+		return -EFAULT;
 
 	return 0;
 }

From 24e82b7c045ba5afde5bd81f691b7a72283de35e Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:29 +0800
Subject: [PATCH 0872/2753] bpf: Add networking timestamping support to
 bpf_get/setsockopt()

The new SK_BPF_CB_FLAGS and new SK_BPF_CB_TX_TIMESTAMPING are
added to bpf_get/setsockopt. The later patches will implement the
BPF networking timestamping. The BPF program will use
bpf_setsockopt(SK_BPF_CB_FLAGS, SK_BPF_CB_TX_TIMESTAMPING) to
enable the BPF networking timestamping on a socket.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-2-kerneljasonxing@gmail.com
---
 include/net/sock.h             |  3 +++
 include/uapi/linux/bpf.h       |  7 +++++++
 net/core/filter.c              | 23 +++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  7 +++++++
 4 files changed, 40 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index 60ebf3c7b229e..a95eedacae76c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -303,6 +303,7 @@ struct sk_filter;
   *	@sk_stamp: time stamp of last packet received
   *	@sk_stamp_seq: lock for accessing sk_stamp on 32 bit architectures only
   *	@sk_tsflags: SO_TIMESTAMPING flags
+  *	@sk_bpf_cb_flags: used in bpf_setsockopt()
   *	@sk_use_task_frag: allow sk_page_frag() to use current->task_frag.
   *			   Sockets that can be used under memory reclaim should
   *			   set this to false.
@@ -525,6 +526,8 @@ struct sock {
 	u8			sk_txtime_deadline_mode : 1,
 				sk_txtime_report_errors : 1,
 				sk_txtime_unused : 6;
+#define SK_BPF_CB_FLAG_TEST(SK, FLAG) ((SK)->sk_bpf_cb_flags & (FLAG))
+	u8			sk_bpf_cb_flags;
 
 	void			*sk_user_data;
 #ifdef CONFIG_SECURITY
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 2acf9b3363717..4e0632848440b 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -6913,6 +6913,12 @@ enum {
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
+enum {
+	SK_BPF_CB_TX_TIMESTAMPING	= 1<<0,
+	SK_BPF_CB_MASK			= (SK_BPF_CB_TX_TIMESTAMPING - 1) |
+					   SK_BPF_CB_TX_TIMESTAMPING
+};
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -7091,6 +7097,7 @@ enum {
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
+	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index ffec7b4357f9f..5b7e44dfc037c 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5222,6 +5222,25 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
+static int sk_bpf_set_get_cb_flags(struct sock *sk, char *optval, bool getopt)
+{
+	u32 sk_bpf_cb_flags;
+
+	if (getopt) {
+		*(u32 *)optval = sk->sk_bpf_cb_flags;
+		return 0;
+	}
+
+	sk_bpf_cb_flags = *(u32 *)optval;
+
+	if (sk_bpf_cb_flags & ~SK_BPF_CB_MASK)
+		return -EINVAL;
+
+	sk->sk_bpf_cb_flags = sk_bpf_cb_flags;
+
+	return 0;
+}
+
 static int sol_socket_sockopt(struct sock *sk, int optname,
 			      char *optval, int *optlen,
 			      bool getopt)
@@ -5238,6 +5257,7 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 	case SO_MAX_PACING_RATE:
 	case SO_BINDTOIFINDEX:
 	case SO_TXREHASH:
+	case SK_BPF_CB_FLAGS:
 		if (*optlen != sizeof(int))
 			return -EINVAL;
 		break;
@@ -5247,6 +5267,9 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 		return -EINVAL;
 	}
 
+	if (optname == SK_BPF_CB_FLAGS)
+		return sk_bpf_set_get_cb_flags(sk, optval, getopt);
+
 	if (getopt) {
 		if (optname == SO_BINDTODEVICE)
 			return -EINVAL;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 2acf9b3363717..4e0632848440b 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -6913,6 +6913,12 @@ enum {
 	BPF_SOCK_OPS_ALL_CB_FLAGS       = 0x7F,
 };
 
+enum {
+	SK_BPF_CB_TX_TIMESTAMPING	= 1<<0,
+	SK_BPF_CB_MASK			= (SK_BPF_CB_TX_TIMESTAMPING - 1) |
+					   SK_BPF_CB_TX_TIMESTAMPING
+};
+
 /* List of known BPF sock_ops operators.
  * New entries can only be added at the end
  */
@@ -7091,6 +7097,7 @@ enum {
 	TCP_BPF_SYN_IP		= 1006, /* Copy the IP[46] and TCP header */
 	TCP_BPF_SYN_MAC         = 1007, /* Copy the MAC, IP[46], and TCP header */
 	TCP_BPF_SOCK_OPS_CB_FLAGS = 1008, /* Get or Set TCP sock ops flags */
+	SK_BPF_CB_FLAGS		= 1009, /* Get or set sock ops flags in socket */
 };
 
 enum {

From df600f3b1d7963e2203ebf0987f564946a2647f1 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:30 +0800
Subject: [PATCH 0873/2753] bpf: Prepare the sock_ops ctx and call bpf prog for
 TX timestamping

This patch introduces a new bpf_skops_tx_timestamping() function
that prepares the "struct bpf_sock_ops" ctx and then executes the
sockops BPF program.

The subsequent patch will utilize bpf_skops_tx_timestamping() at
the existing TX timestamping kernel callbacks (__sk_tstamp_tx
specifically) to call the sockops BPF program. Later, four callback
points to report information to user space based on this patch will
be introduced.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250220072940.99994-3-kerneljasonxing@gmail.com
---
 include/net/sock.h |  7 +++++++
 net/core/sock.c    | 14 ++++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index a95eedacae76c..2f6b55c59c165 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2924,6 +2924,13 @@ int sock_set_timestamping(struct sock *sk, int optname,
 			  struct so_timestamping timestamping);
 
 void sock_enable_timestamps(struct sock *sk);
+#if defined(CONFIG_CGROUP_BPF)
+void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op);
+#else
+static inline void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op)
+{
+}
+#endif
 void sock_no_linger(struct sock *sk);
 void sock_set_keepalive(struct sock *sk);
 void sock_set_priority(struct sock *sk, u32 priority);
diff --git a/net/core/sock.c b/net/core/sock.c
index a197f0a0b8788..ba653c6a12292 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -949,6 +949,20 @@ int sock_set_timestamping(struct sock *sk, int optname,
 	return 0;
 }
 
+#if defined(CONFIG_CGROUP_BPF)
+void bpf_skops_tx_timestamping(struct sock *sk, struct sk_buff *skb, int op)
+{
+	struct bpf_sock_ops_kern sock_ops;
+
+	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
+	sock_ops.op = op;
+	sock_ops.is_fullsock = 1;
+	sock_ops.sk = sk;
+	bpf_skops_init_skb(&sock_ops, skb, 0);
+	__cgroup_bpf_run_filter_sock_ops(sk, &sock_ops, CGROUP_SOCK_OPS);
+}
+#endif
+
 void sock_set_keepalive(struct sock *sk)
 {
 	lock_sock(sk);

From fd93eaffb3f977b23bc0a48d4c8616e654fcf133 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:31 +0800
Subject: [PATCH 0874/2753] bpf: Prevent unsafe access to the sock fields in
 the BPF timestamping callback

The subsequent patch will implement BPF TX timestamping. It will
call the sockops BPF program without holding the sock lock.

This breaks the current assumption that all sock ops programs will
hold the sock lock. The sock's fields of the uapi's bpf_sock_ops
requires this assumption.

To address this, a new "u8 is_locked_tcp_sock;" field is added. This
patch sets it in the current sock_ops callbacks. The "is_fullsock"
test is then replaced by the "is_locked_tcp_sock" test during
sock_ops_convert_ctx_access().

The new TX timestamping callbacks added in the subsequent patch will
not have this set. This will prevent unsafe access from the new
timestamping callbacks.

Potentially, we could allow read-only access. However, this would
require identifying which callback is read-safe-only and also requires
additional BPF instruction rewrites in the covert_ctx. Since the BPF
program can always read everything from a socket (e.g., by using
bpf_core_cast), this patch keeps it simple and disables all read
and write access to any socket fields through the bpf_sock_ops
UAPI from the new TX timestamping callback.

Moreover, note that some of the fields in bpf_sock_ops are specific
to tcp_sock, and sock_ops currently only supports tcp_sock. In
the future, UDP timestamping will be added, which will also break
this assumption. The same idea used in this patch will be reused.
Considering that the current sock_ops only supports tcp_sock, the
variable is named is_locked_"tcp"_sock.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250220072940.99994-4-kerneljasonxing@gmail.com
---
 include/linux/filter.h | 1 +
 include/net/tcp.h      | 1 +
 net/core/filter.c      | 8 ++++----
 net/ipv4/tcp_input.c   | 2 ++
 net/ipv4/tcp_output.c  | 2 ++
 5 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index a3ea462815957..d36d5d5180b11 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1508,6 +1508,7 @@ struct bpf_sock_ops_kern {
 	void	*skb_data_end;
 	u8	op;
 	u8	is_fullsock;
+	u8	is_locked_tcp_sock;
 	u8	remaining_opt_len;
 	u64	temp;			/* temp and everything after is not
 					 * initialized to 0 before calling
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7fd2d7fa4532b..94ea09faedf45 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2657,6 +2657,7 @@ static inline int tcp_call_bpf(struct sock *sk, int op, u32 nargs, u32 *args)
 	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
 	if (sk_fullsock(sk)) {
 		sock_ops.is_fullsock = 1;
+		sock_ops.is_locked_tcp_sock = 1;
 		sock_owned_by_me(sk);
 	}
 
diff --git a/net/core/filter.c b/net/core/filter.c
index 5b7e44dfc037c..7a20ddae76676 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -10382,10 +10382,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 		}							      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
+						is_locked_tcp_sock),	      \
 				      fullsock_reg, si->src_reg,	      \
 				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
+					       is_locked_tcp_sock));	      \
 		*insn++ = BPF_JMP_IMM(BPF_JEQ, fullsock_reg, 0, jmp);	      \
 		if (si->dst_reg == si->src_reg)				      \
 			*insn++ = BPF_LDX_MEM(BPF_DW, reg, si->src_reg,	      \
@@ -10470,10 +10470,10 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type,
 					       temp));			      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern,     \
-						is_fullsock),		      \
+						is_locked_tcp_sock),	      \
 				      reg, si->dst_reg,			      \
 				      offsetof(struct bpf_sock_ops_kern,      \
-					       is_fullsock));		      \
+					       is_locked_tcp_sock));	      \
 		*insn++ = BPF_JMP_IMM(BPF_JEQ, reg, 0, 2);		      \
 		*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(			      \
 						struct bpf_sock_ops_kern, sk),\
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4686783b70def..4a9e70e23ef83 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -169,6 +169,7 @@ static void bpf_skops_parse_hdr(struct sock *sk, struct sk_buff *skb)
 	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
 	sock_ops.op = BPF_SOCK_OPS_PARSE_HDR_OPT_CB;
 	sock_ops.is_fullsock = 1;
+	sock_ops.is_locked_tcp_sock = 1;
 	sock_ops.sk = sk;
 	bpf_skops_init_skb(&sock_ops, skb, tcp_hdrlen(skb));
 
@@ -185,6 +186,7 @@ static void bpf_skops_established(struct sock *sk, int bpf_op,
 	memset(&sock_ops, 0, offsetof(struct bpf_sock_ops_kern, temp));
 	sock_ops.op = bpf_op;
 	sock_ops.is_fullsock = 1;
+	sock_ops.is_locked_tcp_sock = 1;
 	sock_ops.sk = sk;
 	/* sk with TCP_REPAIR_ON does not have skb in tcp_finish_connect */
 	if (skb)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 464232a0d6379..a796cf451e55a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -525,6 +525,7 @@ static void bpf_skops_hdr_opt_len(struct sock *sk, struct sk_buff *skb,
 		sock_owned_by_me(sk);
 
 		sock_ops.is_fullsock = 1;
+		sock_ops.is_locked_tcp_sock = 1;
 		sock_ops.sk = sk;
 	}
 
@@ -570,6 +571,7 @@ static void bpf_skops_write_hdr_opt(struct sock *sk, struct sk_buff *skb,
 		sock_owned_by_me(sk);
 
 		sock_ops.is_fullsock = 1;
+		sock_ops.is_locked_tcp_sock = 1;
 		sock_ops.sk = sk;
 	}
 

From 2958624b25305142e24203165ff65409ba9dd9d7 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:32 +0800
Subject: [PATCH 0875/2753] bpf: Disable unsafe helpers in TX timestamping
 callbacks

New TX timestamping sock_ops callbacks will be added in the
subsequent patch. Some of the existing BPF helpers will not
be safe to be used in the TX timestamping callbacks.

The bpf_sock_ops_setsockopt, bpf_sock_ops_getsockopt, and
bpf_sock_ops_cb_flags_set require owning the sock lock. TX
timestamping callbacks will not own the lock.

The bpf_sock_ops_load_hdr_opt needs the skb->data pointing
to the TCP header. This will not be true in the TX timestamping
callbacks.

At the beginning of these helpers, this patch checks the
bpf_sock->op to ensure these helpers are used by the existing
sock_ops callbacks only.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250220072940.99994-5-kerneljasonxing@gmail.com
---
 net/core/filter.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 7a20ddae76676..90a8fbc2e0967 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5524,6 +5524,11 @@ static int __bpf_setsockopt(struct sock *sk, int level, int optname,
 	return -EINVAL;
 }
 
+static bool is_locked_tcp_sock_ops(struct bpf_sock_ops_kern *bpf_sock)
+{
+	return bpf_sock->op <= BPF_SOCK_OPS_WRITE_HDR_OPT_CB;
+}
+
 static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 			   char *optval, int optlen)
 {
@@ -5674,6 +5679,9 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = {
 BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen);
 }
 
@@ -5759,6 +5767,9 @@ static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock,
 BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock,
 	   int, level, int, optname, char *, optval, int, optlen)
 {
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP &&
 	    optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) {
 		int ret, copy_len = 0;
@@ -5801,6 +5812,9 @@ BPF_CALL_2(bpf_sock_ops_cb_flags_set, struct bpf_sock_ops_kern *, bpf_sock,
 	struct sock *sk = bpf_sock->sk;
 	int val = argval & BPF_SOCK_OPS_ALL_CB_FLAGS;
 
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	if (!IS_ENABLED(CONFIG_INET) || !sk_fullsock(sk))
 		return -EINVAL;
 
@@ -7610,6 +7624,9 @@ BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock,
 	u8 search_kind, search_len, copy_len, magic_len;
 	int ret;
 
+	if (!is_locked_tcp_sock_ops(bpf_sock))
+		return -EOPNOTSUPP;
+
 	/* 2 byte is the minimal option len except TCPOPT_NOP and
 	 * TCPOPT_EOL which are useless for the bpf prog to learn
 	 * and this helper disallow loading them also.

From aa290f93a4af662b8d2d9e9df65798f9f24cecf3 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:33 +0800
Subject: [PATCH 0876/2753] net-timestamp: Prepare for isolating two modes of
 SO_TIMESTAMPING

No functional changes here. Only add test to see if the orig_skb
matches the usage of application SO_TIMESTAMPING.

In this series, bpf timestamping and previous socket timestamping
are implemented in the same function __skb_tstamp_tx(). To test
the socket enables socket timestamping feature, this function
skb_tstamp_tx_report_so_timestamping() is added.

In the next patch, another check for bpf timestamping feature
will be introduced just like the above report function, namely,
skb_tstamp_tx_report_bpf_timestamping(). Then users will be able
to know the socket enables either or both of features.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-6-kerneljasonxing@gmail.com
---
 net/core/skbuff.c | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a441613a1e6c1..341a3290e8982 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5539,6 +5539,23 @@ void skb_complete_tx_timestamp(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp);
 
+static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
+						 struct skb_shared_hwtstamps *hwtstamps,
+						 int tstype)
+{
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
+	case SCM_TSTAMP_SND:
+		return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP :
+						    SKBTX_SW_TSTAMP);
+	case SCM_TSTAMP_ACK:
+		return TCP_SKB_CB(skb)->txstamp_ack;
+	}
+
+	return false;
+}
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     const struct sk_buff *ack_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
@@ -5551,6 +5568,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!sk)
 		return;
 
+	if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
+		return;
+
 	tsflags = READ_ONCE(sk->sk_tsflags);
 	if (!hwtstamps && !(tsflags & SOF_TIMESTAMPING_OPT_TX_SWHW) &&
 	    skb_shinfo(orig_skb)->tx_flags & SKBTX_IN_PROGRESS)

From 6b98ec7e882af1c3088a88757e2226d06c8514f9 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:34 +0800
Subject: [PATCH 0877/2753] bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback

Support SCM_TSTAMP_SCHED case for bpf timestamping.

Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SCHED_CB. This
callback will occur at the same timestamping point as the user
space's SCM_TSTAMP_SCHED. The BPF program can use it to get the
same SCM_TSTAMP_SCHED timestamp without modifying the user-space
application.

A new SKBTX_BPF flag is added to mark skb_shinfo(skb)->tx_flags,
ensuring that the new BPF timestamping and the current user
space's SO_TIMESTAMPING do not interfere with each other.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-7-kerneljasonxing@gmail.com
---
 include/linux/skbuff.h         |  6 +++++-
 include/uapi/linux/bpf.h       |  5 +++++
 net/core/dev.c                 |  3 ++-
 net/core/skbuff.c              | 20 ++++++++++++++++++++
 tools/include/uapi/linux/bpf.h |  5 +++++
 5 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index bb2b751d274ac..52f6e033e704e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -489,10 +489,14 @@ enum {
 
 	/* generate software time stamp when entering packet scheduling */
 	SKBTX_SCHED_TSTAMP = 1 << 6,
+
+	/* used for bpf extension when a bpf program is loaded */
+	SKBTX_BPF = 1 << 7,
 };
 
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
-				 SKBTX_SCHED_TSTAMP)
+				 SKBTX_SCHED_TSTAMP | \
+				 SKBTX_BPF)
 #define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \
 				 SKBTX_HW_TSTAMP_USE_CYCLES | \
 				 SKBTX_ANY_SW_TSTAMP)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4e0632848440b..bb62fe25b2d02 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7031,6 +7031,11 @@ enum {
 					 * by the kernel or the
 					 * earlier bpf-progs.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SCHED_CB,	/* Called when skb is passing
+					 * through dev layer when
+					 * SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/dev.c b/net/core/dev.c
index d5ab9a4b318ea..436f2bdfb2d53 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4501,7 +4501,8 @@ int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 	skb_reset_mac_header(skb);
 	skb_assert_len(skb);
 
-	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP))
+	if (unlikely(skb_shinfo(skb)->tx_flags &
+		     (SKBTX_SCHED_TSTAMP | SKBTX_BPF)))
 		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SCHED);
 
 	/* Disable soft irqs for various locks below. Also
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 341a3290e8982..3206f7708974f 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5556,6 +5556,23 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 	return false;
 }
 
+static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
+						  struct sock *sk,
+						  int tstype)
+{
+	int op;
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
+		break;
+	default:
+		return;
+	}
+
+	bpf_skops_tx_timestamping(sk, skb, op);
+}
+
 void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		     const struct sk_buff *ack_skb,
 		     struct skb_shared_hwtstamps *hwtstamps,
@@ -5568,6 +5585,9 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 	if (!sk)
 		return;
 
+	if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF)
+		skb_tstamp_tx_report_bpf_timestamping(orig_skb, sk, tstype);
+
 	if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
 		return;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4e0632848440b..bb62fe25b2d02 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7031,6 +7031,11 @@ enum {
 					 * by the kernel or the
 					 * earlier bpf-progs.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SCHED_CB,	/* Called when skb is passing
+					 * through dev layer when
+					 * SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect

From ecebb17ad818bc043e558c278a6c56d5bbaebacc Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:35 +0800
Subject: [PATCH 0878/2753] bpf: Add BPF_SOCK_OPS_TSTAMP_SND_SW_CB callback

Support sw SCM_TSTAMP_SND case for bpf timestamping.

Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SND_SW_CB. This
callback will occur at the same timestamping point as the user
space's software SCM_TSTAMP_SND. The BPF program can use it to
get the same SCM_TSTAMP_SND timestamp without modifying the
user-space application.

Based on this patch, BPF program will get the software
timestamp when the driver is ready to send the skb. In the
sebsequent patch, the hardware timestamp will be supported.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-8-kerneljasonxing@gmail.com
---
 include/linux/skbuff.h         | 2 +-
 include/uapi/linux/bpf.h       | 4 ++++
 net/core/skbuff.c              | 9 ++++++++-
 tools/include/uapi/linux/bpf.h | 4 ++++
 4 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 52f6e033e704e..76582500c5eae 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4568,7 +4568,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb,
 static inline void skb_tx_timestamp(struct sk_buff *skb)
 {
 	skb_clone_tx_timestamp(skb);
-	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
+	if (skb_shinfo(skb)->tx_flags & (SKBTX_SW_TSTAMP | SKBTX_BPF))
 		skb_tstamp_tx(skb, NULL);
 }
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index bb62fe25b2d02..abe8d6c30daec 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7036,6 +7036,10 @@ enum {
 					 * SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SND_SW_CB,	/* Called when skb is about to send
+					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 3206f7708974f..308db7dae1ab1 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5557,6 +5557,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 }
 
 static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
+						  struct skb_shared_hwtstamps *hwtstamps,
 						  struct sock *sk,
 						  int tstype)
 {
@@ -5566,6 +5567,11 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
 	case SCM_TSTAMP_SCHED:
 		op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
 		break;
+	case SCM_TSTAMP_SND:
+		if (hwtstamps)
+			return;
+		op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
+		break;
 	default:
 		return;
 	}
@@ -5586,7 +5592,8 @@ void __skb_tstamp_tx(struct sk_buff *orig_skb,
 		return;
 
 	if (skb_shinfo(orig_skb)->tx_flags & SKBTX_BPF)
-		skb_tstamp_tx_report_bpf_timestamping(orig_skb, sk, tstype);
+		skb_tstamp_tx_report_bpf_timestamping(orig_skb, hwtstamps,
+						      sk, tstype);
 
 	if (!skb_tstamp_tx_report_so_timestamping(orig_skb, hwtstamps, tstype))
 		return;
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index bb62fe25b2d02..abe8d6c30daec 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7036,6 +7036,10 @@ enum {
 					 * SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SND_SW_CB,	/* Called when skb is about to send
+					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect

From 2deaf7f42b8c551e84da20483ca2d4a65c3623b3 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:36 +0800
Subject: [PATCH 0879/2753] bpf: Add BPF_SOCK_OPS_TSTAMP_SND_HW_CB callback

Support hw SCM_TSTAMP_SND case for bpf timestamping.

Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_SND_HW_CB. This
callback will occur at the same timestamping point as the user
space's hardware SCM_TSTAMP_SND. The BPF program can use it to
get the same SCM_TSTAMP_SND timestamp without modifying the
user-space application.

To avoid increasing the code complexity, replace SKBTX_HW_TSTAMP
with SKBTX_HW_TSTAMP_NOBPF instead of changing numerous callers
from driver side using SKBTX_HW_TSTAMP. The new definition of
SKBTX_HW_TSTAMP means the combination tests of socket timestamping
and bpf timestamping. After this patch, drivers can work under the
bpf timestamping.

Considering some drivers don't assign the skb with hardware
timestamp, this patch does the assignment and then BPF program
can acquire the hwstamp from skb directly.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-9-kerneljasonxing@gmail.com
---
 include/linux/skbuff.h         |  4 +++-
 include/uapi/linux/bpf.h       |  4 ++++
 net/core/skbuff.c              | 11 +++++++----
 net/dsa/user.c                 |  2 +-
 net/socket.c                   |  2 +-
 tools/include/uapi/linux/bpf.h |  4 ++++
 6 files changed, 20 insertions(+), 7 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 76582500c5eae..0b4f1889500d2 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -470,7 +470,7 @@ struct skb_shared_hwtstamps {
 /* Definitions for tx_flags in struct skb_shared_info */
 enum {
 	/* generate hardware time stamp */
-	SKBTX_HW_TSTAMP = 1 << 0,
+	SKBTX_HW_TSTAMP_NOBPF = 1 << 0,
 
 	/* generate software time stamp when queueing packet to NIC */
 	SKBTX_SW_TSTAMP = 1 << 1,
@@ -494,6 +494,8 @@ enum {
 	SKBTX_BPF = 1 << 7,
 };
 
+#define SKBTX_HW_TSTAMP		(SKBTX_HW_TSTAMP_NOBPF | SKBTX_BPF)
+
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
 				 SKBTX_SCHED_TSTAMP | \
 				 SKBTX_BPF)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index abe8d6c30daec..72045c2423963 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7040,6 +7040,10 @@ enum {
 					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SND_HW_CB,	/* Called in hardware phase when
+					 * SK_BPF_CB_TX_TIMESTAMPING feature
+					 * is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 308db7dae1ab1..77b8866f94c53 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5547,7 +5547,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 	case SCM_TSTAMP_SCHED:
 		return skb_shinfo(skb)->tx_flags & SKBTX_SCHED_TSTAMP;
 	case SCM_TSTAMP_SND:
-		return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP :
+		return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
 						    SKBTX_SW_TSTAMP);
 	case SCM_TSTAMP_ACK:
 		return TCP_SKB_CB(skb)->txstamp_ack;
@@ -5568,9 +5568,12 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
 		op = BPF_SOCK_OPS_TSTAMP_SCHED_CB;
 		break;
 	case SCM_TSTAMP_SND:
-		if (hwtstamps)
-			return;
-		op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
+		if (hwtstamps) {
+			op = BPF_SOCK_OPS_TSTAMP_SND_HW_CB;
+			*skb_hwtstamps(skb) = *hwtstamps;
+		} else {
+			op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
+		}
 		break;
 	default:
 		return;
diff --git a/net/dsa/user.c b/net/dsa/user.c
index 2296a4ead0203..804dc7dac4f2f 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -897,7 +897,7 @@ static void dsa_skb_tx_timestamp(struct dsa_user_priv *p,
 {
 	struct dsa_switch *ds = p->dp->ds;
 
-	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+	if (!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_NOBPF))
 		return;
 
 	if (!ds->ops->port_txtstamp)
diff --git a/net/socket.c b/net/socket.c
index 28bae5a942341..0545e9ea70581 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -681,7 +681,7 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags)
 	u8 flags = *tx_flags;
 
 	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {
-		flags |= SKBTX_HW_TSTAMP;
+		flags |= SKBTX_HW_TSTAMP_NOBPF;
 
 		/* PTP hardware clocks can provide a free running cycle counter
 		 * as a time base for virtual clocks. Tell driver to use the
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index abe8d6c30daec..72045c2423963 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7040,6 +7040,10 @@ enum {
 					 * to the nic when SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SND_HW_CB,	/* Called in hardware phase when
+					 * SK_BPF_CB_TX_TIMESTAMPING feature
+					 * is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect

From b3b81e6b009dd8f85cd3b9c65eb492249c2649a8 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:37 +0800
Subject: [PATCH 0880/2753] bpf: Add BPF_SOCK_OPS_TSTAMP_ACK_CB callback

Support the ACK case for bpf timestamping.

Add a new sock_ops callback, BPF_SOCK_OPS_TSTAMP_ACK_CB. This
callback will occur at the same timestamping point as the user
space's SCM_TSTAMP_ACK. The BPF program can use it to get the
same SCM_TSTAMP_ACK timestamp without modifying the user-space
application.

This patch extends txstamp_ack to two bits: 1 stands for
SO_TIMESTAMPING mode, 2 bpf extension.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-10-kerneljasonxing@gmail.com
---
 include/net/tcp.h              | 6 ++++--
 include/uapi/linux/bpf.h       | 5 +++++
 net/core/skbuff.c              | 5 ++++-
 net/ipv4/tcp.c                 | 2 +-
 tools/include/uapi/linux/bpf.h | 5 +++++
 5 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 94ea09faedf45..ae6c95b01012e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -964,10 +964,12 @@ struct tcp_skb_cb {
 
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
-	__u8		txstamp_ack:1,	/* Record TX timestamp for ack? */
+#define TSTAMP_ACK_SK	0x1
+#define TSTAMP_ACK_BPF	0x2
+	__u8		txstamp_ack:2,	/* Record TX timestamp for ack? */
 			eor:1,		/* Is skb MSG_EOR marked? */
 			has_rxtstamp:1,	/* SKB has a RX timestamp	*/
-			unused:5;
+			unused:4;
 	__u32		ack_seq;	/* Sequence number ACK'd	*/
 	union {
 		struct {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 72045c2423963..cc10104f34a0a 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7044,6 +7044,11 @@ enum {
 					 * SK_BPF_CB_TX_TIMESTAMPING feature
 					 * is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_ACK_CB,	/* Called when all the skbs in the
+					 * same sendmsg call are acked
+					 * when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 77b8866f94c53..dd33c12f00ca2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5550,7 +5550,7 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 		return skb_shinfo(skb)->tx_flags & (hwtstamps ? SKBTX_HW_TSTAMP_NOBPF :
 						    SKBTX_SW_TSTAMP);
 	case SCM_TSTAMP_ACK:
-		return TCP_SKB_CB(skb)->txstamp_ack;
+		return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK;
 	}
 
 	return false;
@@ -5575,6 +5575,9 @@ static void skb_tstamp_tx_report_bpf_timestamping(struct sk_buff *skb,
 			op = BPF_SOCK_OPS_TSTAMP_SND_SW_CB;
 		}
 		break;
+	case SCM_TSTAMP_ACK:
+		op = BPF_SOCK_OPS_TSTAMP_ACK_CB;
+		break;
 	default:
 		return;
 	}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 992d5c9b2487c..2171e2f045bbf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -492,7 +492,7 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
 
 		sock_tx_timestamp(sk, sockc, &shinfo->tx_flags);
 		if (tsflags & SOF_TIMESTAMPING_TX_ACK)
-			tcb->txstamp_ack = 1;
+			tcb->txstamp_ack |= TSTAMP_ACK_SK;
 		if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
 			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
 	}
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 72045c2423963..cc10104f34a0a 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7044,6 +7044,11 @@ enum {
 					 * SK_BPF_CB_TX_TIMESTAMPING feature
 					 * is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_ACK_CB,	/* Called when all the skbs in the
+					 * same sendmsg call are acked
+					 * when SK_BPF_CB_TX_TIMESTAMPING
+					 * feature is on.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect

From c9525d240c8117de35171ae705058ddf9667be27 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:38 +0800
Subject: [PATCH 0881/2753] bpf: Add BPF_SOCK_OPS_TSTAMP_SENDMSG_CB callback

This patch introduces a new callback in tcp_tx_timestamp() to correlate
tcp_sendmsg timestamp with timestamps from other tx timestamping
callbacks (e.g., SND/SW/ACK).

Without this patch, BPF program wouldn't know which timestamps belong
to which flow because of no socket lock protection. This new callback
is inserted in tcp_tx_timestamp() to address this issue because
tcp_tx_timestamp() still owns the same socket lock with
tcp_sendmsg_locked() in the meanwhile tcp_tx_timestamp() initializes
the timestamping related fields for the skb, especially tskey. The
tskey is the bridge to do the correlation.

For TCP, BPF program hooks the beginning of tcp_sendmsg_locked() and
then stores the sendmsg timestamp at the bpf_sk_storage, correlating
this timestamp with its tskey that are later used in other sending
timestamping callbacks.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-11-kerneljasonxing@gmail.com
---
 include/uapi/linux/bpf.h       | 5 +++++
 net/ipv4/tcp.c                 | 4 ++++
 tools/include/uapi/linux/bpf.h | 5 +++++
 3 files changed, 14 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index cc10104f34a0a..defa5bb881f42 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -7049,6 +7049,11 @@ enum {
 					 * when SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SENDMSG_CB,	/* Called when every sendmsg syscall
+					 * is triggered. It's used to correlate
+					 * sendmsg timestamp with corresponding
+					 * tskey.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2171e2f045bbf..298d1da05bee6 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -496,6 +496,10 @@ static void tcp_tx_timestamp(struct sock *sk, struct sockcm_cookie *sockc)
 		if (tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK)
 			shinfo->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
 	}
+
+	if (cgroup_bpf_enabled(CGROUP_SOCK_OPS) &&
+	    SK_BPF_CB_FLAG_TEST(sk, SK_BPF_CB_TX_TIMESTAMPING) && skb)
+		bpf_skops_tx_timestamping(sk, skb, BPF_SOCK_OPS_TSTAMP_SENDMSG_CB);
 }
 
 static bool tcp_stream_is_readable(struct sock *sk, int target)
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index cc10104f34a0a..defa5bb881f42 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -7049,6 +7049,11 @@ enum {
 					 * when SK_BPF_CB_TX_TIMESTAMPING
 					 * feature is on.
 					 */
+	BPF_SOCK_OPS_TSTAMP_SENDMSG_CB,	/* Called when every sendmsg syscall
+					 * is triggered. It's used to correlate
+					 * sendmsg timestamp with corresponding
+					 * tskey.
+					 */
 };
 
 /* List of TCP states. There is a build check in net/ipv4/tcp.c to detect

From 59422464266f8baa091edcb3779f0955a21abf00 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:39 +0800
Subject: [PATCH 0882/2753] bpf: Support selective sampling for bpf
 timestamping

Add the bpf_sock_ops_enable_tx_tstamp kfunc to allow BPF programs to
selectively enable TX timestamping on a skb during tcp_sendmsg().

For example, BPF program will limit tracking X numbers of packets
and then will stop there instead of tracing all the sendmsgs of
matched flow all along. It would be helpful for users who cannot
afford to calculate latencies from every sendmsg call probably
due to the performance or storage space consideration.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-12-kerneljasonxing@gmail.com
---
 kernel/bpf/btf.c  |  1 +
 net/core/filter.c | 31 ++++++++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 9de6acddd479b..551eedb87d580 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8524,6 +8524,7 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
 	case BPF_PROG_TYPE_CGROUP_SOCK_ADDR:
 	case BPF_PROG_TYPE_CGROUP_SOCKOPT:
 	case BPF_PROG_TYPE_CGROUP_SYSCTL:
+	case BPF_PROG_TYPE_SOCK_OPS:
 		return BTF_KFUNC_HOOK_CGROUP;
 	case BPF_PROG_TYPE_SCHED_ACT:
 		return BTF_KFUNC_HOOK_SCHED_ACT;
diff --git a/net/core/filter.c b/net/core/filter.c
index 90a8fbc2e0967..a0867c5b32b37 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -12103,6 +12103,25 @@ __bpf_kfunc int bpf_sk_assign_tcp_reqsk(struct __sk_buff *s, struct sock *sk,
 #endif
 }
 
+__bpf_kfunc int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops,
+					      u64 flags)
+{
+	struct sk_buff *skb;
+
+	if (skops->op != BPF_SOCK_OPS_TSTAMP_SENDMSG_CB)
+		return -EOPNOTSUPP;
+
+	if (flags)
+		return -EINVAL;
+
+	skb = skops->skb;
+	skb_shinfo(skb)->tx_flags |= SKBTX_BPF;
+	TCP_SKB_CB(skb)->txstamp_ack |= TSTAMP_ACK_BPF;
+	skb_shinfo(skb)->tskey = TCP_SKB_CB(skb)->seq + skb->len - 1;
+
+	return 0;
+}
+
 __bpf_kfunc_end_defs();
 
 int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
@@ -12136,6 +12155,10 @@ BTF_KFUNCS_START(bpf_kfunc_check_set_tcp_reqsk)
 BTF_ID_FLAGS(func, bpf_sk_assign_tcp_reqsk, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(bpf_kfunc_check_set_tcp_reqsk)
 
+BTF_KFUNCS_START(bpf_kfunc_check_set_sock_ops)
+BTF_ID_FLAGS(func, bpf_sock_ops_enable_tx_tstamp, KF_TRUSTED_ARGS)
+BTF_KFUNCS_END(bpf_kfunc_check_set_sock_ops)
+
 static const struct btf_kfunc_id_set bpf_kfunc_set_skb = {
 	.owner = THIS_MODULE,
 	.set = &bpf_kfunc_check_set_skb,
@@ -12156,6 +12179,11 @@ static const struct btf_kfunc_id_set bpf_kfunc_set_tcp_reqsk = {
 	.set = &bpf_kfunc_check_set_tcp_reqsk,
 };
 
+static const struct btf_kfunc_id_set bpf_kfunc_set_sock_ops = {
+	.owner = THIS_MODULE,
+	.set = &bpf_kfunc_check_set_sock_ops,
+};
+
 static int __init bpf_kfunc_init(void)
 {
 	int ret;
@@ -12174,7 +12202,8 @@ static int __init bpf_kfunc_init(void)
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &bpf_kfunc_set_xdp);
 	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_CGROUP_SOCK_ADDR,
 					       &bpf_kfunc_set_sock_addr);
-	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
+	ret = ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SCHED_CLS, &bpf_kfunc_set_tcp_reqsk);
+	return ret ?: register_btf_kfunc_id_set(BPF_PROG_TYPE_SOCK_OPS, &bpf_kfunc_set_sock_ops);
 }
 late_initcall(bpf_kfunc_init);
 

From f4924aec58dd9e14779f4bc11a6bf3a830a42a6c Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Thu, 20 Feb 2025 15:29:40 +0800
Subject: [PATCH 0883/2753] selftests/bpf: Add simple bpf tests in the tx path
 for timestamping feature

BPF program calculates a couple of latency deltas between each tx
timestamping callbacks. It can be used in the real world to diagnose
the kernel behaviour in the tx path.

Check the safety issues by accessing a few bpf calls in
bpf_test_access_bpf_calls() which are implemented in the patch 3 and 4.

Check if the bpf timestamping can co-exist with socket timestamping.

There remains a few realistic things[1][2] to highlight:
1. in general a packet may pass through multiple qdiscs. For instance
with bonding or tunnel virtual devices in the egress path.
2. packets may be resent, in which case an ACK might precede a repeat
SCHED and SND.
3. erroneous or malicious peers may also just never send an ACK.

[1]: https://lore.kernel.org/all/67a389af981b0_14e0832949d@willemb.c.googlers.com.notmuch/
[2]: https://lore.kernel.org/all/c329a0c1-239b-4ca1-91f2-cb30b8dd2f6a@linux.dev/

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250220072940.99994-13-kerneljasonxing@gmail.com
---
 .../bpf/prog_tests/net_timestamping.c         | 239 +++++++++++++++++
 .../selftests/bpf/progs/net_timestamping.c    | 248 ++++++++++++++++++
 2 files changed, 487 insertions(+)
 create mode 100644 tools/testing/selftests/bpf/prog_tests/net_timestamping.c
 create mode 100644 tools/testing/selftests/bpf/progs/net_timestamping.c

diff --git a/tools/testing/selftests/bpf/prog_tests/net_timestamping.c b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c
new file mode 100644
index 0000000000000..dbfd87499b6b5
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/net_timestamping.c
@@ -0,0 +1,239 @@
+#include <linux/net_tstamp.h>
+#include <sys/time.h>
+#include <linux/errqueue.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include "net_timestamping.skel.h"
+
+#define CG_NAME "/net-timestamping-test"
+#define NSEC_PER_SEC    1000000000LL
+
+static const char addr4_str[] = "127.0.0.1";
+static const char addr6_str[] = "::1";
+static struct net_timestamping *skel;
+static const int cfg_payload_len = 30;
+static struct timespec usr_ts;
+static u64 delay_tolerance_nsec = 10000000000; /* 10 seconds */
+int SK_TS_SCHED;
+int SK_TS_TXSW;
+int SK_TS_ACK;
+
+static int64_t timespec_to_ns64(struct timespec *ts)
+{
+	return ts->tv_sec * NSEC_PER_SEC + ts->tv_nsec;
+}
+
+static void validate_key(int tskey, int tstype)
+{
+	static int expected_tskey = -1;
+
+	if (tstype == SCM_TSTAMP_SCHED)
+		expected_tskey = cfg_payload_len - 1;
+
+	ASSERT_EQ(expected_tskey, tskey, "tskey mismatch");
+
+	expected_tskey = tskey;
+}
+
+static void validate_timestamp(struct timespec *cur, struct timespec *prev)
+{
+	int64_t cur_ns, prev_ns;
+
+	cur_ns = timespec_to_ns64(cur);
+	prev_ns = timespec_to_ns64(prev);
+
+	ASSERT_LT(cur_ns - prev_ns, delay_tolerance_nsec, "latency");
+}
+
+static void test_socket_timestamp(struct scm_timestamping *tss, int tstype,
+				  int tskey)
+{
+	static struct timespec prev_ts;
+
+	validate_key(tskey, tstype);
+
+	switch (tstype) {
+	case SCM_TSTAMP_SCHED:
+		validate_timestamp(&tss->ts[0], &usr_ts);
+		SK_TS_SCHED += 1;
+		break;
+	case SCM_TSTAMP_SND:
+		validate_timestamp(&tss->ts[0], &prev_ts);
+		SK_TS_TXSW += 1;
+		break;
+	case SCM_TSTAMP_ACK:
+		validate_timestamp(&tss->ts[0], &prev_ts);
+		SK_TS_ACK += 1;
+		break;
+	}
+
+	prev_ts = tss->ts[0];
+}
+
+static void test_recv_errmsg_cmsg(struct msghdr *msg)
+{
+	struct sock_extended_err *serr = NULL;
+	struct scm_timestamping *tss = NULL;
+	struct cmsghdr *cm;
+
+	for (cm = CMSG_FIRSTHDR(msg);
+	     cm && cm->cmsg_len;
+	     cm = CMSG_NXTHDR(msg, cm)) {
+		if (cm->cmsg_level == SOL_SOCKET &&
+		    cm->cmsg_type == SCM_TIMESTAMPING) {
+			tss = (void *)CMSG_DATA(cm);
+		} else if ((cm->cmsg_level == SOL_IP &&
+			    cm->cmsg_type == IP_RECVERR) ||
+			   (cm->cmsg_level == SOL_IPV6 &&
+			    cm->cmsg_type == IPV6_RECVERR) ||
+			   (cm->cmsg_level == SOL_PACKET &&
+			    cm->cmsg_type == PACKET_TX_TIMESTAMP)) {
+			serr = (void *)CMSG_DATA(cm);
+			ASSERT_EQ(serr->ee_origin, SO_EE_ORIGIN_TIMESTAMPING,
+				  "cmsg type");
+		}
+
+		if (serr && tss)
+			test_socket_timestamp(tss, serr->ee_info,
+					      serr->ee_data);
+	}
+}
+
+static bool socket_recv_errmsg(int fd)
+{
+	static char ctrl[1024 /* overprovision*/];
+	char data[cfg_payload_len];
+	static struct msghdr msg;
+	struct iovec entry;
+	int n = 0;
+
+	memset(&msg, 0, sizeof(msg));
+	memset(&entry, 0, sizeof(entry));
+	memset(ctrl, 0, sizeof(ctrl));
+
+	entry.iov_base = data;
+	entry.iov_len = cfg_payload_len;
+	msg.msg_iov = &entry;
+	msg.msg_iovlen = 1;
+	msg.msg_name = NULL;
+	msg.msg_namelen = 0;
+	msg.msg_control = ctrl;
+	msg.msg_controllen = sizeof(ctrl);
+
+	n = recvmsg(fd, &msg, MSG_ERRQUEUE);
+	if (n == -1)
+		ASSERT_EQ(errno, EAGAIN, "recvmsg MSG_ERRQUEUE");
+
+	if (n >= 0)
+		test_recv_errmsg_cmsg(&msg);
+
+	return n == -1;
+}
+
+static void test_socket_timestamping(int fd)
+{
+	while (!socket_recv_errmsg(fd));
+
+	ASSERT_EQ(SK_TS_SCHED, 1, "SCM_TSTAMP_SCHED");
+	ASSERT_EQ(SK_TS_TXSW, 1, "SCM_TSTAMP_SND");
+	ASSERT_EQ(SK_TS_ACK, 1, "SCM_TSTAMP_ACK");
+
+	SK_TS_SCHED = 0;
+	SK_TS_TXSW = 0;
+	SK_TS_ACK = 0;
+}
+
+static void test_tcp(int family, bool enable_socket_timestamping)
+{
+	struct net_timestamping__bss *bss;
+	char buf[cfg_payload_len];
+	int sfd = -1, cfd = -1;
+	unsigned int sock_opt;
+	struct netns_obj *ns;
+	int cg_fd;
+	int ret;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (!ASSERT_OK_FD(cg_fd, "join cgroup"))
+		return;
+
+	ns = netns_new("net_timestamping_ns", true);
+	if (!ASSERT_OK_PTR(ns, "create ns"))
+		goto out;
+
+	skel = net_timestamping__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skel"))
+		goto out;
+
+	if (!ASSERT_OK(net_timestamping__attach(skel), "attach skel"))
+		goto out;
+
+	skel->links.skops_sockopt =
+		bpf_program__attach_cgroup(skel->progs.skops_sockopt, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.skops_sockopt, "attach cgroup"))
+		goto out;
+
+	bss = skel->bss;
+	memset(bss, 0, sizeof(*bss));
+
+	skel->bss->monitored_pid = getpid();
+
+	sfd = start_server(family, SOCK_STREAM,
+			   family == AF_INET6 ? addr6_str : addr4_str, 0, 0);
+	if (!ASSERT_OK_FD(sfd, "start_server"))
+		goto out;
+
+	cfd = connect_to_fd(sfd, 0);
+	if (!ASSERT_OK_FD(cfd, "connect_to_fd_server"))
+		goto out;
+
+	if (enable_socket_timestamping) {
+		sock_opt = SOF_TIMESTAMPING_SOFTWARE |
+			   SOF_TIMESTAMPING_OPT_ID |
+			   SOF_TIMESTAMPING_TX_SCHED |
+			   SOF_TIMESTAMPING_TX_SOFTWARE |
+			   SOF_TIMESTAMPING_TX_ACK;
+		ret = setsockopt(cfd, SOL_SOCKET, SO_TIMESTAMPING,
+				 (char *) &sock_opt, sizeof(sock_opt));
+		if (!ASSERT_OK(ret, "setsockopt SO_TIMESTAMPING"))
+			goto out;
+
+		ret = clock_gettime(CLOCK_REALTIME, &usr_ts);
+		if (!ASSERT_OK(ret, "get user time"))
+			goto out;
+	}
+
+	ret = write(cfd, buf, sizeof(buf));
+	if (!ASSERT_EQ(ret, sizeof(buf), "send to server"))
+		goto out;
+
+	if (enable_socket_timestamping)
+		test_socket_timestamping(cfd);
+
+	ASSERT_EQ(bss->nr_active, 1, "nr_active");
+	ASSERT_EQ(bss->nr_snd, 2, "nr_snd");
+	ASSERT_EQ(bss->nr_sched, 1, "nr_sched");
+	ASSERT_EQ(bss->nr_txsw, 1, "nr_txsw");
+	ASSERT_EQ(bss->nr_ack, 1, "nr_ack");
+
+out:
+	if (sfd >= 0)
+		close(sfd);
+	if (cfd >= 0)
+		close(cfd);
+	net_timestamping__destroy(skel);
+	netns_free(ns);
+	close(cg_fd);
+}
+
+void test_net_timestamping(void)
+{
+	if (test__start_subtest("INET4: bpf timestamping"))
+		test_tcp(AF_INET, false);
+	if (test__start_subtest("INET4: bpf and socket timestamping"))
+		test_tcp(AF_INET, true);
+	if (test__start_subtest("INET6: bpf timestamping"))
+		test_tcp(AF_INET6, false);
+	if (test__start_subtest("INET6: bpf and socket timestamping"))
+		test_tcp(AF_INET6, true);
+}
diff --git a/tools/testing/selftests/bpf/progs/net_timestamping.c b/tools/testing/selftests/bpf/progs/net_timestamping.c
new file mode 100644
index 0000000000000..b4c2f0f2be114
--- /dev/null
+++ b/tools/testing/selftests/bpf/progs/net_timestamping.c
@@ -0,0 +1,248 @@
+#include "vmlinux.h"
+#include "bpf_tracing_net.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+#include "bpf_misc.h"
+#include "bpf_kfuncs.h"
+#include <errno.h>
+
+__u32 monitored_pid = 0;
+
+int nr_active;
+int nr_snd;
+int nr_passive;
+int nr_sched;
+int nr_txsw;
+int nr_ack;
+
+struct sk_stg {
+	__u64 sendmsg_ns;	/* record ts when sendmsg is called */
+};
+
+struct sk_tskey {
+	u64 cookie;
+	u32 tskey;
+};
+
+struct delay_info {
+	u64 sendmsg_ns;		/* record ts when sendmsg is called */
+	u32 sched_delay;	/* SCHED_CB - sendmsg_ns */
+	u32 snd_sw_delay;	/* SND_SW_CB - SCHED_CB */
+	u32 ack_delay;		/* ACK_CB - SND_SW_CB */
+};
+
+struct {
+	__uint(type, BPF_MAP_TYPE_SK_STORAGE);
+	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__type(key, int);
+	__type(value, struct sk_stg);
+} sk_stg_map SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__type(key, struct sk_tskey);
+	__type(value, struct delay_info);
+	__uint(max_entries, 1024);
+} time_map SEC(".maps");
+
+static u64 delay_tolerance_nsec = 10000000000; /* 10 second as an example */
+
+extern int bpf_sock_ops_enable_tx_tstamp(struct bpf_sock_ops_kern *skops, u64 flags) __ksym;
+
+static int bpf_test_sockopt(void *ctx, const struct sock *sk, int expected)
+{
+	int tmp, new = SK_BPF_CB_TX_TIMESTAMPING;
+	int opt = SK_BPF_CB_FLAGS;
+	int level = SOL_SOCKET;
+
+	if (bpf_setsockopt(ctx, level, opt, &new, sizeof(new)) != expected)
+		return 1;
+
+	if (bpf_getsockopt(ctx, level, opt, &tmp, sizeof(tmp)) != expected ||
+	    (!expected && tmp != new))
+		return 1;
+
+	return 0;
+}
+
+static bool bpf_test_access_sockopt(void *ctx, const struct sock *sk)
+{
+	if (bpf_test_sockopt(ctx, sk, -EOPNOTSUPP))
+		return true;
+	return false;
+}
+
+static bool bpf_test_access_load_hdr_opt(struct bpf_sock_ops *skops)
+{
+	u8 opt[3] = {0};
+	int load_flags = 0;
+	int ret;
+
+	ret = bpf_load_hdr_opt(skops, opt, sizeof(opt), load_flags);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+static bool bpf_test_access_cb_flags_set(struct bpf_sock_ops *skops)
+{
+	int ret;
+
+	ret = bpf_sock_ops_cb_flags_set(skops, 0);
+	if (ret != -EOPNOTSUPP)
+		return true;
+
+	return false;
+}
+
+/* In the timestamping callbacks, we're not allowed to call the following
+ * BPF CALLs for the safety concern. Return false if expected.
+ */
+static bool bpf_test_access_bpf_calls(struct bpf_sock_ops *skops,
+				      const struct sock *sk)
+{
+	if (bpf_test_access_sockopt(skops, sk))
+		return true;
+
+	if (bpf_test_access_load_hdr_opt(skops))
+		return true;
+
+	if (bpf_test_access_cb_flags_set(skops))
+		return true;
+
+	return false;
+}
+
+static bool bpf_test_delay(struct bpf_sock_ops *skops, const struct sock *sk)
+{
+	struct bpf_sock_ops_kern *skops_kern;
+	u64 timestamp = bpf_ktime_get_ns();
+	struct skb_shared_info *shinfo;
+	struct delay_info dinfo = {0};
+	struct sk_tskey key = {0};
+	struct delay_info *val;
+	struct sk_buff *skb;
+	struct sk_stg *stg;
+	u64 prior_ts, delay;
+
+	if (bpf_test_access_bpf_calls(skops, sk))
+		return false;
+
+	skops_kern = bpf_cast_to_kern_ctx(skops);
+	skb = skops_kern->skb;
+	shinfo = bpf_core_cast(skb->head + skb->end, struct skb_shared_info);
+
+	key.cookie = bpf_get_socket_cookie(skops);
+	if (!key.cookie)
+		return false;
+
+	if (skops->op == BPF_SOCK_OPS_TSTAMP_SENDMSG_CB) {
+		stg = bpf_sk_storage_get(&sk_stg_map, (void *)sk, 0, 0);
+		if (!stg)
+			return false;
+		dinfo.sendmsg_ns = stg->sendmsg_ns;
+		bpf_sock_ops_enable_tx_tstamp(skops_kern, 0);
+		key.tskey = shinfo->tskey;
+		if (!key.tskey)
+			return false;
+		bpf_map_update_elem(&time_map, &key, &dinfo, BPF_ANY);
+		return true;
+	}
+
+	key.tskey = shinfo->tskey;
+	if (!key.tskey)
+		return false;
+
+	val = bpf_map_lookup_elem(&time_map, &key);
+	if (!val)
+		return false;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_TSTAMP_SCHED_CB:
+		val->sched_delay = timestamp - val->sendmsg_ns;
+		delay = val->sched_delay;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SND_SW_CB:
+		prior_ts = val->sched_delay + val->sendmsg_ns;
+		val->snd_sw_delay = timestamp - prior_ts;
+		delay = val->snd_sw_delay;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_ACK_CB:
+		prior_ts = val->snd_sw_delay + val->sched_delay + val->sendmsg_ns;
+		val->ack_delay = timestamp - prior_ts;
+		delay = val->ack_delay;
+		break;
+	}
+
+	if (delay >= delay_tolerance_nsec)
+		return false;
+
+	/* Since it's the last one, remove from the map after latency check */
+	if (skops->op == BPF_SOCK_OPS_TSTAMP_ACK_CB)
+		bpf_map_delete_elem(&time_map, &key);
+
+	return true;
+}
+
+SEC("fentry/tcp_sendmsg_locked")
+int BPF_PROG(trace_tcp_sendmsg_locked, struct sock *sk, struct msghdr *msg,
+	     size_t size)
+{
+	__u32 pid = bpf_get_current_pid_tgid() >> 32;
+	u64 timestamp = bpf_ktime_get_ns();
+	u32 flag = sk->sk_bpf_cb_flags;
+	struct sk_stg *stg;
+
+	if (pid != monitored_pid || !flag)
+		return 0;
+
+	stg = bpf_sk_storage_get(&sk_stg_map, sk, 0,
+				 BPF_SK_STORAGE_GET_F_CREATE);
+	if (!stg)
+		return 0;
+
+	stg->sendmsg_ns = timestamp;
+	nr_snd += 1;
+	return 0;
+}
+
+SEC("sockops")
+int skops_sockopt(struct bpf_sock_ops *skops)
+{
+	struct bpf_sock *bpf_sk = skops->sk;
+	const struct sock *sk;
+
+	if (!bpf_sk)
+		return 1;
+
+	sk = (struct sock *)bpf_skc_to_tcp_sock(bpf_sk);
+	if (!sk)
+		return 1;
+
+	switch (skops->op) {
+	case BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB:
+		nr_active += !bpf_test_sockopt(skops, sk, 0);
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SENDMSG_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_snd += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SCHED_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_sched += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_SND_SW_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_txsw += 1;
+		break;
+	case BPF_SOCK_OPS_TSTAMP_ACK_CB:
+		if (bpf_test_delay(skops, sk))
+			nr_ack += 1;
+		break;
+	}
+
+	return 1;
+}
+
+char _license[] SEC("license") = "GPL";

From 06e75161b9d4833518a7c266310a0635eab50616 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 18 Feb 2025 10:34:29 +0800
Subject: [PATCH 0884/2753] net: wangxun: Add support for PTP clock

Implement support for PTP clock on Wangxun NICs.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250218023432.146536-2-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/Kconfig          |   1 +
 drivers/net/ethernet/wangxun/libwx/Makefile   |   2 +-
 .../net/ethernet/wangxun/libwx/wx_ethtool.c   |   3 +
 drivers/net/ethernet/wangxun/libwx/wx_lib.c   |  52 +-
 drivers/net/ethernet/wangxun/libwx/wx_ptp.c   | 603 ++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_ptp.h   |  19 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  68 ++
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c |   8 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c |  10 +
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   |  11 +
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    |   9 +
 11 files changed, 780 insertions(+), 6 deletions(-)
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_ptp.c
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_ptp.h

diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index e46ccebcfd22f..6b60173fe1f50 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -18,6 +18,7 @@ if NET_VENDOR_WANGXUN
 
 config LIBWX
 	tristate
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select PAGE_POOL
 	help
 	Common library for Wangxun(R) Ethernet drivers.
diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile
index 42ccd6e4052e5..e9f0f1f2309bf 100644
--- a/drivers/net/ethernet/wangxun/libwx/Makefile
+++ b/drivers/net/ethernet/wangxun/libwx/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_LIBWX) += libwx.o
 
-libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o
+libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index abe5921dde020..c4b3b00b0926b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -41,6 +41,9 @@ static const struct wx_stats wx_gstrings_stats[] = {
 	WX_STAT("rx_csum_offload_good_count", hw_csum_rx_good),
 	WX_STAT("rx_csum_offload_errors", hw_csum_rx_error),
 	WX_STAT("alloc_rx_buff_failed", alloc_rx_buff_failed),
+	WX_STAT("tx_hwtstamp_timeouts", tx_hwtstamp_timeouts),
+	WX_STAT("tx_hwtstamp_skipped", tx_hwtstamp_skipped),
+	WX_STAT("rx_hwtstamp_cleared", rx_hwtstamp_cleared),
 };
 
 static const struct wx_stats wx_gstrings_fdir_stats[] = {
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 2b3d6586f44a5..42f90802870be 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -13,6 +13,7 @@
 
 #include "wx_type.h"
 #include "wx_lib.h"
+#include "wx_ptp.h"
 #include "wx_hw.h"
 
 /* Lookup table mapping the HW PTYPE to the bit field for decoding */
@@ -597,8 +598,17 @@ static void wx_process_skb_fields(struct wx_ring *rx_ring,
 				  union wx_rx_desc *rx_desc,
 				  struct sk_buff *skb)
 {
+	struct wx *wx = netdev_priv(rx_ring->netdev);
+
 	wx_rx_hash(rx_ring, rx_desc, skb);
 	wx_rx_checksum(rx_ring, rx_desc, skb);
+
+	if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, wx->flags)) &&
+	    unlikely(wx_test_staterr(rx_desc, WX_RXD_STAT_TS))) {
+		wx_ptp_rx_hwtstamp(rx_ring->q_vector->wx, skb);
+		rx_ring->last_rx_timestamp = jiffies;
+	}
+
 	wx_rx_vlan(rx_ring, rx_desc, skb);
 	skb_record_rx_queue(skb, rx_ring->queue_index);
 	skb->protocol = eth_type_trans(skb, rx_ring->netdev);
@@ -705,6 +715,7 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector,
 {
 	unsigned int budget = q_vector->wx->tx_work_limit;
 	unsigned int total_bytes = 0, total_packets = 0;
+	struct wx *wx = netdev_priv(tx_ring->netdev);
 	unsigned int i = tx_ring->next_to_clean;
 	struct wx_tx_buffer *tx_buffer;
 	union wx_tx_desc *tx_desc;
@@ -737,6 +748,11 @@ static bool wx_clean_tx_irq(struct wx_q_vector *q_vector,
 		total_bytes += tx_buffer->bytecount;
 		total_packets += tx_buffer->gso_segs;
 
+		/* schedule check for Tx timestamp */
+		if (unlikely(test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state)) &&
+		    skb_shinfo(tx_buffer->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			ptp_schedule_worker(wx->ptp_clock, 0);
+
 		/* free the skb */
 		napi_consume_skb(tx_buffer->skb, napi_budget);
 
@@ -932,9 +948,9 @@ static void wx_tx_olinfo_status(union wx_tx_desc *tx_desc,
 	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
 
-static void wx_tx_map(struct wx_ring *tx_ring,
-		      struct wx_tx_buffer *first,
-		      const u8 hdr_len)
+static int wx_tx_map(struct wx_ring *tx_ring,
+		     struct wx_tx_buffer *first,
+		     const u8 hdr_len)
 {
 	struct sk_buff *skb = first->skb;
 	struct wx_tx_buffer *tx_buffer;
@@ -1013,6 +1029,8 @@ static void wx_tx_map(struct wx_ring *tx_ring,
 
 	netdev_tx_sent_queue(wx_txring_txq(tx_ring), first->bytecount);
 
+	/* set the timestamp */
+	first->time_stamp = jiffies;
 	skb_tx_timestamp(skb);
 
 	/* Force memory writes to complete before letting h/w know there
@@ -1038,7 +1056,7 @@ static void wx_tx_map(struct wx_ring *tx_ring,
 	if (netif_xmit_stopped(wx_txring_txq(tx_ring)) || !netdev_xmit_more())
 		writel(i, tx_ring->tail);
 
-	return;
+	return 0;
 dma_error:
 	dev_err(tx_ring->dev, "TX DMA map failed\n");
 
@@ -1062,6 +1080,8 @@ static void wx_tx_map(struct wx_ring *tx_ring,
 	first->skb = NULL;
 
 	tx_ring->next_to_use = i;
+
+	return -ENOMEM;
 }
 
 static void wx_tx_ctxtdesc(struct wx_ring *tx_ring, u32 vlan_macip_lens,
@@ -1486,6 +1506,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 		tx_flags |= WX_TX_FLAGS_HW_VLAN;
 	}
 
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
+	    wx->ptp_clock) {
+		if (wx->tstamp_config.tx_type == HWTSTAMP_TX_ON &&
+		    !test_and_set_bit_lock(WX_STATE_PTP_TX_IN_PROGRESS,
+					   wx->state)) {
+			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+			tx_flags |= WX_TX_FLAGS_TSTAMP;
+			wx->ptp_tx_skb = skb_get(skb);
+			wx->ptp_tx_start = jiffies;
+		} else {
+			wx->tx_hwtstamp_skipped++;
+		}
+	}
+
 	/* record initial flags and protocol */
 	first->tx_flags = tx_flags;
 	first->protocol = vlan_get_protocol(skb);
@@ -1501,12 +1535,20 @@ static netdev_tx_t wx_xmit_frame_ring(struct sk_buff *skb,
 	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags) && tx_ring->atr_sample_rate)
 		wx->atr(tx_ring, first, ptype);
 
-	wx_tx_map(tx_ring, first, hdr_len);
+	if (wx_tx_map(tx_ring, first, hdr_len))
+		goto cleanup_tx_tstamp;
 
 	return NETDEV_TX_OK;
 out_drop:
 	dev_kfree_skb_any(first->skb);
 	first->skb = NULL;
+cleanup_tx_tstamp:
+	if (unlikely(tx_flags & WX_TX_FLAGS_TSTAMP)) {
+		dev_kfree_skb_any(wx->ptp_tx_skb);
+		wx->ptp_tx_skb = NULL;
+		wx->tx_hwtstamp_errors++;
+		clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+	}
 
 	return NETDEV_TX_OK;
 }
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
new file mode 100644
index 0000000000000..e56288a18614b
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -0,0 +1,603 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+/* Copyright (c) 1999 - 2025 Intel Corporation. */
+
+#include <linux/ptp_classify.h>
+#include <linux/clocksource.h>
+#include <linux/pci.h>
+
+#include "wx_type.h"
+#include "wx_ptp.h"
+#include "wx_hw.h"
+
+#define WX_INCVAL_10GB        0xCCCCCC
+#define WX_INCVAL_1GB         0x800000
+#define WX_INCVAL_100         0xA00000
+#define WX_INCVAL_10          0xC7F380
+#define WX_INCVAL_EM          0x2000000
+
+#define WX_INCVAL_SHIFT_10GB  20
+#define WX_INCVAL_SHIFT_1GB   18
+#define WX_INCVAL_SHIFT_100   15
+#define WX_INCVAL_SHIFT_10    12
+#define WX_INCVAL_SHIFT_EM    22
+
+#define WX_OVERFLOW_PERIOD    (HZ * 30)
+#define WX_PTP_TX_TIMEOUT     (HZ)
+
+#define WX_1588_PPS_WIDTH_EM  120
+
+#define WX_NS_PER_SEC         1000000000ULL
+
+static u64 wx_ptp_timecounter_cyc2time(struct wx *wx, u64 timestamp)
+{
+	unsigned int seq;
+	u64 ns;
+
+	do {
+		seq = read_seqbegin(&wx->hw_tc_lock);
+		ns = timecounter_cyc2time(&wx->hw_tc, timestamp);
+	} while (read_seqretry(&wx->hw_tc_lock, seq));
+
+	return ns;
+}
+
+static u64 wx_ptp_readtime(struct wx *wx, struct ptp_system_timestamp *sts)
+{
+	u32 timeh1, timeh2, timel;
+
+	timeh1 = rd32ptp(wx, WX_TSC_1588_SYSTIMH);
+	ptp_read_system_prets(sts);
+	timel = rd32ptp(wx, WX_TSC_1588_SYSTIML);
+	ptp_read_system_postts(sts);
+	timeh2 = rd32ptp(wx, WX_TSC_1588_SYSTIMH);
+
+	if (timeh1 != timeh2) {
+		ptp_read_system_prets(sts);
+		timel = rd32ptp(wx, WX_TSC_1588_SYSTIML);
+		ptp_read_system_prets(sts);
+	}
+	return (u64)timel | (u64)timeh2 << 32;
+}
+
+static int wx_ptp_adjfine(struct ptp_clock_info *ptp, long ppb)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	u64 incval, mask;
+
+	smp_mb(); /* Force any pending update before accessing. */
+	incval = READ_ONCE(wx->base_incval);
+	incval = adjust_by_scaled_ppm(incval, ppb);
+
+	mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF;
+	incval &= mask;
+	if (wx->mac.type != wx_mac_em)
+		incval |= 2 << 24;
+
+	wr32ptp(wx, WX_TSC_1588_INC, incval);
+
+	return 0;
+}
+
+static int wx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	unsigned long flags;
+
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_adjtime(&wx->hw_tc, delta);
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	return 0;
+}
+
+static int wx_ptp_gettimex64(struct ptp_clock_info *ptp,
+			     struct timespec64 *ts,
+			     struct ptp_system_timestamp *sts)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	u64 ns, stamp;
+
+	stamp = wx_ptp_readtime(wx, sts);
+	ns = wx_ptp_timecounter_cyc2time(wx, stamp);
+	*ts = ns_to_timespec64(ns);
+
+	return 0;
+}
+
+static int wx_ptp_settime64(struct ptp_clock_info *ptp,
+			    const struct timespec64 *ts)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	unsigned long flags;
+	u64 ns;
+
+	ns = timespec64_to_ns(ts);
+	/* reset the timecounter */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_init(&wx->hw_tc, &wx->hw_cc, ns);
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	return 0;
+}
+
+/**
+ * wx_ptp_clear_tx_timestamp - utility function to clear Tx timestamp state
+ * @wx: the private board structure
+ *
+ * This function should be called whenever the state related to a Tx timestamp
+ * needs to be cleared. This helps ensure that all related bits are reset for
+ * the next Tx timestamp event.
+ */
+static void wx_ptp_clear_tx_timestamp(struct wx *wx)
+{
+	rd32ptp(wx, WX_TSC_1588_STMPH);
+	if (wx->ptp_tx_skb) {
+		dev_kfree_skb_any(wx->ptp_tx_skb);
+		wx->ptp_tx_skb = NULL;
+	}
+	clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+}
+
+/**
+ * wx_ptp_convert_to_hwtstamp - convert register value to hw timestamp
+ * @wx: private board structure
+ * @hwtstamp: stack timestamp structure
+ * @timestamp: unsigned 64bit system time value
+ *
+ * We need to convert the adapter's RX/TXSTMP registers into a hwtstamp value
+ * which can be used by the stack's ptp functions.
+ *
+ * The lock is used to protect consistency of the cyclecounter and the SYSTIME
+ * registers. However, it does not need to protect against the Rx or Tx
+ * timestamp registers, as there can't be a new timestamp until the old one is
+ * unlatched by reading.
+ *
+ * In addition to the timestamp in hardware, some controllers need a software
+ * overflow cyclecounter, and this function takes this into account as well.
+ **/
+static void wx_ptp_convert_to_hwtstamp(struct wx *wx,
+				       struct skb_shared_hwtstamps *hwtstamp,
+				       u64 timestamp)
+{
+	u64 ns;
+
+	ns = wx_ptp_timecounter_cyc2time(wx, timestamp);
+	hwtstamp->hwtstamp = ns_to_ktime(ns);
+}
+
+/**
+ * wx_ptp_tx_hwtstamp - utility function which checks for TX time stamp
+ * @wx: the private board struct
+ *
+ * if the timestamp is valid, we convert it into the timecounter ns
+ * value, then store that result into the shhwtstamps structure which
+ * is passed up the network stack
+ */
+static void wx_ptp_tx_hwtstamp(struct wx *wx)
+{
+	struct skb_shared_hwtstamps shhwtstamps;
+	struct sk_buff *skb = wx->ptp_tx_skb;
+	u64 regval = 0;
+
+	regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPL);
+	regval |= (u64)rd32ptp(wx, WX_TSC_1588_STMPH) << 32;
+
+	wx_ptp_convert_to_hwtstamp(wx, &shhwtstamps, regval);
+
+	wx->ptp_tx_skb = NULL;
+	clear_bit_unlock(WX_STATE_PTP_TX_IN_PROGRESS, wx->state);
+	skb_tstamp_tx(skb, &shhwtstamps);
+	dev_kfree_skb_any(skb);
+	wx->tx_hwtstamp_pkts++;
+}
+
+static int wx_ptp_tx_hwtstamp_work(struct wx *wx)
+{
+	u32 tsynctxctl;
+
+	/* we have to have a valid skb to poll for a timestamp */
+	if (!wx->ptp_tx_skb) {
+		wx_ptp_clear_tx_timestamp(wx);
+		return 0;
+	}
+
+	/* stop polling once we have a valid timestamp */
+	tsynctxctl = rd32ptp(wx, WX_TSC_1588_CTL);
+	if (tsynctxctl & WX_TSC_1588_CTL_VALID) {
+		wx_ptp_tx_hwtstamp(wx);
+		return 0;
+	}
+
+	return -1;
+}
+
+static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+	int ts_done;
+
+	ts_done = wx_ptp_tx_hwtstamp_work(wx);
+
+	return ts_done ? 1 : HZ;
+}
+
+static long wx_ptp_create_clock(struct wx *wx)
+{
+	struct net_device *netdev = wx->netdev;
+	long err;
+
+	/* do nothing if we already have a clock device */
+	if (!IS_ERR_OR_NULL(wx->ptp_clock))
+		return 0;
+
+	snprintf(wx->ptp_caps.name, sizeof(wx->ptp_caps.name),
+		 "%s", netdev->name);
+	wx->ptp_caps.owner = THIS_MODULE;
+	wx->ptp_caps.n_alarm = 0;
+	wx->ptp_caps.n_ext_ts = 0;
+	wx->ptp_caps.n_per_out = 0;
+	wx->ptp_caps.pps = 0;
+	wx->ptp_caps.adjfine = wx_ptp_adjfine;
+	wx->ptp_caps.adjtime = wx_ptp_adjtime;
+	wx->ptp_caps.gettimex64 = wx_ptp_gettimex64;
+	wx->ptp_caps.settime64 = wx_ptp_settime64;
+	wx->ptp_caps.do_aux_work = wx_ptp_do_aux_work;
+	if (wx->mac.type == wx_mac_em)
+		wx->ptp_caps.max_adj = 500000000;
+	else
+		wx->ptp_caps.max_adj = 250000000;
+
+	wx->ptp_clock = ptp_clock_register(&wx->ptp_caps, &wx->pdev->dev);
+	if (IS_ERR(wx->ptp_clock)) {
+		err = PTR_ERR(wx->ptp_clock);
+		wx->ptp_clock = NULL;
+		wx_err(wx, "ptp clock register failed\n");
+		return err;
+	} else if (wx->ptp_clock) {
+		dev_info(&wx->pdev->dev, "registered PHC device on %s\n",
+			 netdev->name);
+	}
+
+	/* Set the default timestamp mode to disabled here. We do this in
+	 * create_clock instead of initialization, because we don't want to
+	 * override the previous settings during a suspend/resume cycle.
+	 */
+	wx->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	wx->tstamp_config.tx_type = HWTSTAMP_TX_OFF;
+
+	return 0;
+}
+
+static int wx_ptp_set_timestamp_mode(struct wx *wx,
+				     struct kernel_hwtstamp_config *config)
+{
+	u32 tsync_tx_ctl = WX_TSC_1588_CTL_ENABLED;
+	u32 tsync_rx_ctl = WX_PSR_1588_CTL_ENABLED;
+	DECLARE_BITMAP(flags, WX_PF_FLAGS_NBITS);
+	u32 tsync_rx_mtrl = PTP_EV_PORT << 16;
+	bool is_l2 = false;
+	u32 regval;
+
+	memcpy(flags, wx->flags, sizeof(wx->flags));
+
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		tsync_tx_ctl = 0;
+		break;
+	case HWTSTAMP_TX_ON:
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	switch (config->rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+		tsync_rx_ctl = 0;
+		tsync_rx_mtrl = 0;
+		clear_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		clear_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1;
+		tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_SYNC;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_L4_V1;
+		tsync_rx_mtrl |= WX_PSR_1588_MSG_V1_DELAY_REQ;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+		tsync_rx_ctl |= WX_PSR_1588_CTL_TYPE_EVENT_V2;
+		is_l2 = true;
+		config->rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT;
+		set_bit(WX_FLAG_RX_HWTSTAMP_ENABLED, flags);
+		set_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER, flags);
+		break;
+	default:
+		/* register PSR_1588_MSG must be set in order to do V1 packets,
+		 * therefore it is not possible to time stamp both V1 Sync and
+		 * Delay_Req messages unless hardware supports timestamping all
+		 * packets => return error
+		 */
+		config->rx_filter = HWTSTAMP_FILTER_NONE;
+		return -ERANGE;
+	}
+
+	/* define ethertype filter for timestamping L2 packets */
+	if (is_l2)
+		wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588),
+		     (WX_PSR_ETYPE_SWC_FILTER_EN | /* enable filter */
+		      WX_PSR_ETYPE_SWC_1588 | /* enable timestamping */
+		      ETH_P_1588)); /* 1588 eth protocol type */
+	else
+		wr32(wx, WX_PSR_ETYPE_SWC(WX_PSR_ETYPE_SWC_FILTER_1588), 0);
+
+	/* enable/disable TX */
+	regval = rd32ptp(wx, WX_TSC_1588_CTL);
+	regval &= ~WX_TSC_1588_CTL_ENABLED;
+	regval |= tsync_tx_ctl;
+	wr32ptp(wx, WX_TSC_1588_CTL, regval);
+
+	/* enable/disable RX */
+	regval = rd32(wx, WX_PSR_1588_CTL);
+	regval &= ~(WX_PSR_1588_CTL_ENABLED | WX_PSR_1588_CTL_TYPE_MASK);
+	regval |= tsync_rx_ctl;
+	wr32(wx, WX_PSR_1588_CTL, regval);
+
+	/* define which PTP packets are time stamped */
+	wr32(wx, WX_PSR_1588_MSG, tsync_rx_mtrl);
+
+	WX_WRITE_FLUSH(wx);
+
+	/* configure adapter flags only when HW is actually configured */
+	memcpy(wx->flags, flags, sizeof(wx->flags));
+
+	/* clear TX/RX timestamp state, just to be sure */
+	wx_ptp_clear_tx_timestamp(wx);
+	rd32(wx, WX_PSR_1588_STMPH);
+
+	return 0;
+}
+
+static u64 wx_ptp_read(const struct cyclecounter *hw_cc)
+{
+	struct wx *wx = container_of(hw_cc, struct wx, hw_cc);
+
+	return wx_ptp_readtime(wx, NULL);
+}
+
+static void wx_ptp_link_speed_adjust(struct wx *wx, u32 *shift, u32 *incval)
+{
+	if (wx->mac.type == wx_mac_em) {
+		*shift = WX_INCVAL_SHIFT_EM;
+		*incval = WX_INCVAL_EM;
+		return;
+	}
+
+	switch (wx->speed) {
+	case SPEED_10:
+		*shift = WX_INCVAL_SHIFT_10;
+		*incval = WX_INCVAL_10;
+		break;
+	case SPEED_100:
+		*shift = WX_INCVAL_SHIFT_100;
+		*incval = WX_INCVAL_100;
+		break;
+	case SPEED_1000:
+		*shift = WX_INCVAL_SHIFT_1GB;
+		*incval = WX_INCVAL_1GB;
+		break;
+	case SPEED_10000:
+	default:
+		*shift = WX_INCVAL_SHIFT_10GB;
+		*incval = WX_INCVAL_10GB;
+		break;
+	}
+}
+
+/**
+ * wx_ptp_reset_cyclecounter - create the cycle counter from hw
+ * @wx: pointer to the wx structure
+ *
+ * This function should be called to set the proper values for the TSC_1588_INC
+ * register and tell the cyclecounter structure what the tick rate of SYSTIME
+ * is. It does not directly modify SYSTIME registers or the timecounter
+ * structure. It should be called whenever a new TSC_1588_INC value is
+ * necessary, such as during initialization or when the link speed changes.
+ */
+void wx_ptp_reset_cyclecounter(struct wx *wx)
+{
+	u32 incval = 0, mask = 0;
+	struct cyclecounter cc;
+	unsigned long flags;
+
+	/* For some of the boards below this mask is technically incorrect.
+	 * The timestamp mask overflows at approximately 61bits. However the
+	 * particular hardware does not overflow on an even bitmask value.
+	 * Instead, it overflows due to conversion of upper 32bits billions of
+	 * cycles. Timecounters are not really intended for this purpose so
+	 * they do not properly function if the overflow point isn't 2^N-1.
+	 * However, the actual SYSTIME values in question take ~138 years to
+	 * overflow. In practice this means they won't actually overflow. A
+	 * proper fix to this problem would require modification of the
+	 * timecounter delta calculations.
+	 */
+	cc.mask = CLOCKSOURCE_MASK(64);
+	cc.mult = 1;
+	cc.shift = 0;
+
+	cc.read = wx_ptp_read;
+	wx_ptp_link_speed_adjust(wx, &cc.shift, &incval);
+
+	/* update the base incval used to calculate frequency adjustment */
+	WRITE_ONCE(wx->base_incval, incval);
+
+	mask = (wx->mac.type == wx_mac_em) ? 0x7FFFFFF : 0xFFFFFF;
+	incval &= mask;
+	if (wx->mac.type != wx_mac_em)
+		incval |= 2 << 24;
+	wr32ptp(wx, WX_TSC_1588_INC, incval);
+
+	smp_mb(); /* Force the above update. */
+
+	/* need lock to prevent incorrect read while modifying cyclecounter */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	memcpy(&wx->hw_cc, &cc, sizeof(wx->hw_cc));
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+}
+EXPORT_SYMBOL(wx_ptp_reset_cyclecounter);
+
+void wx_ptp_reset(struct wx *wx)
+{
+	unsigned long flags;
+
+	/* reset the hardware timestamping mode */
+	wx_ptp_set_timestamp_mode(wx, &wx->tstamp_config);
+	wx_ptp_reset_cyclecounter(wx);
+
+	wr32ptp(wx, WX_TSC_1588_SYSTIML, 0);
+	wr32ptp(wx, WX_TSC_1588_SYSTIMH, 0);
+	WX_WRITE_FLUSH(wx);
+
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	timecounter_init(&wx->hw_tc, &wx->hw_cc,
+			 ktime_to_ns(ktime_get_real()));
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+}
+EXPORT_SYMBOL(wx_ptp_reset);
+
+void wx_ptp_init(struct wx *wx)
+{
+	/* Initialize the seqlock_t first, since the user might call the clock
+	 * functions any time after we've initialized the ptp clock device.
+	 */
+	seqlock_init(&wx->hw_tc_lock);
+
+	/* obtain a ptp clock device, or re-use an existing device */
+	if (wx_ptp_create_clock(wx))
+		return;
+
+	wx->tx_hwtstamp_pkts = 0;
+	wx->tx_hwtstamp_timeouts = 0;
+	wx->tx_hwtstamp_skipped = 0;
+	wx->tx_hwtstamp_errors = 0;
+	wx->rx_hwtstamp_cleared = 0;
+	/* reset the ptp related hardware bits */
+	wx_ptp_reset(wx);
+
+	/* enter the WX_STATE_PTP_RUNNING state */
+	set_bit(WX_STATE_PTP_RUNNING, wx->state);
+}
+EXPORT_SYMBOL(wx_ptp_init);
+
+/**
+ * wx_ptp_suspend - stop ptp work items
+ * @wx: pointer to wx struct
+ *
+ * This function suspends ptp activity, and prevents more work from being
+ * generated, but does not destroy the clock device.
+ */
+void wx_ptp_suspend(struct wx *wx)
+{
+	/* leave the WX_STATE_PTP_RUNNING STATE */
+	if (!test_and_clear_bit(WX_STATE_PTP_RUNNING, wx->state))
+		return;
+
+	wx_ptp_clear_tx_timestamp(wx);
+}
+EXPORT_SYMBOL(wx_ptp_suspend);
+
+/**
+ * wx_ptp_stop - destroy the ptp_clock device
+ * @wx: pointer to wx struct
+ *
+ * Completely destroy the ptp_clock device, and disable all PTP related
+ * features. Intended to be run when the device is being closed.
+ */
+void wx_ptp_stop(struct wx *wx)
+{
+	/* first, suspend ptp activity */
+	wx_ptp_suspend(wx);
+
+	/* now destroy the ptp clock device */
+	if (wx->ptp_clock) {
+		ptp_clock_unregister(wx->ptp_clock);
+		wx->ptp_clock = NULL;
+		dev_info(&wx->pdev->dev, "removed PHC on %s\n", wx->netdev->name);
+	}
+}
+EXPORT_SYMBOL(wx_ptp_stop);
+
+/**
+ * wx_ptp_rx_hwtstamp - utility function which checks for RX time stamp
+ * @wx: pointer to wx struct
+ * @skb: particular skb to send timestamp with
+ *
+ * if the timestamp is valid, we convert it into the timecounter ns
+ * value, then store that result into the shhwtstamps structure which
+ * is passed up the network stack
+ */
+void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb)
+{
+	u64 regval = 0;
+	u32 tsyncrxctl;
+
+	/* Read the tsyncrxctl register afterwards in order to prevent taking an
+	 * I/O hit on every packet.
+	 */
+	tsyncrxctl = rd32(wx, WX_PSR_1588_CTL);
+	if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID))
+		return;
+
+	regval |= (u64)rd32(wx, WX_PSR_1588_STMPL);
+	regval |= (u64)rd32(wx, WX_PSR_1588_STMPH) << 32;
+
+	wx_ptp_convert_to_hwtstamp(wx, skb_hwtstamps(skb), regval);
+}
+
+int wx_hwtstamp_get(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	*cfg = wx->tstamp_config;
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_hwtstamp_get);
+
+int wx_hwtstamp_set(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg,
+		    struct netlink_ext_ack *extack)
+{
+	struct wx *wx = netdev_priv(dev);
+	int err;
+
+	if (!netif_running(dev))
+		return -EINVAL;
+
+	err = wx_ptp_set_timestamp_mode(wx, cfg);
+	if (err)
+		return err;
+
+	/* save these settings for future reference */
+	memcpy(&wx->tstamp_config, cfg, sizeof(wx->tstamp_config));
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_hwtstamp_set);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.h b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
new file mode 100644
index 0000000000000..8742d27973636
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2019 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _WX_PTP_H_
+#define _WX_PTP_H_
+
+void wx_ptp_reset_cyclecounter(struct wx *wx);
+void wx_ptp_reset(struct wx *wx);
+void wx_ptp_init(struct wx *wx);
+void wx_ptp_suspend(struct wx *wx);
+void wx_ptp_stop(struct wx *wx);
+void wx_ptp_rx_hwtstamp(struct wx *wx, struct sk_buff *skb);
+int wx_hwtstamp_get(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg);
+int wx_hwtstamp_set(struct net_device *dev,
+		    struct kernel_hwtstamp_config *cfg,
+		    struct netlink_ext_ack *extack);
+
+#endif /* _WX_PTP_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index b54bffda027b4..f83c54d4657c9 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -4,6 +4,8 @@
 #ifndef _WX_TYPE_H_
 #define _WX_TYPE_H_
 
+#include <linux/ptp_clock_kernel.h>
+#include <linux/timecounter.h>
 #include <linux/bitfield.h>
 #include <linux/netdevice.h>
 #include <linux/if_vlan.h>
@@ -180,6 +182,23 @@
 #define WX_PSR_VLAN_CTL              0x15088
 #define WX_PSR_VLAN_CTL_CFIEN        BIT(29)  /* bit 29 */
 #define WX_PSR_VLAN_CTL_VFE          BIT(30)  /* bit 30 */
+/* EType Queue Filter */
+#define WX_PSR_ETYPE_SWC(_i)         (0x15128 + ((_i) * 4))
+#define WX_PSR_ETYPE_SWC_FILTER_1588 3
+#define WX_PSR_ETYPE_SWC_FILTER_EN   BIT(31)
+#define WX_PSR_ETYPE_SWC_1588        BIT(30)
+/* 1588 */
+#define WX_PSR_1588_MSG                 0x15120
+#define WX_PSR_1588_MSG_V1_SYNC         FIELD_PREP(GENMASK(7, 0), 0)
+#define WX_PSR_1588_MSG_V1_DELAY_REQ    FIELD_PREP(GENMASK(7, 0), 1)
+#define WX_PSR_1588_STMPL               0x151E8
+#define WX_PSR_1588_STMPH               0x151A4
+#define WX_PSR_1588_CTL                 0x15188
+#define WX_PSR_1588_CTL_ENABLED         BIT(4)
+#define WX_PSR_1588_CTL_TYPE_MASK       GENMASK(3, 1)
+#define WX_PSR_1588_CTL_TYPE_L4_V1      FIELD_PREP(GENMASK(3, 1), 1)
+#define WX_PSR_1588_CTL_TYPE_EVENT_V2   FIELD_PREP(GENMASK(3, 1), 5)
+#define WX_PSR_1588_CTL_VALID           BIT(0)
 /* mcasst/ucast overflow tbl */
 #define WX_PSR_MC_TBL(_i)            (0x15200  + ((_i) * 4))
 #define WX_PSR_UC_TBL(_i)            (0x15400 + ((_i) * 4))
@@ -253,6 +272,15 @@
 #define WX_TSC_ST_SECTX_RDY          BIT(0)
 #define WX_TSC_BUF_AE                0x1D00C
 #define WX_TSC_BUF_AE_THR            GENMASK(9, 0)
+/* 1588 */
+#define WX_TSC_1588_CTL              0x11F00
+#define WX_TSC_1588_CTL_ENABLED      BIT(4)
+#define WX_TSC_1588_CTL_VALID        BIT(0)
+#define WX_TSC_1588_STMPL            0x11F04
+#define WX_TSC_1588_STMPH            0x11F08
+#define WX_TSC_1588_SYSTIML          0x11F0C
+#define WX_TSC_1588_SYSTIMH          0x11F10
+#define WX_TSC_1588_INC              0x11F14
 
 /************************************** MNG ********************************/
 #define WX_MNG_SWFW_SYNC             0x1E008
@@ -460,6 +488,7 @@ enum WX_MSCA_CMD_value {
 #define WX_RXD_STAT_L4CS             BIT(7) /* L4 xsum calculated */
 #define WX_RXD_STAT_IPCS             BIT(8) /* IP xsum calculated */
 #define WX_RXD_STAT_OUTERIPCS        BIT(10) /* Cloud IP xsum calculated*/
+#define WX_RXD_STAT_TS               BIT(14) /* IEEE1588 Time Stamp */
 
 #define WX_RXD_ERR_OUTERIPER         BIT(26) /* CRC IP Header error */
 #define WX_RXD_ERR_RXE               BIT(29) /* Any MAC Error */
@@ -863,6 +892,7 @@ struct wx_tx_context_desc {
  */
 struct wx_tx_buffer {
 	union wx_tx_desc *next_to_watch;
+	unsigned long time_stamp;
 	struct sk_buff *skb;
 	unsigned int bytecount;
 	unsigned short gso_segs;
@@ -924,6 +954,7 @@ struct wx_ring {
 	unsigned int size;              /* length in bytes */
 
 	u16 count;                      /* amount of descriptors */
+	unsigned long last_rx_timestamp;
 
 	u8 queue_index; /* needed for multiqueue queue management */
 	u8 reg_idx;                     /* holds the special value that gets
@@ -1026,6 +1057,8 @@ struct wx_hw_stats {
 
 enum wx_state {
 	WX_STATE_RESETTING,
+	WX_STATE_PTP_RUNNING,
+	WX_STATE_PTP_TX_IN_PROGRESS,
 	WX_STATE_NBITS,		/* must be last */
 };
 
@@ -1033,6 +1066,8 @@ enum wx_pf_flags {
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
+	WX_FLAG_RX_HWTSTAMP_ENABLED,
+	WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
 	WX_PF_FLAGS_NBITS               /* must be last */
 };
 
@@ -1133,6 +1168,21 @@ struct wx {
 	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);
 	void (*configure_fdir)(struct wx *wx);
 	void (*do_reset)(struct net_device *netdev);
+
+	u32 base_incval;
+	u32 tx_hwtstamp_pkts;
+	u32 tx_hwtstamp_timeouts;
+	u32 tx_hwtstamp_skipped;
+	u32 tx_hwtstamp_errors;
+	u32 rx_hwtstamp_cleared;
+	unsigned long ptp_tx_start;
+	seqlock_t hw_tc_lock; /* seqlock for ptp */
+	struct cyclecounter hw_cc;
+	struct timecounter hw_tc;
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct sk_buff *ptp_tx_skb;
 };
 
 #define WX_INTR_ALL (~0ULL)
@@ -1177,6 +1227,24 @@ rd64(struct wx *wx, u32 reg)
 	return (lsb | msb << 32);
 }
 
+static inline u32
+rd32ptp(struct wx *wx, u32 reg)
+{
+	if (wx->mac.type == wx_mac_em)
+		return rd32(wx, reg);
+
+	return rd32(wx, reg + 0xB500);
+}
+
+static inline void
+wr32ptp(struct wx *wx, u32 reg, u32 value)
+{
+	if (wx->mac.type == wx_mac_em)
+		return wr32(wx, reg, value);
+
+	return wr32(wx, reg + 0xB500, value);
+}
+
 /* On some domestic CPU platforms, sometimes IO is not synchronized with
  * flushing memory, here use readl() to flush PCI read and write.
  */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index 53aeae2f884b0..c60a96cc35086 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -14,6 +14,7 @@
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_hw.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
 #include "ngbe_hw.h"
@@ -317,6 +318,8 @@ void ngbe_down(struct wx *wx)
 {
 	phylink_stop(wx->phylink);
 	ngbe_disable_device(wx);
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset(wx);
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
 }
@@ -379,6 +382,8 @@ static int ngbe_open(struct net_device *netdev)
 	if (err)
 		goto err_dis_phy;
 
+	wx_ptp_init(wx);
+
 	ngbe_up(wx);
 
 	return 0;
@@ -407,6 +412,7 @@ static int ngbe_close(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	wx_ptp_stop(wx);
 	ngbe_down(wx);
 	wx_free_irq(wx);
 	wx_free_isb_resources(wx);
@@ -507,6 +513,8 @@ static const struct net_device_ops ngbe_netdev_ops = {
 	.ndo_get_stats64        = wx_get_stats64,
 	.ndo_vlan_rx_add_vid    = wx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = wx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set       = wx_hwtstamp_set,
+	.ndo_hwtstamp_get       = wx_hwtstamp_get,
 };
 
 /**
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index a5e9b779c44d0..c7944e62838ae 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -7,6 +7,7 @@
 #include <linux/phy.h>
 
 #include "../libwx/wx_type.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
@@ -64,6 +65,11 @@ static void ngbe_mac_config(struct phylink_config *config, unsigned int mode,
 static void ngbe_mac_link_down(struct phylink_config *config,
 			       unsigned int mode, phy_interface_t interface)
 {
+	struct wx *wx = phylink_to_wx(config);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
 }
 
 static void ngbe_mac_link_up(struct phylink_config *config,
@@ -103,6 +109,10 @@ static void ngbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
 	reg = rd32(wx, WX_MAC_WDG_TIMEOUT);
 	wr32(wx, WX_MAC_WDG_TIMEOUT, reg);
+
+	wx->speed = speed;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
 }
 
 static const struct phylink_mac_ops ngbe_mac_ops = {
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index f774502680364..734450af9a432 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -13,6 +13,7 @@
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
 #include "txgbe_hw.h"
@@ -116,6 +117,9 @@ static void txgbe_reset(struct wx *wx)
 	memcpy(old_addr, &wx->mac_table[0].addr, netdev->addr_len);
 	wx_flush_sw_mac_table(wx);
 	wx_mac_set_default_filter(wx, old_addr);
+
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset(wx);
 }
 
 static void txgbe_disable_device(struct wx *wx)
@@ -176,6 +180,7 @@ void txgbe_down(struct wx *wx)
 void txgbe_up(struct wx *wx)
 {
 	wx_configure(wx);
+	wx_ptp_init(wx);
 	txgbe_up_complete(wx);
 }
 
@@ -321,6 +326,8 @@ static int txgbe_open(struct net_device *netdev)
 	if (err)
 		goto err_free_irq;
 
+	wx_ptp_init(wx);
+
 	txgbe_up_complete(wx);
 
 	return 0;
@@ -344,6 +351,7 @@ static int txgbe_open(struct net_device *netdev)
  */
 static void txgbe_close_suspend(struct wx *wx)
 {
+	wx_ptp_suspend(wx);
 	txgbe_disable_device(wx);
 	wx_free_resources(wx);
 }
@@ -363,6 +371,7 @@ static int txgbe_close(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	wx_ptp_stop(wx);
 	txgbe_down(wx);
 	wx_free_irq(wx);
 	wx_free_resources(wx);
@@ -479,6 +488,8 @@ static const struct net_device_ops txgbe_netdev_ops = {
 	.ndo_get_stats64        = wx_get_stats64,
 	.ndo_vlan_rx_add_vid    = wx_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid   = wx_vlan_rx_kill_vid,
+	.ndo_hwtstamp_set       = wx_hwtstamp_set,
+	.ndo_hwtstamp_get       = wx_hwtstamp_get,
 };
 
 /**
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 1ae68f94dd490..60e5f3288ad8a 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -15,6 +15,7 @@
 
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
+#include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
@@ -179,6 +180,10 @@ static void txgbe_mac_link_down(struct phylink_config *config,
 	struct wx *wx = phylink_to_wx(config);
 
 	wr32m(wx, WX_MAC_TX_CFG, WX_MAC_TX_CFG_TE, 0);
+
+	wx->speed = SPEED_UNKNOWN;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
 }
 
 static void txgbe_mac_link_up(struct phylink_config *config,
@@ -215,6 +220,10 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_PKT_FLT, WX_MAC_PKT_FLT_PR);
 	wdg = rd32(wx, WX_MAC_WDG_TIMEOUT);
 	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
+
+	wx->speed = speed;
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset_cyclecounter(wx);
 }
 
 static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,

From ce114069a654be6b1597da983a201c72ceca7a85 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 18 Feb 2025 10:34:30 +0800
Subject: [PATCH 0885/2753] net: wangxun: Support to get ts info

Implement the function get_ts_info and get_ts_stats in ethtool_ops to
get the HW capabilities and statistics for timestamping.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250218023432.146536-3-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/wangxun/libwx/wx_ethtool.c   | 50 +++++++++++++++++++
 .../net/ethernet/wangxun/libwx/wx_ethtool.h   |  4 ++
 .../net/ethernet/wangxun/ngbe/ngbe_ethtool.c  |  2 +
 .../ethernet/wangxun/txgbe/txgbe_ethtool.c    |  2 +
 4 files changed, 58 insertions(+)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index c4b3b00b0926b..28f982fbc64c3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -455,3 +455,53 @@ void wx_set_msglevel(struct net_device *netdev, u32 data)
 	wx->msg_enable = data;
 }
 EXPORT_SYMBOL(wx_set_msglevel);
+
+int wx_get_ts_info(struct net_device *dev,
+		   struct kernel_ethtool_ts_info *info)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) |
+			   BIT(HWTSTAMP_FILTER_PTP_V1_L4_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_EVENT) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_SYNC) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ) |
+			   BIT(HWTSTAMP_FILTER_PTP_V2_EVENT);
+
+	info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE |
+				SOF_TIMESTAMPING_TX_HARDWARE |
+				SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	if (wx->ptp_clock)
+		info->phc_index = ptp_clock_index(wx->ptp_clock);
+	else
+		info->phc_index = -1;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF) |
+			 BIT(HWTSTAMP_TX_ON);
+
+	return 0;
+}
+EXPORT_SYMBOL(wx_get_ts_info);
+
+void wx_get_ptp_stats(struct net_device *dev,
+		      struct ethtool_ts_stats *ts_stats)
+{
+	struct wx *wx = netdev_priv(dev);
+
+	if (wx->ptp_clock) {
+		ts_stats->pkts = wx->tx_hwtstamp_pkts;
+		ts_stats->lost = wx->tx_hwtstamp_timeouts +
+				 wx->tx_hwtstamp_skipped +
+				 wx->rx_hwtstamp_cleared;
+		ts_stats->err = wx->tx_hwtstamp_errors;
+	}
+}
+EXPORT_SYMBOL(wx_get_ptp_stats);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
index 600c3b597d1a9..9e002e699ecab 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.h
@@ -40,4 +40,8 @@ int wx_set_channels(struct net_device *dev,
 		    struct ethtool_channels *ch);
 u32 wx_get_msglevel(struct net_device *netdev);
 void wx_set_msglevel(struct net_device *netdev, u32 data);
+int wx_get_ts_info(struct net_device *dev,
+		   struct kernel_ethtool_ts_info *info);
+void wx_get_ptp_stats(struct net_device *dev,
+		      struct ethtool_ts_stats *ts_stats);
 #endif /* _WX_ETHTOOL_H_ */
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
index e868f7ef49203..7e2d9ec38a306 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_ethtool.c
@@ -138,6 +138,8 @@ static const struct ethtool_ops ngbe_ethtool_ops = {
 	.set_channels		= ngbe_set_channels,
 	.get_msglevel		= wx_get_msglevel,
 	.set_msglevel		= wx_set_msglevel,
+	.get_ts_info		= wx_get_ts_info,
+	.get_ts_stats		= wx_get_ptp_stats,
 };
 
 void ngbe_set_ethtool_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
index d98314b26c194..78999d484f18e 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_ethtool.c
@@ -529,6 +529,8 @@ static const struct ethtool_ops txgbe_ethtool_ops = {
 	.set_rxnfc		= txgbe_set_rxnfc,
 	.get_msglevel		= wx_get_msglevel,
 	.set_msglevel		= wx_set_msglevel,
+	.get_ts_info		= wx_get_ts_info,
+	.get_ts_stats		= wx_get_ptp_stats,
 };
 
 void txgbe_set_ethtool_ops(struct net_device *netdev)

From 704145a854ee01015d52fb8c4c0c319d1810bf32 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 18 Feb 2025 10:34:31 +0800
Subject: [PATCH 0886/2753] net: wangxun: Add periodic checks for overflow and
 errors

Implement watchdog task to detect SYSTIME overflow and error cases of
Rx/Tx timestamp.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250218023432.146536-4-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_ptp.c   | 105 ++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |   2 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c |   1 +
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    |   1 +
 4 files changed, 109 insertions(+)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
index e56288a18614b..76986e41afe00 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -212,6 +212,102 @@ static int wx_ptp_tx_hwtstamp_work(struct wx *wx)
 	return -1;
 }
 
+/**
+ * wx_ptp_overflow_check - watchdog task to detect SYSTIME overflow
+ * @wx: pointer to wx struct
+ *
+ * this watchdog task periodically reads the timecounter
+ * in order to prevent missing when the system time registers wrap
+ * around. This needs to be run approximately twice a minute for the fastest
+ * overflowing hardware. We run it for all hardware since it shouldn't have a
+ * large impact.
+ */
+static void wx_ptp_overflow_check(struct wx *wx)
+{
+	bool timeout = time_is_before_jiffies(wx->last_overflow_check +
+					      WX_OVERFLOW_PERIOD);
+	unsigned long flags;
+
+	if (timeout) {
+		/* Update the timecounter */
+		write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+		timecounter_read(&wx->hw_tc);
+		write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+		wx->last_overflow_check = jiffies;
+	}
+}
+
+/**
+ * wx_ptp_rx_hang - detect error case when Rx timestamp registers latched
+ * @wx: pointer to wx struct
+ *
+ * this watchdog task is scheduled to detect error case where hardware has
+ * dropped an Rx packet that was timestamped when the ring is full. The
+ * particular error is rare but leaves the device in a state unable to
+ * timestamp any future packets.
+ */
+static void wx_ptp_rx_hang(struct wx *wx)
+{
+	struct wx_ring *rx_ring;
+	unsigned long rx_event;
+	u32 tsyncrxctl;
+	int n;
+
+	tsyncrxctl = rd32(wx, WX_PSR_1588_CTL);
+
+	/* if we don't have a valid timestamp in the registers, just update the
+	 * timeout counter and exit
+	 */
+	if (!(tsyncrxctl & WX_PSR_1588_CTL_VALID)) {
+		wx->last_rx_ptp_check = jiffies;
+		return;
+	}
+
+	/* determine the most recent watchdog or rx_timestamp event */
+	rx_event = wx->last_rx_ptp_check;
+	for (n = 0; n < wx->num_rx_queues; n++) {
+		rx_ring = wx->rx_ring[n];
+		if (time_after(rx_ring->last_rx_timestamp, rx_event))
+			rx_event = rx_ring->last_rx_timestamp;
+	}
+
+	/* only need to read the high RXSTMP register to clear the lock */
+	if (time_is_before_jiffies(rx_event + 5 * HZ)) {
+		rd32(wx, WX_PSR_1588_STMPH);
+		wx->last_rx_ptp_check = jiffies;
+
+		wx->rx_hwtstamp_cleared++;
+		dev_warn(&wx->pdev->dev, "clearing RX Timestamp hang");
+	}
+}
+
+/**
+ * wx_ptp_tx_hang - detect error case where Tx timestamp never finishes
+ * @wx: private network wx structure
+ */
+static void wx_ptp_tx_hang(struct wx *wx)
+{
+	bool timeout = time_is_before_jiffies(wx->ptp_tx_start +
+					      WX_PTP_TX_TIMEOUT);
+
+	if (!wx->ptp_tx_skb)
+		return;
+
+	if (!test_bit(WX_STATE_PTP_TX_IN_PROGRESS, wx->state))
+		return;
+
+	/* If we haven't received a timestamp within the timeout, it is
+	 * reasonable to assume that it will never occur, so we can unlock the
+	 * timestamp bit when this occurs.
+	 */
+	if (timeout) {
+		wx_ptp_clear_tx_timestamp(wx);
+		wx->tx_hwtstamp_timeouts++;
+		dev_warn(&wx->pdev->dev, "clearing Tx timestamp hang\n");
+	}
+}
+
 static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp)
 {
 	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
@@ -219,6 +315,12 @@ static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp)
 
 	ts_done = wx_ptp_tx_hwtstamp_work(wx);
 
+	wx_ptp_overflow_check(wx);
+	if (unlikely(test_bit(WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
+			      wx->flags)))
+		wx_ptp_rx_hang(wx);
+	wx_ptp_tx_hang(wx);
+
 	return ts_done ? 1 : HZ;
 }
 
@@ -475,6 +577,9 @@ void wx_ptp_reset(struct wx *wx)
 	timecounter_init(&wx->hw_tc, &wx->hw_cc,
 			 ktime_to_ns(ktime_get_real()));
 	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+
+	wx->last_overflow_check = jiffies;
+	ptp_schedule_worker(wx->ptp_clock, HZ);
 }
 EXPORT_SYMBOL(wx_ptp_reset);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index f83c54d4657c9..0fabfa90d4e71 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1175,6 +1175,8 @@ struct wx {
 	u32 tx_hwtstamp_skipped;
 	u32 tx_hwtstamp_errors;
 	u32 rx_hwtstamp_cleared;
+	unsigned long last_overflow_check;
+	unsigned long last_rx_ptp_check;
 	unsigned long ptp_tx_start;
 	seqlock_t hw_tc_lock; /* seqlock for ptp */
 	struct cyclecounter hw_cc;
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index c7944e62838ae..ea1d7e9a91f3d 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -111,6 +111,7 @@ static void ngbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_WDG_TIMEOUT, reg);
 
 	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
 }
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 60e5f3288ad8a..7e17d727c2bad 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -222,6 +222,7 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 	wr32(wx, WX_MAC_WDG_TIMEOUT, wdg);
 
 	wx->speed = speed;
+	wx->last_rx_ptp_check = jiffies;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
 }

From 2d8967e86c9b12e7b8a82a531572186b2b97e804 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Tue, 18 Feb 2025 10:34:32 +0800
Subject: [PATCH 0887/2753] net: ngbe: Add support for 1PPS and TOD

Implement support for generating a 1pps output signal on SDP0.
And support custom firmware to output TOD.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Link: https://patch.msgid.link/20250218023432.146536-5-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c    |  19 ++
 drivers/net/ethernet/wangxun/libwx/wx_hw.h    |   1 +
 drivers/net/ethernet/wangxun/libwx/wx_ptp.c   | 181 +++++++++++++++++-
 drivers/net/ethernet/wangxun/libwx/wx_ptp.h   |   1 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  35 ++++
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c |  12 +-
 drivers/net/ethernet/wangxun/ngbe/ngbe_type.h |   5 +
 7 files changed, 250 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index deaf670c160eb..907d13ade4048 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -393,6 +393,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 }
 EXPORT_SYMBOL(wx_host_interface_command);
 
+int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles)
+{
+	struct wx_hic_set_pps pps_cmd;
+
+	pps_cmd.hdr.cmd = FW_PPS_SET_CMD;
+	pps_cmd.hdr.buf_len = FW_PPS_SET_LEN;
+	pps_cmd.hdr.cmd_or_resp.cmd_resv = FW_CEM_CMD_RESERVED;
+	pps_cmd.lan_id = wx->bus.func;
+	pps_cmd.enable = (u8)enable;
+	pps_cmd.nsec = nsec;
+	pps_cmd.cycles = cycles;
+	pps_cmd.hdr.checksum = FW_DEFAULT_CHECKSUM;
+
+	return wx_host_interface_command(wx, (u32 *)&pps_cmd,
+					 sizeof(pps_cmd),
+					 WX_HI_COMMAND_TIMEOUT,
+					 false);
+}
+
 /**
  *  wx_read_ee_hostif_data - Read EEPROM word using a host interface cmd
  *  assuming that the semaphore is already obtained.
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index 11fb333494824..b883342bb5767 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -18,6 +18,7 @@ void wx_control_hw(struct wx *wx, bool drv);
 int wx_mng_present(struct wx *wx);
 int wx_host_interface_command(struct wx *wx, u32 *buffer,
 			      u32 length, u32 timeout, bool return_data);
+int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles);
 int wx_read_ee_hostif(struct wx *wx, u16 offset, u16 *data);
 int wx_read_ee_hostif_buffer(struct wx *wx,
 			     u16 offset, u16 words, u16 *data);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
index 76986e41afe00..07c015ba338f4 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -88,6 +88,9 @@ static int wx_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
 	timecounter_adjtime(&wx->hw_tc, delta);
 	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
 
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
 	return 0;
 }
 
@@ -118,6 +121,9 @@ static int wx_ptp_settime64(struct ptp_clock_info *ptp,
 	timecounter_init(&wx->hw_tc, &wx->hw_cc, ns);
 	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
 
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
 	return 0;
 }
 
@@ -324,6 +330,160 @@ static long wx_ptp_do_aux_work(struct ptp_clock_info *ptp)
 	return ts_done ? 1 : HZ;
 }
 
+static u64 wx_ptp_trigger_calc(struct wx *wx)
+{
+	struct cyclecounter *cc = &wx->hw_cc;
+	unsigned long flags;
+	u64 ns = 0;
+	u32 rem;
+
+	/* Read the current clock time, and save the cycle counter value */
+	write_seqlock_irqsave(&wx->hw_tc_lock, flags);
+	ns = timecounter_read(&wx->hw_tc);
+	wx->pps_edge_start = wx->hw_tc.cycle_last;
+	write_sequnlock_irqrestore(&wx->hw_tc_lock, flags);
+	wx->pps_edge_end = wx->pps_edge_start;
+
+	/* Figure out how far past the next second we are */
+	div_u64_rem(ns, WX_NS_PER_SEC, &rem);
+
+	/* Figure out how many nanoseconds to add to round the clock edge up
+	 * to the next full second
+	 */
+	rem = (WX_NS_PER_SEC - rem);
+
+	/* Adjust the clock edge to align with the next full second. */
+	wx->pps_edge_start += div_u64(((u64)rem << cc->shift), cc->mult);
+	wx->pps_edge_end += div_u64(((u64)(rem + wx->pps_width) <<
+				     cc->shift), cc->mult);
+
+	return (ns + rem);
+}
+
+static int wx_ptp_setup_sdp(struct wx *wx)
+{
+	struct cyclecounter *cc = &wx->hw_cc;
+	u32 tsauxc;
+	u64 nsec;
+
+	if (wx->pps_width >= WX_NS_PER_SEC) {
+		wx_err(wx, "PTP pps width cannot be longer than 1s!\n");
+		return -EINVAL;
+	}
+
+	/* disable the pin first */
+	wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0);
+	WX_WRITE_FLUSH(wx);
+
+	if (!test_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags)) {
+		if (wx->pps_enabled) {
+			wx->pps_enabled = false;
+			wx_set_pps(wx, false, 0, 0);
+		}
+		return 0;
+	}
+
+	wx->pps_enabled = true;
+	nsec = wx_ptp_trigger_calc(wx);
+	wx_set_pps(wx, wx->pps_enabled, nsec, wx->pps_edge_start);
+
+	tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 |
+		WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0;
+	wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start);
+	wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32));
+	wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end);
+	wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32));
+	wr32ptp(wx, WX_TSC_1588_SDP(0),
+		WX_TSC_1588_SDP_FUN_SEL_TT0 | WX_TSC_1588_SDP_OUT_LEVEL_H);
+	wr32ptp(wx, WX_TSC_1588_SDP(1), WX_TSC_1588_SDP_FUN_SEL_TS0);
+	wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc);
+	wr32ptp(wx, WX_TSC_1588_INT_EN, WX_TSC_1588_INT_EN_TT1);
+	WX_WRITE_FLUSH(wx);
+
+	/* Adjust the clock edge to align with the next full second. */
+	wx->sec_to_cc = div_u64(((u64)WX_NS_PER_SEC << cc->shift), cc->mult);
+
+	return 0;
+}
+
+static int wx_ptp_feature_enable(struct ptp_clock_info *ptp,
+				 struct ptp_clock_request *rq, int on)
+{
+	struct wx *wx = container_of(ptp, struct wx, ptp_caps);
+
+	/**
+	 * When PPS is enabled, unmask the interrupt for the ClockOut
+	 * feature, so that the interrupt handler can send the PPS
+	 * event when the clock SDP triggers. Clear mask when PPS is
+	 * disabled
+	 */
+	if (rq->type != PTP_CLK_REQ_PEROUT || !wx->ptp_setup_sdp)
+		return -EOPNOTSUPP;
+
+	/* Reject requests with unsupported flags */
+	if (rq->perout.flags & ~(PTP_PEROUT_DUTY_CYCLE |
+				 PTP_PEROUT_PHASE))
+		return -EOPNOTSUPP;
+
+	if (rq->perout.phase.sec || rq->perout.phase.nsec) {
+		wx_err(wx, "Absolute start time not supported.\n");
+		return -EINVAL;
+	}
+
+	if (rq->perout.period.sec != 1 || rq->perout.period.nsec) {
+		wx_err(wx, "Only 1pps is supported.\n");
+		return -EINVAL;
+	}
+
+	if (rq->perout.flags & PTP_PEROUT_DUTY_CYCLE) {
+		struct timespec64 ts_on;
+
+		ts_on.tv_sec = rq->perout.on.sec;
+		ts_on.tv_nsec = rq->perout.on.nsec;
+		wx->pps_width = timespec64_to_ns(&ts_on);
+	} else {
+		wx->pps_width = 120000000;
+	}
+
+	if (on)
+		set_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+	else
+		clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+
+	return wx->ptp_setup_sdp(wx);
+}
+
+void wx_ptp_check_pps_event(struct wx *wx)
+{
+	u32 tsauxc, int_status;
+
+	/* this check is necessary in case the interrupt was enabled via some
+	 * alternative means (ex. debug_fs). Better to check here than
+	 * everywhere that calls this function.
+	 */
+	if (!wx->ptp_clock)
+		return;
+
+	int_status = rd32ptp(wx, WX_TSC_1588_INT_ST);
+	if (int_status & WX_TSC_1588_INT_ST_TT1) {
+		/* disable the pin first */
+		wr32ptp(wx, WX_TSC_1588_AUX_CTL, 0);
+		WX_WRITE_FLUSH(wx);
+
+		wx_ptp_trigger_calc(wx);
+
+		tsauxc = WX_TSC_1588_AUX_CTL_PLSG | WX_TSC_1588_AUX_CTL_EN_TT0 |
+			 WX_TSC_1588_AUX_CTL_EN_TT1 | WX_TSC_1588_AUX_CTL_EN_TS0;
+		wr32ptp(wx, WX_TSC_1588_TRGT_L(0), (u32)wx->pps_edge_start);
+		wr32ptp(wx, WX_TSC_1588_TRGT_H(0), (u32)(wx->pps_edge_start >> 32));
+		wr32ptp(wx, WX_TSC_1588_TRGT_L(1), (u32)wx->pps_edge_end);
+		wr32ptp(wx, WX_TSC_1588_TRGT_H(1), (u32)(wx->pps_edge_end >> 32));
+		wr32ptp(wx, WX_TSC_1588_AUX_CTL, tsauxc);
+		WX_WRITE_FLUSH(wx);
+	}
+}
+EXPORT_SYMBOL(wx_ptp_check_pps_event);
+
 static long wx_ptp_create_clock(struct wx *wx)
 {
 	struct net_device *netdev = wx->netdev;
@@ -338,17 +498,22 @@ static long wx_ptp_create_clock(struct wx *wx)
 	wx->ptp_caps.owner = THIS_MODULE;
 	wx->ptp_caps.n_alarm = 0;
 	wx->ptp_caps.n_ext_ts = 0;
-	wx->ptp_caps.n_per_out = 0;
 	wx->ptp_caps.pps = 0;
 	wx->ptp_caps.adjfine = wx_ptp_adjfine;
 	wx->ptp_caps.adjtime = wx_ptp_adjtime;
 	wx->ptp_caps.gettimex64 = wx_ptp_gettimex64;
 	wx->ptp_caps.settime64 = wx_ptp_settime64;
 	wx->ptp_caps.do_aux_work = wx_ptp_do_aux_work;
-	if (wx->mac.type == wx_mac_em)
+	if (wx->mac.type == wx_mac_em) {
 		wx->ptp_caps.max_adj = 500000000;
-	else
+		wx->ptp_caps.n_per_out = 1;
+		wx->ptp_setup_sdp = wx_ptp_setup_sdp;
+		wx->ptp_caps.enable = wx_ptp_feature_enable;
+	} else {
 		wx->ptp_caps.max_adj = 250000000;
+		wx->ptp_caps.n_per_out = 0;
+		wx->ptp_setup_sdp = NULL;
+	}
 
 	wx->ptp_clock = ptp_clock_register(&wx->ptp_caps, &wx->pdev->dev);
 	if (IS_ERR(wx->ptp_clock)) {
@@ -580,6 +745,12 @@ void wx_ptp_reset(struct wx *wx)
 
 	wx->last_overflow_check = jiffies;
 	ptp_schedule_worker(wx->ptp_clock, HZ);
+
+	/* Now that the shift has been calculated and the systime
+	 * registers reset, (re-)enable the Clock out feature
+	 */
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
 }
 EXPORT_SYMBOL(wx_ptp_reset);
 
@@ -620,6 +791,10 @@ void wx_ptp_suspend(struct wx *wx)
 	if (!test_and_clear_bit(WX_STATE_PTP_RUNNING, wx->state))
 		return;
 
+	clear_bit(WX_FLAG_PTP_PPS_ENABLED, wx->flags);
+	if (wx->ptp_setup_sdp)
+		wx->ptp_setup_sdp(wx);
+
 	wx_ptp_clear_tx_timestamp(wx);
 }
 EXPORT_SYMBOL(wx_ptp_suspend);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.h b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
index 8742d27973636..50db90a6e3ee6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.h
@@ -4,6 +4,7 @@
 #ifndef _WX_PTP_H_
 #define _WX_PTP_H_
 
+void wx_ptp_check_pps_event(struct wx *wx);
 void wx_ptp_reset_cyclecounter(struct wx *wx);
 void wx_ptp_reset(struct wx *wx);
 void wx_ptp_init(struct wx *wx);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 0fabfa90d4e71..db446e690dc7e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -281,6 +281,23 @@
 #define WX_TSC_1588_SYSTIML          0x11F0C
 #define WX_TSC_1588_SYSTIMH          0x11F10
 #define WX_TSC_1588_INC              0x11F14
+#define WX_TSC_1588_INT_ST           0x11F20
+#define WX_TSC_1588_INT_ST_TT1       BIT(5)
+#define WX_TSC_1588_INT_EN           0x11F24
+#define WX_TSC_1588_INT_EN_TT1       BIT(5)
+#define WX_TSC_1588_AUX_CTL          0x11F28
+#define WX_TSC_1588_AUX_CTL_EN_TS0   BIT(8)
+#define WX_TSC_1588_AUX_CTL_EN_TT1   BIT(2)
+#define WX_TSC_1588_AUX_CTL_PLSG     BIT(1)
+#define WX_TSC_1588_AUX_CTL_EN_TT0   BIT(0)
+#define WX_TSC_1588_TRGT_L(i)        (0x11F2C + ((i) * 8)) /* [0,1] */
+#define WX_TSC_1588_TRGT_H(i)        (0x11F30 + ((i) * 8)) /* [0,1] */
+#define WX_TSC_1588_SDP(i)           (0x11F5C + ((i) * 4)) /* [0,3] */
+#define WX_TSC_1588_SDP_OUT_LEVEL_H  FIELD_PREP(BIT(4), 0)
+#define WX_TSC_1588_SDP_OUT_LEVEL_L  FIELD_PREP(BIT(4), 1)
+#define WX_TSC_1588_SDP_FUN_SEL_MASK GENMASK(2, 0)
+#define WX_TSC_1588_SDP_FUN_SEL_TT0  FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 1)
+#define WX_TSC_1588_SDP_FUN_SEL_TS0  FIELD_PREP(WX_TSC_1588_SDP_FUN_SEL_MASK, 5)
 
 /************************************** MNG ********************************/
 #define WX_MNG_SWFW_SYNC             0x1E008
@@ -410,6 +427,8 @@ enum WX_MSCA_CMD_value {
 #define FW_CEM_CMD_RESERVED          0X0
 #define FW_CEM_MAX_RETRIES           3
 #define FW_CEM_RESP_STATUS_SUCCESS   0x1
+#define FW_PPS_SET_CMD               0xF6
+#define FW_PPS_SET_LEN               0x14
 
 #define WX_SW_REGION_PTR             0x1C
 
@@ -730,6 +749,15 @@ struct wx_hic_reset {
 	u16 reset_type;
 };
 
+struct wx_hic_set_pps {
+	struct wx_hic_hdr hdr;
+	u8 lan_id;
+	u8 enable;
+	u16 pad2;
+	u64 nsec;
+	u64 cycles;
+};
+
 /* Bus parameters */
 struct wx_bus_info {
 	u8 func;
@@ -1068,6 +1096,7 @@ enum wx_pf_flags {
 	WX_FLAG_FDIR_PERFECT,
 	WX_FLAG_RX_HWTSTAMP_ENABLED,
 	WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
+	WX_FLAG_PTP_PPS_ENABLED,
 	WX_PF_FLAGS_NBITS               /* must be last */
 };
 
@@ -1168,7 +1197,13 @@ struct wx {
 	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);
 	void (*configure_fdir)(struct wx *wx);
 	void (*do_reset)(struct net_device *netdev);
+	int (*ptp_setup_sdp)(struct wx *wx);
 
+	bool pps_enabled;
+	u64 pps_width;
+	u64 pps_edge_start;
+	u64 pps_edge_end;
+	u64 sec_to_cc;
 	u32 base_incval;
 	u32 tx_hwtstamp_pkts;
 	u32 tx_hwtstamp_timeouts;
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index c60a96cc35086..a6159214ec0a9 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -168,7 +168,7 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	struct wx_q_vector *q_vector;
 	struct wx *wx  = data;
 	struct pci_dev *pdev;
-	u32 eicr;
+	u32 eicr, eicr_misc;
 
 	q_vector = wx->q_vector[0];
 	pdev = wx->pdev;
@@ -186,6 +186,10 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	if (!(pdev->msi_enabled))
 		wr32(wx, WX_PX_INTA, 1);
 
+	eicr_misc = wx_misc_isb(wx, WX_ISB_MISC);
+	if (unlikely(eicr_misc & NGBE_PX_MISC_IC_TIMESYNC))
+		wx_ptp_check_pps_event(wx);
+
 	wx->isb_mem[WX_ISB_MISC] = 0;
 	/* would disable interrupts here but it is auto disabled */
 	napi_schedule_irqoff(&q_vector->napi);
@@ -199,6 +203,12 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
 {
 	struct wx *wx = data;
+	u32 eicr;
+
+	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+
+	if (unlikely(eicr & NGBE_PX_MISC_IC_TIMESYNC))
+		wx_ptp_check_pps_event(wx);
 
 	/* re-enable the original interrupt state, no lsc, no queues */
 	if (netif_running(wx->netdev))
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index f48ed7fc1805a..992adbb98c7d1 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -70,15 +70,20 @@
 
 /* Extended Interrupt Enable Set */
 #define NGBE_PX_MISC_IEN_DEV_RST		BIT(10)
+#define NGBE_PX_MISC_IEN_TIMESYNC		BIT(11)
 #define NGBE_PX_MISC_IEN_ETH_LK			BIT(18)
 #define NGBE_PX_MISC_IEN_INT_ERR		BIT(20)
 #define NGBE_PX_MISC_IEN_GPIO			BIT(26)
 #define NGBE_PX_MISC_IEN_MASK ( \
 				NGBE_PX_MISC_IEN_DEV_RST | \
+				NGBE_PX_MISC_IEN_TIMESYNC | \
 				NGBE_PX_MISC_IEN_ETH_LK | \
 				NGBE_PX_MISC_IEN_INT_ERR | \
 				NGBE_PX_MISC_IEN_GPIO)
 
+/* Extended Interrupt Cause Read */
+#define NGBE_PX_MISC_IC_TIMESYNC		BIT(11) /* time sync */
+
 #define NGBE_INTR_ALL				0x1FF
 #define NGBE_INTR_MISC				BIT(0)
 

From 7b5b7a597fbc19dacf6eefba3dd632a149a539b8 Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Mon, 17 Feb 2025 18:35:20 -0800
Subject: [PATCH 0888/2753] eth: fbnic: Add ethtool support for IRQ coalescing

Add ethtool support to configure the IRQ coalescing behavior. Support
separate timers for Rx and Tx for time based coalescing. For frame based
configuration, currently we only support the Rx side.

The hardware allows configuration of descriptor count instead of frame
count requiring conversion between the two. We assume 2 descriptors
per frame, one for the metadata and one for the data segment.

When rx-frames are not configured, we set the RX descriptor count to
half the ring size as a fail safe.

Default configuration:
ethtool -c eth0 | grep -E "rx-usecs:|tx-usecs:|rx-frames:"
rx-usecs:       30
rx-frames:      0
tx-usecs:       35

IRQ rate test:
With single iperf flow we monitor IRQ rate while changing the tx-usesc and
rx-usecs to high and low values.

ethtool -C eth0 rx-frames 8192 rx-usecs 150 tx-usecs 150
irq/sec   13k
irq/sec   14k
irq/sec   14k

ethtool -C eth0 rx-frames 8192 rx-usecs 10 tx-usecs 10
irq/sec  27k
irq/sec  28k
irq/sec  28k

Validating the use of extack:
ethtool -C eth0 rx-frames 16384
netlink error: fbnic: rx_frames is above device max
netlink error: Invalid argument

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250218023520.2038010-1-mohsin.bashr@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic.h       |  3 +
 .../net/ethernet/meta/fbnic/fbnic_ethtool.c   | 60 +++++++++++++++++++
 .../net/ethernet/meta/fbnic/fbnic_netdev.c    |  4 ++
 .../net/ethernet/meta/fbnic/fbnic_netdev.h    |  6 ++
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c  | 53 +++++++++++++---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h  |  3 +
 6 files changed, 121 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 37f81db1fc301..4ca7b99ef1315 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -186,6 +186,9 @@ void fbnic_dbg_exit(void);
 void fbnic_csr_get_regs(struct fbnic_dev *fbd, u32 *data, u32 *regs_version);
 int fbnic_csr_regs_len(struct fbnic_dev *fbd);
 
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm);
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv);
+
 enum fbnic_boards {
 	fbnic_board_asic
 };
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index fb7139a1da465..c1477aad98a00 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -136,6 +136,61 @@ static void fbnic_clone_free(struct fbnic_net *clone)
 	kfree(clone);
 }
 
+static int fbnic_get_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ec->tx_coalesce_usecs = fbn->tx_usecs;
+	ec->rx_coalesce_usecs = fbn->rx_usecs;
+	ec->rx_max_coalesced_frames = fbn->rx_max_frames;
+
+	return 0;
+}
+
+static int fbnic_set_coalesce(struct net_device *netdev,
+			      struct ethtool_coalesce *ec,
+			      struct kernel_ethtool_coalesce *kernel_coal,
+			      struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	/* Verify against hardware limits */
+	if (ec->rx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->tx_coalesce_usecs > FIELD_MAX(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT)) {
+		NL_SET_ERR_MSG_MOD(extack, "tx_usecs is above device max");
+		return -EINVAL;
+	}
+	if (ec->rx_max_coalesced_frames >
+	    FIELD_MAX(FBNIC_QUEUE_RIM_THRESHOLD_RCD_MASK) /
+	    FBNIC_MIN_RXD_PER_FRAME) {
+		NL_SET_ERR_MSG_MOD(extack, "rx_frames is above device max");
+		return -EINVAL;
+	}
+
+	fbn->tx_usecs = ec->tx_coalesce_usecs;
+	fbn->rx_usecs = ec->rx_coalesce_usecs;
+	fbn->rx_max_frames = ec->rx_max_coalesced_frames;
+
+	if (netif_running(netdev)) {
+		int i;
+
+		for (i = 0; i < fbn->num_napi; i++) {
+			struct fbnic_napi_vector *nv = fbn->napi[i];
+
+			fbnic_config_txrx_usecs(nv, 0);
+			fbnic_config_rx_frames(nv);
+		}
+	}
+
+	return 0;
+}
+
 static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
 {
 	int i;
@@ -1287,10 +1342,15 @@ fbnic_get_eth_mac_stats(struct net_device *netdev,
 }
 
 static const struct ethtool_ops fbnic_ethtool_ops = {
+	.supported_coalesce_params	=
+				  ETHTOOL_COALESCE_USECS |
+				  ETHTOOL_COALESCE_RX_MAX_FRAMES,
 	.rxfh_max_num_contexts	= FBNIC_RPC_RSS_TBL_COUNT,
 	.get_drvinfo		= fbnic_get_drvinfo,
 	.get_regs_len		= fbnic_get_regs_len,
 	.get_regs		= fbnic_get_regs,
+	.get_coalesce		= fbnic_get_coalesce,
+	.set_coalesce		= fbnic_set_coalesce,
 	.get_strings		= fbnic_get_strings,
 	.get_ethtool_stats	= fbnic_get_ethtool_stats,
 	.get_sset_count		= fbnic_get_sset_count,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index c59f1ce8de324..cf8feb90b6174 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -641,6 +641,10 @@ struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 	fbn->ppq_size = FBNIC_PPQ_SIZE_DEFAULT;
 	fbn->rcq_size = FBNIC_RCQ_SIZE_DEFAULT;
 
+	fbn->tx_usecs = FBNIC_TX_USECS_DEFAULT;
+	fbn->rx_usecs = FBNIC_RX_USECS_DEFAULT;
+	fbn->rx_max_frames = FBNIC_RX_FRAMES_DEFAULT;
+
 	default_queues = netif_get_num_default_rss_queues();
 	if (default_queues > fbd->max_num_queues)
 		default_queues = fbd->max_num_queues;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
index b84b447a8d8ad..561837e80ec80 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.h
@@ -12,6 +12,7 @@
 #include "fbnic_txrx.h"
 
 #define FBNIC_MAX_NAPI_VECTORS		128u
+#define FBNIC_MIN_RXD_PER_FRAME		2
 
 /* Natively supported tunnel GSO features (not thru GSO_PARTIAL) */
 #define FBNIC_TUN_GSO_FEATURES		NETIF_F_GSO_IPXIP6
@@ -30,6 +31,11 @@ struct fbnic_net {
 	u32 ppq_size;
 	u32 rcq_size;
 
+	u16 rx_usecs;
+	u16 tx_usecs;
+
+	u32 rx_max_frames;
+
 	u16 num_napi;
 
 	struct phylink *phylink;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index b2e544a66de32..aba4c65974eea 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -2184,9 +2184,51 @@ static void fbnic_config_drop_mode_rcq(struct fbnic_napi_vector *nv,
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RDE_CTL0, rcq_ctl);
 }
 
+static void fbnic_config_rim_threshold(struct fbnic_ring *rcq, u16 nv_idx, u32 rx_desc)
+{
+	u32 threshold;
+
+	/* Set the threhsold to half the ring size if rx_frames
+	 * is not configured
+	 */
+	threshold = rx_desc ? : rcq->size_mask / 2;
+
+	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv_idx);
+	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, threshold);
+}
+
+void fbnic_config_txrx_usecs(struct fbnic_napi_vector *nv, u32 arm)
+{
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
+	struct fbnic_dev *fbd = nv->fbd;
+	u32 val = arm;
+
+	val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT, fbn->rx_usecs) |
+	       FBNIC_INTR_CQ_REARM_RCQ_TIMEOUT_UPD_EN;
+	val |= FIELD_PREP(FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT, fbn->tx_usecs) |
+	       FBNIC_INTR_CQ_REARM_TCQ_TIMEOUT_UPD_EN;
+
+	fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val);
+}
+
+void fbnic_config_rx_frames(struct fbnic_napi_vector *nv)
+{
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
+	int i;
+
+	for (i = nv->txt_count; i < nv->rxt_count + nv->txt_count; i++) {
+		struct fbnic_q_triad *qt = &nv->qt[i];
+
+		fbnic_config_rim_threshold(&qt->cmpl, nv->v_idx,
+					   fbn->rx_max_frames *
+					   FBNIC_MIN_RXD_PER_FRAME);
+	}
+}
+
 static void fbnic_enable_rcq(struct fbnic_napi_vector *nv,
 			     struct fbnic_ring *rcq)
 {
+	struct fbnic_net *fbn = netdev_priv(nv->napi.dev);
 	u32 log_size = fls(rcq->size_mask);
 	u32 rcq_ctl;
 
@@ -2214,8 +2256,8 @@ static void fbnic_enable_rcq(struct fbnic_napi_vector *nv,
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RCQ_SIZE, log_size & 0xf);
 
 	/* Store interrupt information for the completion queue */
-	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_CTL, nv->v_idx);
-	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_THRESHOLD, rcq->size_mask / 2);
+	fbnic_config_rim_threshold(rcq, nv->v_idx, fbn->rx_max_frames *
+						   FBNIC_MIN_RXD_PER_FRAME);
 	fbnic_ring_wr32(rcq, FBNIC_QUEUE_RIM_MASK, 0);
 
 	/* Enable queue */
@@ -2254,12 +2296,7 @@ void fbnic_enable(struct fbnic_net *fbn)
 
 static void fbnic_nv_irq_enable(struct fbnic_napi_vector *nv)
 {
-	struct fbnic_dev *fbd = nv->fbd;
-	u32 val;
-
-	val = FBNIC_INTR_CQ_REARM_INTR_UNMASK;
-
-	fbnic_wr32(fbd, FBNIC_INTR_CQ_REARM(nv->v_idx), val);
+	fbnic_config_txrx_usecs(nv, FBNIC_INTR_CQ_REARM_INTR_UNMASK);
 }
 
 void fbnic_napi_enable(struct fbnic_net *fbn)
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 89a5c394f8463..54368dc22328d 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -31,6 +31,9 @@ struct fbnic_net;
 #define FBNIC_HPQ_SIZE_DEFAULT		256
 #define FBNIC_PPQ_SIZE_DEFAULT		256
 #define FBNIC_RCQ_SIZE_DEFAULT		1024
+#define FBNIC_TX_USECS_DEFAULT		35
+#define FBNIC_RX_USECS_DEFAULT		30
+#define FBNIC_RX_FRAMES_DEFAULT		0
 
 #define FBNIC_RX_TROOM \
 	SKB_DATA_ALIGN(sizeof(struct skb_shared_info))

From ca4419f15abd19ba8be1e109661b60f9f5b6c9f0 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Sun, 16 Feb 2025 17:34:26 +0800
Subject: [PATCH 0889/2753] xsk: Add launch time hardware offload support to
 XDP Tx metadata

Extend the XDP Tx metadata framework so that user can requests launch time
hardware offload, where the Ethernet device will schedule the packet for
transmission at a pre-determined time called launch time. The value of
launch time is communicated from user space to Ethernet driver via
launch_time field of struct xsk_tx_metadata.

Suggested-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250216093430.957880-2-yoong.siang.song@intel.com
---
 Documentation/netlink/specs/netdev.yaml      |  4 ++
 Documentation/networking/xsk-tx-metadata.rst | 62 ++++++++++++++++++++
 include/net/xdp_sock.h                       | 10 ++++
 include/net/xdp_sock_drv.h                   |  1 +
 include/uapi/linux/if_xdp.h                  | 10 ++++
 include/uapi/linux/netdev.h                  |  3 +
 net/core/netdev-genl.c                       |  2 +
 net/xdp/xsk.c                                |  3 +
 tools/include/uapi/linux/if_xdp.h            | 10 ++++
 tools/include/uapi/linux/netdev.h            |  3 +
 10 files changed, 108 insertions(+)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 288923e965aed..5f6f84630b16e 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -70,6 +70,10 @@ definitions:
         name: tx-checksum
         doc:
           L3 checksum HW offload is supported by the driver.
+      -
+        name: tx-launch-time-fifo
+        doc:
+          Launch time HW offload is supported by the driver.
   -
     name: queue-type
     type: enum
diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
index e76b0cfc32f7d..df53a10ccac34 100644
--- a/Documentation/networking/xsk-tx-metadata.rst
+++ b/Documentation/networking/xsk-tx-metadata.rst
@@ -50,6 +50,10 @@ The flags field enables the particular offload:
   checksum. ``csum_start`` specifies byte offset of where the checksumming
   should start and ``csum_offset`` specifies byte offset where the
   device should store the computed checksum.
+- ``XDP_TXMD_FLAGS_LAUNCH_TIME``: requests the device to schedule the
+  packet for transmission at a pre-determined time called launch time. The
+  value of launch time is indicated by ``launch_time`` field of
+  ``union xsk_tx_metadata``.
 
 Besides the flags above, in order to trigger the offloads, the first
 packet's ``struct xdp_desc`` descriptor should set ``XDP_TX_METADATA``
@@ -65,6 +69,63 @@ In this case, when running in ``XDK_COPY`` mode, the TX checksum
 is calculated on the CPU. Do not enable this option in production because
 it will negatively affect performance.
 
+Launch Time
+===========
+
+The value of the requested launch time should be based on the device's PTP
+Hardware Clock (PHC) to ensure accuracy. AF_XDP takes a different data path
+compared to the ETF queuing discipline, which organizes packets and delays
+their transmission. Instead, AF_XDP immediately hands off the packets to
+the device driver without rearranging their order or holding them prior to
+transmission. Since the driver maintains FIFO behavior and does not perform
+packet reordering, a packet with a launch time request will block other
+packets in the same Tx Queue until it is sent. Therefore, it is recommended
+to allocate separate queue for scheduling traffic that is intended for
+future transmission.
+
+In scenarios where the launch time offload feature is disabled, the device
+driver is expected to disregard the launch time request. For correct
+interpretation and meaningful operation, the launch time should never be
+set to a value larger than the farthest programmable time in the future
+(the horizon). Different devices have different hardware limitations on the
+launch time offload feature.
+
+stmmac driver
+-------------
+
+For stmmac, TSO and launch time (TBS) features are mutually exclusive for
+each individual Tx Queue. By default, the driver configures Tx Queue 0 to
+support TSO and the rest of the Tx Queues to support TBS. The launch time
+hardware offload feature can be enabled or disabled by using the tc-etf
+command to call the driver's ndo_setup_tc() callback.
+
+The value of the launch time that is programmed in the Enhanced Normal
+Transmit Descriptors is a 32-bit value, where the most significant 8 bits
+represent the time in seconds and the remaining 24 bits represent the time
+in 256 ns increments. The programmed launch time is compared against the
+PTP time (bits[39:8]) and rolls over after 256 seconds. Therefore, the
+horizon of the launch time for dwmac4 and dwxlgmac2 is 128 seconds in the
+future.
+
+igc driver
+----------
+
+For igc, all four Tx Queues support the launch time feature. The launch
+time hardware offload feature can be enabled or disabled by using the
+tc-etf command to call the driver's ndo_setup_tc() callback. When entering
+TSN mode, the igc driver will reset the device and create a default Qbv
+schedule with a 1-second cycle time, with all Tx Queues open at all times.
+
+The value of the launch time that is programmed in the Advanced Transmit
+Context Descriptor is a relative offset to the starting time of the Qbv
+transmission window of the queue. The Frst flag of the descriptor can be
+set to schedule the packet for the next Qbv cycle. Therefore, the horizon
+of the launch time for i225 and i226 is the ending time of the next cycle
+of the Qbv transmission window of the queue. For example, when the Qbv
+cycle time is set to 1 second, the horizon of the launch time ranges
+from 1 second to 2 seconds, depending on where the Qbv cycle is currently
+running.
+
 Querying Device Capabilities
 ============================
 
@@ -74,6 +135,7 @@ Refer to ``xsk-flags`` features bitmask in
 
 - ``tx-timestamp``: device supports ``XDP_TXMD_FLAGS_TIMESTAMP``
 - ``tx-checksum``: device supports ``XDP_TXMD_FLAGS_CHECKSUM``
+- ``tx-launch-time-fifo``: device supports ``XDP_TXMD_FLAGS_LAUNCH_TIME``
 
 See ``tools/net/ynl/samples/netdev.c`` on how to query this information.
 
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index bfe625b55d55d..a58ae7589d121 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -110,11 +110,16 @@ struct xdp_sock {
  *     indicates position where checksumming should start.
  *     csum_offset indicates position where checksum should be stored.
  *
+ * void (*tmo_request_launch_time)(u64 launch_time, void *priv)
+ *     Called when AF_XDP frame requested launch time HW offload support.
+ *     launch_time indicates the PTP time at which the device can schedule the
+ *     packet for transmission.
  */
 struct xsk_tx_metadata_ops {
 	void	(*tmo_request_timestamp)(void *priv);
 	u64	(*tmo_fill_timestamp)(void *priv);
 	void	(*tmo_request_checksum)(u16 csum_start, u16 csum_offset, void *priv);
+	void	(*tmo_request_launch_time)(u64 launch_time, void *priv);
 };
 
 #ifdef CONFIG_XDP_SOCKETS
@@ -162,6 +167,11 @@ static inline void xsk_tx_metadata_request(const struct xsk_tx_metadata *meta,
 	if (!meta)
 		return;
 
+	if (ops->tmo_request_launch_time)
+		if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+			ops->tmo_request_launch_time(meta->request.launch_time,
+						     priv);
+
 	if (ops->tmo_request_timestamp)
 		if (meta->flags & XDP_TXMD_FLAGS_TIMESTAMP)
 			ops->tmo_request_timestamp(priv);
diff --git a/include/net/xdp_sock_drv.h b/include/net/xdp_sock_drv.h
index 15086dcf51d85..513c8e9704f65 100644
--- a/include/net/xdp_sock_drv.h
+++ b/include/net/xdp_sock_drv.h
@@ -216,6 +216,7 @@ xsk_buff_raw_get_ctx(const struct xsk_buff_pool *pool, u64 addr)
 #define XDP_TXMD_FLAGS_VALID ( \
 		XDP_TXMD_FLAGS_TIMESTAMP | \
 		XDP_TXMD_FLAGS_CHECKSUM | \
+		XDP_TXMD_FLAGS_LAUNCH_TIME | \
 	0)
 
 static inline bool
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index 42ec5ddaab8dc..42869770776ec 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -127,6 +127,12 @@ struct xdp_options {
  */
 #define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
 
+/* Request launch time hardware offload. The device will schedule the packet for
+ * transmission at a pre-determined time called launch time. The value of
+ * launch time is communicated via launch_time field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_LAUNCH_TIME		(1 << 2)
+
 /* AF_XDP offloads request. 'request' union member is consumed by the driver
  * when the packet is being transmitted. 'completion' union member is
  * filled by the driver when the transmit completion arrives.
@@ -142,6 +148,10 @@ struct xsk_tx_metadata {
 			__u16 csum_start;
 			/* Offset from csum_start where checksum should be stored. */
 			__u16 csum_offset;
+
+			/* XDP_TXMD_FLAGS_LAUNCH_TIME */
+			/* Launch time in nanosecond against the PTP HW Clock */
+			__u64 launch_time;
 		} request;
 
 		struct {
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 6c6ee183802d3..b97ff8bbb0c67 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -59,10 +59,13 @@ enum netdev_xdp_rx_metadata {
  *   by the driver.
  * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
  *   driver.
+ * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported
+ *   by the driver.
  */
 enum netdev_xsk_flags {
 	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
 	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+	NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4,
 };
 
 enum netdev_queue_type {
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index c18bb53d13fd8..55bb58d623ace 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -53,6 +53,8 @@ XDP_METADATA_KFUNC_xxx
 			xsk_features |= NETDEV_XSK_FLAGS_TX_TIMESTAMP;
 		if (netdev->xsk_tx_metadata_ops->tmo_request_checksum)
 			xsk_features |= NETDEV_XSK_FLAGS_TX_CHECKSUM;
+		if (netdev->xsk_tx_metadata_ops->tmo_request_launch_time)
+			xsk_features |= NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO;
 	}
 
 	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 89d2bef964698..41093ea63700c 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -742,6 +742,9 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs,
 						goto free_err;
 				}
 			}
+
+			if (meta->flags & XDP_TXMD_FLAGS_LAUNCH_TIME)
+				skb->skb_mstamp_ns = meta->request.launch_time;
 		}
 	}
 
diff --git a/tools/include/uapi/linux/if_xdp.h b/tools/include/uapi/linux/if_xdp.h
index 42ec5ddaab8dc..42869770776ec 100644
--- a/tools/include/uapi/linux/if_xdp.h
+++ b/tools/include/uapi/linux/if_xdp.h
@@ -127,6 +127,12 @@ struct xdp_options {
  */
 #define XDP_TXMD_FLAGS_CHECKSUM			(1 << 1)
 
+/* Request launch time hardware offload. The device will schedule the packet for
+ * transmission at a pre-determined time called launch time. The value of
+ * launch time is communicated via launch_time field of struct xsk_tx_metadata.
+ */
+#define XDP_TXMD_FLAGS_LAUNCH_TIME		(1 << 2)
+
 /* AF_XDP offloads request. 'request' union member is consumed by the driver
  * when the packet is being transmitted. 'completion' union member is
  * filled by the driver when the transmit completion arrives.
@@ -142,6 +148,10 @@ struct xsk_tx_metadata {
 			__u16 csum_start;
 			/* Offset from csum_start where checksum should be stored. */
 			__u16 csum_offset;
+
+			/* XDP_TXMD_FLAGS_LAUNCH_TIME */
+			/* Launch time in nanosecond against the PTP HW Clock */
+			__u64 launch_time;
 		} request;
 
 		struct {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 6c6ee183802d3..b97ff8bbb0c67 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -59,10 +59,13 @@ enum netdev_xdp_rx_metadata {
  *   by the driver.
  * @NETDEV_XSK_FLAGS_TX_CHECKSUM: L3 checksum HW offload is supported by the
  *   driver.
+ * @NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO: Launch time HW offload is supported
+ *   by the driver.
  */
 enum netdev_xsk_flags {
 	NETDEV_XSK_FLAGS_TX_TIMESTAMP = 1,
 	NETDEV_XSK_FLAGS_TX_CHECKSUM = 2,
+	NETDEV_XSK_FLAGS_TX_LAUNCH_TIME_FIFO = 4,
 };
 
 enum netdev_queue_type {

From 6164847e5403dd56ec06c36e22526747bce61b13 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Sun, 16 Feb 2025 17:34:27 +0800
Subject: [PATCH 0890/2753] selftests/bpf: Add launch time request to
 xdp_hw_metadata

Add launch time hardware offload request to xdp_hw_metadata. Users can
configure the delta of launch time relative to HW RX-time using the "-l"
argument. By default, the delta is set to 0 ns, which means the launch time
is disabled. By setting the delta to a non-zero value, the launch time
hardware offload feature will be enabled and requested. Additionally, users
can configure the Tx Queue to be enabled with the launch time hardware
offload using the "-L" argument. By default, Tx Queue 0 will be used.

Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250216093430.957880-3-yoong.siang.song@intel.com
---
 tools/testing/selftests/bpf/xdp_hw_metadata.c | 168 +++++++++++++++++-
 1 file changed, 163 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/bpf/xdp_hw_metadata.c b/tools/testing/selftests/bpf/xdp_hw_metadata.c
index 6f7b15d6c6ed2..3d8de0d4c96a7 100644
--- a/tools/testing/selftests/bpf/xdp_hw_metadata.c
+++ b/tools/testing/selftests/bpf/xdp_hw_metadata.c
@@ -13,6 +13,7 @@
  * - UDP 9091 packets trigger TX reply
  * - TX HW timestamp is requested and reported back upon completion
  * - TX checksum is requested
+ * - TX launch time HW offload is requested for transmission
  */
 
 #include <test_progs.h>
@@ -37,6 +38,15 @@
 #include <time.h>
 #include <unistd.h>
 #include <libgen.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <linux/pkt_sched.h>
+#include <linux/pkt_cls.h>
+#include <linux/ethtool.h>
+#include <sys/socket.h>
+#include <arpa/inet.h>
 
 #include "xdp_metadata.h"
 
@@ -64,6 +74,18 @@ int rxq;
 bool skip_tx;
 __u64 last_hw_rx_timestamp;
 __u64 last_xdp_rx_timestamp;
+__u64 last_launch_time;
+__u64 launch_time_delta_to_hw_rx_timestamp;
+int launch_time_queue;
+
+#define run_command(cmd, ...)					\
+({								\
+	char command[1024];					\
+	memset(command, 0, sizeof(command));			\
+	snprintf(command, sizeof(command), cmd, ##__VA_ARGS__);	\
+	fprintf(stderr, "Running: %s\n", command);		\
+	system(command);					\
+})
 
 void test__fail(void) { /* for network_helpers.c */ }
 
@@ -298,6 +320,12 @@ static bool complete_tx(struct xsk *xsk, clockid_t clock_id)
 	if (meta->completion.tx_timestamp) {
 		__u64 ref_tstamp = gettime(clock_id);
 
+		if (launch_time_delta_to_hw_rx_timestamp) {
+			print_tstamp_delta("HW Launch-time",
+					   "HW TX-complete-time",
+					   last_launch_time,
+					   meta->completion.tx_timestamp);
+		}
 		print_tstamp_delta("HW TX-complete-time", "User TX-complete-time",
 				   meta->completion.tx_timestamp, ref_tstamp);
 		print_tstamp_delta("XDP RX-time", "User TX-complete-time",
@@ -395,6 +423,17 @@ static void ping_pong(struct xsk *xsk, void *rx_packet, clockid_t clock_id)
 	       xsk, ntohs(udph->check), ntohs(want_csum),
 	       meta->request.csum_start, meta->request.csum_offset);
 
+	/* Set the value of launch time */
+	if (launch_time_delta_to_hw_rx_timestamp) {
+		meta->flags |= XDP_TXMD_FLAGS_LAUNCH_TIME;
+		meta->request.launch_time = last_hw_rx_timestamp +
+					    launch_time_delta_to_hw_rx_timestamp;
+		last_launch_time = meta->request.launch_time;
+		print_tstamp_delta("HW RX-time", "HW Launch-time",
+				   last_hw_rx_timestamp,
+				   meta->request.launch_time);
+	}
+
 	memcpy(data, rx_packet, len); /* don't share umem chunk for simplicity */
 	tx_desc->options |= XDP_TX_METADATA;
 	tx_desc->len = len;
@@ -407,6 +446,7 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 	const struct xdp_desc *rx_desc;
 	struct pollfd fds[rxq + 1];
 	__u64 comp_addr;
+	__u64 deadline;
 	__u64 addr;
 	__u32 idx = 0;
 	int ret;
@@ -477,9 +517,15 @@ static int verify_metadata(struct xsk *rx_xsk, int rxq, int server_fd, clockid_t
 					if (ret)
 						printf("kick_tx ret=%d\n", ret);
 
-					for (int j = 0; j < 500; j++) {
+					/* wait 1 second + cover launch time */
+					deadline = gettime(clock_id) +
+						   NANOSEC_PER_SEC +
+						   launch_time_delta_to_hw_rx_timestamp;
+					while (true) {
 						if (complete_tx(xsk, clock_id))
 							break;
+						if (gettime(clock_id) >= deadline)
+							break;
 						usleep(10);
 					}
 				}
@@ -608,6 +654,10 @@ static void print_usage(void)
 		"  -h    Display this help and exit\n\n"
 		"  -m    Enable multi-buffer XDP for larger MTU\n"
 		"  -r    Don't generate AF_XDP reply (rx metadata only)\n"
+		"  -l    Delta of launch time relative to HW RX-time in ns\n"
+		"        default: 0 ns (launch time request is disabled)\n"
+		"  -L    Tx Queue to be enabled with launch time offload\n"
+		"        default: 0 (Tx Queue 0)\n"
 		"Generate test packets on the other machine with:\n"
 		"  echo -n xdp | nc -u -q1 <dst_ip> 9091\n";
 
@@ -618,7 +668,7 @@ static void read_args(int argc, char *argv[])
 {
 	int opt;
 
-	while ((opt = getopt(argc, argv, "chmr")) != -1) {
+	while ((opt = getopt(argc, argv, "chmrl:L:")) != -1) {
 		switch (opt) {
 		case 'c':
 			bind_flags &= ~XDP_USE_NEED_WAKEUP;
@@ -634,6 +684,12 @@ static void read_args(int argc, char *argv[])
 		case 'r':
 			skip_tx = true;
 			break;
+		case 'l':
+			launch_time_delta_to_hw_rx_timestamp = atoll(optarg);
+			break;
+		case 'L':
+			launch_time_queue = atoll(optarg);
+			break;
 		case '?':
 			if (isprint(optopt))
 				fprintf(stderr, "Unknown option: -%c\n", optopt);
@@ -657,23 +713,118 @@ static void read_args(int argc, char *argv[])
 		error(-1, errno, "Invalid interface name");
 }
 
+void clean_existing_configurations(void)
+{
+	/* Check and delete root qdisc if exists */
+	if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc mqprio 8001:'", ifname) == 0)
+		run_command("sudo tc qdisc del dev %s root", ifname);
+
+	/* Check and delete ingress qdisc if exists */
+	if (run_command("sudo tc qdisc show dev %s | grep -q 'qdisc ingress ffff:'", ifname) == 0)
+		run_command("sudo tc qdisc del dev %s ingress", ifname);
+
+	/* Check and delete ethtool filters if any exist */
+	if (run_command("sudo ethtool -n %s | grep -q 'Filter:'", ifname) == 0) {
+		run_command("sudo ethtool -n %s | grep 'Filter:' | awk '{print $2}' | xargs -n1 sudo ethtool -N %s delete >&2",
+			    ifname, ifname);
+	}
+}
+
+#define MAX_TC 16
+
 int main(int argc, char *argv[])
 {
 	clockid_t clock_id = CLOCK_TAI;
+	struct bpf_program *prog;
 	int server_fd = -1;
+	size_t map_len = 0;
+	size_t que_len = 0;
+	char *buf = NULL;
+	char *map = NULL;
+	char *que = NULL;
+	char *tmp = NULL;
+	int tc = 0;
 	int ret;
 	int i;
 
-	struct bpf_program *prog;
-
 	read_args(argc, argv);
 
 	rxq = rxq_num(ifname);
-
 	printf("rxq: %d\n", rxq);
 
+	if (launch_time_queue >= rxq || launch_time_queue < 0)
+		error(1, 0, "Invalid launch_time_queue.");
+
+	clean_existing_configurations();
+	sleep(1);
+
+	/* Enable tx and rx hardware timestamping */
 	hwtstamp_enable(ifname);
 
+	/* Prepare priority to traffic class map for tc-mqprio */
+	for (i = 0; i < MAX_TC; i++) {
+		if (i < rxq)
+			tc = i;
+
+		if (asprintf(&buf, "%d ", tc) == -1) {
+			printf("Failed to malloc buf for tc map.\n");
+			goto free_mem;
+		}
+
+		map_len += strlen(buf);
+		tmp = realloc(map, map_len + 1);
+		if (!tmp) {
+			printf("Failed to realloc tc map.\n");
+			goto free_mem;
+		}
+		map = tmp;
+		strcat(map, buf);
+		free(buf);
+		buf = NULL;
+	}
+
+	/* Prepare traffic class to hardware queue map for tc-mqprio */
+	for (i = 0; i <= tc; i++) {
+		if (asprintf(&buf, "1@%d ", i) == -1) {
+			printf("Failed to malloc buf for tc queues.\n");
+			goto free_mem;
+		}
+
+		que_len += strlen(buf);
+		tmp = realloc(que, que_len + 1);
+		if (!tmp) {
+			printf("Failed to realloc tc queues.\n");
+			goto free_mem;
+		}
+		que = tmp;
+		strcat(que, buf);
+		free(buf);
+		buf = NULL;
+	}
+
+	/* Add mqprio qdisc */
+	run_command("sudo tc qdisc add dev %s handle 8001: parent root mqprio num_tc %d map %squeues %shw 0",
+		    ifname, tc + 1, map, que);
+
+	/* To test launch time, send UDP packet with VLAN priority 1 to port 9091 */
+	if (launch_time_delta_to_hw_rx_timestamp) {
+		/* Enable launch time hardware offload on launch_time_queue */
+		run_command("sudo tc qdisc replace dev %s parent 8001:%d etf offload clockid CLOCK_TAI delta 500000",
+			    ifname, launch_time_queue + 1);
+		sleep(1);
+
+		/* Route incoming packet with VLAN priority 1 into launch_time_queue */
+		if (run_command("sudo ethtool -N %s flow-type ether vlan 0x2000 vlan-mask 0x1FFF action %d",
+				ifname, launch_time_queue)) {
+			run_command("sudo tc qdisc add dev %s ingress", ifname);
+			run_command("sudo tc filter add dev %s parent ffff: protocol 802.1Q flower vlan_prio 1 hw_tc %d",
+				    ifname, launch_time_queue);
+		}
+
+		/* Enable VLAN tag stripping offload */
+		run_command("sudo ethtool -K %s rxvlan on", ifname);
+	}
+
 	rx_xsk = malloc(sizeof(struct xsk) * rxq);
 	if (!rx_xsk)
 		error(1, ENOMEM, "malloc");
@@ -733,4 +884,11 @@ int main(int argc, char *argv[])
 	cleanup();
 	if (ret)
 		error(1, -ret, "verify_metadata");
+
+	clean_existing_configurations();
+
+free_mem:
+	free(buf);
+	free(map);
+	free(que);
 }

From 04f64dea13640fb456422c171c0a68462665d638 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Sun, 16 Feb 2025 17:34:28 +0800
Subject: [PATCH 0891/2753] net: stmmac: Add launch time support to XDP ZC

Enable launch time (Time-Based Scheduling) support for XDP zero copy via
the XDP Tx metadata framework.

This patch has been tested with tools/testing/selftests/bpf/xdp_hw_metadata
on Intel Tiger Lake platform. Below are the test steps and result.

Test 1: Send a single packet with the launch time set to 1 s in the future.

Test steps:
1. On the DUT, start the xdp_hw_metadata selftest application:
   $ sudo ./xdp_hw_metadata enp0s30f4 -l 1000000000 -L 1

2. On the Link Partner, send a UDP packet with VLAN priority 1 to port 9091
   of the DUT.

Result:
When the launch time is set to 1 s in the future, the delta between the
launch time and the transmit hardware timestamp is 16.963 us, as shown in
printout of the xdp_hw_metadata application below.
  0x55b5864717a8: rx_desc[4]->addr=88100 addr=88100 comp_addr=88100 EoP
  No rx_hash, err=-95
  HW RX-time:   1734579065767717328 (sec:1734579065.7677)
                delta to User RX-time sec:0.0004 (375.624 usec)
  XDP RX-time:   1734579065768004454 (sec:1734579065.7680)
                 delta to User RX-time sec:0.0001 (88.498 usec)
  No rx_vlan_tci or rx_vlan_proto, err=-95
  0x55b5864717a8: ping-pong with csum=5619 (want 0000)
                  csum_start=34 csum_offset=6
  HW RX-time:   1734579065767717328 (sec:1734579065.7677)
                delta to HW Launch-time sec:1.0000 (1000000.000 usec)
  0x55b5864717a8: complete tx idx=4 addr=4018
  HW Launch-time:   1734579066767717328 (sec:1734579066.7677)
                    delta to HW TX-complete-time sec:0.0000 (16.963 usec)
  HW TX-complete-time:   1734579066767734291 (sec:1734579066.7677)
                         delta to User TX-complete-time sec:0.0001
                         (130.408 usec)
  XDP RX-time:   1734579065768004454 (sec:1734579065.7680)
                 delta to User TX-complete-time sec:0.9999
                (999860.245 usec)
  HW RX-time:   1734579065767717328 (sec:1734579065.7677)
                delta to HW TX-complete-time sec:1.0000 (1000016.963 usec)
  0x55b5864717a8: complete rx idx=132 addr=88100

Test 2: Send 1000 packets with a 10 ms interval and the launch time set to
        500 us in the future.

Test steps:
1. On the DUT, start the xdp_hw_metadata selftest application:
   $ sudo chrt -f 99 ./xdp_hw_metadata enp0s30f4 -l 500000 -L 1 > \
     /dev/shm/result.log

2. On the Link Partner, send 1000 UDP packets with a 10 ms interval and
   VLAN priority 1 to port 9091 of the DUT.

Result:
When the launch time is set to 500 us in the future, the average delta
between the launch time and the transmit hardware timestamp is 13.854 us,
as shown in the analysis of /dev/shm/result.log below. The XDP launch time
works correctly in sending 1000 packets continuously.
  Min delta: 08.410 us
  Avr delta: 13.854 us
  Max delta: 17.076 us
  Total packets forwarded: 1000

Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250216093430.957880-4-yoong.siang.song@intel.com
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      |  2 ++
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 +++++++++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index f05cae103d836..925d8b97a42bb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -106,6 +106,8 @@ struct stmmac_metadata_request {
 	struct stmmac_priv *priv;
 	struct dma_desc *tx_desc;
 	bool *set_ic;
+	struct dma_edesc *edesc;
+	int tbs;
 };
 
 struct stmmac_xsk_tx_complete {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index d99ff4146512d..61ff545b74e33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -2491,9 +2491,20 @@ static u64 stmmac_xsk_fill_timestamp(void *_priv)
 	return 0;
 }
 
+static void stmmac_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct timespec64 ts = ns_to_timespec64(launch_time);
+	struct stmmac_metadata_request *meta_req = _priv;
+
+	if (meta_req->tbs & STMMAC_TBS_EN)
+		stmmac_set_desc_tbs(meta_req->priv, meta_req->edesc, ts.tv_sec,
+				    ts.tv_nsec);
+}
+
 static const struct xsk_tx_metadata_ops stmmac_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= stmmac_xsk_request_timestamp,
 	.tmo_fill_timestamp		= stmmac_xsk_fill_timestamp,
+	.tmo_request_launch_time	= stmmac_xsk_request_launch_time,
 };
 
 static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
@@ -2577,6 +2588,8 @@ static bool stmmac_xdp_xmit_zc(struct stmmac_priv *priv, u32 queue, u32 budget)
 		meta_req.priv = priv;
 		meta_req.tx_desc = tx_desc;
 		meta_req.set_ic = &set_ic;
+		meta_req.tbs = tx_q->tbs;
+		meta_req.edesc = &tx_q->dma_entx[entry];
 		xsk_tx_metadata_request(meta, &stmmac_xsk_tx_metadata_ops,
 					&meta_req);
 		if (set_ic) {

From f9b53bb13923f0a6ed2e784a35301cfb4c28f4f4 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Sun, 16 Feb 2025 17:34:29 +0800
Subject: [PATCH 0892/2753] igc: Refactor empty frame insertion for launch time
 support

Refactor the code for inserting an empty frame into a new function
igc_insert_empty_frame(). This change extracts the logic for inserting
an empty packet from igc_xmit_frame_ring() into a separate function,
allowing it to be reused in future implementations, such as the XDP
zero copy transmit function.

Remove the igc_desc_unused() checking in igc_init_tx_empty_descriptor()
because the number of descriptors needed is guaranteed.

Ensure that skb allocation and DMA mapping work for the empty frame,
before proceeding to fill in igc_tx_buffer info, context descriptor,
and data descriptor.

Rate limit the error messages for skb allocation and DMA mapping failures.

Update the comment to indicate that the 2 descriptors needed by the empty
frame are already taken into consideration in igc_xmit_frame_ring().

Handle the case where the insertion of an empty frame fails and explain
the reason behind this handling.

Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Faizal Rahim <faizal.abdul.rahim@linux.intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250216093430.957880-5-yoong.siang.song@intel.com
---
 drivers/net/ethernet/intel/igc/igc_main.c | 82 ++++++++++++++---------
 1 file changed, 50 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 84307bb7313e0..1bfa71545e371 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1092,7 +1092,8 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 
 	dma = dma_map_single(ring->dev, skb->data, size, DMA_TO_DEVICE);
 	if (dma_mapping_error(ring->dev, dma)) {
-		netdev_err_once(ring->netdev, "Failed to map DMA for TX\n");
+		net_err_ratelimited("%s: DMA mapping error for empty frame\n",
+				    netdev_name(ring->netdev));
 		return -ENOMEM;
 	}
 
@@ -1108,20 +1109,12 @@ static int igc_init_empty_frame(struct igc_ring *ring,
 	return 0;
 }
 
-static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
-					struct sk_buff *skb,
-					struct igc_tx_buffer *first)
+static void igc_init_tx_empty_descriptor(struct igc_ring *ring,
+					 struct sk_buff *skb,
+					 struct igc_tx_buffer *first)
 {
 	union igc_adv_tx_desc *desc;
 	u32 cmd_type, olinfo_status;
-	int err;
-
-	if (!igc_desc_unused(ring))
-		return -EBUSY;
-
-	err = igc_init_empty_frame(ring, first, skb);
-	if (err)
-		return err;
 
 	cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
 		   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
@@ -1140,8 +1133,6 @@ static int igc_init_tx_empty_descriptor(struct igc_ring *ring,
 	ring->next_to_use++;
 	if (ring->next_to_use == ring->count)
 		ring->next_to_use = 0;
-
-	return 0;
 }
 
 #define IGC_EMPTY_FRAME_SIZE 60
@@ -1567,6 +1558,40 @@ static bool igc_request_tx_tstamp(struct igc_adapter *adapter, struct sk_buff *s
 	return false;
 }
 
+static int igc_insert_empty_frame(struct igc_ring *tx_ring)
+{
+	struct igc_tx_buffer *empty_info;
+	struct sk_buff *empty_skb;
+	void *data;
+	int ret;
+
+	empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
+	empty_skb = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
+	if (unlikely(!empty_skb)) {
+		net_err_ratelimited("%s: skb alloc error for empty frame\n",
+				    netdev_name(tx_ring->netdev));
+		return -ENOMEM;
+	}
+
+	data = skb_put(empty_skb, IGC_EMPTY_FRAME_SIZE);
+	memset(data, 0, IGC_EMPTY_FRAME_SIZE);
+
+	/* Prepare DMA mapping and Tx buffer information */
+	ret = igc_init_empty_frame(tx_ring, empty_info, empty_skb);
+	if (unlikely(ret)) {
+		dev_kfree_skb_any(empty_skb);
+		return ret;
+	}
+
+	/* Prepare advanced context descriptor for empty packet */
+	igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
+
+	/* Prepare advanced data descriptor for empty packet */
+	igc_init_tx_empty_descriptor(tx_ring, empty_skb, empty_info);
+
+	return 0;
+}
+
 static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 				       struct igc_ring *tx_ring)
 {
@@ -1586,6 +1611,7 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	 *	+ 1 desc for skb_headlen/IGC_MAX_DATA_PER_TXD,
 	 *	+ 2 desc gap to keep tail from touching head,
 	 *	+ 1 desc for context descriptor,
+	 *	+ 2 desc for inserting an empty packet for launch time,
 	 * otherwise try next time
 	 */
 	for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
@@ -1605,24 +1631,16 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 	launch_time = igc_tx_launchtime(tx_ring, txtime, &first_flag, &insert_empty);
 
 	if (insert_empty) {
-		struct igc_tx_buffer *empty_info;
-		struct sk_buff *empty;
-		void *data;
-
-		empty_info = &tx_ring->tx_buffer_info[tx_ring->next_to_use];
-		empty = alloc_skb(IGC_EMPTY_FRAME_SIZE, GFP_ATOMIC);
-		if (!empty)
-			goto done;
-
-		data = skb_put(empty, IGC_EMPTY_FRAME_SIZE);
-		memset(data, 0, IGC_EMPTY_FRAME_SIZE);
-
-		igc_tx_ctxtdesc(tx_ring, 0, false, 0, 0, 0);
-
-		if (igc_init_tx_empty_descriptor(tx_ring,
-						 empty,
-						 empty_info) < 0)
-			dev_kfree_skb_any(empty);
+		/* Reset the launch time if the required empty frame fails to
+		 * be inserted. However, this packet is not dropped, so it
+		 * "dirties" the current Qbv cycle. This ensures that the
+		 * upcoming packet, which is scheduled in the next Qbv cycle,
+		 * does not require an empty frame. This way, the launch time
+		 * continues to function correctly despite the current failure
+		 * to insert the empty frame.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			launch_time = 0;
 	}
 
 done:

From d7c3a7ff75028bea9e4879bd3dcd04a6dc3e33c8 Mon Sep 17 00:00:00 2001
From: Song Yoong Siang <yoong.siang.song@intel.com>
Date: Sun, 16 Feb 2025 17:34:30 +0800
Subject: [PATCH 0893/2753] igc: Add launch time support to XDP ZC

Enable Launch Time Control (LTC) support for XDP zero copy via XDP Tx
metadata framework.

This patch has been tested with tools/testing/selftests/bpf/xdp_hw_metadata
on Intel I225-LM Ethernet controller. Below are the test steps and result.

Test 1: Send a single packet with the launch time set to 1 s in the future.

Test steps:
1. On the DUT, start the xdp_hw_metadata selftest application:
   $ sudo ./xdp_hw_metadata enp2s0 -l 1000000000 -L 1

2. On the Link Partner, send a UDP packet with VLAN priority 1 to port 9091
   of the DUT.

Result:
When the launch time is set to 1 s in the future, the delta between the
launch time and the transmit hardware timestamp is 0.016 us, as shown in
printout of the xdp_hw_metadata application below.
  0x562ff5dc8880: rx_desc[4]->addr=84110 addr=84110 comp_addr=84110 EoP
  rx_hash: 0xE343384 with RSS type:0x1
  HW RX-time:   1734578015467548904 (sec:1734578015.4675)
                delta to User RX-time sec:0.0002 (183.103 usec)
  XDP RX-time:   1734578015467651698 (sec:1734578015.4677)
                 delta to User RX-time sec:0.0001 (80.309 usec)
  No rx_vlan_tci or rx_vlan_proto, err=-95
  0x562ff5dc8880: ping-pong with csum=561c (want c7dd)
                  csum_start=34 csum_offset=6
  HW RX-time:   1734578015467548904 (sec:1734578015.4675)
                delta to HW Launch-time sec:1.0000 (1000000.000 usec)
  0x562ff5dc8880: complete tx idx=4 addr=4018
  HW Launch-time:   1734578016467548904 (sec:1734578016.4675)
                    delta to HW TX-complete-time sec:0.0000 (0.016 usec)
  HW TX-complete-time:   1734578016467548920 (sec:1734578016.4675)
                         delta to User TX-complete-time sec:0.0000
                         (32.546 usec)
  XDP RX-time:   1734578015467651698 (sec:1734578015.4677)
                 delta to User TX-complete-time sec:0.9999
                 (999929.768 usec)
  HW RX-time:   1734578015467548904 (sec:1734578015.4675)
                delta to HW TX-complete-time sec:1.0000 (1000000.016 usec)
  0x562ff5dc8880: complete rx idx=132 addr=84110

Test 2: Send 1000 packets with a 10 ms interval and the launch time set to
        500 us in the future.

Test steps:
1. On the DUT, start the xdp_hw_metadata selftest application:
   $ sudo chrt -f 99 ./xdp_hw_metadata enp2s0 -l 500000 -L 1 > \
     /dev/shm/result.log

2. On the Link Partner, send 1000 UDP packets with a 10 ms interval and
   VLAN priority 1 to port 9091 of the DUT.

Result:
When the launch time is set to 500 us in the future, the average delta
between the launch time and the transmit hardware timestamp is 0.016 us,
as shown in the analysis of /dev/shm/result.log below. The XDP launch time
works correctly in sending 1000 packets continuously.
  Min delta: 0.005 us
  Avr delta: 0.016 us
  Max delta: 0.031 us
  Total packets forwarded: 1000

Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Faizal Rahim <faizal.abdul.rahim@linux.intel.com>
Reviewed-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Link: https://patch.msgid.link/20250216093430.957880-6-yoong.siang.song@intel.com
---
 drivers/net/ethernet/intel/igc/igc.h      |  1 +
 drivers/net/ethernet/intel/igc/igc_main.c | 61 ++++++++++++++++++++++-
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h
index b8111ad9a9a83..cd1d7b6c17823 100644
--- a/drivers/net/ethernet/intel/igc/igc.h
+++ b/drivers/net/ethernet/intel/igc/igc.h
@@ -579,6 +579,7 @@ struct igc_metadata_request {
 	struct xsk_tx_metadata *meta;
 	struct igc_ring *tx_ring;
 	u32 cmd_type;
+	u16 used_desc;
 };
 
 struct igc_q_vector {
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 1bfa71545e371..3044392e8ded8 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2971,9 +2971,48 @@ static u64 igc_xsk_fill_timestamp(void *_priv)
 	return *(u64 *)_priv;
 }
 
+static void igc_xsk_request_launch_time(u64 launch_time, void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	__le32 launch_time_offset;
+	bool insert_empty = false;
+	bool first_flag = false;
+	u16 used_desc = 0;
+
+	if (!tx_ring->launchtime_enable)
+		return;
+
+	launch_time_offset = igc_tx_launchtime(tx_ring,
+					       ns_to_ktime(launch_time),
+					       &first_flag, &insert_empty);
+	if (insert_empty) {
+		/* Disregard the launch time request if the required empty frame
+		 * fails to be inserted.
+		 */
+		if (igc_insert_empty_frame(tx_ring))
+			return;
+
+		meta_req->tx_buffer =
+			&tx_ring->tx_buffer_info[tx_ring->next_to_use];
+		/* Inserting an empty packet requires two descriptors:
+		 * one data descriptor and one context descriptor.
+		 */
+		used_desc += 2;
+	}
+
+	/* Use one context descriptor to specify launch time and first flag. */
+	igc_tx_ctxtdesc(tx_ring, launch_time_offset, first_flag, 0, 0, 0);
+	used_desc += 1;
+
+	/* Update the number of used descriptors in this request */
+	meta_req->used_desc += used_desc;
+}
+
 const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
 	.tmo_request_timestamp		= igc_xsk_request_timestamp,
 	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+	.tmo_request_launch_time	= igc_xsk_request_launch_time,
 };
 
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
@@ -2996,7 +3035,13 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	ntu = ring->next_to_use;
 	budget = igc_desc_unused(ring);
 
-	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
+	/* Packets with launch time require one data descriptor and one context
+	 * descriptor. When the launch time falls into the next Qbv cycle, we
+	 * may need to insert an empty packet, which requires two more
+	 * descriptors. Therefore, to be safe, we always ensure we have at least
+	 * 4 descriptors available.
+	 */
+	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) {
 		struct igc_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
@@ -3017,9 +3062,19 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		meta_req.tx_ring = ring;
 		meta_req.tx_buffer = bi;
 		meta_req.meta = meta;
+		meta_req.used_desc = 0;
 		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
 					&meta_req);
 
+		/* xsk_tx_metadata_request() may have updated next_to_use */
+		ntu = ring->next_to_use;
+
+		/* xsk_tx_metadata_request() may have updated Tx buffer info */
+		bi = meta_req.tx_buffer;
+
+		/* xsk_tx_metadata_request() may use a few descriptors */
+		budget -= meta_req.used_desc;
+
 		tx_desc = IGC_TX_DESC(ring, ntu);
 		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
@@ -3037,9 +3092,11 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 		ntu++;
 		if (ntu == ring->count)
 			ntu = 0;
+
+		ring->next_to_use = ntu;
+		budget--;
 	}
 
-	ring->next_to_use = ntu;
 	if (tx_desc) {
 		igc_flush_tx_descriptors(ring);
 		xsk_tx_release(pool);

From b522f180ee2b264b771fcbd0ab67d84cdd9e580d Mon Sep 17 00:00:00 2001
From: Fenghua Yu <fenghua.yu@intel.com>
Date: Fri, 31 Jan 2025 11:07:31 -0800
Subject: [PATCH 0894/2753] MAINTAINERS: Change maintainer for RDT

Due to job transition, I am stepping down as RDT maintainer.
Add Tony as a co-maintainer.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Acked-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/all/20250131190731.3981085-1-fenghua.yu%40intel.com
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index feed152470f68..d1cbaeb58143a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19779,7 +19779,7 @@ F:	net/rds/
 F:	tools/testing/selftests/net/rds/
 
 RDT - RESOURCE ALLOCATION
-M:	Fenghua Yu <fenghua.yu@intel.com>
+M:	Tony Luck <tony.luck@intel.com>
 M:	Reinette Chatre <reinette.chatre@intel.com>
 L:	linux-kernel@vger.kernel.org
 S:	Supported

From 1340461e5168f8a33b2b3e0ed04557742664bee1 Mon Sep 17 00:00:00 2001
From: Purva Yeshi <purvayeshi550@gmail.com>
Date: Tue, 18 Feb 2025 19:40:45 +0530
Subject: [PATCH 0895/2753] af_unix: Fix undefined 'other' error

Fix an issue with the sparse static analysis tool where an
"undefined 'other'" error occurs due to `__releases(&unix_sk(other)->lock)`
being placed before 'other' is in scope.

Remove the `__releases()` annotation from the `unix_wait_for_peer()`
function to eliminate the sparse error. The annotation references `other`
before it is declared, leading to a false positive error during static
analysis.

Since AF_UNIX does not use sparse annotations, this annotation is
unnecessary and does not impact functionality.

Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Purva Yeshi <purvayeshi550@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250218141045.38947-1-purvayeshi550@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 34945de1fb1fa..319153850be18 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1508,7 +1508,6 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr,
 }
 
 static long unix_wait_for_peer(struct sock *other, long timeo)
-	__releases(&unix_sk(other)->lock)
 {
 	struct unix_sock *u = unix_sk(other);
 	int sched;

From f06e4bfd010faefa637689d2df2c727dbf6e1d27 Mon Sep 17 00:00:00 2001
From: Qunqin Zhao <zhaoqunqin@loongson.cn>
Date: Wed, 19 Feb 2025 10:07:01 +0800
Subject: [PATCH 0896/2753] net: stmmac: dwmac-loongson: Add fix_soc_reset()
 callback

Loongson's DWMAC device may take nearly two seconds to complete DMA reset,
however, the default waiting time for reset is 200 milliseconds.
Therefore, the following error message may appear:

[14.427169] dwmac-loongson-pci 0000:00:03.2: Failed to reset the dma

Fixes: 803fc61df261 ("net: stmmac: dwmac-loongson: Add Loongson Multi-channels GMAC support")
Cc: stable@vger.kernel.org
Signed-off-by: Qunqin Zhao <zhaoqunqin@loongson.cn>
Reviewed-by: Huacai Chen <chenhuacai@loongson.cn>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Acked-by: Yanteng Si <si.yanteng@linux.dev>
Link: https://patch.msgid.link/20250219020701.15139-1-zhaoqunqin@loongson.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-loongson.c   | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index bfe6e2d631bdf..f5acfb7d4ff65 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -516,6 +516,19 @@ static int loongson_dwmac_acpi_config(struct pci_dev *pdev,
 	return 0;
 }
 
+/* Loongson's DWMAC device may take nearly two seconds to complete DMA reset */
+static int loongson_dwmac_fix_reset(void *priv, void __iomem *ioaddr)
+{
+	u32 value = readl(ioaddr + DMA_BUS_MODE);
+
+	value |= DMA_BUS_MODE_SFT_RESET;
+	writel(value, ioaddr + DMA_BUS_MODE);
+
+	return readl_poll_timeout(ioaddr + DMA_BUS_MODE, value,
+				  !(value & DMA_BUS_MODE_SFT_RESET),
+				  10000, 2000000);
+}
+
 static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
 	struct plat_stmmacenet_data *plat;
@@ -566,6 +579,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 
 	plat->bsp_priv = ld;
 	plat->setup = loongson_dwmac_setup;
+	plat->fix_soc_reset = loongson_dwmac_fix_reset;
 	ld->dev = &pdev->dev;
 	ld->loongson_id = readl(res.addr + GMAC_VERSION) & 0xff;
 

From 80c4668d024ff7b5427d90b5fad655ce9461c7b1 Mon Sep 17 00:00:00 2001
From: Zenm Chen <zenmchen@gmail.com>
Date: Mon, 10 Feb 2025 15:36:10 +0800
Subject: [PATCH 0897/2753] wifi: rtw88: Add support for Mercusys MA30N and
 D-Link DWA-T185 rev. A1

Add two more USB IDs found in
https://github.com/RinCat/RTL88x2BU-Linux-Driver
to support Mercusys MA30N and D-Link DWA-T185 rev. A1.

Signed-off-by: Zenm Chen <zenmchen@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250210073610.4174-1-zenmchen@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8822bu.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
index 8883300fc6adb..572d1f31832ee 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8822bu.c
@@ -73,6 +73,10 @@ static const struct usb_device_id rtw_8822bu_id_table[] = {
 	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* ELECOM WDB-867DU3S */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x0107, 0xff, 0xff, 0xff),
 	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* Mercusys MA30H */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2c4e, 0x010a, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* Mercusys MA30N */
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x3322, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8822b_hw_spec) }, /* D-Link DWA-T185 rev. A1 */
 	{},
 };
 MODULE_DEVICE_TABLE(usb, rtw_8822bu_id_table);

From 802fb6db9fdc82cc0e0f2e4315a24b2171e6ef4f Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:21 +0100
Subject: [PATCH 0898/2753] net: pktgen: replace ENOTSUPP with EOPNOTSUPP

Replace ENOTSUPP with EOPNOTSUPP, fixes checkpatch hint

  WARNING: ENOTSUPP is not a SUSV4 error code, prefer EOPNOTSUPP

and e.g.

  $ echo "clone_skb 1" > /proc/net/pktgen/lo\@0
  -bash: echo: write error: Unknown error 524

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-2-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 82b6a2c3c141f..496aa16773e78 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1198,7 +1198,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		if ((value > 0) &&
 		    ((pkt_dev->xmit_mode == M_NETIF_RECEIVE) ||
 		     !(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 		if (value > 0 && (pkt_dev->n_imix_entries > 0 ||
 				  !(pkt_dev->flags & F_SHARED)))
 			return -EINVAL;
@@ -1258,7 +1258,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		    ((pkt_dev->xmit_mode == M_QUEUE_XMIT) ||
 		     ((pkt_dev->xmit_mode == M_START_XMIT) &&
 		     (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING)))))
-			return -ENOTSUPP;
+			return -EOPNOTSUPP;
 
 		if (value > 1 && !(pkt_dev->flags & F_SHARED))
 			return -EINVAL;
@@ -1303,7 +1303,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		} else if (strcmp(f, "netif_receive") == 0) {
 			/* clone_skb set earlier, not supported in this mode */
 			if (pkt_dev->clone_skb > 0)
-				return -ENOTSUPP;
+				return -EOPNOTSUPP;
 
 			pkt_dev->xmit_mode = M_NETIF_RECEIVE;
 

From 80604d19b5fc3bc309039670445c73ee418d7a01 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:22 +0100
Subject: [PATCH 0899/2753] net: pktgen: enable 'param=value' parsing

Enable more flexible parameters syntax, allowing 'param=value' in
addition to the already supported 'param value' pattern (additional
this gives the skipping '=' in count_trail_chars() a purpose).

Tested with:

	$ echo "min_pkt_size 999" > /proc/net/pktgen/lo\@0
	$ echo "min_pkt_size=999" > /proc/net/pktgen/lo\@0
	$ echo "min_pkt_size =999" > /proc/net/pktgen/lo\@0
	$ echo "min_pkt_size= 999" > /proc/net/pktgen/lo\@0
	$ echo "min_pkt_size = 999" > /proc/net/pktgen/lo\@0

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-3-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 496aa16773e78..4f8ec6c9bed4a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -823,6 +823,7 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen)
 		case '\r':
 		case '\t':
 		case ' ':
+		case '=':
 			goto done_str;
 		default:
 			break;

From b38504346a2400c822cc57d0164521405fb12757 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:23 +0100
Subject: [PATCH 0900/2753] net: pktgen: fix hex32_arg parsing for short reads

Fix hex32_arg parsing for short reads (here 7 hex digits instead of the
expected 8), shift result only on successful input parsing.

- before the patch

	$ echo "mpls 0000123" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	     mpls: 00001230
	Result: OK: mpls=00001230

- with patch applied

	$ echo "mpls 0000123" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	     mpls: 00000123
	Result: OK: mpls=00000123

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-4-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4f8ec6c9bed4a..28dbbf70e1424 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -753,14 +753,15 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
 	for (; i < maxlen; i++) {
 		int value;
 		char c;
-		*num <<= 4;
 		if (get_user(c, &user_buffer[i]))
 			return -EFAULT;
 		value = hex_to_bin(c);
-		if (value >= 0)
+		if (value >= 0) {
+			*num <<= 4;
 			*num |= value;
-		else
+		} else {
 			break;
+		}
 	}
 	return i;
 }

From 3ba38c25a8c03b77ed448220a6c93dd5552a264e Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:24 +0100
Subject: [PATCH 0901/2753] net: pktgen: fix 'rate 0' error handling (return
 -EINVAL)

Given an invalid 'rate' command e.g. 'rate 0' the return value is '1',
leading to the following misleading output:

- the good case

	$ echo "rate 100" > /proc/net/pktgen/lo\@0
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: OK: rate=100

- the bad case (before the patch)

	$ echo "rate 0" > /proc/net/pktgen/lo\@0"
	-bash: echo: write error: Invalid argument
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: No such parameter "ate"

- with patch applied

	$ echo "rate 0" > /proc/net/pktgen/lo\@0
	-bash: echo: write error: Invalid argument
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: Idle

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-5-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 28dbbf70e1424..75c7511bf492e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1115,7 +1115,7 @@ static ssize_t pktgen_if_write(struct file *file,
 
 		i += len;
 		if (!value)
-			return len;
+			return -EINVAL;
 		pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value;
 		if (debug)
 			pr_info("Delay set at: %llu ns\n", pkt_dev->delay);

From 1c3bc2c325f89e21f52af4a5c940ed1d89e05229 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:25 +0100
Subject: [PATCH 0902/2753] net: pktgen: fix 'ratep 0' error handling (return
 -EINVAL)

Given an invalid 'ratep' command e.g. 'ratep 0' the return value is '1',
leading to the following misleading output:

- the good case

	$ echo "ratep 100" > /proc/net/pktgen/lo\@0
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: OK: ratep=100

- the bad case (before the patch)

	$ echo "ratep 0" > /proc/net/pktgen/lo\@0"
	-bash: echo: write error: Invalid argument
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: No such parameter "atep"

- with patch applied

	$ echo "ratep 0" > /proc/net/pktgen/lo\@0
	-bash: echo: write error: Invalid argument
	$ grep "Result:" /proc/net/pktgen/lo\@0
	Result: Idle

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-6-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 75c7511bf492e..c8a5b4d174073 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1130,7 +1130,7 @@ static ssize_t pktgen_if_write(struct file *file,
 
 		i += len;
 		if (!value)
-			return len;
+			return -EINVAL;
 		pkt_dev->delay = NSEC_PER_SEC/value;
 		if (debug)
 			pr_info("Delay set at: %llu ns\n", pkt_dev->delay);

From 1e5e511373fe1348ed24372cf2a81234b32ac935 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:26 +0100
Subject: [PATCH 0903/2753] net: pktgen: fix ctrl interface command parsing

Enable command writing without trailing '\n':

- the good case

	$ echo "reset" > /proc/net/pktgen/pgctrl

- the bad case (before the patch)

	$ echo -n "reset" > /proc/net/pktgen/pgctrl
	-bash: echo: write error: Invalid argument

- with patch applied

	$ echo -n "reset" > /proc/net/pktgen/pgctrl

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-7-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index c8a5b4d174073..f6e35ba035c7c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -517,21 +517,23 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf,
 			    size_t count, loff_t *ppos)
 {
 	char data[128];
+	size_t max;
 	struct pktgen_net *pn = net_generic(current->nsproxy->net_ns, pg_net_id);
 
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 
-	if (count == 0)
+	if (count < 1)
 		return -EINVAL;
 
-	if (count > sizeof(data))
-		count = sizeof(data);
-
-	if (copy_from_user(data, buf, count))
+	max = min(count, sizeof(data) - 1);
+	if (copy_from_user(data, buf, max))
 		return -EFAULT;
 
-	data[count - 1] = 0;	/* Strip trailing '\n' and terminate string */
+	if (data[max - 1] == '\n')
+		data[max - 1] = 0; /* strip trailing '\n', terminate string */
+	else
+		data[max] = 0; /* terminate string */
 
 	if (!strcmp(data, "stop"))
 		pktgen_stop_all_threads(pn);

From 425e64440ad0a2f03bdaf04be0ae53dededbaa77 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Wed, 19 Feb 2025 09:45:27 +0100
Subject: [PATCH 0904/2753] net: pktgen: fix access outside of user given
 buffer in pktgen_thread_write()

Honour the user given buffer size for the strn_len() calls (otherwise
strn_len() will access memory outside of the user given buffer).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250219084527.20488-8-ps.report@gmx.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/pktgen.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f6e35ba035c7c..55064713223ec 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1900,8 +1900,8 @@ static ssize_t pktgen_thread_write(struct file *file,
 	i = len;
 
 	/* Read variable name */
-
-	len = strn_len(&user_buffer[i], sizeof(name) - 1);
+	max = min(sizeof(name) - 1, count - i);
+	len = strn_len(&user_buffer[i], max);
 	if (len < 0)
 		return len;
 
@@ -1931,7 +1931,8 @@ static ssize_t pktgen_thread_write(struct file *file,
 	if (!strcmp(name, "add_device")) {
 		char f[32];
 		memset(f, 0, 32);
-		len = strn_len(&user_buffer[i], sizeof(f) - 1);
+		max = min(sizeof(f) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0) {
 			ret = len;
 			goto out;

From ef75d8343bc14c5911574c07d18681d98e08ce20 Mon Sep 17 00:00:00 2001
From: Kohei Enju <enjuk@amazon.com>
Date: Wed, 19 Feb 2025 19:22:27 +0900
Subject: [PATCH 0905/2753] neighbour: Replace kvzalloc() with kzalloc() when
 GFP_ATOMIC is specified

kzalloc() uses page allocator when size is larger than
KMALLOC_MAX_CACHE_SIZE, so the intention of commit ab101c553bc1
("neighbour: use kvzalloc()/kvfree()") can be achieved by using kzalloc().

When using GFP_ATOMIC, kvzalloc() only tries the kmalloc path,
since the vmalloc path does not support the flag.
In this case, kvzalloc() is equivalent to kzalloc() in that neither try
the vmalloc path, so this replacement brings no functional change.
This is primarily a cleanup change, as the original code functions
correctly.

This patch replaces kvzalloc() introduced by commit 41b3caa7c076
("neighbour: Add hlist_node to struct neighbour"), which is called in
the same context and with the same gfp flag as the aforementioned commit
ab101c553bc1 ("neighbour: use kvzalloc()/kvfree()").

Signed-off-by: Kohei Enju <enjuk@amazon.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Link: https://patch.msgid.link/20250219102227.72488-1-enjuk@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/neighbour.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index d8dd686b5287e..344c9cd168ec1 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -518,7 +518,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int shift)
 	if (!ret)
 		return NULL;
 
-	hash_heads = kvzalloc(size, GFP_ATOMIC);
+	hash_heads = kzalloc(size, GFP_ATOMIC);
 	if (!hash_heads) {
 		kfree(ret);
 		return NULL;
@@ -536,7 +536,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head)
 						    struct neigh_hash_table,
 						    rcu);
 
-	kvfree(nht->hash_heads);
+	kfree(nht->hash_heads);
 	kfree(nht);
 }
 

From bfc8e71ef6b7913f0129aff47951cab73a175259 Mon Sep 17 00:00:00 2001
From: Dmitry Antipov <dmantipov@yandex.ru>
Date: Thu, 13 Feb 2025 12:50:06 +0300
Subject: [PATCH 0906/2753] wifi: rtw89: rtw8852b{t}: fix TSSI debug timestamps

Since the vendor driver is claimed to measure 'tssi_alimk_time' of
'struct rtw89_tssi_info' in microseconds, adjust rtw8852b{t}-specific
'_tssi_alimentk()' to not mess the former with nanoseconds and print
both per-call and accumulated times. Compile tested only.

Fixes: 7f18a70d7b4d ("wifi: rtw89: 8852b: rfk: add TSSI")
Signed-off-by: Dmitry Antipov <dmantipov@yandex.ru>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250213095006.1308810-1-dmantipov@yandex.ru
---
 drivers/net/wireless/realtek/rtw89/core.h          |  2 +-
 drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c  | 13 +++++++------
 drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c | 13 +++++++------
 3 files changed, 15 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index b3fdd8eded210..eb2a6b90c9407 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -5141,7 +5141,7 @@ struct rtw89_tssi_info {
 	u32 alignment_backup_by_ch[RF_PATH_MAX][TSSI_MAX_CH_NUM][TSSI_ALIMK_VALUE_NUM];
 	u32 alignment_value[RF_PATH_MAX][TSSI_ALIMK_MAX][TSSI_ALIMK_VALUE_NUM];
 	bool alignment_done[RF_PATH_MAX][TSSI_ALIMK_MAX];
-	u32 tssi_alimk_time;
+	u64 tssi_alimk_time;
 };
 
 struct rtw89_power_trim_info {
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
index ef47a5facc836..fbf82d42687ba 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
@@ -3585,9 +3585,10 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	u8 ch_idx = _tssi_ch_to_idx(rtwdev, channel);
 	struct rtw8852bx_bb_tssi_bak tssi_bak;
 	s32 aliment_diff, tssi_cw_default;
-	u32 start_time, finish_time;
 	u32 bb_reg_backup[8] = {0};
+	ktime_t start_time;
 	const s16 *power;
+	s64 this_time;
 	u8 band;
 	bool ok;
 	u32 tmp;
@@ -3613,7 +3614,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		return;
 	}
 
-	start_time = ktime_get_ns();
+	start_time = ktime_get();
 
 	if (chan->band_type == RTW89_BAND_2G)
 		power = power_2g;
@@ -3738,12 +3739,12 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	rtw8852bx_bb_restore_tssi(rtwdev, phy, &tssi_bak);
 	rtw8852bx_bb_tx_mode_switch(rtwdev, phy, 0);
 
-	finish_time = ktime_get_ns();
-	tssi_info->tssi_alimk_time += finish_time - start_time;
+	this_time = ktime_us_delta(ktime_get(), start_time);
+	tssi_info->tssi_alimk_time += this_time;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
-		    "[TSSI PA K] %s processing time = %d ms\n", __func__,
-		    tssi_info->tssi_alimk_time);
+		    "[TSSI PA K] %s processing time = %lld us (acc = %llu us)\n",
+		    __func__, this_time, tssi_info->tssi_alimk_time);
 }
 
 void rtw8852b_dpk_init(struct rtw89_dev *rtwdev)
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
index 336a83e1d46be..6e6889eea9a0d 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt_rfk.c
@@ -3663,9 +3663,10 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	u8 ch_idx = _tssi_ch_to_idx(rtwdev, channel);
 	struct rtw8852bx_bb_tssi_bak tssi_bak;
 	s32 aliment_diff, tssi_cw_default;
-	u32 start_time, finish_time;
 	u32 bb_reg_backup[8] = {};
+	ktime_t start_time;
 	const s16 *power;
+	s64 this_time;
 	u8 band;
 	bool ok;
 	u32 tmp;
@@ -3675,7 +3676,7 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 		    "======> %s   channel=%d   path=%d\n", __func__, channel,
 		    path);
 
-	start_time = ktime_get_ns();
+	start_time = ktime_get();
 
 	if (chan->band_type == RTW89_BAND_2G)
 		power = power_2g;
@@ -3802,12 +3803,12 @@ static void _tssi_alimentk(struct rtw89_dev *rtwdev, enum rtw89_phy_idx phy,
 	rtw8852bx_bb_restore_tssi(rtwdev, phy, &tssi_bak);
 	rtw8852bx_bb_tx_mode_switch(rtwdev, phy, 0);
 
-	finish_time = ktime_get_ns();
-	tssi_info->tssi_alimk_time += finish_time - start_time;
+	this_time = ktime_us_delta(ktime_get(), start_time);
+	tssi_info->tssi_alimk_time += this_time;
 
 	rtw89_debug(rtwdev, RTW89_DBG_RFK,
-		    "[TSSI PA K] %s processing time = %d ms\n", __func__,
-		    tssi_info->tssi_alimk_time);
+		    "[TSSI PA K] %s processing time = %lld us (acc = %llu us)\n",
+		    __func__, this_time, tssi_info->tssi_alimk_time);
 }
 
 void rtw8852bt_dpk_init(struct rtw89_dev *rtwdev)

From 3fe090ad025082556491604a4761cad87d7529da Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Wed, 19 Feb 2025 13:41:08 +0200
Subject: [PATCH 0907/2753] net/mlx5: Bridge, correct config option description

The implication of the previous help text was that without this option
enabled, representor devices couldn't be added to a bridge device, while
in fact that was possible, just that rules didn't get offloaded to hw.

This commit clarifies the help text.

Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219114112.403808-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index ea6070180c96b..bf4015a12b410 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -80,8 +80,8 @@ config MLX5_BRIDGE
 	default y
 	help
 	  mlx5 ConnectX offloads support for Ethernet Bridging (BRIDGE).
-	  Enable adding representors of mlx5 uplink and VF ports to Bridge and
-	  offloading rules for traffic between such ports. Supports VLANs (trunk and
+	  Enable offloading FDB rules from a bridge device containing
+	  representors of mlx5 uplink and VF ports. Supports VLANs (trunk and
 	  access modes).
 
 config MLX5_CLS_ACT

From 5246fd3fc232f50987dad73ffd9ded1f40f1e6f6 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 19 Feb 2025 13:41:09 +0200
Subject: [PATCH 0908/2753] net/mlx5e: Refactor ptys2ethtool_adver_link()

The function ptys2ethtool_adver_link() contains duplicated code that
is found in mlx5e_ethtool_get_speed_arr().

To eliminate this redundancy, we update mlx5e_ethtool_get_speed_arr()
to select the appropriate table based on the ext argument passed by
the caller, rather than querying the supported mode locally.

This allows us to replace the current logic in ptys2ethtool_adver_link()
with a call to mlx5e_ethtool_get_speed_arr().

This adjustment aligns with the ptys2ethtool_supported_link() function
and prepares for an upcoming patch that reduces code duplication.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219114112.403808-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 20 ++++++++-----------
 1 file changed, 8 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index f9113cb13a0c8..a24bc546e270b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -260,12 +260,10 @@ void mlx5e_build_ptys2ethtool_map(void)
 				       ETHTOOL_LINK_MODE_800000baseVR4_Full_BIT);
 }
 
-static void mlx5e_ethtool_get_speed_arr(struct mlx5_core_dev *mdev,
+static void mlx5e_ethtool_get_speed_arr(bool ext,
 					struct ptys2ethtool_config **arr,
 					u32 *size)
 {
-	bool ext = mlx5_ptys_ext_supported(mdev);
-
 	*arr = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
 	*size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
 		      ARRAY_SIZE(ptys2legacy_ethtool_table);
@@ -912,16 +910,15 @@ int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
 	return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal);
 }
 
-static void ptys2ethtool_supported_link(struct mlx5_core_dev *mdev,
-					unsigned long *supported_modes,
-					u32 eth_proto_cap)
+static void ptys2ethtool_supported_link(unsigned long *supported_modes,
+					u32 eth_proto_cap, bool ext)
 {
 	unsigned long proto_cap = eth_proto_cap;
 	struct ptys2ethtool_config *table;
 	u32 max_size;
 	int proto;
 
-	mlx5e_ethtool_get_speed_arr(mdev, &table, &max_size);
+	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
 	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(supported_modes, supported_modes,
 			  table[proto].supported,
@@ -936,10 +933,7 @@ static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
 	u32 max_size;
 	int proto;
 
-	table = ext ? ptys2ext_ethtool_table : ptys2legacy_ethtool_table;
-	max_size = ext ? ARRAY_SIZE(ptys2ext_ethtool_table) :
-			 ARRAY_SIZE(ptys2legacy_ethtool_table);
-
+	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
 	for_each_set_bit(proto, &proto_cap, max_size)
 		bitmap_or(advertising_modes, advertising_modes,
 			  table[proto].advertised,
@@ -1128,7 +1122,9 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 			  struct ethtool_link_ksettings *link_ksettings)
 {
 	unsigned long *supported = link_ksettings->link_modes.supported;
-	ptys2ethtool_supported_link(mdev, supported, eth_proto_cap);
+	bool ext = mlx5_ptys_ext_supported(mdev);
+
+	ptys2ethtool_supported_link(supported, eth_proto_cap, ext);
 
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }

From 64d97f891961a0fa249f6730102cb7c1501f8532 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 19 Feb 2025 13:41:10 +0200
Subject: [PATCH 0909/2753] net/mlx5e: Introduce ptys2ethtool_process_link()

The functions ptys2ethtool_supported_link(), ptys2ethtool_adver_link()
share the same code, thus, in order to remove code duplication we
introduce a new function ptys2ethtool_process_link() to handle the
processing of both supported and advertised link modes.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219114112.403808-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 35 ++++++-------------
 1 file changed, 10 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index a24bc546e270b..6dab58ab50ac3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -910,33 +910,19 @@ int mlx5e_set_per_queue_coalesce(struct net_device *dev, u32 queue,
 	return mlx5e_ethtool_set_per_queue_coalesce(priv, queue, coal);
 }
 
-static void ptys2ethtool_supported_link(unsigned long *supported_modes,
-					u32 eth_proto_cap, bool ext)
+static void ptys2ethtool_process_link(u32 eth_eproto, bool ext, bool advertised,
+				      unsigned long *modes)
 {
-	unsigned long proto_cap = eth_proto_cap;
+	unsigned long eproto = eth_eproto;
 	struct ptys2ethtool_config *table;
 	u32 max_size;
 	int proto;
 
 	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(supported_modes, supported_modes,
-			  table[proto].supported,
-			  __ETHTOOL_LINK_MODE_MASK_NBITS);
-}
-
-static void ptys2ethtool_adver_link(unsigned long *advertising_modes,
-				    u32 eth_proto_cap, bool ext)
-{
-	unsigned long proto_cap = eth_proto_cap;
-	struct ptys2ethtool_config *table;
-	u32 max_size;
-	int proto;
-
-	mlx5e_ethtool_get_speed_arr(ext, &table, &max_size);
-	for_each_set_bit(proto, &proto_cap, max_size)
-		bitmap_or(advertising_modes, advertising_modes,
-			  table[proto].advertised,
+	for_each_set_bit(proto, &eproto, max_size)
+		bitmap_or(modes, modes,
+			  advertised ?
+			  table[proto].advertised : table[proto].supported,
 			  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
@@ -1124,7 +1110,7 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 	unsigned long *supported = link_ksettings->link_modes.supported;
 	bool ext = mlx5_ptys_ext_supported(mdev);
 
-	ptys2ethtool_supported_link(supported, eth_proto_cap, ext);
+	ptys2ethtool_process_link(eth_proto_cap, ext, false, supported);
 
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
@@ -1134,8 +1120,7 @@ static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
 			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
-	ptys2ethtool_adver_link(advertising, eth_proto_cap, ext);
-
+	ptys2ethtool_process_link(eth_proto_cap, ext, true, advertising);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)
@@ -1191,7 +1176,7 @@ static void get_lp_advertising(struct mlx5_core_dev *mdev, u32 eth_proto_lp,
 	unsigned long *lp_advertising = link_ksettings->link_modes.lp_advertising;
 	bool ext = mlx5_ptys_ext_supported(mdev);
 
-	ptys2ethtool_adver_link(lp_advertising, eth_proto_lp, ext);
+	ptys2ethtool_process_link(eth_proto_lp, ext, true, lp_advertising);
 }
 
 static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,

From 9ca3bf013a0ef885fcafd71f68c4abf40cf8b123 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 19 Feb 2025 13:41:11 +0200
Subject: [PATCH 0910/2753] net/mlx5e: Change eth_proto parameter naming

eth_proto_cap parameter represents the supported link modes,
while eth_proto_admin refers to the configured ones.

The function get_advertising() retrieves the configured link
modes, thus we update its parameter name to eth_proto_admin.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219114112.403808-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 6dab58ab50ac3..712171dd07c70 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1115,12 +1115,12 @@ static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
 	ethtool_link_ksettings_add_link_mode(link_ksettings, supported, Pause);
 }
 
-static void get_advertising(u32 eth_proto_cap, u8 tx_pause, u8 rx_pause,
+static void get_advertising(u32 eth_proto_admin, u8 tx_pause, u8 rx_pause,
 			    struct ethtool_link_ksettings *link_ksettings,
 			    bool ext)
 {
 	unsigned long *advertising = link_ksettings->link_modes.advertising;
-	ptys2ethtool_process_link(eth_proto_cap, ext, true, advertising);
+	ptys2ethtool_process_link(eth_proto_admin, ext, true, advertising);
 	if (rx_pause)
 		ethtool_link_ksettings_add_link_mode(link_ksettings, advertising, Pause);
 	if (tx_pause ^ rx_pause)

From 9c362aafda8b9920568f9e7dbd5c904b34fe38bb Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 19 Feb 2025 13:41:12 +0200
Subject: [PATCH 0911/2753] net/mlx5e: Separate extended link modes request
 from link modes type selection

The function ext_requested() serves two distinct purposes: it checks
if extended link modes were requested, and it selects whether to use
extended or legacy link modes.

This change separates these two purposes. Now, ext_link_mode_requested()
is used directly for checking if extended link modes are requested,
while the selection of extended modes is handled independently based on
the autonegotiation status.

By making this distinction, the logic for determining whether to select
extended or legacy link modes is clearer.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219114112.403808-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en_ethtool.c    | 13 ++++---------
 1 file changed, 4 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 712171dd07c70..1bf2212a0bb6f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1344,13 +1344,6 @@ static bool ext_link_mode_requested(const unsigned long *adver)
 	return bitmap_intersects(modes, adver, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static bool ext_requested(u8 autoneg, const unsigned long *adver, bool ext_supported)
-{
-	bool ext_link_mode = ext_link_mode_requested(adver);
-
-	return  autoneg == AUTONEG_ENABLE ? ext_link_mode : ext_supported;
-}
-
 static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 					    const struct ethtool_link_ksettings *link_ksettings)
 {
@@ -1360,6 +1353,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	bool an_changes = false;
 	u8 an_disable_admin;
 	bool ext_supported;
+	bool ext_requested;
 	u8 an_disable_cap;
 	bool an_disable;
 	u32 link_modes;
@@ -1376,10 +1370,11 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	speed = link_ksettings->base.speed;
 
 	ext_supported = mlx5_ptys_ext_supported(mdev);
-	ext = ext_requested(autoneg, adver, ext_supported);
-	if (!ext_supported && ext)
+	ext_requested = ext_link_mode_requested(adver);
+	if (!ext_supported && ext_requested)
 		return -EOPNOTSUPP;
 
+	ext = autoneg == AUTONEG_ENABLE ? ext_requested : ext_supported;
 	ethtool2ptys_adver_func = ext ? mlx5e_ethtool2ptys_ext_adver_link :
 				  mlx5e_ethtool2ptys_adver_link;
 	err = mlx5_port_query_eth_proto(mdev, 1, ext, &eproto);

From bdce0574243b43b3bb2064f609c0c326df44c4c6 Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Mon, 17 Feb 2025 14:12:35 +0800
Subject: [PATCH 0912/2753] wifi: rtw89: 8922a: fix incorrect STA-ID in EHT MU
 PPDU

EHT MU PPDU contains user field of EHT-SIG field with STA-ID that
must match AID subfield in the Associate Response. Add a necessary
setting to prevent these from being inconsistent.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217061235.32031-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 35b86970db2a4..6dbea18355a3d 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3435,9 +3435,10 @@ int rtw89_fw_h2c_assoc_cmac_tbl_g7(struct rtw89_dev *rtwdev,
 			      CCTLINFO_G7_W5_NOMINAL_PKT_PADDING3 |
 			      CCTLINFO_G7_W5_NOMINAL_PKT_PADDING4);
 
-	h2c->w6 = le32_encode_bits(vif->type == NL80211_IFTYPE_STATION ? 1 : 0,
+	h2c->w6 = le32_encode_bits(vif->cfg.aid, CCTLINFO_G7_W6_AID12_PAID) |
+		  le32_encode_bits(vif->type == NL80211_IFTYPE_STATION ? 1 : 0,
 				   CCTLINFO_G7_W6_ULDL);
-	h2c->m6 = cpu_to_le32(CCTLINFO_G7_W6_ULDL);
+	h2c->m6 = cpu_to_le32(CCTLINFO_G7_W6_AID12_PAID | CCTLINFO_G7_W6_ULDL);
 
 	if (rtwsta_link) {
 		h2c->w8 = le32_encode_bits(link_sta->he_cap.has_he,

From 8279a8dacf9f975c37f3dc51634b6c4a8936c57b Mon Sep 17 00:00:00 2001
From: Charalampos Mitrodimas <charmitro@posteo.net>
Date: Wed, 19 Feb 2025 12:41:55 +0000
Subject: [PATCH 0913/2753] net: phy: qt2025: Fix hardware revision check
 comment

Correct the hardware revision check comment in the QT2025 driver. The
revision value was documented as 0x3b instead of the correct 0xb3,
which matches the actual comparison logic in the code.

Reviewed-by: FUJITA Tomonori <fujita.tomonori@gmail.com>
Signed-off-by: Charalampos Mitrodimas <charmitro@posteo.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Trevor Gross <tmgross@umich.edu>
Link: https://patch.msgid.link/20250219-qt2025-comment-fix-v2-1-029f67696516@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qt2025.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/qt2025.rs b/drivers/net/phy/qt2025.rs
index 1ab065798175b..7e754d5d71544 100644
--- a/drivers/net/phy/qt2025.rs
+++ b/drivers/net/phy/qt2025.rs
@@ -41,7 +41,7 @@ impl Driver for PhyQT2025 {
 
     fn probe(dev: &mut phy::Device) -> Result<()> {
         // Check the hardware revision code.
-        // Only 0x3b works with this driver and firmware.
+        // Only 0xb3 works with this driver and firmware.
         let hw_rev = dev.read(C45::new(Mmd::PMAPMD, 0xd001))?;
         if (hw_rev >> 8) != 0xb3 {
             return Err(code::ENODEV);

From ca57d1c56f4015d83fe7840b41d74783ee900b28 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 19 Feb 2025 17:21:14 +0100
Subject: [PATCH 0914/2753] octeontx2: hide unused label

A previous patch introduces a build-time warning when CONFIG_DCB
is disabled:

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c: In function 'otx2_probe':
drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c:3217:1: error: label 'err_free_zc_bmap' defined but not used [-Werror=unused-label]
drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c: In function 'otx2vf_probe':
drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c:740:1: error: label 'err_free_zc_bmap' defined but not used [-Werror=unused-label]

Add the same #ifdef check around it.

Fixes: efabce290151 ("octeontx2-pf: AF_XDP zero copy receive support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Suman Ghosh <sumang@marvell.com>
Link: https://patch.msgid.link/20250219162239.1376865-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c | 2 ++
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c | 2 ++
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index c7c562f0f5e5c..cfed9ec5b1579 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -3214,8 +3214,10 @@ static int otx2_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+#ifdef CONFIG_DCB
 err_free_zc_bmap:
 	bitmap_free(pf->af_xdp_zc_qidx);
+#endif
 err_sriov_cleannup:
 	otx2_sriov_vfcfg_cleanup(pf);
 err_pf_sriov_init:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
index 63ddd262d1229..7ef3ba477d496 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_vf.c
@@ -737,8 +737,10 @@ static int otx2vf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 
 	return 0;
 
+#ifdef CONFIG_DCB
 err_free_zc_bmap:
 	bitmap_free(vf->af_xdp_zc_qidx);
+#endif
 err_unreg_devlink:
 	otx2_unregister_dl(vf);
 err_shutdown_tc:

From a5b8fd3f07d780f8ec48ca1cb0a3d26b29412b28 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:30:52 +0800
Subject: [PATCH 0915/2753] wifi: rtw89: mac: define registers of agg_limit and
 txcnt_limit to share common flow

The agg_limit and txcnt_limit are used by BT-coexistence to reduce
WiFi TX time at once to share time with Bluetooth devices. Since
these registers address are different from WiFi 6 and 7 chips, define
them accordingly.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217063053.38936-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.c    | 17 +++++++++++------
 drivers/net/wireless/realtek/rtw89/mac.h    |  2 ++
 drivers/net/wireless/realtek/rtw89/mac_be.c |  2 ++
 drivers/net/wireless/realtek/rtw89/reg.h    |  7 +++++++
 4 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 3f38f8ed68760..0b2e4ad527746 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -6433,6 +6433,7 @@ __rtw89_mac_set_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_
 			u32 tx_time)
 {
 #define MAC_AX_DFLT_TX_TIME 5280
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u8 mac_idx = rtwsta_link->rtwvif_link->mac_idx;
 	u32 max_tx_time = tx_time == 0 ? MAC_AX_DFLT_TX_TIME : tx_time;
 	u32 reg;
@@ -6448,8 +6449,8 @@ __rtw89_mac_set_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AMPDU_AGG_LIMIT, mac_idx);
-		rtw89_write32_mask(rtwdev, reg, B_AX_AMPDU_MAX_TIME_MASK,
+		reg = rtw89_mac_reg_by_idx(rtwdev, mac->agg_limit.addr, mac_idx);
+		rtw89_write32_mask(rtwdev, reg, mac->agg_limit.mask,
 				   max_tx_time >> 5);
 	}
 
@@ -6475,6 +6476,7 @@ int rtw89_mac_set_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwst
 int rtw89_mac_get_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_link,
 			  u32 *tx_time)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u8 mac_idx = rtwsta_link->rtwvif_link->mac_idx;
 	u32 reg;
 	int ret = 0;
@@ -6488,8 +6490,8 @@ int rtw89_mac_get_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwst
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_AMPDU_AGG_LIMIT, mac_idx);
-		*tx_time = rtw89_read32_mask(rtwdev, reg, B_AX_AMPDU_MAX_TIME_MASK) << 5;
+		reg = rtw89_mac_reg_by_idx(rtwdev, mac->agg_limit.addr, mac_idx);
+		*tx_time = rtw89_read32_mask(rtwdev, reg, mac->agg_limit.mask) << 5;
 	}
 
 	return ret;
@@ -6517,6 +6519,7 @@ int rtw89_mac_set_tx_retry_limit(struct rtw89_dev *rtwdev,
 int rtw89_mac_get_tx_retry_limit(struct rtw89_dev *rtwdev,
 				 struct rtw89_sta_link *rtwsta_link, u8 *tx_retry)
 {
+	const struct rtw89_mac_gen_def *mac = rtwdev->chip->mac_def;
 	u8 mac_idx = rtwsta_link->rtwvif_link->mac_idx;
 	u32 reg;
 	int ret = 0;
@@ -6530,8 +6533,8 @@ int rtw89_mac_get_tx_retry_limit(struct rtw89_dev *rtwdev,
 			return ret;
 		}
 
-		reg = rtw89_mac_reg_by_idx(rtwdev, R_AX_TXCNT, mac_idx);
-		*tx_retry = rtw89_read32_mask(rtwdev, reg, B_AX_L_TXCNT_LMT_MASK);
+		reg = rtw89_mac_reg_by_idx(rtwdev, mac->txcnt_limit.addr, mac_idx);
+		*tx_retry = rtw89_read32_mask(rtwdev, reg, mac->txcnt_limit.mask);
 	}
 
 	return ret;
@@ -6809,6 +6812,8 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_ax = {
 		.mask = B_AX_RXTRIG_RU26_DIS,
 	},
 	.wow_ctrl = {.addr = R_AX_WOW_CTRL, .mask = B_AX_WOW_WOWEN,},
+	.agg_limit = {.addr = R_AX_AMPDU_AGG_LIMIT, .mask = B_AX_AMPDU_MAX_TIME_MASK,},
+	.txcnt_limit = {.addr = R_AX_TXCNT, .mask = B_AX_L_TXCNT_LMT_MASK,},
 
 	.check_mac_en = rtw89_mac_check_mac_en_ax,
 	.sys_init = sys_init_ax,
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 6389f54264e5a..4d5a06a2fe9b7 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -964,6 +964,8 @@ struct rtw89_mac_gen_def {
 	struct rtw89_reg_def bfee_ctrl;
 	struct rtw89_reg_def narrow_bw_ru_dis;
 	struct rtw89_reg_def wow_ctrl;
+	struct rtw89_reg_def agg_limit;
+	struct rtw89_reg_def txcnt_limit;
 
 	int (*check_mac_en)(struct rtw89_dev *rtwdev, u8 band,
 			    enum rtw89_mac_hwmod_sel sel);
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index 16ee378c54187..dce0a4b01440e 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -2585,6 +2585,8 @@ const struct rtw89_mac_gen_def rtw89_mac_gen_be = {
 		.mask = B_BE_RXTRIG_RU26_DIS,
 	},
 	.wow_ctrl = {.addr = R_BE_WOW_CTRL, .mask = B_BE_WOW_WOWEN,},
+	.agg_limit = {.addr = R_BE_AMPDU_AGG_LIMIT, .mask = B_BE_AMPDU_MAX_TIME_MASK,},
+	.txcnt_limit = {.addr = R_BE_TXCNT, .mask = B_BE_L_TXCNT_LMT_MASK,},
 
 	.check_mac_en = rtw89_mac_check_mac_en_be,
 	.sys_init = sys_init_be,
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index c992835d4b63c..ec06f5bd0fab2 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -6618,6 +6618,13 @@
 #define B_BE_RTS_LIMIT_IN_OFDM6 BIT(1)
 #define B_BE_CHECK_CCK_EN BIT(0)
 
+#define R_BE_TXCNT 0x1082C
+#define R_BE_TXCNT_C1 0x1482C
+#define B_BE_ADD_TXCNT_BY BIT(31)
+#define B_BE_TOTAL_TC_OPT BIT(30)
+#define B_BE_S_TXCNT_LMT_MASK GENMASK(29, 24)
+#define B_BE_L_TXCNT_LMT_MASK GENMASK(21, 16)
+
 #define R_BE_MBSSID_DROP_0 0x1083C
 #define R_BE_MBSSID_DROP_0_C1 0x1483C
 #define B_BE_GI_LTF_FB_SEL BIT(30)

From c852d2abee30f464cbf08369e985219fe850dd0f Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:30:53 +0800
Subject: [PATCH 0916/2753] wifi: rtw89: add H2C command of TX time for WiFi 7
 chips

BT-coexistence configure WiFi TX time to share time slots with Bluetooth
devices. Since the format is different from WiFi 6 chips, add the new
format accordingly.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217063053.38936-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  2 +
 drivers/net/wireless/realtek/rtw89/fw.c       | 55 +++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/fw.h       | 11 ++++
 drivers/net/wireless/realtek/rtw89/mac.c      |  6 +-
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 .../net/wireless/realtek/rtw89/rtw8852bt.c    |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |  1 +
 10 files changed, 77 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index eb2a6b90c9407..542390f1d28cb 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3676,6 +3676,8 @@ struct rtw89_chip_ops {
 	int (*h2c_ampdu_cmac_tbl)(struct rtw89_dev *rtwdev,
 				  struct rtw89_vif_link *rtwvif_link,
 				  struct rtw89_sta_link *rtwsta_link);
+	int (*h2c_txtime_cmac_tbl)(struct rtw89_dev *rtwdev,
+				   struct rtw89_sta_link *rtwsta_link);
 	int (*h2c_default_dmac_tbl)(struct rtw89_dev *rtwdev,
 				    struct rtw89_vif_link *rtwvif_link,
 				    struct rtw89_sta_link *rtwsta_link);
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 6dbea18355a3d..eff94f0592c9e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3574,6 +3574,61 @@ int rtw89_fw_h2c_txtime_cmac_tbl(struct rtw89_dev *rtwdev,
 
 	return ret;
 }
+EXPORT_SYMBOL(rtw89_fw_h2c_txtime_cmac_tbl);
+
+int rtw89_fw_h2c_txtime_cmac_tbl_g7(struct rtw89_dev *rtwdev,
+				    struct rtw89_sta_link *rtwsta_link)
+{
+	struct rtw89_h2c_cctlinfo_ud_g7 *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
+	int ret;
+
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
+	if (!skb) {
+		rtw89_err(rtwdev, "failed to alloc skb for txtime_cmac_g7\n");
+		return -ENOMEM;
+	}
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_cctlinfo_ud_g7 *)skb->data;
+
+	h2c->c0 = le32_encode_bits(rtwsta_link->mac_id, CCTLINFO_G7_C0_MACID) |
+		  le32_encode_bits(1, CCTLINFO_G7_C0_OP);
+
+	if (rtwsta_link->cctl_tx_time) {
+		h2c->w3 |= le32_encode_bits(1, CCTLINFO_G7_W3_AMPDU_TIME_SEL);
+		h2c->m3 |= cpu_to_le32(CCTLINFO_G7_W3_AMPDU_TIME_SEL);
+
+		h2c->w2 |= le32_encode_bits(rtwsta_link->ampdu_max_time,
+					   CCTLINFO_G7_W2_AMPDU_MAX_TIME);
+		h2c->m2 |= cpu_to_le32(CCTLINFO_G7_W2_AMPDU_MAX_TIME);
+	}
+	if (rtwsta_link->cctl_tx_retry_limit) {
+		h2c->w2 |= le32_encode_bits(1, CCTLINFO_G7_W2_DATA_TXCNT_LMT_SEL) |
+			   le32_encode_bits(rtwsta_link->data_tx_cnt_lmt,
+					    CCTLINFO_G7_W2_DATA_TX_CNT_LMT);
+		h2c->m2 |= cpu_to_le32(CCTLINFO_G7_W2_DATA_TXCNT_LMT_SEL |
+				       CCTLINFO_G7_W2_DATA_TX_CNT_LMT);
+	}
+
+	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
+			      H2C_CAT_MAC, H2C_CL_MAC_FR_EXCHG,
+			      H2C_FUNC_MAC_CCTLINFO_UD_G7, 0, 1,
+			      len);
+
+	ret = rtw89_h2c_tx(rtwdev, skb, false);
+	if (ret) {
+		rtw89_err(rtwdev, "failed to send h2c\n");
+		goto fail;
+	}
+
+	return 0;
+fail:
+	dev_kfree_skb_any(skb);
+
+	return ret;
+}
+EXPORT_SYMBOL(rtw89_fw_h2c_txtime_cmac_tbl_g7);
 
 int rtw89_fw_h2c_txpath_cmac_tbl(struct rtw89_dev *rtwdev,
 				 struct rtw89_sta_link *rtwsta_link)
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 994d109a9c3c9..53a4083ba1287 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4588,6 +4588,8 @@ int rtw89_fw_h2c_ampdu_cmac_tbl_g7(struct rtw89_dev *rtwdev,
 				   struct rtw89_sta_link *rtwsta_link);
 int rtw89_fw_h2c_txtime_cmac_tbl(struct rtw89_dev *rtwdev,
 				 struct rtw89_sta_link *rtwsta_link);
+int rtw89_fw_h2c_txtime_cmac_tbl_g7(struct rtw89_dev *rtwdev,
+				    struct rtw89_sta_link *rtwsta_link);
 int rtw89_fw_h2c_txpath_cmac_tbl(struct rtw89_dev *rtwdev,
 				 struct rtw89_sta_link *rtwsta_link);
 int rtw89_fw_h2c_update_beacon(struct rtw89_dev *rtwdev,
@@ -4869,6 +4871,15 @@ static inline int rtw89_chip_h2c_ampdu_cmac_tbl(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static inline
+int rtw89_chip_h2c_txtime_cmac_tbl(struct rtw89_dev *rtwdev,
+				   struct rtw89_sta_link *rtwsta_link)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	return chip->ops->h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
+}
+
 static inline
 int rtw89_chip_h2c_ba_cam(struct rtw89_dev *rtwdev, struct rtw89_sta *rtwsta,
 			  bool valid, struct ieee80211_ampdu_params *params)
diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 0b2e4ad527746..513c317b286cc 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -6441,7 +6441,7 @@ __rtw89_mac_set_tx_time(struct rtw89_dev *rtwdev, struct rtw89_sta_link *rtwsta_
 
 	if (rtwsta_link->cctl_tx_time) {
 		rtwsta_link->ampdu_max_time = (max_tx_time - 512) >> 9;
-		ret = rtw89_fw_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
+		ret = rtw89_chip_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
 	} else {
 		ret = rtw89_mac_check_mac_en(rtwdev, mac_idx, RTW89_CMAC_SEL);
 		if (ret) {
@@ -6507,9 +6507,9 @@ int rtw89_mac_set_tx_retry_limit(struct rtw89_dev *rtwdev,
 
 	if (!resume) {
 		rtwsta_link->cctl_tx_retry_limit = true;
-		ret = rtw89_fw_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
+		ret = rtw89_chip_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
 	} else {
-		ret = rtw89_fw_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
+		ret = rtw89_chip_h2c_txtime_cmac_tbl(rtwdev, rtwsta_link);
 		rtwsta_link->cctl_tx_retry_limit = false;
 	}
 
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 82289dbad1f4d..3ef07d80caf16 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2423,6 +2423,7 @@ static const struct rtw89_chip_ops rtw8851b_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
 	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl,
 	.h2c_default_dmac_tbl	= NULL,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 2046832d021fd..bcd71d6fce297 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2149,6 +2149,7 @@ static const struct rtw89_chip_ops rtw8852a_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
 	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl,
 	.h2c_default_dmac_tbl	= NULL,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 652914a362451..2ef534b4e9513 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -776,6 +776,7 @@ static const struct rtw89_chip_ops rtw8852b_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
 	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl,
 	.h2c_default_dmac_tbl	= NULL,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 6f15245b2f749..8f2dccc07bb51 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -710,6 +710,7 @@ static const struct rtw89_chip_ops rtw8852bt_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
 	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl,
 	.h2c_default_dmac_tbl	= NULL,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index ecc1ff3585831..5876b1e8bb6b7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2941,6 +2941,7 @@ static const struct rtw89_chip_ops rtw8852c_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl,
 	.h2c_ampdu_cmac_tbl	= NULL,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl,
 	.h2c_default_dmac_tbl	= NULL,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 898a65a721dc4..f3661eb894dcd 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2702,6 +2702,7 @@ static const struct rtw89_chip_ops rtw8922a_chip_ops = {
 	.h2c_default_cmac_tbl	= rtw89_fw_h2c_default_cmac_tbl_g7,
 	.h2c_assoc_cmac_tbl	= rtw89_fw_h2c_assoc_cmac_tbl_g7,
 	.h2c_ampdu_cmac_tbl	= rtw89_fw_h2c_ampdu_cmac_tbl_g7,
+	.h2c_txtime_cmac_tbl	= rtw89_fw_h2c_txtime_cmac_tbl_g7,
 	.h2c_default_dmac_tbl	= rtw89_fw_h2c_default_dmac_tbl_v2,
 	.h2c_update_beacon	= rtw89_fw_h2c_update_beacon_be,
 	.h2c_ba_cam		= rtw89_fw_h2c_ba_cam_v1,

From f11d042b3a2e92ab1aa10e0da8e290bcdcf31d39 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:43:04 +0800
Subject: [PATCH 0917/2753] wifi: rtw89: fw: add blacklist to avoid obsolete
 secure firmware

To ensure secure chip only runs expected secure firmware, stop using
obsolete firmware in blacklist which weakness or flaw was found.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217064308.43559-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  2 +
 drivers/net/wireless/realtek/rtw89/fw.c       | 52 ++++++++++++++++++-
 drivers/net/wireless/realtek/rtw89/fw.h       | 12 +++++
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 .../net/wireless/realtek/rtw89/rtw8852bt.c    |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |  1 +
 9 files changed, 71 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 542390f1d28cb..865cdcfa59e1d 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -17,6 +17,7 @@ struct rtw89_dev;
 struct rtw89_pci_info;
 struct rtw89_mac_gen_def;
 struct rtw89_phy_gen_def;
+struct rtw89_fw_blacklist;
 struct rtw89_efuse_block_cfg;
 struct rtw89_h2c_rf_tssi;
 struct rtw89_fw_txpwr_track_cfg;
@@ -4259,6 +4260,7 @@ struct rtw89_chip_info {
 	bool try_ce_fw;
 	u8 bbmcu_nr;
 	u32 needed_fw_elms;
+	const struct rtw89_fw_blacklist *fw_blacklist;
 	u32 fifo_size;
 	bool small_fifo_size;
 	u32 dle_scc_rsvd_size;
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index eff94f0592c9e..e4231dd620e6e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -38,6 +38,16 @@ struct rtw89_arp_rsp {
 
 static const u8 mss_signature[] = {0x4D, 0x53, 0x53, 0x4B, 0x50, 0x4F, 0x4F, 0x4C};
 
+const struct rtw89_fw_blacklist rtw89_fw_blacklist_default = {
+	.ver = 0x00,
+	.list = {0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+		 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0,
+	},
+};
+EXPORT_SYMBOL(rtw89_fw_blacklist_default);
+
 union rtw89_fw_element_arg {
 	size_t offset;
 	enum rtw89_rf_path rf_path;
@@ -344,6 +354,46 @@ static int __parse_formatted_mssc(struct rtw89_dev *rtwdev,
 	return 0;
 }
 
+static int __check_secure_blacklist(struct rtw89_dev *rtwdev,
+				    struct rtw89_fw_bin_info *info,
+				    struct rtw89_fw_hdr_section_info *section_info,
+				    const void *content)
+{
+	const struct rtw89_fw_blacklist *chip_blacklist = rtwdev->chip->fw_blacklist;
+	const union rtw89_fw_section_mssc_content *section_content = content;
+	struct rtw89_fw_secure *sec = &rtwdev->fw.sec;
+	u8 byte_idx;
+	u8 bit_mask;
+
+	if (!sec->secure_boot)
+		return 0;
+
+	if (!info->secure_section_exist || section_info->ignore)
+		return 0;
+
+	if (!chip_blacklist) {
+		rtw89_err(rtwdev, "chip no blacklist for secure firmware\n");
+		return -ENOENT;
+	}
+
+	byte_idx = section_content->blacklist.bit_in_chip_list >> 3;
+	bit_mask = BIT(section_content->blacklist.bit_in_chip_list & 0x7);
+
+	if (section_content->blacklist.ver > chip_blacklist->ver) {
+		rtw89_err(rtwdev, "chip blacklist out of date (%u, %u)\n",
+			  section_content->blacklist.ver, chip_blacklist->ver);
+		return -EINVAL;
+	}
+
+	if (chip_blacklist->list[byte_idx] & bit_mask) {
+		rtw89_err(rtwdev, "firmware %u in chip blacklist\n",
+			  section_content->blacklist.ver);
+		return -EPERM;
+	}
+
+	return 0;
+}
+
 static int __parse_security_section(struct rtw89_dev *rtwdev,
 				    struct rtw89_fw_bin_info *info,
 				    struct rtw89_fw_hdr_section_info *section_info,
@@ -374,7 +424,7 @@ static int __parse_security_section(struct rtw89_dev *rtwdev,
 		info->secure_section_exist = true;
 	}
 
-	return 0;
+	return __check_secure_blacklist(rtwdev, info, section_info, content);
 }
 
 static int rtw89_fw_hdr_parser_v1(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 53a4083ba1287..1c53c1e224396 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -663,6 +663,11 @@ struct rtw89_fw_mss_pool_hdr {
 } __packed;
 
 union rtw89_fw_section_mssc_content {
+	struct {
+		u8 pad[0x20];
+		u8 bit_in_chip_list;
+		u8 ver;
+	} __packed blacklist;
 	struct {
 		u8 pad[58];
 		__le32 v;
@@ -673,6 +678,13 @@ union rtw89_fw_section_mssc_content {
 	} __packed key_sign_len;
 } __packed;
 
+struct rtw89_fw_blacklist {
+	u8 ver;
+	u8 list[32];
+};
+
+extern const struct rtw89_fw_blacklist rtw89_fw_blacklist_default;
+
 static inline void SET_CTRL_INFO_MACID(void *table, u32 val)
 {
 	le32p_replace_bits((__le32 *)(table) + 0, val, GENMASK(6, 0));
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 3ef07d80caf16..3cd1d7a4d202c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2459,6 +2459,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= NULL,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index bcd71d6fce297..514ef0c2b32b7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2176,6 +2176,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= NULL,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 2ef534b4e9513..5dbb33d5e4038 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -812,6 +812,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 196608,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index 8f2dccc07bb51..b4832c7897a86 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -746,6 +746,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.try_ce_fw		= true,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= RTW89_AX_GEN_DEF_NEEDED_FW_ELEMENTS_NO_6GHZ,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 458752,
 	.small_fifo_size	= true,
 	.dle_scc_rsvd_size	= 98304,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 5876b1e8bb6b7..f3965a65ae18c 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -2968,6 +2968,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 0,
 	.needed_fw_elms		= 0,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 458752,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index f3661eb894dcd..defa6cf9f7f0b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2729,6 +2729,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.try_ce_fw		= false,
 	.bbmcu_nr		= 1,
 	.needed_fw_elms		= RTW89_BE_GEN_DEF_NEEDED_FW_ELEMENTS,
+	.fw_blacklist		= &rtw89_fw_blacklist_default,
 	.fifo_size		= 589824,
 	.small_fifo_size	= false,
 	.dle_scc_rsvd_size	= 0,

From 2f9da853f4d848d23bade4c22931ea0f5a011674 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:43:05 +0800
Subject: [PATCH 0918/2753] wifi: rtw89: fw: get sb_sel_ver via
 get_unaligned_le32()

The sb_sel_ver is selection version for secure boot recorded in firmware
binary data, and its size is 4 and offset is 58 (not natural alignment).
Use get_unaligned_le32() to get this value safely. Find this by reviewing.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217064308.43559-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index e4231dd620e6e..0a129476171a1 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -324,7 +324,7 @@ static int __parse_formatted_mssc(struct rtw89_dev *rtwdev,
 	if (!sec->secure_boot)
 		goto out;
 
-	sb_sel_ver = le32_to_cpu(section_content->sb_sel_ver.v);
+	sb_sel_ver = get_unaligned_le32(&section_content->sb_sel_ver.v);
 	if (sb_sel_ver && sb_sel_ver != sec->sb_sel_mgn)
 		goto ignore;
 

From 56e1acaa0f80620b8e2c3410db35b4b975782b0a Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:43:06 +0800
Subject: [PATCH 0919/2753] wifi: rtw89: fw: propagate error code from
 rtw89_h2c_tx()

The error code should be propagated to callers during downloading firmware
header and body. Remove unnecessary assignment of -1.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217064308.43559-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 0a129476171a1..e05034fbb898e 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1510,7 +1510,6 @@ static int __rtw89_fw_download_hdr(struct rtw89_dev *rtwdev,
 	ret = rtw89_h2c_tx(rtwdev, skb, false);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to send h2c\n");
-		ret = -1;
 		goto fail;
 	}
 
@@ -1597,7 +1596,6 @@ static int __rtw89_fw_download_main(struct rtw89_dev *rtwdev,
 		ret = rtw89_h2c_tx(rtwdev, skb, true);
 		if (ret) {
 			rtw89_err(rtwdev, "failed to send h2c\n");
-			ret = -1;
 			goto fail;
 		}
 

From dc2fc1a3419e9218fde6e7897c8c238ebe75a69e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:43:07 +0800
Subject: [PATCH 0920/2753] wifi: rtw89: fw: add debug message for unexpected
 secure firmware

If failed to load a non-secure firmware with a secure chip, it only throws
a unclear message:

   rtw89_8922ae 0000:03:00.0: parse fw header fail

To address this case simpler, add a message to point out this.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217064308.43559-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index e05034fbb898e..0cb2fee916cd4 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -414,8 +414,11 @@ static int __parse_security_section(struct rtw89_dev *rtwdev,
 			*mssc_len += section_info->mssc * FWDL_SECURITY_CHKSUM_LEN;
 
 		if (sec->secure_boot) {
-			if (sec->mss_idx >= section_info->mssc)
+			if (sec->mss_idx >= section_info->mssc) {
+				rtw89_err(rtwdev, "unexpected MSS %d >= %d\n",
+					  sec->mss_idx, section_info->mssc);
 				return -EFAULT;
+			}
 			section_info->key_addr = content + section_info->len +
 						 sec->mss_idx * FWDL_SECURITY_SIGLEN;
 			section_info->key_len = FWDL_SECURITY_SIGLEN;

From e0722103306fd5fd3cdde8d100a7588bfe7abdf0 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Mon, 17 Feb 2025 14:43:08 +0800
Subject: [PATCH 0921/2753] wifi: rtw89: fw: safely cast mfw_hdr pointer from
 firmware->data

Check size of struct mfw_hdr within firmware->size before type casting
to ensure to validly dereference fields from mfm_hdr pointer. Then,
check if signature field is equal to RTW89_MFW_SIG to assert current
is multi-firmware.

Addresses-Coverity-ID: 1494046 ("Untrusted loop bound")
Addresses-Coverity-ID: 1544385 ("Untrusted array index read")

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250217064308.43559-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 30 ++++++++++++++++++++-----
 1 file changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 0cb2fee916cd4..b843d259fbfa8 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -542,6 +542,23 @@ static int rtw89_fw_hdr_parser(struct rtw89_dev *rtwdev,
 	}
 }
 
+static
+const struct rtw89_mfw_hdr *rtw89_mfw_get_hdr_ptr(struct rtw89_dev *rtwdev,
+						  const struct firmware *firmware)
+{
+	const struct rtw89_mfw_hdr *mfw_hdr;
+
+	if (sizeof(*mfw_hdr) > firmware->size)
+		return NULL;
+
+	mfw_hdr = (const struct rtw89_mfw_hdr *)firmware->data;
+
+	if (mfw_hdr->sig != RTW89_MFW_SIG)
+		return NULL;
+
+	return mfw_hdr;
+}
+
 static int rtw89_mfw_validate_hdr(struct rtw89_dev *rtwdev,
 				  const struct firmware *firmware,
 				  const struct rtw89_mfw_hdr *mfw_hdr)
@@ -572,14 +589,15 @@ int rtw89_mfw_recognize(struct rtw89_dev *rtwdev, enum rtw89_fw_type type,
 {
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	const struct firmware *firmware = fw_info->req.firmware;
+	const struct rtw89_mfw_info *mfw_info = NULL, *tmp;
+	const struct rtw89_mfw_hdr *mfw_hdr;
 	const u8 *mfw = firmware->data;
 	u32 mfw_len = firmware->size;
-	const struct rtw89_mfw_hdr *mfw_hdr = (const struct rtw89_mfw_hdr *)mfw;
-	const struct rtw89_mfw_info *mfw_info = NULL, *tmp;
 	int ret;
 	int i;
 
-	if (mfw_hdr->sig != RTW89_MFW_SIG) {
+	mfw_hdr = rtw89_mfw_get_hdr_ptr(rtwdev, firmware);
+	if (!mfw_hdr) {
 		rtw89_debug(rtwdev, RTW89_DBG_FW, "use legacy firmware\n");
 		/* legacy firmware support normal type only */
 		if (type != RTW89_FW_NORMAL)
@@ -635,13 +653,13 @@ static u32 rtw89_mfw_get_size(struct rtw89_dev *rtwdev)
 {
 	struct rtw89_fw_info *fw_info = &rtwdev->fw;
 	const struct firmware *firmware = fw_info->req.firmware;
-	const struct rtw89_mfw_hdr *mfw_hdr =
-		(const struct rtw89_mfw_hdr *)firmware->data;
 	const struct rtw89_mfw_info *mfw_info;
+	const struct rtw89_mfw_hdr *mfw_hdr;
 	u32 size;
 	int ret;
 
-	if (mfw_hdr->sig != RTW89_MFW_SIG) {
+	mfw_hdr = rtw89_mfw_get_hdr_ptr(rtwdev, firmware);
+	if (!mfw_hdr) {
 		rtw89_warn(rtwdev, "not mfw format\n");
 		return 0;
 	}

From 846742f7e32f632166e3b2a106304b2bec7541a9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:50 -0800
Subject: [PATCH 0922/2753] selftests: drv-net: add a warning for bkg + shell +
 terminate

Joe Damato reports that some shells will fork before running
the command when python does "sh -c $cmd", while bash on my
machine does an exec of $cmd directly.

This will have implications for our ability to terminate
the child process on various configurations of bash and
other shells. Warn about using

	bkg(... shell=True, termininate=True)

most background commands can hopefully exit cleanly (exit_wait).

Link: https://lore.kernel.org/Z7Yld21sv_Ip3gQx@LQ3V64L9R2
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib/py/utils.py | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index 9e3bcddcf3e83..33b153767d896 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -61,6 +61,10 @@ def __init__(self, comm, shell=True, fail=None, ns=None, host=None,
         self.terminate = not exit_wait
         self.check_fail = fail
 
+        if shell and self.terminate:
+            print("# Warning: combining shell and terminate is risky!")
+            print("#          SIGTERM may not reach the child on zsh/ksh!")
+
     def __enter__(self):
         return self
 

From dabd31baa3b55d90fcb4875db7c1971f5d638718 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:51 -0800
Subject: [PATCH 0923/2753] selftests: drv-net: use cfg.rpath() in netlink xsk
 attr test

The cfg.rpath() helper was been recently added to make formatting
paths for helper binaries easier.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 5fdfebc6415f4..b6896a57a5fd2 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -25,8 +25,7 @@ def nl_get_queues(cfg, nl, qtype='rx'):
     return None
 
 def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
-    test_dir = os.path.dirname(os.path.realpath(__file__))
-    xdp = subprocess.Popen([f"{test_dir}/xdp_helper", f"{cfg.ifindex}", f"{xdp_queue_id}"],
+    xdp = subprocess.Popen([cfg.rpath("xdp_helper"), f"{cfg.ifindex}", f"{xdp_queue_id}"],
                            stdin=subprocess.PIPE, stdout=subprocess.PIPE, bufsize=1,
                            text=True)
     defer(xdp.kill)

From bab59dcf71fbe8f3e710a441f74dc9b76937c3e3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:52 -0800
Subject: [PATCH 0924/2753] selftests: drv-net: add missing new line in
 xdp_helper

Kurt and Joe report missing new line at the end of Usage.

Reviewed-by: Kurt Kanzenbach <kurt@linutronix.de>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/xdp_helper.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c
index cf06a88b830b8..80f86c2fe1a56 100644
--- a/tools/testing/selftests/drivers/net/xdp_helper.c
+++ b/tools/testing/selftests/drivers/net/xdp_helper.c
@@ -35,7 +35,7 @@ int main(int argc, char **argv)
 	char byte;
 
 	if (argc != 3) {
-		fprintf(stderr, "Usage: %s ifindex queue_id", argv[0]);
+		fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]);
 		return 1;
 	}
 

From d3726ab45c57d0ba26234e3b9e4d19903b740f97 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:53 -0800
Subject: [PATCH 0925/2753] selftests: drv-net: probe for AF_XDP sockets more
 explicitly

Separate the support check from socket binding for easier refactoring.
Use: ./helper - - just to probe if we can open the socket.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py    | 12 +++++++-----
 tools/testing/selftests/drivers/net/xdp_helper.c |  7 +++++++
 2 files changed, 14 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index b6896a57a5fd2..0c959b2eb6180 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -25,6 +25,13 @@ def nl_get_queues(cfg, nl, qtype='rx'):
     return None
 
 def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
+    # Probe for support
+    xdp = cmd(cfg.rpath("xdp_helper") + ' - -', fail=False)
+    if xdp.ret == 255:
+        raise KsftSkipEx('AF_XDP unsupported')
+    elif xdp.ret > 0:
+        raise KsftFailEx('unable to create AF_XDP socket')
+
     xdp = subprocess.Popen([cfg.rpath("xdp_helper"), f"{cfg.ifindex}", f"{xdp_queue_id}"],
                            stdin=subprocess.PIPE, stdout=subprocess.PIPE, bufsize=1,
                            text=True)
@@ -33,11 +40,6 @@ def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
     stdout, stderr = xdp.communicate(timeout=10)
     rx = tx = False
 
-    if xdp.returncode == 255:
-        raise KsftSkipEx('AF_XDP unsupported')
-    elif xdp.returncode > 0:
-        raise KsftFailEx('unable to create AF_XDP socket')
-
     queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
     if not queues:
         raise KsftSkipEx("Netlink reports no queues")
diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c
index 80f86c2fe1a56..2bad3b4d616c6 100644
--- a/tools/testing/selftests/drivers/net/xdp_helper.c
+++ b/tools/testing/selftests/drivers/net/xdp_helper.c
@@ -50,6 +50,13 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
+	/* "Probing mode", just checking if AF_XDP sockets are supported */
+	if (!strcmp(argv[1], "-") && !strcmp(argv[2], "-")) {
+		printf("AF_XDP support detected\n");
+		close(sock_fd);
+		return 0;
+	}
+
 	ifindex = atoi(argv[1]);
 	queue = atoi(argv[2]);
 

From 71477137994f4ac8396504bf98346b316da38157 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:54 -0800
Subject: [PATCH 0926/2753] selftests: drv-net: add a way to wait for a local
 process

We use wait_port_listen() extensively to wait for a process
we spawned to be ready. Not all processes will open listening
sockets. Add a method of explicitly waiting for a child to
be ready. Pass a FD to the spawned process and wait for it
to write a message to us. FD number is passed via KSFT_READY_FD
env variable.

Similarly use KSFT_WAIT_FD to let the child process for a sign
that we are done and child should exit. Sending a signal to
a child with shell=True can get tricky.

Make use of this method in the queues test to make it less flaky.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-6-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 49 +++++++------
 .../selftests/drivers/net/xdp_helper.c        | 54 +++++++++++++--
 tools/testing/selftests/net/lib/py/utils.py   | 68 +++++++++++++++++--
 3 files changed, 136 insertions(+), 35 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 0c959b2eb6180..7af2adb61c254 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -5,13 +5,12 @@
 from lib.py import ksft_eq, ksft_raises, KsftSkipEx, KsftFailEx
 from lib.py import EthtoolFamily, NetdevFamily, NlError
 from lib.py import NetDrvEnv
-from lib.py import cmd, defer, ip
+from lib.py import bkg, cmd, defer, ip
 import errno
 import glob
 import os
 import socket
 import struct
-import subprocess
 
 def sys_get_queues(ifname, qtype='rx') -> int:
     folders = glob.glob(f'/sys/class/net/{ifname}/queues/{qtype}-*')
@@ -32,32 +31,30 @@ def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
     elif xdp.ret > 0:
         raise KsftFailEx('unable to create AF_XDP socket')
 
-    xdp = subprocess.Popen([cfg.rpath("xdp_helper"), f"{cfg.ifindex}", f"{xdp_queue_id}"],
-                           stdin=subprocess.PIPE, stdout=subprocess.PIPE, bufsize=1,
-                           text=True)
-    defer(xdp.kill)
+    with bkg(f'{cfg.rpath("xdp_helper")} {cfg.ifindex} {xdp_queue_id}',
+             ksft_wait=3):
 
-    stdout, stderr = xdp.communicate(timeout=10)
-    rx = tx = False
+        rx = tx = False
+
+        queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
+        if not queues:
+            raise KsftSkipEx("Netlink reports no queues")
+
+        for q in queues:
+            if q['id'] == 0:
+                if q['type'] == 'rx':
+                    rx = True
+                if q['type'] == 'tx':
+                    tx = True
+
+                ksft_eq(q['xsk'], {})
+            else:
+                if 'xsk' in q:
+                    _fail("Check failed: xsk attribute set.")
+
+        ksft_eq(rx, True)
+        ksft_eq(tx, True)
 
-    queues = nl.queue_get({'ifindex': cfg.ifindex}, dump=True)
-    if not queues:
-        raise KsftSkipEx("Netlink reports no queues")
-
-    for q in queues:
-        if q['id'] == 0:
-            if q['type'] == 'rx':
-                rx = True
-            if q['type'] == 'tx':
-                tx = True
-
-            ksft_eq(q['xsk'], {})
-        else:
-            if 'xsk' in q:
-                _fail("Check failed: xsk attribute set.")
-
-    ksft_eq(rx, True)
-    ksft_eq(tx, True)
 
 def get_queues(cfg, nl) -> None:
     snl = NetdevFamily(recv_size=4096)
diff --git a/tools/testing/selftests/drivers/net/xdp_helper.c b/tools/testing/selftests/drivers/net/xdp_helper.c
index 2bad3b4d616c6..aeed259141045 100644
--- a/tools/testing/selftests/drivers/net/xdp_helper.c
+++ b/tools/testing/selftests/drivers/net/xdp_helper.c
@@ -14,6 +14,54 @@
 #define UMEM_SZ (1U << 16)
 #define NUM_DESC (UMEM_SZ / 2048)
 
+/* Move this to a common header when reused! */
+static void ksft_ready(void)
+{
+	const char msg[7] = "ready\n";
+	char *env_str;
+	int fd;
+
+	env_str = getenv("KSFT_READY_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_READY_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		fd = STDOUT_FILENO;
+	}
+
+	write(fd, msg, sizeof(msg));
+	if (fd != STDOUT_FILENO)
+		close(fd);
+}
+
+static void ksft_wait(void)
+{
+	char *env_str;
+	char byte;
+	int fd;
+
+	env_str = getenv("KSFT_WAIT_FD");
+	if (env_str) {
+		fd = atoi(env_str);
+		if (!fd) {
+			fprintf(stderr, "invalid KSFT_WAIT_FD = '%s'\n",
+				env_str);
+			return;
+		}
+	} else {
+		/* Not running in KSFT env, wait for input from STDIN instead */
+		fd = STDIN_FILENO;
+	}
+
+	read(fd, &byte, sizeof(byte));
+	if (fd != STDIN_FILENO)
+		close(fd);
+}
+
 /* this is a simple helper program that creates an XDP socket and does the
  * minimum necessary to get bind() to succeed.
  *
@@ -32,7 +80,6 @@ int main(int argc, char **argv)
 	int ifindex;
 	int sock_fd;
 	int queue;
-	char byte;
 
 	if (argc != 3) {
 		fprintf(stderr, "Usage: %s ifindex queue_id\n", argv[0]);
@@ -92,13 +139,12 @@ int main(int argc, char **argv)
 		return 1;
 	}
 
-	/* give the parent program some data when the socket is ready*/
-	fprintf(stdout, "%d\n", sock_fd);
+	ksft_ready();
+	ksft_wait();
 
 	/* parent program will write a byte to stdin when its ready for this
 	 * helper to exit
 	 */
-	read(STDIN_FILENO, &byte, 1);
 
 	close(sock_fd);
 	return 0;
diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index 33b153767d896..d879700ef2b98 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -2,8 +2,10 @@
 
 import errno
 import json as _json
+import os
 import random
 import re
+import select
 import socket
 import subprocess
 import time
@@ -15,21 +17,56 @@ def __init__(self, msg, cmd_obj):
         self.cmd = cmd_obj
 
 
+def fd_read_timeout(fd, timeout):
+    rlist, _, _ = select.select([fd], [], [], timeout)
+    if rlist:
+        return os.read(fd, 1024)
+    else:
+        raise TimeoutError("Timeout waiting for fd read")
+
+
 class cmd:
-    def __init__(self, comm, shell=True, fail=True, ns=None, background=False, host=None, timeout=5):
+    """
+    Execute a command on local or remote host.
+
+    Use bkg() instead to run a command in the background.
+    """
+    def __init__(self, comm, shell=True, fail=True, ns=None, background=False,
+                 host=None, timeout=5, ksft_wait=None):
         if ns:
             comm = f'ip netns exec {ns} ' + comm
 
         self.stdout = None
         self.stderr = None
         self.ret = None
+        self.ksft_term_fd = None
 
         self.comm = comm
         if host:
             self.proc = host.cmd(comm)
         else:
+            # ksft_wait lets us wait for the background process to fully start,
+            # we pass an FD to the child process, and wait for it to write back.
+            # Similarly term_fd tells child it's time to exit.
+            pass_fds = ()
+            env = os.environ.copy()
+            if ksft_wait is not None:
+                rfd, ready_fd = os.pipe()
+                wait_fd, self.ksft_term_fd = os.pipe()
+                pass_fds = (ready_fd, wait_fd, )
+                env["KSFT_READY_FD"] = str(ready_fd)
+                env["KSFT_WAIT_FD"]  = str(wait_fd)
+
             self.proc = subprocess.Popen(comm, shell=shell, stdout=subprocess.PIPE,
-                                         stderr=subprocess.PIPE)
+                                         stderr=subprocess.PIPE, pass_fds=pass_fds,
+                                         env=env)
+            if ksft_wait is not None:
+                os.close(ready_fd)
+                os.close(wait_fd)
+                msg = fd_read_timeout(rfd, ksft_wait)
+                os.close(rfd)
+                if not msg:
+                    raise Exception("Did not receive ready message")
         if not background:
             self.process(terminate=False, fail=fail, timeout=timeout)
 
@@ -37,6 +74,8 @@ def process(self, terminate=True, fail=None, timeout=5):
         if fail is None:
             fail = not terminate
 
+        if self.ksft_term_fd:
+            os.write(self.ksft_term_fd, b"1")
         if terminate:
             self.proc.terminate()
         stdout, stderr = self.proc.communicate(timeout)
@@ -54,11 +93,30 @@ def process(self, terminate=True, fail=None, timeout=5):
 
 
 class bkg(cmd):
+    """
+    Run a command in the background.
+
+    Examples usage:
+
+    Run a command on remote host, and wait for it to finish.
+    This is usually paired with wait_port_listen() to make sure
+    the command has initialized:
+
+        with bkg("socat ...", exit_wait=True, host=cfg.remote) as nc:
+            ...
+
+    Run a command and expect it to let us know that it's ready
+    by writing to a special file descriptor passed via KSFT_READY_FD.
+    Command will be terminated when we exit the context manager:
+
+        with bkg("my_binary", ksft_wait=5):
+    """
     def __init__(self, comm, shell=True, fail=None, ns=None, host=None,
-                 exit_wait=False):
+                 exit_wait=False, ksft_wait=None):
         super().__init__(comm, background=True,
-                         shell=shell, fail=fail, ns=ns, host=host)
-        self.terminate = not exit_wait
+                         shell=shell, fail=fail, ns=ns, host=host,
+                         ksft_wait=ksft_wait)
+        self.terminate = not exit_wait and not ksft_wait
         self.check_fail = fail
 
         if shell and self.terminate:

From 4fde8398462f4c07e765460203f6d1b529e3f17a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:55 -0800
Subject: [PATCH 0927/2753] selftests: drv-net: improve the use of ksft helpers
 in XSK queue test

Avoid exceptions when xsk attr is not present, and add a proper ksft
helper for "not in" condition.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Tested-by: Kurt Kanzenbach <kurt@linutronix.de>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-7-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 9 +++++----
 tools/testing/selftests/net/lib/py/ksft.py    | 5 +++++
 2 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 7af2adb61c254..a49f1a146e28c 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from lib.py import ksft_disruptive, ksft_exit, ksft_run
-from lib.py import ksft_eq, ksft_raises, KsftSkipEx, KsftFailEx
+from lib.py import ksft_eq, ksft_not_in, ksft_raises, KsftSkipEx, KsftFailEx
 from lib.py import EthtoolFamily, NetdevFamily, NlError
 from lib.py import NetDrvEnv
 from lib.py import bkg, cmd, defer, ip
@@ -47,10 +47,11 @@ def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
                 if q['type'] == 'tx':
                     tx = True
 
-                ksft_eq(q['xsk'], {})
+                ksft_eq(q.get('xsk', None), {},
+                        comment="xsk attr on queue we configured")
             else:
-                if 'xsk' in q:
-                    _fail("Check failed: xsk attribute set.")
+                ksft_not_in('xsk', q,
+                            comment="xsk attr on queue we didn't configure")
 
         ksft_eq(rx, True)
         ksft_eq(tx, True)
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index 3efe005436cd1..fd23349fa8ca0 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -71,6 +71,11 @@ def ksft_in(a, b, comment=""):
         _fail("Check failed", a, "not in", b, comment)
 
 
+def ksft_not_in(a, b, comment=""):
+    if a in b:
+        _fail("Check failed", a, "in", b, comment)
+
+
 def ksft_is(a, b, comment=""):
     if a is not b:
         _fail("Check failed", a, "is not", b, comment)

From 932a9249f71f88471045edd0c908f0683b10e88c Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 19 Feb 2025 15:49:56 -0800
Subject: [PATCH 0928/2753] selftests: drv-net: rename queues check_xdp to
 check_xsk

The test is for AF_XDP, we refer to AF_XDP as XSK.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Tested-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250219234956.520599-8-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index a49f1a146e28c..9040baf7b726a 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -23,7 +23,8 @@ def nl_get_queues(cfg, nl, qtype='rx'):
         return len([q for q in queues if q['type'] == qtype])
     return None
 
-def check_xdp(cfg, nl, xdp_queue_id=0) -> None:
+
+def check_xsk(cfg, nl, xdp_queue_id=0) -> None:
     # Probe for support
     xdp = cmd(cfg.rpath("xdp_helper") + ' - -', fail=False)
     if xdp.ret == 255:
@@ -116,7 +117,8 @@ def check_down(cfg, nl) -> None:
 
 def main() -> None:
     with NetDrvEnv(__file__, queue_count=100) as cfg:
-        ksft_run([get_queues, addremove_queues, check_down, check_xdp], args=(cfg, NetdevFamily()))
+        ksft_run([get_queues, addremove_queues, check_down, check_xsk],
+                 args=(cfg, NetdevFamily()))
     ksft_exit()
 
 

From e66bca16638ee59e997f9d9a3711b3ae587d04d9 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:28:59 +0200
Subject: [PATCH 0929/2753] wifi: rtw88: Fix rtw_mac_power_switch() for
 RTL8814AU

rtw_mac_power_switch() checks bit 8 of REG_SYS_STATUS1 to see if the
chip is powered on. This bit appears to be always on in the RTL8814AU,
so ignore it.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/2f0fcffb-3067-4d95-a68c-f2f3a5a47921@gmail.com
---
 drivers/net/wireless/realtek/rtw88/mac.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c
index 63edf6461de87..0491f501c1383 100644
--- a/drivers/net/wireless/realtek/rtw88/mac.c
+++ b/drivers/net/wireless/realtek/rtw88/mac.c
@@ -291,6 +291,7 @@ static int rtw_mac_power_switch(struct rtw_dev *rtwdev, bool pwr_on)
 	if (rtw_read8(rtwdev, REG_CR) == 0xea)
 		cur_pwr = false;
 	else if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB &&
+		 chip->id != RTW_CHIP_TYPE_8814A &&
 		 (rtw_read8(rtwdev, REG_SYS_STATUS1 + 1) & BIT(0)))
 		cur_pwr = false;
 	else

From 86d04f8f991a0509e318fe886d5a1cf795736c7d Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:29:52 +0200
Subject: [PATCH 0930/2753] wifi: rtw88: Fix rtw_desc_to_mcsrate() to handle
 MCS16-31

This function translates the rate number reported by the hardware into
something mac80211 can understand. It was ignoring the 3SS and 4SS HT
rates. Translate them too.

Also set *nss to 0 for the HT rates, just to make sure it's
initialised.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/d0a5a86b-4869-47f6-a5a7-01c0f987cc7f@gmail.com
---
 drivers/net/wireless/realtek/rtw88/util.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/util.c b/drivers/net/wireless/realtek/rtw88/util.c
index e222d3c01a77e..66819f6944055 100644
--- a/drivers/net/wireless/realtek/rtw88/util.c
+++ b/drivers/net/wireless/realtek/rtw88/util.c
@@ -101,7 +101,8 @@ void rtw_desc_to_mcsrate(u16 rate, u8 *mcs, u8 *nss)
 		*nss = 4;
 		*mcs = rate - DESC_RATEVHT4SS_MCS0;
 	} else if (rate >= DESC_RATEMCS0 &&
-		   rate <= DESC_RATEMCS15) {
+		   rate <= DESC_RATEMCS31) {
+		*nss = 0;
 		*mcs = rate - DESC_RATEMCS0;
 	}
 }

From c7eea1ba05ca5b0dbf77a27cf2e1e6e2fb3c0043 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:30:22 +0200
Subject: [PATCH 0931/2753] wifi: rtw88: Fix rtw_init_ht_cap() for RTL8814AU

Set the RX mask and the highest RX rate according to the number of
spatial streams the chip can receive. For RTL8814AU that is 3.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/4e786f50-ed1c-4387-8b28-e6ff00e35e81@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index e4f9b744f24de..3319bb5044c3d 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1565,6 +1565,7 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev,
 {
 	const struct rtw_chip_info *chip = rtwdev->chip;
 	struct rtw_efuse *efuse = &rtwdev->efuse;
+	int i;
 
 	ht_cap->ht_supported = true;
 	ht_cap->cap = 0;
@@ -1584,17 +1585,11 @@ static void rtw_init_ht_cap(struct rtw_dev *rtwdev,
 	ht_cap->ampdu_factor = IEEE80211_HT_MAX_AMPDU_64K;
 	ht_cap->ampdu_density = chip->ampdu_density;
 	ht_cap->mcs.tx_params = IEEE80211_HT_MCS_TX_DEFINED;
-	if (efuse->hw_cap.nss > 1) {
-		ht_cap->mcs.rx_mask[0] = 0xFF;
-		ht_cap->mcs.rx_mask[1] = 0xFF;
-		ht_cap->mcs.rx_mask[4] = 0x01;
-		ht_cap->mcs.rx_highest = cpu_to_le16(300);
-	} else {
-		ht_cap->mcs.rx_mask[0] = 0xFF;
-		ht_cap->mcs.rx_mask[1] = 0x00;
-		ht_cap->mcs.rx_mask[4] = 0x01;
-		ht_cap->mcs.rx_highest = cpu_to_le16(150);
-	}
+
+	for (i = 0; i < efuse->hw_cap.nss; i++)
+		ht_cap->mcs.rx_mask[i] = 0xFF;
+	ht_cap->mcs.rx_mask[4] = 0x01;
+	ht_cap->mcs.rx_highest = cpu_to_le16(150 * efuse->hw_cap.nss);
 }
 
 static void rtw_init_vht_cap(struct rtw_dev *rtwdev,

From 6be7544d19fcfcb729495e793bc6181f85bb8949 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:30:48 +0200
Subject: [PATCH 0932/2753] wifi: rtw88: Fix rtw_init_vht_cap() for RTL8814AU

Set the MCS maps and the highest rates according to the number of
spatial streams the chip has. For RTL8814AU that is 3.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/e86aa009-b5bf-4b3a-8112-ea5e3cd49465@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.c | 23 +++++++++--------------
 1 file changed, 9 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
index 3319bb5044c3d..959f56a3cc1ab 100644
--- a/drivers/net/wireless/realtek/rtw88/main.c
+++ b/drivers/net/wireless/realtek/rtw88/main.c
@@ -1596,8 +1596,9 @@ static void rtw_init_vht_cap(struct rtw_dev *rtwdev,
 			     struct ieee80211_sta_vht_cap *vht_cap)
 {
 	struct rtw_efuse *efuse = &rtwdev->efuse;
-	u16 mcs_map;
+	u16 mcs_map = 0;
 	__le16 highest;
+	int i;
 
 	if (efuse->hw_cap.ptcl != EFUSE_HW_CAP_IGNORE &&
 	    efuse->hw_cap.ptcl != EFUSE_HW_CAP_PTCL_VHT)
@@ -1620,21 +1621,15 @@ static void rtw_init_vht_cap(struct rtw_dev *rtwdev,
 	if (rtw_chip_has_rx_ldpc(rtwdev))
 		vht_cap->cap |= IEEE80211_VHT_CAP_RXLDPC;
 
-	mcs_map = IEEE80211_VHT_MCS_SUPPORT_0_9 << 0 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 4 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 6 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 8 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 10 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 12 |
-		  IEEE80211_VHT_MCS_NOT_SUPPORTED << 14;
-	if (efuse->hw_cap.nss > 1) {
-		highest = cpu_to_le16(780);
-		mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << 2;
-	} else {
-		highest = cpu_to_le16(390);
-		mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << 2;
+	for (i = 0; i < 8; i++) {
+		if (i < efuse->hw_cap.nss)
+			mcs_map |= IEEE80211_VHT_MCS_SUPPORT_0_9 << (i * 2);
+		else
+			mcs_map |= IEEE80211_VHT_MCS_NOT_SUPPORTED << (i * 2);
 	}
 
+	highest = cpu_to_le16(390 * efuse->hw_cap.nss);
+
 	vht_cap->vht_mcs.rx_mcs_map = cpu_to_le16(mcs_map);
 	vht_cap->vht_mcs.tx_mcs_map = cpu_to_le16(mcs_map);
 	vht_cap->vht_mcs.rx_highest = highest;

From 053a7aace0207593776c729f229d87f1be464b98 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:31:13 +0200
Subject: [PATCH 0933/2753] wifi: rtw88: Fix rtw_rx_phy_stat() for RTL8814AU

Record statistics for the 3SS rates too.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/39e3c7cf-37ed-4c0e-af00-dcd9eab351f0@gmail.com
---
 drivers/net/wireless/realtek/rtw88/main.h | 7 +++++++
 drivers/net/wireless/realtek/rtw88/rx.c   | 6 ++++++
 2 files changed, 13 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index 24ac749271cc8..c15e0f55d09a7 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -386,6 +386,9 @@ enum rtw_evm {
 	RTW_EVM_1SS,
 	RTW_EVM_2SS_A,
 	RTW_EVM_2SS_B,
+	RTW_EVM_3SS_A,
+	RTW_EVM_3SS_B,
+	RTW_EVM_3SS_C,
 	/* keep it last */
 	RTW_EVM_NUM
 };
@@ -403,6 +406,10 @@ enum rtw_snr {
 	RTW_SNR_2SS_B,
 	RTW_SNR_2SS_C,
 	RTW_SNR_2SS_D,
+	RTW_SNR_3SS_A,
+	RTW_SNR_3SS_B,
+	RTW_SNR_3SS_C,
+	RTW_SNR_3SS_D,
 	/* keep it last */
 	RTW_SNR_NUM
 };
diff --git a/drivers/net/wireless/realtek/rtw88/rx.c b/drivers/net/wireless/realtek/rtw88/rx.c
index 90fc8a5fa89e7..8b0afaaffaa0e 100644
--- a/drivers/net/wireless/realtek/rtw88/rx.c
+++ b/drivers/net/wireless/realtek/rtw88/rx.c
@@ -73,6 +73,12 @@ static void rtw_rx_phy_stat(struct rtw_dev *rtwdev,
 		rate_ss_evm = 2;
 		evm_id = RTW_EVM_2SS_A;
 		break;
+	case DESC_RATEMCS16...DESC_RATEMCS23:
+	case DESC_RATEVHT3SS_MCS0...DESC_RATEVHT3SS_MCS9:
+		rate_ss = 3;
+		rate_ss_evm = 3;
+		evm_id = RTW_EVM_3SS_A;
+		break;
 	default:
 		rtw_warn(rtwdev, "unknown pkt rate = %d\n", pkt_stat->rate);
 		return;

From 8b42c46cf6656ef3c2f6d1ec0f113753c6875712 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:31:51 +0200
Subject: [PATCH 0934/2753] wifi: rtw88: Extend rtw_phy_config_swing_table()
 for RTL8814AU

Select the TX power tracking tables for RF paths C and D as well.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/e1e532c9-8733-4ec8-84fe-ced4af6c08da@gmail.com
---
 drivers/net/wireless/realtek/rtw88/phy.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/phy.c b/drivers/net/wireless/realtek/rtw88/phy.c
index b487457d22158..55be0d8e0c28d 100644
--- a/drivers/net/wireless/realtek/rtw88/phy.c
+++ b/drivers/net/wireless/realtek/rtw88/phy.c
@@ -2458,32 +2458,56 @@ void rtw_phy_config_swing_table(struct rtw_dev *rtwdev,
 			swing_table->n[RF_PATH_A] = tbl->pwrtrk_2g_ccka_n;
 			swing_table->p[RF_PATH_B] = tbl->pwrtrk_2g_cckb_p;
 			swing_table->n[RF_PATH_B] = tbl->pwrtrk_2g_cckb_n;
+			swing_table->p[RF_PATH_C] = tbl->pwrtrk_2g_cckc_p;
+			swing_table->n[RF_PATH_C] = tbl->pwrtrk_2g_cckc_n;
+			swing_table->p[RF_PATH_D] = tbl->pwrtrk_2g_cckd_p;
+			swing_table->n[RF_PATH_D] = tbl->pwrtrk_2g_cckd_n;
 		} else {
 			swing_table->p[RF_PATH_A] = tbl->pwrtrk_2ga_p;
 			swing_table->n[RF_PATH_A] = tbl->pwrtrk_2ga_n;
 			swing_table->p[RF_PATH_B] = tbl->pwrtrk_2gb_p;
 			swing_table->n[RF_PATH_B] = tbl->pwrtrk_2gb_n;
+			swing_table->p[RF_PATH_C] = tbl->pwrtrk_2gc_p;
+			swing_table->n[RF_PATH_C] = tbl->pwrtrk_2gc_n;
+			swing_table->p[RF_PATH_D] = tbl->pwrtrk_2gd_p;
+			swing_table->n[RF_PATH_D] = tbl->pwrtrk_2gd_n;
 		}
 	} else if (IS_CH_5G_BAND_1(channel) || IS_CH_5G_BAND_2(channel)) {
 		swing_table->p[RF_PATH_A] = tbl->pwrtrk_5ga_p[RTW_PWR_TRK_5G_1];
 		swing_table->n[RF_PATH_A] = tbl->pwrtrk_5ga_n[RTW_PWR_TRK_5G_1];
 		swing_table->p[RF_PATH_B] = tbl->pwrtrk_5gb_p[RTW_PWR_TRK_5G_1];
 		swing_table->n[RF_PATH_B] = tbl->pwrtrk_5gb_n[RTW_PWR_TRK_5G_1];
+		swing_table->p[RF_PATH_C] = tbl->pwrtrk_5gc_p[RTW_PWR_TRK_5G_1];
+		swing_table->n[RF_PATH_C] = tbl->pwrtrk_5gc_n[RTW_PWR_TRK_5G_1];
+		swing_table->p[RF_PATH_D] = tbl->pwrtrk_5gd_p[RTW_PWR_TRK_5G_1];
+		swing_table->n[RF_PATH_D] = tbl->pwrtrk_5gd_n[RTW_PWR_TRK_5G_1];
 	} else if (IS_CH_5G_BAND_3(channel)) {
 		swing_table->p[RF_PATH_A] = tbl->pwrtrk_5ga_p[RTW_PWR_TRK_5G_2];
 		swing_table->n[RF_PATH_A] = tbl->pwrtrk_5ga_n[RTW_PWR_TRK_5G_2];
 		swing_table->p[RF_PATH_B] = tbl->pwrtrk_5gb_p[RTW_PWR_TRK_5G_2];
 		swing_table->n[RF_PATH_B] = tbl->pwrtrk_5gb_n[RTW_PWR_TRK_5G_2];
+		swing_table->p[RF_PATH_C] = tbl->pwrtrk_5gc_p[RTW_PWR_TRK_5G_2];
+		swing_table->n[RF_PATH_C] = tbl->pwrtrk_5gc_n[RTW_PWR_TRK_5G_2];
+		swing_table->p[RF_PATH_D] = tbl->pwrtrk_5gd_p[RTW_PWR_TRK_5G_2];
+		swing_table->n[RF_PATH_D] = tbl->pwrtrk_5gd_n[RTW_PWR_TRK_5G_2];
 	} else if (IS_CH_5G_BAND_4(channel)) {
 		swing_table->p[RF_PATH_A] = tbl->pwrtrk_5ga_p[RTW_PWR_TRK_5G_3];
 		swing_table->n[RF_PATH_A] = tbl->pwrtrk_5ga_n[RTW_PWR_TRK_5G_3];
 		swing_table->p[RF_PATH_B] = tbl->pwrtrk_5gb_p[RTW_PWR_TRK_5G_3];
 		swing_table->n[RF_PATH_B] = tbl->pwrtrk_5gb_n[RTW_PWR_TRK_5G_3];
+		swing_table->p[RF_PATH_C] = tbl->pwrtrk_5gc_p[RTW_PWR_TRK_5G_3];
+		swing_table->n[RF_PATH_C] = tbl->pwrtrk_5gc_n[RTW_PWR_TRK_5G_3];
+		swing_table->p[RF_PATH_D] = tbl->pwrtrk_5gd_p[RTW_PWR_TRK_5G_3];
+		swing_table->n[RF_PATH_D] = tbl->pwrtrk_5gd_n[RTW_PWR_TRK_5G_3];
 	} else {
 		swing_table->p[RF_PATH_A] = tbl->pwrtrk_2ga_p;
 		swing_table->n[RF_PATH_A] = tbl->pwrtrk_2ga_n;
 		swing_table->p[RF_PATH_B] = tbl->pwrtrk_2gb_p;
 		swing_table->n[RF_PATH_B] = tbl->pwrtrk_2gb_n;
+		swing_table->p[RF_PATH_C] = tbl->pwrtrk_2gc_p;
+		swing_table->n[RF_PATH_C] = tbl->pwrtrk_2gc_n;
+		swing_table->p[RF_PATH_D] = tbl->pwrtrk_2gd_p;
+		swing_table->n[RF_PATH_D] = tbl->pwrtrk_2gd_n;
 	}
 }
 EXPORT_SYMBOL(rtw_phy_config_swing_table);

From cfebabdd351e9cbafdc99cb198db482208ec5ad9 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:32:15 +0200
Subject: [PATCH 0935/2753] wifi: rtw88: Extend rtw_debugfs_get_phy_info() for
 RTL8814AU

Print information about the 3rd and 4th RF paths and about the 3rd
spatial stream.

Also, fix a small bug: don't show the average SNR and EVM for the OFDM
and HT/VHT rates when the rate is actually CCK 11M.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/7c8e94e2-e034-40f3-bdaf-b000018b5573@gmail.com
---
 drivers/net/wireless/realtek/rtw88/debug.c | 37 +++++++++++++++-------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index 364ec0436d0fe..1adb03d1210a2 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -654,10 +654,10 @@ static void rtw_print_rate(struct seq_file *m, u8 rate)
 	case DESC_RATE6M...DESC_RATE54M:
 		rtw_print_ofdm_rate_txt(m, rate);
 		break;
-	case DESC_RATEMCS0...DESC_RATEMCS15:
+	case DESC_RATEMCS0...DESC_RATEMCS31:
 		rtw_print_ht_rate_txt(m, rate);
 		break;
-	case DESC_RATEVHT1SS_MCS0...DESC_RATEVHT2SS_MCS9:
+	case DESC_RATEVHT1SS_MCS0...DESC_RATEVHT4SS_MCS9:
 		rtw_print_vht_rate_txt(m, rate);
 		break;
 	default:
@@ -849,20 +849,28 @@ static int rtw_debugfs_get_phy_info(struct seq_file *m, void *v)
 			   last_cnt->num_qry_pkt[rate_id + 9]);
 	}
 
-	seq_printf(m, "[RSSI(dBm)] = {%d, %d}\n",
+	seq_printf(m, "[RSSI(dBm)] = {%d, %d, %d, %d}\n",
 		   dm_info->rssi[RF_PATH_A] - 100,
-		   dm_info->rssi[RF_PATH_B] - 100);
-	seq_printf(m, "[Rx EVM(dB)] = {-%d, -%d}\n",
+		   dm_info->rssi[RF_PATH_B] - 100,
+		   dm_info->rssi[RF_PATH_C] - 100,
+		   dm_info->rssi[RF_PATH_D] - 100);
+	seq_printf(m, "[Rx EVM(dB)] = {-%d, -%d, -%d, -%d}\n",
 		   dm_info->rx_evm_dbm[RF_PATH_A],
-		   dm_info->rx_evm_dbm[RF_PATH_B]);
-	seq_printf(m, "[Rx SNR] = {%d, %d}\n",
+		   dm_info->rx_evm_dbm[RF_PATH_B],
+		   dm_info->rx_evm_dbm[RF_PATH_C],
+		   dm_info->rx_evm_dbm[RF_PATH_D]);
+	seq_printf(m, "[Rx SNR] = {%d, %d, %d, %d}\n",
 		   dm_info->rx_snr[RF_PATH_A],
-		   dm_info->rx_snr[RF_PATH_B]);
-	seq_printf(m, "[CFO_tail(KHz)] = {%d, %d}\n",
+		   dm_info->rx_snr[RF_PATH_B],
+		   dm_info->rx_snr[RF_PATH_C],
+		   dm_info->rx_snr[RF_PATH_D]);
+	seq_printf(m, "[CFO_tail(KHz)] = {%d, %d, %d, %d}\n",
 		   dm_info->cfo_tail[RF_PATH_A],
-		   dm_info->cfo_tail[RF_PATH_B]);
+		   dm_info->cfo_tail[RF_PATH_B],
+		   dm_info->cfo_tail[RF_PATH_C],
+		   dm_info->cfo_tail[RF_PATH_D]);
 
-	if (dm_info->curr_rx_rate >= DESC_RATE11M) {
+	if (dm_info->curr_rx_rate >= DESC_RATE6M) {
 		seq_puts(m, "[Rx Average Status]:\n");
 		seq_printf(m, " * OFDM, EVM: {-%d}, SNR: {%d}\n",
 			   (u8)ewma_evm_read(&ewma_evm[RTW_EVM_OFDM]),
@@ -875,6 +883,13 @@ static int rtw_debugfs_get_phy_info(struct seq_file *m, void *v)
 			   (u8)ewma_evm_read(&ewma_evm[RTW_EVM_2SS_B]),
 			   (u8)ewma_snr_read(&ewma_snr[RTW_SNR_2SS_A]),
 			   (u8)ewma_snr_read(&ewma_snr[RTW_SNR_2SS_B]));
+		seq_printf(m, " * 3SS, EVM: {-%d, -%d, -%d}, SNR: {%d, %d, %d}\n",
+			   (u8)ewma_evm_read(&ewma_evm[RTW_EVM_3SS_A]),
+			   (u8)ewma_evm_read(&ewma_evm[RTW_EVM_3SS_B]),
+			   (u8)ewma_evm_read(&ewma_evm[RTW_EVM_3SS_C]),
+			   (u8)ewma_snr_read(&ewma_snr[RTW_SNR_3SS_A]),
+			   (u8)ewma_snr_read(&ewma_snr[RTW_SNR_3SS_B]),
+			   (u8)ewma_snr_read(&ewma_snr[RTW_SNR_3SS_C]));
 	}
 
 	seq_puts(m, "[Rx Counter]:\n");

From c374281f828545b3698cf936b584249c2f9e40c5 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Tue, 18 Feb 2025 01:32:49 +0200
Subject: [PATCH 0936/2753] wifi: rtw88: Extend rtw_debugfs_get_tx_pwr_tbl()
 for RTL8814AU

Make it print the TX power details for all RF paths, not just A and B,
and for all the rates supported by the chip, not just 1SS and 2SS
rates.

Also skip the RF paths and rates not supported by the chip.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/ea65a978-a735-4c97-af82-d7fe26f95da1@gmail.com
---
 drivers/net/wireless/realtek/rtw88/debug.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/debug.c b/drivers/net/wireless/realtek/rtw88/debug.c
index 1adb03d1210a2..b67d69b01f879 100644
--- a/drivers/net/wireless/realtek/rtw88/debug.c
+++ b/drivers/net/wireless/realtek/rtw88/debug.c
@@ -692,9 +692,11 @@ static int rtw_debugfs_get_tx_pwr_tbl(struct seq_file *m, void *v)
 {
 	struct rtw_debugfs_priv *debugfs_priv = m->private;
 	struct rtw_dev *rtwdev = debugfs_priv->rtwdev;
+	struct rtw_power_params pwr_param = {0};
 	struct rtw_hal *hal = &rtwdev->hal;
+	u8 nss = rtwdev->efuse.hw_cap.nss;
 	u8 path, rate, bw, ch, regd;
-	struct rtw_power_params pwr_param = {0};
+	u8 max_ht_rate, max_rate;
 
 	mutex_lock(&rtwdev->mutex);
 	bw = hal->current_band_width;
@@ -707,19 +709,23 @@ static int rtw_debugfs_get_tx_pwr_tbl(struct seq_file *m, void *v)
 	seq_printf(m, "%-4s %-10s %-9s %-9s (%-4s %-4s %-4s) %-4s\n",
 		   "path", "rate", "pwr", "base", "byr", "lmt", "sar", "rem");
 
+	max_ht_rate = DESC_RATEMCS0 + nss * 8 - 1;
+
+	if (rtwdev->chip->vht_supported)
+		max_rate = DESC_RATEVHT1SS_MCS0 + nss * 10 - 1;
+	else
+		max_rate = max_ht_rate;
+
 	mutex_lock(&hal->tx_power_mutex);
-	for (path = RF_PATH_A; path <= RF_PATH_B; path++) {
+	for (path = RF_PATH_A; path < hal->rf_path_num; path++) {
 		/* there is no CCK rates used in 5G */
 		if (hal->current_band_type == RTW_BAND_5G)
 			rate = DESC_RATE6M;
 		else
 			rate = DESC_RATE1M;
 
-		/* now, not support vht 3ss and vht 4ss*/
-		for (; rate <= DESC_RATEVHT2SS_MCS9; rate++) {
-			/* now, not support ht 3ss and ht 4ss*/
-			if (rate > DESC_RATEMCS15 &&
-			    rate < DESC_RATEVHT1SS_MCS0)
+		for (; rate <= max_rate; rate++) {
+			if (rate > max_ht_rate && rate <= DESC_RATEMCS31)
 				continue;
 
 			rtw_get_tx_power_params(rtwdev, path, rate, bw,

From bb3bb6c92e5719c0f5d7adb9d34db7e76705ac33 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 19 Feb 2025 21:15:05 +0100
Subject: [PATCH 0937/2753] net: phy: remove unused feature array declarations

After 12d5151be010 ("net: phy: remove leftovers from switch to linkmode
bitmaps") the following declarations are unused and can be removed too.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/b2883c75-4108-48f2-ab73-e81647262bc2@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 584710e084eb6..13be48d3b8b31 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -37,10 +37,7 @@ extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1s_p2mp_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init;
-extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init;
-extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init;
-extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap1_features) __ro_after_init;
 extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_eee_cap2_features) __ro_after_init;
 

From dce5c4afd035e8090a26e5d776b1682c0e649683 Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Mon, 17 Feb 2025 10:16:28 +0800
Subject: [PATCH 0938/2753] scsi: core: Clear driver private data when retrying
 request

After commit 1bad6c4a57ef ("scsi: zero per-cmd private driver data for each
MQ I/O"), the xen-scsifront/virtio_scsi/snic drivers all removed code that
explicitly zeroed driver-private command data.

In combination with commit 464a00c9e0ad ("scsi: core: Kill DRIVER_SENSE"),
after virtio_scsi performs a capacity expansion, the first request will
return a unit attention to indicate that the capacity has changed. And then
the original command is retried. As driver-private command data was not
cleared, the request would return UA again and eventually time out and fail.

Zero driver-private command data when a request is retried.

Fixes: f7de50da1479 ("scsi: xen-scsifront: Remove code that zeroes driver-private command data")
Fixes: c2bb87318baa ("scsi: virtio_scsi: Remove code that zeroes driver-private command data")
Fixes: c3006a926468 ("scsi: snic: Remove code that zeroes driver-private command data")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250217021628.2929248-1-yebin@huaweicloud.com
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/scsi/scsi_lib.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index be0890e4e7062..f1cfe0bb89b20 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1669,13 +1669,6 @@ static blk_status_t scsi_prepare_cmd(struct request *req)
 	if (in_flight)
 		__set_bit(SCMD_STATE_INFLIGHT, &cmd->state);
 
-	/*
-	 * Only clear the driver-private command data if the LLD does not supply
-	 * a function to initialize that data.
-	 */
-	if (!shost->hostt->init_cmd_priv)
-		memset(cmd + 1, 0, shost->hostt->cmd_size);
-
 	cmd->prot_op = SCSI_PROT_NORMAL;
 	if (blk_rq_bytes(req))
 		cmd->sc_data_direction = rq_dma_dir(req);
@@ -1842,6 +1835,13 @@ static blk_status_t scsi_queue_rq(struct blk_mq_hw_ctx *hctx,
 	if (!scsi_host_queue_ready(q, shost, sdev, cmd))
 		goto out_dec_target_busy;
 
+	/*
+	 * Only clear the driver-private command data if the LLD does not supply
+	 * a function to initialize that data.
+	 */
+	if (shost->hostt->cmd_size && !shost->hostt->init_cmd_priv)
+		memset(cmd + 1, 0, shost->hostt->cmd_size);
+
 	if (!(req->rq_flags & RQF_DONTPREP)) {
 		ret = scsi_prepare_cmd(req);
 		if (ret != BLK_STS_OK)

From fe06b7c07f3fbcce2a2ca6f7b0d543b5699ea00f Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Wed, 19 Feb 2025 16:20:47 +0530
Subject: [PATCH 0939/2753] scsi: ufs: core: Set default runtime/system PM
 levels before ufshcd_hba_init()

Commit bb9850704c04 ("scsi: ufs: core: Honor runtime/system PM levels if
set by host controller drivers") introduced the check for setting default
PM levels only if the levels are uninitialized by the host controller
drivers. But it missed the fact that the levels could be initialized to 0
(UFS_PM_LVL_0) on purpose by the controller drivers. Even though none of
the drivers are doing so now, the logic should be fixed irrespectively.

So set the default levels unconditionally before calling ufshcd_hba_init()
API which initializes the controller drivers. It ensures that the
controller drivers could override the default levels if required.

Fixes: bb9850704c04 ("scsi: ufs: core: Honor runtime/system PM levels if set by host controller drivers")
Reported-by: Bao D. Nguyen <quic_nguyenb@quicinc.com>
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://lore.kernel.org/r/20250219105047.49932-1-manivannan.sadhasivam@linaro.org
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufshcd.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index f9303e66bb798..464f13da259aa 100644
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -10431,6 +10431,21 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 	 */
 	spin_lock_init(&hba->clk_gating.lock);
 
+	/*
+	 * Set the default power management level for runtime and system PM.
+	 * Host controller drivers can override them in their
+	 * 'ufs_hba_variant_ops::init' callback.
+	 *
+	 * Default power saving mode is to keep UFS link in Hibern8 state
+	 * and UFS device in sleep state.
+	 */
+	hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+	hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
+						UFS_SLEEP_PWR_MODE,
+						UIC_LINK_HIBERN8_STATE);
+
 	err = ufshcd_hba_init(hba);
 	if (err)
 		goto out_error;
@@ -10544,21 +10559,6 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
 		goto out_disable;
 	}
 
-	/*
-	 * Set the default power management level for runtime and system PM if
-	 * not set by the host controller drivers.
-	 * Default power saving mode is to keep UFS link in Hibern8 state
-	 * and UFS device in sleep state.
-	 */
-	if (!hba->rpm_lvl)
-		hba->rpm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-	if (!hba->spm_lvl)
-		hba->spm_lvl = ufs_get_desired_pm_lvl_for_dev_link_state(
-						UFS_SLEEP_PWR_MODE,
-						UIC_LINK_HIBERN8_STATE);
-
 	INIT_DELAYED_WORK(&hba->rpm_dev_flush_recheck_work, ufshcd_rpm_dev_flush_recheck_work);
 	INIT_DELAYED_WORK(&hba->ufs_rtc_update_work, ufshcd_rtc_work);
 

From f27a95845b01e86d67c8b014b4f41bd3327daa63 Mon Sep 17 00:00:00 2001
From: Arthur Simchaev <arthur.simchaev@sandisk.com>
Date: Thu, 20 Feb 2025 16:20:39 +0200
Subject: [PATCH 0940/2753] scsi: ufs: core: bsg: Fix crash when arpmb command
 fails

If the device doesn't support arpmb we'll crash due to copying user data in
bsg_transport_sg_io_fn().

In the case where ufs_bsg_exec_advanced_rpmb_req() returns an error, do not
set the job's reply_len.

Memory crash backtrace:
3,1290,531166405,-;ufshcd 0000:00:12.5: ARPMB OP failed: error code -22

4,1308,531166555,-;Call Trace:

4,1309,531166559,-; <TASK>

4,1310,531166565,-; ? show_regs+0x6d/0x80

4,1311,531166575,-; ? die+0x37/0xa0

4,1312,531166583,-; ? do_trap+0xd4/0xf0

4,1313,531166593,-; ? do_error_trap+0x71/0xb0

4,1314,531166601,-; ? usercopy_abort+0x6c/0x80

4,1315,531166610,-; ? exc_invalid_op+0x52/0x80

4,1316,531166622,-; ? usercopy_abort+0x6c/0x80

4,1317,531166630,-; ? asm_exc_invalid_op+0x1b/0x20

4,1318,531166643,-; ? usercopy_abort+0x6c/0x80

4,1319,531166652,-; __check_heap_object+0xe3/0x120

4,1320,531166661,-; check_heap_object+0x185/0x1d0

4,1321,531166670,-; __check_object_size.part.0+0x72/0x150

4,1322,531166679,-; __check_object_size+0x23/0x30

4,1323,531166688,-; bsg_transport_sg_io_fn+0x314/0x3b0

Fixes: 6ff265fc5ef6 ("scsi: ufs: core: bsg: Add advanced RPMB support in ufs_bsg")
Cc: stable@vger.kernel.org
Reviewed-by: Bean Huo <beanhuo@micron.com>
Signed-off-by: Arthur Simchaev <arthur.simchaev@sandisk.com>
Link: https://lore.kernel.org/r/20250220142039.250992-1-arthur.simchaev@sandisk.com
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ufs/core/ufs_bsg.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/ufs/core/ufs_bsg.c b/drivers/ufs/core/ufs_bsg.c
index 8d4ad0a3f2cf0..252186124669a 100644
--- a/drivers/ufs/core/ufs_bsg.c
+++ b/drivers/ufs/core/ufs_bsg.c
@@ -194,10 +194,12 @@ static int ufs_bsg_request(struct bsg_job *job)
 	ufshcd_rpm_put_sync(hba);
 	kfree(buff);
 	bsg_reply->result = ret;
-	job->reply_len = !rpmb ? sizeof(struct ufs_bsg_reply) : sizeof(struct ufs_rpmb_reply);
 	/* complete the job here only if no error */
-	if (ret == 0)
+	if (ret == 0) {
+		job->reply_len = rpmb ? sizeof(struct ufs_rpmb_reply) :
+					sizeof(struct ufs_bsg_reply);
 		bsg_job_done(job, ret, bsg_reply->reply_payload_rcv_len);
+	}
 
 	return ret;
 }

From 5eddd76ec2fd1988f0a3450fde9730b10dd22992 Mon Sep 17 00:00:00 2001
From: Alexandre Cassen <acassen@corp.free.fr>
Date: Wed, 19 Feb 2025 12:20:37 +0200
Subject: [PATCH 0941/2753] xfrm: fix tunnel mode TX datapath in packet offload
 mode

Packets that match the output xfrm policy are delivered to the netstack.
In IPsec packet mode for tunnel mode, the HW is responsible for building
the hard header and outer IP header. In such a situation, the inner
header may refer to a network that is not directly reachable by the host,
resulting in a failed neighbor resolution. The packet is then dropped.
xfrm policy defines the netdevice to use for xmit so we can send packets
directly to it.

Makes direct xmit exclusive to tunnel mode, since some rules may apply
in transport mode.

Fixes: f8a70afafc17 ("xfrm: add TX datapath support for IPsec packet offload mode")
Signed-off-by: Alexandre Cassen <acassen@corp.free.fr>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_output.c | 41 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index f7abd42c077d5..e5b3e343a5ec1 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -612,6 +612,40 @@ int xfrm_output_resume(struct sock *sk, struct sk_buff *skb, int err)
 }
 EXPORT_SYMBOL_GPL(xfrm_output_resume);
 
+static int xfrm_dev_direct_output(struct sock *sk, struct xfrm_state *x,
+				  struct sk_buff *skb)
+{
+	struct dst_entry *dst = skb_dst(skb);
+	struct net *net = xs_net(x);
+	int err;
+
+	dst = skb_dst_pop(skb);
+	if (!dst) {
+		XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR);
+		kfree_skb(skb);
+		return -EHOSTUNREACH;
+	}
+	skb_dst_set(skb, dst);
+	nf_reset_ct(skb);
+
+	err = skb_dst(skb)->ops->local_out(net, sk, skb);
+	if (unlikely(err != 1)) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	/* In transport mode, network destination is
+	 * directly reachable, while in tunnel mode,
+	 * inner packet network may not be. In packet
+	 * offload type, HW is responsible for hard
+	 * header packet mangling so directly xmit skb
+	 * to netdevice.
+	 */
+	skb->dev = x->xso.dev;
+	__skb_push(skb, skb->dev->hard_header_len);
+	return dev_queue_xmit(skb);
+}
+
 static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	return xfrm_output_resume(sk, skb, 1);
@@ -735,6 +769,13 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 			return -EHOSTUNREACH;
 		}
 
+		/* Exclusive direct xmit for tunnel mode, as
+		 * some filtering or matching rules may apply
+		 * in transport mode.
+		 */
+		if (x->props.mode == XFRM_MODE_TUNNEL)
+			return xfrm_dev_direct_output(sk, x, skb);
+
 		return xfrm_output_resume(sk, skb, 0);
 	}
 

From 0aae2867aa6067f73d066bc98385e23c8454a1d7 Mon Sep 17 00:00:00 2001
From: Cosmin Ratiu <cratiu@nvidia.com>
Date: Wed, 19 Feb 2025 12:52:48 +0200
Subject: [PATCH 0942/2753] xfrm_output: Force software GSO only in tunnel mode

The cited commit fixed a software GSO bug with VXLAN + IPSec in tunnel
mode. Unfortunately, it is slightly broader than necessary, as it also
severely affects performance for Geneve + IPSec transport mode over a
device capable of both HW GSO and IPSec crypto offload. In this case,
xfrm_output unnecessarily triggers software GSO instead of letting the
HW do it. In simple iperf3 tests over Geneve + IPSec transport mode over
a back-2-back pair of NICs with MTU 1500, the performance was observed
to be up to 6x worse when doing software GSO compared to leaving it to
the hardware.

This commit makes xfrm_output only trigger software GSO in crypto
offload cases for already encapsulated packets in tunnel mode, as not
doing so would then cause the inner tunnel skb->inner_networking_header
to be overwritten and break software GSO for that packet later if the
device turns out to not be capable of HW GSO.

Taking a closer look at the conditions for the original bug, to better
understand the reasons for this change:
- vxlan_build_skb -> iptunnel_handle_offloads sets inner_protocol and
  inner network header.
- then, udp_tunnel_xmit_skb -> ip_tunnel_xmit adds outer transport and
  network headers.
- later in the xmit path, xfrm_output -> xfrm_outer_mode_output ->
  xfrm4_prepare_output -> xfrm4_tunnel_encap_add overwrites the inner
  network header with the one set in ip_tunnel_xmit before adding the
  second outer header.
- __dev_queue_xmit -> validate_xmit_skb checks whether GSO segmentation
  needs to happen based on dev features. In the original bug, the hw
  couldn't segment the packets, so skb_gso_segment was invoked.
- deep in the .gso_segment callback machinery, __skb_udp_tunnel_segment
  tries to use the wrong inner network header, expecting the one set in
  iptunnel_handle_offloads but getting the one set by xfrm instead.
- a bit later, ipv6_gso_segment accesses the wrong memory based on that
  wrong inner network header.

With the new change, the original bug (or similar ones) cannot happen
again, as xfrm will now trigger software GSO before applying a tunnel.
This concern doesn't exist in packet offload mode, when the HW adds
encapsulation headers. For the non-offloaded packets (crypto in SW),
software GSO is still done unconditionally in the else branch.

Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Fixes: a204aef9fd77 ("xfrm: call xfrm_output_gso when inner_protocol is set in xfrm_output")
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>
---
 net/xfrm/xfrm_output.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c
index e5b3e343a5ec1..3cabc87978dd1 100644
--- a/net/xfrm/xfrm_output.c
+++ b/net/xfrm/xfrm_output.c
@@ -799,7 +799,7 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb)
 		skb->encapsulation = 1;
 
 		if (skb_is_gso(skb)) {
-			if (skb->inner_protocol)
+			if (skb->inner_protocol && x->props.mode == XFRM_MODE_TUNNEL)
 				return xfrm_output_gso(net, sk, skb);
 
 			skb_shinfo(skb)->gso_type |= SKB_GSO_ESP;

From 59f37036bb7ab3d554c24abc856aabca01126414 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:36:15 +0000
Subject: [PATCH 0943/2753] btrfs: fix use-after-free on inode when scanning
 root during em shrinking

At btrfs_scan_root() we are accessing the inode's root (and fs_info) in a
call to btrfs_fs_closing() after we have scheduled the inode for a delayed
iput, and that can result in a use-after-free on the inode in case the
cleaner kthread does the iput before we dereference the inode in the call
to btrfs_fs_closing().

Fix this by using the fs_info stored already in a local variable instead
of doing inode->root->fs_info.

Fixes: 102044384056 ("btrfs: make the extent map shrinker run asynchronously as a work queue job")
CC: stable@vger.kernel.org # 6.13+
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 67ce85ff0ae25..bee1b94a10495 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1222,8 +1222,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
 		btrfs_add_delayed_iput(inode);
 
-		if (ctx->scanned >= ctx->nr_to_scan ||
-		    btrfs_fs_closing(inode->root->fs_info))
+		if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
 			break;
 
 		cond_resched();

From c6c9c4d56483d941f567eb921434c25fc6086dfa Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:04:15 +0000
Subject: [PATCH 0944/2753] btrfs: skip inodes without loaded extent maps when
 shrinking extent maps

If there are inodes that don't have any loaded extent maps, we end up
grabbing a reference on them and later adding a delayed iput, which wakes
up the cleaner and makes it do unnecessary work. This is common when for
example the inodes were open only to run stat(2) or all their extent maps
were already released through the folio release callback
(btrfs_release_folio()) or released by a previous run of the shrinker, or
directories which never have extent maps.

Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.13+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 78 +++++++++++++++++++++++++++++++------------
 1 file changed, 57 insertions(+), 21 deletions(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index bee1b94a10495..8c6b85ffd18f6 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1128,6 +1128,8 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	long nr_dropped = 0;
 	struct rb_node *node;
 
+	lockdep_assert_held_write(&tree->lock);
+
 	/*
 	 * Take the mmap lock so that we serialize with the inode logging phase
 	 * of fsync because we may need to set the full sync flag on the inode,
@@ -1139,28 +1141,12 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 	 * to find new extents, which may not be there yet because ordered
 	 * extents haven't completed yet.
 	 *
-	 * We also do a try lock because otherwise we could deadlock. This is
-	 * because the shrinker for this filesystem may be invoked while we are
-	 * in a path that is holding the mmap lock in write mode. For example in
-	 * a reflink operation while COWing an extent buffer, when allocating
-	 * pages for a new extent buffer and under memory pressure, the shrinker
-	 * may be invoked, and therefore we would deadlock by attempting to read
-	 * lock the mmap lock while we are holding already a write lock on it.
+	 * We also do a try lock because we don't want to block for too long and
+	 * we are holding the extent map tree's lock in write mode.
 	 */
 	if (!down_read_trylock(&inode->i_mmap_lock))
 		return 0;
 
-	/*
-	 * We want to be fast so if the lock is busy we don't want to spend time
-	 * waiting for it - either some task is about to do IO for the inode or
-	 * we may have another task shrinking extent maps, here in this code, so
-	 * skip this inode.
-	 */
-	if (!write_trylock(&tree->lock)) {
-		up_read(&inode->i_mmap_lock);
-		return 0;
-	}
-
 	node = rb_first(&tree->root);
 	while (node) {
 		struct rb_node *next = rb_next(node);
@@ -1201,12 +1187,61 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
 			break;
 		node = next;
 	}
-	write_unlock(&tree->lock);
 	up_read(&inode->i_mmap_lock);
 
 	return nr_dropped;
 }
 
+static struct btrfs_inode *find_first_inode_to_shrink(struct btrfs_root *root,
+						      u64 min_ino)
+{
+	struct btrfs_inode *inode;
+	unsigned long from = min_ino;
+
+	xa_lock(&root->inodes);
+	while (true) {
+		struct extent_map_tree *tree;
+
+		inode = xa_find(&root->inodes, &from, ULONG_MAX, XA_PRESENT);
+		if (!inode)
+			break;
+
+		tree = &inode->extent_tree;
+
+		/*
+		 * We want to be fast so if the lock is busy we don't want to
+		 * spend time waiting for it (some task is about to do IO for
+		 * the inode).
+		 */
+		if (!write_trylock(&tree->lock))
+			goto next;
+
+		/*
+		 * Skip inode if it doesn't have loaded extent maps, so we avoid
+		 * getting a reference and doing an iput later. This includes
+		 * cases like files that were opened for things like stat(2), or
+		 * files with all extent maps previously released through the
+		 * release folio callback (btrfs_release_folio()) or released in
+		 * a previous run, or directories which never have extent maps.
+		 */
+		if (RB_EMPTY_ROOT(&tree->root)) {
+			write_unlock(&tree->lock);
+			goto next;
+		}
+
+		if (igrab(&inode->vfs_inode))
+			break;
+
+		write_unlock(&tree->lock);
+next:
+		from = btrfs_ino(inode) + 1;
+		cond_resched_lock(&root->inodes.xa_lock);
+	}
+	xa_unlock(&root->inodes);
+
+	return inode;
+}
+
 static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -1214,9 +1249,10 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 	long nr_dropped = 0;
 	u64 min_ino = fs_info->em_shrinker_last_ino + 1;
 
-	inode = btrfs_find_first_inode(root, min_ino);
+	inode = find_first_inode_to_shrink(root, min_ino);
 	while (inode) {
 		nr_dropped += btrfs_scan_inode(inode, ctx);
+		write_unlock(&inode->extent_tree.lock);
 
 		min_ino = btrfs_ino(inode) + 1;
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
@@ -1227,7 +1263,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 
 		cond_resched();
 
-		inode = btrfs_find_first_inode(root, min_ino);
+		inode = find_first_inode_to_shrink(root, min_ino);
 	}
 
 	if (inode) {

From 15b3b3254d1453a8db038b7d44b311a2d6c71f98 Mon Sep 17 00:00:00 2001
From: Filipe Manana <fdmanana@suse.com>
Date: Sat, 15 Feb 2025 11:11:29 +0000
Subject: [PATCH 0945/2753] btrfs: do regular iput instead of delayed iput
 during extent map shrinking

The extent map shrinker now runs in the system unbound workqueue and no
longer in kswapd context so it can directly do an iput() on inodes even
if that blocks or needs to acquire any lock (we aren't holding any locks
when requesting the delayed iput from the shrinker). So we don't need to
add a delayed iput, wake up the cleaner and delegate the iput() to the
cleaner, which also adds extra contention on the spinlock that protects
the delayed iputs list.

Reported-by: Ivan Shapovalov <intelfx@intelfx.name>
Tested-by: Ivan Shapovalov <intelfx@intelfx.name>
Link: https://lore.kernel.org/linux-btrfs/0414d690ac5680d0d77dfc930606cdc36e42e12f.camel@intelfx.name/
CC: stable@vger.kernel.org # 6.12+
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/extent_map.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 8c6b85ffd18f6..7f46abbd6311b 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -1256,7 +1256,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
 
 		min_ino = btrfs_ino(inode) + 1;
 		fs_info->em_shrinker_last_ino = btrfs_ino(inode);
-		btrfs_add_delayed_iput(inode);
+		iput(&inode->vfs_inode);
 
 		if (ctx->scanned >= ctx->nr_to_scan || btrfs_fs_closing(fs_info))
 			break;

From b1bf18223a8340cf5d52162d320badcfe07b905d Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 17 Feb 2025 20:16:39 +1030
Subject: [PATCH 0946/2753] btrfs: output an error message if btrfs failed to
 find the seed fsid

[BUG]
If btrfs failed to locate the seed device for whatever reason, mounting
the sprouted device will fail without any meaning error message:

  # mkfs.btrfs -f /dev/test/scratch1
  # btrfstune -S1 /dev/test/scratch1
  # mount /dev/test/scratch1 /mnt/btrfs
  # btrfs dev add -f /dev/test/scratch2 /mnt/btrfs
  # umount /mnt/btrfs
  # btrfs dev scan -u
  # btrfs mount /dev/test/scratch2 /mnt/btrfs
  mount: /mnt/btrfs: fsconfig system call failed: No such file or directory.
        dmesg(1) may have more information after failed mount system call.
  # dmesg -t | tail -n6
  BTRFS info (device dm-5): first mount of filesystem 64252ded-5953-4868-b962-cea48f7ac4ea
  BTRFS info (device dm-5): using crc32c (crc32c-generic) checksum algorithm
  BTRFS info (device dm-5): using free-space-tree
  BTRFS error (device dm-5): failed to read chunk tree: -2
  BTRFS error (device dm-5): open_ctree failed: -2

[CAUSE]
The failure to mount is pretty straight forward, just unable to find the
seed device and its fsid, caused by `btrfs dev scan -u`.

But the lack of any useful info is a problem.

[FIX]
Just add an extra error message in open_seed_devices() to indicate the
error.

Now the error message would look like this:

 BTRFS info (device dm-4): first mount of filesystem 7769223d-4db1-4e4c-ac29-0a96f53576ab
 BTRFS info (device dm-4): using crc32c (crc32c-generic) checksum algorithm
 BTRFS info (device dm-4): using free-space-tree
 BTRFS error (device dm-4): failed to find fsid e87c12e6-584b-4e98-8b88-962c33a619ff when attempting to open seed devices
 BTRFS error (device dm-4): failed to read chunk tree: -2
 BTRFS error (device dm-4): open_ctree failed: -2

Link: https://github.com/kdave/btrfs-progs/issues/959
Reviewed-by: Anand Jain <anand.jain@oracle.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index a594f66daedf0..f6ae76815e4b5 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7196,8 +7196,12 @@ static struct btrfs_fs_devices *open_seed_devices(struct btrfs_fs_info *fs_info,
 
 	fs_devices = find_fsid(fsid, NULL);
 	if (!fs_devices) {
-		if (!btrfs_test_opt(fs_info, DEGRADED))
+		if (!btrfs_test_opt(fs_info, DEGRADED)) {
+			btrfs_err(fs_info,
+		"failed to find fsid %pU when attempting to open seed devices",
+				  fsid);
 			return ERR_PTR(-ENOENT);
+		}
 
 		fs_devices = alloc_fs_devices(fsid);
 		if (IS_ERR(fs_devices))

From efa11fd269c139e29b71ec21bc9c9c0063fde40d Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Wed, 19 Feb 2025 09:06:33 +1030
Subject: [PATCH 0947/2753] btrfs: fix data overwriting bug during buffered
 write when block size < page size

[BUG]
When running generic/418 with a btrfs whose block size < page size
(subpage cases), it always fails.

And the following minimal reproducer is more than enough to trigger it
reliably:

workload()
{
        mkfs.btrfs -s 4k -f $dev > /dev/null
        dmesg -C
        mount $dev $mnt
        $fsstree_dir/src/dio-invalidate-cache -r -b 4096 -n 3 -i 1 -f $mnt/diotest
        ret=$?
        umount $mnt
        stop_trace
        if [ $ret -ne 0 ]; then
                fail
        fi
}

for (( i = 0; i < 1024; i++)); do
        echo "=== $i/$runtime ==="
        workload
done

[CAUSE]
With extra trace printk added to the following functions:
- btrfs_buffered_write()
  * Which folio is touched
  * The file offset (start) where the buffered write is at
  * How many bytes are copied
  * The content of the write (the first 2 bytes)

- submit_one_sector()
  * Which folio is touched
  * The position inside the folio
  * The content of the page cache (the first 2 bytes)

- pagecache_isize_extended()
  * The parameters of the function itself
  * The parameters of the folio_zero_range()

Which are enough to show the problem:

  22.158114: btrfs_buffered_write: folio pos=0 start=0 copied=4096 content=0x0101
  22.158161: submit_one_sector: r/i=5/257 folio=0 pos=0 content=0x0101
  22.158609: btrfs_buffered_write: folio pos=0 start=4096 copied=4096 content=0x0101
  22.158634: btrfs_buffered_write: folio pos=0 start=8192 copied=4096 content=0x0101
  22.158650: pagecache_isize_extended: folio=0 from=4096 to=8192 bsize=4096 zero off=4096 len=8192
  22.158682: submit_one_sector: r/i=5/257 folio=0 pos=4096 content=0x0000
  22.158686: submit_one_sector: r/i=5/257 folio=0 pos=8192 content=0x0101

The tool dio-invalidate-cache will start 3 threads, each doing a buffered
write with 0x01 at offset 0, 4096 and 8192, do a fsync, then do a direct read,
and compare the read buffer with the write buffer.

Note that all 3 btrfs_buffered_write() are writing the correct 0x01 into
the page cache.

But at submit_one_sector(), at file offset 4096, the content is zeroed
out, by pagecache_isize_extended().

The race happens like this:
 Thread A is writing into range [4K, 8K).
 Thread B is writing into range [8K, 12k).

               Thread A              |         Thread B
-------------------------------------+------------------------------------
btrfs_buffered_write()               | btrfs_buffered_write()
|- old_isize = 4K;                   | |- old_isize = 4096;
|- btrfs_inode_lock()                | |
|- write into folio range [4K, 8K)   | |
|- pagecache_isize_extended()        | |
|  extend isize from 4096 to 8192    | |
|  no folio_zero_range() called      | |
|- btrfs_inode_lock()                | |
                                     | |- btrfs_inode_lock()
				     | |- write into folio range [8K, 12K)
				     | |- pagecache_isize_extended()
				     | |  calling folio_zero_range(4K, 8K)
				     | |  This is caused by the old_isize is
				     | |  grabbed too early, without any
				     | |  inode lock.
				     | |- btrfs_inode_unlock()

The @old_isize is grabbed without inode lock, causing race between two
buffered write threads and making pagecache_isize_extended() to zero
range which is still containing cached data.

And this is only affecting subpage btrfs, because for regular blocksize
== page size case, the function pagecache_isize_extended() will do
nothing if the block size >= page size.

[FIX]
Grab the old i_size while holding the inode lock.
This means each buffered write thread will have a stable view of the
old inode size, thus avoid the above race.

CC: stable@vger.kernel.org # 5.15+
Fixes: 5e8b9ef30392 ("btrfs: move pos increment and pagecache extension to btrfs_buffered_write")
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Qu Wenruo <wqu@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/file.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index ed3c0d6546c5d..0b568c8d24cbc 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -1090,7 +1090,7 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	u64 lockend;
 	size_t num_written = 0;
 	ssize_t ret;
-	loff_t old_isize = i_size_read(inode);
+	loff_t old_isize;
 	unsigned int ilock_flags = 0;
 	const bool nowait = (iocb->ki_flags & IOCB_NOWAIT);
 	unsigned int bdp_flags = (nowait ? BDP_ASYNC : 0);
@@ -1103,6 +1103,13 @@ ssize_t btrfs_buffered_write(struct kiocb *iocb, struct iov_iter *i)
 	if (ret < 0)
 		return ret;
 
+	/*
+	 * We can only trust the isize with inode lock held, or it can race with
+	 * other buffered writes and cause incorrect call of
+	 * pagecache_isize_extended() to overwrite existing data.
+	 */
+	old_isize = i_size_read(inode);
+
 	ret = generic_write_checks(iocb, i);
 	if (ret <= 0)
 		goto out;

From e9a48ea4d90be251e0d057d41665745caccb0351 Mon Sep 17 00:00:00 2001
From: Stephan Gerhold <stephan.gerhold@linaro.org>
Date: Tue, 18 Feb 2025 16:59:18 +0100
Subject: [PATCH 0948/2753] irqchip/qcom-pdc: Workaround hardware register bug
 on X1E80100

On X1E80100, there is a hardware bug in the register logic of the
IRQ_ENABLE_BANK register: While read accesses work on the normal address,
all write accesses must be made to a shifted address. Without a workaround
for this, the wrong interrupt gets enabled in the PDC and it is impossible
to wakeup from deep suspend (CX collapse). This has not caused problems so
far, because the deep suspend state was not enabled. A workaround is
required now since work is ongoing to fix this.

The PDC has multiple "DRV" regions, each one has a size of 0x10000 and
provides the same set of registers for a particular client in the system.
Linux is one the clients and uses DRV region 2 on X1E. Each "bank" inside
the DRV region consists of 32 interrupt pins that can be enabled using the
IRQ_ENABLE_BANK register:

  IRQ_ENABLE_BANK[bank] = base + IRQ_ENABLE_BANK + bank * sizeof(u32)

On X1E, this works as intended for read access. However, write access to
most banks is shifted by 2:

  IRQ_ENABLE_BANK_X1E[0] = IRQ_ENABLE_BANK[-2]
  IRQ_ENABLE_BANK_X1E[1] = IRQ_ENABLE_BANK[-1]
  IRQ_ENABLE_BANK_X1E[2] = IRQ_ENABLE_BANK[0] = IRQ_ENABLE_BANK[2 - 2]
  IRQ_ENABLE_BANK_X1E[3] = IRQ_ENABLE_BANK[1] = IRQ_ENABLE_BANK[3 - 2]
  IRQ_ENABLE_BANK_X1E[4] = IRQ_ENABLE_BANK[2] = IRQ_ENABLE_BANK[4 - 2]
  IRQ_ENABLE_BANK_X1E[5] = IRQ_ENABLE_BANK[5] (this one works as intended)

The negative indexes underflow to banks of the previous DRV/client region:

  IRQ_ENABLE_BANK_X1E[drv 2][bank 0] = IRQ_ENABLE_BANK[drv 2][bank -2]
                                     = IRQ_ENABLE_BANK[drv 1][bank 5-2]
                                     = IRQ_ENABLE_BANK[drv 1][bank 3]
                                     = IRQ_ENABLE_BANK[drv 1][bank 0 + 3]
  IRQ_ENABLE_BANK_X1E[drv 2][bank 1] = IRQ_ENABLE_BANK[drv 2][bank -1]
                                     = IRQ_ENABLE_BANK[drv 1][bank 5-1]
                                     = IRQ_ENABLE_BANK[drv 1][bank 4]
                                     = IRQ_ENABLE_BANK[drv 1][bank 1 + 3]

Introduce a workaround for the bug by matching the qcom,x1e80100-pdc
compatible and apply the offsets as shown above:

 - Bank 0...1: previous DRV region, bank += 3
 - Bank 1...4: our DRV region, bank -= 2
 - Bank 5: our DRV region, no fixup required

The PDC node in the device tree only describes the DRV region for the Linux
client, but the workaround also requires to map parts of the previous DRV
region to issue writes there. To maintain compatibility with old device
trees, obtain the base address of the preceeding region by applying the
-0x10000 offset. Note that this is also more correct from a conceptual
point of view:

It does not really make use of the other region; it just issues shifted
writes that end up in the registers of the Linux associated DRV region 2.

Signed-off-by: Stephan Gerhold <stephan.gerhold@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/all/20250218-x1e80100-pdc-hw-wa-v2-1-29be4c98e355@linaro.org
---
 drivers/irqchip/qcom-pdc.c | 67 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 64 insertions(+), 3 deletions(-)

diff --git a/drivers/irqchip/qcom-pdc.c b/drivers/irqchip/qcom-pdc.c
index 74b2f124116e3..52d77546aacb9 100644
--- a/drivers/irqchip/qcom-pdc.c
+++ b/drivers/irqchip/qcom-pdc.c
@@ -21,9 +21,11 @@
 #include <linux/types.h>
 
 #define PDC_MAX_GPIO_IRQS	256
+#define PDC_DRV_OFFSET		0x10000
 
 /* Valid only on HW version < 3.2 */
 #define IRQ_ENABLE_BANK		0x10
+#define IRQ_ENABLE_BANK_MAX	(IRQ_ENABLE_BANK + BITS_TO_BYTES(PDC_MAX_GPIO_IRQS))
 #define IRQ_i_CFG		0x110
 
 /* Valid only on HW version >= 3.2 */
@@ -46,13 +48,20 @@ struct pdc_pin_region {
 
 static DEFINE_RAW_SPINLOCK(pdc_lock);
 static void __iomem *pdc_base;
+static void __iomem *pdc_prev_base;
 static struct pdc_pin_region *pdc_region;
 static int pdc_region_cnt;
 static unsigned int pdc_version;
+static bool pdc_x1e_quirk;
+
+static void pdc_base_reg_write(void __iomem *base, int reg, u32 i, u32 val)
+{
+	writel_relaxed(val, base + reg + i * sizeof(u32));
+}
 
 static void pdc_reg_write(int reg, u32 i, u32 val)
 {
-	writel_relaxed(val, pdc_base + reg + i * sizeof(u32));
+	pdc_base_reg_write(pdc_base, reg, i, val);
 }
 
 static u32 pdc_reg_read(int reg, u32 i)
@@ -60,6 +69,34 @@ static u32 pdc_reg_read(int reg, u32 i)
 	return readl_relaxed(pdc_base + reg + i * sizeof(u32));
 }
 
+static void pdc_x1e_irq_enable_write(u32 bank, u32 enable)
+{
+	void __iomem *base;
+
+	/* Remap the write access to work around a hardware bug on X1E */
+	switch (bank) {
+	case 0 ... 1:
+		/* Use previous DRV (client) region and shift to bank 3-4 */
+		base = pdc_prev_base;
+		bank += 3;
+		break;
+	case 2 ... 4:
+		/* Use our own region and shift to bank 0-2 */
+		base = pdc_base;
+		bank -= 2;
+		break;
+	case 5:
+		/* No fixup required for bank 5 */
+		base = pdc_base;
+		break;
+	default:
+		WARN_ON(1);
+		return;
+	}
+
+	pdc_base_reg_write(base, IRQ_ENABLE_BANK, bank, enable);
+}
+
 static void __pdc_enable_intr(int pin_out, bool on)
 {
 	unsigned long enable;
@@ -72,7 +109,11 @@ static void __pdc_enable_intr(int pin_out, bool on)
 
 		enable = pdc_reg_read(IRQ_ENABLE_BANK, index);
 		__assign_bit(mask, &enable, on);
-		pdc_reg_write(IRQ_ENABLE_BANK, index, enable);
+
+		if (pdc_x1e_quirk)
+			pdc_x1e_irq_enable_write(index, enable);
+		else
+			pdc_reg_write(IRQ_ENABLE_BANK, index, enable);
 	} else {
 		enable = pdc_reg_read(IRQ_i_CFG, pin_out);
 		__assign_bit(IRQ_i_CFG_IRQ_ENABLE, &enable, on);
@@ -324,10 +365,29 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent)
 	if (res_size > resource_size(&res))
 		pr_warn("%pOF: invalid reg size, please fix DT\n", node);
 
+	/*
+	 * PDC has multiple DRV regions, each one provides the same set of
+	 * registers for a particular client in the system. Due to a hardware
+	 * bug on X1E, some writes to the IRQ_ENABLE_BANK register must be
+	 * issued inside the previous region. This region belongs to
+	 * a different client and is not described in the device tree. Map the
+	 * region with the expected offset to preserve support for old DTs.
+	 */
+	if (of_device_is_compatible(node, "qcom,x1e80100-pdc")) {
+		pdc_prev_base = ioremap(res.start - PDC_DRV_OFFSET, IRQ_ENABLE_BANK_MAX);
+		if (!pdc_prev_base) {
+			pr_err("%pOF: unable to map previous PDC DRV region\n", node);
+			return -ENXIO;
+		}
+
+		pdc_x1e_quirk = true;
+	}
+
 	pdc_base = ioremap(res.start, res_size);
 	if (!pdc_base) {
 		pr_err("%pOF: unable to map PDC registers\n", node);
-		return -ENXIO;
+		ret = -ENXIO;
+		goto fail;
 	}
 
 	pdc_version = pdc_reg_read(PDC_VERSION_REG, 0);
@@ -363,6 +423,7 @@ static int qcom_pdc_init(struct device_node *node, struct device_node *parent)
 fail:
 	kfree(pdc_region);
 	iounmap(pdc_base);
+	iounmap(pdc_prev_base);
 	return ret;
 }
 

From 92527e473911b835c2c18b0c55c337c33e85ff00 Mon Sep 17 00:00:00 2001
From: Elizabeth Figura <zfigura@codeweavers.com>
Date: Thu, 20 Feb 2025 13:23:34 -0600
Subject: [PATCH 0949/2753] ntsync: Check wait count based on byte size.

GCC versions below 13 incorrectly detect the copy size as being static and too
small to fit in the "fds" array. Work around this by explicitly calculating the
size and returning EINVAL based on that, instead of based on the object count.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502072019.LYoCR9bF-lkp@intel.com/
Suggested-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Elizabeth Figura <zfigura@codeweavers.com>

--

Suggested-by as per Arnd's request, but the only thing I changed was preserving
array_size() [as noted by Geert in the linked thread]. I tested and found no
regressions.

v2: Add missing sign-off
Link: https://lore.kernel.org/r/20250220192334.549167-1-zfigura@codeweavers.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/ntsync.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/misc/ntsync.c b/drivers/misc/ntsync.c
index 0b4e56d59b3da..999026a1ae048 100644
--- a/drivers/misc/ntsync.c
+++ b/drivers/misc/ntsync.c
@@ -873,6 +873,7 @@ static int setup_wait(struct ntsync_device *dev,
 {
 	int fds[NTSYNC_MAX_WAIT_COUNT + 1];
 	const __u32 count = args->count;
+	size_t size = array_size(count, sizeof(fds[0]));
 	struct ntsync_q *q;
 	__u32 total_count;
 	__u32 i, j;
@@ -880,15 +881,14 @@ static int setup_wait(struct ntsync_device *dev,
 	if (args->pad || (args->flags & ~NTSYNC_WAIT_REALTIME))
 		return -EINVAL;
 
-	if (args->count > NTSYNC_MAX_WAIT_COUNT)
+	if (size >= sizeof(fds))
 		return -EINVAL;
 
 	total_count = count;
 	if (args->alert)
 		total_count++;
 
-	if (copy_from_user(fds, u64_to_user_ptr(args->objs),
-			   array_size(count, sizeof(*fds))))
+	if (copy_from_user(fds, u64_to_user_ptr(args->objs), size))
 		return -EFAULT;
 	if (args->alert)
 		fds[count] = args->alert;

From d252435aca44d647d57b84de5108556f9c97614a Mon Sep 17 00:00:00 2001
From: BillXiang <xiangwencheng@lanxincomputing.com>
Date: Fri, 21 Feb 2025 18:45:38 +0800
Subject: [PATCH 0950/2753] riscv: KVM: Remove unnecessary vcpu kick
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the unnecessary kick to the vCPU after writing to the vs_file
of IMSIC in kvm_riscv_vcpu_aia_imsic_inject.

For vCPUs that are running, writing to the vs_file directly forwards
the interrupt as an MSI to them and does not need an extra kick.

For vCPUs that are descheduled after emulating WFI, KVM will enable
the guest external interrupt for that vCPU in
kvm_riscv_aia_wakeon_hgei. This means that writing to the vs_file
will cause a guest external interrupt, which will cause KVM to wake
up the vCPU in hgei_interrupt to handle the interrupt properly.

Signed-off-by: BillXiang <xiangwencheng@lanxincomputing.com>
Reviewed-by: Andrew Jones <ajones@ventanamicro.com>
Reviewed-by: Radim Krčmář <rkrcmar@ventanamicro.com>
Link: https://lore.kernel.org/r/20250221104538.2147-1-xiangwencheng@lanxincomputing.com
Signed-off-by: Anup Patel <anup@brainfault.org>
---
 arch/riscv/kvm/aia_imsic.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/riscv/kvm/aia_imsic.c b/arch/riscv/kvm/aia_imsic.c
index a8085cd8215e3..29ef9c2133a93 100644
--- a/arch/riscv/kvm/aia_imsic.c
+++ b/arch/riscv/kvm/aia_imsic.c
@@ -974,7 +974,6 @@ int kvm_riscv_vcpu_aia_imsic_inject(struct kvm_vcpu *vcpu,
 
 	if (imsic->vsfile_cpu >= 0) {
 		writel(iid, imsic->vsfile_va + IMSIC_MMIO_SETIPNUM_LE);
-		kvm_vcpu_kick(vcpu);
 	} else {
 		eix = &imsic->swfile->eix[iid / BITS_PER_TYPE(u64)];
 		set_bit(iid & (BITS_PER_TYPE(u64) - 1), eix->eip);

From 8510edf191d2df0822ea22d6226e4eef87562271 Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Tue, 18 Feb 2025 20:02:08 +0800
Subject: [PATCH 0951/2753] mm/filemap: fix miscalculated file range for
 filemap_fdatawrite_range_kick()

iocb->ki_pos has been updated with the number of written bytes since
generic_perform_write().

Besides __filemap_fdatawrite_range() accepts the inclusive end of the
data range.

Fixes: 1d4457576570 ("mm: call filemap_fdatawrite_range_kick() after IOCB_DONTCACHE issue")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250218120209.88093-2-jefflexu@linux.alibaba.com
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 4 ++--
 mm/filemap.c       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 9346adf28f7bc..2788df98080f8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2975,8 +2975,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
 		struct address_space *mapping = iocb->ki_filp->f_mapping;
 
-		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos,
-					      iocb->ki_pos + count);
+		filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count,
+					      iocb->ki_pos - 1);
 	}
 
 	return count;
diff --git a/mm/filemap.c b/mm/filemap.c
index 804d7365680c1..d4564a79eb353 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -445,7 +445,7 @@ EXPORT_SYMBOL(filemap_fdatawrite_range);
  * filemap_fdatawrite_range_kick - start writeback on a range
  * @mapping:	target address_space
  * @start:	index to start writeback on
- * @end:	last (non-inclusive) index for writeback
+ * @end:	last (inclusive) index for writeback
  *
  * This is a non-integrity writeback helper, to start writing back folios
  * for the indicated range.

From 927289988068a65ccc168eda881ce60f8712707b Mon Sep 17 00:00:00 2001
From: Jingbo Xu <jefflexu@linux.alibaba.com>
Date: Tue, 18 Feb 2025 20:02:09 +0800
Subject: [PATCH 0952/2753] mm/truncate: don't skip dirty page in
 folio_unmap_invalidate()

... otherwise this is a behavior change for the previous callers of
invalidate_complete_folio2(), e.g. the page invalidation routine.

Fixes: 4a9e23159fd3 ("mm/truncate: add folio_unmap_invalidate() helper")
Signed-off-by: Jingbo Xu <jefflexu@linux.alibaba.com>
Link: https://lore.kernel.org/r/20250218120209.88093-3-jefflexu@linux.alibaba.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 mm/truncate.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/mm/truncate.c b/mm/truncate.c
index e2e115adfbc58..76d8fcd89bd00 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -548,8 +548,6 @@ int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
 
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 
-	if (folio_test_dirty(folio))
-		return 0;
 	if (folio_mapped(folio))
 		unmap_mapping_folio(folio);
 	BUG_ON(folio_mapped(folio));

From 517120728484df1ab8b71cba8d2cad19f52f18a1 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@google.com>
Date: Wed, 19 Feb 2025 22:01:24 -0800
Subject: [PATCH 0953/2753] x86/cpufeatures: Make AVX-VNNI depend on AVX

The 'noxsave' boot option disables support for AVX, but support for the
AVX-VNNI feature was still declared on CPUs that support it.  Fix this.

Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/r/20250220060124.89622-1-ebiggers@kernel.org
---
 arch/x86/kernel/cpu/cpuid-deps.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index 8bd84114c2d96..df838e3bdbe02 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -45,6 +45,7 @@ static const struct cpuid_dep cpuid_deps[] = {
 	{ X86_FEATURE_AES,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_SHA_NI,			X86_FEATURE_XMM2      },
 	{ X86_FEATURE_GFNI,			X86_FEATURE_XMM2      },
+	{ X86_FEATURE_AVX_VNNI,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_FMA,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VAES,			X86_FEATURE_AVX       },
 	{ X86_FEATURE_VPCLMULQDQ,		X86_FEATURE_AVX       },

From dc0a241ceaf3b7df6f1a7658b020c92682b75bfc Mon Sep 17 00:00:00 2001
From: Michael Jeanson <mjeanson@efficios.com>
Date: Wed, 19 Feb 2025 15:53:26 -0500
Subject: [PATCH 0954/2753] rseq: Fix rseq registration with CONFIG_DEBUG_RSEQ

With CONFIG_DEBUG_RSEQ=y, at rseq registration the read-only fields are
copied from user-space, if this copy fails the syscall returns -EFAULT
and the registration should not be activated - but it erroneously is.

Move the activation of the registration after the copy of the fields to
fix this bug.

Fixes: 7d5265ffcd8b ("rseq: Validate read-only fields under DEBUG_RSEQ config")
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/r/20250219205330.324770-1-mjeanson@efficios.com
---
 kernel/rseq.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/rseq.c b/kernel/rseq.c
index 442aba29bc4cf..2cb16091ec0ae 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -507,9 +507,6 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 		return -EINVAL;
 	if (!access_ok(rseq, rseq_len))
 		return -EFAULT;
-	current->rseq = rseq;
-	current->rseq_len = rseq_len;
-	current->rseq_sig = sig;
 #ifdef CONFIG_DEBUG_RSEQ
 	/*
 	 * Initialize the in-kernel rseq fields copy for validation of
@@ -521,6 +518,14 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len,
 	    get_user(rseq_kernel_fields(current)->mm_cid, &rseq->mm_cid))
 		return -EFAULT;
 #endif
+	/*
+	 * Activate the registration by setting the rseq area address, length
+	 * and signature in the task struct.
+	 */
+	current->rseq = rseq;
+	current->rseq_len = rseq_len;
+	current->rseq_sig = sig;
+
 	/*
 	 * If rseq was previously inactive, and has just been
 	 * registered, ensure the cpu_id_start and cpu_id fields

From c9876cdb3ac4dcdf3c710ff02094165982e2a557 Mon Sep 17 00:00:00 2001
From: Brian Ochoa <brianeochoa@gmail.com>
Date: Wed, 19 Feb 2025 10:09:20 -0500
Subject: [PATCH 0955/2753] docs: arch/x86/sva: Fix two grammar errors under
 Background and FAQ

- Correct "in order" to "in order to"
- Append missing quantifier

Signed-off-by: Brian Ochoa <brianeochoa@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250219150920.445802-1-brianeochoa@gmail.com
---
 Documentation/arch/x86/sva.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/arch/x86/sva.rst b/Documentation/arch/x86/sva.rst
index 33cb050059820..6a759984d4712 100644
--- a/Documentation/arch/x86/sva.rst
+++ b/Documentation/arch/x86/sva.rst
@@ -25,7 +25,7 @@ to cache translations for virtual addresses. The IOMMU driver uses the
 mmu_notifier() support to keep the device TLB cache and the CPU cache in
 sync. When an ATS lookup fails for a virtual address, the device should
 use the PRI in order to request the virtual address to be paged into the
-CPU page tables. The device must use ATS again in order the fetch the
+CPU page tables. The device must use ATS again in order to fetch the
 translation before use.
 
 Shared Hardware Workqueues
@@ -216,7 +216,7 @@ submitting work and processing completions.
 
 Single Root I/O Virtualization (SR-IOV) focuses on providing independent
 hardware interfaces for virtualizing hardware. Hence, it's required to be
-almost fully functional interface to software supporting the traditional
+an almost fully functional interface to software supporting the traditional
 BARs, space for interrupts via MSI-X, its own register layout.
 Virtual Functions (VFs) are assisted by the Physical Function (PF)
 driver.

From 38b14061947fa546491656e3f5e388d4fedf8dba Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:10 -0500
Subject: [PATCH 0956/2753] ftrace: Fix accounting of adding subops to a
 manager ops

Function graph uses a subops and manager ops mechanism to attach to
ftrace.  The manager ops connects to ftrace and the functions it connects
to is defined by a list of subops that it manages.

The function hash that defines what the above ops attaches to limits the
functions to attach if the hash has any content. If the hash is empty, it
means to trace all functions.

The creation of the manager ops hash is done by iterating over all the
subops hashes. If any of the subops hashes is empty, it means that the
manager ops hash must trace all functions as well.

The issue is in the creation of the manager ops. When a second subops is
attached, a new hash is created by starting it as NULL and adding the
subops one at a time. But the NULL ops is mistaken as an empty hash, and
once an empty hash is found, it stops the loop of subops and just enables
all functions.

  # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
trace_initcall_start_cb (1)             tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
run_init_process (1)            tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
try_to_run_init_process (1)             tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
x86_pmu_show_pmu_cap (1)                tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
cleanup_rapl_pmus (1)                   tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_free_pcibus_map (1)              tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_types_exit (1)                   tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
uncore_pci_exit.part.0 (1)              tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
kvm_shutdown (1)                tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
vmx_dump_msrs (1)               tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
vmx_cleanup_l1d_flush (1)               tramp: 0xffffffffc0309000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
[..]

Fix this by initializing the new hash to NULL and if the hash is NULL do
not treat it as an empty hash but instead allocate by copying the content
of the first sub ops. Then on subsequent iterations, the new hash will not
be NULL, but the content of the previous subops. If that first subops
attached to all functions, then new hash may assume that the manager ops
also needs to attach to all functions.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.060300046@goodmis.org
Fixes: 5fccc7552ccbc ("ftrace: Add subops logic to allow one ops to manage many")
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 33 ++++++++++++++++++++++-----------
 1 file changed, 22 insertions(+), 11 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 728ecda6e8d4d..bec54dc272049 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -3220,15 +3220,22 @@ static struct ftrace_hash *copy_hash(struct ftrace_hash *src)
  *  The filter_hash updates uses just the append_hash() function
  *  and the notrace_hash does not.
  */
-static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash)
+static int append_hash(struct ftrace_hash **hash, struct ftrace_hash *new_hash,
+		       int size_bits)
 {
 	struct ftrace_func_entry *entry;
 	int size;
 	int i;
 
-	/* An empty hash does everything */
-	if (ftrace_hash_empty(*hash))
-		return 0;
+	if (*hash) {
+		/* An empty hash does everything */
+		if (ftrace_hash_empty(*hash))
+			return 0;
+	} else {
+		*hash = alloc_ftrace_hash(size_bits);
+		if (!*hash)
+			return -ENOMEM;
+	}
 
 	/* If new_hash has everything make hash have everything */
 	if (ftrace_hash_empty(new_hash)) {
@@ -3292,16 +3299,18 @@ static int intersect_hash(struct ftrace_hash **hash, struct ftrace_hash *new_has
 /* Return a new hash that has a union of all @ops->filter_hash entries */
 static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
 {
-	struct ftrace_hash *new_hash;
+	struct ftrace_hash *new_hash = NULL;
 	struct ftrace_ops *subops;
+	int size_bits;
 	int ret;
 
-	new_hash = alloc_ftrace_hash(ops->func_hash->filter_hash->size_bits);
-	if (!new_hash)
-		return NULL;
+	if (ops->func_hash->filter_hash)
+		size_bits = ops->func_hash->filter_hash->size_bits;
+	else
+		size_bits = FTRACE_HASH_DEFAULT_BITS;
 
 	list_for_each_entry(subops, &ops->subop_list, list) {
-		ret = append_hash(&new_hash, subops->func_hash->filter_hash);
+		ret = append_hash(&new_hash, subops->func_hash->filter_hash, size_bits);
 		if (ret < 0) {
 			free_ftrace_hash(new_hash);
 			return NULL;
@@ -3310,7 +3319,8 @@ static struct ftrace_hash *append_hashes(struct ftrace_ops *ops)
 		if (ftrace_hash_empty(new_hash))
 			break;
 	}
-	return new_hash;
+	/* Can't return NULL as that means this failed */
+	return new_hash ? : EMPTY_HASH;
 }
 
 /* Make @ops trace evenything except what all its subops do not trace */
@@ -3505,7 +3515,8 @@ int ftrace_startup_subops(struct ftrace_ops *ops, struct ftrace_ops *subops, int
 		filter_hash = alloc_and_copy_ftrace_hash(size_bits, ops->func_hash->filter_hash);
 		if (!filter_hash)
 			return -ENOMEM;
-		ret = append_hash(&filter_hash, subops->func_hash->filter_hash);
+		ret = append_hash(&filter_hash, subops->func_hash->filter_hash,
+				  size_bits);
 		if (ret < 0) {
 			free_ftrace_hash(filter_hash);
 			return ret;

From 8eb4b09e0bbd30981305643229fe7640ad41b667 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:11 -0500
Subject: [PATCH 0957/2753] ftrace: Do not add duplicate entries in subops
 manager ops

Check if a function is already in the manager ops of a subops. A manager
ops contains multiple subops, and if two or more subops are tracing the
same function, the manager ops only needs a single entry in its hash.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.226762894@goodmis.org
Fixes: 4f554e955614f ("ftrace: Add ftrace_set_filter_ips function")
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index bec54dc272049..6b0c25761ccb1 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -5718,6 +5718,9 @@ __ftrace_match_addr(struct ftrace_hash *hash, unsigned long ip, int remove)
 			return -ENOENT;
 		free_hash_entry(hash, entry);
 		return 0;
+	} else if (__ftrace_lookup_ip(hash, ip) != NULL) {
+		/* Already exists */
+		return 0;
 	}
 
 	entry = add_hash_entry(hash, ip);

From ded9140622358a154efb3a777025fa7f7ae2c2d9 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:12 -0500
Subject: [PATCH 0958/2753] fprobe: Always unregister fgraph function from ops

When the last fprobe is removed, it calls unregister_ftrace_graph() to
remove the graph_ops from function graph. The issue is when it does so, it
calls return before removing the function from its graph ops via
ftrace_set_filter_ips(). This leaves the last function lingering in the
fprobe's fgraph ops and if a probe is added it also enables that last
function (even though the callback will just drop it, it does add unneeded
overhead to make that call).

  # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # echo "f:myevent2 schedule_timeout" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
schedule_timeout (1)           	tramp: 0xffffffffc02f3000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

  # > /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions

  # echo "f:myevent3 kmem_cache_free" >> /sys/kernel/tracing/dynamic_events
  # cat /sys/kernel/tracing/enabled_functions
kmem_cache_free (1)           	tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60
schedule_timeout (1)           	tramp: 0xffffffffc0219000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

The above enabled a fprobe on kernel_clone, and then on schedule_timeout.
The content of the enabled_functions shows the functions that have a
callback attached to them. The fprobe attached to those functions
properly. Then the fprobes were cleared, and enabled_functions was empty
after that. But after adding a fprobe on kmem_cache_free, the
enabled_functions shows that the schedule_timeout was attached again. This
is because it was still left in the fprobe ops that is used to tell
function graph what functions it wants callbacks from.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.393254452@goodmis.org
Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer")
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fprobe.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 2560b312ad576..62e8f7d56602f 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -403,11 +403,9 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
 	lockdep_assert_held(&fprobe_mutex);
 
 	fprobe_graph_active--;
-	if (!fprobe_graph_active) {
-		/* Q: should we unregister it ? */
+	/* Q: should we unregister it ? */
+	if (!fprobe_graph_active)
 		unregister_ftrace_graph(&fprobe_graph_ops);
-		return;
-	}
 
 	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }

From ca26554a1498bc905c4a39fb42d55d93f3ae8df2 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:13 -0500
Subject: [PATCH 0959/2753] fprobe: Fix accounting of when to unregister from
 function graph

When adding a new fprobe, it will update the function hash to the
functions the fprobe is attached to and register with function graph to
have it call the registered functions. The fprobe_graph_active variable
keeps track of the number of fprobes that are using function graph.

If two fprobes attach to the same function, it increments the
fprobe_graph_active for each of them. But when they are removed, the first
fprobe to be removed will see that the function it is attached to is also
used by another fprobe and it will not remove that function from
function_graph. The logic will skip decrementing the fprobe_graph_active
variable.

This causes the fprobe_graph_active variable to not go to zero when all
fprobes are removed, and in doing so it does not unregister from
function graph. As the fgraph ops hash will now be empty, and an empty
filter hash means all functions are enabled, this triggers function graph
to add a callback to the fprobe infrastructure for every function!

 # echo "f:myevent1 kernel_clone" >> /sys/kernel/tracing/dynamic_events
 # echo "f:myevent2 kernel_clone%return" >> /sys/kernel/tracing/dynamic_events
 # cat /sys/kernel/tracing/enabled_functions
kernel_clone (1)           	tramp: 0xffffffffc0024000 (ftrace_graph_func+0x0/0x60) ->ftrace_graph_func+0x0/0x60

 # > /sys/kernel/tracing/dynamic_events
 # cat /sys/kernel/tracing/enabled_functions
trace_initcall_start_cb (1)             tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
run_init_process (1)            tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
try_to_run_init_process (1)             tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
x86_pmu_show_pmu_cap (1)                tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
cleanup_rapl_pmus (1)                   tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_free_pcibus_map (1)              tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_types_exit (1)                   tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
uncore_pci_exit.part.0 (1)              tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
kvm_shutdown (1)                tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
vmx_dump_msrs (1)               tramp: 0xffffffffc0026000 (function_trace_call+0x0/0x170) ->function_trace_call+0x0/0x170
[..]

 # cat /sys/kernel/tracing/enabled_functions | wc -l
54702

If a fprobe is being removed and all its functions are also traced by
other fprobes, still decrement the fprobe_graph_active counter.

Cc: stable@vger.kernel.org
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.565129766@goodmis.org
Fixes: 4346ba1604093 ("fprobe: Rewrite fprobe on function-graph tracer")
Closes: https://lore.kernel.org/all/20250217114918.10397-A-hca@linux.ibm.com/
Reported-by: Heiko Carstens <hca@linux.ibm.com>
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/fprobe.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 62e8f7d56602f..33082c4e8154e 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -407,7 +407,8 @@ static void fprobe_graph_remove_ips(unsigned long *addrs, int num)
 	if (!fprobe_graph_active)
 		unregister_ftrace_graph(&fprobe_graph_ops);
 
-	ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
+	if (num)
+		ftrace_set_filter_ips(&fprobe_graph_ops.ops, addrs, num, 1, 0);
 }
 
 static int symbols_cmp(const void *a, const void *b)
@@ -677,8 +678,7 @@ int unregister_fprobe(struct fprobe *fp)
 	}
 	del_fprobe_hash(fp);
 
-	if (count)
-		fprobe_graph_remove_ips(addrs, count);
+	fprobe_graph_remove_ips(addrs, count);
 
 	kfree_rcu(hlist_array, rcu);
 	fp->hlist_array = NULL;

From e85c5e9792b942381ad92ccd0ff745b6d408a91f Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 20 Feb 2025 15:20:14 -0500
Subject: [PATCH 0960/2753] selftests/ftrace: Update fprobe test to check
 enabled_functions file

A few bugs were found in the fprobe accounting logic along with it using
the function graph infrastructure. Update the fprobe selftest to catch
those bugs in case they or something similar shows up in the future.

The test now checks the enabled_functions file which shows all the
functions attached to ftrace or fgraph. When enabling a fprobe, make sure
that its corresponding function is also added to that file. Also add two
more fprobes to enable to make sure that the fprobe logic works properly
with multiple probes.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250220202055.733001756@goodmis.org
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Tested-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../test.d/dynevent/add_remove_fprobe.tc      | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)

diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
index dc25bcf4f9e2c..449f9d8be7462 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
@@ -7,12 +7,38 @@ echo 0 > events/enable
 echo > dynamic_events
 
 PLACE=$FUNCTION_FORK
+PLACE2="kmem_cache_free"
+PLACE3="schedule_timeout"
 
 echo "f:myevent1 $PLACE" >> dynamic_events
+
+# Make sure the event is attached and is the only one
+grep -q $PLACE enabled_functions
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
 echo "f:myevent2 $PLACE%return" >> dynamic_events
 
+# It should till be the only attached function
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
+# add another event
+echo "f:myevent3 $PLACE2" >> dynamic_events
+
+grep -q $PLACE2 enabled_functions
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 2 ]; then
+	exit_fail
+fi
+
 grep -q myevent1 dynamic_events
 grep -q myevent2 dynamic_events
+grep -q myevent3 dynamic_events
 test -d events/fprobes/myevent1
 test -d events/fprobes/myevent2
 
@@ -21,6 +47,34 @@ echo "-:myevent2" >> dynamic_events
 grep -q myevent1 dynamic_events
 ! grep -q myevent2 dynamic_events
 
+# should still have 2 left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 2 ]; then
+	exit_fail
+fi
+
 echo > dynamic_events
 
+# Should have none left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 0 ]; then
+	exit_fail
+fi
+
+echo "f:myevent4 $PLACE" >> dynamic_events
+
+# Should only have one enabled
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 1 ]; then
+	exit_fail
+fi
+
+echo > dynamic_events
+
+# Should have none left
+cnt=`cat enabled_functions | wc -l`
+if [ $cnt -ne 0 ]; then
+	exit_fail
+fi
+
 clear_trace

From 57b76bedc5c52c66968183b5ef57234894c25ce7 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Thu, 20 Feb 2025 15:07:49 +0100
Subject: [PATCH 0961/2753] ftrace: Correct preemption accounting for function
 tracing.

The function tracer should record the preemption level at the point when
the function is invoked. If the tracing subsystem decrement the
preemption counter it needs to correct this before feeding the data into
the trace buffer. This was broken in the commit cited below while
shifting the preempt-disabled section.

Use tracing_gen_ctx_dec() which properly subtracts one from the
preemption counter on a preemptible kernel.

Cc: stable@vger.kernel.org
Cc: Wander Lairson Costa <wander@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/20250220140749.pfw8qoNZ@linutronix.de
Fixes: ce5e48036c9e7 ("ftrace: disable preemption when recursion locked")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Tested-by: Wander Lairson Costa <wander@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_functions.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
index d358c9935164d..df56f9b760109 100644
--- a/kernel/trace/trace_functions.c
+++ b/kernel/trace/trace_functions.c
@@ -216,7 +216,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 
 	parent_ip = function_get_true_parent_ip(parent_ip, fregs);
 
-	trace_ctx = tracing_gen_ctx();
+	trace_ctx = tracing_gen_ctx_dec();
 
 	data = this_cpu_ptr(tr->array_buffer.data);
 	if (!atomic_read(&data->disabled))
@@ -321,7 +321,6 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	struct trace_array *tr = op->private;
 	struct trace_array_cpu *data;
 	unsigned int trace_ctx;
-	unsigned long flags;
 	int bit;
 
 	if (unlikely(!tr->function_enabled))
@@ -347,8 +346,7 @@ function_no_repeats_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (is_repeat_check(tr, last_info, ip, parent_ip))
 		goto out;
 
-	local_save_flags(flags);
-	trace_ctx = tracing_gen_ctx_flags(flags);
+	trace_ctx = tracing_gen_ctx_dec();
 	process_repeats(tr, ip, parent_ip, last_info, trace_ctx);
 
 	trace_function(tr, ip, parent_ip, trace_ctx);

From 2fa6a01345b538faa7b0fae8f723bb6977312428 Mon Sep 17 00:00:00 2001
From: Adrian Huang <ahuang12@lenovo.com>
Date: Thu, 20 Feb 2025 11:15:28 +0800
Subject: [PATCH 0962/2753] tracing: Fix memory leak when reading set_event
 file

kmemleak reports the following memory leak after reading set_event file:

  # cat /sys/kernel/tracing/set_event

  # cat /sys/kernel/debug/kmemleak
  unreferenced object 0xff110001234449e0 (size 16):
  comm "cat", pid 13645, jiffies 4294981880
  hex dump (first 16 bytes):
    01 00 00 00 00 00 00 00 a8 71 e7 84 ff ff ff ff  .........q......
  backtrace (crc c43abbc):
    __kmalloc_cache_noprof+0x3ca/0x4b0
    s_start+0x72/0x2d0
    seq_read_iter+0x265/0x1080
    seq_read+0x2c9/0x420
    vfs_read+0x166/0xc30
    ksys_read+0xf4/0x1d0
    do_syscall_64+0x79/0x150
    entry_SYSCALL_64_after_hwframe+0x76/0x7e

The issue can be reproduced regardless of whether set_event is empty or
not. Here is an example about the valid content of set_event.

  # cat /sys/kernel/tracing/set_event
  sched:sched_process_fork
  sched:sched_switch
  sched:sched_wakeup
  *:*:mod:trace_events_sample

The root cause is that s_next() returns NULL when nothing is found.
This results in s_stop() attempting to free a NULL pointer because its
parameter is NULL.

Fix the issue by freeing the memory appropriately when s_next() fails
to find anything.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250220031528.7373-1-ahuang12@lenovo.com
Fixes: b355247df104 ("tracing: Cache ":mod:" events for modules not loaded yet")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 4cb275316e51e..513de9ceb80ef 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1591,6 +1591,13 @@ s_next(struct seq_file *m, void *v, loff_t *pos)
 		return iter;
 #endif
 
+	/*
+	 * The iter is allocated in s_start() and passed via the 'v'
+	 * parameter. To stop the iterator, NULL must be returned. But
+	 * the return value is what the 'v' parameter in s_stop() receives
+	 * and frees. Free iter here as it will no longer be used.
+	 */
+	kfree(iter);
 	return NULL;
 }
 
@@ -1667,9 +1674,9 @@ static int s_show(struct seq_file *m, void *v)
 }
 #endif
 
-static void s_stop(struct seq_file *m, void *p)
+static void s_stop(struct seq_file *m, void *v)
 {
-	kfree(p);
+	kfree(v);
 	t_stop(m, NULL);
 }
 

From 4ecaa75771a75f2b78a431bf67dea165d19d72a6 Mon Sep 17 00:00:00 2001
From: Yu-Che Cheng <giver@chromium.org>
Date: Wed, 19 Feb 2025 15:07:48 +0800
Subject: [PATCH 0963/2753] thermal: gov_power_allocator: Fix incorrect
 calculation in divvy_up_power()

divvy_up_power() should use weighted_req_power instead of req_power to
calculate granted_power. Otherwise, granted_power may be unexpected as
the denominator total_req_power is a weighted sum.

This is a mistake made during the previous refactor.

Replace req_power with weighted_req_power in divvy_up_power()
calculation.

Fixes: 912e97c67cc3 ("thermal: gov_power_allocator: Move memory allocation out of throttle()")
Signed-off-by: Yu-Che Cheng <giver@chromium.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/20250219-fix-power-allocator-calc-v1-1-48b860291919@chromium.org
[ rjw: Subject and changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/gov_power_allocator.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 3b644de3292e2..3b626db55b2b9 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -370,7 +370,7 @@ static void divvy_up_power(struct power_actor *power, int num_actors,
 
 	for (i = 0; i < num_actors; i++) {
 		struct power_actor *pa = &power[i];
-		u64 req_range = (u64)pa->req_power * power_range;
+		u64 req_range = (u64)pa->weighted_req_power * power_range;
 
 		pa->granted_power = DIV_ROUND_CLOSEST_ULL(req_range,
 							  total_req_power);

From 7241c886a71797cc51efc6fadec7076fcf6435c2 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Sun, 9 Feb 2025 15:52:52 -0800
Subject: [PATCH 0964/2753] fbdev: hyperv_fb: iounmap() the correct memory when
 removing a device

When a Hyper-V framebuffer device is removed, or the driver is unbound
from a device, any allocated and/or mapped memory must be released. In
particular, MMIO address space that was mapped to the framebuffer must
be unmapped. Current code unmaps the wrong address, resulting in an
error like:

[ 4093.980597] iounmap: bad address 00000000c936c05c

followed by a stack dump.

Commit d21987d709e8 ("video: hyperv: hyperv_fb: Support deferred IO for
Hyper-V frame buffer driver") changed the kind of address stored in
info->screen_base, and the iounmap() call in hvfb_putmem() was not
updated accordingly.

Fix this by updating hvfb_putmem() to unmap the correct address.

Fixes: d21987d709e8 ("video: hyperv: hyperv_fb: Support deferred IO for Hyper-V frame buffer driver")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250209235252.2987-1-mhklinux@outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250209235252.2987-1-mhklinux@outlook.com>
---
 drivers/video/fbdev/hyperv_fb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 7fdb5edd7e2e8..363e4ccfcdb77 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -1080,7 +1080,7 @@ static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
 
 	if (par->need_docopy) {
 		vfree(par->dio_vp);
-		iounmap(info->screen_base);
+		iounmap(par->mmio_vp);
 		vmbus_free_mmio(par->mem->start, screen_fb_size);
 	} else {
 		hvfb_release_phymem(hdev, info->fix.smem_start,

From a85035561025063125f81090e4f2bd65da368c83 Mon Sep 17 00:00:00 2001
From: Birger Koblitz <mail@birger-koblitz.de>
Date: Tue, 18 Feb 2025 18:59:40 +0100
Subject: [PATCH 0965/2753] net: sfp: add quirk for 2.5G OEM BX SFP

The OEM SFP-2.5G-BX10-D/U SFP module pair is meant to operate with
2500Base-X. However, in their EEPROM they incorrectly specify:
Transceiver codes   : 0x00 0x12 0x00 0x00 0x12 0x00 0x01 0x05 0x00
BR, Nominal         : 2500MBd

Use sfp_quirk_2500basex for this module to allow 2500Base-X mode anyway.
Tested on BananaPi R3.

Signed-off-by: Birger Koblitz <mail@birger-koblitz.de>
Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Link: https://patch.msgid.link/20250218-b4-lkmsub-v1-1-1e51dcabed90@birger-koblitz.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 7dbcbf0a4ee26..9369f52977694 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -515,6 +515,8 @@ static const struct sfp_quirk sfp_quirks[] = {
 
 	SFP_QUIRK_F("OEM", "SFP-10G-T", sfp_fixup_rollball_cc),
 	SFP_QUIRK_M("OEM", "SFP-2.5G-T", sfp_quirk_oem_2_5g),
+	SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-D", sfp_quirk_2500basex),
+	SFP_QUIRK_M("OEM", "SFP-2.5G-BX10-U", sfp_quirk_2500basex),
 	SFP_QUIRK_F("OEM", "RTSFP-10", sfp_fixup_rollball_cc),
 	SFP_QUIRK_F("OEM", "RTSFP-10G", sfp_fixup_rollball_cc),
 	SFP_QUIRK_F("Turris", "RTSFP-2.5G", sfp_fixup_rollball),

From c34d999ca3145d9fe858258cc3342ec493f47d2e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:44 +0000
Subject: [PATCH 0966/2753] rxrpc: rxperf: Fix missing decoding of terminal
 magic cookie

The rxperf RPCs seem to have a magic cookie at the end of the request that
was failing to be taken account of by the unmarshalling of the request.
Fix the rxperf code to expect this.

Fixes: 75bfdbf2fca3 ("rxrpc: Implement an in-kernel rxperf server for testing purposes")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-2-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/rxperf.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/rxrpc/rxperf.c b/net/rxrpc/rxperf.c
index 7ef93407be830..e848a4777b8c7 100644
--- a/net/rxrpc/rxperf.c
+++ b/net/rxrpc/rxperf.c
@@ -478,6 +478,18 @@ static int rxperf_deliver_request(struct rxperf_call *call)
 		call->unmarshal++;
 		fallthrough;
 	case 2:
+		ret = rxperf_extract_data(call, true);
+		if (ret < 0)
+			return ret;
+
+		/* Deal with the terminal magic cookie. */
+		call->iov_len = 4;
+		call->kvec[0].iov_len	= call->iov_len;
+		call->kvec[0].iov_base	= call->tmp;
+		iov_iter_kvec(&call->iter, READ, call->kvec, 1, call->iov_len);
+		call->unmarshal++;
+		fallthrough;
+	case 3:
 		ret = rxperf_extract_data(call, false);
 		if (ret < 0)
 			return ret;

From 833fefa074444b1e7f7e834cbdce59ce02562ed0 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:45 +0000
Subject: [PATCH 0967/2753] rxrpc: peer->mtu_lock is redundant

The peer->mtu_lock is only used to lock around writes to peer->max_data -
and nothing else; further, all such writes take place in the I/O thread and
the lock is only ever write-locked and never read-locked.

In a couple of places, the write_seqcount_begin() is wrapped in
preempt_disable/enable(), but not in all places.  This can cause lockdep to
complain:

WARNING: CPU: 0 PID: 1549 at include/linux/seqlock.h:221 rxrpc_input_ack_trailer+0x305/0x430
...
RIP: 0010:rxrpc_input_ack_trailer+0x305/0x430

Fix this by just getting rid of the lock.

Fixes: eeaedc5449d9 ("rxrpc: Implement path-MTU probing using padded PING ACKs (RFC8899)")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-3-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/ar-internal.h | 1 -
 net/rxrpc/input.c       | 2 --
 net/rxrpc/peer_event.c  | 9 +--------
 net/rxrpc/peer_object.c | 1 -
 4 files changed, 1 insertion(+), 12 deletions(-)

diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h
index 5e740c4862034..a64a0cab1bf7f 100644
--- a/net/rxrpc/ar-internal.h
+++ b/net/rxrpc/ar-internal.h
@@ -360,7 +360,6 @@ struct rxrpc_peer {
 	u8			pmtud_jumbo;	/* Max jumbo packets for the MTU */
 	bool			ackr_adv_pmtud;	/* T if the peer advertises path-MTU */
 	unsigned int		ackr_max_data;	/* Maximum data advertised by peer */
-	seqcount_t		mtu_lock;	/* Lockless MTU access management */
 	unsigned int		if_mtu;		/* Local interface MTU (- hdrsize) for this peer */
 	unsigned int		max_data;	/* Maximum packet data capacity for this peer */
 	unsigned short		hdrsize;	/* header size (IP + UDP + RxRPC) */
diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c
index 9047ba13bd31e..24aceb183c2c3 100644
--- a/net/rxrpc/input.c
+++ b/net/rxrpc/input.c
@@ -810,9 +810,7 @@ static void rxrpc_input_ack_trailer(struct rxrpc_call *call, struct sk_buff *skb
 	if (max_mtu < peer->max_data) {
 		trace_rxrpc_pmtud_reduce(peer, sp->hdr.serial, max_mtu,
 					 rxrpc_pmtud_reduce_ack);
-		write_seqcount_begin(&peer->mtu_lock);
 		peer->max_data = max_mtu;
-		write_seqcount_end(&peer->mtu_lock);
 	}
 
 	max_data = umin(max_mtu, peer->max_data);
diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c
index bc283da9ee402..7f4729234957e 100644
--- a/net/rxrpc/peer_event.c
+++ b/net/rxrpc/peer_event.c
@@ -130,9 +130,7 @@ static void rxrpc_adjust_mtu(struct rxrpc_peer *peer, unsigned int mtu)
 			peer->pmtud_bad = max_data + 1;
 
 		trace_rxrpc_pmtud_reduce(peer, 0, max_data, rxrpc_pmtud_reduce_icmp);
-		write_seqcount_begin(&peer->mtu_lock);
 		peer->max_data = max_data;
-		write_seqcount_end(&peer->mtu_lock);
 	}
 }
 
@@ -408,13 +406,8 @@ void rxrpc_input_probe_for_pmtud(struct rxrpc_connection *conn, rxrpc_serial_t a
 	}
 
 	max_data = umin(max_data, peer->ackr_max_data);
-	if (max_data != peer->max_data) {
-		preempt_disable();
-		write_seqcount_begin(&peer->mtu_lock);
+	if (max_data != peer->max_data)
 		peer->max_data = max_data;
-		write_seqcount_end(&peer->mtu_lock);
-		preempt_enable();
-	}
 
 	jumbo = max_data + sizeof(struct rxrpc_jumbo_header);
 	jumbo /= RXRPC_JUMBO_SUBPKTLEN;
diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 0fcc87f0409f9..2ddc8ed687429 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -235,7 +235,6 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp,
 		peer->service_conns = RB_ROOT;
 		seqlock_init(&peer->service_conn_lock);
 		spin_lock_init(&peer->lock);
-		seqcount_init(&peer->mtu_lock);
 		peer->debug_id = atomic_inc_return(&rxrpc_debug_id);
 		peer->recent_srtt_us = UINT_MAX;
 		peer->cong_ssthresh = RXRPC_TX_MAX_WINDOW;

From 71f5409176f4ffd460689eb5423a20332d00e342 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:46 +0000
Subject: [PATCH 0968/2753] rxrpc: Fix locking issues with the peer record hash

rxrpc_new_incoming_peer() can't use spin_lock_bh() whilst its caller has
interrupts disabled.

    WARNING: CPU: 0 PID: 1550 at kernel/softirq.c:369 __local_bh_enable_ip+0x46/0xd0
    ...
    Call Trace:
     rxrpc_alloc_incoming_call+0x1b0/0x400
     rxrpc_new_incoming_call+0x1dd/0x5e0
     rxrpc_input_packet+0x84a/0x920
     rxrpc_io_thread+0x40d/0xb40
     kthread+0x2ec/0x300
     ret_from_fork+0x24/0x40
     ret_from_fork_asm+0x1a/0x30
     </TASK>
    irq event stamp: 1811
    hardirqs last  enabled at (1809): _raw_spin_unlock_irq+0x24/0x50
    hardirqs last disabled at (1810): _raw_read_lock_irq+0x17/0x70
    softirqs last  enabled at (1182): handle_softirqs+0x3ee/0x430
    softirqs last disabled at (1811): rxrpc_new_incoming_peer+0x56/0x120

Fix this by using a plain spin_lock() instead.  IRQs are held, so softirqs
can't happen.

Fixes: a2ea9a907260 ("rxrpc: Use irq-disabling spinlocks between app and I/O thread")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-4-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rxrpc/peer_object.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c
index 2ddc8ed687429..56e09d161a97f 100644
--- a/net/rxrpc/peer_object.c
+++ b/net/rxrpc/peer_object.c
@@ -324,10 +324,10 @@ void rxrpc_new_incoming_peer(struct rxrpc_local *local, struct rxrpc_peer *peer)
 	hash_key = rxrpc_peer_hash_key(local, &peer->srx);
 	rxrpc_init_peer(local, peer, hash_key);
 
-	spin_lock_bh(&rxnet->peer_hash_lock);
+	spin_lock(&rxnet->peer_hash_lock);
 	hash_add_rcu(rxnet->peer_hash, &peer->hash_link, hash_key);
 	list_add_tail(&peer->keepalive_link, &rxnet->peer_keepalive_new);
-	spin_unlock_bh(&rxnet->peer_hash_lock);
+	spin_unlock(&rxnet->peer_hash_lock);
 }
 
 /*

From add117e48df4788a86a21bd0515833c0a6db1ad1 Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:47 +0000
Subject: [PATCH 0969/2753] afs: Fix the server_list to unuse a displaced
 server rather than putting it

When allocating and building an afs_server_list struct object from a VLDB
record, we look up each server address to get the server record for it -
but a server may have more than one entry in the record and we discard the
duplicate pointers.  Currently, however, when we discard, we only put a
server record, not unuse it - but the lookup got as an active-user count.

The active-user count on an afs_server_list object determines its lifetime
whereas the refcount keeps the memory backing it around.  Failing to reduce
the active-user counter prevents the record from being cleaned up and can
lead to multiple copied being seen - and pointing to deleted afs_cell
objects and other such things.

Fix this by switching the incorrect 'put' to an 'unuse' instead.

Without this, occasionally, a dead server record can be seen in
/proc/net/afs/servers and list corruption may be observed:

    list_del corruption. prev->next should be ffff888102423e40, but was 0000000000000000. (prev=ffff88810140cd38)

Fixes: 977e5f8ed0ab ("afs: Split the usage count on struct afs_server")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-5-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/server_list.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/afs/server_list.c b/fs/afs/server_list.c
index 7e7e567a7f8a2..d20cd902ef949 100644
--- a/fs/afs/server_list.c
+++ b/fs/afs/server_list.c
@@ -97,8 +97,8 @@ struct afs_server_list *afs_alloc_server_list(struct afs_volume *volume,
 				break;
 		if (j < slist->nr_servers) {
 			if (slist->servers[j].server == server) {
-				afs_put_server(volume->cell->net, server,
-					       afs_server_trace_put_slist_isort);
+				afs_unuse_server(volume->cell->net, server,
+						 afs_server_trace_put_slist_isort);
 				continue;
 			}
 

From 1f0fc3374f3345ff1d150c5c56ac5016e5d3826a Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 18 Feb 2025 19:22:48 +0000
Subject: [PATCH 0970/2753] afs: Give an afs_server object a ref on the
 afs_cell object it points to

Give an afs_server object a ref on the afs_cell object it points to so that
the cell doesn't get deleted before the server record.

Whilst this is circular (cell -> vol -> server_list -> server -> cell), the
ref only pins the memory, not the lifetime as that's controlled by the
activity counter.  When the volume's activity counter reaches 0, it
detaches from the cell and discards its server list; when a cell's activity
counter reaches 0, it discards its root volume.  At that point, the
circularity is cut.

Fixes: d2ddc776a458 ("afs: Overhaul volume and server record caching and fileserver rotation")
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: Simon Horman <horms@kernel.org>
cc: linux-afs@lists.infradead.org
Link: https://patch.msgid.link/20250218192250.296870-6-dhowells@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 fs/afs/server.c            | 3 +++
 include/trace/events/afs.h | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/fs/afs/server.c b/fs/afs/server.c
index 038f9d0ae3af8..4504e16b458cc 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -163,6 +163,8 @@ static struct afs_server *afs_install_server(struct afs_cell *cell,
 	rb_insert_color(&server->uuid_rb, &net->fs_servers);
 	hlist_add_head_rcu(&server->proc_link, &net->fs_proc);
 
+	afs_get_cell(cell, afs_cell_trace_get_server);
+
 added_dup:
 	write_seqlock(&net->fs_addr_lock);
 	estate = rcu_dereference_protected(server->endpoint_state,
@@ -442,6 +444,7 @@ static void afs_server_rcu(struct rcu_head *rcu)
 			 atomic_read(&server->active), afs_server_trace_free);
 	afs_put_endpoint_state(rcu_access_pointer(server->endpoint_state),
 			       afs_estate_trace_put_server);
+	afs_put_cell(server->cell, afs_cell_trace_put_server);
 	kfree(server);
 }
 
diff --git a/include/trace/events/afs.h b/include/trace/events/afs.h
index b0db89058c911..958a2460330c0 100644
--- a/include/trace/events/afs.h
+++ b/include/trace/events/afs.h
@@ -174,6 +174,7 @@ enum yfs_cm_operation {
 	EM(afs_cell_trace_get_queue_dns,	"GET q-dns ") \
 	EM(afs_cell_trace_get_queue_manage,	"GET q-mng ") \
 	EM(afs_cell_trace_get_queue_new,	"GET q-new ") \
+	EM(afs_cell_trace_get_server,		"GET server") \
 	EM(afs_cell_trace_get_vol,		"GET vol   ") \
 	EM(afs_cell_trace_insert,		"INSERT    ") \
 	EM(afs_cell_trace_manage,		"MANAGE    ") \
@@ -182,6 +183,7 @@ enum yfs_cm_operation {
 	EM(afs_cell_trace_put_destroy,		"PUT destry") \
 	EM(afs_cell_trace_put_queue_work,	"PUT q-work") \
 	EM(afs_cell_trace_put_queue_fail,	"PUT q-fail") \
+	EM(afs_cell_trace_put_server,		"PUT server") \
 	EM(afs_cell_trace_put_vol,		"PUT vol   ") \
 	EM(afs_cell_trace_see_source,		"SEE source") \
 	EM(afs_cell_trace_see_ws,		"SEE ws    ") \

From 3fa337651df581e2beba2d1988344671bfa6f07a Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 19 Feb 2025 08:52:12 +1300
Subject: [PATCH 0971/2753] dt-bindings: net: Move realtek,rtl9301-switch to
 net

Initially realtek,rtl9301-switch was placed under mfd/ because it had
some non-switch related blocks (specifically i2c and reset) but with a
bit more review it has become apparent that this was wrong and the
binding should live under net/.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Acked-by: Lee Jones <lee@kernel.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250218195216.1034220-2-chris.packham@alliedtelesis.co.nz
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/{mfd => net}/realtek,rtl9301-switch.yaml           | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
 rename Documentation/devicetree/bindings/{mfd => net}/realtek,rtl9301-switch.yaml (97%)

diff --git a/Documentation/devicetree/bindings/mfd/realtek,rtl9301-switch.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
similarity index 97%
rename from Documentation/devicetree/bindings/mfd/realtek,rtl9301-switch.yaml
rename to Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
index f053303ab1e6b..d0a93d5f03aa0 100644
--- a/Documentation/devicetree/bindings/mfd/realtek,rtl9301-switch.yaml
+++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
 %YAML 1.2
 ---
-$id: http://devicetree.org/schemas/mfd/realtek,rtl9301-switch.yaml#
+$id: http://devicetree.org/schemas/net/realtek,rtl9301-switch.yaml#
 $schema: http://devicetree.org/meta-schemas/core.yaml#
 
 title: Realtek Switch with Internal CPU

From 92575a2182376e1244fe0c45e85158f5ebbd7b51 Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 19 Feb 2025 08:52:13 +1300
Subject: [PATCH 0972/2753] dt-bindings: net: Add switch ports and interrupts
 to RTL9300

Add bindings for the ethernet-switch and interrupt properties for the
RTL9300.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250218195216.1034220-3-chris.packham@alliedtelesis.co.nz
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/realtek,rtl9301-switch.yaml  | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
index d0a93d5f03aa0..5d29647bea2de 100644
--- a/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
+++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
@@ -14,6 +14,8 @@ description:
   number of different peripherals are accessed through a common register block,
   represented here as a syscon node.
 
+$ref: ethernet-switch.yaml#/$defs/ethernet-ports
+
 properties:
   compatible:
     items:
@@ -28,12 +30,23 @@ properties:
   reg:
     maxItems: 1
 
+  interrupts:
+    maxItems: 2
+
+  interrupt-names:
+    items:
+      - const: switch
+      - const: nic
+
   '#address-cells':
     const: 1
 
   '#size-cells':
     const: 1
 
+  ethernet-ports:
+    type: object
+
 patternProperties:
   'reboot@[0-9a-f]+$':
     $ref: /schemas/power/reset/syscon-reboot.yaml#
@@ -44,6 +57,8 @@ patternProperties:
 required:
   - compatible
   - reg
+  - interrupts
+  - interrupt-names
 
 additionalProperties: false
 
@@ -52,6 +67,9 @@ examples:
     ethernet-switch@1b000000 {
       compatible = "realtek,rtl9301-switch", "syscon", "simple-mfd";
       reg = <0x1b000000 0x10000>;
+      interrupt-parent = <&intc>;
+      interrupts = <23>, <24>;
+      interrupt-names = "switch", "nic";
       #address-cells = <1>;
       #size-cells = <1>;
 
@@ -110,5 +128,17 @@ examples:
           };
         };
       };
+
+      ethernet-ports {
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        port@0 {
+          reg = <0>;
+        };
+        port@1 {
+          reg = <1>;
+        };
+      };
     };
 

From 96757457da0ee36b99ced7a978476d521dddd49d Mon Sep 17 00:00:00 2001
From: Chris Packham <chris.packham@alliedtelesis.co.nz>
Date: Wed, 19 Feb 2025 08:52:14 +1300
Subject: [PATCH 0973/2753] dt-bindings: net: Add Realtek MDIO controller

Add dtschema for the MDIO controller found in the RTL9300 Ethernet
switch. The controller is slightly unusual in that direct MDIO
communication is not possible. We model the MDIO controller with the
MDIO buses as child nodes and the PHYs as children of the buses. The
mapping of switch port number to MDIO bus/addr requires the
ethernet-ports sibling to provide the mapping via the phy-handle
property.

Signed-off-by: Chris Packham <chris.packham@alliedtelesis.co.nz>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250218195216.1034220-4-chris.packham@alliedtelesis.co.nz
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/realtek,rtl9301-mdio.yaml    | 86 +++++++++++++++++++
 .../bindings/net/realtek,rtl9301-switch.yaml  | 31 +++++++
 2 files changed, 117 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml

diff --git a/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml
new file mode 100644
index 0000000000000..02e4e33e99698
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-mdio.yaml
@@ -0,0 +1,86 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/realtek,rtl9301-mdio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Realtek RTL9300 MDIO Controller
+
+maintainers:
+  - Chris Packham <chris.packham@alliedtelesis.co.nz>
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - realtek,rtl9302b-mdio
+              - realtek,rtl9302c-mdio
+              - realtek,rtl9303-mdio
+          - const: realtek,rtl9301-mdio
+      - const: realtek,rtl9301-mdio
+
+  '#address-cells':
+    const: 1
+
+  '#size-cells':
+    const: 0
+
+  reg:
+    maxItems: 1
+
+patternProperties:
+  '^mdio-bus@[0-3]$':
+    $ref: mdio.yaml#
+
+    properties:
+      reg:
+        maxItems: 1
+
+    required:
+      - reg
+
+    patternProperties:
+      '^ethernet-phy@[a-f0-9]+$':
+        type: object
+        $ref: ethernet-phy.yaml#
+        unevaluatedProperties: false
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    mdio-controller@ca00 {
+      compatible = "realtek,rtl9301-mdio";
+      reg = <0xca00 0x200>;
+      #address-cells = <1>;
+      #size-cells = <0>;
+
+      mdio-bus@0 {
+        reg = <0>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-phy@0 {
+          compatible = "ethernet-phy-ieee802.3-c45";
+          reg = <0>;
+        };
+      };
+
+      mdio-bus@1 {
+        reg = <1>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        ethernet-phy@0 {
+          compatible = "ethernet-phy-ieee802.3-c45";
+          reg = <0>;
+        };
+      };
+    };
diff --git a/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
index 5d29647bea2de..80eabc1706698 100644
--- a/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
+++ b/Documentation/devicetree/bindings/net/realtek,rtl9301-switch.yaml
@@ -54,6 +54,9 @@ patternProperties:
   'i2c@[0-9a-f]+$':
     $ref: /schemas/i2c/realtek,rtl9301-i2c.yaml#
 
+  'mdio-controller@[0-9a-f]+$':
+    $ref: realtek,rtl9301-mdio.yaml#
+
 required:
   - compatible
   - reg
@@ -129,15 +132,43 @@ examples:
         };
       };
 
+      mdio-controller@ca00 {
+        compatible = "realtek,rtl9301-mdio";
+        reg = <0xca00 0x200>;
+        #address-cells = <1>;
+        #size-cells = <0>;
+
+        mdio-bus@0 {
+          reg = <0>;
+          #address-cells = <1>;
+          #size-cells = <0>;
+
+          phy1: ethernet-phy@0 {
+            reg = <0>;
+          };
+        };
+        mdio-bus@1 {
+          reg = <1>;
+          #address-cells = <1>;
+          #size-cells = <0>;
+
+          phy2: ethernet-phy@0 {
+            reg = <0>;
+          };
+        };
+      };
+
       ethernet-ports {
         #address-cells = <1>;
         #size-cells = <0>;
 
         port@0 {
           reg = <0>;
+          phy-handle = <&phy1>;
         };
         port@1 {
           reg = <1>;
+          phy-handle = <&phy2>;
         };
       };
     };

From ec061546c6cffbb8929495bba3953f0cc5e177fa Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:27 +0800
Subject: [PATCH 0974/2753] rtnetlink: Lookup device in target netns when
 creating link

When creating link, lookup for existing device in target net namespace
instead of current one.
For example, two links created by:

  # ip link add dummy1 type dummy
  # ip link add netns ns1 dummy1 type dummy

should have no conflict since they are in different namespaces.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-2-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index abe1a461ea67b..0f3e2c6021de0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3867,20 +3867,26 @@ static int __rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	struct nlattr ** const tb = tbs->tb;
 	struct net *net = sock_net(skb->sk);
+	struct net *device_net;
 	struct net_device *dev;
 	struct ifinfomsg *ifm;
 	bool link_specified;
 
+	/* When creating, lookup for existing device in target net namespace */
+	device_net = (nlh->nlmsg_flags & NLM_F_CREATE) &&
+		     (nlh->nlmsg_flags & NLM_F_EXCL) ?
+		     tgt_net : net;
+
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifi_index > 0) {
 		link_specified = true;
-		dev = __dev_get_by_index(net, ifm->ifi_index);
+		dev = __dev_get_by_index(device_net, ifm->ifi_index);
 	} else if (ifm->ifi_index < 0) {
 		NL_SET_ERR_MSG(extack, "ifindex can't be negative");
 		return -EINVAL;
 	} else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME]) {
 		link_specified = true;
-		dev = rtnl_dev_get(net, tb);
+		dev = rtnl_dev_get(device_net, tb);
 	} else {
 		link_specified = false;
 		dev = NULL;

From 69c7be1b903fca2835e80ec506bd1d75ce84fb4d Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:28 +0800
Subject: [PATCH 0975/2753] rtnetlink: Pack newlink() params into struct

There are 4 net namespaces involved when creating links:

 - source netns - where the netlink socket resides,
 - target netns - where to put the device being created,
 - link netns - netns associated with the device (backend),
 - peer netns - netns of peer device.

Currently, two nets are passed to newlink() callback - "src_net"
parameter and "dev_net" (implicitly in net_device). They are set as
follows, depending on netlink attributes in the request.

 +------------+-------------------+---------+---------+
 | peer netns | IFLA_LINK_NETNSID | src_net | dev_net |
 +------------+-------------------+---------+---------+
 |            | absent            | source  | target  |
 | absent     +-------------------+---------+---------+
 |            | present           | link    | link    |
 +------------+-------------------+---------+---------+
 |            | absent            | peer    | target  |
 | present    +-------------------+---------+---------+
 |            | present           | peer    | link    |
 +------------+-------------------+---------+---------+

When IFLA_LINK_NETNSID is present, the device is created in link netns
first and then moved to target netns. This has some side effects,
including extra ifindex allocation, ifname validation and link events.
These could be avoided if we create it in target netns from
the beginning.

On the other hand, the meaning of src_net parameter is ambiguous. It
varies depending on how parameters are passed. It is the effective
link (or peer netns) by design, but some drivers ignore it and use
dev_net instead.

To provide more netns context for drivers, this patch packs existing
newlink() parameters, along with the source netns, link netns and peer
netns, into a struct. The old "src_net" is renamed to "net" to avoid
confusion with real source netns, and will be deprecated later. The use
of src_net are converted to params->net trivially.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-3-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/infiniband/ulp/ipoib/ipoib_netlink.c  |  7 ++++--
 drivers/net/amt.c                             |  7 ++++--
 drivers/net/bareudp.c                         |  7 ++++--
 drivers/net/bonding/bond_netlink.c            |  6 +++--
 drivers/net/can/dev/netlink.c                 |  4 +--
 drivers/net/can/vxcan.c                       |  7 ++++--
 .../ethernet/qualcomm/rmnet/rmnet_config.c    |  7 ++++--
 drivers/net/geneve.c                          |  7 ++++--
 drivers/net/gtp.c                             |  6 +++--
 drivers/net/ipvlan/ipvlan.h                   |  3 +--
 drivers/net/ipvlan/ipvlan_main.c              |  6 +++--
 drivers/net/ipvlan/ipvtap.c                   |  6 ++---
 drivers/net/macsec.c                          |  7 ++++--
 drivers/net/macvlan.c                         | 19 ++++++++------
 drivers/net/macvtap.c                         |  6 ++---
 drivers/net/netkit.c                          | 14 +++++++----
 drivers/net/pfcp.c                            |  5 ++--
 drivers/net/ppp/ppp_generic.c                 |  7 ++++--
 drivers/net/team/team_core.c                  |  6 +++--
 drivers/net/veth.c                            |  7 ++++--
 drivers/net/vrf.c                             |  5 ++--
 drivers/net/vxlan/vxlan_core.c                |  7 ++++--
 drivers/net/wireguard/device.c                |  5 ++--
 drivers/net/wireless/virtual/virt_wifi.c      |  6 +++--
 drivers/net/wwan/wwan_core.c                  | 16 +++++++++---
 include/linux/if_macvlan.h                    |  6 +++--
 include/net/rtnetlink.h                       | 25 ++++++++++++++++---
 net/8021q/vlan_netlink.c                      |  7 ++++--
 net/batman-adv/soft-interface.c               |  9 +++----
 net/bridge/br_netlink.c                       |  6 +++--
 net/caif/chnl_net.c                           |  5 ++--
 net/core/rtnetlink.c                          | 15 ++++++++---
 net/hsr/hsr_netlink.c                         |  6 +++--
 net/ieee802154/6lowpan/core.c                 |  5 ++--
 net/ipv4/ip_gre.c                             | 16 ++++++++----
 net/ipv4/ip_vti.c                             |  6 +++--
 net/ipv4/ipip.c                               |  6 +++--
 net/ipv6/ip6_gre.c                            | 14 ++++++++---
 net/ipv6/ip6_tunnel.c                         |  6 +++--
 net/ipv6/ip6_vti.c                            |  5 ++--
 net/ipv6/sit.c                                |  6 +++--
 net/xfrm/xfrm_interface_core.c                |  7 +++---
 42 files changed, 223 insertions(+), 110 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index 9ad8d98562752..16cb8ced9f35c 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -97,10 +97,13 @@ static int ipoib_changelink(struct net_device *dev, struct nlattr *tb[],
 	return ret;
 }
 
-static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
-				struct nlattr *tb[], struct nlattr *data[],
+static int ipoib_new_child_link(struct net_device *dev,
+				struct rtnl_newlink_params *params,
 				struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net_device *pdev;
 	struct ipoib_dev_priv *ppriv;
 	u16 child_pkey;
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 98c6205ed19f1..96b7ec9a2c13e 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3161,11 +3161,14 @@ static int amt_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
-static int amt_newlink(struct net *net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int amt_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
 	struct amt_dev *amt = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	struct net *net = params->net;
 	int err = -EINVAL;
 
 	amt->net = net;
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index 70814303aab86..fc21dcfb4848d 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -698,10 +698,13 @@ static void bareudp_dellink(struct net_device *dev, struct list_head *head)
 	unregister_netdevice_queue(dev, head);
 }
 
-static int bareudp_newlink(struct net *net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int bareudp_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	struct net *net = params->net;
 	struct bareudp_conf conf;
 	int err;
 
diff --git a/drivers/net/bonding/bond_netlink.c b/drivers/net/bonding/bond_netlink.c
index 2a6a424806aa6..ac5e402c34bc6 100644
--- a/drivers/net/bonding/bond_netlink.c
+++ b/drivers/net/bonding/bond_netlink.c
@@ -564,10 +564,12 @@ static int bond_changelink(struct net_device *bond_dev, struct nlattr *tb[],
 	return 0;
 }
 
-static int bond_newlink(struct net *src_net, struct net_device *bond_dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int bond_newlink(struct net_device *bond_dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err;
 
 	err = bond_changelink(bond_dev, tb, data, extack);
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 01aacdcda2606..f1db9b7ffd4d0 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -624,8 +624,8 @@ static int can_fill_xstats(struct sk_buff *skb, const struct net_device *dev)
 	return -EMSGSIZE;
 }
 
-static int can_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int can_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
 	return -EOPNOTSUPP;
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index ca88119410852..6f8ebb1cfd7b2 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -172,10 +172,13 @@ static void vxcan_setup(struct net_device *dev)
 /* forward declaration for rtnl_create_link() */
 static struct rtnl_link_ops vxcan_link_ops;
 
-static int vxcan_newlink(struct net *peer_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int vxcan_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *peer_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct vxcan_priv *priv;
 	struct net_device *peer;
 
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index f3bea196a8f9d..8151e91395e2e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -117,11 +117,14 @@ static void rmnet_unregister_bridge(struct rmnet_port *port)
 	rmnet_unregister_real_device(bridge_dev);
 }
 
-static int rmnet_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int rmnet_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
 	u32 data_format = RMNET_FLAGS_INGRESS_DEAGGREGATION;
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net_device *real_dev;
 	int mode = RMNET_EPMODE_VND;
 	struct rmnet_endpoint *ep;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index dbb3960126ee7..d6e8b25210523 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1614,10 +1614,13 @@ static void geneve_link_config(struct net_device *dev,
 	geneve_change_mtu(dev, ldev_mtu - info->options_len);
 }
 
-static int geneve_newlink(struct net *net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int geneve_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	struct net *net = params->net;
 	struct geneve_config cfg = {
 		.df = GENEVE_DF_UNSET,
 		.use_udp6_rx_checksums = false,
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index b7b46c5e6399a..762514af8b305 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1462,10 +1462,12 @@ static int gtp_create_sockets(struct gtp_dev *gtp, const struct nlattr *nla,
 #define GTP_TH_MAXLEN	(sizeof(struct udphdr) + sizeof(struct gtp0_header))
 #define GTP_IPV6_MAXLEN	(sizeof(struct ipv6hdr) + GTP_TH_MAXLEN)
 
-static int gtp_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int gtp_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
 	unsigned int role = GTP_ROLE_GGSN;
 	struct gtp_dev *gtp;
 	struct gtp_net *gn;
diff --git a/drivers/net/ipvlan/ipvlan.h b/drivers/net/ipvlan/ipvlan.h
index 025e0c19ec255..50de3ee204dbc 100644
--- a/drivers/net/ipvlan/ipvlan.h
+++ b/drivers/net/ipvlan/ipvlan.h
@@ -166,8 +166,7 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 void *ipvlan_get_L3_hdr(struct ipvl_port *port, struct sk_buff *skb, int *type);
 void ipvlan_count_rx(const struct ipvl_dev *ipvlan,
 		     unsigned int len, bool success, bool mcast);
-int ipvlan_link_new(struct net *src_net, struct net_device *dev,
-		    struct nlattr *tb[], struct nlattr *data[],
+int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack);
 void ipvlan_link_delete(struct net_device *dev, struct list_head *head);
 void ipvlan_link_setup(struct net_device *dev);
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index da3a97a655070..19ce19ca7e324 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -532,11 +532,13 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb,
 	return ret;
 }
 
-int ipvlan_link_new(struct net *src_net, struct net_device *dev,
-		    struct nlattr *tb[], struct nlattr *data[],
+int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack)
 {
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct ipvl_port *port;
 	struct net_device *phy_dev;
 	int err;
diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index 1afc4c47be73f..edd13916831a7 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -73,8 +73,8 @@ static void ipvtap_update_features(struct tap_dev *tap,
 	netdev_update_features(vlan->dev);
 }
 
-static int ipvtap_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int ipvtap_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
 	struct ipvtap_dev *vlantap = netdev_priv(dev);
@@ -97,7 +97,7 @@ static int ipvtap_newlink(struct net *src_net, struct net_device *dev,
 	/* Don't put anything that may fail after macvlan_common_newlink
 	 * because we can't undo what it does.
 	 */
-	err =  ipvlan_link_new(src_net, dev, tb, data, extack);
+	err = ipvlan_link_new(dev, params, extack);
 	if (err) {
 		netdev_rx_handler_unregister(dev);
 		return err;
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 1bc1e5993f56e..1869b0513f57c 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4141,11 +4141,14 @@ static int macsec_add_dev(struct net_device *dev, sci_t sci, u8 icv_len)
 
 static struct lock_class_key macsec_netdev_addr_lock_key;
 
-static int macsec_newlink(struct net *net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int macsec_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
 	struct macsec_dev *macsec = macsec_priv(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
+	struct net *net = params->net;
 	rx_handler_func_t *rx_handler;
 	u8 icv_len = MACSEC_DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index fed4fe2a4748f..f903b414eaeb2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1440,16 +1440,19 @@ static int macvlan_changelink_sources(struct macvlan_dev *vlan, u32 mode,
 	return 0;
 }
 
-int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+int macvlan_common_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
 	struct macvlan_dev *vlan = netdev_priv(dev);
-	struct macvlan_port *port;
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net_device *lowerdev;
-	int err;
-	int macmode;
+	struct macvlan_port *port;
 	bool create = false;
+	int macmode;
+	int err;
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
@@ -1565,11 +1568,11 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
 }
 EXPORT_SYMBOL_GPL(macvlan_common_newlink);
 
-static int macvlan_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int macvlan_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
-	return macvlan_common_newlink(src_net, dev, tb, data, extack);
+	return macvlan_common_newlink(dev, params, extack);
 }
 
 void macvlan_dellink(struct net_device *dev, struct list_head *head)
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 29a5929d48e55..b391a0f740a3f 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -77,8 +77,8 @@ static void macvtap_update_features(struct tap_dev *tap,
 	netdev_update_features(vlan->dev);
 }
 
-static int macvtap_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int macvtap_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
 	struct macvtap_dev *vlantap = netdev_priv(dev);
@@ -105,7 +105,7 @@ static int macvtap_newlink(struct net *src_net, struct net_device *dev,
 	/* Don't put anything that may fail after macvlan_common_newlink
 	 * because we can't undo what it does.
 	 */
-	err = macvlan_common_newlink(src_net, dev, tb, data, extack);
+	err = macvlan_common_newlink(dev, params, extack);
 	if (err) {
 		netdev_rx_handler_unregister(dev);
 		return err;
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 1e1b00756be7d..640a2dbbbd28c 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -327,17 +327,20 @@ static int netkit_validate(struct nlattr *tb[], struct nlattr *data[],
 
 static struct rtnl_link_ops netkit_link_ops;
 
-static int netkit_new_link(struct net *peer_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int netkit_new_link(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
-	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp = tb, *attr;
-	enum netkit_action policy_prim = NETKIT_PASS;
-	enum netkit_action policy_peer = NETKIT_PASS;
 	enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT;
 	enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT;
+	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr;
+	enum netkit_action policy_prim = NETKIT_PASS;
+	enum netkit_action policy_peer = NETKIT_PASS;
+	struct nlattr **data = params->data;
+	struct net *peer_net = params->net;
 	enum netkit_mode mode = NETKIT_L3;
 	unsigned char ifname_assign_type;
+	struct nlattr **tb = params->tb;
 	u16 headroom = 0, tailroom = 0;
 	struct ifinfomsg *ifmp = NULL;
 	struct net_device *peer;
@@ -345,6 +348,7 @@ static int netkit_new_link(struct net *peer_net, struct net_device *dev,
 	struct netkit *nk;
 	int err;
 
+	tbp = tb;
 	if (data) {
 		if (data[IFLA_NETKIT_MODE])
 			mode = nla_get_u32(data[IFLA_NETKIT_MODE]);
diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c
index 68d0d9e92a220..7b0575940e1d6 100644
--- a/drivers/net/pfcp.c
+++ b/drivers/net/pfcp.c
@@ -184,11 +184,12 @@ static int pfcp_add_sock(struct pfcp_dev *pfcp)
 	return PTR_ERR_OR_ZERO(pfcp->sock);
 }
 
-static int pfcp_newlink(struct net *net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int pfcp_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
 	struct pfcp_dev *pfcp = netdev_priv(dev);
+	struct net *net = params->net;
 	struct pfcp_net *pn;
 	int err;
 
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 4583e15ad03a0..b3340f8a6149a 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1303,10 +1303,13 @@ static int ppp_nl_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
-static int ppp_nl_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int ppp_nl_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct ppp_config conf = {
 		.unit = -1,
 		.ifname_is_set = true,
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index f4019815f4736..78edb8186b6d0 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -2218,10 +2218,12 @@ static void team_setup(struct net_device *dev)
 	dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_STAG_TX;
 }
 
-static int team_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int team_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct nlattr **tb = params->tb;
+
 	if (tb[IFLA_ADDRESS] == NULL)
 		eth_hw_addr_random(dev);
 
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 01251868a9c27..7dfda89f072fe 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1765,10 +1765,13 @@ static int veth_init_queues(struct net_device *dev, struct nlattr *tb[])
 	return 0;
 }
 
-static int veth_newlink(struct net *peer_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int veth_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *peer_net = params->net;
+	struct nlattr **tb = params->tb;
 	int err;
 	struct net_device *peer;
 	struct veth_priv *priv;
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 5f21ce1013c42..849c3ced2690e 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1675,11 +1675,12 @@ static void vrf_dellink(struct net_device *dev, struct list_head *head)
 	unregister_netdevice_queue(dev, head);
 }
 
-static int vrf_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int vrf_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	struct nlattr **data = params->data;
 	struct netns_vrf *nn_vrf;
 	bool *add_fib_rules;
 	struct net *net;
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index e2354c02def0e..1a1d03abb6b99 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -4400,10 +4400,13 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
-static int vxlan_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int vxlan_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct vxlan_config conf;
 	int err;
 
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 6cf173a008e78..404cf05bd72bf 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -307,11 +307,12 @@ static void wg_setup(struct net_device *dev)
 	wg->dev = dev;
 }
 
-static int wg_newlink(struct net *src_net, struct net_device *dev,
-		      struct nlattr *tb[], struct nlattr *data[],
+static int wg_newlink(struct net_device *dev,
+		      struct rtnl_newlink_params *params,
 		      struct netlink_ext_ack *extack)
 {
 	struct wg_device *wg = netdev_priv(dev);
+	struct net *src_net = params->net;
 	int ret = -ENOMEM;
 
 	rcu_assign_pointer(wg->creating_net, src_net);
diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
index 4ee3740804667..26905b2b3ba37 100644
--- a/drivers/net/wireless/virtual/virt_wifi.c
+++ b/drivers/net/wireless/virtual/virt_wifi.c
@@ -519,11 +519,13 @@ static rx_handler_result_t virt_wifi_rx_handler(struct sk_buff **pskb)
 }
 
 /* Called with rtnl lock held. */
-static int virt_wifi_newlink(struct net *src_net, struct net_device *dev,
-			     struct nlattr *tb[], struct nlattr *data[],
+static int virt_wifi_newlink(struct net_device *dev,
+			     struct rtnl_newlink_params *params,
 			     struct netlink_ext_ack *extack)
 {
 	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	int err;
 
 	if (!tb[IFLA_LINK])
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index a51e2755991af..a05c49b4e7f80 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -967,15 +967,18 @@ static struct net_device *wwan_rtnl_alloc(struct nlattr *tb[],
 	return dev;
 }
 
-static int wwan_rtnl_newlink(struct net *src_net, struct net_device *dev,
-			     struct nlattr *tb[], struct nlattr *data[],
+static int wwan_rtnl_newlink(struct net_device *dev,
+			     struct rtnl_newlink_params *params,
 			     struct netlink_ext_ack *extack)
 {
 	struct wwan_device *wwandev = wwan_dev_get_by_parent(dev->dev.parent);
-	u32 link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]);
 	struct wwan_netdev_priv *priv = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	u32 link_id;
 	int ret;
 
+	link_id = nla_get_u32(data[IFLA_WWAN_LINK_ID]);
+
 	if (IS_ERR(wwandev))
 		return PTR_ERR(wwandev);
 
@@ -1061,6 +1064,11 @@ static void wwan_create_default_link(struct wwan_device *wwandev,
 {
 	struct nlattr *tb[IFLA_MAX + 1], *linkinfo[IFLA_INFO_MAX + 1];
 	struct nlattr *data[IFLA_WWAN_MAX + 1];
+	struct rtnl_newlink_params params = {
+		.net = &init_net,
+		.tb = tb,
+		.data = data,
+	};
 	struct net_device *dev;
 	struct nlmsghdr *nlh;
 	struct sk_buff *msg;
@@ -1105,7 +1113,7 @@ static void wwan_create_default_link(struct wwan_device *wwandev,
 	if (WARN_ON(IS_ERR(dev)))
 		goto unlock;
 
-	if (WARN_ON(wwan_rtnl_newlink(&init_net, dev, tb, data, NULL))) {
+	if (WARN_ON(wwan_rtnl_newlink(dev, &params, NULL))) {
 		free_netdev(dev);
 		goto unlock;
 	}
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 523025106a643..0f7281e3e4488 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -59,8 +59,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 
 extern void macvlan_common_setup(struct net_device *dev);
 
-extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-				  struct nlattr *tb[], struct nlattr *data[],
+struct rtnl_newlink_params;
+
+extern int macvlan_common_newlink(struct net_device *dev,
+				  struct rtnl_newlink_params *params,
 				  struct netlink_ext_ack *extack);
 
 extern void macvlan_dellink(struct net_device *dev, struct list_head *head);
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index bc0069a8b6ea1..563a6a27436c2 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -69,6 +69,25 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
 		return AF_UNSPEC;
 }
 
+/**
+ * struct rtnl_newlink_params - parameters of rtnl_link_ops::newlink()
+ *
+ * @net: Netns of interest
+ * @src_net: Source netns of rtnetlink socket
+ * @link_net: Link netns by IFLA_LINK_NETNSID, NULL if not specified
+ * @peer_net: Peer netns
+ * @tb: IFLA_* attributes
+ * @data: IFLA_INFO_DATA attributes
+ */
+struct rtnl_newlink_params {
+	struct net *net;
+	struct net *src_net;
+	struct net *link_net;
+	struct net *peer_net;
+	struct nlattr **tb;
+	struct nlattr **data;
+};
+
 /**
  *	struct rtnl_link_ops - rtnetlink link operations
  *
@@ -125,10 +144,8 @@ struct rtnl_link_ops {
 					    struct nlattr *data[],
 					    struct netlink_ext_ack *extack);
 
-	int			(*newlink)(struct net *src_net,
-					   struct net_device *dev,
-					   struct nlattr *tb[],
-					   struct nlattr *data[],
+	int			(*newlink)(struct net_device *dev,
+					   struct rtnl_newlink_params *params,
 					   struct netlink_ext_ack *extack);
 	int			(*changelink)(struct net_device *dev,
 					      struct nlattr *tb[],
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 134419667d59e..91df0f96e32ae 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -135,11 +135,14 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[],
 	return 0;
 }
 
-static int vlan_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int vlan_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net_device *real_dev;
 	unsigned int max_mtu;
 	__be16 proto;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index 822d788a5f86b..d893c80132616 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1077,19 +1077,18 @@ static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[],
 
 /**
  * batadv_softif_newlink() - pre-initialize and register new batadv link
- * @src_net: the applicable net namespace
  * @dev: network device to register
- * @tb: IFLA_INFO_DATA netlink attributes
- * @data: enum batadv_ifla_attrs attributes
+ * @params: rtnl newlink parameters
  * @extack: extended ACK report struct
  *
  * Return: 0 if successful or error otherwise.
  */
-static int batadv_softif_newlink(struct net *src_net, struct net_device *dev,
-				 struct nlattr *tb[], struct nlattr *data[],
+static int batadv_softif_newlink(struct net_device *dev,
+				 struct rtnl_newlink_params *params,
 				 struct netlink_ext_ack *extack)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
+	struct nlattr **data = params->data;
 	const char *algo_name;
 	int err;
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 3e0f47203f2a1..6e337937d0d7b 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1553,11 +1553,13 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 	return 0;
 }
 
-static int br_dev_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int br_dev_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
 	struct net_bridge *br = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	int err;
 
 	err = register_netdevice(dev);
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 94ad09e36df2a..fa6a3c2634a8c 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -438,10 +438,11 @@ static void caif_netlink_parms(struct nlattr *data[],
 	}
 }
 
-static int ipcaif_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int ipcaif_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
 	int ret;
 	struct chnl_net *caifdev;
 	ASSERT_RTNL();
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 0f3e2c6021de0..9ebbde0d131ce 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3767,7 +3767,13 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 			       struct netlink_ext_ack *extack)
 {
 	unsigned char name_assign_type = NET_NAME_USER;
-	struct net *net = sock_net(skb->sk);
+	struct rtnl_newlink_params params = {
+		.src_net = sock_net(skb->sk),
+		.link_net = link_net,
+		.peer_net = peer_net,
+		.tb = tb,
+		.data = data,
+	};
 	u32 portid = NETLINK_CB(skb).portid;
 	struct net_device *dev;
 	char ifname[IFNAMSIZ];
@@ -3792,13 +3798,14 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 
 	dev->ifindex = ifm->ifi_index;
 
+	params.net = params.src_net;
 	if (link_net)
-		net = link_net;
+		params.net = link_net;
 	if (peer_net)
-		net = peer_net;
+		params.net = peer_net;
 
 	if (ops->newlink)
-		err = ops->newlink(net, dev, tb, data, extack);
+		err = ops->newlink(dev, &params, extack);
 	else
 		err = register_netdevice(dev);
 	if (err < 0) {
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index b68f2f71d0e1f..39add538ba998 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -29,10 +29,12 @@ static const struct nla_policy hsr_policy[IFLA_HSR_MAX + 1] = {
 /* Here, it seems a netdevice has already been allocated for us, and the
  * hsr_dev_setup routine has been executed. Nice!
  */
-static int hsr_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int hsr_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
 	enum hsr_version proto_version;
 	unsigned char multicast_spec;
 	u8 proto = HSR_PROTOCOL_HSR;
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 175efd860f7b4..704bf9e3f0975 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -129,10 +129,11 @@ static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[],
 	return 0;
 }
 
-static int lowpan_newlink(struct net *src_net, struct net_device *ldev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int lowpan_newlink(struct net_device *ldev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct nlattr **tb = params->tb;
 	struct net_device *wdev;
 	int ret;
 
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index c9f11a046c263..1fe9b13d351c1 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1396,10 +1396,12 @@ ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[])
 	return 0;
 }
 
-static int ipgre_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int ipgre_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct ip_tunnel_parm_kern p;
 	__u32 fwmark = 0;
 	int err;
@@ -1414,10 +1416,12 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev,
 	return ip_tunnel_newlink(dev, tb, &p, fwmark);
 }
 
-static int erspan_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int erspan_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct ip_tunnel_parm_kern p;
 	__u32 fwmark = 0;
 	int err;
@@ -1697,6 +1701,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 					u8 name_assign_type)
 {
+	struct rtnl_newlink_params params = { .net = net };
 	struct nlattr *tb[IFLA_MAX + 1];
 	struct net_device *dev;
 	LIST_HEAD(list_kill);
@@ -1704,6 +1709,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	int err;
 
 	memset(&tb, 0, sizeof(tb));
+	params.tb = tb;
 
 	dev = rtnl_create_link(net, name, name_assign_type,
 			       &ipgre_tap_ops, tb, NULL);
@@ -1714,7 +1720,7 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	t = netdev_priv(dev);
 	t->collect_md = true;
 
-	err = ipgre_newlink(net, dev, tb, NULL, NULL);
+	err = ipgre_newlink(dev, &params, NULL);
 	if (err < 0) {
 		free_netdev(dev);
 		return ERR_PTR(err);
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index f0b4419cef349..b901bee03e6d6 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -575,11 +575,13 @@ static void vti_netlink_parms(struct nlattr *data[],
 		*fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
 }
 
-static int vti_newlink(struct net *src_net, struct net_device *dev,
-		       struct nlattr *tb[], struct nlattr *data[],
+static int vti_newlink(struct net_device *dev,
+		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
 	struct ip_tunnel_parm_kern parms;
+	struct nlattr **tb = params->tb;
 	__u32 fwmark = 0;
 
 	vti_netlink_parms(data, &parms, &fwmark);
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index dc0db5895e0e0..a8b844bcfc645 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -436,11 +436,13 @@ static void ipip_netlink_parms(struct nlattr *data[],
 		*fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
-static int ipip_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int ipip_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct ip_tunnel_encap ipencap;
 	struct ip_tunnel_parm_kern p;
 	__u32 fwmark = 0;
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 235808cfec705..863852abe8eac 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -2005,11 +2005,14 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
 	return err;
 }
 
-static int ip6gre_newlink(struct net *src_net, struct net_device *dev,
-			  struct nlattr *tb[], struct nlattr *data[],
+static int ip6gre_newlink(struct net_device *dev,
+			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
 	struct ip6_tnl *nt = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net *net = dev_net(dev);
 	struct ip6gre_net *ign;
 	int err;
@@ -2241,11 +2244,14 @@ static void ip6erspan_tap_setup(struct net_device *dev)
 	netif_keep_dst(dev);
 }
 
-static int ip6erspan_newlink(struct net *src_net, struct net_device *dev,
-			     struct nlattr *tb[], struct nlattr *data[],
+static int ip6erspan_newlink(struct net_device *dev,
+			     struct rtnl_newlink_params *params,
 			     struct netlink_ext_ack *extack)
 {
 	struct ip6_tnl *nt = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	struct net *src_net = params->net;
+	struct nlattr **tb = params->tb;
 	struct net *net = dev_net(dev);
 	struct ip6gre_net *ign;
 	int err;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 48fd53b989726..54b843d208708 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2002,10 +2002,12 @@ static void ip6_tnl_netlink_parms(struct nlattr *data[],
 		parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]);
 }
 
-static int ip6_tnl_newlink(struct net *src_net, struct net_device *dev,
-			   struct nlattr *tb[], struct nlattr *data[],
+static int ip6_tnl_newlink(struct net_device *dev,
+			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct ip_tunnel_encap ipencap;
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 590737c275379..993f85aeb8823 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -997,10 +997,11 @@ static void vti6_netlink_parms(struct nlattr *data[],
 		parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]);
 }
 
-static int vti6_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
+static int vti6_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
 	struct net *net = dev_net(dev);
 	struct ip6_tnl *nt;
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 39bd8951bfca1..e2bd52cabdee5 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1550,10 +1550,12 @@ static bool ipip6_netlink_6rd_parms(struct nlattr *data[],
 }
 #endif
 
-static int ipip6_newlink(struct net *src_net, struct net_device *dev,
-			 struct nlattr *tb[], struct nlattr *data[],
+static int ipip6_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
+	struct nlattr **tb = params->tb;
 	struct net *net = dev_net(dev);
 	struct ip_tunnel *nt;
 	struct ip_tunnel_encap ipencap;
diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index c397eb99d8679..5659a6cadd519 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -814,10 +814,11 @@ static void xfrmi_netlink_parms(struct nlattr *data[],
 		parms->collect_md = true;
 }
 
-static int xfrmi_newlink(struct net *src_net, struct net_device *dev,
-			struct nlattr *tb[], struct nlattr *data[],
-			struct netlink_ext_ack *extack)
+static int xfrmi_newlink(struct net_device *dev,
+			 struct rtnl_newlink_params *params,
+			 struct netlink_ext_ack *extack)
 {
+	struct nlattr **data = params->data;
 	struct net *net = dev_net(dev);
 	struct xfrm_if_parms p = {};
 	struct xfrm_if *xi;

From cf517ac16ad96f3953d65ea198c0b310a1ffa14f Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:29 +0800
Subject: [PATCH 0976/2753] net: Use link/peer netns in newlink() of
 rtnl_link_ops

Add two helper functions - rtnl_newlink_link_net() and
rtnl_newlink_peer_net() for netns fallback logic. Peer netns falls back
to link netns, and link netns falls back to source netns.

Convert the use of params->net in netdevice drivers to one of the helper
functions for clarity.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-4-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/infiniband/ulp/ipoib/ipoib_netlink.c    |  4 ++--
 drivers/net/amt.c                               |  6 +++---
 drivers/net/bareudp.c                           |  4 ++--
 drivers/net/can/vxcan.c                         |  2 +-
 .../net/ethernet/qualcomm/rmnet/rmnet_config.c  |  4 ++--
 drivers/net/geneve.c                            |  4 ++--
 drivers/net/gtp.c                               |  6 +++---
 drivers/net/ipvlan/ipvlan_main.c                |  4 ++--
 drivers/net/macsec.c                            |  4 ++--
 drivers/net/macvlan.c                           |  4 ++--
 drivers/net/netkit.c                            |  2 +-
 drivers/net/pfcp.c                              |  6 +++---
 drivers/net/ppp/ppp_generic.c                   |  4 ++--
 drivers/net/veth.c                              |  2 +-
 drivers/net/vxlan/vxlan_core.c                  |  4 ++--
 drivers/net/wireguard/device.c                  |  4 ++--
 drivers/net/wireless/virtual/virt_wifi.c        |  4 ++--
 drivers/net/wwan/wwan_core.c                    |  2 +-
 include/net/rtnetlink.h                         | 17 +++++++++++++++++
 net/8021q/vlan_netlink.c                        |  4 ++--
 net/hsr/hsr_netlink.c                           |  8 ++++----
 21 files changed, 58 insertions(+), 41 deletions(-)

diff --git a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
index 16cb8ced9f35c..53db7c8191e38 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_netlink.c
@@ -101,8 +101,8 @@ static int ipoib_new_child_link(struct net_device *dev,
 				struct rtnl_newlink_params *params,
 				struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct net_device *pdev;
 	struct ipoib_dev_priv *ppriv;
@@ -112,7 +112,7 @@ static int ipoib_new_child_link(struct net_device *dev,
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
 
-	pdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	pdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!pdev || pdev->type != ARPHRD_INFINIBAND)
 		return -ENODEV;
 
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 96b7ec9a2c13e..53899b70fae1c 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3165,13 +3165,13 @@ static int amt_newlink(struct net_device *dev,
 		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct amt_dev *amt = netdev_priv(dev);
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = params->net;
 	int err = -EINVAL;
 
-	amt->net = net;
+	amt->net = link_net;
 	amt->mode = nla_get_u32(data[IFLA_AMT_MODE]);
 
 	if (data[IFLA_AMT_MAX_TUNNELS] &&
@@ -3186,7 +3186,7 @@ static int amt_newlink(struct net_device *dev,
 	amt->hash_buckets = AMT_HSIZE;
 	amt->nr_tunnels = 0;
 	get_random_bytes(&amt->hash_seed, sizeof(amt->hash_seed));
-	amt->stream_dev = dev_get_by_index(net,
+	amt->stream_dev = dev_get_by_index(link_net,
 					   nla_get_u32(data[IFLA_AMT_LINK]));
 	if (!amt->stream_dev) {
 		NL_SET_ERR_MSG_ATTR(extack, tb[IFLA_AMT_LINK],
diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
index fc21dcfb4848d..d1473c5f8eefc 100644
--- a/drivers/net/bareudp.c
+++ b/drivers/net/bareudp.c
@@ -702,9 +702,9 @@ static int bareudp_newlink(struct net_device *dev,
 			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = params->net;
 	struct bareudp_conf conf;
 	int err;
 
@@ -712,7 +712,7 @@ static int bareudp_newlink(struct net_device *dev,
 	if (err)
 		return err;
 
-	err = bareudp_configure(net, dev, &conf, extack);
+	err = bareudp_configure(link_net, dev, &conf, extack);
 	if (err)
 		return err;
 
diff --git a/drivers/net/can/vxcan.c b/drivers/net/can/vxcan.c
index 6f8ebb1cfd7b2..99a78a7571674 100644
--- a/drivers/net/can/vxcan.c
+++ b/drivers/net/can/vxcan.c
@@ -176,8 +176,8 @@ static int vxcan_newlink(struct net_device *dev,
 			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
 	struct nlattr **data = params->data;
-	struct net *peer_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct vxcan_priv *priv;
 	struct net_device *peer;
diff --git a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
index 8151e91395e2e..ba8763cac9d9e 100644
--- a/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
+++ b/drivers/net/ethernet/qualcomm/rmnet/rmnet_config.c
@@ -121,9 +121,9 @@ static int rmnet_newlink(struct net_device *dev,
 			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	u32 data_format = RMNET_FLAGS_INGRESS_DEAGGREGATION;
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct net_device *real_dev;
 	int mode = RMNET_EPMODE_VND;
@@ -137,7 +137,7 @@ static int rmnet_newlink(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev) {
 		NL_SET_ERR_MSG_MOD(extack, "link does not exist");
 		return -ENODEV;
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index d6e8b25210523..fc62b25e0362a 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1618,9 +1618,9 @@ static int geneve_newlink(struct net_device *dev,
 			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = params->net;
 	struct geneve_config cfg = {
 		.df = GENEVE_DF_UNSET,
 		.use_udp6_rx_checksums = false,
@@ -1634,7 +1634,7 @@ static int geneve_newlink(struct net_device *dev,
 	if (err)
 		return err;
 
-	err = geneve_configure(net, dev, extack, &cfg);
+	err = geneve_configure(link_net, dev, extack, &cfg);
 	if (err)
 		return err;
 
diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
index 762514af8b305..ef793607890d9 100644
--- a/drivers/net/gtp.c
+++ b/drivers/net/gtp.c
@@ -1466,8 +1466,8 @@ static int gtp_newlink(struct net_device *dev,
 		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	unsigned int role = GTP_ROLE_GGSN;
 	struct gtp_dev *gtp;
 	struct gtp_net *gn;
@@ -1498,7 +1498,7 @@ static int gtp_newlink(struct net_device *dev,
 	gtp->restart_count = nla_get_u8_default(data[IFLA_GTP_RESTART_COUNT],
 						0);
 
-	gtp->net = src_net;
+	gtp->net = link_net;
 
 	err = gtp_hashtable_new(gtp, hashsize);
 	if (err < 0)
@@ -1528,7 +1528,7 @@ static int gtp_newlink(struct net_device *dev,
 		goto out_encap;
 	}
 
-	gn = net_generic(src_net, gtp_net_id);
+	gn = net_generic(link_net, gtp_net_id);
 	list_add(&gtp->list, &gn->gtp_dev_list);
 	dev->priv_destructor = gtp_destructor;
 
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 19ce19ca7e324..b56144ca2fded 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -535,9 +535,9 @@ static int ipvlan_nl_fillinfo(struct sk_buff *skb,
 int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 		    struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct ipvl_dev *ipvlan = netdev_priv(dev);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct ipvl_port *port;
 	struct net_device *phy_dev;
@@ -547,7 +547,7 @@ int ipvlan_link_new(struct net_device *dev, struct rtnl_newlink_params *params,
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
 
-	phy_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	phy_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!phy_dev)
 		return -ENODEV;
 
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 1869b0513f57c..4de5d63fd577c 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -4145,10 +4145,10 @@ static int macsec_newlink(struct net_device *dev,
 			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct macsec_dev *macsec = macsec_priv(dev);
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = params->net;
 	rx_handler_func_t *rx_handler;
 	u8 icv_len = MACSEC_DEFAULT_ICV_LEN;
 	struct net_device *real_dev;
@@ -4157,7 +4157,7 @@ static int macsec_newlink(struct net_device *dev,
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
-	real_dev = __dev_get_by_index(net, nla_get_u32(tb[IFLA_LINK]));
+	real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev)
 		return -ENODEV;
 	if (real_dev->type != ARPHRD_ETHER)
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index f903b414eaeb2..4e9d54be887c1 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -1444,9 +1444,9 @@ int macvlan_common_newlink(struct net_device *dev,
 			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct macvlan_dev *vlan = netdev_priv(dev);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct net_device *lowerdev;
 	struct macvlan_port *port;
@@ -1457,7 +1457,7 @@ int macvlan_common_newlink(struct net_device *dev,
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
 
-	lowerdev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	lowerdev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (lowerdev == NULL)
 		return -ENODEV;
 
diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 640a2dbbbd28c..751347392570e 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -331,13 +331,13 @@ static int netkit_new_link(struct net_device *dev,
 			   struct rtnl_newlink_params *params,
 			   struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
 	enum netkit_scrub scrub_prim = NETKIT_SCRUB_DEFAULT;
 	enum netkit_scrub scrub_peer = NETKIT_SCRUB_DEFAULT;
 	struct nlattr *peer_tb[IFLA_MAX + 1], **tbp, *attr;
 	enum netkit_action policy_prim = NETKIT_PASS;
 	enum netkit_action policy_peer = NETKIT_PASS;
 	struct nlattr **data = params->data;
-	struct net *peer_net = params->net;
 	enum netkit_mode mode = NETKIT_L3;
 	unsigned char ifname_assign_type;
 	struct nlattr **tb = params->tb;
diff --git a/drivers/net/pfcp.c b/drivers/net/pfcp.c
index 7b0575940e1d6..f873a92d24459 100644
--- a/drivers/net/pfcp.c
+++ b/drivers/net/pfcp.c
@@ -188,12 +188,12 @@ static int pfcp_newlink(struct net_device *dev,
 			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct pfcp_dev *pfcp = netdev_priv(dev);
-	struct net *net = params->net;
 	struct pfcp_net *pn;
 	int err;
 
-	pfcp->net = net;
+	pfcp->net = link_net;
 
 	err = pfcp_add_sock(pfcp);
 	if (err) {
@@ -207,7 +207,7 @@ static int pfcp_newlink(struct net_device *dev,
 		goto exit_del_pfcp_sock;
 	}
 
-	pn = net_generic(net, pfcp_net_id);
+	pn = net_generic(link_net, pfcp_net_id);
 	list_add(&pfcp->list, &pn->pfcp_dev_list);
 
 	netdev_dbg(dev, "registered new PFCP interface\n");
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index b3340f8a6149a..6220866258fc4 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -1307,8 +1307,8 @@ static int ppp_nl_newlink(struct net_device *dev,
 			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct ppp_config conf = {
 		.unit = -1,
@@ -1346,7 +1346,7 @@ static int ppp_nl_newlink(struct net_device *dev,
 	if (!tb[IFLA_IFNAME] || !nla_len(tb[IFLA_IFNAME]) || !*(char *)nla_data(tb[IFLA_IFNAME]))
 		conf.ifname_is_set = false;
 
-	err = ppp_dev_configure(src_net, dev, &conf);
+	err = ppp_dev_configure(link_net, dev, &conf);
 
 out_unlock:
 	mutex_unlock(&ppp_mutex);
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 7dfda89f072fe..ba3ae2d8092f8 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1769,8 +1769,8 @@ static int veth_newlink(struct net_device *dev,
 			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct net *peer_net = rtnl_newlink_peer_net(params);
 	struct nlattr **data = params->data;
-	struct net *peer_net = params->net;
 	struct nlattr **tb = params->tb;
 	int err;
 	struct net_device *peer;
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 1a1d03abb6b99..227d7f5a302a9 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -4404,8 +4404,8 @@ static int vxlan_newlink(struct net_device *dev,
 			 struct rtnl_newlink_params *params,
 			 struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct vxlan_config conf;
 	int err;
@@ -4414,7 +4414,7 @@ static int vxlan_newlink(struct net_device *dev,
 	if (err)
 		return err;
 
-	return __vxlan_dev_create(src_net, dev, &conf, extack);
+	return __vxlan_dev_create(link_net, dev, &conf, extack);
 }
 
 static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[],
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 404cf05bd72bf..c496d35b266dd 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -311,11 +311,11 @@ static int wg_newlink(struct net_device *dev,
 		      struct rtnl_newlink_params *params,
 		      struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct wg_device *wg = netdev_priv(dev);
-	struct net *src_net = params->net;
 	int ret = -ENOMEM;
 
-	rcu_assign_pointer(wg->creating_net, src_net);
+	rcu_assign_pointer(wg->creating_net, link_net);
 	init_rwsem(&wg->static_identity.lock);
 	mutex_init(&wg->socket_update_lock);
 	mutex_init(&wg->device_update_lock);
diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
index 26905b2b3ba37..f9d11a0233136 100644
--- a/drivers/net/wireless/virtual/virt_wifi.c
+++ b/drivers/net/wireless/virtual/virt_wifi.c
@@ -524,7 +524,7 @@ static int virt_wifi_newlink(struct net_device *dev,
 			     struct netlink_ext_ack *extack)
 {
 	struct virt_wifi_netdev_priv *priv = netdev_priv(dev);
-	struct net *src_net = params->net;
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **tb = params->tb;
 	int err;
 
@@ -534,7 +534,7 @@ static int virt_wifi_newlink(struct net_device *dev,
 	netif_carrier_off(dev);
 
 	priv->upperdev = dev;
-	priv->lowerdev = __dev_get_by_index(src_net,
+	priv->lowerdev = __dev_get_by_index(link_net,
 					    nla_get_u32(tb[IFLA_LINK]));
 
 	if (!priv->lowerdev)
diff --git a/drivers/net/wwan/wwan_core.c b/drivers/net/wwan/wwan_core.c
index a05c49b4e7f80..63a47d420bc59 100644
--- a/drivers/net/wwan/wwan_core.c
+++ b/drivers/net/wwan/wwan_core.c
@@ -1065,7 +1065,7 @@ static void wwan_create_default_link(struct wwan_device *wwandev,
 	struct nlattr *tb[IFLA_MAX + 1], *linkinfo[IFLA_INFO_MAX + 1];
 	struct nlattr *data[IFLA_WWAN_MAX + 1];
 	struct rtnl_newlink_params params = {
-		.net = &init_net,
+		.src_net = &init_net,
 		.tb = tb,
 		.data = data,
 	};
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 563a6a27436c2..b22a106621fb4 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -88,6 +88,23 @@ struct rtnl_newlink_params {
 	struct nlattr **data;
 };
 
+/* Get effective link netns from newlink params. Generally, this is link_net
+ * and falls back to src_net. But for compatibility, a driver may * choose to
+ * use dev_net(dev) instead.
+ */
+static inline struct net *rtnl_newlink_link_net(struct rtnl_newlink_params *p)
+{
+	return p->link_net ? : p->src_net;
+}
+
+/* Get peer netns from newlink params. Fallback to link netns if peer netns is
+ * not specified explicitly.
+ */
+static inline struct net *rtnl_newlink_peer_net(struct rtnl_newlink_params *p)
+{
+	return p->peer_net ? : rtnl_newlink_link_net(p);
+}
+
 /**
  *	struct rtnl_link_ops - rtnetlink link operations
  *
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 91df0f96e32ae..a000b1ef05206 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -139,9 +139,9 @@ static int vlan_newlink(struct net_device *dev,
 			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct vlan_dev_priv *vlan = vlan_dev_priv(dev);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
 	struct net_device *real_dev;
 	unsigned int max_mtu;
@@ -158,7 +158,7 @@ static int vlan_newlink(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	real_dev = __dev_get_by_index(src_net, nla_get_u32(tb[IFLA_LINK]));
+	real_dev = __dev_get_by_index(link_net, nla_get_u32(tb[IFLA_LINK]));
 	if (!real_dev) {
 		NL_SET_ERR_MSG_MOD(extack, "link does not exist");
 		return -ENODEV;
diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
index 39add538ba998..b120470246cc5 100644
--- a/net/hsr/hsr_netlink.c
+++ b/net/hsr/hsr_netlink.c
@@ -33,8 +33,8 @@ static int hsr_newlink(struct net_device *dev,
 		       struct rtnl_newlink_params *params,
 		       struct netlink_ext_ack *extack)
 {
+	struct net *link_net = rtnl_newlink_link_net(params);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	enum hsr_version proto_version;
 	unsigned char multicast_spec;
 	u8 proto = HSR_PROTOCOL_HSR;
@@ -48,7 +48,7 @@ static int hsr_newlink(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Slave1 device not specified");
 		return -EINVAL;
 	}
-	link[0] = __dev_get_by_index(src_net,
+	link[0] = __dev_get_by_index(link_net,
 				     nla_get_u32(data[IFLA_HSR_SLAVE1]));
 	if (!link[0]) {
 		NL_SET_ERR_MSG_MOD(extack, "Slave1 does not exist");
@@ -58,7 +58,7 @@ static int hsr_newlink(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Slave2 device not specified");
 		return -EINVAL;
 	}
-	link[1] = __dev_get_by_index(src_net,
+	link[1] = __dev_get_by_index(link_net,
 				     nla_get_u32(data[IFLA_HSR_SLAVE2]));
 	if (!link[1]) {
 		NL_SET_ERR_MSG_MOD(extack, "Slave2 does not exist");
@@ -71,7 +71,7 @@ static int hsr_newlink(struct net_device *dev,
 	}
 
 	if (data[IFLA_HSR_INTERLINK])
-		interlink = __dev_get_by_index(src_net,
+		interlink = __dev_get_by_index(link_net,
 					       nla_get_u32(data[IFLA_HSR_INTERLINK]));
 
 	if (interlink && interlink == link[0]) {

From 3533717581dd72c9559b508e0feaede426d825aa Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:30 +0800
Subject: [PATCH 0977/2753] ieee802154: 6lowpan: Validate link netns in
 newlink() of rtnl_link_ops

Device denoted by IFLA_LINK is in link_net (IFLA_LINK_NETNSID) or
source netns by design, but 6lowpan uses dev_net.

Note dev->netns_local is set to true and currently link_net is
implemented via a netns change. These together effectively reject
IFLA_LINK_NETNSID.

This patch adds a validation to ensure link_net is either NULL or
identical to dev_net. Thus it would be fine to continue using dev_net
when rtnetlink core begins to create devices directly in target netns.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-5-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ieee802154/6lowpan/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 704bf9e3f0975..ee318d46817d4 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -143,6 +143,8 @@ static int lowpan_newlink(struct net_device *ldev,
 
 	if (!tb[IFLA_LINK])
 		return -EINVAL;
+	if (params->link_net && !net_eq(params->link_net, dev_net(ldev)))
+		return -EINVAL;
 	/* find and hold wpan device */
 	wdev = dev_get_by_index(dev_net(ldev), nla_get_u32(tb[IFLA_LINK]));
 	if (!wdev)

From 9e17b2a1a097f3f3e8973722ccd3770eef193edd Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:31 +0800
Subject: [PATCH 0978/2753] net: ip_tunnel: Don't set tunnel->net in
 ip_tunnel_init()

ip_tunnel_init() is called from register_netdevice(). In all code paths
reaching here, tunnel->net should already have been set (either in
ip_tunnel_newlink() or __ip_tunnel_create()). So don't set it again.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-6-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/ip_tunnel.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 09b73acf037ae..dd4b4e5be998a 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1326,7 +1326,6 @@ int ip_tunnel_init(struct net_device *dev)
 	}
 
 	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
 	strscpy(tunnel->parms.name, dev->name);
 	iph->version		= 4;
 	iph->ihl		= 5;

From eacb1160536e097ba1eb910a1b212d1032d2e9c6 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:32 +0800
Subject: [PATCH 0979/2753] net: ip_tunnel: Use link netns in newlink() of
 rtnl_link_ops

When link_net is set, use it as link netns instead of dev_net(). This
prepares for rtnetlink core to create device in target netns directly,
in which case the two namespaces may be different.

Convert common ip_tunnel_newlink() to accept an extra link netns
argument.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-7-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_tunnels.h | 5 +++--
 net/ipv4/ip_gre.c        | 8 +++++---
 net/ipv4/ip_tunnel.c     | 6 +++---
 net/ipv4/ip_vti.c        | 3 ++-
 net/ipv4/ipip.c          | 3 ++-
 5 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index e041e4865373e..a36a335cef9fb 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -407,8 +407,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
 		  bool log_ecn_error);
 int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
 			 struct ip_tunnel_parm_kern *p, __u32 fwmark);
-int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm_kern *p, __u32 fwmark);
+int ip_tunnel_newlink(struct net *net, struct net_device *dev,
+		      struct nlattr *tb[], struct ip_tunnel_parm_kern *p,
+		      __u32 fwmark);
 void ip_tunnel_setup(struct net_device *dev, unsigned int net_id);
 
 bool ip_tunnel_netlink_encap_parms(struct nlattr *data[],
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 1fe9b13d351c1..26d15f907551e 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1413,7 +1413,8 @@ static int ipgre_newlink(struct net_device *dev,
 	err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err < 0)
 		return err;
-	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+	return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p,
+				 fwmark);
 }
 
 static int erspan_newlink(struct net_device *dev,
@@ -1433,7 +1434,8 @@ static int erspan_newlink(struct net_device *dev,
 	err = erspan_netlink_parms(dev, data, tb, &p, &fwmark);
 	if (err)
 		return err;
-	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+	return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p,
+				 fwmark);
 }
 
 static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[],
@@ -1701,7 +1703,7 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = {
 struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 					u8 name_assign_type)
 {
-	struct rtnl_newlink_params params = { .net = net };
+	struct rtnl_newlink_params params = { .src_net = net };
 	struct nlattr *tb[IFLA_MAX + 1];
 	struct net_device *dev;
 	LIST_HEAD(list_kill);
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index dd4b4e5be998a..011f2a5aab3b9 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1213,11 +1213,11 @@ void ip_tunnel_delete_nets(struct list_head *net_list, unsigned int id,
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_delete_nets);
 
-int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
-		      struct ip_tunnel_parm_kern *p, __u32 fwmark)
+int ip_tunnel_newlink(struct net *net, struct net_device *dev,
+		      struct nlattr *tb[], struct ip_tunnel_parm_kern *p,
+		      __u32 fwmark)
 {
 	struct ip_tunnel *nt;
-	struct net *net = dev_net(dev);
 	struct ip_tunnel_net *itn;
 	int mtu;
 	int err;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index b901bee03e6d6..159b4473290e0 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -585,7 +585,8 @@ static int vti_newlink(struct net_device *dev,
 	__u32 fwmark = 0;
 
 	vti_netlink_parms(data, &parms, &fwmark);
-	return ip_tunnel_newlink(dev, tb, &parms, fwmark);
+	return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb,
+				 &parms, fwmark);
 }
 
 static int vti_changelink(struct net_device *dev, struct nlattr *tb[],
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index a8b844bcfc645..bab0bf90c908d 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -455,7 +455,8 @@ static int ipip_newlink(struct net_device *dev,
 	}
 
 	ipip_netlink_parms(data, &p, &t->collect_md, &fwmark);
-	return ip_tunnel_newlink(dev, tb, &p, fwmark);
+	return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p,
+				 fwmark);
 }
 
 static int ipip_changelink(struct net_device *dev, struct nlattr *tb[],

From db014522f35606031d8ac58b4aed6b1ed84f03d1 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:33 +0800
Subject: [PATCH 0980/2753] net: ipv6: Init tunnel link-netns before
 registering dev

Currently some IPv6 tunnel drivers set tnl->net to dev_net(dev) in
ndo_init(), which is called in register_netdevice(). However, it lacks
the context of link-netns when we enable cross-net tunnels at device
registration time.

Let's move the init of tunnel link-netns before register_netdevice().

ip6_gre has already initialized netns, so just remove the redundant
assignment.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-8-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_gre.c    | 2 --
 net/ipv6/ip6_tunnel.c | 3 ++-
 net/ipv6/ip6_vti.c    | 3 ++-
 net/ipv6/sit.c        | 8 +++++---
 4 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 863852abe8eac..d9e6b1fd99178 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1498,7 +1498,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
 	tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
@@ -1882,7 +1881,6 @@ static int ip6erspan_tap_init(struct net_device *dev)
 	tunnel = netdev_priv(dev);
 
 	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 54b843d208708..111a8777c2f7a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1878,7 +1878,6 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	int t_hlen;
 
 	t->dev = dev;
-	t->net = dev_net(dev);
 
 	ret = dst_cache_init(&t->dst_cache, GFP_KERNEL);
 	if (ret)
@@ -1940,6 +1939,7 @@ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
 	struct net *net = dev_net(dev);
 	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 
+	t->net = net;
 	t->parms.proto = IPPROTO_IPV6;
 
 	rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -2015,6 +2015,7 @@ static int ip6_tnl_newlink(struct net_device *dev,
 	int err;
 
 	nt = netdev_priv(dev);
+	nt->net = net;
 
 	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
 		err = ip6_tnl_encap_setup(nt, &ipencap);
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 993f85aeb8823..16e0d74f99dd0 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -925,7 +925,6 @@ static inline int vti6_dev_init_gen(struct net_device *dev)
 	struct ip6_tnl *t = netdev_priv(dev);
 
 	t->dev = dev;
-	t->net = dev_net(dev);
 	netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
 	netdev_lockdep_set_classes(dev);
 	return 0;
@@ -958,6 +957,7 @@ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev)
 	struct net *net = dev_net(dev);
 	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
 
+	t->net = net;
 	t->parms.proto = IPPROTO_IPV6;
 
 	rcu_assign_pointer(ip6n->tnls_wc[0], t);
@@ -1009,6 +1009,7 @@ static int vti6_newlink(struct net_device *dev,
 	vti6_netlink_parms(data, &nt->parms);
 
 	nt->parms.proto = IPPROTO_IPV6;
+	nt->net = net;
 
 	if (vti6_locate(net, &nt->parms, 0))
 		return -EEXIST;
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index e2bd52cabdee5..20453671ac502 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -269,6 +269,7 @@ static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
 
 	nt = netdev_priv(dev);
 
+	nt->net = net;
 	nt->parms = *parms;
 	if (ipip6_tunnel_create(dev) < 0)
 		goto failed_free;
@@ -1449,7 +1450,6 @@ static int ipip6_tunnel_init(struct net_device *dev)
 	int err;
 
 	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
 	strcpy(tunnel->parms.name, dev->name);
 
 	ipip6_tunnel_bind_dev(dev);
@@ -1565,6 +1565,7 @@ static int ipip6_newlink(struct net_device *dev,
 	int err;
 
 	nt = netdev_priv(dev);
+	nt->net = net;
 
 	if (ip_tunnel_netlink_encap_parms(data, &ipencap)) {
 		err = ip_tunnel_encap_setup(nt, &ipencap);
@@ -1860,6 +1861,9 @@ static int __net_init sit_init_net(struct net *net)
 	 */
 	sitn->fb_tunnel_dev->netns_local = true;
 
+	t = netdev_priv(sitn->fb_tunnel_dev);
+	t->net = net;
+
 	err = register_netdev(sitn->fb_tunnel_dev);
 	if (err)
 		goto err_reg_dev;
@@ -1867,8 +1871,6 @@ static int __net_init sit_init_net(struct net *net)
 	ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn);
 	ipip6_fb_tunnel_init(sitn->fb_tunnel_dev);
 
-	t = netdev_priv(sitn->fb_tunnel_dev);
-
 	strcpy(t->parms.name, sitn->fb_tunnel_dev->name);
 	return 0;
 

From 5e72ce3e39800791700cf3aae4348a1727d3548d Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:34 +0800
Subject: [PATCH 0981/2753] net: ipv6: Use link netns in newlink() of
 rtnl_link_ops

When link_net is set, use it as link netns instead of dev_net(). This
prepares for rtnetlink core to create device in target netns directly,
in which case the two namespaces may be different.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-9-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_gre.c    | 14 ++++++--------
 net/ipv6/ip6_tunnel.c |  9 +++++----
 net/ipv6/ip6_vti.c    |  6 +++---
 net/ipv6/sit.c        |  6 +++---
 4 files changed, 17 insertions(+), 18 deletions(-)

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d9e6b1fd99178..d31a4ce3b19ff 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1969,7 +1969,7 @@ static bool ip6gre_netlink_encap_parms(struct nlattr *data[],
 	return ret;
 }
 
-static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
+static int ip6gre_newlink_common(struct net *link_net, struct net_device *dev,
 				 struct nlattr *tb[], struct nlattr *data[],
 				 struct netlink_ext_ack *extack)
 {
@@ -1990,7 +1990,7 @@ static int ip6gre_newlink_common(struct net *src_net, struct net_device *dev,
 		eth_hw_addr_random(dev);
 
 	nt->dev = dev;
-	nt->net = dev_net(dev);
+	nt->net = link_net;
 
 	err = register_netdevice(dev);
 	if (err)
@@ -2007,11 +2007,10 @@ static int ip6gre_newlink(struct net_device *dev,
 			  struct rtnl_newlink_params *params,
 			  struct netlink_ext_ack *extack)
 {
+	struct net *net = params->link_net ? : dev_net(dev);
 	struct ip6_tnl *nt = netdev_priv(dev);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
-	struct net *net = dev_net(dev);
 	struct ip6gre_net *ign;
 	int err;
 
@@ -2026,7 +2025,7 @@ static int ip6gre_newlink(struct net_device *dev,
 			return -EEXIST;
 	}
 
-	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+	err = ip6gre_newlink_common(net, dev, tb, data, extack);
 	if (!err) {
 		ip6gre_tnl_link_config(nt, !tb[IFLA_MTU]);
 		ip6gre_tunnel_link_md(ign, nt);
@@ -2246,11 +2245,10 @@ static int ip6erspan_newlink(struct net_device *dev,
 			     struct rtnl_newlink_params *params,
 			     struct netlink_ext_ack *extack)
 {
+	struct net *net = params->link_net ? : dev_net(dev);
 	struct ip6_tnl *nt = netdev_priv(dev);
 	struct nlattr **data = params->data;
-	struct net *src_net = params->net;
 	struct nlattr **tb = params->tb;
-	struct net *net = dev_net(dev);
 	struct ip6gre_net *ign;
 	int err;
 
@@ -2266,7 +2264,7 @@ static int ip6erspan_newlink(struct net_device *dev,
 			return -EEXIST;
 	}
 
-	err = ip6gre_newlink_common(src_net, dev, tb, data, extack);
+	err = ip6gre_newlink_common(net, dev, tb, data, extack);
 	if (!err) {
 		ip6erspan_tnl_link_config(nt, !tb[IFLA_MTU]);
 		ip6erspan_tunnel_link_md(ign, nt);
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 111a8777c2f7a..89d206731af00 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -253,8 +253,7 @@ static void ip6_dev_free(struct net_device *dev)
 static int ip6_tnl_create2(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
+	struct ip6_tnl_net *ip6n = net_generic(t->net, ip6_tnl_net_id);
 	int err;
 
 	dev->rtnl_link_ops = &ip6_link_ops;
@@ -2008,12 +2007,14 @@ static int ip6_tnl_newlink(struct net_device *dev,
 {
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = dev_net(dev);
-	struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
 	struct ip_tunnel_encap ipencap;
+	struct ip6_tnl_net *ip6n;
 	struct ip6_tnl *nt, *t;
+	struct net *net;
 	int err;
 
+	net = params->link_net ? : dev_net(dev);
+	ip6n = net_generic(net, ip6_tnl_net_id);
 	nt = netdev_priv(dev);
 	nt->net = net;
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 16e0d74f99dd0..83c055996fbb0 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -177,8 +177,7 @@ vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t)
 static int vti6_tnl_create2(struct net_device *dev)
 {
 	struct ip6_tnl *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct vti6_net *ip6n = net_generic(net, vti6_net_id);
+	struct vti6_net *ip6n = net_generic(t->net, vti6_net_id);
 	int err;
 
 	dev->rtnl_link_ops = &vti6_link_ops;
@@ -1002,9 +1001,10 @@ static int vti6_newlink(struct net_device *dev,
 			struct netlink_ext_ack *extack)
 {
 	struct nlattr **data = params->data;
-	struct net *net = dev_net(dev);
 	struct ip6_tnl *nt;
+	struct net *net;
 
+	net = params->link_net ? : dev_net(dev);
 	nt = netdev_priv(dev);
 	vti6_netlink_parms(data, &nt->parms);
 
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 20453671ac502..f7b59bc957d3b 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -201,8 +201,7 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
 static int ipip6_tunnel_create(struct net_device *dev)
 {
 	struct ip_tunnel *t = netdev_priv(dev);
-	struct net *net = dev_net(dev);
-	struct sit_net *sitn = net_generic(net, sit_net_id);
+	struct sit_net *sitn = net_generic(t->net, sit_net_id);
 	int err;
 
 	__dev_addr_set(dev, &t->parms.iph.saddr, 4);
@@ -1556,14 +1555,15 @@ static int ipip6_newlink(struct net_device *dev,
 {
 	struct nlattr **data = params->data;
 	struct nlattr **tb = params->tb;
-	struct net *net = dev_net(dev);
 	struct ip_tunnel *nt;
 	struct ip_tunnel_encap ipencap;
 #ifdef CONFIG_IPV6_SIT_6RD
 	struct ip_tunnel_6rd ip6rd;
 #endif
+	struct net *net;
 	int err;
 
+	net = params->link_net ? : dev_net(dev);
 	nt = netdev_priv(dev);
 	nt->net = net;
 

From 5314e3d68455c56161c02133e08a44c3a9e8cf4a Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:35 +0800
Subject: [PATCH 0982/2753] net: xfrm: Use link netns in newlink() of
 rtnl_link_ops

When link_net is set, use it as link netns instead of dev_net(). This
prepares for rtnetlink core to create device in target netns directly,
in which case the two namespaces may be different.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-10-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/xfrm/xfrm_interface_core.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/xfrm/xfrm_interface_core.c b/net/xfrm/xfrm_interface_core.c
index 5659a6cadd519..622445f041d32 100644
--- a/net/xfrm/xfrm_interface_core.c
+++ b/net/xfrm/xfrm_interface_core.c
@@ -242,10 +242,9 @@ static void xfrmi_dev_free(struct net_device *dev)
 	gro_cells_destroy(&xi->gro_cells);
 }
 
-static int xfrmi_create(struct net_device *dev)
+static int xfrmi_create(struct net *net, struct net_device *dev)
 {
 	struct xfrm_if *xi = netdev_priv(dev);
-	struct net *net = dev_net(dev);
 	struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
 	int err;
 
@@ -819,11 +818,12 @@ static int xfrmi_newlink(struct net_device *dev,
 			 struct netlink_ext_ack *extack)
 {
 	struct nlattr **data = params->data;
-	struct net *net = dev_net(dev);
 	struct xfrm_if_parms p = {};
 	struct xfrm_if *xi;
+	struct net *net;
 	int err;
 
+	net = params->link_net ? : dev_net(dev);
 	xfrmi_netlink_parms(data, &p);
 	if (p.collect_md) {
 		struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id);
@@ -852,7 +852,7 @@ static int xfrmi_newlink(struct net_device *dev,
 	xi->net = net;
 	xi->dev = dev;
 
-	err = xfrmi_create(dev);
+	err = xfrmi_create(net, dev);
 	return err;
 }
 

From 9c0fc091dc01894eaa686bc051feb4367b0d033a Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:36 +0800
Subject: [PATCH 0983/2753] rtnetlink: Remove "net" from newlink params

Now that devices have been converted to use the specific netns instead
of ambiguous "net", let's remove it from newlink parameters.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-11-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/rtnetlink.h | 2 --
 net/core/rtnetlink.c    | 6 ------
 2 files changed, 8 deletions(-)

diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index b22a106621fb4..ec65a8cebb992 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -72,7 +72,6 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
 /**
  * struct rtnl_newlink_params - parameters of rtnl_link_ops::newlink()
  *
- * @net: Netns of interest
  * @src_net: Source netns of rtnetlink socket
  * @link_net: Link netns by IFLA_LINK_NETNSID, NULL if not specified
  * @peer_net: Peer netns
@@ -80,7 +79,6 @@ static inline int rtnl_msg_family(const struct nlmsghdr *nlh)
  * @data: IFLA_INFO_DATA attributes
  */
 struct rtnl_newlink_params {
-	struct net *net;
 	struct net *src_net;
 	struct net *link_net;
 	struct net *peer_net;
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9ebbde0d131ce..e980481bdd286 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3798,12 +3798,6 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 
 	dev->ifindex = ifm->ifi_index;
 
-	params.net = params.src_net;
-	if (link_net)
-		params.net = link_net;
-	if (peer_net)
-		params.net = peer_net;
-
 	if (ops->newlink)
 		err = ops->newlink(dev, &params, extack);
 	else

From 7ca486d08a30936e3b45f535d920848828fefb33 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:37 +0800
Subject: [PATCH 0984/2753] rtnetlink: Create link directly in target net
 namespace

Make rtnl_newlink_create() create device in target namespace directly.
Avoid extra netns change when link netns is provided.

Device drivers has been converted to be aware of link netns, that is not
assuming device netns is and link netns is the same when ops->newlink()
is called.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250219125039.18024-12-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/rtnetlink.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e980481bdd286..b52e610e157e9 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3789,8 +3789,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 		name_assign_type = NET_NAME_ENUM;
 	}
 
-	dev = rtnl_create_link(link_net ? : tgt_net, ifname,
-			       name_assign_type, ops, tb, extack);
+	dev = rtnl_create_link(tgt_net, ifname, name_assign_type, ops, tb,
+			       extack);
 	if (IS_ERR(dev)) {
 		err = PTR_ERR(dev);
 		goto out;
@@ -3810,11 +3810,6 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 	err = rtnl_configure_link(dev, ifm, portid, nlh);
 	if (err < 0)
 		goto out_unregister;
-	if (link_net) {
-		err = dev_change_net_namespace(dev, tgt_net, ifname);
-		if (err < 0)
-			goto out_unregister;
-	}
 	if (tb[IFLA_MASTER]) {
 		err = do_set_master(dev, nla_get_u32(tb[IFLA_MASTER]), extack);
 		if (err)

From 030329416232ff9f2e3e4bb065b29e6c9a7d5050 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:38 +0800
Subject: [PATCH 0985/2753] selftests: net: Add python context manager for
 netns entering

Change netns of current thread and switch back on context exit.
For example:

    with NetNSEnter("ns1"):
        ip("link add dummy0 type dummy")

The command be executed in netns "ns1".

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Link: https://patch.msgid.link/20250219125039.18024-13-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib/py/__init__.py |  2 +-
 tools/testing/selftests/net/lib/py/netns.py    | 18 ++++++++++++++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/lib/py/__init__.py b/tools/testing/selftests/net/lib/py/__init__.py
index 7294578593165..8697bd27dc305 100644
--- a/tools/testing/selftests/net/lib/py/__init__.py
+++ b/tools/testing/selftests/net/lib/py/__init__.py
@@ -2,7 +2,7 @@
 
 from .consts import KSRC
 from .ksft import *
-from .netns import NetNS
+from .netns import NetNS, NetNSEnter
 from .nsim import *
 from .utils import *
 from .ynl import NlError, YnlFamily, EthtoolFamily, NetdevFamily, RtnlFamily, RtnlAddrFamily
diff --git a/tools/testing/selftests/net/lib/py/netns.py b/tools/testing/selftests/net/lib/py/netns.py
index ecff85f9074fd..8e9317044eefe 100644
--- a/tools/testing/selftests/net/lib/py/netns.py
+++ b/tools/testing/selftests/net/lib/py/netns.py
@@ -1,9 +1,12 @@
 # SPDX-License-Identifier: GPL-2.0
 
 from .utils import ip
+import ctypes
 import random
 import string
 
+libc = ctypes.cdll.LoadLibrary('libc.so.6')
+
 
 class NetNS:
     def __init__(self, name=None):
@@ -29,3 +32,18 @@ def __str__(self):
 
     def __repr__(self):
         return f"NetNS({self.name})"
+
+
+class NetNSEnter:
+    def __init__(self, ns_name):
+        self.ns_path = f"/run/netns/{ns_name}"
+
+    def __enter__(self):
+        self.saved = open("/proc/thread-self/ns/net")
+        with open(self.ns_path) as ns_file:
+            libc.setns(ns_file.fileno(), 0)
+        return self
+
+    def __exit__(self, exc_type, exc_value, traceback):
+        libc.setns(self.saved.fileno(), 0)
+        self.saved.close()

From 85cb3711acb84ffb42e935cf1447708e19ccaee9 Mon Sep 17 00:00:00 2001
From: Xiao Liang <shaw.leon@gmail.com>
Date: Wed, 19 Feb 2025 20:50:39 +0800
Subject: [PATCH 0986/2753] selftests: net: Add test cases for link and peer
 netns

- Add test for creating link in another netns when a link of the same
   name and ifindex exists in current netns.
 - Add test to verify that link is created in target netns directly -
   no link new/del events should be generated in link netns or current
   netns.
 - Add test cases to verify that link-netns is set as expected for
   various drivers and combination of namespace-related parameters.

Signed-off-by: Xiao Liang <shaw.leon@gmail.com>
Link: https://patch.msgid.link/20250219125039.18024-14-shaw.leon@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile      |   1 +
 tools/testing/selftests/net/config        |   5 +
 tools/testing/selftests/net/link_netns.py | 141 ++++++++++++++++++++++
 tools/testing/selftests/net/netns-name.sh |  10 ++
 4 files changed, 157 insertions(+)
 create mode 100755 tools/testing/selftests/net/link_netns.py

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 8d6116b80cf1a..aeb96c0856146 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -36,6 +36,7 @@ TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += test_so_rcv.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
 TEST_PROGS += netns-name.sh
+TEST_PROGS += link_netns.py
 TEST_PROGS += nl_netdev.py
 TEST_PROGS += rtnetlink.py
 TEST_PROGS += srv6_end_dt46_l3vpn_test.sh
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5b9baf7089506..ab55270669ec4 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -107,3 +107,8 @@ CONFIG_XFRM_INTERFACE=m
 CONFIG_XFRM_USER=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
+CONFIG_IPVLAN=m
+CONFIG_CAN=m
+CONFIG_CAN_DEV=m
+CONFIG_CAN_VXCAN=m
+CONFIG_NETKIT=y
diff --git a/tools/testing/selftests/net/link_netns.py b/tools/testing/selftests/net/link_netns.py
new file mode 100755
index 0000000000000..aab043c59d695
--- /dev/null
+++ b/tools/testing/selftests/net/link_netns.py
@@ -0,0 +1,141 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import time
+
+from lib.py import ksft_run, ksft_exit, ksft_true
+from lib.py import ip
+from lib.py import NetNS, NetNSEnter
+from lib.py import RtnlFamily
+
+
+LINK_NETNSID = 100
+
+
+def test_event() -> None:
+    with NetNS() as ns1, NetNS() as ns2:
+        with NetNSEnter(str(ns2)):
+            rtnl = RtnlFamily()
+
+        rtnl.ntf_subscribe("rtnlgrp-link")
+
+        ip(f"netns set {ns2} {LINK_NETNSID}", ns=str(ns1))
+        ip(f"link add netns {ns1} link-netnsid {LINK_NETNSID} dummy1 type dummy")
+        ip(f"link add netns {ns1} dummy2 type dummy", ns=str(ns2))
+
+        ip("link del dummy1", ns=str(ns1))
+        ip("link del dummy2", ns=str(ns1))
+
+        time.sleep(1)
+        rtnl.check_ntf()
+        ksft_true(rtnl.async_msg_queue.empty(),
+                  "Received unexpected link notification")
+
+
+def validate_link_netns(netns, ifname, link_netnsid) -> bool:
+    link_info = ip(f"-d link show dev {ifname}", ns=netns, json=True)
+    if not link_info:
+        return False
+    return link_info[0].get("link_netnsid") == link_netnsid
+
+
+def test_link_net() -> None:
+    configs = [
+        # type, common args, type args, fallback to dev_net
+        ("ipvlan", "link dummy1", "", False),
+        ("macsec", "link dummy1", "", False),
+        ("macvlan", "link dummy1", "", False),
+        ("macvtap", "link dummy1", "", False),
+        ("vlan", "link dummy1", "id 100", False),
+        ("gre", "", "local 192.0.2.1", True),
+        ("vti", "", "local 192.0.2.1", True),
+        ("ipip", "", "local 192.0.2.1", True),
+        ("ip6gre", "", "local 2001:db8::1", True),
+        ("ip6tnl", "", "local 2001:db8::1", True),
+        ("vti6", "", "local 2001:db8::1", True),
+        ("sit", "", "local 192.0.2.1", True),
+        ("xfrm", "", "if_id 1", True),
+    ]
+
+    with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3:
+        net1, net2, net3 = str(ns1), str(ns2), str(ns3)
+
+        # prepare link netnsid  and a dummy link needed by certain drivers
+        ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+        ip("link add dummy1 type dummy", ns=net3)
+
+        cases = [
+            # source, "netns", "link-netns", expected link-netns
+            (net3, None, None, None, None),
+            (net3, net2, None, None, LINK_NETNSID),
+            (net2, None, net3, LINK_NETNSID, LINK_NETNSID),
+            (net1, net2, net3, LINK_NETNSID, LINK_NETNSID),
+        ]
+
+        for src_net, netns, link_netns, exp1, exp2 in cases:
+            tgt_net = netns or src_net
+            for typ, cargs, targs, fb_dev_net in configs:
+                cmd = "link add"
+                if netns:
+                    cmd += f" netns {netns}"
+                if link_netns:
+                    cmd += f" link-netns {link_netns}"
+                cmd += f" {cargs} foo type {typ} {targs}"
+                ip(cmd, ns=src_net)
+                if fb_dev_net:
+                    ksft_true(validate_link_netns(tgt_net, "foo", exp1),
+                              f"{typ} link_netns validation failed")
+                else:
+                    ksft_true(validate_link_netns(tgt_net, "foo", exp2),
+                              f"{typ} link_netns validation failed")
+                ip(f"link del foo", ns=tgt_net)
+
+
+def test_peer_net() -> None:
+    types = [
+        "vxcan",
+        "netkit",
+        "veth",
+    ]
+
+    with NetNS() as ns1, NetNS() as ns2, NetNS() as ns3, NetNS() as ns4:
+        net1, net2, net3, net4 = str(ns1), str(ns2), str(ns3), str(ns4)
+
+        ip(f"netns set {net3} {LINK_NETNSID}", ns=str(net2))
+
+        cases = [
+            # source, "netns", "link-netns", "peer netns", expected
+            (net1, None, None, None, None),
+            (net1, net2, None, None, None),
+            (net2, None, net3, None, LINK_NETNSID),
+            (net1, net2, net3, None, None),
+            (net2, None, None, net3, LINK_NETNSID),
+            (net1, net2, None, net3, LINK_NETNSID),
+            (net2, None, net2, net3, LINK_NETNSID),
+            (net1, net2, net4, net3, LINK_NETNSID),
+        ]
+
+        for src_net, netns, link_netns, peer_netns, exp in cases:
+            tgt_net = netns or src_net
+            for typ in types:
+                cmd = "link add"
+                if netns:
+                    cmd += f" netns {netns}"
+                if link_netns:
+                    cmd += f" link-netns {link_netns}"
+                cmd += f" foo type {typ}"
+                if peer_netns:
+                    cmd += f" peer netns {peer_netns}"
+                ip(cmd, ns=src_net)
+                ksft_true(validate_link_netns(tgt_net, "foo", exp),
+                          f"{typ} peer_netns validation failed")
+                ip(f"link del foo", ns=tgt_net)
+
+
+def main() -> None:
+    ksft_run([test_event, test_link_net, test_peer_net])
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/netns-name.sh b/tools/testing/selftests/net/netns-name.sh
index 6974474c26f3e..0be1905d1f2f1 100755
--- a/tools/testing/selftests/net/netns-name.sh
+++ b/tools/testing/selftests/net/netns-name.sh
@@ -78,6 +78,16 @@ ip -netns $NS link show dev $ALT_NAME 2> /dev/null &&
     fail "Can still find alt-name after move"
 ip -netns $test_ns link del $DEV || fail
 
+#
+# Test no conflict of the same name/ifindex in different netns
+#
+ip -netns $NS link add name $DEV index 100 type dummy || fail
+ip -netns $NS link add netns $test_ns name $DEV index 100 type dummy ||
+    fail "Can create in netns without moving"
+ip -netns $test_ns link show dev $DEV >> /dev/null || fail "Device not found"
+ip -netns $NS link del $DEV || fail
+ip -netns $test_ns link del $DEV || fail
+
 echo -ne "$(basename $0) \t\t\t\t"
 if [ $RET_CODE -eq 0 ]; then
     echo "[  OK  ]"

From c451715d78e31a27afaad35ee0e9a915935cd6ea Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 19 Feb 2025 23:47:31 +0100
Subject: [PATCH 0987/2753] net/rds: Replace deprecated strncpy() with
 strscpy_pad()

strncpy() is deprecated for NUL-terminated destination buffers. Use
strscpy_pad() instead and remove the manual NUL-termination.

Compile-tested only.

Link: https://github.com/KSPP/linux/issues/90
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Kees Cook <kees@kernel.org>
Reviewed-by: Allison Henderson <allison.henderson@oracle.com>
Tested-by: Allison Henderson <allison.henderson@oracle.com>
Link: https://patch.msgid.link/20250219224730.73093-2-thorsten.blum@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/rds/stats.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/rds/stats.c b/net/rds/stats.c
index 9e87da43c0045..cb2e3d2cdf738 100644
--- a/net/rds/stats.c
+++ b/net/rds/stats.c
@@ -89,8 +89,7 @@ void rds_stats_info_copy(struct rds_info_iterator *iter,
 
 	for (i = 0; i < nr; i++) {
 		BUG_ON(strlen(names[i]) >= sizeof(ctr.name));
-		strncpy(ctr.name, names[i], sizeof(ctr.name) - 1);
-		ctr.name[sizeof(ctr.name) - 1] = '\0';
+		strscpy_pad(ctr.name, names[i]);
 		ctr.value = values[i];
 
 		rds_info_copy(iter, &ctr, sizeof(ctr));

From 4b9c7d8fa113c0b363d0ceee29d1b15cceb771ee Mon Sep 17 00:00:00 2001
From: Ziwei Xiao <ziweixiao@google.com>
Date: Wed, 19 Feb 2025 12:04:51 -0800
Subject: [PATCH 0988/2753] gve: Add RSS cache for non RSS device option
 scenario

Not all the devices have the capability for the driver to query for the
registered RSS configuration. The driver can discover this by checking
the relevant device option during setup. If it cannot, the driver needs
to store the RSS config cache and directly return such cache when
queried by the ethtool. RSS config is inited when driver probes. Also the
default RSS config will be adjusted when there is RX queue count change.

At this point, only keys of GVE_RSS_KEY_SIZE and indirection tables of
GVE_RSS_INDIR_SIZE are supported.

Signed-off-by: Ziwei Xiao <ziweixiao@google.com>
Reviewed-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Jeroen de Borst <jeroendb@google.com>
Link: https://patch.msgid.link/20250219200451.3348166-1-jeroendb@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h         | 16 +++-
 drivers/net/ethernet/google/gve/gve_adminq.c  | 66 +++++++++++---
 drivers/net/ethernet/google/gve/gve_ethtool.c | 60 +++++++++++--
 drivers/net/ethernet/google/gve/gve_main.c    | 86 ++++++++++++++++++-
 4 files changed, 205 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 78d2a19593d18..216d6e157befb 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -68,6 +68,9 @@
 #define GVE_FLOW_RULE_IDS_CACHE_SIZE \
 	(GVE_ADMINQ_BUFFER_SIZE / sizeof(((struct gve_adminq_queried_flow_rule *)0)->location))
 
+#define GVE_RSS_KEY_SIZE	40
+#define GVE_RSS_INDIR_SIZE	128
+
 #define GVE_XDP_ACTIONS 5
 
 #define GVE_GQ_TX_MIN_PKT_DESC_BYTES 182
@@ -672,6 +675,7 @@ struct gve_rx_alloc_rings_cfg {
 	u16 packet_buffer_size;
 	bool raw_addressing;
 	bool enable_header_split;
+	bool reset_rss;
 
 	/* Allocated resources are returned here */
 	struct gve_rx_ring *rx;
@@ -722,6 +726,11 @@ struct gve_flow_rules_cache {
 	u32 rule_ids_cache_num;
 };
 
+struct gve_rss_config {
+	u8 *hash_key;
+	u32 *hash_lut;
+};
+
 struct gve_priv {
 	struct net_device *dev;
 	struct gve_tx_ring *tx; /* array of tx_cfg.num_queues */
@@ -842,6 +851,8 @@ struct gve_priv {
 
 	u16 rss_key_size;
 	u16 rss_lut_size;
+	bool cache_rss_config;
+	struct gve_rss_config rss_config;
 };
 
 enum gve_service_task_flags_bit {
@@ -1220,13 +1231,16 @@ int gve_adjust_config(struct gve_priv *priv,
 		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 int gve_adjust_queues(struct gve_priv *priv,
 		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config);
+		      struct gve_queue_config new_tx_config,
+		      bool reset_rss);
 /* flow steering rule */
 int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_get_flow_rule_ids(struct gve_priv *priv, struct ethtool_rxnfc *cmd, u32 *rule_locs);
 int gve_add_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_del_flow_rule(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
 int gve_flow_rules_reset(struct gve_priv *priv);
+/* RSS config */
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues);
 /* report stats handling */
 void gve_handle_report_stats(struct gve_priv *priv);
 /* exported by ethtool.c */
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index aa7d723011d0c..be7a423e5ab97 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -885,6 +885,15 @@ static void gve_set_default_desc_cnt(struct gve_priv *priv,
 	priv->min_rx_desc_cnt = priv->rx_desc_cnt;
 }
 
+static void gve_set_default_rss_sizes(struct gve_priv *priv)
+{
+	if (!gve_is_gqi(priv)) {
+		priv->rss_key_size = GVE_RSS_KEY_SIZE;
+		priv->rss_lut_size = GVE_RSS_INDIR_SIZE;
+		priv->cache_rss_config = true;
+	}
+}
+
 static void gve_enable_supported_features(struct gve_priv *priv,
 					  u32 supported_features_mask,
 					  const struct gve_device_option_jumbo_frames
@@ -968,6 +977,10 @@ static void gve_enable_supported_features(struct gve_priv *priv,
 			be16_to_cpu(dev_op_rss_config->hash_key_size);
 		priv->rss_lut_size =
 			be16_to_cpu(dev_op_rss_config->hash_lut_size);
+		priv->cache_rss_config = false;
+		dev_dbg(&priv->pdev->dev,
+			"RSS device option enabled with key size of %u, lut size of %u.\n",
+			priv->rss_key_size, priv->rss_lut_size);
 	}
 }
 
@@ -1052,6 +1065,8 @@ int gve_adminq_describe_device(struct gve_priv *priv)
 	/* set default descriptor counts */
 	gve_set_default_desc_cnt(priv, descriptor);
 
+	gve_set_default_rss_sizes(priv);
+
 	/* DQO supports LRO. */
 	if (!gve_is_gqi(priv))
 		priv->dev->hw_features |= NETIF_F_LRO;
@@ -1276,8 +1291,9 @@ int gve_adminq_reset_flow_rules(struct gve_priv *priv)
 
 int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *rxfh)
 {
+	const u32 *hash_lut_to_config = NULL;
+	const u8 *hash_key_to_config = NULL;
 	dma_addr_t lut_bus = 0, key_bus = 0;
-	u16 key_size = 0, lut_size = 0;
 	union gve_adminq_command cmd;
 	__be32 *lut = NULL;
 	u8 hash_alg = 0;
@@ -1287,7 +1303,7 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 
 	switch (rxfh->hfunc) {
 	case ETH_RSS_HASH_NO_CHANGE:
-		break;
+		fallthrough;
 	case ETH_RSS_HASH_TOP:
 		hash_alg = ETH_RSS_HASH_TOP;
 		break;
@@ -1296,27 +1312,46 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 	}
 
 	if (rxfh->indir) {
-		lut_size = priv->rss_lut_size;
+		if (rxfh->indir_size != priv->rss_lut_size)
+			return -EINVAL;
+
+		hash_lut_to_config = rxfh->indir;
+	} else if (priv->cache_rss_config) {
+		hash_lut_to_config = priv->rss_config.hash_lut;
+	}
+
+	if (hash_lut_to_config) {
 		lut = dma_alloc_coherent(&priv->pdev->dev,
-					 lut_size * sizeof(*lut),
+					 priv->rss_lut_size * sizeof(*lut),
 					 &lut_bus, GFP_KERNEL);
 		if (!lut)
 			return -ENOMEM;
 
 		for (i = 0; i < priv->rss_lut_size; i++)
-			lut[i] = cpu_to_be32(rxfh->indir[i]);
+			lut[i] = cpu_to_be32(hash_lut_to_config[i]);
 	}
 
 	if (rxfh->key) {
-		key_size = priv->rss_key_size;
+		if (rxfh->key_size != priv->rss_key_size) {
+			err = -EINVAL;
+			goto out;
+		}
+
+		hash_key_to_config = rxfh->key;
+	} else if (priv->cache_rss_config) {
+		hash_key_to_config = priv->rss_config.hash_key;
+	}
+
+	if (hash_key_to_config) {
 		key = dma_alloc_coherent(&priv->pdev->dev,
-					 key_size, &key_bus, GFP_KERNEL);
+					 priv->rss_key_size,
+					 &key_bus, GFP_KERNEL);
 		if (!key) {
 			err = -ENOMEM;
 			goto out;
 		}
 
-		memcpy(key, rxfh->key, key_size);
+		memcpy(key, hash_key_to_config, priv->rss_key_size);
 	}
 
 	/* Zero-valued fields in the cmd.configure_rss instruct the device to
@@ -1330,8 +1365,10 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 					  BIT(GVE_RSS_HASH_TCPV6) |
 					  BIT(GVE_RSS_HASH_UDPV6)),
 		.hash_alg = hash_alg,
-		.hash_key_size = cpu_to_be16(key_size),
-		.hash_lut_size = cpu_to_be16(lut_size),
+		.hash_key_size =
+			cpu_to_be16((key_bus) ? priv->rss_key_size : 0),
+		.hash_lut_size =
+			cpu_to_be16((lut_bus) ? priv->rss_lut_size : 0),
 		.hash_key_addr = cpu_to_be64(key_bus),
 		.hash_lut_addr = cpu_to_be64(lut_bus),
 	};
@@ -1341,11 +1378,11 @@ int gve_adminq_configure_rss(struct gve_priv *priv, struct ethtool_rxfh_param *r
 out:
 	if (lut)
 		dma_free_coherent(&priv->pdev->dev,
-				  lut_size * sizeof(*lut),
+				  priv->rss_lut_size * sizeof(*lut),
 				  lut, lut_bus);
 	if (key)
 		dma_free_coherent(&priv->pdev->dev,
-				  key_size, key, key_bus);
+				  priv->rss_key_size, key, key_bus);
 	return err;
 }
 
@@ -1449,12 +1486,15 @@ static int gve_adminq_process_rss_query(struct gve_priv *priv,
 	rxfh->hfunc = descriptor->hash_alg;
 
 	rss_info_addr = (void *)(descriptor + 1);
-	if (rxfh->key)
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
 		memcpy(rxfh->key, rss_info_addr, priv->rss_key_size);
+	}
 
 	rss_info_addr += priv->rss_key_size;
 	lut = (__be32 *)rss_info_addr;
 	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
 		for (i = 0; i < priv->rss_lut_size; i++)
 			rxfh->indir[i] = be32_to_cpu(lut[i]);
 	}
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bdfc6e77b2af5..a572f1e059342 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -482,6 +482,7 @@ static int gve_set_channels(struct net_device *netdev,
 	struct ethtool_channels old_settings;
 	int new_tx = cmd->tx_count;
 	int new_rx = cmd->rx_count;
+	bool reset_rss = false;
 
 	gve_get_channels(netdev, &old_settings);
 
@@ -498,16 +499,14 @@ static int gve_set_channels(struct net_device *netdev,
 		return -EINVAL;
 	}
 
-	if (!netif_running(netdev)) {
-		priv->tx_cfg.num_queues = new_tx;
-		priv->rx_cfg.num_queues = new_rx;
-		return 0;
-	}
+	if (new_rx != priv->rx_cfg.num_queues &&
+	    priv->cache_rss_config && !netif_is_rxfh_configured(netdev))
+		reset_rss = true;
 
 	new_tx_cfg.num_queues = new_tx;
 	new_rx_cfg.num_queues = new_rx;
 
-	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg);
+	return gve_adjust_queues(priv, new_rx_cfg, new_tx_cfg, reset_rss);
 }
 
 static void gve_get_ringparam(struct net_device *netdev,
@@ -855,6 +854,25 @@ static u32 gve_get_rxfh_indir_size(struct net_device *netdev)
 	return priv->rss_lut_size;
 }
 
+static void gve_get_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	rxfh->hfunc = ETH_RSS_HASH_TOP;
+
+	if (rxfh->key) {
+		rxfh->key_size = priv->rss_key_size;
+		memcpy(rxfh->key, rss_config->hash_key, priv->rss_key_size);
+	}
+
+	if (rxfh->indir) {
+		rxfh->indir_size = priv->rss_lut_size;
+		memcpy(rxfh->indir, rss_config->hash_lut,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+	}
+}
+
 static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
@@ -862,18 +880,46 @@ static int gve_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rx
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
+	if (priv->cache_rss_config) {
+		gve_get_rss_config_cache(priv, rxfh);
+		return 0;
+	}
+
 	return gve_adminq_query_rss_config(priv, rxfh);
 }
 
+static void gve_set_rss_config_cache(struct gve_priv *priv,
+				     struct ethtool_rxfh_param *rxfh)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (rxfh->key)
+		memcpy(rss_config->hash_key, rxfh->key, priv->rss_key_size);
+
+	if (rxfh->indir)
+		memcpy(rss_config->hash_lut, rxfh->indir,
+		       priv->rss_lut_size * sizeof(*rxfh->indir));
+}
+
 static int gve_set_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *rxfh,
 			struct netlink_ext_ack *extack)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
+	int err;
 
 	if (!priv->rss_key_size || !priv->rss_lut_size)
 		return -EOPNOTSUPP;
 
-	return gve_adminq_configure_rss(priv, rxfh);
+	err = gve_adminq_configure_rss(priv, rxfh);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack, "Fail to configure RSS config");
+		return err;
+	}
+
+	if (priv->cache_rss_config)
+		gve_set_rss_config_cache(priv, rxfh);
+
+	return 0;
 }
 
 const struct ethtool_ops gve_ethtool_ops = {
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 92237fb0b60c1..029be8342b7b8 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -184,6 +184,43 @@ static void gve_free_flow_rule_caches(struct gve_priv *priv)
 	flow_rules_cache->rules_cache = NULL;
 }
 
+static int gve_alloc_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	rss_config->hash_key = kcalloc(priv->rss_key_size,
+				       sizeof(rss_config->hash_key[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_key)
+		return -ENOMEM;
+
+	rss_config->hash_lut = kcalloc(priv->rss_lut_size,
+				       sizeof(rss_config->hash_lut[0]),
+				       GFP_KERNEL);
+	if (!rss_config->hash_lut)
+		goto free_rss_key_cache;
+
+	return 0;
+
+free_rss_key_cache:
+	kfree(rss_config->hash_key);
+	rss_config->hash_key = NULL;
+	return -ENOMEM;
+}
+
+static void gve_free_rss_config_cache(struct gve_priv *priv)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+
+	kfree(rss_config->hash_key);
+	kfree(rss_config->hash_lut);
+
+	memset(rss_config, 0, sizeof(*rss_config));
+}
+
 static int gve_alloc_counter_array(struct gve_priv *priv)
 {
 	priv->counter_array =
@@ -575,9 +612,12 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	err = gve_alloc_flow_rule_caches(priv);
 	if (err)
 		return err;
-	err = gve_alloc_counter_array(priv);
+	err = gve_alloc_rss_config_cache(priv);
 	if (err)
 		goto abort_with_flow_rule_caches;
+	err = gve_alloc_counter_array(priv);
+	if (err)
+		goto abort_with_rss_config_cache;
 	err = gve_alloc_notify_blocks(priv);
 	if (err)
 		goto abort_with_counter;
@@ -611,6 +651,12 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 		}
 	}
 
+	err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+	if (err) {
+		dev_err(&priv->pdev->dev, "Failed to init RSS config");
+		goto abort_with_ptype_lut;
+	}
+
 	err = gve_adminq_report_stats(priv, priv->stats_report_len,
 				      priv->stats_report_bus,
 				      GVE_STATS_REPORT_TIMER_PERIOD);
@@ -629,6 +675,8 @@ static int gve_setup_device_resources(struct gve_priv *priv)
 	gve_free_notify_blocks(priv);
 abort_with_counter:
 	gve_free_counter_array(priv);
+abort_with_rss_config_cache:
+	gve_free_rss_config_cache(priv);
 abort_with_flow_rule_caches:
 	gve_free_flow_rule_caches(priv);
 
@@ -669,6 +717,7 @@ static void gve_teardown_device_resources(struct gve_priv *priv)
 	priv->ptype_lut_dqo = NULL;
 
 	gve_free_flow_rule_caches(priv);
+	gve_free_rss_config_cache(priv);
 	gve_free_counter_array(priv);
 	gve_free_notify_blocks(priv);
 	gve_free_stats_report(priv);
@@ -1390,6 +1439,12 @@ static int gve_queues_start(struct gve_priv *priv,
 	if (err)
 		goto stop_and_free_rings;
 
+	if (rx_alloc_cfg->reset_rss) {
+		err = gve_init_rss_config(priv, priv->rx_cfg.num_queues);
+		if (err)
+			goto reset;
+	}
+
 	err = gve_register_qpls(priv);
 	if (err)
 		goto reset;
@@ -1786,6 +1841,26 @@ static int gve_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 	}
 }
 
+int gve_init_rss_config(struct gve_priv *priv, u16 num_queues)
+{
+	struct gve_rss_config *rss_config = &priv->rss_config;
+	struct ethtool_rxfh_param rxfh = {0};
+	u16 i;
+
+	if (!priv->cache_rss_config)
+		return 0;
+
+	for (i = 0; i < priv->rss_lut_size; i++)
+		rss_config->hash_lut[i] =
+			ethtool_rxfh_indir_default(i, num_queues);
+
+	netdev_rss_key_fill(rss_config->hash_key, priv->rss_key_size);
+
+	rxfh.hfunc = ETH_RSS_HASH_TOP;
+
+	return gve_adminq_configure_rss(priv, &rxfh);
+}
+
 int gve_flow_rules_reset(struct gve_priv *priv)
 {
 	if (!priv->max_flow_rules)
@@ -1834,7 +1909,8 @@ int gve_adjust_config(struct gve_priv *priv,
 
 int gve_adjust_queues(struct gve_priv *priv,
 		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config)
+		      struct gve_queue_config new_tx_config,
+		      bool reset_rss)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
@@ -1847,6 +1923,7 @@ int gve_adjust_queues(struct gve_priv *priv,
 	tx_alloc_cfg.qcfg = &new_tx_config;
 	rx_alloc_cfg.qcfg_tx = &new_tx_config;
 	rx_alloc_cfg.qcfg = &new_rx_config;
+	rx_alloc_cfg.reset_rss = reset_rss;
 	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
 
 	/* Add dedicated XDP TX queues if enabled. */
@@ -1858,6 +1935,11 @@ int gve_adjust_queues(struct gve_priv *priv,
 		return err;
 	}
 	/* Set the config for the next up. */
+	if (reset_rss) {
+		err = gve_init_rss_config(priv, new_rx_config.num_queues);
+		if (err)
+			return err;
+	}
 	priv->tx_cfg = new_tx_config;
 	priv->rx_cfg = new_rx_config;
 

From 5c70eb5c593d64d93b178905da215a9fd288a4b5 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Feb 2025 13:18:54 +0000
Subject: [PATCH 0989/2753] net: better track kernel sockets lifetime

While kernel sockets are dismantled during pernet_operations->exit(),
their freeing can be delayed by any tx packets still held in qdisc
or device queues, due to skb_set_owner_w() prior calls.

This then trigger the following warning from ref_tracker_dir_exit() [1]

To fix this, make sure that kernel sockets own a reference on net->passive.

Add sk_net_refcnt_upgrade() helper, used whenever a kernel socket
is converted to a refcounted one.

[1]

[  136.263918][   T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at
[  136.263918][   T35]      sk_alloc+0x2b3/0x370
[  136.263918][   T35]      inet6_create+0x6ce/0x10f0
[  136.263918][   T35]      __sock_create+0x4c0/0xa30
[  136.263918][   T35]      inet_ctl_sock_create+0xc2/0x250
[  136.263918][   T35]      igmp6_net_init+0x39/0x390
[  136.263918][   T35]      ops_init+0x31e/0x590
[  136.263918][   T35]      setup_net+0x287/0x9e0
[  136.263918][   T35]      copy_net_ns+0x33f/0x570
[  136.263918][   T35]      create_new_namespaces+0x425/0x7b0
[  136.263918][   T35]      unshare_nsproxy_namespaces+0x124/0x180
[  136.263918][   T35]      ksys_unshare+0x57d/0xa70
[  136.263918][   T35]      __x64_sys_unshare+0x38/0x40
[  136.263918][   T35]      do_syscall_64+0xf3/0x230
[  136.263918][   T35]      entry_SYSCALL_64_after_hwframe+0x77/0x7f
[  136.263918][   T35]
[  136.343488][   T35] ref_tracker: net notrefcnt@ffff8880638f01e0 has 1/2 users at
[  136.343488][   T35]      sk_alloc+0x2b3/0x370
[  136.343488][   T35]      inet6_create+0x6ce/0x10f0
[  136.343488][   T35]      __sock_create+0x4c0/0xa30
[  136.343488][   T35]      inet_ctl_sock_create+0xc2/0x250
[  136.343488][   T35]      ndisc_net_init+0xa7/0x2b0
[  136.343488][   T35]      ops_init+0x31e/0x590
[  136.343488][   T35]      setup_net+0x287/0x9e0
[  136.343488][   T35]      copy_net_ns+0x33f/0x570
[  136.343488][   T35]      create_new_namespaces+0x425/0x7b0
[  136.343488][   T35]      unshare_nsproxy_namespaces+0x124/0x180
[  136.343488][   T35]      ksys_unshare+0x57d/0xa70
[  136.343488][   T35]      __x64_sys_unshare+0x38/0x40
[  136.343488][   T35]      do_syscall_64+0xf3/0x230
[  136.343488][   T35]      entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 0cafd77dcd03 ("net: add a refcount tracker for kernel sockets")
Reported-by: syzbot+30a19e01a97420719891@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67b72aeb.050a0220.14d86d.0283.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250220131854.4048077-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h       |  1 +
 net/core/sock.c          | 27 ++++++++++++++++++++++-----
 net/mptcp/subflow.c      |  5 +----
 net/netlink/af_netlink.c | 10 ----------
 net/rds/tcp.c            |  8 ++------
 net/smc/af_smc.c         |  5 +----
 net/sunrpc/svcsock.c     |  5 +----
 net/sunrpc/xprtsock.c    |  8 ++------
 8 files changed, 30 insertions(+), 39 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index 8036b3b79cd8b..7ef728324e4e7 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1751,6 +1751,7 @@ static inline bool sock_allow_reclassification(const struct sock *csk)
 struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		      struct proto *prot, int kern);
 void sk_free(struct sock *sk);
+void sk_net_refcnt_upgrade(struct sock *sk);
 void sk_destruct(struct sock *sk);
 struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
 void sk_free_unlock_clone(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index eae2ae70a2e03..6c0e87f97fa4a 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2246,6 +2246,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 			get_net_track(net, &sk->ns_tracker, priority);
 			sock_inuse_add(net, 1);
 		} else {
+			net_passive_inc(net);
 			__netns_tracker_alloc(net, &sk->ns_tracker,
 					      false, priority);
 		}
@@ -2270,6 +2271,7 @@ EXPORT_SYMBOL(sk_alloc);
 static void __sk_destruct(struct rcu_head *head)
 {
 	struct sock *sk = container_of(head, struct sock, sk_rcu);
+	struct net *net = sock_net(sk);
 	struct sk_filter *filter;
 
 	if (sk->sk_destruct)
@@ -2301,14 +2303,28 @@ static void __sk_destruct(struct rcu_head *head)
 	put_cred(sk->sk_peer_cred);
 	put_pid(sk->sk_peer_pid);
 
-	if (likely(sk->sk_net_refcnt))
-		put_net_track(sock_net(sk), &sk->ns_tracker);
-	else
-		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-
+	if (likely(sk->sk_net_refcnt)) {
+		put_net_track(net, &sk->ns_tracker);
+	} else {
+		__netns_tracker_free(net, &sk->ns_tracker, false);
+		net_passive_dec(net);
+	}
 	sk_prot_free(sk->sk_prot_creator, sk);
 }
 
+void sk_net_refcnt_upgrade(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+
+	WARN_ON_ONCE(sk->sk_net_refcnt);
+	__netns_tracker_free(net, &sk->ns_tracker, false);
+	net_passive_dec(net);
+	sk->sk_net_refcnt = 1;
+	get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
+	sock_inuse_add(net, 1);
+}
+EXPORT_SYMBOL_GPL(sk_net_refcnt_upgrade);
+
 void sk_destruct(struct sock *sk)
 {
 	bool use_call_rcu = sock_flag(sk, SOCK_RCU_FREE);
@@ -2405,6 +2421,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority)
 		 * is not properly dismantling its kernel sockets at netns
 		 * destroy time.
 		 */
+		net_passive_inc(sock_net(newsk));
 		__netns_tracker_alloc(sock_net(newsk), &newsk->ns_tracker,
 				      false, priority);
 	}
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index fd021cf8286ef..dfcbef9c46246 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1772,10 +1772,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
 	 * needs it.
 	 * Update ns_tracker to current stack trace and refcounted tracker.
 	 */
-	__netns_tracker_free(net, &sf->sk->ns_tracker, false);
-	sf->sk->sk_net_refcnt = 1;
-	get_net_track(net, &sf->sk->ns_tracker, GFP_KERNEL);
-	sock_inuse_add(net, 1);
+	sk_net_refcnt_upgrade(sf->sk);
 	err = tcp_set_ulp(sf->sk, "mptcp");
 	if (err)
 		goto err_free;
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 85311226183a2..a53ea60d0a78d 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -795,16 +795,6 @@ static int netlink_release(struct socket *sock)
 
 	sock_prot_inuse_add(sock_net(sk), &netlink_proto, -1);
 
-	/* Because struct net might disappear soon, do not keep a pointer. */
-	if (!sk->sk_net_refcnt && sock_net(sk) != &init_net) {
-		__netns_tracker_free(sock_net(sk), &sk->ns_tracker, false);
-		/* Because of deferred_put_nlk_sk and use of work queue,
-		 * it is possible  netns will be freed before this socket.
-		 */
-		sock_net_set(sk, &init_net);
-		__netns_tracker_alloc(&init_net, &sk->ns_tracker,
-				      false, GFP_KERNEL);
-	}
 	call_rcu(&nlk->rcu, deferred_put_nlk_sk);
 	return 0;
 }
diff --git a/net/rds/tcp.c b/net/rds/tcp.c
index 0581c53e65170..3cc2f303bf786 100644
--- a/net/rds/tcp.c
+++ b/net/rds/tcp.c
@@ -504,12 +504,8 @@ bool rds_tcp_tune(struct socket *sock)
 			release_sock(sk);
 			return false;
 		}
-		/* Update ns_tracker to current stack trace and refcounted tracker */
-		__netns_tracker_free(net, &sk->ns_tracker, false);
-
-		sk->sk_net_refcnt = 1;
-		netns_tracker_alloc(net, &sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(net, 1);
+		sk_net_refcnt_upgrade(sk);
+		put_net(net);
 	}
 	rtn = net_generic(net, rds_tcp_netid);
 	if (rtn->sndbuf_size > 0) {
diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c
index ca6984541edbd..3e6cb35baf25a 100644
--- a/net/smc/af_smc.c
+++ b/net/smc/af_smc.c
@@ -3337,10 +3337,7 @@ int smc_create_clcsk(struct net *net, struct sock *sk, int family)
 	 * which need net ref.
 	 */
 	sk = smc->clcsock->sk;
-	__netns_tracker_free(net, &sk->ns_tracker, false);
-	sk->sk_net_refcnt = 1;
-	get_net_track(net, &sk->ns_tracker, GFP_KERNEL);
-	sock_inuse_add(net, 1);
+	sk_net_refcnt_upgrade(sk);
 	return 0;
 }
 
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index cb3bd12f5818b..72e5a01df3d35 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1541,10 +1541,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 	newlen = error;
 
 	if (protocol == IPPROTO_TCP) {
-		__netns_tracker_free(net, &sock->sk->ns_tracker, false);
-		sock->sk->sk_net_refcnt = 1;
-		get_net_track(net, &sock->sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(net, 1);
+		sk_net_refcnt_upgrade(sock->sk);
 		if ((error = kernel_listen(sock, 64)) < 0)
 			goto bummer;
 	}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index c60936d8cef71..940fe65b2a351 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1941,12 +1941,8 @@ static struct socket *xs_create_sock(struct rpc_xprt *xprt,
 		goto out;
 	}
 
-	if (protocol == IPPROTO_TCP) {
-		__netns_tracker_free(xprt->xprt_net, &sock->sk->ns_tracker, false);
-		sock->sk->sk_net_refcnt = 1;
-		get_net_track(xprt->xprt_net, &sock->sk->ns_tracker, GFP_KERNEL);
-		sock_inuse_add(xprt->xprt_net, 1);
-	}
+	if (protocol == IPPROTO_TCP)
+		sk_net_refcnt_upgrade(sock->sk);
 
 	filp = sock_alloc_file(sock, O_NONBLOCK, NULL);
 	if (IS_ERR(filp))

From 0e4427f8f587c4b603475468bb3aee9418574893 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 09:25:59 +0200
Subject: [PATCH 0990/2753] net: loopback: Avoid sending IP packets without an
 Ethernet header

After commit 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev")
IPv4 neighbors can be constructed on the blackhole net device, but they
are constructed with an output function (neigh_direct_output()) that
simply calls dev_queue_xmit(). The latter will transmit packets via
'skb->dev' which might not be the blackhole net device if dst_dev_put()
switched 'dst->dev' to the blackhole net device while another CPU was
using the dst entry in ip_output(), but after it already initialized
'skb->dev' from 'dst->dev'.

Specifically, the following can happen:

    CPU1                                      CPU2

udp_sendmsg(sk1)                          udp_sendmsg(sk2)
udp_send_skb()                            [...]
ip_output()
    skb->dev = skb_dst(skb)->dev
                                          dst_dev_put()
                                              dst->dev = blackhole_netdev
ip_finish_output2()
    resolves neigh on dst->dev
neigh_output()
neigh_direct_output()
dev_queue_xmit()

This will result in IPv4 packets being sent without an Ethernet header
via a valid net device:

tcpdump: verbose output suppressed, use -v[v]... for full protocol decode
listening on enp9s0, link-type EN10MB (Ethernet), snapshot length 262144 bytes
22:07:02.329668 20:00:40:11:18:fb > 45:00:00:44:f4:94, ethertype Unknown
(0x58c6), length 68:
        0x0000:  8dda 74ca f1ae ca6c ca6c 0098 969c 0400  ..t....l.l......
        0x0010:  0000 4730 3f18 6800 0000 0000 0000 9971  ..G0?.h........q
        0x0020:  c4c9 9055 a157 0a70 9ead bf83 38ca ab38  ...U.W.p....8..8
        0x0030:  8add ab96 e052                           .....R

Fix by making sure that neighbors are constructed on top of the
blackhole net device with an output function that simply consumes the
packets, in a similar fashion to dst_discard_out() and
blackhole_netdev_xmit().

Fixes: 8d7017fd621d ("blackhole_netdev: use blackhole_netdev to invalidate dst entries")
Fixes: 22600596b675 ("ipv4: give an IPv4 dev to blackhole_netdev")
Reported-by: Florian Meister <fmei@sfs.com>
Closes: https://lore.kernel.org/netdev/20250210084931.23a5c2e4@hermes.local/
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250220072559.782296-1-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/loopback.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index c8840c3b9a1bc..f1d68153987e1 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -244,8 +244,22 @@ static netdev_tx_t blackhole_netdev_xmit(struct sk_buff *skb,
 	return NETDEV_TX_OK;
 }
 
+static int blackhole_neigh_output(struct neighbour *n, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+
+static int blackhole_neigh_construct(struct net_device *dev,
+				     struct neighbour *n)
+{
+	n->output = blackhole_neigh_output;
+	return 0;
+}
+
 static const struct net_device_ops blackhole_netdev_ops = {
 	.ndo_start_xmit = blackhole_netdev_xmit,
+	.ndo_neigh_construct = blackhole_neigh_construct,
 };
 
 /* This is a dst-dummy device used specifically for invalidated

From ca4edd969a9483b1a1837056641019f62287063f Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:20 +0200
Subject: [PATCH 0991/2753] net: fib_rules: Add DSCP mask attribute

Add an attribute that allows matching on DSCP with a mask. Matching on
DSCP with a mask is needed in deployments where users encode path
information into certain bits of the DSCP field.

Temporarily set the type of the attribute to 'NLA_REJECT' while support
is being added.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-2-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/fib_rules.h | 1 +
 net/core/fib_rules.c           | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/uapi/linux/fib_rules.h b/include/uapi/linux/fib_rules.h
index 95ec01b15c654..2df6e4035d50b 100644
--- a/include/uapi/linux/fib_rules.h
+++ b/include/uapi/linux/fib_rules.h
@@ -72,6 +72,7 @@ enum {
 	FRA_FLOWLABEL_MASK,	/* flowlabel mask */
 	FRA_SPORT_MASK,	/* sport mask */
 	FRA_DPORT_MASK,	/* dport mask */
+	FRA_DSCP_MASK,	/* dscp mask */
 	__FRA_MAX
 };
 
diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 5ddd34cbe7f6d..00e6fe79ecbaa 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -845,6 +845,7 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
 	[FRA_SPORT_MASK] = { .type = NLA_U16 },
 	[FRA_DPORT_MASK] = { .type = NLA_U16 },
+	[FRA_DSCP_MASK] = { .type = NLA_REJECT },
 };
 
 int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,

From 2ae00699b357618959f815f8f08bddee72c85a72 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:21 +0200
Subject: [PATCH 0992/2753] ipv4: fib_rules: Add DSCP mask matching

Extend IPv4 FIB rules to match on DSCP using a mask. The mask is only
set in rules that match on DSCP (not TOS) and initialized to cover the
entire DSCP field if the mask attribute is not specified.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-3-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_rules.c | 47 +++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 6b3d6a957822b..fa58d6620ed67 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -37,6 +37,7 @@ struct fib4_rule {
 	u8			dst_len;
 	u8			src_len;
 	dscp_t			dscp;
+	dscp_t			dscp_mask;
 	u8			dscp_full:1;	/* DSCP or TOS selector */
 	__be32			src;
 	__be32			srcmask;
@@ -192,7 +193,8 @@ INDIRECT_CALLABLE_SCOPE int fib4_rule_match(struct fib_rule *rule,
 	 * to mask the upper three DSCP bits prior to matching to maintain
 	 * legacy behavior.
 	 */
-	if (r->dscp_full && r->dscp != inet_dsfield_to_dscp(fl4->flowi4_tos))
+	if (r->dscp_full &&
+	    (r->dscp ^ inet_dsfield_to_dscp(fl4->flowi4_tos)) & r->dscp_mask)
 		return 0;
 	else if (!r->dscp_full && r->dscp &&
 		 !fib_dscp_masked_match(r->dscp, fl4))
@@ -235,11 +237,35 @@ static int fib4_nl2rule_dscp(const struct nlattr *nla, struct fib4_rule *rule4,
 	}
 
 	rule4->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	rule4->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK);
 	rule4->dscp_full = true;
 
 	return 0;
 }
 
+static int fib4_nl2rule_dscp_mask(const struct nlattr *nla,
+				  struct fib4_rule *rule4,
+				  struct netlink_ext_ack *extack)
+{
+	dscp_t dscp_mask;
+
+	if (!rule4->dscp_full) {
+		NL_SET_ERR_MSG_ATTR(extack, nla,
+				    "Cannot specify DSCP mask without DSCP value");
+		return -EINVAL;
+	}
+
+	dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	if (rule4->dscp & ~dscp_mask) {
+		NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask");
+		return -EINVAL;
+	}
+
+	rule4->dscp_mask = dscp_mask;
+
+	return 0;
+}
+
 static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 			       struct fib_rule_hdr *frh,
 			       struct nlattr **tb,
@@ -271,6 +297,10 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 	    fib4_nl2rule_dscp(tb[FRA_DSCP], rule4, extack) < 0)
 		goto errout;
 
+	if (tb[FRA_DSCP_MASK] &&
+	    fib4_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule4, extack) < 0)
+		goto errout;
+
 	/* split local/main if they are not already split */
 	err = fib_unmerge(net);
 	if (err)
@@ -366,6 +396,14 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 			return 0;
 	}
 
+	if (tb[FRA_DSCP_MASK]) {
+		dscp_t dscp_mask;
+
+		dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2);
+		if (!rule4->dscp_full || rule4->dscp_mask != dscp_mask)
+			return 0;
+	}
+
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW])))
 		return 0;
@@ -391,7 +429,9 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	if (rule4->dscp_full) {
 		frh->tos = 0;
 		if (nla_put_u8(skb, FRA_DSCP,
-			       inet_dscp_to_dsfield(rule4->dscp) >> 2))
+			       inet_dscp_to_dsfield(rule4->dscp) >> 2) ||
+		    nla_put_u8(skb, FRA_DSCP_MASK,
+			       inet_dscp_to_dsfield(rule4->dscp_mask) >> 2))
 			goto nla_put_failure;
 	} else {
 		frh->tos = inet_dscp_to_dsfield(rule4->dscp);
@@ -418,7 +458,8 @@ static size_t fib4_rule_nlmsg_payload(struct fib_rule *rule)
 	return nla_total_size(4) /* dst */
 	       + nla_total_size(4) /* src */
 	       + nla_total_size(4) /* flow */
-	       + nla_total_size(1); /* dscp */
+	       + nla_total_size(1) /* dscp */
+	       + nla_total_size(1); /* dscp mask */
 }
 
 static void fib4_rule_flush_cache(struct fib_rules_ops *ops)

From c29165c272b86ca4342cba9dfcf8444a5b98863e Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:22 +0200
Subject: [PATCH 0993/2753] ipv6: fib_rules: Add DSCP mask matching

Extend IPv6 FIB rules to match on DSCP using a mask. Unlike IPv4, also
initialize the DSCP mask when a non-zero 'tos' is specified as there is
no difference in matching between 'tos' and 'dscp'. As a side effect,
this makes it possible to match on 'dscp 0', like in IPv4.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-4-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/fib6_rules.c | 45 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 43 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 0144d01417d9e..fd5f7112a51ff 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -29,6 +29,7 @@ struct fib6_rule {
 	__be32			flowlabel;
 	__be32			flowlabel_mask;
 	dscp_t			dscp;
+	dscp_t			dscp_mask;
 	u8			dscp_full:1;	/* DSCP or TOS selector */
 };
 
@@ -331,7 +332,7 @@ INDIRECT_CALLABLE_SCOPE int fib6_rule_match(struct fib_rule *rule,
 			return 0;
 	}
 
-	if (r->dscp && r->dscp != ip6_dscp(fl6->flowlabel))
+	if ((r->dscp ^ ip6_dscp(fl6->flowlabel)) & r->dscp_mask)
 		return 0;
 
 	if ((r->flowlabel ^ flowi6_get_flowlabel(fl6)) & r->flowlabel_mask)
@@ -360,11 +361,35 @@ static int fib6_nl2rule_dscp(const struct nlattr *nla, struct fib6_rule *rule6,
 	}
 
 	rule6->dscp = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	rule6->dscp_mask = inet_dsfield_to_dscp(INET_DSCP_MASK);
 	rule6->dscp_full = true;
 
 	return 0;
 }
 
+static int fib6_nl2rule_dscp_mask(const struct nlattr *nla,
+				  struct fib6_rule *rule6,
+				  struct netlink_ext_ack *extack)
+{
+	dscp_t dscp_mask;
+
+	if (!rule6->dscp_full) {
+		NL_SET_ERR_MSG_ATTR(extack, nla,
+				    "Cannot specify DSCP mask without DSCP value");
+		return -EINVAL;
+	}
+
+	dscp_mask = inet_dsfield_to_dscp(nla_get_u8(nla) << 2);
+	if (rule6->dscp & ~dscp_mask) {
+		NL_SET_ERR_MSG_ATTR(extack, nla, "Invalid DSCP mask");
+		return -EINVAL;
+	}
+
+	rule6->dscp_mask = dscp_mask;
+
+	return 0;
+}
+
 static int fib6_nl2rule_flowlabel(struct nlattr **tb, struct fib6_rule *rule6,
 				  struct netlink_ext_ack *extack)
 {
@@ -409,10 +434,15 @@ static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
 		goto errout;
 	}
 	rule6->dscp = inet_dsfield_to_dscp(frh->tos);
+	rule6->dscp_mask = frh->tos ? inet_dsfield_to_dscp(INET_DSCP_MASK) : 0;
 
 	if (tb[FRA_DSCP] && fib6_nl2rule_dscp(tb[FRA_DSCP], rule6, extack) < 0)
 		goto errout;
 
+	if (tb[FRA_DSCP_MASK] &&
+	    fib6_nl2rule_dscp_mask(tb[FRA_DSCP_MASK], rule6, extack) < 0)
+		goto errout;
+
 	if ((tb[FRA_FLOWLABEL] || tb[FRA_FLOWLABEL_MASK]) &&
 	    fib6_nl2rule_flowlabel(tb, rule6, extack) < 0)
 		goto errout;
@@ -482,6 +512,14 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 			return 0;
 	}
 
+	if (tb[FRA_DSCP_MASK]) {
+		dscp_t dscp_mask;
+
+		dscp_mask = inet_dsfield_to_dscp(nla_get_u8(tb[FRA_DSCP_MASK]) << 2);
+		if (!rule6->dscp_full || rule6->dscp_mask != dscp_mask)
+			return 0;
+	}
+
 	if (tb[FRA_FLOWLABEL] &&
 	    nla_get_be32(tb[FRA_FLOWLABEL]) != rule6->flowlabel)
 		return 0;
@@ -512,7 +550,9 @@ static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
 	if (rule6->dscp_full) {
 		frh->tos = 0;
 		if (nla_put_u8(skb, FRA_DSCP,
-			       inet_dscp_to_dsfield(rule6->dscp) >> 2))
+			       inet_dscp_to_dsfield(rule6->dscp) >> 2) ||
+		    nla_put_u8(skb, FRA_DSCP_MASK,
+			       inet_dscp_to_dsfield(rule6->dscp_mask) >> 2))
 			goto nla_put_failure;
 	} else {
 		frh->tos = inet_dscp_to_dsfield(rule6->dscp);
@@ -539,6 +579,7 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 	return nla_total_size(16) /* dst */
 	       + nla_total_size(16) /* src */
 	       + nla_total_size(1) /* dscp */
+	       + nla_total_size(1) /* dscp mask */
 	       + nla_total_size(4) /* flowlabel */
 	       + nla_total_size(4); /* flowlabel mask */
 }

From ea8af1affdc07bcf62fcb02c94cf8f7c4ad8d498 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:23 +0200
Subject: [PATCH 0994/2753] net: fib_rules: Enable DSCP mask usage

Allow user space to configure FIB rules that match on DSCP with a mask,
now that support has been added to the IPv4 and IPv6 address families.

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-5-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/fib_rules.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 00e6fe79ecbaa..4bc64d912a1c0 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -845,7 +845,7 @@ static const struct nla_policy fib_rule_policy[FRA_MAX + 1] = {
 	[FRA_FLOWLABEL_MASK] = { .type = NLA_BE32 },
 	[FRA_SPORT_MASK] = { .type = NLA_U16 },
 	[FRA_DPORT_MASK] = { .type = NLA_U16 },
-	[FRA_DSCP_MASK] = { .type = NLA_REJECT },
+	[FRA_DSCP_MASK] = NLA_POLICY_MASK(NLA_U8, INET_DSCP_MASK >> 2),
 };
 
 int fib_newrule(struct net *net, struct sk_buff *skb, struct nlmsghdr *nlh,

From 0df1328eaf04b2ccbd4da8478402c3b84df15cf3 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:24 +0200
Subject: [PATCH 0995/2753] netlink: specs: Add FIB rule DSCP mask attribute

Add new DSCP mask attribute to the spec. Example:

 # ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_rule.yaml \
	 --do newrule \
	 --json '{"family": 2, "dscp": 10, "dscp-mask": 63, "action": 1, "table": 1}'
 None
 $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/rt_rule.yaml \
	 --dump getrule --json '{"family": 2}' --output-json | jq '.[]'
 [...]
 {
   "table": 1,
   "suppress-prefixlen": "0xffffffff",
   "protocol": 0,
   "priority": 32765,
   "dscp": 10,
   "dscp-mask": "0x3f",
   "family": 2,
   "dst-len": 0,
   "src-len": 0,
   "tos": 0,
   "action": "to-tbl",
   "flags": 0
 }
 [...]

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-6-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_rule.yaml | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Documentation/netlink/specs/rt_rule.yaml b/Documentation/netlink/specs/rt_rule.yaml
index b30c924087fa8..de0938d365419 100644
--- a/Documentation/netlink/specs/rt_rule.yaml
+++ b/Documentation/netlink/specs/rt_rule.yaml
@@ -190,6 +190,10 @@ attribute-sets:
         name: dport-mask
         type: u16
         display-hint: hex
+      -
+        name: dscp-mask
+        type: u8
+        display-hint: hex
 
 operations:
   enum-model: directional
@@ -225,6 +229,7 @@ operations:
             - flowlabel-mask
             - sport-mask
             - dport-mask
+            - dscp-mask
     -
       name: newrule-ntf
       doc: Notify a rule creation

From e818d1d1a6eeaa75ad7a44082e546de897308de1 Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Thu, 20 Feb 2025 10:05:25 +0200
Subject: [PATCH 0996/2753] selftests: fib_rule_tests: Add DSCP mask match
 tests

Add tests for FIB rules that match on DSCP with a mask. Test both good
and bad flows and both the input and output paths.

 # ./fib_rule_tests.sh
 IPv6 FIB rule tests
 [...]
    TEST: rule6 check: dscp redirect to table                           [ OK ]
    TEST: rule6 check: dscp no redirect to table                        [ OK ]
    TEST: rule6 del by pref: dscp redirect to table                     [ OK ]
    TEST: rule6 check: iif dscp redirect to table                       [ OK ]
    TEST: rule6 check: iif dscp no redirect to table                    [ OK ]
    TEST: rule6 del by pref: iif dscp redirect to table                 [ OK ]
    TEST: rule6 check: dscp masked redirect to table                    [ OK ]
    TEST: rule6 check: dscp masked no redirect to table                 [ OK ]
    TEST: rule6 del by pref: dscp masked redirect to table              [ OK ]
    TEST: rule6 check: iif dscp masked redirect to table                [ OK ]
    TEST: rule6 check: iif dscp masked no redirect to table             [ OK ]
    TEST: rule6 del by pref: iif dscp masked redirect to table          [ OK ]
 [...]

 Tests passed: 316
 Tests failed:   0

Reviewed-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/20250220080525.831924-7-idosch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_rule_tests.sh | 38 +++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/tools/testing/selftests/net/fib_rule_tests.sh b/tools/testing/selftests/net/fib_rule_tests.sh
index 06c51d7ceb4a1..b866bab1d92a1 100755
--- a/tools/testing/selftests/net/fib_rule_tests.sh
+++ b/tools/testing/selftests/net/fib_rule_tests.sh
@@ -310,6 +310,25 @@ fib_rule6_test()
 			"iif dscp no redirect to table"
 	fi
 
+	ip rule help 2>&1 | grep -q "DSCP\[/MASK\]"
+	if [ $? -eq 0 ]; then
+		match="dscp 0x0f/0x0f"
+		tosmatch=$(printf 0x"%x" $((0x1f << 2)))
+		tosnomatch=$(printf 0x"%x" $((0x1e << 2)))
+		getmatch="tos $tosmatch"
+		getnomatch="tos $tosnomatch"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "dscp masked redirect to table" \
+			"dscp masked no redirect to table"
+
+		match="dscp 0x0f/0x0f"
+		getmatch="from $SRC_IP6 iif $DEV tos $tosmatch"
+		getnomatch="from $SRC_IP6 iif $DEV tos $tosnomatch"
+		fib_rule6_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif dscp masked redirect to table" \
+			"iif dscp masked no redirect to table"
+	fi
+
 	fib_check_iproute_support "flowlabel" "flowlabel"
 	if [ $? -eq 0 ]; then
 		match="flowlabel 0xfffff"
@@ -597,6 +616,25 @@ fib_rule4_test()
 			"$getnomatch" "iif dscp redirect to table" \
 			"iif dscp no redirect to table"
 	fi
+
+	ip rule help 2>&1 | grep -q "DSCP\[/MASK\]"
+	if [ $? -eq 0 ]; then
+		match="dscp 0x0f/0x0f"
+		tosmatch=$(printf 0x"%x" $((0x1f << 2)))
+		tosnomatch=$(printf 0x"%x" $((0x1e << 2)))
+		getmatch="tos $tosmatch"
+		getnomatch="tos $tosnomatch"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "dscp masked redirect to table" \
+			"dscp masked no redirect to table"
+
+		match="dscp 0x0f/0x0f"
+		getmatch="from $SRC_IP iif $DEV tos $tosmatch"
+		getnomatch="from $SRC_IP iif $DEV tos $tosnomatch"
+		fib_rule4_test_match_n_redirect "$match" "$getmatch" \
+			"$getnomatch" "iif dscp masked redirect to table" \
+			"iif dscp masked no redirect to table"
+	fi
 }
 
 fib_rule4_vrf_test()

From 465b210fdc653086fca34914c3a633efafb83e71 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 20 Feb 2025 08:53:26 +0000
Subject: [PATCH 0997/2753] selftests: fib_nexthops: do not mark skipped tests
 as failed

The current test marks all unexpected return values as failed and sets ret
to 1. If a test is skipped, the entire test also returns 1, incorrectly
indicating failure.

To fix this, add a skipped variable and set ret to 4 if it was previously
0. Otherwise, keep ret set to 1.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Link: https://patch.msgid.link/20250220085326.1512814-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/fib_nexthops.sh | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/fib_nexthops.sh b/tools/testing/selftests/net/fib_nexthops.sh
index bea1282e02819..b39f748c25722 100755
--- a/tools/testing/selftests/net/fib_nexthops.sh
+++ b/tools/testing/selftests/net/fib_nexthops.sh
@@ -76,11 +76,13 @@ log_test()
 		printf "TEST: %-60s  [ OK ]\n" "${msg}"
 		nsuccess=$((nsuccess+1))
 	else
-		ret=1
-		nfail=$((nfail+1))
 		if [[ $rc -eq $ksft_skip ]]; then
+			[[ $ret -eq 0 ]] && ret=$ksft_skip
+			nskip=$((nskip+1))
 			printf "TEST: %-60s  [SKIP]\n" "${msg}"
 		else
+			ret=1
+			nfail=$((nfail+1))
 			printf "TEST: %-60s  [FAIL]\n" "${msg}"
 		fi
 
@@ -2528,6 +2530,7 @@ done
 if [ "$TESTS" != "none" ]; then
 	printf "\nTests passed: %3d\n" ${nsuccess}
 	printf "Tests failed: %3d\n"   ${nfail}
+	printf "Tests skipped: %2d\n"  ${nskip}
 fi
 
 exit $ret

From c180188ec02281126045414e90d08422a80f75b4 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Thu, 20 Feb 2025 12:07:52 +0100
Subject: [PATCH 0998/2753] net: set the minimum for
 net_hotdata.netdev_budget_usecs

Commit 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs
to enable softirq tuning") added a possibility to set
net_hotdata.netdev_budget_usecs, but added no lower bound checking.

Commit a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies")
made the *initial* value HZ-dependent, so the initial value is at least
2 jiffies even for lower HZ values (2 ms for 1000 Hz, 8ms for 250 Hz, 20
ms for 100 Hz).

But a user still can set improper values by a sysctl. Set .extra1
(the lower bound) for net_hotdata.netdev_budget_usecs to the same value
as in the latter commit. That is to 2 jiffies.

Fixes: a4837980fd9f ("net: revert default NAPI poll timeout to 2 jiffies")
Fixes: 7acf8a1e8a28 ("Replace 2 jiffies with sysctl netdev_budget_usecs to enable softirq tuning")
Signed-off-by: Jiri Slaby (SUSE) <jirislaby@kernel.org>
Cc: Dmitry Yakunin <zeil@yandex-team.ru>
Cc: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Link: https://patch.msgid.link/20250220110752.137639-1-jirislaby@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/sysctl_net_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index ad2741f1346af..c7769ee0d9c55 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -34,6 +34,7 @@ static int min_sndbuf = SOCK_MIN_SNDBUF;
 static int min_rcvbuf = SOCK_MIN_RCVBUF;
 static int max_skb_frags = MAX_SKB_FRAGS;
 static int min_mem_pcpu_rsv = SK_MEMORY_PCPU_RESERVE;
+static int netdev_budget_usecs_min = 2 * USEC_PER_SEC / HZ;
 
 static int net_msg_warn;	/* Unused, but still a sysctl */
 
@@ -587,7 +588,7 @@ static struct ctl_table net_core_table[] = {
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
+		.extra1		= &netdev_budget_usecs_min,
 	},
 	{
 		.procname	= "fb_tunnels_only_for_init_net",

From 3e401818c81bb9f8438d1c2a803471f441981329 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Feb 2025 12:47:49 +0000
Subject: [PATCH 0999/2753] net: stmmac: print stmmac_init_dma_engine() errors
 using netdev_err()

stmmac_init_dma_engine() uses dev_err() which leads to errors being
reported as e.g:

dwc-eth-dwmac 2490000.ethernet: Failed to reset the dma
dwc-eth-dwmac 2490000.ethernet eth0: stmmac_hw_setup: DMA engine initialization failed

stmmac_init_dma_engine() is only called from stmmac_hw_setup() which
itself uses netdev_err(), and we will have a net_device setup. So,
change the dev_err() to netdev_err() to give consistent error
messages.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tl5y1-004UgG-8X@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index edf4b1d651a6e..424fa2fe31c6c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3047,7 +3047,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 	int ret = 0;
 
 	if (!priv->plat->dma_cfg || !priv->plat->dma_cfg->pbl) {
-		dev_err(priv->device, "Invalid DMA configuration\n");
+		netdev_err(priv->dev, "Invalid DMA configuration\n");
 		return -EINVAL;
 	}
 
@@ -3056,7 +3056,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv)
 
 	ret = stmmac_reset(priv, priv->ioaddr);
 	if (ret) {
-		dev_err(priv->device, "Failed to reset the dma\n");
+		netdev_err(priv->dev, "Failed to reset the dma\n");
 		return ret;
 	}
 

From 27843ce6ba3d3122b65066550fe33fb8839f8aef Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Feb 2025 15:53:36 +0000
Subject: [PATCH 1000/2753] ipvlan: ensure network headers are in skb linear
 part

syzbot found that ipvlan_process_v6_outbound() was assuming
the IPv6 network header isis present in skb->head [1]

Add the needed pskb_network_may_pull() calls for both
IPv4 and IPv6 handlers.

[1]
BUG: KMSAN: uninit-value in __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47
  __ipv6_addr_type+0xa2/0x490 net/ipv6/addrconf_core.c:47
  ipv6_addr_type include/net/ipv6.h:555 [inline]
  ip6_route_output_flags_noref net/ipv6/route.c:2616 [inline]
  ip6_route_output_flags+0x51/0x720 net/ipv6/route.c:2651
  ip6_route_output include/net/ip6_route.h:93 [inline]
  ipvlan_route_v6_outbound+0x24e/0x520 drivers/net/ipvlan/ipvlan_core.c:476
  ipvlan_process_v6_outbound drivers/net/ipvlan/ipvlan_core.c:491 [inline]
  ipvlan_process_outbound drivers/net/ipvlan/ipvlan_core.c:541 [inline]
  ipvlan_xmit_mode_l3 drivers/net/ipvlan/ipvlan_core.c:605 [inline]
  ipvlan_queue_xmit+0xd72/0x1780 drivers/net/ipvlan/ipvlan_core.c:671
  ipvlan_start_xmit+0x5b/0x210 drivers/net/ipvlan/ipvlan_main.c:223
  __netdev_start_xmit include/linux/netdevice.h:5150 [inline]
  netdev_start_xmit include/linux/netdevice.h:5159 [inline]
  xmit_one net/core/dev.c:3735 [inline]
  dev_hard_start_xmit+0x247/0xa20 net/core/dev.c:3751
  sch_direct_xmit+0x399/0xd40 net/sched/sch_generic.c:343
  qdisc_restart net/sched/sch_generic.c:408 [inline]
  __qdisc_run+0x14da/0x35d0 net/sched/sch_generic.c:416
  qdisc_run+0x141/0x4d0 include/net/pkt_sched.h:127
  net_tx_action+0x78b/0x940 net/core/dev.c:5484
  handle_softirqs+0x1a0/0x7c0 kernel/softirq.c:561
  __do_softirq+0x14/0x1a kernel/softirq.c:595
  do_softirq+0x9a/0x100 kernel/softirq.c:462
  __local_bh_enable_ip+0x9f/0xb0 kernel/softirq.c:389
  local_bh_enable include/linux/bottom_half.h:33 [inline]
  rcu_read_unlock_bh include/linux/rcupdate.h:919 [inline]
  __dev_queue_xmit+0x2758/0x57d0 net/core/dev.c:4611
  dev_queue_xmit include/linux/netdevice.h:3311 [inline]
  packet_xmit+0x9c/0x6c0 net/packet/af_packet.c:276
  packet_snd net/packet/af_packet.c:3132 [inline]
  packet_sendmsg+0x93e0/0xa7e0 net/packet/af_packet.c:3164
  sock_sendmsg_nosec net/socket.c:718 [inline]

Fixes: 2ad7bf363841 ("ipvlan: Initial check-in of the IPVLAN driver.")
Reported-by: syzbot+93ab4a777bafb9d9f960@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67b74f01.050a0220.14d86d.02d8.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Mahesh Bandewar <maheshb@google.com>
Link: https://patch.msgid.link/20250220155336.61884-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipvlan/ipvlan_core.c | 21 ++++++++++++++++-----
 1 file changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ipvlan/ipvlan_core.c b/drivers/net/ipvlan/ipvlan_core.c
index fd591ddb3884d..ca62188a317ad 100644
--- a/drivers/net/ipvlan/ipvlan_core.c
+++ b/drivers/net/ipvlan/ipvlan_core.c
@@ -416,20 +416,25 @@ struct ipvl_addr *ipvlan_addr_lookup(struct ipvl_port *port, void *lyr3h,
 
 static noinline_for_stack int ipvlan_process_v4_outbound(struct sk_buff *skb)
 {
-	const struct iphdr *ip4h = ip_hdr(skb);
 	struct net_device *dev = skb->dev;
 	struct net *net = dev_net(dev);
-	struct rtable *rt;
 	int err, ret = NET_XMIT_DROP;
+	const struct iphdr *ip4h;
+	struct rtable *rt;
 	struct flowi4 fl4 = {
 		.flowi4_oif = dev->ifindex,
-		.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h)),
 		.flowi4_flags = FLOWI_FLAG_ANYSRC,
 		.flowi4_mark = skb->mark,
-		.daddr = ip4h->daddr,
-		.saddr = ip4h->saddr,
 	};
 
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		goto err;
+
+	ip4h = ip_hdr(skb);
+	fl4.daddr = ip4h->daddr;
+	fl4.saddr = ip4h->saddr;
+	fl4.flowi4_tos = inet_dscp_to_dsfield(ip4h_dscp(ip4h));
+
 	rt = ip_route_output_flow(net, &fl4, NULL);
 	if (IS_ERR(rt))
 		goto err;
@@ -488,6 +493,12 @@ static int ipvlan_process_v6_outbound(struct sk_buff *skb)
 	struct net_device *dev = skb->dev;
 	int err, ret = NET_XMIT_DROP;
 
+	if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr))) {
+		DEV_STATS_INC(dev, tx_errors);
+		kfree_skb(skb);
+		return ret;
+	}
+
 	err = ipvlan_route_v6_outbound(dev, skb);
 	if (unlikely(err)) {
 		DEV_STATS_INC(dev, tx_errors);

From fa52f15c745ce55261b92873676f64f7348cfe82 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 20 Feb 2025 11:29:50 -0500
Subject: [PATCH 1001/2753] net: cadence: macb: Synchronize stats calculations

Stats calculations involve a RMW to add the stat update to the existing
value. This is currently not protected by any synchronization mechanism,
so data races are possible. Add a spinlock to protect the update. The
reader side could be protected using u64_stats, but we would still need
a spinlock for the update side anyway. And we always do an update
immediately before reading the stats anyway.

Fixes: 89e5785fc8a6 ("[PATCH] Atmel MACB ethernet driver")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250220162950.95941-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb.h      |  2 ++
 drivers/net/ethernet/cadence/macb_main.c | 12 ++++++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 5740c98d8c9f0..2847278d9cd48 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1279,6 +1279,8 @@ struct macb {
 	struct clk		*rx_clk;
 	struct clk		*tsu_clk;
 	struct net_device	*dev;
+	/* Protects hw_stats and ethtool_stats */
+	spinlock_t		stats_lock;
 	union {
 		struct macb_stats	macb;
 		struct gem_stats	gem;
diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 48496209fb164..c1f57d96e63fc 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1978,10 +1978,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id)
 
 		if (status & MACB_BIT(ISR_ROVR)) {
 			/* We missed at least one packet */
+			spin_lock(&bp->stats_lock);
 			if (macb_is_gem(bp))
 				bp->hw_stats.gem.rx_overruns++;
 			else
 				bp->hw_stats.macb.rx_overruns++;
+			spin_unlock(&bp->stats_lock);
 
 			if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE)
 				queue_writel(queue, ISR, MACB_BIT(ISR_ROVR));
@@ -3102,6 +3104,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	if (!netif_running(bp->dev))
 		return nstat;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 
 	nstat->rx_errors = (hwstat->rx_frame_check_sequence_errors +
@@ -3131,6 +3134,7 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 	nstat->tx_aborted_errors = hwstat->tx_excessive_collisions;
 	nstat->tx_carrier_errors = hwstat->tx_carrier_sense_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underrun;
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -3138,12 +3142,13 @@ static struct net_device_stats *gem_get_stats(struct macb *bp)
 static void gem_get_ethtool_stats(struct net_device *dev,
 				  struct ethtool_stats *stats, u64 *data)
 {
-	struct macb *bp;
+	struct macb *bp = netdev_priv(dev);
 
-	bp = netdev_priv(dev);
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	memcpy(data, &bp->ethtool_stats, sizeof(u64)
 			* (GEM_STATS_LEN + QUEUE_STATS_LEN * MACB_MAX_QUEUES));
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static int gem_get_sset_count(struct net_device *dev, int sset)
@@ -3193,6 +3198,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 		return gem_get_stats(bp);
 
 	/* read stats from hardware */
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 
 	/* Convert HW stats into netdevice stats */
@@ -3226,6 +3232,7 @@ static struct net_device_stats *macb_get_stats(struct net_device *dev)
 	nstat->tx_carrier_errors = hwstat->tx_carrier_errors;
 	nstat->tx_fifo_errors = hwstat->tx_underruns;
 	/* Don't know about heartbeat or window errors... */
+	spin_unlock_irq(&bp->stats_lock);
 
 	return nstat;
 }
@@ -5097,6 +5104,7 @@ static int macb_probe(struct platform_device *pdev)
 		}
 	}
 	spin_lock_init(&bp->lock);
+	spin_lock_init(&bp->stats_lock);
 
 	/* setup capabilities */
 	macb_configure_caps(bp, macb_config);

From e6a532185daae9302bf2f358c8675733093b906e Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 20 Feb 2025 11:42:57 -0500
Subject: [PATCH 1002/2753] net: cadence: macb: Implement BQL

Implement byte queue limits to allow queuing disciplines to account for
packets enqueued in the ring buffer but not yet transmitted. There are a
separate set of transmit functions for AT91 that I haven't touched since
I don't have hardware to test on.

Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250220164257.96859-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 2112a9701e05f..5345f3e1a7957 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -1079,15 +1079,18 @@ static void macb_tx_error_task(struct work_struct *work)
 						      tx_error_task);
 	bool			halt_timeout = false;
 	struct macb		*bp = queue->bp;
+	u32			queue_index;
+	u32			packets = 0;
+	u32			bytes = 0;
 	struct macb_tx_skb	*tx_skb;
 	struct macb_dma_desc	*desc;
 	struct sk_buff		*skb;
 	unsigned int		tail;
 	unsigned long		flags;
 
+	queue_index = queue - bp->queues;
 	netdev_vdbg(bp->dev, "macb_tx_error_task: q = %u, t = %u, h = %u\n",
-		    (unsigned int)(queue - bp->queues),
-		    queue->tx_tail, queue->tx_head);
+		    queue_index, queue->tx_tail, queue->tx_head);
 
 	/* Prevent the queue NAPI TX poll from running, as it calls
 	 * macb_tx_complete(), which in turn may call netif_wake_subqueue().
@@ -1140,8 +1143,10 @@ static void macb_tx_error_task(struct work_struct *work)
 					    skb->data);
 				bp->dev->stats.tx_packets++;
 				queue->stats.tx_packets++;
+				packets++;
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
+				bytes += skb->len;
 			}
 		} else {
 			/* "Buffers exhausted mid-frame" errors may only happen
@@ -1158,6 +1163,9 @@ static void macb_tx_error_task(struct work_struct *work)
 		macb_tx_unmap(bp, tx_skb, 0);
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	/* Set end of TX queue */
 	desc = macb_tx_desc(queue, 0);
 	macb_set_addr(bp, desc, 0);
@@ -1228,6 +1236,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 	unsigned int tail;
 	unsigned int head;
 	int packets = 0;
+	u32 bytes = 0;
 
 	spin_lock(&queue->tx_ptr_lock);
 	head = queue->tx_head;
@@ -1269,6 +1278,7 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 				bp->dev->stats.tx_bytes += skb->len;
 				queue->stats.tx_bytes += skb->len;
 				packets++;
+				bytes += skb->len;
 			}
 
 			/* Now we can safely release resources */
@@ -1283,6 +1293,9 @@ static int macb_tx_complete(struct macb_queue *queue, int budget)
 		}
 	}
 
+	netdev_tx_completed_queue(netdev_get_tx_queue(bp->dev, queue_index),
+				  packets, bytes);
+
 	queue->tx_tail = tail;
 	if (__netif_subqueue_stopped(bp->dev, queue_index) &&
 	    CIRC_CNT(queue->tx_head, queue->tx_tail,
@@ -2384,6 +2397,8 @@ static netdev_tx_t macb_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	/* Make newly initialized descriptor visible to hardware */
 	wmb();
 	skb_tx_timestamp(skb);
+	netdev_tx_sent_queue(netdev_get_tx_queue(bp->dev, queue_index),
+			     skb->len);
 
 	spin_lock_irq(&bp->lock);
 	macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART));
@@ -3019,6 +3034,7 @@ static int macb_close(struct net_device *dev)
 	for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue) {
 		napi_disable(&queue->napi_rx);
 		napi_disable(&queue->napi_tx);
+		netdev_tx_reset_queue(netdev_get_tx_queue(dev, q));
 	}
 
 	phylink_stop(bp->phylink);

From 28b04731a38c80092f47437af6c2770765e0b99f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 16:50:12 -0800
Subject: [PATCH 1003/2753] MAINTAINERS: fix DWMAC S32 entry

Using L: with more than a bare email address causes getmaintainer.pl
to be unable to parse the entry. Fix this by doing as other entries
that use this email address and convert it to an R: entry.

Link: https://patch.msgid.link/20250221005012.1051897-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3864d473f52f2..ac15093537c6b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2877,7 +2877,7 @@ F:	drivers/pinctrl/nxp/
 
 ARM/NXP S32G/S32R DWMAC ETHERNET DRIVER
 M:	Jan Petrous <jan.petrous@oss.nxp.com>
-L:	NXP S32 Linux Team <s32@nxp.com>
+R:	s32@nxp.com
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/nxp,s32-dwmac.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c

From dcc35baae732b9079b2c6595cfd86da02b34a4e6 Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Fri, 21 Feb 2025 08:56:57 +0800
Subject: [PATCH 1004/2753] usb: Add base USB MCTP definitions

Upcoming changes will add a USB host (and later gadget) driver for the
MCTP-over-USB protocol. Add a header that provides common definitions
for protocol support: the packet header format and a few framing
definitions. Add a define for the MCTP class code, as per
https://usb.org/defined-class-codes.

Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://patch.msgid.link/20250221-dev-mctp-usb-v3-1-3353030fe9cc@codeconstruct.com.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                  |  1 +
 include/linux/usb/mctp-usb.h | 30 ++++++++++++++++++++++++++++++
 include/uapi/linux/usb/ch9.h |  1 +
 3 files changed, 32 insertions(+)
 create mode 100644 include/linux/usb/mctp-usb.h

diff --git a/MAINTAINERS b/MAINTAINERS
index b0cd54818bb31..8019d5a975468 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13896,6 +13896,7 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/networking/mctp.rst
 F:	drivers/net/mctp/
+F:	include/linux/usb/mctp-usb.h
 F:	include/net/mctp.h
 F:	include/net/mctpdevice.h
 F:	include/net/netns/mctp.h
diff --git a/include/linux/usb/mctp-usb.h b/include/linux/usb/mctp-usb.h
new file mode 100644
index 0000000000000..a2f6f1e04efbd
--- /dev/null
+++ b/include/linux/usb/mctp-usb.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * mctp-usb.h - MCTP USB transport binding: common definitions,
+ * based on DMTF0283 specification:
+ * https://www.dmtf.org/sites/default/files/standards/documents/DSP0283_1.0.1.pdf
+ *
+ * These are protocol-level definitions, that may be shared between host
+ * and gadget drivers.
+ *
+ * Copyright (C) 2024-2025 Code Construct Pty Ltd
+ */
+
+#ifndef __LINUX_USB_MCTP_USB_H
+#define __LINUX_USB_MCTP_USB_H
+
+#include <linux/types.h>
+
+struct mctp_usb_hdr {
+	__be16	id;
+	u8	rsvd;
+	u8	len;
+} __packed;
+
+#define MCTP_USB_XFER_SIZE	512
+#define MCTP_USB_BTU		68
+#define MCTP_USB_MTU_MIN	MCTP_USB_BTU
+#define MCTP_USB_MTU_MAX	(U8_MAX - sizeof(struct mctp_usb_hdr))
+#define MCTP_USB_DMTF_ID	0x1ab4
+
+#endif /*  __LINUX_USB_MCTP_USB_H */
diff --git a/include/uapi/linux/usb/ch9.h b/include/uapi/linux/usb/ch9.h
index 91f0f7e214a5a..0522906520465 100644
--- a/include/uapi/linux/usb/ch9.h
+++ b/include/uapi/linux/usb/ch9.h
@@ -330,6 +330,7 @@ struct usb_device_descriptor {
 #define USB_CLASS_AUDIO_VIDEO		0x10
 #define USB_CLASS_BILLBOARD		0x11
 #define USB_CLASS_USB_TYPE_C_BRIDGE	0x12
+#define USB_CLASS_MCTP			0x14
 #define USB_CLASS_MISC			0xef
 #define USB_CLASS_APP_SPEC		0xfe
 #define USB_SUBCLASS_DFU			0x01

From 0791c0327a6e4e7691d6fc5ad334c215de04dcc9 Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Fri, 21 Feb 2025 08:56:58 +0800
Subject: [PATCH 1005/2753] net: mctp: Add MCTP USB transport driver

Add an implementation for DMTF DSP0283, which defines a MCTP-over-USB
transport. As per that spec, we're restricted to full speed mode,
requiring 512-byte transfers.

Each MCTP-over-USB interface is a peer-to-peer link to a single MCTP
endpoint, so no physical addressing is required (of course, that MCTP
endpoint may then bridge to further MCTP endpoints). Consequently,
interfaces will report with no lladdr data:

    # mctp link
    dev lo index 1 address 00:00:00:00:00:00 net 1 mtu 65536 up
    dev mctpusb0 index 6 address none net 1 mtu 68 up

This is a simple initial implementation, with single rx & tx urbs, and
no multi-packet tx transfers - although we do accept multi-packet rx
from the device.

Includes suggested fixes from Santosh Puranik <spuranik@nvidia.com>.

Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Cc: Santosh Puranik <spuranik@nvidia.com>
Link: https://patch.msgid.link/20250221-dev-mctp-usb-v3-2-3353030fe9cc@codeconstruct.com.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mctp/Kconfig    |  10 +
 drivers/net/mctp/Makefile   |   1 +
 drivers/net/mctp/mctp-usb.c | 385 ++++++++++++++++++++++++++++++++++++
 3 files changed, 396 insertions(+)
 create mode 100644 drivers/net/mctp/mctp-usb.c

diff --git a/drivers/net/mctp/Kconfig b/drivers/net/mctp/Kconfig
index 15860d6ac39fe..cf325ab0b1ef5 100644
--- a/drivers/net/mctp/Kconfig
+++ b/drivers/net/mctp/Kconfig
@@ -47,6 +47,16 @@ config MCTP_TRANSPORT_I3C
 	  A MCTP protocol network device is created for each I3C bus
 	  having a "mctp-controller" devicetree property.
 
+config MCTP_TRANSPORT_USB
+	tristate "MCTP USB transport"
+	depends on USB
+	help
+	  Provides a driver to access MCTP devices over USB transport,
+	  defined by DMTF specification DSP0283.
+
+	  MCTP-over-USB interfaces are peer-to-peer, so each interface
+	  represents a physical connection to one remote MCTP endpoint.
+
 endmenu
 
 endif
diff --git a/drivers/net/mctp/Makefile b/drivers/net/mctp/Makefile
index e1cb99ced54ac..c36006849a1e7 100644
--- a/drivers/net/mctp/Makefile
+++ b/drivers/net/mctp/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_MCTP_SERIAL) += mctp-serial.o
 obj-$(CONFIG_MCTP_TRANSPORT_I2C) += mctp-i2c.o
 obj-$(CONFIG_MCTP_TRANSPORT_I3C) += mctp-i3c.o
+obj-$(CONFIG_MCTP_TRANSPORT_USB) += mctp-usb.o
diff --git a/drivers/net/mctp/mctp-usb.c b/drivers/net/mctp/mctp-usb.c
new file mode 100644
index 0000000000000..e8d4b01c3f345
--- /dev/null
+++ b/drivers/net/mctp/mctp-usb.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * mctp-usb.c - MCTP-over-USB (DMTF DSP0283) transport binding driver.
+ *
+ * DSP0283 is available at:
+ * https://www.dmtf.org/sites/default/files/standards/documents/DSP0283_1.0.1.pdf
+ *
+ * Copyright (C) 2024-2025 Code Construct Pty Ltd
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/usb.h>
+#include <linux/usb/mctp-usb.h>
+
+#include <net/mctp.h>
+#include <net/mctpdevice.h>
+#include <net/pkt_sched.h>
+
+#include <uapi/linux/if_arp.h>
+
+struct mctp_usb {
+	struct usb_device *usbdev;
+	struct usb_interface *intf;
+	bool stopped;
+
+	struct net_device *netdev;
+
+	u8 ep_in;
+	u8 ep_out;
+
+	struct urb *tx_urb;
+	struct urb *rx_urb;
+
+	struct delayed_work rx_retry_work;
+};
+
+static void mctp_usb_out_complete(struct urb *urb)
+{
+	struct sk_buff *skb = urb->context;
+	struct net_device *netdev = skb->dev;
+	int status;
+
+	status = urb->status;
+
+	switch (status) {
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+	case -EPROTO:
+		dev_dstats_tx_dropped(netdev);
+		break;
+	case 0:
+		dev_dstats_tx_add(netdev, skb->len);
+		netif_wake_queue(netdev);
+		consume_skb(skb);
+		return;
+	default:
+		netdev_dbg(netdev, "unexpected tx urb status: %d\n", status);
+		dev_dstats_tx_dropped(netdev);
+	}
+
+	kfree_skb(skb);
+}
+
+static netdev_tx_t mctp_usb_start_xmit(struct sk_buff *skb,
+				       struct net_device *dev)
+{
+	struct mctp_usb *mctp_usb = netdev_priv(dev);
+	struct mctp_usb_hdr *hdr;
+	unsigned int plen;
+	struct urb *urb;
+	int rc;
+
+	plen = skb->len;
+
+	if (plen + sizeof(*hdr) > MCTP_USB_XFER_SIZE)
+		goto err_drop;
+
+	rc = skb_cow_head(skb, sizeof(*hdr));
+	if (rc)
+		goto err_drop;
+
+	hdr = skb_push(skb, sizeof(*hdr));
+	if (!hdr)
+		goto err_drop;
+
+	hdr->id = cpu_to_be16(MCTP_USB_DMTF_ID);
+	hdr->rsvd = 0;
+	hdr->len = plen + sizeof(*hdr);
+
+	urb = mctp_usb->tx_urb;
+
+	usb_fill_bulk_urb(urb, mctp_usb->usbdev,
+			  usb_sndbulkpipe(mctp_usb->usbdev, mctp_usb->ep_out),
+			  skb->data, skb->len,
+			  mctp_usb_out_complete, skb);
+
+	rc = usb_submit_urb(urb, GFP_ATOMIC);
+	if (rc)
+		goto err_drop;
+	else
+		netif_stop_queue(dev);
+
+	return NETDEV_TX_OK;
+
+err_drop:
+	dev_dstats_tx_dropped(dev);
+	kfree_skb(skb);
+	return NETDEV_TX_OK;
+}
+
+static void mctp_usb_in_complete(struct urb *urb);
+
+/* If we fail to queue an in urb atomically (either due to skb allocation or
+ * urb submission), we will schedule a rx queue in nonatomic context
+ * after a delay, specified in jiffies
+ */
+static const unsigned long RX_RETRY_DELAY = HZ / 4;
+
+static int mctp_usb_rx_queue(struct mctp_usb *mctp_usb, gfp_t gfp)
+{
+	struct sk_buff *skb;
+	int rc;
+
+	skb = __netdev_alloc_skb(mctp_usb->netdev, MCTP_USB_XFER_SIZE, gfp);
+	if (!skb) {
+		rc = -ENOMEM;
+		goto err_retry;
+	}
+
+	usb_fill_bulk_urb(mctp_usb->rx_urb, mctp_usb->usbdev,
+			  usb_rcvbulkpipe(mctp_usb->usbdev, mctp_usb->ep_in),
+			  skb->data, MCTP_USB_XFER_SIZE,
+			  mctp_usb_in_complete, skb);
+
+	rc = usb_submit_urb(mctp_usb->rx_urb, gfp);
+	if (rc) {
+		netdev_dbg(mctp_usb->netdev, "rx urb submit failure: %d\n", rc);
+		kfree_skb(skb);
+		if (rc == -ENOMEM)
+			goto err_retry;
+	}
+
+	return rc;
+
+err_retry:
+	schedule_delayed_work(&mctp_usb->rx_retry_work, RX_RETRY_DELAY);
+	return rc;
+}
+
+static void mctp_usb_in_complete(struct urb *urb)
+{
+	struct sk_buff *skb = urb->context;
+	struct net_device *netdev = skb->dev;
+	struct mctp_usb *mctp_usb = netdev_priv(netdev);
+	struct mctp_skb_cb *cb;
+	unsigned int len;
+	int status;
+
+	status = urb->status;
+
+	switch (status) {
+	case -ENOENT:
+	case -ECONNRESET:
+	case -ESHUTDOWN:
+	case -EPROTO:
+		kfree_skb(skb);
+		return;
+	case 0:
+		break;
+	default:
+		netdev_dbg(netdev, "unexpected rx urb status: %d\n", status);
+		kfree_skb(skb);
+		return;
+	}
+
+	len = urb->actual_length;
+	__skb_put(skb, len);
+
+	while (skb) {
+		struct sk_buff *skb2 = NULL;
+		struct mctp_usb_hdr *hdr;
+		u8 pkt_len; /* length of MCTP packet, no USB header */
+
+		hdr = skb_pull_data(skb, sizeof(*hdr));
+		if (!hdr)
+			break;
+
+		if (be16_to_cpu(hdr->id) != MCTP_USB_DMTF_ID) {
+			netdev_dbg(netdev, "rx: invalid id %04x\n",
+				   be16_to_cpu(hdr->id));
+			break;
+		}
+
+		if (hdr->len <
+		    sizeof(struct mctp_hdr) + sizeof(struct mctp_usb_hdr)) {
+			netdev_dbg(netdev, "rx: short packet (hdr) %d\n",
+				   hdr->len);
+			break;
+		}
+
+		/* we know we have at least sizeof(struct mctp_usb_hdr) here */
+		pkt_len = hdr->len - sizeof(struct mctp_usb_hdr);
+		if (pkt_len > skb->len) {
+			netdev_dbg(netdev,
+				   "rx: short packet (xfer) %d, actual %d\n",
+				   hdr->len, skb->len);
+			break;
+		}
+
+		if (pkt_len < skb->len) {
+			/* more packets may follow - clone to a new
+			 * skb to use on the next iteration
+			 */
+			skb2 = skb_clone(skb, GFP_ATOMIC);
+			if (skb2) {
+				if (!skb_pull(skb2, pkt_len)) {
+					kfree_skb(skb2);
+					skb2 = NULL;
+				}
+			}
+			skb_trim(skb, pkt_len);
+		}
+
+		dev_dstats_rx_add(netdev, skb->len);
+
+		skb->protocol = htons(ETH_P_MCTP);
+		skb_reset_network_header(skb);
+		cb = __mctp_cb(skb);
+		cb->halen = 0;
+		netif_rx(skb);
+
+		skb = skb2;
+	}
+
+	if (skb)
+		kfree_skb(skb);
+
+	mctp_usb_rx_queue(mctp_usb, GFP_ATOMIC);
+}
+
+static void mctp_usb_rx_retry_work(struct work_struct *work)
+{
+	struct mctp_usb *mctp_usb = container_of(work, struct mctp_usb,
+						 rx_retry_work.work);
+
+	if (READ_ONCE(mctp_usb->stopped))
+		return;
+
+	mctp_usb_rx_queue(mctp_usb, GFP_KERNEL);
+}
+
+static int mctp_usb_open(struct net_device *dev)
+{
+	struct mctp_usb *mctp_usb = netdev_priv(dev);
+
+	WRITE_ONCE(mctp_usb->stopped, false);
+
+	return mctp_usb_rx_queue(mctp_usb, GFP_KERNEL);
+}
+
+static int mctp_usb_stop(struct net_device *dev)
+{
+	struct mctp_usb *mctp_usb = netdev_priv(dev);
+
+	netif_stop_queue(dev);
+
+	/* prevent RX submission retry */
+	WRITE_ONCE(mctp_usb->stopped, true);
+
+	usb_kill_urb(mctp_usb->rx_urb);
+	usb_kill_urb(mctp_usb->tx_urb);
+
+	cancel_delayed_work_sync(&mctp_usb->rx_retry_work);
+
+	return 0;
+}
+
+static const struct net_device_ops mctp_usb_netdev_ops = {
+	.ndo_start_xmit = mctp_usb_start_xmit,
+	.ndo_open = mctp_usb_open,
+	.ndo_stop = mctp_usb_stop,
+};
+
+static void mctp_usb_netdev_setup(struct net_device *dev)
+{
+	dev->type = ARPHRD_MCTP;
+
+	dev->mtu = MCTP_USB_MTU_MIN;
+	dev->min_mtu = MCTP_USB_MTU_MIN;
+	dev->max_mtu = MCTP_USB_MTU_MAX;
+
+	dev->hard_header_len = sizeof(struct mctp_usb_hdr);
+	dev->tx_queue_len = DEFAULT_TX_QUEUE_LEN;
+	dev->flags = IFF_NOARP;
+	dev->netdev_ops = &mctp_usb_netdev_ops;
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_DSTATS;
+}
+
+static int mctp_usb_probe(struct usb_interface *intf,
+			  const struct usb_device_id *id)
+{
+	struct usb_endpoint_descriptor *ep_in, *ep_out;
+	struct usb_host_interface *iface_desc;
+	struct net_device *netdev;
+	struct mctp_usb *dev;
+	int rc;
+
+	/* only one alternate */
+	iface_desc = intf->cur_altsetting;
+
+	rc = usb_find_common_endpoints(iface_desc, &ep_in, &ep_out, NULL, NULL);
+	if (rc) {
+		dev_err(&intf->dev, "invalid endpoints on device?\n");
+		return rc;
+	}
+
+	netdev = alloc_netdev(sizeof(*dev), "mctpusb%d", NET_NAME_ENUM,
+			      mctp_usb_netdev_setup);
+	if (!netdev)
+		return -ENOMEM;
+
+	SET_NETDEV_DEV(netdev, &intf->dev);
+	dev = netdev_priv(netdev);
+	dev->netdev = netdev;
+	dev->usbdev = usb_get_dev(interface_to_usbdev(intf));
+	dev->intf = intf;
+	usb_set_intfdata(intf, dev);
+
+	dev->ep_in = ep_in->bEndpointAddress;
+	dev->ep_out = ep_out->bEndpointAddress;
+
+	dev->tx_urb = usb_alloc_urb(0, GFP_KERNEL);
+	dev->rx_urb = usb_alloc_urb(0, GFP_KERNEL);
+	if (!dev->tx_urb || !dev->rx_urb) {
+		rc = -ENOMEM;
+		goto err_free_urbs;
+	}
+
+	INIT_DELAYED_WORK(&dev->rx_retry_work, mctp_usb_rx_retry_work);
+
+	rc = mctp_register_netdev(netdev, NULL, MCTP_PHYS_BINDING_USB);
+	if (rc)
+		goto err_free_urbs;
+
+	return 0;
+
+err_free_urbs:
+	usb_free_urb(dev->tx_urb);
+	usb_free_urb(dev->rx_urb);
+	free_netdev(netdev);
+	return rc;
+}
+
+static void mctp_usb_disconnect(struct usb_interface *intf)
+{
+	struct mctp_usb *dev = usb_get_intfdata(intf);
+
+	mctp_unregister_netdev(dev->netdev);
+	usb_free_urb(dev->tx_urb);
+	usb_free_urb(dev->rx_urb);
+	usb_put_dev(dev->usbdev);
+	free_netdev(dev->netdev);
+}
+
+static const struct usb_device_id mctp_usb_devices[] = {
+	{ USB_INTERFACE_INFO(USB_CLASS_MCTP, 0x0, 0x1) },
+	{ 0 },
+};
+
+MODULE_DEVICE_TABLE(usb, mctp_usb_devices);
+
+static struct usb_driver mctp_usb_driver = {
+	.name		= "mctp-usb",
+	.id_table	= mctp_usb_devices,
+	.probe		= mctp_usb_probe,
+	.disconnect	= mctp_usb_disconnect,
+};
+
+module_usb_driver(mctp_usb_driver)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Jeremy Kerr <jk@codeconstruct.com.au>");
+MODULE_DESCRIPTION("MCTP USB transport");

From 781813db7909d945c33d3b035822225f3598774d Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Thu, 20 Feb 2025 16:12:12 +0100
Subject: [PATCH 1006/2753] i2c: core: Allocate temporary client dynamically
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

drivers/i2c/i2c-core-base.c: In function ‘i2c_detect.isra’:
drivers/i2c/i2c-core-base.c:2544:1: warning: the frame size of 1312 bytes is larger than 1024 bytes [-Wframe-larger-than=]
 2544 | }
      | ^

Fix this by allocating the temporary client structure dynamically, as it
is a rather large structure (1216 bytes, depending on kernel config).
This is basically a revert of the to-be-fixed commit with some
checkpatch improvements.

Fixes: 735668f8e5c9 ("i2c: core: Allocate temp client on the stack in i2c_detect")
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Su Hui <suhui@nfschina.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
[wsa: updated commit message, merged tags from similar patch]
Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
---
 drivers/i2c/i2c-core-base.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 35a221e2c11c1..7ad1ad5c8c3f5 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -2506,7 +2506,7 @@ static int i2c_detect_address(struct i2c_client *temp_client,
 static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver)
 {
 	const unsigned short *address_list;
-	struct i2c_client temp_client;
+	struct i2c_client *temp_client;
 	int i, err = 0;
 
 	address_list = driver->address_list;
@@ -2527,19 +2527,24 @@ static int i2c_detect(struct i2c_adapter *adapter, struct i2c_driver *driver)
 		return 0;
 
 	/* Set up a temporary client to help detect callback */
-	memset(&temp_client, 0, sizeof(temp_client));
-	temp_client.adapter = adapter;
+	temp_client = kzalloc(sizeof(*temp_client), GFP_KERNEL);
+	if (!temp_client)
+		return -ENOMEM;
+
+	temp_client->adapter = adapter;
 
 	for (i = 0; address_list[i] != I2C_CLIENT_END; i += 1) {
 		dev_dbg(&adapter->dev,
 			"found normal entry for adapter %d, addr 0x%02x\n",
 			i2c_adapter_id(adapter), address_list[i]);
-		temp_client.addr = address_list[i];
-		err = i2c_detect_address(&temp_client, driver);
+		temp_client->addr = address_list[i];
+		err = i2c_detect_address(temp_client, driver);
 		if (unlikely(err))
 			break;
 	}
 
+	kfree(temp_client);
+
 	return err;
 }
 

From b195d60408d49d3d2ed5f0e7baf5034ea0880ee6 Mon Sep 17 00:00:00 2001
From: Simon Wunderlich <sw@simonwunderlich.de>
Date: Sun, 2 Feb 2025 11:09:12 +0100
Subject: [PATCH 1007/2753] batman-adv: Start new development cycle

This version will contain all the (major or even only minor) changes for
Linux 6.15.

The version number isn't a semantic version number with major and minor
information. It is just encoding the year of the expected publishing as
Linux -rc1 and the number of published versions this year (starting at 0).

Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 964f3088af5b5..626618d0c366e 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -13,7 +13,7 @@
 #define BATADV_DRIVER_DEVICE "batman-adv"
 
 #ifndef BATADV_SOURCE_VERSION
-#define BATADV_SOURCE_VERSION "2025.0"
+#define BATADV_SOURCE_VERSION "2025.1"
 #endif
 
 /* B.A.T.M.A.N. parameters */

From 9a006e72d30c95c1bc7efd93441ece60ee15bd4e Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 10:29:23 +0100
Subject: [PATCH 1008/2753] batman-adv: Drop batadv_priv_debug_log struct

The support for the batman-adv ring buffer for debug logs was dropped with
the removal of the debugfs filesystem. The structure storing this ring
buffer is therefore no longer needed since commit aff6f5a68b92
("batman-adv: Drop deprecated debugfs support")

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/types.h | 28 ----------------------------
 1 file changed, 28 deletions(-)

diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index fe89f08533fe6..64a0cf4257ed4 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -1137,29 +1137,6 @@ struct batadv_priv_bla {
 };
 #endif
 
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-
-/**
- * struct batadv_priv_debug_log - debug logging data
- */
-struct batadv_priv_debug_log {
-	/** @log_buff: buffer holding the logs (ring buffer) */
-	char log_buff[BATADV_LOG_BUF_LEN];
-
-	/** @log_start: index of next character to read */
-	unsigned long log_start;
-
-	/** @log_end: index of next character to write */
-	unsigned long log_end;
-
-	/** @lock: lock protecting log_buff, log_start & log_end */
-	spinlock_t lock;
-
-	/** @queue_wait: log reader's wait queue */
-	wait_queue_head_t queue_wait;
-};
-#endif
-
 /**
  * struct batadv_priv_gw - per mesh interface gateway data
  */
@@ -1773,11 +1750,6 @@ struct batadv_priv {
 	struct batadv_priv_bla bla;
 #endif
 
-#ifdef CONFIG_BATMAN_ADV_DEBUG
-	/** @debug_log: holding debug logging relevant data */
-	struct batadv_priv_debug_log *debug_log;
-#endif
-
 	/** @gw: gateway data */
 	struct batadv_priv_gw gw;
 

From 00b35530811f2aa3d7ceec2dbada80861c7632a8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 6 Feb 2025 14:04:22 +0000
Subject: [PATCH 1009/2753] batman-adv: adopt netdev_hold() / netdev_put()

Add a device tracker to struct batadv_hard_iface to help
debugging of network device refcount imbalances.

Signed-off-by: Eric Dumazet <edumazet@google.com>
[sven@narfation.org: fix kernel-doc, adopt for softif reference]
Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/hard-interface.c | 20 ++++++++------------
 net/batman-adv/types.h          |  6 ++++++
 2 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 96a412beab2de..71b2236c00587 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -51,7 +51,7 @@ void batadv_hardif_release(struct kref *ref)
 	struct batadv_hard_iface *hard_iface;
 
 	hard_iface = container_of(ref, struct batadv_hard_iface, refcount);
-	dev_put(hard_iface->net_dev);
+	netdev_put(hard_iface->net_dev, &hard_iface->dev_tracker);
 
 	kfree_rcu(hard_iface, rcu);
 }
@@ -728,6 +728,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	kref_get(&hard_iface->refcount);
 
 	dev_hold(soft_iface);
+	netdev_hold(soft_iface, &hard_iface->softif_dev_tracker, GFP_ATOMIC);
 	hard_iface->soft_iface = soft_iface;
 	bat_priv = netdev_priv(hard_iface->soft_iface);
 
@@ -784,7 +785,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	netdev_upper_dev_unlink(hard_iface->net_dev, soft_iface);
 err_dev:
 	hard_iface->soft_iface = NULL;
-	dev_put(soft_iface);
+	netdev_put(soft_iface, &hard_iface->softif_dev_tracker);
 	batadv_hardif_put(hard_iface);
 	return ret;
 }
@@ -851,7 +852,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 	/* delete all references to this hard_iface */
 	batadv_purge_orig_ref(bat_priv);
 	batadv_purge_outstanding_packets(bat_priv, hard_iface);
-	dev_put(hard_iface->soft_iface);
+	netdev_put(hard_iface->soft_iface, &hard_iface->softif_dev_tracker);
 
 	netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface);
 	batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface);
@@ -875,15 +876,15 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	ASSERT_RTNL();
 
 	if (!batadv_is_valid_iface(net_dev))
-		goto out;
-
-	dev_hold(net_dev);
+		return NULL;
 
 	hard_iface = kzalloc(sizeof(*hard_iface), GFP_ATOMIC);
 	if (!hard_iface)
-		goto release_dev;
+		return NULL;
 
+	netdev_hold(net_dev, &hard_iface->dev_tracker, GFP_ATOMIC);
 	hard_iface->net_dev = net_dev;
+
 	hard_iface->soft_iface = NULL;
 	hard_iface->if_status = BATADV_IF_NOT_IN_USE;
 
@@ -909,11 +910,6 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	batadv_hardif_generation++;
 
 	return hard_iface;
-
-release_dev:
-	dev_put(net_dev);
-out:
-	return NULL;
 }
 
 static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface)
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index 64a0cf4257ed4..b3b4f71f6dec4 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -186,6 +186,9 @@ struct batadv_hard_iface {
 	/** @net_dev: pointer to the net_device */
 	struct net_device *net_dev;
 
+	/** @dev_tracker: device tracker for @net_dev */
+	netdevice_tracker dev_tracker;
+
 	/** @refcount: number of contexts the object is used */
 	struct kref refcount;
 
@@ -201,6 +204,9 @@ struct batadv_hard_iface {
 	 */
 	struct net_device *soft_iface;
 
+	/** @softif_dev_tracker: device tracker for @soft_iface */
+	netdevice_tracker softif_dev_tracker;
+
 	/** @rcu: struct used for freeing in an RCU-safe manner */
 	struct rcu_head rcu;
 

From 1666951c4424205d700143a55d75ced4982afb21 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 12:39:57 +0100
Subject: [PATCH 1010/2753] batman-adv: Add support for jumbo frames

Since batman-adv is not actually depending on hardware capabilities, it has
no limit on the MTU. Only the lower hard interfaces can limit it. In case
these have an high enough MTU or fragmentation is enabled, a higher MTU
than 1500 can be enabled.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/hard-interface.c | 4 +---
 net/batman-adv/main.h           | 2 ++
 net/batman-adv/soft-interface.c | 3 ++-
 3 files changed, 5 insertions(+), 4 deletions(-)

diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index 71b2236c00587..e7e7f14da03c9 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -618,10 +618,8 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 
 	/* the real soft-interface MTU is computed by removing the payload
 	 * overhead from the maximum amount of bytes that was just computed.
-	 *
-	 * However batman-adv does not support MTUs bigger than ETH_DATA_LEN
 	 */
-	return min_t(int, min_mtu - batadv_max_header_len(), ETH_DATA_LEN);
+	return min_t(int, min_mtu - batadv_max_header_len(), BATADV_MAX_MTU);
 }
 
 /**
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 626618d0c366e..4ecc304eaddd7 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -22,6 +22,8 @@
 #define BATADV_THROUGHPUT_MAX_VALUE 0xFFFFFFFF
 #define BATADV_JITTER 20
 
+#define BATADV_MAX_MTU (ETH_MAX_MTU - batadv_max_header_len())
+
 /* Time To Live of broadcast messages */
 #define BATADV_TTL 50
 
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index d893c80132616..b1127e6e8900a 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -790,7 +790,7 @@ static int batadv_softif_init_late(struct net_device *dev)
 	atomic_set(&bat_priv->log_level, 0);
 #endif
 	atomic_set(&bat_priv->fragmentation, 1);
-	atomic_set(&bat_priv->packet_size_max, ETH_DATA_LEN);
+	atomic_set(&bat_priv->packet_size_max, BATADV_MAX_MTU);
 	atomic_set(&bat_priv->bcast_queue_left, BATADV_BCAST_QUEUE_LEN);
 	atomic_set(&bat_priv->batman_queue_left, BATADV_BATMAN_QUEUE_LEN);
 
@@ -1043,6 +1043,7 @@ static void batadv_softif_init_early(struct net_device *dev)
 	 * have not been initialized yet
 	 */
 	dev->mtu = ETH_DATA_LEN;
+	dev->max_mtu = BATADV_MAX_MTU;
 
 	/* generate random address */
 	eth_hw_addr_random(dev);

From 94433355027db60005551310975de94978549783 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 13:39:32 +0100
Subject: [PATCH 1011/2753] batman-adv: Use consistent name for mesh interface

The way how the virtual interface is called inside the batman-adv source
code is not consistent. The genl headers call it meshif and the rest of the
code calls is (mostly) softif.

The genl definitions cannot be touched because they are part of the UAPI.
But the rest of the batman-adv code can be touched to have a consistent
name again.

The bulk of the renaming was done using

  sed -i -e 's/soft\(-\|\_\| \|\)i\([nf]\)/mesh\1i\2/g' \
         -e 's/SOFT\(-\|\_\| \|\)I\([NF]\)/MESH\1I\2/g'

and then it was adjusted slightly when proofreading the changes.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 Documentation/networking/batman-adv.rst       |   2 +-
 include/uapi/linux/batman_adv.h               |  18 +-
 net/batman-adv/Makefile                       |   2 +-
 net/batman-adv/bat_algo.c                     |   8 +-
 net/batman-adv/bat_iv_ogm.c                   |  64 +++---
 net/batman-adv/bat_v.c                        |  28 +--
 net/batman-adv/bat_v_elp.c                    |  16 +-
 net/batman-adv/bat_v_ogm.c                    |  42 ++--
 net/batman-adv/bitarray.c                     |   2 +-
 net/batman-adv/bridge_loop_avoidance.c        | 106 +++++-----
 net/batman-adv/distributed-arp-table.c        |  68 +++---
 net/batman-adv/distributed-arp-table.h        |   4 +-
 net/batman-adv/fragmentation.c                |   2 +-
 net/batman-adv/gateway_client.c               |  38 ++--
 net/batman-adv/gateway_common.c               |   8 +-
 net/batman-adv/hard-interface.c               | 140 ++++++-------
 net/batman-adv/hard-interface.h               |  12 +-
 net/batman-adv/log.c                          |   2 +-
 net/batman-adv/log.h                          |  10 +-
 net/batman-adv/main.c                         |  42 ++--
 net/batman-adv/main.h                         |  16 +-
 .../{soft-interface.c => mesh-interface.c}    | 194 ++++++++---------
 .../{soft-interface.h => mesh-interface.h}    |  22 +-
 net/batman-adv/multicast.c                    | 182 ++++++++--------
 net/batman-adv/multicast_forw.c               |  30 +--
 net/batman-adv/netlink.c                      | 178 ++++++++--------
 net/batman-adv/netlink.h                      |   2 +-
 net/batman-adv/network-coding.c               |  64 +++---
 net/batman-adv/originator.c                   |  58 ++---
 net/batman-adv/routing.c                      |  42 ++--
 net/batman-adv/send.c                         |  34 +--
 net/batman-adv/send.h                         |   4 +-
 net/batman-adv/tp_meter.c                     |  30 +--
 net/batman-adv/trace.h                        |   2 +-
 net/batman-adv/translation-table.c            | 198 +++++++++---------
 net/batman-adv/translation-table.h            |   4 +-
 net/batman-adv/tvlv.c                         |  26 +--
 net/batman-adv/types.h                        |  46 ++--
 38 files changed, 873 insertions(+), 873 deletions(-)
 rename net/batman-adv/{soft-interface.c => mesh-interface.c} (84%)
 rename net/batman-adv/{soft-interface.h => mesh-interface.h} (50%)

diff --git a/Documentation/networking/batman-adv.rst b/Documentation/networking/batman-adv.rst
index 44b9b5cc0e24b..ec53a42499c13 100644
--- a/Documentation/networking/batman-adv.rst
+++ b/Documentation/networking/batman-adv.rst
@@ -27,7 +27,7 @@ Load the batman-adv module into your kernel::
   $ insmod batman-adv.ko
 
 The module is now waiting for activation. You must add some interfaces on which
-batman-adv can operate. The batman-adv soft-interface can be created using the
+batman-adv can operate. The batman-adv mesh-interface can be created using the
 iproute2 tool ``ip``::
 
   $ ip link add name bat0 type batadv
diff --git a/include/uapi/linux/batman_adv.h b/include/uapi/linux/batman_adv.h
index 35dc016c9bb41..936bcac270b5e 100644
--- a/include/uapi/linux/batman_adv.h
+++ b/include/uapi/linux/batman_adv.h
@@ -342,7 +342,7 @@ enum batadv_nl_attrs {
 	BATADV_ATTR_MCAST_FLAGS_PRIV,
 
 	/**
-	 * @BATADV_ATTR_VLANID: VLAN id on top of soft interface
+	 * @BATADV_ATTR_VLANID: VLAN id on top of mesh interface
 	 */
 	BATADV_ATTR_VLANID,
 
@@ -380,7 +380,7 @@ enum batadv_nl_attrs {
 	/**
 	 * @BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED: whether the bridge loop
 	 *  avoidance feature is enabled. This feature detects and avoids loops
-	 *  between the mesh and devices bridged with the soft interface
+	 *  between the mesh and devices bridged with the mesh interface
 	 */
 	BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED,
 
@@ -509,7 +509,7 @@ enum batadv_nl_commands {
 	BATADV_CMD_UNSPEC,
 
 	/**
-	 * @BATADV_CMD_GET_MESH: Get attributes from softif/mesh
+	 * @BATADV_CMD_GET_MESH: Get attributes from mesh(if)
 	 */
 	BATADV_CMD_GET_MESH,
 
@@ -535,7 +535,7 @@ enum batadv_nl_commands {
 
 	/**
 	 * @BATADV_CMD_GET_HARDIF: Get attributes from a hardif of the
-	 *  current softif
+	 *  current mesh(if)
 	 */
 	BATADV_CMD_GET_HARDIF,
 
@@ -591,25 +591,25 @@ enum batadv_nl_commands {
 	BATADV_CMD_GET_MCAST_FLAGS,
 
 	/**
-	 * @BATADV_CMD_SET_MESH: Set attributes for softif/mesh
+	 * @BATADV_CMD_SET_MESH: Set attributes for mesh(if)
 	 */
 	BATADV_CMD_SET_MESH,
 
 	/**
 	 * @BATADV_CMD_SET_HARDIF: Set attributes for hardif of the
-	 *  current softif
+	 *  current mesh(if)
 	 */
 	BATADV_CMD_SET_HARDIF,
 
 	/**
 	 * @BATADV_CMD_GET_VLAN: Get attributes from a VLAN of the
-	 *  current softif
+	 *  current mesh(if)
 	 */
 	BATADV_CMD_GET_VLAN,
 
 	/**
 	 * @BATADV_CMD_SET_VLAN: Set attributes for VLAN of the
-	 *  current softif
+	 *  current mesh(if)
 	 */
 	BATADV_CMD_SET_VLAN,
 
@@ -691,7 +691,7 @@ enum batadv_ifla_attrs {
 	 */
 	IFLA_BATADV_ALGO_NAME,
 
-	/* add attributes above here, update the policy in soft-interface.c */
+	/* add attributes above here, update the policy in mesh-interface.c */
 
 	/**
 	 * @__IFLA_BATADV_MAX: internal use
diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile
index b51d8b071b562..1cc9be6de4569 100644
--- a/net/batman-adv/Makefile
+++ b/net/batman-adv/Makefile
@@ -19,6 +19,7 @@ batman-adv-y += hard-interface.o
 batman-adv-y += hash.o
 batman-adv-$(CONFIG_BATMAN_ADV_DEBUG) += log.o
 batman-adv-y += main.o
+batman-adv-y += mesh-interface.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast.o
 batman-adv-$(CONFIG_BATMAN_ADV_MCAST) += multicast_forw.o
 batman-adv-y += netlink.o
@@ -26,7 +27,6 @@ batman-adv-$(CONFIG_BATMAN_ADV_NC) += network-coding.o
 batman-adv-y += originator.o
 batman-adv-y += routing.o
 batman-adv-y += send.o
-batman-adv-y += soft-interface.o
 batman-adv-$(CONFIG_BATMAN_ADV_TRACING) += trace.o
 batman-adv-y += tp_meter.o
 batman-adv-y += translation-table.o
diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c
index 4eee53d19eb04..c0c982b6f0292 100644
--- a/net/batman-adv/bat_algo.c
+++ b/net/batman-adv/bat_algo.c
@@ -90,15 +90,15 @@ int batadv_algo_register(struct batadv_algo_ops *bat_algo_ops)
 }
 
 /**
- * batadv_algo_select() - Select algorithm of soft interface
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_algo_select() - Select algorithm of mesh interface
+ * @bat_priv: the bat priv with all the mesh interface information
  * @name: name of the algorithm to select
  *
- * The algorithm callbacks for the soft interface will be set when the algorithm
+ * The algorithm callbacks for the mesh interface will be set when the algorithm
  * with the correct name was found. Any previous selected algorithm will not be
  * deinitialized and the new selected algorithm will also not be initialized.
  * It is therefore not allowed to call batadv_algo_select outside the creation
- * function of the soft interface.
+ * function of the mesh interface.
  *
  * Return: 0 on success or negative error number in case of failure
  */
diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 07ae5dd1f150b..8513f6661dd10 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -129,7 +129,7 @@ static u8 batadv_ring_buffer_avg(const u8 lq_recv[])
 /**
  * batadv_iv_ogm_orig_get() - retrieve or create (if does not exist) an
  *  originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: mac address of the originator
  *
  * Return: the originator object corresponding to the passed mac address or NULL
@@ -333,7 +333,7 @@ batadv_iv_ogm_aggr_packet(int buff_pos, int packet_len,
 static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 				     struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	const char *fwd_str;
 	u8 packet_num;
 	s16 buff_pos;
@@ -396,20 +396,20 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 /* send a batman ogm packet */
 static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
 {
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 
 	if (!forw_packet->if_incoming) {
 		pr_err("Error - can't forward packet: incoming iface not specified\n");
 		return;
 	}
 
-	soft_iface = forw_packet->if_incoming->soft_iface;
+	mesh_iface = forw_packet->if_incoming->mesh_iface;
 
 	if (WARN_ON(!forw_packet->if_outgoing))
 		return;
 
-	if (forw_packet->if_outgoing->soft_iface != soft_iface) {
-		pr_warn("%s: soft interface switch for queued OGM\n", __func__);
+	if (forw_packet->if_outgoing->mesh_iface != mesh_iface) {
+		pr_warn("%s: mesh interface switch for queued OGM\n", __func__);
 		return;
 	}
 
@@ -424,7 +424,7 @@ static void batadv_iv_ogm_emit(struct batadv_forw_packet *forw_packet)
  * batadv_iv_ogm_can_aggregate() - find out if an OGM can be aggregated on an
  *  existing forward packet
  * @new_bat_ogm_packet: OGM packet to be aggregated
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @packet_len: (total) length of the OGM
  * @send_time: timestamp (jiffies) when the packet is to be sent
  * @directlink: true if this is a direct link packet
@@ -540,7 +540,7 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 					struct batadv_hard_iface *if_outgoing,
 					int own_packet)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_forw_packet *forw_packet_aggr;
 	struct sk_buff *skb;
 	unsigned char *skb_buff;
@@ -607,7 +607,7 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr,
 
 /**
  * batadv_iv_ogm_queue_add() - queue up an OGM for transmission
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @packet_buff: pointer to the OGM
  * @packet_len: (total) length of the OGM
  * @if_incoming: interface where the packet was received
@@ -686,7 +686,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 				  struct batadv_hard_iface *if_incoming,
 				  struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	u16 tvlv_len;
 
 	if (batadv_ogm_packet->ttl <= 1) {
@@ -739,7 +739,7 @@ static void batadv_iv_ogm_forward(struct batadv_orig_node *orig_node,
 static void
 batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	struct batadv_hashtable *hash = bat_priv->orig_hash;
 	struct hlist_head *head;
 	struct batadv_orig_node *orig_node;
@@ -778,7 +778,7 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface)
  */
 static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff;
 	struct batadv_ogm_packet *batadv_ogm_packet;
 	struct batadv_hard_iface *primary_if, *tmp_hard_iface;
@@ -840,7 +840,7 @@ static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface)
 	 */
 	rcu_read_lock();
 	list_for_each_entry_rcu(tmp_hard_iface, &batadv_hardif_list, list) {
-		if (tmp_hard_iface->soft_iface != hard_iface->soft_iface)
+		if (tmp_hard_iface->mesh_iface != hard_iface->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&tmp_hard_iface->refcount))
@@ -901,7 +901,7 @@ static u8 batadv_iv_orig_ifinfo_sum(struct batadv_orig_node *orig_node,
 /**
  * batadv_iv_ogm_orig_update() - use OGM to update corresponding data in an
  *  originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the orig node who originally emitted the ogm packet
  * @orig_ifinfo: ifinfo for the outgoing interface of the orig_node
  * @ethhdr: Ethernet header of the OGM
@@ -1065,7 +1065,7 @@ static bool batadv_iv_ogm_calc_tq(struct batadv_orig_node *orig_node,
 				  struct batadv_hard_iface *if_incoming,
 				  struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_neigh_node *neigh_node = NULL, *tmp_neigh_node;
 	struct batadv_neigh_ifinfo *neigh_ifinfo;
 	u8 total_count;
@@ -1207,7 +1207,7 @@ batadv_iv_ogm_update_seqnos(const struct ethhdr *ethhdr,
 			    const struct batadv_hard_iface *if_incoming,
 			    struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_orig_node *orig_node;
 	struct batadv_orig_ifinfo *orig_ifinfo = NULL;
 	struct batadv_neigh_node *neigh_node;
@@ -1309,7 +1309,7 @@ batadv_iv_ogm_process_per_outif(const struct sk_buff *skb, int ogm_offset,
 				struct batadv_hard_iface *if_incoming,
 				struct batadv_hard_iface *if_outgoing)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_hardif_neigh_node *hardif_neigh = NULL;
 	struct batadv_neigh_node *router = NULL;
 	struct batadv_neigh_node *router_router = NULL;
@@ -1549,7 +1549,7 @@ static void batadv_iv_ogm_process_reply(struct batadv_ogm_packet *ogm_packet,
 static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
 				  struct batadv_hard_iface *if_incoming)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_orig_node *orig_neigh_node, *orig_node;
 	struct batadv_hard_iface *hard_iface;
 	struct batadv_ogm_packet *ogm_packet;
@@ -1599,7 +1599,7 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != if_incoming->soft_iface)
+		if (hard_iface->mesh_iface != if_incoming->mesh_iface)
 			continue;
 
 		if (batadv_compare_eth(ethhdr->h_source,
@@ -1664,7 +1664,7 @@ static void batadv_iv_ogm_process(const struct sk_buff *skb, int ogm_offset,
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&hard_iface->refcount))
@@ -1690,7 +1690,7 @@ static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work)
 	delayed_work = to_delayed_work(work);
 	forw_packet = container_of(delayed_work, struct batadv_forw_packet,
 				   delayed_work);
-	bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
+	bat_priv = netdev_priv(forw_packet->if_incoming->mesh_iface);
 
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) {
 		dropped = true;
@@ -1721,7 +1721,7 @@ static void batadv_iv_send_outstanding_bat_ogm_packet(struct work_struct *work)
 static int batadv_iv_ogm_receive(struct sk_buff *skb,
 				 struct batadv_hard_iface *if_incoming)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_ogm_packet *ogm_packet;
 	u8 *packet_pos;
 	int ogm_offset;
@@ -1800,7 +1800,7 @@ batadv_iv_ogm_neigh_get_tq_avg(struct batadv_neigh_node *neigh_node,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @orig_node: Originator to dump
  * @neigh_node: Single hops neighbour
@@ -1863,7 +1863,7 @@ batadv_iv_ogm_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @orig_node: Originator to dump
  * @sub_s: Number of sub entries to skip
@@ -1925,7 +1925,7 @@ batadv_iv_ogm_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @head: Bucket to be dumped
  * @idx_s: Number of entries to be skipped
@@ -1966,7 +1966,7 @@ batadv_iv_ogm_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
  * batadv_iv_ogm_orig_dump() - Dump the originators into a message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  */
 static void
@@ -2088,7 +2088,7 @@ batadv_iv_ogm_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @hard_iface: Hard interface to dump the neighbours for
  * @idx_s: Number of entries to skip
  *
@@ -2125,7 +2125,7 @@ batadv_iv_ogm_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq,
  * batadv_iv_ogm_neigh_dump() - Dump the neighbours into a message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @single_hardif: Limit dump to this hard interface
  */
 static void
@@ -2152,7 +2152,7 @@ batadv_iv_ogm_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb,
 	} else {
 		list_for_each_entry_rcu(hard_iface, &batadv_hardif_list,
 					list) {
-			if (hard_iface->soft_iface != bat_priv->soft_iface)
+			if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 				continue;
 
 			if (i_hardif++ < i_hardif_s)
@@ -2236,7 +2236,7 @@ static void batadv_iv_iface_enabled(struct batadv_hard_iface *hard_iface)
 
 /**
  * batadv_iv_init_sel_class() - initialize GW selection class
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_iv_init_sel_class(struct batadv_priv *bat_priv)
 {
@@ -2391,7 +2391,7 @@ static bool batadv_iv_gw_is_eligible(struct batadv_priv *bat_priv,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @gw_node: Gateway to be dumped
  *
  * Return: Error code, or 0 on success
@@ -2466,7 +2466,7 @@ static int batadv_iv_gw_dump_entry(struct sk_buff *msg, u32 portid,
  * batadv_iv_gw_dump() - Dump gateways into a message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  */
 static void batadv_iv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 			      struct batadv_priv *bat_priv)
diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c
index d35479c465e2c..c16c2e60889d2 100644
--- a/net/batman-adv/bat_v.c
+++ b/net/batman-adv/bat_v.c
@@ -43,7 +43,7 @@
 
 static void batadv_v_iface_activate(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	struct batadv_hard_iface *primary_if;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
@@ -97,7 +97,7 @@ static void batadv_v_primary_iface_set(struct batadv_hard_iface *hard_iface)
  */
 static void batadv_v_iface_update_mac(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	struct batadv_hard_iface *primary_if;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
@@ -166,7 +166,7 @@ batadv_v_neigh_dump_neigh(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @hard_iface: The hard interface to be dumped
  * @idx_s: Entries to be skipped
  *
@@ -203,7 +203,7 @@ batadv_v_neigh_dump_hardif(struct sk_buff *msg, u32 portid, u32 seq,
  *  message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @single_hardif: Limit dumping to this hard interface
  */
 static void
@@ -228,7 +228,7 @@ batadv_v_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb,
 		}
 	} else {
 		list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-			if (hard_iface->soft_iface != bat_priv->soft_iface)
+			if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 				continue;
 
 			if (i_hardif++ < i_hardif_s)
@@ -254,7 +254,7 @@ batadv_v_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @orig_node: Originator to dump
  * @neigh_node: Single hops neighbour
@@ -322,7 +322,7 @@ batadv_v_orig_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @orig_node: Originator to dump
  * @sub_s: Number of sub entries to skip
@@ -374,7 +374,7 @@ batadv_v_orig_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  * @head: Bucket to be dumped
  * @idx_s: Number of entries to be skipped
@@ -414,7 +414,7 @@ batadv_v_orig_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
  * batadv_v_orig_dump() - Dump the originators into a message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @if_outgoing: Limit dump to entries with this outgoing interface
  */
 static void
@@ -502,7 +502,7 @@ static bool batadv_v_neigh_is_sob(struct batadv_neigh_node *neigh1,
 
 /**
  * batadv_v_init_sel_class() - initialize GW selection class
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_v_init_sel_class(struct batadv_priv *bat_priv)
 {
@@ -553,7 +553,7 @@ static int batadv_v_gw_throughput_get(struct batadv_gw_node *gw_node, u32 *bw)
 
 /**
  * batadv_v_gw_get_best_gw_node() - retrieve the best GW node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: the GW node having the best GW-metric, NULL if no GW is known
  */
@@ -590,7 +590,7 @@ batadv_v_gw_get_best_gw_node(struct batadv_priv *bat_priv)
 
 /**
  * batadv_v_gw_is_eligible() - check if a originator would be selected as GW
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @curr_gw_orig: originator representing the currently selected GW
  * @orig_node: the originator representing the new candidate
  *
@@ -647,7 +647,7 @@ static bool batadv_v_gw_is_eligible(struct batadv_priv *bat_priv,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @gw_node: Gateway to be dumped
  *
  * Return: Error code, or 0 on success
@@ -746,7 +746,7 @@ static int batadv_v_gw_dump_entry(struct sk_buff *msg, u32 portid,
  * batadv_v_gw_dump() - Dump gateways into a message
  * @msg: Netlink message to dump into
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  */
 static void batadv_v_gw_dump(struct sk_buff *msg, struct netlink_callback *cb,
 			     struct batadv_priv *bat_priv)
diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c
index b065578b4436e..70d6778da0d7b 100644
--- a/net/batman-adv/bat_v_elp.c
+++ b/net/batman-adv/bat_v_elp.c
@@ -82,7 +82,7 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh,
 					u32 *pthroughput)
 {
 	struct batadv_hard_iface *hard_iface = neigh->if_incoming;
-	struct net_device *soft_iface = hard_iface->soft_iface;
+	struct net_device *mesh_iface = hard_iface->mesh_iface;
 	struct ethtool_link_ksettings link_settings;
 	struct net_device *real_netdev;
 	struct station_info sinfo;
@@ -92,7 +92,7 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh,
 	/* don't query throughput when no longer associated with any
 	 * batman-adv interface
 	 */
-	if (!soft_iface)
+	if (!mesh_iface)
 		return false;
 
 	/* if the user specified a customised value for this interface, then
@@ -180,7 +180,7 @@ static bool batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh,
 
 default_throughput:
 	if (!(hard_iface->bat_v.flags & BATADV_WARNING_DEFAULT)) {
-		batadv_info(soft_iface,
+		batadv_info(mesh_iface,
 			    "WiFi driver or ethtool info does not provide information about link speeds on interface %s, therefore defaulting to hardcoded throughput values of %u.%1u Mbps. Consider overriding the throughput manually or checking your driver.\n",
 			    hard_iface->net_dev->name,
 			    BATADV_THROUGHPUT_DEFAULT_VALUE / 10,
@@ -226,7 +226,7 @@ static bool
 batadv_v_elp_wifi_neigh_probe(struct batadv_hardif_neigh_node *neigh)
 {
 	struct batadv_hard_iface *hard_iface = neigh->if_incoming;
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	unsigned long last_tx_diff;
 	struct sk_buff *skb;
 	int probe_len, i;
@@ -295,7 +295,7 @@ static void batadv_v_elp_periodic_work(struct work_struct *work)
 
 	bat_v = container_of(work, struct batadv_hard_iface_bat_v, elp_wq.work);
 	hard_iface = container_of(bat_v, struct batadv_hard_iface, bat_v);
-	bat_priv = netdev_priv(hard_iface->soft_iface);
+	bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING)
 		goto out;
@@ -476,7 +476,7 @@ void batadv_v_elp_primary_iface_set(struct batadv_hard_iface *primary_iface)
 	/* update orig field of every elp iface belonging to this mesh */
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (primary_iface->soft_iface != hard_iface->soft_iface)
+		if (primary_iface->mesh_iface != hard_iface->mesh_iface)
 			continue;
 
 		batadv_v_elp_iface_activate(primary_iface, hard_iface);
@@ -486,7 +486,7 @@ void batadv_v_elp_primary_iface_set(struct batadv_hard_iface *primary_iface)
 
 /**
  * batadv_v_elp_neigh_update() - update an ELP neighbour node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @neigh_addr: the neighbour interface address
  * @if_incoming: the interface the packet was received through
  * @elp_packet: the received ELP packet
@@ -552,7 +552,7 @@ static void batadv_v_elp_neigh_update(struct batadv_priv *bat_priv,
 int batadv_v_elp_packet_recv(struct sk_buff *skb,
 			     struct batadv_hard_iface *if_incoming)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_elp_packet *elp_packet;
 	struct batadv_hard_iface *primary_if;
 	struct ethhdr *ethhdr;
diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c
index e503ee0d896bd..3b9065a3c746a 100644
--- a/net/batman-adv/bat_v_ogm.c
+++ b/net/batman-adv/bat_v_ogm.c
@@ -45,7 +45,7 @@
 
 /**
  * batadv_v_ogm_orig_get() - retrieve and possibly create an originator node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the address of the originator
  *
  * Return: the orig_node corresponding to the specified address. If such an
@@ -96,7 +96,7 @@ static void batadv_v_ogm_start_queue_timer(struct batadv_hard_iface *hard_iface)
 
 /**
  * batadv_v_ogm_start_timer() - restart the OGM sending timer
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv)
 {
@@ -121,7 +121,7 @@ static void batadv_v_ogm_start_timer(struct batadv_priv *bat_priv)
 static void batadv_v_ogm_send_to_if(struct sk_buff *skb,
 				    struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	if (hard_iface->if_status != BATADV_IF_ACTIVE) {
 		kfree_skb(skb);
@@ -239,7 +239,7 @@ static void batadv_v_ogm_aggr_send(struct batadv_hard_iface *hard_iface)
 static void batadv_v_ogm_queue_on_if(struct sk_buff *skb,
 				     struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	if (!atomic_read(&bat_priv->aggregated_ogms)) {
 		batadv_v_ogm_send_to_if(skb, hard_iface);
@@ -256,10 +256,10 @@ static void batadv_v_ogm_queue_on_if(struct sk_buff *skb,
 }
 
 /**
- * batadv_v_ogm_send_softif() - periodic worker broadcasting the own OGM
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_v_ogm_send_meshif() - periodic worker broadcasting the own OGM
+ * @bat_priv: the bat priv with all the mesh interface information
  */
-static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv)
+static void batadv_v_ogm_send_meshif(struct batadv_priv *bat_priv)
 {
 	struct batadv_hard_iface *hard_iface;
 	struct batadv_ogm2_packet *ogm_packet;
@@ -302,7 +302,7 @@ static void batadv_v_ogm_send_softif(struct batadv_priv *bat_priv)
 	/* broadcast on every interface */
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&hard_iface->refcount))
@@ -373,7 +373,7 @@ static void batadv_v_ogm_send(struct work_struct *work)
 	bat_priv = container_of(bat_v, struct batadv_priv, bat_v);
 
 	mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
-	batadv_v_ogm_send_softif(bat_priv);
+	batadv_v_ogm_send_meshif(bat_priv);
 	mutex_unlock(&bat_priv->bat_v.ogm_buff_mutex);
 }
 
@@ -408,7 +408,7 @@ void batadv_v_ogm_aggr_work(struct work_struct *work)
  */
 int batadv_v_ogm_iface_enable(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	batadv_v_ogm_start_queue_timer(hard_iface);
 	batadv_v_ogm_start_timer(bat_priv);
@@ -435,7 +435,7 @@ void batadv_v_ogm_iface_disable(struct batadv_hard_iface *hard_iface)
  */
 void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(primary_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(primary_iface->mesh_iface);
 	struct batadv_ogm2_packet *ogm_packet;
 
 	mutex_lock(&bat_priv->bat_v.ogm_buff_mutex);
@@ -452,7 +452,7 @@ void batadv_v_ogm_primary_iface_set(struct batadv_hard_iface *primary_iface)
 /**
  * batadv_v_forward_penalty() - apply a penalty to the throughput metric
  *  forwarded with B.A.T.M.A.N. V OGMs
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @if_incoming: the interface where the OGM has been received
  * @if_outgoing: the interface where the OGM has to be forwarded to
  * @throughput: the current throughput
@@ -505,7 +505,7 @@ static u32 batadv_v_forward_penalty(struct batadv_priv *bat_priv,
 /**
  * batadv_v_ogm_forward() - check conditions and forward an OGM to the given
  *  outgoing interface
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ogm_received: previously received OGM to be forwarded
  * @orig_node: the originator which has been updated
  * @neigh_node: the neigh_node through with the OGM has been received
@@ -592,7 +592,7 @@ static void batadv_v_ogm_forward(struct batadv_priv *bat_priv,
 
 /**
  * batadv_v_ogm_metric_update() - update route metric based on OGM
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ogm2: OGM2 structure
  * @orig_node: Originator structure for which the OGM has been received
  * @neigh_node: the neigh_node through with the OGM has been received
@@ -675,7 +675,7 @@ static int batadv_v_ogm_metric_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_v_ogm_route_update() - update routes based on OGM
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ethhdr: the Ethernet header of the OGM2
  * @ogm2: OGM2 structure
  * @orig_node: Originator structure for which the OGM has been received
@@ -770,7 +770,7 @@ static bool batadv_v_ogm_route_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_v_ogm_process_per_outif() - process a batman v OGM for an outgoing if
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ethhdr: the Ethernet header of the OGM2
  * @ogm2: OGM2 structure
  * @orig_node: Originator structure for which the OGM has been received
@@ -852,7 +852,7 @@ batadv_v_ogm_aggr_packet(int buff_pos, int packet_len,
 static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 				 struct batadv_hard_iface *if_incoming)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct ethhdr *ethhdr;
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_hardif_neigh_node *hardif_neigh = NULL;
@@ -926,7 +926,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&hard_iface->refcount))
@@ -985,7 +985,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset,
 int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 			     struct batadv_hard_iface *if_incoming)
 {
-	struct batadv_priv *bat_priv = netdev_priv(if_incoming->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(if_incoming->mesh_iface);
 	struct batadv_ogm2_packet *ogm_packet;
 	struct ethhdr *ethhdr;
 	int ogm_offset;
@@ -1036,7 +1036,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,
 
 /**
  * batadv_v_ogm_init() - initialise the OGM2 engine
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or a negative error code in case of failure
  */
@@ -1071,7 +1071,7 @@ int batadv_v_ogm_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_v_ogm_free() - free OGM private resources
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_v_ogm_free(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c
index 649c41f393e1a..2c49b27116503 100644
--- a/net/batman-adv/bitarray.c
+++ b/net/batman-adv/bitarray.c
@@ -23,7 +23,7 @@ static void batadv_bitmap_shift_left(unsigned long *seq_bits, s32 n)
 /**
  * batadv_bit_get_packet() - receive and process one packet within the sequence
  *  number window
- * @priv: the bat priv with all the soft interface information
+ * @priv: the bat priv with all the mesh interface information
  * @seq_bits: pointer to the sequence number receive packet
  * @seq_num_diff: difference between the current/received sequence number and
  *  the last sequence number
diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c
index 8c814f790d177..747755647c6a4 100644
--- a/net/batman-adv/bridge_loop_avoidance.c
+++ b/net/batman-adv/bridge_loop_avoidance.c
@@ -209,7 +209,7 @@ static void batadv_claim_put(struct batadv_bla_claim *claim)
 
 /**
  * batadv_claim_hash_find() - looks for a claim in the claim hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @data: search data (may be local/static data)
  *
  * Return: claim if found or NULL otherwise.
@@ -248,7 +248,7 @@ batadv_claim_hash_find(struct batadv_priv *bat_priv,
 
 /**
  * batadv_backbone_hash_find() - looks for a backbone gateway in the hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the address of the originator
  * @vid: the VLAN ID
  *
@@ -332,7 +332,7 @@ batadv_bla_del_backbone_claims(struct batadv_bla_backbone_gw *backbone_gw)
 
 /**
  * batadv_bla_send_claim() - sends a claim frame according to the provided info
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @mac: the mac address to be announced within the claim
  * @vid: the VLAN ID
  * @claimtype: the type of the claim (CLAIM, UNCLAIM, ANNOUNCE, ...)
@@ -343,7 +343,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac,
 	struct sk_buff *skb;
 	struct ethhdr *ethhdr;
 	struct batadv_hard_iface *primary_if;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	u8 *hw_src;
 	struct batadv_bla_claim_dst local_claim_dest;
 	__be32 zeroip = 0;
@@ -356,12 +356,12 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac,
 	       sizeof(local_claim_dest));
 	local_claim_dest.type = claimtype;
 
-	soft_iface = primary_if->soft_iface;
+	mesh_iface = primary_if->mesh_iface;
 
 	skb = arp_create(ARPOP_REPLY, ETH_P_ARP,
 			 /* IP DST: 0.0.0.0 */
 			 zeroip,
-			 primary_if->soft_iface,
+			 primary_if->mesh_iface,
 			 /* IP SRC: 0.0.0.0 */
 			 zeroip,
 			 /* Ethernet DST: Broadcast */
@@ -439,7 +439,7 @@ static void batadv_bla_send_claim(struct batadv_priv *bat_priv, const u8 *mac,
 	}
 
 	skb_reset_mac_header(skb);
-	skb->protocol = eth_type_trans(skb, soft_iface);
+	skb->protocol = eth_type_trans(skb, mesh_iface);
 	batadv_inc_counter(bat_priv, BATADV_CNT_RX);
 	batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES,
 			   skb->len + ETH_HLEN);
@@ -466,7 +466,7 @@ static void batadv_bla_loopdetect_report(struct work_struct *work)
 				   report_work);
 	bat_priv = backbone_gw->bat_priv;
 
-	batadv_info(bat_priv->soft_iface,
+	batadv_info(bat_priv->mesh_iface,
 		    "Possible loop on VLAN %d detected which can't be handled by BLA - please check your network setup!\n",
 		    batadv_print_vid(backbone_gw->vid));
 	snprintf(vid_str, sizeof(vid_str), "%d",
@@ -481,7 +481,7 @@ static void batadv_bla_loopdetect_report(struct work_struct *work)
 
 /**
  * batadv_bla_get_backbone_gw() - finds or creates a backbone gateway
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the mac address of the originator
  * @vid: the VLAN ID
  * @own_backbone: set if the requested backbone is local
@@ -554,7 +554,7 @@ batadv_bla_get_backbone_gw(struct batadv_priv *bat_priv, const u8 *orig,
 
 /**
  * batadv_bla_update_own_backbone_gw() - updates the own backbone gw for a VLAN
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: the selected primary interface
  * @vid: VLAN identifier
  *
@@ -580,7 +580,7 @@ batadv_bla_update_own_backbone_gw(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_answer_request() - answer a bla request by sending own claims
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: interface where the request came on
  * @vid: the vid where the request came on
  *
@@ -657,7 +657,7 @@ static void batadv_bla_send_request(struct batadv_bla_backbone_gw *backbone_gw)
 
 /**
  * batadv_bla_send_announce() - Send an announcement frame
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @backbone_gw: our backbone gateway which should be announced
  */
 static void batadv_bla_send_announce(struct batadv_priv *bat_priv,
@@ -678,7 +678,7 @@ static void batadv_bla_send_announce(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_add_claim() - Adds a claim in the claim hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @mac: the mac address of the claim
  * @vid: the VLAN ID of the frame
  * @backbone_gw: the backbone gateway which claims it
@@ -788,7 +788,7 @@ batadv_bla_claim_get_backbone_gw(struct batadv_bla_claim *claim)
 
 /**
  * batadv_bla_del_claim() - delete a claim from the claim hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @mac: mac address of the claim to be removed
  * @vid: VLAN id for the claim to be removed
  */
@@ -826,7 +826,7 @@ static void batadv_bla_del_claim(struct batadv_priv *bat_priv,
 
 /**
  * batadv_handle_announce() - check for ANNOUNCE frame
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @an_addr: announcement mac address (ARP Sender HW address)
  * @backbone_addr: originator address of the sender (Ethernet source MAC)
  * @vid: the VLAN ID of the frame
@@ -884,8 +884,8 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr,
 
 /**
  * batadv_handle_request() - check for REQUEST frame
- * @bat_priv: the bat priv with all the soft interface information
- * @primary_if: the primary hard interface of this batman soft interface
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @primary_if: the primary hard interface of this batman mesh interface
  * @backbone_addr: backbone address to be requested (ARP sender HW MAC)
  * @ethhdr: ethernet header of a packet
  * @vid: the VLAN ID of the frame
@@ -917,8 +917,8 @@ static bool batadv_handle_request(struct batadv_priv *bat_priv,
 
 /**
  * batadv_handle_unclaim() - check for UNCLAIM frame
- * @bat_priv: the bat priv with all the soft interface information
- * @primary_if: the primary hard interface of this batman soft interface
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @primary_if: the primary hard interface of this batman mesh interface
  * @backbone_addr: originator address of the backbone (Ethernet source)
  * @claim_addr: Client to be unclaimed (ARP sender HW MAC)
  * @vid: the VLAN ID of the frame
@@ -955,8 +955,8 @@ static bool batadv_handle_unclaim(struct batadv_priv *bat_priv,
 
 /**
  * batadv_handle_claim() - check for CLAIM frame
- * @bat_priv: the bat priv with all the soft interface information
- * @primary_if: the primary hard interface of this batman soft interface
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @primary_if: the primary hard interface of this batman mesh interface
  * @backbone_addr: originator address of the backbone (Ethernet Source)
  * @claim_addr: client mac address to be claimed (ARP sender HW MAC)
  * @vid: the VLAN ID of the frame
@@ -992,7 +992,7 @@ static bool batadv_handle_claim(struct batadv_priv *bat_priv,
 
 /**
  * batadv_check_claim_group() - check for claim group membership
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: the primary interface of this batman interface
  * @hw_src: the Hardware source in the ARP Header
  * @hw_dst: the Hardware destination in the ARP Header
@@ -1067,8 +1067,8 @@ static int batadv_check_claim_group(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_process_claim() - Check if this is a claim frame, and process it
- * @bat_priv: the bat priv with all the soft interface information
- * @primary_if: the primary hard interface of this batman soft interface
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @primary_if: the primary hard interface of this batman mesh interface
  * @skb: the frame to be checked
  *
  * Return: true if it was a claim frame, otherwise return false to
@@ -1210,7 +1210,7 @@ static bool batadv_bla_process_claim(struct batadv_priv *bat_priv,
 /**
  * batadv_bla_purge_backbone_gw() - Remove backbone gateways after a timeout or
  *  immediately
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @now: whether the whole hash shall be wiped now
  *
  * Check when we last heard from other nodes, and remove them in case of
@@ -1262,7 +1262,7 @@ static void batadv_bla_purge_backbone_gw(struct batadv_priv *bat_priv, int now)
 
 /**
  * batadv_bla_purge_claims() - Remove claims after a timeout or immediately
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: the selected primary interface, may be NULL if now is set
  * @now: whether the whole hash shall be wiped now
  *
@@ -1321,7 +1321,7 @@ static void batadv_bla_purge_claims(struct batadv_priv *bat_priv,
 /**
  * batadv_bla_update_orig_address() - Update the backbone gateways when the own
  *  originator address changes
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: the new selected primary_if
  * @oldif: the old primary interface, may be NULL
  */
@@ -1376,7 +1376,7 @@ void batadv_bla_update_orig_address(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_send_loopdetect() - send a loopdetect frame
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @backbone_gw: the backbone gateway for which a loop should be detected
  *
  * To detect loops that the bridge loop avoidance can't handle, send a loop
@@ -1396,7 +1396,7 @@ batadv_bla_send_loopdetect(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_status_update() - purge bla interfaces if necessary
- * @net_dev: the soft interface net device
+ * @net_dev: the mesh interface net device
  */
 void batadv_bla_status_update(struct net_device *net_dev)
 {
@@ -1520,7 +1520,7 @@ static struct lock_class_key batadv_backbone_hash_lock_class_key;
 
 /**
  * batadv_bla_init() - initialize all bla structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success, < 0 on error.
  */
@@ -1586,7 +1586,7 @@ int batadv_bla_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_bla_check_duplist() - Check if a frame is in the broadcast dup.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: contains the multicast packet to be checked
  * @payload_ptr: pointer to position inside the head buffer of the skb
  *  marking the start of the data to be CRC'ed
@@ -1680,7 +1680,7 @@ static bool batadv_bla_check_duplist(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_check_ucast_duplist() - Check if a frame is in the broadcast dup.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: contains the multicast packet to be checked, decapsulated from a
  *  unicast_packet
  *
@@ -1698,7 +1698,7 @@ static bool batadv_bla_check_ucast_duplist(struct batadv_priv *bat_priv,
 
 /**
  * batadv_bla_check_bcast_duplist() - Check if a frame is in the broadcast dup.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: contains the bcast_packet to be checked
  *
  * Check if it is on our broadcast list. Another gateway might have sent the
@@ -1723,7 +1723,7 @@ bool batadv_bla_check_bcast_duplist(struct batadv_priv *bat_priv,
 /**
  * batadv_bla_is_backbone_gw_orig() - Check if the originator is a gateway for
  *  the VLAN identified by vid.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: originator mac address
  * @vid: VLAN identifier
  *
@@ -1766,7 +1766,7 @@ bool batadv_bla_is_backbone_gw_orig(struct batadv_priv *bat_priv, u8 *orig,
  * @orig_node: the orig_node of the frame
  * @hdr_size: maximum length of the frame
  *
- * Return: true if the orig_node is also a gateway on the soft interface,
+ * Return: true if the orig_node is also a gateway on the mesh interface,
  * otherwise it returns false.
  */
 bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
@@ -1796,9 +1796,9 @@ bool batadv_bla_is_backbone_gw(struct sk_buff *skb,
 
 /**
  * batadv_bla_free() - free all bla structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
- * for softinterface free or module unload
+ * for meshinterface free or module unload
  */
 void batadv_bla_free(struct batadv_priv *bat_priv)
 {
@@ -1822,7 +1822,7 @@ void batadv_bla_free(struct batadv_priv *bat_priv)
 
 /**
  * batadv_bla_loopdetect_check() - check and handle a detected loop
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the packet to check
  * @primary_if: interface where the request came on
  * @vid: the VLAN ID of the frame
@@ -1877,7 +1877,7 @@ batadv_bla_loopdetect_check(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_bla_rx() - check packets coming from the mesh.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the frame to be checked
  * @vid: the VLAN ID of the frame
  * @packet_type: the batman packet type this frame came in
@@ -2010,7 +2010,7 @@ bool batadv_bla_rx(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_bla_tx() - check packets going into the mesh
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the frame to be checked
  * @vid: the VLAN ID of the frame
  *
@@ -2232,18 +2232,18 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if = NULL;
 	int portid = NETLINK_CB(cb->skb).portid;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
 	int idx = cb->args[1];
 	int ret = 0;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 	hash = bat_priv->bla.claim_hash;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
@@ -2267,7 +2267,7 @@ int batadv_bla_claim_dump(struct sk_buff *msg, struct netlink_callback *cb)
 out:
 	batadv_hardif_put(primary_if);
 
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	return ret;
 }
@@ -2393,18 +2393,18 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if = NULL;
 	int portid = NETLINK_CB(cb->skb).portid;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
 	int idx = cb->args[1];
 	int ret = 0;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 	hash = bat_priv->bla.backbone_hash;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
@@ -2428,7 +2428,7 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
 out:
 	batadv_hardif_put(primary_if);
 
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	return ret;
 }
@@ -2437,7 +2437,7 @@ int batadv_bla_backbone_dump(struct sk_buff *msg, struct netlink_callback *cb)
 /**
  * batadv_bla_check_claim() - check if address is claimed
  *
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: mac address of which the claim status is checked
  * @vid: the VLAN ID
  *
diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c
index e5a07152d4ecf..8b8132eb0a79f 100644
--- a/net/batman-adv/distributed-arp-table.c
+++ b/net/batman-adv/distributed-arp-table.c
@@ -96,7 +96,7 @@ static void batadv_dat_purge(struct work_struct *work);
 
 /**
  * batadv_dat_start_timer() - initialise the DAT periodic worker
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_dat_start_timer(struct batadv_priv *bat_priv)
 {
@@ -145,7 +145,7 @@ static bool batadv_dat_to_purge(struct batadv_dat_entry *dat_entry)
 
 /**
  * __batadv_dat_purge() - delete entries from the DAT local storage
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @to_purge: function in charge to decide whether an entry has to be purged or
  *	      not. This function takes the dat_entry as argument and has to
  *	      returns a boolean value: true is the entry has to be deleted,
@@ -315,7 +315,7 @@ static u32 batadv_hash_dat(const void *data, u32 size)
 /**
  * batadv_dat_entry_hash_find() - look for a given dat_entry in the local hash
  * table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ip: search key
  * @vid: VLAN identifier
  *
@@ -357,7 +357,7 @@ batadv_dat_entry_hash_find(struct batadv_priv *bat_priv, __be32 ip,
 
 /**
  * batadv_dat_entry_add() - add a new dat entry or update it if already exists
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ip: ipv4 to add/edit
  * @mac_addr: mac address to assign to the given ipv4
  * @vid: VLAN identifier
@@ -414,7 +414,7 @@ static void batadv_dat_entry_add(struct batadv_priv *bat_priv, __be32 ip,
 /**
  * batadv_dbg_arp() - print a debug message containing all the ARP packet
  *  details
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: ARP packet
  * @hdr_size: size of the possible header before the ARP packet
  * @msg: message to print together with the debugging information
@@ -549,7 +549,7 @@ static bool batadv_is_orig_node_eligible(struct batadv_dat_candidate *res,
 
 /**
  * batadv_choose_next_candidate() - select the next DHT candidate
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @cands: candidates array
  * @select: number of candidates already present in the array
  * @ip_key: key to look up in the DHT
@@ -613,7 +613,7 @@ static void batadv_choose_next_candidate(struct batadv_priv *bat_priv,
 /**
  * batadv_dat_select_candidates() - select the nodes which the DHT message has
  *  to be sent to
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ip_dst: ipv4 to look up in the DHT
  * @vid: VLAN identifier
  *
@@ -658,7 +658,7 @@ batadv_dat_select_candidates(struct batadv_priv *bat_priv, __be32 ip_dst,
 
 /**
  * batadv_dat_forward_data() - copy and send payload to the selected candidates
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: payload to send
  * @ip: the DHT key
  * @vid: VLAN identifier
@@ -734,7 +734,7 @@ static bool batadv_dat_forward_data(struct batadv_priv *bat_priv,
 /**
  * batadv_dat_tvlv_container_update() - update the dat tvlv container after dat
  *  setting change
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv)
 {
@@ -756,7 +756,7 @@ static void batadv_dat_tvlv_container_update(struct batadv_priv *bat_priv)
 /**
  * batadv_dat_status_update() - update the dat tvlv container after dat
  *  setting change
- * @net_dev: the soft interface net device
+ * @net_dev: the mesh interface net device
  */
 void batadv_dat_status_update(struct net_device *net_dev)
 {
@@ -767,7 +767,7 @@ void batadv_dat_status_update(struct net_device *net_dev)
 
 /**
  * batadv_dat_tvlv_ogm_handler_v1() - process incoming dat tvlv container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the gateway data
@@ -786,7 +786,7 @@ static void batadv_dat_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 
 /**
  * batadv_dat_hash_free() - free the local DAT hash table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_dat_hash_free(struct batadv_priv *bat_priv)
 {
@@ -802,7 +802,7 @@ static void batadv_dat_hash_free(struct batadv_priv *bat_priv)
 
 /**
  * batadv_dat_init() - initialise the DAT internals
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 in case of success, a negative error code otherwise
  */
@@ -828,7 +828,7 @@ int batadv_dat_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_dat_free() - free the DAT internals
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_dat_free(struct batadv_priv *bat_priv)
 {
@@ -936,18 +936,18 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if = NULL;
 	int portid = NETLINK_CB(cb->skb).portid;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_hashtable *hash;
 	struct batadv_priv *bat_priv;
 	int bucket = cb->args[0];
 	int idx = cb->args[1];
 	int ret = 0;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 	hash = bat_priv->dat.hash;
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
@@ -973,14 +973,14 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb)
 out:
 	batadv_hardif_put(primary_if);
 
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	return ret;
 }
 
 /**
  * batadv_arp_get_type() - parse an ARP packet and gets the type
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to analyse
  * @hdr_size: size of the possible header before the ARP packet in the skb
  *
@@ -1080,7 +1080,7 @@ static unsigned short batadv_dat_get_vid(struct sk_buff *skb, int *hdr_size)
 
 /**
  * batadv_dat_arp_create_reply() - create an ARP Reply
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ip_src: ARP sender IP
  * @ip_dst: ARP target IP
  * @hw_src: Ethernet source and ARP sender MAC
@@ -1099,7 +1099,7 @@ batadv_dat_arp_create_reply(struct batadv_priv *bat_priv, __be32 ip_src,
 {
 	struct sk_buff *skb;
 
-	skb = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_dst, bat_priv->soft_iface,
+	skb = arp_create(ARPOP_REPLY, ETH_P_ARP, ip_dst, bat_priv->mesh_iface,
 			 ip_src, hw_dst, hw_src, hw_dst);
 	if (!skb)
 		return NULL;
@@ -1116,7 +1116,7 @@ batadv_dat_arp_create_reply(struct batadv_priv *bat_priv, __be32 ip_src,
 /**
  * batadv_dat_snoop_outgoing_arp_request() - snoop the ARP request and try to
  * answer using DAT
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to check
  *
  * Return: true if the message has been sent to the dht candidates, false
@@ -1132,7 +1132,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 	bool ret = false;
 	struct batadv_dat_entry *dat_entry = NULL;
 	struct sk_buff *skb_new;
-	struct net_device *soft_iface = bat_priv->soft_iface;
+	struct net_device *mesh_iface = bat_priv->mesh_iface;
 	int hdr_size = 0;
 	unsigned short vid;
 
@@ -1162,7 +1162,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		 * client will answer itself. DAT would only generate a
 		 * duplicate packet.
 		 *
-		 * Moreover, if the soft-interface is enslaved into a bridge, an
+		 * Moreover, if the mesh-interface is enslaved into a bridge, an
 		 * additional DAT answer may trigger kernel warnings about
 		 * a packet coming from the wrong port.
 		 */
@@ -1191,7 +1191,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 		if (!skb_new)
 			goto out;
 
-		skb_new->protocol = eth_type_trans(skb_new, soft_iface);
+		skb_new->protocol = eth_type_trans(skb_new, mesh_iface);
 
 		batadv_inc_counter(bat_priv, BATADV_CNT_RX);
 		batadv_add_counter(bat_priv, BATADV_CNT_RX_BYTES,
@@ -1213,7 +1213,7 @@ bool batadv_dat_snoop_outgoing_arp_request(struct batadv_priv *bat_priv,
 /**
  * batadv_dat_snoop_incoming_arp_request() - snoop the ARP request and try to
  * answer using the local DAT storage
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to check
  * @hdr_size: size of the encapsulation header
  *
@@ -1281,7 +1281,7 @@ bool batadv_dat_snoop_incoming_arp_request(struct batadv_priv *bat_priv,
 
 /**
  * batadv_dat_snoop_outgoing_arp_reply() - snoop the ARP reply and fill the DHT
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to check
  */
 void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
@@ -1324,7 +1324,7 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv,
 /**
  * batadv_dat_snoop_incoming_arp_reply() - snoop the ARP reply and fill the
  *  local DAT storage only
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to check
  * @hdr_size: size of the encapsulation header
  *
@@ -1605,7 +1605,7 @@ static bool batadv_dat_get_dhcp_chaddr(struct sk_buff *skb, u8 *buf)
 /**
  * batadv_dat_put_dhcp() - puts addresses from a DHCP packet into the DHT and
  *  DAT cache
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @chaddr: the DHCP client MAC address
  * @yiaddr: the DHCP client IP address
  * @hw_dst: the DHCP server MAC address
@@ -1690,7 +1690,7 @@ batadv_dat_check_dhcp_ack(struct sk_buff *skb, __be16 proto, __be32 *ip_src,
 
 /**
  * batadv_dat_snoop_outgoing_dhcp_ack() - snoop DHCPACK and fill DAT with it
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the packet to snoop
  * @proto: ethernet protocol hint (behind a potential vlan)
  * @vid: VLAN identifier
@@ -1723,7 +1723,7 @@ void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv,
 
 /**
  * batadv_dat_snoop_incoming_dhcp_ack() - snoop DHCPACK and fill DAT cache
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the packet to snoop
  * @hdr_size: header size, up to the tail of the batman-adv header
  *
@@ -1771,7 +1771,7 @@ void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv,
 /**
  * batadv_dat_drop_broadcast_packet() - check if an ARP request has to be
  *  dropped (because the node has already obtained the reply via DAT) or not
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @forw_packet: the broadcast packet
  *
  * Return: true if the node can drop the packet, false otherwise.
diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h
index bed7f3d208444..e7b75e82eb1d8 100644
--- a/net/batman-adv/distributed-arp-table.h
+++ b/net/batman-adv/distributed-arp-table.h
@@ -56,7 +56,7 @@ batadv_dat_init_orig_node_addr(struct batadv_orig_node *orig_node)
 
 /**
  * batadv_dat_init_own_addr() - assign a DAT address to the node itself
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @primary_if: a pointer to the primary interface
  */
 static inline void
@@ -77,7 +77,7 @@ int batadv_dat_cache_dump(struct sk_buff *msg, struct netlink_callback *cb);
 
 /**
  * batadv_dat_inc_counter() - increment the correct DAT packet counter
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @subtype: the 4addr subtype of the packet to be counted
  *
  * Updates the ethtool statistics for the received packet if it is a DAT subtype
diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c
index 757c084ac2d14..cc14bc41381e0 100644
--- a/net/batman-adv/fragmentation.c
+++ b/net/batman-adv/fragmentation.c
@@ -349,7 +349,7 @@ bool batadv_frag_skb_fwd(struct sk_buff *skb,
 			 struct batadv_hard_iface *recv_if,
 			 struct batadv_orig_node *orig_node_src)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_neigh_node *neigh_node = NULL;
 	struct batadv_frag_packet *packet;
 	u16 total_size;
diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c
index f68e34ed1f627..7a11b245e9f40 100644
--- a/net/batman-adv/gateway_client.c
+++ b/net/batman-adv/gateway_client.c
@@ -71,7 +71,7 @@ void batadv_gw_node_release(struct kref *ref)
 
 /**
  * batadv_gw_get_selected_gw_node() - Get currently selected gateway
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: selected gateway (with increased refcnt), NULL on errors
  */
@@ -95,7 +95,7 @@ batadv_gw_get_selected_gw_node(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_get_selected_orig() - Get originator of currently selected gateway
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: orig_node of selected gateway (with increased refcnt), NULL on errors
  */
@@ -144,7 +144,7 @@ static void batadv_gw_select(struct batadv_priv *bat_priv,
 
 /**
  * batadv_gw_reselect() - force a gateway reselection
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Set a flag to remind the GW component to perform a new gateway reselection.
  * However this function does not ensure that the current gateway is going to be
@@ -160,7 +160,7 @@ void batadv_gw_reselect(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_check_client_stop() - check if client mode has been switched off
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * This function assumes the caller has checked that the gw state *is actually
  * changing*. This function is not supposed to be called when there is no state
@@ -192,7 +192,7 @@ void batadv_gw_check_client_stop(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_election() - Elect the best gateway
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_gw_election(struct batadv_priv *bat_priv)
 {
@@ -280,7 +280,7 @@ void batadv_gw_election(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_check_election() - Elect orig node as best gateway when eligible
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be checked
  */
 void batadv_gw_check_election(struct batadv_priv *bat_priv,
@@ -314,7 +314,7 @@ void batadv_gw_check_election(struct batadv_priv *bat_priv,
 
 /**
  * batadv_gw_node_add() - add gateway node to list of available gateways
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: originator announcing gateway capabilities
  * @gateway: announced bandwidth information
  *
@@ -361,7 +361,7 @@ static void batadv_gw_node_add(struct batadv_priv *bat_priv,
 
 /**
  * batadv_gw_node_get() - retrieve gateway node from list of available gateways
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: originator announcing gateway capabilities
  *
  * Return: gateway node if found or NULL otherwise.
@@ -391,7 +391,7 @@ struct batadv_gw_node *batadv_gw_node_get(struct batadv_priv *bat_priv,
 /**
  * batadv_gw_node_update() - update list of available gateways with changed
  *  bandwidth information
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: originator announcing gateway capabilities
  * @gateway: announced bandwidth information
  */
@@ -458,7 +458,7 @@ void batadv_gw_node_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_gw_node_delete() - Remove orig_node from gateway list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is currently in process of being removed
  */
 void batadv_gw_node_delete(struct batadv_priv *bat_priv,
@@ -473,8 +473,8 @@ void batadv_gw_node_delete(struct batadv_priv *bat_priv,
 }
 
 /**
- * batadv_gw_node_free() - Free gateway information from soft interface
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_gw_node_free() - Free gateway information from mesh interface
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_gw_node_free(struct batadv_priv *bat_priv)
 {
@@ -501,15 +501,15 @@ void batadv_gw_node_free(struct batadv_priv *bat_priv)
 int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if = NULL;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	int ret;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) {
@@ -528,7 +528,7 @@ int batadv_gw_dump(struct sk_buff *msg, struct netlink_callback *cb)
 
 out:
 	batadv_hardif_put(primary_if);
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	return ret;
 }
@@ -657,7 +657,7 @@ batadv_gw_dhcp_recipient_get(struct sk_buff *skb, unsigned int *header_len,
 /**
  * batadv_gw_out_of_range() - check if the dhcp request destination is the best
  *  gateway
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the outgoing packet
  *
  * Check if the skb is a DHCP request and if it is sent to the current best GW
diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c
index 2dd36ef03c841..315fa90f0c947 100644
--- a/net/batman-adv/gateway_common.c
+++ b/net/batman-adv/gateway_common.c
@@ -20,7 +20,7 @@
 /**
  * batadv_gw_tvlv_container_update() - update the gw tvlv container after
  *  gateway setting change
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv)
 {
@@ -48,7 +48,7 @@ void batadv_gw_tvlv_container_update(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_tvlv_ogm_handler_v1() - process incoming gateway tvlv container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the gateway data
@@ -89,7 +89,7 @@ static void batadv_gw_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 
 /**
  * batadv_gw_init() - initialise the gateway handling internals
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_gw_init(struct batadv_priv *bat_priv)
 {
@@ -105,7 +105,7 @@ void batadv_gw_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_gw_free() - free the gateway handling internals
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_gw_free(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c
index e7e7f14da03c9..f145f96626531 100644
--- a/net/batman-adv/hard-interface.c
+++ b/net/batman-adv/hard-interface.c
@@ -36,9 +36,9 @@
 #include "distributed-arp-table.h"
 #include "gateway_client.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "originator.h"
 #include "send.h"
-#include "soft-interface.h"
 #include "translation-table.h"
 
 /**
@@ -141,7 +141,7 @@ static bool batadv_mutual_parents(const struct net_device *dev1,
  * is important to prevent this new interface from being used to create a new
  * mesh network (this behaviour would lead to a batman-over-batman
  * configuration). This function recursively checks all the fathers of the
- * device passed as argument looking for a batman-adv soft interface.
+ * device passed as argument looking for a batman-adv mesh interface.
  *
  * Return: true if the device is descendant of a batman-adv mesh interface (or
  * if it is a batman-adv interface itself), false otherwise
@@ -155,7 +155,7 @@ static bool batadv_is_on_batman_iface(const struct net_device *net_dev)
 	bool ret;
 
 	/* check if this is a batman-adv mesh interface */
-	if (batadv_softif_is_valid(net_dev))
+	if (batadv_meshif_is_valid(net_dev))
 		return true;
 
 	iflink = dev_get_iflink(net_dev);
@@ -233,10 +233,10 @@ static struct net_device *batadv_get_real_netdevice(struct net_device *netdev)
 	}
 
 	hard_iface = batadv_hardif_get_by_netdev(netdev);
-	if (!hard_iface || !hard_iface->soft_iface)
+	if (!hard_iface || !hard_iface->mesh_iface)
 		goto out;
 
-	net = dev_net(hard_iface->soft_iface);
+	net = dev_net(hard_iface->mesh_iface);
 	real_net = batadv_getlink_net(netdev, net);
 
 	/* iflink to itself, most likely physical device */
@@ -438,13 +438,13 @@ int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing,
 }
 
 static struct batadv_hard_iface *
-batadv_hardif_get_active(const struct net_device *soft_iface)
+batadv_hardif_get_active(const struct net_device *mesh_iface)
 {
 	struct batadv_hard_iface *hard_iface;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != soft_iface)
+		if (hard_iface->mesh_iface != mesh_iface)
 			continue;
 
 		if (hard_iface->if_status == BATADV_IF_ACTIVE &&
@@ -532,9 +532,9 @@ static void batadv_check_known_mac_addr(const struct net_device *net_dev)
 
 /**
  * batadv_hardif_recalc_extra_skbroom() - Recalculate skbuff extra head/tailroom
- * @soft_iface: netdev struct of the mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  */
-static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface)
+static void batadv_hardif_recalc_extra_skbroom(struct net_device *mesh_iface)
 {
 	const struct batadv_hard_iface *hard_iface;
 	unsigned short lower_header_len = ETH_HLEN;
@@ -547,7 +547,7 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface)
 		if (hard_iface->if_status == BATADV_IF_NOT_IN_USE)
 			continue;
 
-		if (hard_iface->soft_iface != soft_iface)
+		if (hard_iface->mesh_iface != mesh_iface)
 			continue;
 
 		lower_header_len = max_t(unsigned short, lower_header_len,
@@ -567,20 +567,20 @@ static void batadv_hardif_recalc_extra_skbroom(struct net_device *soft_iface)
 	/* fragmentation headers don't strip the unicast/... header */
 	needed_headroom += sizeof(struct batadv_frag_packet);
 
-	soft_iface->needed_headroom = needed_headroom;
-	soft_iface->needed_tailroom = lower_tailroom;
+	mesh_iface->needed_headroom = needed_headroom;
+	mesh_iface->needed_tailroom = lower_tailroom;
 }
 
 /**
- * batadv_hardif_min_mtu() - Calculate maximum MTU for soft interface
- * @soft_iface: netdev struct of the soft interface
+ * batadv_hardif_min_mtu() - Calculate maximum MTU for mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  *
- * Return: MTU for the soft-interface (limited by the minimal MTU of all active
+ * Return: MTU for the mesh-interface (limited by the minimal MTU of all active
  *  slave interfaces)
  */
-int batadv_hardif_min_mtu(struct net_device *soft_iface)
+int batadv_hardif_min_mtu(struct net_device *mesh_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	const struct batadv_hard_iface *hard_iface;
 	int min_mtu = INT_MAX;
 
@@ -590,7 +590,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 		    hard_iface->if_status != BATADV_IF_TO_BE_ACTIVATED)
 			continue;
 
-		if (hard_iface->soft_iface != soft_iface)
+		if (hard_iface->mesh_iface != mesh_iface)
 			continue;
 
 		min_mtu = min_t(int, hard_iface->net_dev->mtu, min_mtu);
@@ -616,7 +616,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 	 */
 	atomic_set(&bat_priv->packet_size_max, min_mtu);
 
-	/* the real soft-interface MTU is computed by removing the payload
+	/* the real mesh-interface MTU is computed by removing the payload
 	 * overhead from the maximum amount of bytes that was just computed.
 	 */
 	return min_t(int, min_mtu - batadv_max_header_len(), BATADV_MAX_MTU);
@@ -625,15 +625,15 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)
 /**
  * batadv_update_min_mtu() - Adjusts the MTU if a new interface with a smaller
  *  MTU appeared
- * @soft_iface: netdev struct of the soft interface
+ * @mesh_iface: netdev struct of the mesh interface
  */
-void batadv_update_min_mtu(struct net_device *soft_iface)
+void batadv_update_min_mtu(struct net_device *mesh_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	int limit_mtu;
 	int mtu;
 
-	mtu = batadv_hardif_min_mtu(soft_iface);
+	mtu = batadv_hardif_min_mtu(mesh_iface);
 
 	if (bat_priv->mtu_set_by_user)
 		limit_mtu = bat_priv->mtu_set_by_user;
@@ -641,12 +641,12 @@ void batadv_update_min_mtu(struct net_device *soft_iface)
 		limit_mtu = ETH_DATA_LEN;
 
 	mtu = min(mtu, limit_mtu);
-	dev_set_mtu(soft_iface, mtu);
+	dev_set_mtu(mesh_iface, mtu);
 
 	/* Check if the local translate table should be cleaned up to match a
 	 * new (and smaller) MTU.
 	 */
-	batadv_tt_local_resize_to_mtu(soft_iface);
+	batadv_tt_local_resize_to_mtu(mesh_iface);
 }
 
 static void
@@ -658,7 +658,7 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
 	if (hard_iface->if_status != BATADV_IF_INACTIVE)
 		goto out;
 
-	bat_priv = netdev_priv(hard_iface->soft_iface);
+	bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	bat_priv->algo_ops->iface.update_mac(hard_iface);
 	hard_iface->if_status = BATADV_IF_TO_BE_ACTIVATED;
@@ -670,10 +670,10 @@ batadv_hardif_activate_interface(struct batadv_hard_iface *hard_iface)
 	if (!primary_if)
 		batadv_primary_if_select(bat_priv, hard_iface);
 
-	batadv_info(hard_iface->soft_iface, "Interface activated: %s\n",
+	batadv_info(hard_iface->mesh_iface, "Interface activated: %s\n",
 		    hard_iface->net_dev->name);
 
-	batadv_update_min_mtu(hard_iface->soft_iface);
+	batadv_update_min_mtu(hard_iface->mesh_iface);
 
 	if (bat_priv->algo_ops->iface.activate)
 		bat_priv->algo_ops->iface.activate(hard_iface);
@@ -691,21 +691,21 @@ batadv_hardif_deactivate_interface(struct batadv_hard_iface *hard_iface)
 
 	hard_iface->if_status = BATADV_IF_INACTIVE;
 
-	batadv_info(hard_iface->soft_iface, "Interface deactivated: %s\n",
+	batadv_info(hard_iface->mesh_iface, "Interface deactivated: %s\n",
 		    hard_iface->net_dev->name);
 
-	batadv_update_min_mtu(hard_iface->soft_iface);
+	batadv_update_min_mtu(hard_iface->mesh_iface);
 }
 
 /**
- * batadv_hardif_enable_interface() - Enslave hard interface to soft interface
- * @hard_iface: hard interface to add to soft interface
- * @soft_iface: netdev struct of the mesh interface
+ * batadv_hardif_enable_interface() - Enslave hard interface to mesh interface
+ * @hard_iface: hard interface to add to mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  *
  * Return: 0 on success or negative error number in case of failure
  */
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
-				   struct net_device *soft_iface)
+				   struct net_device *mesh_iface)
 {
 	struct batadv_priv *bat_priv;
 	__be16 ethertype = htons(ETH_P_BATMAN);
@@ -715,7 +715,7 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	int ret;
 
 	hardif_mtu = READ_ONCE(hard_iface->net_dev->mtu);
-	required_mtu = READ_ONCE(soft_iface->mtu) + max_header_len;
+	required_mtu = READ_ONCE(mesh_iface->mtu) + max_header_len;
 
 	if (hardif_mtu < ETH_MIN_MTU + max_header_len)
 		return -EINVAL;
@@ -725,13 +725,13 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 
 	kref_get(&hard_iface->refcount);
 
-	dev_hold(soft_iface);
-	netdev_hold(soft_iface, &hard_iface->softif_dev_tracker, GFP_ATOMIC);
-	hard_iface->soft_iface = soft_iface;
-	bat_priv = netdev_priv(hard_iface->soft_iface);
+	dev_hold(mesh_iface);
+	netdev_hold(mesh_iface, &hard_iface->meshif_dev_tracker, GFP_ATOMIC);
+	hard_iface->mesh_iface = mesh_iface;
+	bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	ret = netdev_master_upper_dev_link(hard_iface->net_dev,
-					   soft_iface, NULL, NULL, NULL);
+					   mesh_iface, NULL, NULL, NULL);
 	if (ret)
 		goto err_dev;
 
@@ -747,19 +747,19 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	hard_iface->batman_adv_ptype.dev = hard_iface->net_dev;
 	dev_add_pack(&hard_iface->batman_adv_ptype);
 
-	batadv_info(hard_iface->soft_iface, "Adding interface: %s\n",
+	batadv_info(hard_iface->mesh_iface, "Adding interface: %s\n",
 		    hard_iface->net_dev->name);
 
 	if (atomic_read(&bat_priv->fragmentation) &&
 	    hardif_mtu < required_mtu)
-		batadv_info(hard_iface->soft_iface,
+		batadv_info(hard_iface->mesh_iface,
 			    "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. Packets going over this interface will be fragmented on layer2 which could impact the performance. Setting the MTU to %i would solve the problem.\n",
 			    hard_iface->net_dev->name, hardif_mtu,
 			    required_mtu);
 
 	if (!atomic_read(&bat_priv->fragmentation) &&
 	    hardif_mtu < required_mtu)
-		batadv_info(hard_iface->soft_iface,
+		batadv_info(hard_iface->mesh_iface,
 			    "The MTU of interface %s is too small (%i) to handle the transport of batman-adv packets. If you experience problems getting traffic through try increasing the MTU to %i.\n",
 			    hard_iface->net_dev->name, hardif_mtu,
 			    required_mtu);
@@ -767,11 +767,11 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	if (batadv_hardif_is_iface_up(hard_iface))
 		batadv_hardif_activate_interface(hard_iface);
 	else
-		batadv_err(hard_iface->soft_iface,
+		batadv_err(hard_iface->mesh_iface,
 			   "Not using interface %s (retrying later): interface not active\n",
 			   hard_iface->net_dev->name);
 
-	batadv_hardif_recalc_extra_skbroom(soft_iface);
+	batadv_hardif_recalc_extra_skbroom(mesh_iface);
 
 	if (bat_priv->algo_ops->iface.enabled)
 		bat_priv->algo_ops->iface.enabled(hard_iface);
@@ -780,17 +780,17 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
 	return 0;
 
 err_upper:
-	netdev_upper_dev_unlink(hard_iface->net_dev, soft_iface);
+	netdev_upper_dev_unlink(hard_iface->net_dev, mesh_iface);
 err_dev:
-	hard_iface->soft_iface = NULL;
-	netdev_put(soft_iface, &hard_iface->softif_dev_tracker);
+	hard_iface->mesh_iface = NULL;
+	netdev_put(mesh_iface, &hard_iface->meshif_dev_tracker);
 	batadv_hardif_put(hard_iface);
 	return ret;
 }
 
 /**
- * batadv_hardif_cnt() - get number of interfaces enslaved to soft interface
- * @soft_iface: soft interface to check
+ * batadv_hardif_cnt() - get number of interfaces enslaved to mesh interface
+ * @mesh_iface: mesh interface to check
  *
  * This function is only using RCU for locking - the result can therefore be
  * off when another function is modifying the list at the same time. The
@@ -798,14 +798,14 @@ int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
  *
  * Return: number of connected/enslaved hard interfaces
  */
-static size_t batadv_hardif_cnt(const struct net_device *soft_iface)
+static size_t batadv_hardif_cnt(const struct net_device *mesh_iface)
 {
 	struct batadv_hard_iface *hard_iface;
 	size_t count = 0;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != soft_iface)
+		if (hard_iface->mesh_iface != mesh_iface)
 			continue;
 
 		count++;
@@ -816,12 +816,12 @@ static size_t batadv_hardif_cnt(const struct net_device *soft_iface)
 }
 
 /**
- * batadv_hardif_disable_interface() - Remove hard interface from soft interface
+ * batadv_hardif_disable_interface() - Remove hard interface from mesh interface
  * @hard_iface: hard interface to be removed
  */
 void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	struct batadv_hard_iface *primary_if = NULL;
 
 	batadv_hardif_deactivate_interface(hard_iface);
@@ -829,7 +829,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 	if (hard_iface->if_status != BATADV_IF_INACTIVE)
 		goto out;
 
-	batadv_info(hard_iface->soft_iface, "Removing interface: %s\n",
+	batadv_info(hard_iface->mesh_iface, "Removing interface: %s\n",
 		    hard_iface->net_dev->name);
 	dev_remove_pack(&hard_iface->batman_adv_ptype);
 	batadv_hardif_put(hard_iface);
@@ -838,7 +838,7 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 	if (hard_iface == primary_if) {
 		struct batadv_hard_iface *new_if;
 
-		new_if = batadv_hardif_get_active(hard_iface->soft_iface);
+		new_if = batadv_hardif_get_active(hard_iface->mesh_iface);
 		batadv_primary_if_select(bat_priv, new_if);
 
 		batadv_hardif_put(new_if);
@@ -850,16 +850,16 @@ void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface)
 	/* delete all references to this hard_iface */
 	batadv_purge_orig_ref(bat_priv);
 	batadv_purge_outstanding_packets(bat_priv, hard_iface);
-	netdev_put(hard_iface->soft_iface, &hard_iface->softif_dev_tracker);
+	netdev_put(hard_iface->mesh_iface, &hard_iface->meshif_dev_tracker);
 
-	netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->soft_iface);
-	batadv_hardif_recalc_extra_skbroom(hard_iface->soft_iface);
+	netdev_upper_dev_unlink(hard_iface->net_dev, hard_iface->mesh_iface);
+	batadv_hardif_recalc_extra_skbroom(hard_iface->mesh_iface);
 
 	/* nobody uses this interface anymore */
-	if (batadv_hardif_cnt(hard_iface->soft_iface) <= 1)
+	if (batadv_hardif_cnt(hard_iface->mesh_iface) <= 1)
 		batadv_gw_check_client_stop(bat_priv);
 
-	hard_iface->soft_iface = NULL;
+	hard_iface->mesh_iface = NULL;
 	batadv_hardif_put(hard_iface);
 
 out:
@@ -883,7 +883,7 @@ batadv_hardif_add_interface(struct net_device *net_dev)
 	netdev_hold(net_dev, &hard_iface->dev_tracker, GFP_ATOMIC);
 	hard_iface->net_dev = net_dev;
 
-	hard_iface->soft_iface = NULL;
+	hard_iface->mesh_iface = NULL;
 	hard_iface->if_status = BATADV_IF_NOT_IN_USE;
 
 	INIT_LIST_HEAD(&hard_iface->list);
@@ -926,13 +926,13 @@ static void batadv_hardif_remove_interface(struct batadv_hard_iface *hard_iface)
 }
 
 /**
- * batadv_hard_if_event_softif() - Handle events for soft interfaces
+ * batadv_hard_if_event_meshif() - Handle events for mesh interfaces
  * @event: NETDEV_* event to handle
  * @net_dev: net_device which generated an event
  *
  * Return: NOTIFY_* result
  */
-static int batadv_hard_if_event_softif(unsigned long event,
+static int batadv_hard_if_event_meshif(unsigned long event,
 				       struct net_device *net_dev)
 {
 	struct batadv_priv *bat_priv;
@@ -940,7 +940,7 @@ static int batadv_hard_if_event_softif(unsigned long event,
 	switch (event) {
 	case NETDEV_REGISTER:
 		bat_priv = netdev_priv(net_dev);
-		batadv_softif_create_vlan(bat_priv, BATADV_NO_FLAGS);
+		batadv_meshif_create_vlan(bat_priv, BATADV_NO_FLAGS);
 		break;
 	}
 
@@ -955,8 +955,8 @@ static int batadv_hard_if_event(struct notifier_block *this,
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_priv *bat_priv;
 
-	if (batadv_softif_is_valid(net_dev))
-		return batadv_hard_if_event_softif(event, net_dev);
+	if (batadv_meshif_is_valid(net_dev))
+		return batadv_hard_if_event_meshif(event, net_dev);
 
 	hard_iface = batadv_hardif_get_by_netdev(net_dev);
 	if (!hard_iface && (event == NETDEV_REGISTER ||
@@ -982,8 +982,8 @@ static int batadv_hard_if_event(struct notifier_block *this,
 		batadv_hardif_remove_interface(hard_iface);
 		break;
 	case NETDEV_CHANGEMTU:
-		if (hard_iface->soft_iface)
-			batadv_update_min_mtu(hard_iface->soft_iface);
+		if (hard_iface->mesh_iface)
+			batadv_update_min_mtu(hard_iface->mesh_iface);
 		break;
 	case NETDEV_CHANGEADDR:
 		if (hard_iface->if_status == BATADV_IF_NOT_IN_USE)
@@ -991,7 +991,7 @@ static int batadv_hard_if_event(struct notifier_block *this,
 
 		batadv_check_known_mac_addr(hard_iface->net_dev);
 
-		bat_priv = netdev_priv(hard_iface->soft_iface);
+		bat_priv = netdev_priv(hard_iface->mesh_iface);
 		bat_priv->algo_ops->iface.update_mac(hard_iface);
 
 		primary_if = batadv_primary_if_get_selected(bat_priv);
diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h
index 64f660dbbe542..262a783647427 100644
--- a/net/batman-adv/hard-interface.h
+++ b/net/batman-adv/hard-interface.h
@@ -23,12 +23,12 @@
 enum batadv_hard_if_state {
 	/**
 	 * @BATADV_IF_NOT_IN_USE: interface is not used as slave interface of a
-	 * batman-adv soft interface
+	 * batman-adv mesh interface
 	 */
 	BATADV_IF_NOT_IN_USE,
 
 	/**
-	 * @BATADV_IF_TO_BE_REMOVED: interface will be removed from soft
+	 * @BATADV_IF_TO_BE_REMOVED: interface will be removed from mesh
 	 * interface
 	 */
 	BATADV_IF_TO_BE_REMOVED,
@@ -74,10 +74,10 @@ bool batadv_is_wifi_hardif(struct batadv_hard_iface *hard_iface);
 struct batadv_hard_iface*
 batadv_hardif_get_by_netdev(const struct net_device *net_dev);
 int batadv_hardif_enable_interface(struct batadv_hard_iface *hard_iface,
-				   struct net_device *soft_iface);
+				   struct net_device *mesh_iface);
 void batadv_hardif_disable_interface(struct batadv_hard_iface *hard_iface);
-int batadv_hardif_min_mtu(struct net_device *soft_iface);
-void batadv_update_min_mtu(struct net_device *soft_iface);
+int batadv_hardif_min_mtu(struct net_device *mesh_iface);
+void batadv_update_min_mtu(struct net_device *mesh_iface);
 void batadv_hardif_release(struct kref *ref);
 int batadv_hardif_no_broadcast(struct batadv_hard_iface *if_outgoing,
 			       u8 *orig_addr, u8 *orig_neigh);
@@ -97,7 +97,7 @@ static inline void batadv_hardif_put(struct batadv_hard_iface *hard_iface)
 
 /**
  * batadv_primary_if_get_selected() - Get reference to primary interface
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: primary interface (with increased refcnt), otherwise NULL
  */
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index 7a93a1e94c40e..c19d07eeb0701 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -13,7 +13,7 @@
 
 /**
  * batadv_debug_log() - Add debug log entry
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @fmt: format string
  *
  * Return: 0 on success or negative error number in case of failure
diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h
index 6717c965f0faf..567afaa8df998 100644
--- a/net/batman-adv/log.h
+++ b/net/batman-adv/log.h
@@ -71,7 +71,7 @@ __printf(2, 3);
 /**
  * _batadv_dbg() - Store debug output with(out) rate limiting
  * @type: type of debug message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ratelimited: whether output should be rate limited
  * @fmt: format string
  * @arg: variable arguments
@@ -97,7 +97,7 @@ static inline void _batadv_dbg(int type __always_unused,
 /**
  * batadv_dbg() - Store debug output without rate limiting
  * @type: type of debug message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @arg: format string and variable arguments
  */
 #define batadv_dbg(type, bat_priv, arg...) \
@@ -106,7 +106,7 @@ static inline void _batadv_dbg(int type __always_unused,
 /**
  * batadv_dbg_ratelimited() - Store debug output with rate limiting
  * @type: type of debug message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @arg: format string and variable arguments
  */
 #define batadv_dbg_ratelimited(type, bat_priv, arg...) \
@@ -114,7 +114,7 @@ static inline void _batadv_dbg(int type __always_unused,
 
 /**
  * batadv_info() - Store message in debug buffer and print it to kmsg buffer
- * @net_dev: the soft interface net device
+ * @net_dev: the mesh interface net device
  * @fmt: format string
  * @arg: variable arguments
  */
@@ -128,7 +128,7 @@ static inline void _batadv_dbg(int type __always_unused,
 
 /**
  * batadv_err() - Store error in debug buffer and print it to kmsg buffer
- * @net_dev: the soft interface net device
+ * @net_dev: the mesh interface net device
  * @fmt: format string
  * @arg: variable arguments
  */
diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c
index 333e947afcce7..a08132888a3d4 100644
--- a/net/batman-adv/main.c
+++ b/net/batman-adv/main.c
@@ -51,13 +51,13 @@
 #include "gateway_common.h"
 #include "hard-interface.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "multicast.h"
 #include "netlink.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "routing.h"
 #include "send.h"
-#include "soft-interface.h"
 #include "tp_meter.h"
 #include "translation-table.h"
 
@@ -143,14 +143,14 @@ static void __exit batadv_exit(void)
 }
 
 /**
- * batadv_mesh_init() - Initialize soft interface
- * @soft_iface: netdev struct of the soft interface
+ * batadv_mesh_init() - Initialize mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  *
  * Return: 0 on success or negative error number in case of failure
  */
-int batadv_mesh_init(struct net_device *soft_iface)
+int batadv_mesh_init(struct net_device *mesh_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	int ret;
 
 	spin_lock_init(&bat_priv->forw_bat_list_lock);
@@ -167,7 +167,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 #endif
 	spin_lock_init(&bat_priv->tvlv.container_list_lock);
 	spin_lock_init(&bat_priv->tvlv.handler_list_lock);
-	spin_lock_init(&bat_priv->softif_vlan_list_lock);
+	spin_lock_init(&bat_priv->meshif_vlan_list_lock);
 	spin_lock_init(&bat_priv->tp_list_lock);
 
 	INIT_HLIST_HEAD(&bat_priv->forw_bat_list);
@@ -186,7 +186,7 @@ int batadv_mesh_init(struct net_device *soft_iface)
 #endif
 	INIT_HLIST_HEAD(&bat_priv->tvlv.container_list);
 	INIT_HLIST_HEAD(&bat_priv->tvlv.handler_list);
-	INIT_HLIST_HEAD(&bat_priv->softif_vlan_list);
+	INIT_HLIST_HEAD(&bat_priv->meshif_vlan_list);
 	INIT_HLIST_HEAD(&bat_priv->tp_list);
 
 	bat_priv->gw.generation = 0;
@@ -253,12 +253,12 @@ int batadv_mesh_init(struct net_device *soft_iface)
 }
 
 /**
- * batadv_mesh_free() - Deinitialize soft interface
- * @soft_iface: netdev struct of the soft interface
+ * batadv_mesh_free() - Deinitialize mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  */
-void batadv_mesh_free(struct net_device *soft_iface)
+void batadv_mesh_free(struct net_device *mesh_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 
 	atomic_set(&bat_priv->mesh_state, BATADV_MESH_DEACTIVATING);
 
@@ -297,7 +297,7 @@ void batadv_mesh_free(struct net_device *soft_iface)
 /**
  * batadv_is_my_mac() - check if the given mac address belongs to any of the
  *  real interfaces in the current mesh
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the address to check
  *
  * Return: 'true' if the mac address was found, false otherwise.
@@ -312,7 +312,7 @@ bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr)
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (batadv_compare_eth(hard_iface->net_dev->dev_addr, addr)) {
@@ -457,10 +457,10 @@ int batadv_batman_skb_recv(struct sk_buff *skb, struct net_device *dev,
 	if (unlikely(skb->mac_len != ETH_HLEN || !skb_mac_header(skb)))
 		goto err_free;
 
-	if (!hard_iface->soft_iface)
+	if (!hard_iface->mesh_iface)
 		goto err_free;
 
-	bat_priv = netdev_priv(hard_iface->soft_iface);
+	bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE)
 		goto err_free;
@@ -651,7 +651,7 @@ unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len)
 
 /**
  * batadv_vlan_ap_isola_get() - return AP isolation status for the given vlan
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the VLAN identifier for which the AP isolation attributed as to be
  *  looked up
  *
@@ -661,15 +661,15 @@ unsigned short batadv_get_vid(struct sk_buff *skb, size_t header_len)
 bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
 {
 	bool ap_isolation_enabled = false;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
 	/* if the AP isolation is requested on a VLAN, then check for its
 	 * setting in the proper VLAN private data structure
 	 */
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (vlan) {
 		ap_isolation_enabled = atomic_read(&vlan->ap_isolation);
-		batadv_softif_vlan_put(vlan);
+		batadv_meshif_vlan_put(vlan);
 	}
 
 	return ap_isolation_enabled;
@@ -677,7 +677,7 @@ bool batadv_vlan_ap_isola_get(struct batadv_priv *bat_priv, unsigned short vid)
 
 /**
  * batadv_throw_uevent() - Send an uevent with batman-adv specific env data
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: subsystem type of event. Stored in uevent's BATTYPE
  * @action: action type of event. Stored in uevent's BATACTION
  * @data: string with additional information to the event (ignored for
@@ -692,7 +692,7 @@ int batadv_throw_uevent(struct batadv_priv *bat_priv, enum batadv_uev_type type,
 	struct kobject *bat_kobj;
 	char *uevent_env[4] = { NULL, NULL, NULL, NULL };
 
-	bat_kobj = &bat_priv->soft_iface->dev.kobj;
+	bat_kobj = &bat_priv->mesh_iface->dev.kobj;
 
 	uevent_env[0] = kasprintf(GFP_ATOMIC,
 				  "%s%s", BATADV_UEV_TYPE_VAR,
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 4ecc304eaddd7..5adefdfc69bcd 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -131,10 +131,10 @@
 #define BATADV_TP_MAX_NUM 5
 
 /**
- * enum batadv_mesh_state - State of a soft interface
+ * enum batadv_mesh_state - State of a mesh interface
  */
 enum batadv_mesh_state {
-	/** @BATADV_MESH_INACTIVE: soft interface is not yet running */
+	/** @BATADV_MESH_INACTIVE: mesh interface is not yet running */
 	BATADV_MESH_INACTIVE,
 
 	/** @BATADV_MESH_ACTIVE: interface is up and running */
@@ -240,8 +240,8 @@ extern unsigned int batadv_hardif_generation;
 extern unsigned char batadv_broadcast_addr[];
 extern struct workqueue_struct *batadv_event_workqueue;
 
-int batadv_mesh_init(struct net_device *soft_iface);
-void batadv_mesh_free(struct net_device *soft_iface);
+int batadv_mesh_init(struct net_device *mesh_iface);
+void batadv_mesh_free(struct net_device *mesh_iface);
 bool batadv_is_my_mac(struct batadv_priv *bat_priv, const u8 *addr);
 int batadv_max_header_len(void);
 void batadv_skb_set_priority(struct sk_buff *skb, int offset);
@@ -347,8 +347,8 @@ static inline bool batadv_has_timed_out(unsigned long timestamp,
 #define batadv_seq_after(x, y) batadv_seq_before(y, x)
 
 /**
- * batadv_add_counter() - Add to per cpu statistics counter of soft interface
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_add_counter() - Add to per cpu statistics counter of mesh interface
+ * @bat_priv: the bat priv with all the mesh interface information
  * @idx: counter index which should be modified
  * @count: value to increase counter by
  *
@@ -361,8 +361,8 @@ static inline void batadv_add_counter(struct batadv_priv *bat_priv, size_t idx,
 }
 
 /**
- * batadv_inc_counter() - Increase per cpu statistics counter of soft interface
- * @b: the bat priv with all the soft interface information
+ * batadv_inc_counter() - Increase per cpu statistics counter of mesh interface
+ * @b: the bat priv with all the mesh interface information
  * @i: counter index which should be modified
  */
 #define batadv_inc_counter(b, i) batadv_add_counter(b, i, 1)
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/mesh-interface.c
similarity index 84%
rename from net/batman-adv/soft-interface.c
rename to net/batman-adv/mesh-interface.c
index b1127e6e8900a..c0a2a2a8fbb53 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/mesh-interface.c
@@ -4,7 +4,7 @@
  * Marek Lindner, Simon Wunderlich
  */
 
-#include "soft-interface.h"
+#include "mesh-interface.h"
 #include "main.h"
 
 #include <linux/atomic.h>
@@ -91,7 +91,7 @@ static int batadv_interface_release(struct net_device *dev)
 
 /**
  * batadv_sum_counter() - Sum the cpu-local counters for index 'idx'
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @idx: index of counter to sum up
  *
  * Return: sum of all cpu-local counters
@@ -125,7 +125,7 @@ static struct net_device_stats *batadv_interface_stats(struct net_device *dev)
 static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	struct sockaddr *addr = p;
 	u8 old_addr[ETH_ALEN];
 
@@ -140,7 +140,7 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)
 		return 0;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+	hlist_for_each_entry_rcu(vlan, &bat_priv->meshif_vlan_list, list) {
 		batadv_tt_local_remove(bat_priv, old_addr, vlan->vid,
 				       "mac address changed", false);
 		batadv_tt_local_add(dev, addr->sa_data, vlan->vid,
@@ -170,7 +170,7 @@ static int batadv_interface_change_mtu(struct net_device *dev, int new_mtu)
  * @dev: registered network device to modify
  *
  * We do not actually need to set any rx filters for the virtual batman
- * soft interface. However a dummy handler enables a user to set static
+ * mesh interface. However a dummy handler enables a user to set static
  * multicast listeners for instance.
  */
 static void batadv_interface_set_rx_mode(struct net_device *dev)
@@ -178,10 +178,10 @@ static void batadv_interface_set_rx_mode(struct net_device *dev)
 }
 
 static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
-				       struct net_device *soft_iface)
+				       struct net_device *mesh_iface)
 {
 	struct ethhdr *ethhdr;
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_bcast_packet *bcast_packet;
 	static const u8 stp_addr[ETH_ALEN] = {0x01, 0x80, 0xC2, 0x00,
@@ -209,7 +209,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 	/* reset control block to avoid left overs from previous users */
 	memset(skb->cb, 0, sizeof(struct batadv_skb_cb));
 
-	netif_trans_update(soft_iface);
+	netif_trans_update(mesh_iface);
 	vid = batadv_get_vid(skb, 0);
 
 	skb_reset_mac_header(skb);
@@ -246,7 +246,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 	/* Register the client MAC in the transtable */
 	if (!is_multicast_ether_addr(ethhdr->h_source) &&
 	    !batadv_bla_is_loopdetect_mac(ethhdr->h_source)) {
-		client_added = batadv_tt_local_add(soft_iface, ethhdr->h_source,
+		client_added = batadv_tt_local_add(mesh_iface, ethhdr->h_source,
 						   vid, skb->skb_iif,
 						   skb->mark);
 		if (!client_added)
@@ -397,12 +397,12 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
 
 /**
  * batadv_interface_rx() - receive ethernet frame on local batman-adv interface
- * @soft_iface: local interface which will receive the ethernet frame
- * @skb: ethernet frame for @soft_iface
+ * @mesh_iface: local interface which will receive the ethernet frame
+ * @skb: ethernet frame for @mesh_iface
  * @hdr_size: size of already parsed batman-adv header
  * @orig_node: originator from which the batman-adv packet was sent
  *
- * Sends an ethernet frame to the receive path of the local @soft_iface.
+ * Sends an ethernet frame to the receive path of the local @mesh_iface.
  * skb->data has still point to the batman-adv header with the size @hdr_size.
  * The caller has to have parsed this header already and made sure that at least
  * @hdr_size bytes are still available for pull in @skb.
@@ -412,12 +412,12 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb,
  * unicast packets will be dropped directly when it was sent between two
  * isolated clients.
  */
-void batadv_interface_rx(struct net_device *soft_iface,
+void batadv_interface_rx(struct net_device *mesh_iface,
 			 struct sk_buff *skb, int hdr_size,
 			 struct batadv_orig_node *orig_node)
 {
 	struct batadv_bcast_packet *batadv_bcast_packet;
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	struct vlan_ethhdr *vhdr;
 	struct ethhdr *ethhdr;
 	unsigned short vid;
@@ -457,7 +457,7 @@ void batadv_interface_rx(struct net_device *soft_iface,
 	}
 
 	/* skb->dev & skb->pkt_type are set here */
-	skb->protocol = eth_type_trans(skb, soft_iface);
+	skb->protocol = eth_type_trans(skb, mesh_iface);
 	skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 
 	batadv_inc_counter(bat_priv, BATADV_CNT_RX);
@@ -502,38 +502,38 @@ void batadv_interface_rx(struct net_device *soft_iface,
 }
 
 /**
- * batadv_softif_vlan_release() - release vlan from lists and queue for free
+ * batadv_meshif_vlan_release() - release vlan from lists and queue for free
  *  after rcu grace period
  * @ref: kref pointer of the vlan object
  */
-void batadv_softif_vlan_release(struct kref *ref)
+void batadv_meshif_vlan_release(struct kref *ref)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
-	vlan = container_of(ref, struct batadv_softif_vlan, refcount);
+	vlan = container_of(ref, struct batadv_meshif_vlan, refcount);
 
-	spin_lock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+	spin_lock_bh(&vlan->bat_priv->meshif_vlan_list_lock);
 	hlist_del_rcu(&vlan->list);
-	spin_unlock_bh(&vlan->bat_priv->softif_vlan_list_lock);
+	spin_unlock_bh(&vlan->bat_priv->meshif_vlan_list_lock);
 
 	kfree_rcu(vlan, rcu);
 }
 
 /**
- * batadv_softif_vlan_get() - get the vlan object for a specific vid
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_meshif_vlan_get() - get the vlan object for a specific vid
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the identifier of the vlan object to retrieve
  *
  * Return: the private data of the vlan matching the vid passed as argument or
  * NULL otherwise. The refcounter of the returned object is incremented by 1.
  */
-struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv,
+struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv,
 						  unsigned short vid)
 {
-	struct batadv_softif_vlan *vlan_tmp, *vlan = NULL;
+	struct batadv_meshif_vlan *vlan_tmp, *vlan = NULL;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(vlan_tmp, &bat_priv->softif_vlan_list, list) {
+	hlist_for_each_entry_rcu(vlan_tmp, &bat_priv->meshif_vlan_list, list) {
 		if (vlan_tmp->vid != vid)
 			continue;
 
@@ -549,28 +549,28 @@ struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv,
 }
 
 /**
- * batadv_softif_create_vlan() - allocate the needed resources for a new vlan
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_meshif_create_vlan() - allocate the needed resources for a new vlan
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the VLAN identifier
  *
  * Return: 0 on success, a negative error otherwise.
  */
-int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
+int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
+	spin_lock_bh(&bat_priv->meshif_vlan_list_lock);
 
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (vlan) {
-		batadv_softif_vlan_put(vlan);
-		spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+		batadv_meshif_vlan_put(vlan);
+		spin_unlock_bh(&bat_priv->meshif_vlan_list_lock);
 		return -EEXIST;
 	}
 
 	vlan = kzalloc(sizeof(*vlan), GFP_ATOMIC);
 	if (!vlan) {
-		spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+		spin_unlock_bh(&bat_priv->meshif_vlan_list_lock);
 		return -ENOMEM;
 	}
 
@@ -581,37 +581,37 @@ int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid)
 	atomic_set(&vlan->ap_isolation, 0);
 
 	kref_get(&vlan->refcount);
-	hlist_add_head_rcu(&vlan->list, &bat_priv->softif_vlan_list);
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+	hlist_add_head_rcu(&vlan->list, &bat_priv->meshif_vlan_list);
+	spin_unlock_bh(&bat_priv->meshif_vlan_list_lock);
 
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag
 	 */
-	batadv_tt_local_add(bat_priv->soft_iface,
-			    bat_priv->soft_iface->dev_addr, vid,
+	batadv_tt_local_add(bat_priv->mesh_iface,
+			    bat_priv->mesh_iface->dev_addr, vid,
 			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
 
-	/* don't return reference to new softif_vlan */
-	batadv_softif_vlan_put(vlan);
+	/* don't return reference to new meshif_vlan */
+	batadv_meshif_vlan_put(vlan);
 
 	return 0;
 }
 
 /**
- * batadv_softif_destroy_vlan() - remove and destroy a softif_vlan object
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_meshif_destroy_vlan() - remove and destroy a meshif_vlan object
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vlan: the object to remove
  */
-static void batadv_softif_destroy_vlan(struct batadv_priv *bat_priv,
-				       struct batadv_softif_vlan *vlan)
+static void batadv_meshif_destroy_vlan(struct batadv_priv *bat_priv,
+				       struct batadv_meshif_vlan *vlan)
 {
 	/* explicitly remove the associated TT local entry because it is marked
 	 * with the NOPURGE flag
 	 */
-	batadv_tt_local_remove(bat_priv, bat_priv->soft_iface->dev_addr,
+	batadv_tt_local_remove(bat_priv, bat_priv->mesh_iface->dev_addr,
 			       vlan->vid, "vlan interface destroyed", false);
 
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 }
 
 /**
@@ -629,7 +629,7 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 				    unsigned short vid)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
 	/* only 802.1Q vlans are supported.
 	 * batman-adv does not know how to handle other types
@@ -648,21 +648,21 @@ static int batadv_interface_add_vid(struct net_device *dev, __be16 proto,
 	vid |= BATADV_VLAN_HAS_TAG;
 
 	/* if a new vlan is getting created and it already exists, it means that
-	 * it was not deleted yet. batadv_softif_vlan_get() increases the
+	 * it was not deleted yet. batadv_meshif_vlan_get() increases the
 	 * refcount in order to revive the object.
 	 *
 	 * if it does not exist then create it.
 	 */
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (!vlan)
-		return batadv_softif_create_vlan(bat_priv, vid);
+		return batadv_meshif_create_vlan(bat_priv, vid);
 
 	/* add a new TT local entry. This one will be marked with the NOPURGE
 	 * flag. This must be added again, even if the vlan object already
 	 * exists, because the entry was deleted by kill_vid()
 	 */
-	batadv_tt_local_add(bat_priv->soft_iface,
-			    bat_priv->soft_iface->dev_addr, vid,
+	batadv_tt_local_add(bat_priv->mesh_iface,
+			    bat_priv->mesh_iface->dev_addr, vid,
 			    BATADV_NULL_IFINDEX, BATADV_NO_MARK);
 
 	return 0;
@@ -684,7 +684,7 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
 				     unsigned short vid)
 {
 	struct batadv_priv *bat_priv = netdev_priv(dev);
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
 	/* only 802.1Q vlans are supported. batman-adv does not know how to
 	 * handle other types
@@ -693,19 +693,19 @@ static int batadv_interface_kill_vid(struct net_device *dev, __be16 proto,
 		return -EINVAL;
 
 	/* "priority tag" frames are handled like "untagged" frames
-	 * and no softif_vlan needs to be destroyed
+	 * and no meshif_vlan needs to be destroyed
 	 */
 	if (vid == 0)
 		return 0;
 
-	vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG);
 	if (!vlan)
 		return -ENOENT;
 
-	batadv_softif_destroy_vlan(bat_priv, vlan);
+	batadv_meshif_destroy_vlan(bat_priv, vlan);
 
 	/* finally free the vlan object */
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 
 	return 0;
 }
@@ -741,12 +741,12 @@ static void batadv_set_lockdep_class(struct net_device *dev)
 }
 
 /**
- * batadv_softif_init_late() - late stage initialization of soft interface
+ * batadv_meshif_init_late() - late stage initialization of mesh interface
  * @dev: registered network device to modify
  *
  * Return: error code on failures
  */
-static int batadv_softif_init_late(struct net_device *dev)
+static int batadv_meshif_init_late(struct net_device *dev)
 {
 	struct batadv_priv *bat_priv;
 	u32 random_seqno;
@@ -756,7 +756,7 @@ static int batadv_softif_init_late(struct net_device *dev)
 	batadv_set_lockdep_class(dev);
 
 	bat_priv = netdev_priv(dev);
-	bat_priv->soft_iface = dev;
+	bat_priv->mesh_iface = dev;
 
 	/* batadv_interface_stats() needs to be available as soon as
 	 * register_netdevice() has been called
@@ -837,14 +837,14 @@ static int batadv_softif_init_late(struct net_device *dev)
 }
 
 /**
- * batadv_softif_slave_add() - Add a slave interface to a batadv_soft_interface
- * @dev: batadv_soft_interface used as master interface
+ * batadv_meshif_slave_add() - Add a slave interface to a batadv_mesh_interface
+ * @dev: batadv_mesh_interface used as master interface
  * @slave_dev: net_device which should become the slave interface
  * @extack: extended ACK report struct
  *
  * Return: 0 if successful or error otherwise.
  */
-static int batadv_softif_slave_add(struct net_device *dev,
+static int batadv_meshif_slave_add(struct net_device *dev,
 				   struct net_device *slave_dev,
 				   struct netlink_ext_ack *extack)
 {
@@ -852,7 +852,7 @@ static int batadv_softif_slave_add(struct net_device *dev,
 	int ret = -EINVAL;
 
 	hard_iface = batadv_hardif_get_by_netdev(slave_dev);
-	if (!hard_iface || hard_iface->soft_iface)
+	if (!hard_iface || hard_iface->mesh_iface)
 		goto out;
 
 	ret = batadv_hardif_enable_interface(hard_iface, dev);
@@ -863,13 +863,13 @@ static int batadv_softif_slave_add(struct net_device *dev,
 }
 
 /**
- * batadv_softif_slave_del() - Delete a slave iface from a batadv_soft_interface
- * @dev: batadv_soft_interface used as master interface
+ * batadv_meshif_slave_del() - Delete a slave iface from a batadv_mesh_interface
+ * @dev: batadv_mesh_interface used as master interface
  * @slave_dev: net_device which should be removed from the master interface
  *
  * Return: 0 if successful or error otherwise.
  */
-static int batadv_softif_slave_del(struct net_device *dev,
+static int batadv_meshif_slave_del(struct net_device *dev,
 				   struct net_device *slave_dev)
 {
 	struct batadv_hard_iface *hard_iface;
@@ -877,7 +877,7 @@ static int batadv_softif_slave_del(struct net_device *dev,
 
 	hard_iface = batadv_hardif_get_by_netdev(slave_dev);
 
-	if (!hard_iface || hard_iface->soft_iface != dev)
+	if (!hard_iface || hard_iface->mesh_iface != dev)
 		goto out;
 
 	batadv_hardif_disable_interface(hard_iface);
@@ -889,7 +889,7 @@ static int batadv_softif_slave_del(struct net_device *dev,
 }
 
 static const struct net_device_ops batadv_netdev_ops = {
-	.ndo_init = batadv_softif_init_late,
+	.ndo_init = batadv_meshif_init_late,
 	.ndo_open = batadv_interface_open,
 	.ndo_stop = batadv_interface_release,
 	.ndo_get_stats = batadv_interface_stats,
@@ -900,8 +900,8 @@ static const struct net_device_ops batadv_netdev_ops = {
 	.ndo_set_rx_mode = batadv_interface_set_rx_mode,
 	.ndo_start_xmit = batadv_interface_tx,
 	.ndo_validate_addr = eth_validate_addr,
-	.ndo_add_slave = batadv_softif_slave_add,
-	.ndo_del_slave = batadv_softif_slave_del,
+	.ndo_add_slave = batadv_meshif_slave_add,
+	.ndo_del_slave = batadv_meshif_slave_del,
 };
 
 static void batadv_get_drvinfo(struct net_device *dev,
@@ -1009,10 +1009,10 @@ static const struct ethtool_ops batadv_ethtool_ops = {
 };
 
 /**
- * batadv_softif_free() - Deconstructor of batadv_soft_interface
+ * batadv_meshif_free() - Deconstructor of batadv_mesh_interface
  * @dev: Device to cleanup and remove
  */
-static void batadv_softif_free(struct net_device *dev)
+static void batadv_meshif_free(struct net_device *dev)
 {
 	batadv_mesh_free(dev);
 
@@ -1024,16 +1024,16 @@ static void batadv_softif_free(struct net_device *dev)
 }
 
 /**
- * batadv_softif_init_early() - early stage initialization of soft interface
+ * batadv_meshif_init_early() - early stage initialization of mesh interface
  * @dev: registered network device to modify
  */
-static void batadv_softif_init_early(struct net_device *dev)
+static void batadv_meshif_init_early(struct net_device *dev)
 {
 	ether_setup(dev);
 
 	dev->netdev_ops = &batadv_netdev_ops;
 	dev->needs_free_netdev = true;
-	dev->priv_destructor = batadv_softif_free;
+	dev->priv_destructor = batadv_meshif_free;
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->lltx = true;
@@ -1052,14 +1052,14 @@ static void batadv_softif_init_early(struct net_device *dev)
 }
 
 /**
- * batadv_softif_validate() - validate configuration of new batadv link
+ * batadv_meshif_validate() - validate configuration of new batadv link
  * @tb: IFLA_INFO_DATA netlink attributes
  * @data: enum batadv_ifla_attrs attributes
  * @extack: extended ACK report struct
  *
  * Return: 0 if successful or error otherwise.
  */
-static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[],
+static int batadv_meshif_validate(struct nlattr *tb[], struct nlattr *data[],
 				  struct netlink_ext_ack *extack)
 {
 	struct batadv_algo_ops *algo_ops;
@@ -1077,14 +1077,14 @@ static int batadv_softif_validate(struct nlattr *tb[], struct nlattr *data[],
 }
 
 /**
- * batadv_softif_newlink() - pre-initialize and register new batadv link
+ * batadv_meshif_newlink() - pre-initialize and register new batadv link
  * @dev: network device to register
  * @params: rtnl newlink parameters
  * @extack: extended ACK report struct
  *
  * Return: 0 if successful or error otherwise.
  */
-static int batadv_softif_newlink(struct net_device *dev,
+static int batadv_meshif_newlink(struct net_device *dev,
 				 struct rtnl_newlink_params *params,
 				 struct netlink_ext_ack *extack)
 {
@@ -1104,40 +1104,40 @@ static int batadv_softif_newlink(struct net_device *dev,
 }
 
 /**
- * batadv_softif_destroy_netlink() - deletion of batadv_soft_interface via
+ * batadv_meshif_destroy_netlink() - deletion of batadv_mesh_interface via
  *  netlink
- * @soft_iface: the to-be-removed batman-adv interface
+ * @mesh_iface: the to-be-removed batman-adv interface
  * @head: list pointer
  */
-static void batadv_softif_destroy_netlink(struct net_device *soft_iface,
+static void batadv_meshif_destroy_netlink(struct net_device *mesh_iface,
 					  struct list_head *head)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	struct batadv_hard_iface *hard_iface;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
 	list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface == soft_iface)
+		if (hard_iface->mesh_iface == mesh_iface)
 			batadv_hardif_disable_interface(hard_iface);
 	}
 
 	/* destroy the "untagged" VLAN */
-	vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+	vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS);
 	if (vlan) {
-		batadv_softif_destroy_vlan(bat_priv, vlan);
-		batadv_softif_vlan_put(vlan);
+		batadv_meshif_destroy_vlan(bat_priv, vlan);
+		batadv_meshif_vlan_put(vlan);
 	}
 
-	unregister_netdevice_queue(soft_iface, head);
+	unregister_netdevice_queue(mesh_iface, head);
 }
 
 /**
- * batadv_softif_is_valid() - Check whether device is a batadv soft interface
+ * batadv_meshif_is_valid() - Check whether device is a batadv mesh interface
  * @net_dev: device which should be checked
  *
  * Return: true when net_dev is a batman-adv interface, false otherwise
  */
-bool batadv_softif_is_valid(const struct net_device *net_dev)
+bool batadv_meshif_is_valid(const struct net_device *net_dev)
 {
 	if (net_dev->netdev_ops->ndo_start_xmit == batadv_interface_tx)
 		return true;
@@ -1152,10 +1152,10 @@ static const struct nla_policy batadv_ifla_policy[IFLA_BATADV_MAX + 1] = {
 struct rtnl_link_ops batadv_link_ops __read_mostly = {
 	.kind		= "batadv",
 	.priv_size	= sizeof(struct batadv_priv),
-	.setup		= batadv_softif_init_early,
+	.setup		= batadv_meshif_init_early,
 	.maxtype	= IFLA_BATADV_MAX,
 	.policy		= batadv_ifla_policy,
-	.validate	= batadv_softif_validate,
-	.newlink	= batadv_softif_newlink,
-	.dellink	= batadv_softif_destroy_netlink,
+	.validate	= batadv_meshif_validate,
+	.newlink	= batadv_meshif_newlink,
+	.dellink	= batadv_meshif_destroy_netlink,
 };
diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/mesh-interface.h
similarity index 50%
rename from net/batman-adv/soft-interface.h
rename to net/batman-adv/mesh-interface.h
index 9f2003f1a4972..7ba055b2bc269 100644
--- a/net/batman-adv/soft-interface.h
+++ b/net/batman-adv/mesh-interface.h
@@ -4,8 +4,8 @@
  * Marek Lindner
  */
 
-#ifndef _NET_BATMAN_ADV_SOFT_INTERFACE_H_
-#define _NET_BATMAN_ADV_SOFT_INTERFACE_H_
+#ifndef _NET_BATMAN_ADV_MESH_INTERFACE_H_
+#define _NET_BATMAN_ADV_MESH_INTERFACE_H_
 
 #include "main.h"
 
@@ -16,27 +16,27 @@
 #include <net/rtnetlink.h>
 
 int batadv_skb_head_push(struct sk_buff *skb, unsigned int len);
-void batadv_interface_rx(struct net_device *soft_iface,
+void batadv_interface_rx(struct net_device *mesh_iface,
 			 struct sk_buff *skb, int hdr_size,
 			 struct batadv_orig_node *orig_node);
-bool batadv_softif_is_valid(const struct net_device *net_dev);
+bool batadv_meshif_is_valid(const struct net_device *net_dev);
 extern struct rtnl_link_ops batadv_link_ops;
-int batadv_softif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid);
-void batadv_softif_vlan_release(struct kref *ref);
-struct batadv_softif_vlan *batadv_softif_vlan_get(struct batadv_priv *bat_priv,
+int batadv_meshif_create_vlan(struct batadv_priv *bat_priv, unsigned short vid);
+void batadv_meshif_vlan_release(struct kref *ref);
+struct batadv_meshif_vlan *batadv_meshif_vlan_get(struct batadv_priv *bat_priv,
 						  unsigned short vid);
 
 /**
- * batadv_softif_vlan_put() - decrease the vlan object refcounter and
+ * batadv_meshif_vlan_put() - decrease the vlan object refcounter and
  *  possibly release it
  * @vlan: the vlan object to release
  */
-static inline void batadv_softif_vlan_put(struct batadv_softif_vlan *vlan)
+static inline void batadv_meshif_vlan_put(struct batadv_meshif_vlan *vlan)
 {
 	if (!vlan)
 		return;
 
-	kref_put(&vlan->refcount, batadv_softif_vlan_release);
+	kref_put(&vlan->refcount, batadv_meshif_vlan_release);
 }
 
-#endif /* _NET_BATMAN_ADV_SOFT_INTERFACE_H_ */
+#endif /* _NET_BATMAN_ADV_MESH_INTERFACE_H_ */
diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c
index d95c418484fa2..5786680aff30c 100644
--- a/net/batman-adv/multicast.c
+++ b/net/batman-adv/multicast.c
@@ -63,7 +63,7 @@ static void batadv_mcast_mla_update(struct work_struct *work);
 
 /**
  * batadv_mcast_start_timer() - schedule the multicast periodic worker
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_mcast_start_timer(struct batadv_priv *bat_priv)
 {
@@ -72,18 +72,18 @@ static void batadv_mcast_start_timer(struct batadv_priv *bat_priv)
 }
 
 /**
- * batadv_mcast_get_bridge() - get the bridge on top of the softif if it exists
- * @soft_iface: netdev struct of the mesh interface
+ * batadv_mcast_get_bridge() - get the bridge on top of the meshif if it exists
+ * @mesh_iface: netdev struct of the mesh interface
  *
- * If the given soft interface has a bridge on top then the refcount
+ * If the given mesh interface has a bridge on top then the refcount
  * of the according net device is increased.
  *
  * Return: NULL if no such bridge exists. Otherwise the net device of the
  * bridge.
  */
-static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
+static struct net_device *batadv_mcast_get_bridge(struct net_device *mesh_iface)
 {
-	struct net_device *upper = soft_iface;
+	struct net_device *upper = mesh_iface;
 
 	rcu_read_lock();
 	do {
@@ -97,7 +97,7 @@ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
 }
 
 /**
- * batadv_mcast_mla_rtr_flags_softif_get_ipv4() - get mcast router flags from
+ * batadv_mcast_mla_rtr_flags_meshif_get_ipv4() - get mcast router flags from
  *  node for IPv4
  * @dev: the interface to check
  *
@@ -107,7 +107,7 @@ static struct net_device *batadv_mcast_get_bridge(struct net_device *soft_iface)
  *
  * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR4 otherwise.
  */
-static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev)
+static u8 batadv_mcast_mla_rtr_flags_meshif_get_ipv4(struct net_device *dev)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
 
@@ -118,7 +118,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev)
 }
 
 /**
- * batadv_mcast_mla_rtr_flags_softif_get_ipv6() - get mcast router flags from
+ * batadv_mcast_mla_rtr_flags_meshif_get_ipv6() - get mcast router flags from
  *  node for IPv6
  * @dev: the interface to check
  *
@@ -129,7 +129,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv4(struct net_device *dev)
  * Return: BATADV_NO_FLAGS if present, BATADV_MCAST_WANT_NO_RTR6 otherwise.
  */
 #if IS_ENABLED(CONFIG_IPV6_MROUTE)
-static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
+static u8 batadv_mcast_mla_rtr_flags_meshif_get_ipv6(struct net_device *dev)
 {
 	struct inet6_dev *in6_dev = __in6_dev_get(dev);
 
@@ -140,16 +140,16 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
 }
 #else
 static inline u8
-batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
+batadv_mcast_mla_rtr_flags_meshif_get_ipv6(struct net_device *dev)
 {
 	return BATADV_MCAST_WANT_NO_RTR6;
 }
 #endif
 
 /**
- * batadv_mcast_mla_rtr_flags_softif_get() - get mcast router flags from node
- * @bat_priv: the bat priv with all the soft interface information
- * @bridge: bridge interface on top of the soft_iface if present,
+ * batadv_mcast_mla_rtr_flags_meshif_get() - get mcast router flags from node
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @bridge: bridge interface on top of the mesh_iface if present,
  *  otherwise pass NULL
  *
  * Checks the presence of IPv4 and IPv6 multicast routers on this
@@ -161,16 +161,16 @@ batadv_mcast_mla_rtr_flags_softif_get_ipv6(struct net_device *dev)
  *	BATADV_MCAST_WANT_NO_RTR6: No IPv6 multicast router is present
  *	The former two OR'd: no multicast router is present
  */
-static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv,
+static u8 batadv_mcast_mla_rtr_flags_meshif_get(struct batadv_priv *bat_priv,
 						struct net_device *bridge)
 {
-	struct net_device *dev = bridge ? bridge : bat_priv->soft_iface;
+	struct net_device *dev = bridge ? bridge : bat_priv->mesh_iface;
 	u8 flags = BATADV_NO_FLAGS;
 
 	rcu_read_lock();
 
-	flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv4(dev);
-	flags |= batadv_mcast_mla_rtr_flags_softif_get_ipv6(dev);
+	flags |= batadv_mcast_mla_rtr_flags_meshif_get_ipv4(dev);
+	flags |= batadv_mcast_mla_rtr_flags_meshif_get_ipv6(dev);
 
 	rcu_read_unlock();
 
@@ -179,8 +179,8 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_mla_rtr_flags_bridge_get() - get mcast router flags from bridge
- * @bat_priv: the bat priv with all the soft interface information
- * @bridge: bridge interface on top of the soft_iface if present,
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @bridge: bridge interface on top of the mesh_iface if present,
  *  otherwise pass NULL
  *
  * Checks the presence of IPv4 and IPv6 multicast routers behind a bridge.
@@ -194,7 +194,7 @@ static u8 batadv_mcast_mla_rtr_flags_softif_get(struct batadv_priv *bat_priv,
 static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 						struct net_device *bridge)
 {
-	struct net_device *dev = bat_priv->soft_iface;
+	struct net_device *dev = bat_priv->mesh_iface;
 	u8 flags = BATADV_NO_FLAGS;
 
 	if (!bridge)
@@ -210,8 +210,8 @@ static u8 batadv_mcast_mla_rtr_flags_bridge_get(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_mla_rtr_flags_get() - get multicast router flags
- * @bat_priv: the bat priv with all the soft interface information
- * @bridge: bridge interface on top of the soft_iface if present,
+ * @bat_priv: the bat priv with all the mesh interface information
+ * @bridge: bridge interface on top of the mesh_iface if present,
  *  otherwise pass NULL
  *
  * Checks the presence of IPv4 and IPv6 multicast routers on this
@@ -228,7 +228,7 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv,
 {
 	u8 flags = BATADV_MCAST_WANT_NO_RTR4 | BATADV_MCAST_WANT_NO_RTR6;
 
-	flags &= batadv_mcast_mla_rtr_flags_softif_get(bat_priv, bridge);
+	flags &= batadv_mcast_mla_rtr_flags_meshif_get(bat_priv, bridge);
 	flags &= batadv_mcast_mla_rtr_flags_bridge_get(bat_priv, bridge);
 
 	return flags;
@@ -236,7 +236,7 @@ static u8 batadv_mcast_mla_rtr_flags_get(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_mla_forw_flags_get() - get multicast forwarding flags
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Checks if all active hard interfaces have an MTU larger or equal to 1280
  * bytes (IPv6 minimum MTU).
@@ -252,7 +252,7 @@ static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv)
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (hard_iface->net_dev->mtu < IPV6_MIN_MTU) {
@@ -267,7 +267,7 @@ static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv)
 
 /**
  * batadv_mcast_mla_flags_get() - get the new multicast flags
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: A set of flags for the current/next TVLV, querier and
  * bridge state.
@@ -275,7 +275,7 @@ static u8 batadv_mcast_mla_forw_flags_get(struct batadv_priv *bat_priv)
 static struct batadv_mcast_mla_flags
 batadv_mcast_mla_flags_get(struct batadv_priv *bat_priv)
 {
-	struct net_device *dev = bat_priv->soft_iface;
+	struct net_device *dev = bat_priv->mesh_iface;
 	struct batadv_mcast_querier_state *qr4, *qr6;
 	struct batadv_mcast_mla_flags mla_flags;
 	struct net_device *bridge;
@@ -351,13 +351,13 @@ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr,
 }
 
 /**
- * batadv_mcast_mla_softif_get_ipv4() - get softif IPv4 multicast listeners
+ * batadv_mcast_mla_meshif_get_ipv4() - get meshif IPv4 multicast listeners
  * @dev: the device to collect multicast addresses from
  * @mcast_list: a list to put found addresses into
  * @flags: flags indicating the new multicast state
  *
  * Collects multicast addresses of IPv4 multicast listeners residing
- * on this kernel on the given soft interface, dev, in
+ * on this kernel on the given mesh interface, dev, in
  * the given mcast_list. In general, multicast listeners provided by
  * your multicast receiving applications run directly on this node.
  *
@@ -365,7 +365,7 @@ static bool batadv_mcast_mla_is_duplicate(u8 *mcast_addr,
  * items added to the mcast_list otherwise.
  */
 static int
-batadv_mcast_mla_softif_get_ipv4(struct net_device *dev,
+batadv_mcast_mla_meshif_get_ipv4(struct net_device *dev,
 				 struct hlist_head *mcast_list,
 				 struct batadv_mcast_mla_flags *flags)
 {
@@ -417,13 +417,13 @@ batadv_mcast_mla_softif_get_ipv4(struct net_device *dev,
 }
 
 /**
- * batadv_mcast_mla_softif_get_ipv6() - get softif IPv6 multicast listeners
+ * batadv_mcast_mla_meshif_get_ipv6() - get meshif IPv6 multicast listeners
  * @dev: the device to collect multicast addresses from
  * @mcast_list: a list to put found addresses into
  * @flags: flags indicating the new multicast state
  *
  * Collects multicast addresses of IPv6 multicast listeners residing
- * on this kernel on the given soft interface, dev, in
+ * on this kernel on the given mesh interface, dev, in
  * the given mcast_list. In general, multicast listeners provided by
  * your multicast receiving applications run directly on this node.
  *
@@ -432,7 +432,7 @@ batadv_mcast_mla_softif_get_ipv4(struct net_device *dev,
  */
 #if IS_ENABLED(CONFIG_IPV6)
 static int
-batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
+batadv_mcast_mla_meshif_get_ipv6(struct net_device *dev,
 				 struct hlist_head *mcast_list,
 				 struct batadv_mcast_mla_flags *flags)
 {
@@ -490,7 +490,7 @@ batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
 }
 #else
 static inline int
-batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
+batadv_mcast_mla_meshif_get_ipv6(struct net_device *dev,
 				 struct hlist_head *mcast_list,
 				 struct batadv_mcast_mla_flags *flags)
 {
@@ -499,13 +499,13 @@ batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
 #endif
 
 /**
- * batadv_mcast_mla_softif_get() - get softif multicast listeners
+ * batadv_mcast_mla_meshif_get() - get meshif multicast listeners
  * @dev: the device to collect multicast addresses from
  * @mcast_list: a list to put found addresses into
  * @flags: flags indicating the new multicast state
  *
  * Collects multicast addresses of multicast listeners residing
- * on this kernel on the given soft interface, dev, in
+ * on this kernel on the given mesh interface, dev, in
  * the given mcast_list. In general, multicast listeners provided by
  * your multicast receiving applications run directly on this node.
  *
@@ -518,7 +518,7 @@ batadv_mcast_mla_softif_get_ipv6(struct net_device *dev,
  * items added to the mcast_list otherwise.
  */
 static int
-batadv_mcast_mla_softif_get(struct net_device *dev,
+batadv_mcast_mla_meshif_get(struct net_device *dev,
 			    struct hlist_head *mcast_list,
 			    struct batadv_mcast_mla_flags *flags)
 {
@@ -528,11 +528,11 @@ batadv_mcast_mla_softif_get(struct net_device *dev,
 	if (bridge)
 		dev = bridge;
 
-	ret4 = batadv_mcast_mla_softif_get_ipv4(dev, mcast_list, flags);
+	ret4 = batadv_mcast_mla_meshif_get_ipv4(dev, mcast_list, flags);
 	if (ret4 < 0)
 		goto out;
 
-	ret6 = batadv_mcast_mla_softif_get_ipv6(dev, mcast_list, flags);
+	ret6 = batadv_mcast_mla_meshif_get_ipv6(dev, mcast_list, flags);
 	if (ret6 < 0) {
 		ret4 = 0;
 		goto out;
@@ -576,7 +576,7 @@ static void batadv_mcast_mla_br_addr_cpy(char *dst, const struct br_ip *src)
  *
  * Collects multicast addresses of multicast listeners residing
  * on foreign, non-mesh devices which we gave access to our mesh via
- * a bridge on top of the given soft interface, dev, in the given
+ * a bridge on top of the given mesh interface, dev, in the given
  * mcast_list.
  *
  * Return: -ENOMEM on memory allocation error or the number of
@@ -672,7 +672,7 @@ static void batadv_mcast_mla_list_free(struct hlist_head *mcast_list)
 
 /**
  * batadv_mcast_mla_tt_retract() - clean up multicast listener announcements
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @mcast_list: a list of addresses which should _not_ be removed
  *
  * Retracts the announcement of any multicast listener from the
@@ -704,7 +704,7 @@ static void batadv_mcast_mla_tt_retract(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_mla_tt_add() - add multicast listener announcements
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @mcast_list: a list of addresses which are going to get added
  *
  * Adds multicast listener announcements from the given mcast_list to the
@@ -724,7 +724,7 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
 						  &bat_priv->mcast.mla_list))
 			continue;
 
-		if (!batadv_tt_local_add(bat_priv->soft_iface,
+		if (!batadv_tt_local_add(bat_priv->mesh_iface,
 					 mcast_entry->addr, BATADV_NO_FLAGS,
 					 BATADV_NULL_IFINDEX, BATADV_NO_MARK))
 			continue;
@@ -737,7 +737,7 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
 /**
  * batadv_mcast_querier_log() - debug output regarding the querier status on
  *  link
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @str_proto: a string for the querier protocol (e.g. "IGMP" or "MLD")
  * @old_state: the previous querier state on our link
  * @new_state: the new querier state on our link
@@ -754,7 +754,7 @@ static void batadv_mcast_mla_tt_add(struct batadv_priv *bat_priv,
  * potentially shadowing listeners from us then.
  *
  * This is only interesting for nodes with a bridge on top of their
- * soft interface.
+ * mesh interface.
  */
 static void
 batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
@@ -762,14 +762,14 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
 			 struct batadv_mcast_querier_state *new_state)
 {
 	if (!old_state->exists && new_state->exists)
-		batadv_info(bat_priv->soft_iface, "%s Querier appeared\n",
+		batadv_info(bat_priv->mesh_iface, "%s Querier appeared\n",
 			    str_proto);
 	else if (old_state->exists && !new_state->exists)
-		batadv_info(bat_priv->soft_iface,
+		batadv_info(bat_priv->mesh_iface,
 			    "%s Querier disappeared - multicast optimizations disabled\n",
 			    str_proto);
 	else if (!bat_priv->mcast.mla_flags.bridged && !new_state->exists)
-		batadv_info(bat_priv->soft_iface,
+		batadv_info(bat_priv->mesh_iface,
 			    "No %s Querier present - multicast optimizations disabled\n",
 			    str_proto);
 
@@ -789,7 +789,7 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
 /**
  * batadv_mcast_bridge_log() - debug output for topology changes in bridged
  *  setups
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @new_flags: flags indicating the new multicast state
  *
  * If no bridges are ever used on this node, then this function does nothing.
@@ -798,7 +798,7 @@ batadv_mcast_querier_log(struct batadv_priv *bat_priv, char *str_proto,
  * which might be relevant to our multicast optimizations.
  *
  * More precisely, it outputs information when a bridge interface is added or
- * removed from a soft interface. And when a bridge is present, it further
+ * removed from a mesh interface. And when a bridge is present, it further
  * outputs information about the querier state which is relevant for the
  * multicast flags this node is going to set.
  */
@@ -827,7 +827,7 @@ batadv_mcast_bridge_log(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_flags_log() - output debug information about mcast flag changes
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @flags: TVLV flags indicating the new multicast state
  *
  * Whenever the multicast TVLV flags this node announces change, this function
@@ -860,7 +860,7 @@ static void batadv_mcast_flags_log(struct batadv_priv *bat_priv, u8 flags)
 
 /**
  * batadv_mcast_mla_flags_update() - update multicast flags
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @flags: flags indicating the new multicast state
  *
  * Updates the own multicast tvlv with our current multicast related settings,
@@ -889,7 +889,7 @@ batadv_mcast_mla_flags_update(struct batadv_priv *bat_priv,
 
 /**
  * __batadv_mcast_mla_update() - update the own MLAs
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Updates the own multicast listener announcements in the translation
  * table as well as the own, announced multicast tvlv container.
@@ -901,18 +901,18 @@ batadv_mcast_mla_flags_update(struct batadv_priv *bat_priv,
  */
 static void __batadv_mcast_mla_update(struct batadv_priv *bat_priv)
 {
-	struct net_device *soft_iface = bat_priv->soft_iface;
+	struct net_device *mesh_iface = bat_priv->mesh_iface;
 	struct hlist_head mcast_list = HLIST_HEAD_INIT;
 	struct batadv_mcast_mla_flags flags;
 	int ret;
 
 	flags = batadv_mcast_mla_flags_get(bat_priv);
 
-	ret = batadv_mcast_mla_softif_get(soft_iface, &mcast_list, &flags);
+	ret = batadv_mcast_mla_meshif_get(mesh_iface, &mcast_list, &flags);
 	if (ret < 0)
 		goto out;
 
-	ret = batadv_mcast_mla_bridge_get(soft_iface, &mcast_list, &flags);
+	ret = batadv_mcast_mla_bridge_get(mesh_iface, &mcast_list, &flags);
 	if (ret < 0)
 		goto out;
 
@@ -977,7 +977,7 @@ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb)
 /**
  * batadv_mcast_forw_mode_check_ipv4() - check for optimized forwarding
  *  potential
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the IPv4 packet to check
  * @is_unsnoopable: stores whether the destination is snoopable
  * @is_routable: stores whether the destination is routable
@@ -1042,7 +1042,7 @@ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb)
 /**
  * batadv_mcast_forw_mode_check_ipv6() - check for optimized forwarding
  *  potential
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the IPv6 packet to check
  * @is_unsnoopable: stores whether the destination is snoopable
  * @is_routable: stores whether the destination is routable
@@ -1084,7 +1084,7 @@ static int batadv_mcast_forw_mode_check_ipv6(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_mode_check() - check for optimized forwarding potential
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast frame to check
  * @is_unsnoopable: stores whether the destination is snoopable
  * @is_routable: stores whether the destination is routable
@@ -1124,7 +1124,7 @@ static int batadv_mcast_forw_mode_check(struct batadv_priv *bat_priv,
 /**
  * batadv_mcast_forw_want_all_ip_count() - count nodes with unspecific mcast
  *  interest
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ethhdr: ethernet header of a packet
  *
  * Return: the number of nodes which want all IPv4 multicast traffic if the
@@ -1147,7 +1147,7 @@ static int batadv_mcast_forw_want_all_ip_count(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_rtr_count() - count nodes with a multicast router
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @protocol: the ethernet protocol type to count multicast routers for
  *
  * Return: the number of nodes which want all routable IPv4 multicast traffic
@@ -1170,7 +1170,7 @@ static int batadv_mcast_forw_rtr_count(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_mode_by_count() - get forwarding mode by count
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to check
  * @vid: the vlan identifier
  * @is_routable: stores whether the destination is routable
@@ -1214,7 +1214,7 @@ batadv_mcast_forw_mode_by_count(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_mode() - check on how to forward a multicast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to check
  * @vid: the vlan identifier
  * @is_routable: stores whether the destination is routable
@@ -1259,7 +1259,7 @@ batadv_mcast_forw_mode(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_mcast_forw_send_orig() - send a multicast packet to an originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to send
  * @vid: the vlan identifier
  * @orig_node: the originator to send the packet to
@@ -1288,7 +1288,7 @@ static int batadv_mcast_forw_send_orig(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_tt() - forwards a packet to multicast listeners
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1336,7 +1336,7 @@ batadv_mcast_forw_tt(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_mcast_forw_want_all_ipv4() - forward to nodes with want-all-ipv4
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1373,7 +1373,7 @@ batadv_mcast_forw_want_all_ipv4(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_want_all_ipv6() - forward to nodes with want-all-ipv6
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: The multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1410,7 +1410,7 @@ batadv_mcast_forw_want_all_ipv6(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_want_all() - forward packet to nodes in a want-all list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1439,7 +1439,7 @@ batadv_mcast_forw_want_all(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_want_all_rtr4() - forward to nodes with want-all-rtr4
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1476,7 +1476,7 @@ batadv_mcast_forw_want_all_rtr4(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_want_all_rtr6() - forward to nodes with want-all-rtr6
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: The multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1513,7 +1513,7 @@ batadv_mcast_forw_want_all_rtr6(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_want_rtr() - forward packet to nodes in a want-all-rtr list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  *
@@ -1542,7 +1542,7 @@ batadv_mcast_forw_want_rtr(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_send() - send packet to any detected multicast recipient
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to transmit
  * @vid: the vlan identifier
  * @is_routable: stores whether the destination is routable
@@ -1590,7 +1590,7 @@ int batadv_mcast_forw_send(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_mcast_want_unsnoop_update() - update unsnoop counter and list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1636,7 +1636,7 @@ static void batadv_mcast_want_unsnoop_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_want_ipv4_update() - update want-all-ipv4 counter and list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1681,7 +1681,7 @@ static void batadv_mcast_want_ipv4_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_want_ipv6_update() - update want-all-ipv6 counter and list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1726,7 +1726,7 @@ static void batadv_mcast_want_ipv6_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_want_rtr4_update() - update want-all-rtr4 counter and list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1771,7 +1771,7 @@ static void batadv_mcast_want_rtr4_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_want_rtr6_update() - update want-all-rtr6 counter and list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1816,7 +1816,7 @@ static void batadv_mcast_want_rtr6_update(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_have_mc_ptype_update() - update multicast packet type counter
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node which multicast state might have changed of
  * @mcast_flags: flags indicating the new multicast state
  *
@@ -1872,7 +1872,7 @@ batadv_mcast_tvlv_flags_get(bool enabled, void *tvlv_value, u16 tvlv_value_len)
 
 /**
  * batadv_mcast_tvlv_ogm_handler() - process incoming multicast tvlv container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the multicast data
@@ -1915,7 +1915,7 @@ static void batadv_mcast_tvlv_ogm_handler(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_init() - initialize the multicast optimizations structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_mcast_init(struct batadv_priv *bat_priv)
 {
@@ -1934,7 +1934,7 @@ void batadv_mcast_init(struct batadv_priv *bat_priv)
 /**
  * batadv_mcast_mesh_info_put() - put multicast info into a netlink message
  * @msg: buffer for the message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 or error code.
  */
@@ -2060,7 +2060,7 @@ batadv_mcast_flags_dump_bucket(struct sk_buff *msg, u32 portid,
  * @msg: buffer for the message
  * @portid: netlink port
  * @cb: Control block containing additional options
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @bucket: current bucket to dump
  * @idx: index in current bucket to the next entry to dump
  *
@@ -2103,15 +2103,15 @@ batadv_mcast_netlink_get_primary(struct netlink_callback *cb,
 				 struct batadv_hard_iface **primary_if)
 {
 	struct batadv_hard_iface *hard_iface = NULL;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	int ret = 0;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	hard_iface = batadv_primary_if_get_selected(bat_priv);
 	if (!hard_iface || hard_iface->if_status != BATADV_IF_ACTIVE) {
@@ -2120,7 +2120,7 @@ batadv_mcast_netlink_get_primary(struct netlink_callback *cb,
 	}
 
 out:
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	if (!ret && primary_if)
 		*primary_if = hard_iface;
@@ -2150,7 +2150,7 @@ int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	if (ret)
 		return ret;
 
-	bat_priv = netdev_priv(primary_if->soft_iface);
+	bat_priv = netdev_priv(primary_if->mesh_iface);
 	ret = __batadv_mcast_flags_dump(msg, portid, cb, bat_priv, bucket, idx);
 
 	batadv_hardif_put(primary_if);
@@ -2159,7 +2159,7 @@ int batadv_mcast_flags_dump(struct sk_buff *msg, struct netlink_callback *cb)
 
 /**
  * batadv_mcast_free() - free the multicast optimizations structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_mcast_free(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/multicast_forw.c b/net/batman-adv/multicast_forw.c
index fafd6ba8c056d..b8668a80b94a1 100644
--- a/net/batman-adv/multicast_forw.c
+++ b/net/batman-adv/multicast_forw.c
@@ -131,7 +131,7 @@ batadv_mcast_forw_orig_entry(struct hlist_node *node,
 
 /**
  * batadv_mcast_forw_push_dest() - push an originator MAC address onto an skb
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination address onto
  * @vid: the vlan identifier
  * @orig_node: the originator node to get the MAC address from
@@ -174,7 +174,7 @@ static bool batadv_mcast_forw_push_dest(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_push_dests_list() - push originators from list onto an skb
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination addresses onto
  * @vid: the vlan identifier
  * @head: the list to gather originators from
@@ -215,7 +215,7 @@ static int batadv_mcast_forw_push_dests_list(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_push_tt() - push originators with interest through TT
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination addresses onto
  * @vid: the vlan identifier
  * @num_dests: a pointer to store the number of pushed addresses in
@@ -262,7 +262,7 @@ batadv_mcast_forw_push_tt(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_mcast_forw_push_want_all() - push originators with want-all flag
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination addresses onto
  * @vid: the vlan identifier
  * @num_dests: a pointer to store the number of pushed addresses in
@@ -308,7 +308,7 @@ static bool batadv_mcast_forw_push_want_all(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_push_want_rtr() - push originators with want-router flag
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination addresses onto
  * @vid: the vlan identifier
  * @num_dests: a pointer to store the number of pushed addresses in
@@ -475,7 +475,7 @@ batadv_mcast_forw_push_adjust_padding(struct sk_buff *skb, int *count,
 
 /**
  * batadv_mcast_forw_push_dests() - push originator addresses onto an skb
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the destination addresses onto
  * @vid: the vlan identifier
  * @is_routable: indicates whether the destination is routable
@@ -567,7 +567,7 @@ static int batadv_mcast_forw_push_tracker(struct sk_buff *skb, int num_dests,
 
 /**
  * batadv_mcast_forw_push_tvlvs() - push a multicast tracker TVLV onto an skb
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb to push the tracker TVLV onto
  * @vid: the vlan identifier
  * @is_routable: indicates whether the destination is routable
@@ -634,7 +634,7 @@ batadv_mcast_forw_push_hdr(struct sk_buff *skb, unsigned short tvlv_len)
 
 /**
  * batadv_mcast_forw_scrub_dests() - scrub destinations in a tracker TVLV
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @comp_neigh: next hop neighbor to scrub+collect destinations for
  * @dest: start MAC entry in original skb's tracker TVLV
  * @next_dest: start MAC entry in to be sent skb's tracker TVLV
@@ -905,7 +905,7 @@ static void batadv_mcast_forw_shrink_tracker(struct sk_buff *skb)
 
 /**
  * batadv_mcast_forw_packet() - forward a batman-adv multicast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the received or locally generated batman-adv multicast packet
  * @local_xmit: indicates that the packet was locally generated and not received
  *
@@ -920,7 +920,7 @@ static void batadv_mcast_forw_shrink_tracker(struct sk_buff *skb)
  *
  * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
  * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
- * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ * decapsulated and forwarded to the own mesh interface, NET_RX_DROP otherwise.
  */
 static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
 				    struct sk_buff *skb, bool local_xmit)
@@ -1028,7 +1028,7 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_tracker_tvlv_handler() - handle an mcast tracker tvlv
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the received batman-adv multicast packet
  *
  * Parses the tracker TVLV of an incoming batman-adv multicast packet and
@@ -1042,7 +1042,7 @@ static int batadv_mcast_forw_packet(struct batadv_priv *bat_priv,
  *
  * Return: NET_RX_SUCCESS or NET_RX_DROP on success or a negative error
  * code on failure. NET_RX_SUCCESS if the received packet is supposed to be
- * decapsulated and forwarded to the own soft interface, NET_RX_DROP otherwise.
+ * decapsulated and forwarded to the own mesh interface, NET_RX_DROP otherwise.
  */
 int batadv_mcast_forw_tracker_tvlv_handler(struct batadv_priv *bat_priv,
 					   struct sk_buff *skb)
@@ -1075,7 +1075,7 @@ unsigned int batadv_mcast_forw_packet_hdrlen(unsigned int num_dests)
 
 /**
  * batadv_mcast_forw_expand_head() - expand headroom for an mcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to send
  *
  * Tries to expand an skb's headroom so that its head to tail is 1298
@@ -1110,7 +1110,7 @@ static int batadv_mcast_forw_expand_head(struct batadv_priv *bat_priv,
 
 /**
  * batadv_mcast_forw_push() - encapsulate skb in a batman-adv multicast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to encapsulate and send
  * @vid: the vlan identifier
  * @is_routable: indicates whether the destination is routable
@@ -1154,7 +1154,7 @@ bool batadv_mcast_forw_push(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_mcast_forw_mcsend() - send a self prepared batman-adv multicast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the multicast packet to encapsulate and send
  *
  * Transmits a batman-adv multicast packet that was locally prepared and
diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index eefba5600ded3..13935570fae17 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -43,10 +43,10 @@
 #include "gateway_common.h"
 #include "hard-interface.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "multicast.h"
 #include "network-coding.h"
 #include "originator.h"
-#include "soft-interface.h"
 #include "tp_meter.h"
 #include "translation-table.h"
 
@@ -63,7 +63,7 @@ enum batadv_netlink_multicast_groups {
  */
 enum batadv_genl_ops_flags {
 	/**
-	 * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in
+	 * @BATADV_FLAG_NEED_MESH: request requires valid mesh interface in
 	 *  attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be
 	 *  saved in info->user_ptr[0]
 	 */
@@ -166,24 +166,24 @@ static int batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype)
 }
 
 /**
- * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation softif attribute
+ * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation meshif attribute
  * @msg: Netlink message to dump into
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or negative error number in case of failure
  */
 static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg,
 						 struct batadv_priv *bat_priv)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	u8 ap_isolation;
 
-	vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+	vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS);
 	if (!vlan)
 		return 0;
 
 	ap_isolation = atomic_read(&vlan->ap_isolation);
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 
 	return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED,
 			  !!ap_isolation);
@@ -192,21 +192,21 @@ static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg,
 /**
  * batadv_netlink_set_mesh_ap_isolation() - Set ap_isolation from genl msg
  * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or negative error number in case of failure
  */
 static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr,
 						struct batadv_priv *bat_priv)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
-	vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS);
+	vlan = batadv_meshif_vlan_get(bat_priv, BATADV_NO_FLAGS);
 	if (!vlan)
 		return -ENOENT;
 
 	atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr));
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 
 	return 0;
 }
@@ -214,7 +214,7 @@ static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr,
 /**
  * batadv_netlink_mesh_fill() - Fill message with mesh attributes
  * @msg: Netlink message to dump into
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @cmd: type of message to generate
  * @portid: Port making netlink request
  * @seq: sequence number for message
@@ -227,7 +227,7 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
 				    enum batadv_nl_commands cmd,
 				    u32 portid, u32 seq, int flags)
 {
-	struct net_device *soft_iface = bat_priv->soft_iface;
+	struct net_device *mesh_iface = bat_priv->mesh_iface;
 	struct batadv_hard_iface *primary_if = NULL;
 	struct net_device *hard_iface;
 	void *hdr;
@@ -239,10 +239,10 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
 	if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) ||
 	    nla_put_string(msg, BATADV_ATTR_ALGO_NAME,
 			   bat_priv->algo_ops->name) ||
-	    nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, soft_iface->ifindex) ||
-	    nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, soft_iface->name) ||
+	    nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, mesh_iface->ifindex) ||
+	    nla_put_string(msg, BATADV_ATTR_MESH_IFNAME, mesh_iface->name) ||
 	    nla_put(msg, BATADV_ATTR_MESH_ADDRESS, ETH_ALEN,
-		    soft_iface->dev_addr) ||
+		    mesh_iface->dev_addr) ||
 	    nla_put_u8(msg, BATADV_ATTR_TT_TTVN,
 		       (u8)atomic_read(&bat_priv->tt.vn)))
 		goto nla_put_failure;
@@ -369,8 +369,8 @@ static int batadv_netlink_mesh_fill(struct sk_buff *msg,
 }
 
 /**
- * batadv_netlink_notify_mesh() - send softif attributes to listener
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_netlink_notify_mesh() - send meshif attributes to listener
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success, < 0 on error
  */
@@ -391,14 +391,14 @@ static int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv)
 	}
 
 	genlmsg_multicast_netns(&batadv_netlink_family,
-				dev_net(bat_priv->soft_iface), msg, 0,
+				dev_net(bat_priv->mesh_iface), msg, 0,
 				BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
 
 	return 0;
 }
 
 /**
- * batadv_netlink_get_mesh() - Get softif attributes
+ * batadv_netlink_get_mesh() - Get meshif attributes
  * @skb: Netlink message with request data
  * @info: receiver information
  *
@@ -427,7 +427,7 @@ static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info)
 }
 
 /**
- * batadv_netlink_set_mesh() - Set softif attributes
+ * batadv_netlink_set_mesh() - Set meshif attributes
  * @skb: Netlink message with request data
  * @info: receiver information
  *
@@ -474,7 +474,7 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 
 		atomic_set(&bat_priv->bridge_loop_avoidance,
 			   !!nla_get_u8(attr));
-		batadv_bla_status_update(bat_priv->soft_iface);
+		batadv_bla_status_update(bat_priv->mesh_iface);
 	}
 #endif /* CONFIG_BATMAN_ADV_BLA */
 
@@ -484,7 +484,7 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 
 		atomic_set(&bat_priv->distributed_arp_table,
 			   !!nla_get_u8(attr));
-		batadv_dat_status_update(bat_priv->soft_iface);
+		batadv_dat_status_update(bat_priv->mesh_iface);
 	}
 #endif /* CONFIG_BATMAN_ADV_DAT */
 
@@ -494,7 +494,7 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 		atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr));
 
 		rtnl_lock();
-		batadv_update_min_mtu(bat_priv->soft_iface);
+		batadv_update_min_mtu(bat_priv->mesh_iface);
 		rtnl_unlock();
 	}
 
@@ -594,7 +594,7 @@ static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info)
 		attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED];
 
 		atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr));
-		batadv_nc_status_update(bat_priv->soft_iface);
+		batadv_nc_status_update(bat_priv->mesh_iface);
 	}
 #endif /* CONFIG_BATMAN_ADV_NC */
 
@@ -633,7 +633,7 @@ batadv_netlink_tp_meter_put(struct sk_buff *msg, u32 cookie)
 
 /**
  * batadv_netlink_tpmeter_notify() - send tp_meter result via netlink to client
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: destination of tp_meter session
  * @result: reason for tp meter session stop
  * @test_time: total time of the tp_meter session
@@ -680,7 +680,7 @@ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst,
 	genlmsg_end(msg, hdr);
 
 	genlmsg_multicast_netns(&batadv_netlink_family,
-				dev_net(bat_priv->soft_iface), msg, 0,
+				dev_net(bat_priv->mesh_iface), msg, 0,
 				BATADV_NL_MCGRP_TPMETER, GFP_KERNEL);
 
 	return 0;
@@ -778,7 +778,7 @@ batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info)
 /**
  * batadv_netlink_hardif_fill() - Fill message with hardif attributes
  * @msg: Netlink message to dump into
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hard_iface: hard interface which was modified
  * @cmd: type of message to generate
  * @portid: Port making netlink request
@@ -806,11 +806,11 @@ static int batadv_netlink_hardif_fill(struct sk_buff *msg,
 		genl_dump_check_consistent(cb, hdr);
 
 	if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX,
-			bat_priv->soft_iface->ifindex))
+			bat_priv->mesh_iface->ifindex))
 		goto nla_put_failure;
 
 	if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME,
-			   bat_priv->soft_iface->name))
+			   bat_priv->mesh_iface->name))
 		goto nla_put_failure;
 
 	if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX,
@@ -850,7 +850,7 @@ static int batadv_netlink_hardif_fill(struct sk_buff *msg,
 
 /**
  * batadv_netlink_notify_hardif() - send hardif attributes to listener
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hard_iface: hard interface which was modified
  *
  * Return: 0 on success, < 0 on error
@@ -873,7 +873,7 @@ static int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv,
 	}
 
 	genlmsg_multicast_netns(&batadv_netlink_family,
-				dev_net(bat_priv->soft_iface), msg, 0,
+				dev_net(bat_priv->mesh_iface), msg, 0,
 				BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
 
 	return 0;
@@ -963,24 +963,24 @@ static int batadv_netlink_set_hardif(struct sk_buff *skb,
 static int
 batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
 {
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_hard_iface *hard_iface;
 	struct batadv_priv *bat_priv;
 	int portid = NETLINK_CB(cb->skb).portid;
 	int skip = cb->args[0];
 	int i = 0;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	rtnl_lock();
 	cb->seq = batadv_hardif_generation << 1 | 1;
 
 	list_for_each_entry(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != soft_iface)
+		if (hard_iface->mesh_iface != mesh_iface)
 			continue;
 
 		if (i++ < skip)
@@ -997,7 +997,7 @@ batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
 
 	rtnl_unlock();
 
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	cb->args[0] = i;
 
@@ -1007,7 +1007,7 @@ batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
 /**
  * batadv_netlink_vlan_fill() - Fill message with vlan attributes
  * @msg: Netlink message to dump into
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vlan: vlan which was modified
  * @cmd: type of message to generate
  * @portid: Port making netlink request
@@ -1018,7 +1018,7 @@ batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb)
  */
 static int batadv_netlink_vlan_fill(struct sk_buff *msg,
 				    struct batadv_priv *bat_priv,
-				    struct batadv_softif_vlan *vlan,
+				    struct batadv_meshif_vlan *vlan,
 				    enum batadv_nl_commands cmd,
 				    u32 portid, u32 seq, int flags)
 {
@@ -1029,11 +1029,11 @@ static int batadv_netlink_vlan_fill(struct sk_buff *msg,
 		return -ENOBUFS;
 
 	if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX,
-			bat_priv->soft_iface->ifindex))
+			bat_priv->mesh_iface->ifindex))
 		goto nla_put_failure;
 
 	if (nla_put_string(msg, BATADV_ATTR_MESH_IFNAME,
-			   bat_priv->soft_iface->name))
+			   bat_priv->mesh_iface->name))
 		goto nla_put_failure;
 
 	if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK))
@@ -1053,13 +1053,13 @@ static int batadv_netlink_vlan_fill(struct sk_buff *msg,
 
 /**
  * batadv_netlink_notify_vlan() - send vlan attributes to listener
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vlan: vlan which was modified
  *
  * Return: 0 on success, < 0 on error
  */
 static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
-				      struct batadv_softif_vlan *vlan)
+				      struct batadv_meshif_vlan *vlan)
 {
 	struct sk_buff *msg;
 	int ret;
@@ -1076,7 +1076,7 @@ static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
 	}
 
 	genlmsg_multicast_netns(&batadv_netlink_family,
-				dev_net(bat_priv->soft_iface), msg, 0,
+				dev_net(bat_priv->mesh_iface), msg, 0,
 				BATADV_NL_MCGRP_CONFIG, GFP_KERNEL);
 
 	return 0;
@@ -1091,7 +1091,7 @@ static int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv,
  */
 static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info)
 {
-	struct batadv_softif_vlan *vlan = info->user_ptr[1];
+	struct batadv_meshif_vlan *vlan = info->user_ptr[1];
 	struct batadv_priv *bat_priv = info->user_ptr[0];
 	struct sk_buff *msg;
 	int ret;
@@ -1121,7 +1121,7 @@ static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info)
  */
 static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info)
 {
-	struct batadv_softif_vlan *vlan = info->user_ptr[1];
+	struct batadv_meshif_vlan *vlan = info->user_ptr[1];
 	struct batadv_priv *bat_priv = info->user_ptr[0];
 	struct nlattr *attr;
 
@@ -1137,43 +1137,43 @@ static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info)
 }
 
 /**
- * batadv_netlink_get_softif_from_ifindex() - Get soft-iface from ifindex
+ * batadv_netlink_get_meshif_from_ifindex() - Get mesh-iface from ifindex
  * @net: the applicable net namespace
- * @ifindex: index of the soft interface
+ * @ifindex: index of the mesh interface
  *
- * Return: Pointer to soft interface (with increased refcnt) on success, error
+ * Return: Pointer to mesh interface (with increased refcnt) on success, error
  *  pointer on error
  */
 static struct net_device *
-batadv_netlink_get_softif_from_ifindex(struct net *net, int ifindex)
+batadv_netlink_get_meshif_from_ifindex(struct net *net, int ifindex)
 {
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 
-	soft_iface = dev_get_by_index(net, ifindex);
-	if (!soft_iface)
+	mesh_iface = dev_get_by_index(net, ifindex);
+	if (!mesh_iface)
 		return ERR_PTR(-ENODEV);
 
-	if (!batadv_softif_is_valid(soft_iface))
-		goto err_put_softif;
+	if (!batadv_meshif_is_valid(mesh_iface))
+		goto err_put_meshif;
 
-	return soft_iface;
+	return mesh_iface;
 
-err_put_softif:
-	dev_put(soft_iface);
+err_put_meshif:
+	dev_put(mesh_iface);
 
 	return ERR_PTR(-EINVAL);
 }
 
 /**
- * batadv_netlink_get_softif_from_info() - Get soft-iface from genl attributes
+ * batadv_netlink_get_meshif_from_info() - Get mesh-iface from genl attributes
  * @net: the applicable net namespace
  * @info: receiver information
  *
- * Return: Pointer to soft interface (with increased refcnt) on success, error
+ * Return: Pointer to mesh interface (with increased refcnt) on success, error
  *  pointer on error
  */
 static struct net_device *
-batadv_netlink_get_softif_from_info(struct net *net, struct genl_info *info)
+batadv_netlink_get_meshif_from_info(struct net *net, struct genl_info *info)
 {
 	int ifindex;
 
@@ -1182,30 +1182,30 @@ batadv_netlink_get_softif_from_info(struct net *net, struct genl_info *info)
 
 	ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]);
 
-	return batadv_netlink_get_softif_from_ifindex(net, ifindex);
+	return batadv_netlink_get_meshif_from_ifindex(net, ifindex);
 }
 
 /**
- * batadv_netlink_get_softif() - Retrieve soft interface from netlink callback
+ * batadv_netlink_get_meshif() - Retrieve mesh interface from netlink callback
  * @cb: callback structure containing arguments
  *
- * Return: Pointer to soft interface (with increased refcnt) on success, error
+ * Return: Pointer to mesh interface (with increased refcnt) on success, error
  *  pointer on error
  */
-struct net_device *batadv_netlink_get_softif(struct netlink_callback *cb)
+struct net_device *batadv_netlink_get_meshif(struct netlink_callback *cb)
 {
 	int ifindex = batadv_netlink_get_ifindex(cb->nlh,
 						 BATADV_ATTR_MESH_IFINDEX);
 	if (!ifindex)
 		return ERR_PTR(-ENONET);
 
-	return batadv_netlink_get_softif_from_ifindex(sock_net(cb->skb->sk),
+	return batadv_netlink_get_meshif_from_ifindex(sock_net(cb->skb->sk),
 						      ifindex);
 }
 
 /**
  * batadv_netlink_get_hardif_from_ifindex() - Get hard-iface from ifindex
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @net: the applicable net namespace
  * @ifindex: index of the hard interface
  *
@@ -1227,7 +1227,7 @@ batadv_netlink_get_hardif_from_ifindex(struct batadv_priv *bat_priv,
 	if (!hard_iface)
 		goto err_put_harddev;
 
-	if (hard_iface->soft_iface != bat_priv->soft_iface)
+	if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 		goto err_put_hardif;
 
 	/* hard_dev is referenced by hard_iface and not needed here */
@@ -1245,7 +1245,7 @@ batadv_netlink_get_hardif_from_ifindex(struct batadv_priv *bat_priv,
 
 /**
  * batadv_netlink_get_hardif_from_info() - Get hard-iface from genl attributes
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @net: the applicable net namespace
  * @info: receiver information
  *
@@ -1268,7 +1268,7 @@ batadv_netlink_get_hardif_from_info(struct batadv_priv *bat_priv,
 
 /**
  * batadv_netlink_get_hardif() - Retrieve hard interface from netlink callback
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @cb: callback structure containing arguments
  *
  * Return: Pointer to hard interface (with increased refcnt) on success, error
@@ -1290,18 +1290,18 @@ batadv_netlink_get_hardif(struct batadv_priv *bat_priv,
 
 /**
  * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @net: the applicable net namespace
  * @info: receiver information
  *
  * Return: Pointer to vlan on success (with increased refcnt), error pointer
  *  on error
  */
-static struct batadv_softif_vlan *
+static struct batadv_meshif_vlan *
 batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net,
 			  struct genl_info *info)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	u16 vid;
 
 	if (!info->attrs[BATADV_ATTR_VLANID])
@@ -1309,7 +1309,7 @@ batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net,
 
 	vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]);
 
-	vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG);
 	if (!vlan)
 		return ERR_PTR(-ENOENT);
 
@@ -1331,8 +1331,8 @@ static int batadv_pre_doit(const struct genl_split_ops *ops,
 	struct net *net = genl_info_net(info);
 	struct batadv_hard_iface *hard_iface;
 	struct batadv_priv *bat_priv = NULL;
-	struct batadv_softif_vlan *vlan;
-	struct net_device *soft_iface;
+	struct batadv_meshif_vlan *vlan;
+	struct net_device *mesh_iface;
 	u8 user_ptr1_flags;
 	u8 mesh_dep_flags;
 	int ret;
@@ -1347,11 +1347,11 @@ static int batadv_pre_doit(const struct genl_split_ops *ops,
 		return -EINVAL;
 
 	if (ops->internal_flags & BATADV_FLAG_NEED_MESH) {
-		soft_iface = batadv_netlink_get_softif_from_info(net, info);
-		if (IS_ERR(soft_iface))
-			return PTR_ERR(soft_iface);
+		mesh_iface = batadv_netlink_get_meshif_from_info(net, info);
+		if (IS_ERR(mesh_iface))
+			return PTR_ERR(mesh_iface);
 
-		bat_priv = netdev_priv(soft_iface);
+		bat_priv = netdev_priv(mesh_iface);
 		info->user_ptr[0] = bat_priv;
 	}
 
@@ -1360,7 +1360,7 @@ static int batadv_pre_doit(const struct genl_split_ops *ops,
 								 info);
 		if (IS_ERR(hard_iface)) {
 			ret = PTR_ERR(hard_iface);
-			goto err_put_softif;
+			goto err_put_meshif;
 		}
 
 		info->user_ptr[1] = hard_iface;
@@ -1370,7 +1370,7 @@ static int batadv_pre_doit(const struct genl_split_ops *ops,
 		vlan = batadv_get_vlan_from_info(bat_priv, net, info);
 		if (IS_ERR(vlan)) {
 			ret = PTR_ERR(vlan);
-			goto err_put_softif;
+			goto err_put_meshif;
 		}
 
 		info->user_ptr[1] = vlan;
@@ -1378,9 +1378,9 @@ static int batadv_pre_doit(const struct genl_split_ops *ops,
 
 	return 0;
 
-err_put_softif:
+err_put_meshif:
 	if (bat_priv)
-		dev_put(bat_priv->soft_iface);
+		dev_put(bat_priv->mesh_iface);
 
 	return ret;
 }
@@ -1396,7 +1396,7 @@ static void batadv_post_doit(const struct genl_split_ops *ops,
 			     struct genl_info *info)
 {
 	struct batadv_hard_iface *hard_iface;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	struct batadv_priv *bat_priv;
 
 	if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF &&
@@ -1408,12 +1408,12 @@ static void batadv_post_doit(const struct genl_split_ops *ops,
 
 	if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) {
 		vlan = info->user_ptr[1];
-		batadv_softif_vlan_put(vlan);
+		batadv_meshif_vlan_put(vlan);
 	}
 
 	if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) {
 		bat_priv = info->user_ptr[0];
-		dev_put(bat_priv->soft_iface);
+		dev_put(bat_priv->mesh_iface);
 	}
 }
 
diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h
index 2097c2ae98f16..fe4548b974bb0 100644
--- a/net/batman-adv/netlink.h
+++ b/net/batman-adv/netlink.h
@@ -15,7 +15,7 @@
 
 void batadv_netlink_register(void);
 void batadv_netlink_unregister(void);
-struct net_device *batadv_netlink_get_softif(struct netlink_callback *cb);
+struct net_device *batadv_netlink_get_meshif(struct netlink_callback *cb);
 struct batadv_hard_iface *
 batadv_netlink_get_hardif(struct batadv_priv *bat_priv,
 			  struct netlink_callback *cb);
diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c
index 71ebd0284f95d..9f56308779cc3 100644
--- a/net/batman-adv/network-coding.c
+++ b/net/batman-adv/network-coding.c
@@ -65,7 +65,7 @@ int __init batadv_nc_init(void)
 
 /**
  * batadv_nc_start_timer() - initialise the nc periodic worker
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_nc_start_timer(struct batadv_priv *bat_priv)
 {
@@ -76,7 +76,7 @@ static void batadv_nc_start_timer(struct batadv_priv *bat_priv)
 /**
  * batadv_nc_tvlv_container_update() - update the network coding tvlv container
  *  after network coding setting change
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv)
 {
@@ -98,7 +98,7 @@ static void batadv_nc_tvlv_container_update(struct batadv_priv *bat_priv)
 /**
  * batadv_nc_status_update() - update the network coding tvlv container after
  *  network coding setting change
- * @net_dev: the soft interface net device
+ * @net_dev: the mesh interface net device
  */
 void batadv_nc_status_update(struct net_device *net_dev)
 {
@@ -109,7 +109,7 @@ void batadv_nc_status_update(struct net_device *net_dev)
 
 /**
  * batadv_nc_tvlv_ogm_handler_v1() - process incoming nc tvlv container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the gateway data
@@ -128,7 +128,7 @@ static void batadv_nc_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 
 /**
  * batadv_nc_mesh_init() - initialise coding hash table and start housekeeping
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or negative error number in case of failure
  */
@@ -171,7 +171,7 @@ int batadv_nc_mesh_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_nc_init_bat_priv() - initialise the nc specific bat_priv variables
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_nc_init_bat_priv(struct batadv_priv *bat_priv)
 {
@@ -267,7 +267,7 @@ static void batadv_nc_packet_free(struct batadv_nc_packet *nc_packet,
 
 /**
  * batadv_nc_to_purge_nc_node() - checks whether an nc node has to be purged
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @nc_node: the nc node to check
  *
  * Return: true if the entry has to be purged now, false otherwise
@@ -283,7 +283,7 @@ static bool batadv_nc_to_purge_nc_node(struct batadv_priv *bat_priv,
 
 /**
  * batadv_nc_to_purge_nc_path_coding() - checks whether an nc path has timed out
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @nc_path: the nc path to check
  *
  * Return: true if the entry has to be purged now, false otherwise
@@ -304,7 +304,7 @@ static bool batadv_nc_to_purge_nc_path_coding(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_to_purge_nc_path_decoding() - checks whether an nc path has timed
  *  out
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @nc_path: the nc path to check
  *
  * Return: true if the entry has to be purged now, false otherwise
@@ -325,7 +325,7 @@ static bool batadv_nc_to_purge_nc_path_decoding(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_purge_orig_nc_nodes() - go through list of nc nodes and purge stale
  *  entries
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @list: list of nc nodes
  * @lock: nc node list lock
  * @to_purge: function in charge to decide whether an entry has to be purged or
@@ -363,7 +363,7 @@ batadv_nc_purge_orig_nc_nodes(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_purge_orig() - purges all nc node data attached of the given
  *  originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig_node with the nc node entries to be purged
  * @to_purge: function in charge to decide whether an entry has to be purged or
  *	      not. This function takes the nc node as argument and has to return
@@ -389,7 +389,7 @@ void batadv_nc_purge_orig(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_purge_orig_hash() - traverse entire originator hash to check if
  *  they have timed out nc nodes
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv)
 {
@@ -416,7 +416,7 @@ static void batadv_nc_purge_orig_hash(struct batadv_priv *bat_priv)
 /**
  * batadv_nc_purge_paths() - traverse all nc paths part of the hash and remove
  *  unused ones
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hash: hash table containing the nc paths to check
  * @to_purge: function in charge to decide whether an entry has to be purged or
  *	      not. This function takes the nc node as argument and has to return
@@ -579,7 +579,7 @@ static void batadv_nc_send_packet(struct batadv_nc_packet *nc_packet)
 
 /**
  * batadv_nc_sniffed_purge() - Checks timestamp of given sniffed nc_packet.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @nc_path: the nc path the packet belongs to
  * @nc_packet: the nc packet to be checked
  *
@@ -618,7 +618,7 @@ static bool batadv_nc_sniffed_purge(struct batadv_priv *bat_priv,
 
 /**
  * batadv_nc_fwd_flush() - Checks the timestamp of the given nc packet.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @nc_path: the nc path the packet belongs to
  * @nc_packet: the nc packet to be checked
  *
@@ -657,7 +657,7 @@ static bool batadv_nc_fwd_flush(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_process_nc_paths() - traverse given nc packet pool and free timed
  *  out nc packets
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hash: to be processed hash table
  * @process_fn: Function called to process given nc packet. Should return true
  *	        to encourage this function to proceed with the next packet.
@@ -744,7 +744,7 @@ static void batadv_nc_worker(struct work_struct *work)
 /**
  * batadv_can_nc_with_orig() - checks whether the given orig node is suitable
  *  for coding or not
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: neighboring orig node which may be used as nc candidate
  * @ogm_packet: incoming ogm packet also used for the checks
  *
@@ -825,7 +825,7 @@ batadv_nc_find_nc_node(struct batadv_orig_node *orig_node,
 /**
  * batadv_nc_get_nc_node() - retrieves an nc node or creates the entry if it was
  *  not found
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node originating the ogm packet
  * @orig_neigh_node: neighboring orig node from which we received the ogm packet
  *  (can be equal to orig_node)
@@ -888,7 +888,7 @@ batadv_nc_get_nc_node(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_update_nc_node() - updates stored incoming and outgoing nc node
  *  structs (best called on incoming OGMs)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node originating the ogm packet
  * @orig_neigh_node: neighboring orig node from which we received the ogm packet
  *  (can be equal to orig_node)
@@ -940,7 +940,7 @@ void batadv_nc_update_nc_node(struct batadv_priv *bat_priv,
 
 /**
  * batadv_nc_get_path() - get existing nc_path or allocate a new one
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hash: hash table containing the nc path
  * @src: ethernet source address - first half of the nc path search key
  * @dst: ethernet destination address - second half of the nc path search key
@@ -1032,7 +1032,7 @@ static void batadv_nc_memxor(char *dst, const char *src, unsigned int len)
 /**
  * batadv_nc_code_packets() - code a received unicast_packet with an nc packet
  *  into a coded_packet and send it
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: data skb to forward
  * @ethhdr: pointer to the ethernet header inside the skb
  * @nc_packet: structure containing the packet to the skb can be coded with
@@ -1245,7 +1245,7 @@ static bool batadv_nc_skb_coding_possible(struct sk_buff *skb, u8 *dst, u8 *src)
 /**
  * batadv_nc_path_search() - Find the coding path matching in_nc_node and
  *  out_nc_node to retrieve a buffered packet that can be used for coding.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @in_nc_node: pointer to skb next hop's neighbor nc node
  * @out_nc_node: pointer to skb source's neighbor nc node
  * @skb: data skb to forward
@@ -1313,7 +1313,7 @@ batadv_nc_path_search(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_skb_src_search() - Loops through the list of neighboring nodes of
  *  the skb's sender (may be equal to the originator).
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: data skb to forward
  * @eth_dst: next hop mac address of skb
  * @eth_src: source mac address of skb
@@ -1359,7 +1359,7 @@ batadv_nc_skb_src_search(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_skb_store_before_coding() - set the ethernet src and dst of the
  *  unicast skb before it is stored for use in later decoding
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: data skb to store
  * @eth_dst_new: new destination mac address of skb
  */
@@ -1408,7 +1408,7 @@ static bool batadv_nc_skb_dst_search(struct sk_buff *skb,
 				     struct batadv_neigh_node *neigh_node,
 				     struct ethhdr *ethhdr)
 {
-	struct net_device *netdev = neigh_node->if_incoming->soft_iface;
+	struct net_device *netdev = neigh_node->if_incoming->mesh_iface;
 	struct batadv_priv *bat_priv = netdev_priv(netdev);
 	struct batadv_orig_node *orig_node = neigh_node->orig_node;
 	struct batadv_nc_node *nc_node;
@@ -1495,7 +1495,7 @@ static bool batadv_nc_skb_add_to_path(struct sk_buff *skb,
 bool batadv_nc_skb_forward(struct sk_buff *skb,
 			   struct batadv_neigh_node *neigh_node)
 {
-	const struct net_device *netdev = neigh_node->if_incoming->soft_iface;
+	const struct net_device *netdev = neigh_node->if_incoming->mesh_iface;
 	struct batadv_priv *bat_priv = netdev_priv(netdev);
 	struct batadv_unicast_packet *packet;
 	struct batadv_nc_path *nc_path;
@@ -1544,7 +1544,7 @@ bool batadv_nc_skb_forward(struct sk_buff *skb,
 /**
  * batadv_nc_skb_store_for_decoding() - save a clone of the skb which can be
  *  used when decoding coded packets
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: data skb to store
  */
 void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
@@ -1605,7 +1605,7 @@ void batadv_nc_skb_store_for_decoding(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_skb_store_sniffed_unicast() - check if a received unicast packet
  *  should be saved in the decoding buffer and, if so, store it there
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: unicast skb to store
  */
 void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
@@ -1625,7 +1625,7 @@ void batadv_nc_skb_store_sniffed_unicast(struct batadv_priv *bat_priv,
 /**
  * batadv_nc_skb_decode_packet() - decode given skb using the decode data stored
  *  in nc_packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: unicast skb to decode
  * @nc_packet: decode data needed to decode the skb
  *
@@ -1719,7 +1719,7 @@ batadv_nc_skb_decode_packet(struct batadv_priv *bat_priv, struct sk_buff *skb,
 /**
  * batadv_nc_find_decoding_packet() - search through buffered decoding data to
  *  find the data needed to decode the coded packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @ethhdr: pointer to the ethernet header inside the coded packet
  * @coded: coded packet we try to find decode data for
  *
@@ -1793,7 +1793,7 @@ batadv_nc_find_decoding_packet(struct batadv_priv *bat_priv,
 static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
 				       struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_unicast_packet *unicast_packet;
 	struct batadv_coded_packet *coded_packet;
 	struct batadv_nc_packet *nc_packet;
@@ -1858,7 +1858,7 @@ static int batadv_nc_recv_coded_packet(struct sk_buff *skb,
 
 /**
  * batadv_nc_mesh_free() - clean up network coding memory
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_nc_mesh_free(struct batadv_priv *bat_priv)
 {
diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c
index bcc2e20e0cd6c..d9cfc5c6b2088 100644
--- a/net/batman-adv/originator.c
+++ b/net/batman-adv/originator.c
@@ -47,7 +47,7 @@ static struct lock_class_key batadv_orig_hash_lock_class_key;
 
 /**
  * batadv_orig_hash_find() - Find and return originator from orig_hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @data: mac address of the originator
  *
  * Return: orig_node (with increased refcnt), NULL on errors
@@ -213,7 +213,7 @@ void batadv_orig_node_vlan_release(struct kref *ref)
 
 /**
  * batadv_originator_init() - Initialize all originator structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or negative error number in case of failure
  */
@@ -338,7 +338,7 @@ batadv_orig_router_get(struct batadv_orig_node *orig_node,
 
 /**
  * batadv_orig_to_router() - get next hop neighbor to an orig address
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_addr: the originator MAC address to search the best next hop router for
  * @if_outgoing: the interface where the payload packet has been received or
  *  the OGM should be sent to
@@ -567,7 +567,7 @@ batadv_hardif_neigh_create(struct batadv_hard_iface *hard_iface,
 			   const u8 *neigh_addr,
 			   struct batadv_orig_node *orig_node)
 {
-	struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(hard_iface->mesh_iface);
 	struct batadv_hardif_neigh_node *hardif_neigh;
 
 	spin_lock_bh(&hard_iface->neigh_list_lock);
@@ -754,20 +754,20 @@ batadv_neigh_node_get_or_create(struct batadv_orig_node *orig_node,
 int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if, *hard_iface;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	int ret;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) {
 		ret = -ENOENT;
-		goto out_put_soft_iface;
+		goto out_put_mesh_iface;
 	}
 
 	hard_iface = batadv_netlink_get_hardif(bat_priv, cb);
@@ -794,8 +794,8 @@ int batadv_hardif_neigh_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	batadv_hardif_put(hard_iface);
 out_put_primary_if:
 	batadv_hardif_put(primary_if);
-out_put_soft_iface:
-	dev_put(soft_iface);
+out_put_mesh_iface:
+	dev_put(mesh_iface);
 
 	return ret;
 }
@@ -892,7 +892,7 @@ void batadv_orig_node_release(struct kref *ref)
 
 /**
  * batadv_originator_free() - Free all originator structures
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_originator_free(struct batadv_priv *bat_priv)
 {
@@ -928,7 +928,7 @@ void batadv_originator_free(struct batadv_priv *bat_priv)
 
 /**
  * batadv_orig_node_new() - creates a new orig_node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the originator
  *
  * Creates a new originator object and initialises all the generic fields.
@@ -1009,7 +1009,7 @@ struct batadv_orig_node *batadv_orig_node_new(struct batadv_priv *bat_priv,
 
 /**
  * batadv_purge_neigh_ifinfo() - purge obsolete ifinfo entries from neighbor
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @neigh: orig node which is to be checked
  */
 static void
@@ -1050,7 +1050,7 @@ batadv_purge_neigh_ifinfo(struct batadv_priv *bat_priv,
 
 /**
  * batadv_purge_orig_ifinfo() - purge obsolete ifinfo entries from originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be checked
  *
  * Return: true if any ifinfo entry was purged, false otherwise.
@@ -1102,7 +1102,7 @@ batadv_purge_orig_ifinfo(struct batadv_priv *bat_priv,
 
 /**
  * batadv_purge_orig_neighbors() - purges neighbors from originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be checked
  *
  * Return: true if any neighbor was purged, false otherwise
@@ -1160,7 +1160,7 @@ batadv_purge_orig_neighbors(struct batadv_priv *bat_priv,
 
 /**
  * batadv_find_best_neighbor() - finds the best neighbor after purging
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be checked
  * @if_outgoing: the interface for which the metric should be compared
  *
@@ -1194,7 +1194,7 @@ batadv_find_best_neighbor(struct batadv_priv *bat_priv,
 
 /**
  * batadv_purge_orig_node() - purges obsolete information from an orig_node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be checked
  *
  * This function checks if the orig_node or substructures of it have become
@@ -1236,7 +1236,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 		if (hard_iface->if_status != BATADV_IF_ACTIVE)
 			continue;
 
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&hard_iface->refcount))
@@ -1258,7 +1258,7 @@ static bool batadv_purge_orig_node(struct batadv_priv *bat_priv,
 
 /**
  * batadv_purge_orig_ref() - Purge all outdated originators
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_purge_orig_ref(struct batadv_priv *bat_priv)
 {
@@ -1325,20 +1325,20 @@ static void batadv_purge_orig(struct work_struct *work)
 int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	struct batadv_hard_iface *primary_if, *hard_iface;
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	int ret;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) {
 		ret = -ENOENT;
-		goto out_put_soft_iface;
+		goto out_put_mesh_iface;
 	}
 
 	hard_iface = batadv_netlink_get_hardif(bat_priv, cb);
@@ -1365,8 +1365,8 @@ int batadv_orig_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	batadv_hardif_put(hard_iface);
 out_put_primary_if:
 	batadv_hardif_put(primary_if);
-out_put_soft_iface:
-	dev_put(soft_iface);
+out_put_mesh_iface:
+	dev_put(mesh_iface);
 
 	return ret;
 }
diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c
index f1061985149fc..35d8c57839998 100644
--- a/net/batman-adv/routing.c
+++ b/net/batman-adv/routing.c
@@ -30,10 +30,10 @@
 #include "fragmentation.h"
 #include "hard-interface.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "send.h"
-#include "soft-interface.h"
 #include "tp_meter.h"
 #include "translation-table.h"
 #include "tvlv.h"
@@ -43,7 +43,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 
 /**
  * _batadv_update_route() - set the router for this originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be configured
  * @recv_if: the receive interface for which this route is set
  * @neigh_node: neighbor which should be the next router
@@ -106,7 +106,7 @@ static void _batadv_update_route(struct batadv_priv *bat_priv,
 
 /**
  * batadv_update_route() - set the router for this originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which is to be configured
  * @recv_if: the receive interface for which this route is set
  * @neigh_node: neighbor which should be the next router
@@ -133,7 +133,7 @@ void batadv_update_route(struct batadv_priv *bat_priv,
 /**
  * batadv_window_protected() - checks whether the host restarted and is in the
  *  protection time.
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @seq_num_diff: difference between the current/received sequence number and
  *  the last sequence number
  * @seq_old_max_diff: maximum age of sequence number not considered as restart
@@ -207,7 +207,7 @@ bool batadv_check_management_packet(struct sk_buff *skb,
 
 /**
  * batadv_recv_my_icmp_packet() - receive an icmp packet locally
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: icmp packet to process
  *
  * Return: NET_RX_SUCCESS if the packet has been consumed or NET_RX_DROP
@@ -338,7 +338,7 @@ static int batadv_recv_icmp_ttl_exceeded(struct batadv_priv *bat_priv,
 int batadv_recv_icmp_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_icmp_header *icmph;
 	struct batadv_icmp_packet_rr *icmp_packet_rr;
 	struct ethhdr *ethhdr;
@@ -428,7 +428,7 @@ int batadv_recv_icmp_packet(struct sk_buff *skb,
 
 /**
  * batadv_check_unicast_packet() - Check for malformed unicast packets
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: packet to check
  * @hdr_size: size of header to pull
  *
@@ -511,7 +511,7 @@ batadv_last_bonding_replace(struct batadv_orig_node *orig_node,
 
 /**
  * batadv_find_router() - find a suitable router for this originator
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the destination node
  * @recv_if: pointer to interface this packet was received on
  *
@@ -656,7 +656,7 @@ batadv_find_router(struct batadv_priv *bat_priv,
 static int batadv_route_unicast_packet(struct sk_buff *skb,
 				       struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_unicast_packet *unicast_packet;
 	struct ethhdr *ethhdr = eth_hdr(skb);
@@ -727,7 +727,7 @@ static int batadv_route_unicast_packet(struct sk_buff *skb,
 
 /**
  * batadv_reroute_unicast_packet() - update the unicast header for re-routing
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: unicast packet to process
  * @unicast_packet: the unicast header to be updated
  * @dst_addr: the payload destination
@@ -879,7 +879,7 @@ static bool batadv_check_unicast_ttvn(struct batadv_priv *bat_priv,
 		return false;
 
 	/* update the header in order to let the packet be delivered to this
-	 * node's soft interface
+	 * node's mesh interface
 	 */
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if)
@@ -909,7 +909,7 @@ int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
 					 struct batadv_hard_iface *recv_if)
 {
 	struct batadv_unicast_packet *unicast_packet;
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	int check, hdr_size = sizeof(*unicast_packet);
 
 	check = batadv_check_unicast_packet(bat_priv, skb, hdr_size);
@@ -938,7 +938,7 @@ int batadv_recv_unhandled_unicast_packet(struct sk_buff *skb,
 int batadv_recv_unicast_packet(struct sk_buff *skb,
 			       struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_unicast_packet *unicast_packet;
 	struct batadv_unicast_4addr_packet *unicast_4addr_packet;
 	u8 *orig_addr, *orig_addr_gw;
@@ -1017,7 +1017,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 
 		batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size);
 
-		batadv_interface_rx(recv_if->soft_iface, skb, hdr_size,
+		batadv_interface_rx(recv_if->mesh_iface, skb, hdr_size,
 				    orig_node);
 
 rx_success:
@@ -1047,7 +1047,7 @@ int batadv_recv_unicast_packet(struct sk_buff *skb,
 int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_unicast_tvlv_packet *unicast_tvlv_packet;
 	unsigned char *tvlv_buff;
 	u16 tvlv_buff_len;
@@ -1103,7 +1103,7 @@ int batadv_recv_unicast_tvlv(struct sk_buff *skb,
 int batadv_recv_frag_packet(struct sk_buff *skb,
 			    struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_orig_node *orig_node_src = NULL;
 	struct batadv_frag_packet *frag_packet;
 	int ret = NET_RX_DROP;
@@ -1165,7 +1165,7 @@ int batadv_recv_frag_packet(struct sk_buff *skb,
 int batadv_recv_bcast_packet(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_orig_node *orig_node = NULL;
 	struct batadv_bcast_packet *bcast_packet;
 	struct ethhdr *ethhdr;
@@ -1255,7 +1255,7 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
 	batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size);
 
 	/* broadcast for me */
-	batadv_interface_rx(recv_if->soft_iface, skb, hdr_size, orig_node);
+	batadv_interface_rx(recv_if->mesh_iface, skb, hdr_size, orig_node);
 
 rx_success:
 	ret = NET_RX_SUCCESS;
@@ -1279,14 +1279,14 @@ int batadv_recv_bcast_packet(struct sk_buff *skb,
  *
  * Parses the given, received batman-adv multicast packet. Depending on the
  * contents of its TVLV forwards it and/or decapsulates it to hand it to the
- * soft interface.
+ * mesh interface.
  *
  * Return: NET_RX_DROP if the skb is not consumed, NET_RX_SUCCESS otherwise.
  */
 int batadv_recv_mcast_packet(struct sk_buff *skb,
 			     struct batadv_hard_iface *recv_if)
 {
-	struct batadv_priv *bat_priv = netdev_priv(recv_if->soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(recv_if->mesh_iface);
 	struct batadv_mcast_packet *mcast_packet;
 	int hdr_size = sizeof(*mcast_packet);
 	unsigned char *tvlv_buff;
@@ -1329,7 +1329,7 @@ int batadv_recv_mcast_packet(struct sk_buff *skb,
 		batadv_add_counter(bat_priv, BATADV_CNT_MCAST_RX_LOCAL_BYTES,
 				   skb->len - hdr_size);
 
-		batadv_interface_rx(bat_priv->soft_iface, skb, hdr_size, NULL);
+		batadv_interface_rx(bat_priv->mesh_iface, skb, hdr_size, NULL);
 		/* skb was consumed */
 		skb = NULL;
 	}
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 0379b126865d7..85478fdc8ce88 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -34,10 +34,10 @@
 #include "gateway_client.h"
 #include "hard-interface.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "network-coding.h"
 #include "originator.h"
 #include "routing.h"
-#include "soft-interface.h"
 #include "translation-table.h"
 
 static void batadv_send_outstanding_bcast_packet(struct work_struct *work);
@@ -68,7 +68,7 @@ int batadv_send_skb_packet(struct sk_buff *skb,
 	struct ethhdr *ethhdr;
 	int ret;
 
-	bat_priv = netdev_priv(hard_iface->soft_iface);
+	bat_priv = netdev_priv(hard_iface->mesh_iface);
 
 	if (hard_iface->if_status != BATADV_IF_ACTIVE)
 		goto send_skb_err;
@@ -272,7 +272,7 @@ static bool batadv_send_skb_prepare_unicast(struct sk_buff *skb,
 /**
  * batadv_send_skb_prepare_unicast_4addr() - encapsulate an skb with a
  *  unicast 4addr header
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the skb containing the payload to encapsulate
  * @orig: the destination node
  * @packet_subtype: the unicast 4addr packet subtype to use
@@ -314,7 +314,7 @@ bool batadv_send_skb_prepare_unicast_4addr(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_skb_unicast() - encapsulate and send an skb via unicast
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: payload to send
  * @packet_type: the batman unicast packet type to use
  * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast
@@ -384,7 +384,7 @@ int batadv_send_skb_unicast(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_skb_via_tt_generic() - send an skb via TT lookup
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: payload to send
  * @packet_type: the batman unicast packet type to use
  * @packet_subtype: the unicast 4addr packet subtype (only relevant for unicast
@@ -430,7 +430,7 @@ int batadv_send_skb_via_tt_generic(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_skb_via_gw() - send an skb via gateway lookup
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: payload to send
  * @vid: the vid to be used to search the translation table
  *
@@ -695,7 +695,7 @@ static void batadv_forw_packet_queue(struct batadv_forw_packet *forw_packet,
 
 /**
  * batadv_forw_packet_bcast_queue() - try to queue a broadcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @forw_packet: the forwarding packet to queue
  * @send_time: timestamp (jiffies) when the packet is to be sent
  *
@@ -714,7 +714,7 @@ batadv_forw_packet_bcast_queue(struct batadv_priv *bat_priv,
 
 /**
  * batadv_forw_packet_ogmv1_queue() - try to queue an OGMv1 packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @forw_packet: the forwarding packet to queue
  * @send_time: timestamp (jiffies) when the packet is to be sent
  *
@@ -732,7 +732,7 @@ void batadv_forw_packet_ogmv1_queue(struct batadv_priv *bat_priv,
 
 /**
  * batadv_forw_bcast_packet_to_list() - queue broadcast packet for transmissions
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
@@ -787,7 +787,7 @@ static int batadv_forw_bcast_packet_to_list(struct batadv_priv *bat_priv,
 
 /**
  * batadv_forw_bcast_packet_if() - forward and queue a broadcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
@@ -838,7 +838,7 @@ static int batadv_forw_bcast_packet_if(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_no_broadcast() - check whether (re)broadcast is necessary
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to check
  * @own_packet: true if it is a self-generated broadcast packet
  * @if_out: the outgoing interface checked and considered for (re)broadcast
@@ -900,7 +900,7 @@ static bool batadv_send_no_broadcast(struct batadv_priv *bat_priv,
 
 /**
  * __batadv_forw_bcast_packet() - forward and queue a broadcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
@@ -930,7 +930,7 @@ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(hard_iface, &batadv_hardif_list, list) {
-		if (hard_iface->soft_iface != bat_priv->soft_iface)
+		if (hard_iface->mesh_iface != bat_priv->mesh_iface)
 			continue;
 
 		if (!kref_get_unless_zero(&hard_iface->refcount))
@@ -958,7 +958,7 @@ static int __batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
 
 /**
  * batadv_forw_bcast_packet() - forward and queue a broadcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
@@ -979,7 +979,7 @@ int batadv_forw_bcast_packet(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_bcast_packet() - send and queue a broadcast packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: broadcast packet to add
  * @delay: number of jiffies to wait before sending
  * @own_packet: true if it is a self-generated broadcast packet
@@ -1060,7 +1060,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 	delayed_work = to_delayed_work(work);
 	forw_packet = container_of(delayed_work, struct batadv_forw_packet,
 				   delayed_work);
-	bat_priv = netdev_priv(forw_packet->if_incoming->soft_iface);
+	bat_priv = netdev_priv(forw_packet->if_incoming->mesh_iface);
 
 	if (atomic_read(&bat_priv->mesh_state) == BATADV_MESH_DEACTIVATING) {
 		dropped = true;
@@ -1095,7 +1095,7 @@ static void batadv_send_outstanding_bcast_packet(struct work_struct *work)
 
 /**
  * batadv_purge_outstanding_packets() - stop/purge scheduled bcast/OGMv1 packets
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hard_iface: the hard interface to cancel and purge bcast/ogm packets on
  *
  * This method cancels and purges any broadcast and OGMv1 packet on the given
diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h
index 08af251b765c2..3415afec4a0c2 100644
--- a/net/batman-adv/send.h
+++ b/net/batman-adv/send.h
@@ -68,7 +68,7 @@ int batadv_send_skb_via_gw(struct batadv_priv *bat_priv, struct sk_buff *skb,
 
 /**
  * batadv_send_skb_via_tt() - send an skb via TT lookup
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the payload to send
  * @dst_hint: can be used to override the destination contained in the skb
  * @vid: the vid to be used to search the translation table
@@ -89,7 +89,7 @@ static inline int batadv_send_skb_via_tt(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_skb_via_tt_4addr() - send an skb via TT lookup
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the payload to send
  * @packet_subtype: the unicast 4addr packet subtype to use
  * @dst_hint: can be used to override the destination contained in the skb
diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c
index 7f3dd3c393e07..9fb14e40e1562 100644
--- a/net/batman-adv/tp_meter.c
+++ b/net/batman-adv/tp_meter.c
@@ -206,7 +206,7 @@ static void batadv_tp_update_rto(struct batadv_tp_vars *tp_vars,
  * batadv_tp_batctl_notify() - send client status result to client
  * @reason: reason for tp meter session stop
  * @dst: destination of tp_meter session
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @start_time: start of transmission in jiffies
  * @total_sent: bytes acked to the receiver
  * @cookie: cookie of tp_meter session
@@ -238,7 +238,7 @@ static void batadv_tp_batctl_notify(enum batadv_tp_meter_reason reason,
  * batadv_tp_batctl_error_notify() - send client error result to client
  * @reason: reason for tp meter session stop
  * @dst: destination of tp_meter session
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @cookie: cookie of tp_meter session
  */
 static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason,
@@ -251,7 +251,7 @@ static void batadv_tp_batctl_error_notify(enum batadv_tp_meter_reason reason,
 
 /**
  * batadv_tp_list_find() - find a tp_vars object in the global list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: the other endpoint MAC address to look for
  *
  * Look for a tp_vars object matching dst as end_point and return it after
@@ -287,7 +287,7 @@ static struct batadv_tp_vars *batadv_tp_list_find(struct batadv_priv *bat_priv,
 /**
  * batadv_tp_list_find_session() - find tp_vars session object in the global
  *  list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: the other endpoint MAC address to look for
  * @session: session identifier
  *
@@ -366,7 +366,7 @@ static void batadv_tp_vars_put(struct batadv_tp_vars *tp_vars)
 
 /**
  * batadv_tp_sender_cleanup() - cleanup sender data and drop and timer
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tp_vars: the private data of the current TP meter session to cleanup
  */
 static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv,
@@ -396,7 +396,7 @@ static void batadv_tp_sender_cleanup(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tp_sender_end() - print info about ended session and inform client
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tp_vars: the private data of the current TP meter session
  */
 static void batadv_tp_sender_end(struct batadv_priv *bat_priv,
@@ -619,7 +619,7 @@ static int batadv_tp_send_msg(struct batadv_tp_vars *tp_vars, const u8 *src,
 
 /**
  * batadv_tp_recv_ack() - ACK receiving function
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the buffer containing the received packet
  *
  * Process a received TP ACK packet
@@ -832,7 +832,7 @@ static int batadv_tp_send(void *arg)
 	}
 
 	/* assume that all the hard_interfaces have a correctly
-	 * configured MTU, so use the soft_iface MTU as MSS.
+	 * configured MTU, so use the mesh_iface MTU as MSS.
 	 * This might not be true and in that case the fragmentation
 	 * should be used.
 	 * Now, try to send the packet as it is
@@ -927,7 +927,7 @@ static void batadv_tp_start_kthread(struct batadv_tp_vars *tp_vars)
 
 /**
  * batadv_tp_start() - start a new tp meter session
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: the receiver MAC address
  * @test_length: test length in milliseconds
  * @cookie: session cookie
@@ -993,7 +993,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 
 	/* initialise the CWND to 3*MSS (Section 3.1 in RFC5681).
 	 * For batman-adv the MSS is the size of the payload received by the
-	 * soft_interface, hence its MTU
+	 * mesh_interface, hence its MTU
 	 */
 	tp_vars->cwnd = BATADV_TP_PLEN * 3;
 	/* at the beginning initialise the SS threshold to the biggest possible
@@ -1052,7 +1052,7 @@ void batadv_tp_start(struct batadv_priv *bat_priv, const u8 *dst,
 
 /**
  * batadv_tp_stop() - stop currently running tp meter session
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: the receiver MAC address
  * @return_value: reason for tp meter session stop
  */
@@ -1141,7 +1141,7 @@ static void batadv_tp_receiver_shutdown(struct timer_list *t)
 
 /**
  * batadv_tp_send_ack() - send an ACK packet
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst: the mac address of the destination originator
  * @seq: the sequence number to ACK
  * @timestamp: the timestamp to echo back in the ACK
@@ -1320,7 +1320,7 @@ static void batadv_tp_ack_unordered(struct batadv_tp_vars *tp_vars)
 
 /**
  * batadv_tp_init_recv() - return matching or create new receiver tp_vars
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @icmp: received icmp tp msg
  *
  * Return: corresponding tp_vars or NULL on errors
@@ -1373,7 +1373,7 @@ batadv_tp_init_recv(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tp_recv_msg() - process a single data message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the buffer containing the received packet
  *
  * Process a received TP MSG packet
@@ -1457,7 +1457,7 @@ static void batadv_tp_recv_msg(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tp_meter_recv() - main TP Meter receiving function
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @skb: the buffer containing the received packet
  */
 void batadv_tp_meter_recv(struct batadv_priv *bat_priv, struct sk_buff *skb)
diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h
index 6b816cf1a953b..7da692ec38e90 100644
--- a/net/batman-adv/trace.h
+++ b/net/batman-adv/trace.h
@@ -34,7 +34,7 @@ TRACE_EVENT(batadv_dbg,
 	    TP_ARGS(bat_priv, vaf),
 
 	    TP_STRUCT__entry(
-		    __string(device, bat_priv->soft_iface->name)
+		    __string(device, bat_priv->mesh_iface->name)
 		    __string(driver, KBUILD_MODNAME)
 		    __vstring(msg, vaf->fmt, vaf->va)
 	    ),
diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c
index d4b71d34310f4..4a3165920de19 100644
--- a/net/batman-adv/translation-table.c
+++ b/net/batman-adv/translation-table.c
@@ -47,9 +47,9 @@
 #include "hard-interface.h"
 #include "hash.h"
 #include "log.h"
+#include "mesh-interface.h"
 #include "netlink.h"
 #include "originator.h"
-#include "soft-interface.h"
 #include "tvlv.h"
 
 static struct kmem_cache *batadv_tl_cache __read_mostly;
@@ -161,7 +161,7 @@ batadv_tt_hash_find(struct batadv_hashtable *hash, const u8 *addr,
 
 /**
  * batadv_tt_local_hash_find() - search the local table for a given client
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client to look for
  * @vid: VLAN identifier
  *
@@ -186,7 +186,7 @@ batadv_tt_local_hash_find(struct batadv_priv *bat_priv, const u8 *addr,
 
 /**
  * batadv_tt_global_hash_find() - search the global table for a given client
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client to look for
  * @vid: VLAN identifier
  *
@@ -221,7 +221,7 @@ static void batadv_tt_local_entry_release(struct kref *ref)
 	tt_local_entry = container_of(ref, struct batadv_tt_local_entry,
 				      common.refcount);
 
-	batadv_softif_vlan_put(tt_local_entry->vlan);
+	batadv_meshif_vlan_put(tt_local_entry->vlan);
 
 	kfree_rcu(tt_local_entry, common.rcu);
 }
@@ -260,7 +260,7 @@ void batadv_tt_global_entry_release(struct kref *ref)
 
 /**
  * batadv_tt_global_hash_count() - count the number of orig entries
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client to count entries for
  * @vid: VLAN identifier
  *
@@ -286,28 +286,28 @@ int batadv_tt_global_hash_count(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_local_size_mod() - change the size by v of the local table
  *  identified by vid
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the VLAN identifier of the sub-table to change
  * @v: the amount to sum to the local table size
  */
 static void batadv_tt_local_size_mod(struct batadv_priv *bat_priv,
 				     unsigned short vid, int v)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (!vlan)
 		return;
 
 	atomic_add(v, &vlan->tt.num_entries);
 
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 }
 
 /**
  * batadv_tt_local_size_inc() - increase by one the local table size for the
  *  given vid
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the VLAN identifier
  */
 static void batadv_tt_local_size_inc(struct batadv_priv *bat_priv,
@@ -319,7 +319,7 @@ static void batadv_tt_local_size_inc(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_local_size_dec() - decrease by one the local table size for the
  *  given vid
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: the VLAN identifier
  */
 static void batadv_tt_local_size_dec(struct batadv_priv *bat_priv,
@@ -412,7 +412,7 @@ batadv_tt_orig_list_entry_put(struct batadv_tt_orig_list_entry *orig_entry)
 
 /**
  * batadv_tt_local_event() - store a local TT event (ADD/DEL)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_local_entry: the TT entry involved in the event
  * @event_flags: flags to store in the event structure
  */
@@ -504,7 +504,7 @@ static u16 batadv_tt_entries(u16 tt_len)
 /**
  * batadv_tt_local_table_transmit_size() - calculates the local translation
  *  table size when transmitted over the air
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: local translation table size in bytes.
  */
@@ -512,11 +512,11 @@ static int batadv_tt_local_table_transmit_size(struct batadv_priv *bat_priv)
 {
 	u16 num_vlan = 0;
 	u16 tt_local_entries = 0;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	int hdr_size;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+	hlist_for_each_entry_rcu(vlan, &bat_priv->meshif_vlan_list, list) {
 		num_vlan++;
 		tt_local_entries += atomic_read(&vlan->tt.num_entries);
 	}
@@ -576,7 +576,7 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_local_add() - add a new client to the local table or update an
  *  existing client
- * @soft_iface: netdev struct of the mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  * @addr: the mac address of the client to add
  * @vid: VLAN identifier
  * @ifindex: index of the interface where the client is connected to (useful to
@@ -586,14 +586,14 @@ static void batadv_tt_global_free(struct batadv_priv *bat_priv,
  *
  * Return: true if the client was successfully added, false otherwise.
  */
-bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
+bool batadv_tt_local_add(struct net_device *mesh_iface, const u8 *addr,
 			 unsigned short vid, int ifindex, u32 mark)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	struct batadv_tt_local_entry *tt_local;
 	struct batadv_tt_global_entry *tt_global = NULL;
-	struct net *net = dev_net(soft_iface);
-	struct batadv_softif_vlan *vlan;
+	struct net *net = dev_net(mesh_iface);
+	struct batadv_meshif_vlan *vlan;
 	struct net_device *in_dev = NULL;
 	struct batadv_hard_iface *in_hardif = NULL;
 	struct hlist_head *head;
@@ -650,7 +650,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 	table_size += batadv_tt_len(1);
 	packet_size_max = atomic_read(&bat_priv->packet_size_max);
 	if (table_size > packet_size_max) {
-		net_ratelimited_function(batadv_info, soft_iface,
+		net_ratelimited_function(batadv_info, mesh_iface,
 					 "Local translation table size (%i) exceeds maximum packet size (%i); Ignoring new local tt entry: %pM\n",
 					 table_size, packet_size_max, addr);
 		goto out;
@@ -661,9 +661,9 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 		goto out;
 
 	/* increase the refcounter of the related vlan */
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (!vlan) {
-		net_ratelimited_function(batadv_info, soft_iface,
+		net_ratelimited_function(batadv_info, mesh_iface,
 					 "adding TT local entry %pM to non-existent VLAN %d\n",
 					 addr, batadv_print_vid(vid));
 		kmem_cache_free(batadv_tl_cache, tt_local);
@@ -693,7 +693,7 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
 	/* the batman interface mac and multicast addresses should never be
 	 * purged
 	 */
-	if (batadv_compare_eth(addr, soft_iface->dev_addr) ||
+	if (batadv_compare_eth(addr, mesh_iface->dev_addr) ||
 	    is_multicast_ether_addr(addr))
 		tt_local->common.flags |= BATADV_TT_CLIENT_NOPURGE;
 
@@ -849,7 +849,7 @@ batadv_tt_prepare_tvlv_global_data(struct batadv_orig_node *orig_node,
 /**
  * batadv_tt_prepare_tvlv_local_data() - allocate and prepare the TT TVLV for
  *  this node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_data: uninitialised pointer to the address of the TVLV buffer
  * @tt_change: uninitialised pointer to the address of the area where the TT
  *  changes can be stored
@@ -871,7 +871,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 				  s32 *tt_len)
 {
 	struct batadv_tvlv_tt_vlan_data *tt_vlan;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	u16 num_vlan = 0;
 	u16 vlan_entries = 0;
 	u16 total_entries = 0;
@@ -879,8 +879,8 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 	u8 *tt_change_ptr;
 	int change_offset;
 
-	spin_lock_bh(&bat_priv->softif_vlan_list_lock);
-	hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) {
+	spin_lock_bh(&bat_priv->meshif_vlan_list_lock);
+	hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) {
 		vlan_entries = atomic_read(&vlan->tt.num_entries);
 		if (vlan_entries < 1)
 			continue;
@@ -909,7 +909,7 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 	(*tt_data)->num_vlan = htons(num_vlan);
 
 	tt_vlan = (*tt_data)->vlan_data;
-	hlist_for_each_entry(vlan, &bat_priv->softif_vlan_list, list) {
+	hlist_for_each_entry(vlan, &bat_priv->meshif_vlan_list, list) {
 		vlan_entries = atomic_read(&vlan->tt.num_entries);
 		if (vlan_entries < 1)
 			continue;
@@ -925,14 +925,14 @@ batadv_tt_prepare_tvlv_local_data(struct batadv_priv *bat_priv,
 	*tt_change = (struct batadv_tvlv_tt_change *)tt_change_ptr;
 
 out:
-	spin_unlock_bh(&bat_priv->softif_vlan_list_lock);
+	spin_unlock_bh(&bat_priv->meshif_vlan_list_lock);
 	return tvlv_len;
 }
 
 /**
  * batadv_tt_tvlv_container_update() - update the translation table tvlv
  *  container after local tt changes have been committed
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv)
 {
@@ -956,7 +956,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv)
 	 * The local change history should still be cleaned up so the next
 	 * TT round can start again with a clean state.
 	 */
-	if (tt_diff_len > bat_priv->soft_iface->mtu) {
+	if (tt_diff_len > bat_priv->mesh_iface->mtu) {
 		tt_diff_len = 0;
 		tt_diff_entries_num = 0;
 		drop_changes = true;
@@ -1025,7 +1025,7 @@ static void batadv_tt_tvlv_container_update(struct batadv_priv *bat_priv)
  * @msg :Netlink message to dump into
  * @portid: Port making netlink request
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @common: tt local & tt global common data
  *
  * Return: Error code, or 0 on success
@@ -1037,7 +1037,7 @@ batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid,
 			   struct batadv_tt_common_entry *common)
 {
 	void *hdr;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	struct batadv_tt_local_entry *local;
 	unsigned int last_seen_msecs;
 	u32 crc;
@@ -1045,13 +1045,13 @@ batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid,
 	local = container_of(common, struct batadv_tt_local_entry, common);
 	last_seen_msecs = jiffies_to_msecs(jiffies - local->last_seen);
 
-	vlan = batadv_softif_vlan_get(bat_priv, common->vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, common->vid);
 	if (!vlan)
 		return 0;
 
 	crc = vlan->tt.crc;
 
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 
 	hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq,
 			  &batadv_netlink_family,  NLM_F_MULTI,
@@ -1084,7 +1084,7 @@ batadv_tt_local_dump_entry(struct sk_buff *msg, u32 portid,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @cb: Control block containing additional options
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @hash: hash to dump
  * @bucket: bucket index to dump
  * @idx_s: Number of entries to skip
@@ -1130,7 +1130,7 @@ batadv_tt_local_dump_bucket(struct sk_buff *msg, u32 portid,
  */
 int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_hashtable *hash;
@@ -1139,11 +1139,11 @@ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	int idx = cb->args[1];
 	int portid = NETLINK_CB(cb->skb).portid;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) {
@@ -1165,7 +1165,7 @@ int batadv_tt_local_dump(struct sk_buff *msg, struct netlink_callback *cb)
 
  out:
 	batadv_hardif_put(primary_if);
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	cb->args[0] = bucket;
 	cb->args[1] = idx;
@@ -1194,7 +1194,7 @@ batadv_tt_local_set_pending(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_local_remove() - logically remove an entry from the local table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the MAC address of the client to remove
  * @vid: VLAN identifier
  * @message: message to append to the log on deletion
@@ -1259,7 +1259,7 @@ u16 batadv_tt_local_remove(struct batadv_priv *bat_priv, const u8 *addr,
 
 /**
  * batadv_tt_local_purge_list() - purge inactive tt local entries
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @head: pointer to the list containing the local tt entries
  * @timeout: parameter deciding whether a given tt local entry is considered
  *  inactive or not
@@ -1294,7 +1294,7 @@ static void batadv_tt_local_purge_list(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_local_purge() - purge inactive tt local entries
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @timeout: parameter deciding whether a given tt local entry is considered
  *  inactive or not
  */
@@ -1529,7 +1529,7 @@ batadv_tt_global_orig_entry_add(struct batadv_tt_global_entry *tt_global,
 
 /**
  * batadv_tt_global_add() - add a new TT global entry or update an existing one
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the originator announcing the client
  * @tt_addr: the mac address of the non-mesh client
  * @vid: VLAN identifier
@@ -1702,7 +1702,7 @@ static bool batadv_tt_global_add(struct batadv_priv *bat_priv,
 
 /**
  * batadv_transtable_best_orig() - Get best originator list entry from tt entry
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_global_entry: global translation table entry to be analyzed
  *
  * This function assumes the caller holds rcu_read_lock().
@@ -1809,7 +1809,7 @@ batadv_tt_global_dump_subentry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @common: tt local & tt global common data
  * @sub_s: Number of entries to skip
  *
@@ -1854,7 +1854,7 @@ batadv_tt_global_dump_entry(struct sk_buff *msg, u32 portid, u32 seq,
  * @msg: Netlink message to dump into
  * @portid: Port making netlink request
  * @seq: Sequence number of netlink message
- * @bat_priv: The bat priv with all the soft interface information
+ * @bat_priv: The bat priv with all the mesh interface information
  * @head: Pointer to the list containing the global tt entries
  * @idx_s: Number of entries to skip
  * @sub: Number of entries to skip
@@ -1897,7 +1897,7 @@ batadv_tt_global_dump_bucket(struct sk_buff *msg, u32 portid, u32 seq,
  */
 int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb)
 {
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 	struct batadv_priv *bat_priv;
 	struct batadv_hard_iface *primary_if = NULL;
 	struct batadv_hashtable *hash;
@@ -1908,11 +1908,11 @@ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb)
 	int sub = cb->args[2];
 	int portid = NETLINK_CB(cb->skb).portid;
 
-	soft_iface = batadv_netlink_get_softif(cb);
-	if (IS_ERR(soft_iface))
-		return PTR_ERR(soft_iface);
+	mesh_iface = batadv_netlink_get_meshif(cb);
+	if (IS_ERR(mesh_iface))
+		return PTR_ERR(mesh_iface);
 
-	bat_priv = netdev_priv(soft_iface);
+	bat_priv = netdev_priv(mesh_iface);
 
 	primary_if = batadv_primary_if_get_selected(bat_priv);
 	if (!primary_if || primary_if->if_status != BATADV_IF_ACTIVE) {
@@ -1937,7 +1937,7 @@ int batadv_tt_global_dump(struct sk_buff *msg, struct netlink_callback *cb)
 
  out:
 	batadv_hardif_put(primary_if);
-	dev_put(soft_iface);
+	dev_put(mesh_iface);
 
 	cb->args[0] = bucket;
 	cb->args[1] = idx;
@@ -1990,7 +1990,7 @@ batadv_tt_global_del_orig_list(struct batadv_tt_global_entry *tt_global_entry)
 
 /**
  * batadv_tt_global_del_orig_node() - remove orig_node from a global tt entry
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_global_entry: the global entry to remove the orig_node from
  * @orig_node: the originator announcing the client
  * @message: message to append to the log on deletion
@@ -2069,7 +2069,7 @@ batadv_tt_global_del_roaming(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_global_del() - remove a client from the global table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: an originator serving this client
  * @addr: the mac address of the client
  * @vid: VLAN identifier
@@ -2134,7 +2134,7 @@ static void batadv_tt_global_del(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_global_del_orig() - remove all the TT global entries belonging to
  *  the given originator matching the provided vid
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the originator owning the entries to remove
  * @match_vid: the VLAN identifier to match. If negative all the entries will be
  *  removed
@@ -2305,7 +2305,7 @@ _batadv_is_ap_isolated(struct batadv_tt_local_entry *tt_local_entry,
 
 /**
  * batadv_transtable_search() - get the mesh destination for a given client
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @src: mac address of the source client
  * @addr: mac address of the destination client
  * @vid: VLAN identifier
@@ -2364,7 +2364,7 @@ struct batadv_orig_node *batadv_transtable_search(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_global_crc() - calculates the checksum of the local table belonging
  *  to the given orig_node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: originator for which the CRC should be computed
  * @vid: VLAN identifier for which the CRC32 has to be computed
  *
@@ -2458,7 +2458,7 @@ static u32 batadv_tt_global_crc(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_local_crc() - calculates the checksum of the local table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @vid: VLAN identifier for which the CRC32 has to be computed
  *
  * For details about the computation, please refer to the documentation for
@@ -2593,7 +2593,7 @@ static void batadv_tt_req_purge(struct batadv_priv *bat_priv)
 
 /**
  * batadv_tt_req_node_new() - search and possibly create a tt_req_node object
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node this request is being issued for
  *
  * Return: the pointer to the new tt_req_node struct if no request
@@ -2689,7 +2689,7 @@ static bool batadv_tt_global_valid(const void *entry_ptr,
 /**
  * batadv_tt_tvlv_generate() - fill the tvlv buff with the tt entries from the
  *  specified tt hash
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @hash: hash table containing the tt entries
  * @tt_len: expected tvlv tt data buffer length in number of bytes
  * @tvlv_buff: pointer to the buffer to fill with the TT data
@@ -2810,15 +2810,15 @@ static bool batadv_tt_global_check_crc(struct batadv_orig_node *orig_node,
 
 /**
  * batadv_tt_local_update_crc() - update all the local CRCs
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 static void batadv_tt_local_update_crc(struct batadv_priv *bat_priv)
 {
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 
 	/* recompute the global CRC for each VLAN */
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(vlan, &bat_priv->softif_vlan_list, list) {
+	hlist_for_each_entry_rcu(vlan, &bat_priv->meshif_vlan_list, list) {
 		vlan->tt.crc = batadv_tt_local_crc(bat_priv, vlan->vid);
 	}
 	rcu_read_unlock();
@@ -2826,7 +2826,7 @@ static void batadv_tt_local_update_crc(struct batadv_priv *bat_priv)
 
 /**
  * batadv_tt_global_update_crc() - update all the global CRCs for this orig_node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the orig_node for which the CRCs have to be updated
  */
 static void batadv_tt_global_update_crc(struct batadv_priv *bat_priv,
@@ -2853,7 +2853,7 @@ static void batadv_tt_global_update_crc(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_tt_request() - send a TT Request message to a given node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @dst_orig_node: the destination of the message
  * @ttvn: the version number that the source of the message is looking for
  * @tt_vlan: pointer to the first tvlv VLAN object to request
@@ -2938,7 +2938,7 @@ static bool batadv_send_tt_request(struct batadv_priv *bat_priv,
 /**
  * batadv_send_other_tt_response() - send reply to tt request concerning another
  *  node's translation table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_data: tt data containing the tt request information
  * @req_src: mac address of tt request sender
  * @req_dst: mac address of tt request recipient
@@ -3029,7 +3029,7 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv,
 	/* Don't send the response, if larger than fragmented packet. */
 	tt_len = sizeof(struct batadv_unicast_tvlv_packet) + tvlv_len;
 	if (tt_len > atomic_read(&bat_priv->packet_size_max)) {
-		net_ratelimited_function(batadv_info, bat_priv->soft_iface,
+		net_ratelimited_function(batadv_info, bat_priv->mesh_iface,
 					 "Ignoring TT_REQUEST from %pM; Response size exceeds max packet size.\n",
 					 res_dst_orig_node->orig);
 		goto out;
@@ -3068,7 +3068,7 @@ static bool batadv_send_other_tt_response(struct batadv_priv *bat_priv,
 /**
  * batadv_send_my_tt_response() - send reply to tt request concerning this
  *  node's translation table
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_data: tt data containing the tt request information
  * @req_src: mac address of tt request sender
  *
@@ -3185,7 +3185,7 @@ static bool batadv_send_my_tt_response(struct batadv_priv *bat_priv,
 
 /**
  * batadv_send_tt_response() - send reply to tt request
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_data: tt data containing the tt request information
  * @req_src: mac address of tt request sender
  * @req_dst: mac address of tt request recipient
@@ -3280,7 +3280,7 @@ static void batadv_tt_update_changes(struct batadv_priv *bat_priv,
 
 /**
  * batadv_is_my_client() - check if a client is served by the local node
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client to check
  * @vid: VLAN identifier
  *
@@ -3309,7 +3309,7 @@ bool batadv_is_my_client(struct batadv_priv *bat_priv, const u8 *addr,
 
 /**
  * batadv_handle_tt_response() - process incoming tt reply
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tt_data: tt data containing the tt request information
  * @resp_src: mac address of tt reply sender
  * @num_entries: number of tt change entries appended to the tt data
@@ -3397,7 +3397,7 @@ static void batadv_tt_roam_purge(struct batadv_priv *bat_priv)
 
 /**
  * batadv_tt_check_roam_count() - check if a client has roamed too frequently
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @client: mac address of the roaming client
  *
  * This function checks whether the client already reached the
@@ -3452,7 +3452,7 @@ static bool batadv_tt_check_roam_count(struct batadv_priv *bat_priv, u8 *client)
 
 /**
  * batadv_send_roam_adv() - send a roaming advertisement message
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @client: mac address of the roaming client
  * @vid: VLAN identifier
  * @orig_node: message destination
@@ -3516,8 +3516,8 @@ static void batadv_tt_purge(struct work_struct *work)
 }
 
 /**
- * batadv_tt_free() - Free translation table of soft interface
- * @bat_priv: the bat priv with all the soft interface information
+ * batadv_tt_free() - Free translation table of mesh interface
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_tt_free(struct batadv_priv *bat_priv)
 {
@@ -3540,7 +3540,7 @@ void batadv_tt_free(struct batadv_priv *bat_priv)
 /**
  * batadv_tt_local_set_flags() - set or unset the specified flags on the local
  *  table and possibly count them in the TT size
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @flags: the flag to switch
  * @enable: whether to set or unset the flag
  * @count: whether to increase the TT size by the number of changed entries
@@ -3626,7 +3626,7 @@ static void batadv_tt_local_purge_pending_clients(struct batadv_priv *bat_priv)
 /**
  * batadv_tt_local_commit_changes_nolock() - commit all pending local tt changes
  *  which have been queued in the time since the last commit
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Caller must hold tt->commit_lock.
  */
@@ -3659,7 +3659,7 @@ static void batadv_tt_local_commit_changes_nolock(struct batadv_priv *bat_priv)
 /**
  * batadv_tt_local_commit_changes() - commit all pending local tt changes which
  *  have been queued in the time since the last commit
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  */
 void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv)
 {
@@ -3670,7 +3670,7 @@ void batadv_tt_local_commit_changes(struct batadv_priv *bat_priv)
 
 /**
  * batadv_is_ap_isolated() - Check if packet from upper layer should be dropped
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @src: source mac address of packet
  * @dst: destination mac address of packet
  * @vid: vlan id of packet
@@ -3682,10 +3682,10 @@ bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, u8 *src, u8 *dst,
 {
 	struct batadv_tt_local_entry *tt_local_entry;
 	struct batadv_tt_global_entry *tt_global_entry;
-	struct batadv_softif_vlan *vlan;
+	struct batadv_meshif_vlan *vlan;
 	bool ret = false;
 
-	vlan = batadv_softif_vlan_get(bat_priv, vid);
+	vlan = batadv_meshif_vlan_get(bat_priv, vid);
 	if (!vlan)
 		return false;
 
@@ -3707,14 +3707,14 @@ bool batadv_is_ap_isolated(struct batadv_priv *bat_priv, u8 *src, u8 *dst,
 local_entry_put:
 	batadv_tt_local_entry_put(tt_local_entry);
 vlan_put:
-	batadv_softif_vlan_put(vlan);
+	batadv_meshif_vlan_put(vlan);
 	return ret;
 }
 
 /**
  * batadv_tt_update_orig() - update global translation table with new tt
  *  information received via ogms
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: the orig_node of the ogm
  * @tt_buff: pointer to the first tvlv VLAN entry
  * @tt_num_vlan: number of tvlv VLAN entries
@@ -3798,7 +3798,7 @@ static void batadv_tt_update_orig(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_global_client_is_roaming() - check if a client is marked as roaming
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client to check
  * @vid: VLAN identifier
  *
@@ -3824,7 +3824,7 @@ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_local_client_is_roaming() - tells whether the client is roaming
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the local client to query
  * @vid: VLAN identifier
  *
@@ -3850,7 +3850,7 @@ bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_add_temporary_global_entry() - Add temporary entry to global TT
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig_node: orig node which the temporary entry should be associated with
  * @addr: mac address of the client
  * @vid: VLAN id of the new temporary global translation table
@@ -3883,14 +3883,14 @@ bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_local_resize_to_mtu() - resize the local translation table fit the
  *  maximum packet size that can be transported through the mesh
- * @soft_iface: netdev struct of the mesh interface
+ * @mesh_iface: netdev struct of the mesh interface
  *
  * Remove entries older than 'timeout' and half timeout if more entries need
  * to be removed.
  */
-void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface)
+void batadv_tt_local_resize_to_mtu(struct net_device *mesh_iface)
 {
-	struct batadv_priv *bat_priv = netdev_priv(soft_iface);
+	struct batadv_priv *bat_priv = netdev_priv(mesh_iface);
 	int packet_size_max = atomic_read(&bat_priv->packet_size_max);
 	int table_size, timeout = BATADV_TT_LOCAL_TIMEOUT / 2;
 	bool reduced = false;
@@ -3907,7 +3907,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface)
 
 		timeout /= 2;
 		reduced = true;
-		net_ratelimited_function(batadv_info, soft_iface,
+		net_ratelimited_function(batadv_info, mesh_iface,
 					 "Forced to purge local tt entries to fit new maximum fragment MTU (%i)\n",
 					 packet_size_max);
 	}
@@ -3923,7 +3923,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface)
 
 /**
  * batadv_tt_tvlv_ogm_handler_v1() - process incoming tt tvlv container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @orig: the orig_node of the ogm
  * @flags: flags indicating the tvlv state (see batadv_tvlv_handler_flags)
  * @tvlv_value: tvlv buffer containing the gateway data
@@ -3962,7 +3962,7 @@ static void batadv_tt_tvlv_ogm_handler_v1(struct batadv_priv *bat_priv,
 /**
  * batadv_tt_tvlv_unicast_handler_v1() - process incoming (unicast) tt tvlv
  *  container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @src: mac address of tt tvlv sender
  * @dst: mac address of tt tvlv recipient
  * @tvlv_value: tvlv buffer containing the tt data
@@ -4044,7 +4044,7 @@ static int batadv_tt_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv,
 /**
  * batadv_roam_tvlv_unicast_handler_v1() - process incoming tt roam tvlv
  *  container
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @src: mac address of tt tvlv sender
  * @dst: mac address of tt tvlv recipient
  * @tvlv_value: tvlv buffer containing the tt data
@@ -4093,7 +4093,7 @@ static int batadv_roam_tvlv_unicast_handler_v1(struct batadv_priv *bat_priv,
 
 /**
  * batadv_tt_init() - initialise the translation table internals
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Return: 0 on success or negative error number in case of failure.
  */
@@ -4131,7 +4131,7 @@ int batadv_tt_init(struct batadv_priv *bat_priv)
 
 /**
  * batadv_tt_global_is_isolated() - check if a client is marked as isolated
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @addr: the mac address of the client
  * @vid: the identifier of the VLAN where this client is connected
  *
diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h
index d18740d9a22b6..618d9dbca5eac 100644
--- a/net/batman-adv/translation-table.h
+++ b/net/batman-adv/translation-table.h
@@ -16,7 +16,7 @@
 #include <linux/types.h>
 
 int batadv_tt_init(struct batadv_priv *bat_priv);
-bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,
+bool batadv_tt_local_add(struct net_device *mesh_iface, const u8 *addr,
 			 unsigned short vid, int ifindex, u32 mark);
 u16 batadv_tt_local_remove(struct batadv_priv *bat_priv,
 			   const u8 *addr, unsigned short vid,
@@ -45,7 +45,7 @@ bool batadv_tt_global_client_is_roaming(struct batadv_priv *bat_priv,
 					u8 *addr, unsigned short vid);
 bool batadv_tt_local_client_is_roaming(struct batadv_priv *bat_priv,
 				       u8 *addr, unsigned short vid);
-void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface);
+void batadv_tt_local_resize_to_mtu(struct net_device *mesh_iface);
 bool batadv_tt_add_temporary_global_entry(struct batadv_priv *bat_priv,
 					  struct batadv_orig_node *orig_node,
 					  const unsigned char *addr,
diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c
index 2a583215d439b..76dff1f9c559a 100644
--- a/net/batman-adv/tvlv.c
+++ b/net/batman-adv/tvlv.c
@@ -59,7 +59,7 @@ static void batadv_tvlv_handler_put(struct batadv_tvlv_handler *tvlv_handler)
 /**
  * batadv_tvlv_handler_get() - retrieve tvlv handler from the tvlv handler list
  *  based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: tvlv handler type to look for
  * @version: tvlv handler version to look for
  *
@@ -118,7 +118,7 @@ static void batadv_tvlv_container_put(struct batadv_tvlv_container *tvlv)
 /**
  * batadv_tvlv_container_get() - retrieve tvlv container from the tvlv container
  *  list based on the provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: tvlv container type to look for
  * @version: tvlv container version to look for
  *
@@ -152,7 +152,7 @@ batadv_tvlv_container_get(struct batadv_priv *bat_priv, u8 type, u8 version)
 /**
  * batadv_tvlv_container_list_size() - calculate the size of the tvlv container
  *  list entries
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  *
  * Has to be called with the appropriate locks being acquired
  * (tvlv.container_list_lock).
@@ -177,7 +177,7 @@ static u16 batadv_tvlv_container_list_size(struct batadv_priv *bat_priv)
 /**
  * batadv_tvlv_container_remove() - remove tvlv container from the tvlv
  *  container list
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tvlv: the to be removed tvlv container
  *
  * Has to be called with the appropriate locks being acquired
@@ -201,7 +201,7 @@ static void batadv_tvlv_container_remove(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_container_unregister() - unregister tvlv container based on the
  *  provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: tvlv container type to unregister
  * @version: tvlv container type to unregister
  */
@@ -219,7 +219,7 @@ void batadv_tvlv_container_unregister(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_container_register() - register tvlv type, version and content
  *  to be propagated with each (primary interface) OGM
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: tvlv container type
  * @version: tvlv container version
  * @tvlv_value: tvlv container content
@@ -297,7 +297,7 @@ static bool batadv_tvlv_realloc_packet_buff(unsigned char **packet_buff,
 /**
  * batadv_tvlv_container_ogm_append() - append tvlv container content to given
  *  OGM packet buffer
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @packet_buff: ogm packet buffer
  * @packet_buff_len: ogm packet buffer size including ogm header and tvlv
  *  content
@@ -350,7 +350,7 @@ u16 batadv_tvlv_container_ogm_append(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_call_handler() - parse the given tvlv buffer to call the
  *  appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @tvlv_handler: tvlv callback function handling the tvlv content
  * @packet_type: indicates for which packet type the TVLV handler is called
  * @orig_node: orig node emitting the ogm packet
@@ -421,7 +421,7 @@ static int batadv_tvlv_call_handler(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_containers_process() - parse the given tvlv buffer to call the
  *  appropriate handlers
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @packet_type: indicates for which packet type the TVLV handler is called
  * @orig_node: orig node emitting the ogm packet
  * @skb: the skb the TVLV handler is called for
@@ -490,7 +490,7 @@ int batadv_tvlv_containers_process(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_ogm_receive() - process an incoming ogm and call the appropriate
  *  handlers
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @batadv_ogm_packet: ogm packet containing the tvlv containers
  * @orig_node: orig node emitting the ogm packet
  */
@@ -518,7 +518,7 @@ void batadv_tvlv_ogm_receive(struct batadv_priv *bat_priv,
  * batadv_tvlv_handler_register() - register tvlv handler based on the provided
  *  type and version (both need to match) for ogm tvlv payload and/or unicast
  *  payload
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @optr: ogm tvlv handler callback function. This function receives the orig
  *  node, flags and the tvlv content as argument to process.
  * @uptr: unicast tvlv handler callback function. This function receives the
@@ -583,7 +583,7 @@ void batadv_tvlv_handler_register(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_handler_unregister() - unregister tvlv handler based on the
  *  provided type and version (both need to match)
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @type: tvlv handler type to be unregistered
  * @version: tvlv handler version to be unregistered
  */
@@ -606,7 +606,7 @@ void batadv_tvlv_handler_unregister(struct batadv_priv *bat_priv,
 /**
  * batadv_tvlv_unicast_send() - send a unicast packet with tvlv payload to the
  *  specified host
- * @bat_priv: the bat priv with all the soft interface information
+ * @bat_priv: the bat priv with all the mesh interface information
  * @src: source mac address of the unicast packet
  * @dst: destination mac address of the unicast packet
  * @type: tvlv type
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index b3b4f71f6dec4..b222f8a80ed92 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -199,13 +199,13 @@ struct batadv_hard_iface {
 	struct packet_type batman_adv_ptype;
 
 	/**
-	 * @soft_iface: the batman-adv interface which uses this network
+	 * @mesh_iface: the batman-adv interface which uses this network
 	 *  interface
 	 */
-	struct net_device *soft_iface;
+	struct net_device *mesh_iface;
 
-	/** @softif_dev_tracker: device tracker for @soft_iface */
-	netdevice_tracker softif_dev_tracker;
+	/** @meshif_dev_tracker: device tracker for @mesh_iface */
+	netdevice_tracker meshif_dev_tracker;
 
 	/** @rcu: struct used for freeing in an RCU-safe manner */
 	struct rcu_head rcu;
@@ -493,7 +493,7 @@ struct batadv_orig_node {
 	/** @hash_entry: hlist node for &batadv_priv.orig_hash */
 	struct hlist_node hash_entry;
 
-	/** @bat_priv: pointer to soft_iface this orig node belongs to */
+	/** @bat_priv: pointer to mesh_iface this orig node belongs to */
 	struct batadv_priv *bat_priv;
 
 	/** @bcast_seqno_lock: lock protecting bcast_bits & last_bcast_seqno */
@@ -905,13 +905,13 @@ enum batadv_counters {
 
 	/**
 	 * @BATADV_CNT_MCAST_RX_LOCAL: counter for received batman-adv multicast
-	 *  packets which were forwarded to the local soft interface
+	 *  packets which were forwarded to the local mesh interface
 	 */
 	BATADV_CNT_MCAST_RX_LOCAL,
 
 	/**
 	 * @BATADV_CNT_MCAST_RX_LOCAL_BYTES: bytes counter for received
-	 *  batman-adv multicast packets which were forwarded to the local soft
+	 *  batman-adv multicast packets which were forwarded to the local mesh
 	 *  interface
 	 */
 	BATADV_CNT_MCAST_RX_LOCAL_BYTES,
@@ -1247,7 +1247,7 @@ struct batadv_mcast_mla_flags {
 	/** @enabled: whether the multicast tvlv is currently enabled */
 	unsigned char enabled:1;
 
-	/** @bridged: whether the soft interface has a bridge on top */
+	/** @bridged: whether the mesh interface has a bridge on top */
 	unsigned char bridged:1;
 
 	/** @tvlv_flags: the flags we have last sent in our mcast tvlv */
@@ -1383,7 +1383,7 @@ struct batadv_priv_nc {
 	/**
 	 * @decoding_hash: Hash table used to buffer skbs that might be needed
 	 *  to decode a received coded skb. The buffer is used for 1) skbs
-	 *  arriving on the soft-interface; 2) skbs overheard on the
+	 *  arriving on the mesh-interface; 2) skbs overheard on the
 	 *  hard-interface; and 3) skbs forwarded by batman-adv.
 	 */
 	struct batadv_hashtable *decoding_hash;
@@ -1536,9 +1536,9 @@ struct batadv_tp_vars {
 };
 
 /**
- * struct batadv_softif_vlan - per VLAN attributes set
+ * struct batadv_meshif_vlan - per VLAN attributes set
  */
-struct batadv_softif_vlan {
+struct batadv_meshif_vlan {
 	/** @bat_priv: pointer to the mesh object */
 	struct batadv_priv *bat_priv;
 
@@ -1551,7 +1551,7 @@ struct batadv_softif_vlan {
 	/** @tt: TT private attributes (VLAN specific) */
 	struct batadv_vlan_tt tt;
 
-	/** @list: list node for &bat_priv.softif_vlan_list */
+	/** @list: list node for &bat_priv.meshif_vlan_list */
 	struct hlist_node list;
 
 	/**
@@ -1564,7 +1564,7 @@ struct batadv_softif_vlan {
 };
 
 /**
- * struct batadv_priv_bat_v - B.A.T.M.A.N. V per soft-interface private data
+ * struct batadv_priv_bat_v - B.A.T.M.A.N. V per mesh-interface private data
  */
 struct batadv_priv_bat_v {
 	/** @ogm_buff: buffer holding the OGM packet */
@@ -1593,8 +1593,8 @@ struct batadv_priv {
 	 */
 	atomic_t mesh_state;
 
-	/** @soft_iface: net device which holds this struct as private data */
-	struct net_device *soft_iface;
+	/** @mesh_iface: net device which holds this struct as private data */
+	struct net_device *mesh_iface;
 
 	/**
 	 * @mtu_set_by_user: MTU was set once by user
@@ -1743,13 +1743,13 @@ struct batadv_priv {
 	struct batadv_algo_ops *algo_ops;
 
 	/**
-	 * @softif_vlan_list: a list of softif_vlan structs, one per VLAN
+	 * @meshif_vlan_list: a list of meshif_vlan structs, one per VLAN
 	 *  created on top of the mesh interface represented by this object
 	 */
-	struct hlist_head softif_vlan_list;
+	struct hlist_head meshif_vlan_list;
 
-	/** @softif_vlan_list_lock: lock protecting softif_vlan_list */
-	spinlock_t softif_vlan_list_lock;
+	/** @meshif_vlan_list_lock: lock protecting meshif_vlan_list */
+	spinlock_t meshif_vlan_list_lock;
 
 #ifdef CONFIG_BATMAN_ADV_BLA
 	/** @bla: bridge loop avoidance data */
@@ -1786,7 +1786,7 @@ struct batadv_priv {
 #endif /* CONFIG_BATMAN_ADV_NC */
 
 #ifdef CONFIG_BATMAN_ADV_BATMAN_V
-	/** @bat_v: B.A.T.M.A.N. V per soft-interface private data */
+	/** @bat_v: B.A.T.M.A.N. V per mesh-interface private data */
 	struct batadv_priv_bat_v bat_v;
 #endif
 };
@@ -1809,7 +1809,7 @@ struct batadv_bla_backbone_gw {
 	/** @hash_entry: hlist node for &batadv_priv_bla.backbone_hash */
 	struct hlist_node hash_entry;
 
-	/** @bat_priv: pointer to soft_iface this backbone gateway belongs to */
+	/** @bat_priv: pointer to mesh_iface this backbone gateway belongs to */
 	struct batadv_priv *bat_priv;
 
 	/** @lasttime: last time we heard of this backbone gw */
@@ -1914,8 +1914,8 @@ struct batadv_tt_local_entry {
 	/** @last_seen: timestamp used for purging stale tt local entries */
 	unsigned long last_seen;
 
-	/** @vlan: soft-interface vlan of the entry */
-	struct batadv_softif_vlan *vlan;
+	/** @vlan: mesh-interface vlan of the entry */
+	struct batadv_meshif_vlan *vlan;
 };
 
 /**

From 434becf57bdc89f939db635ed3337b9d1da5967e Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 17:04:10 +0100
Subject: [PATCH 1012/2753] batman-adv: Limit number of aggregated packets
 directly

The currently selected size in BATADV_MAX_AGGREGATION_BYTES (512) is chosen
such that the number of possible aggregated packets is lower than 32. This
number must be limited so that the type of
batadv_forw_packet->direct_link_flags has enough bits to represent each
packet (with the size of at least 24 bytes).

This requirement is better implemented in code instead of having it inside
a comment.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 4 ++++
 net/batman-adv/main.h       | 3 ---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 8513f6661dd10..b715f7343ffdd 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -446,6 +446,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	struct batadv_ogm_packet *batadv_ogm_packet;
 	int aggregated_bytes = forw_packet->packet_len + packet_len;
 	struct batadv_hard_iface *primary_if = NULL;
+	u8 packet_num = forw_packet->num_packets + 1;
 	bool res = false;
 	unsigned long aggregation_end_time;
 
@@ -468,6 +469,9 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES)
 		return false;
 
+	if (packet_num >= BITS_PER_TYPE(forw_packet->direct_link_flags))
+		return false;
+
 	/* packet is not leaving on the same interface. */
 	if (forw_packet->if_outgoing != if_outgoing)
 		return false;
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index 5adefdfc69bcd..c08c96b5b8b13 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -104,9 +104,6 @@
  */
 #define BATADV_TQ_SIMILARITY_THRESHOLD 50
 
-/* should not be bigger than 512 bytes or change the size of
- * forw_packet->direct_link_flags
- */
 #define BATADV_MAX_AGGREGATION_BYTES 512
 #define BATADV_MAX_AGGREGATION_MS 100
 

From 77405977f1872249cb2bea69214c6b779dc06065 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 17:04:11 +0100
Subject: [PATCH 1013/2753] batman-adv: Switch to bitmap helper for aggregation
 handling

The aggregation code duplicates code which already exists in the the bitops
and bitmap helper. By switching to the bitmap helpers, operating on larger
aggregations becomes possible without touching the different portions of
the code which read/modify direct_link_flags.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 19 +++++++++----------
 net/batman-adv/main.h       |  1 +
 net/batman-adv/types.h      |  2 +-
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index b715f7343ffdd..87c1af540457b 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -355,7 +355,7 @@ static void batadv_iv_ogm_send_to_if(struct batadv_forw_packet *forw_packet,
 		/* we might have aggregated direct link packets with an
 		 * ordinary base packet
 		 */
-		if (forw_packet->direct_link_flags & BIT(packet_num) &&
+		if (test_bit(packet_num, forw_packet->direct_link_flags) &&
 		    forw_packet->if_incoming == hard_iface)
 			batadv_ogm_packet->flags |= BATADV_DIRECTLINK;
 		else
@@ -460,6 +460,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	 * - the send time is within our MAX_AGGREGATION_MS time
 	 * - the resulting packet won't be bigger than
 	 *   MAX_AGGREGATION_BYTES
+	 * - the number of packets is lower than MAX_AGGREGATION_PACKETS
 	 * otherwise aggregation is not possible
 	 */
 	if (!time_before(send_time, forw_packet->send_time) ||
@@ -469,7 +470,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES)
 		return false;
 
-	if (packet_num >= BITS_PER_TYPE(forw_packet->direct_link_flags))
+	if (packet_num >= BATADV_MAX_AGGREGATION_PACKETS)
 		return false;
 
 	/* packet is not leaving on the same interface. */
@@ -578,12 +579,13 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 	memcpy(skb_buff, packet_buff, packet_len);
 
 	forw_packet_aggr->own = own_packet;
-	forw_packet_aggr->direct_link_flags = BATADV_NO_FLAGS;
+	bitmap_zero(forw_packet_aggr->direct_link_flags,
+		    BATADV_MAX_AGGREGATION_PACKETS);
 	forw_packet_aggr->send_time = send_time;
 
 	/* save packet direct link flag status */
 	if (direct_link)
-		forw_packet_aggr->direct_link_flags |= 1;
+		set_bit(0, forw_packet_aggr->direct_link_flags);
 
 	INIT_DELAYED_WORK(&forw_packet_aggr->delayed_work,
 			  batadv_iv_send_outstanding_bat_ogm_packet);
@@ -596,17 +598,14 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr,
 				    const unsigned char *packet_buff,
 				    int packet_len, bool direct_link)
 {
-	unsigned long new_direct_link_flag;
-
 	skb_put_data(forw_packet_aggr->skb, packet_buff, packet_len);
 	forw_packet_aggr->packet_len += packet_len;
 	forw_packet_aggr->num_packets++;
 
 	/* save packet direct link flag status */
-	if (direct_link) {
-		new_direct_link_flag = BIT(forw_packet_aggr->num_packets);
-		forw_packet_aggr->direct_link_flags |= new_direct_link_flag;
-	}
+	if (direct_link)
+		set_bit(forw_packet_aggr->num_packets,
+			forw_packet_aggr->direct_link_flags);
 }
 
 /**
diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h
index c08c96b5b8b13..67af435ee04e1 100644
--- a/net/batman-adv/main.h
+++ b/net/batman-adv/main.h
@@ -104,6 +104,7 @@
  */
 #define BATADV_TQ_SIMILARITY_THRESHOLD 50
 
+#define BATADV_MAX_AGGREGATION_PACKETS 32
 #define BATADV_MAX_AGGREGATION_BYTES 512
 #define BATADV_MAX_AGGREGATION_MS 100
 
diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h
index b222f8a80ed92..0ca0fc072fc9c 100644
--- a/net/batman-adv/types.h
+++ b/net/batman-adv/types.h
@@ -2139,7 +2139,7 @@ struct batadv_forw_packet {
 	u16 packet_len;
 
 	/** @direct_link_flags: direct link flags for aggregated OGM packets */
-	u32 direct_link_flags;
+	DECLARE_BITMAP(direct_link_flags, BATADV_MAX_AGGREGATION_PACKETS);
 
 	/** @num_packets: counter for aggregated OGMv1 packets */
 	u8 num_packets;

From 0db110059e7900c3c197281e2ed11ff08484e3ed Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 17:04:12 +0100
Subject: [PATCH 1014/2753] batman-adv: Use actual packet count for aggregated
 packets

The batadv_forw_packet->num_packets didn't store the number of packets but
the the number of packets - 1. This didn't had any effects on the actual
handling of aggregates but can easily be a source of confusion when reading
the code.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 5 +++--
 net/batman-adv/send.c       | 2 +-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index 87c1af540457b..a20d7f3004c11 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -446,7 +446,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	struct batadv_ogm_packet *batadv_ogm_packet;
 	int aggregated_bytes = forw_packet->packet_len + packet_len;
 	struct batadv_hard_iface *primary_if = NULL;
-	u8 packet_num = forw_packet->num_packets + 1;
+	u8 packet_num = forw_packet->num_packets;
 	bool res = false;
 	unsigned long aggregation_end_time;
 
@@ -600,12 +600,13 @@ static void batadv_iv_ogm_aggregate(struct batadv_forw_packet *forw_packet_aggr,
 {
 	skb_put_data(forw_packet_aggr->skb, packet_buff, packet_len);
 	forw_packet_aggr->packet_len += packet_len;
-	forw_packet_aggr->num_packets++;
 
 	/* save packet direct link flag status */
 	if (direct_link)
 		set_bit(forw_packet_aggr->num_packets,
 			forw_packet_aggr->direct_link_flags);
+
+	forw_packet_aggr->num_packets++;
 }
 
 /**
diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c
index 85478fdc8ce88..735ac80778219 100644
--- a/net/batman-adv/send.c
+++ b/net/batman-adv/send.c
@@ -532,7 +532,7 @@ batadv_forw_packet_alloc(struct batadv_hard_iface *if_incoming,
 	forw_packet->queue_left = queue_left;
 	forw_packet->if_incoming = if_incoming;
 	forw_packet->if_outgoing = if_outgoing;
-	forw_packet->num_packets = 0;
+	forw_packet->num_packets = 1;
 
 	return forw_packet;
 

From e4aa3412f632c70276b770fb3efb5b441c11f607 Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 2 Feb 2025 17:04:14 +0100
Subject: [PATCH 1015/2753] batman-adv: Limit aggregation size to outgoing MTU

If a B.A.T.M.A.N. IV aggregated OGM was prepared, it was always assumed
that 512 bytes (BATADV_MAX_AGGREGATION_BYTES) can be transmitted. But the
outgoing MTU might be too small for these 512 bytes and the aggregation
size must be adjusted in this case. Otherwise, the aggregates will cause
unnecessary packet loss.

For now, the non-aggregated packet length is not touched.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/bat_iv_ogm.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c
index a20d7f3004c11..7b4f659612a38 100644
--- a/net/batman-adv/bat_iv_ogm.c
+++ b/net/batman-adv/bat_iv_ogm.c
@@ -23,6 +23,7 @@
 #include <linux/kref.h>
 #include <linux/list.h>
 #include <linux/lockdep.h>
+#include <linux/minmax.h>
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
@@ -444,22 +445,26 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 			    const struct batadv_forw_packet *forw_packet)
 {
 	struct batadv_ogm_packet *batadv_ogm_packet;
-	int aggregated_bytes = forw_packet->packet_len + packet_len;
+	unsigned int aggregated_bytes = forw_packet->packet_len + packet_len;
 	struct batadv_hard_iface *primary_if = NULL;
 	u8 packet_num = forw_packet->num_packets;
 	bool res = false;
 	unsigned long aggregation_end_time;
+	unsigned int max_bytes;
 
 	batadv_ogm_packet = (struct batadv_ogm_packet *)forw_packet->skb->data;
 	aggregation_end_time = send_time;
 	aggregation_end_time += msecs_to_jiffies(BATADV_MAX_AGGREGATION_MS);
 
+	max_bytes = min_t(unsigned int, if_outgoing->net_dev->mtu,
+			  BATADV_MAX_AGGREGATION_BYTES);
+
 	/* we can aggregate the current packet to this aggregated packet
 	 * if:
 	 *
 	 * - the send time is within our MAX_AGGREGATION_MS time
 	 * - the resulting packet won't be bigger than
-	 *   MAX_AGGREGATION_BYTES
+	 *   MAX_AGGREGATION_BYTES and MTU of the outgoing interface
 	 * - the number of packets is lower than MAX_AGGREGATION_PACKETS
 	 * otherwise aggregation is not possible
 	 */
@@ -467,7 +472,7 @@ batadv_iv_ogm_can_aggregate(const struct batadv_ogm_packet *new_bat_ogm_packet,
 	    !time_after_eq(aggregation_end_time, forw_packet->send_time))
 		return false;
 
-	if (aggregated_bytes > BATADV_MAX_AGGREGATION_BYTES)
+	if (aggregated_bytes > max_bytes)
 		return false;
 
 	if (packet_num >= BATADV_MAX_AGGREGATION_PACKETS)
@@ -552,9 +557,9 @@ static void batadv_iv_ogm_aggregate_new(const unsigned char *packet_buff,
 	unsigned int skb_size;
 	atomic_t *queue_left = own_packet ? NULL : &bat_priv->batman_queue_left;
 
-	if (atomic_read(&bat_priv->aggregated_ogms) &&
-	    packet_len < BATADV_MAX_AGGREGATION_BYTES)
-		skb_size = BATADV_MAX_AGGREGATION_BYTES;
+	if (atomic_read(&bat_priv->aggregated_ogms))
+		skb_size = max_t(unsigned int, BATADV_MAX_AGGREGATION_BYTES,
+				 packet_len);
 	else
 		skb_size = packet_len;
 

From 50cef76d5cb0e199cda19f026842560f6eedc4f7 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Thu, 23 Jan 2025 14:44:53 +0100
Subject: [PATCH 1016/2753] x86/microcode/AMD: Load only SHA256-checksummed
 patches

Load patches for which the driver carries a SHA256 checksum of the patch
blob.

This can be disabled by adding "microcode.amd_sha_check=off" on the
kernel cmdline. But it is highly NOT recommended.

Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
---
 arch/x86/Kconfig                         |   1 +
 arch/x86/kernel/cpu/microcode/amd.c      | 111 +++++-
 arch/x86/kernel/cpu/microcode/amd_shas.c | 444 +++++++++++++++++++++++
 3 files changed, 554 insertions(+), 2 deletions(-)
 create mode 100644 arch/x86/kernel/cpu/microcode/amd_shas.c

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index be2c311f5118d..0e27ebd7e36a9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1341,6 +1341,7 @@ config X86_REBOOTFIXUPS
 config MICROCODE
 	def_bool y
 	depends on CPU_SUP_AMD || CPU_SUP_INTEL
+	select CRYPTO_LIB_SHA256 if CPU_SUP_AMD
 
 config MICROCODE_INITRD32
 	def_bool y
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 31f90e129b083..95ac1c6a84fbe 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -23,14 +23,18 @@
 
 #include <linux/earlycpio.h>
 #include <linux/firmware.h>
+#include <linux/bsearch.h>
 #include <linux/uaccess.h>
 #include <linux/vmalloc.h>
 #include <linux/initrd.h>
 #include <linux/kernel.h>
 #include <linux/pci.h>
 
+#include <crypto/sha2.h>
+
 #include <asm/microcode.h>
 #include <asm/processor.h>
+#include <asm/cmdline.h>
 #include <asm/setup.h>
 #include <asm/cpu.h>
 #include <asm/msr.h>
@@ -145,6 +149,98 @@ ucode_path[] __maybe_unused = "kernel/x86/microcode/AuthenticAMD.bin";
  */
 static u32 bsp_cpuid_1_eax __ro_after_init;
 
+static bool sha_check = true;
+
+struct patch_digest {
+	u32 patch_id;
+	u8 sha256[SHA256_DIGEST_SIZE];
+};
+
+#include "amd_shas.c"
+
+static int cmp_id(const void *key, const void *elem)
+{
+	struct patch_digest *pd = (struct patch_digest *)elem;
+	u32 patch_id = *(u32 *)key;
+
+	if (patch_id == pd->patch_id)
+		return 0;
+	else if (patch_id < pd->patch_id)
+		return -1;
+	else
+		return 1;
+}
+
+static bool need_sha_check(u32 cur_rev)
+{
+	switch (cur_rev >> 8) {
+	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x83010: return cur_rev <= 0x830107c; break;
+	case 0x86001: return cur_rev <= 0x860010e; break;
+	case 0x86081: return cur_rev <= 0x8608108; break;
+	case 0x87010: return cur_rev <= 0x8701034; break;
+	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0011: return cur_rev <= 0xa0011da; break;
+	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa1011: return cur_rev <= 0xa101153; break;
+	case 0xa1012: return cur_rev <= 0xa10124e; break;
+	case 0xa1081: return cur_rev <= 0xa108109; break;
+	case 0xa2010: return cur_rev <= 0xa20102f; break;
+	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa6012: return cur_rev <= 0xa60120a; break;
+	case 0xa7041: return cur_rev <= 0xa704109; break;
+	case 0xa7052: return cur_rev <= 0xa705208; break;
+	case 0xa7080: return cur_rev <= 0xa708009; break;
+	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa002: return cur_rev <= 0xaa00218; break;
+	default: break;
+	}
+
+	pr_info("You should not be seeing this. Please send the following couple of lines to x86-<at>-kernel.org\n");
+	pr_info("CPUID(1).EAX: 0x%x, current revision: 0x%x\n", bsp_cpuid_1_eax, cur_rev);
+	return true;
+}
+
+static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsigned int len)
+{
+	struct patch_digest *pd = NULL;
+	u8 digest[SHA256_DIGEST_SIZE];
+	struct sha256_state s;
+	int i;
+
+	if (x86_family(bsp_cpuid_1_eax) < 0x17 ||
+	    x86_family(bsp_cpuid_1_eax) > 0x19)
+		return true;
+
+	if (!need_sha_check(cur_rev))
+		return true;
+
+	if (!sha_check)
+		return true;
+
+	pd = bsearch(&patch_id, phashes, ARRAY_SIZE(phashes), sizeof(struct patch_digest), cmp_id);
+	if (!pd) {
+		pr_err("No sha256 digest for patch ID: 0x%x found\n", patch_id);
+		return false;
+	}
+
+	sha256_init(&s);
+	sha256_update(&s, data, len);
+	sha256_final(&s, digest);
+
+	if (memcmp(digest, pd->sha256, sizeof(digest))) {
+		pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
+
+		for (i = 0; i < SHA256_DIGEST_SIZE; i++)
+			pr_cont("0x%x ", digest[i]);
+		pr_info("\n");
+
+		return false;
+	}
+
+	return true;
+}
+
 static u32 get_patch_level(void)
 {
 	u32 rev, dummy __always_unused;
@@ -497,6 +593,9 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
 {
 	unsigned long p_addr = (unsigned long)&mc->hdr.data_code;
 
+	if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
+		return -1;
+
 	native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
 
 	if (x86_family(bsp_cpuid_1_eax) == 0x17) {
@@ -571,8 +670,17 @@ void __init load_ucode_amd_bsp(struct early_load_data *ed, unsigned int cpuid_1_
 	struct cont_desc desc = { };
 	struct microcode_amd *mc;
 	struct cpio_data cp = { };
+	char buf[4];
 	u32 rev;
 
+	if (cmdline_find_option(boot_command_line, "microcode.amd_sha_check", buf, 4)) {
+		if (!strncmp(buf, "off", 3)) {
+			sha_check = false;
+			pr_warn_once("It is a very very bad idea to disable the blobs SHA check!\n");
+			add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+		}
+	}
+
 	bsp_cpuid_1_eax = cpuid_1_eax;
 
 	rev = get_patch_level();
@@ -902,8 +1010,7 @@ static int verify_and_add_patch(u8 family, u8 *fw, unsigned int leftover,
 }
 
 /* Scan the blob in @data and add microcode patches to the cache. */
-static enum ucode_state __load_microcode_amd(u8 family, const u8 *data,
-					     size_t size)
+static enum ucode_state __load_microcode_amd(u8 family, const u8 *data, size_t size)
 {
 	u8 *fw = (u8 *)data;
 	size_t offset;
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
new file mode 100644
index 0000000000000..2a1655b1fdd88
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -0,0 +1,444 @@
+/* Keep 'em sorted. */
+static const struct patch_digest phashes[] = {
+ { 0x8001227, {
+		0x99,0xc0,0x9b,0x2b,0xcc,0x9f,0x52,0x1b,
+		0x1a,0x5f,0x1d,0x83,0xa1,0x6c,0xc4,0x46,
+		0xe2,0x6c,0xda,0x73,0xfb,0x2d,0x23,0xa8,
+		0x77,0xdc,0x15,0x31,0x33,0x4a,0x46,0x18,
+	}
+ },
+ { 0x8001250, {
+		0xc0,0x0b,0x6b,0x19,0xfd,0x5c,0x39,0x60,
+		0xd5,0xc3,0x57,0x46,0x54,0xe4,0xd1,0xaa,
+		0xa8,0xf7,0x1f,0xa8,0x6a,0x60,0x3e,0xe3,
+		0x27,0x39,0x8e,0x53,0x30,0xf8,0x49,0x19,
+	}
+ },
+ { 0x800126e, {
+		0xf3,0x8b,0x2b,0xb6,0x34,0xe3,0xc8,0x2c,
+		0xef,0xec,0x63,0x6d,0xc8,0x76,0x77,0xb3,
+		0x25,0x5a,0xb7,0x52,0x8c,0x83,0x26,0xe6,
+		0x4c,0xbe,0xbf,0xe9,0x7d,0x22,0x6a,0x43,
+	}
+ },
+ { 0x800126f, {
+		0x2b,0x5a,0xf2,0x9c,0xdd,0xd2,0x7f,0xec,
+		0xec,0x96,0x09,0x57,0xb0,0x96,0x29,0x8b,
+		0x2e,0x26,0x91,0xf0,0x49,0x33,0x42,0x18,
+		0xdd,0x4b,0x65,0x5a,0xd4,0x15,0x3d,0x33,
+	}
+ },
+ { 0x800820d, {
+		0x68,0x98,0x83,0xcd,0x22,0x0d,0xdd,0x59,
+		0x73,0x2c,0x5b,0x37,0x1f,0x84,0x0e,0x67,
+		0x96,0x43,0x83,0x0c,0x46,0x44,0xab,0x7c,
+		0x7b,0x65,0x9e,0x57,0xb5,0x90,0x4b,0x0e,
+	}
+ },
+ { 0x8301025, {
+		0xe4,0x7d,0xdb,0x1e,0x14,0xb4,0x5e,0x36,
+		0x8f,0x3e,0x48,0x88,0x3c,0x6d,0x76,0xa1,
+		0x59,0xc6,0xc0,0x72,0x42,0xdf,0x6c,0x30,
+		0x6f,0x0b,0x28,0x16,0x61,0xfc,0x79,0x77,
+	}
+ },
+ { 0x8301055, {
+		0x81,0x7b,0x99,0x1b,0xae,0x2d,0x4f,0x9a,
+		0xef,0x13,0xce,0xb5,0x10,0xaf,0x6a,0xea,
+		0xe5,0xb0,0x64,0x98,0x10,0x68,0x34,0x3b,
+		0x9d,0x7a,0xd6,0x22,0x77,0x5f,0xb3,0x5b,
+	}
+ },
+ { 0x8301072, {
+		0xcf,0x76,0xa7,0x1a,0x49,0xdf,0x2a,0x5e,
+		0x9e,0x40,0x70,0xe5,0xdd,0x8a,0xa8,0x28,
+		0x20,0xdc,0x91,0xd8,0x2c,0xa6,0xa0,0xb1,
+		0x2d,0x22,0x26,0x94,0x4b,0x40,0x85,0x30,
+	}
+ },
+ { 0x830107a, {
+		0x2a,0x65,0x8c,0x1a,0x5e,0x07,0x21,0x72,
+		0xdf,0x90,0xa6,0x51,0x37,0xd3,0x4b,0x34,
+		0xc4,0xda,0x03,0xe1,0x8a,0x6c,0xfb,0x20,
+		0x04,0xb2,0x81,0x05,0xd4,0x87,0xf4,0x0a,
+	}
+ },
+ { 0x830107b, {
+		0xb3,0x43,0x13,0x63,0x56,0xc1,0x39,0xad,
+		0x10,0xa6,0x2b,0xcc,0x02,0xe6,0x76,0x2a,
+		0x1e,0x39,0x58,0x3e,0x23,0x6e,0xa4,0x04,
+		0x95,0xea,0xf9,0x6d,0xc2,0x8a,0x13,0x19,
+	}
+ },
+ { 0x830107c, {
+		0x21,0x64,0xde,0xfb,0x9f,0x68,0x96,0x47,
+		0x70,0x5c,0xe2,0x8f,0x18,0x52,0x6a,0xac,
+		0xa4,0xd2,0x2e,0xe0,0xde,0x68,0x66,0xc3,
+		0xeb,0x1e,0xd3,0x3f,0xbc,0x51,0x1d,0x38,
+	}
+ },
+ { 0x860010d, {
+		0x86,0xb6,0x15,0x83,0xbc,0x3b,0x9c,0xe0,
+		0xb3,0xef,0x1d,0x99,0x84,0x35,0x15,0xf7,
+		0x7c,0x2a,0xc6,0x42,0xdb,0x73,0x07,0x5c,
+		0x7d,0xc3,0x02,0xb5,0x43,0x06,0x5e,0xf8,
+	}
+ },
+ { 0x8608108, {
+		0x14,0xfe,0x57,0x86,0x49,0xc8,0x68,0xe2,
+		0x11,0xa3,0xcb,0x6e,0xff,0x6e,0xd5,0x38,
+		0xfe,0x89,0x1a,0xe0,0x67,0xbf,0xc4,0xcc,
+		0x1b,0x9f,0x84,0x77,0x2b,0x9f,0xaa,0xbd,
+	}
+ },
+ { 0x8701034, {
+		0xc3,0x14,0x09,0xa8,0x9c,0x3f,0x8d,0x83,
+		0x9b,0x4c,0xa5,0xb7,0x64,0x8b,0x91,0x5d,
+		0x85,0x6a,0x39,0x26,0x1e,0x14,0x41,0xa8,
+		0x75,0xea,0xa6,0xf9,0xc9,0xd1,0xea,0x2b,
+	}
+ },
+ { 0x8a00008, {
+		0xd7,0x2a,0x93,0xdc,0x05,0x2f,0xa5,0x6e,
+		0x0c,0x61,0x2c,0x07,0x9f,0x38,0xe9,0x8e,
+		0xef,0x7d,0x2a,0x05,0x4d,0x56,0xaf,0x72,
+		0xe7,0x56,0x47,0x6e,0x60,0x27,0xd5,0x8c,
+	}
+ },
+ { 0x8a0000a, {
+		0x73,0x31,0x26,0x22,0xd4,0xf9,0xee,0x3c,
+		0x07,0x06,0xe7,0xb9,0xad,0xd8,0x72,0x44,
+		0x33,0x31,0xaa,0x7d,0xc3,0x67,0x0e,0xdb,
+		0x47,0xb5,0xaa,0xbc,0xf5,0xbb,0xd9,0x20,
+	}
+ },
+ { 0xa00104c, {
+		0x3c,0x8a,0xfe,0x04,0x62,0xd8,0x6d,0xbe,
+		0xa7,0x14,0x28,0x64,0x75,0xc0,0xa3,0x76,
+		0xb7,0x92,0x0b,0x97,0x0a,0x8e,0x9c,0x5b,
+		0x1b,0xc8,0x9d,0x3a,0x1e,0x81,0x3d,0x3b,
+	}
+ },
+ { 0xa00104e, {
+		0xc4,0x35,0x82,0x67,0xd2,0x86,0xe5,0xb2,
+		0xfd,0x69,0x12,0x38,0xc8,0x77,0xba,0xe0,
+		0x70,0xf9,0x77,0x89,0x10,0xa6,0x74,0x4e,
+		0x56,0x58,0x13,0xf5,0x84,0x70,0x28,0x0b,
+	}
+ },
+ { 0xa001053, {
+		0x92,0x0e,0xf4,0x69,0x10,0x3b,0xf9,0x9d,
+		0x31,0x1b,0xa6,0x99,0x08,0x7d,0xd7,0x25,
+		0x7e,0x1e,0x89,0xba,0x35,0x8d,0xac,0xcb,
+		0x3a,0xb4,0xdf,0x58,0x12,0xcf,0xc0,0xc3,
+	}
+ },
+ { 0xa001058, {
+		0x33,0x7d,0xa9,0xb5,0x4e,0x62,0x13,0x36,
+		0xef,0x66,0xc9,0xbd,0x0a,0xa6,0x3b,0x19,
+		0xcb,0xf5,0xc2,0xc3,0x55,0x47,0x20,0xec,
+		0x1f,0x7b,0xa1,0x44,0x0e,0x8e,0xa4,0xb2,
+	}
+ },
+ { 0xa001075, {
+		0x39,0x02,0x82,0xd0,0x7c,0x26,0x43,0xe9,
+		0x26,0xa3,0xd9,0x96,0xf7,0x30,0x13,0x0a,
+		0x8a,0x0e,0xac,0xe7,0x1d,0xdc,0xe2,0x0f,
+		0xcb,0x9e,0x8d,0xbc,0xd2,0xa2,0x44,0xe0,
+	}
+ },
+ { 0xa001078, {
+		0x2d,0x67,0xc7,0x35,0xca,0xef,0x2f,0x25,
+		0x4c,0x45,0x93,0x3f,0x36,0x01,0x8c,0xce,
+		0xa8,0x5b,0x07,0xd3,0xc1,0x35,0x3c,0x04,
+		0x20,0xa2,0xfc,0xdc,0xe6,0xce,0x26,0x3e,
+	}
+ },
+ { 0xa001079, {
+		0x43,0xe2,0x05,0x9c,0xfd,0xb7,0x5b,0xeb,
+		0x5b,0xe9,0xeb,0x3b,0x96,0xf4,0xe4,0x93,
+		0x73,0x45,0x3e,0xac,0x8d,0x3b,0xe4,0xdb,
+		0x10,0x31,0xc1,0xe4,0xa2,0xd0,0x5a,0x8a,
+	}
+ },
+ { 0xa00107a, {
+		0x5f,0x92,0xca,0xff,0xc3,0x59,0x22,0x5f,
+		0x02,0xa0,0x91,0x3b,0x4a,0x45,0x10,0xfd,
+		0x19,0xe1,0x8a,0x6d,0x9a,0x92,0xc1,0x3f,
+		0x75,0x78,0xac,0x78,0x03,0x1d,0xdb,0x18,
+	}
+ },
+ { 0xa001143, {
+		0x56,0xca,0xf7,0x43,0x8a,0x4c,0x46,0x80,
+		0xec,0xde,0xe5,0x9c,0x50,0x84,0x9a,0x42,
+		0x27,0xe5,0x51,0x84,0x8f,0x19,0xc0,0x8d,
+		0x0c,0x25,0xb4,0xb0,0x8f,0x10,0xf3,0xf8,
+	}
+ },
+ { 0xa001144, {
+		0x42,0xd5,0x9b,0xa7,0xd6,0x15,0x29,0x41,
+		0x61,0xc4,0x72,0x3f,0xf3,0x06,0x78,0x4b,
+		0x65,0xf3,0x0e,0xfa,0x9c,0x87,0xde,0x25,
+		0xbd,0xb3,0x9a,0xf4,0x75,0x13,0x53,0xdc,
+	}
+ },
+ { 0xa00115d, {
+		0xd4,0xc4,0x49,0x36,0x89,0x0b,0x47,0xdd,
+		0xfb,0x2f,0x88,0x3b,0x5f,0xf2,0x8e,0x75,
+		0xc6,0x6c,0x37,0x5a,0x90,0x25,0x94,0x3e,
+		0x36,0x9c,0xae,0x02,0x38,0x6c,0xf5,0x05,
+	}
+ },
+ { 0xa001173, {
+		0x28,0xbb,0x9b,0xd1,0xa0,0xa0,0x7e,0x3a,
+		0x59,0x20,0xc0,0xa9,0xb2,0x5c,0xc3,0x35,
+		0x53,0x89,0xe1,0x4c,0x93,0x2f,0x1d,0xc3,
+		0xe5,0xf7,0xf3,0xc8,0x9b,0x61,0xaa,0x9e,
+	}
+ },
+ { 0xa0011a8, {
+		0x97,0xc6,0x16,0x65,0x99,0xa4,0x85,0x3b,
+		0xf6,0xce,0xaa,0x49,0x4a,0x3a,0xc5,0xb6,
+		0x78,0x25,0xbc,0x53,0xaf,0x5d,0xcf,0xf4,
+		0x23,0x12,0xbb,0xb1,0xbc,0x8a,0x02,0x2e,
+	}
+ },
+ { 0xa0011ce, {
+		0xcf,0x1c,0x90,0xa3,0x85,0x0a,0xbf,0x71,
+		0x94,0x0e,0x80,0x86,0x85,0x4f,0xd7,0x86,
+		0xae,0x38,0x23,0x28,0x2b,0x35,0x9b,0x4e,
+		0xfe,0xb8,0xcd,0x3d,0x3d,0x39,0xc9,0x6a,
+	}
+ },
+ { 0xa0011d1, {
+		0xdf,0x0e,0xca,0xde,0xf6,0xce,0x5c,0x1e,
+		0x4c,0xec,0xd7,0x71,0x83,0xcc,0xa8,0x09,
+		0xc7,0xc5,0xfe,0xb2,0xf7,0x05,0xd2,0xc5,
+		0x12,0xdd,0xe4,0xf3,0x92,0x1c,0x3d,0xb8,
+	}
+ },
+ { 0xa0011d3, {
+		0x91,0xe6,0x10,0xd7,0x57,0xb0,0x95,0x0b,
+		0x9a,0x24,0xee,0xf7,0xcf,0x56,0xc1,0xa6,
+		0x4a,0x52,0x7d,0x5f,0x9f,0xdf,0xf6,0x00,
+		0x65,0xf7,0xea,0xe8,0x2a,0x88,0xe2,0x26,
+	}
+ },
+ { 0xa0011d5, {
+		0xed,0x69,0x89,0xf4,0xeb,0x64,0xc2,0x13,
+		0xe0,0x51,0x1f,0x03,0x26,0x52,0x7d,0xb7,
+		0x93,0x5d,0x65,0xca,0xb8,0x12,0x1d,0x62,
+		0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
+	}
+ },
+ { 0xa001223, {
+		0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
+		0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
+		0x83,0x75,0x94,0xdd,0xeb,0x7e,0xb7,0x15,
+		0x8e,0x3b,0x50,0x29,0x8a,0x9c,0xcc,0x45,
+	}
+ },
+ { 0xa001224, {
+		0x0e,0x0c,0xdf,0xb4,0x89,0xee,0x35,0x25,
+		0xdd,0x9e,0xdb,0xc0,0x69,0x83,0x0a,0xad,
+		0x26,0xa9,0xaa,0x9d,0xfc,0x3c,0xea,0xf9,
+		0x6c,0xdc,0xd5,0x6d,0x8b,0x6e,0x85,0x4a,
+	}
+ },
+ { 0xa001227, {
+		0xab,0xc6,0x00,0x69,0x4b,0x50,0x87,0xad,
+		0x5f,0x0e,0x8b,0xea,0x57,0x38,0xce,0x1d,
+		0x0f,0x75,0x26,0x02,0xf6,0xd6,0x96,0xe9,
+		0x87,0xb9,0xd6,0x20,0x27,0x7c,0xd2,0xe0,
+	}
+ },
+ { 0xa001229, {
+		0x7f,0x49,0x49,0x48,0x46,0xa5,0x50,0xa6,
+		0x28,0x89,0x98,0xe2,0x9e,0xb4,0x7f,0x75,
+		0x33,0xa7,0x04,0x02,0xe4,0x82,0xbf,0xb4,
+		0xa5,0x3a,0xba,0x24,0x8d,0x31,0x10,0x1d,
+	}
+ },
+ { 0xa00122e, {
+		0x56,0x94,0xa9,0x5d,0x06,0x68,0xfe,0xaf,
+		0xdf,0x7a,0xff,0x2d,0xdf,0x74,0x0f,0x15,
+		0x66,0xfb,0x00,0xb5,0x51,0x97,0x9b,0xfa,
+		0xcb,0x79,0x85,0x46,0x25,0xb4,0xd2,0x10,
+	}
+ },
+ { 0xa001231, {
+		0x0b,0x46,0xa5,0xfc,0x18,0x15,0xa0,0x9e,
+		0xa6,0xdc,0xb7,0xff,0x17,0xf7,0x30,0x64,
+		0xd4,0xda,0x9e,0x1b,0xc3,0xfc,0x02,0x3b,
+		0xe2,0xc6,0x0e,0x41,0x54,0xb5,0x18,0xdd,
+	}
+ },
+ { 0xa001234, {
+		0x88,0x8d,0xed,0xab,0xb5,0xbd,0x4e,0xf7,
+		0x7f,0xd4,0x0e,0x95,0x34,0x91,0xff,0xcc,
+		0xfb,0x2a,0xcd,0xf7,0xd5,0xdb,0x4c,0x9b,
+		0xd6,0x2e,0x73,0x50,0x8f,0x83,0x79,0x1a,
+	}
+ },
+ { 0xa001236, {
+		0x3d,0x30,0x00,0xb9,0x71,0xba,0x87,0x78,
+		0xa8,0x43,0x55,0xc4,0x26,0x59,0xcf,0x9d,
+		0x93,0xce,0x64,0x0e,0x8b,0x72,0x11,0x8b,
+		0xa3,0x8f,0x51,0xe9,0xca,0x98,0xaa,0x25,
+	}
+ },
+ { 0xa001238, {
+		0x72,0xf7,0x4b,0x0c,0x7d,0x58,0x65,0xcc,
+		0x00,0xcc,0x57,0x16,0x68,0x16,0xf8,0x2a,
+		0x1b,0xb3,0x8b,0xe1,0xb6,0x83,0x8c,0x7e,
+		0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
+	}
+ },
+ { 0xa00820c, {
+		0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
+		0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
+		0xf1,0x8c,0x88,0x45,0xd7,0x82,0x80,0xd1,
+		0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
+	}
+ },
+ { 0xa10113e, {
+		0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
+		0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
+		0x15,0xe3,0x3f,0x4b,0x1d,0x0d,0x0a,0xd5,
+		0xfa,0x90,0xc4,0xed,0x9d,0x90,0xaf,0x53,
+	}
+ },
+ { 0xa101144, {
+		0xb3,0x0b,0x26,0x9a,0xf8,0x7c,0x02,0x26,
+		0x35,0x84,0x53,0xa4,0xd3,0x2c,0x7c,0x09,
+		0x68,0x7b,0x96,0xb6,0x93,0xef,0xde,0xbc,
+		0xfd,0x4b,0x15,0xd2,0x81,0xd3,0x51,0x47,
+	}
+ },
+ { 0xa101148, {
+		0x20,0xd5,0x6f,0x40,0x4a,0xf6,0x48,0x90,
+		0xc2,0x93,0x9a,0xc2,0xfd,0xac,0xef,0x4f,
+		0xfa,0xc0,0x3d,0x92,0x3c,0x6d,0x01,0x08,
+		0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
+	}
+ },
+ { 0xa10123e, {
+		0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
+		0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
+		0x1d,0x13,0x53,0x63,0xfe,0x42,0x6f,0xfc,
+		0x19,0x0f,0xf1,0xfc,0xa7,0xdd,0x89,0x1b,
+	}
+ },
+ { 0xa101244, {
+		0x71,0x56,0xb5,0x9f,0x21,0xbf,0xb3,0x3c,
+		0x8c,0xd7,0x36,0xd0,0x34,0x52,0x1b,0xb1,
+		0x46,0x2f,0x04,0xf0,0x37,0xd8,0x1e,0x72,
+		0x24,0xa2,0x80,0x84,0x83,0x65,0x84,0xc0,
+	}
+ },
+ { 0xa101248, {
+		0xed,0x3b,0x95,0xa6,0x68,0xa7,0x77,0x3e,
+		0xfc,0x17,0x26,0xe2,0x7b,0xd5,0x56,0x22,
+		0x2c,0x1d,0xef,0xeb,0x56,0xdd,0xba,0x6e,
+		0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
+	}
+ },
+ { 0xa108108, {
+		0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
+		0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
+		0xf5,0xd4,0x3f,0x7b,0x14,0xd5,0x60,0x2c,
+		0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
+	}
+ },
+ { 0xa20102d, {
+		0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
+		0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
+		0x8b,0x89,0x2f,0xb5,0xbb,0x82,0xef,0x23,
+		0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
+	}
+ },
+ { 0xa201210, {
+		0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
+		0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
+		0x6d,0x3d,0x0e,0x6b,0xa7,0xac,0xe3,0x68,
+		0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
+	}
+ },
+ { 0xa404107, {
+		0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
+		0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
+		0x8b,0x0d,0x9f,0xf9,0x3a,0xdf,0xc6,0x81,
+		0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
+	}
+ },
+ { 0xa500011, {
+		0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
+		0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
+		0xd7,0x5b,0x65,0x3a,0x7d,0xab,0xdf,0xa2,
+		0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
+	}
+ },
+ { 0xa601209, {
+		0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
+		0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
+		0x15,0x86,0xcc,0x5d,0x97,0x0f,0xc0,0x46,
+		0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
+	}
+ },
+ { 0xa704107, {
+		0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
+		0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
+		0x2a,0xad,0x8e,0x6b,0xea,0x9b,0xb7,0xc2,
+		0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
+	}
+ },
+ { 0xa705206, {
+		0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
+		0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
+		0x67,0x6f,0x04,0x18,0xae,0x20,0x87,0x4b,
+		0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
+	}
+ },
+ { 0xa708007, {
+		0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
+		0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
+		0x07,0xaa,0x3a,0xe0,0x57,0x13,0x72,0x80,
+		0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
+	}
+ },
+ { 0xa70c005, {
+		0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
+		0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
+		0x1f,0x1f,0xf1,0x97,0xeb,0xfe,0x56,0x55,
+		0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
+	}
+ },
+ { 0xaa00116, {
+		0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
+		0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
+		0xfe,0x1d,0x5e,0x65,0xc7,0xaa,0x92,0x4d,
+		0x91,0xee,0x76,0xbb,0x4c,0x66,0x78,0xc9,
+	}
+ },
+ { 0xaa00212, {
+		0xbd,0x57,0x5d,0x0a,0x0a,0x30,0xc1,0x75,
+		0x95,0x58,0x5e,0x93,0x02,0x28,0x43,0x71,
+		0xed,0x42,0x29,0xc8,0xec,0x34,0x2b,0xb2,
+		0x1a,0x65,0x4b,0xfe,0x07,0x0f,0x34,0xa1,
+	}
+ },
+ { 0xaa00213, {
+		0xed,0x58,0xb7,0x76,0x81,0x7f,0xd9,0x3a,
+		0x1a,0xff,0x8b,0x34,0xb8,0x4a,0x99,0x0f,
+		0x28,0x49,0x6c,0x56,0x2b,0xdc,0xb7,0xed,
+		0x96,0xd5,0x9d,0xc1,0x7a,0xd4,0x51,0x9b,
+	}
+ },
+ { 0xaa00215, {
+		0x55,0xd3,0x28,0xcb,0x87,0xa9,0x32,0xe9,
+		0x4e,0x85,0x4b,0x7c,0x6b,0xd5,0x7c,0xd4,
+		0x1b,0x51,0x71,0x3a,0x0e,0x0b,0xdc,0x9b,
+		0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
+	}
+ },
+};

From cf7139aac463880cbd5c5e999c118fbe91631411 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Fri, 14 Feb 2025 16:47:51 +0800
Subject: [PATCH 1017/2753] soc: imx8m: Unregister cpufreq and soc dev in
 cleanup path

Unregister the cpufreq device and soc device when resource unwinding,
otherwise there will be warning when do removing test:
sysfs: cannot create duplicate filename '/devices/platform/imx-cpufreq-dt'
CPU: 0 UID: 0 PID: 1 Comm: swapper/0 Not tainted 6.13.0-rc1-next-20241204
Hardware name: NXP i.MX8MPlus EVK board (DT)

Fixes: 9cc832d37799 ("soc: imx8m: Probe the SoC driver as platform driver")
Cc: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Marco Felsch <m.felsch@pengutronix.de>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 drivers/soc/imx/soc-imx8m.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/imx/soc-imx8m.c b/drivers/soc/imx/soc-imx8m.c
index 8ac7658e3d525..3ed8161d7d28b 100644
--- a/drivers/soc/imx/soc-imx8m.c
+++ b/drivers/soc/imx/soc-imx8m.c
@@ -192,9 +192,20 @@ static __maybe_unused const struct of_device_id imx8_soc_match[] = {
 	devm_kasprintf((dev), GFP_KERNEL, "%d.%d", ((soc_rev) >> 4) & 0xf, (soc_rev) & 0xf) : \
 	"unknown"
 
+static void imx8m_unregister_soc(void *data)
+{
+	soc_device_unregister(data);
+}
+
+static void imx8m_unregister_cpufreq(void *data)
+{
+	platform_device_unregister(data);
+}
+
 static int imx8m_soc_probe(struct platform_device *pdev)
 {
 	struct soc_device_attribute *soc_dev_attr;
+	struct platform_device *cpufreq_dev;
 	const struct imx8_soc_data *data;
 	struct device *dev = &pdev->dev;
 	const struct of_device_id *id;
@@ -239,11 +250,22 @@ static int imx8m_soc_probe(struct platform_device *pdev)
 	if (IS_ERR(soc_dev))
 		return PTR_ERR(soc_dev);
 
+	ret = devm_add_action(dev, imx8m_unregister_soc, soc_dev);
+	if (ret)
+		return ret;
+
 	pr_info("SoC: %s revision %s\n", soc_dev_attr->soc_id,
 		soc_dev_attr->revision);
 
-	if (IS_ENABLED(CONFIG_ARM_IMX_CPUFREQ_DT))
-		platform_device_register_simple("imx-cpufreq-dt", -1, NULL, 0);
+	if (IS_ENABLED(CONFIG_ARM_IMX_CPUFREQ_DT)) {
+		cpufreq_dev = platform_device_register_simple("imx-cpufreq-dt", -1, NULL, 0);
+		if (IS_ERR(cpufreq_dev))
+			return dev_err_probe(dev, PTR_ERR(cpufreq_dev),
+					     "Failed to register imx-cpufreq-dev device\n");
+		ret = devm_add_action(dev, imx8m_unregister_cpufreq, cpufreq_dev);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }

From b0612fdba9afdce261bfb8684e0cece6f2e2b0bb Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Mon, 17 Feb 2025 15:56:40 +0100
Subject: [PATCH 1018/2753] arm64: dts: freescale: imx8mp-verdin-dahlia: add
 Microphone Jack to sound card

The simple-audio-card's microphone widget currently connects to the
headphone jack. Routing the microphone input to the microphone jack
allows for independent operation of the microphone and headphones.

This resolves the following boot-time kernel log message, which
indicated a conflict when the microphone and headphone functions were
not separated:
  debugfs: File 'Headphone Jack' in directory 'dapm' already present!

Fixes: 874958916844 ("arm64: dts: freescale: verdin-imx8mp: dahlia: add sound card")
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
index da8902c5f7e5b..1493319aa748d 100644
--- a/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mp-verdin-dahlia.dtsi
@@ -28,10 +28,10 @@
 			"Headphone Jack", "HPOUTR",
 			"IN2L", "Line In Jack",
 			"IN2R", "Line In Jack",
-			"Headphone Jack", "MICBIAS",
-			"IN1L", "Headphone Jack";
+			"Microphone Jack", "MICBIAS",
+			"IN1L", "Microphone Jack";
 		simple-audio-card,widgets =
-			"Microphone", "Headphone Jack",
+			"Microphone", "Microphone Jack",
 			"Headphone", "Headphone Jack",
 			"Line", "Line In Jack";
 

From 2c1092823eb03f8508d6769e2f38eef7e1fe62a0 Mon Sep 17 00:00:00 2001
From: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Date: Mon, 17 Feb 2025 15:56:41 +0100
Subject: [PATCH 1019/2753] arm64: dts: freescale: imx8mm-verdin-dahlia: add
 Microphone Jack to sound card

The simple-audio-card's microphone widget currently connects to the
headphone jack. Routing the microphone input to the microphone jack
allows for independent operation of the microphone and headphones.

This resolves the following boot-time kernel log message, which
indicated a conflict when the microphone and headphone functions were
not separated:
  debugfs: File 'Headphone Jack' in directory 'dapm' already present!

Fixes: 6a57f224f734 ("arm64: dts: freescale: add initial support for verdin imx8m mini")
Signed-off-by: Stefan Eichenberger <stefan.eichenberger@toradex.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Shawn Guo <shawnguo@kernel.org>
---
 arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
index ce20de2598054..3d0b149681310 100644
--- a/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
+++ b/arch/arm64/boot/dts/freescale/imx8mm-verdin-dahlia.dtsi
@@ -16,10 +16,10 @@
 			"Headphone Jack", "HPOUTR",
 			"IN2L", "Line In Jack",
 			"IN2R", "Line In Jack",
-			"Headphone Jack", "MICBIAS",
-			"IN1L", "Headphone Jack";
+			"Microphone Jack", "MICBIAS",
+			"IN1L", "Microphone Jack";
 		simple-audio-card,widgets =
-			"Microphone", "Headphone Jack",
+			"Microphone", "Microphone Jack",
 			"Headphone", "Headphone Jack",
 			"Line", "Line In Jack";
 

From e1a0bdbdfdf08428f0ede5ae49c7f4139ac73ef5 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 20 Feb 2025 08:47:10 +0200
Subject: [PATCH 1020/2753] RDMA/mlx5: Fix bind QP error cleanup flow

When there is a failure during bind QP, the cleanup flow destroys the
counter regardless if it is the one that created it or not, which is
problematic since if it isn't the one that created it, that counter could
still be in use.

Fix that by destroying the counter only if it was created during this call.

Fixes: 45842fc627c7 ("IB/mlx5: Support statistic q counter configuration")
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Zhang <markzhang@nvidia.com>
Link: https://patch.msgid.link/25dfefddb0ebefa668c32e06a94d84e3216257cf.1740033937.git.leon@kernel.org
Reviewed-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/counters.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/counters.c b/drivers/infiniband/hw/mlx5/counters.c
index 4f6c1968a2ee3..81cfa74147a18 100644
--- a/drivers/infiniband/hw/mlx5/counters.c
+++ b/drivers/infiniband/hw/mlx5/counters.c
@@ -546,6 +546,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 				   struct ib_qp *qp)
 {
 	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	bool new = false;
 	int err;
 
 	if (!counter->id) {
@@ -560,6 +561,7 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 			return err;
 		counter->id =
 			MLX5_GET(alloc_q_counter_out, out, counter_set_id);
+		new = true;
 	}
 
 	err = mlx5_ib_qp_set_counter(qp, counter);
@@ -569,8 +571,10 @@ static int mlx5_ib_counter_bind_qp(struct rdma_counter *counter,
 	return 0;
 
 fail_set_counter:
-	mlx5_ib_counter_dealloc(counter);
-	counter->id = 0;
+	if (new) {
+		mlx5_ib_counter_dealloc(counter);
+		counter->id = 0;
+	}
 
 	return err;
 }

From 531ca2b9a215d072ffb4b1ff760a73f5e80c9c46 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 19 Feb 2025 10:58:07 +0200
Subject: [PATCH 1021/2753] net/mlx5: Add new health syndrome error and crr bit
 offset

Add new error value for trust lockdown in health syndrome enum.
Also, include the offset for crr bit in the health buffer layout.

These changes prepare for downstream patches that update health
event handling.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219085808.349923-2-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/device.h   | 1 +
 include/linux/mlx5/mlx5_ifc.h | 1 +
 2 files changed, 2 insertions(+)

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0c48b20f818a9..fd37f4e54d761 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -538,6 +538,7 @@ struct mlx5_cmd_layout {
 };
 
 enum mlx5_rfr_severity_bit_offsets {
+	MLX5_CRR_BIT_OFFSET = 0x6,
 	MLX5_RFR_BIT_OFFSET = 0x7,
 };
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4f3716e124c9c..cc2875e843f7f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -11119,6 +11119,7 @@ enum {
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR                    = 0xf,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR                = 0x10,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR         = 0x12,
+	MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR           = 0x13,
 };
 
 struct mlx5_ifc_initial_seg_bits {

From 80df31f384b4146a62a01b3d4beb376cc7b9a89e Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Wed, 19 Feb 2025 10:58:08 +0200
Subject: [PATCH 1022/2753] net/mlx5: Change POOL_NEXT_SIZE define value and
 make it global

Change POOL_NEXT_SIZE define value from 0 to BIT(30), since this define
is used to request the available maximum sized flow table, and zero doesn't
make sense for it, whereas some places in the driver use zero explicitly
expecting the smallest table size possible but instead due to this
define they end up allocating the biggest table size unawarely.

In addition move the definition to "include/linux/mlx5/fs.h" to expose the
define to IB driver as well, while appropriately renaming it.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250219085808.349923-3-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c    | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c    | 6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h    | 2 --
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 3 ++-
 include/linux/mlx5/fs.h                                 | 2 ++
 5 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
index 45183de424f3d..76382626ad41d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
@@ -96,7 +96,7 @@ static int esw_create_legacy_fdb_table(struct mlx5_eswitch *esw)
 	if (!flow_group_in)
 		return -ENOMEM;
 
-	ft_attr.max_fte = POOL_NEXT_SIZE;
+	ft_attr.max_fte = MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.prio = LEGACY_FDB_PRIO;
 	fdb = mlx5_create_flow_table(root_ns, &ft_attr);
 	if (IS_ERR(fdb)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
index c14590acc7726..f6abfd00d7e68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.c
@@ -50,10 +50,12 @@ mlx5_ft_pool_get_avail_sz(struct mlx5_core_dev *dev, enum fs_flow_table_type tab
 	int i, found_i = -1;
 
 	for (i = ARRAY_SIZE(FT_POOLS) - 1; i >= 0; i--) {
-		if (dev->priv.ft_pool->ft_left[i] && FT_POOLS[i] >= desired_size &&
+		if (dev->priv.ft_pool->ft_left[i] &&
+		    (FT_POOLS[i] >= desired_size ||
+		     desired_size == MLX5_FS_MAX_POOL_SIZE) &&
 		    FT_POOLS[i] <= max_ft_size) {
 			found_i = i;
-			if (desired_size != POOL_NEXT_SIZE)
+			if (desired_size != MLX5_FS_MAX_POOL_SIZE)
 				break;
 		}
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
index 25f4274b372b5..173e312db7204 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_ft_pool.h
@@ -7,8 +7,6 @@
 #include <linux/mlx5/driver.h>
 #include "fs_core.h"
 
-#define POOL_NEXT_SIZE 0
-
 int mlx5_ft_pool_init(struct mlx5_core_dev *dev);
 void mlx5_ft_pool_destroy(struct mlx5_core_dev *dev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33d..c862dd28c4661 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -161,7 +161,8 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ft_attr.flags |= (MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT |
 				  MLX5_FLOW_TABLE_TUNNEL_EN_DECAP);
 
-	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ? FT_TBL_SZ : POOL_NEXT_SIZE;
+	sz = (chain == mlx5_chains_get_nf_ft_chain(chains)) ?
+		FT_TBL_SZ : MLX5_FS_MAX_POOL_SIZE;
 	ft_attr.max_fte = sz;
 
 	/* We use chains_default_ft(chains) as the table's next_ft till
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2a69d9d71276d..01cb72d68c231 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,8 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
+#define MLX5_FS_MAX_POOL_SIZE BIT(30)
+
 enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_NONE,
 	MLX5_FLOW_DESTINATION_TYPE_VPORT,

From 7cfb32456ed82cd548114234ec275d57d4f7554e Mon Sep 17 00:00:00 2001
From: Sven Eckelmann <sven@narfation.org>
Date: Sun, 23 Feb 2025 11:14:53 +0100
Subject: [PATCH 1023/2753] batman-adv: add missing newlines for log macros

Missing trailing newlines can lead to incomplete log lines that do not
appear properly in dmesg or in console output.

Signed-off-by: Sven Eckelmann <sven@narfation.org>
Signed-off-by: Simon Wunderlich <sw@simonwunderlich.de>
---
 net/batman-adv/netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c
index 13935570fae17..e7c8f9f2bb1f9 100644
--- a/net/batman-adv/netlink.c
+++ b/net/batman-adv/netlink.c
@@ -1567,7 +1567,7 @@ void __init batadv_netlink_register(void)
 
 	ret = genl_register_family(&batadv_netlink_family);
 	if (ret)
-		pr_warn("unable to register netlink family");
+		pr_warn("unable to register netlink family\n");
 }
 
 /**

From b66535356a4834a234f99e16a97eb51f2c6c5a7d Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Sat, 22 Feb 2025 07:20:21 -0800
Subject: [PATCH 1024/2753] RDMA/bnxt_re: Fix the page details for the srq
 created by kernel consumers

While using nvme target with use_srq on, below kernel panic is noticed.

[  549.698111] bnxt_en 0000:41:00.0 enp65s0np0: FEC autoneg off encoding: Clause 91 RS(544,514)
[  566.393619] Oops: divide error: 0000 [#1] PREEMPT SMP NOPTI
..
[  566.393799]  <TASK>
[  566.393807]  ? __die_body+0x1a/0x60
[  566.393823]  ? die+0x38/0x60
[  566.393835]  ? do_trap+0xe4/0x110
[  566.393847]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393867]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393881]  ? do_error_trap+0x7c/0x120
[  566.393890]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393911]  ? exc_divide_error+0x34/0x50
[  566.393923]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393939]  ? asm_exc_divide_error+0x16/0x20
[  566.393966]  ? bnxt_qplib_alloc_init_hwq+0x1d4/0x580 [bnxt_re]
[  566.393997]  bnxt_qplib_create_srq+0xc9/0x340 [bnxt_re]
[  566.394040]  bnxt_re_create_srq+0x335/0x3b0 [bnxt_re]
[  566.394057]  ? srso_return_thunk+0x5/0x5f
[  566.394068]  ? __init_swait_queue_head+0x4a/0x60
[  566.394090]  ib_create_srq_user+0xa7/0x150 [ib_core]
[  566.394147]  nvmet_rdma_queue_connect+0x7d0/0xbe0 [nvmet_rdma]
[  566.394174]  ? lock_release+0x22c/0x3f0
[  566.394187]  ? srso_return_thunk+0x5/0x5f

Page size and shift info is set only for the user space SRQs.
Set page size and page shift for kernel space SRQs also.

Fixes: 0c4dcd602817 ("RDMA/bnxt_re: Refactor hardware queue memory allocation")
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1740237621-29291-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/ib_verbs.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
index 2de101d6e8255..6f5db32082dd7 100644
--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
@@ -1870,6 +1870,8 @@ int bnxt_re_create_srq(struct ib_srq *ib_srq,
 	srq->qplib_srq.threshold = srq_init_attr->attr.srq_limit;
 	srq->srq_limit = srq_init_attr->attr.srq_limit;
 	srq->qplib_srq.eventq_hw_ring_id = rdev->nqr->nq[0].ring_id;
+	srq->qplib_srq.sg_info.pgsize = PAGE_SIZE;
+	srq->qplib_srq.sg_info.pgshft = PAGE_SHIFT;
 	nq = &rdev->nqr->nq[0];
 
 	if (udata) {

From 174e5e9da4f5946de3d09c32ee56cbbc9d70505b Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Fri, 21 Feb 2025 09:12:42 +0100
Subject: [PATCH 1025/2753] efi/cper: Fix cper_ia_proc_ctx alignment

According to the UEFI Common Platform Error Record appendix, the
IA32/X64 Processor Context Information Structure is a variable length
structure, but "is padded with zeros if the size is not a multiple
of 16 bytes".

Currently this isn't honoured, causing all but the first structure to
be garbage when printed. Thus align the size to be a multiple of 16.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/cper-x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper-x86.c b/drivers/firmware/efi/cper-x86.c
index 438ed9eff6d01..3949d7b5e808f 100644
--- a/drivers/firmware/efi/cper-x86.c
+++ b/drivers/firmware/efi/cper-x86.c
@@ -325,7 +325,7 @@ void cper_print_proc_ia(const char *pfx, const struct cper_sec_proc_ia *proc)
 
 	ctx_info = (struct cper_ia_proc_ctx *)err_info;
 	for (i = 0; i < VALID_PROC_CXT_INFO_NUM(proc->validation_bits); i++) {
-		int size = sizeof(*ctx_info) + ctx_info->reg_arr_size;
+		int size = ALIGN(sizeof(*ctx_info) + ctx_info->reg_arr_size, 16);
 		int groupsize = 4;
 
 		printk("%sContext Information Structure %d:\n", pfx, i);

From d6a2d02aa060531607f4a8411ec384470faa2761 Mon Sep 17 00:00:00 2001
From: Patrick Rudolph <patrick.rudolph@9elements.com>
Date: Fri, 21 Feb 2025 12:15:16 +0100
Subject: [PATCH 1026/2753] efi/cper: Fix cper_arm_ctx_info alignment

According to the UEFI Common Platform Error Record appendix, the
processor context information structure is a variable length structure,
but "is padded with zeros if the size is not a multiple of 16 bytes".

Currently this isn't honoured, causing all but the first structure to
be garbage when printed. Thus align the size to be a multiple of 16.

Signed-off-by: Patrick Rudolph <patrick.rudolph@9elements.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/cper-arm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/firmware/efi/cper-arm.c b/drivers/firmware/efi/cper-arm.c
index fa9c1c3bf168b..f0a63d09d3c49 100644
--- a/drivers/firmware/efi/cper-arm.c
+++ b/drivers/firmware/efi/cper-arm.c
@@ -311,7 +311,7 @@ void cper_print_proc_arm(const char *pfx,
 	ctx_info = (struct cper_arm_ctx_info *)err_info;
 	max_ctx_type = ARRAY_SIZE(arm_reg_ctx_strs) - 1;
 	for (i = 0; i < proc->context_info_num; i++) {
-		int size = sizeof(*ctx_info) + ctx_info->size;
+		int size = ALIGN(sizeof(*ctx_info) + ctx_info->size, 16);
 
 		printk("%sContext info structure %d:\n", pfx, i);
 		if (len < size) {

From cb6ae457bc6af58c84a7854df5e7e32ba1c6a715 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Sun, 23 Feb 2025 16:48:54 +0100
Subject: [PATCH 1027/2753] efivarfs: Defer PM notifier registration until
 .fill_super

syzbot reports an issue that turns out to be caused by the fact that the
efivarfs PM notifier may be invoked before the efivarfs_fs_info::sb
field is populated, resulting in a NULL deference.

So defer the registration until efivarfs_fill_super() is invoked.

Reported-by: syzbot+00d13e505ef530a45100@syzkaller.appspotmail.com
Tested-by: syzbot+00d13e505ef530a45100@syzkaller.appspotmail.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/super.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 09fcf731e65d6..6eae8cf655c12 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -367,6 +367,8 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (err)
 		return err;
 
+	register_pm_notifier(&sfi->pm_nb);
+
 	return efivar_init(efivarfs_callback, sb, true);
 }
 
@@ -552,7 +554,6 @@ static int efivarfs_init_fs_context(struct fs_context *fc)
 
 	sfi->pm_nb.notifier_call = efivarfs_pm_notify;
 	sfi->pm_nb.priority = 0;
-	register_pm_notifier(&sfi->pm_nb);
 
 	return 0;
 }

From d082ecbc71e9e0bf49883ee4afd435a77a5101b6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 23 Feb 2025 12:32:57 -0800
Subject: [PATCH 1028/2753] Linux 6.14-rc4

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 96407c1d6be16..30dab4c8b0120 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From cf3e6960263a2ecdf5528056b321e41557e9b03d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 22 Feb 2025 09:05:36 -0500
Subject: [PATCH 1029/2753] bcachefs: fix bch2_extent_ptr_eq()

Reviewed-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/extents.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/extents.h b/fs/bcachefs/extents.h
index 620b284aa34f0..204d765dd74c8 100644
--- a/fs/bcachefs/extents.h
+++ b/fs/bcachefs/extents.h
@@ -704,7 +704,7 @@ static inline bool bch2_extent_ptr_eq(struct bch_extent_ptr ptr1,
 		ptr1.unwritten	== ptr2.unwritten &&
 		ptr1.offset	== ptr2.offset &&
 		ptr1.dev	== ptr2.dev &&
-		ptr1.dev	== ptr2.dev);
+		ptr1.gen	== ptr2.gen);
 }
 
 void bch2_ptr_swab(struct bkey_s);

From e13b6da7045f997e1a5a5efd61d40e63c4fc20e8 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 18 Feb 2025 10:39:08 +0800
Subject: [PATCH 1030/2753] virtio-net: tweak for better TX performance in NAPI
 mode

There are several issues existed in start_xmit():

- Transmitted packets need to be freed before sending a packet, this
  introduces delay and increases the average packets transmit
  time. This also increase the time that spent in holding the TX lock.
- Notification is enabled after free_old_xmit_skbs() which will
  introduce unnecessary interrupts if TX notification happens on the
  same CPU that is doing the transmission now (actually, virtio-net
  driver are optimized for this case).

So this patch tries to avoid those issues by not cleaning transmitted
packets in start_xmit() when TX NAPI is enabled and disable
notifications even more aggressively. Notification will be since the
beginning of the start_xmit(). But we can't enable delayed
notification after TX is stopped as we will lose the
notifications. Instead, the delayed notification needs is enabled
after the virtqueue is kicked for best performance.

Performance numbers:

1) single queue 2 vcpus guest with pktgen_sample03_burst_single_flow.sh
   (burst 256) + testpmd (rxonly) on the host:

- When pinning TX IRQ to pktgen VCPU: split virtqueue PPS were
  increased 55% from 6.89 Mpps to 10.7 Mpps and 32% TX interrupts were
  eliminated. Packed virtqueue PPS were increased 50% from 7.09 Mpps to
  10.7 Mpps, 99% TX interrupts were eliminated.

- When pinning TX IRQ to VCPU other than pktgen: split virtqueue PPS
  were increased 96% from 5.29 Mpps to 10.4 Mpps and 45% TX interrupts
  were eliminated; Packed virtqueue PPS were increased 78% from 6.12
  Mpps to 10.9 Mpps and 99% TX interrupts were eliminated.

2) single queue 1 vcpu guest + vhost-net/TAP on the host: single
   session netperf from guest to host shows 82% improvement from
   31Gb/s to 58Gb/s, %stddev were reduced from 34.5% to 1.9% and 88%
   of TX interrupts were eliminated.

Signed-off-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/virtio_net.c | 45 ++++++++++++++++++++++++++++------------
 1 file changed, 32 insertions(+), 13 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7646ddd9bef70..ac26a6201c444 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -1088,11 +1088,10 @@ static bool is_xdp_raw_buffer_queue(struct virtnet_info *vi, int q)
 		return false;
 }
 
-static void check_sq_full_and_disable(struct virtnet_info *vi,
-				      struct net_device *dev,
-				      struct send_queue *sq)
+static bool tx_may_stop(struct virtnet_info *vi,
+			struct net_device *dev,
+			struct send_queue *sq)
 {
-	bool use_napi = sq->napi.weight;
 	int qnum;
 
 	qnum = sq - vi->sq;
@@ -1114,6 +1113,25 @@ static void check_sq_full_and_disable(struct virtnet_info *vi,
 		u64_stats_update_begin(&sq->stats.syncp);
 		u64_stats_inc(&sq->stats.stop);
 		u64_stats_update_end(&sq->stats.syncp);
+
+		return true;
+	}
+
+	return false;
+}
+
+static void check_sq_full_and_disable(struct virtnet_info *vi,
+				      struct net_device *dev,
+				      struct send_queue *sq)
+{
+	bool use_napi = sq->napi.weight;
+	int qnum;
+
+	qnum = sq - vi->sq;
+
+	if (tx_may_stop(vi, dev, sq)) {
+		struct netdev_queue *txq = netdev_get_tx_queue(dev, qnum);
+
 		if (use_napi) {
 			if (unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
 				virtqueue_napi_schedule(&sq->napi, sq->vq);
@@ -3253,15 +3271,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	bool use_napi = sq->napi.weight;
 	bool kick;
 
-	/* Free up any pending old buffers before queueing new ones. */
-	do {
-		if (use_napi)
-			virtqueue_disable_cb(sq->vq);
-
+	if (!use_napi)
 		free_old_xmit(sq, txq, false);
-
-	} while (use_napi && !xmit_more &&
-	       unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
+	else
+		virtqueue_disable_cb(sq->vq);
 
 	/* timestamp packet in software */
 	skb_tx_timestamp(skb);
@@ -3287,7 +3300,10 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		nf_reset_ct(skb);
 	}
 
-	check_sq_full_and_disable(vi, dev, sq);
+	if (use_napi)
+		tx_may_stop(vi, dev, sq);
+	else
+		check_sq_full_and_disable(vi, dev,sq);
 
 	kick = use_napi ? __netdev_tx_sent_queue(txq, skb->len, xmit_more) :
 			  !xmit_more || netif_xmit_stopped(txq);
@@ -3299,6 +3315,9 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 		}
 	}
 
+	if (use_napi && kick && unlikely(!virtqueue_enable_cb_delayed(sq->vq)))
+		virtqueue_napi_schedule(&sq->napi, sq->vq);
+
 	return NETDEV_TX_OK;
 }
 

From f15176b8b6e72ac30e14fd273282d2b72562d26b Mon Sep 17 00:00:00 2001
From: Linus Walleij <linus.walleij@linaro.org>
Date: Thu, 20 Feb 2025 19:48:15 +0100
Subject: [PATCH 1031/2753] net: dsa: rtl8366rb: Fix compilation problem

When the kernel is compiled without LED framework support the
rtl8366rb fails to build like this:

rtl8366rb.o: in function `rtl8366rb_setup_led':
rtl8366rb.c:953:(.text.unlikely.rtl8366rb_setup_led+0xe8):
  undefined reference to `led_init_default_state_get'
rtl8366rb.c:980:(.text.unlikely.rtl8366rb_setup_led+0x240):
  undefined reference to `devm_led_classdev_register_ext'

As this is constantly coming up in different randconfig builds,
bite the bullet and create a separate file for the offending
code, split out a header with all stuff needed both in the
core driver and the leds code.

Add a new bool Kconfig option for the LED compile target, such
that it depends on LEDS_CLASS=y || LEDS_CLASS=RTL8366RB
which make LED support always available when LEDS_CLASS is
compiled into the kernel and enforce that if the LEDS_CLASS
is a module, then the RTL8366RB driver needs to be a module
as well so that modprobe can resolve the dependencies.

Fixes: 32d617005475 ("net: dsa: realtek: add LED drivers for rtl8366rb")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502070525.xMUImayb-lkp@intel.com/
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/realtek/Kconfig          |   6 +
 drivers/net/dsa/realtek/Makefile         |   3 +
 drivers/net/dsa/realtek/rtl8366rb-leds.c | 177 ++++++++++++++++
 drivers/net/dsa/realtek/rtl8366rb.c      | 258 +----------------------
 drivers/net/dsa/realtek/rtl8366rb.h      | 107 ++++++++++
 5 files changed, 299 insertions(+), 252 deletions(-)
 create mode 100644 drivers/net/dsa/realtek/rtl8366rb-leds.c
 create mode 100644 drivers/net/dsa/realtek/rtl8366rb.h

diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 6989972eebc30..10687722d14c0 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -43,4 +43,10 @@ config NET_DSA_REALTEK_RTL8366RB
 	help
 	  Select to enable support for Realtek RTL8366RB.
 
+config NET_DSA_REALTEK_RTL8366RB_LEDS
+	bool "Support RTL8366RB LED control"
+	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
+	depends on NET_DSA_REALTEK_RTL8366RB
+	default NET_DSA_REALTEK_RTL8366RB
+
 endif
diff --git a/drivers/net/dsa/realtek/Makefile b/drivers/net/dsa/realtek/Makefile
index 35491dc20d6d6..17367bcba496c 100644
--- a/drivers/net/dsa/realtek/Makefile
+++ b/drivers/net/dsa/realtek/Makefile
@@ -12,4 +12,7 @@ endif
 
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8366RB) += rtl8366.o
 rtl8366-objs 				:= rtl8366-core.o rtl8366rb.o
+ifdef CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS
+rtl8366-objs 				+= rtl8366rb-leds.o
+endif
 obj-$(CONFIG_NET_DSA_REALTEK_RTL8365MB) += rtl8365mb.o
diff --git a/drivers/net/dsa/realtek/rtl8366rb-leds.c b/drivers/net/dsa/realtek/rtl8366rb-leds.c
new file mode 100644
index 0000000000000..99c890681ae60
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb-leds.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/bitops.h>
+#include <linux/regmap.h>
+#include <net/dsa.h>
+#include "rtl83xx.h"
+#include "rtl8366rb.h"
+
+static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
+{
+	switch (led_group) {
+	case 0:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 1:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 2:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	case 3:
+		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
+	default:
+		return 0;
+	}
+}
+
+static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+	u32 val;
+
+	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
+			  &val);
+	if (ret) {
+		dev_err(priv->dev, "error reading LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
+}
+
+static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
+{
+	struct realtek_priv *priv = led->priv;
+	u8 led_group = led->led_group;
+	u8 port_num = led->port_num;
+	int ret;
+
+	ret = regmap_update_bits(priv->map,
+				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
+				 rtl8366rb_led_group_port_mask(led_group,
+							       port_num),
+				 enable ? 0xffff : 0);
+	if (ret) {
+		dev_err(priv->dev, "error updating LED on port %d group %d\n",
+			led_group, port_num);
+		return ret;
+	}
+
+	/* Change the LED group to manual controlled LEDs if required */
+	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
+					 RTL8366RB_LEDGROUP_FORCE);
+
+	if (ret) {
+		dev_err(priv->dev, "error updating LED GROUP group %d\n",
+			led_group);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int
+rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
+				       enum led_brightness brightness)
+{
+	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
+						 cdev);
+
+	return rb8366rb_set_port_led(led, brightness == LED_ON);
+}
+
+static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
+			       struct fwnode_handle *led_fwnode)
+{
+	struct rtl8366rb *rb = priv->chip_data;
+	struct led_init_data init_data = { };
+	enum led_default_state state;
+	struct rtl8366rb_led *led;
+	u32 led_group;
+	int ret;
+
+	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
+	if (ret)
+		return ret;
+
+	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
+		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
+			 led_group, dp->index);
+		return -EINVAL;
+	}
+
+	led = &rb->leds[dp->index][led_group];
+	led->port_num = dp->index;
+	led->led_group = led_group;
+	led->priv = priv;
+
+	state = led_init_default_state_get(led_fwnode);
+	switch (state) {
+	case LEDS_DEFSTATE_ON:
+		led->cdev.brightness = 1;
+		rb8366rb_set_port_led(led, 1);
+		break;
+	case LEDS_DEFSTATE_KEEP:
+		led->cdev.brightness =
+			rb8366rb_get_port_led(led);
+		break;
+	case LEDS_DEFSTATE_OFF:
+	default:
+		led->cdev.brightness = 0;
+		rb8366rb_set_port_led(led, 0);
+	}
+
+	led->cdev.max_brightness = 1;
+	led->cdev.brightness_set_blocking =
+		rtl8366rb_cled_brightness_set_blocking;
+	init_data.fwnode = led_fwnode;
+	init_data.devname_mandatory = true;
+
+	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
+					 dp->ds->index, dp->index, led_group);
+	if (!init_data.devicename)
+		return -ENOMEM;
+
+	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
+	if (ret) {
+		dev_warn(priv->dev, "Failed to init LED %d for port %d",
+			 led_group, dp->index);
+		return ret;
+	}
+
+	return 0;
+}
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	struct dsa_switch *ds = &priv->ds;
+	struct device_node *leds_np;
+	struct dsa_port *dp;
+	int ret = 0;
+
+	dsa_switch_for_each_port(dp, ds) {
+		if (!dp->dn)
+			continue;
+
+		leds_np = of_get_child_by_name(dp->dn, "leds");
+		if (!leds_np) {
+			dev_dbg(priv->dev, "No leds defined for port %d",
+				dp->index);
+			continue;
+		}
+
+		for_each_child_of_node_scoped(leds_np, led_np) {
+			ret = rtl8366rb_setup_led(priv, dp,
+						  of_fwnode_handle(led_np));
+			if (ret)
+				break;
+		}
+
+		of_node_put(leds_np);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
diff --git a/drivers/net/dsa/realtek/rtl8366rb.c b/drivers/net/dsa/realtek/rtl8366rb.c
index 4c4a95d4380ce..f54771cab56d4 100644
--- a/drivers/net/dsa/realtek/rtl8366rb.c
+++ b/drivers/net/dsa/realtek/rtl8366rb.c
@@ -27,11 +27,7 @@
 #include "realtek-smi.h"
 #include "realtek-mdio.h"
 #include "rtl83xx.h"
-
-#define RTL8366RB_PORT_NUM_CPU		5
-#define RTL8366RB_NUM_PORTS		6
-#define RTL8366RB_PHY_NO_MAX		4
-#define RTL8366RB_PHY_ADDR_MAX		31
+#include "rtl8366rb.h"
 
 /* Switch Global Configuration register */
 #define RTL8366RB_SGCR				0x0000
@@ -176,39 +172,6 @@
  */
 #define RTL8366RB_VLAN_INGRESS_CTRL2_REG	0x037f
 
-/* LED control registers */
-/* The LED blink rate is global; it is used by all triggers in all groups. */
-#define RTL8366RB_LED_BLINKRATE_REG		0x0430
-#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
-#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
-#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
-#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
-#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
-#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
-#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
-
-/* LED trigger event for each group */
-#define RTL8366RB_LED_CTRL_REG			0x0431
-#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
-	(4 * (led_group))
-#define RTL8366RB_LED_CTRL_MASK(led_group)	\
-	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
-
-/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
- * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
- * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
- */
-#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
-#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
-#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
-	((led_group) <= 1 ? \
-		RTL8366RB_LED_0_1_CTRL_REG : \
-		RTL8366RB_LED_2_3_CTRL_REG)
-#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
-#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
-#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
-
 #define RTL8366RB_MIB_COUNT			33
 #define RTL8366RB_GLOBAL_MIB_COUNT		1
 #define RTL8366RB_MIB_COUNTER_PORT_OFFSET	0x0050
@@ -244,7 +207,6 @@
 #define RTL8366RB_PORT_STATUS_AN_MASK		0x0080
 
 #define RTL8366RB_NUM_VLANS		16
-#define RTL8366RB_NUM_LEDGROUPS		4
 #define RTL8366RB_NUM_VIDS		4096
 #define RTL8366RB_PRIORITYMAX		7
 #define RTL8366RB_NUM_FIDS		8
@@ -351,46 +313,6 @@
 #define RTL8366RB_GREEN_FEATURE_TX	BIT(0)
 #define RTL8366RB_GREEN_FEATURE_RX	BIT(2)
 
-enum rtl8366_ledgroup_mode {
-	RTL8366RB_LEDGROUP_OFF			= 0x0,
-	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
-	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
-	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
-	RTL8366RB_LEDGROUP_SPD100		= 0x4,
-	RTL8366RB_LEDGROUP_SPD10		= 0x5,
-	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
-	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
-	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
-	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
-	RTL8366RB_LEDGROUP_FIBER		= 0xa,
-	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
-	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
-	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
-	RTL8366RB_LEDGROUP_MASTER		= 0xe,
-	RTL8366RB_LEDGROUP_FORCE		= 0xf,
-
-	__RTL8366RB_LEDGROUP_MODE_MAX
-};
-
-struct rtl8366rb_led {
-	u8 port_num;
-	u8 led_group;
-	struct realtek_priv *priv;
-	struct led_classdev cdev;
-};
-
-/**
- * struct rtl8366rb - RTL8366RB-specific data
- * @max_mtu: per-port max MTU setting
- * @pvid_enabled: if PVID is set for respective port
- * @leds: per-port and per-ledgroup led info
- */
-struct rtl8366rb {
-	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
-	bool pvid_enabled[RTL8366RB_NUM_PORTS];
-	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
-};
-
 static struct rtl8366_mib_counter rtl8366rb_mib_counters[] = {
 	{ 0,  0, 4, "IfInOctets"				},
 	{ 0,  4, 4, "EtherStatsOctets"				},
@@ -831,9 +753,10 @@ static int rtl8366rb_jam_table(const struct rtl8366rb_jam_tbl_entry *jam_table,
 	return 0;
 }
 
-static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
-				      u8 led_group,
-				      enum rtl8366_ledgroup_mode mode)
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode)
 {
 	int ret;
 	u32 val;
@@ -850,144 +773,7 @@ static int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
 	return 0;
 }
 
-static inline u32 rtl8366rb_led_group_port_mask(u8 led_group, u8 port)
-{
-	switch (led_group) {
-	case 0:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 1:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 2:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	case 3:
-		return FIELD_PREP(RTL8366RB_LED_0_X_CTRL_MASK, BIT(port));
-	default:
-		return 0;
-	}
-}
-
-static int rb8366rb_get_port_led(struct rtl8366rb_led *led)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-	u32 val;
-
-	ret = regmap_read(priv->map, RTL8366RB_LED_X_X_CTRL_REG(led_group),
-			  &val);
-	if (ret) {
-		dev_err(priv->dev, "error reading LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	return !!(val & rtl8366rb_led_group_port_mask(led_group, port_num));
-}
-
-static int rb8366rb_set_port_led(struct rtl8366rb_led *led, bool enable)
-{
-	struct realtek_priv *priv = led->priv;
-	u8 led_group = led->led_group;
-	u8 port_num = led->port_num;
-	int ret;
-
-	ret = regmap_update_bits(priv->map,
-				 RTL8366RB_LED_X_X_CTRL_REG(led_group),
-				 rtl8366rb_led_group_port_mask(led_group,
-							       port_num),
-				 enable ? 0xffff : 0);
-	if (ret) {
-		dev_err(priv->dev, "error updating LED on port %d group %d\n",
-			led_group, port_num);
-		return ret;
-	}
-
-	/* Change the LED group to manual controlled LEDs if required */
-	ret = rb8366rb_set_ledgroup_mode(priv, led_group,
-					 RTL8366RB_LEDGROUP_FORCE);
-
-	if (ret) {
-		dev_err(priv->dev, "error updating LED GROUP group %d\n",
-			led_group);
-		return ret;
-	}
-
-	return 0;
-}
-
-static int
-rtl8366rb_cled_brightness_set_blocking(struct led_classdev *ldev,
-				       enum led_brightness brightness)
-{
-	struct rtl8366rb_led *led = container_of(ldev, struct rtl8366rb_led,
-						 cdev);
-
-	return rb8366rb_set_port_led(led, brightness == LED_ON);
-}
-
-static int rtl8366rb_setup_led(struct realtek_priv *priv, struct dsa_port *dp,
-			       struct fwnode_handle *led_fwnode)
-{
-	struct rtl8366rb *rb = priv->chip_data;
-	struct led_init_data init_data = { };
-	enum led_default_state state;
-	struct rtl8366rb_led *led;
-	u32 led_group;
-	int ret;
-
-	ret = fwnode_property_read_u32(led_fwnode, "reg", &led_group);
-	if (ret)
-		return ret;
-
-	if (led_group >= RTL8366RB_NUM_LEDGROUPS) {
-		dev_warn(priv->dev, "Invalid LED reg %d defined for port %d",
-			 led_group, dp->index);
-		return -EINVAL;
-	}
-
-	led = &rb->leds[dp->index][led_group];
-	led->port_num = dp->index;
-	led->led_group = led_group;
-	led->priv = priv;
-
-	state = led_init_default_state_get(led_fwnode);
-	switch (state) {
-	case LEDS_DEFSTATE_ON:
-		led->cdev.brightness = 1;
-		rb8366rb_set_port_led(led, 1);
-		break;
-	case LEDS_DEFSTATE_KEEP:
-		led->cdev.brightness =
-			rb8366rb_get_port_led(led);
-		break;
-	case LEDS_DEFSTATE_OFF:
-	default:
-		led->cdev.brightness = 0;
-		rb8366rb_set_port_led(led, 0);
-	}
-
-	led->cdev.max_brightness = 1;
-	led->cdev.brightness_set_blocking =
-		rtl8366rb_cled_brightness_set_blocking;
-	init_data.fwnode = led_fwnode;
-	init_data.devname_mandatory = true;
-
-	init_data.devicename = kasprintf(GFP_KERNEL, "Realtek-%d:0%d:%d",
-					 dp->ds->index, dp->index, led_group);
-	if (!init_data.devicename)
-		return -ENOMEM;
-
-	ret = devm_led_classdev_register_ext(priv->dev, &led->cdev, &init_data);
-	if (ret) {
-		dev_warn(priv->dev, "Failed to init LED %d for port %d",
-			 led_group, dp->index);
-		return ret;
-	}
-
-	return 0;
-}
-
+/* This code is used also with LEDs disabled */
 static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 {
 	int ret = 0;
@@ -1008,38 +794,6 @@ static int rtl8366rb_setup_all_leds_off(struct realtek_priv *priv)
 	return ret;
 }
 
-static int rtl8366rb_setup_leds(struct realtek_priv *priv)
-{
-	struct dsa_switch *ds = &priv->ds;
-	struct device_node *leds_np;
-	struct dsa_port *dp;
-	int ret = 0;
-
-	dsa_switch_for_each_port(dp, ds) {
-		if (!dp->dn)
-			continue;
-
-		leds_np = of_get_child_by_name(dp->dn, "leds");
-		if (!leds_np) {
-			dev_dbg(priv->dev, "No leds defined for port %d",
-				dp->index);
-			continue;
-		}
-
-		for_each_child_of_node_scoped(leds_np, led_np) {
-			ret = rtl8366rb_setup_led(priv, dp,
-						  of_fwnode_handle(led_np));
-			if (ret)
-				break;
-		}
-
-		of_node_put(leds_np);
-		if (ret)
-			return ret;
-	}
-	return 0;
-}
-
 static int rtl8366rb_setup(struct dsa_switch *ds)
 {
 	struct realtek_priv *priv = ds->priv;
diff --git a/drivers/net/dsa/realtek/rtl8366rb.h b/drivers/net/dsa/realtek/rtl8366rb.h
new file mode 100644
index 0000000000000..685ff3275faa1
--- /dev/null
+++ b/drivers/net/dsa/realtek/rtl8366rb.h
@@ -0,0 +1,107 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _RTL8366RB_H
+#define _RTL8366RB_H
+
+#include "realtek.h"
+
+#define RTL8366RB_PORT_NUM_CPU		5
+#define RTL8366RB_NUM_PORTS		6
+#define RTL8366RB_PHY_NO_MAX		4
+#define RTL8366RB_NUM_LEDGROUPS		4
+#define RTL8366RB_PHY_ADDR_MAX		31
+
+/* LED control registers */
+/* The LED blink rate is global; it is used by all triggers in all groups. */
+#define RTL8366RB_LED_BLINKRATE_REG		0x0430
+#define RTL8366RB_LED_BLINKRATE_MASK		0x0007
+#define RTL8366RB_LED_BLINKRATE_28MS		0x0000
+#define RTL8366RB_LED_BLINKRATE_56MS		0x0001
+#define RTL8366RB_LED_BLINKRATE_84MS		0x0002
+#define RTL8366RB_LED_BLINKRATE_111MS		0x0003
+#define RTL8366RB_LED_BLINKRATE_222MS		0x0004
+#define RTL8366RB_LED_BLINKRATE_446MS		0x0005
+
+/* LED trigger event for each group */
+#define RTL8366RB_LED_CTRL_REG			0x0431
+#define RTL8366RB_LED_CTRL_OFFSET(led_group)	\
+	(4 * (led_group))
+#define RTL8366RB_LED_CTRL_MASK(led_group)	\
+	(0xf << RTL8366RB_LED_CTRL_OFFSET(led_group))
+
+/* The RTL8366RB_LED_X_X registers are used to manually set the LED state only
+ * when the corresponding LED group in RTL8366RB_LED_CTRL_REG is
+ * RTL8366RB_LEDGROUP_FORCE. Otherwise, it is ignored.
+ */
+#define RTL8366RB_LED_0_1_CTRL_REG		0x0432
+#define RTL8366RB_LED_2_3_CTRL_REG		0x0433
+#define RTL8366RB_LED_X_X_CTRL_REG(led_group)	\
+	((led_group) <= 1 ? \
+		RTL8366RB_LED_0_1_CTRL_REG : \
+		RTL8366RB_LED_2_3_CTRL_REG)
+#define RTL8366RB_LED_0_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_1_CTRL_MASK		GENMASK(11, 6)
+#define RTL8366RB_LED_2_X_CTRL_MASK		GENMASK(5, 0)
+#define RTL8366RB_LED_X_3_CTRL_MASK		GENMASK(11, 6)
+
+enum rtl8366_ledgroup_mode {
+	RTL8366RB_LEDGROUP_OFF			= 0x0,
+	RTL8366RB_LEDGROUP_DUP_COL		= 0x1,
+	RTL8366RB_LEDGROUP_LINK_ACT		= 0x2,
+	RTL8366RB_LEDGROUP_SPD1000		= 0x3,
+	RTL8366RB_LEDGROUP_SPD100		= 0x4,
+	RTL8366RB_LEDGROUP_SPD10		= 0x5,
+	RTL8366RB_LEDGROUP_SPD1000_ACT		= 0x6,
+	RTL8366RB_LEDGROUP_SPD100_ACT		= 0x7,
+	RTL8366RB_LEDGROUP_SPD10_ACT		= 0x8,
+	RTL8366RB_LEDGROUP_SPD100_10_ACT	= 0x9,
+	RTL8366RB_LEDGROUP_FIBER		= 0xa,
+	RTL8366RB_LEDGROUP_AN_FAULT		= 0xb,
+	RTL8366RB_LEDGROUP_LINK_RX		= 0xc,
+	RTL8366RB_LEDGROUP_LINK_TX		= 0xd,
+	RTL8366RB_LEDGROUP_MASTER		= 0xe,
+	RTL8366RB_LEDGROUP_FORCE		= 0xf,
+
+	__RTL8366RB_LEDGROUP_MODE_MAX
+};
+
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+
+struct rtl8366rb_led {
+	u8 port_num;
+	u8 led_group;
+	struct realtek_priv *priv;
+	struct led_classdev cdev;
+};
+
+int rtl8366rb_setup_leds(struct realtek_priv *priv);
+
+#else
+
+static inline int rtl8366rb_setup_leds(struct realtek_priv *priv)
+{
+	return 0;
+}
+
+#endif /* IS_ENABLED(CONFIG_LEDS_CLASS) */
+
+/**
+ * struct rtl8366rb - RTL8366RB-specific data
+ * @max_mtu: per-port max MTU setting
+ * @pvid_enabled: if PVID is set for respective port
+ * @leds: per-port and per-ledgroup led info
+ */
+struct rtl8366rb {
+	unsigned int max_mtu[RTL8366RB_NUM_PORTS];
+	bool pvid_enabled[RTL8366RB_NUM_PORTS];
+#if IS_ENABLED(CONFIG_NET_DSA_REALTEK_RTL8366RB_LEDS)
+	struct rtl8366rb_led leds[RTL8366RB_NUM_PORTS][RTL8366RB_NUM_LEDGROUPS];
+#endif
+};
+
+/* This code is used also with LEDs disabled */
+int rb8366rb_set_ledgroup_mode(struct realtek_priv *priv,
+			       u8 led_group,
+			       enum rtl8366_ledgroup_mode mode);
+
+#endif /* _RTL8366RB_H */

From 02cfe2b6529c6c5fcf39d52a826927f4f93392af Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 24 Feb 2025 11:27:02 +0100
Subject: [PATCH 1032/2753] pidfs: remove d_op->d_delete

Pidfs only deals with unhashed dentries and there's currently no way for
them to become hashed. So remove d_op->d_delete.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/pidfs.c b/fs/pidfs.c
index 63f9699ebac36..c0478b3c55d9f 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -521,7 +521,6 @@ static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
 }
 
 const struct dentry_operations pidfs_dentry_operations = {
-	.d_delete	= always_delete_dentry,
 	.d_dname	= pidfs_dname,
 	.d_prune	= stashed_dentry_prune,
 };

From 425e3e3bd62c568a4365af0923d6ebad71a7dcfc Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Mon, 24 Feb 2025 11:30:35 +0100
Subject: [PATCH 1033/2753] nsfs: remove d_op->d_delete

Nsfs only deals with unhashed dentries and there's currently no way for
them to become hashed. So remove d_op->d_delete.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/nsfs.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/fs/nsfs.c b/fs/nsfs.c
index 663f8656158d5..f7fddf8ecf73f 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -37,7 +37,6 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
 }
 
 const struct dentry_operations ns_dentry_operations = {
-	.d_delete	= always_delete_dentry,
 	.d_dname	= ns_dname,
 	.d_prune	= stashed_dentry_prune,
 };

From 36e1b81f599a093ec7477e4593e110104adcfb96 Mon Sep 17 00:00:00 2001
From: Ken Raeburn <raeburn@redhat.com>
Date: Wed, 19 Feb 2025 17:56:00 -0500
Subject: [PATCH 1034/2753] dm vdo: add missing spin_lock_init

Signed-off-by: Ken Raeburn <raeburn@redhat.com>
Signed-off-by: Matthew Sakai <msakai@redhat.com>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
---
 drivers/md/dm-vdo/dedupe.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/md/dm-vdo/dedupe.c b/drivers/md/dm-vdo/dedupe.c
index b6f8e2dc7729f..3f3d29af1be47 100644
--- a/drivers/md/dm-vdo/dedupe.c
+++ b/drivers/md/dm-vdo/dedupe.c
@@ -2178,6 +2178,7 @@ static int initialize_index(struct vdo *vdo, struct hash_zones *zones)
 
 	vdo_set_dedupe_index_timeout_interval(vdo_dedupe_index_timeout_interval);
 	vdo_set_dedupe_index_min_timer_interval(vdo_dedupe_index_min_timer_interval);
+	spin_lock_init(&zones->lock);
 
 	/*
 	 * Since we will save up the timeouts that would have been reported but were ratelimited,

From 5b0c02f9b8acf2a791e531bbc09acae2d51f4f9b Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Sat, 22 Feb 2025 20:39:57 +0100
Subject: [PATCH 1035/2753] ASoC: es8328: fix route from DAC to output

The ES8328 codec driver, which is also used for the ES8388 chip that
appears to have an identical register map, claims that the output can
either take the route from DAC->Mixer->Output or through DAC->Output
directly. To the best of what I could find, this is not true, and
creates problems.

Without DACCONTROL17 bit index 7 set for the left channel, as well as
DACCONTROL20 bit index 7 set for the right channel, I cannot get any
analog audio out on Left Out 2 and Right Out 2 respectively, despite the
DAPM routes claiming that this should be possible. Furthermore, the same
is the case for Left Out 1 and Right Out 1, showing that those two don't
have a direct route from DAC to output bypassing the mixer either.

Those control bits toggle whether the DACs are fed (stale bread?) into
their respective mixers. If one "unmutes" the mixer controls in
alsamixer, then sure, the audio output works, but if it doesn't work
without the mixer being fed the DAC input then evidently it's not a
direct output from the DAC.

ES8328/ES8388 are seemingly not alone in this. ES8323, which uses a
separate driver for what appears to be a very similar register map,
simply flips those two bits on in its probe function, and then pretends
there is no power management whatsoever for the individual controls.
Fair enough.

My theory as to why nobody has noticed this up to this point is that
everyone just assumes it's their fault when they had to unmute an
additional control in ALSA.

Fix this in the es8328 driver by removing the erroneous direct route,
then get rid of the playback switch controls and have those bits tied to
the mixer's widget instead, which until now had no register to play
with.

Fixes: 567e4f98922c ("ASoC: add es8328 codec driver")
Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Link: https://patch.msgid.link/20250222-es8328-route-bludgeoning-v1-1-99bfb7fb22d9@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/es8328.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index f3c97da798dc8..76159c45e6b52 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -233,7 +233,6 @@ static const struct snd_kcontrol_new es8328_right_line_controls =
 
 /* Left Mixer */
 static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
-	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL17, 7, 1, 0),
 	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL17, 6, 1, 0),
 	SOC_DAPM_SINGLE("Right Playback Switch", ES8328_DACCONTROL18, 7, 1, 0),
 	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL18, 6, 1, 0),
@@ -243,7 +242,6 @@ static const struct snd_kcontrol_new es8328_left_mixer_controls[] = {
 static const struct snd_kcontrol_new es8328_right_mixer_controls[] = {
 	SOC_DAPM_SINGLE("Left Playback Switch", ES8328_DACCONTROL19, 7, 1, 0),
 	SOC_DAPM_SINGLE("Left Bypass Switch", ES8328_DACCONTROL19, 6, 1, 0),
-	SOC_DAPM_SINGLE("Playback Switch", ES8328_DACCONTROL20, 7, 1, 0),
 	SOC_DAPM_SINGLE("Right Bypass Switch", ES8328_DACCONTROL20, 6, 1, 0),
 };
 
@@ -336,10 +334,10 @@ static const struct snd_soc_dapm_widget es8328_dapm_widgets[] = {
 	SND_SOC_DAPM_DAC("Left DAC", "Left Playback", ES8328_DACPOWER,
 			ES8328_DACPOWER_LDAC_OFF, 1),
 
-	SND_SOC_DAPM_MIXER("Left Mixer", SND_SOC_NOPM, 0, 0,
+	SND_SOC_DAPM_MIXER("Left Mixer", ES8328_DACCONTROL17, 7, 0,
 		&es8328_left_mixer_controls[0],
 		ARRAY_SIZE(es8328_left_mixer_controls)),
-	SND_SOC_DAPM_MIXER("Right Mixer", SND_SOC_NOPM, 0, 0,
+	SND_SOC_DAPM_MIXER("Right Mixer", ES8328_DACCONTROL20, 7, 0,
 		&es8328_right_mixer_controls[0],
 		ARRAY_SIZE(es8328_right_mixer_controls)),
 
@@ -418,19 +416,14 @@ static const struct snd_soc_dapm_route es8328_dapm_routes[] = {
 	{ "Right Line Mux", "PGA", "Right PGA Mux" },
 	{ "Right Line Mux", "Differential", "Differential Mux" },
 
-	{ "Left Out 1", NULL, "Left DAC" },
-	{ "Right Out 1", NULL, "Right DAC" },
-	{ "Left Out 2", NULL, "Left DAC" },
-	{ "Right Out 2", NULL, "Right DAC" },
-
-	{ "Left Mixer", "Playback Switch", "Left DAC" },
+	{ "Left Mixer", NULL, "Left DAC" },
 	{ "Left Mixer", "Left Bypass Switch", "Left Line Mux" },
 	{ "Left Mixer", "Right Playback Switch", "Right DAC" },
 	{ "Left Mixer", "Right Bypass Switch", "Right Line Mux" },
 
 	{ "Right Mixer", "Left Playback Switch", "Left DAC" },
 	{ "Right Mixer", "Left Bypass Switch", "Left Line Mux" },
-	{ "Right Mixer", "Playback Switch", "Right DAC" },
+	{ "Right Mixer", NULL, "Right DAC" },
 	{ "Right Mixer", "Right Bypass Switch", "Right Line Mux" },
 
 	{ "DAC DIG", NULL, "DAC STM" },

From 11d963d44c77261d6a948f3745bbd678eef4b83b Mon Sep 17 00:00:00 2001
From: Baochen Qiang <quic_bqiang@quicinc.com>
Date: Mon, 9 Dec 2024 10:41:46 +0800
Subject: [PATCH 1036/2753] wifi: ath12k: use link specific bss_conf as well in
 ath12k_mac_vif_cache_flush()

Commit 3952657848c0 ("wifi: ath12k: Use mac80211 vif's link_conf instead of
bss_conf") aims at, where applicable, replacing all usage of vif's bss_conf
with link specific bss_conff, but missed one instance in
ath12k_mac_vif_cache_flush(). This results in wrong configurations passed
to ath12k_mac_bss_info_changed() when the link in question is not the default
link.

Change to use the link specific bss_conf to fix this issue.

Tested-on: WCN7850 hw2.0 PCI WLAN.HMT.1.0-03427-QCAHMTSWPL_V1.0_V2.0_SILICONZ-1.15378.4

Fixes: 3952657848c0 ("wifi: ath12k: Use mac80211 vif's link_conf instead of bss_conf")
Signed-off-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20241209024146.3282-1-quic_bqiang@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 27d2fad1b915c..3e3afdc56fc96 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -8346,6 +8346,7 @@ static void ath12k_mac_vif_cache_flush(struct ath12k *ar, struct ath12k_link_vif
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
 	struct ath12k_vif_cache *cache = ahvif->cache[arvif->link_id];
 	struct ath12k_base *ab = ar->ab;
+	struct ieee80211_bss_conf *link_conf;
 
 	int ret;
 
@@ -8364,7 +8365,13 @@ static void ath12k_mac_vif_cache_flush(struct ath12k *ar, struct ath12k_link_vif
 	}
 
 	if (cache->bss_conf_changed) {
-		ath12k_mac_bss_info_changed(ar, arvif, &vif->bss_conf,
+		link_conf = ath12k_mac_get_link_bss_conf(arvif);
+		if (!link_conf) {
+			ath12k_warn(ar->ab, "unable to access bss link conf in cache flush for vif %pM link %u\n",
+				    vif->addr, arvif->link_id);
+			return;
+		}
+		ath12k_mac_bss_info_changed(ar, arvif, link_conf,
 					    cache->bss_conf_changed);
 	}
 

From e180a01bf2c4a67db13d70d2d91410a8c6f74be3 Mon Sep 17 00:00:00 2001
From: Roopni Devanathan <quic_rdevanat@quicinc.com>
Date: Fri, 21 Feb 2025 09:42:50 +0530
Subject: [PATCH 1037/2753] wifi: ath12k: Add NULL check to validate tpc_stats

While processing TPC stats received from firmware, there are chances that
the tpc_stats might not be filled and the data is not available. This can
happen under two scenarios. First, when firmware sends a non-zero event
count before event count 0. When this happens, tpc_stats will be checked
for data before memory allocation and the tpc_stats will be unavailable.
Second, when memory allocation failed when event count received is 0 and
the firmware still sends a non-zero event. When this happens, memory will
not be allocated for tpc_stats though event count is 0, so when non-zero
event count is received, tpc_stats will be empty. There are checks to
validate if tpc_stats variable is filled that are used in two subsequent
places, but these are placed after tpc_stats is dereference without
checking if it is NULL or has valid data.

Fix this by removing the mentioned checks and adding a NULL check after
assigning tpc_stats to check if it is valid.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Closes: https://scan7.scan.coverity.com/#/project-view/52668/11354?selectedIssue=1637145
Fixes: f0c3bb78e42f ("wifi: ath12k: Add Support to Parse TPC Event from Firmware")
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250221041250.769491-1-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 1d6b7af546bf7..96c473c4adc65 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -8442,6 +8442,10 @@ static void ath12k_wmi_process_tpc_stats(struct ath12k_base *ab,
 	}
 
 	tpc_stats = ar->debug.tpc_stats;
+	if (!tpc_stats) {
+		ath12k_warn(ab, "tpc stats memory unavailable\n");
+		goto unlock;
+	}
 
 	if (!(event_count == 0)) {
 		if (event_count != tpc_stats->event_count + 1) {
@@ -8460,13 +8464,12 @@ static void ath12k_wmi_process_tpc_stats(struct ath12k_base *ab,
 				  ath12k_wmi_tpc_stats_event_parser,
 				  tpc_stats);
 	if (ret) {
-		if (tpc_stats)
-			ath12k_wmi_free_tpc_stats_mem(ar);
+		ath12k_wmi_free_tpc_stats_mem(ar);
 		ath12k_warn(ab, "failed to parse tpc_stats tlv: %d\n", ret);
 		goto unlock;
 	}
 
-	if (tpc_stats && tpc_stats->end_of_event)
+	if (tpc_stats->end_of_event)
 		complete(&ar->debug.tpc_complete);
 
 unlock:

From 0fe8813baf4b2e865d3b2c735ce1a15b86002c74 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 17 Jan 2025 06:41:07 -0800
Subject: [PATCH 1038/2753] perf/core: Add RCU read lock protection to
 perf_iterate_ctx()

The perf_iterate_ctx() function performs RCU list traversal but
currently lacks RCU read lock protection. This causes lockdep warnings
when running perf probe with unshare(1) under CONFIG_PROVE_RCU_LIST=y:

	WARNING: suspicious RCU usage
	kernel/events/core.c:8168 RCU-list traversed in non-reader section!!

	 Call Trace:
	  lockdep_rcu_suspicious
	  ? perf_event_addr_filters_apply
	  perf_iterate_ctx
	  perf_event_exec
	  begin_new_exec
	  ? load_elf_phdrs
	  load_elf_binary
	  ? lock_acquire
	  ? find_held_lock
	  ? bprm_execve
	  bprm_execve
	  do_execveat_common.isra.0
	  __x64_sys_execve
	  do_syscall_64
	  entry_SYSCALL_64_after_hwframe

This protection was previously present but was removed in commit
bd2756811766 ("perf: Rewrite core context handling"). Add back the
necessary rcu_read_lock()/rcu_read_unlock() pair around
perf_iterate_ctx() call in perf_event_exec().

[ mingo: Use scoped_guard() as suggested by Peter ]

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Signed-off-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117-fix_perf_rcu-v1-1-13cb9210fc6a@debian.org
---
 kernel/events/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index bcb09e011e9e1..7dabbcaf825a0 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -8321,7 +8321,8 @@ void perf_event_exec(void)
 
 	perf_event_enable_on_exec(ctx);
 	perf_event_remove_on_exec(ctx);
-	perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
+	scoped_guard(rcu)
+		perf_iterate_ctx(ctx, perf_event_addr_filters_exec, NULL, true);
 
 	perf_unpin_context(ctx);
 	put_ctx(ctx);

From 2016066c66192a99d9e0ebf433789c490a6785a2 Mon Sep 17 00:00:00 2001
From: Luo Gengkun <luogengkun@huaweicloud.com>
Date: Wed, 22 Jan 2025 07:33:56 +0000
Subject: [PATCH 1039/2753] perf/core: Order the PMU list to fix warning about
 unordered pmu_ctx_list

Syskaller triggers a warning due to prev_epc->pmu != next_epc->pmu in
perf_event_swap_task_ctx_data(). vmcore shows that two lists have the same
perf_event_pmu_context, but not in the same order.

The problem is that the order of pmu_ctx_list for the parent is impacted by
the time when an event/PMU is added. While the order for a child is
impacted by the event order in the pinned_groups and flexible_groups. So
the order of pmu_ctx_list in the parent and child may be different.

To fix this problem, insert the perf_event_pmu_context to its proper place
after iteration of the pmu_ctx_list.

The follow testcase can trigger above warning:

 # perf record -e cycles --call-graph lbr -- taskset -c 3 ./a.out &
 # perf stat -e cpu-clock,cs -p xxx // xxx is the pid of a.out

 test.c

 void main() {
        int count = 0;
        pid_t pid;

        printf("%d running\n", getpid());
        sleep(30);
        printf("running\n");

        pid = fork();
        if (pid == -1) {
                printf("fork error\n");
                return;
        }
        if (pid == 0) {
                while (1) {
                        count++;
                }
        } else {
                while (1) {
                        count++;
                }
        }
 }

The testcase first opens an LBR event, so it will allocate task_ctx_data,
and then open tracepoint and software events, so the parent context will
have 3 different perf_event_pmu_contexts. On inheritance, child ctx will
insert the perf_event_pmu_context in another order and the warning will
trigger.

[ mingo: Tidied up the changelog. ]

Fixes: bd2756811766 ("perf: Rewrite core context handling")
Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250122073356.1824736-1-luogengkun@huaweicloud.com
---
 kernel/events/core.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7dabbcaf825a0..086d46d096963 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4950,7 +4950,7 @@ static struct perf_event_pmu_context *
 find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 		     struct perf_event *event)
 {
-	struct perf_event_pmu_context *new = NULL, *epc;
+	struct perf_event_pmu_context *new = NULL, *pos = NULL, *epc;
 	void *task_ctx_data = NULL;
 
 	if (!ctx->task) {
@@ -5007,12 +5007,19 @@ find_get_pmu_context(struct pmu *pmu, struct perf_event_context *ctx,
 			atomic_inc(&epc->refcount);
 			goto found_epc;
 		}
+		/* Make sure the pmu_ctx_list is sorted by PMU type: */
+		if (!pos && epc->pmu->type > pmu->type)
+			pos = epc;
 	}
 
 	epc = new;
 	new = NULL;
 
-	list_add(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	if (!pos)
+		list_add_tail(&epc->pmu_ctx_entry, &ctx->pmu_ctx_list);
+	else
+		list_add(&epc->pmu_ctx_entry, pos->pmu_ctx_entry.prev);
+
 	epc->ctx = ctx;
 
 found_epc:

From 0da83ab025bc45e9742e87c2cce19bff423377c8 Mon Sep 17 00:00:00 2001
From: Chancel Liu <chancel.liu@nxp.com>
Date: Mon, 17 Feb 2025 10:04:37 +0900
Subject: [PATCH 1040/2753] ASoC: fsl: Rename stream name of SAI DAI driver

If stream names of DAI driver are duplicated there'll be warnings when
machine driver tries to add widgets on a route:

[    8.831335] fsl-asoc-card sound-wm8960: ASoC: sink widget CPU-Playback overwritten
[    8.839917] fsl-asoc-card sound-wm8960: ASoC: source widget CPU-Capture overwritten

Use different stream names to avoid such warnings.
DAI names in AUDMIX are also updated accordingly.

Fixes: 15c958390460 ("ASoC: fsl_sai: Add separate DAI for transmitter and receiver")
Signed-off-by: Chancel Liu <chancel.liu@nxp.com>
Acked-by: Shengjiu Wang <shengjiu.wang@gmail.com>
Link: https://patch.msgid.link/20250217010437.258621-1-chancel.liu@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/fsl/fsl_sai.c    | 6 +++---
 sound/soc/fsl/imx-audmix.c | 4 ++--
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/sound/soc/fsl/fsl_sai.c b/sound/soc/fsl/fsl_sai.c
index c4eb87c5d39e4..9f33dd11d47f6 100644
--- a/sound/soc/fsl/fsl_sai.c
+++ b/sound/soc/fsl/fsl_sai.c
@@ -994,10 +994,10 @@ static struct snd_soc_dai_driver fsl_sai_dai_template[] = {
 	{
 		.name = "sai-tx",
 		.playback = {
-			.stream_name = "CPU-Playback",
+			.stream_name = "SAI-Playback",
 			.channels_min = 1,
 			.channels_max = 32,
-				.rate_min = 8000,
+			.rate_min = 8000,
 			.rate_max = 2822400,
 			.rates = SNDRV_PCM_RATE_KNOT,
 			.formats = FSL_SAI_FORMATS,
@@ -1007,7 +1007,7 @@ static struct snd_soc_dai_driver fsl_sai_dai_template[] = {
 	{
 		.name = "sai-rx",
 		.capture = {
-			.stream_name = "CPU-Capture",
+			.stream_name = "SAI-Capture",
 			.channels_min = 1,
 			.channels_max = 32,
 			.rate_min = 8000,
diff --git a/sound/soc/fsl/imx-audmix.c b/sound/soc/fsl/imx-audmix.c
index 50ecc5f51100e..dac5d4ddacd6e 100644
--- a/sound/soc/fsl/imx-audmix.c
+++ b/sound/soc/fsl/imx-audmix.c
@@ -119,8 +119,8 @@ static const struct snd_soc_ops imx_audmix_be_ops = {
 static const char *name[][3] = {
 	{"HiFi-AUDMIX-FE-0", "HiFi-AUDMIX-FE-1", "HiFi-AUDMIX-FE-2"},
 	{"sai-tx", "sai-tx", "sai-rx"},
-	{"AUDMIX-Playback-0", "AUDMIX-Playback-1", "CPU-Capture"},
-	{"CPU-Playback", "CPU-Playback", "AUDMIX-Capture-0"},
+	{"AUDMIX-Playback-0", "AUDMIX-Playback-1", "SAI-Capture"},
+	{"SAI-Playback", "SAI-Playback", "AUDMIX-Capture-0"},
 };
 
 static int imx_audmix_probe(struct platform_device *pdev)

From d31babd7e304d3b800d36ff74be6739405b985f2 Mon Sep 17 00:00:00 2001
From: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Date: Fri, 21 Feb 2025 21:39:32 +0100
Subject: [PATCH 1041/2753] ASoC: dapm-graph: set fill colour of turned on
 nodes

Some tools like KGraphViewer interpret the "ON" nodes not having an
explicitly set fill colour as them being entirely black, which obscures
the text on them and looks funny. In fact, I thought they were off for
the longest time. Comparing to the output of the `dot` tool, I assume
they are supposed to be white.

Instead of speclawyering over who's in the wrong and must immediately
atone for their wickedness at the altar of RFC2119, just be explicit
about it, set the fillcolor to white, and nobody gets confused.

Signed-off-by: Nicolas Frattaroli <nicolas.frattaroli@collabora.com>
Tested-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Reviewed-by: Luca Ceresoli <luca.ceresoli@bootlin.com>
Link: https://patch.msgid.link/20250221-dapm-graph-node-colour-v1-1-514ed0aa7069@collabora.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 tools/sound/dapm-graph | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/sound/dapm-graph b/tools/sound/dapm-graph
index f14bdfedee8f1..b6196ee5065a4 100755
--- a/tools/sound/dapm-graph
+++ b/tools/sound/dapm-graph
@@ -10,7 +10,7 @@ set -eu
 
 STYLE_COMPONENT_ON="color=dodgerblue;style=bold"
 STYLE_COMPONENT_OFF="color=gray40;style=filled;fillcolor=gray90"
-STYLE_NODE_ON="shape=box,style=bold,color=green4"
+STYLE_NODE_ON="shape=box,style=bold,color=green4,fillcolor=white"
 STYLE_NODE_OFF="shape=box,style=filled,color=gray30,fillcolor=gray95"
 
 # Print usage and exit

From 39ec9eaaa165d297d008d1fa385748430bd18e4d Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 19 Feb 2025 11:53:16 -0800
Subject: [PATCH 1042/2753] coredump: Only sort VMAs when core_sort_vma sysctl
 is set

The sorting of VMAs by size in commit 7d442a33bfe8 ("binfmt_elf: Dump
smaller VMAs first in ELF cores") breaks elfutils[1]. Instead, sort
based on the setting of the new sysctl, core_sort_vma, which defaults
to 0, no sorting.

Reported-by: Michael Stapelberg <michael@stapelberg.ch>
Closes: https://lore.kernel.org/all/20250218085407.61126-1-michael@stapelberg.de/ [1]
Fixes: 7d442a33bfe8 ("binfmt_elf: Dump smaller VMAs first in ELF cores")
Signed-off-by: Kees Cook <kees@kernel.org>
---
 Documentation/admin-guide/sysctl/kernel.rst | 11 +++++++++++
 fs/coredump.c                               | 15 +++++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index a43b78b4b6464..dd49a89a62d35 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -212,6 +212,17 @@ pid>/``).
 This value defaults to 0.
 
 
+core_sort_vma
+=============
+
+The default coredump writes VMAs in address order. By setting
+``core_sort_vma`` to 1, VMAs will be written from smallest size
+to largest size. This is known to break at least elfutils, but
+can be handy when dealing with very large (and truncated)
+coredumps where the more useful debugging details are included
+in the smaller VMAs.
+
+
 core_uses_pid
 =============
 
diff --git a/fs/coredump.c b/fs/coredump.c
index 591700e1b2ce6..4375c70144d0a 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -63,6 +63,7 @@ static void free_vma_snapshot(struct coredump_params *cprm);
 
 static int core_uses_pid;
 static unsigned int core_pipe_limit;
+static unsigned int core_sort_vma;
 static char core_pattern[CORENAME_MAX_SIZE] = "core";
 static int core_name_size = CORENAME_MAX_SIZE;
 unsigned int core_file_note_size_limit = CORE_FILE_NOTE_SIZE_DEFAULT;
@@ -1026,6 +1027,15 @@ static const struct ctl_table coredump_sysctls[] = {
 		.extra1		= (unsigned int *)&core_file_note_size_min,
 		.extra2		= (unsigned int *)&core_file_note_size_max,
 	},
+	{
+		.procname	= "core_sort_vma",
+		.data		= &core_sort_vma,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_douintvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
 };
 
 static int __init init_fs_coredump_sysctls(void)
@@ -1256,8 +1266,9 @@ static bool dump_vma_snapshot(struct coredump_params *cprm)
 		cprm->vma_data_size += m->dump_size;
 	}
 
-	sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta),
-		cmp_vma_size, NULL);
+	if (core_sort_vma)
+		sort(cprm->vma_meta, cprm->vma_count, sizeof(*cprm->vma_meta),
+		     cmp_vma_size, NULL);
 
 	return true;
 }

From bddf10d26e6e5114e7415a0e442ec6f51a559468 Mon Sep 17 00:00:00 2001
From: Tong Tiangen <tongtiangen@huawei.com>
Date: Mon, 24 Feb 2025 11:11:49 +0800
Subject: [PATCH 1043/2753] uprobes: Reject the shared zeropage in
 uprobe_write_opcode()

We triggered the following crash in syzkaller tests:

  BUG: Bad page state in process syz.7.38  pfn:1eff3
  page: refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x1eff3
  flags: 0x3fffff00004004(referenced|reserved|node=0|zone=1|lastcpupid=0x1fffff)
  raw: 003fffff00004004 ffffe6c6c07bfcc8 ffffe6c6c07bfcc8 0000000000000000
  raw: 0000000000000000 0000000000000000 00000000fffffffe 0000000000000000
  page dumped because: PAGE_FLAGS_CHECK_AT_FREE flag(s) set
  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014
  Call Trace:
   <TASK>
   dump_stack_lvl+0x32/0x50
   bad_page+0x69/0xf0
   free_unref_page_prepare+0x401/0x500
   free_unref_page+0x6d/0x1b0
   uprobe_write_opcode+0x460/0x8e0
   install_breakpoint.part.0+0x51/0x80
   register_for_each_vma+0x1d9/0x2b0
   __uprobe_register+0x245/0x300
   bpf_uprobe_multi_link_attach+0x29b/0x4f0
   link_create+0x1e2/0x280
   __sys_bpf+0x75f/0xac0
   __x64_sys_bpf+0x1a/0x30
   do_syscall_64+0x56/0x100
   entry_SYSCALL_64_after_hwframe+0x78/0xe2

   BUG: Bad rss-counter state mm:00000000452453e0 type:MM_FILEPAGES val:-1

The following syzkaller test case can be used to reproduce:

  r2 = creat(&(0x7f0000000000)='./file0\x00', 0x8)
  write$nbd(r2, &(0x7f0000000580)=ANY=[], 0x10)
  r4 = openat(0xffffffffffffff9c, &(0x7f0000000040)='./file0\x00', 0x42, 0x0)
  mmap$IORING_OFF_SQ_RING(&(0x7f0000ffd000/0x3000)=nil, 0x3000, 0x0, 0x12, r4, 0x0)
  r5 = userfaultfd(0x80801)
  ioctl$UFFDIO_API(r5, 0xc018aa3f, &(0x7f0000000040)={0xaa, 0x20})
  r6 = userfaultfd(0x80801)
  ioctl$UFFDIO_API(r6, 0xc018aa3f, &(0x7f0000000140))
  ioctl$UFFDIO_REGISTER(r6, 0xc020aa00, &(0x7f0000000100)={{&(0x7f0000ffc000/0x4000)=nil, 0x4000}, 0x2})
  ioctl$UFFDIO_ZEROPAGE(r5, 0xc020aa04, &(0x7f0000000000)={{&(0x7f0000ffd000/0x1000)=nil, 0x1000}})
  r7 = bpf$PROG_LOAD(0x5, &(0x7f0000000140)={0x2, 0x3, &(0x7f0000000200)=ANY=[@ANYBLOB="1800000000120000000000000000000095"], &(0x7f0000000000)='GPL\x00', 0x7, 0x0, 0x0, 0x0, 0x0, '\x00', 0x0, @fallback=0x30, 0xffffffffffffffff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x10, 0x0, @void, @value}, 0x94)
  bpf$BPF_LINK_CREATE_XDP(0x1c, &(0x7f0000000040)={r7, 0x0, 0x30, 0x1e, @val=@uprobe_multi={&(0x7f0000000080)='./file0\x00', &(0x7f0000000100)=[0x2], 0x0, 0x0, 0x1}}, 0x40)

The cause is that zero pfn is set to the PTE without increasing the RSS
count in mfill_atomic_pte_zeropage() and the refcount of zero folio does
not increase accordingly. Then, the operation on the same pfn is performed
in uprobe_write_opcode()->__replace_page() to unconditional decrease the
RSS count and old_folio's refcount.

Therefore, two bugs are introduced:

 1. The RSS count is incorrect, when process exit, the check_mm() report
    error "Bad rss-count".

 2. The reserved folio (zero folio) is freed when folio->refcount is zero,
    then free_pages_prepare->free_page_is_bad() report error
    "Bad page state".

There is more, the following warning could also theoretically be triggered:

  __replace_page()
    -> ...
      -> folio_remove_rmap_pte()
        -> VM_WARN_ON_FOLIO(is_zero_folio(folio), folio)

Considering that uprobe hit on the zero folio is a very rare case, just
reject zero old folio immediately after get_user_page_vma_remote().

[ mingo: Cleaned up the changelog ]

Fixes: 7396fa818d62 ("uprobes/core: Make background page replacement logic account for rss_stat counters")
Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints")
Signed-off-by: Tong Tiangen <tongtiangen@huawei.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Link: https://lore.kernel.org/r/20250224031149.1598949-1-tongtiangen@huawei.com
---
 kernel/events/uprobes.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index bf2a87a0a3787..af53fbd2d12c4 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -495,6 +495,11 @@ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm,
 	if (ret <= 0)
 		goto put_old;
 
+	if (is_zero_page(old_page)) {
+		ret = -EINVAL;
+		goto put_old;
+	}
+
 	if (WARN(!is_register && PageCompound(old_page),
 		 "uprobe unregister should never work on compound page\n")) {
 		ret = -EINVAL;

From 815291c11acda54515f1af5ce6fe307490de9127 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 08:28:59 -0800
Subject: [PATCH 1044/2753] configfs: update MAINTAINERS

Joel will go back to maintain configfs alone on a time permitting basis.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Joel Becker <jlbec@evilplan.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4ff26fa94895d..089c1178f25a5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5856,7 +5856,6 @@ F:	Documentation/security/snp-tdx-threat-model.rst
 
 CONFIGFS
 M:	Joel Becker <jlbec@evilplan.org>
-M:	Christoph Hellwig <hch@lst.de>
 S:	Supported
 T:	git git://git.infradead.org/users/hch/configfs.git
 F:	fs/configfs/

From f7d5db965f3e132887779c6b449452db2b807caa Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 08:27:21 -0800
Subject: [PATCH 1045/2753] dma-mapping: update MAINTAINERS

Marek has graciously offered to maintain the dma-mapping tree.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 089c1178f25a5..a78eaaa24a699 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6878,7 +6878,6 @@ F:	kernel/dma/map_benchmark.c
 F:	tools/testing/selftests/dma/
 
 DMA MAPPING HELPERS
-M:	Christoph Hellwig <hch@lst.de>
 M:	Marek Szyprowski <m.szyprowski@samsung.com>
 R:	Robin Murphy <robin.murphy@arm.com>
 L:	iommu@lists.linux.dev

From e043dc16c28c8446e66c55adfe7c6e862a6a7bb7 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 21 Feb 2025 14:38:41 +0000
Subject: [PATCH 1046/2753] drm/xe/userptr: restore invalidation list on error
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

On error restore anything still on the pin_list back to the invalidation
list on error. For the actual pin, so long as the vma is tracked on
either list it should get picked up on the next pin, however it looks
possible for the vma to get nuked but still be present on this per vm
pin_list leading to corruption. An alternative might be then to instead
just remove the link when destroying the vma.

v2:
 - Also add some asserts.
 - Keep the overzealous locking so that we are consistent with the docs;
   updating the docs and related bits will be done as a follow up.

Fixes: ed2bdf3b264d ("drm/xe/vm: Subclass userptr vmas")
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.8+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221143840.167150-4-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 4e37e928928b730de9aa9a2f5dc853feeebc1742)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 28 +++++++++++++++++++++-------
 1 file changed, 21 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 690330352d4cd..47f7d8f2094b6 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -666,15 +666,16 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 
 	/* Collect invalidated userptrs */
 	spin_lock(&vm->userptr.invalidated_lock);
+	xe_assert(vm->xe, list_empty(&vm->userptr.repin_list));
 	list_for_each_entry_safe(uvma, next, &vm->userptr.invalidated,
 				 userptr.invalidate_link) {
 		list_del_init(&uvma->userptr.invalidate_link);
-		list_move_tail(&uvma->userptr.repin_link,
-			       &vm->userptr.repin_list);
+		list_add_tail(&uvma->userptr.repin_link,
+			      &vm->userptr.repin_list);
 	}
 	spin_unlock(&vm->userptr.invalidated_lock);
 
-	/* Pin and move to temporary list */
+	/* Pin and move to bind list */
 	list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
 				 userptr.repin_link) {
 		err = xe_vma_userptr_pin_pages(uvma);
@@ -690,10 +691,10 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 			err = xe_vm_invalidate_vma(&uvma->vma);
 			xe_vm_unlock(vm);
 			if (err)
-				return err;
+				break;
 		} else {
-			if (err < 0)
-				return err;
+			if (err)
+				break;
 
 			list_del_init(&uvma->userptr.repin_link);
 			list_move_tail(&uvma->vma.combined_links.rebind,
@@ -701,7 +702,19 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		}
 	}
 
-	return 0;
+	if (err) {
+		down_write(&vm->userptr.notifier_lock);
+		spin_lock(&vm->userptr.invalidated_lock);
+		list_for_each_entry_safe(uvma, next, &vm->userptr.repin_list,
+					 userptr.repin_link) {
+			list_del_init(&uvma->userptr.repin_link);
+			list_move_tail(&uvma->userptr.invalidate_link,
+				       &vm->userptr.invalidated);
+		}
+		spin_unlock(&vm->userptr.invalidated_lock);
+		up_write(&vm->userptr.notifier_lock);
+	}
+	return err;
 }
 
 /**
@@ -1066,6 +1079,7 @@ static void xe_vma_destroy(struct xe_vma *vma, struct dma_fence *fence)
 		xe_assert(vm->xe, vma->gpuva.flags & XE_VMA_DESTROYED);
 
 		spin_lock(&vm->userptr.invalidated_lock);
+		xe_assert(vm->xe, list_empty(&to_userptr_vma(vma)->userptr.repin_link));
 		list_del(&to_userptr_vma(vma)->userptr.invalidate_link);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	} else if (!xe_vma_is_null(vma)) {

From a9f4fa3a7efa65615ff7db13023ac84516e99e21 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Fri, 21 Feb 2025 14:38:42 +0000
Subject: [PATCH 1047/2753] drm/xe/userptr: fix EFAULT handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we treat EFAULT from hmm_range_fault() as a non-fatal error
when called from xe_vm_userptr_pin() with the idea that we want to avoid
killing the entire vm and chucking an error, under the assumption that
the user just did an unmap or something, and has no intention of
actually touching that memory from the GPU.  At this point we have
already zapped the PTEs so any access should generate a page fault, and
if the pin fails there also it will then become fatal.

However it looks like it's possible for the userptr vma to still be on
the rebind list in preempt_rebind_work_func(), if we had to retry the
pin again due to something happening in the caller before we did the
rebind step, but in the meantime needing to re-validate the userptr and
this time hitting the EFAULT.

This explains an internal user report of hitting:

[  191.738349] WARNING: CPU: 1 PID: 157 at drivers/gpu/drm/xe/xe_res_cursor.h:158 xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738551] Workqueue: xe-ordered-wq preempt_rebind_work_func [xe]
[  191.738616] RIP: 0010:xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738690] Call Trace:
[  191.738692]  <TASK>
[  191.738694]  ? show_regs+0x69/0x80
[  191.738698]  ? __warn+0x93/0x1a0
[  191.738703]  ? xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738759]  ? report_bug+0x18f/0x1a0
[  191.738764]  ? handle_bug+0x63/0xa0
[  191.738767]  ? exc_invalid_op+0x19/0x70
[  191.738770]  ? asm_exc_invalid_op+0x1b/0x20
[  191.738777]  ? xe_pt_stage_bind.constprop.0+0x60a/0x6b0 [xe]
[  191.738834]  ? ret_from_fork_asm+0x1a/0x30
[  191.738849]  bind_op_prepare+0x105/0x7b0 [xe]
[  191.738906]  ? dma_resv_reserve_fences+0x301/0x380
[  191.738912]  xe_pt_update_ops_prepare+0x28c/0x4b0 [xe]
[  191.738966]  ? kmemleak_alloc+0x4b/0x80
[  191.738973]  ops_execute+0x188/0x9d0 [xe]
[  191.739036]  xe_vm_rebind+0x4ce/0x5a0 [xe]
[  191.739098]  ? trace_hardirqs_on+0x4d/0x60
[  191.739112]  preempt_rebind_work_func+0x76f/0xd00 [xe]

Followed by NPD, when running some workload, since the sg was never
actually populated but the vma is still marked for rebind when it should
be skipped for this special EFAULT case. This is confirmed to fix the
user report.

v2 (MattB):
 - Move earlier.
v3 (MattB):
 - Update the commit message to make it clear that this indeed fixes the
   issue.

Fixes: 521db22a1d70 ("drm/xe: Invalidate userptr VMA on page pin fault")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221143840.167150-5-matthew.auld@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 6b93cb98910c826c2e2004942f8b060311e43618)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 47f7d8f2094b6..30259eba450b5 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -681,6 +681,18 @@ int xe_vm_userptr_pin(struct xe_vm *vm)
 		err = xe_vma_userptr_pin_pages(uvma);
 		if (err == -EFAULT) {
 			list_del_init(&uvma->userptr.repin_link);
+			/*
+			 * We might have already done the pin once already, but
+			 * then had to retry before the re-bind happened, due
+			 * some other condition in the caller, but in the
+			 * meantime the userptr got dinged by the notifier such
+			 * that we need to revalidate here, but this time we hit
+			 * the EFAULT. In such a case make sure we remove
+			 * ourselves from the rebind list to avoid going down in
+			 * flames.
+			 */
+			if (!list_empty(&uvma->vma.combined_links.rebind))
+				list_del_init(&uvma->vma.combined_links.rebind);
 
 			/* Wait for pending binds */
 			xe_vm_lock(vm, false);

From 98f9928843331fc4e91b25d9969a9458c3f9c552 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 21 Feb 2025 11:38:20 +0000
Subject: [PATCH 1048/2753] net: stmmac: qcom-ethqos: use rgmii_clock() to set
 the link clock

The link clock operates at twice the RGMII clock rate. Therefore, we
can use the rgmii_clock() helper to set this clock rate.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Vinod Koul <vkoul@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tlRMK-004Vsx-Ss@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-qcom-ethqos.c        | 23 ++++---------------
 1 file changed, 5 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index 192f270197c8d..eafe637540b60 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -169,30 +169,17 @@ static void rgmii_dump(void *priv)
 		rgmii_readl(ethqos, EMAC_SYSTEM_LOW_POWER_DEBUG));
 }
 
-/* Clock rates */
-#define RGMII_1000_NOM_CLK_FREQ			(250 * 1000 * 1000UL)
-#define RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ	 (50 * 1000 * 1000UL)
-#define RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ	  (5 * 1000 * 1000UL)
-
 static void
 ethqos_update_link_clk(struct qcom_ethqos *ethqos, int speed)
 {
+	long rate;
+
 	if (!phy_interface_mode_is_rgmii(ethqos->phy_mode))
 		return;
 
-	switch (speed) {
-	case SPEED_1000:
-		ethqos->link_clk_rate =  RGMII_1000_NOM_CLK_FREQ;
-		break;
-
-	case SPEED_100:
-		ethqos->link_clk_rate =  RGMII_ID_MODE_100_LOW_SVS_CLK_FREQ;
-		break;
-
-	case SPEED_10:
-		ethqos->link_clk_rate =  RGMII_ID_MODE_10_LOW_SVS_CLK_FREQ;
-		break;
-	}
+	rate = rgmii_clock(speed);
+	if (rate > 0)
+		ethqos->link_clk_rate = rate * 2;
 
 	clk_set_rate(ethqos->link_clk, ethqos->link_clk_rate);
 }

From db10fde5c4f96231e1d2bbfd01feb5f2f59b96d1 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 18:51:40 -0800
Subject: [PATCH 1049/2753] net: ethtool: fix ioctl confusing drivers about
 desired HDS user config

The legacy ioctl path does not have support for extended attributes.
So we issue a GET to fetch the current settings from the driver,
in an attempt to keep them unchanged. HDS is a bit "special" as
the GET only returns on/off while the SET takes a "ternary" argument
(on/off/default). If the driver was in the "default" setting -
executing the ioctl path binds it to on or off, even tho the user
did not intend to change HDS config.

Factor the relevant logic out of the netlink code and reuse it.

Fixes: 87c8f8496a05 ("bnxt_en: add support for tcp-data-split ethtool command")
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Tested-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250221025141.1132944-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/common.c | 16 ++++++++++++++++
 net/ethtool/common.h |  6 ++++++
 net/ethtool/ioctl.c  |  4 ++--
 net/ethtool/rings.c  |  9 ++++-----
 4 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index d88e9080643b8..b97374b508f67 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -6,6 +6,7 @@
 #include <linux/rtnetlink.h>
 #include <linux/ptp_clock_kernel.h>
 #include <linux/phy_link_topology.h>
+#include <net/netdev_queues.h>
 
 #include "netlink.h"
 #include "common.h"
@@ -771,6 +772,21 @@ int ethtool_check_ops(const struct ethtool_ops *ops)
 	return 0;
 }
 
+void ethtool_ringparam_get_cfg(struct net_device *dev,
+			       struct ethtool_ringparam *param,
+			       struct kernel_ethtool_ringparam *kparam,
+			       struct netlink_ext_ack *extack)
+{
+	memset(param, 0, sizeof(*param));
+	memset(kparam, 0, sizeof(*kparam));
+
+	param->cmd = ETHTOOL_GRINGPARAM;
+	dev->ethtool_ops->get_ringparam(dev, param, kparam, extack);
+
+	/* Driver gives us current state, we want to return current config */
+	kparam->tcp_data_split = dev->cfg->hds_config;
+}
+
 static void ethtool_init_tsinfo(struct kernel_ethtool_ts_info *info)
 {
 	memset(info, 0, sizeof(*info));
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index 58e9e7db06f90..a1088c2441d0a 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -51,6 +51,12 @@ int ethtool_check_max_channel(struct net_device *dev,
 			      struct ethtool_channels channels,
 			      struct genl_info *info);
 int ethtool_check_rss_ctx_busy(struct net_device *dev, u32 rss_context);
+
+void ethtool_ringparam_get_cfg(struct net_device *dev,
+			       struct ethtool_ringparam *param,
+			       struct kernel_ethtool_ringparam *kparam,
+			       struct netlink_ext_ack *extack);
+
 int __ethtool_get_ts_info(struct net_device *dev, struct kernel_ethtool_ts_info *info);
 int ethtool_get_ts_info_by_phc(struct net_device *dev,
 			       struct kernel_ethtool_ts_info *info,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 7609ce2b2c5e2..1c3ba2247776b 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2059,8 +2059,8 @@ static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr)
 
 static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
 {
-	struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM };
 	struct kernel_ethtool_ringparam kernel_ringparam;
+	struct ethtool_ringparam ringparam, max;
 	int ret;
 
 	if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam)
@@ -2069,7 +2069,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
 	if (copy_from_user(&ringparam, useraddr, sizeof(ringparam)))
 		return -EFAULT;
 
-	dev->ethtool_ops->get_ringparam(dev, &max, &kernel_ringparam, NULL);
+	ethtool_ringparam_get_cfg(dev, &max, &kernel_ringparam, NULL);
 
 	/* ensure new ring parameters are within the maximums */
 	if (ringparam.rx_pending > max.rx_max_pending ||
diff --git a/net/ethtool/rings.c b/net/ethtool/rings.c
index 7839bfd1ac6a0..aeedd5ec6b8cd 100644
--- a/net/ethtool/rings.c
+++ b/net/ethtool/rings.c
@@ -215,17 +215,16 @@ ethnl_set_rings_validate(struct ethnl_req_info *req_info,
 static int
 ethnl_set_rings(struct ethnl_req_info *req_info, struct genl_info *info)
 {
-	struct kernel_ethtool_ringparam kernel_ringparam = {};
-	struct ethtool_ringparam ringparam = {};
+	struct kernel_ethtool_ringparam kernel_ringparam;
 	struct net_device *dev = req_info->dev;
+	struct ethtool_ringparam ringparam;
 	struct nlattr **tb = info->attrs;
 	const struct nlattr *err_attr;
 	bool mod = false;
 	int ret;
 
-	dev->ethtool_ops->get_ringparam(dev, &ringparam,
-					&kernel_ringparam, info->extack);
-	kernel_ringparam.tcp_data_split = dev->cfg->hds_config;
+	ethtool_ringparam_get_cfg(dev, &ringparam, &kernel_ringparam,
+				  info->extack);
 
 	ethnl_update_u32(&ringparam.rx_pending, tb[ETHTOOL_A_RINGS_RX], &mod);
 	ethnl_update_u32(&ringparam.rx_mini_pending,

From 29b036be1b0bfcfc958380d5931325997fddf08a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 20 Feb 2025 18:51:41 -0800
Subject: [PATCH 1050/2753] selftests: drv-net: test XDP, HDS auto and the
 ioctl path

Test XDP and HDS interaction. While at it add a test for using the IOCTL,
as that turned out to be the real culprit.

Testing bnxt:

  # NETIF=eth0 ./ksft-net-drv/drivers/net/hds.py
  KTAP version 1
  1..12
  ok 1 hds.get_hds
  ok 2 hds.get_hds_thresh
  ok 3 hds.set_hds_disable # SKIP disabling of HDS not supported by the device
  ok 4 hds.set_hds_enable
  ok 5 hds.set_hds_thresh_zero
  ok 6 hds.set_hds_thresh_max
  ok 7 hds.set_hds_thresh_gt
  ok 8 hds.set_xdp
  ok 9 hds.enabled_set_xdp
  ok 10 hds.ioctl
  ok 11 hds.ioctl_set_xdp
  ok 12 hds.ioctl_enabled_set_xdp
  # Totals: pass:11 fail:0 xfail:0 xpass:0 skip:1 error:0

and netdevsim:

  # ./ksft-net-drv/drivers/net/hds.py
  KTAP version 1
  1..12
  ok 1 hds.get_hds
  ok 2 hds.get_hds_thresh
  ok 3 hds.set_hds_disable
  ok 4 hds.set_hds_enable
  ok 5 hds.set_hds_thresh_zero
  ok 6 hds.set_hds_thresh_max
  ok 7 hds.set_hds_thresh_gt
  ok 8 hds.set_xdp
  ok 9 hds.enabled_set_xdp
  ok 10 hds.ioctl
  ok 11 hds.ioctl_set_xdp
  ok 12 hds.ioctl_enabled_set_xdp
  # Totals: pass:12 fail:0 xfail:0 xpass:0 skip:0 error:0

Netdevsim needs a sane default for tx/rx ring size.

ethtool 6.11 is needed for the --disable-netlink option.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Tested-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250221025141.1132944-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/ethtool.c               |   2 +
 tools/testing/selftests/drivers/net/hds.py    | 145 +++++++++++++++++-
 tools/testing/selftests/net/lib/Makefile      |   3 +
 .../testing/selftests/net/lib/xdp_dummy.bpf.c |  13 ++
 4 files changed, 160 insertions(+), 3 deletions(-)
 create mode 100644 tools/testing/selftests/net/lib/xdp_dummy.bpf.c

diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 5c80fbee79138..7ab358616e035 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -184,9 +184,11 @@ static const struct ethtool_ops nsim_ethtool_ops = {
 
 static void nsim_ethtool_ring_init(struct netdevsim *ns)
 {
+	ns->ethtool.ring.rx_pending = 512;
 	ns->ethtool.ring.rx_max_pending = 4096;
 	ns->ethtool.ring.rx_jumbo_max_pending = 4096;
 	ns->ethtool.ring.rx_mini_max_pending = 4096;
+	ns->ethtool.ring.tx_pending = 512;
 	ns->ethtool.ring.tx_max_pending = 4096;
 }
 
diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 394971b25c0b1..873f5219e41d7 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -2,17 +2,54 @@
 # SPDX-License-Identifier: GPL-2.0
 
 import errno
+import os
 from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_raises, KsftSkipEx
-from lib.py import EthtoolFamily, NlError
+from lib.py import CmdExitFailure, EthtoolFamily, NlError
 from lib.py import NetDrvEnv
+from lib.py import defer, ethtool, ip
 
-def get_hds(cfg, netnl) -> None:
+
+def _get_hds_mode(cfg, netnl) -> str:
     try:
         rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
     except NlError as e:
         raise KsftSkipEx('ring-get not supported by device')
     if 'tcp-data-split' not in rings:
         raise KsftSkipEx('tcp-data-split not supported by device')
+    return rings['tcp-data-split']
+
+
+def _xdp_onoff(cfg):
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    ip("link set dev %s xdp obj %s sec xdp" %
+       (cfg.ifname, prog))
+    ip("link set dev %s xdp off" % cfg.ifname)
+
+
+def _ioctl_ringparam_modify(cfg, netnl) -> None:
+    """
+    Helper for performing a hopefully unimportant IOCTL SET.
+    IOCTL does not support HDS, so it should not affect the HDS config.
+    """
+    try:
+        rings = netnl.rings_get({'header': {'dev-index': cfg.ifindex}})
+    except NlError as e:
+        raise KsftSkipEx('ring-get not supported by device')
+
+    if 'tx' not in rings:
+        raise KsftSkipEx('setting Tx ring size not supported')
+
+    try:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] // 2}")
+    except CmdExitFailure as e:
+        ethtool(f"--disable-netlink -G {cfg.ifname} tx {rings['tx'] * 2}")
+    defer(ethtool, f"-G {cfg.ifname} tx {rings['tx']}")
+
+
+def get_hds(cfg, netnl) -> None:
+    _get_hds_mode(cfg, netnl)
+
 
 def get_hds_thresh(cfg, netnl) -> None:
     try:
@@ -104,6 +141,103 @@ def set_hds_thresh_gt(cfg, netnl) -> None:
         netnl.rings_set({'header': {'dev-index': cfg.ifindex}, 'hds-thresh': hds_gt})
     ksft_eq(e.exception.nl_msg.error, -errno.EINVAL)
 
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "auto" / UNKNOWN mode, XDP installation should work.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _xdp_onoff(cfg)
+
+
+def enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
+def ioctl(cfg, netnl) -> None:
+    mode1 = _get_hds_mode(cfg, netnl)
+    _ioctl_ringparam_modify(cfg, netnl)
+    mode2 = _get_hds_mode(cfg, netnl)
+
+    ksft_eq(mode1, mode2)
+
+
+def ioctl_set_xdp(cfg, netnl) -> None:
+    """
+    Like set_xdp(), but we perturb the settings via the legacy ioctl.
+    """
+    mode = _get_hds_mode(cfg, netnl)
+    if mode == 'enabled':
+        netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                         'tcp-data-split': 'unknown'})
+
+    _ioctl_ringparam_modify(cfg, netnl)
+
+    _xdp_onoff(cfg)
+
+
+def ioctl_enabled_set_xdp(cfg, netnl) -> None:
+    """
+    Enable single-buffer XDP on the device.
+    When HDS is in "enabled" mode, XDP installation should not work.
+    """
+    _get_hds_mode(cfg, netnl)  # Trigger skip if not supported
+
+    netnl.rings_set({'header': {'dev-index': cfg.ifindex},
+                     'tcp-data-split': 'enabled'})
+    defer(netnl.rings_set, {'header': {'dev-index': cfg.ifindex},
+                            'tcp-data-split': 'unknown'})
+
+    with ksft_raises(CmdExitFailure) as e:
+        _xdp_onoff(cfg)
+
+
 def main() -> None:
     with NetDrvEnv(__file__, queue_count=3) as cfg:
         ksft_run([get_hds,
@@ -112,7 +246,12 @@ def main() -> None:
                   set_hds_enable,
                   set_hds_thresh_zero,
                   set_hds_thresh_max,
-                  set_hds_thresh_gt],
+                  set_hds_thresh_gt,
+                  set_xdp,
+                  enabled_set_xdp,
+                  ioctl,
+                  ioctl_set_xdp,
+                  ioctl_enabled_set_xdp],
                  args=(cfg, EthtoolFamily()))
     ksft_exit()
 
diff --git a/tools/testing/selftests/net/lib/Makefile b/tools/testing/selftests/net/lib/Makefile
index bc6b6762baf3e..c22623b9a2a5f 100644
--- a/tools/testing/selftests/net/lib/Makefile
+++ b/tools/testing/selftests/net/lib/Makefile
@@ -9,7 +9,10 @@ TEST_FILES := ../../../../../Documentation/netlink/specs
 TEST_FILES += ../../../../net/ynl
 
 TEST_GEN_FILES += csum
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
 TEST_INCLUDES := $(wildcard py/*.py sh/*.sh)
 
 include ../../lib.mk
+
+include ../bpf.mk
diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
new file mode 100644
index 0000000000000..d988b2e0cee84
--- /dev/null
+++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

From 75bc3dab4e49b4daccb27ad6ce8ce2fcd253fc1b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 21 Feb 2025 05:12:23 +0000
Subject: [PATCH 1051/2753] net-sysfs: restore behavior for not running devices

modprobe dummy dumdummies=1

Old behavior :

$ cat /sys/class/net/dummy0/carrier
cat: /sys/class/net/dummy0/carrier: Invalid argument

After blamed commit, an empty string is reported.

$ cat /sys/class/net/dummy0/carrier
$

In this commit, I restore the old behavior for carrier,
speed and duplex attributes.

Fixes: 79c61899b5ee ("net-sysfs: remove rtnl_trylock from device attributes")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: Marco Leogrande <leogrande@google.com>
Reviewed-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250221051223.576726-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/net-sysfs.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 3fe2c521e5740..f61c1d8298119 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -313,12 +313,13 @@ static ssize_t carrier_show(struct device *dev,
 			    struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
-	int ret = -EINVAL;
+	int ret;
 
 	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
 	if (ret)
 		return ret;
 
+	ret = -EINVAL;
 	if (netif_running(netdev)) {
 		/* Synchronize carrier state with link watch,
 		 * see also rtnl_getlink().
@@ -349,6 +350,7 @@ static ssize_t speed_show(struct device *dev,
 	if (ret)
 		return ret;
 
+	ret = -EINVAL;
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
 
@@ -376,6 +378,7 @@ static ssize_t duplex_show(struct device *dev,
 	if (ret)
 		return ret;
 
+	ret = -EINVAL;
 	if (netif_running(netdev)) {
 		struct ethtool_link_ksettings cmd;
 

From 352bc4513ec3907db71cb5674fb93a76fc341ca9 Mon Sep 17 00:00:00 2001
From: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Date: Fri, 21 Feb 2025 14:18:18 +0900
Subject: [PATCH 1052/2753] net: stmmac: Correct usage of maximum queue number
 macros

The maximum numbers of each Rx and Tx queues are defined by
MTL_MAX_RX_QUEUES and MTL_MAX_TX_QUEUES respectively.

There are some places where Rx and Tx are used in reverse. There is no
issue when the Tx and Rx macros have the same value, but should correct
usage of macros for maximum queue number to keep consistency and prevent
unexpected mistakes.

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Huacai Chen <chenhuacai@kernel.org>
Signed-off-by: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Link: https://patch.msgid.link/20250221051818.4163678-1-hayashi.kunihiko@socionext.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/common.h | 4 ++--
 drivers/net/ethernet/stmicro/stmmac/stmmac.h | 7 +++----
 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h
index 55053528e4984..412b07e779456 100644
--- a/drivers/net/ethernet/stmicro/stmmac/common.h
+++ b/drivers/net/ethernet/stmicro/stmmac/common.h
@@ -101,8 +101,8 @@ struct stmmac_rxq_stats {
 /* Updates on each CPU protected by not allowing nested irqs. */
 struct stmmac_pcpu_stats {
 	struct u64_stats_sync syncp;
-	u64_stats_t rx_normal_irq_n[MTL_MAX_TX_QUEUES];
-	u64_stats_t tx_normal_irq_n[MTL_MAX_RX_QUEUES];
+	u64_stats_t rx_normal_irq_n[MTL_MAX_RX_QUEUES];
+	u64_stats_t tx_normal_irq_n[MTL_MAX_TX_QUEUES];
 };
 
 /* Extra statistic and debug information exposed by ethtool */
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index b403029b1aaa8..b321872846079 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -259,7 +259,7 @@ struct stmmac_priv {
 	/* Frequently used values are kept adjacent for cache effect */
 	u32 tx_coal_frames[MTL_MAX_TX_QUEUES];
 	u32 tx_coal_timer[MTL_MAX_TX_QUEUES];
-	u32 rx_coal_frames[MTL_MAX_TX_QUEUES];
+	u32 rx_coal_frames[MTL_MAX_RX_QUEUES];
 
 	int hwts_tx_en;
 	bool tx_path_in_lpi_mode;
@@ -267,8 +267,7 @@ struct stmmac_priv {
 	int sph;
 	int sph_cap;
 	u32 sarc_type;
-
-	u32 rx_riwt[MTL_MAX_TX_QUEUES];
+	u32 rx_riwt[MTL_MAX_RX_QUEUES];
 	int hwts_rx_en;
 
 	void __iomem *ioaddr;
@@ -344,7 +343,7 @@ struct stmmac_priv {
 	char int_name_sfty[IFNAMSIZ + 10];
 	char int_name_sfty_ce[IFNAMSIZ + 10];
 	char int_name_sfty_ue[IFNAMSIZ + 10];
-	char int_name_rx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 14];
+	char int_name_rx_irq[MTL_MAX_RX_QUEUES][IFNAMSIZ + 14];
 	char int_name_tx_irq[MTL_MAX_TX_QUEUES][IFNAMSIZ + 18];
 
 #ifdef CONFIG_DEBUG_FS

From 89ac4a59ca6d98091e8317bc5a342f38669e19e2 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 21 Feb 2025 12:07:28 +0100
Subject: [PATCH 1053/2753] skbuff: kill skb_flow_get_ports()

Since commit a815bde56b15 ("net, bonding: Refactor bond_xmit_hash for use
with xdp_buff"), this function is not used anymore.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250221110941.2041629-2-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 0b4f1889500d2..21644e9215e41 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1536,12 +1536,6 @@ u32 __skb_get_poff(const struct sk_buff *skb, const void *data,
 __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 			    const void *data, int hlen_proto);
 
-static inline __be32 skb_flow_get_ports(const struct sk_buff *skb,
-					int thoff, u8 ip_proto)
-{
-	return __skb_flow_get_ports(skb, thoff, ip_proto, NULL, 0);
-}
-
 void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     const struct flow_dissector_key *key,
 			     unsigned int key_count);

From c52fd4f083cc634c57fc98fce36860e63f6bce2b Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 21 Feb 2025 12:07:29 +0100
Subject: [PATCH 1054/2753] net: remove '__' from __skb_flow_get_ports()

Only one version of skb_flow_get_ports() exists after the previous commit,
so let's remove the useless '__'.

Suggested-by: Simon Horman <horms@kernel.org>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Link: https://patch.msgid.link/20250221110941.2041629-3-nicolas.dichtel@6wind.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c |  2 +-
 include/linux/skbuff.h          |  4 ++--
 net/core/flow_dissector.c       | 10 +++++-----
 3 files changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index f6d0628a36d9f..7d716e90a84c3 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -4214,7 +4214,7 @@ static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, const void *
 	}
 
 	if (l34 && *ip_proto >= 0)
-		fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
+		fk->ports.ports = skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
 
 	return true;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 21644e9215e41..f2bb8473d99a5 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1533,8 +1533,8 @@ void __skb_get_hash_net(const struct net *net, struct sk_buff *skb);
 u32 skb_get_poff(const struct sk_buff *skb);
 u32 __skb_get_poff(const struct sk_buff *skb, const void *data,
 		   const struct flow_keys_basic *keys, int hlen);
-__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
-			    const void *data, int hlen_proto);
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			  const void *data, int hlen_proto);
 
 void skb_flow_dissector_init(struct flow_dissector *flow_dissector,
 			     const struct flow_dissector_key *key,
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 9cd8de6bebb54..1b61bb25ba0e5 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -106,7 +106,7 @@ int flow_dissector_bpf_prog_attach_check(struct net *net,
 #endif /* CONFIG_BPF_SYSCALL */
 
 /**
- * __skb_flow_get_ports - extract the upper layer ports and return them
+ * skb_flow_get_ports - extract the upper layer ports and return them
  * @skb: sk_buff to extract the ports from
  * @thoff: transport header offset
  * @ip_proto: protocol for which to get port offset
@@ -116,8 +116,8 @@ int flow_dissector_bpf_prog_attach_check(struct net *net,
  * The function will try to retrieve the ports at offset thoff + poff where poff
  * is the protocol port offset returned from proto_ports_offset
  */
-__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
-			    const void *data, int hlen)
+__be32 skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			  const void *data, int hlen)
 {
 	int poff = proto_ports_offset(ip_proto);
 
@@ -137,7 +137,7 @@ __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
 
 	return 0;
 }
-EXPORT_SYMBOL(__skb_flow_get_ports);
+EXPORT_SYMBOL(skb_flow_get_ports);
 
 static bool icmp_has_id(u8 type)
 {
@@ -870,7 +870,7 @@ __skb_flow_dissect_ports(const struct sk_buff *skb,
 	if (!key_ports && !key_ports_range)
 		return;
 
-	ports = __skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen);
+	ports = skb_flow_get_ports(skb, nhoff, ip_proto, data, hlen);
 
 	if (key_ports)
 		key_ports->ports = ports;

From 8c1624b63a7d24142a2bbc3a5ee7e95f004ea36e Mon Sep 17 00:00:00 2001
From: Sagi Grimberg <sagi@grimberg.me>
Date: Thu, 20 Feb 2025 13:18:30 +0200
Subject: [PATCH 1055/2753] nvme-tcp: fix possible UAF in nvme_tcp_poll

nvme_tcp_poll() may race with the send path error handler because
it may complete the request while it is actively being polled for
completion, resulting in a UAF panic [1]:

We should make sure to stop polling when we see an error when
trying to read from the socket. Hence make sure to propagate the
error so that the block layer breaks the polling cycle.

[1]:
--
[35665.692310] nvme nvme2: failed to send request -13
[35665.702265] nvme nvme2: unsupported pdu type (3)
[35665.702272] BUG: kernel NULL pointer dereference, address: 0000000000000000
[35665.702542] nvme nvme2: queue 1 receive failed:  -22
[35665.703209] #PF: supervisor write access in kernel mode
[35665.703213] #PF: error_code(0x0002) - not-present page
[35665.703214] PGD 8000003801cce067 P4D 8000003801cce067 PUD 37e6f79067 PMD 0
[35665.703220] Oops: 0002 [#1] SMP PTI
[35665.703658] nvme nvme2: starting error recovery
[35665.705809] Hardware name: Inspur aaabbb/YZMB-00882-104, BIOS 4.1.26 09/22/2022
[35665.705812] Workqueue: kblockd blk_mq_requeue_work
[35665.709172] RIP: 0010:_raw_spin_lock+0xc/0x30
[35665.715788] Call Trace:
[35665.716201]  <TASK>
[35665.716613]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717049]  ? show_trace_log_lvl+0x1c1/0x2d9
[35665.717457]  ? blk_mq_request_bypass_insert+0x2c/0xb0
[35665.717950]  ? __die_body.cold+0x8/0xd
[35665.718361]  ? page_fault_oops+0xac/0x140
[35665.718749]  ? blk_mq_start_request+0x30/0xf0
[35665.719144]  ? nvme_tcp_queue_rq+0xc7/0x170 [nvme_tcp]
[35665.719547]  ? exc_page_fault+0x62/0x130
[35665.719938]  ? asm_exc_page_fault+0x22/0x30
[35665.720333]  ? _raw_spin_lock+0xc/0x30
[35665.720723]  blk_mq_request_bypass_insert+0x2c/0xb0
[35665.721101]  blk_mq_requeue_work+0xa5/0x180
[35665.721451]  process_one_work+0x1e8/0x390
[35665.721809]  worker_thread+0x53/0x3d0
[35665.722159]  ? process_one_work+0x390/0x390
[35665.722501]  kthread+0x124/0x150
[35665.722849]  ? set_kthread_struct+0x50/0x50
[35665.723182]  ret_from_fork+0x1f/0x30

Reported-by: Zhang Guanghui <zhang.guanghui@cestc.cn>
Signed-off-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8a9131c95a3da..8c14018201dbd 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -2699,6 +2699,7 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 {
 	struct nvme_tcp_queue *queue = hctx->driver_data;
 	struct sock *sk = queue->sock->sk;
+	int ret;
 
 	if (!test_bit(NVME_TCP_Q_LIVE, &queue->flags))
 		return 0;
@@ -2706,9 +2707,9 @@ static int nvme_tcp_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 	set_bit(NVME_TCP_Q_POLLING, &queue->flags);
 	if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue))
 		sk_busy_loop(sk, true);
-	nvme_tcp_try_recv(queue);
+	ret = nvme_tcp_try_recv(queue);
 	clear_bit(NVME_TCP_Q_POLLING, &queue->flags);
-	return queue->nr_cqe;
+	return ret < 0 ? ret : queue->nr_cqe;
 }
 
 static int nvme_tcp_get_address(struct nvme_ctrl *ctrl, char *buf, int size)

From 171fd7cb153c4614d4132fbb135ef1c0855e330a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 21 Feb 2025 14:15:12 +0000
Subject: [PATCH 1056/2753] net: stmmac: thead: use rgmii_clock() for RGMII
 clock rate

Switch to using rgmii_clock() to get the RGMII TXC rate, and calculate
the divisor from the parent clock rate and the rate indicated by
rgmii_clock().

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Drew Fustini <drew@pdp7.com>
Link: https://patch.msgid.link/E1tlTo8-004W3a-CO@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-thead.c    | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index ddb1d8aba3215..f16fa341aadb3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -109,6 +109,7 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 	struct plat_stmmacenet_data *plat;
 	struct thead_dwmac *dwmac = priv;
 	unsigned long rate;
+	long tx_rate;
 	u32 div, reg;
 
 	plat = dwmac->plat;
@@ -131,21 +132,14 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 
 		writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV);
 
-		switch (speed) {
-		case SPEED_1000:
-			div = rate / GMAC_GMII_RGMII_RATE;
-			break;
-		case SPEED_100:
-			div = rate / GMAC_MII_RATE;
-			break;
-		case SPEED_10:
-			div = rate * 10 / GMAC_MII_RATE;
-			break;
-		default:
+		tx_rate = rgmii_clock(speed);
+		if (tx_rate < 0) {
 			dev_err(dwmac->dev, "invalid speed %d\n", speed);
 			return;
 		}
 
+		div = rate / tx_rate;
+
 		reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) |
 		      FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div);
 		writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV);

From 8bfff0481d917ef92bfad607839acb7edb5e0b0d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 21 Feb 2025 14:15:17 +0000
Subject: [PATCH 1057/2753] net: stmmac: thead: ensure divisor gives proper
 rate

thead was checking that the stmmac_clk rate was a multiple of the
RGMII rates for 1G and 100M, but didn't check for 10M. Rather than
use this with hard-coded speeds, check that the calculated divisor
gives the required rate by multplying the transmit clock rate back
up to the stmmac clock rate and checking that it agrees.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Drew Fustini <drew@pdp7.com>
Link: https://patch.msgid.link/E1tlToD-004W3g-HB@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index f16fa341aadb3..f9f2bd65959fa 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -45,9 +45,6 @@
 #define  TXCLK_DIR_OUTPUT		FIELD_PREP(TXCLK_DIR_MASK, 0)
 #define  TXCLK_DIR_INPUT		FIELD_PREP(TXCLK_DIR_MASK, 1)
 
-#define GMAC_GMII_RGMII_RATE	125000000
-#define GMAC_MII_RATE		25000000
-
 struct thead_dwmac {
 	struct plat_stmmacenet_data *plat;
 	void __iomem *apb_base;
@@ -124,11 +121,6 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 	case PHY_INTERFACE_MODE_RGMII_RXID:
 	case PHY_INTERFACE_MODE_RGMII_TXID:
 		rate = clk_get_rate(plat->stmmac_clk);
-		if (!rate || rate % GMAC_GMII_RGMII_RATE != 0 ||
-		    rate % GMAC_MII_RATE != 0) {
-			dev_err(dwmac->dev, "invalid gmac rate %ld\n", rate);
-			return;
-		}
 
 		writel(0, dwmac->apb_base + GMAC_PLLCLK_DIV);
 
@@ -139,6 +131,10 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 		}
 
 		div = rate / tx_rate;
+		if (rate != tx_rate * div) {
+			dev_err(dwmac->dev, "invalid gmac rate %lu\n", rate);
+			return;
+		}
 
 		reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) |
 		      FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div);

From 7183877d6853801258b7a8d3b51b415982e5097e Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 21 Feb 2025 09:51:27 -0800
Subject: [PATCH 1058/2753] net: Remove shadow variable in netdev_run_todo()

Fix a shadow variable warning in net/core/dev.c when compiled with
CONFIG_LOCKDEP enabled. The warning occurs because 'dev' is redeclared
inside the while loop, shadowing the outer scope declaration.

	net/core/dev.c:11211:22: warning: declaration shadows a local variable [-Wshadow]
		struct net_device *dev = list_first_entry(&unlink_list,

	net/core/dev.c:11202:21: note: previous declaration is here
		struct net_device *dev, *tmp;

Remove the redundant declaration since the variable is already defined
in the outer scope and will be overwritten in the subsequent
list_for_each_entry_safe() loop anyway.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250221-netcons_fix_shadow-v1-1-dee20c8658dd@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 8c7ee7ada6a3e..3f525278a8718 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11209,9 +11209,8 @@ void netdev_run_todo(void)
 	list_replace_init(&net_unlink_list, &unlink_list);
 
 	while (!list_empty(&unlink_list)) {
-		struct net_device *dev = list_first_entry(&unlink_list,
-							  struct net_device,
-							  unlink_list);
+		dev = list_first_entry(&unlink_list, struct net_device,
+				       unlink_list);
 		list_del_init(&dev->unlink_list);
 		dev->nested_level = dev->lower_level - 1;
 	}

From 6a3572e10f740acd48e2713ef37e92186a3ce5e8 Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <uwu@icenowy.me>
Date: Thu, 13 Feb 2025 01:04:43 +0800
Subject: [PATCH 1059/2753] nvme-pci: clean up CMBMSC when registering CMB
 fails

CMB decoding should get disabled when the CMB block isn't successfully
registered to P2P DMA subsystem.

Clean up the CMBMSC register in this error handling codepath to disable
CMB decoding (and CMBLOC/CMBSZ registers).

Signed-off-by: Icenowy Zheng <uwu@icenowy.me>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 950289405ef28..218506e3dabea 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2003,6 +2003,7 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");
+		hi_lo_writeq(0, dev->bar + NVME_REG_CMBMSC);
 		return;
 	}
 

From 56cf7ef0d490b28fad8f8629fc135c5ab7c9f54e Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <uwu@icenowy.me>
Date: Thu, 13 Feb 2025 01:04:44 +0800
Subject: [PATCH 1060/2753] nvme-pci: skip CMB blocks incompatible with PCI P2P
 DMA

The PCI P2PDMA code will register the CMB block to the memory
hot-plugging subsystem, which have an alignment requirement. Memory
blocks that do not satisfy this alignment requirement (usually 2MB) will
lead to a WARNING from memory hotplugging.

Verify the CMB block's address and size against the alignment and only
try to send CMB blocks compatible with it to prevent this warning.

Tested on Intel DC D4502 SSD, which has a 512K CMB block that is too
small for memory hotplugging (thus PCI P2PDMA).

Signed-off-by: Icenowy Zheng <uwu@icenowy.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 20 ++++++++++++--------
 1 file changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 218506e3dabea..640590b217282 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1982,6 +1982,18 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 	if (offset > bar_size)
 		return;
 
+	/*
+	 * Controllers may support a CMB size larger than their BAR, for
+	 * example, due to being behind a bridge. Reduce the CMB to the
+	 * reported size of the BAR
+	 */
+	size = min(size, bar_size - offset);
+
+	if (!IS_ALIGNED(size, memremap_compat_align()) ||
+	    !IS_ALIGNED(pci_resource_start(pdev, bar),
+			memremap_compat_align()))
+		return;
+
 	/*
 	 * Tell the controller about the host side address mapping the CMB,
 	 * and enable CMB decoding for the NVMe 1.4+ scheme:
@@ -1992,14 +2004,6 @@ static void nvme_map_cmb(struct nvme_dev *dev)
 			     dev->bar + NVME_REG_CMBMSC);
 	}
 
-	/*
-	 * Controllers may support a CMB size larger than their BAR,
-	 * for example, due to being behind a bridge. Reduce the CMB to
-	 * the reported size of the BAR
-	 */
-	if (size > bar_size - offset)
-		size = bar_size - offset;
-
 	if (pci_p2pdma_add_resource(pdev, bar, size, offset)) {
 		dev_warn(dev->ctrl.device,
 			 "failed to register the CMB\n");

From 6538c8ca8ee182a8b8233e0e57b5bffd8318d60c Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 24 Feb 2025 00:36:11 +0100
Subject: [PATCH 1061/2753] net: ethernet: renesas: rcar_gen4_ptp: Remove bool
 conversion
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Remove the unnecessary bool conversion and simplify the code.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Link: https://patch.msgid.link/20250223233613.100518-2-thorsten.blum@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/renesas/rcar_gen4_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
index 72e7fcc56693a..4c3e8cc5046f5 100644
--- a/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
+++ b/drivers/net/ethernet/renesas/rcar_gen4_ptp.c
@@ -29,8 +29,8 @@ static const struct rcar_gen4_ptp_reg_offset gen4_offs = {
 static int rcar_gen4_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
 {
 	struct rcar_gen4_ptp_private *ptp_priv = ptp_to_priv(ptp);
-	bool neg_adj = scaled_ppm < 0 ? true : false;
 	s64 addend = ptp_priv->default_addend;
+	bool neg_adj = scaled_ppm < 0;
 	s64 diff;
 
 	if (neg_adj)

From f5be37ca2c99fc764408ceeeaf941bea062cdc9b Mon Sep 17 00:00:00 2001
From: Andras Sebok <sebokandris2009@gmail.com>
Date: Mon, 24 Feb 2025 10:03:56 +0100
Subject: [PATCH 1062/2753] dt-bindings: input/touchscreen: imagis: add
 compatible for ist3038h

IST3038H is a touchscreen IC which seems mostly compatible with IST3038C
except that it reports a different chip ID value.

Signed-off-by: Andras Sebok <sebokandris2009@gmail.com>
Link: https://lore.kernel.org/r/20250224090354.102903-4-sebokandris2009@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml   | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml b/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml
index e24cbd9609933..bd8ede3a4ad89 100644
--- a/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml
+++ b/Documentation/devicetree/bindings/input/touchscreen/imagis,ist3038c.yaml
@@ -19,6 +19,7 @@ properties:
       - imagis,ist3038
       - imagis,ist3038b
       - imagis,ist3038c
+      - imagis,ist3038h
 
   reg:
     maxItems: 1

From 5797c04400ee117bfe459ff1e468d0ea38054ab4 Mon Sep 17 00:00:00 2001
From: Paul Fertser <fercerpav@gmail.com>
Date: Thu, 23 Jan 2025 15:20:02 +0300
Subject: [PATCH 1063/2753] hwmon: (peci/dimmtemp) Do not provide fake
 thresholds data

When an Icelake or Sapphire Rapids CPU isn't providing the maximum and
critical thresholds for particular DIMM the driver should return an
error to the userspace instead of giving it stale (best case) or wrong
(the structure contains all zeros after kzalloc() call) data.

The issue can be reproduced by binding the peci driver while the host is
fully booted and idle, this makes PECI interaction unreliable enough.

Fixes: 73bc1b885dae ("hwmon: peci: Add dimmtemp driver")
Fixes: 621995b6d795 ("hwmon: (peci/dimmtemp) Add Sapphire Rapids support")
Cc: stable@vger.kernel.org
Signed-off-by: Paul Fertser <fercerpav@gmail.com>
Reviewed-by: Iwona Winiarska <iwona.winiarska@intel.com>
Link: https://lore.kernel.org/r/20250123122003.6010-1-fercerpav@gmail.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/peci/dimmtemp.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/hwmon/peci/dimmtemp.c b/drivers/hwmon/peci/dimmtemp.c
index d6762259dd69c..fbe82d9852e01 100644
--- a/drivers/hwmon/peci/dimmtemp.c
+++ b/drivers/hwmon/peci/dimmtemp.c
@@ -127,8 +127,6 @@ static int update_thresholds(struct peci_dimmtemp *priv, int dimm_no)
 		return 0;
 
 	ret = priv->gen_info->read_thresholds(priv, dimm_order, chan_rank, &data);
-	if (ret == -ENODATA) /* Use default or previous value */
-		return 0;
 	if (ret)
 		return ret;
 
@@ -509,11 +507,11 @@ read_thresholds_icx(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 13, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 224e0: IMC 0 channel 0 -> rank 0
@@ -546,11 +544,11 @@ read_thresholds_spr(struct peci_dimmtemp *priv, int dimm_order, int chan_rank, u
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd4, &reg_val);
 	if (ret || !(reg_val & BIT(31)))
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	ret = peci_ep_pci_local_read(priv->peci_dev, 0, 30, 0, 2, 0xd0, &reg_val);
 	if (ret)
-		return -ENODATA; /* Use default or previous value */
+		return -ENODATA;
 
 	/*
 	 * Device 26, Offset 219a8: IMC 0 channel 0 -> rank 0

From 83a4a5a82a154277dfe61d135a445901cd6d0e6f Mon Sep 17 00:00:00 2001
From: Andras Sebok <sebokandris2009@gmail.com>
Date: Mon, 24 Feb 2025 10:03:54 +0100
Subject: [PATCH 1064/2753] Input: imagis - add support for imagis IST3038H

Add support for imagis IST3038H, which seems mostly compatible with
IST3038C except that it reports a different chip ID value.

Tested on samsung,j5y17lte.

Signed-off-by: Andras Sebok <sebokandris2009@gmail.com>
Link: https://lore.kernel.org/r/20250224090354.102903-2-sebokandris2009@gmail.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/imagis.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/input/touchscreen/imagis.c b/drivers/input/touchscreen/imagis.c
index abeae9102323c..3c8bbe284b731 100644
--- a/drivers/input/touchscreen/imagis.c
+++ b/drivers/input/touchscreen/imagis.c
@@ -22,6 +22,7 @@
 
 #define IST3032C_WHOAMI			0x32c
 #define IST3038C_WHOAMI			0x38c
+#define IST3038H_WHOAMI			0x38d
 
 #define IST3038B_REG_CHIPID		0x30
 #define IST3038B_WHOAMI			0x30380b
@@ -428,11 +429,19 @@ static const struct imagis_properties imagis_3038c_data = {
 	.protocol_b = true,
 };
 
+static const struct imagis_properties imagis_3038h_data = {
+	.interrupt_msg_cmd = IST3038C_REG_INTR_MESSAGE,
+	.touch_coord_cmd = IST3038C_REG_TOUCH_COORD,
+	.whoami_cmd = IST3038C_REG_CHIPID,
+	.whoami_val = IST3038H_WHOAMI,
+};
+
 static const struct of_device_id imagis_of_match[] = {
 	{ .compatible = "imagis,ist3032c", .data = &imagis_3032c_data },
 	{ .compatible = "imagis,ist3038", .data = &imagis_3038_data },
 	{ .compatible = "imagis,ist3038b", .data = &imagis_3038b_data },
 	{ .compatible = "imagis,ist3038c", .data = &imagis_3038c_data },
+	{ .compatible = "imagis,ist3038h", .data = &imagis_3038h_data },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, imagis_of_match);

From 2e5af6b2ae85328051f2ecb1b7fe64cdd835c8e9 Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Fri, 21 Feb 2025 14:57:17 +0800
Subject: [PATCH 1065/2753] net: txgbe: Add basic support for new AML devices

There is a new 40/25/10 Gigabit Ethernet device.

To support basic functions, PHYLINK is temporarily skipped as it is
intended to implement these configurations in the firmware. And the
associated link IRQ is also skipped.

And Implement the new SW-FW interaction interface, which use 64 Byte
message buffer.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Link: https://patch.msgid.link/20250221065718.197544-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/wangxun/libwx/wx_ethtool.c   |  44 +++-
 drivers/net/ethernet/wangxun/libwx/wx_hw.c    | 213 +++++++++++++++---
 drivers/net/ethernet/wangxun/libwx/wx_lib.c   |  25 +-
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  29 ++-
 drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c |   6 +
 .../net/ethernet/wangxun/txgbe/txgbe_irq.c    |   7 +
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   |  43 +++-
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    |   6 +
 .../net/ethernet/wangxun/txgbe/txgbe_type.h   |  14 ++
 9 files changed, 333 insertions(+), 54 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index 28f982fbc64c3..6d3b57233a39c 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -219,6 +219,9 @@ int wx_nway_reset(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_nway_reset(wx->phylink);
 }
 EXPORT_SYMBOL(wx_nway_reset);
@@ -228,6 +231,9 @@ int wx_get_link_ksettings(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_ksettings_get(wx->phylink, cmd);
 }
 EXPORT_SYMBOL(wx_get_link_ksettings);
@@ -237,6 +243,9 @@ int wx_set_link_ksettings(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_ksettings_set(wx->phylink, cmd);
 }
 EXPORT_SYMBOL(wx_set_link_ksettings);
@@ -246,6 +255,9 @@ void wx_get_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml)
+		return;
+
 	phylink_ethtool_get_pauseparam(wx->phylink, pause);
 }
 EXPORT_SYMBOL(wx_get_pauseparam);
@@ -255,6 +267,9 @@ int wx_set_pauseparam(struct net_device *netdev,
 {
 	struct wx *wx = netdev_priv(netdev);
 
+	if (wx->mac.type == wx_mac_aml)
+		return -EOPNOTSUPP;
+
 	return phylink_ethtool_set_pauseparam(wx->phylink, pause);
 }
 EXPORT_SYMBOL(wx_set_pauseparam);
@@ -325,10 +340,17 @@ int wx_set_coalesce(struct net_device *netdev,
 	if (ec->tx_max_coalesced_frames_irq)
 		wx->tx_work_limit = ec->tx_max_coalesced_frames_irq;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
 		max_eitr = WX_SP_MAX_EITR;
-	else
+		break;
+	case wx_mac_aml:
+		max_eitr = WX_AML_MAX_EITR;
+		break;
+	default:
 		max_eitr = WX_EM_MAX_EITR;
+		break;
+	}
 
 	if ((ec->rx_coalesce_usecs > (max_eitr >> 2)) ||
 	    (ec->tx_coalesce_usecs > (max_eitr >> 2)))
@@ -350,10 +372,15 @@ int wx_set_coalesce(struct net_device *netdev,
 		wx->tx_itr_setting = ec->tx_coalesce_usecs;
 
 	if (wx->tx_itr_setting == 1) {
-		if (wx->mac.type == wx_mac_sp)
+		switch (wx->mac.type) {
+		case wx_mac_sp:
+		case wx_mac_aml:
 			tx_itr_param = WX_12K_ITR;
-		else
+			break;
+		default:
 			tx_itr_param = WX_20K_ITR;
+			break;
+		}
 	} else {
 		tx_itr_param = wx->tx_itr_setting;
 	}
@@ -386,10 +413,15 @@ static unsigned int wx_max_channels(struct wx *wx)
 		max_combined = 1;
 	} else {
 		/* support up to max allowed queues with RSS */
-		if (wx->mac.type == wx_mac_sp)
+		switch (wx->mac.type) {
+		case wx_mac_sp:
+		case wx_mac_aml:
 			max_combined = 63;
-		else
+			break;
+		default:
 			max_combined = 8;
+			break;
+		}
 	}
 
 	return max_combined;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 907d13ade4048..b5f35b187077a 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -112,10 +112,15 @@ static void wx_intr_disable(struct wx *wx, u64 qmask)
 	if (mask)
 		wr32(wx, WX_PX_IMS(0), mask);
 
-	if (wx->mac.type == wx_mac_sp) {
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMS(1), mask);
+		break;
+	default:
+		break;
 	}
 }
 
@@ -126,10 +131,16 @@ void wx_intr_enable(struct wx *wx, u64 qmask)
 	mask = (qmask & U32_MAX);
 	if (mask)
 		wr32(wx, WX_PX_IMC(0), mask);
-	if (wx->mac.type == wx_mac_sp) {
+
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
 		mask = (qmask >> 32);
 		if (mask)
 			wr32(wx, WX_PX_IMC(1), mask);
+		break;
+	default:
+		break;
 	}
 }
 EXPORT_SYMBOL(wx_intr_enable);
@@ -278,22 +289,8 @@ static int wx_acquire_sw_sync(struct wx *wx, u32 mask)
 	return ret;
 }
 
-/**
- *  wx_host_interface_command - Issue command to manageability block
- *  @wx: pointer to the HW structure
- *  @buffer: contains the command to write and where the return status will
- *   be placed
- *  @length: length of buffer, must be multiple of 4 bytes
- *  @timeout: time in ms to wait for command completion
- *  @return_data: read and return data from the buffer (true) or not (false)
- *   Needed because FW structures are big endian and decoding of
- *   these fields can be 8 bit or 16 bit based on command. Decoding
- *   is not easily understood without making a table of commands.
- *   So we will leave this up to the caller to read back the data
- *   in these cases.
- **/
-int wx_host_interface_command(struct wx *wx, u32 *buffer,
-			      u32 length, u32 timeout, bool return_data)
+static int wx_host_interface_command_s(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
 {
 	u32 hdr_size = sizeof(struct wx_hic_hdr);
 	u32 hicr, i, bi, buf[64] = {};
@@ -301,22 +298,10 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	u32 dword_len;
 	u16 buf_len;
 
-	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
-		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
-		return -EINVAL;
-	}
-
 	status = wx_acquire_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	if (status != 0)
 		return status;
 
-	/* Calculate length in DWORDs. We must be DWORD aligned */
-	if ((length % (sizeof(u32))) != 0) {
-		wx_err(wx, "Buffer length failure, not aligned to dword");
-		status = -EINVAL;
-		goto rel_out;
-	}
-
 	dword_len = length >> 2;
 
 	/* The device driver writes the relevant command block
@@ -391,6 +376,139 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	wx_release_sw_sync(wx, WX_MNG_SWFW_SYNC_SW_MB);
 	return status;
 }
+
+static bool wx_poll_fw_reply(struct wx *wx, u32 *buffer, u8 send_cmd)
+{
+	u32 dword_len = sizeof(struct wx_hic_hdr) >> 2;
+	struct wx_hic_hdr *recv_hdr;
+	u32 i;
+
+	/* read hdr */
+	for (i = 0; i < dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+	/* check hdr */
+	recv_hdr = (struct wx_hic_hdr *)buffer;
+	if (recv_hdr->cmd == send_cmd &&
+	    recv_hdr->index == wx->swfw_index)
+		return true;
+
+	return false;
+}
+
+static int wx_host_interface_command_r(struct wx *wx, u32 *buffer,
+				       u32 length, u32 timeout, bool return_data)
+{
+	struct wx_hic_hdr *hdr = (struct wx_hic_hdr *)buffer;
+	u32 hdr_size = sizeof(struct wx_hic_hdr);
+	bool busy, reply;
+	u32 dword_len;
+	u16 buf_len;
+	int err = 0;
+	u8 send_cmd;
+	u32 i;
+
+	/* wait to get lock */
+	might_sleep();
+	err = read_poll_timeout(test_and_set_bit, busy, !busy, 1000, timeout * 1000,
+				false, WX_STATE_SWFW_BUSY, wx->state);
+	if (err)
+		return err;
+
+	/* index to unique seq id for each mbox message */
+	hdr->index = wx->swfw_index;
+	send_cmd = hdr->cmd;
+
+	dword_len = length >> 2;
+	/* write data to SW-FW mbox array */
+	for (i = 0; i < dword_len; i++) {
+		wr32a(wx, WX_SW2FW_MBOX, i, (__force u32)cpu_to_le32(buffer[i]));
+		/* write flush */
+		rd32a(wx, WX_SW2FW_MBOX, i);
+	}
+
+	/* generate interrupt to notify FW */
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, 0);
+	wr32m(wx, WX_SW2FW_MBOX_CMD, WX_SW2FW_MBOX_CMD_VLD, WX_SW2FW_MBOX_CMD_VLD);
+
+	/* polling reply from FW */
+	err = read_poll_timeout(wx_poll_fw_reply, reply, reply, 1000, 50000,
+				true, wx, buffer, send_cmd);
+	if (err) {
+		wx_err(wx, "Polling from FW messages timeout, cmd: 0x%x, index: %d\n",
+		       send_cmd, wx->swfw_index);
+		goto rel_out;
+	}
+
+	/* expect no reply from FW then return */
+	if (!return_data)
+		goto rel_out;
+
+	/* If there is any thing in data position pull it in */
+	buf_len = hdr->buf_len;
+	if (buf_len == 0)
+		goto rel_out;
+
+	if (length < buf_len + hdr_size) {
+		wx_err(wx, "Buffer not large enough for reply message.\n");
+		err = -EFAULT;
+		goto rel_out;
+	}
+
+	/* Calculate length in DWORDs, add 3 for odd lengths */
+	dword_len = (buf_len + 3) >> 2;
+	for (i = hdr_size >> 2; i <= dword_len; i++) {
+		buffer[i] = rd32a(wx, WX_FW2SW_MBOX, i);
+		le32_to_cpus(&buffer[i]);
+	}
+
+rel_out:
+	/* index++, index replace wx_hic_hdr.checksum */
+	if (wx->swfw_index == WX_HIC_HDR_INDEX_MAX)
+		wx->swfw_index = 0;
+	else
+		wx->swfw_index++;
+
+	clear_bit(WX_STATE_SWFW_BUSY, wx->state);
+	return err;
+}
+
+/**
+ *  wx_host_interface_command - Issue command to manageability block
+ *  @wx: pointer to the HW structure
+ *  @buffer: contains the command to write and where the return status will
+ *   be placed
+ *  @length: length of buffer, must be multiple of 4 bytes
+ *  @timeout: time in ms to wait for command completion
+ *  @return_data: read and return data from the buffer (true) or not (false)
+ *   Needed because FW structures are big endian and decoding of
+ *   these fields can be 8 bit or 16 bit based on command. Decoding
+ *   is not easily understood without making a table of commands.
+ *   So we will leave this up to the caller to read back the data
+ *   in these cases.
+ **/
+int wx_host_interface_command(struct wx *wx, u32 *buffer,
+			      u32 length, u32 timeout, bool return_data)
+{
+	if (length == 0 || length > WX_HI_MAX_BLOCK_BYTE_LENGTH) {
+		wx_err(wx, "Buffer length failure buffersize=%d.\n", length);
+		return -EINVAL;
+	}
+
+	/* Calculate length in DWORDs. We must be DWORD aligned */
+	if ((length % (sizeof(u32))) != 0) {
+		wx_err(wx, "Buffer length failure, not aligned to dword");
+		return -EINVAL;
+	}
+
+	if (test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		return wx_host_interface_command_r(wx, buffer, length,
+						   timeout, return_data);
+
+	return wx_host_interface_command_s(wx, buffer, length, timeout, return_data);
+}
 EXPORT_SYMBOL(wx_host_interface_command);
 
 int wx_set_pps(struct wx *wx, bool enable, u64 nsec, u64 cycles)
@@ -442,7 +560,10 @@ static int wx_read_ee_hostif_data(struct wx *wx, u16 offset, u16 *data)
 	if (status != 0)
 		return status;
 
-	*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+		*data = (u16)rd32a(wx, WX_MNG_MBOX, FW_NVM_DATA_OFFSET);
+	else
+		*data = (u16)rd32a(wx, WX_FW2SW_MBOX, FW_NVM_DATA_OFFSET);
 
 	return status;
 }
@@ -486,6 +607,7 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 	u16 words_to_read;
 	u32 value = 0;
 	int status;
+	u32 mbox;
 	u32 i;
 
 	/* Take semaphore for the entire operation. */
@@ -518,8 +640,12 @@ int wx_read_ee_hostif_buffer(struct wx *wx,
 			goto out;
 		}
 
+		if (!test_bit(WX_FLAG_SWFW_RING, wx->flags))
+			mbox = WX_MNG_MBOX;
+		else
+			mbox = WX_FW2SW_MBOX;
 		for (i = 0; i < words_to_read; i++) {
-			u32 reg = WX_MNG_MBOX + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
+			u32 reg = mbox + (FW_NVM_DATA_OFFSET << 2) + 2 * i;
 
 			value = rd32(wx, reg);
 			data[current_word] = (u16)(value & 0xffff);
@@ -569,12 +695,17 @@ void wx_init_eeprom_params(struct wx *wx)
 		}
 	}
 
-	if (wx->mac.type == wx_mac_sp) {
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
 		if (wx_read_ee_hostif(wx, WX_SW_REGION_PTR, &data)) {
 			wx_err(wx, "NVM Read Error\n");
 			return;
 		}
 		data = data >> 1;
+		break;
+	default:
+		break;
 	}
 
 	eeprom->sw_region_offset = data;
@@ -635,8 +766,15 @@ static int wx_set_rar(struct wx *wx, u32 index, u8 *addr, u64 pools,
 
 	/* setup VMDq pool mapping */
 	wr32(wx, WX_PSR_MAC_SWC_VM_L, pools & 0xFFFFFFFF);
-	if (wx->mac.type == wx_mac_sp)
+
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
 		wr32(wx, WX_PSR_MAC_SWC_VM_H, pools >> 32);
+		break;
+	default:
+		break;
+	}
 
 	/* HW expects these in little endian so we reverse the byte
 	 * order from network order (big endian) to little endian
@@ -774,9 +912,14 @@ void wx_init_rx_addrs(struct wx *wx)
 
 		wx_set_rar(wx, 0, wx->mac.addr, 0, WX_PSR_MAC_SWC_AD_H_AV);
 
-		if (wx->mac.type == wx_mac_sp) {
+		switch (wx->mac.type) {
+		case wx_mac_sp:
+		case wx_mac_aml:
 			/* clear VMDq pool/queue selection for RAR 0 */
 			wx_clear_vmdq(wx, 0, WX_CLEAR_VMDQ_ALL);
+			break;
+		default:
+			break;
 		}
 	}
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 42f90802870be..895f3c96a678f 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1823,10 +1823,16 @@ static int wx_alloc_q_vector(struct wx *wx,
 	/* initialize pointer to rings */
 	ring = q_vector->ring;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+	case wx_mac_aml:
 		default_itr = WX_12K_ITR;
-	else
+		break;
+	default:
 		default_itr = WX_7K_ITR;
+		break;
+	}
+
 	/* initialize ITR */
 	if (txr_count && !rxr_count)
 		/* tx only vector */
@@ -2182,10 +2188,17 @@ void wx_write_eitr(struct wx_q_vector *q_vector)
 	int v_idx = q_vector->v_idx;
 	u32 itr_reg;
 
-	if (wx->mac.type == wx_mac_sp)
+	switch (wx->mac.type) {
+	case wx_mac_sp:
 		itr_reg = q_vector->itr & WX_SP_MAX_EITR;
-	else
+		break;
+	case wx_mac_aml:
+		itr_reg = (q_vector->itr >> 3) & WX_AML_MAX_EITR;
+		break;
+	default:
 		itr_reg = q_vector->itr & WX_EM_MAX_EITR;
+		break;
+	}
 
 	itr_reg |= WX_PX_ITR_CNT_WDIS;
 
@@ -2761,7 +2774,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 
 	netdev->features = features;
 
-	if (wx->mac.type == wx_mac_sp && changed & NETIF_F_HW_VLAN_CTAG_RX)
+	if (changed & NETIF_F_HW_VLAN_CTAG_RX && wx->do_reset)
 		wx->do_reset(netdev);
 	else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER))
 		wx_set_rx_mode(netdev);
@@ -2793,7 +2806,7 @@ int wx_set_features(struct net_device *netdev, netdev_features_t features)
 		break;
 	}
 
-	if (need_reset)
+	if (need_reset && wx->do_reset)
 		wx->do_reset(netdev);
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index db446e690dc7e..f79746ac6aca3 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -309,6 +309,10 @@
 #define WX_MNG_MBOX_CTL_FWRDY        BIT(2)
 #define WX_MNG_BMC2OS_CNT            0x1E090
 #define WX_MNG_OS2BMC_CNT            0x1E094
+#define WX_SW2FW_MBOX_CMD            0x1E0A0
+#define WX_SW2FW_MBOX_CMD_VLD        BIT(31)
+#define WX_SW2FW_MBOX                0x1E200
+#define WX_FW2SW_MBOX                0x1E300
 
 /************************************* ETH MAC *****************************/
 #define WX_MAC_TX_CFG                0x11000
@@ -372,6 +376,7 @@ enum WX_MSCA_CMD_value {
 #define WX_12K_ITR                   336
 #define WX_20K_ITR                   200
 #define WX_SP_MAX_EITR               0x00000FF8U
+#define WX_AML_MAX_EITR              0x00000FFFU
 #define WX_EM_MAX_EITR               0x00007FFCU
 
 /* transmit DMA Registers */
@@ -415,6 +420,7 @@ enum WX_MSCA_CMD_value {
 /****************** Manageablility Host Interface defines ********************/
 #define WX_HI_MAX_BLOCK_BYTE_LENGTH  256 /* Num of bytes in range */
 #define WX_HI_COMMAND_TIMEOUT        1000 /* Process HI command limit */
+#define WX_HIC_HDR_INDEX_MAX         255
 
 #define FW_READ_SHADOW_RAM_CMD       0x31
 #define FW_READ_SHADOW_RAM_LEN       0x6
@@ -711,21 +717,30 @@ struct wx_hic_hdr {
 		u8 cmd_resv;
 		u8 ret_status;
 	} cmd_or_resp;
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 struct wx_hic_hdr2_req {
 	u8 cmd;
 	u8 buf_lenh;
 	u8 buf_lenl;
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 struct wx_hic_hdr2_rsp {
 	u8 cmd;
 	u8 buf_lenl;
 	u8 buf_lenh_status;     /* 7-5: high bits of buf_len, 4-0: status */
-	u8 checksum;
+	union {
+		u8 checksum;
+		u8 index;
+	};
 };
 
 union wx_hic_hdr2 {
@@ -773,7 +788,8 @@ struct wx_thermal_sensor_data {
 enum wx_mac_type {
 	wx_mac_unknown = 0,
 	wx_mac_sp,
-	wx_mac_em
+	wx_mac_em,
+	wx_mac_aml,
 };
 
 enum sp_media_type {
@@ -1085,12 +1101,14 @@ struct wx_hw_stats {
 
 enum wx_state {
 	WX_STATE_RESETTING,
+	WX_STATE_SWFW_BUSY,
 	WX_STATE_PTP_RUNNING,
 	WX_STATE_PTP_TX_IN_PROGRESS,
-	WX_STATE_NBITS,		/* must be last */
+	WX_STATE_NBITS		/* must be last */
 };
 
 enum wx_pf_flags {
+	WX_FLAG_SWFW_RING,
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
@@ -1130,6 +1148,7 @@ struct wx {
 	char eeprom_id[32];
 	char *driver_name;
 	enum wx_reset_type reset_type;
+	u8 swfw_index;
 
 	/* PHY stuff */
 	unsigned int link;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
index cd1372da92a94..4b9921b7bb112 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_hw.c
@@ -197,6 +197,12 @@ int txgbe_reset_hw(struct wx *wx)
 
 	txgbe_reset_misc(wx);
 
+	if (wx->mac.type != wx_mac_sp) {
+		wr32(wx, TXGBE_PX_PF_BME, 0x1);
+		wr32m(wx, TXGBE_RDM_RSC_CTL, TXGBE_RDM_RSC_CTL_FREE_CTL,
+		      TXGBE_RDM_RSC_CTL_FREE_CTL);
+	}
+
 	wx_clear_hw_cntrs(wx);
 
 	/* Store the permanent mac address */
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 0ee73a265545c..8658a51ee8106 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -166,6 +166,9 @@ static void txgbe_del_irq_domain(struct txgbe *txgbe)
 
 void txgbe_free_misc_irq(struct txgbe *txgbe)
 {
+	if (txgbe->wx->mac.type == wx_mac_aml)
+		return;
+
 	free_irq(txgbe->link_irq, txgbe);
 	free_irq(txgbe->misc.irq, txgbe);
 	txgbe_del_irq_domain(txgbe);
@@ -177,6 +180,9 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int hwirq, err;
 
+	if (wx->mac.type == wx_mac_aml)
+		goto skip_sp_irq;
+
 	txgbe->misc.nirqs = 1;
 	txgbe->misc.domain = irq_domain_add_simple(NULL, txgbe->misc.nirqs, 0,
 						   &txgbe_misc_irq_domain_ops, txgbe);
@@ -206,6 +212,7 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	if (err)
 		goto free_msic_irq;
 
+skip_sp_irq:
 	wx->misc_irq_domain = true;
 
 	return 0;
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index 734450af9a432..ce83811a45e2d 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -35,6 +35,12 @@ char txgbe_driver_name[] = "txgbe";
 static const struct pci_device_id txgbe_pci_tbl[] = {
 	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_SP1000), 0},
 	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_WX1820), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5010), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5110), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5025), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5125), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5040), 0},
+	{ PCI_VDEVICE(WANGXUN, TXGBE_DEV_ID_AML5140), 0},
 	/* required last entry */
 	{ .device = 0 }
 };
@@ -90,7 +96,18 @@ static void txgbe_up_complete(struct wx *wx)
 	smp_mb__before_atomic();
 	wx_napi_enable_all(wx);
 
-	phylink_start(wx->phylink);
+	if (wx->mac.type == wx_mac_aml) {
+		u32 reg;
+
+		reg = rd32(wx, TXGBE_AML_MAC_TX_CFG);
+		reg &= ~TXGBE_AML_MAC_TX_CFG_SPEED_MASK;
+		reg |= TXGBE_AML_MAC_TX_CFG_SPEED_25G;
+		wr32(wx, WX_MAC_TX_CFG, reg);
+		txgbe_enable_sec_tx_path(wx);
+		netif_carrier_on(wx->netdev);
+	} else {
+		phylink_start(wx->phylink);
+	}
 
 	/* clear any pending interrupts, may auto mask */
 	rd32(wx, WX_PX_IC(0));
@@ -171,7 +188,10 @@ void txgbe_down(struct wx *wx)
 {
 	txgbe_disable_device(wx);
 	txgbe_reset(wx);
-	phylink_stop(wx->phylink);
+	if (wx->mac.type == wx_mac_aml)
+		netif_carrier_off(wx->netdev);
+	else
+		phylink_stop(wx->phylink);
 
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
@@ -197,6 +217,14 @@ static void txgbe_init_type_code(struct wx *wx)
 	case TXGBE_DEV_ID_WX1820:
 		wx->mac.type = wx_mac_sp;
 		break;
+	case TXGBE_DEV_ID_AML5010:
+	case TXGBE_DEV_ID_AML5110:
+	case TXGBE_DEV_ID_AML5025:
+	case TXGBE_DEV_ID_AML5125:
+	case TXGBE_DEV_ID_AML5040:
+	case TXGBE_DEV_ID_AML5140:
+		wx->mac.type = wx_mac_aml;
+		break;
 	default:
 		wx->mac.type = wx_mac_unknown;
 		break;
@@ -284,6 +312,17 @@ static int txgbe_sw_init(struct wx *wx)
 
 	wx->do_reset = txgbe_do_reset;
 
+	switch (wx->mac.type) {
+	case wx_mac_sp:
+		break;
+	case wx_mac_aml:
+		set_bit(WX_FLAG_SWFW_RING, wx->flags);
+		wx->swfw_index = 0;
+		break;
+	default:
+		break;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 7e17d727c2bad..85f022ceef4fe 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -567,6 +567,9 @@ int txgbe_init_phy(struct txgbe *txgbe)
 	struct wx *wx = txgbe->wx;
 	int ret;
 
+	if (wx->mac.type == wx_mac_aml)
+		return 0;
+
 	if (txgbe->wx->media_type == sp_media_copper)
 		return txgbe_ext_phy_init(txgbe);
 
@@ -631,6 +634,9 @@ int txgbe_init_phy(struct txgbe *txgbe)
 
 void txgbe_remove_phy(struct txgbe *txgbe)
 {
+	if (txgbe->wx->mac.type == wx_mac_aml)
+		return;
+
 	if (txgbe->wx->media_type == sp_media_copper) {
 		phylink_disconnect_phy(txgbe->wx->phylink);
 		phylink_destroy(txgbe->wx->phylink);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 629a13e96b859..9c1c26234cad9 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -10,6 +10,12 @@
 /* Device IDs */
 #define TXGBE_DEV_ID_SP1000                     0x1001
 #define TXGBE_DEV_ID_WX1820                     0x2001
+#define TXGBE_DEV_ID_AML5010                    0x5010
+#define TXGBE_DEV_ID_AML5110                    0x5110
+#define TXGBE_DEV_ID_AML5025                    0x5025
+#define TXGBE_DEV_ID_AML5125                    0x5125
+#define TXGBE_DEV_ID_AML5040                    0x5040
+#define TXGBE_DEV_ID_AML5140                    0x5140
 
 /* Subsystem IDs */
 /* SFP */
@@ -137,6 +143,14 @@
 #define TXGBE_RDB_FDIR_FLEX_CFG_MSK             BIT(2)
 #define TXGBE_RDB_FDIR_FLEX_CFG_OFST(v)         FIELD_PREP(GENMASK(7, 3), v)
 
+/*************************** Amber Lite Registers ****************************/
+#define TXGBE_PX_PF_BME                         0x4B8
+#define TXGBE_AML_MAC_TX_CFG                    0x11000
+#define TXGBE_AML_MAC_TX_CFG_SPEED_MASK         GENMASK(30, 27)
+#define TXGBE_AML_MAC_TX_CFG_SPEED_25G          BIT(28)
+#define TXGBE_RDM_RSC_CTL                       0x1200C
+#define TXGBE_RDM_RSC_CTL_FREE_CTL              BIT(7)
+
 /* Checksum and EEPROM pointers */
 #define TXGBE_EEPROM_LAST_WORD                  0x800
 #define TXGBE_EEPROM_CHECKSUM                   0x2F

From a3ad653c915990fcbb72f9d41c94628255278abc Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Fri, 21 Feb 2025 14:57:18 +0800
Subject: [PATCH 1066/2753] net: wangxun: Replace the judgement of MAC type
 with flags

Since device MAC types are constantly being added, the judgments of
wx->mac.type are complex. Try to convert the types to flags depending
on functions.

Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Link: https://patch.msgid.link/20250221065718.197544-2-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_ethtool.c | 8 ++++----
 drivers/net/ethernet/wangxun/libwx/wx_hw.c      | 4 ++--
 drivers/net/ethernet/wangxun/libwx/wx_type.h    | 1 +
 drivers/net/ethernet/wangxun/txgbe/txgbe_main.c | 2 ++
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
index 6d3b57233a39c..43019ec9329c8 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ethtool.c
@@ -72,7 +72,7 @@ int wx_get_sset_count(struct net_device *netdev, int sset)
 
 	switch (sset) {
 	case ETH_SS_STATS:
-		return (wx->mac.type == wx_mac_sp) ?
+		return (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) ?
 			WX_STATS_LEN + WX_FDIR_STATS_LEN : WX_STATS_LEN;
 	default:
 		return -EOPNOTSUPP;
@@ -90,7 +90,7 @@ void wx_get_strings(struct net_device *netdev, u32 stringset, u8 *data)
 	case ETH_SS_STATS:
 		for (i = 0; i < WX_GLOBAL_STATS_LEN; i++)
 			ethtool_puts(&p, wx_gstrings_stats[i].stat_string);
-		if (wx->mac.type == wx_mac_sp) {
+		if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 			for (i = 0; i < WX_FDIR_STATS_LEN; i++)
 				ethtool_puts(&p, wx_gstrings_fdir_stats[i].stat_string);
 		}
@@ -124,7 +124,7 @@ void wx_get_ethtool_stats(struct net_device *netdev,
 			   sizeof(u64)) ? *(u64 *)p : *(u32 *)p;
 	}
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 		for (k = 0; k < WX_FDIR_STATS_LEN; k++) {
 			p = (char *)wx + wx_gstrings_fdir_stats[k].stat_offset;
 			data[i++] = *(u64 *)p;
@@ -199,7 +199,7 @@ void wx_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *info)
 	unsigned int stats_len = WX_STATS_LEN;
 	struct wx *wx = netdev_priv(netdev);
 
-	if (wx->mac.type == wx_mac_sp)
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags))
 		stats_len += WX_FDIR_STATS_LEN;
 
 	strscpy(info->driver, wx->driver_name, sizeof(info->driver));
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index b5f35b187077a..aed45abafb1b7 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1861,7 +1861,7 @@ void wx_configure_rx(struct wx *wx)
 	/* enable hw crc stripping */
 	wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_RSC_CAPABLE, wx->flags)) {
 		u32 psrctl;
 
 		/* RSC Setup */
@@ -2513,7 +2513,7 @@ void wx_update_stats(struct wx *wx)
 	hwstats->b2ogprc += rd32(wx, WX_RDM_BMC2OS_CNT);
 	hwstats->rdmdrop += rd32(wx, WX_RDM_DRP_PKT);
 
-	if (wx->mac.type == wx_mac_sp) {
+	if (test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)) {
 		hwstats->fdirmatch += rd32(wx, WX_RDB_FDIR_MATCH);
 		hwstats->fdirmiss += rd32(wx, WX_RDB_FDIR_MISS);
 	}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index f79746ac6aca3..5b230ecbbabb5 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1112,6 +1112,7 @@ enum wx_pf_flags {
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
+	WX_FLAG_RSC_CAPABLE,
 	WX_FLAG_RX_HWTSTAMP_ENABLED,
 	WX_FLAG_RX_HWTSTAMP_IN_REGISTER,
 	WX_FLAG_PTP_PPS_ENABLED,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index ce83811a45e2d..a2e245e3b0168 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -298,6 +298,8 @@ static int txgbe_sw_init(struct wx *wx)
 	wx->atr = txgbe_atr;
 	wx->configure_fdir = txgbe_configure_fdir;
 
+	set_bit(WX_FLAG_RSC_CAPABLE, wx->flags);
+
 	/* enable itr by default in dynamic mode */
 	wx->rx_itr_setting = 1;
 	wx->tx_itr_setting = 1;

From 3400ae49cd1a5a2a638c31498a5f5d0a0e11d8f8 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:51 +0200
Subject: [PATCH 1067/2753] net/mlx5e: Add helper function to update IPSec
 default destination
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The default destination of IPSec steering rules for MPV mode will be
updated when the master device is brought up or down. Move the common
code into the helper function. It’s convenient to update destinations
in later patches.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c         | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index e7b64679f1219..7f82d530d3e14 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -493,6 +493,14 @@ static int ipsec_miss_create(struct mlx5_core_dev *mdev,
 	return err;
 }
 
+static void ipsec_rx_update_default_dest(struct mlx5e_ipsec_rx *rx,
+					 struct mlx5_flow_destination *old_dest,
+					 struct mlx5_flow_destination *new_dest)
+{
+	mlx5_modify_rule_destination(rx->status.rule, new_dest, old_dest);
+	mlx5_modify_rule_destination(rx->sa.rule, new_dest, old_dest);
+}
+
 static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
 {
 	struct mlx5e_ipsec_rx *rx = ipsec_rx(ipsec, family, XFRM_DEV_OFFLOAD_PACKET);
@@ -507,8 +515,7 @@ static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
 
 	new_dest.ft = mlx5_ipsec_fs_roce_ft_get(ipsec->roce, family);
 	new_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 }
 
 static void handle_ipsec_rx_cleanup(struct mlx5e_ipsec *ipsec, u32 family)
@@ -520,8 +527,7 @@ static void handle_ipsec_rx_cleanup(struct mlx5e_ipsec *ipsec, u32 family)
 	old_dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
 	new_dest = mlx5_ttc_get_default_dest(mlx5e_fs_get_ttc(ipsec->fs, false),
 					     family2tt(family));
-	mlx5_modify_rule_destination(rx->sa.rule, &new_dest, &old_dest);
-	mlx5_modify_rule_destination(rx->status.rule, &new_dest, &old_dest);
+	ipsec_rx_update_default_dest(rx, &old_dest, &new_dest);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, ipsec->mdev);
 }

From 20d5fdc8951a1ed63af2b5b1671afb3b4f5a3293 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:52 +0200
Subject: [PATCH 1068/2753] net/mlx5e: Change the destination of IPSec RX SA
 miss rule

For eswitch in legacy mode, the packets decrypted in RX SA table will
continue to be processed for RoCE. But this is not necessary for the
un-decrypted packets, which don't match any decryption rules but hit
the miss rule at the end of the table. So, change the destination of
miss rule to TTC default one and skip RoCE.

For eswitch in switchdev mode, the destination is unchanged.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 20 ++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 7f82d530d3e14..7c9fdea213662 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -498,7 +498,6 @@ static void ipsec_rx_update_default_dest(struct mlx5e_ipsec_rx *rx,
 					 struct mlx5_flow_destination *new_dest)
 {
 	mlx5_modify_rule_destination(rx->status.rule, new_dest, old_dest);
-	mlx5_modify_rule_destination(rx->sa.rule, new_dest, old_dest);
 }
 
 static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
@@ -658,6 +657,20 @@ static int ipsec_rx_status_pass_dest_get(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static void ipsec_rx_sa_miss_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5e_ipsec_rx_create_attr *attr,
+				      struct mlx5_flow_destination *dest,
+				      struct mlx5_flow_destination *miss_dest)
+{
+	if (rx == ipsec->rx_esw)
+		*miss_dest = *dest;
+	else
+		*miss_dest =
+			mlx5_ttc_get_default_dest(attr->ttc,
+						  family2tt(attr->family));
+}
+
 static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 				struct mlx5e_ipsec_rx *rx,
 				struct mlx5e_ipsec_rx_create_attr *attr)
@@ -672,8 +685,8 @@ static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
+	struct mlx5_flow_destination dest[2], miss_dest;
 	struct mlx5e_ipsec_rx_create_attr attr;
-	struct mlx5_flow_destination dest[2];
 	struct mlx5_flow_table *ft;
 	u32 flags = 0;
 	int err;
@@ -709,7 +722,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	}
 	rx->ft.sa = ft;
 
-	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, dest);
+	ipsec_rx_sa_miss_dest_get(ipsec, rx, &attr, &dest[0], &miss_dest);
+	err = ipsec_miss_create(mdev, rx->ft.sa, &rx->sa, &miss_dest);
 	if (err)
 		goto err_fs;
 

From 85e4a808af2545fefaf18c8fe50071b06fcbdabc Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:53 +0200
Subject: [PATCH 1069/2753] net/mlx5e: Add correct match to check IPSec
 syndromes for switchdev mode

In commit dddb49b63d86 ("net/mlx5e: Add IPsec and ASO syndromes check
in HW"), IPSec and ASO syndromes checks after decryption for the
specified ASO object were added. But they are correct only for eswith
in legacy mode. For switchdev mode, metadata register c1 is used to
save the mapped id (not ASO object id). So, need to change the match
accordingly for the check rules in status table.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 28 ++++++++++++++-----
 .../mellanox/mlx5/core/esw/ipsec_fs.c         | 13 +++++++++
 .../mellanox/mlx5/core/esw/ipsec_fs.h         |  5 ++++
 include/linux/mlx5/eswitch.h                  |  2 ++
 4 files changed, 41 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 7c9fdea213662..e1b518aedee8a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -165,6 +165,25 @@ static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 #endif
 }
 
+static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					struct mlx5e_ipsec_rx *rx,
+					struct mlx5_flow_spec *spec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+
+	if (rx == ipsec->rx_esw) {
+		mlx5_esw_ipsec_rx_rule_add_match_obj(sa_entry, spec);
+	} else {
+		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+				 misc_parameters_2.metadata_reg_c_2);
+		MLX5_SET(fte_match_param, spec->match_value,
+			 misc_parameters_2.metadata_reg_c_2,
+			 sa_entry->ipsec_obj_id | BIT(31));
+
+		spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+	}
+}
+
 static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 					 struct mlx5e_ipsec_rx *rx)
 {
@@ -200,11 +219,8 @@ static int rx_add_rule_drop_auth_trailer(struct mlx5e_ipsec_sa_entry *sa_entry,
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.ipsec_syndrome);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.ipsec_syndrome, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
@@ -281,10 +297,8 @@ static int rx_add_rule_drop_replay(struct mlx5e_ipsec_sa_entry *sa_entry, struct
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_4);
 	MLX5_SET(fte_match_param, spec->match_value, misc_parameters_2.metadata_reg_c_4, 1);
-	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria, misc_parameters_2.metadata_reg_c_2);
-	MLX5_SET(fte_match_param, spec->match_value,  misc_parameters_2.metadata_reg_c_2,
-		 sa_entry->ipsec_obj_id | BIT(31));
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, &dest, 1);
 	if (IS_ERR(rule)) {
 		err = PTR_ERR(rule);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index ed977ae75fab8..4bba2884c1c05 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -85,6 +85,19 @@ int mlx5_esw_ipsec_rx_setup_modify_header(struct mlx5e_ipsec_sa_entry *sa_entry,
 	return err;
 }
 
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec)
+{
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_1,
+		 ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_1,
+		 sa_entry->rx_mapped_id << ESW_ZONE_ID_BITS);
+
+	spec->match_criteria_enable |= MLX5_MATCH_MISC_PARAMETERS_2;
+}
+
 void mlx5_esw_ipsec_rx_id_mapping_remove(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
index ac9c65b89166e..514c15258b1d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.h
@@ -20,6 +20,8 @@ int mlx5_esw_ipsec_rx_ipsec_obj_id_search(struct mlx5e_priv *priv, u32 id,
 void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_tx_create_attr *attr);
 void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev);
+void mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+					  struct mlx5_flow_spec *spec);
 #else
 static inline void mlx5_esw_ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_rx_create_attr *attr) {}
@@ -48,5 +50,8 @@ static inline void mlx5_esw_ipsec_tx_create_attr_set(struct mlx5e_ipsec *ipsec,
 						     struct mlx5e_ipsec_tx_create_attr *attr) {}
 
 static inline void mlx5_esw_ipsec_restore_dest_uplink(struct mlx5_core_dev *mdev) {}
+static inline void
+mlx5_esw_ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
+				     struct mlx5_flow_spec *spec) {}
 #endif /* CONFIG_MLX5_ESWITCH */
 #endif /* __MLX5_ESW_IPSEC_FS_H__ */
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index df73a2ccc9af3..67256e776566c 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -147,6 +147,8 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 
 /* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */
 #define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
+#define ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK \
+	GENMASK(31 - ESW_RESERVED_BITS, ESW_ZONE_ID_BITS)
 
 u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);

From 7d9e292ecd678269fd11ec8d09610fd1eda2742e Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:54 +0200
Subject: [PATCH 1070/2753] net/mlx5e: Move IPSec policy check after decryption
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, xfrm policy check is done before decryption in mlx5 driver.
If matching any policy, packets are forwarded to xfrm state table for
decryption. But this is exact opposite to what software does. For
kernel implementation, xfrm decode is unconditionally activated
whenever an IPSec packet reaches the input flow if there’s a matching
state rule.

This patch changes the order, move policy check after decryption.
Besides, a miss flow table is added at the end for legacy mode, to
make it easier to update the default destination of the steering rules.

So ESP packets are firstly forwarded to SA table for decryption, then
the result is checked in status table. If the decryption succeeds,
packets are forwarded to another table to check xfrm policy rules.
When a policy with allow action is matched, if in legacy mode packets
are forwarded to miss flow table with one rule to forward them to RoCE
tables, if in switchdev mode they are forwarded directly to TC root
chain instead.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/fs.h   |   4 +-
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 195 +++++++++++++-----
 .../mellanox/mlx5/core/esw/ipsec_fs.c         |   2 +-
 3 files changed, 145 insertions(+), 56 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
index 1e8b7d3307014..b5c3a2a9d2a59 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
@@ -84,9 +84,9 @@ enum {
 	MLX5E_ARFS_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 #endif
 #ifdef CONFIG_MLX5_EN_IPSEC
-	MLX5E_ACCEL_FS_POL_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
-	MLX5E_ACCEL_FS_ESP_FT_LEVEL,
+	MLX5E_ACCEL_FS_ESP_FT_LEVEL = MLX5E_INNER_TTC_FT_LEVEL + 1,
 	MLX5E_ACCEL_FS_ESP_FT_ERR_LEVEL,
+	MLX5E_ACCEL_FS_POL_FT_LEVEL,
 	MLX5E_ACCEL_FS_ESP_FT_ROCE_LEVEL,
 #endif
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index e1b518aedee8a..3d9d7aa2a06ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -45,6 +45,8 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_status_checks status_drops;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
+	struct mlx5_flow_table *pol_miss_ft;
+	struct mlx5_flow_handle *pol_miss_rule;
 	u8 allow_tunnel_mode : 1;
 };
 
@@ -156,13 +158,6 @@ static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
 	mlx5_del_flow_rules(rx->status.rule);
-
-	if (rx != ipsec->rx_esw)
-		return;
-
-#ifdef CONFIG_MLX5_ESWITCH
-	mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch), 0, 1, 0);
-#endif
 }
 
 static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
@@ -415,7 +410,7 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
-	flow_act.flags = FLOW_ACT_NO_APPEND;
+	flow_act.flags = FLOW_ACT_NO_APPEND | FLOW_ACT_IGNORE_FLOW_LEVEL;
 	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
 			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
 	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
@@ -596,13 +591,8 @@ static void ipsec_rx_ft_disconnect(struct mlx5e_ipsec *ipsec, u32 family)
 	mlx5_ttc_fwd_default_dest(ttc, family2tt(family));
 }
 
-static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
-		       struct mlx5e_ipsec_rx *rx, u32 family)
+static void ipsec_rx_policy_destroy(struct mlx5e_ipsec_rx *rx)
 {
-	/* disconnect */
-	if (rx != ipsec->rx_esw)
-		ipsec_rx_ft_disconnect(ipsec, family);
-
 	if (rx->chains) {
 		ipsec_chains_destroy(rx->chains);
 	} else {
@@ -611,6 +601,19 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		mlx5_destroy_flow_table(rx->ft.pol);
 	}
 
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+}
+
+static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
+		       struct mlx5e_ipsec_rx *rx, u32 family)
+{
+	/* disconnect */
+	if (rx != ipsec->rx_esw)
+		ipsec_rx_ft_disconnect(ipsec, family);
+
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 	mlx5_destroy_flow_table(rx->ft.sa);
@@ -619,7 +622,15 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
+	ipsec_rx_policy_destroy(rx);
+
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
+
+#ifdef CONFIG_MLX5_ESWITCH
+	if (rx == ipsec->rx_esw)
+		mlx5_chains_put_table(esw_chains(ipsec->mdev->priv.eswitch),
+				      0, 1, 0);
+#endif
 }
 
 static void ipsec_rx_create_attr_set(struct mlx5e_ipsec *ipsec,
@@ -685,6 +696,14 @@ static void ipsec_rx_sa_miss_dest_get(struct mlx5e_ipsec *ipsec,
 						  family2tt(attr->family));
 }
 
+static void ipsec_rx_default_dest_get(struct mlx5e_ipsec *ipsec,
+				      struct mlx5e_ipsec_rx *rx,
+				      struct mlx5_flow_destination *dest)
+{
+	dest->type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest->ft = rx->pol_miss_ft;
+}
+
 static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 				struct mlx5e_ipsec_rx *rx,
 				struct mlx5e_ipsec_rx_create_attr *attr)
@@ -692,10 +711,105 @@ static void ipsec_rx_ft_connect(struct mlx5e_ipsec *ipsec,
 	struct mlx5_flow_destination dest = {};
 
 	dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest.ft = rx->ft.pol;
+	dest.ft = rx->ft.sa;
 	mlx5_ttc_fwd_dest(attr->ttc, family2tt(attr->family), &dest);
 }
 
+static int ipsec_rx_chains_create_miss(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr,
+				       struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_table_attr ft_attr = {};
+	MLX5_DECLARE_FLOW_ACT(flow_act);
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	if (rx == ipsec->rx_esw) {
+		/* No need to create miss table for switchdev mode,
+		 * just set it to the root chain table.
+		 */
+		rx->pol_miss_ft = dest->ft;
+		return 0;
+	}
+
+	ft_attr.max_fte = 1;
+	ft_attr.autogroup.max_num_groups = 1;
+	ft_attr.level = attr->pol_level;
+	ft_attr.prio = attr->prio;
+
+	ft = mlx5_create_auto_grouped_flow_table(attr->ns, &ft_attr);
+	if (IS_ERR(ft))
+		return PTR_ERR(ft);
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_rule;
+	}
+
+	rx->pol_miss_ft = ft;
+	rx->pol_miss_rule = rule;
+
+	return 0;
+
+err_rule:
+	mlx5_destroy_flow_table(ft);
+	return err;
+}
+
+static int ipsec_rx_policy_create(struct mlx5e_ipsec *ipsec,
+				  struct mlx5e_ipsec_rx *rx,
+				  struct mlx5e_ipsec_rx_create_attr *attr,
+				  struct mlx5_flow_destination *dest)
+{
+	struct mlx5_flow_destination default_dest;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_table *ft;
+	int err;
+
+	err = ipsec_rx_chains_create_miss(ipsec, rx, attr, dest);
+	if (err)
+		return err;
+
+	ipsec_rx_default_dest_get(ipsec, rx, &default_dest);
+
+	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
+		rx->chains = ipsec_chains_create(mdev,
+						 default_dest.ft,
+						 attr->chains_ns,
+						 attr->prio,
+						 attr->sa_level,
+						 &rx->ft.pol);
+		if (IS_ERR(rx->chains))
+			err = PTR_ERR(rx->chains);
+	} else {
+		ft = ipsec_ft_create(attr->ns, attr->pol_level,
+				     attr->prio, 2, 0);
+		if (IS_ERR(ft)) {
+			err = PTR_ERR(ft);
+			goto err_out;
+		}
+		rx->ft.pol = ft;
+
+		err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol,
+					&default_dest);
+		if (err)
+			mlx5_destroy_flow_table(rx->ft.pol);
+	}
+
+	if (!err)
+		return 0;
+
+err_out:
+	if (rx->pol_miss_rule) {
+		mlx5_del_flow_rules(rx->pol_miss_rule);
+		mlx5_destroy_flow_table(rx->pol_miss_ft);
+	}
+	return err;
+}
+
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
@@ -718,12 +832,6 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	}
 	rx->ft.status = ft;
 
-	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
-	dest[1].counter = rx->fc->cnt;
-	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
-	if (err)
-		goto err_add;
-
 	/* Create FT */
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
 		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
@@ -741,51 +849,33 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		goto err_fs;
 
-	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_PRIO) {
-		rx->chains = ipsec_chains_create(mdev, rx->ft.sa,
-						 attr.chains_ns,
-						 attr.prio,
-						 attr.pol_level,
-						 &rx->ft.pol);
-		if (IS_ERR(rx->chains)) {
-			err = PTR_ERR(rx->chains);
-			goto err_pol_ft;
-		}
-
-		goto connect;
-	}
+	err = ipsec_rx_policy_create(ipsec, rx, &attr, &dest[0]);
+	if (err)
+		goto err_policy;
 
-	ft = ipsec_ft_create(attr.ns, attr.pol_level, attr.prio, 2, 0);
-	if (IS_ERR(ft)) {
-		err = PTR_ERR(ft);
-		goto err_pol_ft;
-	}
-	rx->ft.pol = ft;
-	memset(dest, 0x00, 2 * sizeof(*dest));
 	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[0].ft = rx->ft.sa;
-	err = ipsec_miss_create(mdev, rx->ft.pol, &rx->pol, dest);
+	dest[0].ft = rx->ft.pol;
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
 	if (err)
-		goto err_pol_miss;
+		goto err_add;
 
-connect:
 	/* connect */
 	if (rx != ipsec->rx_esw)
 		ipsec_rx_ft_connect(ipsec, rx, &attr);
 	return 0;
 
-err_pol_miss:
-	mlx5_destroy_flow_table(rx->ft.pol);
-err_pol_ft:
+err_add:
+	ipsec_rx_policy_destroy(rx);
+err_policy:
 	mlx5_del_flow_rules(rx->sa.rule);
 	mlx5_destroy_flow_group(rx->sa.group);
 err_fs:
 	mlx5_destroy_flow_table(rx->ft.sa);
-err_fs_ft:
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
-	mlx5_ipsec_rx_status_destroy(ipsec, rx);
-err_add:
+err_fs_ft:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -1957,8 +2047,7 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	flow_act.flags |= FLOW_ACT_NO_APPEND;
 	if (rx == ipsec->rx_esw && rx->chains)
 		flow_act.flags |= FLOW_ACT_IGNORE_FLOW_LEVEL;
-	dest[dstn].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[dstn].ft = rx->ft.sa;
+	ipsec_rx_default_dest_get(ipsec, rx, &dest[dstn]);
 	dstn++;
 	rule = mlx5_add_flow_rules(ft, spec, &flow_act, dest, dstn);
 	if (IS_ERR(rule)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
index 4bba2884c1c05..3cfe743610d3f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/ipsec_fs.c
@@ -10,9 +10,9 @@
 #endif
 
 enum {
-	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_LEVEL,
 	MLX5_ESW_IPSEC_RX_ESP_FT_CHK_LEVEL,
+	MLX5_ESW_IPSEC_RX_POL_FT_LEVEL,
 };
 
 enum {

From aa2961e19ff60f2b69c0e35320221f2827d0bac6 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:55 +0200
Subject: [PATCH 1071/2753] net/mlx5e: Skip IPSec RX policy check for crypto
 offload

For crypto offload, there is no xfrm policy rule offloaded to
hardware, so no need to continue with policy check for it.

Previously, for crypto offload, the hardware metadata reg c4 is not
used and not changed, but set to ASO_OK(0) before decryption to avoid
garbage data. Then a default rule is added to check ipsec_syndrome and
this register. Packets are forwarded to policy table if succeed, or
drop if fails.

According to hardware document, this register value could be 0, 1.
So a special value (0xAA), which is not used by hardware, is chosen as
an indication for crypto offload. It is set to c4 before decryption.
Then a default rule, which matches on 0xAA (and ipsec_syndrome on 0),
is added, which means packets are done by crypto offload, and
sends them to kernel directly, thus skips the policy check.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 81 +++++++++++++------
 1 file changed, 56 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 3d9d7aa2a06ae..e72b365f24be8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -16,6 +16,14 @@
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
 #define IPSEC_TUNNEL_DEFAULT_TTL 0x40
 
+enum {
+	MLX5_IPSEC_ASO_OK,
+	MLX5_IPSEC_ASO_BAD_REPLY,
+
+	/* For crypto offload, set by driver */
+	MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD = 0xAA,
+};
+
 struct mlx5e_ipsec_fc {
 	struct mlx5_fc *cnt;
 	struct mlx5_fc *drop;
@@ -33,6 +41,8 @@ struct mlx5e_ipsec_tx {
 };
 
 struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_handle *packet_offload_pass_rule;
+	struct mlx5_flow_handle *crypto_offload_pass_rule;
 	struct mlx5_flow_group *drop_all_group;
 	struct mlx5e_ipsec_drop all;
 };
@@ -41,8 +51,7 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
 	struct mlx5e_ipsec_miss sa;
-	struct mlx5e_ipsec_rule status;
-	struct mlx5e_ipsec_status_checks status_drops;
+	struct mlx5e_ipsec_status_checks status_checks;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
 	struct mlx5_flow_table *pol_miss_ft;
@@ -149,15 +158,16 @@ static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 static void ipsec_rx_status_drop_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status_drops.all.rule);
-	mlx5_fc_destroy(ipsec->mdev, rx->status_drops.all.fc);
-	mlx5_destroy_flow_group(rx->status_drops.drop_all_group);
+	mlx5_del_flow_rules(rx->status_checks.all.rule);
+	mlx5_fc_destroy(ipsec->mdev, rx->status_checks.all.fc);
+	mlx5_destroy_flow_group(rx->status_checks.drop_all_group);
 }
 
 static void ipsec_rx_status_pass_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
-	mlx5_del_flow_rules(rx->status.rule);
+	mlx5_del_flow_rules(rx->status_checks.packet_offload_pass_rule);
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
 }
 
 static void ipsec_rx_rule_add_match_obj(struct mlx5e_ipsec_sa_entry *sa_entry,
@@ -368,9 +378,9 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status_drops.drop_all_group = g;
-	rx->status_drops.all.rule = rule;
-	rx->status_drops.all.fc = flow_counter;
+	rx->status_checks.drop_all_group = g;
+	rx->status_checks.all.rule = rule;
+	rx->status_checks.all.fc = flow_counter;
 
 	kvfree(flow_group_in);
 	kvfree(spec);
@@ -386,9 +396,11 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 	return err;
 }
 
-static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
-				       struct mlx5e_ipsec_rx *rx,
-				       struct mlx5_flow_destination *dest)
+static struct mlx5_flow_handle *
+ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
+			    struct mlx5e_ipsec_rx *rx,
+			    struct mlx5_flow_destination *dest,
+			    u8 aso_ok)
 {
 	struct mlx5_flow_act flow_act = {};
 	struct mlx5_flow_handle *rule;
@@ -397,7 +409,7 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
 			 misc_parameters_2.ipsec_syndrome);
@@ -406,7 +418,7 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 	MLX5_SET(fte_match_param, spec->match_value,
 		 misc_parameters_2.ipsec_syndrome, 0);
 	MLX5_SET(fte_match_param, spec->match_value,
-		 misc_parameters_2.metadata_reg_c_4, 0);
+		 misc_parameters_2.metadata_reg_c_4, aso_ok);
 	if (rx == ipsec->rx_esw)
 		spec->flow_context.flow_source = MLX5_FLOW_CONTEXT_FLOW_SOURCE_UPLINK;
 	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
@@ -421,13 +433,12 @@ static int ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 		goto err_rule;
 	}
 
-	rx->status.rule = rule;
 	kvfree(spec);
-	return 0;
+	return rule;
 
 err_rule:
 	kvfree(spec);
-	return err;
+	return ERR_PTR(err);
 }
 
 static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
@@ -441,19 +452,38 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 				       struct mlx5e_ipsec_rx *rx,
 				       struct mlx5_flow_destination *dest)
 {
+	struct mlx5_flow_destination pol_dest[2];
+	struct mlx5_flow_handle *rule;
 	int err;
 
 	err = ipsec_rx_status_drop_all_create(ipsec, rx);
 	if (err)
 		return err;
 
-	err = ipsec_rx_status_pass_create(ipsec, rx, dest);
-	if (err)
-		goto err_pass_create;
+	rule = ipsec_rx_status_pass_create(ipsec, rx, dest,
+					   MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_crypto_offload_pass_create;
+	}
+	rx->status_checks.crypto_offload_pass_rule = rule;
+
+	pol_dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	pol_dest[0].ft = rx->ft.pol;
+	pol_dest[1] = dest[1];
+	rule = ipsec_rx_status_pass_create(ipsec, rx, pol_dest,
+					   MLX5_IPSEC_ASO_OK);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		goto err_packet_offload_pass_create;
+	}
+	rx->status_checks.packet_offload_pass_rule = rule;
 
 	return 0;
 
-err_pass_create:
+err_packet_offload_pass_create:
+	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
+err_crypto_offload_pass_create:
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 	return err;
 }
@@ -506,7 +536,9 @@ static void ipsec_rx_update_default_dest(struct mlx5e_ipsec_rx *rx,
 					 struct mlx5_flow_destination *old_dest,
 					 struct mlx5_flow_destination *new_dest)
 {
-	mlx5_modify_rule_destination(rx->status.rule, new_dest, old_dest);
+	mlx5_modify_rule_destination(rx->pol_miss_rule, new_dest, old_dest);
+	mlx5_modify_rule_destination(rx->status_checks.crypto_offload_pass_rule,
+				     new_dest, old_dest);
 }
 
 static void handle_ipsec_rx_bringup(struct mlx5e_ipsec *ipsec, u32 family)
@@ -853,8 +885,6 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		goto err_policy;
 
-	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
-	dest[0].ft = rx->ft.pol;
 	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
 	dest[1].counter = rx->fc->cnt;
 	err = mlx5_ipsec_rx_status_create(ipsec, rx, dest);
@@ -1464,7 +1494,8 @@ static int setup_modify_header(struct mlx5e_ipsec *ipsec, int type, u32 val, u8
 				 MLX5_ACTION_TYPE_SET);
 			MLX5_SET(set_action_in, action[2], field,
 				 MLX5_ACTION_IN_FIELD_METADATA_REG_C_4);
-			MLX5_SET(set_action_in, action[2], data, 0);
+			MLX5_SET(set_action_in, action[2], data,
+				 MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
 			MLX5_SET(set_action_in, action[2], offset, 0);
 			MLX5_SET(set_action_in, action[2], length, 32);
 		}

From e20674a7e5b1599a6b581206da8b3dbaadca423e Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:56 +0200
Subject: [PATCH 1072/2753] net/mlx5e: Add num_reserved_entries param for
 ipsec_ft_create()

Add parameter for ipsec_ft_create() to pass the number of the reserved
entries when creating auto-grouped flow table. It's used to create
table with pre-defined group(s) which may have more than one rule.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c        | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index e72b365f24be8..2ee4c7bfd7e6a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -141,11 +141,12 @@ static void ipsec_chains_put_table(struct mlx5_fs_chains *chains, u32 prio)
 
 static struct mlx5_flow_table *ipsec_ft_create(struct mlx5_flow_namespace *ns,
 					       int level, int prio,
+					       int num_reserved_entries,
 					       int max_num_groups, u32 flags)
 {
 	struct mlx5_flow_table_attr ft_attr = {};
 
-	ft_attr.autogroup.num_reserved_entries = 1;
+	ft_attr.autogroup.num_reserved_entries = num_reserved_entries;
 	ft_attr.autogroup.max_num_groups = max_num_groups;
 	ft_attr.max_fte = NUM_IPSEC_FTE;
 	ft_attr.level = level;
@@ -818,7 +819,7 @@ static int ipsec_rx_policy_create(struct mlx5e_ipsec *ipsec,
 			err = PTR_ERR(rx->chains);
 	} else {
 		ft = ipsec_ft_create(attr->ns, attr->pol_level,
-				     attr->prio, 2, 0);
+				     attr->prio, 1, 2, 0);
 		if (IS_ERR(ft)) {
 			err = PTR_ERR(ft);
 			goto err_out;
@@ -857,7 +858,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 3, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
@@ -869,7 +870,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (rx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 2, flags);
+	ft = ipsec_ft_create(attr.ns, attr.sa_level, attr.prio, 1, 2, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft;
@@ -1095,7 +1096,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 	int err;
 
 	ipsec_tx_create_attr_set(ipsec, tx, &attr);
-	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 0);
+	ft = ipsec_ft_create(tx->ns, attr.cnt_level, attr.prio, 1, 1, 0);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 	tx->ft.status = ft;
@@ -1108,7 +1109,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		tx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
 	if (tx->allow_tunnel_mode)
 		flags = MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT;
-	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 4, flags);
+	ft = ipsec_ft_create(tx->ns, attr.sa_level, attr.prio, 1, 4, flags);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_sa_ft;
@@ -1136,7 +1137,7 @@ static int tx_create(struct mlx5e_ipsec *ipsec, struct mlx5e_ipsec_tx *tx,
 		goto connect_roce;
 	}
 
-	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 2, 0);
+	ft = ipsec_ft_create(tx->ns, attr.pol_level, attr.prio, 1, 2, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_pol_ft;

From 78e77a41e4019bc4538d09a3738180077220fa77 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:57 +0200
Subject: [PATCH 1073/2753] net/mlx5e: Add pass flow group for IPSec RX status
 table

This flow group is added for the pass rules for both crypto offload
and packet offload. It is placed at the end of the table, and right
before the miss group. There are two entries, and the default pass
rules for both offloads are added in this group.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-8-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 51 ++++++++++++++++++-
 1 file changed, 50 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 2ee4c7bfd7e6a..840d9e0514d3e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -41,6 +41,7 @@ struct mlx5e_ipsec_tx {
 };
 
 struct mlx5e_ipsec_status_checks {
+	struct mlx5_flow_group *pass_group;
 	struct mlx5_flow_handle *packet_offload_pass_rule;
 	struct mlx5_flow_handle *crypto_offload_pass_rule;
 	struct mlx5_flow_group *drop_all_group;
@@ -397,6 +398,47 @@ static int ipsec_rx_status_drop_all_create(struct mlx5e_ipsec *ipsec,
 	return err;
 }
 
+static int ipsec_rx_status_pass_group_create(struct mlx5e_ipsec *ipsec,
+					     struct mlx5e_ipsec_rx *rx)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_flow_table *ft = rx->ft.status;
+	struct mlx5_flow_group *fg;
+	void *match_criteria;
+	u32 *flow_group_in;
+	int err = 0;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	MLX5_SET(create_flow_group_in, flow_group_in, match_criteria_enable,
+		 MLX5_MATCH_MISC_PARAMETERS_2);
+	match_criteria = MLX5_ADDR_OF(create_flow_group_in, flow_group_in,
+				      match_criteria);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 start_flow_index, ft->max_fte - 3);
+	MLX5_SET(create_flow_group_in, flow_group_in,
+		 end_flow_index, ft->max_fte - 2);
+
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_warn(ipsec->mdev,
+			       "Failed to create rx status pass flow group, err=%d\n",
+			       err);
+	}
+	rx->status_checks.pass_group = fg;
+
+	kvfree(flow_group_in);
+	return err;
+}
+
 static struct mlx5_flow_handle *
 ipsec_rx_status_pass_create(struct mlx5e_ipsec *ipsec,
 			    struct mlx5e_ipsec_rx *rx,
@@ -446,6 +488,7 @@ static void mlx5_ipsec_rx_status_destroy(struct mlx5e_ipsec *ipsec,
 					 struct mlx5e_ipsec_rx *rx)
 {
 	ipsec_rx_status_pass_destroy(ipsec, rx);
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 }
 
@@ -461,6 +504,10 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
+	err = ipsec_rx_status_pass_group_create(ipsec, rx);
+	if (err)
+		goto err_pass_group_create;
+
 	rule = ipsec_rx_status_pass_create(ipsec, rx, dest,
 					   MLX5_IPSEC_ASO_SW_CRYPTO_OFFLOAD);
 	if (IS_ERR(rule)) {
@@ -485,6 +532,8 @@ static int mlx5_ipsec_rx_status_create(struct mlx5e_ipsec *ipsec,
 err_packet_offload_pass_create:
 	mlx5_del_flow_rules(rx->status_checks.crypto_offload_pass_rule);
 err_crypto_offload_pass_create:
+	mlx5_destroy_flow_group(rx->status_checks.pass_group);
+err_pass_group_create:
 	ipsec_rx_status_drop_destroy(ipsec, rx);
 	return err;
 }
@@ -858,7 +907,7 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 1, 3, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 3, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;

From c69046c3f2dcef3fe65eb771544547286934a865 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 20 Feb 2025 23:39:58 +0200
Subject: [PATCH 1074/2753] net/mlx5e: Support RX xfrm state selector's UPSPEC
 for packet offload

Previously, the upper layer matches are added for the decryption rule
when xfrm selector's UPSPEC is specified in the command. However, it's
impossible as packets are not decrypted, and there is no way to do
match on the upper protocol (TCP/UDP) with specific source/destination
port. The result is that packets are not decrypted by hardware because
of this mismatch. Instead, they are forwarded to kernel, and
decryption is done by software.

To resolve this issue, this patch adds new table (sa_sel) after status
table and before policy table. When UPSPEC's proto is specified in
xfrm state's selector, a rule is added in status table to forward the
decrypted packets to sa_sel table, where the corresponding rule for
selector's UPSPEC is added, and packet's upper headers are checked
there. If matched, they will be forward to policy table to do policy
check. Otherwise, they are dropped immediately.

Besides, add a global count for this kind of packet drop.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250220213959.504304-9-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.h       |   5 +
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 238 +++++++++++++++++-
 .../mellanox/mlx5/core/en_accel/ipsec_stats.c |   1 +
 3 files changed, 242 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 7d943e93cf6dc..ad8db9e1fd1d0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -128,6 +128,7 @@ struct mlx5e_ipsec_hw_stats {
 	u64 ipsec_rx_bytes;
 	u64 ipsec_rx_drop_pkts;
 	u64 ipsec_rx_drop_bytes;
+	u64 ipsec_rx_drop_mismatch_sa_sel;
 	u64 ipsec_tx_pkts;
 	u64 ipsec_tx_bytes;
 	u64 ipsec_tx_drop_pkts;
@@ -184,6 +185,7 @@ struct mlx5e_ipsec_ft {
 	struct mutex mutex; /* Protect changes to this struct */
 	struct mlx5_flow_table *pol;
 	struct mlx5_flow_table *sa;
+	struct mlx5_flow_table *sa_sel;
 	struct mlx5_flow_table *status;
 	u32 refcnt;
 };
@@ -195,6 +197,8 @@ struct mlx5e_ipsec_drop {
 
 struct mlx5e_ipsec_rule {
 	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_handle *status_pass;
+	struct mlx5_flow_handle *sa_sel;
 	struct mlx5_modify_hdr *modify_hdr;
 	struct mlx5_pkt_reformat *pkt_reformat;
 	struct mlx5_fc *fc;
@@ -206,6 +210,7 @@ struct mlx5e_ipsec_rule {
 struct mlx5e_ipsec_miss {
 	struct mlx5_flow_group *group;
 	struct mlx5_flow_handle *rule;
+	struct mlx5_fc *fc;
 };
 
 struct mlx5e_ipsec_tx_create_attr {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 840d9e0514d3e..d51ace739637b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -16,6 +16,8 @@
 #define MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_SIZE 16
 #define IPSEC_TUNNEL_DEFAULT_TTL 0x40
 
+#define MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS 16
+
 enum {
 	MLX5_IPSEC_ASO_OK,
 	MLX5_IPSEC_ASO_BAD_REPLY,
@@ -52,6 +54,7 @@ struct mlx5e_ipsec_rx {
 	struct mlx5e_ipsec_ft ft;
 	struct mlx5e_ipsec_miss pol;
 	struct mlx5e_ipsec_miss sa;
+	struct mlx5e_ipsec_miss sa_sel;
 	struct mlx5e_ipsec_status_checks status_checks;
 	struct mlx5e_ipsec_fc *fc;
 	struct mlx5_fs_chains *chains;
@@ -689,6 +692,16 @@ static void ipsec_rx_policy_destroy(struct mlx5e_ipsec_rx *rx)
 	}
 }
 
+static void ipsec_rx_sa_selector_destroy(struct mlx5_core_dev *mdev,
+					 struct mlx5e_ipsec_rx *rx)
+{
+	mlx5_del_flow_rules(rx->sa_sel.rule);
+	mlx5_fc_destroy(mdev, rx->sa_sel.fc);
+	rx->sa_sel.fc = NULL;
+	mlx5_destroy_flow_group(rx->sa_sel.group);
+	mlx5_destroy_flow_table(rx->ft.sa_sel);
+}
+
 static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		       struct mlx5e_ipsec_rx *rx, u32 family)
 {
@@ -704,6 +717,8 @@ static void rx_destroy(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	mlx5_ipsec_rx_status_destroy(ipsec, rx);
 	mlx5_destroy_flow_table(rx->ft.status);
 
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+
 	ipsec_rx_policy_destroy(rx);
 
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -892,6 +907,115 @@ static int ipsec_rx_policy_create(struct mlx5e_ipsec *ipsec,
 	return err;
 }
 
+static int ipsec_rx_sa_selector_create(struct mlx5e_ipsec *ipsec,
+				       struct mlx5e_ipsec_rx *rx,
+				       struct mlx5e_ipsec_rx_create_attr *attr)
+{
+	int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in);
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_destination dest;
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_table *ft;
+	struct mlx5_flow_group *fg;
+	u32 *flow_group_in;
+	struct mlx5_fc *fc;
+	int err;
+
+	flow_group_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!flow_group_in)
+		return -ENOMEM;
+
+	ft = ipsec_ft_create(attr->ns, attr->status_level, attr->prio, 1,
+			     MLX5_IPSEC_FS_SA_SELECTOR_MAX_NUM_GROUPS, 0);
+	if (IS_ERR(ft)) {
+		err = PTR_ERR(ft);
+		mlx5_core_err(mdev, "Failed to create RX SA selector flow table, err=%d\n",
+			      err);
+		goto err_ft;
+	}
+
+	MLX5_SET(create_flow_group_in, flow_group_in, start_flow_index,
+		 ft->max_fte - 1);
+	MLX5_SET(create_flow_group_in, flow_group_in, end_flow_index,
+		 ft->max_fte - 1);
+	fg = mlx5_create_flow_group(ft, flow_group_in);
+	if (IS_ERR(fg)) {
+		err = PTR_ERR(fg);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss group, err=%d\n",
+			      err);
+		goto err_fg;
+	}
+
+	fc = mlx5_fc_create(mdev, false);
+	if (IS_ERR(fc)) {
+		err = PTR_ERR(fc);
+		mlx5_core_err(mdev,
+			      "Failed to create ipsec RX SA selector miss rule counter, err=%d\n",
+			      err);
+		goto err_cnt;
+	}
+
+	dest.type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest.counter = fc;
+	flow_act.action =
+		MLX5_FLOW_CONTEXT_ACTION_COUNT | MLX5_FLOW_CONTEXT_ACTION_DROP;
+
+	rule = mlx5_add_flow_rules(ft, NULL, &flow_act, &dest, 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev, "Failed to create RX SA selector miss drop rule, err=%d\n",
+			      err);
+		goto err_rule;
+	}
+
+	rx->ft.sa_sel = ft;
+	rx->sa_sel.group = fg;
+	rx->sa_sel.fc = fc;
+	rx->sa_sel.rule = rule;
+
+	kvfree(flow_group_in);
+
+	return 0;
+
+err_rule:
+	mlx5_fc_destroy(mdev, fc);
+err_cnt:
+	mlx5_destroy_flow_group(fg);
+err_fg:
+	mlx5_destroy_flow_table(ft);
+err_ft:
+	kvfree(flow_group_in);
+	return err;
+}
+
+/* The decryption processing is as follows:
+ *
+ *   +----------+                         +-------------+
+ *   |          |                         |             |
+ *   |  Kernel  <--------------+----------+ policy miss <------------+
+ *   |          |              ^          |             |            ^
+ *   +----^-----+              |          +-------------+            |
+ *        |                  crypto                                  |
+ *      miss                offload ok                         allow/default
+ *        ^                    ^                                     ^
+ *        |                    |                  packet             |
+ *   +----+---------+     +----+-------------+   offload ok   +------+---+
+ *   |              |     |                  |   (no UPSPEC)  |          |
+ *   | SA (decrypt) +----->      status      +--->------->----+  policy  |
+ *   |              |     |                  |                |          |
+ *   +--------------+     ++---------+-------+                +-^----+---+
+ *                         |         |                          |    |
+ *                         v        packet             +-->->---+    v
+ *                         |       offload ok        match           |
+ *                       fails    (with UPSPEC)        |           block
+ *                         |         |   +-------------+-+           |
+ *                         v         v   |               |  miss     v
+ *                        drop       +--->    SA sel     +--------->drop
+ *                                       |               |
+ *                                       +---------------+
+ */
+
 static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 		     struct mlx5e_ipsec_rx *rx, u32 family)
 {
@@ -907,13 +1031,17 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (err)
 		return err;
 
-	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 3, 0);
+	ft = ipsec_ft_create(attr.ns, attr.status_level, attr.prio, 3, 4, 0);
 	if (IS_ERR(ft)) {
 		err = PTR_ERR(ft);
 		goto err_fs_ft_status;
 	}
 	rx->ft.status = ft;
 
+	err = ipsec_rx_sa_selector_create(ipsec, rx, &attr);
+	if (err)
+		goto err_fs_ft_sa_sel;
+
 	/* Create FT */
 	if (mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_TUNNEL)
 		rx->allow_tunnel_mode = mlx5_eswitch_block_encap(mdev);
@@ -956,6 +1084,8 @@ static int rx_create(struct mlx5_core_dev *mdev, struct mlx5e_ipsec *ipsec,
 	if (rx->allow_tunnel_mode)
 		mlx5_eswitch_unblock_encap(mdev);
 err_fs_ft:
+	ipsec_rx_sa_selector_destroy(mdev, rx);
+err_fs_ft_sa_sel:
 	mlx5_destroy_flow_table(rx->ft.status);
 err_fs_ft_status:
 	mlx5_ipsec_fs_roce_rx_destroy(ipsec->roce, family, mdev);
@@ -1781,6 +1911,85 @@ static int setup_pkt_reformat(struct mlx5e_ipsec *ipsec,
 	return 0;
 }
 
+static int rx_add_rule_sa_selector(struct mlx5e_ipsec_sa_entry *sa_entry,
+				   struct mlx5e_ipsec_rx *rx,
+				   struct upspec *upspec)
+{
+	struct mlx5e_ipsec *ipsec = sa_entry->ipsec;
+	struct mlx5_core_dev *mdev = ipsec->mdev;
+	struct mlx5_flow_destination dest[2];
+	struct mlx5_flow_act flow_act = {};
+	struct mlx5_flow_handle *rule;
+	struct mlx5_flow_spec *spec;
+	int err = 0;
+
+	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
+	if (!spec)
+		return -ENOMEM;
+
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.ipsec_syndrome);
+	MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
+			 misc_parameters_2.metadata_reg_c_4);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_value,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+	spec->match_criteria_enable = MLX5_MATCH_MISC_PARAMETERS_2;
+
+	ipsec_rx_rule_add_match_obj(sa_entry, rx, spec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST |
+			  MLX5_FLOW_CONTEXT_ACTION_COUNT;
+	flow_act.flags = FLOW_ACT_IGNORE_FLOW_LEVEL;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.sa_sel;
+	dest[1].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER;
+	dest[1].counter = rx->fc->cnt;
+
+	rule = mlx5_add_flow_rules(rx->ft.status, spec, &flow_act, dest, 2);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx pass rule, err=%d\n",
+			      err);
+		goto err_add_status_pass_rule;
+	}
+
+	sa_entry->ipsec_rule.status_pass = rule;
+
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.ipsec_syndrome, 0);
+	MLX5_SET(fte_match_param, spec->match_criteria,
+		 misc_parameters_2.metadata_reg_c_4, 0);
+
+	setup_fte_upper_proto_match(spec, upspec);
+
+	flow_act.action = MLX5_FLOW_CONTEXT_ACTION_FWD_DEST;
+	dest[0].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE;
+	dest[0].ft = rx->ft.pol;
+
+	rule = mlx5_add_flow_rules(rx->ft.sa_sel, spec, &flow_act, &dest[0], 1);
+	if (IS_ERR(rule)) {
+		err = PTR_ERR(rule);
+		mlx5_core_err(mdev,
+			      "Failed to add ipsec rx sa selector rule, err=%d\n",
+			      err);
+		goto err_add_sa_sel_rule;
+	}
+
+	sa_entry->ipsec_rule.sa_sel = rule;
+
+	kvfree(spec);
+	return 0;
+
+err_add_sa_sel_rule:
+	mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+err_add_status_pass_rule:
+	kvfree(spec);
+	return err;
+}
+
 static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 {
 	struct mlx5_accel_esp_xfrm_attrs *attrs = &sa_entry->attrs;
@@ -1813,7 +2022,6 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	if (!attrs->encap)
 		setup_fte_esp(spec);
 	setup_fte_no_frags(spec);
-	setup_fte_upper_proto_match(spec, &attrs->upspec);
 
 	if (!attrs->drop) {
 		if (rx != ipsec->rx_esw)
@@ -1861,6 +2069,13 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_core_err(mdev, "fail to add RX ipsec rule err=%d\n", err);
 		goto err_add_flow;
 	}
+
+	if (attrs->upspec.proto && attrs->type == XFRM_DEV_OFFLOAD_PACKET) {
+		err = rx_add_rule_sa_selector(sa_entry, rx, &attrs->upspec);
+		if (err)
+			goto err_add_sa_sel;
+	}
+
 	if (attrs->type == XFRM_DEV_OFFLOAD_PACKET)
 		err = rx_add_rule_drop_replay(sa_entry, rx);
 	if (err)
@@ -1884,6 +2099,11 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_fc_destroy(mdev, sa_entry->ipsec_rule.replay.fc);
 	}
 err_add_replay:
+	if (sa_entry->ipsec_rule.sa_sel) {
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.sa_sel);
+		mlx5_del_flow_rules(sa_entry->ipsec_rule.status_pass);
+	}
+err_add_sa_sel:
 	mlx5_del_flow_rules(rule);
 err_add_flow:
 	mlx5_fc_destroy(mdev, counter);
@@ -2265,6 +2485,7 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	stats->ipsec_rx_bytes = 0;
 	stats->ipsec_rx_drop_pkts = 0;
 	stats->ipsec_rx_drop_bytes = 0;
+	stats->ipsec_rx_drop_mismatch_sa_sel = 0;
 	stats->ipsec_tx_pkts = 0;
 	stats->ipsec_tx_bytes = 0;
 	stats->ipsec_tx_drop_pkts = 0;
@@ -2274,6 +2495,9 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_rx_pkts, &stats->ipsec_rx_bytes);
 	mlx5_fc_query(mdev, fc->drop, &stats->ipsec_rx_drop_pkts,
 		      &stats->ipsec_rx_drop_bytes);
+	if (ipsec->rx_ipv4->sa_sel.fc)
+		mlx5_fc_query(mdev, ipsec->rx_ipv4->sa_sel.fc,
+			      &stats->ipsec_rx_drop_mismatch_sa_sel, &bytes);
 
 	fc = ipsec->tx->fc;
 	mlx5_fc_query(mdev, fc->cnt, &stats->ipsec_tx_pkts, &stats->ipsec_tx_bytes);
@@ -2302,6 +2526,11 @@ void mlx5e_accel_ipsec_fs_read_stats(struct mlx5e_priv *priv, void *ipsec_stats)
 			stats->ipsec_tx_drop_pkts += packets;
 			stats->ipsec_tx_drop_bytes += bytes;
 		}
+
+		if (ipsec->rx_esw->sa_sel.fc &&
+		    !mlx5_fc_query(mdev, ipsec->rx_esw->sa_sel.fc,
+				   &packets, &bytes))
+			stats->ipsec_rx_drop_mismatch_sa_sel += packets;
 	}
 }
 
@@ -2399,6 +2628,11 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	mlx5_del_flow_rules(ipsec_rule->auth.rule);
 	mlx5_fc_destroy(mdev, ipsec_rule->auth.fc);
 
+	if (ipsec_rule->sa_sel) {
+		mlx5_del_flow_rules(ipsec_rule->sa_sel);
+		mlx5_del_flow_rules(ipsec_rule->status_pass);
+	}
+
 	if (ipsec_rule->replay.rule) {
 		mlx5_del_flow_rules(ipsec_rule->replay.rule);
 		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
index 92bf3fa44a3b1..93be388068f89 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_stats.c
@@ -42,6 +42,7 @@ static const struct counter_desc mlx5e_ipsec_hw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_bytes) },
+	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_rx_drop_mismatch_sa_sel) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_pkts) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_bytes) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_ipsec_hw_stats, ipsec_tx_drop_pkts) },

From 8f3f4464ff08f70e959c026fad2f3790abe84be6 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Fri, 21 Feb 2025 09:53:22 +0100
Subject: [PATCH 1075/2753] net/mlx5: Use secs_to_jiffies() instead of
 msecs_to_jiffies()

Use secs_to_jiffies() and simplify the code.

Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://patch.msgid.link/20250221085350.198024-3-thorsten.blum@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
index 3dbd4efa21a2a..19dce1ba512d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.c
@@ -220,7 +220,7 @@ static int hws_bwc_queue_poll(struct mlx5hws_context *ctx,
 			      bool drain)
 {
 	unsigned long timeout = jiffies +
-				msecs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT * MSEC_PER_SEC);
+				secs_to_jiffies(MLX5HWS_BWC_POLLING_TIMEOUT);
 	struct mlx5hws_flow_op_result comp[MLX5HWS_BWC_MATCHER_REHASH_BURST_TH];
 	u16 burst_th = hws_bwc_get_burst_th(ctx, queue_id);
 	bool got_comp = *pending_rules >= burst_th;

From bc337e8c0e762b0c1eaca00aa6955cd0e7013ba1 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 21 Feb 2025 16:43:54 +0100
Subject: [PATCH 1076/2753] mptcp: pm: remove unused ret value to set flags

The returned value is not used, it can then be dropped.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-1-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 99705a9c2238c..ff1e5695dc1db 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1922,13 +1922,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-static int mptcp_nl_set_flags(struct net *net,
-			      struct mptcp_addr_info *addr,
-			      u8 bkup, u8 changed)
+static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
+			       u8 bkup, u8 changed)
 {
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
-	int ret = -EINVAL;
 
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
@@ -1938,7 +1936,7 @@ static int mptcp_nl_set_flags(struct net *net,
 
 		lock_sock(sk);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
+			mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
 		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
 			mptcp_pm_nl_fullmesh(msk, addr);
 		release_sock(sk);
@@ -1948,7 +1946,7 @@ static int mptcp_nl_set_flags(struct net *net,
 		cond_resched();
 	}
 
-	return ret;
+	return;
 }
 
 int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,

From 145dc6cc4abdb3b76eb01a0943a540db2a01ebe6 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 21 Feb 2025 16:43:55 +0100
Subject: [PATCH 1077/2753] mptcp: pm: change to fullmesh only for 'subflow'

If an endpoint doesn't have the 'subflow' flag -- in fact, has no type,
so not 'subflow', 'signal', nor 'implicit' -- there are then no subflows
created from this local endpoint to at least the initial destination
address. In this case, no need to call mptcp_pm_nl_fullmesh() which is
there to recreate the subflows to reflect the new value of the fullmesh
attribute.

Similarly, there is then no need to iterate over all connections to do
nothing, if only the 'fullmesh' flag has been changed, and the endpoint
doesn't have the 'subflow' one. So stop early when dealing with this
specific case.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-2-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index ff1e5695dc1db..1a0695e087af0 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1923,11 +1923,16 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 }
 
 static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
-			       u8 bkup, u8 changed)
+			       u8 flags, u8 changed)
 {
+	u8 is_subflow = !!(flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
+	u8 bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
 
+	if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow)
+		return;
+
 	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
 		struct sock *sk = (struct sock *)msk;
 
@@ -1937,7 +1942,8 @@ static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
 		lock_sock(sk);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
 			mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
-		if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)
+		/* Subflows will only be recreated if the SUBFLOW flag is set */
+		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
 			mptcp_pm_nl_fullmesh(msk, addr);
 		release_sock(sk);
 
@@ -1959,7 +1965,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
 	u8 lookup_by_id = 0;
-	u8 bkup = 0;
 
 	pernet = pm_nl_get_pernet(net);
 
@@ -1972,9 +1977,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 		}
 	}
 
-	if (local->flags & MPTCP_PM_ADDR_FLAG_BACKUP)
-		bkup = 1;
-
 	spin_lock_bh(&pernet->lock);
 	entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) :
 			       __lookup_addr(pernet, &local->addr);
@@ -1996,7 +1998,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, &local->addr, bkup, changed);
+	mptcp_nl_set_flags(net, &local->addr, entry->flags, changed);
 	return 0;
 }
 

From 63132fb054744e58de61d45a6d4f2a707cdfcfb3 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:43:56 +0100
Subject: [PATCH 1078/2753] mptcp: pm: add a build check for
 userspace_pm_dump_addr

This patch adds a build check for mptcp_userspace_pm_dump_addr() to make
sure there is enough space in 'cb->ctx' to store an address id bitmap.

Just in case info stored in 'cb->ctx' are increased later.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-3-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_userspace.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 277cf092a8704..b69fb5b18130c 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -643,6 +643,8 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	struct sock *sk;
 	void *hdr;
 
+	BUILD_BUG_ON(sizeof(struct id_bitmap) > sizeof(cb->ctx));
+
 	bitmap = (struct id_bitmap *)cb->ctx;
 
 	msk = mptcp_userspace_pm_get_sock(info);

From f8fe8174657329609a80f66da1d3dd80a80de76b Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:43:57 +0100
Subject: [PATCH 1079/2753] mptcp: pm: add mptcp_pm_genl_fill_addr helper

To save some redundant code in dump_addr() interfaces of both the
netlink PM and userspace PM, the code that calls netlink message
helpers (genlmsg_put/cancel/end) and mptcp_nl_fill_addr() is wrapped
into a new helper mptcp_pm_genl_fill_addr().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-4-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c           | 21 +++++++++++++++++++++
 net/mptcp/pm_netlink.c   | 12 +-----------
 net/mptcp/pm_userspace.c | 12 +-----------
 net/mptcp/protocol.h     |  3 +++
 4 files changed, 26 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index b1f36dc1a0911..16cacce6c10fe 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -489,6 +489,27 @@ int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
+int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
+			    struct netlink_callback *cb,
+			    struct mptcp_pm_addr_entry *entry)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &mptcp_genl_family,
+			  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
+	if (!hdr)
+		return -EINVAL;
+
+	if (mptcp_nl_fill_addr(msg, entry) < 0) {
+		genlmsg_cancel(msg, hdr);
+		return -EINVAL;
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+}
+
 static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
 {
 	const struct genl_info *info = genl_info_dump(cb);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 1a0695e087af0..98fcbf8b14656 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1798,7 +1798,6 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
 	int id = cb->args[0];
-	void *hdr;
 	int i;
 
 	pernet = pm_nl_get_pernet(net);
@@ -1813,19 +1812,10 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
 			if (entry->addr.id <= id)
 				continue;
 
-			hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
-					  cb->nlh->nlmsg_seq, &mptcp_genl_family,
-					  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
-			if (!hdr)
+			if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
 				break;
 
-			if (mptcp_nl_fill_addr(msg, entry) < 0) {
-				genlmsg_cancel(msg, hdr);
-				break;
-			}
-
 			id = entry->addr.id;
-			genlmsg_end(msg, hdr);
 		}
 	}
 	rcu_read_unlock();
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b69fb5b18130c..bedd6f9ebc8b0 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -641,7 +641,6 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 	struct mptcp_sock *msk;
 	int ret = -EINVAL;
 	struct sock *sk;
-	void *hdr;
 
 	BUILD_BUG_ON(sizeof(struct id_bitmap) > sizeof(cb->ctx));
 
@@ -659,19 +658,10 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg,
 		if (test_bit(entry->addr.id, bitmap->map))
 			continue;
 
-		hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
-				  cb->nlh->nlmsg_seq, &mptcp_genl_family,
-				  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
-		if (!hdr)
+		if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
 			break;
 
-		if (mptcp_nl_fill_addr(msg, entry) < 0) {
-			genlmsg_cancel(msg, hdr);
-			break;
-		}
-
 		__set_bit(entry->addr.id, bitmap->map);
-		genlmsg_end(msg, hdr);
 	}
 	spin_unlock_bh(&msk->pm.lock);
 	release_sock(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ca65f8bff632f..256677c43ca65 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1057,6 +1057,9 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 					      struct request_sock *req);
 int mptcp_nl_fill_addr(struct sk_buff *skb,
 		       struct mptcp_pm_addr_entry *entry);
+int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
+			    struct netlink_callback *cb,
+			    struct mptcp_pm_addr_entry *entry);
 
 static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk)
 {

From 640e3d69d0bc70d7d3de34800a1640793262bd08 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:43:58 +0100
Subject: [PATCH 1080/2753] mptcp: pm: drop match in
 userspace_pm_append_new_local_addr

The variable 'match' in mptcp_userspace_pm_append_new_local_addr() is a
redundant one, and this patch drops it.

No need to define 'match' as 'struct mptcp_pm_addr_entry *' type. In this
function, it's only used to check whether it's NULL. It can be defined as
a Boolean one.

Also other variables 'addr_match' and 'id_match' make 'match' a redundant
one, which can be replaced by directly checking 'addr_match && id_match'.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-5-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_userspace.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index bedd6f9ebc8b0..a16e2fb45a6c6 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -48,7 +48,6 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 						    bool needs_id)
 {
 	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	struct mptcp_pm_addr_entry *match = NULL;
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *e;
 	bool addr_match = false;
@@ -63,16 +62,12 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		if (addr_match && entry->addr.id == 0 && needs_id)
 			entry->addr.id = e->addr.id;
 		id_match = (e->addr.id == entry->addr.id);
-		if (addr_match && id_match) {
-			match = e;
+		if (addr_match || id_match)
 			break;
-		} else if (addr_match || id_match) {
-			break;
-		}
 		__set_bit(e->addr.id, id_bitmap);
 	}
 
-	if (!match && !addr_match && !id_match) {
+	if (!addr_match && !id_match) {
 		/* Memory for the entry is allocated from the
 		 * sock option buffer.
 		 */
@@ -90,7 +85,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list);
 		msk->pm.local_addr_used++;
 		ret = e->addr.id;
-	} else if (match) {
+	} else if (addr_match && id_match) {
 		ret = entry->addr.id;
 	}
 

From dc41695200a1f5db720f7988952a74833542831d Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:43:59 +0100
Subject: [PATCH 1081/2753] mptcp: pm: drop inet6_sk after inet_sk

In mptcp_event_add_subflow(), mptcp_event_pm_listener() and
mptcp_nl_find_ssk(), 'issk' has already been got through inet_sk().

No need to use inet6_sk() to get 'ipv6_pinfo' again, just use
issk->pinet6 instead. This patch also drops these 'ipv6_pinfo'
variables.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-6-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c   | 8 ++------
 net/mptcp/pm_userspace.c | 4 +---
 2 files changed, 3 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 98fcbf8b14656..f67b637c1fcf7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -2022,9 +2022,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk)
 		break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	case AF_INET6: {
-		const struct ipv6_pinfo *np = inet6_sk(ssk);
-
-		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr))
+		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr))
 			return -EMSGSIZE;
 		if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr))
 			return -EMSGSIZE;
@@ -2251,9 +2249,7 @@ void mptcp_event_pm_listener(const struct sock *ssk,
 		break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 	case AF_INET6: {
-		const struct ipv6_pinfo *np = inet6_sk(ssk);
-
-		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr))
+		if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr))
 			goto nla_put_failure;
 		break;
 	}
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index a16e2fb45a6c6..6bf6a20ef7f3e 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -460,9 +460,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk,
 			break;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 		case AF_INET6: {
-			const struct ipv6_pinfo *pinfo = inet6_sk(ssk);
-
-			if (!ipv6_addr_equal(&local->addr6, &pinfo->saddr) ||
+			if (!ipv6_addr_equal(&local->addr6, &issk->pinet6->saddr) ||
 			    !ipv6_addr_equal(&remote->addr6, &ssk->sk_v6_daddr))
 				continue;
 			break;

From 7720790fd56b91259efe500a702ad4c0fd29b260 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:44:00 +0100
Subject: [PATCH 1082/2753] mptcp: pm: use ipv6_addr_equal in addresses_equal

Use ipv6_addr_equal() to check whether two IPv6 addresses are equal in
mptcp_addresses_equal().

This is more appropriate than using !ipv6_addr_cmp().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-7-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f67b637c1fcf7..ef85a60151ad7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -64,7 +64,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			addr_equals = a->addr.s_addr == b->addr.s_addr;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
 		else
-			addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6);
+			addr_equals = ipv6_addr_equal(&a->addr6, &b->addr6);
 	} else if (a->family == AF_INET) {
 		if (ipv6_addr_v4mapped(&b->addr6))
 			addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];

From 9771a96a7a35daa2220cc4f170b840b34af28b2c Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 21 Feb 2025 16:44:01 +0100
Subject: [PATCH 1083/2753] mptcp: sched: split get_subflow interface into two

get_retrans() interface of the burst packet scheduler invokes a sleeping
function mptcp_pm_subflow_chk_stale(), which calls __lock_sock_fast().
So get_retrans() interface should be set with BPF_F_SLEEPABLE flag in
BPF. But get_send() interface of this scheduler can't be set with
BPF_F_SLEEPABLE flag since it's invoked in ack_update_msk() under mptcp
data lock.

So this patch has to split get_subflow() interface of packet scheduer into
two interfaces: get_send() and get_retrans(). Then we can set get_retrans()
interface alone with BPF_F_SLEEPABLE flag.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-8-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/mptcp.h |  5 +++--
 net/mptcp/sched.c   | 35 ++++++++++++++++++++++++-----------
 2 files changed, 27 insertions(+), 13 deletions(-)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 814b5f2e3ed5e..2c85ca92bb1c3 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -103,13 +103,14 @@ struct mptcp_out_options {
 #define MPTCP_SUBFLOWS_MAX	8
 
 struct mptcp_sched_data {
-	bool	reinject;
 	u8	subflows;
 	struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX];
 };
 
 struct mptcp_sched_ops {
-	int (*get_subflow)(struct mptcp_sock *msk,
+	int (*get_send)(struct mptcp_sock *msk,
+			struct mptcp_sched_data *data);
+	int (*get_retrans)(struct mptcp_sock *msk,
 			   struct mptcp_sched_data *data);
 
 	char			name[MPTCP_SCHED_NAME_MAX];
diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index df7dbcfa3b713..94dc4b3ad82f6 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -16,13 +16,25 @@
 static DEFINE_SPINLOCK(mptcp_sched_list_lock);
 static LIST_HEAD(mptcp_sched_list);
 
-static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk,
+static int mptcp_sched_default_get_send(struct mptcp_sock *msk,
+					struct mptcp_sched_data *data)
+{
+	struct sock *ssk;
+
+	ssk = mptcp_subflow_get_send(msk);
+	if (!ssk)
+		return -EINVAL;
+
+	mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true);
+	return 0;
+}
+
+static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk,
 					   struct mptcp_sched_data *data)
 {
 	struct sock *ssk;
 
-	ssk = data->reinject ? mptcp_subflow_get_retrans(msk) :
-			       mptcp_subflow_get_send(msk);
+	ssk = mptcp_subflow_get_retrans(msk);
 	if (!ssk)
 		return -EINVAL;
 
@@ -31,7 +43,8 @@ static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk,
 }
 
 static struct mptcp_sched_ops mptcp_sched_default = {
-	.get_subflow	= mptcp_sched_default_get_subflow,
+	.get_send	= mptcp_sched_default_get_send,
+	.get_retrans	= mptcp_sched_default_get_retrans,
 	.name		= "default",
 	.owner		= THIS_MODULE,
 };
@@ -73,7 +86,7 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen)
 
 int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
 {
-	if (!sched->get_subflow)
+	if (!sched->get_send)
 		return -EINVAL;
 
 	spin_lock(&mptcp_sched_list_lock);
@@ -164,10 +177,9 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	data.reinject = false;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_subflow(msk, &data);
-	return msk->sched->get_subflow(msk, &data);
+		return mptcp_sched_default_get_send(msk, &data);
+	return msk->sched->get_send(msk, &data);
 }
 
 int mptcp_sched_get_retrans(struct mptcp_sock *msk)
@@ -186,8 +198,9 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 			return 0;
 	}
 
-	data.reinject = true;
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_subflow(msk, &data);
-	return msk->sched->get_subflow(msk, &data);
+		return mptcp_sched_default_get_retrans(msk, &data);
+	if (msk->sched->get_retrans)
+		return msk->sched->get_retrans(msk, &data);
+	return msk->sched->get_send(msk, &data);
 }

From b68b106b0f15424db6c78d8c1a0616f698080b9d Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 21 Feb 2025 16:44:02 +0100
Subject: [PATCH 1084/2753] mptcp: sched: reduce size for unused data

Thanks for the previous commit ("mptcp: sched: split get_subflow
interface into two"), the mptcp_sched_data structure is now currently
unused.

This structure has been added to allow future extensions that are not
ready yet. At the end, this structure will not even be used at all when
mptcp_subflow bpf_iter will be supported [1].

Here is a first step to save 64 bytes on the stack for each scheduling
operation. The structure is not removed yet not to break the WIP work on
these extensions, but will be done when [1] will be ready and applied.

Link: https://lore.kernel.org/6645ad6e-8874-44c5-8730-854c30673218@linux.dev [1]
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-9-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/sched.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
index 94dc4b3ad82f6..c16c6fbd4ba2f 100644
--- a/net/mptcp/sched.c
+++ b/net/mptcp/sched.c
@@ -157,7 +157,7 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow,
 int mptcp_sched_get_send(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data data;
+	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -178,14 +178,14 @@ int mptcp_sched_get_send(struct mptcp_sock *msk)
 	}
 
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_send(msk, &data);
-	return msk->sched->get_send(msk, &data);
+		return mptcp_sched_default_get_send(msk, data);
+	return msk->sched->get_send(msk, data);
 }
 
 int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow;
-	struct mptcp_sched_data data;
+	struct mptcp_sched_data *data = NULL;
 
 	msk_owned_by_me(msk);
 
@@ -199,8 +199,8 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk)
 	}
 
 	if (msk->sched == &mptcp_sched_default || !msk->sched)
-		return mptcp_sched_default_get_retrans(msk, &data);
+		return mptcp_sched_default_get_retrans(msk, data);
 	if (msk->sched->get_retrans)
-		return msk->sched->get_retrans(msk, &data);
-	return msk->sched->get_send(msk, &data);
+		return msk->sched->get_retrans(msk, data);
+	return msk->sched->get_send(msk, data);
 }

From 8275ac799ee15e972841eb77b694d63f5e888519 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 21 Feb 2025 16:44:03 +0100
Subject: [PATCH 1085/2753] mptcp: blackhole: avoid checking the state twice

A small cleanup, reordering the conditions to avoid checking things
twice.

The code here is called in case of timeout on a TCP connection, before
triggering a retransmission. But it only acts on SYN + MPC packets.

So the conditions can be re-order to exit early in case of non-MPTCP
SYN + MPC. This also reduce the indentation levels.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-10-2b70ab1cee79@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/ctrl.c | 30 +++++++++++++++++-------------
 1 file changed, 17 insertions(+), 13 deletions(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 2dd81e6c26bdb..be6c0237e10bf 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -401,26 +401,30 @@ void mptcp_active_enable(struct sock *sk)
 void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 {
 	struct mptcp_subflow_context *subflow;
+	u8 timeouts, to_max;
+	struct net *net;
 
-	if (!sk_is_mptcp(ssk))
+	/* Only check MPTCP SYN ... */
+	if (likely(!sk_is_mptcp(ssk) || ssk->sk_state != TCP_SYN_SENT))
 		return;
 
 	subflow = mptcp_subflow_ctx(ssk);
 
-	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) {
-		struct net *net = sock_net(ssk);
-		u8 timeouts, to_max;
+	/* ... + MP_CAPABLE */
+	if (!subflow->request_mptcp) {
+		/* Mark as blackhole iif the 1st non-MPTCP SYN is accepted */
+		subflow->mpc_drop = 0;
+		return;
+	}
 
-		timeouts = inet_csk(ssk)->icsk_retransmits;
-		to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
+	net = sock_net(ssk);
+	timeouts = inet_csk(ssk)->icsk_retransmits;
+	to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
 
-		if (timeouts == to_max || (timeouts < to_max && expired)) {
-			MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
-			subflow->mpc_drop = 1;
-			mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
-		}
-	} else if (ssk->sk_state == TCP_SYN_SENT) {
-		subflow->mpc_drop = 0;
+	if (timeouts == to_max || (timeouts < to_max && expired)) {
+		MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
+		subflow->mpc_drop = 1;
+		mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
 	}
 }
 

From a3e51d4711793be001220784bd7d8ce81517003e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 22 Feb 2025 09:36:10 +0100
Subject: [PATCH 1086/2753] net: phy: add phylib-internal.h

This patch is a starting point for moving phylib-internal
declarations to a private header file.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/082eacd2-a888-4716-8797-b3491ce02820@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c          |  1 +
 drivers/net/phy/phy-core.c         |  3 ++-
 drivers/net/phy/phy.c              |  2 ++
 drivers/net/phy/phy_device.c       |  2 ++
 drivers/net/phy/phy_led_triggers.c |  2 ++
 drivers/net/phy/phylib-internal.h  | 25 +++++++++++++++++++++++++
 include/linux/phy.h                | 13 -------------
 7 files changed, 34 insertions(+), 14 deletions(-)
 create mode 100644 drivers/net/phy/phylib-internal.h

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 37c9a344bf4a3..0bcbdce381071 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -9,6 +9,7 @@
 #include <linux/phy.h>
 
 #include "mdio-open-alliance.h"
+#include "phylib-internal.h"
 
 /**
  * genphy_c45_baset1_able - checks if the PMA has BASE-T1 extended abilities
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 2fd1d153abc99..b1c1670de23b0 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -6,6 +6,8 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
+#include "phylib-internal.h"
+
 /**
  * phy_speed_to_str - Return a string representing the PHY link speed
  *
@@ -544,7 +546,6 @@ void phy_check_downshift(struct phy_device *phydev)
 
 	phydev->downshifted_rate = 1;
 }
-EXPORT_SYMBOL_GPL(phy_check_downshift);
 
 static int phy_resolve_min_speed(struct phy_device *phydev, bool fdx_only)
 {
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 831b368396277..16ffc00b419ca 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -36,6 +36,8 @@
 #include <net/genetlink.h>
 #include <net/sock.h>
 
+#include "phylib-internal.h"
+
 #define PHY_STATE_TIME	HZ
 
 #define PHY_STATE_STR(_state)			\
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 7c4e1ad1864c7..a38d399f244bb 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -41,6 +41,8 @@
 #include <linux/uaccess.h>
 #include <linux/unistd.h>
 
+#include "phylib-internal.h"
+
 MODULE_DESCRIPTION("PHY library");
 MODULE_AUTHOR("Andy Fleming");
 MODULE_LICENSE("GPL");
diff --git a/drivers/net/phy/phy_led_triggers.c b/drivers/net/phy/phy_led_triggers.c
index f550576eb9dae..bd3c9554f6acb 100644
--- a/drivers/net/phy/phy_led_triggers.c
+++ b/drivers/net/phy/phy_led_triggers.c
@@ -5,6 +5,8 @@
 #include <linux/phy_led_triggers.h>
 #include <linux/netdevice.h>
 
+#include "phylib-internal.h"
+
 static struct phy_led_trigger *phy_speed_to_led_trigger(struct phy_device *phy,
 							unsigned int speed)
 {
diff --git a/drivers/net/phy/phylib-internal.h b/drivers/net/phy/phylib-internal.h
new file mode 100644
index 0000000000000..dc9592c6bb8e7
--- /dev/null
+++ b/drivers/net/phy/phylib-internal.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * phylib-internal header
+ */
+
+#ifndef __PHYLIB_INTERNAL_H
+#define __PHYLIB_INTERNAL_H
+
+struct phy_device;
+
+/*
+ * phy_supported_speeds - return all speeds currently supported by a PHY device
+ */
+unsigned int phy_supported_speeds(struct phy_device *phy,
+				  unsigned int *speeds,
+				  unsigned int size);
+void of_set_phy_supported(struct phy_device *phydev);
+void of_set_phy_eee_broken(struct phy_device *phydev);
+void of_set_phy_timing_role(struct phy_device *phydev);
+int phy_speed_down_core(struct phy_device *phydev);
+void phy_check_downshift(struct phy_device *phydev);
+
+int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv);
+
+#endif /* __PHYLIB_INTERNAL_H */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 13be48d3b8b31..7bfbae51070a8 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -181,13 +181,6 @@ static inline void phy_interface_set_rgmii(unsigned long *intf)
 	__set_bit(PHY_INTERFACE_MODE_RGMII_TXID, intf);
 }
 
-/*
- * phy_supported_speeds - return all speeds currently supported by a PHY device
- */
-unsigned int phy_supported_speeds(struct phy_device *phy,
-				      unsigned int *speeds,
-				      unsigned int size);
-
 /**
  * phy_modes - map phy_interface_t enum to device tree binding of phy-mode
  * @interface: enum phy_interface_t value
@@ -1331,10 +1324,6 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
 		   bool exact);
 size_t phy_speeds(unsigned int *speeds, size_t size,
 		  unsigned long *mask);
-void of_set_phy_supported(struct phy_device *phydev);
-void of_set_phy_eee_broken(struct phy_device *phydev);
-void of_set_phy_timing_role(struct phy_device *phydev);
-int phy_speed_down_core(struct phy_device *phydev);
 
 /**
  * phy_is_started - Convenience function to check whether PHY is started
@@ -1360,7 +1349,6 @@ static inline void phy_disable_eee_mode(struct phy_device *phydev, u32 link_mode
 
 void phy_resolve_aneg_pause(struct phy_device *phydev);
 void phy_resolve_aneg_linkmode(struct phy_device *phydev);
-void phy_check_downshift(struct phy_device *phydev);
 
 /**
  * phy_read - Convenience function for reading a given PHY register
@@ -2035,7 +2023,6 @@ int genphy_c45_ethtool_get_eee(struct phy_device *phydev,
 int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 			       struct ethtool_keee *data);
 int genphy_c45_an_config_eee_aneg(struct phy_device *phydev);
-int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv);
 
 /* Generic C45 PHY driver */
 extern struct phy_driver genphy_c45_driver;

From 5bab1ae5a375ccde25ac9a142ea933a5d3bdf38d Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 3 Jan 2025 10:21:35 +0100
Subject: [PATCH 1087/2753] Input: goodix-berlin - fix comment referencing
 wrong regulator

In the statement above AVDD gets enabled, and not IOVDD, so fix this
copy-paste mistake.

Fixes: 44362279bdd4 ("Input: add core support for Goodix Berlin Touchscreen IC")
Reported-by: Jens Reidel <adrian@travitia.xyz>
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250103-goodix-berlin-fixes-v1-1-b014737b08b2@fairphone.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/touchscreen/goodix_berlin_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/input/touchscreen/goodix_berlin_core.c b/drivers/input/touchscreen/goodix_berlin_core.c
index 3fc03cf0ca23f..e273fb8edc6b9 100644
--- a/drivers/input/touchscreen/goodix_berlin_core.c
+++ b/drivers/input/touchscreen/goodix_berlin_core.c
@@ -263,7 +263,7 @@ static int goodix_berlin_power_on(struct goodix_berlin_core *cd)
 		goto err_iovdd_disable;
 	}
 
-	/* Vendor waits 15ms for IOVDD to settle */
+	/* Vendor waits 15ms for AVDD to settle */
 	usleep_range(15000, 15100);
 
 	gpiod_set_value_cansleep(cd->reset_gpio, 0);

From 3b0011059334a1cf554c2c1f67d7a7b822d8238a Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Fri, 3 Jan 2025 10:21:36 +0100
Subject: [PATCH 1088/2753] Input: goodix-berlin - fix vddio regulator
 references

As per dt-bindings the property is called vddio-supply, so use the
correct name in the driver instead of iovdd. The datasheet also calls
the supply 'VDDIO'.

Fixes: 44362279bdd4 ("Input: add core support for Goodix Berlin Touchscreen IC")
Cc: stable@vger.kernel.org
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250103-goodix-berlin-fixes-v1-2-b014737b08b2@fairphone.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 .../input/touchscreen/goodix_berlin_core.c    | 24 +++++++++----------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/input/touchscreen/goodix_berlin_core.c b/drivers/input/touchscreen/goodix_berlin_core.c
index e273fb8edc6b9..7f8cfdd106fae 100644
--- a/drivers/input/touchscreen/goodix_berlin_core.c
+++ b/drivers/input/touchscreen/goodix_berlin_core.c
@@ -165,7 +165,7 @@ struct goodix_berlin_core {
 	struct device *dev;
 	struct regmap *regmap;
 	struct regulator *avdd;
-	struct regulator *iovdd;
+	struct regulator *vddio;
 	struct gpio_desc *reset_gpio;
 	struct touchscreen_properties props;
 	struct goodix_berlin_fw_version fw_version;
@@ -248,19 +248,19 @@ static int goodix_berlin_power_on(struct goodix_berlin_core *cd)
 {
 	int error;
 
-	error = regulator_enable(cd->iovdd);
+	error = regulator_enable(cd->vddio);
 	if (error) {
-		dev_err(cd->dev, "Failed to enable iovdd: %d\n", error);
+		dev_err(cd->dev, "Failed to enable vddio: %d\n", error);
 		return error;
 	}
 
-	/* Vendor waits 3ms for IOVDD to settle */
+	/* Vendor waits 3ms for VDDIO to settle */
 	usleep_range(3000, 3100);
 
 	error = regulator_enable(cd->avdd);
 	if (error) {
 		dev_err(cd->dev, "Failed to enable avdd: %d\n", error);
-		goto err_iovdd_disable;
+		goto err_vddio_disable;
 	}
 
 	/* Vendor waits 15ms for AVDD to settle */
@@ -283,8 +283,8 @@ static int goodix_berlin_power_on(struct goodix_berlin_core *cd)
 err_dev_reset:
 	gpiod_set_value_cansleep(cd->reset_gpio, 1);
 	regulator_disable(cd->avdd);
-err_iovdd_disable:
-	regulator_disable(cd->iovdd);
+err_vddio_disable:
+	regulator_disable(cd->vddio);
 	return error;
 }
 
@@ -292,7 +292,7 @@ static void goodix_berlin_power_off(struct goodix_berlin_core *cd)
 {
 	gpiod_set_value_cansleep(cd->reset_gpio, 1);
 	regulator_disable(cd->avdd);
-	regulator_disable(cd->iovdd);
+	regulator_disable(cd->vddio);
 }
 
 static int goodix_berlin_read_version(struct goodix_berlin_core *cd)
@@ -744,10 +744,10 @@ int goodix_berlin_probe(struct device *dev, int irq, const struct input_id *id,
 		return dev_err_probe(dev, PTR_ERR(cd->avdd),
 				     "Failed to request avdd regulator\n");
 
-	cd->iovdd = devm_regulator_get(dev, "iovdd");
-	if (IS_ERR(cd->iovdd))
-		return dev_err_probe(dev, PTR_ERR(cd->iovdd),
-				     "Failed to request iovdd regulator\n");
+	cd->vddio = devm_regulator_get(dev, "vddio");
+	if (IS_ERR(cd->vddio))
+		return dev_err_probe(dev, PTR_ERR(cd->vddio),
+				     "Failed to request vddio regulator\n");
 
 	error = goodix_berlin_power_on(cd);
 	if (error) {

From b5799106b44e1df594f4696500dbbc3b326bba18 Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Mon, 24 Feb 2025 15:45:38 +0000
Subject: [PATCH 1089/2753] iomap: Minor code simplification in
 iomap_dio_bio_iter()

Combine 'else' and 'if' conditional statements onto a single line and drop
unrequired braces, as is standard coding style.

The code had been like this since commit c3b0e880bbfa ("iomap: support
REQ_OP_ZONE_APPEND").

Signed-off-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/r/20250224154538.548028-1-john.g.garry@oracle.com
Reviewed-by: "Darrick J. Wong" <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/direct-io.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b521eb15759e8..0e47da82b0c24 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -427,12 +427,10 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 			bio_put(bio);
 			goto zero_tail;
 		}
-		if (dio->flags & IOMAP_DIO_WRITE) {
+		if (dio->flags & IOMAP_DIO_WRITE)
 			task_io_account_write(n);
-		} else {
-			if (dio->flags & IOMAP_DIO_DIRTY)
-				bio_set_pages_dirty(bio);
-		}
+		else if (dio->flags & IOMAP_DIO_DIRTY)
+			bio_set_pages_dirty(bio);
 
 		dio->size += n;
 		copied += n;

From 423de5b5bc5b267586b449abd1c4fde562aa0cf9 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 21 Feb 2025 17:57:11 +0100
Subject: [PATCH 1090/2753] thermal/of: Fix cdev lookup in
 thermal_of_should_bind()

Since thermal_of_should_bind() terminates the loop after processing
the first child found in cooling-maps, it will never match more than
one cdev to a given trip point which is incorrect, as there may be
cooling-maps associating one trip point with multiple cooling devices.

Address this by letting the loop continue until either all
children have been processed or a matching one has been found.

To avoid adding conditionals or goto statements, put the loop in
question into a separate function and make that function return
right away after finding a matching cooling-maps entry.

Fixes: 94c6110b0b13 ("thermal/of: Use the .should_bind() thermal zone callback")
Link: https://lore.kernel.org/linux-pm/20250219-fix-thermal-of-v1-1-de36e7a590c4@chromium.org/
Reported-by: Yu-Che Cheng <giver@chromium.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Yu-Che Cheng <giver@chromium.org>
Tested-by: Yu-Che Cheng <giver@chromium.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
Tested-by: Lukasz Luba <lukasz.luba@arm.com>
Link: https://patch.msgid.link/2788228.mvXUDI8C0e@rjwysocki.net
---
 drivers/thermal/thermal_of.c | 50 +++++++++++++++++++++---------------
 1 file changed, 29 insertions(+), 21 deletions(-)

diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
index 5ab4ce4daaebd..5401f03d6b6c1 100644
--- a/drivers/thermal/thermal_of.c
+++ b/drivers/thermal/thermal_of.c
@@ -274,6 +274,34 @@ static bool thermal_of_get_cooling_spec(struct device_node *map_np, int index,
 	return true;
 }
 
+static bool thermal_of_cm_lookup(struct device_node *cm_np,
+				 const struct thermal_trip *trip,
+				 struct thermal_cooling_device *cdev,
+				 struct cooling_spec *c)
+{
+	for_each_child_of_node_scoped(cm_np, child) {
+		struct device_node *tr_np;
+		int count, i;
+
+		tr_np = of_parse_phandle(child, "trip", 0);
+		if (tr_np != trip->priv)
+			continue;
+
+		/* The trip has been found, look up the cdev. */
+		count = of_count_phandle_with_args(child, "cooling-device",
+						   "#cooling-cells");
+		if (count <= 0)
+			pr_err("Add a cooling_device property with at least one device\n");
+
+		for (i = 0; i < count; i++) {
+			if (thermal_of_get_cooling_spec(child, i, cdev, c))
+				return true;
+		}
+	}
+
+	return false;
+}
+
 static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 				   const struct thermal_trip *trip,
 				   struct thermal_cooling_device *cdev,
@@ -293,27 +321,7 @@ static bool thermal_of_should_bind(struct thermal_zone_device *tz,
 		goto out;
 
 	/* Look up the trip and the cdev in the cooling maps. */
-	for_each_child_of_node_scoped(cm_np, child) {
-		struct device_node *tr_np;
-		int count, i;
-
-		tr_np = of_parse_phandle(child, "trip", 0);
-		if (tr_np != trip->priv)
-			continue;
-
-		/* The trip has been found, look up the cdev. */
-		count = of_count_phandle_with_args(child, "cooling-device", "#cooling-cells");
-		if (count <= 0)
-			pr_err("Add a cooling_device property with at least one device\n");
-
-		for (i = 0; i < count; i++) {
-			result = thermal_of_get_cooling_spec(child, i, cdev, c);
-			if (result)
-				break;
-		}
-
-		break;
-	}
+	result = thermal_of_cm_lookup(cm_np, trip, cdev, c);
 
 	of_node_put(cm_np);
 out:

From 0cde378a10c1cbfaa8dd2b89672d42f36c2809c3 Mon Sep 17 00:00:00 2001
From: Yu-Che Cheng <giver@chromium.org>
Date: Sat, 22 Feb 2025 11:20:34 +0800
Subject: [PATCH 1091/2753] thermal: gov_power_allocator: Update total_weight
 on bind and cdev updates

params->total_weight is not initialized during bind and not updated when
the bound cdev changes. The cooling device weight will not be used due
to the uninitialized total_weight, until an update via sysfs is
triggered.

The bound cdevs are updated during thermal zone registration, where each
cooling device will be bound to the thermal zone one by one, but
power_allocator_bind() can be called without an additional cdev update
when manually changing the policy of a thermal zone via sysfs.

Add a new function to handle weight update logic, including updating
total_weight, and call it when bind, weight changes, and cdev updates to
ensure total_weight is always correct.

Fixes: a3cd6db4cc2e ("thermal: gov_power_allocator: Support new update callback of weights")
Signed-off-by: Yu-Che Cheng <giver@chromium.org>
Link: https://patch.msgid.link/20250222-fix-power-allocator-weight-v2-1-a94de86b685a@chromium.org
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/thermal/gov_power_allocator.c | 30 ++++++++++++++++++++-------
 1 file changed, 22 insertions(+), 8 deletions(-)

diff --git a/drivers/thermal/gov_power_allocator.c b/drivers/thermal/gov_power_allocator.c
index 3b626db55b2b9..0d9f636c80f4d 100644
--- a/drivers/thermal/gov_power_allocator.c
+++ b/drivers/thermal/gov_power_allocator.c
@@ -641,6 +641,22 @@ static int allocate_actors_buffer(struct power_allocator_params *params,
 	return ret;
 }
 
+static void power_allocator_update_weight(struct power_allocator_params *params)
+{
+	const struct thermal_trip_desc *td;
+	struct thermal_instance *instance;
+
+	if (!params->trip_max)
+		return;
+
+	td = trip_to_trip_desc(params->trip_max);
+
+	params->total_weight = 0;
+	list_for_each_entry(instance, &td->thermal_instances, trip_node)
+		if (power_actor_is_valid(instance))
+			params->total_weight += instance->weight;
+}
+
 static void power_allocator_update_tz(struct thermal_zone_device *tz,
 				      enum thermal_notify_event reason)
 {
@@ -656,16 +672,12 @@ static void power_allocator_update_tz(struct thermal_zone_device *tz,
 			if (power_actor_is_valid(instance))
 				num_actors++;
 
-		if (num_actors == params->num_actors)
-			return;
+		if (num_actors != params->num_actors)
+			allocate_actors_buffer(params, num_actors);
 
-		allocate_actors_buffer(params, num_actors);
-		break;
+		fallthrough;
 	case THERMAL_INSTANCE_WEIGHT_CHANGED:
-		params->total_weight = 0;
-		list_for_each_entry(instance, &td->thermal_instances, trip_node)
-			if (power_actor_is_valid(instance))
-				params->total_weight += instance->weight;
+		power_allocator_update_weight(params);
 		break;
 	default:
 		break;
@@ -731,6 +743,8 @@ static int power_allocator_bind(struct thermal_zone_device *tz)
 
 	tz->governor_data = params;
 
+	power_allocator_update_weight(params);
+
 	return 0;
 
 free_params:

From c6aa4e2cdff6351ec32404b63b83e5a4126a019b Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Fri, 21 Feb 2025 12:18:11 -0800
Subject: [PATCH 1092/2753] eth: fbnic: Add PCIe registers dump

Provide coverage to PCIe registers in ethtool register dump

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_csr.c | 1 +
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h | 5 +++++
 2 files changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
index aeb9f333f4c7a..d9c0dc1c2af97 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.c
@@ -30,6 +30,7 @@ static const struct fbnic_csr_bounds fbnic_csr_sects[] = {
 	FBNIC_BOUNDS(RSFEC),
 	FBNIC_BOUNDS(MAC_MAC),
 	FBNIC_BOUNDS(SIG),
+	FBNIC_BOUNDS(PCIE_SS_COMPHY),
 	FBNIC_BOUNDS(PUL_USER),
 	FBNIC_BOUNDS(QUEUE),
 	FBNIC_BOUNDS(RPC_RAM),
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index 6f24c5f2e175e..af6d33931c353 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -788,6 +788,11 @@ enum {
 #define FBNIC_MAC_STAT_TX_MULTICAST_H	0x11a4b		/* 0x4692c */
 #define FBNIC_MAC_STAT_TX_BROADCAST_L	0x11a4c		/* 0x46930 */
 #define FBNIC_MAC_STAT_TX_BROADCAST_H	0x11a4d		/* 0x46934 */
+
+/* PCIE Comphy Registers */
+#define FBNIC_CSR_START_PCIE_SS_COMPHY	0x2442e /* CSR section delimiter */
+#define FBNIC_CSR_END_PCIE_SS_COMPHY	0x279d7	/* CSR section delimiter */
+
 /* PUL User Registers */
 #define FBNIC_CSR_START_PUL_USER	0x31000	/* CSR section delimiter */
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG	0x3103d		/* 0xc40f4 */

From e4e7c9be21170bf60820d8db2ba9db29c7a7d9ac Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Fri, 21 Feb 2025 12:18:12 -0800
Subject: [PATCH 1093/2753] eth: fbnic: Consolidate PUL_USER CSR section

Move PUL_USER CSRs in the relevant section, update the end boundary
address, and remove the redundant definition of end boundary.

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_csr.h | 73 ++++++++++-----------
 1 file changed, 35 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
index af6d33931c353..3b12a0ab59065 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_csr.h
@@ -799,7 +799,41 @@ enum {
 #define FBNIC_PUL_OB_TLP_HDR_AW_CFG_BME		CSR_BIT(18)
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG	0x3103e		/* 0xc40f8 */
 #define FBNIC_PUL_OB_TLP_HDR_AR_CFG_BME		CSR_BIT(18)
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
+#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
+					0x3106e		/* 0xc41b8 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
+					0x31070		/* 0xc41c0 */
+#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
+					0x31071		/* 0xc41c4 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
+					0x31072		/* 0xc41c8 */
+#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
+					0x31073		/* 0xc41cc */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
+					0x31074		/* 0xc41d0 */
+#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
+					0x31075		/* 0xc41d4 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
+					0x31076		/* 0xc41d8 */
+#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
+					0x31077		/* 0xc41dc */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
+					0x31078		/* 0xc41e0 */
+#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
+					0x31079		/* 0xc41e4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
+					0x3107a		/* 0xc41e8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
+					0x3107b		/* 0xc41ec */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
+					0x3107c		/* 0xc41f0 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
+					0x3107d		/* 0xc41f4 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
+					0x3107e		/* 0xc41f8 */
+#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
+					0x3107f		/* 0xc41fc */
+#define FBNIC_CSR_END_PUL_USER	0x310ea	/* CSR section delimiter */
 
 /* Queue Registers
  *
@@ -939,43 +973,6 @@ enum {
 #define FBNIC_MAX_QUEUES		128
 #define FBNIC_CSR_END_QUEUE	(0x40000 + 0x400 * FBNIC_MAX_QUEUES - 1)
 
-/* PUL User Registers*/
-#define FBNIC_PUL_USER_OB_RD_TLP_CNT_31_0 \
-					0x3106e		/* 0xc41b8 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_31_0 \
-					0x31070		/* 0xc41c0 */
-#define FBNIC_PUL_USER_OB_RD_DWORD_CNT_63_32 \
-					0x31071		/* 0xc41c4 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_31_0 \
-					0x31072		/* 0xc41c8 */
-#define FBNIC_PUL_USER_OB_WR_TLP_CNT_63_32 \
-					0x31073		/* 0xc41cc */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_31_0 \
-					0x31074		/* 0xc41d0 */
-#define FBNIC_PUL_USER_OB_WR_DWORD_CNT_63_32 \
-					0x31075		/* 0xc41d4 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_31_0 \
-					0x31076		/* 0xc41d8 */
-#define FBNIC_PUL_USER_OB_CPL_TLP_CNT_63_32 \
-					0x31077		/* 0xc41dc */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_31_0 \
-					0x31078		/* 0xc41e0 */
-#define FBNIC_PUL_USER_OB_CPL_DWORD_CNT_63_32 \
-					0x31079		/* 0xc41e4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_31_0 \
-					0x3107a		/* 0xc41e8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_CPL_CRED_63_32 \
-					0x3107b		/* 0xc41ec */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_31_0 \
-					0x3107c		/* 0xc41f0 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_TAG_63_32 \
-					0x3107d		/* 0xc41f4 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_31_0 \
-					0x3107e		/* 0xc41f8 */
-#define FBNIC_PUL_USER_OB_RD_DBG_CNT_NP_CRED_63_32 \
-					0x3107f		/* 0xc41fc */
-#define FBNIC_CSR_END_PUL_USER	0x31080	/* CSR section delimiter */
-
 /* BAR 4 CSRs */
 
 /* The IPC mailbox consists of 32 mailboxes, with each mailbox consisting

From 26aa7992b456629882b74b2f3916dd2b94a87e7b Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Fri, 21 Feb 2025 12:18:13 -0800
Subject: [PATCH 1094/2753] eth: fbnic: Update return value in kdoc

Fix return value in kdoc for fbnic_netdev_alloc()

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/meta/fbnic/fbnic_netdev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
index cf8feb90b6174..79a01fdd1dd16 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_netdev.c
@@ -611,7 +611,7 @@ void fbnic_netdev_free(struct fbnic_dev *fbd)
  * Allocate and initialize the netdev and netdev private structure. Bind
  * together the hardware, netdev, and pci data structures.
  *
- *  Return: 0 on success, negative on failure
+ *  Return: Pointer to net_device on success, NULL on failure
  **/
 struct net_device *fbnic_netdev_alloc(struct fbnic_dev *fbd)
 {

From 4b90de5bc0f5a6d1151acd74c838275f9b7be3a5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:52 -0800
Subject: [PATCH 1095/2753] xfs: reduce context switches for synchronous
 buffered I/O

Currently all metadata I/O completions happen in the m_buf_workqueue
workqueue.  But for synchronous I/O (i.e. all buffer reads) there is no
need for that, as there always is a called in process context that is
waiting for the I/O.  Factor out the guts of xfs_buf_ioend into a
separate helper and call it from xfs_buf_iowait to avoid a double
an extra context switch to the workqueue.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c | 43 +++++++++++++++++++++++++++----------------
 1 file changed, 27 insertions(+), 16 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 15bb790359f81..dfc1849b3314b 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1345,6 +1345,7 @@ xfs_buf_ioend_handle_error(
 resubmit:
 	xfs_buf_ioerror(bp, 0);
 	bp->b_flags |= (XBF_DONE | XBF_WRITE_FAIL);
+	reinit_completion(&bp->b_iowait);
 	xfs_buf_submit(bp);
 	return true;
 out_stale:
@@ -1355,8 +1356,9 @@ xfs_buf_ioend_handle_error(
 	return false;
 }
 
-static void
-xfs_buf_ioend(
+/* returns false if the caller needs to resubmit the I/O, else true */
+static bool
+__xfs_buf_ioend(
 	struct xfs_buf	*bp)
 {
 	trace_xfs_buf_iodone(bp, _RET_IP_);
@@ -1376,7 +1378,7 @@ xfs_buf_ioend(
 		}
 
 		if (unlikely(bp->b_error) && xfs_buf_ioend_handle_error(bp))
-			return;
+			return false;
 
 		/* clear the retry state */
 		bp->b_last_error = 0;
@@ -1397,7 +1399,15 @@ xfs_buf_ioend(
 
 	bp->b_flags &= ~(XBF_READ | XBF_WRITE | XBF_READ_AHEAD |
 			 _XBF_LOGRECOVERY);
+	return true;
+}
 
+static void
+xfs_buf_ioend(
+	struct xfs_buf	*bp)
+{
+	if (!__xfs_buf_ioend(bp))
+		return;
 	if (bp->b_flags & XBF_ASYNC)
 		xfs_buf_relse(bp);
 	else
@@ -1411,15 +1421,8 @@ xfs_buf_ioend_work(
 	struct xfs_buf		*bp =
 		container_of(work, struct xfs_buf, b_ioend_work);
 
-	xfs_buf_ioend(bp);
-}
-
-static void
-xfs_buf_ioend_async(
-	struct xfs_buf	*bp)
-{
-	INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
-	queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+	if (__xfs_buf_ioend(bp))
+		xfs_buf_relse(bp);
 }
 
 void
@@ -1491,7 +1494,13 @@ xfs_buf_bio_end_io(
 		 XFS_TEST_ERROR(false, bp->b_mount, XFS_ERRTAG_BUF_IOERROR))
 		xfs_buf_ioerror(bp, -EIO);
 
-	xfs_buf_ioend_async(bp);
+	if (bp->b_flags & XBF_ASYNC) {
+		INIT_WORK(&bp->b_ioend_work, xfs_buf_ioend_work);
+		queue_work(bp->b_mount->m_buf_workqueue, &bp->b_ioend_work);
+	} else {
+		complete(&bp->b_iowait);
+	}
+
 	bio_put(bio);
 }
 
@@ -1568,9 +1577,11 @@ xfs_buf_iowait(
 {
 	ASSERT(!(bp->b_flags & XBF_ASYNC));
 
-	trace_xfs_buf_iowait(bp, _RET_IP_);
-	wait_for_completion(&bp->b_iowait);
-	trace_xfs_buf_iowait_done(bp, _RET_IP_);
+	do {
+		trace_xfs_buf_iowait(bp, _RET_IP_);
+		wait_for_completion(&bp->b_iowait);
+		trace_xfs_buf_iowait_done(bp, _RET_IP_);
+	} while (!__xfs_buf_ioend(bp));
 
 	return bp->b_error;
 }

From efc5f7a9f3d887ce44b7610bc39388094b6f97d5 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:53 -0800
Subject: [PATCH 1096/2753] xfs: decouple buffer readahead from the normal
 buffer read path

xfs_buf_readahead_map is the only caller of xfs_buf_read_map and thus
_xfs_buf_read that is not synchronous.  Split it from xfs_buf_read_map
so that the asynchronous path is self-contained and the now purely
synchronous xfs_buf_read_map / _xfs_buf_read implementation can be
simplified.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c         | 41 ++++++++++++++++++++--------------------
 fs/xfs/xfs_buf.h         |  2 +-
 fs/xfs/xfs_log_recover.c |  2 +-
 fs/xfs/xfs_trace.h       |  1 +
 4 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index dfc1849b3314b..4ea20483d5213 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -794,18 +794,13 @@ xfs_buf_get_map(
 
 int
 _xfs_buf_read(
-	struct xfs_buf		*bp,
-	xfs_buf_flags_t		flags)
+	struct xfs_buf		*bp)
 {
-	ASSERT(!(flags & XBF_WRITE));
 	ASSERT(bp->b_maps[0].bm_bn != XFS_BUF_DADDR_NULL);
 
 	bp->b_flags &= ~(XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD | XBF_DONE);
-	bp->b_flags |= flags & (XBF_READ | XBF_ASYNC | XBF_READ_AHEAD);
-
+	bp->b_flags |= XBF_READ;
 	xfs_buf_submit(bp);
-	if (flags & XBF_ASYNC)
-		return 0;
 	return xfs_buf_iowait(bp);
 }
 
@@ -857,6 +852,8 @@ xfs_buf_read_map(
 	struct xfs_buf		*bp;
 	int			error;
 
+	ASSERT(!(flags & (XBF_WRITE | XBF_ASYNC | XBF_READ_AHEAD)));
+
 	flags |= XBF_READ;
 	*bpp = NULL;
 
@@ -870,21 +867,11 @@ xfs_buf_read_map(
 		/* Initiate the buffer read and wait. */
 		XFS_STATS_INC(target->bt_mount, xb_get_read);
 		bp->b_ops = ops;
-		error = _xfs_buf_read(bp, flags);
-
-		/* Readahead iodone already dropped the buffer, so exit. */
-		if (flags & XBF_ASYNC)
-			return 0;
+		error = _xfs_buf_read(bp);
 	} else {
 		/* Buffer already read; all we need to do is check it. */
 		error = xfs_buf_reverify(bp, ops);
 
-		/* Readahead already finished; drop the buffer and exit. */
-		if (flags & XBF_ASYNC) {
-			xfs_buf_relse(bp);
-			return 0;
-		}
-
 		/* We do not want read in the flags */
 		bp->b_flags &= ~XBF_READ;
 		ASSERT(bp->b_ops != NULL || ops == NULL);
@@ -936,6 +923,7 @@ xfs_buf_readahead_map(
 	int			nmaps,
 	const struct xfs_buf_ops *ops)
 {
+	const xfs_buf_flags_t	flags = XBF_READ | XBF_ASYNC | XBF_READ_AHEAD;
 	struct xfs_buf		*bp;
 
 	/*
@@ -945,9 +933,20 @@ xfs_buf_readahead_map(
 	if (xfs_buftarg_is_mem(target))
 		return;
 
-	xfs_buf_read_map(target, map, nmaps,
-		     XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD, &bp, ops,
-		     __this_address);
+	if (xfs_buf_get_map(target, map, nmaps, flags | XBF_TRYLOCK, &bp))
+		return;
+	trace_xfs_buf_readahead(bp, 0, _RET_IP_);
+
+	if (bp->b_flags & XBF_DONE) {
+		xfs_buf_reverify(bp, ops);
+		xfs_buf_relse(bp);
+		return;
+	}
+	XFS_STATS_INC(target->bt_mount, xb_get_read);
+	bp->b_ops = ops;
+	bp->b_flags &= ~(XBF_WRITE | XBF_DONE);
+	bp->b_flags |= flags;
+	xfs_buf_submit(bp);
 }
 
 /*
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 3b4ed42e11c01..2e747555ad3fa 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -291,7 +291,7 @@ int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
 int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
 		size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp,
 		const struct xfs_buf_ops *ops);
-int _xfs_buf_read(struct xfs_buf *bp, xfs_buf_flags_t flags);
+int _xfs_buf_read(struct xfs_buf *bp);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index b3c27dbccce86..2f76531842f83 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -3380,7 +3380,7 @@ xlog_do_recover(
 	 */
 	xfs_buf_lock(bp);
 	xfs_buf_hold(bp);
-	error = _xfs_buf_read(bp, XBF_READ);
+	error = _xfs_buf_read(bp);
 	if (error) {
 		if (!xlog_is_shutdown(log)) {
 			xfs_buf_ioerror_alert(bp, __this_address);
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index b29462363b815..bfc2f12490224 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -593,6 +593,7 @@ DEFINE_EVENT(xfs_buf_flags_class, name, \
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_find);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_get);
 DEFINE_BUF_FLAGS_EVENT(xfs_buf_read);
+DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead);
 
 TRACE_EVENT(xfs_buf_ioerror,
 	TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip),

From 0d1120b9bbe48a2d119afe0dc64f9c0666745bc8 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:54 -0800
Subject: [PATCH 1097/2753] xfs: remove most in-flight buffer accounting

The buffer cache keeps a bt_io_count per-CPU counter to track all
in-flight I/O, which is used to ensure no I/O is in flight when
unmounting the file system.

For most I/O we already keep track of inflight I/O at higher levels:

 - for synchronous I/O (xfs_buf_read/xfs_bwrite/xfs_buf_delwri_submit),
   the caller has a reference and waits for I/O completions using
   xfs_buf_iowait
 - for xfs_buf_delwri_submit_nowait the only caller (AIL writeback)
   tracks the log items that the buffer attached to

This only leaves only xfs_buf_readahead_map as a submitter of
asynchronous I/O that is not tracked by anything else.  Replace the
bt_io_count per-cpu counter with a more specific bt_readahead_count
counter only tracking readahead I/O.  This allows to simply increment
it when submitting readahead I/O and decrementing it when it completed,
and thus simplify xfs_buf_rele and remove the needed for the
XBF_NO_IOACCT flags and the XFS_BSTATE_IN_FLIGHT buffer state.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c     | 90 ++++++++------------------------------------
 fs/xfs/xfs_buf.h     |  5 +--
 fs/xfs/xfs_buf_mem.c |  2 +-
 fs/xfs/xfs_mount.c   |  7 +---
 fs/xfs/xfs_rtalloc.c |  2 +-
 5 files changed, 20 insertions(+), 86 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 4ea20483d5213..e161f3ab41087 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -29,11 +29,6 @@ struct kmem_cache *xfs_buf_cache;
 /*
  * Locking orders
  *
- * xfs_buf_ioacct_inc:
- * xfs_buf_ioacct_dec:
- *	b_sema (caller holds)
- *	  b_lock
- *
  * xfs_buf_stale:
  *	b_sema (caller holds)
  *	  b_lock
@@ -81,51 +76,6 @@ xfs_buf_vmap_len(
 	return (bp->b_page_count * PAGE_SIZE);
 }
 
-/*
- * Bump the I/O in flight count on the buftarg if we haven't yet done so for
- * this buffer. The count is incremented once per buffer (per hold cycle)
- * because the corresponding decrement is deferred to buffer release. Buffers
- * can undergo I/O multiple times in a hold-release cycle and per buffer I/O
- * tracking adds unnecessary overhead. This is used for sychronization purposes
- * with unmount (see xfs_buftarg_drain()), so all we really need is a count of
- * in-flight buffers.
- *
- * Buffers that are never released (e.g., superblock, iclog buffers) must set
- * the XBF_NO_IOACCT flag before I/O submission. Otherwise, the buftarg count
- * never reaches zero and unmount hangs indefinitely.
- */
-static inline void
-xfs_buf_ioacct_inc(
-	struct xfs_buf	*bp)
-{
-	if (bp->b_flags & XBF_NO_IOACCT)
-		return;
-
-	ASSERT(bp->b_flags & XBF_ASYNC);
-	spin_lock(&bp->b_lock);
-	if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
-		bp->b_state |= XFS_BSTATE_IN_FLIGHT;
-		percpu_counter_inc(&bp->b_target->bt_io_count);
-	}
-	spin_unlock(&bp->b_lock);
-}
-
-/*
- * Clear the in-flight state on a buffer about to be released to the LRU or
- * freed and unaccount from the buftarg.
- */
-static inline void
-__xfs_buf_ioacct_dec(
-	struct xfs_buf	*bp)
-{
-	lockdep_assert_held(&bp->b_lock);
-
-	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
-		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
-		percpu_counter_dec(&bp->b_target->bt_io_count);
-	}
-}
-
 /*
  * When we mark a buffer stale, we remove the buffer from the LRU and clear the
  * b_lru_ref count so that the buffer is freed immediately when the buffer
@@ -156,8 +106,6 @@ xfs_buf_stale(
 	 * status now to preserve accounting consistency.
 	 */
 	spin_lock(&bp->b_lock);
-	__xfs_buf_ioacct_dec(bp);
-
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
 	    (list_lru_del_obj(&bp->b_target->bt_lru, &bp->b_lru)))
@@ -946,6 +894,7 @@ xfs_buf_readahead_map(
 	bp->b_ops = ops;
 	bp->b_flags &= ~(XBF_WRITE | XBF_DONE);
 	bp->b_flags |= flags;
+	percpu_counter_inc(&target->bt_readahead_count);
 	xfs_buf_submit(bp);
 }
 
@@ -1002,10 +951,12 @@ xfs_buf_get_uncached(
 	struct xfs_buf		*bp;
 	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
+	/* there are currently no valid flags for xfs_buf_get_uncached */
+	ASSERT(flags == 0);
+
 	*bpp = NULL;
 
-	/* flags might contain irrelevant bits, pass only what we care about */
-	error = _xfs_buf_alloc(target, &map, 1, flags & XBF_NO_IOACCT, &bp);
+	error = _xfs_buf_alloc(target, &map, 1, flags, &bp);
 	if (error)
 		return error;
 
@@ -1059,7 +1010,6 @@ xfs_buf_rele_uncached(
 		spin_unlock(&bp->b_lock);
 		return;
 	}
-	__xfs_buf_ioacct_dec(bp);
 	spin_unlock(&bp->b_lock);
 	xfs_buf_free(bp);
 }
@@ -1078,19 +1028,11 @@ xfs_buf_rele_cached(
 	spin_lock(&bp->b_lock);
 	ASSERT(bp->b_hold >= 1);
 	if (bp->b_hold > 1) {
-		/*
-		 * Drop the in-flight state if the buffer is already on the LRU
-		 * and it holds the only reference. This is racy because we
-		 * haven't acquired the pag lock, but the use of _XBF_IN_FLIGHT
-		 * ensures the decrement occurs only once per-buf.
-		 */
-		if (--bp->b_hold == 1 && !list_empty(&bp->b_lru))
-			__xfs_buf_ioacct_dec(bp);
+		bp->b_hold--;
 		goto out_unlock;
 	}
 
 	/* we are asked to drop the last reference */
-	__xfs_buf_ioacct_dec(bp);
 	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU, keep the reference to the
@@ -1370,6 +1312,8 @@ __xfs_buf_ioend(
 			bp->b_ops->verify_read(bp);
 		if (!bp->b_error)
 			bp->b_flags |= XBF_DONE;
+		if (bp->b_flags & XBF_READ_AHEAD)
+			percpu_counter_dec(&bp->b_target->bt_readahead_count);
 	} else {
 		if (!bp->b_error) {
 			bp->b_flags &= ~XBF_WRITE_FAIL;
@@ -1658,9 +1602,6 @@ xfs_buf_submit(
 	 */
 	bp->b_error = 0;
 
-	if (bp->b_flags & XBF_ASYNC)
-		xfs_buf_ioacct_inc(bp);
-
 	if ((bp->b_flags & XBF_WRITE) && !xfs_buf_verify_write(bp)) {
 		xfs_force_shutdown(bp->b_mount, SHUTDOWN_CORRUPT_INCORE);
 		xfs_buf_ioend(bp);
@@ -1786,9 +1727,8 @@ xfs_buftarg_wait(
 	struct xfs_buftarg	*btp)
 {
 	/*
-	 * First wait on the buftarg I/O count for all in-flight buffers to be
-	 * released. This is critical as new buffers do not make the LRU until
-	 * they are released.
+	 * First wait for all in-flight readahead buffers to be released.  This is
+	 * critical as new buffers do not make the LRU until they are released.
 	 *
 	 * Next, flush the buffer workqueue to ensure all completion processing
 	 * has finished. Just waiting on buffer locks is not sufficient for
@@ -1797,7 +1737,7 @@ xfs_buftarg_wait(
 	 * all reference counts have been dropped before we start walking the
 	 * LRU list.
 	 */
-	while (percpu_counter_sum(&btp->bt_io_count))
+	while (percpu_counter_sum(&btp->bt_readahead_count))
 		delay(100);
 	flush_workqueue(btp->bt_mount->m_buf_workqueue);
 }
@@ -1914,8 +1854,8 @@ xfs_destroy_buftarg(
 	struct xfs_buftarg	*btp)
 {
 	shrinker_free(btp->bt_shrinker);
-	ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
-	percpu_counter_destroy(&btp->bt_io_count);
+	ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
+	percpu_counter_destroy(&btp->bt_readahead_count);
 	list_lru_destroy(&btp->bt_lru);
 }
 
@@ -1969,7 +1909,7 @@ xfs_init_buftarg(
 
 	if (list_lru_init(&btp->bt_lru))
 		return -ENOMEM;
-	if (percpu_counter_init(&btp->bt_io_count, 0, GFP_KERNEL))
+	if (percpu_counter_init(&btp->bt_readahead_count, 0, GFP_KERNEL))
 		goto out_destroy_lru;
 
 	btp->bt_shrinker =
@@ -1983,7 +1923,7 @@ xfs_init_buftarg(
 	return 0;
 
 out_destroy_io_count:
-	percpu_counter_destroy(&btp->bt_io_count);
+	percpu_counter_destroy(&btp->bt_readahead_count);
 out_destroy_lru:
 	list_lru_destroy(&btp->bt_lru);
 	return -ENOMEM;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 2e747555ad3fa..80e06eecaf56e 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -27,7 +27,6 @@ struct xfs_buf;
 #define XBF_READ	 (1u << 0) /* buffer intended for reading from device */
 #define XBF_WRITE	 (1u << 1) /* buffer intended for writing to device */
 #define XBF_READ_AHEAD	 (1u << 2) /* asynchronous read-ahead */
-#define XBF_NO_IOACCT	 (1u << 3) /* bypass I/O accounting (non-LRU bufs) */
 #define XBF_ASYNC	 (1u << 4) /* initiator will not wait for completion */
 #define XBF_DONE	 (1u << 5) /* all pages in the buffer uptodate */
 #define XBF_STALE	 (1u << 6) /* buffer has been staled, do not find it */
@@ -58,7 +57,6 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_READ,		"READ" }, \
 	{ XBF_WRITE,		"WRITE" }, \
 	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
-	{ XBF_NO_IOACCT,	"NO_IOACCT" }, \
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \
@@ -77,7 +75,6 @@ typedef unsigned int xfs_buf_flags_t;
  * Internal state flags.
  */
 #define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
-#define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
 struct xfs_buf_cache {
 	struct rhashtable	bc_hash;
@@ -116,7 +113,7 @@ struct xfs_buftarg {
 	struct shrinker		*bt_shrinker;
 	struct list_lru		bt_lru;
 
-	struct percpu_counter	bt_io_count;
+	struct percpu_counter	bt_readahead_count;
 	struct ratelimit_state	bt_ioerror_rl;
 
 	/* Atomic write unit values */
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index 07bebbfb16ee1..5b64a2b3b113f 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -117,7 +117,7 @@ xmbuf_free(
 	struct xfs_buftarg	*btp)
 {
 	ASSERT(xfs_buftarg_is_mem(btp));
-	ASSERT(percpu_counter_sum(&btp->bt_io_count) == 0);
+	ASSERT(percpu_counter_sum(&btp->bt_readahead_count) == 0);
 
 	trace_xmbuf_free(btp);
 
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 477c5262cf912..b69356582b86f 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -181,14 +181,11 @@ xfs_readsb(
 
 	/*
 	 * Allocate a (locked) buffer to hold the superblock. This will be kept
-	 * around at all times to optimize access to the superblock. Therefore,
-	 * set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
-	 * elevated.
+	 * around at all times to optimize access to the superblock.
 	 */
 reread:
 	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				      BTOBB(sector_size), XBF_NO_IOACCT, &bp,
-				      buf_ops);
+				      BTOBB(sector_size), 0, &bp, buf_ops);
 	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index d8e6d073d64dc..57bef567e0116 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1407,7 +1407,7 @@ xfs_rtmount_readsb(
 
 	/* m_blkbb_log is not set up yet */
 	error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
-			mp->m_sb.sb_blocksize >> BBSHIFT, XBF_NO_IOACCT, &bp,
+			mp->m_sb.sb_blocksize >> BBSHIFT, 0, &bp,
 			&xfs_rtsb_buf_ops);
 	if (error) {
 		xfs_warn(mp, "rt sb validate failed with error %d.", error);

From 9b47d37496e2669078c8616334e5a7200f91681a Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Mon, 24 Feb 2025 15:48:55 -0800
Subject: [PATCH 1098/2753] xfs: remove the XBF_STALE check from
 xfs_buf_rele_cached

xfs_buf_stale already set b_lru_ref to 0, and thus prevents the buffer
from moving to the LRU.  Remove the duplicate check.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/xfs_buf.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index e161f3ab41087..5d560e9073f42 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -99,12 +99,6 @@ xfs_buf_stale(
 	 */
 	bp->b_flags &= ~_XBF_DELWRI_Q;
 
-	/*
-	 * Once the buffer is marked stale and unlocked, a subsequent lookup
-	 * could reset b_flags. There is no guarantee that the buffer is
-	 * unaccounted (released to LRU) before that occurs. Drop in-flight
-	 * status now to preserve accounting consistency.
-	 */
 	spin_lock(&bp->b_lock);
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
@@ -1033,7 +1027,7 @@ xfs_buf_rele_cached(
 	}
 
 	/* we are asked to drop the last reference */
-	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
+	if (atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU, keep the reference to the
 		 * buffer for the LRU and clear the (now stale) dispose list

From de2c211868b9424f9aa9b3432c4430825bafb41b Mon Sep 17 00:00:00 2001
From: Philo Lu <lulie@linux.alibaba.com>
Date: Sat, 22 Feb 2025 11:35:18 +0800
Subject: [PATCH 1099/2753] ipvs: Always clear ipvs_property flag in
 skb_scrub_packet()

We found an issue when using bpf_redirect with ipvs NAT mode after
commit ff70202b2d1a ("dev_forward_skb: do not scrub skb mark within
the same name space"). Particularly, we use bpf_redirect to return
the skb directly back to the netif it comes from, i.e., xnet is
false in skb_scrub_packet(), and then ipvs_property is preserved
and SNAT is skipped in the rx path.

ipvs_property has been already cleared when netns is changed in
commit 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when
SKB net namespace changed"). This patch just clears it in spite of
netns.

Fixes: 2b5ec1a5f973 ("netfilter/ipvs: clear ipvs_property flag when SKB net namespace changed")
Signed-off-by: Philo Lu <lulie@linux.alibaba.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Link: https://patch.msgid.link/20250222033518.126087-1-lulie@linux.alibaba.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/skbuff.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 7b03b64fdcb27..b1c81687e9d82 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -6033,11 +6033,11 @@ void skb_scrub_packet(struct sk_buff *skb, bool xnet)
 	skb->offload_fwd_mark = 0;
 	skb->offload_l3_fwd_mark = 0;
 #endif
+	ipvs_reset(skb);
 
 	if (!xnet)
 		return;
 
-	ipvs_reset(skb);
 	skb->mark = 0;
 	skb_clear_tstamp(skb);
 }

From bc50682128bde778a1ddc457a02d92a637c20c6f Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Sat, 22 Feb 2025 12:28:04 -0500
Subject: [PATCH 1100/2753] MAINTAINERS: socket timestamping: add Jason Xing as
 reviewer

Jason has been helping as reviewer for this area already, and has
contributed various features directly, notably BPF timestamping.

Also extend coverage to all timestamping tests, including those new
with BPF timestamping.

Link: https://lore.kernel.org/netdev/20250220072940.99994-1-kerneljasonxing@gmail.com/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250222172839.642079-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index ac15093537c6b..c92bcd02049e6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21923,10 +21923,13 @@ F:	sound/soc/uniphier/
 
 SOCKET TIMESTAMPING
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
+R:	Jason Xing <kernelxing@tencent.com>
 S:	Maintained
 F:	Documentation/networking/timestamping.rst
 F:	include/linux/net_tstamp.h
 F:	include/uapi/linux/net_tstamp.h
+F:	tools/testing/selftests/bpf/*/net_timestamping*
+F:	tools/testing/selftests/net/*timestamp*
 F:	tools/testing/selftests/net/so_txtime.c
 
 SOEKRIS NET48XX LED SUPPORT

From 56a677293509b2a0d39ac8d02b583c1ab1fe4d94 Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 25 Feb 2025 17:37:15 +0800
Subject: [PATCH 1101/2753] ASoC: SOF: Intel: don't check number of sdw links
 when set dmic_fixup
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, we assume that the PCH DMIC pins are pin-muxed with SoundWire
links. However, we do see a HW design that use PCH DMIC along with 3
SoundWire links. Remove the check now.
With this change the PCM DMIC will be presented if it is reported by the
BIOS irrespective of whether there are SDW links present or not.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20250225093716.67240-2-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/sof/intel/hda.c | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
index be689f6e10c81..a1ccd95da8bb7 100644
--- a/sound/soc/sof/intel/hda.c
+++ b/sound/soc/sof/intel/hda.c
@@ -1312,22 +1312,8 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
 		/* report to machine driver if any DMICs are found */
 		mach->mach_params.dmic_num = check_dmic_num(sdev);
 
-		if (sdw_mach_found) {
-			/*
-			 * DMICs use up to 4 pins and are typically pin-muxed with SoundWire
-			 * link 2 and 3, or link 1 and 2, thus we only try to enable dmics
-			 * if all conditions are true:
-			 * a) 2 or fewer links are used by SoundWire
-			 * b) the NHLT table reports the presence of microphones
-			 */
-			if (hweight_long(mach->link_mask) <= 2)
-				dmic_fixup = true;
-			else
-				mach->mach_params.dmic_num = 0;
-		} else {
-			if (mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER)
-				dmic_fixup = true;
-		}
+		if (sdw_mach_found || mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_DMIC_NUMBER)
+			dmic_fixup = true;
 
 		if (tplg_fixup &&
 		    dmic_fixup &&

From 4bcef04ca67fa8c46591a211885bb9c37f25dbbd Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Tue, 25 Feb 2025 17:37:16 +0800
Subject: [PATCH 1102/2753] ASoC: Intel: sof_sdw: warn both sdw and pch dmic
 are used
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Typically, SoundWire MIC and PCH DMIC will not coexist. However, we may
want to use both of them in some special cases. Add a warning to let
users know that SoundWire MIC and PCH DMIC are both present and they
could overwrite it with kernel params.

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Link: https://patch.msgid.link/20250225093716.67240-3-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index 203b07d4d833c..c13064c777261 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -803,7 +803,9 @@ static int create_sdw_dailink(struct snd_soc_card *card,
 			      int *be_id, struct snd_soc_codec_conf **codec_conf)
 {
 	struct device *dev = card->dev;
+	struct snd_soc_acpi_mach *mach = dev_get_platdata(card->dev);
 	struct asoc_sdw_mc_private *ctx = snd_soc_card_get_drvdata(card);
+	struct snd_soc_acpi_mach_params *mach_params = &mach->mach_params;
 	struct intel_mc_ctx *intel_ctx = (struct intel_mc_ctx *)ctx->private;
 	struct asoc_sdw_endpoint *sof_end;
 	int stream;
@@ -900,6 +902,11 @@ static int create_sdw_dailink(struct snd_soc_card *card,
 
 			codecs[j].name = sof_end->codec_name;
 			codecs[j].dai_name = sof_end->dai_info->dai_name;
+			if (sof_end->dai_info->dai_type == SOC_SDW_DAI_TYPE_MIC &&
+			    mach_params->dmic_num > 0) {
+				dev_warn(dev,
+					 "Both SDW DMIC and PCH DMIC are present, if incorrect, please set kernel params snd_sof_intel_hda_generic dmic_num=0 to disable PCH DMIC\n");
+			}
 			j++;
 		}
 

From 88ec7eedbbd21cad38707620ad6c48a4e9a87c18 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:11 -0800
Subject: [PATCH 1103/2753] perf/x86: Fix low freqency setting issue

Perf doesn't work at low frequencies:

  $ perf record -e cpu_core/instructions/ppp -F 120
  Error:
  The sys_perf_event_open() syscall returned with 22 (Invalid argument)
  for event (cpu_core/instructions/ppp).
  "dmesg | grep -i perf" may provide additional information.

The limit_period() check avoids a low sampling period on a counter. It
doesn't intend to limit the frequency.

The check in the x86_pmu_hw_config() should be limited to non-freq mode.
The attr.sample_period and attr.sample_freq are union. The
attr.sample_period should not be used to indicate the frequency mode.

Fixes: c46e665f0377 ("perf/x86: Add INST_RETIRED.ALL workarounds")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117151913.3043942-1-kan.liang@linux.intel.com
Closes: https://lore.kernel.org/lkml/20250115154949.3147-1-ravi.bangoria@amd.com/
---
 arch/x86/events/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 8f218ac0d445c..2092d615333da 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -628,7 +628,7 @@ int x86_pmu_hw_config(struct perf_event *event)
 	if (event->attr.type == event->pmu->type)
 		event->hw.config |= x86_pmu_get_event_config(event);
 
-	if (event->attr.sample_period && x86_pmu.limit_period) {
+	if (!event->attr.freq && x86_pmu.limit_period) {
 		s64 left = event->attr.sample_period;
 		x86_pmu.limit_period(event, &left);
 		if (left > event->attr.sample_period)

From 0d39844150546fa1415127c5fbae26db64070dd3 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:12 -0800
Subject: [PATCH 1104/2753] perf/core: Fix low freq setting via IOC_PERIOD

A low attr::freq value cannot be set via IOC_PERIOD on some platforms.

The perf_event_check_period() introduced in:

  81ec3f3c4c4d ("perf/x86: Add check_period PMU callback")

was intended to check the period, rather than the frequency.
A low frequency may be mistakenly rejected by limit_period().

Fix it.

Fixes: 81ec3f3c4c4d ("perf/x86: Add check_period PMU callback")
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250117151913.3043942-2-kan.liang@linux.intel.com
Closes: https://lore.kernel.org/lkml/20250115154949.3147-1-ravi.bangoria@amd.com/
---
 kernel/events/core.c | 17 +++++++++--------
 1 file changed, 9 insertions(+), 8 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 086d46d096963..6364319e2f888 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -5969,14 +5969,15 @@ static int _perf_event_period(struct perf_event *event, u64 value)
 	if (!value)
 		return -EINVAL;
 
-	if (event->attr.freq && value > sysctl_perf_event_sample_rate)
-		return -EINVAL;
-
-	if (perf_event_check_period(event, value))
-		return -EINVAL;
-
-	if (!event->attr.freq && (value & (1ULL << 63)))
-		return -EINVAL;
+	if (event->attr.freq) {
+		if (value > sysctl_perf_event_sample_rate)
+			return -EINVAL;
+	} else {
+		if (perf_event_check_period(event, value))
+			return -EINVAL;
+		if (value & (1ULL << 63))
+			return -EINVAL;
+	}
 
 	event_function_call(event, __perf_event_period, &value);
 

From 5bd566703e16b17d17f4fb648440d54f8967462c Mon Sep 17 00:00:00 2001
From: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Date: Fri, 21 Feb 2025 13:33:52 -0800
Subject: [PATCH 1105/2753] drm/xe/oa: Allow oa_exponent value of 0

OA exponent value of 0 is a valid value for periodic reports. Allow user
to pass 0 for the OA sampling interval since it gets converted to 2 gt
clock ticks.

v2: Update the check in xe_oa_stream_init as well (Ashutosh)
v3: Fix mi-rpc failure by setting default exponent to -1 (CI)
v4: Add the Fixes tag

Fixes: b6fd51c62119 ("drm/xe/oa/uapi: Define and parse OA stream properties")
Signed-off-by: Umesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: Ashutosh Dixit <ashutosh.dixit@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221213352.1712932-1-umesh.nerlige.ramappa@intel.com
(cherry picked from commit 30341f0b8ea71725cc4ab2c43e3a3b749892fc92)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_oa.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
index fa873f3d0a9d1..eb6cd91e1e226 100644
--- a/drivers/gpu/drm/xe/xe_oa.c
+++ b/drivers/gpu/drm/xe/xe_oa.c
@@ -1689,7 +1689,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
 	stream->oa_buffer.format = &stream->oa->oa_formats[param->oa_format];
 
 	stream->sample = param->sample;
-	stream->periodic = param->period_exponent > 0;
+	stream->periodic = param->period_exponent >= 0;
 	stream->period_exponent = param->period_exponent;
 	stream->no_preempt = param->no_preempt;
 	stream->wait_num_reports = param->wait_num_reports;
@@ -1970,6 +1970,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 	}
 
 	param.xef = xef;
+	param.period_exponent = -1;
 	ret = xe_oa_user_extensions(oa, XE_OA_USER_EXTN_FROM_OPEN, data, 0, &param);
 	if (ret)
 		return ret;
@@ -2024,7 +2025,7 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
 		goto err_exec_q;
 	}
 
-	if (param.period_exponent > 0) {
+	if (param.period_exponent >= 0) {
 		u64 oa_period, oa_freq_hz;
 
 		/* Requesting samples from OAG buffer is a privileged operation */

From 287044abff8291993ce9565ac6e6a72b85e33b85 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Sun, 23 Feb 2025 21:45:07 +0100
Subject: [PATCH 1106/2753] sctp: Remove unused payload from sctp_idatahdr

Remove the unused payload array from the struct sctp_idatahdr.

Cc: Kees Cook <kees@kernel.org>
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250223204505.2499-3-thorsten.blum@linux.dev
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/sctp.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/include/linux/sctp.h b/include/linux/sctp.h
index 812011d8b67e7..6719949135c96 100644
--- a/include/linux/sctp.h
+++ b/include/linux/sctp.h
@@ -238,7 +238,6 @@ struct sctp_idatahdr {
 		__u32 ppid;
 		__be32 fsn;
 	};
-	__u8 payload[0];
 };
 
 struct sctp_idata_chunk {

From fe08b7d5085a9774abc30c26d5aebc5b9cdd6091 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Tue, 25 Feb 2025 13:18:42 +0000
Subject: [PATCH 1107/2753] firmware: cs_dsp: Remove async regmap writes

Change calls to async regmap write functions to use the normal
blocking writes so that the cs35l56 driver can use spi_bus_lock() to
gain exclusive access to the SPI bus.

As this is part of a fix, it makes only the minimal change to swap the
functions to the blocking equivalents. There's no need to risk
reworking the buffer allocation logic that is now partially redundant.

The async writes are a 12-year-old workaround for inefficiency of
synchronous writes in the SPI subsystem. The SPI subsystem has since
been changed to avoid the overheads, so this workaround should not be
necessary.

The cs35l56 driver needs to use spi_bus_lock() prevent bus activity
while it is soft-resetting the cs35l56. But spi_bus_lock() is
incompatible with spi_async() calls, which will fail with -EBUSY.

Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250225131843.113752-2-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/cirrus/cs_dsp.c | 24 ++++++------------------
 1 file changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index 5365e9a430007..42433c19eb308 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -1609,8 +1609,8 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 				goto out_fw;
 			}
 
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(region->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(region->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write %d bytes at %d in %s: %d\n",
@@ -1625,12 +1625,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 		regions++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0) {
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-		goto out_fw;
-	}
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, regions, pos - firmware->size);
@@ -1638,7 +1632,6 @@ static int cs_dsp_load(struct cs_dsp *dsp, const struct firmware *firmware,
 	cs_dsp_debugfs_save_wmfwname(dsp, file);
 
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2326,8 +2319,8 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 			cs_dsp_dbg(dsp, "%s.%d: Writing %d bytes at %x\n",
 				   file, blocks, le32_to_cpu(blk->len),
 				   reg);
-			ret = regmap_raw_write_async(regmap, reg, buf->buf,
-						     le32_to_cpu(blk->len));
+			ret = regmap_raw_write(regmap, reg, buf->buf,
+					       le32_to_cpu(blk->len));
 			if (ret != 0) {
 				cs_dsp_err(dsp,
 					   "%s.%d: Failed to write to %x in %s: %d\n",
@@ -2339,10 +2332,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 		blocks++;
 	}
 
-	ret = regmap_async_complete(regmap);
-	if (ret != 0)
-		cs_dsp_err(dsp, "Failed to complete async write: %d\n", ret);
-
 	if (pos > firmware->size)
 		cs_dsp_warn(dsp, "%s.%d: %zu bytes at end of file\n",
 			    file, blocks, pos - firmware->size);
@@ -2350,7 +2339,6 @@ static int cs_dsp_load_coeff(struct cs_dsp *dsp, const struct firmware *firmware
 	cs_dsp_debugfs_save_binname(dsp, file);
 
 out_fw:
-	regmap_async_complete(regmap);
 	cs_dsp_buf_free(&buf_list);
 
 	if (ret == -EOVERFLOW)
@@ -2561,8 +2549,8 @@ static int cs_dsp_adsp2_enable_core(struct cs_dsp *dsp)
 {
 	int ret;
 
-	ret = regmap_update_bits_async(dsp->regmap, dsp->base + ADSP2_CONTROL,
-				       ADSP2_SYS_ENA, ADSP2_SYS_ENA);
+	ret = regmap_update_bits(dsp->regmap, dsp->base + ADSP2_CONTROL,
+				 ADSP2_SYS_ENA, ADSP2_SYS_ENA);
 	if (ret != 0)
 		return ret;
 

From 769c1b79295c38d60fde4c0a8f5f31e01360c54f Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Tue, 25 Feb 2025 13:18:43 +0000
Subject: [PATCH 1108/2753] ASoC: cs35l56: Prevent races when soft-resetting
 using SPI control

When SPI is used for control, the driver must hold the SPI bus lock
while issuing the sequence of writes to perform a soft reset.

>From the time the driver writes the SYSTEM_RESET command until the
driver does a write to terminate the reset, there must not be any
activity on the SPI bus lines. If there is any SPI activity during the
soft-reset, another soft-reset will be triggered. The state of the SPI
chip select is irrelevant.

A repeated soft-reset does not in itself cause any problems, and it is
not an infinite loop. The problem is a race between these resets and
the driver polling for boot completion. There is a time window between
soft resets where the driver could read HALO_STATE as 2 (fully booted)
while the chip is actually soft-resetting. Although this window is
small, it is long enough that it is possible to hit it in normal
operation.

To prevent this race and ensure the chip really is fully booted, the
driver calls spi_bus_lock() to prevent other activity while resetting.
It then issues the SYSTEM_RESET mailbox command. After allowing
sufficient time for reset to take effect, the driver issues a PING
mailbox command, which will force completion of the full soft-reset
sequence. The SPI bus lock can then be released. The mailbox is
checked for any boot or wakeup response from the firmware, before the
value in HALO_STATE will be trusted.

This does not affect SoundWire or I2C control.

Fixes: 8a731fd37f8b ("ASoC: cs35l56: Move utility functions to shared file")
Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250225131843.113752-3-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/cs35l56.h           | 31 ++++++++++++
 sound/pci/hda/cs35l56_hda_spi.c   |  3 ++
 sound/soc/codecs/cs35l56-shared.c | 80 +++++++++++++++++++++++++++++++
 sound/soc/codecs/cs35l56-spi.c    |  3 ++
 4 files changed, 117 insertions(+)

diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
index 3dc7a1551ac35..5d653a3491d07 100644
--- a/include/sound/cs35l56.h
+++ b/include/sound/cs35l56.h
@@ -12,6 +12,7 @@
 #include <linux/firmware/cirrus/cs_dsp.h>
 #include <linux/regulator/consumer.h>
 #include <linux/regmap.h>
+#include <linux/spi/spi.h>
 #include <sound/cs-amp-lib.h>
 
 #define CS35L56_DEVID					0x0000000
@@ -61,6 +62,7 @@
 #define CS35L56_IRQ1_MASK_8				0x000E0AC
 #define CS35L56_IRQ1_MASK_18				0x000E0D4
 #define CS35L56_IRQ1_MASK_20				0x000E0DC
+#define CS35L56_DSP_MBOX_1_RAW				0x0011000
 #define CS35L56_DSP_VIRTUAL1_MBOX_1			0x0011020
 #define CS35L56_DSP_VIRTUAL1_MBOX_2			0x0011024
 #define CS35L56_DSP_VIRTUAL1_MBOX_3			0x0011028
@@ -224,6 +226,7 @@
 #define CS35L56_HALO_STATE_SHUTDOWN			1
 #define CS35L56_HALO_STATE_BOOT_DONE			2
 
+#define CS35L56_MBOX_CMD_PING				0x0A000000
 #define CS35L56_MBOX_CMD_AUDIO_PLAY			0x0B000001
 #define CS35L56_MBOX_CMD_AUDIO_PAUSE			0x0B000002
 #define CS35L56_MBOX_CMD_AUDIO_REINIT			0x0B000003
@@ -254,6 +257,16 @@
 #define CS35L56_NUM_BULK_SUPPLIES			3
 #define CS35L56_NUM_DSP_REGIONS				5
 
+/* Additional margin for SYSTEM_RESET to control port ready on SPI */
+#define CS35L56_SPI_RESET_TO_PORT_READY_US (CS35L56_CONTROL_PORT_READY_US + 2500)
+
+struct cs35l56_spi_payload {
+	__be32	addr;
+	__be16	pad;
+	__be32	value;
+} __packed;
+static_assert(sizeof(struct cs35l56_spi_payload) == 10);
+
 struct cs35l56_base {
 	struct device *dev;
 	struct regmap *regmap;
@@ -269,6 +282,7 @@ struct cs35l56_base {
 	s8 cal_index;
 	struct cirrus_amp_cal_data cal_data;
 	struct gpio_desc *reset_gpio;
+	struct cs35l56_spi_payload *spi_payload_buf;
 };
 
 static inline bool cs35l56_is_otp_register(unsigned int reg)
@@ -276,6 +290,23 @@ static inline bool cs35l56_is_otp_register(unsigned int reg)
 	return (reg >> 16) == 3;
 }
 
+static inline int cs35l56_init_config_for_spi(struct cs35l56_base *cs35l56,
+					      struct spi_device *spi)
+{
+	cs35l56->spi_payload_buf = devm_kzalloc(&spi->dev,
+						sizeof(*cs35l56->spi_payload_buf),
+						GFP_KERNEL | GFP_DMA);
+	if (!cs35l56->spi_payload_buf)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static inline bool cs35l56_is_spi(struct cs35l56_base *cs35l56)
+{
+	return IS_ENABLED(CONFIG_SPI_MASTER) && !!cs35l56->spi_payload_buf;
+}
+
 extern const struct regmap_config cs35l56_regmap_i2c;
 extern const struct regmap_config cs35l56_regmap_spi;
 extern const struct regmap_config cs35l56_regmap_sdw;
diff --git a/sound/pci/hda/cs35l56_hda_spi.c b/sound/pci/hda/cs35l56_hda_spi.c
index d4ee5bb7c4866..9035784669053 100644
--- a/sound/pci/hda/cs35l56_hda_spi.c
+++ b/sound/pci/hda/cs35l56_hda_spi.c
@@ -22,6 +22,9 @@ static int cs35l56_hda_spi_probe(struct spi_device *spi)
 		return -ENOMEM;
 
 	cs35l56->base.dev = &spi->dev;
+	ret = cs35l56_init_config_for_spi(&cs35l56->base, spi);
+	if (ret)
+		return ret;
 
 #ifdef CS35L56_WAKE_HOLD_TIME_US
 	cs35l56->base.can_hibernate = true;
diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
index e0ed4fc11155a..e28bfefa72f33 100644
--- a/sound/soc/codecs/cs35l56-shared.c
+++ b/sound/soc/codecs/cs35l56-shared.c
@@ -10,6 +10,7 @@
 #include <linux/gpio/consumer.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
+#include <linux/spi/spi.h>
 #include <linux/types.h>
 #include <sound/cs-amp-lib.h>
 
@@ -303,6 +304,79 @@ void cs35l56_wait_min_reset_pulse(void)
 }
 EXPORT_SYMBOL_NS_GPL(cs35l56_wait_min_reset_pulse, "SND_SOC_CS35L56_SHARED");
 
+static const struct {
+	u32 addr;
+	u32 value;
+} cs35l56_spi_system_reset_stages[] = {
+	{ .addr = CS35L56_DSP_VIRTUAL1_MBOX_1, .value = CS35L56_MBOX_CMD_SYSTEM_RESET },
+	/* The next write is necessary to delimit the soft reset */
+	{ .addr = CS35L56_DSP_MBOX_1_RAW, .value = CS35L56_MBOX_CMD_PING },
+};
+
+static void cs35l56_spi_issue_bus_locked_reset(struct cs35l56_base *cs35l56_base,
+					       struct spi_device *spi)
+{
+	struct cs35l56_spi_payload *buf = cs35l56_base->spi_payload_buf;
+	struct spi_transfer t = {
+		.tx_buf		= buf,
+		.len		= sizeof(*buf),
+	};
+	struct spi_message m;
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(cs35l56_spi_system_reset_stages); i++) {
+		buf->addr = cpu_to_be32(cs35l56_spi_system_reset_stages[i].addr);
+		buf->value = cpu_to_be32(cs35l56_spi_system_reset_stages[i].value);
+		spi_message_init_with_transfers(&m, &t, 1);
+		ret = spi_sync_locked(spi, &m);
+		if (ret)
+			dev_warn(cs35l56_base->dev, "spi_sync failed: %d\n", ret);
+
+		usleep_range(CS35L56_SPI_RESET_TO_PORT_READY_US,
+			     2 * CS35L56_SPI_RESET_TO_PORT_READY_US);
+	}
+}
+
+static void cs35l56_spi_system_reset(struct cs35l56_base *cs35l56_base)
+{
+	struct spi_device *spi = to_spi_device(cs35l56_base->dev);
+	unsigned int val;
+	int read_ret, ret;
+
+	/*
+	 * There must not be any other SPI bus activity while the amp is
+	 * soft-resetting.
+	 */
+	ret = spi_bus_lock(spi->controller);
+	if (ret) {
+		dev_warn(cs35l56_base->dev, "spi_bus_lock failed: %d\n", ret);
+		return;
+	}
+
+	cs35l56_spi_issue_bus_locked_reset(cs35l56_base, spi);
+	spi_bus_unlock(spi->controller);
+
+	/*
+	 * Check firmware boot by testing for a response in MBOX_2.
+	 * HALO_STATE cannot be trusted yet because the reset sequence
+	 * can leave it with stale state. But MBOX is reset.
+	 * The regmap must remain in cache-only until the chip has
+	 * booted, so use a bypassed read.
+	 */
+	ret = read_poll_timeout(regmap_read_bypassed, read_ret,
+				(val > 0) && (val < 0xffffffff),
+				CS35L56_HALO_STATE_POLL_US,
+				CS35L56_HALO_STATE_TIMEOUT_US,
+				false,
+				cs35l56_base->regmap,
+				CS35L56_DSP_VIRTUAL1_MBOX_2,
+				&val);
+	if (ret) {
+		dev_err(cs35l56_base->dev, "SPI reboot timed out(%d): MBOX2=%#x\n",
+			read_ret, val);
+	}
+}
+
 static const struct reg_sequence cs35l56_system_reset_seq[] = {
 	REG_SEQ0(CS35L56_DSP1_HALO_STATE, 0),
 	REG_SEQ0(CS35L56_DSP_VIRTUAL1_MBOX_1, CS35L56_MBOX_CMD_SYSTEM_RESET),
@@ -315,6 +389,12 @@ void cs35l56_system_reset(struct cs35l56_base *cs35l56_base, bool is_soundwire)
 	 * accesses other than the controlled system reset sequence below.
 	 */
 	regcache_cache_only(cs35l56_base->regmap, true);
+
+	if (cs35l56_is_spi(cs35l56_base)) {
+		cs35l56_spi_system_reset(cs35l56_base);
+		return;
+	}
+
 	regmap_multi_reg_write_bypassed(cs35l56_base->regmap,
 					cs35l56_system_reset_seq,
 					ARRAY_SIZE(cs35l56_system_reset_seq));
diff --git a/sound/soc/codecs/cs35l56-spi.c b/sound/soc/codecs/cs35l56-spi.c
index c101134e85328..ca6c03a8766d3 100644
--- a/sound/soc/codecs/cs35l56-spi.c
+++ b/sound/soc/codecs/cs35l56-spi.c
@@ -33,6 +33,9 @@ static int cs35l56_spi_probe(struct spi_device *spi)
 
 	cs35l56->base.dev = &spi->dev;
 	cs35l56->base.can_hibernate = true;
+	ret = cs35l56_init_config_for_spi(&cs35l56->base, spi);
+	if (ret)
+		return ret;
 
 	ret = cs35l56_common_probe(cs35l56);
 	if (ret != 0)

From 8ec43c58d3be615a71548bc09148212013fb7e5f Mon Sep 17 00:00:00 2001
From: Harry Wentland <harry.wentland@amd.com>
Date: Thu, 19 Dec 2024 21:33:08 -0700
Subject: [PATCH 1109/2753] drm/vkms: Round fixp2int conversion in lerp_u16

fixp2int always rounds down, fixp2int_ceil rounds up. We need
the new fixp2int_round.

Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Harry Wentland <harry.wentland@amd.com>
Reviewed-by: Louis Chauvet <louis.chauvet@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241220043410.416867-3-alex.hung@amd.com
Signed-off-by: Louis Chauvet <louis.chauvet@bootlin.com>
---
 drivers/gpu/drm/vkms/vkms_composer.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index b20ac17057262..fa269d279e257 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -67,7 +67,7 @@ static u16 lerp_u16(u16 a, u16 b, s64 t)
 
 	s64 delta = drm_fixp_mul(b_fp - a_fp, t);
 
-	return drm_fixp2int(a_fp + delta);
+	return drm_fixp2int_round(a_fp + delta);
 }
 
 static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)

From 889c57066ceee5e9172232da0608a8ac053bb6e5 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Tue, 25 Feb 2025 10:21:41 +0800
Subject: [PATCH 1110/2753] block: make segment size limit workable for > 4K
 PAGE_SIZE

Using PAGE_SIZE as a minimum expected DMA segment size in consideration
of devices which have a max DMA segment size of < 64k when used on 64k
PAGE_SIZE systems leads to devices not being able to probe such as
eMMC and Exynos UFS controller [0] [1] you can end up with a probe failure
as follows:

WARNING: CPU: 2 PID: 397 at block/blk-settings.c:339 blk_validate_limits+0x364/0x3c0

Ensure we use min(max_seg_size, seg_boundary_mask + 1) as the new min segment
size when max segment size is < PAGE_SIZE for 16k and 64k base page size systems.

If anyone need to backport this patch, the following commits are depended:

	commit 6aeb4f836480 ("block: remove bio_add_pc_page")
	commit 02ee5d69e3ba ("block: remove blk_rq_bio_prep")
	commit b7175e24d6ac ("block: add a dma mapping iterator")

Link: https://lore.kernel.org/linux-block/20230612203314.17820-1-bvanassche@acm.org/ # [0]
Link: https://lore.kernel.org/linux-block/1d55e942-5150-de4c-3a02-c3d066f87028@acm.org/ # [1]
Cc: Yi Zhang <yi.zhang@redhat.com>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Keith Busch <kbusch@kernel.org>
Tested-by: Paul Bunyan <pbunyan@redhat.com>
Reviewed-by: Daniel Gomez <da.gomez@kernel.org>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250225022141.2154581-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-merge.c      |  2 +-
 block/blk-settings.c   | 14 +++++++++++---
 block/blk.h            |  9 +++++++--
 include/linux/blkdev.h |  1 +
 4 files changed, 20 insertions(+), 6 deletions(-)

diff --git a/block/blk-merge.c b/block/blk-merge.c
index c7c85e10cf9cb..1d1589c352976 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -329,7 +329,7 @@ int bio_split_rw_at(struct bio *bio, const struct queue_limits *lim,
 
 		if (nsegs < lim->max_segments &&
 		    bytes + bv.bv_len <= max_bytes &&
-		    bv.bv_offset + bv.bv_len <= PAGE_SIZE) {
+		    bv.bv_offset + bv.bv_len <= lim->min_segment_size) {
 			nsegs++;
 			bytes += bv.bv_len;
 		} else {
diff --git a/block/blk-settings.c b/block/blk-settings.c
index c44dadc35e1ec..b9c6f0ec1c499 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -246,6 +246,7 @@ int blk_validate_limits(struct queue_limits *lim)
 {
 	unsigned int max_hw_sectors;
 	unsigned int logical_block_sectors;
+	unsigned long seg_size;
 	int err;
 
 	/*
@@ -303,7 +304,7 @@ int blk_validate_limits(struct queue_limits *lim)
 	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
 				lim->max_dev_sectors);
 	if (lim->max_user_sectors) {
-		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
+		if (lim->max_user_sectors < BLK_MIN_SEGMENT_SIZE / SECTOR_SIZE)
 			return -EINVAL;
 		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
 	} else if (lim->io_opt > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
@@ -341,7 +342,7 @@ int blk_validate_limits(struct queue_limits *lim)
 	 */
 	if (!lim->seg_boundary_mask)
 		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
-	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
+	if (WARN_ON_ONCE(lim->seg_boundary_mask < BLK_MIN_SEGMENT_SIZE - 1))
 		return -EINVAL;
 
 	/*
@@ -362,10 +363,17 @@ int blk_validate_limits(struct queue_limits *lim)
 		 */
 		if (!lim->max_segment_size)
 			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
-		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
+		if (WARN_ON_ONCE(lim->max_segment_size < BLK_MIN_SEGMENT_SIZE))
 			return -EINVAL;
 	}
 
+	/* setup min segment size for building new segment in fast path */
+	if (lim->seg_boundary_mask > lim->max_segment_size - 1)
+		seg_size = lim->max_segment_size;
+	else
+		seg_size = lim->seg_boundary_mask + 1;
+	lim->min_segment_size = min_t(unsigned int, seg_size, PAGE_SIZE);
+
 	/*
 	 * We require drivers to at least do logical block aligned I/O, but
 	 * historically could not check for that due to the separate calls
diff --git a/block/blk.h b/block/blk.h
index 90fa5f28ccabf..9cf9a0099416d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -14,6 +14,7 @@
 struct elevator_type;
 
 #define	BLK_DEV_MAX_SECTORS	(LLONG_MAX >> 9)
+#define	BLK_MIN_SEGMENT_SIZE	4096
 
 /* Max future timer expiry for timeouts */
 #define BLK_MAX_TIMEOUT		(5 * HZ)
@@ -358,8 +359,12 @@ struct bio *bio_split_zone_append(struct bio *bio,
 static inline bool bio_may_need_split(struct bio *bio,
 		const struct queue_limits *lim)
 {
-	return lim->chunk_sectors || bio->bi_vcnt != 1 ||
-		bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset > PAGE_SIZE;
+	if (lim->chunk_sectors)
+		return true;
+	if (bio->bi_vcnt != 1)
+		return true;
+	return bio->bi_io_vec->bv_len + bio->bi_io_vec->bv_offset >
+		lim->min_segment_size;
 }
 
 /**
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 248416ecd01c9..58ff5aca83b67 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -367,6 +367,7 @@ struct queue_limits {
 	unsigned int		max_sectors;
 	unsigned int		max_user_sectors;
 	unsigned int		max_segment_size;
+	unsigned int		min_segment_size;
 	unsigned int		physical_block_size;
 	unsigned int		logical_block_size;
 	unsigned int		alignment_offset;

From 9e7c6779e3530bbdd465214afcd13f19c33e51a2 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 25 Feb 2025 16:45:32 +0100
Subject: [PATCH 1111/2753] ALSA: hda/realtek: Fix wrong mic setup for ASUS
 VivoBook 15

ASUS VivoBook 15 with SSID 1043:1460 took an incorrect quirk via the
pin pattern matching for ASUS (ALC256_FIXUP_ASUS_MIC), resulting in
the two built-in mic pins (0x13 and 0x1b).  This had worked without
problems casually in the past because the right pin (0x1b) was picked
up as the primary device.  But since we fixed the pin enumeration for
other bugs, the bogus one (0x13) is picked up as the primary device,
hence the bug surfaced now.

For addressing the regression, this patch explicitly specifies the
quirk entry with ALC256_FIXUP_ASUS_MIC_NO_PRESENCE, which sets up only
the headset mic pin.

Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219807
Link: https://patch.msgid.link/20250225154540.13543-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 224616fbec4fa..e5c80d4be535c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10623,6 +10623,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x13b0, "ASUS Z550SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1427, "Asus Zenbook UX31E", ALC269VB_FIXUP_ASUS_ZENBOOK),
 	SND_PCI_QUIRK(0x1043, 0x1433, "ASUS GX650PY/PZ/PV/PU/PYV/PZV/PIV/PVV", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
+	SND_PCI_QUIRK(0x1043, 0x1460, "Asus VivoBook 15", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1463, "Asus GA402X/GA402N", ALC285_FIXUP_ASUS_I2C_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1473, "ASUS GU604VI/VC/VE/VG/VJ/VQ/VU/VV/VY/VZ", ALC285_FIXUP_ASUS_HEADSET_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1483, "ASUS GU603VQ/VU/VV/VJ/VI", ALC285_FIXUP_ASUS_HEADSET_MIC),

From f00db31d235946853fb430de8c6aa1295efc8353 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Tue, 25 Feb 2025 14:44:40 +0100
Subject: [PATCH 1112/2753] Revert "arm64: dts: qcom: sdm845: Affirm IDR0.CCTW
 on apps_smmu"

There are reports that the pagetable walker cache coherency is not a
given across the spectrum of SDM845/850 devices, leading to lock-ups
and resets. It works fine on some devices (like the Dragonboard 845c,
but not so much on the Lenovo Yoga C630).

This unfortunately looks like a fluke in firmware development, where
likely somewhere in the vast hypervisor stack, a change to accommodate
for this was only introduced after the initial software release (which
often serves as a baseline for products).

Revert the change to avoid additional guesswork around crashes.

This reverts commit 6b31a9744b8726c69bb0af290f8475a368a4b805.

Reported-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Closes: https://lore.kernel.org/linux-arm-msm/20250215-yoga-dma-coherent-v1-1-2419ee184a81@linaro.org/
Fixes: 6b31a9744b87 ("arm64: dts: qcom: sdm845: Affirm IDR0.CCTW on apps_smmu")
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250225-topic-845_smmu_not_coherent-v1-1-98ca9d17471c@oss.qualcomm.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 arch/arm64/boot/dts/qcom/sdm845.dtsi | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
index e0ce804bb1a35..d0314cdf0b92f 100644
--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
+++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
@@ -5163,7 +5163,6 @@
 				     <GIC_SPI 341 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 342 IRQ_TYPE_LEVEL_HIGH>,
 				     <GIC_SPI 343 IRQ_TYPE_LEVEL_HIGH>;
-			dma-coherent;
 		};
 
 		anoc_1_tbu: tbu@150c5000 {

From 6ebf05189dfc6d0d597c99a6448a4d1064439a18 Mon Sep 17 00:00:00 2001
From: Pavel Begunkov <asml.silence@gmail.com>
Date: Tue, 25 Feb 2025 15:59:02 +0000
Subject: [PATCH 1113/2753] io_uring/net: save msg_control for compat

Match the compat part of io_sendmsg_copy_hdr() with its counterpart and
save msg_control.

Fixes: c55978024d123 ("io_uring/net: move receive multishot out of the generic msghdr path")
Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/2a8418821fe83d3b64350ad2b3c0303e9b732bbd.1740498502.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/net.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/io_uring/net.c b/io_uring/net.c
index 17852a6616ffe..5d0b56ff50eed 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -322,7 +322,9 @@ static int io_sendmsg_copy_hdr(struct io_kiocb *req,
 		if (unlikely(ret))
 			return ret;
 
-		return __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+		ret = __get_compat_msghdr(&iomsg->msg, &cmsg, NULL);
+		sr->msg_control = iomsg->msg.msg_control_user;
+		return ret;
 	}
 #endif
 

From 709329c48214ad2acf12eed1b5c0eb798e40a64c Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 24 Feb 2025 22:59:34 -0800
Subject: [PATCH 1114/2753] Input: xpad - add support for ZOTAC Gaming Zone

ZOTAC Gaming Zone is ZOTAC's 2024 handheld release. As it is common
with these handhelds, it uses a hybrid USB device with an xpad
endpoint, a keyboard endpoint, and a vendor-specific endpoint for
RGB control et al.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250222170010.188761-2-lkml@antheas.dev
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 16493235bf9ee..29d7e6eb51cf0 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -349,6 +349,7 @@ static const struct xpad_device {
 	{ 0x1bad, 0xfa01, "MadCatz GamePad", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0xfd00, "Razer Onza TE", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0xfd01, "Razer Onza", 0, XTYPE_XBOX360 },
+	{ 0x1ee9, 0x1590, "ZOTAC Gaming Zone", 0, XTYPE_XBOX360 },
 	{ 0x20d6, 0x2001, "BDA Xbox Series X Wired Controller", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x2009, "PowerA Enhanced Wired Controller for Xbox Series X|S", 0, XTYPE_XBOXONE },
 	{ 0x20d6, 0x281f, "PowerA Wired Controller For Xbox 360", 0, XTYPE_XBOX360 },
@@ -538,6 +539,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
 	XPAD_XBOX360_VENDOR(0x1a86),		/* QH Electronics */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
+	XPAD_XBOX360_VENDOR(0x1ee9),		/* ZOTAC Technology Limited */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOXONE_VENDOR(0x20d6),		/* PowerA controllers */
 	XPAD_XBOX360_VENDOR(0x2345),		/* Machenike Controllers */

From 95a54a96f657fd069d2a9922b6c2d293a72a001f Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 24 Feb 2025 23:00:29 -0800
Subject: [PATCH 1115/2753] Input: xpad - add support for TECNO Pocket Go

TECNO Pocket Go is a kickstarter handheld by manufacturer TECNO Mobile.
It poses a unique feature: it does not have a display. Instead, the
handheld is essentially a pc in a controller. As customary, it has an
xpad endpoint, a keyboard endpoint, and a vendor endpoint for its
vendor software.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250222170010.188761-3-lkml@antheas.dev
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 29d7e6eb51cf0..79e1c8f1f99c2 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -382,6 +382,7 @@ static const struct xpad_device {
 	{ 0x2563, 0x058d, "OneXPlayer Gamepad", 0, XTYPE_XBOX360 },
 	{ 0x294b, 0x3303, "Snakebyte GAMEPAD BASE X", 0, XTYPE_XBOXONE },
 	{ 0x294b, 0x3404, "Snakebyte GAMEPAD RGB X", 0, XTYPE_XBOXONE },
+	{ 0x2993, 0x2001, "TECNO Pocket Go", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x2000, "8BitDo Pro 2 Wired Controller fox Xbox", 0, XTYPE_XBOXONE },
 	{ 0x2dc8, 0x3106, "8BitDo Ultimate Wireless / Pro 2 Wired Controller", 0, XTYPE_XBOX360 },
 	{ 0x2dc8, 0x3109, "8BitDo Ultimate Wireless Bluetooth", 0, XTYPE_XBOX360 },
@@ -548,6 +549,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x2563),		/* OneXPlayer Gamepad */
 	XPAD_XBOX360_VENDOR(0x260d),		/* Dareu H101 */
 	XPAD_XBOXONE_VENDOR(0x294b),		/* Snakebyte */
+	XPAD_XBOX360_VENDOR(0x2993),		/* TECNO Mobile */
 	XPAD_XBOX360_VENDOR(0x2c22),		/* Qanba Controllers */
 	XPAD_XBOX360_VENDOR(0x2dc8),		/* 8BitDo Controllers */
 	XPAD_XBOXONE_VENDOR(0x2dc8),		/* 8BitDo Controllers */

From 659a7614dd72e2835ac0b220c2fa68fabd8d1df9 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Mon, 24 Feb 2025 23:01:55 -0800
Subject: [PATCH 1116/2753] Input: xpad - rename QH controller to Legion Go S

The QH controller is actually the controller of the Legion Go S, with
the manufacturer string wch.cn and product name Legion Go S in its
USB descriptor. A cursory lookup of the VID reveals the same.

Therefore, rename the xpad entries to match.

Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://lore.kernel.org/r/20250222170010.188761-4-lkml@antheas.dev
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/joystick/xpad.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/input/joystick/xpad.c b/drivers/input/joystick/xpad.c
index 79e1c8f1f99c2..c33e6f33265ba 100644
--- a/drivers/input/joystick/xpad.c
+++ b/drivers/input/joystick/xpad.c
@@ -312,7 +312,7 @@ static const struct xpad_device {
 	{ 0x1689, 0xfe00, "Razer Sabertooth", 0, XTYPE_XBOX360 },
 	{ 0x17ef, 0x6182, "Lenovo Legion Controller for Windows", 0, XTYPE_XBOX360 },
 	{ 0x1949, 0x041a, "Amazon Game Controller", 0, XTYPE_XBOX360 },
-	{ 0x1a86, 0xe310, "QH Electronics Controller", 0, XTYPE_XBOX360 },
+	{ 0x1a86, 0xe310, "Legion Go S", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0002, "Harmonix Rock Band Guitar", 0, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0003, "Harmonix Rock Band Drumkit", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
 	{ 0x1bad, 0x0130, "Ion Drum Rocker", MAP_DPAD_TO_BUTTONS, XTYPE_XBOX360 },
@@ -538,7 +538,7 @@ static const struct usb_device_id xpad_table[] = {
 	XPAD_XBOX360_VENDOR(0x1689),		/* Razer Onza */
 	XPAD_XBOX360_VENDOR(0x17ef),		/* Lenovo */
 	XPAD_XBOX360_VENDOR(0x1949),		/* Amazon controllers */
-	XPAD_XBOX360_VENDOR(0x1a86),		/* QH Electronics */
+	XPAD_XBOX360_VENDOR(0x1a86),		/* Nanjing Qinheng Microelectronics (WCH) */
 	XPAD_XBOX360_VENDOR(0x1bad),		/* Harmonix Rock Band guitar and drums */
 	XPAD_XBOX360_VENDOR(0x1ee9),		/* ZOTAC Technology Limited */
 	XPAD_XBOX360_VENDOR(0x20d6),		/* PowerA controllers */

From 68283c1cb573143c0b7515e93206f3503616bc10 Mon Sep 17 00:00:00 2001
From: Artur Weber <aweber.kernel@gmail.com>
Date: Fri, 7 Feb 2025 21:02:41 +0100
Subject: [PATCH 1117/2753] pinctrl: bcm281xx: Fix incorrect regmap
 max_registers value

The max_registers value does not take into consideration the stride;
currently, it's set to the number of the last pin, but this does not
accurately represent the final register.

Fix this by multiplying the current value by 4.

Fixes: 54b1aa5a5b16 ("ARM: pinctrl: Add Broadcom Capri pinctrl driver")
Signed-off-by: Artur Weber <aweber.kernel@gmail.com>
Link: https://lore.kernel.org/20250207-bcm21664-pinctrl-v1-2-e7cfac9b2d3b@gmail.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/bcm/pinctrl-bcm281xx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
index 73dbf29c002f3..cf6efa9c0364a 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm281xx.c
@@ -974,7 +974,7 @@ static const struct regmap_config bcm281xx_pinctrl_regmap_config = {
 	.reg_bits = 32,
 	.reg_stride = 4,
 	.val_bits = 32,
-	.max_register = BCM281XX_PIN_VC_CAM3_SDA,
+	.max_register = BCM281XX_PIN_VC_CAM3_SDA * 4,
 };
 
 static int bcm281xx_pinctrl_get_groups_count(struct pinctrl_dev *pctldev)

From acf40ab42799e4ae1397ee6f5c5941092d66f999 Mon Sep 17 00:00:00 2001
From: Charles Han <hanchunchao@inspur.com>
Date: Wed, 12 Feb 2025 18:05:32 +0800
Subject: [PATCH 1118/2753] pinctrl: nuvoton: npcm8xx: Add NULL check in
 npcm8xx_gpio_fw

devm_kasprintf() calls can return null pointers on failure.
But the return values were not checked in npcm8xx_gpio_fw().
Add NULL check in npcm8xx_gpio_fw(), to handle kernel NULL
pointer dereference error.

Fixes: acf4884a5717 ("pinctrl: nuvoton: add NPCM8XX pinctrl and GPIO driver")
Signed-off-by: Charles Han <hanchunchao@inspur.com>
Link: https://lore.kernel.org/20250212100532.4317-1-hanchunchao@inspur.com
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c b/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
index 471f644c5eef2..d09a5e9b2eca5 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-npcm8xx.c
@@ -2374,6 +2374,9 @@ static int npcm8xx_gpio_fw(struct npcm8xx_pinctrl *pctrl)
 		pctrl->gpio_bank[id].gc.parent = dev;
 		pctrl->gpio_bank[id].gc.fwnode = child;
 		pctrl->gpio_bank[id].gc.label = devm_kasprintf(dev, GFP_KERNEL, "%pfw", child);
+		if (pctrl->gpio_bank[id].gc.label == NULL)
+			return -ENOMEM;
+
 		pctrl->gpio_bank[id].gc.dbg_show = npcmgpio_dbg_show;
 		pctrl->gpio_bank[id].direction_input = pctrl->gpio_bank[id].gc.direction_input;
 		pctrl->gpio_bank[id].gc.direction_input = npcmgpio_direction_input;

From 7ff4faba63571c51004280f7eb5d6362b15ec61f Mon Sep 17 00:00:00 2001
From: Yixun Lan <dlan@gentoo.org>
Date: Tue, 18 Feb 2025 08:31:44 +0800
Subject: [PATCH 1119/2753] pinctrl: spacemit: enable config option

Pinctrl is an essential driver for SpacemiT's SoC,
The uart driver requires it, same as sd card driver,
so let's enable it by default for this SoC.

The CONFIG_PINCTRL_SPACEMIT_K1 isn't enabled when using
'make defconfig' to select kernel configuration options.
This result in a broken uart driver where fail at probe()
stage due to no pins found.

Fixes: a83c29e1d145 ("pinctrl: spacemit: add support for SpacemiT K1 SoC")
Reported-by: Alex Elder <elder@kernel.org>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Tested-by: Alex Elder <elder@riscstar.com>
Signed-off-by: Yixun Lan <dlan@gentoo.org>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Tested-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://lore.kernel.org/20250218-k1-pinctrl-option-v3-1-36e031e0da1b@gentoo.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 arch/riscv/Kconfig.socs               | 1 +
 drivers/pinctrl/spacemit/Kconfig      | 3 ++-
 drivers/pinctrl/spacemit/pinctrl-k1.c | 2 +-
 3 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/riscv/Kconfig.socs b/arch/riscv/Kconfig.socs
index 1916cf7ba450e..17606940bb523 100644
--- a/arch/riscv/Kconfig.socs
+++ b/arch/riscv/Kconfig.socs
@@ -26,6 +26,7 @@ config ARCH_SOPHGO
 
 config ARCH_SPACEMIT
 	bool "SpacemiT SoCs"
+	select PINCTRL
 	help
 	  This enables support for SpacemiT SoC platform hardware.
 
diff --git a/drivers/pinctrl/spacemit/Kconfig b/drivers/pinctrl/spacemit/Kconfig
index 168f8a5ffbb95..a2f98b3f8a755 100644
--- a/drivers/pinctrl/spacemit/Kconfig
+++ b/drivers/pinctrl/spacemit/Kconfig
@@ -4,9 +4,10 @@
 #
 
 config PINCTRL_SPACEMIT_K1
-	tristate "SpacemiT K1 SoC Pinctrl driver"
+	bool "SpacemiT K1 SoC Pinctrl driver"
 	depends on ARCH_SPACEMIT || COMPILE_TEST
 	depends on OF
+	default y
 	select GENERIC_PINCTRL_GROUPS
 	select GENERIC_PINMUX_FUNCTIONS
 	select GENERIC_PINCONF
diff --git a/drivers/pinctrl/spacemit/pinctrl-k1.c b/drivers/pinctrl/spacemit/pinctrl-k1.c
index a32579d736130..59fd555ff38d4 100644
--- a/drivers/pinctrl/spacemit/pinctrl-k1.c
+++ b/drivers/pinctrl/spacemit/pinctrl-k1.c
@@ -1044,7 +1044,7 @@ static struct platform_driver k1_pinctrl_driver = {
 		.of_match_table		= k1_pinctrl_ids,
 	},
 };
-module_platform_driver(k1_pinctrl_driver);
+builtin_platform_driver(k1_pinctrl_driver);
 
 MODULE_AUTHOR("Yixun Lan <dlan@gentoo.org>");
 MODULE_DESCRIPTION("Pinctrl driver for the SpacemiT K1 SoC");

From 00817f0f1c45b007965f5676b9a2013bb39c7228 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Mon, 24 Feb 2025 17:13:30 -0800
Subject: [PATCH 1120/2753] nvme-ioctl: fix leaked requests on mapping error

All the callers assume nvme_map_user_request() frees the request on a
failure. This wasn't happening on invalid metadata or io_uring command
flags, so we've been leaking those requests.

Fixes: 23fd22e55b767b ("nvme: wire up fixed buffer support for nvme passthrough")
Fixes: 7c2fd76048e95d ("nvme: fix metadata handling in nvme-passthrough")
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Kanchan Joshi <joshi.k@samsung.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/ioctl.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index b1b46c2713e1c..24e2c702da7a2 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -128,8 +128,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 	if (!nvme_ctrl_sgl_supported(ctrl))
 		dev_warn_once(ctrl->device, "using unchecked data buffer\n");
 	if (has_metadata) {
-		if (!supports_metadata)
-			return -EINVAL;
+		if (!supports_metadata) {
+			ret = -EINVAL;
+			goto out;
+		}
 		if (!nvme_ctrl_meta_sgl_supported(ctrl))
 			dev_warn_once(ctrl->device,
 				      "using unchecked metadata buffer\n");
@@ -139,8 +141,10 @@ static int nvme_map_user_request(struct request *req, u64 ubuffer,
 		struct iov_iter iter;
 
 		/* fixedbufs is only for non-vectored io */
-		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC))
-			return -EINVAL;
+		if (WARN_ON_ONCE(flags & NVME_IOCTL_VEC)) {
+			ret = -EINVAL;
+			goto out;
+		}
 		ret = io_uring_cmd_import_fixed(ubuffer, bufflen,
 				rq_data_dir(req), &iter, ioucmd);
 		if (ret < 0)

From 91dcc66b34beb72dde8412421bdc1b4cd40e4fb8 Mon Sep 17 00:00:00 2001
From: "chr[]" <chris@rudorff.com>
Date: Wed, 12 Feb 2025 16:51:38 +0100
Subject: [PATCH 1121/2753] amdgpu/pm/legacy: fix suspend/resume issues

resume and irq handler happily races in set_power_state()

* amdgpu_legacy_dpm_compute_clocks() needs lock
* protect irq work handler
* fix dpm_enabled usage

v2: fix clang build, integrate Lijo's comments (Alex)

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2524
Fixes: 3712e7a49459 ("drm/amd/pm: unified lock protections in amdgpu_dpm.c")
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Tested-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name> # on Oland PRO
Signed-off-by: chr[] <chris@rudorff.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ee3dc9e204d271c9c7a8d4d38a0bce4745d33e71)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c    | 25 +++++++++++++-----
 .../gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c    |  8 ++++--
 drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c    | 26 ++++++++++++++-----
 3 files changed, 45 insertions(+), 14 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
index 67a8e22b1126d..e237ea1185a71 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
@@ -3042,6 +3042,7 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	kv_dpm_setup_asic(adev);
 	ret = kv_dpm_enable(adev);
 	if (ret)
@@ -3049,6 +3050,8 @@ static int kv_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
+
 	return ret;
 }
 
@@ -3066,32 +3069,42 @@ static int kv_dpm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		kv_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
 	return 0;
 }
 
 static int kv_dpm_resume(struct amdgpu_ip_block *ip_block)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
 		/* asic init will reset to the boot state */
 		kv_dpm_setup_asic(adev);
 		ret = kv_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+	return ret;
 }
 
 static bool kv_dpm_is_idle(void *handle)
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
index e861355ebd75b..c7518b13e7879 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
@@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
 	int temp, size = sizeof(temp);
 
-	if (!adev->pm.dpm_enabled)
-		return;
+	mutex_lock(&adev->pm.mutex);
 
+	if (!adev->pm.dpm_enabled) {
+		mutex_unlock(&adev->pm.mutex);
+		return;
+	}
 	if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
 				   AMDGPU_PP_SENSOR_GPU_TEMP,
 				   (void *)&temp,
@@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(struct work_struct *work)
 	adev->pm.dpm.state = dpm_state;
 
 	amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
+	mutex_unlock(&adev->pm.mutex);
 }
diff --git a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
index a87dcf0974bc1..d6dfe2599ebea 100644
--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
@@ -7786,6 +7786,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	if (!amdgpu_dpm)
 		return 0;
 
+	mutex_lock(&adev->pm.mutex);
 	si_dpm_setup_asic(adev);
 	ret = si_dpm_enable(adev);
 	if (ret)
@@ -7793,6 +7794,7 @@ static int si_dpm_hw_init(struct amdgpu_ip_block *ip_block)
 	else
 		adev->pm.dpm_enabled = true;
 	amdgpu_legacy_dpm_compute_clocks(adev);
+	mutex_unlock(&adev->pm.mutex);
 	return ret;
 }
 
@@ -7810,32 +7812,44 @@ static int si_dpm_suspend(struct amdgpu_ip_block *ip_block)
 {
 	struct amdgpu_device *adev = ip_block->adev;
 
+	cancel_work_sync(&adev->pm.dpm.thermal.work);
+
 	if (adev->pm.dpm_enabled) {
+		mutex_lock(&adev->pm.mutex);
+		adev->pm.dpm_enabled = false;
 		/* disable dpm */
 		si_dpm_disable(adev);
 		/* reset the power state */
 		adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
+		mutex_unlock(&adev->pm.mutex);
 	}
+
 	return 0;
 }
 
 static int si_dpm_resume(struct amdgpu_ip_block *ip_block)
 {
-	int ret;
+	int ret = 0;
 	struct amdgpu_device *adev = ip_block->adev;
 
-	if (adev->pm.dpm_enabled) {
+	if (!amdgpu_dpm)
+		return 0;
+
+	if (!adev->pm.dpm_enabled) {
 		/* asic init will reset to the boot state */
+		mutex_lock(&adev->pm.mutex);
 		si_dpm_setup_asic(adev);
 		ret = si_dpm_enable(adev);
-		if (ret)
+		if (ret) {
 			adev->pm.dpm_enabled = false;
-		else
+		} else {
 			adev->pm.dpm_enabled = true;
-		if (adev->pm.dpm_enabled)
 			amdgpu_legacy_dpm_compute_clocks(adev);
+		}
+		mutex_unlock(&adev->pm.mutex);
 	}
-	return 0;
+
+	return ret;
 }
 
 static bool si_dpm_is_idle(void *handle)

From 3502ab5022bb5ef1edd063bdb6465a8bf3b46e66 Mon Sep 17 00:00:00 2001
From: David Yat Sin <David.YatSin@amd.com>
Date: Wed, 19 Feb 2025 17:34:38 -0500
Subject: [PATCH 1122/2753] drm/amdkfd: Preserve cp_hqd_pq_control on
 update_mqd

When userspace applications call AMDKFD_IOC_UPDATE_QUEUE. Preserve
bitfields that do not need to be modified as they contain flags to
track queue states that are used by CP FW.

Signed-off-by: David Yat Sin <David.YatSin@amd.com>
Reviewed-by: Jay Cornwall <jay.cornwall@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 8150827990b709ab5a40c46c30d21b7f7b9e9440)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c | 6 ++++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 5 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c | 5 +++--
 drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c  | 5 ++++-
 4 files changed, 14 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
index 2eff37aaf8273..1695dd78ede8e 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v10.c
@@ -107,6 +107,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -167,10 +169,10 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
index 68dbc0399c87a..3c0ae28c5923b 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c
@@ -154,6 +154,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -221,10 +223,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
index 2b72d5b4949b6..565858b9044d4 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v12.c
@@ -121,6 +121,8 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x55 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -184,10 +186,9 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |=
 			ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1;
-	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 
 	m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
index ff417d5361c42..3014925d95ffc 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
@@ -183,6 +183,9 @@ static void init_mqd(struct mqd_manager *mm, void **mqd,
 	m->cp_hqd_persistent_state = CP_HQD_PERSISTENT_STATE__PRELOAD_REQ_MASK |
 			0x53 << CP_HQD_PERSISTENT_STATE__PRELOAD_SIZE__SHIFT;
 
+	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK;
+
 	m->cp_mqd_control = 1 << CP_MQD_CONTROL__PRIV_STATE__SHIFT;
 
 	m->cp_mqd_base_addr_lo        = lower_32_bits(addr);
@@ -245,7 +248,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd,
 
 	m = get_mqd(mqd);
 
-	m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT;
+	m->cp_hqd_pq_control &= ~CP_HQD_PQ_CONTROL__QUEUE_SIZE_MASK;
 	m->cp_hqd_pq_control |= order_base_2(q->queue_size / 4) - 1;
 	pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control);
 

From 099bffc7cadff40bfab1517c3461c53a7a38a0d7 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Mon, 17 Feb 2025 10:55:05 -0500
Subject: [PATCH 1123/2753] drm/amdgpu: disable BAR resize on Dell G5 SE

There was a quirk added to add a workaround for a Sapphire
RX 5600 XT Pulse that didn't allow BAR resizing.  However,
the quirk caused a regression with runtime pm on Dell laptops
using those chips, rather than narrowing the scope of the
resizing quirk, add a quirk to prevent amdgpu from resizing
the BAR on those Dell platforms unless runtime pm is disabled.

v2: update commit message, add runpm check

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/1707
Fixes: 907830b0fc9e ("PCI: Add a REBAR size quirk for Sapphire RX 5600 XT Pulse")
Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5235053f443cef4210606e5fb71f99b915a9723d)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d100bb7a137cd..018dfccd771ba 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1638,6 +1638,13 @@ int amdgpu_device_resize_fb_bar(struct amdgpu_device *adev)
 	if (amdgpu_sriov_vf(adev))
 		return 0;
 
+	/* resizing on Dell G5 SE platforms causes problems with runtime pm */
+	if ((amdgpu_runtime_pm != 0) &&
+	    adev->pdev->vendor == PCI_VENDOR_ID_ATI &&
+	    adev->pdev->device == 0x731f &&
+	    adev->pdev->subsystem_vendor == PCI_VENDOR_ID_DELL)
+		return 0;
+
 	/* PCI_EXT_CAP_ID_VNDR extended capability is located at 0x100 */
 	if (!pci_find_ext_capability(adev->pdev, PCI_EXT_CAP_ID_VNDR))
 		DRM_WARN("System can't access extended configuration space, please check!!\n");

From 8005351c7d53c31fb7eb5a423da7ab4bc3ad7639 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Tue, 11 Feb 2025 15:38:20 -0500
Subject: [PATCH 1124/2753] MAINTAINERS: update amdgpu maintainers list
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Xinhui's email is no longer valid.

Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit c19390ca9094dfcbc16d96b233a409c01e21d85b)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 4ff26fa94895d..d6ea828345fdb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19657,7 +19657,6 @@ F:	drivers/net/wireless/quantenna
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
 M:	Christian König <christian.koenig@amd.com>
-M:	Xinhui Pan <Xinhui.Pan@amd.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 B:	https://gitlab.freedesktop.org/drm/amd/-/issues

From e7ea88207cef513514e706aacc534527ac88b9b8 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Thu, 13 Feb 2025 13:37:01 -0500
Subject: [PATCH 1125/2753] drm/amdgpu/gfx: only call mes for enforce isolation
 if supported

This should not be called on chips without MES so check if
MES is enabled and if the cleaner shader is supported.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Reviewed-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Cc: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
(cherry picked from commit 80513e389765c8f9543b26d8fa4bbdf0e59ff8bc)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index 784b03abb3a43..c6aff3ddb42d7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1643,11 +1643,13 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 		if (adev->enforce_isolation[i] && !partition_values[i]) {
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, false);
+			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
+				amdgpu_mes_set_enforce_isolation(adev, i, false);
 		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-			amdgpu_mes_set_enforce_isolation(adev, i, true);
+			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
+				amdgpu_mes_set_enforce_isolation(adev, i, true);
 		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}

From 748a1f51bb74453f1fe22d3ca68a717cb31f02e5 Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Fri, 14 Feb 2025 12:32:30 -0500
Subject: [PATCH 1126/2753] drm/amdgpu/mes: keep enforce isolation up to date

Re-send the mes message on resume to make sure the
mes state is up to date.

Fixes: 8521e3c5f058 ("drm/amd/amdgpu: limit single process inside MES")
Acked-by: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Cc: Shaoyun Liu <shaoyun.liu@amd.com>
Cc: Srinivasan Shanmugam <srinivasan.shanmugam@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 27b791514789844e80da990c456c2465325e0851)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 13 ++++---------
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c | 20 +++++++++++++++++++-
 drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h |  2 +-
 drivers/gpu/drm/amd/amdgpu/mes_v11_0.c  |  4 ++++
 drivers/gpu/drm/amd/amdgpu/mes_v12_0.c  |  4 ++++
 5 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
index c6aff3ddb42d7..c1f35ded684e8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
@@ -1638,24 +1638,19 @@ static ssize_t amdgpu_gfx_set_enforce_isolation(struct device *dev,
 	}
 
 	mutex_lock(&adev->enforce_isolation_mutex);
-
 	for (i = 0; i < num_partitions; i++) {
-		if (adev->enforce_isolation[i] && !partition_values[i]) {
+		if (adev->enforce_isolation[i] && !partition_values[i])
 			/* Going from enabled to disabled */
 			amdgpu_vmid_free_reserved(adev, AMDGPU_GFXHUB(i));
-			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
-				amdgpu_mes_set_enforce_isolation(adev, i, false);
-		} else if (!adev->enforce_isolation[i] && partition_values[i]) {
+		else if (!adev->enforce_isolation[i] && partition_values[i])
 			/* Going from disabled to enabled */
 			amdgpu_vmid_alloc_reserved(adev, AMDGPU_GFXHUB(i));
-			if (adev->enable_mes && adev->gfx.enable_cleaner_shader)
-				amdgpu_mes_set_enforce_isolation(adev, i, true);
-		}
 		adev->enforce_isolation[i] = partition_values[i];
 	}
-
 	mutex_unlock(&adev->enforce_isolation_mutex);
 
+	amdgpu_mes_update_enforce_isolation(adev);
+
 	return count;
 }
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
index 32b27a1658e78..709c11cbeabd8 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.c
@@ -1681,7 +1681,8 @@ bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev)
 }
 
 /* Fix me -- node_id is used to identify the correct MES instances in the future */
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable)
+static int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev,
+					    uint32_t node_id, bool enable)
 {
 	struct mes_misc_op_input op_input = {0};
 	int r;
@@ -1703,6 +1704,23 @@ int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_i
 	return r;
 }
 
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev)
+{
+	int i, r = 0;
+
+	if (adev->enable_mes && adev->gfx.enable_cleaner_shader) {
+		mutex_lock(&adev->enforce_isolation_mutex);
+		for (i = 0; i < (adev->xcp_mgr ? adev->xcp_mgr->num_xcps : 1); i++) {
+			if (adev->enforce_isolation[i])
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, true);
+			else
+				r |= amdgpu_mes_set_enforce_isolation(adev, i, false);
+		}
+		mutex_unlock(&adev->enforce_isolation_mutex);
+	}
+	return r;
+}
+
 #if defined(CONFIG_DEBUG_FS)
 
 static int amdgpu_debugfs_mes_event_log_show(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
index 2df2444ee892c..e98ea7ede1bab 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mes.h
@@ -534,6 +534,6 @@ static inline void amdgpu_mes_unlock(struct amdgpu_mes *mes)
 
 bool amdgpu_mes_suspend_resume_all_supported(struct amdgpu_device *adev);
 
-int amdgpu_mes_set_enforce_isolation(struct amdgpu_device *adev, uint32_t node_id, bool enable);
+int amdgpu_mes_update_enforce_isolation(struct amdgpu_device *adev);
 
 #endif /* __AMDGPU_MES_H__ */
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
index 65f389eb65e5f..f9a4d08eef925 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
@@ -1633,6 +1633,10 @@ static int mes_v11_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.
diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
index 901e924e69ad9..0fd0fa6ed5184 100644
--- a/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/mes_v12_0.c
@@ -1743,6 +1743,10 @@ static int mes_v12_0_hw_init(struct amdgpu_ip_block *ip_block)
 		goto failure;
 	}
 
+	r = amdgpu_mes_update_enforce_isolation(adev);
+	if (r)
+		goto failure;
+
 out:
 	/*
 	 * Disable KIQ ring usage from the driver once MES is enabled.

From 733d675c2a436b416107893db87eb182585c1b39 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <siqueira@igalia.com>
Date: Wed, 19 Feb 2025 11:46:19 -0700
Subject: [PATCH 1127/2753] MAINTAINERS: Change my role from Maintainer to
 Reviewer

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 9b3ef540397cfc356f10f504841b2e9d16e31286)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index d6ea828345fdb..f3fdc43bdd497 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1046,7 +1046,7 @@ F:	drivers/crypto/ccp/hsti.*
 AMD DISPLAY CORE
 M:	Harry Wentland <harry.wentland@amd.com>
 M:	Leo Li <sunpeng.li@amd.com>
-M:	Rodrigo Siqueira <Rodrigo.Siqueira@amd.com>
+R:	Rodrigo Siqueira <siqueira@igalia.com>
 L:	amd-gfx@lists.freedesktop.org
 S:	Supported
 T:	git https://gitlab.freedesktop.org/agd5f/linux.git

From 96989f3dca6f51f202b6dbc92c37e17df6ca12f4 Mon Sep 17 00:00:00 2001
From: Rodrigo Siqueira <siqueira@igalia.com>
Date: Wed, 19 Feb 2025 11:46:20 -0700
Subject: [PATCH 1128/2753] mailmap: Add entry for Rodrigo Siqueira

Map all of my previously used email addresses to my @igalia.com address.

Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Rodrigo Siqueira <siqueira@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 289387d0dbf806bd59063ab93d94f48cd4c75c7c)
Cc: stable@vger.kernel.org
---
 .mailmap | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..ec18b01f0be2a 100644
--- a/.mailmap
+++ b/.mailmap
@@ -613,6 +613,8 @@ Richard Leitner <richard.leitner@linux.dev> <me@g0hl1n.net>
 Richard Leitner <richard.leitner@linux.dev> <richard.leitner@skidata.com>
 Robert Foss <rfoss@kernel.org> <robert.foss@linaro.org>
 Rocky Liao <quic_rjliao@quicinc.com> <rjliao@codeaurora.org>
+Rodrigo Siqueira <siqueira@igalia.com> <rodrigosiqueiramelo@gmail.com>
+Rodrigo Siqueira <siqueira@igalia.com> <Rodrigo.Siqueira@amd.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guro@fb.com>
 Roman Gushchin <roman.gushchin@linux.dev> <guroan@gmail.com>
 Roman Gushchin <roman.gushchin@linux.dev> <klamm@yandex-team.ru>

From 12f3b92d1cfa5526715fff93a6d6fe29300d5e2a Mon Sep 17 00:00:00 2001
From: Melissa Wen <mwen@igalia.com>
Date: Sat, 15 Feb 2025 18:15:47 -0300
Subject: [PATCH 1129/2753] drm/amd/display: restore edid reading from a given
 i2c adapter

When switching to drm_edid, we slightly changed how to get edid by
removing the possibility of getting them from dc_link when in aux
transaction mode. As MST doesn't initialize the connector with
`drm_connector_init_with_ddc()`, restore the original behavior to avoid
functional changes.

v2:
- Fix build warning of unchecked dereference (kernel test bot)

CC: Alex Hung <alex.hung@amd.com>
CC: Mario Limonciello <mario.limonciello@amd.com>
CC: Roman Li <Roman.Li@amd.com>
CC: Aurabindo Pillai <Aurabindo.Pillai@amd.com>
Fixes: 48edb2a4256e ("drm/amd/display: switch amdgpu_dm_connector to use struct drm_edid")
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Melissa Wen <mwen@igalia.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 81262b1656feb3813e3d917ab78824df6831e69e)
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c   | 17 +++++++++++++++--
 1 file changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index ac3fd81fecef2..5ddd21466e22f 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -7240,8 +7240,14 @@ static void amdgpu_dm_connector_funcs_force(struct drm_connector *connector)
 	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink *dc_em_sink = aconnector->dc_em_sink;
 	const struct drm_edid *drm_edid;
+	struct i2c_adapter *ddc;
 
-	drm_edid = drm_edid_read(connector);
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
+
+	drm_edid = drm_edid_read_ddc(connector, ddc);
 	drm_edid_connector_update(connector, drm_edid);
 	if (!drm_edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);
@@ -7286,14 +7292,21 @@ static int get_modes(struct drm_connector *connector)
 static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
 {
 	struct drm_connector *connector = &aconnector->base;
+	struct dc_link *dc_link = aconnector->dc_link;
 	struct dc_sink_init_data init_params = {
 			.link = aconnector->dc_link,
 			.sink_signal = SIGNAL_TYPE_VIRTUAL
 	};
 	const struct drm_edid *drm_edid;
 	const struct edid *edid;
+	struct i2c_adapter *ddc;
+
+	if (dc_link && dc_link->aux_mode)
+		ddc = &aconnector->dm_dp_aux.aux.ddc;
+	else
+		ddc = &aconnector->i2c->base;
 
-	drm_edid = drm_edid_read(connector);
+	drm_edid = drm_edid_read_ddc(connector, ddc);
 	drm_edid_connector_update(connector, drm_edid);
 	if (!drm_edid) {
 		DRM_ERROR("No EDID found on connector: %s.\n", connector->name);

From a04bf34e0829f2c5d5f1ea7317daae2efa560fd1 Mon Sep 17 00:00:00 2001
From: Aurabindo Pillai <aurabindo.pillai@amd.com>
Date: Fri, 21 Feb 2025 14:19:12 -0500
Subject: [PATCH 1130/2753] MAINTAINERS: Update AMDGPU DML maintainers info

Chaitanya is no longer with AMD, and the responsibility has been
taken over by Austin.

Signed-off-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a101fa705d016d46463dd4ce488671369c922bc2)
Cc: stable@vger.kernel.org
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index f3fdc43bdd497..95bce73f3ef44 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1053,7 +1053,7 @@ T:	git https://gitlab.freedesktop.org/agd5f/linux.git
 F:	drivers/gpu/drm/amd/display/
 
 AMD DISPLAY CORE - DML
-M:	Chaitanya Dhere <chaitanya.dhere@amd.com>
+M:	Austin Zheng <austin.zheng@amd.com>
 M:	Jun Lei <jun.lei@amd.com>
 S:	Supported
 F:	drivers/gpu/drm/amd/display/dc/dml/

From e8863f8b0316d8ee1e7e5291e8f2f72c91ac967d Mon Sep 17 00:00:00 2001
From: Tom Chung <chiahsuan.chung@amd.com>
Date: Thu, 6 Feb 2025 11:31:23 +0800
Subject: [PATCH 1131/2753] drm/amd/display: Disable PSR-SU on eDP panels

[Why]
PSR-SU may cause some glitching randomly on several panels.

[How]
Temporarily disable the PSR-SU and fallback to PSR1 for
all eDP panels.

Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3388
Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Sun peng Li <sunpeng.li@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Signed-off-by: Roman Li <roman.li@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 6deeefb820d0efb0b36753622fb982d03b37b3ad)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
index 45858bf1523d8..e140b7a04d724 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_psr.c
@@ -54,7 +54,8 @@ static bool link_supports_psrsu(struct dc_link *link)
 	if (amdgpu_dc_debug_mask & DC_DISABLE_PSR_SU)
 		return false;
 
-	return dc_dmub_check_min_version(dc->ctx->dmub_srv->dmub);
+	/* Temporarily disable PSR-SU to avoid glitches */
+	return false;
 }
 
 /*

From b5f7242e49b927cfe488b369fa552f2eff579ef1 Mon Sep 17 00:00:00 2001
From: Yilin Chen <Yilin.Chen@amd.com>
Date: Fri, 7 Feb 2025 15:26:19 -0500
Subject: [PATCH 1132/2753] drm/amd/display: add a quirk to enable eDP0 on DP1

[why]
some board designs have eDP0 connected to DP1, need a way to enable
support_edp0_on_dp1 flag, otherwise edp related features cannot work

[how]
do a dmi check during dm initialization to identify systems that
require support_edp0_on_dp1. Optimize quirk table with callback
functions to set quirk entries, retrieve_dmi_info can set quirks
according to quirk entries

Cc: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Nicholas Kazlauskas <nicholas.kazlauskas@amd.com>
Signed-off-by: Yilin Chen <Yilin.Chen@amd.com>
Signed-off-by: Zaeem Mohamed <zaeem.mohamed@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f6d17270d18a6a6753fff046330483d43f8405e4)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 69 +++++++++++++++++--
 1 file changed, 62 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 5ddd21466e22f..9d9645a2d18ef 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -1618,75 +1618,130 @@ static bool dm_should_disable_stutter(struct pci_dev *pdev)
 	return false;
 }
 
-static const struct dmi_system_id hpd_disconnect_quirk_table[] = {
+struct amdgpu_dm_quirks {
+	bool aux_hpd_discon;
+	bool support_edp0_on_dp1;
+};
+
+static struct amdgpu_dm_quirks quirk_entries = {
+	.aux_hpd_discon = false,
+	.support_edp0_on_dp1 = false
+};
+
+static int edp0_on_dp1_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.support_edp0_on_dp1 = true;
+	return 0;
+}
+
+static int aux_hpd_discon_callback(const struct dmi_system_id *id)
+{
+	quirk_entries.aux_hpd_discon = true;
+	return 0;
+}
+
+static const struct dmi_system_id dmi_quirk_table[] = {
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3660"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3260"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "Precision 3460"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Tower 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex SFF 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro Plus 7010"),
 		},
 	},
 	{
+		.callback = aux_hpd_discon_callback,
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
 			DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex Micro 7010"),
 		},
 	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP Elite mt645 G8 Mobile Thin Client"),
+		},
+	},
+	{
+		.callback = edp0_on_dp1_callback,
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "HP EliteBook 665 16 inch G11 Notebook PC"),
+		},
+	},
 	{}
 	/* TODO: refactor this from a fixed table to a dynamic option */
 };
 
-static void retrieve_dmi_info(struct amdgpu_display_manager *dm)
+static void retrieve_dmi_info(struct amdgpu_display_manager *dm, struct dc_init_data *init_data)
 {
-	const struct dmi_system_id *dmi_id;
+	int dmi_id;
+	struct drm_device *dev = dm->ddev;
 
 	dm->aux_hpd_discon_quirk = false;
+	init_data->flags.support_edp0_on_dp1 = false;
+
+	dmi_id = dmi_check_system(dmi_quirk_table);
 
-	dmi_id = dmi_first_match(hpd_disconnect_quirk_table);
-	if (dmi_id) {
+	if (!dmi_id)
+		return;
+
+	if (quirk_entries.aux_hpd_discon) {
 		dm->aux_hpd_discon_quirk = true;
-		DRM_INFO("aux_hpd_discon_quirk attached\n");
+		drm_info(dev, "aux_hpd_discon_quirk attached\n");
+	}
+	if (quirk_entries.support_edp0_on_dp1) {
+		init_data->flags.support_edp0_on_dp1 = true;
+		drm_info(dev, "aux_hpd_discon_quirk attached\n");
 	}
 }
 
@@ -1994,7 +2049,7 @@ static int amdgpu_dm_init(struct amdgpu_device *adev)
 	if (amdgpu_ip_version(adev, DCE_HWIP, 0) >= IP_VERSION(3, 0, 0))
 		init_data.num_virtual_links = 1;
 
-	retrieve_dmi_info(&adev->dm);
+	retrieve_dmi_info(&adev->dm, &init_data);
 
 	if (adev->dm.bb_from_dmub)
 		init_data.bb_from_dmub = adev->dm.bb_from_dmub;

From 4de141b8b1b7991b607f77e5f4580e1c67c24717 Mon Sep 17 00:00:00 2001
From: Roman Li <Roman.Li@amd.com>
Date: Wed, 12 Feb 2025 14:49:36 -0500
Subject: [PATCH 1133/2753] drm/amd/display: Fix HPD after gpu reset

[Why]
DC is not using amdgpu_irq_get/put to manage the HPD interrupt refcounts.
So when amdgpu_irq_gpu_reset_resume_helper() reprograms all of the IRQs,
HPD gets disabled.

[How]
Use amdgpu_irq_get/put() for HPD init/fini in DM in order to sync refcounts

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Aurabindo Pillai <aurabindo.pillai@amd.com>
Signed-off-by: Roman Li <Roman.Li@amd.com>
Signed-off-by: Zaeem Mohamed <zaeem.mohamed@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit f3dde2ff7fcaacd77884502e8f572f2328e9c745)
Cc: stable@vger.kernel.org
---
 .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c  | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index 3390f0d8420a0..c4a7fd453e5fc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -894,6 +894,7 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int i;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -920,6 +921,12 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
+
+	/* Update reference counts for HPDs */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+		if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+			drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i);
+	}
 }
 
 /**
@@ -935,6 +942,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int i;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -960,4 +968,10 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
+
+	/* Update reference counts for HPDs */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
+		if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
+			drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i);
+	}
 }

From d3c7059b6a8600fc62cd863f1ea203b8675e63e1 Mon Sep 17 00:00:00 2001
From: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Date: Thu, 20 Feb 2025 14:41:59 +0100
Subject: [PATCH 1134/2753] drm/amdgpu: init return value in
 amdgpu_ttm_clear_buffer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Otherwise an uninitialized value can be returned if
amdgpu_res_cleared returns true for all regions.

Possibly closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3812

Fixes: a68c7eaa7a8f ("drm/amdgpu: Enable clear page functionality")
Signed-off-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7c62aacc3b452f73a1284198c81551035fac6d71)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
index 01ae2f88dec8c..262bd010a283d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -2281,7 +2281,7 @@ int amdgpu_ttm_clear_buffer(struct amdgpu_bo *bo,
 	struct amdgpu_ring *ring = adev->mman.buffer_funcs_ring;
 	struct amdgpu_res_cursor cursor;
 	u64 addr;
-	int r;
+	int r = 0;
 
 	if (!adev->mman.buffer_funcs_enabled)
 		return -EINVAL;

From 68f3ea7ee199ef77551e090dfef5a49046ea8443 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 21 Feb 2025 14:57:06 +0100
Subject: [PATCH 1135/2753] vmlinux.lds: Ensure that const vars with
 relocations are mapped R/O

In the kernel, there are architectures (x86, arm64) that perform
boot-time relocation (for KASLR) without relying on PIE codegen. In this
case, all const global objects are emitted into .rodata, including const
objects with fields that will be fixed up by the boot-time relocation
code.  This implies that .rodata (and .text in some cases) need to be
writable at boot, but they will usually be mapped read-only as soon as
the boot completes.

When using PIE codegen, the compiler will emit const global objects into
.data.rel.ro rather than .rodata if the object contains fields that need
such fixups at boot-time. This permits the linker to annotate such
regions as requiring read-write access only at load time, but not at
execution time (in user space), while keeping .rodata truly const (in
user space, this is important for reducing the CoW footprint of dynamic
executables).

This distinction does not matter for the kernel, but it does imply that
const data will end up in writable memory if the .data.rel.ro sections
are not treated in a special way, as they will end up in the writable
.data segment by default.

So emit .data.rel.ro into the .rodata segment.

Cc: stable@vger.kernel.org
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250221135704.431269-5-ardb+git@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 include/asm-generic/vmlinux.lds.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 54504013c7491..337d3336e1756 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -457,7 +457,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 	. = ALIGN((align));						\
 	.rodata           : AT(ADDR(.rodata) - LOAD_OFFSET) {		\
 		__start_rodata = .;					\
-		*(.rodata) *(.rodata.*)					\
+		*(.rodata) *(.rodata.*) *(.data.rel.ro*)		\
 		SCHED_DATA						\
 		RO_AFTER_INIT_DATA	/* Read only after init */	\
 		. = ALIGN(8);						\

From 73cfc53cc3b6380eccf013049574485f64cb83ca Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 21 Feb 2025 14:57:07 +0100
Subject: [PATCH 1136/2753] objtool: Fix C jump table annotations for Clang

A C jump table (such as the one used by the BPF interpreter) is a const
global array of absolute code addresses, and this means that the actual
values in the table may not be known until the kernel is booted (e.g.,
when using KASLR or when the kernel VA space is sized dynamically).

When using PIE codegen, the compiler will default to placing such const
global objects in .data.rel.ro (which is annotated as writable), rather
than .rodata (which is annotated as read-only). As C jump tables are
explicitly emitted into .rodata, this used to result in warnings for
LoongArch builds (which uses PIE codegen for the entire kernel) like

  Warning: setting incorrect section attributes for .rodata..c_jump_table

due to the fact that the explicitly specified .rodata section inherited
the read-write annotation that the compiler uses for such objects when
using PIE codegen.

This warning was suppressed by explicitly adding the read-only
annotation to the __attribute__((section(""))) string, by commit

  c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table")

Unfortunately, this hack does not work on Clang's integrated assembler,
which happily interprets the appended section type and permission
specifiers as part of the section name, which therefore no longer
matches the hard-coded pattern '.rodata..c_jump_table' that objtool
expects, causing it to emit a warning

  kernel/bpf/core.o: warning: objtool: ___bpf_prog_run+0x20: sibling call from callable instruction with modified stack frame

Work around this, by emitting C jump tables into .data.rel.ro instead,
which is treated as .rodata by the linker script for all builds, not
just PIE based ones.

Fixes: c5b1184decc8 ("compiler.h: specify correct attribute for .rodata..c_jump_table")
Tested-by: Tiezhu Yang <yangtiezhu@loongson.cn> # on LoongArch
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250221135704.431269-6-ardb+git@google.com
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 include/linux/compiler.h                | 2 +-
 tools/objtool/check.c                   | 7 ++++---
 tools/objtool/include/objtool/special.h | 2 +-
 3 files changed, 6 insertions(+), 5 deletions(-)

diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index b087de2f3e94b..0c25f3e429bba 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -110,7 +110,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 /* Unreachable code */
 #ifdef CONFIG_OBJTOOL
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
+#define __annotate_jump_table __section(".data.rel.ro.c_jump_table")
 #else /* !CONFIG_OBJTOOL */
 #define __annotate_jump_table
 #endif /* CONFIG_OBJTOOL */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 497cb8dfb3eb3..1b5a1b3ea7a9f 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -2471,13 +2471,14 @@ static void mark_rodata(struct objtool_file *file)
 	 *
 	 * - .rodata: can contain GCC switch tables
 	 * - .rodata.<func>: same, if -fdata-sections is being used
-	 * - .rodata..c_jump_table: contains C annotated jump tables
+	 * - .data.rel.ro.c_jump_table: contains C annotated jump tables
 	 *
 	 * .rodata.str1.* sections are ignored; they don't contain jump tables.
 	 */
 	for_each_sec(file, sec) {
-		if (!strncmp(sec->name, ".rodata", 7) &&
-		    !strstr(sec->name, ".str1.")) {
+		if ((!strncmp(sec->name, ".rodata", 7) &&
+		     !strstr(sec->name, ".str1.")) ||
+		    !strncmp(sec->name, ".data.rel.ro", 12)) {
 			sec->rodata = true;
 			found = true;
 		}
diff --git a/tools/objtool/include/objtool/special.h b/tools/objtool/include/objtool/special.h
index e7ee7ffccefd4..e049679bb17b2 100644
--- a/tools/objtool/include/objtool/special.h
+++ b/tools/objtool/include/objtool/special.h
@@ -10,7 +10,7 @@
 #include <objtool/check.h>
 #include <objtool/elf.h>
 
-#define C_JUMP_TABLE_SECTION ".rodata..c_jump_table"
+#define C_JUMP_TABLE_SECTION ".data.rel.ro.c_jump_table"
 
 struct special_alt {
 	struct list_head list;

From b4ae43b053537ec28f430c0ddb9b916ab296dbe5 Mon Sep 17 00:00:00 2001
From: Youling Tang <tangyouling@kylinos.cn>
Date: Tue, 18 Feb 2025 14:42:30 +0800
Subject: [PATCH 1137/2753] objtool: Add
 bch2_trans_unlocked_or_in_restart_error() to bcachefs noreturns

Fix the following objtool warning during build time:

  fs/bcachefs/btree_cache.o: warning: objtool: btree_node_lock.constprop.0() falls through to next function bch2_recalc_btree_reserve()
  fs/bcachefs/btree_update.o: warning: objtool: bch2_trans_update_get_key_cache() falls through to next function need_whiteout_for_snapshot()

bch2_trans_unlocked_or_in_restart_error() is an Obviously Correct (tm)
panic() wrapper, add it to the list of known noreturns.

Fixes: b318882022a8 ("bcachefs: bch2_trans_verify_not_unlocked_or_in_restart()")
Reported-by: k2ci <kernel-bot@kylinos.cn>
Signed-off-by: Youling Tang <tangyouling@kylinos.cn>
Reviewed-by: Kent Overstreet <kent.overstreet@linux.dev>
Link: https://lore.kernel.org/r/20250218064230.219997-1-youling.tang@linux.dev
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
---
 tools/objtool/noreturns.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
index b2174894f9f71..6bb7edda3094d 100644
--- a/tools/objtool/noreturns.h
+++ b/tools/objtool/noreturns.h
@@ -19,7 +19,7 @@ NORETURN(__x64_sys_exit_group)
 NORETURN(arch_cpu_idle_dead)
 NORETURN(bch2_trans_in_restart_error)
 NORETURN(bch2_trans_restart_error)
-NORETURN(bch2_trans_unlocked_error)
+NORETURN(bch2_trans_unlocked_or_in_restart_error)
 NORETURN(cpu_bringup_and_idle)
 NORETURN(cpu_startup_entry)
 NORETURN(do_exit)

From 8fef0a3b17bb258130a4fcbcb5addf94b25e9ec5 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Tue, 25 Feb 2025 06:02:23 -1000
Subject: [PATCH 1138/2753] sched_ext: Fix pick_task_scx() picking non-queued
 tasks when it's called without balance()

a6250aa251ea ("sched_ext: Handle cases where pick_task_scx() is called
without preceding balance_scx()") added a workaround to handle the cases
where pick_task_scx() is called without prececing balance_scx() which is due
to a fair class bug where pick_taks_fair() may return NULL after a true
return from balance_fair().

The workaround detects when pick_task_scx() is called without preceding
balance_scx() and emulates SCX_RQ_BAL_KEEP and triggers kicking to avoid
stalling. Unfortunately, the workaround code was testing whether @prev was
on SCX to decide whether to keep the task running. This is incorrect as the
task may be on SCX but no longer runnable.

This could lead to a non-runnable task to be returned from pick_task_scx()
which cause interesting confusions and failures. e.g. A common failure mode
is the task ending up with (!on_rq && on_cpu) state which can cause
potential wakers to busy loop, which can easily lead to deadlocks.

Fix it by testing whether @prev has SCX_TASK_QUEUED set. This makes
@prev_on_scx only used in one place. Open code the usage and improve the
comment while at it.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Pat Cody <patcody@meta.com>
Fixes: a6250aa251ea ("sched_ext: Handle cases where pick_task_scx() is called without preceding balance_scx()")
Cc: stable@vger.kernel.org # v6.12+
Acked-by: Andrea Righi <arighi@nvidia.com>
---
 kernel/sched/ext.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5a81d9a1e31f2..0f1da199cfc7c 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3117,7 +3117,6 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 {
 	struct task_struct *prev = rq->curr;
 	struct task_struct *p;
-	bool prev_on_scx = prev->sched_class == &ext_sched_class;
 	bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
 	bool kick_idle = false;
 
@@ -3137,14 +3136,18 @@ static struct task_struct *pick_task_scx(struct rq *rq)
 	 * if pick_task_scx() is called without preceding balance_scx().
 	 */
 	if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) {
-		if (prev_on_scx) {
+		if (prev->scx.flags & SCX_TASK_QUEUED) {
 			keep_prev = true;
 		} else {
 			keep_prev = false;
 			kick_idle = true;
 		}
-	} else if (unlikely(keep_prev && !prev_on_scx)) {
-		/* only allowed during transitions */
+	} else if (unlikely(keep_prev &&
+			    prev->sched_class != &ext_sched_class)) {
+		/*
+		 * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
+		 * conditional on scx_enabled() and may have been skipped.
+		 */
 		WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED);
 		keep_prev = false;
 	}

From f44fa354a0715577ca32b085f6f60bcf32c748dd Mon Sep 17 00:00:00 2001
From: Stefan Wahren <wahrenst@gmx.net>
Date: Sat, 1 Feb 2025 12:27:29 +0100
Subject: [PATCH 1139/2753] ARM: dts: bcm2711: Fix xHCI power-domain

During s2idle tests on the Raspberry CM4 the VPU firmware always crashes
on xHCI power-domain resume:

root@raspberrypi:/sys/power# echo freeze > state
[   70.724347] xhci_suspend finished
[   70.727730] xhci_plat_suspend finished
[   70.755624] bcm2835-power bcm2835-power: Power grafx off
[   70.761127]  USB: Set power to 0

[   74.653040]  USB: Failed to set power to 1 (-110)

This seems to be caused because of the mixed usage of
raspberrypi-power and bcm2835-power at the same time. So avoid
the usage of the VPU firmware power-domain driver, which
prevents the VPU crash.

Fixes: 522c35e08b53 ("ARM: dts: bcm2711: Add BCM2711 xHCI support")
Link: https://github.com/raspberrypi/linux/issues/6537
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20250201112729.31509-1-wahrenst@gmx.net
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi | 5 -----
 arch/arm/boot/dts/broadcom/bcm2711.dtsi     | 1 +
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
index 6bf4241fe3b73..c78ed064d1667 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711-rpi.dtsi
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "bcm2835-rpi.dtsi"
 
-#include <dt-bindings/power/raspberrypi-power.h>
 #include <dt-bindings/reset/raspberrypi,firmware-reset.h>
 
 / {
@@ -101,7 +100,3 @@
 &vchiq {
 	interrupts = <GIC_SPI 34 IRQ_TYPE_LEVEL_HIGH>;
 };
-
-&xhci {
-	power-domains = <&power RPI_POWER_DOMAIN_USB>;
-};
diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index e4e42af21ef3a..5eaec6c6a1df3 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -610,6 +610,7 @@
 			#address-cells = <1>;
 			#size-cells = <0>;
 			interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+			power-domains = <&pm BCM2835_POWER_DOMAIN_USB>;
 			/* DWC2 and this IP block share the same USB PHY,
 			 * enabling both at the same time results in lockups.
 			 * So keep this node disabled and let the bootloader

From 0de09025f161f67c07978c4742e221243d070d41 Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.com>
Date: Sun, 23 Feb 2025 13:56:13 +0100
Subject: [PATCH 1140/2753] ARM: dts: bcm2711: PL011 UARTs are actually r1p5

The ARM PL011 UART instances in BCM2711 are r1p5 spec, which means they
have 32-entry FIFOs. The correct periphid value for this is 0x00341011.
Thanks to N Buchwitz for pointing this out.

Signed-off-by: Phil Elwell <phil@raspberrypi.com>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20250223125614.3592-2-wahrenst@gmx.net
Fixes: 7dbe8c62ceeb ("ARM: dts: Add minimal Raspberry Pi 4 support")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm/boot/dts/broadcom/bcm2711.dtsi | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index 5eaec6c6a1df3..4fd0732a34d32 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -134,7 +134,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -145,7 +145,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -156,7 +156,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -167,7 +167,7 @@
 			clocks = <&clocks BCM2835_CLOCK_UART>,
 				 <&clocks BCM2835_CLOCK_VPU>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 
@@ -1178,6 +1178,7 @@
 };
 
 &uart0 {
+	arm,primecell-periphid = <0x00341011>;
 	interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 };
 

From 768953614c1c13fdf771be5742f1be573eea8fa4 Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.com>
Date: Sun, 23 Feb 2025 13:56:14 +0100
Subject: [PATCH 1141/2753] arm64: dts: bcm2712: PL011 UARTs are actually r1p5

The ARM PL011 UART instances in BCM2712 are r1p5 spec, which means they
have 32-entry FIFOs. The correct periphid value for this is 0x00341011.
Thanks to N Buchwitz for pointing this out.

Signed-off-by: Phil Elwell <phil@raspberrypi.com>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Link: https://lore.kernel.org/r/20250223125614.3592-3-wahrenst@gmx.net
Fixes: faa3381267d0 ("arm64: dts: broadcom: Add minimal support for Raspberry Pi 5")
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm64/boot/dts/broadcom/bcm2712.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
index 689c82b7f596a..9e610a89a3378 100644
--- a/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
+++ b/arch/arm64/boot/dts/broadcom/bcm2712.dtsi
@@ -227,7 +227,7 @@
 			interrupts = <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>;
 			clocks = <&clk_uart>, <&clk_vpu>;
 			clock-names = "uartclk", "apb_pclk";
-			arm,primecell-periphid = <0x00241011>;
+			arm,primecell-periphid = <0x00341011>;
 			status = "disabled";
 		};
 

From a26b24b2e21f6222635a95426b9ef9eec63d69b1 Mon Sep 17 00:00:00 2001
From: Kan Liang <kan.liang@linux.intel.com>
Date: Fri, 17 Jan 2025 07:19:13 -0800
Subject: [PATCH 1142/2753] perf/x86/intel: Use better start period for
 frequency mode

Freqency mode is the current default mode of Linux perf. A period of 1 is
used as a starting period. The period is auto-adjusted on each tick or an
overflow, to meet the frequency target.

The start period of 1 is too low and may trigger some issues:

- Many HWs do not support period 1 well.
  https://lore.kernel.org/lkml/875xs2oh69.ffs@tglx/

- For an event that occurs frequently, period 1 is too far away from the
  real period. Lots of samples are generated at the beginning.
  The distribution of samples may not be even.

- A low starting period for frequently occurring events also challenges
  virtualization, which has a longer path to handle a PMI.

The limit_period value only checks the minimum acceptable value for HW.
It cannot be used to set the start period, because some events may
need a very low period. The limit_period cannot be set too high. It
doesn't help with the events that occur frequently.

It's hard to find a universal starting period for all events. The idea
implemented by this patch is to only give an estimate for the popular
HW and HW cache events. For the rest of the events, start from the lowest
possible recommended value.

Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250117151913.3043942-3-kan.liang@linux.intel.com
---
 arch/x86/events/intel/core.c | 85 ++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)

diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cdcebf30468a0..cdb19e3ba3aa3 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3952,6 +3952,85 @@ static inline bool intel_pmu_has_cap(struct perf_event *event, int idx)
 	return test_bit(idx, (unsigned long *)&intel_cap->capabilities);
 }
 
+static u64 intel_pmu_freq_start_period(struct perf_event *event)
+{
+	int type = event->attr.type;
+	u64 config, factor;
+	s64 start;
+
+	/*
+	 * The 127 is the lowest possible recommended SAV (sample after value)
+	 * for a 4000 freq (default freq), according to the event list JSON file.
+	 * Also, assume the workload is idle 50% time.
+	 */
+	factor = 64 * 4000;
+	if (type != PERF_TYPE_HARDWARE && type != PERF_TYPE_HW_CACHE)
+		goto end;
+
+	/*
+	 * The estimation of the start period in the freq mode is
+	 * based on the below assumption.
+	 *
+	 * For a cycles or an instructions event, 1GHZ of the
+	 * underlying platform, 1 IPC. The workload is idle 50% time.
+	 * The start period = 1,000,000,000 * 1 / freq / 2.
+	 *		    = 500,000,000 / freq
+	 *
+	 * Usually, the branch-related events occur less than the
+	 * instructions event. According to the Intel event list JSON
+	 * file, the SAV (sample after value) of a branch-related event
+	 * is usually 1/4 of an instruction event.
+	 * The start period of branch-related events = 125,000,000 / freq.
+	 *
+	 * The cache-related events occurs even less. The SAV is usually
+	 * 1/20 of an instruction event.
+	 * The start period of cache-related events = 25,000,000 / freq.
+	 */
+	config = event->attr.config & PERF_HW_EVENT_MASK;
+	if (type == PERF_TYPE_HARDWARE) {
+		switch (config) {
+		case PERF_COUNT_HW_CPU_CYCLES:
+		case PERF_COUNT_HW_INSTRUCTIONS:
+		case PERF_COUNT_HW_BUS_CYCLES:
+		case PERF_COUNT_HW_STALLED_CYCLES_FRONTEND:
+		case PERF_COUNT_HW_STALLED_CYCLES_BACKEND:
+		case PERF_COUNT_HW_REF_CPU_CYCLES:
+			factor = 500000000;
+			break;
+		case PERF_COUNT_HW_BRANCH_INSTRUCTIONS:
+		case PERF_COUNT_HW_BRANCH_MISSES:
+			factor = 125000000;
+			break;
+		case PERF_COUNT_HW_CACHE_REFERENCES:
+		case PERF_COUNT_HW_CACHE_MISSES:
+			factor = 25000000;
+			break;
+		default:
+			goto end;
+		}
+	}
+
+	if (type == PERF_TYPE_HW_CACHE)
+		factor = 25000000;
+end:
+	/*
+	 * Usually, a prime or a number with less factors (close to prime)
+	 * is chosen as an SAV, which makes it less likely that the sampling
+	 * period synchronizes with some periodic event in the workload.
+	 * Minus 1 to make it at least avoiding values near power of twos
+	 * for the default freq.
+	 */
+	start = DIV_ROUND_UP_ULL(factor, event->attr.sample_freq) - 1;
+
+	if (start > x86_pmu.max_period)
+		start = x86_pmu.max_period;
+
+	if (x86_pmu.limit_period)
+		x86_pmu.limit_period(event, &start);
+
+	return start;
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -3963,6 +4042,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	if (ret)
 		return ret;
 
+	if (event->attr.freq && event->attr.sample_freq) {
+		event->hw.sample_period = intel_pmu_freq_start_period(event);
+		event->hw.last_period = event->hw.sample_period;
+		local64_set(&event->hw.period_left, event->hw.sample_period);
+	}
+
 	if (event->attr.precise_ip) {
 		if ((event->attr.config & INTEL_ARCH_EVENT_MASK) == INTEL_FIXED_VLBR_EVENT)
 			return -EINVAL;

From 1f7a4f98c11fbeb18ed21f3b3a497e90a50ad2e0 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 15:52:21 +0100
Subject: [PATCH 1143/2753] sunrpc: suppress warnings for unused procfs
 functions

There is a warning about unused variables when building with W=1 and no procfs:

net/sunrpc/cache.c:1660:30: error: 'cache_flush_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1660 | static const struct proc_ops cache_flush_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~~~~~
net/sunrpc/cache.c:1622:30: error: 'content_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1622 | static const struct proc_ops content_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~
net/sunrpc/cache.c:1598:30: error: 'cache_channel_proc_ops' defined but not used [-Werror=unused-const-variable=]
 1598 | static const struct proc_ops cache_channel_proc_ops = {
      |                              ^~~~~~~~~~~~~~~~~~~~~~

These are used inside of an #ifdef, so replacing that with an
IS_ENABLED() check lets the compiler see how they are used while
still dropping them during dead code elimination.

Fixes: dbf847ecb631 ("knfsd: allow cache_register to return error on failure")
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 net/sunrpc/cache.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index cb279eb9ac4ba..7ce5e28a6c031 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -1674,12 +1674,14 @@ static void remove_cache_proc_entries(struct cache_detail *cd)
 	}
 }
 
-#ifdef CONFIG_PROC_FS
 static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 {
 	struct proc_dir_entry *p;
 	struct sunrpc_net *sn;
 
+	if (!IS_ENABLED(CONFIG_PROC_FS))
+		return 0;
+
 	sn = net_generic(net, sunrpc_net_id);
 	cd->procfs = proc_mkdir(cd->name, sn->proc_net_rpc);
 	if (cd->procfs == NULL)
@@ -1707,12 +1709,6 @@ static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
 	remove_cache_proc_entries(cd);
 	return -ENOMEM;
 }
-#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd, struct net *net)
-{
-	return 0;
-}
-#endif
 
 void __init cache_initialize(void)
 {

From 9084ed79ddaaaa1ec01cd304af9fb532c26252db Mon Sep 17 00:00:00 2001
From: Stephen Smalley <stephen.smalley.work@gmail.com>
Date: Thu, 20 Feb 2025 14:29:36 -0500
Subject: [PATCH 1144/2753] lsm,nfs: fix memory leak of lsm_context

commit b530104f50e8 ("lsm: lsm_context in security_dentry_init_security")
did not preserve the lsm id for subsequent release calls, which results
in a memory leak. Fix it by saving the lsm id in the nfs4_label and
providing it on the subsequent release call.

Fixes: b530104f50e8 ("lsm: lsm_context in security_dentry_init_security")
Signed-off-by: Stephen Smalley <stephen.smalley.work@gmail.com>
Acked-by: Paul Moore <paul@paul-moore.com>
Acked-by: Casey Schaufler <casey@schaufler-ca.com>
Signed-off-by: Anna Schumaker <anna.schumaker@oracle.com>
---
 fs/nfs/nfs4proc.c    | 7 ++++---
 include/linux/nfs4.h | 1 +
 2 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index c25ecdb76d304..6e95db6c17e92 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -133,6 +133,7 @@ nfs4_label_init_security(struct inode *dir, struct dentry *dentry,
 	if (err)
 		return NULL;
 
+	label->lsmid = shim.id;
 	label->label = shim.context;
 	label->len = shim.len;
 	return label;
@@ -145,7 +146,7 @@ nfs4_label_release_security(struct nfs4_label *label)
 	if (label) {
 		shim.context = label->label;
 		shim.len = label->len;
-		shim.id = LSM_ID_UNDEF;
+		shim.id = label->lsmid;
 		security_release_secctx(&shim);
 	}
 }
@@ -6272,7 +6273,7 @@ static int _nfs4_get_security_label(struct inode *inode, void *buf,
 					size_t buflen)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-	struct nfs4_label label = {0, 0, buflen, buf};
+	struct nfs4_label label = {0, 0, 0, buflen, buf};
 
 	u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL };
 	struct nfs_fattr fattr = {
@@ -6377,7 +6378,7 @@ static int nfs4_do_set_security_label(struct inode *inode,
 static int
 nfs4_set_security_label(struct inode *inode, const void *buf, size_t buflen)
 {
-	struct nfs4_label ilabel = {0, 0, buflen, (char *)buf };
+	struct nfs4_label ilabel = {0, 0, 0, buflen, (char *)buf };
 	struct nfs_fattr *fattr;
 	int status;
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 71fbebfa43c7e..9ac83ca883266 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -47,6 +47,7 @@ struct nfs4_acl {
 struct nfs4_label {
 	uint32_t	lfs;
 	uint32_t	pi;
+	u32		lsmid;
 	u32		len;
 	char	*label;
 };

From 729d163232971672d0f41b93c02092fb91f0e758 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Sat, 22 Feb 2025 00:01:22 +0100
Subject: [PATCH 1145/2753] Input: i8042 - swap old quirk combination with new
 quirk for NHxxRZQ

Some older Clevo barebones have problems like no or laggy keyboard after
resume or boot which can be fixed with the SERIO_QUIRK_FORCENORESTORE
quirk.

With the old i8042 quirks this devices keyboard is sometimes laggy after
resume. With the new quirk this issue doesn't happen.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://lore.kernel.org/r/20250221230137.70292-1-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 10 +---------
 1 file changed, 1 insertion(+), 9 deletions(-)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 127cfdc8668a0..a764248ea11d3 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1209,18 +1209,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
 	{
-		/*
-		 * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes
-		 * the keyboard very laggy for ~5 seconds after boot and
-		 * sometimes also after resume.
-		 * However both are required for the keyboard to not fail
-		 * completely sometimes after boot or resume.
-		 */
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NHxxRZQ"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {

From 9ed468e17d5b80e7116fd35842df3648e808ae47 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Sat, 22 Feb 2025 00:01:23 +0100
Subject: [PATCH 1146/2753] Input: i8042 - add required quirks for missing old
 boardnames

Some older Clevo barebones have problems like no or laggy keyboard after
resume or boot which can be fixed with the SERIO_QUIRK_FORCENORESTORE
quirk.

The PB71RD keyboard is sometimes laggy after resume and the PC70DR, PB51RF,
P640RE, and PCX0DX_GN20 keyboard is sometimes unresponsive after resume.
This quirk fixes that.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://lore.kernel.org/r/20250221230137.70292-2-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 30 +++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index a764248ea11d3..57a6eec4c2a5d 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1260,6 +1260,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "P640RE"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
 	{
 		/*
 		 * This is only a partial board_name and might be followed by
@@ -1335,6 +1341,24 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PB51RF"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PB71RD"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PC70DR"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"),
@@ -1342,6 +1366,12 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
 					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
 	},
+	{
+		.matches = {
+			DMI_MATCH(DMI_BOARD_NAME, "PCX0DX_GN20"),
+		},
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+	},
 	/* See comment on TUXEDO InfinityBook S17 Gen6 / Clevo NS70MU above */
 	{
 		.matches = {

From 75ee4ebebbbe8dc4b55ba37f388924fa96bf1564 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Sat, 22 Feb 2025 00:01:24 +0100
Subject: [PATCH 1147/2753] Input: i8042 - swap old quirk combination with new
 quirk for several devices

Some older Clevo barebones have problems like no or laggy keyboard after
resume or boot which can be fixed with the SERIO_QUIRK_FORCENORESTORE
quirk.

While the old quirk combination did not show negative effects on these
devices specifically, the new quirk works just as well and seems more
stable in general.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://lore.kernel.org/r/20250221230137.70292-3-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 40 ++++++++++-----------------
 1 file changed, 14 insertions(+), 26 deletions(-)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 57a6eec4c2a5d..9df1ef6032dd0 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1080,16 +1080,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
 			DMI_MATCH(DMI_BOARD_NAME, "AURA1501"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_VENDOR, "TUXEDO"),
 			DMI_MATCH(DMI_BOARD_NAME, "EDUBOOK1502"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/* Mivvy M310 */
@@ -1171,8 +1169,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71A"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1205,8 +1202,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NH5xAx"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1218,8 +1214,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NL5xRU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	/*
 	 * At least one modern Clevo barebone has the touchpad connected both
@@ -1235,17 +1230,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NS50MU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
-					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
-					SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX |
+					SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NS50_70MU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOAUX | SERIO_QUIRK_NOMUX |
-					SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP |
-					SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_NOAUX |
+					SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1319,8 +1312,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RS"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1338,8 +1330,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "PB50_70DFx,DDx"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1363,8 +1354,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "PCX0DX"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1383,15 +1373,13 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "X170SM"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "X170KM-G"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*

From d85862ccca452eeb19329e9f4f9a6ce1d1e53561 Mon Sep 17 00:00:00 2001
From: Werner Sembach <wse@tuxedocomputers.com>
Date: Sat, 22 Feb 2025 00:01:25 +0100
Subject: [PATCH 1148/2753] Input: i8042 - swap old quirk combination with new
 quirk for more devices

Some older Clevo barebones have problems like no or laggy keyboard after
resume or boot which can be fixed with the SERIO_QUIRK_FORCENORESTORE
quirk.

We could not activly retest these devices because we no longer have them in
our archive, but based on the other old Clevo barebones we tested where the
new quirk had the same or a better behaviour I think it would be good to
apply it on these too.

Cc: stable@vger.kernel.org
Signed-off-by: Werner Sembach <wse@tuxedocomputers.com>
Link: https://lore.kernel.org/r/20250221230137.70292-4-wse@tuxedocomputers.com
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/serio/i8042-acpipnpio.h | 31 +++++++++------------------
 1 file changed, 10 insertions(+), 21 deletions(-)

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
index 9df1ef6032dd0..6ed9fc34948cb 100644
--- a/drivers/input/serio/i8042-acpipnpio.h
+++ b/drivers/input/serio/i8042-acpipnpio.h
@@ -1157,9 +1157,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 	},
 	/*
 	 * A lot of modern Clevo barebones have touchpad and/or keyboard issues
-	 * after suspend fixable with nomux + reset + noloop + nopnp. Luckily,
-	 * none of them have an external PS/2 port so this can safely be set for
-	 * all of them.
+	 * after suspend fixable with the forcenorestore quirk.
 	 * Clevo barebones come with board_vendor and/or system_vendor set to
 	 * either the very generic string "Notebook" and/or a different value
 	 * for each individual reseller. The only somewhat universal way to
@@ -1175,22 +1173,19 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "LAPQC71B"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "N140CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "N141CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1250,8 +1245,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_BOARD_NAME, "NJ50_70CU"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {
@@ -1268,16 +1262,14 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xH"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/* Clevo P650RS, 650RP6, Sager NP8152-S, and others */
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65xRP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1288,8 +1280,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_P67H"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1300,8 +1291,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P65_67RP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		/*
@@ -1323,8 +1313,7 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
 		.matches = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "P67xRP"),
 		},
-		.driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
-					SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+		.driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
 	},
 	{
 		.matches = {

From 96f41f644c4885761b0d117fc36dc5dcf92e15ec Mon Sep 17 00:00:00 2001
From: Dmytro Maluka <dmaluka@chromium.org>
Date: Sun, 5 Jan 2025 17:27:40 +0000
Subject: [PATCH 1149/2753] x86/of: Don't use DTB for SMP setup if ACPI is
 enabled

There are cases when it is useful to use both ACPI and DTB provided by
the bootloader, however in such cases we should make sure to prevent
conflicts between the two. Namely, don't try to use DTB for SMP setup
if ACPI is enabled.

Precisely, this prevents at least:

- incorrectly calling register_lapic_address(APIC_DEFAULT_PHYS_BASE)
  after the LAPIC was already successfully enumerated via ACPI, causing
  noisy kernel warnings and probably potential real issues as well

- failed IOAPIC setup in the case when IOAPIC is enumerated via mptable
  instead of ACPI (e.g. with acpi=noirq), due to
  mpparse_parse_smp_config() overridden by x86_dtb_parse_smp_config()

Signed-off-by: Dmytro Maluka <dmaluka@chromium.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250105172741.3476758-2-dmaluka@chromium.org
---
 arch/x86/kernel/devicetree.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
index 59d23cdf4ed0f..dd8748c45529a 100644
--- a/arch/x86/kernel/devicetree.c
+++ b/arch/x86/kernel/devicetree.c
@@ -2,6 +2,7 @@
 /*
  * Architecture specific OF callbacks.
  */
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/io.h>
 #include <linux/interrupt.h>
@@ -313,6 +314,6 @@ void __init x86_flattree_get_config(void)
 	if (initial_dtb)
 		early_memunmap(dt, map_len);
 #endif
-	if (of_have_populated_dt())
+	if (acpi_disabled && of_have_populated_dt())
 		x86_init.mpparse.parse_smp_cfg = x86_dtb_parse_smp_config;
 }

From bebe35bb738b573c32a5033499cd59f20293f2a3 Mon Sep 17 00:00:00 2001
From: Russell Senior <russell@personaltelco.net>
Date: Tue, 25 Feb 2025 22:31:20 +0100
Subject: [PATCH 1150/2753] x86/CPU: Fix warm boot hang regression on AMD
 SC1100 SoC systems

I still have some Soekris net4826 in a Community Wireless Network I
volunteer with. These devices use an AMD SC1100 SoC. I am running
OpenWrt on them, which uses a patched kernel, that naturally has
evolved over time.  I haven't updated the ones in the field in a
number of years (circa 2017), but have one in a test bed, where I have
intermittently tried out test builds.

A few years ago, I noticed some trouble, particularly when "warm
booting", that is, doing a reboot without removing power, and noticed
the device was hanging after the kernel message:

  [    0.081615] Working around Cyrix MediaGX virtual DMA bugs.

If I removed power and then restarted, it would boot fine, continuing
through the message above, thusly:

  [    0.081615] Working around Cyrix MediaGX virtual DMA bugs.
  [    0.090076] Enable Memory-Write-back mode on Cyrix/NSC processor.
  [    0.100000] Enable Memory access reorder on Cyrix/NSC processor.
  [    0.100070] Last level iTLB entries: 4KB 0, 2MB 0, 4MB 0
  [    0.110058] Last level dTLB entries: 4KB 0, 2MB 0, 4MB 0, 1GB 0
  [    0.120037] CPU: NSC Geode(TM) Integrated Processor by National Semi (family: 0x5, model: 0x9, stepping: 0x1)
  [...]

In order to continue using modern tools, like ssh, to interact with
the software on these old devices, I need modern builds of the OpenWrt
firmware on the devices. I confirmed that the warm boot hang was still
an issue in modern OpenWrt builds (currently using a patched linux
v6.6.65).

Last night, I decided it was time to get to the bottom of the warm
boot hang, and began bisecting. From preserved builds, I narrowed down
the bisection window from late February to late May 2019. During this
period, the OpenWrt builds were using 4.14.x. I was able to build
using period-correct Ubuntu 18.04.6. After a number of bisection
iterations, I identified a kernel bump from 4.14.112 to 4.14.113 as
the commit that introduced the warm boot hang.

  https://github.com/openwrt/openwrt/commit/07aaa7e3d62ad32767d7067107db64b6ade81537

Looking at the upstream changes in the stable kernel between 4.14.112
and 4.14.113 (tig v4.14.112..v4.14.113), I spotted a likely suspect:

  https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=20afb90f730982882e65b01fb8bdfe83914339c5

So, I tried reverting just that kernel change on top of the breaking
OpenWrt commit, and my warm boot hang went away.

Presumably, the warm boot hang is due to some register not getting
cleared in the same way that a loss of power does. That is
approximately as much as I understand about the problem.

More poking/prodding and coaching from Jonas Gorski, it looks
like this test patch fixes the problem on my board: Tested against
v6.6.67 and v4.14.113.

Fixes: 18fb053f9b82 ("x86/cpu/cyrix: Use correct macros for Cyrix calls on Geode processors")
Debugged-by: Jonas Gorski <jonas.gorski@gmail.com>
Signed-off-by: Russell Senior <russell@personaltelco.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/CAHP3WfOgs3Ms4Z+L9i0-iBOE21sdMk5erAiJurPjnrL9LSsgRA@mail.gmail.com
Cc: Matthew Whitehead <tedheadster@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/kernel/cpu/cyrix.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 9651275aecd1b..dfec2c61e3547 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -153,8 +153,8 @@ static void geode_configure(void)
 	u8 ccr3;
 	local_irq_save(flags);
 
-	/* Suspend on halt power saving and enable #SUSP pin */
-	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
+	/* Suspend on halt power saving */
+	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x08);
 
 	ccr3 = getCx86(CX86_CCR3);
 	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */

From 9de7695925d5d2d2085681ba935857246eb2817d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 22:32:33 +0100
Subject: [PATCH 1151/2753] x86/irq: Define trace events conditionally

When both of X86_LOCAL_APIC and X86_THERMAL_VECTOR are disabled,
the irq tracing produces a W=1 build warning for the tracing
definitions:

  In file included from include/trace/trace_events.h:27,
                 from include/trace/define_trace.h:113,
                 from arch/x86/include/asm/trace/irq_vectors.h:383,
                 from arch/x86/kernel/irq.c:29:
  include/trace/stages/init.h:2:23: error: 'str__irq_vectors__trace_system_name' defined but not used [-Werror=unused-const-variable=]

Make the tracepoints conditional on the same symbosl that guard
their usage.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250225213236.3141752-1-arnd@kernel.org
---
 arch/x86/kernel/irq.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 385e3a5fc3045..feca4f20b06aa 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -25,8 +25,10 @@
 #include <asm/posted_intr.h>
 #include <asm/irq_remapping.h>
 
+#if defined(CONFIG_X86_LOCAL_APIC) || defined(CONFIG_X86_THERMAL_VECTOR)
 #define CREATE_TRACE_POINTS
 #include <asm/trace/irq_vectors.h>
+#endif
 
 DEFINE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 EXPORT_PER_CPU_SYMBOL(irq_stat);

From 68a9b0e313302451468c0b0eda53c383fa51a8f4 Mon Sep 17 00:00:00 2001
From: Aaron Ma <aaron.ma@canonical.com>
Date: Tue, 24 Dec 2024 22:55:16 +0800
Subject: [PATCH 1152/2753] perf/x86/rapl: Add support for Intel Arrow Lake U

Add Arrow Lake U model for RAPL:

  $ ls -1 /sys/devices/power/events/
  energy-cores
  energy-cores.scale
  energy-cores.unit
  energy-gpu
  energy-gpu.scale
  energy-gpu.unit
  energy-pkg
  energy-pkg.scale
  energy-pkg.unit
  energy-psys
  energy-psys.scale
  energy-psys.unit

The same output as ArrowLake:

  $ perf stat -a -I 1000 --per-socket -e power/energy-pkg/

Signed-off-by: Aaron Ma <aaron.ma@canonical.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Zhang Rui <rui.zhang@intel.com>
Link: https://lore.kernel.org/r/20241224145516.349028-1-aaron.ma@canonical.com
---
 arch/x86/events/rapl.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 4952faf03e82d..6941f4811bec1 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -879,6 +879,7 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&model_skl),
 	X86_MATCH_VFM(INTEL_ARROWLAKE,		&model_skl),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&model_skl),
 	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&model_skl),
 	{},
 };

From 0f6750b15ffdf274668b12824b09bd49ea854e18 Mon Sep 17 00:00:00 2001
From: Daniel Sneddon <daniel.sneddon@linux.intel.com>
Date: Thu, 19 Dec 2024 08:52:27 -0700
Subject: [PATCH 1153/2753] x86/entry: Fix kernel-doc warning

The do_int80_emulation() function is missing a kernel-doc formatted
description of its argument. This is causing a warning when building
with W=1. Add a brief description of the argument to satisfy
kernel-doc.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Daniel Sneddon <daniel.sneddon@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241219155227.685692-1-daniel.sneddon@linux.intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202412131236.a5HhOqXo-lkp@intel.com/
---
 arch/x86/entry/common.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index 94941c5a10ac1..14db5b85114c1 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -190,6 +190,7 @@ static __always_inline bool int80_is_external(void)
 
 /**
  * do_int80_emulation - 32-bit legacy syscall C entry from asm
+ * @regs: syscall arguments in struct pt_args on the stack.
  *
  * This entry point can be used by 32-bit and 64-bit programs to perform
  * 32-bit system calls.  Instances of INT $0x80 can be found inline in

From f8c857238a392f21d5726d07966f6061007c8d4f Mon Sep 17 00:00:00 2001
From: Andrii Nakryiko <andrii@kernel.org>
Date: Tue, 25 Feb 2025 14:32:14 -0800
Subject: [PATCH 1154/2753] uprobes: Remove too strict lockdep_assert()
 condition in hprobe_expire()

hprobe_expire() is used to atomically switch pending uretprobe instance
(struct return_instance) from being SRCU protected to be refcounted.
This can be done from background timer thread, or synchronously within
current thread when task is forked.

In the former case, return_instance has to be protected through RCU read
lock, and that's what hprobe_expire() used to check with
lockdep_assert(rcu_read_lock_held()).

But in the latter case (hprobe_expire() called from dup_utask()) there
is no RCU lock being held, and it's both unnecessary and incovenient.
Inconvenient due to the intervening memory allocations inside
dup_return_instance()'s loop. Unnecessary because dup_utask() is called
synchronously in current thread, and no uretprobe can run at that point,
so return_instance can't be freed either.

So drop rcu_read_lock_held() condition, and expand corresponding comment
to explain necessary lifetime guarantees. lockdep_assert()-detected
issue is a false positive.

Fixes: dd1a7567784e ("uprobes: SRCU-protect uretprobe lifetime (with timeout)")
Reported-by: Breno Leitao <leitao@debian.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250225223214.2970740-1-andrii@kernel.org
---
 kernel/events/uprobes.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index af53fbd2d12c4..b4ca8898fe178 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -767,10 +767,14 @@ static struct uprobe *hprobe_expire(struct hprobe *hprobe, bool get)
 	enum hprobe_state hstate;
 
 	/*
-	 * return_instance's hprobe is protected by RCU.
-	 * Underlying uprobe is itself protected from reuse by SRCU.
+	 * Caller should guarantee that return_instance is not going to be
+	 * freed from under us. This can be achieved either through holding
+	 * rcu_read_lock() or by owning return_instance in the first place.
+	 *
+	 * Underlying uprobe is itself protected from reuse by SRCU, so ensure
+	 * SRCU lock is held properly.
 	 */
-	lockdep_assert(rcu_read_lock_held() && srcu_read_lock_held(&uretprobes_srcu));
+	lockdep_assert(srcu_read_lock_held(&uretprobes_srcu));
 
 	hstate = READ_ONCE(hprobe->state);
 	switch (hstate) {

From 66cb85c441cd9c44b193ff75b4d0358fccdc6b9c Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 25 Feb 2025 22:25:00 +0000
Subject: [PATCH 1155/2753] cifs: Fix the smb1 readv callback to correctly call
 netfs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix cifs_readv_callback() to call netfs_read_subreq_terminated() rather
than queuing the subrequest work item (which is unset).  Also call the
I/O progress tracepoint.

cc: Jeff Layton <jlayton@kernel.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Fixes: e2d46f2ec332 ("netfs: Change the read result collector to only use one work item")
Reported-by: Jean-Christophe Guillain <jean-christophe@guillain.net>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219793
Tested-by: Jean-Christophe Guillain <jean-christophe@guillain.net>
Tested-by: Pali Rohár <pali@kernel.org>
Reviewed-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifssmb.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
index 3feaa0f681699..d07682020c645 100644
--- a/fs/smb/client/cifssmb.c
+++ b/fs/smb/client/cifssmb.c
@@ -1338,7 +1338,8 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	rdata->credits.value = 0;
 	rdata->subreq.error = rdata->result;
 	rdata->subreq.transferred += rdata->got_bytes;
-	queue_work(cifsiod_wq, &rdata->subreq.work);
+	trace_netfs_sreq(&rdata->subreq, netfs_sreq_trace_io_progress);
+	netfs_read_subreq_terminated(&rdata->subreq);
 	release_mid(mid);
 	add_credits(server, &credits, 0);
 }

From fc9167192f29485be5621e2e9c8208b717b65753 Mon Sep 17 00:00:00 2001
From: Hariprasad Kelam <hkelam@marvell.com>
Date: Mon, 24 Feb 2025 09:26:03 +0530
Subject: [PATCH 1156/2753] Octeontx2-af: RPM: Register driver with PCI subsys
 IDs

Although the PCI device ID and Vendor ID for the RPM (MAC) block
have remained the same across Octeon CN10K and the next-generation
CN20K silicon, Hardware architecture has changed (NIX mapped RPMs
and RFOE Mapped RPMs).

Add PCI Subsystem IDs to the device table to ensure that this driver
can be probed from NIX mapped RPM devices only.

Signed-off-by: Hariprasad Kelam <hkelam@marvell.com>
Link: https://patch.msgid.link/20250224035603.1220913-1-hkelam@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/octeontx2/af/cgx.c | 14 ++++++++++++--
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h |  2 ++
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
index 8216f843a7cd5..0b27a695008bd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/cgx.c
@@ -66,8 +66,18 @@ static int cgx_fwi_link_change(struct cgx *cgx, int lmac_id, bool en);
 /* Supported devices */
 static const struct pci_device_id cgx_id_table[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_OCTEONTX2_CGX) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_A) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10K_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN10K_B) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CN20KA) },
+	{ PCI_DEVICE_SUB(PCI_VENDOR_ID_CAVIUM, PCI_DEVID_CN10KB_RPM,
+	  PCI_ANY_ID, PCI_SUBSYS_DEVID_CNF20KA) },
 	{ 0, }  /* end of table */
 };
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index a383b5ef5b2d8..60f085b00a8cc 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -30,6 +30,8 @@
 #define PCI_SUBSYS_DEVID_CNF10K_A	       0xBA00
 #define PCI_SUBSYS_DEVID_CNF10K_B              0xBC00
 #define PCI_SUBSYS_DEVID_CN10K_B               0xBD00
+#define PCI_SUBSYS_DEVID_CN20KA                0xC220
+#define PCI_SUBSYS_DEVID_CNF20KA               0xC320
 
 /* PCI BAR nos */
 #define	PCI_AF_REG_BAR_NUM			0

From bab3a6e9ffd600f9db0ebaf8f45e1c6111cf314c Mon Sep 17 00:00:00 2001
From: Sascha Hauer <s.hauer@pengutronix.de>
Date: Mon, 24 Feb 2025 06:17:16 +0100
Subject: [PATCH 1157/2753] net: ethernet: ti: am65-cpsw: select PAGE_POOL

am65-cpsw uses page_pool_dev_alloc_pages(), thus needs PAGE_POOL
selected to avoid linker errors. This is missing since the driver
started to use page_pool helpers in 8acacc40f733 ("net: ethernet:
ti: am65-cpsw: Add minimal XDP support")

Fixes: 8acacc40f733 ("net: ethernet: ti: am65-cpsw: Add minimal XDP support")
Signed-off-by: Sascha Hauer <s.hauer@pengutronix.de>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250224-net-am654-nuss-kconfig-v2-1-c124f4915c92@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 0d5a862cd78a6..3a13d60a947a8 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -99,6 +99,7 @@ config TI_K3_AM65_CPSW_NUSS
 	select NET_DEVLINK
 	select TI_DAVINCI_MDIO
 	select PHYLINK
+	select PAGE_POOL
 	select TI_K3_CPPI_DESC_POOL
 	imply PHY_TI_GMII_SEL
 	depends on TI_K3_AM65_CPTS || !TI_K3_AM65_CPTS

From 0f58804080e3eea9d2b92188175a49adaefae34c Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Mon, 24 Feb 2025 09:40:13 +0000
Subject: [PATCH 1158/2753] selftests/net: ensure mptcp is enabled in netns

Some distributions may not enable MPTCP by default. All other MPTCP tests
source mptcp_lib.sh to ensure MPTCP is enabled before testing. However,
the ip_local_port_range test is the only one that does not include this
step.

Let's also ensure MPTCP is enabled in netns for ip_local_port_range so
that it passes on all distributions.

Suggested-by: Davide Caratti <dcaratti@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250224094013.13159-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/ip_local_port_range.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/ip_local_port_range.sh b/tools/testing/selftests/net/ip_local_port_range.sh
index 6c6ad346eaa0c..4ff746db12564 100755
--- a/tools/testing/selftests/net/ip_local_port_range.sh
+++ b/tools/testing/selftests/net/ip_local_port_range.sh
@@ -2,4 +2,6 @@
 # SPDX-License-Identifier: GPL-2.0
 
 ./in_netns.sh \
-  sh -c 'sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && ./ip_local_port_range'
+  sh -c 'sysctl -q -w net.mptcp.enabled=1 && \
+         sysctl -q -w net.ipv4.ip_local_port_range="40000 49999" && \
+         ./ip_local_port_range'

From 6002850fdfe0b4343136670a9895b6ba4ee3285b Mon Sep 17 00:00:00 2001
From: Jonas Gottlieb <jonas.gottlieb@stackit.cloud>
Date: Mon, 24 Feb 2025 10:44:27 +0100
Subject: [PATCH 1159/2753] Add OVN to `rtnetlink.h`

- The Open Virtual Network (OVN) routing netlink handler uses ID 84
- Will also add to `/etc/iproute2/rt_protos` once this is accepted
- For more information: https://github.com/ovn-org/ovn

Signed-off-by: Jonas Gottlieb <jonas.gottlieb@stackit.cloud>
Link: https://patch.msgid.link/Z7w_e7cfA3xmHDa6@SIT-SDELAP4051.int.lidl.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/uapi/linux/rtnetlink.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h
index 66c3903d29cf6..dab9493c791b8 100644
--- a/include/uapi/linux/rtnetlink.h
+++ b/include/uapi/linux/rtnetlink.h
@@ -307,6 +307,7 @@ enum {
 #define RTPROT_MROUTED		17	/* Multicast daemon */
 #define RTPROT_KEEPALIVED	18	/* Keepalived daemon */
 #define RTPROT_BABEL		42	/* Babel daemon */
+#define RTPROT_OVN		84	/* OVN daemon */
 #define RTPROT_OPENR		99	/* Open Routing (Open/R) Routes */
 #define RTPROT_BGP		186	/* BGP Routes */
 #define RTPROT_ISIS		187	/* ISIS Routes */

From 18912c520674ec4d920fe3826e7e4fefeecdf5ae Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Mon, 24 Feb 2025 09:44:01 -0800
Subject: [PATCH 1160/2753] tcp: devmem: don't write truncated dmabuf CMSGs to
 userspace

Currently, we report -ETOOSMALL (err) only on the first iteration
(!sent). When we get put_cmsg error after a bunch of successful
put_cmsg calls, we don't signal the error at all. This might be
confusing on the userspace side which will see truncated CMSGs
but no MSG_CTRUNC signal.

Consider the following case:
- sizeof(struct cmsghdr) = 16
- sizeof(struct dmabuf_cmsg) = 24
- total cmsg size (CMSG_LEN) = 40 (16+24)

When calling recvmsg with msg_controllen=60, the userspace
will receive two(!) dmabuf_cmsg(s), the first one will
be a valid one and the second one will be silently truncated. There is no
easy way to discover the truncation besides doing something like
"cm->cmsg_len != CMSG_LEN(sizeof(dmabuf_cmsg))".

Introduce new put_devmem_cmsg wrapper that reports an error instead
of doing the truncation. Mina suggests that it's the intended way
this API should work.

Note that we might now report MSG_CTRUNC when the users (incorrectly)
call us with msg_control == NULL.

Fixes: 8f0b3cc9a4c1 ("tcp: RX path for devmem TCP")
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250224174401.3582695-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/socket.h |  2 ++
 net/core/scm.c         | 10 ++++++++++
 net/ipv4/tcp.c         | 26 ++++++++++----------------
 3 files changed, 22 insertions(+), 16 deletions(-)

diff --git a/include/linux/socket.h b/include/linux/socket.h
index d18cc47e89bd0..c3322eb3d6865 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -392,6 +392,8 @@ struct ucred {
 
 extern int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr);
 extern int put_cmsg(struct msghdr*, int level, int type, int len, void *data);
+extern int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+			    void *data);
 
 struct timespec64;
 struct __kernel_timespec;
diff --git a/net/core/scm.c b/net/core/scm.c
index 4f6a14babe5ae..733c0cbd393d2 100644
--- a/net/core/scm.c
+++ b/net/core/scm.c
@@ -282,6 +282,16 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
 }
 EXPORT_SYMBOL(put_cmsg);
 
+int put_cmsg_notrunc(struct msghdr *msg, int level, int type, int len,
+		     void *data)
+{
+	/* Don't produce truncated CMSGs */
+	if (!msg->msg_control || msg->msg_controllen < CMSG_LEN(len))
+		return -ETOOSMALL;
+
+	return put_cmsg(msg, level, type, len, data);
+}
+
 void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal)
 {
 	struct scm_timestamping64 tss;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 0d704bda6c416..d74281eca14f0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2438,14 +2438,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 			 */
 			memset(&dmabuf_cmsg, 0, sizeof(dmabuf_cmsg));
 			dmabuf_cmsg.frag_size = copy;
-			err = put_cmsg(msg, SOL_SOCKET, SO_DEVMEM_LINEAR,
-				       sizeof(dmabuf_cmsg), &dmabuf_cmsg);
-			if (err || msg->msg_flags & MSG_CTRUNC) {
-				msg->msg_flags &= ~MSG_CTRUNC;
-				if (!err)
-					err = -ETOOSMALL;
+			err = put_cmsg_notrunc(msg, SOL_SOCKET,
+					       SO_DEVMEM_LINEAR,
+					       sizeof(dmabuf_cmsg),
+					       &dmabuf_cmsg);
+			if (err)
 				goto out;
-			}
 
 			sent += copy;
 
@@ -2499,16 +2497,12 @@ static int tcp_recvmsg_dmabuf(struct sock *sk, const struct sk_buff *skb,
 				offset += copy;
 				remaining_len -= copy;
 
-				err = put_cmsg(msg, SOL_SOCKET,
-					       SO_DEVMEM_DMABUF,
-					       sizeof(dmabuf_cmsg),
-					       &dmabuf_cmsg);
-				if (err || msg->msg_flags & MSG_CTRUNC) {
-					msg->msg_flags &= ~MSG_CTRUNC;
-					if (!err)
-						err = -ETOOSMALL;
+				err = put_cmsg_notrunc(msg, SOL_SOCKET,
+						       SO_DEVMEM_DMABUF,
+						       sizeof(dmabuf_cmsg),
+						       &dmabuf_cmsg);
+				if (err)
 					goto out;
-				}
 
 				atomic_long_inc(&niov->pp_ref_count);
 				tcp_xa_pool.netmems[tcp_xa_pool.idx++] = skb_frag_netmem(frag);

From cff608268bafc6c70a3c67680805df6ffb389e57 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 24 Feb 2025 16:53:10 +0000
Subject: [PATCH 1161/2753] net: stmmac: dwc-qos: name struct
 plat_stmmacenet_data consistently

Most of the stmmac driver uses "plat_dat" to name the platform data,
and "data" is used for the glue driver data. make dwc-qos follow
this pattern to avoid silly mistakes.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/E1tmbhe-004vSt-M3@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-dwc-qos-eth.c        | 32 +++++++++----------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 392574bdd4a47..acb0a2e1664f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -224,7 +224,7 @@ static int tegra_eqos_init(struct platform_device *pdev, void *priv)
 }
 
 static int tegra_eqos_probe(struct platform_device *pdev,
-			    struct plat_stmmacenet_data *data,
+			    struct plat_stmmacenet_data *plat_dat,
 			    struct stmmac_resources *res)
 {
 	struct device *dev = &pdev->dev;
@@ -241,12 +241,12 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
 
-	for (int i = 0; i < data->num_clks; i++) {
-		if (strcmp(data->clks[i].id, "slave_bus") == 0) {
-			eqos->clk_slave = data->clks[i].clk;
-			data->stmmac_clk = eqos->clk_slave;
-		} else if (strcmp(data->clks[i].id, "tx") == 0) {
-			eqos->clk_tx = data->clks[i].clk;
+	for (int i = 0; i < plat_dat->num_clks; i++) {
+		if (strcmp(plat_dat->clks[i].id, "slave_bus") == 0) {
+			eqos->clk_slave = plat_dat->clks[i].clk;
+			plat_dat->stmmac_clk = eqos->clk_slave;
+		} else if (strcmp(plat_dat->clks[i].id, "tx") == 0) {
+			eqos->clk_tx = plat_dat->clks[i].clk;
 		}
 	}
 
@@ -260,7 +260,7 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	gpiod_set_value(eqos->reset, 0);
 
 	/* MDIO bus was already reset just above */
-	data->mdio_bus_data->needs_reset = false;
+	plat_dat->mdio_bus_data->needs_reset = false;
 
 	eqos->rst = devm_reset_control_get(&pdev->dev, "eqos");
 	if (IS_ERR(eqos->rst)) {
@@ -281,10 +281,10 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	usleep_range(2000, 4000);
 
 bypass_clk_reset_gpio:
-	data->fix_mac_speed = tegra_eqos_fix_speed;
-	data->init = tegra_eqos_init;
-	data->bsp_priv = eqos;
-	data->flags |= STMMAC_FLAG_SPH_DISABLE;
+	plat_dat->fix_mac_speed = tegra_eqos_fix_speed;
+	plat_dat->init = tegra_eqos_init;
+	plat_dat->bsp_priv = eqos;
+	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE;
 
 	err = tegra_eqos_init(pdev, eqos);
 	if (err < 0)
@@ -309,7 +309,7 @@ static void tegra_eqos_remove(struct platform_device *pdev)
 
 struct dwc_eth_dwmac_data {
 	int (*probe)(struct platform_device *pdev,
-		     struct plat_stmmacenet_data *data,
+		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res);
 	void (*remove)(struct platform_device *pdev);
 };
@@ -387,15 +387,15 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 static void dwc_eth_dwmac_remove(struct platform_device *pdev)
 {
 	const struct dwc_eth_dwmac_data *data = device_get_match_data(&pdev->dev);
-	struct plat_stmmacenet_data *plat_data = dev_get_platdata(&pdev->dev);
+	struct plat_stmmacenet_data *plat_dat = dev_get_platdata(&pdev->dev);
 
 	stmmac_dvr_remove(&pdev->dev);
 
 	if (data->remove)
 		data->remove(pdev);
 
-	if (plat_data)
-		clk_bulk_disable_unprepare(plat_data->num_clks, plat_data->clks);
+	if (plat_dat)
+		clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
 }
 
 static const struct of_device_id dwc_eth_dwmac_match[] = {

From 196b07ba910403c75d96a82000efa3942da243b8 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 24 Feb 2025 16:53:15 +0000
Subject: [PATCH 1162/2753] net: stmmac: dwc-qos: clean up clock initialisation

Clean up the clock initialisation by providing a helper to find a
named clock in the bulk clocks, and provide the name of the stmmac
clock in match data so we can locate the stmmac clock in generic
code.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Thierry Reding <treding@nvidia.com>
Link: https://patch.msgid.link/E1tmbhj-004vSz-Pt@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-dwc-qos-eth.c        | 33 +++++++++++--------
 1 file changed, 19 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index acb0a2e1664f9..6cadf24a575c5 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -35,6 +35,16 @@ struct tegra_eqos {
 	struct gpio_desc *reset;
 };
 
+static struct clk *dwc_eth_find_clk(struct plat_stmmacenet_data *plat_dat,
+				    const char *name)
+{
+	for (int i = 0; i < plat_dat->num_clks; i++)
+		if (strcmp(plat_dat->clks[i].id, name) == 0)
+			return plat_dat->clks[i].clk;
+
+	return NULL;
+}
+
 static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 				   struct plat_stmmacenet_data *plat_dat)
 {
@@ -121,12 +131,7 @@ static int dwc_qos_probe(struct platform_device *pdev,
 			 struct plat_stmmacenet_data *plat_dat,
 			 struct stmmac_resources *stmmac_res)
 {
-	for (int i = 0; i < plat_dat->num_clks; i++) {
-		if (strcmp(plat_dat->clks[i].id, "apb_pclk") == 0)
-			plat_dat->stmmac_clk = plat_dat->clks[i].clk;
-		else if (strcmp(plat_dat->clks[i].id, "phy_ref_clk") == 0)
-			plat_dat->pclk = plat_dat->clks[i].clk;
-	}
+	plat_dat->pclk = dwc_eth_find_clk(plat_dat, "phy_ref_clk");
 
 	return 0;
 }
@@ -237,18 +242,12 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 
 	eqos->dev = &pdev->dev;
 	eqos->regs = res->addr;
+	eqos->clk_slave = plat_dat->stmmac_clk;
 
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
 
-	for (int i = 0; i < plat_dat->num_clks; i++) {
-		if (strcmp(plat_dat->clks[i].id, "slave_bus") == 0) {
-			eqos->clk_slave = plat_dat->clks[i].clk;
-			plat_dat->stmmac_clk = eqos->clk_slave;
-		} else if (strcmp(plat_dat->clks[i].id, "tx") == 0) {
-			eqos->clk_tx = plat_dat->clks[i].clk;
-		}
-	}
+	eqos->clk_tx = dwc_eth_find_clk(plat_dat, "tx");
 
 	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(eqos->reset)) {
@@ -312,15 +311,18 @@ struct dwc_eth_dwmac_data {
 		     struct plat_stmmacenet_data *plat_dat,
 		     struct stmmac_resources *res);
 	void (*remove)(struct platform_device *pdev);
+	const char *stmmac_clk_name;
 };
 
 static const struct dwc_eth_dwmac_data dwc_qos_data = {
 	.probe = dwc_qos_probe,
+	.stmmac_clk_name = "apb_pclk",
 };
 
 static const struct dwc_eth_dwmac_data tegra_eqos_data = {
 	.probe = tegra_eqos_probe,
 	.remove = tegra_eqos_remove,
+	.stmmac_clk_name = "slave_bus",
 };
 
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
@@ -360,6 +362,9 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return dev_err_probe(&pdev->dev, ret, "Failed to enable clocks\n");
 
+	plat_dat->stmmac_clk = dwc_eth_find_clk(plat_dat,
+						data->stmmac_clk_name);
+
 	ret = data->probe(pdev, plat_dat, &stmmac_res);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n");

From ad530283d3c8bb926a08bb1a14c8aa053de4bc2c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 24 Feb 2025 14:00:37 +0200
Subject: [PATCH 1163/2753] drivers: net: xgene: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

In this case replace *gpio.h, which are subject to remove by the GPIOLIB
subsystem, with the respective headers that are being used by the driver.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20250224120037.3801609-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
index 86607b79c09f7..cc3b1631c9053 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c
@@ -6,8 +6,14 @@
  *	    Keyur Chudgar <kchudgar@apm.com>
  */
 
-#include <linux/of_gpio.h>
-#include <linux/gpio.h>
+#include <linux/acpi.h>
+#include <linux/clk.h>
+#include <linux/err.h>
+#include <linux/gpio/consumer.h>
+#include <linux/io.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
 #include "xgene_enet_main.h"
 #include "xgene_enet_hw.h"
 #include "xgene_enet_xgmac.h"

From ecdff893384cf169a55a66ca68c9d8917f8417a9 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 24 Feb 2025 19:44:13 +0200
Subject: [PATCH 1164/2753] ethtool: Symmetric OR-XOR RSS hash

Add an additional type of symmetric RSS hash type: OR-XOR.
The "Symmetric-OR-XOR" algorithm transforms the input as follows:

(SRC_IP | DST_IP, SRC_IP ^ DST_IP, SRC_PORT | DST_PORT, SRC_PORT ^ DST_PORT)

Change 'cap_rss_sym_xor_supported' to 'supported_input_xfrm', a bitmap
of supported RXH_XFRM_* types.

Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20250224174416.499070-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ethtool-netlink.rst   |  2 +-
 Documentation/networking/scaling.rst           | 15 +++++++++++----
 drivers/net/ethernet/intel/iavf/iavf_ethtool.c |  2 +-
 drivers/net/ethernet/intel/ice/ice_ethtool.c   |  2 +-
 include/linux/ethtool.h                        |  5 ++---
 include/uapi/linux/ethtool.h                   |  4 ++++
 net/ethtool/ioctl.c                            |  8 ++++----
 7 files changed, 24 insertions(+), 14 deletions(-)

diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 3770a22945097..b6e9af4d0f1b9 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1934,7 +1934,7 @@ ETHTOOL_A_RSS_INDIR attribute returns RSS indirection table where each byte
 indicates queue number.
 ETHTOOL_A_RSS_INPUT_XFRM attribute is a bitmap indicating the type of
 transformation applied to the input protocol fields before given to the RSS
-hfunc. Current supported option is symmetric-xor.
+hfunc. Current supported options are symmetric-xor and symmetric-or-xor.
 
 PLCA_GET_CFG
 ============
diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst
index 4eb50bcb9d429..6984700cec6ad 100644
--- a/Documentation/networking/scaling.rst
+++ b/Documentation/networking/scaling.rst
@@ -49,14 +49,21 @@ destination address) and TCP/UDP (source port, destination port) tuples
 are swapped, the computed hash is the same. This is beneficial in some
 applications that monitor TCP/IP flows (IDS, firewalls, ...etc) and need
 both directions of the flow to land on the same Rx queue (and CPU). The
-"Symmetric-XOR" is a type of RSS algorithms that achieves this hash
-symmetry by XORing the input source and destination fields of the IP
-and/or L4 protocols. This, however, results in reduced input entropy and
-could potentially be exploited. Specifically, the algorithm XORs the input
+"Symmetric-XOR" and "Symmetric-OR-XOR" are types of RSS algorithms that
+achieve this hash symmetry by XOR/ORing the input source and destination
+fields of the IP and/or L4 protocols. This, however, results in reduced
+input entropy and could potentially be exploited.
+
+Specifically, the "Symmetric-XOR" algorithm XORs the input
 as follows::
 
     # (SRC_IP ^ DST_IP, SRC_IP ^ DST_IP, SRC_PORT ^ DST_PORT, SRC_PORT ^ DST_PORT)
 
+The "Symmetric-OR-XOR" algorithm, on the other hand, transforms the input as
+follows::
+
+    # (SRC_IP | DST_IP, SRC_IP ^ DST_IP, SRC_PORT | DST_PORT, SRC_PORT ^ DST_PORT)
+
 The result is then fed to the underlying RSS algorithm.
 
 Some advanced NICs allow steering packets to queues based on
diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
index 74a1e9fe18212..288bb5b2e72ef 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c
@@ -1808,7 +1808,7 @@ static int iavf_set_rxfh(struct net_device *netdev,
 static const struct ethtool_ops iavf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
-	.cap_rss_sym_xor_supported = true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
 	.get_drvinfo		= iavf_get_drvinfo,
 	.get_link		= ethtool_op_get_link,
 	.get_ringparam		= iavf_get_ringparam,
diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c
index b0805704834d7..7c2dc347e4e57 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c
@@ -4770,7 +4770,7 @@ static const struct ethtool_ops ice_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_RX_USECS_HIGH,
-	.cap_rss_sym_xor_supported = true,
+	.supported_input_xfrm	= RXH_XFRM_SYM_XOR,
 	.rxfh_per_ctx_key	= true,
 	.get_link_ksettings	= ice_get_link_ksettings,
 	.set_link_ksettings	= ice_set_link_ksettings,
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 870994cc3ef7e..7f222dccc7d1d 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -763,13 +763,12 @@ struct kernel_ethtool_ts_info {
 
 /**
  * struct ethtool_ops - optional netdev operations
+ * @supported_input_xfrm: supported types of input xfrm from %RXH_XFRM_*.
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
  * @cap_rss_ctx_supported: indicates if the driver supports RSS
  *	contexts via legacy API, drivers implementing @create_rxfh_context
  *	do not have to set this bit.
- * @cap_rss_sym_xor_supported: indicates if the driver supports symmetric-xor
- *	RSS.
  * @rxfh_per_ctx_key: device supports setting different RSS key for each
  *	additional context. Netlink API should report hfunc, key, and input_xfrm
  *	for every context, not just context 0.
@@ -995,9 +994,9 @@ struct kernel_ethtool_ts_info {
  * of the generic netdev features interface.
  */
 struct ethtool_ops {
+	u32     supported_input_xfrm:8;
 	u32     cap_link_lanes_supported:1;
 	u32     cap_rss_ctx_supported:1;
-	u32	cap_rss_sym_xor_supported:1;
 	u32	rxfh_per_ctx_key:1;
 	u32	cap_rss_rxnfc_adds:1;
 	u32	rxfh_indir_space;
diff --git a/include/uapi/linux/ethtool.h b/include/uapi/linux/ethtool.h
index 2feba0929a8a9..84833cca29fec 100644
--- a/include/uapi/linux/ethtool.h
+++ b/include/uapi/linux/ethtool.h
@@ -2289,6 +2289,10 @@ static inline int ethtool_validate_duplex(__u8 duplex)
  * be exploited to reduce the RSS queue spread.
  */
 #define	RXH_XFRM_SYM_XOR	(1 << 0)
+/* Similar to SYM_XOR, except that one copy of the XOR'ed fields is replaced by
+ * an OR of the same fields
+ */
+#define	RXH_XFRM_SYM_OR_XOR	(1 << 1)
 #define	RXH_XFRM_NO_CHANGE	0xff
 
 /* L2-L4 network traffic flow types */
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 271c7cef9ef3e..77d714874ecae 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1011,11 +1011,11 @@ static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev,
 		if (rc)
 			return rc;
 
-		/* Sanity check: if symmetric-xor is set, then:
+		/* Sanity check: if symmetric-xor/symmetric-or-xor is set, then:
 		 * 1 - no other fields besides IP src/dst and/or L4 src/dst
 		 * 2 - If src is set, dst must also be set
 		 */
-		if ((rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
+		if ((rxfh.input_xfrm & (RXH_XFRM_SYM_XOR | RXH_XFRM_SYM_OR_XOR)) &&
 		    ((info.data & ~(RXH_IP_SRC | RXH_IP_DST |
 				    RXH_L4_B_0_1 | RXH_L4_B_2_3)) ||
 		     (!!(info.data & RXH_IP_SRC) ^ !!(info.data & RXH_IP_DST)) ||
@@ -1388,11 +1388,11 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 		return -EOPNOTSUPP;
 	/* Check input data transformation capabilities */
 	if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR &&
+	    rxfh.input_xfrm != RXH_XFRM_SYM_OR_XOR &&
 	    rxfh.input_xfrm != RXH_XFRM_NO_CHANGE)
 		return -EINVAL;
 	if (rxfh.input_xfrm != RXH_XFRM_NO_CHANGE &&
-	    (rxfh.input_xfrm & RXH_XFRM_SYM_XOR) &&
-	    !ops->cap_rss_sym_xor_supported)
+	    rxfh.input_xfrm & ~ops->supported_input_xfrm)
 		return -EOPNOTSUPP;
 	create = rxfh.rss_context == ETH_RXFH_CONTEXT_ALLOC;
 

From 4d20c9f2db83a066537e54f3cffc40e85f17ad37 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 24 Feb 2025 19:44:14 +0200
Subject: [PATCH 1165/2753] net/mlx5e: Symmetric OR-XOR RSS hash control

Allow control over the symmetric RSS hash, which was previously set to
enabled by default by the driver.

Symmetric OR-XOR RSS can now be queried and controlled using the
'ethtool -x/X' command.

Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250224174416.499070-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/rss.c    | 13 +++++++++++--
 .../net/ethernet/mellanox/mlx5/core/en/rss.h    |  4 ++--
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.c | 11 ++++++-----
 .../net/ethernet/mellanox/mlx5/core/en/rx_res.h |  5 +++--
 .../net/ethernet/mellanox/mlx5/core/en/tir.c    |  2 +-
 .../net/ethernet/mellanox/mlx5/core/en/tir.h    |  1 +
 .../ethernet/mellanox/mlx5/core/en_ethtool.c    | 17 ++++++++++++++---
 7 files changed, 38 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
index 0d8ccc7b6c11d..74cd111ee320c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.c
@@ -161,6 +161,7 @@ static void mlx5e_rss_params_init(struct mlx5e_rss *rss)
 {
 	enum mlx5_traffic_types tt;
 
+	rss->hash.symmetric = true;
 	rss->hash.hfunc = ETH_RSS_HASH_TOP;
 	netdev_rss_key_fill(rss->hash.toeplitz_hash_key,
 			    sizeof(rss->hash.toeplitz_hash_key));
@@ -566,7 +567,7 @@ int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 	return final_err;
 }
 
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc, bool *symmetric)
 {
 	if (indir)
 		memcpy(indir, rss->indir.table,
@@ -579,11 +580,14 @@ int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc)
 	if (hfunc)
 		*hfunc = rss->hash.hfunc;
 
+	if (symmetric)
+		*symmetric = rss->hash.symmetric;
+
 	return 0;
 }
 
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns)
 {
 	bool changed_indir = false;
@@ -623,6 +627,11 @@ int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
 		       rss->indir.actual_table_size * sizeof(*rss->indir.table));
 	}
 
+	if (symmetric) {
+		rss->hash.symmetric = *symmetric;
+		changed_hash = true;
+	}
+
 	if (changed_indir && rss->enabled) {
 		err = mlx5e_rss_apply(rss, rqns, vhca_ids, num_rqns);
 		if (err) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
index 72089f5f473c2..8ac902190010b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rss.h
@@ -47,9 +47,9 @@ void mlx5e_rss_disable(struct mlx5e_rss *rss);
 
 int mlx5e_rss_packet_merge_set_param(struct mlx5e_rss *rss,
 				     struct mlx5e_packet_merge_param *pkt_merge_param);
-int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc);
+int mlx5e_rss_get_rxfh(struct mlx5e_rss *rss, u32 *indir, u8 *key, u8 *hfunc, bool *symmetric);
 int mlx5e_rss_set_rxfh(struct mlx5e_rss *rss, const u32 *indir,
-		       const u8 *key, const u8 *hfunc,
+		       const u8 *key, const u8 *hfunc, const bool *symmetric,
 		       u32 *rqns, u32 *vhca_ids, unsigned int num_rqns);
 struct mlx5e_rss_params_hash mlx5e_rss_get_hash(struct mlx5e_rss *rss);
 u8 mlx5e_rss_get_hash_fields(struct mlx5e_rss *rss, enum mlx5_traffic_types tt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
index 9d8b2f5f6c967..5fcbe47337b08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.c
@@ -194,7 +194,7 @@ void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int n
 }
 
 int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc)
+			      u32 *indir, u8 *key, u8 *hfunc, bool *symmetric)
 {
 	struct mlx5e_rss *rss;
 
@@ -205,11 +205,12 @@ int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc);
+	return mlx5e_rss_get_rxfh(rss, indir, key, hfunc, symmetric);
 }
 
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc)
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric)
 {
 	u32 *vhca_ids = get_vhca_ids(res, 0);
 	struct mlx5e_rss *rss;
@@ -221,8 +222,8 @@ int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
 	if (!rss)
 		return -ENOENT;
 
-	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, res->rss_rqns, vhca_ids,
-				  res->rss_nch);
+	return mlx5e_rss_set_rxfh(rss, indir, key, hfunc, symmetric,
+				  res->rss_rqns, vhca_ids, res->rss_nch);
 }
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
index 05b438043bcb3..3e09d91281af9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rx_res.h
@@ -49,9 +49,10 @@ void mlx5e_rx_res_xsk_update(struct mlx5e_rx_res *res, struct mlx5e_channels *ch
 /* Configuration API */
 void mlx5e_rx_res_rss_set_indir_uniform(struct mlx5e_rx_res *res, unsigned int nch);
 int mlx5e_rx_res_rss_get_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      u32 *indir, u8 *key, u8 *hfunc);
+			      u32 *indir, u8 *key, u8 *hfunc, bool *symmetric);
 int mlx5e_rx_res_rss_set_rxfh(struct mlx5e_rx_res *res, u32 rss_idx,
-			      const u32 *indir, const u8 *key, const u8 *hfunc);
+			      const u32 *indir, const u8 *key, const u8 *hfunc,
+			      const bool *symmetric);
 
 int mlx5e_rx_res_rss_get_hash_fields(struct mlx5e_rx_res *res, u32 rss_idx,
 				     enum mlx5_traffic_types tt);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
index 11f724ad90dbf..19499072f67f6 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.c
@@ -124,7 +124,7 @@ void mlx5e_tir_builder_build_rss(struct mlx5e_tir_builder *builder,
 		const size_t len = MLX5_FLD_SZ_BYTES(tirc, rx_hash_toeplitz_key);
 		void *rss_key = MLX5_ADDR_OF(tirc, tirc, rx_hash_toeplitz_key);
 
-		MLX5_SET(tirc, tirc, rx_hash_symmetric, 1);
+		MLX5_SET(tirc, tirc, rx_hash_symmetric, rss_hash->symmetric);
 		memcpy(rss_key, rss_hash->toeplitz_hash_key, len);
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
index 857a84bcd53af..e8df3aaf6562f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tir.h
@@ -9,6 +9,7 @@
 struct mlx5e_rss_params_hash {
 	u8 hfunc;
 	u8 toeplitz_hash_key[40];
+	bool symmetric;
 };
 
 struct mlx5e_rss_params_traffic_type {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 1bf2212a0bb6f..0cb515fa179f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1456,18 +1456,27 @@ static int mlx5e_get_rxfh(struct net_device *netdev, struct ethtool_rxfh_param *
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	u32 rss_context = rxfh->rss_context;
+	bool symmetric;
 	int err;
 
 	mutex_lock(&priv->state_lock);
 	err = mlx5e_rx_res_rss_get_rxfh(priv->rx_res, rss_context,
-					rxfh->indir, rxfh->key, &rxfh->hfunc);
+					rxfh->indir, rxfh->key, &rxfh->hfunc, &symmetric);
 	mutex_unlock(&priv->state_lock);
-	return err;
+
+	if (err)
+		return err;
+
+	if (symmetric)
+		rxfh->input_xfrm = RXH_XFRM_SYM_OR_XOR;
+
+	return 0;
 }
 
 static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxfh,
 			  struct netlink_ext_ack *extack)
 {
+	bool symmetric = rxfh->input_xfrm == RXH_XFRM_SYM_OR_XOR;
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	u32 *rss_context = &rxfh->rss_context;
 	u8 hfunc = rxfh->hfunc;
@@ -1502,7 +1511,8 @@ static int mlx5e_set_rxfh(struct net_device *dev, struct ethtool_rxfh_param *rxf
 
 	err = mlx5e_rx_res_rss_set_rxfh(priv->rx_res, *rss_context,
 					rxfh->indir, rxfh->key,
-					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc);
+					hfunc == ETH_RSS_HASH_NO_CHANGE ? NULL : &hfunc,
+					rxfh->input_xfrm == RXH_XFRM_NO_CHANGE ? NULL : &symmetric);
 
 unlock:
 	mutex_unlock(&priv->state_lock);
@@ -2611,6 +2621,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = {
 				     ETHTOOL_COALESCE_MAX_FRAMES |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE |
 				     ETHTOOL_COALESCE_USE_CQE,
+	.supported_input_xfrm = RXH_XFRM_SYM_OR_XOR,
 	.get_drvinfo       = mlx5e_get_drvinfo,
 	.get_link          = ethtool_op_get_link,
 	.get_link_ext_state  = mlx5e_get_link_ext_state,

From 0163250039c3a861f922a293f6108880b2d4516f Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 24 Feb 2025 19:44:15 +0200
Subject: [PATCH 1166/2753] selftests: drv-net: Make rand_port() get a port
 more reliably

Instead of guessing a port and checking whether it's available, get an
available port from the OS.

Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250224174416.499070-4-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/lib/py/utils.py | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index d879700ef2b98..a6af97c7e2838 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -187,18 +187,11 @@ def ethtool(args, json=None, ns=None, host=None):
 
 def rand_port():
     """
-    Get a random unprivileged port, try to make sure it's not already used.
+    Get a random unprivileged port.
     """
-    for _ in range(1000):
-        port = random.randint(10000, 65535)
-        try:
-            with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
-                s.bind(("", port))
-            return port
-        except OSError as e:
-            if e.errno != errno.EADDRINUSE:
-                raise
-    raise Exception("Can't find any free unprivileged port")
+    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+        s.bind(("", 0))
+        return s.getsockname()[1]
 
 
 def wait_port_listen(port, proto="tcp", ns=None, host=None, sleep=0.005, deadline=5):

From da87cabaf87702d43a016d255f11be5379892b6a Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 24 Feb 2025 19:44:16 +0200
Subject: [PATCH 1167/2753] selftests: drv-net-hw: Add a test for symmetric RSS
 hash

Add a selftest that verifies symmetric RSS hash is working as intended.
The test runs iterations of traffic, swapping the src/dst UDP ports, and
verifies that the same RX queue is receiving the traffic in both cases.

Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250224174416.499070-5-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/hw/Makefile |  1 +
 .../drivers/net/hw/rss_input_xfrm.py          | 87 +++++++++++++++++++
 tools/testing/selftests/net/lib/py/utils.py   |  4 +-
 3 files changed, 90 insertions(+), 2 deletions(-)
 create mode 100755 tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index ae783e18be83b..b2be14d0cc56e 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -15,6 +15,7 @@ TEST_PROGS = \
 	nic_performance.py \
 	pp_alloc_fail.py \
 	rss_ctx.py \
+	rss_input_xfrm.py \
 	tso.py \
 	#
 
diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
new file mode 100755
index 0000000000000..53bb08cc29ec3
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+import multiprocessing
+import socket
+from lib.py import ksft_run, ksft_exit, ksft_eq, ksft_ge, cmd, fd_read_timeout
+from lib.py import NetDrvEpEnv
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import KsftSkipEx, KsftFailEx
+from lib.py import rand_port
+
+
+def traffic(cfg, local_port, remote_port, ipver):
+    af_inet = socket.AF_INET if ipver == "4" else socket.AF_INET6
+    sock = socket.socket(af_inet, socket.SOCK_DGRAM)
+    sock.bind(("", local_port))
+    sock.connect((cfg.remote_addr_v[ipver], remote_port))
+    tgt = f"{ipver}:[{cfg.addr_v[ipver]}]:{local_port},sourceport={remote_port}"
+    cmd("echo a | socat - UDP" + tgt, host=cfg.remote)
+    fd_read_timeout(sock.fileno(), 5)
+    return sock.getsockopt(socket.SOL_SOCKET, socket.SO_INCOMING_CPU)
+
+
+def test_rss_input_xfrm(cfg, ipver):
+    """
+    Test symmetric input_xfrm.
+    If symmetric RSS hash is configured, send traffic twice, swapping the
+    src/dst UDP ports, and verify that the same queue is receiving the traffic
+    in both cases (IPs are constant).
+    """
+
+    if multiprocessing.cpu_count() < 2:
+        raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
+
+    input_xfrm = cfg.ethnl.rss_get(
+        {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
+
+    # Check for symmetric xor/or-xor
+    if not input_xfrm or (input_xfrm != 1 and input_xfrm != 2):
+        raise KsftSkipEx("Symmetric RSS hash not requested")
+
+    cpus = set()
+    successful = 0
+    for _ in range(100):
+        try:
+            port1 = rand_port(socket.SOCK_DGRAM)
+            port2 = rand_port(socket.SOCK_DGRAM)
+            cpu1 = traffic(cfg, port1, port2, ipver)
+            cpu2 = traffic(cfg, port2, port1, ipver)
+            cpus.update([cpu1, cpu2])
+            ksft_eq(
+                cpu1, cpu2, comment=f"Received traffic on different cpus with ports ({port1 = }, {port2 = }) while symmetric hash is configured")
+
+            successful += 1
+            if successful == 10:
+                break
+        except:
+            continue
+    else:
+        raise KsftFailEx("Failed to run traffic")
+
+    ksft_ge(len(cpus), 2,
+            comment=f"Received traffic on less than two cpus {cpus = }")
+
+
+def test_rss_input_xfrm_ipv4(cfg):
+    cfg.require_ipver("4")
+    test_rss_input_xfrm(cfg, "4")
+
+
+def test_rss_input_xfrm_ipv6(cfg):
+    cfg.require_ipver("6")
+    test_rss_input_xfrm(cfg, "6")
+
+
+def main() -> None:
+    with NetDrvEpEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netdevnl = NetdevFamily()
+
+        ksft_run([test_rss_input_xfrm_ipv4, test_rss_input_xfrm_ipv6],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/net/lib/py/utils.py b/tools/testing/selftests/net/lib/py/utils.py
index a6af97c7e2838..34470d65d871a 100644
--- a/tools/testing/selftests/net/lib/py/utils.py
+++ b/tools/testing/selftests/net/lib/py/utils.py
@@ -185,11 +185,11 @@ def ethtool(args, json=None, ns=None, host=None):
     return tool('ethtool', args, json=json, ns=ns, host=host)
 
 
-def rand_port():
+def rand_port(type=socket.SOCK_STREAM):
     """
     Get a random unprivileged port.
     """
-    with socket.socket(socket.AF_INET6, socket.SOCK_STREAM) as s:
+    with socket.socket(socket.AF_INET6, type) as s:
         s.bind(("", 0))
         return s.getsockname()[1]
 

From 8fa19c2c69fbf1f615e84d24d75dcf001ea91ccb Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Mon, 24 Feb 2025 15:05:06 +0100
Subject: [PATCH 1168/2753] net: wangxun: fix LIBWX dependencies

Selecting LIBWX requires that its dependencies are met first:

WARNING: unmet direct dependencies detected for LIBWX
  Depends on [m]: NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_WANGXUN [=y] && PTP_1588_CLOCK_OPTIONAL [=m]
  Selected by [y]:
  - TXGBE [=y] && NETDEVICES [=y] && ETHERNET [=y] && NET_VENDOR_WANGXUN [=y] && PCI [=y] && COMMON_CLK [=y] && I2C_DESIGNWARE_PLATFORM [=y]
ld.lld-21: error: undefined symbol: ptp_schedule_worker
>>> referenced by wx_ptp.c:747 (/home/arnd/arm-soc/drivers/net/ethernet/wangxun/libwx/wx_ptp.c:747)
>>>               drivers/net/ethernet/wangxun/libwx/wx_ptp.o:(wx_ptp_reset) in archive vmlinux.a

Add the smae dependency on PTP_1588_CLOCK_OPTIONAL to the two driver
using this library module.

Fixes: 06e75161b9d4 ("net: wangxun: Add support for PTP clock")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250224140516.1168214-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/Kconfig | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/wangxun/Kconfig b/drivers/net/ethernet/wangxun/Kconfig
index 6b60173fe1f50..47e3e8434b9ef 100644
--- a/drivers/net/ethernet/wangxun/Kconfig
+++ b/drivers/net/ethernet/wangxun/Kconfig
@@ -26,6 +26,7 @@ config LIBWX
 config NGBE
 	tristate "Wangxun(R) GbE PCI Express adapters support"
 	depends on PCI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select LIBWX
 	select PHYLINK
 	help
@@ -43,6 +44,7 @@ config TXGBE
 	depends on PCI
 	depends on COMMON_CLK
 	depends on I2C_DESIGNWARE_PLATFORM
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select MARVELL_10G_PHY
 	select REGMAP
 	select PHYLINK

From f865c24bc55158313d5779fc81116023a6940ca3 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Mon, 24 Feb 2025 19:11:50 +0100
Subject: [PATCH 1169/2753] mptcp: always handle address removal under msk
 socket lock

Syzkaller reported a lockdep splat in the PM control path:

  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 sock_owned_by_me include/net/sock.h:1711 [inline]
  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 msk_owned_by_me net/mptcp/protocol.h:363 [inline]
  WARNING: CPU: 0 PID: 6693 at ./include/net/sock.h:1711 mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788
  Modules linked in:
  CPU: 0 UID: 0 PID: 6693 Comm: syz.0.205 Not tainted 6.14.0-rc2-syzkaller-00303-gad1b832bf1cf #0
  Hardware name: Google Compute Engine/Google Compute Engine, BIOS Google 12/27/2024
  RIP: 0010:sock_owned_by_me include/net/sock.h:1711 [inline]
  RIP: 0010:msk_owned_by_me net/mptcp/protocol.h:363 [inline]
  RIP: 0010:mptcp_pm_nl_addr_send_ack+0x57c/0x610 net/mptcp/pm_netlink.c:788
  Code: 5b 41 5c 41 5d 41 5e 41 5f 5d c3 cc cc cc cc e8 ca 7b d3 f5 eb b9 e8 c3 7b d3 f5 90 0f 0b 90 e9 dd fb ff ff e8 b5 7b d3 f5 90 <0f> 0b 90 e9 3e fb ff ff 44 89 f1 80 e1 07 38 c1 0f 8c eb fb ff ff
  RSP: 0000:ffffc900034f6f60 EFLAGS: 00010283
  RAX: ffffffff8bee3c2b RBX: 0000000000000001 RCX: 0000000000080000
  RDX: ffffc90004d42000 RSI: 000000000000a407 RDI: 000000000000a408
  RBP: ffffc900034f7030 R08: ffffffff8bee37f6 R09: 0100000000000000
  R10: dffffc0000000000 R11: ffffed100bcc62e4 R12: ffff88805e6316e0
  R13: ffff88805e630c00 R14: dffffc0000000000 R15: ffff88805e630c00
  FS:  00007f7e9a7e96c0(0000) GS:ffff8880b8600000(0000) knlGS:0000000000000000
  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  CR2: 0000001b2fd18ff8 CR3: 0000000032c24000 CR4: 00000000003526f0
  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  Call Trace:
   <TASK>
   mptcp_pm_remove_addr+0x103/0x1d0 net/mptcp/pm.c:59
   mptcp_pm_remove_anno_addr+0x1f4/0x2f0 net/mptcp/pm_netlink.c:1486
   mptcp_nl_remove_subflow_and_signal_addr net/mptcp/pm_netlink.c:1518 [inline]
   mptcp_pm_nl_del_addr_doit+0x118d/0x1af0 net/mptcp/pm_netlink.c:1629
   genl_family_rcv_msg_doit net/netlink/genetlink.c:1115 [inline]
   genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
   genl_rcv_msg+0xb1f/0xec0 net/netlink/genetlink.c:1210
   netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2543
   genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
   netlink_unicast_kernel net/netlink/af_netlink.c:1322 [inline]
   netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1348
   netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1892
   sock_sendmsg_nosec net/socket.c:718 [inline]
   __sock_sendmsg+0x221/0x270 net/socket.c:733
   ____sys_sendmsg+0x53a/0x860 net/socket.c:2573
   ___sys_sendmsg net/socket.c:2627 [inline]
   __sys_sendmsg+0x269/0x350 net/socket.c:2659
   do_syscall_x64 arch/x86/entry/common.c:52 [inline]
   do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
   entry_SYSCALL_64_after_hwframe+0x77/0x7f
  RIP: 0033:0x7f7e9998cde9
  Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
  RSP: 002b:00007f7e9a7e9038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
  RAX: ffffffffffffffda RBX: 00007f7e99ba5fa0 RCX: 00007f7e9998cde9
  RDX: 000000002000c094 RSI: 0000400000000000 RDI: 0000000000000007
  RBP: 00007f7e99a0e2a0 R08: 0000000000000000 R09: 0000000000000000
  R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
  R13: 0000000000000000 R14: 00007f7e99ba5fa0 R15: 00007fff49231088

Indeed the PM can try to send a RM_ADDR over a msk without acquiring
first the msk socket lock.

The bugged code-path comes from an early optimization: when there
are no subflows, the PM should (usually) not send RM_ADDR
notifications.

The above statement is incorrect, as without locks another process
could concurrent create a new subflow and cause the RM_ADDR generation.

Additionally the supposed optimization is not very effective even
performance-wise, as most mptcp sockets should have at least one
subflow: the MPC one.

Address the issue removing the buggy code path, the existing "slow-path"
will handle correctly even the edge case.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reported-by: syzbot+cd3ce3d03a3393ae9700@syzkaller.appspotmail.com
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/546
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-1-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 572d160edca33..c0e47f4f7b1aa 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1514,11 +1514,6 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		if (mptcp_pm_is_userspace(msk))
 			goto next;
 
-		if (list_empty(&msk->conn_list)) {
-			mptcp_pm_remove_anno_addr(msk, addr, false);
-			goto next;
-		}
-
 		lock_sock(sk);
 		remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr);
 		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&

From 8668860b0ad32a13fcd6c94a0995b7aa7638c9ef Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 24 Feb 2025 19:11:51 +0100
Subject: [PATCH 1170/2753] mptcp: reset when MPTCP opts are dropped after join

Before this patch, if the checksum was not used, the subflow was only
reset if map_data_len was != 0. If there were no MPTCP options or an
invalid mapping, map_data_len was not set to the data len, and then the
subflow was not reset as it should have been, leaving the MPTCP
connection in a wrong fallback mode.

This map_data_len condition has been introduced to handle the reception
of the infinite mapping. Instead, a new dedicated mapping error could
have been returned and treated as a special case. However, the commit
31bf11de146c ("mptcp: introduce MAPPING_BAD_CSUM") has been introduced
by Paolo Abeni soon after, and backported later on to stable. It better
handle the csum case, and it means the exception for valid_csum_seen in
subflow_can_fallback(), plus this one for the infinite mapping in
subflow_check_data_avail(), are no longer needed.

In other words, the code can be simplified there: a fallback should only
be done if msk->allow_infinite_fallback is set. This boolean is set to
false once MPTCP-specific operations acting on the whole MPTCP
connection vs the initial path have been done, e.g. a second path has
been created, or an MPTCP re-injection -- yes, possible even with a
single subflow. The subflow_can_fallback() helper can then be dropped,
and replaced by this single condition.

This also makes the code clearer: a fallback should only be done if it
is possible to do so.

While at it, no need to set map_data_len to 0 in get_mapping_status()
for the infinite mapping case: it will be set to skb->len just after, at
the end of subflow_check_data_avail(), and not read in between.

Fixes: f8d4bcacff3b ("mptcp: infinite mapping receiving")
Cc: stable@vger.kernel.org
Reported-by: Chester A. Unal <chester.a.unal@xpedite-tech.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/544
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Tested-by: Chester A. Unal <chester.a.unal@xpedite-tech.com>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-2-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/subflow.c | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index dfcbef9c46246..9f18217dddc86 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -1142,7 +1142,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
 	if (data_len == 0) {
 		pr_debug("infinite mapping received\n");
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
-		subflow->map_data_len = 0;
 		return MAPPING_INVALID;
 	}
 
@@ -1286,18 +1285,6 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 		mptcp_schedule_work(sk);
 }
 
-static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
-{
-	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
-
-	if (subflow->mp_join)
-		return false;
-	else if (READ_ONCE(msk->csum_enabled))
-		return !subflow->valid_csum_seen;
-	else
-		return READ_ONCE(msk->allow_infinite_fallback);
-}
-
 static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1393,7 +1380,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
 			return true;
 		}
 
-		if (!subflow_can_fallback(subflow) && subflow->map_data_len) {
+		if (!READ_ONCE(msk->allow_infinite_fallback)) {
 			/* fatal protocol error, close the socket.
 			 * subflow_error_report() will introduce the appropriate barriers
 			 */

From db75a16813aabae3b78c06b1b99f5e314c1f55d3 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 24 Feb 2025 19:11:52 +0100
Subject: [PATCH 1171/2753] mptcp: safety check before fallback

Recently, some fallback have been initiated, while the connection was
not supposed to fallback.

Add a safety check with a warning to detect when an wrong attempt to
fallback is being done. This should help detecting any future issues
quicker.

Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250224-net-mptcp-misc-fixes-v1-3-f550f636b435@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.h | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f6a207958459d..ad21925af0612 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1199,6 +1199,8 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
 		pr_debug("TCP fallback already done (msk=%p)\n", msk);
 		return;
 	}
+	if (WARN_ON_ONCE(!READ_ONCE(msk->allow_infinite_fallback)))
+		return;
 	set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
 }
 

From a6aa36e957a1bfb5341986dec32d013d23228fe1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 14 Feb 2025 13:14:34 +0900
Subject: [PATCH 1172/2753] block: Remove zone write plugs when handling native
 zone append writes

For devices that natively support zone append operations,
REQ_OP_ZONE_APPEND BIOs are not processed through zone write plugging
and are immediately issued to the zoned device. This means that there is
no write pointer offset tracking done for these operations and that a
zone write plug is not necessary.

However, when receiving a zone append BIO, we may already have a zone
write plug for the target zone if that zone was previously partially
written using regular write operations. In such case, since the write
pointer offset of the zone write plug is not incremented by the amount
of sectors appended to the zone, 2 issues arise:
1) we risk leaving the plug in the disk hash table if the zone is fully
   written using zone append or regular write operations, because the
   write pointer offset will never reach the "zone full" state.
2) Regular write operations that are issued after zone append operations
   will always be failed by blk_zone_wplug_prepare_bio() as the write
   pointer alignment check will fail, even if the user correctly
   accounted for the zone append operations and issued the regular
   writes with a correct sector.

Avoid these issues by immediately removing the zone write plug of zones
that are the target of zone append operations when blk_zone_plug_bio()
is called. The new function blk_zone_wplug_handle_native_zone_append()
implements this for devices that natively support zone append. The
removal of the zone write plug using disk_remove_zone_wplug() requires
aborting all plugged regular write using disk_zone_wplug_abort() as
otherwise the plugged write BIOs would never be executed (with the plug
removed, the completion path will never see again the zone write plug as
disk_get_zone_wplug() will return NULL). Rate-limited warnings are added
to blk_zone_wplug_handle_native_zone_append() and to
disk_zone_wplug_abort() to signal this.

Since blk_zone_wplug_handle_native_zone_append() is called in the hot
path for operations that will not be plugged, disk_get_zone_wplug() is
optimized under the assumption that a user issuing zone append
operations is not at the same time issuing regular writes and that there
are no hashed zone write plugs. The struct gendisk atomic counter
nr_zone_wplugs is added to check this, with this counter incremented in
disk_insert_zone_wplug() and decremented in disk_remove_zone_wplug().

To be consistent with this fix, we do not need to fill the zone write
plug hash table with zone write plugs for zones that are partially
written for a device that supports native zone append operations.
So modify blk_revalidate_seq_zone() to return early to avoid allocating
and inserting a zone write plug for partially written sequential zones
if the device natively supports zone append.

Reported-by: Jorgen Hansen <Jorgen.Hansen@wdc.com>
Fixes: 9b1ce7f0c6f8 ("block: Implement zone append emulation")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Tested-by: Jorgen Hansen <Jorgen.Hansen@wdc.com>
Link: https://lore.kernel.org/r/20250214041434.82564-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-zoned.c      | 76 ++++++++++++++++++++++++++++++++++++++----
 include/linux/blkdev.h |  7 ++--
 2 files changed, 73 insertions(+), 10 deletions(-)

diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 761ea662ddc34..0c77244a35c92 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -410,13 +410,14 @@ static bool disk_insert_zone_wplug(struct gendisk *disk,
 		}
 	}
 	hlist_add_head_rcu(&zwplug->node, &disk->zone_wplugs_hash[idx]);
+	atomic_inc(&disk->nr_zone_wplugs);
 	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
 
 	return true;
 }
 
-static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
-						  sector_t sector)
+static struct blk_zone_wplug *disk_get_hashed_zone_wplug(struct gendisk *disk,
+							 sector_t sector)
 {
 	unsigned int zno = disk_zone_no(disk, sector);
 	unsigned int idx = hash_32(zno, disk->zone_wplugs_hash_bits);
@@ -437,6 +438,15 @@ static struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
 	return NULL;
 }
 
+static inline struct blk_zone_wplug *disk_get_zone_wplug(struct gendisk *disk,
+							 sector_t sector)
+{
+	if (!atomic_read(&disk->nr_zone_wplugs))
+		return NULL;
+
+	return disk_get_hashed_zone_wplug(disk, sector);
+}
+
 static void disk_free_zone_wplug_rcu(struct rcu_head *rcu_head)
 {
 	struct blk_zone_wplug *zwplug =
@@ -503,6 +513,7 @@ static void disk_remove_zone_wplug(struct gendisk *disk,
 	zwplug->flags |= BLK_ZONE_WPLUG_UNHASHED;
 	spin_lock_irqsave(&disk->zone_wplugs_lock, flags);
 	hlist_del_init_rcu(&zwplug->node);
+	atomic_dec(&disk->nr_zone_wplugs);
 	spin_unlock_irqrestore(&disk->zone_wplugs_lock, flags);
 	disk_put_zone_wplug(zwplug);
 }
@@ -593,6 +604,11 @@ static void disk_zone_wplug_abort(struct blk_zone_wplug *zwplug)
 {
 	struct bio *bio;
 
+	if (bio_list_empty(&zwplug->bio_list))
+		return;
+
+	pr_warn_ratelimited("%s: zone %u: Aborting plugged BIOs\n",
+			    zwplug->disk->disk_name, zwplug->zone_no);
 	while ((bio = bio_list_pop(&zwplug->bio_list)))
 		blk_zone_wplug_bio_io_error(zwplug, bio);
 }
@@ -1040,6 +1056,47 @@ static bool blk_zone_wplug_handle_write(struct bio *bio, unsigned int nr_segs)
 	return true;
 }
 
+static void blk_zone_wplug_handle_native_zone_append(struct bio *bio)
+{
+	struct gendisk *disk = bio->bi_bdev->bd_disk;
+	struct blk_zone_wplug *zwplug;
+	unsigned long flags;
+
+	/*
+	 * We have native support for zone append operations, so we are not
+	 * going to handle @bio through plugging. However, we may already have a
+	 * zone write plug for the target zone if that zone was previously
+	 * partially written using regular writes. In such case, we risk leaving
+	 * the plug in the disk hash table if the zone is fully written using
+	 * zone append operations. Avoid this by removing the zone write plug.
+	 */
+	zwplug = disk_get_zone_wplug(disk, bio->bi_iter.bi_sector);
+	if (likely(!zwplug))
+		return;
+
+	spin_lock_irqsave(&zwplug->lock, flags);
+
+	/*
+	 * We are about to remove the zone write plug. But if the user
+	 * (mistakenly) has issued regular writes together with native zone
+	 * append, we must aborts the writes as otherwise the plugged BIOs would
+	 * not be executed by the plug BIO work as disk_get_zone_wplug() will
+	 * return NULL after the plug is removed. Aborting the plugged write
+	 * BIOs is consistent with the fact that these writes will most likely
+	 * fail anyway as there is no ordering guarantees between zone append
+	 * operations and regular write operations.
+	 */
+	if (!bio_list_empty(&zwplug->bio_list)) {
+		pr_warn_ratelimited("%s: zone %u: Invalid mix of zone append and regular writes\n",
+				    disk->disk_name, zwplug->zone_no);
+		disk_zone_wplug_abort(zwplug);
+	}
+	disk_remove_zone_wplug(disk, zwplug);
+	spin_unlock_irqrestore(&zwplug->lock, flags);
+
+	disk_put_zone_wplug(zwplug);
+}
+
 /**
  * blk_zone_plug_bio - Handle a zone write BIO with zone write plugging
  * @bio: The BIO being submitted
@@ -1096,8 +1153,10 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 	 */
 	switch (bio_op(bio)) {
 	case REQ_OP_ZONE_APPEND:
-		if (!bdev_emulates_zone_append(bdev))
+		if (!bdev_emulates_zone_append(bdev)) {
+			blk_zone_wplug_handle_native_zone_append(bio);
 			return false;
+		}
 		fallthrough;
 	case REQ_OP_WRITE:
 	case REQ_OP_WRITE_ZEROES:
@@ -1284,6 +1343,7 @@ static int disk_alloc_zone_resources(struct gendisk *disk,
 {
 	unsigned int i;
 
+	atomic_set(&disk->nr_zone_wplugs, 0);
 	disk->zone_wplugs_hash_bits =
 		min(ilog2(pool_size) + 1, BLK_ZONE_WPLUG_MAX_HASH_BITS);
 
@@ -1338,6 +1398,7 @@ static void disk_destroy_zone_wplugs_hash_table(struct gendisk *disk)
 		}
 	}
 
+	WARN_ON_ONCE(atomic_read(&disk->nr_zone_wplugs));
 	kfree(disk->zone_wplugs_hash);
 	disk->zone_wplugs_hash = NULL;
 	disk->zone_wplugs_hash_bits = 0;
@@ -1550,11 +1611,12 @@ static int blk_revalidate_seq_zone(struct blk_zone *zone, unsigned int idx,
 	}
 
 	/*
-	 * We need to track the write pointer of all zones that are not
-	 * empty nor full. So make sure we have a zone write plug for
-	 * such zone if the device has a zone write plug hash table.
+	 * If the device needs zone append emulation, we need to track the
+	 * write pointer of all zones that are not empty nor full. So make sure
+	 * we have a zone write plug for such zone if the device has a zone
+	 * write plug hash table.
 	 */
-	if (!disk->zone_wplugs_hash)
+	if (!queue_emulates_zone_append(disk->queue) || !disk->zone_wplugs_hash)
 		return 0;
 
 	disk_zone_wplug_sync_wp_offset(disk, zone);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 58ff5aca83b67..d37751789bf58 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -196,10 +196,11 @@ struct gendisk {
 	unsigned int		zone_capacity;
 	unsigned int		last_zone_capacity;
 	unsigned long __rcu	*conv_zones_bitmap;
-	unsigned int            zone_wplugs_hash_bits;
-	spinlock_t              zone_wplugs_lock;
+	unsigned int		zone_wplugs_hash_bits;
+	atomic_t		nr_zone_wplugs;
+	spinlock_t		zone_wplugs_lock;
 	struct mempool_s	*zone_wplugs_pool;
-	struct hlist_head       *zone_wplugs_hash;
+	struct hlist_head	*zone_wplugs_hash;
 	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 

From 91c8d8e4b7a38dc099b26e14b22f814ca4e75089 Mon Sep 17 00:00:00 2001
From: John Daley <johndale@cisco.com>
Date: Mon, 24 Feb 2025 15:43:50 -0800
Subject: [PATCH 1173/2753] enic: add dependency on Page Pool

Driver was not configured to select page_pool, causing a compile error
if page pool module was not already selected.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502211253.3XRosM9I-lkp@intel.com/
Fixes: d24cb52b2d8a ("enic: Use the Page Pool API for RX")
Reviewed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250224234350.23157-2-johndale@cisco.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cisco/enic/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/cisco/enic/Kconfig b/drivers/net/ethernet/cisco/enic/Kconfig
index ad80c0fa96a68..96709875fe4f2 100644
--- a/drivers/net/ethernet/cisco/enic/Kconfig
+++ b/drivers/net/ethernet/cisco/enic/Kconfig
@@ -6,5 +6,6 @@
 config ENIC
 	tristate "Cisco VIC Ethernet NIC Support"
 	depends on PCI
+	select PAGE_POOL
 	help
 	  This enables the support for the Cisco VIC Ethernet card.

From 79990cf5e7aded76d0c092c9f5ed31eb1c75e02c Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Mon, 24 Feb 2025 11:06:41 -0800
Subject: [PATCH 1174/2753] ice: Fix deinitializing VF in error path

If ice_ena_vfs() fails after calling ice_create_vf_entries(), it frees
all VFs without removing them from snapshot PF-VF mailbox list, leading
to list corruption.

Reproducer:
  devlink dev eswitch set $PF1_PCI mode switchdev
  ip l s $PF1 up
  ip l s $PF1 promisc on
  sleep 1
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs
  sleep 1
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs

Trace (minimized):
  list_add corruption. next->prev should be prev (ffff8882e241c6f0), but was 0000000000000000. (next=ffff888455da1330).
  kernel BUG at lib/list_debug.c:29!
  RIP: 0010:__list_add_valid_or_report+0xa6/0x100
   ice_mbx_init_vf_info+0xa7/0x180 [ice]
   ice_initialize_vf_entry+0x1fa/0x250 [ice]
   ice_sriov_configure+0x8d7/0x1520 [ice]
   ? __percpu_ref_switch_mode+0x1b1/0x5d0
   ? __pfx_ice_sriov_configure+0x10/0x10 [ice]

Sometimes a KASAN report can be seen instead with a similar stack trace:
  BUG: KASAN: use-after-free in __list_add_valid_or_report+0xf1/0x100

VFs are added to this list in ice_mbx_init_vf_info(), but only removed
in ice_free_vfs(). Move the removing to ice_free_vf_entries(), which is
also being called in other places where VFs are being removed (including
ice_free_vfs() itself).

Fixes: 8cd8a6b17d27 ("ice: move VF overflow message count into struct ice_mbx_vf_info")
Reported-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com
Reviewed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-2-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_sriov.c          | 5 +----
 drivers/net/ethernet/intel/ice/ice_vf_lib.c         | 8 ++++++++
 drivers/net/ethernet/intel/ice/ice_vf_lib_private.h | 1 +
 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index b83f99c01d91b..8aabf7749aa5e 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -36,6 +36,7 @@ static void ice_free_vf_entries(struct ice_pf *pf)
 
 	hash_for_each_safe(vfs->table, bkt, tmp, vf, entry) {
 		hash_del_rcu(&vf->entry);
+		ice_deinitialize_vf_entry(vf);
 		ice_put_vf(vf);
 	}
 }
@@ -193,10 +194,6 @@ void ice_free_vfs(struct ice_pf *pf)
 			wr32(hw, GLGEN_VFLRSTAT(reg_idx), BIT(bit_idx));
 		}
 
-		/* clear malicious info since the VF is getting released */
-		if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
-			list_del(&vf->mbx_info.list_entry);
-
 		mutex_unlock(&vf->cfg_lock);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib.c b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
index c7c0c2f50c265..815ad0bfe8326 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib.c
@@ -1036,6 +1036,14 @@ void ice_initialize_vf_entry(struct ice_vf *vf)
 	mutex_init(&vf->cfg_lock);
 }
 
+void ice_deinitialize_vf_entry(struct ice_vf *vf)
+{
+	struct ice_pf *pf = vf->pf;
+
+	if (!ice_is_feature_supported(pf, ICE_F_MBX_LIMIT))
+		list_del(&vf->mbx_info.list_entry);
+}
+
 /**
  * ice_dis_vf_qs - Disable the VF queues
  * @vf: pointer to the VF structure
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
index 0c7e77c0a09fa..5392b04049862 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
+++ b/drivers/net/ethernet/intel/ice/ice_vf_lib_private.h
@@ -24,6 +24,7 @@
 #endif
 
 void ice_initialize_vf_entry(struct ice_vf *vf);
+void ice_deinitialize_vf_entry(struct ice_vf *vf);
 void ice_dis_vf_qs(struct ice_vf *vf);
 int ice_check_vf_init(struct ice_vf *vf);
 enum virtchnl_status_code ice_err_to_virt_err(int err);

From 5c07be96d8b3f8447e980f29b967bf2e1d7ac732 Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Mon, 24 Feb 2025 11:06:42 -0800
Subject: [PATCH 1175/2753] ice: Avoid setting default Rx VSI twice in
 switchdev setup

As part of switchdev environment setup, uplink VSI is configured as
default for both Tx and Rx. Default Rx VSI is also used by promiscuous
mode. If promisc mode is enabled and an attempt to enter switchdev mode
is made, the setup will fail because Rx VSI is already configured as
default (rule exists).

Reproducer:
  devlink dev eswitch set $PF1_PCI mode switchdev
  ip l s $PF1 up
  ip l s $PF1 promisc on
  echo 1 > /sys/class/net/$PF1/device/sriov_numvfs

In switchdev setup, use ice_set_dflt_vsi() instead of plain
ice_cfg_dflt_vsi(), which avoids repeating setting default VSI for Rx if
it's already configured.

Fixes: 50d62022f455 ("ice: default Tx rule instead of to queue")
Reported-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Closes: https://lore.kernel.org/intel-wired-lan/PH0PR11MB50138B635F2E5CEB7075325D961F2@PH0PR11MB5013.namprd11.prod.outlook.com
Reviewed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-3-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index fb527434b58b1..d649c197cf673 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -38,8 +38,7 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (ice_vsi_add_vlan_zero(uplink_vsi))
 		goto err_vlan_zero;
 
-	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,
-			     ICE_FLTR_RX))
+	if (ice_set_dflt_vsi(uplink_vsi))
 		goto err_def_rx;
 
 	if (ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, true,

From c6124f6fd3ca37d53ec5cbf62f9d9130ef439eca Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 24 Feb 2025 11:06:44 -0800
Subject: [PATCH 1176/2753] iavf: fix circular lock dependency with netdev_lock

We have recently seen reports of lockdep circular lock dependency warnings
when loading the iAVF driver:

[ 1504.790308] ======================================================
[ 1504.790309] WARNING: possible circular locking dependency detected
[ 1504.790310] 6.13.0 #net_next_rt.c2933b2befe2.el9 Not tainted
[ 1504.790311] ------------------------------------------------------
[ 1504.790312] kworker/u128:0/13566 is trying to acquire lock:
[ 1504.790313] ffff97d0e4738f18 (&dev->lock){+.+.}-{4:4}, at: register_netdevice+0x52c/0x710
[ 1504.790320]
[ 1504.790320] but task is already holding lock:
[ 1504.790321] ffff97d0e47392e8 (&adapter->crit_lock){+.+.}-{4:4}, at: iavf_finish_config+0x37/0x240 [iavf]
[ 1504.790330]
[ 1504.790330] which lock already depends on the new lock.
[ 1504.790330]
[ 1504.790330]
[ 1504.790330] the existing dependency chain (in reverse order) is:
[ 1504.790331]
[ 1504.790331] -> #1 (&adapter->crit_lock){+.+.}-{4:4}:
[ 1504.790333]        __lock_acquire+0x52d/0xbb0
[ 1504.790337]        lock_acquire+0xd9/0x330
[ 1504.790338]        mutex_lock_nested+0x4b/0xb0
[ 1504.790341]        iavf_finish_config+0x37/0x240 [iavf]
[ 1504.790347]        process_one_work+0x248/0x6d0
[ 1504.790350]        worker_thread+0x18d/0x330
[ 1504.790352]        kthread+0x10e/0x250
[ 1504.790354]        ret_from_fork+0x30/0x50
[ 1504.790357]        ret_from_fork_asm+0x1a/0x30
[ 1504.790361]
[ 1504.790361] -> #0 (&dev->lock){+.+.}-{4:4}:
[ 1504.790364]        check_prev_add+0xf1/0xce0
[ 1504.790366]        validate_chain+0x46a/0x570
[ 1504.790368]        __lock_acquire+0x52d/0xbb0
[ 1504.790370]        lock_acquire+0xd9/0x330
[ 1504.790371]        mutex_lock_nested+0x4b/0xb0
[ 1504.790372]        register_netdevice+0x52c/0x710
[ 1504.790374]        iavf_finish_config+0xfa/0x240 [iavf]
[ 1504.790379]        process_one_work+0x248/0x6d0
[ 1504.790381]        worker_thread+0x18d/0x330
[ 1504.790383]        kthread+0x10e/0x250
[ 1504.790385]        ret_from_fork+0x30/0x50
[ 1504.790387]        ret_from_fork_asm+0x1a/0x30
[ 1504.790389]
[ 1504.790389] other info that might help us debug this:
[ 1504.790389]
[ 1504.790389]  Possible unsafe locking scenario:
[ 1504.790389]
[ 1504.790390]        CPU0                    CPU1
[ 1504.790391]        ----                    ----
[ 1504.790391]   lock(&adapter->crit_lock);
[ 1504.790393]                                lock(&dev->lock);
[ 1504.790394]                                lock(&adapter->crit_lock);
[ 1504.790395]   lock(&dev->lock);
[ 1504.790397]
[ 1504.790397]  *** DEADLOCK ***

This appears to be caused by the change in commit 5fda3f35349b ("net: make
netdev_lock() protect netdev->reg_state"), which added a netdev_lock() in
register_netdevice.

The iAVF driver calls register_netdevice() from iavf_finish_config(), as a
final stage of its state machine post-probe. It currently takes the RTNL
lock, then the netdev lock, and then the device critical lock. This pattern
is used throughout the driver. Thus there is a strong dependency that the
crit_lock should not be acquired before the net device lock. The change to
register_netdevice creates an ABBA lock order violation because the iAVF
driver is holding the crit_lock while calling register_netdevice, which
then takes the netdev_lock.

It seems likely that future refactors could result in netdev APIs which
hold the netdev_lock while calling into the driver. This means that we
should not re-order the locks so that netdev_lock is acquired after the
device private crit_lock.

Instead, notice that we already release the netdev_lock prior to calling
the register_netdevice. This flow only happens during the early driver
initialization as we transition through the __IAVF_STARTUP,
__IAVF_INIT_VERSION_CHECK, __IAVF_INIT_GET_RESOURCES, etc.

Analyzing the places where we take crit_lock in the driver there are two
sources:

a) several of the work queue tasks including adminq_task, watchdog_task,
reset_task, and the finish_config task.

b) various callbacks which ultimately stem back to .ndo operations or
ethtool operations.

The latter cannot be triggered until after the netdevice registration is
completed successfully.

The iAVF driver uses alloc_ordered_workqueue, which is an unbound workqueue
that has a max limit of 1, and thus guarantees that only a single work item
on the queue is executing at any given time, so none of the other work
threads could be executing due to the ordered workqueue guarantees.

The iavf_finish_config() function also does not do anything else after
register_netdevice, unless it fails. It seems unlikely that the driver
private crit_lock is protecting anything that register_netdevice() itself
touches.

Thus, to fix this ABBA lock violation, lets simply release the
adapter->crit_lock as well as netdev_lock prior to calling
register_netdevice(). We do still keep holding the RTNL lock as required by
the function. If we do fail to register the netdevice, then we re-acquire
the adapter critical lock to finish the transition back to
__IAVF_INIT_CONFIG_ADAPTER.

This ensures every call where both netdev_lock and the adapter->crit_lock
are acquired under the same ordering.

Fixes: afc664987ab3 ("eth: iavf: extend the netdev_lock usage")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-5-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 852e5b62f0a5d..6faa62bced3a2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1983,7 +1983,7 @@ static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool runni
 static void iavf_finish_config(struct work_struct *work)
 {
 	struct iavf_adapter *adapter;
-	bool netdev_released = false;
+	bool locks_released = false;
 	int pairs, err;
 
 	adapter = container_of(work, struct iavf_adapter, finish_config);
@@ -2012,19 +2012,22 @@ static void iavf_finish_config(struct work_struct *work)
 		netif_set_real_num_tx_queues(adapter->netdev, pairs);
 
 		if (adapter->netdev->reg_state != NETREG_REGISTERED) {
+			mutex_unlock(&adapter->crit_lock);
 			netdev_unlock(adapter->netdev);
-			netdev_released = true;
+			locks_released = true;
 			err = register_netdevice(adapter->netdev);
 			if (err) {
 				dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n",
 					err);
 
 				/* go back and try again.*/
+				mutex_lock(&adapter->crit_lock);
 				iavf_free_rss(adapter);
 				iavf_free_misc_irq(adapter);
 				iavf_reset_interrupt_capability(adapter);
 				iavf_change_state(adapter,
 						  __IAVF_INIT_CONFIG_ADAPTER);
+				mutex_unlock(&adapter->crit_lock);
 				goto out;
 			}
 		}
@@ -2040,9 +2043,10 @@ static void iavf_finish_config(struct work_struct *work)
 	}
 
 out:
-	mutex_unlock(&adapter->crit_lock);
-	if (!netdev_released)
+	if (!locks_released) {
+		mutex_unlock(&adapter->crit_lock);
 		netdev_unlock(adapter->netdev);
+	}
 	rtnl_unlock();
 }
 

From b1e44b4aecb551727a368df5b85c535f2ce932ea Mon Sep 17 00:00:00 2001
From: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Date: Mon, 24 Feb 2025 11:06:45 -0800
Subject: [PATCH 1177/2753] ixgbe: fix media cage present detection for E610
 device

The commit 23c0e5a16bcc ("ixgbe: Add link management support for E610
device") introduced incorrect checking of media cage presence for E610
device. Fix it.

Fixes: 23c0e5a16bcc ("ixgbe: Add link management support for E610 device")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/all/e7d73b32-f12a-49d1-8b60-1ef83359ec13@stanley.mountain/
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Bharath R <bharath.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250224190647.3601930-6-anthony.l.nguyen@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index 683c668672d65..cb07ecd8937d3 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -1122,7 +1122,7 @@ static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw)
 	 * returns error (ENOENT), then no cage present. If no cage present then
 	 * connection type is backplane or BASE-T.
 	 */
-	return ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
+	return !ixgbe_aci_get_netlist_node(hw, cmd, NULL, NULL);
 }
 
 /**

From 39ab773e4c120f7f98d759415ccc2aca706bbc10 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:44 +0800
Subject: [PATCH 1178/2753] net: enetc: fix the off-by-one issue in
 enetc_map_tx_buffs()

When a DMA mapping error occurs while processing skb frags, it will free
one more tx_swbd than expected, so fix this off-by-one issue.

Fixes: d4fd0404c1c9 ("enetc: Introduce basic PF and VF ENETC ethernet drivers")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Suggested-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-2-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 26 ++++++++++++++------
 1 file changed, 19 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 6a6fc819dfdee..55ad31a5073e7 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -167,6 +167,24 @@ static bool enetc_skb_is_tcp(struct sk_buff *skb)
 	return skb->csum_offset == offsetof(struct tcphdr, check);
 }
 
+/**
+ * enetc_unwind_tx_frame() - Unwind the DMA mappings of a multi-buffer Tx frame
+ * @tx_ring: Pointer to the Tx ring on which the buffer descriptors are located
+ * @count: Number of Tx buffer descriptors which need to be unmapped
+ * @i: Index of the last successfully mapped Tx buffer descriptor
+ */
+static void enetc_unwind_tx_frame(struct enetc_bdr *tx_ring, int count, int i)
+{
+	while (count--) {
+		struct enetc_tx_swbd *tx_swbd = &tx_ring->tx_swbd[i];
+
+		enetc_free_tx_frame(tx_ring, tx_swbd);
+		if (i == 0)
+			i = tx_ring->bd_count;
+		i--;
+	}
+}
+
 static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 {
 	bool do_vlan, do_onestep_tstamp = false, do_twostep_tstamp = false;
@@ -372,13 +390,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 dma_err:
 	dev_err(tx_ring->dev, "DMA map error");
 
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }

From da291996b16ebd10626d4b20288327b743aff110 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:45 +0800
Subject: [PATCH 1179/2753] net: enetc: keep track of correct Tx BD count in
 enetc_map_tx_tso_buffs()

When creating a TSO header, if the skb is VLAN tagged, the extended BD
will be used and the 'count' should be increased by 2 instead of 1.
Otherwise, when an error occurs, less tx_swbd will be freed than the
actual number.

Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-3-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 16 ++++++++++------
 1 file changed, 10 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 55ad31a5073e7..174db9e2ce813 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -395,14 +395,15 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 	return 0;
 }
 
-static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
-				 struct enetc_tx_swbd *tx_swbd,
-				 union enetc_tx_bd *txbd, int *i, int hdr_len,
-				 int data_len)
+static int enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
+				struct enetc_tx_swbd *tx_swbd,
+				union enetc_tx_bd *txbd, int *i, int hdr_len,
+				int data_len)
 {
 	union enetc_tx_bd txbd_tmp;
 	u8 flags = 0, e_flags = 0;
 	dma_addr_t addr;
+	int count = 1;
 
 	enetc_clear_tx_bd(&txbd_tmp);
 	addr = tx_ring->tso_headers_dma + *i * TSO_HEADER_SIZE;
@@ -445,7 +446,10 @@ static void enetc_map_tx_tso_hdr(struct enetc_bdr *tx_ring, struct sk_buff *skb,
 		/* Write the BD */
 		txbd_tmp.ext.e_flags = e_flags;
 		*txbd = txbd_tmp;
+		count++;
 	}
+
+	return count;
 }
 
 static int enetc_map_tx_tso_data(struct enetc_bdr *tx_ring, struct sk_buff *skb,
@@ -802,9 +806,9 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 
 		/* compute the csum over the L4 header */
 		csum = enetc_tso_hdr_csum(&tso, skb, hdr, hdr_len, &pos);
-		enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd, &i, hdr_len, data_len);
+		count += enetc_map_tx_tso_hdr(tx_ring, skb, tx_swbd, txbd,
+					      &i, hdr_len, data_len);
 		bd_data_num = 0;
-		count++;
 
 		while (data_len > 0) {
 			int size;

From 432a2cb3ee97a7c6ea578888fe81baad035b9307 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:46 +0800
Subject: [PATCH 1180/2753] net: enetc: correct the xdp_tx statistics

The 'xdp_tx' is used to count the number of XDP_TX frames sent, not the
number of Tx BDs.

Fixes: 7ed2bc80074e ("net: enetc: add support for XDP_TX")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-4-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 174db9e2ce813..3cb9ebb13b19b 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -1917,7 +1917,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				tx_ring->stats.xdp_tx_drops++;
 			} else {
-				tx_ring->stats.xdp_tx += xdp_tx_bd_cnt;
+				tx_ring->stats.xdp_tx++;
 				rx_ring->xdp.xdp_tx_in_flight += xdp_tx_bd_cnt;
 				xdp_tx_frm_cnt++;
 				/* The XDP_TX enqueue was successful, so we

From a562d0c4a893eae3ea51d512c4d90ab858a6b7ec Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:47 +0800
Subject: [PATCH 1181/2753] net: enetc: VFs do not support
 HWTSTAMP_TX_ONESTEP_SYNC

Actually ENETC VFs do not support HWTSTAMP_TX_ONESTEP_SYNC because only
ENETC PF can access PMa_SINGLE_STEP registers. And there will be a crash
if VFs are used to test one-step timestamp, the crash log as follows.

[  129.110909] Unable to handle kernel paging request at virtual address 00000000000080c0
[  129.287769] Call trace:
[  129.290219]  enetc_port_mac_wr+0x30/0xec (P)
[  129.294504]  enetc_start_xmit+0xda4/0xe74
[  129.298525]  enetc_xmit+0x70/0xec
[  129.301848]  dev_hard_start_xmit+0x98/0x118

Fixes: 41514737ecaa ("enetc: add get_ts_info interface for ethtool")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-5-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c         | 3 +++
 drivers/net/ethernet/freescale/enetc/enetc_ethtool.c | 7 +++++--
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 3cb9ebb13b19b..e946d86527904 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -3244,6 +3244,9 @@ static int enetc_hwtstamp_set(struct net_device *ndev, struct ifreq *ifr)
 		new_offloads |= ENETC_F_TX_TSTAMP;
 		break;
 	case HWTSTAMP_TX_ONESTEP_SYNC:
+		if (!enetc_si_is_pf(priv->si))
+			return -EOPNOTSUPP;
+
 		new_offloads &= ~ENETC_F_TX_TSTAMP_MASK;
 		new_offloads |= ENETC_F_TX_ONESTEP_SYNC_TSTAMP;
 		break;
diff --git a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
index bf34b5bb1e358..ece3ae28ba827 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc_ethtool.c
@@ -832,6 +832,7 @@ static int enetc_set_coalesce(struct net_device *ndev,
 static int enetc_get_ts_info(struct net_device *ndev,
 			     struct kernel_ethtool_ts_info *info)
 {
+	struct enetc_ndev_priv *priv = netdev_priv(ndev);
 	int *phc_idx;
 
 	phc_idx = symbol_get(enetc_phc_index);
@@ -852,8 +853,10 @@ static int enetc_get_ts_info(struct net_device *ndev,
 				SOF_TIMESTAMPING_TX_SOFTWARE;
 
 	info->tx_types = (1 << HWTSTAMP_TX_OFF) |
-			 (1 << HWTSTAMP_TX_ON) |
-			 (1 << HWTSTAMP_TX_ONESTEP_SYNC);
+			 (1 << HWTSTAMP_TX_ON);
+
+	if (enetc_si_is_pf(priv->si))
+		info->tx_types |= (1 << HWTSTAMP_TX_ONESTEP_SYNC);
 
 	info->rx_filters = (1 << HWTSTAMP_FILTER_NONE) |
 			   (1 << HWTSTAMP_FILTER_ALL);

From bbcbc906ab7b5834c1219cd17a38d78dba904aa0 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:48 +0800
Subject: [PATCH 1182/2753] net: enetc: update UDP checksum when updating
 originTimestamp field

There is an issue with one-step timestamp based on UDP/IP. The peer will
discard the sync packet because of the wrong UDP checksum. For ENETC v1,
the software needs to update the UDP checksum when updating the
originTimestamp field, so that the hardware can correctly update the UDP
checksum when updating the correction field. Otherwise, the UDP checksum
in the sync packet will be wrong.

Fixes: 7294380c5211 ("enetc: support PTP Sync packet one-step timestamping")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-6-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 41 ++++++++++++++++----
 1 file changed, 34 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index e946d86527904..9801c51b6a590 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -297,9 +297,11 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 		}
 
 		if (do_onestep_tstamp) {
-			u32 lo, hi, val;
-			u64 sec, nsec;
+			__be32 new_sec_l, new_nsec;
+			u32 lo, hi, nsec, val;
+			__be16 new_sec_h;
 			u8 *data;
+			u64 sec;
 
 			lo = enetc_rd_hot(hw, ENETC_SICTR0);
 			hi = enetc_rd_hot(hw, ENETC_SICTR1);
@@ -313,13 +315,38 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb)
 			/* Update originTimestamp field of Sync packet
 			 * - 48 bits seconds field
 			 * - 32 bits nanseconds field
+			 *
+			 * In addition, the UDP checksum needs to be updated
+			 * by software after updating originTimestamp field,
+			 * otherwise the hardware will calculate the wrong
+			 * checksum when updating the correction field and
+			 * update it to the packet.
 			 */
 			data = skb_mac_header(skb);
-			*(__be16 *)(data + offset2) =
-				htons((sec >> 32) & 0xffff);
-			*(__be32 *)(data + offset2 + 2) =
-				htonl(sec & 0xffffffff);
-			*(__be32 *)(data + offset2 + 6) = htonl(nsec);
+			new_sec_h = htons((sec >> 32) & 0xffff);
+			new_sec_l = htonl(sec & 0xffffffff);
+			new_nsec = htonl(nsec);
+			if (udp) {
+				struct udphdr *uh = udp_hdr(skb);
+				__be32 old_sec_l, old_nsec;
+				__be16 old_sec_h;
+
+				old_sec_h = *(__be16 *)(data + offset2);
+				inet_proto_csum_replace2(&uh->check, skb, old_sec_h,
+							 new_sec_h, false);
+
+				old_sec_l = *(__be32 *)(data + offset2 + 2);
+				inet_proto_csum_replace4(&uh->check, skb, old_sec_l,
+							 new_sec_l, false);
+
+				old_nsec = *(__be32 *)(data + offset2 + 6);
+				inet_proto_csum_replace4(&uh->check, skb, old_nsec,
+							 new_nsec, false);
+			}
+
+			*(__be16 *)(data + offset2) = new_sec_h;
+			*(__be32 *)(data + offset2 + 2) = new_sec_l;
+			*(__be32 *)(data + offset2 + 6) = new_nsec;
 
 			/* Configure single-step register */
 			val = ENETC_PM0_SINGLE_STEP_EN;

From 8e43decdfbb477dd7800e3902d2d2f105d22ef5f Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:49 +0800
Subject: [PATCH 1183/2753] net: enetc: add missing enetc4_link_deinit()

The enetc4_link_init() is called when the PF driver probes to create
phylink and MDIO bus, but we forgot to call enetc4_link_deinit() to
free the phylink and MDIO bus when the driver was unbound. so add
missing enetc4_link_deinit() to enetc4_pf_netdev_destroy().

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-7-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index fc41078c4f5da..48861c8b499a0 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -684,6 +684,7 @@ static void enetc4_pf_netdev_destroy(struct enetc_si *si)
 	struct net_device *ndev = si->ndev;
 
 	unregister_netdev(ndev);
+	enetc4_link_deinit(priv);
 	enetc_free_msix(priv);
 	free_netdev(ndev);
 }

From 119049b66b883c7e7e575a0b69dc6e3d211662cc Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:50 +0800
Subject: [PATCH 1184/2753] net: enetc: remove the mm_lock from the ENETC v4
 driver

Currently, the ENETC v4 driver has not added the MAC merge layer support
in the upstream, so the mm_lock is not initialized and used, so remove
the mm_lock from the driver.

Fixes: 99100d0d9922 ("net: enetc: add preliminary support for i.MX95 ENETC PF")
Cc: stable@vger.kernel.org
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-8-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc4_pf.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
index 48861c8b499a0..73ac8c6afb3ad 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc4_pf.c
@@ -672,7 +672,6 @@ static int enetc4_pf_netdev_create(struct enetc_si *si)
 err_alloc_msix:
 err_config_si:
 err_clk_get:
-	mutex_destroy(&priv->mm_lock);
 	free_netdev(ndev);
 
 	return err;

From 249df695c3ffe8c8d36d46c2580ce72410976f96 Mon Sep 17 00:00:00 2001
From: Wei Fang <wei.fang@nxp.com>
Date: Mon, 24 Feb 2025 19:12:51 +0800
Subject: [PATCH 1185/2753] net: enetc: fix the off-by-one issue in
 enetc_map_tx_tso_buffs()

There is an off-by-one issue for the err_chained_bd path, it will free
one more tx_swbd than expected. But there is no such issue for the
err_map_data path. To fix this off-by-one issue and make the two error
handling consistent, the increment of 'i' and 'count' remain in sync
and enetc_unwind_tx_frame() is called for error handling.

Fixes: fb8629e2cbfc ("net: enetc: add support for software TSO")
Cc: stable@vger.kernel.org
Suggested-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: Wei Fang <wei.fang@nxp.com>
Reviewed-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Claudiu Manoil <claudiu.manoil@nxp.com>
Link: https://patch.msgid.link/20250224111251.1061098-9-wei.fang@nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/enetc/enetc.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
index 9801c51b6a590..2106861463e40 100644
--- a/drivers/net/ethernet/freescale/enetc/enetc.c
+++ b/drivers/net/ethernet/freescale/enetc/enetc.c
@@ -859,8 +859,13 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 			err = enetc_map_tx_tso_data(tx_ring, skb, tx_swbd, txbd,
 						    tso.data, size,
 						    size == data_len);
-			if (err)
+			if (err) {
+				if (i == 0)
+					i = tx_ring->bd_count;
+				i--;
+
 				goto err_map_data;
+			}
 
 			data_len -= size;
 			count++;
@@ -889,13 +894,7 @@ static int enetc_map_tx_tso_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb
 	dev_err(tx_ring->dev, "DMA map error");
 
 err_chained_bd:
-	do {
-		tx_swbd = &tx_ring->tx_swbd[i];
-		enetc_free_tx_frame(tx_ring, tx_swbd);
-		if (i == 0)
-			i = tx_ring->bd_count;
-		i--;
-	} while (count--);
+	enetc_unwind_tx_frame(tx_ring, count, i);
 
 	return 0;
 }

From 5a4041f2c47247575a6c2e53ce14f7b0ac946c33 Mon Sep 17 00:00:00 2001
From: Naohiro Aota <naohiro.aota@wdc.com>
Date: Wed, 19 Feb 2025 16:02:11 +0900
Subject: [PATCH 1186/2753] btrfs: zoned: fix extent range end unlock in
 cow_file_range()

Running generic/751 on the for-next branch often results in a hang like
below. They are both stack by locking an extent. This suggests someone
forget to unlock an extent.

  INFO: task kworker/u128:1:12 blocked for more than 323 seconds.
        Not tainted 6.13.0-BTRFS-ZNS+ #503
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:kworker/u128:1  state:D stack:0     pid:12    tgid:12    ppid:2      flags:0x00004000
  Workqueue: btrfs-fixup btrfs_work_helper [btrfs]
  Call Trace:
   <TASK>
   __schedule+0x534/0xdd0
   schedule+0x39/0x140
   __lock_extent+0x31b/0x380 [btrfs]
   ? __pfx_autoremove_wake_function+0x10/0x10
   btrfs_writepage_fixup_worker+0xf1/0x3a0 [btrfs]
   btrfs_work_helper+0xff/0x480 [btrfs]
   ? lock_release+0x178/0x2c0
   process_one_work+0x1ee/0x570
   ? srso_return_thunk+0x5/0x5f
   worker_thread+0x1d1/0x3b0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0x10b/0x230
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x30/0x50
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>
  INFO: task kworker/u134:0:184 blocked for more than 323 seconds.
        Not tainted 6.13.0-BTRFS-ZNS+ #503
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:kworker/u134:0  state:D stack:0     pid:184   tgid:184   ppid:2      flags:0x00004000
  Workqueue: writeback wb_workfn (flush-btrfs-4)
  Call Trace:
   <TASK>
   __schedule+0x534/0xdd0
   schedule+0x39/0x140
   __lock_extent+0x31b/0x380 [btrfs]
   ? __pfx_autoremove_wake_function+0x10/0x10
   find_lock_delalloc_range+0xdb/0x260 [btrfs]
   writepage_delalloc+0x12f/0x500 [btrfs]
   ? srso_return_thunk+0x5/0x5f
   extent_write_cache_pages+0x232/0x840 [btrfs]
   btrfs_writepages+0x72/0x130 [btrfs]
   do_writepages+0xe7/0x260
   ? srso_return_thunk+0x5/0x5f
   ? lock_acquire+0xd2/0x300
   ? srso_return_thunk+0x5/0x5f
   ? find_held_lock+0x2b/0x80
   ? wbc_attach_and_unlock_inode.part.0+0x102/0x250
   ? wbc_attach_and_unlock_inode.part.0+0x102/0x250
   __writeback_single_inode+0x5c/0x4b0
   writeback_sb_inodes+0x22d/0x550
   __writeback_inodes_wb+0x4c/0xe0
   wb_writeback+0x2f6/0x3f0
   wb_workfn+0x32a/0x510
   process_one_work+0x1ee/0x570
   ? srso_return_thunk+0x5/0x5f
   worker_thread+0x1d1/0x3b0
   ? __pfx_worker_thread+0x10/0x10
   kthread+0x10b/0x230
   ? __pfx_kthread+0x10/0x10
   ret_from_fork+0x30/0x50
   ? __pfx_kthread+0x10/0x10
   ret_from_fork_asm+0x1a/0x30
   </TASK>

This happens because we have another success path for the zoned mode. When
there is no active zone available, btrfs_reserve_extent() returns
-EAGAIN. In this case, we have two reactions.

(1) If the given range is never allocated, we can only wait for someone
    to finish a zone, so wait on BTRFS_FS_NEED_ZONE_FINISH bit and retry
    afterward.

(2) Or, if some allocations are already done, we must bail out and let
    the caller to send IOs for the allocation. This is because these IOs
    may be necessary to finish a zone.

The commit 06f364284794 ("btrfs: do proper folio cleanup when
cow_file_range() failed") moved the unlock code from the inside of the
loop to the outside. So, previously, the allocated extents are unlocked
just after the allocation and so before returning from the function.
However, they are no longer unlocked on the case (2) above. That caused
the hang issue.

Fix the issue by modifying the 'end' to the end of the allocated
range. Then, we can exit the loop and the same unlock code can properly
handle the case.

Reported-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Tested-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Fixes: 06f364284794 ("btrfs: do proper folio cleanup when cow_file_range() failed")
CC: stable@vger.kernel.org
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/inode.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index fe2c810335ff0..69e90ed33cfe5 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -1382,8 +1382,13 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
 				continue;
 			}
 			if (done_offset) {
-				*done_offset = start - 1;
-				return 0;
+				/*
+				 * Move @end to the end of the processed range,
+				 * and exit the loop to unlock the processed extents.
+				 */
+				end = start - 1;
+				ret = 0;
+				break;
 			}
 			ret = -ENOSPC;
 		}

From 2df2c6ed89600a02e1c7a581a6a55e53c38ce0f5 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 25 Feb 2025 20:26:14 +0100
Subject: [PATCH 1187/2753] btrfs: replace deprecated strncpy() with strscpy()

strncpy() is deprecated for NUL-terminated destination buffers. Use
strscpy() instead and don't zero-initialize the param array.

Link: https://github.com/KSPP/linux/issues/90
Cc: linux-hardening@vger.kernel.org
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/sysfs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 53b846d99ecea..14f53f7575553 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -1330,13 +1330,13 @@ MODULE_PARM_DESC(read_policy,
 
 int btrfs_read_policy_to_enum(const char *str, s64 *value_ret)
 {
-	char param[32] = { 0 };
+	char param[32];
 	char __maybe_unused *value_str;
 
 	if (!str || strlen(str) == 0)
 		return 0;
 
-	strncpy(param, str, sizeof(param) - 1);
+	strscpy(param, str);
 
 #ifdef CONFIG_BTRFS_EXPERIMENTAL
 	/* Separate value from input in policy:value format. */

From 8d52da23b6c68a0f6bad83959ebb61a2cf623c4e Mon Sep 17 00:00:00 2001
From: Wang Hai <wanghai38@huawei.com>
Date: Mon, 24 Feb 2025 17:00:47 +0800
Subject: [PATCH 1188/2753] tcp: Defer ts_recent changes until req is owned

Recently a bug was discovered where the server had entered TCP_ESTABLISHED
state, but the upper layers were not notified.

The same 5-tuple packet may be processed by different CPUSs, so two
CPUs may receive different ack packets at the same time when the
state is TCP_NEW_SYN_RECV.

In that case, req->ts_recent in tcp_check_req may be changed concurrently,
which will probably cause the newsk's ts_recent to be incorrectly large.
So that tcp_validate_incoming will fail. At this point, newsk will not be
able to enter the TCP_ESTABLISHED.

cpu1                                    cpu2
tcp_check_req
                                        tcp_check_req
 req->ts_recent = rcv_tsval = t1
                                         req->ts_recent = rcv_tsval = t2

 syn_recv_sock
  tcp_sk(child)->rx_opt.ts_recent = req->ts_recent = t2 // t1 < t2
tcp_child_process
 tcp_rcv_state_process
  tcp_validate_incoming
   tcp_paws_check
    if ((s32)(rx_opt->ts_recent - rx_opt->rcv_tsval) <= paws_win)
        // t2 - t1 > paws_win, failed
                                        tcp_v4_do_rcv
                                         tcp_rcv_state_process
                                         // TCP_ESTABLISHED

The cpu2's skb or a newly received skb will call tcp_v4_do_rcv to get
the newsk into the TCP_ESTABLISHED state, but at this point it is no
longer possible to notify the upper layer application. A notification
mechanism could be added here, but the fix is more complex, so the
current fix is used.

In tcp_check_req, req->ts_recent is used to assign a value to
tcp_sk(child)->rx_opt.ts_recent, so removing the change in req->ts_recent
and changing tcp_sk(child)->rx_opt.ts_recent directly after owning the
req fixes this bug.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Wang Hai <wanghai38@huawei.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_minisocks.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index b089b08e96178..dfdb7a4608a85 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -815,12 +815,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 	/* In sequence, PAWS is OK. */
 
-	/* TODO: We probably should defer ts_recent change once
-	 * we take ownership of @req.
-	 */
-	if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
-		WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval);
-
 	if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) {
 		/* Truncate SYN, it is out of window starting
 		   at tcp_rsk(req)->rcv_isn + 1. */
@@ -869,6 +863,10 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	if (!child)
 		goto listen_overflow;
 
+	if (own_req && tmp_opt.saw_tstamp &&
+	    !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt))
+		tcp_sk(child)->rx_opt.ts_recent = tmp_opt.rcv_tsval;
+
 	if (own_req && rsk_drop_req(req)) {
 		reqsk_queue_removed(&inet_csk(req->rsk_listener)->icsk_accept_queue, req);
 		inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, req);

From 17bcd714426386fda741a4bccd96a2870179344b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 15:55:36 -0800
Subject: [PATCH 1189/2753] KVM: x86: Free vCPUs before freeing VM state

Free vCPUs before freeing any VM state, as both SVM and VMX may access
VM state when "freeing" a vCPU that is currently "in" L2, i.e. that needs
to be kicked out of nested guest mode.

Commit 6fcee03df6a1 ("KVM: x86: avoid loading a vCPU after .vm_destroy was
called") partially fixed the issue, but for unknown reasons only moved the
MMU unloading before VM destruction.  Complete the change, and free all
vCPU state prior to destroying VM state, as nVMX accesses even more state
than nSVM.

In addition to the AVIC, KVM can hit a use-after-free on MSR filters:

  kvm_msr_allowed+0x4c/0xd0
  __kvm_set_msr+0x12d/0x1e0
  kvm_set_msr+0x19/0x40
  load_vmcs12_host_state+0x2d8/0x6e0 [kvm_intel]
  nested_vmx_vmexit+0x715/0xbd0 [kvm_intel]
  nested_vmx_free_vcpu+0x33/0x50 [kvm_intel]
  vmx_free_vcpu+0x54/0xc0 [kvm_intel]
  kvm_arch_vcpu_destroy+0x28/0xf0
  kvm_vcpu_destroy+0x12/0x50
  kvm_arch_destroy_vm+0x12c/0x1c0
  kvm_put_kvm+0x263/0x3c0
  kvm_vm_release+0x21/0x30

and an upcoming fix to process injectable interrupts on nested VM-Exit
will access the PIC:

  BUG: kernel NULL pointer dereference, address: 0000000000000090
  #PF: supervisor read access in kernel mode
  #PF: error_code(0x0000) - not-present page
  CPU: 23 UID: 1000 PID: 2658 Comm: kvm-nx-lpage-re
  RIP: 0010:kvm_cpu_has_extint+0x2f/0x60 [kvm]
  Call Trace:
   <TASK>
   kvm_cpu_has_injectable_intr+0xe/0x60 [kvm]
   nested_vmx_vmexit+0x2d7/0xdf0 [kvm_intel]
   nested_vmx_free_vcpu+0x40/0x50 [kvm_intel]
   vmx_vcpu_free+0x2d/0x80 [kvm_intel]
   kvm_arch_vcpu_destroy+0x2d/0x130 [kvm]
   kvm_destroy_vcpus+0x8a/0x100 [kvm]
   kvm_arch_destroy_vm+0xa7/0x1d0 [kvm]
   kvm_destroy_vm+0x172/0x300 [kvm]
   kvm_vcpu_release+0x31/0x50 [kvm]

Inarguably, both nSVM and nVMX need to be fixed, but punt on those
cleanups for the moment.  Conceptually, vCPUs should be freed before VM
state.  Assets like the I/O APIC and PIC _must_ be allocated before vCPUs
are created, so it stands to reason that they must be freed _after_ vCPUs
are destroyed.

Reported-by: Aaron Lewis <aaronlewis@google.com>
Closes: https://lore.kernel.org/all/20240703175618.2304869-2-aaronlewis@google.com
Cc: Jim Mattson <jmattson@google.com>
Cc: Yan Zhao <yan.y.zhao@intel.com>
Cc: Rick P Edgecombe <rick.p.edgecombe@intel.com>
Cc: Kai Huang <kai.huang@intel.com>
Cc: Isaku Yamahata <isaku.yamahata@intel.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-2-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/x86.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29e..6fc4ddc606bd4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12877,11 +12877,11 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 		mutex_unlock(&kvm->slots_lock);
 	}
 	kvm_unload_vcpu_mmus(kvm);
+	kvm_destroy_vcpus(kvm);
 	kvm_x86_call(vm_destroy)(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
-	kvm_destroy_vcpus(kvm);
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);

From 982caaa1150479f022003390cd72a1941663d211 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 15:55:37 -0800
Subject: [PATCH 1190/2753] KVM: nVMX: Process events on nested VM-Exit if
 injectable IRQ or NMI is pending

Process pending events on nested VM-Exit if the vCPU has an injectable IRQ
or NMI, as the event may have become pending while L2 was active, i.e. may
not be tracked in the context of vmcs01.  E.g. if L1 has passed its APIC
through to L2 and an IRQ arrives while L2 is active, then KVM needs to
request an IRQ window prior to running L1, otherwise delivery of the IRQ
will be delayed until KVM happens to process events for some other reason.

The missed failure is detected by vmx_apic_passthrough_tpr_threshold_test
in KVM-Unit-Tests, but has effectively been masked due to a flaw in KVM's
PIC emulation that causes KVM to make spurious KVM_REQ_EVENT requests (and
apparently no one ever ran the test with split IRQ chips).

Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
Message-ID: <20250224235542.2562848-3-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/vmx/nested.c | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a7af02d466e9..ed8a3cb539612 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -5084,6 +5084,17 @@ void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
 
 		load_vmcs12_host_state(vcpu, vmcs12);
 
+		/*
+		 * Process events if an injectable IRQ or NMI is pending, even
+		 * if the event is blocked (RFLAGS.IF is cleared on VM-Exit).
+		 * If an event became pending while L2 was active, KVM needs to
+		 * either inject the event or request an IRQ/NMI window.  SMIs
+		 * don't need to be processed as SMM is mutually exclusive with
+		 * non-root mode.  INIT/SIPI don't need to be checked as INIT
+		 * is blocked post-VMXON, and SIPIs are ignored.
+		 */
+		if (kvm_cpu_has_injectable_intr(vcpu) || vcpu->arch.nmi_pending)
+			kvm_make_request(KVM_REQ_EVENT, vcpu);
 		return;
 	}
 

From 2e064e3f3282ec016d80cb7b1fadff0d8e2014ca Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Mon, 10 Feb 2025 19:23:50 +0900
Subject: [PATCH 1191/2753] drm/imagination: remove unnecessary header include
 path

drivers/gpu/drm/imagination/ includes local headers with the double-quote
form (#include "...").

Hence, the header search path addition is unneeded.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250210102352.1517115-1-masahiroy@kernel.org
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/Makefile | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/Makefile b/drivers/gpu/drm/imagination/Makefile
index 9bc6a3884c223..3d9d4d40fb806 100644
--- a/drivers/gpu/drm/imagination/Makefile
+++ b/drivers/gpu/drm/imagination/Makefile
@@ -1,8 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0-only OR MIT
 # Copyright (c) 2023 Imagination Technologies Ltd.
 
-subdir-ccflags-y := -I$(src)
-
 powervr-y := \
 	pvr_ccb.o \
 	pvr_cccb.o \

From 130ff5c8b78e6fd05270a04985c50bce6a3de6c1 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Tue, 25 Feb 2025 15:16:12 +0100
Subject: [PATCH 1192/2753] ata: ahci: Make ahci_ignore_port() handle empty
 mask_port_map
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port
numbers") added a skip to ahci_platform_enable_phys() for ports that are
not in mask_port_map.

The code in ahci_platform_get_resources(), will currently set mask_port_map
for each child "port" node it finds in the device tree.

However, device trees that do not have any child "port" nodes will not have
mask_port_map set, and for non-device tree platforms mask_port_map will
only exist as a quirk for specific PCI device + vendor IDs, or as a kernel
module parameter, but will not be set by default.

Therefore, the common thing is that mask_port_map is only set if you do not
want to use all ports (as defined by Offset 0Ch: PI – Ports Implemented
register), but instead only want to use the ports in mask_port_map. If
mask_port_map is not set, all ports are available.

Thus, ahci_ignore_port() must be able to handle an empty mask_port_map.

Fixes: 8c87215dd3a2 ("ata: libahci_platform: support non-consecutive port numbers")
Fixes: 2c202e6c4f4d ("ata: libahci_platform: Do not set mask_port_map when not needed")
Fixes: c9b5be909e65 ("ahci: Introduce ahci_ignore_port() helper")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/linux-ide/10b31dd0-d0bb-4f76-9305-2195c3e17670@samsung.com/
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Co-developed-by: Damien Le Moal <dlemoal@kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250225141612.942170-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.h    | 8 ++++++--
 drivers/ata/libahci.c | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/ata/ahci.h b/drivers/ata/ahci.h
index aea30df50c581..b2e0ef4efbdc3 100644
--- a/drivers/ata/ahci.h
+++ b/drivers/ata/ahci.h
@@ -386,8 +386,12 @@ struct ahci_host_priv {
 static inline bool ahci_ignore_port(struct ahci_host_priv *hpriv,
 				    unsigned int portid)
 {
-	return portid >= hpriv->nports ||
-		!(hpriv->mask_port_map & (1 << portid));
+	if (portid >= hpriv->nports)
+		return true;
+	/* mask_port_map not set means that all ports are available */
+	if (!hpriv->mask_port_map)
+		return false;
+	return !(hpriv->mask_port_map & (1 << portid));
 }
 
 extern int ahci_ignore_sss;
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index fdfa7b2662180..e7ace4b10f15b 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -541,6 +541,7 @@ void ahci_save_initial_config(struct device *dev, struct ahci_host_priv *hpriv)
 		hpriv->saved_port_map = port_map;
 	}
 
+	/* mask_port_map not set means that all ports are available */
 	if (hpriv->mask_port_map) {
 		dev_warn(dev, "masking port_map 0x%lx -> 0x%lx\n",
 			port_map,

From f2ba0cf1ca32e075617813de98c826ab55d57f11 Mon Sep 17 00:00:00 2001
From: Mingcong Bai <jeffbai@aosc.io>
Date: Tue, 25 Feb 2025 15:31:01 +0800
Subject: [PATCH 1193/2753] drm/xe/regs: remove a duplicate definition for
 RING_CTL_SIZE(size)

Commit b79e8fd954c4 ("drm/xe: Remove dependency on intel_engine_regs.h")
introduced an internal set of engine registers, however, as part of this
change, it has also introduced two duplicate `define' lines for
`RING_CTL_SIZE(size)'. This commit was introduced to the tree in v6.8-rc1.

While this is harmless as the definitions did not change, so no compiler
warning was observed.

Drop this line anyway for the sake of correctness.

Cc: stable@vger.kernel.org # v6.8-rc1+
Fixes: b79e8fd954c4 ("drm/xe: Remove dependency on intel_engine_regs.h")
Signed-off-by: Mingcong Bai <jeffbai@aosc.io>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250225073104.865230-1-jeffbai@aosc.io
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 6b68c4542ffecc36087a9e14db8fc990c88bb01b)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_engine_regs.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
index d86219dedde2a..b732c89816dff 100644
--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
@@ -53,7 +53,6 @@
 
 #define RING_CTL(base)				XE_REG((base) + 0x3c)
 #define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
-#define   RING_CTL_SIZE(size)			((size) - PAGE_SIZE) /* in bytes -> pages */
 
 #define RING_START_UDW(base)			XE_REG((base) + 0x48)
 

From 12c2f962fe71f390951d9242725bc7e608f55927 Mon Sep 17 00:00:00 2001
From: Tejas Upadhyay <tejas.upadhyay@intel.com>
Date: Tue, 25 Feb 2025 10:27:54 +0530
Subject: [PATCH 1194/2753] drm/xe: cancel pending job timer before freeing
 scheduler

The async call to __guc_exec_queue_fini_async frees the scheduler
while a submission may time out and restart. To prevent this race
condition, the pending job timer should be canceled before freeing
the scheduler.

V3(MattB):
 - Adjust position of cancel pending job
 - Remove gitlab issue# from commit message
V2(MattB):
 - Cancel pending jobs before scheduler finish

Fixes: a20c75dba192 ("drm/xe: Call __guc_exec_queue_fini_async direct for KERNEL exec_queues")
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250225045754.600905-1-tejas.upadhyay@intel.com
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
(cherry picked from commit 18fbd567e75f9b97b699b2ab4f1fa76b7cf268f6)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index 913c74d6e2aeb..b6a2dd742ebdc 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1248,6 +1248,8 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
+	/* Confirm no work left behind accessing device structures */
+	cancel_delayed_work_sync(&ge->sched.base.work_tdr);
 	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);

From 16fef33fdb1e2269c20697d9b61ae8022bc92665 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Mon, 24 Feb 2025 11:32:42 +0200
Subject: [PATCH 1195/2753] drm/i915/dp_mst: Fix encoder HW state readout for
 UHBR MST

The encoder HW/SW state verification should use a SW state which stays
unchanged while the encoder/output is active. The intel_dp::is_mst flag
used during state computation to choose between the DP SST/MST modes can
change while the output is active, if the sink gets disconnected or the
MST topology is removed for another reason. A subsequent state
verification using intel_dp::is_mst leads then to a mismatch if the
output is disabled/re-enabled without recomputing its state.

Use the encoder's active MST link count instead, which will be always
non-zero for an active MST output and will be zero for SST.

Fixes: 35d2e4b75649 ("drm/i915/ddi: start distinguishing 128b/132b SST and MST at state readout")
Fixes: 40d489fac0e8 ("drm/i915/ddi: handle 128b/132b SST in intel_ddi_read_func_ctl()")
Cc: Jani Nikula <jani.nikula@intel.com>
Reviewed-by: Jani Nikula <jani.nikula@intel.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250224093242.1859583-1-imre.deak@intel.com
(cherry picked from commit 0159e311772af9d6598aafe072c020687720f1d7)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_ddi.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_ddi.c b/drivers/gpu/drm/i915/display/intel_ddi.c
index 18c66992aa1d8..ff2cf3daa7a2b 100644
--- a/drivers/gpu/drm/i915/display/intel_ddi.c
+++ b/drivers/gpu/drm/i915/display/intel_ddi.c
@@ -866,7 +866,7 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 			    encoder->base.base.id, encoder->base.name);
 
 	if (!mst_pipe_mask && dp128b132b_pipe_mask) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 		/*
 		 * If we don't have 8b/10b MST, but have more than one
@@ -878,7 +878,8 @@ static void intel_ddi_get_encoder_pipes(struct intel_encoder *encoder,
 		 * we don't expect MST to have been enabled at that point, and
 		 * can assume it's SST.
 		 */
-		if (hweight8(dp128b132b_pipe_mask) > 1 || intel_dp->is_mst)
+		if (hweight8(dp128b132b_pipe_mask) > 1 ||
+		    intel_dp_mst_encoder_active_links(dig_port))
 			mst_pipe_mask = dp128b132b_pipe_mask;
 	}
 
@@ -4151,13 +4152,13 @@ static void intel_ddi_read_func_ctl(struct intel_encoder *encoder,
 	} else if (ddi_mode == TRANS_DDI_MODE_SELECT_DP_MST) {
 		intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
 	} else if (ddi_mode == TRANS_DDI_MODE_SELECT_FDI_OR_128B132B && HAS_DP20(display)) {
-		struct intel_dp *intel_dp = enc_to_intel_dp(encoder);
+		struct intel_digital_port *dig_port = enc_to_dig_port(encoder);
 
 		/*
 		 * If this is true, we know we're being called from mst stream
 		 * encoder's ->get_config().
 		 */
-		if (intel_dp->is_mst)
+		if (intel_dp_mst_encoder_active_links(dig_port))
 			intel_ddi_read_func_ctl_dp_mst(encoder, pipe_config, ddi_func_ctl);
 		else
 			intel_ddi_read_func_ctl_dp_sst(encoder, pipe_config, ddi_func_ctl);

From c6557ccf8094ce2e1142c6e49cd47f5d5e2933a8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Adrien=20Verg=C3=A9?= <adrienverge@gmail.com>
Date: Wed, 26 Feb 2025 14:55:15 +0100
Subject: [PATCH 1196/2753] ALSA: hda/realtek: Fix microphone regression on
 ASUS N705UD
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This fixes a regression introduced a few weeks ago in stable kernels
6.12.14 and 6.13.3. The internal microphone on ASUS Vivobook N705UD /
X705UD laptops is broken: the microphone appears in userspace (e.g.
Gnome settings) but no sound is detected.
I bisected it to commit 3b4309546b48 ("ALSA: hda: Fix headset detection
failure due to unstable sort").

I figured out the cause:
1. The initial pins enabled for the ALC256 driver are:
       cfg->inputs == {
         { pin=0x19, type=AUTO_PIN_MIC,
           is_headset_mic=1, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x1a, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 } }
2. Since 2017 and commits c1732ede5e8 ("ALSA: hda/realtek - Fix headset
   and mic on several ASUS laptops with ALC256") and 28e8af8a163 ("ALSA:
   hda/realtek: Fix mic and headset jack sense on ASUS X705UD"), the
   quirk ALC256_FIXUP_ASUS_MIC is also applied to ASUS X705UD / N705UD
   laptops.
   This added another internal microphone on pin 0x13:
       cfg->inputs == {
         { pin=0x13, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x19, type=AUTO_PIN_MIC,
           is_headset_mic=1, is_headphone_mic=0, has_boost_on_pin=1 },
         { pin=0x1a, type=AUTO_PIN_MIC,
           is_headset_mic=0, is_headphone_mic=0, has_boost_on_pin=1 } }
   I don't know what this pin 0x13 corresponds to. To the best of my
   knowledge, these laptops have only one internal microphone.
3. Before 2025 and commit 3b4309546b48 ("ALSA: hda: Fix headset
   detection failure due to unstable sort"), the sort function would let
   the microphone of pin 0x1a (the working one) *before* the microphone
   of pin 0x13 (the phantom one).
4. After this commit 3b4309546b48, the fixed sort function puts the
   working microphone (pin 0x1a) *after* the phantom one (pin 0x13). As
   a result, no sound is detected anymore.

It looks like the quirk ALC256_FIXUP_ASUS_MIC is not needed anymore for
ASUS Vivobook X705UD / N705UD laptops. Without it, everything works
fine:
- the internal microphone is detected and records actual sound,
- plugging in a jack headset is detected and can record actual sound
  with it,
- unplugging the jack headset makes the system go back to internal
  microphone and can record actual sound.

Cc: stable@vger.kernel.org
Cc: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Chris Chiu <chris.chiu@canonical.com>
Fixes: 3b4309546b48 ("ALSA: hda: Fix headset detection failure due to unstable sort")
Tested-by: Adrien Vergé <adrienverge@gmail.com>
Signed-off-by: Adrien Vergé <adrienverge@gmail.com>
Link: https://patch.msgid.link/20250226135515.24219-1-adrienverge@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e5c80d4be535c..c735f630ecb5a 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10657,7 +10657,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x19ce, "ASUS B9450FA", ALC294_FIXUP_ASUS_HPE),
 	SND_PCI_QUIRK(0x1043, 0x19e1, "ASUS UX581LV", ALC295_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
-	SND_PCI_QUIRK(0x1043, 0x1a30, "ASUS X705UD", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1a63, "ASUS UX3405MA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1a83, "ASUS UM5302LA", ALC294_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1a8f, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),

From 99ca2c28e6b68084a0fb65585df09b9e28c3ec16 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 21 Feb 2025 11:24:50 +0100
Subject: [PATCH 1197/2753] wifi: mac80211: fix MLE non-inheritance parsing

The code is erroneously applying the non-inheritance element
to the inner elements rather than the outer, which is clearly
completely wrong. Fix it by finding the MLE basic element at
the beginning, and then applying the non-inheritance for the
outer parsing.

While at it, do some general cleanups such as not allowing
callers to try looking for a specific non-transmitted BSS
and link at the same time.

Fixes: 45ebac4f059b ("wifi: mac80211: Parse station profile from association response")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250221112451.b46d42f45b66.If5b95dc3c80208e0c62d8895fb6152aa54b6620b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c  |   1 +
 net/mac80211/parse.c | 127 ++++++++++++++++++++++++++++---------------
 2 files changed, 83 insertions(+), 45 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f8d52b3b0d0e4..36a9be9a66c8e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4959,6 +4959,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
 		parse_params.start = bss_ies->data;
 		parse_params.len = bss_ies->len;
 		parse_params.bss = cbss;
+		parse_params.link_id = -1;
 		bss_elems = ieee802_11_parse_elems_full(&parse_params);
 		if (!bss_elems) {
 			ret = false;
diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index cd318c1c67bec..3d5d6658fe8d5 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -47,6 +47,8 @@ struct ieee80211_elems_parse {
 	/* The EPCS Multi-Link element in the original elements */
 	const struct element *ml_epcs_elem;
 
+	bool multi_link_inner;
+
 	/*
 	 * scratch buffer that can be used for various element parsing related
 	 * tasks, e.g., element de-fragmentation etc.
@@ -152,12 +154,11 @@ ieee80211_parse_extension_element(u32 *crc,
 			switch (le16_get_bits(mle->control,
 					      IEEE80211_ML_CONTROL_TYPE)) {
 			case IEEE80211_ML_CONTROL_TYPE_BASIC:
-				if (elems_parse->ml_basic_elem) {
+				if (elems_parse->multi_link_inner) {
 					elems->parse_error |=
 						IEEE80211_PARSE_ERR_DUP_NEST_ML_BASIC;
 					break;
 				}
-				elems_parse->ml_basic_elem = elem;
 				break;
 			case IEEE80211_ML_CONTROL_TYPE_RECONF:
 				elems_parse->ml_reconf_elem = elem;
@@ -866,21 +867,36 @@ ieee80211_mle_get_sta_prof(struct ieee80211_elems_parse *elems_parse,
 	}
 }
 
-static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
-				     struct ieee80211_elems_parse_params *params)
+static const struct element *
+ieee80211_prep_mle_link_parse(struct ieee80211_elems_parse *elems_parse,
+			      struct ieee80211_elems_parse_params *params,
+			      struct ieee80211_elems_parse_params *sub)
 {
 	struct ieee802_11_elems *elems = &elems_parse->elems;
 	struct ieee80211_mle_per_sta_profile *prof;
-	struct ieee80211_elems_parse_params sub = {
-		.mode = params->mode,
-		.action = params->action,
-		.from_ap = params->from_ap,
-		.link_id = -1,
-	};
-	ssize_t ml_len = elems->ml_basic_len;
-	const struct element *non_inherit = NULL;
+	const struct element *tmp;
+	ssize_t ml_len;
 	const u8 *end;
 
+	if (params->mode < IEEE80211_CONN_MODE_EHT)
+		return NULL;
+
+	for_each_element_extid(tmp, WLAN_EID_EXT_EHT_MULTI_LINK,
+			       elems->ie_start, elems->total_len) {
+		const struct ieee80211_multi_link_elem *mle =
+			(void *)tmp->data + 1;
+
+		if (!ieee80211_mle_size_ok(tmp->data + 1, tmp->datalen - 1))
+			continue;
+
+		if (le16_get_bits(mle->control, IEEE80211_ML_CONTROL_TYPE) !=
+		    IEEE80211_ML_CONTROL_TYPE_BASIC)
+			continue;
+
+		elems_parse->ml_basic_elem = tmp;
+		break;
+	}
+
 	ml_len = cfg80211_defragment_element(elems_parse->ml_basic_elem,
 					     elems->ie_start,
 					     elems->total_len,
@@ -891,26 +907,26 @@ static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
 					     WLAN_EID_FRAGMENT);
 
 	if (ml_len < 0)
-		return;
+		return NULL;
 
 	elems->ml_basic = (const void *)elems_parse->scratch_pos;
 	elems->ml_basic_len = ml_len;
 	elems_parse->scratch_pos += ml_len;
 
 	if (params->link_id == -1)
-		return;
+		return NULL;
 
 	ieee80211_mle_get_sta_prof(elems_parse, params->link_id);
 	prof = elems->prof;
 
 	if (!prof)
-		return;
+		return NULL;
 
 	/* check if we have the 4 bytes for the fixed part in assoc response */
 	if (elems->sta_prof_len < sizeof(*prof) + prof->sta_info_len - 1 + 4) {
 		elems->prof = NULL;
 		elems->sta_prof_len = 0;
-		return;
+		return NULL;
 	}
 
 	/*
@@ -919,13 +935,17 @@ static void ieee80211_mle_parse_link(struct ieee80211_elems_parse *elems_parse,
 	 * the -1 is because the 'sta_info_len' is accounted to as part of the
 	 * per-STA profile, but not part of the 'u8 variable[]' portion.
 	 */
-	sub.start = prof->variable + prof->sta_info_len - 1 + 4;
+	sub->start = prof->variable + prof->sta_info_len - 1 + 4;
 	end = (const u8 *)prof + elems->sta_prof_len;
-	sub.len = end - sub.start;
+	sub->len = end - sub->start;
 
-	non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
-					     sub.start, sub.len);
-	_ieee802_11_parse_elems_full(&sub, elems_parse, non_inherit);
+	sub->mode = params->mode;
+	sub->action = params->action;
+	sub->from_ap = params->from_ap;
+	sub->link_id = -1;
+
+	return cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+				      sub->start, sub->len);
 }
 
 static void
@@ -973,15 +993,19 @@ ieee80211_mle_defrag_epcs(struct ieee80211_elems_parse *elems_parse)
 struct ieee802_11_elems *
 ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 {
+	struct ieee80211_elems_parse_params sub = {};
 	struct ieee80211_elems_parse *elems_parse;
-	struct ieee802_11_elems *elems;
 	const struct element *non_inherit = NULL;
-	u8 *nontransmitted_profile;
-	int nontransmitted_profile_len = 0;
+	struct ieee802_11_elems *elems;
 	size_t scratch_len = 3 * params->len;
+	bool multi_link_inner = false;
 
 	BUILD_BUG_ON(offsetof(typeof(*elems_parse), elems) != 0);
 
+	/* cannot parse for both a specific link and non-transmitted BSS */
+	if (WARN_ON(params->link_id >= 0 && params->bss))
+		return NULL;
+
 	elems_parse = kzalloc(struct_size(elems_parse, scratch, scratch_len),
 			      GFP_ATOMIC);
 	if (!elems_parse)
@@ -998,34 +1022,47 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 	ieee80211_clear_tpe(&elems->tpe);
 	ieee80211_clear_tpe(&elems->csa_tpe);
 
-	nontransmitted_profile = elems_parse->scratch_pos;
-	nontransmitted_profile_len =
-		ieee802_11_find_bssid_profile(params->start, params->len,
-					      elems, params->bss,
-					      nontransmitted_profile);
-	elems_parse->scratch_pos += nontransmitted_profile_len;
-	non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
-					     nontransmitted_profile,
-					     nontransmitted_profile_len);
+	/*
+	 * If we're looking for a non-transmitted BSS then we cannot at
+	 * the same time be looking for a second link as the two can only
+	 * appear in the same frame carrying info for different BSSes.
+	 *
+	 * In any case, we only look for one at a time, as encoded by
+	 * the WARN_ON above.
+	 */
+	if (params->bss) {
+		int nontx_len =
+			ieee802_11_find_bssid_profile(params->start,
+						      params->len,
+						      elems, params->bss,
+						      elems_parse->scratch_pos);
+		sub.start = elems_parse->scratch_pos;
+		sub.mode = params->mode;
+		sub.len = nontx_len;
+		sub.action = params->action;
+		sub.link_id = params->link_id;
+
+		/* consume the space used for non-transmitted profile */
+		elems_parse->scratch_pos += nontx_len;
+
+		non_inherit = cfg80211_find_ext_elem(WLAN_EID_EXT_NON_INHERITANCE,
+						     sub.start, nontx_len);
+	} else {
+		/* must always parse to get elems_parse->ml_basic_elem */
+		non_inherit = ieee80211_prep_mle_link_parse(elems_parse, params,
+							    &sub);
+		multi_link_inner = true;
+	}
 
 	elems->crc = _ieee802_11_parse_elems_full(params, elems_parse,
 						  non_inherit);
 
-	/* Override with nontransmitted profile, if found */
-	if (nontransmitted_profile_len) {
-		struct ieee80211_elems_parse_params sub = {
-			.mode = params->mode,
-			.start = nontransmitted_profile,
-			.len = nontransmitted_profile_len,
-			.action = params->action,
-			.link_id = params->link_id,
-		};
-
+	/* Override with nontransmitted/per-STA profile if found */
+	if (sub.len) {
+		elems_parse->multi_link_inner = multi_link_inner;
 		_ieee802_11_parse_elems_full(&sub, elems_parse, NULL);
 	}
 
-	ieee80211_mle_parse_link(elems_parse, params);
-
 	ieee80211_mle_defrag_reconf(elems_parse);
 
 	ieee80211_mle_defrag_epcs(elems_parse);

From 130067e9c13bdc4820748ef16076a6972364745f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Fri, 21 Feb 2025 11:24:51 +0100
Subject: [PATCH 1198/2753] wifi: mac80211: fix vendor-specific inheritance

If there's any vendor-specific element in the subelements
then the outer element parsing must not parse any vendor
element at all. This isn't implemented correctly now due
to parsing into the pointers and then overriding them, so
explicitly skip vendor elements if any exist in the sub-
elements (non-transmitted profile or per-STA profile).

Fixes: 671042a4fb77 ("mac80211: support non-inheritance element")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250221112451.fd71e5268840.I9db3e6a3367e6ff38d052d07dc07005f0dd3bd5c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/parse.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/mac80211/parse.c b/net/mac80211/parse.c
index 3d5d6658fe8d5..6da39c864f45b 100644
--- a/net/mac80211/parse.c
+++ b/net/mac80211/parse.c
@@ -48,6 +48,7 @@ struct ieee80211_elems_parse {
 	const struct element *ml_epcs_elem;
 
 	bool multi_link_inner;
+	bool skip_vendor;
 
 	/*
 	 * scratch buffer that can be used for various element parsing related
@@ -400,6 +401,9 @@ _ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params,
 					IEEE80211_PARSE_ERR_BAD_ELEM_SIZE;
 			break;
 		case WLAN_EID_VENDOR_SPECIFIC:
+			if (elems_parse->skip_vendor)
+				break;
+
 			if (elen >= 4 && pos[0] == 0x00 && pos[1] == 0x50 &&
 			    pos[2] == 0xf2) {
 				/* Microsoft OUI (00:50:F2) */
@@ -1054,12 +1058,16 @@ ieee802_11_parse_elems_full(struct ieee80211_elems_parse_params *params)
 		multi_link_inner = true;
 	}
 
+	elems_parse->skip_vendor =
+		cfg80211_find_elem(WLAN_EID_VENDOR_SPECIFIC,
+				   sub.start, sub.len);
 	elems->crc = _ieee802_11_parse_elems_full(params, elems_parse,
 						  non_inherit);
 
 	/* Override with nontransmitted/per-STA profile if found */
 	if (sub.len) {
 		elems_parse->multi_link_inner = multi_link_inner;
+		elems_parse->skip_vendor = false;
 		_ieee802_11_parse_elems_full(&sub, elems_parse, NULL);
 	}
 

From 861d0445e72e9e33797f2ceef882c74decb16a87 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Thu, 13 Feb 2025 22:43:30 +0100
Subject: [PATCH 1199/2753] wifi: mac80211: Fix sparse warning for
 monitor_sdata

Use rcu_access_pointer() to avoid sparse warning in
drv_remove_interface().

Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502130534.bVrZZBK0-lkp@intel.com/
Fixes: 646262c71aca ("wifi: mac80211: remove debugfs dir for virtual monitor")
Link: https://patch.msgid.link/20250213214330.6113-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/driver-ops.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/driver-ops.c b/net/mac80211/driver-ops.c
index 2fc60e1e77a55..35349a7f16cb4 100644
--- a/net/mac80211/driver-ops.c
+++ b/net/mac80211/driver-ops.c
@@ -121,7 +121,7 @@ void drv_remove_interface(struct ieee80211_local *local,
 	 * The virtual monitor interface doesn't get a debugfs
 	 * entry, so it's exempt here.
 	 */
-	if (sdata != local->monitor_sdata)
+	if (sdata != rcu_access_pointer(local->monitor_sdata))
 		ieee80211_debugfs_recreate_netdev(sdata,
 						  sdata->vif.valid_links);
 

From 8c3170628a9ce24a59647bd24f897e666af919b8 Mon Sep 17 00:00:00 2001
From: Matthias Proske <email@matthias-proske.de>
Date: Wed, 12 Feb 2025 19:59:35 +0100
Subject: [PATCH 1200/2753] wifi: brcmfmac: keep power during suspend if board
 requires it

After commit 92cadedd9d5f ("brcmfmac: Avoid keeping power to SDIO card
unless WOWL is used"), the wifi adapter by default is turned off on
suspend and then re-probed on resume.

This conflicts with some embedded boards that require to remain powered.
They will fail on resume with:

brcmfmac: brcmf_sdio_bus_rxctl: resumed on timeout
ieee80211 phy1: brcmf_bus_started: failed: -110
ieee80211 phy1: brcmf_attach: dongle is not responding: err=-110
brcmfmac: brcmf_sdio_firmware_callback: brcmf_attach failed

This commit checks for the Device Tree property 'cap-power-off-cards'.
If this property is not set, it means that we do not have the capability
to power off and should therefore remain powered.

Signed-off-by: Matthias Proske <email@matthias-proske.de>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>
Link: https://patch.msgid.link/20250212185941.146958-2-email@matthias-proske.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../broadcom/brcm80211/brcmfmac/bcmsdh.c      | 20 ++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 60eb95fc19a5a..6bc107476a2a3 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -1172,6 +1172,7 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	struct brcmf_bus *bus_if;
 	struct brcmf_sdio_dev *sdiodev;
 	mmc_pm_flag_t sdio_flags;
+	bool cap_power_off;
 	int ret = 0;
 
 	func = container_of(dev, struct sdio_func, dev);
@@ -1179,19 +1180,23 @@ static int brcmf_ops_sdio_suspend(struct device *dev)
 	if (func->num != 1)
 		return 0;
 
+	cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	bus_if = dev_get_drvdata(dev);
 	sdiodev = bus_if->bus_priv.sdio;
 
-	if (sdiodev->wowl_enabled) {
+	if (sdiodev->wowl_enabled || !cap_power_off) {
 		brcmf_sdiod_freezer_on(sdiodev);
 		brcmf_sdio_wd_timer(sdiodev->bus, 0);
 
 		sdio_flags = MMC_PM_KEEP_POWER;
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
-			enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
-		else
-			sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+
+		if (sdiodev->wowl_enabled) {
+			if (sdiodev->settings->bus.sdio.oob_irq_supported)
+				enable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
+			else
+				sdio_flags |= MMC_PM_WAKE_SDIO_IRQ;
+		}
 
 		if (sdio_set_host_pm_flags(sdiodev->func1, sdio_flags))
 			brcmf_err("Failed to set pm_flags %x\n", sdio_flags);
@@ -1213,18 +1218,19 @@ static int brcmf_ops_sdio_resume(struct device *dev)
 	struct brcmf_sdio_dev *sdiodev = bus_if->bus_priv.sdio;
 	struct sdio_func *func = container_of(dev, struct sdio_func, dev);
 	int ret = 0;
+	bool cap_power_off = !!(func->card->host->caps & MMC_CAP_POWER_OFF_CARD);
 
 	brcmf_dbg(SDIO, "Enter: F%d\n", func->num);
 	if (func->num != 2)
 		return 0;
 
-	if (!sdiodev->wowl_enabled) {
+	if (!sdiodev->wowl_enabled && cap_power_off) {
 		/* bus was powered off and device removed, probe again */
 		ret = brcmf_sdiod_probe(sdiodev);
 		if (ret)
 			brcmf_err("Failed to probe device on resume\n");
 	} else {
-		if (sdiodev->settings->bus.sdio.oob_irq_supported)
+		if (sdiodev->wowl_enabled && sdiodev->settings->bus.sdio.oob_irq_supported)
 			disable_irq_wake(sdiodev->settings->bus.sdio.oob_irq_nr);
 
 		brcmf_sdiod_freezer_off(sdiodev);

From e4cf8ec4de4e13f156c1d61977d282d90c221085 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Thu, 20 Feb 2025 08:14:43 +0000
Subject: [PATCH 1201/2753] affs: generate OFS sequence numbers starting at 1

If I write a file to an OFS floppy image, and try to read it back on
an emulated Amiga running Workbench 1.3, the Amiga reports a disk
error trying to read the file. (That is, it's unable to read it _at
all_, even to copy it to the NIL: device. It isn't a matter of getting
the wrong data and being unable to parse the file format.)

This is because the 'sequence number' field in the OFS data block
header is supposed to be based at 1, but affs writes it based at 0.
All three locations changed by this patch were setting the sequence
number to a variable 'bidx' which was previously obtained by dividing
a file position by bsize, so bidx will naturally use 0 for the first
block. Therefore all three should add 1 to that value before writing
it into the sequence number field.

With this change, the Amiga successfully reads the file.

For data block reference: https://wiki.osdev.org/FFS_(Amiga)

Signed-off-by: Simon Tatham <anakin@pobox.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/affs/file.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/affs/file.c b/fs/affs/file.c
index a5a861dd52230..226308f8627e7 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -596,7 +596,7 @@ affs_extent_file_ofs(struct inode *inode, u32 newsize)
 		BUG_ON(tmp > bsize);
 		AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 		AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+		AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 		affs_fix_checksum(sb, bh);
 		bh->b_state &= ~(1UL << BH_New);
@@ -746,7 +746,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(bsize);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);
@@ -780,7 +780,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		if (buffer_new(bh)) {
 			AFFS_DATA_HEAD(bh)->ptype = cpu_to_be32(T_DATA);
 			AFFS_DATA_HEAD(bh)->key = cpu_to_be32(inode->i_ino);
-			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx);
+			AFFS_DATA_HEAD(bh)->sequence = cpu_to_be32(bidx + 1);
 			AFFS_DATA_HEAD(bh)->size = cpu_to_be32(tmp);
 			AFFS_DATA_HEAD(bh)->next = 0;
 			bh->b_state &= ~(1UL << BH_New);

From 011ea742a25a77bac3d995f457886a67d178c6f0 Mon Sep 17 00:00:00 2001
From: Simon Tatham <anakin@pobox.com>
Date: Thu, 20 Feb 2025 08:14:44 +0000
Subject: [PATCH 1202/2753] affs: don't write overlarge OFS data block size
 fields

If a data sector on an OFS floppy contains a value > 0x1e8 (the
largest amount of data that fits in the sector after its header), then
an Amiga reading the file can return corrupt data, by taking the
overlarge size at its word and reading past the end of the buffer it
read the disk sector into!

The cause: when affs_write_end_ofs() writes data to an OFS filesystem,
the new size field for a data block was computed by adding the amount
of data currently being written (into the block) to the existing value
of the size field. This is correct if you're extending the file at the
end, but if you seek backwards in the file and overwrite _existing_
data, it can lead to the size field being larger than the maximum
legal value.

This commit changes the calculation so that it sets the size field to
the max of its previous size and the position within the block that we
just wrote up to.

Signed-off-by: Simon Tatham <anakin@pobox.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/affs/file.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/affs/file.c b/fs/affs/file.c
index 226308f8627e7..7a71018e3f675 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -724,7 +724,8 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 		tmp = min(bsize - boff, to - from);
 		BUG_ON(boff + tmp > bsize || tmp > bsize);
 		memcpy(AFFS_DATA(bh) + boff, data + from, tmp);
-		be32_add_cpu(&AFFS_DATA_HEAD(bh)->size, tmp);
+		AFFS_DATA_HEAD(bh)->size = cpu_to_be32(
+			max(boff + tmp, be32_to_cpu(AFFS_DATA_HEAD(bh)->size)));
 		affs_fix_checksum(sb, bh);
 		mark_buffer_dirty_inode(bh, inode);
 		written += tmp;

From cf6b9ba172ddc1eb989695225c456c219370f1a5 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 15:53:53 +0100
Subject: [PATCH 1203/2753] wifi: iwlegacy: don't warn for unused variables
 with DEBUG_FS=n

The reference to il_rate_mcs is inside of an #ifdef, causing a W=1 warning:

drivers/net/wireless/intel/iwlegacy/4965-rs.c:189:38: error: unused variable 'il_rate_mcs' [-Werror,-Wunused-const-variable]
static const struct il_rate_mcs_info il_rate_mcs[RATE_COUNT] = {

Replace the #ifdef with a PTR_IF() for better compile time analysis.
The dead code will still get eliminated, but the warning goes away.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250225145359.1126786-1-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlegacy/4965-rs.c | 15 ++-------------
 drivers/net/wireless/intel/iwlegacy/common.h  |  2 --
 2 files changed, 2 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index 718efb1aa1b0c..f754fb979546e 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -132,15 +132,8 @@ static void il4965_rs_fill_link_cmd(struct il_priv *il,
 static void il4965_rs_stay_in_table(struct il_lq_sta *lq_sta,
 				    bool force_search);
 
-#ifdef CONFIG_MAC80211_DEBUGFS
 static void il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta,
 				    u32 *rate_n_flags, int idx);
-#else
-static void
-il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta, u32 * rate_n_flags, int idx)
-{
-}
-#endif
 
 /*
  * The following tables contain the expected throughput metrics for all rates
@@ -2495,8 +2488,6 @@ il4965_rs_free_sta(void *il_r, struct ieee80211_sta *sta, void *il_sta)
 	D_RATE("leave\n");
 }
 
-#ifdef CONFIG_MAC80211_DEBUGFS
-
 static void
 il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta, u32 * rate_n_flags, int idx)
 {
@@ -2758,7 +2749,6 @@ il4965_rs_add_debugfs(void *il, void *il_sta, struct dentry *dir)
 	debugfs_create_u8("tx_agg_tid_enable", 0600, dir,
 			  &lq_sta->tx_agg_tid_en);
 }
-#endif
 
 /*
  * Initialization of rate scaling information is done by driver after
@@ -2781,9 +2771,8 @@ static const struct rate_control_ops rs_4965_ops = {
 	.free = il4965_rs_free,
 	.alloc_sta = il4965_rs_alloc_sta,
 	.free_sta = il4965_rs_free_sta,
-#ifdef CONFIG_MAC80211_DEBUGFS
-	.add_sta_debugfs = il4965_rs_add_debugfs,
-#endif
+	.add_sta_debugfs = PTR_IF(IS_ENABLED(CONFIG_MAC80211_DEBUGFS),
+				  il4965_rs_add_debugfs),
 };
 
 int
diff --git a/drivers/net/wireless/intel/iwlegacy/common.h b/drivers/net/wireless/intel/iwlegacy/common.h
index 92285412ab109..52610f5e57a39 100644
--- a/drivers/net/wireless/intel/iwlegacy/common.h
+++ b/drivers/net/wireless/intel/iwlegacy/common.h
@@ -2815,9 +2815,7 @@ struct il_lq_sta {
 	struct il_scale_tbl_info lq_info[LQ_SIZE];	/* "active", "search" */
 	struct il_traffic_load load[TID_MAX_LOAD_COUNT];
 	u8 tx_agg_tid_en;
-#ifdef CONFIG_MAC80211_DEBUGFS
 	u32 dbg_fixed_rate;
-#endif
 	struct il_priv *drv;
 
 	/* used to be in sta_info */

From 129860044c611008be37f49d04cf41874e3659e6 Mon Sep 17 00:00:00 2001
From: Alexander Wetzel <Alexander@wetzel-home.de>
Date: Thu, 20 Feb 2025 10:41:39 +0100
Subject: [PATCH 1204/2753] wifi: mac80211: Add counter for all monitor
 interfaces

Count open monitor interfaces regardless of the monitor interface type.
The new counter virt_monitors takes over counting interfaces depending
on the virtual monitor interface while monitors is used for all active
monitor interfaces.

This fixes monitor packet mirroring when using MONITOR_FLAG_ACTIVE or
NO_VIRTUAL_MONITOR interfaces.

Fixes: 286e69677065 ("wifi: mac80211: Drop cooked monitor support")
Reported-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Closes: https://lore.kernel.org/r/cc715114-4e3b-619a-49dc-a4878075e1dc@quicinc.com
Signed-off-by: Alexander Wetzel <Alexander@wetzel-home.de>
Tested-by: Karthikeyan Periyasamy <quic_periyasa@quicinc.com>
Link: https://patch.msgid.link/20250220094139.61459-1-Alexander@wetzel-home.de
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c         |  5 ++---
 net/mac80211/ethtool.c     |  2 +-
 net/mac80211/ieee80211_i.h |  2 +-
 net/mac80211/iface.c       | 22 +++++++++++++---------
 net/mac80211/util.c        |  3 ++-
 5 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 5785fe30adaa1..09708a060bb79 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -4370,9 +4370,8 @@ static int ieee80211_cfg_get_channel(struct wiphy *wiphy,
 	if (chanctx_conf) {
 		*chandef = link->conf->chanreq.oper;
 		ret = 0;
-	} else if (!ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR) &&
-		   local->open_count > 0 &&
-		   local->open_count == local->monitors &&
+	} else if (local->open_count > 0 &&
+		   local->open_count == local->virt_monitors &&
 		   sdata->vif.type == NL80211_IFTYPE_MONITOR) {
 		*chandef = local->monitor_chanreq.oper;
 		ret = 0;
diff --git a/net/mac80211/ethtool.c b/net/mac80211/ethtool.c
index 42f7ee142ce3f..0397755a3bd1c 100644
--- a/net/mac80211/ethtool.c
+++ b/net/mac80211/ethtool.c
@@ -158,7 +158,7 @@ static void ieee80211_get_stats(struct net_device *dev,
 	if (chanctx_conf)
 		channel = chanctx_conf->def.chan;
 	else if (local->open_count > 0 &&
-		 local->open_count == local->monitors &&
+		 local->open_count == local->virt_monitors &&
 		 sdata->vif.type == NL80211_IFTYPE_MONITOR)
 		channel = local->monitor_chanreq.oper.chan;
 	else
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index f23be8b5d0d87..845888ac3d2cb 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -1384,7 +1384,7 @@ struct ieee80211_local {
 	spinlock_t queue_stop_reason_lock;
 
 	int open_count;
-	int monitors, tx_mntrs;
+	int monitors, virt_monitors, tx_mntrs;
 	/* number of interfaces with corresponding FIF_ flags */
 	int fif_fcsfail, fif_plcpfail, fif_control, fif_other_bss, fif_pspoll,
 	    fif_probe_req;
diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
index d8b14ba95ae24..33c7c62d19f58 100644
--- a/net/mac80211/iface.c
+++ b/net/mac80211/iface.c
@@ -582,11 +582,13 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 		/* no need to tell driver */
 		break;
 	case NL80211_IFTYPE_MONITOR:
+		local->monitors--;
+
 		if (!(sdata->u.mntr.flags & MONITOR_FLAG_ACTIVE) &&
 		    !ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
 
-			local->monitors--;
-			if (local->monitors == 0) {
+			local->virt_monitors--;
+			if (local->virt_monitors == 0) {
 				local->hw.conf.flags &= ~IEEE80211_CONF_MONITOR;
 				hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
 			}
@@ -683,7 +685,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	case NL80211_IFTYPE_AP_VLAN:
 		break;
 	case NL80211_IFTYPE_MONITOR:
-		if (local->monitors == 0)
+		if (local->virt_monitors == 0)
 			ieee80211_del_virtual_monitor(local);
 
 		ieee80211_recalc_idle(local);
@@ -720,7 +722,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
 	ieee80211_configure_filter(local);
 	ieee80211_hw_config(local, hw_reconf_flags);
 
-	if (local->monitors == local->open_count)
+	if (local->virt_monitors == local->open_count)
 		ieee80211_add_virtual_monitor(local);
 }
 
@@ -979,7 +981,7 @@ static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdat
 		    local->hw.wiphy->frag_threshold != (u32)-1)
 			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
 
-		if (local->monitors)
+		if (local->virt_monitors)
 			flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
 	} else {
 		flags &= ~IEEE80211_OFFLOAD_ENCAP_ENABLED;
@@ -989,7 +991,7 @@ static bool ieee80211_set_sdata_offload_flags(struct ieee80211_sub_if_data *sdat
 	    ieee80211_iftype_supports_hdr_offload(sdata->vif.type)) {
 		flags |= IEEE80211_OFFLOAD_DECAP_ENABLED;
 
-		if (local->monitors &&
+		if (local->virt_monitors &&
 		    !ieee80211_hw_check(&local->hw, SUPPORTS_CONC_MON_RX_DECAP))
 			flags &= ~IEEE80211_OFFLOAD_DECAP_ENABLED;
 	} else {
@@ -1332,20 +1334,22 @@ int ieee80211_do_open(struct wireless_dev *wdev, bool coming_up)
 			if (res)
 				goto err_stop;
 		} else {
-			if (local->monitors == 0 && local->open_count == 0) {
+			if (local->virt_monitors == 0 && local->open_count == 0) {
 				res = ieee80211_add_virtual_monitor(local);
 				if (res)
 					goto err_stop;
 			}
-			local->monitors++;
+			local->virt_monitors++;
 
 			/* must be before the call to ieee80211_configure_filter */
-			if (local->monitors == 1) {
+			if (local->virt_monitors == 1) {
 				local->hw.conf.flags |= IEEE80211_CONF_MONITOR;
 				hw_reconf_flags |= IEEE80211_CONF_CHANGE_MONITOR;
 			}
 		}
 
+		local->monitors++;
+
 		ieee80211_adjust_monitor_flags(sdata, 1);
 		ieee80211_configure_filter(local);
 		ieee80211_recalc_offload(local);
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index f6b631faf4f7f..49fa38fbe242b 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2155,7 +2155,8 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 
  wake_up:
 
-	if (local->monitors == local->open_count && local->monitors > 0)
+	if (local->virt_monitors > 0 &&
+	    local->virt_monitors == local->open_count)
 		ieee80211_add_virtual_monitor(local);
 
 	/*

From 7d2497ff7e5ffd5a2e4fb1a7f2547db61bcbebdd Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 19 Feb 2025 20:32:40 +0000
Subject: [PATCH 1205/2753] wifi: cfg80211: convert timeouts to
 secs_to_jiffies()

Commit b35108a51cf7 ("jiffies: Define secs_to_jiffies()") introduced
secs_to_jiffies().  As the value here is a multiple of 1000, use
secs_to_jiffies() instead of msecs_to_jiffies to avoid the multiplication.

This is converted using scripts/coccinelle/misc/secs_to_jiffies.cocci with
the following Coccinelle rules:

@depends on patch@
expression E;
@@

-msecs_to_jiffies(E * 1000)
+secs_to_jiffies(E)

-msecs_to_jiffies(E * MSEC_PER_SEC)
+secs_to_jiffies(E)

Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Reviewed-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
Link: https://patch.msgid.link/20250219203240.141272-1-eahariha@linux.microsoft.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/scan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index cd21243295210..1de25e9763cbb 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -1365,7 +1365,7 @@ void cfg80211_bss_age(struct cfg80211_registered_device *rdev,
                       unsigned long age_secs)
 {
 	struct cfg80211_internal_bss *bss;
-	unsigned long age_jiffies = msecs_to_jiffies(age_secs * MSEC_PER_SEC);
+	unsigned long age_jiffies = secs_to_jiffies(age_secs);
 
 	spin_lock_bh(&rdev->bss_lock);
 	list_for_each_entry(bss, &rdev->bss_list, list)

From ebf9944bed4ef69d29371cd3b7276f858c513954 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Fri, 14 Feb 2025 09:47:21 +0200
Subject: [PATCH 1206/2753] wifi: mac80211: Fix possible integer promotion
 issue

Fix a possible integer promotion issue in mac80211 in ieee80211_ml_epcs()

Fixes: de86c5f60839 ("wifi: mac80211: Add support for EPCS configuration")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Link: https://patch.msgid.link/20250214074721.1613549-1-ilan.peer@intel.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4e8f0a5f6251e..23d85a1abbc59 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10704,7 +10704,7 @@ static void ieee80211_ml_epcs(struct ieee80211_sub_if_data *sdata,
 						  elems->ml_epcs_len,
 						  scratch, scratch_len,
 						  IEEE80211_MLE_SUBELEM_FRAGMENT);
-		if (len < sizeof(control))
+		if (len < (ssize_t)sizeof(control))
 			continue;
 
 		pos = scratch + sizeof(control);

From d00c0c4105e5ab8a6a13ed23d701cceb285761fa Mon Sep 17 00:00:00 2001
From: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Date: Wed, 12 Feb 2025 08:21:25 +0000
Subject: [PATCH 1207/2753] wifi: mac80211: fix integer overflow in
 hwmp_route_info_get()

Since the new_metric and last_hop_metric variables can reach
the MAX_METRIC(0xffffffff) value, an integer overflow may occur
when multiplying them by 10/9. It can lead to incorrect behavior.

Found by InfoTeCS on behalf of Linux Verification Center
(linuxtesting.org) with SVACE.

Fixes: a8d418d9ac25 ("mac80211: mesh: only switch path when new metric is at least 10% better")
Cc: stable@vger.kernel.org
Signed-off-by: Ilia Gavrilov <Ilia.Gavrilov@infotecs.ru>
Link: https://patch.msgid.link/20250212082124.4078236-1-Ilia.Gavrilov@infotecs.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mesh_hwmp.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c
index 4e9546e998b6d..c94a9c7ca960e 100644
--- a/net/mac80211/mesh_hwmp.c
+++ b/net/mac80211/mesh_hwmp.c
@@ -367,6 +367,12 @@ u32 airtime_link_metric_get(struct ieee80211_local *local,
 	return (u32)result;
 }
 
+/* Check that the first metric is at least 10% better than the second one */
+static bool is_metric_better(u32 x, u32 y)
+{
+	return (x < y) && (x < (y - x / 10));
+}
+
 /**
  * hwmp_route_info_get - Update routing info to originator and transmitter
  *
@@ -458,8 +464,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata,
 				    (mpath->sn == orig_sn &&
 				     (rcu_access_pointer(mpath->next_hop) !=
 						      sta ?
-					      mult_frac(new_metric, 10, 9) :
-					      new_metric) >= mpath->metric)) {
+					      !is_metric_better(new_metric, mpath->metric) :
+					      new_metric >= mpath->metric))) {
 					process = false;
 					fresh_info = false;
 				}
@@ -533,8 +539,8 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata,
 			if ((mpath->flags & MESH_PATH_FIXED) ||
 			    ((mpath->flags & MESH_PATH_ACTIVE) &&
 			     ((rcu_access_pointer(mpath->next_hop) != sta ?
-				       mult_frac(last_hop_metric, 10, 9) :
-				       last_hop_metric) > mpath->metric)))
+				      !is_metric_better(last_hop_metric, mpath->metric) :
+				       last_hop_metric > mpath->metric))))
 				fresh_info = false;
 		} else {
 			mpath = mesh_path_add(sdata, ta);

From ebba23e0779834e68a200b7968975274cbe260ef Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 08:22:57 +0200
Subject: [PATCH 1208/2753] wifi: mac80211: add
 ieee80211_iter_chan_contexts_mtx

Add a chanctx iterator that can be called from a wiphy-locked context.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212082137.d85eef3024de.Icda0616416c5fd4b2cbf892bdab2476f26e644ec@changeid
[fix kernel-doc]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/mac80211.h | 25 +++++++++++++++++++++++++
 net/mac80211/chan.c    | 20 +++++++++++++++++++-
 2 files changed, 44 insertions(+), 1 deletion(-)

diff --git a/include/net/mac80211.h b/include/net/mac80211.h
index 22d32419e8a05..c498f685d01f3 100644
--- a/include/net/mac80211.h
+++ b/include/net/mac80211.h
@@ -6671,6 +6671,31 @@ void ieee80211_iter_chan_contexts_atomic(
 		     void *data),
 	void *iter_data);
 
+/**
+ * ieee80211_iter_chan_contexts_mtx - iterate channel contexts
+ * @hw: pointer obtained from ieee80211_alloc_hw().
+ * @iter: iterator function
+ * @iter_data: data passed to iterator function
+ *
+ * Iterate all active channel contexts. This function can only be used while
+ * holding the wiphy mutex.
+ *
+ * The iterator will not find a context that's being added (during
+ * the driver callback to add it) but will find it while it's being
+ * removed.
+ *
+ * Note that during hardware restart, all contexts that existed
+ * before the restart are considered already present so will be
+ * found while iterating, whether they've been re-added already
+ * or not.
+ */
+void ieee80211_iter_chan_contexts_mtx(
+	struct ieee80211_hw *hw,
+	void (*iter)(struct ieee80211_hw *hw,
+		     struct ieee80211_chanctx_conf *chanctx_conf,
+		     void *data),
+	void *iter_data);
+
 /**
  * ieee80211_ap_probereq_get - retrieve a Probe Request template
  * @hw: pointer obtained from ieee80211_alloc_hw().
diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
index dc28f2b0957ae..c3bfac58151f6 100644
--- a/net/mac80211/chan.c
+++ b/net/mac80211/chan.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
  * mac80211 - channel management
- * Copyright 2020 - 2024 Intel Corporation
+ * Copyright 2020 - 2025 Intel Corporation
  */
 
 #include <linux/nl80211.h>
@@ -2178,3 +2178,21 @@ void ieee80211_iter_chan_contexts_atomic(
 	rcu_read_unlock();
 }
 EXPORT_SYMBOL_GPL(ieee80211_iter_chan_contexts_atomic);
+
+void ieee80211_iter_chan_contexts_mtx(
+	struct ieee80211_hw *hw,
+	void (*iter)(struct ieee80211_hw *hw,
+		     struct ieee80211_chanctx_conf *chanctx_conf,
+		     void *data),
+	void *iter_data)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_chanctx *ctx;
+
+	lockdep_assert_wiphy(hw->wiphy);
+
+	list_for_each_entry(ctx, &local->chanctx_list, list)
+		if (ctx->driver_present)
+			iter(hw, &ctx->conf, iter_data);
+}
+EXPORT_SYMBOL_GPL(ieee80211_iter_chan_contexts_mtx);

From ceaad3c435964f601602531d0f6f7deaff329e21 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Wed, 12 Feb 2025 08:22:58 +0200
Subject: [PATCH 1209/2753] wifi: cfg80211: expose update timestamp to drivers

This information is exposed to userspace but not drivers. Make this
field public so that drivers are also able to access it. The information
is for example useful for link selection to determine whether the BSS
corresponding to an MLO link has been seen in a recent scan.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212082137.b682ee7aebc8.I0f7cca9effa2b1cee79f4f2eb8b549c99b4e0571@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 3 +++
 net/wireless/core.h    | 1 -
 net/wireless/nl80211.c | 4 ++--
 net/wireless/scan.c    | 6 +++---
 4 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index a72e7eb7027f2..3580f3f5f44ee 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2947,6 +2947,7 @@ struct cfg80211_bss_ies {
  * @nontrans_list: list of non-transmitted BSS, if this is a transmitted one
  *	(multi-BSSID support)
  * @signal: signal strength value (type depends on the wiphy's signal_type)
+ * @ts_boottime: timestamp of the last BSS update in nanoseconds since boot
  * @chains: bitmask for filled values in @chain_signal.
  * @chain_signal: per-chain signal strength of last received BSS in dBm.
  * @bssid_index: index in the multiple BSS set
@@ -2971,6 +2972,8 @@ struct cfg80211_bss {
 
 	s32 signal;
 
+	u64 ts_boottime;
+
 	u16 beacon_interval;
 	u16 capability;
 
diff --git a/net/wireless/core.h b/net/wireless/core.h
index 826299f3d7813..b094b526b05db 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -180,7 +180,6 @@ struct cfg80211_internal_bss {
 	struct list_head list;
 	struct list_head hidden_list;
 	struct rb_node rbn;
-	u64 ts_boottime;
 	unsigned long ts;
 	unsigned long refcount;
 	atomic_t hold;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8bd09110d393e..79b3f34e72e2a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10519,9 +10519,9 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb,
 		     intbss->parent_bssid)))
 		goto nla_put_failure;
 
-	if (intbss->ts_boottime &&
+	if (res->ts_boottime &&
 	    nla_put_u64_64bit(msg, NL80211_BSS_LAST_SEEN_BOOTTIME,
-			      intbss->ts_boottime, NL80211_BSS_PAD))
+			      res->ts_boottime, NL80211_BSS_PAD))
 		goto nla_put_failure;
 
 	if (!nl80211_put_signal(msg, intbss->pub.chains,
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 1de25e9763cbb..9865f305275da 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -5,7 +5,7 @@
  * Copyright 2008 Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2016	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -1934,7 +1934,7 @@ cfg80211_update_known_bss(struct cfg80211_registered_device *rdev,
 		known->pub.signal = new->pub.signal;
 	known->pub.capability = new->pub.capability;
 	known->ts = new->ts;
-	known->ts_boottime = new->ts_boottime;
+	known->pub.ts_boottime = new->pub.ts_boottime;
 	known->parent_tsf = new->parent_tsf;
 	known->pub.chains = new->pub.chains;
 	memcpy(known->pub.chain_signal, new->pub.chain_signal,
@@ -2291,7 +2291,7 @@ cfg80211_inform_single_bss_data(struct wiphy *wiphy,
 		tmp.pub.signal = 0;
 	tmp.pub.beacon_interval = data->beacon_interval;
 	tmp.pub.capability = data->capability;
-	tmp.ts_boottime = drv_data->boottime_ns;
+	tmp.pub.ts_boottime = drv_data->boottime_ns;
 	tmp.parent_tsf = drv_data->parent_tsf;
 	ether_addr_copy(tmp.parent_bssid, drv_data->parent_bssid);
 	tmp.pub.chains = drv_data->chains;

From 180d52d224ccaf475a0279563381b5e7fd8d1f05 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Wed, 12 Feb 2025 07:43:22 +0200
Subject: [PATCH 1210/2753] wifi: iwlwifi: location api cleanup

Remove the version suffix from the latest version of the range
request command structs and the range response notification structs.
In addition, don't use MVM in the API file as it is not MVM specific.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.294b7109e0be.I229ceef5933e825815d84c33855cadd62687ee04@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/location.h  | 66 +++++++++----------
 .../intel/iwlwifi/mvm/ftm-initiator.c         | 18 ++---
 .../net/wireless/intel/iwlwifi/mvm/mac80211.c |  4 +-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h  |  4 +-
 4 files changed, 46 insertions(+), 46 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
index b8dff139aa05f..e1952fc6d1490 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/location.h
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
  * Copyright (C) 2018-2022 Intel Corporation
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #ifndef __iwl_fw_api_location_h__
 #define __iwl_fw_api_location_h__
@@ -1015,7 +1015,7 @@ struct iwl_tof_range_req_ap_entry_v9 {
 } __packed; /* LOCATION_RANGE_REQ_AP_ENTRY_CMD_API_S_VER_9 */
 
 /**
- * struct iwl_tof_range_req_ap_entry_v10 - AP configuration parameters
+ * struct iwl_tof_range_req_ap_entry - AP configuration parameters
  * @initiator_ap_flags: see &enum iwl_initiator_ap_flags.
  * @band: 0 for 5.2 GHz, 1 for 2.4 GHz, 2 for 6GHz
  * @channel_num: AP Channel number
@@ -1063,7 +1063,7 @@ struct iwl_tof_range_req_ap_entry_v9 {
  * @min_time_between_msr: For non trigger based NDP ranging, the minimum time
  *	between measurements in units of milliseconds
  */
-struct iwl_tof_range_req_ap_entry_v10 {
+struct iwl_tof_range_req_ap_entry {
 	__le32 initiator_ap_flags;
 	u8 band;
 	u8 channel_num;
@@ -1134,7 +1134,7 @@ enum iwl_tof_initiator_flags {
 	IWL_TOF_INITIATOR_FLAGS_NON_ASAP_SUPPORT = BIT(20),
 }; /* LOCATION_RANGE_REQ_CMD_API_S_VER_5 */
 
-#define IWL_MVM_TOF_MAX_APS 5
+#define IWL_TOF_MAX_APS 5
 #define IWL_MVM_TOF_MAX_TWO_SIDED_APS 5
 
 /**
@@ -1153,7 +1153,7 @@ enum iwl_tof_initiator_flags {
  *		   when the session is done (successfully / partially).
  *		   one of iwl_tof_response_mode.
  * @reserved0: reserved
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @macaddr_random: '0' Use default source MAC address (i.e. p2_p),
  *	            '1' Use MAC Address randomization according to the below
  * @range_req_bssid: ranging request BSSID
@@ -1183,7 +1183,7 @@ struct iwl_tof_range_req_cmd_v5 {
 	u8 ftm_tx_chains;
 	__le16 common_calib;
 	__le16 specific_calib;
-	struct iwl_tof_range_req_ap_entry_v2 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v2 ap[IWL_TOF_MAX_APS];
 } __packed;
 /* LOCATION_RANGE_REQ_CMD_API_S_VER_5 */
 
@@ -1192,7 +1192,7 @@ struct iwl_tof_range_req_cmd_v5 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1216,7 +1216,7 @@ struct iwl_tof_range_req_cmd_v7 {
 	__le32 tsf_mac_id;
 	__le16 common_calib;
 	__le16 specific_calib;
-	struct iwl_tof_range_req_ap_entry_v3 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v3 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_7 */
 
 /**
@@ -1224,7 +1224,7 @@ struct iwl_tof_range_req_cmd_v7 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1248,7 +1248,7 @@ struct iwl_tof_range_req_cmd_v8 {
 	__le32 tsf_mac_id;
 	__le16 common_calib;
 	__le16 specific_calib;
-	struct iwl_tof_range_req_ap_entry_v4 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v4 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_8 */
 
 /**
@@ -1256,7 +1256,7 @@ struct iwl_tof_range_req_cmd_v8 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1276,7 +1276,7 @@ struct iwl_tof_range_req_cmd_v9 {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry_v6 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v6 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_9 */
 
 /**
@@ -1284,7 +1284,7 @@ struct iwl_tof_range_req_cmd_v9 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1304,7 +1304,7 @@ struct iwl_tof_range_req_cmd_v11 {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry_v7 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v7 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_11 */
 
 /**
@@ -1312,7 +1312,7 @@ struct iwl_tof_range_req_cmd_v11 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1332,7 +1332,7 @@ struct iwl_tof_range_req_cmd_v12 {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry_v8 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v8 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_12 */
 
 /**
@@ -1340,7 +1340,7 @@ struct iwl_tof_range_req_cmd_v12 {
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1360,15 +1360,15 @@ struct iwl_tof_range_req_cmd_v13 {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry_v9 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_req_ap_entry_v9 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_13 */
 
 /**
- * struct iwl_tof_range_req_cmd_v14 - start measurement cmd
+ * struct iwl_tof_range_req_cmd - start measurement cmd
  * @initiator_flags: see flags @ iwl_tof_initiator_flags
  * @request_id: A Token incremented per request. The same Token will be
  *		sent back in the range response
- * @num_of_ap: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_ap: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @range_req_bssid: ranging request BSSID
  * @macaddr_mask: Bits set to 0 shall be copied from the MAC address template.
  *		  Bits set to 1 shall be randomized by the UMAC
@@ -1377,9 +1377,9 @@ struct iwl_tof_range_req_cmd_v13 {
  *	This is the session time for completing the measurement.
  * @tsf_mac_id: report the measurement start time for each ap in terms of the
  *	TSF of this mac id. 0xff to disable TSF reporting.
- * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry_v10.
+ * @ap: per-AP request data, see &struct iwl_tof_range_req_ap_entry.
  */
-struct iwl_tof_range_req_cmd_v14 {
+struct iwl_tof_range_req_cmd {
 	__le32 initiator_flags;
 	u8 request_id;
 	u8 num_of_ap;
@@ -1388,8 +1388,8 @@ struct iwl_tof_range_req_cmd_v14 {
 	u8 macaddr_template[ETH_ALEN];
 	__le32 req_timeout_ms;
 	__le32 tsf_mac_id;
-	struct iwl_tof_range_req_ap_entry_v10 ap[IWL_MVM_TOF_MAX_APS];
-} __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_13 */
+	struct iwl_tof_range_req_ap_entry ap[IWL_TOF_MAX_APS];
+} __packed; /* LOCATION_RANGE_REQ_CMD_API_S_VER_15 */
 
 /*
  * enum iwl_tof_range_request_status - status of the sent request
@@ -1609,7 +1609,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v5 {
 } __packed; /* LOCATION_RANGE_RSP_AP_ETRY_NTFY_API_S_VER_5 */
 
 /**
- * struct iwl_tof_range_rsp_ap_entry_ntfy_v6 - AP parameters (response)
+ * struct iwl_tof_range_rsp_ap_entry_ntfy - AP parameters (response)
  * @bssid: BSSID of the AP
  * @measure_status: current APs measurement status, one of
  *	&enum iwl_tof_entry_status.
@@ -1645,7 +1645,7 @@ struct iwl_tof_range_rsp_ap_entry_ntfy_v5 {
  * @tx_pn: the last PN used for this responder Tx in case PMF is configured in
  *	LE byte order.
  */
-struct iwl_tof_range_rsp_ap_entry_ntfy_v6 {
+struct iwl_tof_range_rsp_ap_entry_ntfy {
 	u8 bssid[ETH_ALEN];
 	u8 measure_status;
 	u8 measure_bw;
@@ -1695,7 +1695,7 @@ enum iwl_tof_response_status {
  * @request_status: status of current measurement session, one of
  *	&enum iwl_tof_response_status.
  * @last_in_batch: reprot policy (when not all responses are uploaded at once)
- * @num_of_aps: Number of APs to measure (error if > IWL_MVM_TOF_MAX_APS)
+ * @num_of_aps: Number of APs to measure (error if > IWL_TOF_MAX_APS)
  * @ap: per-AP data
  */
 struct iwl_tof_range_rsp_ntfy_v5 {
@@ -1703,7 +1703,7 @@ struct iwl_tof_range_rsp_ntfy_v5 {
 	u8 request_status;
 	u8 last_in_batch;
 	u8 num_of_aps;
-	struct iwl_tof_range_rsp_ap_entry_ntfy_v3 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v3 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_5 */
 
 /**
@@ -1719,7 +1719,7 @@ struct iwl_tof_range_rsp_ntfy_v6 {
 	u8 num_of_aps;
 	u8 last_report;
 	u8 reserved;
-	struct iwl_tof_range_rsp_ap_entry_ntfy_v4 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v4 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_6 */
 
 /**
@@ -1735,23 +1735,23 @@ struct iwl_tof_range_rsp_ntfy_v7 {
 	u8 num_of_aps;
 	u8 last_report;
 	u8 reserved;
-	struct iwl_tof_range_rsp_ap_entry_ntfy_v5 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_rsp_ap_entry_ntfy_v5 ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_7 */
 
 /**
- * struct iwl_tof_range_rsp_ntfy_v8 - ranging response notification
+ * struct iwl_tof_range_rsp_ntfy - ranging response notification
  * @request_id: A Token ID of the corresponding Range request
  * @num_of_aps: Number of APs results
  * @last_report: 1 if no more FTM sessions are scheduled, 0 otherwise.
  * @reserved: reserved
  * @ap: per-AP data
  */
-struct iwl_tof_range_rsp_ntfy_v8 {
+struct iwl_tof_range_rsp_ntfy {
 	u8 request_id;
 	u8 num_of_aps;
 	u8 last_report;
 	u8 reserved;
-	struct iwl_tof_range_rsp_ap_entry_ntfy_v6 ap[IWL_MVM_TOF_MAX_APS];
+	struct iwl_tof_range_rsp_ap_entry_ntfy ap[IWL_TOF_MAX_APS];
 } __packed; /* LOCATION_RANGE_RSP_NTFY_API_S_VER_8,
 	       LOCATION_RANGE_RSP_NTFY_API_S_VER_9 */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index f7034fa40c265..dfb25b964f0eb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/etherdevice.h>
 #include <linux/math64.h>
@@ -848,7 +848,7 @@ static int iwl_mvm_ftm_start_v13(struct iwl_mvm *mvm,
 static int
 iwl_mvm_ftm_put_target_v10(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 			   struct cfg80211_pmsr_request_peer *peer,
-			   struct iwl_tof_range_req_ap_entry_v10 *target)
+			   struct iwl_tof_range_req_ap_entry *target)
 {
 	u32 i2r_max_sts, flags;
 	int ret;
@@ -920,7 +920,7 @@ static int iwl_mvm_ftm_start_v14(struct iwl_mvm *mvm,
 				 struct ieee80211_vif *vif,
 				 struct cfg80211_pmsr_request *req)
 {
-	struct iwl_tof_range_req_cmd_v14 cmd;
+	struct iwl_tof_range_req_cmd cmd;
 	struct iwl_host_cmd hcmd = {
 		.id = WIDE_ID(LOCATION_GROUP, TOF_RANGE_REQ_CMD),
 		.dataflags[0] = IWL_HCMD_DFL_DUP,
@@ -934,7 +934,7 @@ static int iwl_mvm_ftm_start_v14(struct iwl_mvm *mvm,
 
 	for (i = 0; i < cmd.num_of_ap; i++) {
 		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
-		struct iwl_tof_range_req_ap_entry_v10 *target = &cmd.ap[i];
+		struct iwl_tof_range_req_ap_entry *target = &cmd.ap[i];
 
 		err = iwl_mvm_ftm_put_target_v10(mvm, vif, peer, target);
 		if (err)
@@ -1200,7 +1200,7 @@ static void iwl_mvm_debug_range_resp(struct iwl_mvm *mvm, u8 index,
 
 static void
 iwl_mvm_ftm_pasn_update_pn(struct iwl_mvm *mvm,
-			   struct iwl_tof_range_rsp_ap_entry_ntfy_v6 *fw_ap)
+			   struct iwl_tof_range_rsp_ap_entry_ntfy *fw_ap)
 {
 	struct iwl_mvm_ftm_pasn_entry *entry;
 
@@ -1238,7 +1238,7 @@ static bool iwl_mvm_ftm_resp_size_validation(u8 ver, unsigned int pkt_len)
 	switch (ver) {
 	case 9:
 	case 8:
-		return pkt_len == sizeof(struct iwl_tof_range_rsp_ntfy_v8);
+		return pkt_len == sizeof(struct iwl_tof_range_rsp_ntfy);
 	case 7:
 		return pkt_len == sizeof(struct iwl_tof_range_rsp_ntfy_v7);
 	case 6:
@@ -1258,7 +1258,7 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 	struct iwl_tof_range_rsp_ntfy_v5 *fw_resp_v5 = (void *)pkt->data;
 	struct iwl_tof_range_rsp_ntfy_v6 *fw_resp_v6 = (void *)pkt->data;
 	struct iwl_tof_range_rsp_ntfy_v7 *fw_resp_v7 = (void *)pkt->data;
-	struct iwl_tof_range_rsp_ntfy_v8 *fw_resp_v8 = (void *)pkt->data;
+	struct iwl_tof_range_rsp_ntfy *fw_resp_v8 = (void *)pkt->data;
 	int i;
 	bool new_api = fw_has_api(&mvm->fw->ucode_capa,
 				  IWL_UCODE_TLV_API_FTM_NEW_RANGE_REQ);
@@ -1294,9 +1294,9 @@ void iwl_mvm_ftm_range_resp(struct iwl_mvm *mvm, struct iwl_rx_cmd_buffer *rxb)
 	IWL_DEBUG_INFO(mvm, "request id: %lld, num of entries: %u\n",
 		       mvm->ftm_initiator.req->cookie, num_of_aps);
 
-	for (i = 0; i < num_of_aps && i < IWL_MVM_TOF_MAX_APS; i++) {
+	for (i = 0; i < num_of_aps && i < IWL_TOF_MAX_APS; i++) {
 		struct cfg80211_pmsr_result result = {};
-		struct iwl_tof_range_rsp_ap_entry_ntfy_v6 *fw_ap;
+		struct iwl_tof_range_rsp_ap_entry_ntfy *fw_ap;
 		int peer_idx;
 
 		if (new_api) {
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 014777c9cc5d4..20aaef913e3f1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -70,7 +70,7 @@ static const struct ieee80211_iface_combination iwl_mvm_iface_combinations[] = {
 };
 
 static const struct cfg80211_pmsr_capabilities iwl_mvm_pmsr_capa = {
-	.max_peers = IWL_MVM_TOF_MAX_APS,
+	.max_peers = IWL_TOF_MAX_APS,
 	.report_ap_tsf = 1,
 	.randomize_mac_addr = 1,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index d17592d3f6c8e..b6e0b63cbd3c1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1310,7 +1310,7 @@ struct iwl_mvm {
 		struct cfg80211_pmsr_request *req;
 		struct wireless_dev *req_wdev;
 		struct list_head loc_list;
-		int responses[IWL_MVM_TOF_MAX_APS];
+		int responses[IWL_TOF_MAX_APS];
 		struct {
 			struct list_head resp;
 		} smooth;

From 79c06299e719f21ecb9b657cd2baa980698b1f0b Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 12 Feb 2025 07:43:23 +0200
Subject: [PATCH 1211/2753] wifi: iwlwifi: use 0xff instead of 0xffffffff for
 invalid

The firmware is now able to understand 0xff and that is more widely
used.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.c6719e6dc0a6.Ifd149101fa886730602dbbb02f980be8e554fe84@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/context.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/context.h b/drivers/net/wireless/intel/iwlwifi/fw/api/context.h
index a9fa5f054ce08..464eed9b5e71d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/context.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/context.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2022 Intel Corporation
+ * Copyright (C) 2012-2014, 2022, 2024 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -14,6 +14,9 @@
  * @FW_CTXT_COLOR_POS: position of the color
  * @FW_CTXT_COLOR_MSK: mask of the color
  * @FW_CTXT_INVALID: value used to indicate unused/invalid
+ * @FW_CTXT_ID_INVALID: value used to indicate unused/invalid. This can be
+ *	used with newer firmware which no longer use the color. Typically,
+ *	firmware versions supported by iwlmld can use this value.
  */
 enum iwl_ctxt_id_and_color {
 	FW_CTXT_ID_POS		= 0,
@@ -21,6 +24,7 @@ enum iwl_ctxt_id_and_color {
 	FW_CTXT_COLOR_POS	= 8,
 	FW_CTXT_COLOR_MSK	= 0xff << FW_CTXT_COLOR_POS,
 	FW_CTXT_INVALID		= 0xffffffff,
+	FW_CTXT_ID_INVALID	= 0xff,
 };
 
 #define FW_CMD_ID_AND_COLOR(_id, _color) (((_id) << FW_CTXT_ID_POS) |\

From e1fc9288a1faf77947990327593f7fdeef4a62bc Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:24 +0200
Subject: [PATCH 1212/2753] wifi: iwlwifi: remove mvm prefix from
 iwl_mvm_esr_mode_notif

This is not specific to mvm.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.c536eeaae129.I848307be6df21913c0ce3eb6baef715cd401db1a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h | 4 ++--
 drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h  | 4 ++--
 drivers/net/wireless/intel/iwlwifi/mvm/ops.c         | 6 +++---
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index 570a3f7225103..34a562d6c2085 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  * Copyright (C) 2012-2014, 2018-2022 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
@@ -92,7 +92,7 @@ enum iwl_data_path_subcmd_ids {
 
 	/**
 	 * @ESR_MODE_NOTIF: notification to recommend/force a wanted esr mode,
-	 *	uses &struct iwl_mvm_esr_mode_notif
+	 *	uses &struct iwl_esr_mode_notif
 	 */
 	ESR_MODE_NOTIF = 0xF3,
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
index 511e86ea11d44..b511e3aa6bb2f 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/mac-cfg.h
@@ -697,11 +697,11 @@ enum iwl_mvm_fw_esr_recommendation {
 }; /* ESR_MODE_RECOMMENDATION_CODE_API_E_VER_1 */
 
 /**
- * struct iwl_mvm_esr_mode_notif - FWs recommendation/force for esr mode
+ * struct iwl_esr_mode_notif - FWs recommendation/force for esr mode
  *
  * @action: the action to apply on esr state. See &iwl_mvm_fw_esr_recommendation
  */
-struct iwl_mvm_esr_mode_notif {
+struct iwl_esr_mode_notif {
 	__le32 action;
 } __packed; /* ESR_MODE_RECOMMENDATION_NTFY_API_S_VER_1 */
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
index 984f407f70272..76603ef02704a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -145,7 +145,7 @@ static void iwl_mvm_rx_esr_mode_notif(struct iwl_mvm *mvm,
 				      struct iwl_rx_cmd_buffer *rxb)
 {
 	struct iwl_rx_packet *pkt = rxb_addr(rxb);
-	struct iwl_mvm_esr_mode_notif *notif = (void *)pkt->data;
+	struct iwl_esr_mode_notif *notif = (void *)pkt->data;
 	struct ieee80211_vif *vif = iwl_mvm_get_bss_vif(mvm);
 
 	/* FW recommendations is only for entering EMLSR */
@@ -495,7 +495,7 @@ static const struct iwl_rx_handlers iwl_mvm_rx_handlers[] = {
 	RX_HANDLER_GRP(DATA_PATH_GROUP, ESR_MODE_NOTIF,
 		       iwl_mvm_rx_esr_mode_notif,
 		       RX_HANDLER_ASYNC_LOCKED_WIPHY,
-		       struct iwl_mvm_esr_mode_notif),
+		       struct iwl_esr_mode_notif),
 
 	RX_HANDLER_GRP(DATA_PATH_GROUP, MONITOR_NOTIF,
 		       iwl_mvm_rx_monitor_notif, RX_HANDLER_ASYNC_LOCKED,

From 2bfbd823abde3f462d956b03e7f0d043eaba385a Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:25 +0200
Subject: [PATCH 1213/2753] wifi: iwlwifi: mld: add a debug level for PTP
 prints

This is required for PTP related debug prints.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.866f8f66b1d7.I764abcb845d992d058c753ce8fa9d45fed2ff4ec@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-debug.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
index bf52c2edaad12..5377dda9ad536 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
@@ -2,7 +2,7 @@
 /******************************************************************************
  *
  * Copyright(c) 2003 - 2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2018 - 2021, 2024 Intel Corporation
+ * Copyright(c) 2018 - 2021, 2024-2025 Intel Corporation
  *
  * Portions of this file are derived from the ipw3945 project.
  *****************************************************************************/
@@ -156,6 +156,7 @@ do {                                            			\
 #define IWL_DL_FW		0x00010000
 #define IWL_DL_RF_KILL		0x00020000
 #define IWL_DL_TPT		0x00040000
+#define IWL_DL_PTP		0x00080000
 /* 0x00F00000 - 0x00100000 */
 #define IWL_DL_RATE		0x00100000
 #define IWL_DL_CALIB		0x00200000
@@ -216,5 +217,6 @@ do {                                            			\
 #define IWL_DEBUG_LAR(p, f, a...)	IWL_DEBUG(p, IWL_DL_LAR, f, ## a)
 #define IWL_DEBUG_FW_INFO(p, f, a...)		\
 		IWL_DEBUG(p, IWL_DL_INFO | IWL_DL_FW, f, ## a)
+#define IWL_DEBUG_PTP(p, f, a...)	IWL_DEBUG(p, IWL_DL_PTP, f, ## a)
 
 #endif

From e51f035b5a0850061483537d14988b5677d2f748 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:26 +0200
Subject: [PATCH 1214/2753] wifi: iwlwifi: mld: add a debug level for EHT
 prints

This is required for EHT related debug prints.
As there are no more available debug levels, delete IWL_DL_EXTERNAL,
which is not used, and replace it with IWL_DL_EHT.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.9b1e0d87e7e4.Iea6c1329f7b6312a73896f9a9d9bce72bd6548e2@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-debug.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
index 5377dda9ad536..ea32dc88584f5 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-debug.h
@@ -166,7 +166,7 @@ do {                                            			\
 #define IWL_DL_RX		0x01000000
 #define IWL_DL_ISR		0x02000000
 #define IWL_DL_HT		0x04000000
-#define IWL_DL_EXTERNAL		0x08000000
+#define IWL_DL_EHT		0x08000000
 /* 0xF0000000 - 0x10000000 */
 #define IWL_DL_11H		0x10000000
 #define IWL_DL_STATS		0x20000000
@@ -176,7 +176,6 @@ do {                                            			\
 #define IWL_DEBUG_INFO(p, f, a...)	IWL_DEBUG(p, IWL_DL_INFO, f, ## a)
 #define IWL_DEBUG_TDLS(p, f, a...)	IWL_DEBUG(p, IWL_DL_TDLS, f, ## a)
 #define IWL_DEBUG_MAC80211(p, f, a...)	IWL_DEBUG(p, IWL_DL_MAC80211, f, ## a)
-#define IWL_DEBUG_EXTERNAL(p, f, a...)	IWL_DEBUG(p, IWL_DL_EXTERNAL, f, ## a)
 #define IWL_DEBUG_TEMP(p, f, a...)	IWL_DEBUG(p, IWL_DL_TEMP, f, ## a)
 #define IWL_DEBUG_SCAN(p, f, a...)	IWL_DEBUG(p, IWL_DL_SCAN, f, ## a)
 #define IWL_DEBUG_RX(p, f, a...)	IWL_DEBUG(p, IWL_DL_RX, f, ## a)
@@ -218,5 +217,5 @@ do {                                            			\
 #define IWL_DEBUG_FW_INFO(p, f, a...)		\
 		IWL_DEBUG(p, IWL_DL_INFO | IWL_DL_FW, f, ## a)
 #define IWL_DEBUG_PTP(p, f, a...)	IWL_DEBUG(p, IWL_DL_PTP, f, ## a)
-
+#define IWL_DEBUG_EHT(p, f, a...)	IWL_DEBUG(p, IWL_DL_EHT, f, ## a)
 #endif

From f8e02ca6497cfa8946b4599d75bb7cab04be2404 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 12 Feb 2025 07:43:27 +0200
Subject: [PATCH 1215/2753] wifi: iwlwifi: add support for external 32 KHz
 clock

In case the BIOS allows it, instruct the firmware to use the external 32
KHz clock.
The op mode specific implementation (i.e. reading the BIOS table) will
come in a later patch.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.9aae3f74fee0.I25ae45ef02b9ea387b512f974c1f3e5367a537e5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/iwl-context-info-gen3.h    | 8 +++++---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.h            | 3 +++
 drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c  | 5 ++++-
 3 files changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
index cd25a1b9f2ff4..20563a32a21a8 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-context-info-gen3.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2018, 2020-2024 Intel Corporation
+ * Copyright (C) 2018, 2020-2025 Intel Corporation
  */
 #ifndef __iwl_context_info_file_gen3_h__
 #define __iwl_context_info_file_gen3_h__
@@ -80,10 +80,12 @@ enum iwl_prph_scratch_flags {
  * enum iwl_prph_scratch_ext_flags - PRPH scratch control ext flags
  * @IWL_PRPH_SCRATCH_EXT_URM_FW: switch to URM mode based on fw setting
  * @IWL_PRPH_SCRATCH_EXT_URM_PERM: switch to permanent URM mode
+ * @IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID: use external 32 KHz clock
  */
 enum iwl_prph_scratch_ext_flags {
-	IWL_PRPH_SCRATCH_EXT_URM_FW	= BIT(4),
-	IWL_PRPH_SCRATCH_EXT_URM_PERM	= BIT(5),
+	IWL_PRPH_SCRATCH_EXT_URM_FW		= BIT(4),
+	IWL_PRPH_SCRATCH_EXT_URM_PERM		= BIT(5),
+	IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID	= BIT(8),
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
index 021691513a576..25fb4c50e38b1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
@@ -888,6 +888,7 @@ struct iwl_txq {
  * @trans_specific: data for the specific transport this is allocated for/with
  * @dsbr_urm_fw_dependent: switch to URM based on fw settings
  * @dsbr_urm_permanent: switch to URM permanently
+ * @ext_32khz_clock_valid: if true, the external 32 KHz clock can be used
  */
 struct iwl_trans {
 	bool csme_own;
@@ -916,6 +917,8 @@ struct iwl_trans {
 	u8 dsbr_urm_fw_dependent:1,
 	   dsbr_urm_permanent:1;
 
+	bool ext_32khz_clock_valid;
+
 	u8 rx_mpdu_cmd, rx_mpdu_cmd_hdr_size;
 
 	bool pm_support;
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
index 838c426db7f05..8aa7c455bdee3 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/dmi.h>
 #include "iwl-trans.h"
@@ -137,6 +137,9 @@ int iwl_pcie_ctxt_info_gen3_init(struct iwl_trans *trans,
 	if (trans->dsbr_urm_permanent)
 		control_flags_ext |= IWL_PRPH_SCRATCH_EXT_URM_PERM;
 
+	if (trans->ext_32khz_clock_valid)
+		control_flags_ext |= IWL_PRPH_SCRATCH_EXT_32KHZ_CLK_VALID;
+
 	/* Allocate prph scratch */
 	prph_scratch = dma_alloc_coherent(trans->dev, sizeof(*prph_scratch),
 					  &trans_pcie->prph_scratch_dma_addr,

From f073cc3a66cb72cd811bd18033185fce2764e083 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 12 Feb 2025 07:43:28 +0200
Subject: [PATCH 1216/2753] wifi: iwlwifi: export iwl_get_lari_config_bitmap

This will now be called from another opmode we are writing.
iwl_fill_lari_config will only be used for the older ones.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.9bb7fbc592a6.I8850691eac7c8471257f3031e8c05905afc72f70@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/regulatory.c | 7 ++++++-
 drivers/net/wireless/intel/iwlwifi/fw/regulatory.h | 1 +
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
index 11f54339acc65..6adcfa6e214a0 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.c
@@ -474,7 +474,7 @@ bool iwl_add_mcc_to_tas_block_list(u16 *list, u8 *size, u16 mcc)
 }
 IWL_EXPORT_SYMBOL(iwl_add_mcc_to_tas_block_list);
 
-static __le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt)
+__le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt)
 {
 	int ret;
 	u32 val;
@@ -521,6 +521,7 @@ static __le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt)
 
 	return config_bitmap;
 }
+IWL_EXPORT_SYMBOL(iwl_get_lari_config_bitmap);
 
 static size_t iwl_get_lari_config_cmd_size(u8 cmd_ver)
 {
@@ -571,6 +572,10 @@ int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt,
 					   WIDE_ID(REGULATORY_AND_NVM_GROUP,
 						   LARI_CONFIG_CHANGE), 1);
 
+	if (WARN_ONCE(cmd_ver > 12,
+		      "Don't add newer versions to this function\n"))
+		return -EINVAL;
+
 	memset(cmd, 0, sizeof(*cmd));
 	*cmd_size = iwl_get_lari_config_cmd_size(cmd_ver);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
index d978a4fadfae6..53693314d5059 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/regulatory.h
@@ -215,6 +215,7 @@ int iwl_bios_get_mcc(struct iwl_fw_runtime *fwrt, char *mcc);
 int iwl_bios_get_eckv(struct iwl_fw_runtime *fwrt, u32 *ext_clk);
 int iwl_bios_get_wbem(struct iwl_fw_runtime *fwrt, u32 *value);
 
+__le32 iwl_get_lari_config_bitmap(struct iwl_fw_runtime *fwrt);
 int iwl_fill_lari_config(struct iwl_fw_runtime *fwrt,
 			 struct iwl_lari_config_change_cmd *cmd,
 			 size_t *cmd_size);

From d645fbb47dcf80d86ebe70e703277634824850ca Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Wed, 12 Feb 2025 07:43:29 +0200
Subject: [PATCH 1217/2753] wifi: iwlwifi: remember if the UATS table was read
 successfully

This will allow to read the table once, and not any time the command is
sent. The actual use of this will be in a later patch.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.61801b78a2cb.I710a766888f370a75b47116fec29d41c106b13ed@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/runtime.h | 2 ++
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c    | 3 +++
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
index 048877fa7c71a..a9e6bba2419e5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
@@ -104,6 +104,7 @@ struct iwl_txf_iter_data {
  *	the driver by calling &iwl_fw_set_current_image()
  * @dump: debug dump data
  * @uats_table: AP type table
+ * @uats_valid: is AP type table valid
  * @uefi_tables_lock_status: The status of the WIFI GUID UEFI variables lock:
  *	0: Unlocked, 1 and 2: Locked.
  *	Only read the UEFI variables if locked.
@@ -181,6 +182,7 @@ struct iwl_fw_runtime {
 	struct iwl_sar_offset_mapping_cmd sgom_table;
 	bool sgom_enabled;
 	struct iwl_mcc_allowed_ap_type_cmd uats_table;
+	bool uats_valid;
 	u8 uefi_tables_lock_status;
 };
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 434eed4130b90..78bd0eb7aa929 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -402,6 +402,9 @@ static int iwl_uefi_uats_parse(struct uefi_cnv_wlan_uats_data *uats_data,
 
 	memcpy(fwrt->uats_table.offset_map, uats_data->offset_map,
 	       sizeof(fwrt->uats_table.offset_map));
+
+	fwrt->uats_valid = true;
+
 	return 0;
 }
 

From 048a3d94b0a80b6a4daeffc182ebb5bba4b5a71e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:30 +0200
Subject: [PATCH 1218/2753] wifi: iwlwifi: remove mvm prefix from
 iwl_mvm_d3_end_notif

This is not op mode specific.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.c99748f63511.I5c8dcc46e992e76c82fdf7dbee65957cbdca1b43@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/d3.h | 2 +-
 drivers/net/wireless/intel/iwlwifi/mvm/d3.c    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
index c2362bc786b28..9c271ea67155c 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/d3.h
@@ -1006,7 +1006,7 @@ struct iwl_wowlan_wake_pkt_notif {
  * struct iwl_mvm_d3_end_notif -  d3 end notification
  * @flags: See &enum iwl_d0i3_flags
  */
-struct iwl_mvm_d3_end_notif {
+struct iwl_d3_end_notif {
 	__le32 flags;
 } __packed;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
index 129b6bdf9ef90..632f1a26672cc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/d3.c
@@ -3376,7 +3376,7 @@ static bool iwl_mvm_wait_d3_notif(struct iwl_notif_wait_data *notif_wait,
 		break;
 	}
 	case WIDE_ID(PROT_OFFLOAD_GROUP, D3_END_NOTIFICATION): {
-		struct iwl_mvm_d3_end_notif *notif = (void *)pkt->data;
+		struct iwl_d3_end_notif *notif = (void *)pkt->data;
 
 		d3_data->d3_end_flags = __le32_to_cpu(notif->flags);
 		d3_data->notif_received |= IWL_D3_NOTIF_D3_END_NOTIF;

From 26fef6d386a0c6c0e1c848755687aa9c753bf22c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 12 Feb 2025 07:43:31 +0200
Subject: [PATCH 1219/2753] wifi: iwlwifi: add OMI bandwidth reduction APIs

This adds the API definitions needed for OMI bandwidth reduction.
Will be used in a later patches.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.4d34e8f5a3df.Idd6185cdb8d8a133f92032db9278c1510961cbdc@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/datapath.h  | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
index 34a562d6c2085..c139b965980d5 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/datapath.h
@@ -90,6 +90,12 @@ enum iwl_data_path_subcmd_ids {
 	 */
 	SEC_KEY_CMD = 0x18,
 
+	/**
+	 * @OMI_SEND_STATUS_NOTIF: notification after OMI was sent
+	 *	uses &struct iwl_omi_send_status_notif
+	 */
+	OMI_SEND_STATUS_NOTIF = 0xF2,
+
 	/**
 	 * @ESR_MODE_NOTIF: notification to recommend/force a wanted esr mode,
 	 *	uses &struct iwl_esr_mode_notif
@@ -688,4 +694,13 @@ struct iwl_sec_key_cmd {
 	} __packed u; /* SEC_KEY_OPERATION_API_U_VER_1 */
 } __packed; /* SEC_KEY_CMD_API_S_VER_1 */
 
+/**
+ * struct iwl_omi_send_status_notif - OMI status notification
+ * @success: indicates that the OMI was sent successfully
+ *	(currently always set)
+ */
+struct iwl_omi_send_status_notif {
+	__le32 success;
+} __packed; /* OMI_SEND_STATUS_NTFY_API_S_VER_1 */
+
 #endif /* __iwl_fw_api_datapath_h__ */

From 5098c09a174c2e769bd016f989f6010c11fdef8c Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:32 +0200
Subject: [PATCH 1220/2753] wifi: iwlwifi: add IWL_MAX_NUM_IGTKS macro

This macro represents the number of IGTKS the FW can support.
Will be used in a later patch.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.a8e3c7461f13.If63cbc73eaf328b2c1d7c8e57627eb93c35b0c70@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/sta.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
index d7f8a276b6833..ecbcd5084cd8d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/sta.h
@@ -191,6 +191,7 @@ enum iwl_sta_sleep_flag {
 #define STA_KEY_IDX_INVALID (0xff)
 #define STA_KEY_MAX_DATA_KEY_NUM (4)
 #define IWL_MAX_GLOBAL_KEYS (4)
+#define IWL_MAX_NUM_IGTKS 2
 #define STA_KEY_LEN_WEP40 (5)
 #define STA_KEY_LEN_WEP104 (13)
 

From 95da92e7c6ffd63aa0c30d20963793dae4ae94ef Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Wed, 12 Feb 2025 07:43:33 +0200
Subject: [PATCH 1221/2753] wifi: iwlwifi: add Debug Host Command APIs

Add the defintition of those APIs, those will be used in a later patch.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250212073923.d842253ee55d.I2e8d65f22d5acde70ed6be16f913160a93d06852@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/fw/api/commands.h  |   5 +
 .../net/wireless/intel/iwlwifi/fw/api/dhc.h   | 129 ++++++++++++++++++
 .../net/wireless/intel/iwlwifi/fw/api/rs.h    |  52 +++++++
 3 files changed, 186 insertions(+)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
index 4b450c722a9ce..d43adb6f92200 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/commands.h
@@ -506,6 +506,11 @@ enum iwl_legacy_cmds {
 	 */
 	DTS_MEASUREMENT_NOTIFICATION = 0xdd,
 
+	/**
+	 * @DEBUG_HOST_COMMAND: &struct iwl_dhc_cmd
+	 */
+	DEBUG_HOST_COMMAND = 0xf1,
+
 	/**
 	 * @LDBG_CONFIG_CMD: configure continuous trace recording
 	 */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h
new file mode 100644
index 0000000000000..dbe06f3fc6626
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h
@@ -0,0 +1,129 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#ifndef __iwl_fw_api_dhc_h__
+#define __iwl_fw_api_dhc_h__
+
+#define DHC_TABLE_MASK_POS (28)
+
+/**
+ * enum iwl_dhc_table_id - DHC table operations index
+ */
+enum iwl_dhc_table_id {
+	/**
+	 * @DHC_TABLE_INTEGRATION: select the integration table
+	 */
+	DHC_TABLE_INTEGRATION	= 2 << DHC_TABLE_MASK_POS,
+};
+
+/**
+ * enum iwl_dhc_umac_integration_table - integration operations
+ */
+enum iwl_dhc_umac_integration_table {
+	/**
+	 * @DHC_INT_UMAC_TWT_OPERATION: trigger a TWT operation
+	 */
+	DHC_INT_UMAC_TWT_OPERATION = 4,
+	/**
+	 * @DHC_INTEGRATION_TLC_DEBUG_CONFIG: TLC debug
+	 */
+	DHC_INTEGRATION_TLC_DEBUG_CONFIG = 1,
+	/**
+	 * @DHC_INTEGRATION_MAX: Maximum UMAC integration table entries
+	 */
+	DHC_INTEGRATION_MAX
+};
+
+#define DHC_TARGET_UMAC BIT(27)
+
+/**
+ * struct iwl_dhc_cmd - debug host command
+ * @length: length in DWs of the data structure that is concatenated to the end
+ *	of this struct
+ * @index_and_mask: bit 31 is 1 for data set operation else it's 0
+ *	bits 28-30 is the index of the table of the operation -
+ *	&enum iwl_dhc_table_id *
+ *	bit 27 is 0 if the cmd targeted to LMAC and 1 if targeted to UMAC,
+ *	(LMAC is 0 for backward compatibility)
+ *	bit 26 is 0 if the cmd targeted to LMAC0 and 1 if targeted to LMAC1,
+ *	relevant only if bit 27 set to 0
+ *	bits 0-25 is a specific entry index in the table specified in bits 28-30
+ *
+ * @data: the concatenated data.
+ */
+struct iwl_dhc_cmd {
+	__le32 length;
+	__le32 index_and_mask;
+	__le32 data[];
+} __packed; /* DHC_CMD_API_S */
+
+/**
+ * enum iwl_dhc_twt_operation_type - describes the TWT operation type
+ *
+ * @DHC_TWT_REQUEST: Send a Request TWT command
+ * @DHC_TWT_SUGGEST: Send a Suggest TWT command
+ * @DHC_TWT_DEMAND: Send a Demand TWT command
+ * @DHC_TWT_GROUPING: Send a Grouping TWT command
+ * @DHC_TWT_ACCEPT: Send a Accept TWT command
+ * @DHC_TWT_ALTERNATE: Send a Alternate TWT command
+ * @DHC_TWT_DICTATE: Send a Dictate TWT command
+ * @DHC_TWT_REJECT: Send a Reject TWT command
+ * @DHC_TWT_TEARDOWN: Send a TearDown TWT command
+ */
+enum iwl_dhc_twt_operation_type {
+	DHC_TWT_REQUEST,
+	DHC_TWT_SUGGEST,
+	DHC_TWT_DEMAND,
+	DHC_TWT_GROUPING,
+	DHC_TWT_ACCEPT,
+	DHC_TWT_ALTERNATE,
+	DHC_TWT_DICTATE,
+	DHC_TWT_REJECT,
+	DHC_TWT_TEARDOWN,
+}; /* DHC_TWT_OPERATION_TYPE_E */
+
+/**
+ * struct iwl_dhc_twt_operation - trigger a TWT operation
+ *
+ * @mac_id: the mac Id on which to trigger TWT operation
+ * @twt_operation: see &enum iwl_dhc_twt_operation_type
+ * @target_wake_time: when should we be on channel
+ * @interval_exp: the exponent for the interval
+ * @interval_mantissa: the mantissa for the interval
+ * @min_wake_duration: the minimum duration for the wake period
+ * @trigger: is the TWT triggered or not
+ * @flow_type: is the TWT announced or not
+ * @flow_id: the TWT flow identifier from 0 to 7
+ * @protection: is the TWT protected
+ * @ndo_paging_indicator: is ndo_paging_indicator set
+ * @responder_pm_mode: is responder_pm_mode set
+ * @negotiation_type: if the responder wants to doze outside the TWT SP
+ * @twt_request: 1 for TWT request, 0 otherwise
+ * @implicit: is TWT implicit
+ * @twt_group_assignment: the TWT group assignment
+ * @twt_channel: the TWT channel
+ * @reserved: reserved
+ */
+struct iwl_dhc_twt_operation {
+	__le32 mac_id;
+	__le32 twt_operation;
+	__le64 target_wake_time;
+	__le32 interval_exp;
+	__le32 interval_mantissa;
+	__le32 min_wake_duration;
+	u8 trigger;
+	u8 flow_type;
+	u8 flow_id;
+	u8 protection;
+	u8 ndo_paging_indicator;
+	u8 responder_pm_mode;
+	u8 negotiation_type;
+	u8 twt_request;
+	u8 implicit;
+	u8 twt_group_assignment;
+	u8 twt_channel;
+	u8 reserved;
+}; /* DHC_TWT_OPERATION_API_S */
+
+#endif /* __iwl_fw_api_dhc_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
index 1a60f0cdf9728..c2f806cbab59d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/rs.h
@@ -226,6 +226,58 @@ struct iwl_tlc_update_notif {
 	__le32 amsdu_enabled;
 } __packed; /* TLC_MNG_UPDATE_NTFY_API_S_VER_2 */
 
+/**
+ * enum iwl_tlc_debug_types - debug options
+ */
+enum iwl_tlc_debug_types {
+	/**
+	 *  @IWL_TLC_DEBUG_FIXED_RATE: set fixed rate for rate scaling
+	 */
+	IWL_TLC_DEBUG_FIXED_RATE,
+	/**
+	 * @IWL_TLC_DEBUG_AGG_DURATION_LIM: time limit for a BA
+	 * session, in usec
+	 */
+	IWL_TLC_DEBUG_AGG_DURATION_LIM,
+	/**
+	 * @IWL_TLC_DEBUG_AGG_FRAME_CNT_LIM: set max number of frames
+	 * in an aggregation
+	 */
+	IWL_TLC_DEBUG_AGG_FRAME_CNT_LIM,
+	/**
+	 * @IWL_TLC_DEBUG_TPC_ENABLED: enable or disable tpc
+	 */
+	IWL_TLC_DEBUG_TPC_ENABLED,
+	/**
+	 * @IWL_TLC_DEBUG_TPC_STATS: get number of frames Tx'ed in each
+	 * tpc step
+	 */
+	IWL_TLC_DEBUG_TPC_STATS,
+	/**
+	 * @IWL_TLC_DEBUG_RTS_DISABLE: disable RTS (bool true/false).
+	 */
+	IWL_TLC_DEBUG_RTS_DISABLE,
+	/**
+	 * @IWL_TLC_DEBUG_PARTIAL_FIXED_RATE: set partial fixed rate to fw
+	 */
+	IWL_TLC_DEBUG_PARTIAL_FIXED_RATE,
+}; /* TLC_MNG_DEBUG_TYPES_API_E */
+
+#define MAX_DATA_IN_DHC_TLC_CMD 10
+
+/**
+ * struct iwl_dhc_tlc_cmd - fixed debug config
+ * @sta_id: bit 0 - enable/disable, bits 1 - 7 hold station id
+ * @reserved1: reserved
+ * @type: type id of %enum iwl_tlc_debug_types
+ * @data: data to send
+ */
+struct iwl_dhc_tlc_cmd {
+	u8 sta_id;
+	u8 reserved1[3];
+	__le32 type;
+	__le32 data[MAX_DATA_IN_DHC_TLC_CMD];
+} __packed; /* TLC_MNG_DEBUG_CMD_S */
 
 #define IWL_MAX_MCS_DISPLAY_SIZE        12
 

From 27d38bdfd416f4db70e09c3bef3b030c86fd235a Mon Sep 17 00:00:00 2001
From: Ramasamy Kaliappan <quic_rkaliapp@quicinc.com>
Date: Fri, 7 Feb 2025 11:30:05 +0530
Subject: [PATCH 1222/2753] wifi: ath12k: Improve BSS discovery with hidden
 SSID in 6 GHz band

Currently, sometimes, the station is unable to identify the configured
AP SSID in its scan results when the AP is not broadcasting its name
publicly and has a hidden SSID.

Currently, channel dwell time for an ath12k station is 30 ms. Sometimes,
station can send broadcast probe request to AP close to the end of dwell
time. In some of these cases, before AP sends a response to the received
probe request, the dwell time on the station side would come to an end.
So, the station will move to scan next channel and will not be able to
acknowledge the unicast probe response.

Resolve this issue by increasing station's channel dwell time to 70 ms,
so that the it remains on the same channel for a longer period. This
would increase the station's chance of receiving probe response from the
AP. The station will then send a response acknowledgment back to the AP,
thus leading to successful scan and BSS discovery.

With an increased dwell time, scan would take longer than it takes now.
But, this fix is an improvement for hidden SSID scan issue.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.4.1-00199-QCAHKSWPL_SILICONZ-1

Signed-off-by: Ramasamy Kaliappan <quic_rkaliapp@quicinc.com>
Signed-off-by: Roopni Devanathan <quic_rdevanat@quicinc.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250207060005.153835-1-quic_rdevanat@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/wmi.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
index 96c473c4adc65..0c3cd65f96929 100644
--- a/drivers/net/wireless/ath/ath12k/wmi.c
+++ b/drivers/net/wireless/ath/ath12k/wmi.c
@@ -2433,8 +2433,8 @@ void ath12k_wmi_start_scan_init(struct ath12k *ar,
 	arg->dwell_time_active = 50;
 	arg->dwell_time_active_2g = 0;
 	arg->dwell_time_passive = 150;
-	arg->dwell_time_active_6g = 40;
-	arg->dwell_time_passive_6g = 30;
+	arg->dwell_time_active_6g = 70;
+	arg->dwell_time_passive_6g = 70;
 	arg->min_rest_time = 50;
 	arg->max_rest_time = 500;
 	arg->repeat_probe_time = 0;

From 01f1d77a2630e774ce33233c4e6723bca3ae9daa Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Tue, 14 Jan 2025 10:57:25 +0100
Subject: [PATCH 1223/2753] drm/nouveau: Do not override forced connector
 status

Keep user-forced connector status even if it cannot be programmed. Same
behavior as for the rest of the drivers.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Lyude Paul <lyude@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250114100214.195386-1-tzimmermann@suse.de
---
 drivers/gpu/drm/nouveau/nouveau_connector.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_connector.c b/drivers/gpu/drm/nouveau/nouveau_connector.c
index 8d5c9c74cbb90..eac0d1d2dbda2 100644
--- a/drivers/gpu/drm/nouveau/nouveau_connector.c
+++ b/drivers/gpu/drm/nouveau/nouveau_connector.c
@@ -775,7 +775,6 @@ nouveau_connector_force(struct drm_connector *connector)
 	if (!nv_encoder) {
 		NV_ERROR(drm, "can't find encoder to force %s on!\n",
 			 connector->name);
-		connector->status = connector_status_disconnected;
 		return;
 	}
 

From 75f1f311d883dfaffb98be3c1da208d6ed5d4df9 Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 26 Feb 2025 13:38:19 -0600
Subject: [PATCH 1224/2753] Revert "of: reserved-memory: Fix using wrong number
 of cells to get property 'alignment'"

This reverts commit 267b21d0bef8e67dbe6c591c9991444e58237ec9.

Turns out some DTs do depend on this behavior. Specifically, a
downstream Pixel 6 DT. Revert the change at least until we can decide if
the DT spec can be changed instead.

Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
 drivers/of/of_reserved_mem.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c
index 75e819f66a561..ee2e31522d7ef 100644
--- a/drivers/of/of_reserved_mem.c
+++ b/drivers/of/of_reserved_mem.c
@@ -415,12 +415,12 @@ static int __init __reserved_mem_alloc_size(unsigned long node, const char *unam
 
 	prop = of_get_flat_dt_prop(node, "alignment", &len);
 	if (prop) {
-		if (len != dt_root_size_cells * sizeof(__be32)) {
+		if (len != dt_root_addr_cells * sizeof(__be32)) {
 			pr_err("invalid alignment property in '%s' node.\n",
 				uname);
 			return -EINVAL;
 		}
-		align = dt_mem_next_cell(dt_root_size_cells, &prop);
+		align = dt_mem_next_cell(dt_root_addr_cells, &prop);
 	}
 
 	nomap = of_get_flat_dt_prop(node, "no-map", NULL) != NULL;

From dd1998e243f5fa25d348a384ba0b6c84d980f2b2 Mon Sep 17 00:00:00 2001
From: Tyrone Ting <kfting@nuvoton.com>
Date: Thu, 20 Feb 2025 12:00:29 +0800
Subject: [PATCH 1225/2753] i2c: npcm: disable interrupt enable bit before
 devm_request_irq

The customer reports that there is a soft lockup issue related to
the i2c driver. After checking, the i2c module was doing a tx transfer
and the bmc machine reboots in the middle of the i2c transaction, the i2c
module keeps the status without being reset.

Due to such an i2c module status, the i2c irq handler keeps getting
triggered since the i2c irq handler is registered in the kernel booting
process after the bmc machine is doing a warm rebooting.
The continuous triggering is stopped by the soft lockup watchdog timer.

Disable the interrupt enable bit in the i2c module before calling
devm_request_irq to fix this issue since the i2c relative status bit
is read-only.

Here is the soft lockup log.
[   28.176395] watchdog: BUG: soft lockup - CPU#0 stuck for 26s! [swapper/0:1]
[   28.183351] Modules linked in:
[   28.186407] CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.15.120-yocto-s-dirty-bbebc78 #1
[   28.201174] pstate: 40000005 (nZcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   28.208128] pc : __do_softirq+0xb0/0x368
[   28.212055] lr : __do_softirq+0x70/0x368
[   28.215972] sp : ffffff8035ebca00
[   28.219278] x29: ffffff8035ebca00 x28: 0000000000000002 x27: ffffff80071a3780
[   28.226412] x26: ffffffc008bdc000 x25: ffffffc008bcc640 x24: ffffffc008be50c0
[   28.233546] x23: ffffffc00800200c x22: 0000000000000000 x21: 000000000000001b
[   28.240679] x20: 0000000000000000 x19: ffffff80001c3200 x18: ffffffffffffffff
[   28.247812] x17: ffffffc02d2e0000 x16: ffffff8035eb8b40 x15: 00001e8480000000
[   28.254945] x14: 02c3647e37dbfcb6 x13: 02c364f2ab14200c x12: 0000000002c364f2
[   28.262078] x11: 00000000fa83b2da x10: 000000000000b67e x9 : ffffffc008010250
[   28.269211] x8 : 000000009d983d00 x7 : 7fffffffffffffff x6 : 0000036d74732434
[   28.276344] x5 : 00ffffffffffffff x4 : 0000000000000015 x3 : 0000000000000198
[   28.283476] x2 : ffffffc02d2e0000 x1 : 00000000000000e0 x0 : ffffffc008bdcb40
[   28.290611] Call trace:
[   28.293052]  __do_softirq+0xb0/0x368
[   28.296625]  __irq_exit_rcu+0xe0/0x100
[   28.300374]  irq_exit+0x14/0x20
[   28.303513]  handle_domain_irq+0x68/0x90
[   28.307440]  gic_handle_irq+0x78/0xb0
[   28.311098]  call_on_irq_stack+0x20/0x38
[   28.315019]  do_interrupt_handler+0x54/0x5c
[   28.319199]  el1_interrupt+0x2c/0x4c
[   28.322777]  el1h_64_irq_handler+0x14/0x20
[   28.326872]  el1h_64_irq+0x74/0x78
[   28.330269]  __setup_irq+0x454/0x780
[   28.333841]  request_threaded_irq+0xd0/0x1b4
[   28.338107]  devm_request_threaded_irq+0x84/0x100
[   28.342809]  npcm_i2c_probe_bus+0x188/0x3d0
[   28.346990]  platform_probe+0x6c/0xc4
[   28.350653]  really_probe+0xcc/0x45c
[   28.354227]  __driver_probe_device+0x8c/0x160
[   28.358578]  driver_probe_device+0x44/0xe0
[   28.362670]  __driver_attach+0x124/0x1d0
[   28.366589]  bus_for_each_dev+0x7c/0xe0
[   28.370426]  driver_attach+0x28/0x30
[   28.373997]  bus_add_driver+0x124/0x240
[   28.377830]  driver_register+0x7c/0x124
[   28.381662]  __platform_driver_register+0x2c/0x34
[   28.386362]  npcm_i2c_init+0x3c/0x5c
[   28.389937]  do_one_initcall+0x74/0x230
[   28.393768]  kernel_init_freeable+0x24c/0x2b4
[   28.398126]  kernel_init+0x28/0x130
[   28.401614]  ret_from_fork+0x10/0x20
[   28.405189] Kernel panic - not syncing: softlockup: hung tasks
[   28.411011] SMP: stopping secondary CPUs
[   28.414933] Kernel Offset: disabled
[   28.418412] CPU features: 0x00000000,00000802
[   28.427644] Rebooting in 20 seconds..

Fixes: 56a1485b102e ("i2c: npcm7xx: Add Nuvoton NPCM I2C controller driver")
Signed-off-by: Tyrone Ting <kfting@nuvoton.com>
Cc: <stable@vger.kernel.org> # v5.8+
Reviewed-by: Tali Perry <tali.perry1@gmail.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250220040029.27596-2-kfting@nuvoton.com
---
 drivers/i2c/busses/i2c-npcm7xx.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/i2c/busses/i2c-npcm7xx.c b/drivers/i2c/busses/i2c-npcm7xx.c
index 3ca08b8ef8af3..de713b5747fe5 100644
--- a/drivers/i2c/busses/i2c-npcm7xx.c
+++ b/drivers/i2c/busses/i2c-npcm7xx.c
@@ -2554,6 +2554,13 @@ static int npcm_i2c_probe_bus(struct platform_device *pdev)
 	if (irq < 0)
 		return irq;
 
+	/*
+	 * Disable the interrupt to avoid the interrupt handler being triggered
+	 * incorrectly by the asynchronous interrupt status since the machine
+	 * might do a warm reset during the last smbus/i2c transfer session.
+	 */
+	npcm_i2c_int_enable(bus, false);
+
 	ret = devm_request_irq(bus->dev, irq, npcm_i2c_bus_irq, 0,
 			       dev_name(bus->dev), bus);
 	if (ret)

From 71c49ee9bb41e1709abac7e2eb05f9193222e580 Mon Sep 17 00:00:00 2001
From: Binbin Zhou <zhoubinbin@loongson.cn>
Date: Thu, 20 Feb 2025 20:56:12 +0800
Subject: [PATCH 1226/2753] i2c: ls2x: Fix frequency division register access

According to the chip manual, the I2C register access type of
Loongson-2K2000/LS7A is "B", so we can only access registers in byte
form (readb()/writeb()).

Although Loongson-2K0500/Loongson-2K1000 do not have similar
constraints, register accesses in byte form also behave correctly.

Also, in hardware, the frequency division registers are defined as two
separate registers (high 8-bit and low 8-bit), so we just access them
directly as bytes.

Fixes: 015e61f0bffd ("i2c: ls2x: Add driver for Loongson-2K/LS7A I2C controller")
Co-developed-by: Hongliang Wang <wanghongliang@loongson.cn>
Signed-off-by: Hongliang Wang <wanghongliang@loongson.cn>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
Cc: stable@vger.kernel.org # v6.3+
Reviewed-by: Andy Shevchenko <andy@kernel.org>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250220125612.1910990-1-zhoubinbin@loongson.cn
---
 drivers/i2c/busses/i2c-ls2x.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/i2c/busses/i2c-ls2x.c b/drivers/i2c/busses/i2c-ls2x.c
index 8821cac3897b6..b475dd27b7af9 100644
--- a/drivers/i2c/busses/i2c-ls2x.c
+++ b/drivers/i2c/busses/i2c-ls2x.c
@@ -10,6 +10,7 @@
  * Rewritten for mainline by Binbin Zhou <zhoubinbin@loongson.cn>
  */
 
+#include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/completion.h>
 #include <linux/device.h>
@@ -26,7 +27,8 @@
 #include <linux/units.h>
 
 /* I2C Registers */
-#define I2C_LS2X_PRER		0x0 /* Freq Division Register(16 bits) */
+#define I2C_LS2X_PRER_LO	0x0 /* Freq Division Low Byte Register */
+#define I2C_LS2X_PRER_HI	0x1 /* Freq Division High Byte Register */
 #define I2C_LS2X_CTR		0x2 /* Control Register */
 #define I2C_LS2X_TXR		0x3 /* Transport Data Register */
 #define I2C_LS2X_RXR		0x3 /* Receive Data Register */
@@ -93,6 +95,7 @@ static irqreturn_t ls2x_i2c_isr(int this_irq, void *dev_id)
  */
 static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 {
+	u16 val;
 	struct i2c_timings *t = &priv->i2c_t;
 	struct device *dev = priv->adapter.dev.parent;
 	u32 acpi_speed = i2c_acpi_find_bus_speed(dev);
@@ -104,9 +107,14 @@ static void ls2x_i2c_adjust_bus_speed(struct ls2x_i2c_priv *priv)
 	else
 		t->bus_freq_hz = LS2X_I2C_FREQ_STD;
 
-	/* Calculate and set i2c frequency. */
-	writew(LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1,
-	       priv->base + I2C_LS2X_PRER);
+	/*
+	 * According to the chip manual, we can only access the registers as bytes,
+	 * otherwise the high bits will be truncated.
+	 * So set the I2C frequency with a sequential writeb() instead of writew().
+	 */
+	val = LS2X_I2C_PCLK_FREQ / (5 * t->bus_freq_hz) - 1;
+	writeb(FIELD_GET(GENMASK(7, 0), val), priv->base + I2C_LS2X_PRER_LO);
+	writeb(FIELD_GET(GENMASK(15, 8), val), priv->base + I2C_LS2X_PRER_HI);
 }
 
 static void ls2x_i2c_init(struct ls2x_i2c_priv *priv)

From 9f3c507cb44498067c980674139bcad56e582ee6 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 19 Feb 2025 19:27:47 +0530
Subject: [PATCH 1227/2753] i2c: amd-asf: Fix EOI register write to enable
 successive interrupts

The commit b1f8921dfbaa
("i2c: amd-asf: Clear remote IRR bit to get successive interrupt")
introduced a method to enable successive interrupts but inadvertently
omitted the necessary write to the EOI register, resulting in a failure to
receive successive interrupts.

Fix this by adding the required write to the EOI register.

Fixes: b1f8921dfbaa ("i2c: amd-asf: Clear remote IRR bit to get successive interrupt")
Cc: stable@vger.kernel.org # v6.13+
Co-developed-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Sanket Goswami <Sanket.Goswami@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Fixes: 9b25419ad397 ("i2c: amd-asf: Add routine to handle the ASF slave process")
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250219135747.3251182-1-Shyam-sundar.S-k@amd.com
---
 drivers/i2c/busses/i2c-amd-asf-plat.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/i2c/busses/i2c-amd-asf-plat.c b/drivers/i2c/busses/i2c-amd-asf-plat.c
index 7512614bf4b73..93ebec162c6dd 100644
--- a/drivers/i2c/busses/i2c-amd-asf-plat.c
+++ b/drivers/i2c/busses/i2c-amd-asf-plat.c
@@ -293,6 +293,7 @@ static irqreturn_t amd_asf_irq_handler(int irq, void *ptr)
 		amd_asf_update_ioport_target(piix4_smba, ASF_SLV_INTR, SMBHSTSTS, true);
 	}
 
+	iowrite32(irq, dev->eoi_base);
 	return IRQ_HANDLED;
 }
 

From b8501febdc513541afc5663d063bfac7ea575b71 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 29 Jan 2025 16:45:19 +0100
Subject: [PATCH 1228/2753] clk: qcom: dispcc-sm8750: Drop incorrect
 CLK_SET_RATE_PARENT on byte intf parent

The parent of disp_cc_mdss_byte0_intf_clk clock should not propagate up
the rates, because this messes up entire clock hierarchy when setting
clock rates in MSM DSI driver.

The dsi_link_clk_set_rate_6g() first sets entire clock hierarchy rates
via dev_pm_opp_set_rate() on byte clock and then sets individual clock
rates, like pixel and byte_intf clocks, to proper frequencies.  Having
CLK_SET_RATE_PARENT caused that entire tree was re-calced and the byte
clock received halved frequency.  Drop CLK_SET_RATE_PARENT to fix this
and align with SM8550 and SM8650.

Fixes: f1080d8dab0f ("clk: qcom: dispcc-sm8750: Add SM8750 Display clock controller")
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250129154519.209791-1-krzysztof.kozlowski@linaro.org
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Reviewed-by: Abhinav Kumar <quic_abhinavk@quicinc.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/qcom/dispcc-sm8750.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/clk/qcom/dispcc-sm8750.c b/drivers/clk/qcom/dispcc-sm8750.c
index 0358dff91da5d..e9bca179998b9 100644
--- a/drivers/clk/qcom/dispcc-sm8750.c
+++ b/drivers/clk/qcom/dispcc-sm8750.c
@@ -827,7 +827,6 @@ static struct clk_regmap_div disp_cc_mdss_byte0_div_clk_src = {
 			&disp_cc_mdss_byte0_clk_src.clkr.hw,
 		},
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
 		.ops = &clk_regmap_div_ops,
 	},
 };
@@ -842,7 +841,6 @@ static struct clk_regmap_div disp_cc_mdss_byte1_div_clk_src = {
 			&disp_cc_mdss_byte1_clk_src.clkr.hw,
 		},
 		.num_parents = 1,
-		.flags = CLK_SET_RATE_PARENT,
 		.ops = &clk_regmap_div_ops,
 	},
 };

From ac965d7d88fc36fb42e3d50225c0a44dd8326da4 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:18:46 +0900
Subject: [PATCH 1229/2753] tracing: tprobe-events: Fix a memory leak when
 tprobe with $retval

Fix a memory leak when a tprobe is defined with $retval. This
combination is not allowed, but the parse_symbol_and_return() does
not free the *symbol which should not be used if it returns the error.
Thus, it leaks the *symbol memory in that error path.

Link: https://lore.kernel.org/all/174055072650.4079315.3063014346697447838.stgit@mhiramat.tok.corp.google.com/

Fixes: ce51e6153f77 ("tracing: fprobe-event: Fix to check tracepoint event and return")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace_fprobe.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index b8f3c4ba309b6..8826f44f69a44 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1056,6 +1056,8 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 			if (is_tracepoint) {
 				trace_probe_log_set_index(i);
 				trace_probe_log_err(tmp - argv[i], RETVAL_ON_PROBE);
+				kfree(*symbol);
+				*symbol = NULL;
 				return -EINVAL;
 			}
 			*is_return = true;

From d0453655b6ddc685a4837f3cc0776ae8eef62d01 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:18:54 +0900
Subject: [PATCH 1230/2753] tracing: tprobe-events: Reject invalid tracepoint
 name

Commit 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on
future loaded modules") allows user to set a tprobe on non-exist
tracepoint but it does not check the tracepoint name is acceptable.
So it leads tprobe has a wrong character for events (e.g. with
subsystem prefix). In this case, the event is not shown in the
events directory.

Reject such invalid tracepoint name.

The tracepoint name must consist of alphabet or digit or '_'.

Link: https://lore.kernel.org/all/174055073461.4079315.15875502830565214255.stgit@mhiramat.tok.corp.google.com/

Fixes: 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on future loaded modules")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace_fprobe.c | 13 +++++++++++++
 kernel/trace/trace_probe.h  |  1 +
 2 files changed, 14 insertions(+)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 8826f44f69a44..85f037dc14623 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1049,6 +1049,19 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 	if (*is_return)
 		return 0;
 
+	if (is_tracepoint) {
+		tmp = *symbol;
+		while (*tmp && (isalnum(*tmp) || *tmp == '_'))
+			tmp++;
+		if (*tmp) {
+			/* find a wrong character. */
+			trace_probe_log_err(tmp - *symbol, BAD_TP_NAME);
+			kfree(*symbol);
+			*symbol = NULL;
+			return -EINVAL;
+		}
+	}
+
 	/* If there is $retval, this should be a return fprobe. */
 	for (i = 2; i < argc; i++) {
 		tmp = strstr(argv[i], "$retval");
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 5803e6a415705..fba3ede870541 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -481,6 +481,7 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(NON_UNIQ_SYMBOL,	"The symbol is not unique"),		\
 	C(BAD_RETPROBE,		"Retprobe address must be an function entry"), \
 	C(NO_TRACEPOINT,	"Tracepoint is not found"),		\
+	C(BAD_TP_NAME,		"Invalid character in tracepoint name"),\
 	C(BAD_ADDR_SUFFIX,	"Invalid probed address suffix"), \
 	C(NO_GROUP_NAME,	"Group name is not specified"),		\
 	C(GROUP_TOO_LONG,	"Group name is too long"),		\

From db5e228611b118cf7b1f8084063feda5c037f4a7 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:19:02 +0900
Subject: [PATCH 1231/2753] tracing: fprobe-events: Log error for exceeding the
 number of entry args

Add error message when the number of entry argument exceeds the
maximum size of entry data.
This is currently checked when registering fprobe, but in this case
no error message is shown in the error_log file.

Link: https://lore.kernel.org/all/174055074269.4079315.17809232650360988538.stgit@mhiramat.tok.corp.google.com/

Fixes: 25f00e40ce79 ("tracing/probes: Support $argN in return probe (kprobe and fprobe)")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_fprobe.c | 5 +++++
 kernel/trace/trace_probe.h  | 3 ++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 85f037dc14623..e27305d31fc57 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1230,6 +1230,11 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	if (is_return && tf->tp.entry_arg) {
 		tf->fp.entry_handler = trace_fprobe_entry_handler;
 		tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp);
+		if (ALIGN(tf->fp.entry_data_size, sizeof(long)) > MAX_FPROBE_DATA_SIZE) {
+			trace_probe_log_set_index(2);
+			trace_probe_log_err(0, TOO_MANY_EARGS);
+			return -E2BIG;
+		}
 	}
 
 	ret = traceprobe_set_print_fmt(&tf->tp,
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index fba3ede870541..c47ca002347a7 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -545,7 +545,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(NO_BTF_FIELD,		"This field is not found."),	\
 	C(BAD_BTF_TID,		"Failed to get BTF type info."),\
 	C(BAD_TYPE4STR,		"This type does not fit for string."),\
-	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),
+	C(NEED_STRING_TYPE,	"$comm and immediate-string only accepts string type"),\
+	C(TOO_MANY_EARGS,	"Too many entry arguments specified"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a

From 2b1283e1ea9b5e0b06f075f79391a51d9f70749b Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Tue, 25 Feb 2025 11:46:36 +0000
Subject: [PATCH 1232/2753] arm64/mm: Fix Boot panic on Ampere Altra

When the range of present physical memory is sufficiently small enough
and the reserved address space for the linear map is sufficiently large
enough, The linear map base address is randomized in
arm64_memblock_init().

Prior to commit 62cffa496aac ("arm64/mm: Override PARange for !LPA2 and
use it consistently"), we decided if the sizes were suitable with the
help of the raw mmfr0.parange. But the commit changed this to use the
sanitized version instead. But the function runs before the register has
been sanitized so this returns 0, interpreted as a parange of 32 bits.
Some fun wrapping occurs and the logic concludes that there is enough
room to randomize the linear map base address, when really there isn't.
So the top of the linear map ends up outside the reserved address space.

Since the PA range cannot be overridden in the first place, restore the
mmfr0 reading logic to its state prior to 62cffa496aac, where the raw
register value is used.

Reported-by: Luiz Capitulino <luizcap@redhat.com>
Suggested-by: Ard Biesheuvel <ardb@kernel.org>
Closes: https://lore.kernel.org/all/a3d9acbe-07c2-43b6-9ba9-a7585f770e83@redhat.com/
Fixes: 62cffa496aac ("arm64/mm: Override PARange for !LPA2 and use it consistently")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250225114638.2038006-1-ryan.roberts@arm.com
Cc: stable@vger.kernel.org
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/init.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 9c0b8d9558fc4..ccdef53872a0b 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -279,12 +279,7 @@ void __init arm64_memblock_init(void)
 
 	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE)) {
 		extern u16 memstart_offset_seed;
-
-		/*
-		 * Use the sanitised version of id_aa64mmfr0_el1 so that linear
-		 * map randomization can be enabled by shrinking the IPA space.
-		 */
-		u64 mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1);
+		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
 					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -

From 4804f3ac2649475509b1836a4d252c04de143249 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 26 Feb 2025 19:30:38 -0500
Subject: [PATCH 1233/2753] bcachefs: Revert directory i_size

This turned out to have several bugs, which were missed because the fsck
code wasn't properly reporting errors - whoops.

Kicking it out for now, hopefully it can make 6.15.

Cc: Hongbo Li <lihongbo22@huawei.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/dirent.h       |  5 -----
 fs/bcachefs/fs-common.c    | 11 -----------
 fs/bcachefs/fsck.c         | 21 ---------------------
 fs/bcachefs/sb-downgrade.c |  5 +----
 4 files changed, 1 insertion(+), 41 deletions(-)

diff --git a/fs/bcachefs/dirent.h b/fs/bcachefs/dirent.h
index a633f83c1ac78..362b3b2f2f2e3 100644
--- a/fs/bcachefs/dirent.h
+++ b/fs/bcachefs/dirent.h
@@ -31,11 +31,6 @@ static inline unsigned dirent_val_u64s(unsigned len)
 			    sizeof(u64));
 }
 
-static inline unsigned int dirent_occupied_size(const struct qstr *name)
-{
-	return (BKEY_U64s + dirent_val_u64s(name->len)) * sizeof(u64);
-}
-
 int bch2_dirent_read_target(struct btree_trans *, subvol_inum,
 			    struct bkey_s_c_dirent, subvol_inum *);
 
diff --git a/fs/bcachefs/fs-common.c b/fs/bcachefs/fs-common.c
index d70d9f634cea9..2c3d46ac70c61 100644
--- a/fs/bcachefs/fs-common.c
+++ b/fs/bcachefs/fs-common.c
@@ -152,7 +152,6 @@ int bch2_create_trans(struct btree_trans *trans,
 		if (is_subdir_for_nlink(new_inode))
 			dir_u->bi_nlink++;
 		dir_u->bi_mtime = dir_u->bi_ctime = now;
-		dir_u->bi_size += dirent_occupied_size(name);
 
 		ret = bch2_inode_write(trans, &dir_iter, dir_u);
 		if (ret)
@@ -221,7 +220,6 @@ int bch2_link_trans(struct btree_trans *trans,
 	}
 
 	dir_u->bi_mtime = dir_u->bi_ctime = now;
-	dir_u->bi_size += dirent_occupied_size(name);
 
 	dir_hash = bch2_hash_info_init(c, dir_u);
 
@@ -324,7 +322,6 @@ int bch2_unlink_trans(struct btree_trans *trans,
 
 	dir_u->bi_mtime = dir_u->bi_ctime = inode_u->bi_ctime = now;
 	dir_u->bi_nlink -= is_subdir_for_nlink(inode_u);
-	dir_u->bi_size	-= dirent_occupied_size(name);
 
 	ret =   bch2_hash_delete_at(trans, bch2_dirent_hash_desc,
 				    &dir_hash, &dirent_iter,
@@ -463,14 +460,6 @@ int bch2_rename_trans(struct btree_trans *trans,
 		goto err;
 	}
 
-	if (mode == BCH_RENAME) {
-		src_dir_u->bi_size -= dirent_occupied_size(src_name);
-		dst_dir_u->bi_size += dirent_occupied_size(dst_name);
-	}
-
-	if (mode == BCH_RENAME_OVERWRITE)
-		src_dir_u->bi_size -= dirent_occupied_size(src_name);
-
 	if (src_inode_u->bi_parent_subvol)
 		src_inode_u->bi_parent_subvol = dst_dir.subvol;
 
diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
index 9bf316e7b845d..0e85131d0af88 100644
--- a/fs/bcachefs/fsck.c
+++ b/fs/bcachefs/fsck.c
@@ -1978,31 +1978,10 @@ static int check_subdir_count_notnested(struct btree_trans *trans, struct inode_
 	return ret;
 }
 
-static int check_dir_i_size_notnested(struct btree_trans *trans, struct inode_walker *w)
-{
-	struct bch_fs *c = trans->c;
-	int ret = 0;
-
-	darray_for_each(w->inodes, i)
-		if (fsck_err_on(i->inode.bi_size != i->i_size,
-				trans, inode_dir_wrong_nlink,
-				"directory %llu:%u with wrong i_size: got %llu, should be %llu",
-				w->last_pos.inode, i->snapshot, i->inode.bi_size, i->i_size)) {
-			i->inode.bi_size = i->i_size;
-			ret = bch2_fsck_write_inode(trans, &i->inode);
-			if (ret)
-				break;
-		}
-fsck_err:
-	bch_err_fn(c, ret);
-	return ret;
-}
-
 static int check_subdir_dirents_count(struct btree_trans *trans, struct inode_walker *w)
 {
 	u32 restart_count = trans->restart_count;
 	return check_subdir_count_notnested(trans, w) ?:
-		check_dir_i_size_notnested(trans, w) ?:
 		trans_was_restarted(trans, restart_count);
 }
 
diff --git a/fs/bcachefs/sb-downgrade.c b/fs/bcachefs/sb-downgrade.c
index 35e07bc8fbd34..051214fdc7352 100644
--- a/fs/bcachefs/sb-downgrade.c
+++ b/fs/bcachefs/sb-downgrade.c
@@ -90,10 +90,7 @@
 	  BIT_ULL(BCH_RECOVERY_PASS_check_allocations),		\
 	  BCH_FSCK_ERR_accounting_mismatch,			\
 	  BCH_FSCK_ERR_accounting_key_replicas_nr_devs_0,	\
-	  BCH_FSCK_ERR_accounting_key_junk_at_end)		\
-	x(directory_size,					\
-	  BIT_ULL(BCH_RECOVERY_PASS_check_dirents),		\
-	  BCH_FSCK_ERR_directory_size_mismatch)			\
+	  BCH_FSCK_ERR_accounting_key_junk_at_end)
 
 #define DOWNGRADE_TABLE()					\
 	x(bucket_stripe_sectors,				\

From 7909d1fb90e290ffd7b8570f4e2f97fe2fb381d0 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 25 Feb 2025 22:35:28 -0500
Subject: [PATCH 1234/2753] bcachefs: Check for -BCH_ERR_open_buckets_empty in
 journal resize

This fixes occasional failures from journal resize.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 24c294d4634e0..5dabbf3c0965c 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1194,7 +1194,9 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 
 		closure_sync(&cl);
 
-		if (ret && ret != -BCH_ERR_bucket_alloc_blocked)
+		if (ret &&
+		    ret != -BCH_ERR_bucket_alloc_blocked &&
+		    ret != -BCH_ERR_open_buckets_empty)
 			break;
 	}
 

From 677bdb7346b6fd806ea45b11cbfe36de0b0cd644 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Wed, 26 Feb 2025 17:33:22 +0800
Subject: [PATCH 1235/2753] bcachefs: Fix deadlock

This fixes two deadlocks:

1.pcpu_alloc_mutex involved one as pointed by syzbot[1]
2.recursion deadlock.

The root cause is that we hold the bc lock during alloc_percpu, fix it
by following the pattern used by __btree_node_mem_alloc().

[1] https://lore.kernel.org/all/66f97d9a.050a0220.6bad9.001d.GAE@google.com/T/

Reported-by: syzbot+fe63f377148a6371a9db@syzkaller.appspotmail.com
Tested-by: syzbot+fe63f377148a6371a9db@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_cache.c     | 9 +++++----
 fs/bcachefs/btree_key_cache.c | 2 +-
 fs/bcachefs/btree_locking.c   | 5 +++--
 fs/bcachefs/btree_locking.h   | 2 +-
 fs/bcachefs/six.c             | 5 +++--
 fs/bcachefs/six.h             | 7 ++++---
 6 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/fs/bcachefs/btree_cache.c b/fs/bcachefs/btree_cache.c
index ca755e8d1a372..1ec1f90e0eb38 100644
--- a/fs/bcachefs/btree_cache.c
+++ b/fs/bcachefs/btree_cache.c
@@ -203,7 +203,7 @@ struct btree *__bch2_btree_node_mem_alloc(struct bch_fs *c)
 		return NULL;
 	}
 
-	bch2_btree_lock_init(&b->c, 0);
+	bch2_btree_lock_init(&b->c, 0, GFP_KERNEL);
 
 	__bch2_btree_node_to_freelist(bc, b);
 	return b;
@@ -795,17 +795,18 @@ struct btree *bch2_btree_node_mem_alloc(struct btree_trans *trans, bool pcpu_rea
 		}
 
 	b = __btree_node_mem_alloc(c, GFP_NOWAIT|__GFP_NOWARN);
-	if (!b) {
+	if (b) {
+		bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_NOWAIT);
+	} else {
 		mutex_unlock(&bc->lock);
 		bch2_trans_unlock(trans);
 		b = __btree_node_mem_alloc(c, GFP_KERNEL);
 		if (!b)
 			goto err;
+		bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL);
 		mutex_lock(&bc->lock);
 	}
 
-	bch2_btree_lock_init(&b->c, pcpu_read_locks ? SIX_LOCK_INIT_PCPU : 0);
-
 	BUG_ON(!six_trylock_intent(&b->c.lock));
 	BUG_ON(!six_trylock_write(&b->c.lock));
 
diff --git a/fs/bcachefs/btree_key_cache.c b/fs/bcachefs/btree_key_cache.c
index 1821f40c161a1..edce594333756 100644
--- a/fs/bcachefs/btree_key_cache.c
+++ b/fs/bcachefs/btree_key_cache.c
@@ -156,7 +156,7 @@ bkey_cached_alloc(struct btree_trans *trans, struct btree_path *path, unsigned k
 	}
 
 	if (ck) {
-		bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0);
+		bch2_btree_lock_init(&ck->c, pcpu_readers ? SIX_LOCK_INIT_PCPU : 0, GFP_KERNEL);
 		ck->c.cached = true;
 		goto lock;
 	}
diff --git a/fs/bcachefs/btree_locking.c b/fs/bcachefs/btree_locking.c
index 10b805a60f526..caef65adeae49 100644
--- a/fs/bcachefs/btree_locking.c
+++ b/fs/bcachefs/btree_locking.c
@@ -7,9 +7,10 @@
 static struct lock_class_key bch2_btree_node_lock_key;
 
 void bch2_btree_lock_init(struct btree_bkey_cached_common *b,
-			  enum six_lock_init_flags flags)
+			  enum six_lock_init_flags flags,
+			  gfp_t gfp)
 {
-	__six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags);
+	__six_lock_init(&b->lock, "b->c.lock", &bch2_btree_node_lock_key, flags, gfp);
 	lockdep_set_notrack_class(&b->lock);
 }
 
diff --git a/fs/bcachefs/btree_locking.h b/fs/bcachefs/btree_locking.h
index b54ef48eb8cc2..b33ab7af84402 100644
--- a/fs/bcachefs/btree_locking.h
+++ b/fs/bcachefs/btree_locking.h
@@ -13,7 +13,7 @@
 #include "btree_iter.h"
 #include "six.h"
 
-void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags);
+void bch2_btree_lock_init(struct btree_bkey_cached_common *, enum six_lock_init_flags, gfp_t gfp);
 
 void bch2_trans_unlock_noassert(struct btree_trans *);
 void bch2_trans_unlock_write(struct btree_trans *);
diff --git a/fs/bcachefs/six.c b/fs/bcachefs/six.c
index 7e7c66a1e1a6b..7c403427fbdb8 100644
--- a/fs/bcachefs/six.c
+++ b/fs/bcachefs/six.c
@@ -850,7 +850,8 @@ void six_lock_exit(struct six_lock *lock)
 EXPORT_SYMBOL_GPL(six_lock_exit);
 
 void __six_lock_init(struct six_lock *lock, const char *name,
-		     struct lock_class_key *key, enum six_lock_init_flags flags)
+		     struct lock_class_key *key, enum six_lock_init_flags flags,
+		     gfp_t gfp)
 {
 	atomic_set(&lock->state, 0);
 	raw_spin_lock_init(&lock->wait_lock);
@@ -873,7 +874,7 @@ void __six_lock_init(struct six_lock *lock, const char *name,
 		 * failure if they wish by checking lock->readers, but generally
 		 * will not want to treat it as an error.
 		 */
-		lock->readers = alloc_percpu(unsigned);
+		lock->readers = alloc_percpu_gfp(unsigned, gfp);
 	}
 #endif
 }
diff --git a/fs/bcachefs/six.h b/fs/bcachefs/six.h
index c142e06b7a3a7..59b851cf8bacc 100644
--- a/fs/bcachefs/six.h
+++ b/fs/bcachefs/six.h
@@ -164,18 +164,19 @@ enum six_lock_init_flags {
 };
 
 void __six_lock_init(struct six_lock *lock, const char *name,
-		     struct lock_class_key *key, enum six_lock_init_flags flags);
+		     struct lock_class_key *key, enum six_lock_init_flags flags,
+		     gfp_t gfp);
 
 /**
  * six_lock_init - initialize a six lock
  * @lock:	lock to initialize
  * @flags:	optional flags, i.e. SIX_LOCK_INIT_PCPU
  */
-#define six_lock_init(lock, flags)					\
+#define six_lock_init(lock, flags, gfp)					\
 do {									\
 	static struct lock_class_key __key;				\
 									\
-	__six_lock_init((lock), #lock, &__key, flags);			\
+	__six_lock_init((lock), #lock, &__key, flags, gfp);			\
 } while (0)
 
 /**

From eb54d2695b57426638fed0ec066ae17a18c4426c Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 26 Feb 2025 10:57:26 -0500
Subject: [PATCH 1236/2753] bcachefs: Fix truncate sometimes failing and
 returning 1

__bch_truncate_folio() may return 1 to indicate dirtyness of the folio
being truncated, needed for fpunch to get the i_size writes correct.

But truncate was forgetting to clear ret, and sometimes returning it as
an error.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/fs-io.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/fs-io.c b/fs/bcachefs/fs-io.c
index 94bf34b9b65f0..717e7b94c66f8 100644
--- a/fs/bcachefs/fs-io.c
+++ b/fs/bcachefs/fs-io.c
@@ -466,6 +466,7 @@ int bchfs_truncate(struct mnt_idmap *idmap,
 	ret = bch2_truncate_folio(inode, iattr->ia_size);
 	if (unlikely(ret < 0))
 		goto err;
+	ret = 0;
 
 	truncate_setsize(&inode->v, iattr->ia_size);
 

From 01c9c123db76357d4373b2e97b760a856d6fe822 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 25 Feb 2025 13:10:23 -0800
Subject: [PATCH 1237/2753] net: Use rtnl_net_dev_lock() in
 register_netdevice_notifier_dev_net().

Breno Leitao reported the splat below. [0]

Commit 65161fb544aa ("net: Fix dev_net(dev) race in
unregister_netdevice_notifier_dev_net().") added the
DEBUG_NET_WARN_ON_ONCE(), assuming that the netdev is not
registered before register_netdevice_notifier_dev_net().

But the assumption was simply wrong.

Let's use rtnl_net_dev_lock() in register_netdevice_notifier_dev_net().

[0]:
WARNING: CPU: 25 PID: 849 at net/core/dev.c:2150 register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 <TASK>
 ? __warn (kernel/panic.c:242 kernel/panic.c:748)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? report_bug (lib/bug.c:? lib/bug.c:219)
 ? handle_bug (arch/x86/kernel/traps.c:285)
 ? exc_invalid_op (arch/x86/kernel/traps.c:309)
 ? asm_exc_invalid_op (./arch/x86/include/asm/idtentry.h:621)
 ? register_netdevice_notifier_dev_net (net/core/dev.c:2150)
 ? register_netdevice_notifier_dev_net (./include/net/net_namespace.h:406 ./include/linux/netdevice.h:2663 net/core/dev.c:2144)
 mlx5e_mdev_notifier_event+0x9f/0xf0 mlx5_ib
 notifier_call_chain.llvm.12241336988804114627 (kernel/notifier.c:85)
 blocking_notifier_call_chain (kernel/notifier.c:380)
 mlx5_core_uplink_netdev_event_replay (drivers/net/ethernet/mellanox/mlx5/core/main.c:352)
 mlx5_ib_roce_init.llvm.12447516292400117075+0x1c6/0x550 mlx5_ib
 mlx5r_probe+0x375/0x6a0 mlx5_ib
 ? kernfs_put (./include/linux/instrumented.h:96 ./include/linux/atomic/atomic-arch-fallback.h:2278 ./include/linux/atomic/atomic-instrumented.h:1384 fs/kernfs/dir.c:557)
 ? auxiliary_match_id (drivers/base/auxiliary.c:174)
 ? mlx5r_mp_remove+0x160/0x160 mlx5_ib
 really_probe (drivers/base/dd.c:? drivers/base/dd.c:658)
 driver_probe_device (drivers/base/dd.c:830)
 __driver_attach (drivers/base/dd.c:1217)
 bus_for_each_dev (drivers/base/bus.c:369)
 ? driver_attach (drivers/base/dd.c:1157)
 bus_add_driver (drivers/base/bus.c:679)
 driver_register (drivers/base/driver.c:249)

Fixes: 7fb1073300a2 ("net: Hold rtnl_net_lock() in (un)?register_netdevice_notifier_dev_net().")
Reported-by: Breno Leitao <leitao@debian.org>
Closes: https://lore.kernel.org/netdev/20250224-noisy-cordial-roadrunner-fad40c@leitao/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Tested-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250225211023.96448-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 1b252e9459fdb..70c01bd1799e5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2141,21 +2141,15 @@ int register_netdevice_notifier_dev_net(struct net_device *dev,
 					struct notifier_block *nb,
 					struct netdev_net_notifier *nn)
 {
-	struct net *net = dev_net(dev);
 	int err;
 
-	/* rtnl_net_lock() assumes dev is not yet published by
-	 * register_netdevice().
-	 */
-	DEBUG_NET_WARN_ON_ONCE(!list_empty(&dev->dev_list));
-
-	rtnl_net_lock(net);
-	err = __register_netdevice_notifier_net(net, nb, false);
+	rtnl_net_dev_lock(dev);
+	err = __register_netdevice_notifier_net(dev_net(dev), nb, false);
 	if (!err) {
 		nn->nb = nb;
 		list_add(&nn->list, &dev->net_notifier_list);
 	}
-	rtnl_net_unlock(net);
+	rtnl_net_dev_unlock(dev);
 
 	return err;
 }

From de70981f295e7eab86325db3bf349fa676f16c42 Mon Sep 17 00:00:00 2001
From: Harshitha Ramamurthy <hramamurthy@google.com>
Date: Wed, 26 Feb 2025 00:35:26 +0000
Subject: [PATCH 1238/2753] gve: unlink old napi when stopping a queue using
 queue API

When a queue is stopped using the ndo queue API, before
destroying its page pool, the associated NAPI instance
needs to be unlinked to avoid warnings.

Handle this by calling page_pool_disable_direct_recycling()
when stopping a queue.

Cc: stable@vger.kernel.org
Fixes: ebdfae0d377b ("gve: adopt page pool for DQ RDA mode")
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250226003526.1546854-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 8ac0047f1ada1..f0674a4435670 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -109,10 +109,12 @@ static void gve_rx_reset_ring_dqo(struct gve_priv *priv, int idx)
 void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 {
 	int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
+	struct gve_rx_ring *rx = &priv->rx[idx];
 
 	if (!gve_rx_was_added_to_block(priv, idx))
 		return;
 
+	page_pool_disable_direct_recycling(rx->dqo.page_pool);
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
 	gve_rx_reset_ring_dqo(priv, idx);

From 3ba075278c11cdb19e2dbb80362042f1b0c08f74 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 25 Feb 2025 17:10:48 +0000
Subject: [PATCH 1239/2753] tcp: be less liberal in TSEcr received while in
 SYN_RECV state

Yong-Hao Zou mentioned that linux was not strict as other OS in 3WHS,
for flows using TCP TS option (RFC 7323)

As hinted by an old comment in tcp_check_req(),
we can check the TSEcr value in the incoming packet corresponds
to one of the SYNACK TSval values we have sent.

In this patch, I record the oldest and most recent values
that SYNACK packets have used.

Send a challenge ACK if we receive a TSEcr outside
of this range, and increase a new SNMP counter.

nstat -az | grep TSEcrRejected
TcpExtTSEcrRejected            0                  0.0

Due to TCP fastopen implementation, do not apply yet these checks
for fastopen flows.

v2: No longer use req->num_timeout, but treq->snt_tsval_first
    to detect when first SYNACK is prepared. This means
    we make sure to not send an initial zero TSval.
    Make sure MPTCP and TCP selftests are passing.
    Change MIB name to TcpExtTSEcrRejected

v1: https://lore.kernel.org/netdev/CADVnQykD8i4ArpSZaPKaoNxLJ2if2ts9m4As+=Jvdkrgx1qMHw@mail.gmail.com/T/

Reported-by: Yong-Hao Zou <yonghaoz1994@gmail.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250225171048.3105061-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../networking/net_cachelines/snmp.rst        |  1 +
 include/linux/tcp.h                           |  2 ++
 include/uapi/linux/snmp.h                     |  1 +
 net/ipv4/proc.c                               |  1 +
 net/ipv4/syncookies.c                         |  1 +
 net/ipv4/tcp_input.c                          |  1 +
 net/ipv4/tcp_minisocks.c                      | 26 +++++++++++--------
 net/ipv4/tcp_output.c                         |  6 +++++
 8 files changed, 28 insertions(+), 11 deletions(-)

diff --git a/Documentation/networking/net_cachelines/snmp.rst b/Documentation/networking/net_cachelines/snmp.rst
index 90ca2d92547d4..bc96efc92cf5b 100644
--- a/Documentation/networking/net_cachelines/snmp.rst
+++ b/Documentation/networking/net_cachelines/snmp.rst
@@ -36,6 +36,7 @@ unsigned_long  LINUX_MIB_TIMEWAITRECYCLED
 unsigned_long  LINUX_MIB_TIMEWAITKILLED
 unsigned_long  LINUX_MIB_PAWSACTIVEREJECTED
 unsigned_long  LINUX_MIB_PAWSESTABREJECTED
+unsigned_long  LINUX_MIB_TSECR_REJECTED
 unsigned_long  LINUX_MIB_DELAYEDACKLOST
 unsigned_long  LINUX_MIB_LISTENOVERFLOWS
 unsigned_long  LINUX_MIB_LISTENDROPS
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index f88daaa76d836..159b2c59eb627 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -160,6 +160,8 @@ struct tcp_request_sock {
 	u32				rcv_isn;
 	u32				snt_isn;
 	u32				ts_off;
+	u32				snt_tsval_first;
+	u32				snt_tsval_last;
 	u32				last_oow_ack_time; /* last SYNACK */
 	u32				rcv_nxt; /* the ack # by SYNACK. For
 						  * FastOpen it's the seq#
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index 848c7784e684c..eb9fb776fdc3e 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -186,6 +186,7 @@ enum
 	LINUX_MIB_TIMEWAITKILLED,		/* TimeWaitKilled */
 	LINUX_MIB_PAWSACTIVEREJECTED,		/* PAWSActiveRejected */
 	LINUX_MIB_PAWSESTABREJECTED,		/* PAWSEstabRejected */
+	LINUX_MIB_TSECRREJECTED,		/* TSEcrRejected */
 	LINUX_MIB_PAWS_OLD_ACK,			/* PAWSOldAck */
 	LINUX_MIB_DELAYEDACKS,			/* DelayedACKs */
 	LINUX_MIB_DELAYEDACKLOCKED,		/* DelayedACKLocked */
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index affd21a0f5728..10cbeb76c2745 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -189,6 +189,7 @@ static const struct snmp_mib snmp4_net_list[] = {
 	SNMP_MIB_ITEM("TWKilled", LINUX_MIB_TIMEWAITKILLED),
 	SNMP_MIB_ITEM("PAWSActive", LINUX_MIB_PAWSACTIVEREJECTED),
 	SNMP_MIB_ITEM("PAWSEstab", LINUX_MIB_PAWSESTABREJECTED),
+	SNMP_MIB_ITEM("TSEcrRejected", LINUX_MIB_TSECRREJECTED),
 	SNMP_MIB_ITEM("PAWSOldAck", LINUX_MIB_PAWS_OLD_ACK),
 	SNMP_MIB_ITEM("DelayedACKs", LINUX_MIB_DELAYEDACKS),
 	SNMP_MIB_ITEM("DelayedACKLocked", LINUX_MIB_DELAYEDACKLOCKED),
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 26816b876dd8b..5459a78b98095 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -279,6 +279,7 @@ static int cookie_tcp_reqsk_init(struct sock *sk, struct sk_buff *skb,
 		ireq->smc_ok = 0;
 
 	treq->snt_synack = 0;
+	treq->snt_tsval_first = 0;
 	treq->tfo_listener = false;
 	treq->txhash = net_tx_rndhash();
 	treq->rcv_isn = ntohl(th->seq) - 1;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 217a8747a79b5..d22ad553b45b1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -7081,6 +7081,7 @@ static void tcp_openreq_init(struct request_sock *req,
 	tcp_rsk(req)->rcv_isn = TCP_SKB_CB(skb)->seq;
 	tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
 	tcp_rsk(req)->snt_synack = 0;
+	tcp_rsk(req)->snt_tsval_first = 0;
 	tcp_rsk(req)->last_oow_ack_time = 0;
 	req->mss = rx_opt->mss_clamp;
 	req->ts_recent = rx_opt->saw_tstamp ? rx_opt->rcv_tsval : 0;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 1eccc518b957e..4f87406ddbcd4 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -663,6 +663,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	struct sock *child;
 	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
+	bool tsecr_reject = false;
 	bool paws_reject = false;
 	bool own_req;
 
@@ -672,8 +673,13 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 
 		if (tmp_opt.saw_tstamp) {
 			tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
-			if (tmp_opt.rcv_tsecr)
+			if (tmp_opt.rcv_tsecr) {
+				if (inet_rsk(req)->tstamp_ok && !fastopen)
+					tsecr_reject = !between(tmp_opt.rcv_tsecr,
+							tcp_rsk(req)->snt_tsval_first,
+							READ_ONCE(tcp_rsk(req)->snt_tsval_last));
 				tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off;
+			}
 			/* We do not store true stamp, but it is not required,
 			 * it can be estimated (approximately)
 			 * from another data.
@@ -788,18 +794,14 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	     tcp_rsk(req)->snt_isn + 1))
 		return sk;
 
-	/* Also, it would be not so bad idea to check rcv_tsecr, which
-	 * is essentially ACK extension and too early or too late values
-	 * should cause reset in unsynchronized states.
-	 */
-
 	/* RFC793: "first check sequence number". */
 
-	if (paws_reject || !tcp_in_window(TCP_SKB_CB(skb)->seq,
-					  TCP_SKB_CB(skb)->end_seq,
-					  tcp_rsk(req)->rcv_nxt,
-					  tcp_rsk(req)->rcv_nxt +
-					  tcp_synack_window(req))) {
+	if (paws_reject || tsecr_reject ||
+	    !tcp_in_window(TCP_SKB_CB(skb)->seq,
+			   TCP_SKB_CB(skb)->end_seq,
+			   tcp_rsk(req)->rcv_nxt,
+			   tcp_rsk(req)->rcv_nxt +
+			   tcp_synack_window(req))) {
 		/* Out of window: send ACK and drop. */
 		if (!(flg & TCP_FLAG_RST) &&
 		    !tcp_oow_rate_limited(sock_net(sk), skb,
@@ -808,6 +810,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			req->rsk_ops->send_ack(sk, skb, req);
 		if (paws_reject)
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
+		else if (tsecr_reject)
+			NET_INC_STATS(sock_net(sk), LINUX_MIB_TSECRREJECTED);
 		return NULL;
 	}
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9a3cf51eab787..0a660075add5b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -943,6 +943,12 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 		opts->options |= OPTION_TS;
 		opts->tsval = tcp_skb_timestamp_ts(tcp_rsk(req)->req_usec_ts, skb) +
 			      tcp_rsk(req)->ts_off;
+		if (!tcp_rsk(req)->snt_tsval_first) {
+			if (!opts->tsval)
+				opts->tsval = ~0U;
+			tcp_rsk(req)->snt_tsval_first = opts->tsval;
+		}
+		WRITE_ONCE(tcp_rsk(req)->snt_tsval_last, opts->tsval);
 		opts->tsecr = READ_ONCE(req->ts_recent);
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}

From 49806fe6e61b045b5be8610e08b5a3083c109aa0 Mon Sep 17 00:00:00 2001
From: Mohammad Heib <mheib@redhat.com>
Date: Tue, 25 Feb 2025 13:28:52 +0200
Subject: [PATCH 1240/2753] net: Clear old fragment checksum value in
 napi_reuse_skb

In certain cases, napi_get_frags() returns an skb that points to an old
received fragment, This skb may have its skb->ip_summed, csum, and other
fields set from previous fragment handling.

Some network drivers set skb->ip_summed to either CHECKSUM_COMPLETE or
CHECKSUM_UNNECESSARY when getting skb from napi_get_frags(), while
others only set skb->ip_summed when RX checksum offload is enabled on
the device, and do not set any value for skb->ip_summed when hardware
checksum offload is disabled, assuming that the skb->ip_summed
initiated to zero by napi_reuse_skb, ionic driver for example will
ignore/unset any value for the ip_summed filed if HW checksum offload is
disabled, and if we have a situation where the user disables the
checksum offload during a traffic that could lead to the following
errors shown in the kernel logs:
<IRQ>
dump_stack_lvl+0x34/0x48
 __skb_gro_checksum_complete+0x7e/0x90
tcp6_gro_receive+0xc6/0x190
ipv6_gro_receive+0x1ec/0x430
dev_gro_receive+0x188/0x360
? ionic_rx_clean+0x25a/0x460 [ionic]
napi_gro_frags+0x13c/0x300
? __pfx_ionic_rx_service+0x10/0x10 [ionic]
ionic_rx_service+0x67/0x80 [ionic]
ionic_cq_service+0x58/0x90 [ionic]
ionic_txrx_napi+0x64/0x1b0 [ionic]
 __napi_poll+0x27/0x170
net_rx_action+0x29c/0x370
handle_softirqs+0xce/0x270
__irq_exit_rcu+0xa3/0xc0
common_interrupt+0x80/0xa0
</IRQ>

This inconsistency sometimes leads to checksum validation issues in the
upper layers of the network stack.

To resolve this, this patch clears the skb->ip_summed value for each
reused skb in by napi_reuse_skb(), ensuring that the caller is responsible
for setting the correct checksum status. This eliminates potential
checksum validation issues caused by improper handling of
skb->ip_summed.

Fixes: 76620aafd66f ("gro: New frags interface to avoid copying shinfo")
Signed-off-by: Mohammad Heib <mheib@redhat.com>
Reviewed-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250225112852.2507709-1-mheib@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/gro.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/gro.c b/net/core/gro.c
index 78b320b631744..0ad549b07e039 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -653,6 +653,7 @@ static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 	skb->pkt_type = PACKET_HOST;
 
 	skb->encapsulation = 0;
+	skb->ip_summed = CHECKSUM_NONE;
 	skb_shinfo(skb)->gso_type = 0;
 	skb_shinfo(skb)->gso_size = 0;
 	if (unlikely(skb->slow_gro)) {

From 77e45145e3039a0fb212556ab3f8c87f54771757 Mon Sep 17 00:00:00 2001
From: Frederic Weisbecker <frederic@kernel.org>
Date: Sun, 23 Feb 2025 23:17:08 +0100
Subject: [PATCH 1241/2753] net: Handle napi_schedule() calls from
 non-interrupt

napi_schedule() is expected to be called either:

* From an interrupt, where raised softirqs are handled on IRQ exit

* From a softirq disabled section, where raised softirqs are handled on
  the next call to local_bh_enable().

* From a softirq handler, where raised softirqs are handled on the next
  round in do_softirq(), or further deferred to a dedicated kthread.

Other bare tasks context may end up ignoring the raised NET_RX vector
until the next random softirq handling opportunity, which may not
happen before a while if the CPU goes idle afterwards with the tick
stopped.

Such "misuses" have been detected on several places thanks to messages
of the kind:

	"NOHZ tick-stop error: local softirq work is pending, handler #08!!!"

For example:

       __raise_softirq_irqoff
        __napi_schedule
        rtl8152_runtime_resume.isra.0
        rtl8152_resume
        usb_resume_interface.isra.0
        usb_resume_both
        __rpm_callback
        rpm_callback
        rpm_resume
        __pm_runtime_resume
        usb_autoresume_device
        usb_remote_wakeup
        hub_event
        process_one_work
        worker_thread
        kthread
        ret_from_fork
        ret_from_fork_asm

And also:

* drivers/net/usb/r8152.c::rtl_work_func_t
* drivers/net/netdevsim/netdev.c::nsim_start_xmit

There is a long history of issues of this kind:

	019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()")
	330068589389 ("idpf: disable local BH when scheduling napi for marker packets")
	e3d5d70cb483 ("net: lan78xx: fix "softirq work is pending" error")
	e55c27ed9ccf ("mt76: mt7615: add missing bh-disable around rx napi schedule")
	c0182aa98570 ("mt76: mt7915: add missing bh-disable around tx napi enable/schedule")
	970be1dff26d ("mt76: disable BH around napi_schedule() calls")
	019edd01d174 ("ath10k: sdio: Add missing BH locking around napi_schdule()")
	30bfec4fec59 ("can: rx-offload: can_rx_offload_threaded_irq_finish(): add new  function to be called from threaded interrupt")
	e63052a5dd3c ("mlx5e: add add missing BH locking around napi_schdule()")
	83a0c6e58901 ("i40e: Invoke softirqs after napi_reschedule")
	bd4ce941c8d5 ("mlx4: Invoke softirqs after napi_reschedule")
	8cf699ec849f ("mlx4: do not call napi_schedule() without care")
	ec13ee80145c ("virtio_net: invoke softirqs after __napi_schedule")

This shows that relying on the caller to arrange a proper context for
the softirqs to be handled while calling napi_schedule() is very fragile
and error prone. Also fixing them can also prove challenging if the
caller may be called from different kinds of contexts.

Therefore fix this from napi_schedule() itself with waking up ksoftirqd
when softirqs are raised from task contexts.

Reported-by: Paul Menzel <pmenzel@molgen.mpg.de>
Reported-by: Jakub Kicinski <kuba@kernel.org>
Reported-by: Francois Romieu <romieu@fr.zoreil.com>
Closes: https://lore.kernel.org/lkml/354a2690-9bbf-4ccb-8769-fa94707a9340@molgen.mpg.de/
Cc: Breno Leitao <leitao@debian.org>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250223221708.27130-1-frederic@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 70c01bd1799e5..30da277c5a6f8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4757,7 +4757,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 	 * we have to raise NET_RX_SOFTIRQ.
 	 */
 	if (!sd->in_net_rx_action)
-		__raise_softirq_irqoff(NET_RX_SOFTIRQ);
+		raise_softirq_irqoff(NET_RX_SOFTIRQ);
 }
 
 #ifdef CONFIG_RPS

From c1d6d629ab0b3dd991c7fb04587dd2adf2c4b426 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 24 Feb 2025 21:23:58 -0500
Subject: [PATCH 1242/2753] selftests/net: prepare cmsg_ipv6.sh for ipv4

Move IPV6_TCLASS and IPV6_HOPLIMIT into loops, to be able to use them
for IP_TOS and IP_TTL in a follow-on patch.

Indentation in this file is a mix of four spaces and tabs for double
indents. To minimize code churn, maintain that pattern.

Very small diff if viewing with -w.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250225022431.2083926-2-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/cmsg_ipv6.sh | 109 ++++++++++++-----------
 1 file changed, 59 insertions(+), 50 deletions(-)

diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ipv6.sh
index 8bc23fb4c82b7..51132c26e9b55 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ipv6.sh
@@ -64,76 +64,85 @@ for ovr in setsock cmsg both diff; do
 done
 
 # IPV6_TCLASS
-TOS=0x10
-TOS2=0x20
 
-ip -6 -netns $NS rule add tos $TOS lookup 300
-ip -6 -netns $NS route add table 300 prohibit any
+test_dscp() {
+    local -r TOS=0x10
+    local -r TOS2=0x20
 
-for ovr in setsock cmsg both diff; do
-    for p in u i r; do
-	[ $p == "u" ] && prot=UDP
-	[ $p == "i" ] && prot=ICMP
-	[ $p == "r" ] && prot=RAW
+    ip -6 -netns $NS rule add tos $TOS lookup 300
+    ip -6 -netns $NS route add table 300 prohibit any
 
-	[ $ovr == "setsock" ] && m="-C"
-	[ $ovr == "cmsg" ]    && m="-c"
-	[ $ovr == "both" ]    && m="-C $((TOS2)) -c"
-	[ $ovr == "diff" ]    && m="-C $((TOS )) -c"
+    for ovr in setsock cmsg both diff; do
+	for p in u i r; do
+	    [ $p == "u" ] && prot=UDP
+	    [ $p == "i" ] && prot=ICMP
+	    [ $p == "r" ] && prot=RAW
 
-	$NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
-	BG=$!
-	sleep 0.05
+	    [ $ovr == "setsock" ] && m="-C"
+	    [ $ovr == "cmsg" ]    && m="-c"
+	    [ $ovr == "both" ]    && m="-C $((TOS2)) -c"
+	    [ $ovr == "diff" ]    && m="-C $((TOS )) -c"
 
-	$NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
-	check_result $? 0 "TCLASS $prot $ovr - pass"
+	    $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
+	    BG=$!
+	    sleep 0.05
 
-	while [ -d /proc/$BG ]; do
 	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
-	done
+	    check_result $? 0 "TCLASS $prot $ovr - pass"
 
-	tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
-	check_result $? 0 "TCLASS $prot $ovr - packet data"
-	rm $TMPF
+	    while [ -d /proc/$BG ]; do
+	        $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
+	    done
 
-	[ $ovr == "both" ]    && m="-C $((TOS )) -c"
-	[ $ovr == "diff" ]    && m="-C $((TOS2)) -c"
+	    tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
+	    check_result $? 0 "TCLASS $prot $ovr - packet data"
+	    rm $TMPF
 
-	$NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234
-	check_result $? 1 "TCLASS $prot $ovr - rejection"
+	    [ $ovr == "both" ]    && m="-C $((TOS )) -c"
+	    [ $ovr == "diff" ]    && m="-C $((TOS2)) -c"
+
+	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234
+	    check_result $? 1 "TCLASS $prot $ovr - rejection"
+	done
     done
-done
+}
 
-# IPV6_HOPLIMIT
-LIM=4
+test_dscp
 
-for ovr in setsock cmsg both diff; do
-    for p in u i r; do
-	[ $p == "u" ] && prot=UDP
-	[ $p == "i" ] && prot=ICMP
-	[ $p == "r" ] && prot=RAW
+# IPV6_HOPLIMIT
+test_hoplimit() {
+    local -r LIM=4
 
-	[ $ovr == "setsock" ] && m="-L"
-	[ $ovr == "cmsg" ]    && m="-l"
-	[ $ovr == "both" ]    && m="-L $LIM -l"
-	[ $ovr == "diff" ]    && m="-L $((LIM + 1)) -l"
+    for ovr in setsock cmsg both diff; do
+	for p in u i r; do
+	    [ $p == "u" ] && prot=UDP
+	    [ $p == "i" ] && prot=ICMP
+	    [ $p == "r" ] && prot=RAW
 
-	$NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
-	BG=$!
-	sleep 0.05
+	    [ $ovr == "setsock" ] && m="-L"
+	    [ $ovr == "cmsg" ]    && m="-l"
+	    [ $ovr == "both" ]    && m="-L $LIM -l"
+	    [ $ovr == "diff" ]    && m="-L $((LIM + 1)) -l"
 
-	$NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
-	check_result $? 0 "HOPLIMIT $prot $ovr - pass"
+	    $NSEXE nohup tcpdump --immediate-mode -p -ni dummy0 -w $TMPF -c 4 2> /dev/null &
+	    BG=$!
+	    sleep 0.05
 
-	while [ -d /proc/$BG ]; do
 	    $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
-	done
+	    check_result $? 0 "HOPLIMIT $prot $ovr - pass"
 
-	tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
-	check_result $? 0 "HOPLIMIT $prot $ovr - packet data"
-	rm $TMPF
+	    while [ -d /proc/$BG ]; do
+	        $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
+	    done
+
+	    tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
+	    check_result $? 0 "HOPLIMIT $prot $ovr - packet data"
+	    rm $TMPF
+	done
     done
-done
+}
+
+test_hoplimit
 
 # IPV6 exthdr
 for p in u i r; do

From 2e5584e0f913b53630238223443ae2a67eea714c Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 24 Feb 2025 21:23:59 -0500
Subject: [PATCH 1243/2753] selftests/net: expand cmsg_ipv6.sh with ipv4

Expand IPV6_TCLASS to also cover IP_TOS.
Expand IPV6_HOPLIMIT to also cover IP_TTL.

Expand csmg_sender.c to allow setting IPv4 setsockopts.
Also rename struct v6 to cmsg to match its expanded scope.
Don't bother updating all occurrences of tclass and hoplimit.

Rename cmsg_ipv6.sh to cmsg_ip.sh to match the expanded scope.

Be careful around the subtle API difference between TCLASS and TOS.
IP_TOS includes ECN bits. Add a test to verify that these are masked
when making routing decisions.

Diff is more concise with --word-diff

Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250225022431.2083926-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/Makefile          |  2 +-
 .../net/{cmsg_ipv6.sh => cmsg_ip.sh}          | 59 ++++++++----
 tools/testing/selftests/net/cmsg_sender.c     | 90 +++++++++++--------
 3 files changed, 96 insertions(+), 55 deletions(-)
 rename tools/testing/selftests/net/{cmsg_ipv6.sh => cmsg_ip.sh} (65%)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index aeb96c0856146..2e16ce6d28e46 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -34,7 +34,7 @@ TEST_PROGS += gre_gso.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += test_so_rcv.sh
-TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
+TEST_PROGS += cmsg_time.sh cmsg_ip.sh
 TEST_PROGS += netns-name.sh
 TEST_PROGS += link_netns.py
 TEST_PROGS += nl_netdev.py
diff --git a/tools/testing/selftests/net/cmsg_ipv6.sh b/tools/testing/selftests/net/cmsg_ip.sh
similarity index 65%
rename from tools/testing/selftests/net/cmsg_ipv6.sh
rename to tools/testing/selftests/net/cmsg_ip.sh
index 51132c26e9b55..2a52520aca327 100755
--- a/tools/testing/selftests/net/cmsg_ipv6.sh
+++ b/tools/testing/selftests/net/cmsg_ip.sh
@@ -3,6 +3,8 @@
 
 source lib.sh
 
+IP4=172.16.0.1/24
+TGT4=172.16.0.2
 IP6=2001:db8:1::1/64
 TGT6=2001:db8:1::2
 TMPF=$(mktemp --suffix ".pcap")
@@ -30,6 +32,7 @@ $NSEXE sysctl -w net.ipv4.ping_group_range='0 2147483647' > /dev/null
 # Connectivity
 ip -netns $NS link add type dummy
 ip -netns $NS link set dev dummy0 up
+ip -netns $NS addr add $IP4 dev dummy0
 ip -netns $NS addr add $IP6 dev dummy0
 
 # Test
@@ -63,14 +66,19 @@ for ovr in setsock cmsg both diff; do
     done
 done
 
-# IPV6_TCLASS
+# IP_TOS + IPV6_TCLASS
 
 test_dscp() {
+    local -r IPVER=$1
+    local -r TGT=$2
+    local -r MATCH=$3
+
     local -r TOS=0x10
     local -r TOS2=0x20
+    local -r ECN=0x3
 
-    ip -6 -netns $NS rule add tos $TOS lookup 300
-    ip -6 -netns $NS route add table 300 prohibit any
+    ip $IPVER -netns $NS rule add tos $TOS lookup 300
+    ip $IPVER -netns $NS route add table 300 prohibit any
 
     for ovr in setsock cmsg both diff; do
 	for p in u i r; do
@@ -87,30 +95,42 @@ test_dscp() {
 	    BG=$!
 	    sleep 0.05
 
-	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
-	    check_result $? 0 "TCLASS $prot $ovr - pass"
+	    $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234
+	    check_result $? 0 "$MATCH $prot $ovr - pass"
 
 	    while [ -d /proc/$BG ]; do
-	        $NSEXE ./cmsg_sender -6 -p $p $m $((TOS2)) $TGT6 1234
+	        $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS2)) $TGT 1234
 	    done
 
-	    tcpdump -r $TMPF -v 2>&1 | grep "class $TOS2" >> /dev/null
-	    check_result $? 0 "TCLASS $prot $ovr - packet data"
+	    tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $TOS2" >> /dev/null
+	    check_result $? 0 "$MATCH $prot $ovr - packet data"
 	    rm $TMPF
 
 	    [ $ovr == "both" ]    && m="-C $((TOS )) -c"
 	    [ $ovr == "diff" ]    && m="-C $((TOS2)) -c"
 
-	    $NSEXE ./cmsg_sender -6 -p $p $m $((TOS)) -s $TGT6 1234
-	    check_result $? 1 "TCLASS $prot $ovr - rejection"
+	    # Match prohibit rule: expect failure
+	    $NSEXE ./cmsg_sender $IPVER -p $p $m $((TOS)) -s $TGT 1234
+	    check_result $? 1 "$MATCH $prot $ovr - rejection"
+
+	    # Match prohibit rule: IPv4 masks ECN: expect failure
+	    if [[ "$IPVER" == "-4" ]]; then
+		$NSEXE ./cmsg_sender $IPVER -p $p $m "$((TOS | ECN))" -s $TGT 1234
+		check_result $? 1 "$MATCH $prot $ovr - rejection (ECN)"
+	    fi
 	done
     done
 }
 
-test_dscp
+test_dscp -4 $TGT4 tos
+test_dscp -6 $TGT6 class
+
+# IP_TTL + IPV6_HOPLIMIT
+test_ttl_hoplimit() {
+    local -r IPVER=$1
+    local -r TGT=$2
+    local -r MATCH=$3
 
-# IPV6_HOPLIMIT
-test_hoplimit() {
     local -r LIM=4
 
     for ovr in setsock cmsg both diff; do
@@ -128,21 +148,22 @@ test_hoplimit() {
 	    BG=$!
 	    sleep 0.05
 
-	    $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
-	    check_result $? 0 "HOPLIMIT $prot $ovr - pass"
+	    $NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234
+	    check_result $? 0 "$MATCH $prot $ovr - pass"
 
 	    while [ -d /proc/$BG ]; do
-	        $NSEXE ./cmsg_sender -6 -p $p $m $LIM $TGT6 1234
+		$NSEXE ./cmsg_sender $IPVER -p $p $m $LIM $TGT 1234
 	    done
 
-	    tcpdump -r $TMPF -v 2>&1 | grep "hlim $LIM[^0-9]" >> /dev/null
-	    check_result $? 0 "HOPLIMIT $prot $ovr - packet data"
+	    tcpdump -r $TMPF -v 2>&1 | grep "$MATCH $LIM[^0-9]" >> /dev/null
+	    check_result $? 0 "$MATCH $prot $ovr - packet data"
 	    rm $TMPF
 	done
     done
 }
 
-test_hoplimit
+test_ttl_hoplimit -4 $TGT4 ttl
+test_ttl_hoplimit -6 $TGT6 hlim
 
 # IPV6 exthdr
 for p in u i r; do
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index bc314382e4e1b..19bd8499031bf 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -72,7 +72,7 @@ struct options {
 		struct option_cmsg_u32 tclass;
 		struct option_cmsg_u32 hlimit;
 		struct option_cmsg_u32 exthdr;
-	} v6;
+	} cmsg;
 } opt = {
 	.size = 13,
 	.num_pkt = 1,
@@ -104,10 +104,10 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
 	       "\t\t-t      Enable time stamp reporting\n"
 	       "\t\t-f val  Set don't fragment via cmsg\n"
 	       "\t\t-F val  Set don't fragment via setsockopt\n"
-	       "\t\t-c val  Set TCLASS via cmsg\n"
-	       "\t\t-C val  Set TCLASS via setsockopt\n"
-	       "\t\t-l val  Set HOPLIMIT via cmsg\n"
-	       "\t\t-L val  Set HOPLIMIT via setsockopt\n"
+	       "\t\t-c val  Set TOS/TCLASS via cmsg\n"
+	       "\t\t-C val  Set TOS/TCLASS via setsockopt\n"
+	       "\t\t-l val  Set TTL/HOPLIMIT via cmsg\n"
+	       "\t\t-L val  Set TTL/HOPLIMIT via setsockopt\n"
 	       "\t\t-H type Add an IPv6 header option\n"
 	       "\t\t        (h = HOP; d = DST; r = RTDST)"
 	       "");
@@ -169,37 +169,37 @@ static void cs_parse_args(int argc, char *argv[])
 			opt.ts.ena = true;
 			break;
 		case 'f':
-			opt.v6.dontfrag.ena = true;
-			opt.v6.dontfrag.val = atoi(optarg);
+			opt.cmsg.dontfrag.ena = true;
+			opt.cmsg.dontfrag.val = atoi(optarg);
 			break;
 		case 'F':
 			opt.sockopt.dontfrag = atoi(optarg);
 			break;
 		case 'c':
-			opt.v6.tclass.ena = true;
-			opt.v6.tclass.val = atoi(optarg);
+			opt.cmsg.tclass.ena = true;
+			opt.cmsg.tclass.val = atoi(optarg);
 			break;
 		case 'C':
 			opt.sockopt.tclass = atoi(optarg);
 			break;
 		case 'l':
-			opt.v6.hlimit.ena = true;
-			opt.v6.hlimit.val = atoi(optarg);
+			opt.cmsg.hlimit.ena = true;
+			opt.cmsg.hlimit.val = atoi(optarg);
 			break;
 		case 'L':
 			opt.sockopt.hlimit = atoi(optarg);
 			break;
 		case 'H':
-			opt.v6.exthdr.ena = true;
+			opt.cmsg.exthdr.ena = true;
 			switch (optarg[0]) {
 			case 'h':
-				opt.v6.exthdr.val = IPV6_HOPOPTS;
+				opt.cmsg.exthdr.val = IPV6_HOPOPTS;
 				break;
 			case 'd':
-				opt.v6.exthdr.val = IPV6_DSTOPTS;
+				opt.cmsg.exthdr.val = IPV6_DSTOPTS;
 				break;
 			case 'r':
-				opt.v6.exthdr.val = IPV6_RTHDRDSTOPTS;
+				opt.cmsg.exthdr.val = IPV6_RTHDRDSTOPTS;
 				break;
 			default:
 				printf("Error: hdr type: %s\n", optarg);
@@ -261,12 +261,20 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 			  SOL_SOCKET, SO_MARK, &opt.mark);
 	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
 			  SOL_SOCKET, SO_PRIORITY, &opt.priority);
-	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
-			  SOL_IPV6, IPV6_DONTFRAG, &opt.v6.dontfrag);
-	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
-			  SOL_IPV6, IPV6_TCLASS, &opt.v6.tclass);
-	ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
-			  SOL_IPV6, IPV6_HOPLIMIT, &opt.v6.hlimit);
+
+	if (opt.sock.family == AF_INET) {
+		ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+				  SOL_IP, IP_TOS, &opt.cmsg.tclass);
+		ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+				  SOL_IP, IP_TTL, &opt.cmsg.hlimit);
+	} else {
+		ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+				  SOL_IPV6, IPV6_DONTFRAG, &opt.cmsg.dontfrag);
+		ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+				  SOL_IPV6, IPV6_TCLASS, &opt.cmsg.tclass);
+		ca_write_cmsg_u32(cbuf, cbuf_sz, &cmsg_len,
+				  SOL_IPV6, IPV6_HOPLIMIT, &opt.cmsg.hlimit);
+	}
 
 	if (opt.txtime.ena) {
 		__u64 txtime;
@@ -297,14 +305,14 @@ cs_write_cmsg(int fd, struct msghdr *msg, char *cbuf, size_t cbuf_sz)
 		*(__u32 *)CMSG_DATA(cmsg) = SOF_TIMESTAMPING_TX_SCHED |
 					    SOF_TIMESTAMPING_TX_SOFTWARE;
 	}
-	if (opt.v6.exthdr.ena) {
+	if (opt.cmsg.exthdr.ena) {
 		cmsg = (struct cmsghdr *)(cbuf + cmsg_len);
 		cmsg_len += CMSG_SPACE(8);
 		if (cbuf_sz < cmsg_len)
 			error(ERN_CMSG_WR, EFAULT, "cmsg buffer too small");
 
 		cmsg->cmsg_level = SOL_IPV6;
-		cmsg->cmsg_type = opt.v6.exthdr.val;
+		cmsg->cmsg_type = opt.cmsg.exthdr.val;
 		cmsg->cmsg_len = CMSG_LEN(8);
 		*(__u64 *)CMSG_DATA(cmsg) = 0;
 	}
@@ -405,23 +413,35 @@ static void ca_set_sockopts(int fd)
 	    setsockopt(fd, SOL_SOCKET, SO_MARK,
 		       &opt.sockopt.mark, sizeof(opt.sockopt.mark)))
 		error(ERN_SOCKOPT, errno, "setsockopt SO_MARK");
-	if (opt.sockopt.dontfrag &&
-	    setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG,
-		       &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag)))
-		error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG");
-	if (opt.sockopt.tclass &&
-	    setsockopt(fd, SOL_IPV6, IPV6_TCLASS,
-		       &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
-		error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS");
-	if (opt.sockopt.hlimit &&
-	    setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS,
-		       &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
-		error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT");
 	if (opt.sockopt.priority &&
 	    setsockopt(fd, SOL_SOCKET, SO_PRIORITY,
 		       &opt.sockopt.priority, sizeof(opt.sockopt.priority)))
 		error(ERN_SOCKOPT, errno, "setsockopt SO_PRIORITY");
 
+	if (opt.sock.family == AF_INET) {
+		if (opt.sockopt.tclass &&
+		    setsockopt(fd, SOL_IP, IP_TOS,
+			       &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
+			error(ERN_SOCKOPT, errno, "setsockopt IP_TOS");
+		if (opt.sockopt.hlimit &&
+		    setsockopt(fd, SOL_IP, IP_TTL,
+			       &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
+			error(ERN_SOCKOPT, errno, "setsockopt IP_TTL");
+	} else {
+		if (opt.sockopt.dontfrag &&
+		    setsockopt(fd, SOL_IPV6, IPV6_DONTFRAG,
+			       &opt.sockopt.dontfrag, sizeof(opt.sockopt.dontfrag)))
+			error(ERN_SOCKOPT, errno, "setsockopt IPV6_DONTFRAG");
+		if (opt.sockopt.tclass &&
+		    setsockopt(fd, SOL_IPV6, IPV6_TCLASS,
+			       &opt.sockopt.tclass, sizeof(opt.sockopt.tclass)))
+			error(ERN_SOCKOPT, errno, "setsockopt IPV6_TCLASS");
+		if (opt.sockopt.hlimit &&
+		    setsockopt(fd, SOL_IPV6, IPV6_UNICAST_HOPS,
+			       &opt.sockopt.hlimit, sizeof(opt.sockopt.hlimit)))
+			error(ERN_SOCKOPT, errno, "setsockopt IPV6_HOPLIMIT");
+	}
+
 	if (opt.txtime.ena) {
 		struct sock_txtime so_txtime = {
 			.clockid = CLOCK_MONOTONIC,

From e6116fc605574bb58c2016938ff24a7fbafe6e2a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Mon, 24 Feb 2025 21:33:55 -0500
Subject: [PATCH 1244/2753] net: skb: free up one bit in tx_flags

The linked series wants to add skb tx completion timestamps.
That needs a bit in skb_shared_info.tx_flags, but all are in use.

A per-skb bit is only needed for features that are configured on a
per packet basis. Per socket features can be read from sk->sk_tsflags.

Per packet tsflags can be set in sendmsg using cmsg, but only those in
SOF_TIMESTAMPING_TX_RECORD_MASK.

Per packet tsflags can also be set without cmsg by sandwiching a
send inbetween two setsockopts:

    val |= SOF_TIMESTAMPING_$FEATURE;
    setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));
    write(fd, buf, sz);
    val &= ~SOF_TIMESTAMPING_$FEATURE;
    setsockopt(fd, SOL_SOCKET, SO_TIMESTAMPING, &val, sizeof(val));

Changing a datapath test from skb_shinfo(skb)->tx_flags to
skb->sk->sk_tsflags can change behavior in that case, as the tx_flags
is written before the second setsockopt updates sk_tsflags.

Therefore, only bits can be reclaimed that cannot be set by cmsg and
are also highly unlikely to be used to target individual packets
otherwise.

Free up the bit currently used for SKBTX_HW_TSTAMP_USE_CYCLES. This
selects between clock and free running counter source for HW TX
timestamps. It is probable that all packets of the same socket will
always use the same source.

Link: https://lore.kernel.org/netdev/cover.1739988644.git.pav@iki.fi/
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250225023416.2088705-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/engleder/tsnep_main.c |  4 ++--
 drivers/net/ethernet/intel/igc/igc_main.c  |  3 ++-
 include/linux/skbuff.h                     |  5 ++---
 net/socket.c                               | 11 +----------
 4 files changed, 7 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 0d030cb0b21c7..3de4cb06e2668 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -852,8 +852,8 @@ static bool tsnep_tx_poll(struct tsnep_tx *tx, int napi_budget)
 			struct skb_shared_hwtstamps hwtstamps;
 			u64 timestamp;
 
-			if (skb_shinfo(entry->skb)->tx_flags &
-			    SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (entry->skb->sk &&
+			    READ_ONCE(entry->skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				timestamp =
 					__le64_to_cpu(entry->desc_wb->counter);
 			else
diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 3044392e8ded8..472f009630c98 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -1668,7 +1668,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb,
 		if (igc_request_tx_tstamp(adapter, skb, &tstamp_flags)) {
 			skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 			tx_flags |= IGC_TX_FLAGS_TSTAMP | tstamp_flags;
-			if (skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP_USE_CYCLES)
+			if (skb->sk &&
+			    READ_ONCE(skb->sk->sk_tsflags) & SOF_TIMESTAMPING_BIND_PHC)
 				tx_flags |= IGC_TX_FLAGS_TSTAMP_TIMER_1;
 		} else {
 			adapter->tx_hwtstamp_skipped++;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index f2bb8473d99a5..171aa15f65414 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -478,8 +478,8 @@ enum {
 	/* device driver is going to provide hardware time stamp */
 	SKBTX_IN_PROGRESS = 1 << 2,
 
-	/* generate hardware time stamp based on cycles if supported */
-	SKBTX_HW_TSTAMP_USE_CYCLES = 1 << 3,
+	/* reserved */
+	SKBTX_RESERVED = 1 << 3,
 
 	/* generate wifi status information (where possible) */
 	SKBTX_WIFI_STATUS = 1 << 4,
@@ -500,7 +500,6 @@ enum {
 				 SKBTX_SCHED_TSTAMP | \
 				 SKBTX_BPF)
 #define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \
-				 SKBTX_HW_TSTAMP_USE_CYCLES | \
 				 SKBTX_ANY_SW_TSTAMP)
 
 /* Definitions for flags in struct skb_shared_info */
diff --git a/net/socket.c b/net/socket.c
index 0545e9ea70581..b64ecf2722e7b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -680,18 +680,9 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags)
 {
 	u8 flags = *tx_flags;
 
-	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) {
+	if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE)
 		flags |= SKBTX_HW_TSTAMP_NOBPF;
 
-		/* PTP hardware clocks can provide a free running cycle counter
-		 * as a time base for virtual clocks. Tell driver to use the
-		 * free running cycle counter for timestamp if socket is bound
-		 * to virtual clock.
-		 */
-		if (tsflags & SOF_TIMESTAMPING_BIND_PHC)
-			flags |= SKBTX_HW_TSTAMP_USE_CYCLES;
-	}
-
 	if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE)
 		flags |= SKBTX_SW_TSTAMP;
 

From bc23d4e30866011700787bab8563de45d5bf8431 Mon Sep 17 00:00:00 2001
From: Adrian Huang <ahuang12@lenovo.com>
Date: Tue, 25 Feb 2025 10:14:57 +0800
Subject: [PATCH 1245/2753] af_unix: Fix memory leak in unix_dgram_sendmsg()

After running the 'sendmsg02' program of Linux Test Project (LTP),
kmemleak reports the following memory leak:

  # cat /sys/kernel/debug/kmemleak
  unreferenced object 0xffff888243866800 (size 2048):
    comm "sendmsg02", pid 67, jiffies 4294903166
    hex dump (first 32 bytes):
      00 00 00 00 00 00 00 00 5e 00 00 00 00 00 00 00  ........^.......
      01 00 07 40 00 00 00 00 00 00 00 00 00 00 00 00  ...@............
    backtrace (crc 7e96a3f2):
      kmemleak_alloc+0x56/0x90
      kmem_cache_alloc_noprof+0x209/0x450
      sk_prot_alloc.constprop.0+0x60/0x160
      sk_alloc+0x32/0xc0
      unix_create1+0x67/0x2b0
      unix_create+0x47/0xa0
      __sock_create+0x12e/0x200
      __sys_socket+0x6d/0x100
      __x64_sys_socket+0x1b/0x30
      x64_sys_call+0x7e1/0x2140
      do_syscall_64+0x54/0x110
      entry_SYSCALL_64_after_hwframe+0x76/0x7e

Commit 689c398885cc ("af_unix: Defer sock_put() to clean up path in
unix_dgram_sendmsg().") defers sock_put() in the error handling path.
However, it fails to account for the condition 'msg->msg_namelen != 0',
resulting in a memory leak when the code jumps to the 'lookup' label.

Fix issue by calling sock_put() if 'msg->msg_namelen != 0' is met.

Fixes: 689c398885cc ("af_unix: Defer sock_put() to clean up path in unix_dgram_sendmsg().")
Signed-off-by: Adrian Huang <ahuang12@lenovo.com>
Acked-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250225021457.1824-1-ahuang12@lenovo.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/unix/af_unix.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 34945de1fb1fa..f0e613d976640 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2102,6 +2102,7 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg,
 			goto out_sock_put;
 		}
 
+		sock_put(other);
 		goto lookup;
 	}
 

From 28d68d396a1cd21591e8c6d74afbde33a7ea107e Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Tue, 25 Feb 2025 03:39:14 +0000
Subject: [PATCH 1246/2753] bonding: report duplicate MAC address in all
 situations
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Normally, a bond uses the MAC address of the first added slave as the bond’s
MAC address. And the bond will set active slave’s MAC address to bond’s
address if fail_over_mac is set to none (0) or follow (2).

When the first slave is removed, the bond will still use the removed slave’s
MAC address, which can lead to a duplicate MAC address and potentially cause
issues with the switch. To avoid confusion, let's warn the user in all
situations, including when fail_over_mac is set to 2 or not in active-backup
mode.

Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250225033914.18617-1-liuhangbin@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7d716e90a84c3..7d98fee5a27f9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2548,7 +2548,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	RCU_INIT_POINTER(bond->current_arp_slave, NULL);
 
-	if (!all && (!bond->params.fail_over_mac ||
+	if (!all && (bond->params.fail_over_mac != BOND_FOM_ACTIVE ||
 		     BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) {
 		if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) &&
 		    bond_has_slaves(bond))

From 2d253726ff7106b39a44483b6864398bba8a2f74 Mon Sep 17 00:00:00 2001
From: Harshal Chaudhari <hchaudhari@marvell.com>
Date: Mon, 24 Feb 2025 20:20:58 -0800
Subject: [PATCH 1247/2753] net: mvpp2: cls: Fixed Non IP flow, with vlan tag
 flow defination.

Non IP flow, with vlan tag not working as expected while
running below command for vlan-priority. fixed that.

ethtool -N eth1 flow-type ether vlan 0x8000 vlan-mask 0x1fff action 0 loc 0

Fixes: 1274daede3ef ("net: mvpp2: cls: Add steering based on vlan Id and priority.")
Signed-off-by: Harshal Chaudhari <hchaudhari@marvell.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250225042058.2643838-1-hchaudhari@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
index 1641791a2d5b4..8ed83fb988624 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_cls.c
@@ -324,7 +324,7 @@ static const struct mvpp2_cls_flow cls_flows[MVPP2_N_PRS_FLOWS] = {
 		       MVPP2_PRS_RI_VLAN_MASK),
 	/* Non IP flow, with vlan tag */
 	MVPP2_DEF_FLOW(MVPP22_FLOW_ETHERNET, MVPP2_FL_NON_IP_TAG,
-		       MVPP22_CLS_HEK_OPT_VLAN,
+		       MVPP22_CLS_HEK_TAGGED,
 		       0, 0),
 };
 

From 7f3528f7d2f98b70e19a6bb7b130fc82c079ac54 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:06 +0200
Subject: [PATCH 1248/2753] net/mlx5: Fix vport QoS cleanup on error

When enabling vport QoS fails, the scheduling node was never freed,
causing a leak.

Add the missing free and reset the vport scheduling node pointer to
NULL.

Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250225072608.526866-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 8b7c843446e11..07a28073a49ea 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -591,8 +591,11 @@ static int mlx5_esw_qos_vport_enable(struct mlx5_vport *vport, enum sched_node_t
 	sched_node->vport = vport;
 	vport->qos.sched_node = sched_node;
 	err = esw_qos_vport_enable(vport, parent, extack);
-	if (err)
+	if (err) {
+		__esw_qos_free_node(sched_node);
 		esw_qos_put(esw);
+		vport->qos.sched_node = NULL;
+	}
 
 	return err;
 }

From 47bcd9bf3d231bfd4698d7d3013597490fd5e2d6 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:07 +0200
Subject: [PATCH 1249/2753] net/mlx5: Restore missing trace event when enabling
 vport QoS

Restore the `trace_mlx5_esw_vport_qos_create` event when creating
the vport scheduling element. This trace event was lost during
refactoring.

Fixes: be034baba83e ("net/mlx5: Make vport QoS enablement more flexible for future extensions")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250225072608.526866-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 07a28073a49ea..823c1ba456cd1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -564,6 +564,9 @@ static int esw_qos_vport_enable(struct mlx5_vport *vport, struct mlx5_esw_sched_
 		return err;
 
 	esw_qos_normalize_min_rate(parent->esw, parent, extack);
+	trace_mlx5_esw_vport_qos_create(vport->dev, vport,
+					vport->qos.sched_node->max_rate,
+					vport->qos.sched_node->bw_share);
 
 	return 0;
 }

From 2f5a6014eb168a97b24153adccfa663d3b282767 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 25 Feb 2025 09:26:08 +0200
Subject: [PATCH 1250/2753] net/mlx5: IRQ, Fix null string in debug print

irq_pool_alloc() debug print can print a null string.
Fix it by providing a default string to print.

Fixes: 71e084e26414 ("net/mlx5: Allocating a pool of MSI-X vectors for SFs")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202501141055.SwfIphN0-lkp@intel.com/
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Link: https://patch.msgid.link/20250225072608.526866-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index 7db9cab9bedf6..d9362eabc6a1c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -572,7 +572,7 @@ irq_pool_alloc(struct mlx5_core_dev *dev, int start, int size, char *name,
 	pool->min_threshold = min_threshold * MLX5_EQ_REFS_PER_IRQ;
 	pool->max_threshold = max_threshold * MLX5_EQ_REFS_PER_IRQ;
 	mlx5_core_dbg(dev, "pool->name = %s, pool->size = %d, pool->start = %d",
-		      name, size, start);
+		      name ? name : "mlx5_pcif_pool", size, start);
 	return pool;
 }
 

From bd7c00605ee0cf0bf27764d5da0b948d8004229e Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Mon, 24 Feb 2025 16:22:22 -0700
Subject: [PATCH 1251/2753] net: move aRFS rmap management and CPU affinity to
 core

A common task for most drivers is to remember the user-set CPU affinity
to its IRQs. On each netdev reset, the driver should re-assign the user's
settings to the IRQs. Unify this task across all drivers by moving the CPU
affinity to napi->config.

However, to move the CPU affinity to core, we also need to move aRFS
rmap management since aRFS uses its own IRQ notifiers.

For the aRFS, add a new netdev flag "rx_cpu_rmap_auto". Drivers supporting
aRFS should set the flag via netif_enable_cpu_rmap() and core will allocate
and manage the aRFS rmaps. Freeing the rmap is also done by core when the
netdev is freed. For better IRQ affinity management, move the IRQ rmap
notifier inside the napi_struct and add new notify.notify and
notify.release functions: netif_irq_cpu_rmap_notify() and
netif_napi_affinity_release().

Now we have the aRFS rmap management in core, add CPU affinity mask to
napi_config. To delegate the CPU affinity management to the core, drivers
must:
 1 - set the new netdev flag "irq_affinity_auto":
                                       netif_enable_irq_affinity(netdev)
 2 - create the napi with persistent config:
                                       netif_napi_add_config()
 3 - bind an IRQ to the napi instance: netif_napi_set_irq()

the core will then make sure to use re-assign affinity to the napi's
IRQ.

The default IRQ mask is set to one cpu starting from the closest NUMA.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-2-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/scaling.rst |   6 +-
 include/linux/cpu_rmap.h             |   1 +
 include/linux/netdevice.h            |  24 +++-
 lib/cpu_rmap.c                       |   2 +-
 net/core/dev.c                       | 169 +++++++++++++++++++++++++++
 5 files changed, 195 insertions(+), 7 deletions(-)

diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst
index 6984700cec6ad..99b6a61e5e31c 100644
--- a/Documentation/networking/scaling.rst
+++ b/Documentation/networking/scaling.rst
@@ -434,8 +434,10 @@ rps_dev_flow_table. The stack consults a CPU to hardware queue map which
 is maintained by the NIC driver. This is an auto-generated reverse map of
 the IRQ affinity table shown by /proc/interrupts. Drivers can use
 functions in the cpu_rmap (“CPU affinity reverse map”) kernel library
-to populate the map. For each CPU, the corresponding queue in the map is
-set to be one whose processing CPU is closest in cache locality.
+to populate the map. Alternatively, drivers can delegate the cpu_rmap
+management to the Kernel by calling netif_enable_cpu_rmap(). For each CPU,
+the corresponding queue in the map is set to be one whose processing CPU is
+closest in cache locality.
 
 
 Accelerated RFS Configuration
diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index 20b5729903d72..2fd7ba75362aa 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -32,6 +32,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
+extern void cpu_rmap_get(struct cpu_rmap *rmap);
 extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9a387d456592e..2094d3edda739 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -352,6 +352,7 @@ struct napi_config {
 	u64 gro_flush_timeout;
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
+	cpumask_t affinity_mask;
 	unsigned int napi_id;
 };
 
@@ -394,6 +395,8 @@ struct napi_struct {
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
+	struct irq_affinity_notify notify;
+	int			napi_rmap_idx;
 	int			index;
 	struct napi_config	*config;
 };
@@ -409,6 +412,7 @@ enum {
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
 	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
+	NAPI_STATE_HAS_NOTIFIER,	/* Napi has an IRQ notifier */
 };
 
 enum {
@@ -422,6 +426,7 @@ enum {
 	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
 	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
+	NAPIF_STATE_HAS_NOTIFIER	= BIT(NAPI_STATE_HAS_NOTIFIER),
 };
 
 enum gro_result {
@@ -1989,6 +1994,15 @@ enum netdev_reg_state {
  *
  *	@threaded:	napi threaded mode is enabled
  *
+ *	@irq_affinity_auto: driver wants the core to store and re-assign the IRQ
+ *			    affinity. Set by netif_enable_irq_affinity(), then
+ *			    the driver must create a persistent napi by
+ *			    netif_napi_add_config() and finally bind the napi to
+ *			    IRQ (via netif_napi_set_irq()).
+ *
+ *	@rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap.
+ *	                   Set by calling netif_enable_cpu_rmap().
+ *
  *	@see_all_hwtstamp_requests: device wants to see calls to
  *			ndo_hwtstamp_set() for all timestamp requests
  *			regardless of source, even if those aren't
@@ -2396,6 +2410,8 @@ struct net_device {
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
 	bool			threaded;
+	bool			irq_affinity_auto;
+	bool			rx_cpu_rmap_auto;
 
 	/* priv_flags_slow, ungrouped to save space */
 	unsigned long		see_all_hwtstamp_requests:1;
@@ -2724,10 +2740,7 @@ static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
 		netdev_assert_locked(dev);
 }
 
-static inline void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
-{
-	napi->irq = irq;
-}
+void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
 
 static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
 {
@@ -2865,6 +2878,9 @@ static inline void netif_napi_del(struct napi_struct *napi)
 	synchronize_net();
 }
 
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
+void netif_set_affinity_auto(struct net_device *dev);
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	bool			ignore_outgoing;
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 4c348670da314..f03d9be3f06ba 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -73,7 +73,7 @@ static void cpu_rmap_release(struct kref *ref)
  * cpu_rmap_get - internal helper to get new ref on a cpu_rmap
  * @rmap: reverse-map allocated with alloc_cpu_rmap()
  */
-static inline void cpu_rmap_get(struct cpu_rmap *rmap)
+void cpu_rmap_get(struct cpu_rmap *rmap)
 {
 	kref_get(&rmap->refcount);
 }
diff --git a/net/core/dev.c b/net/core/dev.c
index 3f525278a8718..b0ab0169f5070 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6943,11 +6943,175 @@ void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
 }
 EXPORT_SYMBOL(netif_queue_set_napi);
 
+static void
+netif_napi_irq_notify(struct irq_affinity_notify *notify,
+		      const cpumask_t *mask)
+{
+	struct napi_struct *napi =
+		container_of(notify, struct napi_struct, notify);
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+	int err;
+#endif
+
+	if (napi->config && napi->dev->irq_affinity_auto)
+		cpumask_copy(&napi->config->affinity_mask, mask);
+
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		err = cpu_rmap_update(rmap, napi->napi_rmap_idx, mask);
+		if (err)
+			netdev_warn(napi->dev, "RMAP update failed (%d)\n",
+				    err);
+	}
+#endif
+}
+
+#ifdef CONFIG_RFS_ACCEL
+static void netif_napi_affinity_release(struct kref *ref)
+{
+	struct napi_struct *napi =
+		container_of(ref, struct napi_struct, notify.kref);
+	struct cpu_rmap *rmap = napi->dev->rx_cpu_rmap;
+
+	netdev_assert_locked(napi->dev);
+	WARN_ON(test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER,
+				   &napi->state));
+
+	if (!napi->dev->rx_cpu_rmap_auto)
+		return;
+	rmap->obj[napi->napi_rmap_idx] = NULL;
+	napi->napi_rmap_idx = -1;
+	cpu_rmap_put(rmap);
+}
+
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
+{
+	if (dev->rx_cpu_rmap_auto)
+		return 0;
+
+	dev->rx_cpu_rmap = alloc_irq_cpu_rmap(num_irqs);
+	if (!dev->rx_cpu_rmap)
+		return -ENOMEM;
+
+	dev->rx_cpu_rmap_auto = true;
+	return 0;
+}
+EXPORT_SYMBOL(netif_enable_cpu_rmap);
+
+static void netif_del_cpu_rmap(struct net_device *dev)
+{
+	struct cpu_rmap *rmap = dev->rx_cpu_rmap;
+
+	if (!dev->rx_cpu_rmap_auto)
+		return;
+
+	/* Free the rmap */
+	cpu_rmap_put(rmap);
+	dev->rx_cpu_rmap = NULL;
+	dev->rx_cpu_rmap_auto = false;
+}
+
+#else
+static void netif_napi_affinity_release(struct kref *ref)
+{
+}
+
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs)
+{
+	return 0;
+}
+EXPORT_SYMBOL(netif_enable_cpu_rmap);
+
+static void netif_del_cpu_rmap(struct net_device *dev)
+{
+}
+#endif
+
+void netif_set_affinity_auto(struct net_device *dev)
+{
+	unsigned int i, maxqs, numa;
+
+	maxqs = max(dev->num_tx_queues, dev->num_rx_queues);
+	numa = dev_to_node(&dev->dev);
+
+	for (i = 0; i < maxqs; i++)
+		cpumask_set_cpu(cpumask_local_spread(i, numa),
+				&dev->napi_config[i].affinity_mask);
+
+	dev->irq_affinity_auto = true;
+}
+EXPORT_SYMBOL(netif_set_affinity_auto);
+
+void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
+{
+	int rc;
+
+	netdev_assert_locked_or_invisible(napi->dev);
+
+	if (napi->irq == irq)
+		return;
+
+	/* Remove existing resources */
+	if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
+		irq_set_affinity_notifier(napi->irq, NULL);
+
+	napi->irq = irq;
+	if (irq < 0 ||
+	    (!napi->dev->rx_cpu_rmap_auto && !napi->dev->irq_affinity_auto))
+		return;
+
+	/* Abort for buggy drivers */
+	if (napi->dev->irq_affinity_auto && WARN_ON_ONCE(!napi->config))
+		return;
+
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		rc = cpu_rmap_add(napi->dev->rx_cpu_rmap, napi);
+		if (rc < 0)
+			return;
+
+		cpu_rmap_get(napi->dev->rx_cpu_rmap);
+		napi->napi_rmap_idx = rc;
+	}
+#endif
+
+	/* Use core IRQ notifier */
+	napi->notify.notify = netif_napi_irq_notify;
+	napi->notify.release = netif_napi_affinity_release;
+	rc = irq_set_affinity_notifier(irq, &napi->notify);
+	if (rc) {
+		netdev_warn(napi->dev, "Unable to set IRQ notifier (%d)\n",
+			    rc);
+		goto put_rmap;
+	}
+
+	set_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state);
+	return;
+
+put_rmap:
+#ifdef CONFIG_RFS_ACCEL
+	if (napi->dev->rx_cpu_rmap_auto) {
+		cpu_rmap_put(napi->dev->rx_cpu_rmap);
+		napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL;
+		napi->napi_rmap_idx = -1;
+	}
+#endif
+	napi->notify.notify = NULL;
+	napi->notify.release = NULL;
+}
+EXPORT_SYMBOL(netif_napi_set_irq_locked);
+
 static void napi_restore_config(struct napi_struct *n)
 {
 	n->defer_hard_irqs = n->config->defer_hard_irqs;
 	n->gro_flush_timeout = n->config->gro_flush_timeout;
 	n->irq_suspend_timeout = n->config->irq_suspend_timeout;
+
+	if (n->dev->irq_affinity_auto &&
+	    test_bit(NAPI_STATE_HAS_NOTIFIER, &n->state))
+		irq_set_affinity(n->irq, &n->config->affinity_mask);
+
 	/* a NAPI ID might be stored in the config, if so use it. if not, use
 	 * napi_hash_add to generate one for us.
 	 */
@@ -7168,6 +7332,9 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	/* Make sure NAPI is disabled (or was never enabled). */
 	WARN_ON(!test_bit(NAPI_STATE_SCHED, &napi->state));
 
+	if (test_and_clear_bit(NAPI_STATE_HAS_NOTIFIER, &napi->state))
+		irq_set_affinity_notifier(napi->irq, NULL);
+
 	if (napi->config) {
 		napi->index = -1;
 		napi->config = NULL;
@@ -11720,6 +11887,8 @@ void free_netdev(struct net_device *dev)
 
 	netdev_napi_exit(dev);
 
+	netif_del_cpu_rmap(dev);
+
 	ref_tracker_dir_exit(&dev->refcnt_tracker);
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	free_percpu(dev->pcpu_refcnt);

From de340d8206bf1897fcc05436adffb4d63a0a13e0 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Mon, 24 Feb 2025 16:22:23 -0700
Subject: [PATCH 1252/2753] net: ena: use napi's aRFS rmap notifers

Use the core's rmap notifiers and delete our own.

Acked-by: David Arinzon <darinzon@amazon.com>
Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-3-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 43 +-------------------
 1 file changed, 1 insertion(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index c1295dfad0d07..6aab85a7c60a1 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -5,9 +5,6 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#ifdef CONFIG_RFS_ACCEL
-#include <linux/cpu_rmap.h>
-#endif /* CONFIG_RFS_ACCEL */
 #include <linux/ethtool.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -162,30 +159,6 @@ int ena_xmit_common(struct ena_adapter *adapter,
 	return 0;
 }
 
-static int ena_init_rx_cpu_rmap(struct ena_adapter *adapter)
-{
-#ifdef CONFIG_RFS_ACCEL
-	u32 i;
-	int rc;
-
-	adapter->netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(adapter->num_io_queues);
-	if (!adapter->netdev->rx_cpu_rmap)
-		return -ENOMEM;
-	for (i = 0; i < adapter->num_io_queues; i++) {
-		int irq_idx = ENA_IO_IRQ_IDX(i);
-
-		rc = irq_cpu_rmap_add(adapter->netdev->rx_cpu_rmap,
-				      pci_irq_vector(adapter->pdev, irq_idx));
-		if (rc) {
-			free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-			adapter->netdev->rx_cpu_rmap = NULL;
-			return rc;
-		}
-	}
-#endif /* CONFIG_RFS_ACCEL */
-	return 0;
-}
-
 static void ena_init_io_rings_common(struct ena_adapter *adapter,
 				     struct ena_ring *ring, u16 qid)
 {
@@ -1596,7 +1569,7 @@ static int ena_enable_msix(struct ena_adapter *adapter)
 		adapter->num_io_queues = irq_cnt - ENA_ADMIN_MSIX_VEC;
 	}
 
-	if (ena_init_rx_cpu_rmap(adapter))
+	if (netif_enable_cpu_rmap(adapter->netdev, adapter->num_io_queues))
 		netif_warn(adapter, probe, adapter->netdev,
 			   "Failed to map IRQs to CPUs\n");
 
@@ -1742,13 +1715,6 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	struct ena_irq *irq;
 	int i;
 
-#ifdef CONFIG_RFS_ACCEL
-	if (adapter->msix_vecs >= 1) {
-		free_irq_cpu_rmap(adapter->netdev->rx_cpu_rmap);
-		adapter->netdev->rx_cpu_rmap = NULL;
-	}
-#endif /* CONFIG_RFS_ACCEL */
-
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
@@ -4131,13 +4097,6 @@ static void __ena_shutoff(struct pci_dev *pdev, bool shutdown)
 	ena_dev = adapter->ena_dev;
 	netdev = adapter->netdev;
 
-#ifdef CONFIG_RFS_ACCEL
-	if ((adapter->msix_vecs >= 1) && (netdev->rx_cpu_rmap)) {
-		free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-		netdev->rx_cpu_rmap = NULL;
-	}
-
-#endif /* CONFIG_RFS_ACCEL */
 	/* Make sure timer and reset routine won't be called after
 	 * freeing device resources.
 	 */

From 30b78ba3d4fe7a4dcf86f7ed21e719a62b71a392 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Mon, 24 Feb 2025 16:22:24 -0700
Subject: [PATCH 1253/2753] ice: clear NAPI's IRQ numbers in
 ice_vsi_clear_napi_queues()

We set the NAPI's IRQ number in ice_vsi_set_napi_queues(). Clear the
NAPI's IRQ in ice_vsi_clear_napi_queues().

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-4-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_lib.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 7f5b229cab059..ce30674abf8f1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2765,11 +2765,18 @@ void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
 void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
 {
 	struct net_device *netdev = vsi->netdev;
-	int q_idx;
+	int q_idx, v_idx;
 
 	if (!netdev)
 		return;
 
+	/* Clear the NAPI's interrupt number */
+	ice_for_each_q_vector(vsi, v_idx) {
+		struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+
+		netif_napi_set_irq(&q_vector->napi, -1);
+	}
+
 	ice_for_each_txq(vsi, q_idx)
 		netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
 

From 4063af296762e239588e0f69abc268e82f651983 Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Mon, 24 Feb 2025 16:22:25 -0700
Subject: [PATCH 1254/2753] ice: use napi's irq affinity and rmap IRQ notifiers

Delete the driver CPU affinity and aRFS rmap info, use the core's
API instead.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-5-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice.h      |  3 --
 drivers/net/ethernet/intel/ice/ice_arfs.c | 33 +---------------
 drivers/net/ethernet/intel/ice/ice_arfs.h |  2 -
 drivers/net/ethernet/intel/ice/ice_base.c |  7 +---
 drivers/net/ethernet/intel/ice/ice_lib.c  |  7 ----
 drivers/net/ethernet/intel/ice/ice_main.c | 47 ++---------------------
 6 files changed, 6 insertions(+), 93 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index c9104b13e1d2a..5ceeae664598c 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -475,9 +475,6 @@ struct ice_q_vector {
 	struct ice_ring_container rx;
 	struct ice_ring_container tx;
 
-	cpumask_t affinity_mask;
-	struct irq_affinity_notify affinity_notify;
-
 	struct ice_channel *ch;
 
 	char name[ICE_INT_NAME_STR_LEN];
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d16..171cdec741c2e 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -570,25 +570,6 @@ void ice_clear_arfs(struct ice_vsi *vsi)
 	vsi->arfs_fltr_cntrs = NULL;
 }
 
-/**
- * ice_free_cpu_rx_rmap - free setup CPU reverse map
- * @vsi: the VSI to be forwarded to
- */
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi)
-{
-	struct net_device *netdev;
-
-	if (!vsi || vsi->type != ICE_VSI_PF)
-		return;
-
-	netdev = vsi->netdev;
-	if (!netdev || !netdev->rx_cpu_rmap)
-		return;
-
-	free_irq_cpu_rmap(netdev->rx_cpu_rmap);
-	netdev->rx_cpu_rmap = NULL;
-}
-
 /**
  * ice_set_cpu_rx_rmap - setup CPU reverse map for each queue
  * @vsi: the VSI to be forwarded to
@@ -597,7 +578,6 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 {
 	struct net_device *netdev;
 	struct ice_pf *pf;
-	int i;
 
 	if (!vsi || vsi->type != ICE_VSI_PF)
 		return 0;
@@ -610,18 +590,7 @@ int ice_set_cpu_rx_rmap(struct ice_vsi *vsi)
 	netdev_dbg(netdev, "Setup CPU RMAP: vsi type 0x%x, ifname %s, q_vectors %d\n",
 		   vsi->type, netdev->name, vsi->num_q_vectors);
 
-	netdev->rx_cpu_rmap = alloc_irq_cpu_rmap(vsi->num_q_vectors);
-	if (unlikely(!netdev->rx_cpu_rmap))
-		return -EINVAL;
-
-	ice_for_each_q_vector(vsi, i)
-		if (irq_cpu_rmap_add(netdev->rx_cpu_rmap,
-				     vsi->q_vectors[i]->irq.virq)) {
-			ice_free_cpu_rx_rmap(vsi);
-			return -EINVAL;
-		}
-
-	return 0;
+	return netif_enable_cpu_rmap(netdev, vsi->num_q_vectors);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.h b/drivers/net/ethernet/intel/ice/ice_arfs.h
index 9669ad9bf7b54..9706293128c3b 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.h
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.h
@@ -45,7 +45,6 @@ int
 ice_rx_flow_steer(struct net_device *netdev, const struct sk_buff *skb,
 		  u16 rxq_idx, u32 flow_id);
 void ice_clear_arfs(struct ice_vsi *vsi);
-void ice_free_cpu_rx_rmap(struct ice_vsi *vsi);
 void ice_init_arfs(struct ice_vsi *vsi);
 void ice_sync_arfs_fltrs(struct ice_pf *pf);
 int ice_set_cpu_rx_rmap(struct ice_vsi *vsi);
@@ -56,7 +55,6 @@ ice_is_arfs_using_perfect_flow(struct ice_hw *hw,
 			       enum ice_fltr_ptype flow_type);
 #else
 static inline void ice_clear_arfs(struct ice_vsi *vsi) { }
-static inline void ice_free_cpu_rx_rmap(struct ice_vsi *vsi) { }
 static inline void ice_init_arfs(struct ice_vsi *vsi) { }
 static inline void ice_sync_arfs_fltrs(struct ice_pf *pf) { }
 static inline void ice_remove_arfs(struct ice_pf *pf) { }
diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index b3234a55a2532..6db4ad8fc70b0 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -147,10 +147,6 @@ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, u16 v_idx)
 	q_vector->reg_idx = q_vector->irq.index;
 	q_vector->vf_reg_idx = q_vector->irq.index;
 
-	/* only set affinity_mask if the CPU is online */
-	if (cpu_online(v_idx))
-		cpumask_set_cpu(v_idx, &q_vector->affinity_mask);
-
 	/* This will not be called in the driver load path because the netdev
 	 * will not be created yet. All other cases with register the NAPI
 	 * handler here (i.e. resume, reset/rebuild, etc.)
@@ -276,7 +272,8 @@ static void ice_cfg_xps_tx_ring(struct ice_tx_ring *ring)
 	if (test_and_set_bit(ICE_TX_XPS_INIT_DONE, ring->xps_state))
 		return;
 
-	netif_set_xps_queue(ring->netdev, &ring->q_vector->affinity_mask,
+	netif_set_xps_queue(ring->netdev,
+			    &ring->q_vector->napi.config->affinity_mask,
 			    ring->q_index);
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index ce30674abf8f1..715efd8a359f0 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -2592,7 +2592,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		return;
 
 	vsi->irqs_ready = false;
-	ice_free_cpu_rx_rmap(vsi);
 
 	ice_for_each_q_vector(vsi, i) {
 		int irq_num;
@@ -2605,12 +2604,6 @@ void ice_vsi_free_irq(struct ice_vsi *vsi)
 		      vsi->q_vectors[i]->num_ring_rx))
 			continue;
 
-		/* clear the affinity notifier in the IRQ descriptor */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-
-		/* clear the affinity_hint in the IRQ descriptor */
-		irq_update_affinity_hint(irq_num, NULL);
 		synchronize_irq(irq_num);
 		devm_free_irq(ice_pf_to_dev(pf), irq_num, vsi->q_vectors[i]);
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index b084839eb8113..eff4afabeef61 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -2527,34 +2527,6 @@ int ice_schedule_reset(struct ice_pf *pf, enum ice_reset_req reset)
 	return 0;
 }
 
-/**
- * ice_irq_affinity_notify - Callback for affinity changes
- * @notify: context as to what irq was changed
- * @mask: the new affinity mask
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * so that we may register to receive changes to the irq affinity masks.
- */
-static void
-ice_irq_affinity_notify(struct irq_affinity_notify *notify,
-			const cpumask_t *mask)
-{
-	struct ice_q_vector *q_vector =
-		container_of(notify, struct ice_q_vector, affinity_notify);
-
-	cpumask_copy(&q_vector->affinity_mask, mask);
-}
-
-/**
- * ice_irq_affinity_release - Callback for affinity notifier release
- * @ref: internal core kernel usage
- *
- * This is a callback function used by the irq_set_affinity_notifier function
- * to inform the current notification subscriber that they will no longer
- * receive notifications.
- */
-static void ice_irq_affinity_release(struct kref __always_unused *ref) {}
-
 /**
  * ice_vsi_ena_irq - Enable IRQ for the given VSI
  * @vsi: the VSI being configured
@@ -2618,19 +2590,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 				   err);
 			goto free_q_irqs;
 		}
-
-		/* register for affinity change notifications */
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL)) {
-			struct irq_affinity_notify *affinity_notify;
-
-			affinity_notify = &q_vector->affinity_notify;
-			affinity_notify->notify = ice_irq_affinity_notify;
-			affinity_notify->release = ice_irq_affinity_release;
-			irq_set_affinity_notifier(irq_num, affinity_notify);
-		}
-
-		/* assign the mask for this irq */
-		irq_update_affinity_hint(irq_num, &q_vector->affinity_mask);
 	}
 
 	err = ice_set_cpu_rx_rmap(vsi);
@@ -2646,9 +2605,6 @@ static int ice_vsi_req_irq_msix(struct ice_vsi *vsi, char *basename)
 free_q_irqs:
 	while (vector--) {
 		irq_num = vsi->q_vectors[vector]->irq.virq;
-		if (!IS_ENABLED(CONFIG_RFS_ACCEL))
-			irq_set_affinity_notifier(irq_num, NULL);
-		irq_update_affinity_hint(irq_num, NULL);
 		devm_free_irq(dev, irq_num, &vsi->q_vectors[vector]);
 	}
 	return err;
@@ -3675,6 +3631,9 @@ void ice_set_netdev_features(struct net_device *netdev)
 	 */
 	netdev->hw_features |= NETIF_F_RXFCS;
 
+	/* Allow core to manage IRQs affinity */
+	netif_set_affinity_auto(netdev);
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 

From deab38f8f0118615feed2cd95da5f17aa9bff7ef Mon Sep 17 00:00:00 2001
From: Ahmed Zaki <ahmed.zaki@intel.com>
Date: Mon, 24 Feb 2025 16:22:26 -0700
Subject: [PATCH 1255/2753] idpf: use napi's irq affinity

Delete the driver CPU affinity info and use the core's napi config
instead.

Signed-off-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-6-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c  |  1 +
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 22 +++++++--------------
 drivers/net/ethernet/intel/idpf/idpf_txrx.h |  6 ++----
 3 files changed, 10 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index a3d6b8f198a86..f3aea7bcdaa3b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -814,6 +814,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
 	netdev->hw_features |= dflt_features | offloads;
 	netdev->hw_enc_features |= dflt_features | offloads;
 	idpf_set_ethtool_ops(netdev);
+	netif_set_affinity_auto(netdev);
 	SET_NETDEV_DEV(netdev, &adapter->pdev->dev);
 
 	/* carrier off on init to avoid Tx hangs */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 2747dc69999aa..672dfad1fb218 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3551,8 +3551,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
 		q_vector->tx = NULL;
 		kfree(q_vector->rx);
 		q_vector->rx = NULL;
-
-		free_cpumask_var(q_vector->affinity_mask);
 	}
 
 	kfree(vport->q_vectors);
@@ -3579,8 +3577,6 @@ static void idpf_vport_intr_rel_irq(struct idpf_vport *vport)
 		vidx = vport->q_vector_idxs[vector];
 		irq_num = adapter->msix_entries[vidx].vector;
 
-		/* clear the affinity_mask in the IRQ descriptor */
-		irq_set_affinity_hint(irq_num, NULL);
 		kfree(free_irq(irq_num, q_vector));
 	}
 }
@@ -3768,8 +3764,6 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
 				   "Request_irq failed, error: %d\n", err);
 			goto free_q_irqs;
 		}
-		/* assign the mask for this irq */
-		irq_set_affinity_hint(irq_num, q_vector->affinity_mask);
 	}
 
 	return 0;
@@ -4181,7 +4175,8 @@ static int idpf_vport_intr_init_vec_idx(struct idpf_vport *vport)
 static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 {
 	int (*napi_poll)(struct napi_struct *napi, int budget);
-	u16 v_idx;
+	u16 v_idx, qv_idx;
+	int irq_num;
 
 	if (idpf_is_queue_model_split(vport->txq_model))
 		napi_poll = idpf_vport_splitq_napi_poll;
@@ -4190,12 +4185,12 @@ static void idpf_vport_intr_napi_add_all(struct idpf_vport *vport)
 
 	for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
 		struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+		qv_idx = vport->q_vector_idxs[v_idx];
+		irq_num = vport->adapter->msix_entries[qv_idx].vector;
 
-		netif_napi_add(vport->netdev, &q_vector->napi, napi_poll);
-
-		/* only set affinity_mask if the CPU is online */
-		if (cpu_online(v_idx))
-			cpumask_set_cpu(v_idx, q_vector->affinity_mask);
+		netif_napi_add_config(vport->netdev, &q_vector->napi,
+				      napi_poll, v_idx);
+		netif_napi_set_irq(&q_vector->napi, irq_num);
 	}
 }
 
@@ -4239,9 +4234,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
 		q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
 		q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
 
-		if (!zalloc_cpumask_var(&q_vector->affinity_mask, GFP_KERNEL))
-			goto error;
-
 		q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
 				       GFP_KERNEL);
 		if (!q_vector->tx)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index cd9a20c9cc7fb..b029f566e57cd 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -382,7 +382,6 @@ struct idpf_intr_reg {
  * @rx_intr_mode: Dynamic ITR or not
  * @rx_itr_idx: RX ITR index
  * @v_idx: Vector index
- * @affinity_mask: CPU affinity mask
  */
 struct idpf_q_vector {
 	__cacheline_group_begin_aligned(read_mostly);
@@ -419,13 +418,12 @@ struct idpf_q_vector {
 	__cacheline_group_begin_aligned(cold);
 	u16 v_idx;
 
-	cpumask_var_t affinity_mask;
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_q_vector, 120,
 			    24 + sizeof(struct napi_struct) +
 			    2 * sizeof(struct dim),
-			    8 + sizeof(cpumask_var_t));
+			    8);
 
 struct idpf_rx_queue_stats {
 	u64_stats_t packets;
@@ -921,7 +919,7 @@ static inline int idpf_q_vector_to_mem(const struct idpf_q_vector *q_vector)
 	if (!q_vector)
 		return NUMA_NO_NODE;
 
-	cpu = cpumask_first(q_vector->affinity_mask);
+	cpu = cpumask_first(&q_vector->napi.config->affinity_mask);
 
 	return cpu < nr_cpu_ids ? cpu_to_mem(cpu) : NUMA_NO_NODE;
 }

From 185646a8a0a88c9016a782f9b98eea0eb6078512 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 24 Feb 2025 16:22:27 -0700
Subject: [PATCH 1256/2753] selftests: drv-net: add tests for napi IRQ affinity
 notifiers

Add tests to check that the napi retained the IRQ after down/up,
multiple changes in the number of rx queues and after
attaching/releasing XDP program.

Tested on ice and idpf:

   # NETIF=<iface> tools/testing/selftests/drivers/net/hw/irq.py
    KTAP version 1
    1..4
    ok 1 irq.check_irqs_reported
    ok 2 irq.check_reconfig_queues
    ok 3 irq.check_reconfig_xdp
    ok 4 irq.check_down
    # Totals: pass:4 fail:0 xfail:0 xpass:0 skip:0 error:0

Tested-by: Ahmed Zaki <ahmed.zaki@intel.com>
Link: https://patch.msgid.link/20250224232228.990783-7-ahmed.zaki@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/drivers/net/hw/Makefile |  4 +
 tools/testing/selftests/drivers/net/hw/irq.py | 99 +++++++++++++++++++
 .../selftests/drivers/net/hw/xdp_dummy.bpf.c  | 13 +++
 .../selftests/drivers/net/lib/py/env.py       |  8 +-
 4 files changed, 123 insertions(+), 1 deletion(-)
 create mode 100755 tools/testing/selftests/drivers/net/hw/irq.py
 create mode 100644 tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c

diff --git a/tools/testing/selftests/drivers/net/hw/Makefile b/tools/testing/selftests/drivers/net/hw/Makefile
index b2be14d0cc56e..cde5814ff9a75 100644
--- a/tools/testing/selftests/drivers/net/hw/Makefile
+++ b/tools/testing/selftests/drivers/net/hw/Makefile
@@ -10,6 +10,7 @@ TEST_PROGS = \
 	ethtool_rmon.sh \
 	hw_stats_l3.sh \
 	hw_stats_l3_gre.sh \
+	irq.py \
 	loopback.sh \
 	nic_link_layer.py \
 	nic_performance.py \
@@ -34,9 +35,12 @@ TEST_INCLUDES := \
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := ncdevmem
 TEST_GEN_FILES += $(YNL_GEN_FILES)
+TEST_GEN_FILES += $(patsubst %.c,%.o,$(wildcard *.bpf.c))
 
 include ../../../lib.mk
 
 # YNL build
 YNL_GENS := ethtool netdev
 include ../../../net/ynl.mk
+
+include ../../../net/bpf.mk
diff --git a/tools/testing/selftests/drivers/net/hw/irq.py b/tools/testing/selftests/drivers/net/hw/irq.py
new file mode 100755
index 0000000000000..42ab983702458
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/irq.py
@@ -0,0 +1,99 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+
+from lib.py import ksft_run, ksft_exit
+from lib.py import ksft_ge, ksft_eq
+from lib.py import KsftSkipEx
+from lib.py import ksft_disruptive
+from lib.py import EthtoolFamily, NetdevFamily
+from lib.py import NetDrvEnv
+from lib.py import cmd, ip, defer
+
+
+def read_affinity(irq) -> str:
+    with open(f'/proc/irq/{irq}/smp_affinity', 'r') as fp:
+        return fp.read().lstrip("0,").strip()
+
+
+def write_affinity(irq, what) -> str:
+    if what != read_affinity(irq):
+        with open(f'/proc/irq/{irq}/smp_affinity', 'w') as fp:
+            fp.write(what)
+
+
+def check_irqs_reported(cfg) -> None:
+    """ Check that device reports IRQs for NAPI instances """
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    irqs = sum(['irq' in x for x in napis])
+
+    ksft_ge(irqs, 1)
+    ksft_eq(irqs, len(napis))
+
+
+def _check_reconfig(cfg, reconfig_cb) -> None:
+    napis = cfg.netnl.napi_get({"ifindex": cfg.ifindex}, dump=True)
+    for n in reversed(napis):
+        if 'irq' in n:
+            break
+    else:
+        raise KsftSkipEx(f"Device has no NAPI with IRQ attribute (#napis: {len(napis)}")
+
+    old = read_affinity(n['irq'])
+    # pick an affinity that's not the current one
+    new = "3" if old != "3" else "5"
+    write_affinity(n['irq'], new)
+    defer(write_affinity, n['irq'], old)
+
+    reconfig_cb(cfg)
+
+    ksft_eq(read_affinity(n['irq']), new, comment="IRQ affinity changed after reconfig")
+
+
+def check_reconfig_queues(cfg) -> None:
+    def reconfig(cfg) -> None:
+        channels = cfg.ethnl.channels_get({'header': {'dev-index': cfg.ifindex}})
+        if channels['combined-count'] == 0:
+            rx_type = 'rx'
+        else:
+            rx_type = 'combined'
+        cur_queue_cnt = channels[f'{rx_type}-count']
+        max_queue_cnt = channels[f'{rx_type}-max']
+
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} 1")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {max_queue_cnt}")
+        cmd(f"ethtool -L {cfg.ifname} {rx_type} {cur_queue_cnt}")
+
+    _check_reconfig(cfg, reconfig)
+
+
+def check_reconfig_xdp(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip(f"link set dev %s xdp obj %s sec xdp" %
+            (cfg.ifname, cfg.rpath("xdp_dummy.bpf.o")))
+        ip(f"link set dev %s xdp off" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+@ksft_disruptive
+def check_down(cfg) -> None:
+    def reconfig(cfg) -> None:
+        ip("link set dev %s down" % cfg.ifname)
+        ip("link set dev %s up" % cfg.ifname)
+
+    _check_reconfig(cfg, reconfig)
+
+
+def main() -> None:
+    with NetDrvEnv(__file__, nsim_test=False) as cfg:
+        cfg.ethnl = EthtoolFamily()
+        cfg.netnl = NetdevFamily()
+
+        ksft_run([check_irqs_reported, check_reconfig_queues,
+                  check_reconfig_xdp, check_down],
+                 args=(cfg, ))
+    ksft_exit()
+
+
+if __name__ == "__main__":
+    main()
diff --git a/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
new file mode 100644
index 0000000000000..d988b2e0cee84
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/hw/xdp_dummy.bpf.c
@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/drivers/net/lib/py/env.py b/tools/testing/selftests/drivers/net/lib/py/env.py
index 96b33b5ef9dd4..fd4d674e6c72e 100644
--- a/tools/testing/selftests/drivers/net/lib/py/env.py
+++ b/tools/testing/selftests/drivers/net/lib/py/env.py
@@ -58,14 +58,20 @@ class NetDrvEnv(NetDrvEnvBase):
     """
     Class for a single NIC / host env, with no remote end
     """
-    def __init__(self, src_path, **kwargs):
+    def __init__(self, src_path, nsim_test=None, **kwargs):
         super().__init__(src_path)
 
         self._ns = None
 
         if 'NETIF' in self.env:
+            if nsim_test is True:
+                raise KsftXfailEx("Test only works on netdevsim")
+
             self.dev = ip("-d link show dev " + self.env['NETIF'], json=True)[0]
         else:
+            if nsim_test is False:
+                raise KsftXfailEx("Test does not work on netdevsim")
+
             self._ns = NetdevSimDev(**kwargs)
             self.dev = self._ns.nsims[0].dev
         self.ifname = self.dev['ifname']

From 9e9877bd82a8073fe73e110ce4868e51adba701f Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Thu, 20 Feb 2025 14:23:44 +0800
Subject: [PATCH 1257/2753] wifi: rtw89: add support for HW TKIP crypto

For 8852BTE, 8852CE, and 8922AE, TKIP encryption and decryption
will be handled by hardware. All other chips will retain their
existing software-based encryption and decryption.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250220062344.15836-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/cam.c       | 6 ++++++
 drivers/net/wireless/realtek/rtw89/core.h      | 1 +
 drivers/net/wireless/realtek/rtw89/mac_be.c    | 4 ++--
 drivers/net/wireless/realtek/rtw89/rtw8851b.c  | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c  | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c  | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852bt.c | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c  | 1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c  | 1 +
 9 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/cam.c b/drivers/net/wireless/realtek/rtw89/cam.c
index 8fa1e6c1ce139..eca3d767ff603 100644
--- a/drivers/net/wireless/realtek/rtw89/cam.c
+++ b/drivers/net/wireless/realtek/rtw89/cam.c
@@ -476,6 +476,12 @@ int rtw89_cam_sec_key_add(struct rtw89_dev *rtwdev,
 	case WLAN_CIPHER_SUITE_WEP104:
 		hw_key_type = RTW89_SEC_KEY_TYPE_WEP104;
 		break;
+	case WLAN_CIPHER_SUITE_TKIP:
+		if (!chip->hw_tkip_crypto)
+			return -EOPNOTSUPP;
+		hw_key_type = RTW89_SEC_KEY_TYPE_TKIP;
+		key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIC;
+		break;
 	case WLAN_CIPHER_SUITE_CCMP:
 		hw_key_type = RTW89_SEC_KEY_TYPE_CCMP128;
 		if (!chip->hw_mgmt_tx_encrypt)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 865cdcfa59e1d..3d458dbbdd002 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4285,6 +4285,7 @@ struct rtw89_chip_info {
 	bool ul_tb_pwr_diff;
 	bool hw_sec_hdr;
 	bool hw_mgmt_tx_encrypt;
+	bool hw_tkip_crypto;
 	u8 rf_path_num;
 	u8 tx_nss;
 	u8 rx_nss;
diff --git a/drivers/net/wireless/realtek/rtw89/mac_be.c b/drivers/net/wireless/realtek/rtw89/mac_be.c
index dce0a4b01440e..99b82dc85ea38 100644
--- a/drivers/net/wireless/realtek/rtw89/mac_be.c
+++ b/drivers/net/wireless/realtek/rtw89/mac_be.c
@@ -708,8 +708,8 @@ static int sec_eng_init_be(struct rtw89_dev *rtwdev)
 	val32 |= B_BE_CLK_EN_CGCMP | B_BE_CLK_EN_WAPI | B_BE_CLK_EN_WEP_TKIP |
 		 B_BE_SEC_TX_ENC | B_BE_SEC_RX_DEC |
 		 B_BE_MC_DEC | B_BE_BC_DEC |
-		 B_BE_BMC_MGNT_DEC | B_BE_UC_MGNT_DEC;
-	val32 &= ~B_BE_SEC_PRE_ENQUE_TX;
+		 B_BE_BMC_MGNT_DEC | B_BE_UC_MGNT_DEC |
+		 B_BE_SEC_PRE_ENQUE_TX;
 	rtw89_write32(rtwdev, R_BE_SEC_ENG_CTRL, val32);
 
 	rtw89_write32_set(rtwdev, R_BE_SEC_MPDU_PROC, B_BE_APPEND_ICV | B_BE_APPEND_MIC);
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 3cd1d7a4d202c..34f2278ddf201 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2502,6 +2502,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
+	.hw_tkip_crypto		= false,
 	.rf_path_num		= 1,
 	.tx_nss			= 1,
 	.rx_nss			= 1,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 514ef0c2b32b7..66d85c04da263 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2220,6 +2220,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
+	.hw_tkip_crypto		= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 5dbb33d5e4038..7650576f0577b 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -856,6 +856,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
+	.hw_tkip_crypto		= false,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index b4832c7897a86..c96ef0dfbae27 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -789,6 +789,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt     = false,
+	.hw_tkip_crypto		= true,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index f3965a65ae18c..7ba92bf898e31 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -3015,6 +3015,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.ul_tb_pwr_diff		= true,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
+	.hw_tkip_crypto		= true,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index defa6cf9f7f0b..157685c1b6864 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2774,6 +2774,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.ul_tb_pwr_diff		= false,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
+	.hw_tkip_crypto		= true,
 	.rf_path_num		= 2,
 	.tx_nss			= 2,
 	.rx_nss			= 2,

From e16acf907a3c66b9996a5df43e177a5edec8e0a5 Mon Sep 17 00:00:00 2001
From: Chih-Kang Chang <gary.chang@realtek.com>
Date: Thu, 20 Feb 2025 14:43:57 +0800
Subject: [PATCH 1258/2753] wifi: rtw89: Parse channel from IE to correct
 invalid hardware reports during scanning

For some packets, we could not get channel information from PPDU status.
And this causes wrong frequencies being reported. Parse the channel
information from IE if provided by AP to fix this.

Signed-off-by: Chih-Kang Chang <gary.chang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250220064357.17962-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.c     | 44 +++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/core.h     |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |  1 +
 .../net/wireless/realtek/rtw89/rtw8852bt.c    |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |  1 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |  1 +
 8 files changed, 51 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 8d5dc22fb5080..4d286182e21d6 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -2382,6 +2382,49 @@ static void rtw89_core_validate_rx_signal(struct ieee80211_rx_status *rx_status)
 		rx_status->flag |= RX_FLAG_NO_SIGNAL_VAL;
 }
 
+static void rtw89_core_update_rx_freq_from_ie(struct rtw89_dev *rtwdev,
+					      struct sk_buff *skb,
+					      struct ieee80211_rx_status *rx_status)
+{
+	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data;
+	size_t hdr_len, ielen;
+	u8 *variable;
+	int chan;
+
+	if (!rtwdev->chip->rx_freq_frome_ie)
+		return;
+
+	if (!rtwdev->scanning)
+		return;
+
+	if (ieee80211_is_beacon(mgmt->frame_control)) {
+		variable = mgmt->u.beacon.variable;
+		hdr_len = offsetof(struct ieee80211_mgmt,
+				   u.beacon.variable);
+	} else if (ieee80211_is_probe_resp(mgmt->frame_control)) {
+		variable = mgmt->u.probe_resp.variable;
+		hdr_len = offsetof(struct ieee80211_mgmt,
+				   u.probe_resp.variable);
+	} else {
+		return;
+	}
+
+	if (skb->len > hdr_len)
+		ielen = skb->len - hdr_len;
+	else
+		return;
+
+	/* The parsing code for both 2GHz and 5GHz bands is the same in this
+	 * function.
+	 */
+	chan = cfg80211_get_ies_channel_number(variable, ielen, NL80211_BAND_2GHZ);
+	if (chan == -1)
+		return;
+
+	rx_status->band = chan > 14 ? RTW89_BAND_5G : RTW89_BAND_2G;
+	rx_status->freq = ieee80211_channel_to_frequency(chan, rx_status->band);
+}
+
 static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev,
 				      struct rtw89_rx_phy_ppdu *phy_ppdu,
 				      struct rtw89_rx_desc_info *desc_info,
@@ -2399,6 +2442,7 @@ static void rtw89_core_rx_to_mac80211(struct rtw89_dev *rtwdev,
 	rtw89_core_update_rx_status_by_ppdu(rtwdev, rx_status, phy_ppdu);
 	rtw89_core_update_radiotap(rtwdev, skb_ppdu, rx_status);
 	rtw89_core_validate_rx_signal(rx_status);
+	rtw89_core_update_rx_freq_from_ie(rtwdev, skb_ppdu, rx_status);
 
 	/* In low power mode, it does RX in thread context. */
 	local_bh_disable();
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 3d458dbbdd002..3f62df657e1fd 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4283,6 +4283,7 @@ struct rtw89_chip_info {
 	bool support_ant_gain;
 	bool ul_tb_waveform_ctrl;
 	bool ul_tb_pwr_diff;
+	bool rx_freq_frome_ie;
 	bool hw_sec_hdr;
 	bool hw_mgmt_tx_encrypt;
 	bool hw_tkip_crypto;
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index 34f2278ddf201..b709dd71b06a2 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2500,6 +2500,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 	.support_ant_gain	= false,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
+	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 66d85c04da263..638236bffebb5 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2218,6 +2218,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 	.support_ant_gain	= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
+	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 7650576f0577b..8bec74716f84a 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -854,6 +854,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 	.support_ant_gain	= true,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
+	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt	= false,
 	.hw_tkip_crypto		= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index c96ef0dfbae27..e628106600054 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -787,6 +787,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 	.support_ant_gain	= true,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
+	.rx_freq_frome_ie	= true,
 	.hw_sec_hdr		= false,
 	.hw_mgmt_tx_encrypt     = false,
 	.hw_tkip_crypto		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 7ba92bf898e31..5d3e105dc87fc 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -3013,6 +3013,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 	.support_ant_gain	= true,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= true,
+	.rx_freq_frome_ie	= false,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
 	.hw_tkip_crypto		= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 157685c1b6864..210fa818ffe8f 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2772,6 +2772,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 	.support_ant_gain	= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
+	.rx_freq_frome_ie	= false,
 	.hw_sec_hdr		= true,
 	.hw_mgmt_tx_encrypt	= true,
 	.hw_tkip_crypto		= true,

From e521f516716de7895acd1b5b7fac788214a390b9 Mon Sep 17 00:00:00 2001
From: Caleb Connolly <caleb.connolly@linaro.org>
Date: Sat, 8 Feb 2025 22:30:54 +0000
Subject: [PATCH 1259/2753] dmaengine: Revert "dmaengine: qcom: bam_dma: Avoid
 writing unavailable register"

This commit causes a hard crash on sdm845 and likely other platforms.
Revert it until a proper fix is found.

This reverts commit 57a7138d0627: ("dmaengine: qcom: bam_dma: Avoid writing
unavailable register")

Signed-off-by: Caleb Connolly <caleb.connolly@linaro.org>
Fixes: 57a7138d0627 ("dmaengine: qcom: bam_dma: Avoid writing unavailable register")
Tested-by: Neil Armstrong <neil.armstrong@linaro.org> # on sdm845-DB845c
Tested-by: David Heidelberg <david@ixit.cz>
Link: https://lore.kernel.org/r/20250208223112.142567-1-caleb.connolly@linaro.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/qcom/bam_dma.c | 24 ++++++++----------------
 1 file changed, 8 insertions(+), 16 deletions(-)

diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c
index c14557efd5770..bbc3276992bb0 100644
--- a/drivers/dma/qcom/bam_dma.c
+++ b/drivers/dma/qcom/bam_dma.c
@@ -59,9 +59,6 @@ struct bam_desc_hw {
 #define DESC_FLAG_NWD BIT(12)
 #define DESC_FLAG_CMD BIT(11)
 
-#define BAM_NDP_REVISION_START	0x20
-#define BAM_NDP_REVISION_END	0x27
-
 struct bam_async_desc {
 	struct virt_dma_desc vd;
 
@@ -401,7 +398,6 @@ struct bam_device {
 
 	/* dma start transaction tasklet */
 	struct tasklet_struct task;
-	u32 bam_revision;
 };
 
 /**
@@ -445,10 +441,8 @@ static void bam_reset(struct bam_device *bdev)
 	writel_relaxed(val, bam_addr(bdev, 0, BAM_CTRL));
 
 	/* set descriptor threshold, start with 4 bytes */
-	if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
-		     BAM_NDP_REVISION_END))
-		writel_relaxed(DEFAULT_CNT_THRSHLD,
-			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+	writel_relaxed(DEFAULT_CNT_THRSHLD,
+			bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 
 	/* Enable default set of h/w workarounds, ie all except BAM_FULL_PIPE */
 	writel_relaxed(BAM_CNFG_BITS_DEFAULT, bam_addr(bdev, 0, BAM_CNFG_BITS));
@@ -1006,10 +1000,9 @@ static void bam_apply_new_config(struct bam_chan *bchan,
 			maxburst = bchan->slave.src_maxburst;
 		else
 			maxburst = bchan->slave.dst_maxburst;
-		if (in_range(bdev->bam_revision, BAM_NDP_REVISION_START,
-			     BAM_NDP_REVISION_END))
-			writel_relaxed(maxburst,
-				       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
+
+		writel_relaxed(maxburst,
+			       bam_addr(bdev, 0, BAM_DESC_CNT_TRSHLD));
 	}
 
 	bchan->reconfigure = 0;
@@ -1199,11 +1192,10 @@ static int bam_init(struct bam_device *bdev)
 	u32 val;
 
 	/* read revision and configuration information */
-	val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
-	if (!bdev->num_ees)
+	if (!bdev->num_ees) {
+		val = readl_relaxed(bam_addr(bdev, 0, BAM_REVISION));
 		bdev->num_ees = (val >> NUM_EES_SHIFT) & NUM_EES_MASK;
-
-	bdev->bam_revision = val & REVISION_MASK;
+	}
 
 	/* check that configured EE is within range */
 	if (bdev->ee >= bdev->num_ees)

From 3603996432997f7c88da37a97062a46cda01ac9d Mon Sep 17 00:00:00 2001
From: Thomas Zimmermann <tzimmermann@suse.de>
Date: Wed, 11 Dec 2024 10:06:28 +0100
Subject: [PATCH 1260/2753] drm/fbdev-dma: Add shadow buffering for deferred
 I/O
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DMA areas are not necessarily backed by struct page, so we cannot
rely on it for deferred I/O. Allocate a shadow buffer for drivers
that require deferred I/O and use it as framebuffer memory.

Fixes driver errors about being "Unable to handle kernel NULL pointer
dereference at virtual address" or "Unable to handle kernel paging
request at virtual address".

The patch splits drm_fbdev_dma_driver_fbdev_probe() in an initial
allocation, which creates the DMA-backed buffer object, and a tail
that sets up the fbdev data structures. There is a tail function for
direct memory mappings and a tail function for deferred I/O with
the shadow buffer.

It is no longer possible to use deferred I/O without shadow buffer.
It can be re-added if there exists a reliably test for usable struct
page in the allocated DMA-backed buffer object.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Reported-by: Nuno Gonçalves <nunojpg@gmail.com>
CLoses: https://lore.kernel.org/dri-devel/CAEXMXLR55DziAMbv_+2hmLeH-jP96pmit6nhs6siB22cpQFr9w@mail.gmail.com/
Tested-by: Nuno Gonçalves <nunojpg@gmail.com>
Fixes: 5ab91447aa13 ("drm/tiny/ili9225: Use fbdev-dma")
Cc: Thomas Zimmermann <tzimmermann@suse.de>
Cc: <stable@vger.kernel.org> # v6.11+
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241211090643.74250-1-tzimmermann@suse.de
---
 drivers/gpu/drm/drm_fbdev_dma.c | 217 +++++++++++++++++++++++---------
 1 file changed, 155 insertions(+), 62 deletions(-)

diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
index b14b581c059d3..02a516e771927 100644
--- a/drivers/gpu/drm/drm_fbdev_dma.c
+++ b/drivers/gpu/drm/drm_fbdev_dma.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: MIT
 
 #include <linux/fb.h>
+#include <linux/vmalloc.h>
 
 #include <drm/drm_drv.h>
 #include <drm/drm_fbdev_dma.h>
@@ -70,37 +71,102 @@ static const struct fb_ops drm_fbdev_dma_fb_ops = {
 	.fb_destroy = drm_fbdev_dma_fb_destroy,
 };
 
-FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma,
+FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(drm_fbdev_dma_shadowed,
 				   drm_fb_helper_damage_range,
 				   drm_fb_helper_damage_area);
 
-static int drm_fbdev_dma_deferred_fb_mmap(struct fb_info *info, struct vm_area_struct *vma)
+static void drm_fbdev_dma_shadowed_fb_destroy(struct fb_info *info)
 {
 	struct drm_fb_helper *fb_helper = info->par;
-	struct drm_framebuffer *fb = fb_helper->fb;
-	struct drm_gem_dma_object *dma = drm_fb_dma_get_gem_obj(fb, 0);
+	void *shadow = info->screen_buffer;
+
+	if (!fb_helper->dev)
+		return;
 
-	if (!dma->map_noncoherent)
-		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
+	if (info->fbdefio)
+		fb_deferred_io_cleanup(info);
+	drm_fb_helper_fini(fb_helper);
+	vfree(shadow);
 
-	return fb_deferred_io_mmap(info, vma);
+	drm_client_buffer_vunmap(fb_helper->buffer);
+	drm_client_framebuffer_delete(fb_helper->buffer);
+	drm_client_release(&fb_helper->client);
+	drm_fb_helper_unprepare(fb_helper);
+	kfree(fb_helper);
 }
 
-static const struct fb_ops drm_fbdev_dma_deferred_fb_ops = {
+static const struct fb_ops drm_fbdev_dma_shadowed_fb_ops = {
 	.owner = THIS_MODULE,
 	.fb_open = drm_fbdev_dma_fb_open,
 	.fb_release = drm_fbdev_dma_fb_release,
-	__FB_DEFAULT_DEFERRED_OPS_RDWR(drm_fbdev_dma),
+	FB_DEFAULT_DEFERRED_OPS(drm_fbdev_dma_shadowed),
 	DRM_FB_HELPER_DEFAULT_OPS,
-	__FB_DEFAULT_DEFERRED_OPS_DRAW(drm_fbdev_dma),
-	.fb_mmap = drm_fbdev_dma_deferred_fb_mmap,
-	.fb_destroy = drm_fbdev_dma_fb_destroy,
+	.fb_destroy = drm_fbdev_dma_shadowed_fb_destroy,
 };
 
 /*
  * struct drm_fb_helper
  */
 
+static void drm_fbdev_dma_damage_blit_real(struct drm_fb_helper *fb_helper,
+					   struct drm_clip_rect *clip,
+					   struct iosys_map *dst)
+{
+	struct drm_framebuffer *fb = fb_helper->fb;
+	size_t offset = clip->y1 * fb->pitches[0];
+	size_t len = clip->x2 - clip->x1;
+	unsigned int y;
+	void *src;
+
+	switch (drm_format_info_bpp(fb->format, 0)) {
+	case 1:
+		offset += clip->x1 / 8;
+		len = DIV_ROUND_UP(len + clip->x1 % 8, 8);
+		break;
+	case 2:
+		offset += clip->x1 / 4;
+		len = DIV_ROUND_UP(len + clip->x1 % 4, 4);
+		break;
+	case 4:
+		offset += clip->x1 / 2;
+		len = DIV_ROUND_UP(len + clip->x1 % 2, 2);
+		break;
+	default:
+		offset += clip->x1 * fb->format->cpp[0];
+		len *= fb->format->cpp[0];
+		break;
+	}
+
+	src = fb_helper->info->screen_buffer + offset;
+	iosys_map_incr(dst, offset); /* go to first pixel within clip rect */
+
+	for (y = clip->y1; y < clip->y2; y++) {
+		iosys_map_memcpy_to(dst, 0, src, len);
+		iosys_map_incr(dst, fb->pitches[0]);
+		src += fb->pitches[0];
+	}
+}
+
+static int drm_fbdev_dma_damage_blit(struct drm_fb_helper *fb_helper,
+				     struct drm_clip_rect *clip)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct iosys_map dst;
+
+	/*
+	 * For fbdev emulation, we only have to protect against fbdev modeset
+	 * operations. Nothing else will involve the client buffer's BO. So it
+	 * is sufficient to acquire struct drm_fb_helper.lock here.
+	 */
+	mutex_lock(&fb_helper->lock);
+
+	dst = buffer->map;
+	drm_fbdev_dma_damage_blit_real(fb_helper, clip, &dst);
+
+	mutex_unlock(&fb_helper->lock);
+
+	return 0;
+}
 static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
 					 struct drm_clip_rect *clip)
 {
@@ -112,6 +178,10 @@ static int drm_fbdev_dma_helper_fb_dirty(struct drm_fb_helper *helper,
 		return 0;
 
 	if (helper->fb->funcs->dirty) {
+		ret = drm_fbdev_dma_damage_blit(helper, clip);
+		if (drm_WARN_ONCE(dev, ret, "Damage blitter failed: ret=%d\n", ret))
+			return ret;
+
 		ret = helper->fb->funcs->dirty(helper->fb, NULL, 0, 0, clip, 1);
 		if (drm_WARN_ONCE(dev, ret, "Dirty helper failed: ret=%d\n", ret))
 			return ret;
@@ -128,14 +198,80 @@ static const struct drm_fb_helper_funcs drm_fbdev_dma_helper_funcs = {
  * struct drm_fb_helper
  */
 
+static int drm_fbdev_dma_driver_fbdev_probe_tail(struct drm_fb_helper *fb_helper,
+						 struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_device *dev = fb_helper->dev;
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct drm_gem_dma_object *dma_obj = to_drm_gem_dma_obj(buffer->gem);
+	struct drm_framebuffer *fb = fb_helper->fb;
+	struct fb_info *info = fb_helper->info;
+	struct iosys_map map = buffer->map;
+
+	info->fbops = &drm_fbdev_dma_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	if (dma_obj->map_noncoherent)
+		info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_size = sizes->surface_height * fb->pitches[0];
+	info->screen_buffer = map.vaddr;
+	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
+		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
+			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
+	}
+	info->fix.smem_len = info->screen_size;
+
+	return 0;
+}
+
+static int drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(struct drm_fb_helper *fb_helper,
+							  struct drm_fb_helper_surface_size *sizes)
+{
+	struct drm_client_buffer *buffer = fb_helper->buffer;
+	struct fb_info *info = fb_helper->info;
+	size_t screen_size = buffer->gem->size;
+	void *screen_buffer;
+	int ret;
+
+	/*
+	 * Deferred I/O requires struct page for framebuffer memory,
+	 * which is not guaranteed for all DMA ranges. We thus create
+	 * a shadow buffer in system memory.
+	 */
+	screen_buffer = vzalloc(screen_size);
+	if (!screen_buffer)
+		return -ENOMEM;
+
+	info->fbops = &drm_fbdev_dma_shadowed_fb_ops;
+
+	/* screen */
+	info->flags |= FBINFO_VIRTFB; /* system memory */
+	info->flags |= FBINFO_READS_FAST; /* signal caching */
+	info->screen_buffer = screen_buffer;
+	info->fix.smem_len = screen_size;
+
+	fb_helper->fbdefio.delay = HZ / 20;
+	fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
+
+	info->fbdefio = &fb_helper->fbdefio;
+	ret = fb_deferred_io_init(info);
+	if (ret)
+		goto err_vfree;
+
+	return 0;
+
+err_vfree:
+	vfree(screen_buffer);
+	return ret;
+}
+
 int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 				     struct drm_fb_helper_surface_size *sizes)
 {
 	struct drm_client_dev *client = &fb_helper->client;
 	struct drm_device *dev = fb_helper->dev;
-	bool use_deferred_io = false;
 	struct drm_client_buffer *buffer;
-	struct drm_gem_dma_object *dma_obj;
 	struct drm_framebuffer *fb;
 	struct fb_info *info;
 	u32 format;
@@ -152,19 +288,9 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 					       sizes->surface_height, format);
 	if (IS_ERR(buffer))
 		return PTR_ERR(buffer);
-	dma_obj = to_drm_gem_dma_obj(buffer->gem);
 
 	fb = buffer->fb;
 
-	/*
-	 * Deferred I/O requires struct page for framebuffer memory,
-	 * which is not guaranteed for all DMA ranges. We thus only
-	 * install deferred I/O if we have a framebuffer that requires
-	 * it.
-	 */
-	if (fb->funcs->dirty)
-		use_deferred_io = true;
-
 	ret = drm_client_buffer_vmap(buffer, &map);
 	if (ret) {
 		goto err_drm_client_buffer_delete;
@@ -185,45 +311,12 @@ int drm_fbdev_dma_driver_fbdev_probe(struct drm_fb_helper *fb_helper,
 
 	drm_fb_helper_fill_info(info, fb_helper, sizes);
 
-	if (use_deferred_io)
-		info->fbops = &drm_fbdev_dma_deferred_fb_ops;
+	if (fb->funcs->dirty)
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail_shadowed(fb_helper, sizes);
 	else
-		info->fbops = &drm_fbdev_dma_fb_ops;
-
-	/* screen */
-	info->flags |= FBINFO_VIRTFB; /* system memory */
-	if (dma_obj->map_noncoherent)
-		info->flags |= FBINFO_READS_FAST; /* signal caching */
-	info->screen_size = sizes->surface_height * fb->pitches[0];
-	info->screen_buffer = map.vaddr;
-	if (!(info->flags & FBINFO_HIDE_SMEM_START)) {
-		if (!drm_WARN_ON(dev, is_vmalloc_addr(info->screen_buffer)))
-			info->fix.smem_start = page_to_phys(virt_to_page(info->screen_buffer));
-	}
-	info->fix.smem_len = info->screen_size;
-
-	/*
-	 * Only set up deferred I/O if the screen buffer supports
-	 * it. If this disagrees with the previous test for ->dirty,
-	 * mmap on the /dev/fb file might not work correctly.
-	 */
-	if (!is_vmalloc_addr(info->screen_buffer) && info->fix.smem_start) {
-		unsigned long pfn = info->fix.smem_start >> PAGE_SHIFT;
-
-		if (drm_WARN_ON(dev, !pfn_to_page(pfn)))
-			use_deferred_io = false;
-	}
-
-	/* deferred I/O */
-	if (use_deferred_io) {
-		fb_helper->fbdefio.delay = HZ / 20;
-		fb_helper->fbdefio.deferred_io = drm_fb_helper_deferred_io;
-
-		info->fbdefio = &fb_helper->fbdefio;
-		ret = fb_deferred_io_init(info);
-		if (ret)
-			goto err_drm_fb_helper_release_info;
-	}
+		ret = drm_fbdev_dma_driver_fbdev_probe_tail(fb_helper, sizes);
+	if (ret)
+		goto err_drm_fb_helper_release_info;
 
 	return 0;
 

From 6d48ad04075729519f6baaa1dc9e5a3a39d05f53 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Wed, 26 Feb 2025 21:28:41 +0800
Subject: [PATCH 1261/2753] MIPS: Ignore relocs against __ex_table for
 relocatable kernel

Since commit 6f2c2f93a190 ("scripts/sorttable: Remove unneeded
Elf_Rel"), sorttable no longer clears relocs against __ex_table,
claiming "it was never used."  But in fact MIPS relocatable kernel had
been implicitly depending on this behavior, so after this commit the
MIPS relocatable kernel has started to spit oops like:

	CPU 1 Unable to handle kernel paging request at virtual address 000000fffbbdbff8, epc == ffffffff818f9a6c, ra == ffffffff813ad7d0
	... ...
	Call Trace:
	[<ffffffff818f9a6c>] __raw_copy_from_user+0x48/0x2fc
	[<ffffffff813ad7d0>] cp_statx+0x1a0/0x1e0
	[<ffffffff813ae528>] do_statx_fd+0xa8/0x118
	[<ffffffff813ae670>] sys_statx+0xd8/0xf8
	[<ffffffff81156cc8>] syscall_common+0x34/0x58

So ignore those relocs on our own to fix the issue.

Fixes: 6f2c2f93a190 ("scripts/sorttable: Remove unneeded Elf_Rel")
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 arch/mips/boot/tools/relocs.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/arch/mips/boot/tools/relocs.c b/arch/mips/boot/tools/relocs.c
index a88d66c46d7f7..9863e1d5c62e3 100644
--- a/arch/mips/boot/tools/relocs.c
+++ b/arch/mips/boot/tools/relocs.c
@@ -468,6 +468,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 			Elf_Sym *sym, const char *symname))
 {
 	int i;
+	struct section *extab_sec = sec_lookup("__ex_table");
+	int extab_index = extab_sec ? extab_sec - secs : -1;
 
 	/* Walk through the relocations */
 	for (i = 0; i < ehdr.e_shnum; i++) {
@@ -480,6 +482,9 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
 		if (sec->shdr.sh_type != SHT_REL_TYPE)
 			continue;
 
+		if (sec->shdr.sh_info == extab_index)
+			continue;
+
 		sec_symtab  = sec->link;
 		sec_applies = &secs[sec->shdr.sh_info];
 		if (!(sec_applies->shdr.sh_flags & SHF_ALLOC))

From fc20737d8b85691ecabab3739ed7d06c9b7bc00f Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Wed, 26 Feb 2025 16:48:26 -0500
Subject: [PATCH 1262/2753] efivarfs: allow creation of zero length files

Temporarily allow the creation of zero length files in efivarfs so the
'fwupd' user space firmware update tool can continue to operate. This
hack should be reverted as soon as the fwupd mechanisms for updating
firmware have been fixed.

fwupd has been coded to open a firmware file, close it, remove the
immutable bit and write to it.  Since commit 908af31f4896 ("efivarfs:
fix error on write to new variable leaving remnants") this behaviour
results in the first close removing the file which causes the second
write to fail.  To allow fwupd to keep working code up an indicator of
size 1 if a write fails and only remove the file on that condition (so
create at zero size is allowed).

Tested-by: Richard Hughes <richard@hughsie.com>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
[ardb: replace LVFS with fwupd, as suggested by Richard]
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/file.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/efivarfs/file.c b/fs/efivarfs/file.c
index cb1b6d0c34545..c294a8fc566da 100644
--- a/fs/efivarfs/file.c
+++ b/fs/efivarfs/file.c
@@ -57,10 +57,11 @@ static ssize_t efivarfs_file_write(struct file *file,
 
 	if (bytes == -ENOENT) {
 		/*
-		 * zero size signals to release that the write deleted
-		 * the variable
+		 * FIXME: temporary workaround for fwupdate, signal
+		 * failed write with a 1 to keep created but not
+		 * written files
 		 */
-		i_size_write(inode, 0);
+		i_size_write(inode, 1);
 	} else {
 		i_size_write(inode, datasize + sizeof(attributes));
 		inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
@@ -124,7 +125,8 @@ static int efivarfs_file_release(struct inode *inode, struct file *file)
 	struct efivar_entry *var = inode->i_private;
 
 	inode_lock(inode);
-	var->removed = (--var->open_count == 0 && i_size_read(inode) == 0);
+	/* FIXME: temporary work around for fwupdate */
+	var->removed = (--var->open_count == 0 && i_size_read(inode) == 1);
 	inode_unlock(inode);
 
 	if (var->removed)

From 1cf9631d836b289bd5490776551961c883ae8a4f Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Mon, 24 Feb 2025 20:29:17 +0300
Subject: [PATCH 1263/2753] usbnet: gl620a: fix endpoint checking in
 genelink_bind()

Syzbot reports [1] a warning in usb_submit_urb() triggered by
inconsistencies between expected and actually present endpoints
in gl620a driver. Since genelink_bind() does not properly
verify whether specified eps are in fact provided by the device,
in this case, an artificially manufactured one, one may get a
mismatch.

Fix the issue by resorting to a usbnet utility function
usbnet_get_endpoints(), usually reserved for this very problem.
Check for endpoints and return early before proceeding further if
any are missing.

[1] Syzbot report:
usb 5-1: Manufacturer: syz
usb 5-1: SerialNumber: syz
usb 5-1: config 0 descriptor??
gl620a 5-1:0.23 usb0: register 'gl620a' at usb-dummy_hcd.0-1, ...
------------[ cut here ]------------
usb 5-1: BOGUS urb xfer, pipe 3 != type 1
WARNING: CPU: 2 PID: 1841 at drivers/usb/core/urb.c:503 usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503
Modules linked in:
CPU: 2 UID: 0 PID: 1841 Comm: kworker/2:2 Not tainted 6.12.0-syzkaller-07834-g06afb0f36106 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Workqueue: mld mld_ifc_work
RIP: 0010:usb_submit_urb+0xe4b/0x1730 drivers/usb/core/urb.c:503
...
Call Trace:
 <TASK>
 usbnet_start_xmit+0x6be/0x2780 drivers/net/usb/usbnet.c:1467
 __netdev_start_xmit include/linux/netdevice.h:5002 [inline]
 netdev_start_xmit include/linux/netdevice.h:5011 [inline]
 xmit_one net/core/dev.c:3590 [inline]
 dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3606
 sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343
 __dev_xmit_skb net/core/dev.c:3827 [inline]
 __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4400
 dev_queue_xmit include/linux/netdevice.h:3168 [inline]
 neigh_resolve_output net/core/neighbour.c:1514 [inline]
 neigh_resolve_output+0x5bc/0x950 net/core/neighbour.c:1494
 neigh_output include/net/neighbour.h:539 [inline]
 ip6_finish_output2+0xb1b/0x2070 net/ipv6/ip6_output.c:141
 __ip6_finish_output net/ipv6/ip6_output.c:215 [inline]
 ip6_finish_output+0x3f9/0x1360 net/ipv6/ip6_output.c:226
 NF_HOOK_COND include/linux/netfilter.h:303 [inline]
 ip6_output+0x1f8/0x540 net/ipv6/ip6_output.c:247
 dst_output include/net/dst.h:450 [inline]
 NF_HOOK include/linux/netfilter.h:314 [inline]
 NF_HOOK include/linux/netfilter.h:308 [inline]
 mld_sendpack+0x9f0/0x11d0 net/ipv6/mcast.c:1819
 mld_send_cr net/ipv6/mcast.c:2120 [inline]
 mld_ifc_work+0x740/0xca0 net/ipv6/mcast.c:2651
 process_one_work+0x9c5/0x1ba0 kernel/workqueue.c:3229
 process_scheduled_works kernel/workqueue.c:3310 [inline]
 worker_thread+0x6c8/0xf00 kernel/workqueue.c:3391
 kthread+0x2c1/0x3a0 kernel/kthread.c:389
 ret_from_fork+0x45/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Reported-by: syzbot+d693c07c6f647e0388d3@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=d693c07c6f647e0388d3
Fixes: 47ee3051c856 ("[PATCH] USB: usbnet (5/9) module for genesys gl620a cables")
Cc: stable@vger.kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250224172919.1220522-1-n.zhandarovich@fintech.ru
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/gl620a.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/usb/gl620a.c b/drivers/net/usb/gl620a.c
index 46af78caf457a..0bfa37c140591 100644
--- a/drivers/net/usb/gl620a.c
+++ b/drivers/net/usb/gl620a.c
@@ -179,9 +179,7 @@ static int genelink_bind(struct usbnet *dev, struct usb_interface *intf)
 {
 	dev->hard_mtu = GL_RCV_BUF_SIZE;
 	dev->net->hard_header_len += 4;
-	dev->in = usb_rcvbulkpipe(dev->udev, dev->driver_info->in);
-	dev->out = usb_sndbulkpipe(dev->udev, dev->driver_info->out);
-	return 0;
+	return usbnet_get_endpoints(dev, intf);
 }
 
 static const struct driver_info	genelink_info = {

From af4a5da8ed54561b7e856534cf62ea07632e7b7b Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 09:57:14 +0100
Subject: [PATCH 1264/2753] pktgen: avoid unused-const-variable warning

When extra warnings are enable, there are configurations that build
pktgen without CONFIG_XFRM, which leaves a static const variable unused:

net/core/pktgen.c:213:1: error: unused variable 'F_IPSEC' [-Werror,-Wunused-const-variable]
  213 | PKT_FLAGS
      | ^~~~~~~~~
net/core/pktgen.c:197:2: note: expanded from macro 'PKT_FLAGS'
  197 |         pf(IPSEC)               /* ipsec on for flows */                \
      |         ^~~~~~~~~

This could be marked as __maybe_unused, or by making the one use visible
to the compiler by slightly rearranging the #ifdef blocks. The second
variant looks slightly nicer here, so use that.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Peter Seiderer <ps.report@gmx.net>
Link: https://patch.msgid.link/20250225085722.469868-1-arnd@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 55064713223ec..402e01a2ce19e 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -158,9 +158,7 @@
 #include <net/udp.h>
 #include <net/ip6_checksum.h>
 #include <net/addrconf.h>
-#ifdef CONFIG_XFRM
 #include <net/xfrm.h>
-#endif
 #include <net/netns/generic.h>
 #include <asm/byteorder.h>
 #include <linux/rcupdate.h>
@@ -2363,13 +2361,13 @@ static inline int f_pick(struct pktgen_dev *pkt_dev)
 }
 
 
-#ifdef CONFIG_XFRM
 /* If there was already an IPSEC SA, we keep it as is, else
  * we go look for it ...
 */
 #define DUMMY_MARK 0
 static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 {
+#ifdef CONFIG_XFRM
 	struct xfrm_state *x = pkt_dev->flows[flow].x;
 	struct pktgen_net *pn = net_generic(dev_net(pkt_dev->odev), pg_net_id);
 	if (!x) {
@@ -2395,11 +2393,10 @@ static void get_ipsec_sa(struct pktgen_dev *pkt_dev, int flow)
 		}
 
 	}
-}
 #endif
+}
 static void set_cur_queue_map(struct pktgen_dev *pkt_dev)
 {
-
 	if (pkt_dev->flags & F_QUEUE_MAP_CPU)
 		pkt_dev->cur_queue_map = smp_processor_id();
 
@@ -2574,10 +2571,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev)
 				pkt_dev->flows[flow].flags |= F_INIT;
 				pkt_dev->flows[flow].cur_daddr =
 				    pkt_dev->cur_daddr;
-#ifdef CONFIG_XFRM
 				if (pkt_dev->flags & F_IPSEC)
 					get_ipsec_sa(pkt_dev, flow);
-#endif
 				pkt_dev->nflows++;
 			}
 		}

From 9355f7277d6987f7b6c087cca1b565713519a510 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 17:33:32 +0100
Subject: [PATCH 1265/2753] net: hisilicon: hns_mdio: remove incorrect ACPI_PTR
 annotation

Building with W=1 shows a warning about hns_mdio_acpi_match being unused when
CONFIG_ACPI is disabled:

drivers/net/ethernet/hisilicon/hns_mdio.c:631:36: error: unused variable 'hns_mdio_acpi_match' [-Werror,-Wunused-const-variable]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250225163341.4168238-1-arnd@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns_mdio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns_mdio.c b/drivers/net/ethernet/hisilicon/hns_mdio.c
index a1aa6c1f966ec..6812be8dc64fe 100644
--- a/drivers/net/ethernet/hisilicon/hns_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns_mdio.c
@@ -640,7 +640,7 @@ static struct platform_driver hns_mdio_driver = {
 	.driver = {
 		   .name = MDIO_DRV_NAME,
 		   .of_match_table = hns_mdio_match,
-		   .acpi_match_table = ACPI_PTR(hns_mdio_acpi_match),
+		   .acpi_match_table = hns_mdio_acpi_match,
 		   },
 };
 

From 01358e8fe922f716c05d7864ac2213b2440026e7 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 17:33:33 +0100
Subject: [PATCH 1266/2753] net: xgene-v2: remove incorrect ACPI_PTR annotation

Building with W=1 shows a warning about xge_acpi_match being unused when
CONFIG_ACPI is disabled:

drivers/net/ethernet/apm/xgene-v2/main.c:723:36: error: unused variable 'xge_acpi_match' [-Werror,-Wunused-const-variable]

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250225163341.4168238-2-arnd@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/apm/xgene-v2/main.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c
index 2a91c84aebdb0..d7ca847d44c7c 100644
--- a/drivers/net/ethernet/apm/xgene-v2/main.c
+++ b/drivers/net/ethernet/apm/xgene-v2/main.c
@@ -9,8 +9,6 @@
 
 #include "main.h"
 
-static const struct acpi_device_id xge_acpi_match[];
-
 static int xge_get_resources(struct xge_pdata *pdata)
 {
 	struct platform_device *pdev;
@@ -731,7 +729,7 @@ MODULE_DEVICE_TABLE(acpi, xge_acpi_match);
 static struct platform_driver xge_driver = {
 	.driver = {
 		   .name = "xgene-enet-v2",
-		   .acpi_match_table = ACPI_PTR(xge_acpi_match),
+		   .acpi_match_table = xge_acpi_match,
 	},
 	.probe = xge_probe,
 	.remove = xge_remove,

From 291515c7640962f8865e4c54897a5e91526b450c Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:43 +0100
Subject: [PATCH 1267/2753] net: gro: decouple GRO from the NAPI layer
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In fact, these two are not tied closely to each other. The only
requirements to GRO are to use it in the BH context and have some
sane limits on the packet batches, e.g. NAPI has a limit of its
budget (64/8/etc.).
Move purely GRO fields into a new structure, &gro_node. Embed it
into &napi_struct and adjust all the references.
gro_node::cached_napi_id is effectively the same as
napi_struct::napi_id, but to be used on GRO hotpath to mark skbs.
napi_struct::napi_id is now a fully control path field.

Three Ethernet drivers use napi_gro_flush() not really meant to be
exported, so move it to <net/gro.h> and add that include there.
napi_gro_receive() is used in more than 100 drivers, keep it
in <linux/netdevice.h>.
This does not make GRO ready to use outside of the NAPI context
yet.

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Acked-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/brocade/bna/bnad.c    |  1 +
 drivers/net/ethernet/cortina/gemini.c      |  1 +
 drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c |  1 +
 include/linux/netdevice.h                  | 37 +++++++++---
 include/net/busy_poll.h                    | 12 +++-
 include/net/gro.h                          | 35 +++++++----
 net/core/dev.c                             | 66 ++++++++++-----------
 net/core/gro.c                             | 69 +++++++++++-----------
 8 files changed, 130 insertions(+), 92 deletions(-)

diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
index ece6f3b483273..3b9107003b007 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -19,6 +19,7 @@
 #include <linux/ip.h>
 #include <linux/prefetch.h>
 #include <linux/module.h>
+#include <net/gro.h>
 
 #include "bnad.h"
 #include "bna.h"
diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
index 991e3839858b5..1f8067bdd61a6 100644
--- a/drivers/net/ethernet/cortina/gemini.c
+++ b/drivers/net/ethernet/cortina/gemini.c
@@ -40,6 +40,7 @@
 #include <linux/in.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <net/gro.h>
 
 #include "gemini.h"
 
diff --git a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c
index 7a9c09cd4fdcf..6a7a26085fc70 100644
--- a/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c
+++ b/drivers/net/wwan/t7xx/t7xx_hif_dpmaif_rx.c
@@ -41,6 +41,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 #include <linux/workqueue.h>
+#include <net/gro.h>
 
 #include "t7xx_dpmaif.h"
 #include "t7xx_hif_dpmaif.h"
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2094d3edda739..26a0c4e4d963d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -340,11 +340,27 @@ struct gro_list {
 };
 
 /*
- * size of gro hash buckets, must less than bit number of
- * napi_struct::gro_bitmask
+ * size of gro hash buckets, must be <= the number of bits in
+ * gro_node::bitmask
  */
 #define GRO_HASH_BUCKETS	8
 
+/**
+ * struct gro_node - structure to support Generic Receive Offload
+ * @bitmask: bitmask to indicate used buckets in @hash
+ * @hash: hashtable of pending aggregated skbs, separated by flows
+ * @rx_list: list of pending ``GRO_NORMAL`` skbs
+ * @rx_count: cached current length of @rx_list
+ * @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone
+ */
+struct gro_node {
+	unsigned long		bitmask;
+	struct gro_list		hash[GRO_HASH_BUCKETS];
+	struct list_head	rx_list;
+	u32			rx_count;
+	u32			cached_napi_id;
+};
+
 /*
  * Structure for per-NAPI config
  */
@@ -371,7 +387,6 @@ struct napi_struct {
 	unsigned long		state;
 	int			weight;
 	u32			defer_hard_irqs_count;
-	unsigned long		gro_bitmask;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
 	/* CPU actively polling if netpoll is configured */
@@ -380,11 +395,8 @@ struct napi_struct {
 	/* CPU on which NAPI has been scheduled for processing */
 	int			list_owner;
 	struct net_device	*dev;
-	struct gro_list		gro_hash[GRO_HASH_BUCKETS];
 	struct sk_buff		*skb;
-	struct list_head	rx_list; /* Pending GRO_NORMAL skbs */
-	int			rx_count; /* length of rx_list */
-	unsigned int		napi_id; /* protected by netdev_lock */
+	struct gro_node		gro;
 	struct hrtimer		timer;
 	/* all fields past this point are write-protected by netdev_lock */
 	struct task_struct	*thread;
@@ -392,6 +404,7 @@ struct napi_struct {
 	unsigned long		irq_suspend_timeout;
 	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
+	u32			napi_id;
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
 	int			irq;
@@ -4131,8 +4144,14 @@ int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list_internal(struct list_head *head);
 void netif_receive_skb_list(struct list_head *head);
-gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
-void napi_gro_flush(struct napi_struct *napi, bool flush_old);
+gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb);
+
+static inline gro_result_t napi_gro_receive(struct napi_struct *napi,
+					    struct sk_buff *skb)
+{
+	return gro_receive_skb(&napi->gro, skb);
+}
+
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
 gro_result_t napi_gro_frags(struct napi_struct *napi);
 
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index cab6146a510a1..6e172d0f6ef5f 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -127,18 +127,24 @@ static inline void sk_busy_loop(struct sock *sk, int nonblock)
 }
 
 /* used in the NIC receive handler to mark the skb */
-static inline void skb_mark_napi_id(struct sk_buff *skb,
-				    struct napi_struct *napi)
+static inline void __skb_mark_napi_id(struct sk_buff *skb,
+				      const struct gro_node *gro)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
 	/* If the skb was already marked with a valid NAPI ID, avoid overwriting
 	 * it.
 	 */
 	if (!napi_id_valid(skb->napi_id))
-		skb->napi_id = napi->napi_id;
+		skb->napi_id = gro->cached_napi_id;
 #endif
 }
 
+static inline void skb_mark_napi_id(struct sk_buff *skb,
+				    const struct napi_struct *napi)
+{
+	__skb_mark_napi_id(skb, &napi->gro);
+}
+
 /* used in the protocol handler to propagate the napi_id to the socket */
 static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 {
diff --git a/include/net/gro.h b/include/net/gro.h
index 7b548f91754bf..38d70c69ff807 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -509,26 +509,41 @@ static inline int gro_receive_network_flush(const void *th, const void *th2,
 
 int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
 int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
+void __gro_flush(struct gro_node *gro, bool flush_old);
+
+static inline void gro_flush(struct gro_node *gro, bool flush_old)
+{
+	if (!gro->bitmask)
+		return;
+
+	__gro_flush(gro, flush_old);
+}
+
+static inline void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+{
+	gro_flush(&napi->gro, flush_old);
+}
 
 /* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
-static inline void gro_normal_list(struct napi_struct *napi)
+static inline void gro_normal_list(struct gro_node *gro)
 {
-	if (!napi->rx_count)
+	if (!gro->rx_count)
 		return;
-	netif_receive_skb_list_internal(&napi->rx_list);
-	INIT_LIST_HEAD(&napi->rx_list);
-	napi->rx_count = 0;
+	netif_receive_skb_list_internal(&gro->rx_list);
+	INIT_LIST_HEAD(&gro->rx_list);
+	gro->rx_count = 0;
 }
 
 /* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
  * pass the whole batch up to the stack.
  */
-static inline void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int segs)
+static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb,
+				  int segs)
 {
-	list_add_tail(&skb->list, &napi->rx_list);
-	napi->rx_count += segs;
-	if (napi->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch))
-		gro_normal_list(napi);
+	list_add_tail(&skb->list, &gro->rx_list);
+	gro->rx_count += segs;
+	if (gro->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch))
+		gro_normal_list(gro);
 }
 
 /* This function is the alternative of 'inet_iif' and 'inet_sdif'
diff --git a/net/core/dev.c b/net/core/dev.c
index b0ab0169f5070..634bfcb3b5096 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6484,7 +6484,7 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		return false;
 
 	if (work_done) {
-		if (n->gro_bitmask)
+		if (n->gro.bitmask)
 			timeout = napi_get_gro_flush_timeout(n);
 		n->defer_hard_irqs_count = napi_get_defer_hard_irqs(n);
 	}
@@ -6494,15 +6494,14 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 		if (timeout)
 			ret = false;
 	}
-	if (n->gro_bitmask) {
-		/* When the NAPI instance uses a timeout and keeps postponing
-		 * it, we need to bound somehow the time packets are kept in
-		 * the GRO layer
-		 */
-		napi_gro_flush(n, !!timeout);
-	}
 
-	gro_normal_list(n);
+	/*
+	 * When the NAPI instance uses a timeout and keeps postponing
+	 * it, we need to bound somehow the time packets are kept in
+	 * the GRO layer.
+	 */
+	gro_flush(&n->gro, !!timeout);
+	gro_normal_list(&n->gro);
 
 	if (unlikely(!list_empty(&n->poll_list))) {
 		/* If n->poll_list is not empty, we need to mask irqs */
@@ -6566,19 +6565,15 @@ static void skb_defer_free_flush(struct softnet_data *sd)
 static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 {
 	if (!skip_schedule) {
-		gro_normal_list(napi);
+		gro_normal_list(&napi->gro);
 		__napi_schedule(napi);
 		return;
 	}
 
-	if (napi->gro_bitmask) {
-		/* flush too old packets
-		 * If HZ < 1000, flush all packets.
-		 */
-		napi_gro_flush(napi, HZ >= 1000);
-	}
+	/* Flush too old packets. If HZ < 1000, flush all packets */
+	gro_flush(&napi->gro, HZ >= 1000);
+	gro_normal_list(&napi->gro);
 
-	gro_normal_list(napi);
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
 
@@ -6685,7 +6680,7 @@ static void __napi_busy_loop(unsigned int napi_id,
 		}
 		work = napi_poll(napi, budget);
 		trace_napi_poll(napi, work, budget);
-		gro_normal_list(napi);
+		gro_normal_list(&napi->gro);
 count:
 		if (work > 0)
 			__NET_ADD_STATS(dev_net(napi->dev),
@@ -6785,6 +6780,8 @@ void napi_resume_irqs(unsigned int napi_id)
 static void __napi_hash_add_with_id(struct napi_struct *napi,
 				    unsigned int napi_id)
 {
+	napi->gro.cached_napi_id = napi_id;
+
 	WRITE_ONCE(napi->napi_id, napi_id);
 	hlist_add_head_rcu(&napi->napi_hash_node,
 			   &napi_hash[napi->napi_id % HASH_SIZE(napi_hash)]);
@@ -6858,10 +6855,12 @@ static void init_gro_hash(struct napi_struct *napi)
 	int i;
 
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		INIT_LIST_HEAD(&napi->gro_hash[i].list);
-		napi->gro_hash[i].count = 0;
+		INIT_LIST_HEAD(&napi->gro.hash[i].list);
+		napi->gro.hash[i].count = 0;
 	}
-	napi->gro_bitmask = 0;
+
+	napi->gro.bitmask = 0;
+	napi->gro.cached_napi_id = 0;
 }
 
 int dev_set_threaded(struct net_device *dev, bool threaded)
@@ -7193,8 +7192,8 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	napi->timer.function = napi_watchdog;
 	init_gro_hash(napi);
 	napi->skb = NULL;
-	INIT_LIST_HEAD(&napi->rx_list);
-	napi->rx_count = 0;
+	INIT_LIST_HEAD(&napi->gro.rx_list);
+	napi->gro.rx_count = 0;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
 		netdev_err_once(dev, "%s() called with weight %d\n", __func__,
@@ -7315,10 +7314,13 @@ static void flush_gro_hash(struct napi_struct *napi)
 	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
 		struct sk_buff *skb, *n;
 
-		list_for_each_entry_safe(skb, n, &napi->gro_hash[i].list, list)
+		list_for_each_entry_safe(skb, n, &napi->gro.hash[i].list, list)
 			kfree_skb(skb);
-		napi->gro_hash[i].count = 0;
+		napi->gro.hash[i].count = 0;
 	}
+
+	napi->gro.bitmask = 0;
+	napi->gro.cached_napi_id = 0;
 }
 
 /* Must be called in process context */
@@ -7344,7 +7346,6 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	napi_free_frags(napi);
 
 	flush_gro_hash(napi);
-	napi->gro_bitmask = 0;
 
 	if (napi->thread) {
 		kthread_stop(napi->thread);
@@ -7403,14 +7404,9 @@ static int __napi_poll(struct napi_struct *n, bool *repoll)
 		return work;
 	}
 
-	if (n->gro_bitmask) {
-		/* flush too old packets
-		 * If HZ < 1000, flush all packets.
-		 */
-		napi_gro_flush(n, HZ >= 1000);
-	}
-
-	gro_normal_list(n);
+	/* Flush too old packets. If HZ < 1000, flush all packets */
+	gro_flush(&n->gro, HZ >= 1000);
+	gro_normal_list(&n->gro);
 
 	/* Some drivers may have called napi_schedule
 	 * prior to exhausting their budget.
@@ -12439,7 +12435,7 @@ static struct hlist_head * __net_init netdev_create_hash(void)
 static int __net_init netdev_init(struct net *net)
 {
 	BUILD_BUG_ON(GRO_HASH_BUCKETS >
-		     8 * sizeof_field(struct napi_struct, gro_bitmask));
+		     BITS_PER_BYTE * sizeof_field(struct gro_node, bitmask));
 
 	INIT_LIST_HEAD(&net->dev_base_head);
 
diff --git a/net/core/gro.c b/net/core/gro.c
index 78b320b631744..9e1803fdf249c 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -250,8 +250,7 @@ int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb)
 	return 0;
 }
 
-
-static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
+static void gro_complete(struct gro_node *gro, struct sk_buff *skb)
 {
 	struct list_head *head = &net_hotdata.offload_base;
 	struct packet_offload *ptype;
@@ -284,43 +283,43 @@ static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb)
 	}
 
 out:
-	gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count);
+	gro_normal_one(gro, skb, NAPI_GRO_CB(skb)->count);
 }
 
-static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index,
-				   bool flush_old)
+static void __gro_flush_chain(struct gro_node *gro, u32 index, bool flush_old)
 {
-	struct list_head *head = &napi->gro_hash[index].list;
+	struct list_head *head = &gro->hash[index].list;
 	struct sk_buff *skb, *p;
 
 	list_for_each_entry_safe_reverse(skb, p, head, list) {
 		if (flush_old && NAPI_GRO_CB(skb)->age == jiffies)
 			return;
 		skb_list_del_init(skb);
-		napi_gro_complete(napi, skb);
-		napi->gro_hash[index].count--;
+		gro_complete(gro, skb);
+		gro->hash[index].count--;
 	}
 
-	if (!napi->gro_hash[index].count)
-		__clear_bit(index, &napi->gro_bitmask);
+	if (!gro->hash[index].count)
+		__clear_bit(index, &gro->bitmask);
 }
 
-/* napi->gro_hash[].list contains packets ordered by age.
+/*
+ * gro->hash[].list contains packets ordered by age.
  * youngest packets at the head of it.
  * Complete skbs in reverse order to reduce latencies.
  */
-void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+void __gro_flush(struct gro_node *gro, bool flush_old)
 {
-	unsigned long bitmask = napi->gro_bitmask;
+	unsigned long bitmask = gro->bitmask;
 	unsigned int i, base = ~0U;
 
 	while ((i = ffs(bitmask)) != 0) {
 		bitmask >>= i;
 		base += i;
-		__napi_gro_flush_chain(napi, base, flush_old);
+		__gro_flush_chain(gro, base, flush_old);
 	}
 }
-EXPORT_SYMBOL(napi_gro_flush);
+EXPORT_SYMBOL(__gro_flush);
 
 static unsigned long gro_list_prepare_tc_ext(const struct sk_buff *skb,
 					     const struct sk_buff *p,
@@ -439,7 +438,7 @@ static void gro_try_pull_from_frag0(struct sk_buff *skb)
 		gro_pull_from_frag0(skb, grow);
 }
 
-static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
+static void gro_flush_oldest(struct gro_node *gro, struct list_head *head)
 {
 	struct sk_buff *oldest;
 
@@ -455,14 +454,15 @@ static void gro_flush_oldest(struct napi_struct *napi, struct list_head *head)
 	 * SKB to the chain.
 	 */
 	skb_list_del_init(oldest);
-	napi_gro_complete(napi, oldest);
+	gro_complete(gro, oldest);
 }
 
-static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static enum gro_result dev_gro_receive(struct gro_node *gro,
+				       struct sk_buff *skb)
 {
 	u32 bucket = skb_get_hash_raw(skb) & (GRO_HASH_BUCKETS - 1);
-	struct gro_list *gro_list = &napi->gro_hash[bucket];
 	struct list_head *head = &net_hotdata.offload_base;
+	struct gro_list *gro_list = &gro->hash[bucket];
 	struct packet_offload *ptype;
 	__be16 type = skb->protocol;
 	struct sk_buff *pp = NULL;
@@ -526,7 +526,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 
 	if (pp) {
 		skb_list_del_init(pp);
-		napi_gro_complete(napi, pp);
+		gro_complete(gro, pp);
 		gro_list->count--;
 	}
 
@@ -537,7 +537,7 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 		goto normal;
 
 	if (unlikely(gro_list->count >= MAX_GRO_SKBS))
-		gro_flush_oldest(napi, &gro_list->list);
+		gro_flush_oldest(gro, &gro_list->list);
 	else
 		gro_list->count++;
 
@@ -551,10 +551,10 @@ static enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff
 	ret = GRO_HELD;
 ok:
 	if (gro_list->count) {
-		if (!test_bit(bucket, &napi->gro_bitmask))
-			__set_bit(bucket, &napi->gro_bitmask);
-	} else if (test_bit(bucket, &napi->gro_bitmask)) {
-		__clear_bit(bucket, &napi->gro_bitmask);
+		if (!test_bit(bucket, &gro->bitmask))
+			__set_bit(bucket, &gro->bitmask);
+	} else if (test_bit(bucket, &gro->bitmask)) {
+		__clear_bit(bucket, &gro->bitmask);
 	}
 
 	return ret;
@@ -593,13 +593,12 @@ struct packet_offload *gro_find_complete_by_type(__be16 type)
 }
 EXPORT_SYMBOL(gro_find_complete_by_type);
 
-static gro_result_t napi_skb_finish(struct napi_struct *napi,
-				    struct sk_buff *skb,
-				    gro_result_t ret)
+static gro_result_t gro_skb_finish(struct gro_node *gro, struct sk_buff *skb,
+				   gro_result_t ret)
 {
 	switch (ret) {
 	case GRO_NORMAL:
-		gro_normal_one(napi, skb, 1);
+		gro_normal_one(gro, skb, 1);
 		break;
 
 	case GRO_MERGED_FREE:
@@ -620,21 +619,21 @@ static gro_result_t napi_skb_finish(struct napi_struct *napi,
 	return ret;
 }
 
-gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb)
 {
 	gro_result_t ret;
 
-	skb_mark_napi_id(skb, napi);
+	__skb_mark_napi_id(skb, gro);
 	trace_napi_gro_receive_entry(skb);
 
 	skb_gro_reset_offset(skb, 0);
 
-	ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb));
+	ret = gro_skb_finish(gro, skb, dev_gro_receive(gro, skb));
 	trace_napi_gro_receive_exit(ret);
 
 	return ret;
 }
-EXPORT_SYMBOL(napi_gro_receive);
+EXPORT_SYMBOL(gro_receive_skb);
 
 static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 {
@@ -690,7 +689,7 @@ static gro_result_t napi_frags_finish(struct napi_struct *napi,
 		__skb_push(skb, ETH_HLEN);
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		if (ret == GRO_NORMAL)
-			gro_normal_one(napi, skb, 1);
+			gro_normal_one(&napi->gro, skb, 1);
 		break;
 
 	case GRO_MERGED_FREE:
@@ -759,7 +758,7 @@ gro_result_t napi_gro_frags(struct napi_struct *napi)
 
 	trace_napi_gro_frags_entry(skb);
 
-	ret = napi_frags_finish(napi, skb, dev_gro_receive(napi, skb));
+	ret = napi_frags_finish(napi, skb, dev_gro_receive(&napi->gro, skb));
 	trace_napi_gro_frags_exit(ret);
 
 	return ret;

From 388d31417ce0f1d08a1a86cab4c1dd700e9e9481 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:44 +0100
Subject: [PATCH 1268/2753] net: gro: expose GRO init/cleanup to use outside of
 NAPI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Make GRO init and cleanup functions global to be able to use GRO
without a NAPI instance. Taking into account already global gro_flush(),
it's now fully usable standalone.
New functions are not exported, since they're not supposed to be used
outside of the kernel core code.

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/gro.h |  3 +++
 net/core/dev.c    | 37 +++----------------------------------
 net/core/gro.c    | 34 ++++++++++++++++++++++++++++++++++
 3 files changed, 40 insertions(+), 34 deletions(-)

diff --git a/include/net/gro.h b/include/net/gro.h
index 38d70c69ff807..22d3a69e4404c 100644
--- a/include/net/gro.h
+++ b/include/net/gro.h
@@ -546,6 +546,9 @@ static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb,
 		gro_normal_list(gro);
 }
 
+void gro_init(struct gro_node *gro);
+void gro_cleanup(struct gro_node *gro);
+
 /* This function is the alternative of 'inet_iif' and 'inet_sdif'
  * functions in case we can not rely on fields of IPCB.
  *
diff --git a/net/core/dev.c b/net/core/dev.c
index 634bfcb3b5096..2dd9e6f490e61 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6850,19 +6850,6 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-static void init_gro_hash(struct napi_struct *napi)
-{
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		INIT_LIST_HEAD(&napi->gro.hash[i].list);
-		napi->gro.hash[i].count = 0;
-	}
-
-	napi->gro.bitmask = 0;
-	napi->gro.cached_napi_id = 0;
-}
-
 int dev_set_threaded(struct net_device *dev, bool threaded)
 {
 	struct napi_struct *napi;
@@ -7190,10 +7177,8 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	INIT_HLIST_NODE(&napi->napi_hash_node);
 	hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 	napi->timer.function = napi_watchdog;
-	init_gro_hash(napi);
+	gro_init(&napi->gro);
 	napi->skb = NULL;
-	INIT_LIST_HEAD(&napi->gro.rx_list);
-	napi->gro.rx_count = 0;
 	napi->poll = poll;
 	if (weight > NAPI_POLL_WEIGHT)
 		netdev_err_once(dev, "%s() called with weight %d\n", __func__,
@@ -7307,22 +7292,6 @@ void napi_enable(struct napi_struct *n)
 }
 EXPORT_SYMBOL(napi_enable);
 
-static void flush_gro_hash(struct napi_struct *napi)
-{
-	int i;
-
-	for (i = 0; i < GRO_HASH_BUCKETS; i++) {
-		struct sk_buff *skb, *n;
-
-		list_for_each_entry_safe(skb, n, &napi->gro.hash[i].list, list)
-			kfree_skb(skb);
-		napi->gro.hash[i].count = 0;
-	}
-
-	napi->gro.bitmask = 0;
-	napi->gro.cached_napi_id = 0;
-}
-
 /* Must be called in process context */
 void __netif_napi_del_locked(struct napi_struct *napi)
 {
@@ -7345,7 +7314,7 @@ void __netif_napi_del_locked(struct napi_struct *napi)
 	list_del_rcu(&napi->dev_list);
 	napi_free_frags(napi);
 
-	flush_gro_hash(napi);
+	gro_cleanup(&napi->gro);
 
 	if (napi->thread) {
 		kthread_stop(napi->thread);
@@ -12800,7 +12769,7 @@ static int __init net_dev_init(void)
 		INIT_CSD(&sd->defer_csd, trigger_rx_softirq, sd);
 		spin_lock_init(&sd->defer_lock);
 
-		init_gro_hash(&sd->backlog);
+		gro_init(&sd->backlog.gro);
 		sd->backlog.poll = process_backlog;
 		sd->backlog.weight = weight_p;
 		INIT_LIST_HEAD(&sd->backlog.poll_list);
diff --git a/net/core/gro.c b/net/core/gro.c
index 9e1803fdf249c..19bd4cdaee3ac 100644
--- a/net/core/gro.c
+++ b/net/core/gro.c
@@ -790,3 +790,37 @@ __sum16 __skb_gro_checksum_complete(struct sk_buff *skb)
 	return sum;
 }
 EXPORT_SYMBOL(__skb_gro_checksum_complete);
+
+void gro_init(struct gro_node *gro)
+{
+	for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) {
+		INIT_LIST_HEAD(&gro->hash[i].list);
+		gro->hash[i].count = 0;
+	}
+
+	gro->bitmask = 0;
+	gro->cached_napi_id = 0;
+
+	INIT_LIST_HEAD(&gro->rx_list);
+	gro->rx_count = 0;
+}
+
+void gro_cleanup(struct gro_node *gro)
+{
+	struct sk_buff *skb, *n;
+
+	for (u32 i = 0; i < GRO_HASH_BUCKETS; i++) {
+		list_for_each_entry_safe(skb, n, &gro->hash[i].list, list)
+			kfree_skb(skb);
+
+		gro->hash[i].count = 0;
+	}
+
+	gro->bitmask = 0;
+	gro->cached_napi_id = 0;
+
+	list_for_each_entry_safe(skb, n, &gro->rx_list, list)
+		kfree_skb(skb);
+
+	gro->rx_count = 0;
+}

From 4f8ab26a034f04f918c8d36c051ec84e4082eed5 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:45 +0100
Subject: [PATCH 1269/2753] bpf: cpumap: switch to GRO from
 netif_receive_skb_list()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cpumap has its own BH context based on kthread. It has a sane batch
size of 8 frames per one cycle.
GRO can be used here on its own. Adjust cpumap calls to the upper stack
to use GRO API instead of netif_receive_skb_list() which processes skbs
by batches, but doesn't involve GRO layer at all.
In plenty of tests, GRO performs better than listed receiving even
given that it has to calculate full frame checksums on the CPU.
As GRO passes the skbs to the upper stack in the batches of
@gro_normal_batch, i.e. 8 by default, and skb->dev points to the
device where the frame comes from, it is enough to disable GRO
netdev feature on it to completely restore the original behaviour:
untouched frames will be being bulked and passed to the upper stack
by 8, as it was with netif_receive_skb_list().

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 kernel/bpf/cpumap.c | 46 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 43 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 774accbd4a223..f0909736eaa50 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -33,8 +33,8 @@
 #include <trace/events/xdp.h>
 #include <linux/btf_ids.h>
 
-#include <linux/netdevice.h>   /* netif_receive_skb_list */
-#include <linux/etherdevice.h> /* eth_type_trans */
+#include <linux/netdevice.h>
+#include <net/gro.h>
 
 /* General idea: XDP packets getting XDP redirected to another CPU,
  * will maximum be stored/queued for one driver ->poll() call.  It is
@@ -68,6 +68,7 @@ struct bpf_cpu_map_entry {
 
 	struct bpf_cpumap_val value;
 	struct bpf_prog *prog;
+	struct gro_node gro;
 
 	struct completion kthread_running;
 	struct rcu_work free_work;
@@ -261,10 +262,36 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	return nframes;
 }
 
+static void cpu_map_gro_receive(struct bpf_cpu_map_entry *rcpu,
+				struct list_head *list)
+{
+	struct sk_buff *skb, *tmp;
+
+	list_for_each_entry_safe(skb, tmp, list, list) {
+		skb_list_del_init(skb);
+		gro_receive_skb(&rcpu->gro, skb);
+	}
+}
+
+static void cpu_map_gro_flush(struct bpf_cpu_map_entry *rcpu, bool empty)
+{
+	/*
+	 * If the ring is not empty, there'll be a new iteration soon, and we
+	 * only need to do a full flush if a tick is long (> 1 ms).
+	 * If the ring is empty, to not hold GRO packets in the stack for too
+	 * long, do a full flush.
+	 * This is equivalent to how NAPI decides whether to perform a full
+	 * flush.
+	 */
+	gro_flush(&rcpu->gro, !empty && HZ >= 1000);
+	gro_normal_list(&rcpu->gro);
+}
+
 static int cpu_map_kthread_run(void *data)
 {
 	struct bpf_cpu_map_entry *rcpu = data;
 	unsigned long last_qs = jiffies;
+	u32 packets = 0;
 
 	complete(&rcpu->kthread_running);
 	set_current_state(TASK_INTERRUPTIBLE);
@@ -282,6 +309,7 @@ static int cpu_map_kthread_run(void *data)
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
 		LIST_HEAD(list);
+		bool empty;
 
 		/* Release CPU reschedule checks */
 		if (__ptr_ring_empty(rcpu->queue)) {
@@ -361,7 +389,16 @@ static int cpu_map_kthread_run(void *data)
 		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
 					 sched, &stats);
 
-		netif_receive_skb_list(&list);
+		cpu_map_gro_receive(rcpu, &list);
+
+		/* Flush either every 64 packets or in case of empty ring */
+		packets += n;
+		empty = __ptr_ring_empty(rcpu->queue);
+		if (packets >= NAPI_POLL_WEIGHT || empty) {
+			cpu_map_gro_flush(rcpu, empty);
+			packets = 0;
+		}
+
 		local_bh_enable(); /* resched point, may call do_softirq() */
 	}
 	__set_current_state(TASK_RUNNING);
@@ -430,6 +467,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	rcpu->cpu    = cpu;
 	rcpu->map_id = map->id;
 	rcpu->value.qsize  = value->qsize;
+	gro_init(&rcpu->gro);
 
 	if (fd > 0 && __cpu_map_load_bpf_program(rcpu, map, fd))
 		goto free_ptr_ring;
@@ -458,6 +496,7 @@ __cpu_map_entry_alloc(struct bpf_map *map, struct bpf_cpumap_val *value,
 	if (rcpu->prog)
 		bpf_prog_put(rcpu->prog);
 free_ptr_ring:
+	gro_cleanup(&rcpu->gro);
 	ptr_ring_cleanup(rcpu->queue, NULL);
 free_queue:
 	kfree(rcpu->queue);
@@ -487,6 +526,7 @@ static void __cpu_map_entry_free(struct work_struct *work)
 
 	if (rcpu->prog)
 		bpf_prog_put(rcpu->prog);
+	gro_cleanup(&rcpu->gro);
 	/* The queue should be empty at this point */
 	__cpu_map_ring_cleanup(rcpu->queue);
 	ptr_ring_cleanup(rcpu->queue, NULL);

From 57efe762cd3c8796f8a4b410a578af8c8e99d22f Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:46 +0100
Subject: [PATCH 1270/2753] bpf: cpumap: reuse skb array instead of a linked
 list to chain skbs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

cpumap still uses linked lists to store a list of skbs to pass to the
stack. Now that we don't use listified Rx in favor of
napi_gro_receive(), linked list is now an unneeded overhead.
Inside the polling loop, we already have an array of skbs. Let's reuse
it for skbs passed to cpumap (generic XDP) and keep there in case of
XDP_PASS when a program is installed to the map itself. Don't list
regular xdp_frames after converting them to skbs as well; store them
in the mentioned array (but *before* generic skbs as the latters have
lower priority) and call gro_receive_skb() for each array element after
they're done.

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 kernel/bpf/cpumap.c | 119 +++++++++++++++++++++++---------------------
 1 file changed, 61 insertions(+), 58 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index f0909736eaa50..85936f09d8d77 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -134,22 +134,23 @@ static void __cpu_map_ring_cleanup(struct ptr_ring *ring)
 	}
 }
 
-static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
-				     struct list_head *listp,
-				     struct xdp_cpumap_stats *stats)
+static u32 cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
+				    void **skbs, u32 skb_n,
+				    struct xdp_cpumap_stats *stats)
 {
-	struct sk_buff *skb, *tmp;
 	struct xdp_buff xdp;
-	u32 act;
+	u32 act, pass = 0;
 	int err;
 
-	list_for_each_entry_safe(skb, tmp, listp, list) {
+	for (u32 i = 0; i < skb_n; i++) {
+		struct sk_buff *skb = skbs[i];
+
 		act = bpf_prog_run_generic_xdp(skb, &xdp, rcpu->prog);
 		switch (act) {
 		case XDP_PASS:
+			skbs[pass++] = skb;
 			break;
 		case XDP_REDIRECT:
-			skb_list_del_init(skb);
 			err = xdp_do_generic_redirect(skb->dev, skb, &xdp,
 						      rcpu->prog);
 			if (unlikely(err)) {
@@ -158,7 +159,7 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 			} else {
 				stats->redirect++;
 			}
-			return;
+			break;
 		default:
 			bpf_warn_invalid_xdp_action(NULL, rcpu->prog, act);
 			fallthrough;
@@ -166,12 +167,15 @@ static void cpu_map_bpf_prog_run_skb(struct bpf_cpu_map_entry *rcpu,
 			trace_xdp_exception(skb->dev, rcpu->prog, act);
 			fallthrough;
 		case XDP_DROP:
-			skb_list_del_init(skb);
-			kfree_skb(skb);
+			napi_consume_skb(skb, true);
 			stats->drop++;
-			return;
+			break;
 		}
 	}
+
+	stats->pass += pass;
+
+	return pass;
 }
 
 static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
@@ -205,7 +209,6 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 				stats->drop++;
 			} else {
 				frames[nframes++] = xdpf;
-				stats->pass++;
 			}
 			break;
 		case XDP_REDIRECT:
@@ -229,48 +232,44 @@ static int cpu_map_bpf_prog_run_xdp(struct bpf_cpu_map_entry *rcpu,
 	}
 
 	xdp_clear_return_frame_no_direct();
+	stats->pass += nframes;
 
 	return nframes;
 }
 
 #define CPUMAP_BATCH 8
 
-static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
-				int xdp_n, struct xdp_cpumap_stats *stats,
-				struct list_head *list)
+struct cpu_map_ret {
+	u32 xdp_n;
+	u32 skb_n;
+};
+
+static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
+				 void **skbs, struct cpu_map_ret *ret,
+				 struct xdp_cpumap_stats *stats)
 {
 	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
-	int nframes;
 
 	if (!rcpu->prog)
-		return xdp_n;
+		goto out;
 
 	rcu_read_lock_bh();
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
-	nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats);
+	ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats);
+	if (unlikely(ret->skb_n))
+		ret->skb_n = cpu_map_bpf_prog_run_skb(rcpu, skbs, ret->skb_n,
+						      stats);
 
 	if (stats->redirect)
 		xdp_do_flush();
 
-	if (unlikely(!list_empty(list)))
-		cpu_map_bpf_prog_run_skb(rcpu, list, stats);
-
 	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
 
-	return nframes;
-}
-
-static void cpu_map_gro_receive(struct bpf_cpu_map_entry *rcpu,
-				struct list_head *list)
-{
-	struct sk_buff *skb, *tmp;
-
-	list_for_each_entry_safe(skb, tmp, list, list) {
-		skb_list_del_init(skb);
-		gro_receive_skb(&rcpu->gro, skb);
-	}
+out:
+	if (unlikely(ret->skb_n) && ret->xdp_n)
+		memmove(&skbs[ret->xdp_n], skbs, ret->skb_n * sizeof(*skbs));
 }
 
 static void cpu_map_gro_flush(struct bpf_cpu_map_entry *rcpu, bool empty)
@@ -305,10 +304,10 @@ static int cpu_map_kthread_run(void *data)
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
 		unsigned int kmem_alloc_drops = 0, sched = 0;
 		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
-		int i, n, m, nframes, xdp_n;
+		struct cpu_map_ret ret = { };
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
-		LIST_HEAD(list);
+		u32 i, n, m;
 		bool empty;
 
 		/* Release CPU reschedule checks */
@@ -334,7 +333,7 @@ static int cpu_map_kthread_run(void *data)
 		 */
 		n = __ptr_ring_consume_batched(rcpu->queue, frames,
 					       CPUMAP_BATCH);
-		for (i = 0, xdp_n = 0; i < n; i++) {
+		for (i = 0; i < n; i++) {
 			void *f = frames[i];
 			struct page *page;
 
@@ -342,11 +341,11 @@ static int cpu_map_kthread_run(void *data)
 				struct sk_buff *skb = f;
 
 				__ptr_clear_bit(0, &skb);
-				list_add_tail(&skb->list, &list);
+				skbs[ret.skb_n++] = skb;
 				continue;
 			}
 
-			frames[xdp_n++] = f;
+			frames[ret.xdp_n++] = f;
 			page = virt_to_page(f);
 
 			/* Bring struct page memory area to curr CPU. Read by
@@ -357,39 +356,43 @@ static int cpu_map_kthread_run(void *data)
 		}
 
 		/* Support running another XDP prog on this CPU */
-		nframes = cpu_map_bpf_prog_run(rcpu, frames, xdp_n, &stats, &list);
-		if (nframes) {
-			m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
-						  gfp, nframes, skbs);
-			if (unlikely(m == 0)) {
-				for (i = 0; i < nframes; i++)
-					skbs[i] = NULL; /* effect: xdp_return_frame */
-				kmem_alloc_drops += nframes;
-			}
+		cpu_map_bpf_prog_run(rcpu, frames, skbs, &ret, &stats);
+		if (!ret.xdp_n) {
+			local_bh_disable();
+			goto stats;
+		}
+
+		m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp,
+					  ret.xdp_n, skbs);
+		if (unlikely(m < ret.xdp_n)) {
+			for (i = m; i < ret.xdp_n; i++)
+				xdp_return_frame(frames[i]);
+
+			if (ret.skb_n)
+				memmove(&skbs[m], &skbs[ret.xdp_n],
+					ret.skb_n * sizeof(*skbs));
+
+			kmem_alloc_drops += ret.xdp_n - m;
+			ret.xdp_n = m;
 		}
 
 		local_bh_disable();
-		for (i = 0; i < nframes; i++) {
+		for (i = 0; i < ret.xdp_n; i++) {
 			struct xdp_frame *xdpf = frames[i];
-			struct sk_buff *skb = skbs[i];
-
-			skb = __xdp_build_skb_from_frame(xdpf, skb,
-							 xdpf->dev_rx);
-			if (!skb) {
-				xdp_return_frame(xdpf);
-				continue;
-			}
 
-			list_add_tail(&skb->list, &list);
+			/* Can fail only when !skb -- already handled above */
+			__xdp_build_skb_from_frame(xdpf, skbs[i], xdpf->dev_rx);
 		}
 
+stats:
 		/* Feedback loop via tracepoint.
 		 * NB: keep before recv to allow measuring enqueue/dequeue latency.
 		 */
 		trace_xdp_cpumap_kthread(rcpu->map_id, n, kmem_alloc_drops,
 					 sched, &stats);
 
-		cpu_map_gro_receive(rcpu, &list);
+		for (i = 0; i < ret.xdp_n + ret.skb_n; i++)
+			gro_receive_skb(&rcpu->gro, skbs[i]);
 
 		/* Flush either every 64 packets or in case of empty ring */
 		packets += n;

From 859d6acd94cc4ad65e9eb3fa2a9815a19e5b35cf Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:47 +0100
Subject: [PATCH 1271/2753] net: skbuff: introduce napi_skb_cache_get_bulk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a function to get an array of skbs from the NAPI percpu cache.
It's supposed to be a drop-in replacement for
kmem_cache_alloc_bulk(skbuff_head_cache, GFP_ATOMIC) and
xdp_alloc_skb_bulk(GFP_ATOMIC). The difference (apart from the
requirement to call it only from the BH) is that it tries to use
as many NAPI cache entries for skbs as possible, and allocate new
ones only if needed.

The logic is as follows:

* there is enough skbs in the cache: decache them and return to the
  caller;
* not enough: try refilling the cache first. If there is now enough
  skbs, return;
* still not enough: try allocating skbs directly to the output array
  with %GFP_ZERO, maybe we'll be able to get some. If there's now
  enough, return;
* still not enough: return as many as we were able to obtain.

Most of times, if called from the NAPI polling loop, the first one will
be true, sometimes (rarely) the second one. The third and the fourth --
only under heavy memory pressure.
It can save significant amounts of CPU cycles if there are GRO cycles
and/or Tx completion cycles (anything that descends to
napi_skb_cache_put()) happening on this CPU.

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/skbuff.h |  1 +
 net/core/skbuff.c      | 62 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 63 insertions(+)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 171aa15f65414..14517e95a46c4 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -1320,6 +1320,7 @@ struct sk_buff *build_skb_around(struct sk_buff *skb,
 				 void *data, unsigned int frag_size);
 void skb_attempt_defer_free(struct sk_buff *skb);
 
+u32 napi_skb_cache_get_bulk(void **skbs, u32 n);
 struct sk_buff *napi_build_skb(void *data, unsigned int frag_size);
 struct sk_buff *slab_build_skb(void *data);
 
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 5b241c9e6f381..f12815f9c83d2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -295,6 +295,68 @@ static struct sk_buff *napi_skb_cache_get(void)
 	return skb;
 }
 
+/**
+ * napi_skb_cache_get_bulk - obtain a number of zeroed skb heads from the cache
+ * @skbs: pointer to an at least @n-sized array to fill with skb pointers
+ * @n: number of entries to provide
+ *
+ * Tries to obtain @n &sk_buff entries from the NAPI percpu cache and writes
+ * the pointers into the provided array @skbs. If there are less entries
+ * available, tries to replenish the cache and bulk-allocates the diff from
+ * the MM layer if needed.
+ * The heads are being zeroed with either memset() or %__GFP_ZERO, so they are
+ * ready for {,__}build_skb_around() and don't have any data buffers attached.
+ * Must be called *only* from the BH context.
+ *
+ * Return: number of successfully allocated skbs (@n if no actual allocation
+ *	   needed or kmem_cache_alloc_bulk() didn't fail).
+ */
+u32 napi_skb_cache_get_bulk(void **skbs, u32 n)
+{
+	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	u32 bulk, total = n;
+
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+
+	if (nc->skb_count >= n)
+		goto get;
+
+	/* No enough cached skbs. Try refilling the cache first */
+	bulk = min(NAPI_SKB_CACHE_SIZE - nc->skb_count, NAPI_SKB_CACHE_BULK);
+	nc->skb_count += kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
+					       GFP_ATOMIC | __GFP_NOWARN, bulk,
+					       &nc->skb_cache[nc->skb_count]);
+	if (likely(nc->skb_count >= n))
+		goto get;
+
+	/* Still not enough. Bulk-allocate the missing part directly, zeroed */
+	n -= kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
+				   GFP_ATOMIC | __GFP_ZERO | __GFP_NOWARN,
+				   n - nc->skb_count, &skbs[nc->skb_count]);
+	if (likely(nc->skb_count >= n))
+		goto get;
+
+	/* kmem_cache didn't allocate the number we need, limit the output */
+	total -= n - nc->skb_count;
+	n = nc->skb_count;
+
+get:
+	for (u32 base = nc->skb_count - n, i = 0; i < n; i++) {
+		u32 cache_size = kmem_cache_size(net_hotdata.skbuff_cache);
+
+		skbs[i] = nc->skb_cache[base + i];
+
+		kasan_mempool_unpoison_object(skbs[i], cache_size);
+		memset(skbs[i], 0, offsetof(struct sk_buff, tail));
+	}
+
+	nc->skb_count -= n;
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
+
+	return total;
+}
+EXPORT_SYMBOL_GPL(napi_skb_cache_get_bulk);
+
 static inline void __finalize_skb_around(struct sk_buff *skb, void *data,
 					 unsigned int size)
 {

From ed16b8a4d1ca901fc13ced042b76dde54738249a Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:48 +0100
Subject: [PATCH 1272/2753] bpf: cpumap: switch to napi_skb_cache_get_bulk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that cpumap uses GRO, which drops unused skb heads to the NAPI
cache, use napi_skb_cache_get_bulk() to try to reuse cached entries
and lower MM layer pressure. Always disable the BH before checking and
running the cpumap-pinned XDP prog and don't re-enable it in between
that and allocating an skb bulk, as we can access the NAPI caches only
from the BH context.
The better GRO aggregates packets, the less new skbs will be allocated.
If an aggregated skb contains 16 frags, this means 15 skbs were returned
to the cache, so next 15 skbs will be built without allocating anything.

The same trafficgen UDP GRO test now shows:

                GRO off   GRO on
threaded GRO    2.3       4         Mpps
thr bulk GRO    2.4       4.7       Mpps

diff            +4        +17       %

Comparing to the baseline cpumap:

baseline        2.7       N/A       Mpps
thr bulk GRO    2.4       4.7       Mpps
diff            -11       +74       %

Tested-by: Daniel Xu <dxu@dxuuu.xyz>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 kernel/bpf/cpumap.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index 85936f09d8d77..67e8a2fc1a99d 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -253,7 +253,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	if (!rcpu->prog)
 		goto out;
 
-	rcu_read_lock_bh();
+	rcu_read_lock();
 	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	ret->xdp_n = cpu_map_bpf_prog_run_xdp(rcpu, frames, ret->xdp_n, stats);
@@ -265,7 +265,7 @@ static void cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 		xdp_do_flush();
 
 	bpf_net_ctx_clear(bpf_net_ctx);
-	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
+	rcu_read_unlock();
 
 out:
 	if (unlikely(ret->skb_n) && ret->xdp_n)
@@ -303,7 +303,6 @@ static int cpu_map_kthread_run(void *data)
 	while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) {
 		struct xdp_cpumap_stats stats = {}; /* zero stats */
 		unsigned int kmem_alloc_drops = 0, sched = 0;
-		gfp_t gfp = __GFP_ZERO | GFP_ATOMIC;
 		struct cpu_map_ret ret = { };
 		void *frames[CPUMAP_BATCH];
 		void *skbs[CPUMAP_BATCH];
@@ -355,15 +354,14 @@ static int cpu_map_kthread_run(void *data)
 			prefetchw(page);
 		}
 
+		local_bh_disable();
+
 		/* Support running another XDP prog on this CPU */
 		cpu_map_bpf_prog_run(rcpu, frames, skbs, &ret, &stats);
-		if (!ret.xdp_n) {
-			local_bh_disable();
+		if (!ret.xdp_n)
 			goto stats;
-		}
 
-		m = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp,
-					  ret.xdp_n, skbs);
+		m = napi_skb_cache_get_bulk(skbs, ret.xdp_n);
 		if (unlikely(m < ret.xdp_n)) {
 			for (i = m; i < ret.xdp_n; i++)
 				xdp_return_frame(frames[i]);
@@ -376,7 +374,6 @@ static int cpu_map_kthread_run(void *data)
 			ret.xdp_n = m;
 		}
 
-		local_bh_disable();
 		for (i = 0; i < ret.xdp_n; i++) {
 			struct xdp_frame *xdpf = frames[i];
 

From 1c5bf4de975dd4d493cea3567703404819c81425 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:49 +0100
Subject: [PATCH 1273/2753] veth: use napi_skb_cache_get_bulk() instead of
 xdp_alloc_skb_bulk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that we can bulk-allocate skbs from the NAPI cache, use that
function to do that in veth as well instead of direct allocation from
the kmem caches. veth uses NAPI and GRO, so this is both context-safe
and beneficial.

Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/veth.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index ba3ae2d8092f8..05f5eeef539f0 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -684,8 +684,7 @@ static void veth_xdp_rcv_bulk_skb(struct veth_rq *rq, void **frames,
 	void *skbs[VETH_XDP_BATCH];
 	int i;
 
-	if (xdp_alloc_skb_bulk(skbs, n_xdpf,
-			       GFP_ATOMIC | __GFP_ZERO) < 0) {
+	if (unlikely(!napi_skb_cache_get_bulk(skbs, n_xdpf))) {
 		for (i = 0; i < n_xdpf; i++)
 			xdp_return_frame(frames[i]);
 		stats->rx_drops += n_xdpf;

From b696d289c07d8480a7d4752e448f4ee2bee9e443 Mon Sep 17 00:00:00 2001
From: Alexander Lobakin <aleksander.lobakin@intel.com>
Date: Tue, 25 Feb 2025 18:17:50 +0100
Subject: [PATCH 1274/2753] xdp: remove xdp_alloc_skb_bulk()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only user was veth, which now uses napi_skb_cache_get_bulk().
It's now preferred over a direct allocation and is exported as
well, so remove this one.

Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/xdp.h |  1 -
 net/core/xdp.c    | 10 ----------
 2 files changed, 11 deletions(-)

diff --git a/include/net/xdp.h b/include/net/xdp.h
index 4dafc5e021f13..48efacbaa35da 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -343,7 +343,6 @@ struct sk_buff *__xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					   struct net_device *dev);
 struct sk_buff *xdp_build_skb_from_frame(struct xdp_frame *xdpf,
 					 struct net_device *dev);
-int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp);
 struct xdp_frame *xdpf_clone(struct xdp_frame *xdpf);
 
 static inline
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 2c6ab6fb452f7..f86eedad586a7 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -618,16 +618,6 @@ void xdp_warn(const char *msg, const char *func, const int line)
 };
 EXPORT_SYMBOL_GPL(xdp_warn);
 
-int xdp_alloc_skb_bulk(void **skbs, int n_skb, gfp_t gfp)
-{
-	n_skb = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache, gfp, n_skb, skbs);
-	if (unlikely(!n_skb))
-		return -ENOMEM;
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(xdp_alloc_skb_bulk);
-
 /**
  * xdp_build_skb_from_buff - create an skb from &xdp_buff
  * @xdp: &xdp_buff to convert to an skb

From 38f4aa34a5f737ea8588dac320d884cc2e762c03 Mon Sep 17 00:00:00 2001
From: Justin Klaassen <justin@tidylabs.net>
Date: Tue, 25 Feb 2025 17:03:58 +0000
Subject: [PATCH 1275/2753] arm64: dts: rockchip: fix u2phy1_host status for
 NanoPi R4S

The u2phy1_host should always have the same status as usb_host1_ehci
and usb_host1_ohci, otherwise the EHCI and OHCI drivers may be
initialized for a disabled usb port.

Per the NanoPi R4S schematic, the phy-supply for u2phy1_host is set to
the vdd_5v regulator.

Fixes: db792e9adbf8 ("rockchip: rk3399: Add support for FriendlyARM NanoPi R4S")
Cc: stable@vger.kernel.org
Signed-off-by: Justin Klaassen <justin@tidylabs.net>
Reviewed-by: Dragan Simic <dsimic@manjaro.org>
Link: https://lore.kernel.org/r/20250225170420.3898-1-justin@tidylabs.net
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
index b1c9bd0e63ef3..8d94d9f91a5c6 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-nanopi-r4s.dtsi
@@ -115,7 +115,7 @@
 };
 
 &u2phy1_host {
-	status = "disabled";
+	phy-supply = <&vdd_5v>;
 };
 
 &uart0 {

From c64a0727f9b1cbc63a5538c8c0014e9a175ad864 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 25 Feb 2025 18:51:38 +0100
Subject: [PATCH 1276/2753] net: ipv6: fix dst ref loop on input in seg6 lwt

Prevent a dst ref loop on input in seg6_iptunnel.

Fixes: af4a2209b134 ("ipv6: sr: use dst_cache in seg6_input")
Cc: David Lebrun <dlebrun@google.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/seg6_iptunnel.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c
index 33833b2064c07..51583461ae29b 100644
--- a/net/ipv6/seg6_iptunnel.c
+++ b/net/ipv6/seg6_iptunnel.c
@@ -472,10 +472,18 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
+	struct lwtunnel_state *lwtst;
 	struct seg6_lwt *slwt;
 	int err;
 
-	slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
+	/* We cannot dereference "orig_dst" once ip6_route_input() or
+	 * skb_dst_drop() is called. However, in order to detect a dst loop, we
+	 * need the address of its lwtstate. So, save the address of lwtstate
+	 * now and use it later as a comparison.
+	 */
+	lwtst = orig_dst->lwtstate;
+
+	slwt = seg6_lwt_lwtunnel(lwtst);
 
 	local_bh_disable();
 	dst = dst_cache_get(&slwt->cache);
@@ -490,7 +498,9 @@ static int seg6_input_core(struct net *net, struct sock *sk,
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
-		if (!dst->error) {
+
+		/* cache only if we don't create a dst reference loop */
+		if (!dst->error && lwtst != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&slwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);

From 13e55fbaec176119cff68a7e1693b251c8883c5f Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 25 Feb 2025 18:51:39 +0100
Subject: [PATCH 1277/2753] net: ipv6: fix dst ref loop on input in rpl lwt

Prevent a dst ref loop on input in rpl_iptunnel.

Fixes: a7a29f9c361f ("net: ipv6: add rpl sr tunnel")
Cc: Alexander Aring <alex.aring@gmail.com>
Cc: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/rpl_iptunnel.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
index 0ac4283acdf20..7c05ac846646f 100644
--- a/net/ipv6/rpl_iptunnel.c
+++ b/net/ipv6/rpl_iptunnel.c
@@ -262,10 +262,18 @@ static int rpl_input(struct sk_buff *skb)
 {
 	struct dst_entry *orig_dst = skb_dst(skb);
 	struct dst_entry *dst = NULL;
+	struct lwtunnel_state *lwtst;
 	struct rpl_lwt *rlwt;
 	int err;
 
-	rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+	/* We cannot dereference "orig_dst" once ip6_route_input() or
+	 * skb_dst_drop() is called. However, in order to detect a dst loop, we
+	 * need the address of its lwtstate. So, save the address of lwtstate
+	 * now and use it later as a comparison.
+	 */
+	lwtst = orig_dst->lwtstate;
+
+	rlwt = rpl_lwt_lwtunnel(lwtst);
 
 	local_bh_disable();
 	dst = dst_cache_get(&rlwt->cache);
@@ -280,7 +288,9 @@ static int rpl_input(struct sk_buff *skb)
 	if (!dst) {
 		ip6_route_input(skb);
 		dst = skb_dst(skb);
-		if (!dst->error) {
+
+		/* cache only if we don't create a dst reference loop */
+		if (!dst->error && lwtst != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&rlwt->cache, dst,
 					  &ipv6_hdr(skb)->saddr);

From 2db7d29c7b1629ced3cbab3de242511eb3c22066 Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@cherry.de>
Date: Tue, 25 Feb 2025 12:53:29 +0100
Subject: [PATCH 1278/2753] arm64: dts: rockchip: fix pinmux of UART0 for PX30
 Ringneck on Haikou
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

UART0 pinmux by default configures GPIO0_B5 in its UART RTS function for
UART0. However, by default on Haikou, it is used as GPIO as UART RTS for
UART5.

Therefore, let's update UART0 pinmux to not configure the pin in that
mode, a later commit will make UART5 request the GPIO pinmux.

Fixes: c484cf93f61b ("arm64: dts: rockchip: add PX30-µQ7 (Ringneck) SoM with Haikou baseboard")
Cc: stable@vger.kernel.org
Signed-off-by: Quentin Schulz <quentin.schulz@cherry.de>
Link: https://lore.kernel.org/r/20250225-ringneck-dtbos-v3-1-853a9a6dd597@cherry.de
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index eb9470a00e549..6d45a19413ce6 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -222,6 +222,8 @@
 };
 
 &uart0 {
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart0_xfer>;
 	status = "okay";
 };
 

From 55de171bba1b8c0e3dd18b800955ac4b46a63d4b Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@cherry.de>
Date: Tue, 25 Feb 2025 12:53:30 +0100
Subject: [PATCH 1279/2753] arm64: dts: rockchip: fix pinmux of UART5 for PX30
 Ringneck on Haikou

UART5 uses GPIO0_B5 as UART RTS but muxed in its GPIO function,
therefore UART5 must request this pin to be muxed in that function, so
let's do that.

Fixes: 5963d97aa780 ("arm64: dts: rockchip: add rs485 support on uart5 of px30-ringneck-haikou")
Cc: stable@vger.kernel.org
Signed-off-by: Quentin Schulz <quentin.schulz@cherry.de>
Link: https://lore.kernel.org/r/20250225-ringneck-dtbos-v3-2-853a9a6dd597@cherry.de
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
index 6d45a19413ce6..1a59e8b1dc46e 100644
--- a/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
+++ b/arch/arm64/boot/dts/rockchip/px30-ringneck-haikou.dts
@@ -194,6 +194,13 @@
 			  <3 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
 		};
 	};
+
+	uart {
+		uart5_rts_pin: uart5-rts-pin {
+			rockchip,pins =
+			  <0 RK_PB5 RK_FUNC_GPIO &pcfg_pull_none>;
+		};
+	};
 };
 
 &pwm0 {
@@ -228,6 +235,9 @@
 };
 
 &uart5 {
+	/* Add pinmux for rts-gpios (uart5_rts_pin) */
+	pinctrl-names = "default";
+	pinctrl-0 = <&uart5_xfer &uart5_rts_pin>;
 	rts-gpios = <&gpio0 RK_PB5 GPIO_ACTIVE_HIGH>;
 	status = "okay";
 };

From 7fe0353606d77a32c4c7f2814833dd1c043ebdd2 Mon Sep 17 00:00:00 2001
From: Eric Woudstra <ericwouds@gmail.com>
Date: Tue, 25 Feb 2025 21:15:09 +0100
Subject: [PATCH 1280/2753] net: ethernet: mtk_ppe_offload: Allow QinQ, double
 ETH_P_8021Q only

mtk_foe_entry_set_vlan() in mtk_ppe.c already supports double vlan
tagging, but mtk_flow_offload_replace() in mtk_ppe_offload.c only allows
for 1 vlan tag, optionally in combination with pppoe and dsa tags.

However, mtk_foe_entry_set_vlan() only allows for setting the vlan id.
The protocol cannot be set, it is always ETH_P_8021Q, for inner and outer
tag. This patch adds QinQ support to mtk_flow_offload_replace(), only in
the case that both inner and outer tags are ETH_P_8021Q.

Only PPPoE-in-Q (as before) and Q-in-Q are allowed. A combination
of PPPoE and Q-in-Q is not allowed.

Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
Link: https://patch.msgid.link/20250225201509.20843-1-ericwouds@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mediatek/mtk_ppe_offload.c   | 22 +++++++++----------
 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
index f20bb390df3ad..c855fb799ce14 100644
--- a/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
+++ b/drivers/net/ethernet/mediatek/mtk_ppe_offload.c
@@ -34,8 +34,10 @@ struct mtk_flow_data {
 	u16 vlan_in;
 
 	struct {
-		u16 id;
-		__be16 proto;
+		struct {
+			u16 id;
+			__be16 proto;
+		} vlans[2];
 		u8 num;
 	} vlan;
 	struct {
@@ -349,18 +351,19 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 		case FLOW_ACTION_CSUM:
 			break;
 		case FLOW_ACTION_VLAN_PUSH:
-			if (data.vlan.num == 1 ||
+			if (data.vlan.num + data.pppoe.num == 2 ||
 			    act->vlan.proto != htons(ETH_P_8021Q))
 				return -EOPNOTSUPP;
 
-			data.vlan.id = act->vlan.vid;
-			data.vlan.proto = act->vlan.proto;
+			data.vlan.vlans[data.vlan.num].id = act->vlan.vid;
+			data.vlan.vlans[data.vlan.num].proto = act->vlan.proto;
 			data.vlan.num++;
 			break;
 		case FLOW_ACTION_VLAN_POP:
 			break;
 		case FLOW_ACTION_PPPOE_PUSH:
-			if (data.pppoe.num == 1)
+			if (data.pppoe.num == 1 ||
+			    data.vlan.num == 2)
 				return -EOPNOTSUPP;
 
 			data.pppoe.sid = act->pppoe.sid;
@@ -450,12 +453,9 @@ mtk_flow_offload_replace(struct mtk_eth *eth, struct flow_cls_offload *f,
 	if (offload_type == MTK_PPE_PKT_TYPE_BRIDGE)
 		foe.bridge.vlan = data.vlan_in;
 
-	if (data.vlan.num == 1) {
-		if (data.vlan.proto != htons(ETH_P_8021Q))
-			return -EOPNOTSUPP;
+	for (i = 0; i < data.vlan.num; i++)
+		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.vlans[i].id);
 
-		mtk_foe_entry_set_vlan(eth, &foe, data.vlan.id);
-	}
 	if (data.pppoe.num == 1)
 		mtk_foe_entry_set_pppoe(eth, &foe, data.pppoe.sid);
 

From 1cbddbddee68d17feb6467fc556c144777af91ef Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Wed, 26 Feb 2025 18:19:57 +0000
Subject: [PATCH 1281/2753] selftests: drv-net: Check if combined-count exists

Some drivers, like tg3, do not set combined-count:

$ ethtool -l enp4s0f1
Channel parameters for enp4s0f1:
Pre-set maximums:
RX:		4
TX:		4
Other:		n/a
Combined:	n/a
Current hardware settings:
RX:		4
TX:		1
Other:		n/a
Combined:	n/a

In the case where combined-count is not set, the ethtool netlink code
in the kernel elides the value and the code in the test:

  netnl.channels_get(...)

With a tg3 device, the returned dictionary looks like:

{'header': {'dev-index': 3, 'dev-name': 'enp4s0f1'},
 'rx-max': 4,
 'rx-count': 4,
 'tx-max': 4,
 'tx-count': 1}

Note that the key 'combined-count' is missing. As a result of this
missing key the test raises an exception:

 # Exception|     if channels['combined-count'] == 0:
 # Exception|        ~~~~~~~~^^^^^^^^^^^^^^^^^^
 # Exception| KeyError: 'combined-count'

Change the test to check if 'combined-count' is a key in the dictionary
first and if not assume that this means the driver has separate RX and
TX queues.

With this change, the test now passes successfully on tg3 and mlx5
(which does have a 'combined-count').

Fixes: 1cf270424218 ("net: selftest: add test for netdev netlink queue-get API")
Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: David Wei <dw@davidwei.uk>
Link: https://patch.msgid.link/20250226181957.212189-1-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/queues.py | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/queues.py b/tools/testing/selftests/drivers/net/queues.py
index 38303da957ee5..8a518905a9f9c 100755
--- a/tools/testing/selftests/drivers/net/queues.py
+++ b/tools/testing/selftests/drivers/net/queues.py
@@ -45,10 +45,9 @@ def addremove_queues(cfg, nl) -> None:
 
     netnl = EthtoolFamily()
     channels = netnl.channels_get({'header': {'dev-index': cfg.ifindex}})
-    if channels['combined-count'] == 0:
-        rx_type = 'rx'
-    else:
-        rx_type = 'combined'
+    rx_type = 'rx'
+    if channels.get('combined-count', 0) > 0:
+            rx_type = 'combined'
 
     expected = curr_queues - 1
     cmd(f"ethtool -L {cfg.dev['ifname']} {rx_type} {expected}", timeout=10)

From 674fcb4f4a7e3e277417a01788cc6daae47c3804 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2025 22:12:52 +0000
Subject: [PATCH 1282/2753] idpf: fix checksums set in idpf_rx_rsc()

idpf_rx_rsc() uses skb_transport_offset(skb) while the transport header
is not set yet.

This triggers the following warning for CONFIG_DEBUG_NET=y builds.

DEBUG_NET_WARN_ON_ONCE(!skb_transport_header_was_set(skb))

[   69.261620] WARNING: CPU: 7 PID: 0 at ./include/linux/skbuff.h:3020 idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261629] Modules linked in: vfat fat dummy bridge intel_uncore_frequency_tpmi intel_uncore_frequency_common intel_vsec_tpmi idpf intel_vsec cdc_ncm cdc_eem cdc_ether usbnet mii xhci_pci xhci_hcd ehci_pci ehci_hcd libeth
[   69.261644] CPU: 7 UID: 0 PID: 0 Comm: swapper/7 Tainted: G S      W          6.14.0-smp-DEV #1697
[   69.261648] Tainted: [S]=CPU_OUT_OF_SPEC, [W]=WARN
[   69.261650] RIP: 0010:idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261677] ? __warn (kernel/panic.c:242 kernel/panic.c:748)
[   69.261682] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261687] ? report_bug (lib/bug.c:?)
[   69.261690] ? handle_bug (arch/x86/kernel/traps.c:285)
[   69.261694] ? exc_invalid_op (arch/x86/kernel/traps.c:309)
[   69.261697] ? asm_exc_invalid_op (arch/x86/include/asm/idtentry.h:621)
[   69.261700] ? __pfx_idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:4011) idpf
[   69.261704] ? idpf_vport_splitq_napi_poll (include/linux/skbuff.h:3020) idpf
[   69.261708] ? idpf_vport_splitq_napi_poll (drivers/net/ethernet/intel/idpf/idpf_txrx.c:3072) idpf
[   69.261712] __napi_poll (net/core/dev.c:7194)
[   69.261716] net_rx_action (net/core/dev.c:7265)
[   69.261718] ? __qdisc_run (net/sched/sch_generic.c:293)
[   69.261721] ? sched_clock (arch/x86/include/asm/preempt.h:84 arch/x86/kernel/tsc.c:288)
[   69.261726] handle_softirqs (kernel/softirq.c:561)

Fixes: 3a8845af66edb ("idpf: add RX splitq napi poll support")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Alan Brady <alan.brady@intel.com>
Cc: Joshua Hay <joshua.a.hay@intel.com>
Cc: Willem de Bruijn <willemb@google.com>
Acked-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20250226221253.1927782-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/idpf/idpf_txrx.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 9be6a6b59c4e1..977741c414980 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3013,7 +3013,6 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	skb_shinfo(skb)->gso_size = rsc_seg_len;
 
 	skb_reset_network_header(skb);
-	len = skb->len - skb_transport_offset(skb);
 
 	if (ipv4) {
 		struct iphdr *ipv4h = ip_hdr(skb);
@@ -3022,6 +3021,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		/* Reset and set transport header offset in skb */
 		skb_set_transport_header(skb, sizeof(struct iphdr));
+		len = skb->len - skb_transport_offset(skb);
 
 		/* Compute the TCP pseudo header checksum*/
 		tcp_hdr(skb)->check =
@@ -3031,6 +3031,7 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 
 		skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 		skb_set_transport_header(skb, sizeof(struct ipv6hdr));
+		len = skb->len - skb_transport_offset(skb);
 		tcp_hdr(skb)->check =
 			~tcp_v6_check(len, &ipv6h->saddr, &ipv6h->daddr, 0);
 	}

From 54e1b4becf5e220be03db4e1be773c1310e8cbbd Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Thu, 27 Feb 2025 14:54:41 +0530
Subject: [PATCH 1283/2753] net: ti: icss-iep: Reject perout generation request

IEP driver supports both perout and pps signal generation
but perout feature is faulty with half-cooked support
due to some missing configuration. Remove perout
support from the driver and reject perout requests with
"not supported" error code.

Fixes: c1e0230eeaab2 ("net: ti: icss-iep: Add IEP driver")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250227092441.1848419-1-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 21 +--------------------
 1 file changed, 1 insertion(+), 20 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 768578c0d9587..d59c1744840af 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -474,26 +474,7 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 static int icss_iep_perout_enable(struct icss_iep *iep,
 				  struct ptp_perout_request *req, int on)
 {
-	int ret = 0;
-
-	mutex_lock(&iep->ptp_clk_mutex);
-
-	if (iep->pps_enabled) {
-		ret = -EBUSY;
-		goto exit;
-	}
-
-	if (iep->perout_enabled == !!on)
-		goto exit;
-
-	ret = icss_iep_perout_enable_hw(iep, req, on);
-	if (!ret)
-		iep->perout_enabled = !!on;
-
-exit:
-	mutex_unlock(&iep->ptp_clk_mutex);
-
-	return ret;
+	return -EOPNOTSUPP;
 }
 
 static void icss_iep_cap_cmp_work(struct work_struct *work)

From 68410c5bd381a81bcc92b808e7dc4e6b9ed25d11 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 25 Feb 2025 11:04:45 +0530
Subject: [PATCH 1284/2753] wifi: ath11k: Clear affinity hint before calling
 ath11k_pcic_free_irq() in error path

If a shared IRQ is used by the driver due to platform limitation, then the
IRQ affinity hint is set right after the allocation of IRQ vectors in
ath11k_pci_alloc_msi(). This does no harm unless one of the functions
requesting the IRQ fails and attempt to free the IRQ. This results in the
below warning:

WARNING: CPU: 7 PID: 349 at kernel/irq/manage.c:1929 free_irq+0x278/0x29c
Call trace:
 free_irq+0x278/0x29c
 ath11k_pcic_free_irq+0x70/0x10c [ath11k]
 ath11k_pci_probe+0x800/0x820 [ath11k_pci]
 local_pci_probe+0x40/0xbc

The warning is due to not clearing the affinity hint before freeing the
IRQs.

So to fix this issue, clear the IRQ affinity hint before calling
ath11k_pcic_free_irq() in the error path. The affinity will be cleared once
again further down the error path due to code organization, but that does
no harm.

Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-05266-QCAHSTSWPLZ_V2_TO_X86-1

Cc: Baochen Qiang <quic_bqiang@quicinc.com>
Fixes: 39564b475ac5 ("wifi: ath11k: fix boot failure with one MSI vector")
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250225053447.16824-2-manivannan.sadhasivam@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 6565ac1917b79..450ac5313de19 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -1125,6 +1125,8 @@ static int ath11k_pci_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
+	/* __free_irq() expects the caller to have cleared the affinity hint */
+	ath11k_pci_set_irq_affinity_hint(ab_pci, NULL);
 	ath11k_pcic_free_irq(ab);
 
 err_ce_free:

From b43b1e2c52db77c872bd60d30cdcc72c47df70c7 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 25 Feb 2025 11:04:46 +0530
Subject: [PATCH 1285/2753] wifi: ath12k: Clear affinity hint before calling
 ath12k_pci_free_irq() in error path

If a shared IRQ is used by the driver due to platform limitation, then the
IRQ affinity hint is set right after the allocation of IRQ vectors in
ath12k_pci_msi_alloc(). This does no harm unless one of the functions
requesting the IRQ fails and attempt to free the IRQ.

This may end up with a warning from the IRQ core that is expecting the
affinity hint to be cleared before freeing the IRQ:

kernel/irq/manage.c:

	/* make sure affinity_hint is cleaned up */
	if (WARN_ON_ONCE(desc->affinity_hint))
		desc->affinity_hint = NULL;

So to fix this issue, clear the IRQ affinity hint before calling
ath12k_pci_free_irq() in the error path. The affinity will be cleared once
again further down the error path due to code organization, but that does
no harm.

Fixes: a3012f206d07 ("wifi: ath12k: set IRQ affinity to CPU0 in case of one MSI vector")
Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Reviewed-by: Baochen Qiang <quic_bqiang@quicinc.com>
Link: https://patch.msgid.link/20250225053447.16824-3-manivannan.sadhasivam@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/pci.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 7126cc361deff..213a0f21d5880 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -1697,6 +1697,8 @@ static int ath12k_pci_probe(struct pci_dev *pdev,
 	return 0;
 
 err_free_irq:
+	/* __free_irq() expects the caller to have cleared the affinity hint */
+	ath12k_pci_set_irq_affinity_hint(ab_pci, NULL);
 	ath12k_pci_free_irq(ab);
 
 err_ce_free:

From 6f2d839d11b36c630dbcad2c68613f15409de392 Mon Sep 17 00:00:00 2001
From: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Date: Tue, 25 Feb 2025 11:04:47 +0530
Subject: [PATCH 1286/2753] wifi: ath11k/ath12k: Replace
 irq_set_affinity_hint() with irq_set_affinity_and_hint()

irq_set_affinity_hint() API is deprecated now, so let's use the recommended
equivalent irq_set_affinity_and_hint().

Tested-on: QCA6390 hw2.0 PCI WLAN.HST.1.0.1-05266-QCAHSTSWPLZ_V2_TO_X86-1

Signed-off-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>
Link: https://patch.msgid.link/20250225053447.16824-4-manivannan.sadhasivam@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/pci.c | 2 +-
 drivers/net/wireless/ath/ath12k/pci.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
index 450ac5313de19..412f4a134e4a8 100644
--- a/drivers/net/wireless/ath/ath11k/pci.c
+++ b/drivers/net/wireless/ath/ath11k/pci.c
@@ -921,7 +921,7 @@ static int ath11k_pci_set_irq_affinity_hint(struct ath11k_pci *ab_pci,
 	if (test_bit(ATH11K_FLAG_MULTI_MSI_VECTORS, &ab_pci->ab->dev_flags))
 		return 0;
 
-	return irq_set_affinity_hint(ab_pci->pdev->irq, m);
+	return irq_set_affinity_and_hint(ab_pci->pdev->irq, m);
 }
 
 static int ath11k_pci_probe(struct pci_dev *pdev,
diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
index 213a0f21d5880..b474696ac6d8c 100644
--- a/drivers/net/wireless/ath/ath12k/pci.c
+++ b/drivers/net/wireless/ath/ath12k/pci.c
@@ -649,7 +649,7 @@ static int ath12k_pci_set_irq_affinity_hint(struct ath12k_pci *ab_pci,
 	if (test_bit(ATH12K_PCI_FLAG_MULTI_MSI_VECTORS, &ab_pci->flags))
 		return 0;
 
-	return irq_set_affinity_hint(ab_pci->pdev->irq, m);
+	return irq_set_affinity_and_hint(ab_pci->pdev->irq, m);
 }
 
 static int ath12k_pci_config_irq(struct ath12k_base *ab)

From 2b90e7ace79774a3540ce569e000388f8d22c9e0 Mon Sep 17 00:00:00 2001
From: Peter Jones <pjones@redhat.com>
Date: Wed, 26 Feb 2025 15:18:39 -0500
Subject: [PATCH 1287/2753] efi: Don't map the entire mokvar table to determine
 its size

Currently, when validating the mokvar table, we (re)map the entire table
on each iteration of the loop, adding space as we discover new entries.
If the table grows over a certain size, this fails due to limitations of
early_memmap(), and we get a failure and traceback:

  ------------[ cut here ]------------
  WARNING: CPU: 0 PID: 0 at mm/early_ioremap.c:139 __early_ioremap+0xef/0x220
  ...
  Call Trace:
   <TASK>
   ? __early_ioremap+0xef/0x220
   ? __warn.cold+0x93/0xfa
   ? __early_ioremap+0xef/0x220
   ? report_bug+0xff/0x140
   ? early_fixup_exception+0x5d/0xb0
   ? early_idt_handler_common+0x2f/0x3a
   ? __early_ioremap+0xef/0x220
   ? efi_mokvar_table_init+0xce/0x1d0
   ? setup_arch+0x864/0xc10
   ? start_kernel+0x6b/0xa10
   ? x86_64_start_reservations+0x24/0x30
   ? x86_64_start_kernel+0xed/0xf0
   ? common_startup_64+0x13e/0x141
   </TASK>
  ---[ end trace 0000000000000000 ]---
  mokvar: Failed to map EFI MOKvar config table pa=0x7c4c3000, size=265187.

Mapping the entire structure isn't actually necessary, as we don't ever
need more than one entry header mapped at once.

Changes efi_mokvar_table_init() to only map each entry header, not the
entire table, when determining the table size.  Since we're not mapping
any data past the variable name, it also changes the code to enforce
that each variable name is NUL terminated, rather than attempting to
verify it in place.

Cc: <stable@vger.kernel.org>
Signed-off-by: Peter Jones <pjones@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/mokvar-table.c | 41 +++++++++--------------------
 1 file changed, 13 insertions(+), 28 deletions(-)

diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index 5ed0602c2f75f..d865cb1dbaad1 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -103,7 +103,6 @@ void __init efi_mokvar_table_init(void)
 	void *va = NULL;
 	unsigned long cur_offset = 0;
 	unsigned long offset_limit;
-	unsigned long map_size = 0;
 	unsigned long map_size_needed = 0;
 	unsigned long size;
 	struct efi_mokvar_table_entry *mokvar_entry;
@@ -134,48 +133,34 @@ void __init efi_mokvar_table_init(void)
 	 */
 	err = -EINVAL;
 	while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
-		mokvar_entry = va + cur_offset;
-		map_size_needed = cur_offset + sizeof(*mokvar_entry);
-		if (map_size_needed > map_size) {
-			if (va)
-				early_memunmap(va, map_size);
-			/*
-			 * Map a little more than the fixed size entry
-			 * header, anticipating some data. It's safe to
-			 * do so as long as we stay within current memory
-			 * descriptor.
-			 */
-			map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
-				       offset_limit);
-			va = early_memremap(efi.mokvar_table, map_size);
-			if (!va) {
-				pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%lu.\n",
-				       efi.mokvar_table, map_size);
-				return;
-			}
-			mokvar_entry = va + cur_offset;
+		if (va)
+			early_memunmap(va, sizeof(*mokvar_entry));
+		va = early_memremap(efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+		if (!va) {
+			pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
+			       efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
+			return;
 		}
+		mokvar_entry = va;
 
 		/* Check for last sentinel entry */
 		if (mokvar_entry->name[0] == '\0') {
 			if (mokvar_entry->data_size != 0)
 				break;
 			err = 0;
+			map_size_needed = cur_offset + sizeof(*mokvar_entry);
 			break;
 		}
 
-		/* Sanity check that the name is null terminated */
-		size = strnlen(mokvar_entry->name,
-			       sizeof(mokvar_entry->name));
-		if (size >= sizeof(mokvar_entry->name))
-			break;
+		/* Enforce that the name is NUL terminated */
+		mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
 
 		/* Advance to the next entry */
-		cur_offset = map_size_needed + mokvar_entry->data_size;
+		cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
 	}
 
 	if (va)
-		early_memunmap(va, map_size);
+		early_memunmap(va, sizeof(*mokvar_entry));
 	if (err) {
 		pr_err("EFI MOKvar config table is not valid\n");
 		return;

From e3cf2d91d0583cae70aeb512da87e3ade25ea912 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 27 Feb 2025 14:30:22 +0100
Subject: [PATCH 1288/2753] efi/mokvar-table: Avoid repeated map/unmap of the
 same page

Tweak the logic that traverses the MOKVAR UEFI configuration table to
only unmap the entry header and map the next one if they don't live in
the same physical page.

Link: https://lore.kernel.org/all/8f085931-3e9d-4386-9209-1d6c95616327@uncooperative.org/
Tested-By: Peter Jones <pjones@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/mokvar-table.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/firmware/efi/mokvar-table.c b/drivers/firmware/efi/mokvar-table.c
index d865cb1dbaad1..208db29613c63 100644
--- a/drivers/firmware/efi/mokvar-table.c
+++ b/drivers/firmware/efi/mokvar-table.c
@@ -99,13 +99,13 @@ static struct kobject *mokvar_kobj;
  */
 void __init efi_mokvar_table_init(void)
 {
+	struct efi_mokvar_table_entry __aligned(1) *mokvar_entry, *next_entry;
 	efi_memory_desc_t md;
 	void *va = NULL;
 	unsigned long cur_offset = 0;
 	unsigned long offset_limit;
 	unsigned long map_size_needed = 0;
 	unsigned long size;
-	struct efi_mokvar_table_entry *mokvar_entry;
 	int err;
 
 	if (!efi_enabled(EFI_MEMMAP))
@@ -142,7 +142,7 @@ void __init efi_mokvar_table_init(void)
 			return;
 		}
 		mokvar_entry = va;
-
+next:
 		/* Check for last sentinel entry */
 		if (mokvar_entry->name[0] == '\0') {
 			if (mokvar_entry->data_size != 0)
@@ -156,7 +156,19 @@ void __init efi_mokvar_table_init(void)
 		mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
 
 		/* Advance to the next entry */
-		cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
+		size = sizeof(*mokvar_entry) + mokvar_entry->data_size;
+		cur_offset += size;
+
+		/*
+		 * Don't bother remapping if the current entry header and the
+		 * next one end on the same page.
+		 */
+		next_entry = (void *)((unsigned long)mokvar_entry + size);
+		if (((((unsigned long)(mokvar_entry + 1) - 1) ^
+		      ((unsigned long)(next_entry + 1) - 1)) & PAGE_MASK) == 0) {
+			mokvar_entry = next_entry;
+			goto next;
+		}
 	}
 
 	if (va)

From 02410ac72ac3707936c07ede66e94360d0d65319 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:51 +0000
Subject: [PATCH 1289/2753] mm: hugetlb: Add huge page size param to
 huge_ptep_get_and_clear()

In order to fix a bug, arm64 needs to be told the size of the huge page
for which the huge_pte is being cleared in huge_ptep_get_and_clear().
Provide for this by adding an `unsigned long sz` parameter to the
function. This follows the same pattern as huge_pte_clear() and
set_huge_pte_at().

This commit makes the required interface modifications to the core mm as
well as all arches that implement this function (arm64, loongarch, mips,
parisc, powerpc, riscv, s390, sparc). The actual arm64 bug will be fixed
in a separate commit.

Cc: stable@vger.kernel.org
Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit")
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Alexandre Ghiti <alexghiti@rivosinc.com> # riscv
Reviewed-by: Christophe Leroy <christophe.leroy@csgroup.eu>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> # s390
Link: https://lore.kernel.org/r/20250226120656.2400136-2-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/hugetlb.h     |  4 ++--
 arch/arm64/mm/hugetlbpage.c          |  8 +++++---
 arch/loongarch/include/asm/hugetlb.h |  6 ++++--
 arch/mips/include/asm/hugetlb.h      |  6 ++++--
 arch/parisc/include/asm/hugetlb.h    |  2 +-
 arch/parisc/mm/hugetlbpage.c         |  2 +-
 arch/powerpc/include/asm/hugetlb.h   |  6 ++++--
 arch/riscv/include/asm/hugetlb.h     |  3 ++-
 arch/riscv/mm/hugetlbpage.c          |  2 +-
 arch/s390/include/asm/hugetlb.h      | 16 ++++++++++++----
 arch/s390/mm/hugetlbpage.c           |  4 ++--
 arch/sparc/include/asm/hugetlb.h     |  2 +-
 arch/sparc/mm/hugetlbpage.c          |  2 +-
 include/asm-generic/hugetlb.h        |  2 +-
 include/linux/hugetlb.h              |  4 +++-
 mm/hugetlb.c                         |  4 ++--
 16 files changed, 46 insertions(+), 27 deletions(-)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index c6dff3e69539b..03db9cb21ace8 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -42,8 +42,8 @@ extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-				     unsigned long addr, pte_t *ptep);
+extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				     pte_t *ptep, unsigned long sz);
 #define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 98a2a0e64e255..06db4649af916 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -396,8 +396,8 @@ void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		__pte_clear(mm, addr, ptep);
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, unsigned long sz)
 {
 	int ncontig;
 	size_t pgsize;
@@ -549,6 +549,8 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
@@ -558,7 +560,7 @@ pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr
 		if (pte_user_exec(__ptep_get(ptep)))
 			return huge_ptep_clear_flush(vma, addr, ptep);
 	}
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 
 void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep,
diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index c8e4057734d0d..4dc4b3e04225f 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -36,7 +36,8 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = ptep_get(ptep);
@@ -51,8 +52,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index d0a86ce83de91..fbc71ddcf0f68 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -27,7 +27,8 @@ static inline int prepare_hugepage_range(struct file *file,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	pte_t clear;
 	pte_t pte = *ptep;
@@ -42,13 +43,14 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
 	/*
 	 * clear the huge pte entry firstly, so that the other smp threads will
 	 * not get old pte entry after finishing flush_tlb_page and before
 	 * setting new huge pte entry
 	 */
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_tlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/parisc/include/asm/hugetlb.h b/arch/parisc/include/asm/hugetlb.h
index 5b3a5429f71b3..21e9ace177395 100644
--- a/arch/parisc/include/asm/hugetlb.h
+++ b/arch/parisc/include/asm/hugetlb.h
@@ -10,7 +10,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/parisc/mm/hugetlbpage.c b/arch/parisc/mm/hugetlbpage.c
index e9d18cf25b792..a94fe546d434f 100644
--- a/arch/parisc/mm/hugetlbpage.c
+++ b/arch/parisc/mm/hugetlbpage.c
@@ -126,7 +126,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t entry;
 
diff --git a/arch/powerpc/include/asm/hugetlb.h b/arch/powerpc/include/asm/hugetlb.h
index dad2e7980f245..86326587e58de 100644
--- a/arch/powerpc/include/asm/hugetlb.h
+++ b/arch/powerpc/include/asm/hugetlb.h
@@ -45,7 +45,8 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
 {
 	return __pte(pte_update(mm, addr, ptep, ~0UL, 0, 1));
 }
@@ -55,8 +56,9 @@ static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
 	pte_t pte;
+	unsigned long sz = huge_page_size(hstate_vma(vma));
 
-	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	pte = huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, sz);
 	flush_hugetlb_page(vma, addr);
 	return pte;
 }
diff --git a/arch/riscv/include/asm/hugetlb.h b/arch/riscv/include/asm/hugetlb.h
index faf3624d80577..4461264977684 100644
--- a/arch/riscv/include/asm/hugetlb.h
+++ b/arch/riscv/include/asm/hugetlb.h
@@ -28,7 +28,8 @@ void set_huge_pte_at(struct mm_struct *mm,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep);
+			      unsigned long addr, pte_t *ptep,
+			      unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/riscv/mm/hugetlbpage.c b/arch/riscv/mm/hugetlbpage.c
index 42314f0939220..b4a78a4b35cff 100644
--- a/arch/riscv/mm/hugetlbpage.c
+++ b/arch/riscv/mm/hugetlbpage.c
@@ -293,7 +293,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 			      unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	pte_t orig_pte = ptep_get(ptep);
 	int pte_num;
diff --git a/arch/s390/include/asm/hugetlb.h b/arch/s390/include/asm/hugetlb.h
index 7c52acaf9f828..663e87220e89f 100644
--- a/arch/s390/include/asm/hugetlb.h
+++ b/arch/s390/include/asm/hugetlb.h
@@ -25,8 +25,16 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 #define __HAVE_ARCH_HUGE_PTEP_GET
 pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
+				pte_t *ptep);
+
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+					    unsigned long addr, pte_t *ptep,
+					    unsigned long sz)
+{
+	return __huge_ptep_get_and_clear(mm, addr, ptep);
+}
 
 static inline void arch_clear_hugetlb_flags(struct folio *folio)
 {
@@ -48,7 +56,7 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long address, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
+	return __huge_ptep_get_and_clear(vma->vm_mm, address, ptep);
 }
 
 #define  __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
@@ -59,7 +67,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	int changed = !pte_same(huge_ptep_get(vma->vm_mm, addr, ptep), pte);
 
 	if (changed) {
-		huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+		__huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
 		__set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
 	}
 	return changed;
@@ -69,7 +77,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
-	pte_t pte = huge_ptep_get_and_clear(mm, addr, ptep);
+	pte_t pte = __huge_ptep_get_and_clear(mm, addr, ptep);
 
 	__set_huge_pte_at(mm, addr, ptep, pte_wrprotect(pte));
 }
diff --git a/arch/s390/mm/hugetlbpage.c b/arch/s390/mm/hugetlbpage.c
index d9ce199953de9..2e568f175cd41 100644
--- a/arch/s390/mm/hugetlbpage.c
+++ b/arch/s390/mm/hugetlbpage.c
@@ -188,8 +188,8 @@ pte_t huge_ptep_get(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 	return __rste_to_pte(pte_val(*ptep));
 }
 
-pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-			      unsigned long addr, pte_t *ptep)
+pte_t __huge_ptep_get_and_clear(struct mm_struct *mm,
+				unsigned long addr, pte_t *ptep)
 {
 	pte_t pte = huge_ptep_get(mm, addr, ptep);
 	pmd_t *pmdp = (pmd_t *) ptep;
diff --git a/arch/sparc/include/asm/hugetlb.h b/arch/sparc/include/asm/hugetlb.h
index c714ca6a05aa0..e7a9cdd498dca 100644
--- a/arch/sparc/include/asm/hugetlb.h
+++ b/arch/sparc/include/asm/hugetlb.h
@@ -20,7 +20,7 @@ void __set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep);
+			      pte_t *ptep, unsigned long sz);
 
 #define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
diff --git a/arch/sparc/mm/hugetlbpage.c b/arch/sparc/mm/hugetlbpage.c
index eee601a0d2cfb..80504148d8a5b 100644
--- a/arch/sparc/mm/hugetlbpage.c
+++ b/arch/sparc/mm/hugetlbpage.c
@@ -260,7 +260,7 @@ void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 }
 
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
-			      pte_t *ptep)
+			      pte_t *ptep, unsigned long sz)
 {
 	unsigned int i, nptes, orig_shift, shift;
 	unsigned long size;
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index f42133dae68e5..2afc95bf1655f 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -90,7 +90,7 @@ static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 
 #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-		unsigned long addr, pte_t *ptep)
+		unsigned long addr, pte_t *ptep, unsigned long sz)
 {
 	return ptep_get_and_clear(mm, addr, ptep);
 }
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ec8c0ccc8f959..bf5f7256bd281 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -1004,7 +1004,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 #endif
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 65068671e460a..de9d49e521c13 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5447,7 +5447,7 @@ static void move_huge_pte(struct vm_area_struct *vma, unsigned long old_addr,
 	if (src_ptl != dst_ptl)
 		spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 
-	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte);
+	pte = huge_ptep_get_and_clear(mm, old_addr, src_pte, sz);
 
 	if (need_clear_uffd_wp && pte_marker_uffd_wp(pte))
 		huge_pte_clear(mm, new_addr, dst_pte, sz);
@@ -5622,7 +5622,7 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			set_vma_resv_flags(vma, HPAGE_RESV_UNMAPPED);
 		}
 
-		pte = huge_ptep_get_and_clear(mm, address, ptep);
+		pte = huge_ptep_get_and_clear(mm, address, ptep, sz);
 		tlb_remove_huge_tlb_entry(h, tlb, ptep, address);
 		if (huge_pte_dirty(pte))
 			set_page_dirty(page);

From 49c87f7677746f3c5bd16c81b23700bb6b88bfd4 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:52 +0000
Subject: [PATCH 1290/2753] arm64: hugetlb: Fix huge_ptep_get_and_clear() for
 non-present ptes

arm64 supports multiple huge_pte sizes. Some of the sizes are covered by
a single pte entry at a particular level (PMD_SIZE, PUD_SIZE), and some
are covered by multiple ptes at a particular level (CONT_PTE_SIZE,
CONT_PMD_SIZE). So the function has to figure out the size from the
huge_pte pointer. This was previously done by walking the pgtable to
determine the level and by using the PTE_CONT bit to determine the
number of ptes at the level.

But the PTE_CONT bit is only valid when the pte is present. For
non-present pte values (e.g. markers, migration entries), the previous
implementation was therefore erroneously determining the size. There is
at least one known caller in core-mm, move_huge_pte(), which may call
huge_ptep_get_and_clear() for a non-present pte. So we must be robust to
this case. Additionally the "regular" ptep_get_and_clear() is robust to
being called for non-present ptes so it makes sense to follow the
behavior.

Fix this by using the new sz parameter which is now provided to the
function. Additionally when clearing each pte in a contig range, don't
gather the access and dirty bits if the pte is not present.

An alternative approach that would not require API changes would be to
store the PTE_CONT bit in a spare bit in the swap entry pte for the
non-present case. But it felt cleaner to follow other APIs' lead and
just pass in the size.

As an aside, PTE_CONT is bit 52, which corresponds to bit 40 in the swap
entry offset field (layout of non-present pte). Since hugetlb is never
swapped to disk, this field will only be populated for markers, which
always set this bit to 0 and hwpoison swap entries, which set the offset
field to a PFN; So it would only ever be 1 for a 52-bit PVA system where
memory in that high half was poisoned (I think!). So in practice, this
bit would almost always be zero for non-present ptes and we would only
clear the first entry if it was actually a contiguous block. That's
probably a less severe symptom than if it was always interpreted as 1
and cleared out potentially-present neighboring PTEs.

Cc: stable@vger.kernel.org
Fixes: 66b3923a1a0f ("arm64: hugetlb: add support for PTE contiguous bit")
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250226120656.2400136-3-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/hugetlbpage.c | 53 ++++++++++++++-----------------------
 1 file changed, 20 insertions(+), 33 deletions(-)

diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 06db4649af916..b3a7fafe8892d 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -100,20 +100,11 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 
 static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 {
-	int contig_ptes = 0;
+	int contig_ptes = 1;
 
 	*pgsize = size;
 
 	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		if (pud_sect_supported())
-			contig_ptes = 1;
-		break;
-#endif
-	case PMD_SIZE:
-		contig_ptes = 1;
-		break;
 	case CONT_PMD_SIZE:
 		*pgsize = PMD_SIZE;
 		contig_ptes = CONT_PMDS;
@@ -122,6 +113,8 @@ static inline int num_contig_ptes(unsigned long size, size_t *pgsize)
 		*pgsize = PAGE_SIZE;
 		contig_ptes = CONT_PTES;
 		break;
+	default:
+		WARN_ON(!__hugetlb_valid_size(size));
 	}
 
 	return contig_ptes;
@@ -163,24 +156,23 @@ static pte_t get_clear_contig(struct mm_struct *mm,
 			     unsigned long pgsize,
 			     unsigned long ncontig)
 {
-	pte_t orig_pte = __ptep_get(ptep);
-	unsigned long i;
-
-	for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) {
-		pte_t pte = __ptep_get_and_clear(mm, addr, ptep);
-
-		/*
-		 * If HW_AFDBM is enabled, then the HW could turn on
-		 * the dirty or accessed bit for any page in the set,
-		 * so check them all.
-		 */
-		if (pte_dirty(pte))
-			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
-			orig_pte = pte_mkyoung(orig_pte);
+	pte_t pte, tmp_pte;
+	bool present;
+
+	pte = __ptep_get_and_clear(mm, addr, ptep);
+	present = pte_present(pte);
+	while (--ncontig) {
+		ptep++;
+		addr += pgsize;
+		tmp_pte = __ptep_get_and_clear(mm, addr, ptep);
+		if (present) {
+			if (pte_dirty(tmp_pte))
+				pte = pte_mkdirty(pte);
+			if (pte_young(tmp_pte))
+				pte = pte_mkyoung(pte);
+		}
 	}
-	return orig_pte;
+	return pte;
 }
 
 static pte_t get_clear_contig_flush(struct mm_struct *mm,
@@ -401,13 +393,8 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 {
 	int ncontig;
 	size_t pgsize;
-	pte_t orig_pte = __ptep_get(ptep);
-
-	if (!pte_cont(orig_pte))
-		return __ptep_get_and_clear(mm, addr, ptep);
-
-	ncontig = find_num_contig(mm, addr, ptep, &pgsize);
 
+	ncontig = num_contig_ptes(sz, &pgsize);
 	return get_clear_contig(mm, addr, ptep, pgsize, ncontig);
 }
 

From eed6bfa8b28230382b797a88569f2c7569a1a419 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:06:53 +0000
Subject: [PATCH 1291/2753] arm64: hugetlb: Fix flush_hugetlb_tlb_range()
 invalidation level

commit c910f2b65518 ("arm64/mm: Update tlb invalidation routines for
FEAT_LPA2") changed the "invalidation level unknown" hint from 0 to
TLBI_TTL_UNKNOWN (INT_MAX). But the fallback "unknown level" path in
flush_hugetlb_tlb_range() was not updated. So as it stands, when trying
to invalidate CONT_PMD_SIZE or CONT_PTE_SIZE hugetlb mappings, we will
spuriously try to invalidate at level 0 on LPA2-enabled systems.

Fix this so that the fallback passes TLBI_TTL_UNKNOWN, and while we are
at it, explicitly use the correct stride and level for CONT_PMD_SIZE and
CONT_PTE_SIZE, which should provide a minor optimization.

Cc: stable@vger.kernel.org
Fixes: c910f2b65518 ("arm64/mm: Update tlb invalidation routines for FEAT_LPA2")
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Link: https://lore.kernel.org/r/20250226120656.2400136-4-ryan.roberts@arm.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/hugetlb.h | 22 ++++++++++++++++------
 1 file changed, 16 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/include/asm/hugetlb.h b/arch/arm64/include/asm/hugetlb.h
index 03db9cb21ace8..07fbf5bf85a7e 100644
--- a/arch/arm64/include/asm/hugetlb.h
+++ b/arch/arm64/include/asm/hugetlb.h
@@ -76,12 +76,22 @@ static inline void flush_hugetlb_tlb_range(struct vm_area_struct *vma,
 {
 	unsigned long stride = huge_page_size(hstate_vma(vma));
 
-	if (stride == PMD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 2);
-	else if (stride == PUD_SIZE)
-		__flush_tlb_range(vma, start, end, stride, false, 1);
-	else
-		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
+	switch (stride) {
+#ifndef __PAGETABLE_PMD_FOLDED
+	case PUD_SIZE:
+		__flush_tlb_range(vma, start, end, PUD_SIZE, false, 1);
+		break;
+#endif
+	case CONT_PMD_SIZE:
+	case PMD_SIZE:
+		__flush_tlb_range(vma, start, end, PMD_SIZE, false, 2);
+		break;
+	case CONT_PTE_SIZE:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 3);
+		break;
+	default:
+		__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
+	}
 }
 
 #endif /* __ASM_HUGETLB_H */

From 6b481ab0e6855fb30e2923c51f62f1662d1cda7e Mon Sep 17 00:00:00 2001
From: Dave Airlie <airlied@redhat.com>
Date: Fri, 7 Feb 2025 11:25:31 +1000
Subject: [PATCH 1292/2753] drm/nouveau: select FW caching

nouveau tries to load some firmware during suspend that it loaded
earlier, but with fw caching disabled it hangs suspend, so just rely on
FW cache enabling instead of working around it in the driver.

Fixes: 176fdcbddfd2 ("drm/nouveau/gsp/r535: add support for booting GSP-RM")
Signed-off-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250207012531.621369-1-airlied@gmail.com
---
 drivers/gpu/drm/nouveau/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig
index ce840300578d8..1050a4617fc15 100644
--- a/drivers/gpu/drm/nouveau/Kconfig
+++ b/drivers/gpu/drm/nouveau/Kconfig
@@ -4,6 +4,7 @@ config DRM_NOUVEAU
 	depends on DRM && PCI && MMU
 	select IOMMU_API
 	select FW_LOADER
+	select FW_CACHE if PM_SLEEP
 	select DRM_CLIENT_SELECTION
 	select DRM_DISPLAY_DP_HELPER
 	select DRM_DISPLAY_HDMI_HELPER

From 82c387ef7568c0d96a918a5a78d9cad6256cfa15 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 16 Dec 2024 14:20:56 +0100
Subject: [PATCH 1293/2753] sched/core: Prevent rescheduling when interrupts
 are disabled

David reported a warning observed while loop testing kexec jump:

  Interrupts enabled after irqrouter_resume+0x0/0x50
  WARNING: CPU: 0 PID: 560 at drivers/base/syscore.c:103 syscore_resume+0x18a/0x220
   kernel_kexec+0xf6/0x180
   __do_sys_reboot+0x206/0x250
   do_syscall_64+0x95/0x180

The corresponding interrupt flag trace:

  hardirqs last  enabled at (15573): [<ffffffffa8281b8e>] __up_console_sem+0x7e/0x90
  hardirqs last disabled at (15580): [<ffffffffa8281b73>] __up_console_sem+0x63/0x90

That means __up_console_sem() was invoked with interrupts enabled. Further
instrumentation revealed that in the interrupt disabled section of kexec
jump one of the syscore_suspend() callbacks woke up a task, which set the
NEED_RESCHED flag. A later callback in the resume path invoked
cond_resched() which in turn led to the invocation of the scheduler:

  __cond_resched+0x21/0x60
  down_timeout+0x18/0x60
  acpi_os_wait_semaphore+0x4c/0x80
  acpi_ut_acquire_mutex+0x3d/0x100
  acpi_ns_get_node+0x27/0x60
  acpi_ns_evaluate+0x1cb/0x2d0
  acpi_rs_set_srs_method_data+0x156/0x190
  acpi_pci_link_set+0x11c/0x290
  irqrouter_resume+0x54/0x60
  syscore_resume+0x6a/0x200
  kernel_kexec+0x145/0x1c0
  __do_sys_reboot+0xeb/0x240
  do_syscall_64+0x95/0x180

This is a long standing problem, which probably got more visible with
the recent printk changes. Something does a task wakeup and the
scheduler sets the NEED_RESCHED flag. cond_resched() sees it set and
invokes schedule() from a completely bogus context. The scheduler
enables interrupts after context switching, which causes the above
warning at the end.

Quite some of the code paths in syscore_suspend()/resume() can result in
triggering a wakeup with the exactly same consequences. They might not
have done so yet, but as they share a lot of code with normal operations
it's just a question of time.

The problem only affects the PREEMPT_NONE and PREEMPT_VOLUNTARY scheduling
models. Full preemption is not affected as cond_resched() is disabled and
the preemption check preemptible() takes the interrupt disabled flag into
account.

Cure the problem by adding a corresponding check into cond_resched().

Reported-by: David Woodhouse <dwmw@amazon.co.uk>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: David Woodhouse <dwmw@amazon.co.uk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@vger.kernel.org
Closes: https://lore.kernel.org/all/7717fe2ac0ce5f0a2c43fdab8b11f4483d54a2a4.camel@infradead.org
---
 kernel/sched/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9aecd914ac691..67189907214d3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7285,7 +7285,7 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
 #if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
 int __sched __cond_resched(void)
 {
-	if (should_resched(0)) {
+	if (should_resched(0) && !irqs_disabled()) {
 		preempt_schedule_common();
 		return 1;
 	}

From c133ec0e5717868c9967fa3df92a55e537b1aead Mon Sep 17 00:00:00 2001
From: Michal Pecio <michal.pecio@gmail.com>
Date: Tue, 25 Feb 2025 11:59:27 +0200
Subject: [PATCH 1294/2753] usb: xhci: Enable the TRB overfetch quirk on VIA
 VL805

Raspberry Pi is a major user of those chips and they discovered a bug -
when the end of a transfer ring segment is reached, up to four TRBs can
be prefetched from the next page even if the segment ends with link TRB
and on page boundary (the chip claims to support standard 4KB pages).

It also appears that if the prefetched TRBs belong to a different ring
whose doorbell is later rung, they may be used without refreshing from
system RAM and the endpoint will stay idle if their cycle bit is stale.

Other users complain about IOMMU faults on x86 systems, unsurprisingly.

Deal with it by using existing quirk which allocates a dummy page after
each transfer ring segment. This was seen to resolve both problems. RPi
came up with a more efficient solution, shortening each segment by four
TRBs, but it complicated the driver and they ditched it for this quirk.

Also rename the quirk and add VL805 device ID macro.

Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Link: https://github.com/raspberrypi/linux/issues/4685
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=215906
CC: stable@vger.kernel.org
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250225095927.2512358-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-mem.c |  3 ++-
 drivers/usb/host/xhci-pci.c | 10 +++++++---
 drivers/usb/host/xhci.h     |  2 +-
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 92703efda1f7b..fdf0c1008225a 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -2437,7 +2437,8 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 	 * and our use of dma addresses in the trb_address_map radix tree needs
 	 * TRB_SEGMENT_SIZE alignment, so we pick the greater alignment need.
 	 */
-	if (xhci->quirks & XHCI_ZHAOXIN_TRB_FETCH)
+	if (xhci->quirks & XHCI_TRB_OVERFETCH)
+		/* Buggy HC prefetches beyond segment bounds - allocate dummy space at the end */
 		xhci->segment_pool = dma_pool_create("xHCI ring segments", dev,
 				TRB_SEGMENT_SIZE * 2, TRB_SEGMENT_SIZE * 2, xhci->page_size * 2);
 	else
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index ad0ff356f6fa0..54460d11f7ee8 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -38,6 +38,8 @@
 #define PCI_DEVICE_ID_ETRON_EJ168		0x7023
 #define PCI_DEVICE_ID_ETRON_EJ188		0x7052
 
+#define PCI_DEVICE_ID_VIA_VL805			0x3483
+
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_XHCI		0x8c31
 #define PCI_DEVICE_ID_INTEL_LYNXPOINT_LP_XHCI		0x9c31
 #define PCI_DEVICE_ID_INTEL_WILDCATPOINT_LP_XHCI	0x9cb1
@@ -418,8 +420,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 			pdev->device == 0x3432)
 		xhci->quirks |= XHCI_BROKEN_STREAMS;
 
-	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == 0x3483)
+	if (pdev->vendor == PCI_VENDOR_ID_VIA && pdev->device == PCI_DEVICE_ID_VIA_VL805) {
 		xhci->quirks |= XHCI_LPM_SUPPORT;
+		xhci->quirks |= XHCI_TRB_OVERFETCH;
+	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_ASMEDIA &&
 		pdev->device == PCI_DEVICE_ID_ASMEDIA_1042_XHCI) {
@@ -467,11 +471,11 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 
 		if (pdev->device == 0x9202) {
 			xhci->quirks |= XHCI_RESET_ON_RESUME;
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 		}
 
 		if (pdev->device == 0x9203)
-			xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+			xhci->quirks |= XHCI_TRB_OVERFETCH;
 	}
 
 	if (pdev->vendor == PCI_VENDOR_ID_CDNS &&
diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
index 8c164340a2c35..779b01dee068f 100644
--- a/drivers/usb/host/xhci.h
+++ b/drivers/usb/host/xhci.h
@@ -1632,7 +1632,7 @@ struct xhci_hcd {
 #define XHCI_EP_CTX_BROKEN_DCS	BIT_ULL(42)
 #define XHCI_SUSPEND_RESUME_CLKS	BIT_ULL(43)
 #define XHCI_RESET_TO_DEFAULT	BIT_ULL(44)
-#define XHCI_ZHAOXIN_TRB_FETCH	BIT_ULL(45)
+#define XHCI_TRB_OVERFETCH	BIT_ULL(45)
 #define XHCI_ZHAOXIN_HOST	BIT_ULL(46)
 #define XHCI_WRITE_64_HI_LO	BIT_ULL(47)
 #define XHCI_CDNS_SCTX_QUIRK	BIT_ULL(48)

From 2397d61ee45cddb8f3bd3a3a9840ef0f0b5aa843 Mon Sep 17 00:00:00 2001
From: Christian Heusel <christian@heusel.eu>
Date: Mon, 24 Feb 2025 09:32:59 +0100
Subject: [PATCH 1295/2753] Revert "drivers/card_reader/rtsx_usb: Restore
 interrupt based detection"

This reverts commit 235b630eda072d7e7b102ab346d6b8a2c028a772.

This commit was found responsible for issues with SD card recognition,
as users had to re-insert their cards in the readers and wait for a
while. As for some people the SD card was involved in the boot process
it also caused boot failures.

Cc: stable@vger.kernel.org
Link: https://bbs.archlinux.org/viewtopic.php?id=303321
Fixes: 235b630eda07 ("drivers/card_reader/rtsx_usb: Restore interrupt based detection")
Reported-by: qf <quintafeira@tutanota.com>
Closes: https://lore.kernel.org/all/1de87dfa-1e81-45b7-8dcb-ad86c21d5352@heusel.eu
Signed-off-by: Christian Heusel <christian@heusel.eu>
Link: https://lore.kernel.org/r/20250224-revert-sdcard-patch-v1-1-d1a457fbb796@heusel.eu
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/cardreader/rtsx_usb.c | 15 ---------------
 1 file changed, 15 deletions(-)

diff --git a/drivers/misc/cardreader/rtsx_usb.c b/drivers/misc/cardreader/rtsx_usb.c
index e0174da5e9fc3..77b0490a1b38d 100644
--- a/drivers/misc/cardreader/rtsx_usb.c
+++ b/drivers/misc/cardreader/rtsx_usb.c
@@ -286,7 +286,6 @@ static int rtsx_usb_get_status_with_bulk(struct rtsx_ucr *ucr, u16 *status)
 int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 {
 	int ret;
-	u8 interrupt_val = 0;
 	u16 *buf;
 
 	if (!status)
@@ -309,20 +308,6 @@ int rtsx_usb_get_card_status(struct rtsx_ucr *ucr, u16 *status)
 		ret = rtsx_usb_get_status_with_bulk(ucr, status);
 	}
 
-	rtsx_usb_read_register(ucr, CARD_INT_PEND, &interrupt_val);
-	/* Cross check presence with interrupts */
-	if (*status & XD_CD)
-		if (!(interrupt_val & XD_INT))
-			*status &= ~XD_CD;
-
-	if (*status & SD_CD)
-		if (!(interrupt_val & SD_INT))
-			*status &= ~SD_CD;
-
-	if (*status & MS_CD)
-		if (!(interrupt_val & MS_INT))
-			*status &= ~MS_CD;
-
 	/* usb_control_msg may return positive when success */
 	if (ret < 0)
 		return ret;

From cbf85b9cb80bec6345ffe0368dfff98386f4714f Mon Sep 17 00:00:00 2001
From: Salah Triki <salah.triki@gmail.com>
Date: Fri, 21 Feb 2025 22:32:59 +0100
Subject: [PATCH 1296/2753] bluetooth: btusb: Initialize .owner field of
 force_poll_sync_fops

Initialize .owner field of force_poll_sync_fops to THIS_MODULE in order to
prevent btusb from being unloaded while its operations are in use.

Fixes: 800fe5ec302e ("Bluetooth: btusb: Add support for queuing during polling interval")
Signed-off-by: Salah Triki <salah.triki@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 8149e53fd0a76..2a8d91963c63f 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3644,6 +3644,7 @@ static ssize_t force_poll_sync_write(struct file *file,
 }
 
 static const struct file_operations force_poll_sync_fops = {
+	.owner		= THIS_MODULE,
 	.open		= simple_open,
 	.read		= force_poll_sync_read,
 	.write		= force_poll_sync_write,

From f2176a07e7b19f73e05c805cf3d130a2999154cb Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 21 Feb 2025 16:49:47 +0800
Subject: [PATCH 1297/2753] Bluetooth: Add check for mgmt_alloc_skb() in
 mgmt_remote_name()

Add check for the return value of mgmt_alloc_skb() in
mgmt_remote_name() to prevent null pointer dereference.

Fixes: ba17bb62ce41 ("Bluetooth: Fix skb allocation in mgmt_remote_name() & mgmt_device_connected()")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index f53304cb09dbe..3e0f88cd975c8 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -10413,6 +10413,8 @@ void mgmt_remote_name(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 
 	skb = mgmt_alloc_skb(hdev, MGMT_EV_DEVICE_FOUND,
 			     sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0));
+	if (!skb)
+		return;
 
 	ev = skb_put(skb, sizeof(*ev));
 	bacpy(&ev->addr.bdaddr, bdaddr);

From d8df010f72b8a32aaea393e36121738bb53ed905 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 21 Feb 2025 16:58:01 +0800
Subject: [PATCH 1298/2753] Bluetooth: Add check for mgmt_alloc_skb() in
 mgmt_device_connected()

Add check for the return value of mgmt_alloc_skb() in
mgmt_device_connected() to prevent null pointer dereference.

Fixes: e96741437ef0 ("Bluetooth: mgmt: Make use of mgmt_send_event_skb in MGMT_EV_DEVICE_CONNECTED")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 3e0f88cd975c8..621c555f639be 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -9660,6 +9660,9 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
 				     sizeof(*ev) + (name ? eir_precalc_len(name_len) : 0) +
 				     eir_precalc_len(sizeof(conn->dev_class)));
 
+	if (!skb)
+		return;
+
 	ev = skb_put(skb, sizeof(*ev));
 	bacpy(&ev->addr.bdaddr, &conn->dst);
 	ev->addr.type = link_to_bdaddr(conn->type, conn->dst_type);

From 0979ff3676b1b4e6a20970bc265491d23c2da42b Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Thu, 27 Feb 2025 20:00:05 +0100
Subject: [PATCH 1299/2753] nvmet: remove old function prototype

nvmet_subsys_nsid_exists() doesn't exist anymore

Fixes: 74d16965d7ac ("nvmet-loop: avoid using mutex in IO hotpath")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/nvmet.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/nvme/target/nvmet.h b/drivers/nvme/target/nvmet.h
index d2c1233981e1a..fcf4f460dc9a4 100644
--- a/drivers/nvme/target/nvmet.h
+++ b/drivers/nvme/target/nvmet.h
@@ -647,7 +647,6 @@ void nvmet_subsys_disc_changed(struct nvmet_subsys *subsys,
 		struct nvmet_host *host);
 void nvmet_add_async_event(struct nvmet_ctrl *ctrl, u8 event_type,
 		u8 event_info, u8 log_page);
-bool nvmet_subsys_nsid_exists(struct nvmet_subsys *subsys, u32 nsid);
 
 #define NVMET_MIN_QUEUE_SIZE	16
 #define NVMET_MAX_QUEUE_SIZE	1024

From afb41b08c44e5386f2f52fa859010ac4afd2b66f Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Mon, 24 Feb 2025 15:40:58 +0100
Subject: [PATCH 1300/2753] nvme-tcp: Fix a C2HTermReq error message

In H2CTermReq, a FES with value 0x05 means "R2T Limit Exceeded"; but
in C2HTermReq the same value has a different meaning (Data Transfer Limit
Exceeded).

Fixes: 84e009042d0f ("nvme-tcp: add basic support for the C2HTermReq PDU")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 8c14018201dbd..1094cbbec169f 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -775,7 +775,7 @@ static void nvme_tcp_handle_c2h_term(struct nvme_tcp_queue *queue,
 		[NVME_TCP_FES_PDU_SEQ_ERR] = "PDU Sequence Error",
 		[NVME_TCP_FES_HDR_DIGEST_ERR] = "Header Digest Error",
 		[NVME_TCP_FES_DATA_OUT_OF_RANGE] = "Data Transfer Out Of Range",
-		[NVME_TCP_FES_R2T_LIMIT_EXCEEDED] = "R2T Limit Exceeded",
+		[NVME_TCP_FES_DATA_LIMIT_EXCEEDED] = "Data Transfer Limit Exceeded",
 		[NVME_TCP_FES_UNSUPPORTED_PARAM] = "Unsupported Parameter",
 	};
 

From f8131f4cc5bda6154d81ee5bafe3db7e2e72a89c Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 21:09:23 +0100
Subject: [PATCH 1301/2753] net: qed: make 'qed_ll2_ops_pass' as __maybe_unused

gcc warns about unused const variables even in header files when
building with W=1:

    In file included from include/linux/qed/qed_rdma_if.h:14,
                     from drivers/net/ethernet/qlogic/qed/qed_rdma.h:16,
                     from drivers/net/ethernet/qlogic/qed/qed_cxt.c:23:
    include/linux/qed/qed_ll2_if.h:270:33: error: 'qed_ll2_ops_pass' defined but not used [-Werror=unused-const-variable=]
      270 | static const struct qed_ll2_ops qed_ll2_ops_pass = {

This one is intentional, so mark it as __maybe_unused to it can be
included from a file that doesn't use this variable.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Simon Horman <horms@kernel.org> # build-tested
Link: https://patch.msgid.link/20250225200926.4057723-1-arnd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/qed/qed_ll2_if.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h
index 5b67cd03276eb..aa29ac53b8330 100644
--- a/include/linux/qed/qed_ll2_if.h
+++ b/include/linux/qed/qed_ll2_if.h
@@ -267,7 +267,7 @@ struct qed_ll2_ops {
 int qed_ll2_alloc_if(struct qed_dev *);
 void qed_ll2_dealloc_if(struct qed_dev *);
 #else
-static const struct qed_ll2_ops qed_ll2_ops_pass = {
+static __maybe_unused const struct qed_ll2_ops qed_ll2_ops_pass = {
 	.start = NULL,
 	.stop = NULL,
 	.start_xmit = NULL,

From 047e059cf21210f633bb538799107af10650a9c7 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Tue, 25 Feb 2025 22:29:27 +0100
Subject: [PATCH 1302/2753] netkit: Remove double invocation to clear ipvs
 property flag

With ipvs_reset() now done unconditionally in skb_scrub_packet()
we would then call the former twice netkit_prep_forward(). Thus
remove the now unnecessary explicit call.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250225212927.69271-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netkit.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index 751347392570e..d072a7968f567 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -65,7 +65,6 @@ static void netkit_prep_forward(struct sk_buff *skb,
 	skb_reset_mac_header(skb);
 	if (!xnet)
 		return;
-	ipvs_reset(skb);
 	skb_clear_tstamp(skb);
 	if (xnet_scrub)
 		netkit_xnet(skb);

From bf08fd32cc55961c720f6f48a0fe317f0c710f09 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Wed, 26 Feb 2025 13:47:32 +1030
Subject: [PATCH 1303/2753] net/mlx5e: Avoid a hundred
 -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in this particular case, we create a new `struct mlx5e_umr_wqe_hdr`
to enclose the header part of flexible structure `struct mlx5e_umr_wqe`.
This is, all the members except the flexible arrays `inline_mtts`,
`inline_klms` and `inline_ksms` in the anonymous union. We then replace
the header part with `struct mlx5e_umr_wqe_hdr hdr;` in `struct
mlx5e_umr_wqe`, and change the type of the object currently causing
trouble `umr_wqe` from `struct mlx5e_umr_wqe` to `struct
mlx5e_umr_wqe_hdr` --this last bit gets rid of the flex-array-in-the-middle
part and avoid the warnings.

Also, no new members should be added to `struct mlx5e_umr_wqe`, instead
any new members must be included in the header structure `struct
mlx5e_umr_wqe_hdr`. To enforce this, we use `static_assert()`, ensuring
that the memory layout of both the flexible structure and the newly
created header struct remain consistent.

The next step is to refactor the rest of the related code accordingly,
which means adding a bunch of `hdr.` wherever needed.

Lastly, we use `container_of()` whenever we need to retrieve a pointer
to the flexible structure `struct mlx5e_umr_wqe`.

So, with these changes, fix 125 of the following warnings:

drivers/net/ethernet/mellanox/mlx5/core/en.h:664:48: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Reviewed-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://patch.msgid.link/Z76HzPW1dFTLOSSy@kspp
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  | 10 +++++++--
 .../ethernet/mellanox/mlx5/core/en/xsk/rx.c   |  6 ++---
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  8 ++++---
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 22 +++++++++----------
 4 files changed, 27 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 769e683f24883..8df185e2ef7fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -230,16 +230,22 @@ struct mlx5e_rx_wqe_cyc {
 	DECLARE_FLEX_ARRAY(struct mlx5_wqe_data_seg, data);
 };
 
-struct mlx5e_umr_wqe {
+struct mlx5e_umr_wqe_hdr {
 	struct mlx5_wqe_ctrl_seg       ctrl;
 	struct mlx5_wqe_umr_ctrl_seg   uctrl;
 	struct mlx5_mkey_seg           mkc;
+};
+
+struct mlx5e_umr_wqe {
+	struct mlx5e_umr_wqe_hdr hdr;
 	union {
 		DECLARE_FLEX_ARRAY(struct mlx5_mtt, inline_mtts);
 		DECLARE_FLEX_ARRAY(struct mlx5_klm, inline_klms);
 		DECLARE_FLEX_ARRAY(struct mlx5_ksm, inline_ksms);
 	};
 };
+static_assert(offsetof(struct mlx5e_umr_wqe, inline_mtts) == sizeof(struct mlx5e_umr_wqe_hdr),
+	      "struct members should be included in struct mlx5e_umr_wqe_hdr, not in struct mlx5e_umr_wqe");
 
 enum mlx5e_priv_flag {
 	MLX5E_PFLAG_RX_CQE_BASED_MODER,
@@ -657,7 +663,7 @@ struct mlx5e_rq {
 		} wqe;
 		struct {
 			struct mlx5_wq_ll      wq;
-			struct mlx5e_umr_wqe   umr_wqe;
+			struct mlx5e_umr_wqe_hdr umr_wqe;
 			struct mlx5e_mpw_info *info;
 			mlx5e_fp_skb_from_cqe_mpwrq skb_from_cqe_mpwrq;
 			__be32                 umr_mkey_be;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
index 1b7132fa70de2..2b05536d564ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c
@@ -123,7 +123,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((icosq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) | MLX5_OPCODE_UMR);
 
 	/* Optimized for speed: keep in sync with mlx5e_mpwrq_umr_entry_size. */
@@ -134,7 +134,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 		offset = offset * sizeof(struct mlx5_klm) * 2 / MLX5_OCTWORD;
 	else if (unlikely(rq->mpwqe.umr_mode == MLX5E_MPWRQ_UMR_MODE_TRIPLE))
 		offset = offset * sizeof(struct mlx5_ksm) * 4 / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	icosq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -144,7 +144,7 @@ int mlx5e_xsk_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	icosq->pc += rq->mpwqe.umr_wqebbs;
 
-	icosq->doorbell_cseg = &umr_wqe->ctrl;
+	icosq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5d5e7b19c396b..7e3aad0151117 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -311,8 +311,8 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq,
 				       struct mlx5e_icosq *sq,
 				       struct mlx5e_umr_wqe *wqe)
 {
-	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->ctrl;
-	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->uctrl;
+	struct mlx5_wqe_ctrl_seg      *cseg = &wqe->hdr.ctrl;
+	struct mlx5_wqe_umr_ctrl_seg *ucseg = &wqe->hdr.uctrl;
 	u16 octowords;
 	u8 ds_cnt;
 
@@ -393,7 +393,9 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, int node)
 		bitmap_fill(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	}
 
-	mlx5e_build_umr_wqe(rq, rq->icosq, &rq->mpwqe.umr_wqe);
+	mlx5e_build_umr_wqe(rq, rq->icosq,
+			    container_of(&rq->mpwqe.umr_wqe,
+					 struct mlx5e_umr_wqe, hdr));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 1963bc5adb188..5fd70b4d55beb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -631,16 +631,16 @@ static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
 			  __be32 key, u16 offset, u16 ksm_len)
 {
 	memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_ksms));
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			     MLX5_OPCODE_UMR);
-	umr_wqe->ctrl.umr_mkey = key;
-	umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
+	umr_wqe->hdr.ctrl.umr_mkey = key;
+	umr_wqe->hdr.ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
 					    | MLX5E_KSM_UMR_DS_CNT(ksm_len));
-	umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
-	umr_wqe->uctrl.xlt_octowords = cpu_to_be16(ksm_len);
-	umr_wqe->uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+	umr_wqe->hdr.uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_octowords = cpu_to_be16(ksm_len);
+	umr_wqe->hdr.uctrl.mkey_mask     = cpu_to_be64(MLX5_MKEY_MASK_FREE);
 }
 
 static struct mlx5e_frag_page *mlx5e_shampo_hd_to_frag_page(struct mlx5e_rq *rq, int header_index)
@@ -704,7 +704,7 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
 
 	shampo->pi = (shampo->pi + ksm_entries) & (shampo->hd_per_wq - 1);
 	sq->pc += wqe_bbs;
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 
@@ -814,12 +814,12 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 	bitmap_zero(wi->skip_release_bitmap, rq->mpwqe.pages_per_wqe);
 	wi->consumed_strides = 0;
 
-	umr_wqe->ctrl.opmod_idx_opcode =
+	umr_wqe->hdr.ctrl.opmod_idx_opcode =
 		cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
 			    MLX5_OPCODE_UMR);
 
 	offset = (ix * rq->mpwqe.mtts_per_wqe) * sizeof(struct mlx5_mtt) / MLX5_OCTWORD;
-	umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+	umr_wqe->hdr.uctrl.xlt_offset = cpu_to_be16(offset);
 
 	sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
 		.wqe_type   = MLX5E_ICOSQ_WQE_UMR_RX,
@@ -829,7 +829,7 @@ static int mlx5e_alloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix)
 
 	sq->pc += rq->mpwqe.umr_wqebbs;
 
-	sq->doorbell_cseg = &umr_wqe->ctrl;
+	sq->doorbell_cseg = &umr_wqe->hdr.ctrl;
 
 	return 0;
 

From e1f95b1992b8cc31e37505787806918b0447909b Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 26 Feb 2025 19:20:29 +0100
Subject: [PATCH 1304/2753] geneve: Allow users to specify source port range

Recently, in case of Cilium, we run into users on Azure who require to use
tunneling for east/west traffic due to hitting IPAM API limits for Kubernetes
Pods if they would have gone with publicly routable IPs for Pods. In case
of tunneling, Cilium supports the option of vxlan or geneve. In order to
RSS spread flows among remote CPUs both derive a source port hash via
udp_flow_src_port() which takes the inner packet's skb->hash into account.
For clusters with many nodes, this can then hit a new limitation [0]: Today,
the Azure networking stack supports 1M total flows (500k inbound and 500k
outbound) for a VM. [...] Once this limit is hit, other connections are
dropped. [...] Each flow is distinguished by a 5-tuple (protocol, local IP
address, remote IP address, local port, and remote port) information. [...]

For vxlan and geneve, this can create a massive amount of UDP flows which
then run into the limits if stale flows are not evicted fast enough. One
option to mitigate this for vxlan is to narrow the source port range via
IFLA_VXLAN_PORT_RANGE while still being able to benefit from RSS. However,
geneve currently does not have this option and it spreads traffic across
the full source port range of [1, USHRT_MAX]. To overcome this limitation
also for geneve, add an equivalent IFLA_GENEVE_PORT_RANGE setting for users.

Note that struct geneve_config before/after still remains at 2 cachelines
on x86-64. The low/high members of struct ifla_geneve_port_range (which is
uapi exposed) are of type __be16. While they would be perfectly fine to be
of __u16 type, the consensus was that it would be good to be consistent
with the existing struct ifla_vxlan_port_range from a uapi consumer PoV.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://learn.microsoft.com/en-us/azure/virtual-network/virtual-machine-network-throughput [0]
Link: https://patch.msgid.link/20250226182030.89440-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/geneve.c         | 52 +++++++++++++++++++++++++++++++++---
 include/uapi/linux/if_link.h |  6 +++++
 2 files changed, 54 insertions(+), 4 deletions(-)

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index fc62b25e0362a..2c65f867fd31d 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -57,6 +57,8 @@ struct geneve_config {
 	bool			ttl_inherit;
 	enum ifla_geneve_df	df;
 	bool			inner_proto_inherit;
+	u16			port_min;
+	u16			port_max;
 };
 
 /* Pseudo network device */
@@ -835,7 +837,9 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	tos = geneve_get_dsfield(skb, dev, info, &use_cache);
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	sport = udp_flow_src_port(geneve->net, skb,
+				  geneve->cfg.port_min,
+				  geneve->cfg.port_max, true);
 
 	rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr,
 				   &info->key,
@@ -945,7 +949,9 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
 
 	use_cache = ip_tunnel_dst_cache_usable(skb, info);
 	prio = geneve_get_dsfield(skb, dev, info, &use_cache);
-	sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
+	sport = udp_flow_src_port(geneve->net, skb,
+				  geneve->cfg.port_min,
+				  geneve->cfg.port_max, true);
 
 	dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0,
 				     &saddr, key, sport,
@@ -1084,7 +1090,8 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		use_cache = ip_tunnel_dst_cache_usable(skb, info);
 		tos = geneve_get_dsfield(skb, dev, info, &use_cache);
 		sport = udp_flow_src_port(geneve->net, skb,
-					  1, USHRT_MAX, true);
+					  geneve->cfg.port_min,
+					  geneve->cfg.port_max, true);
 
 		rt = udp_tunnel_dst_lookup(skb, dev, geneve->net, 0, &saddr,
 					   &info->key,
@@ -1110,7 +1117,8 @@ static int geneve_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		use_cache = ip_tunnel_dst_cache_usable(skb, info);
 		prio = geneve_get_dsfield(skb, dev, info, &use_cache);
 		sport = udp_flow_src_port(geneve->net, skb,
-					  1, USHRT_MAX, true);
+					  geneve->cfg.port_min,
+					  geneve->cfg.port_max, true);
 
 		dst = udp_tunnel6_dst_lookup(skb, dev, geneve->net, gs6->sock, 0,
 					     &saddr, &info->key, sport,
@@ -1234,6 +1242,7 @@ static const struct nla_policy geneve_policy[IFLA_GENEVE_MAX + 1] = {
 	[IFLA_GENEVE_TTL_INHERIT]	= { .type = NLA_U8 },
 	[IFLA_GENEVE_DF]		= { .type = NLA_U8 },
 	[IFLA_GENEVE_INNER_PROTO_INHERIT]	= { .type = NLA_FLAG },
+	[IFLA_GENEVE_PORT_RANGE]	= NLA_POLICY_EXACT_LEN(sizeof(struct ifla_geneve_port_range)),
 };
 
 static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
@@ -1279,6 +1288,17 @@ static int geneve_validate(struct nlattr *tb[], struct nlattr *data[],
 		}
 	}
 
+	if (data[IFLA_GENEVE_PORT_RANGE]) {
+		const struct ifla_geneve_port_range *p;
+
+		p = nla_data(data[IFLA_GENEVE_PORT_RANGE]);
+		if (ntohs(p->high) < ntohs(p->low)) {
+			NL_SET_ERR_MSG_ATTR(extack, data[IFLA_GENEVE_PORT_RANGE],
+					    "Invalid source port range");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
@@ -1506,6 +1526,18 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[],
 		info->key.tp_dst = nla_get_be16(data[IFLA_GENEVE_PORT]);
 	}
 
+	if (data[IFLA_GENEVE_PORT_RANGE]) {
+		const struct ifla_geneve_port_range *p;
+
+		if (changelink) {
+			attrtype = IFLA_GENEVE_PORT_RANGE;
+			goto change_notsup;
+		}
+		p = nla_data(data[IFLA_GENEVE_PORT_RANGE]);
+		cfg->port_min = ntohs(p->low);
+		cfg->port_max = ntohs(p->high);
+	}
+
 	if (data[IFLA_GENEVE_COLLECT_METADATA]) {
 		if (changelink) {
 			attrtype = IFLA_GENEVE_COLLECT_METADATA;
@@ -1626,6 +1658,8 @@ static int geneve_newlink(struct net_device *dev,
 		.use_udp6_rx_checksums = false,
 		.ttl_inherit = false,
 		.collect_md = false,
+		.port_min = 1,
+		.port_max = USHRT_MAX,
 	};
 	int err;
 
@@ -1744,6 +1778,7 @@ static size_t geneve_get_size(const struct net_device *dev)
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_UDP_ZERO_CSUM6_RX */
 		nla_total_size(sizeof(__u8)) + /* IFLA_GENEVE_TTL_INHERIT */
 		nla_total_size(0) +	 /* IFLA_GENEVE_INNER_PROTO_INHERIT */
+		nla_total_size(sizeof(struct ifla_geneve_port_range)) + /* IFLA_GENEVE_PORT_RANGE */
 		0;
 }
 
@@ -1753,6 +1788,10 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	struct ip_tunnel_info *info = &geneve->cfg.info;
 	bool ttl_inherit = geneve->cfg.ttl_inherit;
 	bool metadata = geneve->cfg.collect_md;
+	struct ifla_geneve_port_range ports = {
+		.low	= htons(geneve->cfg.port_min),
+		.high	= htons(geneve->cfg.port_max),
+	};
 	__u8 tmp_vni[3];
 	__u32 vni;
 
@@ -1809,6 +1848,9 @@ static int geneve_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	    nla_put_flag(skb, IFLA_GENEVE_INNER_PROTO_INHERIT))
 		goto nla_put_failure;
 
+	if (nla_put(skb, IFLA_GENEVE_PORT_RANGE, sizeof(ports), &ports))
+		goto nla_put_failure;
+
 	return 0;
 
 nla_put_failure:
@@ -1841,6 +1883,8 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 		.use_udp6_rx_checksums = true,
 		.ttl_inherit = false,
 		.collect_md = true,
+		.port_min = 1,
+		.port_max = USHRT_MAX,
 	};
 
 	memset(tb, 0, sizeof(tb));
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index bfe880fbbb24b..3b586fb0bc4cd 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1438,6 +1438,7 @@ enum {
 	IFLA_GENEVE_TTL_INHERIT,
 	IFLA_GENEVE_DF,
 	IFLA_GENEVE_INNER_PROTO_INHERIT,
+	IFLA_GENEVE_PORT_RANGE,
 	__IFLA_GENEVE_MAX
 };
 #define IFLA_GENEVE_MAX	(__IFLA_GENEVE_MAX - 1)
@@ -1450,6 +1451,11 @@ enum ifla_geneve_df {
 	GENEVE_DF_MAX = __GENEVE_DF_END - 1,
 };
 
+struct ifla_geneve_port_range {
+	__be16 low;
+	__be16 high;
+};
+
 /* Bareudp section  */
 enum {
 	IFLA_BAREUDP_UNSPEC,

From 5a41a00cd5d5bac4c7f081f2333df2256eb74d90 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 26 Feb 2025 19:20:30 +0100
Subject: [PATCH 1305/2753] geneve, specs: Add port range to rt_link
 specification

Add the port range to rt_link, example:

  # tools/net/ynl/pyynl/cli.py --spec Documentation/netlink/specs/rt_link.yaml \
    --do getlink --json '{"ifname": "geneve1"}' --output-json | jq
  {
    "ifname": "geneve1",
    [...]
    "linkinfo": {
      "kind": "geneve",
      "data": {
        "id": 1000,
        "remote": "147.28.227.100",
        "udp-csum": 0,
        "ttl": 0,
        "tos": 0,
        "label": 0,
        "df": 0,
        "port": 49431,
        "udp-zero-csum6-rx": 1,
        "ttl-inherit": 0,
        "port-range": {
          "low": 4000,
          "high": 5000
        }
      }
    },
    [...]
  }

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://patch.msgid.link/20250226182030.89440-2-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/rt_link.yaml | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 0d492500c7e57..8b5c0f0673285 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -770,6 +770,18 @@ definitions:
       -
         name: to
         type: u32
+  -
+    name: ifla-geneve-port-range
+    type: struct
+    members:
+      -
+        name: low
+        type: u16
+        byte-order: big-endian
+      -
+        name: high
+        type: u16
+        byte-order: big-endian
   -
     name: ifla-vf-mac
     type: struct
@@ -1915,6 +1927,10 @@ attribute-sets:
       -
         name: inner-proto-inherit
         type: flag
+      -
+        name: port-range
+        type: binary
+        struct: ifla-geneve-port-range
   -
     name: linkinfo-iptun-attrs
     name-prefix: ifla-iptun-

From ada9ce437a4da8e27243251bd7a9ecec32ebd72a Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Thu, 27 Feb 2025 02:21:26 +0100
Subject: [PATCH 1306/2753] mailmap: remove unwanted entry for Antonio
 Quartulli

antonio@openvpn.net is still used for sending
patches under the OpenVPN Inc. umbrella, therefore this
address should not be re-mapped.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Link: https://patch.msgid.link/20250227-b4-ovpn-v20-1-93f363310834@openvpn.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .mailmap | 1 -
 1 file changed, 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..598f31c4b498e 100644
--- a/.mailmap
+++ b/.mailmap
@@ -88,7 +88,6 @@ Antonio Quartulli <antonio@mandelbit.com> <antonio@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <antonio.quartulli@open-mesh.com>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@autistici.org>
 Antonio Quartulli <antonio@mandelbit.com> <ordex@ritirata.org>
-Antonio Quartulli <antonio@mandelbit.com> <antonio@openvpn.net>
 Antonio Quartulli <antonio@mandelbit.com> <a@unstable.cc>
 Anup Patel <anup@brainfault.org> <anup.patel@wdc.com>
 Archit Taneja <archit@ti.com>

From 38d41cf575f755fb8db3c4879006aa383ca4341e Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Wed, 26 Feb 2025 18:46:43 +0100
Subject: [PATCH 1307/2753] net-sysfs: remove unused initial ret values

In some net-sysfs functions the ret value is initialized but never used
as it is always overridden. Remove those.

Signed-off-by: Antoine Tenart <atenart@kernel.org>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Link: https://patch.msgid.link/20250226174644.311136-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/net-sysfs.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f61c1d8298119..8d9dc048a548b 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -568,7 +568,7 @@ static ssize_t ifalias_store(struct device *dev, struct device_attribute *attr,
 	struct net_device *netdev = to_net_dev(dev);
 	struct net *net = dev_net(netdev);
 	size_t count = len;
-	ssize_t ret = 0;
+	ssize_t ret;
 
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
@@ -597,7 +597,7 @@ static ssize_t ifalias_show(struct device *dev,
 {
 	const struct net_device *netdev = to_net_dev(dev);
 	char tmp[IFALIASZ];
-	ssize_t ret = 0;
+	ssize_t ret;
 
 	ret = dev_get_alias(netdev, tmp, sizeof(tmp));
 	if (ret > 0)
@@ -638,7 +638,7 @@ static ssize_t phys_port_id_show(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netdev_phys_item_id ppid;
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
 
 	/* The check is also done in dev_get_phys_port_id; this helps returning
 	 * early without hitting the locking section below.
@@ -664,8 +664,8 @@ static ssize_t phys_port_name_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct net_device *netdev = to_net_dev(dev);
-	ssize_t ret = -EINVAL;
 	char name[IFNAMSIZ];
+	ssize_t ret;
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
 	 * returning early without hitting the locking section below.
@@ -693,7 +693,7 @@ static ssize_t phys_switch_id_show(struct device *dev,
 {
 	struct net_device *netdev = to_net_dev(dev);
 	struct netdev_phys_item_id ppid = { };
-	ssize_t ret = -EINVAL;
+	ssize_t ret;
 
 	/* The checks are also done in dev_get_phys_port_name; this helps
 	 * returning early without hitting the locking section below. This works

From 6f86bdeab633a56d5c6dccf1a2c5989b6a5e323e Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Thu, 27 Feb 2025 16:39:44 -0500
Subject: [PATCH 1308/2753] tracing: Fix bad hist from corrupting
 named_triggers list

The following commands causes a crash:

 ~# cd /sys/kernel/tracing/events/rcu/rcu_callback
 ~# echo 'hist:name=bad:keys=common_pid:onmax(bogus).save(common_pid)' > trigger
 bash: echo: write error: Invalid argument
 ~# echo 'hist:name=bad:keys=common_pid' > trigger

Because the following occurs:

event_trigger_write() {
  trigger_process_regex() {
    event_hist_trigger_parse() {

      data = event_trigger_alloc(..);

      event_trigger_register(.., data) {
        cmd_ops->reg(.., data, ..) [hist_register_trigger()] {
          data->ops->init() [event_hist_trigger_init()] {
            save_named_trigger(name, data) {
              list_add(&data->named_list, &named_triggers);
            }
          }
        }
      }

      ret = create_actions(); (return -EINVAL)
      if (ret)
        goto out_unreg;
[..]
      ret = hist_trigger_enable(data, ...) {
        list_add_tail_rcu(&data->list, &file->triggers); <<<---- SKIPPED!!! (this is important!)
[..]
 out_unreg:
      event_hist_unregister(.., data) {
        cmd_ops->unreg(.., data, ..) [hist_unregister_trigger()] {
          list_for_each_entry(iter, &file->triggers, list) {
            if (!hist_trigger_match(data, iter, named_data, false))   <- never matches
                continue;
            [..]
            test = iter;
          }
          if (test && test->ops->free) <<<-- test is NULL

            test->ops->free(test) [event_hist_trigger_free()] {
              [..]
              if (data->name)
                del_named_trigger(data) {
                  list_del(&data->named_list);  <<<<-- NEVER gets removed!
                }
              }
           }
         }

         [..]
         kfree(data); <<<-- frees item but it is still on list

The next time a hist with name is registered, it causes an u-a-f bug and
the kernel can crash.

Move the code around such that if event_trigger_register() succeeds, the
next thing called is hist_trigger_enable() which adds it to the list.

A bunch of actions is called if get_named_trigger_data() returns false.
But that doesn't need to be called after event_trigger_register(), so it
can be moved up, allowing event_trigger_register() to be called just
before hist_trigger_enable() keeping them together and allowing the
file->triggers to be properly populated.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250227163944.1c37f85f@gandalf.local.home
Fixes: 067fe038e70f6 ("tracing: Add variable reference handling to hist triggers")
Reported-by: Tomas Glozar <tglozar@redhat.com>
Tested-by: Tomas Glozar <tglozar@redhat.com>
Reviewed-by: Tom Zanussi <zanussi@kernel.org>
Closes: https://lore.kernel.org/all/CAP4=nvTsxjckSBTz=Oe_UYh8keD9_sZC4i++4h72mJLic4_W4A@mail.gmail.com/
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 261163b00137a..ad7419e240556 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -6724,27 +6724,27 @@ static int event_hist_trigger_parse(struct event_command *cmd_ops,
 	if (existing_hist_update_only(glob, trigger_data, file))
 		goto out_free;
 
-	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
-	if (ret < 0)
-		goto out_free;
+	if (!get_named_trigger_data(trigger_data)) {
 
-	if (get_named_trigger_data(trigger_data))
-		goto enable;
+		ret = create_actions(hist_data);
+		if (ret)
+			goto out_free;
 
-	ret = create_actions(hist_data);
-	if (ret)
-		goto out_unreg;
+		if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
+			ret = save_hist_vars(hist_data);
+			if (ret)
+				goto out_free;
+		}
 
-	if (has_hist_vars(hist_data) || hist_data->n_var_refs) {
-		ret = save_hist_vars(hist_data);
+		ret = tracing_map_init(hist_data->map);
 		if (ret)
-			goto out_unreg;
+			goto out_free;
 	}
 
-	ret = tracing_map_init(hist_data->map);
-	if (ret)
-		goto out_unreg;
-enable:
+	ret = event_trigger_register(cmd_ops, file, glob, trigger_data);
+	if (ret < 0)
+		goto out_free;
+
 	ret = hist_trigger_enable(trigger_data, file);
 	if (ret)
 		goto out_unreg;

From 3908b6baf2ac20138915b5ca98338b4f063954d8 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Wed, 26 Feb 2025 15:27:03 +0100
Subject: [PATCH 1309/2753] selftests/ftrace: Let fprobe test consider already
 enabled functions

The fprobe test fails on Fedora 41 since the fprobe test assumption that
the number of enabled_functions is zero before the test starts is not
necessarily true. Some user space tools, like systemd, add BPF programs
that attach to functions. Those will show up in the enabled_functions table
and must be taken into account by the fprobe test.

Therefore count the number of lines of enabled_functions before tests
start, and use that as base when comparing expected results.

Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Link: https://lore.kernel.org/20250226142703.910860-1-hca@linux.ibm.com
Fixes: e85c5e9792b9 ("selftests/ftrace: Update fprobe test to check enabled_functions file")
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 .../test.d/dynevent/add_remove_fprobe.tc       | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
index 449f9d8be7462..73f6c6fcecabe 100644
--- a/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
+++ b/tools/testing/selftests/ftrace/test.d/dynevent/add_remove_fprobe.tc
@@ -10,12 +10,16 @@ PLACE=$FUNCTION_FORK
 PLACE2="kmem_cache_free"
 PLACE3="schedule_timeout"
 
+# Some functions may have BPF programs attached, therefore
+# count already enabled_functions before tests start
+ocnt=`cat enabled_functions | wc -l`
+
 echo "f:myevent1 $PLACE" >> dynamic_events
 
 # Make sure the event is attached and is the only one
 grep -q $PLACE enabled_functions
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -23,7 +27,7 @@ echo "f:myevent2 $PLACE%return" >> dynamic_events
 
 # It should till be the only attached function
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -32,7 +36,7 @@ echo "f:myevent3 $PLACE2" >> dynamic_events
 
 grep -q $PLACE2 enabled_functions
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 2 ]; then
+if [ $cnt -ne $((ocnt + 2)) ]; then
 	exit_fail
 fi
 
@@ -49,7 +53,7 @@ grep -q myevent1 dynamic_events
 
 # should still have 2 left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 2 ]; then
+if [ $cnt -ne $((ocnt + 2)) ]; then
 	exit_fail
 fi
 
@@ -57,7 +61,7 @@ echo > dynamic_events
 
 # Should have none left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 0 ]; then
+if [ $cnt -ne $ocnt ]; then
 	exit_fail
 fi
 
@@ -65,7 +69,7 @@ echo "f:myevent4 $PLACE" >> dynamic_events
 
 # Should only have one enabled
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 1 ]; then
+if [ $cnt -ne $((ocnt + 1)) ]; then
 	exit_fail
 fi
 
@@ -73,7 +77,7 @@ echo > dynamic_events
 
 # Should have none left
 cnt=`cat enabled_functions | wc -l`
-if [ $cnt -ne 0 ]; then
+if [ $cnt -ne $ocnt ]; then
 	exit_fail
 fi
 

From a1a7eb89ca0b89dc1c326eeee2596f263291aca3 Mon Sep 17 00:00:00 2001
From: Nikolay Kuratov <kniv@yandex-team.ru>
Date: Thu, 6 Feb 2025 12:01:56 +0300
Subject: [PATCH 1310/2753] ftrace: Avoid potential division by zero in
 function_stat_show()

Check whether denominator expression x * (x - 1) * 1000 mod {2^32, 2^64}
produce zero and skip stddev computation in that case.

For now don't care about rec->counter * rec->counter overflow because
rec->time * rec->time overflow will likely happen earlier.

Cc: stable@vger.kernel.org
Cc: Wen Yang <wenyang@linux.alibaba.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250206090156.1561783-1-kniv@yandex-team.ru
Fixes: e31f7939c1c27 ("ftrace: Avoid potential division by zero in function profiler")
Signed-off-by: Nikolay Kuratov <kniv@yandex-team.ru>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/ftrace.c | 27 ++++++++++++---------------
 1 file changed, 12 insertions(+), 15 deletions(-)

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 6b0c25761ccb1..fc88e0688daf0 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -540,6 +540,7 @@ static int function_stat_show(struct seq_file *m, void *v)
 	static struct trace_seq s;
 	unsigned long long avg;
 	unsigned long long stddev;
+	unsigned long long stddev_denom;
 #endif
 	guard(mutex)(&ftrace_profile_lock);
 
@@ -559,23 +560,19 @@ static int function_stat_show(struct seq_file *m, void *v)
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	seq_puts(m, "    ");
 
-	/* Sample standard deviation (s^2) */
-	if (rec->counter <= 1)
-		stddev = 0;
-	else {
-		/*
-		 * Apply Welford's method:
-		 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
-		 */
+	/*
+	 * Variance formula:
+	 * s^2 = 1 / (n * (n-1)) * (n * \Sum (x_i)^2 - (\Sum x_i)^2)
+	 * Maybe Welford's method is better here?
+	 * Divide only by 1000 for ns^2 -> us^2 conversion.
+	 * trace_print_graph_duration will divide by 1000 again.
+	 */
+	stddev = 0;
+	stddev_denom = rec->counter * (rec->counter - 1) * 1000;
+	if (stddev_denom) {
 		stddev = rec->counter * rec->time_squared -
 			 rec->time * rec->time;
-
-		/*
-		 * Divide only 1000 for ns^2 -> us^2 conversion.
-		 * trace_print_graph_duration will divide 1000 again.
-		 */
-		stddev = div64_ul(stddev,
-				  rec->counter * (rec->counter - 1) * 1000);
+		stddev = div64_ul(stddev, stddev_denom);
 	}
 
 	trace_seq_init(&s);

From 5ace19bd8395e8a98ff0bca0fd20ae3fac3e1d6f Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 26 Feb 2025 11:39:00 +0200
Subject: [PATCH 1311/2753] coccinelle: Add missing (GE)NL_SET_ERR_MSG_* to
 strings ending with newline test

Add missing (GE)NL_SET_ERR_MSG_*() variants to the list of macros
checked for strings ending with a newline.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250226093904.6632-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 scripts/coccinelle/misc/newline_in_nl_msg.cocci | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/scripts/coccinelle/misc/newline_in_nl_msg.cocci b/scripts/coccinelle/misc/newline_in_nl_msg.cocci
index 9baffe55d9170..2814f6b205b9a 100644
--- a/scripts/coccinelle/misc/newline_in_nl_msg.cocci
+++ b/scripts/coccinelle/misc/newline_in_nl_msg.cocci
@@ -1,7 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 ///
-/// Catch strings ending in newline with GENL_SET_ERR_MSG, NL_SET_ERR_MSG,
-/// NL_SET_ERR_MSG_MOD.
+/// Catch strings ending in newline with (GE)NL_SET_ERR_MSG*.
 ///
 // Confidence: Very High
 // Copyright: (C) 2020 Intel Corporation
@@ -17,7 +16,11 @@ expression e;
 constant m;
 position p;
 @@
-  \(GENL_SET_ERR_MSG\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\)(e,m@p)
+  \(GENL_SET_ERR_MSG\|GENL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG\|NL_SET_ERR_MSG_MOD\|
+  NL_SET_ERR_MSG_FMT\|NL_SET_ERR_MSG_FMT_MOD\|NL_SET_ERR_MSG_WEAK\|
+  NL_SET_ERR_MSG_WEAK_MOD\|NL_SET_ERR_MSG_ATTR_POL\|
+  NL_SET_ERR_MSG_ATTR_POL_FMT\|NL_SET_ERR_MSG_ATTR\|
+  NL_SET_ERR_MSG_ATTR_FMT\)(e,m@p,...)
 
 @script:python@
 m << r.m;
@@ -32,7 +35,7 @@ expression r.e;
 constant r.m;
 position r.p;
 @@
-  fname(e,m@p)
+  fname(e,m@p,...)
 
 //----------------------------------------------------------
 //  For context mode
@@ -43,7 +46,7 @@ identifier r1.fname;
 expression r.e;
 constant r.m;
 @@
-* fname(e,m)
+* fname(e,m,...)
 
 //----------------------------------------------------------
 //  For org mode

From 3a2295ff3f00d44c97baec37c43b6ede3eea9df9 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 26 Feb 2025 11:39:01 +0200
Subject: [PATCH 1312/2753] net/mlx5: Remove newline at the end of a netlink
 error message

Netlink error messages should not have a newline at the end of the
string.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250226093904.6632-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/dpll.c            | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c      | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c      | 6 +++---
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
index 31142f6cc3729..1e5522a194839 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/dpll.c
@@ -242,7 +242,7 @@ static int mlx5_dpll_clock_quality_level_get(const struct dpll_device *dpll,
 		return 0;
 	}
 errout:
-	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware\n");
+	NL_SET_ERR_MSG_MOD(extack, "Invalid clock quality level obtained from firmware");
 	return -EINVAL;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
index e4e487c8431b8..5c762a71818db 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_vxlan.c
@@ -140,7 +140,7 @@ static int mlx5e_tc_tun_parse_vxlan_gbp_option(struct mlx5e_priv *priv,
 	gbp_mask = (u32 *)&enc_opts.mask->data[0];
 
 	if (*gbp_mask & ~VXLAN_GBP_MASK) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)\n", *gbp_mask);
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Wrong VxLAN GBP mask(0x%08X)", *gbp_mask);
 		return -EINVAL;
 	}
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 0cb515fa179f5..3b2efde9dda24 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2026,7 +2026,7 @@ static int mlx5e_get_module_eeprom_by_page(struct net_device *netdev,
 		if (size_read < 0) {
 			NL_SET_ERR_MSG_FMT_MOD(
 				extack,
-				"Query module eeprom by page failed, read %u bytes, err %d\n",
+				"Query module eeprom by page failed, read %u bytes, err %d",
 				i, size_read);
 			return i;
 		}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
index 5f647358a05ca..76e35c827da00 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/bridge.c
@@ -1863,7 +1863,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 			 "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
 			 addr, vport_num);
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)\n",
+				       "Failed to lookup bridge port to add MDB (MAC=%pM,vport=%u)",
 				       addr, vport_num);
 		return -EINVAL;
 	}
@@ -1876,7 +1876,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 				 "Failed to lookup bridge port vlan metadata to create MDB (MAC=%pM,vid=%u,vport=%u)\n",
 				 addr, vid, vport_num);
 			NL_SET_ERR_MSG_FMT_MOD(extack,
-					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)\n",
+					       "Failed to lookup vlan metadata for MDB (MAC=%pM,vid=%u,vport=%u)",
 					       addr, vid, vport_num);
 			return -EINVAL;
 		}
@@ -1884,7 +1884,7 @@ int mlx5_esw_bridge_port_mdb_add(struct net_device *dev, u16 vport_num, u16 esw_
 
 	err = mlx5_esw_bridge_port_mdb_attach(dev, port, addr, vid);
 	if (err) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)\n",
+		NL_SET_ERR_MSG_FMT_MOD(extack, "Failed to add MDB (MAC=%pM,vid=%u,vport=%u)",
 				       addr, vid, vport_num);
 		return err;
 	}

From 79d89fab225e85e3219258af860b5f086f40f3d3 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 26 Feb 2025 11:39:02 +0200
Subject: [PATCH 1313/2753] sfc: Remove newline at the end of a netlink error
 message

Netlink error messages should not have a newline at the end of the
string.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250226093904.6632-4-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/sfc/mae.c | 2 +-
 drivers/net/ethernet/sfc/tc.c  | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mae.c b/drivers/net/ethernet/sfc/mae.c
index 50f097487b140..6fd0c1e9a7d54 100644
--- a/drivers/net/ethernet/sfc/mae.c
+++ b/drivers/net/ethernet/sfc/mae.c
@@ -755,7 +755,7 @@ int efx_mae_match_check_caps_lhs(struct efx_nic *efx,
 	rc = efx_mae_match_check_cap_typ(supported_fields[MAE_FIELD_INGRESS_PORT],
 					 ingress_port_mask_type);
 	if (rc) {
-		NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field %s\n",
+		NL_SET_ERR_MSG_FMT_MOD(extack, "No support for %s mask in field %s",
 				       mask_type_name(ingress_port_mask_type),
 				       "ingress_port");
 		return rc;
diff --git a/drivers/net/ethernet/sfc/tc.c b/drivers/net/ethernet/sfc/tc.c
index 0d93164988fc6..fa94aa3cd5fee 100644
--- a/drivers/net/ethernet/sfc/tc.c
+++ b/drivers/net/ethernet/sfc/tc.c
@@ -1043,7 +1043,7 @@ static int efx_tc_flower_handle_lhs_actions(struct efx_nic *efx,
 				return -EOPNOTSUPP;
 			}
 			if (fa->ct.action) {
-				NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled ct.action %u for LHS rule\n",
+				NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled ct.action %u for LHS rule",
 						       fa->ct.action);
 				return -EOPNOTSUPP;
 			}
@@ -1056,7 +1056,7 @@ static int efx_tc_flower_handle_lhs_actions(struct efx_nic *efx,
 			act->zone = ct_zone;
 			break;
 		default:
-			NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u for LHS rule\n",
+			NL_SET_ERR_MSG_FMT_MOD(extack, "Unhandled action %u for LHS rule",
 					       fa->id);
 			return -EOPNOTSUPP;
 		}
@@ -1581,7 +1581,7 @@ static int efx_tc_flower_replace_foreign_lhs(struct efx_nic *efx,
 
 	type = efx_tc_indr_netdev_type(net_dev);
 	if (type == EFX_ENCAP_TYPE_NONE) {
-		NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device\n");
+		NL_SET_ERR_MSG_MOD(extack, "Egress encap match on unsupported tunnel device");
 		return -EOPNOTSUPP;
 	}
 

From c94fae5f1ccfd38de6ca92fda9736412b0d96770 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 26 Feb 2025 11:39:03 +0200
Subject: [PATCH 1314/2753] net: sched: Remove newline at the end of a netlink
 error message

Netlink error messages should not have a newline at the end of the
string.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250226093904.6632-5-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_qfq.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 6a07cdbdb9e12..2cfbc977fe6d0 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -447,7 +447,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (q->wsum + delta_w > QFQ_MAX_WSUM) {
 		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "total weight out of range (%d + %u)\n",
+				       "total weight out of range (%d + %u)",
 				       delta_w, q->wsum);
 		return -EINVAL;
 	}

From e0c032d26dab01461e918e3b599630b2ab8c8ec6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 26 Feb 2025 11:39:04 +0200
Subject: [PATCH 1315/2753] ice: dpll: Remove newline at the end of a netlink
 error message

Netlink error messages should not have a newline at the end of the
string.

Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Acked-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250226093904.6632-6-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/ice/ice_dpll.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 8d806d8ad761a..bce3ad6ca2a6f 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -95,7 +95,7 @@ ice_dpll_pin_freq_set(struct ice_pf *pf, struct ice_dpll_pin *pin,
 	}
 	if (ret) {
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin freq:%u on pin:%u\n",
+				   "err:%d %s failed to set pin freq:%u on pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   freq, pin->idx);
@@ -322,7 +322,7 @@ ice_dpll_pin_enable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to enable %s pin:%u\n",
+				   "err:%d %s failed to enable %s pin:%u",
 				   ret, ice_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
@@ -367,7 +367,7 @@ ice_dpll_pin_disable(struct ice_hw *hw, struct ice_dpll_pin *pin,
 	}
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to disable %s pin:%u\n",
+				   "err:%d %s failed to disable %s pin:%u",
 				   ret, ice_aq_str(hw->adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
 
@@ -479,7 +479,7 @@ ice_dpll_pin_state_update(struct ice_pf *pf, struct ice_dpll_pin *pin,
 err:
 	if (extack)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to update %s pin:%u\n",
+				   "err:%d %s failed to update %s pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   pin_type_name[pin_type], pin->idx);
@@ -518,7 +518,7 @@ ice_dpll_hw_input_prio_set(struct ice_pf *pf, struct ice_dpll *dpll,
 				      (u8)prio);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin prio:%u on pin:%u\n",
+				   "err:%d %s failed to set pin prio:%u on pin:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   prio, pin->idx);
@@ -1004,7 +1004,7 @@ ice_dpll_pin_phase_adjust_set(const struct dpll_pin *pin, void *pin_priv,
 	mutex_unlock(&pf->dplls.lock);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u\n",
+				   "err:%d %s failed to set pin phase_adjust:%d for pin:%u on dpll:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   phase_adjust, p->idx, d->dpll_idx);
@@ -1362,7 +1362,7 @@ ice_dpll_rclk_state_on_pin_set(const struct dpll_pin *pin, void *pin_priv,
 					 &p->freq);
 	if (ret)
 		NL_SET_ERR_MSG_FMT(extack,
-				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u\n",
+				   "err:%d %s failed to set pin state:%u for pin:%u on parent:%u",
 				   ret,
 				   ice_aq_str(pf->hw.adminq.sq_last_status),
 				   state, p->idx, parent->idx);

From ad95bab0cd28ed77c2c0d0b6e76e03e031391064 Mon Sep 17 00:00:00 2001
From: Maurizio Lombardi <mlombard@redhat.com>
Date: Wed, 26 Feb 2025 14:42:18 +0100
Subject: [PATCH 1316/2753] nvme-tcp: fix potential memory corruption in
 nvme_tcp_recv_pdu()

nvme_tcp_recv_pdu() doesn't check the validity of the header length.
When header digests are enabled, a target might send a packet with an
invalid header length (e.g. 255), causing nvme_tcp_verify_hdgst()
to access memory outside the allocated area and cause memory corruptions
by overwriting it with the calculated digest.

Fix this by rejecting packets with an unexpected header length.

Fixes: 3f2304f8c6d6 ("nvme-tcp: add NVMe over TCP host driver")
Signed-off-by: Maurizio Lombardi <mlombard@redhat.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 32 +++++++++++++++++++++++++++++---
 1 file changed, 29 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 1094cbbec169f..23f11527d29d0 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -217,6 +217,19 @@ static inline int nvme_tcp_queue_id(struct nvme_tcp_queue *queue)
 	return queue - queue->ctrl->queues;
 }
 
+static inline bool nvme_tcp_recv_pdu_supported(enum nvme_tcp_pdu_type type)
+{
+	switch (type) {
+	case nvme_tcp_c2h_term:
+	case nvme_tcp_c2h_data:
+	case nvme_tcp_r2t:
+	case nvme_tcp_rsp:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*
  * Check if the queue is TLS encrypted
  */
@@ -818,6 +831,16 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		return 0;
 
 	hdr = queue->pdu;
+	if (unlikely(hdr->hlen != sizeof(struct nvme_tcp_rsp_pdu))) {
+		if (!nvme_tcp_recv_pdu_supported(hdr->type))
+			goto unsupported_pdu;
+
+		dev_err(queue->ctrl->ctrl.device,
+			"pdu type %d has unexpected header length (%d)\n",
+			hdr->type, hdr->hlen);
+		return -EPROTO;
+	}
+
 	if (unlikely(hdr->type == nvme_tcp_c2h_term)) {
 		/*
 		 * C2HTermReq never includes Header or Data digests.
@@ -850,10 +873,13 @@ static int nvme_tcp_recv_pdu(struct nvme_tcp_queue *queue, struct sk_buff *skb,
 		nvme_tcp_init_recv_ctx(queue);
 		return nvme_tcp_handle_r2t(queue, (void *)queue->pdu);
 	default:
-		dev_err(queue->ctrl->ctrl.device,
-			"unsupported pdu type (%d)\n", hdr->type);
-		return -EINVAL;
+		goto unsupported_pdu;
 	}
+
+unsupported_pdu:
+	dev_err(queue->ctrl->ctrl.device,
+		"unsupported pdu type (%d)\n", hdr->type);
+	return -EINVAL;
 }
 
 static inline void nvme_tcp_end_request(struct request *rq, u16 status)

From a16f88964c647103dad7743a484b216d488a6352 Mon Sep 17 00:00:00 2001
From: Meir Elisha <meir.elisha@volumez.com>
Date: Wed, 26 Feb 2025 09:28:12 +0200
Subject: [PATCH 1317/2753] nvmet-tcp: Fix a possible sporadic response drops
 in weakly ordered arch

The order in which queue->cmd and rcv_state are updated is crucial.
If these assignments are reordered by the compiler, the worker might not
get queued in nvmet_tcp_queue_response(), hanging the IO. to enforce the
the correct reordering, set rcv_state using smp_store_release().

Fixes: bdaf13279192 ("nvmet-tcp: fix a segmentation fault during io parsing error")

Signed-off-by: Meir Elisha <meir.elisha@volumez.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/tcp.c | 15 +++++++++++----
 1 file changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
index 7c51c2a8c109a..4f9cac8a5abe0 100644
--- a/drivers/nvme/target/tcp.c
+++ b/drivers/nvme/target/tcp.c
@@ -571,10 +571,16 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 	struct nvmet_tcp_cmd *cmd =
 		container_of(req, struct nvmet_tcp_cmd, req);
 	struct nvmet_tcp_queue	*queue = cmd->queue;
+	enum nvmet_tcp_recv_state queue_state;
+	struct nvmet_tcp_cmd *queue_cmd;
 	struct nvme_sgl_desc *sgl;
 	u32 len;
 
-	if (unlikely(cmd == queue->cmd)) {
+	/* Pairs with store_release in nvmet_prepare_receive_pdu() */
+	queue_state = smp_load_acquire(&queue->rcv_state);
+	queue_cmd = READ_ONCE(queue->cmd);
+
+	if (unlikely(cmd == queue_cmd)) {
 		sgl = &cmd->req.cmd->common.dptr.sgl;
 		len = le32_to_cpu(sgl->length);
 
@@ -583,7 +589,7 @@ static void nvmet_tcp_queue_response(struct nvmet_req *req)
 		 * Avoid using helpers, this might happen before
 		 * nvmet_req_init is completed.
 		 */
-		if (queue->rcv_state == NVMET_TCP_RECV_PDU &&
+		if (queue_state == NVMET_TCP_RECV_PDU &&
 		    len && len <= cmd->req.port->inline_data_size &&
 		    nvme_is_write(cmd->req.cmd))
 			return;
@@ -847,8 +853,9 @@ static void nvmet_prepare_receive_pdu(struct nvmet_tcp_queue *queue)
 {
 	queue->offset = 0;
 	queue->left = sizeof(struct nvme_tcp_hdr);
-	queue->cmd = NULL;
-	queue->rcv_state = NVMET_TCP_RECV_PDU;
+	WRITE_ONCE(queue->cmd, NULL);
+	/* Ensure rcv_state is visible only after queue->cmd is set */
+	smp_store_release(&queue->rcv_state, NVMET_TCP_RECV_PDU);
 }
 
 static void nvmet_tcp_free_crypto(struct nvmet_tcp_queue *queue)

From 00371a3f48775967950c2fe3ec97b7c786ca956d Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Wed, 26 Feb 2025 09:52:05 +0100
Subject: [PATCH 1318/2753] stmmac: loongson: Pass correct arg to PCI function

pcim_iomap_regions() should receive the driver's name as its third
parameter, not the PCI device's name.

Define the driver name with a macro and use it at the appropriate
places, including pcim_iomap_regions().

Cc: stable@vger.kernel.org # v5.14+
Fixes: 30bba69d7db4 ("stmmac: pci: Add dwmac support for Loongson")
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Yanteng Si <si.yanteng@linux.dev>
Tested-by: Henry Chen <chenx97@aosc.io>
Link: https://patch.msgid.link/20250226085208.97891-2-phasta@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
index f5acfb7d4ff65..ab7c2750c1042 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
@@ -11,6 +11,8 @@
 #include "dwmac_dma.h"
 #include "dwmac1000.h"
 
+#define DRIVER_NAME "dwmac-loongson-pci"
+
 /* Normal Loongson Tx Summary */
 #define DMA_INTR_ENA_NIE_TX_LOONGSON	0x00040000
 /* Normal Loongson Rx Summary */
@@ -568,7 +570,7 @@ static int loongson_dwmac_probe(struct pci_dev *pdev, const struct pci_device_id
 	for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 		if (pci_resource_len(pdev, i) == 0)
 			continue;
-		ret = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+		ret = pcim_iomap_regions(pdev, BIT(0), DRIVER_NAME);
 		if (ret)
 			goto err_disable_device;
 		break;
@@ -687,7 +689,7 @@ static const struct pci_device_id loongson_dwmac_id_table[] = {
 MODULE_DEVICE_TABLE(pci, loongson_dwmac_id_table);
 
 static struct pci_driver loongson_dwmac_driver = {
-	.name = "dwmac-loongson-pci",
+	.name = DRIVER_NAME,
 	.id_table = loongson_dwmac_id_table,
 	.probe = loongson_dwmac_probe,
 	.remove = loongson_dwmac_remove,

From 784e6abd99f24024a8998b5916795f0bec9d2fd9 Mon Sep 17 00:00:00 2001
From: Kevin Krakauer <krakauer@google.com>
Date: Wed, 26 Feb 2025 11:27:23 -0800
Subject: [PATCH 1319/2753] selftests/net: have `gro.sh -t` return a correct
 exit code

Modify gro.sh to return a useful exit code when the -t flag is used. It
formerly returned 0 no matter what.

Tested: Ran `gro.sh -t large` and verified that test failures return 1.
Signed-off-by: Kevin Krakauer <krakauer@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250226192725.621969-2-krakauer@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/gro.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index 02c21ff4ca81f..aabd6e5480b8e 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -100,5 +100,6 @@ trap cleanup EXIT
 if [[ "${test}" == "all" ]]; then
   run_all_tests
 else
-  run_test "${proto}" "${test}"
+  exit_code=$(run_test "${proto}" "${test}")
+  exit $exit_code
 fi;

From 41cda5728470618f1768cf71a2f3ae9fb550844d Mon Sep 17 00:00:00 2001
From: Kevin Krakauer <krakauer@google.com>
Date: Wed, 26 Feb 2025 11:27:24 -0800
Subject: [PATCH 1320/2753] selftests/net: only print passing message in GRO
 tests when tests pass

gro.c:main no longer erroneously claims a test passes when running as a
sender.

Tested: Ran `gro.sh -t large` to verify the sender no longer prints a
status.

Signed-off-by: Kevin Krakauer <krakauer@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250226192725.621969-3-krakauer@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/gro.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/gro.c b/tools/testing/selftests/net/gro.c
index b2184847e3881..d5824eadea109 100644
--- a/tools/testing/selftests/net/gro.c
+++ b/tools/testing/selftests/net/gro.c
@@ -1318,11 +1318,13 @@ int main(int argc, char **argv)
 	read_MAC(src_mac, smac);
 	read_MAC(dst_mac, dmac);
 
-	if (tx_socket)
+	if (tx_socket) {
 		gro_sender();
-	else
+	} else {
+		/* Only the receiver exit status determines test success. */
 		gro_receiver();
+		fprintf(stderr, "Gro::%s test passed.\n", testname);
+	}
 
-	fprintf(stderr, "Gro::%s test passed.\n", testname);
 	return 0;
 }

From 51bef03e1a71a27f2bc25c9739992d472830c83c Mon Sep 17 00:00:00 2001
From: Kevin Krakauer <krakauer@google.com>
Date: Wed, 26 Feb 2025 11:27:25 -0800
Subject: [PATCH 1321/2753] selftests/net: deflake GRO tests

GRO tests are timing dependent and can easily flake. This is partially
mitigated in gro.sh by giving each subtest 3 chances to pass. However,
this still flakes on some machines. Reduce the flakiness by:

- Bumping retries to 6.
- Setting napi_defer_hard_irqs to 1 to reduce the chance that GRO is
  flushed prematurely. This also lets us reduce the gro_flush_timeout
  from 1ms to 100us.

Tested: Ran `gro.sh -t large` 1000 times. There were no failures with
this change. Ran inside strace to increase flakiness.

Signed-off-by: Kevin Krakauer <krakauer@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250226192725.621969-4-krakauer@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/gro.sh        | 4 ++--
 tools/testing/selftests/net/setup_veth.sh | 3 ++-
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/gro.sh b/tools/testing/selftests/net/gro.sh
index aabd6e5480b8e..9e3f186bc2a14 100755
--- a/tools/testing/selftests/net/gro.sh
+++ b/tools/testing/selftests/net/gro.sh
@@ -18,10 +18,10 @@ run_test() {
   "--smac" "${CLIENT_MAC}" "--test" "${test}" "--verbose" )
 
   setup_ns
-  # Each test is run 3 times to deflake, because given the receive timing,
+  # Each test is run 6 times to deflake, because given the receive timing,
   # not all packets that should coalesce will be considered in the same flow
   # on every try.
-  for tries in {1..3}; do
+  for tries in {1..6}; do
     # Actual test starts here
     ip netns exec $server_ns ./gro "${ARGS[@]}" "--rx" "--iface" "server" \
       1>>log.txt &
diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index 1f78a87f6f37e..eb3182066d126 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,8 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up
 

From b5d7b2f04ebcff740f44ef4d295b3401aeb029f4 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 26 Feb 2025 14:25:40 +0200
Subject: [PATCH 1322/2753] net/mlx5: Avoid report two health errors on same
 syndrome

In case health counter has not increased for few polling intervals, miss
counter will reach max misses threshold and health report will be
triggered for FW health reporter. In case syndrome found on same health
poll another health report will be triggered.

Avoid two health reports on same syndrome by marking this syndrome as
already known.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index a6329ca2d9bff..52c8035547be5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -799,6 +799,7 @@ static void poll_health(struct timer_list *t)
 	health->prev = count;
 	if (health->miss_counter == MAX_MISSES) {
 		mlx5_core_err(dev, "device's health compromised - reached miss count\n");
+		health->synd = ioread8(&h->synd);
 		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
 	}

From 6bdce277a32632045648abaf3386bb5229670e68 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Wed, 26 Feb 2025 14:25:41 +0200
Subject: [PATCH 1323/2753] net/mlx5: Log health buffer data on any syndrome

Currently health buffer data is logged either when FW fatal error
detected or miss counter reached max misses threshold.

Log health buffer whenever new health syndrome is detected.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shahar Shitrit <shshitrit@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 52c8035547be5..665cbce891757 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -806,8 +806,10 @@ static void poll_health(struct timer_list *t)
 
 	prev_synd = health->synd;
 	health->synd = ioread8(&h->synd);
-	if (health->synd && health->synd != prev_synd)
+	if (health->synd && health->synd != prev_synd) {
+		print_health_info(dev);
 		queue_work(health->wq, &health->report_work);
+	}
 
 out:
 	mod_timer(&health->timer, get_next_poll_jiffies(dev));

From 63f26199721fdf9bf6be74c8daf3df4f6e7e80ea Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 26 Feb 2025 14:25:42 +0200
Subject: [PATCH 1324/2753] net/mlx5: Expose crr in health buffer

Expose crr bit in struct health buffer. When set, it indicates that
the error cannot be recovered without flow involving a cold reset.
Add its value to the health buffer info log.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index 665cbce891757..c7ff646e08650 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -96,6 +96,11 @@ static int mlx5_health_get_rfr(u8 rfr_severity)
 	return rfr_severity >> MLX5_RFR_BIT_OFFSET;
 }
 
+static int mlx5_health_get_crr(u8 rfr_severity)
+{
+	return (rfr_severity >> MLX5_CRR_BIT_OFFSET) & 0x01;
+}
+
 static bool sensor_fw_synd_rfr(struct mlx5_core_dev *dev)
 {
 	struct mlx5_core_health *health = &dev->priv.health;
@@ -442,12 +447,15 @@ static void print_health_info(struct mlx5_core_dev *dev)
 	mlx5_log(dev, severity, "time %u\n", ioread32be(&h->time));
 	mlx5_log(dev, severity, "hw_id 0x%08x\n", ioread32be(&h->hw_id));
 	mlx5_log(dev, severity, "rfr %d\n", mlx5_health_get_rfr(rfr_severity));
+	mlx5_log(dev, severity, "crr %d\n", mlx5_health_get_crr(rfr_severity));
 	mlx5_log(dev, severity, "severity %d (%s)\n", severity, mlx5_loglevel_str(severity));
 	mlx5_log(dev, severity, "irisc_index %d\n", ioread8(&h->irisc_index));
 	mlx5_log(dev, severity, "synd 0x%x: %s\n", ioread8(&h->synd),
 		 hsynd_str(ioread8(&h->synd)));
 	mlx5_log(dev, severity, "ext_synd 0x%04x\n", ioread16be(&h->ext_synd));
 	mlx5_log(dev, severity, "raw fw_ver 0x%08x\n", ioread32be(&h->fw_ver));
+	if (mlx5_health_get_crr(rfr_severity))
+		mlx5_core_warn(dev, "Cold reset is required\n");
 }
 
 static int

From 680173b6bb6b7b521af6a50e9ff14bb1b0cdf931 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Wed, 26 Feb 2025 14:25:43 +0200
Subject: [PATCH 1325/2753] net/mlx5: Add trust lockdown error to health
 syndrome print function

Add the new health syndrome value to hsynd_str() function
to indicate that the device got a trust lockdown fault.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mellanox/mlx5/core/health.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c
index c7ff646e08650..91613d5a36cd4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/health.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c
@@ -380,6 +380,8 @@ static const char *hsynd_str(u8 synd)
 		return "High temperature";
 	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR:
 		return "ICM fetch PCI data poisoned error";
+	case MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR:
+		return "Trust lockdown error";
 	default:
 		return "unrecognized error";
 	}

From c72e455b89f216b43cd0dbb518036ec4c98f5c46 Mon Sep 17 00:00:00 2001
From: Manuel Fombuena <fombuena@outlook.com>
Date: Tue, 25 Feb 2025 22:01:02 +0000
Subject: [PATCH 1326/2753] leds: leds-st1202: Fix NULL pointer access on race
 condition

st1202_dt_init() calls devm_led_classdev_register_ext() before the
internal data structures are properly set up, so the LEDs become visible
to user space while being partially initialized, leading to a window
where trying to access them causes a NULL pointer access.

Move devm_led_classdev_register_ext() from DT initialization
to the end of the probe function when DT and hardware are fully
initialized and ready to interact with user space.

Fixes: 259230378c65 ("leds: Add LED1202 I2C driver")
Signed-off-by: Manuel Fombuena <fombuena@outlook.com>
Link: https://lore.kernel.org/r/CWLP123MB54732771AC0CE5491B3C84DCC5C32@CWLP123MB5473.GBRP123.PROD.OUTLOOK.COM
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/leds-st1202.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/leds/leds-st1202.c b/drivers/leds/leds-st1202.c
index b691c4886993f..e894b3f9a0f46 100644
--- a/drivers/leds/leds-st1202.c
+++ b/drivers/leds/leds-st1202.c
@@ -261,8 +261,6 @@ static int st1202_dt_init(struct st1202_chip *chip)
 	int err, reg;
 
 	for_each_available_child_of_node_scoped(dev_of_node(dev), child) {
-		struct led_init_data init_data = {};
-
 		err = of_property_read_u32(child, "reg", &reg);
 		if (err)
 			return dev_err_probe(dev, err, "Invalid register\n");
@@ -276,15 +274,6 @@ static int st1202_dt_init(struct st1202_chip *chip)
 		led->led_cdev.pattern_set = st1202_led_pattern_set;
 		led->led_cdev.pattern_clear = st1202_led_pattern_clear;
 		led->led_cdev.default_trigger = "pattern";
-
-		init_data.fwnode = led->fwnode;
-		init_data.devicename = "st1202";
-		init_data.default_label = ":";
-
-		err = devm_led_classdev_register_ext(dev, &led->led_cdev, &init_data);
-		if (err < 0)
-			return dev_err_probe(dev, err, "Failed to register LED class device\n");
-
 		led->led_cdev.brightness_set = st1202_brightness_set;
 		led->led_cdev.brightness_get = st1202_brightness_get;
 	}
@@ -368,6 +357,7 @@ static int st1202_probe(struct i2c_client *client)
 		return ret;
 
 	for (int i = 0; i < ST1202_MAX_LEDS; i++) {
+		struct led_init_data init_data = {};
 		led = &chip->leds[i];
 		led->chip = chip;
 		led->led_num = i;
@@ -384,6 +374,15 @@ static int st1202_probe(struct i2c_client *client)
 		if (ret < 0)
 			return dev_err_probe(&client->dev, ret,
 					"Failed to clear LED pattern\n");
+
+		init_data.fwnode = led->fwnode;
+		init_data.devicename = "st1202";
+		init_data.default_label = ":";
+
+		ret = devm_led_classdev_register_ext(&client->dev, &led->led_cdev, &init_data);
+		if (ret < 0)
+			return dev_err_probe(&client->dev, ret,
+					"Failed to register LED class device\n");
 	}
 
 	return 0;

From 3414cda9d41f41703832d0abd01063dd8de82b89 Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Thu, 27 Feb 2025 18:51:06 +0100
Subject: [PATCH 1327/2753] ALSA: hda/realtek: Remove (revert) duplicate Ally X
 config

In commit 1e9c708dc3ae ("ALSA: hda/tas2781: Add new quirk for Lenovo,
ASUS, Dell projects") Baojun adds a bunch of projects to the file,
including for the Ally X. Turns out the initial Ally X was not sorted
properly, so the kernel had 2 quirks for it.

The previous quirk overrode the new one due to being earlier and they
are different. When AB testing, the normal pin fixup seems to work ok
but causes a bit of a minor popping. Given the other config is more
complicated and may cause undefined behavior, revert it.

Fixes: 1e9c708dc3ae ("ALSA: hda/tas2781: Add new quirk for Lenovo, ASUS, Dell projects")
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20250227175107.33432-2-lkml@antheas.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c735f630ecb5a..f92de4a95a4c6 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -7690,7 +7690,6 @@ enum {
 	ALC285_FIXUP_THINKPAD_X1_GEN7,
 	ALC285_FIXUP_THINKPAD_HEADSET_JACK,
 	ALC294_FIXUP_ASUS_ALLY,
-	ALC294_FIXUP_ASUS_ALLY_X,
 	ALC294_FIXUP_ASUS_ALLY_PINS,
 	ALC294_FIXUP_ASUS_ALLY_VERBS,
 	ALC294_FIXUP_ASUS_ALLY_SPEAKER,
@@ -9138,12 +9137,6 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC294_FIXUP_ASUS_ALLY_PINS
 	},
-	[ALC294_FIXUP_ASUS_ALLY_X] = {
-		.type = HDA_FIXUP_FUNC,
-		.v.func = tas2781_fixup_i2c,
-		.chained = true,
-		.chain_id = ALC294_FIXUP_ASUS_ALLY_PINS
-	},
 	[ALC294_FIXUP_ASUS_ALLY_PINS] = {
 		.type = HDA_FIXUP_PINS,
 		.v.pins = (const struct hda_pintbl[]) {
@@ -10645,7 +10638,6 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1740, "ASUS UX430UA", ALC295_FIXUP_ASUS_DACS),
 	SND_PCI_QUIRK(0x1043, 0x17d1, "ASUS UX431FL", ALC294_FIXUP_ASUS_DUAL_SPK),
 	SND_PCI_QUIRK(0x1043, 0x17f3, "ROG Ally NR2301L/X", ALC294_FIXUP_ASUS_ALLY),
-	SND_PCI_QUIRK(0x1043, 0x1eb3, "ROG Ally X RC72LA", ALC294_FIXUP_ASUS_ALLY_X),
 	SND_PCI_QUIRK(0x1043, 0x1863, "ASUS UX6404VI/VV", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1881, "ASUS Zephyrus S/M", ALC294_FIXUP_ASUS_GX502_PINS),
 	SND_PCI_QUIRK(0x1043, 0x18b1, "Asus MJ401TA", ALC256_FIXUP_ASUS_HEADSET_MIC),

From 12784ca33b62fd327631749e6a0cd2a10110a56c Mon Sep 17 00:00:00 2001
From: Antheas Kapenekakis <lkml@antheas.dev>
Date: Thu, 27 Feb 2025 18:51:07 +0100
Subject: [PATCH 1328/2753] ALSA: hda/realtek: Fix Asus Z13 2025 audio

Use the basic quirk for this type of amplifier. Sound works in speakers,
headphones, and microphone. Whereas none worked before.

Tested-by: Kyle Gospodnetich <me@kylegospodneti.ch>
Signed-off-by: Antheas Kapenekakis <lkml@antheas.dev>
Link: https://patch.msgid.link/20250227175107.33432-3-lkml@antheas.dev
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f92de4a95a4c6..926007b4a9ba7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10692,6 +10692,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
+	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From f479ecc5ef15ed8d774968c1a8726a49420f11a0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Daniel=20B=C3=A1rta?= <daniel.barta@trustlab.cz>
Date: Thu, 27 Feb 2025 17:12:55 +0100
Subject: [PATCH 1329/2753] ALSA: hda: Fix speakers on ASUS EXPERTBOOK P5405CSA
 1.0
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After some digging around I have found that this laptop has Cirrus's smart
aplifiers connected to SPI bus (spi1-CSC3551:00-cs35l41-hda).

To get them correctly detected and working I had to modify patch_realtek.c
with ASUS EXPERTBOOK P5405CSA 1.0 SystemID (0x1043, 0x1f63) and add
corresponding hda_quirk (ALC245_FIXUP_CS35L41_SPI_2).

Signed-off-by: Daniel Bárta <daniel.barta@trustlab.cz>
Link: https://patch.msgid.link/20250227161256.18061-2-daniel.barta@trustlab.cz
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 926007b4a9ba7..d58743b955f81 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10691,6 +10691,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f12, "ASUS UM5302", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x1f1f, "ASUS H7604JI/JV/J3D", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x1f63, "ASUS P5405CSA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),

From c5b0320bbf79548fbf058a3925a07c8f281beeab Mon Sep 17 00:00:00 2001
From: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Date: Mon, 6 Jan 2025 19:14:13 +0000
Subject: [PATCH 1330/2753] iommu/amd: Preserve default DTE fields when
 updating Host Page Table Root

When updating the page table root field on the DTE, avoid overwriting any
bits that are already set. The earlier call to make_clear_dte() writes
default values that all DTEs must have set (currently DTE[V]), and those
must be preserved.

Currently this doesn't cause problems since the page table root update is
the first field that is set after make_clear_dte() is called, and
DTE_FLAG_V is set again later along with the permission bits (IR/IW).
Remove this redundant assignment too.

Fixes: fd5dff9de4be ("iommu/amd: Modify set_dte_entry() to use 256-bit DTE helpers")
Signed-off-by: Alejandro Jimenez <alejandro.j.jimenez@oracle.com>
Reviewed-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20250106191413.3107140-1-alejandro.j.jimenez@oracle.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/amd/iommu.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index b48a72bd7b23d..cd5116d8c3b28 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -2043,12 +2043,12 @@ static void set_dte_entry(struct amd_iommu *iommu,
 	make_clear_dte(dev_data, dte, &new);
 
 	if (domain->iop.mode != PAGE_MODE_NONE)
-		new.data[0] = iommu_virt_to_phys(domain->iop.root);
+		new.data[0] |= iommu_virt_to_phys(domain->iop.root);
 
 	new.data[0] |= (domain->iop.mode & DEV_ENTRY_MODE_MASK)
 		    << DEV_ENTRY_MODE_SHIFT;
 
-	new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW | DTE_FLAG_V;
+	new.data[0] |= DTE_FLAG_IR | DTE_FLAG_IW;
 
 	/*
 	 * When SNP is enabled, we can only support TV=1 with non-zero domain ID.

From 64f792981e35e191eb619f6f2fefab76cc7d6112 Mon Sep 17 00:00:00 2001
From: Jerry Snitselaar <jsnitsel@redhat.com>
Date: Fri, 28 Feb 2025 18:27:25 +0800
Subject: [PATCH 1331/2753] iommu/vt-d: Remove device comparison in
 context_setup_pass_through_cb

Remove the device comparison check in context_setup_pass_through_cb.
pci_for_each_dma_alias already makes a decision on whether the
callback function should be called for a device. With the check
in place it will fail to create context entries for aliases as
it walks up to the root bus.

Fixes: 2031c469f816 ("iommu/vt-d: Add support for static identity domain")
Closes: https://lore.kernel.org/linux-iommu/82499eb6-00b7-4f83-879a-e97b4144f576@linux.intel.com/
Cc: stable@vger.kernel.org
Signed-off-by: Jerry Snitselaar <jsnitsel@redhat.com>
Link: https://lore.kernel.org/r/20250224180316.140123-1-jsnitsel@redhat.com
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/iommu.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index cc46098f875b1..4d8d4593c9c81 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4378,9 +4378,6 @@ static int context_setup_pass_through_cb(struct pci_dev *pdev, u16 alias, void *
 {
 	struct device *dev = data;
 
-	if (dev != &pdev->dev)
-		return 0;
-
 	return context_setup_pass_through(dev, PCI_BUS_NUM(alias), alias & 0xff);
 }
 

From b150654f74bf0df8e6a7936d5ec51400d9ec06d8 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@linux.intel.com>
Date: Fri, 28 Feb 2025 18:27:26 +0800
Subject: [PATCH 1332/2753] iommu/vt-d: Fix suspicious RCU usage

Commit <d74169ceb0d2> ("iommu/vt-d: Allocate DMAR fault interrupts
locally") moved the call to enable_drhd_fault_handling() to a code
path that does not hold any lock while traversing the drhd list. Fix
it by ensuring the dmar_global_lock lock is held when traversing the
drhd list.

Without this fix, the following warning is triggered:
 =============================
 WARNING: suspicious RCU usage
 6.14.0-rc3 #55 Not tainted
 -----------------------------
 drivers/iommu/intel/dmar.c:2046 RCU-list traversed in non-reader section!!
               other info that might help us debug this:
               rcu_scheduler_active = 1, debug_locks = 1
 2 locks held by cpuhp/1/23:
 #0: ffffffff84a67c50 (cpu_hotplug_lock){++++}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
 #1: ffffffff84a6a380 (cpuhp_state-up){+.+.}-{0:0}, at: cpuhp_thread_fun+0x87/0x2c0
 stack backtrace:
 CPU: 1 UID: 0 PID: 23 Comm: cpuhp/1 Not tainted 6.14.0-rc3 #55
 Call Trace:
  <TASK>
  dump_stack_lvl+0xb7/0xd0
  lockdep_rcu_suspicious+0x159/0x1f0
  ? __pfx_enable_drhd_fault_handling+0x10/0x10
  enable_drhd_fault_handling+0x151/0x180
  cpuhp_invoke_callback+0x1df/0x990
  cpuhp_thread_fun+0x1ea/0x2c0
  smpboot_thread_fn+0x1f5/0x2e0
  ? __pfx_smpboot_thread_fn+0x10/0x10
  kthread+0x12a/0x2d0
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x4a/0x60
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>

Holding the lock in enable_drhd_fault_handling() triggers a lockdep splat
about a possible deadlock between dmar_global_lock and cpu_hotplug_lock.
This is avoided by not holding dmar_global_lock when calling
iommu_device_register(), which initiates the device probe process.

Fixes: d74169ceb0d2 ("iommu/vt-d: Allocate DMAR fault interrupts locally")
Reported-and-tested-by: Ido Schimmel <idosch@nvidia.com>
Closes: https://lore.kernel.org/linux-iommu/Zx9OwdLIc_VoQ0-a@shredder.mtl.com/
Tested-by: Breno Leitao <leitao@debian.org>
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250218022422.2315082-1-baolu.lu@linux.intel.com
Tested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Joerg Roedel <jroedel@suse.de>
---
 drivers/iommu/intel/dmar.c  | 1 +
 drivers/iommu/intel/iommu.c | 7 +++++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 9f424acf474e9..e540092d664d2 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/drivers/iommu/intel/dmar.c
@@ -2043,6 +2043,7 @@ int enable_drhd_fault_handling(unsigned int cpu)
 	/*
 	 * Enable fault control interrupt.
 	 */
+	guard(rwsem_read)(&dmar_global_lock);
 	for_each_iommu(iommu, drhd) {
 		u32 fault_status;
 		int ret;
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 4d8d4593c9c81..bf1f0c8143483 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -3146,7 +3146,14 @@ int __init intel_iommu_init(void)
 		iommu_device_sysfs_add(&iommu->iommu, NULL,
 				       intel_iommu_groups,
 				       "%s", iommu->name);
+		/*
+		 * The iommu device probe is protected by the iommu_probe_device_lock.
+		 * Release the dmar_global_lock before entering the device probe path
+		 * to avoid unnecessary lock order splat.
+		 */
+		up_read(&dmar_global_lock);
 		iommu_device_register(&iommu->iommu, &intel_iommu_ops, NULL);
+		down_read(&dmar_global_lock);
 
 		iommu_pmu_register(iommu);
 	}

From 7ed3f3c40d7b5cd8d8e4ce8e4c27d604a27c1861 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 27 Feb 2025 22:19:17 +0000
Subject: [PATCH 1333/2753] wifi: iwlwifi: Fix spelling mistake "Increate" ->
 "Increase"

There is a spelling mistake in a IWL_DEBUG_RATE message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Link: https://patch.msgid.link/20250227221917.658401-1-colin.i.king@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/rs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
index a8c4e354e2ce7..068c58e9c1eb4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/rs.c
@@ -1783,7 +1783,7 @@ static enum rs_action rs_get_rate_action(struct iwl_mvm *mvm,
 	if ((high_tpt != IWL_INVALID_VALUE) &&
 	    (high_tpt > current_tpt)) {
 		IWL_DEBUG_RATE(mvm,
-			       "Higher rate is better. Increate rate\n");
+			       "Higher rate is better. Increase rate\n");
 		return RS_ACTION_UPSCALE;
 	}
 

From 23ff5f6f23f1419d87351243fd4258c2eec0fbf7 Mon Sep 17 00:00:00 2001
From: Sarika Sharma <quic_sarishar@quicinc.com>
Date: Thu, 13 Feb 2025 22:46:21 +0530
Subject: [PATCH 1334/2753] wifi: cfg80211: reorg sinfo structure elements for
 mesh

Currently, as multi-link operation(MLO) is not supported for mesh,
reorganize the sinfo structure for mesh-specific fields and embed
mesh related NL attributes together in organized view.
This will allow for the simplified reorganization of sinfo structure
for link level in a subsequent patch to add support for MLO station
statistics.
No functionality changes added.

Pahole summary before the reorg of sinfo structure:
 - size: 256, cachelines: 4, members: 50
 - sum members: 239, holes: 4, sum holes: 17
 - paddings: 2, sum paddings: 2
 - forced alignments: 1, forced holes: 1, sum forced holes: 1

Pahole summary after the reorg of sinfo structure:
 - size: 248, cachelines: 4, members: 50
 - sum members: 239, holes: 4, sum holes: 9
 - paddings: 2, sum paddings: 2
 - forced alignments: 1, last cacheline: 56 bytes

Signed-off-by: Sarika Sharma <quic_sarishar@quicinc.com>
Link: https://patch.msgid.link/20250213171632.1646538-2-quic_sarishar@quicinc.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 43 +++++++++++++++++++++---------------------
 net/wireless/nl80211.c | 11 ++++++-----
 2 files changed, 27 insertions(+), 27 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 3580f3f5f44ee..6b170a8d086c8 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -2045,9 +2045,6 @@ struct cfg80211_tid_stats {
  * @assoc_at: bootime (ns) of the last association
  * @rx_bytes: bytes (size of MPDUs) received from this station
  * @tx_bytes: bytes (size of MPDUs) transmitted to this station
- * @llid: mesh local link id
- * @plid: mesh peer link id
- * @plink_state: mesh peer link state
  * @signal: The signal strength, type depends on the wiphy's signal_type.
  *	For CFG80211_SIGNAL_TYPE_MBM, value is expressed in _dBm_.
  * @signal_avg: Average signal strength, type depends on the wiphy's signal_type.
@@ -2067,14 +2064,20 @@ struct cfg80211_tid_stats {
  *	This number should increase every time the list of stations
  *	changes, i.e. when a station is added or removed, so that
  *	userspace can tell whether it got a consistent snapshot.
+ * @beacon_loss_count: Number of times beacon loss event has triggered.
  * @assoc_req_ies: IEs from (Re)Association Request.
  *	This is used only when in AP mode with drivers that do not use
  *	user space MLME/SME implementation. The information is provided for
  *	the cfg80211_new_sta() calls to notify user space of the IEs.
  * @assoc_req_ies_len: Length of assoc_req_ies buffer in octets.
  * @sta_flags: station flags mask & values
- * @beacon_loss_count: Number of times beacon loss event has triggered.
  * @t_offset: Time offset of the station relative to this host.
+ * @llid: mesh local link id
+ * @plid: mesh peer link id
+ * @plink_state: mesh peer link state
+ * @connected_to_gate: true if mesh STA has a path to mesh gate
+ * @connected_to_as: true if mesh STA has a path to authentication server
+ * @airtime_link_metric: mesh airtime link metric.
  * @local_pm: local mesh STA power save mode
  * @peer_pm: peer mesh STA power save mode
  * @nonpeer_pm: non-peer mesh STA power save mode
@@ -2083,7 +2086,6 @@ struct cfg80211_tid_stats {
  * @rx_beacon: number of beacons received from this peer
  * @rx_beacon_signal_avg: signal strength average (in dBm) for beacons received
  *	from this peer
- * @connected_to_gate: true if mesh STA has a path to mesh gate
  * @rx_duration: aggregate PPDU duration(usecs) for all the frames from a peer
  * @tx_duration: aggregate PPDU duration(usecs) for all the frames to a peer
  * @airtime_weight: current airtime scheduling weight
@@ -2097,8 +2099,6 @@ struct cfg80211_tid_stats {
  * @fcs_err_count: number of packets (MPDUs) received from this station with
  *	an FCS error. This counter should be incremented only when TA of the
  *	received packet with an FCS error matches the peer MAC address.
- * @airtime_link_metric: mesh airtime link metric.
- * @connected_to_as: true if mesh STA has a path to authentication server
  * @mlo_params_valid: Indicates @assoc_link_id and @mld_addr fields are filled
  *	by driver. Drivers use this only in cfg80211_new_sta() calls when AP
  *	MLD's MLME/SME is offload to driver. Drivers won't fill this
@@ -2125,9 +2125,6 @@ struct station_info {
 	u64 assoc_at;
 	u64 rx_bytes;
 	u64 tx_bytes;
-	u16 llid;
-	u16 plid;
-	u8 plink_state;
 	s8 signal;
 	s8 signal_avg;
 
@@ -2147,36 +2144,38 @@ struct station_info {
 
 	int generation;
 
+	u32 beacon_loss_count;
+
 	const u8 *assoc_req_ies;
 	size_t assoc_req_ies_len;
 
-	u32 beacon_loss_count;
 	s64 t_offset;
+	u16 llid;
+	u16 plid;
+	u8 plink_state;
+	u8 connected_to_gate;
+	u8 connected_to_as;
+	u32 airtime_link_metric;
 	enum nl80211_mesh_power_mode local_pm;
 	enum nl80211_mesh_power_mode peer_pm;
 	enum nl80211_mesh_power_mode nonpeer_pm;
 
 	u32 expected_throughput;
 
-	u64 tx_duration;
-	u64 rx_duration;
-	u64 rx_beacon;
-	u8 rx_beacon_signal_avg;
-	u8 connected_to_gate;
+	u16 airtime_weight;
 
-	struct cfg80211_tid_stats *pertid;
 	s8 ack_signal;
 	s8 avg_ack_signal;
+	struct cfg80211_tid_stats *pertid;
 
-	u16 airtime_weight;
+	u64 tx_duration;
+	u64 rx_duration;
+	u64 rx_beacon;
+	u8 rx_beacon_signal_avg;
 
 	u32 rx_mpdu_count;
 	u32 fcs_err_count;
 
-	u32 airtime_link_metric;
-
-	u8 connected_to_as;
-
 	bool mlo_params_valid;
 	u8 assoc_link_id;
 	u8 mld_addr[ETH_ALEN] __aligned(2);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 79b3f34e72e2a..2c4e06610a791 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -6750,9 +6750,6 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 
 	PUT_SINFO_U64(RX_BYTES64, rx_bytes);
 	PUT_SINFO_U64(TX_BYTES64, tx_bytes);
-	PUT_SINFO(LLID, llid, u16);
-	PUT_SINFO(PLID, plid, u16);
-	PUT_SINFO(PLINK_STATE, plink_state, u8);
 	PUT_SINFO_U64(RX_DURATION, rx_duration);
 	PUT_SINFO_U64(TX_DURATION, tx_duration);
 
@@ -6796,13 +6793,18 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 	PUT_SINFO(TX_RETRIES, tx_retries, u32);
 	PUT_SINFO(TX_FAILED, tx_failed, u32);
 	PUT_SINFO(EXPECTED_THROUGHPUT, expected_throughput, u32);
-	PUT_SINFO(AIRTIME_LINK_METRIC, airtime_link_metric, u32);
 	PUT_SINFO(BEACON_LOSS, beacon_loss_count, u32);
+
+	PUT_SINFO(LLID, llid, u16);
+	PUT_SINFO(PLID, plid, u16);
+	PUT_SINFO(PLINK_STATE, plink_state, u8);
+	PUT_SINFO(AIRTIME_LINK_METRIC, airtime_link_metric, u32);
 	PUT_SINFO(LOCAL_PM, local_pm, u32);
 	PUT_SINFO(PEER_PM, peer_pm, u32);
 	PUT_SINFO(NONPEER_PM, nonpeer_pm, u32);
 	PUT_SINFO(CONNECTED_TO_GATE, connected_to_gate, u8);
 	PUT_SINFO(CONNECTED_TO_AS, connected_to_as, u8);
+	PUT_SINFO_U64(T_OFFSET, t_offset);
 
 	if (sinfo->filled & BIT_ULL(NL80211_STA_INFO_BSS_PARAM)) {
 		bss_param = nla_nest_start_noflag(msg,
@@ -6830,7 +6832,6 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid,
 		    &sinfo->sta_flags))
 		goto nla_put_failure;
 
-	PUT_SINFO_U64(T_OFFSET, t_offset);
 	PUT_SINFO_U64(RX_DROP_MISC, rx_dropped_misc);
 	PUT_SINFO_U64(BEACON_RX, rx_beacon);
 	PUT_SINFO(BEACON_SIGNAL_AVG, rx_beacon_signal_avg, u8);

From e5328c14590d034dc586e56aaab88e966d06efa7 Mon Sep 17 00:00:00 2001
From: Sarika Sharma <quic_sarishar@quicinc.com>
Date: Thu, 13 Feb 2025 22:46:22 +0530
Subject: [PATCH 1335/2753] wifi: mac80211: refactor populating mesh related
 fields in sinfo

Introduce the sta_set_mesh_sinfo() to populate mesh related
fields in sinfo structure for station statistics.
This will allow for the simplified population of other fields in the
sinfo structure for link level in a subsequent patch to add support
for MLO station statistics.
No functionality changes added.

Signed-off-by: Sarika Sharma <quic_sarishar@quicinc.com>
Link: https://patch.msgid.link/20250213171632.1646538-3-quic_sarishar@quicinc.com
[reword since it's just an internal thing]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 64 ++++++++++++++++++++++-------------------
 1 file changed, 35 insertions(+), 29 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f83268fa9f928..a4b4506cd35ba 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -2584,6 +2584,39 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats)
 	return value;
 }
 
+#ifdef CONFIG_MAC80211_MESH
+static void sta_set_mesh_sinfo(struct sta_info *sta,
+			       struct station_info *sinfo)
+{
+	struct ieee80211_local *local = sta->sdata->local;
+
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) |
+			 BIT_ULL(NL80211_STA_INFO_PLID) |
+			 BIT_ULL(NL80211_STA_INFO_PLINK_STATE) |
+			 BIT_ULL(NL80211_STA_INFO_LOCAL_PM) |
+			 BIT_ULL(NL80211_STA_INFO_PEER_PM) |
+			 BIT_ULL(NL80211_STA_INFO_NONPEER_PM) |
+			 BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE) |
+			 BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_AS);
+
+	sinfo->llid = sta->mesh->llid;
+	sinfo->plid = sta->mesh->plid;
+	sinfo->plink_state = sta->mesh->plink_state;
+	if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
+		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET);
+		sinfo->t_offset = sta->mesh->t_offset;
+	}
+	sinfo->local_pm = sta->mesh->local_pm;
+	sinfo->peer_pm = sta->mesh->peer_pm;
+	sinfo->nonpeer_pm = sta->mesh->nonpeer_pm;
+	sinfo->connected_to_gate = sta->mesh->connected_to_gate;
+	sinfo->connected_to_as = sta->mesh->connected_to_as;
+
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_LINK_METRIC);
+	sinfo->airtime_link_metric = airtime_link_metric_get(local, sta);
+}
+#endif
+
 void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 		   bool tidstats)
 {
@@ -2768,31 +2801,10 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 			sta_set_tidstats(sta, &sinfo->pertid[i], i);
 	}
 
-	if (ieee80211_vif_is_mesh(&sdata->vif)) {
 #ifdef CONFIG_MAC80211_MESH
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_LLID) |
-				 BIT_ULL(NL80211_STA_INFO_PLID) |
-				 BIT_ULL(NL80211_STA_INFO_PLINK_STATE) |
-				 BIT_ULL(NL80211_STA_INFO_LOCAL_PM) |
-				 BIT_ULL(NL80211_STA_INFO_PEER_PM) |
-				 BIT_ULL(NL80211_STA_INFO_NONPEER_PM) |
-				 BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_GATE) |
-				 BIT_ULL(NL80211_STA_INFO_CONNECTED_TO_AS);
-
-		sinfo->llid = sta->mesh->llid;
-		sinfo->plid = sta->mesh->plid;
-		sinfo->plink_state = sta->mesh->plink_state;
-		if (test_sta_flag(sta, WLAN_STA_TOFFSET_KNOWN)) {
-			sinfo->filled |= BIT_ULL(NL80211_STA_INFO_T_OFFSET);
-			sinfo->t_offset = sta->mesh->t_offset;
-		}
-		sinfo->local_pm = sta->mesh->local_pm;
-		sinfo->peer_pm = sta->mesh->peer_pm;
-		sinfo->nonpeer_pm = sta->mesh->nonpeer_pm;
-		sinfo->connected_to_gate = sta->mesh->connected_to_gate;
-		sinfo->connected_to_as = sta->mesh->connected_to_as;
+	if (ieee80211_vif_is_mesh(&sdata->vif))
+		sta_set_mesh_sinfo(sta, sinfo);
 #endif
-	}
 
 	sinfo->bss_param.flags = 0;
 	if (sdata->vif.bss_conf.use_cts_prot)
@@ -2848,12 +2860,6 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo,
 		sinfo->filled |=
 			BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG);
 	}
-
-	if (ieee80211_vif_is_mesh(&sdata->vif)) {
-		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_LINK_METRIC);
-		sinfo->airtime_link_metric =
-			airtime_link_metric_get(local, sta);
-	}
 }
 
 u32 sta_get_expected_throughput(struct sta_info *sta)

From b654f7a51ffb386131de42aa98ed831f8c126546 Mon Sep 17 00:00:00 2001
From: Ming Lei <ming.lei@redhat.com>
Date: Fri, 28 Feb 2025 21:26:56 +0800
Subject: [PATCH 1336/2753] block: fix 'kmem_cache of name 'bio-108' already
 exists'

Device mapper bioset often has big bio_slab size, which can be more than
1000, then 8byte can't hold the slab name any more, cause the kmem_cache
allocation warning of 'kmem_cache of name 'bio-108' already exists'.

Fix the warning by extending bio_slab->name to 12 bytes, but fix output
of /proc/slabinfo

Reported-by: Guangwu Zhang <guazhang@redhat.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250228132656.2838008-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/bio.c b/block/bio.c
index f0c416e5931d9..6ac5983ba51e6 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -77,7 +77,7 @@ struct bio_slab {
 	struct kmem_cache *slab;
 	unsigned int slab_ref;
 	unsigned int slab_size;
-	char name[8];
+	char name[12];
 };
 static DEFINE_MUTEX(bio_slab_lock);
 static DEFINE_XARRAY(bio_slabs);

From 64407f4b5807dc9dec8135e1bfd45d2cb11b4ea0 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 28 Feb 2025 16:03:47 +0300
Subject: [PATCH 1337/2753] gpiolib: Fix Oops in
 gpiod_direction_input_nonotify()

The gpiod_direction_input_nonotify() function is supposed to return zero
if the direction for the pin is input.  But instead it accidentally
returns GPIO_LINE_DIRECTION_IN (1) which will be cast into an ERR_PTR()
in gpiochip_request_own_desc().  The callers dereference it and it leads
to a crash.

I changed gpiod_direction_output_raw_commit() just for consistency but
returning GPIO_LINE_DIRECTION_OUT (0) is fine.

Cc: stable@vger.kernel.org
Fixes: 9d846b1aebbe ("gpiolib: check the return value of gpio_chip::get_direction()")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/254f3925-3015-4c9d-aac5-bb9b4b2cd2c5@stanley.mountain
[Bartosz: moved the variable declarations to the top of the functions]
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index fc19df5a64c2b..8741600af7efb 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2712,7 +2712,7 @@ EXPORT_SYMBOL_GPL(gpiod_direction_input);
 
 int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 {
-	int ret = 0;
+	int ret = 0, dir;
 
 	CLASS(gpio_chip_guard, guard)(desc);
 	if (!guard.gc)
@@ -2740,12 +2740,12 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 		ret = guard.gc->direction_input(guard.gc,
 						gpio_chip_hwgpio(desc));
 	} else if (guard.gc->get_direction) {
-		ret = guard.gc->get_direction(guard.gc,
+		dir = guard.gc->get_direction(guard.gc,
 					      gpio_chip_hwgpio(desc));
-		if (ret < 0)
-			return ret;
+		if (dir < 0)
+			return dir;
 
-		if (ret != GPIO_LINE_DIRECTION_IN) {
+		if (dir != GPIO_LINE_DIRECTION_IN) {
 			gpiod_warn(desc,
 				   "%s: missing direction_input() operation and line is output\n",
 				    __func__);
@@ -2764,7 +2764,7 @@ int gpiod_direction_input_nonotify(struct gpio_desc *desc)
 
 static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 {
-	int val = !!value, ret = 0;
+	int val = !!value, ret = 0, dir;
 
 	CLASS(gpio_chip_guard, guard)(desc);
 	if (!guard.gc)
@@ -2788,12 +2788,12 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 	} else {
 		/* Check that we are in output mode if we can */
 		if (guard.gc->get_direction) {
-			ret = guard.gc->get_direction(guard.gc,
+			dir = guard.gc->get_direction(guard.gc,
 						      gpio_chip_hwgpio(desc));
-			if (ret < 0)
-				return ret;
+			if (dir < 0)
+				return dir;
 
-			if (ret != GPIO_LINE_DIRECTION_OUT) {
+			if (dir != GPIO_LINE_DIRECTION_OUT) {
 				gpiod_warn(desc,
 					   "%s: missing direction_output() operation\n",
 					   __func__);

From be45bc4eff33d9a7dae84a2150f242a91a617402 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 08:54:41 -0800
Subject: [PATCH 1338/2753] KVM: SVM: Set RFLAGS.IF=1 in C code, to get VMRUN
 out of the STI shadow

Enable/disable local IRQs, i.e. set/clear RFLAGS.IF, in the common
svm_vcpu_enter_exit() just after/before guest_state_{enter,exit}_irqoff()
so that VMRUN is not executed in an STI shadow.  AMD CPUs have a quirk
(some would say "bug"), where the STI shadow bleeds into the guest's
intr_state field if a #VMEXIT occurs during injection of an event, i.e. if
the VMRUN doesn't complete before the subsequent #VMEXIT.

The spurious "interrupts masked" state is relatively benign, as it only
occurs during event injection and is transient.  Because KVM is already
injecting an event, the guest can't be in HLT, and if KVM is querying IRQ
blocking for injection, then KVM would need to force an immediate exit
anyways since injecting multiple events is impossible.

However, because KVM copies int_state verbatim from vmcb02 to vmcb12, the
spurious STI shadow is visible to L1 when running a nested VM, which can
trip sanity checks, e.g. in VMware's VMM.

Hoist the STI+CLI all the way to C code, as the aforementioned calls to
guest_state_{enter,exit}_irqoff() already inform lockdep that IRQs are
enabled/disabled, and taking a fault on VMRUN with RFLAGS.IF=1 is already
possible.  I.e. if there's kernel code that is confused by running with
RFLAGS.IF=1, then it's already a problem.  In practice, since GIF=0 also
blocks NMIs, the only change in exposure to non-KVM code (relative to
surrounding VMRUN with STI+CLI) is exception handling code, and except for
the kvm_rebooting=1 case, all exception in the core VM-Enter/VM-Exit path
are fatal.

Use the "raw" variants to enable/disable IRQs to avoid tracing in the
"no instrumentation" code; the guest state helpers also take care of
tracing IRQ state.

Oppurtunstically document why KVM needs to do STI in the first place.

Reported-by: Doug Covelli <doug.covelli@broadcom.com>
Closes: https://lore.kernel.org/all/CADH9ctBs1YPmE4aCfGPNBwA10cA8RuAk2gO7542DjMZgs4uzJQ@mail.gmail.com
Fixes: f14eec0a3203 ("KVM: SVM: move more vmentry code to assembly")
Cc: stable@vger.kernel.org
Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250224165442.2338294-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c     | 14 ++++++++++++++
 arch/x86/kvm/svm/vmenter.S | 10 +---------
 2 files changed, 15 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a713c803a3a37..0d299f3f921e6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4189,6 +4189,18 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 
 	guest_state_enter_irqoff();
 
+	/*
+	 * Set RFLAGS.IF prior to VMRUN, as the host's RFLAGS.IF at the time of
+	 * VMRUN controls whether or not physical IRQs are masked (KVM always
+	 * runs with V_INTR_MASKING_MASK).  Toggle RFLAGS.IF here to avoid the
+	 * temptation to do STI+VMRUN+CLI, as AMD CPUs bleed the STI shadow
+	 * into guest state if delivery of an event during VMRUN triggers a
+	 * #VMEXIT, and the guest_state transitions already tell lockdep that
+	 * IRQs are being enabled/disabled.  Note!  GIF=0 for the entirety of
+	 * this path, so IRQs aren't actually unmasked while running host code.
+	 */
+	raw_local_irq_enable();
+
 	amd_clear_divider();
 
 	if (sev_es_guest(vcpu->kvm))
@@ -4197,6 +4209,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
 	else
 		__svm_vcpu_run(svm, spec_ctrl_intercepted);
 
+	raw_local_irq_disable();
+
 	guest_state_exit_irqoff();
 }
 
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 2ed80aea3bb13..0c61153b275f6 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -170,12 +170,8 @@ SYM_FUNC_START(__svm_vcpu_run)
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
 	/* Enter guest mode */
-	sti
-
 3:	vmrun %_ASM_AX
 4:
-	cli
-
 	/* Pop @svm to RAX while it's the only available register. */
 	pop %_ASM_AX
 
@@ -340,12 +336,8 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov KVM_VMCB_pa(%rax), %rax
 
 	/* Enter guest mode */
-	sti
-
 1:	vmrun %rax
-
-2:	cli
-
+2:
 	/* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */
 	FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_VMEXIT
 

From f3513a335e71296a1851167b4e3b0e2bf09fc5f1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Mon, 24 Feb 2025 08:54:42 -0800
Subject: [PATCH 1339/2753] KVM: selftests: Assert that STI blocking isn't set
 after event injection

Add an L1 (guest) assert to the nested exceptions test to verify that KVM
doesn't put VMRUN in an STI shadow (AMD CPUs bleed the shadow into the
guest's int_state if a #VMEXIT occurs before VMRUN fully completes).

Add a similar assert to the VMX side as well, because why not.

Reviewed-by: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250224165442.2338294-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/nested_exceptions_test.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
index 3eb0313ffa397..3641a42934acb 100644
--- a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
@@ -85,6 +85,7 @@ static void svm_run_l2(struct svm_test_data *svm, void *l2_code, int vector,
 
 	GUEST_ASSERT_EQ(ctrl->exit_code, (SVM_EXIT_EXCP_BASE + vector));
 	GUEST_ASSERT_EQ(ctrl->exit_info_1, error_code);
+	GUEST_ASSERT(!ctrl->int_state);
 }
 
 static void l1_svm_code(struct svm_test_data *svm)
@@ -122,6 +123,7 @@ static void vmx_run_l2(void *l2_code, int vector, uint32_t error_code)
 	GUEST_ASSERT_EQ(vmreadz(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
 	GUEST_ASSERT_EQ((vmreadz(VM_EXIT_INTR_INFO) & 0xff), vector);
 	GUEST_ASSERT_EQ(vmreadz(VM_EXIT_INTR_ERROR_CODE), error_code);
+	GUEST_ASSERT(!vmreadz(GUEST_INTERRUPTIBILITY_INFO));
 }
 
 static void l1_vmx_code(struct vmx_pages *vmx)

From ee89e8013383d50a27ea9bf3c8a69eed6799856f Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:06 -0800
Subject: [PATCH 1340/2753] KVM: SVM: Drop DEBUGCTL[5:2] from guest's effective
 value
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drop bits 5:2 from the guest's effective DEBUGCTL value, as AMD changed
the architectural behavior of the bits and broke backwards compatibility.
On CPUs without BusLockTrap (or at least, in APMs from before ~2023),
bits 5:2 controlled the behavior of external pins:

  Performance-Monitoring/Breakpoint Pin-Control (PBi)—Bits 5:2, read/write.
  Software uses thesebits to control the type of information reported by
  the four external performance-monitoring/breakpoint pins on the
  processor. When a PBi bit is cleared to 0, the corresponding external pin
  (BPi) reports performance-monitor information. When a PBi bit is set to
  1, the corresponding external pin (BPi) reports breakpoint information.

With the introduction of BusLockTrap, presumably to be compatible with
Intel CPUs, AMD redefined bit 2 to be BLCKDB:

  Bus Lock #DB Trap (BLCKDB)—Bit 2, read/write. Software sets this bit to
  enable generation of a #DB trap following successful execution of a bus
  lock when CPL is > 0.

and redefined bits 5:3 (and bit 6) as "6:3 Reserved MBZ".

Ideally, KVM would treat bits 5:2 as reserved.  Defer that change to a
feature cleanup to avoid breaking existing guest in LTS kernels.  For now,
drop the bits to retain backwards compatibility (of a sort).

Note, dropping bits 5:2 is still a guest-visible change, e.g. if the guest
is enabling LBRs *and* the legacy PBi bits, then the state of the PBi bits
is visible to the guest, whereas now the guest will always see '0'.

Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 12 ++++++++++++
 arch/x86/kvm/svm/svm.h |  2 +-
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 0d299f3f921e6..bdafbde1f211a 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3165,6 +3165,18 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 			kvm_pr_unimpl_wrmsr(vcpu, ecx, data);
 			break;
 		}
+
+		/*
+		 * AMD changed the architectural behavior of bits 5:2.  On CPUs
+		 * without BusLockTrap, bits 5:2 control "external pins", but
+		 * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
+		 * and bits 5:3 are reserved-to-zero.  Sadly, old KVM allowed
+		 * the guest to set bits 5:2 despite not actually virtualizing
+		 * Performance-Monitoring/Breakpoint external pins.  Drop bits
+		 * 5:2 for backwards compatibility.
+		 */
+		data &= ~GENMASK(5, 2);
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 9d7cdb8fbf872..3a931d3885e71 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -584,7 +584,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(0x3fULL))
+#define DEBUGCTL_RESERVED_BITS (~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR))
 
 extern bool dump_invalid_vmcb;
 

From d0eac42f5cecce009d315655bee341304fbe075e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:07 -0800
Subject: [PATCH 1341/2753] KVM: SVM: Suppress DEBUGCTL.BTF on AMD

Mark BTF as reserved in DEBUGCTL on AMD, as KVM doesn't actually support
BTF, and fully enabling BTF virtualization is non-trivial due to
interactions with the emulator, guest_debug, #DB interception, nested SVM,
etc.

Don't inject #GP if the guest attempts to set BTF, as there's no way to
communicate lack of support to the guest, and instead suppress the flag
and treat the WRMSR as (partially) unsupported.

In short, make KVM behave the same on AMD and Intel (VMX already squashes
BTF).

Note, due to other bugs in KVM's handling of DEBUGCTL, the only way BTF
has "worked" in any capacity is if the guest simultaneously enables LBRs.

Reported-by: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 9 +++++++++
 arch/x86/kvm/svm/svm.h | 2 +-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index bdafbde1f211a..ed48465186961 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3177,6 +3177,15 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		 */
 		data &= ~GENMASK(5, 2);
 
+		/*
+		 * Suppress BTF as KVM doesn't virtualize BTF, but there's no
+		 * way to communicate lack of support to the guest.
+		 */
+		if (data & DEBUGCTLMSR_BTF) {
+			kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+			data &= ~DEBUGCTLMSR_BTF;
+		}
+
 		if (data & DEBUGCTL_RESERVED_BITS)
 			return 1;
 
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index 3a931d3885e71..ea44c1da5a7c9 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -584,7 +584,7 @@ static inline bool is_vnmi_enabled(struct vcpu_svm *svm)
 /* svm.c */
 #define MSR_INVALID				0xffffffffU
 
-#define DEBUGCTL_RESERVED_BITS (~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR))
+#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
 
 extern bool dump_invalid_vmcb;
 

From fb71c795935652fa20eaf9517ca9547f5af99a76 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:08 -0800
Subject: [PATCH 1342/2753] KVM: x86: Snapshot the host's DEBUGCTL in common
 x86

Move KVM's snapshot of DEBUGCTL to kvm_vcpu_arch and take the snapshot in
common x86, so that SVM can also use the snapshot.

Opportunistically change the field to a u64.  While bits 63:32 are reserved
on AMD, not mentioned at all in Intel's SDM, and managed as an "unsigned
long" by the kernel, DEBUGCTL is an MSR and therefore a 64-bit value.

Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h | 1 +
 arch/x86/kvm/vmx/vmx.c          | 8 ++------
 arch/x86/kvm/vmx/vmx.h          | 2 --
 arch/x86/kvm/x86.c              | 1 +
 4 files changed, 4 insertions(+), 8 deletions(-)

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 0b7af5902ff75..32ae3aa50c7e3 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -780,6 +780,7 @@ struct kvm_vcpu_arch {
 	u32 pkru;
 	u32 hflags;
 	u64 efer;
+	u64 host_debugctl;
 	u64 apic_base;
 	struct kvm_lapic *apic;    /* kernel irqchip context */
 	bool load_eoi_exitmap_pending;
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 6c56d5235f0f3..3b92f893b2392 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -1514,16 +1514,12 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
  */
 void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 {
-	struct vcpu_vmx *vmx = to_vmx(vcpu);
-
 	if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 
 	vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
 
 	vmx_vcpu_pi_load(vcpu, cpu);
-
-	vmx->host_debugctlmsr = get_debugctlmsr();
 }
 
 void vmx_vcpu_put(struct kvm_vcpu *vcpu)
@@ -7458,8 +7454,8 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
 	}
 
 	/* MSR_IA32_DEBUGCTLMSR is zeroed on vmexit. Restore it if needed */
-	if (vmx->host_debugctlmsr)
-		update_debugctlmsr(vmx->host_debugctlmsr);
+	if (vcpu->arch.host_debugctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
 
 #ifndef CONFIG_X86_64
 	/*
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 8b111ce1087c7..951e44dc9d0ea 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -340,8 +340,6 @@ struct vcpu_vmx {
 	/* apic deadline value in host tsc */
 	u64 hv_deadline_tsc;
 
-	unsigned long host_debugctlmsr;
-
 	/*
 	 * Only bits masked by msr_ia32_feature_control_valid_bits can be set in
 	 * msr_ia32_feature_control. FEAT_CTL_LOCKED is always included
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02159c967d29e..5c6fd0edc41f4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4968,6 +4968,7 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Save host pkru register if supported */
 	vcpu->arch.host_pkru = read_pkru();
+	vcpu->arch.host_debugctl = get_debugctlmsr();
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {

From 433265870ab3455b418885bff48fa5fd02f7e448 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:09 -0800
Subject: [PATCH 1343/2753] KVM: SVM: Manually context switch DEBUGCTL if LBR
 virtualization is disabled

Manually load the guest's DEBUGCTL prior to VMRUN (and restore the host's
value on #VMEXIT) if it diverges from the host's value and LBR
virtualization is disabled, as hardware only context switches DEBUGCTL if
LBR virtualization is fully enabled.  Running the guest with the host's
value has likely been mildly problematic for quite some time, e.g. it will
result in undesirable behavior if BTF diverges (with the caveat that KVM
now suppresses guest BTF due to lack of support).

But the bug became fatal with the introduction of Bus Lock Trap ("Detect"
in kernel paralance) support for AMD (commit 408eb7417a92
("x86/bus_lock: Add support for AMD")), as a bus lock in the guest will
trigger an unexpected #DB.

Note, suppressing the bus lock #DB, i.e. simply resuming the guest without
injecting a #DB, is not an option.  It wouldn't address the general issue
with DEBUGCTL, e.g. for things like BTF, and there are other guest-visible
side effects if BusLockTrap is left enabled.

If BusLockTrap is disabled, then DR6.BLD is reserved-to-1; any attempts to
clear it by software are ignored.  But if BusLockTrap is enabled, software
can clear DR6.BLD:

  Software enables bus lock trap by setting DebugCtl MSR[BLCKDB] (bit 2)
  to 1.  When bus lock trap is enabled, ... The processor indicates that
  this #DB was caused by a bus lock by clearing DR6[BLD] (bit 11).  DR6[11]
  previously had been defined to be always 1.

and clearing DR6.BLD is "sticky" in that it's not set (i.e. lowered) by
other #DBs:

  All other #DB exceptions leave DR6[BLD] unmodified

E.g. leaving BusLockTrap enable can confuse a legacy guest that writes '0'
to reset DR6.

Reported-by: rangemachine@gmail.com
Reported-by: whanos@sergal.fun
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219787
Closes: https://lore.kernel.org/all/bug-219787-28872@https.bugzilla.kernel.org%2F
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/svm.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index ed48465186961..e67de787fc714 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -4288,6 +4288,16 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	clgi();
 	kvm_load_guest_xsave_state(vcpu);
 
+	/*
+	 * Hardware only context switches DEBUGCTL if LBR virtualization is
+	 * enabled.  Manually load DEBUGCTL if necessary (and restore it after
+	 * VM-Exit), as running with the host's DEBUGCTL can negatively affect
+	 * guest state and can even be fatal, e.g. due to Bus Lock Detect.
+	 */
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(svm->vmcb->save.dbgctl);
+
 	kvm_wait_lapic_expire(vcpu);
 
 	/*
@@ -4315,6 +4325,10 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
 	if (unlikely(svm->vmcb->control.exit_code == SVM_EXIT_NMI))
 		kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
 
+	if (!(svm->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK) &&
+	    vcpu->arch.host_debugctl != svm->vmcb->save.dbgctl)
+		update_debugctlmsr(vcpu->arch.host_debugctl);
+
 	kvm_load_host_xsave_state(vcpu);
 	stgi();
 

From 189ecdb3e112da703ac0699f4ec76aa78122f911 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 27 Feb 2025 14:24:10 -0800
Subject: [PATCH 1344/2753] KVM: x86: Snapshot the host's DEBUGCTL after
 disabling IRQs

Snapshot the host's DEBUGCTL after disabling IRQs, as perf can toggle
debugctl bits from IRQ context, e.g. when enabling/disabling events via
smp_call_function_single().  Taking the snapshot (long) before IRQs are
disabled could result in KVM effectively clobbering DEBUGCTL due to using
a stale snapshot.

Cc: stable@vger.kernel.org
Reviewed-and-tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20250227222411.3490595-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 5c6fd0edc41f4..12d5f47c1bbe9 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4968,7 +4968,6 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Save host pkru register if supported */
 	vcpu->arch.host_pkru = read_pkru();
-	vcpu->arch.host_debugctl = get_debugctlmsr();
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
@@ -10969,6 +10968,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		set_debugreg(0, 7);
 	}
 
+	vcpu->arch.host_debugctl = get_debugctlmsr();
+
 	guest_timing_enter_irqoff();
 
 	for (;;) {

From dea5c8ec20be7603e4a56b9d6571321f330626c1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:23 +0000
Subject: [PATCH 1345/2753] net: stmmac: provide set_clk_tx_rate() hook

Several stmmac sub-drivers which support RGMII follow the same pattern.
They calculate the transmit clock rate, and then call clk_set_rate().

Analysis of several implementation documents suggests that the platform
is responsible for providing the transmit clock to the DWMAC core's
clk_tx_i. The expected rates are:

	10Mbps	100Mbps	1Gbps
MII	2.5MHz	25MHz
RMII	2.5MHz	25MHz
GMII			125MHz
RGMI	2.5MHz	25MHz	125MHz

It seems some platforms require this clock to be manually configured,
but there are outputs from the MAC core that indicate the speed, so a
platform may use these to automatically configure the clock. Thus, we
can't just provide one solution to configure this clock rate.

Moreover, the clock may need to be derived from one of several sources
depending on the interface mode.

Provide a platform hook that is passed the transmit clock, interface
mode and speed.

Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0F-0052sS-Lr@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 +++++++++++
 include/linux/stmmac.h                            |  4 ++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 424fa2fe31c6c..e66cd68897287 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -928,6 +928,7 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	struct stmmac_priv *priv = netdev_priv(to_net_dev(config->dev));
 	unsigned int flow_ctrl;
 	u32 old_ctrl, ctrl;
+	int ret;
 
 	if ((priv->plat->flags & STMMAC_FLAG_SERDES_UP_AFTER_PHY_LINKUP) &&
 	    priv->plat->serdes_powerup)
@@ -1020,6 +1021,16 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 	if (ctrl != old_ctrl)
 		writel(ctrl, priv->ioaddr + MAC_CTRL_REG);
 
+	if (priv->plat->set_clk_tx_rate) {
+		ret = priv->plat->set_clk_tx_rate(priv->plat->bsp_priv,
+						priv->plat->clk_tx_i,
+						interface, speed);
+		if (ret < 0)
+			netdev_err(priv->dev,
+				   "failed to configure transmit clock for %dMbps: %pe\n",
+				   speed, ERR_PTR(ret));
+	}
+
 	stmmac_mac_set(priv, priv->ioaddr, true);
 	if (priv->dma_cap.eee)
 		stmmac_set_eee_pls(priv, priv->hw, true);
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index 6d2aa77ea9635..cd0d1383df872 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -78,6 +78,7 @@
 			| DMA_AXI_BLEN_32 | DMA_AXI_BLEN_64 \
 			| DMA_AXI_BLEN_128 | DMA_AXI_BLEN_256)
 
+struct clk;
 struct stmmac_priv;
 
 /* Platfrom data for platform device structure's platform_data field */
@@ -231,6 +232,8 @@ struct plat_stmmacenet_data {
 	u8 tx_sched_algorithm;
 	struct stmmac_rxq_cfg rx_queues_cfg[MTL_MAX_RX_QUEUES];
 	struct stmmac_txq_cfg tx_queues_cfg[MTL_MAX_TX_QUEUES];
+	int (*set_clk_tx_rate)(void *priv, struct clk *clk_tx_i,
+			       phy_interface_t interface, int speed);
 	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 	int (*fix_soc_reset)(void *priv, void __iomem *ioaddr);
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
@@ -252,6 +255,7 @@ struct plat_stmmacenet_data {
 	struct clk *stmmac_clk;
 	struct clk *pclk;
 	struct clk *clk_ptp_ref;
+	struct clk *clk_tx_i;		/* clk_tx_i to MAC core */
 	unsigned long clk_ptp_rate;
 	unsigned long clk_ref_rate;
 	struct clk_bulk_data *clks;

From 12bce6d5404ea30180536322c1ad31bc45a988d2 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:28 +0000
Subject: [PATCH 1346/2753] net: stmmac: provide generic implementation for
 set_clk_tx_rate method

Provide a generic implementation for the set_clk_tx_rate method
introduced by the previous patch, which is capable of configuring the
MAC transmit clock for 10M, 100M and 1000M speeds for at least MII,
GMII, RGMII and RMII interface modes.

Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0K-0052sY-QF@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h  |  2 ++
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 32 +++++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index b321872846079..3a00a988cb36f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -407,6 +407,8 @@ int stmmac_dvr_probe(struct device *device,
 int stmmac_reinit_queues(struct net_device *dev, u32 rx_cnt, u32 tx_cnt);
 int stmmac_reinit_ringparam(struct net_device *dev, u32 rx_size, u32 tx_size);
 int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled);
+int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+			   phy_interface_t interface, int speed);
 
 static inline bool stmmac_xdp_is_enabled(struct stmmac_priv *priv)
 {
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index e66cd68897287..aec230353ac48 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -177,6 +177,38 @@ int stmmac_bus_clks_config(struct stmmac_priv *priv, bool enabled)
 }
 EXPORT_SYMBOL_GPL(stmmac_bus_clks_config);
 
+/**
+ * stmmac_set_clk_tx_rate() - set the clock rate for the MAC transmit clock
+ * @bsp_priv: BSP private data structure (unused)
+ * @clk_tx_i: the transmit clock
+ * @interface: the selected interface mode
+ * @speed: the speed that the MAC will be operating at
+ *
+ * Set the transmit clock rate for the MAC, normally 2.5MHz for 10Mbps,
+ * 25MHz for 100Mbps and 125MHz for 1Gbps. This is suitable for at least
+ * MII, GMII, RGMII and RMII interface modes. Platforms can hook this into
+ * the plat_data->set_clk_tx_rate method directly, call it via their own
+ * implementation, or implement their own method should they have more
+ * complex requirements. It is intended to only be used in this method.
+ *
+ * plat_data->clk_tx_i must be filled in.
+ */
+int stmmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+			   phy_interface_t interface, int speed)
+{
+	long rate = rgmii_clock(speed);
+
+	/* Silently ignore unsupported speeds as rgmii_clock() only
+	 * supports 10, 100 and 1000Mbps. We do not want to spit
+	 * errors for 2500 and higher speeds here.
+	 */
+	if (rate < 0)
+		return 0;
+
+	return clk_set_rate(clk_tx_i, rate);
+}
+EXPORT_SYMBOL_GPL(stmmac_set_clk_tx_rate);
+
 /**
  * stmmac_verify_args - verify the driver parameters.
  * Description: it checks the driver parameters and set a default in case of

From 17c24f6dc641a28eead628008587c1730b449b9a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:33 +0000
Subject: [PATCH 1347/2753] net: stmmac: dwc-qos: use generic
 stmmac_set_clk_tx_rate()

Use the generic stmmac_set_clk_tx_rate() to configure the MAC transmit
clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0P-0052se-Tv@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c    | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 6cadf24a575c5..3f0f4ea6cf2e4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -30,7 +30,6 @@ struct tegra_eqos {
 
 	struct reset_control *rst;
 	struct clk *clk_slave;
-	struct clk *clk_tx;
 
 	struct gpio_desc *reset;
 };
@@ -150,7 +149,6 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct tegra_eqos *eqos = priv;
 	bool needs_calibration = false;
-	long rate = 125000000;
 	u32 value;
 	int err;
 
@@ -161,7 +159,6 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 		fallthrough;
 
 	case SPEED_10:
-		rate = rgmii_clock(speed);
 		break;
 
 	default:
@@ -208,10 +205,6 @@ static void tegra_eqos_fix_speed(void *priv, int speed, unsigned int mode)
 		value &= ~AUTO_CAL_CONFIG_ENABLE;
 		writel(value, eqos->regs + AUTO_CAL_CONFIG);
 	}
-
-	err = clk_set_rate(eqos->clk_tx, rate);
-	if (err < 0)
-		dev_err(eqos->dev, "failed to set TX rate: %d\n", err);
 }
 
 static int tegra_eqos_init(struct platform_device *pdev, void *priv)
@@ -247,7 +240,7 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 	if (!is_of_node(dev->fwnode))
 		goto bypass_clk_reset_gpio;
 
-	eqos->clk_tx = dwc_eth_find_clk(plat_dat, "tx");
+	plat_dat->clk_tx_i = dwc_eth_find_clk(plat_dat, "tx");
 
 	eqos->reset = devm_gpiod_get(&pdev->dev, "phy-reset", GPIOD_OUT_HIGH);
 	if (IS_ERR(eqos->reset)) {
@@ -281,6 +274,7 @@ static int tegra_eqos_probe(struct platform_device *pdev,
 
 bypass_clk_reset_gpio:
 	plat_dat->fix_mac_speed = tegra_eqos_fix_speed;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 	plat_dat->init = tegra_eqos_init;
 	plat_dat->bsp_priv = eqos;
 	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE;

From c81eb3da0be8a3a7784a1e55924ca3aaaa533955 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:39 +0000
Subject: [PATCH 1348/2753] net: stmmac: starfive: use generic
 stmmac_set_clk_tx_rate()

Use the generic stmmac_set_clk_tx_rate() to configure the MAC transmit
clock.

Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0V-0052sk-1L@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/dwmac-starfive.c  | 26 +++----------------
 1 file changed, 4 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 282c846dad0b2..5e31cb3bb4b83 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -27,27 +27,9 @@ struct starfive_dwmac_data {
 
 struct starfive_dwmac {
 	struct device *dev;
-	struct clk *clk_tx;
 	const struct starfive_dwmac_data *data;
 };
 
-static void starfive_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
-{
-	struct starfive_dwmac *dwmac = priv;
-	long rate;
-	int err;
-
-	rate = rgmii_clock(speed);
-	if (rate < 0) {
-		dev_err(dwmac->dev, "invalid speed %d\n", speed);
-		return;
-	}
-
-	err = clk_set_rate(dwmac->clk_tx, rate);
-	if (err)
-		dev_err(dwmac->dev, "failed to set tx rate %lu\n", rate);
-}
-
 static int starfive_dwmac_set_mode(struct plat_stmmacenet_data *plat_dat)
 {
 	struct starfive_dwmac *dwmac = plat_dat->bsp_priv;
@@ -122,9 +104,9 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 
 	dwmac->data = device_get_match_data(&pdev->dev);
 
-	dwmac->clk_tx = devm_clk_get_enabled(&pdev->dev, "tx");
-	if (IS_ERR(dwmac->clk_tx))
-		return dev_err_probe(&pdev->dev, PTR_ERR(dwmac->clk_tx),
+	plat_dat->clk_tx_i = devm_clk_get_enabled(&pdev->dev, "tx");
+	if (IS_ERR(plat_dat->clk_tx_i))
+		return dev_err_probe(&pdev->dev, PTR_ERR(plat_dat->clk_tx_i),
 				     "error getting tx clock\n");
 
 	clk_gtx = devm_clk_get_enabled(&pdev->dev, "gtx");
@@ -139,7 +121,7 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 	 * internally, because rgmii_rxin will be adaptively adjusted.
 	 */
 	if (!device_property_read_bool(&pdev->dev, "starfive,tx-use-rgmii-clk"))
-		plat_dat->fix_mac_speed = starfive_dwmac_fix_mac_speed;
+		plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 
 	dwmac->dev = &pdev->dev;
 	plat_dat->bsp_priv = dwmac;

From 36fa8c960720b55b5821ebea0f499ba8a8402c0a Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:44 +0000
Subject: [PATCH 1349/2753] net: stmmac: s32: use generic
 stmmac_set_clk_tx_rate()

Use the generic stmmac_set_clk_tx_rate() to configure the MAC transmit
clock.

Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0a-0052sq-59@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-s32.c   | 22 +++----------------
 1 file changed, 3 insertions(+), 19 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
index 6a498833b8ed0..221539d760bc8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-s32.c
@@ -100,24 +100,6 @@ static void s32_gmac_exit(struct platform_device *pdev, void *priv)
 	clk_disable_unprepare(gmac->rx_clk);
 }
 
-static void s32_fix_mac_speed(void *priv, int speed, unsigned int mode)
-{
-	struct s32_priv_data *gmac = priv;
-	long tx_clk_rate;
-	int ret;
-
-	tx_clk_rate = rgmii_clock(speed);
-	if (tx_clk_rate < 0) {
-		dev_err(gmac->dev, "Unsupported/Invalid speed: %d\n", speed);
-		return;
-	}
-
-	dev_dbg(gmac->dev, "Set tx clock to %ld Hz\n", tx_clk_rate);
-	ret = clk_set_rate(gmac->tx_clk, tx_clk_rate);
-	if (ret)
-		dev_err(gmac->dev, "Can't set tx clock\n");
-}
-
 static int s32_dwmac_probe(struct platform_device *pdev)
 {
 	struct plat_stmmacenet_data *plat;
@@ -172,7 +154,9 @@ static int s32_dwmac_probe(struct platform_device *pdev)
 
 	plat->init = s32_gmac_init;
 	plat->exit = s32_gmac_exit;
-	plat->fix_mac_speed = s32_fix_mac_speed;
+
+	plat->clk_tx_i = gmac->tx_clk;
+	plat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 
 	plat->bsp_priv = gmac;
 

From 61356fb1b0d64105475254c2fa74ad63b90b3248 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:49 +0000
Subject: [PATCH 1350/2753] net: stmmac: intel: use generic
 stmmac_set_clk_tx_rate()

Use the generic stmmac_set_clk_tx_rate() to configure the MAC transmit
clock.

Note that given the current unpatched driver structure,
plat_dat->fix_mac_speed will always be populated with
kmb_eth_fix_mac_speed(), even when no clock is present. We preserve
this behaviour in this patch by always initialising plat_dat->clk_tx_i
and plat_dat->set_clk_tx_rate.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0f-0052sw-8r@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../stmicro/stmmac/dwmac-intel-plat.c         | 24 +++----------------
 1 file changed, 3 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
index 0591756a2100e..599def7b3a649 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel-plat.c
@@ -22,31 +22,12 @@ struct intel_dwmac {
 };
 
 struct intel_dwmac_data {
-	void (*fix_mac_speed)(void *priv, int speed, unsigned int mode);
 	unsigned long ptp_ref_clk_rate;
 	unsigned long tx_clk_rate;
 	bool tx_clk_en;
 };
 
-static void kmb_eth_fix_mac_speed(void *priv, int speed, unsigned int mode)
-{
-	struct intel_dwmac *dwmac = priv;
-	long rate;
-	int ret;
-
-	rate = rgmii_clock(speed);
-	if (rate < 0) {
-		dev_err(dwmac->dev, "Invalid speed\n");
-		return;
-	}
-
-	ret = clk_set_rate(dwmac->tx_clk, rate);
-	if (ret)
-		dev_err(dwmac->dev, "Failed to configure tx clock rate\n");
-}
-
 static const struct intel_dwmac_data kmb_data = {
-	.fix_mac_speed = kmb_eth_fix_mac_speed,
 	.ptp_ref_clk_rate = 200000000,
 	.tx_clk_rate = 125000000,
 	.tx_clk_en = true,
@@ -89,8 +70,6 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 	 * platform_match().
 	 */
 	dwmac->data = device_get_match_data(&pdev->dev);
-	if (dwmac->data->fix_mac_speed)
-		plat_dat->fix_mac_speed = dwmac->data->fix_mac_speed;
 
 	/* Enable TX clock */
 	if (dwmac->data->tx_clk_en) {
@@ -132,6 +111,9 @@ static int intel_eth_plat_probe(struct platform_device *pdev)
 		}
 	}
 
+	plat_dat->clk_tx_i = dwmac->tx_clk;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->eee_usecs_rate = plat_dat->clk_ptp_rate;
 

From b693ce4f2704977b3e473d9ca454808c04667d70 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:54 +0000
Subject: [PATCH 1351/2753] net: stmmac: imx: use generic
 stmmac_set_clk_tx_rate()

Convert non-i.MX93 users to use the generic stmmac_set_clk_tx_rate() to
configure the MAC transmit clock rate.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0k-0052t2-Cc@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-imx.c   | 21 +++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
index 610204b51e3fe..5d279fa54b3e8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c
@@ -192,6 +192,19 @@ static void imx_dwmac_exit(struct platform_device *pdev, void *priv)
 	/* nothing to do now */
 }
 
+static int imx_dwmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				     phy_interface_t interface, int speed)
+{
+	struct imx_priv_data *dwmac = bsp_priv;
+
+	interface = dwmac->plat_dat->mac_interface;
+	if (interface == PHY_INTERFACE_MODE_RMII ||
+	    interface == PHY_INTERFACE_MODE_MII)
+		return 0;
+
+	return stmmac_set_clk_tx_rate(bsp_priv, clk_tx_i, interface, speed);
+}
+
 static void imx_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 {
 	struct plat_stmmacenet_data *plat_dat;
@@ -358,7 +371,6 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;
 	plat_dat->clks_config = imx_dwmac_clks_config;
-	plat_dat->fix_mac_speed = imx_dwmac_fix_speed;
 	plat_dat->bsp_priv = dwmac;
 	dwmac->plat_dat = plat_dat;
 	dwmac->base_addr = stmmac_res.addr;
@@ -371,8 +383,13 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		goto err_dwmac_init;
 
-	if (dwmac->ops->fix_mac_speed)
+	if (dwmac->ops->fix_mac_speed) {
 		plat_dat->fix_mac_speed = dwmac->ops->fix_mac_speed;
+	} else if (!dwmac->ops->mac_rgmii_txclk_auto_adj) {
+		plat_dat->clk_tx_i = dwmac->clk_tx;
+		plat_dat->set_clk_tx_rate = imx_dwmac_set_clk_tx_rate;
+	}
+
 	dwmac->plat_dat->fix_soc_reset = dwmac->ops->fix_soc_reset;
 
 	ret = stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);

From c8caf6100f6d68ad4323eb8d41358688e5cfdf13 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:16:59 +0000
Subject: [PATCH 1352/2753] net: stmmac: rk: switch to use set_clk_tx_rate()
 hook

Switch from using the fix_mac_speed() hook to set_clk_tx_rate() to
manage the transmit clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0p-0052t8-Gn@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 83d104a274c50..003fa5cf42c33 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1920,9 +1920,10 @@ static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 	gmac_clk_enable(gmac, false);
 }
 
-static void rk_fix_speed(void *priv, int speed, unsigned int mode)
+static int rk_set_clk_tx_rate(void *bsp_priv_, struct clk *clk_tx_i,
+			      phy_interface_t interface, int speed)
 {
-	struct rk_priv_data *bsp_priv = priv;
+	struct rk_priv_data *bsp_priv = bsp_priv_;
 	struct device *dev = &bsp_priv->pdev->dev;
 
 	switch (bsp_priv->phy_iface) {
@@ -1940,6 +1941,8 @@ static void rk_fix_speed(void *priv, int speed, unsigned int mode)
 	default:
 		dev_err(dev, "unsupported interface %d", bsp_priv->phy_iface);
 	}
+
+	return 0;
 }
 
 static int rk_gmac_probe(struct platform_device *pdev)
@@ -1968,7 +1971,8 @@ static int rk_gmac_probe(struct platform_device *pdev)
 	 */
 	if (!plat_dat->has_gmac4)
 		plat_dat->has_gmac = true;
-	plat_dat->fix_mac_speed = rk_fix_speed;
+
+	plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate;
 
 	plat_dat->bsp_priv = rk_gmac_setup(pdev, plat_dat, data);
 	if (IS_ERR(plat_dat->bsp_priv))

From ca723519c28ba60f9f851a04dbe7dd407177cbbc Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:17:04 +0000
Subject: [PATCH 1353/2753] net: stmmac: ipq806x: switch to use
 set_clk_tx_rate() hook

Switch from using the fix_mac_speed() hook to set_clk_tx_rate() to
manage the transmit clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0u-0052tH-KQ@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 7f4b9c1cc32b7..0a9c137cc4e63 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -260,11 +260,12 @@ static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
 	return PTR_ERR_OR_ZERO(gmac->qsgmii_csr);
 }
 
-static void ipq806x_gmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
+static int ipq806x_gmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct ipq806x_gmac *gmac = priv;
+	struct ipq806x_gmac *gmac = bsp_priv;
 
-	ipq806x_gmac_set_speed(gmac, speed);
+	return ipq806x_gmac_set_speed(gmac, speed);
 }
 
 static int
@@ -478,7 +479,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	plat_dat->has_gmac = true;
 	plat_dat->bsp_priv = gmac;
-	plat_dat->fix_mac_speed = ipq806x_gmac_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = ipq806x_gmac_set_clk_tx_rate;
 	plat_dat->multicast_filter_bins = 0;
 	plat_dat->tx_fifo_size = 8192;
 	plat_dat->rx_fifo_size = 8192;

From 2a7d55f901a5753d779ad02cd3600024fb576a53 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:17:09 +0000
Subject: [PATCH 1354/2753] net: stmmac: meson: switch to use set_clk_tx_rate()
 hook

Switch from using the fix_mac_speed() hook to set_clk_tx_rate() to
manage the transmit clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna0z-0052tN-O1@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
index b115b7873cefa..07c504d07604c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c
@@ -22,9 +22,10 @@ struct meson_dwmac {
 	void __iomem	*reg;
 };
 
-static void meson6_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
+static int meson6_dwmac_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+					phy_interface_t interface, int speed)
 {
-	struct meson_dwmac *dwmac = priv;
+	struct meson_dwmac *dwmac = bsp_priv;
 	unsigned int val;
 
 	val = readl(dwmac->reg);
@@ -39,6 +40,8 @@ static void meson6_dwmac_fix_mac_speed(void *priv, int speed, unsigned int mode)
 	}
 
 	writel(val, dwmac->reg);
+
+	return 0;
 }
 
 static int meson6_dwmac_probe(struct platform_device *pdev)
@@ -65,7 +68,7 @@ static int meson6_dwmac_probe(struct platform_device *pdev)
 		return PTR_ERR(dwmac->reg);
 
 	plat_dat->bsp_priv = dwmac;
-	plat_dat->fix_mac_speed = meson6_dwmac_fix_mac_speed;
+	plat_dat->set_clk_tx_rate = meson6_dwmac_set_clk_tx_rate;
 
 	return stmmac_dvr_probe(&pdev->dev, plat_dat, &stmmac_res);
 }

From 945db208fbe7fc7687157d0738cdfa832ebab186 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 27 Feb 2025 09:17:14 +0000
Subject: [PATCH 1355/2753] net: stmmac: thead: switch to use set_clk_tx_rate()
 hook

Switch from using the fix_mac_speed() hook to set_clk_tx_rate() to
manage the transmit clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tna14-0052tT-S4@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-thead.c  | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
index f9f2bd65959fa..c72ee759aae58 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-thead.c
@@ -101,10 +101,11 @@ static int thead_dwmac_set_txclk_dir(struct plat_stmmacenet_data *plat)
 	return 0;
 }
 
-static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
+static int thead_set_clk_tx_rate(void *bsp_priv, struct clk *clk_tx_i,
+				 phy_interface_t interface, int speed)
 {
+	struct thead_dwmac *dwmac = bsp_priv;
 	struct plat_stmmacenet_data *plat;
-	struct thead_dwmac *dwmac = priv;
 	unsigned long rate;
 	long tx_rate;
 	u32 div, reg;
@@ -114,7 +115,7 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 	switch (plat->mac_interface) {
 	/* For MII, rxc/txc is provided by phy */
 	case PHY_INTERFACE_MODE_MII:
-		return;
+		return 0;
 
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -127,23 +128,24 @@ static void thead_dwmac_fix_speed(void *priv, int speed, unsigned int mode)
 		tx_rate = rgmii_clock(speed);
 		if (tx_rate < 0) {
 			dev_err(dwmac->dev, "invalid speed %d\n", speed);
-			return;
+			return tx_rate;
 		}
 
 		div = rate / tx_rate;
 		if (rate != tx_rate * div) {
 			dev_err(dwmac->dev, "invalid gmac rate %lu\n", rate);
-			return;
+			return -EINVAL;
 		}
 
 		reg = FIELD_PREP(GMAC_PLLCLK_DIV_EN, 1) |
 		      FIELD_PREP(GMAC_PLLCLK_DIV_NUM, div);
 		writel(reg, dwmac->apb_base + GMAC_PLLCLK_DIV);
-		break;
+		return 0;
+
 	default:
 		dev_err(dwmac->dev, "unsupported phy interface %d\n",
 			plat->mac_interface);
-		return;
+		return -EINVAL;
 	}
 }
 
@@ -235,7 +237,7 @@ static int thead_dwmac_probe(struct platform_device *pdev)
 	dwmac->plat = plat;
 	dwmac->apb_base = apb;
 	plat->bsp_priv = dwmac;
-	plat->fix_mac_speed = thead_dwmac_fix_speed;
+	plat->set_clk_tx_rate = thead_set_clk_tx_rate;
 	plat->init = thead_dwmac_init;
 
 	return devm_stmmac_pltfr_probe(pdev, plat, &stmmac_res);

From ab8a17bc63e2d187ea4602e1d1b9baf10c7b252d Mon Sep 17 00:00:00 2001
From: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Date: Mon, 10 Feb 2025 10:27:14 -0800
Subject: [PATCH 1356/2753] wifi: ath11k: refactor transmitted arvif retrieval

Create a new function ath11k_mac_get_tx_arvif() to retrieve 'arvif'
for the transmitted interface of the MBSSID set. This will help
modifying the same code path to reflect mac80211 data structure
changes to support MLO. This also fixes an issue in
ath11k_mac_update_vif_chan() where tx_arvif is not reset to NULL
inside for loop during each iteration. Compile tested only.

Signed-off-by: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210182718.408891-2-aloka.dixit@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 53 +++++++++++++--------------
 1 file changed, 26 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 14ed538365899..466a314b938b6 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -1529,6 +1529,14 @@ static int ath11k_mac_set_vif_params(struct ath11k_vif *arvif,
 	return ret;
 }
 
+static struct ath11k_vif *ath11k_mac_get_tx_arvif(struct ath11k_vif *arvif)
+{
+	if (arvif->vif->mbssid_tx_vif)
+		return ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
+
+	return NULL;
+}
+
 static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif)
 {
 	struct ath11k_vif *tx_arvif;
@@ -1538,7 +1546,7 @@ static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif)
 	u32 params = 0;
 	u8 i = 0;
 
-	tx_arvif = ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
+	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
 
 	beacons = ieee80211_beacon_get_template_ema_list(tx_arvif->ar->hw,
 							 tx_arvif->vif, 0);
@@ -1589,21 +1597,21 @@ static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif)
 {
 	struct ath11k *ar = arvif->ar;
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *tx_arvif = arvif;
+	struct ath11k_vif *tx_arvif;
 	struct ieee80211_hw *hw = ar->hw;
 	struct ieee80211_vif *vif = arvif->vif;
 	struct ieee80211_mutable_offsets offs = {};
 	struct sk_buff *bcn;
 	int ret;
 
-	if (vif->mbssid_tx_vif) {
-		tx_arvif = ath11k_vif_to_arvif(vif->mbssid_tx_vif);
-		if (tx_arvif != arvif) {
-			ar = tx_arvif->ar;
-			ab = ar->ab;
-			hw = ar->hw;
-			vif = tx_arvif->vif;
-		}
+	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
+	if (tx_arvif && tx_arvif != arvif) {
+		ar = tx_arvif->ar;
+		ab = ar->ab;
+		hw = ar->hw;
+		vif = tx_arvif->vif;
+	} else {
+		tx_arvif = arvif;
 	}
 
 	bcn = ieee80211_beacon_get_template(hw, vif, &offs, 0);
@@ -1674,7 +1682,7 @@ static void ath11k_control_beaconing(struct ath11k_vif *arvif,
 				     struct ieee80211_bss_conf *info)
 {
 	struct ath11k *ar = arvif->ar;
-	struct ath11k_vif *tx_arvif = NULL;
+	struct ath11k_vif *tx_arvif;
 	int ret = 0;
 
 	lockdep_assert_held(&arvif->ar->conf_mutex);
@@ -1701,9 +1709,7 @@ static void ath11k_control_beaconing(struct ath11k_vif *arvif,
 
 	ether_addr_copy(arvif->bssid, info->bssid);
 
-	if (arvif->vif->mbssid_tx_vif)
-		tx_arvif = ath11k_vif_to_arvif(arvif->vif->mbssid_tx_vif);
-
+	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
 	ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 				 arvif->bssid,
 				 tx_arvif ? tx_arvif->bssid : NULL,
@@ -6385,23 +6391,20 @@ static int ath11k_mac_setup_vdev_params_mbssid(struct ath11k_vif *arvif,
 {
 	struct ath11k *ar = arvif->ar;
 	struct ath11k_vif *tx_arvif;
-	struct ieee80211_vif *tx_vif;
 
 	*tx_vdev_id = 0;
-	tx_vif = arvif->vif->mbssid_tx_vif;
-	if (!tx_vif) {
+	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
+	if (!tx_arvif) {
 		*flags = WMI_HOST_VDEV_FLAGS_NON_MBSSID_AP;
 		return 0;
 	}
 
-	tx_arvif = ath11k_vif_to_arvif(tx_vif);
-
 	if (arvif->vif->bss_conf.nontransmitted) {
-		if (ar->hw->wiphy != ieee80211_vif_to_wdev(tx_vif)->wiphy)
+		if (ar->hw->wiphy != tx_arvif->ar->hw->wiphy)
 			return -EINVAL;
 
 		*flags = WMI_HOST_VDEV_FLAGS_NON_TRANSMIT_AP;
-		*tx_vdev_id = ath11k_vif_to_arvif(tx_vif)->vdev_id;
+		*tx_vdev_id = tx_arvif->vdev_id;
 	} else if (tx_arvif == arvif) {
 		*flags = WMI_HOST_VDEV_FLAGS_TRANSMIT_AP;
 	} else {
@@ -7361,8 +7364,7 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 			   int n_vifs)
 {
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *arvif, *tx_arvif = NULL;
-	struct ieee80211_vif *mbssid_tx_vif;
+	struct ath11k_vif *arvif, *tx_arvif;
 	int ret;
 	int i;
 	bool monitor_vif = false;
@@ -7416,10 +7418,7 @@ ath11k_mac_update_vif_chan(struct ath11k *ar,
 			ath11k_warn(ab, "failed to update bcn tmpl during csa: %d\n",
 				    ret);
 
-		mbssid_tx_vif = arvif->vif->mbssid_tx_vif;
-		if (mbssid_tx_vif)
-			tx_arvif = ath11k_vif_to_arvif(mbssid_tx_vif);
-
+		tx_arvif = ath11k_mac_get_tx_arvif(arvif);
 		ret = ath11k_wmi_vdev_up(arvif->ar, arvif->vdev_id, arvif->aid,
 					 arvif->bssid,
 					 tx_arvif ? tx_arvif->bssid : NULL,

From 8e30bfad4dc96c27f52b84b3fc5928252dafee5d Mon Sep 17 00:00:00 2001
From: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Date: Mon, 10 Feb 2025 10:27:15 -0800
Subject: [PATCH 1357/2753] wifi: ath11k: pass tx arvif for MBSSID and EMA
 beacon generation

Function ath11k_mac_setup_bcn_tmpl() retrieves tx_arvif only for
a sanity check and then calls ath11k_mac_setup_bcn_tmpl_mbssid()
or ath11k_mac_setup_bcn_tmpl_ema() both of which again retrieve
the same pointer. Instead store the pointer and pass it to the
latter two functions. Compile tested only.

Signed-off-by: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210182718.408891-3-aloka.dixit@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/mac.c | 32 +++++++++++++--------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
index 466a314b938b6..97816916abac9 100644
--- a/drivers/net/wireless/ath/ath11k/mac.c
+++ b/drivers/net/wireless/ath/ath11k/mac.c
@@ -1537,17 +1537,15 @@ static struct ath11k_vif *ath11k_mac_get_tx_arvif(struct ath11k_vif *arvif)
 	return NULL;
 }
 
-static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif)
+static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif,
+					 struct ath11k_vif *tx_arvif)
 {
-	struct ath11k_vif *tx_arvif;
 	struct ieee80211_ema_beacons *beacons;
 	int ret = 0;
 	bool nontx_vif_params_set = false;
 	u32 params = 0;
 	u8 i = 0;
 
-	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
-
 	beacons = ieee80211_beacon_get_template_ema_list(tx_arvif->ar->hw,
 							 tx_arvif->vif, 0);
 	if (!beacons || !beacons->cnt) {
@@ -1593,25 +1591,22 @@ static int ath11k_mac_setup_bcn_tmpl_ema(struct ath11k_vif *arvif)
 	return ret;
 }
 
-static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif)
+static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif,
+					    struct ath11k_vif *tx_arvif)
 {
 	struct ath11k *ar = arvif->ar;
 	struct ath11k_base *ab = ar->ab;
-	struct ath11k_vif *tx_arvif;
 	struct ieee80211_hw *hw = ar->hw;
 	struct ieee80211_vif *vif = arvif->vif;
 	struct ieee80211_mutable_offsets offs = {};
 	struct sk_buff *bcn;
 	int ret;
 
-	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
-	if (tx_arvif && tx_arvif != arvif) {
+	if (tx_arvif != arvif) {
 		ar = tx_arvif->ar;
 		ab = ar->ab;
 		hw = ar->hw;
 		vif = tx_arvif->vif;
-	} else {
-		tx_arvif = arvif;
 	}
 
 	bcn = ieee80211_beacon_get_template(hw, vif, &offs, 0);
@@ -1640,6 +1635,7 @@ static int ath11k_mac_setup_bcn_tmpl_mbssid(struct ath11k_vif *arvif)
 static int ath11k_mac_setup_bcn_tmpl(struct ath11k_vif *arvif)
 {
 	struct ieee80211_vif *vif = arvif->vif;
+	struct ath11k_vif *tx_arvif;
 
 	if (arvif->vdev_type != WMI_VDEV_TYPE_AP)
 		return 0;
@@ -1647,14 +1643,18 @@ static int ath11k_mac_setup_bcn_tmpl(struct ath11k_vif *arvif)
 	/* Target does not expect beacon templates for the already up
 	 * non-transmitting interfaces, and results in a crash if sent.
 	 */
-	if (vif->mbssid_tx_vif &&
-	    arvif != ath11k_vif_to_arvif(vif->mbssid_tx_vif) && arvif->is_up)
-		return 0;
+	tx_arvif = ath11k_mac_get_tx_arvif(arvif);
+	if (tx_arvif) {
+		if (arvif != tx_arvif && arvif->is_up)
+			return 0;
 
-	if (vif->bss_conf.ema_ap && vif->mbssid_tx_vif)
-		return ath11k_mac_setup_bcn_tmpl_ema(arvif);
+		if (vif->bss_conf.ema_ap)
+			return ath11k_mac_setup_bcn_tmpl_ema(arvif, tx_arvif);
+	} else {
+		tx_arvif = arvif;
+	}
 
-	return ath11k_mac_setup_bcn_tmpl_mbssid(arvif);
+	return ath11k_mac_setup_bcn_tmpl_mbssid(arvif, tx_arvif);
 }
 
 void ath11k_mac_bcn_tx_event(struct ath11k_vif *arvif)

From 20fe6390b503f0c8fa15a73720fdceb2c3745c87 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Date: Mon, 10 Feb 2025 10:27:16 -0800
Subject: [PATCH 1358/2753] wifi: ath12k: refactor transmitted arvif retrieval

Create a new function ath12k_mac_get_tx_arvif() to retrieve 'arvif'
for the transmitted interface of the MBSSID set. This clean up will
help modifying the same code path for MLO changes.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210182718.408891-4-aloka.dixit@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 60 +++++++++++++++------------
 1 file changed, 33 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 3e3afdc56fc96..2de9a9b003a62 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -580,6 +580,19 @@ static int ath12k_mac_vif_link_chan(struct ieee80211_vif *vif, u8 link_id,
 	return 0;
 }
 
+static struct ath12k_link_vif *ath12k_mac_get_tx_arvif(struct ath12k_link_vif *arvif)
+{
+	struct ath12k_vif *tx_ahvif;
+
+	if (arvif->ahvif->vif->mbssid_tx_vif) {
+		tx_ahvif = ath12k_vif_to_ahvif(arvif->ahvif->vif->mbssid_tx_vif);
+		if (tx_ahvif)
+			return &tx_ahvif->deflink;
+	}
+
+	return NULL;
+}
+
 struct ieee80211_bss_conf *
 ath12k_mac_get_link_bss_conf(struct ath12k_link_vif *arvif)
 {
@@ -1638,7 +1651,6 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif)
 	struct ieee80211_ema_beacons *beacons;
 	struct ath12k_link_vif *tx_arvif;
 	bool nontx_profile_found = false;
-	struct ath12k_vif *tx_ahvif;
 	int ret = 0;
 	u8 i;
 
@@ -1650,10 +1662,9 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif)
 		return -ENOLINK;
 	}
 
-	tx_ahvif = ath12k_vif_to_ahvif(ahvif->vif->mbssid_tx_vif);
-	tx_arvif = &tx_ahvif->deflink;
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
 	beacons = ieee80211_beacon_get_template_ema_list(ath12k_ar_to_hw(tx_arvif->ar),
-							 tx_ahvif->vif,
+							 tx_arvif->ahvif->vif,
 							 tx_arvif->link_id);
 	if (!beacons || !beacons->cnt) {
 		ath12k_warn(arvif->ar->ab,
@@ -1696,11 +1707,10 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 	struct ath12k_vif *ahvif = arvif->ahvif;
 	struct ieee80211_vif *vif = ath12k_ahvif_to_vif(ahvif);
 	struct ieee80211_bss_conf *link_conf;
-	struct ath12k_link_vif *tx_arvif = arvif;
+	struct ath12k_link_vif *tx_arvif;
 	struct ath12k *ar = arvif->ar;
 	struct ath12k_base *ab = ar->ab;
 	struct ieee80211_mutable_offsets offs = {};
-	struct ath12k_vif *tx_ahvif = ahvif;
 	bool nontx_profile_found = false;
 	struct sk_buff *bcn;
 	int ret;
@@ -1715,17 +1725,19 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 		return -ENOLINK;
 	}
 
-	if (vif->mbssid_tx_vif) {
-		tx_ahvif = ath12k_vif_to_ahvif(vif->mbssid_tx_vif);
-		tx_arvif = &tx_ahvif->deflink;
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	if (tx_arvif) {
 		if (tx_arvif != arvif && arvif->is_up)
 			return 0;
 
 		if (link_conf->ema_ap)
 			return ath12k_mac_setup_bcn_tmpl_ema(arvif);
+	} else {
+		tx_arvif = arvif;
 	}
 
-	bcn = ieee80211_beacon_get_template(ath12k_ar_to_hw(tx_arvif->ar), tx_ahvif->vif,
+	bcn = ieee80211_beacon_get_template(ath12k_ar_to_hw(tx_arvif->ar),
+					    tx_arvif->ahvif->vif,
 					    &offs, tx_arvif->link_id);
 	if (!bcn) {
 		ath12k_warn(ab, "failed to get beacon template from mac80211\n");
@@ -1782,6 +1794,7 @@ static void ath12k_control_beaconing(struct ath12k_link_vif *arvif,
 {
 	struct ath12k_wmi_vdev_up_params params = {};
 	struct ath12k_vif *ahvif = arvif->ahvif;
+	struct ath12k_link_vif *tx_arvif;
 	struct ath12k *ar = arvif->ar;
 	int ret;
 
@@ -1812,11 +1825,9 @@ static void ath12k_control_beaconing(struct ath12k_link_vif *arvif,
 	params.vdev_id = arvif->vdev_id;
 	params.aid = ahvif->aid;
 	params.bssid = arvif->bssid;
-	if (ahvif->vif->mbssid_tx_vif) {
-		struct ath12k_vif *tx_ahvif =
-			ath12k_vif_to_ahvif(ahvif->vif->mbssid_tx_vif);
-		struct ath12k_link_vif *tx_arvif = &tx_ahvif->deflink;
 
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	if (tx_arvif) {
 		params.tx_bssid = tx_arvif->bssid;
 		params.nontx_profile_idx = info->bssid_index;
 		params.nontx_profile_cnt = 1 << info->bssid_indicator;
@@ -7841,14 +7852,9 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif,
 					       u32 *flags, u32 *tx_vdev_id)
 {
 	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ieee80211_vif *tx_vif = ahvif->vif->mbssid_tx_vif;
 	struct ieee80211_bss_conf *link_conf;
 	struct ath12k *ar = arvif->ar;
 	struct ath12k_link_vif *tx_arvif;
-	struct ath12k_vif *tx_ahvif;
-
-	if (!tx_vif)
-		return 0;
 
 	link_conf = ath12k_mac_get_link_bss_conf(arvif);
 	if (!link_conf) {
@@ -7857,11 +7863,13 @@ static int ath12k_mac_setup_vdev_params_mbssid(struct ath12k_link_vif *arvif,
 		return -ENOLINK;
 	}
 
-	tx_ahvif = ath12k_vif_to_ahvif(tx_vif);
-	tx_arvif = &tx_ahvif->deflink;
+	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+	if (!tx_arvif)
+		return 0;
 
 	if (link_conf->nontransmitted) {
-		if (ar->ah->hw->wiphy != ieee80211_vif_to_wdev(tx_vif)->wiphy)
+		if (ath12k_ar_to_hw(ar)->wiphy !=
+		    ath12k_ar_to_hw(tx_arvif->ar)->wiphy)
 			return -EINVAL;
 
 		*flags = WMI_VDEV_MBSSID_FLAGS_NON_TRANSMIT_AP;
@@ -9238,9 +9246,9 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 			   int n_vifs)
 {
 	struct ath12k_wmi_vdev_up_params params = {};
+	struct ath12k_link_vif *arvif, *tx_arvif;
 	struct ieee80211_bss_conf *link_conf;
 	struct ath12k_base *ab = ar->ab;
-	struct ath12k_link_vif *arvif;
 	struct ieee80211_vif *vif;
 	struct ath12k_vif *ahvif;
 	u8 link_id;
@@ -9308,11 +9316,9 @@ ath12k_mac_update_vif_chan(struct ath12k *ar,
 		params.vdev_id = arvif->vdev_id;
 		params.aid = ahvif->aid;
 		params.bssid = arvif->bssid;
-		if (vif->mbssid_tx_vif) {
-			struct ath12k_vif *tx_ahvif =
-				ath12k_vif_to_ahvif(vif->mbssid_tx_vif);
-			struct ath12k_link_vif *tx_arvif = &tx_ahvif->deflink;
 
+		tx_arvif = ath12k_mac_get_tx_arvif(arvif);
+		if (tx_arvif) {
 			params.tx_bssid = tx_arvif->bssid;
 			params.nontx_profile_idx = link_conf->bssid_index;
 			params.nontx_profile_cnt = 1 << link_conf->bssid_indicator;

From 5f1e9f2cbc2b8aff6a2bef9b67c09c8ac8923285 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Date: Mon, 10 Feb 2025 10:27:17 -0800
Subject: [PATCH 1359/2753] wifi: ath12k: pass tx arvif for MBSSID and EMA
 beacon generation

Add new input parameter to ath12k_mac_setup_bcn_tmpl_ema() for
'tx_arvif' as the caller ath12k_mac_setup_bcn_tmpl() already
stores it locally. Avoid duplicate retrieval.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210182718.408891-5-aloka.dixit@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index 2de9a9b003a62..cdf40d68e43df 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1643,13 +1643,13 @@ static void ath12k_mac_set_arvif_ies(struct ath12k_link_vif *arvif, struct sk_bu
 	}
 }
 
-static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif)
+static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif,
+					 struct ath12k_link_vif *tx_arvif)
 {
 	struct ath12k_vif *ahvif = arvif->ahvif;
 	struct ieee80211_bss_conf *bss_conf;
 	struct ath12k_wmi_bcn_tmpl_ema_arg ema_args;
 	struct ieee80211_ema_beacons *beacons;
-	struct ath12k_link_vif *tx_arvif;
 	bool nontx_profile_found = false;
 	int ret = 0;
 	u8 i;
@@ -1662,7 +1662,6 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif)
 		return -ENOLINK;
 	}
 
-	tx_arvif = ath12k_mac_get_tx_arvif(arvif);
 	beacons = ieee80211_beacon_get_template_ema_list(ath12k_ar_to_hw(tx_arvif->ar),
 							 tx_arvif->ahvif->vif,
 							 tx_arvif->link_id);
@@ -1731,7 +1730,7 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 			return 0;
 
 		if (link_conf->ema_ap)
-			return ath12k_mac_setup_bcn_tmpl_ema(arvif);
+			return ath12k_mac_setup_bcn_tmpl_ema(arvif, tx_arvif);
 	} else {
 		tx_arvif = arvif;
 	}

From f4f5ee5e3a21830c3c4f1925108dbc7c3c070574 Mon Sep 17 00:00:00 2001
From: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Date: Mon, 10 Feb 2025 10:27:18 -0800
Subject: [PATCH 1360/2753] wifi: ath12k: pass BSSID index as input for EMA

Function ath12k_mac_setup_bcn_tmpl_ema() retrieves 'bss_conf'
only to get BSSID index which is an overhead because the
caller ath12k_mac_setup_bcn_tmpl() has already stored this
locally. Pass the index as an input instead.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Aloka Dixit <aloka.dixit@oss.qualcomm.com>
Reviewed-by: Vasanthakumar Thiagarajan <vasanthakumar.thiagarajan@oss.qualcomm.com>
Link: https://patch.msgid.link/20250210182718.408891-6-aloka.dixit@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/mac.c | 20 ++++++--------------
 1 file changed, 6 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
index cdf40d68e43df..dfa05f0ee6c9f 100644
--- a/drivers/net/wireless/ath/ath12k/mac.c
+++ b/drivers/net/wireless/ath/ath12k/mac.c
@@ -1644,24 +1644,15 @@ static void ath12k_mac_set_arvif_ies(struct ath12k_link_vif *arvif, struct sk_bu
 }
 
 static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif,
-					 struct ath12k_link_vif *tx_arvif)
+					 struct ath12k_link_vif *tx_arvif,
+					 u8 bssid_index)
 {
-	struct ath12k_vif *ahvif = arvif->ahvif;
-	struct ieee80211_bss_conf *bss_conf;
 	struct ath12k_wmi_bcn_tmpl_ema_arg ema_args;
 	struct ieee80211_ema_beacons *beacons;
 	bool nontx_profile_found = false;
 	int ret = 0;
 	u8 i;
 
-	bss_conf = ath12k_mac_get_link_bss_conf(arvif);
-	if (!bss_conf) {
-		ath12k_warn(arvif->ar->ab,
-			    "failed to get link bss conf to update bcn tmpl for vif %pM link %u\n",
-			    ahvif->vif->addr, arvif->link_id);
-		return -ENOLINK;
-	}
-
 	beacons = ieee80211_beacon_get_template_ema_list(ath12k_ar_to_hw(tx_arvif->ar),
 							 tx_arvif->ahvif->vif,
 							 tx_arvif->link_id);
@@ -1677,7 +1668,7 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif,
 	for (i = 0; i < beacons->cnt; i++) {
 		if (tx_arvif != arvif && !nontx_profile_found)
 			ath12k_mac_set_arvif_ies(arvif, beacons->bcn[i].skb,
-						 bss_conf->bssid_index,
+						 bssid_index,
 						 &nontx_profile_found);
 
 		ema_args.bcn_cnt = beacons->cnt;
@@ -1695,7 +1686,7 @@ static int ath12k_mac_setup_bcn_tmpl_ema(struct ath12k_link_vif *arvif,
 	if (tx_arvif != arvif && !nontx_profile_found)
 		ath12k_warn(arvif->ar->ab,
 			    "nontransmitted bssid index %u not found in beacon template\n",
-			    bss_conf->bssid_index);
+			    bssid_index);
 
 	ieee80211_beacon_free_ema_list(beacons);
 	return ret;
@@ -1730,7 +1721,8 @@ static int ath12k_mac_setup_bcn_tmpl(struct ath12k_link_vif *arvif)
 			return 0;
 
 		if (link_conf->ema_ap)
-			return ath12k_mac_setup_bcn_tmpl_ema(arvif, tx_arvif);
+			return ath12k_mac_setup_bcn_tmpl_ema(arvif, tx_arvif,
+							     link_conf->bssid_index);
 	} else {
 		tx_arvif = arvif;
 	}

From fcd37e2a33167cf6b507256365e45a43009d74eb Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Feb 2025 10:05:32 +0100
Subject: [PATCH 1361/2753] dt-bindings: wireless: ath10k: Strip ath10k prefix
 from calibration properties

Devicetree properties describing exactly the same thing should be
reusable between device bindings.  All Qualcomm Atheros WiFi chips needs
certain calibration data, so properties should not be prefixed with
device family (ath10k).

Deprecate qcom,ath10k-calibration-variant and alike, so we gradually
switch to a common property.  This will also allow moving these
properties to common schema, if desired.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250225-b-wifi-qcom-calibration-variant-v1-1-3b2aa3f89c53@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../bindings/net/wireless/qcom,ath10k.yaml    | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
index 070c4c9b86437..a8a992b0b54ee 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath10k.yaml
@@ -93,20 +93,41 @@ properties:
 
   ieee80211-freq-limit: true
 
+  qcom,calibration-data:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description:
+      Calibration data + board-specific data as a byte array. The length
+      can vary between hardware versions.
+
   qcom,ath10k-calibration-data:
     $ref: /schemas/types.yaml#/definitions/uint8-array
+    deprecated: true
     description:
       Calibration data + board-specific data as a byte array. The length
       can vary between hardware versions.
 
+  qcom,calibration-variant:
+    $ref: /schemas/types.yaml#/definitions/string
+    description:
+      Unique variant identifier of the calibration data in board-2.bin
+      for designs with colliding bus and device specific ids
+
   qcom,ath10k-calibration-variant:
     $ref: /schemas/types.yaml#/definitions/string
+    deprecated: true
     description:
       Unique variant identifier of the calibration data in board-2.bin
       for designs with colliding bus and device specific ids
 
+  qcom,pre-calibration-data:
+    $ref: /schemas/types.yaml#/definitions/uint8-array
+    description:
+      Pre-calibration data as a byte array. The length can vary between
+      hardware versions.
+
   qcom,ath10k-pre-calibration-data:
     $ref: /schemas/types.yaml#/definitions/uint8-array
+    deprecated: true
     description:
       Pre-calibration data as a byte array. The length can vary between
       hardware versions.

From 352e8c4379fa540747cbb6c94c4b149c7487feac Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Feb 2025 10:05:33 +0100
Subject: [PATCH 1362/2753] dt-bindings: wireless: ath11k: Strip ath11k prefix
 from calibration property

Devicetree properties describing exactly the same thing should be
reusable between device bindings.  All Qualcomm Atheros WiFi chips needs
certain calibration data, so properties should not be prefixed with
device family (ath11k).

Deprecate qcom,ath11k-calibration-variant and alike, so we gradually
switch to a common property.  This will also allow moving these
properties to common schema, if desired.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250225-b-wifi-qcom-calibration-variant-v1-2-3b2aa3f89c53@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../bindings/net/wireless/qcom,ath11k-pci.yaml           | 9 ++++++++-
 .../devicetree/bindings/net/wireless/qcom,ath11k.yaml    | 7 +++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml
index a71fdf05bc1ea..25b0afd1b6152 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k-pci.yaml
@@ -23,8 +23,15 @@ properties:
   reg:
     maxItems: 1
 
+  qcom,calibration-variant:
+    $ref: /schemas/types.yaml#/definitions/string
+    description: |
+      string to uniquely identify variant of the calibration data for designs
+      with colliding bus and device ids
+
   qcom,ath11k-calibration-variant:
     $ref: /schemas/types.yaml#/definitions/string
+    deprecated: true
     description: |
       string to uniquely identify variant of the calibration data for designs
       with colliding bus and device ids
@@ -128,7 +135,7 @@ examples:
                 vddrfa1p2-supply = <&vreg_pmu_rfa_1p2>;
                 vddrfa1p8-supply = <&vreg_pmu_rfa_1p7>;
 
-                qcom,ath11k-calibration-variant = "LE_X13S";
+                qcom,calibration-variant = "LE_X13S";
             };
         };
     };
diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
index ff5763dc66a88..e70b9b0a2e29b 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath11k.yaml
@@ -42,8 +42,15 @@ properties:
         * reg
         * reg-names
 
+  qcom,calibration-variant:
+    $ref: /schemas/types.yaml#/definitions/string
+    description:
+      string to uniquely identify variant of the calibration data in the
+      board-2.bin for designs with colliding bus and device specific ids
+
   qcom,ath11k-calibration-variant:
     $ref: /schemas/types.yaml#/definitions/string
+    deprecated: true
     description:
       string to uniquely identify variant of the calibration data in the
       board-2.bin for designs with colliding bus and device specific ids

From 64e37c19383f840da534449b88d7adea4c69f52d Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Feb 2025 10:05:34 +0100
Subject: [PATCH 1363/2753] dt-bindings: wireless: ath12k: Strip ath12k prefix
 from calibration property

Devicetree properties describing exactly the same thing should be
reusable between device bindings.  All Qualcomm Atheros WiFi chips needs
certain calibration data, so properties should not be prefixed with
device family (ath12k).

Deprecate qcom,ath12k-calibration-variant and alike, so we gradually
switch to a common property.  This will also allow moving these
properties to common schema, if desired.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250225-b-wifi-qcom-calibration-variant-v1-3-3b2aa3f89c53@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 .../bindings/net/wireless/qcom,ath12k-wsi.yaml      | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml
index cbfb559f6b69b..7f83871bd1072 100644
--- a/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml
+++ b/Documentation/devicetree/bindings/net/wireless/qcom,ath12k-wsi.yaml
@@ -53,8 +53,15 @@ properties:
   reg:
     maxItems: 1
 
+  qcom,calibration-variant:
+    $ref: /schemas/types.yaml#/definitions/string
+    description:
+      String to uniquely identify variant of the calibration data for designs
+      with colliding bus and device ids
+
   qcom,ath12k-calibration-variant:
     $ref: /schemas/types.yaml#/definitions/string
+    deprecated: true
     description:
       String to uniquely identify variant of the calibration data for designs
       with colliding bus and device ids
@@ -104,7 +111,7 @@ examples:
                 compatible = "pci17cb,1109";
                 reg = <0x0 0x0 0x0 0x0 0x0>;
 
-                qcom,ath12k-calibration-variant = "RDP433_1";
+                qcom,calibration-variant = "RDP433_1";
 
                 ports {
                     #address-cells = <1>;
@@ -140,7 +147,7 @@ examples:
                 compatible = "pci17cb,1109";
                 reg = <0x0 0x0 0x0 0x0 0x0>;
 
-                qcom,ath12k-calibration-variant = "RDP433_2";
+                qcom,calibration-variant = "RDP433_2";
                 qcom,wsi-controller;
 
                 ports {
@@ -177,7 +184,7 @@ examples:
                 compatible = "pci17cb,1109";
                 reg = <0x0 0x0 0x0 0x0 0x0>;
 
-                qcom,ath12k-calibration-variant = "RDP433_3";
+                qcom,calibration-variant = "RDP433_3";
 
                 ports {
                     #address-cells = <1>;

From a97ed4ecb797a69f52f66445ebca538c93462ba4 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Feb 2025 10:05:35 +0100
Subject: [PATCH 1364/2753] wifi: ath10k: Deprecate
 qcom,ath10k-calibration-variant properties

Add support for calibration-like properties without 'ath10k' prefix,
while still keeping everything backwards compatible.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250225-b-wifi-qcom-calibration-variant-v1-4-3b2aa3f89c53@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath10k/core.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/core.c b/drivers/net/wireless/ath/ath10k/core.c
index b3294287bce1f..6d336e39d6738 100644
--- a/drivers/net/wireless/ath/ath10k/core.c
+++ b/drivers/net/wireless/ath/ath10k/core.c
@@ -1163,8 +1163,11 @@ int ath10k_core_check_dt(struct ath10k *ar)
 	if (!node)
 		return -ENOENT;
 
-	of_property_read_string(node, "qcom,ath10k-calibration-variant",
+	of_property_read_string(node, "qcom,calibration-variant",
 				&variant);
+	if (!variant)
+		of_property_read_string(node, "qcom,ath10k-calibration-variant",
+					&variant);
 	if (!variant)
 		return -ENODATA;
 
@@ -2259,7 +2262,9 @@ static int ath10k_core_pre_cal_download(struct ath10k *ar)
 		   "boot did not find a pre calibration file, try DT next: %d\n",
 		   ret);
 
-	ret = ath10k_download_cal_dt(ar, "qcom,ath10k-pre-calibration-data");
+	ret = ath10k_download_cal_dt(ar, "qcom,pre-calibration-data");
+	if (ret == -ENOENT)
+		ret = ath10k_download_cal_dt(ar, "qcom,ath10k-pre-calibration-data");
 	if (ret) {
 		ath10k_dbg(ar, ATH10K_DBG_BOOT,
 			   "unable to load pre cal data from DT: %d\n", ret);
@@ -2337,7 +2342,9 @@ static int ath10k_download_cal_data(struct ath10k *ar)
 		   "boot did not find a calibration file, try DT next: %d\n",
 		   ret);
 
-	ret = ath10k_download_cal_dt(ar, "qcom,ath10k-calibration-data");
+	ret = ath10k_download_cal_dt(ar, "qcom,calibration-data");
+	if (ret == -ENOENT)
+		ret = ath10k_download_cal_dt(ar, "qcom,ath10k-calibration-data");
 	if (ret == 0) {
 		ar->cal_mode = ATH10K_CAL_MODE_DT;
 		goto done;

From 1bd9ffec4cdb9a1f09bbba16bba538f6c58a397b Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Tue, 25 Feb 2025 10:05:36 +0100
Subject: [PATCH 1365/2753] wifi: ath11k: Deprecate
 qcom,ath11k-calibration-variant properties

Add support for calibration-like properties without 'ath11k' prefix,
while still keeping everything backwards compatible.

Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Link: https://patch.msgid.link/20250225-b-wifi-qcom-calibration-variant-v1-5-3b2aa3f89c53@linaro.org
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath11k/core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
index 65bba0ae69a9a..3d39ff85ba94a 100644
--- a/drivers/net/wireless/ath/ath11k/core.c
+++ b/drivers/net/wireless/ath/ath11k/core.c
@@ -1175,8 +1175,11 @@ int ath11k_core_check_dt(struct ath11k_base *ab)
 	if (!node)
 		return -ENOENT;
 
-	of_property_read_string(node, "qcom,ath11k-calibration-variant",
+	of_property_read_string(node, "qcom,calibration-variant",
 				&variant);
+	if (!variant)
+		of_property_read_string(node, "qcom,ath11k-calibration-variant",
+					&variant);
 	if (!variant)
 		return -ENODATA;
 

From d2d9c9b8de725e1006d3aa3d18678a732f5d3584 Mon Sep 17 00:00:00 2001
From: Vinith Kumar R <quic_vinithku@quicinc.com>
Date: Fri, 22 Nov 2024 23:04:32 +0530
Subject: [PATCH 1366/2753] wifi: ath12k: Report proper tx completion status to
 mac80211

Currently Tx completion for few exception packets are received from
firmware and the tx status updated to mac80211. The tx status values of
HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP and HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL
are considered as tx failure and reported as tx failure to mac80211.
But these failure status is due to internal firmware tx drop and these
packets were not tried to transmit in the air.
In case of mesh this invalid tx status report might trigger mpath broken
issue due to increase in mpath fail average.
So do not report these tx status as tx failure instead free the skb
by calling ieee80211_free_txskb(), and that will be accounted as dropped
frame.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Vinith Kumar R <quic_vinithku@quicinc.com>
Signed-off-by: Tamizh Chelvam Raja <quic_tamizhr@quicinc.com>
Acked-by: Jeff Johnson <quic_jjohnson@quicinc.com>
Link: https://patch.msgid.link/20241122173432.2064858-1-quic_tamizhr@quicinc.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_tx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
index 46a55554c19c8..ced232bf4aed0 100644
--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
@@ -576,13 +576,13 @@ ath12k_dp_tx_process_htt_tx_complete(struct ath12k_base *ab,
 
 	switch (wbm_status) {
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_OK:
-	case HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP:
-	case HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL:
 		ts.acked = (wbm_status == HAL_WBM_REL_HTT_TX_COMP_STATUS_OK);
 		ts.ack_rssi = le32_get_bits(status_desc->info2,
 					    HTT_TX_WBM_COMP_INFO2_ACK_RSSI);
 		ath12k_dp_tx_htt_tx_complete_buf(ab, msdu, tx_ring, &ts);
 		break;
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_DROP:
+	case HAL_WBM_REL_HTT_TX_COMP_STATUS_TTL:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_REINJ:
 	case HAL_WBM_REL_HTT_TX_COMP_STATUS_INSPECT:
 		ath12k_dp_tx_free_txbuf(ab, msdu, mac_id, tx_ring);

From 9a0dddfb30f120db3851627935851d262e4e7acb Mon Sep 17 00:00:00 2001
From: Manish Dharanenthiran <quic_mdharane@quicinc.com>
Date: Tue, 11 Feb 2025 14:33:02 +0530
Subject: [PATCH 1367/2753] wifi: ath12k: Fix invalid data access in
 ath12k_dp_rx_h_undecap_nwifi

In certain cases, hardware might provide packets with a
length greater than the maximum native Wi-Fi header length.
This can lead to accessing and modifying fields in the header
within the ath12k_dp_rx_h_undecap_nwifi function for
DP_RX_DECAP_TYPE_NATIVE_WIFI decap type and
potentially resulting in invalid data access and memory corruption.

Add a sanity check before processing the SKB to prevent invalid
data access in the undecap native Wi-Fi function for the
DP_RX_DECAP_TYPE_NATIVE_WIFI decap type.

Tested-on: QCN9274 hw2.0 PCI WLAN.WBE.1.3.1-00173-QCAHKSWPL_SILICONZ-1

Signed-off-by: Manish Dharanenthiran <quic_mdharane@quicinc.com>
Signed-off-by: Tamizh Chelvam Raja <tamizh.raja@oss.qualcomm.com>
Link: https://patch.msgid.link/20250211090302.4105141-1-tamizh.raja@oss.qualcomm.com
Signed-off-by: Jeff Johnson <jeff.johnson@oss.qualcomm.com>
---
 drivers/net/wireless/ath/ath12k/dp_rx.c | 42 +++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
index 95c9056642cfd..ff6a709b5042c 100644
--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
+++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
@@ -2548,6 +2548,29 @@ static void ath12k_dp_rx_deliver_msdu(struct ath12k *ar, struct napi_struct *nap
 	ieee80211_rx_napi(ath12k_ar_to_hw(ar), pubsta, msdu, napi);
 }
 
+static bool ath12k_dp_rx_check_nwifi_hdr_len_valid(struct ath12k_base *ab,
+						   struct hal_rx_desc *rx_desc,
+						   struct sk_buff *msdu)
+{
+	struct ieee80211_hdr *hdr;
+	u8 decap_type;
+	u32 hdr_len;
+
+	decap_type = ath12k_dp_rx_h_decap_type(ab, rx_desc);
+	if (decap_type != DP_RX_DECAP_TYPE_NATIVE_WIFI)
+		return true;
+
+	hdr = (struct ieee80211_hdr *)msdu->data;
+	hdr_len = ieee80211_hdrlen(hdr->frame_control);
+
+	if ((likely(hdr_len <= DP_MAX_NWIFI_HDR_LEN)))
+		return true;
+
+	ab->soc_stats.invalid_rbm++;
+	WARN_ON_ONCE(1);
+	return false;
+}
+
 static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 				     struct sk_buff *msdu,
 				     struct sk_buff_head *msdu_list,
@@ -2606,6 +2629,11 @@ static int ath12k_dp_rx_process_msdu(struct ath12k *ar,
 		}
 	}
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, rx_desc, msdu))) {
+		ret = -EINVAL;
+		goto free_out;
+	}
+
 	ath12k_dp_rx_h_ppdu(ar, rx_desc, rx_status);
 	ath12k_dp_rx_h_mpdu(ar, msdu, rx_desc, rx_status);
 
@@ -2996,6 +3024,9 @@ static int ath12k_dp_rx_h_verify_tkip_mic(struct ath12k *ar, struct ath12k_peer
 		    RX_FLAG_IV_STRIPPED | RX_FLAG_DECRYPTED;
 	skb_pull(msdu, hal_rx_desc_sz);
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, rx_desc, msdu)))
+		return -EINVAL;
+
 	ath12k_dp_rx_h_ppdu(ar, rx_desc, rxs);
 	ath12k_dp_rx_h_undecap(ar, msdu, rx_desc,
 			       HAL_ENCRYPT_TYPE_TKIP_MIC, rxs, true);
@@ -3738,6 +3769,9 @@ static int ath12k_dp_rx_h_null_q_desc(struct ath12k *ar, struct sk_buff *msdu,
 		skb_put(msdu, hal_rx_desc_sz + l3pad_bytes + msdu_len);
 		skb_pull(msdu, hal_rx_desc_sz + l3pad_bytes);
 	}
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
+		return -EINVAL;
+
 	ath12k_dp_rx_h_ppdu(ar, desc, status);
 
 	ath12k_dp_rx_h_mpdu(ar, msdu, desc, status);
@@ -3782,7 +3816,7 @@ static bool ath12k_dp_rx_h_reo_err(struct ath12k *ar, struct sk_buff *msdu,
 	return drop;
 }
 
-static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
+static bool ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 					struct ieee80211_rx_status *status)
 {
 	struct ath12k_base *ab = ar->ab;
@@ -3800,6 +3834,9 @@ static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 	skb_put(msdu, hal_rx_desc_sz + l3pad_bytes + msdu_len);
 	skb_pull(msdu, hal_rx_desc_sz + l3pad_bytes);
 
+	if (unlikely(!ath12k_dp_rx_check_nwifi_hdr_len_valid(ab, desc, msdu)))
+		return true;
+
 	ath12k_dp_rx_h_ppdu(ar, desc, status);
 
 	status->flag |= (RX_FLAG_MMIC_STRIPPED | RX_FLAG_MMIC_ERROR |
@@ -3807,6 +3844,7 @@ static void ath12k_dp_rx_h_tkip_mic_err(struct ath12k *ar, struct sk_buff *msdu,
 
 	ath12k_dp_rx_h_undecap(ar, msdu, desc,
 			       HAL_ENCRYPT_TYPE_TKIP_MIC, status, false);
+	return false;
 }
 
 static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
@@ -3825,7 +3863,7 @@ static bool ath12k_dp_rx_h_rxdma_err(struct ath12k *ar,  struct sk_buff *msdu,
 	case HAL_REO_ENTR_RING_RXDMA_ECODE_TKIP_MIC_ERR:
 		err_bitmap = ath12k_dp_rx_h_mpdu_err(ab, rx_desc);
 		if (err_bitmap & HAL_RX_MPDU_ERR_TKIP_MIC) {
-			ath12k_dp_rx_h_tkip_mic_err(ar, msdu, status);
+			drop = ath12k_dp_rx_h_tkip_mic_err(ar, msdu, status);
 			break;
 		}
 		fallthrough;

From c157d351460bcf202970e97e611cb6b54a3dd4a4 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 25 Feb 2025 23:37:08 +0100
Subject: [PATCH 1368/2753] intel_idle: Handle older CPUs, which stop the TSC
 in deeper C states, correctly

The Intel idle driver is preferred over the ACPI processor idle driver,
but fails to implement the work around for Core2 generation CPUs, where
the TSC stops in C2 and deeper C-states. This causes stalls and boot
delays, when the clocksource watchdog does not catch the unstable TSC
before the CPU goes deep idle for the first time.

The ACPI driver marks the TSC unstable when it detects that the CPU
supports C2 or deeper and the CPU does not have a non-stop TSC.

Add the equivivalent work around to the Intel idle driver to cure that.

Fixes: 18734958e9bf ("intel_idle: Use ACPI _CST for processor models without C-state tables")
Reported-by: Fab Stz <fabstz-it@yahoo.fr>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Fab Stz <fabstz-it@yahoo.fr>
Cc: All applicable <stable@vger.kernel.org>
Closes: https://lore.kernel.org/all/10cf96aa-1276-4bd4-8966-c890377030c3@yahoo.fr
Link: https://patch.msgid.link/87bjupfy7f.ffs@tglx
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/idle/intel_idle.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 118fe1d37c226..0fdb1d1316c44 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -56,6 +56,7 @@
 #include <asm/intel-family.h>
 #include <asm/mwait.h>
 #include <asm/spec-ctrl.h>
+#include <asm/tsc.h>
 #include <asm/fpu/api.h>
 
 #define INTEL_IDLE_VERSION "0.5.1"
@@ -1799,6 +1800,9 @@ static void __init intel_idle_init_cstates_acpi(struct cpuidle_driver *drv)
 		if (intel_idle_state_needs_timer_stop(state))
 			state->flags |= CPUIDLE_FLAG_TIMER_STOP;
 
+		if (cx->type > ACPI_STATE_C1 && !boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
+			mark_tsc_unstable("TSC halts in idle");
+
 		state->enter = intel_idle;
 		state->enter_s2idle = intel_idle_s2idle;
 	}

From 43c854c65e47d2f3763345683b06257b4d12e4e3 Mon Sep 17 00:00:00 2001
From: Yao Zi <ziyao@disroot.org>
Date: Fri, 28 Feb 2025 16:31:18 +0000
Subject: [PATCH 1369/2753] arm64: dts: rockchip: Remove undocumented sdmmc
 property from lubancat-1

Property "supports-sd" isn't documented anywhere and is unnecessary for
mainline driver to function. It seems a property used by downstream
kernel was brought into mainline.

This should be reported by dtbs_check, but mmc-controller-common.yaml
defaults additionalProperties to true thus allows it. Remove the
property to clean the devicetree up and avoid possible confusion.

Fixes: 8d94da58de53 ("arm64: dts: rockchip: Add EmbedFire LubanCat 1")
Signed-off-by: Yao Zi <ziyao@disroot.org>
Link: https://lore.kernel.org/r/20250228163117.47318-2-ziyao@disroot.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
index 61dd71c259aac..ddf84c2a19cfa 100644
--- a/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3566-lubancat-1.dts
@@ -512,7 +512,6 @@
 
 &sdmmc0 {
 	max-frequency = <150000000>;
-	supports-sd;
 	bus-width = <4>;
 	cap-mmc-highspeed;
 	cap-sd-highspeed;

From daeb6a8f3b00d3b6f40593d80ab6be4f6d3d968d Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2025 18:34:36 +0000
Subject: [PATCH 1370/2753] ipv4: icmp: do not process ICMP_EXT_ECHOREPLY for
 broadcast/multicast addresses

There is no point processing ICMP_EXT_ECHOREPLY for routes
which would drop ICMP_ECHOREPLY (RFC 1122 3.2.2.6, 3.2.2.8)

This seems an oversight of the initial implementation.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250226183437.1457318-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c | 32 ++++++++++++++++----------------
 1 file changed, 16 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 799775ba97d4f..058d4c1e300d0 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1248,22 +1248,6 @@ int icmp_rcv(struct sk_buff *skb)
 		goto reason_check;
 	}
 
-	if (icmph->type == ICMP_EXT_ECHOREPLY) {
-		reason = ping_rcv(skb);
-		goto reason_check;
-	}
-
-	/*
-	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
-	 *
-	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
-	 *		  discarded.
-	 */
-	if (icmph->type > NR_ICMP_TYPES) {
-		reason = SKB_DROP_REASON_UNHANDLED_PROTO;
-		goto error;
-	}
-
 	/*
 	 *	Parse the ICMP message
 	 */
@@ -1290,6 +1274,22 @@ int icmp_rcv(struct sk_buff *skb)
 		}
 	}
 
+	if (icmph->type == ICMP_EXT_ECHOREPLY) {
+		reason = ping_rcv(skb);
+		goto reason_check;
+	}
+
+	/*
+	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
+	 *
+	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
+	 *		  discarded.
+	 */
+	if (icmph->type > NR_ICMP_TYPES) {
+		reason = SKB_DROP_REASON_UNHANDLED_PROTO;
+		goto error;
+	}
+
 	reason = icmp_pointers[icmph->type].handler(skb);
 reason_check:
 	if (!reason)  {

From a7e38208fe71498102de3ea9d20cfe847cdb6893 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 26 Feb 2025 18:34:37 +0000
Subject: [PATCH 1371/2753] inet: ping: avoid skb_clone() dance in ping_rcv()

ping_rcv() callers currently call skb_free() or consume_skb(),
forcing ping_rcv() to clone the skb.

After this patch ping_rcv() is now 'consuming' the original skb,
either moving to a socket receive queue, or dropping it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250226183437.1457318-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/icmp.c |  5 +++--
 net/ipv4/ping.c | 20 +++++---------------
 net/ipv6/icmp.c |  7 ++-----
 3 files changed, 10 insertions(+), 22 deletions(-)

diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 058d4c1e300d0..717cb7d3607a1 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -1274,9 +1274,10 @@ int icmp_rcv(struct sk_buff *skb)
 		}
 	}
 
-	if (icmph->type == ICMP_EXT_ECHOREPLY) {
+	if (icmph->type == ICMP_EXT_ECHOREPLY ||
+	    icmph->type == ICMP_ECHOREPLY) {
 		reason = ping_rcv(skb);
-		goto reason_check;
+		return reason ? NET_RX_DROP : NET_RX_SUCCESS;
 	}
 
 	/*
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 85d09f2ecadcb..c14baa6589c74 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -966,10 +966,9 @@ EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
 
 enum skb_drop_reason ping_rcv(struct sk_buff *skb)
 {
-	enum skb_drop_reason reason = SKB_DROP_REASON_NO_SOCKET;
-	struct sock *sk;
 	struct net *net = dev_net(skb->dev);
 	struct icmphdr *icmph = icmp_hdr(skb);
+	struct sock *sk;
 
 	/* We assume the packet has already been checked by icmp_rcv */
 
@@ -980,20 +979,11 @@ enum skb_drop_reason ping_rcv(struct sk_buff *skb)
 	skb_push(skb, skb->data - (u8 *)icmph);
 
 	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
-	if (sk) {
-		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
-
-		pr_debug("rcv on socket %p\n", sk);
-		if (skb2)
-			reason = __ping_queue_rcv_skb(sk, skb2);
-		else
-			reason = SKB_DROP_REASON_NOMEM;
-	}
-
-	if (reason)
-		pr_debug("no socket, dropping\n");
+	if (sk)
+		return __ping_queue_rcv_skb(sk, skb);
 
-	return reason;
+	kfree_skb_reason(skb, SKB_DROP_REASON_NO_SOCKET);
+	return SKB_DROP_REASON_NO_SOCKET;
 }
 EXPORT_SYMBOL_GPL(ping_rcv);
 
diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
index 4d14ab7f7e99f..3fd19a84b358d 100644
--- a/net/ipv6/icmp.c
+++ b/net/ipv6/icmp.c
@@ -957,12 +957,9 @@ static int icmpv6_rcv(struct sk_buff *skb)
 		break;
 
 	case ICMPV6_ECHO_REPLY:
-		reason = ping_rcv(skb);
-		break;
-
 	case ICMPV6_EXT_ECHO_REPLY:
-		reason = ping_rcv(skb);
-		break;
+		ping_rcv(skb);
+		return 0;
 
 	case ICMPV6_PKT_TOOBIG:
 		/* BUGGG_FUTURE: if packet contains rthdr, we cannot update

From 4a4f9b5c7c13601c4f1b3d8c607d7439e39f40d2 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 15:58:30 -0500
Subject: [PATCH 1372/2753] bcachefs: Don't set
 BCH_FEATURE_incompat_version_field unless requested

We shouldn't be setting incompatible bits or the incompatible version
field unless explicitly request or allowed - otherwise we break mounting
with old kernels or userspace.

Reported-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super-io.c | 24 ++++++++++++++++--------
 fs/bcachefs/super-io.h | 11 ++++-------
 2 files changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/bcachefs/super-io.c b/fs/bcachefs/super-io.c
index 8037ccbacf6af..a81a7b6c09897 100644
--- a/fs/bcachefs/super-io.c
+++ b/fs/bcachefs/super-io.c
@@ -69,14 +69,20 @@ enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_meta
 	return v;
 }
 
-void bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version)
+bool bch2_set_version_incompat(struct bch_fs *c, enum bcachefs_metadata_version version)
 {
-	mutex_lock(&c->sb_lock);
-	SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
-		max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
-	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field);
-	bch2_write_super(c);
-	mutex_unlock(&c->sb_lock);
+	bool ret = (c->sb.features & BIT_ULL(BCH_FEATURE_incompat_version_field)) &&
+		   version <= c->sb.version_incompat_allowed;
+
+	if (ret) {
+		mutex_lock(&c->sb_lock);
+		SET_BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb,
+			max(BCH_SB_VERSION_INCOMPAT(c->disk_sb.sb), version));
+		bch2_write_super(c);
+		mutex_unlock(&c->sb_lock);
+	}
+
+	return ret;
 }
 
 const char * const bch2_sb_fields[] = {
@@ -1219,9 +1225,11 @@ void bch2_sb_upgrade(struct bch_fs *c, unsigned new_version, bool incompat)
 	c->disk_sb.sb->version = cpu_to_le16(new_version);
 	c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_SB_FEATURES_ALL);
 
-	if (incompat)
+	if (incompat) {
 		SET_BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb,
 			max(BCH_SB_VERSION_INCOMPAT_ALLOWED(c->disk_sb.sb), new_version));
+		c->disk_sb.sb->features[0] |= cpu_to_le64(BCH_FEATURE_incompat_version_field);
+	}
 }
 
 static int bch2_sb_ext_validate(struct bch_sb *sb, struct bch_sb_field *f,
diff --git a/fs/bcachefs/super-io.h b/fs/bcachefs/super-io.h
index f1ab4f9437203..b4cff9ebdebbf 100644
--- a/fs/bcachefs/super-io.h
+++ b/fs/bcachefs/super-io.h
@@ -21,17 +21,14 @@ static inline bool bch2_version_compatible(u16 version)
 void bch2_version_to_text(struct printbuf *, enum bcachefs_metadata_version);
 enum bcachefs_metadata_version bch2_latest_compatible_version(enum bcachefs_metadata_version);
 
-void bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version);
+bool bch2_set_version_incompat(struct bch_fs *, enum bcachefs_metadata_version);
 
 static inline bool bch2_request_incompat_feature(struct bch_fs *c,
 						 enum bcachefs_metadata_version version)
 {
-	if (unlikely(version > c->sb.version_incompat)) {
-		if (version > c->sb.version_incompat_allowed)
-			return false;
-		bch2_set_version_incompat(c, version);
-	}
-	return true;
+	return likely(version <= c->sb.version_incompat)
+		? true
+		: bch2_set_version_incompat(c, version);
 }
 
 static inline size_t bch2_sb_field_bytes(struct bch_sb_field *f)

From ee01b2f2d7d0010787c2343463965bbc283a497f Mon Sep 17 00:00:00 2001
From: Antoine Tenart <atenart@kernel.org>
Date: Wed, 26 Feb 2025 18:13:42 +0100
Subject: [PATCH 1373/2753] net: gso: fix ownership in __udp_gso_segment

In __udp_gso_segment the skb destructor is removed before segmenting the
skb but the socket reference is kept as-is. This is an issue if the
original skb is later orphaned as we can hit the following bug:

  kernel BUG at ./include/linux/skbuff.h:3312!  (skb_orphan)
  RIP: 0010:ip_rcv_core+0x8b2/0xca0
  Call Trace:
   ip_rcv+0xab/0x6e0
   __netif_receive_skb_one_core+0x168/0x1b0
   process_backlog+0x384/0x1100
   __napi_poll.constprop.0+0xa1/0x370
   net_rx_action+0x925/0xe50

The above can happen following a sequence of events when using
OpenVSwitch, when an OVS_ACTION_ATTR_USERSPACE action precedes an
OVS_ACTION_ATTR_OUTPUT action:

1. OVS_ACTION_ATTR_USERSPACE is handled (in do_execute_actions): the skb
   goes through queue_gso_packets and then __udp_gso_segment, where its
   destructor is removed.
2. The segments' data are copied and sent to userspace.
3. OVS_ACTION_ATTR_OUTPUT is handled (in do_execute_actions) and the
   same original skb is sent to its path.
4. If it later hits skb_orphan, we hit the bug.

Fix this by also removing the reference to the socket in
__udp_gso_segment.

Fixes: ad405857b174 ("udp: better wmem accounting on gso")
Signed-off-by: Antoine Tenart <atenart@kernel.org>
Link: https://patch.msgid.link/20250226171352.258045-1-atenart@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp_offload.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a5be6e4ed326f..ecfca59f31f13 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -321,13 +321,17 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 
 	/* clear destructor to avoid skb_segment assigning it to tail */
 	copy_dtor = gso_skb->destructor == sock_wfree;
-	if (copy_dtor)
+	if (copy_dtor) {
 		gso_skb->destructor = NULL;
+		gso_skb->sk = NULL;
+	}
 
 	segs = skb_segment(gso_skb, features);
 	if (IS_ERR_OR_NULL(segs)) {
-		if (copy_dtor)
+		if (copy_dtor) {
 			gso_skb->destructor = sock_wfree;
+			gso_skb->sk = sk;
+		}
 		return segs;
 	}
 

From e8cdd91926aac2c53a23925c538ad4c44be4201f Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Thu, 27 Feb 2025 12:24:39 +0100
Subject: [PATCH 1374/2753] net: usb: qmi_wwan: add Telit Cinterion FE990B
 composition

Add the following Telit Cinterion FE990B composition:
0x10b0: rmnet + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb

usb-devices:
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#=  7 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10b0 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FE990
S:  SerialNumber=28c2595e
C:  #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250227112441.3653819-2-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 14d1c85c80004..287375b8a2727 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1365,6 +1365,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10b0, 0)}, /* Telit FE990B */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c0, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c4, 0)}, /* Telit FE910C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10c8, 0)}, /* Telit FE910C04 */

From 5728b289abbb4e1faf7b5eb264624f08442861f4 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Thu, 27 Feb 2025 12:24:40 +0100
Subject: [PATCH 1375/2753] net: usb: qmi_wwan: fix Telit Cinterion FE990A name

The correct name for FE990 is FE990A so use it in order to avoid
confusion with FE990B.

Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250227112441.3653819-3-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/qmi_wwan.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
index 287375b8a2727..b586b1c13a47f 100644
--- a/drivers/net/usb/qmi_wwan.c
+++ b/drivers/net/usb/qmi_wwan.c
@@ -1361,7 +1361,7 @@ static const struct usb_device_id products[] = {
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1057, 2)},	/* Telit FN980 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1060, 2)},	/* Telit LN920 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1070, 2)},	/* Telit FN990A */
-	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990 */
+	{QMI_QUIRK_SET_DTR(0x1bc7, 0x1080, 2)}, /* Telit FE990A */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a0, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a4, 0)}, /* Telit FN920C04 */
 	{QMI_QUIRK_SET_DTR(0x1bc7, 0x10a9, 0)}, /* Telit FN920C04 */

From 97fc6863637630cdf9a5e9ed2569fe9a7974434b Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Thu, 27 Feb 2025 12:24:41 +0100
Subject: [PATCH 1376/2753] net: usb: cdc_mbim: fix Telit Cinterion FE990A name

The correct name for FE990 is FE990A so use it in order to avoid
confusion with FE990B.

Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Link: https://patch.msgid.link/20250227112441.3653819-4-fabio.porcedda@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_mbim.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/usb/cdc_mbim.c b/drivers/net/usb/cdc_mbim.c
index 88921c13b6294..dbf01210b0e78 100644
--- a/drivers/net/usb/cdc_mbim.c
+++ b/drivers/net/usb/cdc_mbim.c
@@ -665,7 +665,7 @@ static const struct usb_device_id mbim_devs[] = {
 	  .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle,
 	},
 
-	/* Telit FE990 */
+	/* Telit FE990A */
 	{ USB_DEVICE_AND_INTERFACE_INFO(0x1bc7, 0x1081, USB_CLASS_COMM, USB_CDC_SUBCLASS_MBIM, USB_CDC_PROTO_NONE),
 	  .driver_info = (unsigned long)&cdc_mbim_info_avoid_altsetting_toggle,
 	},

From a466fd7e9fafd975949e5945e2f70c33a94b1a70 Mon Sep 17 00:00:00 2001
From: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Date: Thu, 27 Feb 2025 23:46:27 +0500
Subject: [PATCH 1377/2753] caif_virtio: fix wrong pointer check in cfv_probe()

del_vqs() frees virtqueues, therefore cfv->vq_tx pointer should be checked
for NULL before calling it, not cfv->vdev. Also the current implementation
is redundant because the pointer cfv->vdev is dereferenced before it is
checked for NULL.

Fix this by checking cfv->vq_tx for NULL instead of cfv->vdev before
calling del_vqs().

Fixes: 0d2e1a2926b1 ("caif_virtio: Introduce caif over virtio")
Signed-off-by: Vitaliy Shevtsov <v.shevtsov@mt-integration.ru>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250227184716.4715-1-v.shevtsov@mt-integration.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/caif/caif_virtio.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
index 7fea00c7ca8a6..c60386bf2d1a4 100644
--- a/drivers/net/caif/caif_virtio.c
+++ b/drivers/net/caif/caif_virtio.c
@@ -745,7 +745,7 @@ static int cfv_probe(struct virtio_device *vdev)
 
 	if (cfv->vr_rx)
 		vdev->vringh_config->del_vrhs(cfv->vdev);
-	if (cfv->vdev)
+	if (cfv->vq_tx)
 		vdev->config->del_vqs(cfv->vdev);
 	free_netdev(netdev);
 	return err;

From cb380909ae3b1ebf14d6a455a4f92d7916d790cb Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 27 Feb 2025 15:06:30 -0800
Subject: [PATCH 1378/2753] vhost: return task creation error instead of NULL

Lets callers distinguish why the vhost task creation failed. No one
currently cares why it failed, so no real runtime change from this
patch, but that will not be the case for long.

Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-2-kbusch@meta.com>
Reviewed-by: Mike Christie <michael.christie@oracle.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c | 2 +-
 drivers/vhost/vhost.c  | 2 +-
 kernel/vhost_task.c    | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index d4ac4a1f8b81b..18ca1ea6dc240 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7471,7 +7471,7 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm_nx_huge_page_recovery_worker_kill,
 				      kvm, "kvm-nx-lpage-recovery");
 
-	if (!nx_thread)
+	if (IS_ERR(nx_thread))
 		return;
 
 	vhost_task_start(nx_thread);
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index 9ac25d08f473e..63612faeab727 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -666,7 +666,7 @@ static struct vhost_worker *vhost_worker_create(struct vhost_dev *dev)
 
 	vtsk = vhost_task_create(vhost_run_work_list, vhost_worker_killed,
 				 worker, name);
-	if (!vtsk)
+	if (IS_ERR(vtsk))
 		goto free_worker;
 
 	mutex_init(&worker->mutex);
diff --git a/kernel/vhost_task.c b/kernel/vhost_task.c
index 8800f5acc0071..2ef2e1b800916 100644
--- a/kernel/vhost_task.c
+++ b/kernel/vhost_task.c
@@ -133,7 +133,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *),
 
 	vtsk = kzalloc(sizeof(*vtsk), GFP_KERNEL);
 	if (!vtsk)
-		return NULL;
+		return ERR_PTR(-ENOMEM);
 	init_completion(&vtsk->exited);
 	mutex_init(&vtsk->exit_mutex);
 	vtsk->data = arg;
@@ -145,7 +145,7 @@ struct vhost_task *vhost_task_create(bool (*fn)(void *),
 	tsk = copy_process(NULL, 0, NUMA_NO_NODE, &args);
 	if (IS_ERR(tsk)) {
 		kfree(vtsk);
-		return NULL;
+		return ERR_PTR(PTR_ERR(tsk));
 	}
 
 	vtsk->task = tsk;

From 916b7f42b3b3b539a71c204a9b49fdc4ca92cd82 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 27 Feb 2025 15:06:31 -0800
Subject: [PATCH 1379/2753] kvm: retry nx_huge_page_recovery_thread creation

A VMM may send a non-fatal signal to its threads, including vCPU tasks,
at any time, and thus may signal vCPU tasks during KVM_RUN.  If a vCPU
task receives the signal while its trying to spawn the huge page recovery
vhost task, then KVM_RUN will fail due to copy_process() returning
-ERESTARTNOINTR.

Rework call_once() to mark the call complete if and only if the called
function succeeds, and plumb the function's true error code back to the
call_once() invoker.  This provides userspace with the correct, non-fatal
error code so that the VMM doesn't terminate the VM on -ENOMEM, and allows
subsequent KVM_RUN a succeed by virtue of retrying creation of the NX huge
page task.

Co-developed-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
[implemented the kvm user side]
Signed-off-by: Keith Busch <kbusch@kernel.org>
Message-ID: <20250227230631.303431-3-kbusch@meta.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
---
 arch/x86/kvm/mmu/mmu.c    | 10 ++++-----
 include/linux/call_once.h | 47 ++++++++++++++++++++++++++++-----------
 2 files changed, 38 insertions(+), 19 deletions(-)

diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 18ca1ea6dc240..8160870398b90 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -7460,7 +7460,7 @@ static bool kvm_nx_huge_page_recovery_worker(void *data)
 	return true;
 }
 
-static void kvm_mmu_start_lpage_recovery(struct once *once)
+static int kvm_mmu_start_lpage_recovery(struct once *once)
 {
 	struct kvm_arch *ka = container_of(once, struct kvm_arch, nx_once);
 	struct kvm *kvm = container_of(ka, struct kvm, arch);
@@ -7472,12 +7472,13 @@ static void kvm_mmu_start_lpage_recovery(struct once *once)
 				      kvm, "kvm-nx-lpage-recovery");
 
 	if (IS_ERR(nx_thread))
-		return;
+		return PTR_ERR(nx_thread);
 
 	vhost_task_start(nx_thread);
 
 	/* Make the task visible only once it is fully started. */
 	WRITE_ONCE(kvm->arch.nx_huge_page_recovery_thread, nx_thread);
+	return 0;
 }
 
 int kvm_mmu_post_init_vm(struct kvm *kvm)
@@ -7485,10 +7486,7 @@ int kvm_mmu_post_init_vm(struct kvm *kvm)
 	if (nx_hugepage_mitigation_hard_disabled)
 		return 0;
 
-	call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
-	if (!kvm->arch.nx_huge_page_recovery_thread)
-		return -ENOMEM;
-	return 0;
+	return call_once(&kvm->arch.nx_once, kvm_mmu_start_lpage_recovery);
 }
 
 void kvm_mmu_pre_destroy_vm(struct kvm *kvm)
diff --git a/include/linux/call_once.h b/include/linux/call_once.h
index 6261aa0b3fb00..13cd6469e7e56 100644
--- a/include/linux/call_once.h
+++ b/include/linux/call_once.h
@@ -26,20 +26,41 @@ do {									\
 	__once_init((once), #once, &__key);				\
 } while (0)
 
-static inline void call_once(struct once *once, void (*cb)(struct once *))
+/*
+ * call_once - Ensure a function has been called exactly once
+ *
+ * @once: Tracking struct
+ * @cb: Function to be called
+ *
+ * If @once has never completed successfully before, call @cb and, if
+ * it returns a zero or positive value, mark @once as completed.  Return
+ * the value returned by @cb
+ *
+ * If @once has completed succesfully before, return 0.
+ *
+ * The call to @cb is implicitly surrounded by a mutex, though for
+ * efficiency the * function avoids taking it after the first call.
+ */
+static inline int call_once(struct once *once, int (*cb)(struct once *))
 {
-        /* Pairs with atomic_set_release() below.  */
-        if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
-                return;
-
-        guard(mutex)(&once->lock);
-        WARN_ON(atomic_read(&once->state) == ONCE_RUNNING);
-        if (atomic_read(&once->state) != ONCE_NOT_STARTED)
-                return;
-
-        atomic_set(&once->state, ONCE_RUNNING);
-        cb(once);
-        atomic_set_release(&once->state, ONCE_COMPLETED);
+	int r, state;
+
+	/* Pairs with atomic_set_release() below.  */
+	if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
+		return 0;
+
+	guard(mutex)(&once->lock);
+	state = atomic_read(&once->state);
+	if (unlikely(state != ONCE_NOT_STARTED))
+		return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0;
+
+	atomic_set(&once->state, ONCE_RUNNING);
+	r = cb(once);
+	if (r < 0)
+		atomic_set(&once->state, ONCE_NOT_STARTED);
+	else
+		atomic_set_release(&once->state, ONCE_COMPLETED);
+	return r;
 }
 
 #endif /* _LINUX_CALL_ONCE_H */

From a2f925a2f62254119cdaa360cfc9c0424bccd531 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Fri, 28 Feb 2025 13:26:04 +0100
Subject: [PATCH 1380/2753] Revert "ata: libata-core: Add ATA_QUIRK_NOLPM for
 Samsung SSD 870 QVO drives"

This reverts commit cc77e2ce187d26cc66af3577bf896d7410eb25ab.

It was reported that adding ATA_QUIRK_NOLPM for Samsung SSD 870 QVO drives
breaks entering lower package states for certain systems.

It turns out that Samsung SSD 870 QVO actually has working LPM when using
a recent SSD firmware version.

The author of commit cc77e2ce187d ("ata: libata-core: Add ATA_QUIRK_NOLPM
for Samsung SSD 870 QVO drives") reported himself that only older SSD
firmware versions have broken LPM:
https://lore.kernel.org/stable/93c10d38-718c-459d-84a5-4d87680b4da7@debian.org/

Unfortunately, he did not specify which older firmware version he was using
which had broken LPM.

Let's revert this quirk, which has FW version field specified as NULL
(which means that it applies for all Samsung SSD 870 QVO firmware versions)
for now. Once the author reports which older firmware version(s) that are
broken, we can create a more fine grained quirk, which populates the FW
version field accordingly.

Fixes: cc77e2ce187d ("ata: libata-core: Add ATA_QUIRK_NOLPM for Samsung SSD 870 QVO drives")
Reported-by: Dieter Mummenschanz <dmummenschanz@web.de>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=219747
Link: https://lore.kernel.org/r/20250228122603.91814-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 63ec2f2184319..c085dd81ebe7f 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -4143,10 +4143,6 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 	{ "Samsung SSD 860*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },
-	{ "Samsung SSD 870 QVO*",	NULL,	ATA_QUIRK_NO_NCQ_TRIM |
-						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI |
-						ATA_QUIRK_NOLPM },
 	{ "Samsung SSD 870*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
 						ATA_QUIRK_NO_NCQ_ON_ATI },

From 2565e42539b120b81a68a58da961ce5d1e34eac8 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:11 +0100
Subject: [PATCH 1381/2753] perf/core: Fix pmus_lock vs. pmus_srcu ordering

Commit a63fbed776c7 ("perf/tracing/cpuhotplug: Fix locking order")
placed pmus_lock inside pmus_srcu, this makes perf_pmu_unregister()
trip lockdep.

Move the locking about such that only pmu_idr and pmus (list) are
modified while holding pmus_lock. This avoids doing synchronize_srcu()
while holding pmus_lock and all is well again.

Fixes: a63fbed776c7 ("perf/tracing/cpuhotplug: Fix locking order")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241104135517.679556858@infradead.org
---
 kernel/events/core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 6364319e2f888..11793d690cbb7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11939,6 +11939,8 @@ void perf_pmu_unregister(struct pmu *pmu)
 {
 	mutex_lock(&pmus_lock);
 	list_del_rcu(&pmu->entry);
+	idr_remove(&pmu_idr, pmu->type);
+	mutex_unlock(&pmus_lock);
 
 	/*
 	 * We dereference the pmu list under both SRCU and regular RCU, so
@@ -11948,7 +11950,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	idr_remove(&pmu_idr, pmu->type);
 	if (pmu_bus_running && pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		if (pmu->nr_addr_filters)
 			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
@@ -11956,7 +11957,6 @@ void perf_pmu_unregister(struct pmu *pmu)
 		put_device(pmu->dev);
 	}
 	free_pmu_context(pmu);
-	mutex_unlock(&pmus_lock);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);
 

From 003659fec9f6d8c04738cb74b5384398ae8a7e88 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Mon, 4 Nov 2024 14:39:12 +0100
Subject: [PATCH 1382/2753] perf/core: Fix perf_pmu_register() vs.
 perf_init_event()

There is a fairly obvious race between perf_init_event() doing
idr_find() and perf_pmu_register() doing idr_alloc() with an
incompletely initialized PMU pointer.

Avoid by doing idr_alloc() on a NULL pointer to register the id, and
swizzling the real struct pmu pointer at the end using idr_replace().

Also making sure to not set struct pmu members after publishing
the struct pmu, duh.

[ introduce idr_cmpxchg() in order to better handle the idr_replace()
  error case -- if it were to return an unexpected pointer, it will
  already have replaced the value and there is no going back. ]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20241104135517.858805880@infradead.org
---
 kernel/events/core.c | 28 ++++++++++++++++++++++++++--
 1 file changed, 26 insertions(+), 2 deletions(-)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 11793d690cbb7..823aa08249161 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -11830,6 +11830,21 @@ static int pmu_dev_alloc(struct pmu *pmu)
 static struct lock_class_key cpuctx_mutex;
 static struct lock_class_key cpuctx_lock;
 
+static bool idr_cmpxchg(struct idr *idr, unsigned long id, void *old, void *new)
+{
+	void *tmp, *val = idr_find(idr, id);
+
+	if (val != old)
+		return false;
+
+	tmp = idr_replace(idr, new, id);
+	if (IS_ERR(tmp))
+		return false;
+
+	WARN_ON_ONCE(tmp != val);
+	return true;
+}
+
 int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 {
 	int cpu, ret, max = PERF_TYPE_MAX;
@@ -11856,7 +11871,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (type >= 0)
 		max = type;
 
-	ret = idr_alloc(&pmu_idr, pmu, max, 0, GFP_KERNEL);
+	ret = idr_alloc(&pmu_idr, NULL, max, 0, GFP_KERNEL);
 	if (ret < 0)
 		goto free_pdc;
 
@@ -11864,6 +11879,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 
 	type = ret;
 	pmu->type = type;
+	atomic_set(&pmu->exclusive_cnt, 0);
 
 	if (pmu_bus_running && !pmu->dev) {
 		ret = pmu_dev_alloc(pmu);
@@ -11912,14 +11928,22 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 	if (!pmu->event_idx)
 		pmu->event_idx = perf_event_idx_default;
 
+	/*
+	 * Now that the PMU is complete, make it visible to perf_try_init_event().
+	 */
+	if (!idr_cmpxchg(&pmu_idr, pmu->type, NULL, pmu))
+		goto free_context;
 	list_add_rcu(&pmu->entry, &pmus);
-	atomic_set(&pmu->exclusive_cnt, 0);
+
 	ret = 0;
 unlock:
 	mutex_unlock(&pmus_lock);
 
 	return ret;
 
+free_context:
+	free_percpu(pmu->cpu_pmu_context);
+
 free_dev:
 	if (pmu->dev && pmu->dev != PMU_NULL_DEV) {
 		device_del(pmu->dev);

From c9ce148ea753bef66686460fa3cec6641cdfbb9f Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Sat, 1 Mar 2025 12:45:29 +0100
Subject: [PATCH 1383/2753] ALSA: seq: Avoid module auto-load handling at event
 delivery

snd_seq_client_use_ptr() is supposed to return the snd_seq_client
object for the given client ID, and it tries to handle the module
auto-loading when no matching object is found.  Although the module
handling is performed only conditionally with "!in_interrupt()", this
condition may be fragile, e.g. when the code is called from the ALSA
timer callback where the spinlock is temporarily disabled while the
irq is disabled.  Then his doesn't fit well and spews the error about
sleep from invalid context, as complained recently by syzbot.

Also, in general, handling the module-loading at each time if no
matching object is found is really an overkill.  It can be still
useful when performed at the top-level ioctl or proc reads, but it
shouldn't be done at event delivery at all.

For addressing the issues above, this patch disables the module
handling in snd_seq_client_use_ptr() in normal cases like event
deliveries, but allow only in limited and safe situations.
A new function client_load_and_use_ptr() is used for the cases where
the module loading can be done safely, instead.

Reported-by: syzbot+4cb9fad083898f54c517@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/67c272e5.050a0220.dc10f.0159.GAE@google.com
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250301114530.8975-1-tiwai@suse.de
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/core/seq/seq_clientmgr.c | 46 ++++++++++++++++++++++------------
 1 file changed, 30 insertions(+), 16 deletions(-)

diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
index cb66ec42a3f8a..706f53e39b53c 100644
--- a/sound/core/seq/seq_clientmgr.c
+++ b/sound/core/seq/seq_clientmgr.c
@@ -106,7 +106,7 @@ static struct snd_seq_client *clientptr(int clientid)
 	return clienttab[clientid];
 }
 
-struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
+static struct snd_seq_client *client_use_ptr(int clientid, bool load_module)
 {
 	unsigned long flags;
 	struct snd_seq_client *client;
@@ -126,7 +126,7 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	}
 	spin_unlock_irqrestore(&clients_lock, flags);
 #ifdef CONFIG_MODULES
-	if (!in_interrupt()) {
+	if (load_module) {
 		static DECLARE_BITMAP(client_requested, SNDRV_SEQ_GLOBAL_CLIENTS);
 		static DECLARE_BITMAP(card_requested, SNDRV_CARDS);
 
@@ -168,6 +168,20 @@ struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
 	return client;
 }
 
+/* get snd_seq_client object for the given id quickly */
+struct snd_seq_client *snd_seq_client_use_ptr(int clientid)
+{
+	return client_use_ptr(clientid, false);
+}
+
+/* get snd_seq_client object for the given id;
+ * if not found, retry after loading the modules
+ */
+static struct snd_seq_client *client_load_and_use_ptr(int clientid)
+{
+	return client_use_ptr(clientid, IS_ENABLED(CONFIG_MODULES));
+}
+
 /* Take refcount and perform ioctl_mutex lock on the given client;
  * used only for OSS sequencer
  * Unlock via snd_seq_client_ioctl_unlock() below
@@ -176,7 +190,7 @@ bool snd_seq_client_ioctl_lock(int clientid)
 {
 	struct snd_seq_client *client;
 
-	client = snd_seq_client_use_ptr(clientid);
+	client = client_load_and_use_ptr(clientid);
 	if (!client)
 		return false;
 	mutex_lock(&client->ioctl_mutex);
@@ -1195,7 +1209,7 @@ static int snd_seq_ioctl_running_mode(struct snd_seq_client *client, void  *arg)
 	int err = 0;
 
 	/* requested client number */
-	cptr = snd_seq_client_use_ptr(info->client);
+	cptr = client_load_and_use_ptr(info->client);
 	if (cptr == NULL)
 		return -ENOENT;		/* don't change !!! */
 
@@ -1257,7 +1271,7 @@ static int snd_seq_ioctl_get_client_info(struct snd_seq_client *client,
 	struct snd_seq_client *cptr;
 
 	/* requested client number */
-	cptr = snd_seq_client_use_ptr(client_info->client);
+	cptr = client_load_and_use_ptr(client_info->client);
 	if (cptr == NULL)
 		return -ENOENT;		/* don't change !!! */
 
@@ -1396,7 +1410,7 @@ static int snd_seq_ioctl_get_port_info(struct snd_seq_client *client, void *arg)
 	struct snd_seq_client *cptr;
 	struct snd_seq_client_port *port;
 
-	cptr = snd_seq_client_use_ptr(info->addr.client);
+	cptr = client_load_and_use_ptr(info->addr.client);
 	if (cptr == NULL)
 		return -ENXIO;
 
@@ -1503,10 +1517,10 @@ static int snd_seq_ioctl_subscribe_port(struct snd_seq_client *client,
 	struct snd_seq_client *receiver = NULL, *sender = NULL;
 	struct snd_seq_client_port *sport = NULL, *dport = NULL;
 
-	receiver = snd_seq_client_use_ptr(subs->dest.client);
+	receiver = client_load_and_use_ptr(subs->dest.client);
 	if (!receiver)
 		goto __end;
-	sender = snd_seq_client_use_ptr(subs->sender.client);
+	sender = client_load_and_use_ptr(subs->sender.client);
 	if (!sender)
 		goto __end;
 	sport = snd_seq_port_use_ptr(sender, subs->sender.port);
@@ -1871,7 +1885,7 @@ static int snd_seq_ioctl_get_client_pool(struct snd_seq_client *client,
 	struct snd_seq_client_pool *info = arg;
 	struct snd_seq_client *cptr;
 
-	cptr = snd_seq_client_use_ptr(info->client);
+	cptr = client_load_and_use_ptr(info->client);
 	if (cptr == NULL)
 		return -ENOENT;
 	memset(info, 0, sizeof(*info));
@@ -1975,7 +1989,7 @@ static int snd_seq_ioctl_get_subscription(struct snd_seq_client *client,
 	struct snd_seq_client_port *sport = NULL;
 
 	result = -EINVAL;
-	sender = snd_seq_client_use_ptr(subs->sender.client);
+	sender = client_load_and_use_ptr(subs->sender.client);
 	if (!sender)
 		goto __end;
 	sport = snd_seq_port_use_ptr(sender, subs->sender.port);
@@ -2006,7 +2020,7 @@ static int snd_seq_ioctl_query_subs(struct snd_seq_client *client, void *arg)
 	struct list_head *p;
 	int i;
 
-	cptr = snd_seq_client_use_ptr(subs->root.client);
+	cptr = client_load_and_use_ptr(subs->root.client);
 	if (!cptr)
 		goto __end;
 	port = snd_seq_port_use_ptr(cptr, subs->root.port);
@@ -2073,7 +2087,7 @@ static int snd_seq_ioctl_query_next_client(struct snd_seq_client *client,
 	if (info->client < 0)
 		info->client = 0;
 	for (; info->client < SNDRV_SEQ_MAX_CLIENTS; info->client++) {
-		cptr = snd_seq_client_use_ptr(info->client);
+		cptr = client_load_and_use_ptr(info->client);
 		if (cptr)
 			break; /* found */
 	}
@@ -2096,7 +2110,7 @@ static int snd_seq_ioctl_query_next_port(struct snd_seq_client *client,
 	struct snd_seq_client *cptr;
 	struct snd_seq_client_port *port = NULL;
 
-	cptr = snd_seq_client_use_ptr(info->addr.client);
+	cptr = client_load_and_use_ptr(info->addr.client);
 	if (cptr == NULL)
 		return -ENXIO;
 
@@ -2193,7 +2207,7 @@ static int snd_seq_ioctl_client_ump_info(struct snd_seq_client *caller,
 		size = sizeof(struct snd_ump_endpoint_info);
 	else
 		size = sizeof(struct snd_ump_block_info);
-	cptr = snd_seq_client_use_ptr(client);
+	cptr = client_load_and_use_ptr(client);
 	if (!cptr)
 		return -ENOENT;
 
@@ -2475,7 +2489,7 @@ int snd_seq_kernel_client_enqueue(int client, struct snd_seq_event *ev,
 	if (check_event_type_and_length(ev))
 		return -EINVAL;
 
-	cptr = snd_seq_client_use_ptr(client);
+	cptr = client_load_and_use_ptr(client);
 	if (cptr == NULL)
 		return -EINVAL;
 	
@@ -2707,7 +2721,7 @@ void snd_seq_info_clients_read(struct snd_info_entry *entry,
 
 	/* list the client table */
 	for (c = 0; c < SNDRV_SEQ_MAX_CLIENTS; c++) {
-		client = snd_seq_client_use_ptr(c);
+		client = client_load_and_use_ptr(c);
 		if (client == NULL)
 			continue;
 		if (client->type == NO_CLIENT) {

From 7a68b55ff39b0a1638acb1694c185d49f6077a0d Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Thu, 27 Feb 2025 18:05:25 +0000
Subject: [PATCH 1384/2753] KVM: arm64: Initialize HCR_EL2.E2H early

On CPUs without FEAT_E2H0, HCR_EL2.E2H is RES1, but may reset to an
UNKNOWN value out of reset and consequently may not read as 1 unless it
has been explicitly initialized.

We handled this for the head.S boot code in commits:

  3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
  b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")

Unfortunately, we forgot to apply a similar fix to the KVM PSCI entry
points used when relaying CPU_ON, CPU_SUSPEND, and SYSTEM SUSPEND. When
KVM is entered via these entry points, the value of HCR_EL2.E2H may be
consumed before it has been initialized (e.g. by the 'init_el2_state'
macro).

Initialize HCR_EL2.E2H early in these paths such that it can be consumed
reliably. The existing code in head.S is factored out into a new
'init_el2_hcr' macro, and this is used in the __kvm_hyp_init_cpu()
function common to all the relevant PSCI entry points.

For clarity, I've tweaked the assembly used to check whether
ID_AA64MMFR4_EL1.E2H0 is negative. The bitfield is extracted as a signed
value, and this is checked with a signed-greater-or-equal (GE) comparison.

As the hyp code will reconfigure HCR_EL2 later in ___kvm_hyp_init(), all
bits other than E2H are initialized to zero in __kvm_hyp_init_cpu().

Fixes: 3944382fa6f22b54 ("arm64: Treat HCR_EL2.E2H as RES1 when ID_AA64MMFR4_EL1.E2H0 is negative")
Fixes: b3320142f3db9b3f ("arm64: Fix early handling of FEAT_E2H0 not being implemented")
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250227180526.1204723-2-mark.rutland@arm.com
[maz: fixed LT->GE thinko]
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h | 26 ++++++++++++++++++++++++++
 arch/arm64/kernel/head.S           | 19 +------------------
 arch/arm64/kvm/hyp/nvhe/hyp-init.S |  8 +++++++-
 3 files changed, 34 insertions(+), 19 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 25e1626517500..56034a394b437 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -16,6 +16,32 @@
 #include <asm/sysreg.h>
 #include <linux/irqchip/arm-gic-v3.h>
 
+.macro init_el2_hcr	val
+	mov_q	x0, \val
+
+	/*
+	 * Compliant CPUs advertise their VHE-onlyness with
+	 * ID_AA64MMFR4_EL1.E2H0 < 0. On such CPUs HCR_EL2.E2H is RES1, but it
+	 * can reset into an UNKNOWN state and might not read as 1 until it has
+	 * been initialized explicitly.
+	 *
+	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
+	 * don't advertise it (they predate this relaxation).
+	 *
+	 * Initalize HCR_EL2.E2H so that later code can rely upon HCR_EL2.E2H
+	 * indicating whether the CPU is running in E2H mode.
+	 */
+	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
+	sbfx	x1, x1, #ID_AA64MMFR4_EL1_E2H0_SHIFT, #ID_AA64MMFR4_EL1_E2H0_WIDTH
+	cmp	x1, #0
+	b.ge	.LnVHE_\@
+
+	orr	x0, x0, #HCR_E2H
+.LnVHE_\@:
+	msr	hcr_el2, x0
+	isb
+.endm
+
 .macro __init_el2_sctlr
 	mov_q	x0, INIT_SCTLR_EL2_MMU_OFF
 	msr	sctlr_el2, x0
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 5ab1970ee5436..2d56459d6c94c 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -298,25 +298,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el2, x0
 	isb
 0:
-	mov_q	x0, HCR_HOST_NVHE_FLAGS
-
-	/*
-	 * Compliant CPUs advertise their VHE-onlyness with
-	 * ID_AA64MMFR4_EL1.E2H0 < 0. HCR_EL2.E2H can be
-	 * RES1 in that case. Publish the E2H bit early so that
-	 * it can be picked up by the init_el2_state macro.
-	 *
-	 * Fruity CPUs seem to have HCR_EL2.E2H set to RAO/WI, but
-	 * don't advertise it (they predate this relaxation).
-	 */
-	mrs_s	x1, SYS_ID_AA64MMFR4_EL1
-	tbz	x1, #(ID_AA64MMFR4_EL1_E2H0_SHIFT + ID_AA64MMFR4_EL1_E2H0_WIDTH - 1), 1f
-
-	orr	x0, x0, #HCR_E2H
-1:
-	msr	hcr_el2, x0
-	isb
 
+	init_el2_hcr	HCR_HOST_NVHE_FLAGS
 	init_el2_state
 
 	/* Hypervisor stub */
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index fc18662260676..3fb5504a7d7fc 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -73,8 +73,12 @@ __do_hyp_init:
 	eret
 SYM_CODE_END(__kvm_hyp_init)
 
+/*
+ * Initialize EL2 CPU state to sane values.
+ *
+ * HCR_EL2.E2H must have been initialized already.
+ */
 SYM_CODE_START_LOCAL(__kvm_init_el2_state)
-	/* Initialize EL2 CPU state to sane values. */
 	init_el2_state				// Clobbers x0..x2
 	finalise_el2_state
 	ret
@@ -206,6 +210,8 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 2:	msr	SPsel, #1			// We want to use SP_EL{1,2}
 
+	init_el2_hcr	0
+
 	bl	__kvm_init_el2_state
 
 	__init_el2_nvhe_prepare_eret

From 3855a7b91d42ebf3513b7ccffc44807274978b3d Mon Sep 17 00:00:00 2001
From: Ahmed Genidi <ahmed.genidi@arm.com>
Date: Thu, 27 Feb 2025 18:05:26 +0000
Subject: [PATCH 1385/2753] KVM: arm64: Initialize SCTLR_EL1 in
 __kvm_hyp_init_cpu()

When KVM is in protected mode, host calls to PSCI are proxied via EL2,
and cold entries from CPU_ON, CPU_SUSPEND, and SYSTEM_SUSPEND bounce
through __kvm_hyp_init_cpu() at EL2 before entering the host kernel's
entry point at EL1. While __kvm_hyp_init_cpu() initializes SPSR_EL2 for
the exception return to EL1, it does not initialize SCTLR_EL1.

Due to this, it's possible to enter EL1 with SCTLR_EL1 in an UNKNOWN
state. In practice this has been seen to result in kernel crashes after
CPU_ON as a result of SCTLR_EL1.M being 1 in violation of the initial
core configuration specified by PSCI.

Fix this by initializing SCTLR_EL1 for cold entry to the host kernel.
As it's necessary to write to SCTLR_EL12 in VHE mode, this
initialization is moved into __kvm_host_psci_cpu_entry() where we can
use write_sysreg_el1().

The remnants of the '__init_el2_nvhe_prepare_eret' macro are folded into
its only caller, as this is clearer than having the macro.

Fixes: cdf367192766ad11 ("KVM: arm64: Intercept host's CPU_ON SMCs")
Reported-by: Leo Yan <leo.yan@arm.com>
Signed-off-by: Ahmed Genidi <ahmed.genidi@arm.com>
[ Mark: clarify commit message, handle E2H, move to C, remove macro ]
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Ahmed Genidi <ahmed.genidi@arm.com>
Cc: Ben Horgan <ben.horgan@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Leo Yan <leo.yan@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: Will Deacon <will@kernel.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lore.kernel.org/r/20250227180526.1204723-3-mark.rutland@arm.com
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/el2_setup.h   | 5 -----
 arch/arm64/kernel/head.S             | 3 ++-
 arch/arm64/kvm/hyp/nvhe/hyp-init.S   | 2 --
 arch/arm64/kvm/hyp/nvhe/psci-relay.c | 3 +++
 4 files changed, 5 insertions(+), 8 deletions(-)

diff --git a/arch/arm64/include/asm/el2_setup.h b/arch/arm64/include/asm/el2_setup.h
index 56034a394b437..555c613fd2324 100644
--- a/arch/arm64/include/asm/el2_setup.h
+++ b/arch/arm64/include/asm/el2_setup.h
@@ -270,11 +270,6 @@
 .Lskip_gcs_\@:
 .endm
 
-.macro __init_el2_nvhe_prepare_eret
-	mov	x0, #INIT_PSTATE_EL1
-	msr	spsr_el2, x0
-.endm
-
 .macro __init_el2_mpam
 	/* Memory Partitioning And Monitoring: disable EL2 traps */
 	mrs	x1, id_aa64pfr0_el1
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index 2d56459d6c94c..2ce73525de2c9 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -322,7 +322,8 @@ SYM_INNER_LABEL(init_el2, SYM_L_LOCAL)
 	msr	sctlr_el1, x1
 	mov	x2, xzr
 3:
-	__init_el2_nvhe_prepare_eret
+	mov	x0, #INIT_PSTATE_EL1
+	msr	spsr_el2, x0
 
 	mov	w0, #BOOT_CPU_MODE_EL2
 	orr	x0, x0, x2
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 3fb5504a7d7fc..f8af11189572f 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -214,8 +214,6 @@ SYM_CODE_START_LOCAL(__kvm_hyp_init_cpu)
 
 	bl	__kvm_init_el2_state
 
-	__init_el2_nvhe_prepare_eret
-
 	/* Enable MMU, set vectors and stack. */
 	mov	x0, x28
 	bl	___kvm_hyp_init			// Clobbers x0..x2
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 9c2ce1e0e99a5..c3e196fb8b18f 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -218,6 +218,9 @@ asmlinkage void __noreturn __kvm_host_psci_cpu_entry(bool is_cpu_on)
 	if (is_cpu_on)
 		release_boot_args(boot_args);
 
+	write_sysreg_el1(INIT_SCTLR_EL1_MMU_OFF, SYS_SCTLR);
+	write_sysreg(INIT_PSTATE_EL1, SPSR_EL2);
+
 	__host_enter(host_ctxt);
 }
 

From e04918dc594669068f5d59d567d08db531167188 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sun, 2 Mar 2025 15:18:24 +0800
Subject: [PATCH 1386/2753] cred: Fix RCU warnings in override/revert_creds

Fix RCU warnings in override_creds and revert_creds by turning
the RCU pointer into a normal pointer using rcu_replace_pointer.

These warnings were previously private to the cred code, but due
to the move into the header file they are now polluting unrelated
subsystems.

Fixes: 49dffdfde462 ("cred: Add a light version of override/revert_creds()")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Link: https://lore.kernel.org/r/Z8QGQGW0IaSklKG7@gondor.apana.org.au
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/cred.h | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 0c3c4b16b469c..5658a3bfe803c 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -172,18 +172,12 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 
 static inline const struct cred *override_creds(const struct cred *override_cred)
 {
-	const struct cred *old = current->cred;
-
-	rcu_assign_pointer(current->cred, override_cred);
-	return old;
+	return rcu_replace_pointer(current->cred, override_cred, 1);
 }
 
 static inline const struct cred *revert_creds(const struct cred *revert_cred)
 {
-	const struct cred *override_cred = current->cred;
-
-	rcu_assign_pointer(current->cred, revert_cred);
-	return override_cred;
+	return rcu_replace_pointer(current->cred, revert_cred, 1);
 }
 
 /**

From 6b6e2e8fd0de3fa7c6f4f8fe6841b01770b2e7bc Mon Sep 17 00:00:00 2001
From: Titus Rwantare <titusr@google.com>
Date: Thu, 27 Feb 2025 22:24:55 +0000
Subject: [PATCH 1387/2753] hwmon: (pmbus) Initialise page count in
 pmbus_identify()

The `pmbus_identify()` function fails to correctly determine the number
of supported pages on PMBus devices. This occurs because `info->pages`
is implicitly zero-initialised, and `pmbus_set_page()` does not perform
writes to the page register if `info->pages` is not yet initialised.
Without this patch, `info->pages` is always set to the maximum after
scanning.

This patch initialises `info->pages` to `PMBUS_PAGES` before the probing
loop, enabling `pmbus_set_page()` writes to make it out onto the bus
correctly identifying the number of pages. `PMBUS_PAGES` seemed like a
reasonable non-zero number because that's the current result of the
identification process.

Testing was done with a PMBus device in QEMU.

Signed-off-by: Titus Rwantare <titusr@google.com>
Fixes: 442aba78728e7 ("hwmon: PMBus device driver")
Link: https://lore.kernel.org/r/20250227222455.2583468-1-titusr@google.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/pmbus/pmbus.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hwmon/pmbus/pmbus.c b/drivers/hwmon/pmbus/pmbus.c
index 77cf268e7d2d6..920cd5408141a 100644
--- a/drivers/hwmon/pmbus/pmbus.c
+++ b/drivers/hwmon/pmbus/pmbus.c
@@ -103,6 +103,8 @@ static int pmbus_identify(struct i2c_client *client,
 		if (pmbus_check_byte_register(client, 0, PMBUS_PAGE)) {
 			int page;
 
+			info->pages = PMBUS_PAGES;
+
 			for (page = 1; page < PMBUS_PAGES; page++) {
 				if (pmbus_set_page(client, page, 0xff) < 0)
 					break;

From 1c7932d5ae0f5c22fa52ac811b4c427bbca5aff5 Mon Sep 17 00:00:00 2001
From: Maud Spierings <maudspierings@gocontroll.com>
Date: Thu, 27 Feb 2025 13:57:53 +0100
Subject: [PATCH 1388/2753] hwmon: (ntc_thermistor) Fix the ncpXXxh103 sensor
 table

I could not find a single table that has the values currently present in
the table, change it to the actual values that can be found in [1]/[2]
and [3] (page 15 column 2)

[1]: https://www.murata.com/products/productdetail?partno=NCP15XH103F03RC
[2]: https://www.murata.com/products/productdata/8796836626462/NTHCG83.txt?1437969843000
[3]: https://nl.mouser.com/datasheet/2/281/r44e-522712.pdf

Fixes: 54ce3a0d8011 ("hwmon: (ntc_thermistor) Add support for ncpXXxh103")
Signed-off-by: Maud Spierings <maudspierings@gocontroll.com>
Link: https://lore.kernel.org/r/20250227-ntc_thermistor_fixes-v1-3-70fa73200b52@gocontroll.com
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ntc_thermistor.c | 66 +++++++++++++++++-----------------
 1 file changed, 33 insertions(+), 33 deletions(-)

diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
index b5352900463fb..0d29c8f97ba7c 100644
--- a/drivers/hwmon/ntc_thermistor.c
+++ b/drivers/hwmon/ntc_thermistor.c
@@ -181,40 +181,40 @@ static const struct ntc_compensation ncpXXwf104[] = {
 };
 
 static const struct ntc_compensation ncpXXxh103[] = {
-	{ .temp_c	= -40, .ohm	= 247565 },
-	{ .temp_c	= -35, .ohm	= 181742 },
-	{ .temp_c	= -30, .ohm	= 135128 },
-	{ .temp_c	= -25, .ohm	= 101678 },
-	{ .temp_c	= -20, .ohm	= 77373 },
-	{ .temp_c	= -15, .ohm	= 59504 },
-	{ .temp_c	= -10, .ohm	= 46222 },
-	{ .temp_c	= -5, .ohm	= 36244 },
-	{ .temp_c	= 0, .ohm	= 28674 },
-	{ .temp_c	= 5, .ohm	= 22878 },
-	{ .temp_c	= 10, .ohm	= 18399 },
-	{ .temp_c	= 15, .ohm	= 14910 },
-	{ .temp_c	= 20, .ohm	= 12169 },
+	{ .temp_c	= -40, .ohm	= 195652 },
+	{ .temp_c	= -35, .ohm	= 148171 },
+	{ .temp_c	= -30, .ohm	= 113347 },
+	{ .temp_c	= -25, .ohm	= 87559 },
+	{ .temp_c	= -20, .ohm	= 68237 },
+	{ .temp_c	= -15, .ohm	= 53650 },
+	{ .temp_c	= -10, .ohm	= 42506 },
+	{ .temp_c	= -5, .ohm	= 33892 },
+	{ .temp_c	= 0, .ohm	= 27219 },
+	{ .temp_c	= 5, .ohm	= 22021 },
+	{ .temp_c	= 10, .ohm	= 17926 },
+	{ .temp_c	= 15, .ohm	= 14674 },
+	{ .temp_c	= 20, .ohm	= 12081 },
 	{ .temp_c	= 25, .ohm	= 10000 },
-	{ .temp_c	= 30, .ohm	= 8271 },
-	{ .temp_c	= 35, .ohm	= 6883 },
-	{ .temp_c	= 40, .ohm	= 5762 },
-	{ .temp_c	= 45, .ohm	= 4851 },
-	{ .temp_c	= 50, .ohm	= 4105 },
-	{ .temp_c	= 55, .ohm	= 3492 },
-	{ .temp_c	= 60, .ohm	= 2985 },
-	{ .temp_c	= 65, .ohm	= 2563 },
-	{ .temp_c	= 70, .ohm	= 2211 },
-	{ .temp_c	= 75, .ohm	= 1915 },
-	{ .temp_c	= 80, .ohm	= 1666 },
-	{ .temp_c	= 85, .ohm	= 1454 },
-	{ .temp_c	= 90, .ohm	= 1275 },
-	{ .temp_c	= 95, .ohm	= 1121 },
-	{ .temp_c	= 100, .ohm	= 990 },
-	{ .temp_c	= 105, .ohm	= 876 },
-	{ .temp_c	= 110, .ohm	= 779 },
-	{ .temp_c	= 115, .ohm	= 694 },
-	{ .temp_c	= 120, .ohm	= 620 },
-	{ .temp_c	= 125, .ohm	= 556 },
+	{ .temp_c	= 30, .ohm	= 8315 },
+	{ .temp_c	= 35, .ohm	= 6948 },
+	{ .temp_c	= 40, .ohm	= 5834 },
+	{ .temp_c	= 45, .ohm	= 4917 },
+	{ .temp_c	= 50, .ohm	= 4161 },
+	{ .temp_c	= 55, .ohm	= 3535 },
+	{ .temp_c	= 60, .ohm	= 3014 },
+	{ .temp_c	= 65, .ohm	= 2586 },
+	{ .temp_c	= 70, .ohm	= 2228 },
+	{ .temp_c	= 75, .ohm	= 1925 },
+	{ .temp_c	= 80, .ohm	= 1669 },
+	{ .temp_c	= 85, .ohm	= 1452 },
+	{ .temp_c	= 90, .ohm	= 1268 },
+	{ .temp_c	= 95, .ohm	= 1110 },
+	{ .temp_c	= 100, .ohm	= 974 },
+	{ .temp_c	= 105, .ohm	= 858 },
+	{ .temp_c	= 110, .ohm	= 758 },
+	{ .temp_c	= 115, .ohm	= 672 },
+	{ .temp_c	= 120, .ohm	= 596 },
+	{ .temp_c	= 125, .ohm	= 531 },
 };
 
 /*

From e278d5e8aef4c0a1d9a9fa8b8910d713a89aa800 Mon Sep 17 00:00:00 2001
From: Erik Schumacher <erik.schumacher@iris-sensing.com>
Date: Mon, 24 Feb 2025 09:19:04 +0000
Subject: [PATCH 1389/2753] hwmon: (ad7314) Validate leading zero bits and
 return error

Leading zero bits are sent on the bus before the temperature value is
transmitted. If any of these bits are high, the connection might be
unstable or there could be no AD7314 / ADT730x (or compatible) at all.
Return -EIO in that case.

Signed-off-by: Erik Schumacher <erik.schumacher@iris-sensing.com>
Fixes: 4f3a659581cab ("hwmon: AD7314 driver (ported from IIO)")
Link: https://lore.kernel.org/r/24a50c2981a318580aca8f50d23be7987b69ea00.camel@iris-sensing.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/ad7314.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/hwmon/ad7314.c b/drivers/hwmon/ad7314.c
index 7802bbf5f9587..59424103f6348 100644
--- a/drivers/hwmon/ad7314.c
+++ b/drivers/hwmon/ad7314.c
@@ -22,11 +22,13 @@
  */
 #define AD7314_TEMP_MASK		0x7FE0
 #define AD7314_TEMP_SHIFT		5
+#define AD7314_LEADING_ZEROS_MASK	BIT(15)
 
 /*
  * ADT7301 and ADT7302 temperature masks
  */
 #define ADT7301_TEMP_MASK		0x3FFF
+#define ADT7301_LEADING_ZEROS_MASK	(BIT(15) | BIT(14))
 
 enum ad7314_variant {
 	adt7301,
@@ -65,12 +67,20 @@ static ssize_t ad7314_temperature_show(struct device *dev,
 		return ret;
 	switch (spi_get_device_id(chip->spi_dev)->driver_data) {
 	case ad7314:
+		if (ret & AD7314_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		data = (ret & AD7314_TEMP_MASK) >> AD7314_TEMP_SHIFT;
 		data = sign_extend32(data, 9);
 
 		return sprintf(buf, "%d\n", 250 * data);
 	case adt7301:
 	case adt7302:
+		if (ret & ADT7301_LEADING_ZEROS_MASK) {
+			/* Invalid read-out, leading zero part is missing */
+			return -EIO;
+		}
 		/*
 		 * Documented as a 13 bit twos complement register
 		 * with a sign bit - which is a 14 bit 2's complement

From 7eb172143d5508b4da468ed59ee857c6e5e01da6 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 2 Mar 2025 11:48:20 -0800
Subject: [PATCH 1390/2753] Linux 6.14-rc5

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 30dab4c8b0120..70bdbf2218fc5 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From fd5ba38390c59e1c147480ae49b6133c4ac24001 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Wed, 26 Feb 2025 15:19:18 +0900
Subject: [PATCH 1391/2753] tracing: probe-events: Remove unused
 MAX_ARG_BUF_LEN macro

Commit 18b1e870a496 ("tracing/probes: Add $arg* meta argument for all
function args") introduced MAX_ARG_BUF_LEN but it is not used.
Remove it.

Link: https://lore.kernel.org/all/174055075876.4079315.8805416872155957588.stgit@mhiramat.tok.corp.google.com/

Fixes: 18b1e870a496 ("tracing/probes: Add $arg* meta argument for all function args")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_probe.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index c47ca002347a7..96792bc4b0924 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -36,7 +36,6 @@
 #define MAX_BTF_ARGS_LEN	128
 #define MAX_DENTRY_ARGS_LEN	256
 #define MAX_STRING_SIZE		PATH_MAX
-#define MAX_ARG_BUF_LEN		(MAX_TRACE_ARGS * MAX_ARG_NAME_LEN)
 
 /* Reserved field names */
 #define FIELD_STRING_IP		"__probe_ip"

From 4dd541f9d9e4d8cdfa9797e68d893b0c27e4c46c Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Sat, 15 Feb 2025 11:01:49 +0900
Subject: [PATCH 1392/2753] MAINTAINERS: update email address in cifs and ksmbd
 entry

Steve mainly checks his email through his gmail address.
I also check issues through another email address.

Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 MAINTAINERS | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8e0736dc2ee0e..ca11a553d4121 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5775,6 +5775,7 @@ X:	drivers/clk/clkdev.c
 
 COMMON INTERNET FILE SYSTEM CLIENT (CIFS and SMB3)
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Paulo Alcantara <pc@manguebit.com> (DFS, global name space)
 R:	Ronnie Sahlberg <ronniesahlberg@gmail.com> (directory leases, sparse files)
 R:	Shyam Prasad N <sprasad@microsoft.com> (multichannel)
@@ -12655,7 +12656,9 @@ F:	tools/testing/selftests/
 
 KERNEL SMB3 SERVER (KSMBD)
 M:	Namjae Jeon <linkinjeon@kernel.org>
+M:	Namjae Jeon <linkinjeon@samba.org>
 M:	Steve French <sfrench@samba.org>
+M:	Steve French <smfrench@gmail.com>
 R:	Sergey Senozhatsky <senozhatsky@chromium.org>
 R:	Tom Talpey <tom@talpey.com>
 L:	linux-cifs@vger.kernel.org

From d6e13e19063db24f94b690159d0633aaf72a0f03 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Tue, 18 Feb 2025 22:49:50 +0900
Subject: [PATCH 1393/2753] ksmbd: fix out-of-bounds in parse_sec_desc()

If osidoffset, gsidoffset and dacloffset could be greater than smb_ntsd
struct size. If it is smaller, It could cause slab-out-of-bounds.
And when validating sid, It need to check it included subauth array size.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smbacl.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index d39d3e553366d..89415b02dd649 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -807,6 +807,13 @@ static int parse_sid(struct smb_sid *psid, char *end_of_acl)
 		return -EINVAL;
 	}
 
+	if (!psid->num_subauth)
+		return 0;
+
+	if (psid->num_subauth > SID_MAX_SUB_AUTHORITIES ||
+	    end_of_acl < (char *)psid + 8 + sizeof(__le32) * psid->num_subauth)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -848,6 +855,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 	pntsd->type = cpu_to_le16(DACL_PRESENT);
 
 	if (pntsd->osidoffset) {
+		if (le32_to_cpu(pntsd->osidoffset) < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		rc = parse_sid(owner_sid_ptr, end_of_acl);
 		if (rc) {
 			pr_err("%s: Error %d parsing Owner SID\n", __func__, rc);
@@ -863,6 +873,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 	}
 
 	if (pntsd->gsidoffset) {
+		if (le32_to_cpu(pntsd->gsidoffset) < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		rc = parse_sid(group_sid_ptr, end_of_acl);
 		if (rc) {
 			pr_err("%s: Error %d mapping Owner SID to gid\n",
@@ -884,6 +897,9 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 		pntsd->type |= cpu_to_le16(DACL_PROTECTED);
 
 	if (dacloffset) {
+		if (dacloffset < sizeof(struct smb_ntsd))
+			return -EINVAL;
+
 		parse_dacl(idmap, dacl_ptr, end_of_acl,
 			   owner_sid_ptr, group_sid_ptr, fattr);
 	}

From e2ff19f0b7a30e03516e6eb73b948e27a55bc9d2 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 21 Feb 2025 14:16:23 +0900
Subject: [PATCH 1394/2753] ksmbd: fix type confusion via race condition when
 using ipc_msg_send_request

req->handle is allocated using ksmbd_acquire_id(&ipc_ida), based on
ida_alloc. req->handle from ksmbd_ipc_login_request and
FSCTL_PIPE_TRANSCEIVE ioctl can be same and it could lead to type confusion
between messages, resulting in access to unexpected parts of memory after
an incorrect delivery. ksmbd check type of ipc response but missing add
continue to check next ipc reponse.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/transport_ipc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/smb/server/transport_ipc.c b/fs/smb/server/transport_ipc.c
index 0460ebea6ff02..3f185ae60dc51 100644
--- a/fs/smb/server/transport_ipc.c
+++ b/fs/smb/server/transport_ipc.c
@@ -281,6 +281,7 @@ static int handle_response(int type, void *payload, size_t sz)
 		if (entry->type + 1 != type) {
 			pr_err("Waiting for IPC type %d, got %d. Ignore.\n",
 			       entry->type + 1, type);
+			continue;
 		}
 
 		entry->response = kvzalloc(sz, KSMBD_DEFAULT_GFP);

From 84d2d1641b71dec326e8736a749b7ee76a9599fc Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 26 Feb 2025 15:44:02 +0900
Subject: [PATCH 1395/2753] ksmbd: fix use-after-free in smb2_lock

If smb_lock->zero_len has value, ->llist of smb_lock is not delete and
flock is old one. It will cause use-after-free on error handling
routine.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index f1efcd0274750..35bed8fc1b970 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7458,13 +7458,13 @@ int smb2_lock(struct ksmbd_work *work)
 		}
 
 no_check_cl:
+		flock = smb_lock->fl;
+		list_del(&smb_lock->llist);
+
 		if (smb_lock->zero_len) {
 			err = 0;
 			goto skip;
 		}
-
-		flock = smb_lock->fl;
-		list_del(&smb_lock->llist);
 retry:
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:

From e26e2d2e15daf1ab33e0135caf2304a0cfa2744b Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Thu, 27 Feb 2025 15:49:10 +0900
Subject: [PATCH 1396/2753] ksmbd: fix bug on trap in smb2_lock

If lock count is greater than 1, flags could be old value.
It should be checked with flags of smb_lock, not flags.
It will cause bug-on trap from locks_free_lock in error handling
routine.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smb2pdu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 35bed8fc1b970..c53121538990e 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7468,7 +7468,7 @@ int smb2_lock(struct ksmbd_work *work)
 retry:
 		rc = vfs_lock_file(filp, smb_lock->cmd, flock, NULL);
 skip:
-		if (flags & SMB2_LOCKFLAG_UNLOCK) {
+		if (smb_lock->flags & SMB2_LOCKFLAG_UNLOCK) {
 			if (!rc) {
 				ksmbd_debug(SMB, "File unlocked\n");
 			} else if (rc == -ENOENT) {

From 62e7dd0a39c2d0d7ff03274c36df971f1b3d2d0d Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 23:26:09 +0900
Subject: [PATCH 1397/2753] smb: common: change the data type of num_aces to
 le16

2.4.5 in [MS-DTYP].pdf describe the data type of num_aces as le16.

AceCount (2 bytes): An unsigned 16-bit integer that specifies the count
of the number of ACE records in the ACL.

Change it to le16 and add reserved field to smb_acl struct.

Reported-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Tested-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c | 26 +++++++++++++-------------
 fs/smb/common/smbacl.h  |  3 ++-
 fs/smb/server/smbacl.c  | 31 ++++++++++++++++---------------
 fs/smb/server/smbacl.h  |  2 +-
 4 files changed, 32 insertions(+), 30 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 699a3f76d0834..7d953208046af 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -763,7 +763,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 		       struct cifs_fattr *fattr, bool mode_from_special_sid)
 {
 	int i;
-	int num_aces = 0;
+	u16 num_aces = 0;
 	int acl_size;
 	char *acl_base;
 	struct smb_ace **ppace;
@@ -785,7 +785,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 
 	cifs_dbg(NOISY, "DACL revision %d size %d num aces %d\n",
 		 le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
-		 le32_to_cpu(pdacl->num_aces));
+		 le16_to_cpu(pdacl->num_aces));
 
 	/* reset rwx permissions for user/group/other.
 	   Also, if num_aces is 0 i.e. DACL has no ACEs,
@@ -795,7 +795,7 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	acl_base = (char *)pdacl;
 	acl_size = sizeof(struct smb_acl);
 
-	num_aces = le32_to_cpu(pdacl->num_aces);
+	num_aces = le16_to_cpu(pdacl->num_aces);
 	if (num_aces > 0) {
 		umode_t denied_mode = 0;
 
@@ -937,12 +937,12 @@ unsigned int setup_special_user_owner_ACE(struct smb_ace *pntace)
 static void populate_new_aces(char *nacl_base,
 		struct smb_sid *pownersid,
 		struct smb_sid *pgrpsid,
-		__u64 *pnmode, u32 *pnum_aces, u16 *pnsize,
+		__u64 *pnmode, u16 *pnum_aces, u16 *pnsize,
 		bool modefromsid,
 		bool posix)
 {
 	__u64 nmode;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	u16 nsize = 0;
 	__u64 user_mode;
 	__u64 group_mode;
@@ -1050,7 +1050,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
 	u16 size = 0;
 	struct smb_ace *pntace = NULL;
 	char *acl_base = NULL;
-	u32 src_num_aces = 0;
+	u16 src_num_aces = 0;
 	u16 nsize = 0;
 	struct smb_ace *pnntace = NULL;
 	char *nacl_base = NULL;
@@ -1058,7 +1058,7 @@ static __u16 replace_sids_and_copy_aces(struct smb_acl *pdacl, struct smb_acl *p
 
 	acl_base = (char *)pdacl;
 	size = sizeof(struct smb_acl);
-	src_num_aces = le32_to_cpu(pdacl->num_aces);
+	src_num_aces = le16_to_cpu(pdacl->num_aces);
 
 	nacl_base = (char *)pndacl;
 	nsize = sizeof(struct smb_acl);
@@ -1090,11 +1090,11 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 	u16 size = 0;
 	struct smb_ace *pntace = NULL;
 	char *acl_base = NULL;
-	u32 src_num_aces = 0;
+	u16 src_num_aces = 0;
 	u16 nsize = 0;
 	struct smb_ace *pnntace = NULL;
 	char *nacl_base = NULL;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	bool new_aces_set = false;
 
 	/* Assuming that pndacl and pnmode are never NULL */
@@ -1112,7 +1112,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 
 	acl_base = (char *)pdacl;
 	size = sizeof(struct smb_acl);
-	src_num_aces = le32_to_cpu(pdacl->num_aces);
+	src_num_aces = le16_to_cpu(pdacl->num_aces);
 
 	/* Retain old ACEs which we can retain */
 	for (i = 0; i < src_num_aces; ++i) {
@@ -1158,7 +1158,7 @@ static int set_chmod_dacl(struct smb_acl *pdacl, struct smb_acl *pndacl,
 	}
 
 finalize_dacl:
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(nsize);
 
 	return 0;
@@ -1293,7 +1293,7 @@ static int build_sec_desc(struct smb_ntsd *pntsd, struct smb_ntsd *pnntsd,
 			dacloffset ? dacl_ptr->revision : cpu_to_le16(ACL_REVISION);
 
 		ndacl_ptr->size = cpu_to_le16(0);
-		ndacl_ptr->num_aces = cpu_to_le32(0);
+		ndacl_ptr->num_aces = cpu_to_le16(0);
 
 		rc = set_chmod_dacl(dacl_ptr, ndacl_ptr, owner_sid_ptr, group_sid_ptr,
 				    pnmode, mode_from_sid, posix);
@@ -1653,7 +1653,7 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 *pnmode,
 			dacl_ptr = (struct smb_acl *)((char *)pntsd + dacloffset);
 			if (mode_from_sid)
 				nsecdesclen +=
-					le32_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
+					le16_to_cpu(dacl_ptr->num_aces) * sizeof(struct smb_ace);
 			else /* cifsacl */
 				nsecdesclen += le16_to_cpu(dacl_ptr->size);
 		}
diff --git a/fs/smb/common/smbacl.h b/fs/smb/common/smbacl.h
index 6a60698fc6f0f..a624ec9e4a144 100644
--- a/fs/smb/common/smbacl.h
+++ b/fs/smb/common/smbacl.h
@@ -107,7 +107,8 @@ struct smb_sid {
 struct smb_acl {
 	__le16 revision; /* revision level */
 	__le16 size;
-	__le32 num_aces;
+	__le16 num_aces;
+	__le16 reserved;
 } __attribute__((packed));
 
 struct smb_ace {
diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 89415b02dd649..561f80d3f953e 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -333,7 +333,7 @@ void posix_state_to_acl(struct posix_acl_state *state,
 	pace->e_perm = state->other.allow;
 }
 
-int init_acl_state(struct posix_acl_state *state, int cnt)
+int init_acl_state(struct posix_acl_state *state, u16 cnt)
 {
 	int alloc;
 
@@ -368,7 +368,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 		       struct smb_fattr *fattr)
 {
 	int i, ret;
-	int num_aces = 0;
+	u16 num_aces = 0;
 	unsigned int acl_size;
 	char *acl_base;
 	struct smb_ace **ppace;
@@ -389,12 +389,12 @@ static void parse_dacl(struct mnt_idmap *idmap,
 
 	ksmbd_debug(SMB, "DACL revision %d size %d num aces %d\n",
 		    le16_to_cpu(pdacl->revision), le16_to_cpu(pdacl->size),
-		    le32_to_cpu(pdacl->num_aces));
+		    le16_to_cpu(pdacl->num_aces));
 
 	acl_base = (char *)pdacl;
 	acl_size = sizeof(struct smb_acl);
 
-	num_aces = le32_to_cpu(pdacl->num_aces);
+	num_aces = le16_to_cpu(pdacl->num_aces);
 	if (num_aces <= 0)
 		return;
 
@@ -580,7 +580,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 
 static void set_posix_acl_entries_dacl(struct mnt_idmap *idmap,
 				       struct smb_ace *pndace,
-				       struct smb_fattr *fattr, u32 *num_aces,
+				       struct smb_fattr *fattr, u16 *num_aces,
 				       u16 *size, u32 nt_aces_num)
 {
 	struct posix_acl_entry *pace;
@@ -701,7 +701,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
 			   struct smb_fattr *fattr)
 {
 	struct smb_ace *ntace, *pndace;
-	int nt_num_aces = le32_to_cpu(nt_dacl->num_aces), num_aces = 0;
+	u16 nt_num_aces = le16_to_cpu(nt_dacl->num_aces), num_aces = 0;
 	unsigned short size = 0;
 	int i;
 
@@ -728,7 +728,7 @@ static void set_ntacl_dacl(struct mnt_idmap *idmap,
 
 	set_posix_acl_entries_dacl(idmap, pndace, fattr,
 				   &num_aces, &size, nt_num_aces);
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
 }
 
@@ -736,7 +736,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
 			  struct smb_acl *pndacl, struct smb_fattr *fattr)
 {
 	struct smb_ace *pace, *pndace;
-	u32 num_aces = 0;
+	u16 num_aces = 0;
 	u16 size = 0, ace_size = 0;
 	uid_t uid;
 	const struct smb_sid *sid;
@@ -792,7 +792,7 @@ static void set_mode_dacl(struct mnt_idmap *idmap,
 				 fattr->cf_mode, 0007);
 
 out:
-	pndacl->num_aces = cpu_to_le32(num_aces);
+	pndacl->num_aces = cpu_to_le16(num_aces);
 	pndacl->size = cpu_to_le16(le16_to_cpu(pndacl->size) + size);
 }
 
@@ -1022,8 +1022,9 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 	struct smb_sid owner_sid, group_sid;
 	struct dentry *parent = path->dentry->d_parent;
 	struct mnt_idmap *idmap = mnt_idmap(path->mnt);
-	int inherited_flags = 0, flags = 0, i, ace_cnt = 0, nt_size = 0, pdacl_size;
-	int rc = 0, num_aces, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+	int inherited_flags = 0, flags = 0, i, nt_size = 0, pdacl_size;
+	int rc = 0, dacloffset, pntsd_type, pntsd_size, acl_len, aces_size;
+	u16 num_aces, ace_cnt = 0;
 	char *aces_base;
 	bool is_dir = S_ISDIR(d_inode(path->dentry)->i_mode);
 
@@ -1039,7 +1040,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 
 	parent_pdacl = (struct smb_acl *)((char *)parent_pntsd + dacloffset);
 	acl_len = pntsd_size - dacloffset;
-	num_aces = le32_to_cpu(parent_pdacl->num_aces);
+	num_aces = le16_to_cpu(parent_pdacl->num_aces);
 	pntsd_type = le16_to_cpu(parent_pntsd->type);
 	pdacl_size = le16_to_cpu(parent_pdacl->size);
 
@@ -1199,7 +1200,7 @@ int smb_inherit_dacl(struct ksmbd_conn *conn,
 			pdacl = (struct smb_acl *)((char *)pntsd + le32_to_cpu(pntsd->dacloffset));
 			pdacl->revision = cpu_to_le16(2);
 			pdacl->size = cpu_to_le16(sizeof(struct smb_acl) + nt_size);
-			pdacl->num_aces = cpu_to_le32(ace_cnt);
+			pdacl->num_aces = cpu_to_le16(ace_cnt);
 			pace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 			memcpy(pace, aces_base, nt_size);
 			pntsd_size += sizeof(struct smb_acl) + nt_size;
@@ -1280,7 +1281,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 
 		ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 		aces_size = acl_size - sizeof(struct smb_acl);
-		for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+		for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
 			if (offsetof(struct smb_ace, access_req) > aces_size)
 				break;
 			ace_size = le16_to_cpu(ace->size);
@@ -1301,7 +1302,7 @@ int smb_check_perm_dacl(struct ksmbd_conn *conn, const struct path *path,
 
 	ace = (struct smb_ace *)((char *)pdacl + sizeof(struct smb_acl));
 	aces_size = acl_size - sizeof(struct smb_acl);
-	for (i = 0; i < le32_to_cpu(pdacl->num_aces); i++) {
+	for (i = 0; i < le16_to_cpu(pdacl->num_aces); i++) {
 		if (offsetof(struct smb_ace, access_req) > aces_size)
 			break;
 		ace_size = le16_to_cpu(ace->size);
diff --git a/fs/smb/server/smbacl.h b/fs/smb/server/smbacl.h
index 24ce576fc2924..355adaee39b87 100644
--- a/fs/smb/server/smbacl.h
+++ b/fs/smb/server/smbacl.h
@@ -86,7 +86,7 @@ int parse_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 int build_sec_desc(struct mnt_idmap *idmap, struct smb_ntsd *pntsd,
 		   struct smb_ntsd *ppntsd, int ppntsd_size, int addition_info,
 		   __u32 *secdesclen, struct smb_fattr *fattr);
-int init_acl_state(struct posix_acl_state *state, int cnt);
+int init_acl_state(struct posix_acl_state *state, u16 cnt);
 void free_acl_state(struct posix_acl_state *state);
 void posix_state_to_acl(struct posix_acl_state *state,
 			struct posix_acl_entry *pace);

From 1b8b67f3c5e5169535e26efedd3e422172e2db64 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 09:32:11 +0900
Subject: [PATCH 1398/2753] ksmbd: fix incorrect validation for num_aces field
 of smb_acl

parse_dcal() validate num_aces to allocate posix_ace_state_array.

if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))

It is an incorrect validation that we can create an array of size ULONG_MAX.
smb_acl has ->size field to calculate actual number of aces in request buffer
size. Use this to check invalid num_aces.

Reported-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Tested-by: Igor Leite Ladessa <igor-ladessa@hotmail.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/smbacl.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/smb/server/smbacl.c b/fs/smb/server/smbacl.c
index 561f80d3f953e..49b128698670a 100644
--- a/fs/smb/server/smbacl.c
+++ b/fs/smb/server/smbacl.c
@@ -398,7 +398,9 @@ static void parse_dacl(struct mnt_idmap *idmap,
 	if (num_aces <= 0)
 		return;
 
-	if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+	if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+			(offsetof(struct smb_ace, sid) +
+			 offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
 		return;
 
 	ret = init_acl_state(&acl_state, num_aces);
@@ -432,6 +434,7 @@ static void parse_dacl(struct mnt_idmap *idmap,
 			offsetof(struct smb_sid, sub_auth);
 
 		if (end_of_acl - acl_base < acl_size ||
+		    ppace[i]->sid.num_subauth == 0 ||
 		    ppace[i]->sid.num_subauth > SID_MAX_SUB_AUTHORITIES ||
 		    (end_of_acl - acl_base <
 		     acl_size + sizeof(__le32) * ppace[i]->sid.num_subauth) ||

From aa2a739a75ab6f24ef72fb3fdb9192c081eacf06 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 12 Feb 2025 09:37:57 +0900
Subject: [PATCH 1399/2753] cifs: fix incorrect validation for num_aces field
 of smb_acl

parse_dcal() validate num_aces to allocate ace array.

f (num_aces > ULONG_MAX / sizeof(struct smb_ace *))

It is an incorrect validation that we can create an array of size ULONG_MAX.
smb_acl has ->size field to calculate actual number of aces in response buffer
size. Use this to check invalid num_aces.

Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/cifsacl.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/cifsacl.c b/fs/smb/client/cifsacl.c
index 7d953208046af..64bd68f750f84 100644
--- a/fs/smb/client/cifsacl.c
+++ b/fs/smb/client/cifsacl.c
@@ -778,7 +778,8 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	}
 
 	/* validate that we do not go past end of acl */
-	if (end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
+	if (end_of_acl < (char *)pdacl + sizeof(struct smb_acl) ||
+	    end_of_acl < (char *)pdacl + le16_to_cpu(pdacl->size)) {
 		cifs_dbg(VFS, "ACL too small to parse DACL\n");
 		return;
 	}
@@ -799,8 +800,11 @@ static void parse_dacl(struct smb_acl *pdacl, char *end_of_acl,
 	if (num_aces > 0) {
 		umode_t denied_mode = 0;
 
-		if (num_aces > ULONG_MAX / sizeof(struct smb_ace *))
+		if (num_aces > (le16_to_cpu(pdacl->size) - sizeof(struct smb_acl)) /
+				(offsetof(struct smb_ace, sid) +
+				 offsetof(struct smb_sid, sub_auth) + sizeof(__le16)))
 			return;
+
 		ppace = kmalloc_array(num_aces, sizeof(struct smb_ace *),
 				      GFP_KERNEL);
 		if (!ppace)

From f603b159231b0c58f0c27ab39348534063d38223 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Mon, 3 Mar 2025 14:56:10 +0800
Subject: [PATCH 1400/2753] ALSA: hda/realtek - add supported Mic Mute LED for
 Lenovo platform

Support Mic Mute LED for ThinkCentre M series.

Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Link: https://lore.kernel.org/c211a2702f1f411e86bd7420d7eebc03@realtek.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d58743b955f81..ebf54ef5877a4 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -5053,6 +5053,16 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 	}
 }
 
+static void alc233_fixup_lenovo_low_en_micmute_led(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE)
+		spec->micmute_led_polarity = 1;
+	alc233_fixup_lenovo_line2_mic_hotkey(codec, fix, action);
+}
+
 static void alc_hp_mute_disable(struct hda_codec *codec, unsigned int delay)
 {
 	if (delay <= 0)
@@ -7621,6 +7631,7 @@ enum {
 	ALC275_FIXUP_DELL_XPS,
 	ALC293_FIXUP_LENOVO_SPK_NOISE,
 	ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY,
+	ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED,
 	ALC255_FIXUP_DELL_SPK_NOISE,
 	ALC225_FIXUP_DISABLE_MIC_VREF,
 	ALC225_FIXUP_DELL1_MIC_NO_PRESENCE,
@@ -8615,6 +8626,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc233_fixup_lenovo_line2_mic_hotkey,
 	},
+	[ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc233_fixup_lenovo_low_en_micmute_led,
+	},
 	[ALC233_FIXUP_INTEL_NUC8_DMIC] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc_fixup_inv_dmic,
@@ -10906,6 +10921,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x17aa, 0x3178, "ThinkCentre Station", ALC283_FIXUP_HEADSET_MIC),
 	SND_PCI_QUIRK(0x17aa, 0x31af, "ThinkCentre Station", ALC623_FIXUP_LENOVO_THINKSTATION_P340),
 	SND_PCI_QUIRK(0x17aa, 0x334b, "Lenovo ThinkCentre M70 Gen5", ALC283_FIXUP_HEADSET_MIC),
+	SND_PCI_QUIRK(0x17aa, 0x3384, "ThinkCentre M90a PRO", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
+	SND_PCI_QUIRK(0x17aa, 0x3386, "ThinkCentre M90a Gen6", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
+	SND_PCI_QUIRK(0x17aa, 0x3387, "ThinkCentre M70a Gen6", ALC233_FIXUP_LENOVO_L2MH_LOW_ENLED),
 	SND_PCI_QUIRK(0x17aa, 0x3801, "Lenovo Yoga9 14IAP7", ALC287_FIXUP_YOGA9_14IAP7_BASS_SPK_PIN),
 	HDA_CODEC_QUIRK(0x17aa, 0x3802, "DuetITL 2021", ALC287_FIXUP_YOGA7_14ITL_SPEAKERS),
 	SND_PCI_QUIRK(0x17aa, 0x3802, "Lenovo Yoga Pro 9 14IRP8", ALC287_FIXUP_TAS2781_I2C),

From 59b348be7597c4a9903cb003c69e37df20c04a30 Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Fri, 28 Feb 2025 16:46:57 +0300
Subject: [PATCH 1401/2753] wifi: cfg80211: regulatory: improve invalid hints
 checking
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Syzbot keeps reporting an issue [1] that occurs when erroneous symbols
sent from userspace get through into user_alpha2[] via
regulatory_hint_user() call. Such invalid regulatory hints should be
rejected.

While a sanity check from commit 47caf685a685 ("cfg80211: regulatory:
reject invalid hints") looks to be enough to deter these very cases,
there is a way to get around it due to 2 reasons.

1) The way isalpha() works, symbols other than latin lower and
upper letters may be used to determine a country/domain.
For instance, greek letters will also be considered upper/lower
letters and for such characters isalpha() will return true as well.
However, ISO-3166-1 alpha2 codes should only hold latin
characters.

2) While processing a user regulatory request, between
reg_process_hint_user() and regulatory_hint_user() there happens to
be a call to queue_regulatory_request() which modifies letters in
request->alpha2[] with toupper(). This works fine for latin symbols,
less so for weird letter characters from the second part of _ctype[].

Syzbot triggers a warning in is_user_regdom_saved() by first sending
over an unexpected non-latin letter that gets malformed by toupper()
into a character that ends up failing isalpha() check.

Prevent this by enhancing is_an_alpha2() to ensure that incoming
symbols are latin letters and nothing else.

[1] Syzbot report:
------------[ cut here ]------------
Unexpected user alpha2: A�
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 is_user_regdom_saved net/wireless/reg.c:440 [inline]
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 restore_alpha2 net/wireless/reg.c:3424 [inline]
WARNING: CPU: 1 PID: 964 at net/wireless/reg.c:442 restore_regulatory_settings+0x3c0/0x1e50 net/wireless/reg.c:3516
Modules linked in:
CPU: 1 UID: 0 PID: 964 Comm: kworker/1:2 Not tainted 6.12.0-rc5-syzkaller-00044-gc1e939a21eb1 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Workqueue: events_power_efficient crda_timeout_work
RIP: 0010:is_user_regdom_saved net/wireless/reg.c:440 [inline]
RIP: 0010:restore_alpha2 net/wireless/reg.c:3424 [inline]
RIP: 0010:restore_regulatory_settings+0x3c0/0x1e50 net/wireless/reg.c:3516
...
Call Trace:
 <TASK>
 crda_timeout_work+0x27/0x50 net/wireless/reg.c:542
 process_one_work kernel/workqueue.c:3229 [inline]
 process_scheduled_works+0xa65/0x1850 kernel/workqueue.c:3310
 worker_thread+0x870/0xd30 kernel/workqueue.c:3391
 kthread+0x2f2/0x390 kernel/kthread.c:389
 ret_from_fork+0x4d/0x80 arch/x86/kernel/process.c:147
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:244
 </TASK>

Reported-by: syzbot+e10709ac3c44f3d4e800@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=e10709ac3c44f3d4e800
Fixes: 09d989d179d0 ("cfg80211: add regulatory hint disconnect support")
Cc: stable@kernel.org
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250228134659.1577656-1-n.zhandarovich@fintech.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/reg.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2dd0533e76605..212e9561aae77 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -407,7 +407,8 @@ static bool is_an_alpha2(const char *alpha2)
 {
 	if (!alpha2)
 		return false;
-	return isalpha(alpha2[0]) && isalpha(alpha2[1]);
+	return isascii(alpha2[0]) && isalpha(alpha2[0]) &&
+	       isascii(alpha2[1]) && isalpha(alpha2[1]);
 }
 
 static bool alpha2_equal(const char *alpha2_x, const char *alpha2_y)

From 487cfd4a8e3dc42d34a759017978a4edaf85fce0 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Thu, 27 Feb 2025 19:45:29 +0000
Subject: [PATCH 1402/2753] xhci: Restrict USB4 tunnel detection for USB3
 devices to Intel hosts

When adding support for USB3-over-USB4 tunnelling detection, a check
for an Intel-specific capability was added. This capability, which
goes by ID 206, is used without any check that we are actually
dealing with an Intel host.

As it turns out, the Cadence XHCI controller *also* exposes an
extended capability numbered 206 (for unknown purposes), but of
course doesn't have the Intel-specific registers that the tunnelling
code is trying to access. Fun follows.

The core of the problems is that the tunnelling code blindly uses
vendor-specific capabilities without any check (the Intel-provided
documentation I have at hand indicates that 192-255 are indeed
vendor-specific).

Restrict the detection code to Intel HW for real, preventing any
further explosion on my (non-Intel) HW.

Cc: stable <stable@kernel.org>
Fixes: 948ce83fbb7df ("xhci: Add USB4 tunnel detection for USB3 devices on Intel hosts")
Signed-off-by: Marc Zyngier <maz@kernel.org>
Acked-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250227194529.2288718-1-maz@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci-hub.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/usb/host/xhci-hub.c b/drivers/usb/host/xhci-hub.c
index 9693464c05204..69c278b64084b 100644
--- a/drivers/usb/host/xhci-hub.c
+++ b/drivers/usb/host/xhci-hub.c
@@ -12,6 +12,7 @@
 #include <linux/slab.h>
 #include <linux/unaligned.h>
 #include <linux/bitfield.h>
+#include <linux/pci.h>
 
 #include "xhci.h"
 #include "xhci-trace.h"
@@ -770,9 +771,16 @@ static int xhci_exit_test_mode(struct xhci_hcd *xhci)
 enum usb_link_tunnel_mode xhci_port_is_tunneled(struct xhci_hcd *xhci,
 						struct xhci_port *port)
 {
+	struct usb_hcd *hcd;
 	void __iomem *base;
 	u32 offset;
 
+	/* Don't try and probe this capability for non-Intel hosts */
+	hcd = xhci_to_hcd(xhci);
+	if (!dev_is_pci(hcd->self.controller) ||
+	    to_pci_dev(hcd->self.controller)->vendor != PCI_VENDOR_ID_INTEL)
+		return USB_LINK_UNKNOWN;
+
 	base = &xhci->cap_regs->hc_capbase;
 	offset = xhci_find_next_ext_cap(base, 0, XHCI_EXT_CAPS_INTEL_SPR_SHADOW);
 

From 8e812e9355a6f14dffd54a33d951ca403b9732f5 Mon Sep 17 00:00:00 2001
From: Prashanth K <prashanth.k@oss.qualcomm.com>
Date: Mon, 24 Feb 2025 14:26:04 +0530
Subject: [PATCH 1403/2753] usb: gadget: Check bmAttributes only if
 configuration is valid

If the USB configuration is not valid, then avoid checking for
bmAttributes to prevent null pointer deference.

Cc: stable <stable@kernel.org>
Fixes: 40e89ff5750f ("usb: gadget: Set self-powered based on MaxPower and bmAttributes")
Signed-off-by: Prashanth K <prashanth.k@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250224085604.417327-1-prashanth.k@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 4bcf73bae7610..869ad99afb48b 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1051,7 +1051,7 @@ static int set_config(struct usb_composite_dev *cdev,
 		usb_gadget_set_remote_wakeup(gadget, 0);
 done:
 	if (power > USB_SELF_POWER_VBUS_MAX_DRAW ||
-	    !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER))
+	    (c && !(c->bmAttributes & USB_CONFIG_ATT_SELFPOWER)))
 		usb_gadget_clear_selfpowered(gadget);
 	else
 		usb_gadget_set_selfpowered(gadget);

From 69c58deec19628c8a686030102176484eb94fed4 Mon Sep 17 00:00:00 2001
From: Badhri Jagan Sridharan <badhri@google.com>
Date: Sun, 16 Feb 2025 22:30:02 +0000
Subject: [PATCH 1404/2753] usb: dwc3: gadget: Prevent irq storm when TH
 re-executes

While commit d325a1de49d6 ("usb: dwc3: gadget: Prevent losing events in
event cache") makes sure that top half(TH) does not end up overwriting the
cached events before processing them when the TH gets invoked more than one
time, returning IRQ_HANDLED results in occasional irq storm where the TH
hogs the CPU. The irq storm can be prevented by the flag before event
handler busy is cleared. Default enable interrupt moderation in all
versions which support them.

ftrace event stub during dwc3 irq storm:
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000866: irq_handler_exit: irq=14 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000872: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000874: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000881: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000883: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000889: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000892: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000898: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000901: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000907: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000909: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000915: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000918: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000924: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000927: irq_handler_exit: irq=504 ret=handled
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000933: irq_handler_entry: irq=504 name=dwc3
    irq/504_dwc3-1111  ( 1111) [000] .... 70.000935: irq_handler_exit: irq=504 ret=handled
    ....

Cc: stable <stable@kernel.org>
Suggested-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Fixes: d325a1de49d6 ("usb: dwc3: gadget: Prevent losing events in event cache")
Signed-off-by: Badhri Jagan Sridharan <badhri@google.com>
Acked-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/20250216223003.3568039-1-badhri@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c   | 16 ++++++----------
 drivers/usb/dwc3/gadget.c | 10 +++++++---
 2 files changed, 13 insertions(+), 13 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index dfa1b5fe48dc4..2c472cb97f6c7 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -1835,8 +1835,6 @@ static void dwc3_get_properties(struct dwc3 *dwc)
 	dwc->tx_thr_num_pkt_prd = tx_thr_num_pkt_prd;
 	dwc->tx_max_burst_prd = tx_max_burst_prd;
 
-	dwc->imod_interval = 0;
-
 	dwc->tx_fifo_resize_max_num = tx_fifo_resize_max_num;
 }
 
@@ -1854,21 +1852,19 @@ static void dwc3_check_params(struct dwc3 *dwc)
 	unsigned int hwparam_gen =
 		DWC3_GHWPARAMS3_SSPHY_IFC(dwc->hwparams.hwparams3);
 
-	/* Check for proper value of imod_interval */
-	if (dwc->imod_interval && !dwc3_has_imod(dwc)) {
-		dev_warn(dwc->dev, "Interrupt moderation not supported\n");
-		dwc->imod_interval = 0;
-	}
-
 	/*
+	 * Enable IMOD for all supporting controllers.
+	 *
+	 * Particularly, DWC_usb3 v3.00a must enable this feature for
+	 * the following reason:
+	 *
 	 * Workaround for STAR 9000961433 which affects only version
 	 * 3.00a of the DWC_usb3 core. This prevents the controller
 	 * interrupt from being masked while handling events. IMOD
 	 * allows us to work around this issue. Enable it for the
 	 * affected version.
 	 */
-	if (!dwc->imod_interval &&
-	    DWC3_VER_IS(DWC3, 300A))
+	if (dwc3_has_imod((dwc)))
 		dwc->imod_interval = 1;
 
 	/* Check the maximum_speed parameter */
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index ddd6b2ce57107..89a4dc8ebf948 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -4501,14 +4501,18 @@ static irqreturn_t dwc3_process_event_buf(struct dwc3_event_buffer *evt)
 	dwc3_writel(dwc->regs, DWC3_GEVNTSIZ(0),
 		    DWC3_GEVNTSIZ_SIZE(evt->length));
 
+	evt->flags &= ~DWC3_EVENT_PENDING;
+	/*
+	 * Add an explicit write memory barrier to make sure that the update of
+	 * clearing DWC3_EVENT_PENDING is observed in dwc3_check_event_buf()
+	 */
+	wmb();
+
 	if (dwc->imod_interval) {
 		dwc3_writel(dwc->regs, DWC3_GEVNTCOUNT(0), DWC3_GEVNTCOUNT_EHB);
 		dwc3_writel(dwc->regs, DWC3_DEV_IMOD(0), dwc->imod_interval);
 	}
 
-	/* Keep the clearing of DWC3_EVENT_PENDING at the end */
-	evt->flags &= ~DWC3_EVENT_PENDING;
-
 	return ret;
 }
 

From b5ea08aa883da05106fcc683d12489a4292d1122 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:46 +0200
Subject: [PATCH 1405/2753] usb: renesas_usbhs: Call clk_put()

Clocks acquired with of_clk_get() need to be freed with clk_put(). Call
clk_put() on priv->clks[0] on error path.

Fixes: 3df0e240caba ("usb: renesas_usbhs: Add multiple clocks management")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-2-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index 935fc496fe94b..6c7857b66a219 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -312,8 +312,10 @@ static int usbhsc_clk_get(struct device *dev, struct usbhs_priv *priv)
 	priv->clks[1] = of_clk_get(dev_of_node(dev), 1);
 	if (PTR_ERR(priv->clks[1]) == -ENOENT)
 		priv->clks[1] = NULL;
-	else if (IS_ERR(priv->clks[1]))
+	else if (IS_ERR(priv->clks[1])) {
+		clk_put(priv->clks[0]);
 		return PTR_ERR(priv->clks[1]);
+	}
 
 	return 0;
 }

From e0c92440938930e7fa7aa6362780d39cdea34449 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:47 +0200
Subject: [PATCH 1406/2753] usb: renesas_usbhs: Use devm_usb_get_phy()

The gpriv->transceiver is retrieved in probe() through usb_get_phy() but
never released. Use devm_usb_get_phy() to handle this scenario.

This issue was identified through code investigation. No issue was found
without this change.

Fixes: b5a2875605ca ("usb: renesas_usbhs: Allow an OTG PHY driver to provide VBUS")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-3-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/mod_gadget.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/usb/renesas_usbhs/mod_gadget.c b/drivers/usb/renesas_usbhs/mod_gadget.c
index 105132ae87acb..e8e5723f54122 100644
--- a/drivers/usb/renesas_usbhs/mod_gadget.c
+++ b/drivers/usb/renesas_usbhs/mod_gadget.c
@@ -1094,7 +1094,7 @@ int usbhs_mod_gadget_probe(struct usbhs_priv *priv)
 		goto usbhs_mod_gadget_probe_err_gpriv;
 	}
 
-	gpriv->transceiver = usb_get_phy(USB_PHY_TYPE_UNDEFINED);
+	gpriv->transceiver = devm_usb_get_phy(dev, USB_PHY_TYPE_UNDEFINED);
 	dev_info(dev, "%stransceiver found\n",
 		 !IS_ERR(gpriv->transceiver) ? "" : "no ");
 

From 552ca6b87e3778f3dd5b87842f95138162e16c82 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Tue, 25 Feb 2025 13:02:48 +0200
Subject: [PATCH 1407/2753] usb: renesas_usbhs: Flush the notify_hotplug_work

When performing continuous unbind/bind operations on the USB drivers
available on the Renesas RZ/G2L SoC, a kernel crash with the message
"Unable to handle kernel NULL pointer dereference at virtual address"
may occur. This issue points to the usbhsc_notify_hotplug() function.

Flush the delayed work to avoid its execution when driver resources are
unavailable.

Fixes: bc57381e6347 ("usb: renesas_usbhs: use delayed_work instead of work_struct")
Cc: stable <stable@kernel.org>
Reviewed-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Tested-by: Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Link: https://lore.kernel.org/r/20250225110248.870417-4-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/renesas_usbhs/common.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/usb/renesas_usbhs/common.c b/drivers/usb/renesas_usbhs/common.c
index 6c7857b66a219..4b35ef216125c 100644
--- a/drivers/usb/renesas_usbhs/common.c
+++ b/drivers/usb/renesas_usbhs/common.c
@@ -781,6 +781,8 @@ static void usbhs_remove(struct platform_device *pdev)
 
 	dev_dbg(&pdev->dev, "usb remove\n");
 
+	flush_delayed_work(&priv->notify_hotplug_work);
+
 	/* power off */
 	if (!usbhs_get_dparam(priv, runtime_pwctrl))
 		usbhsc_power_ctrl(priv, 0);

From 2b66ef84d0d2a0ea955b40bd306f5e3abbc5cf9c Mon Sep 17 00:00:00 2001
From: Pawel Laszczak <pawell@cadence.com>
Date: Fri, 28 Feb 2025 07:50:25 +0000
Subject: [PATCH 1408/2753] usb: hub: lack of clearing xHC resources

The xHC resources allocated for USB devices are not released in correct
order after resuming in case when while suspend device was reconnected.

This issue has been detected during the fallowing scenario:
- connect hub HS to root port
- connect LS/FS device to hub port
- wait for enumeration to finish
- force host to suspend
- reconnect hub attached to root port
- wake host

For this scenario during enumeration of USB LS/FS device the Cadence xHC
reports completion error code for xHC commands because the xHC resources
used for devices has not been properly released.
XHCI specification doesn't mention that device can be reset in any order
so, we should not treat this issue as Cadence xHC controller bug.
Similar as during disconnecting in this case the device resources should
be cleared starting form the last usb device in tree toward the root hub.
To fix this issue usbcore driver should call hcd->driver->reset_device
for all USB devices connected to hub which was reconnected while
suspending.

Fixes: 3d82904559f4 ("usb: cdnsp: cdns3 Add main part of Cadence USBSSP DRD Driver")
Cc: stable <stable@kernel.org>
Signed-off-by: Pawel Laszczak <pawell@cadence.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/PH7PR07MB953841E38C088678ACDCF6EEDDCC2@PH7PR07MB9538.namprd07.prod.outlook.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index a76bb50b62026..dcba4281ea486 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -6065,6 +6065,36 @@ void usb_hub_cleanup(void)
 	usb_deregister(&hub_driver);
 } /* usb_hub_cleanup() */
 
+/**
+ * hub_hc_release_resources - clear resources used by host controller
+ * @udev: pointer to device being released
+ *
+ * Context: task context, might sleep
+ *
+ * Function releases the host controller resources in correct order before
+ * making any operation on resuming usb device. The host controller resources
+ * allocated for devices in tree should be released starting from the last
+ * usb device in tree toward the root hub. This function is used only during
+ * resuming device when usb device require reinitialization – that is, when
+ * flag udev->reset_resume is set.
+ *
+ * This call is synchronous, and may not be used in an interrupt context.
+ */
+static void hub_hc_release_resources(struct usb_device *udev)
+{
+	struct usb_hub *hub = usb_hub_to_struct_hub(udev);
+	struct usb_hcd *hcd = bus_to_hcd(udev->bus);
+	int i;
+
+	/* Release up resources for all children before this device */
+	for (i = 0; i < udev->maxchild; i++)
+		if (hub->ports[i]->child)
+			hub_hc_release_resources(hub->ports[i]->child);
+
+	if (hcd->driver->reset_device)
+		hcd->driver->reset_device(hcd, udev);
+}
+
 /**
  * usb_reset_and_verify_device - perform a USB port reset to reinitialize a device
  * @udev: device to reset (not in SUSPENDED or NOTATTACHED state)
@@ -6129,6 +6159,9 @@ static int usb_reset_and_verify_device(struct usb_device *udev)
 	bos = udev->bos;
 	udev->bos = NULL;
 
+	if (udev->reset_resume)
+		hub_hc_release_resources(udev);
+
 	mutex_lock(hcd->address0_mutex);
 
 	for (i = 0; i < PORT_INIT_TRIES; ++i) {

From 1be4e29e94a6be77de3bc210820b74f40814f17a Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 27 Feb 2025 11:03:06 -0600
Subject: [PATCH 1409/2753] platform/x86/amd/pmf: Initialize and clean up
 `cb_mutex`
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

`cb_mutex` was introduced in commit 9e0894d07072e ("platform/x86/amd/pmf:
Enable Custom BIOS Inputs for PMF-TA") to prevent conccurrent access for
BIOS inputs. It however isn't initialized and so on use it may lead to
a NULL pointer dereference.

Add code to initialize on probe and clean up on destroy.

Reported-by: Yijun Shen <Yijun.Shen@dell.com>
Cc: Richard Gong <richgong@amd.com>
Fixes: 9e0894d07072e ("platform/x86/amd/pmf: Enable Custom BIOS Inputs for PMF-TA")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-By: Yijun Shen <Yijun_Shen@Dell.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250227170308.435862-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/core.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
index 764cc1fe90ae4..a2cb2d5544f5b 100644
--- a/drivers/platform/x86/amd/pmf/core.c
+++ b/drivers/platform/x86/amd/pmf/core.c
@@ -452,6 +452,7 @@ static int amd_pmf_probe(struct platform_device *pdev)
 
 	mutex_init(&dev->lock);
 	mutex_init(&dev->update_mutex);
+	mutex_init(&dev->cb_mutex);
 
 	apmf_acpi_init(dev);
 	platform_set_drvdata(pdev, dev);
@@ -477,6 +478,7 @@ static void amd_pmf_remove(struct platform_device *pdev)
 	amd_pmf_dbgfs_unregister(dev);
 	mutex_destroy(&dev->lock);
 	mutex_destroy(&dev->update_mutex);
+	mutex_destroy(&dev->cb_mutex);
 	kfree(dev->buf);
 }
 

From 010c4a461c1dbf3fa75ddea8df018a6128b700c6 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:43 -0800
Subject: [PATCH 1410/2753] x86/speculation: Simplify and make CALL_NOSPEC
 consistent

CALL_NOSPEC macro is used to generate Spectre-v2 mitigation friendly
indirect branches. At compile time the macro defaults to indirect branch,
and at runtime those can be patched to thunk based mitigations.

This approach is opposite of what is done for the rest of the kernel, where
the compile time default is to replace indirect calls with retpoline thunk
calls.

Make CALL_NOSPEC consistent with the rest of the kernel, default to
retpoline thunk at compile time when CONFIG_MITIGATION_RETPOLINE is
enabled.

Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-1-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 15 +++++----------
 1 file changed, 5 insertions(+), 10 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7e8bf78c03d5d..1e6b915ce9564 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -424,16 +424,11 @@ static inline void call_depth_return_thunk(void) {}
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
-# define CALL_NOSPEC						\
-	ALTERNATIVE_2(						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
-	X86_FEATURE_RETPOLINE,					\
-	"lfence;\n"						\
-	ANNOTATE_RETPOLINE_SAFE					\
-	"call *%[thunk_target]\n",				\
-	X86_FEATURE_RETPOLINE_LFENCE)
+#ifdef CONFIG_MITIGATION_RETPOLINE
+#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#else
+#define CALL_NOSPEC	"call *%[thunk_target]\n"
+#endif
 
 # define THUNK_TARGET(addr) [thunk_target] "r" (addr)
 

From 9af9ad85ac44cb754e526d468c3006b48db5dfd8 Mon Sep 17 00:00:00 2001
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Date: Fri, 28 Feb 2025 18:35:58 -0800
Subject: [PATCH 1411/2753] x86/speculation: Add a conditional CS prefix to
 CALL_NOSPEC

Retpoline mitigation for spectre-v2 uses thunks for indirect branches. To
support this mitigation compilers add a CS prefix with
-mindirect-branch-cs-prefix. For an indirect branch in asm, this needs to
be added manually.

CS prefix is already being added to indirect branches in asm files, but not
in inline asm. Add CS prefix to CALL_NOSPEC for inline asm as well. There
is no JMP_NOSPEC for inline asm.

Reported-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Andrew Cooper <andrew.cooper3@citrix.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250228-call-nospec-v3-2-96599fed0f33@linux.intel.com
---
 arch/x86/include/asm/nospec-branch.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 1e6b915ce9564..aee26bb8230f8 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -198,9 +198,8 @@
 .endm
 
 /*
- * Equivalent to -mindirect-branch-cs-prefix; emit the 5 byte jmp/call
- * to the retpoline thunk with a CS prefix when the register requires
- * a RAX prefix byte to encode. Also see apply_retpolines().
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
  */
 .macro __CS_PREFIX reg:req
 	.irp rs,r8,r9,r10,r11,r12,r13,r14,r15
@@ -420,12 +419,24 @@ static inline void call_depth_return_thunk(void) {}
 
 #ifdef CONFIG_X86_64
 
+/*
+ * Emits a conditional CS prefix that is compatible with
+ * -mindirect-branch-cs-prefix.
+ */
+#define __CS_PREFIX(reg)				\
+	".irp rs,r8,r9,r10,r11,r12,r13,r14,r15\n"	\
+	".ifc \\rs," reg "\n"				\
+	".byte 0x2e\n"					\
+	".endif\n"					\
+	".endr\n"
+
 /*
  * Inline asm uses the %V modifier which is only in newer GCC
  * which is ensured when CONFIG_MITIGATION_RETPOLINE is defined.
  */
 #ifdef CONFIG_MITIGATION_RETPOLINE
-#define CALL_NOSPEC	"call __x86_indirect_thunk_%V[thunk_target]\n"
+#define CALL_NOSPEC	__CS_PREFIX("%V[thunk_target]")	\
+			"call __x86_indirect_thunk_%V[thunk_target]\n"
 #else
 #define CALL_NOSPEC	"call *%[thunk_target]\n"
 #endif

From df1a1ed5e1bdd9cc13148e0e5549f5ebcf76cf13 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:42:19 +0000
Subject: [PATCH 1412/2753] drm/imagination: avoid deadlock on fence release

Do scheduler queue fence release processing on a workqueue, rather
than in the release function itself.

Fixes deadlock issues such as the following:

[  607.400437] ============================================
[  607.405755] WARNING: possible recursive locking detected
[  607.415500] --------------------------------------------
[  607.420817] weston:zfq0/24149 is trying to acquire lock:
[  607.426131] ffff000017d041a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: pvr_gem_object_vunmap+0x40/0xc0 [powervr]
[  607.436728]
               but task is already holding lock:
[  607.442554] ffff000017d105a0 (reservation_ww_class_mutex){+.+.}-{3:3}, at: dma_buf_ioctl+0x250/0x554
[  607.451727]
               other info that might help us debug this:
[  607.458245]  Possible unsafe locking scenario:

[  607.464155]        CPU0
[  607.466601]        ----
[  607.469044]   lock(reservation_ww_class_mutex);
[  607.473584]   lock(reservation_ww_class_mutex);
[  607.478114]
                *** DEADLOCK ***

Cc: stable@vger.kernel.org
Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-fence-release-deadlock-v2-1-6fed2fc1fe88@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_queue.c | 13 +++++++++++--
 drivers/gpu/drm/imagination/pvr_queue.h |  4 ++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index c4f08432882b1..f3f1c5212df74 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -109,12 +109,20 @@ pvr_queue_fence_get_driver_name(struct dma_fence *f)
 	return PVR_DRIVER_NAME;
 }
 
+static void pvr_queue_fence_release_work(struct work_struct *w)
+{
+	struct pvr_queue_fence *fence = container_of(w, struct pvr_queue_fence, release_work);
+
+	pvr_context_put(fence->queue->ctx);
+	dma_fence_free(&fence->base);
+}
+
 static void pvr_queue_fence_release(struct dma_fence *f)
 {
 	struct pvr_queue_fence *fence = container_of(f, struct pvr_queue_fence, base);
+	struct pvr_device *pvr_dev = fence->queue->ctx->pvr_dev;
 
-	pvr_context_put(fence->queue->ctx);
-	dma_fence_free(f);
+	queue_work(pvr_dev->sched_wq, &fence->release_work);
 }
 
 static const char *
@@ -268,6 +276,7 @@ pvr_queue_fence_init(struct dma_fence *f,
 
 	pvr_context_get(queue->ctx);
 	fence->queue = queue;
+	INIT_WORK(&fence->release_work, pvr_queue_fence_release_work);
 	dma_fence_init(&fence->base, fence_ops,
 		       &fence_ctx->lock, fence_ctx->id,
 		       atomic_inc_return(&fence_ctx->seqno));
diff --git a/drivers/gpu/drm/imagination/pvr_queue.h b/drivers/gpu/drm/imagination/pvr_queue.h
index e06ced69302fc..93fe9ac9f58cc 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.h
+++ b/drivers/gpu/drm/imagination/pvr_queue.h
@@ -5,6 +5,7 @@
 #define PVR_QUEUE_H
 
 #include <drm/gpu_scheduler.h>
+#include <linux/workqueue.h>
 
 #include "pvr_cccb.h"
 #include "pvr_device.h"
@@ -63,6 +64,9 @@ struct pvr_queue_fence {
 
 	/** @queue: Queue that created this fence. */
 	struct pvr_queue *queue;
+
+	/** @release_work: Fence release work structure. */
+	struct work_struct release_work;
 };
 
 /**

From a5c4c3ba95a52d66315acdfbaba9bd82ed39c250 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:43:06 +0000
Subject: [PATCH 1413/2753] drm/imagination: Hold drm_gem_gpuva lock for unmap

Avoid a warning from drm_gem_gpuva_assert_lock_held in drm_gpuva_unlink.

The Imagination driver uses the GEM object reservation lock to protect
the gpuva list, but the GEM object was not always known in the code
paths that ended up calling drm_gpuva_unlink. When the GEM object isn't
known, it is found by calling drm_gpuva_find to lookup the object
associated with a given virtual address range, or by calling
drm_gpuva_find_first when removing all mappings.

Cc: stable@vger.kernel.org
Fixes: 4bc736f890ce ("drm/imagination: vm: make use of GPUVM's drm_exec helper")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-hold-drm_gem_gpuva-lock-for-unmap-v2-1-3fdacded227f@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_fw_meta.c |   6 +-
 drivers/gpu/drm/imagination/pvr_vm.c      | 134 +++++++++++++++++-----
 drivers/gpu/drm/imagination/pvr_vm.h      |   3 +
 3 files changed, 115 insertions(+), 28 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_fw_meta.c b/drivers/gpu/drm/imagination/pvr_fw_meta.c
index c39beb70c3173..6d13864851fc2 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_meta.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_meta.c
@@ -527,8 +527,10 @@ pvr_meta_vm_map(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 static void
 pvr_meta_vm_unmap(struct pvr_device *pvr_dev, struct pvr_fw_object *fw_obj)
 {
-	pvr_vm_unmap(pvr_dev->kernel_vm_ctx, fw_obj->fw_mm_node.start,
-		     fw_obj->fw_mm_node.size);
+	struct pvr_gem_object *pvr_obj = fw_obj->gem;
+
+	pvr_vm_unmap_obj(pvr_dev->kernel_vm_ctx, pvr_obj,
+			 fw_obj->fw_mm_node.start, fw_obj->fw_mm_node.size);
 }
 
 static bool
diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
index 363f885a70982..2896fa7501b1c 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.c
+++ b/drivers/gpu/drm/imagination/pvr_vm.c
@@ -293,8 +293,9 @@ pvr_vm_bind_op_map_init(struct pvr_vm_bind_op *bind_op,
 
 static int
 pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
-			  struct pvr_vm_context *vm_ctx, u64 device_addr,
-			  u64 size)
+			  struct pvr_vm_context *vm_ctx,
+			  struct pvr_gem_object *pvr_obj,
+			  u64 device_addr, u64 size)
 {
 	int err;
 
@@ -318,6 +319,7 @@ pvr_vm_bind_op_unmap_init(struct pvr_vm_bind_op *bind_op,
 		goto err_bind_op_fini;
 	}
 
+	bind_op->pvr_obj = pvr_obj;
 	bind_op->vm_ctx = vm_ctx;
 	bind_op->device_addr = device_addr;
 	bind_op->size = size;
@@ -597,20 +599,6 @@ pvr_vm_create_context(struct pvr_device *pvr_dev, bool is_userspace_context)
 	return ERR_PTR(err);
 }
 
-/**
- * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
- * @vm_ctx: Target VM context.
- *
- * This function ensures that no mappings are left dangling by unmapping them
- * all in order of ascending device-virtual address.
- */
-void
-pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
-{
-	WARN_ON(pvr_vm_unmap(vm_ctx, vm_ctx->gpuvm_mgr.mm_start,
-			     vm_ctx->gpuvm_mgr.mm_range));
-}
-
 /**
  * pvr_vm_context_release() - Teardown a VM context.
  * @ref_count: Pointer to reference counter of the VM context.
@@ -703,11 +691,7 @@ pvr_vm_lock_extra(struct drm_gpuvm_exec *vm_exec)
 	struct pvr_vm_bind_op *bind_op = vm_exec->extra.priv;
 	struct pvr_gem_object *pvr_obj = bind_op->pvr_obj;
 
-	/* Unmap operations don't have an object to lock. */
-	if (!pvr_obj)
-		return 0;
-
-	/* Acquire lock on the GEM being mapped. */
+	/* Acquire lock on the GEM object being mapped/unmapped. */
 	return drm_exec_lock_obj(&vm_exec->exec, gem_from_pvr_gem(pvr_obj));
 }
 
@@ -772,8 +756,10 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
 }
 
 /**
- * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * pvr_vm_unmap_obj_locked() - Unmap an already mapped section of device-virtual
+ * memory.
  * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
  * @device_addr: Virtual device address at the start of the target mapping.
  * @size: Size of the target mapping.
  *
@@ -784,9 +770,13 @@ pvr_vm_map(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
  *  * Any error encountered while performing internal operations required to
  *    destroy the mapping (returned from pvr_vm_gpuva_unmap or
  *    pvr_vm_gpuva_remap).
+ *
+ * The vm_ctx->lock must be held when calling this function.
  */
-int
-pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+static int
+pvr_vm_unmap_obj_locked(struct pvr_vm_context *vm_ctx,
+			struct pvr_gem_object *pvr_obj,
+			u64 device_addr, u64 size)
 {
 	struct pvr_vm_bind_op bind_op = {0};
 	struct drm_gpuvm_exec vm_exec = {
@@ -799,11 +789,13 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 		},
 	};
 
-	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, device_addr,
-					    size);
+	int err = pvr_vm_bind_op_unmap_init(&bind_op, vm_ctx, pvr_obj,
+					    device_addr, size);
 	if (err)
 		return err;
 
+	pvr_gem_object_get(pvr_obj);
+
 	err = drm_gpuvm_exec_lock(&vm_exec);
 	if (err)
 		goto err_cleanup;
@@ -818,6 +810,96 @@ pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
 	return err;
 }
 
+/**
+ * pvr_vm_unmap_obj() - Unmap an already mapped section of device-virtual
+ * memory.
+ * @vm_ctx: Target VM context.
+ * @pvr_obj: Target PowerVR memory object.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx, struct pvr_gem_object *pvr_obj,
+		 u64 device_addr, u64 size)
+{
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+	err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj, device_addr, size);
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap() - Unmap an already mapped section of device-virtual memory.
+ * @vm_ctx: Target VM context.
+ * @device_addr: Virtual device address at the start of the target mapping.
+ * @size: Size of the target mapping.
+ *
+ * Return:
+ *  * 0 on success,
+ *  * Any error encountered by drm_gpuva_find,
+ *  * Any error encountered by pvr_vm_unmap_obj_locked.
+ */
+int
+pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size)
+{
+	struct pvr_gem_object *pvr_obj;
+	struct drm_gpuva *va;
+	int err;
+
+	mutex_lock(&vm_ctx->lock);
+
+	va = drm_gpuva_find(&vm_ctx->gpuvm_mgr, device_addr, size);
+	if (va) {
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+		err = pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+					      va->va.addr, va->va.range);
+	} else {
+		err = -ENOENT;
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+
+	return err;
+}
+
+/**
+ * pvr_vm_unmap_all() - Unmap all mappings associated with a VM context.
+ * @vm_ctx: Target VM context.
+ *
+ * This function ensures that no mappings are left dangling by unmapping them
+ * all in order of ascending device-virtual address.
+ */
+void
+pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx)
+{
+	mutex_lock(&vm_ctx->lock);
+
+	for (;;) {
+		struct pvr_gem_object *pvr_obj;
+		struct drm_gpuva *va;
+
+		va = drm_gpuva_find_first(&vm_ctx->gpuvm_mgr,
+					  vm_ctx->gpuvm_mgr.mm_start,
+					  vm_ctx->gpuvm_mgr.mm_range);
+		if (!va)
+			break;
+
+		pvr_obj = gem_to_pvr_gem(va->gem.obj);
+
+		WARN_ON(pvr_vm_unmap_obj_locked(vm_ctx, pvr_obj,
+						va->va.addr, va->va.range));
+	}
+
+	mutex_unlock(&vm_ctx->lock);
+}
+
 /* Static data areas are determined by firmware. */
 static const struct drm_pvr_static_data_area static_data_areas[] = {
 	{
diff --git a/drivers/gpu/drm/imagination/pvr_vm.h b/drivers/gpu/drm/imagination/pvr_vm.h
index 79406243617c1..b0528dffa7f1b 100644
--- a/drivers/gpu/drm/imagination/pvr_vm.h
+++ b/drivers/gpu/drm/imagination/pvr_vm.h
@@ -38,6 +38,9 @@ struct pvr_vm_context *pvr_vm_create_context(struct pvr_device *pvr_dev,
 int pvr_vm_map(struct pvr_vm_context *vm_ctx,
 	       struct pvr_gem_object *pvr_obj, u64 pvr_obj_offset,
 	       u64 device_addr, u64 size);
+int pvr_vm_unmap_obj(struct pvr_vm_context *vm_ctx,
+		     struct pvr_gem_object *pvr_obj,
+		     u64 device_addr, u64 size);
 int pvr_vm_unmap(struct pvr_vm_context *vm_ctx, u64 device_addr, u64 size);
 void pvr_vm_unmap_all(struct pvr_vm_context *vm_ctx);
 

From 91cf42c63f2d8a9c1bcdfe923218e079b32e1a69 Mon Sep 17 00:00:00 2001
From: Conor Dooley <conor.dooley@microchip.com>
Date: Mon, 3 Mar 2025 10:47:40 +0000
Subject: [PATCH 1414/2753] spi: microchip-core: prevent RX overflows when
 transmit size > FIFO size

When the size of a transfer exceeds the size of the FIFO (32 bytes), RX
overflows will be generated and receive data will be corrupted and
warnings will be produced. For example, here's an error generated by a
transfer of 36 bytes:

  spi_master spi0: mchp_corespi_interrupt: RX OVERFLOW: rxlen: 4, txlen: 0

The driver is currently split between handling receiving in the
interrupt handler, and sending outside of it. Move all handling out of
the interrupt handling, and explicitly link the number of bytes read of
of the RX FIFO to the number written into the TX one. This both resolves
the overflow problems as well as simplifying the flow of the driver.

CC: stable@vger.kernel.org
Fixes: 9ac8d17694b6 ("spi: add support for microchip fpga spi controllers")
Signed-off-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://patch.msgid.link/20250303-veal-snooper-712c1dfad336@wendy
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/spi/spi-microchip-core.c | 41 ++++++++++++++------------------
 1 file changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-microchip-core.c
index 5b6af55855efc..62ba0bd9cbb7e 100644
--- a/drivers/spi/spi-microchip-core.c
+++ b/drivers/spi/spi-microchip-core.c
@@ -70,8 +70,7 @@
 #define INT_RX_CHANNEL_OVERFLOW		BIT(2)
 #define INT_TX_CHANNEL_UNDERRUN		BIT(3)
 
-#define INT_ENABLE_MASK (CONTROL_RX_DATA_INT | CONTROL_TX_DATA_INT | \
-			 CONTROL_RX_OVER_INT | CONTROL_TX_UNDER_INT)
+#define INT_ENABLE_MASK (CONTROL_RX_OVER_INT | CONTROL_TX_UNDER_INT)
 
 #define REG_CONTROL		(0x00)
 #define REG_FRAME_SIZE		(0x04)
@@ -133,10 +132,15 @@ static inline void mchp_corespi_disable(struct mchp_corespi *spi)
 	mchp_corespi_write(spi, REG_CONTROL, control);
 }
 
-static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi)
+static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi, int fifo_max)
 {
-	while (spi->rx_len >= spi->n_bytes && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)) {
-		u32 data = mchp_corespi_read(spi, REG_RX_DATA);
+	for (int i = 0; i < fifo_max; i++) {
+		u32 data;
+
+		while (mchp_corespi_read(spi, REG_STATUS) & STATUS_RXFIFO_EMPTY)
+			;
+
+		data = mchp_corespi_read(spi, REG_RX_DATA);
 
 		spi->rx_len -= spi->n_bytes;
 
@@ -211,11 +215,10 @@ static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
 	mchp_corespi_write(spi, REG_FRAMESUP, len);
 }
 
-static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi)
+static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi, int fifo_max)
 {
-	int fifo_max, i = 0;
+	int i = 0;
 
-	fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
 	mchp_corespi_set_xfer_size(spi, fifo_max);
 
 	while ((i < fifo_max) && !(mchp_corespi_read(spi, REG_STATUS) & STATUS_TXFIFO_FULL)) {
@@ -413,19 +416,6 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
 	if (intfield == 0)
 		return IRQ_NONE;
 
-	if (intfield & INT_TXDONE)
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_TXDONE);
-
-	if (intfield & INT_RXRDY) {
-		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
-
-		if (spi->rx_len)
-			mchp_corespi_read_fifo(spi);
-	}
-
-	if (!spi->rx_len && !spi->tx_len)
-		finalise = true;
-
 	if (intfield & INT_RX_CHANNEL_OVERFLOW) {
 		mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
 		finalise = true;
@@ -512,9 +502,14 @@ static int mchp_corespi_transfer_one(struct spi_controller *host,
 
 	mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
 
-	while (spi->tx_len)
-		mchp_corespi_write_fifo(spi);
+	while (spi->tx_len) {
+		int fifo_max = DIV_ROUND_UP(min(spi->tx_len, FIFO_DEPTH), spi->n_bytes);
+
+		mchp_corespi_write_fifo(spi, fifo_max);
+		mchp_corespi_read_fifo(spi, fifo_max);
+	}
 
+	spi_finalize_current_transfer(host);
 	return 1;
 }
 

From 68c3de7f707e8a70e0a6d8087cf0fe4a3d5dbfb0 Mon Sep 17 00:00:00 2001
From: Brendan King <Brendan.King@imgtec.com>
Date: Wed, 26 Feb 2025 15:43:54 +0000
Subject: [PATCH 1415/2753] drm/imagination: only init job done fences once

Ensure job done fences are only initialised once.

This fixes a memory manager not clean warning from drm_mm_takedown
on module unload.

Cc: stable@vger.kernel.org
Fixes: eaf01ee5ba28 ("drm/imagination: Implement job submission and scheduling")
Signed-off-by: Brendan King <brendan.king@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226-init-done-fences-once-v2-1-c1b2f556b329@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_queue.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_queue.c b/drivers/gpu/drm/imagination/pvr_queue.c
index f3f1c5212df74..43411be930a21 100644
--- a/drivers/gpu/drm/imagination/pvr_queue.c
+++ b/drivers/gpu/drm/imagination/pvr_queue.c
@@ -313,8 +313,9 @@ pvr_queue_cccb_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 static void
 pvr_queue_job_fence_init(struct dma_fence *fence, struct pvr_queue *queue)
 {
-	pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
-			     &queue->job_fence_ctx);
+	if (!fence->ops)
+		pvr_queue_fence_init(fence, queue, &pvr_queue_job_fence_ops,
+				     &queue->job_fence_ctx);
 }
 
 /**

From 1d2eabb6616433ccaa13927811bdfa205e91ba60 Mon Sep 17 00:00:00 2001
From: Alessio Belle <alessio.belle@imgtec.com>
Date: Fri, 21 Feb 2025 10:49:35 +0000
Subject: [PATCH 1416/2753] drm/imagination: Fix timestamps in firmware traces

When firmware traces are enabled, the firmware dumps 48-bit timestamps
for each trace as two 32-bit values, highest 32 bits (of which only 16
useful) first.

The driver was reassembling them the other way round i.e. interpreting
the first value in memory as the lowest 32 bits, and the second value
as the highest 32 bits (then truncated to 16 bits).

Due to this, firmware trace dumps showed very large timestamps even for
traces recorded shortly after GPU boot. The timestamps in these dumps
would also sometimes jump backwards because of the truncation.

Example trace dumped after loading the powervr module and enabling
firmware traces, where each line is commented with the timestamp value
in hexadecimal to better show both issues:

[93540092739584] : Host Sync Partition marker: 1    // 0x551300000000
[28419798597632] : GPU units deinit                 // 0x19d900000000
[28548647616512] : GPU deinit                       // 0x19f700000000

Update logic to reassemble the timestamps halves in the correct order.

Fixes: cb56cd610866 ("drm/imagination: Add firmware trace to debugfs")
Signed-off-by: Alessio Belle <alessio.belle@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250221-fix-fw-trace-timestamps-v1-1-dba4aeb030ca@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
---
 drivers/gpu/drm/imagination/pvr_fw_trace.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/imagination/pvr_fw_trace.c b/drivers/gpu/drm/imagination/pvr_fw_trace.c
index 73707daa4e52d..5dbb636d7d4ff 100644
--- a/drivers/gpu/drm/imagination/pvr_fw_trace.c
+++ b/drivers/gpu/drm/imagination/pvr_fw_trace.c
@@ -333,8 +333,8 @@ static int fw_trace_seq_show(struct seq_file *s, void *v)
 	if (sf_id == ROGUE_FW_SF_LAST)
 		return -EINVAL;
 
-	timestamp = read_fw_trace(trace_seq_data, 1) |
-		((u64)read_fw_trace(trace_seq_data, 2) << 32);
+	timestamp = ((u64)read_fw_trace(trace_seq_data, 1) << 32) |
+		read_fw_trace(trace_seq_data, 2);
 	timestamp = (timestamp & ~ROGUE_FWT_TIMESTAMP_TIME_CLRMSK) >>
 		ROGUE_FWT_TIMESTAMP_TIME_SHIFT;
 

From 2738d06fb4f01145b24c542fb06de538ffc56430 Mon Sep 17 00:00:00 2001
From: Dmitry Panchenko <dmitry@d-systems.ee>
Date: Thu, 20 Feb 2025 17:39:31 +0200
Subject: [PATCH 1417/2753] platform/x86: intel-hid: fix volume buttons on
 Microsoft Surface Go 4 tablet
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Volume buttons on Microsoft Surface Go 4 tablet didn't send any events.
Add Surface Go 4 DMI match to button_array_table to fix this.

Signed-off-by: Dmitry Panchenko <dmitry@d-systems.ee>
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Link: https://lore.kernel.org/r/20250220154016.3620917-1-dmitry@d-systems.ee
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/hid.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/hid.c b/drivers/platform/x86/intel/hid.c
index 927a2993f6160..88a1a9ff2f344 100644
--- a/drivers/platform/x86/intel/hid.c
+++ b/drivers/platform/x86/intel/hid.c
@@ -139,6 +139,13 @@ static const struct dmi_system_id button_array_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 3"),
 		},
 	},
+	{
+		.ident = "Microsoft Surface Go 4",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Microsoft Corporation"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Surface Go 4"),
+		},
+	},
 	{ }
 };
 

From d0d10eaedcb53740883d7e5d53c5e15c879b48fb Mon Sep 17 00:00:00 2001
From: Mingcong Bai <jeffbai@aosc.io>
Date: Sat, 22 Feb 2025 00:48:24 +0800
Subject: [PATCH 1418/2753] platform/x86: thinkpad_acpi: Add battery quirk for
 ThinkPad X131e
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Based on the dmesg messages from the original reporter:

[    4.964073] ACPI: \_SB_.PCI0.LPCB.EC__.HKEY: BCTG evaluated but flagged as error
[    4.964083] thinkpad_acpi: Error probing battery 2

Lenovo ThinkPad X131e also needs this battery quirk.

Reported-by: Fan Yang <804284660@qq.com>
Tested-by: Fan Yang <804284660@qq.com>
Co-developed-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Xi Ruoyao <xry111@xry111.site>
Signed-off-by: Mingcong Bai <jeffbai@aosc.io>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250221164825.77315-1-jeffbai@aosc.io
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/thinkpad_acpi.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 72a10ed2017ce..1cc91173e0127 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -9972,6 +9972,7 @@ static const struct tpacpi_quirk battery_quirk_table[] __initconst = {
 	 * Individual addressing is broken on models that expose the
 	 * primary battery as BAT1.
 	 */
+	TPACPI_Q_LNV('G', '8', true),       /* ThinkPad X131e */
 	TPACPI_Q_LNV('8', 'F', true),       /* Thinkpad X120e */
 	TPACPI_Q_LNV('J', '7', true),       /* B5400 */
 	TPACPI_Q_LNV('J', 'I', true),       /* Thinkpad 11e */

From f317f38e7fbb15a0d8329289fef8cf034938fb4f Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 26 Feb 2025 13:47:27 -0800
Subject: [PATCH 1419/2753] platform/x86/intel/vsec: Add Diamond Rapids support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add PCI ID for the Diamond Rapids Platforms

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250226214728.1256747-1-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/vsec.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 8272f1dd0fbc0..db3c031d17572 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -404,6 +404,11 @@ static const struct intel_vsec_platform_info oobmsm_info = {
 	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_SDSI | VSEC_CAP_TPMI,
 };
 
+/* DMR OOBMSM info */
+static const struct intel_vsec_platform_info dmr_oobmsm_info = {
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_TPMI,
+};
+
 /* TGL info */
 static const struct intel_vsec_platform_info tgl_info = {
 	.caps = VSEC_CAP_TELEMETRY,
@@ -420,6 +425,7 @@ static const struct intel_vsec_platform_info lnl_info = {
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_M		0x7d0d
 #define PCI_DEVICE_ID_INTEL_VSEC_MTL_S		0xad0d
 #define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM		0x09a7
+#define PCI_DEVICE_ID_INTEL_VSEC_OOBMSM_DMR	0x09a1
 #define PCI_DEVICE_ID_INTEL_VSEC_RPL		0xa77d
 #define PCI_DEVICE_ID_INTEL_VSEC_TGL		0x9a0d
 #define PCI_DEVICE_ID_INTEL_VSEC_LNL_M		0x647d
@@ -430,6 +436,7 @@ static const struct pci_device_id intel_vsec_pci_ids[] = {
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_M, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_MTL_S, &mtl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM, &oobmsm_info) },
+	{ PCI_DEVICE_DATA(INTEL, VSEC_OOBMSM_DMR, &dmr_oobmsm_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_RPL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_TGL, &tgl_info) },
 	{ PCI_DEVICE_DATA(INTEL, VSEC_LNL_M, &lnl_info) },

From 172a0f509723fe4741d4b8e9190cf434b18320d8 Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Mon, 3 Mar 2025 13:04:13 +0300
Subject: [PATCH 1420/2753] ALSA: usx2y: validate nrpacks module parameter on
 probe

The module parameter defines number of iso packets per one URB. User is
allowed to set any value to the parameter of type int, which can lead to
various kinds of weird and incorrect behavior like integer overflows,
truncations, etc. Number of packets should be a small non-negative number.

Since this parameter is read-only, its value can be validated on driver
probe.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Link: https://patch.msgid.link/20250303100413.835-1-m.masimov@mt-integration.ru
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/usb/usx2y/usbusx2y.c      | 11 +++++++++++
 sound/usb/usx2y/usbusx2y.h      | 26 ++++++++++++++++++++++++++
 sound/usb/usx2y/usbusx2yaudio.c | 27 ---------------------------
 3 files changed, 37 insertions(+), 27 deletions(-)

diff --git a/sound/usb/usx2y/usbusx2y.c b/sound/usb/usx2y/usbusx2y.c
index 5f81c68fd42b6..5756ff3528a2d 100644
--- a/sound/usb/usx2y/usbusx2y.c
+++ b/sound/usb/usx2y/usbusx2y.c
@@ -151,6 +151,12 @@ static int snd_usx2y_card_used[SNDRV_CARDS];
 static void snd_usx2y_card_private_free(struct snd_card *card);
 static void usx2y_unlinkseq(struct snd_usx2y_async_seq *s);
 
+#ifdef USX2Y_NRPACKS_VARIABLE
+int nrpacks = USX2Y_NRPACKS; /* number of packets per urb */
+module_param(nrpacks, int, 0444);
+MODULE_PARM_DESC(nrpacks, "Number of packets per URB.");
+#endif
+
 /*
  * pipe 4 is used for switching the lamps, setting samplerate, volumes ....
  */
@@ -432,6 +438,11 @@ static int snd_usx2y_probe(struct usb_interface *intf,
 	struct snd_card *card;
 	int err;
 
+#ifdef USX2Y_NRPACKS_VARIABLE
+	if (nrpacks < 0 || nrpacks > USX2Y_NRPACKS_MAX)
+		return -EINVAL;
+#endif
+
 	if (le16_to_cpu(device->descriptor.idVendor) != 0x1604 ||
 	    (le16_to_cpu(device->descriptor.idProduct) != USB_ID_US122 &&
 	     le16_to_cpu(device->descriptor.idProduct) != USB_ID_US224 &&
diff --git a/sound/usb/usx2y/usbusx2y.h b/sound/usb/usx2y/usbusx2y.h
index 391fd7b4ed5ef..6a76d04bf1c7d 100644
--- a/sound/usb/usx2y/usbusx2y.h
+++ b/sound/usb/usx2y/usbusx2y.h
@@ -7,6 +7,32 @@
 
 #define NRURBS	        2
 
+/* Default value used for nr of packs per urb.
+ * 1 to 4 have been tested ok on uhci.
+ * To use 3 on ohci, you'd need a patch:
+ * look for "0000425-linux-2.6.9-rc4-mm1_ohci-hcd.patch.gz" on
+ * "https://bugtrack.alsa-project.org/alsa-bug/bug_view_page.php?bug_id=0000425"
+ *
+ * 1, 2 and 4 work out of the box on ohci, if I recall correctly.
+ * Bigger is safer operation, smaller gives lower latencies.
+ */
+#define USX2Y_NRPACKS 4
+
+#define USX2Y_NRPACKS_MAX 1024
+
+/* If your system works ok with this module's parameter
+ * nrpacks set to 1, you might as well comment
+ * this define out, and thereby produce smaller, faster code.
+ * You'd also set USX2Y_NRPACKS to 1 then.
+ */
+#define USX2Y_NRPACKS_VARIABLE 1
+
+#ifdef USX2Y_NRPACKS_VARIABLE
+extern int nrpacks;
+#define nr_of_packs() nrpacks
+#else
+#define nr_of_packs() USX2Y_NRPACKS
+#endif
 
 #define URBS_ASYNC_SEQ 10
 #define URB_DATA_LEN_ASYNC_SEQ 32
diff --git a/sound/usb/usx2y/usbusx2yaudio.c b/sound/usb/usx2y/usbusx2yaudio.c
index f540f46a0b143..acca8bead82e5 100644
--- a/sound/usb/usx2y/usbusx2yaudio.c
+++ b/sound/usb/usx2y/usbusx2yaudio.c
@@ -28,33 +28,6 @@
 #include "usx2y.h"
 #include "usbusx2y.h"
 
-/* Default value used for nr of packs per urb.
- * 1 to 4 have been tested ok on uhci.
- * To use 3 on ohci, you'd need a patch:
- * look for "0000425-linux-2.6.9-rc4-mm1_ohci-hcd.patch.gz" on
- * "https://bugtrack.alsa-project.org/alsa-bug/bug_view_page.php?bug_id=0000425"
- *
- * 1, 2 and 4 work out of the box on ohci, if I recall correctly.
- * Bigger is safer operation, smaller gives lower latencies.
- */
-#define USX2Y_NRPACKS 4
-
-/* If your system works ok with this module's parameter
- * nrpacks set to 1, you might as well comment
- * this define out, and thereby produce smaller, faster code.
- * You'd also set USX2Y_NRPACKS to 1 then.
- */
-#define USX2Y_NRPACKS_VARIABLE 1
-
-#ifdef USX2Y_NRPACKS_VARIABLE
-static int nrpacks = USX2Y_NRPACKS; /* number of packets per urb */
-#define  nr_of_packs() nrpacks
-module_param(nrpacks, int, 0444);
-MODULE_PARM_DESC(nrpacks, "Number of packets per URB.");
-#else
-#define nr_of_packs() USX2Y_NRPACKS
-#endif
-
 static int usx2y_urb_capt_retire(struct snd_usx2y_substream *subs)
 {
 	struct urb	*urb = subs->completed_urb;

From 5cfe5612ca9590db69b9be29dc83041dbf001108 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 17 Feb 2025 17:02:42 +0100
Subject: [PATCH 1421/2753] netfilter: nft_ct: Use __refcount_inc() for per-CPU
 nft_ct_pcpu_template.

nft_ct_pcpu_template is a per-CPU variable and relies on disabled BH for its
locking. The refcounter is read and if its value is set to one then the
refcounter is incremented and variable is used - otherwise it is already
in use and left untouched.

Without per-CPU locking in local_bh_disable() on PREEMPT_RT the
read-then-increment operation is not atomic and therefore racy.

This can be avoided by using unconditionally __refcount_inc() which will
increment counter and return the old value as an atomic operation.
In case the returned counter is not one, the variable is in use and we
need to decrement counter. Otherwise we can use it.

Use __refcount_inc() instead of read and a conditional increment.

Fixes: edee4f1e9245 ("netfilter: nft_ct: add zone id set support")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_ct.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c
index 2e59aba681a13..d526e69a2a2b8 100644
--- a/net/netfilter/nft_ct.c
+++ b/net/netfilter/nft_ct.c
@@ -230,6 +230,7 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 	enum ip_conntrack_info ctinfo;
 	u16 value = nft_reg_load16(&regs->data[priv->sreg]);
 	struct nf_conn *ct;
+	int oldcnt;
 
 	ct = nf_ct_get(skb, &ctinfo);
 	if (ct) /* already tracked */
@@ -250,10 +251,11 @@ static void nft_ct_set_zone_eval(const struct nft_expr *expr,
 
 	ct = this_cpu_read(nft_ct_pcpu_template);
 
-	if (likely(refcount_read(&ct->ct_general.use) == 1)) {
-		refcount_inc(&ct->ct_general.use);
+	__refcount_inc(&ct->ct_general.use, &oldcnt);
+	if (likely(oldcnt == 1)) {
 		nf_ct_zone_add(ct, &zone);
 	} else {
+		refcount_dec(&ct->ct_general.use);
 		/* previous skb got queued to userspace, allocate temporary
 		 * one until percpu template can be reused.
 		 */

From 4363f02a39e25e80e68039b4323c570b0848ec66 Mon Sep 17 00:00:00 2001
From: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Date: Mon, 3 Mar 2025 14:55:52 +0800
Subject: [PATCH 1422/2753] ASoC: Intel: sof_sdw: Fix unlikely uninitialized
 variable use in create_sdw_dailinks()

Initialize current_be_id to 0 to handle the unlikely case when there are
no devices connected to a DAI.
In this case create_sdw_dailink() would return without touching the passed
pointer to current_be_id.

Found by gcc -fanalyzer

Fixes: 59bf457d8055 ("ASoC: intel: sof_sdw: Factor out SoundWire DAI creation")
Signed-off-by: Peter Ujfalusi <peter.ujfalusi@linux.intel.com>
Cc: stable@vger.kernel.org
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Link: https://patch.msgid.link/20250303065552.78328-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/intel/boards/sof_sdw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/intel/boards/sof_sdw.c b/sound/soc/intel/boards/sof_sdw.c
index c13064c777261..90dafa810b2ec 100644
--- a/sound/soc/intel/boards/sof_sdw.c
+++ b/sound/soc/intel/boards/sof_sdw.c
@@ -954,7 +954,7 @@ static int create_sdw_dailinks(struct snd_soc_card *card,
 
 	/* generate DAI links by each sdw link */
 	while (sof_dais->initialised) {
-		int current_be_id;
+		int current_be_id = 0;
 
 		ret = create_sdw_dailink(card, sof_dais, dai_links,
 					 &current_be_id, codec_conf);

From d776f016d24816f15033169dcd081f077b6c10f4 Mon Sep 17 00:00:00 2001
From: Alexey Klimov <alexey.klimov@linaro.org>
Date: Fri, 21 Feb 2025 04:40:24 +0000
Subject: [PATCH 1423/2753] ASoC: codecs: wsa884x: report temps to hwmon in
 millidegree of Celsius
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Temperatures are reported in units of Celsius however hwmon expects
values to be in millidegree of Celsius. Userspace tools observe values
close to zero and report it as "Not available" or incorrect values like
0C or 1C. Add a simple conversion to fix that.

Before the change:

wsa884x-virtual-0
Adapter: Virtual device
temp1:         +0.0°C
--
wsa884x-virtual-0
Adapter: Virtual device
temp1:         +0.0°C

Also reported as N/A before first amplifier power on.

After this change and initial wsa884x power on:

wsa884x-virtual-0
Adapter: Virtual device
temp1:        +39.0°C
--
wsa884x-virtual-0
Adapter: Virtual device
temp1:        +37.0°C

Tested on sm8550 only.

Cc: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Cc: Srinivas Kandagatla <srinivas.kandagatla@linaro.org>
Signed-off-by: Alexey Klimov <alexey.klimov@linaro.org>
Link: https://patch.msgid.link/20250221044024.1207921-1-alexey.klimov@linaro.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wsa884x.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c
index 86df5152c547b..560a2c04b6955 100644
--- a/sound/soc/codecs/wsa884x.c
+++ b/sound/soc/codecs/wsa884x.c
@@ -1875,7 +1875,7 @@ static int wsa884x_get_temp(struct wsa884x_priv *wsa884x, long *temp)
 		 * Reading temperature is possible only when Power Amplifier is
 		 * off. Report last cached data.
 		 */
-		*temp = wsa884x->temperature;
+		*temp = wsa884x->temperature * 1000;
 		return 0;
 	}
 
@@ -1934,7 +1934,7 @@ static int wsa884x_get_temp(struct wsa884x_priv *wsa884x, long *temp)
 	if ((val > WSA884X_LOW_TEMP_THRESHOLD) &&
 	    (val < WSA884X_HIGH_TEMP_THRESHOLD)) {
 		wsa884x->temperature = val;
-		*temp = val;
+		*temp = val * 1000;
 		ret = 0;
 	} else {
 		ret = -EAGAIN;

From 3d6c9dd4cb3013fe83524949b914f1497855e3de Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Sat, 22 Feb 2025 23:56:59 +0100
Subject: [PATCH 1424/2753] ASoC: tegra: Fix ADX S24_LE audio format

Commit 4204eccc7b2a ("ASoC: tegra: Add support for S24_LE audio format")
added support for the S24_LE audio format, but duplicated S16_LE in
OUT_DAI() for ADX instead.

Fix this by adding support for the S24_LE audio format.

Compile-tested only.

Cc: stable@vger.kernel.org
Fixes: 4204eccc7b2a ("ASoC: tegra: Add support for S24_LE audio format")
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250222225700.539673-2-thorsten.blum@linux.dev
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/tegra/tegra210_adx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/soc/tegra/tegra210_adx.c b/sound/soc/tegra/tegra210_adx.c
index 3e6e8f51f380b..0aa93b948378f 100644
--- a/sound/soc/tegra/tegra210_adx.c
+++ b/sound/soc/tegra/tegra210_adx.c
@@ -264,7 +264,7 @@ static const struct snd_soc_dai_ops tegra210_adx_out_dai_ops = {
 			.rates = SNDRV_PCM_RATE_8000_192000,	\
 			.formats = SNDRV_PCM_FMTBIT_S8 |	\
 				   SNDRV_PCM_FMTBIT_S16_LE |	\
-				   SNDRV_PCM_FMTBIT_S16_LE |	\
+				   SNDRV_PCM_FMTBIT_S24_LE |	\
 				   SNDRV_PCM_FMTBIT_S32_LE,	\
 		},						\
 		.capture = {					\
@@ -274,7 +274,7 @@ static const struct snd_soc_dai_ops tegra210_adx_out_dai_ops = {
 			.rates = SNDRV_PCM_RATE_8000_192000,	\
 			.formats = SNDRV_PCM_FMTBIT_S8 |	\
 				   SNDRV_PCM_FMTBIT_S16_LE |	\
-				   SNDRV_PCM_FMTBIT_S16_LE |	\
+				   SNDRV_PCM_FMTBIT_S24_LE |	\
 				   SNDRV_PCM_FMTBIT_S32_LE,	\
 		},						\
 		.ops = &tegra210_adx_out_dai_ops,		\

From 64e6a754d33d31aa844b3ee66fb93ac84ca1565e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 27 Feb 2025 08:26:42 +0000
Subject: [PATCH 1425/2753] llc: do not use skb_get() before dev_queue_xmit()

syzbot is able to crash hosts [1], using llc and devices
not supporting IFF_TX_SKB_SHARING.

In this case, e1000 driver calls eth_skb_pad(), while
the skb is shared.

Simply replace skb_get() by skb_clone() in net/llc/llc_s_ac.c

Note that e1000 driver might have an issue with pktgen,
because it does not clear IFF_TX_SKB_SHARING, this is an
orthogonal change.

We need to audit other skb_get() uses in net/llc.

[1]

kernel BUG at net/core/skbuff.c:2178 !
Oops: invalid opcode: 0000 [#1] PREEMPT SMP KASAN NOPTI
CPU: 0 UID: 0 PID: 16371 Comm: syz.2.2764 Not tainted 6.14.0-rc4-syzkaller-00052-gac9c34d1e45a #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
 RIP: 0010:pskb_expand_head+0x6ce/0x1240 net/core/skbuff.c:2178
Call Trace:
 <TASK>
  __skb_pad+0x18a/0x610 net/core/skbuff.c:2466
  __skb_put_padto include/linux/skbuff.h:3843 [inline]
  skb_put_padto include/linux/skbuff.h:3862 [inline]
  eth_skb_pad include/linux/etherdevice.h:656 [inline]
  e1000_xmit_frame+0x2d99/0x5800 drivers/net/ethernet/intel/e1000/e1000_main.c:3128
  __netdev_start_xmit include/linux/netdevice.h:5151 [inline]
  netdev_start_xmit include/linux/netdevice.h:5160 [inline]
  xmit_one net/core/dev.c:3806 [inline]
  dev_hard_start_xmit+0x9a/0x7b0 net/core/dev.c:3822
  sch_direct_xmit+0x1ae/0xc30 net/sched/sch_generic.c:343
  __dev_xmit_skb net/core/dev.c:4045 [inline]
  __dev_queue_xmit+0x13d4/0x43e0 net/core/dev.c:4621
  dev_queue_xmit include/linux/netdevice.h:3313 [inline]
  llc_sap_action_send_test_c+0x268/0x320 net/llc/llc_s_ac.c:144
  llc_exec_sap_trans_actions net/llc/llc_sap.c:153 [inline]
  llc_sap_next_state net/llc/llc_sap.c:182 [inline]
  llc_sap_state_process+0x239/0x510 net/llc/llc_sap.c:209
  llc_ui_sendmsg+0xd0d/0x14e0 net/llc/af_llc.c:993
  sock_sendmsg_nosec net/socket.c:718 [inline]

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+da65c993ae113742a25f@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67c020c0.050a0220.222324.0011.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/llc/llc_s_ac.c | 49 +++++++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 22 deletions(-)

diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c
index 06fb8e6944b06..7a0cae9a81114 100644
--- a/net/llc/llc_s_ac.c
+++ b/net/llc/llc_s_ac.c
@@ -24,7 +24,7 @@
 #include <net/llc_s_ac.h>
 #include <net/llc_s_ev.h>
 #include <net/llc_sap.h>
-
+#include <net/sock.h>
 
 /**
  *	llc_sap_action_unitdata_ind - forward UI PDU to network layer
@@ -40,6 +40,26 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb)
 	return 0;
 }
 
+static int llc_prepare_and_xmit(struct sk_buff *skb)
+{
+	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
+	struct sk_buff *nskb;
+	int rc;
+
+	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
+	if (rc)
+		return rc;
+
+	nskb = skb_clone(skb, GFP_ATOMIC);
+	if (!nskb)
+		return -ENOMEM;
+
+	if (skb->sk)
+		skb_set_owner_w(nskb, skb->sk);
+
+	return dev_queue_xmit(nskb);
+}
+
 /**
  *	llc_sap_action_send_ui - sends UI PDU resp to UNITDATA REQ to MAC layer
  *	@sap: SAP
@@ -52,17 +72,12 @@ int llc_sap_action_unitdata_ind(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_ui_cmd(skb);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 /**
@@ -77,17 +92,12 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U_XID, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 /**
@@ -133,17 +143,12 @@ int llc_sap_action_send_xid_r(struct llc_sap *sap, struct sk_buff *skb)
 int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb)
 {
 	struct llc_sap_state_ev *ev = llc_sap_ev(skb);
-	int rc;
 
 	llc_pdu_header_init(skb, LLC_PDU_TYPE_U, ev->saddr.lsap,
 			    ev->daddr.lsap, LLC_PDU_CMD);
 	llc_pdu_init_as_test_cmd(skb);
-	rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac);
-	if (likely(!rc)) {
-		skb_get(skb);
-		rc = dev_queue_xmit(skb);
-	}
-	return rc;
+
+	return llc_prepare_and_xmit(skb);
 }
 
 int llc_sap_action_send_test_r(struct llc_sap *sap, struct sk_buff *skb)

From 10fce7ebe888fa8c97eee7e317a47e7603e5e78d Mon Sep 17 00:00:00 2001
From: Xinghuo Chen <xinghuo.chen@foxmail.com>
Date: Mon, 3 Mar 2025 07:57:33 -0500
Subject: [PATCH 1426/2753] hwmon: fix a NULL vs IS_ERR_OR_NULL() check in
 xgene_hwmon_probe()

The devm_memremap() function returns error pointers on error,
it doesn't return NULL.

Fixes: c7cefce03e69 ("hwmon: (xgene) access mailbox as RAM")
Signed-off-by: Xinghuo Chen <xinghuo.chen@foxmail.com>
Link: https://lore.kernel.org/r/tencent_9AD8E7683EC29CAC97496B44F3F865BA070A@qq.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/xgene-hwmon.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 1e3bd129a922d..7087197383c96 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -706,7 +706,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 			goto out;
 		}
 
-		if (!ctx->pcc_comm_addr) {
+		if (IS_ERR_OR_NULL(ctx->pcc_comm_addr)) {
 			dev_err(&pdev->dev,
 				"Failed to ioremap PCC comm region\n");
 			rc = -ENOMEM;

From 23e0832d6d7be2d3c713f9390c060b6f1c48bf36 Mon Sep 17 00:00:00 2001
From: Philipp Stanner <phasta@kernel.org>
Date: Tue, 18 Feb 2025 13:41:50 +0100
Subject: [PATCH 1427/2753] drm/sched: Fix preprocessor guard

When writing the header guard for gpu_scheduler_trace.h, a typo,
apparently, occurred.

Fix the typo and document the scope of the guard.

Fixes: 353da3c520b4 ("drm/amdgpu: add tracepoint for scheduler (v2)")
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Signed-off-by: Philipp Stanner <phasta@kernel.org>
Link: https://patchwork.freedesktop.org/patch/msgid/20250218124149.118002-2-phasta@kernel.org
---
 drivers/gpu/drm/scheduler/gpu_scheduler_trace.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
index c75302ca3427c..f56e77e7f6d02 100644
--- a/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
+++ b/drivers/gpu/drm/scheduler/gpu_scheduler_trace.h
@@ -21,7 +21,7 @@
  *
  */
 
-#if !defined(_GPU_SCHED_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#if !defined(_GPU_SCHED_TRACE_H_) || defined(TRACE_HEADER_MULTI_READ)
 #define _GPU_SCHED_TRACE_H_
 
 #include <linux/stringify.h>
@@ -106,7 +106,7 @@ TRACE_EVENT(drm_sched_job_wait_dep,
 		      __entry->seqno)
 );
 
-#endif
+#endif /* _GPU_SCHED_TRACE_H_ */
 
 /* This part must be outside protection */
 #undef TRACE_INCLUDE_PATH

From b2653cd3b75f62f29b72df4070e20357acb52bc4 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 26 Feb 2025 17:25:32 -0800
Subject: [PATCH 1428/2753] KVM: SVM: Save host DR masks on CPUs with DebugSwap

When running SEV-SNP guests on a CPU that supports DebugSwap, always save
the host's DR0..DR3 mask MSR values irrespective of whether or not
DebugSwap is enabled, to ensure the host values aren't clobbered by the
CPU.  And for now, also save DR0..DR3, even though doing so isn't
necessary (see below).

SVM_VMGEXIT_AP_CREATE is deeply flawed in that it allows the *guest* to
create a VMSA with guest-controlled SEV_FEATURES.  A well behaved guest
can inform the hypervisor, i.e. KVM, of its "requested" features, but on
CPUs without ALLOWED_SEV_FEATURES support, nothing prevents the guest from
lying about which SEV features are being enabled (or not!).

If a misbehaving guest enables DebugSwap in a secondary vCPU's VMSA, the
CPU will load the DR0..DR3 mask MSRs on #VMEXIT, i.e. will clobber the
MSRs with '0' if KVM doesn't save its desired value.

Note, DR0..DR3 themselves are "ok", as DR7 is reset on #VMEXIT, and KVM
restores all DRs in common x86 code as needed via hw_breakpoint_restore().
I.e. there is no risk of host DR0..DR3 being clobbered (when it matters).
However, there is a flaw in the opposite direction; because the guest can
lie about enabling DebugSwap, i.e. can *disable* DebugSwap without KVM's
knowledge, KVM must not rely on the CPU to restore DRs.  Defer fixing
that wart, as it's more of a documentation issue than a bug in the code.

Note, KVM added support for DebugSwap on commit d1f85fbe836e ("KVM: SEV:
Enable data breakpoints in SEV-ES"), but that is not an appropriate Fixes,
as the underlying flaw exists in hardware, not in KVM.  I.e. all kernels
that support SEV-SNP need to be patched, not just kernels with KVM's full
support for DebugSwap (ignoring that DebugSwap support landed first).

Opportunistically fix an incorrect statement in the comment; on CPUs
without DebugSwap, the CPU does NOT save or load debug registers, i.e.

Fixes: e366f92ea99e ("KVM: SEV: Support SEV-SNP AP Creation NAE event")
Cc: stable@vger.kernel.org
Cc: Naveen N Rao <naveen@kernel.org>
Cc: Kim Phillips <kim.phillips@amd.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Alexey Kardashevskiy <aik@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 13 ++++++++++---
 1 file changed, 10 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a2a794c320503..ef057c85a67ce 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4580,6 +4580,8 @@ void sev_es_vcpu_reset(struct vcpu_svm *svm)
 
 void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa)
 {
+	struct kvm *kvm = svm->vcpu.kvm;
+
 	/*
 	 * All host state for SEV-ES guests is categorized into three swap types
 	 * based on how it is handled by hardware during a world switch:
@@ -4603,10 +4605,15 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
-	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU both
-	 * saves and loads debug registers (Type-A).
+	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
+	 * not save or load debug registers.  Sadly, on CPUs without
+	 * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling
+	 * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create".
+	 * Save all registers if DebugSwap is supported to prevent host state
+	 * from being clobbered by a misbehaving guest.
 	 */
-	if (sev_vcpu_has_debug_swap(svm)) {
+	if (sev_vcpu_has_debug_swap(svm) ||
+	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
 		hostsa->dr0 = native_get_debugreg(0);
 		hostsa->dr1 = native_get_debugreg(1);
 		hostsa->dr2 = native_get_debugreg(2);

From 807cb9ce2ed9a1b6e79e70fb2cdb7860f1517dcc Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 26 Feb 2025 17:25:33 -0800
Subject: [PATCH 1429/2753] KVM: SVM: Don't rely on DebugSwap to restore host
 DR0..DR3

Never rely on the CPU to restore/load host DR0..DR3 values, even if the
CPU supports DebugSwap, as there are no guarantees that SNP guests will
actually enable DebugSwap on APs.  E.g. if KVM were to rely on the CPU to
load DR0..DR3 and skipped them during hw_breakpoint_restore(), KVM would
run with clobbered-to-zero DRs if an SNP guest created APs without
DebugSwap enabled.

Update the comment to explain the dangers, and hopefully prevent breaking
KVM in the future.

Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20250227012541.3234589-3-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/sev.c | 21 ++++++++++++---------
 1 file changed, 12 insertions(+), 9 deletions(-)

diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index ef057c85a67ce..080f8cecd7ca6 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -4606,18 +4606,21 @@ void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_are
 	/*
 	 * If DebugSwap is enabled, debug registers are loaded but NOT saved by
 	 * the CPU (Type-B). If DebugSwap is disabled/unsupported, the CPU does
-	 * not save or load debug registers.  Sadly, on CPUs without
-	 * ALLOWED_SEV_FEATURES, KVM can't prevent SNP guests from enabling
-	 * DebugSwap on secondary vCPUs without KVM's knowledge via "AP Create".
-	 * Save all registers if DebugSwap is supported to prevent host state
-	 * from being clobbered by a misbehaving guest.
+	 * not save or load debug registers.  Sadly, KVM can't prevent SNP
+	 * guests from lying about DebugSwap on secondary vCPUs, i.e. the
+	 * SEV_FEATURES provided at "AP Create" isn't guaranteed to match what
+	 * the guest has actually enabled (or not!) in the VMSA.
+	 *
+	 * If DebugSwap is *possible*, save the masks so that they're restored
+	 * if the guest enables DebugSwap.  But for the DRs themselves, do NOT
+	 * rely on the CPU to restore the host values; KVM will restore them as
+	 * needed in common code, via hw_breakpoint_restore().  Note, KVM does
+	 * NOT support virtualizing Breakpoint Extensions, i.e. the mask MSRs
+	 * don't need to be restored per se, KVM just needs to ensure they are
+	 * loaded with the correct values *if* the CPU writes the MSRs.
 	 */
 	if (sev_vcpu_has_debug_swap(svm) ||
 	    (sev_snp_guest(kvm) && cpu_feature_enabled(X86_FEATURE_DEBUG_SWAP))) {
-		hostsa->dr0 = native_get_debugreg(0);
-		hostsa->dr1 = native_get_debugreg(1);
-		hostsa->dr2 = native_get_debugreg(2);
-		hostsa->dr3 = native_get_debugreg(3);
 		hostsa->dr0_addr_mask = amd_get_dr_addr_mask(0);
 		hostsa->dr1_addr_mask = amd_get_dr_addr_mask(1);
 		hostsa->dr2_addr_mask = amd_get_dr_addr_mask(2);

From d88ed5fb7c88f404e57fe2b2a6d19fefc35b4dc7 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Feb 2025 15:08:04 -0800
Subject: [PATCH 1430/2753] KVM: selftests: Ensure all vCPUs hit -EFAULT during
 initial RO stage

During the initial mprotect(RO) stage of mmu_stress_test, keep vCPUs
spinning until all vCPUs have hit -EFAULT, i.e. until all vCPUs have tried
to write to a read-only page.  If a vCPU manages to complete an entire
iteration of the loop without hitting a read-only page, *and* the vCPU
observes mprotect_ro_done before starting a second iteration, then the
vCPU will prematurely fall through to GUEST_SYNC(3) (on x86 and arm64) and
get out of sequence.

Replace the "do-while (!r)" loop around the associated _vcpu_run() with
a single invocation, as barring a KVM bug, the vCPU is guaranteed to hit
-EFAULT, and retrying on success is super confusion, hides KVM bugs, and
complicates this fix.  The do-while loop was semi-unintentionally added
specifically to fudge around a KVM x86 bug, and said bug is unhittable
without modifying the test to force x86 down the !(x86||arm64) path.

On x86, if forced emulation is enabled, vcpu_arch_put_guest() may trigger
emulation of the store to memory.  Due a (very, very) longstanding bug in
KVM x86's emulator, emulate writes to guest memory that fail during
__kvm_write_guest_page() unconditionally return KVM_EXIT_MMIO.  While that
is desirable in the !memslot case, it's wrong in this case as the failure
happens due to __copy_to_user() hitting a read-only page, not an emulated
MMIO region.

But as above, x86 only uses vcpu_arch_put_guest() if the __x86_64__ guards
are clobbered to force x86 down the common path, and of course the
unexpected MMIO is a KVM bug, i.e. *should* cause a test failure.

Fixes: b6c304aec648 ("KVM: selftests: Verify KVM correctly handles mprotect(PROT_READ)")
Reported-by: Yan Zhao <yan.y.zhao@intel.com>
Closes: https://lore.kernel.org/all/20250208105318.16861-1-yan.y.zhao@intel.com
Debugged-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Tested-by: Yan Zhao <yan.y.zhao@intel.com>
Link: https://lore.kernel.org/r/20250228230804.3845860-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/mmu_stress_test.c | 21 ++++++++++++-------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/kvm/mmu_stress_test.c b/tools/testing/selftests/kvm/mmu_stress_test.c
index d9c76b4c0d88a..6a437d2be9fa4 100644
--- a/tools/testing/selftests/kvm/mmu_stress_test.c
+++ b/tools/testing/selftests/kvm/mmu_stress_test.c
@@ -18,6 +18,7 @@
 #include "ucall_common.h"
 
 static bool mprotect_ro_done;
+static bool all_vcpus_hit_ro_fault;
 
 static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 {
@@ -36,9 +37,9 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 
 	/*
 	 * Write to the region while mprotect(PROT_READ) is underway.  Keep
-	 * looping until the memory is guaranteed to be read-only, otherwise
-	 * vCPUs may complete their writes and advance to the next stage
-	 * prematurely.
+	 * looping until the memory is guaranteed to be read-only and a fault
+	 * has occurred, otherwise vCPUs may complete their writes and advance
+	 * to the next stage prematurely.
 	 *
 	 * For architectures that support skipping the faulting instruction,
 	 * generate the store via inline assembly to ensure the exact length
@@ -56,7 +57,7 @@ static void guest_code(uint64_t start_gpa, uint64_t end_gpa, uint64_t stride)
 #else
 			vcpu_arch_put_guest(*((volatile uint64_t *)gpa), gpa);
 #endif
-	} while (!READ_ONCE(mprotect_ro_done));
+	} while (!READ_ONCE(mprotect_ro_done) || !READ_ONCE(all_vcpus_hit_ro_fault));
 
 	/*
 	 * Only architectures that write the entire range can explicitly sync,
@@ -81,6 +82,7 @@ struct vcpu_info {
 
 static int nr_vcpus;
 static atomic_t rendezvous;
+static atomic_t nr_ro_faults;
 
 static void rendezvous_with_boss(void)
 {
@@ -148,12 +150,16 @@ static void *vcpu_worker(void *data)
 	 * be stuck on the faulting instruction for other architectures.  Go to
 	 * stage 3 without a rendezvous
 	 */
-	do {
-		r = _vcpu_run(vcpu);
-	} while (!r);
+	r = _vcpu_run(vcpu);
 	TEST_ASSERT(r == -1 && errno == EFAULT,
 		    "Expected EFAULT on write to RO memory, got r = %d, errno = %d", r, errno);
 
+	atomic_inc(&nr_ro_faults);
+	if (atomic_read(&nr_ro_faults) == nr_vcpus) {
+		WRITE_ONCE(all_vcpus_hit_ro_fault, true);
+		sync_global_to_guest(vm, all_vcpus_hit_ro_fault);
+	}
+
 #if defined(__x86_64__) || defined(__aarch64__)
 	/*
 	 * Verify *all* writes from the guest hit EFAULT due to the VMA now
@@ -378,7 +384,6 @@ int main(int argc, char *argv[])
 	rendezvous_with_vcpus(&time_run2, "run 2");
 
 	mprotect(mem, slot_size, PROT_READ);
-	usleep(10);
 	mprotect_ro_done = true;
 	sync_global_to_guest(vm, mprotect_ro_done);
 

From 3b2d3db368013729fd2167a0d91fec821dba807c Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 28 Feb 2025 15:38:52 -0800
Subject: [PATCH 1431/2753] KVM: selftests: Fix printf() format goof in SEV
 smoke test

Print out the index of mismatching XSAVE bytes using unsigned decimal
format.  Some versions of clang complain about trying to print an integer
as an unsigned char.

  x86/sev_smoke_test.c:55:51: error: format specifies type 'unsigned char'
                                     but the argument has type 'int' [-Werror,-Wformat]

Fixes: 8c53183dbaa2 ("selftests: kvm: add test for transferring FPU state into VMSA")
Link: https://lore.kernel.org/r/20250228233852.3855676-1-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 tools/testing/selftests/kvm/x86/sev_smoke_test.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kvm/x86/sev_smoke_test.c b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
index a1a688e752666..d97816dc476a2 100644
--- a/tools/testing/selftests/kvm/x86/sev_smoke_test.c
+++ b/tools/testing/selftests/kvm/x86/sev_smoke_test.c
@@ -52,7 +52,8 @@ static void compare_xsave(u8 *from_host, u8 *from_guest)
 	bool bad = false;
 	for (i = 0; i < 4095; i++) {
 		if (from_host[i] != from_guest[i]) {
-			printf("mismatch at %02hhx | %02hhx %02hhx\n", i, from_host[i], from_guest[i]);
+			printf("mismatch at %u | %02hhx %02hhx\n",
+			       i, from_host[i], from_guest[i]);
 			bad = true;
 		}
 	}

From 9360dfe4cbd62ff1eb8217b815964931523b75b3 Mon Sep 17 00:00:00 2001
From: Andrea Righi <arighi@nvidia.com>
Date: Mon, 3 Mar 2025 18:51:59 +0100
Subject: [PATCH 1432/2753] sched_ext: Validate prev_cpu in
 scx_bpf_select_cpu_dfl()

If a BPF scheduler provides an invalid CPU (outside the nr_cpu_ids
range) as prev_cpu to scx_bpf_select_cpu_dfl() it can cause a kernel
crash.

To prevent this, validate prev_cpu in scx_bpf_select_cpu_dfl() and
trigger an scx error if an invalid CPU is specified.

Fixes: f0e1a0643a59b ("sched_ext: Implement BPF extensible scheduler class")
Cc: stable@vger.kernel.org # v6.12+
Signed-off-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 kernel/sched/ext.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 0f1da199cfc7c..7b9dfee858e79 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6422,6 +6422,9 @@ static bool check_builtin_idle_enabled(void)
 __bpf_kfunc s32 scx_bpf_select_cpu_dfl(struct task_struct *p, s32 prev_cpu,
 				       u64 wake_flags, bool *is_idle)
 {
+	if (!ops_cpu_valid(prev_cpu, NULL))
+		goto prev_cpu;
+
 	if (!check_builtin_idle_enabled())
 		goto prev_cpu;
 

From 8ce2eb9dfac8743d1c423b86339336a5b6a6069e Mon Sep 17 00:00:00 2001
From: Zhu Yanjun <yanjun.zhu@linux.dev>
Date: Sun, 2 Mar 2025 22:54:44 +0100
Subject: [PATCH 1433/2753] RDMA/rxe: Fix the failure of ibv_query_device() and
 ibv_query_device_ex() tests

In rdma-core, the following failures appear.

"
$ ./build/bin/run_tests.py -k device
ssssssss....FF........s
======================================================================
FAIL: test_query_device (tests.test_device.DeviceTest.test_query_device)
Test ibv_query_device()
----------------------------------------------------------------------
Traceback (most recent call last):
   File "/home/ubuntu/rdma-core/tests/test_device.py", line 63, in
   test_query_device
     self.verify_device_attr(attr, dev)
   File "/home/ubuntu/rdma-core/tests/test_device.py", line 200, in
   verify_device_attr
     assert attr.sys_image_guid != 0
            ^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError

======================================================================
FAIL: test_query_device_ex (tests.test_device.DeviceTest.test_query_device_ex)
Test ibv_query_device_ex()
----------------------------------------------------------------------
Traceback (most recent call last):
   File "/home/ubuntu/rdma-core/tests/test_device.py", line 222, in
   test_query_device_ex
     self.verify_device_attr(attr_ex.orig_attr, dev)
   File "/home/ubuntu/rdma-core/tests/test_device.py", line 200, in
   verify_device_attr
     assert attr.sys_image_guid != 0
            ^^^^^^^^^^^^^^^^^^^^^^^^
AssertionError
"

The root cause is: before a net device is set with rxe, this net device
is used to generate a sys_image_guid.

Fixes: 2ac5415022d1 ("RDMA/rxe: Remove the direct link to net_device")
Signed-off-by: Zhu Yanjun <yanjun.zhu@linux.dev>
Link: https://patch.msgid.link/20250302215444.3742072-1-yanjun.zhu@linux.dev
Reviewed-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Tested-by: Daisuke Matsuda <matsuda-daisuke@fujitsu.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/sw/rxe/rxe.c | 25 ++++++-------------------
 1 file changed, 6 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 1ba4a0c8726ae..e27478fe9456c 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -38,10 +38,8 @@ void rxe_dealloc(struct ib_device *ib_dev)
 }
 
 /* initialize rxe device parameters */
-static void rxe_init_device_param(struct rxe_dev *rxe)
+static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 {
-	struct net_device *ndev;
-
 	rxe->max_inline_data			= RXE_MAX_INLINE_DATA;
 
 	rxe->attr.vendor_id			= RXE_VENDOR_ID;
@@ -74,15 +72,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_pkeys			= RXE_MAX_PKEYS;
 	rxe->attr.local_ca_ack_delay		= RXE_LOCAL_CA_ACK_DELAY;
 
-	ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
-	if (!ndev)
-		return;
-
 	addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
 			ndev->dev_addr);
 
-	dev_put(ndev);
-
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
 }
 
@@ -115,18 +107,13 @@ static void rxe_init_port_param(struct rxe_port *port)
 /* initialize port state, note IB convention that HCA ports are always
  * numbered from 1
  */
-static void rxe_init_ports(struct rxe_dev *rxe)
+static void rxe_init_ports(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	struct rxe_port *port = &rxe->port;
-	struct net_device *ndev;
 
 	rxe_init_port_param(port);
-	ndev = rxe_ib_device_get_netdev(&rxe->ib_dev);
-	if (!ndev)
-		return;
 	addrconf_addr_eui48((unsigned char *)&port->port_guid,
 			    ndev->dev_addr);
-	dev_put(ndev);
 	spin_lock_init(&port->port_lock);
 }
 
@@ -144,12 +131,12 @@ static void rxe_init_pools(struct rxe_dev *rxe)
 }
 
 /* initialize rxe device state */
-static void rxe_init(struct rxe_dev *rxe)
+static void rxe_init(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	/* init default device parameters */
-	rxe_init_device_param(rxe);
+	rxe_init_device_param(rxe, ndev);
 
-	rxe_init_ports(rxe);
+	rxe_init_ports(rxe, ndev);
 	rxe_init_pools(rxe);
 
 	/* init pending mmap list */
@@ -184,7 +171,7 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
 int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name,
 			struct net_device *ndev)
 {
-	rxe_init(rxe);
+	rxe_init(rxe, ndev);
 	rxe_set_mtu(rxe, mtu);
 
 	return rxe_register_device(rxe, ibdev_name, ndev);

From 82f1f575aa13a66906aff05ab05ffe757227b95f Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Mon, 3 Mar 2025 08:59:36 -0800
Subject: [PATCH 1434/2753] RDMA/bnxt_re: Fix allocation of QP table

Driver is creating QP table too early while probing before
querying firmware capabilities. Driver currently is using
a hard coded values of 64K as size while creating QP table.
This resulted in a crash when firmwre supported QP count is
more than 64K.

To fix the issue, move the QP tabel creation after the firmware
capabilities are queried. Use the firmware returned maximum value
of QPs while creating the QP table.

Fixes: b1b66ae094cd ("bnxt_en: Use FW defined resource limits for RoCE")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1741021178-2569-2-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/bnxt_re.h    |  6 ------
 drivers/infiniband/hw/bnxt_re/main.c       |  3 +--
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.c | 10 +---------
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.h |  3 +--
 drivers/infiniband/hw/bnxt_re/qplib_res.c  |  9 +++++++++
 drivers/infiniband/hw/bnxt_re/qplib_res.h  |  7 +++++++
 6 files changed, 19 insertions(+), 19 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/bnxt_re.h b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
index 3721446c6ba4b..502a79136d4df 100644
--- a/drivers/infiniband/hw/bnxt_re/bnxt_re.h
+++ b/drivers/infiniband/hw/bnxt_re/bnxt_re.h
@@ -53,12 +53,6 @@
 #define BNXT_RE_MAX_MR_SIZE_HIGH	BIT_ULL(39)
 #define BNXT_RE_MAX_MR_SIZE		BNXT_RE_MAX_MR_SIZE_HIGH
 
-#define BNXT_RE_MAX_QPC_COUNT		(64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT		(64 * 1024)
-#define BNXT_RE_MAX_SRQC_COUNT		(64 * 1024)
-#define BNXT_RE_MAX_CQ_COUNT		(64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT_64K	(64 * 1024)
-#define BNXT_RE_MAX_MRW_COUNT_256K	(256 * 1024)
 
 /* Number of MRs to reserve for PF, leaving remainder for VFs */
 #define BNXT_RE_RESVD_MR_FOR_PF         (32 * 1024)
diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c
index a94c8c5387d9e..4659a2f733644 100644
--- a/drivers/infiniband/hw/bnxt_re/main.c
+++ b/drivers/infiniband/hw/bnxt_re/main.c
@@ -2130,8 +2130,7 @@ static int bnxt_re_dev_init(struct bnxt_re_dev *rdev, u8 op_type)
 	 * memory for the function and all child VFs
 	 */
 	rc = bnxt_qplib_alloc_rcfw_channel(&rdev->qplib_res, &rdev->rcfw,
-					   &rdev->qplib_ctx,
-					   BNXT_RE_MAX_QPC_COUNT);
+					   &rdev->qplib_ctx);
 	if (rc) {
 		ibdev_err(&rdev->ibdev,
 			  "Failed to allocate RCFW Channel: %#x\n", rc);
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
index 17e62f22683b1..d230743834282 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.c
@@ -915,7 +915,6 @@ int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 
 void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
 {
-	kfree(rcfw->qp_tbl);
 	kfree(rcfw->crsqe_tbl);
 	bnxt_qplib_free_hwq(rcfw->res, &rcfw->cmdq.hwq);
 	bnxt_qplib_free_hwq(rcfw->res, &rcfw->creq.hwq);
@@ -924,8 +923,7 @@ void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw)
 
 int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 				  struct bnxt_qplib_rcfw *rcfw,
-				  struct bnxt_qplib_ctx *ctx,
-				  int qp_tbl_sz)
+				  struct bnxt_qplib_ctx *ctx)
 {
 	struct bnxt_qplib_hwq_attr hwq_attr = {};
 	struct bnxt_qplib_sg_info sginfo = {};
@@ -969,12 +967,6 @@ int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 	if (!rcfw->crsqe_tbl)
 		goto fail;
 
-	/* Allocate one extra to hold the QP1 entries */
-	rcfw->qp_tbl_size = qp_tbl_sz + 1;
-	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
-			       GFP_KERNEL);
-	if (!rcfw->qp_tbl)
-		goto fail;
 	spin_lock_init(&rcfw->tbl_lock);
 
 	rcfw->max_timeout = res->cctx->hwrm_cmd_max_timeout;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 88814cb3aa741..30e5e1871f642 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -262,8 +262,7 @@ static inline void bnxt_qplib_fill_cmdqmsg(struct bnxt_qplib_cmdqmsg *msg,
 void bnxt_qplib_free_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_alloc_rcfw_channel(struct bnxt_qplib_res *res,
 				  struct bnxt_qplib_rcfw *rcfw,
-				  struct bnxt_qplib_ctx *ctx,
-				  int qp_tbl_sz);
+				  struct bnxt_qplib_ctx *ctx);
 void bnxt_qplib_rcfw_stop_irq(struct bnxt_qplib_rcfw *rcfw, bool kill);
 void bnxt_qplib_disable_rcfw_channel(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_rcfw_start_irq(struct bnxt_qplib_rcfw *rcfw, int msix_vector,
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.c b/drivers/infiniband/hw/bnxt_re/qplib_res.c
index 02922a0987ad7..6cd05207ffedd 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.c
@@ -871,6 +871,7 @@ int bnxt_qplib_init_res(struct bnxt_qplib_res *res)
 
 void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
 {
+	kfree(res->rcfw->qp_tbl);
 	bnxt_qplib_free_sgid_tbl(res, &res->sgid_tbl);
 	bnxt_qplib_free_pd_tbl(&res->pd_tbl);
 	bnxt_qplib_free_dpi_tbl(res, &res->dpi_tbl);
@@ -878,12 +879,20 @@ void bnxt_qplib_free_res(struct bnxt_qplib_res *res)
 
 int bnxt_qplib_alloc_res(struct bnxt_qplib_res *res, struct net_device *netdev)
 {
+	struct bnxt_qplib_rcfw *rcfw = res->rcfw;
 	struct bnxt_qplib_dev_attr *dev_attr;
 	int rc;
 
 	res->netdev = netdev;
 	dev_attr = res->dattr;
 
+	/* Allocate one extra to hold the QP1 entries */
+	rcfw->qp_tbl_size = max_t(u32, BNXT_RE_MAX_QPC_COUNT + 1, dev_attr->max_qp);
+	rcfw->qp_tbl = kcalloc(rcfw->qp_tbl_size, sizeof(struct bnxt_qplib_qp_node),
+			       GFP_KERNEL);
+	if (!rcfw->qp_tbl)
+		return -ENOMEM;
+
 	rc = bnxt_qplib_alloc_sgid_tbl(res, &res->sgid_tbl, dev_attr->max_sgid);
 	if (rc)
 		goto fail;
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 711990232de1c..2fb540f0e7271 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -49,6 +49,13 @@ extern const struct bnxt_qplib_gid bnxt_qplib_gid_zero;
 #define CHIP_NUM_58818          0xd818
 #define CHIP_NUM_57608          0x1760
 
+#define BNXT_RE_MAX_QPC_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_SRQC_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_CQ_COUNT		(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_64K	(64 * 1024)
+#define BNXT_RE_MAX_MRW_COUNT_256K	(256 * 1024)
+
 #define BNXT_QPLIB_DBR_VALID		(0x1UL << 26)
 #define BNXT_QPLIB_DBR_EPOCH_SHIFT	24
 #define BNXT_QPLIB_DBR_TOGGLE_SHIFT	25

From 67ee8d496511ad8e1cb88f72944847e7b3e4e47c Mon Sep 17 00:00:00 2001
From: Kashyap Desai <kashyap.desai@broadcom.com>
Date: Mon, 3 Mar 2025 08:59:37 -0800
Subject: [PATCH 1435/2753] RDMA/bnxt_re: Add missing paranthesis in
 map_qp_id_to_tbl_indx

The modulo operation returns wrong result without the
paranthesis and that resulted in wrong QP table indexing.

Fixes: 84cf229f4001 ("RDMA/bnxt_re: Fix the qp table indexing")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1741021178-2569-3-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_rcfw.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
index 30e5e1871f642..ff873c5f1b259 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_rcfw.h
@@ -284,9 +284,10 @@ int bnxt_qplib_deinit_rcfw(struct bnxt_qplib_rcfw *rcfw);
 int bnxt_qplib_init_rcfw(struct bnxt_qplib_rcfw *rcfw,
 			 struct bnxt_qplib_ctx *ctx, int is_virtfn);
 void bnxt_qplib_mark_qp_error(void *qp_handle);
+
 static inline u32 map_qp_id_to_tbl_indx(u32 qid, struct bnxt_qplib_rcfw *rcfw)
 {
 	/* Last index of the qp_tbl is for QP1 ie. qp_tbl_size - 1*/
-	return (qid == 1) ? rcfw->qp_tbl_size - 1 : qid % rcfw->qp_tbl_size - 2;
+	return (qid == 1) ? rcfw->qp_tbl_size - 1 : (qid % (rcfw->qp_tbl_size - 2));
 }
 #endif /* __BNXT_QPLIB_RCFW_H__ */

From e8e6087c2f7407dfb8c7592bb6dd533e129b2932 Mon Sep 17 00:00:00 2001
From: Preethi G <preethi.gurusiddalingeswaraswamy@broadcom.com>
Date: Mon, 3 Mar 2025 08:59:38 -0800
Subject: [PATCH 1436/2753] RDMA/bnxt_re: Fix reporting maximum SRQs on P7
 chips

Firmware reports support for additional SRQs in the max_srq_ext field.
In CREQ_QUERY_FUNC response, if MAX_SRQ_EXTENDED flag is set, driver
should derive the total number of max SRQs by the summation of
"max_srq" and "max_srq_ext" fields.

Fixes: b1b66ae094cd ("bnxt_en: Use FW defined resource limits for RoCE")
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Preethi G <preethi.gurusiddalingeswaraswamy@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1741021178-2569-4-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_res.h | 5 +++++
 drivers/infiniband/hw/bnxt_re/qplib_sp.c  | 3 +++
 drivers/infiniband/hw/bnxt_re/roce_hsi.h  | 3 ++-
 3 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_res.h b/drivers/infiniband/hw/bnxt_re/qplib_res.h
index 2fb540f0e7271..6a13927674b44 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_res.h
+++ b/drivers/infiniband/hw/bnxt_re/qplib_res.h
@@ -607,4 +607,9 @@ static inline bool _is_cq_coalescing_supported(u16 dev_cap_ext_flags2)
 	return dev_cap_ext_flags2 & CREQ_QUERY_FUNC_RESP_SB_CQ_COALESCING_SUPPORTED;
 }
 
+static inline bool _is_max_srq_ext_supported(u16 dev_cap_ext_flags_2)
+{
+	return !!(dev_cap_ext_flags_2 & CREQ_QUERY_FUNC_RESP_SB_MAX_SRQ_EXTENDED);
+}
+
 #endif /* __BNXT_QPLIB_RES_H__ */
diff --git a/drivers/infiniband/hw/bnxt_re/qplib_sp.c b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
index 4ccd4405355af..f231e886ad9d5 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_sp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_sp.c
@@ -176,6 +176,9 @@ int bnxt_qplib_get_dev_attr(struct bnxt_qplib_rcfw *rcfw)
 	attr->dev_cap_flags = le16_to_cpu(sb->dev_cap_flags);
 	attr->dev_cap_flags2 = le16_to_cpu(sb->dev_cap_ext_flags_2);
 
+	if (_is_max_srq_ext_supported(attr->dev_cap_flags2))
+		attr->max_srq += le16_to_cpu(sb->max_srq_ext);
+
 	bnxt_qplib_query_version(rcfw, attr->fw_ver);
 
 	for (i = 0; i < MAX_TQM_ALLOC_REQ / 4; i++) {
diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index 0ee60fdc18b33..7eceb3e9f4ce5 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -2215,11 +2215,12 @@ struct creq_query_func_resp_sb {
 	#define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE   (0x2UL << 4)
 	#define CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_LAST	\
 			CREQ_QUERY_FUNC_RESP_SB_REQ_RETRANSMISSION_SUPPORT_IQM_MSN_TABLE
+	#define CREQ_QUERY_FUNC_RESP_SB_MAX_SRQ_EXTENDED                         0x40UL
 	#define CREQ_QUERY_FUNC_RESP_SB_MIN_RNR_RTR_RTS_OPT_SUPPORTED            0x1000UL
 	__le16	max_xp_qp_size;
 	__le16	create_qp_batch_size;
 	__le16	destroy_qp_batch_size;
-	__le16	reserved16;
+	__le16  max_srq_ext;
 	__le64	reserved64;
 };
 

From bd1c959f37f384b477f51572331b0dc828bd009a Mon Sep 17 00:00:00 2001
From: Dragan Simic <dsimic@manjaro.org>
Date: Sun, 2 Mar 2025 19:48:03 +0100
Subject: [PATCH 1437/2753] arm64: dts: rockchip: Add avdd HDMI supplies to
 RockPro64 board dtsi

Add missing "avdd-0v9-supply" and "avdd-1v8-supply" properties to the "hdmi"
node in the Pine64 RockPro64 board dtsi file.  To achieve this, also add the
associated "vcca_0v9" regulator that produces the 0.9 V supply, [1][2] which
hasn't been defined previously in the board dtsi file.

This also eliminates the following warnings from the kernel log:

  dwhdmi-rockchip ff940000.hdmi: supply avdd-0v9 not found, using dummy regulator
  dwhdmi-rockchip ff940000.hdmi: supply avdd-1v8 not found, using dummy regulator

There are no functional changes to the way board works with these additions,
because the "vcc1v8_dvp" and "vcca_0v9" regulators are always enabled, [1][2]
but these additions improve the accuracy of hardware description.

These changes apply to the both supported hardware revisions of the Pine64
RockPro64, i.e. to the production-run revisions 2.0 and 2.1. [1][2]

[1] https://files.pine64.org/doc/rockpro64/rockpro64_v21-SCH.pdf
[2] https://files.pine64.org/doc/rockpro64/rockpro64_v20-SCH.pdf

Fixes: e4f3fb490967 ("arm64: dts: rockchip: add initial dts support for Rockpro64")
Cc: stable@vger.kernel.org
Suggested-by: Diederik de Haas <didi.debian@cknow.org>
Signed-off-by: Dragan Simic <dsimic@manjaro.org>
Tested-by: Diederik de Haas <didi.debian@cknow.org>
Link: https://lore.kernel.org/r/df3d7e8fe74ed5e727e085b18c395260537bb5ac.1740941097.git.dsimic@manjaro.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
index 69a9d61706495..47dc198706c85 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
@@ -227,6 +227,16 @@
 		vin-supply = <&vcc12v_dcin>;
 	};
 
+	vcca_0v9: regulator-vcca-0v9 {
+		compatible = "regulator-fixed";
+		regulator-name = "vcca_0v9";
+		regulator-always-on;
+		regulator-boot-on;
+		regulator-min-microvolt = <900000>;
+		regulator-max-microvolt = <900000>;
+		vin-supply = <&vcc3v3_sys>;
+	};
+
 	vdd_log: regulator-vdd-log {
 		compatible = "pwm-regulator";
 		pwms = <&pwm2 0 25000 1>;
@@ -312,6 +322,8 @@
 };
 
 &hdmi {
+	avdd-0v9-supply = <&vcca_0v9>;
+	avdd-1v8-supply = <&vcc1v8_dvp>;
 	ddc-i2c-bus = <&i2c3>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_cec>;

From d110dbf1490b130f70fd0cd73a658ff495bc75e0 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 28 Feb 2025 10:00:07 -0800
Subject: [PATCH 1438/2753] selftests: net: report output format as TAP 13 in
 Python tests

The Python lib based tests report that they are producing
"KTAP version 1", but really we aren't making use of any
KTAP features, like subtests. Our output is plain TAP.

Report TAP 13 instead of KTAP 1, this is what mptcp tests do,
and what NIPA knows how to parse best. For HW testing we need
precise subtest result tracking.

Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228180007.83325-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/README.rst | 4 ++--
 tools/testing/selftests/net/lib/py/ksft.py     | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/README.rst b/tools/testing/selftests/drivers/net/README.rst
index 3b6a29e6564b9..eb838ae948441 100644
--- a/tools/testing/selftests/drivers/net/README.rst
+++ b/tools/testing/selftests/drivers/net/README.rst
@@ -107,7 +107,7 @@ On the target machine, running the tests will use netdevsim by default::
   1..1
   # timeout set to 45
   # selftests: drivers/net: ping.py
-  # KTAP version 1
+  # TAP version 13
   # 1..3
   # ok 1 ping.test_v4
   # ok 2 ping.test_v6
@@ -128,7 +128,7 @@ Create a config with remote info::
 Run the test::
 
   [/root] # ./ksft-net-drv/drivers/net/ping.py
-  KTAP version 1
+  TAP version 13
   1..3
   ok 1 ping.test_v4
   ok 2 ping.test_v6 # SKIP Test requires IPv6 connectivity
diff --git a/tools/testing/selftests/net/lib/py/ksft.py b/tools/testing/selftests/net/lib/py/ksft.py
index fd23349fa8ca0..3cfad0fd45703 100644
--- a/tools/testing/selftests/net/lib/py/ksft.py
+++ b/tools/testing/selftests/net/lib/py/ksft.py
@@ -207,7 +207,7 @@ def ksft_run(cases=None, globs=None, case_pfx=None, args=()):
 
     totals = {"pass": 0, "fail": 0, "skip": 0, "xfail": 0}
 
-    print("KTAP version 1")
+    print("TAP version 13")
     print("1.." + str(len(cases)))
 
     global KSFT_RESULT

From e5bf1c39e894d754092ff55b06035ed222a359ec Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:17 -0800
Subject: [PATCH 1439/2753] ipv4: fib: Use cached net in fib_inetaddr_event().

net is available in fib_inetaddr_event(), let's use it.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-2-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 272e42d813230..6730e2034cf8e 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1450,7 +1450,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 		fib_sync_up(dev, RTNH_F_DEAD);
 #endif
 		atomic_inc(&net->ipv4.dev_addr_genid);
-		rt_cache_flush(dev_net(dev));
+		rt_cache_flush(net);
 		break;
 	case NETDEV_DOWN:
 		fib_del_ifaddr(ifa, NULL);
@@ -1461,7 +1461,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
 			 */
 			fib_disable_ip(dev, event, true);
 		} else {
-			rt_cache_flush(dev_net(dev));
+			rt_cache_flush(net);
 		}
 		break;
 	}

From fa336adc100e1d76a50da782c3e9abb1541a72f3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:18 -0800
Subject: [PATCH 1440/2753] ipv4: fib: Allocate fib_info_hash[] and
 fib_info_laddrhash[] by kvcalloc().

Both fib_info_hash[] and fib_info_laddrhash[] are hash tables for
struct fib_info and are allocated by kvzmalloc() separately.

Let's replace the two kvzmalloc() calls with kvcalloc() to remove
the fib_info_laddrhash pointer later.

Note that fib_info_hash_alloc() allocates a new hash table based on
fib_info_hash_bits because we will remove fib_info_hash_size later.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-3-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_semantics.c | 43 +++++++++++++++++++++++-----------------
 1 file changed, 25 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index d2cee5c314f5e..23aae379ba423 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -357,6 +357,18 @@ static inline unsigned int fib_info_hashfn(struct fib_info *fi)
 	return fib_info_hashfn_result(fi->fib_net, val);
 }
 
+static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
+{
+	/* The second half is used for prefsrc */
+	return kvcalloc((1 << hash_bits) * 2, sizeof(struct hlist_head *),
+			GFP_KERNEL);
+}
+
+static void fib_info_hash_free(struct hlist_head *head)
+{
+	kvfree(head);
+}
+
 /* no metrics, only nexthop id */
 static struct fib_info *fib_find_info_nh(struct net *net,
 					 const struct fib_config *cfg)
@@ -1249,9 +1261,9 @@ fib_info_laddrhash_bucket(const struct net *net, __be32 val)
 }
 
 static void fib_info_hash_move(struct hlist_head *new_info_hash,
-			       struct hlist_head *new_laddrhash,
 			       unsigned int new_size)
 {
+	struct hlist_head *new_laddrhash = new_info_hash + new_size;
 	struct hlist_head *old_info_hash, *old_laddrhash;
 	unsigned int old_size = fib_info_hash_size;
 	unsigned int i;
@@ -1293,8 +1305,7 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
 		}
 	}
 
-	kvfree(old_info_hash);
-	kvfree(old_laddrhash);
+	fib_info_hash_free(old_info_hash);
 }
 
 __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
@@ -1412,22 +1423,18 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	err = -ENOBUFS;
 
 	if (fib_info_cnt >= fib_info_hash_size) {
-		unsigned int new_size = fib_info_hash_size << 1;
 		struct hlist_head *new_info_hash;
-		struct hlist_head *new_laddrhash;
-		size_t bytes;
-
-		if (!new_size)
-			new_size = 16;
-		bytes = (size_t)new_size * sizeof(struct hlist_head *);
-		new_info_hash = kvzalloc(bytes, GFP_KERNEL);
-		new_laddrhash = kvzalloc(bytes, GFP_KERNEL);
-		if (!new_info_hash || !new_laddrhash) {
-			kvfree(new_info_hash);
-			kvfree(new_laddrhash);
-		} else {
-			fib_info_hash_move(new_info_hash, new_laddrhash, new_size);
-		}
+		unsigned int new_hash_bits;
+
+		if (!fib_info_hash_bits)
+			new_hash_bits = 4;
+		else
+			new_hash_bits = fib_info_hash_bits + 1;
+
+		new_info_hash = fib_info_hash_alloc(new_hash_bits);
+		if (new_info_hash)
+			fib_info_hash_move(new_info_hash, 1 << new_hash_bits);
+
 		if (!fib_info_hash_size)
 			goto failure;
 	}

From cfc47029fa124e5e04411fb1dbd3726db90fd346 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:19 -0800
Subject: [PATCH 1441/2753] ipv4: fib: Allocate fib_info_hash[] during netns
 initialisation.

We will allocate fib_info_hash[] and fib_info_laddrhash[] for each netns.

Currently, fib_info_hash[] is allocated when the first route is added.

Let's move the first allocation to a new __net_init function.

Note that we must call fib4_semantics_exit() in fib_net_exit_batch()
because ->exit() is called earlier than ->exit_batch().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-4-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/ip_fib.h     |  2 ++
 net/ipv4/fib_frontend.c  | 11 ++++++++++
 net/ipv4/fib_semantics.c | 45 ++++++++++++++++++++++++++++------------
 3 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index a113c11ab56b5..e3864b74e92a6 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -162,6 +162,8 @@ struct fib_info {
 	struct fib_nh		fib_nh[] __counted_by(fib_nhs);
 };
 
+int __net_init fib4_semantics_init(struct net *net);
+void __net_exit fib4_semantics_exit(struct net *net);
 
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 struct fib_rule;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6730e2034cf8e..40c062f820f2d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1615,9 +1615,15 @@ static int __net_init fib_net_init(struct net *net)
 	error = ip_fib_net_init(net);
 	if (error < 0)
 		goto out;
+
+	error = fib4_semantics_init(net);
+	if (error)
+		goto out_semantics;
+
 	error = nl_fib_lookup_init(net);
 	if (error < 0)
 		goto out_nlfl;
+
 	error = fib_proc_init(net);
 	if (error < 0)
 		goto out_proc;
@@ -1627,6 +1633,8 @@ static int __net_init fib_net_init(struct net *net)
 out_proc:
 	nl_fib_lookup_exit(net);
 out_nlfl:
+	fib4_semantics_exit(net);
+out_semantics:
 	rtnl_lock();
 	ip_fib_net_exit(net);
 	rtnl_unlock();
@@ -1648,6 +1656,9 @@ static void __net_exit fib_net_exit_batch(struct list_head *net_list)
 		ip_fib_net_exit(net);
 
 	rtnl_unlock();
+
+	list_for_each_entry(net, net_list, exit_list)
+		fib4_semantics_exit(net);
 }
 
 static struct pernet_operations fib_net_ops = {
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 23aae379ba423..b7e2023bf742d 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1420,28 +1420,21 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	err = -ENOBUFS;
-
 	if (fib_info_cnt >= fib_info_hash_size) {
+		unsigned int new_hash_bits = fib_info_hash_bits + 1;
 		struct hlist_head *new_info_hash;
-		unsigned int new_hash_bits;
-
-		if (!fib_info_hash_bits)
-			new_hash_bits = 4;
-		else
-			new_hash_bits = fib_info_hash_bits + 1;
 
 		new_info_hash = fib_info_hash_alloc(new_hash_bits);
 		if (new_info_hash)
 			fib_info_hash_move(new_info_hash, 1 << new_hash_bits);
-
-		if (!fib_info_hash_size)
-			goto failure;
 	}
 
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
-	if (!fi)
+	if (!fi) {
+		err = -ENOBUFS;
 		goto failure;
+	}
+
 	fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack);
 	if (IS_ERR(fi->fib_metrics)) {
 		err = PTR_ERR(fi->fib_metrics);
@@ -1862,7 +1855,7 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local)
 	struct fib_info *fi;
 	int ret = 0;
 
-	if (!fib_info_laddrhash || local == 0)
+	if (!local)
 		return 0;
 
 	head = fib_info_laddrhash_bucket(net, local);
@@ -2264,3 +2257,29 @@ void fib_select_path(struct net *net, struct fib_result *res,
 			fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
 	}
 }
+
+int __net_init fib4_semantics_init(struct net *net)
+{
+	unsigned int hash_bits = 4;
+
+	if (!net_eq(net, &init_net))
+		return 0;
+
+	fib_info_hash = fib_info_hash_alloc(hash_bits);
+	if (!fib_info_hash)
+		return -ENOMEM;
+
+	fib_info_hash_bits = hash_bits;
+	fib_info_hash_size = 1 << hash_bits;
+	fib_info_laddrhash = fib_info_hash + fib_info_hash_size;
+
+	return 0;
+}
+
+void __net_exit fib4_semantics_exit(struct net *net)
+{
+	if (!net_eq(net, &init_net))
+		return;
+
+	fib_info_hash_free(fib_info_hash);
+}

From 84c75e94ecee7d783eb1d4282a66d6d26d848246 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:20 -0800
Subject: [PATCH 1442/2753] ipv4: fib: Make fib_info_hashfn() return struct
 hlist_head.

Every time fib_info_hashfn() returns a hash value, we fetch
&fib_info_hash[hash].

Let's return the hlist_head pointer from fib_info_hashfn() and
rename it to fib_info_hash_bucket() to match a similar function,
fib_info_laddrhash_bucket().

Note that we need to move the fib_info_hash assignment earlier in
fib_info_hash_move() to use fib_info_hash_bucket() in the for loop.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-5-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_semantics.c | 28 +++++++++-------------------
 1 file changed, 9 insertions(+), 19 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index b7e2023bf742d..54749dd7afc8a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -338,7 +338,7 @@ static unsigned int fib_info_hashfn_result(const struct net *net,
 	return hash_32(val ^ net_hash_mix(net), fib_info_hash_bits);
 }
 
-static inline unsigned int fib_info_hashfn(struct fib_info *fi)
+static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
 {
 	unsigned int val;
 
@@ -354,7 +354,7 @@ static inline unsigned int fib_info_hashfn(struct fib_info *fi)
 		} endfor_nexthops(fi)
 	}
 
-	return fib_info_hashfn_result(fi->fib_net, val);
+	return &fib_info_hash[fib_info_hashfn_result(fi->fib_net, val)];
 }
 
 static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
@@ -404,12 +404,8 @@ static struct fib_info *fib_find_info_nh(struct net *net,
 
 static struct fib_info *fib_find_info(struct fib_info *nfi)
 {
-	struct hlist_head *head;
+	struct hlist_head *head = fib_info_hash_bucket(nfi);
 	struct fib_info *fi;
-	unsigned int hash;
-
-	hash = fib_info_hashfn(nfi);
-	head = &fib_info_hash[hash];
 
 	hlist_for_each_entry(fi, head, fib_hash) {
 		if (!net_eq(fi->fib_net, nfi->fib_net))
@@ -1273,22 +1269,16 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
 	old_laddrhash = fib_info_laddrhash;
 	fib_info_hash_size = new_size;
 	fib_info_hash_bits = ilog2(new_size);
+	fib_info_hash = new_info_hash;
 
 	for (i = 0; i < old_size; i++) {
-		struct hlist_head *head = &fib_info_hash[i];
+		struct hlist_head *head = &old_info_hash[i];
 		struct hlist_node *n;
 		struct fib_info *fi;
 
-		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
-			struct hlist_head *dest;
-			unsigned int new_hash;
-
-			new_hash = fib_info_hashfn(fi);
-			dest = &new_info_hash[new_hash];
-			hlist_add_head(&fi->fib_hash, dest);
-		}
+		hlist_for_each_entry_safe(fi, n, head, fib_hash)
+			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
 	}
-	fib_info_hash = new_info_hash;
 
 	fib_info_laddrhash = new_laddrhash;
 	for (i = 0; i < old_size; i++) {
@@ -1572,8 +1562,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	refcount_set(&fi->fib_clntref, 1);
 
 	fib_info_cnt++;
-	hlist_add_head(&fi->fib_hash,
-		       &fib_info_hash[fib_info_hashfn(fi)]);
+	hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+
 	if (fi->fib_prefsrc) {
 		struct hlist_head *head;
 

From 0dbca8c269ba786cde720d159f3c7dcbc2166f34 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:21 -0800
Subject: [PATCH 1443/2753] ipv4: fib: Remove fib_info_laddrhash pointer.

We will allocate the fib_info hash tables per netns.

There are 5 global variables for fib_info hash tables:
fib_info_hash, fib_info_laddrhash, fib_info_hash_size,
fib_info_hash_bits, fib_info_cnt.

However, fib_info_laddrhash and fib_info_hash_size can be
easily calculated from fib_info_hash and fib_info_hash_bits.

Let's remove the fib_info_laddrhash pointer and instead use
fib_info_hash + (1 << fib_info_hash_bits).

While at it, fib_info_laddrhash_bucket() is moved near other
hash-table-specific functions.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-6-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_semantics.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 54749dd7afc8a..6cc518dd665f9 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -51,7 +51,6 @@
 #include "fib_lookup.h"
 
 static struct hlist_head *fib_info_hash;
-static struct hlist_head *fib_info_laddrhash;
 static unsigned int fib_info_hash_size;
 static unsigned int fib_info_hash_bits;
 static unsigned int fib_info_cnt;
@@ -357,6 +356,15 @@ static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
 	return &fib_info_hash[fib_info_hashfn_result(fi->fib_net, val)];
 }
 
+static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
+						    __be32 val)
+{
+	u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
+			   fib_info_hash_bits);
+
+	return &fib_info_hash[(1 << fib_info_hash_bits) + slot];
+}
+
 static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
 {
 	/* The second half is used for prefsrc */
@@ -1247,26 +1255,15 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 	return err;
 }
 
-static struct hlist_head *
-fib_info_laddrhash_bucket(const struct net *net, __be32 val)
-{
-	u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
-			   fib_info_hash_bits);
-
-	return &fib_info_laddrhash[slot];
-}
-
 static void fib_info_hash_move(struct hlist_head *new_info_hash,
 			       unsigned int new_size)
 {
-	struct hlist_head *new_laddrhash = new_info_hash + new_size;
-	struct hlist_head *old_info_hash, *old_laddrhash;
 	unsigned int old_size = fib_info_hash_size;
+	struct hlist_head *old_info_hash;
 	unsigned int i;
 
 	ASSERT_RTNL();
 	old_info_hash = fib_info_hash;
-	old_laddrhash = fib_info_laddrhash;
 	fib_info_hash_size = new_size;
 	fib_info_hash_bits = ilog2(new_size);
 	fib_info_hash = new_info_hash;
@@ -1280,9 +1277,8 @@ static void fib_info_hash_move(struct hlist_head *new_info_hash,
 			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
 	}
 
-	fib_info_laddrhash = new_laddrhash;
 	for (i = 0; i < old_size; i++) {
-		struct hlist_head *lhead = &old_laddrhash[i];
+		struct hlist_head *lhead = &old_info_hash[old_size + i];
 		struct hlist_node *n;
 		struct fib_info *fi;
 
@@ -2261,7 +2257,6 @@ int __net_init fib4_semantics_init(struct net *net)
 
 	fib_info_hash_bits = hash_bits;
 	fib_info_hash_size = 1 << hash_bits;
-	fib_info_laddrhash = fib_info_hash + fib_info_hash_size;
 
 	return 0;
 }

From d6306b9d98850a1a7247eb10fe5bb78506ee343b Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:22 -0800
Subject: [PATCH 1444/2753] ipv4: fib: Remove fib_info_hash_size.

We will allocate the fib_info hash tables per netns.

There are 5 global variables for fib_info hash tables:
fib_info_hash, fib_info_laddrhash, fib_info_hash_size,
fib_info_hash_bits, fib_info_cnt.

However, fib_info_laddrhash and fib_info_hash_size can be
easily calculated from fib_info_hash and fib_info_hash_bits.

Let's remove fib_info_hash_size and use (1 << fib_info_hash_bits)
instead.

Now we need not pass the new hash table size to fib_info_hash_move().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-7-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_semantics.c | 17 ++++++-----------
 1 file changed, 6 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 6cc518dd665f9..9dc09e80b92be 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -51,7 +51,6 @@
 #include "fib_lookup.h"
 
 static struct hlist_head *fib_info_hash;
-static unsigned int fib_info_hash_size;
 static unsigned int fib_info_hash_bits;
 static unsigned int fib_info_cnt;
 
@@ -1255,17 +1254,15 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 	return err;
 }
 
-static void fib_info_hash_move(struct hlist_head *new_info_hash,
-			       unsigned int new_size)
+static void fib_info_hash_move(struct hlist_head *new_info_hash)
 {
-	unsigned int old_size = fib_info_hash_size;
+	unsigned int old_size = 1 << fib_info_hash_bits;
 	struct hlist_head *old_info_hash;
 	unsigned int i;
 
 	ASSERT_RTNL();
 	old_info_hash = fib_info_hash;
-	fib_info_hash_size = new_size;
-	fib_info_hash_bits = ilog2(new_size);
+	fib_info_hash_bits += 1;
 	fib_info_hash = new_info_hash;
 
 	for (i = 0; i < old_size; i++) {
@@ -1406,13 +1403,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	if (fib_info_cnt >= fib_info_hash_size) {
-		unsigned int new_hash_bits = fib_info_hash_bits + 1;
+	if (fib_info_cnt >= (1 << fib_info_hash_bits)) {
 		struct hlist_head *new_info_hash;
 
-		new_info_hash = fib_info_hash_alloc(new_hash_bits);
+		new_info_hash = fib_info_hash_alloc(fib_info_hash_bits + 1);
 		if (new_info_hash)
-			fib_info_hash_move(new_info_hash, 1 << new_hash_bits);
+			fib_info_hash_move(new_info_hash);
 	}
 
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
@@ -2256,7 +2252,6 @@ int __net_init fib4_semantics_init(struct net *net)
 		return -ENOMEM;
 
 	fib_info_hash_bits = hash_bits;
-	fib_info_hash_size = 1 << hash_bits;
 
 	return 0;
 }

From b79bcaf7d95261bb8c205fa6826100ca4ed961c1 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:23 -0800
Subject: [PATCH 1445/2753] ipv4: fib: Add fib_info_hash_grow().

When the number of struct fib_info exceeds the hash table size in
fib_create_info(), we try to allocate a new hash table with the
doubled size.

The allocation is done in fib_create_info(), and if successful, each
struct fib_info is moved to the new hash table by fib_info_hash_move().

Let's integrate the allocation and fib_info_hash_move() as
fib_info_hash_grow() to make the following change cleaner.

While at it, fib_info_hash_grow() is placed near other hash-table-specific
functions.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-8-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_semantics.c | 85 +++++++++++++++++++---------------------
 1 file changed, 41 insertions(+), 44 deletions(-)

diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 9dc09e80b92be..0cd40ff18d8be 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -376,6 +376,46 @@ static void fib_info_hash_free(struct hlist_head *head)
 	kvfree(head);
 }
 
+static void fib_info_hash_grow(void)
+{
+	struct hlist_head *new_info_hash, *old_info_hash;
+	unsigned int old_size = 1 << fib_info_hash_bits;
+	unsigned int i;
+
+	if (fib_info_cnt < old_size)
+		return;
+
+	new_info_hash = fib_info_hash_alloc(fib_info_hash_bits + 1);
+	if (!new_info_hash)
+		return;
+
+	old_info_hash = fib_info_hash;
+	fib_info_hash = new_info_hash;
+	fib_info_hash_bits += 1;
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *head = &old_info_hash[i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, head, fib_hash)
+			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
+	}
+
+	for (i = 0; i < old_size; i++) {
+		struct hlist_head *lhead = &old_info_hash[old_size + i];
+		struct hlist_node *n;
+		struct fib_info *fi;
+
+		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash)
+			hlist_add_head(&fi->fib_lhash,
+				       fib_info_laddrhash_bucket(fi->fib_net,
+								 fi->fib_prefsrc));
+	}
+
+	fib_info_hash_free(old_info_hash);
+}
+
 /* no metrics, only nexthop id */
 static struct fib_info *fib_find_info_nh(struct net *net,
 					 const struct fib_config *cfg)
@@ -1254,43 +1294,6 @@ int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope,
 	return err;
 }
 
-static void fib_info_hash_move(struct hlist_head *new_info_hash)
-{
-	unsigned int old_size = 1 << fib_info_hash_bits;
-	struct hlist_head *old_info_hash;
-	unsigned int i;
-
-	ASSERT_RTNL();
-	old_info_hash = fib_info_hash;
-	fib_info_hash_bits += 1;
-	fib_info_hash = new_info_hash;
-
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *head = &old_info_hash[i];
-		struct hlist_node *n;
-		struct fib_info *fi;
-
-		hlist_for_each_entry_safe(fi, n, head, fib_hash)
-			hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
-	}
-
-	for (i = 0; i < old_size; i++) {
-		struct hlist_head *lhead = &old_info_hash[old_size + i];
-		struct hlist_node *n;
-		struct fib_info *fi;
-
-		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
-			struct hlist_head *ldest;
-
-			ldest = fib_info_laddrhash_bucket(fi->fib_net,
-							  fi->fib_prefsrc);
-			hlist_add_head(&fi->fib_lhash, ldest);
-		}
-	}
-
-	fib_info_hash_free(old_info_hash);
-}
-
 __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc,
 				 unsigned char scope)
 {
@@ -1403,13 +1406,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	if (fib_info_cnt >= (1 << fib_info_hash_bits)) {
-		struct hlist_head *new_info_hash;
-
-		new_info_hash = fib_info_hash_alloc(fib_info_hash_bits + 1);
-		if (new_info_hash)
-			fib_info_hash_move(new_info_hash);
-	}
+	fib_info_hash_grow();
 
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
 	if (!fi) {

From 9f7f3ebeba9388c30b0cba9dc5df0c43d0e07605 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:24 -0800
Subject: [PATCH 1446/2753] ipv4: fib: Namespacify fib_info hash tables.

We will convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL.
Then, we need to have per-netns hash tables for struct fib_info.

Let's allocate the hash tables per netns.

fib_info_hash, fib_info_hash_bits, and fib_info_cnt are now moved
to struct netns_ipv4 and accessed with net->ipv4.fib_XXX.

Also, the netns checks are removed from fib_find_info_nh() and
fib_find_info().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-9-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netns/ipv4.h |  3 ++
 net/ipv4/fib_semantics.c | 61 +++++++++++++++++-----------------------
 2 files changed, 29 insertions(+), 35 deletions(-)

diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 45ac125e8aebb..650b2dc9199f4 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -111,6 +111,9 @@ struct netns_ipv4 {
 #endif
 	struct hlist_head	*fib_table_hash;
 	struct sock		*fibnl;
+	struct hlist_head	*fib_info_hash;
+	unsigned int		fib_info_hash_bits;
+	unsigned int		fib_info_cnt;
 
 	struct sock		*mc_autojoin_sk;
 
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 0cd40ff18d8be..f68bb9e34c34c 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -50,10 +50,6 @@
 
 #include "fib_lookup.h"
 
-static struct hlist_head *fib_info_hash;
-static unsigned int fib_info_hash_bits;
-static unsigned int fib_info_cnt;
-
 /* for_nexthops and change_nexthops only used when nexthop object
  * is not set in a fib_info. The logic within can reference fib_nh.
  */
@@ -256,8 +252,7 @@ void fib_release_info(struct fib_info *fi)
 	ASSERT_RTNL();
 	if (fi && refcount_dec_and_test(&fi->fib_treeref)) {
 		hlist_del(&fi->fib_hash);
-
-		fib_info_cnt--;
+		fi->fib_net->ipv4.fib_info_cnt--;
 
 		if (fi->fib_prefsrc)
 			hlist_del(&fi->fib_lhash);
@@ -333,11 +328,12 @@ static unsigned int fib_info_hashfn_1(int init_val, u8 protocol, u8 scope,
 static unsigned int fib_info_hashfn_result(const struct net *net,
 					   unsigned int val)
 {
-	return hash_32(val ^ net_hash_mix(net), fib_info_hash_bits);
+	return hash_32(val ^ net_hash_mix(net), net->ipv4.fib_info_hash_bits);
 }
 
 static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
 {
+	struct net *net = fi->fib_net;
 	unsigned int val;
 
 	val = fib_info_hashfn_1(fi->fib_nhs, fi->fib_protocol,
@@ -352,16 +348,18 @@ static struct hlist_head *fib_info_hash_bucket(struct fib_info *fi)
 		} endfor_nexthops(fi)
 	}
 
-	return &fib_info_hash[fib_info_hashfn_result(fi->fib_net, val)];
+	return &net->ipv4.fib_info_hash[fib_info_hashfn_result(net, val)];
 }
 
 static struct hlist_head *fib_info_laddrhash_bucket(const struct net *net,
 						    __be32 val)
 {
-	u32 slot = hash_32(net_hash_mix(net) ^ (__force u32)val,
-			   fib_info_hash_bits);
+	unsigned int hash_bits = net->ipv4.fib_info_hash_bits;
+	u32 slot;
 
-	return &fib_info_hash[(1 << fib_info_hash_bits) + slot];
+	slot = hash_32(net_hash_mix(net) ^ (__force u32)val, hash_bits);
+
+	return &net->ipv4.fib_info_hash[(1 << hash_bits) + slot];
 }
 
 static struct hlist_head *fib_info_hash_alloc(unsigned int hash_bits)
@@ -376,22 +374,22 @@ static void fib_info_hash_free(struct hlist_head *head)
 	kvfree(head);
 }
 
-static void fib_info_hash_grow(void)
+static void fib_info_hash_grow(struct net *net)
 {
+	unsigned int old_size = 1 << net->ipv4.fib_info_hash_bits;
 	struct hlist_head *new_info_hash, *old_info_hash;
-	unsigned int old_size = 1 << fib_info_hash_bits;
 	unsigned int i;
 
-	if (fib_info_cnt < old_size)
+	if (net->ipv4.fib_info_cnt < old_size)
 		return;
 
-	new_info_hash = fib_info_hash_alloc(fib_info_hash_bits + 1);
+	new_info_hash = fib_info_hash_alloc(net->ipv4.fib_info_hash_bits + 1);
 	if (!new_info_hash)
 		return;
 
-	old_info_hash = fib_info_hash;
-	fib_info_hash = new_info_hash;
-	fib_info_hash_bits += 1;
+	old_info_hash = net->ipv4.fib_info_hash;
+	net->ipv4.fib_info_hash = new_info_hash;
+	net->ipv4.fib_info_hash_bits += 1;
 
 	for (i = 0; i < old_size; i++) {
 		struct hlist_head *head = &old_info_hash[i];
@@ -429,13 +427,12 @@ static struct fib_info *fib_find_info_nh(struct net *net,
 				 (__force u32)cfg->fc_prefsrc,
 				 cfg->fc_priority);
 	hash = fib_info_hashfn_result(net, hash);
-	head = &fib_info_hash[hash];
+	head = &net->ipv4.fib_info_hash[hash];
 
 	hlist_for_each_entry(fi, head, fib_hash) {
-		if (!net_eq(fi->fib_net, net))
-			continue;
 		if (!fi->nh || fi->nh->id != cfg->fc_nh_id)
 			continue;
+
 		if (cfg->fc_protocol == fi->fib_protocol &&
 		    cfg->fc_scope == fi->fib_scope &&
 		    cfg->fc_prefsrc == fi->fib_prefsrc &&
@@ -455,10 +452,9 @@ static struct fib_info *fib_find_info(struct fib_info *nfi)
 	struct fib_info *fi;
 
 	hlist_for_each_entry(fi, head, fib_hash) {
-		if (!net_eq(fi->fib_net, nfi->fib_net))
-			continue;
 		if (fi->fib_nhs != nfi->fib_nhs)
 			continue;
+
 		if (nfi->fib_protocol == fi->fib_protocol &&
 		    nfi->fib_scope == fi->fib_scope &&
 		    nfi->fib_prefsrc == fi->fib_prefsrc &&
@@ -1406,7 +1402,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	}
 #endif
 
-	fib_info_hash_grow();
+	fib_info_hash_grow(net);
 
 	fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
 	if (!fi) {
@@ -1550,7 +1546,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
 	refcount_set(&fi->fib_treeref, 1);
 	refcount_set(&fi->fib_clntref, 1);
 
-	fib_info_cnt++;
+	net->ipv4.fib_info_cnt++;
 	hlist_add_head(&fi->fib_hash, fib_info_hash_bucket(fi));
 
 	if (fi->fib_prefsrc) {
@@ -2241,22 +2237,17 @@ int __net_init fib4_semantics_init(struct net *net)
 {
 	unsigned int hash_bits = 4;
 
-	if (!net_eq(net, &init_net))
-		return 0;
-
-	fib_info_hash = fib_info_hash_alloc(hash_bits);
-	if (!fib_info_hash)
+	net->ipv4.fib_info_hash = fib_info_hash_alloc(hash_bits);
+	if (!net->ipv4.fib_info_hash)
 		return -ENOMEM;
 
-	fib_info_hash_bits = hash_bits;
+	net->ipv4.fib_info_hash_bits = hash_bits;
+	net->ipv4.fib_info_cnt = 0;
 
 	return 0;
 }
 
 void __net_exit fib4_semantics_exit(struct net *net)
 {
-	if (!net_eq(net, &init_net))
-		return;
-
-	fib_info_hash_free(fib_info_hash);
+	fib_info_hash_free(net->ipv4.fib_info_hash);
 }

From af5cd2a8f07842d14be2cbc628ea511adfd6bba9 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:25 -0800
Subject: [PATCH 1447/2753] ipv4: fib: Hold rtnl_net_lock() for
 ip_fib_net_exit().

ip_fib_net_exit() requires RTNL and is called from fib_net_init()
and fib_net_exit_batch().

Let's hold rtnl_net_lock() before ip_fib_net_exit().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-10-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 40c062f820f2d..c48ed369b1796 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1575,7 +1575,7 @@ static void ip_fib_net_exit(struct net *net)
 {
 	int i;
 
-	ASSERT_RTNL();
+	ASSERT_RTNL_NET(net);
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
 	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
@@ -1635,9 +1635,9 @@ static int __net_init fib_net_init(struct net *net)
 out_nlfl:
 	fib4_semantics_exit(net);
 out_semantics:
-	rtnl_lock();
+	rtnl_net_lock(net);
 	ip_fib_net_exit(net);
-	rtnl_unlock();
+	rtnl_net_unlock(net);
 	goto out;
 }
 
@@ -1652,9 +1652,11 @@ static void __net_exit fib_net_exit_batch(struct list_head *net_list)
 	struct net *net;
 
 	rtnl_lock();
-	list_for_each_entry(net, net_list, exit_list)
+	list_for_each_entry(net, net_list, exit_list) {
+		__rtnl_net_lock(net);
 		ip_fib_net_exit(net);
-
+		__rtnl_net_unlock(net);
+	}
 	rtnl_unlock();
 
 	list_for_each_entry(net, net_list, exit_list)

From c0ebe1cdc2cff0dee092a67f2c50377bb5fcf43d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:26 -0800
Subject: [PATCH 1448/2753] ipv4: fib: Hold rtnl_net_lock() in ip_rt_ioctl().

ioctl(SIOCADDRT/SIOCDELRT) calls ip_rt_ioctl() to add/remove a route in
the netns of the specified socket.

Let's hold rtnl_net_lock() there.

Note that rtentry_to_fib_config() can be called without rtnl_net_lock()
if we convert rtentry.dev handling to RCU later.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-11-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c48ed369b1796..a76dacc3e577a 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -553,18 +553,16 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
 			const struct in_ifaddr *ifa;
 			struct in_device *in_dev;
 
-			in_dev = __in_dev_get_rtnl(dev);
+			in_dev = __in_dev_get_rtnl_net(dev);
 			if (!in_dev)
 				return -ENODEV;
 
 			*colon = ':';
 
-			rcu_read_lock();
-			in_dev_for_each_ifa_rcu(ifa, in_dev) {
+			in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev) {
 				if (strcmp(ifa->ifa_label, devname) == 0)
 					break;
 			}
-			rcu_read_unlock();
 
 			if (!ifa)
 				return -ENODEV;
@@ -635,7 +633,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 
-		rtnl_lock();
+		rtnl_net_lock(net);
 		err = rtentry_to_fib_config(net, cmd, rt, &cfg);
 		if (err == 0) {
 			struct fib_table *tb;
@@ -659,7 +657,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
 			/* allocated by rtentry_to_fib_config() */
 			kfree(cfg.fc_mx);
 		}
-		rtnl_unlock();
+		rtnl_net_unlock(net);
 		return err;
 	}
 	return -EINVAL;

From 254ba7e6032d3fc738050d500b0c1d8197af90ca Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:27 -0800
Subject: [PATCH 1449/2753] ipv4: fib: Move fib_valid_key_len() to
 rtm_to_fib_config().

fib_valid_key_len() is called in the beginning of fib_table_insert()
or fib_table_delete() to check if the prefix length is valid.

fib_table_insert() and fib_table_delete() are called from 3 paths

  - ip_rt_ioctl()
  - inet_rtm_newroute() / inet_rtm_delroute()
  - fib_magic()

In the first ioctl() path, rtentry_to_fib_config() checks the prefix
length with bad_mask().  Also, fib_magic() always passes the correct
prefix: 32 or ifa->ifa_prefixlen, which is already validated.

Let's move fib_valid_key_len() to the rtnetlink path, rtm_to_fib_config().

While at it, 2 direct returns in rtm_to_fib_config() are changed to
goto to match other places in the same function

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-12-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 18 ++++++++++++++++--
 net/ipv4/fib_trie.c     | 22 ----------------------
 2 files changed, 16 insertions(+), 24 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a76dacc3e577a..a6372d934e459 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -835,19 +835,33 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		}
 	}
 
+	if (cfg->fc_dst_len > 32) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix length");
+		err = -EINVAL;
+		goto errout;
+	}
+
+	if (cfg->fc_dst_len < 32 && (ntohl(cfg->fc_dst) << cfg->fc_dst_len)) {
+		NL_SET_ERR_MSG(extack, "Invalid prefix for given prefix length");
+		err = -EINVAL;
+		goto errout;
+	}
+
 	if (cfg->fc_nh_id) {
 		if (cfg->fc_oif || cfg->fc_gw_family ||
 		    cfg->fc_encap || cfg->fc_mp) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop specification and nexthop id are mutually exclusive");
-			return -EINVAL;
+			err = -EINVAL;
+			goto errout;
 		}
 	}
 
 	if (has_gw && has_via) {
 		NL_SET_ERR_MSG(extack,
 			       "Nexthop configuration can not contain both GATEWAY and VIA");
-		return -EINVAL;
+		err = -EINVAL;
+		goto errout;
 	}
 
 	if (!cfg->fc_table)
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index d6411ac810961..59a6f0a9638f9 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1187,22 +1187,6 @@ static int fib_insert_alias(struct trie *t, struct key_vector *tp,
 	return 0;
 }
 
-static bool fib_valid_key_len(u32 key, u8 plen, struct netlink_ext_ack *extack)
-{
-	if (plen > KEYLENGTH) {
-		NL_SET_ERR_MSG(extack, "Invalid prefix length");
-		return false;
-	}
-
-	if ((plen < KEYLENGTH) && (key << plen)) {
-		NL_SET_ERR_MSG(extack,
-			       "Invalid prefix for given prefix length");
-		return false;
-	}
-
-	return true;
-}
-
 static void fib_remove_alias(struct trie *t, struct key_vector *tp,
 			     struct key_vector *l, struct fib_alias *old);
 
@@ -1223,9 +1207,6 @@ int fib_table_insert(struct net *net, struct fib_table *tb,
 
 	key = ntohl(cfg->fc_dst);
 
-	if (!fib_valid_key_len(key, plen, extack))
-		return -EINVAL;
-
 	pr_debug("Insert table=%u %08x/%d\n", tb->tb_id, key, plen);
 
 	fi = fib_create_info(cfg, extack);
@@ -1717,9 +1698,6 @@ int fib_table_delete(struct net *net, struct fib_table *tb,
 
 	key = ntohl(cfg->fc_dst);
 
-	if (!fib_valid_key_len(key, plen, extack))
-		return -EINVAL;
-
 	l = fib_find_node(t, &tp, key);
 	if (!l)
 		return -ESRCH;

From 1dd2af7963e95df90590fe40425fe1bdf982ae8f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 27 Feb 2025 20:23:28 -0800
Subject: [PATCH 1450/2753] ipv4: fib: Convert RTM_NEWROUTE and RTM_DELROUTE to
 per-netns RTNL.

We converted fib_info hash tables to per-netns one and now ready to
convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL.

Let's hold rtnl_net_lock() in inet_rtm_newroute() and inet_rtm_delroute().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250228042328.96624-13-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/fib_frontend.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index a6372d934e459..6de77415b5b30 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -884,20 +884,24 @@ static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		goto errout;
 
+	rtnl_net_lock(net);
+
 	if (cfg.fc_nh_id && !nexthop_find_by_id(net, cfg.fc_nh_id)) {
 		NL_SET_ERR_MSG(extack, "Nexthop id does not exist");
 		err = -EINVAL;
-		goto errout;
+		goto unlock;
 	}
 
 	tb = fib_get_table(net, cfg.fc_table);
 	if (!tb) {
 		NL_SET_ERR_MSG(extack, "FIB table does not exist");
 		err = -ESRCH;
-		goto errout;
+		goto unlock;
 	}
 
 	err = fib_table_delete(net, tb, &cfg, extack);
+unlock:
+	rtnl_net_unlock(net);
 errout:
 	return err;
 }
@@ -914,15 +918,20 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err < 0)
 		goto errout;
 
+	rtnl_net_lock(net);
+
 	tb = fib_new_table(net, cfg.fc_table);
 	if (!tb) {
 		err = -ENOBUFS;
-		goto errout;
+		goto unlock;
 	}
 
 	err = fib_table_insert(net, tb, &cfg, extack);
 	if (!err && cfg.fc_type == RTN_LOCAL)
 		net->ipv4.fib_has_custom_local_routes = true;
+
+unlock:
+	rtnl_net_unlock(net);
 errout:
 	return err;
 }
@@ -1683,9 +1692,9 @@ static struct pernet_operations fib_net_ops = {
 
 static const struct rtnl_msg_handler fib_rtnl_msg_handlers[] __initconst = {
 	{.protocol = PF_INET, .msgtype = RTM_NEWROUTE,
-	 .doit = inet_rtm_newroute},
+	 .doit = inet_rtm_newroute, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_DELROUTE,
-	 .doit = inet_rtm_delroute},
+	 .doit = inet_rtm_delroute, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_GETROUTE, .dumpit = inet_dump_fib,
 	 .flags = RTNL_FLAG_DUMP_UNLOCKED | RTNL_FLAG_DUMP_SPLIT_NLM_DONE},
 };

From e34100c2ecbb79a7d69474eb2f58545bb9926a5f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:19 +0000
Subject: [PATCH 1451/2753] tcp: add a drop_reason pointer to tcp_check_req()

We want to add new drop reasons for packets dropped in 3WHS in the
following patches.

tcp_rcv_state_process() has to set reason to TCP_FASTOPEN,
because tcp_check_req() will conditionally overwrite the drop_reason.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h        | 2 +-
 net/ipv4/tcp_input.c     | 5 ++---
 net/ipv4/tcp_ipv4.c      | 3 ++-
 net/ipv4/tcp_minisocks.c | 3 ++-
 net/ipv6/tcp_ipv6.c      | 3 ++-
 5 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index f9b9377a28974..a9bc959fb102f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -392,7 +392,7 @@ enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
 					      u32 *tw_isn);
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req, bool fastopen,
-			   bool *lost_race);
+			   bool *lost_race, enum skb_drop_reason *drop_reason);
 enum skb_drop_reason tcp_child_process(struct sock *parent, struct sock *child,
 				       struct sk_buff *skb);
 void tcp_enter_loss(struct sock *sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d22ad553b45b1..4e22123480889 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6812,10 +6812,9 @@ tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
 		    sk->sk_state != TCP_FIN_WAIT1);
 
-		if (!tcp_check_req(sk, skb, req, true, &req_stolen)) {
-			SKB_DR_SET(reason, TCP_FASTOPEN);
+		SKB_DR_SET(reason, TCP_FASTOPEN);
+		if (!tcp_check_req(sk, skb, req, true, &req_stolen, &reason))
 			goto discard;
-		}
 	}
 
 	if (!th->ack && !th->rst && !th->syn) {
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7900855237d92..218f01a8cc5f6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2265,7 +2265,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 			th = (const struct tcphdr *)skb->data;
 			iph = ip_hdr(skb);
 			tcp_v4_fill_cb(skb, iph, th);
-			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
+			nsk = tcp_check_req(sk, skb, req, false, &req_stolen,
+					    &drop_reason);
 		} else {
 			drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 29b54ade75723..46c86c4f80e9f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -657,7 +657,8 @@ EXPORT_SYMBOL(tcp_create_openreq_child);
 
 struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 			   struct request_sock *req,
-			   bool fastopen, bool *req_stolen)
+			   bool fastopen, bool *req_stolen,
+			   enum skb_drop_reason *drop_reason)
 {
 	struct tcp_options_received tmp_opt;
 	struct sock *child;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a806082602985..d01088ab80d24 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1828,7 +1828,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 			th = (const struct tcphdr *)skb->data;
 			hdr = ipv6_hdr(skb);
 			tcp_v6_fill_cb(skb, hdr, th);
-			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
+			nsk = tcp_check_req(sk, skb, req, false, &req_stolen,
+					    &drop_reason);
 		} else {
 			drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		}

From a11a791ca81e5cd9bf2d48e1368d836bc53f00ca Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:20 +0000
Subject: [PATCH 1452/2753] tcp: add four drop reasons to tcp_check_req()

Use two existing drop reasons in tcp_check_req():

- TCP_RFC7323_PAWS

- TCP_OVERWINDOW

Add two new ones:

- TCP_RFC7323_TSECR (corresponds to LINUX_MIB_TSECRREJECTED)

- TCP_LISTEN_OVERFLOW (when a listener accept queue is full)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/dropreason-core.h |  9 +++++++++
 net/ipv4/tcp_minisocks.c      | 10 ++++++++--
 2 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 32a34dfe8cc58..e4fdc6b54ceff 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -40,6 +40,8 @@
 	FN(TCP_OFOMERGE)		\
 	FN(TCP_RFC7323_PAWS)		\
 	FN(TCP_RFC7323_PAWS_ACK)	\
+	FN(TCP_RFC7323_TSECR)		\
+	FN(TCP_LISTEN_OVERFLOW)		\
 	FN(TCP_OLD_SEQUENCE)		\
 	FN(TCP_INVALID_SEQUENCE)	\
 	FN(TCP_INVALID_ACK_SEQUENCE)	\
@@ -281,6 +283,13 @@ enum skb_drop_reason {
 	 * Corresponds to LINUX_MIB_PAWS_OLD_ACK.
 	 */
 	SKB_DROP_REASON_TCP_RFC7323_PAWS_ACK,
+	/**
+	 * @SKB_DROP_REASON_TCP_RFC7323_TSECR: PAWS check, invalid TSEcr.
+	 * Corresponds to LINUX_MIB_TSECRREJECTED.
+	 */
+	SKB_DROP_REASON_TCP_RFC7323_TSECR,
+	/** @SKB_DROP_REASON_TCP_LISTEN_OVERFLOW: listener queue full. */
+	SKB_DROP_REASON_TCP_LISTEN_OVERFLOW,
 	/** @SKB_DROP_REASON_TCP_OLD_SEQUENCE: Old SEQ field (duplicate packet) */
 	SKB_DROP_REASON_TCP_OLD_SEQUENCE,
 	/** @SKB_DROP_REASON_TCP_INVALID_SEQUENCE: Not acceptable SEQ field */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 46c86c4f80e9f..ba4a5d7f251d8 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -809,10 +809,15 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 					  LINUX_MIB_TCPACKSKIPPEDSYNRECV,
 					  &tcp_rsk(req)->last_oow_ack_time))
 			req->rsk_ops->send_ack(sk, skb, req);
-		if (paws_reject)
+		if (paws_reject) {
+			SKB_DR_SET(*drop_reason, TCP_RFC7323_PAWS);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
-		else if (tsecr_reject)
+		} else if (tsecr_reject) {
+			SKB_DR_SET(*drop_reason, TCP_RFC7323_TSECR);
 			NET_INC_STATS(sock_net(sk), LINUX_MIB_TSECRREJECTED);
+		} else {
+			SKB_DR_SET(*drop_reason, TCP_OVERWINDOW);
+		}
 		return NULL;
 	}
 
@@ -882,6 +887,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 	return inet_csk_complete_hashdance(sk, child, req, own_req);
 
 listen_overflow:
+	SKB_DR_SET(*drop_reason, TCP_LISTEN_OVERFLOW);
 	if (sk != req->rsk_listener)
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
 

From e7b9ecce562ca6a1de32c56c597fa45e08c44ec0 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:21 +0000
Subject: [PATCH 1453/2753] tcp: convert to dev_net_rcu()

TCP uses of dev_net() are under RCU protection, change them
to dev_net_rcu() to get LOCKDEP support.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet6_hashtables.h |  2 +-
 include/net/inet_hashtables.h  |  2 +-
 net/ipv4/tcp_ipv4.c            | 12 ++++++------
 net/ipv4/tcp_metrics.c         |  6 +++---
 net/ipv6/tcp_ipv6.c            | 22 +++++++++++-----------
 5 files changed, 22 insertions(+), 22 deletions(-)

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 74dd90ff5f129..c32878c69179d 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -150,7 +150,7 @@ static inline struct sock *__inet6_lookup_skb(struct inet_hashinfo *hashinfo,
 					      int iif, int sdif,
 					      bool *refcounted)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = dev_net_rcu(skb_dst(skb)->dev);
 	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
 	struct sock *sk;
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 5eea47f135a42..da818fb0205fe 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -492,7 +492,7 @@ static inline struct sock *__inet_lookup_skb(struct inet_hashinfo *hashinfo,
 					     const int sdif,
 					     bool *refcounted)
 {
-	struct net *net = dev_net(skb_dst(skb)->dev);
+	struct net *net = dev_net_rcu(skb_dst(skb)->dev);
 	const struct iphdr *iph = ip_hdr(skb);
 	struct sock *sk;
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 218f01a8cc5f6..ae07613e4f335 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -494,14 +494,14 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
 {
 	const struct iphdr *iph = (const struct iphdr *)skb->data;
 	struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2));
-	struct tcp_sock *tp;
+	struct net *net = dev_net_rcu(skb->dev);
 	const int type = icmp_hdr(skb)->type;
 	const int code = icmp_hdr(skb)->code;
-	struct sock *sk;
 	struct request_sock *fastopen;
+	struct tcp_sock *tp;
 	u32 seq, snd_una;
+	struct sock *sk;
 	int err;
-	struct net *net = dev_net(skb->dev);
 
 	sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 				       iph->daddr, th->dest, iph->saddr,
@@ -786,7 +786,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	arg.iov[0].iov_base = (unsigned char *)&rep;
 	arg.iov[0].iov_len  = sizeof(rep.th);
 
-	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
+	net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
 
 	/* Invalid TCP option size or twice included auth */
 	if (tcp_parse_auth_options(tcp_hdr(skb), &md5_hash_location, &aoh))
@@ -1961,7 +1961,7 @@ EXPORT_SYMBOL(tcp_v4_do_rcv);
 
 int tcp_v4_early_demux(struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	struct sock *sk;
@@ -2172,7 +2172,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 
 int tcp_v4_rcv(struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	enum skb_drop_reason drop_reason;
 	int sdif = inet_sdif(skb);
 	int dif = inet_iif(skb);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 95669935494ef..4251670e328c8 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -170,7 +170,7 @@ static struct tcp_metrics_block *tcpm_new(struct dst_entry *dst,
 	bool reclaim = false;
 
 	spin_lock_bh(&tcp_metrics_lock);
-	net = dev_net(dst->dev);
+	net = dev_net_rcu(dst->dev);
 
 	/* While waiting for the spin-lock the cache might have been populated
 	 * with this entry and so we have to check again.
@@ -273,7 +273,7 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req,
 		return NULL;
 	}
 
-	net = dev_net(dst->dev);
+	net = dev_net_rcu(dst->dev);
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 
@@ -318,7 +318,7 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk,
 	else
 		return NULL;
 
-	net = dev_net(dst->dev);
+	net = dev_net_rcu(dst->dev);
 	hash ^= net_hash_mix(net);
 	hash = hash_32(hash, tcp_metrics_hash_log);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index d01088ab80d24..fe75ad8e606cb 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -376,7 +376,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 {
 	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
 	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	struct request_sock *fastopen;
 	struct ipv6_pinfo *np;
 	struct tcp_sock *tp;
@@ -866,16 +866,16 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 				 int oif, int rst, u8 tclass, __be32 label,
 				 u32 priority, u32 txhash, struct tcp_key *key)
 {
-	const struct tcphdr *th = tcp_hdr(skb);
-	struct tcphdr *t1;
-	struct sk_buff *buff;
-	struct flowi6 fl6;
-	struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
-	struct sock *ctl_sk = net->ipv6.tcp_sk;
+	struct net *net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
 	unsigned int tot_len = sizeof(struct tcphdr);
+	struct sock *ctl_sk = net->ipv6.tcp_sk;
+	const struct tcphdr *th = tcp_hdr(skb);
 	__be32 mrst = 0, *topt;
 	struct dst_entry *dst;
-	__u32 mark = 0;
+	struct sk_buff *buff;
+	struct tcphdr *t1;
+	struct flowi6 fl6;
+	u32 mark = 0;
 
 	if (tsecr)
 		tot_len += TCPOLEN_TSTAMP_ALIGNED;
@@ -1041,7 +1041,7 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
 	if (!sk && !ipv6_unicast_destination(skb))
 		return;
 
-	net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);
+	net = sk ? sock_net(sk) : dev_net_rcu(skb_dst(skb)->dev);
 	/* Invalid TCP option size or twice included auth */
 	if (tcp_parse_auth_options(th, &md5_hash_location, &aoh))
 		return;
@@ -1740,6 +1740,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 
 INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 {
+	struct net *net = dev_net_rcu(skb->dev);
 	enum skb_drop_reason drop_reason;
 	int sdif = inet6_sdif(skb);
 	int dif = inet6_iif(skb);
@@ -1749,7 +1750,6 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 	bool refcounted;
 	int ret;
 	u32 isn;
-	struct net *net = dev_net(skb->dev);
 
 	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (skb->pkt_type != PACKET_HOST)
@@ -2001,7 +2001,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 
 void tcp_v6_early_demux(struct sk_buff *skb)
 {
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	const struct ipv6hdr *hdr;
 	const struct tcphdr *th;
 	struct sock *sk;

From 9b49f57ccd3aa1560f215b3f8218b2783ff18391 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:22 +0000
Subject: [PATCH 1454/2753] net: gro: convert four dev_net() calls

tcp4_check_fraglist_gro(), tcp6_check_fraglist_gro(),
udp4_gro_lookup_skb() and udp6_gro_lookup_skb()
assume RCU is held so that the net structure does not disappear.

Use dev_net_rcu() instead of dev_net() to get LOCKDEP support.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_offload.c   | 2 +-
 net/ipv4/udp_offload.c   | 2 +-
 net/ipv6/tcpv6_offload.c | 2 +-
 net/ipv6/udp_offload.c   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2308665b51c53..ecef16c58c071 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -425,7 +425,7 @@ static void tcp4_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
 
 	inet_get_iif_sdif(skb, &iif, &sdif);
 	iph = skb_gro_network_header(skb);
-	net = dev_net(skb->dev);
+	net = dev_net_rcu(skb->dev);
 	sk = __inet_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 				       iph->saddr, th->source,
 				       iph->daddr, ntohs(th->dest),
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index a5be6e4ed326f..c1a85b300ee87 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -630,7 +630,7 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 					__be16 dport)
 {
 	const struct iphdr *iph = skb_gro_network_header(skb);
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	int iif, sdif;
 
 	inet_get_iif_sdif(skb, &iif, &sdif);
diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index a45bf17cb2a17..91b88daa5b555 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -35,7 +35,7 @@ static void tcp6_check_fraglist_gro(struct list_head *head, struct sk_buff *skb,
 
 	inet6_get_iif_sdif(skb, &iif, &sdif);
 	hdr = skb_gro_network_header(skb);
-	net = dev_net(skb->dev);
+	net = dev_net_rcu(skb->dev);
 	sk = __inet6_lookup_established(net, net->ipv4.tcp_death_row.hashinfo,
 					&hdr->saddr, th->source,
 					&hdr->daddr, ntohs(th->dest),
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b41152dd42469..404212dfc99ab 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -117,7 +117,7 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 					__be16 dport)
 {
 	const struct ipv6hdr *iph = skb_gro_network_header(skb);
-	struct net *net = dev_net(skb->dev);
+	struct net *net = dev_net_rcu(skb->dev);
 	int iif, sdif;
 
 	inet6_get_iif_sdif(skb, &iif, &sdif);

From 5282de17621f80a1e2c6c26229975182ecade5b9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:23 +0000
Subject: [PATCH 1455/2753] tcp: remove READ_ONCE(req->ts_recent)

After commit 8d52da23b6c6 ("tcp: Defer ts_recent changes
until req is owned"), req->ts_recent is not changed anymore.

It is set once in tcp_openreq_init(), bpf_sk_assign_tcp_reqsk()
or cookie_tcp_reqsk_alloc() before the req can be seen by other
cpus/threads.

This completes the revert of eba20811f326 ("tcp: annotate
data-races around tcp_rsk(req)->ts_recent").

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Wang Hai <wanghai38@huawei.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-6-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c      | 2 +-
 net/ipv4/tcp_minisocks.c | 4 ++--
 net/ipv4/tcp_output.c    | 2 +-
 net/ipv6/tcp_ipv6.c      | 2 +-
 4 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index ae07613e4f335..d9405b012dff0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1155,7 +1155,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_nxt,
 			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
-			READ_ONCE(req->ts_recent),
+			req->ts_recent,
 			0, &key,
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
 			ip_hdr(skb)->tos,
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index ba4a5d7f251d8..3cb8f281186b2 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -585,7 +585,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
 
 	if (newtp->rx_opt.tstamp_ok) {
 		newtp->tcp_usec_ts = treq->req_usec_ts;
-		newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent);
+		newtp->rx_opt.ts_recent = req->ts_recent;
 		newtp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 		newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED;
 	} else {
@@ -673,7 +673,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL);
 
 		if (tmp_opt.saw_tstamp) {
-			tmp_opt.ts_recent = READ_ONCE(req->ts_recent);
+			tmp_opt.ts_recent = req->ts_recent;
 			if (tmp_opt.rcv_tsecr) {
 				if (inet_rsk(req)->tstamp_ok && !fastopen)
 					tsecr_reject = !between(tmp_opt.rcv_tsecr,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0a660075add5b..24e56bf967472 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -949,7 +949,7 @@ static unsigned int tcp_synack_options(const struct sock *sk,
 			tcp_rsk(req)->snt_tsval_first = opts->tsval;
 		}
 		WRITE_ONCE(tcp_rsk(req)->snt_tsval_last, opts->tsval);
-		opts->tsecr = READ_ONCE(req->ts_recent);
+		opts->tsecr = req->ts_recent;
 		remaining -= TCPOLEN_TSTAMP_ALIGNED;
 	}
 	if (likely(ireq->sack_ok)) {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index fe75ad8e606cb..85c4820bfe158 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1279,7 +1279,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_rsk(req)->rcv_nxt,
 			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
-			READ_ONCE(req->ts_recent), sk->sk_bound_dev_if,
+			req->ts_recent, sk->sk_bound_dev_if,
 			&key, ipv6_get_dsfield(ipv6_hdr(skb)), 0,
 			READ_ONCE(sk->sk_priority),
 			READ_ONCE(tcp_rsk(req)->txhash));

From 863a952eb79a6acf2b1f654f4e75ed104ff4cc81 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sat, 1 Mar 2025 20:14:24 +0000
Subject: [PATCH 1456/2753] tcp: tcp_set_window_clamp() cleanup

Remove one indentation level.

Use max_t() and clamp() macros.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250301201424.2046477-7-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 36 ++++++++++++++++++------------------
 1 file changed, 18 insertions(+), 18 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 1184866922130..eb5a60c7a9ccd 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3693,33 +3693,33 @@ EXPORT_SYMBOL(tcp_sock_set_keepcnt);
 
 int tcp_set_window_clamp(struct sock *sk, int val)
 {
+	u32 old_window_clamp, new_window_clamp;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (!val) {
 		if (sk->sk_state != TCP_CLOSE)
 			return -EINVAL;
 		WRITE_ONCE(tp->window_clamp, 0);
-	} else {
-		u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp;
-		u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ?
-						SOCK_MIN_RCVBUF / 2 : val;
+		return 0;
+	}
 
-		if (new_window_clamp == old_window_clamp)
-			return 0;
+	old_window_clamp = tp->window_clamp;
+	new_window_clamp = max_t(int, SOCK_MIN_RCVBUF / 2, val);
 
-		WRITE_ONCE(tp->window_clamp, new_window_clamp);
-		if (new_window_clamp < old_window_clamp) {
-			/* need to apply the reserved mem provisioning only
-			 * when shrinking the window clamp
-			 */
-			__tcp_adjust_rcv_ssthresh(sk, tp->window_clamp);
+	if (new_window_clamp == old_window_clamp)
+		return 0;
 
-		} else {
-			new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp);
-			tp->rcv_ssthresh = max(new_rcv_ssthresh,
-					       tp->rcv_ssthresh);
-		}
-	}
+	WRITE_ONCE(tp->window_clamp, new_window_clamp);
+
+	/* Need to apply the reserved mem provisioning only
+	 * when shrinking the window clamp.
+	 */
+	if (new_window_clamp < old_window_clamp)
+		__tcp_adjust_rcv_ssthresh(sk, new_window_clamp);
+	else
+		tp->rcv_ssthresh = clamp(new_window_clamp,
+					 tp->rcv_ssthresh,
+					 tp->rcv_wnd);
 	return 0;
 }
 

From 456cc675b6d4cadd4872a477d8976ff56eef4b6f Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 28 Feb 2025 18:01:31 +0800
Subject: [PATCH 1457/2753] sock: add sock_kmemdup helper

This patch adds the sock version of kmemdup() helper, named sock_kmemdup(),
to duplicate the input "src" memory block using the socket's option memory
buffer.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/f828077394c7d1f3560123497348b438c875b510.1740735165.git.tanggeliang@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/sock.h |  2 ++
 net/core/sock.c    | 16 ++++++++++++++++
 2 files changed, 18 insertions(+)

diff --git a/include/net/sock.h b/include/net/sock.h
index e771d99f81b0d..8daf1b3b12c60 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1797,6 +1797,8 @@ static inline struct sk_buff *sock_alloc_send_skb(struct sock *sk,
 }
 
 void *sock_kmalloc(struct sock *sk, int size, gfp_t priority);
+void *sock_kmemdup(struct sock *sk, const void *src,
+		   int size, gfp_t priority);
 void sock_kfree_s(struct sock *sk, void *mem, int size);
 void sock_kzfree_s(struct sock *sk, void *mem, int size);
 void sk_send_sigurg(struct sock *sk);
diff --git a/net/core/sock.c b/net/core/sock.c
index 23bce41f7f1ff..a0598518ce898 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2836,6 +2836,22 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
 }
 EXPORT_SYMBOL(sock_kmalloc);
 
+/*
+ * Duplicate the input "src" memory block using the socket's
+ * option memory buffer.
+ */
+void *sock_kmemdup(struct sock *sk, const void *src,
+		   int size, gfp_t priority)
+{
+	void *mem;
+
+	mem = sock_kmalloc(sk, size, priority);
+	if (mem)
+		memcpy(mem, src, size);
+	return mem;
+}
+EXPORT_SYMBOL(sock_kmemdup);
+
 /* Free an option memory block. Note, we actually want the inline
  * here as this allows gcc to detect the nullify and fold away the
  * condition entirely.

From 483cec55c1ccb9deeefb515fbeb181f736c41736 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 28 Feb 2025 18:01:32 +0800
Subject: [PATCH 1458/2753] net: use sock_kmemdup for ip_options

Instead of using sock_kmalloc() to allocate an ip_options and then
immediately duplicate another ip_options to the newly allocated one in
ipv6_dup_options(), mptcp_copy_ip_options() and sctp_v4_copy_ip_options(),
the newly added sock_kmemdup() helper can be used to simplify the code.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/91ae749d66600ec6fb679e0e518fda6acb5c3e6f.1740735165.git.tanggeliang@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/exthdrs.c   | 3 +--
 net/mptcp/protocol.c | 7 ++-----
 net/sctp/protocol.c  | 7 ++-----
 3 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c
index 6789623b2b0d1..457de0745a338 100644
--- a/net/ipv6/exthdrs.c
+++ b/net/ipv6/exthdrs.c
@@ -1204,10 +1204,9 @@ ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt)
 {
 	struct ipv6_txoptions *opt2;
 
-	opt2 = sock_kmalloc(sk, opt->tot_len, GFP_ATOMIC);
+	opt2 = sock_kmemdup(sk, opt, opt->tot_len, GFP_ATOMIC);
 	if (opt2) {
 		long dif = (char *)opt2 - (char *)opt;
-		memcpy(opt2, opt, opt->tot_len);
 		if (opt2->hopopt)
 			*((char **)&opt2->hopopt) += dif;
 		if (opt2->dst0opt)
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index 6b61b7dee33be..ec23e65ef0f11 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3178,12 +3178,9 @@ static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk)
 	rcu_read_lock();
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt) {
-		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+		newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) +
 				      inet_opt->opt.optlen, GFP_ATOMIC);
-		if (newopt)
-			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
-			       inet_opt->opt.optlen);
-		else
+		if (!newopt)
 			net_warn_ratelimited("%s: Failed to copy ip options\n", __func__);
 	}
 	RCU_INIT_POINTER(newinet->inet_opt, newopt);
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 29727ed1008ed..5407a3922101d 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -185,12 +185,9 @@ static void sctp_v4_copy_ip_options(struct sock *sk, struct sock *newsk)
 	rcu_read_lock();
 	inet_opt = rcu_dereference(inet->inet_opt);
 	if (inet_opt) {
-		newopt = sock_kmalloc(newsk, sizeof(*inet_opt) +
+		newopt = sock_kmemdup(newsk, inet_opt, sizeof(*inet_opt) +
 				      inet_opt->opt.optlen, GFP_ATOMIC);
-		if (newopt)
-			memcpy(newopt, inet_opt, sizeof(*inet_opt) +
-			       inet_opt->opt.optlen);
-		else
+		if (!newopt)
 			pr_err("%s: Failed to copy ip options\n", __func__);
 	}
 	RCU_INIT_POINTER(newinet->inet_opt, newopt);

From 52f83c0b5f857dbe24f66fc9a7f035523e9ffbc9 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 28 Feb 2025 18:01:33 +0800
Subject: [PATCH 1459/2753] mptcp: use sock_kmemdup for address entry

Instead of using sock_kmalloc() to allocate an address
entry "e" and then immediately duplicate the input "entry"
to it, the newly added sock_kmemdup() helper can be used in
mptcp_userspace_pm_append_new_local_addr() to simplify the code.

More importantly, the code "*e = *entry;" that assigns "entry"
to "e" is not easy to implemented in BPF if we use the same code
to implement an append_new_local_addr() helper of a BFP path
manager. This patch avoids this type of memory assignment
operation.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/3e5a307aed213038a87e44ff93b5793229b16279.1740735165.git.tanggeliang@kylinos.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_userspace.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 6bf6a20ef7f3e..7e7d01bef5d40 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -71,13 +71,12 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk,
 		/* Memory for the entry is allocated from the
 		 * sock option buffer.
 		 */
-		e = sock_kmalloc(sk, sizeof(*e), GFP_ATOMIC);
+		e = sock_kmemdup(sk, entry, sizeof(*entry), GFP_ATOMIC);
 		if (!e) {
 			ret = -ENOMEM;
 			goto append_err;
 		}
 
-		*e = *entry;
 		if (!e->addr.id && needs_id)
 			e->addr.id = find_next_zero_bit(id_bitmap,
 							MPTCP_PM_MAX_ADDR_ID + 1,

From 60d7505292c4591b7c805511d8db1eef04ecbe9d Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Fri, 28 Feb 2025 17:51:48 +0800
Subject: [PATCH 1460/2753] mptcp: Remove unused declaration
 mptcp_set_owner_r()

Commit 6639498ed85f ("mptcp: cleanup mem accounting")
removed the implementation but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228095148.4003065-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/protocol.h | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index abafc99496b91..7b74dedc79362 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -720,7 +720,6 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk);
 bool __mptcp_close(struct sock *sk, long timeout);
 void mptcp_cancel_work(struct sock *sk);
 void __mptcp_unaccepted_force_close(struct sock *sk);
-void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk);
 void mptcp_set_state(struct sock *sk, int state);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,

From 05ec5c085eb7ae044d49e04a3cff194a0b2a3251 Mon Sep 17 00:00:00 2001
From: Martin Schiller <ms@dev.tdt.de>
Date: Thu, 27 Feb 2025 08:10:58 +0100
Subject: [PATCH 1461/2753] net: sfp: add quirk for FS SFP-10GM-T copper SFP+
 module

Add quirk for a copper SFP that identifies itself as "FS" "SFP-10GM-T".
It uses RollBall protocol to talk to the PHY and needs 4 sec wait before
probing the PHY.

Signed-off-by: Martin Schiller <ms@dev.tdt.de>
Link: https://patch.msgid.link/20250227071058.1520027-1-ms@dev.tdt.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/sfp.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index 9369f52977694..c88217af44a14 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -385,7 +385,7 @@ static void sfp_fixup_rollball(struct sfp *sfp)
 	sfp->phy_t_retry = msecs_to_jiffies(1000);
 }
 
-static void sfp_fixup_fs_2_5gt(struct sfp *sfp)
+static void sfp_fixup_rollball_wait4s(struct sfp *sfp)
 {
 	sfp_fixup_rollball(sfp);
 
@@ -399,7 +399,7 @@ static void sfp_fixup_fs_2_5gt(struct sfp *sfp)
 static void sfp_fixup_fs_10gt(struct sfp *sfp)
 {
 	sfp_fixup_10gbaset_30m(sfp);
-	sfp_fixup_fs_2_5gt(sfp);
+	sfp_fixup_rollball_wait4s(sfp);
 }
 
 static void sfp_fixup_halny_gsfp(struct sfp *sfp)
@@ -479,9 +479,10 @@ static const struct sfp_quirk sfp_quirks[] = {
 	// PHY.
 	SFP_QUIRK_F("FS", "SFP-10G-T", sfp_fixup_fs_10gt),
 
-	// Fiberstore SFP-2.5G-T uses Rollball protocol to talk to the PHY and
-	// needs 4 sec wait before probing the PHY.
-	SFP_QUIRK_F("FS", "SFP-2.5G-T", sfp_fixup_fs_2_5gt),
+	// Fiberstore SFP-2.5G-T and SFP-10GM-T uses Rollball protocol to talk
+	// to the PHY and needs 4 sec wait before probing the PHY.
+	SFP_QUIRK_F("FS", "SFP-2.5G-T", sfp_fixup_rollball_wait4s),
+	SFP_QUIRK_F("FS", "SFP-10GM-T", sfp_fixup_rollball_wait4s),
 
 	// Fiberstore GPON-ONU-34-20BI can operate at 2500base-X, but report 1.2GBd
 	// NRZ in their EEPROM

From cc5bfc4e16fc1d1c520cd7bb28646e82b6e69217 Mon Sep 17 00:00:00 2001
From: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Date: Thu, 30 Jan 2025 23:49:31 +0000
Subject: [PATCH 1462/2753] usb: dwc3: Set SUSPENDENABLE soon after phy init

After phy initialization, some phy operations can only be executed while
in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and
GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid blocking
phy ops.

Previously the SUSPENDENABLE bits are only set after the controller
initialization, which may not happen right away if there's no gadget
driver or xhci driver bound. Revise this to clear SUSPENDENABLE bits
only when there's mode switching (change in GCTL.PRTCAPDIR).

Fixes: 6d735722063a ("usb: dwc3: core: Prevent phy suspend during init")
Cc: stable <stable@kernel.org>
Signed-off-by: Thinh Nguyen <Thinh.Nguyen@synopsys.com>
Link: https://lore.kernel.org/r/633aef0afee7d56d2316f7cc3e1b2a6d518a8cc9.1738280911.git.Thinh.Nguyen@synopsys.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/dwc3/core.c | 69 +++++++++++++++++++++++++----------------
 drivers/usb/dwc3/core.h |  2 +-
 drivers/usb/dwc3/drd.c  |  4 +--
 3 files changed, 45 insertions(+), 30 deletions(-)

diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
index 2c472cb97f6c7..66a08b5271653 100644
--- a/drivers/usb/dwc3/core.c
+++ b/drivers/usb/dwc3/core.c
@@ -131,11 +131,24 @@ void dwc3_enable_susphy(struct dwc3 *dwc, bool enable)
 	}
 }
 
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode)
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy)
 {
+	unsigned int hw_mode;
 	u32 reg;
 
 	reg = dwc3_readl(dwc->regs, DWC3_GCTL);
+
+	 /*
+	  * For DRD controllers, GUSB3PIPECTL.SUSPENDENABLE and
+	  * GUSB2PHYCFG.SUSPHY should be cleared during mode switching,
+	  * and they can be set after core initialization.
+	  */
+	hw_mode = DWC3_GHWPARAMS0_MODE(dwc->hwparams.hwparams0);
+	if (hw_mode == DWC3_GHWPARAMS0_MODE_DRD && !ignore_susphy) {
+		if (DWC3_GCTL_PRTCAP(reg) != mode)
+			dwc3_enable_susphy(dwc, false);
+	}
+
 	reg &= ~(DWC3_GCTL_PRTCAPDIR(DWC3_GCTL_PRTCAP_OTG));
 	reg |= DWC3_GCTL_PRTCAPDIR(mode);
 	dwc3_writel(dwc->regs, DWC3_GCTL, reg);
@@ -216,7 +229,7 @@ static void __dwc3_set_mode(struct work_struct *work)
 
 	spin_lock_irqsave(&dwc->lock, flags);
 
-	dwc3_set_prtcap(dwc, desired_dr_role);
+	dwc3_set_prtcap(dwc, desired_dr_role, false);
 
 	spin_unlock_irqrestore(&dwc->lock, flags);
 
@@ -658,16 +671,7 @@ static int dwc3_ss_phy_setup(struct dwc3 *dwc, int index)
 	 */
 	reg &= ~DWC3_GUSB3PIPECTL_UX_EXIT_PX;
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB3PIPECTL_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB3PIPECTL.SUSPENDENABLE must be
-	 * cleared after power-on reset, and it can be set after core
-	 * initialization.
-	 */
+	/* Ensure the GUSB3PIPECTL.SUSPENDENABLE is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB3PIPECTL_SUSPHY;
 
 	if (dwc->u2ss_inp3_quirk)
@@ -747,15 +751,7 @@ static int dwc3_hs_phy_setup(struct dwc3 *dwc, int index)
 		break;
 	}
 
-	/*
-	 * Above DWC_usb3.0 1.94a, it is recommended to set
-	 * DWC3_GUSB2PHYCFG_SUSPHY to '0' during coreConsultant configuration.
-	 * So default value will be '0' when the core is reset. Application
-	 * needs to set it to '1' after the core initialization is completed.
-	 *
-	 * Similarly for DRD controllers, GUSB2PHYCFG.SUSPHY must be cleared
-	 * after power-on reset, and it can be set after core initialization.
-	 */
+	/* Ensure the GUSB2PHYCFG.SUSPHY is cleared prior to phy init. */
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
 
 	if (dwc->dis_enblslpm_quirk)
@@ -830,6 +826,25 @@ static int dwc3_phy_init(struct dwc3 *dwc)
 			goto err_exit_usb3_phy;
 	}
 
+	/*
+	 * Above DWC_usb3.0 1.94a, it is recommended to set
+	 * DWC3_GUSB3PIPECTL_SUSPHY and DWC3_GUSB2PHYCFG_SUSPHY to '0' during
+	 * coreConsultant configuration. So default value will be '0' when the
+	 * core is reset. Application needs to set it to '1' after the core
+	 * initialization is completed.
+	 *
+	 * Certain phy requires to be in P0 power state during initialization.
+	 * Make sure GUSB3PIPECTL.SUSPENDENABLE and GUSB2PHYCFG.SUSPHY are clear
+	 * prior to phy init to maintain in the P0 state.
+	 *
+	 * After phy initialization, some phy operations can only be executed
+	 * while in lower P states. Ensure GUSB3PIPECTL.SUSPENDENABLE and
+	 * GUSB2PHYCFG.SUSPHY are set soon after initialization to avoid
+	 * blocking phy ops.
+	 */
+	if (!DWC3_VER_IS_WITHIN(DWC3, ANY, 194A))
+		dwc3_enable_susphy(dwc, true);
+
 	return 0;
 
 err_exit_usb3_phy:
@@ -1588,7 +1603,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 
 	switch (dwc->dr_mode) {
 	case USB_DR_MODE_PERIPHERAL:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, false);
@@ -1600,7 +1615,7 @@ static int dwc3_core_init_mode(struct dwc3 *dwc)
 			return dev_err_probe(dev, ret, "failed to initialize gadget\n");
 		break;
 	case USB_DR_MODE_HOST:
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, false);
 
 		if (dwc->usb2_phy)
 			otg_set_vbus(dwc->usb2_phy->otg, true);
@@ -1645,7 +1660,7 @@ static void dwc3_core_exit_mode(struct dwc3 *dwc)
 	}
 
 	/* de-assert DRVVBUS for HOST and OTG mode */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 }
 
 static void dwc3_get_software_properties(struct dwc3 *dwc)
@@ -2453,7 +2468,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_DEVICE, true);
 		dwc3_gadget_resume(dwc);
 		break;
 	case DWC3_GCTL_PRTCAP_HOST:
@@ -2461,7 +2476,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 			ret = dwc3_core_init_for_resume(dwc);
 			if (ret)
 				return ret;
-			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST);
+			dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_HOST, true);
 			break;
 		}
 		/* Restore GUSB2PHYCFG bits that were modified in suspend */
@@ -2490,7 +2505,7 @@ static int dwc3_resume_common(struct dwc3 *dwc, pm_message_t msg)
 		if (ret)
 			return ret;
 
-		dwc3_set_prtcap(dwc, dwc->current_dr_role);
+		dwc3_set_prtcap(dwc, dwc->current_dr_role, true);
 
 		dwc3_otg_init(dwc);
 		if (dwc->current_otg_role == DWC3_OTG_ROLE_HOST) {
diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
index c955039bb4f62..aaa39e663f60a 100644
--- a/drivers/usb/dwc3/core.h
+++ b/drivers/usb/dwc3/core.h
@@ -1558,7 +1558,7 @@ struct dwc3_gadget_ep_cmd_params {
 #define DWC3_HAS_OTG			BIT(3)
 
 /* prototypes */
-void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode);
+void dwc3_set_prtcap(struct dwc3 *dwc, u32 mode, bool ignore_susphy);
 void dwc3_set_mode(struct dwc3 *dwc, u32 mode);
 u32 dwc3_core_fifo_space(struct dwc3_ep *dep, u8 type);
 
diff --git a/drivers/usb/dwc3/drd.c b/drivers/usb/dwc3/drd.c
index d76ae676783cf..7977860932b14 100644
--- a/drivers/usb/dwc3/drd.c
+++ b/drivers/usb/dwc3/drd.c
@@ -173,7 +173,7 @@ void dwc3_otg_init(struct dwc3 *dwc)
 	 * block "Initialize GCTL for OTG operation".
 	 */
 	/* GCTL.PrtCapDir=2'b11 */
-	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+	dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 	/* GUSB2PHYCFG0.SusPHY=0 */
 	reg = dwc3_readl(dwc->regs, DWC3_GUSB2PHYCFG(0));
 	reg &= ~DWC3_GUSB2PHYCFG_SUSPHY;
@@ -556,7 +556,7 @@ int dwc3_drd_init(struct dwc3 *dwc)
 
 		dwc3_drd_update(dwc);
 	} else {
-		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG);
+		dwc3_set_prtcap(dwc, DWC3_GCTL_PRTCAP_OTG, true);
 
 		/* use OTG block to get ID event */
 		irq = dwc3_otg_get_irq(dwc);

From dfd3df31c9db752234d7d2e09bef2aeabb643ce4 Mon Sep 17 00:00:00 2001
From: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Date: Fri, 28 Feb 2025 13:13:56 +0100
Subject: [PATCH 1463/2753] mm/slab/kvfree_rcu: Switch to WQ_MEM_RECLAIM wq

Currently kvfree_rcu() APIs use a system workqueue which is
"system_unbound_wq" to driver RCU machinery to reclaim a memory.

Recently, it has been noted that the following kernel warning can
be observed:

<snip>
workqueue: WQ_MEM_RECLAIM nvme-wq:nvme_scan_work is flushing !WQ_MEM_RECLAIM events_unbound:kfree_rcu_work
  WARNING: CPU: 21 PID: 330 at kernel/workqueue.c:3719 check_flush_dependency+0x112/0x120
  Modules linked in: intel_uncore_frequency(E) intel_uncore_frequency_common(E) skx_edac(E) ...
  CPU: 21 UID: 0 PID: 330 Comm: kworker/u144:6 Tainted: G            E      6.13.2-0_g925d379822da #1
  Hardware name: Wiwynn Twin Lakes MP/Twin Lakes Passive MP, BIOS YMM20 02/01/2023
  Workqueue: nvme-wq nvme_scan_work
  RIP: 0010:check_flush_dependency+0x112/0x120
  Code: 05 9a 40 14 02 01 48 81 c6 c0 00 00 00 48 8b 50 18 48 81 c7 c0 00 00 00 48 89 f9 48 ...
  RSP: 0018:ffffc90000df7bd8 EFLAGS: 00010082
  RAX: 000000000000006a RBX: ffffffff81622390 RCX: 0000000000000027
  RDX: 00000000fffeffff RSI: 000000000057ffa8 RDI: ffff88907f960c88
  RBP: 0000000000000000 R08: ffffffff83068e50 R09: 000000000002fffd
  R10: 0000000000000004 R11: 0000000000000000 R12: ffff8881001a4400
  R13: 0000000000000000 R14: ffff88907f420fb8 R15: 0000000000000000
  FS:  0000000000000000(0000) GS:ffff88907f940000(0000) knlGS:0000000000000000
  CR2: 00007f60c3001000 CR3: 000000107d010005 CR4: 00000000007726f0
  PKRU: 55555554
  Call Trace:
   <TASK>
   ? __warn+0xa4/0x140
   ? check_flush_dependency+0x112/0x120
   ? report_bug+0xe1/0x140
   ? check_flush_dependency+0x112/0x120
   ? handle_bug+0x5e/0x90
   ? exc_invalid_op+0x16/0x40
   ? asm_exc_invalid_op+0x16/0x20
   ? timer_recalc_next_expiry+0x190/0x190
   ? check_flush_dependency+0x112/0x120
   ? check_flush_dependency+0x112/0x120
   __flush_work.llvm.1643880146586177030+0x174/0x2c0
   flush_rcu_work+0x28/0x30
   kvfree_rcu_barrier+0x12f/0x160
   kmem_cache_destroy+0x18/0x120
   bioset_exit+0x10c/0x150
   disk_release.llvm.6740012984264378178+0x61/0xd0
   device_release+0x4f/0x90
   kobject_put+0x95/0x180
   nvme_put_ns+0x23/0xc0
   nvme_remove_invalid_namespaces+0xb3/0xd0
   nvme_scan_work+0x342/0x490
   process_scheduled_works+0x1a2/0x370
   worker_thread+0x2ff/0x390
   ? pwq_release_workfn+0x1e0/0x1e0
   kthread+0xb1/0xe0
   ? __kthread_parkme+0x70/0x70
   ret_from_fork+0x30/0x40
   ? __kthread_parkme+0x70/0x70
   ret_from_fork_asm+0x11/0x20
   </TASK>
  ---[ end trace 0000000000000000 ]---
<snip>

To address this switch to use of independent WQ_MEM_RECLAIM
workqueue, so the rules are not violated from workqueue framework
point of view.

Apart of that, since kvfree_rcu() does reclaim memory it is worth
to go with WQ_MEM_RECLAIM type of wq because it is designed for
this purpose.

Fixes: 6c6c47b063b5 ("mm, slab: call kvfree_rcu_barrier() from kmem_cache_destroy()"),
Reported-by: Keith Busch <kbusch@kernel.org>
Closes: https://lore.kernel.org/all/Z7iqJtCjHKfo8Kho@kbusch-mbp/
Cc: stable@vger.kernel.org
Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 mm/slab_common.c | 14 ++++++++++----
 1 file changed, 10 insertions(+), 4 deletions(-)

diff --git a/mm/slab_common.c b/mm/slab_common.c
index 4030907b6b7d8..4c9f0a87f733b 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -1304,6 +1304,8 @@ module_param(rcu_min_cached_objs, int, 0444);
 static int rcu_delay_page_cache_fill_msec = 5000;
 module_param(rcu_delay_page_cache_fill_msec, int, 0444);
 
+static struct workqueue_struct *rcu_reclaim_wq;
+
 /* Maximum number of jiffies to wait before draining a batch. */
 #define KFREE_DRAIN_JIFFIES (5 * HZ)
 #define KFREE_N_BATCHES 2
@@ -1632,10 +1634,10 @@ __schedule_delayed_monitor_work(struct kfree_rcu_cpu *krcp)
 	if (delayed_work_pending(&krcp->monitor_work)) {
 		delay_left = krcp->monitor_work.timer.expires - jiffies;
 		if (delay < delay_left)
-			mod_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
+			mod_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay);
 		return;
 	}
-	queue_delayed_work(system_unbound_wq, &krcp->monitor_work, delay);
+	queue_delayed_work(rcu_reclaim_wq, &krcp->monitor_work, delay);
 }
 
 static void
@@ -1733,7 +1735,7 @@ kvfree_rcu_queue_batch(struct kfree_rcu_cpu *krcp)
 			// "free channels", the batch can handle. Break
 			// the loop since it is done with this CPU thus
 			// queuing an RCU work is _always_ success here.
-			queued = queue_rcu_work(system_unbound_wq, &krwp->rcu_work);
+			queued = queue_rcu_work(rcu_reclaim_wq, &krwp->rcu_work);
 			WARN_ON_ONCE(!queued);
 			break;
 		}
@@ -1883,7 +1885,7 @@ run_page_cache_worker(struct kfree_rcu_cpu *krcp)
 	if (rcu_scheduler_active == RCU_SCHEDULER_RUNNING &&
 			!atomic_xchg(&krcp->work_in_progress, 1)) {
 		if (atomic_read(&krcp->backoff_page_cache_fill)) {
-			queue_delayed_work(system_unbound_wq,
+			queue_delayed_work(rcu_reclaim_wq,
 				&krcp->page_cache_work,
 					msecs_to_jiffies(rcu_delay_page_cache_fill_msec));
 		} else {
@@ -2120,6 +2122,10 @@ void __init kvfree_rcu_init(void)
 	int i, j;
 	struct shrinker *kfree_rcu_shrinker;
 
+	rcu_reclaim_wq = alloc_workqueue("kvfree_rcu_reclaim",
+			WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+	WARN_ON(!rcu_reclaim_wq);
+
 	/* Clamp it to [0:100] seconds interval. */
 	if (rcu_delay_page_cache_fill_msec < 0 ||
 		rcu_delay_page_cache_fill_msec > 100 * MSEC_PER_SEC) {

From 8177c6bedb7013cf736137da586cf783922309dd Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:12 +0100
Subject: [PATCH 1464/2753] x86/cacheinfo: Validate CPUID leaf 0x2 EDX output

CPUID leaf 0x2 emits one-byte descriptors in its four output registers
EAX, EBX, ECX, and EDX.  For these descriptors to be valid, the most
significant bit (MSB) of each register must be clear.

The historical Git commit:

  019361a20f016 ("- pre6: Intel: start to add Pentium IV specific stuff (128-byte cacheline etc)...")

introduced leaf 0x2 output parsing.  It only validated the MSBs of EAX,
EBX, and ECX, but left EDX unchecked.

Validate EDX's most-significant bit.

Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@vger.kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-2-darwi@linutronix.de
---
 arch/x86/kernel/cpu/cacheinfo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index e6fa03ed9172c..a6c6bccfa8b8d 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -808,7 +808,7 @@ void init_intel_cacheinfo(struct cpuinfo_x86 *c)
 			cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 			/* If bit 31 is set, this is an unknown format */
-			for (j = 0 ; j < 3 ; j++)
+			for (j = 0 ; j < 4 ; j++)
 				if (regs[j] & (1 << 31))
 					regs[j] = 0;
 

From 1881148215c67151b146450fb89ec22fd92337a7 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:13 +0100
Subject: [PATCH 1465/2753] x86/cpu: Validate CPUID leaf 0x2 EDX output

CPUID leaf 0x2 emits one-byte descriptors in its four output registers
EAX, EBX, ECX, and EDX.  For these descriptors to be valid, the most
significant bit (MSB) of each register must be clear.

Leaf 0x2 parsing at intel.c only validated the MSBs of EAX, EBX, and
ECX, but left EDX unchecked.

Validate EDX's most-significant bit as well.

Fixes: e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-3-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 3dce22f00dc34..2a3716afee633 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -799,7 +799,7 @@ static void intel_detect_tlb(struct cpuinfo_x86 *c)
 		cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
 
 		/* If bit 31 is set, this is an unknown format */
-		for (j = 0 ; j < 3 ; j++)
+		for (j = 0 ; j < 4 ; j++)
 			if (regs[j] & (1 << 31))
 				regs[j] = 0;
 

From f6bdaab79ee4228a143ee1b4cb80416d6ffc0c63 Mon Sep 17 00:00:00 2001
From: "Ahmed S. Darwish" <darwi@linutronix.de>
Date: Tue, 4 Mar 2025 09:51:14 +0100
Subject: [PATCH 1466/2753] x86/cpu: Properly parse CPUID leaf 0x2 TLB
 descriptor 0x63

CPUID leaf 0x2's one-byte TLB descriptors report the number of entries
for specific TLB types, among other properties.

Typically, each emitted descriptor implies the same number of entries
for its respective TLB type(s).  An emitted 0x63 descriptor is an
exception: it implies 4 data TLB entries for 1GB pages and 32 data TLB
entries for 2MB or 4MB pages.

For the TLB descriptors parsing code, the entry count for 1GB pages is
encoded at the intel_tlb_table[] mapping, but the 2MB/4MB entry count is
totally ignored.

Update leaf 0x2's parsing logic 0x2 to account for 32 data TLB entries
for 2MB/4MB pages implied by the 0x63 descriptor.

Fixes: e0ba94f14f74 ("x86/tlb_info: get last level TLB entry number of CPU")
Signed-off-by: Ahmed S. Darwish <darwi@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: stable@kernel.org
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250304085152.51092-4-darwi@linutronix.de
---
 arch/x86/kernel/cpu/intel.c | 50 +++++++++++++++++++++++++------------
 1 file changed, 34 insertions(+), 16 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 2a3716afee633..134368a3f4b1e 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -635,26 +635,37 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
 }
 #endif
 
-#define TLB_INST_4K	0x01
-#define TLB_INST_4M	0x02
-#define TLB_INST_2M_4M	0x03
+#define TLB_INST_4K		0x01
+#define TLB_INST_4M		0x02
+#define TLB_INST_2M_4M		0x03
 
-#define TLB_INST_ALL	0x05
-#define TLB_INST_1G	0x06
+#define TLB_INST_ALL		0x05
+#define TLB_INST_1G		0x06
 
-#define TLB_DATA_4K	0x11
-#define TLB_DATA_4M	0x12
-#define TLB_DATA_2M_4M	0x13
-#define TLB_DATA_4K_4M	0x14
+#define TLB_DATA_4K		0x11
+#define TLB_DATA_4M		0x12
+#define TLB_DATA_2M_4M		0x13
+#define TLB_DATA_4K_4M		0x14
 
-#define TLB_DATA_1G	0x16
+#define TLB_DATA_1G		0x16
+#define TLB_DATA_1G_2M_4M	0x17
 
-#define TLB_DATA0_4K	0x21
-#define TLB_DATA0_4M	0x22
-#define TLB_DATA0_2M_4M	0x23
+#define TLB_DATA0_4K		0x21
+#define TLB_DATA0_4M		0x22
+#define TLB_DATA0_2M_4M		0x23
 
-#define STLB_4K		0x41
-#define STLB_4K_2M	0x42
+#define STLB_4K			0x41
+#define STLB_4K_2M		0x42
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of
+ * entries for their respective TLB types.  The 0x63 descriptor is an
+ * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
+ * for 2MB or 4MB pages.  Encode descriptor 0x63 dTLB entry count for
+ * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
+ * intel_tlb_table[] mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES	32
 
 static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x01, TLB_INST_4K,		32,	" TLB_INST 4 KByte pages, 4-way set associative" },
@@ -676,7 +687,8 @@ static const struct _tlb_table intel_tlb_table[] = {
 	{ 0x5c, TLB_DATA_4K_4M,		128,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x5d, TLB_DATA_4K_4M,		256,	" TLB_DATA 4 KByte and 4 MByte pages" },
 	{ 0x61, TLB_INST_4K,		48,	" TLB_INST 4 KByte pages, full associative" },
-	{ 0x63, TLB_DATA_1G,		4,	" TLB_DATA 1 GByte pages, 4-way set associative" },
+	{ 0x63, TLB_DATA_1G_2M_4M,	4,	" TLB_DATA 1 GByte pages, 4-way set associative"
+						" (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here)" },
 	{ 0x6b, TLB_DATA_4K,		256,	" TLB_DATA 4 KByte pages, 8-way associative" },
 	{ 0x6c, TLB_DATA_2M_4M,		128,	" TLB_DATA 2 MByte or 4 MByte pages, 8-way associative" },
 	{ 0x6d, TLB_DATA_1G,		16,	" TLB_DATA 1 GByte pages, fully associative" },
@@ -776,6 +788,12 @@ static void intel_tlb_lookup(const unsigned char desc)
 		if (tlb_lld_4m[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_4m[ENTRIES] = intel_tlb_table[k].entries;
 		break;
+	case TLB_DATA_1G_2M_4M:
+		if (tlb_lld_2m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_2m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		if (tlb_lld_4m[ENTRIES] < TLB_0x63_2M_4M_ENTRIES)
+			tlb_lld_4m[ENTRIES] = TLB_0x63_2M_4M_ENTRIES;
+		fallthrough;
 	case TLB_DATA_1G:
 		if (tlb_lld_1g[ENTRIES] < intel_tlb_table[k].entries)
 			tlb_lld_1g[ENTRIES] = intel_tlb_table[k].entries;

From 90b856ae3528e42b56baf3e59eba91cad1139778 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:55:57 +0100
Subject: [PATCH 1467/2753] net: pktgen: fix mix of int/long

Fix mix of int/long (and multiple conversion from/to) by using consequently
size_t for i and max and ssize_t for len and adjust function signatures
of hex32_arg(), count_trail_chars(), num_arg() and strn_len() accordingly.

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 38 ++++++++++++++++++++------------------
 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 402e01a2ce19e..4775cdd2ae1c3 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -744,10 +744,11 @@ static int pktgen_if_show(struct seq_file *seq, void *v)
 }
 
 
-static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
-		     __u32 *num)
+static ssize_t hex32_arg(const char __user *user_buffer, size_t maxlen,
+			 __u32 *num)
 {
-	int i = 0;
+	size_t i = 0;
+
 	*num = 0;
 
 	for (; i < maxlen; i++) {
@@ -766,10 +767,9 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen,
 	return i;
 }
 
-static int count_trail_chars(const char __user * user_buffer,
-			     unsigned int maxlen)
+static ssize_t count_trail_chars(const char __user *user_buffer, size_t maxlen)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < maxlen; i++) {
 		char c;
@@ -791,10 +791,10 @@ static int count_trail_chars(const char __user * user_buffer,
 	return i;
 }
 
-static long num_arg(const char __user *user_buffer, unsigned long maxlen,
-				unsigned long *num)
+static ssize_t num_arg(const char __user *user_buffer, size_t maxlen,
+		       unsigned long *num)
 {
-	int i;
+	size_t i;
 	*num = 0;
 
 	for (i = 0; i < maxlen; i++) {
@@ -810,9 +810,9 @@ static long num_arg(const char __user *user_buffer, unsigned long maxlen,
 	return i;
 }
 
-static int strn_len(const char __user * user_buffer, unsigned int maxlen)
+static ssize_t strn_len(const char __user *user_buffer, size_t maxlen)
 {
-	int i;
+	size_t i;
 
 	for (i = 0; i < maxlen; i++) {
 		char c;
@@ -842,9 +842,9 @@ static int strn_len(const char __user * user_buffer, unsigned int maxlen)
 static ssize_t get_imix_entries(const char __user *buffer,
 				struct pktgen_dev *pkt_dev)
 {
-	const int max_digits = 10;
-	int i = 0;
-	long len;
+	const size_t max_digits = 10;
+	size_t i = 0;
+	ssize_t len;
 	char c;
 
 	pkt_dev->n_imix_entries = 0;
@@ -893,9 +893,9 @@ static ssize_t get_imix_entries(const char __user *buffer,
 static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
 {
 	unsigned int n = 0;
+	size_t i = 0;
+	ssize_t len;
 	char c;
-	ssize_t i = 0;
-	int len;
 
 	pkt_dev->nr_labels = 0;
 	do {
@@ -954,7 +954,8 @@ static ssize_t pktgen_if_write(struct file *file,
 {
 	struct seq_file *seq = file->private_data;
 	struct pktgen_dev *pkt_dev = seq->private;
-	int i, max, len;
+	size_t i, max;
+	ssize_t len;
 	char name[16], valstr[32];
 	unsigned long value = 0;
 	char *pg_result = NULL;
@@ -1881,7 +1882,8 @@ static ssize_t pktgen_thread_write(struct file *file,
 {
 	struct seq_file *seq = file->private_data;
 	struct pktgen_thread *t = seq->private;
-	int i, max, len, ret;
+	size_t i, max;
+	ssize_t len, ret;
 	char name[40];
 	char *pg_result;
 

From 7d39e01803bdc210b71abacde74ff01a71f1b79c Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:55:58 +0100
Subject: [PATCH 1468/2753] net: pktgen: remove extra tmp variable (re-use len
 instead)

Remove extra tmp variable in pktgen_if_write (re-use len instead).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 4775cdd2ae1c3..9a5fc1298bd33 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -959,7 +959,6 @@ static ssize_t pktgen_if_write(struct file *file,
 	char name[16], valstr[32];
 	unsigned long value = 0;
 	char *pg_result = NULL;
-	int tmp = 0;
 	char buf[128];
 
 	pg_result = &(pkt_dev->result[0]);
@@ -970,12 +969,12 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	max = count;
-	tmp = count_trail_chars(user_buffer, max);
-	if (tmp < 0) {
+	len = count_trail_chars(user_buffer, max);
+	if (len < 0) {
 		pr_warn("illegal format\n");
-		return tmp;
+		return len;
 	}
-	i = tmp;
+	i = len;
 
 	/* Read variable name */
 

From 80f6c198dfd5fd7e59b39cb6be292528b6fcaaca Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:55:59 +0100
Subject: [PATCH 1469/2753] net: pktgen: remove some superfluous variable
 initializing

Remove some superfluous variable initializing before hex32_arg call (as the
same init is done here already).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 9a5fc1298bd33..b678b28dedae3 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1785,7 +1785,7 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "tos")) {
-		__u32 tmp_value = 0;
+		__u32 tmp_value;
 		len = hex32_arg(&user_buffer[i], 2, &tmp_value);
 		if (len < 0)
 			return len;
@@ -1801,7 +1801,7 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "traffic_class")) {
-		__u32 tmp_value = 0;
+		__u32 tmp_value;
 		len = hex32_arg(&user_buffer[i], 2, &tmp_value);
 		if (len < 0)
 			return len;

From 2b15a0693f70d1e8119743ee89edbfb1271b3ea8 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:56:00 +0100
Subject: [PATCH 1470/2753] net: pktgen: fix mpls maximum labels list parsing

Fix mpls maximum labels list parsing up to MAX_MPLS_LABELS entries (instead
of up to MAX_MPLS_LABELS - 1).

Addresses the following:

	$ echo "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f" > /proc/net/pktgen/lo\@0
	-bash: echo: write error: Argument list too long

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index b678b28dedae3..def35a734d9d5 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -900,6 +900,10 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
 	pkt_dev->nr_labels = 0;
 	do {
 		__u32 tmp;
+
+		if (n >= MAX_MPLS_LABELS)
+			return -E2BIG;
+
 		len = hex32_arg(&buffer[i], 8, &tmp);
 		if (len <= 0)
 			return len;
@@ -911,8 +915,6 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
 			return -EFAULT;
 		i++;
 		n++;
-		if (n >= MAX_MPLS_LABELS)
-			return -E2BIG;
 	} while (c == ',');
 
 	pkt_dev->nr_labels = n;

From c5cdbf23b84c8b502cfa4f81d9d33ddfc25a1182 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:56:01 +0100
Subject: [PATCH 1471/2753] net: pktgen: fix access outside of user given
 buffer in pktgen_if_write()

Honour the user given buffer size for the hex32_arg(), num_arg(),
strn_len(), get_imix_entries() and get_labels() calls (otherwise they will
access memory outside of the user given buffer).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 178 ++++++++++++++++++++++++++++++----------------
 1 file changed, 118 insertions(+), 60 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index def35a734d9d5..f4f9c9d83694a 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -840,10 +840,10 @@ static ssize_t strn_len(const char __user *user_buffer, size_t maxlen)
  * "size1,weight_1 size2,weight_2 ... size_n,weight_n" for example.
  */
 static ssize_t get_imix_entries(const char __user *buffer,
+				size_t maxlen,
 				struct pktgen_dev *pkt_dev)
 {
-	const size_t max_digits = 10;
-	size_t i = 0;
+	size_t i = 0, max;
 	ssize_t len;
 	char c;
 
@@ -856,10 +856,13 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES)
 			return -E2BIG;
 
-		len = num_arg(&buffer[i], max_digits, &size);
+		max = min(10, maxlen - i);
+		len = num_arg(&buffer[i], max, &size);
 		if (len < 0)
 			return len;
 		i += len;
+		if (i >= maxlen)
+			return -EINVAL;
 		if (get_user(c, &buffer[i]))
 			return -EFAULT;
 		/* Check for comma between size_i and weight_i */
@@ -870,7 +873,8 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		if (size < 14 + 20 + 8)
 			size = 14 + 20 + 8;
 
-		len = num_arg(&buffer[i], max_digits, &weight);
+		max = min(10, maxlen - i);
+		len = num_arg(&buffer[i], max, &weight);
 		if (len < 0)
 			return len;
 		if (weight <= 0)
@@ -880,20 +884,23 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		pkt_dev->imix_entries[pkt_dev->n_imix_entries].weight = weight;
 
 		i += len;
+		pkt_dev->n_imix_entries++;
+
+		if (i >= maxlen)
+			break;
 		if (get_user(c, &buffer[i]))
 			return -EFAULT;
-
 		i++;
-		pkt_dev->n_imix_entries++;
 	} while (c == ' ');
 
 	return i;
 }
 
-static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
+static ssize_t get_labels(const char __user *buffer,
+			  size_t maxlen, struct pktgen_dev *pkt_dev)
 {
 	unsigned int n = 0;
-	size_t i = 0;
+	size_t i = 0, max;
 	ssize_t len;
 	char c;
 
@@ -904,17 +911,20 @@ static ssize_t get_labels(const char __user *buffer, struct pktgen_dev *pkt_dev)
 		if (n >= MAX_MPLS_LABELS)
 			return -E2BIG;
 
-		len = hex32_arg(&buffer[i], 8, &tmp);
+		max = min(8, maxlen - i);
+		len = hex32_arg(&buffer[i], max, &tmp);
 		if (len <= 0)
 			return len;
 		pkt_dev->labels[n] = htonl(tmp);
 		if (pkt_dev->labels[n] & MPLS_STACK_BOTTOM)
 			pkt_dev->flags |= F_MPLS_RND;
 		i += len;
+		n++;
+		if (i >= maxlen)
+			break;
 		if (get_user(c, &buffer[i]))
 			return -EFAULT;
 		i++;
-		n++;
 	} while (c == ',');
 
 	pkt_dev->nr_labels = n;
@@ -979,8 +989,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	i = len;
 
 	/* Read variable name */
-
-	len = strn_len(&user_buffer[i], sizeof(name) - 1);
+	max = min(sizeof(name) - 1, count - i);
+	len = strn_len(&user_buffer[i], max);
 	if (len < 0)
 		return len;
 
@@ -1008,7 +1018,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "min_pkt_size")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1025,7 +1036,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "max_pkt_size")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1044,7 +1056,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	/* Shortcut for min = max */
 
 	if (!strcmp(name, "pkt_size")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1064,7 +1077,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (pkt_dev->clone_skb > 0)
 			return -EINVAL;
 
-		len = get_imix_entries(&user_buffer[i], pkt_dev);
+		max = count - i;
+		len = get_imix_entries(&user_buffer[i], max, pkt_dev);
 		if (len < 0)
 			return len;
 
@@ -1075,7 +1089,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "debug")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1086,7 +1101,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "frags")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1096,7 +1112,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "delay")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1111,7 +1128,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "rate")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1126,7 +1144,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "ratep")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1141,7 +1160,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "udp_src_min")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1154,7 +1174,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "udp_dst_min")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1167,7 +1188,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "udp_src_max")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1180,7 +1202,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "udp_dst_max")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1193,7 +1216,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "clone_skb")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 		/* clone_skb is not supported for netif_receive xmit_mode and
@@ -1214,7 +1238,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "count")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1225,7 +1250,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "src_mac_count")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1239,7 +1265,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst_mac_count")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1253,7 +1280,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "burst")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1272,7 +1300,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "node")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1293,11 +1322,12 @@ static ssize_t pktgen_if_write(struct file *file,
 	if (!strcmp(name, "xmit_mode")) {
 		char f[32];
 
-		memset(f, 0, 32);
-		len = strn_len(&user_buffer[i], sizeof(f) - 1);
+		max = min(sizeof(f) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
+		memset(f, 0, sizeof(f));
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
 		i += len;
@@ -1333,11 +1363,12 @@ static ssize_t pktgen_if_write(struct file *file,
 		char f[32];
 		char *end;
 
-		memset(f, 0, 32);
-		len = strn_len(&user_buffer[i], sizeof(f) - 1);
+		max = min(sizeof(f) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
+		memset(f, 0, 32);
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
 		i += len;
@@ -1382,7 +1413,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst_min") || !strcmp(name, "dst")) {
-		len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_min) - 1);
+		max = min(sizeof(pkt_dev->dst_min) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1402,7 +1434,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst_max")) {
-		len = strn_len(&user_buffer[i], sizeof(pkt_dev->dst_max) - 1);
+		max = min(sizeof(pkt_dev->dst_max) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1422,7 +1455,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst6")) {
-		len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+		max = min(sizeof(buf) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1445,7 +1479,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst6_min")) {
-		len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+		max = min(sizeof(buf) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1467,7 +1502,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst6_max")) {
-		len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+		max = min(sizeof(buf) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1488,7 +1524,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "src6")) {
-		len = strn_len(&user_buffer[i], sizeof(buf) - 1);
+		max = min(sizeof(buf) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1511,7 +1548,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "src_min")) {
-		len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_min) - 1);
+		max = min(sizeof(pkt_dev->src_min) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1531,7 +1569,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "src_max")) {
-		len = strn_len(&user_buffer[i], sizeof(pkt_dev->src_max) - 1);
+		max = min(sizeof(pkt_dev->src_max) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1551,7 +1590,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "dst_mac")) {
-		len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
+		max = min(sizeof(valstr) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1568,7 +1608,8 @@ static ssize_t pktgen_if_write(struct file *file,
 		return count;
 	}
 	if (!strcmp(name, "src_mac")) {
-		len = strn_len(&user_buffer[i], sizeof(valstr) - 1);
+		max = min(sizeof(valstr) - 1, count - i);
+		len = strn_len(&user_buffer[i], max);
 		if (len < 0)
 			return len;
 
@@ -1592,7 +1633,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "flows")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1606,7 +1648,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 #ifdef CONFIG_XFRM
 	if (!strcmp(name, "spi")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1617,7 +1660,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 #endif
 	if (!strcmp(name, "flowlen")) {
-		len = num_arg(&user_buffer[i], 10, &value);
+		max = min(10, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1628,7 +1672,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "queue_map_min")) {
-		len = num_arg(&user_buffer[i], 5, &value);
+		max = min(5, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1639,7 +1684,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "queue_map_max")) {
-		len = num_arg(&user_buffer[i], 5, &value);
+		max = min(5, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1652,7 +1698,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	if (!strcmp(name, "mpls")) {
 		unsigned int n, cnt;
 
-		len = get_labels(&user_buffer[i], pkt_dev);
+		max = count - i;
+		len = get_labels(&user_buffer[i], max, pkt_dev);
 		if (len < 0)
 			return len;
 		i += len;
@@ -1673,7 +1720,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "vlan_id")) {
-		len = num_arg(&user_buffer[i], 4, &value);
+		max = min(4, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1700,7 +1748,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "vlan_p")) {
-		len = num_arg(&user_buffer[i], 1, &value);
+		max = min(1, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1715,7 +1764,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "vlan_cfi")) {
-		len = num_arg(&user_buffer[i], 1, &value);
+		max = min(1, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1730,7 +1780,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "svlan_id")) {
-		len = num_arg(&user_buffer[i], 4, &value);
+		max = min(4, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1757,7 +1808,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "svlan_p")) {
-		len = num_arg(&user_buffer[i], 1, &value);
+		max = min(1, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1772,7 +1824,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "svlan_cfi")) {
-		len = num_arg(&user_buffer[i], 1, &value);
+		max = min(1, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 
@@ -1788,7 +1841,9 @@ static ssize_t pktgen_if_write(struct file *file,
 
 	if (!strcmp(name, "tos")) {
 		__u32 tmp_value;
-		len = hex32_arg(&user_buffer[i], 2, &tmp_value);
+
+		max = min(2, count - i);
+		len = hex32_arg(&user_buffer[i], max, &tmp_value);
 		if (len < 0)
 			return len;
 
@@ -1804,7 +1859,9 @@ static ssize_t pktgen_if_write(struct file *file,
 
 	if (!strcmp(name, "traffic_class")) {
 		__u32 tmp_value;
-		len = hex32_arg(&user_buffer[i], 2, &tmp_value);
+
+		max = min(2, count - i);
+		len = hex32_arg(&user_buffer[i], max, &tmp_value);
 		if (len < 0)
 			return len;
 
@@ -1819,7 +1876,8 @@ static ssize_t pktgen_if_write(struct file *file,
 	}
 
 	if (!strcmp(name, "skb_priority")) {
-		len = num_arg(&user_buffer[i], 9, &value);
+		max = min(9, count - i);
+		len = num_arg(&user_buffer[i], max, &value);
 		if (len < 0)
 			return len;
 

From 4bedafa7474ead37bdf31f19a7268ab1a14a7388 Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:56:02 +0100
Subject: [PATCH 1472/2753] net: pktgen: fix mpls reset parsing

Fix mpls list reset parsing to work as describe in
Documentation/networking/pktgen.rst:

  pgset "mpls 0"    turn off mpls (or any invalid argument works too!)

- before the patch

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	     mpls: 00000001, 00000002
	Result: OK: mpls=00000001,00000002

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ echo "mpls 0" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	     mpls: 00000000
	Result: OK: mpls=00000000

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ echo "mpls invalid" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	Result: OK: mpls=

- after the patch

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	     mpls: 00000001, 00000002
	Result: OK: mpls=00000001,00000002

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ echo "mpls 0" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	Result: OK: mpls=

	$ echo "mpls 00000001,00000002" > /proc/net/pktgen/lo\@0
	$ echo "mpls invalid" > /proc/net/pktgen/lo\@0
	$ grep mpls /proc/net/pktgen/lo\@0
	Result: OK: mpls=

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index f4f9c9d83694a..c604a68f2840f 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -913,8 +913,13 @@ static ssize_t get_labels(const char __user *buffer,
 
 		max = min(8, maxlen - i);
 		len = hex32_arg(&buffer[i], max, &tmp);
-		if (len <= 0)
+		if (len < 0)
 			return len;
+
+		/* return empty list in case of invalid input or zero value */
+		if (len == 0 || tmp == 0)
+			return maxlen;
+
 		pkt_dev->labels[n] = htonl(tmp);
 		if (pkt_dev->labels[n] & MPLS_STACK_BOTTOM)
 			pkt_dev->flags |= F_MPLS_RND;

From 21d0d99aebbd9bf152403aed137dc3117283930d Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:56:03 +0100
Subject: [PATCH 1473/2753] net: pktgen: remove all superfluous index
 assignements

Remove all superfluous index ('i += len') assignements (value not used
afterwards).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/pktgen.c | 52 ++++++-----------------------------------------
 1 file changed, 6 insertions(+), 46 deletions(-)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index c604a68f2840f..e850598db3e70 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -1028,7 +1028,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value < 14 + 20 + 8)
 			value = 14 + 20 + 8;
 		if (value != pkt_dev->min_pkt_size) {
@@ -1046,7 +1045,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value < 14 + 20 + 8)
 			value = 14 + 20 + 8;
 		if (value != pkt_dev->max_pkt_size) {
@@ -1066,7 +1064,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value < 14 + 20 + 8)
 			value = 14 + 20 + 8;
 		if (value != pkt_dev->min_pkt_size) {
@@ -1089,7 +1086,6 @@ static ssize_t pktgen_if_write(struct file *file,
 
 		fill_imix_distribution(pkt_dev);
 
-		i += len;
 		return count;
 	}
 
@@ -1099,7 +1095,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		debug = value;
 		sprintf(pg_result, "OK: debug=%u", debug);
 		return count;
@@ -1111,7 +1106,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->nfrags = value;
 		sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags);
 		return count;
@@ -1122,7 +1116,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value == 0x7FFFFFFF)
 			pkt_dev->delay = ULLONG_MAX;
 		else
@@ -1138,7 +1131,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (!value)
 			return -EINVAL;
 		pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value;
@@ -1154,7 +1146,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (!value)
 			return -EINVAL;
 		pkt_dev->delay = NSEC_PER_SEC/value;
@@ -1170,7 +1161,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value != pkt_dev->udp_src_min) {
 			pkt_dev->udp_src_min = value;
 			pkt_dev->cur_udp_src = value;
@@ -1184,7 +1174,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value != pkt_dev->udp_dst_min) {
 			pkt_dev->udp_dst_min = value;
 			pkt_dev->cur_udp_dst = value;
@@ -1198,7 +1187,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value != pkt_dev->udp_src_max) {
 			pkt_dev->udp_src_max = value;
 			pkt_dev->cur_udp_src = value;
@@ -1212,7 +1200,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value != pkt_dev->udp_dst_max) {
 			pkt_dev->udp_dst_max = value;
 			pkt_dev->cur_udp_dst = value;
@@ -1236,7 +1223,6 @@ static ssize_t pktgen_if_write(struct file *file,
 				  !(pkt_dev->flags & F_SHARED)))
 			return -EINVAL;
 
-		i += len;
 		pkt_dev->clone_skb = value;
 
 		sprintf(pg_result, "OK: clone_skb=%d", pkt_dev->clone_skb);
@@ -1248,7 +1234,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->count = value;
 		sprintf(pg_result, "OK: count=%llu",
 			(unsigned long long)pkt_dev->count);
@@ -1260,7 +1245,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (pkt_dev->src_mac_count != value) {
 			pkt_dev->src_mac_count = value;
 			pkt_dev->cur_src_mac_offset = 0;
@@ -1275,7 +1259,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (pkt_dev->dst_mac_count != value) {
 			pkt_dev->dst_mac_count = value;
 			pkt_dev->cur_dst_mac_offset = 0;
@@ -1290,7 +1273,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value > 1) &&
 		    ((pkt_dev->xmit_mode == M_QUEUE_XMIT) ||
 		     ((pkt_dev->xmit_mode == M_START_XMIT) &&
@@ -1310,8 +1292,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
-
 		if (node_possible(value)) {
 			pkt_dev->node = value;
 			sprintf(pg_result, "OK: node=%d", pkt_dev->node);
@@ -1335,7 +1315,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		memset(f, 0, sizeof(f));
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
-		i += len;
 
 		if (strcmp(f, "start_xmit") == 0) {
 			pkt_dev->xmit_mode = M_START_XMIT;
@@ -1376,7 +1355,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		memset(f, 0, 32);
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
-		i += len;
 
 		flag = pktgen_read_flag(f, &disable);
 		if (flag) {
@@ -1434,7 +1412,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		}
 		if (debug)
 			pr_debug("dst_min set to: %s\n", pkt_dev->dst_min);
-		i += len;
+
 		sprintf(pg_result, "OK: dst_min=%s", pkt_dev->dst_min);
 		return count;
 	}
@@ -1455,7 +1433,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		}
 		if (debug)
 			pr_debug("dst_max set to: %s\n", pkt_dev->dst_max);
-		i += len;
+
 		sprintf(pg_result, "OK: dst_max=%s", pkt_dev->dst_max);
 		return count;
 	}
@@ -1479,7 +1457,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (debug)
 			pr_debug("dst6 set to: %s\n", buf);
 
-		i += len;
 		sprintf(pg_result, "OK: dst6=%s", buf);
 		return count;
 	}
@@ -1502,7 +1479,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (debug)
 			pr_debug("dst6_min set to: %s\n", buf);
 
-		i += len;
 		sprintf(pg_result, "OK: dst6_min=%s", buf);
 		return count;
 	}
@@ -1524,7 +1500,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (debug)
 			pr_debug("dst6_max set to: %s\n", buf);
 
-		i += len;
 		sprintf(pg_result, "OK: dst6_max=%s", buf);
 		return count;
 	}
@@ -1548,7 +1523,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (debug)
 			pr_debug("src6 set to: %s\n", buf);
 
-		i += len;
 		sprintf(pg_result, "OK: src6=%s", buf);
 		return count;
 	}
@@ -1569,7 +1543,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		}
 		if (debug)
 			pr_debug("src_min set to: %s\n", pkt_dev->src_min);
-		i += len;
+
 		sprintf(pg_result, "OK: src_min=%s", pkt_dev->src_min);
 		return count;
 	}
@@ -1590,7 +1564,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		}
 		if (debug)
 			pr_debug("src_max set to: %s\n", pkt_dev->src_max);
-		i += len;
+
 		sprintf(pg_result, "OK: src_max=%s", pkt_dev->src_max);
 		return count;
 	}
@@ -1643,7 +1617,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value > MAX_CFLOWS)
 			value = MAX_CFLOWS;
 
@@ -1658,7 +1631,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->spi = value;
 		sprintf(pg_result, "OK: spi=%u", pkt_dev->spi);
 		return count;
@@ -1670,7 +1642,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->lflow = value;
 		sprintf(pg_result, "OK: flowlen=%u", pkt_dev->lflow);
 		return count;
@@ -1682,7 +1653,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->queue_map_min = value;
 		sprintf(pg_result, "OK: queue_map_min=%u", pkt_dev->queue_map_min);
 		return count;
@@ -1694,7 +1664,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->queue_map_max = value;
 		sprintf(pg_result, "OK: queue_map_max=%u", pkt_dev->queue_map_max);
 		return count;
@@ -1707,7 +1676,7 @@ static ssize_t pktgen_if_write(struct file *file,
 		len = get_labels(&user_buffer[i], max, pkt_dev);
 		if (len < 0)
 			return len;
-		i += len;
+
 		cnt = sprintf(pg_result, "OK: mpls=");
 		for (n = 0; n < pkt_dev->nr_labels; n++)
 			cnt += sprintf(pg_result + cnt,
@@ -1730,7 +1699,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (value <= 4095) {
 			pkt_dev->vlan_id = value;  /* turn on VLAN */
 
@@ -1758,7 +1726,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value <= 7) && (pkt_dev->vlan_id != 0xffff)) {
 			pkt_dev->vlan_p = value;
 			sprintf(pg_result, "OK: vlan_p=%u", pkt_dev->vlan_p);
@@ -1774,7 +1741,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value <= 1) && (pkt_dev->vlan_id != 0xffff)) {
 			pkt_dev->vlan_cfi = value;
 			sprintf(pg_result, "OK: vlan_cfi=%u", pkt_dev->vlan_cfi);
@@ -1790,7 +1756,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value <= 4095) && ((pkt_dev->vlan_id != 0xffff))) {
 			pkt_dev->svlan_id = value;  /* turn on SVLAN */
 
@@ -1818,7 +1783,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value <= 7) && (pkt_dev->svlan_id != 0xffff)) {
 			pkt_dev->svlan_p = value;
 			sprintf(pg_result, "OK: svlan_p=%u", pkt_dev->svlan_p);
@@ -1834,7 +1798,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if ((value <= 1) && (pkt_dev->svlan_id != 0xffff)) {
 			pkt_dev->svlan_cfi = value;
 			sprintf(pg_result, "OK: svlan_cfi=%u", pkt_dev->svlan_cfi);
@@ -1852,7 +1815,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (len == 2) {
 			pkt_dev->tos = tmp_value;
 			sprintf(pg_result, "OK: tos=0x%02x", pkt_dev->tos);
@@ -1870,7 +1832,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		if (len == 2) {
 			pkt_dev->traffic_class = tmp_value;
 			sprintf(pg_result, "OK: traffic_class=0x%02x", pkt_dev->traffic_class);
@@ -1886,7 +1847,6 @@ static ssize_t pktgen_if_write(struct file *file,
 		if (len < 0)
 			return len;
 
-		i += len;
 		pkt_dev->skb_priority = value;
 		sprintf(pg_result, "OK: skb_priority=%i",
 			pkt_dev->skb_priority);
@@ -2003,7 +1963,7 @@ static ssize_t pktgen_thread_write(struct file *file,
 		}
 		if (copy_from_user(f, &user_buffer[i], len))
 			return -EFAULT;
-		i += len;
+
 		mutex_lock(&pktgen_thread_lock);
 		ret = pktgen_add_device(t, f);
 		mutex_unlock(&pktgen_thread_lock);

From 03544faad76194f70c351aeb306c8aca5809089f Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Thu, 27 Feb 2025 14:56:04 +0100
Subject: [PATCH 1474/2753] selftest: net: add proc_net_pktgen

Add some test for /proc/net/pktgen/... interface.

- enable 'CONFIG_NET_PKTGEN=m' in tools/testing/selftests/net/config

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 +
 tools/testing/selftests/net/config            |   1 +
 tools/testing/selftests/net/proc_net_pktgen.c | 646 ++++++++++++++++++
 3 files changed, 648 insertions(+)
 create mode 100644 tools/testing/selftests/net/proc_net_pktgen.c

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 2e16ce6d28e46..d5aa16185f429 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -104,6 +104,7 @@ TEST_PROGS += vlan_bridge_binding.sh
 TEST_PROGS += bpf_offload.py
 TEST_PROGS += ipv6_route_update_soft_lockup.sh
 TEST_PROGS += busy_poll_test.sh
+TEST_GEN_PROGS += proc_net_pktgen
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index ab55270669ec4..a86f3e752ce2f 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -112,3 +112,4 @@ CONFIG_CAN=m
 CONFIG_CAN_DEV=m
 CONFIG_CAN_VXCAN=m
 CONFIG_NETKIT=y
+CONFIG_NET_PKTGEN=m
diff --git a/tools/testing/selftests/net/proc_net_pktgen.c b/tools/testing/selftests/net/proc_net_pktgen.c
new file mode 100644
index 0000000000000..462805ac16147
--- /dev/null
+++ b/tools/testing/selftests/net/proc_net_pktgen.c
@@ -0,0 +1,646 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * proc_net_pktgen: kselftest for /proc/net/pktgen interface
+ *
+ * Copyright (c) 2025 Peter Seiderer <ps.report@gmx.net>
+ *
+ */
+#include <errno.h>
+#include <fcntl.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include "../kselftest_harness.h"
+
+static const char ctrl_cmd_stop[] = "stop";
+static const char ctrl_cmd_start[] = "start";
+static const char ctrl_cmd_reset[] = "reset";
+
+static const char wrong_ctrl_cmd[] = "0123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789012345678901234567890123456789";
+
+static const char thr_cmd_add_loopback_0[] = "add_device lo@0";
+static const char thr_cmd_rm_loopback_0[] = "rem_device_all";
+
+static const char wrong_thr_cmd[] = "forsureawrongcommand";
+static const char legacy_thr_cmd[] = "max_before_softirq";
+
+static const char wrong_dev_cmd[] = "forsurewrongcommand";
+static const char dev_cmd_min_pkt_size_0[] = "min_pkt_size";
+static const char dev_cmd_min_pkt_size_1[] = "min_pkt_size ";
+static const char dev_cmd_min_pkt_size_2[] = "min_pkt_size 0";
+static const char dev_cmd_min_pkt_size_3[] = "min_pkt_size 1";
+static const char dev_cmd_min_pkt_size_4[] = "min_pkt_size 100";
+static const char dev_cmd_min_pkt_size_5[] = "min_pkt_size=1001";
+static const char dev_cmd_min_pkt_size_6[] = "min_pkt_size =2002";
+static const char dev_cmd_min_pkt_size_7[] = "min_pkt_size= 3003";
+static const char dev_cmd_min_pkt_size_8[] = "min_pkt_size = 4004";
+static const char dev_cmd_max_pkt_size_0[] = "max_pkt_size 200";
+static const char dev_cmd_pkt_size_0[] = "pkt_size 300";
+static const char dev_cmd_imix_weights_0[] = "imix_weights 0,7 576,4 1500,1";
+static const char dev_cmd_imix_weights_1[] = "imix_weights 101,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20";
+static const char dev_cmd_imix_weights_2[] = "imix_weights 100,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20 121,21";
+static const char dev_cmd_debug_0[] = "debug 1";
+static const char dev_cmd_debug_1[] = "debug 0";
+static const char dev_cmd_frags_0[] = "frags 100";
+static const char dev_cmd_delay_0[] = "delay 100";
+static const char dev_cmd_delay_1[] = "delay 2147483647";
+static const char dev_cmd_rate_0[] = "rate 0";
+static const char dev_cmd_rate_1[] = "rate 100";
+static const char dev_cmd_ratep_0[] = "ratep 0";
+static const char dev_cmd_ratep_1[] = "ratep 200";
+static const char dev_cmd_udp_src_min_0[] = "udp_src_min 1";
+static const char dev_cmd_udp_dst_min_0[] = "udp_dst_min 2";
+static const char dev_cmd_udp_src_max_0[] = "udp_src_max 3";
+static const char dev_cmd_udp_dst_max_0[] = "udp_dst_max 4";
+static const char dev_cmd_clone_skb_0[] = "clone_skb 1";
+static const char dev_cmd_clone_skb_1[] = "clone_skb 0";
+static const char dev_cmd_count_0[] = "count 100";
+static const char dev_cmd_src_mac_count_0[] = "src_mac_count 100";
+static const char dev_cmd_dst_mac_count_0[] = "dst_mac_count 100";
+static const char dev_cmd_burst_0[] = "burst 0";
+static const char dev_cmd_node_0[] = "node 100";
+static const char dev_cmd_xmit_mode_0[] = "xmit_mode start_xmit";
+static const char dev_cmd_xmit_mode_1[] = "xmit_mode netif_receive";
+static const char dev_cmd_xmit_mode_2[] = "xmit_mode queue_xmit";
+static const char dev_cmd_xmit_mode_3[] = "xmit_mode nonsense";
+static const char dev_cmd_flag_0[] = "flag UDPCSUM";
+static const char dev_cmd_flag_1[] = "flag !UDPCSUM";
+static const char dev_cmd_flag_2[] = "flag nonsense";
+static const char dev_cmd_dst_min_0[] = "dst_min 101.102.103.104";
+static const char dev_cmd_dst_0[] = "dst 101.102.103.104";
+static const char dev_cmd_dst_max_0[] = "dst_max 201.202.203.204";
+static const char dev_cmd_dst6_0[] = "dst6 2001:db38:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_dst6_min_0[] = "dst6_min 2001:db8:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_dst6_max_0[] = "dst6_max 2001:db8:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_src6_0[] = "src6 2001:db38:1234:0000:0000:0000:0000:0000";
+static const char dev_cmd_src_min_0[] = "src_min 101.102.103.104";
+static const char dev_cmd_src_max_0[] = "src_max 201.202.203.204";
+static const char dev_cmd_dst_mac_0[] = "dst_mac 01:02:03:04:05:06";
+static const char dev_cmd_src_mac_0[] = "src_mac 11:12:13:14:15:16";
+static const char dev_cmd_clear_counters_0[] = "clear_counters";
+static const char dev_cmd_flows_0[] = "flows 100";
+static const char dev_cmd_spi_0[] = "spi 100";
+static const char dev_cmd_flowlen_0[] = "flowlen 100";
+static const char dev_cmd_queue_map_min_0[] = "queue_map_min 1";
+static const char dev_cmd_queue_map_max_0[] = "queue_map_max 2";
+static const char dev_cmd_mpls_0[] = "mpls 00000001";
+static const char dev_cmd_mpls_1[] = "mpls 00000001,000000f2";
+static const char dev_cmd_mpls_2[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f";
+static const char dev_cmd_mpls_3[] = "mpls 00000f00,00000f01,00000f02,00000f03,00000f04,00000f05,00000f06,00000f07,00000f08,00000f09,00000f0a,00000f0b,00000f0c,00000f0d,00000f0e,00000f0f,00000f10";
+static const char dev_cmd_vlan_id_0[] = "vlan_id 1";
+static const char dev_cmd_vlan_p_0[] = "vlan_p 1";
+static const char dev_cmd_vlan_cfi_0[] = "vlan_cfi 1";
+static const char dev_cmd_vlan_id_1[] = "vlan_id 4096";
+static const char dev_cmd_svlan_id_0[] = "svlan_id 1";
+static const char dev_cmd_svlan_p_0[] = "svlan_p 1";
+static const char dev_cmd_svlan_cfi_0[] = "svlan_cfi 1";
+static const char dev_cmd_svlan_id_1[] = "svlan_id 4096";
+static const char dev_cmd_tos_0[] = "tos 0";
+static const char dev_cmd_tos_1[] = "tos 0f";
+static const char dev_cmd_tos_2[] = "tos 0ff";
+static const char dev_cmd_traffic_class_0[] = "traffic_class f0";
+static const char dev_cmd_skb_priority_0[] = "skb_priority 999";
+
+FIXTURE(proc_net_pktgen) {
+	int ctrl_fd;
+	int thr_fd;
+	int dev_fd;
+};
+
+FIXTURE_SETUP(proc_net_pktgen) {
+	int r;
+	ssize_t len;
+
+	r = system("modprobe pktgen");
+	ASSERT_EQ(r, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+	self->ctrl_fd = open("/proc/net/pktgen/pgctrl", O_RDWR);
+	ASSERT_GE(self->ctrl_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+	self->thr_fd = open("/proc/net/pktgen/kpktgend_0", O_RDWR);
+	ASSERT_GE(self->thr_fd, 0) TH_LOG("CONFIG_NET_PKTGEN not enabled, module pktgen not loaded?");
+
+	len = write(self->thr_fd, thr_cmd_add_loopback_0, sizeof(thr_cmd_add_loopback_0));
+	ASSERT_EQ(len, sizeof(thr_cmd_add_loopback_0)) TH_LOG("device lo@0 already registered?");
+
+	self->dev_fd = open("/proc/net/pktgen/lo@0", O_RDWR);
+	ASSERT_GE(self->dev_fd, 0) TH_LOG("device entry for lo@0 missing?");
+}
+
+FIXTURE_TEARDOWN(proc_net_pktgen) {
+	int ret;
+	ssize_t len;
+
+	ret = close(self->dev_fd);
+	EXPECT_EQ(ret, 0);
+
+	len = write(self->thr_fd, thr_cmd_rm_loopback_0, sizeof(thr_cmd_rm_loopback_0));
+	EXPECT_EQ(len, sizeof(thr_cmd_rm_loopback_0));
+
+	ret = close(self->thr_fd);
+	EXPECT_EQ(ret, 0);
+
+	ret = close(self->ctrl_fd);
+	EXPECT_EQ(ret, 0);
+}
+
+TEST_F(proc_net_pktgen, wrong_ctrl_cmd) {
+	for (int i = 0; i <= sizeof(wrong_ctrl_cmd); i++) {
+		ssize_t len;
+
+		len = write(self->ctrl_fd, wrong_ctrl_cmd, i);
+		EXPECT_EQ(len, -1);
+		EXPECT_EQ(errno, EINVAL);
+	}
+}
+
+TEST_F(proc_net_pktgen, ctrl_cmd) {
+	ssize_t len;
+
+	len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop));
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_stop));
+
+	len = write(self->ctrl_fd, ctrl_cmd_stop, sizeof(ctrl_cmd_stop) - 1);
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_stop) - 1);
+
+	len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start));
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_start));
+
+	len = write(self->ctrl_fd, ctrl_cmd_start, sizeof(ctrl_cmd_start) - 1);
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_start) - 1);
+
+	len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset));
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_reset));
+
+	len = write(self->ctrl_fd, ctrl_cmd_reset, sizeof(ctrl_cmd_reset) - 1);
+	EXPECT_EQ(len,	sizeof(ctrl_cmd_reset) - 1);
+}
+
+TEST_F(proc_net_pktgen, wrong_thr_cmd) {
+	for (int i = 0; i <= sizeof(wrong_thr_cmd); i++) {
+		ssize_t len;
+
+		len = write(self->thr_fd, wrong_thr_cmd, i);
+		EXPECT_EQ(len, -1);
+		EXPECT_EQ(errno, EINVAL);
+	}
+}
+
+TEST_F(proc_net_pktgen, legacy_thr_cmd) {
+	for (int i = 0; i <= sizeof(legacy_thr_cmd); i++) {
+		ssize_t len;
+
+		len = write(self->thr_fd, legacy_thr_cmd, i);
+		if (i < (sizeof(legacy_thr_cmd) - 1)) {
+			/* incomplete command string */
+			EXPECT_EQ(len, -1);
+			EXPECT_EQ(errno, EINVAL);
+		} else {
+			/* complete command string without/with trailing '\0' */
+			EXPECT_EQ(len, i);
+		}
+	}
+}
+
+TEST_F(proc_net_pktgen, wrong_dev_cmd) {
+	for (int i = 0; i <= sizeof(wrong_dev_cmd); i++) {
+		ssize_t len;
+
+		len = write(self->dev_fd, wrong_dev_cmd, i);
+		EXPECT_EQ(len, -1);
+		EXPECT_EQ(errno, EINVAL);
+	}
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_min_pkt_size) {
+	ssize_t len;
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0));
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_0, sizeof(dev_cmd_min_pkt_size_0) - 1);
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_0) - 1);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1));
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_1, sizeof(dev_cmd_min_pkt_size_1) - 1);
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_1) - 1);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2));
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_2, sizeof(dev_cmd_min_pkt_size_2) - 1);
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_2) - 1);
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_3, sizeof(dev_cmd_min_pkt_size_3));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_3));
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_4, sizeof(dev_cmd_min_pkt_size_4));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_4));
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_5, sizeof(dev_cmd_min_pkt_size_5));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_5));
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_6, sizeof(dev_cmd_min_pkt_size_6));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_6));
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_7, sizeof(dev_cmd_min_pkt_size_7));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_7));
+
+	len = write(self->dev_fd, dev_cmd_min_pkt_size_8, sizeof(dev_cmd_min_pkt_size_8));
+	EXPECT_EQ(len, sizeof(dev_cmd_min_pkt_size_8));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_max_pkt_size) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_max_pkt_size_0, sizeof(dev_cmd_max_pkt_size_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_max_pkt_size_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_pkt_size) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_pkt_size_0, sizeof(dev_cmd_pkt_size_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_pkt_size_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_imix_weights) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_imix_weights_0, sizeof(dev_cmd_imix_weights_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_0));
+
+	len = write(self->dev_fd, dev_cmd_imix_weights_1, sizeof(dev_cmd_imix_weights_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_imix_weights_1));
+
+	len = write(self->dev_fd, dev_cmd_imix_weights_2, sizeof(dev_cmd_imix_weights_2));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, E2BIG);
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_debug) {
+	ssize_t len;
+
+	/* debug on */
+	len = write(self->dev_fd, dev_cmd_debug_0, sizeof(dev_cmd_debug_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_debug_0));
+
+	/* debug off */
+	len = write(self->dev_fd, dev_cmd_debug_1, sizeof(dev_cmd_debug_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_debug_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_frags) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_frags_0, sizeof(dev_cmd_frags_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_frags_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_delay) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_delay_0, sizeof(dev_cmd_delay_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_delay_0));
+
+	len = write(self->dev_fd, dev_cmd_delay_1, sizeof(dev_cmd_delay_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_delay_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_rate) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_rate_0, sizeof(dev_cmd_rate_0));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	len = write(self->dev_fd, dev_cmd_rate_1, sizeof(dev_cmd_rate_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_rate_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_ratep) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_ratep_0, sizeof(dev_cmd_ratep_0));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	len = write(self->dev_fd, dev_cmd_ratep_1, sizeof(dev_cmd_ratep_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_ratep_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_src_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_udp_src_min_0, sizeof(dev_cmd_udp_src_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_udp_src_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_dst_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_udp_dst_min_0, sizeof(dev_cmd_udp_dst_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_src_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_udp_src_max_0, sizeof(dev_cmd_udp_src_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_udp_src_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_udp_dst_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_udp_dst_max_0, sizeof(dev_cmd_udp_dst_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_udp_dst_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_clone_skb) {
+	ssize_t len;
+
+	/* clone_skb on (gives EOPNOTSUPP on lo device) */
+	len = write(self->dev_fd, dev_cmd_clone_skb_0, sizeof(dev_cmd_clone_skb_0));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EOPNOTSUPP);
+
+	/* clone_skb off */
+	len = write(self->dev_fd, dev_cmd_clone_skb_1, sizeof(dev_cmd_clone_skb_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_clone_skb_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_count) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_count_0, sizeof(dev_cmd_count_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_mac_count) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_src_mac_count_0, sizeof(dev_cmd_src_mac_count_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_src_mac_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_mac_count) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst_mac_count_0, sizeof(dev_cmd_dst_mac_count_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_count_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_burst) {
+	ssize_t len;
+
+	/* burst off */
+	len = write(self->dev_fd, dev_cmd_burst_0, sizeof(dev_cmd_burst_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_burst_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_node) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_node_0, sizeof(dev_cmd_node_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_node_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_xmit_mode) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_xmit_mode_0, sizeof(dev_cmd_xmit_mode_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_0));
+
+	len = write(self->dev_fd, dev_cmd_xmit_mode_1, sizeof(dev_cmd_xmit_mode_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_1));
+
+	len = write(self->dev_fd, dev_cmd_xmit_mode_2, sizeof(dev_cmd_xmit_mode_2));
+	EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_2));
+
+	len = write(self->dev_fd, dev_cmd_xmit_mode_3, sizeof(dev_cmd_xmit_mode_3));
+	EXPECT_EQ(len, sizeof(dev_cmd_xmit_mode_3));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flag) {
+	ssize_t len;
+
+	/* flag UDPCSUM on */
+	len = write(self->dev_fd, dev_cmd_flag_0, sizeof(dev_cmd_flag_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_flag_0));
+
+	/* flag UDPCSUM off */
+	len = write(self->dev_fd, dev_cmd_flag_1, sizeof(dev_cmd_flag_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_flag_1));
+
+	/* flag invalid */
+	len = write(self->dev_fd, dev_cmd_flag_2, sizeof(dev_cmd_flag_2));
+	EXPECT_EQ(len, sizeof(dev_cmd_flag_2));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst_min_0, sizeof(dev_cmd_dst_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst_0, sizeof(dev_cmd_dst_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst_max_0, sizeof(dev_cmd_dst_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst6_0, sizeof(dev_cmd_dst6_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst6_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst6_min_0, sizeof(dev_cmd_dst6_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst6_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst6_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst6_max_0, sizeof(dev_cmd_dst6_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst6_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src6) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_src6_0, sizeof(dev_cmd_src6_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_src6_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_src_min_0, sizeof(dev_cmd_src_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_src_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_src_max_0, sizeof(dev_cmd_src_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_src_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_dst_mac) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_dst_mac_0, sizeof(dev_cmd_dst_mac_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_dst_mac_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_src_mac) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_src_mac_0, sizeof(dev_cmd_src_mac_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_src_mac_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_clear_counters) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_clear_counters_0, sizeof(dev_cmd_clear_counters_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_clear_counters_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flows) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_flows_0, sizeof(dev_cmd_flows_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_flows_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_spi) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_spi_0, sizeof(dev_cmd_spi_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_spi_0)) TH_LOG("CONFIG_XFRM not enabled?");
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_flowlen) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_flowlen_0, sizeof(dev_cmd_flowlen_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_flowlen_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_queue_map_min) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_queue_map_min_0, sizeof(dev_cmd_queue_map_min_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_queue_map_min_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_queue_map_max) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_queue_map_max_0, sizeof(dev_cmd_queue_map_max_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_queue_map_max_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_mpls) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_mpls_0, sizeof(dev_cmd_mpls_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_mpls_0));
+
+	len = write(self->dev_fd, dev_cmd_mpls_1, sizeof(dev_cmd_mpls_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_mpls_1));
+
+	len = write(self->dev_fd, dev_cmd_mpls_2, sizeof(dev_cmd_mpls_2));
+	EXPECT_EQ(len, sizeof(dev_cmd_mpls_2));
+
+	len = write(self->dev_fd, dev_cmd_mpls_3, sizeof(dev_cmd_mpls_3));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, E2BIG);
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_vlan_id) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_vlan_id_0, sizeof(dev_cmd_vlan_id_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_0));
+
+	len = write(self->dev_fd, dev_cmd_vlan_p_0, sizeof(dev_cmd_vlan_p_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_vlan_p_0));
+
+	len = write(self->dev_fd, dev_cmd_vlan_cfi_0, sizeof(dev_cmd_vlan_cfi_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_vlan_cfi_0));
+
+	len = write(self->dev_fd, dev_cmd_vlan_id_1, sizeof(dev_cmd_vlan_id_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_vlan_id_1));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_svlan_id) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_svlan_id_0, sizeof(dev_cmd_svlan_id_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_0));
+
+	len = write(self->dev_fd, dev_cmd_svlan_p_0, sizeof(dev_cmd_svlan_p_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_svlan_p_0));
+
+	len = write(self->dev_fd, dev_cmd_svlan_cfi_0, sizeof(dev_cmd_svlan_cfi_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_svlan_cfi_0));
+
+	len = write(self->dev_fd, dev_cmd_svlan_id_1, sizeof(dev_cmd_svlan_id_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_svlan_id_1));
+}
+
+
+TEST_F(proc_net_pktgen, dev_cmd_tos) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_tos_0, sizeof(dev_cmd_tos_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_tos_0));
+
+	len = write(self->dev_fd, dev_cmd_tos_1, sizeof(dev_cmd_tos_1));
+	EXPECT_EQ(len, sizeof(dev_cmd_tos_1));
+
+	len = write(self->dev_fd, dev_cmd_tos_2, sizeof(dev_cmd_tos_2));
+	EXPECT_EQ(len, sizeof(dev_cmd_tos_2));
+}
+
+
+TEST_F(proc_net_pktgen, dev_cmd_traffic_class) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_traffic_class_0, sizeof(dev_cmd_traffic_class_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_traffic_class_0));
+}
+
+TEST_F(proc_net_pktgen, dev_cmd_skb_priority) {
+	ssize_t len;
+
+	len = write(self->dev_fd, dev_cmd_skb_priority_0, sizeof(dev_cmd_skb_priority_0));
+	EXPECT_EQ(len, sizeof(dev_cmd_skb_priority_0));
+}
+
+TEST_HARNESS_MAIN

From 1a82d19ca2d6835904ee71e2d40fd331098f94a0 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Thu, 27 Feb 2025 18:41:29 +0200
Subject: [PATCH 1475/2753] be2net: fix sleeping while atomic bugs in
 be_ndo_bridge_getlink

Partially revert commit b71724147e73 ("be2net: replace polling with
sleeping in the FW completion path") w.r.t mcc mutex it introduces and the
use of usleep_range. The be2net be_ndo_bridge_getlink() callback is
called with rcu_read_lock, so this code has been broken for a long time.
Both the mutex_lock and the usleep_range can cause the issue Ian Kumlien
reported[1]. The call path is:
be_ndo_bridge_getlink -> be_cmd_get_hsw_config -> be_mcc_notify_wait ->
be_mcc_wait_compl -> usleep_range()

[1] https://lore.kernel.org/netdev/CAA85sZveppNgEVa_FD+qhOMtG_AavK9_mFiU+jWrMtXmwqefGA@mail.gmail.com/

Tested-by: Ian Kumlien <ian.kumlien@gmail.com>
Fixes: b71724147e73 ("be2net: replace polling with sleeping in the FW completion path")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Link: https://patch.msgid.link/20250227164129.1201164-1-razor@blackwall.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/emulex/benet/be.h      |   2 +-
 drivers/net/ethernet/emulex/benet/be_cmds.c | 197 ++++++++++----------
 drivers/net/ethernet/emulex/benet/be_main.c |   2 +-
 3 files changed, 100 insertions(+), 101 deletions(-)

diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h
index e48b861e4ce15..270ff9aab3352 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -562,7 +562,7 @@ struct be_adapter {
 	struct be_dma_mem mbox_mem_alloced;
 
 	struct be_mcc_obj mcc_obj;
-	struct mutex mcc_lock;	/* For serializing mcc cmds to BE card */
+	spinlock_t mcc_lock;	/* For serializing mcc cmds to BE card */
 	spinlock_t mcc_cq_lock;
 
 	u16 cfg_num_rx_irqs;		/* configured via set-channels */
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 61adcebeef010..51b8377edd1d0 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -575,7 +575,7 @@ int be_process_mcc(struct be_adapter *adapter)
 /* Wait till no more pending mcc requests are present */
 static int be_mcc_wait_compl(struct be_adapter *adapter)
 {
-#define mcc_timeout		12000 /* 12s timeout */
+#define mcc_timeout		120000 /* 12s timeout */
 	int i, status = 0;
 	struct be_mcc_obj *mcc_obj = &adapter->mcc_obj;
 
@@ -589,7 +589,7 @@ static int be_mcc_wait_compl(struct be_adapter *adapter)
 
 		if (atomic_read(&mcc_obj->q.used) == 0)
 			break;
-		usleep_range(500, 1000);
+		udelay(100);
 	}
 	if (i == mcc_timeout) {
 		dev_err(&adapter->pdev->dev, "FW not responding\n");
@@ -866,7 +866,7 @@ static bool use_mcc(struct be_adapter *adapter)
 static int be_cmd_lock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter)) {
-		mutex_lock(&adapter->mcc_lock);
+		spin_lock_bh(&adapter->mcc_lock);
 		return 0;
 	} else {
 		return mutex_lock_interruptible(&adapter->mbox_lock);
@@ -877,7 +877,7 @@ static int be_cmd_lock(struct be_adapter *adapter)
 static void be_cmd_unlock(struct be_adapter *adapter)
 {
 	if (use_mcc(adapter))
-		return mutex_unlock(&adapter->mcc_lock);
+		return spin_unlock_bh(&adapter->mcc_lock);
 	else
 		return mutex_unlock(&adapter->mbox_lock);
 }
@@ -1047,7 +1047,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	struct be_cmd_req_mac_query *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1076,7 +1076,7 @@ int be_cmd_mac_addr_query(struct be_adapter *adapter, u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1088,7 +1088,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	struct be_cmd_req_pmac_add *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1113,7 +1113,7 @@ int be_cmd_pmac_add(struct be_adapter *adapter, const u8 *mac_addr,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_UNAUTHORIZED_REQUEST)
 		status = -EPERM;
@@ -1131,7 +1131,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	if (pmac_id == -1)
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1151,7 +1151,7 @@ int be_cmd_pmac_del(struct be_adapter *adapter, u32 if_id, int pmac_id, u32 dom)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1414,7 +1414,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	struct be_dma_mem *q_mem = &rxq->dma_mem;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1444,7 +1444,7 @@ int be_cmd_rxq_create(struct be_adapter *adapter,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1508,7 +1508,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	struct be_cmd_req_q_destroy *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1525,7 +1525,7 @@ int be_cmd_rxq_destroy(struct be_adapter *adapter, struct be_queue_info *q)
 	q->created = false;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1593,7 +1593,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	struct be_cmd_req_hdr *hdr;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1621,7 +1621,7 @@ int be_cmd_get_stats(struct be_adapter *adapter, struct be_dma_mem *nonemb_cmd)
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1637,7 +1637,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 			    CMD_SUBSYSTEM_ETH))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1660,7 +1660,7 @@ int lancer_cmd_get_pport_stats(struct be_adapter *adapter,
 	adapter->stats_cmd_sent = true;
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1697,7 +1697,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	struct be_cmd_req_link_status *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	if (link_status)
 		*link_status = LINK_DOWN;
@@ -1736,7 +1736,7 @@ int be_cmd_link_status_query(struct be_adapter *adapter, u16 *link_speed,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1747,7 +1747,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 	struct be_cmd_req_get_cntl_addnl_attribs *req;
 	int status = 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1762,7 +1762,7 @@ int be_cmd_get_die_temperature(struct be_adapter *adapter)
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1811,7 +1811,7 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 	if (!get_fat_cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	while (total_size) {
 		buf_size = min(total_size, (u32)60 * 1024);
@@ -1849,9 +1849,9 @@ int be_cmd_get_fat_dump(struct be_adapter *adapter, u32 buf_len, void *buf)
 		log_offset += buf_size;
 	}
 err:
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_fat_cmd.size,
 			  get_fat_cmd.va, get_fat_cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1862,7 +1862,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 	struct be_cmd_req_get_fw_version *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1885,7 +1885,7 @@ int be_cmd_get_fw_ver(struct be_adapter *adapter)
 			sizeof(adapter->fw_on_flash));
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1899,7 +1899,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 	struct be_cmd_req_modify_eq_delay *req;
 	int status = 0, i;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1922,7 +1922,7 @@ static int __be_cmd_modify_eqd(struct be_adapter *adapter,
 
 	status = be_mcc_notify(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1949,7 +1949,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 	struct be_cmd_req_vlan_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -1971,7 +1971,7 @@ int be_cmd_vlan_config(struct be_adapter *adapter, u32 if_id, u16 *vtag_array,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -1982,7 +1982,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 	struct be_cmd_req_rx_filter *req = mem->va;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2015,7 +2015,7 @@ static int __be_cmd_rx_filter(struct be_adapter *adapter, u32 flags, u32 value)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2046,7 +2046,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2066,7 +2066,7 @@ int be_cmd_set_flow_control(struct be_adapter *adapter, u32 tx_fc, u32 rx_fc)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (base_status(status) == MCC_STATUS_FEATURE_NOT_SUPPORTED)
 		return  -EOPNOTSUPP;
@@ -2085,7 +2085,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2108,7 +2108,7 @@ int be_cmd_get_flow_control(struct be_adapter *adapter, u32 *tx_fc, u32 *rx_fc)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2189,7 +2189,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 	if (!(be_if_cap_flags(adapter) & BE_IF_FLAGS_RSS))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2214,7 +2214,7 @@ int be_cmd_rss_config(struct be_adapter *adapter, u8 *rsstable,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2226,7 +2226,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	struct be_cmd_req_enable_disable_beacon *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2247,7 +2247,7 @@ int be_cmd_set_beacon_state(struct be_adapter *adapter, u8 port_num,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2258,7 +2258,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	struct be_cmd_req_get_beacon_state *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2282,7 +2282,7 @@ int be_cmd_get_beacon_state(struct be_adapter *adapter, u8 port_num, u32 *state)
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2306,7 +2306,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2328,7 +2328,7 @@ int be_cmd_read_port_transceiver_data(struct be_adapter *adapter,
 		memcpy(data, resp->page_data + off, len);
 	}
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 	return status;
 }
@@ -2345,7 +2345,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	void *ctxt = NULL;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2387,7 +2387,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(60000)))
@@ -2406,7 +2406,7 @@ static int lancer_cmd_write_object(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2460,7 +2460,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2478,7 +2478,7 @@ static int lancer_cmd_delete_object(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2491,7 +2491,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	struct lancer_cmd_resp_read_object *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2525,7 +2525,7 @@ int lancer_cmd_read_object(struct be_adapter *adapter, struct be_dma_mem *cmd,
 	}
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2537,7 +2537,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	struct be_cmd_write_flashrom *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 	adapter->flash_status = 0;
 
 	wrb = wrb_from_mccq(adapter);
@@ -2562,7 +2562,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(40000)))
@@ -2573,7 +2573,7 @@ static int be_cmd_write_flashrom(struct be_adapter *adapter,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -2584,7 +2584,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -2611,7 +2611,7 @@ static int be_cmd_get_flash_crc(struct be_adapter *adapter, u8 *flashed_crc,
 		memcpy(flashed_crc, req->crc, 4);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3217,7 +3217,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	struct be_cmd_req_acpi_wol_magic_config *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3234,7 +3234,7 @@ int be_cmd_enable_magic_wol(struct be_adapter *adapter, u8 *mac,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3249,7 +3249,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3272,7 +3272,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	if (status)
 		goto err_unlock;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	if (!wait_for_completion_timeout(&adapter->et_cmd_compl,
 					 msecs_to_jiffies(SET_LB_MODE_TIMEOUT)))
@@ -3281,7 +3281,7 @@ int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num,
 	return status;
 
 err_unlock:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3298,7 +3298,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3324,7 +3324,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 	if (status)
 		goto err;
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 
 	wait_for_completion(&adapter->et_cmd_compl);
 	resp = embedded_payload(wrb);
@@ -3332,7 +3332,7 @@ int be_cmd_loopback_test(struct be_adapter *adapter, u32 port_num,
 
 	return status;
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3348,7 +3348,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 			    CMD_SUBSYSTEM_LOWLEVEL))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3382,7 +3382,7 @@ int be_cmd_ddr_dma_test(struct be_adapter *adapter, u64 pattern,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3393,7 +3393,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	struct be_cmd_req_seeprom_read *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3409,7 +3409,7 @@ int be_cmd_get_seeprom_data(struct be_adapter *adapter,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3424,7 +3424,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3469,7 +3469,7 @@ int be_cmd_get_phy_info(struct be_adapter *adapter)
 	}
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3479,7 +3479,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	struct be_cmd_req_set_qos *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3499,7 +3499,7 @@ static int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain)
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3611,7 +3611,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	struct be_cmd_req_get_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3643,7 +3643,7 @@ int be_cmd_get_fn_privileges(struct be_adapter *adapter, u32 *privilege,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3655,7 +3655,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 	struct be_cmd_req_set_fn_privileges *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3675,7 +3675,7 @@ int be_cmd_set_fn_privileges(struct be_adapter *adapter, u32 privileges,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3707,7 +3707,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 		return -ENOMEM;
 	}
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3771,7 +3771,7 @@ int be_cmd_get_mac_from_list(struct be_adapter *adapter, u8 *mac,
 	}
 
 out:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	dma_free_coherent(&adapter->pdev->dev, get_mac_list_cmd.size,
 			  get_mac_list_cmd.va, get_mac_list_cmd.dma);
 	return status;
@@ -3831,7 +3831,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 	if (!cmd.va)
 		return -ENOMEM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3853,7 +3853,7 @@ int be_cmd_set_mac_list(struct be_adapter *adapter, u8 *mac_array,
 
 err:
 	dma_free_coherent(&adapter->pdev->dev, cmd.size, cmd.va, cmd.dma);
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3889,7 +3889,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 			    CMD_SUBSYSTEM_COMMON))
 		return -EPERM;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3930,7 +3930,7 @@ int be_cmd_set_hsw_config(struct be_adapter *adapter, u16 pvid,
 	status = be_mcc_notify_wait(adapter);
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -3944,7 +3944,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	int status;
 	u16 vid;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -3991,7 +3991,7 @@ int be_cmd_get_hsw_config(struct be_adapter *adapter, u16 *pvid,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4190,7 +4190,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 	struct be_cmd_req_set_ext_fat_caps *req;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4206,7 +4206,7 @@ int be_cmd_set_ext_fat_capabilites(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4684,7 +4684,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 	if (iface == 0xFFFFFFFF)
 		return -1;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4701,7 +4701,7 @@ int be_cmd_manage_iface(struct be_adapter *adapter, u32 iface, u8 op)
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4735,7 +4735,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	struct be_cmd_resp_get_iface_list *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4756,7 +4756,7 @@ int be_cmd_get_if_id(struct be_adapter *adapter, struct be_vf_cfg *vf_cfg,
 	}
 
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4850,7 +4850,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	if (BEx_chip(adapter))
 		return 0;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4868,7 +4868,7 @@ int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain)
 	req->enable = 1;
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -4941,7 +4941,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 	u32 link_config = 0;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -4969,7 +4969,7 @@ __be_cmd_set_logical_link_config(struct be_adapter *adapter,
 
 	status = be_mcc_notify_wait(adapter);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5000,8 +5000,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 	struct be_mcc_wrb *wrb;
 	int status;
 
-	if (mutex_lock_interruptible(&adapter->mcc_lock))
-		return -1;
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5039,7 +5038,7 @@ int be_cmd_set_features(struct be_adapter *adapter)
 		dev_info(&adapter->pdev->dev,
 			 "Adapter does not support HW error recovery\n");
 
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 
@@ -5053,7 +5052,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	struct be_cmd_resp_hdr *resp;
 	int status;
 
-	mutex_lock(&adapter->mcc_lock);
+	spin_lock_bh(&adapter->mcc_lock);
 
 	wrb = wrb_from_mccq(adapter);
 	if (!wrb) {
@@ -5076,7 +5075,7 @@ int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
 	memcpy(wrb_payload, resp, sizeof(*resp) + resp->response_length);
 	be_dws_le_to_cpu(wrb_payload, sizeof(*resp) + resp->response_length);
 err:
-	mutex_unlock(&adapter->mcc_lock);
+	spin_unlock_bh(&adapter->mcc_lock);
 	return status;
 }
 EXPORT_SYMBOL(be_roce_mcc_cmd);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index 875fe379eea21..3d2e215921191 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5667,8 +5667,8 @@ static int be_drv_init(struct be_adapter *adapter)
 	}
 
 	mutex_init(&adapter->mbox_lock);
-	mutex_init(&adapter->mcc_lock);
 	mutex_init(&adapter->rx_filter_lock);
+	spin_lock_init(&adapter->mcc_lock);
 	spin_lock_init(&adapter->mcc_cq_lock);
 	init_completion(&adapter->et_cmd_compl);
 

From c34424eb3be4c01db831428c0d7d483701ae820f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 27 Feb 2025 16:45:34 -0800
Subject: [PATCH 1476/2753] net: dsa: rtl8366rb: don't prompt users for LED
 control

Make NET_DSA_REALTEK_RTL8366RB_LEDS a hidden symbol.
It seems very unlikely user would want to intentionally
disable it.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20250228004534.3428681-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/realtek/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/dsa/realtek/Kconfig b/drivers/net/dsa/realtek/Kconfig
index 10687722d14c0..d6eb6713e5f6b 100644
--- a/drivers/net/dsa/realtek/Kconfig
+++ b/drivers/net/dsa/realtek/Kconfig
@@ -44,7 +44,7 @@ config NET_DSA_REALTEK_RTL8366RB
 	  Select to enable support for Realtek RTL8366RB.
 
 config NET_DSA_REALTEK_RTL8366RB_LEDS
-	bool "Support RTL8366RB LED control"
+	bool
 	depends on (LEDS_CLASS=y || LEDS_CLASS=NET_DSA_REALTEK_RTL8366RB)
 	depends on NET_DSA_REALTEK_RTL8366RB
 	default NET_DSA_REALTEK_RTL8366RB

From ffcef3df680c437ca33ff434be18ec24d72907c2 Mon Sep 17 00:00:00 2001
From: Dragan Simic <dsimic@manjaro.org>
Date: Sun, 2 Mar 2025 19:48:04 +0100
Subject: [PATCH 1477/2753] arm64: dts: rockchip: Add missing PCIe supplies to
 RockPro64 board dtsi

Add missing "vpcie0v9-supply" and "vpcie1v8-supply" properties to the "pcie0"
node in the Pine64 RockPro64 board dtsi file.  This eliminates the following
warnings from the kernel log:

  rockchip-pcie f8000000.pcie: supply vpcie1v8 not found, using dummy regulator
  rockchip-pcie f8000000.pcie: supply vpcie0v9 not found, using dummy regulator

These additions improve the accuracy of hardware description of the RockPro64
and, in theory, they should result in no functional changes to the way board
works after the changes, because the "vcca_0v9" and "vcca_1v8" regulators are
always enabled. [1][2]  However, extended reliability testing, performed by
Chris, [3] has proven that the age-old issues with some PCI Express cards,
when used with a Pine64 RockPro64, are also resolved.

Those issues were already mentioned in the commit 43853e843aa6 (arm64: dts:
rockchip: Remove unsupported node from the Pinebook Pro dts, 2024-04-01),
together with a brief description of the out-of-tree enumeration delay patch
that reportedly resolves those issues.  In a nutshell, booting a RockPro64
with some PCI Express cards attached to it caused a kernel oops. [4]

Symptomatically enough, to the commit author's best knowledge, only the Pine64
RockPro64, out of all RK3399-based boards and devices supported upstream, has
been reported to suffer from those PCI Express issues, and only the RockPro64
had some of the PCI Express supplies missing in its DT.  Thus, perhaps some
weird timing issues exist that caused the "vcca_1v8" always-on regulator,
which is part of the RK808 PMIC, to actually not be enabled before the PCI
Express is initialized and enumerated on the RockPro64, causing oopses with
some PCIe cards, and the aforementioned enumeration delay patch [4] probably
acted as just a workaround for the underlying timing issue.

Admittedly, the Pine64 RockPro64 is a bit specific board by having a standard
PCI Express slot, allowing use of various standard cards, but pretty much
standard PCI Express cards have been attached to other RK3399 boards as well,
and the commit author is unaware ot such issues reported for them.

It's quite hard to be sure that the PCI Express issues are fully resolved by
these additions to the DT, without some really extensive and time-consuming
testing.  However, these additions to the DT can result in good things and
improvements anyway, making them perfectly safe from the standpoint of being
unable to do any harm or cause some unforeseen regressions.

These changes apply to the both supported hardware revisions of the Pine64
RockPro64, i.e. to the production-run revisions 2.0 and 2.1. [1][2]

[1] https://files.pine64.org/doc/rockpro64/rockpro64_v21-SCH.pdf
[2] https://files.pine64.org/doc/rockpro64/rockpro64_v20-SCH.pdf
[3] https://z9.de/hedgedoc/s/nF4d5G7rg#reboot-tests-for-PCIe-improvements
[4] https://lore.kernel.org/lkml/20230509153912.515218-1-vincenzopalazzodev@gmail.com/T/#u

Fixes: bba821f5479e ("arm64: dts: rockchip: add PCIe nodes on rk3399-rockpro64")
Cc: stable@vger.kernel.org
Cc: Vincenzo Palazzo <vincenzopalazzodev@gmail.com>
Cc: Peter Geis <pgwipeout@gmail.com>
Cc: Bjorn Helgaas <helgaas@kernel.org>
Reported-by: Diederik de Haas <didi.debian@cknow.org>
Tested-by: Chris Vogel <chris@z9.de>
Signed-off-by: Dragan Simic <dsimic@manjaro.org>
Tested-by: Diederik de Haas <didi.debian@cknow.org>
Link: https://lore.kernel.org/r/b39cfd7490d8194f053bf3971f13a43472d1769e.1740941097.git.dsimic@manjaro.org
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
index 47dc198706c85..51c6aa26d8285 100644
--- a/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
+++ b/arch/arm64/boot/dts/rockchip/rk3399-rockpro64.dtsi
@@ -673,6 +673,8 @@
 	num-lanes = <4>;
 	pinctrl-names = "default";
 	pinctrl-0 = <&pcie_perst>;
+	vpcie0v9-supply = <&vcca_0v9>;
+	vpcie1v8-supply = <&vcca_1v8>;
 	vpcie12v-supply = <&vcc12v_dcin>;
 	vpcie3v3-supply = <&vcc3v3_pcie>;
 	status = "okay";

From 0c493da86374dffff7505e67289ad75b21f5b301 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 28 Feb 2025 11:20:56 +0100
Subject: [PATCH 1478/2753] net: rename netns_local to netns_immutable

The name 'netns_local' is confusing. A following commit will export it via
netlink, so let's use a more explicit name.

Reported-by: Eric Dumazet <edumazet@google.com>
Suggested-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/net_cachelines/net_device.rst |  2 +-
 Documentation/networking/switchdev.rst                 |  2 +-
 drivers/net/amt.c                                      |  2 +-
 drivers/net/bonding/bond_main.c                        |  2 +-
 drivers/net/ethernet/adi/adin1110.c                    |  2 +-
 drivers/net/ethernet/marvell/prestera/prestera_main.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c      |  4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/en_rep.c       |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c         |  2 +-
 drivers/net/ethernet/rocker/rocker_main.c              |  2 +-
 drivers/net/ethernet/ti/cpsw_new.c                     |  2 +-
 drivers/net/loopback.c                                 |  2 +-
 drivers/net/net_failover.c                             |  2 +-
 drivers/net/team/team_core.c                           |  2 +-
 drivers/net/vrf.c                                      |  2 +-
 include/linux/netdevice.h                              |  4 ++--
 net/batman-adv/soft-interface.c                        |  2 +-
 net/bridge/br_device.c                                 |  2 +-
 net/core/dev.c                                         |  4 ++--
 net/hsr/hsr_device.c                                   |  2 +-
 net/ieee802154/6lowpan/core.c                          |  2 +-
 net/ieee802154/core.c                                  | 10 +++++-----
 net/ipv4/ip_tunnel.c                                   |  2 +-
 net/ipv4/ipmr.c                                        |  2 +-
 net/ipv6/ip6_gre.c                                     |  2 +-
 net/ipv6/ip6_tunnel.c                                  |  2 +-
 net/ipv6/ip6mr.c                                       |  2 +-
 net/ipv6/sit.c                                         |  2 +-
 net/openvswitch/vport-internal_dev.c                   |  2 +-
 net/wireless/core.c                                    | 10 +++++-----
 tools/testing/selftests/net/forwarding/README          |  2 +-
 31 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 15e31ece675fc..6327e689e8a84 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -167,7 +167,7 @@ unsigned:1                          wol_enabled
 unsigned:1                          threaded                                                            napi_poll(napi_enable,dev_set_threaded)
 unsigned_long:1                     see_all_hwtstamp_requests
 unsigned_long:1                     change_proto_down
-unsigned_long:1                     netns_local
+unsigned_long:1                     netns_immutable
 unsigned_long:1                     fcoe_mtu
 struct list_head                    net_notifier_list
 struct macsec_ops*                  macsec_ops
diff --git a/Documentation/networking/switchdev.rst b/Documentation/networking/switchdev.rst
index f355f0166f1b4..2966b7122f050 100644
--- a/Documentation/networking/switchdev.rst
+++ b/Documentation/networking/switchdev.rst
@@ -137,7 +137,7 @@ would be sub-port 0 on port 1 on switch 1.
 Port Features
 ^^^^^^^^^^^^^
 
-dev->netns_local
+dev->netns_immutable
 
 If the switchdev driver (and device) only supports offloading of the default
 network namespace (netns), the driver should set this private flag to prevent
diff --git a/drivers/net/amt.c b/drivers/net/amt.c
index 53899b70fae1c..734a0b3242a9b 100644
--- a/drivers/net/amt.c
+++ b/drivers/net/amt.c
@@ -3099,7 +3099,7 @@ static void amt_link_setup(struct net_device *dev)
 	dev->addr_len		= 0;
 	dev->priv_flags		|= IFF_NO_QUEUE;
 	dev->lltx		= true;
-	dev->netns_local	= true;
+	dev->netns_immutable	= true;
 	dev->features		|= NETIF_F_GSO_SOFTWARE;
 	dev->hw_features	|= NETIF_F_SG | NETIF_F_HW_CSUM;
 	dev->hw_features	|= NETIF_F_FRAGLIST | NETIF_F_RXCSUM;
diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 7d98fee5a27f9..fe7072336e8fd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -6025,7 +6025,7 @@ void bond_setup(struct net_device *bond_dev)
 	bond_dev->lltx = true;
 
 	/* Don't allow bond devices to change network namespaces. */
-	bond_dev->netns_local = true;
+	bond_dev->netns_immutable = true;
 
 	/* By default, we declare the bond to be fully
 	 * VLAN hardware accelerated capable. Special
diff --git a/drivers/net/ethernet/adi/adin1110.c b/drivers/net/ethernet/adi/adin1110.c
index 68fad5575fd4f..30f9d271e5953 100644
--- a/drivers/net/ethernet/adi/adin1110.c
+++ b/drivers/net/ethernet/adi/adin1110.c
@@ -1599,7 +1599,7 @@ static int adin1110_probe_netdevs(struct adin1110_priv *priv)
 		netdev->netdev_ops = &adin1110_netdev_ops;
 		netdev->ethtool_ops = &adin1110_ethtool_ops;
 		netdev->priv_flags |= IFF_UNICAST_FLT;
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 
 		port_priv->phydev = get_phy_device(priv->mii_bus, i + 1, false);
 		if (IS_ERR(port_priv->phydev)) {
diff --git a/drivers/net/ethernet/marvell/prestera/prestera_main.c b/drivers/net/ethernet/marvell/prestera/prestera_main.c
index 8cdecf61253cc..71ffb55d1fc48 100644
--- a/drivers/net/ethernet/marvell/prestera/prestera_main.c
+++ b/drivers/net/ethernet/marvell/prestera/prestera_main.c
@@ -634,7 +634,7 @@ static int prestera_port_create(struct prestera_switch *sw, u32 id)
 		goto err_dl_port_register;
 
 	dev->features |= NETIF_F_HW_TC;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 	dev->netdev_ops = &prestera_netdev_ops;
 	dev->ethtool_ops = &prestera_ethtool_ops;
 	SET_NETDEV_DEV(dev, sw->dev->dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 7e3aad0151117..6eb8642d2e2b1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -4423,9 +4423,9 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
 
 	if (mlx5e_is_uplink_rep(priv)) {
 		features = mlx5e_fix_uplink_rep_features(netdev, features);
-		netdev->netns_local = true;
+		netdev->netns_immutable = true;
 	} else {
-		netdev->netns_local = false;
+		netdev->netns_immutable = false;
 	}
 
 	mutex_unlock(&priv->state_lock);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 07f38f472a279..2abab241f03bd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@ -905,7 +905,7 @@ static void mlx5e_build_rep_netdev(struct net_device *netdev,
 
 	netdev->features |= netdev->hw_features;
 
-	netdev->netns_local = true;
+	netdev->netns_immutable = true;
 }
 
 static int mlx5e_init_rep(struct mlx5_core_dev *mdev,
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 1f8362788c756..c7e6a32582448 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -1579,7 +1579,7 @@ static int mlxsw_sp_port_create(struct mlxsw_sp *mlxsw_sp, u16 local_port,
 			    NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
 	dev->lltx = true;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->min_mtu = ETH_MIN_MTU;
 	dev->max_mtu = MLXSW_PORT_MAX_MTU - MLXSW_PORT_ETH_FRAME_HDR;
diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c
index fe0bf1d3217af..36af94a2e062a 100644
--- a/drivers/net/ethernet/rocker/rocker_main.c
+++ b/drivers/net/ethernet/rocker/rocker_main.c
@@ -2576,7 +2576,7 @@ static int rocker_probe_port(struct rocker *rocker, unsigned int port_number)
 	rocker_carrier_init(rocker_port);
 
 	dev->features |= NETIF_F_SG;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	/* MTU range: 68 - 9000 */
 	dev->min_mtu = ROCKER_PORT_MIN_MTU;
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index cec0a90659d94..b01289d4726da 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1409,7 +1409,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 
 		ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER |
 				  NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC;
-		ndev->netns_local = true;
+		ndev->netns_immutable = true;
 
 		ndev->xdp_features = NETDEV_XDP_ACT_BASIC |
 				     NETDEV_XDP_ACT_REDIRECT |
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index f1d68153987e1..201fddcd3b1e8 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -172,7 +172,7 @@ static void gen_lo_setup(struct net_device *dev,
 	dev->flags		= IFF_LOOPBACK;
 	dev->priv_flags		|= IFF_LIVE_ADDR_CHANGE | IFF_NO_QUEUE;
 	dev->lltx		= true;
-	dev->netns_local	= true;
+	dev->netns_immutable	= true;
 	netif_keep_dst(dev);
 	dev->hw_features	= NETIF_F_GSO_SOFTWARE;
 	dev->features		= NETIF_F_SG | NETIF_F_FRAGLIST
diff --git a/drivers/net/net_failover.c b/drivers/net/net_failover.c
index 54c8b9d5b5fcf..5b50d9186f121 100644
--- a/drivers/net/net_failover.c
+++ b/drivers/net/net_failover.c
@@ -734,7 +734,7 @@ struct failover *net_failover_create(struct net_device *standby_dev)
 	failover_dev->lltx = true;
 
 	/* Don't allow failover devices to change network namespaces. */
-	failover_dev->netns_local = true;
+	failover_dev->netns_immutable = true;
 
 	failover_dev->hw_features = FAILOVER_VLAN_FEATURES |
 				    NETIF_F_HW_VLAN_CTAG_TX |
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index 78edb8186b6d0..fb917560d0a24 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -2203,7 +2203,7 @@ static void team_setup(struct net_device *dev)
 	dev->lltx = true;
 
 	/* Don't allow team devices to change network namespaces. */
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->features |= NETIF_F_GRO;
 
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 849c3ced2690e..36cf6191335ea 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -1617,7 +1617,7 @@ static void vrf_setup(struct net_device *dev)
 	dev->lltx = true;
 
 	/* don't allow vrf devices to change network namespaces. */
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	/* does not make sense for a VLAN to be added to a vrf device */
 	dev->features   |= NETIF_F_VLAN_CHALLENGED;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 26a0c4e4d963d..b8728d67ea91d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2021,7 +2021,7 @@ enum netdev_reg_state {
  *			regardless of source, even if those aren't
  *			HWTSTAMP_SOURCE_NETDEV
  *	@change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
- *	@netns_local: interface can't change network namespaces
+ *	@netns_immutable: interface can't change network namespaces
  *	@fcoe_mtu:	device supports maximum FCoE MTU, 2158 bytes
  *
  *	@net_notifier_list:	List of per-net netdev notifier block
@@ -2429,7 +2429,7 @@ struct net_device {
 	/* priv_flags_slow, ungrouped to save space */
 	unsigned long		see_all_hwtstamp_requests:1;
 	unsigned long		change_proto_down:1;
-	unsigned long		netns_local:1;
+	unsigned long		netns_immutable:1;
 	unsigned long		fcoe_mtu:1;
 
 	struct list_head	net_notifier_list;
diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c
index d893c80132616..e190fa954f228 100644
--- a/net/batman-adv/soft-interface.c
+++ b/net/batman-adv/soft-interface.c
@@ -1037,7 +1037,7 @@ static void batadv_softif_init_early(struct net_device *dev)
 	dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER;
 	dev->priv_flags |= IFF_NO_QUEUE;
 	dev->lltx = true;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	/* can't call min_mtu, because the needed variables
 	 * have not been initialized yet
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 0ab4613aa07ad..9d8c72ed01aba 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -488,7 +488,7 @@ void br_dev_setup(struct net_device *dev)
 	SET_NETDEV_DEVTYPE(dev, &br_type);
 	dev->priv_flags = IFF_EBRIDGE | IFF_NO_QUEUE;
 	dev->lltx = true;
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
 			NETIF_F_HW_VLAN_STAG_TX;
diff --git a/net/core/dev.c b/net/core/dev.c
index d6d68a2d2355a..357ae88064a5f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12151,7 +12151,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 
 	/* Don't allow namespace local devices to be moved. */
 	err = -EINVAL;
-	if (dev->netns_local)
+	if (dev->netns_immutable)
 		goto out;
 
 	/* Ensure the device has been registered */
@@ -12533,7 +12533,7 @@ static void __net_exit default_device_exit_net(struct net *net)
 		char fb_name[IFNAMSIZ];
 
 		/* Ignore unmoveable devices (i.e. loopback) */
-		if (dev->netns_local)
+		if (dev->netns_immutable)
 			continue;
 
 		/* Leave virtual devices for the generic cleanup */
diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index b6fb18469439a..c6f8614e9ed1f 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -643,7 +643,7 @@ void hsr_dev_setup(struct net_device *dev)
 	/* Not sure about this. Taken from bridge code. netdevice.h says
 	 * it means "Does not change network namespaces".
 	 */
-	dev->netns_local = true;
+	dev->netns_immutable = true;
 
 	dev->needs_free_netdev = true;
 
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index ee318d46817d4..9a9da74b0a4fa 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -116,7 +116,7 @@ static void lowpan_setup(struct net_device *ldev)
 	ldev->netdev_ops	= &lowpan_netdev_ops;
 	ldev->header_ops	= &lowpan_header_ops;
 	ldev->needs_free_netdev	= true;
-	ldev->netns_local	= true;
+	ldev->netns_immutable	= true;
 }
 
 static int lowpan_validate(struct nlattr *tb[], struct nlattr *data[],
diff --git a/net/ieee802154/core.c b/net/ieee802154/core.c
index 88adb04e40722..89b671b12600f 100644
--- a/net/ieee802154/core.c
+++ b/net/ieee802154/core.c
@@ -226,11 +226,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 	list_for_each_entry(wpan_dev, &rdev->wpan_dev_list, list) {
 		if (!wpan_dev->netdev)
 			continue;
-		wpan_dev->netdev->netns_local = false;
+		wpan_dev->netdev->netns_immutable = false;
 		err = dev_change_net_namespace(wpan_dev->netdev, net, "wpan%d");
 		if (err)
 			break;
-		wpan_dev->netdev->netns_local = true;
+		wpan_dev->netdev->netns_immutable = true;
 	}
 
 	if (err) {
@@ -242,11 +242,11 @@ int cfg802154_switch_netns(struct cfg802154_registered_device *rdev,
 						     list) {
 			if (!wpan_dev->netdev)
 				continue;
-			wpan_dev->netdev->netns_local = false;
+			wpan_dev->netdev->netns_immutable = false;
 			err = dev_change_net_namespace(wpan_dev->netdev, net,
 						       "wpan%d");
 			WARN_ON(err);
-			wpan_dev->netdev->netns_local = true;
+			wpan_dev->netdev->netns_immutable = true;
 		}
 
 		return err;
@@ -291,7 +291,7 @@ static int cfg802154_netdev_notifier_call(struct notifier_block *nb,
 	switch (state) {
 		/* TODO NETDEV_DEVTYPE */
 	case NETDEV_REGISTER:
-		dev->netns_local = true;
+		dev->netns_immutable = true;
 		wpan_dev->identifier = ++rdev->wpan_dev_id;
 		list_add_rcu(&wpan_dev->list, &rdev->wpan_dev_list);
 		rdev->devlist_generation++;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 011f2a5aab3b9..4b06dc7e04f2f 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -1162,7 +1162,7 @@ int ip_tunnel_init_net(struct net *net, unsigned int ip_tnl_net_id,
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
 	if (!IS_ERR(itn->fb_tunnel_dev)) {
-		itn->fb_tunnel_dev->netns_local = true;
+		itn->fb_tunnel_dev->netns_immutable = true;
 		itn->fb_tunnel_dev->mtu = ip_tunnel_bind_dev(itn->fb_tunnel_dev);
 		ip_tunnel_add(itn, netdev_priv(itn->fb_tunnel_dev));
 		itn->type = itn->fb_tunnel_dev->type;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 21ae7594a8525..b81c8131e23fc 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -563,7 +563,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->needs_free_netdev	= true;
-	dev->netns_local	= true;
+	dev->netns_immutable	= true;
 }
 
 static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt)
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index d31a4ce3b19ff..c6ebb6a6d3908 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -1620,7 +1620,7 @@ static int __net_init ip6gre_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	ign->fb_tunnel_dev->netns_local = true;
+	ign->fb_tunnel_dev->netns_immutable = true;
 
 	ip6gre_fb_tunnel_init(ign->fb_tunnel_dev);
 	ign->fb_tunnel_dev->rtnl_link_ops = &ip6gre_link_ops;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 89d206731af00..170a6ac30889a 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -2265,7 +2265,7 @@ static int __net_init ip6_tnl_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	ip6n->fb_tnl_dev->netns_local = true;
+	ip6n->fb_tnl_dev->netns_immutable = true;
 
 	err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev);
 	if (err < 0)
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 535e9f72514c0..e8ade93a0f0eb 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -668,7 +668,7 @@ static void reg_vif_setup(struct net_device *dev)
 	dev->flags		= IFF_NOARP;
 	dev->netdev_ops		= &reg_vif_netdev_ops;
 	dev->needs_free_netdev	= true;
-	dev->netns_local	= true;
+	dev->netns_immutable	= true;
 }
 
 static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index f7b59bc957d3b..6f04703fe6386 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1859,7 +1859,7 @@ static int __net_init sit_init_net(struct net *net)
 	/* FB netdevice is special: we have one, and only one per netns.
 	 * Allowing to move it to another netns is clearly unsafe.
 	 */
-	sitn->fb_tunnel_dev->netns_local = true;
+	sitn->fb_tunnel_dev->netns_immutable = true;
 
 	t = netdev_priv(sitn->fb_tunnel_dev);
 	t->net = net;
diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
index 2412d7813d244..125d310871e93 100644
--- a/net/openvswitch/vport-internal_dev.c
+++ b/net/openvswitch/vport-internal_dev.c
@@ -149,7 +149,7 @@ static struct vport *internal_dev_create(const struct vport_parms *parms)
 
 	/* Restrict bridge port to current netns. */
 	if (vport->port_no == OVSP_LOCAL)
-		vport->dev->netns_local = true;
+		vport->dev->netns_immutable = true;
 
 	rtnl_lock();
 	err = register_netdevice(vport->dev);
diff --git a/net/wireless/core.c b/net/wireless/core.c
index 12b780de8779c..15bbc9d06c9e9 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -162,11 +162,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 	list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) {
 		if (!wdev->netdev)
 			continue;
-		wdev->netdev->netns_local = false;
+		wdev->netdev->netns_immutable = false;
 		err = dev_change_net_namespace(wdev->netdev, net, "wlan%d");
 		if (err)
 			break;
-		wdev->netdev->netns_local = true;
+		wdev->netdev->netns_immutable = true;
 	}
 
 	if (err) {
@@ -178,11 +178,11 @@ int cfg80211_switch_netns(struct cfg80211_registered_device *rdev,
 						     list) {
 			if (!wdev->netdev)
 				continue;
-			wdev->netdev->netns_local = false;
+			wdev->netdev->netns_immutable = false;
 			err = dev_change_net_namespace(wdev->netdev, net,
 							"wlan%d");
 			WARN_ON(err);
-			wdev->netdev->netns_local = true;
+			wdev->netdev->netns_immutable = true;
 		}
 
 		return err;
@@ -1513,7 +1513,7 @@ static int cfg80211_netdev_notifier_call(struct notifier_block *nb,
 		SET_NETDEV_DEVTYPE(dev, &wiphy_type);
 		wdev->netdev = dev;
 		/* can only change netns with wiphy */
-		dev->netns_local = true;
+		dev->netns_immutable = true;
 
 		cfg80211_init_wdev(wdev);
 		break;
diff --git a/tools/testing/selftests/net/forwarding/README b/tools/testing/selftests/net/forwarding/README
index a652429bfd53c..7b41cff993adb 100644
--- a/tools/testing/selftests/net/forwarding/README
+++ b/tools/testing/selftests/net/forwarding/README
@@ -6,7 +6,7 @@ to easily create and test complex environments.
 
 Unfortunately, these namespaces can not be used with actual switching
 ASICs, as their ports can not be migrated to other network namespaces
-(dev->netns_local) and most of them probably do not support the
+(dev->netns_immutable) and most of them probably do not support the
 L1-separation provided by namespaces.
 
 However, a similar kind of flexibility can be achieved by using VRFs and

From 4754affe0b57e55fbd17c0986c89b548d093d5c4 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 28 Feb 2025 11:20:57 +0100
Subject: [PATCH 1479/2753] net: advertise netns_immutable property via netlink

Since commit 05c1280a2bcf ("netdev_features: convert NETIF_F_NETNS_LOCAL to
dev->netns_local"), there is no way to see if the netns_immutable property
s set on a device. Let's add a netlink attribute to advertise it.

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/netlink/specs/rt_link.yaml | 3 +++
 include/uapi/linux/if_link.h             | 1 +
 net/core/rtnetlink.c                     | 3 +++
 3 files changed, 7 insertions(+)

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 8b5c0f0673285..31238455f8e9d 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -1160,6 +1160,9 @@ attribute-sets:
         name: max-pacing-offload-horizon
         type: uint
         doc: EDT offload horizon supported by the device (in nsec).
+      -
+        name: netns-immutable
+        type: u8
   -
     name: af-spec-attrs
     attributes:
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3b586fb0bc4cd..318386cc5b0d1 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -378,6 +378,7 @@ enum {
 	IFLA_GRO_IPV4_MAX_SIZE,
 	IFLA_DPLL_PIN,
 	IFLA_MAX_PACING_OFFLOAD_HORIZON,
+	IFLA_NETNS_IMMUTABLE,
 	__IFLA_MAX
 };
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b52e610e157e9..8b6bf5e9bb342 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1292,6 +1292,7 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev,
 	       + nla_total_size(4) /* IFLA_TSO_MAX_SEGS */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
 	       + nla_total_size(1) /* IFLA_LINKMODE */
+	       + nla_total_size(1) /* IFLA_NETNS_IMMUTABLE */
 	       + nla_total_size(4) /* IFLA_CARRIER_CHANGES */
 	       + nla_total_size(4) /* IFLA_LINK_NETNSID */
 	       + nla_total_size(4) /* IFLA_GROUP */
@@ -2046,6 +2047,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 		       netif_running(dev) ? READ_ONCE(dev->operstate) :
 					    IF_OPER_DOWN) ||
 	    nla_put_u8(skb, IFLA_LINKMODE, READ_ONCE(dev->link_mode)) ||
+	    nla_put_u8(skb, IFLA_NETNS_IMMUTABLE, dev->netns_immutable) ||
 	    nla_put_u32(skb, IFLA_MTU, READ_ONCE(dev->mtu)) ||
 	    nla_put_u32(skb, IFLA_MIN_MTU, READ_ONCE(dev->min_mtu)) ||
 	    nla_put_u32(skb, IFLA_MAX_MTU, READ_ONCE(dev->max_mtu)) ||
@@ -2234,6 +2236,7 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_ALLMULTI]		= { .type = NLA_REJECT },
 	[IFLA_GSO_IPV4_MAX_SIZE]	= NLA_POLICY_MIN(NLA_U32, MAX_TCP_HEADER + 1),
 	[IFLA_GRO_IPV4_MAX_SIZE]	= { .type = NLA_U32 },
+	[IFLA_NETNS_IMMUTABLE]	= { .type = NLA_REJECT },
 };
 
 static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {

From 12b6f7069ba5aa160f3332916408b34ae8e0b0f6 Mon Sep 17 00:00:00 2001
From: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Date: Fri, 28 Feb 2025 11:20:58 +0100
Subject: [PATCH 1480/2753] net: plumb extack in __dev_change_net_namespace()

It could be hard to understand why the netlink command fails. For example,
if dev->netns_immutable is set, the error is "Invalid argument".

Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h |  5 +++--
 net/core/dev.c            | 43 +++++++++++++++++++++++++++++++--------
 net/core/rtnetlink.c      |  2 +-
 3 files changed, 38 insertions(+), 12 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b8728d67ea91d..7ab86ec228b7f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4191,12 +4191,13 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
 int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int __dev_change_net_namespace(struct net_device *dev, struct net *net,
-			       const char *pat, int new_ifindex);
+			       const char *pat, int new_ifindex,
+			       struct netlink_ext_ack *extack);
 static inline
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
 			     const char *pat)
 {
-	return __dev_change_net_namespace(dev, net, pat, 0);
+	return __dev_change_net_namespace(dev, net, pat, 0, NULL);
 }
 int __dev_set_mtu(struct net_device *, int);
 int dev_set_mtu(struct net_device *, int);
diff --git a/net/core/dev.c b/net/core/dev.c
index 357ae88064a5f..5c9d2bd29e156 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -12131,6 +12131,7 @@ EXPORT_SYMBOL(unregister_netdev);
  *	      is already taken in the destination network namespace.
  *	@new_ifindex: If not zero, specifies device index in the target
  *	              namespace.
+ *	@extack: netlink extended ack
  *
  *	This function shuts down a device interface and moves it
  *	to a new network namespace. On success 0 is returned, on
@@ -12140,7 +12141,8 @@ EXPORT_SYMBOL(unregister_netdev);
  */
 
 int __dev_change_net_namespace(struct net_device *dev, struct net *net,
-			       const char *pat, int new_ifindex)
+			       const char *pat, int new_ifindex,
+			       struct netlink_ext_ack *extack)
 {
 	struct netdev_name_node *name_node;
 	struct net *net_old = dev_net(dev);
@@ -12151,12 +12153,16 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 
 	/* Don't allow namespace local devices to be moved. */
 	err = -EINVAL;
-	if (dev->netns_immutable)
+	if (dev->netns_immutable) {
+		NL_SET_ERR_MSG(extack, "The interface netns is immutable");
 		goto out;
+	}
 
 	/* Ensure the device has been registered */
-	if (dev->reg_state != NETREG_REGISTERED)
+	if (dev->reg_state != NETREG_REGISTERED) {
+		NL_SET_ERR_MSG(extack, "The interface isn't registered");
 		goto out;
+	}
 
 	/* Get out if there is nothing todo */
 	err = 0;
@@ -12169,30 +12175,49 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	err = -EEXIST;
 	if (netdev_name_in_use(net, dev->name)) {
 		/* We get here if we can't use the current device name */
-		if (!pat)
+		if (!pat) {
+			NL_SET_ERR_MSG(extack,
+				       "An interface with the same name exists in the target netns");
 			goto out;
+		}
 		err = dev_prep_valid_name(net, dev, pat, new_name, EEXIST);
-		if (err < 0)
+		if (err < 0) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "Unable to use '%s' for the new interface name in the target netns",
+					   pat);
 			goto out;
+		}
 	}
 	/* Check that none of the altnames conflicts. */
 	err = -EEXIST;
-	netdev_for_each_altname(dev, name_node)
-		if (netdev_name_in_use(net, name_node->name))
+	netdev_for_each_altname(dev, name_node) {
+		if (netdev_name_in_use(net, name_node->name)) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "An interface with the altname %s exists in the target netns",
+					   name_node->name);
 			goto out;
+		}
+	}
 
 	/* Check that new_ifindex isn't used yet. */
 	if (new_ifindex) {
 		err = dev_index_reserve(net, new_ifindex);
-		if (err < 0)
+		if (err < 0) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "The ifindex %d is not available in the target netns",
+					   new_ifindex);
 			goto out;
+		}
 	} else {
 		/* If there is an ifindex conflict assign a new one */
 		err = dev_index_reserve(net, dev->ifindex);
 		if (err == -EBUSY)
 			err = dev_index_reserve(net, 0);
-		if (err < 0)
+		if (err < 0) {
+			NL_SET_ERR_MSG(extack,
+				       "Unable to allocate a new ifindex in the target netns");
 			goto out;
+		}
 		new_ifindex = err;
 	}
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 8b6bf5e9bb342..b4612d3059704 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3028,7 +3028,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 		new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
 
-		err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex);
+		err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex, extack);
 		if (err)
 			goto errout;
 

From 1f860eb4cdda634589d75e78ff586d5dff20b8af Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Mon, 3 Mar 2025 11:05:36 +0100
Subject: [PATCH 1481/2753] wifi: nl80211: disable multi-link reconfiguration

Both the APIs in cfg80211 and the implementation in mac80211
aren't really ready yet, we have a large number of fixes. In
addition, it's not possible right now to discover support for
this feature from userspace. Disable it for now, there's no
rush.

Link: https://patch.msgid.link/20250303110538.fbeef42a5687.Iab122c22137e5675ebd99f5c031e30c0e5c7af2e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fdb2aac951d18..e87267fbb442e 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -16534,7 +16534,7 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
-	err = cfg80211_assoc_ml_reconf(rdev, dev, links, rem_links);
+	err = -EOPNOTSUPP;
 
 out:
 	for (link_id = 0; link_id < ARRAY_SIZE(links); link_id++)

From b7365eab39831487a84e63a9638209b68dc54008 Mon Sep 17 00:00:00 2001
From: Peiyang Wang <wangpeiyang1@huawei.com>
Date: Fri, 28 Feb 2025 18:52:58 +0800
Subject: [PATCH 1482/2753] net: hns3: make sure ptp clock is unregister and
 freed if hclge_ptp_get_cycle returns an error

During the initialization of ptp, hclge_ptp_get_cycle might return an error
and returned directly without unregister clock and free it. To avoid that,
call hclge_ptp_destroy_clock to unregist and free clock if
hclge_ptp_get_cycle failed.

Fixes: 8373cd38a888 ("net: hns3: change the method of obtaining default ptp cycle")
Signed-off-by: Peiyang Wang <wangpeiyang1@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250228105258.1243461-1-shaojijie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index bab16c2191b2f..181af419b878d 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -483,7 +483,7 @@ int hclge_ptp_init(struct hclge_dev *hdev)
 
 		ret = hclge_ptp_get_cycle(hdev);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	ret = hclge_ptp_int_en(hdev, true);

From fb3dda82fd38ca42140f29b3082324dcdc128293 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:09 +0100
Subject: [PATCH 1483/2753] net: airoha: Move airoha_eth driver in a dedicated
 folder

The airoha_eth driver has no codebase shared with mtk_eth_soc one.
Moreover, the upcoming features (flowtable hw offloading, PCS, ..) will
not reuse any code from MediaTek driver. Move the Airoha driver in a
dedicated folder.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/Kconfig                   |  2 ++
 drivers/net/ethernet/Makefile                  |  1 +
 drivers/net/ethernet/airoha/Kconfig            | 18 ++++++++++++++++++
 drivers/net/ethernet/airoha/Makefile           |  6 ++++++
 .../ethernet/{mediatek => airoha}/airoha_eth.c |  0
 drivers/net/ethernet/mediatek/Kconfig          |  8 --------
 drivers/net/ethernet/mediatek/Makefile         |  1 -
 7 files changed, 27 insertions(+), 9 deletions(-)
 create mode 100644 drivers/net/ethernet/airoha/Kconfig
 create mode 100644 drivers/net/ethernet/airoha/Makefile
 rename drivers/net/ethernet/{mediatek => airoha}/airoha_eth.c (100%)

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 977b42bc1e8c1..7941983d21e9e 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -20,6 +20,8 @@ source "drivers/net/ethernet/actions/Kconfig"
 source "drivers/net/ethernet/adaptec/Kconfig"
 source "drivers/net/ethernet/aeroflex/Kconfig"
 source "drivers/net/ethernet/agere/Kconfig"
+source "drivers/net/ethernet/airoha/Kconfig"
+source "drivers/net/ethernet/mellanox/Kconfig"
 source "drivers/net/ethernet/alacritech/Kconfig"
 source "drivers/net/ethernet/allwinner/Kconfig"
 source "drivers/net/ethernet/alteon/Kconfig"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 99fa180dedb80..67182339469a0 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_NET_VENDOR_ADAPTEC) += adaptec/
 obj-$(CONFIG_GRETH) += aeroflex/
 obj-$(CONFIG_NET_VENDOR_ADI) += adi/
 obj-$(CONFIG_NET_VENDOR_AGERE) += agere/
+obj-$(CONFIG_NET_VENDOR_AIROHA) += airoha/
 obj-$(CONFIG_NET_VENDOR_ALACRITECH) += alacritech/
 obj-$(CONFIG_NET_VENDOR_ALLWINNER) += allwinner/
 obj-$(CONFIG_NET_VENDOR_ALTEON) += alteon/
diff --git a/drivers/net/ethernet/airoha/Kconfig b/drivers/net/ethernet/airoha/Kconfig
new file mode 100644
index 0000000000000..b6a131845f13b
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Kconfig
@@ -0,0 +1,18 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config NET_VENDOR_AIROHA
+	bool "Airoha devices"
+	depends on ARCH_AIROHA || COMPILE_TEST
+	help
+	  If you have a Airoha SoC with ethernet, say Y.
+
+if NET_VENDOR_AIROHA
+
+config NET_AIROHA
+	tristate "Airoha SoC Gigabit Ethernet support"
+	depends on NET_DSA || !NET_DSA
+	select PAGE_POOL
+	help
+	  This driver supports the gigabit ethernet MACs in the
+	  Airoha SoC family.
+
+endif #NET_VENDOR_AIROHA
diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
new file mode 100644
index 0000000000000..73a6f3680a4c4
--- /dev/null
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Airoha for the Mediatek SoCs built-in ethernet macs
+#
+
+obj-$(CONFIG_NET_AIROHA) += airoha_eth.o
diff --git a/drivers/net/ethernet/mediatek/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
similarity index 100%
rename from drivers/net/ethernet/mediatek/airoha_eth.c
rename to drivers/net/ethernet/airoha/airoha_eth.c
diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig
index 95c4405b7d7be..7bfd3f230ff50 100644
--- a/drivers/net/ethernet/mediatek/Kconfig
+++ b/drivers/net/ethernet/mediatek/Kconfig
@@ -7,14 +7,6 @@ config NET_VENDOR_MEDIATEK
 
 if NET_VENDOR_MEDIATEK
 
-config NET_AIROHA
-	tristate "Airoha SoC Gigabit Ethernet support"
-	depends on NET_DSA || !NET_DSA
-	select PAGE_POOL
-	help
-	  This driver supports the gigabit ethernet MACs in the
-	  Airoha SoC family.
-
 config NET_MEDIATEK_SOC_WED
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	def_bool NET_MEDIATEK_SOC != n
diff --git a/drivers/net/ethernet/mediatek/Makefile b/drivers/net/ethernet/mediatek/Makefile
index ddbb7f4a516ca..03e008fbc859b 100644
--- a/drivers/net/ethernet/mediatek/Makefile
+++ b/drivers/net/ethernet/mediatek/Makefile
@@ -11,4 +11,3 @@ mtk_eth-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_debugfs.o
 endif
 obj-$(CONFIG_NET_MEDIATEK_SOC_WED) += mtk_wed_ops.o
 obj-$(CONFIG_NET_MEDIATEK_STAR_EMAC) += mtk_star_emac.o
-obj-$(CONFIG_NET_AIROHA) += airoha_eth.o

From b38f4ff0ceacd6ce8d333a8dc90f405a040968d3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:10 +0100
Subject: [PATCH 1484/2753] net: airoha: Move definitions in airoha_eth.h

Move common airoha_eth definitions in airoha_eth.h in order to reuse
them for Packet Processor Engine (PPE) codebase.
PPE module is used to enable support for flowtable hw offloading in
airoha_eth driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 240 +---------------------
 drivers/net/ethernet/airoha/airoha_eth.h | 251 +++++++++++++++++++++++
 2 files changed, 252 insertions(+), 239 deletions(-)
 create mode 100644 drivers/net/ethernet/airoha/airoha_eth.h

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index aa5f220ddbcf9..0048a5665576a 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -3,14 +3,9 @@
  * Copyright (c) 2024 AIROHA Inc
  * Author: Lorenzo Bianconi <lorenzo@kernel.org>
  */
-#include <linux/etherdevice.h>
-#include <linux/iopoll.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/platform_device.h>
-#include <linux/reset.h>
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
 #include <net/dsa.h>
@@ -18,35 +13,7 @@
 #include <net/pkt_cls.h>
 #include <uapi/linux/ppp_defs.h>
 
-#define AIROHA_MAX_NUM_GDM_PORTS	1
-#define AIROHA_MAX_NUM_QDMA		2
-#define AIROHA_MAX_NUM_RSTS		3
-#define AIROHA_MAX_NUM_XSI_RSTS		5
-#define AIROHA_MAX_MTU			2000
-#define AIROHA_MAX_PACKET_SIZE		2048
-#define AIROHA_NUM_QOS_CHANNELS		4
-#define AIROHA_NUM_QOS_QUEUES		8
-#define AIROHA_NUM_TX_RING		32
-#define AIROHA_NUM_RX_RING		32
-#define AIROHA_NUM_NETDEV_TX_RINGS	(AIROHA_NUM_TX_RING + \
-					 AIROHA_NUM_QOS_CHANNELS)
-#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
-#define AIROHA_FE_MC_MAX_VLAN_PORT	16
-#define AIROHA_NUM_TX_IRQ		2
-#define HW_DSCP_NUM			2048
-#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
-#define TX_DSCP_NUM			1024
-#define RX_DSCP_NUM(_n)			\
-	((_n) ==  2 ? 128 :		\
-	 (_n) == 11 ? 128 :		\
-	 (_n) == 15 ? 128 :		\
-	 (_n) ==  0 ? 1024 : 16)
-
-#define PSE_RSV_PAGES			128
-#define PSE_QUEUE_RSV_PAGES		64
-
-#define QDMA_METER_IDX(_n)		((_n) & 0xff)
-#define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
+#include "airoha_eth.h"
 
 /* FE */
 #define PSE_BASE			0x0100
@@ -706,211 +673,6 @@ struct airoha_qdma_fwd_desc {
 	__le32 rsv1;
 };
 
-enum {
-	QDMA_INT_REG_IDX0,
-	QDMA_INT_REG_IDX1,
-	QDMA_INT_REG_IDX2,
-	QDMA_INT_REG_IDX3,
-	QDMA_INT_REG_IDX4,
-	QDMA_INT_REG_MAX
-};
-
-enum {
-	XSI_PCIE0_PORT,
-	XSI_PCIE1_PORT,
-	XSI_USB_PORT,
-	XSI_AE_PORT,
-	XSI_ETH_PORT,
-};
-
-enum {
-	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
-	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
-	XSI_USB_VIP_PORT_MASK	= BIT(25),
-	XSI_ETH_VIP_PORT_MASK	= BIT(24),
-};
-
-enum {
-	DEV_STATE_INITIALIZED,
-};
-
-enum {
-	CDM_CRSN_QSEL_Q1 = 1,
-	CDM_CRSN_QSEL_Q5 = 5,
-	CDM_CRSN_QSEL_Q6 = 6,
-	CDM_CRSN_QSEL_Q15 = 15,
-};
-
-enum {
-	CRSN_08 = 0x8,
-	CRSN_21 = 0x15, /* KA */
-	CRSN_22 = 0x16, /* hit bind and force route to CPU */
-	CRSN_24 = 0x18,
-	CRSN_25 = 0x19,
-};
-
-enum {
-	FE_PSE_PORT_CDM1,
-	FE_PSE_PORT_GDM1,
-	FE_PSE_PORT_GDM2,
-	FE_PSE_PORT_GDM3,
-	FE_PSE_PORT_PPE1,
-	FE_PSE_PORT_CDM2,
-	FE_PSE_PORT_CDM3,
-	FE_PSE_PORT_CDM4,
-	FE_PSE_PORT_PPE2,
-	FE_PSE_PORT_GDM4,
-	FE_PSE_PORT_CDM5,
-	FE_PSE_PORT_DROP = 0xf,
-};
-
-enum tx_sched_mode {
-	TC_SCH_WRR8,
-	TC_SCH_SP,
-	TC_SCH_WRR7,
-	TC_SCH_WRR6,
-	TC_SCH_WRR5,
-	TC_SCH_WRR4,
-	TC_SCH_WRR3,
-	TC_SCH_WRR2,
-};
-
-enum trtcm_param_type {
-	TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */
-	TRTCM_TOKEN_RATE_MODE,
-	TRTCM_BUCKETSIZE_SHIFT_MODE,
-	TRTCM_BUCKET_COUNTER_MODE,
-};
-
-enum trtcm_mode_type {
-	TRTCM_COMMIT_MODE,
-	TRTCM_PEAK_MODE,
-};
-
-enum trtcm_param {
-	TRTCM_TICK_SEL = BIT(0),
-	TRTCM_PKT_MODE = BIT(1),
-	TRTCM_METER_MODE = BIT(2),
-};
-
-#define MIN_TOKEN_SIZE				4096
-#define MAX_TOKEN_SIZE_OFFSET			17
-#define TRTCM_TOKEN_RATE_MASK			GENMASK(23, 6)
-#define TRTCM_TOKEN_RATE_FRACTION_MASK		GENMASK(5, 0)
-
-struct airoha_queue_entry {
-	union {
-		void *buf;
-		struct sk_buff *skb;
-	};
-	dma_addr_t dma_addr;
-	u16 dma_len;
-};
-
-struct airoha_queue {
-	struct airoha_qdma *qdma;
-
-	/* protect concurrent queue accesses */
-	spinlock_t lock;
-	struct airoha_queue_entry *entry;
-	struct airoha_qdma_desc *desc;
-	u16 head;
-	u16 tail;
-
-	int queued;
-	int ndesc;
-	int free_thr;
-	int buf_size;
-
-	struct napi_struct napi;
-	struct page_pool *page_pool;
-};
-
-struct airoha_tx_irq_queue {
-	struct airoha_qdma *qdma;
-
-	struct napi_struct napi;
-
-	int size;
-	u32 *q;
-};
-
-struct airoha_hw_stats {
-	/* protect concurrent hw_stats accesses */
-	spinlock_t lock;
-	struct u64_stats_sync syncp;
-
-	/* get_stats64 */
-	u64 rx_ok_pkts;
-	u64 tx_ok_pkts;
-	u64 rx_ok_bytes;
-	u64 tx_ok_bytes;
-	u64 rx_multicast;
-	u64 rx_errors;
-	u64 rx_drops;
-	u64 tx_drops;
-	u64 rx_crc_error;
-	u64 rx_over_errors;
-	/* ethtool stats */
-	u64 tx_broadcast;
-	u64 tx_multicast;
-	u64 tx_len[7];
-	u64 rx_broadcast;
-	u64 rx_fragment;
-	u64 rx_jabber;
-	u64 rx_len[7];
-};
-
-struct airoha_qdma {
-	struct airoha_eth *eth;
-	void __iomem *regs;
-
-	/* protect concurrent irqmask accesses */
-	spinlock_t irq_lock;
-	u32 irqmask[QDMA_INT_REG_MAX];
-	int irq;
-
-	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
-
-	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
-	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
-
-	/* descriptor and packet buffers for qdma hw forward */
-	struct {
-		void *desc;
-		void *q;
-	} hfwd;
-};
-
-struct airoha_gdm_port {
-	struct airoha_qdma *qdma;
-	struct net_device *dev;
-	int id;
-
-	struct airoha_hw_stats stats;
-
-	DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
-
-	/* qos stats counters */
-	u64 cpu_tx_packets;
-	u64 fwd_tx_packets;
-};
-
-struct airoha_eth {
-	struct device *dev;
-
-	unsigned long state;
-	void __iomem *fe_regs;
-
-	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
-	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
-
-	struct net_device *napi_dev;
-
-	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
-	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
-};
-
 static u32 airoha_rr(void __iomem *base, u32 offset)
 {
 	return readl(base + offset);
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
new file mode 100644
index 0000000000000..3310e0cf85f1d
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -0,0 +1,251 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_ETH_H
+#define AIROHA_ETH_H
+
+#include <linux/etherdevice.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/reset.h>
+
+#define AIROHA_MAX_NUM_GDM_PORTS	1
+#define AIROHA_MAX_NUM_QDMA		2
+#define AIROHA_MAX_NUM_RSTS		3
+#define AIROHA_MAX_NUM_XSI_RSTS		5
+#define AIROHA_MAX_MTU			2000
+#define AIROHA_MAX_PACKET_SIZE		2048
+#define AIROHA_NUM_QOS_CHANNELS		4
+#define AIROHA_NUM_QOS_QUEUES		8
+#define AIROHA_NUM_TX_RING		32
+#define AIROHA_NUM_RX_RING		32
+#define AIROHA_NUM_NETDEV_TX_RINGS	(AIROHA_NUM_TX_RING + \
+					 AIROHA_NUM_QOS_CHANNELS)
+#define AIROHA_FE_MC_MAX_VLAN_TABLE	64
+#define AIROHA_FE_MC_MAX_VLAN_PORT	16
+#define AIROHA_NUM_TX_IRQ		2
+#define HW_DSCP_NUM			2048
+#define IRQ_QUEUE_LEN(_n)		((_n) ? 1024 : 2048)
+#define TX_DSCP_NUM			1024
+#define RX_DSCP_NUM(_n)			\
+	((_n) ==  2 ? 128 :		\
+	 (_n) == 11 ? 128 :		\
+	 (_n) == 15 ? 128 :		\
+	 (_n) ==  0 ? 1024 : 16)
+
+#define PSE_RSV_PAGES			128
+#define PSE_QUEUE_RSV_PAGES		64
+
+#define QDMA_METER_IDX(_n)		((_n) & 0xff)
+#define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
+
+enum {
+	QDMA_INT_REG_IDX0,
+	QDMA_INT_REG_IDX1,
+	QDMA_INT_REG_IDX2,
+	QDMA_INT_REG_IDX3,
+	QDMA_INT_REG_IDX4,
+	QDMA_INT_REG_MAX
+};
+
+enum {
+	XSI_PCIE0_PORT,
+	XSI_PCIE1_PORT,
+	XSI_USB_PORT,
+	XSI_AE_PORT,
+	XSI_ETH_PORT,
+};
+
+enum {
+	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
+	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
+	XSI_USB_VIP_PORT_MASK	= BIT(25),
+	XSI_ETH_VIP_PORT_MASK	= BIT(24),
+};
+
+enum {
+	DEV_STATE_INITIALIZED,
+};
+
+enum {
+	CDM_CRSN_QSEL_Q1 = 1,
+	CDM_CRSN_QSEL_Q5 = 5,
+	CDM_CRSN_QSEL_Q6 = 6,
+	CDM_CRSN_QSEL_Q15 = 15,
+};
+
+enum {
+	CRSN_08 = 0x8,
+	CRSN_21 = 0x15, /* KA */
+	CRSN_22 = 0x16, /* hit bind and force route to CPU */
+	CRSN_24 = 0x18,
+	CRSN_25 = 0x19,
+};
+
+enum {
+	FE_PSE_PORT_CDM1,
+	FE_PSE_PORT_GDM1,
+	FE_PSE_PORT_GDM2,
+	FE_PSE_PORT_GDM3,
+	FE_PSE_PORT_PPE1,
+	FE_PSE_PORT_CDM2,
+	FE_PSE_PORT_CDM3,
+	FE_PSE_PORT_CDM4,
+	FE_PSE_PORT_PPE2,
+	FE_PSE_PORT_GDM4,
+	FE_PSE_PORT_CDM5,
+	FE_PSE_PORT_DROP = 0xf,
+};
+
+enum tx_sched_mode {
+	TC_SCH_WRR8,
+	TC_SCH_SP,
+	TC_SCH_WRR7,
+	TC_SCH_WRR6,
+	TC_SCH_WRR5,
+	TC_SCH_WRR4,
+	TC_SCH_WRR3,
+	TC_SCH_WRR2,
+};
+
+enum trtcm_param_type {
+	TRTCM_MISC_MODE, /* meter_en, pps_mode, tick_sel */
+	TRTCM_TOKEN_RATE_MODE,
+	TRTCM_BUCKETSIZE_SHIFT_MODE,
+	TRTCM_BUCKET_COUNTER_MODE,
+};
+
+enum trtcm_mode_type {
+	TRTCM_COMMIT_MODE,
+	TRTCM_PEAK_MODE,
+};
+
+enum trtcm_param {
+	TRTCM_TICK_SEL = BIT(0),
+	TRTCM_PKT_MODE = BIT(1),
+	TRTCM_METER_MODE = BIT(2),
+};
+
+#define MIN_TOKEN_SIZE				4096
+#define MAX_TOKEN_SIZE_OFFSET			17
+#define TRTCM_TOKEN_RATE_MASK			GENMASK(23, 6)
+#define TRTCM_TOKEN_RATE_FRACTION_MASK		GENMASK(5, 0)
+
+struct airoha_queue_entry {
+	union {
+		void *buf;
+		struct sk_buff *skb;
+	};
+	dma_addr_t dma_addr;
+	u16 dma_len;
+};
+
+struct airoha_queue {
+	struct airoha_qdma *qdma;
+
+	/* protect concurrent queue accesses */
+	spinlock_t lock;
+	struct airoha_queue_entry *entry;
+	struct airoha_qdma_desc *desc;
+	u16 head;
+	u16 tail;
+
+	int queued;
+	int ndesc;
+	int free_thr;
+	int buf_size;
+
+	struct napi_struct napi;
+	struct page_pool *page_pool;
+};
+
+struct airoha_tx_irq_queue {
+	struct airoha_qdma *qdma;
+
+	struct napi_struct napi;
+
+	int size;
+	u32 *q;
+};
+
+struct airoha_hw_stats {
+	/* protect concurrent hw_stats accesses */
+	spinlock_t lock;
+	struct u64_stats_sync syncp;
+
+	/* get_stats64 */
+	u64 rx_ok_pkts;
+	u64 tx_ok_pkts;
+	u64 rx_ok_bytes;
+	u64 tx_ok_bytes;
+	u64 rx_multicast;
+	u64 rx_errors;
+	u64 rx_drops;
+	u64 tx_drops;
+	u64 rx_crc_error;
+	u64 rx_over_errors;
+	/* ethtool stats */
+	u64 tx_broadcast;
+	u64 tx_multicast;
+	u64 tx_len[7];
+	u64 rx_broadcast;
+	u64 rx_fragment;
+	u64 rx_jabber;
+	u64 rx_len[7];
+};
+
+struct airoha_qdma {
+	struct airoha_eth *eth;
+	void __iomem *regs;
+
+	/* protect concurrent irqmask accesses */
+	spinlock_t irq_lock;
+	u32 irqmask[QDMA_INT_REG_MAX];
+	int irq;
+
+	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
+
+	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];
+	struct airoha_queue q_rx[AIROHA_NUM_RX_RING];
+
+	/* descriptor and packet buffers for qdma hw forward */
+	struct {
+		void *desc;
+		void *q;
+	} hfwd;
+};
+
+struct airoha_gdm_port {
+	struct airoha_qdma *qdma;
+	struct net_device *dev;
+	int id;
+
+	struct airoha_hw_stats stats;
+
+	DECLARE_BITMAP(qos_sq_bmap, AIROHA_NUM_QOS_CHANNELS);
+
+	/* qos stats counters */
+	u64 cpu_tx_packets;
+	u64 fwd_tx_packets;
+};
+
+struct airoha_eth {
+	struct device *dev;
+
+	unsigned long state;
+	void __iomem *fe_regs;
+
+	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
+	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
+
+	struct net_device *napi_dev;
+
+	struct airoha_qdma qdma[AIROHA_MAX_NUM_QDMA];
+	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
+};
+
+#endif /* AIROHA_ETH_H */

From e0758a8694fbaffdc72940774db295585e951119 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:11 +0100
Subject: [PATCH 1485/2753] net: airoha: Move reg/write utility routines in
 airoha_eth.h

This is a preliminary patch to introduce flowtable hw offloading
support for airoha_eth driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 28 +++---------------------
 drivers/net/ethernet/airoha/airoha_eth.h | 26 ++++++++++++++++++++++
 2 files changed, 29 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 0048a5665576a..1c6fb7b9ccbba 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -673,17 +673,17 @@ struct airoha_qdma_fwd_desc {
 	__le32 rsv1;
 };
 
-static u32 airoha_rr(void __iomem *base, u32 offset)
+u32 airoha_rr(void __iomem *base, u32 offset)
 {
 	return readl(base + offset);
 }
 
-static void airoha_wr(void __iomem *base, u32 offset, u32 val)
+void airoha_wr(void __iomem *base, u32 offset, u32 val)
 {
 	writel(val, base + offset);
 }
 
-static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 {
 	val |= (airoha_rr(base, offset) & ~mask);
 	airoha_wr(base, offset, val);
@@ -691,28 +691,6 @@ static u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val)
 	return val;
 }
 
-#define airoha_fe_rr(eth, offset)				\
-	airoha_rr((eth)->fe_regs, (offset))
-#define airoha_fe_wr(eth, offset, val)				\
-	airoha_wr((eth)->fe_regs, (offset), (val))
-#define airoha_fe_rmw(eth, offset, mask, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
-#define airoha_fe_set(eth, offset, val)				\
-	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
-#define airoha_fe_clear(eth, offset, val)			\
-	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
-
-#define airoha_qdma_rr(qdma, offset)				\
-	airoha_rr((qdma)->regs, (offset))
-#define airoha_qdma_wr(qdma, offset, val)			\
-	airoha_wr((qdma)->regs, (offset), (val))
-#define airoha_qdma_rmw(qdma, offset, mask, val)		\
-	airoha_rmw((qdma)->regs, (offset), (mask), (val))
-#define airoha_qdma_set(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), 0, (val))
-#define airoha_qdma_clear(qdma, offset, val)			\
-	airoha_rmw((qdma)->regs, (offset), (val), 0)
-
 static void airoha_qdma_set_irqmask(struct airoha_qdma *qdma, int index,
 				    u32 clear, u32 set)
 {
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 3310e0cf85f1d..743aaf10235fe 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -248,4 +248,30 @@ struct airoha_eth {
 	struct airoha_gdm_port *ports[AIROHA_MAX_NUM_GDM_PORTS];
 };
 
+u32 airoha_rr(void __iomem *base, u32 offset);
+void airoha_wr(void __iomem *base, u32 offset, u32 val);
+u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
+
+#define airoha_fe_rr(eth, offset)				\
+	airoha_rr((eth)->fe_regs, (offset))
+#define airoha_fe_wr(eth, offset, val)				\
+	airoha_wr((eth)->fe_regs, (offset), (val))
+#define airoha_fe_rmw(eth, offset, mask, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (mask), (val))
+#define airoha_fe_set(eth, offset, val)				\
+	airoha_rmw((eth)->fe_regs, (offset), 0, (val))
+#define airoha_fe_clear(eth, offset, val)			\
+	airoha_rmw((eth)->fe_regs, (offset), (val), 0)
+
+#define airoha_qdma_rr(qdma, offset)				\
+	airoha_rr((qdma)->regs, (offset))
+#define airoha_qdma_wr(qdma, offset, val)			\
+	airoha_wr((qdma)->regs, (offset), (val))
+#define airoha_qdma_rmw(qdma, offset, mask, val)		\
+	airoha_rmw((qdma)->regs, (offset), (mask), (val))
+#define airoha_qdma_set(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), 0, (val))
+#define airoha_qdma_clear(qdma, offset, val)			\
+	airoha_rmw((qdma)->regs, (offset), (val), 0)
+
 #endif /* AIROHA_ETH_H */

From ec663d9a82bf4d16721f6b1fc29df4892ba6c088 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:12 +0100
Subject: [PATCH 1486/2753] net: airoha: Move register definitions in
 airoha_regs.h

Move common airoha_eth register definitions in airoha_regs.h in order
to reuse them for Packet Processor Engine (PPE) codebase.
PPE module is used to enable support for flowtable hw offloading in
airoha_eth driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c  | 659 +--------------------
 drivers/net/ethernet/airoha/airoha_regs.h | 670 ++++++++++++++++++++++
 2 files changed, 671 insertions(+), 658 deletions(-)
 create mode 100644 drivers/net/ethernet/airoha/airoha_regs.h

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 1c6fb7b9ccbba..b79556f1b4951 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -13,666 +13,9 @@
 #include <net/pkt_cls.h>
 #include <uapi/linux/ppp_defs.h>
 
+#include "airoha_regs.h"
 #include "airoha_eth.h"
 
-/* FE */
-#define PSE_BASE			0x0100
-#define CSR_IFC_BASE			0x0200
-#define CDM1_BASE			0x0400
-#define GDM1_BASE			0x0500
-#define PPE1_BASE			0x0c00
-
-#define CDM2_BASE			0x1400
-#define GDM2_BASE			0x1500
-
-#define GDM3_BASE			0x1100
-#define GDM4_BASE			0x2500
-
-#define GDM_BASE(_n)			\
-	((_n) == 4 ? GDM4_BASE :	\
-	 (_n) == 3 ? GDM3_BASE :	\
-	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
-
-#define REG_FE_DMA_GLO_CFG		0x0000
-#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
-#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
-
-#define REG_FE_RST_GLO_CFG		0x0004
-#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
-#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
-#define FE_RST_CORE_MASK		BIT(0)
-
-#define REG_FE_WAN_MAC_H		0x0030
-#define REG_FE_LAN_MAC_H		0x0040
-
-#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
-#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
-
-#define REG_FE_CDM1_OQ_MAP0		0x0050
-#define REG_FE_CDM1_OQ_MAP1		0x0054
-#define REG_FE_CDM1_OQ_MAP2		0x0058
-#define REG_FE_CDM1_OQ_MAP3		0x005c
-
-#define REG_FE_PCE_CFG			0x0070
-#define PCE_DPI_EN_MASK			BIT(2)
-#define PCE_KA_EN_MASK			BIT(1)
-#define PCE_MC_EN_MASK			BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
-#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
-#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
-#define PSE_CFG_WR_EN_MASK		BIT(8)
-#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
-
-#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
-#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
-
-#define PSE_FQ_CFG			0x008c
-#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
-
-#define REG_FE_PSE_BUF_SET		0x0090
-#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
-#define PSE_ALLRSV_MASK			GENMASK(14, 0)
-
-#define REG_PSE_SHARE_USED_THD		0x0094
-#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
-#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
-
-#define REG_GDM_MISC_CFG		0x0148
-#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
-#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
-
-#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
-#define FE_IFC_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PORT_EN		0x01f0
-#define REG_FE_IFC_PORT_EN		0x01f4
-
-#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
-#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
-
-#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
-#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
-#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
-
-#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
-#define PATN_FCPU_EN_MASK		BIT(7)
-#define PATN_SWP_EN_MASK		BIT(6)
-#define PATN_DP_EN_MASK			BIT(5)
-#define PATN_SP_EN_MASK			BIT(4)
-#define PATN_TYPE_MASK			GENMASK(3, 1)
-#define PATN_EN_MASK			BIT(0)
-
-#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
-#define PATN_DP_MASK			GENMASK(31, 16)
-#define PATN_SP_MASK			GENMASK(15, 0)
-
-#define REG_CDM1_VLAN_CTRL		CDM1_BASE
-#define CDM1_VLAN_MASK			GENMASK(31, 16)
-
-#define REG_CDM1_FWD_CFG		(CDM1_BASE + 0x08)
-#define CDM1_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM1_CRSN_QSEL(_n)		(CDM1_BASE + 0x10 + ((_n) << 2))
-#define CDM1_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_CDM2_FWD_CFG		(CDM2_BASE + 0x08)
-#define CDM2_OAM_QSEL_MASK		GENMASK(31, 27)
-#define CDM2_VIP_QSEL_MASK		GENMASK(24, 20)
-
-#define REG_CDM2_CRSN_QSEL(_n)		(CDM2_BASE + 0x10 + ((_n) << 2))
-#define CDM2_CRSN_QSEL_REASON_MASK(_n)	\
-	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
-
-#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
-#define GDM_DROP_CRC_ERR		BIT(23)
-#define GDM_IP4_CKSUM			BIT(22)
-#define GDM_TCP_CKSUM			BIT(21)
-#define GDM_UDP_CKSUM			BIT(20)
-#define GDM_UCFQ_MASK			GENMASK(15, 12)
-#define GDM_BCFQ_MASK			GENMASK(11, 8)
-#define GDM_MCFQ_MASK			GENMASK(7, 4)
-#define GDM_OCFQ_MASK			GENMASK(3, 0)
-
-#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
-#define GDM_INGRESS_FC_EN_MASK		BIT(1)
-#define GDM_STAG_EN_MASK		BIT(0)
-
-#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
-#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
-#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
-
-#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
-#define FE_CPORT_PAD			BIT(26)
-#define FE_CPORT_PORT_XFC_MASK		BIT(25)
-#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
-
-#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
-#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
-#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
-
-#define REG_FE_GDM1_MIB_CFG		(GDM1_BASE + 0xf4)
-#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
-#define FE_GDM1_TX_MIB_SPLIT_EN_MASK	BIT(17)
-#define FE_GDM1_RX_MIB_SPLIT_EN_MASK	BIT(16)
-#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
-#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
-#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
-#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
-#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
-#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
-#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
-#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
-#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
-#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
-#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
-#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
-#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
-#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
-#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
-#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
-#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
-#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
-#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
-#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
-#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
-#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
-#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
-#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
-#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
-#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
-#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
-#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
-#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
-
-#define REG_PPE1_TB_HASH_CFG		(PPE1_BASE + 0x250)
-#define PPE1_SRAM_TABLE_EN_MASK		BIT(0)
-#define PPE1_SRAM_HASH1_EN_MASK		BIT(8)
-#define PPE1_DRAM_TABLE_EN_MASK		BIT(16)
-#define PPE1_DRAM_HASH1_EN_MASK		BIT(24)
-
-#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
-#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
-#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
-#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
-
-#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
-#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
-#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
-#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
-#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
-#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
-#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
-#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
-#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
-#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
-#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
-#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
-#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
-#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
-#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
-#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
-
-#define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
-#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
-#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
-
-#define REG_GDM3_FWD_CFG		GDM3_BASE
-#define GDM3_PAD_EN_MASK		BIT(28)
-
-#define REG_GDM4_FWD_CFG		GDM4_BASE
-#define GDM4_PAD_EN_MASK		BIT(28)
-#define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
-
-#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x23c)
-#define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
-#define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
-#define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
-
-#define REG_IP_FRAG_FP			0x2010
-#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
-#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
-#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
-#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
-
-#define REG_MC_VLAN_EN			0x2100
-#define MC_VLAN_EN_MASK			BIT(0)
-
-#define REG_MC_VLAN_CFG			0x2104
-#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
-#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
-#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
-#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
-#define MC_VLAN_CFG_RW_MASK		BIT(0)
-
-#define REG_MC_VLAN_DATA		0x2108
-
-#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
-
-/* QDMA */
-#define REG_QDMA_GLOBAL_CFG			0x0004
-#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
-#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
-#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
-#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
-#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
-#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
-#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
-#define GLOBAL_CFG_RESET_MASK			BIT(23)
-#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
-#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
-#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
-#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
-#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
-#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
-#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
-#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
-#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
-#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
-#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
-#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
-#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
-#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
-#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
-
-#define REG_FWD_DSCP_BASE			0x0010
-#define REG_FWD_BUF_BASE			0x0014
-
-#define REG_HW_FWD_DSCP_CFG			0x0018
-#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
-#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
-#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
-
-#define REG_INT_STATUS(_n)		\
-	(((_n) == 4) ? 0x0730 :		\
-	 ((_n) == 3) ? 0x0724 :		\
-	 ((_n) == 2) ? 0x0720 :		\
-	 ((_n) == 1) ? 0x0024 : 0x0020)
-
-#define REG_INT_ENABLE(_n)		\
-	(((_n) == 4) ? 0x0750 :		\
-	 ((_n) == 3) ? 0x0744 :		\
-	 ((_n) == 2) ? 0x0740 :		\
-	 ((_n) == 1) ? 0x002c : 0x0028)
-
-/* QDMA_CSR_INT_ENABLE1 */
-#define RX15_COHERENT_INT_MASK		BIT(31)
-#define RX14_COHERENT_INT_MASK		BIT(30)
-#define RX13_COHERENT_INT_MASK		BIT(29)
-#define RX12_COHERENT_INT_MASK		BIT(28)
-#define RX11_COHERENT_INT_MASK		BIT(27)
-#define RX10_COHERENT_INT_MASK		BIT(26)
-#define RX9_COHERENT_INT_MASK		BIT(25)
-#define RX8_COHERENT_INT_MASK		BIT(24)
-#define RX7_COHERENT_INT_MASK		BIT(23)
-#define RX6_COHERENT_INT_MASK		BIT(22)
-#define RX5_COHERENT_INT_MASK		BIT(21)
-#define RX4_COHERENT_INT_MASK		BIT(20)
-#define RX3_COHERENT_INT_MASK		BIT(19)
-#define RX2_COHERENT_INT_MASK		BIT(18)
-#define RX1_COHERENT_INT_MASK		BIT(17)
-#define RX0_COHERENT_INT_MASK		BIT(16)
-#define TX7_COHERENT_INT_MASK		BIT(15)
-#define TX6_COHERENT_INT_MASK		BIT(14)
-#define TX5_COHERENT_INT_MASK		BIT(13)
-#define TX4_COHERENT_INT_MASK		BIT(12)
-#define TX3_COHERENT_INT_MASK		BIT(11)
-#define TX2_COHERENT_INT_MASK		BIT(10)
-#define TX1_COHERENT_INT_MASK		BIT(9)
-#define TX0_COHERENT_INT_MASK		BIT(8)
-#define CNT_OVER_FLOW_INT_MASK		BIT(7)
-#define IRQ1_FULL_INT_MASK		BIT(5)
-#define IRQ1_INT_MASK			BIT(4)
-#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
-#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
-#define IRQ0_FULL_INT_MASK		BIT(1)
-#define IRQ0_INT_MASK			BIT(0)
-
-#define TX_DONE_INT_MASK(_n)					\
-	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
-	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_TX_MASK						\
-	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
-	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
-
-#define INT_IDX0_MASK						\
-	(TX0_COHERENT_INT_MASK | TX1_COHERENT_INT_MASK |	\
-	 TX2_COHERENT_INT_MASK | TX3_COHERENT_INT_MASK |	\
-	 TX4_COHERENT_INT_MASK | TX5_COHERENT_INT_MASK |	\
-	 TX6_COHERENT_INT_MASK | TX7_COHERENT_INT_MASK |	\
-	 RX0_COHERENT_INT_MASK | RX1_COHERENT_INT_MASK |	\
-	 RX2_COHERENT_INT_MASK | RX3_COHERENT_INT_MASK |	\
-	 RX4_COHERENT_INT_MASK | RX7_COHERENT_INT_MASK |	\
-	 RX8_COHERENT_INT_MASK | RX9_COHERENT_INT_MASK |	\
-	 RX15_COHERENT_INT_MASK | INT_TX_MASK)
-
-/* QDMA_CSR_INT_ENABLE2 */
-#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
-#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
-#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
-#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
-#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
-#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
-#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
-#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
-#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
-#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
-#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
-#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
-#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
-#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
-#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
-#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
-#define RX15_DONE_INT_MASK		BIT(15)
-#define RX14_DONE_INT_MASK		BIT(14)
-#define RX13_DONE_INT_MASK		BIT(13)
-#define RX12_DONE_INT_MASK		BIT(12)
-#define RX11_DONE_INT_MASK		BIT(11)
-#define RX10_DONE_INT_MASK		BIT(10)
-#define RX9_DONE_INT_MASK		BIT(9)
-#define RX8_DONE_INT_MASK		BIT(8)
-#define RX7_DONE_INT_MASK		BIT(7)
-#define RX6_DONE_INT_MASK		BIT(6)
-#define RX5_DONE_INT_MASK		BIT(5)
-#define RX4_DONE_INT_MASK		BIT(4)
-#define RX3_DONE_INT_MASK		BIT(3)
-#define RX2_DONE_INT_MASK		BIT(2)
-#define RX1_DONE_INT_MASK		BIT(1)
-#define RX0_DONE_INT_MASK		BIT(0)
-
-#define RX_DONE_INT_MASK					\
-	(RX0_DONE_INT_MASK | RX1_DONE_INT_MASK |		\
-	 RX2_DONE_INT_MASK | RX3_DONE_INT_MASK |		\
-	 RX4_DONE_INT_MASK | RX7_DONE_INT_MASK |		\
-	 RX8_DONE_INT_MASK | RX9_DONE_INT_MASK |		\
-	 RX15_DONE_INT_MASK)
-#define INT_IDX1_MASK						\
-	(RX_DONE_INT_MASK |					\
-	 RX0_NO_CPU_DSCP_INT_MASK | RX1_NO_CPU_DSCP_INT_MASK |	\
-	 RX2_NO_CPU_DSCP_INT_MASK | RX3_NO_CPU_DSCP_INT_MASK |	\
-	 RX4_NO_CPU_DSCP_INT_MASK | RX7_NO_CPU_DSCP_INT_MASK |	\
-	 RX8_NO_CPU_DSCP_INT_MASK | RX9_NO_CPU_DSCP_INT_MASK |	\
-	 RX15_NO_CPU_DSCP_INT_MASK)
-
-/* QDMA_CSR_INT_ENABLE5 */
-#define TX31_COHERENT_INT_MASK		BIT(31)
-#define TX30_COHERENT_INT_MASK		BIT(30)
-#define TX29_COHERENT_INT_MASK		BIT(29)
-#define TX28_COHERENT_INT_MASK		BIT(28)
-#define TX27_COHERENT_INT_MASK		BIT(27)
-#define TX26_COHERENT_INT_MASK		BIT(26)
-#define TX25_COHERENT_INT_MASK		BIT(25)
-#define TX24_COHERENT_INT_MASK		BIT(24)
-#define TX23_COHERENT_INT_MASK		BIT(23)
-#define TX22_COHERENT_INT_MASK		BIT(22)
-#define TX21_COHERENT_INT_MASK		BIT(21)
-#define TX20_COHERENT_INT_MASK		BIT(20)
-#define TX19_COHERENT_INT_MASK		BIT(19)
-#define TX18_COHERENT_INT_MASK		BIT(18)
-#define TX17_COHERENT_INT_MASK		BIT(17)
-#define TX16_COHERENT_INT_MASK		BIT(16)
-#define TX15_COHERENT_INT_MASK		BIT(15)
-#define TX14_COHERENT_INT_MASK		BIT(14)
-#define TX13_COHERENT_INT_MASK		BIT(13)
-#define TX12_COHERENT_INT_MASK		BIT(12)
-#define TX11_COHERENT_INT_MASK		BIT(11)
-#define TX10_COHERENT_INT_MASK		BIT(10)
-#define TX9_COHERENT_INT_MASK		BIT(9)
-#define TX8_COHERENT_INT_MASK		BIT(8)
-
-#define INT_IDX4_MASK						\
-	(TX8_COHERENT_INT_MASK | TX9_COHERENT_INT_MASK |	\
-	 TX10_COHERENT_INT_MASK | TX11_COHERENT_INT_MASK |	\
-	 TX12_COHERENT_INT_MASK | TX13_COHERENT_INT_MASK |	\
-	 TX14_COHERENT_INT_MASK | TX15_COHERENT_INT_MASK |	\
-	 TX16_COHERENT_INT_MASK | TX17_COHERENT_INT_MASK |	\
-	 TX18_COHERENT_INT_MASK | TX19_COHERENT_INT_MASK |	\
-	 TX20_COHERENT_INT_MASK | TX21_COHERENT_INT_MASK |	\
-	 TX22_COHERENT_INT_MASK | TX23_COHERENT_INT_MASK |	\
-	 TX24_COHERENT_INT_MASK | TX25_COHERENT_INT_MASK |	\
-	 TX26_COHERENT_INT_MASK | TX27_COHERENT_INT_MASK |	\
-	 TX28_COHERENT_INT_MASK | TX29_COHERENT_INT_MASK |	\
-	 TX30_COHERENT_INT_MASK | TX31_COHERENT_INT_MASK)
-
-#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
-
-#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
-#define TX_IRQ_THR_MASK			GENMASK(27, 16)
-#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
-
-#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
-#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
-
-#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
-#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
-#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
-
-#define REG_TX_RING_BASE(_n)	\
-	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
-
-#define REG_TX_RING_BLOCKING(_n)	\
-	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
-
-#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
-#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
-#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
-#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
-#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
-
-#define REG_TX_CPU_IDX(_n)	\
-	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
-
-#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_TX_DMA_IDX(_n)	\
-	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
-
-#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
-#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_RING_BASE(_n)	\
-	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
-
-#define REG_RX_RING_SIZE(_n)	\
-	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
-
-#define RX_RING_THR_MASK		GENMASK(31, 16)
-#define RX_RING_SIZE_MASK		GENMASK(15, 0)
-
-#define REG_RX_CPU_IDX(_n)	\
-	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
-
-#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
-
-#define REG_RX_DMA_IDX(_n)	\
-	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
-
-#define REG_RX_DELAY_INT_IDX(_n)	\
-	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
-
-#define RX_DELAY_INT_MASK		GENMASK(15, 0)
-
-#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
-
-#define REG_INGRESS_TRTCM_CFG		0x0070
-#define INGRESS_TRTCM_EN_MASK		BIT(31)
-#define INGRESS_TRTCM_MODE_MASK		BIT(30)
-#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_QUEUE_CLOSE_CFG(_n)		(0x00a0 + ((_n) & 0xfc))
-#define TXQ_DISABLE_CHAN_QUEUE_MASK(_n, _m)	BIT((_m) + (((_n) & 0x3) << 3))
-
-#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
-#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
-
-#define REG_CNTR_CFG(_n)		(0x0400 + ((_n) << 3))
-#define CNTR_EN_MASK			BIT(31)
-#define CNTR_ALL_CHAN_EN_MASK		BIT(30)
-#define CNTR_ALL_QUEUE_EN_MASK		BIT(29)
-#define CNTR_ALL_DSCP_RING_EN_MASK	BIT(28)
-#define CNTR_SRC_MASK			GENMASK(27, 24)
-#define CNTR_DSCP_RING_MASK		GENMASK(20, 16)
-#define CNTR_CHAN_MASK			GENMASK(7, 3)
-#define CNTR_QUEUE_MASK			GENMASK(2, 0)
-
-#define REG_CNTR_VAL(_n)		(0x0404 + ((_n) << 3))
-
-#define REG_LMGR_INIT_CFG		0x1000
-#define LMGR_INIT_START			BIT(31)
-#define LMGR_SRAM_MODE_MASK		BIT(30)
-#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
-#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
-
-#define REG_FWD_DSCP_LOW_THR		0x1004
-#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
-
-#define REG_EGRESS_RATE_METER_CFG		0x100c
-#define EGRESS_RATE_METER_EN_MASK		BIT(31)
-#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
-#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
-#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
-
-#define REG_EGRESS_TRTCM_CFG		0x1010
-#define EGRESS_TRTCM_EN_MASK		BIT(31)
-#define EGRESS_TRTCM_MODE_MASK		BIT(30)
-#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define TRTCM_PARAM_RW_MASK		BIT(31)
-#define TRTCM_PARAM_RW_DONE_MASK	BIT(30)
-#define TRTCM_PARAM_TYPE_MASK		GENMASK(29, 28)
-#define TRTCM_METER_GROUP_MASK		GENMASK(27, 26)
-#define TRTCM_PARAM_INDEX_MASK		GENMASK(23, 17)
-#define TRTCM_PARAM_RATE_TYPE_MASK	BIT(16)
-
-#define REG_TRTCM_CFG_PARAM(_n)		((_n) + 0x4)
-#define REG_TRTCM_DATA_LOW(_n)		((_n) + 0x8)
-#define REG_TRTCM_DATA_HIGH(_n)		((_n) + 0xc)
-
-#define REG_TXWRR_MODE_CFG		0x1020
-#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
-#define TWRR_WEIGHT_BASE_MASK		BIT(3)
-
-#define REG_TXWRR_WEIGHT_CFG		0x1024
-#define TWRR_RW_CMD_MASK		BIT(31)
-#define TWRR_RW_CMD_DONE		BIT(30)
-#define TWRR_CHAN_IDX_MASK		GENMASK(23, 19)
-#define TWRR_QUEUE_IDX_MASK		GENMASK(18, 16)
-#define TWRR_VALUE_MASK			GENMASK(15, 0)
-
-#define REG_PSE_BUF_USAGE_CFG		0x1028
-#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
-
-#define REG_CHAN_QOS_MODE(_n)		(0x1040 + ((_n) << 2))
-#define CHAN_QOS_MODE_MASK(_n)		GENMASK(2 + ((_n) << 2), (_n) << 2)
-
-#define REG_GLB_TRTCM_CFG		0x1080
-#define GLB_TRTCM_EN_MASK		BIT(31)
-#define GLB_TRTCM_MODE_MASK		BIT(30)
-#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
-
-#define REG_TXQ_CNGST_CFG		0x10a0
-#define TXQ_CNGST_DROP_EN		BIT(31)
-#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
-
-#define REG_SLA_TRTCM_CFG		0x1150
-#define SLA_TRTCM_EN_MASK		BIT(31)
-#define SLA_TRTCM_MODE_MASK		BIT(30)
-#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
-#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
-
-/* CTRL */
-#define QDMA_DESC_DONE_MASK		BIT(31)
-#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
-#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
-#define QDMA_DESC_DEI_MASK		BIT(25)
-#define QDMA_DESC_NO_DROP_MASK		BIT(24)
-#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
-/* DATA */
-#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
-/* TX MSG0 */
-#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
-#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
-#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
-#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
-#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
-#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
-#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
-#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
-/* TX MSG1 */
-#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
-#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
-#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
-#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
-#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
-#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
-#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
-#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
-#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
-
-/* RX MSG1 */
-#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
-#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
-#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
-#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
-#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
-#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
-#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
-#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
-#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
-
-struct airoha_qdma_desc {
-	__le32 rsv;
-	__le32 ctrl;
-	__le32 addr;
-	__le32 data;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 msg2;
-	__le32 msg3;
-};
-
-/* CTRL0 */
-#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
-#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
-#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
-#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
-/* CTRL1 */
-#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
-/* CTRL2 */
-#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
-
-struct airoha_qdma_fwd_desc {
-	__le32 addr;
-	__le32 ctrl0;
-	__le32 ctrl1;
-	__le32 ctrl2;
-	__le32 msg0;
-	__le32 msg1;
-	__le32 rsv0;
-	__le32 rsv1;
-};
-
 u32 airoha_rr(void __iomem *base, u32 offset)
 {
 	return readl(base + offset);
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
new file mode 100644
index 0000000000000..7c9dadb348834
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -0,0 +1,670 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#ifndef AIROHA_REGS_H
+#define AIROHA_REGS_H
+
+#include <linux/types.h>
+
+/* FE */
+#define PSE_BASE			0x0100
+#define CSR_IFC_BASE			0x0200
+#define CDM1_BASE			0x0400
+#define GDM1_BASE			0x0500
+#define PPE1_BASE			0x0c00
+
+#define CDM2_BASE			0x1400
+#define GDM2_BASE			0x1500
+
+#define GDM3_BASE			0x1100
+#define GDM4_BASE			0x2500
+
+#define GDM_BASE(_n)			\
+	((_n) == 4 ? GDM4_BASE :	\
+	 (_n) == 3 ? GDM3_BASE :	\
+	 (_n) == 2 ? GDM2_BASE : GDM1_BASE)
+
+#define REG_FE_DMA_GLO_CFG		0x0000
+#define FE_DMA_GLO_L2_SPACE_MASK	GENMASK(7, 4)
+#define FE_DMA_GLO_PG_SZ_MASK		BIT(3)
+
+#define REG_FE_RST_GLO_CFG		0x0004
+#define FE_RST_GDM4_MBI_ARB_MASK	BIT(3)
+#define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
+#define FE_RST_CORE_MASK		BIT(0)
+
+#define REG_FE_WAN_MAC_H		0x0030
+#define REG_FE_LAN_MAC_H		0x0040
+
+#define REG_FE_MAC_LMIN(_n)		((_n) + 0x04)
+#define REG_FE_MAC_LMAX(_n)		((_n) + 0x08)
+
+#define REG_FE_CDM1_OQ_MAP0		0x0050
+#define REG_FE_CDM1_OQ_MAP1		0x0054
+#define REG_FE_CDM1_OQ_MAP2		0x0058
+#define REG_FE_CDM1_OQ_MAP3		0x005c
+
+#define REG_FE_PCE_CFG			0x0070
+#define PCE_DPI_EN_MASK			BIT(2)
+#define PCE_KA_EN_MASK			BIT(1)
+#define PCE_MC_EN_MASK			BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_WR		0x0080
+#define PSE_CFG_PORT_ID_MASK		GENMASK(27, 24)
+#define PSE_CFG_QUEUE_ID_MASK		GENMASK(20, 16)
+#define PSE_CFG_WR_EN_MASK		BIT(8)
+#define PSE_CFG_OQRSV_SEL_MASK		BIT(0)
+
+#define REG_FE_PSE_QUEUE_CFG_VAL	0x0084
+#define PSE_CFG_OQ_RSV_MASK		GENMASK(13, 0)
+
+#define PSE_FQ_CFG			0x008c
+#define PSE_FQ_LIMIT_MASK		GENMASK(14, 0)
+
+#define REG_FE_PSE_BUF_SET		0x0090
+#define PSE_SHARE_USED_LTHD_MASK	GENMASK(31, 16)
+#define PSE_ALLRSV_MASK			GENMASK(14, 0)
+
+#define REG_PSE_SHARE_USED_THD		0x0094
+#define PSE_SHARE_USED_MTHD_MASK	GENMASK(31, 16)
+#define PSE_SHARE_USED_HTHD_MASK	GENMASK(15, 0)
+
+#define REG_GDM_MISC_CFG		0x0148
+#define GDM2_RDM_ACK_WAIT_PREF_MASK	BIT(9)
+#define GDM2_CHN_VLD_MODE_MASK		BIT(5)
+
+#define REG_FE_CSR_IFC_CFG		CSR_IFC_BASE
+#define FE_IFC_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PORT_EN		0x01f0
+#define REG_FE_IFC_PORT_EN		0x01f4
+
+#define REG_PSE_IQ_REV1			(PSE_BASE + 0x08)
+#define PSE_IQ_RES1_P2_MASK		GENMASK(23, 16)
+
+#define REG_PSE_IQ_REV2			(PSE_BASE + 0x0c)
+#define PSE_IQ_RES2_P5_MASK		GENMASK(15, 8)
+#define PSE_IQ_RES2_P4_MASK		GENMASK(7, 0)
+
+#define REG_FE_VIP_EN(_n)		(0x0300 + ((_n) << 3))
+#define PATN_FCPU_EN_MASK		BIT(7)
+#define PATN_SWP_EN_MASK		BIT(6)
+#define PATN_DP_EN_MASK			BIT(5)
+#define PATN_SP_EN_MASK			BIT(4)
+#define PATN_TYPE_MASK			GENMASK(3, 1)
+#define PATN_EN_MASK			BIT(0)
+
+#define REG_FE_VIP_PATN(_n)		(0x0304 + ((_n) << 3))
+#define PATN_DP_MASK			GENMASK(31, 16)
+#define PATN_SP_MASK			GENMASK(15, 0)
+
+#define REG_CDM1_VLAN_CTRL		CDM1_BASE
+#define CDM1_VLAN_MASK			GENMASK(31, 16)
+
+#define REG_CDM1_FWD_CFG		(CDM1_BASE + 0x08)
+#define CDM1_VIP_QSEL_MASK		GENMASK(24, 20)
+
+#define REG_CDM1_CRSN_QSEL(_n)		(CDM1_BASE + 0x10 + ((_n) << 2))
+#define CDM1_CRSN_QSEL_REASON_MASK(_n)	\
+	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
+
+#define REG_CDM2_FWD_CFG		(CDM2_BASE + 0x08)
+#define CDM2_OAM_QSEL_MASK		GENMASK(31, 27)
+#define CDM2_VIP_QSEL_MASK		GENMASK(24, 20)
+
+#define REG_CDM2_CRSN_QSEL(_n)		(CDM2_BASE + 0x10 + ((_n) << 2))
+#define CDM2_CRSN_QSEL_REASON_MASK(_n)	\
+	GENMASK(4 + (((_n) % 4) << 3),	(((_n) % 4) << 3))
+
+#define REG_GDM_FWD_CFG(_n)		GDM_BASE(_n)
+#define GDM_DROP_CRC_ERR		BIT(23)
+#define GDM_IP4_CKSUM			BIT(22)
+#define GDM_TCP_CKSUM			BIT(21)
+#define GDM_UDP_CKSUM			BIT(20)
+#define GDM_UCFQ_MASK			GENMASK(15, 12)
+#define GDM_BCFQ_MASK			GENMASK(11, 8)
+#define GDM_MCFQ_MASK			GENMASK(7, 4)
+#define GDM_OCFQ_MASK			GENMASK(3, 0)
+
+#define REG_GDM_INGRESS_CFG(_n)		(GDM_BASE(_n) + 0x10)
+#define GDM_INGRESS_FC_EN_MASK		BIT(1)
+#define GDM_STAG_EN_MASK		BIT(0)
+
+#define REG_GDM_LEN_CFG(_n)		(GDM_BASE(_n) + 0x14)
+#define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
+#define GDM_LONG_LEN_MASK		GENMASK(29, 16)
+
+#define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
+#define FE_CPORT_PAD			BIT(26)
+#define FE_CPORT_PORT_XFC_MASK		BIT(25)
+#define FE_CPORT_QUEUE_XFC_MASK		BIT(24)
+
+#define REG_FE_GDM_MIB_CLEAR(_n)	(GDM_BASE(_n) + 0xf0)
+#define FE_GDM_MIB_RX_CLEAR_MASK	BIT(1)
+#define FE_GDM_MIB_TX_CLEAR_MASK	BIT(0)
+
+#define REG_FE_GDM1_MIB_CFG		(GDM1_BASE + 0xf4)
+#define FE_STRICT_RFC2819_MODE_MASK	BIT(31)
+#define FE_GDM1_TX_MIB_SPLIT_EN_MASK	BIT(17)
+#define FE_GDM1_RX_MIB_SPLIT_EN_MASK	BIT(16)
+#define FE_TX_MIB_ID_MASK		GENMASK(15, 8)
+#define FE_RX_MIB_ID_MASK		GENMASK(7, 0)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x104)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x10c)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x110)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x114)
+#define REG_FE_GDM_TX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x118)
+#define REG_FE_GDM_TX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x11c)
+#define REG_FE_GDM_TX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x120)
+#define REG_FE_GDM_TX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x124)
+#define REG_FE_GDM_TX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x128)
+#define REG_FE_GDM_TX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x12c)
+#define REG_FE_GDM_TX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x130)
+#define REG_FE_GDM_TX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x134)
+#define REG_FE_GDM_TX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x138)
+#define REG_FE_GDM_TX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x13c)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x140)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x148)
+#define REG_FE_GDM_RX_FC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x14c)
+#define REG_FE_GDM_RX_RC_DROP_CNT(_n)		(GDM_BASE(_n) + 0x150)
+#define REG_FE_GDM_RX_OVERFLOW_DROP_CNT(_n)	(GDM_BASE(_n) + 0x154)
+#define REG_FE_GDM_RX_ERROR_DROP_CNT(_n)	(GDM_BASE(_n) + 0x158)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_L(_n)		(GDM_BASE(_n) + 0x15c)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_L(_n)		(GDM_BASE(_n) + 0x160)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_L(_n)	(GDM_BASE(_n) + 0x164)
+#define REG_FE_GDM_RX_ETH_DROP_CNT(_n)		(GDM_BASE(_n) + 0x168)
+#define REG_FE_GDM_RX_ETH_BC_CNT(_n)		(GDM_BASE(_n) + 0x16c)
+#define REG_FE_GDM_RX_ETH_MC_CNT(_n)		(GDM_BASE(_n) + 0x170)
+#define REG_FE_GDM_RX_ETH_CRC_ERR_CNT(_n)	(GDM_BASE(_n) + 0x174)
+#define REG_FE_GDM_RX_ETH_FRAG_CNT(_n)		(GDM_BASE(_n) + 0x178)
+#define REG_FE_GDM_RX_ETH_JABBER_CNT(_n)	(GDM_BASE(_n) + 0x17c)
+#define REG_FE_GDM_RX_ETH_RUNT_CNT(_n)		(GDM_BASE(_n) + 0x180)
+#define REG_FE_GDM_RX_ETH_LONG_CNT(_n)		(GDM_BASE(_n) + 0x184)
+#define REG_FE_GDM_RX_ETH_E64_CNT_L(_n)		(GDM_BASE(_n) + 0x188)
+#define REG_FE_GDM_RX_ETH_L64_CNT_L(_n)		(GDM_BASE(_n) + 0x18c)
+#define REG_FE_GDM_RX_ETH_L127_CNT_L(_n)	(GDM_BASE(_n) + 0x190)
+#define REG_FE_GDM_RX_ETH_L255_CNT_L(_n)	(GDM_BASE(_n) + 0x194)
+#define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
+
+#define REG_PPE1_TB_HASH_CFG		(PPE1_BASE + 0x250)
+#define PPE1_SRAM_TABLE_EN_MASK		BIT(0)
+#define PPE1_SRAM_HASH1_EN_MASK		BIT(8)
+#define PPE1_DRAM_TABLE_EN_MASK		BIT(16)
+#define PPE1_DRAM_HASH1_EN_MASK		BIT(24)
+
+#define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
+#define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)
+#define REG_FE_GDM_TX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x288)
+#define REG_FE_GDM_TX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x28c)
+
+#define REG_FE_GDM_RX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x290)
+#define REG_FE_GDM_RX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x294)
+#define REG_FE_GDM_RX_ETH_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x298)
+#define REG_FE_GDM_RX_ETH_BYTE_CNT_H(_n)	(GDM_BASE(_n) + 0x29c)
+#define REG_FE_GDM_TX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2b8)
+#define REG_FE_GDM_TX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2bc)
+#define REG_FE_GDM_TX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2c0)
+#define REG_FE_GDM_TX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2c4)
+#define REG_FE_GDM_TX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2c8)
+#define REG_FE_GDM_TX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2cc)
+#define REG_FE_GDM_RX_ETH_E64_CNT_H(_n)		(GDM_BASE(_n) + 0x2e8)
+#define REG_FE_GDM_RX_ETH_L64_CNT_H(_n)		(GDM_BASE(_n) + 0x2ec)
+#define REG_FE_GDM_RX_ETH_L127_CNT_H(_n)	(GDM_BASE(_n) + 0x2f0)
+#define REG_FE_GDM_RX_ETH_L255_CNT_H(_n)	(GDM_BASE(_n) + 0x2f4)
+#define REG_FE_GDM_RX_ETH_L511_CNT_H(_n)	(GDM_BASE(_n) + 0x2f8)
+#define REG_FE_GDM_RX_ETH_L1023_CNT_H(_n)	(GDM_BASE(_n) + 0x2fc)
+
+#define REG_GDM2_CHN_RLS		(GDM2_BASE + 0x20)
+#define MBI_RX_AGE_SEL_MASK		GENMASK(26, 25)
+#define MBI_TX_AGE_SEL_MASK		GENMASK(18, 17)
+
+#define REG_GDM3_FWD_CFG		GDM3_BASE
+#define GDM3_PAD_EN_MASK		BIT(28)
+
+#define REG_GDM4_FWD_CFG		GDM4_BASE
+#define GDM4_PAD_EN_MASK		BIT(28)
+#define GDM4_SPORT_OFFSET0_MASK		GENMASK(11, 8)
+
+#define REG_GDM4_SRC_PORT_SET		(GDM4_BASE + 0x23c)
+#define GDM4_SPORT_OFF2_MASK		GENMASK(19, 16)
+#define GDM4_SPORT_OFF1_MASK		GENMASK(15, 12)
+#define GDM4_SPORT_OFF0_MASK		GENMASK(11, 8)
+
+#define REG_IP_FRAG_FP			0x2010
+#define IP_ASSEMBLE_PORT_MASK		GENMASK(24, 21)
+#define IP_ASSEMBLE_NBQ_MASK		GENMASK(20, 16)
+#define IP_FRAGMENT_PORT_MASK		GENMASK(8, 5)
+#define IP_FRAGMENT_NBQ_MASK		GENMASK(4, 0)
+
+#define REG_MC_VLAN_EN			0x2100
+#define MC_VLAN_EN_MASK			BIT(0)
+
+#define REG_MC_VLAN_CFG			0x2104
+#define MC_VLAN_CFG_CMD_DONE_MASK	BIT(31)
+#define MC_VLAN_CFG_TABLE_ID_MASK	GENMASK(21, 16)
+#define MC_VLAN_CFG_PORT_ID_MASK	GENMASK(11, 8)
+#define MC_VLAN_CFG_TABLE_SEL_MASK	BIT(4)
+#define MC_VLAN_CFG_RW_MASK		BIT(0)
+
+#define REG_MC_VLAN_DATA		0x2108
+
+#define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
+
+/* QDMA */
+#define REG_QDMA_GLOBAL_CFG			0x0004
+#define GLOBAL_CFG_RX_2B_OFFSET_MASK		BIT(31)
+#define GLOBAL_CFG_DMA_PREFERENCE_MASK		GENMASK(30, 29)
+#define GLOBAL_CFG_CPU_TXR_RR_MASK		BIT(28)
+#define GLOBAL_CFG_DSCP_BYTE_SWAP_MASK		BIT(27)
+#define GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK	BIT(26)
+#define GLOBAL_CFG_MULTICAST_MODIFY_FP_MASK	BIT(25)
+#define GLOBAL_CFG_OAM_MODIFY_MASK		BIT(24)
+#define GLOBAL_CFG_RESET_MASK			BIT(23)
+#define GLOBAL_CFG_RESET_DONE_MASK		BIT(22)
+#define GLOBAL_CFG_MULTICAST_EN_MASK		BIT(21)
+#define GLOBAL_CFG_IRQ1_EN_MASK			BIT(20)
+#define GLOBAL_CFG_IRQ0_EN_MASK			BIT(19)
+#define GLOBAL_CFG_LOOPCNT_EN_MASK		BIT(18)
+#define GLOBAL_CFG_RD_BYPASS_WR_MASK		BIT(17)
+#define GLOBAL_CFG_QDMA_LOOPBACK_MASK		BIT(16)
+#define GLOBAL_CFG_LPBK_RXQ_SEL_MASK		GENMASK(13, 8)
+#define GLOBAL_CFG_CHECK_DONE_MASK		BIT(7)
+#define GLOBAL_CFG_TX_WB_DONE_MASK		BIT(6)
+#define GLOBAL_CFG_MAX_ISSUE_NUM_MASK		GENMASK(5, 4)
+#define GLOBAL_CFG_RX_DMA_BUSY_MASK		BIT(3)
+#define GLOBAL_CFG_RX_DMA_EN_MASK		BIT(2)
+#define GLOBAL_CFG_TX_DMA_BUSY_MASK		BIT(1)
+#define GLOBAL_CFG_TX_DMA_EN_MASK		BIT(0)
+
+#define REG_FWD_DSCP_BASE			0x0010
+#define REG_FWD_BUF_BASE			0x0014
+
+#define REG_HW_FWD_DSCP_CFG			0x0018
+#define HW_FWD_DSCP_PAYLOAD_SIZE_MASK		GENMASK(29, 28)
+#define HW_FWD_DSCP_SCATTER_LEN_MASK		GENMASK(17, 16)
+#define HW_FWD_DSCP_MIN_SCATTER_LEN_MASK	GENMASK(15, 0)
+
+#define REG_INT_STATUS(_n)		\
+	(((_n) == 4) ? 0x0730 :		\
+	 ((_n) == 3) ? 0x0724 :		\
+	 ((_n) == 2) ? 0x0720 :		\
+	 ((_n) == 1) ? 0x0024 : 0x0020)
+
+#define REG_INT_ENABLE(_n)		\
+	(((_n) == 4) ? 0x0750 :		\
+	 ((_n) == 3) ? 0x0744 :		\
+	 ((_n) == 2) ? 0x0740 :		\
+	 ((_n) == 1) ? 0x002c : 0x0028)
+
+/* QDMA_CSR_INT_ENABLE1 */
+#define RX15_COHERENT_INT_MASK		BIT(31)
+#define RX14_COHERENT_INT_MASK		BIT(30)
+#define RX13_COHERENT_INT_MASK		BIT(29)
+#define RX12_COHERENT_INT_MASK		BIT(28)
+#define RX11_COHERENT_INT_MASK		BIT(27)
+#define RX10_COHERENT_INT_MASK		BIT(26)
+#define RX9_COHERENT_INT_MASK		BIT(25)
+#define RX8_COHERENT_INT_MASK		BIT(24)
+#define RX7_COHERENT_INT_MASK		BIT(23)
+#define RX6_COHERENT_INT_MASK		BIT(22)
+#define RX5_COHERENT_INT_MASK		BIT(21)
+#define RX4_COHERENT_INT_MASK		BIT(20)
+#define RX3_COHERENT_INT_MASK		BIT(19)
+#define RX2_COHERENT_INT_MASK		BIT(18)
+#define RX1_COHERENT_INT_MASK		BIT(17)
+#define RX0_COHERENT_INT_MASK		BIT(16)
+#define TX7_COHERENT_INT_MASK		BIT(15)
+#define TX6_COHERENT_INT_MASK		BIT(14)
+#define TX5_COHERENT_INT_MASK		BIT(13)
+#define TX4_COHERENT_INT_MASK		BIT(12)
+#define TX3_COHERENT_INT_MASK		BIT(11)
+#define TX2_COHERENT_INT_MASK		BIT(10)
+#define TX1_COHERENT_INT_MASK		BIT(9)
+#define TX0_COHERENT_INT_MASK		BIT(8)
+#define CNT_OVER_FLOW_INT_MASK		BIT(7)
+#define IRQ1_FULL_INT_MASK		BIT(5)
+#define IRQ1_INT_MASK			BIT(4)
+#define HWFWD_DSCP_LOW_INT_MASK		BIT(3)
+#define HWFWD_DSCP_EMPTY_INT_MASK	BIT(2)
+#define IRQ0_FULL_INT_MASK		BIT(1)
+#define IRQ0_INT_MASK			BIT(0)
+
+#define TX_DONE_INT_MASK(_n)					\
+	((_n) ? IRQ1_INT_MASK | IRQ1_FULL_INT_MASK		\
+	      : IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+#define INT_TX_MASK						\
+	(IRQ1_INT_MASK | IRQ1_FULL_INT_MASK |			\
+	 IRQ0_INT_MASK | IRQ0_FULL_INT_MASK)
+
+#define INT_IDX0_MASK						\
+	(TX0_COHERENT_INT_MASK | TX1_COHERENT_INT_MASK |	\
+	 TX2_COHERENT_INT_MASK | TX3_COHERENT_INT_MASK |	\
+	 TX4_COHERENT_INT_MASK | TX5_COHERENT_INT_MASK |	\
+	 TX6_COHERENT_INT_MASK | TX7_COHERENT_INT_MASK |	\
+	 RX0_COHERENT_INT_MASK | RX1_COHERENT_INT_MASK |	\
+	 RX2_COHERENT_INT_MASK | RX3_COHERENT_INT_MASK |	\
+	 RX4_COHERENT_INT_MASK | RX7_COHERENT_INT_MASK |	\
+	 RX8_COHERENT_INT_MASK | RX9_COHERENT_INT_MASK |	\
+	 RX15_COHERENT_INT_MASK | INT_TX_MASK)
+
+/* QDMA_CSR_INT_ENABLE2 */
+#define RX15_NO_CPU_DSCP_INT_MASK	BIT(31)
+#define RX14_NO_CPU_DSCP_INT_MASK	BIT(30)
+#define RX13_NO_CPU_DSCP_INT_MASK	BIT(29)
+#define RX12_NO_CPU_DSCP_INT_MASK	BIT(28)
+#define RX11_NO_CPU_DSCP_INT_MASK	BIT(27)
+#define RX10_NO_CPU_DSCP_INT_MASK	BIT(26)
+#define RX9_NO_CPU_DSCP_INT_MASK	BIT(25)
+#define RX8_NO_CPU_DSCP_INT_MASK	BIT(24)
+#define RX7_NO_CPU_DSCP_INT_MASK	BIT(23)
+#define RX6_NO_CPU_DSCP_INT_MASK	BIT(22)
+#define RX5_NO_CPU_DSCP_INT_MASK	BIT(21)
+#define RX4_NO_CPU_DSCP_INT_MASK	BIT(20)
+#define RX3_NO_CPU_DSCP_INT_MASK	BIT(19)
+#define RX2_NO_CPU_DSCP_INT_MASK	BIT(18)
+#define RX1_NO_CPU_DSCP_INT_MASK	BIT(17)
+#define RX0_NO_CPU_DSCP_INT_MASK	BIT(16)
+#define RX15_DONE_INT_MASK		BIT(15)
+#define RX14_DONE_INT_MASK		BIT(14)
+#define RX13_DONE_INT_MASK		BIT(13)
+#define RX12_DONE_INT_MASK		BIT(12)
+#define RX11_DONE_INT_MASK		BIT(11)
+#define RX10_DONE_INT_MASK		BIT(10)
+#define RX9_DONE_INT_MASK		BIT(9)
+#define RX8_DONE_INT_MASK		BIT(8)
+#define RX7_DONE_INT_MASK		BIT(7)
+#define RX6_DONE_INT_MASK		BIT(6)
+#define RX5_DONE_INT_MASK		BIT(5)
+#define RX4_DONE_INT_MASK		BIT(4)
+#define RX3_DONE_INT_MASK		BIT(3)
+#define RX2_DONE_INT_MASK		BIT(2)
+#define RX1_DONE_INT_MASK		BIT(1)
+#define RX0_DONE_INT_MASK		BIT(0)
+
+#define RX_DONE_INT_MASK					\
+	(RX0_DONE_INT_MASK | RX1_DONE_INT_MASK |		\
+	 RX2_DONE_INT_MASK | RX3_DONE_INT_MASK |		\
+	 RX4_DONE_INT_MASK | RX7_DONE_INT_MASK |		\
+	 RX8_DONE_INT_MASK | RX9_DONE_INT_MASK |		\
+	 RX15_DONE_INT_MASK)
+#define INT_IDX1_MASK						\
+	(RX_DONE_INT_MASK |					\
+	 RX0_NO_CPU_DSCP_INT_MASK | RX1_NO_CPU_DSCP_INT_MASK |	\
+	 RX2_NO_CPU_DSCP_INT_MASK | RX3_NO_CPU_DSCP_INT_MASK |	\
+	 RX4_NO_CPU_DSCP_INT_MASK | RX7_NO_CPU_DSCP_INT_MASK |	\
+	 RX8_NO_CPU_DSCP_INT_MASK | RX9_NO_CPU_DSCP_INT_MASK |	\
+	 RX15_NO_CPU_DSCP_INT_MASK)
+
+/* QDMA_CSR_INT_ENABLE5 */
+#define TX31_COHERENT_INT_MASK		BIT(31)
+#define TX30_COHERENT_INT_MASK		BIT(30)
+#define TX29_COHERENT_INT_MASK		BIT(29)
+#define TX28_COHERENT_INT_MASK		BIT(28)
+#define TX27_COHERENT_INT_MASK		BIT(27)
+#define TX26_COHERENT_INT_MASK		BIT(26)
+#define TX25_COHERENT_INT_MASK		BIT(25)
+#define TX24_COHERENT_INT_MASK		BIT(24)
+#define TX23_COHERENT_INT_MASK		BIT(23)
+#define TX22_COHERENT_INT_MASK		BIT(22)
+#define TX21_COHERENT_INT_MASK		BIT(21)
+#define TX20_COHERENT_INT_MASK		BIT(20)
+#define TX19_COHERENT_INT_MASK		BIT(19)
+#define TX18_COHERENT_INT_MASK		BIT(18)
+#define TX17_COHERENT_INT_MASK		BIT(17)
+#define TX16_COHERENT_INT_MASK		BIT(16)
+#define TX15_COHERENT_INT_MASK		BIT(15)
+#define TX14_COHERENT_INT_MASK		BIT(14)
+#define TX13_COHERENT_INT_MASK		BIT(13)
+#define TX12_COHERENT_INT_MASK		BIT(12)
+#define TX11_COHERENT_INT_MASK		BIT(11)
+#define TX10_COHERENT_INT_MASK		BIT(10)
+#define TX9_COHERENT_INT_MASK		BIT(9)
+#define TX8_COHERENT_INT_MASK		BIT(8)
+
+#define INT_IDX4_MASK						\
+	(TX8_COHERENT_INT_MASK | TX9_COHERENT_INT_MASK |	\
+	 TX10_COHERENT_INT_MASK | TX11_COHERENT_INT_MASK |	\
+	 TX12_COHERENT_INT_MASK | TX13_COHERENT_INT_MASK |	\
+	 TX14_COHERENT_INT_MASK | TX15_COHERENT_INT_MASK |	\
+	 TX16_COHERENT_INT_MASK | TX17_COHERENT_INT_MASK |	\
+	 TX18_COHERENT_INT_MASK | TX19_COHERENT_INT_MASK |	\
+	 TX20_COHERENT_INT_MASK | TX21_COHERENT_INT_MASK |	\
+	 TX22_COHERENT_INT_MASK | TX23_COHERENT_INT_MASK |	\
+	 TX24_COHERENT_INT_MASK | TX25_COHERENT_INT_MASK |	\
+	 TX26_COHERENT_INT_MASK | TX27_COHERENT_INT_MASK |	\
+	 TX28_COHERENT_INT_MASK | TX29_COHERENT_INT_MASK |	\
+	 TX30_COHERENT_INT_MASK | TX31_COHERENT_INT_MASK)
+
+#define REG_TX_IRQ_BASE(_n)		((_n) ? 0x0048 : 0x0050)
+
+#define REG_TX_IRQ_CFG(_n)		((_n) ? 0x004c : 0x0054)
+#define TX_IRQ_THR_MASK			GENMASK(27, 16)
+#define TX_IRQ_DEPTH_MASK		GENMASK(11, 0)
+
+#define REG_IRQ_CLEAR_LEN(_n)		((_n) ? 0x0064 : 0x0058)
+#define IRQ_CLEAR_LEN_MASK		GENMASK(7, 0)
+
+#define REG_IRQ_STATUS(_n)		((_n) ? 0x0068 : 0x005c)
+#define IRQ_ENTRY_LEN_MASK		GENMASK(27, 16)
+#define IRQ_HEAD_IDX_MASK		GENMASK(11, 0)
+
+#define REG_TX_RING_BASE(_n)	\
+	(((_n) < 8) ? 0x0100 + ((_n) << 5) : 0x0b00 + (((_n) - 8) << 5))
+
+#define REG_TX_RING_BLOCKING(_n)	\
+	(((_n) < 8) ? 0x0104 + ((_n) << 5) : 0x0b04 + (((_n) - 8) << 5))
+
+#define TX_RING_IRQ_BLOCKING_MAP_MASK			BIT(6)
+#define TX_RING_IRQ_BLOCKING_CFG_MASK			BIT(4)
+#define TX_RING_IRQ_BLOCKING_TX_DROP_EN_MASK		BIT(2)
+#define TX_RING_IRQ_BLOCKING_MAX_TH_TXRING_EN_MASK	BIT(1)
+#define TX_RING_IRQ_BLOCKING_MIN_TH_TXRING_EN_MASK	BIT(0)
+
+#define REG_TX_CPU_IDX(_n)	\
+	(((_n) < 8) ? 0x0108 + ((_n) << 5) : 0x0b08 + (((_n) - 8) << 5))
+
+#define TX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_TX_DMA_IDX(_n)	\
+	(((_n) < 8) ? 0x010c + ((_n) << 5) : 0x0b0c + (((_n) - 8) << 5))
+
+#define TX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define IRQ_RING_IDX_MASK		GENMASK(20, 16)
+#define IRQ_DESC_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_RING_BASE(_n)	\
+	(((_n) < 16) ? 0x0200 + ((_n) << 5) : 0x0e00 + (((_n) - 16) << 5))
+
+#define REG_RX_RING_SIZE(_n)	\
+	(((_n) < 16) ? 0x0204 + ((_n) << 5) : 0x0e04 + (((_n) - 16) << 5))
+
+#define RX_RING_THR_MASK		GENMASK(31, 16)
+#define RX_RING_SIZE_MASK		GENMASK(15, 0)
+
+#define REG_RX_CPU_IDX(_n)	\
+	(((_n) < 16) ? 0x0208 + ((_n) << 5) : 0x0e08 + (((_n) - 16) << 5))
+
+#define RX_RING_CPU_IDX_MASK		GENMASK(15, 0)
+
+#define REG_RX_DMA_IDX(_n)	\
+	(((_n) < 16) ? 0x020c + ((_n) << 5) : 0x0e0c + (((_n) - 16) << 5))
+
+#define REG_RX_DELAY_INT_IDX(_n)	\
+	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
+
+#define RX_DELAY_INT_MASK		GENMASK(15, 0)
+
+#define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
+
+#define REG_INGRESS_TRTCM_CFG		0x0070
+#define INGRESS_TRTCM_EN_MASK		BIT(31)
+#define INGRESS_TRTCM_MODE_MASK		BIT(30)
+#define INGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define INGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_QUEUE_CLOSE_CFG(_n)		(0x00a0 + ((_n) & 0xfc))
+#define TXQ_DISABLE_CHAN_QUEUE_MASK(_n, _m)	BIT((_m) + (((_n) & 0x3) << 3))
+
+#define REG_TXQ_DIS_CFG_BASE(_n)	((_n) ? 0x20a0 : 0x00a0)
+#define REG_TXQ_DIS_CFG(_n, _m)		(REG_TXQ_DIS_CFG_BASE((_n)) + (_m) << 2)
+
+#define REG_CNTR_CFG(_n)		(0x0400 + ((_n) << 3))
+#define CNTR_EN_MASK			BIT(31)
+#define CNTR_ALL_CHAN_EN_MASK		BIT(30)
+#define CNTR_ALL_QUEUE_EN_MASK		BIT(29)
+#define CNTR_ALL_DSCP_RING_EN_MASK	BIT(28)
+#define CNTR_SRC_MASK			GENMASK(27, 24)
+#define CNTR_DSCP_RING_MASK		GENMASK(20, 16)
+#define CNTR_CHAN_MASK			GENMASK(7, 3)
+#define CNTR_QUEUE_MASK			GENMASK(2, 0)
+
+#define REG_CNTR_VAL(_n)		(0x0404 + ((_n) << 3))
+
+#define REG_LMGR_INIT_CFG		0x1000
+#define LMGR_INIT_START			BIT(31)
+#define LMGR_SRAM_MODE_MASK		BIT(30)
+#define HW_FWD_PKTSIZE_OVERHEAD_MASK	GENMASK(27, 20)
+#define HW_FWD_DESC_NUM_MASK		GENMASK(16, 0)
+
+#define REG_FWD_DSCP_LOW_THR		0x1004
+#define FWD_DSCP_LOW_THR_MASK		GENMASK(17, 0)
+
+#define REG_EGRESS_RATE_METER_CFG		0x100c
+#define EGRESS_RATE_METER_EN_MASK		BIT(31)
+#define EGRESS_RATE_METER_EQ_RATE_EN_MASK	BIT(17)
+#define EGRESS_RATE_METER_WINDOW_SZ_MASK	GENMASK(16, 12)
+#define EGRESS_RATE_METER_TIMESLICE_MASK	GENMASK(10, 0)
+
+#define REG_EGRESS_TRTCM_CFG		0x1010
+#define EGRESS_TRTCM_EN_MASK		BIT(31)
+#define EGRESS_TRTCM_MODE_MASK		BIT(30)
+#define EGRESS_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define EGRESS_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define TRTCM_PARAM_RW_MASK		BIT(31)
+#define TRTCM_PARAM_RW_DONE_MASK	BIT(30)
+#define TRTCM_PARAM_TYPE_MASK		GENMASK(29, 28)
+#define TRTCM_METER_GROUP_MASK		GENMASK(27, 26)
+#define TRTCM_PARAM_INDEX_MASK		GENMASK(23, 17)
+#define TRTCM_PARAM_RATE_TYPE_MASK	BIT(16)
+
+#define REG_TRTCM_CFG_PARAM(_n)		((_n) + 0x4)
+#define REG_TRTCM_DATA_LOW(_n)		((_n) + 0x8)
+#define REG_TRTCM_DATA_HIGH(_n)		((_n) + 0xc)
+
+#define REG_TXWRR_MODE_CFG		0x1020
+#define TWRR_WEIGHT_SCALE_MASK		BIT(31)
+#define TWRR_WEIGHT_BASE_MASK		BIT(3)
+
+#define REG_TXWRR_WEIGHT_CFG		0x1024
+#define TWRR_RW_CMD_MASK		BIT(31)
+#define TWRR_RW_CMD_DONE		BIT(30)
+#define TWRR_CHAN_IDX_MASK		GENMASK(23, 19)
+#define TWRR_QUEUE_IDX_MASK		GENMASK(18, 16)
+#define TWRR_VALUE_MASK			GENMASK(15, 0)
+
+#define REG_PSE_BUF_USAGE_CFG		0x1028
+#define PSE_BUF_ESTIMATE_EN_MASK	BIT(29)
+
+#define REG_CHAN_QOS_MODE(_n)		(0x1040 + ((_n) << 2))
+#define CHAN_QOS_MODE_MASK(_n)		GENMASK(2 + ((_n) << 2), (_n) << 2)
+
+#define REG_GLB_TRTCM_CFG		0x1080
+#define GLB_TRTCM_EN_MASK		BIT(31)
+#define GLB_TRTCM_MODE_MASK		BIT(30)
+#define GLB_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define GLB_FAST_TICK_MASK		GENMASK(15, 0)
+
+#define REG_TXQ_CNGST_CFG		0x10a0
+#define TXQ_CNGST_DROP_EN		BIT(31)
+#define TXQ_CNGST_DEI_DROP_EN		BIT(30)
+
+#define REG_SLA_TRTCM_CFG		0x1150
+#define SLA_TRTCM_EN_MASK		BIT(31)
+#define SLA_TRTCM_MODE_MASK		BIT(30)
+#define SLA_SLOW_TICK_RATIO_MASK	GENMASK(29, 16)
+#define SLA_FAST_TICK_MASK		GENMASK(15, 0)
+
+/* CTRL */
+#define QDMA_DESC_DONE_MASK		BIT(31)
+#define QDMA_DESC_DROP_MASK		BIT(30) /* tx: drop - rx: overflow */
+#define QDMA_DESC_MORE_MASK		BIT(29) /* more SG elements */
+#define QDMA_DESC_DEI_MASK		BIT(25)
+#define QDMA_DESC_NO_DROP_MASK		BIT(24)
+#define QDMA_DESC_LEN_MASK		GENMASK(15, 0)
+/* DATA */
+#define QDMA_DESC_NEXT_ID_MASK		GENMASK(15, 0)
+/* TX MSG0 */
+#define QDMA_ETH_TXMSG_MIC_IDX_MASK	BIT(30)
+#define QDMA_ETH_TXMSG_SP_TAG_MASK	GENMASK(29, 14)
+#define QDMA_ETH_TXMSG_ICO_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_UCO_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_TCO_MASK		BIT(11)
+#define QDMA_ETH_TXMSG_TSO_MASK		BIT(10)
+#define QDMA_ETH_TXMSG_FAST_MASK	BIT(9)
+#define QDMA_ETH_TXMSG_OAM_MASK		BIT(8)
+#define QDMA_ETH_TXMSG_CHAN_MASK	GENMASK(7, 3)
+#define QDMA_ETH_TXMSG_QUEUE_MASK	GENMASK(2, 0)
+/* TX MSG1 */
+#define QDMA_ETH_TXMSG_NO_DROP		BIT(31)
+#define QDMA_ETH_TXMSG_METER_MASK	GENMASK(30, 24)	/* 0x7f no meters */
+#define QDMA_ETH_TXMSG_FPORT_MASK	GENMASK(23, 20)
+#define QDMA_ETH_TXMSG_NBOQ_MASK	GENMASK(19, 15)
+#define QDMA_ETH_TXMSG_HWF_MASK		BIT(14)
+#define QDMA_ETH_TXMSG_HOP_MASK		BIT(13)
+#define QDMA_ETH_TXMSG_PTP_MASK		BIT(12)
+#define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
+#define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
+
+/* RX MSG1 */
+#define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
+#define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)
+#define QDMA_ETH_RXMSG_IP4_MASK		BIT(29)
+#define QDMA_ETH_RXMSG_IP4F_MASK	BIT(28)
+#define QDMA_ETH_RXMSG_L4_VALID_MASK	BIT(27)
+#define QDMA_ETH_RXMSG_L4F_MASK		BIT(26)
+#define QDMA_ETH_RXMSG_SPORT_MASK	GENMASK(25, 21)
+#define QDMA_ETH_RXMSG_CRSN_MASK	GENMASK(20, 16)
+#define QDMA_ETH_RXMSG_PPE_ENTRY_MASK	GENMASK(15, 0)
+
+struct airoha_qdma_desc {
+	__le32 rsv;
+	__le32 ctrl;
+	__le32 addr;
+	__le32 data;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 msg2;
+	__le32 msg3;
+};
+
+/* CTRL0 */
+#define QDMA_FWD_DESC_CTX_MASK		BIT(31)
+#define QDMA_FWD_DESC_RING_MASK		GENMASK(30, 28)
+#define QDMA_FWD_DESC_IDX_MASK		GENMASK(27, 16)
+#define QDMA_FWD_DESC_LEN_MASK		GENMASK(15, 0)
+/* CTRL1 */
+#define QDMA_FWD_DESC_FIRST_IDX_MASK	GENMASK(15, 0)
+/* CTRL2 */
+#define QDMA_FWD_DESC_MORE_PKT_NUM_MASK	GENMASK(2, 0)
+
+struct airoha_qdma_fwd_desc {
+	__le32 addr;
+	__le32 ctrl0;
+	__le32 ctrl1;
+	__le32 ctrl2;
+	__le32 msg0;
+	__le32 msg1;
+	__le32 rsv0;
+	__le32 rsv1;
+};
+
+#endif /* AIROHA_REGS_H */

From af3cf757d5c99011b9b94ea8d78aeaccc0153fdc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:13 +0100
Subject: [PATCH 1487/2753] net: airoha: Move DSA tag in DMA descriptor

Packet Processor Engine (PPE) module reads DSA tags from the DMA descriptor
and requires untagged DSA packets to properly parse them. Move DSA tag
in the DMA descriptor on TX side and read DSA tag from DMA descriptor
on RX side. In order to avoid skb reallocation, store tag in skb_dst on
RX side.
This is a preliminary patch to enable netfilter flowtable hw offloading
on EN7581 SoC.

Tested-by: Sayantan Nandy <sayantan.nandy@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c  | 125 ++++++++++++++++++++--
 drivers/net/ethernet/airoha/airoha_eth.h  |   7 ++
 drivers/net/ethernet/airoha/airoha_regs.h |   2 +
 3 files changed, 128 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index b79556f1b4951..347fc403f2998 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -9,6 +9,7 @@
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
 #include <net/dsa.h>
+#include <net/dst_metadata.h>
 #include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
 #include <uapi/linux/ppp_defs.h>
@@ -656,6 +657,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
 		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
+		struct airoha_gdm_port *port;
 		struct sk_buff *skb;
 		int len, p;
 
@@ -683,6 +685,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 			continue;
 		}
 
+		port = eth->ports[p];
 		skb = napi_build_skb(e->buf, q->buf_size);
 		if (!skb) {
 			page_pool_put_full_page(q->page_pool,
@@ -694,10 +697,26 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		skb_reserve(skb, 2);
 		__skb_put(skb, len);
 		skb_mark_for_recycle(skb);
-		skb->dev = eth->ports[p]->dev;
+		skb->dev = port->dev;
 		skb->protocol = eth_type_trans(skb, skb->dev);
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 		skb_record_rx_queue(skb, qid);
+
+		if (netdev_uses_dsa(port->dev)) {
+			/* PPE module requires untagged packets to work
+			 * properly and it provides DSA port index via the
+			 * DMA descriptor. Report DSA tag to the DSA stack
+			 * via skb dst info.
+			 */
+			u32 sptag = FIELD_GET(QDMA_ETH_RXMSG_SPTAG,
+					      le32_to_cpu(desc->msg0));
+
+			if (sptag < ARRAY_SIZE(port->dsa_meta) &&
+			    port->dsa_meta[sptag])
+				skb_dst_set_noref(skb,
+						  &port->dsa_meta[sptag]->dst);
+		}
+
 		napi_gro_receive(&q->napi, skb);
 
 		done++;
@@ -1636,25 +1655,76 @@ static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
 	return queue < dev->num_tx_queues ? queue : 0;
 }
 
+static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct ethhdr *ehdr;
+	struct dsa_port *dp;
+	u8 xmit_tpid;
+	u16 tag;
+
+	if (!netdev_uses_dsa(dev))
+		return 0;
+
+	dp = dev->dsa_ptr;
+	if (IS_ERR(dp))
+		return 0;
+
+	if (dp->tag_ops->proto != DSA_TAG_PROTO_MTK)
+		return 0;
+
+	if (skb_cow_head(skb, 0))
+		return 0;
+
+	ehdr = (struct ethhdr *)skb->data;
+	tag = be16_to_cpu(ehdr->h_proto);
+	xmit_tpid = tag >> 8;
+
+	switch (xmit_tpid) {
+	case MTK_HDR_XMIT_TAGGED_TPID_8100:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021Q);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_8100 << 8);
+		break;
+	case MTK_HDR_XMIT_TAGGED_TPID_88A8:
+		ehdr->h_proto = cpu_to_be16(ETH_P_8021AD);
+		tag &= ~(MTK_HDR_XMIT_TAGGED_TPID_88A8 << 8);
+		break;
+	default:
+		/* PPE module requires untagged DSA packets to work properly,
+		 * so move DSA tag to DMA descriptor.
+		 */
+		memmove(skb->data + MTK_HDR_LEN, skb->data, 2 * ETH_ALEN);
+		__skb_pull(skb, MTK_HDR_LEN);
+		break;
+	}
+
+	return tag;
+#else
+	return 0;
+#endif
+}
+
 static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 				   struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
-	u32 nr_frags = 1 + skb_shinfo(skb)->nr_frags;
-	u32 msg0, msg1, len = skb_headlen(skb);
 	struct airoha_qdma *qdma = port->qdma;
+	u32 nr_frags, tag, msg0, msg1, len;
 	struct netdev_queue *txq;
 	struct airoha_queue *q;
-	void *data = skb->data;
+	void *data;
 	int i, qid;
 	u16 index;
 	u8 fport;
 
 	qid = skb_get_queue_mapping(skb) % ARRAY_SIZE(qdma->q_tx);
+	tag = airoha_get_dsa_tag(skb, dev);
+
 	msg0 = FIELD_PREP(QDMA_ETH_TXMSG_CHAN_MASK,
 			  qid / AIROHA_NUM_QOS_QUEUES) |
 	       FIELD_PREP(QDMA_ETH_TXMSG_QUEUE_MASK,
-			  qid % AIROHA_NUM_QOS_QUEUES);
+			  qid % AIROHA_NUM_QOS_QUEUES) |
+	       FIELD_PREP(QDMA_ETH_TXMSG_SP_TAG_MASK, tag);
 	if (skb->ip_summed == CHECKSUM_PARTIAL)
 		msg0 |= FIELD_PREP(QDMA_ETH_TXMSG_TCO_MASK, 1) |
 			FIELD_PREP(QDMA_ETH_TXMSG_UCO_MASK, 1) |
@@ -1685,6 +1755,8 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 	spin_lock_bh(&q->lock);
 
 	txq = netdev_get_tx_queue(dev, qid);
+	nr_frags = 1 + skb_shinfo(skb)->nr_frags;
+
 	if (q->queued + nr_frags > q->ndesc) {
 		/* not enough space in the queue */
 		netif_tx_stop_queue(txq);
@@ -1692,7 +1764,10 @@ static netdev_tx_t airoha_dev_xmit(struct sk_buff *skb,
 		return NETDEV_TX_BUSY;
 	}
 
+	len = skb_headlen(skb);
+	data = skb->data;
 	index = q->head;
+
 	for (i = 0; i < nr_frags; i++) {
 		struct airoha_qdma_desc *desc = &q->desc[index];
 		struct airoha_queue_entry *e = &q->entry[index];
@@ -2226,6 +2301,37 @@ static const struct ethtool_ops airoha_ethtool_ops = {
 	.get_rmon_stats		= airoha_ethtool_get_rmon_stats,
 };
 
+static int airoha_metadata_dst_alloc(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		struct metadata_dst *md_dst;
+
+		md_dst = metadata_dst_alloc(0, METADATA_HW_PORT_MUX,
+					    GFP_KERNEL);
+		if (!md_dst)
+			return -ENOMEM;
+
+		md_dst->u.port_info.port_id = i;
+		port->dsa_meta[i] = md_dst;
+	}
+
+	return 0;
+}
+
+static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(port->dsa_meta); i++) {
+		if (!port->dsa_meta[i])
+			continue;
+
+		metadata_dst_free(port->dsa_meta[i]);
+	}
+}
+
 static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 {
 	const __be32 *id_ptr = of_get_property(np, "reg", NULL);
@@ -2298,6 +2404,10 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	port->id = id;
 	eth->ports[index] = port;
 
+	err = airoha_metadata_dst_alloc(port);
+	if (err)
+		return err;
+
 	return register_netdev(dev);
 }
 
@@ -2390,8 +2500,10 @@ static int airoha_probe(struct platform_device *pdev)
 	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
 		struct airoha_gdm_port *port = eth->ports[i];
 
-		if (port && port->dev->reg_state == NETREG_REGISTERED)
+		if (port && port->dev->reg_state == NETREG_REGISTERED) {
 			unregister_netdev(port->dev);
+			airoha_metadata_dst_free(port);
+		}
 	}
 	free_netdev(eth->napi_dev);
 	platform_set_drvdata(pdev, NULL);
@@ -2417,6 +2529,7 @@ static void airoha_remove(struct platform_device *pdev)
 
 		airoha_dev_stop(port->dev);
 		unregister_netdev(port->dev);
+		airoha_metadata_dst_free(port);
 	}
 	free_netdev(eth->napi_dev);
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 743aaf10235fe..fee6c10eaedfd 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -15,6 +15,7 @@
 
 #define AIROHA_MAX_NUM_GDM_PORTS	1
 #define AIROHA_MAX_NUM_QDMA		2
+#define AIROHA_MAX_DSA_PORTS		7
 #define AIROHA_MAX_NUM_RSTS		3
 #define AIROHA_MAX_NUM_XSI_RSTS		5
 #define AIROHA_MAX_MTU			2000
@@ -43,6 +44,10 @@
 #define QDMA_METER_IDX(_n)		((_n) & 0xff)
 #define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
 
+#define MTK_HDR_LEN			4
+#define MTK_HDR_XMIT_TAGGED_TPID_8100	1
+#define MTK_HDR_XMIT_TAGGED_TPID_88A8	2
+
 enum {
 	QDMA_INT_REG_IDX0,
 	QDMA_INT_REG_IDX1,
@@ -231,6 +236,8 @@ struct airoha_gdm_port {
 	/* qos stats counters */
 	u64 cpu_tx_packets;
 	u64 fwd_tx_packets;
+
+	struct metadata_dst *dsa_meta[AIROHA_MAX_DSA_PORTS];
 };
 
 struct airoha_eth {
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 7c9dadb348834..e467dd81ff44a 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -624,6 +624,8 @@
 #define QDMA_ETH_TXMSG_ACNT_G1_MASK	GENMASK(10, 6)	/* 0x1f do not count */
 #define QDMA_ETH_TXMSG_ACNT_G0_MASK	GENMASK(5, 0)	/* 0x3f do not count */
 
+/* RX MSG0 */
+#define QDMA_ETH_RXMSG_SPTAG		GENMASK(21, 14)
 /* RX MSG1 */
 #define QDMA_ETH_RXMSG_DEI_MASK		BIT(31)
 #define QDMA_ETH_RXMSG_IP6_MASK		BIT(30)

From ab667db1e6014634c6607ebdddc16c1b8394a935 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:14 +0100
Subject: [PATCH 1488/2753] net: dsa: mt7530: Enable Rx sptag for EN7581 SoC

Packet Processor Engine (PPE) module used for hw acceleration on EN7581
mac block, in order to properly parse packets, requires DSA untagged
packets on TX side and read DSA tag from DMA descriptor on RX side.
For this reason, enable RX Special Tag (SPTAG) for EN7581 SoC.
This is a preliminary patch to enable netfilter flowtable hw offloading
on EN7581 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/dsa/mt7530.c | 5 +++++
 drivers/net/dsa/mt7530.h | 4 ++++
 2 files changed, 9 insertions(+)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 8422262febaf7..aaa36c27b0f9f 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2586,6 +2586,11 @@ mt7531_setup_common(struct dsa_switch *ds)
 	/* Allow mirroring frames received on the local port (monitor port). */
 	mt7530_set(priv, MT753X_AGC, LOCAL_EN);
 
+	/* Enable Special Tag for rx frames */
+	if (priv->id == ID_EN7581)
+		mt7530_write(priv, MT753X_CPORT_SPTAG_CFG,
+			     CPORT_SW2FE_STAG_EN | CPORT_FE2SW_STAG_EN);
+
 	/* Flush the FDB table */
 	ret = mt7530_fdb_cmd(priv, MT7530_FDB_FLUSH, NULL);
 	if (ret < 0)
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 448200689f492..349d72a35771f 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -627,6 +627,10 @@ enum mt7531_xtal_fsel {
 #define  MT7531_GPIO12_RG_RXD3_MASK	GENMASK(19, 16)
 #define  MT7531_EXT_P_MDIO_12		(2 << 16)
 
+#define MT753X_CPORT_SPTAG_CFG		0x7c10
+#define  CPORT_SW2FE_STAG_EN		BIT(1)
+#define  CPORT_FE2SW_STAG_EN		BIT(0)
+
 /* Registers for LED GPIO control (MT7530 only)
  * All registers follow this pattern:
  * [ 2: 0]  port 0

From 80369686737fe07c233a1152da0b84372dabdcd6 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:15 +0100
Subject: [PATCH 1489/2753] net: airoha: Enable support for multiple
 net_devices

In the current codebase airoha_eth driver supports just a single
net_device connected to the Packet Switch Engine (PSE) lan port (GDM1).
As shown in commit 23020f049327 ("net: airoha: Introduce ethernet
support for EN7581 SoC"), PSE can switch packets between four GDM ports.
Enable the capability to create a net_device for each GDM port of the
PSE module. Moreover, since the QDMA blocks can be shared between
net_devices, do not stop TX/RX DMA in airoha_dev_stop() if there are
active net_devices for this QDMA block.
This is a preliminary patch to enable flowtable hw offloading for EN7581
SoC.

Co-developed-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 35 ++++++++++++++----------
 drivers/net/ethernet/airoha/airoha_eth.h |  4 ++-
 2 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 347fc403f2998..69775dfbc1c34 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1562,6 +1562,7 @@ static int airoha_dev_open(struct net_device *dev)
 	airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
 			GLOBAL_CFG_TX_DMA_EN_MASK |
 			GLOBAL_CFG_RX_DMA_EN_MASK);
+	atomic_inc(&qdma->users);
 
 	return 0;
 }
@@ -1577,16 +1578,20 @@ static int airoha_dev_stop(struct net_device *dev)
 	if (err)
 		return err;
 
-	airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
-			  GLOBAL_CFG_TX_DMA_EN_MASK |
-			  GLOBAL_CFG_RX_DMA_EN_MASK);
+	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++)
+		netdev_tx_reset_subqueue(dev, i);
 
-	for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
-		if (!qdma->q_tx[i].ndesc)
-			continue;
+	if (atomic_dec_and_test(&qdma->users)) {
+		airoha_qdma_clear(qdma, REG_QDMA_GLOBAL_CFG,
+				  GLOBAL_CFG_TX_DMA_EN_MASK |
+				  GLOBAL_CFG_RX_DMA_EN_MASK);
 
-		airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
-		netdev_tx_reset_subqueue(dev, i);
+		for (i = 0; i < ARRAY_SIZE(qdma->q_tx); i++) {
+			if (!qdma->q_tx[i].ndesc)
+				continue;
+
+			airoha_qdma_cleanup_tx_queue(&qdma->q_tx[i]);
+		}
 	}
 
 	return 0;
@@ -2332,13 +2337,14 @@ static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
 	}
 }
 
-static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
+static int airoha_alloc_gdm_port(struct airoha_eth *eth,
+				 struct device_node *np, int index)
 {
 	const __be32 *id_ptr = of_get_property(np, "reg", NULL);
 	struct airoha_gdm_port *port;
 	struct airoha_qdma *qdma;
 	struct net_device *dev;
-	int err, index;
+	int err, p;
 	u32 id;
 
 	if (!id_ptr) {
@@ -2347,14 +2353,14 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	}
 
 	id = be32_to_cpup(id_ptr);
-	index = id - 1;
+	p = id - 1;
 
 	if (!id || id > ARRAY_SIZE(eth->ports)) {
 		dev_err(eth->dev, "invalid gdm port id: %d\n", id);
 		return -EINVAL;
 	}
 
-	if (eth->ports[index]) {
+	if (eth->ports[p]) {
 		dev_err(eth->dev, "duplicate gdm port id: %d\n", id);
 		return -EINVAL;
 	}
@@ -2402,7 +2408,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth, struct device_node *np)
 	port->qdma = qdma;
 	port->dev = dev;
 	port->id = id;
-	eth->ports[index] = port;
+	eth->ports[p] = port;
 
 	err = airoha_metadata_dst_alloc(port);
 	if (err)
@@ -2474,6 +2480,7 @@ static int airoha_probe(struct platform_device *pdev)
 	for (i = 0; i < ARRAY_SIZE(eth->qdma); i++)
 		airoha_qdma_start_napi(&eth->qdma[i]);
 
+	i = 0;
 	for_each_child_of_node(pdev->dev.of_node, np) {
 		if (!of_device_is_compatible(np, "airoha,eth-mac"))
 			continue;
@@ -2481,7 +2488,7 @@ static int airoha_probe(struct platform_device *pdev)
 		if (!of_device_is_available(np))
 			continue;
 
-		err = airoha_alloc_gdm_port(eth, np);
+		err = airoha_alloc_gdm_port(eth, np, i++);
 		if (err) {
 			of_node_put(np);
 			goto error_napi_stop;
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index fee6c10eaedfd..74bdfd9e8d2fb 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -13,7 +13,7 @@
 #include <linux/netdevice.h>
 #include <linux/reset.h>
 
-#define AIROHA_MAX_NUM_GDM_PORTS	1
+#define AIROHA_MAX_NUM_GDM_PORTS	4
 #define AIROHA_MAX_NUM_QDMA		2
 #define AIROHA_MAX_DSA_PORTS		7
 #define AIROHA_MAX_NUM_RSTS		3
@@ -212,6 +212,8 @@ struct airoha_qdma {
 	u32 irqmask[QDMA_INT_REG_MAX];
 	int irq;
 
+	atomic_t users;
+
 	struct airoha_tx_irq_queue q_tx_irq[AIROHA_NUM_TX_IRQ];
 
 	struct airoha_queue q_tx[AIROHA_NUM_TX_RING];

From 67fde5d58cd43d129a979e918ec9cd5d2e2fbcfb Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:16 +0100
Subject: [PATCH 1490/2753] net: airoha: Move REG_GDM_FWD_CFG() initialization
 in airoha_dev_init()

Move REG_GDM_FWD_CFG() register initialization in airoha_dev_init
routine. Moreover, always send traffic PPE module in order to be
processed by hw accelerator.
This is a preliminary patch to enable netfilter flowtable hw offloading
on EN7581 SoC.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 69775dfbc1c34..4e74fd1839919 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -107,25 +107,20 @@ static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
 
 static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
 {
-	u32 val = enable ? FE_PSE_PORT_PPE1 : FE_PSE_PORT_DROP;
-	u32 vip_port, cfg_addr;
+	u32 vip_port;
 
 	switch (port) {
 	case XSI_PCIE0_PORT:
 		vip_port = XSI_PCIE0_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
 		break;
 	case XSI_PCIE1_PORT:
 		vip_port = XSI_PCIE1_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(3);
 		break;
 	case XSI_USB_PORT:
 		vip_port = XSI_USB_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
 		break;
 	case XSI_ETH_PORT:
 		vip_port = XSI_ETH_VIP_PORT_MASK;
-		cfg_addr = REG_GDM_FWD_CFG(4);
 		break;
 	default:
 		return -EINVAL;
@@ -139,8 +134,6 @@ static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
 		airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, vip_port);
 	}
 
-	airoha_set_gdm_port_fwd_cfg(eth, cfg_addr, val);
-
 	return 0;
 }
 
@@ -177,8 +170,6 @@ static void airoha_fe_maccr_init(struct airoha_eth *eth)
 		airoha_fe_set(eth, REG_GDM_FWD_CFG(p),
 			      GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM |
 			      GDM_DROP_CRC_ERR);
-		airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(p),
-					    FE_PSE_PORT_CDM1);
 		airoha_fe_rmw(eth, REG_GDM_LEN_CFG(p),
 			      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
 			      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
@@ -1614,8 +1605,11 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
 
 	airoha_set_macaddr(port, dev->dev_addr);
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id),
+				    FE_PSE_PORT_PPE1);
 
 	return 0;
 }

From c28b8375f6d02ef3b5e8c51234cc3f6d47d9fb7f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:17 +0100
Subject: [PATCH 1491/2753] net: airoha: Rename airoha_set_gdm_port_fwd_cfg()
 in airoha_set_vip_for_gdm_port()

Rename airoha_set_gdm_port() in airoha_set_vip_for_gdm_port().
Get rid of airoha_set_gdm_ports routine.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 49 ++++++------------------
 drivers/net/ethernet/airoha/airoha_eth.h |  8 ----
 2 files changed, 11 insertions(+), 46 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 4e74fd1839919..8a5f7c080b48c 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -105,25 +105,23 @@ static void airoha_set_gdm_port_fwd_cfg(struct airoha_eth *eth, u32 addr,
 		      FIELD_PREP(GDM_UCFQ_MASK, val));
 }
 
-static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
+static int airoha_set_vip_for_gdm_port(struct airoha_gdm_port *port,
+				       bool enable)
 {
+	struct airoha_eth *eth = port->qdma->eth;
 	u32 vip_port;
 
-	switch (port) {
-	case XSI_PCIE0_PORT:
+	switch (port->id) {
+	case 3:
+		/* FIXME: handle XSI_PCIE1_PORT */
 		vip_port = XSI_PCIE0_VIP_PORT_MASK;
 		break;
-	case XSI_PCIE1_PORT:
-		vip_port = XSI_PCIE1_VIP_PORT_MASK;
-		break;
-	case XSI_USB_PORT:
-		vip_port = XSI_USB_VIP_PORT_MASK;
-		break;
-	case XSI_ETH_PORT:
+	case 4:
+		/* FIXME: handle XSI_USB_PORT */
 		vip_port = XSI_ETH_VIP_PORT_MASK;
 		break;
 	default:
-		return -EINVAL;
+		return 0;
 	}
 
 	if (enable) {
@@ -137,31 +135,6 @@ static int airoha_set_gdm_port(struct airoha_eth *eth, int port, bool enable)
 	return 0;
 }
 
-static int airoha_set_gdm_ports(struct airoha_eth *eth, bool enable)
-{
-	const int port_list[] = {
-		XSI_PCIE0_PORT,
-		XSI_PCIE1_PORT,
-		XSI_USB_PORT,
-		XSI_ETH_PORT
-	};
-	int i, err;
-
-	for (i = 0; i < ARRAY_SIZE(port_list); i++) {
-		err = airoha_set_gdm_port(eth, port_list[i], enable);
-		if (err)
-			goto error;
-	}
-
-	return 0;
-
-error:
-	for (i--; i >= 0; i--)
-		airoha_set_gdm_port(eth, port_list[i], false);
-
-	return err;
-}
-
 static void airoha_fe_maccr_init(struct airoha_eth *eth)
 {
 	int p;
@@ -1539,7 +1512,7 @@ static int airoha_dev_open(struct net_device *dev)
 	int err;
 
 	netif_tx_start_all_queues(dev);
-	err = airoha_set_gdm_ports(qdma->eth, true);
+	err = airoha_set_vip_for_gdm_port(port, true);
 	if (err)
 		return err;
 
@@ -1565,7 +1538,7 @@ static int airoha_dev_stop(struct net_device *dev)
 	int i, err;
 
 	netif_tx_disable(dev);
-	err = airoha_set_gdm_ports(qdma->eth, false);
+	err = airoha_set_vip_for_gdm_port(port, false);
 	if (err)
 		return err;
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 74bdfd9e8d2fb..44834227a5898 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -57,14 +57,6 @@ enum {
 	QDMA_INT_REG_MAX
 };
 
-enum {
-	XSI_PCIE0_PORT,
-	XSI_PCIE1_PORT,
-	XSI_USB_PORT,
-	XSI_AE_PORT,
-	XSI_ETH_PORT,
-};
-
 enum {
 	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
 	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),

From 266f7a0f81c059e68748d05f89258fc97f5b07f9 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:18 +0100
Subject: [PATCH 1492/2753] dt-bindings: net: airoha: Add the NPU node for
 EN7581 SoC

This patch adds the NPU document binding for EN7581 SoC.
The Airoha Network Processor Unit (NPU) provides a configuration interface
to implement wired and wireless hardware flow offloading programming Packet
Processor Engine (PPE) flow table.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../bindings/net/airoha,en7581-npu.yaml       | 84 +++++++++++++++++++
 1 file changed, 84 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml

diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml
new file mode 100644
index 0000000000000..76dd97c3fb400
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/airoha,en7581-npu.yaml
@@ -0,0 +1,84 @@
+# SPDX-License-Identifier: (GPL-2.0 OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/airoha,en7581-npu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha Network Processor Unit for EN7581 SoC
+
+maintainers:
+  - Lorenzo Bianconi <lorenzo@kernel.org>
+
+description:
+  The Airoha Network Processor Unit (NPU) provides a configuration interface
+  to implement wired and wireless hardware flow offloading programming Packet
+  Processor Engine (PPE) flow table.
+
+properties:
+  compatible:
+    enum:
+      - airoha,en7581-npu
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    items:
+      - description: mbox host irq line
+      - description: watchdog0 irq line
+      - description: watchdog1 irq line
+      - description: watchdog2 irq line
+      - description: watchdog3 irq line
+      - description: watchdog4 irq line
+      - description: watchdog5 irq line
+      - description: watchdog6 irq line
+      - description: watchdog7 irq line
+      - description: wlan irq line0
+      - description: wlan irq line1
+      - description: wlan irq line2
+      - description: wlan irq line3
+      - description: wlan irq line4
+      - description: wlan irq line5
+
+  memory-region:
+    maxItems: 1
+    description:
+      Memory used to store NPU firmware binary.
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - memory-region
+
+additionalProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/interrupt-controller/irq.h>
+    soc {
+      #address-cells = <2>;
+      #size-cells = <2>;
+
+      npu@1e900000 {
+        compatible = "airoha,en7581-npu";
+        reg = <0 0x1e900000 0 0x313000>;
+        interrupts = <GIC_SPI 125 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 103 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 109 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 113 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 117 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 134 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 135 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 136 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 137 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 118 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 121 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 122 IRQ_TYPE_LEVEL_HIGH>,
+                     <GIC_SPI 123 IRQ_TYPE_LEVEL_HIGH>;
+        memory-region = <&npu_binary>;
+      };
+    };

From 9b1a0b72264cafdbc1e06ef8531bc6bd693b49ca Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:19 +0100
Subject: [PATCH 1493/2753] dt-bindings: net: airoha: Add airoha,npu phandle
 property

Introduce the airoha,npu property for the NPU node available on
EN7581 SoC. The airoha Network Processor Unit (NPU) is used to
offload network traffic forwarded between Packet Switch Engine
(PSE) ports.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../devicetree/bindings/net/airoha,en7581-eth.yaml     | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
index c578637c5826d..0fdd112654177 100644
--- a/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
+++ b/Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
@@ -63,6 +63,14 @@ properties:
   "#size-cells":
     const: 0
 
+  airoha,npu:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description:
+      Phandle to the node used to configure the NPU module.
+      The Airoha Network Processor Unit (NPU) provides a configuration
+      interface to implement hardware flow offloading programming Packet
+      Processor Engine (PPE) flow table.
+
 patternProperties:
   "^ethernet@[1-4]$":
     type: object
@@ -132,6 +140,8 @@ examples:
                      <GIC_SPI 49 IRQ_TYPE_LEVEL_HIGH>,
                      <GIC_SPI 64 IRQ_TYPE_LEVEL_HIGH>;
 
+        airoha,npu = <&npu>;
+
         #address-cells = <1>;
         #size-cells = <0>;
 

From 23290c7bc190def4e1ca61610992d9b7c32e33f3 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:20 +0100
Subject: [PATCH 1494/2753] net: airoha: Introduce Airoha NPU support

Packet Processor Engine (PPE) module available on EN7581 SoC populates
the PPE table with 5-tuples flower rules learned from traffic forwarded
between the GDM ports connected to the Packet Switch Engine (PSE) module.
The airoha_eth driver can enable hw acceleration of learned 5-tuples
rules if the user configure them in netfilter flowtable (netfilter
flowtable support will be added with subsequent patches).
airoha_eth driver configures and collects data from the PPE module via a
Network Processor Unit (NPU) RISC-V module available on the EN7581 SoC.
Introduce basic support for Airoha NPU module.

Tested-by: Sayantan Nandy <sayantan.nandy@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/Kconfig      |   9 +
 drivers/net/ethernet/airoha/Makefile     |   1 +
 drivers/net/ethernet/airoha/airoha_eth.h |   2 +
 drivers/net/ethernet/airoha/airoha_npu.c | 520 +++++++++++++++++++++++
 drivers/net/ethernet/airoha/airoha_npu.h |  34 ++
 5 files changed, 566 insertions(+)
 create mode 100644 drivers/net/ethernet/airoha/airoha_npu.c
 create mode 100644 drivers/net/ethernet/airoha/airoha_npu.h

diff --git a/drivers/net/ethernet/airoha/Kconfig b/drivers/net/ethernet/airoha/Kconfig
index b6a131845f13b..1a4cf6a259f67 100644
--- a/drivers/net/ethernet/airoha/Kconfig
+++ b/drivers/net/ethernet/airoha/Kconfig
@@ -7,9 +7,18 @@ config NET_VENDOR_AIROHA
 
 if NET_VENDOR_AIROHA
 
+config NET_AIROHA_NPU
+	tristate "Airoha NPU support"
+	select WANT_DEV_COREDUMP
+	select REGMAP_MMIO
+	help
+	  This driver supports Airoha Network Processor (NPU) available
+	  on the Airoha Soc family.
+
 config NET_AIROHA
 	tristate "Airoha SoC Gigabit Ethernet support"
 	depends on NET_DSA || !NET_DSA
+	select NET_AIROHA_NPU
 	select PAGE_POOL
 	help
 	  This driver supports the gigabit ethernet MACs in the
diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
index 73a6f3680a4c4..fcd3fc7759485 100644
--- a/drivers/net/ethernet/airoha/Makefile
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_NET_AIROHA) += airoha_eth.o
+obj-$(CONFIG_NET_AIROHA_NPU) += airoha_npu.o
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 44834227a5898..7be932a8e8d2e 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -240,6 +240,8 @@ struct airoha_eth {
 	unsigned long state;
 	void __iomem *fe_regs;
 
+	struct airoha_npu __rcu *npu;
+
 	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
 	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
 
diff --git a/drivers/net/ethernet/airoha/airoha_npu.c b/drivers/net/ethernet/airoha/airoha_npu.c
new file mode 100644
index 0000000000000..7a5710f9ccf6a
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_npu.c
@@ -0,0 +1,520 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/devcoredump.h>
+#include <linux/firmware.h>
+#include <linux/platform_device.h>
+#include <linux/of_net.h>
+#include <linux/of_platform.h>
+#include <linux/of_reserved_mem.h>
+#include <linux/regmap.h>
+
+#include "airoha_npu.h"
+
+#define NPU_EN7581_FIRMWARE_DATA		"airoha/en7581_npu_data.bin"
+#define NPU_EN7581_FIRMWARE_RV32		"airoha/en7581_npu_rv32.bin"
+#define NPU_EN7581_FIRMWARE_RV32_MAX_SIZE	0x200000
+#define NPU_EN7581_FIRMWARE_DATA_MAX_SIZE	0x10000
+#define NPU_DUMP_SIZE				512
+
+#define REG_NPU_LOCAL_SRAM		0x0
+
+#define NPU_PC_BASE_ADDR		0x305000
+#define REG_PC_DBG(_n)			(0x305000 + ((_n) * 0x100))
+
+#define NPU_CLUSTER_BASE_ADDR		0x306000
+
+#define REG_CR_BOOT_TRIGGER		(NPU_CLUSTER_BASE_ADDR + 0x000)
+#define REG_CR_BOOT_CONFIG		(NPU_CLUSTER_BASE_ADDR + 0x004)
+#define REG_CR_BOOT_BASE(_n)		(NPU_CLUSTER_BASE_ADDR + 0x020 + ((_n) << 2))
+
+#define NPU_MBOX_BASE_ADDR		0x30c000
+
+#define REG_CR_MBOX_INT_STATUS		(NPU_MBOX_BASE_ADDR + 0x000)
+#define MBOX_INT_STATUS_MASK		BIT(8)
+
+#define REG_CR_MBOX_INT_MASK(_n)	(NPU_MBOX_BASE_ADDR + 0x004 + ((_n) << 2))
+#define REG_CR_MBQ0_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x030 + ((_n) << 2))
+#define REG_CR_MBQ8_CTRL(_n)		(NPU_MBOX_BASE_ADDR + 0x0b0 + ((_n) << 2))
+#define REG_CR_NPU_MIB(_n)		(NPU_MBOX_BASE_ADDR + 0x140 + ((_n) << 2))
+
+#define NPU_TIMER_BASE_ADDR		0x310100
+#define REG_WDT_TIMER_CTRL(_n)		(NPU_TIMER_BASE_ADDR + ((_n) * 0x100))
+#define WDT_EN_MASK			BIT(25)
+#define WDT_INTR_MASK			BIT(21)
+
+enum {
+	NPU_OP_SET = 1,
+	NPU_OP_SET_NO_WAIT,
+	NPU_OP_GET,
+	NPU_OP_GET_NO_WAIT,
+};
+
+enum {
+	NPU_FUNC_WIFI,
+	NPU_FUNC_TUNNEL,
+	NPU_FUNC_NOTIFY,
+	NPU_FUNC_DBA,
+	NPU_FUNC_TR471,
+	NPU_FUNC_PPE,
+};
+
+enum {
+	NPU_MBOX_ERROR,
+	NPU_MBOX_SUCCESS,
+};
+
+enum {
+	PPE_FUNC_SET_WAIT,
+	PPE_FUNC_SET_WAIT_HWNAT_INIT,
+	PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
+	PPE_FUNC_SET_WAIT_API,
+};
+
+enum {
+	PPE2_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_ENTRY,
+	PPE_SRAM_SET_VAL,
+	PPE_SRAM_RESET_VAL,
+};
+
+enum {
+	QDMA_WAN_ETHER = 1,
+	QDMA_WAN_PON_XDSL,
+};
+
+#define MBOX_MSG_FUNC_ID	GENMASK(14, 11)
+#define MBOX_MSG_STATIC_BUF	BIT(5)
+#define MBOX_MSG_STATUS		GENMASK(4, 2)
+#define MBOX_MSG_DONE		BIT(1)
+#define MBOX_MSG_WAIT_RSP	BIT(0)
+
+#define PPE_TYPE_L2B_IPV4	2
+#define PPE_TYPE_L2B_IPV4_IPV6	3
+
+struct ppe_mbox_data {
+	u32 func_type;
+	u32 func_id;
+	union {
+		struct {
+			u8 cds;
+			u8 xpon_hal_api;
+			u8 wan_xsi;
+			u8 ct_joyme4;
+			int ppe_type;
+			int wan_mode;
+			int wan_sel;
+		} init_info;
+		struct {
+			int func_id;
+			u32 size;
+			u32 data;
+		} set_info;
+	};
+};
+
+static int airoha_npu_send_msg(struct airoha_npu *npu, int func_id,
+			       void *p, int size)
+{
+	u16 core = 0; /* FIXME */
+	u32 val, offset = core << 4;
+	dma_addr_t dma_addr;
+	void *addr;
+	int ret;
+
+	addr = kmemdup(p, size, GFP_ATOMIC);
+	if (!addr)
+		return -ENOMEM;
+
+	dma_addr = dma_map_single(npu->dev, addr, size, DMA_TO_DEVICE);
+	ret = dma_mapping_error(npu->dev, dma_addr);
+	if (ret)
+		goto out;
+
+	spin_lock_bh(&npu->cores[core].lock);
+
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(0) + offset, dma_addr);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(1) + offset, size);
+	regmap_read(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, &val);
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(2) + offset, val + 1);
+	val = FIELD_PREP(MBOX_MSG_FUNC_ID, func_id) | MBOX_MSG_WAIT_RSP;
+	regmap_write(npu->regmap, REG_CR_MBQ0_CTRL(3) + offset, val);
+
+	ret = regmap_read_poll_timeout_atomic(npu->regmap,
+					      REG_CR_MBQ0_CTRL(3) + offset,
+					      val, (val & MBOX_MSG_DONE),
+					      100, 100 * MSEC_PER_SEC);
+	if (!ret && FIELD_GET(MBOX_MSG_STATUS, val) != NPU_MBOX_SUCCESS)
+		ret = -EINVAL;
+
+	spin_unlock_bh(&npu->cores[core].lock);
+
+	dma_unmap_single(npu->dev, dma_addr, size, DMA_TO_DEVICE);
+out:
+	kfree(addr);
+
+	return ret;
+}
+
+static int airoha_npu_run_firmware(struct device *dev, void __iomem *base,
+				   struct reserved_mem *rmem)
+{
+	const struct firmware *fw;
+	void __iomem *addr;
+	int ret;
+
+	ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_RV32, dev);
+	if (ret)
+		return ret == -ENOENT ? -EPROBE_DEFER : ret;
+
+	if (fw->size > NPU_EN7581_FIRMWARE_RV32_MAX_SIZE) {
+		dev_err(dev, "%s: fw size too overlimit (%zu)\n",
+			NPU_EN7581_FIRMWARE_RV32, fw->size);
+		ret = -E2BIG;
+		goto out;
+	}
+
+	addr = devm_ioremap(dev, rmem->base, rmem->size);
+	if (!addr) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	memcpy_toio(addr, fw->data, fw->size);
+	release_firmware(fw);
+
+	ret = request_firmware(&fw, NPU_EN7581_FIRMWARE_DATA, dev);
+	if (ret)
+		return ret == -ENOENT ? -EPROBE_DEFER : ret;
+
+	if (fw->size > NPU_EN7581_FIRMWARE_DATA_MAX_SIZE) {
+		dev_err(dev, "%s: fw size too overlimit (%zu)\n",
+			NPU_EN7581_FIRMWARE_DATA, fw->size);
+		ret = -E2BIG;
+		goto out;
+	}
+
+	memcpy_toio(base + REG_NPU_LOCAL_SRAM, fw->data, fw->size);
+out:
+	release_firmware(fw);
+
+	return ret;
+}
+
+static irqreturn_t airoha_npu_mbox_handler(int irq, void *npu_instance)
+{
+	struct airoha_npu *npu = npu_instance;
+
+	/* clear mbox interrupt status */
+	regmap_write(npu->regmap, REG_CR_MBOX_INT_STATUS,
+		     MBOX_INT_STATUS_MASK);
+
+	/* acknowledge npu */
+	regmap_update_bits(npu->regmap, REG_CR_MBQ8_CTRL(3),
+			   MBOX_MSG_STATUS | MBOX_MSG_DONE, MBOX_MSG_DONE);
+
+	return IRQ_HANDLED;
+}
+
+static void airoha_npu_wdt_work(struct work_struct *work)
+{
+	struct airoha_npu_core *core;
+	struct airoha_npu *npu;
+	void *dump;
+	u32 val[3];
+	int c;
+
+	core = container_of(work, struct airoha_npu_core, wdt_work);
+	npu = core->npu;
+
+	dump = vzalloc(NPU_DUMP_SIZE);
+	if (!dump)
+		return;
+
+	c = core - &npu->cores[0];
+	regmap_bulk_read(npu->regmap, REG_PC_DBG(c), val, ARRAY_SIZE(val));
+	snprintf(dump, NPU_DUMP_SIZE, "PC: %08x SP: %08x LR: %08x\n",
+		 val[0], val[1], val[2]);
+
+	dev_coredumpv(npu->dev, dump, NPU_DUMP_SIZE, GFP_KERNEL);
+}
+
+static irqreturn_t airoha_npu_wdt_handler(int irq, void *core_instance)
+{
+	struct airoha_npu_core *core = core_instance;
+	struct airoha_npu *npu = core->npu;
+	int c = core - &npu->cores[0];
+	u32 val;
+
+	regmap_set_bits(npu->regmap, REG_WDT_TIMER_CTRL(c), WDT_INTR_MASK);
+	if (!regmap_read(npu->regmap, REG_WDT_TIMER_CTRL(c), &val) &&
+	    FIELD_GET(WDT_EN_MASK, val))
+		schedule_work(&core->wdt_work);
+
+	return IRQ_HANDLED;
+}
+
+static int airoha_npu_ppe_init(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data ppe_data = {
+		.func_type = NPU_OP_SET,
+		.func_id = PPE_FUNC_SET_WAIT_HWNAT_INIT,
+		.init_info = {
+			.ppe_type = PPE_TYPE_L2B_IPV4_IPV6,
+			.wan_mode = QDMA_WAN_ETHER,
+		},
+	};
+
+	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
+				   sizeof(struct ppe_mbox_data));
+}
+
+static int airoha_npu_ppe_deinit(struct airoha_npu *npu)
+{
+	struct ppe_mbox_data ppe_data = {
+		.func_type = NPU_OP_SET,
+		.func_id = PPE_FUNC_SET_WAIT_HWNAT_DEINIT,
+	};
+
+	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
+				   sizeof(struct ppe_mbox_data));
+}
+
+static int airoha_npu_ppe_flush_sram_entries(struct airoha_npu *npu,
+					     dma_addr_t foe_addr,
+					     int sram_num_entries)
+{
+	struct ppe_mbox_data ppe_data = {
+		.func_type = NPU_OP_SET,
+		.func_id = PPE_FUNC_SET_WAIT_API,
+		.set_info = {
+			.func_id = PPE_SRAM_RESET_VAL,
+			.data = foe_addr,
+			.size = sram_num_entries,
+		},
+	};
+
+	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
+				   sizeof(struct ppe_mbox_data));
+}
+
+static int airoha_npu_foe_commit_entry(struct airoha_npu *npu,
+				       dma_addr_t foe_addr,
+				       u32 entry_size, u32 hash, bool ppe2)
+{
+	struct ppe_mbox_data ppe_data = {
+		.func_type = NPU_OP_SET,
+		.func_id = PPE_FUNC_SET_WAIT_API,
+		.set_info = {
+			.data = foe_addr,
+			.size = entry_size,
+		},
+	};
+	int err;
+
+	ppe_data.set_info.func_id = ppe2 ? PPE2_SRAM_SET_ENTRY
+					 : PPE_SRAM_SET_ENTRY;
+
+	err = airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
+				  sizeof(struct ppe_mbox_data));
+	if (err)
+		return err;
+
+	ppe_data.set_info.func_id = PPE_SRAM_SET_VAL;
+	ppe_data.set_info.data = hash;
+	ppe_data.set_info.size = sizeof(u32);
+
+	return airoha_npu_send_msg(npu, NPU_FUNC_PPE, &ppe_data,
+				   sizeof(struct ppe_mbox_data));
+}
+
+struct airoha_npu *airoha_npu_get(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct airoha_npu *npu;
+
+	np = of_parse_phandle(dev->of_node, "airoha,npu", 0);
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(np);
+	of_node_put(np);
+
+	if (!pdev) {
+		dev_err(dev, "cannot find device node %s\n", np->name);
+		return ERR_PTR(-ENODEV);
+	}
+
+	if (!try_module_get(THIS_MODULE)) {
+		dev_err(dev, "failed to get the device driver module\n");
+		npu = ERR_PTR(-ENODEV);
+		goto error_pdev_put;
+	}
+
+	npu = platform_get_drvdata(pdev);
+	if (!npu) {
+		npu = ERR_PTR(-ENODEV);
+		goto error_module_put;
+	}
+
+	if (!device_link_add(dev, &pdev->dev, DL_FLAG_AUTOREMOVE_SUPPLIER)) {
+		dev_err(&pdev->dev,
+			"failed to create device link to consumer %s\n",
+			dev_name(dev));
+		npu = ERR_PTR(-EINVAL);
+		goto error_module_put;
+	}
+
+	return npu;
+
+error_module_put:
+	module_put(THIS_MODULE);
+error_pdev_put:
+	platform_device_put(pdev);
+
+	return npu;
+}
+EXPORT_SYMBOL_GPL(airoha_npu_get);
+
+void airoha_npu_put(struct airoha_npu *npu)
+{
+	module_put(THIS_MODULE);
+	put_device(npu->dev);
+}
+EXPORT_SYMBOL_GPL(airoha_npu_put);
+
+static const struct of_device_id of_airoha_npu_match[] = {
+	{ .compatible = "airoha,en7581-npu" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, of_airoha_npu_match);
+
+static const struct regmap_config regmap_config = {
+	.name			= "npu",
+	.reg_bits		= 32,
+	.val_bits		= 32,
+	.reg_stride		= 4,
+	.disable_locking	= true,
+};
+
+static int airoha_npu_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct reserved_mem *rmem;
+	struct airoha_npu *npu;
+	struct device_node *np;
+	void __iomem *base;
+	int i, irq, err;
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	npu = devm_kzalloc(dev, sizeof(*npu), GFP_KERNEL);
+	if (!npu)
+		return -ENOMEM;
+
+	npu->dev = dev;
+	npu->ops.ppe_init = airoha_npu_ppe_init;
+	npu->ops.ppe_deinit = airoha_npu_ppe_deinit;
+	npu->ops.ppe_flush_sram_entries = airoha_npu_ppe_flush_sram_entries;
+	npu->ops.ppe_foe_commit_entry = airoha_npu_foe_commit_entry;
+
+	npu->regmap = devm_regmap_init_mmio(dev, base, &regmap_config);
+	if (IS_ERR(npu->regmap))
+		return PTR_ERR(npu->regmap);
+
+	np = of_parse_phandle(dev->of_node, "memory-region", 0);
+	if (!np)
+		return -ENODEV;
+
+	rmem = of_reserved_mem_lookup(np);
+	of_node_put(np);
+
+	if (!rmem)
+		return -ENODEV;
+
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0)
+		return irq;
+
+	err = devm_request_irq(dev, irq, airoha_npu_mbox_handler,
+			       IRQF_SHARED, "airoha-npu-mbox", npu);
+	if (err)
+		return err;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++) {
+		struct airoha_npu_core *core = &npu->cores[i];
+
+		spin_lock_init(&core->lock);
+		core->npu = npu;
+
+		irq = platform_get_irq(pdev, i + 1);
+		if (irq < 0)
+			return irq;
+
+		err = devm_request_irq(dev, irq, airoha_npu_wdt_handler,
+				       IRQF_SHARED, "airoha-npu-wdt", core);
+		if (err)
+			return err;
+
+		INIT_WORK(&core->wdt_work, airoha_npu_wdt_work);
+	}
+
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err)
+		return err;
+
+	err = airoha_npu_run_firmware(dev, base, rmem);
+	if (err)
+		return dev_err_probe(dev, err, "failed to run npu firmware\n");
+
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(10),
+		     rmem->base + NPU_EN7581_FIRMWARE_RV32_MAX_SIZE);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(11), 0x40000); /* SRAM 256K */
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(12), 0);
+	regmap_write(npu->regmap, REG_CR_NPU_MIB(21), 1);
+	msleep(100);
+
+	/* setting booting address */
+	for (i = 0; i < NPU_NUM_CORES; i++)
+		regmap_write(npu->regmap, REG_CR_BOOT_BASE(i), rmem->base);
+	usleep_range(1000, 2000);
+
+	/* enable NPU cores */
+	/* do not start core3 since it is used for WiFi offloading */
+	regmap_write(npu->regmap, REG_CR_BOOT_CONFIG, 0xf7);
+	regmap_write(npu->regmap, REG_CR_BOOT_TRIGGER, 0x1);
+	msleep(100);
+
+	platform_set_drvdata(pdev, npu);
+
+	return 0;
+}
+
+static void airoha_npu_remove(struct platform_device *pdev)
+{
+	struct airoha_npu *npu = platform_get_drvdata(pdev);
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(npu->cores); i++)
+		cancel_work_sync(&npu->cores[i].wdt_work);
+}
+
+static struct platform_driver airoha_npu_driver = {
+	.probe = airoha_npu_probe,
+	.remove = airoha_npu_remove,
+	.driver = {
+		.name = "airoha-npu",
+		.of_match_table = of_airoha_npu_match,
+	},
+};
+module_platform_driver(airoha_npu_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
+MODULE_DESCRIPTION("Airoha Network Processor Unit driver");
diff --git a/drivers/net/ethernet/airoha/airoha_npu.h b/drivers/net/ethernet/airoha/airoha_npu.h
new file mode 100644
index 0000000000000..a2b8ae4d94739
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_npu.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#define NPU_NUM_CORES		8
+
+struct airoha_npu {
+	struct device *dev;
+	struct regmap *regmap;
+
+	struct airoha_npu_core {
+		struct airoha_npu *npu;
+		/* protect concurrent npu memory accesses */
+		spinlock_t lock;
+		struct work_struct wdt_work;
+	} cores[NPU_NUM_CORES];
+
+	struct {
+		int (*ppe_init)(struct airoha_npu *npu);
+		int (*ppe_deinit)(struct airoha_npu *npu);
+		int (*ppe_flush_sram_entries)(struct airoha_npu *npu,
+					      dma_addr_t foe_addr,
+					      int sram_num_entries);
+		int (*ppe_foe_commit_entry)(struct airoha_npu *npu,
+					    dma_addr_t foe_addr,
+					    u32 entry_size, u32 hash,
+					    bool ppe2);
+	} ops;
+};
+
+struct airoha_npu *airoha_npu_get(struct device *dev);
+void airoha_npu_put(struct airoha_npu *npu);

From 00a7678310fe3d3f408513e55d9a0b67f0db380f Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:21 +0100
Subject: [PATCH 1495/2753] net: airoha: Introduce flowtable offload support

Introduce netfilter flowtable integration in order to allow airoha_eth
driver to offload 5-tuple flower rules learned by the PPE module if the
user accelerates them using a nft configuration similar to the one reported
below:

table inet filter {
	flowtable ft {
		hook ingress priority filter
		devices = { lan1, lan2, lan3, lan4, eth1 }
		flags offload;
	}
	chain forward {
		type filter hook forward priority filter; policy accept;
		meta l4proto { tcp, udp } flow add @ft
	}
}

Tested-by: Sayantan Nandy <sayantan.nandy@airoha.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/Makefile      |   3 +-
 drivers/net/ethernet/airoha/airoha_eth.c  |  60 +-
 drivers/net/ethernet/airoha/airoha_eth.h  | 250 ++++++
 drivers/net/ethernet/airoha/airoha_ppe.c  | 901 ++++++++++++++++++++++
 drivers/net/ethernet/airoha/airoha_regs.h | 107 ++-
 5 files changed, 1314 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/ethernet/airoha/airoha_ppe.c

diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
index fcd3fc7759485..6deff2f16229a 100644
--- a/drivers/net/ethernet/airoha/Makefile
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -3,5 +3,6 @@
 # Airoha for the Mediatek SoCs built-in ethernet macs
 #
 
-obj-$(CONFIG_NET_AIROHA) += airoha_eth.o
+obj-$(CONFIG_NET_AIROHA) += airoha-eth.o
+airoha-eth-y := airoha_eth.o airoha_ppe.o
 obj-$(CONFIG_NET_AIROHA_NPU) += airoha_npu.o
diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 8a5f7c080b48c..382ed81df8088 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -8,7 +8,6 @@
 #include <linux/platform_device.h>
 #include <linux/tcp.h>
 #include <linux/u64_stats_sync.h>
-#include <net/dsa.h>
 #include <net/dst_metadata.h>
 #include <net/page_pool/helpers.h>
 #include <net/pkt_cls.h>
@@ -619,6 +618,7 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 	while (done < budget) {
 		struct airoha_queue_entry *e = &q->entry[q->tail];
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
+		u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
 		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
 		struct airoha_gdm_port *port;
@@ -681,6 +681,15 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 						  &port->dsa_meta[sptag]->dst);
 		}
 
+		hash = FIELD_GET(AIROHA_RXD4_FOE_ENTRY, msg1);
+		if (hash != AIROHA_RXD4_FOE_ENTRY)
+			skb_set_hash(skb, jhash_1word(hash, 0),
+				     PKT_HASH_TYPE_L4);
+
+		reason = FIELD_GET(AIROHA_RXD4_PPE_CPU_REASON, msg1);
+		if (reason == PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
+			airoha_ppe_check_skb(eth->ppe, hash);
+
 		napi_gro_receive(&q->napi, skb);
 
 		done++;
@@ -1301,6 +1310,10 @@ static int airoha_hw_init(struct platform_device *pdev,
 			return err;
 	}
 
+	err = airoha_ppe_init(eth);
+	if (err)
+		return err;
+
 	set_bit(DEV_STATE_INITIALIZED, &eth->state);
 
 	return 0;
@@ -2168,6 +2181,47 @@ static int airoha_tc_htb_alloc_leaf_queue(struct airoha_gdm_port *port,
 	return 0;
 }
 
+static int airoha_dev_setup_tc_block(struct airoha_gdm_port *port,
+				     struct flow_block_offload *f)
+{
+	flow_setup_cb_t *cb = airoha_ppe_setup_tc_block_cb;
+	static LIST_HEAD(block_cb_list);
+	struct flow_block_cb *block_cb;
+
+	if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
+		return -EOPNOTSUPP;
+
+	f->driver_block_list = &block_cb_list;
+	switch (f->command) {
+	case FLOW_BLOCK_BIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (block_cb) {
+			flow_block_cb_incref(block_cb);
+			return 0;
+		}
+		block_cb = flow_block_cb_alloc(cb, port->dev, port->dev, NULL);
+		if (IS_ERR(block_cb))
+			return PTR_ERR(block_cb);
+
+		flow_block_cb_incref(block_cb);
+		flow_block_cb_add(block_cb, f);
+		list_add_tail(&block_cb->driver_list, &block_cb_list);
+		return 0;
+	case FLOW_BLOCK_UNBIND:
+		block_cb = flow_block_cb_lookup(f->block, cb, port->dev);
+		if (!block_cb)
+			return -ENOENT;
+
+		if (!flow_block_cb_decref(block_cb)) {
+			flow_block_cb_remove(block_cb, f);
+			list_del(&block_cb->driver_list);
+		}
+		return 0;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static void airoha_tc_remove_htb_queue(struct airoha_gdm_port *port, int queue)
 {
 	struct net_device *dev = port->dev;
@@ -2251,6 +2305,9 @@ static int airoha_dev_tc_setup(struct net_device *dev, enum tc_setup_type type,
 		return airoha_tc_setup_qdisc_ets(port, type_data);
 	case TC_SETUP_QDISC_HTB:
 		return airoha_tc_setup_qdisc_htb(port, type_data);
+	case TC_SETUP_BLOCK:
+	case TC_SETUP_FT:
+		return airoha_dev_setup_tc_block(port, type_data);
 	default:
 		return -EOPNOTSUPP;
 	}
@@ -2507,6 +2564,7 @@ static void airoha_remove(struct platform_device *pdev)
 	}
 	free_netdev(eth->napi_dev);
 
+	airoha_ppe_deinit(eth);
 	platform_set_drvdata(pdev, NULL);
 }
 
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 7be932a8e8d2e..db25a6d3b2cd1 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 #include <linux/reset.h>
+#include <net/dsa.h>
 
 #define AIROHA_MAX_NUM_GDM_PORTS	4
 #define AIROHA_MAX_NUM_QDMA		2
@@ -44,6 +45,15 @@
 #define QDMA_METER_IDX(_n)		((_n) & 0xff)
 #define QDMA_METER_GROUP(_n)		(((_n) >> 8) & 0x3)
 
+#define PPE_NUM				2
+#define PPE1_SRAM_NUM_ENTRIES		(8 * 1024)
+#define PPE_SRAM_NUM_ENTRIES		(2 * PPE1_SRAM_NUM_ENTRIES)
+#define PPE_DRAM_NUM_ENTRIES		(16 * 1024)
+#define PPE_NUM_ENTRIES			(PPE_SRAM_NUM_ENTRIES + PPE_DRAM_NUM_ENTRIES)
+#define PPE_HASH_MASK			(PPE_NUM_ENTRIES - 1)
+#define PPE_ENTRY_SIZE			80
+#define PPE_RAM_NUM_ENTRIES_SHIFT(_n)	(__ffs((_n) >> 10))
+
 #define MTK_HDR_LEN			4
 #define MTK_HDR_XMIT_TAGGED_TPID_8100	1
 #define MTK_HDR_XMIT_TAGGED_TPID_88A8	2
@@ -195,6 +205,224 @@ struct airoha_hw_stats {
 	u64 rx_len[7];
 };
 
+enum {
+	PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED = 0x0f,
+};
+
+enum {
+	AIROHA_FOE_STATE_INVALID,
+	AIROHA_FOE_STATE_UNBIND,
+	AIROHA_FOE_STATE_BIND,
+	AIROHA_FOE_STATE_FIN
+};
+
+enum {
+	PPE_PKT_TYPE_IPV4_HNAPT = 0,
+	PPE_PKT_TYPE_IPV4_ROUTE = 1,
+	PPE_PKT_TYPE_BRIDGE = 2,
+	PPE_PKT_TYPE_IPV4_DSLITE = 3,
+	PPE_PKT_TYPE_IPV6_ROUTE_3T = 4,
+	PPE_PKT_TYPE_IPV6_ROUTE_5T = 5,
+	PPE_PKT_TYPE_IPV6_6RD = 7,
+};
+
+#define AIROHA_FOE_MAC_SMAC_ID		GENMASK(20, 16)
+#define AIROHA_FOE_MAC_PPPOE_ID		GENMASK(15, 0)
+
+struct airoha_foe_mac_info_common {
+	u16 vlan1;
+	u16 etype;
+
+	u32 dest_mac_hi;
+
+	u16 vlan2;
+	u16 dest_mac_lo;
+
+	u32 src_mac_hi;
+};
+
+struct airoha_foe_mac_info {
+	struct airoha_foe_mac_info_common common;
+
+	u16 pppoe_id;
+	u16 src_mac_lo;
+};
+
+#define AIROHA_FOE_IB1_UNBIND_PREBIND		BIT(24)
+#define AIROHA_FOE_IB1_UNBIND_PACKETS		GENMASK(23, 8)
+#define AIROHA_FOE_IB1_UNBIND_TIMESTAMP		GENMASK(7, 0)
+
+#define AIROHA_FOE_IB1_BIND_STATIC		BIT(31)
+#define AIROHA_FOE_IB1_BIND_UDP			BIT(30)
+#define AIROHA_FOE_IB1_BIND_STATE		GENMASK(29, 28)
+#define AIROHA_FOE_IB1_BIND_PACKET_TYPE		GENMASK(27, 25)
+#define AIROHA_FOE_IB1_BIND_TTL			BIT(24)
+#define AIROHA_FOE_IB1_BIND_TUNNEL_DECAP	BIT(23)
+#define AIROHA_FOE_IB1_BIND_PPPOE		BIT(22)
+#define AIROHA_FOE_IB1_BIND_VPM			GENMASK(21, 20)
+#define AIROHA_FOE_IB1_BIND_VLAN_LAYER		GENMASK(19, 16)
+#define AIROHA_FOE_IB1_BIND_KEEPALIVE		BIT(15)
+#define AIROHA_FOE_IB1_BIND_TIMESTAMP		GENMASK(14, 0)
+
+#define AIROHA_FOE_IB2_DSCP			GENMASK(31, 24)
+#define AIROHA_FOE_IB2_PORT_AG			GENMASK(23, 13)
+#define AIROHA_FOE_IB2_PCP			BIT(12)
+#define AIROHA_FOE_IB2_MULTICAST		BIT(11)
+#define AIROHA_FOE_IB2_FAST_PATH		BIT(10)
+#define AIROHA_FOE_IB2_PSE_QOS			BIT(9)
+#define AIROHA_FOE_IB2_PSE_PORT			GENMASK(8, 5)
+#define AIROHA_FOE_IB2_NBQ			GENMASK(4, 0)
+
+#define AIROHA_FOE_ACTDP			GENMASK(31, 24)
+#define AIROHA_FOE_SHAPER_ID			GENMASK(23, 16)
+#define AIROHA_FOE_CHANNEL			GENMASK(15, 11)
+#define AIROHA_FOE_QID				GENMASK(10, 8)
+#define AIROHA_FOE_DPI				BIT(7)
+#define AIROHA_FOE_TUNNEL			BIT(6)
+#define AIROHA_FOE_TUNNEL_ID			GENMASK(5, 0)
+
+struct airoha_foe_bridge {
+	u32 dest_mac_hi;
+
+	u16 src_mac_hi;
+	u16 dest_mac_lo;
+
+	u32 src_mac_lo;
+
+	u32 ib2;
+
+	u32 rsv[5];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_tuple {
+	u32 src_ip;
+	u32 dest_ip;
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 _pad[3]; /* fill with 0xa5a5a5 */
+		};
+		u32 ports;
+	};
+};
+
+struct airoha_foe_ipv4 {
+	struct airoha_foe_ipv4_tuple orig_tuple;
+
+	u32 ib2;
+
+	struct airoha_foe_ipv4_tuple new_tuple;
+
+	u32 rsv[2];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv4_dslite {
+	struct airoha_foe_ipv4_tuple ip4;
+
+	u32 ib2;
+
+	u8 flow_label[3];
+	u8 priority;
+
+	u32 rsv[4];
+
+	u32 data;
+
+	struct airoha_foe_mac_info l2;
+};
+
+struct airoha_foe_ipv6 {
+	u32 src_ip[4];
+	u32 dest_ip[4];
+
+	union {
+		struct {
+			u16 dest_port;
+			u16 src_port;
+		};
+		struct {
+			u8 protocol;
+			u8 pad[3];
+		};
+		u32 ports;
+	};
+
+	u32 data;
+
+	u32 ib2;
+
+	struct airoha_foe_mac_info_common l2;
+};
+
+struct airoha_foe_entry {
+	union {
+		struct {
+			u32 ib1;
+			union {
+				struct airoha_foe_bridge bridge;
+				struct airoha_foe_ipv4 ipv4;
+				struct airoha_foe_ipv4_dslite dslite;
+				struct airoha_foe_ipv6 ipv6;
+				DECLARE_FLEX_ARRAY(u32, d);
+			};
+		};
+		u8 data[PPE_ENTRY_SIZE];
+	};
+};
+
+struct airoha_flow_data {
+	struct ethhdr eth;
+
+	union {
+		struct {
+			__be32 src_addr;
+			__be32 dst_addr;
+		} v4;
+
+		struct {
+			struct in6_addr src_addr;
+			struct in6_addr dst_addr;
+		} v6;
+	};
+
+	__be16 src_port;
+	__be16 dst_port;
+
+	struct {
+		struct {
+			u16 id;
+			__be16 proto;
+		} hdr[2];
+		u8 num;
+	} vlan;
+	struct {
+		u16 sid;
+		u8 num;
+	} pppoe;
+};
+
+struct airoha_flow_table_entry {
+	struct hlist_node list;
+
+	struct airoha_foe_entry data;
+	u32 hash;
+
+	struct rhash_head node;
+	unsigned long cookie;
+};
+
 struct airoha_qdma {
 	struct airoha_eth *eth;
 	void __iomem *regs;
@@ -234,6 +462,19 @@ struct airoha_gdm_port {
 	struct metadata_dst *dsa_meta[AIROHA_MAX_DSA_PORTS];
 };
 
+#define AIROHA_RXD4_PPE_CPU_REASON	GENMASK(20, 16)
+#define AIROHA_RXD4_FOE_ENTRY		GENMASK(15, 0)
+
+struct airoha_ppe {
+	struct airoha_eth *eth;
+
+	void *foe;
+	dma_addr_t foe_dma;
+
+	struct hlist_head *foe_flow;
+	u16 foe_check_time[PPE_NUM_ENTRIES];
+};
+
 struct airoha_eth {
 	struct device *dev;
 
@@ -242,6 +483,9 @@ struct airoha_eth {
 
 	struct airoha_npu __rcu *npu;
 
+	struct airoha_ppe *ppe;
+	struct rhashtable flow_table;
+
 	struct reset_control_bulk_data rsts[AIROHA_MAX_NUM_RSTS];
 	struct reset_control_bulk_data xsi_rsts[AIROHA_MAX_NUM_XSI_RSTS];
 
@@ -277,4 +521,10 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
 #define airoha_qdma_clear(qdma, offset, val)			\
 	airoha_rmw((qdma)->regs, (offset), (val), 0)
 
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash);
+int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv);
+int airoha_ppe_init(struct airoha_eth *eth);
+void airoha_ppe_deinit(struct airoha_eth *eth);
+
 #endif /* AIROHA_ETH_H */
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
new file mode 100644
index 0000000000000..37074121224a3
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -0,0 +1,901 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/rhashtable.h>
+#include <net/ipv6.h>
+#include <net/pkt_cls.h>
+
+#include "airoha_npu.h"
+#include "airoha_regs.h"
+#include "airoha_eth.h"
+
+static DEFINE_MUTEX(flow_offload_mutex);
+static DEFINE_SPINLOCK(ppe_lock);
+
+static const struct rhashtable_params airoha_flow_table_params = {
+	.head_offset = offsetof(struct airoha_flow_table_entry, node),
+	.key_offset = offsetof(struct airoha_flow_table_entry, cookie),
+	.key_len = sizeof(unsigned long),
+	.automatic_shrinking = true,
+};
+
+static bool airoha_ppe2_is_enabled(struct airoha_eth *eth)
+{
+	return airoha_fe_rr(eth, REG_PPE_GLO_CFG(1)) & PPE_GLO_CFG_EN_MASK;
+}
+
+static u32 airoha_ppe_get_timestamp(struct airoha_ppe *ppe)
+{
+	u16 timestamp = airoha_fe_rr(ppe->eth, REG_FE_FOE_TS);
+
+	return FIELD_GET(AIROHA_FOE_IB1_BIND_TIMESTAMP, timestamp);
+}
+
+static void airoha_ppe_hw_init(struct airoha_ppe *ppe)
+{
+	u32 sram_tb_size, sram_num_entries, dram_num_entries;
+	struct airoha_eth *eth = ppe->eth;
+	int i;
+
+	sram_tb_size = PPE_SRAM_NUM_ENTRIES * sizeof(struct airoha_foe_entry);
+	dram_num_entries = PPE_RAM_NUM_ENTRIES_SHIFT(PPE_DRAM_NUM_ENTRIES);
+
+	for (i = 0; i < PPE_NUM; i++) {
+		int p;
+
+		airoha_fe_wr(eth, REG_PPE_TB_BASE(i),
+			     ppe->foe_dma + sram_tb_size);
+
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE0(i),
+			      PPE_BIND_AGE0_DELTA_NON_L4 |
+			      PPE_BIND_AGE0_DELTA_UDP,
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_NON_L4, 1) |
+			      FIELD_PREP(PPE_BIND_AGE0_DELTA_UDP, 12));
+		airoha_fe_rmw(eth, REG_PPE_BND_AGE1(i),
+			      PPE_BIND_AGE1_DELTA_TCP_FIN |
+			      PPE_BIND_AGE1_DELTA_TCP,
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP_FIN, 1) |
+			      FIELD_PREP(PPE_BIND_AGE1_DELTA_TCP, 7));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_HASH_CFG(i),
+			      PPE_SRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH1_EN_MASK |
+			      PPE_DRAM_TABLE_EN_MASK |
+			      PPE_SRAM_HASH0_MODE_MASK |
+			      PPE_SRAM_HASH1_MODE_MASK |
+			      PPE_DRAM_HASH0_MODE_MASK |
+			      PPE_DRAM_HASH1_MODE_MASK,
+			      FIELD_PREP(PPE_SRAM_TABLE_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_EN_MASK, 1) |
+			      FIELD_PREP(PPE_SRAM_HASH1_MODE_MASK, 1) |
+			      FIELD_PREP(PPE_DRAM_HASH1_MODE_MASK, 3));
+
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(i),
+			      PPE_TB_CFG_SEARCH_MISS_MASK |
+			      PPE_TB_ENTRY_SIZE_MASK,
+			      FIELD_PREP(PPE_TB_CFG_SEARCH_MISS_MASK, 3) |
+			      FIELD_PREP(PPE_TB_ENTRY_SIZE_MASK, 0));
+
+		airoha_fe_wr(eth, REG_PPE_HASH_SEED(i), PPE_HASH_SEED);
+
+		for (p = 0; p < ARRAY_SIZE(eth->ports); p++)
+			airoha_fe_rmw(eth, REG_PPE_MTU(i, p),
+				      FP0_EGRESS_MTU_MASK |
+				      FP1_EGRESS_MTU_MASK,
+				      FIELD_PREP(FP0_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU) |
+				      FIELD_PREP(FP1_EGRESS_MTU_MASK,
+						 AIROHA_MAX_MTU));
+	}
+
+	if (airoha_ppe2_is_enabled(eth)) {
+		sram_num_entries =
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE1_SRAM_NUM_ENTRIES);
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(1),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+	} else {
+		sram_num_entries =
+			PPE_RAM_NUM_ENTRIES_SHIFT(PPE_SRAM_NUM_ENTRIES);
+		airoha_fe_rmw(eth, REG_PPE_TB_CFG(0),
+			      PPE_SRAM_TB_NUM_ENTRY_MASK |
+			      PPE_DRAM_TB_NUM_ENTRY_MASK,
+			      FIELD_PREP(PPE_SRAM_TB_NUM_ENTRY_MASK,
+					 sram_num_entries) |
+			      FIELD_PREP(PPE_DRAM_TB_NUM_ENTRY_MASK,
+					 dram_num_entries));
+	}
+}
+
+static void airoha_ppe_flow_mangle_eth(const struct flow_action_entry *act, void *eth)
+{
+	void *dest = eth + act->mangle.offset;
+	const void *src = &act->mangle.val;
+
+	if (act->mangle.offset > 8)
+		return;
+
+	if (act->mangle.mask == 0xffff) {
+		src += 2;
+		dest += 2;
+	}
+
+	memcpy(dest, src, act->mangle.mask ? 2 : 4);
+}
+
+static int airoha_ppe_flow_mangle_ports(const struct flow_action_entry *act,
+					struct airoha_flow_data *data)
+{
+	u32 val = be32_to_cpu((__force __be32)act->mangle.val);
+
+	switch (act->mangle.offset) {
+	case 0:
+		if ((__force __be32)act->mangle.mask == ~cpu_to_be32(0xffff))
+			data->dst_port = cpu_to_be16(val);
+		else
+			data->src_port = cpu_to_be16(val >> 16);
+		break;
+	case 2:
+		data->dst_port = cpu_to_be16(val);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_flow_mangle_ipv4(const struct flow_action_entry *act,
+				       struct airoha_flow_data *data)
+{
+	__be32 *dest;
+
+	switch (act->mangle.offset) {
+	case offsetof(struct iphdr, saddr):
+		dest = &data->v4.src_addr;
+		break;
+	case offsetof(struct iphdr, daddr):
+		dest = &data->v4.dst_addr;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	memcpy(dest, &act->mangle.val, sizeof(u32));
+
+	return 0;
+}
+
+static int airoha_get_dsa_port(struct net_device **dev)
+{
+#if IS_ENABLED(CONFIG_NET_DSA)
+	struct dsa_port *dp = dsa_port_from_netdev(*dev);
+
+	if (IS_ERR(dp))
+		return -ENODEV;
+
+	*dev = dsa_port_to_conduit(dp);
+	return dp->index;
+#else
+	return -ENODEV;
+#endif
+}
+
+static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe,
+					struct net_device *dev, int type,
+					struct airoha_flow_data *data,
+					int l4proto)
+{
+	int dsa_port = airoha_get_dsa_port(&dev);
+	struct airoha_foe_mac_info_common *l2;
+	u32 qdata, ports_pad, val;
+
+	memset(hwe, 0, sizeof(*hwe));
+
+	val = FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE, AIROHA_FOE_STATE_BIND) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_PACKET_TYPE, type) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_UDP, l4proto == IPPROTO_UDP) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VLAN_LAYER, data->vlan.num) |
+	      FIELD_PREP(AIROHA_FOE_IB1_BIND_VPM, data->vlan.num) |
+	      AIROHA_FOE_IB1_BIND_TTL;
+	hwe->ib1 = val;
+
+	val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f);
+	if (dsa_port >= 0)
+		val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, dsa_port);
+
+	if (dev) {
+		struct airoha_gdm_port *port = netdev_priv(dev);
+		u8 pse_port;
+
+		pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
+		val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port);
+	}
+
+	/* FIXME: implement QoS support setting pse_port to 2 (loopback)
+	 * for uplink and setting qos bit in ib2
+	 */
+
+	if (is_multicast_ether_addr(data->eth.h_dest))
+		val |= AIROHA_FOE_IB2_MULTICAST;
+
+	ports_pad = 0xa5a5a500 | (l4proto & 0xff);
+	if (type == PPE_PKT_TYPE_IPV4_ROUTE)
+		hwe->ipv4.orig_tuple.ports = ports_pad;
+	if (type == PPE_PKT_TYPE_IPV6_ROUTE_3T)
+		hwe->ipv6.ports = ports_pad;
+
+	qdata = FIELD_PREP(AIROHA_FOE_SHAPER_ID, 0x7f);
+	if (type == PPE_PKT_TYPE_BRIDGE) {
+		hwe->bridge.dest_mac_hi = get_unaligned_be32(data->eth.h_dest);
+		hwe->bridge.dest_mac_lo =
+			get_unaligned_be16(data->eth.h_dest + 4);
+		hwe->bridge.src_mac_hi =
+			get_unaligned_be16(data->eth.h_source);
+		hwe->bridge.src_mac_lo =
+			get_unaligned_be32(data->eth.h_source + 2);
+		hwe->bridge.data = qdata;
+		hwe->bridge.ib2 = val;
+		l2 = &hwe->bridge.l2.common;
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		hwe->ipv6.data = qdata;
+		hwe->ipv6.ib2 = val;
+		l2 = &hwe->ipv6.l2;
+	} else {
+		hwe->ipv4.data = qdata;
+		hwe->ipv4.ib2 = val;
+		l2 = &hwe->ipv4.l2.common;
+	}
+
+	l2->dest_mac_hi = get_unaligned_be32(data->eth.h_dest);
+	l2->dest_mac_lo = get_unaligned_be16(data->eth.h_dest + 4);
+	if (type <= PPE_PKT_TYPE_IPV4_DSLITE) {
+		l2->src_mac_hi = get_unaligned_be32(data->eth.h_source);
+		hwe->ipv4.l2.src_mac_lo =
+			get_unaligned_be16(data->eth.h_source + 4);
+	} else {
+		l2->src_mac_hi = FIELD_PREP(AIROHA_FOE_MAC_SMAC_ID, 0xf);
+	}
+
+	if (data->vlan.num) {
+		l2->etype = dsa_port >= 0 ? BIT(dsa_port) : 0;
+		l2->vlan1 = data->vlan.hdr[0].id;
+		if (data->vlan.num == 2)
+			l2->vlan2 = data->vlan.hdr[1].id;
+	} else if (dsa_port >= 0) {
+		l2->etype = BIT(15) | BIT(dsa_port);
+	} else if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+		l2->etype = ETH_P_IPV6;
+	} else {
+		l2->etype = ETH_P_IP;
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv4_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data,
+					       bool egress)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	struct airoha_foe_ipv4_tuple *t;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		if (egress) {
+			t = &hwe->ipv4.new_tuple;
+			break;
+		}
+		fallthrough;
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+		t = &hwe->ipv4.orig_tuple;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	t->src_ip = be32_to_cpu(data->v4.src_addr);
+	t->dest_ip = be32_to_cpu(data->v4.dst_addr);
+
+	if (type != PPE_PKT_TYPE_IPV4_ROUTE) {
+		t->src_port = be16_to_cpu(data->src_port);
+		t->dest_port = be16_to_cpu(data->dst_port);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_foe_entry_set_ipv6_tuple(struct airoha_foe_entry *hwe,
+					       struct airoha_flow_data *data)
+
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 *src, *dest;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+	case PPE_PKT_TYPE_IPV6_6RD:
+		hwe->ipv6.src_port = be16_to_cpu(data->src_port);
+		hwe->ipv6.dest_port = be16_to_cpu(data->dst_port);
+		fallthrough;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		src = hwe->ipv6.src_ip;
+		dest = hwe->ipv6.dest_ip;
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	ipv6_addr_be32_to_cpu(src, data->v6.src_addr.s6_addr32);
+	ipv6_addr_be32_to_cpu(dest, data->v6.dst_addr.s6_addr32);
+
+	return 0;
+}
+
+static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+	u32 hash, hv1, hv2, hv3;
+
+	switch (type) {
+	case PPE_PKT_TYPE_IPV4_ROUTE:
+	case PPE_PKT_TYPE_IPV4_HNAPT:
+		hv1 = hwe->ipv4.orig_tuple.ports;
+		hv2 = hwe->ipv4.orig_tuple.dest_ip;
+		hv3 = hwe->ipv4.orig_tuple.src_ip;
+		break;
+	case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+	case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+		hv1 = hwe->ipv6.src_ip[3] ^ hwe->ipv6.dest_ip[3];
+		hv1 ^= hwe->ipv6.ports;
+
+		hv2 = hwe->ipv6.src_ip[2] ^ hwe->ipv6.dest_ip[2];
+		hv2 ^= hwe->ipv6.dest_ip[0];
+
+		hv3 = hwe->ipv6.src_ip[1] ^ hwe->ipv6.dest_ip[1];
+		hv3 ^= hwe->ipv6.src_ip[0];
+		break;
+	case PPE_PKT_TYPE_IPV4_DSLITE:
+	case PPE_PKT_TYPE_IPV6_6RD:
+	default:
+		WARN_ON_ONCE(1);
+		return PPE_HASH_MASK;
+	}
+
+	hash = (hv1 & hv2) | ((~hv1) & hv3);
+	hash = (hash >> 24) | ((hash & 0xffffff) << 8);
+	hash ^= hv1 ^ hv2 ^ hv3;
+	hash ^= hash >> 16;
+	hash &= PPE_NUM_ENTRIES - 1;
+
+	return hash;
+}
+
+static struct airoha_foe_entry *
+airoha_ppe_foe_get_entry(struct airoha_ppe *ppe, u32 hash)
+{
+	if (hash < PPE_SRAM_NUM_ENTRIES) {
+		u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry);
+		struct airoha_eth *eth = ppe->eth;
+		bool ppe2;
+		u32 val;
+		int i;
+
+		ppe2 = airoha_ppe2_is_enabled(ppe->eth) &&
+		       hash >= PPE1_SRAM_NUM_ENTRIES;
+		airoha_fe_wr(ppe->eth, REG_PPE_RAM_CTRL(ppe2),
+			     FIELD_PREP(PPE_SRAM_CTRL_ENTRY_MASK, hash) |
+			     PPE_SRAM_CTRL_REQ_MASK);
+		if (read_poll_timeout_atomic(airoha_fe_rr, val,
+					     val & PPE_SRAM_CTRL_ACK_MASK,
+					     10, 100, false, eth,
+					     REG_PPE_RAM_CTRL(ppe2)))
+			return NULL;
+
+		for (i = 0; i < sizeof(struct airoha_foe_entry) / 4; i++)
+			hwe[i] = airoha_fe_rr(eth,
+					      REG_PPE_RAM_ENTRY(ppe2, i));
+	}
+
+	return ppe->foe + hash * sizeof(struct airoha_foe_entry);
+}
+
+static bool airoha_ppe_foe_compare_entry(struct airoha_flow_table_entry *e,
+					 struct airoha_foe_entry *hwe)
+{
+	int type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, e->data.ib1);
+	int len;
+
+	if ((hwe->ib1 ^ e->data.ib1) & AIROHA_FOE_IB1_BIND_UDP)
+		return false;
+
+	if (type > PPE_PKT_TYPE_IPV4_DSLITE)
+		len = offsetof(struct airoha_foe_entry, ipv6.data);
+	else
+		len = offsetof(struct airoha_foe_entry, ipv4.ib2);
+
+	return !memcmp(&e->data.d, &hwe->d, len - sizeof(hwe->ib1));
+}
+
+static int airoha_ppe_foe_commit_entry(struct airoha_ppe *ppe,
+				       struct airoha_foe_entry *e,
+				       u32 hash)
+{
+	struct airoha_foe_entry *hwe = ppe->foe + hash * sizeof(*hwe);
+	u32 ts = airoha_ppe_get_timestamp(ppe);
+	struct airoha_eth *eth = ppe->eth;
+
+	memcpy(&hwe->d, &e->d, sizeof(*hwe) - sizeof(hwe->ib1));
+	wmb();
+
+	e->ib1 &= ~AIROHA_FOE_IB1_BIND_TIMESTAMP;
+	e->ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_TIMESTAMP, ts);
+	hwe->ib1 = e->ib1;
+
+	if (hash < PPE_SRAM_NUM_ENTRIES) {
+		dma_addr_t addr = ppe->foe_dma + hash * sizeof(*hwe);
+		bool ppe2 = airoha_ppe2_is_enabled(eth) &&
+			    hash >= PPE1_SRAM_NUM_ENTRIES;
+		struct airoha_npu *npu;
+		int err = -ENODEV;
+
+		rcu_read_lock();
+		npu = rcu_dereference(eth->npu);
+		if (npu)
+			err = npu->ops.ppe_foe_commit_entry(npu, addr,
+							    sizeof(*hwe), hash,
+							    ppe2);
+		rcu_read_unlock();
+
+		return err;
+	}
+
+	return 0;
+}
+
+static void airoha_ppe_foe_insert_entry(struct airoha_ppe *ppe, u32 hash)
+{
+	struct airoha_flow_table_entry *e;
+	struct airoha_foe_entry *hwe;
+	struct hlist_node *n;
+	u32 index, state;
+
+	spin_lock_bh(&ppe_lock);
+
+	hwe = airoha_ppe_foe_get_entry(ppe, hash);
+	if (!hwe)
+		goto unlock;
+
+	state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+	if (state == AIROHA_FOE_STATE_BIND)
+		goto unlock;
+
+	index = airoha_ppe_foe_get_entry_hash(hwe);
+	hlist_for_each_entry_safe(e, n, &ppe->foe_flow[index], list) {
+		if (airoha_ppe_foe_compare_entry(e, hwe)) {
+			airoha_ppe_foe_commit_entry(ppe, &e->data, hash);
+			e->hash = hash;
+			break;
+		}
+	}
+unlock:
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int airoha_ppe_foe_flow_commit_entry(struct airoha_ppe *ppe,
+					    struct airoha_flow_table_entry *e)
+{
+	u32 hash = airoha_ppe_foe_get_entry_hash(&e->data);
+
+	e->hash = 0xffff;
+
+	spin_lock_bh(&ppe_lock);
+	hlist_add_head(&e->list, &ppe->foe_flow[hash]);
+	spin_unlock_bh(&ppe_lock);
+
+	return 0;
+}
+
+static void airoha_ppe_foe_flow_remove_entry(struct airoha_ppe *ppe,
+					     struct airoha_flow_table_entry *e)
+{
+	spin_lock_bh(&ppe_lock);
+
+	hlist_del_init(&e->list);
+	if (e->hash != 0xffff) {
+		e->data.ib1 &= ~AIROHA_FOE_IB1_BIND_STATE;
+		e->data.ib1 |= FIELD_PREP(AIROHA_FOE_IB1_BIND_STATE,
+					  AIROHA_FOE_STATE_INVALID);
+		airoha_ppe_foe_commit_entry(ppe, &e->data, e->hash);
+		e->hash = 0xffff;
+	}
+
+	spin_unlock_bh(&ppe_lock);
+}
+
+static int airoha_ppe_flow_offload_replace(struct airoha_gdm_port *port,
+					   struct flow_cls_offload *f)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(f);
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+	struct airoha_flow_data data = {};
+	struct net_device *odev = NULL;
+	struct flow_action_entry *act;
+	struct airoha_foe_entry hwe;
+	int err, i, offload_type;
+	u16 addr_type = 0;
+	u8 l4proto = 0;
+
+	if (rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params))
+		return -EEXIST;
+
+	if (!flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return -EOPNOTSUPP;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_CONTROL)) {
+		struct flow_match_control match;
+
+		flow_rule_match_control(rule, &match);
+		addr_type = match.key->addr_type;
+		if (flow_rule_has_control_flags(match.mask->flags,
+						f->common.extack))
+			return -EOPNOTSUPP;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_BASIC)) {
+		struct flow_match_basic match;
+
+		flow_rule_match_basic(rule, &match);
+		l4proto = match.key->ip_proto;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	switch (addr_type) {
+	case 0:
+		offload_type = PPE_PKT_TYPE_BRIDGE;
+		if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS)) {
+			struct flow_match_eth_addrs match;
+
+			flow_rule_match_eth_addrs(rule, &match);
+			memcpy(data.eth.h_dest, match.key->dst, ETH_ALEN);
+			memcpy(data.eth.h_source, match.key->src, ETH_ALEN);
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	case FLOW_DISSECTOR_KEY_IPV4_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV4_HNAPT;
+		break;
+	case FLOW_DISSECTOR_KEY_IPV6_ADDRS:
+		offload_type = PPE_PKT_TYPE_IPV6_ROUTE_5T;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_MANGLE:
+			if (offload_type == PPE_PKT_TYPE_BRIDGE)
+				return -EOPNOTSUPP;
+
+			if (act->mangle.htype == FLOW_ACT_MANGLE_HDR_TYPE_ETH)
+				airoha_ppe_flow_mangle_eth(act, &data.eth);
+			break;
+		case FLOW_ACTION_REDIRECT:
+			odev = act->dev;
+			break;
+		case FLOW_ACTION_CSUM:
+			break;
+		case FLOW_ACTION_VLAN_PUSH:
+			if (data.vlan.num == 2 ||
+			    act->vlan.proto != htons(ETH_P_8021Q))
+				return -EOPNOTSUPP;
+
+			data.vlan.hdr[data.vlan.num].id = act->vlan.vid;
+			data.vlan.hdr[data.vlan.num].proto = act->vlan.proto;
+			data.vlan.num++;
+			break;
+		case FLOW_ACTION_VLAN_POP:
+			break;
+		case FLOW_ACTION_PPPOE_PUSH:
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+	}
+
+	if (!is_valid_ether_addr(data.eth.h_source) ||
+	    !is_valid_ether_addr(data.eth.h_dest))
+		return -EINVAL;
+
+	err = airoha_ppe_foe_entry_prepare(&hwe, odev, offload_type,
+					   &data, l4proto);
+	if (err)
+		return err;
+
+	if (flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_PORTS)) {
+		struct flow_match_ports ports;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		flow_rule_match_ports(rule, &ports);
+		data.src_port = ports.key->src;
+		data.dst_port = ports.key->dst;
+	} else if (offload_type != PPE_PKT_TYPE_BRIDGE) {
+		return -EOPNOTSUPP;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		struct flow_match_ipv4_addrs addrs;
+
+		flow_rule_match_ipv4_addrs(rule, &addrs);
+		data.v4.src_addr = addrs.key->src;
+		data.v4.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, false);
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) {
+		struct flow_match_ipv6_addrs addrs;
+
+		flow_rule_match_ipv6_addrs(rule, &addrs);
+
+		data.v6.src_addr = addrs.key->src;
+		data.v6.dst_addr = addrs.key->dst;
+		airoha_ppe_foe_entry_set_ipv6_tuple(&hwe, &data);
+	}
+
+	flow_action_for_each(i, act, &rule->action) {
+		if (act->id != FLOW_ACTION_MANGLE)
+			continue;
+
+		if (offload_type == PPE_PKT_TYPE_BRIDGE)
+			return -EOPNOTSUPP;
+
+		switch (act->mangle.htype) {
+		case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
+		case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
+			err = airoha_ppe_flow_mangle_ports(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_IP4:
+			err = airoha_ppe_flow_mangle_ipv4(act, &data);
+			break;
+		case FLOW_ACT_MANGLE_HDR_TYPE_ETH:
+			/* handled earlier */
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		if (err)
+			return err;
+	}
+
+	if (addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) {
+		err = airoha_ppe_foe_entry_set_ipv4_tuple(&hwe, &data, true);
+		if (err)
+			return err;
+	}
+
+	e = kzalloc(sizeof(*e), GFP_KERNEL);
+	if (!e)
+		return -ENOMEM;
+
+	e->cookie = f->cookie;
+	memcpy(&e->data, &hwe, sizeof(e->data));
+
+	err = airoha_ppe_foe_flow_commit_entry(eth->ppe, e);
+	if (err)
+		goto free_entry;
+
+	err = rhashtable_insert_fast(&eth->flow_table, &e->node,
+				     airoha_flow_table_params);
+	if (err < 0)
+		goto remove_foe_entry;
+
+	return 0;
+
+remove_foe_entry:
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+free_entry:
+	kfree(e);
+
+	return err;
+}
+
+static int airoha_ppe_flow_offload_destroy(struct airoha_gdm_port *port,
+					   struct flow_cls_offload *f)
+{
+	struct airoha_eth *eth = port->qdma->eth;
+	struct airoha_flow_table_entry *e;
+
+	e = rhashtable_lookup(&eth->flow_table, &f->cookie,
+			      airoha_flow_table_params);
+	if (!e)
+		return -ENOENT;
+
+	airoha_ppe_foe_flow_remove_entry(eth->ppe, e);
+	rhashtable_remove_fast(&eth->flow_table, &e->node,
+			       airoha_flow_table_params);
+	kfree(e);
+
+	return 0;
+}
+
+static int airoha_ppe_flow_offload_cmd(struct airoha_gdm_port *port,
+				       struct flow_cls_offload *f)
+{
+	switch (f->command) {
+	case FLOW_CLS_REPLACE:
+		return airoha_ppe_flow_offload_replace(port, f);
+	case FLOW_CLS_DESTROY:
+		return airoha_ppe_flow_offload_destroy(port, f);
+	default:
+		break;
+	}
+
+	return -EOPNOTSUPP;
+}
+
+static int airoha_ppe_flush_sram_entries(struct airoha_ppe *ppe,
+					 struct airoha_npu *npu)
+{
+	int i, sram_num_entries = PPE_SRAM_NUM_ENTRIES;
+	struct airoha_foe_entry *hwe = ppe->foe;
+
+	if (airoha_ppe2_is_enabled(ppe->eth))
+		sram_num_entries = sram_num_entries / 2;
+
+	for (i = 0; i < sram_num_entries; i++)
+		memset(&hwe[i], 0, sizeof(*hwe));
+
+	return npu->ops.ppe_flush_sram_entries(npu, ppe->foe_dma,
+					       PPE_SRAM_NUM_ENTRIES);
+}
+
+static struct airoha_npu *airoha_ppe_npu_get(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_npu_get(eth->dev);
+
+	if (IS_ERR(npu)) {
+		request_module("airoha-npu");
+		npu = airoha_npu_get(eth->dev);
+	}
+
+	return npu;
+}
+
+static int airoha_ppe_offload_setup(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu = airoha_ppe_npu_get(eth);
+	int err;
+
+	if (IS_ERR(npu))
+		return PTR_ERR(npu);
+
+	err = npu->ops.ppe_init(npu);
+	if (err)
+		goto error_npu_put;
+
+	airoha_ppe_hw_init(eth->ppe);
+	err = airoha_ppe_flush_sram_entries(eth->ppe, npu);
+	if (err)
+		goto error_npu_put;
+
+	rcu_assign_pointer(eth->npu, npu);
+	synchronize_rcu();
+
+	return 0;
+
+error_npu_put:
+	airoha_npu_put(npu);
+
+	return err;
+}
+
+int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
+				 void *cb_priv)
+{
+	struct flow_cls_offload *cls = type_data;
+	struct net_device *dev = cb_priv;
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+	int err = 0;
+
+	if (!tc_can_offload(dev) || type != TC_SETUP_CLSFLOWER)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&flow_offload_mutex);
+
+	if (!eth->npu)
+		err = airoha_ppe_offload_setup(eth);
+	if (!err)
+		err = airoha_ppe_flow_offload_cmd(port, cls);
+
+	mutex_unlock(&flow_offload_mutex);
+
+	return err;
+}
+
+void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash)
+{
+	u16 now, diff;
+
+	if (hash > PPE_HASH_MASK)
+		return;
+
+	now = (u16)jiffies;
+	diff = now - ppe->foe_check_time[hash];
+	if (diff < HZ / 10)
+		return;
+
+	ppe->foe_check_time[hash] = now;
+	airoha_ppe_foe_insert_entry(ppe, hash);
+}
+
+int airoha_ppe_init(struct airoha_eth *eth)
+{
+	struct airoha_ppe *ppe;
+	int foe_size;
+
+	ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL);
+	if (!ppe)
+		return -ENOMEM;
+
+	foe_size = PPE_NUM_ENTRIES * sizeof(struct airoha_foe_entry);
+	ppe->foe = dmam_alloc_coherent(eth->dev, foe_size, &ppe->foe_dma,
+				       GFP_KERNEL);
+	if (!ppe->foe)
+		return -ENOMEM;
+
+	ppe->eth = eth;
+	eth->ppe = ppe;
+
+	ppe->foe_flow = devm_kzalloc(eth->dev,
+				     PPE_NUM_ENTRIES * sizeof(*ppe->foe_flow),
+				     GFP_KERNEL);
+	if (!ppe->foe_flow)
+		return -ENOMEM;
+
+	return rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
+}
+
+void airoha_ppe_deinit(struct airoha_eth *eth)
+{
+	struct airoha_npu *npu;
+
+	rcu_read_lock();
+	npu = rcu_dereference(eth->npu);
+	if (npu) {
+		npu->ops.ppe_deinit(npu);
+		airoha_npu_put(npu);
+	}
+	rcu_read_unlock();
+
+	rhashtable_destroy(&eth->flow_table);
+}
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index e467dd81ff44a..6cc64c60953a3 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -15,6 +15,7 @@
 #define CDM1_BASE			0x0400
 #define GDM1_BASE			0x0500
 #define PPE1_BASE			0x0c00
+#define PPE2_BASE			0x1c00
 
 #define CDM2_BASE			0x1400
 #define GDM2_BASE			0x1500
@@ -36,6 +37,7 @@
 #define FE_RST_GDM3_MBI_ARB_MASK	BIT(2)
 #define FE_RST_CORE_MASK		BIT(0)
 
+#define REG_FE_FOE_TS			0x0010
 #define REG_FE_WAN_MAC_H		0x0030
 #define REG_FE_LAN_MAC_H		0x0040
 
@@ -192,11 +194,106 @@
 #define REG_FE_GDM_RX_ETH_L511_CNT_L(_n)	(GDM_BASE(_n) + 0x198)
 #define REG_FE_GDM_RX_ETH_L1023_CNT_L(_n)	(GDM_BASE(_n) + 0x19c)
 
-#define REG_PPE1_TB_HASH_CFG		(PPE1_BASE + 0x250)
-#define PPE1_SRAM_TABLE_EN_MASK		BIT(0)
-#define PPE1_SRAM_HASH1_EN_MASK		BIT(8)
-#define PPE1_DRAM_TABLE_EN_MASK		BIT(16)
-#define PPE1_DRAM_HASH1_EN_MASK		BIT(24)
+#define REG_PPE_GLO_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x200)
+#define PPE_GLO_CFG_BUSY_MASK			BIT(31)
+#define PPE_GLO_CFG_FLOW_DROP_UPDATE_MASK	BIT(9)
+#define PPE_GLO_CFG_PSE_HASH_OFS_MASK		BIT(6)
+#define PPE_GLO_CFG_PPE_BSWAP_MASK		BIT(5)
+#define PPE_GLO_CFG_TTL_DROP_MASK		BIT(4)
+#define PPE_GLO_CFG_IP4_CS_DROP_MASK		BIT(3)
+#define PPE_GLO_CFG_IP4_L4_CS_DROP_MASK		BIT(2)
+#define PPE_GLO_CFG_EN_MASK			BIT(0)
+
+#define REG_PPE_PPE_FLOW_CFG(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x204)
+#define PPE_FLOW_CFG_IP6_HASH_GRE_KEY_MASK	BIT(20)
+#define PPE_FLOW_CFG_IP4_HASH_GRE_KEY_MASK	BIT(19)
+#define PPE_FLOW_CFG_IP4_HASH_FLOW_LABEL_MASK	BIT(18)
+#define PPE_FLOW_CFG_IP4_NAT_FRAG_MASK		BIT(17)
+#define PPE_FLOW_CFG_IP_PROTO_BLACKLIST_MASK	BIT(16)
+#define PPE_FLOW_CFG_IP4_DSLITE_MASK		BIT(14)
+#define PPE_FLOW_CFG_IP4_NAPT_MASK		BIT(13)
+#define PPE_FLOW_CFG_IP4_NAT_MASK		BIT(12)
+#define PPE_FLOW_CFG_IP6_6RD_MASK		BIT(10)
+#define PPE_FLOW_CFG_IP6_5T_ROUTE_MASK		BIT(9)
+#define PPE_FLOW_CFG_IP6_3T_ROUTE_MASK		BIT(8)
+#define PPE_FLOW_CFG_IP4_UDP_FRAG_MASK		BIT(7)
+#define PPE_FLOW_CFG_IP4_TCP_FRAG_MASK		BIT(6)
+
+#define REG_PPE_IP_PROTO_CHK(_n)		(((_n) ? PPE2_BASE : PPE1_BASE) + 0x208)
+#define PPE_IP_PROTO_CHK_IPV4_MASK		GENMASK(15, 0)
+#define PPE_IP_PROTO_CHK_IPV6_MASK		GENMASK(31, 16)
+
+#define REG_PPE_TB_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x21c)
+#define PPE_SRAM_TB_NUM_ENTRY_MASK		GENMASK(26, 24)
+#define PPE_TB_CFG_KEEPALIVE_MASK		GENMASK(13, 12)
+#define PPE_TB_CFG_AGE_TCP_FIN_MASK		BIT(11)
+#define PPE_TB_CFG_AGE_UDP_MASK			BIT(10)
+#define PPE_TB_CFG_AGE_TCP_MASK			BIT(9)
+#define PPE_TB_CFG_AGE_UNBIND_MASK		BIT(8)
+#define PPE_TB_CFG_AGE_NON_L4_MASK		BIT(7)
+#define PPE_TB_CFG_AGE_PREBIND_MASK		BIT(6)
+#define PPE_TB_CFG_SEARCH_MISS_MASK		GENMASK(5, 4)
+#define PPE_TB_ENTRY_SIZE_MASK			BIT(3)
+#define PPE_DRAM_TB_NUM_ENTRY_MASK		GENMASK(2, 0)
+
+#define REG_PPE_TB_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x220)
+
+#define REG_PPE_BIND_RATE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x228)
+#define PPE_BIND_RATE_L2B_BIND_MASK		GENMASK(31, 16)
+#define PPE_BIND_RATE_BIND_MASK			GENMASK(15, 0)
+
+#define REG_PPE_BIND_LIMIT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x22c)
+#define PPE_BIND_LIMIT0_HALF_MASK		GENMASK(29, 16)
+#define PPE_BIND_LIMIT0_QUARTER_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BIND_LIMIT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x230)
+#define PPE_BIND_LIMIT1_NON_L4_MASK		GENMASK(23, 16)
+#define PPE_BIND_LIMIT1_FULL_MASK		GENMASK(13, 0)
+
+#define REG_PPE_BND_AGE0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x23c)
+#define PPE_BIND_AGE0_DELTA_NON_L4		GENMASK(30, 16)
+#define PPE_BIND_AGE0_DELTA_UDP			GENMASK(14, 0)
+
+#define REG_PPE_UNBIND_AGE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x238)
+#define PPE_UNBIND_AGE_MIN_PACKETS_MASK		GENMASK(31, 16)
+#define PPE_UNBIND_AGE_DELTA_MASK		GENMASK(7, 0)
+
+#define REG_PPE_BND_AGE1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x240)
+#define PPE_BIND_AGE1_DELTA_TCP_FIN		GENMASK(30, 16)
+#define PPE_BIND_AGE1_DELTA_TCP			GENMASK(14, 0)
+
+#define REG_PPE_HASH_SEED(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x244)
+#define PPE_HASH_SEED				0x12345678
+
+#define REG_PPE_DFT_CPORT0(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x248)
+
+#define REG_PPE_DFT_CPORT1(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x24c)
+
+#define REG_PPE_TB_HASH_CFG(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x250)
+#define PPE_DRAM_HASH1_MODE_MASK		GENMASK(31, 28)
+#define PPE_DRAM_HASH1_EN_MASK			BIT(24)
+#define PPE_DRAM_HASH0_MODE_MASK		GENMASK(23, 20)
+#define PPE_DRAM_TABLE_EN_MASK			BIT(16)
+#define PPE_SRAM_HASH1_MODE_MASK		GENMASK(15, 12)
+#define PPE_SRAM_HASH1_EN_MASK			BIT(8)
+#define PPE_SRAM_HASH0_MODE_MASK		GENMASK(7, 4)
+#define PPE_SRAM_TABLE_EN_MASK			BIT(0)
+
+#define REG_PPE_MTU_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x304)
+#define REG_PPE_MTU(_m, _n)			(REG_PPE_MTU_BASE(_m) + ((_n) << 2))
+#define FP1_EGRESS_MTU_MASK			GENMASK(29, 16)
+#define FP0_EGRESS_MTU_MASK			GENMASK(13, 0)
+
+#define REG_PPE_RAM_CTRL(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x31c)
+#define PPE_SRAM_CTRL_ACK_MASK			BIT(31)
+#define PPE_SRAM_CTRL_DUAL_SUCESS_MASK		BIT(30)
+#define PPE_SRAM_CTRL_ENTRY_MASK		GENMASK(23, 8)
+#define PPE_SRAM_WR_DUAL_DIRECTION_MASK		BIT(2)
+#define PPE_SRAM_CTRL_WR_MASK			BIT(1)
+#define PPE_SRAM_CTRL_REQ_MASK			BIT(0)
+
+#define REG_PPE_RAM_BASE(_n)			(((_n) ? PPE2_BASE : PPE1_BASE) + 0x320)
+#define REG_PPE_RAM_ENTRY(_m, _n)		(REG_PPE_RAM_BASE(_m) + ((_n) << 2))
 
 #define REG_FE_GDM_TX_OK_PKT_CNT_H(_n)		(GDM_BASE(_n) + 0x280)
 #define REG_FE_GDM_TX_OK_BYTE_CNT_H(_n)		(GDM_BASE(_n) + 0x284)

From 9cd451d414f6e29f507a216fb3b19fa68c011f8c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:22 +0100
Subject: [PATCH 1496/2753] net: airoha: Add loopback support for GDM2

Enable hw redirection for traffic received on GDM2 port to GDM{3,4}.
This is required to apply Qdisc offloading (HTB or ETS) for traffic to
and from GDM{3,4} port.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/airoha_eth.c  | 71 ++++++++++++++++++++++-
 drivers/net/ethernet/airoha/airoha_eth.h  |  7 +++
 drivers/net/ethernet/airoha/airoha_ppe.c  | 12 ++--
 drivers/net/ethernet/airoha/airoha_regs.h | 29 +++++++++
 4 files changed, 111 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 382ed81df8088..ff837168845d6 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1588,14 +1588,81 @@ static int airoha_dev_set_macaddr(struct net_device *dev, void *p)
 	return 0;
 }
 
+static void airhoha_set_gdm2_loopback(struct airoha_gdm_port *port)
+{
+	u32 pse_port = port->id == 3 ? FE_PSE_PORT_GDM3 : FE_PSE_PORT_GDM4;
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 chan = port->id == 3 ? 4 : 0;
+
+	/* Forward the traffic to the proper GDM port */
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(2), pse_port);
+	airoha_fe_clear(eth, REG_GDM_FWD_CFG(2), GDM_STRIP_CRC);
+
+	/* Enable GDM2 loopback */
+	airoha_fe_wr(eth, REG_GDM_TXCHN_EN(2), 0xffffffff);
+	airoha_fe_wr(eth, REG_GDM_RXCHN_EN(2), 0xffff);
+	airoha_fe_rmw(eth, REG_GDM_LPBK_CFG(2),
+		      LPBK_CHAN_MASK | LPBK_MODE_MASK | LPBK_EN_MASK,
+		      FIELD_PREP(LPBK_CHAN_MASK, chan) | LPBK_EN_MASK);
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(2),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, AIROHA_MAX_MTU));
+
+	/* Disable VIP and IFC for GDM2 */
+	airoha_fe_clear(eth, REG_FE_VIP_PORT_EN, BIT(2));
+	airoha_fe_clear(eth, REG_FE_IFC_PORT_EN, BIT(2));
+
+	if (port->id == 3) {
+		/* FIXME: handle XSI_PCE1_PORT */
+		airoha_fe_wr(eth, REG_PPE_DFT_CPORT0(0),  0x5500);
+		airoha_fe_rmw(eth, REG_FE_WAN_PORT,
+			      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
+			      FIELD_PREP(WAN0_MASK, HSGMII_LAN_PCIE0_SRCPORT));
+		airoha_fe_rmw(eth,
+			      REG_SP_DFT_CPORT(HSGMII_LAN_PCIE0_SRCPORT >> 3),
+			      SP_CPORT_PCIE0_MASK,
+			      FIELD_PREP(SP_CPORT_PCIE0_MASK,
+					 FE_PSE_PORT_CDM2));
+	} else {
+		/* FIXME: handle XSI_USB_PORT */
+		airoha_fe_rmw(eth, REG_SRC_PORT_FC_MAP6,
+			      FC_ID_OF_SRC_PORT24_MASK,
+			      FIELD_PREP(FC_ID_OF_SRC_PORT24_MASK, 2));
+		airoha_fe_rmw(eth, REG_FE_WAN_PORT,
+			      WAN1_EN_MASK | WAN1_MASK | WAN0_MASK,
+			      FIELD_PREP(WAN0_MASK, HSGMII_LAN_ETH_SRCPORT));
+		airoha_fe_rmw(eth,
+			      REG_SP_DFT_CPORT(HSGMII_LAN_ETH_SRCPORT >> 3),
+			      SP_CPORT_ETH_MASK,
+			      FIELD_PREP(SP_CPORT_ETH_MASK, FE_PSE_PORT_CDM2));
+	}
+}
+
 static int airoha_dev_init(struct net_device *dev)
 {
 	struct airoha_gdm_port *port = netdev_priv(dev);
 	struct airoha_eth *eth = port->qdma->eth;
+	u32 pse_port;
 
 	airoha_set_macaddr(port, dev->dev_addr);
-	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id),
-				    FE_PSE_PORT_PPE1);
+
+	switch (port->id) {
+	case 3:
+	case 4:
+		/* If GDM2 is active we can't enable loopback */
+		if (!eth->ports[1])
+			airhoha_set_gdm2_loopback(port);
+		fallthrough;
+	case 2:
+		pse_port = FE_PSE_PORT_PPE2;
+		break;
+	default:
+		pse_port = FE_PSE_PORT_PPE1;
+		break;
+	}
+
+	airoha_set_gdm_port_fwd_cfg(eth, REG_GDM_FWD_CFG(port->id), pse_port);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index db25a6d3b2cd1..a59ff6e41890a 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -67,6 +67,13 @@ enum {
 	QDMA_INT_REG_MAX
 };
 
+enum {
+	HSGMII_LAN_PCIE0_SRCPORT = 0x16,
+	HSGMII_LAN_PCIE1_SRCPORT,
+	HSGMII_LAN_ETH_SRCPORT,
+	HSGMII_LAN_USB_SRCPORT,
+};
+
 enum {
 	XSI_PCIE0_VIP_PORT_MASK	= BIT(22),
 	XSI_PCIE1_VIP_PORT_MASK	= BIT(23),
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 37074121224a3..de291f44cf14b 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -216,7 +216,8 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe,
 	      AIROHA_FOE_IB1_BIND_TTL;
 	hwe->ib1 = val;
 
-	val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f);
+	val = FIELD_PREP(AIROHA_FOE_IB2_PORT_AG, 0x1f) |
+	      AIROHA_FOE_IB2_PSE_QOS;
 	if (dsa_port >= 0)
 		val |= FIELD_PREP(AIROHA_FOE_IB2_NBQ, dsa_port);
 
@@ -224,14 +225,13 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe,
 		struct airoha_gdm_port *port = netdev_priv(dev);
 		u8 pse_port;
 
-		pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
+		if (dsa_port >= 0)
+			pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
+		else
+			pse_port = 2; /* uplink relies on GDM2 loopback */
 		val |= FIELD_PREP(AIROHA_FOE_IB2_PSE_PORT, pse_port);
 	}
 
-	/* FIXME: implement QoS support setting pse_port to 2 (loopback)
-	 * for uplink and setting qos bit in ib2
-	 */
-
 	if (is_multicast_ether_addr(data->eth.h_dest))
 		val |= AIROHA_FOE_IB2_MULTICAST;
 
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 6cc64c60953a3..1aa06cdffe232 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -38,6 +38,12 @@
 #define FE_RST_CORE_MASK		BIT(0)
 
 #define REG_FE_FOE_TS			0x0010
+
+#define REG_FE_WAN_PORT			0x0024
+#define WAN1_EN_MASK			BIT(16)
+#define WAN1_MASK			GENMASK(12, 8)
+#define WAN0_MASK			GENMASK(4, 0)
+
 #define REG_FE_WAN_MAC_H		0x0030
 #define REG_FE_LAN_MAC_H		0x0040
 
@@ -126,6 +132,7 @@
 #define GDM_IP4_CKSUM			BIT(22)
 #define GDM_TCP_CKSUM			BIT(21)
 #define GDM_UDP_CKSUM			BIT(20)
+#define GDM_STRIP_CRC			BIT(16)
 #define GDM_UCFQ_MASK			GENMASK(15, 12)
 #define GDM_BCFQ_MASK			GENMASK(11, 8)
 #define GDM_MCFQ_MASK			GENMASK(7, 4)
@@ -139,6 +146,16 @@
 #define GDM_SHORT_LEN_MASK		GENMASK(13, 0)
 #define GDM_LONG_LEN_MASK		GENMASK(29, 16)
 
+#define REG_GDM_LPBK_CFG(_n)		(GDM_BASE(_n) + 0x1c)
+#define LPBK_GAP_MASK			GENMASK(31, 24)
+#define LPBK_LEN_MASK			GENMASK(23, 10)
+#define LPBK_CHAN_MASK			GENMASK(8, 4)
+#define LPBK_MODE_MASK			GENMASK(3, 1)
+#define LPBK_EN_MASK			BIT(0)
+
+#define REG_GDM_TXCHN_EN(_n)		(GDM_BASE(_n) + 0x24)
+#define REG_GDM_RXCHN_EN(_n)		(GDM_BASE(_n) + 0x28)
+
 #define REG_FE_CPORT_CFG		(GDM1_BASE + 0x40)
 #define FE_CPORT_PAD			BIT(26)
 #define FE_CPORT_PORT_XFC_MASK		BIT(25)
@@ -351,6 +368,18 @@
 
 #define REG_MC_VLAN_DATA		0x2108
 
+#define REG_SP_DFT_CPORT(_n)		(0x20e0 + ((_n) << 2))
+#define SP_CPORT_PCIE1_MASK		GENMASK(31, 28)
+#define SP_CPORT_PCIE0_MASK		GENMASK(27, 24)
+#define SP_CPORT_USB_MASK		GENMASK(7, 4)
+#define SP_CPORT_ETH_MASK		GENMASK(7, 4)
+
+#define REG_SRC_PORT_FC_MAP6		0x2298
+#define FC_ID_OF_SRC_PORT27_MASK	GENMASK(28, 24)
+#define FC_ID_OF_SRC_PORT26_MASK	GENMASK(20, 16)
+#define FC_ID_OF_SRC_PORT25_MASK	GENMASK(12, 8)
+#define FC_ID_OF_SRC_PORT24_MASK	GENMASK(4, 0)
+
 #define REG_CDM5_RX_OQ1_DROP_CNT	0x29d4
 
 /* QDMA */

From 3fe15c640f3808c3faf235553c67c867d1389e5c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Fri, 28 Feb 2025 11:54:23 +0100
Subject: [PATCH 1497/2753] net: airoha: Introduce PPE debugfs support

Similar to PPE support for Mediatek devices, introduce PPE debugfs
in order to dump binded and unbinded flows.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/airoha/Makefile          |   1 +
 drivers/net/ethernet/airoha/airoha_eth.h      |  14 ++
 drivers/net/ethernet/airoha/airoha_ppe.c      |  17 +-
 .../net/ethernet/airoha/airoha_ppe_debugfs.c  | 181 ++++++++++++++++++
 4 files changed, 209 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/airoha/airoha_ppe_debugfs.c

diff --git a/drivers/net/ethernet/airoha/Makefile b/drivers/net/ethernet/airoha/Makefile
index 6deff2f16229a..94468053e34be 100644
--- a/drivers/net/ethernet/airoha/Makefile
+++ b/drivers/net/ethernet/airoha/Makefile
@@ -5,4 +5,5 @@
 
 obj-$(CONFIG_NET_AIROHA) += airoha-eth.o
 airoha-eth-y := airoha_eth.o airoha_ppe.o
+airoha-eth-$(CONFIG_DEBUG_FS) += airoha_ppe_debugfs.o
 obj-$(CONFIG_NET_AIROHA_NPU) += airoha_npu.o
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index a59ff6e41890a..b7a3bd7a76b7b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -7,6 +7,7 @@
 #ifndef AIROHA_ETH_H
 #define AIROHA_ETH_H
 
+#include <linux/debugfs.h>
 #include <linux/etherdevice.h>
 #include <linux/iopoll.h>
 #include <linux/kernel.h>
@@ -480,6 +481,8 @@ struct airoha_ppe {
 
 	struct hlist_head *foe_flow;
 	u16 foe_check_time[PPE_NUM_ENTRIES];
+
+	struct dentry *debugfs_dir;
 };
 
 struct airoha_eth {
@@ -533,5 +536,16 @@ int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				 void *cb_priv);
 int airoha_ppe_init(struct airoha_eth *eth);
 void airoha_ppe_deinit(struct airoha_eth *eth);
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash);
+
+#if CONFIG_DEBUG_FS
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe);
+#else
+static inline int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	return 0;
+}
+#endif
 
 #endif /* AIROHA_ETH_H */
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index de291f44cf14b..8b55e871352d3 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -390,8 +390,8 @@ static u32 airoha_ppe_foe_get_entry_hash(struct airoha_foe_entry *hwe)
 	return hash;
 }
 
-static struct airoha_foe_entry *
-airoha_ppe_foe_get_entry(struct airoha_ppe *ppe, u32 hash)
+struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
+						  u32 hash)
 {
 	if (hash < PPE_SRAM_NUM_ENTRIES) {
 		u32 *hwe = ppe->foe + hash * sizeof(struct airoha_foe_entry);
@@ -861,7 +861,7 @@ void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash)
 int airoha_ppe_init(struct airoha_eth *eth)
 {
 	struct airoha_ppe *ppe;
-	int foe_size;
+	int foe_size, err;
 
 	ppe = devm_kzalloc(eth->dev, sizeof(*ppe), GFP_KERNEL);
 	if (!ppe)
@@ -882,7 +882,15 @@ int airoha_ppe_init(struct airoha_eth *eth)
 	if (!ppe->foe_flow)
 		return -ENOMEM;
 
-	return rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
+	err = rhashtable_init(&eth->flow_table, &airoha_flow_table_params);
+	if (err)
+		return err;
+
+	err = airoha_ppe_debugfs_init(ppe);
+	if (err)
+		rhashtable_destroy(&eth->flow_table);
+
+	return err;
 }
 
 void airoha_ppe_deinit(struct airoha_eth *eth)
@@ -898,4 +906,5 @@ void airoha_ppe_deinit(struct airoha_eth *eth)
 	rcu_read_unlock();
 
 	rhashtable_destroy(&eth->flow_table);
+	debugfs_remove(eth->ppe->debugfs_dir);
 }
diff --git a/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
new file mode 100644
index 0000000000000..3cdc6fd53fc75
--- /dev/null
+++ b/drivers/net/ethernet/airoha/airoha_ppe_debugfs.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2025 AIROHA Inc
+ * Author: Lorenzo Bianconi <lorenzo@kernel.org>
+ */
+
+#include "airoha_eth.h"
+
+static void airoha_debugfs_ppe_print_tuple(struct seq_file *m,
+					   void *src_addr, void *dest_addr,
+					   u16 *src_port, u16 *dest_port,
+					   bool ipv6)
+{
+	__be32 n_addr[IPV6_ADDR_WORDS];
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, src_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", src_addr);
+	}
+	if (src_port)
+		seq_printf(m, ":%d", *src_port);
+
+	seq_puts(m, "->");
+
+	if (ipv6) {
+		ipv6_addr_cpu_to_be32(n_addr, dest_addr);
+		seq_printf(m, "%pI6", n_addr);
+	} else {
+		seq_printf(m, "%pI4h", dest_addr);
+	}
+	if (dest_port)
+		seq_printf(m, ":%d", *dest_port);
+}
+
+static int airoha_ppe_debugfs_foe_show(struct seq_file *m, void *private,
+				       bool bind)
+{
+	static const char *const ppe_type_str[] = {
+		[PPE_PKT_TYPE_IPV4_HNAPT] = "IPv4 5T",
+		[PPE_PKT_TYPE_IPV4_ROUTE] = "IPv4 3T",
+		[PPE_PKT_TYPE_BRIDGE] = "L2B",
+		[PPE_PKT_TYPE_IPV4_DSLITE] = "DS-LITE",
+		[PPE_PKT_TYPE_IPV6_ROUTE_3T] = "IPv6 3T",
+		[PPE_PKT_TYPE_IPV6_ROUTE_5T] = "IPv6 5T",
+		[PPE_PKT_TYPE_IPV6_6RD] = "6RD",
+	};
+	static const char *const ppe_state_str[] = {
+		[AIROHA_FOE_STATE_INVALID] = "INV",
+		[AIROHA_FOE_STATE_UNBIND] = "UNB",
+		[AIROHA_FOE_STATE_BIND] = "BND",
+		[AIROHA_FOE_STATE_FIN] = "FIN",
+	};
+	struct airoha_ppe *ppe = m->private;
+	int i;
+
+	for (i = 0; i < PPE_NUM_ENTRIES; i++) {
+		const char *state_str, *type_str = "UNKNOWN";
+		void *src_addr = NULL, *dest_addr = NULL;
+		u16 *src_port = NULL, *dest_port = NULL;
+		struct airoha_foe_mac_info_common *l2;
+		unsigned char h_source[ETH_ALEN] = {};
+		unsigned char h_dest[ETH_ALEN];
+		struct airoha_foe_entry *hwe;
+		u32 type, state, ib2, data;
+		bool ipv6 = false;
+
+		hwe = airoha_ppe_foe_get_entry(ppe, i);
+		if (!hwe)
+			continue;
+
+		state = FIELD_GET(AIROHA_FOE_IB1_BIND_STATE, hwe->ib1);
+		if (!state)
+			continue;
+
+		if (bind && state != AIROHA_FOE_STATE_BIND)
+			continue;
+
+		state_str = ppe_state_str[state % ARRAY_SIZE(ppe_state_str)];
+		type = FIELD_GET(AIROHA_FOE_IB1_BIND_PACKET_TYPE, hwe->ib1);
+		if (type < ARRAY_SIZE(ppe_type_str) && ppe_type_str[type])
+			type_str = ppe_type_str[type];
+
+		seq_printf(m, "%05x %s %7s", i, state_str, type_str);
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.orig_tuple.src_port;
+			dest_port = &hwe->ipv4.orig_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.orig_tuple.src_ip;
+			dest_addr = &hwe->ipv4.orig_tuple.dest_ip;
+			break;
+		case PPE_PKT_TYPE_IPV6_ROUTE_5T:
+			src_port = &hwe->ipv6.src_port;
+			dest_port = &hwe->ipv6.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV6_ROUTE_3T:
+		case PPE_PKT_TYPE_IPV6_6RD:
+			src_addr = &hwe->ipv6.src_ip;
+			dest_addr = &hwe->ipv6.dest_ip;
+			ipv6 = true;
+			break;
+		default:
+			break;
+		}
+
+		if (src_addr && dest_addr) {
+			seq_puts(m, " orig=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port, ipv6);
+		}
+
+		switch (type) {
+		case PPE_PKT_TYPE_IPV4_HNAPT:
+		case PPE_PKT_TYPE_IPV4_DSLITE:
+			src_port = &hwe->ipv4.new_tuple.src_port;
+			dest_port = &hwe->ipv4.new_tuple.dest_port;
+			fallthrough;
+		case PPE_PKT_TYPE_IPV4_ROUTE:
+			src_addr = &hwe->ipv4.new_tuple.src_ip;
+			dest_addr = &hwe->ipv4.new_tuple.dest_ip;
+			seq_puts(m, " new=");
+			airoha_debugfs_ppe_print_tuple(m, src_addr, dest_addr,
+						       src_port, dest_port,
+						       ipv6);
+			break;
+		default:
+			break;
+		}
+
+		if (type >= PPE_PKT_TYPE_IPV6_ROUTE_3T) {
+			data = hwe->ipv6.data;
+			ib2 = hwe->ipv6.ib2;
+			l2 = &hwe->ipv6.l2;
+		} else {
+			data = hwe->ipv4.data;
+			ib2 = hwe->ipv4.ib2;
+			l2 = &hwe->ipv4.l2.common;
+			*((__be16 *)&h_source[4]) =
+				cpu_to_be16(hwe->ipv4.l2.src_mac_lo);
+		}
+
+		*((__be32 *)h_dest) = cpu_to_be32(l2->dest_mac_hi);
+		*((__be16 *)&h_dest[4]) = cpu_to_be16(l2->dest_mac_lo);
+		*((__be32 *)h_source) = cpu_to_be32(l2->src_mac_hi);
+
+		seq_printf(m, " eth=%pM->%pM etype=%04x data=%08x"
+			      " vlan=%d,%d ib1=%08x ib2=%08x\n",
+			   h_source, h_dest, l2->etype, data,
+			   l2->vlan1, l2->vlan2, hwe->ib1, ib2);
+	}
+
+	return 0;
+}
+
+static int airoha_ppe_debugfs_foe_all_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, false);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_all);
+
+static int airoha_ppe_debugfs_foe_bind_show(struct seq_file *m, void *private)
+{
+	return airoha_ppe_debugfs_foe_show(m, private, true);
+}
+DEFINE_SHOW_ATTRIBUTE(airoha_ppe_debugfs_foe_bind);
+
+int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)
+{
+	ppe->debugfs_dir = debugfs_create_dir("ppe", NULL);
+	debugfs_create_file("entries", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_all_fops);
+	debugfs_create_file("bind", 0444, ppe->debugfs_dir, ppe,
+			    &airoha_ppe_debugfs_foe_bind_fops);
+
+	return 0;
+}

From c0bf9bf31e79273196cbdaa045972617fdd1a498 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:06 +0800
Subject: [PATCH 1498/2753] net: hibmcge: Add support for dump statistics

The driver supports many hw statistics. This patch supports
dump statistics through ethtool_ops and ndo.get_stats64().

The type of hw statistics register is u32,
To prevent the statistics register from overflowing,
the driver dump the statistics every 30 seconds.
in a scheduled task.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/hisilicon/hibmcge/hbg_common.h   | 111 +++++++
 .../ethernet/hisilicon/hibmcge/hbg_ethtool.c  | 297 ++++++++++++++++++
 .../ethernet/hisilicon/hibmcge/hbg_ethtool.h  |   5 +
 .../net/ethernet/hisilicon/hibmcge/hbg_main.c |  70 +++++
 .../net/ethernet/hisilicon/hibmcge/hbg_reg.h  |  96 ++++++
 .../net/ethernet/hisilicon/hibmcge/hbg_txrx.c | 164 +++++++++-
 6 files changed, 741 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index b4300d8ea4ad2..920514a8e29a5 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -142,6 +142,115 @@ struct hbg_user_def {
 	struct ethtool_pauseparam pause_param;
 };
 
+struct hbg_stats {
+	u64 rx_desc_drop;
+	u64 rx_desc_l2_err_cnt;
+	u64 rx_desc_pkt_len_err_cnt;
+	u64 rx_desc_l3l4_err_cnt;
+	u64 rx_desc_l3_wrong_head_cnt;
+	u64 rx_desc_l3_csum_err_cnt;
+	u64 rx_desc_l3_len_err_cnt;
+	u64 rx_desc_l3_zero_ttl_cnt;
+	u64 rx_desc_l3_other_cnt;
+	u64 rx_desc_l4_err_cnt;
+	u64 rx_desc_l4_wrong_head_cnt;
+	u64 rx_desc_l4_len_err_cnt;
+	u64 rx_desc_l4_csum_err_cnt;
+	u64 rx_desc_l4_zero_port_num_cnt;
+	u64 rx_desc_l4_other_cnt;
+	u64 rx_desc_frag_cnt;
+	u64 rx_desc_ip_ver_err_cnt;
+	u64 rx_desc_ipv4_pkt_cnt;
+	u64 rx_desc_ipv6_pkt_cnt;
+	u64 rx_desc_no_ip_pkt_cnt;
+	u64 rx_desc_ip_pkt_cnt;
+	u64 rx_desc_tcp_pkt_cnt;
+	u64 rx_desc_udp_pkt_cnt;
+	u64 rx_desc_vlan_pkt_cnt;
+	u64 rx_desc_icmp_pkt_cnt;
+	u64 rx_desc_arp_pkt_cnt;
+	u64 rx_desc_rarp_pkt_cnt;
+	u64 rx_desc_multicast_pkt_cnt;
+	u64 rx_desc_broadcast_pkt_cnt;
+	u64 rx_desc_ipsec_pkt_cnt;
+	u64 rx_desc_ip_opt_pkt_cnt;
+	u64 rx_desc_key_not_match_cnt;
+
+	u64 rx_octets_total_ok_cnt;
+	u64 rx_uc_pkt_cnt;
+	u64 rx_mc_pkt_cnt;
+	u64 rx_bc_pkt_cnt;
+	u64 rx_vlan_pkt_cnt;
+	u64 rx_octets_bad_cnt;
+	u64 rx_octets_total_filt_cnt;
+	u64 rx_filt_pkt_cnt;
+	u64 rx_trans_pkt_cnt;
+	u64 rx_framesize_64;
+	u64 rx_framesize_65_127;
+	u64 rx_framesize_128_255;
+	u64 rx_framesize_256_511;
+	u64 rx_framesize_512_1023;
+	u64 rx_framesize_1024_1518;
+	u64 rx_framesize_bt_1518;
+	u64 rx_fcs_error_cnt;
+	u64 rx_data_error_cnt;
+	u64 rx_align_error_cnt;
+	u64 rx_pause_macctl_frame_cnt;
+	u64 rx_unknown_macctl_frame_cnt;
+	/* crc ok, > max_frm_size, < 2max_frm_size */
+	u64 rx_frame_long_err_cnt;
+	/* crc fail, > max_frm_size, < 2max_frm_size */
+	u64 rx_jabber_err_cnt;
+	/* > 2max_frm_size */
+	u64 rx_frame_very_long_err_cnt;
+	/* < 64byte, >= short_runts_thr */
+	u64 rx_frame_runt_err_cnt;
+	/* < short_runts_thr */
+	u64 rx_frame_short_err_cnt;
+	/* PCU: dropped when the RX FIFO is full.*/
+	u64 rx_overflow_cnt;
+	/* GMAC: the count of overflows of the RX FIFO */
+	u64 rx_overrun_cnt;
+	/* PCU: the count of buffer alloc errors in RX */
+	u64 rx_bufrq_err_cnt;
+	/* PCU: the count of write descriptor errors in RX */
+	u64 rx_we_err_cnt;
+	/* GMAC: the count of pkts that contain PAD but length is not 64 */
+	u64 rx_lengthfield_err_cnt;
+	u64 rx_fail_comma_cnt;
+
+	u64 rx_dma_err_cnt;
+
+	u64 tx_octets_total_ok_cnt;
+	u64 tx_uc_pkt_cnt;
+	u64 tx_mc_pkt_cnt;
+	u64 tx_bc_pkt_cnt;
+	u64 tx_vlan_pkt_cnt;
+	u64 tx_octets_bad_cnt;
+	u64 tx_trans_pkt_cnt;
+	u64 tx_pause_frame_cnt;
+	u64 tx_framesize_64;
+	u64 tx_framesize_65_127;
+	u64 tx_framesize_128_255;
+	u64 tx_framesize_256_511;
+	u64 tx_framesize_512_1023;
+	u64 tx_framesize_1024_1518;
+	u64 tx_framesize_bt_1518;
+	/* GMAC: the count of times that frames fail to be transmitted
+	 *       due to internal errors.
+	 */
+	u64 tx_underrun_err_cnt;
+	u64 tx_add_cs_fail_cnt;
+	/* PCU: the count of buffer free errors in TX */
+	u64 tx_bufrl_err_cnt;
+	u64 tx_crc_err_cnt;
+	u64 tx_drop_cnt;
+	u64 tx_excessive_length_drop_cnt;
+
+	u64 tx_timeout_cnt;
+	u64 tx_dma_err_cnt;
+};
+
 struct hbg_priv {
 	struct net_device *netdev;
 	struct pci_dev *pdev;
@@ -155,6 +264,8 @@ struct hbg_priv {
 	struct hbg_mac_filter filter;
 	enum hbg_reset_type reset_type;
 	struct hbg_user_def user_def;
+	struct hbg_stats stats;
+	struct delayed_work service_task;
 };
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index 00364a438ec2e..f5be8d0ef6116 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -9,6 +9,135 @@
 #include "hbg_ethtool.h"
 #include "hbg_hw.h"
 
+struct hbg_ethtool_stats {
+	char name[ETH_GSTRING_LEN];
+	unsigned long offset;
+	u32 reg; /* set to 0 if stats is not updated via dump reg */
+};
+
+#define HBG_STATS_I(stats) { #stats, HBG_STATS_FIELD_OFF(stats), 0}
+#define HBG_STATS_REG_I(stats, reg) { #stats, HBG_STATS_FIELD_OFF(stats), reg}
+
+static const struct hbg_ethtool_stats hbg_ethtool_stats_info[] = {
+	HBG_STATS_I(rx_desc_l2_err_cnt),
+	HBG_STATS_I(rx_desc_pkt_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l3_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l3_len_err_cnt),
+	HBG_STATS_I(rx_desc_l3_zero_ttl_cnt),
+	HBG_STATS_I(rx_desc_l3_other_cnt),
+	HBG_STATS_I(rx_desc_l4_wrong_head_cnt),
+	HBG_STATS_I(rx_desc_l4_len_err_cnt),
+	HBG_STATS_I(rx_desc_l4_csum_err_cnt),
+	HBG_STATS_I(rx_desc_l4_zero_port_num_cnt),
+	HBG_STATS_I(rx_desc_l4_other_cnt),
+	HBG_STATS_I(rx_desc_ip_ver_err_cnt),
+	HBG_STATS_I(rx_desc_ipv4_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipv6_pkt_cnt),
+	HBG_STATS_I(rx_desc_no_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_pkt_cnt),
+	HBG_STATS_I(rx_desc_tcp_pkt_cnt),
+	HBG_STATS_I(rx_desc_udp_pkt_cnt),
+	HBG_STATS_I(rx_desc_vlan_pkt_cnt),
+	HBG_STATS_I(rx_desc_icmp_pkt_cnt),
+	HBG_STATS_I(rx_desc_arp_pkt_cnt),
+	HBG_STATS_I(rx_desc_rarp_pkt_cnt),
+	HBG_STATS_I(rx_desc_multicast_pkt_cnt),
+	HBG_STATS_I(rx_desc_broadcast_pkt_cnt),
+	HBG_STATS_I(rx_desc_ipsec_pkt_cnt),
+	HBG_STATS_I(rx_desc_ip_opt_pkt_cnt),
+	HBG_STATS_I(rx_desc_key_not_match_cnt),
+
+	HBG_STATS_REG_I(rx_octets_bad_cnt, HBG_REG_RX_OCTETS_BAD_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_filt_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR),
+	HBG_STATS_REG_I(rx_uc_pkt_cnt, HBG_REG_RX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_vlan_pkt_cnt, HBG_REG_RX_TAGGED_ADDR),
+	HBG_STATS_REG_I(rx_filt_pkt_cnt, HBG_REG_RX_FILT_PKT_CNT_ADDR),
+	HBG_STATS_REG_I(rx_data_error_cnt, HBG_REG_RX_DATA_ERR_ADDR),
+	HBG_STATS_REG_I(rx_frame_long_err_cnt, HBG_REG_RX_LONG_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_jabber_err_cnt, HBG_REG_RX_JABBER_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_frame_very_long_err_cnt,
+			HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_runt_err_cnt, HBG_REG_RX_RUNT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_frame_short_err_cnt, HBG_REG_RX_SHORT_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overflow_cnt, HBG_REG_RX_OVER_FLOW_CNT_ADDR),
+	HBG_STATS_REG_I(rx_bufrq_err_cnt, HBG_REG_RX_BUFRQ_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_we_err_cnt, HBG_REG_RX_WE_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_overrun_cnt, HBG_REG_RX_OVERRUN_CNT_ADDR),
+	HBG_STATS_REG_I(rx_lengthfield_err_cnt,
+			HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fail_comma_cnt, HBG_REG_RX_FAIL_COMMA_CNT_ADDR),
+	HBG_STATS_I(rx_dma_err_cnt),
+
+	HBG_STATS_REG_I(tx_uc_pkt_cnt, HBG_REG_TX_UC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_vlan_pkt_cnt, HBG_REG_TX_TAGGED_ADDR),
+	HBG_STATS_REG_I(tx_octets_bad_cnt, HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR),
+
+	HBG_STATS_REG_I(tx_underrun_err_cnt, HBG_REG_TX_UNDERRUN_ADDR),
+	HBG_STATS_REG_I(tx_add_cs_fail_cnt, HBG_REG_TX_CS_FAIL_CNT_ADDR),
+	HBG_STATS_REG_I(tx_bufrl_err_cnt, HBG_REG_TX_BUFRL_ERR_CNT_ADDR),
+	HBG_STATS_REG_I(tx_crc_err_cnt, HBG_REG_TX_CRC_ERROR_ADDR),
+	HBG_STATS_REG_I(tx_drop_cnt, HBG_REG_TX_DROP_CNT_ADDR),
+	HBG_STATS_REG_I(tx_excessive_length_drop_cnt,
+			HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR),
+	HBG_STATS_I(tx_dma_err_cnt),
+	HBG_STATS_I(tx_timeout_cnt),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_rmon_stats_info[] = {
+	HBG_STATS_I(rx_desc_frag_cnt),
+	HBG_STATS_REG_I(rx_framesize_64, HBG_REG_RX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_65_127,
+			HBG_REG_RX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_128_255,
+			HBG_REG_RX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_256_511,
+			HBG_REG_RX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_512_1023,
+			HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_1024_1518,
+			HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(rx_framesize_bt_1518,
+			HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_64, HBG_REG_TX_PKTS_64OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_65_127,
+			HBG_REG_TX_PKTS_65TO127OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_128_255,
+			HBG_REG_TX_PKTS_128TO255OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_256_511,
+			HBG_REG_TX_PKTS_256TO511OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_512_1023,
+			HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_1024_1518,
+			HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR),
+	HBG_STATS_REG_I(tx_framesize_bt_1518,
+			HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_mac_stats_info[] = {
+	HBG_STATS_REG_I(rx_mc_pkt_cnt, HBG_REG_RX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_bc_pkt_cnt, HBG_REG_RX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(rx_align_error_cnt, HBG_REG_RX_ALIGN_ERRORS_ADDR),
+	HBG_STATS_REG_I(rx_octets_total_ok_cnt,
+			HBG_REG_RX_OCTETS_TOTAL_OK_ADDR),
+	HBG_STATS_REG_I(rx_trans_pkt_cnt, HBG_REG_RX_TRANS_PKG_CNT_ADDR),
+	HBG_STATS_REG_I(rx_fcs_error_cnt, HBG_REG_RX_FCS_ERRORS_ADDR),
+	HBG_STATS_REG_I(tx_mc_pkt_cnt, HBG_REG_TX_MC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_bc_pkt_cnt, HBG_REG_TX_BC_PKTS_ADDR),
+	HBG_STATS_REG_I(tx_octets_total_ok_cnt,
+			HBG_REG_OCTETS_TRANSMITTED_OK_ADDR),
+	HBG_STATS_REG_I(tx_trans_pkt_cnt, HBG_REG_TX_TRANS_PKG_CNT_ADDR),
+};
+
+static const struct hbg_ethtool_stats hbg_ethtool_ctrl_stats_info[] = {
+	HBG_STATS_REG_I(rx_pause_macctl_frame_cnt,
+			HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR),
+	HBG_STATS_REG_I(tx_pause_frame_cnt, HBG_REG_TX_PAUSE_FRAMES_ADDR),
+	HBG_STATS_REG_I(rx_unknown_macctl_frame_cnt,
+			HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR),
+};
+
 enum hbg_reg_dump_type {
 	HBG_DUMP_REG_TYPE_SPEC = 0,
 	HBG_DUMP_REG_TYPE_MDIO,
@@ -180,6 +309,167 @@ static int hbg_ethtool_reset(struct net_device *netdev, u32 *flags)
 	return hbg_reset(priv);
 }
 
+static void hbg_update_stats_by_info(struct hbg_priv *priv,
+				     const struct hbg_ethtool_stats *info,
+				     u32 info_len)
+{
+	const struct hbg_ethtool_stats *stats;
+	u32 i;
+
+	for (i = 0; i < info_len; i++) {
+		stats = &info[i];
+		if (!stats->reg)
+			continue;
+
+		HBG_STATS_U(&priv->stats, stats->offset,
+			    hbg_reg_read(priv, stats->reg));
+	}
+}
+
+void hbg_update_stats(struct hbg_priv *priv)
+{
+	hbg_update_stats_by_info(priv, hbg_ethtool_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_rmon_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_rmon_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_mac_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_mac_stats_info));
+	hbg_update_stats_by_info(priv, hbg_ethtool_ctrl_stats_info,
+				 ARRAY_SIZE(hbg_ethtool_ctrl_stats_info));
+}
+
+static int hbg_ethtool_get_sset_count(struct net_device *netdev, int stringset)
+{
+	if (stringset != ETH_SS_STATS)
+		return -EOPNOTSUPP;
+
+	return ARRAY_SIZE(hbg_ethtool_stats_info);
+}
+
+static void hbg_ethtool_get_strings(struct net_device *netdev,
+				    u32 stringset, u8 *data)
+{
+	u32 i;
+
+	if (stringset != ETH_SS_STATS)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		ethtool_puts(&data, hbg_ethtool_stats_info[i].name);
+}
+
+static void hbg_ethtool_get_stats(struct net_device *netdev,
+				  struct ethtool_stats *stats, u64 *data)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	u32 i;
+
+	hbg_update_stats(priv);
+	for (i = 0; i < ARRAY_SIZE(hbg_ethtool_stats_info); i++)
+		*data++ = HBG_STATS_R(&priv->stats,
+				      hbg_ethtool_stats_info[i].offset);
+}
+
+static void hbg_ethtool_get_pause_stats(struct net_device *netdev,
+					struct ethtool_pause_stats *epstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	epstats->rx_pause_frames = stats->rx_pause_macctl_frame_cnt;
+	epstats->tx_pause_frames = stats->tx_pause_frame_cnt;
+}
+
+static void hbg_ethtool_get_eth_mac_stats(struct net_device *netdev,
+					  struct ethtool_eth_mac_stats *emstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	emstats->FramesTransmittedOK = stats->tx_trans_pkt_cnt;
+	emstats->FramesReceivedOK = stats->rx_trans_pkt_cnt;
+	emstats->FrameCheckSequenceErrors = stats->rx_fcs_error_cnt;
+	emstats->AlignmentErrors = stats->rx_align_error_cnt;
+	emstats->OctetsTransmittedOK = stats->tx_octets_total_ok_cnt;
+	emstats->OctetsReceivedOK = stats->rx_octets_total_ok_cnt;
+
+	emstats->MulticastFramesXmittedOK = stats->tx_mc_pkt_cnt;
+	emstats->BroadcastFramesXmittedOK = stats->tx_bc_pkt_cnt;
+	emstats->MulticastFramesReceivedOK = stats->rx_mc_pkt_cnt;
+	emstats->BroadcastFramesReceivedOK = stats->rx_bc_pkt_cnt;
+	emstats->InRangeLengthErrors = stats->rx_fcs_error_cnt +
+				       stats->rx_jabber_err_cnt +
+				       stats->rx_unknown_macctl_frame_cnt +
+				       stats->rx_bufrq_err_cnt +
+				       stats->rx_we_err_cnt;
+	emstats->OutOfRangeLengthField = stats->rx_frame_short_err_cnt +
+					 stats->rx_frame_runt_err_cnt +
+					 stats->rx_lengthfield_err_cnt +
+					 stats->rx_frame_long_err_cnt +
+					 stats->rx_frame_very_long_err_cnt;
+	emstats->FrameTooLongErrors = stats->rx_frame_long_err_cnt +
+				      stats->rx_frame_very_long_err_cnt;
+}
+
+static void
+hbg_ethtool_get_eth_ctrl_stats(struct net_device *netdev,
+			       struct ethtool_eth_ctrl_stats *ecstats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *s = &priv->stats;
+
+	hbg_update_stats(priv);
+	ecstats->MACControlFramesTransmitted = s->tx_pause_frame_cnt;
+	ecstats->MACControlFramesReceived = s->rx_pause_macctl_frame_cnt;
+	ecstats->UnsupportedOpcodesReceived = s->rx_unknown_macctl_frame_cnt;
+}
+
+static const struct ethtool_rmon_hist_range hbg_rmon_ranges[] = {
+	{    0,    64 },
+	{   65,   127 },
+	{  128,   255 },
+	{  256,   511 },
+	{  512,  1023 },
+	{ 1024,  1518 },
+	{ 1519,  4095 },
+};
+
+static void
+hbg_ethtool_get_rmon_stats(struct net_device *netdev,
+			   struct ethtool_rmon_stats *rmon_stats,
+			   const struct ethtool_rmon_hist_range **ranges)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	rmon_stats->undersize_pkts = stats->rx_frame_short_err_cnt +
+				     stats->rx_frame_runt_err_cnt +
+				     stats->rx_lengthfield_err_cnt;
+	rmon_stats->oversize_pkts = stats->rx_frame_long_err_cnt +
+				    stats->rx_frame_very_long_err_cnt;
+	rmon_stats->fragments = stats->rx_desc_frag_cnt;
+	rmon_stats->hist[0] = stats->rx_framesize_64;
+	rmon_stats->hist[1] = stats->rx_framesize_65_127;
+	rmon_stats->hist[2] = stats->rx_framesize_128_255;
+	rmon_stats->hist[3] = stats->rx_framesize_256_511;
+	rmon_stats->hist[4] = stats->rx_framesize_512_1023;
+	rmon_stats->hist[5] = stats->rx_framesize_1024_1518;
+	rmon_stats->hist[6] = stats->rx_framesize_bt_1518;
+
+	rmon_stats->hist_tx[0] = stats->tx_framesize_64;
+	rmon_stats->hist_tx[1] = stats->tx_framesize_65_127;
+	rmon_stats->hist_tx[2] = stats->tx_framesize_128_255;
+	rmon_stats->hist_tx[3] = stats->tx_framesize_256_511;
+	rmon_stats->hist_tx[4] = stats->tx_framesize_512_1023;
+	rmon_stats->hist_tx[5] = stats->tx_framesize_1024_1518;
+	rmon_stats->hist_tx[6] = stats->tx_framesize_bt_1518;
+
+	*ranges = hbg_rmon_ranges;
+}
+
 static const struct ethtool_ops hbg_ethtool_ops = {
 	.get_link		= ethtool_op_get_link,
 	.get_link_ksettings	= phy_ethtool_get_link_ksettings,
@@ -190,6 +480,13 @@ static const struct ethtool_ops hbg_ethtool_ops = {
 	.set_pauseparam         = hbg_ethtool_set_pauseparam,
 	.reset			= hbg_ethtool_reset,
 	.nway_reset		= phy_ethtool_nway_reset,
+	.get_sset_count		= hbg_ethtool_get_sset_count,
+	.get_strings		= hbg_ethtool_get_strings,
+	.get_ethtool_stats	= hbg_ethtool_get_stats,
+	.get_pause_stats	= hbg_ethtool_get_pause_stats,
+	.get_eth_mac_stats	= hbg_ethtool_get_eth_mac_stats,
+	.get_eth_ctrl_stats	= hbg_ethtool_get_eth_ctrl_stats,
+	.get_rmon_stats		= hbg_ethtool_get_rmon_stats,
 };
 
 void hbg_ethtool_set_ops(struct net_device *netdev)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
index 628707ec2686d..e173155b146a8 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.h
@@ -6,6 +6,11 @@
 
 #include <linux/netdevice.h>
 
+#define HBG_STATS_FIELD_OFF(f) (offsetof(struct hbg_stats, f))
+#define HBG_STATS_R(p, offset) (*(u64 *)((u8 *)(p) + (offset)))
+#define HBG_STATS_U(p, offset, val) (HBG_STATS_R(p, offset) += (val))
+
 void hbg_ethtool_set_ops(struct net_device *netdev);
+void hbg_update_stats(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index bb0f25ac97600..969df60209429 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -214,6 +214,10 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	char *buf = ring->tout_log_buf;
 	u32 pos = 0;
 
+	priv->stats.tx_timeout_cnt++;
+
+	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
+			 "tx_timeout cnt: %llu\n", priv->stats.tx_timeout_cnt);
 	pos += scnprintf(buf + pos, HBG_TX_TIMEOUT_BUF_LEN - pos,
 			 "ring used num: %u, fifo used num: %u\n",
 			 hbg_get_queue_used_num(ring),
@@ -226,6 +230,39 @@ static void hbg_net_tx_timeout(struct net_device *netdev, unsigned int txqueue)
 	netdev_info(netdev, "%s", buf);
 }
 
+static void hbg_net_get_stats(struct net_device *netdev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct hbg_priv *priv = netdev_priv(netdev);
+	struct hbg_stats *h_stats = &priv->stats;
+
+	hbg_update_stats(priv);
+	dev_get_tstats64(netdev, stats);
+
+	/* fifo empty */
+	stats->tx_fifo_errors += h_stats->tx_drop_cnt;
+
+	stats->tx_dropped += h_stats->tx_excessive_length_drop_cnt +
+			     h_stats->tx_drop_cnt;
+	stats->tx_errors += h_stats->tx_add_cs_fail_cnt +
+			    h_stats->tx_bufrl_err_cnt +
+			    h_stats->tx_underrun_err_cnt +
+			    h_stats->tx_crc_err_cnt;
+	stats->rx_errors += h_stats->rx_data_error_cnt;
+	stats->multicast += h_stats->rx_mc_pkt_cnt;
+	stats->rx_dropped += h_stats->rx_desc_drop;
+	stats->rx_length_errors += h_stats->rx_frame_very_long_err_cnt +
+				   h_stats->rx_frame_long_err_cnt +
+				   h_stats->rx_frame_runt_err_cnt +
+				   h_stats->rx_frame_short_err_cnt +
+				   h_stats->rx_lengthfield_err_cnt;
+	stats->rx_frame_errors += h_stats->rx_desc_l2_err_cnt +
+				  h_stats->rx_desc_l3l4_err_cnt;
+	stats->rx_fifo_errors += h_stats->rx_overflow_cnt +
+				 h_stats->rx_overrun_cnt;
+	stats->rx_crc_errors += h_stats->rx_fcs_error_cnt;
+}
+
 static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_open		= hbg_net_open,
 	.ndo_stop		= hbg_net_stop,
@@ -235,8 +272,37 @@ static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_change_mtu		= hbg_net_change_mtu,
 	.ndo_tx_timeout		= hbg_net_tx_timeout,
 	.ndo_set_rx_mode	= hbg_net_set_rx_mode,
+	.ndo_get_stats64	= hbg_net_get_stats,
 };
 
+static void hbg_service_task(struct work_struct *work)
+{
+	struct hbg_priv *priv = container_of(work, struct hbg_priv,
+					     service_task.work);
+
+	/* The type of statistics register is u32,
+	 * To prevent the statistics register from overflowing,
+	 * the driver dumps the statistics every 30 seconds.
+	 */
+	hbg_update_stats(priv);
+	schedule_delayed_work(&priv->service_task,
+			      msecs_to_jiffies(30 * MSEC_PER_SEC));
+}
+
+static void hbg_cancel_delayed_work_sync(void *data)
+{
+	cancel_delayed_work_sync(data);
+}
+
+static int hbg_delaywork_init(struct hbg_priv *priv)
+{
+	INIT_DELAYED_WORK(&priv->service_task, hbg_service_task);
+	schedule_delayed_work(&priv->service_task, 0);
+	return devm_add_action_or_reset(&priv->pdev->dev,
+					hbg_cancel_delayed_work_sync,
+					&priv->service_task);
+}
+
 static int hbg_mac_filter_init(struct hbg_priv *priv)
 {
 	struct hbg_dev_specs *dev_specs = &priv->dev_specs;
@@ -291,6 +357,10 @@ static int hbg_init(struct hbg_priv *priv)
 	if (ret)
 		return ret;
 
+	ret = hbg_delaywork_init(priv);
+	if (ret)
+		return ret;
+
 	hbg_debugfs_init(priv);
 	hbg_init_user_def(priv);
 	return 0;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index f12efc12f3c54..106d0e0408ba4 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -60,6 +60,48 @@
 #define HBG_REG_TRANSMIT_CTRL_AN_EN_B		BIT(5)
 #define HBG_REG_REC_FILT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0064)
 #define HBG_REG_REC_FILT_CTRL_UC_MATCH_EN_B	BIT(0)
+#define HBG_REG_RX_OCTETS_TOTAL_OK_ADDR		(HBG_REG_SGMII_BASE + 0x0080)
+#define HBG_REG_RX_OCTETS_BAD_ADDR		(HBG_REG_SGMII_BASE + 0x0084)
+#define HBG_REG_RX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0088)
+#define HBG_REG_RX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x008C)
+#define HBG_REG_RX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0090)
+#define HBG_REG_RX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0094)
+#define HBG_REG_RX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0098)
+#define HBG_REG_RX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x009C)
+#define HBG_REG_RX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A0)
+#define HBG_REG_RX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A4)
+#define HBG_REG_RX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00A8)
+#define HBG_REG_RX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x00AC)
+#define HBG_REG_RX_FCS_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00B0)
+#define HBG_REG_RX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x00B4)
+#define HBG_REG_RX_DATA_ERR_ADDR		(HBG_REG_SGMII_BASE + 0x00B8)
+#define HBG_REG_RX_ALIGN_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00BC)
+#define HBG_REG_RX_LONG_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C0)
+#define HBG_REG_RX_JABBER_ERRORS_ADDR		(HBG_REG_SGMII_BASE + 0x00C4)
+#define HBG_REG_RX_PAUSE_MACCTL_FRAMCOUNTER_ADDR   (HBG_REG_SGMII_BASE + 0x00C8)
+#define HBG_REG_RX_UNKNOWN_MACCTL_FRAMCOUNTER_ADDR (HBG_REG_SGMII_BASE + 0x00CC)
+#define HBG_REG_RX_VERY_LONG_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x00D0)
+#define HBG_REG_RX_RUNT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D4)
+#define HBG_REG_RX_SHORT_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00D8)
+#define HBG_REG_RX_FILT_PKT_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x00E8)
+#define HBG_REG_RX_OCTETS_TOTAL_FILT_ADDR	(HBG_REG_SGMII_BASE + 0x00EC)
+#define HBG_REG_OCTETS_TRANSMITTED_OK_ADDR	(HBG_REG_SGMII_BASE + 0x0100)
+#define HBG_REG_OCTETS_TRANSMITTED_BAD_ADDR	(HBG_REG_SGMII_BASE + 0x0104)
+#define HBG_REG_TX_UC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0108)
+#define HBG_REG_TX_MC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x010C)
+#define HBG_REG_TX_BC_PKTS_ADDR			(HBG_REG_SGMII_BASE + 0x0110)
+#define HBG_REG_TX_PKTS_64OCTETS_ADDR		(HBG_REG_SGMII_BASE + 0x0114)
+#define HBG_REG_TX_PKTS_65TO127OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0118)
+#define HBG_REG_TX_PKTS_128TO255OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x011C)
+#define HBG_REG_TX_PKTS_256TO511OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0120)
+#define HBG_REG_TX_PKTS_512TO1023OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0124)
+#define HBG_REG_TX_PKTS_1024TO1518OCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x0128)
+#define HBG_REG_TX_PKTS_1519TOMAXOCTETS_ADDR	(HBG_REG_SGMII_BASE + 0x012C)
+#define HBG_REG_TX_EXCESSIVE_LENGTH_DROP_ADDR	(HBG_REG_SGMII_BASE + 0x014C)
+#define HBG_REG_TX_UNDERRUN_ADDR		(HBG_REG_SGMII_BASE + 0x0150)
+#define HBG_REG_TX_TAGGED_ADDR			(HBG_REG_SGMII_BASE + 0x0154)
+#define HBG_REG_TX_CRC_ERROR_ADDR		(HBG_REG_SGMII_BASE + 0x0158)
+#define HBG_REG_TX_PAUSE_FRAMES_ADDR		(HBG_REG_SGMII_BASE + 0x015C)
 #define HBG_REG_LINE_LOOP_BACK_ADDR		(HBG_REG_SGMII_BASE + 0x01A8)
 #define HBG_REG_CF_CRC_STRIP_ADDR		(HBG_REG_SGMII_BASE + 0x01B0)
 #define HBG_REG_CF_CRC_STRIP_B			BIT(0)
@@ -69,6 +111,9 @@
 #define HBG_REG_RECV_CTRL_ADDR			(HBG_REG_SGMII_BASE + 0x01E0)
 #define HBG_REG_RECV_CTRL_STRIP_PAD_EN_B	BIT(3)
 #define HBG_REG_VLAN_CODE_ADDR			(HBG_REG_SGMII_BASE + 0x01E8)
+#define HBG_REG_RX_OVERRUN_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01EC)
+#define HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR	(HBG_REG_SGMII_BASE + 0x01F4)
+#define HBG_REG_RX_FAIL_COMMA_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x01F8)
 #define HBG_REG_STATION_ADDR_LOW_0_ADDR		(HBG_REG_SGMII_BASE + 0x0200)
 #define HBG_REG_STATION_ADDR_HIGH_0_ADDR	(HBG_REG_SGMII_BASE + 0x0204)
 #define HBG_REG_STATION_ADDR_LOW_1_ADDR		(HBG_REG_SGMII_BASE + 0x0208)
@@ -111,12 +156,17 @@
 #define HBG_REG_RX_BUS_ERR_ADDR_ADDR		(HBG_REG_SGMII_BASE + 0x0440)
 #define HBG_REG_MAX_FRAME_LEN_ADDR		(HBG_REG_SGMII_BASE + 0x0444)
 #define HBG_REG_MAX_FRAME_LEN_M			GENMASK(15, 0)
+#define HBG_REG_TX_DROP_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0448)
+#define HBG_REG_RX_OVER_FLOW_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x044C)
 #define HBG_REG_DEBUG_ST_MCH_ADDR		(HBG_REG_SGMII_BASE + 0x0450)
 #define HBG_REG_FIFO_CURR_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0454)
 #define HBG_REG_FIFO_HIST_STATUS_ADDR		(HBG_REG_SGMII_BASE + 0x0458)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR		(HBG_REG_SGMII_BASE + 0x045C)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_TX_M	GENMASK(8, 0)
 #define HBG_REG_CF_CFF_DATA_NUM_ADDR_RX_M	GENMASK(24, 16)
+#define HBG_REG_TX_CS_FAIL_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0460)
+#define HBG_REG_RX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0464)
+#define HBG_REG_TX_TRANS_PKG_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0468)
 #define HBG_REG_CF_TX_PAUSE_ADDR		(HBG_REG_SGMII_BASE + 0x0470)
 #define HBG_REG_TX_CFF_ADDR_0_ADDR		(HBG_REG_SGMII_BASE + 0x0488)
 #define HBG_REG_TX_CFF_ADDR_1_ADDR		(HBG_REG_SGMII_BASE + 0x048C)
@@ -136,6 +186,9 @@
 #define HBG_REG_RX_CTRL_RXBUF_1ST_SKIP_SIZE2_M	GENMASK(3, 0)
 #define HBG_REG_RX_PKT_MODE_ADDR		(HBG_REG_SGMII_BASE + 0x04F4)
 #define HBG_REG_RX_PKT_MODE_PARSE_MODE_M	GENMASK(22, 21)
+#define HBG_REG_RX_BUFRQ_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x058C)
+#define HBG_REG_TX_BUFRL_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0590)
+#define HBG_REG_RX_WE_ERR_CNT_ADDR		(HBG_REG_SGMII_BASE + 0x0594)
 #define HBG_REG_DBG_ST0_ADDR			(HBG_REG_SGMII_BASE + 0x05E4)
 #define HBG_REG_DBG_ST1_ADDR			(HBG_REG_SGMII_BASE + 0x05E8)
 #define HBG_REG_DBG_ST2_ADDR			(HBG_REG_SGMII_BASE + 0x05EC)
@@ -178,5 +231,48 @@ struct hbg_rx_desc {
 };
 
 #define HBG_RX_DESC_W2_PKT_LEN_M	GENMASK(31, 16)
+#define HBG_RX_DESC_W2_PORT_NUM_M	GENMASK(15, 12)
+#define HBG_RX_DESC_W4_IP_TCP_UDP_M	GENMASK(31, 30)
+#define HBG_RX_DESC_W4_IPSEC_B		BIT(29)
+#define HBG_RX_DESC_W4_IP_VERSION_B	BIT(28)
+#define HBG_RX_DESC_W4_L4_ERR_CODE_M	GENMASK(26, 23)
+#define HBG_RX_DESC_W4_FRAG_B		BIT(22)
+#define HBG_RX_DESC_W4_OPT_B		BIT(21)
+#define HBG_RX_DESC_W4_IP_VERSION_ERR_B	BIT(20)
+#define HBG_RX_DESC_W4_BRD_CST_B	BIT(19)
+#define HBG_RX_DESC_W4_MUL_CST_B	BIT(18)
+#define HBG_RX_DESC_W4_ARP_B		BIT(17)
+#define HBG_RX_DESC_W4_RARP_B		BIT(16)
+#define HBG_RX_DESC_W4_ICMP_B		BIT(15)
+#define HBG_RX_DESC_W4_VLAN_FLAG_B	BIT(14)
+#define HBG_RX_DESC_W4_DROP_B		BIT(13)
+#define HBG_RX_DESC_W4_L3_ERR_CODE_M	GENMASK(12, 9)
+#define HBG_RX_DESC_W4_L2_ERR_B		BIT(8)
+#define HBG_RX_DESC_W4_IDX_MATCH_B	BIT(7)
+
+enum hbg_l3_err_code {
+	HBG_L3_OK = 0,
+	HBG_L3_WRONG_HEAD,
+	HBG_L3_CSUM_ERR,
+	HBG_L3_LEN_ERR,
+	HBG_L3_ZERO_TTL,
+	HBG_L3_RSVD,
+};
+
+enum hbg_l4_err_code {
+	HBG_L4_OK = 0,
+	HBG_L4_WRONG_HEAD,
+	HBG_L4_LEN_ERR,
+	HBG_L4_CSUM_ERR,
+	HBG_L4_ZERO_PORT_NUM,
+	HBG_L4_RSVD,
+};
+
+enum hbg_pkt_type_code {
+	HBG_NO_IP_PKT = 0,
+	HBG_IP_PKT,
+	HBG_TCP_PKT,
+	HBG_UDP_PKT,
+};
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
index f4f256a0dfea4..35dd3512d00e4 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
@@ -38,8 +38,14 @@ static int hbg_dma_map(struct hbg_buffer *buffer)
 	buffer->skb_dma = dma_map_single(&priv->pdev->dev,
 					 buffer->skb->data, buffer->skb_len,
 					 buffer_to_dma_dir(buffer));
-	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma)))
+	if (unlikely(dma_mapping_error(&priv->pdev->dev, buffer->skb_dma))) {
+		if (buffer->dir == HBG_DIR_RX)
+			priv->stats.rx_dma_err_cnt++;
+		else
+			priv->stats.tx_dma_err_cnt++;
+
 		return -ENOMEM;
+	}
 
 	return 0;
 }
@@ -195,6 +201,156 @@ static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget)
 	return packet_done;
 }
 
+static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
+				    struct hbg_rx_desc *desc)
+{
+	if (likely(!FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4) &&
+		   !FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)))
+		return true;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4)) {
+	case HBG_L3_OK:
+		break;
+	case HBG_L3_WRONG_HEAD:
+		priv->stats.rx_desc_l3_wrong_head_cnt++;
+		return false;
+	case HBG_L3_CSUM_ERR:
+		priv->stats.rx_desc_l3_csum_err_cnt++;
+		return false;
+	case HBG_L3_LEN_ERR:
+		priv->stats.rx_desc_l3_len_err_cnt++;
+		return false;
+	case HBG_L3_ZERO_TTL:
+		priv->stats.rx_desc_l3_zero_ttl_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l3_other_cnt++;
+		return false;
+	}
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)) {
+	case HBG_L4_OK:
+		break;
+	case HBG_L4_WRONG_HEAD:
+		priv->stats.rx_desc_l4_wrong_head_cnt++;
+		return false;
+	case HBG_L4_LEN_ERR:
+		priv->stats.rx_desc_l4_len_err_cnt++;
+		return false;
+	case HBG_L4_CSUM_ERR:
+		priv->stats.rx_desc_l4_csum_err_cnt++;
+		return false;
+	case HBG_L4_ZERO_PORT_NUM:
+		priv->stats.rx_desc_l4_zero_port_num_cnt++;
+		return false;
+	default:
+		priv->stats.rx_desc_l4_other_cnt++;
+		return false;
+	}
+
+	return true;
+}
+
+static void hbg_update_rx_ip_protocol_stats(struct hbg_priv *priv,
+					    struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4))) {
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		return;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_ip_ver_err_cnt++;
+		return;
+	}
+
+	/* 0:ipv4, 1:ipv6 */
+	if (FIELD_GET(HBG_RX_DESC_W4_IP_VERSION_B, desc->word4))
+		priv->stats.rx_desc_ipv6_pkt_cnt++;
+	else
+		priv->stats.rx_desc_ipv4_pkt_cnt++;
+
+	switch (FIELD_GET(HBG_RX_DESC_W4_IP_TCP_UDP_M, desc->word4)) {
+	case HBG_IP_PKT:
+		priv->stats.rx_desc_ip_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_OPT_B, desc->word4))
+			priv->stats.rx_desc_ip_opt_pkt_cnt++;
+		if (FIELD_GET(HBG_RX_DESC_W4_FRAG_B, desc->word4))
+			priv->stats.rx_desc_frag_cnt++;
+
+		if (FIELD_GET(HBG_RX_DESC_W4_ICMP_B, desc->word4))
+			priv->stats.rx_desc_icmp_pkt_cnt++;
+		else if (FIELD_GET(HBG_RX_DESC_W4_IPSEC_B, desc->word4))
+			priv->stats.rx_desc_ipsec_pkt_cnt++;
+		break;
+	case HBG_TCP_PKT:
+		priv->stats.rx_desc_tcp_pkt_cnt++;
+		break;
+	case HBG_UDP_PKT:
+		priv->stats.rx_desc_udp_pkt_cnt++;
+		break;
+	default:
+		priv->stats.rx_desc_no_ip_pkt_cnt++;
+		break;
+	}
+}
+
+static void hbg_update_rx_protocol_stats(struct hbg_priv *priv,
+					 struct hbg_rx_desc *desc)
+{
+	if (unlikely(!FIELD_GET(HBG_RX_DESC_W4_IDX_MATCH_B, desc->word4))) {
+		priv->stats.rx_desc_key_not_match_cnt++;
+		return;
+	}
+
+	if (FIELD_GET(HBG_RX_DESC_W4_BRD_CST_B, desc->word4))
+		priv->stats.rx_desc_broadcast_pkt_cnt++;
+	else if (FIELD_GET(HBG_RX_DESC_W4_MUL_CST_B, desc->word4))
+		priv->stats.rx_desc_multicast_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_VLAN_FLAG_B, desc->word4))
+		priv->stats.rx_desc_vlan_pkt_cnt++;
+
+	if (FIELD_GET(HBG_RX_DESC_W4_ARP_B, desc->word4)) {
+		priv->stats.rx_desc_arp_pkt_cnt++;
+		return;
+	} else if (FIELD_GET(HBG_RX_DESC_W4_RARP_B, desc->word4)) {
+		priv->stats.rx_desc_rarp_pkt_cnt++;
+		return;
+	}
+
+	hbg_update_rx_ip_protocol_stats(priv, desc);
+}
+
+static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc)
+{
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, desc->word2) >
+		     priv->dev_specs.max_frame_len)) {
+		priv->stats.rx_desc_pkt_len_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PORT_NUM_M, desc->word2) !=
+		     priv->dev_specs.mac_id ||
+		     FIELD_GET(HBG_RX_DESC_W4_DROP_B, desc->word4))) {
+		priv->stats.rx_desc_drop++;
+		return false;
+	}
+
+	if (unlikely(FIELD_GET(HBG_RX_DESC_W4_L2_ERR_B, desc->word4))) {
+		priv->stats.rx_desc_l2_err_cnt++;
+		return false;
+	}
+
+	if (unlikely(!hbg_rx_check_l3l4_error(priv, desc))) {
+		priv->stats.rx_desc_l3l4_err_cnt++;
+		return false;
+	}
+
+	hbg_update_rx_protocol_stats(priv, desc);
+	return true;
+}
+
 static int hbg_rx_fill_one_buffer(struct hbg_priv *priv)
 {
 	struct hbg_ring *ring = &priv->rx_ring;
@@ -257,8 +413,12 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget)
 		rx_desc = (struct hbg_rx_desc *)buffer->skb->data;
 		pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2);
 
-		hbg_dma_unmap(buffer);
+		if (unlikely(!hbg_rx_pkt_check(priv, rx_desc))) {
+			hbg_buffer_free(buffer);
+			goto next_buffer;
+		}
 
+		hbg_dma_unmap(buffer);
 		skb_reserve(buffer->skb, HBG_PACKET_HEAD_SIZE + NET_IP_ALIGN);
 		skb_put(buffer->skb, pkt_len);
 		buffer->skb->protocol = eth_type_trans(buffer->skb,

From 833b65a3b54d715965d5c444ad1015321633b3f8 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:07 +0800
Subject: [PATCH 1499/2753] net: hibmcge: Add support for checksum offload

This patch implements the rx checksum offload feature.

The tx checksum offload processing in .ndo_start_xmit()
has been accepted. This patch also adds the tx checksum
feature, including NETIF_F_IP_CSUM and NETIF_F_IPV6_CSUM

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/hisilicon/hibmcge/hbg_main.c |  6 ++++
 .../net/ethernet/hisilicon/hibmcge/hbg_txrx.c | 29 +++++++++++++++----
 2 files changed, 29 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 969df60209429..688f408de84cd 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -14,6 +14,9 @@
 #include "hbg_txrx.h"
 #include "hbg_debugfs.h"
 
+#define HBG_SUPPORT_FEATURES (NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | \
+			     NETIF_F_RXCSUM)
+
 static void hbg_all_irq_enable(struct hbg_priv *priv, bool enabled)
 {
 	struct hbg_irq_info *info;
@@ -419,6 +422,9 @@ static int hbg_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (ret)
 		return ret;
 
+	/* set default features */
+	netdev->features |= HBG_SUPPORT_FEATURES;
+	netdev->hw_features |= HBG_SUPPORT_FEATURES;
 	netdev->priv_flags |= IFF_UNICAST_FLT;
 
 	netdev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
index 35dd3512d00e4..8d814c8f19ea0 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_txrx.c
@@ -202,8 +202,14 @@ static int hbg_napi_tx_recycle(struct napi_struct *napi, int budget)
 }
 
 static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
-				    struct hbg_rx_desc *desc)
+				    struct hbg_rx_desc *desc,
+				    struct sk_buff *skb)
 {
+	bool rx_checksum_offload = !!(priv->netdev->features & NETIF_F_RXCSUM);
+
+	skb->ip_summed = rx_checksum_offload ?
+			 CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
+
 	if (likely(!FIELD_GET(HBG_RX_DESC_W4_L3_ERR_CODE_M, desc->word4) &&
 		   !FIELD_GET(HBG_RX_DESC_W4_L4_ERR_CODE_M, desc->word4)))
 		return true;
@@ -215,8 +221,13 @@ static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
 		priv->stats.rx_desc_l3_wrong_head_cnt++;
 		return false;
 	case HBG_L3_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
 		priv->stats.rx_desc_l3_csum_err_cnt++;
-		return false;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
 	case HBG_L3_LEN_ERR:
 		priv->stats.rx_desc_l3_len_err_cnt++;
 		return false;
@@ -238,8 +249,13 @@ static bool hbg_rx_check_l3l4_error(struct hbg_priv *priv,
 		priv->stats.rx_desc_l4_len_err_cnt++;
 		return false;
 	case HBG_L4_CSUM_ERR:
+		skb->ip_summed = CHECKSUM_NONE;
 		priv->stats.rx_desc_l4_csum_err_cnt++;
-		return false;
+
+		/* Don't drop packets on csum validation failure,
+		 * suggest by Jakub
+		 */
+		break;
 	case HBG_L4_ZERO_PORT_NUM:
 		priv->stats.rx_desc_l4_zero_port_num_cnt++;
 		return false;
@@ -322,7 +338,8 @@ static void hbg_update_rx_protocol_stats(struct hbg_priv *priv,
 	hbg_update_rx_ip_protocol_stats(priv, desc);
 }
 
-static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc)
+static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc,
+			     struct sk_buff *skb)
 {
 	if (unlikely(FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, desc->word2) >
 		     priv->dev_specs.max_frame_len)) {
@@ -342,7 +359,7 @@ static bool hbg_rx_pkt_check(struct hbg_priv *priv, struct hbg_rx_desc *desc)
 		return false;
 	}
 
-	if (unlikely(!hbg_rx_check_l3l4_error(priv, desc))) {
+	if (unlikely(!hbg_rx_check_l3l4_error(priv, desc, skb))) {
 		priv->stats.rx_desc_l3l4_err_cnt++;
 		return false;
 	}
@@ -413,7 +430,7 @@ static int hbg_napi_rx_poll(struct napi_struct *napi, int budget)
 		rx_desc = (struct hbg_rx_desc *)buffer->skb->data;
 		pkt_len = FIELD_GET(HBG_RX_DESC_W2_PKT_LEN_M, rx_desc->word2);
 
-		if (unlikely(!hbg_rx_pkt_check(priv, rx_desc))) {
+		if (unlikely(!hbg_rx_pkt_check(priv, rx_desc, buffer->skb))) {
 			hbg_buffer_free(buffer);
 			goto next_buffer;
 		}

From fd394a334b1c29caeae45f15d8b99b77c881bc63 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:08 +0800
Subject: [PATCH 1500/2753] net: hibmcge: Add support for abnormal irq handling
 feature

the hardware error was reported by interrupt,
and need be fixed by doing function reset,
but the whole reset flow takes a long time,
should not do it in irq handler,
so do it in scheduled task.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/hisilicon/hibmcge/hbg_common.h   |  5 ++
 .../ethernet/hisilicon/hibmcge/hbg_debugfs.c  |  5 +-
 .../net/ethernet/hisilicon/hibmcge/hbg_err.c  | 58 +++++++++++++++++++
 .../net/ethernet/hisilicon/hibmcge/hbg_err.h  |  1 +
 .../ethernet/hisilicon/hibmcge/hbg_ethtool.c  |  1 +
 .../net/ethernet/hisilicon/hibmcge/hbg_irq.c  | 55 +++++++++++-------
 .../net/ethernet/hisilicon/hibmcge/hbg_main.c |  9 +++
 .../net/ethernet/hisilicon/hibmcge/hbg_reg.h  |  1 +
 8 files changed, 112 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index 920514a8e29a5..4e4d33d2832a7 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -36,6 +36,7 @@ enum hbg_nic_state {
 	HBG_NIC_STATE_EVENT_HANDLING = 0,
 	HBG_NIC_STATE_RESETTING,
 	HBG_NIC_STATE_RESET_FAIL,
+	HBG_NIC_STATE_NEED_RESET, /* trigger a reset in scheduled task */
 };
 
 enum hbg_reset_type {
@@ -104,6 +105,7 @@ struct hbg_irq_info {
 	u32 mask;
 	bool re_enable;
 	bool need_print;
+	bool need_reset;
 	u64 count;
 
 	void (*irq_handle)(struct hbg_priv *priv, struct hbg_irq_info *info);
@@ -220,6 +222,7 @@ struct hbg_stats {
 	u64 rx_fail_comma_cnt;
 
 	u64 rx_dma_err_cnt;
+	u64 rx_fifo_less_empty_thrsld_cnt;
 
 	u64 tx_octets_total_ok_cnt;
 	u64 tx_uc_pkt_cnt;
@@ -268,4 +271,6 @@ struct hbg_priv {
 	struct delayed_work service_task;
 };
 
+void hbg_err_reset_task_schedule(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
index 8473c43d171a9..55ce90b4319aa 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -67,10 +67,11 @@ static int hbg_dbg_irq_info(struct seq_file *s, void *unused)
 	for (i = 0; i < priv->vectors.info_array_len; i++) {
 		info = &priv->vectors.info_array[i];
 		seq_printf(s,
-			   "%-20s: enabled: %-5s, logged: %-5s, count: %llu\n",
+			   "%-20s: enabled: %-5s, reset: %-5s, logged: %-5s, count: %llu\n",
 			   info->name,
 			   str_true_false(hbg_hw_irq_is_enabled(priv,
 								info->mask)),
+			   str_true_false(info->need_reset),
 			   str_true_false(info->need_print),
 			   info->count);
 	}
@@ -114,6 +115,8 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 		   state_str_true_false(priv, HBG_NIC_STATE_RESET_FAIL));
 	seq_printf(s, "last reset type: %s\n",
 		   reset_type_str[priv->reset_type]);
+	seq_printf(s, "need reset state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
index 4d1f4a33391a8..4e8cb66f601c0 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.c
@@ -105,6 +105,62 @@ int hbg_reset(struct hbg_priv *priv)
 	return hbg_reset_done(priv, HBG_RESET_TYPE_FUNCTION);
 }
 
+void hbg_err_reset(struct hbg_priv *priv)
+{
+	bool running;
+
+	rtnl_lock();
+	running = netif_running(priv->netdev);
+	if (running)
+		dev_close(priv->netdev);
+
+	hbg_reset(priv);
+
+	/* in hbg_pci_err_detected(), we will detach first,
+	 * so we need to attach before open
+	 */
+	if (!netif_device_present(priv->netdev))
+		netif_device_attach(priv->netdev);
+
+	if (running)
+		dev_open(priv->netdev, NULL);
+	rtnl_unlock();
+}
+
+static pci_ers_result_t hbg_pci_err_detected(struct pci_dev *pdev,
+					     pci_channel_state_t state)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+
+	netif_device_detach(netdev);
+
+	if (state == pci_channel_io_perm_failure)
+		return PCI_ERS_RESULT_DISCONNECT;
+
+	pci_disable_device(pdev);
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+static pci_ers_result_t hbg_pci_err_slot_reset(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct hbg_priv *priv = netdev_priv(netdev);
+
+	if (pci_enable_device(pdev)) {
+		dev_err(&pdev->dev,
+			"failed to re-enable PCI device after reset\n");
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	pci_set_master(pdev);
+	pci_restore_state(pdev);
+	pci_save_state(pdev);
+
+	hbg_err_reset(priv);
+	netif_device_attach(netdev);
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
 static void hbg_pci_err_reset_prepare(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -124,6 +180,8 @@ static void hbg_pci_err_reset_done(struct pci_dev *pdev)
 }
 
 static const struct pci_error_handlers hbg_pci_err_handler = {
+	.error_detected = hbg_pci_err_detected,
+	.slot_reset = hbg_pci_err_slot_reset,
 	.reset_prepare = hbg_pci_err_reset_prepare,
 	.reset_done = hbg_pci_err_reset_done,
 };
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
index d7828e446308f..fb9fbe7004e8f 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_err.h
@@ -9,5 +9,6 @@
 void hbg_set_pci_err_handler(struct pci_driver *pdrv);
 int hbg_reset(struct hbg_priv *priv);
 int hbg_rebuild(struct hbg_priv *priv);
+void hbg_err_reset(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
index f5be8d0ef6116..8f1107b85fbb0 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_ethtool.c
@@ -69,6 +69,7 @@ static const struct hbg_ethtool_stats hbg_ethtool_stats_info[] = {
 			HBG_REG_RX_LENGTHFIELD_ERR_CNT_ADDR),
 	HBG_STATS_REG_I(rx_fail_comma_cnt, HBG_REG_RX_FAIL_COMMA_CNT_ADDR),
 	HBG_STATS_I(rx_dma_err_cnt),
+	HBG_STATS_I(rx_fifo_less_empty_thrsld_cnt),
 
 	HBG_STATS_REG_I(tx_uc_pkt_cnt, HBG_REG_TX_UC_PKTS_ADDR),
 	HBG_STATS_REG_I(tx_vlan_pkt_cnt, HBG_REG_TX_TAGGED_ADDR),
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
index 25dd25f096fe0..e79e9ab3e5308 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_irq.c
@@ -11,6 +11,9 @@ static void hbg_irq_handle_err(struct hbg_priv *priv,
 	if (irq_info->need_print)
 		dev_err(&priv->pdev->dev,
 			"receive error interrupt: %s\n", irq_info->name);
+
+	if (irq_info->need_reset)
+		hbg_err_reset_task_schedule(priv);
 }
 
 static void hbg_irq_handle_tx(struct hbg_priv *priv,
@@ -25,30 +28,38 @@ static void hbg_irq_handle_rx(struct hbg_priv *priv,
 	napi_schedule(&priv->rx_ring.napi);
 }
 
-#define HBG_TXRX_IRQ_I(name, handle) \
-	{#name, HBG_INT_MSK_##name##_B, false, false, 0, handle}
-#define HBG_ERR_IRQ_I(name, need_print) \
-	{#name, HBG_INT_MSK_##name##_B, true, need_print, 0, hbg_irq_handle_err}
+static void hbg_irq_handle_rx_buf_val(struct hbg_priv *priv,
+				      struct hbg_irq_info *irq_info)
+{
+	priv->stats.rx_fifo_less_empty_thrsld_cnt++;
+}
+
+#define HBG_IRQ_I(name, handle) \
+	{#name, HBG_INT_MSK_##name##_B, false, false, false, 0, handle}
+#define HBG_ERR_IRQ_I(name, need_print, ndde_reset) \
+	{#name, HBG_INT_MSK_##name##_B, true, need_print, \
+	ndde_reset, 0, hbg_irq_handle_err}
 
 static struct hbg_irq_info hbg_irqs[] = {
-	HBG_TXRX_IRQ_I(RX, hbg_irq_handle_rx),
-	HBG_TXRX_IRQ_I(TX, hbg_irq_handle_tx),
-	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true),
-	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true),
-	HBG_ERR_IRQ_I(TX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(RX_BUF_AVL, false),
-	HBG_ERR_IRQ_I(REL_BUF_ERR, true),
-	HBG_ERR_IRQ_I(TXCFG_AVL, false),
-	HBG_ERR_IRQ_I(TX_DROP, false),
-	HBG_ERR_IRQ_I(RX_DROP, false),
-	HBG_ERR_IRQ_I(RX_AHB_ERR, true),
-	HBG_ERR_IRQ_I(MAC_FIFO_ERR, false),
-	HBG_ERR_IRQ_I(RBREQ_ERR, false),
-	HBG_ERR_IRQ_I(WE_ERR, false),
+	HBG_IRQ_I(RX, hbg_irq_handle_rx),
+	HBG_IRQ_I(TX, hbg_irq_handle_tx),
+	HBG_ERR_IRQ_I(TX_PKT_CPL, true, true),
+	HBG_ERR_IRQ_I(MAC_MII_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_PCS_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_RX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(MAC_APP_TX_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(SRAM_PARITY_ERR, true, false),
+	HBG_ERR_IRQ_I(TX_AHB_ERR, true, true),
+	HBG_IRQ_I(RX_BUF_AVL, hbg_irq_handle_rx_buf_val),
+	HBG_ERR_IRQ_I(REL_BUF_ERR, true, false),
+	HBG_ERR_IRQ_I(TXCFG_AVL, false, false),
+	HBG_ERR_IRQ_I(TX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_DROP, false, false),
+	HBG_ERR_IRQ_I(RX_AHB_ERR, true, false),
+	HBG_ERR_IRQ_I(MAC_FIFO_ERR, true, true),
+	HBG_ERR_IRQ_I(RBREQ_ERR, true, true),
+	HBG_ERR_IRQ_I(WE_ERR, true, true),
 };
 
 static irqreturn_t hbg_irq_handle(int irq_num, void *p)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 688f408de84cd..40f62db33feda 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -283,6 +283,9 @@ static void hbg_service_task(struct work_struct *work)
 	struct hbg_priv *priv = container_of(work, struct hbg_priv,
 					     service_task.work);
 
+	if (test_and_clear_bit(HBG_NIC_STATE_NEED_RESET, &priv->state))
+		hbg_err_reset(priv);
+
 	/* The type of statistics register is u32,
 	 * To prevent the statistics register from overflowing,
 	 * the driver dumps the statistics every 30 seconds.
@@ -292,6 +295,12 @@ static void hbg_service_task(struct work_struct *work)
 			      msecs_to_jiffies(30 * MSEC_PER_SEC));
 }
 
+void hbg_err_reset_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NEED_RESET, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
 static void hbg_cancel_delayed_work_sync(void *data)
 {
 	cancel_delayed_work_sync(data);
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index 106d0e0408ba4..c45450ab608c9 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -148,6 +148,7 @@
 #define HBG_INT_MSK_MAC_PCS_TX_FIFO_ERR_B	BIT(17)
 #define HBG_INT_MSK_MAC_PCS_RX_FIFO_ERR_B	BIT(16)
 #define HBG_INT_MSK_MAC_MII_FIFO_ERR_B		BIT(15)
+#define HBG_INT_MSK_TX_PKT_CPL_B		BIT(14)
 #define HBG_INT_MSK_TX_B			BIT(1) /* just used in driver */
 #define HBG_INT_MSK_RX_B			BIT(0) /* just used in driver */
 #define HBG_REG_CF_INTRPT_STAT_ADDR		(HBG_REG_SGMII_BASE + 0x0434)

From e0306637e85da84a0695452f42dc29a552051402 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:09 +0800
Subject: [PATCH 1501/2753] net: hibmcge: Add support for mac link exception
 handling feature

If the rate changed frequently, the PHY link ok,
but the MAC link maybe fails.
As a result, the network port is unavailable.

According to the documents of the chip,
core_reset needs to do to fix the fault.

In hw_adjus_link(), the core_reset is added to try to
ensure that MAC link status is normal.
In addition, MAC link failure detection is added.
If the MAC link fails after core_reset, driver invokes
the phy_stop() and phy_start() to re-link.

Due to phydev->lock, re-link cannot be triggered
in adjust_link(). Therefore, this operation
is invoked in a scheduled task.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/hisilicon/hibmcge/hbg_common.h   |  5 +++++
 .../ethernet/hisilicon/hibmcge/hbg_debugfs.c  |  2 ++
 .../net/ethernet/hisilicon/hibmcge/hbg_hw.c   | 10 +++++++++
 .../net/ethernet/hisilicon/hibmcge/hbg_main.c |  9 ++++++++
 .../net/ethernet/hisilicon/hibmcge/hbg_mdio.c | 22 +++++++++++++++++++
 .../net/ethernet/hisilicon/hibmcge/hbg_mdio.h |  2 ++
 .../net/ethernet/hisilicon/hibmcge/hbg_reg.h  |  1 +
 7 files changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index 4e4d33d2832a7..8b943912184bc 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -37,6 +37,7 @@ enum hbg_nic_state {
 	HBG_NIC_STATE_RESETTING,
 	HBG_NIC_STATE_RESET_FAIL,
 	HBG_NIC_STATE_NEED_RESET, /* trigger a reset in scheduled task */
+	HBG_NIC_STATE_NP_LINK_FAIL,
 };
 
 enum hbg_reset_type {
@@ -82,6 +83,7 @@ enum hbg_hw_event_type {
 	HBG_HW_EVENT_NONE = 0,
 	HBG_HW_EVENT_INIT, /* driver is loading */
 	HBG_HW_EVENT_RESET,
+	HBG_HW_EVENT_CORE_RESET,
 };
 
 struct hbg_dev_specs {
@@ -252,6 +254,8 @@ struct hbg_stats {
 
 	u64 tx_timeout_cnt;
 	u64 tx_dma_err_cnt;
+
+	u64 np_link_fail_cnt;
 };
 
 struct hbg_priv {
@@ -272,5 +276,6 @@ struct hbg_priv {
 };
 
 void hbg_err_reset_task_schedule(struct hbg_priv *priv);
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv);
 
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
index 55ce90b4319aa..5e0ba4d5b08d2 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_debugfs.c
@@ -117,6 +117,8 @@ static int hbg_dbg_nic_state(struct seq_file *s, void *unused)
 		   reset_type_str[priv->reset_type]);
 	seq_printf(s, "need reset state: %s\n",
 		   state_str_true_false(priv, HBG_NIC_STATE_NEED_RESET));
+	seq_printf(s, "np_link fail state: %s\n",
+		   state_str_true_false(priv, HBG_NIC_STATE_NP_LINK_FAIL));
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
index e7798f2136450..74a18033b4441 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_hw.c
@@ -213,10 +213,20 @@ void hbg_hw_fill_buffer(struct hbg_priv *priv, u32 buffer_dma_addr)
 
 void hbg_hw_adjust_link(struct hbg_priv *priv, u32 speed, u32 duplex)
 {
+	hbg_hw_mac_enable(priv, HBG_STATUS_DISABLE);
+
 	hbg_reg_write_field(priv, HBG_REG_PORT_MODE_ADDR,
 			    HBG_REG_PORT_MODE_M, speed);
 	hbg_reg_write_field(priv, HBG_REG_DUPLEX_TYPE_ADDR,
 			    HBG_REG_DUPLEX_B, duplex);
+
+	hbg_hw_event_notify(priv, HBG_HW_EVENT_CORE_RESET);
+
+	hbg_hw_mac_enable(priv, HBG_STATUS_ENABLE);
+
+	if (!hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+				HBG_REG_AN_NEG_STATE_NP_LINK_OK_B))
+		hbg_np_link_fail_task_schedule(priv);
 }
 
 /* only support uc filter */
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 40f62db33feda..3b7955f57b4d6 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -286,6 +286,9 @@ static void hbg_service_task(struct work_struct *work)
 	if (test_and_clear_bit(HBG_NIC_STATE_NEED_RESET, &priv->state))
 		hbg_err_reset(priv);
 
+	if (test_and_clear_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state))
+		hbg_fix_np_link_fail(priv);
+
 	/* The type of statistics register is u32,
 	 * To prevent the statistics register from overflowing,
 	 * the driver dumps the statistics every 30 seconds.
@@ -301,6 +304,12 @@ void hbg_err_reset_task_schedule(struct hbg_priv *priv)
 	schedule_delayed_work(&priv->service_task, 0);
 }
 
+void hbg_np_link_fail_task_schedule(struct hbg_priv *priv)
+{
+	set_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state);
+	schedule_delayed_work(&priv->service_task, 0);
+}
+
 static void hbg_cancel_delayed_work_sync(void *data)
 {
 	cancel_delayed_work_sync(data);
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
index db6bc4cfb971f..f29a937ad0879 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.c
@@ -17,6 +17,8 @@
 #define HBG_MDIO_OP_TIMEOUT_US		(1 * 1000 * 1000)
 #define HBG_MDIO_OP_INTERVAL_US		(5 * 1000)
 
+#define HBG_NP_LINK_FAIL_RETRY_TIMES	5
+
 static void hbg_mdio_set_command(struct hbg_mac *mac, u32 cmd)
 {
 	hbg_reg_write(HBG_MAC_GET_PRIV(mac), HBG_REG_MDIO_COMMAND_ADDR, cmd);
@@ -127,6 +129,26 @@ static void hbg_flowctrl_cfg(struct hbg_priv *priv)
 	hbg_hw_set_pause_enable(priv, tx_pause, rx_pause);
 }
 
+void hbg_fix_np_link_fail(struct hbg_priv *priv)
+{
+	struct device *dev = &priv->pdev->dev;
+
+	if (priv->stats.np_link_fail_cnt >= HBG_NP_LINK_FAIL_RETRY_TIMES) {
+		dev_err(dev, "failed to fix the MAC link status\n");
+		priv->stats.np_link_fail_cnt = 0;
+		return;
+	}
+
+	priv->stats.np_link_fail_cnt++;
+	dev_err(dev, "failed to link between MAC and PHY, try to fix...\n");
+
+	/* Replace phy_reset() with phy_stop() and phy_start(),
+	 * as suggested by Andrew.
+	 */
+	hbg_phy_stop(priv);
+	hbg_phy_start(priv);
+}
+
 static void hbg_phy_adjust_link(struct net_device *netdev)
 {
 	struct hbg_priv *priv = netdev_priv(netdev);
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
index febd02a309c79..f3771c1bbd347 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_mdio.h
@@ -9,4 +9,6 @@
 int hbg_mdio_init(struct hbg_priv *priv);
 void hbg_phy_start(struct hbg_priv *priv);
 void hbg_phy_stop(struct hbg_priv *priv);
+void hbg_fix_np_link_fail(struct hbg_priv *priv);
+
 #endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index c45450ab608c9..23c55a24b2848 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -54,6 +54,7 @@
 #define HBG_REG_PAUSE_ENABLE_RX_B		BIT(0)
 #define HBG_REG_PAUSE_ENABLE_TX_B		BIT(1)
 #define HBG_REG_AN_NEG_STATE_ADDR		(HBG_REG_SGMII_BASE + 0x0058)
+#define HBG_REG_AN_NEG_STATE_NP_LINK_OK_B	BIT(15)
 #define HBG_REG_TRANSMIT_CTRL_ADDR		(HBG_REG_SGMII_BASE + 0x0060)
 #define HBG_REG_TRANSMIT_CTRL_PAD_EN_B		BIT(7)
 #define HBG_REG_TRANSMIT_CTRL_CRC_ADD_B		BIT(6)

From 7a5d60dcf9981a5cc7b676e2d7472e10e0c1b681 Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:10 +0800
Subject: [PATCH 1502/2753] net: hibmcge: Add support for BMC diagnose feature

The MAC hardware is on the BMC side, and the driver is on the host side.
When the driver is abnormal, the BMC cannot directly detect the
exception cause.
Therefore, this patch implements the BMC diagnosis feature.

When users query driver diagnosis information on the BMC, the driver
detects the query request in the scheduled task and reports
driver statistics and link status to the BMC through the bar space.
The BMC collects logs to analyze exception causes.

Currently, the scheduled task is executed every 30 seconds
To quickly respond to user query requests,
this patch changes the scheduled task to once every second.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/hisilicon/hibmcge/Makefile   |   2 +-
 .../ethernet/hisilicon/hibmcge/hbg_common.h   |   1 +
 .../ethernet/hisilicon/hibmcge/hbg_diagnose.c | 348 ++++++++++++++++++
 .../ethernet/hisilicon/hibmcge/hbg_diagnose.h |  11 +
 .../net/ethernet/hisilicon/hibmcge/hbg_main.c |  11 +-
 .../net/ethernet/hisilicon/hibmcge/hbg_reg.h  |   7 +
 6 files changed, 377 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
 create mode 100644 drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/Makefile b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
index 7ea15f9ef8492..1a9da564b306a 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/Makefile
+++ b/drivers/net/ethernet/hisilicon/hibmcge/Makefile
@@ -6,4 +6,4 @@
 obj-$(CONFIG_HIBMCGE) += hibmcge.o
 
 hibmcge-objs = hbg_main.o hbg_hw.o hbg_mdio.o hbg_irq.o hbg_txrx.o hbg_ethtool.o \
-		hbg_debugfs.o hbg_err.o
+		hbg_debugfs.o hbg_err.o hbg_diagnose.o
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
index 8b943912184bc..f8cdab62bf85c 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_common.h
@@ -272,6 +272,7 @@ struct hbg_priv {
 	enum hbg_reset_type reset_type;
 	struct hbg_user_def user_def;
 	struct hbg_stats stats;
+	unsigned long last_update_stats_time;
 	struct delayed_work service_task;
 };
 
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
new file mode 100644
index 0000000000000..d61c03f34ff05
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.c
@@ -0,0 +1,348 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (c) 2025 Hisilicon Limited.
+
+#include <linux/iopoll.h>
+#include <linux/phy.h>
+#include "hbg_common.h"
+#include "hbg_ethtool.h"
+#include "hbg_hw.h"
+#include "hbg_diagnose.h"
+
+#define HBG_MSG_DATA_MAX_NUM	64
+
+struct hbg_diagnose_message {
+	u32 opcode;
+	u32 status;
+	u32 data_num;
+	struct hbg_priv *priv;
+
+	u32 data[HBG_MSG_DATA_MAX_NUM];
+};
+
+#define HBG_HW_PUSH_WAIT_TIMEOUT_US	(2 * 1000 * 1000)
+#define HBG_HW_PUSH_WAIT_INTERVAL_US	(1 * 1000)
+
+enum hbg_push_cmd {
+	HBG_PUSH_CMD_IRQ = 0,
+	HBG_PUSH_CMD_STATS,
+	HBG_PUSH_CMD_LINK,
+};
+
+struct hbg_push_stats_info {
+	/* id is used to match the name of the current stats item.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u64 offset;
+};
+
+struct hbg_push_irq_info {
+	/* id is used to match the name of the current irq.
+	 * and is used for pretty print on BMC
+	 */
+	u32 id;
+	u32 mask;
+};
+
+#define HBG_PUSH_IRQ_I(name, id) {id, HBG_INT_MSK_##name##_B}
+static const struct hbg_push_irq_info hbg_push_irq_list[] = {
+	HBG_PUSH_IRQ_I(RX, 0),
+	HBG_PUSH_IRQ_I(TX, 1),
+	HBG_PUSH_IRQ_I(TX_PKT_CPL, 2),
+	HBG_PUSH_IRQ_I(MAC_MII_FIFO_ERR, 3),
+	HBG_PUSH_IRQ_I(MAC_PCS_RX_FIFO_ERR, 4),
+	HBG_PUSH_IRQ_I(MAC_PCS_TX_FIFO_ERR, 5),
+	HBG_PUSH_IRQ_I(MAC_APP_RX_FIFO_ERR, 6),
+	HBG_PUSH_IRQ_I(MAC_APP_TX_FIFO_ERR, 7),
+	HBG_PUSH_IRQ_I(SRAM_PARITY_ERR, 8),
+	HBG_PUSH_IRQ_I(TX_AHB_ERR, 9),
+	HBG_PUSH_IRQ_I(RX_BUF_AVL, 10),
+	HBG_PUSH_IRQ_I(REL_BUF_ERR, 11),
+	HBG_PUSH_IRQ_I(TXCFG_AVL, 12),
+	HBG_PUSH_IRQ_I(TX_DROP, 13),
+	HBG_PUSH_IRQ_I(RX_DROP, 14),
+	HBG_PUSH_IRQ_I(RX_AHB_ERR, 15),
+	HBG_PUSH_IRQ_I(MAC_FIFO_ERR, 16),
+	HBG_PUSH_IRQ_I(RBREQ_ERR, 17),
+	HBG_PUSH_IRQ_I(WE_ERR, 18),
+};
+
+#define HBG_PUSH_STATS_I(name, id) {id, HBG_STATS_FIELD_OFF(name)}
+static const struct hbg_push_stats_info hbg_push_stats_list[] = {
+	HBG_PUSH_STATS_I(rx_desc_drop, 0),
+	HBG_PUSH_STATS_I(rx_desc_l2_err_cnt, 1),
+	HBG_PUSH_STATS_I(rx_desc_pkt_len_err_cnt, 2),
+	HBG_PUSH_STATS_I(rx_desc_l3_wrong_head_cnt, 3),
+	HBG_PUSH_STATS_I(rx_desc_l3_csum_err_cnt, 4),
+	HBG_PUSH_STATS_I(rx_desc_l3_len_err_cnt, 5),
+	HBG_PUSH_STATS_I(rx_desc_l3_zero_ttl_cnt, 6),
+	HBG_PUSH_STATS_I(rx_desc_l3_other_cnt, 7),
+	HBG_PUSH_STATS_I(rx_desc_l4_err_cnt, 8),
+	HBG_PUSH_STATS_I(rx_desc_l4_wrong_head_cnt, 9),
+	HBG_PUSH_STATS_I(rx_desc_l4_len_err_cnt, 10),
+	HBG_PUSH_STATS_I(rx_desc_l4_csum_err_cnt, 11),
+	HBG_PUSH_STATS_I(rx_desc_l4_zero_port_num_cnt, 12),
+	HBG_PUSH_STATS_I(rx_desc_l4_other_cnt, 13),
+	HBG_PUSH_STATS_I(rx_desc_frag_cnt, 14),
+	HBG_PUSH_STATS_I(rx_desc_ip_ver_err_cnt, 15),
+	HBG_PUSH_STATS_I(rx_desc_ipv4_pkt_cnt, 16),
+	HBG_PUSH_STATS_I(rx_desc_ipv6_pkt_cnt, 17),
+	HBG_PUSH_STATS_I(rx_desc_no_ip_pkt_cnt, 18),
+	HBG_PUSH_STATS_I(rx_desc_ip_pkt_cnt, 19),
+	HBG_PUSH_STATS_I(rx_desc_tcp_pkt_cnt, 20),
+	HBG_PUSH_STATS_I(rx_desc_udp_pkt_cnt, 21),
+	HBG_PUSH_STATS_I(rx_desc_vlan_pkt_cnt, 22),
+	HBG_PUSH_STATS_I(rx_desc_icmp_pkt_cnt, 23),
+	HBG_PUSH_STATS_I(rx_desc_arp_pkt_cnt, 24),
+	HBG_PUSH_STATS_I(rx_desc_rarp_pkt_cnt, 25),
+	HBG_PUSH_STATS_I(rx_desc_multicast_pkt_cnt, 26),
+	HBG_PUSH_STATS_I(rx_desc_broadcast_pkt_cnt, 27),
+	HBG_PUSH_STATS_I(rx_desc_ipsec_pkt_cnt, 28),
+	HBG_PUSH_STATS_I(rx_desc_ip_opt_pkt_cnt, 29),
+	HBG_PUSH_STATS_I(rx_desc_key_not_match_cnt, 30),
+	HBG_PUSH_STATS_I(rx_octets_total_ok_cnt, 31),
+	HBG_PUSH_STATS_I(rx_uc_pkt_cnt, 32),
+	HBG_PUSH_STATS_I(rx_mc_pkt_cnt, 33),
+	HBG_PUSH_STATS_I(rx_bc_pkt_cnt, 34),
+	HBG_PUSH_STATS_I(rx_vlan_pkt_cnt, 35),
+	HBG_PUSH_STATS_I(rx_octets_bad_cnt, 36),
+	HBG_PUSH_STATS_I(rx_octets_total_filt_cnt, 37),
+	HBG_PUSH_STATS_I(rx_filt_pkt_cnt, 38),
+	HBG_PUSH_STATS_I(rx_trans_pkt_cnt, 39),
+	HBG_PUSH_STATS_I(rx_framesize_64, 40),
+	HBG_PUSH_STATS_I(rx_framesize_65_127, 41),
+	HBG_PUSH_STATS_I(rx_framesize_128_255, 42),
+	HBG_PUSH_STATS_I(rx_framesize_256_511, 43),
+	HBG_PUSH_STATS_I(rx_framesize_512_1023, 44),
+	HBG_PUSH_STATS_I(rx_framesize_1024_1518, 45),
+	HBG_PUSH_STATS_I(rx_framesize_bt_1518, 46),
+	HBG_PUSH_STATS_I(rx_fcs_error_cnt, 47),
+	HBG_PUSH_STATS_I(rx_data_error_cnt, 48),
+	HBG_PUSH_STATS_I(rx_align_error_cnt, 49),
+	HBG_PUSH_STATS_I(rx_frame_long_err_cnt, 50),
+	HBG_PUSH_STATS_I(rx_jabber_err_cnt, 51),
+	HBG_PUSH_STATS_I(rx_pause_macctl_frame_cnt, 52),
+	HBG_PUSH_STATS_I(rx_unknown_macctl_frame_cnt, 53),
+	HBG_PUSH_STATS_I(rx_frame_very_long_err_cnt, 54),
+	HBG_PUSH_STATS_I(rx_frame_runt_err_cnt, 55),
+	HBG_PUSH_STATS_I(rx_frame_short_err_cnt, 56),
+	HBG_PUSH_STATS_I(rx_overflow_cnt, 57),
+	HBG_PUSH_STATS_I(rx_bufrq_err_cnt, 58),
+	HBG_PUSH_STATS_I(rx_we_err_cnt, 59),
+	HBG_PUSH_STATS_I(rx_overrun_cnt, 60),
+	HBG_PUSH_STATS_I(rx_lengthfield_err_cnt, 61),
+	HBG_PUSH_STATS_I(rx_fail_comma_cnt, 62),
+	HBG_PUSH_STATS_I(rx_dma_err_cnt, 63),
+	HBG_PUSH_STATS_I(rx_fifo_less_empty_thrsld_cnt, 64),
+	HBG_PUSH_STATS_I(tx_octets_total_ok_cnt, 65),
+	HBG_PUSH_STATS_I(tx_uc_pkt_cnt, 66),
+	HBG_PUSH_STATS_I(tx_mc_pkt_cnt, 67),
+	HBG_PUSH_STATS_I(tx_bc_pkt_cnt, 68),
+	HBG_PUSH_STATS_I(tx_vlan_pkt_cnt, 69),
+	HBG_PUSH_STATS_I(tx_octets_bad_cnt, 70),
+	HBG_PUSH_STATS_I(tx_trans_pkt_cnt, 71),
+	HBG_PUSH_STATS_I(tx_pause_frame_cnt, 72),
+	HBG_PUSH_STATS_I(tx_framesize_64, 73),
+	HBG_PUSH_STATS_I(tx_framesize_65_127, 74),
+	HBG_PUSH_STATS_I(tx_framesize_128_255, 75),
+	HBG_PUSH_STATS_I(tx_framesize_256_511, 76),
+	HBG_PUSH_STATS_I(tx_framesize_512_1023, 77),
+	HBG_PUSH_STATS_I(tx_framesize_1024_1518, 78),
+	HBG_PUSH_STATS_I(tx_framesize_bt_1518, 79),
+	HBG_PUSH_STATS_I(tx_underrun_err_cnt, 80),
+	HBG_PUSH_STATS_I(tx_add_cs_fail_cnt, 81),
+	HBG_PUSH_STATS_I(tx_bufrl_err_cnt, 82),
+	HBG_PUSH_STATS_I(tx_crc_err_cnt, 83),
+	HBG_PUSH_STATS_I(tx_drop_cnt, 84),
+	HBG_PUSH_STATS_I(tx_excessive_length_drop_cnt, 85),
+	HBG_PUSH_STATS_I(tx_dma_err_cnt, 86),
+};
+
+static int hbg_push_msg_send(struct hbg_priv *priv,
+			     struct hbg_diagnose_message *msg)
+{
+	u32 header = 0;
+	u32 i;
+
+	if (msg->data_num == 0)
+		return 0;
+
+	for (i = 0; i < msg->data_num && i < HBG_MSG_DATA_MAX_NUM; i++)
+		hbg_reg_write(priv,
+			      HBG_REG_MSG_DATA_BASE_ADDR + i * sizeof(u32),
+			      msg->data[i]);
+
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_OPCODE_M, msg->opcode);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_DATA_NUM_M,  msg->data_num);
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_RESP_CODE_M, ETIMEDOUT);
+
+	/* start status */
+	hbg_field_modify(header, HBG_REG_MSG_HEADER_STATUS_M, 1);
+
+	/* write header msg to start push */
+	hbg_reg_write(priv, HBG_REG_MSG_HEADER_ADDR, header);
+
+	/* wait done */
+	readl_poll_timeout(priv->io_base + HBG_REG_MSG_HEADER_ADDR, header,
+			   !FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header),
+			   HBG_HW_PUSH_WAIT_INTERVAL_US,
+			   HBG_HW_PUSH_WAIT_TIMEOUT_US);
+
+	msg->status = FIELD_GET(HBG_REG_MSG_HEADER_STATUS_M, header);
+	return -(int)FIELD_GET(HBG_REG_MSG_HEADER_RESP_CODE_M, header);
+}
+
+static int hbg_push_data(struct hbg_priv *priv,
+			 u32 opcode, u32 *data, u32 data_num)
+{
+	struct hbg_diagnose_message msg = {0};
+	u32 data_left_num;
+	u32 i, j;
+	int ret;
+
+	msg.priv = priv;
+	msg.opcode = opcode;
+	for (i = 0; i < data_num / HBG_MSG_DATA_MAX_NUM + 1; i++) {
+		if (i * HBG_MSG_DATA_MAX_NUM >= data_num)
+			break;
+
+		data_left_num = data_num - i * HBG_MSG_DATA_MAX_NUM;
+		for (j = 0; j < data_left_num && j < HBG_MSG_DATA_MAX_NUM; j++)
+			msg.data[j] = data[i * HBG_MSG_DATA_MAX_NUM + j];
+
+		msg.data_num = j;
+		ret = hbg_push_msg_send(priv, &msg);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int hbg_push_data_u64(struct hbg_priv *priv, u32 opcode,
+			     u64 *data, u32 data_num)
+{
+	/* The length of u64 is twice that of u32,
+	 * the data_num must be multiplied by 2.
+	 */
+	return hbg_push_data(priv, opcode, (u32 *)data, data_num * 2);
+}
+
+static u64 hbg_get_irq_stats(struct hbg_vector *vectors, u32 mask)
+{
+	u32 i = 0;
+
+	for (i = 0; i < vectors->info_array_len; i++)
+		if (vectors->info_array[i].mask == mask)
+			return vectors->info_array[i].count;
+
+	return 0;
+}
+
+static int hbg_push_irq_cnt(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u32 data_num = ARRAY_SIZE(hbg_push_irq_list) * 2;
+	struct hbg_vector *vectors = &priv->vectors;
+	const struct hbg_push_irq_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_irq_list[j++];
+		data[i] = info->id;
+		data[i + 1] = hbg_get_irq_stats(vectors, info->mask);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_IRQ, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+static int hbg_push_link_status(struct hbg_priv *priv)
+{
+	u32 link_status[2];
+
+	/* phy link status */
+	link_status[0] = priv->mac.phydev->link;
+	/* mac link status */
+	link_status[1] = hbg_reg_read_field(priv, HBG_REG_AN_NEG_STATE_ADDR,
+					    HBG_REG_AN_NEG_STATE_NP_LINK_OK_B);
+
+	return hbg_push_data(priv, HBG_PUSH_CMD_LINK,
+			     link_status, ARRAY_SIZE(link_status));
+}
+
+static int hbg_push_stats(struct hbg_priv *priv)
+{
+	/* An id needs to be added for each data.
+	 * Therefore, the data_num must be multiplied by 2.
+	 */
+	u64 data_num = ARRAY_SIZE(hbg_push_stats_list) * 2;
+	struct hbg_stats *stats = &priv->stats;
+	const struct hbg_push_stats_info *info;
+	u32 i, j = 0;
+	u64 *data;
+	int ret;
+
+	data = kcalloc(data_num, sizeof(u64), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* An id needs to be added for each data.
+	 * So i + 2 for each loop.
+	 */
+	for (i = 0; i < data_num; i += 2) {
+		info = &hbg_push_stats_list[j++];
+		data[i] = info->id;
+		data[i + 1] = HBG_STATS_R(stats, info->offset);
+	}
+
+	ret = hbg_push_data_u64(priv, HBG_PUSH_CMD_STATS, data, data_num);
+	kfree(data);
+	return ret;
+}
+
+void hbg_diagnose_message_push(struct hbg_priv *priv)
+{
+	int ret;
+
+	if (test_bit(HBG_NIC_STATE_RESETTING, &priv->state))
+		return;
+
+	/* only 1 is the right value */
+	if (hbg_reg_read(priv, HBG_REG_PUSH_REQ_ADDR) != 1)
+		return;
+
+	ret = hbg_push_irq_cnt(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push irq cnt, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_link_status(priv);
+	if (ret) {
+		dev_err(&priv->pdev->dev,
+			"failed to push link status, ret = %d\n", ret);
+		goto push_done;
+	}
+
+	ret = hbg_push_stats(priv);
+	if (ret)
+		dev_err(&priv->pdev->dev,
+			"failed to push stats, ret = %d\n", ret);
+
+push_done:
+	hbg_reg_write(priv, HBG_REG_PUSH_REQ_ADDR, 0);
+}
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
new file mode 100644
index 0000000000000..ba04c6d8c03db
--- /dev/null
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_diagnose.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (c) 2025 Hisilicon Limited. */
+
+#ifndef __HBG_DIAGNOSE_H
+#define __HBG_DIAGNOSE_H
+
+#include "hbg_common.h"
+
+void hbg_diagnose_message_push(struct hbg_priv *priv);
+
+#endif
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index 3b7955f57b4d6..c6a955e640fc1 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include "hbg_common.h"
+#include "hbg_diagnose.h"
 #include "hbg_err.h"
 #include "hbg_ethtool.h"
 #include "hbg_hw.h"
@@ -289,13 +290,19 @@ static void hbg_service_task(struct work_struct *work)
 	if (test_and_clear_bit(HBG_NIC_STATE_NP_LINK_FAIL, &priv->state))
 		hbg_fix_np_link_fail(priv);
 
+	hbg_diagnose_message_push(priv);
+
 	/* The type of statistics register is u32,
 	 * To prevent the statistics register from overflowing,
 	 * the driver dumps the statistics every 30 seconds.
 	 */
-	hbg_update_stats(priv);
+	if (time_after(jiffies, priv->last_update_stats_time + 30 * HZ)) {
+		hbg_update_stats(priv);
+		priv->last_update_stats_time = jiffies;
+	}
+
 	schedule_delayed_work(&priv->service_task,
-			      msecs_to_jiffies(30 * MSEC_PER_SEC));
+			      msecs_to_jiffies(MSEC_PER_SEC));
 }
 
 void hbg_err_reset_task_schedule(struct hbg_priv *priv)
diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
index 23c55a24b2848..cc2cc612770d7 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_reg.h
@@ -18,6 +18,13 @@
 #define HBG_REG_TX_FIFO_NUM_ADDR		0x0030
 #define HBG_REG_RX_FIFO_NUM_ADDR		0x0034
 #define HBG_REG_VLAN_LAYERS_ADDR		0x0038
+#define HBG_REG_PUSH_REQ_ADDR			0x00F0
+#define HBG_REG_MSG_HEADER_ADDR			0x00F4
+#define HBG_REG_MSG_HEADER_OPCODE_M		GENMASK(7, 0)
+#define HBG_REG_MSG_HEADER_STATUS_M		GENMASK(11, 8)
+#define HBG_REG_MSG_HEADER_DATA_NUM_M		GENMASK(19, 12)
+#define HBG_REG_MSG_HEADER_RESP_CODE_M		GENMASK(27, 20)
+#define HBG_REG_MSG_DATA_BASE_ADDR		0x0100
 
 /* MDIO */
 #define HBG_REG_MDIO_BASE			0x8000

From 615552c601ed3f7c8b88cdb9745e2ace769c264f Mon Sep 17 00:00:00 2001
From: Jijie Shao <shaojijie@huawei.com>
Date: Fri, 28 Feb 2025 19:54:11 +0800
Subject: [PATCH 1503/2753] net: hibmcge: Add support for ioctl

This patch implements the .ndo_eth_ioctl() to
read and write the PHY register.

Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
index c6a955e640fc1..2ac5454338e4d 100644
--- a/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
+++ b/drivers/net/ethernet/hisilicon/hibmcge/hbg_main.c
@@ -5,6 +5,7 @@
 #include <linux/if_vlan.h>
 #include <linux/netdevice.h>
 #include <linux/pci.h>
+#include <linux/phy.h>
 #include "hbg_common.h"
 #include "hbg_diagnose.h"
 #include "hbg_err.h"
@@ -277,6 +278,7 @@ static const struct net_device_ops hbg_netdev_ops = {
 	.ndo_tx_timeout		= hbg_net_tx_timeout,
 	.ndo_set_rx_mode	= hbg_net_set_rx_mode,
 	.ndo_get_stats64	= hbg_net_get_stats,
+	.ndo_eth_ioctl		= phy_do_ioctl_running,
 };
 
 static void hbg_service_task(struct work_struct *work)

From 799b7f93c01060d3d24c09d971bb6ce3c9601c71 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 4 Mar 2025 13:47:59 +0100
Subject: [PATCH 1504/2753] wifi: iwlwifi: remove mld/roc.c

This file should never have been part of the commit, remove it.

Fixes: af3be9088404 ("wifi: iwlwifi: support ROC version 6")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/roc.c | 224 -------------------
 1 file changed, 224 deletions(-)
 delete mode 100644 drivers/net/wireless/intel/iwlwifi/mld/roc.c

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.c b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
deleted file mode 100644
index b87faca23cebe..0000000000000
--- a/drivers/net/wireless/intel/iwlwifi/mld/roc.c
+++ /dev/null
@@ -1,224 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
-/*
- * Copyright (C) 2024 - 2025 Intel Corporation
- */
-#include <net/cfg80211.h>
-#include <net/mac80211.h>
-
-#include "mld.h"
-#include "roc.h"
-#include "hcmd.h"
-#include "iface.h"
-#include "sta.h"
-#include "mlo.h"
-
-#include "fw/api/context.h"
-#include "fw/api/time-event.h"
-
-#define AUX_ROC_MAX_DELAY MSEC_TO_TU(200)
-
-static void
-iwl_mld_vif_iter_emlsr_block_roc(void *data, u8 *mac, struct ieee80211_vif *vif)
-{
-	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	int *result = data;
-	int ret;
-
-	ret = iwl_mld_block_emlsr_sync(mld_vif->mld, vif,
-				       IWL_MLD_EMLSR_BLOCKED_ROC,
-				       iwl_mld_get_primary_link(vif));
-	if (ret)
-		*result = ret;
-}
-
-int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
-		      struct ieee80211_channel *channel, int duration,
-		      enum ieee80211_roc_type type)
-{
-	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
-	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct iwl_mld_int_sta *aux_sta;
-	struct iwl_roc_req cmd = {
-		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
-	};
-	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
-				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
-	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
-	enum iwl_roc_activity activity;
-	int ret = 0;
-
-	lockdep_assert_wiphy(mld->wiphy);
-
-	ieee80211_iterate_active_interfaces_mtx(mld->hw,
-						IEEE80211_IFACE_ITER_NORMAL,
-						iwl_mld_vif_iter_emlsr_block_roc,
-						&ret);
-	if (ret)
-		return ret;
-
-	/* TODO: task=Hotspot 2.0 */
-	if (vif->type != NL80211_IFTYPE_P2P_DEVICE) {
-		IWL_ERR(mld, "NOT SUPPORTED: ROC on vif->type %d\n",
-			vif->type);
-
-		return -EOPNOTSUPP;
-	}
-
-	switch (type) {
-	case IEEE80211_ROC_TYPE_NORMAL:
-		activity = ROC_ACTIVITY_P2P_DISC;
-		break;
-	case IEEE80211_ROC_TYPE_MGMT_TX:
-		activity = ROC_ACTIVITY_P2P_NEG;
-		break;
-	default:
-		WARN_ONCE(1, "Got an invalid P2P ROC type\n");
-		return -EINVAL;
-	}
-
-	if (WARN_ON(mld_vif->roc_activity != ROC_NUM_ACTIVITIES))
-		return -EBUSY;
-
-	/* No MLO on P2P device */
-	aux_sta = &mld_vif->deflink.aux_sta;
-
-	ret = iwl_mld_add_aux_sta(mld, aux_sta);
-	if (ret)
-		return ret;
-
-	cmd.activity = cpu_to_le32(activity);
-	cmd.sta_id = cpu_to_le32(aux_sta->sta_id);
-	cmd.channel_info.channel = cpu_to_le32(channel->hw_value);
-	cmd.channel_info.band = iwl_mld_nl80211_band_to_fw(channel->band);
-	cmd.channel_info.width = IWL_PHY_CHANNEL_MODE20;
-	/* TODO: task=Hotspot 2.0, revisit those parameters when we add an ROC
-	 * on the BSS vif
-	 */
-	cmd.max_delay = cpu_to_le32(AUX_ROC_MAX_DELAY);
-	cmd.duration = cpu_to_le32(MSEC_TO_TU(duration));
-
-	memcpy(cmd.node_addr, vif->addr, ETH_ALEN);
-
-	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
-				   &cmd, cmd_len);
-	if (ret) {
-		IWL_ERR(mld, "Couldn't send the ROC_CMD\n");
-		return ret;
-	}
-	mld_vif->roc_activity = activity;
-
-	return 0;
-}
-
-static void
-iwl_mld_vif_iter_emlsr_unblock_roc(void *data, u8 *mac,
-				   struct ieee80211_vif *vif)
-{
-	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-
-	iwl_mld_unblock_emlsr(mld_vif->mld, vif, IWL_MLD_EMLSR_BLOCKED_ROC);
-}
-
-static void iwl_mld_destroy_roc(struct iwl_mld *mld,
-				struct ieee80211_vif *vif,
-				struct iwl_mld_vif *mld_vif)
-{
-	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
-
-	ieee80211_iterate_active_interfaces_mtx(mld->hw,
-						IEEE80211_IFACE_ITER_NORMAL,
-						iwl_mld_vif_iter_emlsr_unblock_roc,
-						NULL);
-
-	/* wait until every tx has seen that roc_activity has been reset */
-	synchronize_net();
-	/* from here, no new tx will be added
-	 * we can flush the Tx on the queues
-	 */
-
-	iwl_mld_flush_link_sta_txqs(mld, mld_vif->deflink.aux_sta.sta_id);
-
-	iwl_mld_remove_aux_sta(mld, vif, &vif->bss_conf);
-}
-
-int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
-		       struct ieee80211_vif *vif)
-{
-	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
-	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
-	struct iwl_roc_req cmd = {
-		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
-	};
-	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
-				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
-	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
-	int ret;
-
-	lockdep_assert_wiphy(mld->wiphy);
-
-	/* TODO: task=Hotspot 2.0 */
-	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
-		return -EOPNOTSUPP;
-
-	/* No roc activity running it's probably already done */
-	if (mld_vif->roc_activity == ROC_NUM_ACTIVITIES)
-		return 0;
-
-	cmd.activity = cpu_to_le32(mld_vif->roc_activity);
-
-	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
-				   &cmd, cmd_len);
-	if (ret)
-		IWL_ERR(mld, "Couldn't send the command to cancel the ROC\n");
-
-	/* We may have raced with the firmware expiring the ROC instance at
-	 * this very moment. In that case, we can have a notification in the
-	 * async processing queue. However, none can arrive _after_ this as
-	 * ROC_CMD was sent synchronously, i.e. we waited for a response and
-	 * the firmware cannot refer to this ROC after the response. Thus,
-	 * if we just cancel the notification (if there's one) we'll be at a
-	 * clean state for any possible next ROC.
-	 */
-	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_ROC,
-					       mld_vif->roc_activity);
-
-	iwl_mld_destroy_roc(mld, vif, mld_vif);
-
-	return 0;
-}
-
-void iwl_mld_handle_roc_notif(struct iwl_mld *mld,
-			      struct iwl_rx_packet *pkt)
-{
-	const struct iwl_roc_notif *notif = (void *)pkt->data;
-	u32 activity = le32_to_cpu(notif->activity);
-	/* TODO: task=Hotspot 2.0 - roc can run on BSS */
-	struct ieee80211_vif *vif = mld->p2p_device_vif;
-	struct iwl_mld_vif *mld_vif;
-
-	if (WARN_ON(!vif))
-		return;
-
-	mld_vif = iwl_mld_vif_from_mac80211(vif);
-	/* It is possible that the ROC was canceled
-	 * but the notification was already fired.
-	 */
-	if (mld_vif->roc_activity != activity)
-		return;
-
-	if (le32_to_cpu(notif->success) &&
-	    le32_to_cpu(notif->started)) {
-		/* We had a successful start */
-		ieee80211_ready_on_channel(mld->hw);
-	} else {
-		/* ROC was not successful, tell the firmware to remove it */
-		if (le32_to_cpu(notif->started))
-			iwl_mld_cancel_roc(mld->hw, vif);
-		else
-			iwl_mld_destroy_roc(mld, vif, mld_vif);
-		/* we need to let know mac80211 about end OR
-		 * an unsuccessful start
-		 */
-		ieee80211_remain_on_channel_expired(mld->hw);
-	}
-}

From c7c1f3b05c67173f462d73d301d572b3f9e57e3b Mon Sep 17 00:00:00 2001
From: Michal Pecio <michal.pecio@gmail.com>
Date: Tue, 4 Mar 2025 13:31:47 +0200
Subject: [PATCH 1505/2753] usb: xhci: Fix host controllers "dying" after
 suspend and resume

A recent cleanup went a bit too far and dropped clearing the cycle bit
of link TRBs, so it stays different from the rest of the ring half of
the time. Then a race occurs: if the xHC reaches such link TRB before
more commands are queued, the link's cycle bit unintentionally matches
the xHC's cycle so it follows the link and waits for further commands.
If more commands are queued before the xHC gets there, inc_enq() flips
the bit so the xHC later sees a mismatch and stops executing commands.

This function is called before suspend and 50% of times after resuming
the xHC is doomed to get stuck sooner or later. Then some Stop Endpoint
command fails to complete in 5 seconds and this shows up

xhci_hcd 0000:00:10.0: xHCI host not responding to stop endpoint command
xhci_hcd 0000:00:10.0: xHCI host controller not responding, assume dead
xhci_hcd 0000:00:10.0: HC died; cleaning up

followed by loss of all USB decives on the affected bus. That's if you
are lucky, because if Set Deq gets stuck instead, the failure is silent.

Likely responsible for kernel bug 219824. I found this while searching
for possible causes of that regression and reproduced it locally before
hearing back from the reporter. To repro, simply wait for link cycle to
become set (debugfs), then suspend, resume and wait. To accelerate the
failure I used a script which repeatedly starts and stops a UVC camera.

Some HCs get fully reinitialized on resume and they are not affected.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=219824
Fixes: 36b972d4b7ce ("usb: xhci: improve xhci_clear_command_ring()")
Cc: stable@vger.kernel.org
Signed-off-by: Michal Pecio <michal.pecio@gmail.com>
Signed-off-by: Mathias Nyman <mathias.nyman@linux.intel.com>
Link: https://lore.kernel.org/r/20250304113147.3322584-2-mathias.nyman@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/host/xhci.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 45653114ccd7f..1a90ebc8a30ea 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -780,8 +780,12 @@ static void xhci_clear_command_ring(struct xhci_hcd *xhci)
 	struct xhci_segment *seg;
 
 	ring = xhci->cmd_ring;
-	xhci_for_each_ring_seg(ring->first_seg, seg)
+	xhci_for_each_ring_seg(ring->first_seg, seg) {
+		/* erase all TRBs before the link */
 		memset(seg->trbs, 0, sizeof(union xhci_trb) * (TRBS_PER_SEGMENT - 1));
+		/* clear link cycle bit */
+		seg->trbs[TRBS_PER_SEGMENT - 1].link.control &= cpu_to_le32(~TRB_CYCLE);
+	}
 
 	xhci_initialize_ring_info(ring);
 	/*

From 8a683295c2264e66cd8522ab6a15edfb52aa20bc Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:17 -0800
Subject: [PATCH 1506/2753] netconsole: prefix CPU_NR sysdata feature with
 SYSDATA_

Rename the CPU_NR enum value to SYSDATA_CPU_NR to establish a consistent
naming convention for sysdata features. This change prepares for
upcoming additions to the sysdata feature set by clearly grouping
related features under the SYSDATA prefix.

This change is purely cosmetic and does not modify any functionality.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index f77eddf221850..c086e2fe51f87 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -103,7 +103,7 @@ struct netconsole_target_stats  {
  */
 enum sysdata_feature {
 	/* Populate the CPU that sends the message */
-	CPU_NR = BIT(0),
+	SYSDATA_CPU_NR = BIT(0),
 };
 
 /**
@@ -418,7 +418,7 @@ static ssize_t sysdata_cpu_nr_enabled_show(struct config_item *item, char *buf)
 	bool cpu_nr_enabled;
 
 	mutex_lock(&dynamic_netconsole_mutex);
-	cpu_nr_enabled = !!(nt->sysdata_fields & CPU_NR);
+	cpu_nr_enabled = !!(nt->sysdata_fields & SYSDATA_CPU_NR);
 	mutex_unlock(&dynamic_netconsole_mutex);
 
 	return sysfs_emit(buf, "%d\n", cpu_nr_enabled);
@@ -699,7 +699,7 @@ static size_t count_extradata_entries(struct netconsole_target *nt)
 	/* Userdata entries */
 	entries = list_count_nodes(&nt->userdata_group.cg_children);
 	/* Plus sysdata entries */
-	if (nt->sysdata_fields & CPU_NR)
+	if (nt->sysdata_fields & SYSDATA_CPU_NR)
 		entries += 1;
 
 	return entries;
@@ -850,7 +850,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 		return ret;
 
 	mutex_lock(&dynamic_netconsole_mutex);
-	curr = nt->sysdata_fields & CPU_NR;
+	curr = nt->sysdata_fields & SYSDATA_CPU_NR;
 	if (cpu_nr_enabled == curr)
 		/* no change requested */
 		goto unlock_ok;
@@ -865,13 +865,13 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 	}
 
 	if (cpu_nr_enabled)
-		nt->sysdata_fields |= CPU_NR;
+		nt->sysdata_fields |= SYSDATA_CPU_NR;
 	else
 		/* This is special because extradata_complete might have
 		 * remaining data from previous sysdata, and it needs to be
 		 * cleaned.
 		 */
-		disable_sysdata_feature(nt, CPU_NR);
+		disable_sysdata_feature(nt, SYSDATA_CPU_NR);
 
 unlock_ok:
 	ret = strnlen(buf, count);
@@ -1130,7 +1130,7 @@ static int prepare_extradata(struct netconsole_target *nt)
 	 */
 	extradata_len = nt->userdata_length;
 
-	if (!(nt->sysdata_fields & CPU_NR))
+	if (!(nt->sysdata_fields & SYSDATA_CPU_NR))
 		goto out;
 
 	/* Append cpu=%d at extradata_complete after userdata str */

From efb878fbe8d1fae3bf1974628e6d267dc861207e Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:18 -0800
Subject: [PATCH 1507/2753] netconsole: Make boolean comparison consistent

Convert the current state assignment to use explicit boolean conversion,
making the code more robust and easier to read. This change adds a
double-negation operator to ensure consistent boolean conversion as
suggested by Paolo[1].

This approach aligns with the existing pattern used in
sysdata_cpu_nr_enabled_show().

Link: https://lore.kernel.org/all/7309e760-63b0-4b58-ad33-2fb8db361141@redhat.com/ [1]
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index c086e2fe51f87..698dbbea2713f 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -850,7 +850,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 		return ret;
 
 	mutex_lock(&dynamic_netconsole_mutex);
-	curr = nt->sysdata_fields & SYSDATA_CPU_NR;
+	curr = !!(nt->sysdata_fields & SYSDATA_CPU_NR);
 	if (cpu_nr_enabled == curr)
 		/* no change requested */
 		goto unlock_ok;

From 4d989521a93bcabce7c18060d5cf98a207d56cbe Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:19 -0800
Subject: [PATCH 1508/2753] netconsole: refactor CPU number formatting into
 separate function

Extract CPU number formatting logic from prepare_extradata() into a new
append_cpu_nr() function.

This refactoring improves code organization by isolating CPU number
formatting into its own function while reducing the complexity of
prepare_extradata().

The change prepares the codebase for the upcoming taskname feature by
establishing a consistent pattern for handling sysdata features.

The CPU number formatting logic itself remains unchanged; only its
location has moved to improve maintainability.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 18 +++++++++++-------
 1 file changed, 11 insertions(+), 7 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 698dbbea2713f..96153fd01f46e 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1117,13 +1117,21 @@ static void populate_configfs_item(struct netconsole_target *nt,
 	init_target_config_group(nt, target_name);
 }
 
+static int append_cpu_nr(struct netconsole_target *nt, int offset)
+{
+	/* Append cpu=%d at extradata_complete after userdata str */
+	return scnprintf(&nt->extradata_complete[offset],
+			 MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n",
+			 raw_smp_processor_id());
+}
+
 /*
  * prepare_extradata - append sysdata at extradata_complete in runtime
  * @nt: target to send message to
  */
 static int prepare_extradata(struct netconsole_target *nt)
 {
-	int sysdata_len, extradata_len;
+	int extradata_len;
 
 	/* userdata was appended when configfs write helper was called
 	 * by update_userdata().
@@ -1133,12 +1141,8 @@ static int prepare_extradata(struct netconsole_target *nt)
 	if (!(nt->sysdata_fields & SYSDATA_CPU_NR))
 		goto out;
 
-	/* Append cpu=%d at extradata_complete after userdata str */
-	sysdata_len = scnprintf(&nt->extradata_complete[nt->userdata_length],
-				MAX_EXTRADATA_ENTRY_LEN, " cpu=%u\n",
-				raw_smp_processor_id());
-
-	extradata_len += sysdata_len;
+	if (nt->sysdata_fields & SYSDATA_CPU_NR)
+		extradata_len += append_cpu_nr(nt, extradata_len);
 
 	WARN_ON_ONCE(extradata_len >
 		     MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS);

From 33e4b29f2b3b7d013629bb86abe5cb726ec91199 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:20 -0800
Subject: [PATCH 1509/2753] netconsole: add taskname to extradata entry count

New SYSDATA_TASKNAME feature flag to track when taskname append is enabled.

Additional check in count_extradata_entries() to include taskname in
total, counting it as an entry in extradata. This function is used to
check if we are not overflowing the number of extradata items.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 96153fd01f46e..f46a0edf9c11e 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -104,6 +104,8 @@ struct netconsole_target_stats  {
 enum sysdata_feature {
 	/* Populate the CPU that sends the message */
 	SYSDATA_CPU_NR = BIT(0),
+	/* Populate the task name (as in current->comm) in sysdata */
+	SYSDATA_TASKNAME = BIT(1),
 };
 
 /**
@@ -701,6 +703,8 @@ static size_t count_extradata_entries(struct netconsole_target *nt)
 	/* Plus sysdata entries */
 	if (nt->sysdata_fields & SYSDATA_CPU_NR)
 		entries += 1;
+	if (nt->sysdata_fields & SYSDATA_TASKNAME)
+		entries += 1;
 
 	return entries;
 }

From 09e877590bc28ae897b10f6b1becc29786fe1bd4 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:21 -0800
Subject: [PATCH 1510/2753] netconsole: add configfs controls for taskname
 sysdata feature

Add configfs interface to enable/disable the taskname sysdata feature.
This adds the following functionality:

The implementation follows the same pattern as the existing CPU number
feature, ensuring consistent behavior and error handling across sysdata
features.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 50 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index f46a0edf9c11e..9798b2b409e26 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -426,6 +426,20 @@ static ssize_t sysdata_cpu_nr_enabled_show(struct config_item *item, char *buf)
 	return sysfs_emit(buf, "%d\n", cpu_nr_enabled);
 }
 
+/* configfs helper to display if taskname sysdata feature is enabled */
+static ssize_t sysdata_taskname_enabled_show(struct config_item *item,
+					     char *buf)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool taskname_enabled;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	taskname_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME);
+	mutex_unlock(&dynamic_netconsole_mutex);
+
+	return sysfs_emit(buf, "%d\n", taskname_enabled);
+}
+
 /*
  * This one is special -- targets created through the configfs interface
  * are not enabled (and the corresponding netpoll activated) by default.
@@ -841,6 +855,40 @@ static void disable_sysdata_feature(struct netconsole_target *nt,
 	nt->extradata_complete[nt->userdata_length] = 0;
 }
 
+static ssize_t sysdata_taskname_enabled_store(struct config_item *item,
+					      const char *buf, size_t count)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool taskname_enabled, curr;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &taskname_enabled);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	curr = !!(nt->sysdata_fields & SYSDATA_TASKNAME);
+	if (taskname_enabled == curr)
+		goto unlock_ok;
+
+	if (taskname_enabled &&
+	    count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) {
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	if (taskname_enabled)
+		nt->sysdata_fields |= SYSDATA_TASKNAME;
+	else
+		disable_sysdata_feature(nt, SYSDATA_TASKNAME);
+
+unlock_ok:
+	ret = strnlen(buf, count);
+unlock:
+	mutex_unlock(&dynamic_netconsole_mutex);
+	return ret;
+}
+
 /* configfs helper to sysdata cpu_nr feature */
 static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 					    const char *buf, size_t count)
@@ -886,6 +934,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 
 CONFIGFS_ATTR(userdatum_, value);
 CONFIGFS_ATTR(sysdata_, cpu_nr_enabled);
+CONFIGFS_ATTR(sysdata_, taskname_enabled);
 
 static struct configfs_attribute *userdatum_attrs[] = {
 	&userdatum_attr_value,
@@ -946,6 +995,7 @@ static void userdatum_drop(struct config_group *group, struct config_item *item)
 
 static struct configfs_attribute *userdata_attrs[] = {
 	&sysdata_attr_cpu_nr_enabled,
+	&sysdata_attr_taskname_enabled,
 	NULL,
 };
 

From dd30ae533242495a724b37066cae1fb03ee6b601 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:22 -0800
Subject: [PATCH 1511/2753] netconsole: add task name to extra data fields

This is the core patch for this whole patchset. Add support for
including the current task's name in netconsole's extra data output.
This adds a new append_taskname() function that writes the task name
(from current->comm) into the target's extradata buffer, similar to how
CPU numbers are handled.

The task name is included when the SYSDATA_TASKNAME field is set,
appearing in the format "taskname=<name>" in the output. This additional
context can help with debugging by showing which task generated each
console message.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 9798b2b409e26..098ea9eb02373 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1179,12 +1179,19 @@ static int append_cpu_nr(struct netconsole_target *nt, int offset)
 			 raw_smp_processor_id());
 }
 
+static int append_taskname(struct netconsole_target *nt, int offset)
+{
+	return scnprintf(&nt->extradata_complete[offset],
+			 MAX_EXTRADATA_ENTRY_LEN, " taskname=%s\n",
+			 current->comm);
+}
 /*
  * prepare_extradata - append sysdata at extradata_complete in runtime
  * @nt: target to send message to
  */
 static int prepare_extradata(struct netconsole_target *nt)
 {
+	u32 fields = SYSDATA_CPU_NR | SYSDATA_TASKNAME;
 	int extradata_len;
 
 	/* userdata was appended when configfs write helper was called
@@ -1192,11 +1199,13 @@ static int prepare_extradata(struct netconsole_target *nt)
 	 */
 	extradata_len = nt->userdata_length;
 
-	if (!(nt->sysdata_fields & SYSDATA_CPU_NR))
+	if (!(nt->sysdata_fields & fields))
 		goto out;
 
 	if (nt->sysdata_fields & SYSDATA_CPU_NR)
 		extradata_len += append_cpu_nr(nt, extradata_len);
+	if (nt->sysdata_fields & SYSDATA_TASKNAME)
+		extradata_len += append_taskname(nt, extradata_len);
 
 	WARN_ON_ONCE(extradata_len >
 		     MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS);

From 7010b619830f639bdb930ed1da3766fbb379d5dc Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:23 -0800
Subject: [PATCH 1512/2753] netconsole: docs: document the task name feature

Add documentation for the netconsole task name feature in
Documentation/networking/netconsole.rst. This explains how to enable
task name via configfs and demonstrates the output format.

The documentation includes:
- How to enable/disable the feature via taskname_enabled
- The format of the task name in the output
- An example showing the task name appearing in messages

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/netconsole.rst | 28 +++++++++++++++++++++++++
 1 file changed, 28 insertions(+)

diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
index 84803c59968a3..ae82a6337a8d8 100644
--- a/Documentation/networking/netconsole.rst
+++ b/Documentation/networking/netconsole.rst
@@ -240,6 +240,34 @@ Delete `userdata` entries with `rmdir`::
 
    It is recommended to not write user data values with newlines.
 
+Task name auto population in userdata
+-------------------------------------
+
+Inside the netconsole configfs hierarchy, there is a file called
+`taskname_enabled` under the `userdata` directory. This file is used to enable
+or disable the automatic task name population feature. This feature
+automatically populates the current task name that is scheduled in the CPU
+sneding the message.
+
+To enable task name auto-population::
+
+  echo 1 > /sys/kernel/config/netconsole/target1/userdata/taskname_enabled
+
+When this option is enabled, the netconsole messages will include an additional
+line in the userdata field with the format `taskname=<task name>`. This allows
+the receiver of the netconsole messages to easily find which application was
+currently scheduled when that message was generated, providing extra context
+for kernel messages and helping to categorize them.
+
+Example::
+
+  echo "This is a message" > /dev/kmsg
+  12,607,22085407756,-;This is a message
+   taskname=echo
+
+In this example, the message was generated while "echo" was the current
+scheduled process.
+
 CPU number auto population in userdata
 --------------------------------------
 

From d7a2522426e86036f40fde6ba055aa20de1f3d8a Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 28 Feb 2025 04:50:24 -0800
Subject: [PATCH 1513/2753] netconsole: selftest: add task name append testing

Add test coverage for the netconsole task name feature to the existing
sysdata selftest script. This extends the test infrastructure to verify
that task names are correctly appended when enabled and absent when
disabled.

The test validates that:
  - Task names appear in the expected format "taskname=<name>"
  - Task names are included when the feature is enabled
  - Task names are excluded when the feature is disabled
  - The feature works correctly alongside other sysdata fields like CPU

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/drivers/net/netcons_sysdata.sh  | 51 ++++++++++++++++---
 1 file changed, 44 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
index 2b78fd1f5982f..f351206ed1bda 100755
--- a/tools/testing/selftests/drivers/net/netcons_sysdata.sh
+++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
@@ -31,17 +31,38 @@ function set_cpu_nr() {
 	echo 1 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
 }
 
+# Enable the taskname to be appended to sysdata
+function set_taskname() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/taskname_enabled" ]]
+	then
+		echo "Not able to enable taskname sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/taskname_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/taskname_enabled"
+}
+
 # Disable the sysdata cpu_nr feature
 function unset_cpu_nr() {
 	echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
 }
 
-# Test if MSG content and `cpu=${CPU}` exists in OUTPUT_FILE
-function validate_sysdata_cpu_exists() {
+# Once called, taskname=<..> will not be appended anymore
+function unset_taskname() {
+	echo 0 > "${NETCONS_PATH}/userdata/taskname_enabled"
+}
+
+# Test if MSG contains sysdata
+function validate_sysdata() {
 	# OUTPUT_FILE will contain something like:
 	# 6.11.1-0_fbk0_rc13_509_g30d75cea12f7,13,1822,115075213798,-;netconsole selftest: netcons_gtJHM
 	#  userdatakey=userdatavalue
 	#  cpu=X
+	#  taskname=<taskname>
+
+	# Echo is what this test uses to create the message. See runtest()
+	# function
+	SENDER="echo"
 
 	if [ ! -f "$OUTPUT_FILE" ]; then
 		echo "FAIL: File was not generated." >&2
@@ -62,12 +83,19 @@ function validate_sysdata_cpu_exists() {
 		exit "${ksft_fail}"
 	fi
 
+	if ! grep -q "taskname=${SENDER}" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'taskname=echo' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
 	rm "${OUTPUT_FILE}"
 	pkill_socat
 }
 
-# Test if MSG content exists in OUTPUT_FILE but no `cpu=` string
-function validate_sysdata_no_cpu() {
+# Test if MSG content exists in OUTPUT_FILE but no `cpu=` and `taskname=`
+# strings
+function validate_no_sysdata() {
 	if [ ! -f "$OUTPUT_FILE" ]; then
 		echo "FAIL: File was not generated." >&2
 		exit "${ksft_fail}"
@@ -85,6 +113,12 @@ function validate_sysdata_no_cpu() {
 		exit "${ksft_fail}"
 	fi
 
+	if grep -q "taskname=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'taskname=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
 	rm "${OUTPUT_FILE}"
 }
 
@@ -133,10 +167,12 @@ OUTPUT_FILE="/tmp/${TARGET}_1"
 MSG="Test #1 from CPU${CPU}"
 # Enable the auto population of cpu_nr
 set_cpu_nr
+# Enable taskname to be appended to sysdata
+set_taskname
 runtest
 # Make sure the message was received in the dst part
 # and exit
-validate_sysdata_cpu_exists
+validate_sysdata
 
 #====================================================
 # TEST #2
@@ -148,7 +184,7 @@ OUTPUT_FILE="/tmp/${TARGET}_2"
 MSG="Test #2 from CPU${CPU}"
 set_user_data
 runtest
-validate_sysdata_cpu_exists
+validate_sysdata
 
 # ===================================================
 # TEST #3
@@ -160,8 +196,9 @@ OUTPUT_FILE="/tmp/${TARGET}_3"
 MSG="Test #3 from CPU${CPU}"
 # Enable the auto population of cpu_nr
 unset_cpu_nr
+unset_taskname
 runtest
 # At this time, cpu= shouldn't be present in the msg
-validate_sysdata_no_cpu
+validate_no_sysdata
 
 exit "${ksft_pass}"

From 164b7dd4546b57c08b373e9e3cf315ff98cb032d Mon Sep 17 00:00:00 2001
From: Maciej Strozek <mstrozek@opensource.cirrus.com>
Date: Tue, 4 Mar 2025 14:05:04 +0000
Subject: [PATCH 1514/2753] ASoC: cs42l43: Add jack delay debounce after
 suspend

Hardware reports jack absent after reset/suspension regardless of jack
state, so introduce an additional delay only in suspension case to allow
proper detection to take place after a short delay.

Signed-off-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250304140504.139245-1-mstrozek@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43-jack.c | 13 ++++++++++---
 sound/soc/codecs/cs42l43.c      | 15 ++++++++++++++-
 sound/soc/codecs/cs42l43.h      |  3 +++
 3 files changed, 27 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/cs42l43-jack.c b/sound/soc/codecs/cs42l43-jack.c
index d9ab003e166bf..ac19a572fe70c 100644
--- a/sound/soc/codecs/cs42l43-jack.c
+++ b/sound/soc/codecs/cs42l43-jack.c
@@ -167,7 +167,7 @@ int cs42l43_set_jack(struct snd_soc_component *component,
 		autocontrol |= 0x3 << CS42L43_JACKDET_MODE_SHIFT;
 
 	ret = cs42l43_find_index(priv, "cirrus,tip-fall-db-ms", 500,
-				 NULL, cs42l43_accdet_db_ms,
+				 &priv->tip_fall_db_ms, cs42l43_accdet_db_ms,
 				 ARRAY_SIZE(cs42l43_accdet_db_ms));
 	if (ret < 0)
 		goto error;
@@ -175,7 +175,7 @@ int cs42l43_set_jack(struct snd_soc_component *component,
 	tip_deb |= ret << CS42L43_TIPSENSE_FALLING_DB_TIME_SHIFT;
 
 	ret = cs42l43_find_index(priv, "cirrus,tip-rise-db-ms", 500,
-				 NULL, cs42l43_accdet_db_ms,
+				 &priv->tip_rise_db_ms, cs42l43_accdet_db_ms,
 				 ARRAY_SIZE(cs42l43_accdet_db_ms));
 	if (ret < 0)
 		goto error;
@@ -764,6 +764,8 @@ void cs42l43_tip_sense_work(struct work_struct *work)
 error:
 	mutex_unlock(&priv->jack_lock);
 
+	priv->suspend_jack_debounce = false;
+
 	pm_runtime_mark_last_busy(priv->dev);
 	pm_runtime_put_autosuspend(priv->dev);
 }
@@ -771,14 +773,19 @@ void cs42l43_tip_sense_work(struct work_struct *work)
 irqreturn_t cs42l43_tip_sense(int irq, void *data)
 {
 	struct cs42l43_codec *priv = data;
+	unsigned int db_delay = priv->tip_debounce_ms;
 
 	cancel_delayed_work(&priv->bias_sense_timeout);
 	cancel_delayed_work(&priv->tip_sense_work);
 	cancel_delayed_work(&priv->button_press_work);
 	cancel_work(&priv->button_release_work);
 
+	// Ensure delay after suspend is long enough to avoid false detection
+	if (priv->suspend_jack_debounce)
+		db_delay += priv->tip_fall_db_ms + priv->tip_rise_db_ms;
+
 	queue_delayed_work(system_long_wq, &priv->tip_sense_work,
-			   msecs_to_jiffies(priv->tip_debounce_ms));
+			   msecs_to_jiffies(db_delay));
 
 	return IRQ_HANDLED;
 }
diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index d2a2daefc2ec6..4257dbefe9dd1 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2402,9 +2402,22 @@ static int cs42l43_codec_runtime_resume(struct device *dev)
 	return 0;
 }
 
+static int cs42l43_codec_runtime_force_suspend(struct device *dev)
+{
+	struct cs42l43_codec *priv = dev_get_drvdata(dev);
+
+	dev_dbg(priv->dev, "Runtime suspend\n");
+
+	priv->suspend_jack_debounce = true;
+
+	pm_runtime_force_suspend(dev);
+
+	return 0;
+}
+
 static const struct dev_pm_ops cs42l43_codec_pm_ops = {
 	RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(pm_runtime_force_suspend, pm_runtime_force_resume)
+	SET_SYSTEM_SLEEP_PM_OPS(cs42l43_codec_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 static const struct platform_device_id cs42l43_codec_id_table[] = {
diff --git a/sound/soc/codecs/cs42l43.h b/sound/soc/codecs/cs42l43.h
index 9c144e129535f..1cd9d8a71c439 100644
--- a/sound/soc/codecs/cs42l43.h
+++ b/sound/soc/codecs/cs42l43.h
@@ -78,6 +78,8 @@ struct cs42l43_codec {
 
 	bool use_ring_sense;
 	unsigned int tip_debounce_ms;
+	unsigned int tip_fall_db_ms;
+	unsigned int tip_rise_db_ms;
 	unsigned int bias_low;
 	unsigned int bias_sense_ua;
 	unsigned int bias_ramp_ms;
@@ -95,6 +97,7 @@ struct cs42l43_codec {
 	bool button_detect_running;
 	bool jack_present;
 	int jack_override;
+	bool suspend_jack_debounce;
 
 	struct work_struct hp_ilimit_work;
 	struct delayed_work hp_ilimit_clear_work;

From d0bbe332669c5db32c8c92bc967f8e7f8d460ddf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 4 Mar 2025 15:25:55 +0100
Subject: [PATCH 1515/2753] ALSA: hda: realtek: fix incorrect IS_REACHABLE()
 usage

The alternative path leads to a build error after a recent change:

sound/pci/hda/patch_realtek.c: In function 'alc233_fixup_lenovo_low_en_micmute_led':
include/linux/stddef.h:9:14: error: called object is not a function or function pointer
    9 | #define NULL ((void *)0)
      |              ^
sound/pci/hda/patch_realtek.c:5041:49: note: in expansion of macro 'NULL'
 5041 | #define alc233_fixup_lenovo_line2_mic_hotkey    NULL
      |                                                 ^~~~
sound/pci/hda/patch_realtek.c:5063:9: note: in expansion of macro 'alc233_fixup_lenovo_line2_mic_hotkey'
 5063 |         alc233_fixup_lenovo_line2_mic_hotkey(codec, fix, action);

Using IS_REACHABLE() is somewhat questionable here anyway since it
leads to the input code not working when the HDA driver is builtin
but input is in a loadable module. Replace this with a hard compile-time
dependency on CONFIG_INPUT. In practice this won't chance much
other than solve the compiler error because it is rare to require
sound output but no input support.

Fixes: f603b159231b ("ALSA: hda/realtek - add supported Mic Mute LED for Lenovo platform")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://patch.msgid.link/20250304142620.582191-1-arnd@kernel.org
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/Kconfig         | 1 +
 sound/pci/hda/patch_realtek.c | 5 -----
 2 files changed, 1 insertion(+), 5 deletions(-)

diff --git a/sound/pci/hda/Kconfig b/sound/pci/hda/Kconfig
index e393578cbe684..84ebf19f28836 100644
--- a/sound/pci/hda/Kconfig
+++ b/sound/pci/hda/Kconfig
@@ -222,6 +222,7 @@ comment "Set to Y if you want auto-loading the side codec driver"
 
 config SND_HDA_CODEC_REALTEK
 	tristate "Build Realtek HD-audio codec support"
+	depends on INPUT
 	select SND_HDA_GENERIC
 	select SND_HDA_GENERIC_LEDS
 	select SND_HDA_SCODEC_COMPONENT
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index ebf54ef5877a4..697a38e41e166 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4927,7 +4927,6 @@ static void alc298_fixup_samsung_amp_v2_4_amps(struct hda_codec *codec,
 		alc298_samsung_v2_init_amps(codec, 4);
 }
 
-#if IS_REACHABLE(CONFIG_INPUT)
 static void gpio2_mic_hotkey_event(struct hda_codec *codec,
 				   struct hda_jack_callback *event)
 {
@@ -5036,10 +5035,6 @@ static void alc233_fixup_lenovo_line2_mic_hotkey(struct hda_codec *codec,
 		spec->kb_dev = NULL;
 	}
 }
-#else /* INPUT */
-#define alc280_fixup_hp_gpio2_mic_hotkey	NULL
-#define alc233_fixup_lenovo_line2_mic_hotkey	NULL
-#endif /* INPUT */
 
 static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)

From 5623bc23a1cb9f9a9470fa73b3a20321dc4c4870 Mon Sep 17 00:00:00 2001
From: Heiko Carstens <hca@linux.ibm.com>
Date: Tue, 25 Feb 2025 10:53:10 +0100
Subject: [PATCH 1516/2753] s390/traps: Fix test_monitor_call() inline assembly

The test_monitor_call() inline assembly uses the xgr instruction, which
also modifies the condition code, to clear a register. However the clobber
list of the inline assembly does not specify that the condition code is
modified, which may lead to incorrect code generation.

Use the lhi instruction instead to clear the register without that the
condition code is modified. Furthermore this limits clearing to the lower
32 bits of val, since its type is int.

Fixes: 17248ea03674 ("s390: fix __EMIT_BUG() macro")
Cc: stable@vger.kernel.org
Reviewed-by: Juergen Christ <jchrist@linux.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/traps.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/arch/s390/kernel/traps.c b/arch/s390/kernel/traps.c
index 24fee11b030d8..b746213d3110c 100644
--- a/arch/s390/kernel/traps.c
+++ b/arch/s390/kernel/traps.c
@@ -285,10 +285,10 @@ static void __init test_monitor_call(void)
 		return;
 	asm volatile(
 		"	mc	0,0\n"
-		"0:	xgr	%0,%0\n"
+		"0:	lhi	%[val],0\n"
 		"1:\n"
-		EX_TABLE(0b,1b)
-		: "+d" (val));
+		EX_TABLE(0b, 1b)
+		: [val] "+d" (val));
 	if (!val)
 		panic("Monitor call doesn't work!\n");
 }

From a22ee38d2efe18edc53791fd1036396c23b43ad0 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 14:04:18 +0100
Subject: [PATCH 1517/2753] selftests/vDSO: Fix GNU hash table entry size for
 s390x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 14be4e6f3522 ("selftests: vDSO: fix ELF hash table entry size for s390x")
changed the type of the ELF hash table entries to 64bit on s390x.
However the *GNU* hash tables entries are always 32bit.
The "bucket" pointer is shared between both hash algorithms.
On s390, this caused the GNU hash algorithm to access its 32-bit entries as if they
were 64-bit, triggering compiler warnings (assignment between "Elf64_Xword *" and
"Elf64_Word *") and runtime crashes.

Introduce a new dedicated "gnu_bucket" pointer which is used by the GNU hash.

Fixes: e0746bde6f82 ("selftests/vDSO: support DT_GNU_HASH")
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Acked-by: Shuah Khan <skhan@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250217-selftests-vdso-s390-gnu-hash-v2-1-f6c2532ffe2a@linutronix.de
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 tools/testing/selftests/vDSO/parse_vdso.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/vDSO/parse_vdso.c b/tools/testing/selftests/vDSO/parse_vdso.c
index 2fe5e983cb22f..f89d052c730eb 100644
--- a/tools/testing/selftests/vDSO/parse_vdso.c
+++ b/tools/testing/selftests/vDSO/parse_vdso.c
@@ -53,7 +53,7 @@ static struct vdso_info
 	/* Symbol table */
 	ELF(Sym) *symtab;
 	const char *symstrings;
-	ELF(Word) *gnu_hash;
+	ELF(Word) *gnu_hash, *gnu_bucket;
 	ELF_HASH_ENTRY *bucket, *chain;
 	ELF_HASH_ENTRY nbucket, nchain;
 
@@ -185,8 +185,8 @@ void vdso_init_from_sysinfo_ehdr(uintptr_t base)
 		/* The bucket array is located after the header (4 uint32) and the bloom
 		 * filter (size_t array of gnu_hash[2] elements).
 		 */
-		vdso_info.bucket = vdso_info.gnu_hash + 4 +
-				   sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
+		vdso_info.gnu_bucket = vdso_info.gnu_hash + 4 +
+				       sizeof(size_t) / 4 * vdso_info.gnu_hash[2];
 	} else {
 		vdso_info.nbucket = hash[0];
 		vdso_info.nchain = hash[1];
@@ -268,11 +268,11 @@ void *vdso_sym(const char *version, const char *name)
 	if (vdso_info.gnu_hash) {
 		uint32_t h1 = gnu_hash(name), h2, *hashval;
 
-		i = vdso_info.bucket[h1 % vdso_info.nbucket];
+		i = vdso_info.gnu_bucket[h1 % vdso_info.nbucket];
 		if (i == 0)
 			return 0;
 		h1 |= 1;
-		hashval = vdso_info.bucket + vdso_info.nbucket +
+		hashval = vdso_info.gnu_bucket + vdso_info.nbucket +
 			  (i - vdso_info.gnu_hash[1]);
 		for (;; i++) {
 			ELF(Sym) *sym = &vdso_info.symtab[i];

From b4a1dec11793936ffe1a9fb811724532ff3b1174 Mon Sep 17 00:00:00 2001
From: Sumanth Korikkar <sumanthk@linux.ibm.com>
Date: Mon, 24 Feb 2025 12:27:04 +0100
Subject: [PATCH 1518/2753] s390/ftrace: Fix return address recovery of traced
 function

When fgraph is enabled the traced function return address is replaced with
trampoline return_to_handler(). The original return address of the traced
function is saved in per task return stack along with a stack pointer for
reliable stack unwinding via function_graph_enter_regs().

During stack unwinding e.g. for livepatching, ftrace_graph_ret_addr()
identifies the original return address of the traced function with the
saved stack pointer.

With a recent change, the stack pointers passed to ftrace_graph_ret_addr()
and function_graph_enter_regs() do not match anymore, and therefore the
original return address is not found.

Pass the correct stack pointer to function_graph_enter_regs() to fix this.

Fixes: 7495e179b478 ("s390/tracing: Enable HAVE_FTRACE_GRAPH_FUNC")
Reviewed-by: Heiko Carstens <hca@linux.ibm.com>
Signed-off-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
---
 arch/s390/kernel/ftrace.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
index 63ba6306632ef..e540b022ceb23 100644
--- a/arch/s390/kernel/ftrace.c
+++ b/arch/s390/kernel/ftrace.c
@@ -266,12 +266,13 @@ void ftrace_graph_func(unsigned long ip, unsigned long parent_ip,
 		       struct ftrace_ops *op, struct ftrace_regs *fregs)
 {
 	unsigned long *parent = &arch_ftrace_regs(fregs)->regs.gprs[14];
+	unsigned long sp = arch_ftrace_regs(fregs)->regs.gprs[15];
 
 	if (unlikely(ftrace_graph_is_dead()))
 		return;
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
-	if (!function_graph_enter_regs(*parent, ip, 0, parent, fregs))
+	if (!function_graph_enter_regs(*parent, ip, 0, (unsigned long *)sp, fregs))
 		*parent = (unsigned long)&return_to_handler;
 }
 

From f9dc8fb3afc968042bdaf4b6e445a9272071c9f3 Mon Sep 17 00:00:00 2001
From: Xiaoyao Li <xiaoyao.li@intel.com>
Date: Tue, 4 Mar 2025 03:23:14 -0500
Subject: [PATCH 1519/2753] KVM: x86: Explicitly zero EAX and EBX when
 PERFMON_V2 isn't supported by KVM

Fix a goof where KVM sets CPUID.0x80000022.EAX to CPUID.0x80000022.EBX
instead of zeroing both when PERFMON_V2 isn't supported by KVM.  In
practice, barring a buggy CPU (or vCPU model when running nested) only the
!enable_pmu case is affected, as KVM always supports PERFMON_V2 if it's
available in hardware, i.e. CPUID.0x80000022.EBX will be '0' if PERFMON_V2
is unsupported.

For the !enable_pmu case, the bug is relatively benign as KVM will refuse
to enable PMU capabilities, but a VMM that reflects KVM's supported CPUID
into the guest could inadvertently induce #GPs in the guest due to
advertising support for MSRs that KVM refuses to emulate.

Fixes: 94cdeebd8211 ("KVM: x86/cpuid: Add AMD CPUID ExtPerfMonAndDbg leaf 0x80000022")
Signed-off-by: Xiaoyao Li <xiaoyao.li@intel.com>
Link: https://lore.kernel.org/r/20250304082314.472202-3-xiaoyao.li@intel.com
[sean: massage shortlog and changelog, tag for stable]
Cc: stable@vger.kernel.org
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/cpuid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 8eb3a88707f21..121edf1f2a79a 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -1763,7 +1763,7 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 
 		entry->ecx = entry->edx = 0;
 		if (!enable_pmu || !kvm_cpu_cap_has(X86_FEATURE_PERFMON_V2)) {
-			entry->eax = entry->ebx;
+			entry->eax = entry->ebx = 0;
 			break;
 		}
 

From 3d252160b818045f3a152b13756f6f37ca34639d Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Tue, 4 Mar 2025 13:51:38 +0000
Subject: [PATCH 1520/2753] fs/pipe: Read pipe->{head,tail} atomically outside
 pipe->mutex

pipe_readable(), pipe_writable(), and pipe_poll() can read "pipe->head"
and "pipe->tail" outside of "pipe->mutex" critical section. When the
head and the tail are read individually in that order, there is a window
for interruption between the two reads in which both the head and the
tail can be updated by concurrent readers and writers.

One of the problematic scenarios observed with hackbench running
multiple groups on a large server on a particular pipe inode is as
follows:

    pipe->head = 36
    pipe->tail = 36

    hackbench-118762  [057] .....  1029.550548: pipe_write: *wakes up: pipe not full*
    hackbench-118762  [057] .....  1029.550548: pipe_write: head: 36 -> 37 [tail: 36]
    hackbench-118762  [057] .....  1029.550548: pipe_write: *wake up next reader 118740*
    hackbench-118762  [057] .....  1029.550548: pipe_write: *wake up next writer 118768*

    hackbench-118768  [206] .....  1029.55055X: pipe_write: *writer wakes up*
    hackbench-118768  [206] .....  1029.55055X: pipe_write: head = READ_ONCE(pipe->head) [37]
    ... CPU 206 interrupted (exact wakeup was not traced but 118768 did read head at 37 in traces)

    hackbench-118740  [057] .....  1029.550558: pipe_read:  *reader wakes up: pipe is not empty*
    hackbench-118740  [057] .....  1029.550558: pipe_read:  tail: 36 -> 37 [head = 37]
    hackbench-118740  [057] .....  1029.550559: pipe_read:  *pipe is empty; wakeup writer 118768*
    hackbench-118740  [057] .....  1029.550559: pipe_read:  *sleeps*

    hackbench-118766  [185] .....  1029.550592: pipe_write: *New writer comes in*
    hackbench-118766  [185] .....  1029.550592: pipe_write: head: 37 -> 38 [tail: 37]
    hackbench-118766  [185] .....  1029.550592: pipe_write: *wakes up reader 118766*

    hackbench-118740  [185] .....  1029.550598: pipe_read:  *reader wakes up; pipe not empty*
    hackbench-118740  [185] .....  1029.550599: pipe_read:  tail: 37 -> 38 [head: 38]
    hackbench-118740  [185] .....  1029.550599: pipe_read:  *pipe is empty*
    hackbench-118740  [185] .....  1029.550599: pipe_read:  *reader sleeps; wakeup writer 118768*

    ... CPU 206 switches back to writer
    hackbench-118768  [206] .....  1029.550601: pipe_write: tail = READ_ONCE(pipe->tail) [38]
    hackbench-118768  [206] .....  1029.550601: pipe_write: pipe_full()? (u32)(37 - 38) >= 16? Yes
    hackbench-118768  [206] .....  1029.550601: pipe_write: *writer goes back to sleep*

    [ Tasks 118740 and 118768 can then indefinitely wait on each other. ]

The unsigned arithmetic in pipe_occupancy() wraps around when
"pipe->tail > pipe->head" leading to pipe_full() returning true despite
the pipe being empty.

The case of genuine wraparound of "pipe->head" is handled since pipe
buffer has data allowing readers to make progress until the pipe->tail
wraps too after which the reader will wakeup a sleeping writer, however,
mistaking the pipe to be full when it is in fact empty can lead to
readers and writers waiting on each other indefinitely.

This issue became more problematic and surfaced as a hang in hackbench
after the optimization in commit aaec5a95d596 ("pipe_read: don't wake up
the writer if the pipe is still full") significantly reduced the number
of spurious wakeups of writers that had previously helped mask the
issue.

To avoid missing any updates between the reads of "pipe->head" and
"pipe->write", unionize the two with a single unsigned long
"pipe->head_tail" member that can be loaded atomically.

Using "pipe->head_tail" to read the head and the tail ensures the
lockless checks do not miss any updates to the head or the tail and
since those two are only updated under "pipe->mutex", it ensures that
the head is always ahead of, or equal to the tail resulting in correct
calculations.

  [ prateek: commit log, testing on x86 platforms. ]

Reported-and-debugged-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Closes: https://lore.kernel.org/lkml/e813814e-7094-4673-bc69-731af065a0eb@amd.com/
Reported-by: Alexey Gladkov <legion@kernel.org>
Closes: https://lore.kernel.org/all/Z8Wn0nTvevLRG_4m@example.org/
Fixes: 8cefc107ca54 ("pipe: Use head and tail pointers for the ring, not cursor and length")
Tested-by: Swapnil Sapkal <swapnil.sapkal@amd.com>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Tested-by: Alexey Gladkov <legion@kernel.org>
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/pipe.c                 | 19 ++++++++-----------
 include/linux/pipe_fs_i.h | 39 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 45 insertions(+), 13 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index ce1af7592780d..e8e6698f36981 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -210,11 +210,10 @@ static const struct pipe_buf_operations anon_pipe_buf_ops = {
 /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
 static inline bool pipe_readable(const struct pipe_inode_info *pipe)
 {
-	unsigned int head = READ_ONCE(pipe->head);
-	unsigned int tail = READ_ONCE(pipe->tail);
+	union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
 	unsigned int writers = READ_ONCE(pipe->writers);
 
-	return !pipe_empty(head, tail) || !writers;
+	return !pipe_empty(idx.head, idx.tail) || !writers;
 }
 
 static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe,
@@ -417,11 +416,10 @@ static inline int is_packetized(struct file *file)
 /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */
 static inline bool pipe_writable(const struct pipe_inode_info *pipe)
 {
-	unsigned int head = READ_ONCE(pipe->head);
-	unsigned int tail = READ_ONCE(pipe->tail);
+	union pipe_index idx = { .head_tail = READ_ONCE(pipe->head_tail) };
 	unsigned int max_usage = READ_ONCE(pipe->max_usage);
 
-	return !pipe_full(head, tail, max_usage) ||
+	return !pipe_full(idx.head, idx.tail, max_usage) ||
 		!READ_ONCE(pipe->readers);
 }
 
@@ -659,7 +657,7 @@ pipe_poll(struct file *filp, poll_table *wait)
 {
 	__poll_t mask;
 	struct pipe_inode_info *pipe = filp->private_data;
-	unsigned int head, tail;
+	union pipe_index idx;
 
 	/* Epoll has some historical nasty semantics, this enables them */
 	WRITE_ONCE(pipe->poll_usage, true);
@@ -680,19 +678,18 @@ pipe_poll(struct file *filp, poll_table *wait)
 	 * if something changes and you got it wrong, the poll
 	 * table entry will wake you up and fix it.
 	 */
-	head = READ_ONCE(pipe->head);
-	tail = READ_ONCE(pipe->tail);
+	idx.head_tail = READ_ONCE(pipe->head_tail);
 
 	mask = 0;
 	if (filp->f_mode & FMODE_READ) {
-		if (!pipe_empty(head, tail))
+		if (!pipe_empty(idx.head, idx.tail))
 			mask |= EPOLLIN | EPOLLRDNORM;
 		if (!pipe->writers && filp->f_pipe != pipe->w_counter)
 			mask |= EPOLLHUP;
 	}
 
 	if (filp->f_mode & FMODE_WRITE) {
-		if (!pipe_full(head, tail, pipe->max_usage))
+		if (!pipe_full(idx.head, idx.tail, pipe->max_usage))
 			mask |= EPOLLOUT | EPOLLWRNORM;
 		/*
 		 * Most Unices do not set EPOLLERR for FIFOs but on Linux they
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 8ff23bf5a8197..3cc4f8eab853f 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -31,6 +31,33 @@ struct pipe_buffer {
 	unsigned long private;
 };
 
+/*
+ * Really only alpha needs 32-bit fields, but
+ * might as well do it for 64-bit architectures
+ * since that's what we've historically done,
+ * and it makes 'head_tail' always be a simple
+ * 'unsigned long'.
+ */
+#ifdef CONFIG_64BIT
+typedef unsigned int pipe_index_t;
+#else
+typedef unsigned short pipe_index_t;
+#endif
+
+/*
+ * We have to declare this outside 'struct pipe_inode_info',
+ * but then we can't use 'union pipe_index' for an anonymous
+ * union, so we end up having to duplicate this declaration
+ * below. Annoying.
+ */
+union pipe_index {
+	unsigned long head_tail;
+	struct {
+		pipe_index_t head;
+		pipe_index_t tail;
+	};
+};
+
 /**
  *	struct pipe_inode_info - a linux kernel pipe
  *	@mutex: mutex protecting the whole thing
@@ -58,8 +85,16 @@ struct pipe_buffer {
 struct pipe_inode_info {
 	struct mutex mutex;
 	wait_queue_head_t rd_wait, wr_wait;
-	unsigned int head;
-	unsigned int tail;
+
+	/* This has to match the 'union pipe_index' above */
+	union {
+		unsigned long head_tail;
+		struct {
+			pipe_index_t head;
+			pipe_index_t tail;
+		};
+	};
+
 	unsigned int max_usage;
 	unsigned int ring_size;
 	unsigned int nr_accounted;

From dfc1b168a8c4b376fa222b27b97c2c4ad4b786e1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Wei=C3=9Fschuh?= <thomas.weissschuh@linutronix.de>
Date: Mon, 17 Feb 2025 08:27:54 +0100
Subject: [PATCH 1521/2753] kbuild: userprogs: use correct lld when linking
 through clang
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The userprog infrastructure links objects files through $(CC).
Either explicitly by manually calling $(CC) on multiple object files or
implicitly by directly compiling a source file to an executable.
The documentation at Documentation/kbuild/llvm.rst indicates that ld.lld
would be used for linking if LLVM=1 is specified.
However clang instead will use either a globally installed cross linker
from $PATH called ${target}-ld or fall back to the system linker, which
probably does not support crosslinking.
For the normal kernel build this is not an issue because the linker is
always executed directly, without the compiler being involved.

Explicitly pass --ld-path to clang so $(LD) is respected.
As clang 13.0.1 is required to build the kernel, this option is available.

Fixes: 7f3a59db274c ("kbuild: add infrastructure to build userspace programs")
Cc: stable@vger.kernel.org # needs wrapping in $(cc-option) for < 6.9
Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Makefile | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/Makefile b/Makefile
index 70bdbf2218fc5..6a8e5be6b0043 100644
--- a/Makefile
+++ b/Makefile
@@ -1123,6 +1123,11 @@ endif
 KBUILD_USERCFLAGS  += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 KBUILD_USERLDFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
+# userspace programs are linked via the compiler, use the correct linker
+ifeq ($(CONFIG_CC_IS_CLANG)$(CONFIG_LD_IS_LLD),yy)
+KBUILD_USERLDFLAGS += --ld-path=$(LD)
+endif
+
 # make the checker run with the right architecture
 CHECKFLAGS += --arch=$(ARCH)
 

From 02e9a22ceef0227175e391902d8760425fa072c6 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 25 Feb 2025 11:00:31 +0100
Subject: [PATCH 1522/2753] kbuild: hdrcheck: fix cross build with clang

The headercheck tries to call clang with a mix of compiler arguments
that don't include the target architecture. When building e.g. x86
headers on arm64, this produces a warning like

   clang: warning: unknown platform, assuming -mfloat-abi=soft

Add in the KBUILD_CPPFLAGS, which contain the target, in order to make it
build properly.

See also 1b71c2fb04e7 ("kbuild: userprogs: fix bitsize and target
detection on clang").

Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Fixes: feb843a469fb ("kbuild: add $(CLANG_FLAGS) to KBUILD_CPPFLAGS")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 usr/include/Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/usr/include/Makefile b/usr/include/Makefile
index 6c6de1b1622b1..e3d6b03527fec 100644
--- a/usr/include/Makefile
+++ b/usr/include/Makefile
@@ -10,7 +10,7 @@ UAPI_CFLAGS := -std=c90 -Wall -Werror=implicit-function-declaration
 
 # In theory, we do not care -m32 or -m64 for header compile tests.
 # It is here just because CONFIG_CC_CAN_LINK is tested with -m32 or -m64.
-UAPI_CFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CFLAGS))
+UAPI_CFLAGS += $(filter -m32 -m64 --target=%, $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS))
 
 # USERCFLAGS might contain sysroot location for CC.
 UAPI_CFLAGS += $(USERCFLAGS)

From dd0b7d4a56e3349de65bf9752734510fb55baf29 Mon Sep 17 00:00:00 2001
From: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Date: Fri, 28 Feb 2025 20:37:08 +0900
Subject: [PATCH 1523/2753] docs: Kconfig: fix defconfig description

Commit 2a86f6612164 ("kbuild: use KBUILD_DEFCONFIG as the fallback
for DEFCONFIG_LIST") removed arch/$ARCH/defconfig; however,
the document has not been updated to reflect this change yet.

Signed-off-by: Satoru Takeuchi <satoru.takeuchi@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 Documentation/admin-guide/README.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/README.rst b/Documentation/admin-guide/README.rst
index eb94526689091..b557cf1c820d2 100644
--- a/Documentation/admin-guide/README.rst
+++ b/Documentation/admin-guide/README.rst
@@ -176,7 +176,7 @@ Configuring the kernel
                         values without prompting.
 
      "make defconfig"   Create a ./.config file by using the default
-                        symbol values from either arch/$ARCH/defconfig
+                        symbol values from either arch/$ARCH/configs/defconfig
                         or arch/$ARCH/configs/${PLATFORM}_defconfig,
                         depending on the architecture.
 

From 30bfc151f0c1ec80c27a80a7651b2c15c648ad16 Mon Sep 17 00:00:00 2001
From: Maarten Lankhorst <dev@lankhorst.se>
Date: Tue, 10 Dec 2024 09:31:02 +0100
Subject: [PATCH 1524/2753] drm/xe: Remove double pageflip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This is already handled below in the code by fixup_initial_plane_config.

Fixes: a8153627520a ("drm/i915: Try to relocate the BIOS fb to the start of ggtt")
Cc: Ville Syrjälä <ville.syrjala@linux.intel.com>
Reviewed-by: Vinod Govindapillai <vinod.govindapillai@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20241210083111.230484-3-dev@lankhorst.se
Signed-off-by: Maarten Lankhorst <dev@lankhorst.se>
(cherry picked from commit 2218704997979fbf11765281ef752f07c5cf25bb)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/display/xe_plane_initial.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/gpu/drm/xe/display/xe_plane_initial.c b/drivers/gpu/drm/xe/display/xe_plane_initial.c
index 2eb9633f163a7..2a2f250fa495d 100644
--- a/drivers/gpu/drm/xe/display/xe_plane_initial.c
+++ b/drivers/gpu/drm/xe/display/xe_plane_initial.c
@@ -194,8 +194,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 		to_intel_plane(crtc->base.primary);
 	struct intel_plane_state *plane_state =
 		to_intel_plane_state(plane->base.state);
-	struct intel_crtc_state *crtc_state =
-		to_intel_crtc_state(crtc->base.state);
 	struct drm_framebuffer *fb;
 	struct i915_vma *vma;
 
@@ -241,14 +239,6 @@ intel_find_initial_plane_obj(struct intel_crtc *crtc,
 	atomic_or(plane->frontbuffer_bit, &to_intel_frontbuffer(fb)->bits);
 
 	plane_config->vma = vma;
-
-	/*
-	 * Flip to the newly created mapping ASAP, so we can re-use the
-	 * first part of GGTT for WOPCM, prevent flickering, and prevent
-	 * the lookup of sysmem scratch pages.
-	 */
-	plane->check_plane(crtc_state, plane_state);
-	plane->async_flip(NULL, plane, crtc_state, plane_state, true);
 	return;
 
 nofb:

From d1039a3c12fffe501c5379c7eb1372eaab318e0a Mon Sep 17 00:00:00 2001
From: Jani Nikula <jani.nikula@intel.com>
Date: Wed, 26 Feb 2025 15:56:26 +0200
Subject: [PATCH 1525/2753] drm/i915/mst: update max stream count to match
 number of pipes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We create the stream encoders and attach connectors for each pipe we
have. As the number of pipes has increased, we've failed to update the
topology manager maximum number of payloads to match that. Bump up the
max stream count to match number of pipes, enabling the fourth stream on
platforms that support four pipes.

Cc: stable@vger.kernel.org
Cc: Imre Deak <imre.deak@intel.com>
Cc: Ville Syrjala <ville.syrjala@linux.intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226135626.1956012-1-jani.nikula@intel.com
Signed-off-by: Jani Nikula <jani.nikula@intel.com>
(cherry picked from commit 15bccbfb78d63a2a621b30caff8b9424160c6c89)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_dp_mst.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
index a65cf97ad12df..86d6185fda50a 100644
--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
@@ -1867,7 +1867,8 @@ intel_dp_mst_encoder_init(struct intel_digital_port *dig_port, int conn_base_id)
 	/* create encoders */
 	mst_stream_encoders_create(dig_port);
 	ret = drm_dp_mst_topology_mgr_init(&intel_dp->mst_mgr, display->drm,
-					   &intel_dp->aux, 16, 3, conn_base_id);
+					   &intel_dp->aux, 16,
+					   INTEL_NUM_PIPES(display), conn_base_id);
 	if (ret) {
 		intel_dp->mst_mgr.cbs = NULL;
 		return ret;

From 475d06e00b7496c7915d87f7ae67af26738e4649 Mon Sep 17 00:00:00 2001
From: Matthew Auld <matthew.auld@intel.com>
Date: Wed, 26 Feb 2025 17:47:49 +0000
Subject: [PATCH 1526/2753] drm/xe/userptr: properly setup pfn_flags_mask
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently we just leave it uninitialised, which at first looks harmless,
however we also don't zero out the pfn array, and with pfn_flags_mask
the idea is to be able set individual flags for a given range of pfn or
completely ignore them, outside of default_flags. So here we end up with
pfn[i] & pfn_flags_mask, and if both are uninitialised we might get back
an unexpected flags value, like asking for read only with default_flags,
but getting back write on top, leading to potentially bogus behaviour.

To fix this ensure we zero the pfn_flags_mask, such that hmm only
considers the default_flags and not also the initial pfn[i] value.

v2 (Thomas):
 - Prefer proper initializer.

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Signed-off-by: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Thomas Hellström <thomas.hellstrom@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250226174748.294285-2-matthew.auld@intel.com
(cherry picked from commit dd8c01e42f4c5c1eaf02f003d7d588ba6706aa71)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 0898344678801..2e4ae61567d8d 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -166,13 +166,20 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 {
 	unsigned long timeout =
 		jiffies + msecs_to_jiffies(HMM_RANGE_DEFAULT_TIMEOUT);
-	unsigned long *pfns, flags = HMM_PFN_REQ_FAULT;
+	unsigned long *pfns;
 	struct xe_userptr *userptr;
 	struct xe_vma *vma = &uvma->vma;
 	u64 userptr_start = xe_vma_userptr(vma);
 	u64 userptr_end = userptr_start + xe_vma_size(vma);
 	struct xe_vm *vm = xe_vma_vm(vma);
-	struct hmm_range hmm_range;
+	struct hmm_range hmm_range = {
+		.pfn_flags_mask = 0, /* ignore pfns */
+		.default_flags = HMM_PFN_REQ_FAULT,
+		.start = userptr_start,
+		.end = userptr_end,
+		.notifier = &uvma->userptr.notifier,
+		.dev_private_owner = vm->xe,
+	};
 	bool write = !xe_vma_read_only(vma);
 	unsigned long notifier_seq;
 	u64 npages;
@@ -199,19 +206,14 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 		return -ENOMEM;
 
 	if (write)
-		flags |= HMM_PFN_REQ_WRITE;
+		hmm_range.default_flags |= HMM_PFN_REQ_WRITE;
 
 	if (!mmget_not_zero(userptr->notifier.mm)) {
 		ret = -EFAULT;
 		goto free_pfns;
 	}
 
-	hmm_range.default_flags = flags;
 	hmm_range.hmm_pfns = pfns;
-	hmm_range.notifier = &userptr->notifier;
-	hmm_range.start = userptr_start;
-	hmm_range.end = userptr_end;
-	hmm_range.dev_private_owner = vm->xe;
 
 	while (true) {
 		hmm_range.notifier_seq = mmu_interval_read_begin(&userptr->notifier);

From 54f94dc7f6b4db45dbc23b4db3d20c7194e2c54f Mon Sep 17 00:00:00 2001
From: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Date: Thu, 27 Feb 2025 10:13:00 +0000
Subject: [PATCH 1527/2753] drm/xe: Fix GT "for each engine" workarounds

Any rules using engine matching are currently broken due RTP processing
happening too in early init, before the list of hardware engines has been
initialised.

Fix this by moving workaround processing to later in the driver probe
sequence, to just before the processed list is used for the first time.

Looking at the debugfs gt0/workarounds on ADL-P we notice 14011060649
should be present while we see, before:

 GT Workarounds
     14011059788
     14015795083

And with the patch:

 GT Workarounds
     14011060649
     14011059788
     14015795083

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@igalia.com>
Cc: Lucas De Marchi <lucas.demarchi@intel.com>
Cc: Matt Roper <matthew.d.roper@intel.com>
Cc: stable@vger.kernel.org # v6.11+
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250227101304.46660-2-tvrtko.ursulin@igalia.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 25d434cef791e03cf40680f5441b576c639bfa84)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_gt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c
index 5d6fb79957b63..9f4f27d1ef4a9 100644
--- a/drivers/gpu/drm/xe/xe_gt.c
+++ b/drivers/gpu/drm/xe/xe_gt.c
@@ -380,9 +380,7 @@ int xe_gt_init_early(struct xe_gt *gt)
 	if (err)
 		return err;
 
-	xe_wa_process_gt(gt);
 	xe_wa_process_oob(gt);
-	xe_tuning_process_gt(gt);
 
 	xe_force_wake_init_gt(gt, gt_to_fw(gt));
 	spin_lock_init(&gt->global_invl_lock);
@@ -474,6 +472,8 @@ static int all_fw_domain_init(struct xe_gt *gt)
 	}
 
 	xe_gt_mcr_set_implicit_defaults(gt);
+	xe_wa_process_gt(gt);
+	xe_tuning_process_gt(gt);
 	xe_reg_sr_apply_mmio(&gt->reg_sr, gt);
 
 	err = xe_gt_clock_init(gt);

From 778b94d7ac17b5800aa857222911f09cc986b509 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:53 -0600
Subject: [PATCH 1528/2753] ACPI: platform_profile: Add support for hidden
 choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When two drivers don't support all the same profiles the legacy interface
only exports the common profiles.

This causes problems for cases where one driver uses low-power but another
uses quiet because the result is that neither is exported to sysfs.

To allow two drivers to disagree, add support for "hidden choices".
Hidden choices are platform profiles that a driver supports to be
compatible with the platform profile of another driver.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Reported-by: Antheas Kapenekakis <lkml@antheas.dev>
Closes: https://lore.kernel.org/platform-driver-x86/e64b771e-3255-42ad-9257-5b8fc6c24ac9@gmx.de/T/#mc068042dd29df36c16c8af92664860fc4763974b
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-2-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/platform_profile.c  | 94 +++++++++++++++++++++++++-------
 include/linux/platform_profile.h |  3 +
 2 files changed, 76 insertions(+), 21 deletions(-)

diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index 2ad53cc6aae53..ef9444482db19 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -21,9 +21,15 @@ struct platform_profile_handler {
 	struct device dev;
 	int minor;
 	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	unsigned long hidden_choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
 	const struct platform_profile_ops *ops;
 };
 
+struct aggregate_choices_data {
+	unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	int count;
+};
+
 static const char * const profile_names[] = {
 	[PLATFORM_PROFILE_LOW_POWER] = "low-power",
 	[PLATFORM_PROFILE_COOL] = "cool",
@@ -73,7 +79,7 @@ static int _store_class_profile(struct device *dev, void *data)
 
 	lockdep_assert_held(&profile_lock);
 	handler = to_pprof_handler(dev);
-	if (!test_bit(*bit, handler->choices))
+	if (!test_bit(*bit, handler->choices) && !test_bit(*bit, handler->hidden_choices))
 		return -EOPNOTSUPP;
 
 	return handler->ops->profile_set(dev, *bit);
@@ -239,21 +245,44 @@ static const struct class platform_profile_class = {
 /**
  * _aggregate_choices - Aggregate the available profile choices
  * @dev: The device
- * @data: The available profile choices
+ * @arg: struct aggregate_choices_data
  *
  * Return: 0 on success, -errno on failure
  */
-static int _aggregate_choices(struct device *dev, void *data)
+static int _aggregate_choices(struct device *dev, void *arg)
 {
+	unsigned long tmp[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data *data = arg;
 	struct platform_profile_handler *handler;
-	unsigned long *aggregate = data;
 
 	lockdep_assert_held(&profile_lock);
 	handler = to_pprof_handler(dev);
-	if (test_bit(PLATFORM_PROFILE_LAST, aggregate))
-		bitmap_copy(aggregate, handler->choices, PLATFORM_PROFILE_LAST);
+	bitmap_or(tmp, handler->choices, handler->hidden_choices, PLATFORM_PROFILE_LAST);
+	if (test_bit(PLATFORM_PROFILE_LAST, data->aggregate))
+		bitmap_copy(data->aggregate, tmp, PLATFORM_PROFILE_LAST);
 	else
-		bitmap_and(aggregate, handler->choices, aggregate, PLATFORM_PROFILE_LAST);
+		bitmap_and(data->aggregate, tmp, data->aggregate, PLATFORM_PROFILE_LAST);
+	data->count++;
+
+	return 0;
+}
+
+/**
+ * _remove_hidden_choices - Remove hidden choices from aggregate data
+ * @dev: The device
+ * @arg: struct aggregate_choices_data
+ *
+ * Return: 0 on success, -errno on failure
+ */
+static int _remove_hidden_choices(struct device *dev, void *arg)
+{
+	struct aggregate_choices_data *data = arg;
+	struct platform_profile_handler *handler;
+
+	lockdep_assert_held(&profile_lock);
+	handler = to_pprof_handler(dev);
+	bitmap_andnot(data->aggregate, handler->choices,
+		      handler->hidden_choices, PLATFORM_PROFILE_LAST);
 
 	return 0;
 }
@@ -270,22 +299,31 @@ static ssize_t platform_profile_choices_show(struct device *dev,
 					     struct device_attribute *attr,
 					     char *buf)
 {
-	unsigned long aggregate[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	int err;
 
-	set_bit(PLATFORM_PROFILE_LAST, aggregate);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		err = class_for_each_device(&platform_profile_class, NULL,
-					    aggregate, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (err)
 			return err;
+		if (data.count == 1) {
+			err = class_for_each_device(&platform_profile_class, NULL,
+						    &data, _remove_hidden_choices);
+			if (err)
+				return err;
+		}
 	}
 
 	/* no profile handler registered any more */
-	if (bitmap_empty(aggregate, PLATFORM_PROFILE_LAST))
+	if (bitmap_empty(data.aggregate, PLATFORM_PROFILE_LAST))
 		return -EINVAL;
 
-	return _commmon_choices_show(aggregate, buf);
+	return _commmon_choices_show(data.aggregate, buf);
 }
 
 /**
@@ -373,7 +411,10 @@ static ssize_t platform_profile_store(struct device *dev,
 				      struct device_attribute *attr,
 				      const char *buf, size_t count)
 {
-	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	int ret;
 	int i;
 
@@ -381,13 +422,13 @@ static ssize_t platform_profile_store(struct device *dev,
 	i = sysfs_match_string(profile_names, buf);
 	if (i < 0 || i == PLATFORM_PROFILE_CUSTOM)
 		return -EINVAL;
-	set_bit(PLATFORM_PROFILE_LAST, choices);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		ret = class_for_each_device(&platform_profile_class, NULL,
-					    choices, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (ret)
 			return ret;
-		if (!test_bit(i, choices))
+		if (!test_bit(i, data.aggregate))
 			return -EOPNOTSUPP;
 
 		ret = class_for_each_device(&platform_profile_class, NULL, &i,
@@ -453,12 +494,15 @@ EXPORT_SYMBOL_GPL(platform_profile_notify);
  */
 int platform_profile_cycle(void)
 {
+	struct aggregate_choices_data data = {
+		.aggregate = { [0 ... BITS_TO_LONGS(PLATFORM_PROFILE_LAST) - 1] = ~0UL },
+		.count = 0,
+	};
 	enum platform_profile_option next = PLATFORM_PROFILE_LAST;
 	enum platform_profile_option profile = PLATFORM_PROFILE_LAST;
-	unsigned long choices[BITS_TO_LONGS(PLATFORM_PROFILE_LAST)];
 	int err;
 
-	set_bit(PLATFORM_PROFILE_LAST, choices);
+	set_bit(PLATFORM_PROFILE_LAST, data.aggregate);
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
 		err = class_for_each_device(&platform_profile_class, NULL,
 					    &profile, _aggregate_profiles);
@@ -470,14 +514,14 @@ int platform_profile_cycle(void)
 			return -EINVAL;
 
 		err = class_for_each_device(&platform_profile_class, NULL,
-					    choices, _aggregate_choices);
+					    &data, _aggregate_choices);
 		if (err)
 			return err;
 
 		/* never iterate into a custom if all drivers supported it */
-		clear_bit(PLATFORM_PROFILE_CUSTOM, choices);
+		clear_bit(PLATFORM_PROFILE_CUSTOM, data.aggregate);
 
-		next = find_next_bit_wrap(choices,
+		next = find_next_bit_wrap(data.aggregate,
 					  PLATFORM_PROFILE_LAST,
 					  profile + 1);
 
@@ -532,6 +576,14 @@ struct device *platform_profile_register(struct device *dev, const char *name,
 		return ERR_PTR(-EINVAL);
 	}
 
+	if (ops->hidden_choices) {
+		err = ops->hidden_choices(drvdata, pprof->hidden_choices);
+		if (err) {
+			dev_err(dev, "platform_profile hidden_choices failed\n");
+			return ERR_PTR(err);
+		}
+	}
+
 	guard(mutex)(&profile_lock);
 
 	/* create class interface for individual handler */
diff --git a/include/linux/platform_profile.h b/include/linux/platform_profile.h
index 8ab5b0e8eb2c1..8c9df7dadd5d3 100644
--- a/include/linux/platform_profile.h
+++ b/include/linux/platform_profile.h
@@ -33,6 +33,8 @@ enum platform_profile_option {
  * @probe: Callback to setup choices available to the new class device. These
  *	   choices will only be enforced when setting a new profile, not when
  *	   getting the current one.
+ * @hidden_choices: Callback to setup choices that are not visible to the user
+ *		    but can be set by the driver.
  * @profile_get: Callback that will be called when showing the current platform
  *		 profile in sysfs.
  * @profile_set: Callback that will be called when storing a new platform
@@ -40,6 +42,7 @@ enum platform_profile_option {
  */
 struct platform_profile_ops {
 	int (*probe)(void *drvdata, unsigned long *choices);
+	int (*hidden_choices)(void *drvdata, unsigned long *choices);
 	int (*profile_get)(struct device *dev, enum platform_profile_option *profile);
 	int (*profile_set)(struct device *dev, enum platform_profile_option profile);
 };

From 44e94fece5170ed9110564efec592d0e88830a28 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:54 -0600
Subject: [PATCH 1529/2753] platform/x86/amd: pmf: Add 'quiet' to hidden
 choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When amd-pmf and asus-wmi are both bound no low power option shows
up in sysfs.  Add a hidden choice for amd-pmf to support 'quiet' mode
to let both bind.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Suggested-by: Antheas Kapenekakis <lkml@antheas.dev>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-3-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/platform/x86/amd/pmf/sps.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index e6cf0b22dac33..3a0079c17cb17 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -303,6 +303,7 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf)
 		mode = POWER_MODE_BALANCED_POWER;
 		break;
 	case PLATFORM_PROFILE_LOW_POWER:
+	case PLATFORM_PROFILE_QUIET:
 		mode = POWER_MODE_POWER_SAVER;
 		break;
 	default:
@@ -387,6 +388,13 @@ static int amd_pmf_profile_set(struct device *dev,
 	return 0;
 }
 
+static int amd_pmf_hidden_choices(void *drvdata, unsigned long *choices)
+{
+	set_bit(PLATFORM_PROFILE_QUIET, choices);
+
+	return 0;
+}
+
 static int amd_pmf_profile_probe(void *drvdata, unsigned long *choices)
 {
 	set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
@@ -398,6 +406,7 @@ static int amd_pmf_profile_probe(void *drvdata, unsigned long *choices)
 
 static const struct platform_profile_ops amd_pmf_profile_ops = {
 	.probe = amd_pmf_profile_probe,
+	.hidden_choices = amd_pmf_hidden_choices,
 	.profile_get = amd_pmf_profile_get,
 	.profile_set = amd_pmf_profile_set,
 };

From 9a43102daf64dd0d172d8b39836dbc1dba4da1ea Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 11:01:55 -0600
Subject: [PATCH 1530/2753] platform/x86/amd: pmf: Add balanced-performance to
 hidden choices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Acer's WMI driver uses balanced-performance but AMD-PMF doesn't.
In case a machine binds with both drivers let amd-pmf use
balanced-performance as well.

Fixes: 688834743d67 ("ACPI: platform_profile: Allow multiple handlers")
Suggested-by: Antheas Kapenekakis <lkml@antheas.dev>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Antheas Kapenekakis <lkml@antheas.dev>
Tested-by: Derek J. Clark <derekjohn.clark@gmail.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250228170155.2623386-4-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/platform/x86/amd/pmf/sps.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/sps.c b/drivers/platform/x86/amd/pmf/sps.c
index 3a0079c17cb17..d3083383f11fb 100644
--- a/drivers/platform/x86/amd/pmf/sps.c
+++ b/drivers/platform/x86/amd/pmf/sps.c
@@ -297,6 +297,7 @@ int amd_pmf_get_pprof_modes(struct amd_pmf_dev *pmf)
 
 	switch (pmf->current_profile) {
 	case PLATFORM_PROFILE_PERFORMANCE:
+	case PLATFORM_PROFILE_BALANCED_PERFORMANCE:
 		mode = POWER_MODE_PERFORMANCE;
 		break;
 	case PLATFORM_PROFILE_BALANCED:
@@ -391,6 +392,7 @@ static int amd_pmf_profile_set(struct device *dev,
 static int amd_pmf_hidden_choices(void *drvdata, unsigned long *choices)
 {
 	set_bit(PLATFORM_PROFILE_QUIET, choices);
+	set_bit(PLATFORM_PROFILE_BALANCED_PERFORMANCE, choices);
 
 	return 0;
 }

From 723aa55c08c9d1e0734e39a815fd41272eac8269 Mon Sep 17 00:00:00 2001
From: Wentao Guan <guanwentao@uniontech.com>
Date: Fri, 14 Feb 2025 19:04:18 +0800
Subject: [PATCH 1531/2753] HID: i2c-hid: improve i2c_hid_get_report error
 message

We have two places to print "failed to set a report to ...",
use "get a report from" instead of "set a report to", it makes
people who knows less about the module to know where the error
happened.

Before:
i2c_hid_acpi i2c-FTSC1000:00: failed to set a report to device: -11

After:
i2c_hid_acpi i2c-FTSC1000:00: failed to get a report from device: -11

Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/i2c-hid/i2c-hid-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/i2c-hid/i2c-hid-core.c b/drivers/hid/i2c-hid/i2c-hid-core.c
index 75544448c2393..d3912e3f2f13a 100644
--- a/drivers/hid/i2c-hid/i2c-hid-core.c
+++ b/drivers/hid/i2c-hid/i2c-hid-core.c
@@ -290,7 +290,7 @@ static int i2c_hid_get_report(struct i2c_hid *ihid,
 			     ihid->rawbuf, recv_len + sizeof(__le16));
 	if (error) {
 		dev_err(&ihid->client->dev,
-			"failed to set a report to device: %d\n", error);
+			"failed to get a report from device: %d\n", error);
 		return error;
 	}
 

From 221cea1003d8a412e5ec64a58df7ab19b654f490 Mon Sep 17 00:00:00 2001
From: Alex Henrie <alexhenrie24@gmail.com>
Date: Sun, 23 Feb 2025 22:36:30 -0700
Subject: [PATCH 1532/2753] HID: apple: disable Fn key handling on the Omoton
 KB066

Remove the fixup to make the Omoton KB066's F6 key F6 when not holding
Fn. That was really just a hack to allow typing F6 in fnmode>0, and it
didn't fix any of the other F keys that were likewise untypable in
fnmode>0. Instead, because the Omoton's Fn key is entirely internal to
the keyboard, completely disable Fn key translation when an Omoton is
detected, which will prevent the hid-apple driver from interfering with
the keyboard's built-in Fn key handling. All of the F keys, including
F6, are then typable when Fn is held.

The Omoton KB066 and the Apple A1255 both have HID product code
05ac:022c. The self-reported name of every original A1255 when they left
the factory was "Apple Wireless Keyboard". By default, Mac OS changes
the name to "<username>'s keyboard" when pairing with the keyboard, but
Mac OS allows the user to set the internal name of Apple keyboards to
anything they like. The Omoton KB066's name, on the other hand, is not
configurable: It is always "Bluetooth Keyboard". Because that name is so
generic that a user might conceivably use the same name for a real Apple
keyboard, detect Omoton keyboards based on both having that exact name
and having HID product code 022c.

Fixes: 819083cb6eed ("HID: apple: fix up the F6 key on the Omoton KB066 keyboard")
Signed-off-by: Alex Henrie <alexhenrie24@gmail.com>
Reviewed-by: Aditya Garg <gargaditya08@live.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-apple.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index 49812a76b7edd..d900dd05c335c 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -378,6 +378,12 @@ static bool apple_is_non_apple_keyboard(struct hid_device *hdev)
 	return false;
 }
 
+static bool apple_is_omoton_kb066(struct hid_device *hdev)
+{
+	return hdev->product == USB_DEVICE_ID_APPLE_ALU_WIRELESS_ANSI &&
+		strcmp(hdev->name, "Bluetooth Keyboard") == 0;
+}
+
 static inline void apple_setup_key_translation(struct input_dev *input,
 		const struct apple_key_translation *table)
 {
@@ -546,9 +552,6 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 		}
 	}
 
-	if (usage->hid == 0xc0301) /* Omoton KB066 quirk */
-		code = KEY_F6;
-
 	if (usage->code != code) {
 		input_event_with_scancode(input, usage->type, code, usage->hid, value);
 
@@ -728,7 +731,7 @@ static int apple_input_configured(struct hid_device *hdev,
 {
 	struct apple_sc *asc = hid_get_drvdata(hdev);
 
-	if ((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) {
+	if (((asc->quirks & APPLE_HAS_FN) && !asc->fn_found) || apple_is_omoton_kb066(hdev)) {
 		hid_info(hdev, "Fn key not found (Apple Wireless Keyboard clone?), disabling Fn key handling\n");
 		asc->quirks &= ~APPLE_HAS_FN;
 	}

From 2ff5baa9b5275e3acafdf7f2089f74cccb2f38d1 Mon Sep 17 00:00:00 2001
From: Daniil Dulov <d.dulov@aladdin.ru>
Date: Mon, 24 Feb 2025 20:30:30 +0300
Subject: [PATCH 1533/2753] HID: appleir: Fix potential NULL dereference at raw
 event handle

Syzkaller reports a NULL pointer dereference issue in input_event().

BUG: KASAN: null-ptr-deref in instrument_atomic_read include/linux/instrumented.h:68 [inline]
BUG: KASAN: null-ptr-deref in _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline]
BUG: KASAN: null-ptr-deref in is_event_supported drivers/input/input.c:67 [inline]
BUG: KASAN: null-ptr-deref in input_event+0x42/0xa0 drivers/input/input.c:395
Read of size 8 at addr 0000000000000028 by task syz-executor199/2949

CPU: 0 UID: 0 PID: 2949 Comm: syz-executor199 Not tainted 6.13.0-rc4-syzkaller-00076-gf097a36ef88d #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Call Trace:
 <IRQ>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 kasan_report+0xd9/0x110 mm/kasan/report.c:602
 check_region_inline mm/kasan/generic.c:183 [inline]
 kasan_check_range+0xef/0x1a0 mm/kasan/generic.c:189
 instrument_atomic_read include/linux/instrumented.h:68 [inline]
 _test_bit include/asm-generic/bitops/instrumented-non-atomic.h:141 [inline]
 is_event_supported drivers/input/input.c:67 [inline]
 input_event+0x42/0xa0 drivers/input/input.c:395
 input_report_key include/linux/input.h:439 [inline]
 key_down drivers/hid/hid-appleir.c:159 [inline]
 appleir_raw_event+0x3e5/0x5e0 drivers/hid/hid-appleir.c:232
 __hid_input_report.constprop.0+0x312/0x440 drivers/hid/hid-core.c:2111
 hid_ctrl+0x49f/0x550 drivers/hid/usbhid/hid-core.c:484
 __usb_hcd_giveback_urb+0x389/0x6e0 drivers/usb/core/hcd.c:1650
 usb_hcd_giveback_urb+0x396/0x450 drivers/usb/core/hcd.c:1734
 dummy_timer+0x17f7/0x3960 drivers/usb/gadget/udc/dummy_hcd.c:1993
 __run_hrtimer kernel/time/hrtimer.c:1739 [inline]
 __hrtimer_run_queues+0x20a/0xae0 kernel/time/hrtimer.c:1803
 hrtimer_run_softirq+0x17d/0x350 kernel/time/hrtimer.c:1820
 handle_softirqs+0x206/0x8d0 kernel/softirq.c:561
 __do_softirq kernel/softirq.c:595 [inline]
 invoke_softirq kernel/softirq.c:435 [inline]
 __irq_exit_rcu+0xfa/0x160 kernel/softirq.c:662
 irq_exit_rcu+0x9/0x30 kernel/softirq.c:678
 instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1049 [inline]
 sysvec_apic_timer_interrupt+0x90/0xb0 arch/x86/kernel/apic/apic.c:1049
 </IRQ>
 <TASK>
 asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702
 __mod_timer+0x8f6/0xdc0 kernel/time/timer.c:1185
 add_timer+0x62/0x90 kernel/time/timer.c:1295
 schedule_timeout+0x11f/0x280 kernel/time/sleep_timeout.c:98
 usbhid_wait_io+0x1c7/0x380 drivers/hid/usbhid/hid-core.c:645
 usbhid_init_reports+0x19f/0x390 drivers/hid/usbhid/hid-core.c:784
 hiddev_ioctl+0x1133/0x15b0 drivers/hid/usbhid/hiddev.c:794
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:906 [inline]
 __se_sys_ioctl fs/ioctl.c:892 [inline]
 __x64_sys_ioctl+0x190/0x200 fs/ioctl.c:892
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 </TASK>

This happens due to the malformed report items sent by the emulated device
which results in a report, that has no fields, being added to the report list.
Due to this appleir_input_configured() is never called, hidinput_connect()
fails which results in the HID_CLAIMED_INPUT flag is not being set. However,
it  does not make appleir_probe() fail and lets the event callback to be
called without the associated input device.

Thus, add a check for the HID_CLAIMED_INPUT flag and leave the event hook
early if the driver didn't claim any input_dev for some reason. Moreover,
some other hid drivers accessing input_dev in their event callbacks do have
similar checks, too.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 9a4a5574ce42 ("HID: appleir: add support for Apple ir devices")
Cc: stable@vger.kernel.org
Signed-off-by: Daniil Dulov <d.dulov@aladdin.ru>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-appleir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-appleir.c b/drivers/hid/hid-appleir.c
index 8deded1857254..c45e5aa569d25 100644
--- a/drivers/hid/hid-appleir.c
+++ b/drivers/hid/hid-appleir.c
@@ -188,7 +188,7 @@ static int appleir_raw_event(struct hid_device *hid, struct hid_report *report,
 	static const u8 flatbattery[] = { 0x25, 0x87, 0xe0 };
 	unsigned long flags;
 
-	if (len != 5)
+	if (len != 5 || !(hid->claimed & HID_CLAIMED_INPUT))
 		goto out;
 
 	if (!memcmp(data, keydown, sizeof(keydown))) {

From a6a4f4e9b8018806cca30049b59a1c3c8b513701 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Thu, 27 Feb 2025 22:33:57 +0000
Subject: [PATCH 1534/2753] HID: debug: Fix spelling mistake "Messanger" ->
 "Messenger"

There is a spelling mistake in a literal string. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-debug.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-debug.c b/drivers/hid/hid-debug.c
index 541d682af15aa..8433306148d57 100644
--- a/drivers/hid/hid-debug.c
+++ b/drivers/hid/hid-debug.c
@@ -3450,7 +3450,7 @@ static const char *keys[KEY_MAX + 1] = {
 	[KEY_MACRO_RECORD_START] = "MacroRecordStart",
 	[KEY_MACRO_RECORD_STOP] = "MacroRecordStop",
 	[KEY_MARK_WAYPOINT] = "MarkWayPoint",	[KEY_MEDIA_REPEAT] = "MediaRepeat",
-	[KEY_MEDIA_TOP_MENU] = "MediaTopMenu",	[KEY_MESSENGER] = "Messanger",
+	[KEY_MEDIA_TOP_MENU] = "MediaTopMenu",	[KEY_MESSENGER] = "Messenger",
 	[KEY_NAV_CHART] = "NavChar",		[KEY_NAV_INFO] = "NavInfo",
 	[KEY_NEWS] = "News",			[KEY_NEXT_ELEMENT] = "NextElement",
 	[KEY_NEXT_FAVORITE] = "NextFavorite",	[KEY_NOTIFICATION_CENTER] = "NotificationCenter",

From e53fc232a65f7488ab75d03a5b95f06aaada7262 Mon Sep 17 00:00:00 2001
From: Vicki Pfau <vi@endrift.com>
Date: Thu, 27 Feb 2025 15:41:33 -0800
Subject: [PATCH 1535/2753] HID: hid-steam: Fix use-after-free when detaching
 device

When a hid-steam device is removed it must clean up the client_hdev used for
intercepting hidraw access. This can lead to scheduling deferred work to
reattach the input device. Though the cleanup cancels the deferred work, this
was done before the client_hdev itself is cleaned up, so it gets rescheduled.
This patch fixes the ordering to make sure the deferred work is properly
canceled.

Reported-by: syzbot+0154da2d403396b2bd59@syzkaller.appspotmail.com
Fixes: 79504249d7e2 ("HID: hid-steam: Move hidraw input (un)registering to work")
Signed-off-by: Vicki Pfau <vi@endrift.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-steam.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/hid-steam.c b/drivers/hid/hid-steam.c
index c9e65e9088b31..10460b7bde1a2 100644
--- a/drivers/hid/hid-steam.c
+++ b/drivers/hid/hid-steam.c
@@ -1327,11 +1327,11 @@ static void steam_remove(struct hid_device *hdev)
 		return;
 	}
 
+	hid_destroy_device(steam->client_hdev);
 	cancel_delayed_work_sync(&steam->mode_switch);
 	cancel_work_sync(&steam->work_connect);
 	cancel_work_sync(&steam->rumble_work);
 	cancel_work_sync(&steam->unregister_work);
-	hid_destroy_device(steam->client_hdev);
 	steam->client_hdev = NULL;
 	steam->client_opened = 0;
 	if (steam->quirks & STEAM_QUIRK_WIRELESS) {

From 0132c406705a466b95854ce1058f3d8354f90a42 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Fri, 28 Feb 2025 08:41:39 +0000
Subject: [PATCH 1536/2753] HID: intel-thc-hid: Fix spelling mistake "intput"
 -> "input"

There is a spelling mistake in a dev_err_once message. Fix it.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Reviewed-by: Even Xu <even.xu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
index 7373238ceb18b..918050af73e55 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/quickspi-protocol.c
@@ -107,7 +107,7 @@ static int quickspi_get_device_descriptor(struct quickspi_device *qsdev)
 		return 0;
 	}
 
-	dev_err_once(qsdev->dev, "Unexpected intput report type: %d\n", input_rep_type);
+	dev_err_once(qsdev->dev, "Unexpected input report type: %d\n", input_rep_type);
 	return -EINVAL;
 }
 

From db52926fb0be40e1d588a346df73f5ea3a34a4c6 Mon Sep 17 00:00:00 2001
From: Even Xu <even.xu@intel.com>
Date: Tue, 4 Mar 2025 11:22:55 +0800
Subject: [PATCH 1537/2753] HID: Intel-thc-hid: Intel-quickspi: Correct device
 state after S4

During S4 retore flow, quickspi device was resetted by driver and state
was changed to RESETTED. It is needed to be change to ENABLED state
after S4 re-initialization finished, otherwise, device will run in wrong
state and HID input data will be dropped.

Signed-off-by: Even Xu <even.xu@intel.com>
Fixes: 6912aaf3fd24 ("HID: intel-thc-hid: intel-quickspi: Add PM implementation")
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
index 4641e818dfa44..6b2c7620be2b1 100644
--- a/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
+++ b/drivers/hid/intel-thc-hid/intel-quickspi/pci-quickspi.c
@@ -909,6 +909,8 @@ static int quickspi_restore(struct device *device)
 
 	thc_change_ltr_mode(qsdev->thc_hw, THC_LTR_MODE_ACTIVE);
 
+	qsdev->state = QUICKSPI_ENABLED;
+
 	return 0;
 }
 

From 5eb3dc1396aa7e315486b24df80df782912334b7 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:40 +0100
Subject: [PATCH 1538/2753] net: ipa: Fix v4.7 resource group names

In the downstream IPA driver there's only one group defined for source
and destination, and the destination group doesn't have a _DPL suffix.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-1-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index c8c23d9be961b..7e315779e6648 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -28,12 +28,10 @@ enum ipa_resource_type {
 enum ipa_rsrc_group_id {
 	/* Source resource group identifiers */
 	IPA_RSRC_GROUP_SRC_UL_DL			= 0,
-	IPA_RSRC_GROUP_SRC_UC_RX_Q,
 	IPA_RSRC_GROUP_SRC_COUNT,	/* Last in set; not a source group */
 
 	/* Destination resource group identifiers */
-	IPA_RSRC_GROUP_DST_UL_DL_DPL			= 0,
-	IPA_RSRC_GROUP_DST_UNUSED_1,
+	IPA_RSRC_GROUP_DST_UL_DL			= 0,
 	IPA_RSRC_GROUP_DST_COUNT,	/* Last; not a destination group */
 };
 
@@ -81,7 +79,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
 				.aggregation	= true,
 				.status_enable	= true,
 				.rx = {
@@ -128,7 +126,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		},
 		.endpoint = {
 			.config = {
-				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL_DPL,
+				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {
@@ -197,12 +195,12 @@ static const struct ipa_resource ipa_resource_src[] = {
 /* Destination resource configuration data for an SoC having IPA v4.7 */
 static const struct ipa_resource ipa_resource_dst[] = {
 	[IPA_RESOURCE_TYPE_DST_DATA_SECTORS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 7,	.max = 7,
 		},
 	},
 	[IPA_RESOURCE_TYPE_DST_DPS_DMARS] = {
-		.limits[IPA_RSRC_GROUP_DST_UL_DL_DPL] = {
+		.limits[IPA_RSRC_GROUP_DST_UL_DL] = {
 			.min = 2,	.max = 2,
 		},
 	},

From 6a2843aaf551d87beb92d774f7d5b8ae007fe774 Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:41 +0100
Subject: [PATCH 1539/2753] net: ipa: Fix QSB data for v4.7

As per downstream reference, max_writes should be 12 and max_reads
should be 13.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-2-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index 7e315779e6648..e63dcf8d45567 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -38,8 +38,8 @@ enum ipa_rsrc_group_id {
 /* QSB configuration data for an SoC having IPA v4.7 */
 static const struct ipa_qsb_data ipa_qsb_data[] = {
 	[IPA_QSB_MASTER_DDR] = {
-		.max_writes		= 8,
-		.max_reads		= 0,	/* no limit (hardware max) */
+		.max_writes		= 12,
+		.max_reads		= 13,
 		.max_reads_beats	= 120,
 	},
 };

From 934e69669e32eb653234898424ae007bae2f636e Mon Sep 17 00:00:00 2001
From: Luca Weiss <luca.weiss@fairphone.com>
Date: Thu, 27 Feb 2025 11:33:42 +0100
Subject: [PATCH 1540/2753] net: ipa: Enable checksum for
 IPA_ENDPOINT_AP_MODEM_{RX,TX} for v4.7

Enable the checksum option for these two endpoints in order to allow
mobile data to actually work. Without this, no packets seem to make it
through the IPA.

Fixes: b310de784bac ("net: ipa: add IPA v4.7 support")
Signed-off-by: Luca Weiss <luca.weiss@fairphone.com>
Reviewed-by: Alex Elder <elder@riscstar.com>
Link: https://patch.msgid.link/20250227-ipa-v4-7-fixes-v1-3-a88dd8249d8a@fairphone.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ipa/data/ipa_data-v4.7.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ipa/data/ipa_data-v4.7.c b/drivers/net/ipa/data/ipa_data-v4.7.c
index e63dcf8d45567..41f212209993f 100644
--- a/drivers/net/ipa/data/ipa_data-v4.7.c
+++ b/drivers/net/ipa/data/ipa_data-v4.7.c
@@ -104,6 +104,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 			.filter_support	= true,
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_SRC_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.status_enable	= true,
 				.tx = {
@@ -127,6 +128,7 @@ static const struct ipa_gsi_endpoint_data ipa_gsi_endpoint_data[] = {
 		.endpoint = {
 			.config = {
 				.resource_group	= IPA_RSRC_GROUP_DST_UL_DL,
+				.checksum       = true,
 				.qmap		= true,
 				.aggregation	= true,
 				.rx = {

From 4c2d14c40a68678d885eab4008a0129646805bae Mon Sep 17 00:00:00 2001
From: Jiayuan Chen <jiayuan.chen@linux.dev>
Date: Fri, 28 Feb 2025 22:14:08 +0800
Subject: [PATCH 1541/2753] ppp: Fix KMSAN uninit-value warning with bpf

Syzbot caught an "KMSAN: uninit-value" warning [1], which is caused by the
ppp driver not initializing a 2-byte header when using socket filter.

The following code can generate a PPP filter BPF program:
'''
struct bpf_program fp;
pcap_t *handle;
handle = pcap_open_dead(DLT_PPP_PPPD, 65535);
pcap_compile(handle, &fp, "ip and outbound", 0, 0);
bpf_dump(&fp, 1);
'''
Its output is:
'''
(000) ldh [2]
(001) jeq #0x21 jt 2 jf 5
(002) ldb [0]
(003) jeq #0x1 jt 4 jf 5
(004) ret #65535
(005) ret #0
'''
Wen can find similar code at the following link:
https://github.com/ppp-project/ppp/blob/master/pppd/options.c#L1680
The maintainer of this code repository is also the original maintainer
of the ppp driver.

As you can see the BPF program skips 2 bytes of data and then reads the
'Protocol' field to determine if it's an IP packet. Then it read the first
byte of the first 2 bytes to determine the direction.

The issue is that only the first byte indicating direction is initialized
in current ppp driver code while the second byte is not initialized.

For normal BPF programs generated by libpcap, uninitialized data won't be
used, so it's not a problem. However, for carefully crafted BPF programs,
such as those generated by syzkaller [2], which start reading from offset
0, the uninitialized data will be used and caught by KMSAN.

[1] https://syzkaller.appspot.com/bug?extid=853242d9c9917165d791
[2] https://syzkaller.appspot.com/text?tag=ReproC&x=11994913980000

Cc: Paul Mackerras <paulus@samba.org>
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+853242d9c9917165d791@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/bpf/000000000000dea025060d6bc3bc@google.com/
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250228141408.393864-1-jiayuan.chen@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/ppp_generic.c | 28 +++++++++++++++++++---------
 1 file changed, 19 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 4583e15ad03a0..1420c4efa48e6 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -72,6 +72,17 @@
 #define PPP_PROTO_LEN	2
 #define PPP_LCP_HDRLEN	4
 
+/* The filter instructions generated by libpcap are constructed
+ * assuming a four-byte PPP header on each packet, where the last
+ * 2 bytes are the protocol field defined in the RFC and the first
+ * byte of the first 2 bytes indicates the direction.
+ * The second byte is currently unused, but we still need to initialize
+ * it to prevent crafted BPF programs from reading them which would
+ * cause reading of uninitialized data.
+ */
+#define PPP_FILTER_OUTBOUND_TAG 0x0100
+#define PPP_FILTER_INBOUND_TAG  0x0000
+
 /*
  * An instance of /dev/ppp can be associated with either a ppp
  * interface unit or a ppp channel.  In both cases, file->private_data
@@ -1762,10 +1773,10 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
 
 	if (proto < 0x8000) {
 #ifdef CONFIG_PPP_FILTER
-		/* check if we should pass this packet */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
-		*(u8 *)skb_push(skb, 2) = 1;
+		/* check if the packet passes the pass and active filters.
+		 * See comment for PPP_FILTER_OUTBOUND_TAG above.
+		 */
+		*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_OUTBOUND_TAG);
 		if (ppp->pass_filter &&
 		    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 			if (ppp->debug & 1)
@@ -2482,14 +2493,13 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 		/* network protocol frame - give it to the kernel */
 
 #ifdef CONFIG_PPP_FILTER
-		/* check if the packet passes the pass and active filters */
-		/* the filter instructions are constructed assuming
-		   a four-byte PPP header on each packet */
 		if (ppp->pass_filter || ppp->active_filter) {
 			if (skb_unclone(skb, GFP_ATOMIC))
 				goto err;
-
-			*(u8 *)skb_push(skb, 2) = 0;
+			/* Check if the packet passes the pass and active filters.
+			 * See comment for PPP_FILTER_INBOUND_TAG above.
+			 */
+			*(__be16 *)skb_push(skb, 2) = htons(PPP_FILTER_INBOUND_TAG);
 			if (ppp->pass_filter &&
 			    bpf_prog_run(ppp->pass_filter, skb) == 0) {
 				if (ppp->debug & 1)

From 00f5e338cf7e2612ecf66d07b391135dd32f74e1 Mon Sep 17 00:00:00 2001
From: Gang Yan <yangang@kylinos.cn>
Date: Fri, 28 Feb 2025 15:38:35 +0100
Subject: [PATCH 1542/2753] selftests: mptcp: Add a tool to get specific
 msk_info

This patch enables the retrieval of the mptcp_info structure corresponding
to a specified MPTCP socket (msk). When multiple MPTCP connections are
present, specific information can be obtained for a given connection
through the 'mptcp_diag_dump_one' by using the 'token' associated with
the msk.

Signed-off-by: Gang Yan <yangang@kylinos.cn>
Co-developed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228-net-next-mptcp-coverage-small-opti-v1-1-f933c4275676@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/Makefile    |   2 +-
 .../testing/selftests/net/mptcp/mptcp_diag.c  | 272 ++++++++++++++++++
 2 files changed, 273 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/net/mptcp/mptcp_diag.c

diff --git a/tools/testing/selftests/net/mptcp/Makefile b/tools/testing/selftests/net/mptcp/Makefile
index c76525fe2b84d..340e1a777e16a 100644
--- a/tools/testing/selftests/net/mptcp/Makefile
+++ b/tools/testing/selftests/net/mptcp/Makefile
@@ -7,7 +7,7 @@ CFLAGS += -Wall -Wl,--no-as-needed -O2 -g -I$(top_srcdir)/usr/include $(KHDR_INC
 TEST_PROGS := mptcp_connect.sh pm_netlink.sh mptcp_join.sh diag.sh \
 	      simult_flows.sh mptcp_sockopt.sh userspace_pm.sh
 
-TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq
+TEST_GEN_FILES = mptcp_connect pm_nl_ctl mptcp_sockopt mptcp_inq mptcp_diag
 
 TEST_FILES := mptcp_lib.sh settings
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_diag.c b/tools/testing/selftests/net/mptcp/mptcp_diag.c
new file mode 100644
index 0000000000000..284286c524cfe
--- /dev/null
+++ b/tools/testing/selftests/net/mptcp/mptcp_diag.c
@@ -0,0 +1,272 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2025, Kylin Software */
+
+#include <linux/sock_diag.h>
+#include <linux/rtnetlink.h>
+#include <linux/inet_diag.h>
+#include <linux/netlink.h>
+#include <sys/socket.h>
+#include <netinet/in.h>
+#include <linux/tcp.h>
+
+#include <unistd.h>
+#include <stdlib.h>
+#include <string.h>
+#include <errno.h>
+#include <stdio.h>
+
+#ifndef IPPROTO_MPTCP
+#define IPPROTO_MPTCP 262
+#endif
+
+struct mptcp_info {
+	__u8	mptcpi_subflows;
+	__u8	mptcpi_add_addr_signal;
+	__u8	mptcpi_add_addr_accepted;
+	__u8	mptcpi_subflows_max;
+	__u8	mptcpi_add_addr_signal_max;
+	__u8	mptcpi_add_addr_accepted_max;
+	__u32	mptcpi_flags;
+	__u32	mptcpi_token;
+	__u64	mptcpi_write_seq;
+	__u64	mptcpi_snd_una;
+	__u64	mptcpi_rcv_nxt;
+	__u8	mptcpi_local_addr_used;
+	__u8	mptcpi_local_addr_max;
+	__u8	mptcpi_csum_enabled;
+	__u32	mptcpi_retransmits;
+	__u64	mptcpi_bytes_retrans;
+	__u64	mptcpi_bytes_sent;
+	__u64	mptcpi_bytes_received;
+	__u64	mptcpi_bytes_acked;
+	__u8	mptcpi_subflows_total;
+	__u8	reserved[3];
+	__u32	mptcpi_last_data_sent;
+	__u32	mptcpi_last_data_recv;
+	__u32	mptcpi_last_ack_recv;
+};
+
+static void die_perror(const char *msg)
+{
+	perror(msg);
+	exit(1);
+}
+
+static void die_usage(int r)
+{
+	fprintf(stderr, "Usage: mptcp_diag -t\n");
+	exit(r);
+}
+
+static void send_query(int fd, __u32 token)
+{
+	struct sockaddr_nl nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct {
+		struct nlmsghdr nlh;
+		struct inet_diag_req_v2 r;
+	} req = {
+		.nlh = {
+			.nlmsg_len = sizeof(req),
+			.nlmsg_type = SOCK_DIAG_BY_FAMILY,
+			.nlmsg_flags = NLM_F_REQUEST
+		},
+		.r = {
+			.sdiag_family = AF_INET,
+			/* Real proto is set via INET_DIAG_REQ_PROTOCOL */
+			.sdiag_protocol = IPPROTO_TCP,
+			.id.idiag_cookie[0] = token,
+		}
+	};
+	struct rtattr rta_proto;
+	struct iovec iov[6];
+	int iovlen = 1;
+	__u32 proto;
+
+	req.r.idiag_ext |= (1 << (INET_DIAG_INFO - 1));
+	proto = IPPROTO_MPTCP;
+	rta_proto.rta_type = INET_DIAG_REQ_PROTOCOL;
+	rta_proto.rta_len = RTA_LENGTH(sizeof(proto));
+
+	iov[0] = (struct iovec) {
+		.iov_base = &req,
+		.iov_len = sizeof(req)
+	};
+	iov[iovlen] = (struct iovec){ &rta_proto, sizeof(rta_proto)};
+	iov[iovlen + 1] = (struct iovec){ &proto, sizeof(proto)};
+	req.nlh.nlmsg_len += RTA_LENGTH(sizeof(proto));
+	iovlen += 2;
+	struct msghdr msg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = iov,
+		.msg_iovlen = iovlen
+	};
+
+	for (;;) {
+		if (sendmsg(fd, &msg, 0) < 0) {
+			if (errno == EINTR)
+				continue;
+			die_perror("sendmsg");
+		}
+		break;
+	}
+}
+
+static void parse_rtattr_flags(struct rtattr *tb[], int max, struct rtattr *rta,
+			       int len, unsigned short flags)
+{
+	unsigned short type;
+
+	memset(tb, 0, sizeof(struct rtattr *) * (max + 1));
+	while (RTA_OK(rta, len)) {
+		type = rta->rta_type & ~flags;
+		if (type <= max && !tb[type])
+			tb[type] = rta;
+		rta = RTA_NEXT(rta, len);
+	}
+}
+
+static void print_info_msg(struct mptcp_info *info)
+{
+	printf("Token & Flags\n");
+	printf("token:        %x\n", info->mptcpi_token);
+	printf("flags:        %x\n", info->mptcpi_flags);
+	printf("csum_enabled: %u\n", info->mptcpi_csum_enabled);
+
+	printf("\nBasic Info\n");
+	printf("subflows:              %u\n", info->mptcpi_subflows);
+	printf("subflows_max:          %u\n", info->mptcpi_subflows_max);
+	printf("subflows_total:        %u\n", info->mptcpi_subflows_total);
+	printf("local_addr_used:       %u\n", info->mptcpi_local_addr_used);
+	printf("local_addr_max:        %u\n", info->mptcpi_local_addr_max);
+	printf("add_addr_signal:       %u\n", info->mptcpi_add_addr_signal);
+	printf("add_addr_accepted:     %u\n", info->mptcpi_add_addr_accepted);
+	printf("add_addr_signal_max:   %u\n", info->mptcpi_add_addr_signal_max);
+	printf("add_addr_accepted_max: %u\n", info->mptcpi_add_addr_accepted_max);
+
+	printf("\nTransmission Info\n");
+	printf("write_seq:        %llu\n", info->mptcpi_write_seq);
+	printf("snd_una:          %llu\n", info->mptcpi_snd_una);
+	printf("rcv_nxt:          %llu\n", info->mptcpi_rcv_nxt);
+	printf("last_data_sent:   %u\n", info->mptcpi_last_data_sent);
+	printf("last_data_recv:   %u\n", info->mptcpi_last_data_recv);
+	printf("last_ack_recv:    %u\n", info->mptcpi_last_ack_recv);
+	printf("retransmits:      %u\n", info->mptcpi_retransmits);
+	printf("retransmit bytes: %llu\n", info->mptcpi_bytes_retrans);
+	printf("bytes_sent:       %llu\n", info->mptcpi_bytes_sent);
+	printf("bytes_received:   %llu\n", info->mptcpi_bytes_received);
+	printf("bytes_acked:      %llu\n", info->mptcpi_bytes_acked);
+}
+
+static void parse_nlmsg(struct nlmsghdr *nlh)
+{
+	struct inet_diag_msg *r = NLMSG_DATA(nlh);
+	struct rtattr *tb[INET_DIAG_MAX + 1];
+
+	parse_rtattr_flags(tb, INET_DIAG_MAX, (struct rtattr *)(r + 1),
+			   nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*r)),
+			   NLA_F_NESTED);
+
+	if (tb[INET_DIAG_INFO]) {
+		int len = RTA_PAYLOAD(tb[INET_DIAG_INFO]);
+		struct mptcp_info *info;
+
+		/* workaround fort older kernels with less fields */
+		if (len < sizeof(*info)) {
+			info = alloca(sizeof(*info));
+			memcpy(info, RTA_DATA(tb[INET_DIAG_INFO]), len);
+			memset((char *)info + len, 0, sizeof(*info) - len);
+		} else {
+			info = RTA_DATA(tb[INET_DIAG_INFO]);
+		}
+		print_info_msg(info);
+	}
+}
+
+static void recv_nlmsg(int fd, struct nlmsghdr *nlh)
+{
+	char rcv_buff[8192];
+	struct sockaddr_nl rcv_nladdr = {
+		.nl_family = AF_NETLINK
+	};
+	struct iovec rcv_iov = {
+		.iov_base = rcv_buff,
+		.iov_len = sizeof(rcv_buff)
+	};
+	struct msghdr rcv_msg = {
+		.msg_name = &rcv_nladdr,
+		.msg_namelen = sizeof(rcv_nladdr),
+		.msg_iov = &rcv_iov,
+		.msg_iovlen = 1
+	};
+	int len;
+
+	len = recvmsg(fd, &rcv_msg, 0);
+	nlh = (struct nlmsghdr *)rcv_buff;
+
+	while (NLMSG_OK(nlh, len)) {
+		if (nlh->nlmsg_type == NLMSG_DONE) {
+			printf("NLMSG_DONE\n");
+			break;
+		} else if (nlh->nlmsg_type == NLMSG_ERROR) {
+			struct nlmsgerr *err;
+
+			err = (struct nlmsgerr *)NLMSG_DATA(nlh);
+			printf("Error %d:%s\n",
+			       -(err->error), strerror(-(err->error)));
+			break;
+		}
+		parse_nlmsg(nlh);
+		nlh = NLMSG_NEXT(nlh, len);
+	}
+}
+
+static void get_mptcpinfo(__u32 token)
+{
+	struct nlmsghdr *nlh = NULL;
+	int fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_SOCK_DIAG);
+	if (fd < 0)
+		die_perror("Netlink socket");
+
+	send_query(fd, token);
+	recv_nlmsg(fd, nlh);
+
+	close(fd);
+}
+
+static void parse_opts(int argc, char **argv, __u32 *target_token)
+{
+	int c;
+
+	if (argc < 2)
+		die_usage(1);
+
+	while ((c = getopt(argc, argv, "ht:")) != -1) {
+		switch (c) {
+		case 'h':
+			die_usage(0);
+			break;
+		case 't':
+			sscanf(optarg, "%x", target_token);
+			break;
+		default:
+			die_usage(1);
+			break;
+		}
+	}
+}
+
+int main(int argc, char *argv[])
+{
+	__u32 target_token;
+
+	parse_opts(argc, argv, &target_token);
+	get_mptcpinfo(target_token);
+
+	return 0;
+}
+

From ba24001665704d27976a2f190cd8361e339f8581 Mon Sep 17 00:00:00 2001
From: Gang Yan <yangang@kylinos.cn>
Date: Fri, 28 Feb 2025 15:38:36 +0100
Subject: [PATCH 1543/2753] selftests: mptcp: add a test for
 mptcp_diag_dump_one

This patch introduces a new 'chk_diag' test in diag.sh. It retrieves
the token for a specified MPTCP socket (msk) using the 'ss' command and
then accesses the 'mptcp_diag_dump_one' in kernel via ./mptcp_diag
to verify if the correct token is returned.

Link: https://github.com/multipath-tcp/mptcp_net-next/issues/524
Signed-off-by: Gang Yan <yangang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228-net-next-mptcp-coverage-small-opti-v1-2-f933c4275676@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/diag.sh | 27 +++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh
index 2bd0c1eb70c5b..4f55477ffe087 100755
--- a/tools/testing/selftests/net/mptcp/diag.sh
+++ b/tools/testing/selftests/net/mptcp/diag.sh
@@ -200,6 +200,32 @@ chk_msk_cestab()
 		 "${expected}" "${msg}" ""
 }
 
+chk_dump_one()
+{
+	local ss_token
+	local token
+	local msg
+
+	ss_token="$(ss -inmHMN $ns | grep 'token:' |\
+		    head -n 1 |\
+		    sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+
+	token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
+		 awk -F':[ \t]+' '/^token/ {print $2}')"
+
+	msg="....chk dump_one"
+
+	mptcp_lib_print_title "$msg"
+	if [ -n "$ss_token" ] && [ "$ss_token" = "$token" ]; then
+		mptcp_lib_pr_ok
+		mptcp_lib_result_pass "${msg}"
+	else
+		mptcp_lib_pr_fail "expected $ss_token found $token"
+		mptcp_lib_result_fail "${msg}"
+		ret=${KSFT_FAIL}
+	fi
+}
+
 msk_info_get_value()
 {
 	local port="${1}"
@@ -290,6 +316,7 @@ chk_msk_remote_key_nr 2 "....chk remote_key"
 chk_msk_fallback_nr 0 "....chk no fallback"
 chk_msk_inuse 2
 chk_msk_cestab 2
+chk_dump_one
 flush_pids
 
 chk_msk_inuse 0 "2->0"

From e85d33b35508da7e7570c0b54f007b59e205f623 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 28 Feb 2025 15:38:37 +0100
Subject: [PATCH 1544/2753] mptcp: pm: in-kernel: avoid access entry without
 lock

In mptcp_pm_nl_set_flags(), "entry" is copied to "local" when pernet->lock
is held to avoid direct access to entry without pernet->lock.

Therefore, "local->flags" should be passed to mptcp_nl_set_flags instead
of "entry->flags" when pernet->lock is not held, so as to avoid access to
entry.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Fixes: 145dc6cc4abd ("mptcp: pm: change to fullmesh only for 'subflow'")
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228-net-next-mptcp-coverage-small-opti-v1-3-f933c4275676@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index d4328443d844d..fb83eba041f17 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1983,7 +1983,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, &local->addr, entry->flags, changed);
+	mptcp_nl_set_flags(net, &local->addr, local->flags, changed);
 	return 0;
 }
 

From 70c575d5a94f4817d839a2ef1e0a10b1fbd6383e Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 28 Feb 2025 15:38:38 +0100
Subject: [PATCH 1545/2753] mptcp: pm: in-kernel: reduce parameters of
 set_flags

The number of parameters in mptcp_nl_set_flags() can be reduced.
Only need to pass a "local" parameter to it instead of "local->addr"
and "local->flags".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228-net-next-mptcp-coverage-small-opti-v1-4-f933c4275676@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 15 ++++++++-------
 1 file changed, 8 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index fb83eba041f17..4bebc4963c42d 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1907,11 +1907,12 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
-			       u8 flags, u8 changed)
+static void mptcp_nl_set_flags(struct net *net,
+			       struct mptcp_pm_addr_entry *local,
+			       u8 changed)
 {
-	u8 is_subflow = !!(flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
-	u8 bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	u8 is_subflow = !!(local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
+	u8 bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
 	long s_slot = 0, s_num = 0;
 	struct mptcp_sock *msk;
 
@@ -1926,10 +1927,10 @@ static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr,
 
 		lock_sock(sk);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup);
+			mptcp_pm_nl_mp_prio_send_ack(msk, &local->addr, NULL, bkup);
 		/* Subflows will only be recreated if the SUBFLOW flag is set */
 		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
-			mptcp_pm_nl_fullmesh(msk, addr);
+			mptcp_pm_nl_fullmesh(msk, &local->addr);
 		release_sock(sk);
 
 next:
@@ -1983,7 +1984,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, &local->addr, local->flags, changed);
+	mptcp_nl_set_flags(net, local, changed);
 	return 0;
 }
 

From f0de92479a098ba930506ed2e715a7aad3887ec1 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 28 Feb 2025 15:38:39 +0100
Subject: [PATCH 1546/2753] mptcp: pm: exit early with ADD_ADDR echo if
 possible

When the userspace PM is used, or when the in-kernel limits are reached,
there will be no need to schedule the PM worker to signal new addresses.
That corresponds to pm->work_pending set to 0.

In this case, an early exit can be done in mptcp_pm_add_addr_echoed()
not to hold the PM lock, and iterate over the announced addresses list,
not to schedule the worker anyway in this case. This is similar to what
is done when a connection or a subflow has been established.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250228-net-next-mptcp-coverage-small-opti-v1-5-f933c4275676@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 16cacce6c10fe..6c8cadf84f31f 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -251,6 +251,9 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
 
 	pr_debug("msk=%p\n", msk);
 
+	if (!READ_ONCE(pm->work_pending))
+		return;
+
 	spin_lock_bh(&pm->lock);
 
 	if (mptcp_lookup_anno_list_by_saddr(msk, addr) && READ_ONCE(pm->work_pending))

From 39e912a959c19338855b768eaaee2917d7841f71 Mon Sep 17 00:00:00 2001
From: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Date: Fri, 28 Feb 2025 15:02:10 +0000
Subject: [PATCH 1547/2753] dpll: Add an assertion to check freq_supported_num

Since the driver is broken in the case that src->freq_supported is not
NULL but src->freq_supported_num is 0, add an assertion for it.

Signed-off-by: Jiasheng Jiang <jiashengjiangcool@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Link: https://patch.msgid.link/20250228150210.34404-1-jiashengjiangcool@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/dpll_core.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 32019dc33cca7..940c26b9dd53c 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -443,8 +443,11 @@ static void dpll_pin_prop_free(struct dpll_pin_properties *prop)
 static int dpll_pin_prop_dup(const struct dpll_pin_properties *src,
 			     struct dpll_pin_properties *dst)
 {
+	if (WARN_ON(src->freq_supported && !src->freq_supported_num))
+		return -EINVAL;
+
 	memcpy(dst, src, sizeof(*dst));
-	if (src->freq_supported && src->freq_supported_num) {
+	if (src->freq_supported) {
 		size_t freq_size = src->freq_supported_num *
 				   sizeof(*src->freq_supported);
 		dst->freq_supported = kmemdup(src->freq_supported,

From a06a868a0cd96bc51401cdea897313a3f6ad01a0 Mon Sep 17 00:00:00 2001
From: Andrei Botila <andrei.botila@oss.nxp.com>
Date: Fri, 28 Feb 2025 17:43:19 +0200
Subject: [PATCH 1548/2753] net: phy: nxp-c45-tja11xx: add match_phy_device to
 TJA1103/TJA1104

Add .match_phy_device for the existing TJAs to differentiate between
TJA1103 and TJA1104.
TJA1103 and TJA1104 share the same PHY_ID but TJA1104 has MACsec
capabilities while TJA1103 doesn't.

Signed-off-by: Andrei Botila <andrei.botila@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250228154320.2979000-2-andrei.botila@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 54 +++++++++++++++++++++++++++++--
 1 file changed, 52 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 34231b5b91754..4013a17c205ad 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /* NXP C45 PHY driver
- * Copyright 2021-2023 NXP
+ * Copyright 2021-2025 NXP
  * Author: Radu Pirea <radu-nicolae.pirea@oss.nxp.com>
  */
 
@@ -19,6 +19,8 @@
 
 #include "nxp-c45-tja11xx.h"
 
+#define PHY_ID_MASK			GENMASK(31, 4)
+/* Same id: TJA1103, TJA1104 */
 #define PHY_ID_TJA_1103			0x001BB010
 #define PHY_ID_TJA_1120			0x001BB031
 
@@ -1888,6 +1890,30 @@ static void tja1120_nmi_handler(struct phy_device *phydev,
 	}
 }
 
+static int nxp_c45_macsec_ability(struct phy_device *phydev)
+{
+	bool macsec_ability;
+	int phy_abilities;
+
+	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_PORT_ABILITIES);
+	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+
+	return macsec_ability;
+}
+
+static int tja1103_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
+	       !nxp_c45_macsec_ability(phydev);
+}
+
+static int tja1104_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1103, PHY_ID_MASK) &&
+	       nxp_c45_macsec_ability(phydev);
+}
+
 static const struct nxp_c45_regmap tja1120_regmap = {
 	.vend1_ptp_clk_period	= 0x1020,
 	.vend1_event_msg_filt	= 0x9010,
@@ -1958,7 +1984,6 @@ static const struct nxp_c45_phy_data tja1120_phy_data = {
 
 static struct phy_driver nxp_c45_driver[] = {
 	{
-		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1103),
 		.name			= "NXP C45 TJA1103",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1103_phy_data,
@@ -1980,6 +2005,31 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1103_match_phy_device,
+	},
+	{
+		.name			= "NXP C45 TJA1104",
+		.get_features		= nxp_c45_get_features,
+		.driver_data		= &tja1103_phy_data,
+		.probe			= nxp_c45_probe,
+		.soft_reset		= nxp_c45_soft_reset,
+		.config_aneg		= genphy_c45_config_aneg,
+		.config_init		= nxp_c45_config_init,
+		.config_intr		= tja1103_config_intr,
+		.handle_interrupt	= nxp_c45_handle_interrupt,
+		.read_status		= genphy_c45_read_status,
+		.suspend		= genphy_c45_pma_suspend,
+		.resume			= genphy_c45_pma_resume,
+		.get_sset_count		= nxp_c45_get_sset_count,
+		.get_strings		= nxp_c45_get_strings,
+		.get_stats		= nxp_c45_get_stats,
+		.cable_test_start	= nxp_c45_cable_test_start,
+		.cable_test_get_status	= nxp_c45_cable_test_get_status,
+		.set_loopback		= genphy_c45_loopback,
+		.get_sqi		= nxp_c45_get_sqi,
+		.get_sqi_max		= nxp_c45_get_sqi_max,
+		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1104_match_phy_device,
 	},
 	{
 		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),

From 7215e9375694dbb2306082b516d824b9335fa409 Mon Sep 17 00:00:00 2001
From: Andrei Botila <andrei.botila@oss.nxp.com>
Date: Fri, 28 Feb 2025 17:43:20 +0200
Subject: [PATCH 1549/2753] net: phy: nxp-c45-tja11xx: add support for TJA1121

Add support for TJA1121 which is based on TJA1120 but with
additional MACsec IP.

Signed-off-by: Andrei Botila <andrei.botila@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250228154320.2979000-3-andrei.botila@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Kconfig           |  2 +-
 drivers/net/phy/nxp-c45-tja11xx.c | 40 ++++++++++++++++++++++++++++++-
 2 files changed, 40 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig
index 41c15a2c20379..d29f9f7fd2e11 100644
--- a/drivers/net/phy/Kconfig
+++ b/drivers/net/phy/Kconfig
@@ -328,7 +328,7 @@ config NXP_C45_TJA11XX_PHY
 	depends on MACSEC || !MACSEC
 	help
 	  Enable support for NXP C45 TJA11XX PHYs.
-	  Currently supports the TJA1103, TJA1104 and TJA1120 PHYs.
+	  Currently supports the TJA1103, TJA1104, TJA1120 and TJA1121 PHYs.
 
 config NXP_TJA11XX_PHY
 	tristate "NXP TJA11xx PHYs support"
diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 4013a17c205ad..63945fe58227e 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -22,6 +22,7 @@
 #define PHY_ID_MASK			GENMASK(31, 4)
 /* Same id: TJA1103, TJA1104 */
 #define PHY_ID_TJA_1103			0x001BB010
+/* Same id: TJA1120, TJA1121 */
 #define PHY_ID_TJA_1120			0x001BB031
 
 #define VEND1_DEVICE_CONTROL		0x0040
@@ -1914,6 +1915,18 @@ static int tja1104_match_phy_device(struct phy_device *phydev)
 	       nxp_c45_macsec_ability(phydev);
 }
 
+static int tja1120_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, PHY_ID_MASK) &&
+	       !nxp_c45_macsec_ability(phydev);
+}
+
+static int tja1121_match_phy_device(struct phy_device *phydev)
+{
+	return phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, PHY_ID_MASK) &&
+	       nxp_c45_macsec_ability(phydev);
+}
+
 static const struct nxp_c45_regmap tja1120_regmap = {
 	.vend1_ptp_clk_period	= 0x1020,
 	.vend1_event_msg_filt	= 0x9010,
@@ -2032,7 +2045,6 @@ static struct phy_driver nxp_c45_driver[] = {
 		.match_phy_device	= tja1104_match_phy_device,
 	},
 	{
-		PHY_ID_MATCH_MODEL(PHY_ID_TJA_1120),
 		.name			= "NXP C45 TJA1120",
 		.get_features		= nxp_c45_get_features,
 		.driver_data		= &tja1120_phy_data,
@@ -2055,6 +2067,32 @@ static struct phy_driver nxp_c45_driver[] = {
 		.get_sqi		= nxp_c45_get_sqi,
 		.get_sqi_max		= nxp_c45_get_sqi_max,
 		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1120_match_phy_device,
+	},
+	{
+		.name			= "NXP C45 TJA1121",
+		.get_features		= nxp_c45_get_features,
+		.driver_data		= &tja1120_phy_data,
+		.probe			= nxp_c45_probe,
+		.soft_reset		= nxp_c45_soft_reset,
+		.config_aneg		= genphy_c45_config_aneg,
+		.config_init		= nxp_c45_config_init,
+		.config_intr		= tja1120_config_intr,
+		.handle_interrupt	= nxp_c45_handle_interrupt,
+		.read_status		= genphy_c45_read_status,
+		.link_change_notify	= tja1120_link_change_notify,
+		.suspend		= genphy_c45_pma_suspend,
+		.resume			= genphy_c45_pma_resume,
+		.get_sset_count		= nxp_c45_get_sset_count,
+		.get_strings		= nxp_c45_get_strings,
+		.get_stats		= nxp_c45_get_stats,
+		.cable_test_start	= nxp_c45_cable_test_start,
+		.cable_test_get_status	= nxp_c45_cable_test_get_status,
+		.set_loopback		= genphy_c45_loopback,
+		.get_sqi		= nxp_c45_get_sqi,
+		.get_sqi_max		= nxp_c45_get_sqi_max,
+		.remove			= nxp_c45_remove,
+		.match_phy_device	= tja1121_match_phy_device,
 	},
 };
 

From e4c4522390c90f9ef2d3491e9eb5f19a6fac00e2 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Fri, 28 Feb 2025 18:32:50 +0100
Subject: [PATCH 1550/2753] dt-bindings: net: Convert fsl,gianfar-{mdio,tbi} to
 YAML
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Move the information related to the Freescale Gianfar (TSEC) MDIO bus
and the Ten-Bit Interface (TBI) from fsl-tsec-phy.txt to a new binding
file in YAML format, fsl,gianfar-mdio.yaml.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250228-gianfar-yaml-v2-1-6beeefbd4818@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../bindings/net/fsl,gianfar-mdio.yaml        | 113 ++++++++++++++++++
 .../devicetree/bindings/net/fsl-tsec-phy.txt  |  41 +------
 2 files changed, 115 insertions(+), 39 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml

diff --git a/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml b/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
new file mode 100644
index 0000000000000..22369771c1361
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
@@ -0,0 +1,113 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/fsl,gianfar-mdio.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale Gianfar (TSEC) MDIO Device
+
+description:
+  This binding describes the MDIO is a bus to which the PHY devices are
+  connected. For each device that exists on this bus, a child node should be
+  created.
+
+  As of this writing, every TSEC is associated with an internal Ten-Bit
+  Interface (TBI) PHY. This PHY is accessed through the local MDIO bus. These
+  buses are defined similarly to the mdio buses, except they are compatible
+  with "fsl,gianfar-tbi". The TBI PHYs underneath them are similar to normal
+  PHYs, but the reg property is considered instructive, rather than
+  descriptive. The reg property should be chosen so it doesn't interfere with
+  other PHYs on the bus.
+
+maintainers:
+  - J. Neuschäfer <j.ne@posteo.net>
+
+# This is needed to distinguish gianfar.yaml and gianfar-mdio.yaml, because
+# both use compatible = "gianfar" (with different device_type values)
+select:
+  oneOf:
+    - properties:
+        compatible:
+          contains:
+            const: gianfar
+        device_type:
+          const: mdio
+      required:
+        - device_type
+
+    - properties:
+        compatible:
+          contains:
+            enum:
+              - fsl,gianfar-tbi
+              - fsl,gianfar-mdio
+              - fsl,etsec2-tbi
+              - fsl,etsec2-mdio
+              - fsl,ucc-mdio
+              - ucc_geth_phy
+
+  required:
+    - compatible
+
+properties:
+  compatible:
+    enum:
+      - fsl,gianfar-tbi
+      - fsl,gianfar-mdio
+      - fsl,etsec2-tbi
+      - fsl,etsec2-mdio
+      - fsl,ucc-mdio
+      - gianfar
+      - ucc_geth_phy
+
+  reg:
+    minItems: 1
+    items:
+      - description:
+          Offset and length of the register set for the device
+
+      - description:
+          Optionally, the offset and length of the TBIPA register (TBI PHY
+          address register). If TBIPA register is not specified, the driver
+          will attempt to infer it from the register set specified (your
+          mileage may vary).
+
+  device_type:
+    const: mdio
+
+required:
+  - reg
+  - "#address-cells"
+  - "#size-cells"
+
+allOf:
+  - $ref: mdio.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: ucc_geth_phy
+    then:
+      required:
+        - device_type
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    soc {
+        #address-cells = <1>;
+        #size-cells = <1>;
+
+        mdio@24520 {
+            reg = <0x24520 0x20>;
+            compatible = "fsl,gianfar-mdio";
+            #address-cells = <1>;
+            #size-cells = <0>;
+
+            ethernet-phy@0 {
+                reg = <0>;
+            };
+        };
+    };
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index 9c9668c1b6a24..0e55e0af7d6f5 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -1,47 +1,10 @@
 * MDIO IO device
 
-The MDIO is a bus to which the PHY devices are connected.  For each
-device that exists on this bus, a child node should be created.  See
-the definition of the PHY node in booting-without-of.txt for an example
-of how to define a PHY.
-
-Required properties:
-  - reg : Offset and length of the register set for the device, and optionally
-          the offset and length of the TBIPA register (TBI PHY address
-	  register).  If TBIPA register is not specified, the driver will
-	  attempt to infer it from the register set specified (your mileage may
-	  vary).
-  - compatible : Should define the compatible device type for the
-    mdio. Currently supported strings/devices are:
-	- "fsl,gianfar-tbi"
-	- "fsl,gianfar-mdio"
-	- "fsl,etsec2-tbi"
-	- "fsl,etsec2-mdio"
-	- "fsl,ucc-mdio"
-	- "fsl,fman-mdio"
-    When device_type is "mdio", the following strings are also considered:
-	- "gianfar"
-	- "ucc_geth_phy"
-
-Example:
-
-	mdio@24520 {
-		reg = <24520 20>;
-		compatible = "fsl,gianfar-mdio";
-
-		ethernet-phy@0 {
-			......
-		};
-	};
+Refer to Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
 
 * TBI Internal MDIO bus
 
-As of this writing, every tsec is associated with an internal TBI PHY.
-This PHY is accessed through the local MDIO bus.  These buses are defined
-similarly to the mdio buses, except they are compatible with "fsl,gianfar-tbi".
-The TBI PHYs underneath them are similar to normal PHYs, but the reg property
-is considered instructive, rather than descriptive.  The reg property should
-be chosen so it doesn't interfere with other PHYs on the bus.
+Refer to Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
 
 * Gianfar-compatible ethernet nodes
 

From 0386e29e60bdb0985f4bdf1c4a7fadebdef724be Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Fri, 28 Feb 2025 18:32:51 +0100
Subject: [PATCH 1551/2753] dt-bindings: net: fsl,gianfar-mdio: Update
 information about TBI
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When this binding was originally written, all known TSEC Ethernet
controllers had a Ten-Bit Interface (TBI). However, some datasheets such
as for the MPC8315E suggest that this is not universally true:

  The eTSECs do not support TBI, GMII, and FIFO operating modes, so all
  references to these interfaces and features should be ignored for this
  device.

Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Link: https://patch.msgid.link/20250228-gianfar-yaml-v2-2-6beeefbd4818@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/fsl,gianfar-mdio.yaml   | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml b/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
index 22369771c1361..03c819bc701be 100644
--- a/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
+++ b/Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
@@ -11,13 +11,12 @@ description:
   connected. For each device that exists on this bus, a child node should be
   created.
 
-  As of this writing, every TSEC is associated with an internal Ten-Bit
-  Interface (TBI) PHY. This PHY is accessed through the local MDIO bus. These
-  buses are defined similarly to the mdio buses, except they are compatible
-  with "fsl,gianfar-tbi". The TBI PHYs underneath them are similar to normal
-  PHYs, but the reg property is considered instructive, rather than
-  descriptive. The reg property should be chosen so it doesn't interfere with
-  other PHYs on the bus.
+  Some TSECs are associated with an internal Ten-Bit Interface (TBI) PHY. This
+  PHY is accessed through the local MDIO bus. These buses are defined similarly
+  to the mdio buses, except they are compatible with "fsl,gianfar-tbi". The TBI
+  PHYs underneath them are similar to normal PHYs, but the reg property is
+  considered instructive, rather than descriptive. The reg property should be
+  chosen so it doesn't interfere with other PHYs on the bus.
 
 maintainers:
   - J. Neuschäfer <j.ne@posteo.net>

From a70fdd936818c2c12b8c2dd04ce8586c31837d9a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=2E=20Neusch=C3=A4fer?= <j.ne@posteo.net>
Date: Fri, 28 Feb 2025 18:32:52 +0100
Subject: [PATCH 1552/2753] dt-bindings: net: Convert fsl,gianfar to YAML
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a binding for the "Gianfar" ethernet controller, also known as
TSEC/eTSEC.

Signed-off-by: J. Neuschäfer <j.ne@posteo.net>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://patch.msgid.link/20250228-gianfar-yaml-v2-3-6beeefbd4818@posteo.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/fsl,gianfar.yaml  | 248 ++++++++++++++++++
 .../devicetree/bindings/net/fsl-tsec-phy.txt  |  39 +--
 2 files changed, 249 insertions(+), 38 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/net/fsl,gianfar.yaml

diff --git a/Documentation/devicetree/bindings/net/fsl,gianfar.yaml b/Documentation/devicetree/bindings/net/fsl,gianfar.yaml
new file mode 100644
index 0000000000000..f92f284aa05b0
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/fsl,gianfar.yaml
@@ -0,0 +1,248 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/fsl,gianfar.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Freescale Three-Speed Ethernet Controller (TSEC), "Gianfar"
+
+maintainers:
+  - J. Neuschäfer <j.ne@posteo.net>
+
+# This is needed to distinguish gianfar.yaml and gianfar-mdio.yaml, because
+# both use compatible = "gianfar" (with different device_type values)
+select:
+  oneOf:
+    - properties:
+        compatible:
+          contains:
+            const: gianfar
+        device_type:
+          const: network
+      required:
+        - device_type
+
+    - properties:
+        compatible:
+          const: fsl,etsec2
+
+  required:
+    - compatible
+
+properties:
+  compatible:
+    enum:
+      - gianfar
+      - fsl,etsec2
+
+  device_type:
+    const: network
+
+  model:
+    enum:
+      - FEC
+      - TSEC
+      - eTSEC
+
+  reg:
+    maxItems: 1
+
+  ranges: true
+
+  "#address-cells":
+    enum: [ 1, 2 ]
+
+  "#size-cells":
+    enum: [ 1, 2 ]
+
+  cell-index:
+    $ref: /schemas/types.yaml#/definitions/uint32
+
+  interrupts:
+    minItems: 1
+    items:
+      - description: Transmit interrupt or single combined interrupt
+      - description: Receive interrupt
+      - description: Error interrupt
+
+  dma-coherent: true
+
+  fsl,magic-packet:
+    type: boolean
+    description:
+      If present, indicates that the hardware supports waking up via magic packet.
+
+  fsl,wake-on-filer:
+    type: boolean
+    description:
+      If present, indicates that the hardware supports waking up by Filer
+      General Purpose Interrupt (FGPI) asserted on the Rx int line. This is
+      an advanced power management capability allowing certain packet types
+      (user) defined by filer rules to wake up the system.
+
+  bd-stash:
+    type: boolean
+    description:
+      If present, indicates that the hardware supports stashing buffer
+      descriptors in the L2.
+
+  rx-stash-len:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Denotes the number of bytes of a received buffer to stash in the L2.
+
+  rx-stash-idx:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description:
+      Denotes the index of the first byte from the received buffer to stash in
+      the L2.
+
+  fsl,num_rx_queues:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: Number of receive queues
+    const: 8
+
+  fsl,num_tx_queues:
+    $ref: /schemas/types.yaml#/definitions/uint32
+    description: Number of transmit queues
+    const: 8
+
+  tbi-handle:
+    $ref: /schemas/types.yaml#/definitions/phandle
+    description: Reference (phandle) to the TBI node
+
+required:
+  - compatible
+  - model
+
+patternProperties:
+  "^mdio@[0-9a-f]+$":
+    $ref: /schemas/net/fsl,gianfar-mdio.yaml#
+
+allOf:
+  - $ref: ethernet-controller.yaml#
+
+  # eTSEC2 controller nodes have "queue group" subnodes and don't need a "reg"
+  # property.
+  - if:
+      properties:
+        compatible:
+          contains:
+            const: fsl,etsec2
+    then:
+      patternProperties:
+        "^queue-group@[0-9a-f]+$":
+          type: object
+
+          properties:
+            reg:
+              maxItems: 1
+
+            interrupts:
+              items:
+                - description: Transmit interrupt
+                - description: Receive interrupt
+                - description: Error interrupt
+
+          required:
+            - reg
+            - interrupts
+
+          additionalProperties: false
+    else:
+      required:
+        - reg
+
+  # TSEC and eTSEC devices require three interrupts
+  - if:
+      properties:
+        model:
+          contains:
+            enum: [ TSEC, eTSEC ]
+    then:
+      properties:
+        interrupts:
+          items:
+            - description: Transmit interrupt
+            - description: Receive interrupt
+            - description: Error interrupt
+
+
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    ethernet@24000 {
+        device_type = "network";
+        model = "TSEC";
+        compatible = "gianfar";
+        reg = <0x24000 0x1000>;
+        local-mac-address = [ 00 00 00 00 00 00 ];
+        interrupts = <29 2>, <30 2>, <34 2>;
+        interrupt-parent = <&mpic>;
+        phy-handle = <&phy0>;
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    ethernet@24000 {
+        compatible = "gianfar";
+        reg = <0x24000 0x1000>;
+        ranges = <0x0 0x24000 0x1000>;
+        #address-cells = <1>;
+        #size-cells = <1>;
+        cell-index = <0>;
+        device_type = "network";
+        model = "eTSEC";
+        local-mac-address = [ 00 00 00 00 00 00 ];
+        interrupts = <32 IRQ_TYPE_LEVEL_LOW>,
+                     <33 IRQ_TYPE_LEVEL_LOW>,
+                     <34 IRQ_TYPE_LEVEL_LOW>;
+        interrupt-parent = <&ipic>;
+
+        mdio@520 {
+            #address-cells = <1>;
+            #size-cells = <0>;
+            compatible = "fsl,gianfar-mdio";
+            reg = <0x520 0x20>;
+        };
+    };
+
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+
+    bus {
+        #address-cells = <2>;
+        #size-cells = <2>;
+
+        ethernet {
+            compatible = "fsl,etsec2";
+            ranges;
+            device_type = "network";
+            #address-cells = <2>;
+            #size-cells = <2>;
+            interrupt-parent = <&gic>;
+            model = "eTSEC";
+            fsl,magic-packet;
+            dma-coherent;
+
+            queue-group@2d10000 {
+                reg = <0x0 0x2d10000 0x0 0x1000>;
+                interrupts = <GIC_SPI 144 IRQ_TYPE_LEVEL_HIGH>,
+                             <GIC_SPI 145 IRQ_TYPE_LEVEL_HIGH>,
+                             <GIC_SPI 146 IRQ_TYPE_LEVEL_HIGH>;
+            };
+
+            queue-group@2d14000  {
+                reg = <0x0 0x2d14000 0x0 0x1000>;
+                interrupts = <GIC_SPI 147 IRQ_TYPE_LEVEL_HIGH>,
+                             <GIC_SPI 148 IRQ_TYPE_LEVEL_HIGH>,
+                             <GIC_SPI 149 IRQ_TYPE_LEVEL_HIGH>;
+            };
+        };
+    };
+
+...
diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
index 0e55e0af7d6f5..b18bb4c997ea3 100644
--- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
+++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt
@@ -8,44 +8,7 @@ Refer to Documentation/devicetree/bindings/net/fsl,gianfar-mdio.yaml
 
 * Gianfar-compatible ethernet nodes
 
-Properties:
-
-  - device_type : Should be "network"
-  - model : Model of the device.  Can be "TSEC", "eTSEC", or "FEC"
-  - compatible : Should be "gianfar"
-  - reg : Offset and length of the register set for the device
-  - interrupts : For FEC devices, the first interrupt is the device's
-    interrupt.  For TSEC and eTSEC devices, the first interrupt is
-    transmit, the second is receive, and the third is error.
-  - phy-handle : See ethernet.txt file in the same directory.
-  - fixed-link : See fixed-link.txt in the same directory.
-  - phy-connection-type : See ethernet.txt file in the same directory.
-    This property is only really needed if the connection is of type
-    "rgmii-id", as all other connection types are detected by hardware.
-  - fsl,magic-packet : If present, indicates that the hardware supports
-    waking up via magic packet.
-  - fsl,wake-on-filer : If present, indicates that the hardware supports
-    waking up by Filer General Purpose Interrupt (FGPI) asserted on the
-    Rx int line.  This is an advanced power management capability allowing
-    certain packet types (user) defined by filer rules to wake up the system.
-  - bd-stash : If present, indicates that the hardware supports stashing
-    buffer descriptors in the L2.
-  - rx-stash-len : Denotes the number of bytes of a received buffer to stash
-    in the L2.
-  - rx-stash-idx : Denotes the index of the first byte from the received
-    buffer to stash in the L2.
-
-Example:
-	ethernet@24000 {
-		device_type = "network";
-		model = "TSEC";
-		compatible = "gianfar";
-		reg = <0x24000 0x1000>;
-		local-mac-address = [ 00 E0 0C 00 73 00 ];
-		interrupts = <29 2 30 2 34 2>;
-		interrupt-parent = <&mpic>;
-		phy-handle = <&phy0>
-	};
+Refer to Documentation/devicetree/bindings/net/fsl,gianfar.yaml
 
 * Gianfar PTP clock nodes
 

From 56bcc6ecff8fdc06258c637226986ed522027ca5 Mon Sep 17 00:00:00 2001
From: Lee Trager <lee@trager.us>
Date: Fri, 28 Feb 2025 11:15:26 -0800
Subject: [PATCH 1553/2753] eth: fbnic: Prepend TSENE FW fields with FBNIC_FW

All other firmware fields are prepended with FBNIC_FW. Update TSENE fields
to follow the same format.

Signed-off-by: Lee Trager <lee@trager.us>
Link: https://patch.msgid.link/20250228191935.3953712-2-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c | 16 ++++++++--------
 drivers/net/ethernet/meta/fbnic/fbnic_fw.h |  8 ++++----
 2 files changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index bbc7c1c0c37ef..76a225f017186 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -743,9 +743,9 @@ int fbnic_fw_xmit_tsene_read_msg(struct fbnic_dev *fbd,
 }
 
 static const struct fbnic_tlv_index fbnic_tsene_read_resp_index[] = {
-	FBNIC_TLV_ATTR_S32(FBNIC_TSENE_THERM),
-	FBNIC_TLV_ATTR_S32(FBNIC_TSENE_VOLT),
-	FBNIC_TLV_ATTR_S32(FBNIC_TSENE_ERROR),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_THERM),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_VOLT),
+	FBNIC_TLV_ATTR_S32(FBNIC_FW_TSENE_ERROR),
 	FBNIC_TLV_ATTR_LAST
 };
 
@@ -762,21 +762,21 @@ static int fbnic_fw_parse_tsene_read_resp(void *opaque,
 	if (!cmpl_data)
 		return -EINVAL;
 
-	if (results[FBNIC_TSENE_ERROR]) {
-		err = fbnic_tlv_attr_get_unsigned(results[FBNIC_TSENE_ERROR]);
+	if (results[FBNIC_FW_TSENE_ERROR]) {
+		err = fbnic_tlv_attr_get_unsigned(results[FBNIC_FW_TSENE_ERROR]);
 		if (err)
 			goto exit_complete;
 	}
 
-	if (!results[FBNIC_TSENE_THERM] || !results[FBNIC_TSENE_VOLT]) {
+	if (!results[FBNIC_FW_TSENE_THERM] || !results[FBNIC_FW_TSENE_VOLT]) {
 		err = -EINVAL;
 		goto exit_complete;
 	}
 
 	cmpl_data->u.tsene.millidegrees =
-		fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_THERM]);
+		fbnic_tlv_attr_get_signed(results[FBNIC_FW_TSENE_THERM]);
 	cmpl_data->u.tsene.millivolts =
-		fbnic_tlv_attr_get_signed(results[FBNIC_TSENE_VOLT]);
+		fbnic_tlv_attr_get_signed(results[FBNIC_FW_TSENE_VOLT]);
 
 exit_complete:
 	cmpl_data->result = err;
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index fe68333d51b18..a3618e7826c25 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -139,10 +139,10 @@ enum {
 };
 
 enum {
-	FBNIC_TSENE_THERM			= 0x0,
-	FBNIC_TSENE_VOLT			= 0x1,
-	FBNIC_TSENE_ERROR			= 0x2,
-	FBNIC_TSENE_MSG_MAX
+	FBNIC_FW_TSENE_THERM			= 0x0,
+	FBNIC_FW_TSENE_VOLT			= 0x1,
+	FBNIC_FW_TSENE_ERROR			= 0x2,
+	FBNIC_FW_TSENE_MSG_MAX
 };
 
 enum {

From e5cf5107c9e4286377d9adae114e524787cbe104 Mon Sep 17 00:00:00 2001
From: Lee Trager <lee@trager.us>
Date: Fri, 28 Feb 2025 11:15:27 -0800
Subject: [PATCH 1554/2753] eth: fbnic: Update fbnic_tlv_attr_get_string() to
 work like nla_strscpy()

Allow fbnic_tlv_attr_get_string() to return an error code. In the event the
source mailbox attribute is missing return -EINVAL. Like nla_strscpy() return
-E2BIG when the source string is larger than the destination string. In this
case the amount of data copied is equal to dstsize.

Signed-off-by: Lee Trager <lee@trager.us>
Link: https://patch.msgid.link/20250228191935.3953712-3-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_tlv.c | 39 ++++++++++++++++-----
 drivers/net/ethernet/meta/fbnic/fbnic_tlv.h |  4 +--
 2 files changed, 32 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
index 2a174ab062a3d..400fb6c800532 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
@@ -233,19 +233,40 @@ s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr)
 /**
  * fbnic_tlv_attr_get_string - Retrieve string value from result
  * @attr: Attribute to retrieve data from
- * @str: Pointer to an allocated string to store the data
- * @max_size: The maximum size which can be in str
+ * @dst: Pointer to an allocated string to store the data
+ * @dstsize: The maximum size which can be in dst
  *
- * Return: the size of the string read from firmware
+ * Return: the size of the string read from firmware or negative error.
  **/
-size_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *str,
-				 size_t max_size)
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize)
 {
-	max_size = min_t(size_t, max_size,
-			 (le16_to_cpu(attr->hdr.len) * 4) - sizeof(*attr));
-	memcpy(str, &attr->value, max_size);
+	size_t srclen, len;
+	ssize_t ret;
 
-	return max_size;
+	if (!attr)
+		return -EINVAL;
+
+	if (dstsize == 0)
+		return -E2BIG;
+
+	srclen = le16_to_cpu(attr->hdr.len) - sizeof(*attr);
+	if (srclen > 0 && attr->value[srclen - 1] == '\0')
+		srclen--;
+
+	if (srclen >= dstsize) {
+		len = dstsize - 1;
+		ret = -E2BIG;
+	} else {
+		len = srclen;
+		ret = len;
+	}
+
+	memcpy(dst, &attr->value, len);
+	/* Zero pad end of dst. */
+	memset(dst + len, 0, dstsize - len);
+
+	return ret;
 }
 
 /**
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
index 67300ab443532..b29ed26495852 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
@@ -116,8 +116,8 @@ static inline bool fbnic_tlv_attr_get_bool(struct fbnic_tlv_msg *attr)
 
 u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr);
 s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr);
-size_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *str,
-				 size_t max_size);
+ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
+				  size_t dstsize);
 
 #define get_unsigned_result(id, location) \
 do { \

From 8cb3e49b23cc673efcb844488aeb46ff4c615824 Mon Sep 17 00:00:00 2001
From: Lee Trager <lee@trager.us>
Date: Fri, 28 Feb 2025 11:15:28 -0800
Subject: [PATCH 1555/2753] eth: fbnic: Replace firmware field macros

Replace the firmware field macros with new macros which follow typical
kernel standards. No variables are required to be predefined for use and
results are now returned. These macros are prefixed with fta or fbnic
TLV attribute.

Signed-off-by: Lee Trager <lee@trager.us>
Link: https://patch.msgid.link/20250228191935.3953712-4-lee@trager.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_fw.c  | 101 ++++++++++----------
 drivers/net/ethernet/meta/fbnic/fbnic_tlv.c |  16 +++-
 drivers/net/ethernet/meta/fbnic/fbnic_tlv.h |  35 ++-----
 3 files changed, 70 insertions(+), 82 deletions(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
index 76a225f017186..88db3dacb9405 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.c
@@ -494,16 +494,13 @@ static int fbnic_fw_parse_bmc_addrs(u8 bmc_mac_addr[][ETH_ALEN],
 
 static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 {
-	u32 active_slot = 0, all_multi = 0;
+	u32 all_multi = 0, version = 0;
 	struct fbnic_dev *fbd = opaque;
-	u32 speed = 0, fec = 0;
-	size_t commit_size = 0;
 	bool bmc_present;
 	int err;
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_VERSION,
-			    fbd->fw_cap.running.mgmt.version);
-
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_VERSION);
+	fbd->fw_cap.running.mgmt.version = version;
 	if (!fbd->fw_cap.running.mgmt.version)
 		return -EINVAL;
 
@@ -524,43 +521,41 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		return -EINVAL;
 	}
 
-	get_string_result(FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-	if (!commit_size)
+	if (fta_get_str(results, FBNIC_FW_CAP_RESP_VERSION_COMMIT_STR,
+			fbd->fw_cap.running.mgmt.commit,
+			FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE) <= 0)
 		dev_warn(fbd->dev, "Firmware did not send mgmt commit!\n");
 
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_VERSION,
-			    fbd->fw_cap.stored.mgmt.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.mgmt.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_CMRT_VERSION,
-			    fbd->fw_cap.running.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.running.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION,
-			    fbd->fw_cap.stored.bootloader.version);
-	get_string_result(FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.bootloader.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_UEFI_VERSION,
-			    fbd->fw_cap.stored.undi.version);
-	get_string_result(FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR, commit_size,
-			  fbd->fw_cap.stored.undi.commit,
-			  FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT, active_slot);
-	fbd->fw_cap.active_slot = active_slot;
-
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_SPEED, speed);
-	get_unsigned_result(FBNIC_FW_CAP_RESP_FW_LINK_FEC, fec);
-	fbd->fw_cap.link_speed = speed;
-	fbd->fw_cap.link_fec = fec;
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_VERSION);
+	fbd->fw_cap.stored.mgmt.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_COMMIT_STR,
+		    fbd->fw_cap.stored.mgmt.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_CMRT_VERSION);
+	fbd->fw_cap.running.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_CMRT_COMMIT_STR,
+		    fbd->fw_cap.running.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_STORED_CMRT_VERSION);
+	fbd->fw_cap.stored.bootloader.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_STORED_CMRT_COMMIT_STR,
+		    fbd->fw_cap.stored.bootloader.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	version = fta_get_uint(results, FBNIC_FW_CAP_RESP_UEFI_VERSION);
+	fbd->fw_cap.stored.undi.version = version;
+	fta_get_str(results, FBNIC_FW_CAP_RESP_UEFI_COMMIT_STR,
+		    fbd->fw_cap.stored.undi.commit,
+		    FBNIC_FW_CAP_RESP_COMMIT_MAX_SIZE);
+
+	fbd->fw_cap.active_slot =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_ACTIVE_FW_SLOT);
+	fbd->fw_cap.link_speed =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_SPEED);
+	fbd->fw_cap.link_fec =
+		fta_get_uint(results, FBNIC_FW_CAP_RESP_FW_LINK_FEC);
 
 	bmc_present = !!results[FBNIC_FW_CAP_RESP_BMC_PRESENT];
 	if (bmc_present) {
@@ -575,7 +570,8 @@ static int fbnic_fw_parse_cap_resp(void *opaque, struct fbnic_tlv_msg **results)
 		if (err)
 			return err;
 
-		get_unsigned_result(FBNIC_FW_CAP_RESP_BMC_ALL_MULTI, all_multi);
+		all_multi =
+			fta_get_uint(results, FBNIC_FW_CAP_RESP_BMC_ALL_MULTI);
 	} else {
 		memset(fbd->fw_cap.bmc_mac_addr, 0,
 		       sizeof(fbd->fw_cap.bmc_mac_addr));
@@ -754,32 +750,31 @@ static int fbnic_fw_parse_tsene_read_resp(void *opaque,
 {
 	struct fbnic_fw_completion *cmpl_data;
 	struct fbnic_dev *fbd = opaque;
+	s32 err_resp;
 	int err = 0;
 
 	/* Verify we have a completion pointer to provide with data */
 	cmpl_data = fbnic_fw_get_cmpl_by_type(fbd,
 					      FBNIC_TLV_MSG_ID_TSENE_READ_RESP);
 	if (!cmpl_data)
-		return -EINVAL;
+		return -ENOSPC;
 
-	if (results[FBNIC_FW_TSENE_ERROR]) {
-		err = fbnic_tlv_attr_get_unsigned(results[FBNIC_FW_TSENE_ERROR]);
-		if (err)
-			goto exit_complete;
-	}
+	err_resp = fta_get_sint(results, FBNIC_FW_TSENE_ERROR);
+	if (err_resp)
+		goto msg_err;
 
 	if (!results[FBNIC_FW_TSENE_THERM] || !results[FBNIC_FW_TSENE_VOLT]) {
 		err = -EINVAL;
-		goto exit_complete;
+		goto msg_err;
 	}
 
 	cmpl_data->u.tsene.millidegrees =
-		fbnic_tlv_attr_get_signed(results[FBNIC_FW_TSENE_THERM]);
+		fta_get_sint(results, FBNIC_FW_TSENE_THERM);
 	cmpl_data->u.tsene.millivolts =
-		fbnic_tlv_attr_get_signed(results[FBNIC_FW_TSENE_VOLT]);
+		fta_get_sint(results, FBNIC_FW_TSENE_VOLT);
 
-exit_complete:
-	cmpl_data->result = err;
+msg_err:
+	cmpl_data->result = err_resp ? : err;
 	complete(&cmpl_data->done);
 	fbnic_fw_put_cmpl(cmpl_data);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
index 400fb6c800532..d558d176e0dfc 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
@@ -196,13 +196,17 @@ int fbnic_tlv_attr_put_string(struct fbnic_tlv_msg *msg, u16 attr_id,
 /**
  * fbnic_tlv_attr_get_unsigned - Retrieve unsigned value from result
  * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
  *
  * Return: unsigned 64b value containing integer value
  **/
-u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr)
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def)
 {
 	__le64 le64_value = 0;
 
+	if (!attr)
+		return def;
+
 	memcpy(&le64_value, &attr->value[0],
 	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
 
@@ -212,15 +216,21 @@ u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr)
 /**
  * fbnic_tlv_attr_get_signed - Retrieve signed value from result
  * @attr: Attribute to retrieve data from
+ * @def: The default value if attr is NULL
  *
  * Return: signed 64b value containing integer value
  **/
-s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr)
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def)
 {
-	int shift = (8 + sizeof(*attr) - le16_to_cpu(attr->hdr.len)) * 8;
 	__le64 le64_value = 0;
+	int shift;
 	s64 value;
 
+	if (!attr)
+		return def;
+
+	shift = (8 + sizeof(*attr) - le16_to_cpu(attr->hdr.len)) * 8;
+
 	/* Copy the value and adjust for byte ordering */
 	memcpy(&le64_value, &attr->value[0],
 	       le16_to_cpu(attr->hdr.len) - sizeof(*attr));
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
index b29ed26495852..c34bf87eeec95 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.h
@@ -114,34 +114,10 @@ static inline bool fbnic_tlv_attr_get_bool(struct fbnic_tlv_msg *attr)
 	return !!attr;
 }
 
-u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr);
-s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr);
+u64 fbnic_tlv_attr_get_unsigned(struct fbnic_tlv_msg *attr, u64 def);
+s64 fbnic_tlv_attr_get_signed(struct fbnic_tlv_msg *attr, s64 def);
 ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
 				  size_t dstsize);
-
-#define get_unsigned_result(id, location) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		location = fbnic_tlv_attr_get_unsigned(result); \
-} while (0)
-
-#define get_signed_result(id, location) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		location = fbnic_tlv_attr_get_signed(result); \
-} while (0)
-
-#define get_string_result(id, size, str, max_size) \
-do { \
-	struct fbnic_tlv_msg *result = results[id]; \
-	if (result) \
-		size = fbnic_tlv_attr_get_string(result, str, max_size); \
-} while (0)
-
-#define get_bool(id) (!!(results[id]))
-
 struct fbnic_tlv_msg *fbnic_tlv_msg_alloc(u16 msg_id);
 int fbnic_tlv_attr_put_flag(struct fbnic_tlv_msg *msg, const u16 attr_id);
 int fbnic_tlv_attr_put_value(struct fbnic_tlv_msg *msg, const u16 attr_id,
@@ -170,6 +146,13 @@ int fbnic_tlv_msg_parse(void *opaque, struct fbnic_tlv_msg *msg,
 			const struct fbnic_tlv_parser *parser);
 int fbnic_tlv_parser_error(void *opaque, struct fbnic_tlv_msg **results);
 
+#define fta_get_uint(_results, _id) \
+	fbnic_tlv_attr_get_unsigned(_results[_id], 0)
+#define fta_get_sint(_results, _id) \
+	fbnic_tlv_attr_get_signed(_results[_id], 0)
+#define fta_get_str(_results, _id, _dst, _dstsize) \
+	fbnic_tlv_attr_get_string(_results[_id], _dst, _dstsize)
+
 #define FBNIC_TLV_MSG_ERROR \
 	FBNIC_TLV_PARSER(UNKNOWN, NULL, fbnic_tlv_parser_error)
 #endif /* _FBNIC_TLV_H_ */

From 95d0d094ba26432ec467e2260f4bf553053f1f8f Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Sat, 1 Mar 2025 21:55:16 +0800
Subject: [PATCH 1556/2753] ppp: use IFF_NO_QUEUE in virtual interfaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

For PPPoE, PPTP, and PPPoL2TP, the start_xmit() function directly
forwards packets to the underlying network stack and never returns
anything other than 1. So these interfaces do not require a qdisc,
and the IFF_NO_QUEUE flag should be set.

Introduces a direct_xmit flag in struct ppp_channel to indicate when
IFF_NO_QUEUE should be applied. The flag is set in ppp_connect_channel()
for relevant protocols.

While at it, remove the usused latency member from struct ppp_channel.

Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Link: https://patch.msgid.link/20250301135517.695809-1-dqfext@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ppp/ppp_generic.c | 4 ++++
 drivers/net/ppp/pppoe.c       | 1 +
 drivers/net/ppp/pptp.c        | 1 +
 include/linux/ppp_channel.h   | 3 +--
 net/l2tp/l2tp_ppp.c           | 1 +
 5 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index 6220866258fc4..815108c98b78c 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -3493,6 +3493,10 @@ ppp_connect_channel(struct channel *pch, int unit)
 		ret = -ENOTCONN;
 		goto outl;
 	}
+	if (pch->chan->direct_xmit)
+		ppp->dev->priv_flags |= IFF_NO_QUEUE;
+	else
+		ppp->dev->priv_flags &= ~IFF_NO_QUEUE;
 	spin_unlock_bh(&pch->downl);
 	if (pch->file.hdrlen > ppp->file.hdrlen)
 		ppp->file.hdrlen = pch->file.hdrlen;
diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 2ea4f4890d23b..68e631718ab0b 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -693,6 +693,7 @@ static int pppoe_connect(struct socket *sock, struct sockaddr *uservaddr,
 		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
 		po->chan.private = sk;
 		po->chan.ops = &pppoe_chan_ops;
+		po->chan.direct_xmit = true;
 
 		error = ppp_register_net_channel(dev_net(dev), &po->chan);
 		if (error) {
diff --git a/drivers/net/ppp/pptp.c b/drivers/net/ppp/pptp.c
index 689687bd2574b..5feaa70b5f47e 100644
--- a/drivers/net/ppp/pptp.c
+++ b/drivers/net/ppp/pptp.c
@@ -465,6 +465,7 @@ static int pptp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.mtu -= PPTP_HEADER_OVERHEAD;
 
 	po->chan.hdrlen = 2 + sizeof(struct pptp_gre_header);
+	po->chan.direct_xmit = true;
 	error = ppp_register_channel(&po->chan);
 	if (error) {
 		pr_err("PPTP: failed to register PPP channel (%d)\n", error);
diff --git a/include/linux/ppp_channel.h b/include/linux/ppp_channel.h
index 45e6e427ceb8a..f73fbea0dbc23 100644
--- a/include/linux/ppp_channel.h
+++ b/include/linux/ppp_channel.h
@@ -42,8 +42,7 @@ struct ppp_channel {
 	int		hdrlen;		/* amount of headroom channel needs */
 	void		*ppp;		/* opaque to channel */
 	int		speed;		/* transfer rate (bytes/second) */
-	/* the following is not used at present */
-	int		latency;	/* overhead time in milliseconds */
+	bool		direct_xmit;	/* no qdisc, xmit directly */
 };
 
 #ifdef __KERNEL__
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 53baf2dd5d5da..fc5c2fd8f34c7 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -806,6 +806,7 @@ static int pppol2tp_connect(struct socket *sock, struct sockaddr *uservaddr,
 	po->chan.private = sk;
 	po->chan.ops	 = &pppol2tp_chan_ops;
 	po->chan.mtu	 = pppol2tp_tunnel_mtu(tunnel);
+	po->chan.direct_xmit	= true;
 
 	error = ppp_register_net_channel(sock_net(sk), &po->chan);
 	if (error) {

From 637399bf7e77797811adf340090b561a8f9d1213 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Sat, 1 Mar 2025 15:11:13 +0100
Subject: [PATCH 1557/2753] net: ethtool: netlink: Allow NULL nlattrs when
 getting a phy_device

ethnl_req_get_phydev() is used to lookup a phy_device, in the case an
ethtool netlink command targets a specific phydev within a netdev's
topology.

It takes as a parameter a const struct nlattr *header that's used for
error handling :

       if (!phydev) {
               NL_SET_ERR_MSG_ATTR(extack, header,
                                   "no phy matching phyindex");
               return ERR_PTR(-ENODEV);
       }

In the notify path after a ->set operation however, there's no request
attributes available.

The typical callsite for the above function looks like:

	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_XXX_HEADER],
				      info->extack);

So, when tb is NULL (such as in the ethnl notify path), we have a nice
crash.

It turns out that there's only the PLCA command that is in that case, as
the other phydev-specific commands don't have a notification.

This commit fixes the crash by passing the cmd index and the nlattr
array separately, allowing NULL-checking it directly inside the helper.

Fixes: c15e065b46dc ("net: ethtool: Allow passing a phy index for some commands")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Reported-by: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
Link: https://patch.msgid.link/20250301141114.97204-1-maxime.chevallier@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/cabletest.c | 8 ++++----
 net/ethtool/linkstate.c | 2 +-
 net/ethtool/netlink.c   | 6 +++---
 net/ethtool/netlink.h   | 5 +++--
 net/ethtool/phy.c       | 2 +-
 net/ethtool/plca.c      | 6 +++---
 net/ethtool/pse-pd.c    | 4 ++--
 net/ethtool/stats.c     | 2 +-
 net/ethtool/strset.c    | 2 +-
 9 files changed, 19 insertions(+), 18 deletions(-)

diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index f22051f33868a..84096f6b0236e 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -72,8 +72,8 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
-	phydev = ethnl_req_get_phydev(&req_info,
-				      tb[ETHTOOL_A_CABLE_TEST_HEADER],
+	phydev = ethnl_req_get_phydev(&req_info, tb,
+				      ETHTOOL_A_CABLE_TEST_HEADER,
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
@@ -339,8 +339,8 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		goto out_dev_put;
 
 	rtnl_lock();
-	phydev = ethnl_req_get_phydev(&req_info,
-				      tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
+	phydev = ethnl_req_get_phydev(&req_info, tb,
+				      ETHTOOL_A_CABLE_TEST_TDR_HEADER,
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
diff --git a/net/ethtool/linkstate.c b/net/ethtool/linkstate.c
index af19e1bed303f..05a5f72c99fab 100644
--- a/net/ethtool/linkstate.c
+++ b/net/ethtool/linkstate.c
@@ -103,7 +103,7 @@ static int linkstate_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_LINKSTATE_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_LINKSTATE_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev)) {
 		ret = PTR_ERR(phydev);
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index b4c45207fa32e..734849a573691 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -211,7 +211,7 @@ int ethnl_parse_header_dev_get(struct ethnl_req_info *req_info,
 }
 
 struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
-					const struct nlattr *header,
+					struct nlattr **tb, unsigned int header,
 					struct netlink_ext_ack *extack)
 {
 	struct phy_device *phydev;
@@ -225,8 +225,8 @@ struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
 		return req_info->dev->phydev;
 
 	phydev = phy_link_topo_get_phy(req_info->dev, req_info->phy_index);
-	if (!phydev) {
-		NL_SET_ERR_MSG_ATTR(extack, header,
+	if (!phydev && tb) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[header],
 				    "no phy matching phyindex");
 		return ERR_PTR(-ENODEV);
 	}
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index ff69ca0715dea..ec6ab5443a6f2 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -275,7 +275,8 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
  * ethnl_req_get_phydev() - Gets the phy_device targeted by this request,
  *			    if any. Must be called under rntl_lock().
  * @req_info:	The ethnl request to get the phy from.
- * @header:	The netlink header, used for error reporting.
+ * @tb:		The netlink attributes array, for error reporting.
+ * @header:	The netlink header index, used for error reporting.
  * @extack:	The netlink extended ACK, for error reporting.
  *
  * The caller must hold RTNL, until it's done interacting with the returned
@@ -289,7 +290,7 @@ static inline void ethnl_parse_header_dev_put(struct ethnl_req_info *req_info)
  *	   is returned.
  */
 struct phy_device *ethnl_req_get_phydev(const struct ethnl_req_info *req_info,
-					const struct nlattr *header,
+					struct nlattr **tb, unsigned int header,
 					struct netlink_ext_ack *extack);
 
 /**
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index ed8f690f6bac8..e067cc234419d 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -125,7 +125,7 @@ static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
 	struct phy_req_info *req_info = PHY_REQINFO(req_base);
 	struct phy_device *phydev;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PHY_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PHY_HEADER,
 				      extack);
 	if (!phydev)
 		return 0;
diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index d95d92f173a6d..e1f7820a6158f 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -62,7 +62,7 @@ static int plca_get_cfg_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev)) {
@@ -152,7 +152,7 @@ ethnl_set_plca(struct ethnl_req_info *req_info, struct genl_info *info)
 	bool mod = false;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev))
@@ -211,7 +211,7 @@ static int plca_get_status_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PLCA_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PLCA_HEADER,
 				      info->extack);
 	// check that the PHY device is available and connected
 	if (IS_ERR_OR_NULL(phydev)) {
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 2819e2ba6be2d..4f6b99eab2a6c 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -64,7 +64,7 @@ static int pse_prepare_data(const struct ethnl_req_info *req_base,
 	if (ret < 0)
 		return ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_PSE_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PSE_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev))
 		return -ENODEV;
@@ -261,7 +261,7 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_info, tb[ETHTOOL_A_PSE_HEADER],
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PSE_HEADER,
 				      info->extack);
 	ret = ethnl_set_pse_validate(phydev, info);
 	if (ret)
diff --git a/net/ethtool/stats.c b/net/ethtool/stats.c
index 038a2558f0520..3ca8eb2a3b314 100644
--- a/net/ethtool/stats.c
+++ b/net/ethtool/stats.c
@@ -138,7 +138,7 @@ static int stats_prepare_data(const struct ethnl_req_info *req_base,
 	struct phy_device *phydev;
 	int ret;
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_STATS_HEADER],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_STATS_HEADER,
 				      info->extack);
 	if (IS_ERR(phydev))
 		return PTR_ERR(phydev);
diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c
index 6b76c05caba4d..f6a67109beda1 100644
--- a/net/ethtool/strset.c
+++ b/net/ethtool/strset.c
@@ -309,7 +309,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base,
 		return 0;
 	}
 
-	phydev = ethnl_req_get_phydev(req_base, tb[ETHTOOL_A_HEADER_FLAGS],
+	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_HEADER_FLAGS,
 				      info->extack);
 
 	/* phydev can be NULL, check for errors only */

From 254f6b272e3b67bf31c42ee9da62a449d74d1478 Mon Sep 17 00:00:00 2001
From: Daniel Golle <daniel@makrotopia.org>
Date: Sat, 1 Mar 2025 01:41:18 +0000
Subject: [PATCH 1558/2753] dsa: mt7530: Utilize REGMAP_IRQ for interrupt
 handling

Replace the custom IRQ chip handler and mask/unmask functions with
REGMAP_IRQ. This significantly simplifies the code and allows for the
removal of almost all interrupt-related functions from mt7530.c.

Tested on MT7988A built-in switch (MMIO) as well as MT7531AE IC (MDIO).

Signed-off-by: Daniel Golle <daniel@makrotopia.org>
Acked-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/221013c3530b61504599e285c341a993f6188f00.1740792674.git.daniel@makrotopia.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/Kconfig  |   1 +
 drivers/net/dsa/mt7530.c | 236 ++++++++++-----------------------------
 drivers/net/dsa/mt7530.h |   4 -
 3 files changed, 57 insertions(+), 184 deletions(-)

diff --git a/drivers/net/dsa/Kconfig b/drivers/net/dsa/Kconfig
index 2d10b4d6cfbbe..bb9812b3b0e82 100644
--- a/drivers/net/dsa/Kconfig
+++ b/drivers/net/dsa/Kconfig
@@ -37,6 +37,7 @@ config NET_DSA_LANTIQ_GSWIP
 config NET_DSA_MT7530
 	tristate "MediaTek MT7530 and MT7531 Ethernet switch support"
 	select NET_DSA_TAG_MTK
+	select REGMAP_IRQ
 	imply NET_DSA_MT7530_MDIO
 	imply NET_DSA_MT7530_MMIO
 	help
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index aaa36c27b0f9f..ac5d9f7a1722f 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2050,131 +2050,6 @@ mt7530_setup_gpio(struct mt7530_priv *priv)
 }
 #endif /* CONFIG_GPIOLIB */
 
-static irqreturn_t
-mt7530_irq_thread_fn(int irq, void *dev_id)
-{
-	struct mt7530_priv *priv = dev_id;
-	bool handled = false;
-	u32 val;
-	int p;
-
-	mt7530_mutex_lock(priv);
-	val = mt7530_mii_read(priv, MT7530_SYS_INT_STS);
-	mt7530_mii_write(priv, MT7530_SYS_INT_STS, val);
-	mt7530_mutex_unlock(priv);
-
-	for (p = 0; p < MT7530_NUM_PHYS; p++) {
-		if (BIT(p) & val) {
-			unsigned int irq;
-
-			irq = irq_find_mapping(priv->irq_domain, p);
-			handle_nested_irq(irq);
-			handled = true;
-		}
-	}
-
-	return IRQ_RETVAL(handled);
-}
-
-static void
-mt7530_irq_mask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable &= ~BIT(d->hwirq);
-}
-
-static void
-mt7530_irq_unmask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable |= BIT(d->hwirq);
-}
-
-static void
-mt7530_irq_bus_lock(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	mt7530_mutex_lock(priv);
-}
-
-static void
-mt7530_irq_bus_sync_unlock(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-	mt7530_mutex_unlock(priv);
-}
-
-static struct irq_chip mt7530_irq_chip = {
-	.name = KBUILD_MODNAME,
-	.irq_mask = mt7530_irq_mask,
-	.irq_unmask = mt7530_irq_unmask,
-	.irq_bus_lock = mt7530_irq_bus_lock,
-	.irq_bus_sync_unlock = mt7530_irq_bus_sync_unlock,
-};
-
-static int
-mt7530_irq_map(struct irq_domain *domain, unsigned int irq,
-	       irq_hw_number_t hwirq)
-{
-	irq_set_chip_data(irq, domain->host_data);
-	irq_set_chip_and_handler(irq, &mt7530_irq_chip, handle_simple_irq);
-	irq_set_nested_thread(irq, true);
-	irq_set_noprobe(irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops mt7530_irq_domain_ops = {
-	.map = mt7530_irq_map,
-	.xlate = irq_domain_xlate_onecell,
-};
-
-static void
-mt7988_irq_mask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable &= ~BIT(d->hwirq);
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-}
-
-static void
-mt7988_irq_unmask(struct irq_data *d)
-{
-	struct mt7530_priv *priv = irq_data_get_irq_chip_data(d);
-
-	priv->irq_enable |= BIT(d->hwirq);
-	mt7530_mii_write(priv, MT7530_SYS_INT_EN, priv->irq_enable);
-}
-
-static struct irq_chip mt7988_irq_chip = {
-	.name = KBUILD_MODNAME,
-	.irq_mask = mt7988_irq_mask,
-	.irq_unmask = mt7988_irq_unmask,
-};
-
-static int
-mt7988_irq_map(struct irq_domain *domain, unsigned int irq,
-	       irq_hw_number_t hwirq)
-{
-	irq_set_chip_data(irq, domain->host_data);
-	irq_set_chip_and_handler(irq, &mt7988_irq_chip, handle_simple_irq);
-	irq_set_nested_thread(irq, true);
-	irq_set_noprobe(irq);
-
-	return 0;
-}
-
-static const struct irq_domain_ops mt7988_irq_domain_ops = {
-	.map = mt7988_irq_map,
-	.xlate = irq_domain_xlate_onecell,
-};
-
 static void
 mt7530_setup_mdio_irq(struct mt7530_priv *priv)
 {
@@ -2191,49 +2066,72 @@ mt7530_setup_mdio_irq(struct mt7530_priv *priv)
 	}
 }
 
+static const struct regmap_irq mt7530_irqs[] = {
+	REGMAP_IRQ_REG_LINE(0, 32),  /* PHY0_LC */
+	REGMAP_IRQ_REG_LINE(1, 32),  /* PHY1_LC */
+	REGMAP_IRQ_REG_LINE(2, 32),  /* PHY2_LC */
+	REGMAP_IRQ_REG_LINE(3, 32),  /* PHY3_LC */
+	REGMAP_IRQ_REG_LINE(4, 32),  /* PHY4_LC */
+	REGMAP_IRQ_REG_LINE(5, 32),  /* PHY5_LC */
+	REGMAP_IRQ_REG_LINE(6, 32),  /* PHY6_LC */
+	REGMAP_IRQ_REG_LINE(16, 32), /* MAC_PC */
+	REGMAP_IRQ_REG_LINE(17, 32), /* BMU */
+	REGMAP_IRQ_REG_LINE(18, 32), /* MIB */
+	REGMAP_IRQ_REG_LINE(22, 32), /* ARL_COL_FULL_COL */
+	REGMAP_IRQ_REG_LINE(23, 32), /* ARL_COL_FULL */
+	REGMAP_IRQ_REG_LINE(24, 32), /* ARL_TBL_ERR */
+	REGMAP_IRQ_REG_LINE(25, 32), /* ARL_PKT_QERR */
+	REGMAP_IRQ_REG_LINE(26, 32), /* ARL_EQ_ERR */
+	REGMAP_IRQ_REG_LINE(27, 32), /* ARL_PKT_BC */
+	REGMAP_IRQ_REG_LINE(28, 32), /* ARL_SEC_IG1X */
+	REGMAP_IRQ_REG_LINE(29, 32), /* ARL_SEC_VLAN */
+	REGMAP_IRQ_REG_LINE(30, 32), /* ARL_SEC_TAG */
+	REGMAP_IRQ_REG_LINE(31, 32), /* ACL */
+};
+
+static const struct regmap_irq_chip mt7530_regmap_irq_chip = {
+	.name = KBUILD_MODNAME,
+	.status_base = MT7530_SYS_INT_STS,
+	.unmask_base = MT7530_SYS_INT_EN,
+	.ack_base = MT7530_SYS_INT_STS,
+	.init_ack_masked = true,
+	.irqs = mt7530_irqs,
+	.num_irqs = ARRAY_SIZE(mt7530_irqs),
+	.num_regs = 1,
+};
+
 static int
 mt7530_setup_irq(struct mt7530_priv *priv)
 {
+	struct regmap_irq_chip_data *irq_data;
 	struct device *dev = priv->dev;
 	struct device_node *np = dev->of_node;
-	int ret;
+	int irq, ret;
 
 	if (!of_property_read_bool(np, "interrupt-controller")) {
 		dev_info(dev, "no interrupt support\n");
 		return 0;
 	}
 
-	priv->irq = of_irq_get(np, 0);
-	if (priv->irq <= 0) {
-		dev_err(dev, "failed to get parent IRQ: %d\n", priv->irq);
-		return priv->irq ? : -EINVAL;
-	}
-
-	if (priv->id == ID_MT7988 || priv->id == ID_EN7581)
-		priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
-							 &mt7988_irq_domain_ops,
-							 priv);
-	else
-		priv->irq_domain = irq_domain_add_linear(np, MT7530_NUM_PHYS,
-							 &mt7530_irq_domain_ops,
-							 priv);
-
-	if (!priv->irq_domain) {
-		dev_err(dev, "failed to create IRQ domain\n");
-		return -ENOMEM;
+	irq = of_irq_get(np, 0);
+	if (irq <= 0) {
+		dev_err(dev, "failed to get parent IRQ: %d\n", irq);
+		return irq ? : -EINVAL;
 	}
 
 	/* This register must be set for MT7530 to properly fire interrupts */
 	if (priv->id == ID_MT7530 || priv->id == ID_MT7621)
 		mt7530_set(priv, MT7530_TOP_SIG_CTRL, TOP_SIG_CTRL_NORMAL);
 
-	ret = request_threaded_irq(priv->irq, NULL, mt7530_irq_thread_fn,
-				   IRQF_ONESHOT, KBUILD_MODNAME, priv);
-	if (ret) {
-		irq_domain_remove(priv->irq_domain);
-		dev_err(dev, "failed to request IRQ: %d\n", ret);
+	ret = devm_regmap_add_irq_chip_fwnode(dev, dev_fwnode(dev),
+					      priv->regmap, irq,
+					      IRQF_ONESHOT,
+					      0, &mt7530_regmap_irq_chip,
+					      &irq_data);
+	if (ret)
 		return ret;
-	}
+
+	priv->irq_domain = regmap_irq_get_domain(irq_data);
 
 	return 0;
 }
@@ -2253,26 +2151,6 @@ mt7530_free_mdio_irq(struct mt7530_priv *priv)
 	}
 }
 
-static void
-mt7530_free_irq_common(struct mt7530_priv *priv)
-{
-	free_irq(priv->irq, priv);
-	irq_domain_remove(priv->irq_domain);
-}
-
-static void
-mt7530_free_irq(struct mt7530_priv *priv)
-{
-	struct device_node *mnp, *np = priv->dev->of_node;
-
-	mnp = of_get_child_by_name(np, "mdio");
-	if (!mnp)
-		mt7530_free_mdio_irq(priv);
-	of_node_put(mnp);
-
-	mt7530_free_irq_common(priv);
-}
-
 static int
 mt7530_setup_mdio(struct mt7530_priv *priv)
 {
@@ -2307,13 +2185,13 @@ mt7530_setup_mdio(struct mt7530_priv *priv)
 	bus->parent = dev;
 	bus->phy_mask = ~ds->phys_mii_mask;
 
-	if (priv->irq && !mnp)
+	if (priv->irq_domain && !mnp)
 		mt7530_setup_mdio_irq(priv);
 
 	ret = devm_of_mdiobus_register(dev, bus, mnp);
 	if (ret) {
 		dev_err(dev, "failed to register MDIO bus: %d\n", ret);
-		if (priv->irq && !mnp)
+		if (priv->irq_domain && !mnp)
 			mt7530_free_mdio_irq(priv);
 	}
 
@@ -3101,8 +2979,6 @@ mt753x_setup(struct dsa_switch *ds)
 		return ret;
 
 	ret = mt7530_setup_mdio(priv);
-	if (ret && priv->irq)
-		mt7530_free_irq_common(priv);
 	if (ret)
 		return ret;
 
@@ -3113,11 +2989,11 @@ mt753x_setup(struct dsa_switch *ds)
 		priv->pcs[i].port = i;
 	}
 
-	if (priv->create_sgmii) {
+	if (priv->create_sgmii)
 		ret = priv->create_sgmii(priv);
-		if (ret && priv->irq)
-			mt7530_free_irq(priv);
-	}
+
+	if (ret && priv->irq_domain)
+		mt7530_free_mdio_irq(priv);
 
 	return ret;
 }
@@ -3361,8 +3237,8 @@ EXPORT_SYMBOL_GPL(mt7530_probe_common);
 void
 mt7530_remove_common(struct mt7530_priv *priv)
 {
-	if (priv->irq)
-		mt7530_free_irq(priv);
+	if (priv->irq_domain)
+		mt7530_free_mdio_irq(priv);
 
 	dsa_unregister_switch(priv->ds);
 
diff --git a/drivers/net/dsa/mt7530.h b/drivers/net/dsa/mt7530.h
index 349d72a35771f..c3ea403d7acfd 100644
--- a/drivers/net/dsa/mt7530.h
+++ b/drivers/net/dsa/mt7530.h
@@ -819,9 +819,7 @@ struct mt753x_info {
  * @p5_mode:		Holding the current mode of port 5 of the MT7530 switch
  * @p5_sgmii:		Flag for distinguishing if port 5 of the MT7531 switch
  *			has got SGMII
- * @irq:		IRQ number of the switch
  * @irq_domain:		IRQ domain of the switch irq_chip
- * @irq_enable:		IRQ enable bits, synced to SYS_INT_EN
  * @create_sgmii:	Pointer to function creating SGMII PCS instance(s)
  * @active_cpu_ports:	Holding the active CPU ports
  * @mdiodev:		The pointer to the MDIO device structure
@@ -846,9 +844,7 @@ struct mt7530_priv {
 	struct mt753x_pcs	pcs[MT7530_NUM_PORTS];
 	/* protect among processes for registers access*/
 	struct mutex reg_mutex;
-	int irq;
 	struct irq_domain *irq_domain;
-	u32 irq_enable;
 	int (*create_sgmii)(struct mt7530_priv *priv);
 	u8 active_cpu_ports;
 	struct mdio_device *mdiodev;

From ea4342739df3da79a2d1a994fb42971d14dd015b Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 28 Feb 2025 13:29:55 -0800
Subject: [PATCH 1559/2753] selftests: drv-net: use env.rpath in the HDS test

Commit 29b036be1b0b ("selftests: drv-net: test XDP, HDS auto and
the ioctl path") added a new test case in the net tree, now that
this code has made its way to net-next convert it to use the env.rpath()
helper instead of manually computing the relative path.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250228212956.25399-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/hds.py | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/hds.py b/tools/testing/selftests/drivers/net/hds.py
index 873f5219e41d7..7cc74faed7430 100755
--- a/tools/testing/selftests/drivers/net/hds.py
+++ b/tools/testing/selftests/drivers/net/hds.py
@@ -20,8 +20,7 @@ def _get_hds_mode(cfg, netnl) -> str:
 
 
 def _xdp_onoff(cfg):
-    test_dir = os.path.dirname(os.path.realpath(__file__))
-    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    prog = cfg.rpath("../../net/lib/xdp_dummy.bpf.o")
     ip("link set dev %s xdp obj %s sec xdp" %
        (cfg.ifname, prog))
     ip("link set dev %s xdp off" % cfg.ifname)

From 859abe3f92d7b3e47264e26f77e53dee651a24b7 Mon Sep 17 00:00:00 2001
From: Markus Elfring <elfring@users.sourceforge.net>
Date: Thu, 13 Apr 2023 17:00:11 +0200
Subject: [PATCH 1560/2753] =?UTF-8?q?tipc:=20Reduce=20scope=20for=20the=20?=
 =?UTF-8?q?variable=20=E2=80=9Cfdefq=E2=80=9D=20in=20tipc=5Flink=5Ftnl=5Fp?=
 =?UTF-8?q?repare()?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The address of a data structure member was determined before
a corresponding null pointer check in the implementation of
the function “tipc_link_tnl_prepare”.

Thus avoid the risk for undefined behaviour by moving the definition
for the local variable “fdefq” into an if branch at the end.

This issue was detected by using the Coccinelle software.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Link: https://patch.msgid.link/08fe8fc3-19c3-4324-8719-0ee74b0f32c9@web.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tipc/link.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/tipc/link.c b/net/tipc/link.c
index 5c2088a469cea..50c2e0846ea4d 100644
--- a/net/tipc/link.c
+++ b/net/tipc/link.c
@@ -1951,7 +1951,6 @@ void tipc_link_create_dummy_tnl_msg(struct tipc_link *l,
 void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
 			   int mtyp, struct sk_buff_head *xmitq)
 {
-	struct sk_buff_head *fdefq = &tnl->failover_deferdq;
 	struct sk_buff *skb, *tnlskb;
 	struct tipc_msg *hdr, tnlhdr;
 	struct sk_buff_head *queue = &l->transmq;
@@ -2078,6 +2077,8 @@ void tipc_link_tnl_prepare(struct tipc_link *l, struct tipc_link *tnl,
 	tipc_link_xmit(tnl, &tnlq, xmitq);
 
 	if (mtyp == FAILOVER_MSG) {
+		struct sk_buff_head *fdefq = &tnl->failover_deferdq;
+
 		tnl->drop_point = l->rcv_nxt;
 		tnl->failover_reasm_skb = l->reasm_buf;
 		l->reasm_buf = NULL;

From 7ff1c88fc89688c27f773ba956f65f0c11367269 Mon Sep 17 00:00:00 2001
From: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Date: Mon, 3 Mar 2025 08:46:57 +0100
Subject: [PATCH 1561/2753] net: ethernet: ti: cpsw_new: populate netdev
 of_node

So that of_find_net_device_by_node() can find CPSW ports and other DSA
switches can be stacked downstream. Tested in conjunction with KSZ8873.

Reviewed-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Link: https://patch.msgid.link/20250303074703.1758297-1-alexander.sverdlin@siemens.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/cpsw_new.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index b01289d4726da..3da1c131335df 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -1418,6 +1418,7 @@ static int cpsw_create_ports(struct cpsw_common *cpsw)
 		ndev->netdev_ops = &cpsw_netdev_ops;
 		ndev->ethtool_ops = &cpsw_ethtool_ops;
 		SET_NETDEV_DEV(ndev, dev);
+		ndev->dev.of_node = slave_data->slave_node;
 
 		if (!napi_ndev) {
 			/* CPSW Host port CPDMA interface is shared between

From 022bfe24aad8937705704ff2e414b100cf0f2e1a Mon Sep 17 00:00:00 2001
From: Krister Johansen <kjlx@templeofstupid.com>
Date: Mon, 3 Mar 2025 18:10:13 +0100
Subject: [PATCH 1562/2753] mptcp: fix 'scheduling while atomic' in
 mptcp_pm_nl_append_new_local_addr

If multiple connection requests attempt to create an implicit mptcp
endpoint in parallel, more than one caller may end up in
mptcp_pm_nl_append_new_local_addr because none found the address in
local_addr_list during their call to mptcp_pm_nl_get_local_id.  In this
case, the concurrent new_local_addr calls may delete the address entry
created by the previous caller.  These deletes use synchronize_rcu, but
this is not permitted in some of the contexts where this function may be
called.  During packet recv, the caller may be in a rcu read critical
section and have preemption disabled.

An example stack:

   BUG: scheduling while atomic: swapper/2/0/0x00000302

   Call Trace:
   <IRQ>
   dump_stack_lvl (lib/dump_stack.c:117 (discriminator 1))
   dump_stack (lib/dump_stack.c:124)
   __schedule_bug (kernel/sched/core.c:5943)
   schedule_debug.constprop.0 (arch/x86/include/asm/preempt.h:33 kernel/sched/core.c:5970)
   __schedule (arch/x86/include/asm/jump_label.h:27 include/linux/jump_label.h:207 kernel/sched/features.h:29 kernel/sched/core.c:6621)
   schedule (arch/x86/include/asm/preempt.h:84 kernel/sched/core.c:6804 kernel/sched/core.c:6818)
   schedule_timeout (kernel/time/timer.c:2160)
   wait_for_completion (kernel/sched/completion.c:96 kernel/sched/completion.c:116 kernel/sched/completion.c:127 kernel/sched/completion.c:148)
   __wait_rcu_gp (include/linux/rcupdate.h:311 kernel/rcu/update.c:444)
   synchronize_rcu (kernel/rcu/tree.c:3609)
   mptcp_pm_nl_append_new_local_addr (net/mptcp/pm_netlink.c:966 net/mptcp/pm_netlink.c:1061)
   mptcp_pm_nl_get_local_id (net/mptcp/pm_netlink.c:1164)
   mptcp_pm_get_local_id (net/mptcp/pm.c:420)
   subflow_check_req (net/mptcp/subflow.c:98 net/mptcp/subflow.c:213)
   subflow_v4_route_req (net/mptcp/subflow.c:305)
   tcp_conn_request (net/ipv4/tcp_input.c:7216)
   subflow_v4_conn_request (net/mptcp/subflow.c:651)
   tcp_rcv_state_process (net/ipv4/tcp_input.c:6709)
   tcp_v4_do_rcv (net/ipv4/tcp_ipv4.c:1934)
   tcp_v4_rcv (net/ipv4/tcp_ipv4.c:2334)
   ip_protocol_deliver_rcu (net/ipv4/ip_input.c:205 (discriminator 1))
   ip_local_deliver_finish (include/linux/rcupdate.h:813 net/ipv4/ip_input.c:234)
   ip_local_deliver (include/linux/netfilter.h:314 include/linux/netfilter.h:308 net/ipv4/ip_input.c:254)
   ip_sublist_rcv_finish (include/net/dst.h:461 net/ipv4/ip_input.c:580)
   ip_sublist_rcv (net/ipv4/ip_input.c:640)
   ip_list_rcv (net/ipv4/ip_input.c:675)
   __netif_receive_skb_list_core (net/core/dev.c:5583 net/core/dev.c:5631)
   netif_receive_skb_list_internal (net/core/dev.c:5685 net/core/dev.c:5774)
   napi_complete_done (include/linux/list.h:37 include/net/gro.h:449 include/net/gro.h:444 net/core/dev.c:6114)
   igb_poll (drivers/net/ethernet/intel/igb/igb_main.c:8244) igb
   __napi_poll (net/core/dev.c:6582)
   net_rx_action (net/core/dev.c:6653 net/core/dev.c:6787)
   handle_softirqs (kernel/softirq.c:553)
   __irq_exit_rcu (kernel/softirq.c:588 kernel/softirq.c:427 kernel/softirq.c:636)
   irq_exit_rcu (kernel/softirq.c:651)
   common_interrupt (arch/x86/kernel/irq.c:247 (discriminator 14))
   </IRQ>

This problem seems particularly prevalent if the user advertises an
endpoint that has a different external vs internal address.  In the case
where the external address is advertised and multiple connections
already exist, multiple subflow SYNs arrive in parallel which tends to
trigger the race during creation of the first local_addr_list entries
which have the internal address instead.

Fix by skipping the replacement of an existing implicit local address if
called via mptcp_pm_nl_get_local_id.

Fixes: d045b9eb95a9 ("mptcp: introduce implicit endpoints")
Cc: stable@vger.kernel.org
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250303-net-mptcp-fix-sched-while-atomic-v1-1-f6a216c5a74c@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index c0e47f4f7b1aa..7868207c4e9d9 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -977,7 +977,7 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
 
 static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 					     struct mptcp_pm_addr_entry *entry,
-					     bool needs_id)
+					     bool needs_id, bool replace)
 {
 	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
 	unsigned int addr_max;
@@ -1017,6 +1017,17 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
 			if (entry->addr.id)
 				goto out;
 
+			/* allow callers that only need to look up the local
+			 * addr's id to skip replacement. This allows them to
+			 * avoid calling synchronize_rcu in the packet recv
+			 * path.
+			 */
+			if (!replace) {
+				kfree(entry);
+				ret = cur->addr.id;
+				goto out;
+			}
+
 			pernet->addrs--;
 			entry->addr.id = cur->addr.id;
 			list_del_rcu(&cur->list);
@@ -1165,7 +1176,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	entry->ifindex = 0;
 	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
 	entry->lsk = NULL;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true);
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
 		kfree(entry);
 
@@ -1433,7 +1444,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		}
 	}
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
-						!mptcp_pm_has_addr_attr_id(attr, info));
+						!mptcp_pm_has_addr_attr_id(attr, info),
+						true);
 	if (ret < 0) {
 		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
 		goto out_free;

From ae9d5b19b322d4b557efda684da2f4df21670ef8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 2 Mar 2025 12:42:34 +0000
Subject: [PATCH 1563/2753] tcp: use RCU in __inet{6}_check_established()

When __inet_hash_connect() has to try many 4-tuples before
finding an available one, we see a high spinlock cost from
__inet_check_established() and/or __inet6_check_established().

This patch adds an RCU lookup to avoid the spinlock
acquisition when the 4-tuple is found in the hash table.

Note that there are still spin_lock_bh() calls in
__inet_hash_connect() to protect inet_bind_hashbucket,
this will be fixed later in this series.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250302124237.3913746-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_hashtables.c  | 19 ++++++++++++++++---
 net/ipv6/inet6_hashtables.c | 19 ++++++++++++++++---
 2 files changed, 32 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 9bfcfd016e182..46d39aa2199ec 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -551,11 +551,24 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	unsigned int hash = inet_ehashfn(net, daddr, lport,
 					 saddr, inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
-	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
-	struct sock *sk2;
-	const struct hlist_nulls_node *node;
 	struct inet_timewait_sock *tw = NULL;
+	const struct hlist_nulls_node *node;
+	struct sock *sk2;
+	spinlock_t *lock;
+
+	rcu_read_lock();
+	sk_nulls_for_each(sk2, node, &head->chain) {
+		if (sk2->sk_hash != hash ||
+		    !inet_match(net, sk2, acookie, ports, dif, sdif))
+			continue;
+		if (sk2->sk_state == TCP_TIME_WAIT)
+			break;
+		rcu_read_unlock();
+		return -EADDRNOTAVAIL;
+	}
+	rcu_read_unlock();
 
+	lock = inet_ehash_lockp(hinfo, hash);
 	spin_lock(lock);
 
 	sk_nulls_for_each(sk2, node, &head->chain) {
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 9ec05e354baa6..3604a5cae5d29 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -276,11 +276,24 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
 						inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
-	spinlock_t *lock = inet_ehash_lockp(hinfo, hash);
-	struct sock *sk2;
-	const struct hlist_nulls_node *node;
 	struct inet_timewait_sock *tw = NULL;
+	const struct hlist_nulls_node *node;
+	struct sock *sk2;
+	spinlock_t *lock;
+
+	rcu_read_lock();
+	sk_nulls_for_each(sk2, node, &head->chain) {
+		if (sk2->sk_hash != hash ||
+		    !inet6_match(net, sk2, saddr, daddr, ports, dif, sdif))
+			continue;
+		if (sk2->sk_state == TCP_TIME_WAIT)
+			break;
+		rcu_read_unlock();
+		return -EADDRNOTAVAIL;
+	}
+	rcu_read_unlock();
 
+	lock = inet_ehash_lockp(hinfo, hash);
 	spin_lock(lock);
 
 	sk_nulls_for_each(sk2, node, &head->chain) {

From ca79d80b0b9f42362a893f06413a9fe91811158a Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 2 Mar 2025 12:42:35 +0000
Subject: [PATCH 1564/2753] tcp: optimize inet_use_bhash2_on_bind()

There is no reason to call ipv6_addr_type().

Instead, use highly optimized ipv6_addr_any() and ipv6_addr_v4mapped().

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250302124237.3913746-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_connection_sock.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index bf9ce0c196575..b4e514da22b64 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -157,12 +157,10 @@ static bool inet_use_bhash2_on_bind(const struct sock *sk)
 {
 #if IS_ENABLED(CONFIG_IPV6)
 	if (sk->sk_family == AF_INET6) {
-		int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);
-
-		if (addr_type == IPV6_ADDR_ANY)
+		if (ipv6_addr_any(&sk->sk_v6_rcv_saddr))
 			return false;
 
-		if (addr_type != IPV6_ADDR_MAPPED)
+		if (!ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr))
 			return true;
 	}
 #endif

From d186f405fdf4229d0e9a52ba71662404b06cc002 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 2 Mar 2025 12:42:36 +0000
Subject: [PATCH 1565/2753] tcp: add RCU management to inet_bind_bucket

Add RCU protection to inet_bind_bucket structure.

- Add rcu_head field to the structure definition.

- Use kfree_rcu() at destroy time, and remove inet_bind_bucket_destroy()
  first argument.

- Use hlist_del_rcu() and hlist_add_head_rcu() methods.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250302124237.3913746-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_hashtables.h   |  4 ++--
 net/ipv4/inet_connection_sock.c |  2 +-
 net/ipv4/inet_hashtables.c      | 14 +++++++-------
 net/ipv4/inet_timewait_sock.c   |  2 +-
 4 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index da818fb0205fe..1061c4f536a66 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -89,6 +89,7 @@ struct inet_bind_bucket {
 	bool			fast_ipv6_only;
 	struct hlist_node	node;
 	struct hlist_head	bhash2;
+	struct rcu_head		rcu;
 };
 
 struct inet_bind2_bucket {
@@ -226,8 +227,7 @@ struct inet_bind_bucket *
 inet_bind_bucket_create(struct kmem_cache *cachep, struct net *net,
 			struct inet_bind_hashbucket *head,
 			const unsigned short snum, int l3mdev);
-void inet_bind_bucket_destroy(struct kmem_cache *cachep,
-			      struct inet_bind_bucket *tb);
+void inet_bind_bucket_destroy(struct inet_bind_bucket *tb);
 
 bool inet_bind_bucket_match(const struct inet_bind_bucket *tb,
 			    const struct net *net, unsigned short port,
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index b4e514da22b64..e93c660340770 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -598,7 +598,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum)
 		if (bhash2_created)
 			inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, tb2);
 		if (bhash_created)
-			inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
+			inet_bind_bucket_destroy(tb);
 	}
 	if (head2_lock_acquired)
 		spin_unlock(&head2->lock);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 46d39aa2199ec..b737e13f8459c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -76,7 +76,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 		tb->fastreuse = 0;
 		tb->fastreuseport = 0;
 		INIT_HLIST_HEAD(&tb->bhash2);
-		hlist_add_head(&tb->node, &head->chain);
+		hlist_add_head_rcu(&tb->node, &head->chain);
 	}
 	return tb;
 }
@@ -84,11 +84,11 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep,
 /*
  * Caller must hold hashbucket lock for this tb with local BH disabled
  */
-void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket *tb)
+void inet_bind_bucket_destroy(struct inet_bind_bucket *tb)
 {
 	if (hlist_empty(&tb->bhash2)) {
-		__hlist_del(&tb->node);
-		kmem_cache_free(cachep, tb);
+		hlist_del_rcu(&tb->node);
+		kfree_rcu(tb, rcu);
 	}
 }
 
@@ -201,7 +201,7 @@ static void __inet_put_port(struct sock *sk)
 	}
 	spin_unlock(&head2->lock);
 
-	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+	inet_bind_bucket_destroy(tb);
 	spin_unlock(&head->lock);
 }
 
@@ -285,7 +285,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child)
 
 error:
 	if (created_inet_bind_bucket)
-		inet_bind_bucket_destroy(table->bind_bucket_cachep, tb);
+		inet_bind_bucket_destroy(tb);
 	spin_unlock(&head2->lock);
 	spin_unlock(&head->lock);
 	return -ENOMEM;
@@ -1162,7 +1162,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	spin_unlock(&head2->lock);
 	if (tb_created)
-		inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb);
+		inet_bind_bucket_destroy(tb);
 	spin_unlock(&head->lock);
 
 	if (tw)
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 337390ba85b40..aded4bf1bc16d 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -39,7 +39,7 @@ void inet_twsk_bind_unhash(struct inet_timewait_sock *tw,
 	tw->tw_tb = NULL;
 	tw->tw_tb2 = NULL;
 	inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2);
-	inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb);
+	inet_bind_bucket_destroy(tb);
 
 	__sock_put((struct sock *)tw);
 }

From 86c2bc293b8130aec9fa504e953531a84a6eb9a6 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Sun, 2 Mar 2025 12:42:37 +0000
Subject: [PATCH 1566/2753] tcp: use RCU lookup in __inet_hash_connect()

When __inet_hash_connect() has to try many 4-tuples before
finding an available one, we see a high spinlock cost from
the many spin_lock_bh(&head->lock) performed in its loop.

This patch adds an RCU lookup to avoid the spinlock cost.

check_established() gets a new @rcu_lookup argument.
First reason is to not make any changes while head->lock
is not held.
Second reason is to not make this RCU lookup a second time
after the spinlock has been acquired.

Tested:

Server:

ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog

Client:

ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server

Before series:

  utime_start=0.288582
  utime_end=1.548707
  stime_start=20.637138
  stime_end=2002.489845
  num_transactions=484453
  latency_min=0.156279245
  latency_max=20.922042756
  latency_mean=1.546521274
  latency_stddev=3.936005194
  num_samples=312537
  throughput=47426.00

perf top on the client:

 49.54%  [kernel]       [k] _raw_spin_lock
 25.87%  [kernel]       [k] _raw_spin_lock_bh
  5.97%  [kernel]       [k] queued_spin_lock_slowpath
  5.67%  [kernel]       [k] __inet_hash_connect
  3.53%  [kernel]       [k] __inet6_check_established
  3.48%  [kernel]       [k] inet6_ehashfn
  0.64%  [kernel]       [k] rcu_all_qs

After this series:

  utime_start=0.271607
  utime_end=3.847111
  stime_start=18.407684
  stime_end=1997.485557
  num_transactions=1350742
  latency_min=0.014131929
  latency_max=17.895073144
  latency_mean=0.505675853  # Nice reduction of latency metrics
  latency_stddev=2.125164772
  num_samples=307884
  throughput=139866.80      # 190 % increase

perf top on client:

 56.86%  [kernel]       [k] __inet6_check_established
 17.96%  [kernel]       [k] __inet_hash_connect
 13.88%  [kernel]       [k] inet6_ehashfn
  2.52%  [kernel]       [k] rcu_all_qs
  2.01%  [kernel]       [k] __cond_resched
  0.41%  [kernel]       [k] _raw_spin_lock

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250302124237.3913746-5-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_hashtables.h |  3 +-
 net/ipv4/inet_hashtables.c    | 52 +++++++++++++++++++++++------------
 net/ipv6/inet6_hashtables.c   | 24 ++++++++--------
 3 files changed, 50 insertions(+), 29 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index 1061c4f536a66..f447d61d95982 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -529,7 +529,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 			struct sock *sk, u64 port_offset,
 			int (*check_established)(struct inet_timewait_death_row *,
 						 struct sock *, __u16,
-						 struct inet_timewait_sock **));
+						 struct inet_timewait_sock **,
+						 bool rcu_lookup));
 
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk);
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index b737e13f8459c..d1b5f45ee7184 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -537,7 +537,8 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established);
 /* called with local bh disabled */
 static int __inet_check_established(struct inet_timewait_death_row *death_row,
 				    struct sock *sk, __u16 lport,
-				    struct inet_timewait_sock **twp)
+				    struct inet_timewait_sock **twp,
+				    bool rcu_lookup)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -556,17 +557,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	struct sock *sk2;
 	spinlock_t *lock;
 
-	rcu_read_lock();
-	sk_nulls_for_each(sk2, node, &head->chain) {
-		if (sk2->sk_hash != hash ||
-		    !inet_match(net, sk2, acookie, ports, dif, sdif))
-			continue;
-		if (sk2->sk_state == TCP_TIME_WAIT)
-			break;
-		rcu_read_unlock();
-		return -EADDRNOTAVAIL;
+	if (rcu_lookup) {
+		sk_nulls_for_each(sk2, node, &head->chain) {
+			if (sk2->sk_hash != hash ||
+			    !inet_match(net, sk2, acookie, ports, dif, sdif))
+				continue;
+			if (sk2->sk_state == TCP_TIME_WAIT)
+				break;
+			return -EADDRNOTAVAIL;
+		}
+		return 0;
 	}
-	rcu_read_unlock();
 
 	lock = inet_ehash_lockp(hinfo, hash);
 	spin_lock(lock);
@@ -1007,7 +1008,8 @@ static u32 *table_perturb;
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u64 port_offset,
 		int (*check_established)(struct inet_timewait_death_row *,
-			struct sock *, __u16, struct inet_timewait_sock **))
+			struct sock *, __u16, struct inet_timewait_sock **,
+			bool rcu_lookup))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_bind_hashbucket *head, *head2;
@@ -1025,7 +1027,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	if (port) {
 		local_bh_disable();
-		ret = check_established(death_row, sk, port, NULL);
+		ret = check_established(death_row, sk, port, NULL, false);
 		local_bh_enable();
 		return ret;
 	}
@@ -1061,6 +1063,21 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 			continue;
 		head = &hinfo->bhash[inet_bhashfn(net, port,
 						  hinfo->bhash_size)];
+		rcu_read_lock();
+		hlist_for_each_entry_rcu(tb, &head->chain, node) {
+			if (!inet_bind_bucket_match(tb, net, port, l3mdev))
+				continue;
+			if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) {
+				rcu_read_unlock();
+				goto next_port;
+			}
+			if (!check_established(death_row, sk, port, &tw, true))
+				break;
+			rcu_read_unlock();
+			goto next_port;
+		}
+		rcu_read_unlock();
+
 		spin_lock_bh(&head->lock);
 
 		/* Does not bother with rcv_saddr checks, because
@@ -1070,12 +1087,12 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 			if (inet_bind_bucket_match(tb, net, port, l3mdev)) {
 				if (tb->fastreuse >= 0 ||
 				    tb->fastreuseport >= 0)
-					goto next_port;
+					goto next_port_unlock;
 				WARN_ON(hlist_empty(&tb->bhash2));
 				if (!check_established(death_row, sk,
-						       port, &tw))
+						       port, &tw, false))
 					goto ok;
-				goto next_port;
+				goto next_port_unlock;
 			}
 		}
 
@@ -1089,8 +1106,9 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		tb->fastreuse = -1;
 		tb->fastreuseport = -1;
 		goto ok;
-next_port:
+next_port_unlock:
 		spin_unlock_bh(&head->lock);
+next_port:
 		cond_resched();
 	}
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3604a5cae5d29..9be315496459f 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -263,7 +263,8 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
 
 static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 				     struct sock *sk, const __u16 lport,
-				     struct inet_timewait_sock **twp)
+				     struct inet_timewait_sock **twp,
+				     bool rcu_lookup)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -281,17 +282,18 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	struct sock *sk2;
 	spinlock_t *lock;
 
-	rcu_read_lock();
-	sk_nulls_for_each(sk2, node, &head->chain) {
-		if (sk2->sk_hash != hash ||
-		    !inet6_match(net, sk2, saddr, daddr, ports, dif, sdif))
-			continue;
-		if (sk2->sk_state == TCP_TIME_WAIT)
-			break;
-		rcu_read_unlock();
-		return -EADDRNOTAVAIL;
+	if (rcu_lookup) {
+		sk_nulls_for_each(sk2, node, &head->chain) {
+			if (sk2->sk_hash != hash ||
+			    !inet6_match(net, sk2, saddr, daddr,
+					 ports, dif, sdif))
+				continue;
+			if (sk2->sk_state == TCP_TIME_WAIT)
+				break;
+			return -EADDRNOTAVAIL;
+		}
+		return 0;
 	}
-	rcu_read_unlock();
 
 	lock = inet_ehash_lockp(hinfo, hash);
 	spin_lock(lock);

From b9564ca3a2c877cb62bbd22bad5708c3d7cdb186 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Mon, 3 Mar 2025 18:18:32 -0500
Subject: [PATCH 1567/2753] net: cadence: macb: Synchronize standard stats

The new stats calculations add several additional calls to
macb/gem_update_stats() and accesses to bp->hw_stats. These are
protected by a spinlock since commit fa52f15c745c ("net: cadence: macb:
Synchronize stats calculations"), which was applied in parallel. Add
some locking now that the net has been merged into net-next.

Fixes: f6af690a295a ("net: cadence: macb: Report standard stats")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Link: https://patch.msgid.link/20250303231832.1648274-1-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/cadence/macb_main.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index 6c462de81f200..b5797c1ac0a41 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -3253,9 +3253,11 @@ static void macb_get_pause_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
 	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void gem_get_pause_stats(struct net_device *dev,
@@ -3264,9 +3266,11 @@ static void gem_get_pause_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	pause_stats->tx_pause_frames = hwstat->tx_pause_frames;
 	pause_stats->rx_pause_frames = hwstat->rx_pause_frames;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void macb_get_eth_mac_stats(struct net_device *dev,
@@ -3275,6 +3279,7 @@ static void macb_get_eth_mac_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 	mac_stats->FramesTransmittedOK = hwstat->tx_ok;
 	mac_stats->SingleCollisionFrames = hwstat->tx_single_cols;
@@ -3290,6 +3295,7 @@ static void macb_get_eth_mac_stats(struct net_device *dev,
 	mac_stats->FramesLostDueToIntMACRcvError = hwstat->rx_overruns;
 	mac_stats->InRangeLengthErrors = hwstat->rx_length_mismatch;
 	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_pkts;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void gem_get_eth_mac_stats(struct net_device *dev,
@@ -3298,6 +3304,7 @@ static void gem_get_eth_mac_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	mac_stats->FramesTransmittedOK = hwstat->tx_frames;
 	mac_stats->SingleCollisionFrames = hwstat->tx_single_collision_frames;
@@ -3320,6 +3327,7 @@ static void gem_get_eth_mac_stats(struct net_device *dev,
 	mac_stats->BroadcastFramesReceivedOK = hwstat->rx_broadcast_frames;
 	mac_stats->InRangeLengthErrors = hwstat->rx_length_field_frame_errors;
 	mac_stats->FrameTooLongErrors = hwstat->rx_oversize_frames;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 /* TODO: Report SQE test errors when added to phy_stats */
@@ -3329,8 +3337,10 @@ static void macb_get_eth_phy_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void gem_get_eth_phy_stats(struct net_device *dev,
@@ -3339,8 +3349,10 @@ static void gem_get_eth_phy_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	phy_stats->SymbolErrorDuringCarrier = hwstat->rx_symbol_errors;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static void macb_get_rmon_stats(struct net_device *dev,
@@ -3350,10 +3362,12 @@ static void macb_get_rmon_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct macb_stats *hwstat = &bp->hw_stats.macb;
 
+	spin_lock_irq(&bp->stats_lock);
 	macb_update_stats(bp);
 	rmon_stats->undersize_pkts = hwstat->rx_undersize_pkts;
 	rmon_stats->oversize_pkts = hwstat->rx_oversize_pkts;
 	rmon_stats->jabbers = hwstat->rx_jabbers;
+	spin_unlock_irq(&bp->stats_lock);
 }
 
 static const struct ethtool_rmon_hist_range gem_rmon_ranges[] = {
@@ -3374,6 +3388,7 @@ static void gem_get_rmon_stats(struct net_device *dev,
 	struct macb *bp = netdev_priv(dev);
 	struct gem_stats *hwstat = &bp->hw_stats.gem;
 
+	spin_lock_irq(&bp->stats_lock);
 	gem_update_stats(bp);
 	rmon_stats->undersize_pkts = hwstat->rx_undersized_frames;
 	rmon_stats->oversize_pkts = hwstat->rx_oversize_frames;
@@ -3392,6 +3407,7 @@ static void gem_get_rmon_stats(struct net_device *dev,
 	rmon_stats->hist_tx[4] = hwstat->tx_512_1023_byte_frames;
 	rmon_stats->hist_tx[5] = hwstat->tx_1024_1518_byte_frames;
 	rmon_stats->hist_tx[6] = hwstat->tx_greater_than_1518_byte_frames;
+	spin_unlock_irq(&bp->stats_lock);
 	*ranges = gem_rmon_ranges;
 }
 

From f252f23ab657cd224cb8334ba69966396f3f629b Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 3 Mar 2025 15:02:12 +0300
Subject: [PATCH 1568/2753] net: Prevent use after free in
 netif_napi_set_irq_locked()

The cpu_rmap_put() will call kfree() when the last reference is dropped
so it could result in a use after free when we dereference the same
pointer the next line.  Move the cpu_rmap_put() after the dereference.

Fixes: bd7c00605ee0 ("net: move aRFS rmap management and CPU affinity to core")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://patch.msgid.link/5a9c53a4-5487-4b8c-9ffa-d8e5343aaaaf@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index 5c9d2bd29e156..2dc705604509e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7072,8 +7072,8 @@ void netif_napi_set_irq_locked(struct napi_struct *napi, int irq)
 put_rmap:
 #ifdef CONFIG_RFS_ACCEL
 	if (napi->dev->rx_cpu_rmap_auto) {
-		cpu_rmap_put(napi->dev->rx_cpu_rmap);
 		napi->dev->rx_cpu_rmap->obj[napi->napi_rmap_idx] = NULL;
+		cpu_rmap_put(napi->dev->rx_cpu_rmap);
 		napi->napi_rmap_idx = -1;
 	}
 #endif

From b33a534610067ade2bdaf2052900aaad99701353 Mon Sep 17 00:00:00 2001
From: Oscar Maes <oscmaes92@gmail.com>
Date: Mon, 3 Mar 2025 16:56:19 +0100
Subject: [PATCH 1569/2753] vlan: enforce underlying device type

Currently, VLAN devices can be created on top of non-ethernet devices.

Besides the fact that it doesn't make much sense, this also causes a
bug which leaks the address of a kernel function to usermode.

When creating a VLAN device, we initialize GARP (garp_init_applicant)
and MRP (mrp_init_applicant) for the underlying device.

As part of the initialization process, we add the multicast address of
each applicant to the underlying device, by calling dev_mc_add.

__dev_mc_add uses dev->addr_len to determine the length of the new
multicast address.

This causes an out-of-bounds read if dev->addr_len is greater than 6,
since the multicast addresses provided by GARP and MRP are only 6
bytes long.

This behaviour can be reproduced using the following commands:

ip tunnel add gretest mode ip6gre local ::1 remote ::2 dev lo
ip l set up dev gretest
ip link add link gretest name vlantest type vlan id 100

Then, the following command will display the address of garp_pdu_rcv:

ip maddr show | grep 01:80:c2:00:00:21

Fix the bug by enforcing the type of the underlying device during VLAN
device initialization.

Fixes: 22bedad3ce11 ("net: convert multicast list to list_head")
Reported-by: syzbot+91161fe81857b396c8a0@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/000000000000ca9a81061a01ec20@google.com/
Signed-off-by: Oscar Maes <oscmaes92@gmail.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Link: https://patch.msgid.link/20250303155619.8918-1-oscmaes92@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/8021q/vlan.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index e45187b882206..41be38264493d 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -131,7 +131,8 @@ int vlan_check_real_dev(struct net_device *real_dev,
 {
 	const char *name = real_dev->name;
 
-	if (real_dev->features & NETIF_F_VLAN_CHALLENGED) {
+	if (real_dev->features & NETIF_F_VLAN_CHALLENGED ||
+	    real_dev->type != ARPHRD_ETHER) {
 		pr_info("VLANs not supported on %s\n", name);
 		NL_SET_ERR_MSG_MOD(extack, "VLANs not supported on device");
 		return -EOPNOTSUPP;

From d1e879ec600f9b3bdd253167533959facfefb17b Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 16 Feb 2025 11:42:40 +0200
Subject: [PATCH 1570/2753] wifi: iwlwifi: add iwlmld sub-driver

iwlwifi is the driver of all Intel wifi devices since 2008.
Since then, the hardware has changed a lot, but the firmware
API has changed even more. The need to keep one driver that
supports all those different APIs led us to introduce a new
architecture circa 2012 which allowed us to keep the same
interface to the hardware (DMAs, Tx queues, etc...) with a
new layer to implement the mid-layer between mac80211 and
the firmware. The first component is called the 'transport'
and the latter is called 'operation_mode' a.k.a  op_mode.

In 2013 we took advantage of the new architecture to
introduce iwlmvm which allowed us to implement the, then,
new firmware API. This op_mode supports 7260 and up, those
devices supports support at least VHT.

Since then, wifi evolved and so did the firmware. It became
much bigger and took a lot of functionality from the driver.
It became increasingly hard to keep the same op_mode for the
newest devices and we experienced frequent regressions on
older devices. In order to avoid those regressions and keep
the code maintainable, we decided it was about time to start
a new op_mode.

iwlmld is a new op_mode that supports BE200 or newer if the
firmware being used is 97.ucode or newer. If the user has
an older devices or BE200 with .96.ucode, iwlmvm will be
loaded. Of course, this op_mode selection is seamless.

All the features supported in iwlmvm are supported in
iwlmld besides a few seldom used use cases: injection and
Hotspot 2.0. Those are under work.

A few points about the implementation:
 * iwlmld doesn't have any mutexes, it relies on the
   wiphy_lock
 * iwlmld is more "resource oriented": stations, links and
   interfaces are allocated and freed only after all the
   relevant flows are completed.
 * Firmware notifications' sizes are validated in a more
   structured way.

We would love to see this new op_mode merged in 6.15. The
firmware for this new driver (.97.ucode) is not yet publicly
available but it'll be sent very soon.
People eager to get an early version of this firmware can
contact Emmanuel at:
emmanuel.grumbach@intel.com

I've listed the people who directly contributed
code, but many others from various teams have
contributed in other ways.

Co-developed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Co-developed-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Co-developed-by: Daniel Gabay <daniel.gabay@intel.com>
Signed-off-by: Daniel Gabay <daniel.gabay@intel.com>
Co-developed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Co-developed-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Co-developed-by: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Signed-off-by: Yedidya Benshimol <yedidya.ben.shimol@intel.com>
Co-developed-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Co-developed-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Shaul Triebitz <shaul.triebitz@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://lore.kernel.org/linux-wireless/20250216094321.537988-1-miriam.rachel.korenblit@intel.com/
[fix Kconfig, fix api/phy.h includes, SPDX tag and coding
 style issues, duplicated includes per 0-day robot]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/Kconfig    |   15 +-
 drivers/net/wireless/intel/iwlwifi/Makefile   |    5 +-
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c   |    5 +
 .../net/wireless/intel/iwlwifi/fw/api/phy.h   |    4 +-
 .../net/wireless/intel/iwlwifi/iwl-config.h   |    6 +-
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c  |   28 +-
 .../net/wireless/intel/iwlwifi/mld/Makefile   |   16 +
 drivers/net/wireless/intel/iwlwifi/mld/agg.c  |  670 +++++
 drivers/net/wireless/intel/iwlwifi/mld/agg.h  |  127 +
 drivers/net/wireless/intel/iwlwifi/mld/ap.c   |  344 +++
 drivers/net/wireless/intel/iwlwifi/mld/ap.h   |   45 +
 drivers/net/wireless/intel/iwlwifi/mld/coex.c |   40 +
 drivers/net/wireless/intel/iwlwifi/mld/coex.h |   15 +
 .../wireless/intel/iwlwifi/mld/constants.h    |   88 +
 drivers/net/wireless/intel/iwlwifi/mld/d3.c   | 1998 ++++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/d3.h   |   51 +
 .../net/wireless/intel/iwlwifi/mld/debugfs.c  |  823 +++++
 .../net/wireless/intel/iwlwifi/mld/debugfs.h  |  200 ++
 .../intel/iwlwifi/mld/ftm-initiator.c         |  451 +++
 .../intel/iwlwifi/mld/ftm-initiator.h         |   15 +
 drivers/net/wireless/intel/iwlwifi/mld/fw.c   |  536 ++++
 drivers/net/wireless/intel/iwlwifi/mld/hcmd.h |   54 +
 .../net/wireless/intel/iwlwifi/mld/iface.c    |  671 +++++
 .../net/wireless/intel/iwlwifi/mld/iface.h    |  234 ++
 drivers/net/wireless/intel/iwlwifi/mld/key.c  |  358 +++
 drivers/net/wireless/intel/iwlwifi/mld/key.h  |   39 +
 drivers/net/wireless/intel/iwlwifi/mld/led.c  |  100 +
 drivers/net/wireless/intel/iwlwifi/mld/led.h  |   29 +
 drivers/net/wireless/intel/iwlwifi/mld/link.c | 1216 ++++++++
 drivers/net/wireless/intel/iwlwifi/mld/link.h |  153 +
 .../wireless/intel/iwlwifi/mld/low_latency.c  |  335 +++
 .../wireless/intel/iwlwifi/mld/low_latency.h  |   68 +
 .../net/wireless/intel/iwlwifi/mld/mac80211.c | 2671 +++++++++++++++++
 .../net/wireless/intel/iwlwifi/mld/mac80211.h |   13 +
 drivers/net/wireless/intel/iwlwifi/mld/mcc.c  |  329 ++
 drivers/net/wireless/intel/iwlwifi/mld/mcc.h  |   17 +
 drivers/net/wireless/intel/iwlwifi/mld/mld.c  |  707 +++++
 drivers/net/wireless/intel/iwlwifi/mld/mld.h  |  584 ++++
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  |  994 ++++++
 drivers/net/wireless/intel/iwlwifi/mld/mlo.h  |  157 +
 .../net/wireless/intel/iwlwifi/mld/notif.c    |  758 +++++
 .../net/wireless/intel/iwlwifi/mld/notif.h    |   35 +
 drivers/net/wireless/intel/iwlwifi/mld/phy.c  |  116 +
 drivers/net/wireless/intel/iwlwifi/mld/phy.h  |   49 +
 .../net/wireless/intel/iwlwifi/mld/power.c    |  395 +++
 .../net/wireless/intel/iwlwifi/mld/power.h    |   33 +
 drivers/net/wireless/intel/iwlwifi/mld/ptp.c  |  321 ++
 drivers/net/wireless/intel/iwlwifi/mld/ptp.h  |   45 +
 .../wireless/intel/iwlwifi/mld/regulatory.c   |  393 +++
 .../wireless/intel/iwlwifi/mld/regulatory.h   |   23 +
 drivers/net/wireless/intel/iwlwifi/mld/roc.c  |  224 ++
 drivers/net/wireless/intel/iwlwifi/mld/roc.h  |   20 +
 drivers/net/wireless/intel/iwlwifi/mld/rx.c   | 2060 +++++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/rx.h   |   72 +
 drivers/net/wireless/intel/iwlwifi/mld/scan.c | 2006 +++++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/scan.h |  135 +
 .../intel/iwlwifi/mld/session-protect.c       |  222 ++
 .../intel/iwlwifi/mld/session-protect.h       |  102 +
 drivers/net/wireless/intel/iwlwifi/mld/sta.c  | 1265 ++++++++
 drivers/net/wireless/intel/iwlwifi/mld/sta.h  |  266 ++
 .../net/wireless/intel/iwlwifi/mld/stats.c    |  509 ++++
 .../net/wireless/intel/iwlwifi/mld/stats.h    |   22 +
 .../wireless/intel/iwlwifi/mld/tests/Makefile |    5 +
 .../wireless/intel/iwlwifi/mld/tests/agg.c    |  663 ++++
 .../wireless/intel/iwlwifi/mld/tests/hcmd.c   |   62 +
 .../intel/iwlwifi/mld/tests/link-selection.c  |  171 ++
 .../wireless/intel/iwlwifi/mld/tests/link.c   |  103 +
 .../wireless/intel/iwlwifi/mld/tests/module.c |   11 +
 .../net/wireless/intel/iwlwifi/mld/tests/rx.c |  353 +++
 .../wireless/intel/iwlwifi/mld/tests/utils.c  |  475 +++
 .../wireless/intel/iwlwifi/mld/tests/utils.h  |  124 +
 .../net/wireless/intel/iwlwifi/mld/thermal.c  |  438 +++
 .../net/wireless/intel/iwlwifi/mld/thermal.h  |   36 +
 .../wireless/intel/iwlwifi/mld/time_sync.c    |  240 ++
 .../wireless/intel/iwlwifi/mld/time_sync.h    |   26 +
 drivers/net/wireless/intel/iwlwifi/mld/tlc.c  |  717 +++++
 drivers/net/wireless/intel/iwlwifi/mld/tlc.h  |   23 +
 drivers/net/wireless/intel/iwlwifi/mld/tx.c   | 1374 +++++++++
 drivers/net/wireless/intel/iwlwifi/mld/tx.h   |   77 +
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c |    9 +-
 80 files changed, 28178 insertions(+), 11 deletions(-)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/Makefile
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/agg.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/agg.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ap.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ap.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/coex.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/coex.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/constants.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/d3.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/d3.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/fw.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/iface.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/iface.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/key.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/key.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/led.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/led.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/link.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/link.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/low_latency.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mac80211.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mcc.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mcc.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mld.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mld.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mlo.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/mlo.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/notif.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/notif.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/phy.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/phy.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/power.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/power.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ptp.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/ptp.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/regulatory.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/roc.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/roc.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/rx.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/rx.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/scan.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/scan.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/session-protect.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/session-protect.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/sta.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/sta.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/stats.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/stats.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/module.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/rx.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/thermal.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/thermal.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/time_sync.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/time_sync.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tlc.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tlc.h
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tx.c
 create mode 100644 drivers/net/wireless/intel/iwlwifi/mld/tx.h

diff --git a/drivers/net/wireless/intel/iwlwifi/Kconfig b/drivers/net/wireless/intel/iwlwifi/Kconfig
index 4b04865fc2c9e..82f577da1a8b5 100644
--- a/drivers/net/wireless/intel/iwlwifi/Kconfig
+++ b/drivers/net/wireless/intel/iwlwifi/Kconfig
@@ -81,14 +81,25 @@ config IWLMVM
 	  of the devices that use this firmware is available here:
 	  https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi#firmware
 
+config IWLMLD
+	tristate "Intel Wireless WiFi MLD Firmware support"
+	select WANT_DEV_COREDUMP
+	depends on MAC80211
+	depends on PTP_1588_CLOCK_OPTIONAL
+	help
+	  This is the driver that supports firmwares of MLD capable devices.
+	  The list of the devices that use this firmware is available here:
+	  https://wireless.wiki.kernel.org/en/users/drivers/iwlwifi#firmware
+
 # don't call it _MODULE -- will confuse Kconfig/fixdep/...
 config IWLWIFI_OPMODE_MODULAR
 	bool
 	default y if IWLDVM=m
 	default y if IWLMVM=m
+	default y if IWLMLD=m
 
-comment "WARNING: iwlwifi is useless without IWLDVM or IWLMVM"
-	depends on IWLDVM=n && IWLMVM=n
+comment "WARNING: iwlwifi is useless without IWLDVM or IWLMVM or IWLMLD"
+	depends on IWLDVM=n && IWLMVM=n && IWLMLD=n
 
 menu "Debugging Options"
 
diff --git a/drivers/net/wireless/intel/iwlwifi/Makefile b/drivers/net/wireless/intel/iwlwifi/Makefile
index 19c4ce6f2465f..9546ceeaf5e37 100644
--- a/drivers/net/wireless/intel/iwlwifi/Makefile
+++ b/drivers/net/wireless/intel/iwlwifi/Makefile
@@ -12,7 +12,8 @@ iwlwifi-objs		+= pcie/ctxt-info.o pcie/ctxt-info-gen3.o
 iwlwifi-objs		+= pcie/trans-gen2.o pcie/tx-gen2.o
 iwlwifi-$(CONFIG_IWLDVM) += cfg/1000.o cfg/2000.o cfg/5000.o cfg/6000.o
 iwlwifi-$(CONFIG_IWLMVM) += cfg/7000.o cfg/8000.o cfg/9000.o cfg/22000.o
-iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o cfg/bz.o cfg/sc.o cfg/dr.o
+iwlwifi-$(CONFIG_IWLMVM) += cfg/ax210.o
+iwlwifi-$(CONFIG_IWLMLD) += cfg/bz.o cfg/sc.o cfg/dr.o
 iwlwifi-objs		+= iwl-dbg-tlv.o
 iwlwifi-objs		+= iwl-trans.o
 
@@ -20,6 +21,7 @@ iwlwifi-objs		+= fw/img.o fw/notif-wait.o fw/rs.o
 iwlwifi-objs		+= fw/dbg.o fw/pnvm.o fw/dump.o
 iwlwifi-objs		+= fw/regulatory.o
 iwlwifi-$(CONFIG_IWLMVM) += fw/paging.o fw/smem.o fw/init.o
+iwlwifi-$(CONFIG_IWLMLD) += fw/smem.o fw/init.o
 iwlwifi-$(CONFIG_ACPI) += fw/acpi.o
 iwlwifi-$(CONFIG_EFI)	+= fw/uefi.o
 iwlwifi-$(CONFIG_IWLWIFI_DEBUGFS) += fw/debugfs.o
@@ -33,6 +35,7 @@ ccflags-y += -I$(src)
 obj-$(CONFIG_IWLDVM)	+= dvm/
 obj-$(CONFIG_IWLMVM)	+= mvm/
 obj-$(CONFIG_IWLMEI)	+= mei/
+obj-$(CONFIG_IWLMLD)	+= mld/
 
 obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += tests/
 
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index 64a5bbb45c836..36e8e3a991dcb 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -38,6 +38,11 @@
 #define IWL_BZ_A_HR_B_MODULE_FIRMWARE(api) \
 	IWL_BZ_A_HR_B_FW_PRE "-" __stringify(api) ".ucode"
 
+#if !IS_ENABLED(CONFIG_IWLMVM)
+const char iwl_ax211_name[] = "Intel(R) Wi-Fi 6E AX211 160MHz";
+const char iwl_ax201_name[] = "Intel(R) Wi-Fi 6 AX201 160MHz";
+#endif
+
 static const struct iwl_base_params iwl_bz_base_params = {
 	.eeprom_size = OTP_LOW_IMAGE_SIZE_32K,
 	.num_of_queues = 512,
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
index eb8961b51cb01..f63b25b03b7e4 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/phy.h
@@ -1,11 +1,13 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2012-2014, 2019-2022, 2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2019-2022, 2024-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
 #ifndef __iwl_fw_api_phy_h__
 #define __iwl_fw_api_phy_h__
+#include <linux/types.h>
+#include <linux/bits.h>
 
 /**
  * enum iwl_phy_ops_subcmd_ids - PHY group commands
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 5fc9ce2b350e9..7e4864c00780b 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -653,6 +653,10 @@ extern const struct iwl_cfg iwl_cfg_ma;
 
 extern const struct iwl_cfg iwl_cfg_so_a0_hr_a0;
 extern const struct iwl_cfg iwl_cfg_quz_a0_hr_b0;
+#endif /* CONFIG_IWLMVM */
+
+#if IS_ENABLED(CONFIG_IWLMLD)
+extern const struct iwl_ht_params iwl_bz_ht_params;
 
 extern const struct iwl_ht_params iwl_bz_ht_params;
 
@@ -664,6 +668,6 @@ extern const struct iwl_cfg iwl_cfg_sc2;
 extern const struct iwl_cfg iwl_cfg_sc2f;
 extern const struct iwl_cfg iwl_cfg_dr;
 extern const struct iwl_cfg iwl_cfg_br;
-#endif /* CONFIG_IWLMVM */
+#endif /* CONFIG_IWLMLD */
 
 #endif /* __IWL_CONFIG_H__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index d3a65f33097cb..7606780c59deb 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -75,6 +75,9 @@ struct iwl_drv {
 enum {
 	DVM_OP_MODE,
 	MVM_OP_MODE,
+#if IS_ENABLED(CONFIG_IWLMLD)
+	MLD_OP_MODE,
+#endif
 };
 
 /* Protects the table contents, i.e. the ops pointer & drv list */
@@ -86,6 +89,9 @@ static struct iwlwifi_opmode_table {
 } iwlwifi_opmode_table[] = {		/* ops set when driver is initialized */
 	[DVM_OP_MODE] = { .name = "iwldvm", .ops = NULL },
 	[MVM_OP_MODE] = { .name = "iwlmvm", .ops = NULL },
+#if IS_ENABLED(CONFIG_IWLMLD)
+	[MLD_OP_MODE] = { .name = "iwlmld", .ops = NULL },
+#endif
 };
 
 #define IWL_DEFAULT_SCAN_CHANNELS 40
@@ -316,6 +322,7 @@ struct iwl_firmware_pieces {
 	size_t dbg_trigger_tlv_len[FW_DBG_TRIGGER_MAX];
 	struct iwl_fw_dbg_mem_seg_tlv *dbg_mem_tlv;
 	size_t n_mem_tlv;
+	u32 major;
 };
 
 static void alloc_sec_data(struct iwl_firmware_pieces *pieces,
@@ -957,19 +964,19 @@ static int iwl_parse_tlv_firmware(struct iwl_drv *drv,
 			break;
 		case IWL_UCODE_TLV_FW_VERSION: {
 			const __le32 *ptr = (const void *)tlv_data;
-			u32 major, minor;
+			u32 minor;
 			u8 local_comp;
 
 			if (tlv_len != sizeof(u32) * 3)
 				goto invalid_tlv_len;
 
-			major = le32_to_cpup(ptr++);
+			pieces->major = le32_to_cpup(ptr++);
 			minor = le32_to_cpup(ptr++);
 			local_comp = le32_to_cpup(ptr);
 
 			snprintf(drv->fw.fw_version,
 				 sizeof(drv->fw.fw_version),
-				 "%u.%08x.%u %s", major, minor,
+				 "%u.%08x.%u %s", pieces->major, minor,
 				 local_comp, iwl_reduced_fw_name(drv));
 			break;
 			}
@@ -1468,6 +1475,8 @@ static void _iwl_op_mode_stop(struct iwl_drv *drv)
 	}
 }
 
+#define IWL_MLD_SUPPORTED_FW_VERSION 97
+
 /*
  * iwl_req_fw_callback - callback when firmware was loaded
  *
@@ -1720,6 +1729,19 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 		break;
 	}
 
+#if IS_ENABLED(CONFIG_IWLMLD)
+	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION)
+		op = &iwlwifi_opmode_table[MLD_OP_MODE];
+	else
+#else
+	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION) {
+		IWL_ERR(drv,
+			"IWLMLD needs to be compiled to support this firmware\n");
+		mutex_unlock(&iwlwifi_opmode_table_mtx);
+		goto out_unbind;
+	}
+#endif
+
 	IWL_INFO(drv, "loaded firmware version %s op_mode %s\n",
 		 drv->fw.fw_version, op->name);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/Makefile b/drivers/net/wireless/intel/iwlwifi/mld/Makefile
new file mode 100644
index 0000000000000..ece66e7a9be41
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/Makefile
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+obj-$(CONFIG_IWLMLD)   += iwlmld.o
+obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += tests/
+
+iwlmld-y += mld.o notif.o mac80211.o fw.o power.o iface.o link.o rx.o mcc.o session-protect.o phy.o
+iwlmld-y += scan.o sta.o tx.o coex.o tlc.o agg.o key.o regulatory.o ap.o thermal.o roc.o stats.o
+iwlmld-y += low_latency.o mlo.o ptp.o time_sync.o ftm-initiator.o
+iwlmld-$(CONFIG_IWLWIFI_DEBUGFS) += debugfs.o
+iwlmld-$(CONFIG_IWLWIFI_LEDS) += led.o
+iwlmld-$(CONFIG_PM_SLEEP) += d3.o
+
+# non-upstream things
+iwlmld-$(CONFIG_IWL_VENDOR_CMDS) += vendor-cmd.o
+iwlmld-$(CONFIG_IWLMVM_AX_SOFTAP_TESTMODE) += ax-softap-testmode.o
+
+subdir-ccflags-y += -I$(src)/../
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
new file mode 100644
index 0000000000000..db9e0f04f4b77
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.c
@@ -0,0 +1,670 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include "agg.h"
+#include "sta.h"
+#include "hcmd.h"
+
+static void
+iwl_mld_reorder_release_frames(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			       struct napi_struct *napi,
+			       struct iwl_mld_baid_data *baid_data,
+			       struct iwl_mld_reorder_buffer *reorder_buf,
+			       u16 nssn)
+{
+	struct iwl_mld_reorder_buf_entry *entries =
+		&baid_data->entries[reorder_buf->queue *
+				    baid_data->entries_per_queue];
+	u16 ssn = reorder_buf->head_sn;
+
+	while (ieee80211_sn_less(ssn, nssn)) {
+		int index = ssn % baid_data->buf_size;
+		struct sk_buff_head *skb_list = &entries[index].frames;
+		struct sk_buff *skb;
+
+		ssn = ieee80211_sn_inc(ssn);
+
+		/* Empty the list. Will have more than one frame for A-MSDU.
+		 * Empty list is valid as well since nssn indicates frames were
+		 * received.
+		 */
+		while ((skb = __skb_dequeue(skb_list))) {
+			iwl_mld_pass_packet_to_mac80211(mld, napi, skb,
+							reorder_buf->queue,
+							sta);
+			reorder_buf->num_stored--;
+		}
+	}
+	reorder_buf->head_sn = nssn;
+}
+
+static void iwl_mld_release_frames_from_notif(struct iwl_mld *mld,
+					      struct napi_struct *napi,
+					      u8 baid, u16 nssn, int queue)
+{
+	struct iwl_mld_reorder_buffer *reorder_buf;
+	struct iwl_mld_baid_data *ba_data;
+	struct ieee80211_link_sta *link_sta;
+	u32 sta_id;
+
+	IWL_DEBUG_HT(mld, "Frame release notification for BAID %u, NSSN %d\n",
+		     baid, nssn);
+
+	if (WARN_ON_ONCE(baid == IWL_RX_REORDER_DATA_INVALID_BAID ||
+			 baid >= ARRAY_SIZE(mld->fw_id_to_ba)))
+		return;
+
+	rcu_read_lock();
+
+	ba_data = rcu_dereference(mld->fw_id_to_ba[baid]);
+	if (!ba_data) {
+		IWL_DEBUG_HT(mld, "BAID %d not found in map\n", baid);
+		goto out_unlock;
+	}
+
+	/* pick any STA ID to find the pointer */
+	sta_id = ffs(ba_data->sta_mask) - 1;
+	link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]);
+	if (WARN_ON_ONCE(IS_ERR_OR_NULL(link_sta) || !link_sta->sta))
+		goto out_unlock;
+
+	reorder_buf = &ba_data->reorder_buf[queue];
+
+	iwl_mld_reorder_release_frames(mld, link_sta->sta, napi, ba_data,
+				       reorder_buf, nssn);
+out_unlock:
+	rcu_read_unlock();
+}
+
+void iwl_mld_handle_frame_release_notif(struct iwl_mld *mld,
+					struct napi_struct *napi,
+					struct iwl_rx_packet *pkt, int queue)
+{
+	struct iwl_frame_release *release = (void *)pkt->data;
+	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+
+	if (IWL_FW_CHECK(mld, pkt_len < sizeof(*release),
+			 "Unexpected frame release notif size %u (expected %zu)\n",
+			 pkt_len, sizeof(*release)))
+		return;
+
+	iwl_mld_release_frames_from_notif(mld, napi, release->baid,
+					  le16_to_cpu(release->nssn),
+					  queue);
+}
+
+void iwl_mld_handle_bar_frame_release_notif(struct iwl_mld *mld,
+					    struct napi_struct *napi,
+					    struct iwl_rx_packet *pkt,
+					    int queue)
+{
+	struct iwl_bar_frame_release *release = (void *)pkt->data;
+	struct iwl_mld_baid_data *baid_data;
+	unsigned int baid, nssn, sta_id, tid;
+	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+
+	if (IWL_FW_CHECK(mld, pkt_len < sizeof(*release),
+			 "Unexpected frame release notif size %u (expected %zu)\n",
+			 pkt_len, sizeof(*release)))
+		return;
+
+	baid = le32_get_bits(release->ba_info,
+			     IWL_BAR_FRAME_RELEASE_BAID_MASK);
+	nssn = le32_get_bits(release->ba_info,
+			     IWL_BAR_FRAME_RELEASE_NSSN_MASK);
+	sta_id = le32_get_bits(release->sta_tid,
+			       IWL_BAR_FRAME_RELEASE_STA_MASK);
+	tid = le32_get_bits(release->sta_tid,
+			    IWL_BAR_FRAME_RELEASE_TID_MASK);
+
+	if (IWL_FW_CHECK(mld, baid >= ARRAY_SIZE(mld->fw_id_to_ba),
+			 "BAR release: invalid BAID (%x)\n", baid))
+		return;
+
+	rcu_read_lock();
+	baid_data = rcu_dereference(mld->fw_id_to_ba[baid]);
+	if (!IWL_FW_CHECK(mld, !baid_data,
+			  "Got valid BAID %d but not allocated, invalid BAR release!\n",
+			  baid))
+		goto out_unlock;
+
+	if (IWL_FW_CHECK(mld, tid != baid_data->tid ||
+			 sta_id > mld->fw->ucode_capa.num_stations ||
+			 !(baid_data->sta_mask & BIT(sta_id)),
+			 "BAID 0x%x is mapped to sta_mask:0x%x tid:%d, but BAR release received for sta:%d tid:%d\n",
+			 baid, baid_data->sta_mask, baid_data->tid, sta_id,
+			 tid))
+		goto out_unlock;
+
+	IWL_DEBUG_DROP(mld, "Received a BAR, expect packet loss: nssn %d\n",
+		       nssn);
+
+	iwl_mld_release_frames_from_notif(mld, napi, baid, nssn, queue);
+out_unlock:
+	rcu_read_unlock();
+}
+
+void iwl_mld_del_ba(struct iwl_mld *mld, int queue,
+		    struct iwl_mld_delba_data *data)
+{
+	struct iwl_mld_baid_data *ba_data;
+	struct iwl_mld_reorder_buffer *reorder_buf;
+	struct ieee80211_link_sta *link_sta;
+	u8 baid = data->baid;
+	u32 sta_id;
+
+	if (WARN_ONCE(baid >= IWL_MAX_BAID, "invalid BAID: %x\n", baid))
+		return;
+
+	rcu_read_lock();
+
+	ba_data = rcu_dereference(mld->fw_id_to_ba[baid]);
+	if (WARN_ON_ONCE(!ba_data))
+		goto out_unlock;
+
+	/* pick any STA ID to find the pointer */
+	sta_id = ffs(ba_data->sta_mask) - 1;
+	link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]);
+	if (WARN_ON_ONCE(IS_ERR_OR_NULL(link_sta) || !link_sta->sta))
+		goto out_unlock;
+
+	reorder_buf = &ba_data->reorder_buf[queue];
+
+	/* release all frames that are in the reorder buffer to the stack */
+	iwl_mld_reorder_release_frames(mld, link_sta->sta, NULL,
+				       ba_data, reorder_buf,
+				       ieee80211_sn_add(reorder_buf->head_sn,
+							ba_data->buf_size));
+out_unlock:
+	rcu_read_unlock();
+}
+
+/* Returns true if the MPDU was buffered\dropped, false if it should be passed
+ * to upper layer.
+ */
+enum iwl_mld_reorder_result
+iwl_mld_reorder(struct iwl_mld *mld, struct napi_struct *napi,
+		int queue, struct ieee80211_sta *sta,
+		struct sk_buff *skb, struct iwl_rx_mpdu_desc *desc)
+{
+	struct ieee80211_hdr *hdr = (void *)skb_mac_header(skb);
+	struct iwl_mld_baid_data *baid_data;
+	struct iwl_mld_reorder_buffer *buffer;
+	struct iwl_mld_reorder_buf_entry *entries;
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_link_sta *mld_link_sta;
+	u32 reorder = le32_to_cpu(desc->reorder_data);
+	bool amsdu, last_subframe, is_old_sn, is_dup;
+	u8 tid = ieee80211_get_tid(hdr);
+	u8 baid;
+	u16 nssn, sn;
+	u32 sta_mask = 0;
+	int index;
+	u8 link_id;
+
+	baid = u32_get_bits(reorder, IWL_RX_MPDU_REORDER_BAID_MASK);
+
+	/* This also covers the case of receiving a Block Ack Request
+	 * outside a BA session; we'll pass it to mac80211 and that
+	 * then sends a delBA action frame.
+	 * This also covers pure monitor mode, in which case we won't
+	 * have any BA sessions.
+	 */
+	if (baid == IWL_RX_REORDER_DATA_INVALID_BAID)
+		return IWL_MLD_PASS_SKB;
+
+	/* no sta yet */
+	if (WARN_ONCE(!sta,
+		      "Got valid BAID without a valid station assigned\n"))
+		return IWL_MLD_PASS_SKB;
+
+	/* not a data packet */
+	if (!ieee80211_is_data_qos(hdr->frame_control) ||
+	    is_multicast_ether_addr(hdr->addr1))
+		return IWL_MLD_PASS_SKB;
+
+	if (unlikely(!ieee80211_is_data_present(hdr->frame_control)))
+		return IWL_MLD_PASS_SKB;
+
+	baid_data = rcu_dereference(mld->fw_id_to_ba[baid]);
+	if (!baid_data) {
+		IWL_DEBUG_HT(mld,
+			     "Got valid BAID but no baid allocated, bypass re-ordering (BAID=%d reorder=0x%x)\n",
+			     baid, reorder);
+		return IWL_MLD_PASS_SKB;
+	}
+
+	for_each_mld_link_sta(mld_sta, mld_link_sta, link_id)
+		sta_mask |= BIT(mld_link_sta->fw_id);
+
+	/* verify the BAID is correctly mapped to the sta and tid */
+	if (IWL_FW_CHECK(mld,
+			 tid != baid_data->tid ||
+			 !(sta_mask & baid_data->sta_mask),
+			 "BAID 0x%x is mapped to sta_mask:0x%x tid:%d, but was received for sta_mask:0x%x tid:%d\n",
+			 baid, baid_data->sta_mask, baid_data->tid,
+			 sta_mask, tid))
+		return IWL_MLD_PASS_SKB;
+
+	buffer = &baid_data->reorder_buf[queue];
+	entries = &baid_data->entries[queue * baid_data->entries_per_queue];
+
+	is_old_sn = !!(reorder & IWL_RX_MPDU_REORDER_BA_OLD_SN);
+
+	if (!buffer->valid && is_old_sn)
+		return IWL_MLD_PASS_SKB;
+
+	buffer->valid = true;
+
+	is_dup = !!(desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_DUPLICATE));
+
+	/* drop any duplicated or outdated packets */
+	if (is_dup || is_old_sn)
+		return IWL_MLD_DROP_SKB;
+
+	sn = u32_get_bits(reorder, IWL_RX_MPDU_REORDER_SN_MASK);
+	nssn = u32_get_bits(reorder, IWL_RX_MPDU_REORDER_NSSN_MASK);
+	amsdu = desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU;
+	last_subframe = desc->amsdu_info & IWL_RX_MPDU_AMSDU_LAST_SUBFRAME;
+
+	/* release immediately if allowed by nssn and no stored frames */
+	if (!buffer->num_stored && ieee80211_sn_less(sn, nssn)) {
+		if (!amsdu || last_subframe)
+			buffer->head_sn = nssn;
+		return IWL_MLD_PASS_SKB;
+	}
+
+	/* release immediately if there are no stored frames, and the sn is
+	 * equal to the head.
+	 * This can happen due to reorder timer, where NSSN is behind head_sn.
+	 * When we released everything, and we got the next frame in the
+	 * sequence, according to the NSSN we can't release immediately,
+	 * while technically there is no hole and we can move forward.
+	 */
+	if (!buffer->num_stored && sn == buffer->head_sn) {
+		if (!amsdu || last_subframe)
+			buffer->head_sn = ieee80211_sn_inc(buffer->head_sn);
+		return IWL_MLD_PASS_SKB;
+	}
+
+	/* put in reorder buffer */
+	index = sn % baid_data->buf_size;
+	__skb_queue_tail(&entries[index].frames, skb);
+	buffer->num_stored++;
+
+	/* We cannot trust NSSN for AMSDU sub-frames that are not the last. The
+	 * reason is that NSSN advances on the first sub-frame, and may cause
+	 * the reorder buffer to advance before all the sub-frames arrive.
+	 *
+	 * Example: reorder buffer contains SN 0 & 2, and we receive AMSDU with
+	 * SN 1. NSSN for first sub frame will be 3 with the result of driver
+	 * releasing SN 0,1, 2. When sub-frame 1 arrives - reorder buffer is
+	 * already ahead and it will be dropped.
+	 * If the last sub-frame is not on this queue - we will get frame
+	 * release notification with up to date NSSN.
+	 */
+	if (!amsdu || last_subframe)
+		iwl_mld_reorder_release_frames(mld, sta, napi, baid_data,
+					       buffer, nssn);
+
+	return IWL_MLD_BUFFERED_SKB;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_reorder);
+
+static void iwl_mld_rx_agg_session_expired(struct timer_list *t)
+{
+	struct iwl_mld_baid_data *data =
+		from_timer(data, t, session_timer);
+	struct iwl_mld_baid_data __rcu **rcu_ptr = data->rcu_ptr;
+	struct iwl_mld_baid_data *ba_data;
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_sta *mld_sta;
+	unsigned long timeout;
+	unsigned int sta_id;
+
+	rcu_read_lock();
+
+	ba_data = rcu_dereference(*rcu_ptr);
+	if (WARN_ON(!ba_data))
+		goto unlock;
+
+	if (WARN_ON(!ba_data->timeout))
+		goto unlock;
+
+	timeout = ba_data->last_rx_timestamp +
+		  TU_TO_JIFFIES(ba_data->timeout * 2);
+	if (time_is_after_jiffies(timeout)) {
+		mod_timer(&ba_data->session_timer, timeout);
+		goto unlock;
+	}
+
+	/* timer expired, pick any STA ID to find the pointer */
+	sta_id = ffs(ba_data->sta_mask) - 1;
+	link_sta = rcu_dereference(ba_data->mld->fw_id_to_link_sta[sta_id]);
+
+	/* sta should be valid unless the following happens:
+	 * The firmware asserts which triggers a reconfig flow, but
+	 * the reconfig fails before we set the pointer to sta into
+	 * the fw_id_to_link_sta pointer table. mac80211 can't stop
+	 * A-MPDU and hence the timer continues to run. Then, the
+	 * timer expires and sta is NULL.
+	 */
+	if (IS_ERR_OR_NULL(link_sta) || WARN_ON(!link_sta->sta))
+		goto unlock;
+
+	mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+	ieee80211_rx_ba_timer_expired(mld_sta->vif, link_sta->sta->addr,
+				      ba_data->tid);
+unlock:
+	rcu_read_unlock();
+}
+
+static int
+iwl_mld_stop_ba_in_fw(struct iwl_mld *mld, struct ieee80211_sta *sta, int tid)
+{
+	struct iwl_rx_baid_cfg_cmd cmd = {
+		.action = cpu_to_le32(IWL_RX_BAID_ACTION_REMOVE),
+		.remove.sta_id_mask =
+			cpu_to_le32(iwl_mld_fw_sta_id_mask(mld, sta)),
+		.remove.tid = cpu_to_le32(tid),
+
+	};
+	int ret;
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(DATA_PATH_GROUP,
+					   RX_BAID_ALLOCATION_CONFIG_CMD),
+				   &cmd);
+	if (ret)
+		return ret;
+
+	IWL_DEBUG_HT(mld, "RX BA Session stopped in fw\n");
+
+	return ret;
+}
+
+static int
+iwl_mld_start_ba_in_fw(struct iwl_mld *mld, struct ieee80211_sta *sta,
+		       int tid, u16 ssn, u16 buf_size)
+{
+	struct iwl_rx_baid_cfg_cmd cmd = {
+		.action = cpu_to_le32(IWL_RX_BAID_ACTION_ADD),
+		.alloc.sta_id_mask =
+			cpu_to_le32(iwl_mld_fw_sta_id_mask(mld, sta)),
+		.alloc.tid = tid,
+		.alloc.ssn = cpu_to_le16(ssn),
+		.alloc.win_size = cpu_to_le16(buf_size),
+	};
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(DATA_PATH_GROUP, RX_BAID_ALLOCATION_CONFIG_CMD),
+		.flags = CMD_WANT_SKB,
+		.len[0] = sizeof(cmd),
+		.data[0] = &cmd,
+	};
+	struct iwl_rx_baid_cfg_resp *resp;
+	struct iwl_rx_packet *pkt;
+	u32 resp_len;
+	int ret, baid;
+
+	BUILD_BUG_ON(sizeof(*resp) != sizeof(baid));
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (ret)
+		return ret;
+
+	pkt = hcmd.resp_pkt;
+
+	resp_len = iwl_rx_packet_payload_len(pkt);
+	if (IWL_FW_CHECK(mld, resp_len != sizeof(*resp),
+			 "BAID_ALLOC_CMD: unexpected response length %d\n",
+			 resp_len)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	IWL_DEBUG_HT(mld, "RX BA Session started in fw\n");
+
+	resp = (void *)pkt->data;
+	baid = le32_to_cpu(resp->baid);
+
+	if (IWL_FW_CHECK(mld, baid < 0 || baid >= ARRAY_SIZE(mld->fw_id_to_ba),
+			 "BAID_ALLOC_CMD: invalid BAID response %d\n", baid)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	ret = baid;
+out:
+	iwl_free_resp(&hcmd);
+	return ret;
+}
+
+static void iwl_mld_init_reorder_buffer(struct iwl_mld *mld,
+					struct iwl_mld_baid_data *data,
+					u16 ssn)
+{
+	for (int i = 0; i < mld->trans->num_rx_queues; i++) {
+		struct iwl_mld_reorder_buffer *reorder_buf =
+			&data->reorder_buf[i];
+		struct iwl_mld_reorder_buf_entry *entries =
+			&data->entries[i * data->entries_per_queue];
+
+		reorder_buf->head_sn = ssn;
+		reorder_buf->queue = i;
+
+		for (int j = 0; j < data->buf_size; j++)
+			__skb_queue_head_init(&entries[j].frames);
+	}
+}
+
+static void iwl_mld_free_reorder_buffer(struct iwl_mld *mld,
+					struct iwl_mld_baid_data *data)
+{
+	struct iwl_mld_delba_data delba_data = {
+		.baid = data->baid,
+	};
+
+	iwl_mld_sync_rx_queues(mld, IWL_MLD_RXQ_NOTIF_DEL_BA,
+			       &delba_data, sizeof(delba_data));
+
+	for (int i = 0; i < mld->trans->num_rx_queues; i++) {
+		struct iwl_mld_reorder_buffer *reorder_buf =
+			&data->reorder_buf[i];
+		struct iwl_mld_reorder_buf_entry *entries =
+			&data->entries[i * data->entries_per_queue];
+
+		if (likely(!reorder_buf->num_stored))
+			continue;
+
+		/* This shouldn't happen in regular DELBA since the RX queues
+		 * sync internal DELBA notification should trigger a release
+		 * of all frames in the reorder buffer.
+		 */
+		WARN_ON(1);
+
+		for (int j = 0; j < data->buf_size; j++)
+			__skb_queue_purge(&entries[j].frames);
+	}
+}
+
+int iwl_mld_ampdu_rx_start(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			   int tid, u16 ssn, u16 buf_size, u16 timeout)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_baid_data *baid_data = NULL;
+	u32 reorder_buf_size = buf_size * sizeof(baid_data->entries[0]);
+	int ret, baid;
+	u32 sta_mask;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (mld->num_rx_ba_sessions >= IWL_MAX_BAID) {
+		IWL_DEBUG_HT(mld,
+			     "Max num of RX BA sessions reached; blocking new session\n");
+		return -ENOSPC;
+	}
+
+	sta_mask = iwl_mld_fw_sta_id_mask(mld, sta);
+	if (WARN_ON(!sta_mask))
+		return -EINVAL;
+
+	/* sparse doesn't like the __align() so don't check */
+#ifndef __CHECKER__
+	/* The division below will be OK if either the cache line size
+	 * can be divided by the entry size (ALIGN will round up) or if
+	 * the entry size can be divided by the cache line size, in which
+	 * case the ALIGN() will do nothing.
+	 */
+	BUILD_BUG_ON(SMP_CACHE_BYTES % sizeof(baid_data->entries[0]) &&
+		     sizeof(baid_data->entries[0]) % SMP_CACHE_BYTES);
+#endif
+
+	/* Upward align the reorder buffer size to fill an entire cache
+	 * line for each queue, to avoid sharing cache lines between
+	 * different queues.
+	 */
+	reorder_buf_size = ALIGN(reorder_buf_size, SMP_CACHE_BYTES);
+
+	/* Allocate here so if allocation fails we can bail out early
+	 * before starting the BA session in the firmware
+	 */
+	baid_data = kzalloc(sizeof(*baid_data) +
+			    mld->trans->num_rx_queues * reorder_buf_size,
+			    GFP_KERNEL);
+	if (!baid_data)
+		return -ENOMEM;
+
+	/* This division is why we need the above BUILD_BUG_ON(),
+	 * if that doesn't hold then this will not be right.
+	 */
+	baid_data->entries_per_queue =
+		reorder_buf_size / sizeof(baid_data->entries[0]);
+
+	baid = iwl_mld_start_ba_in_fw(mld, sta, tid, ssn, buf_size);
+	if (baid < 0) {
+		ret = baid;
+		goto out_free;
+	}
+
+	mld->num_rx_ba_sessions++;
+	mld_sta->tid_to_baid[tid] = baid;
+
+	baid_data->baid = baid;
+	baid_data->mld = mld;
+	baid_data->tid = tid;
+	baid_data->buf_size = buf_size;
+	baid_data->sta_mask = sta_mask;
+	baid_data->timeout = timeout;
+	baid_data->last_rx_timestamp = jiffies;
+	baid_data->rcu_ptr = &mld->fw_id_to_ba[baid];
+
+	iwl_mld_init_reorder_buffer(mld, baid_data, ssn);
+
+	timer_setup(&baid_data->session_timer, iwl_mld_rx_agg_session_expired,
+		    0);
+	if (timeout)
+		mod_timer(&baid_data->session_timer,
+			  TU_TO_EXP_TIME(timeout * 2));
+
+	IWL_DEBUG_HT(mld, "STA mask=0x%x (tid=%d) is assigned to BAID %d\n",
+		     baid_data->sta_mask, tid, baid);
+
+	/* protect the BA data with RCU to cover a case where our
+	 * internal RX sync mechanism will timeout (not that it's
+	 * supposed to happen) and we will free the session data while
+	 * RX is being processed in parallel
+	 */
+	WARN_ON(rcu_access_pointer(mld->fw_id_to_ba[baid]));
+	rcu_assign_pointer(mld->fw_id_to_ba[baid], baid_data);
+
+	return 0;
+
+out_free:
+	kfree(baid_data);
+	return ret;
+}
+
+int iwl_mld_ampdu_rx_stop(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			  int tid)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	int baid = mld_sta->tid_to_baid[tid];
+	struct iwl_mld_baid_data *baid_data;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* during firmware restart, do not send the command as the firmware no
+	 * longer recognizes the session. instead, only clear the driver BA
+	 * session data.
+	 */
+	if (!mld->fw_status.in_hw_restart) {
+		ret = iwl_mld_stop_ba_in_fw(mld, sta, tid);
+		if (ret)
+			return ret;
+	}
+
+	if (!WARN_ON(mld->num_rx_ba_sessions == 0))
+		mld->num_rx_ba_sessions--;
+
+	baid_data = wiphy_dereference(mld->wiphy, mld->fw_id_to_ba[baid]);
+	if (WARN_ON(!baid_data))
+		return -EINVAL;
+
+	if (timer_pending(&baid_data->session_timer))
+		timer_shutdown_sync(&baid_data->session_timer);
+
+	iwl_mld_free_reorder_buffer(mld, baid_data);
+
+	RCU_INIT_POINTER(mld->fw_id_to_ba[baid], NULL);
+	kfree_rcu(baid_data, rcu_head);
+
+	IWL_DEBUG_HT(mld, "BAID %d is free\n", baid);
+
+	return 0;
+}
+
+int iwl_mld_update_sta_baids(struct iwl_mld *mld,
+			     u32 old_sta_mask,
+			     u32 new_sta_mask)
+{
+	struct iwl_rx_baid_cfg_cmd cmd = {
+		.action = cpu_to_le32(IWL_RX_BAID_ACTION_MODIFY),
+		.modify.old_sta_id_mask = cpu_to_le32(old_sta_mask),
+		.modify.new_sta_id_mask = cpu_to_le32(new_sta_mask),
+	};
+	u32 cmd_id = WIDE_ID(DATA_PATH_GROUP, RX_BAID_ALLOCATION_CONFIG_CMD);
+	int baid;
+
+	/* mac80211 will remove sessions later, but we ignore all that */
+	if (mld->fw_status.in_hw_restart)
+		return 0;
+
+	BUILD_BUG_ON(sizeof(struct iwl_rx_baid_cfg_resp) != sizeof(baid));
+
+	for (baid = 0; baid < ARRAY_SIZE(mld->fw_id_to_ba); baid++) {
+		struct iwl_mld_baid_data *data;
+		int ret;
+
+		data = wiphy_dereference(mld->wiphy, mld->fw_id_to_ba[baid]);
+		if (!data)
+			continue;
+
+		if (!(data->sta_mask & old_sta_mask))
+			continue;
+
+		WARN_ONCE(data->sta_mask != old_sta_mask,
+			  "BAID data for %d corrupted - expected 0x%x found 0x%x\n",
+			  baid, old_sta_mask, data->sta_mask);
+
+		cmd.modify.tid = cpu_to_le32(data->tid);
+
+		ret = iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd);
+		if (ret)
+			return ret;
+		data->sta_mask = new_sta_mask;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/agg.h b/drivers/net/wireless/intel/iwlwifi/mld/agg.h
new file mode 100644
index 0000000000000..651c80d1c7cda
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/agg.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_agg_h__
+#define __iwl_agg_h__
+
+#include "mld.h"
+#include "fw/api/rx.h"
+
+/**
+ * struct iwl_mld_reorder_buffer - per ra/tid/queue reorder buffer
+ * @head_sn: reorder window head sequence number
+ * @num_stored: number of MPDUs stored in the buffer
+ * @queue: queue of this reorder buffer
+ * @valid: true if reordering is valid for this queue
+ */
+struct iwl_mld_reorder_buffer {
+	u16 head_sn;
+	u16 num_stored;
+	int queue;
+	bool valid;
+} ____cacheline_aligned_in_smp;
+
+/**
+ * struct iwl_mld_reorder_buf_entry - reorder buffer entry per-queue/per-seqno
+ * @frames: list of skbs stored. a list is necessary because in an A-MSDU,
+ *	all sub-frames share the same sequence number, so they are stored
+ *	together in the same list.
+ */
+struct iwl_mld_reorder_buf_entry {
+	struct sk_buff_head frames;
+}
+#ifndef __CHECKER__
+/* sparse doesn't like this construct: "bad integer constant expression" */
+__aligned(roundup_pow_of_two(sizeof(struct sk_buff_head)))
+#endif
+;
+
+/**
+ * struct iwl_mld_baid_data - Block Ack session data
+ * @rcu_head: RCU head for freeing this data
+ * @sta_mask: station mask for the BAID
+ * @tid: tid of the session
+ * @baid: baid of the session
+ * @buf_size: the reorder buffer size as set by the last ADDBA request
+ * @entries_per_queue: number of buffers per queue, this actually gets
+ *	aligned up to avoid cache line sharing between queues
+ * @timeout: the timeout value specified in the ADDBA request.
+ * @last_rx_timestamp: timestamp of the last received packet (in jiffies). This
+ *	value is updated only when the configured @timeout has passed since
+ *	the last update to minimize cache bouncing between RX queues.
+ * @session_timer: timer is set to expire after 2 * @timeout (since we want
+ *	to minimize the cache bouncing by updating @last_rx_timestamp only once
+ *	after @timeout has passed). If no packets are received within this
+ *	period, it informs mac80211 to initiate delBA flow, terminating the
+ *	BA session.
+ * @rcu_ptr: BA data RCU protected access
+ * @mld: mld pointer, needed for timer context
+ * @reorder_buf: reorder buffer, allocated per queue
+ * @entries: data
+ */
+struct iwl_mld_baid_data {
+	struct rcu_head rcu_head;
+	u32 sta_mask;
+	u8 tid;
+	u8 baid;
+	u16 buf_size;
+	u16 entries_per_queue;
+	u16 timeout;
+	struct timer_list session_timer;
+	unsigned long last_rx_timestamp;
+	struct iwl_mld_baid_data __rcu **rcu_ptr;
+	struct iwl_mld *mld;
+	struct iwl_mld_reorder_buffer reorder_buf[IWL_MAX_RX_HW_QUEUES];
+	struct iwl_mld_reorder_buf_entry entries[] ____cacheline_aligned_in_smp;
+};
+
+/**
+ * struct iwl_mld_delba_data - RX queue sync data for %IWL_MLD_RXQ_NOTIF_DEL_BA
+ *
+ * @baid: Block Ack id, used to identify the BA session to be removed
+ */
+struct iwl_mld_delba_data {
+	u32 baid;
+} __packed;
+
+/**
+ * enum iwl_mld_reorder_result - Possible return values for iwl_mld_reorder()
+ * indicating how the caller should handle the skb based on the result.
+ *
+ * @IWL_MLD_PASS_SKB: skb should be passed to upper layer.
+ * @IWL_MLD_BUFFERED_SKB: skb has been buffered, don't pass it to upper layer.
+ * @IWL_MLD_DROP_SKB: skb should be dropped and freed by the caller.
+ */
+enum iwl_mld_reorder_result {
+	IWL_MLD_PASS_SKB,
+	IWL_MLD_BUFFERED_SKB,
+	IWL_MLD_DROP_SKB
+};
+
+int iwl_mld_ampdu_rx_start(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			   int tid, u16 ssn, u16 buf_size, u16 timeout);
+int iwl_mld_ampdu_rx_stop(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			  int tid);
+
+enum iwl_mld_reorder_result
+iwl_mld_reorder(struct iwl_mld *mld, struct napi_struct *napi,
+		int queue, struct ieee80211_sta *sta,
+		struct sk_buff *skb, struct iwl_rx_mpdu_desc *desc);
+
+void iwl_mld_handle_frame_release_notif(struct iwl_mld *mld,
+					struct napi_struct *napi,
+					struct iwl_rx_packet *pkt, int queue);
+void iwl_mld_handle_bar_frame_release_notif(struct iwl_mld *mld,
+					    struct napi_struct *napi,
+					    struct iwl_rx_packet *pkt,
+					    int queue);
+
+void iwl_mld_del_ba(struct iwl_mld *mld, int queue,
+		    struct iwl_mld_delba_data *data);
+
+int iwl_mld_update_sta_baids(struct iwl_mld *mld,
+			     u32 old_sta_mask,
+			     u32 new_sta_mask);
+
+#endif /* __iwl_agg_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ap.c b/drivers/net/wireless/intel/iwlwifi/mld/ap.c
new file mode 100644
index 0000000000000..571eabd0b511f
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ap.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <linux/crc32.h>
+
+#include <net/mac80211.h>
+
+#include "ap.h"
+#include "hcmd.h"
+#include "tx.h"
+#include "power.h"
+#include "key.h"
+#include "iwl-utils.h"
+
+#include "fw/api/sta.h"
+
+void iwl_mld_set_tim_idx(struct iwl_mld *mld, __le32 *tim_index,
+			 u8 *beacon, u32 frame_size)
+{
+	u32 tim_idx;
+	struct ieee80211_mgmt *mgmt = (void *)beacon;
+
+	/* The index is relative to frame start but we start looking at the
+	 * variable-length part of the beacon.
+	 */
+	tim_idx = mgmt->u.beacon.variable - beacon;
+
+	/* Parse variable-length elements of beacon to find WLAN_EID_TIM */
+	while ((tim_idx < (frame_size - 2)) &&
+	       (beacon[tim_idx] != WLAN_EID_TIM))
+		tim_idx += beacon[tim_idx + 1] + 2;
+
+	/* If TIM field was found, set variables */
+	if ((tim_idx < (frame_size - 1)) && beacon[tim_idx] == WLAN_EID_TIM)
+		*tim_index = cpu_to_le32(tim_idx);
+	else
+		IWL_WARN(mld, "Unable to find TIM Element in beacon\n");
+}
+
+u8 iwl_mld_get_rate_flags(struct iwl_mld *mld,
+			  struct ieee80211_tx_info *info,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link,
+			  enum nl80211_band band)
+{
+	u32 legacy = link->beacon_tx_rate.control[band].legacy;
+	u32 rate_idx, rate_flags = 0, fw_rate;
+
+	/* if beacon rate was configured try using it */
+	if (hweight32(legacy) == 1) {
+		u32 rate = ffs(legacy) - 1;
+		struct ieee80211_supported_band *sband =
+			mld->hw->wiphy->bands[band];
+
+		rate_idx = sband->bitrates[rate].hw_value;
+	} else {
+		rate_idx = iwl_mld_get_lowest_rate(mld, info, vif);
+	}
+
+	if (rate_idx <= IWL_LAST_CCK_RATE)
+		rate_flags = IWL_MAC_BEACON_CCK;
+
+	/* Legacy rates are indexed as follows:
+	 * 0 - 3 for CCK and 0 - 7 for OFDM.
+	 */
+	fw_rate = (rate_idx >= IWL_FIRST_OFDM_RATE ?
+		     rate_idx - IWL_FIRST_OFDM_RATE : rate_idx);
+
+	return fw_rate | rate_flags;
+}
+
+int iwl_mld_send_beacon_template_cmd(struct iwl_mld *mld,
+				     struct sk_buff *beacon,
+				     struct iwl_mac_beacon_cmd *cmd)
+{
+	struct iwl_host_cmd hcmd = {
+		.id = BEACON_TEMPLATE_CMD,
+	};
+
+	hcmd.len[0] = sizeof(*cmd);
+	hcmd.data[0] = cmd;
+
+	hcmd.len[1] = beacon->len;
+	hcmd.data[1] = beacon->data;
+	hcmd.dataflags[1] = IWL_HCMD_DFL_DUP;
+
+	return iwl_mld_send_cmd(mld, &hcmd);
+}
+
+static int iwl_mld_fill_beacon_template_cmd(struct iwl_mld *mld,
+					    struct ieee80211_vif *vif,
+					    struct sk_buff *beacon,
+					    struct iwl_mac_beacon_cmd *cmd,
+					    struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(beacon);
+	struct ieee80211_chanctx_conf *ctx;
+	bool enable_fils;
+	u16 flags = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	cmd->link_id = cpu_to_le32(mld_link->fw_id);
+
+	ctx = wiphy_dereference(mld->wiphy, link->chanctx_conf);
+	if (WARN_ON(!ctx || !ctx->def.chan))
+		return -EINVAL;
+
+	enable_fils = cfg80211_channel_is_psc(ctx->def.chan) ||
+		(ctx->def.chan->band == NL80211_BAND_6GHZ &&
+		 ctx->def.width >= NL80211_CHAN_WIDTH_80);
+
+	if (enable_fils) {
+		flags |= IWL_MAC_BEACON_FILS;
+		cmd->short_ssid = cpu_to_le32(~crc32_le(~0, vif->cfg.ssid,
+							vif->cfg.ssid_len));
+	}
+
+	cmd->byte_cnt = cpu_to_le16((u16)beacon->len);
+
+	flags |= iwl_mld_get_rate_flags(mld, info, vif, link,
+					ctx->def.chan->band);
+
+	cmd->flags = cpu_to_le16(flags);
+
+	if (vif->type == NL80211_IFTYPE_AP) {
+		iwl_mld_set_tim_idx(mld, &cmd->tim_idx,
+				    beacon->data, beacon->len);
+
+		cmd->btwt_offset =
+			cpu_to_le32(iwl_find_ie_offset(beacon->data,
+						       WLAN_EID_S1G_TWT,
+						       beacon->len));
+	}
+
+	cmd->csa_offset =
+		cpu_to_le32(iwl_find_ie_offset(beacon->data,
+					       WLAN_EID_CHANNEL_SWITCH,
+					       beacon->len));
+	cmd->ecsa_offset =
+		cpu_to_le32(iwl_find_ie_offset(beacon->data,
+					       WLAN_EID_EXT_CHANSWITCH_ANN,
+					       beacon->len));
+
+	return 0;
+}
+
+/* The beacon template for the AP/GO/IBSS has changed and needs update */
+int iwl_mld_update_beacon_template(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_bss_conf *link_conf)
+{
+	struct iwl_mac_beacon_cmd cmd = {};
+	struct sk_buff *beacon;
+	int ret;
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+#endif
+
+	WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+		vif->type != NL80211_IFTYPE_ADHOC);
+
+	if (IWL_MLD_NON_TRANSMITTING_AP)
+		return 0;
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	if (mld_vif->beacon_inject_active) {
+		IWL_DEBUG_INFO(mld,
+			       "Can't update template, beacon injection's active\n");
+		return -EBUSY;
+	}
+
+#endif
+	beacon = ieee80211_beacon_get_template(mld->hw, vif, NULL,
+					       link_conf->link_id);
+	if (!beacon)
+		return -ENOMEM;
+
+	ret = iwl_mld_fill_beacon_template_cmd(mld, vif, beacon, &cmd,
+					       link_conf);
+
+	if (!ret)
+		ret = iwl_mld_send_beacon_template_cmd(mld, beacon, &cmd);
+
+	dev_kfree_skb(beacon);
+
+	return ret;
+}
+
+void iwl_mld_free_ap_early_key(struct iwl_mld *mld,
+			       struct ieee80211_key_conf *key,
+			       struct iwl_mld_vif *mld_vif)
+{
+	struct iwl_mld_link *link;
+
+	if (WARN_ON(key->link_id < 0))
+		return;
+
+	link = iwl_mld_link_dereference_check(mld_vif, key->link_id);
+	if (WARN_ON(!link))
+		return;
+
+	for (int i = 0; i < ARRAY_SIZE(link->ap_early_keys); i++) {
+		if (link->ap_early_keys[i] != key)
+			continue;
+		/* Those weren't sent to FW, so should be marked as INVALID */
+		if (WARN_ON(key->hw_key_idx != STA_KEY_IDX_INVALID))
+			key->hw_key_idx = STA_KEY_IDX_INVALID;
+		link->ap_early_keys[i] = NULL;
+	}
+}
+
+int iwl_mld_store_ap_early_key(struct iwl_mld *mld,
+			       struct ieee80211_key_conf *key,
+			       struct iwl_mld_vif *mld_vif)
+{
+	struct iwl_mld_link *link;
+
+	if (WARN_ON(key->link_id < 0))
+		return -EINVAL;
+
+	link = iwl_mld_link_dereference_check(mld_vif, key->link_id);
+	if (WARN_ON(!link))
+		return -EINVAL;
+
+	for (int i = 0; i < ARRAY_SIZE(link->ap_early_keys); i++) {
+		if (!link->ap_early_keys[i]) {
+			link->ap_early_keys[i] = key;
+			return 0;
+		}
+	}
+
+	return -ENOSPC;
+}
+
+static int iwl_mld_send_ap_early_keys(struct iwl_mld *mld,
+				      struct ieee80211_vif *vif,
+				      struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	int ret = 0;
+
+	if (WARN_ON(!link))
+		return -EINVAL;
+
+	for (int i = 0; i < ARRAY_SIZE(mld_link->ap_early_keys); i++) {
+		struct ieee80211_key_conf *key = mld_link->ap_early_keys[i];
+
+		if (!key)
+			continue;
+
+		mld_link->ap_early_keys[i] = NULL;
+
+		ret = iwl_mld_add_key(mld, vif, NULL, key);
+		if (ret)
+			break;
+	}
+	return ret;
+}
+
+int iwl_mld_start_ap_ibss(struct ieee80211_hw *hw,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	if (vif->type == NL80211_IFTYPE_AP)
+		iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link);
+
+	ret = iwl_mld_update_beacon_template(mld, vif, link);
+	if (ret)
+		return ret;
+
+	/* the link should be already activated when assigning chan context,
+	 * and LINK_CONTEXT_MODIFY_EHT_PARAMS is deprecated
+	 */
+	ret = iwl_mld_change_link_in_fw(mld, link,
+					LINK_CONTEXT_MODIFY_ALL &
+					~(LINK_CONTEXT_MODIFY_ACTIVE |
+					  LINK_CONTEXT_MODIFY_EHT_PARAMS));
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_add_mcast_sta(mld, vif, link);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_add_bcast_sta(mld, vif, link);
+	if (ret)
+		goto rm_mcast;
+
+	/* Those keys were configured by the upper layers before starting the
+	 * AP. Now that it is started and the bcast and mcast sta were added to
+	 * the FW, we can add the keys too.
+	 */
+	ret = iwl_mld_send_ap_early_keys(mld, vif, link);
+	if (ret)
+		goto rm_bcast;
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_AP)
+		iwl_mld_vif_update_low_latency(mld, vif, true,
+					       LOW_LATENCY_VIF_TYPE);
+
+	mld_vif->ap_ibss_active = true;
+
+	if (vif->p2p && mld->p2p_device_vif)
+		return iwl_mld_mac_fw_action(mld, mld->p2p_device_vif,
+					     FW_CTXT_ACTION_MODIFY);
+
+	return 0;
+rm_bcast:
+	iwl_mld_remove_bcast_sta(mld, vif, link);
+rm_mcast:
+	iwl_mld_remove_mcast_sta(mld, vif, link);
+	return ret;
+}
+
+void iwl_mld_stop_ap_ibss(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	mld_vif->ap_ibss_active = false;
+
+	if (vif->p2p && mld->p2p_device_vif)
+		iwl_mld_mac_fw_action(mld, mld->p2p_device_vif,
+				      FW_CTXT_ACTION_MODIFY);
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_AP)
+		iwl_mld_vif_update_low_latency(mld, vif, false,
+					       LOW_LATENCY_VIF_TYPE);
+
+	iwl_mld_remove_bcast_sta(mld, vif, link);
+
+	iwl_mld_remove_mcast_sta(mld, vif, link);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ap.h b/drivers/net/wireless/intel/iwlwifi/mld/ap.h
new file mode 100644
index 0000000000000..4a6f52b9552d7
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ap.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_ap_h__
+#define __iwl_ap_h__
+
+#include "mld.h"
+#include "iface.h"
+
+#include "fw/api/tx.h"
+
+int iwl_mld_update_beacon_template(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_bss_conf *link_conf);
+
+int iwl_mld_start_ap_ibss(struct ieee80211_hw *hw,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link);
+
+void iwl_mld_stop_ap_ibss(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link);
+
+int iwl_mld_store_ap_early_key(struct iwl_mld *mld,
+			       struct ieee80211_key_conf *key,
+			       struct iwl_mld_vif *mld_vif);
+
+void iwl_mld_free_ap_early_key(struct iwl_mld *mld,
+			       struct ieee80211_key_conf *key,
+			       struct iwl_mld_vif *mld_vif);
+
+u8 iwl_mld_get_rate_flags(struct iwl_mld *mld,
+			  struct ieee80211_tx_info *info,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link,
+			  enum nl80211_band band);
+
+void iwl_mld_set_tim_idx(struct iwl_mld *mld, __le32 *tim_index,
+			 u8 *beacon, u32 frame_size);
+
+int iwl_mld_send_beacon_template_cmd(struct iwl_mld *mld,
+				     struct sk_buff *beacon,
+				     struct iwl_mac_beacon_cmd *cmd);
+
+#endif /* __iwl_ap_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/coex.c b/drivers/net/wireless/intel/iwlwifi/mld/coex.c
new file mode 100644
index 0000000000000..5f262bd43f21d
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/coex.c
@@ -0,0 +1,40 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "fw/api/coex.h"
+
+#include "coex.h"
+#include "mld.h"
+#include "hcmd.h"
+#include "mlo.h"
+
+int iwl_mld_send_bt_init_conf(struct iwl_mld *mld)
+{
+	struct iwl_bt_coex_cmd cmd = {
+		.mode = cpu_to_le32(BT_COEX_NW),
+		.enabled_modules = cpu_to_le32(BT_COEX_MPLUT_ENABLED |
+					       BT_COEX_HIGH_BAND_RET),
+	};
+
+	return iwl_mld_send_cmd_pdu(mld, BT_CONFIG, &cmd);
+}
+
+void iwl_mld_handle_bt_coex_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt)
+{
+	const struct iwl_bt_coex_profile_notif *notif = (void *)pkt->data;
+	const struct iwl_bt_coex_profile_notif zero_notif = {};
+	/* zeroed structure means that BT is OFF */
+	bool bt_is_active = memcmp(notif, &zero_notif, sizeof(*notif));
+
+	if (bt_is_active == mld->bt_is_active)
+		return;
+
+	IWL_DEBUG_INFO(mld, "BT was turned %s\n", bt_is_active ? "ON" : "OFF");
+
+	mld->bt_is_active = bt_is_active;
+
+	iwl_mld_emlsr_check_bt(mld);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/coex.h b/drivers/net/wireless/intel/iwlwifi/mld/coex.h
new file mode 100644
index 0000000000000..a77c5dc9613c0
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/coex.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_coex_h__
+#define __iwl_mld_coex_h__
+
+#include "mld.h"
+
+int iwl_mld_send_bt_init_conf(struct iwl_mld *mld);
+
+void iwl_mld_handle_bt_coex_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt);
+
+#endif /* __iwl_mld_coex_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/constants.h b/drivers/net/wireless/intel/iwlwifi/mld/constants.h
new file mode 100644
index 0000000000000..9a24996014b8d
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/constants.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_constants_h__
+#define __iwl_mld_constants_h__
+
+#define IWL_MLD_MISSED_BEACONS_SINCE_RX_THOLD			4
+#define IWL_MLD_MISSED_BEACONS_THRESHOLD			8
+#define IWL_MLD_MISSED_BEACONS_THRESHOLD_LONG			19
+#define IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS		5
+#define IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH			15
+#define IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_BSS_PARAM_CHANGED	11
+#define IWL_MLD_LOW_RSSI_MLO_SCAN_THRESH			-72
+
+#define IWL_MLD_DEFAULT_PS_TX_DATA_TIMEOUT	(100 * USEC_PER_MSEC)
+#define IWL_MLD_DEFAULT_PS_RX_DATA_TIMEOUT	(100 * USEC_PER_MSEC)
+#define IWL_MLD_WOWLAN_PS_TX_DATA_TIMEOUT	(10 * USEC_PER_MSEC)
+#define IWL_MLD_WOWLAN_PS_RX_DATA_TIMEOUT	(10 * USEC_PER_MSEC)
+#define IWL_MLD_SHORT_PS_TX_DATA_TIMEOUT	(2 * 1024) /* defined in TU */
+#define IWL_MLD_SHORT_PS_RX_DATA_TIMEOUT	(40 * 1024) /* defined in TU */
+
+#define IWL_MLD_UAPSD_RX_DATA_TIMEOUT		(50 * USEC_PER_MSEC)
+#define IWL_MLD_UAPSD_TX_DATA_TIMEOUT		(50 * USEC_PER_MSEC)
+
+#define IWL_MLD_PS_SNOOZE_INTERVAL		25
+#define IWL_MLD_PS_SNOOZE_INTERVAL		25
+#define IWL_MLD_PS_SNOOZE_WINDOW		50
+
+#define IWL_MLD_PS_SNOOZE_HEAVY_TX_THLD_PACKETS	30
+#define IWL_MLD_PS_SNOOZE_HEAVY_RX_THLD_PACKETS	20
+
+#define IWL_MLD_PS_HEAVY_TX_THLD_PERCENT	50
+#define IWL_MLD_PS_HEAVY_RX_THLD_PERCENT	50
+#define IWL_MLD_PS_HEAVY_TX_THLD_PACKETS	20
+#define IWL_MLD_PS_HEAVY_RX_THLD_PACKETS	8
+
+#define IWL_MLD_TRIGGER_LINK_SEL_TIME_SEC	30
+#define IWL_MLD_SCAN_EXPIRE_TIME_SEC		20
+
+#define IWL_MLD_TPT_COUNT_WINDOW (5 * HZ)
+
+/* OMI reduced BW thresholds (channel load percentage) */
+#define IWL_MLD_OMI_ENTER_CHAN_LOAD		10
+#define IWL_MLD_OMI_EXIT_CHAN_LOAD_160		20
+#define IWL_MLD_OMI_EXIT_CHAN_LOAD_320		30
+/* time (in milliseconds) to let AP "settle" the OMI */
+#define IWL_MLD_OMI_AP_SETTLE_DELAY		27
+/* time (in milliseconds) to not enter OMI reduced BW after leaving */
+#define IWL_MLD_OMI_EXIT_PROTECTION		5000
+
+#define IWL_MLD_DIS_RANDOM_FW_ID                false
+#define IWL_MLD_D3_DEBUG                        false
+#define IWL_MLD_NON_TRANSMITTING_AP	        false
+#define IWL_MLD_6GHZ_PASSIVE_SCAN_TIMEOUT       3000 /* in seconds */
+#define IWL_MLD_6GHZ_PASSIVE_SCAN_ASSOC_TIMEOUT 60   /* in seconds */
+#define IWL_MLD_CONN_LISTEN_INTERVAL		10
+#define IWL_MLD_ADAPTIVE_DWELL_NUM_APS_OVERRIDE 0
+#define IWL_MLD_AUTO_EML_ENABLE			true
+
+#define IWL_MLD_HIGH_RSSI_THRESH_20MHZ		-67
+#define IWL_MLD_LOW_RSSI_THRESH_20MHZ		-72
+#define IWL_MLD_HIGH_RSSI_THRESH_40MHZ		-64
+#define IWL_MLD_LOW_RSSI_THRESH_40MHZ		-72
+#define IWL_MLD_HIGH_RSSI_THRESH_80MHZ		-61
+#define IWL_MLD_LOW_RSSI_THRESH_80MHZ		-72
+#define IWL_MLD_HIGH_RSSI_THRESH_160MHZ		-58
+#define IWL_MLD_LOW_RSSI_THRESH_160MHZ		-72
+
+#define IWL_MLD_ENTER_EMLSR_TPT_THRESH		400
+#define IWL_MLD_CHAN_LOAD_THRESH		2 /* in percentage */
+
+#define IWL_MLD_FTM_INITIATOR_ALGO		IWL_TOF_ALGO_TYPE_MAX_LIKE
+#define IWL_MLD_FTM_INITIATOR_DYNACK		true
+#define IWL_MLD_FTM_LMR_FEEDBACK_TERMINATE	false
+#define IWL_MLD_FTM_TEST_INCORRECT_SAC		false
+#define IWL_MLD_FTM_R2I_MAX_REP			7
+#define IWL_MLD_FTM_I2R_MAX_REP			7
+#define IWL_MLD_FTM_R2I_MAX_STS			1
+#define IWL_MLD_FTM_I2R_MAX_STS			1
+#define IWL_MLD_FTM_R2I_MAX_TOTAL_LTF		3
+#define IWL_MLD_FTM_I2R_MAX_TOTAL_LTF		3
+#define IWL_MLD_FTM_RESP_NDP_SUPPORT		true
+#define IWL_MLD_FTM_RESP_LMR_FEEDBACK_SUPPORT	true
+#define IWL_MLD_FTM_NON_TB_MIN_TIME_BETWEEN_MSR	7
+#define IWL_MLD_FTM_NON_TB_MAX_TIME_BETWEEN_MSR	1000
+
+#endif /* __iwl_mld_constants_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.c b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
new file mode 100644
index 0000000000000..5a7207accd867
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.c
@@ -0,0 +1,1998 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include "mld.h"
+
+#include "d3.h"
+#include "power.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "mcc.h"
+#include "sta.h"
+#include "mlo.h"
+
+#include "fw/api/d3.h"
+#include "fw/api/offload.h"
+#include "fw/api/sta.h"
+#include "fw/dbg.h"
+
+#include <net/ipv6.h>
+#include <net/addrconf.h>
+#include <linux/bitops.h>
+
+/**
+ * enum iwl_mld_d3_notif - d3 notifications
+ * @IWL_D3_NOTIF_WOWLAN_INFO: WOWLAN_INFO_NOTIF is expected/was received
+ * @IWL_D3_NOTIF_WOWLAN_WAKE_PKT: WOWLAN_WAKE_PKT_NOTIF is expected/was received
+ * @IWL_D3_NOTIF_PROT_OFFLOAD: PROT_OFFLOAD_NOTIF is expected/was received
+ * @IWL_D3_ND_MATCH_INFO: OFFLOAD_MATCH_INFO_NOTIF is expected/was received
+ * @IWL_D3_NOTIF_D3_END_NOTIF: D3_END_NOTIF is expected/was received
+ */
+enum iwl_mld_d3_notif {
+	IWL_D3_NOTIF_WOWLAN_INFO =	BIT(0),
+	IWL_D3_NOTIF_WOWLAN_WAKE_PKT =	BIT(1),
+	IWL_D3_NOTIF_PROT_OFFLOAD =	BIT(2),
+	IWL_D3_ND_MATCH_INFO      =     BIT(3),
+	IWL_D3_NOTIF_D3_END_NOTIF =	BIT(4)
+};
+
+struct iwl_mld_resume_key_iter_data {
+	struct iwl_mld *mld;
+	struct iwl_mld_wowlan_status *wowlan_status;
+	u32 num_keys, gtk_cipher, igtk_cipher, bigtk_cipher;
+	bool unhandled_cipher;
+};
+
+struct iwl_mld_suspend_key_iter_data {
+	struct iwl_wowlan_rsc_tsc_params_cmd *rsc;
+	bool have_rsc;
+	int gtks;
+	int found_gtk_idx[4];
+	__le32 gtk_cipher;
+	__le32 igtk_cipher;
+	__le32 bigtk_cipher;
+};
+
+struct iwl_mld_mcast_key_data {
+	u8 key[WOWLAN_KEY_MAX_SIZE];
+	u8 len;
+	u8 flags;
+	u8 id;
+	union {
+		struct {
+			struct ieee80211_key_seq aes_seq[IWL_MAX_TID_COUNT];
+			struct ieee80211_key_seq tkip_seq[IWL_MAX_TID_COUNT];
+		} gtk;
+		struct {
+			struct ieee80211_key_seq cmac_gmac_seq;
+		} igtk_bigtk;
+	};
+
+};
+
+/**
+ * struct iwl_mld_wowlan_status - contains wowlan status data from
+ * all wowlan notifications
+ * @wakeup_reasons: wakeup reasons, see &enum iwl_wowlan_wakeup_reason
+ * @replay_ctr: GTK rekey replay counter
+ * @pattern_number: number of the matched patterns on packets
+ * @last_qos_seq: QoS sequence counter of offloaded tid
+ * @num_of_gtk_rekeys: number of GTK rekeys during D3
+ * @tid_offloaded_tx: tid used by the firmware to transmit data packets
+ *	while in wowlan
+ * @wake_packet: wakeup packet received
+ * @wake_packet_length: wake packet length
+ * @wake_packet_bufsize: wake packet bufsize
+ * @gtk: data of the last two used gtk's by the FW upon resume
+ * @igtk: data of the last used igtk by the FW upon resume
+ * @bigtk: data of the last two used gtk's by the FW upon resume
+ * @ptk: last seq numbers per tid passed by the FW,
+ *	holds both in tkip and aes formats
+ */
+struct iwl_mld_wowlan_status {
+	u32 wakeup_reasons;
+	u64 replay_ctr;
+	u16 pattern_number;
+	u16 last_qos_seq;
+	u32 num_of_gtk_rekeys;
+	u8 tid_offloaded_tx;
+	u8 *wake_packet;
+	u32 wake_packet_length;
+	u32 wake_packet_bufsize;
+	struct iwl_mld_mcast_key_data gtk[WOWLAN_GTK_KEYS_NUM];
+	struct iwl_mld_mcast_key_data igtk;
+	struct iwl_mld_mcast_key_data bigtk[WOWLAN_BIGTK_KEYS_NUM];
+	struct {
+		struct ieee80211_key_seq aes_seq[IWL_MAX_TID_COUNT];
+		struct ieee80211_key_seq tkip_seq[IWL_MAX_TID_COUNT];
+
+	} ptk;
+};
+
+#define NETDETECT_QUERY_BUF_LEN \
+	(sizeof(struct iwl_scan_offload_profile_match) * \
+	 IWL_SCAN_MAX_PROFILES_V2)
+
+/**
+ * struct iwl_mld_netdetect_res - contains netdetect results from
+ * match_info_notif
+ * @matched_profiles: bitmap of matched profiles, referencing the
+ *	matches passed in the scan offload request
+ * @matches: array of match information, one for each match
+ */
+struct iwl_mld_netdetect_res {
+	u32 matched_profiles;
+	u8 matches[NETDETECT_QUERY_BUF_LEN];
+};
+
+/**
+ * struct iwl_mld_resume_data - d3 resume flow data
+ * @notifs_expected: bitmap of expected notifications from fw,
+ *	see &enum iwl_mld_d3_notif
+ * @notifs_received: bitmap of received notifications from fw,
+ *	see &enum iwl_mld_d3_notif
+ * @d3_end_flags: bitmap of flags from d3_end_notif
+ * @notif_handling_err: error handling one of the resume notifications
+ * @wowlan_status: wowlan status data from all wowlan notifications
+ * @netdetect_res: contains netdetect results from match_info_notif
+ */
+struct iwl_mld_resume_data {
+	u32 notifs_expected;
+	u32 notifs_received;
+	u32 d3_end_flags;
+	bool notif_handling_err;
+	struct iwl_mld_wowlan_status *wowlan_status;
+	struct iwl_mld_netdetect_res *netdetect_res;
+};
+
+#define IWL_WOWLAN_WAKEUP_REASON_HAS_WAKEUP_PKT \
+	(IWL_WOWLAN_WAKEUP_BY_MAGIC_PACKET | \
+	IWL_WOWLAN_WAKEUP_BY_PATTERN | \
+	IWL_WAKEUP_BY_PATTERN_IPV4_TCP_SYN |\
+	IWL_WAKEUP_BY_PATTERN_IPV4_TCP_SYN_WILDCARD |\
+	IWL_WAKEUP_BY_PATTERN_IPV6_TCP_SYN |\
+	IWL_WAKEUP_BY_PATTERN_IPV6_TCP_SYN_WILDCARD)
+
+#define IWL_WOWLAN_OFFLOAD_TID 0
+
+void iwl_mld_set_rekey_data(struct ieee80211_hw *hw,
+			    struct ieee80211_vif *vif,
+			    struct cfg80211_gtk_rekey_data *data)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_wowlan_data *wowlan_data = &mld_vif->wowlan_data;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	wowlan_data->rekey_data.kek_len = data->kek_len;
+	wowlan_data->rekey_data.kck_len = data->kck_len;
+	memcpy(wowlan_data->rekey_data.kek, data->kek, data->kek_len);
+	memcpy(wowlan_data->rekey_data.kck, data->kck, data->kck_len);
+	wowlan_data->rekey_data.akm = data->akm & 0xFF;
+	wowlan_data->rekey_data.replay_ctr =
+		cpu_to_le64(be64_to_cpup((const __be64 *)data->replay_ctr));
+	wowlan_data->rekey_data.valid = true;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+void iwl_mld_ipv6_addr_change(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct inet6_dev *idev)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_wowlan_data *wowlan_data = &mld_vif->wowlan_data;
+	struct inet6_ifaddr *ifa;
+	int idx = 0;
+
+	memset(wowlan_data->tentative_addrs, 0,
+	       sizeof(wowlan_data->tentative_addrs));
+
+	read_lock_bh(&idev->lock);
+	list_for_each_entry(ifa, &idev->addr_list, if_list) {
+		wowlan_data->target_ipv6_addrs[idx] = ifa->addr;
+		if (ifa->flags & IFA_F_TENTATIVE)
+			__set_bit(idx, wowlan_data->tentative_addrs);
+		idx++;
+		if (idx >= IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_MAX)
+			break;
+	}
+	read_unlock_bh(&idev->lock);
+
+	wowlan_data->num_target_ipv6_addrs = idx;
+}
+#endif
+
+enum rt_status {
+	FW_ALIVE,
+	FW_NEEDS_RESET,
+	FW_ERROR,
+};
+
+static enum rt_status iwl_mld_check_err_tables(struct iwl_mld *mld,
+					       struct ieee80211_vif *vif)
+{
+	u32 err_id;
+
+	/* check for lmac1 error */
+	if (iwl_fwrt_read_err_table(mld->trans,
+				    mld->trans->dbg.lmac_error_event_table[0],
+				    &err_id)) {
+		if (err_id == RF_KILL_INDICATOR_FOR_WOWLAN && vif) {
+			struct cfg80211_wowlan_wakeup wakeup = {
+				.rfkill_release = true,
+			};
+			ieee80211_report_wowlan_wakeup(vif, &wakeup,
+						       GFP_KERNEL);
+
+			return FW_NEEDS_RESET;
+		}
+		return FW_ERROR;
+	}
+
+	/* check if we have lmac2 set and check for error */
+	if (iwl_fwrt_read_err_table(mld->trans,
+				    mld->trans->dbg.lmac_error_event_table[1],
+				    NULL))
+		return FW_ERROR;
+
+	/* check for umac error */
+	if (iwl_fwrt_read_err_table(mld->trans,
+				    mld->trans->dbg.umac_error_event_table,
+				    NULL))
+		return FW_ERROR;
+
+	return FW_ALIVE;
+}
+
+static bool iwl_mld_fw_needs_restart(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif)
+{
+	enum rt_status rt_status = iwl_mld_check_err_tables(mld, vif);
+
+	if (rt_status == FW_ALIVE)
+		return false;
+
+	if (rt_status == FW_ERROR) {
+		IWL_ERR(mld, "FW Error occurred during suspend\n");
+		iwl_fwrt_dump_error_logs(&mld->fwrt);
+		iwl_dbg_tlv_time_point(&mld->fwrt,
+				       IWL_FW_INI_TIME_POINT_FW_ASSERT, NULL);
+	}
+
+	return true;
+}
+
+static int
+iwl_mld_netdetect_config(struct iwl_mld *mld,
+			 struct ieee80211_vif *vif,
+			 const struct cfg80211_wowlan *wowlan)
+{
+	int ret;
+	struct cfg80211_sched_scan_request *netdetect_cfg =
+		wowlan->nd_config;
+	struct ieee80211_scan_ies ies = {};
+
+	ret = iwl_mld_scan_stop(mld, IWL_MLD_SCAN_SCHED, true);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_sched_scan_start(mld, vif, netdetect_cfg, &ies,
+				       IWL_MLD_SCAN_NETDETECT);
+	return ret;
+}
+
+static void
+iwl_mld_le64_to_tkip_seq(__le64 le_pn, struct ieee80211_key_seq *seq)
+{
+	u64 pn = le64_to_cpu(le_pn);
+
+	seq->tkip.iv16 = (u16)pn;
+	seq->tkip.iv32 = (u32)(pn >> 16);
+}
+
+static void
+iwl_mld_le64_to_aes_seq(__le64 le_pn, struct ieee80211_key_seq *seq)
+{
+	u64 pn = le64_to_cpu(le_pn);
+
+	seq->ccmp.pn[0] = pn >> 40;
+	seq->ccmp.pn[1] = pn >> 32;
+	seq->ccmp.pn[2] = pn >> 24;
+	seq->ccmp.pn[3] = pn >> 16;
+	seq->ccmp.pn[4] = pn >> 8;
+	seq->ccmp.pn[5] = pn;
+}
+
+static void
+iwl_mld_convert_gtk_resume_seq(struct iwl_mld_mcast_key_data *gtk_data,
+			       const struct iwl_wowlan_all_rsc_tsc_v5 *sc,
+			       int rsc_idx)
+{
+	struct ieee80211_key_seq *aes_seq = gtk_data->gtk.aes_seq;
+	struct ieee80211_key_seq *tkip_seq = gtk_data->gtk.tkip_seq;
+
+	if (rsc_idx >= ARRAY_SIZE(sc->mcast_rsc))
+		return;
+
+	/* We store both the TKIP and AES representations coming from the
+	 * FW because we decode the data from there before we iterate
+	 * the keys and know which type is used.
+	 */
+	for (int tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
+		iwl_mld_le64_to_tkip_seq(sc->mcast_rsc[rsc_idx][tid],
+					 &tkip_seq[tid]);
+		iwl_mld_le64_to_aes_seq(sc->mcast_rsc[rsc_idx][tid],
+					&aes_seq[tid]);
+	}
+}
+
+static void
+iwl_mld_convert_gtk_resume_data(struct iwl_mld *mld,
+				struct iwl_mld_wowlan_status *wowlan_status,
+				const struct iwl_wowlan_gtk_status_v3 *gtk_data,
+				const struct iwl_wowlan_all_rsc_tsc_v5 *sc)
+{
+	int status_idx = 0;
+
+	BUILD_BUG_ON(sizeof(wowlan_status->gtk[0].key) <
+		     sizeof(gtk_data[0].key));
+	BUILD_BUG_ON(ARRAY_SIZE(wowlan_status->gtk) < WOWLAN_GTK_KEYS_NUM);
+
+	for (int notif_idx = 0; notif_idx < ARRAY_SIZE(wowlan_status->gtk);
+	     notif_idx++) {
+		int rsc_idx;
+
+		if (!(gtk_data[notif_idx].key_len))
+			continue;
+
+		wowlan_status->gtk[status_idx].len =
+			gtk_data[notif_idx].key_len;
+		wowlan_status->gtk[status_idx].flags =
+			gtk_data[notif_idx].key_flags;
+		wowlan_status->gtk[status_idx].id =
+			wowlan_status->gtk[status_idx].flags &
+			IWL_WOWLAN_GTK_IDX_MASK;
+		memcpy(wowlan_status->gtk[status_idx].key,
+		       gtk_data[notif_idx].key,
+		       sizeof(gtk_data[notif_idx].key));
+
+		/* The rsc for both gtk keys are stored in gtk[0]->sc->mcast_rsc
+		 * The gtk ids can be any two numbers between 0 and 3,
+		 * the id_map maps between the key id and the index in sc->mcast
+		 */
+		rsc_idx =
+			sc->mcast_key_id_map[wowlan_status->gtk[status_idx].id];
+		iwl_mld_convert_gtk_resume_seq(&wowlan_status->gtk[status_idx],
+					       sc, rsc_idx);
+
+		/* if it's as long as the TKIP encryption key, copy MIC key */
+		if (wowlan_status->gtk[status_idx].len ==
+		    NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY)
+			memcpy(wowlan_status->gtk[status_idx].key +
+			       NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY,
+			       gtk_data[notif_idx].tkip_mic_key,
+			       sizeof(gtk_data[notif_idx].tkip_mic_key));
+		status_idx++;
+	}
+}
+
+static void
+iwl_mld_convert_ptk_resume_seq(struct iwl_mld *mld,
+			       struct iwl_mld_wowlan_status *wowlan_status,
+			       const struct iwl_wowlan_all_rsc_tsc_v5 *sc)
+{
+	struct ieee80211_key_seq *aes_seq = wowlan_status->ptk.aes_seq;
+	struct ieee80211_key_seq *tkip_seq = wowlan_status->ptk.tkip_seq;
+
+	BUILD_BUG_ON(ARRAY_SIZE(sc->ucast_rsc) != IWL_MAX_TID_COUNT);
+
+	for (int tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
+		iwl_mld_le64_to_aes_seq(sc->ucast_rsc[tid], &aes_seq[tid]);
+		iwl_mld_le64_to_tkip_seq(sc->ucast_rsc[tid], &tkip_seq[tid]);
+	}
+}
+
+static void
+iwl_mld_convert_mcast_ipn(struct iwl_mld_mcast_key_data *key_status,
+			  const struct iwl_wowlan_igtk_status *key)
+{
+	struct ieee80211_key_seq *seq =
+		&key_status->igtk_bigtk.cmac_gmac_seq;
+	u8 ipn_len = ARRAY_SIZE(key->ipn);
+
+	BUILD_BUG_ON(ipn_len != ARRAY_SIZE(seq->aes_gmac.pn));
+	BUILD_BUG_ON(ipn_len != ARRAY_SIZE(seq->aes_cmac.pn));
+	BUILD_BUG_ON(offsetof(struct ieee80211_key_seq, aes_gmac) !=
+		     offsetof(struct ieee80211_key_seq, aes_cmac));
+
+	/* mac80211 expects big endian for memcmp() to work, convert.
+	 * We don't have the key cipher yet so copy to both to cmac and gmac
+	 */
+	for (int i = 0; i < ipn_len; i++) {
+		seq->aes_gmac.pn[i] = key->ipn[ipn_len - i - 1];
+		seq->aes_cmac.pn[i] = key->ipn[ipn_len - i - 1];
+	}
+}
+
+static void
+iwl_mld_convert_igtk_resume_data(struct iwl_mld_wowlan_status *wowlan_status,
+				 const struct iwl_wowlan_igtk_status *igtk)
+{
+	BUILD_BUG_ON(sizeof(wowlan_status->igtk.key) < sizeof(igtk->key));
+
+	if (!igtk->key_len)
+		return;
+
+	wowlan_status->igtk.len = igtk->key_len;
+	wowlan_status->igtk.flags = igtk->key_flags;
+	wowlan_status->igtk.id =
+		u32_get_bits(igtk->key_flags,
+			     IWL_WOWLAN_IGTK_BIGTK_IDX_MASK) +
+		WOWLAN_IGTK_MIN_INDEX;
+
+	memcpy(wowlan_status->igtk.key, igtk->key, sizeof(igtk->key));
+	iwl_mld_convert_mcast_ipn(&wowlan_status->igtk, igtk);
+}
+
+static void
+iwl_mld_convert_bigtk_resume_data(struct iwl_mld_wowlan_status *wowlan_status,
+				  const struct iwl_wowlan_igtk_status *bigtk)
+{
+	int status_idx = 0;
+
+	BUILD_BUG_ON(ARRAY_SIZE(wowlan_status->bigtk) < WOWLAN_BIGTK_KEYS_NUM);
+
+	for (int notif_idx = 0; notif_idx < WOWLAN_BIGTK_KEYS_NUM;
+	     notif_idx++) {
+		if (!bigtk[notif_idx].key_len)
+			continue;
+
+		wowlan_status->bigtk[status_idx].len = bigtk[notif_idx].key_len;
+		wowlan_status->bigtk[status_idx].flags =
+			bigtk[notif_idx].key_flags;
+		wowlan_status->bigtk[status_idx].id =
+			u32_get_bits(bigtk[notif_idx].key_flags,
+				     IWL_WOWLAN_IGTK_BIGTK_IDX_MASK)
+			+ WOWLAN_BIGTK_MIN_INDEX;
+
+		BUILD_BUG_ON(sizeof(wowlan_status->bigtk[status_idx].key) <
+			     sizeof(bigtk[notif_idx].key));
+		memcpy(wowlan_status->bigtk[status_idx].key,
+		       bigtk[notif_idx].key, sizeof(bigtk[notif_idx].key));
+		iwl_mld_convert_mcast_ipn(&wowlan_status->bigtk[status_idx],
+					  &bigtk[notif_idx]);
+		status_idx++;
+	}
+}
+
+static bool
+iwl_mld_handle_wowlan_info_notif(struct iwl_mld *mld,
+				 struct iwl_mld_wowlan_status *wowlan_status,
+				 struct iwl_rx_packet *pkt)
+{
+	const struct iwl_wowlan_info_notif *notif = (void *)pkt->data;
+	u32 expected_len, len = iwl_rx_packet_payload_len(pkt);
+
+	expected_len = sizeof(*notif);
+
+	if (IWL_FW_CHECK(mld, len < expected_len,
+			 "Invalid wowlan_info_notif (expected=%ud got=%ud)\n",
+			 expected_len, len))
+		return true;
+
+	if (IWL_FW_CHECK(mld, notif->tid_offloaded_tx != IWL_WOWLAN_OFFLOAD_TID,
+			 "Invalid tid_offloaded_tx %d\n",
+			 wowlan_status->tid_offloaded_tx))
+		return true;
+
+	iwl_mld_convert_gtk_resume_data(mld, wowlan_status, notif->gtk,
+					&notif->gtk[0].sc);
+	iwl_mld_convert_ptk_resume_seq(mld, wowlan_status, &notif->gtk[0].sc);
+	/* only one igtk is passed by FW */
+	iwl_mld_convert_igtk_resume_data(wowlan_status, &notif->igtk[0]);
+	iwl_mld_convert_bigtk_resume_data(wowlan_status, notif->bigtk);
+
+	wowlan_status->replay_ctr = le64_to_cpu(notif->replay_ctr);
+	wowlan_status->pattern_number = le16_to_cpu(notif->pattern_number);
+
+	wowlan_status->tid_offloaded_tx = notif->tid_offloaded_tx;
+	wowlan_status->last_qos_seq = le16_to_cpu(notif->qos_seq_ctr);
+	wowlan_status->num_of_gtk_rekeys =
+		le32_to_cpu(notif->num_of_gtk_rekeys);
+	wowlan_status->wakeup_reasons = le32_to_cpu(notif->wakeup_reasons);
+	return false;
+	/* TODO: mlo_links (task=MLO)*/
+}
+
+static bool
+iwl_mld_handle_wake_pkt_notif(struct iwl_mld *mld,
+			      struct iwl_mld_wowlan_status *wowlan_status,
+			      struct iwl_rx_packet *pkt)
+{
+	const struct iwl_wowlan_wake_pkt_notif *notif = (void *)pkt->data;
+	u32 actual_size, len = iwl_rx_packet_payload_len(pkt);
+	u32 expected_size = le32_to_cpu(notif->wake_packet_length);
+
+	if (IWL_FW_CHECK(mld, len < sizeof(*notif),
+			 "Invalid WoWLAN wake packet notification (expected size=%zu got=%u)\n",
+			 sizeof(*notif), len))
+		return true;
+
+	if (IWL_FW_CHECK(mld, !(wowlan_status->wakeup_reasons &
+				IWL_WOWLAN_WAKEUP_REASON_HAS_WAKEUP_PKT),
+			 "Got wake packet but wakeup reason is %x\n",
+			 wowlan_status->wakeup_reasons))
+		return true;
+
+	actual_size = len - offsetof(struct iwl_wowlan_wake_pkt_notif,
+				     wake_packet);
+
+	/* actual_size got the padding from the notification, remove it. */
+	if (expected_size < actual_size)
+		actual_size = expected_size;
+	wowlan_status->wake_packet = kmemdup(notif->wake_packet, actual_size,
+					     GFP_ATOMIC);
+	if (!wowlan_status->wake_packet)
+		return true;
+
+	wowlan_status->wake_packet_length = expected_size;
+	wowlan_status->wake_packet_bufsize = actual_size;
+
+	return false;
+}
+
+static void
+iwl_mld_set_wake_packet(struct iwl_mld *mld,
+			struct ieee80211_vif *vif,
+			const struct iwl_mld_wowlan_status *wowlan_status,
+			struct cfg80211_wowlan_wakeup *wakeup,
+			struct sk_buff **_pkt)
+{
+	int pkt_bufsize = wowlan_status->wake_packet_bufsize;
+	int expected_pktlen = wowlan_status->wake_packet_length;
+	const u8 *pktdata = wowlan_status->wake_packet;
+	const struct ieee80211_hdr *hdr = (const void *)pktdata;
+	int truncated = expected_pktlen - pkt_bufsize;
+
+	if (ieee80211_is_data(hdr->frame_control)) {
+		int hdrlen = ieee80211_hdrlen(hdr->frame_control);
+		int ivlen = 0, icvlen = 4; /* also FCS */
+
+		struct sk_buff *pkt = alloc_skb(pkt_bufsize, GFP_KERNEL);
+		*_pkt = pkt;
+		if (!pkt)
+			return;
+
+		skb_put_data(pkt, pktdata, hdrlen);
+		pktdata += hdrlen;
+		pkt_bufsize -= hdrlen;
+
+		/* if truncated, FCS/ICV is (partially) gone */
+		if (truncated >= icvlen) {
+			truncated -= icvlen;
+			icvlen = 0;
+		} else {
+			icvlen -= truncated;
+			truncated = 0;
+		}
+
+		pkt_bufsize -= ivlen + icvlen;
+		pktdata += ivlen;
+
+		skb_put_data(pkt, pktdata, pkt_bufsize);
+
+		if (ieee80211_data_to_8023(pkt, vif->addr, vif->type))
+			return;
+		wakeup->packet = pkt->data;
+		wakeup->packet_present_len = pkt->len;
+		wakeup->packet_len = pkt->len - truncated;
+		wakeup->packet_80211 = false;
+	} else {
+		int fcslen = 4;
+
+		if (truncated >= 4) {
+			truncated -= 4;
+			fcslen = 0;
+		} else {
+			fcslen -= truncated;
+			truncated = 0;
+		}
+		pkt_bufsize -= fcslen;
+		wakeup->packet = wowlan_status->wake_packet;
+		wakeup->packet_present_len = pkt_bufsize;
+		wakeup->packet_len = expected_pktlen - truncated;
+		wakeup->packet_80211 = true;
+	}
+}
+
+static void
+iwl_mld_report_wowlan_wakeup(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct iwl_mld_wowlan_status *wowlan_status)
+{
+	struct sk_buff *pkt = NULL;
+	struct cfg80211_wowlan_wakeup wakeup = {
+		.pattern_idx = -1,
+	};
+	u32 reasons = wowlan_status->wakeup_reasons;
+
+	if (reasons == IWL_WOWLAN_WAKEUP_BY_NON_WIRELESS) {
+		ieee80211_report_wowlan_wakeup(vif, NULL, GFP_KERNEL);
+		return;
+	}
+
+	pm_wakeup_event(mld->dev, 0);
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_MAGIC_PACKET)
+		wakeup.magic_pkt = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_PATTERN)
+		wakeup.pattern_idx =
+			wowlan_status->pattern_number;
+
+	if (reasons & (IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_MISSED_BEACON |
+		       IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_DEAUTH |
+		       IWL_WOWLAN_WAKEUP_BY_GTK_REKEY_FAILURE))
+		wakeup.disconnect = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_GTK_REKEY_FAILURE)
+		wakeup.gtk_rekey_failure = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_RFKILL_DEASSERTED)
+		wakeup.rfkill_release = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_EAPOL_REQUEST)
+		wakeup.eap_identity_req = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_FOUR_WAY_HANDSHAKE)
+		wakeup.four_way_handshake = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_REM_WAKE_LINK_LOSS)
+		wakeup.tcp_connlost = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_REM_WAKE_SIGNATURE_TABLE)
+		wakeup.tcp_nomoretokens = true;
+
+	if (reasons & IWL_WOWLAN_WAKEUP_BY_REM_WAKE_WAKEUP_PACKET)
+		wakeup.tcp_match = true;
+
+	if (reasons & IWL_WAKEUP_BY_11W_UNPROTECTED_DEAUTH_OR_DISASSOC)
+		wakeup.unprot_deauth_disassoc = true;
+
+	if (wowlan_status->wake_packet)
+		iwl_mld_set_wake_packet(mld, vif, wowlan_status, &wakeup, &pkt);
+
+	ieee80211_report_wowlan_wakeup(vif, &wakeup, GFP_KERNEL);
+	kfree_skb(pkt);
+}
+
+static void
+iwl_mld_set_key_rx_seq_tids(struct ieee80211_key_conf *key,
+			    struct ieee80211_key_seq *seq)
+{
+	int tid;
+
+	for (tid = 0; tid < IWL_MAX_TID_COUNT; tid++)
+		ieee80211_set_key_rx_seq(key, tid, &seq[tid]);
+}
+
+static void
+iwl_mld_set_key_rx_seq(struct ieee80211_key_conf *key,
+		       struct iwl_mld_mcast_key_data *key_data)
+{
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		iwl_mld_set_key_rx_seq_tids(key,
+					    key_data->gtk.aes_seq);
+		break;
+	case WLAN_CIPHER_SUITE_TKIP:
+		iwl_mld_set_key_rx_seq_tids(key,
+					    key_data->gtk.tkip_seq);
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		/* igtk/bigtk ciphers*/
+		ieee80211_set_key_rx_seq(key, 0,
+					 &key_data->igtk_bigtk.cmac_gmac_seq);
+		break;
+	default:
+		WARN_ON(1);
+	}
+}
+
+static void
+iwl_mld_d3_update_mcast_key(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct iwl_mld_wowlan_status *wowlan_status,
+			    struct ieee80211_key_conf *key,
+			    struct iwl_mld_mcast_key_data *key_data)
+{
+	if (key->keyidx != key_data->id &&
+	    (key->keyidx < 4 || key->keyidx > 5)) {
+		IWL_ERR(mld,
+			"Unexpected keyId mismatch. Old keyId:%d, New keyId:%d\n",
+			key->keyidx, key_data->id);
+		return;
+	}
+
+	/* All installed keys are sent by the FW, even weren't
+	 * rekeyed during D3.
+	 * We remove an existing key if it has the same index as
+	 * a new key and a rekey has occurred during d3
+	 */
+	if (wowlan_status->num_of_gtk_rekeys && key_data->len) {
+		if (key->keyidx == 4 || key->keyidx == 5) {
+			struct iwl_mld_vif *mld_vif =
+				iwl_mld_vif_from_mac80211(vif);
+			struct iwl_mld_link *mld_link;
+			int link_id = vif->active_links ?
+				__ffs(vif->active_links) : 0;
+
+			mld_link = iwl_mld_link_dereference_check(mld_vif,
+								  link_id);
+			if (WARN_ON(!mld_link))
+				return;
+
+			if (mld_link->igtk == key)
+				mld_link->igtk = NULL;
+			mld->num_igtks--;
+		}
+
+		ieee80211_remove_key(key);
+		return;
+	}
+
+	iwl_mld_set_key_rx_seq(key, key_data);
+}
+
+static void
+iwl_mld_update_ptk_rx_seq(struct iwl_mld *mld,
+			  struct iwl_mld_wowlan_status *wowlan_status,
+			  struct ieee80211_sta *sta,
+			  struct ieee80211_key_conf *key,
+			  bool is_tkip)
+{
+	struct iwl_mld_sta *mld_sta =
+		iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_ptk_pn *mld_ptk_pn =
+		wiphy_dereference(mld->wiphy,
+				  mld_sta->ptk_pn[key->keyidx]);
+
+	iwl_mld_set_key_rx_seq_tids(key, is_tkip ?
+				    wowlan_status->ptk.tkip_seq :
+				    wowlan_status->ptk.aes_seq);
+	if (is_tkip)
+		return;
+
+	if (WARN_ON(!mld_ptk_pn))
+		return;
+
+	for (int tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
+		for (int i = 1; i < mld->trans->num_rx_queues; i++)
+			memcpy(mld_ptk_pn->q[i].pn[tid],
+			       wowlan_status->ptk.aes_seq[tid].ccmp.pn,
+			       IEEE80211_CCMP_PN_LEN);
+	}
+}
+
+static void
+iwl_mld_resume_keys_iter(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta,
+			 struct ieee80211_key_conf *key,
+			 void *_data)
+{
+	struct iwl_mld_resume_key_iter_data *data = _data;
+	struct iwl_mld_wowlan_status *wowlan_status = data->wowlan_status;
+	u8 status_idx;
+
+	/* TODO: check key link id (task=MLO) */
+	if (data->unhandled_cipher)
+		return;
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+		/* ignore WEP completely, nothing to do */
+		return;
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+	case WLAN_CIPHER_SUITE_TKIP:
+		if (sta) {
+			iwl_mld_update_ptk_rx_seq(data->mld, wowlan_status,
+						  sta, key,
+						  key->cipher ==
+						  WLAN_CIPHER_SUITE_TKIP);
+			return;
+		}
+
+		if (WARN_ON(data->gtk_cipher &&
+			    data->gtk_cipher != key->cipher))
+			return;
+
+		data->gtk_cipher = key->cipher;
+		status_idx = key->keyidx == wowlan_status->gtk[1].id;
+		iwl_mld_d3_update_mcast_key(data->mld, vif, wowlan_status, key,
+					    &wowlan_status->gtk[status_idx]);
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		if (key->keyidx == 4 || key->keyidx == 5) {
+			if (WARN_ON(data->igtk_cipher &&
+				    data->igtk_cipher != key->cipher))
+				return;
+
+			data->igtk_cipher = key->cipher;
+			iwl_mld_d3_update_mcast_key(data->mld, vif,
+						    wowlan_status,
+						    key, &wowlan_status->igtk);
+		}
+		if (key->keyidx == 6 || key->keyidx == 7) {
+			if (WARN_ON(data->bigtk_cipher &&
+				    data->bigtk_cipher != key->cipher))
+				return;
+
+			data->bigtk_cipher = key->cipher;
+			status_idx = key->keyidx == wowlan_status->bigtk[1].id;
+			iwl_mld_d3_update_mcast_key(data->mld, vif,
+						    wowlan_status, key,
+						    &wowlan_status->bigtk[status_idx]);
+		}
+		break;
+	default:
+		data->unhandled_cipher = true;
+		return;
+	}
+	data->num_keys++;
+}
+
+static bool
+iwl_mld_add_mcast_rekey(struct ieee80211_vif *vif,
+			struct iwl_mld *mld,
+			struct iwl_mld_mcast_key_data *key_data,
+			struct ieee80211_bss_conf *link_conf,
+			u32 cipher)
+{
+	struct ieee80211_key_conf *key_config;
+	struct {
+		struct ieee80211_key_conf conf;
+		u8 key[WOWLAN_KEY_MAX_SIZE];
+	} conf = {
+		.conf.cipher = cipher,
+		.conf.keyidx = key_data->id,
+	};
+	int link_id = vif->active_links ? __ffs(vif->active_links) : -1;
+
+	BUILD_BUG_ON(WLAN_KEY_LEN_CCMP != WLAN_KEY_LEN_GCMP);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_CCMP);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_GCMP_256);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_TKIP);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_BIP_GMAC_128);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_BIP_GMAC_256);
+	BUILD_BUG_ON(sizeof(conf.key) < WLAN_KEY_LEN_AES_CMAC);
+	BUILD_BUG_ON(sizeof(conf.key) < sizeof(key_data->key));
+
+	if (!key_data->len)
+		return true;
+
+	switch (cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+		conf.conf.keylen = WLAN_KEY_LEN_CCMP;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		conf.conf.keylen = WLAN_KEY_LEN_GCMP_256;
+		break;
+	case WLAN_CIPHER_SUITE_TKIP:
+		conf.conf.keylen = WLAN_KEY_LEN_TKIP;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		conf.conf.keylen = WLAN_KEY_LEN_BIP_GMAC_128;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		conf.conf.keylen = WLAN_KEY_LEN_BIP_GMAC_256;
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		conf.conf.keylen = WLAN_KEY_LEN_AES_CMAC;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		conf.conf.keylen = WLAN_KEY_LEN_BIP_CMAC_256;
+		break;
+	default:
+		WARN_ON(1);
+	}
+
+	memcpy(conf.conf.key, key_data->key, conf.conf.keylen);
+	key_config = ieee80211_gtk_rekey_add(vif, &conf.conf, link_id);
+	if (IS_ERR(key_config))
+		return false;
+
+	iwl_mld_set_key_rx_seq(key_config, key_data);
+
+	/* The FW holds only one igtk so we keep track of the valid one */
+	if (key_config->keyidx == 4 || key_config->keyidx == 5) {
+		struct iwl_mld_link *mld_link =
+			iwl_mld_link_from_mac80211(link_conf);
+		mld_link->igtk = key_config;
+		mld->num_igtks++;
+	}
+	return true;
+}
+
+static bool
+iwl_mld_add_all_rekeys(struct ieee80211_vif *vif,
+		       struct iwl_mld_wowlan_status *wowlan_status,
+		       struct iwl_mld_resume_key_iter_data *key_iter_data,
+		       struct ieee80211_bss_conf *link_conf)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(wowlan_status->gtk); i++)
+		if (!iwl_mld_add_mcast_rekey(vif, key_iter_data->mld,
+					     &wowlan_status->gtk[i],
+					     link_conf,
+					     key_iter_data->gtk_cipher))
+			return false;
+
+	if (!iwl_mld_add_mcast_rekey(vif, key_iter_data->mld,
+				     &wowlan_status->igtk,
+				     link_conf, key_iter_data->igtk_cipher))
+		return false;
+
+	for (i = 0; i < ARRAY_SIZE(wowlan_status->bigtk); i++)
+		if (!iwl_mld_add_mcast_rekey(vif, key_iter_data->mld,
+					     &wowlan_status->bigtk[i],
+					     link_conf,
+					     key_iter_data->bigtk_cipher))
+			return false;
+
+	return true;
+}
+
+static bool
+iwl_mld_update_sec_keys(struct iwl_mld *mld,
+			struct ieee80211_vif *vif,
+			struct iwl_mld_wowlan_status *wowlan_status)
+{
+	int link_id = vif->active_links ? __ffs(vif->active_links) : 0;
+	struct ieee80211_bss_conf *link_conf =
+		link_conf_dereference_protected(vif, link_id);
+	__be64 replay_ctr = cpu_to_be64(wowlan_status->replay_ctr);
+	struct iwl_mld_resume_key_iter_data key_iter_data = {
+		.mld = mld,
+		.wowlan_status = wowlan_status,
+	};
+
+	if (WARN_ON(!link_conf))
+		return false;
+
+	ieee80211_iter_keys(mld->hw, vif, iwl_mld_resume_keys_iter,
+			    &key_iter_data);
+
+	if (key_iter_data.unhandled_cipher)
+		return false;
+
+	IWL_DEBUG_WOWLAN(mld,
+			 "Number of installed keys: %d, Number of rekeys: %d\n",
+			 key_iter_data.num_keys,
+			 wowlan_status->num_of_gtk_rekeys);
+
+	if (!key_iter_data.num_keys || !wowlan_status->num_of_gtk_rekeys)
+		return true;
+
+	iwl_mld_add_all_rekeys(vif, wowlan_status, &key_iter_data,
+			       link_conf);
+
+	ieee80211_gtk_rekey_notify(vif, link_conf->bssid,
+				   (void *)&replay_ctr, GFP_KERNEL);
+	/* TODO: MLO rekey (task=MLO) */
+	return true;
+}
+
+static bool
+iwl_mld_process_wowlan_status(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct iwl_mld_wowlan_status *wowlan_status)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_sta *ap_sta = mld_vif->ap_sta;
+	struct iwl_mld_txq *mld_txq;
+
+	iwl_mld_report_wowlan_wakeup(mld, vif, wowlan_status);
+
+	if (WARN_ON(!ap_sta))
+		return false;
+
+	mld_txq =
+		iwl_mld_txq_from_mac80211(ap_sta->txq[wowlan_status->tid_offloaded_tx]);
+
+	/* Update the pointers of the Tx queue that may have moved during
+	 * suspend if the firmware sent frames.
+	 * The firmware stores last-used value, we store next value.
+	 */
+	WARN_ON(!mld_txq->status.allocated);
+	iwl_trans_set_q_ptrs(mld->trans, mld_txq->fw_id,
+			     (wowlan_status->last_qos_seq +
+			     0x10) >> 4);
+
+	if (!iwl_mld_update_sec_keys(mld, vif, wowlan_status))
+		return false;
+
+	if (wowlan_status->wakeup_reasons &
+	    (IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_MISSED_BEACON |
+	     IWL_WOWLAN_WAKEUP_BY_DISCONNECTION_ON_DEAUTH |
+	     IWL_WOWLAN_WAKEUP_BY_GTK_REKEY_FAILURE))
+		return false;
+
+	return true;
+}
+
+static bool
+iwl_mld_netdetect_match_info_handler(struct iwl_mld *mld,
+				     struct iwl_mld_resume_data *resume_data,
+				     struct iwl_rx_packet *pkt)
+{
+	struct iwl_mld_netdetect_res *results = resume_data->netdetect_res;
+	const struct iwl_scan_offload_match_info *notif = (void *)pkt->data;
+	u32 len = iwl_rx_packet_payload_len(pkt);
+
+	if (IWL_FW_CHECK(mld, !mld->netdetect,
+			 "Got scan match info notif when mld->netdetect==%d\n",
+			 mld->netdetect))
+		return true;
+
+	if (IWL_FW_CHECK(mld, len < sizeof(*notif),
+			 "Invalid scan offload match notif of length: %d\n",
+			 len))
+		return true;
+
+	if (IWL_FW_CHECK(mld, resume_data->wowlan_status->wakeup_reasons !=
+			 IWL_WOWLAN_WAKEUP_BY_NON_WIRELESS,
+			 "Ignore scan match info: unexpected wakeup reason (expected=0x%x got=0x%x)\n",
+			 IWL_WOWLAN_WAKEUP_BY_NON_WIRELESS,
+			 resume_data->wowlan_status->wakeup_reasons))
+		return true;
+
+	results->matched_profiles = le32_to_cpu(notif->matched_profiles);
+	IWL_DEBUG_WOWLAN(mld, "number of matched profiles=%u\n",
+			 results->matched_profiles);
+
+	if (results->matched_profiles)
+		memcpy(results->matches, notif->matches,
+		       NETDETECT_QUERY_BUF_LEN);
+
+	/* No scan should be active at this point */
+	mld->scan.status = 0;
+	memset(mld->scan.uid_status, 0, sizeof(mld->scan.uid_status));
+	return false;
+}
+
+static void
+iwl_mld_set_netdetect_info(struct iwl_mld *mld,
+			   const struct cfg80211_sched_scan_request *netdetect_cfg,
+			   struct cfg80211_wowlan_nd_info *netdetect_info,
+			   struct iwl_mld_netdetect_res *netdetect_res,
+			   unsigned long matched_profiles)
+{
+	int i;
+
+	for_each_set_bit(i, &matched_profiles, netdetect_cfg->n_match_sets) {
+		struct cfg80211_wowlan_nd_match *match;
+		int idx, j, n_channels = 0;
+		struct iwl_scan_offload_profile_match *matches =
+			(void *)netdetect_res->matches;
+
+		for (int k = 0; k < SCAN_OFFLOAD_MATCHING_CHANNELS_LEN; k++)
+			n_channels +=
+				hweight8(matches[i].matching_channels[k]);
+		match = kzalloc(struct_size(match, channels, n_channels),
+				GFP_KERNEL);
+		if (!match)
+			return;
+
+		netdetect_info->matches[netdetect_info->n_matches++] = match;
+
+		/* We inverted the order of the SSIDs in the scan
+		 * request, so invert the index here.
+		 */
+		idx = netdetect_cfg->n_match_sets - i - 1;
+		match->ssid.ssid_len =
+			netdetect_cfg->match_sets[idx].ssid.ssid_len;
+		memcpy(match->ssid.ssid,
+		       netdetect_cfg->match_sets[idx].ssid.ssid,
+		       match->ssid.ssid_len);
+
+		if (netdetect_cfg->n_channels < n_channels)
+			continue;
+
+		for_each_set_bit(j,
+				 (unsigned long *)&matches[i].matching_channels[0],
+				 sizeof(matches[i].matching_channels))
+			match->channels[match->n_channels++] =
+				netdetect_cfg->channels[j]->center_freq;
+	}
+}
+
+static void
+iwl_mld_process_netdetect_res(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct iwl_mld_resume_data *resume_data)
+{
+	struct cfg80211_wowlan_nd_info *netdetect_info = NULL;
+	const struct cfg80211_sched_scan_request *netdetect_cfg;
+	struct cfg80211_wowlan_wakeup wakeup = {
+		.pattern_idx = -1,
+	};
+	struct cfg80211_wowlan_wakeup *wakeup_report = &wakeup;
+	unsigned long matched_profiles;
+	u32 wakeup_reasons;
+	int n_matches;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld->wiphy->wowlan_config ||
+		    !mld->wiphy->wowlan_config->nd_config)) {
+		IWL_DEBUG_WOWLAN(mld,
+				 "Netdetect isn't configured on resume flow\n");
+		goto out;
+	}
+
+	netdetect_cfg = mld->wiphy->wowlan_config->nd_config;
+	wakeup_reasons = resume_data->wowlan_status->wakeup_reasons;
+
+	if (wakeup_reasons & IWL_WOWLAN_WAKEUP_BY_RFKILL_DEASSERTED)
+		wakeup.rfkill_release = true;
+
+	if (wakeup_reasons != IWL_WOWLAN_WAKEUP_BY_NON_WIRELESS)
+		goto out;
+
+	if (!resume_data->netdetect_res->matched_profiles) {
+		IWL_DEBUG_WOWLAN(mld,
+				 "Netdetect results aren't valid\n");
+		wakeup_report = NULL;
+		goto out;
+	}
+
+	matched_profiles = resume_data->netdetect_res->matched_profiles;
+	if (!netdetect_cfg->n_match_sets) {
+		IWL_DEBUG_WOWLAN(mld,
+				 "No netdetect match sets are configured\n");
+		goto out;
+	}
+	n_matches = hweight_long(matched_profiles);
+	netdetect_info = kzalloc(struct_size(netdetect_info, matches,
+					     n_matches), GFP_KERNEL);
+	if (netdetect_info)
+		iwl_mld_set_netdetect_info(mld, netdetect_cfg, netdetect_info,
+					   resume_data->netdetect_res,
+					   matched_profiles);
+
+	wakeup.net_detect = netdetect_info;
+ out:
+	ieee80211_report_wowlan_wakeup(vif, wakeup_report, GFP_KERNEL);
+	if (netdetect_info) {
+		for (int i = 0; i < netdetect_info->n_matches; i++)
+			kfree(netdetect_info->matches[i]);
+		kfree(netdetect_info);
+	}
+}
+
+static bool iwl_mld_handle_d3_notif(struct iwl_notif_wait_data *notif_wait,
+				    struct iwl_rx_packet *pkt, void *data)
+{
+	struct iwl_mld_resume_data *resume_data = data;
+	struct iwl_mld *mld =
+		container_of(notif_wait, struct iwl_mld, notif_wait);
+
+	switch (WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd)) {
+	case WIDE_ID(PROT_OFFLOAD_GROUP, WOWLAN_INFO_NOTIFICATION): {
+		if (resume_data->notifs_received & IWL_D3_NOTIF_WOWLAN_INFO) {
+			IWL_DEBUG_WOWLAN(mld,
+					 "got additional wowlan_info notif\n");
+			break;
+		}
+		resume_data->notif_handling_err =
+			iwl_mld_handle_wowlan_info_notif(mld,
+							 resume_data->wowlan_status,
+							 pkt);
+		resume_data->notifs_received |= IWL_D3_NOTIF_WOWLAN_INFO;
+
+		if (resume_data->wowlan_status->wakeup_reasons &
+		    IWL_WOWLAN_WAKEUP_REASON_HAS_WAKEUP_PKT)
+			resume_data->notifs_expected |=
+				IWL_D3_NOTIF_WOWLAN_WAKE_PKT;
+		break;
+	}
+	case WIDE_ID(PROT_OFFLOAD_GROUP, WOWLAN_WAKE_PKT_NOTIFICATION): {
+		if (resume_data->notifs_received &
+		    IWL_D3_NOTIF_WOWLAN_WAKE_PKT) {
+			/* We shouldn't get two wake packet notifications */
+			IWL_DEBUG_WOWLAN(mld,
+					 "Got additional wowlan wake packet notification\n");
+			break;
+		}
+		resume_data->notif_handling_err =
+			iwl_mld_handle_wake_pkt_notif(mld,
+						      resume_data->wowlan_status,
+						      pkt);
+		resume_data->notifs_received |= IWL_D3_NOTIF_WOWLAN_WAKE_PKT;
+		break;
+	}
+	case WIDE_ID(SCAN_GROUP, OFFLOAD_MATCH_INFO_NOTIF): {
+		if (resume_data->notifs_received & IWL_D3_ND_MATCH_INFO) {
+			IWL_ERR(mld,
+				"Got additional netdetect match info\n");
+			break;
+		}
+
+		resume_data->notif_handling_err =
+			iwl_mld_netdetect_match_info_handler(mld, resume_data,
+							     pkt);
+		resume_data->notifs_received |= IWL_D3_ND_MATCH_INFO;
+		break;
+	}
+	case WIDE_ID(PROT_OFFLOAD_GROUP, D3_END_NOTIFICATION): {
+		struct iwl_d3_end_notif *notif = (void *)pkt->data;
+
+		resume_data->d3_end_flags = le32_to_cpu(notif->flags);
+		resume_data->notifs_received |= IWL_D3_NOTIF_D3_END_NOTIF;
+		break;
+	}
+	default:
+		WARN_ON(1);
+	}
+
+	return resume_data->notifs_received == resume_data->notifs_expected;
+}
+
+#define IWL_MLD_D3_NOTIF_TIMEOUT (HZ / 3)
+
+static int iwl_mld_wait_d3_notif(struct iwl_mld *mld,
+				 struct iwl_mld_resume_data *resume_data,
+				 bool with_wowlan)
+{
+	static const u16 wowlan_resume_notif[] = {
+		WIDE_ID(PROT_OFFLOAD_GROUP, WOWLAN_INFO_NOTIFICATION),
+		WIDE_ID(PROT_OFFLOAD_GROUP, WOWLAN_WAKE_PKT_NOTIFICATION),
+		WIDE_ID(SCAN_GROUP, OFFLOAD_MATCH_INFO_NOTIF),
+		WIDE_ID(PROT_OFFLOAD_GROUP, D3_END_NOTIFICATION)
+	};
+	static const u16 d3_resume_notif[] = {
+		WIDE_ID(PROT_OFFLOAD_GROUP, D3_END_NOTIFICATION)
+	};
+	struct iwl_notification_wait wait_d3_notif;
+	enum iwl_d3_status d3_status;
+	int ret;
+
+	if (with_wowlan)
+		iwl_init_notification_wait(&mld->notif_wait, &wait_d3_notif,
+					   wowlan_resume_notif,
+					   ARRAY_SIZE(wowlan_resume_notif),
+					   iwl_mld_handle_d3_notif,
+					   resume_data);
+	else
+		iwl_init_notification_wait(&mld->notif_wait, &wait_d3_notif,
+					   d3_resume_notif,
+					   ARRAY_SIZE(d3_resume_notif),
+					   iwl_mld_handle_d3_notif,
+					   resume_data);
+
+	ret = iwl_trans_d3_resume(mld->trans, &d3_status, false, false);
+	if (ret || d3_status != IWL_D3_STATUS_ALIVE) {
+		if (d3_status != IWL_D3_STATUS_ALIVE) {
+			IWL_INFO(mld, "Device was reset during suspend\n");
+			ret = -ENOENT;
+		} else {
+			IWL_ERR(mld, "Transport resume failed\n");
+		}
+		iwl_remove_notification(&mld->notif_wait, &wait_d3_notif);
+		return ret;
+	}
+
+	ret = iwl_wait_notification(&mld->notif_wait, &wait_d3_notif,
+				    IWL_MLD_D3_NOTIF_TIMEOUT);
+	if (ret)
+		IWL_ERR(mld, "Couldn't get the d3 notif %d\n", ret);
+
+	if (resume_data->notif_handling_err)
+		ret = -EIO;
+
+	return ret;
+}
+
+int iwl_mld_no_wowlan_suspend(struct iwl_mld *mld)
+{
+	struct iwl_d3_manager_config d3_cfg_cmd_data = {};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	IWL_DEBUG_WOWLAN(mld, "Starting the no wowlan suspend flow\n");
+
+	iwl_mld_low_latency_stop(mld);
+
+	/* This will happen if iwl_mld_supsend failed with FW error */
+	if (mld->trans->state == IWL_TRANS_NO_FW &&
+	    test_bit(STATUS_FW_ERROR, &mld->trans->status))
+		return -ENODEV;
+
+	ret = iwl_mld_update_device_power(mld, true);
+	if (ret) {
+		IWL_ERR(mld,
+			"d3 suspend: couldn't send power_device %d\n", ret);
+		goto out;
+	}
+
+	ret = iwl_mld_send_cmd_pdu(mld, D3_CONFIG_CMD,
+				   &d3_cfg_cmd_data);
+	if (ret) {
+		IWL_ERR(mld,
+			"d3 suspend: couldn't send D3_CONFIG_CMD %d\n", ret);
+		goto out;
+	}
+
+	ret = iwl_trans_d3_suspend(mld->trans, false, false);
+	if (ret) {
+		IWL_ERR(mld, "d3 suspend: trans_d3_suspend failed %d\n", ret);
+	} else {
+		mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_D3;
+		mld->fw_status.in_d3 = true;
+	}
+
+ out:
+	if (ret) {
+		mld->trans->state = IWL_TRANS_NO_FW;
+		set_bit(STATUS_FW_ERROR, &mld->trans->status);
+	}
+
+	return ret;
+}
+
+int iwl_mld_no_wowlan_resume(struct iwl_mld *mld)
+{
+	struct iwl_mld_resume_data resume_data = {
+		.notifs_expected =
+			IWL_D3_NOTIF_D3_END_NOTIF,
+	};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	IWL_DEBUG_WOWLAN(mld, "Starting the no wowlan resume flow\n");
+
+	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
+	mld->fw_status.in_d3 = false;
+	iwl_fw_dbg_read_d3_debug_data(&mld->fwrt);
+
+	if (iwl_mld_fw_needs_restart(mld, NULL))
+		ret = -ENODEV;
+	else
+		ret = iwl_mld_wait_d3_notif(mld, &resume_data, false);
+
+	if (!ret && (resume_data.d3_end_flags & IWL_D0I3_RESET_REQUIRE))
+		return -ENODEV;
+
+	if (ret) {
+		mld->trans->state = IWL_TRANS_NO_FW;
+		set_bit(STATUS_FW_ERROR, &mld->trans->status);
+		return ret;
+	}
+	iwl_mld_low_latency_restart(mld);
+
+	return iwl_mld_update_device_power(mld, false);
+}
+
+static void
+iwl_mld_aes_seq_to_le64_pn(struct ieee80211_key_conf *key,
+			   __le64 *key_rsc)
+{
+	for (int i = 0; i < IWL_MAX_TID_COUNT; i++) {
+		struct ieee80211_key_seq seq;
+		u8 *pn = key->cipher == WLAN_CIPHER_SUITE_CCMP ? seq.ccmp.pn :
+			seq.gcmp.pn;
+
+		ieee80211_get_key_rx_seq(key, i, &seq);
+		key_rsc[i] = cpu_to_le64((u64)pn[5] |
+					 ((u64)pn[4] << 8) |
+					 ((u64)pn[3] << 16) |
+					 ((u64)pn[2] << 24) |
+					 ((u64)pn[1] << 32) |
+					 ((u64)pn[0] << 40));
+	}
+}
+
+static void
+iwl_mld_suspend_set_ucast_pn(struct iwl_mld *mld, struct ieee80211_sta *sta,
+			     struct ieee80211_key_conf *key, __le64 *key_rsc)
+{
+	struct iwl_mld_sta *mld_sta =
+		iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_ptk_pn *mld_ptk_pn;
+
+	if (WARN_ON(key->keyidx >= ARRAY_SIZE(mld_sta->ptk_pn)))
+		return;
+
+	mld_ptk_pn = wiphy_dereference(mld->wiphy,
+				       mld_sta->ptk_pn[key->keyidx]);
+	if (WARN_ON(!mld_ptk_pn))
+		return;
+
+	for (int tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
+		struct ieee80211_key_seq seq;
+		u8 *max_pn = seq.ccmp.pn;
+
+		/* get the PN from mac80211, used on the default queue */
+		ieee80211_get_key_rx_seq(key, tid, &seq);
+
+		/* and use the internal data for all queues */
+		for (int que = 1; que < mld->trans->num_rx_queues; que++) {
+			u8 *cur_pn = mld_ptk_pn->q[que].pn[tid];
+
+			if (memcmp(max_pn, cur_pn, IEEE80211_CCMP_PN_LEN) < 0)
+				max_pn = cur_pn;
+		}
+		key_rsc[tid] = cpu_to_le64((u64)max_pn[5] |
+					   ((u64)max_pn[4] << 8) |
+					   ((u64)max_pn[3] << 16) |
+					   ((u64)max_pn[2] << 24) |
+					   ((u64)max_pn[1] << 32) |
+					   ((u64)max_pn[0] << 40));
+	}
+}
+
+static void
+iwl_mld_suspend_convert_tkip_ipn(struct ieee80211_key_conf *key,
+				 __le64 *rsc)
+{
+	struct ieee80211_key_seq seq;
+
+	for (int i = 0; i < IWL_MAX_TID_COUNT; i++) {
+		ieee80211_get_key_rx_seq(key, i, &seq);
+		rsc[i] =
+			cpu_to_le64(((u64)seq.tkip.iv32 << 16) |
+				    seq.tkip.iv16);
+	}
+}
+
+static void
+iwl_mld_suspend_key_data_iter(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_sta *sta,
+			      struct ieee80211_key_conf *key,
+			      void *_data)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_suspend_key_iter_data *data = _data;
+	__le64 *key_rsc;
+	__le32 cipher = 0;
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_CCMP:
+		cipher = cpu_to_le32(STA_KEY_FLG_CCM);
+		fallthrough;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+		if (!cipher)
+			cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
+		fallthrough;
+	case WLAN_CIPHER_SUITE_TKIP:
+		if (!cipher)
+			cipher = cpu_to_le32(STA_KEY_FLG_TKIP);
+		if (sta) {
+			key_rsc = data->rsc->ucast_rsc;
+			if (key->cipher == WLAN_CIPHER_SUITE_TKIP)
+				iwl_mld_suspend_convert_tkip_ipn(key, key_rsc);
+			else
+				iwl_mld_suspend_set_ucast_pn(mld, sta, key,
+							     key_rsc);
+
+			data->have_rsc = true;
+			return;
+		}
+		/* We're iterating from old to new, there're 4 possible
+		 * gtk ids, and only the last two keys matter
+		 */
+		if (WARN_ON(data->gtks >=
+				ARRAY_SIZE(data->found_gtk_idx)))
+			return;
+
+		if (WARN_ON(key->keyidx >=
+				ARRAY_SIZE(data->rsc->mcast_key_id_map)))
+			return;
+		data->gtk_cipher = cipher;
+		data->found_gtk_idx[data->gtks] = key->keyidx;
+		key_rsc = data->rsc->mcast_rsc[data->gtks % 2];
+		data->rsc->mcast_key_id_map[key->keyidx] =
+			data->gtks % 2;
+
+		if (data->gtks >= 2) {
+			int prev = data->gtks % 2;
+			int prev_idx = data->found_gtk_idx[prev];
+
+			data->rsc->mcast_key_id_map[prev_idx] =
+				IWL_MCAST_KEY_MAP_INVALID;
+		}
+
+		if (key->cipher == WLAN_CIPHER_SUITE_TKIP)
+			iwl_mld_suspend_convert_tkip_ipn(key, key_rsc);
+		else
+			iwl_mld_aes_seq_to_le64_pn(key, key_rsc);
+
+		data->gtks++;
+		data->have_rsc = true;
+		break;
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		cipher = cpu_to_le32(STA_KEY_FLG_GCMP);
+		fallthrough;
+	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+		if (!cipher)
+			cipher = cpu_to_le32(STA_KEY_FLG_CCM);
+		if (key->keyidx == 4 || key->keyidx == 5)
+			data->igtk_cipher = cipher;
+
+		if (key->keyidx == 6 || key->keyidx == 7)
+			data->bigtk_cipher = cipher;
+
+		break;
+	}
+}
+
+static int
+iwl_mld_send_kek_kck_cmd(struct iwl_mld *mld,
+			 struct iwl_mld_vif *mld_vif,
+			 struct iwl_mld_suspend_key_iter_data data,
+			 int ap_sta_id)
+{
+	struct iwl_wowlan_kek_kck_material_cmd_v4 kek_kck_cmd = {};
+	struct iwl_mld_rekey_data *rekey_data =
+		&mld_vif->wowlan_data.rekey_data;
+
+	memcpy(kek_kck_cmd.kck, rekey_data->kck,
+	       rekey_data->kck_len);
+	kek_kck_cmd.kck_len = cpu_to_le16(rekey_data->kck_len);
+	memcpy(kek_kck_cmd.kek, rekey_data->kek,
+	       rekey_data->kek_len);
+	kek_kck_cmd.kek_len = cpu_to_le16(rekey_data->kek_len);
+	kek_kck_cmd.replay_ctr = rekey_data->replay_ctr;
+	kek_kck_cmd.akm = cpu_to_le32(rekey_data->akm);
+	kek_kck_cmd.sta_id = cpu_to_le32(ap_sta_id);
+	kek_kck_cmd.gtk_cipher = data.gtk_cipher;
+	kek_kck_cmd.igtk_cipher = data.igtk_cipher;
+	kek_kck_cmd.bigtk_cipher = data.bigtk_cipher;
+
+	IWL_DEBUG_WOWLAN(mld, "setting akm %d\n",
+			 rekey_data->akm);
+
+	return iwl_mld_send_cmd_pdu(mld, WOWLAN_KEK_KCK_MATERIAL,
+				    &kek_kck_cmd);
+}
+
+static int
+iwl_mld_suspend_send_security_cmds(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct iwl_mld_vif *mld_vif,
+				   int ap_sta_id)
+{
+	struct iwl_mld_suspend_key_iter_data data = {};
+	int ret;
+
+	data.rsc = kzalloc(sizeof(*data.rsc), GFP_KERNEL);
+	if (!data.rsc)
+		return -ENOMEM;
+
+	memset(data.rsc->mcast_key_id_map, IWL_MCAST_KEY_MAP_INVALID,
+	       ARRAY_SIZE(data.rsc->mcast_key_id_map));
+
+	data.rsc->sta_id = cpu_to_le32(ap_sta_id);
+	ieee80211_iter_keys(mld->hw, vif,
+			    iwl_mld_suspend_key_data_iter,
+			    &data);
+
+	if (data.have_rsc)
+		ret = iwl_mld_send_cmd_pdu(mld, WOWLAN_TSC_RSC_PARAM,
+					   data.rsc);
+	else
+		ret = 0;
+
+	if (!ret && mld_vif->wowlan_data.rekey_data.valid)
+		ret = iwl_mld_send_kek_kck_cmd(mld, mld_vif, data, ap_sta_id);
+
+	kfree(data.rsc);
+
+	return ret;
+}
+
+static void
+iwl_mld_set_wowlan_config_cmd(struct iwl_mld *mld,
+			      struct cfg80211_wowlan *wowlan,
+			      struct iwl_wowlan_config_cmd *wowlan_config_cmd,
+			      struct ieee80211_sta *ap_sta)
+{
+	wowlan_config_cmd->is_11n_connection =
+					ap_sta->deflink.ht_cap.ht_supported;
+	wowlan_config_cmd->flags = ENABLE_L3_FILTERING |
+		ENABLE_NBNS_FILTERING | ENABLE_DHCP_FILTERING;
+
+	if (ap_sta->mfp)
+		wowlan_config_cmd->flags |= IS_11W_ASSOC;
+
+	if (wowlan->disconnect)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_BEACON_MISS |
+				    IWL_WOWLAN_WAKEUP_LINK_CHANGE);
+	if (wowlan->magic_pkt)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_MAGIC_PACKET);
+	if (wowlan->gtk_rekey_failure)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_GTK_REKEY_FAIL);
+	if (wowlan->eap_identity_req)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_EAP_IDENT_REQ);
+	if (wowlan->four_way_handshake)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_4WAY_HANDSHAKE);
+	if (wowlan->n_patterns)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_PATTERN_MATCH);
+
+	if (wowlan->rfkill_release)
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_RF_KILL_DEASSERT);
+
+	if (wowlan->any) {
+		wowlan_config_cmd->wakeup_filter |=
+			cpu_to_le32(IWL_WOWLAN_WAKEUP_BEACON_MISS |
+				    IWL_WOWLAN_WAKEUP_LINK_CHANGE |
+				    IWL_WOWLAN_WAKEUP_RX_FRAME |
+				    IWL_WOWLAN_WAKEUP_BCN_FILTERING);
+	}
+}
+
+static int iwl_mld_send_patterns(struct iwl_mld *mld,
+				 struct cfg80211_wowlan *wowlan,
+				 int ap_sta_id)
+{
+	struct iwl_wowlan_patterns_cmd *pattern_cmd;
+	struct iwl_host_cmd cmd = {
+		.id = WOWLAN_PATTERNS,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+	int ret;
+
+	if (!wowlan->n_patterns)
+		return 0;
+
+	cmd.len[0] = struct_size(pattern_cmd, patterns, wowlan->n_patterns);
+
+	pattern_cmd = kzalloc(cmd.len[0], GFP_KERNEL);
+	if (!pattern_cmd)
+		return -ENOMEM;
+
+	pattern_cmd->n_patterns = wowlan->n_patterns;
+	pattern_cmd->sta_id = ap_sta_id;
+
+	for (int i = 0; i < wowlan->n_patterns; i++) {
+		int mask_len = DIV_ROUND_UP(wowlan->patterns[i].pattern_len, 8);
+
+		pattern_cmd->patterns[i].pattern_type =
+			WOWLAN_PATTERN_TYPE_BITMASK;
+
+		memcpy(&pattern_cmd->patterns[i].u.bitmask.mask,
+		       wowlan->patterns[i].mask, mask_len);
+		memcpy(&pattern_cmd->patterns[i].u.bitmask.pattern,
+		       wowlan->patterns[i].pattern,
+		       wowlan->patterns[i].pattern_len);
+		pattern_cmd->patterns[i].u.bitmask.mask_size = mask_len;
+		pattern_cmd->patterns[i].u.bitmask.pattern_size =
+			wowlan->patterns[i].pattern_len;
+	}
+
+	cmd.data[0] = pattern_cmd;
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	kfree(pattern_cmd);
+	return ret;
+}
+
+static int
+iwl_mld_send_proto_offload(struct iwl_mld *mld,
+			   struct ieee80211_vif *vif,
+			   u8 ap_sta_id)
+{
+	struct iwl_proto_offload_cmd_v4 *cmd __free(kfree);
+	struct iwl_host_cmd hcmd = {
+		.id = PROT_OFFLOAD_CONFIG_CMD,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+		.len[0] = sizeof(*cmd),
+	};
+	u32 enabled = 0;
+
+	cmd = kzalloc(hcmd.len[0], GFP_KERNEL);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_wowlan_data *wowlan_data = &mld_vif->wowlan_data;
+	struct iwl_ns_config *nsc;
+	struct iwl_targ_addr *addrs;
+	int n_nsc, n_addrs;
+	int i, c;
+	int num_skipped = 0;
+
+	nsc = cmd->ns_config;
+	n_nsc = IWL_PROTO_OFFLOAD_NUM_NS_CONFIG_V3L;
+	addrs = cmd->targ_addrs;
+	n_addrs = IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_V3L;
+
+	/* For each address we have (and that will fit) fill a target
+	 * address struct and combine for NS offload structs with the
+	 * solicited node addresses.
+	 */
+	for (i = 0, c = 0;
+		i < wowlan_data->num_target_ipv6_addrs &&
+		i < n_addrs && c < n_nsc; i++) {
+		int j;
+		struct in6_addr solicited_addr;
+
+		/* Because ns is offloaded skip tentative address to avoid
+		 * violating RFC4862.
+		 */
+		if (test_bit(i, wowlan_data->tentative_addrs)) {
+			num_skipped++;
+			continue;
+		}
+
+		addrconf_addr_solict_mult(&wowlan_data->target_ipv6_addrs[i],
+					  &solicited_addr);
+		for (j = 0; j < c; j++)
+			if (ipv6_addr_cmp(&nsc[j].dest_ipv6_addr,
+					  &solicited_addr) == 0)
+				break;
+		if (j == c)
+			c++;
+		addrs[i].addr = wowlan_data->target_ipv6_addrs[i];
+		addrs[i].config_num = cpu_to_le32(j);
+		nsc[j].dest_ipv6_addr = solicited_addr;
+		memcpy(nsc[j].target_mac_addr, vif->addr, ETH_ALEN);
+	}
+
+	if (wowlan_data->num_target_ipv6_addrs - num_skipped)
+		enabled |= IWL_D3_PROTO_IPV6_VALID;
+
+	cmd->num_valid_ipv6_addrs = cpu_to_le32(i - num_skipped);
+	if (enabled & IWL_D3_PROTO_IPV6_VALID)
+		enabled |= IWL_D3_PROTO_OFFLOAD_NS;
+#endif
+
+	if (vif->cfg.arp_addr_cnt) {
+		enabled |= IWL_D3_PROTO_OFFLOAD_ARP | IWL_D3_PROTO_IPV4_VALID;
+		cmd->common.host_ipv4_addr = vif->cfg.arp_addr_list[0];
+		ether_addr_copy(cmd->common.arp_mac_addr, vif->addr);
+	}
+
+	enabled |= IWL_D3_PROTO_OFFLOAD_BTM;
+	cmd->common.enabled = cpu_to_le32(enabled);
+	cmd->sta_id = cpu_to_le32(ap_sta_id);
+	hcmd.data[0] = cmd;
+	return iwl_mld_send_cmd(mld, &hcmd);
+}
+
+static int
+iwl_mld_wowlan_config(struct iwl_mld *mld, struct ieee80211_vif *bss_vif,
+		      struct cfg80211_wowlan *wowlan)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_vif);
+	struct ieee80211_sta *ap_sta = mld_vif->ap_sta;
+	struct iwl_wowlan_config_cmd wowlan_config_cmd = {
+			.offloading_tid = IWL_WOWLAN_OFFLOAD_TID,
+	};
+	u32 sta_id_mask;
+	int ap_sta_id, ret;
+	int link_id = iwl_mld_get_primary_link(bss_vif);
+	struct ieee80211_bss_conf *link_conf;
+
+	ret = iwl_mld_block_emlsr_sync(mld, bss_vif,
+				       IWL_MLD_EMLSR_BLOCKED_WOWLAN, link_id);
+	if (ret)
+		return ret;
+
+	link_conf = link_conf_dereference_protected(bss_vif, link_id);
+
+	if (WARN_ON(!ap_sta || !link_conf))
+		return -EINVAL;
+
+	sta_id_mask = iwl_mld_fw_sta_id_mask(mld, ap_sta);
+	if (WARN_ON(hweight32(sta_id_mask) != 1))
+		return -EINVAL;
+
+	ap_sta_id = __ffs(sta_id_mask);
+	wowlan_config_cmd.sta_id = ap_sta_id;
+
+	ret = iwl_mld_ensure_queue(mld,
+				   ap_sta->txq[wowlan_config_cmd.offloading_tid]);
+	if (ret)
+		return ret;
+
+	iwl_mld_set_wowlan_config_cmd(mld, wowlan,
+				      &wowlan_config_cmd, ap_sta);
+	ret = iwl_mld_send_cmd_pdu(mld, WOWLAN_CONFIGURATION,
+				   &wowlan_config_cmd);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_suspend_send_security_cmds(mld, bss_vif, mld_vif,
+						 ap_sta_id);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_send_patterns(mld, wowlan, ap_sta_id);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_send_proto_offload(mld, bss_vif, ap_sta_id);
+	if (ret)
+		return ret;
+
+	iwl_mld_enable_beacon_filter(mld, link_conf, true);
+	return iwl_mld_update_mac_power(mld, bss_vif, true);
+}
+
+int iwl_mld_wowlan_suspend(struct iwl_mld *mld, struct cfg80211_wowlan *wowlan)
+{
+	struct ieee80211_vif *bss_vif;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!wowlan))
+		return 1;
+
+	IWL_DEBUG_WOWLAN(mld, "Starting the wowlan suspend flow\n");
+
+	bss_vif = iwl_mld_get_bss_vif(mld);
+	if (WARN_ON(!bss_vif))
+		return 1;
+
+	if (!bss_vif->cfg.assoc) {
+		int ret;
+		/* If we're not associated, this must be netdetect */
+		if (WARN_ON(!wowlan->nd_config))
+			return 1;
+
+		ret = iwl_mld_netdetect_config(mld, bss_vif, wowlan);
+		if (!ret)
+			mld->netdetect = true;
+
+		return ret;
+	}
+
+	return iwl_mld_wowlan_config(mld, bss_vif, wowlan);
+}
+
+/* Returns 0 on success, 1 if an error occurred in firmware during d3,
+ * A negative value is expected only in unrecovreable cases.
+ */
+int iwl_mld_wowlan_resume(struct iwl_mld *mld)
+{
+	struct ieee80211_vif *bss_vif;
+	struct ieee80211_bss_conf *link_conf;
+	struct iwl_mld_netdetect_res netdetect_res;
+	struct iwl_mld_resume_data resume_data = {
+		.notifs_expected =
+			IWL_D3_NOTIF_WOWLAN_INFO |
+			IWL_D3_NOTIF_D3_END_NOTIF,
+		.netdetect_res = &netdetect_res,
+	};
+	int link_id;
+	int ret;
+	bool fw_err = false;
+	bool keep_connection;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	IWL_DEBUG_WOWLAN(mld, "Starting the wowlan resume flow\n");
+
+	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
+	if (!mld->fw_status.in_d3) {
+		IWL_DEBUG_WOWLAN(mld,
+				 "Device_powered_off() was called during wowlan\n");
+		goto err;
+	}
+
+	mld->fw_status.in_d3 = false;
+	mld->scan.last_start_time_jiffies = jiffies;
+
+	bss_vif = iwl_mld_get_bss_vif(mld);
+	if (WARN_ON(!bss_vif))
+		goto err;
+
+	/* We can't have several links upon wowlan entry,
+	 * this is enforced in the suspend flow.
+	 */
+	WARN_ON(hweight16(bss_vif->active_links) > 1);
+	link_id = bss_vif->active_links ? __ffs(bss_vif->active_links) : 0;
+	link_conf = link_conf_dereference_protected(bss_vif, link_id);
+
+	if (WARN_ON(!link_conf))
+		goto err;
+
+	iwl_fw_dbg_read_d3_debug_data(&mld->fwrt);
+
+	if (iwl_mld_fw_needs_restart(mld, bss_vif)) {
+		fw_err = true;
+		goto err;
+	}
+
+	resume_data.wowlan_status = kzalloc(sizeof(*resume_data.wowlan_status),
+					    GFP_KERNEL);
+	if (!resume_data.wowlan_status)
+		return -1;
+
+	if (mld->netdetect)
+		resume_data.notifs_expected |= IWL_D3_ND_MATCH_INFO;
+
+	ret = iwl_mld_wait_d3_notif(mld, &resume_data, true);
+	if (ret) {
+		IWL_ERR(mld, "Couldn't get the d3 notifs %d\n", ret);
+		fw_err = true;
+		goto err;
+	}
+
+	if (resume_data.d3_end_flags & IWL_D0I3_RESET_REQUIRE) {
+		mld->fw_status.in_hw_restart = true;
+		goto process_wakeup_results;
+	}
+
+	iwl_mld_update_changed_regdomain(mld);
+	iwl_mld_update_mac_power(mld, bss_vif, false);
+	iwl_mld_enable_beacon_filter(mld, link_conf, false);
+	iwl_mld_update_device_power(mld, false);
+
+	if (mld->netdetect)
+		ret = iwl_mld_scan_stop(mld, IWL_MLD_SCAN_NETDETECT, false);
+
+ process_wakeup_results:
+	if (mld->netdetect) {
+		iwl_mld_process_netdetect_res(mld, bss_vif, &resume_data);
+		mld->netdetect = false;
+	} else {
+		keep_connection =
+			iwl_mld_process_wowlan_status(mld, bss_vif,
+						      resume_data.wowlan_status);
+
+		/* EMLSR state will be cleared if the connection is not kept */
+		if (keep_connection)
+			iwl_mld_unblock_emlsr(mld, bss_vif,
+					      IWL_MLD_EMLSR_BLOCKED_WOWLAN);
+	}
+
+	if (!mld->netdetect && !keep_connection)
+		ieee80211_resume_disconnect(bss_vif);
+
+	goto out;
+
+ err:
+	if (fw_err) {
+		mld->trans->state = IWL_TRANS_NO_FW;
+		set_bit(STATUS_FW_ERROR, &mld->trans->status);
+	}
+
+	mld->fw_status.in_hw_restart = true;
+	ret = 1;
+ out:
+	if (resume_data.wowlan_status) {
+		kfree(resume_data.wowlan_status->wake_packet);
+		kfree(resume_data.wowlan_status);
+	}
+
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/d3.h b/drivers/net/wireless/intel/iwlwifi/mld/d3.h
new file mode 100644
index 0000000000000..618d6fb3c7964
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/d3.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_d3_h__
+#define __iwl_mld_d3_h__
+
+#include "fw/api/d3.h"
+
+struct iwl_mld_rekey_data {
+	bool valid;
+	u8 kck[NL80211_KCK_EXT_LEN];
+	u8 kek[NL80211_KEK_EXT_LEN];
+	size_t kck_len;
+	size_t kek_len;
+	__le64 replay_ctr;
+	u32 akm;
+};
+
+/**
+ * struct iwl_mld_wowlan_data - data used by the wowlan suspend flow
+ *
+ * @target_ipv6_addrs: IPv6 addresses on this interface for offload
+ * @tentative_addrs: bitmap of tentative IPv6 addresses in @target_ipv6_addrs
+ * @num_target_ipv6_addrs: number of @target_ipv6_addrs
+ * @rekey_data: security key data used for rekeying during D3
+ */
+struct iwl_mld_wowlan_data {
+#if IS_ENABLED(CONFIG_IPV6)
+	struct in6_addr target_ipv6_addrs[IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_MAX];
+	unsigned long tentative_addrs[BITS_TO_LONGS(IWL_PROTO_OFFLOAD_NUM_IPV6_ADDRS_MAX)];
+	int num_target_ipv6_addrs;
+#endif
+	struct iwl_mld_rekey_data rekey_data;
+};
+
+int iwl_mld_no_wowlan_resume(struct iwl_mld *mld);
+int iwl_mld_no_wowlan_suspend(struct iwl_mld *mld);
+int iwl_mld_wowlan_suspend(struct iwl_mld *mld,
+			   struct cfg80211_wowlan *wowlan);
+int iwl_mld_wowlan_resume(struct iwl_mld *mld);
+void iwl_mld_set_rekey_data(struct ieee80211_hw *hw,
+			    struct ieee80211_vif *vif,
+			    struct cfg80211_gtk_rekey_data *data);
+#if IS_ENABLED(CONFIG_IPV6)
+void iwl_mld_ipv6_addr_change(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct inet6_dev *idev);
+#endif
+
+#endif /* __iwl_mld_d3_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
new file mode 100644
index 0000000000000..c759c5c68dc04
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -0,0 +1,823 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "mld.h"
+#include "debugfs.h"
+#include "iwl-io.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "sta.h"
+#include "tlc.h"
+#include "power.h"
+#include "notif.h"
+#include "ap.h"
+#include "iwl-utils.h"
+#ifdef CONFIG_THERMAL
+#include "thermal.h"
+#endif
+
+#include "fw/api/rs.h"
+#include "fw/api/dhc.h"
+#include "fw/api/rfi.h"
+
+#define MLD_DEBUGFS_READ_FILE_OPS(name, bufsz)				\
+	_MLD_DEBUGFS_READ_FILE_OPS(name, bufsz, struct iwl_mld)
+
+#define MLD_DEBUGFS_ADD_FILE_ALIAS(alias, name, parent, mode)		\
+	debugfs_create_file(alias, mode, parent, mld,			\
+			    &iwl_dbgfs_##name##_ops)
+#define MLD_DEBUGFS_ADD_FILE(name, parent, mode)			\
+	MLD_DEBUGFS_ADD_FILE_ALIAS(#name, name, parent, mode)
+
+static bool iwl_mld_dbgfs_fw_cmd_disabled(struct iwl_mld *mld)
+{
+#ifdef CONFIG_PM_SLEEP
+	return !mld->fw_status.running || mld->fw_status.in_d3;
+#else
+	return !mld->fw_status.running;
+#endif /* CONFIG_PM_SLEEP */
+}
+
+static ssize_t iwl_dbgfs_fw_dbg_clear_write(struct iwl_mld *mld,
+					    char *buf, size_t count)
+{
+	/* If the firmware is not running, silently succeed since there is
+	 * no data to clear.
+	 */
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return 0;
+
+	iwl_fw_dbg_clear_monitor_buf(&mld->fwrt);
+
+	return count;
+}
+
+static ssize_t iwl_dbgfs_fw_nmi_write(struct iwl_mld *mld, char *buf,
+				      size_t count)
+{
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	IWL_ERR(mld, "Triggering an NMI from debugfs\n");
+
+	if (count == 6 && !strcmp(buf, "nolog\n"))
+		mld->fw_status.do_not_dump_once = true;
+
+	iwl_force_nmi(mld->trans);
+
+	return count;
+}
+
+static ssize_t iwl_dbgfs_fw_restart_write(struct iwl_mld *mld, char *buf,
+					  size_t count)
+{
+	int __maybe_unused ret;
+
+	if (!iwlwifi_mod_params.fw_restart)
+		return -EPERM;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	if (count == 6 && !strcmp(buf, "nolog\n")) {
+		mld->fw_status.do_not_dump_once = true;
+		set_bit(STATUS_SUPPRESS_CMD_ERROR_ONCE, &mld->trans->status);
+	}
+
+	/* take the return value to make compiler happy - it will
+	 * fail anyway
+	 */
+	ret = iwl_mld_send_cmd_empty(mld, WIDE_ID(LONG_GROUP, REPLY_ERROR));
+
+	return count;
+}
+
+static ssize_t iwl_dbgfs_send_echo_cmd_write(struct iwl_mld *mld, char *buf,
+					     size_t count)
+{
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	return iwl_mld_send_cmd_empty(mld, ECHO_CMD) ?: count;
+}
+
+struct iwl_mld_sniffer_apply {
+	struct iwl_mld *mld;
+	const u8 *bssid;
+	u16 aid;
+};
+
+static bool iwl_mld_sniffer_apply(struct iwl_notif_wait_data *notif_data,
+				  struct iwl_rx_packet *pkt, void *data)
+{
+	struct iwl_mld_sniffer_apply *apply = data;
+
+	apply->mld->monitor.cur_aid = cpu_to_le16(apply->aid);
+	memcpy(apply->mld->monitor.cur_bssid, apply->bssid,
+	       sizeof(apply->mld->monitor.cur_bssid));
+
+	return true;
+}
+
+static ssize_t
+iwl_dbgfs_he_sniffer_params_write(struct iwl_mld *mld, char *buf,
+				  size_t count)
+{
+	struct iwl_notification_wait wait;
+	struct iwl_he_monitor_cmd he_mon_cmd = {};
+	struct iwl_mld_sniffer_apply apply = {
+		.mld = mld,
+	};
+	u16 wait_cmds[] = {
+		WIDE_ID(DATA_PATH_GROUP, HE_AIR_SNIFFER_CONFIG_CMD),
+	};
+	u32 aid;
+	int ret;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	if (!mld->monitor.on)
+		return -ENODEV;
+
+	ret = sscanf(buf, "%x %2hhx:%2hhx:%2hhx:%2hhx:%2hhx:%2hhx", &aid,
+		     &he_mon_cmd.bssid[0], &he_mon_cmd.bssid[1],
+		     &he_mon_cmd.bssid[2], &he_mon_cmd.bssid[3],
+		     &he_mon_cmd.bssid[4], &he_mon_cmd.bssid[5]);
+	if (ret != 7)
+		return -EINVAL;
+
+	he_mon_cmd.aid = cpu_to_le16(aid);
+
+	apply.aid = aid;
+	apply.bssid = (void *)he_mon_cmd.bssid;
+
+	/* Use the notification waiter to get our function triggered
+	 * in sequence with other RX. This ensures that frames we get
+	 * on the RX queue _before_ the new configuration is applied
+	 * still have mld->cur_aid pointing to the old AID, and that
+	 * frames on the RX queue _after_ the firmware processed the
+	 * new configuration (and sent the response, synchronously)
+	 * get mld->cur_aid correctly set to the new AID.
+	 */
+	iwl_init_notification_wait(&mld->notif_wait, &wait,
+				   wait_cmds, ARRAY_SIZE(wait_cmds),
+				   iwl_mld_sniffer_apply, &apply);
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(DATA_PATH_GROUP,
+					   HE_AIR_SNIFFER_CONFIG_CMD),
+				   &he_mon_cmd);
+
+	/* no need to really wait, we already did anyway */
+	iwl_remove_notification(&mld->notif_wait, &wait);
+
+	return ret ?: count;
+}
+
+static ssize_t
+iwl_dbgfs_he_sniffer_params_read(struct iwl_mld *mld, size_t count,
+				 char *buf)
+{
+	return scnprintf(buf, count,
+			 "%d %02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx\n",
+			 le16_to_cpu(mld->monitor.cur_aid),
+			 mld->monitor.cur_bssid[0], mld->monitor.cur_bssid[1],
+			 mld->monitor.cur_bssid[2], mld->monitor.cur_bssid[3],
+			 mld->monitor.cur_bssid[4], mld->monitor.cur_bssid[5]);
+}
+
+/* The size computation is as follows:
+ * each number needs at most 3 characters, number of rows is the size of
+ * the table; So, need 5 chars for the "freq: " part and each tuple afterwards
+ * needs 6 characters for numbers and 5 for the punctuation around. 32 bytes
+ * for feature support message.
+ */
+#define IWL_RFI_DDR_BUF_SIZE (IWL_RFI_DDR_LUT_INSTALLED_SIZE *\
+				(5 + IWL_RFI_DDR_LUT_ENTRY_CHANNELS_NUM *\
+					(6 + 5)) + 32)
+#define IWL_RFI_DLVR_BUF_SIZE (IWL_RFI_DLVR_LUT_INSTALLED_SIZE *\
+				(5 + IWL_RFI_DLVR_LUT_ENTRY_CHANNELS_NUM *\
+					(6 + 5)) + 32)
+#define IWL_RFI_DESENSE_BUF_SIZE IWL_RFI_DDR_BUF_SIZE
+
+/* Extra 32 for "DDR and DLVR table" message */
+#define IWL_RFI_BUF_SIZE (IWL_RFI_DDR_BUF_SIZE + IWL_RFI_DLVR_BUF_SIZE +\
+				IWL_RFI_DESENSE_BUF_SIZE + 32)
+
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_nmi, 10);
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_restart, 10);
+WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD(he_sniffer_params, 32);
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_dbg_clear, 10);
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(send_echo_cmd, 8);
+
+static ssize_t iwl_dbgfs_wifi_6e_enable_read(struct iwl_mld *mld,
+					     size_t count, u8 *buf)
+{
+	int err;
+	u32 value;
+
+	err = iwl_bios_get_dsm(&mld->fwrt, DSM_FUNC_ENABLE_6E, &value);
+	if (err)
+		return err;
+
+	return scnprintf(buf, count, "0x%08x\n", value);
+}
+
+MLD_DEBUGFS_READ_FILE_OPS(wifi_6e_enable, 64);
+
+static ssize_t iwl_dbgfs_inject_packet_write(struct iwl_mld *mld,
+					     char *buf, size_t count)
+{
+	struct iwl_op_mode *opmode = container_of((void *)mld,
+						  struct iwl_op_mode,
+						  op_mode_specific);
+	struct iwl_rx_cmd_buffer rxb = {};
+	struct iwl_rx_packet *pkt;
+	int n_bytes = count / 2;
+	int ret = -EINVAL;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	rxb._page = alloc_pages(GFP_KERNEL, 0);
+	if (!rxb._page)
+		return -ENOMEM;
+	pkt = rxb_addr(&rxb);
+
+	ret = hex2bin(page_address(rxb._page), buf, n_bytes);
+	if (ret)
+		goto out;
+
+	/* avoid invalid memory access and malformed packet */
+	if (n_bytes < sizeof(*pkt) ||
+	    n_bytes != sizeof(*pkt) + iwl_rx_packet_payload_len(pkt))
+		goto out;
+
+	local_bh_disable();
+	iwl_mld_rx(opmode, NULL, &rxb);
+	local_bh_enable();
+	ret = 0;
+
+out:
+	iwl_free_rxb(&rxb);
+
+	return ret ?: count;
+}
+
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(inject_packet, 512);
+
+#ifdef CONFIG_THERMAL
+
+static ssize_t iwl_dbgfs_stop_ctdp_write(struct iwl_mld *mld,
+					 char *buf, size_t count)
+{
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	return iwl_mld_config_ctdp(mld, mld->cooling_dev.cur_state,
+				   CTDP_CMD_OPERATION_STOP) ? : count;
+}
+
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(stop_ctdp, 8);
+
+static ssize_t iwl_dbgfs_start_ctdp_write(struct iwl_mld *mld,
+					  char *buf, size_t count)
+{
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	return iwl_mld_config_ctdp(mld, mld->cooling_dev.cur_state,
+				   CTDP_CMD_OPERATION_START) ? : count;
+}
+
+WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(start_ctdp, 8);
+
+#endif /* CONFIG_THERMAL */
+
+void
+iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir)
+{
+	/* Add debugfs files here */
+
+	MLD_DEBUGFS_ADD_FILE(fw_nmi, debugfs_dir, 0200);
+	MLD_DEBUGFS_ADD_FILE(fw_restart, debugfs_dir, 0200);
+	MLD_DEBUGFS_ADD_FILE(wifi_6e_enable, debugfs_dir, 0400);
+	MLD_DEBUGFS_ADD_FILE(he_sniffer_params, debugfs_dir, 0600);
+	MLD_DEBUGFS_ADD_FILE(fw_dbg_clear, debugfs_dir, 0200);
+	MLD_DEBUGFS_ADD_FILE(send_echo_cmd, debugfs_dir, 0200);
+#ifdef CONFIG_THERMAL
+	MLD_DEBUGFS_ADD_FILE(start_ctdp, debugfs_dir, 0200);
+	MLD_DEBUGFS_ADD_FILE(stop_ctdp, debugfs_dir, 0200);
+#endif
+	MLD_DEBUGFS_ADD_FILE(inject_packet, debugfs_dir, 0200);
+
+	/* Create a symlink with mac80211. It will be removed when mac80211
+	 * exits (before the opmode exits which removes the target.)
+	 */
+	if (!IS_ERR(debugfs_dir)) {
+		char buf[100];
+
+		snprintf(buf, 100, "../../%pd2", debugfs_dir->d_parent);
+		debugfs_create_symlink("iwlwifi", mld->wiphy->debugfsdir,
+				       buf);
+	}
+}
+
+#define VIF_DEBUGFS_WRITE_FILE_OPS(name, bufsz)			\
+	WIPHY_DEBUGFS_WRITE_FILE_OPS(vif_##name, bufsz, vif)
+
+#define VIF_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz)			    \
+	IEEE80211_WIPHY_DEBUGFS_READ_WRITE_FILE_OPS(vif_##name, bufsz, vif) \
+
+#define VIF_DEBUGFS_ADD_FILE_ALIAS(alias, name, parent, mode)	\
+	debugfs_create_file(alias, mode, parent, vif,		\
+			    &iwl_dbgfs_vif_##name##_ops)
+#define VIF_DEBUGFS_ADD_FILE(name, parent, mode)		\
+	VIF_DEBUGFS_ADD_FILE_ALIAS(#name, name, parent, mode)
+
+static ssize_t iwl_dbgfs_vif_bf_params_write(struct iwl_mld *mld, char *buf,
+					     size_t count, void *data)
+{
+	struct ieee80211_vif *vif = data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int link_id = vif->active_links ? __ffs(vif->active_links) : 0;
+	struct ieee80211_bss_conf *link_conf;
+	int val;
+
+	if (!strncmp("bf_enable_beacon_filter=", buf, 24)) {
+		if (sscanf(buf + 24, "%d", &val) != 1)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	link_conf = link_conf_dereference_protected(vif, link_id);
+	if (WARN_ON(!link_conf))
+		return -ENODEV;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	mld_vif->disable_bf = !val;
+
+	if (val)
+		return iwl_mld_enable_beacon_filter(mld, link_conf,
+						    false) ?: count;
+	else
+		return iwl_mld_disable_beacon_filter(mld, vif) ?: count;
+}
+
+static ssize_t iwl_dbgfs_vif_pm_params_write(struct iwl_mld *mld,
+					     char *buf,
+					     size_t count, void *data)
+{
+	struct ieee80211_vif *vif = data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int val;
+
+	if (!strncmp("use_ps_poll=", buf, 12)) {
+		if (sscanf(buf + 12, "%d", &val) != 1)
+			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	mld_vif->use_ps_poll = val;
+
+	return iwl_mld_update_mac_power(mld, vif, false) ?: count;
+}
+
+static ssize_t iwl_dbgfs_vif_low_latency_write(struct iwl_mld *mld,
+					       char *buf, size_t count,
+					       void *data)
+{
+	struct ieee80211_vif *vif = data;
+	u8 value;
+	int ret;
+
+	ret = kstrtou8(buf, 0, &value);
+	if (ret)
+		return ret;
+
+	if (value > 1)
+		return -EINVAL;
+
+	iwl_mld_vif_update_low_latency(mld, vif, value, LOW_LATENCY_DEBUGFS);
+
+	return count;
+}
+
+static ssize_t iwl_dbgfs_vif_low_latency_read(struct ieee80211_vif *vif,
+					      size_t count, char *buf)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	char format[] = "traffic=%d\ndbgfs=%d\nvif_type=%d\nactual=%d\n";
+	u8 ll_causes;
+
+	if (WARN_ON(count < sizeof(format)))
+		return -EINVAL;
+
+	ll_causes = READ_ONCE(mld_vif->low_latency_causes);
+
+	/* all values in format are boolean so the size of format is enough
+	 * for holding the result string
+	 */
+	return scnprintf(buf, count, format,
+			 !!(ll_causes & LOW_LATENCY_TRAFFIC),
+			 !!(ll_causes & LOW_LATENCY_DEBUGFS),
+			 !!(ll_causes & LOW_LATENCY_VIF_TYPE),
+			 !!(ll_causes));
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(pm_params, 32);
+VIF_DEBUGFS_WRITE_FILE_OPS(bf_params, 32);
+VIF_DEBUGFS_READ_WRITE_FILE_OPS(low_latency, 45);
+
+static int
+_iwl_dbgfs_inject_beacon_ie(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			    char *bin, ssize_t len,
+			    bool restore)
+{
+	struct iwl_mld_vif *mld_vif;
+	struct iwl_mld_link *mld_link;
+	struct iwl_mac_beacon_cmd beacon_cmd = {};
+	int n_bytes = len / 2;
+
+	/* Element len should be represented by u8 */
+	if (n_bytes >= U8_MAX)
+		return -EINVAL;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	if (!vif)
+		return -EINVAL;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	mld_vif->beacon_inject_active = true;
+	mld->hw->extra_beacon_tailroom = n_bytes;
+
+	for_each_mld_vif_valid_link(mld_vif, mld_link) {
+		u32 offset;
+		struct ieee80211_tx_info *info;
+		struct ieee80211_bss_conf *link_conf =
+			link_conf_dereference_protected(vif, link_id);
+		struct ieee80211_chanctx_conf *ctx =
+			wiphy_dereference(mld->wiphy, link_conf->chanctx_conf);
+		struct sk_buff *beacon =
+			ieee80211_beacon_get_template(mld->hw, vif,
+						      NULL, link_id);
+
+		if (!beacon)
+			return -EINVAL;
+
+		if (!restore && (WARN_ON(!n_bytes || !bin) ||
+				 hex2bin(skb_put_zero(beacon, n_bytes),
+					 bin, n_bytes))) {
+			dev_kfree_skb(beacon);
+			return -EINVAL;
+		}
+
+		info = IEEE80211_SKB_CB(beacon);
+
+		beacon_cmd.flags =
+			cpu_to_le16(iwl_mld_get_rate_flags(mld, info, vif,
+							   link_conf,
+							   ctx->def.chan->band));
+		beacon_cmd.byte_cnt = cpu_to_le16((u16)beacon->len);
+		beacon_cmd.link_id =
+			cpu_to_le32(mld_link->fw_id);
+
+		iwl_mld_set_tim_idx(mld, &beacon_cmd.tim_idx,
+				    beacon->data, beacon->len);
+
+		offset = iwl_find_ie_offset(beacon->data,
+					    WLAN_EID_S1G_TWT,
+					    beacon->len);
+
+		beacon_cmd.btwt_offset = cpu_to_le32(offset);
+
+		iwl_mld_send_beacon_template_cmd(mld, beacon, &beacon_cmd);
+		dev_kfree_skb(beacon);
+	}
+
+	if (restore)
+		mld_vif->beacon_inject_active = false;
+
+	return 0;
+}
+
+static ssize_t
+iwl_dbgfs_vif_inject_beacon_ie_write(struct iwl_mld *mld,
+				     char *buf, size_t count,
+				     void *data)
+{
+	struct ieee80211_vif *vif = data;
+	int ret = _iwl_dbgfs_inject_beacon_ie(mld, vif, buf,
+					      count, false);
+
+	mld->hw->extra_beacon_tailroom = 0;
+	return ret ?: count;
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(inject_beacon_ie, 512);
+
+static ssize_t
+iwl_dbgfs_vif_inject_beacon_ie_restore_write(struct iwl_mld *mld,
+					     char *buf,
+					     size_t count,
+					     void *data)
+{
+	struct ieee80211_vif *vif = data;
+	int ret = _iwl_dbgfs_inject_beacon_ie(mld, vif, NULL,
+					      0, true);
+
+	mld->hw->extra_beacon_tailroom = 0;
+	return ret ?: count;
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(inject_beacon_ie_restore, 512);
+
+static ssize_t
+iwl_dbgfs_vif_twt_setup_write(struct iwl_mld *mld, char *buf, size_t count,
+			      void *data)
+{
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(IWL_ALWAYS_LONG_GROUP, DEBUG_HOST_COMMAND),
+	};
+	struct ieee80211_vif *vif = data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_dhc_twt_operation *dhc_twt_cmd;
+	struct iwl_dhc_cmd *cmd __free(kfree);
+	u64 target_wake_time;
+	u32 twt_operation, interval_exp, interval_mantissa, min_wake_duration;
+	u8 trigger, flow_type, flow_id, protection, tenth_param;
+	u8 twt_request = 1, broadcast = 0;
+	int ret;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	ret = sscanf(buf, "%u %llu %u %u %u %hhu %hhu %hhu %hhu %hhu",
+		     &twt_operation, &target_wake_time, &interval_exp,
+		     &interval_mantissa, &min_wake_duration, &trigger,
+		     &flow_type, &flow_id, &protection, &tenth_param);
+
+	/* the new twt_request parameter is optional for station */
+	if ((ret != 9 && ret != 10) ||
+	    (ret == 10 && vif->type != NL80211_IFTYPE_STATION &&
+	     tenth_param == 1))
+		return -EINVAL;
+
+	/* The 10th parameter:
+	 * In STA mode - the TWT type (broadcast or individual)
+	 * In AP mode - the role (0 responder, 2 unsolicited)
+	 */
+	if (ret == 10) {
+		if (vif->type == NL80211_IFTYPE_STATION)
+			broadcast = tenth_param;
+		else
+			twt_request = tenth_param;
+	}
+
+	cmd = kzalloc(sizeof(*cmd) + sizeof(*dhc_twt_cmd), GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	dhc_twt_cmd = (void *)cmd->data;
+	dhc_twt_cmd->mac_id = cpu_to_le32(mld_vif->fw_id);
+	dhc_twt_cmd->twt_operation = cpu_to_le32(twt_operation);
+	dhc_twt_cmd->target_wake_time = cpu_to_le64(target_wake_time);
+	dhc_twt_cmd->interval_exp = cpu_to_le32(interval_exp);
+	dhc_twt_cmd->interval_mantissa = cpu_to_le32(interval_mantissa);
+	dhc_twt_cmd->min_wake_duration = cpu_to_le32(min_wake_duration);
+	dhc_twt_cmd->trigger = trigger;
+	dhc_twt_cmd->flow_type = flow_type;
+	dhc_twt_cmd->flow_id = flow_id;
+	dhc_twt_cmd->protection = protection;
+	dhc_twt_cmd->twt_request = twt_request;
+	dhc_twt_cmd->negotiation_type = broadcast ? 3 : 0;
+
+	cmd->length = cpu_to_le32(sizeof(*dhc_twt_cmd) >> 2);
+	cmd->index_and_mask =
+		cpu_to_le32(DHC_TABLE_INTEGRATION | DHC_TARGET_UMAC |
+			    DHC_INT_UMAC_TWT_OPERATION);
+
+	hcmd.len[0] = sizeof(*cmd) + sizeof(*dhc_twt_cmd);
+	hcmd.data[0] = cmd;
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+
+	return ret ?: count;
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(twt_setup, 256);
+
+static ssize_t
+iwl_dbgfs_vif_twt_operation_write(struct iwl_mld *mld, char *buf, size_t count,
+				  void *data)
+{
+	struct ieee80211_vif *vif = data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_twt_operation_cmd twt_cmd = {};
+	int link_id = vif->active_links ? __ffs(vif->active_links) : 0;
+	struct iwl_mld_link *mld_link = iwl_mld_link_dereference_check(mld_vif,
+								       link_id);
+	int ret;
+
+	if (WARN_ON(!mld_link))
+		return -ENODEV;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	if (hweight16(vif->active_links) > 1)
+		return -EOPNOTSUPP;
+
+	ret = sscanf(buf,
+		     "%u %llu %u %u %u %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu %hhu",
+		     &twt_cmd.twt_operation, &twt_cmd.target_wake_time,
+		     &twt_cmd.interval_exponent, &twt_cmd.interval_mantissa,
+		     &twt_cmd.minimum_wake_duration, &twt_cmd.trigger,
+		     &twt_cmd.flow_type, &twt_cmd.flow_id,
+		     &twt_cmd.twt_protection, &twt_cmd.ndp_paging_indicator,
+		     &twt_cmd.responder_pm_mode, &twt_cmd.negotiation_type,
+		     &twt_cmd.twt_request, &twt_cmd.implicit,
+		     &twt_cmd.twt_group_assignment, &twt_cmd.twt_channel,
+		     &twt_cmd.restricted_info_present, &twt_cmd.dl_bitmap_valid,
+		     &twt_cmd.ul_bitmap_valid, &twt_cmd.dl_tid_bitmap,
+		     &twt_cmd.ul_tid_bitmap);
+
+	if (ret != 21)
+		return -EINVAL;
+
+	twt_cmd.link_id = cpu_to_le32(mld_link->fw_id);
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(MAC_CONF_GROUP, TWT_OPERATION_CMD),
+				   &twt_cmd);
+	return ret ?: count;
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(twt_operation, 256);
+
+void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif)
+{
+	struct dentry *mld_vif_dbgfs =
+		debugfs_create_dir("iwlmld", vif->debugfs_dir);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	char target[3 * 3 + 11 + (NL80211_WIPHY_NAME_MAXLEN + 1) +
+		    (7 + IFNAMSIZ + 1) + 6 + 1];
+	char name[7 + IFNAMSIZ + 1];
+
+	/* Create symlink for convenience pointing to interface specific
+	 * debugfs entries for the driver. For example, under
+	 * /sys/kernel/debug/iwlwifi/0000\:02\:00.0/iwlmld/
+	 * find
+	 * netdev:wlan0 -> ../../../ieee80211/phy0/netdev:wlan0/iwlmld/
+	 */
+	snprintf(name, sizeof(name), "%pd", vif->debugfs_dir);
+	snprintf(target, sizeof(target), "../../../%pd3/iwlmld",
+		 vif->debugfs_dir);
+	mld_vif->dbgfs_slink =
+		debugfs_create_symlink(name, mld->debugfs_dir, target);
+
+	if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM &&
+	    vif->type == NL80211_IFTYPE_STATION) {
+		VIF_DEBUGFS_ADD_FILE(pm_params, mld_vif_dbgfs, 0200);
+		VIF_DEBUGFS_ADD_FILE(bf_params, mld_vif_dbgfs, 0200);
+	}
+
+	if (vif->type == NL80211_IFTYPE_AP) {
+		VIF_DEBUGFS_ADD_FILE(inject_beacon_ie, mld_vif_dbgfs, 0200);
+		VIF_DEBUGFS_ADD_FILE(inject_beacon_ie_restore,
+				     mld_vif_dbgfs, 0200);
+	}
+
+	VIF_DEBUGFS_ADD_FILE(low_latency, mld_vif_dbgfs, 0600);
+	VIF_DEBUGFS_ADD_FILE(twt_setup, mld_vif_dbgfs, 0200);
+	VIF_DEBUGFS_ADD_FILE(twt_operation, mld_vif_dbgfs, 0200);
+}
+
+#define LINK_DEBUGFS_WRITE_FILE_OPS(name, bufsz)			\
+	WIPHY_DEBUGFS_WRITE_FILE_OPS(link_##name, bufsz, bss_conf)
+
+#define LINK_DEBUGFS_ADD_FILE_ALIAS(alias, name, parent, mode)		\
+	debugfs_create_file(alias, mode, parent, link_conf,		\
+			    &iwl_dbgfs_link_##name##_ops)
+#define LINK_DEBUGFS_ADD_FILE(name, parent, mode)			\
+	LINK_DEBUGFS_ADD_FILE_ALIAS(#name, name, parent, mode)
+
+void iwl_mld_add_link_debugfs(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link_conf,
+			      struct dentry *dir)
+{
+	struct dentry *mld_link_dir;
+
+	mld_link_dir = debugfs_lookup("iwlmld", dir);
+
+	/* For non-MLO vifs, the dir of deflink is the same as the vif's one.
+	 * so if iwlmld dir already exists, this means that this is deflink.
+	 * If not, this is a per-link dir of a MLO vif, add in it the iwlmld
+	 * dir.
+	 */
+	if (!mld_link_dir)
+		mld_link_dir = debugfs_create_dir("iwlmld", dir);
+}
+
+static ssize_t iwl_dbgfs_fixed_rate_write(struct iwl_mld *mld, char *buf,
+					  size_t count, void *data)
+{
+	struct ieee80211_link_sta *link_sta = data;
+	struct iwl_mld_link_sta *mld_link_sta;
+	u32 rate;
+	u32 partial = false;
+	char pretty_rate[100];
+	int ret;
+	u8 fw_sta_id;
+
+	mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+	if (WARN_ON(!mld_link_sta))
+		return -EINVAL;
+
+	fw_sta_id = mld_link_sta->fw_id;
+
+	if (sscanf(buf, "%i %i", &rate, &partial) == 0)
+		return -EINVAL;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	ret = iwl_mld_send_tlc_dhc(mld, fw_sta_id,
+				   partial ? IWL_TLC_DEBUG_PARTIAL_FIXED_RATE :
+					     IWL_TLC_DEBUG_FIXED_RATE,
+				   rate);
+
+	rs_pretty_print_rate(pretty_rate, sizeof(pretty_rate), rate);
+
+	IWL_DEBUG_RATE(mld, "sta_id %d rate %s partial: %d, ret:%d\n",
+		       fw_sta_id, pretty_rate, partial, ret);
+
+	return ret ? : count;
+}
+
+static ssize_t iwl_dbgfs_tlc_dhc_write(struct iwl_mld *mld, char *buf,
+				       size_t count, void *data)
+{
+	struct ieee80211_link_sta *link_sta = data;
+	struct iwl_mld_link_sta *mld_link_sta;
+	u32 type, value;
+	int ret;
+	u8 fw_sta_id;
+
+	mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+	if (WARN_ON(!mld_link_sta))
+		return -EINVAL;
+
+	fw_sta_id = mld_link_sta->fw_id;
+
+	if (sscanf(buf, "%i %i", &type, &value) != 2) {
+		IWL_DEBUG_RATE(mld, "usage <type> <value>\n");
+		return -EINVAL;
+	}
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	ret = iwl_mld_send_tlc_dhc(mld, fw_sta_id, type, value);
+
+	return ret ? : count;
+}
+
+#define LINK_STA_DEBUGFS_ADD_FILE_ALIAS(alias, name, parent, mode)	\
+	debugfs_create_file(alias, mode, parent, link_sta,		\
+			    &iwl_dbgfs_##name##_ops)
+#define LINK_STA_DEBUGFS_ADD_FILE(name, parent, mode)			\
+	LINK_STA_DEBUGFS_ADD_FILE_ALIAS(#name, name, parent, mode)
+
+#define LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(name, bufsz)			\
+	WIPHY_DEBUGFS_WRITE_FILE_OPS(name, bufsz, link_sta)
+
+LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(tlc_dhc, 64);
+LINK_STA_WIPHY_DEBUGFS_WRITE_OPS(fixed_rate, 64);
+
+void iwl_mld_add_link_sta_debugfs(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_link_sta *link_sta,
+				  struct dentry *dir)
+{
+	LINK_STA_DEBUGFS_ADD_FILE(fixed_rate, dir, 0200);
+	LINK_STA_DEBUGFS_ADD_FILE(tlc_dhc, dir, 0200);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
new file mode 100644
index 0000000000000..04c536db8b166
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include "iface.h"
+#include "sta.h"
+
+#define MLD_DEBUGFS_OPEN_WRAPPER(name, buflen, argtype)			\
+struct dbgfs_##name##_data {						\
+	argtype *arg;							\
+	bool read_done;							\
+	ssize_t rlen;							\
+	char buf[buflen];						\
+};									\
+static int _iwl_dbgfs_##name##_open(struct inode *inode,		\
+				    struct file *file)			\
+{									\
+	struct dbgfs_##name##_data *data;				\
+									\
+	if ((file->f_flags & O_ACCMODE) == O_RDWR)			\
+		return -EOPNOTSUPP;					\
+									\
+	data = kzalloc(sizeof(*data), GFP_KERNEL);			\
+	if (!data)							\
+		return -ENOMEM;						\
+									\
+	data->read_done = false;					\
+	data->arg = inode->i_private;					\
+	file->private_data = data;					\
+									\
+	return 0;							\
+}
+
+#define MLD_DEBUGFS_READ_WRAPPER(name)					\
+static ssize_t _iwl_dbgfs_##name##_read(struct file *file,		\
+					char __user *user_buf,		\
+					size_t count, loff_t *ppos)	\
+{									\
+	struct dbgfs_##name##_data *data = file->private_data;		\
+									\
+	if (!data->read_done) {						\
+		data->read_done = true;					\
+		data->rlen = iwl_dbgfs_##name##_read(data->arg,		\
+						     sizeof(data->buf),\
+						     data->buf);	\
+	}								\
+									\
+	if (data->rlen < 0)						\
+		return data->rlen;					\
+	return simple_read_from_buffer(user_buf, count, ppos,		\
+				       data->buf, data->rlen);		\
+}
+
+static int _iwl_dbgfs_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+#define _MLD_DEBUGFS_READ_FILE_OPS(name, buflen, argtype)		\
+MLD_DEBUGFS_OPEN_WRAPPER(name, buflen, argtype)				\
+MLD_DEBUGFS_READ_WRAPPER(name)						\
+static const struct file_operations iwl_dbgfs_##name##_ops = {		\
+	.read = _iwl_dbgfs_##name##_read,				\
+	.open = _iwl_dbgfs_##name##_open,				\
+	.llseek = generic_file_llseek,					\
+	.release = _iwl_dbgfs_release,					\
+}
+
+#define WIPHY_DEBUGFS_HANDLER_WRAPPER(name)				\
+static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
+				       struct file *file, char *buf,	\
+				       size_t count, void *data)	\
+{									\
+	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);		\
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);			\
+	return iwl_dbgfs_##name##_write(mld, buf, count, data);		\
+}
+
+static inline struct iwl_mld *
+iwl_mld_from_link_sta(struct ieee80211_link_sta *link_sta)
+{
+	struct ieee80211_vif *vif =
+		iwl_mld_sta_from_mac80211(link_sta->sta)->vif;
+	return iwl_mld_vif_from_mac80211(vif)->mld;
+}
+
+static inline struct iwl_mld *
+iwl_mld_from_bss_conf(struct ieee80211_bss_conf *link)
+{
+	return iwl_mld_vif_from_mac80211(link->vif)->mld;
+}
+
+static inline struct iwl_mld *iwl_mld_from_vif(struct ieee80211_vif *vif)
+{
+	return iwl_mld_vif_from_mac80211(vif)->mld;
+}
+
+#define WIPHY_DEBUGFS_WRITE_WRAPPER(name, bufsz, objtype)		\
+WIPHY_DEBUGFS_HANDLER_WRAPPER(name)					\
+static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
+					  const char __user *user_buf,	\
+					  size_t count, loff_t *ppos)	\
+{									\
+	struct ieee80211_##objtype *arg = file->private_data;		\
+	struct iwl_mld *mld = iwl_mld_from_##objtype(arg);		\
+	char buf[bufsz] = {};						\
+									\
+	return wiphy_locked_debugfs_write(mld->wiphy, file,		\
+				buf, sizeof(buf),			\
+				user_buf, count,			\
+				iwl_dbgfs_##name##_write_handler,	\
+				arg);					\
+}
+
+#define WIPHY_DEBUGFS_WRITE_FILE_OPS(name, bufsz, objtype)		\
+	WIPHY_DEBUGFS_WRITE_WRAPPER(name, bufsz, objtype)		\
+	static const struct file_operations iwl_dbgfs_##name##_ops = {	\
+		.write = __iwl_dbgfs_##name##_write,			\
+		.open = simple_open,					\
+		.llseek = generic_file_llseek,				\
+	}
+
+#define WIPHY_DEBUGFS_HANDLER_WRAPPER_MLD(name)				\
+static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
+				       struct file *file, char *buf,	\
+				       size_t count, void *data)	\
+{									\
+	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);		\
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);			\
+	return iwl_dbgfs_##name##_write(mld, buf, count);		\
+}
+
+#define WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\
+WIPHY_DEBUGFS_HANDLER_WRAPPER_MLD(name)					\
+static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
+					  const char __user *user_buf,	\
+					  size_t count, loff_t *ppos)	\
+{									\
+	struct dbgfs_##name##_data *data = file->private_data;		\
+	struct iwl_mld *mld = data->arg;				\
+									\
+	return wiphy_locked_debugfs_write(mld->wiphy, file,		\
+				data->buf, sizeof(data->buf),		\
+				user_buf, count,			\
+				iwl_dbgfs_##name##_write_handler,	\
+				NULL);					\
+}
+
+#define WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(name, bufsz)			\
+	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct iwl_mld)		\
+	WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\
+	static const struct file_operations iwl_dbgfs_##name##_ops = {	\
+		.write = __iwl_dbgfs_##name##_write,			\
+		.open = _iwl_dbgfs_##name##_open,			\
+		.llseek = generic_file_llseek,				\
+		.release = _iwl_dbgfs_release,				\
+	}
+
+#define WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD(name, bufsz)		\
+	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct iwl_mld)		\
+	WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\
+	MLD_DEBUGFS_READ_WRAPPER(name)					\
+	static const struct file_operations iwl_dbgfs_##name##_ops = {	\
+		.write = __iwl_dbgfs_##name##_write,			\
+		.read = _iwl_dbgfs_##name##_read,			\
+		.open = _iwl_dbgfs_##name##_open,			\
+		.llseek = generic_file_llseek,				\
+		.release = _iwl_dbgfs_release,				\
+	}
+
+#define WIPHY_DEBUGFS_WRITE_WRAPPER_IEEE80211(name, bufsz, objtype)	\
+WIPHY_DEBUGFS_HANDLER_WRAPPER(name)					\
+static ssize_t _iwl_dbgfs_##name##_write(struct file *file,		\
+					  const char __user *user_buf,	\
+					  size_t count, loff_t *ppos)	\
+{									\
+	struct dbgfs_##name##_data *data = file->private_data;		\
+	struct ieee80211_##objtype *arg = data->arg;			\
+	struct iwl_mld *mld = iwl_mld_from_##objtype(arg);		\
+	char buf[bufsz] = {};						\
+									\
+	return wiphy_locked_debugfs_write(mld->wiphy, file,		\
+				buf, sizeof(buf),			\
+				user_buf, count,			\
+				iwl_dbgfs_##name##_write_handler,	\
+				arg);					\
+}
+
+#define IEEE80211_WIPHY_DEBUGFS_READ_WRITE_FILE_OPS(name, bufsz, objtype) \
+	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct ieee80211_##objtype) \
+	WIPHY_DEBUGFS_WRITE_WRAPPER_IEEE80211(name, bufsz, objtype)	  \
+	MLD_DEBUGFS_READ_WRAPPER(name)					  \
+	static const struct file_operations iwl_dbgfs_##name##_ops = {	  \
+		.write = _iwl_dbgfs_##name##_write,			  \
+		.read = _iwl_dbgfs_##name##_read,			  \
+		.open = _iwl_dbgfs_##name##_open,			  \
+		.llseek = generic_file_llseek,				  \
+		.release = _iwl_dbgfs_release,				  \
+	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.c
new file mode 100644
index 0000000000000..f77ba21a174dd
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.c
@@ -0,0 +1,451 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include <linux/etherdevice.h>
+#include <linux/math64.h>
+#include <net/cfg80211.h>
+#include "mld.h"
+#include "iface.h"
+#include "phy.h"
+#include "iwl-io.h"
+#include "iwl-prph.h"
+#include "constants.h"
+#include "fw/api/location.h"
+#include "ftm-initiator.h"
+
+static void iwl_mld_ftm_cmd_common(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct iwl_tof_range_req_cmd *cmd,
+				   struct cfg80211_pmsr_request *req)
+{
+	int i;
+
+	cmd->initiator_flags =
+		cpu_to_le32(IWL_TOF_INITIATOR_FLAGS_MACADDR_RANDOM |
+			    IWL_TOF_INITIATOR_FLAGS_NON_ASAP_SUPPORT);
+	cmd->request_id = req->cookie;
+	cmd->num_of_ap = req->n_peers;
+
+	/* Use a large value for "no timeout". Don't use the maximum value
+	 * because of fw limitations.
+	 */
+	if (req->timeout)
+		cmd->req_timeout_ms = cpu_to_le32(min(req->timeout, 0xfffff));
+	else
+		cmd->req_timeout_ms = cpu_to_le32(0xfffff);
+
+	memcpy(cmd->macaddr_template, req->mac_addr, ETH_ALEN);
+	for (i = 0; i < ETH_ALEN; i++)
+		cmd->macaddr_mask[i] = ~req->mac_addr_mask[i];
+
+	if (vif->cfg.assoc) {
+		memcpy(cmd->range_req_bssid, vif->bss_conf.bssid, ETH_ALEN);
+
+		/* AP's TSF is only relevant if associated */
+		for (i = 0; i < req->n_peers; i++) {
+			if (req->peers[i].report_ap_tsf) {
+				struct iwl_mld_vif *mld_vif =
+					iwl_mld_vif_from_mac80211(vif);
+
+				cmd->tsf_mac_id = cpu_to_le32(mld_vif->fw_id);
+				return;
+			}
+		}
+	} else {
+		eth_broadcast_addr(cmd->range_req_bssid);
+	}
+
+	/* Don't report AP's TSF */
+	cmd->tsf_mac_id = cpu_to_le32(0xff);
+}
+
+static int
+iwl_mld_ftm_set_target_chandef(struct iwl_mld *mld,
+			       struct cfg80211_pmsr_request_peer *peer,
+			       struct iwl_tof_range_req_ap_entry *target)
+{
+	u32 freq = peer->chandef.chan->center_freq;
+
+	target->channel_num = ieee80211_frequency_to_channel(freq);
+
+	switch (peer->chandef.width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+		target->format_bw = IWL_LOCATION_FRAME_FORMAT_LEGACY;
+		target->format_bw |= IWL_LOCATION_BW_20MHZ << LOCATION_BW_POS;
+		break;
+	case NL80211_CHAN_WIDTH_20:
+		target->format_bw = IWL_LOCATION_FRAME_FORMAT_HT;
+		target->format_bw |= IWL_LOCATION_BW_20MHZ << LOCATION_BW_POS;
+		break;
+	case NL80211_CHAN_WIDTH_40:
+		target->format_bw = IWL_LOCATION_FRAME_FORMAT_HT;
+		target->format_bw |= IWL_LOCATION_BW_40MHZ << LOCATION_BW_POS;
+		break;
+	case NL80211_CHAN_WIDTH_80:
+		target->format_bw = IWL_LOCATION_FRAME_FORMAT_VHT;
+		target->format_bw |= IWL_LOCATION_BW_80MHZ << LOCATION_BW_POS;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		target->format_bw = IWL_LOCATION_FRAME_FORMAT_HE;
+		target->format_bw |= IWL_LOCATION_BW_160MHZ << LOCATION_BW_POS;
+		break;
+	default:
+		IWL_ERR(mld, "Unsupported BW in FTM request (%d)\n",
+			peer->chandef.width);
+		return -EINVAL;
+}
+
+	/* non EDCA based measurement must use HE preamble */
+	if (peer->ftm.trigger_based || peer->ftm.non_trigger_based)
+		target->format_bw |= IWL_LOCATION_FRAME_FORMAT_HE;
+
+	target->ctrl_ch_position =
+		(peer->chandef.width > NL80211_CHAN_WIDTH_20) ?
+		iwl_mld_get_fw_ctrl_pos(&peer->chandef) : 0;
+
+	target->band = iwl_mld_nl80211_band_to_fw(peer->chandef.chan->band);
+	return 0;
+}
+
+#define FTM_SET_FLAG(flag) (target->initiator_ap_flags |= \
+			    cpu_to_le32(IWL_INITIATOR_AP_FLAGS_##flag))
+
+static void
+iwl_mld_ftm_set_target_flags(struct iwl_mld *mld,
+			     struct cfg80211_pmsr_request_peer *peer,
+			     struct iwl_tof_range_req_ap_entry *target)
+{
+	target->initiator_ap_flags = cpu_to_le32(0);
+
+	if (peer->ftm.asap)
+		FTM_SET_FLAG(ASAP);
+
+	if (peer->ftm.request_lci)
+		FTM_SET_FLAG(LCI_REQUEST);
+
+	if (peer->ftm.request_civicloc)
+		FTM_SET_FLAG(CIVIC_REQUEST);
+
+	if (IWL_MLD_FTM_INITIATOR_DYNACK)
+		FTM_SET_FLAG(DYN_ACK);
+
+	if (IWL_MLD_FTM_INITIATOR_ALGO == IWL_TOF_ALGO_TYPE_LINEAR_REG)
+		FTM_SET_FLAG(ALGO_LR);
+	else if (IWL_MLD_FTM_INITIATOR_ALGO == IWL_TOF_ALGO_TYPE_FFT)
+		FTM_SET_FLAG(ALGO_FFT);
+
+	if (peer->ftm.trigger_based)
+		FTM_SET_FLAG(TB);
+	else if (peer->ftm.non_trigger_based)
+		FTM_SET_FLAG(NON_TB);
+
+	if ((peer->ftm.trigger_based || peer->ftm.non_trigger_based) &&
+	    peer->ftm.lmr_feedback)
+		FTM_SET_FLAG(LMR_FEEDBACK);
+}
+
+static void iwl_mld_ftm_set_sta(struct iwl_mld *mld, struct ieee80211_vif *vif,
+				struct cfg80211_pmsr_request_peer *peer,
+				struct iwl_tof_range_req_ap_entry *target)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	u32 sta_id_mask;
+
+	target->sta_id = IWL_INVALID_STA;
+
+	/* TODO: add ftm_unprotected debugfs support */
+
+	if (!vif->cfg.assoc || !mld_vif->ap_sta)
+		return;
+
+	sta_id_mask = iwl_mld_fw_sta_id_mask(mld, mld_vif->ap_sta);
+	if (WARN_ON(hweight32(sta_id_mask) != 1))
+		return;
+
+	target->sta_id = __ffs(sta_id_mask);
+
+	if (mld_vif->ap_sta->mfp &&
+	    (peer->ftm.trigger_based || peer->ftm.non_trigger_based))
+		FTM_SET_FLAG(PMF);
+}
+
+static int
+iwl_mld_ftm_set_target(struct iwl_mld *mld, struct ieee80211_vif *vif,
+		       struct cfg80211_pmsr_request_peer *peer,
+		       struct iwl_tof_range_req_ap_entry *target)
+{
+	u32 i2r_max_sts;
+	int ret;
+
+	ret = iwl_mld_ftm_set_target_chandef(mld, peer, target);
+	if (ret)
+		return ret;
+
+	memcpy(target->bssid, peer->addr, ETH_ALEN);
+	target->burst_period = cpu_to_le16(peer->ftm.burst_period);
+	target->samples_per_burst = peer->ftm.ftms_per_burst;
+	target->num_of_bursts = peer->ftm.num_bursts_exp;
+	iwl_mld_ftm_set_target_flags(mld, peer, target);
+	iwl_mld_ftm_set_sta(mld, vif, peer, target);
+
+	/* TODO: add secured ranging support */
+
+	i2r_max_sts = IWL_MLD_FTM_I2R_MAX_STS > 1 ? 1 :
+		IWL_MLD_FTM_I2R_MAX_STS;
+
+	target->r2i_ndp_params = IWL_MLD_FTM_R2I_MAX_REP |
+		(IWL_MLD_FTM_R2I_MAX_STS << IWL_LOCATION_MAX_STS_POS) |
+		(IWL_MLD_FTM_R2I_MAX_TOTAL_LTF << IWL_LOCATION_TOTAL_LTF_POS);
+	target->i2r_ndp_params = IWL_MLD_FTM_I2R_MAX_REP |
+		(i2r_max_sts << IWL_LOCATION_MAX_STS_POS) |
+		(IWL_MLD_FTM_I2R_MAX_TOTAL_LTF << IWL_LOCATION_TOTAL_LTF_POS);
+
+	if (peer->ftm.non_trigger_based) {
+		target->min_time_between_msr =
+			cpu_to_le16(IWL_MLD_FTM_NON_TB_MIN_TIME_BETWEEN_MSR);
+		target->burst_period =
+			cpu_to_le16(IWL_MLD_FTM_NON_TB_MAX_TIME_BETWEEN_MSR);
+	} else {
+		target->min_time_between_msr = cpu_to_le16(0);
+	}
+
+	/* TODO: Beacon interval is currently unknown, so use the common value
+	 * of 100 TUs.
+	 */
+	target->beacon_interval = cpu_to_le16(100);
+
+	return 0;
+}
+
+int iwl_mld_ftm_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
+		      struct cfg80211_pmsr_request *req)
+{
+	struct iwl_tof_range_req_cmd cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(LOCATION_GROUP, TOF_RANGE_REQ_CMD),
+		.dataflags[0] = IWL_HCMD_DFL_DUP,
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+	};
+	u8 i;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (mld->ftm_initiator.req)
+		return -EBUSY;
+
+	if (req->n_peers > ARRAY_SIZE(cmd.ap))
+		return -EINVAL;
+
+	memset(&cmd, 0, sizeof(cmd));
+
+	iwl_mld_ftm_cmd_common(mld, vif, (void *)&cmd, req);
+
+	for (i = 0; i < cmd.num_of_ap; i++) {
+		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
+		struct iwl_tof_range_req_ap_entry *target = &cmd.ap[i];
+
+		ret = iwl_mld_ftm_set_target(mld, vif, peer, target);
+		if (ret)
+			return ret;
+	}
+
+	/* TODO: get the status from the response*/
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (!ret) {
+		mld->ftm_initiator.req = req;
+		mld->ftm_initiator.req_wdev = ieee80211_vif_to_wdev(vif);
+	}
+
+	return ret;
+}
+
+static void iwl_mld_ftm_reset(struct iwl_mld *mld)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	mld->ftm_initiator.req = NULL;
+	mld->ftm_initiator.req_wdev = NULL;
+	memset(mld->ftm_initiator.responses, 0,
+	       sizeof(mld->ftm_initiator.responses));
+}
+
+static int iwl_mld_ftm_range_resp_valid(struct iwl_mld *mld, u8 request_id,
+					u8 num_of_aps)
+{
+	if (IWL_FW_CHECK(mld, request_id != (u8)mld->ftm_initiator.req->cookie,
+			 "Request ID mismatch, got %u, active %u\n",
+			 request_id, (u8)mld->ftm_initiator.req->cookie))
+		return -EINVAL;
+
+	if (IWL_FW_CHECK(mld, num_of_aps > mld->ftm_initiator.req->n_peers ||
+			 num_of_aps > IWL_TOF_MAX_APS,
+			 "FTM range response: invalid num of APs (%u)\n",
+			 num_of_aps))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int iwl_mld_ftm_find_peer(struct cfg80211_pmsr_request *req,
+				 const u8 *addr)
+{
+	for (int i = 0; i < req->n_peers; i++) {
+		struct cfg80211_pmsr_request_peer *peer = &req->peers[i];
+
+		if (ether_addr_equal_unaligned(peer->addr, addr))
+			return i;
+	}
+
+	return -ENOENT;
+}
+
+static void iwl_mld_debug_range_resp(struct iwl_mld *mld, u8 index,
+				     struct cfg80211_pmsr_result *res)
+{
+	s64 rtt_avg = div_s64(res->ftm.rtt_avg * 100, 6666);
+
+	IWL_DEBUG_INFO(mld, "entry %d\n", index);
+	IWL_DEBUG_INFO(mld, "\tstatus: %d\n", res->status);
+	IWL_DEBUG_INFO(mld, "\tBSSID: %pM\n", res->addr);
+	IWL_DEBUG_INFO(mld, "\thost time: %llu\n", res->host_time);
+	IWL_DEBUG_INFO(mld, "\tburst index: %d\n", res->ftm.burst_index);
+	IWL_DEBUG_INFO(mld, "\tsuccess num: %u\n", res->ftm.num_ftmr_successes);
+	IWL_DEBUG_INFO(mld, "\trssi: %d\n", res->ftm.rssi_avg);
+	IWL_DEBUG_INFO(mld, "\trssi spread: %d\n", res->ftm.rssi_spread);
+	IWL_DEBUG_INFO(mld, "\trtt: %lld\n", res->ftm.rtt_avg);
+	IWL_DEBUG_INFO(mld, "\trtt var: %llu\n", res->ftm.rtt_variance);
+	IWL_DEBUG_INFO(mld, "\trtt spread: %llu\n", res->ftm.rtt_spread);
+	IWL_DEBUG_INFO(mld, "\tdistance: %lld\n", rtt_avg);
+}
+
+void iwl_mld_handle_ftm_resp_notif(struct iwl_mld *mld,
+				   struct iwl_rx_packet *pkt)
+{
+	struct iwl_tof_range_rsp_ntfy *fw_resp = (void *)pkt->data;
+	u8 num_of_aps, last_in_batch;
+
+	if (IWL_FW_CHECK(mld, !mld->ftm_initiator.req,
+			 "FTM response without a pending request\n"))
+		return;
+
+	if (iwl_mld_ftm_range_resp_valid(mld, fw_resp->request_id,
+					 fw_resp->num_of_aps))
+		return;
+
+	num_of_aps = fw_resp->num_of_aps;
+	last_in_batch = fw_resp->last_report;
+
+	IWL_DEBUG_INFO(mld, "Range response received\n");
+	IWL_DEBUG_INFO(mld, "request id: %llu, num of entries: %u\n",
+		       mld->ftm_initiator.req->cookie, num_of_aps);
+
+	for (int i = 0; i < num_of_aps; i++) {
+		struct cfg80211_pmsr_result result = {};
+		struct iwl_tof_range_rsp_ap_entry_ntfy *fw_ap;
+		int peer_idx;
+
+		fw_ap = &fw_resp->ap[i];
+		result.final = fw_ap->last_burst;
+		result.ap_tsf = le32_to_cpu(fw_ap->start_tsf);
+		result.ap_tsf_valid = 1;
+
+		peer_idx = iwl_mld_ftm_find_peer(mld->ftm_initiator.req,
+						 fw_ap->bssid);
+		if (peer_idx < 0) {
+			IWL_WARN(mld,
+				 "Unknown address (%pM, target #%d) in FTM response\n",
+				 fw_ap->bssid, i);
+			continue;
+		}
+
+		switch (fw_ap->measure_status) {
+		case IWL_TOF_ENTRY_SUCCESS:
+			result.status = NL80211_PMSR_STATUS_SUCCESS;
+			break;
+		case IWL_TOF_ENTRY_TIMING_MEASURE_TIMEOUT:
+			result.status = NL80211_PMSR_STATUS_TIMEOUT;
+			break;
+		case IWL_TOF_ENTRY_NO_RESPONSE:
+			result.status = NL80211_PMSR_STATUS_FAILURE;
+			result.ftm.failure_reason =
+				NL80211_PMSR_FTM_FAILURE_NO_RESPONSE;
+			break;
+		case IWL_TOF_ENTRY_REQUEST_REJECTED:
+			result.status = NL80211_PMSR_STATUS_FAILURE;
+			result.ftm.failure_reason =
+				NL80211_PMSR_FTM_FAILURE_PEER_BUSY;
+			result.ftm.busy_retry_time = fw_ap->refusal_period;
+			break;
+		default:
+			result.status = NL80211_PMSR_STATUS_FAILURE;
+			result.ftm.failure_reason =
+				NL80211_PMSR_FTM_FAILURE_UNSPECIFIED;
+			break;
+		}
+		memcpy(result.addr, fw_ap->bssid, ETH_ALEN);
+
+		/* TODO: convert the timestamp from the result to systime */
+		result.host_time = ktime_get_boottime_ns();
+
+		result.type = NL80211_PMSR_TYPE_FTM;
+		result.ftm.burst_index = mld->ftm_initiator.responses[peer_idx];
+		mld->ftm_initiator.responses[peer_idx]++;
+		result.ftm.rssi_avg = fw_ap->rssi;
+		result.ftm.rssi_avg_valid = 1;
+		result.ftm.rssi_spread = fw_ap->rssi_spread;
+		result.ftm.rssi_spread_valid = 1;
+		result.ftm.rtt_avg = (s32)le32_to_cpu(fw_ap->rtt);
+		result.ftm.rtt_avg_valid = 1;
+		result.ftm.rtt_variance = le32_to_cpu(fw_ap->rtt_variance);
+		result.ftm.rtt_variance_valid = 1;
+		result.ftm.rtt_spread = le32_to_cpu(fw_ap->rtt_spread);
+		result.ftm.rtt_spread_valid = 1;
+
+		cfg80211_pmsr_report(mld->ftm_initiator.req_wdev,
+				     mld->ftm_initiator.req,
+				     &result, GFP_KERNEL);
+
+		if (fw_has_api(&mld->fw->ucode_capa,
+			       IWL_UCODE_TLV_API_FTM_RTT_ACCURACY))
+			IWL_DEBUG_INFO(mld, "RTT confidence: %u\n",
+				       fw_ap->rttConfidence);
+
+		iwl_mld_debug_range_resp(mld, i, &result);
+	}
+
+	if (last_in_batch) {
+		cfg80211_pmsr_complete(mld->ftm_initiator.req_wdev,
+				       mld->ftm_initiator.req,
+				       GFP_KERNEL);
+		iwl_mld_ftm_reset(mld);
+	}
+}
+
+void iwl_mld_ftm_restart_cleanup(struct iwl_mld *mld)
+{
+	struct cfg80211_pmsr_result result = {
+		.status = NL80211_PMSR_STATUS_FAILURE,
+		.final = 1,
+		.host_time = ktime_get_boottime_ns(),
+		.type = NL80211_PMSR_TYPE_FTM,
+	};
+
+	if (!mld->ftm_initiator.req)
+		return;
+
+	for (int i = 0; i < mld->ftm_initiator.req->n_peers; i++) {
+		memcpy(result.addr, mld->ftm_initiator.req->peers[i].addr,
+		       ETH_ALEN);
+
+		cfg80211_pmsr_report(mld->ftm_initiator.req_wdev,
+				     mld->ftm_initiator.req,
+				     &result, GFP_KERNEL);
+	}
+
+	cfg80211_pmsr_complete(mld->ftm_initiator.req_wdev,
+			       mld->ftm_initiator.req, GFP_KERNEL);
+	iwl_mld_ftm_reset(mld);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
new file mode 100644
index 0000000000000..e98fac34beba4
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#ifndef __iwl_mld_ftm_initiator_h__
+#define __iwl_mld_ftm_initiator_h__
+
+int iwl_mld_ftm_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
+		      struct cfg80211_pmsr_request *req);
+
+void iwl_mld_handle_ftm_resp_notif(struct iwl_mld *mld,
+				   struct iwl_rx_packet *pkt);
+void iwl_mld_ftm_restart_cleanup(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_ftm_initiator_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
new file mode 100644
index 0000000000000..ec93af362cfc8
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -0,0 +1,536 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "mld.h"
+
+#include "fw/api/alive.h"
+#include "fw/api/scan.h"
+#include "fw/api/rx.h"
+#include "fw/dbg.h"
+#include "fw/pnvm.h"
+#include "hcmd.h"
+#include "iwl-nvm-parse.h"
+#include "power.h"
+#include "mcc.h"
+#include "led.h"
+#include "coex.h"
+#include "regulatory.h"
+#include "thermal.h"
+
+static int iwl_mld_send_tx_ant_cfg(struct iwl_mld *mld)
+{
+	struct iwl_tx_ant_cfg_cmd cmd;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	cmd.valid = cpu_to_le32(iwl_mld_get_valid_tx_ant(mld));
+
+	IWL_DEBUG_FW(mld, "select valid tx ant: %u\n", cmd.valid);
+
+	return iwl_mld_send_cmd_pdu(mld, TX_ANT_CONFIGURATION_CMD, &cmd);
+}
+
+static int iwl_mld_send_rss_cfg_cmd(struct iwl_mld *mld)
+{
+	struct iwl_rss_config_cmd cmd = {
+		.flags = cpu_to_le32(IWL_RSS_ENABLE),
+		.hash_mask = BIT(IWL_RSS_HASH_TYPE_IPV4_TCP) |
+			     BIT(IWL_RSS_HASH_TYPE_IPV4_UDP) |
+			     BIT(IWL_RSS_HASH_TYPE_IPV4_PAYLOAD) |
+			     BIT(IWL_RSS_HASH_TYPE_IPV6_TCP) |
+			     BIT(IWL_RSS_HASH_TYPE_IPV6_UDP) |
+			     BIT(IWL_RSS_HASH_TYPE_IPV6_PAYLOAD),
+	};
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* Do not direct RSS traffic to Q 0 which is our fallback queue */
+	for (int i = 0; i < ARRAY_SIZE(cmd.indirection_table); i++)
+		cmd.indirection_table[i] =
+			1 + (i % (mld->trans->num_rx_queues - 1));
+	netdev_rss_key_fill(cmd.secret_key, sizeof(cmd.secret_key));
+
+	return iwl_mld_send_cmd_pdu(mld, RSS_CONFIG_CMD, &cmd);
+}
+
+static int iwl_mld_config_scan(struct iwl_mld *mld)
+{
+	struct iwl_scan_config cmd = {
+		.tx_chains = cpu_to_le32(iwl_mld_get_valid_tx_ant(mld)),
+		.rx_chains = cpu_to_le32(iwl_mld_get_valid_rx_ant(mld))
+	};
+
+	return iwl_mld_send_cmd_pdu(mld, WIDE_ID(LONG_GROUP, SCAN_CFG_CMD),
+				    &cmd);
+}
+
+static void iwl_mld_alive_imr_data(struct iwl_trans *trans,
+				   const struct iwl_imr_alive_info *imr_info)
+{
+	struct iwl_imr_data *imr_data = &trans->dbg.imr_data;
+
+	imr_data->imr_enable = le32_to_cpu(imr_info->enabled);
+	imr_data->imr_size = le32_to_cpu(imr_info->size);
+	imr_data->imr2sram_remainbyte = imr_data->imr_size;
+	imr_data->imr_base_addr = imr_info->base_addr;
+	imr_data->imr_curr_addr = le64_to_cpu(imr_data->imr_base_addr);
+
+	if (imr_data->imr_enable)
+		return;
+
+	for (int i = 0; i < ARRAY_SIZE(trans->dbg.active_regions); i++) {
+		struct iwl_fw_ini_region_tlv *reg;
+
+		if (!trans->dbg.active_regions[i])
+			continue;
+
+		reg = (void *)trans->dbg.active_regions[i]->data;
+
+		/* We have only one DRAM IMR region, so we
+		 * can break as soon as we find the first
+		 * one.
+		 */
+		if (reg->type == IWL_FW_INI_REGION_DRAM_IMR) {
+			trans->dbg.unsupported_region_msk |= BIT(i);
+			break;
+		}
+	}
+}
+
+static bool iwl_alive_fn(struct iwl_notif_wait_data *notif_wait,
+			 struct iwl_rx_packet *pkt, void *data)
+{
+	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
+	struct iwl_mld *mld =
+		container_of(notif_wait, struct iwl_mld, notif_wait);
+	struct iwl_trans *trans = mld->trans;
+	u32 version = iwl_fw_lookup_notif_ver(mld->fw, LEGACY_GROUP,
+					      UCODE_ALIVE_NTFY, 0);
+	struct iwl_alive_ntf_v6 *palive;
+	bool *alive_valid = data;
+	struct iwl_umac_alive *umac;
+	struct iwl_lmac_alive *lmac1;
+	struct iwl_lmac_alive *lmac2 = NULL;
+	u32 lmac_error_event_table;
+	u32 umac_error_table;
+	u16 status;
+
+	if (version < 6 || version > 7 || pkt_len != sizeof(*palive))
+		return false;
+
+	palive = (void *)pkt->data;
+
+	iwl_mld_alive_imr_data(trans, &palive->imr);
+
+	umac = &palive->umac_data;
+	lmac1 = &palive->lmac_data[0];
+	lmac2 = &palive->lmac_data[1];
+	status = le16_to_cpu(palive->status);
+
+	trans->sku_id[0] = le32_to_cpu(palive->sku_id.data[0]);
+	trans->sku_id[1] = le32_to_cpu(palive->sku_id.data[1]);
+	trans->sku_id[2] = le32_to_cpu(palive->sku_id.data[2]);
+
+	IWL_DEBUG_FW(mld, "Got sku_id: 0x0%x 0x0%x 0x0%x\n",
+		     trans->sku_id[0], trans->sku_id[1], trans->sku_id[2]);
+
+	lmac_error_event_table =
+		le32_to_cpu(lmac1->dbg_ptrs.error_event_table_ptr);
+	iwl_fw_lmac1_set_alive_err_table(trans, lmac_error_event_table);
+
+	if (lmac2)
+		trans->dbg.lmac_error_event_table[1] =
+			le32_to_cpu(lmac2->dbg_ptrs.error_event_table_ptr);
+
+	umac_error_table = le32_to_cpu(umac->dbg_ptrs.error_info_addr) &
+		~FW_ADDR_CACHE_CONTROL;
+
+	if (umac_error_table >= trans->cfg->min_umac_error_event_table)
+		iwl_fw_umac_set_alive_err_table(trans, umac_error_table);
+	else
+		IWL_ERR(mld, "Not valid error log pointer 0x%08X\n",
+			umac_error_table);
+
+	*alive_valid = status == IWL_ALIVE_STATUS_OK;
+
+	IWL_DEBUG_FW(mld,
+		     "Alive ucode status 0x%04x revision 0x%01X 0x%01X\n",
+		     status, lmac1->ver_type, lmac1->ver_subtype);
+
+	if (lmac2)
+		IWL_DEBUG_FW(mld, "Alive ucode CDB\n");
+
+	IWL_DEBUG_FW(mld,
+		     "UMAC version: Major - 0x%x, Minor - 0x%x\n",
+		     le32_to_cpu(umac->umac_major),
+		     le32_to_cpu(umac->umac_minor));
+
+	if (version >= 7)
+		IWL_DEBUG_FW(mld, "FW alive flags 0x%x\n",
+			     le16_to_cpu(palive->flags));
+
+	iwl_fwrt_update_fw_versions(&mld->fwrt, lmac1, umac);
+
+	return true;
+}
+
+#define MLD_ALIVE_TIMEOUT		(2 * HZ)
+#define MLD_INIT_COMPLETE_TIMEOUT	(2 * HZ)
+
+static void iwl_mld_print_alive_notif_timeout(struct iwl_mld *mld)
+{
+	struct iwl_trans *trans = mld->trans;
+	struct iwl_pc_data *pc_data;
+	u8 count;
+
+	IWL_ERR(mld,
+		"SecBoot CPU1 Status: 0x%x, CPU2 Status: 0x%x\n",
+		iwl_read_umac_prph(trans, UMAG_SB_CPU_1_STATUS),
+		iwl_read_umac_prph(trans,
+				   UMAG_SB_CPU_2_STATUS));
+#define IWL_FW_PRINT_REG_INFO(reg_name) \
+	IWL_ERR(mld, #reg_name ": 0x%x\n", iwl_read_umac_prph(trans, reg_name))
+
+	IWL_FW_PRINT_REG_INFO(WFPM_LMAC1_PD_NOTIFICATION);
+
+	IWL_FW_PRINT_REG_INFO(HPM_SECONDARY_DEVICE_STATE);
+
+	/* print OTP info */
+	IWL_FW_PRINT_REG_INFO(WFPM_MAC_OTP_CFG7_ADDR);
+	IWL_FW_PRINT_REG_INFO(WFPM_MAC_OTP_CFG7_DATA);
+#undef IWL_FW_PRINT_REG_INFO
+
+	pc_data = trans->dbg.pc_data;
+	for (count = 0; count < trans->dbg.num_pc; count++, pc_data++)
+		IWL_ERR(mld, "%s: 0x%x\n", pc_data->pc_name,
+			pc_data->pc_address);
+}
+
+static int iwl_mld_load_fw_wait_alive(struct iwl_mld *mld)
+{
+	const struct fw_img *fw =
+		iwl_get_ucode_image(mld->fw, IWL_UCODE_REGULAR);
+	static const u16 alive_cmd[] = { UCODE_ALIVE_NTFY };
+	struct iwl_notification_wait alive_wait;
+	bool alive_valid = false;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	iwl_init_notification_wait(&mld->notif_wait, &alive_wait,
+				   alive_cmd, ARRAY_SIZE(alive_cmd),
+				   iwl_alive_fn, &alive_valid);
+
+	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_EARLY, NULL);
+
+	ret = iwl_trans_start_fw(mld->trans, fw, true);
+	if (ret) {
+		iwl_remove_notification(&mld->notif_wait, &alive_wait);
+		return ret;
+	}
+
+	ret = iwl_wait_notification(&mld->notif_wait, &alive_wait,
+				    MLD_ALIVE_TIMEOUT);
+
+	if (ret) {
+		if (ret == -ETIMEDOUT)
+			iwl_fw_dbg_error_collect(&mld->fwrt,
+						 FW_DBG_TRIGGER_ALIVE_TIMEOUT);
+		iwl_mld_print_alive_notif_timeout(mld);
+		goto alive_failure;
+	}
+
+	if (!alive_valid) {
+		IWL_ERR(mld, "Loaded firmware is not valid!\n");
+		ret = -EIO;
+		goto alive_failure;
+	}
+
+	iwl_trans_fw_alive(mld->trans, 0);
+
+	return 0;
+
+alive_failure:
+	iwl_trans_stop_device(mld->trans);
+	return ret;
+}
+
+int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
+{
+	struct iwl_notification_wait init_wait;
+	struct iwl_init_extended_cfg_cmd init_cfg = {};
+	static const u16 init_complete[] = {
+		INIT_COMPLETE_NOTIF,
+	};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_load_fw_wait_alive(mld);
+	if (ret)
+		return ret;
+
+	mld->trans->step_urm =
+		!!(iwl_read_umac_prph(mld->trans, CNVI_PMU_STEP_FLOW) &
+		   CNVI_PMU_STEP_FLOW_FORCE_URM);
+
+	ret = iwl_pnvm_load(mld->trans, &mld->notif_wait,
+			    &mld->fw->ucode_capa);
+	if (ret) {
+		IWL_ERR(mld, "Timeout waiting for PNVM load %d\n", ret);
+		goto init_failure;
+	}
+
+	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_AFTER_ALIVE,
+			       NULL);
+
+	iwl_init_notification_wait(&mld->notif_wait,
+				   &init_wait,
+				   init_complete,
+				   ARRAY_SIZE(init_complete),
+				   NULL, NULL);
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(SYSTEM_GROUP, INIT_EXTENDED_CFG_CMD),
+				   &init_cfg);
+	if (ret) {
+		IWL_ERR(mld, "Failed to send init config command: %d\n", ret);
+		iwl_remove_notification(&mld->notif_wait, &init_wait);
+		goto init_failure;
+	}
+
+	ret = iwl_wait_notification(&mld->notif_wait, &init_wait,
+				    MLD_INIT_COMPLETE_TIMEOUT);
+	if (ret) {
+		IWL_ERR(mld, "Failed to get INIT_COMPLETE %d\n", ret);
+		goto init_failure;
+	}
+
+	if (!mld->nvm_data) {
+		mld->nvm_data = iwl_get_nvm(mld->trans, mld->fw, 0, 0);
+		if (IS_ERR(mld->nvm_data)) {
+			ret = PTR_ERR(mld->nvm_data);
+			mld->nvm_data = NULL;
+			IWL_ERR(mld, "Failed to read NVM: %d\n", ret);
+			goto init_failure;
+		}
+	}
+
+	return 0;
+
+init_failure:
+	iwl_trans_stop_device(mld->trans);
+	return ret;
+}
+
+int iwl_mld_load_fw(struct iwl_mld *mld)
+{
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_trans_start_hw(mld->trans);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_run_fw_init_sequence(mld);
+	if (ret)
+		return ret;
+
+	mld->fw_status.running = true;
+
+	return 0;
+}
+
+void iwl_mld_stop_fw(struct iwl_mld *mld)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	iwl_abort_notification_waits(&mld->notif_wait);
+
+	iwl_fw_dbg_stop_sync(&mld->fwrt);
+
+	iwl_trans_stop_device(mld->trans);
+
+	mld->fw_status.running = false;
+}
+
+static void iwl_mld_restart_disconnect_iter(void *data, u8 *mac,
+					    struct ieee80211_vif *vif)
+{
+	if (vif->type == NL80211_IFTYPE_STATION)
+		ieee80211_hw_restart_disconnect(vif);
+}
+
+void iwl_mld_send_recovery_cmd(struct iwl_mld *mld, u32 flags)
+{
+	u32 error_log_size = mld->fw->ucode_capa.error_log_size;
+	struct iwl_fw_error_recovery_cmd recovery_cmd = {
+		.flags = cpu_to_le32(flags),
+	};
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(SYSTEM_GROUP, FW_ERROR_RECOVERY_CMD),
+		.flags = CMD_WANT_SKB,
+		.data = {&recovery_cmd, },
+		.len = {sizeof(recovery_cmd), },
+	};
+	int ret;
+
+	/* no error log was defined in TLV */
+	if (!error_log_size)
+		return;
+
+	if (flags & ERROR_RECOVERY_UPDATE_DB) {
+		/* no buf was allocated upon NIC error */
+		if (!mld->error_recovery_buf)
+			return;
+
+		cmd.data[1] = mld->error_recovery_buf;
+		cmd.len[1] =  error_log_size;
+		cmd.dataflags[1] = IWL_HCMD_DFL_NOCOPY;
+		recovery_cmd.buf_size = cpu_to_le32(error_log_size);
+	}
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+
+	/* we no longer need the recovery buffer */
+	kfree(mld->error_recovery_buf);
+	mld->error_recovery_buf = NULL;
+
+	if (ret) {
+		IWL_ERR(mld, "Failed to send recovery cmd %d\n", ret);
+		return;
+	}
+
+	if (flags & ERROR_RECOVERY_UPDATE_DB) {
+		struct iwl_rx_packet *pkt = cmd.resp_pkt;
+		u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+		u32 resp;
+
+		if (IWL_FW_CHECK(mld, pkt_len != sizeof(resp),
+				 "Unexpected recovery cmd response size %u (expected %zu)\n",
+				 pkt_len, sizeof(resp)))
+			goto out;
+
+		resp = le32_to_cpup((__le32 *)cmd.resp_pkt->data);
+		if (!resp)
+			goto out;
+
+		IWL_ERR(mld,
+			"Failed to send recovery cmd blob was invalid %d\n",
+			resp);
+
+		ieee80211_iterate_interfaces(mld->hw, 0,
+					     iwl_mld_restart_disconnect_iter,
+					     NULL);
+	}
+
+out:
+	iwl_free_resp(&cmd);
+}
+
+static int iwl_mld_config_fw(struct iwl_mld *mld)
+{
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	iwl_fw_disable_dbg_asserts(&mld->fwrt);
+	iwl_get_shared_mem_conf(&mld->fwrt);
+
+	ret = iwl_mld_send_tx_ant_cfg(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_send_bt_init_conf(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_set_soc_latency(&mld->fwrt);
+	if (ret)
+		return ret;
+
+	iwl_mld_configure_lari(mld);
+
+	ret = iwl_mld_config_temp_report_ths(mld);
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_THERMAL
+	ret = iwl_mld_config_ctdp(mld, mld->cooling_dev.cur_state,
+				  CTDP_CMD_OPERATION_START);
+	if (ret)
+		return ret;
+#endif
+
+	ret = iwl_configure_rxq(&mld->fwrt);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_send_rss_cfg_cmd(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_config_scan(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_update_device_power(mld, false);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_init_mcc(mld);
+	if (ret)
+		return ret;
+
+	if (mld->fw_status.in_hw_restart) {
+		iwl_mld_send_recovery_cmd(mld, ERROR_RECOVERY_UPDATE_DB);
+		iwl_mld_time_sync_fw_config(mld);
+	}
+
+	iwl_mld_led_config_fw(mld);
+
+	ret = iwl_mld_init_ppag(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_init_sar(mld);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_init_sgom(mld);
+	if (ret)
+		return ret;
+
+	iwl_mld_init_tas(mld);
+	iwl_mld_init_uats(mld);
+
+	return 0;
+}
+
+int iwl_mld_start_fw(struct iwl_mld *mld)
+{
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_load_fw(mld);
+	if (IWL_FW_CHECK(mld, ret, "Failed to start firmware %d\n", ret)) {
+		iwl_fw_dbg_error_collect(&mld->fwrt, FW_DBG_TRIGGER_DRIVER);
+		goto error;
+	}
+
+	IWL_DEBUG_INFO(mld, "uCode started.\n");
+
+	ret = iwl_mld_config_fw(mld);
+	if (ret)
+		goto error;
+
+	return 0;
+
+error:
+	iwl_mld_stop_fw(mld);
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h b/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
new file mode 100644
index 0000000000000..773bc1b093921
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_hcmd_h__
+#define __iwl_mld_hcmd_h__
+
+static inline int iwl_mld_send_cmd(struct iwl_mld *mld, struct iwl_host_cmd *cmd)
+{
+	/* No commands, including the d3 related commands, should be sent
+	 * after entering d3
+	 */
+	if (WARN_ON(mld->fw_status.in_d3))
+		return -EIO;
+
+	if (!(cmd->flags & CMD_ASYNC))
+		lockdep_assert_wiphy(mld->wiphy);
+
+	/* Devices that need to shutdown immediately on rfkill are not
+	 * supported, so we can send all the cmds in rfkill
+	 */
+	cmd->flags |= CMD_SEND_IN_RFKILL;
+
+	return iwl_trans_send_cmd(mld->trans, cmd);
+}
+
+static inline int
+__iwl_mld_send_cmd_with_flags_pdu(struct iwl_mld *mld, u32 id,
+				  u32 flags, const void *data, u16 len)
+{
+	struct iwl_host_cmd cmd = {
+		.id = id,
+		.len = { data ? len : 0, },
+		.data = { data, },
+		.flags = flags,
+	};
+
+	return iwl_mld_send_cmd(mld, &cmd);
+}
+
+#define _iwl_mld_send_cmd_with_flags_pdu(mld, id, flags, data, len,	\
+					 ignored...)			\
+	__iwl_mld_send_cmd_with_flags_pdu(mld, id, flags, data, len)
+#define iwl_mld_send_cmd_with_flags_pdu(mld, id, flags, data, len...)	\
+	_iwl_mld_send_cmd_with_flags_pdu(mld, id, flags, data, ##len,	\
+					 sizeof(*(data)))
+
+#define iwl_mld_send_cmd_pdu(mld, id, ...)				\
+	iwl_mld_send_cmd_with_flags_pdu(mld, id, 0, __VA_ARGS__)
+
+#define iwl_mld_send_cmd_empty(mld, id)					\
+	iwl_mld_send_cmd_with_flags_pdu(mld, id, 0, NULL, 0)
+
+#endif /* __iwl_mld_hcmd_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
new file mode 100644
index 0000000000000..691062b444619
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
@@ -0,0 +1,671 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include <net/cfg80211.h>
+
+#include "iface.h"
+#include "hcmd.h"
+#include "key.h"
+#include "mlo.h"
+#include "mac80211.h"
+
+#include "fw/api/context.h"
+#include "fw/api/mac.h"
+#include "fw/api/time-event.h"
+#include "fw/api/datapath.h"
+
+/* Cleanup function for struct iwl_mld_vif, will be called in restart */
+void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = mld_vif->mld;
+	struct iwl_mld_link *link;
+
+	/* EMLSR is turned back on during recovery */
+	vif->driver_flags &= ~IEEE80211_VIF_EML_ACTIVE;
+
+	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
+
+	for_each_mld_vif_valid_link(mld_vif, link) {
+		iwl_mld_cleanup_link(mld_vif->mld, link);
+
+		/* Correctly allocated primary link in non-MLO mode */
+		if (!ieee80211_vif_is_mld(vif) &&
+		    link_id == 0 && link == &mld_vif->deflink)
+			continue;
+
+		if (vif->active_links & BIT(link_id))
+			continue;
+
+		/* Should not happen as link removal should always succeed */
+		WARN_ON(1);
+		if (link != &mld_vif->deflink)
+			kfree_rcu(link, rcu_head);
+		RCU_INIT_POINTER(mld_vif->link[link_id], NULL);
+	}
+
+	ieee80211_iter_keys(mld->hw, vif, iwl_mld_cleanup_keys_iter, NULL);
+
+	CLEANUP_STRUCT(mld_vif);
+}
+
+static int iwl_mld_send_mac_cmd(struct iwl_mld *mld,
+				struct iwl_mac_config_cmd *cmd)
+{
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(MAC_CONF_GROUP, MAC_CONFIG_CMD),
+				   cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to send MAC_CONFIG_CMD ret = %d\n", ret);
+
+	return ret;
+}
+
+int iwl_mld_mac80211_iftype_to_fw(const struct ieee80211_vif *vif)
+{
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		return vif->p2p ? FW_MAC_TYPE_P2P_STA : FW_MAC_TYPE_BSS_STA;
+	case NL80211_IFTYPE_AP:
+		return FW_MAC_TYPE_GO;
+	case NL80211_IFTYPE_MONITOR:
+		return FW_MAC_TYPE_LISTENER;
+	case NL80211_IFTYPE_P2P_DEVICE:
+		return FW_MAC_TYPE_P2P_DEVICE;
+	case NL80211_IFTYPE_ADHOC:
+		return FW_MAC_TYPE_IBSS;
+	default:
+		WARN_ON_ONCE(1);
+	}
+	return FW_MAC_TYPE_BSS_STA;
+}
+
+static bool iwl_mld_is_nic_ack_enabled(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif)
+{
+	const struct ieee80211_supported_band *sband;
+	const struct ieee80211_sta_he_cap *own_he_cap;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* This capability is the same for all bands,
+	 * so take it from one of them.
+	 */
+	sband = mld->hw->wiphy->bands[NL80211_BAND_2GHZ];
+	own_he_cap = ieee80211_get_he_iftype_cap_vif(sband, vif);
+
+	return own_he_cap && (own_he_cap->he_cap_elem.mac_cap_info[2] &
+			       IEEE80211_HE_MAC_CAP2_ACK_EN);
+}
+
+/* fill the common part for all interface types */
+static void iwl_mld_mac_cmd_fill_common(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct iwl_mac_config_cmd *cmd,
+					u32 action)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_bss_conf *link_conf;
+	unsigned int link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	cmd->id_and_color = cpu_to_le32(mld_vif->fw_id);
+	cmd->action = cpu_to_le32(action);
+
+	cmd->mac_type =
+		cpu_to_le32(iwl_mld_mac80211_iftype_to_fw(vif));
+
+	memcpy(cmd->local_mld_addr, vif->addr, ETH_ALEN);
+
+	if (iwlwifi_mod_params.disable_11ax)
+		return;
+
+	cmd->nic_not_ack_enabled =
+		cpu_to_le32(!iwl_mld_is_nic_ack_enabled(mld, vif));
+
+	/* If we have MLO enabled, then the firmware needs to enable
+	 * address translation for the station(s) we add. That depends
+	 * on having EHT enabled in firmware, which in turn depends on
+	 * mac80211 in the code below.
+	 * However, mac80211 doesn't enable HE/EHT until it has parsed
+	 * the association response successfully, so just skip all that
+	 * and enable both when we have MLO.
+	 */
+	if (ieee80211_vif_is_mld(vif)) {
+		if (vif->type == NL80211_IFTYPE_AP)
+			cmd->he_ap_support = cpu_to_le16(1);
+		else
+			cmd->he_support = cpu_to_le16(1);
+
+		cmd->eht_support = cpu_to_le32(1);
+		return;
+	}
+
+	for_each_vif_active_link(vif, link_conf, link_id) {
+		if (!link_conf->he_support)
+			continue;
+
+		if (vif->type == NL80211_IFTYPE_AP)
+			cmd->he_ap_support = cpu_to_le16(1);
+		else
+			cmd->he_support = cpu_to_le16(1);
+
+		/* EHT, if supported, was already set above */
+		break;
+	}
+}
+
+static void iwl_mld_fill_mac_cmd_sta(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif, u32 action,
+				     struct iwl_mac_config_cmd *cmd)
+{
+	struct ieee80211_bss_conf *link;
+	u32 twt_policy = 0;
+	int link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	WARN_ON(vif->type != NL80211_IFTYPE_STATION);
+
+	/* We always want to hear MCAST frames, if we're not authorized yet,
+	 * we'll drop them.
+	 */
+	cmd->filter_flags |= cpu_to_le32(MAC_CFG_FILTER_ACCEPT_GRP);
+
+	/* Adding a MAC ctxt with is_assoc set is not allowed in fw
+	 * (and shouldn't happen)
+	 */
+	if (vif->cfg.assoc && action != FW_CTXT_ACTION_ADD) {
+		cmd->client.is_assoc = 1;
+
+		if (!iwl_mld_vif_from_mac80211(vif)->authorized)
+			cmd->client.data_policy |=
+				cpu_to_le16(COEX_HIGH_PRIORITY_ENABLE);
+	} else {
+		/* Allow beacons to pass through as long as we are not
+		 * associated
+		 */
+		cmd->filter_flags |= cpu_to_le32(MAC_CFG_FILTER_ACCEPT_BEACON);
+	}
+
+	cmd->client.assoc_id = cpu_to_le16(vif->cfg.aid);
+
+	if (ieee80211_vif_is_mld(vif)) {
+		u16 esr_transition_timeout =
+			u16_get_bits(vif->cfg.eml_cap,
+				     IEEE80211_EML_CAP_TRANSITION_TIMEOUT);
+
+		cmd->client.esr_transition_timeout =
+			min_t(u16, IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU,
+			      esr_transition_timeout);
+		cmd->client.medium_sync_delay =
+			cpu_to_le16(vif->cfg.eml_med_sync_delay);
+	}
+
+	for_each_vif_active_link(vif, link, link_id) {
+		if (!link->he_support)
+			continue;
+
+		if (link->twt_requester)
+			twt_policy |= TWT_SUPPORTED;
+		if (link->twt_protected)
+			twt_policy |= PROTECTED_TWT_SUPPORTED;
+		if (link->twt_broadcast)
+			twt_policy |= BROADCAST_TWT_SUPPORTED;
+	}
+
+	if (!iwlwifi_mod_params.disable_11ax)
+		cmd->client.data_policy |= cpu_to_le16(twt_policy);
+
+	if (vif->probe_req_reg && vif->cfg.assoc && vif->p2p)
+		cmd->filter_flags |=
+			cpu_to_le32(MAC_CFG_FILTER_ACCEPT_PROBE_REQ);
+
+	if (vif->p2p)
+		cmd->client.ctwin =
+			cpu_to_le32(vif->bss_conf.p2p_noa_attr.oppps_ctwindow &
+				    IEEE80211_P2P_OPPPS_CTWINDOW_MASK);
+}
+
+static void iwl_mld_fill_mac_cmd_ap(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif,
+				    struct iwl_mac_config_cmd *cmd)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	WARN_ON(vif->type != NL80211_IFTYPE_AP);
+
+	cmd->filter_flags |= cpu_to_le32(MAC_CFG_FILTER_ACCEPT_PROBE_REQ);
+
+	/* in AP mode, pass beacons from other APs (needed for ht protection).
+	 * When there're no any associated station, which means that we are not
+	 * TXing anyway, don't ask FW to pass beacons to prevent unnecessary
+	 * wake-ups.
+	 */
+	if (mld_vif->num_associated_stas)
+		cmd->filter_flags |= cpu_to_le32(MAC_CFG_FILTER_ACCEPT_BEACON);
+}
+
+static void iwl_mld_go_iterator(void *_data, u8 *mac, struct ieee80211_vif *vif)
+{
+	bool *go_active = _data;
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_P2P_GO &&
+	    iwl_mld_vif_from_mac80211(vif)->ap_ibss_active)
+		*go_active = true;
+}
+
+static bool iwl_mld_p2p_dev_has_extended_disc(struct iwl_mld *mld)
+{
+	bool go_active = false;
+
+	/* This flag should be set to true when the P2P Device is
+	 * discoverable and there is at least a P2P GO. Setting
+	 * this flag will allow the P2P Device to be discoverable on other
+	 * channels in addition to its listen channel.
+	 * Note that this flag should not be set in other cases as it opens the
+	 * Rx filters on all MAC and increases the number of interrupts.
+	 */
+	ieee80211_iterate_active_interfaces(mld->hw,
+					    IEEE80211_IFACE_ITER_RESUME_ALL,
+					    iwl_mld_go_iterator, &go_active);
+
+	return go_active;
+}
+
+static void iwl_mld_fill_mac_cmd_p2p_dev(struct iwl_mld *mld,
+					 struct ieee80211_vif *vif,
+					 struct iwl_mac_config_cmd *cmd)
+{
+	bool ext_disc = iwl_mld_p2p_dev_has_extended_disc(mld);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* Override the filter flags to accept all management frames. This is
+	 * needed to support both P2P device discovery using probe requests and
+	 * P2P service discovery using action frames
+	 */
+	cmd->filter_flags = cpu_to_le32(MAC_CFG_FILTER_ACCEPT_CONTROL_AND_MGMT);
+
+	if (ext_disc)
+		cmd->p2p_dev.is_disc_extended = cpu_to_le32(1);
+}
+
+static void iwl_mld_fill_mac_cmd_ibss(struct iwl_mld *mld,
+				      struct ieee80211_vif *vif,
+				      struct iwl_mac_config_cmd *cmd)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	WARN_ON(vif->type != NL80211_IFTYPE_ADHOC);
+
+	cmd->filter_flags |= cpu_to_le32(MAC_CFG_FILTER_ACCEPT_BEACON |
+					 MAC_CFG_FILTER_ACCEPT_PROBE_REQ |
+					 MAC_CFG_FILTER_ACCEPT_GRP);
+}
+
+static int
+iwl_mld_rm_mac_from_fw(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mac_config_cmd cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+		.id_and_color = cpu_to_le32(mld_vif->fw_id),
+	};
+
+	return iwl_mld_send_mac_cmd(mld, &cmd);
+}
+
+int iwl_mld_mac_fw_action(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			  u32 action)
+{
+	struct iwl_mac_config_cmd cmd = {};
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (action == FW_CTXT_ACTION_REMOVE)
+		return iwl_mld_rm_mac_from_fw(mld, vif);
+
+	iwl_mld_mac_cmd_fill_common(mld, vif, &cmd, action);
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		iwl_mld_fill_mac_cmd_sta(mld, vif, action, &cmd);
+		break;
+	case NL80211_IFTYPE_AP:
+		iwl_mld_fill_mac_cmd_ap(mld, vif, &cmd);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+		cmd.filter_flags =
+			cpu_to_le32(MAC_CFG_FILTER_PROMISC |
+				    MAC_CFG_FILTER_ACCEPT_CONTROL_AND_MGMT |
+				    MAC_CFG_FILTER_ACCEPT_BEACON |
+				    MAC_CFG_FILTER_ACCEPT_PROBE_REQ |
+				    MAC_CFG_FILTER_ACCEPT_GRP);
+		break;
+	case NL80211_IFTYPE_P2P_DEVICE:
+		iwl_mld_fill_mac_cmd_p2p_dev(mld, vif, &cmd);
+		break;
+	case NL80211_IFTYPE_ADHOC:
+		iwl_mld_fill_mac_cmd_ibss(mld, vif, &cmd);
+		break;
+	default:
+		WARN(1, "not supported yet\n");
+		return -EOPNOTSUPP;
+	}
+
+	return iwl_mld_send_mac_cmd(mld, &cmd);
+}
+
+IWL_MLD_ALLOC_FN(vif, vif)
+
+/* Constructor function for struct iwl_mld_vif */
+static int
+iwl_mld_init_vif(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	mld_vif->mld = mld;
+	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
+
+	ret = iwl_mld_allocate_vif_fw_id(mld, &mld_vif->fw_id, vif);
+	if (ret)
+		return ret;
+
+	if (!mld->fw_status.in_hw_restart) {
+		wiphy_work_init(&mld_vif->emlsr.unblock_tpt_wk,
+				iwl_mld_emlsr_unblock_tpt_wk);
+		wiphy_delayed_work_init(&mld_vif->emlsr.check_tpt_wk,
+					iwl_mld_emlsr_check_tpt);
+		wiphy_delayed_work_init(&mld_vif->emlsr.prevent_done_wk,
+					iwl_mld_emlsr_prevent_done_wk);
+		wiphy_delayed_work_init(&mld_vif->emlsr.tmp_non_bss_done_wk,
+					iwl_mld_emlsr_tmp_non_bss_done_wk);
+	}
+
+	return 0;
+}
+
+int iwl_mld_add_vif(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_init_vif(mld, vif);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_ADD);
+	if (ret)
+		RCU_INIT_POINTER(mld->fw_id_to_vif[mld_vif->fw_id], NULL);
+
+	return ret;
+}
+
+int iwl_mld_rm_vif(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_REMOVE);
+
+	if (WARN_ON(mld_vif->fw_id >= ARRAY_SIZE(mld->fw_id_to_vif)))
+		return -EINVAL;
+
+	RCU_INIT_POINTER(mld->fw_id_to_vif[mld_vif->fw_id], NULL);
+
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_VIF,
+					       mld_vif->fw_id);
+
+	return ret;
+}
+
+void iwl_mld_set_vif_associated(struct iwl_mld *mld,
+				struct ieee80211_vif *vif)
+{
+	struct ieee80211_bss_conf *link;
+	unsigned int link_id;
+
+	for_each_vif_active_link(vif, link, link_id) {
+		if (iwl_mld_link_set_associated(mld, vif, link))
+			IWL_ERR(mld, "failed to update link %d\n", link_id);
+	}
+
+	iwl_mld_recalc_multicast_filter(mld);
+}
+
+static void iwl_mld_get_fw_id_bss_bitmap_iter(void *_data, u8 *mac,
+					      struct ieee80211_vif *vif)
+{
+	u8 *fw_id_bitmap = _data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION)
+		return;
+
+	*fw_id_bitmap |= BIT(mld_vif->fw_id);
+}
+
+u8 iwl_mld_get_fw_bss_vifs_ids(struct iwl_mld *mld)
+{
+	u8 fw_id_bitmap = 0;
+
+	ieee80211_iterate_interfaces(mld->hw,
+				     IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER,
+				     iwl_mld_get_fw_id_bss_bitmap_iter,
+				     &fw_id_bitmap);
+
+	return fw_id_bitmap;
+}
+
+void iwl_mld_handle_probe_resp_data_notif(struct iwl_mld *mld,
+					  struct iwl_rx_packet *pkt)
+{
+	const struct iwl_probe_resp_data_notif *notif = (void *)pkt->data;
+	struct iwl_probe_resp_data *old_data, *new_data;
+	struct ieee80211_vif *vif;
+	struct iwl_mld_link *mld_link;
+
+	IWL_DEBUG_INFO(mld, "Probe response data notif: noa %d, csa %d\n",
+		       notif->noa_active, notif->csa_counter);
+
+	if (IWL_FW_CHECK(mld, le32_to_cpu(notif->mac_id) >=
+			 ARRAY_SIZE(mld->fw_id_to_vif),
+			 "mac id is invalid: %d\n",
+			 le32_to_cpu(notif->mac_id)))
+		return;
+
+	vif = wiphy_dereference(mld->wiphy,
+				mld->fw_id_to_vif[le32_to_cpu(notif->mac_id)]);
+
+	/* the firmware gives us the mac_id (and not the link_id), mac80211
+	 * gets a vif and not a link, bottom line, this flow is not MLD ready
+	 * yet.
+	 */
+	if (WARN_ON(!vif) || ieee80211_vif_is_mld(vif))
+		return;
+
+	if (notif->csa_counter != IWL_PROBE_RESP_DATA_NO_CSA &&
+	    notif->csa_counter >= 1)
+		ieee80211_beacon_set_cntdwn(vif, notif->csa_counter);
+
+	if (!vif->p2p)
+		return;
+
+	mld_link = &iwl_mld_vif_from_mac80211(vif)->deflink;
+
+	new_data = kzalloc(sizeof(*new_data), GFP_KERNEL);
+	if (!new_data)
+		return;
+
+	memcpy(&new_data->notif, notif, sizeof(new_data->notif));
+
+	/* noa_attr contains 1 reserved byte, need to substruct it */
+	new_data->noa_len = sizeof(struct ieee80211_vendor_ie) +
+			    sizeof(new_data->notif.noa_attr) - 1;
+
+	/*
+	 * If it's a one time NoA, only one descriptor is needed,
+	 * adjust the length according to len_low.
+	 */
+	if (new_data->notif.noa_attr.len_low ==
+	    sizeof(struct ieee80211_p2p_noa_desc) + 2)
+		new_data->noa_len -= sizeof(struct ieee80211_p2p_noa_desc);
+
+	old_data = wiphy_dereference(mld->wiphy, mld_link->probe_resp_data);
+	rcu_assign_pointer(mld_link->probe_resp_data, new_data);
+
+	if (old_data)
+		kfree_rcu(old_data, rcu_head);
+}
+
+void iwl_mld_handle_uapsd_misbehaving_ap_notif(struct iwl_mld *mld,
+					       struct iwl_rx_packet *pkt)
+{
+	struct iwl_uapsd_misbehaving_ap_notif *notif = (void *)pkt->data;
+	struct ieee80211_vif *vif;
+
+	if (IWL_FW_CHECK(mld, notif->mac_id >= ARRAY_SIZE(mld->fw_id_to_vif),
+			 "mac id is invalid: %d\n", notif->mac_id))
+		return;
+
+	vif = wiphy_dereference(mld->wiphy, mld->fw_id_to_vif[notif->mac_id]);
+
+	if (WARN_ON(!vif) || ieee80211_vif_is_mld(vif))
+		return;
+
+	IWL_WARN(mld, "uapsd misbehaving AP: %pM\n", vif->bss_conf.bssid);
+}
+
+void iwl_mld_handle_datapath_monitor_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt)
+{
+	struct iwl_datapath_monitor_notif *notif = (void *)pkt->data;
+	struct ieee80211_bss_conf *link;
+	struct ieee80211_supported_band *sband;
+	const struct ieee80211_sta_he_cap *he_cap;
+	struct ieee80211_vif *vif;
+	struct iwl_mld_vif *mld_vif;
+
+	if (notif->type != cpu_to_le32(IWL_DP_MON_NOTIF_TYPE_EXT_CCA))
+		return;
+
+	link = iwl_mld_fw_id_to_link_conf(mld, notif->link_id);
+	if (WARN_ON(!link))
+		return;
+
+	vif = link->vif;
+	if (WARN_ON(!vif) || vif->type != NL80211_IFTYPE_STATION ||
+	    !vif->cfg.assoc)
+		return;
+
+	if (!link->chanreq.oper.chan ||
+	    link->chanreq.oper.chan->band != NL80211_BAND_2GHZ ||
+	    link->chanreq.oper.width < NL80211_CHAN_WIDTH_40)
+		return;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	/* this shouldn't happen *again*, ignore it */
+	if (mld_vif->cca_40mhz_workaround != CCA_40_MHZ_WA_NONE)
+		return;
+
+	mld_vif->cca_40mhz_workaround = CCA_40_MHZ_WA_RECONNECT;
+
+	/*
+	 * This capability manipulation isn't really ideal, but it's the
+	 * easiest choice - otherwise we'd have to do some major changes
+	 * in mac80211 to support this, which isn't worth it. This does
+	 * mean that userspace may have outdated information, but that's
+	 * actually not an issue at all.
+	 */
+	sband = mld->wiphy->bands[NL80211_BAND_2GHZ];
+
+	WARN_ON(!sband->ht_cap.ht_supported);
+	WARN_ON(!(sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40));
+	sband->ht_cap.cap &= ~IEEE80211_HT_CAP_SUP_WIDTH_20_40;
+
+	he_cap = ieee80211_get_he_iftype_cap_vif(sband, vif);
+
+	if (he_cap) {
+		/* we know that ours is writable */
+		struct ieee80211_sta_he_cap *he = (void *)(uintptr_t)he_cap;
+
+		WARN_ON(!he->has_he);
+		WARN_ON(!(he->he_cap_elem.phy_cap_info[0] &
+			  IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G));
+		he->he_cap_elem.phy_cap_info[0] &=
+			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G;
+	}
+
+	ieee80211_disconnect(vif, true);
+}
+
+void iwl_mld_reset_cca_40mhz_workaround(struct iwl_mld *mld,
+					struct ieee80211_vif *vif)
+{
+	struct ieee80211_supported_band *sband;
+	const struct ieee80211_sta_he_cap *he_cap;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	if (mld_vif->cca_40mhz_workaround == CCA_40_MHZ_WA_NONE)
+		return;
+
+	/* Now we are just reconnecting with the new capabilities,
+	 * but remember to reset the capabilities when we disconnect for real
+	 */
+	if (mld_vif->cca_40mhz_workaround == CCA_40_MHZ_WA_RECONNECT) {
+		mld_vif->cca_40mhz_workaround = CCA_40_MHZ_WA_RESET;
+		return;
+	}
+
+	/* Now cca_40mhz_workaround == CCA_40_MHZ_WA_RESET */
+
+	sband = mld->wiphy->bands[NL80211_BAND_2GHZ];
+
+	sband->ht_cap.cap |= IEEE80211_HT_CAP_SUP_WIDTH_20_40;
+
+	he_cap = ieee80211_get_he_iftype_cap_vif(sband, vif);
+
+	if (he_cap) {
+		/* we know that ours is writable */
+		struct ieee80211_sta_he_cap *he = (void *)(uintptr_t)he_cap;
+
+		he->he_cap_elem.phy_cap_info[0] |=
+			IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G;
+	}
+
+	mld_vif->cca_40mhz_workaround = CCA_40_MHZ_WA_NONE;
+}
+
+struct ieee80211_vif *iwl_mld_get_bss_vif(struct iwl_mld *mld)
+{
+	unsigned long fw_id_bitmap = iwl_mld_get_fw_bss_vifs_ids(mld);
+	int fw_id;
+
+	if (hweight8(fw_id_bitmap) != 1)
+		return NULL;
+
+	fw_id = __ffs(fw_id_bitmap);
+
+	return wiphy_dereference(mld->wiphy,
+				 mld->fw_id_to_vif[fw_id]);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
new file mode 100644
index 0000000000000..2c928113f6802
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_iface_h__
+#define __iwl_mld_iface_h__
+
+#include <net/mac80211.h>
+
+#include "link.h"
+#include "session-protect.h"
+#include "d3.h"
+
+enum iwl_mld_cca_40mhz_wa_status {
+	CCA_40_MHZ_WA_NONE,
+	CCA_40_MHZ_WA_RESET,
+	CCA_40_MHZ_WA_RECONNECT,
+};
+
+/**
+ * enum iwl_mld_emlsr_blocked - defines reasons for which EMLSR is blocked
+ *
+ * These blocks are applied/stored per-VIF.
+ *
+ * @IWL_MLD_EMLSR_BLOCKED_PREVENTION: Prevent repeated EMLSR enter/exit
+ * @IWL_MLD_EMLSR_BLOCKED_WOWLAN: WOWLAN is preventing EMLSR
+ * @IWL_MLD_EMLSR_BLOCKED_FW: FW did not recommend MLO
+ * @IWL_MLD_EMLSR_BLOCKED_ROC: remain-on-channel is preventing EMLSR
+ * @IWL_MLD_EMLSR_BLOCKED_NON_BSS: An active non-BSS interface's link is
+ *      preventing EMLSR
+ * @IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS: An expected active non-BSS interface's
+ *      link is preventing EMLSR. This is a temporary blocking that is set when
+ *      there is an indication that a non-BSS interface is to be added.
+ * @IWL_MLD_EMLSR_BLOCKED_TPT: throughput is too low to make EMLSR worthwhile
+ */
+enum iwl_mld_emlsr_blocked {
+	IWL_MLD_EMLSR_BLOCKED_PREVENTION	= 0x1,
+	IWL_MLD_EMLSR_BLOCKED_WOWLAN		= 0x2,
+	IWL_MLD_EMLSR_BLOCKED_FW		= 0x4,
+	IWL_MLD_EMLSR_BLOCKED_ROC		= 0x8,
+	IWL_MLD_EMLSR_BLOCKED_NON_BSS		= 0x10,
+	IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS	= 0x20,
+	IWL_MLD_EMLSR_BLOCKED_TPT		= 0x40,
+};
+
+/**
+ * enum iwl_mld_emlsr_exit - defines reasons for exiting EMLSR
+ *
+ * Reasons to exit EMLSR may be either link specific or even specific to a
+ * combination of links.
+ *
+ * @IWL_MLD_EMLSR_EXIT_BLOCK: Exit due to a block reason being set
+ * @IWL_MLD_EMLSR_EXIT_MISSED_BEACON: Exit due to missed beacons
+ * @IWL_MLD_EMLSR_EXIT_FAIL_ENTRY: FW failed to enter EMLSR
+ * @IWL_MLD_EMLSR_EXIT_CSA: EMLSR prevented due to channel switch on link
+ * @IWL_MLD_EMLSR_EXIT_EQUAL_BAND: EMLSR prevented as both links share the band
+ * @IWL_MLD_EMLSR_EXIT_BANDWIDTH: Bandwidths of primary and secondary links are
+ *      not equal
+ * @IWL_MLD_EMLSR_EXIT_LOW_RSSI: Link RSSI is unsuitable for EMLSR
+ * @IWL_MLD_EMLSR_EXIT_LINK_USAGE: Exit EMLSR due to low TPT on secondary link
+ * @IWL_MLD_EMLSR_EXIT_BT_COEX: Exit EMLSR due to BT coexistence
+ * @IWL_MLD_EMLSR_EXIT_CHAN_LOAD: Exit EMLSR because the primary channel is not
+ *	loaded enough to justify EMLSR.
+ * @IWL_MLD_EMLSR_EXIT_RFI: Exit EMLSR due to RFI
+ */
+enum iwl_mld_emlsr_exit {
+	IWL_MLD_EMLSR_EXIT_BLOCK		= 0x1,
+	IWL_MLD_EMLSR_EXIT_MISSED_BEACON	= 0x2,
+	IWL_MLD_EMLSR_EXIT_FAIL_ENTRY		= 0x4,
+	IWL_MLD_EMLSR_EXIT_CSA			= 0x8,
+	IWL_MLD_EMLSR_EXIT_EQUAL_BAND		= 0x10,
+	IWL_MLD_EMLSR_EXIT_BANDWIDTH		= 0x20,
+	IWL_MLD_EMLSR_EXIT_LOW_RSSI		= 0x40,
+	IWL_MLD_EMLSR_EXIT_LINK_USAGE		= 0x80,
+	IWL_MLD_EMLSR_EXIT_BT_COEX		= 0x100,
+	IWL_MLD_EMLSR_EXIT_CHAN_LOAD		= 0x200,
+	IWL_MLD_EMLSR_EXIT_RFI			= 0x400,
+};
+
+/**
+ * struct iwl_mld_emlsr - per-VIF data about EMLSR operation
+ *
+ * @primary: The current primary link
+ * @selected_primary: Primary link as selected during the last link selection
+ * @selected_links: Links as selected during the last link selection
+ * @blocked_reasons: Reasons preventing EMLSR from being enabled
+ * @last_exit_reason: Reason for the last EMLSR exit
+ * @last_exit_ts: Time of the last EMLSR exit (if @last_exit_reason is non-zero)
+ * @exit_repeat_count: Number of times EMLSR was exited for the same reason
+ * @unblock_tpt_wk: Unblock EMLSR because the throughput limit was reached
+ * @check_tpt_wk: a worker to check if IWL_MLD_EMLSR_BLOCKED_TPT should be
+ *	added, for example if there is no longer enough traffic.
+ * @prevent_done_wk: Worker to remove %IWL_MLD_EMLSR_BLOCKED_PREVENTION
+ * @tmp_non_bss_done_wk: Worker to remove %IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS
+ */
+struct iwl_mld_emlsr {
+	struct_group(zeroed_on_not_authorized,
+		u8 primary;
+
+		u8 selected_primary;
+		u16 selected_links;
+
+		enum iwl_mld_emlsr_blocked blocked_reasons;
+
+		enum iwl_mld_emlsr_exit last_exit_reason;
+		unsigned long last_exit_ts;
+		u8 exit_repeat_count;
+	);
+
+	struct wiphy_work unblock_tpt_wk;
+	struct wiphy_delayed_work check_tpt_wk;
+
+	struct wiphy_delayed_work prevent_done_wk;
+	struct wiphy_delayed_work tmp_non_bss_done_wk;
+};
+
+/**
+ * struct iwl_mld_vif - virtual interface (MAC context) configuration parameters
+ *
+ * @fw_id: fw id of the mac context.
+ * @session_protect: session protection parameters
+ * @ap_sta: pointer to AP sta, for easier access to it.
+ *	Relevant only for STA vifs.
+ * @authorized: indicates the AP station was set to authorized
+ * @bigtks: BIGTKs of the AP, for beacon protection.
+ *	Only valid for STA. (FIXME: needs to be per link)
+ * @num_associated_stas: number of associated STAs. Relevant only for AP mode.
+ * @ap_ibss_active: whether the AP/IBSS was started
+ * @roc_activity: the id of the roc_activity running. Relevant for p2p device
+ *	only. Set to %ROC_NUM_ACTIVITIES when not in use.
+ * @cca_40mhz_workaround: When we are connected in 2.4 GHz and 40 MHz, and the
+ *	environment is too loaded, we work around this by reconnecting to the
+ *	same AP with 20 MHz. This manages the status of the workaround.
+ * @beacon_inject_active: indicates an active debugfs beacon ie injection
+ * @low_latency_causes: bit flags, indicating the causes for low-latency,
+ *	see @iwl_mld_low_latency_cause.
+ * @mld: pointer to the mld structure.
+ * @deflink: default link data, for use in non-MLO,
+ * @link: reference to link data for each valid link, for use in MLO.
+ * @emlsr: information related to EMLSR
+ * @wowlan_data: data used by the wowlan suspend flow
+ * @use_ps_poll: use ps_poll frames
+ * @disable_bf: disable beacon filter
+ * @dbgfs_slink: debugfs symlink for this interface
+ */
+struct iwl_mld_vif {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		u8 fw_id;
+		struct iwl_mld_session_protect session_protect;
+		struct ieee80211_sta *ap_sta;
+		bool authorized;
+		struct ieee80211_key_conf __rcu *bigtks[2];
+		u8 num_associated_stas;
+		bool ap_ibss_active;
+		u32 roc_activity;
+		enum iwl_mld_cca_40mhz_wa_status cca_40mhz_workaround;
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+		bool beacon_inject_active;
+#endif
+		u8 low_latency_causes;
+	);
+	/* And here fields that survive a fw restart */
+	struct iwl_mld *mld;
+	struct iwl_mld_link deflink;
+	struct iwl_mld_link __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
+
+	struct iwl_mld_emlsr emlsr;
+
+#if CONFIG_PM_SLEEP
+	struct iwl_mld_wowlan_data wowlan_data;
+#endif
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	bool use_ps_poll;
+	bool disable_bf;
+	struct dentry *dbgfs_slink;
+#endif
+};
+
+static inline struct iwl_mld_vif *
+iwl_mld_vif_from_mac80211(struct ieee80211_vif *vif)
+{
+	return (void *)vif->drv_priv;
+}
+
+#define iwl_mld_link_dereference_check(mld_vif, link_id)		\
+	rcu_dereference_check((mld_vif)->link[link_id],			\
+			      lockdep_is_held(&mld_vif->mld->wiphy->mtx))
+
+#define for_each_mld_vif_valid_link(mld_vif, mld_link)			\
+	for (int link_id = 0; link_id < ARRAY_SIZE((mld_vif)->link);	\
+	     link_id++)							\
+		if ((mld_link = iwl_mld_link_dereference_check(mld_vif, link_id)))
+
+/* Retrieve pointer to mld link from mac80211 structures */
+static inline struct iwl_mld_link *
+iwl_mld_link_from_mac80211(struct ieee80211_bss_conf *bss_conf)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif);
+
+	return iwl_mld_link_dereference_check(mld_vif, bss_conf->link_id);
+}
+
+int iwl_mld_mac80211_iftype_to_fw(const struct ieee80211_vif *vif);
+
+/* Cleanup function for struct iwl_mld_vif, will be called in restart */
+void iwl_mld_cleanup_vif(void *data, u8 *mac, struct ieee80211_vif *vif);
+int iwl_mld_mac_fw_action(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			  u32 action);
+int iwl_mld_add_vif(struct iwl_mld *mld, struct ieee80211_vif *vif);
+int iwl_mld_rm_vif(struct iwl_mld *mld, struct ieee80211_vif *vif);
+void iwl_mld_set_vif_associated(struct iwl_mld *mld,
+				struct ieee80211_vif *vif);
+u8 iwl_mld_get_fw_bss_vifs_ids(struct iwl_mld *mld);
+void iwl_mld_handle_probe_resp_data_notif(struct iwl_mld *mld,
+					  struct iwl_rx_packet *pkt);
+
+void iwl_mld_handle_datapath_monitor_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt);
+
+void iwl_mld_handle_uapsd_misbehaving_ap_notif(struct iwl_mld *mld,
+					       struct iwl_rx_packet *pkt);
+
+void iwl_mld_reset_cca_40mhz_workaround(struct iwl_mld *mld,
+					struct ieee80211_vif *vif);
+
+static inline bool iwl_mld_vif_low_latency(const struct iwl_mld_vif *mld_vif)
+{
+	return !!mld_vif->low_latency_causes;
+}
+
+struct ieee80211_vif *iwl_mld_get_bss_vif(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_iface_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/key.c b/drivers/net/wireless/intel/iwlwifi/mld/key.c
new file mode 100644
index 0000000000000..0eff13e5ffd57
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/key.c
@@ -0,0 +1,358 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include "key.h"
+#include "iface.h"
+#include "sta.h"
+#include "fw/api/datapath.h"
+
+static u32 iwl_mld_get_key_flags(struct iwl_mld *mld,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_sta *sta,
+				 struct ieee80211_key_conf *key)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	bool pairwise = key->flags & IEEE80211_KEY_FLAG_PAIRWISE;
+	bool igtk = key->keyidx == 4 || key->keyidx == 5;
+	u32 flags = 0;
+
+	if (!pairwise)
+		flags |= IWL_SEC_KEY_FLAG_MCAST_KEY;
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_TKIP:
+		flags |= IWL_SEC_KEY_FLAG_CIPHER_TKIP;
+		break;
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_CCMP:
+		flags |= IWL_SEC_KEY_FLAG_CIPHER_CCMP;
+		break;
+	case WLAN_CIPHER_SUITE_GCMP_256:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		flags |= IWL_SEC_KEY_FLAG_KEY_SIZE;
+		fallthrough;
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		flags |= IWL_SEC_KEY_FLAG_CIPHER_GCMP;
+		break;
+	}
+
+	if (!sta && vif->type == NL80211_IFTYPE_STATION)
+		sta = mld_vif->ap_sta;
+
+	/* If we are installing an iGTK (in AP or STA mode), we need to tell
+	 * the firmware this key will en/decrypt MGMT frames.
+	 * Same goes if we are installing a pairwise key for an MFP station.
+	 * In case we're installing a groupwise key (which is not an iGTK),
+	 * then, we will not use this key for MGMT frames.
+	 */
+	if ((sta && sta->mfp && pairwise) || igtk)
+		flags |= IWL_SEC_KEY_FLAG_MFP;
+
+	if (key->flags & IEEE80211_KEY_FLAG_SPP_AMSDU)
+		flags |= IWL_SEC_KEY_FLAG_SPP_AMSDU;
+
+	return flags;
+}
+
+static u32 iwl_mld_get_key_sta_mask(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta,
+				    struct ieee80211_key_conf *key)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_link_sta *link_sta;
+	int sta_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* AP group keys are per link and should be on the mcast/bcast STA */
+	if (vif->type == NL80211_IFTYPE_AP &&
+	    !(key->flags & IEEE80211_KEY_FLAG_PAIRWISE)) {
+		struct iwl_mld_link *link = NULL;
+
+		if (key->link_id >= 0)
+			link = iwl_mld_link_dereference_check(mld_vif,
+							      key->link_id);
+
+		if (WARN_ON(!link))
+			return 0;
+
+		/* In this stage we should have both the bcast and mcast STAs */
+		if (WARN_ON(link->bcast_sta.sta_id == IWL_INVALID_STA ||
+			    link->mcast_sta.sta_id == IWL_INVALID_STA))
+			return 0;
+
+		/* IGTK/BIGTK to bcast STA */
+		if (key->keyidx >= 4)
+			return BIT(link->bcast_sta.sta_id);
+
+		/* GTK for data to mcast STA */
+		return BIT(link->mcast_sta.sta_id);
+	}
+
+	/* for client mode use the AP STA also for group keys */
+	if (!sta && vif->type == NL80211_IFTYPE_STATION)
+		sta = mld_vif->ap_sta;
+
+	/* STA should be non-NULL now */
+	if (WARN_ON(!sta))
+		return 0;
+
+	/* Key is not per-link, get the full sta mask */
+	if (key->link_id < 0)
+		return iwl_mld_fw_sta_id_mask(mld, sta);
+
+	/* The link_sta shouldn't be NULL now, but this is checked in
+	 * iwl_mld_fw_sta_id_mask
+	 */
+	link_sta = link_sta_dereference_check(sta, key->link_id);
+
+	sta_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
+	if (sta_id < 0)
+		return 0;
+
+	return BIT(sta_id);
+}
+
+static int iwl_mld_add_key_to_fw(struct iwl_mld *mld, u32 sta_mask,
+				 u32 key_flags, struct ieee80211_key_conf *key)
+{
+	struct iwl_sec_key_cmd cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
+		.u.add.sta_mask = cpu_to_le32(sta_mask),
+		.u.add.key_id = cpu_to_le32(key->keyidx),
+		.u.add.key_flags = cpu_to_le32(key_flags),
+		.u.add.tx_seq = cpu_to_le64(atomic64_read(&key->tx_pn)),
+	};
+	bool tkip = key->cipher == WLAN_CIPHER_SUITE_TKIP;
+	int max_key_len = sizeof(cmd.u.add.key);
+
+	if (WARN_ON(!sta_mask))
+		return -EINVAL;
+
+	if (WARN_ON(key->keylen > max_key_len))
+		return -EINVAL;
+
+	memcpy(cmd.u.add.key, key->key, key->keylen);
+
+	if (tkip) {
+		memcpy(cmd.u.add.tkip_mic_rx_key,
+		       key->key + NL80211_TKIP_DATA_OFFSET_RX_MIC_KEY,
+		       8);
+		memcpy(cmd.u.add.tkip_mic_tx_key,
+		       key->key + NL80211_TKIP_DATA_OFFSET_TX_MIC_KEY,
+		       8);
+	}
+
+	return iwl_mld_send_cmd_pdu(mld, WIDE_ID(DATA_PATH_GROUP, SEC_KEY_CMD),
+				    &cmd);
+}
+
+static void iwl_mld_remove_key_from_fw(struct iwl_mld *mld, u32 sta_mask,
+				       u32 key_flags, u32 keyidx)
+{
+	struct iwl_sec_key_cmd cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+		.u.remove.sta_mask = cpu_to_le32(sta_mask),
+		.u.remove.key_id = cpu_to_le32(keyidx),
+		.u.remove.key_flags = cpu_to_le32(key_flags),
+	};
+
+	if (WARN_ON(!sta_mask))
+		return;
+
+	iwl_mld_send_cmd_pdu(mld, WIDE_ID(DATA_PATH_GROUP, SEC_KEY_CMD), &cmd);
+}
+
+void iwl_mld_remove_key(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta,
+			struct ieee80211_key_conf *key)
+{
+	u32 sta_mask = iwl_mld_get_key_sta_mask(mld, vif, sta, key);
+	u32 key_flags = iwl_mld_get_key_flags(mld, vif, sta, key);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!sta_mask)
+		return;
+
+	if (key->keyidx == 4 || key->keyidx == 5) {
+		struct iwl_mld_link *mld_link;
+		unsigned int link_id = 0;
+
+		/* set to -1 for non-MLO right now */
+		if (key->link_id >= 0)
+			link_id = key->link_id;
+
+		mld_link = iwl_mld_link_dereference_check(mld_vif, link_id);
+		if (WARN_ON(!mld_link))
+			return;
+
+		if (mld_link->igtk == key)
+			mld_link->igtk = NULL;
+
+		mld->num_igtks--;
+	}
+
+	iwl_mld_remove_key_from_fw(mld, sta_mask, key_flags, key->keyidx);
+
+	/* no longer in HW */
+	key->hw_key_idx = STA_KEY_IDX_INVALID;
+}
+
+int iwl_mld_add_key(struct iwl_mld *mld,
+		    struct ieee80211_vif *vif,
+		    struct ieee80211_sta *sta,
+		    struct ieee80211_key_conf *key)
+{
+	u32 sta_mask = iwl_mld_get_key_sta_mask(mld, vif, sta, key);
+	u32 key_flags = iwl_mld_get_key_flags(mld, vif, sta, key);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *mld_link = NULL;
+	bool igtk = key->keyidx == 4 || key->keyidx == 5;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!sta_mask)
+		return -EINVAL;
+
+	if (igtk) {
+		if (mld->num_igtks == IWL_MAX_NUM_IGTKS)
+			return -EOPNOTSUPP;
+
+		u8 link_id = 0;
+
+		/* set to -1 for non-MLO right now */
+		if (key->link_id >= 0)
+			link_id = key->link_id;
+
+		mld_link = iwl_mld_link_dereference_check(mld_vif, link_id);
+
+		if (WARN_ON(!mld_link))
+			return -EINVAL;
+
+		if (mld_link->igtk) {
+			IWL_DEBUG_MAC80211(mld, "remove old IGTK %d\n",
+					   mld_link->igtk->keyidx);
+			iwl_mld_remove_key(mld, vif, sta, mld_link->igtk);
+		}
+
+		WARN_ON(mld_link->igtk);
+	}
+
+	ret = iwl_mld_add_key_to_fw(mld, sta_mask, key_flags, key);
+	if (ret)
+		return ret;
+
+	if (mld_link) {
+		mld_link->igtk = key;
+		mld->num_igtks++;
+	}
+
+	/* We don't really need this, but need it to be not invalid,
+	 * so we will know if the key is in fw.
+	 */
+	key->hw_key_idx = 0;
+
+	return 0;
+}
+
+struct remove_ap_keys_iter_data {
+	u8 link_id;
+	struct ieee80211_sta *sta;
+};
+
+static void iwl_mld_remove_ap_keys_iter(struct ieee80211_hw *hw,
+					struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta,
+					struct ieee80211_key_conf *key,
+					void *_data)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct remove_ap_keys_iter_data *data = _data;
+
+	if (key->hw_key_idx == STA_KEY_IDX_INVALID)
+		return;
+
+	/* All the pairwise keys should have been removed by now */
+	if (WARN_ON(sta))
+		return;
+
+	if (key->link_id >= 0 && key->link_id != data->link_id)
+		return;
+
+	iwl_mld_remove_key(mld, vif, data->sta, key);
+}
+
+void iwl_mld_remove_ap_keys(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			    struct ieee80211_sta *sta, unsigned int link_id)
+{
+	struct remove_ap_keys_iter_data iter_data = {
+		.link_id = link_id,
+		.sta = sta,
+	};
+
+	if (WARN_ON_ONCE(vif->type != NL80211_IFTYPE_STATION))
+		return;
+
+	ieee80211_iter_keys(mld->hw, vif,
+			    iwl_mld_remove_ap_keys_iter,
+			    &iter_data);
+}
+
+struct iwl_mvm_sta_key_update_data {
+	struct ieee80211_sta *sta;
+	u32 old_sta_mask;
+	u32 new_sta_mask;
+	int err;
+};
+
+static void iwl_mld_update_sta_key_iter(struct ieee80211_hw *hw,
+					struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta,
+					struct ieee80211_key_conf *key,
+					void *_data)
+{
+	struct iwl_mvm_sta_key_update_data *data = _data;
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_sec_key_cmd cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_MODIFY),
+		.u.modify.old_sta_mask = cpu_to_le32(data->old_sta_mask),
+		.u.modify.new_sta_mask = cpu_to_le32(data->new_sta_mask),
+		.u.modify.key_id = cpu_to_le32(key->keyidx),
+		.u.modify.key_flags =
+			cpu_to_le32(iwl_mld_get_key_flags(mld, vif, sta, key)),
+	};
+	int err;
+
+	/* only need to do this for pairwise keys (link_id == -1) */
+	if (sta != data->sta || key->link_id >= 0)
+		return;
+
+	err = iwl_mld_send_cmd_pdu(mld, WIDE_ID(DATA_PATH_GROUP, SEC_KEY_CMD),
+				   &cmd);
+
+	if (err)
+		data->err = err;
+}
+
+int iwl_mld_update_sta_keys(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_sta *sta,
+			    u32 old_sta_mask,
+			    u32 new_sta_mask)
+{
+	struct iwl_mvm_sta_key_update_data data = {
+		.sta = sta,
+		.old_sta_mask = old_sta_mask,
+		.new_sta_mask = new_sta_mask,
+	};
+
+	ieee80211_iter_keys(mld->hw, vif, iwl_mld_update_sta_key_iter,
+			    &data);
+	return data.err;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/key.h b/drivers/net/wireless/intel/iwlwifi/mld/key.h
new file mode 100644
index 0000000000000..a68ea48913be6
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/key.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_key_h__
+#define __iwl_mld_key_h__
+
+#include "mld.h"
+#include <net/mac80211.h>
+#include "fw/api/sta.h"
+
+void iwl_mld_remove_key(struct iwl_mld *mld,
+			struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta,
+			struct ieee80211_key_conf *key);
+int iwl_mld_add_key(struct iwl_mld *mld,
+		    struct ieee80211_vif *vif,
+		    struct ieee80211_sta *sta,
+		    struct ieee80211_key_conf *key);
+void iwl_mld_remove_ap_keys(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_sta *sta,
+			    unsigned int link_id);
+
+int iwl_mld_update_sta_keys(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_sta *sta,
+			    u32 old_sta_mask,
+			    u32 new_sta_mask);
+
+static inline void
+iwl_mld_cleanup_keys_iter(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			  struct ieee80211_sta *sta,
+			  struct ieee80211_key_conf *key, void *data)
+{
+	key->hw_key_idx = STA_KEY_IDX_INVALID;
+}
+
+#endif /* __iwl_mld_key_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/led.c b/drivers/net/wireless/intel/iwlwifi/mld/led.c
new file mode 100644
index 0000000000000..a37b32cbc6e65
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/led.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <linux/leds.h>
+#include <net/mac80211.h>
+
+#include "fw/api/led.h"
+#include "mld.h"
+#include "led.h"
+#include "hcmd.h"
+
+static void iwl_mld_send_led_fw_cmd(struct iwl_mld *mld, bool on)
+{
+	struct iwl_led_cmd led_cmd = {
+		.status = cpu_to_le32(on),
+	};
+	int err;
+
+	if (WARN_ON(!mld->fw_status.running))
+		return;
+
+	err = iwl_mld_send_cmd_with_flags_pdu(mld, WIDE_ID(LONG_GROUP,
+							   LEDS_CMD),
+					      CMD_ASYNC, &led_cmd);
+
+	if (err)
+		IWL_WARN(mld, "LED command failed: %d\n", err);
+}
+
+static void iwl_led_brightness_set(struct led_classdev *led_cdev,
+				   enum led_brightness brightness)
+{
+	struct iwl_mld *mld = container_of(led_cdev, struct iwl_mld, led);
+
+	if (!mld->fw_status.running)
+		return;
+
+	iwl_mld_send_led_fw_cmd(mld, brightness > 0);
+}
+
+int iwl_mld_leds_init(struct iwl_mld *mld)
+{
+	int mode = iwlwifi_mod_params.led_mode;
+	int ret;
+
+	switch (mode) {
+	case IWL_LED_BLINK:
+		IWL_ERR(mld, "Blink led mode not supported, used default\n");
+		fallthrough;
+	case IWL_LED_DEFAULT:
+	case IWL_LED_RF_STATE:
+		mode = IWL_LED_RF_STATE;
+		break;
+	case IWL_LED_DISABLE:
+		IWL_INFO(mld, "Led disabled\n");
+		return 0;
+	default:
+		return -EINVAL;
+	}
+
+	mld->led.name = kasprintf(GFP_KERNEL, "%s-led",
+				  wiphy_name(mld->hw->wiphy));
+	if (!mld->led.name)
+		return -ENOMEM;
+
+	mld->led.brightness_set = iwl_led_brightness_set;
+	mld->led.max_brightness = 1;
+
+	if (mode == IWL_LED_RF_STATE)
+		mld->led.default_trigger =
+			ieee80211_get_radio_led_name(mld->hw);
+
+	ret = led_classdev_register(mld->trans->dev, &mld->led);
+	if (ret) {
+		kfree(mld->led.name);
+		mld->led.name = NULL;
+		IWL_INFO(mld, "Failed to enable led\n");
+	}
+
+	return ret;
+}
+
+void iwl_mld_led_config_fw(struct iwl_mld *mld)
+{
+	if (!mld->led.name)
+		return;
+
+	iwl_mld_send_led_fw_cmd(mld, mld->led.brightness > 0);
+}
+
+void iwl_mld_leds_exit(struct iwl_mld *mld)
+{
+	if (!mld->led.name)
+		return;
+
+	led_classdev_unregister(&mld->led);
+	kfree(mld->led.name);
+	mld->led.name = NULL;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/led.h b/drivers/net/wireless/intel/iwlwifi/mld/led.h
new file mode 100644
index 0000000000000..0954e214e73d6
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/led.h
@@ -0,0 +1,29 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_led_h__
+#define __iwl_mld_led_h__
+
+#include "mld.h"
+
+#ifdef CONFIG_IWLWIFI_LEDS
+int iwl_mld_leds_init(struct iwl_mld *mld);
+void iwl_mld_leds_exit(struct iwl_mld *mld);
+void iwl_mld_led_config_fw(struct iwl_mld *mld);
+#else
+static inline int iwl_mld_leds_init(struct iwl_mld *mld)
+{
+	return 0;
+}
+
+static inline void iwl_mld_leds_exit(struct iwl_mld *mld)
+{
+}
+
+static inline void iwl_mld_led_config_fw(struct iwl_mld *mld)
+{
+}
+#endif
+
+#endif /* __iwl_mld_led_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
new file mode 100644
index 0000000000000..64ebafc35c9bf
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -0,0 +1,1216 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "constants.h"
+#include "link.h"
+#include "iface.h"
+#include "mlo.h"
+#include "hcmd.h"
+#include "phy.h"
+#include "fw/api/rs.h"
+#include "fw/api/txq.h"
+#include "fw/api/mac.h"
+
+#include "fw/api/context.h"
+#include "fw/dbg.h"
+
+static int iwl_mld_send_link_cmd(struct iwl_mld *mld,
+				 struct iwl_link_config_cmd *cmd,
+				 enum iwl_ctxt_action action)
+{
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	cmd->action = cpu_to_le32(action);
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(MAC_CONF_GROUP, LINK_CONFIG_CMD),
+				   cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to send LINK_CONFIG_CMD (action:%d): %d\n",
+			action, ret);
+	return ret;
+}
+
+static int iwl_mld_add_link_to_fw(struct iwl_mld *mld,
+				  struct ieee80211_bss_conf *link_conf)
+{
+	struct ieee80211_vif *vif = link_conf->vif;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link = iwl_mld_link_from_mac80211(link_conf);
+	struct iwl_link_config_cmd cmd = {};
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!link))
+		return -EINVAL;
+
+	cmd.link_id = cpu_to_le32(link->fw_id);
+	cmd.mac_id = cpu_to_le32(mld_vif->fw_id);
+	cmd.spec_link_id = link_conf->link_id;
+	cmd.phy_id = cpu_to_le32(FW_CTXT_ID_INVALID);
+
+	ether_addr_copy(cmd.local_link_addr, link_conf->addr);
+
+	if (vif->type == NL80211_IFTYPE_ADHOC && link_conf->bssid)
+		ether_addr_copy(cmd.ibss_bssid_addr, link_conf->bssid);
+
+	return iwl_mld_send_link_cmd(mld, &cmd, FW_CTXT_ACTION_ADD);
+}
+
+/* Get the basic rates of the used band and add the mandatory ones */
+static void iwl_mld_fill_rates(struct iwl_mld *mld,
+			       struct ieee80211_bss_conf *link,
+			       struct ieee80211_chanctx_conf *chan_ctx,
+			       __le32 *cck_rates, __le32 *ofdm_rates)
+{
+	struct cfg80211_chan_def *chandef =
+		iwl_mld_get_chandef_from_chanctx(chan_ctx);
+	struct ieee80211_supported_band *sband =
+		mld->hw->wiphy->bands[chandef->chan->band];
+	unsigned long basic = link->basic_rates;
+	int lowest_present_ofdm = 100;
+	int lowest_present_cck = 100;
+	u32 cck = 0;
+	u32 ofdm = 0;
+	int i;
+
+	for_each_set_bit(i, &basic, BITS_PER_LONG) {
+		int hw = sband->bitrates[i].hw_value;
+
+		if (hw >= IWL_FIRST_OFDM_RATE) {
+			ofdm |= BIT(hw - IWL_FIRST_OFDM_RATE);
+			if (lowest_present_ofdm > hw)
+				lowest_present_ofdm = hw;
+		} else {
+			BUILD_BUG_ON(IWL_FIRST_CCK_RATE != 0);
+
+			cck |= BIT(hw);
+			if (lowest_present_cck > hw)
+				lowest_present_cck = hw;
+		}
+	}
+
+	/* Now we've got the basic rates as bitmaps in the ofdm and cck
+	 * variables. This isn't sufficient though, as there might not
+	 * be all the right rates in the bitmap. E.g. if the only basic
+	 * rates are 5.5 Mbps and 11 Mbps, we still need to add 1 Mbps
+	 * and 6 Mbps because the 802.11-2007 standard says in 9.6:
+	 *
+	 *    [...] a STA responding to a received frame shall transmit
+	 *    its Control Response frame [...] at the highest rate in the
+	 *    BSSBasicRateSet parameter that is less than or equal to the
+	 *    rate of the immediately previous frame in the frame exchange
+	 *    sequence ([...]) and that is of the same modulation class
+	 *    ([...]) as the received frame. If no rate contained in the
+	 *    BSSBasicRateSet parameter meets these conditions, then the
+	 *    control frame sent in response to a received frame shall be
+	 *    transmitted at the highest mandatory rate of the PHY that is
+	 *    less than or equal to the rate of the received frame, and
+	 *    that is of the same modulation class as the received frame.
+	 *
+	 * As a consequence, we need to add all mandatory rates that are
+	 * lower than all of the basic rates to these bitmaps.
+	 */
+
+	if (lowest_present_ofdm > IWL_RATE_24M_INDEX)
+		ofdm |= IWL_RATE_BIT_MSK(24) >> IWL_FIRST_OFDM_RATE;
+	if (lowest_present_ofdm > IWL_RATE_12M_INDEX)
+		ofdm |= IWL_RATE_BIT_MSK(12) >> IWL_FIRST_OFDM_RATE;
+	/* 6M already there or needed so always add */
+	ofdm |= IWL_RATE_BIT_MSK(6) >> IWL_FIRST_OFDM_RATE;
+
+	/* CCK is a bit more complex with DSSS vs. HR/DSSS vs. ERP.
+	 * Note, however:
+	 *  - if no CCK rates are basic, it must be ERP since there must
+	 *    be some basic rates at all, so they're OFDM => ERP PHY
+	 *    (or we're in 5 GHz, and the cck bitmap will never be used)
+	 *  - if 11M is a basic rate, it must be ERP as well, so add 5.5M
+	 *  - if 5.5M is basic, 1M and 2M are mandatory
+	 *  - if 2M is basic, 1M is mandatory
+	 *  - if 1M is basic, that's the only valid ACK rate.
+	 * As a consequence, it's not as complicated as it sounds, just add
+	 * any lower rates to the ACK rate bitmap.
+	 */
+	if (lowest_present_cck > IWL_RATE_11M_INDEX)
+		cck |= IWL_RATE_BIT_MSK(11) >> IWL_FIRST_CCK_RATE;
+	if (lowest_present_cck > IWL_RATE_5M_INDEX)
+		cck |= IWL_RATE_BIT_MSK(5) >> IWL_FIRST_CCK_RATE;
+	if (lowest_present_cck > IWL_RATE_2M_INDEX)
+		cck |= IWL_RATE_BIT_MSK(2) >> IWL_FIRST_CCK_RATE;
+	/* 1M already there or needed so always add */
+	cck |= IWL_RATE_BIT_MSK(1) >> IWL_FIRST_CCK_RATE;
+
+	*cck_rates = cpu_to_le32((u32)cck);
+	*ofdm_rates = cpu_to_le32((u32)ofdm);
+}
+
+static void iwl_mld_fill_protection_flags(struct iwl_mld *mld,
+					  struct ieee80211_bss_conf *link,
+					  __le32 *protection_flags)
+{
+	u8 protection_mode = link->ht_operation_mode &
+				IEEE80211_HT_OP_MODE_PROTECTION;
+	u8 ht_flag = LINK_PROT_FLG_HT_PROT | LINK_PROT_FLG_FAT_PROT;
+
+	IWL_DEBUG_RATE(mld, "HT protection mode: %d\n", protection_mode);
+
+	if (link->use_cts_prot)
+		*protection_flags |= cpu_to_le32(LINK_PROT_FLG_TGG_PROTECT);
+
+	/* See section 9.23.3.1 of IEEE 80211-2012.
+	 * Nongreenfield HT STAs Present is not supported.
+	 */
+	switch (protection_mode) {
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONE:
+		break;
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER:
+	case IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED:
+		*protection_flags |= cpu_to_le32(ht_flag);
+		break;
+	case IEEE80211_HT_OP_MODE_PROTECTION_20MHZ:
+		/* Protect when channel wider than 20MHz */
+		if (link->chanreq.oper.width > NL80211_CHAN_WIDTH_20)
+			*protection_flags |= cpu_to_le32(ht_flag);
+		break;
+	}
+}
+
+static u8 iwl_mld_mac80211_ac_to_fw_ac(enum ieee80211_ac_numbers ac)
+{
+	static const u8 mac80211_ac_to_fw[] = {
+		AC_VO,
+		AC_VI,
+		AC_BE,
+		AC_BK
+	};
+
+	return mac80211_ac_to_fw[ac];
+}
+
+static void iwl_mld_fill_qos_params(struct ieee80211_bss_conf *link,
+				    struct iwl_ac_qos *ac, __le32 *qos_flags)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+
+	/* no need to check mld_link since it is done in the caller */
+
+	for (int mac_ac = 0; mac_ac < IEEE80211_NUM_ACS; mac_ac++) {
+		u8 txf = iwl_mld_mac80211_ac_to_fw_tx_fifo(mac_ac);
+		u8 fw_ac = iwl_mld_mac80211_ac_to_fw_ac(mac_ac);
+
+		ac[fw_ac].cw_min =
+			cpu_to_le16(mld_link->queue_params[mac_ac].cw_min);
+		ac[fw_ac].cw_max =
+			cpu_to_le16(mld_link->queue_params[mac_ac].cw_max);
+		ac[fw_ac].edca_txop =
+			cpu_to_le16(mld_link->queue_params[mac_ac].txop * 32);
+		ac[fw_ac].aifsn = mld_link->queue_params[mac_ac].aifs;
+		ac[fw_ac].fifos_mask = BIT(txf);
+	}
+
+	if (link->qos)
+		*qos_flags |= cpu_to_le32(MAC_QOS_FLG_UPDATE_EDCA);
+
+	if (link->chanreq.oper.width != NL80211_CHAN_WIDTH_20_NOHT)
+		*qos_flags |= cpu_to_le32(MAC_QOS_FLG_TGN);
+}
+
+static bool iwl_mld_fill_mu_edca(struct iwl_mld *mld,
+				 const struct iwl_mld_link *mld_link,
+				 struct iwl_he_backoff_conf *trig_based_txf)
+{
+	for (int mac_ac = 0; mac_ac < IEEE80211_NUM_ACS; mac_ac++) {
+		const struct ieee80211_he_mu_edca_param_ac_rec *mu_edca =
+			&mld_link->queue_params[mac_ac].mu_edca_param_rec;
+		u8 fw_ac = iwl_mld_mac80211_ac_to_fw_ac(mac_ac);
+
+		if (!mld_link->queue_params[mac_ac].mu_edca)
+			return false;
+
+		trig_based_txf[fw_ac].cwmin =
+			cpu_to_le16(mu_edca->ecw_min_max & 0xf);
+		trig_based_txf[fw_ac].cwmax =
+			cpu_to_le16((mu_edca->ecw_min_max & 0xf0) >> 4);
+		trig_based_txf[fw_ac].aifsn =
+			cpu_to_le16(mu_edca->aifsn & 0xf);
+		trig_based_txf[fw_ac].mu_time =
+			cpu_to_le16(mu_edca->mu_edca_timer);
+	}
+	return true;
+}
+
+static u8 iwl_mld_sta_rx_bw_to_fw(enum ieee80211_sta_rx_bandwidth bw)
+{
+	switch (bw) {
+	default: /* potential future values not supported by this hw/driver */
+	case IEEE80211_STA_RX_BW_20:
+		return IWL_LINK_MODIFY_BW_20;
+	case IEEE80211_STA_RX_BW_40:
+		return IWL_LINK_MODIFY_BW_40;
+	case IEEE80211_STA_RX_BW_80:
+		return IWL_LINK_MODIFY_BW_80;
+	case IEEE80211_STA_RX_BW_160:
+		return IWL_LINK_MODIFY_BW_160;
+	case IEEE80211_STA_RX_BW_320:
+		return IWL_LINK_MODIFY_BW_320;
+	}
+}
+
+static int _iwl_mld_change_link_in_fw(struct iwl_mld *mld,
+				      struct ieee80211_bss_conf *link,
+				      enum ieee80211_sta_rx_bandwidth bw,
+				      u32 changes)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	struct ieee80211_vif *vif = link->vif;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_chanctx_conf *chan_ctx;
+	struct iwl_link_config_cmd cmd = {};
+	u32 flags = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	cmd.link_id = cpu_to_le32(mld_link->fw_id);
+	cmd.spec_link_id = link->link_id;
+	cmd.mac_id = cpu_to_le32(mld_vif->fw_id);
+
+	chan_ctx = wiphy_dereference(mld->wiphy, mld_link->chan_ctx);
+
+	cmd.phy_id = cpu_to_le32(chan_ctx ?
+		iwl_mld_phy_from_mac80211(chan_ctx)->fw_id :
+		FW_CTXT_ID_INVALID);
+
+	ether_addr_copy(cmd.local_link_addr, link->addr);
+
+	cmd.active = cpu_to_le32(mld_link->active);
+
+	if ((changes & LINK_CONTEXT_MODIFY_ACTIVE) && !mld_link->active &&
+	    mld_link->silent_deactivation) {
+		/* We are de-activating a link that is having CSA with
+		 * immediate quiet in EMLSR. Tell the firmware not to send any
+		 * frame.
+		 */
+		cmd.block_tx = 1;
+		mld_link->silent_deactivation = false;
+	}
+
+	if (vif->type == NL80211_IFTYPE_ADHOC && link->bssid)
+		ether_addr_copy(cmd.ibss_bssid_addr, link->bssid);
+
+	/* Channel context is needed to get the rates */
+	if (chan_ctx)
+		iwl_mld_fill_rates(mld, link, chan_ctx, &cmd.cck_rates,
+				   &cmd.ofdm_rates);
+
+	cmd.cck_short_preamble = cpu_to_le32(link->use_short_preamble);
+	cmd.short_slot = cpu_to_le32(link->use_short_slot);
+
+	iwl_mld_fill_protection_flags(mld, link, &cmd.protection_flags);
+
+	iwl_mld_fill_qos_params(link, cmd.ac, &cmd.qos_flags);
+
+	cmd.bi = cpu_to_le32(link->beacon_int);
+	cmd.dtim_interval = cpu_to_le32(link->beacon_int * link->dtim_period);
+
+	if (changes & LINK_CONTEXT_MODIFY_BANDWIDTH)
+		cmd.modify_bandwidth = iwl_mld_sta_rx_bw_to_fw(bw);
+
+	/* Configure HE parameters only if HE is supported, and only after
+	 * the parameters are set in mac80211 (meaning after assoc)
+	 */
+	if (!link->he_support || iwlwifi_mod_params.disable_11ax ||
+	    (vif->type == NL80211_IFTYPE_STATION && !vif->cfg.assoc)) {
+		changes &= ~LINK_CONTEXT_MODIFY_HE_PARAMS;
+		goto send_cmd;
+	}
+
+	/* ap_sta may be NULL if we're disconnecting */
+	if (mld_vif->ap_sta) {
+		struct ieee80211_link_sta *link_sta =
+			link_sta_dereference_check(mld_vif->ap_sta,
+						   link->link_id);
+
+		if (!WARN_ON(!link_sta) && link_sta->he_cap.has_he &&
+		    link_sta->he_cap.he_cap_elem.mac_cap_info[5] &
+		    IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX)
+			cmd.ul_mu_data_disable = 1;
+	}
+
+	cmd.htc_trig_based_pkt_ext = link->htc_trig_based_pkt_ext;
+
+	if (link->uora_exists) {
+		cmd.rand_alloc_ecwmin = link->uora_ocw_range & 0x7;
+		cmd.rand_alloc_ecwmax = (link->uora_ocw_range >> 3) & 0x7;
+	}
+
+	if (iwl_mld_fill_mu_edca(mld, mld_link, cmd.trig_based_txf))
+		flags |= LINK_FLG_MU_EDCA_CW;
+
+	cmd.bss_color = link->he_bss_color.color;
+
+	if (!link->he_bss_color.enabled)
+		flags |= LINK_FLG_BSS_COLOR_DIS;
+
+	cmd.frame_time_rts_th = cpu_to_le16(link->frame_time_rts_th);
+
+	/* Block 26-tone RU OFDMA transmissions */
+	if (mld_link->he_ru_2mhz_block)
+		flags |= LINK_FLG_RU_2MHZ_BLOCK;
+
+	if (link->nontransmitted) {
+		ether_addr_copy(cmd.ref_bssid_addr, link->transmitter_bssid);
+		cmd.bssid_index = link->bssid_index;
+	}
+
+	/* The only EHT parameter is puncturing, and starting from PHY cmd
+	 * version 6 - it is sent there. For older versions of the PHY cmd,
+	 * puncturing is not needed at all.
+	 */
+	if (WARN_ON(changes & LINK_CONTEXT_MODIFY_EHT_PARAMS))
+		changes &= ~LINK_CONTEXT_MODIFY_EHT_PARAMS;
+
+send_cmd:
+	cmd.modify_mask = cpu_to_le32(changes);
+	cmd.flags = cpu_to_le32(flags);
+
+	return iwl_mld_send_link_cmd(mld, &cmd, FW_CTXT_ACTION_MODIFY);
+}
+
+int iwl_mld_change_link_in_fw(struct iwl_mld *mld,
+			      struct ieee80211_bss_conf *link,
+			      u32 changes)
+{
+	if (WARN_ON(changes & LINK_CONTEXT_MODIFY_BANDWIDTH))
+		changes &= ~LINK_CONTEXT_MODIFY_BANDWIDTH;
+
+	return _iwl_mld_change_link_in_fw(mld, link, 0, changes);
+}
+
+int iwl_mld_change_link_omi_bw(struct iwl_mld *mld,
+			       struct ieee80211_bss_conf *link,
+			       enum ieee80211_sta_rx_bandwidth bw)
+{
+	return _iwl_mld_change_link_in_fw(mld, link, bw,
+					  LINK_CONTEXT_MODIFY_BANDWIDTH);
+}
+
+int iwl_mld_activate_link(struct iwl_mld *mld,
+			  struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link || mld_link->active))
+		return -EINVAL;
+
+	mld_link->rx_omi.exit_ts = jiffies;
+	mld_link->active = true;
+
+	ret = iwl_mld_change_link_in_fw(mld, link,
+					LINK_CONTEXT_MODIFY_ACTIVE);
+	if (ret)
+		mld_link->active = false;
+
+	return ret;
+}
+
+void iwl_mld_deactivate_link(struct iwl_mld *mld,
+			     struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	struct iwl_probe_resp_data *probe_data;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link || !mld_link->active))
+		return;
+
+	iwl_mld_cancel_session_protection(mld, link->vif, link->link_id);
+
+	/* If we deactivate the link, we will probably remove it, or switch
+	 * channel. In both cases, the CSA or Notice of Absence information is
+	 * now irrelevant. Remove the data here.
+	 */
+	probe_data = wiphy_dereference(mld->wiphy, mld_link->probe_resp_data);
+	RCU_INIT_POINTER(mld_link->probe_resp_data, NULL);
+	if (probe_data)
+		kfree_rcu(probe_data, rcu_head);
+
+	mld_link->active = false;
+
+	iwl_mld_change_link_in_fw(mld, link, LINK_CONTEXT_MODIFY_ACTIVE);
+
+	/* Now that the link is not active in FW, we don't expect any new
+	 * notifications for it. Cancel the ones that are already pending
+	 */
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_LINK,
+					       mld_link->fw_id);
+}
+
+static int
+iwl_mld_rm_link_from_fw(struct iwl_mld *mld, struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	struct iwl_link_config_cmd cmd = {};
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	cmd.link_id = cpu_to_le32(mld_link->fw_id);
+	cmd.spec_link_id = link->link_id;
+	cmd.phy_id = cpu_to_le32(FW_CTXT_ID_INVALID);
+
+	return iwl_mld_send_link_cmd(mld, &cmd, FW_CTXT_ACTION_REMOVE);
+}
+
+static void iwl_mld_omi_bw_update(struct iwl_mld *mld,
+				  struct ieee80211_bss_conf *link_conf,
+				  struct iwl_mld_link *mld_link,
+				  struct ieee80211_link_sta *link_sta,
+				  enum ieee80211_sta_rx_bandwidth bw,
+				  bool ap_update)
+{
+	enum ieee80211_sta_rx_bandwidth apply_bw;
+
+	mld_link->rx_omi.desired_bw = bw;
+
+	/* Can't update OMI while already in progress, desired_bw was
+	 * set so on FW notification the worker will see the change
+	 * and apply new the new desired bw.
+	 */
+	if (mld_link->rx_omi.bw_in_progress)
+		return;
+
+	if (bw == IEEE80211_STA_RX_BW_MAX)
+		apply_bw = ieee80211_chan_width_to_rx_bw(link_conf->chanreq.oper.width);
+	else
+		apply_bw = bw;
+
+	if (!ap_update) {
+		/* The update isn't due to AP tracking after leaving OMI,
+		 * where the AP could increase BW and then we must tell
+		 * it that we can do the increased BW as well, if we did
+		 * update the chandef.
+		 * In this case, if we want MAX, then we will need to send
+		 * a new OMI to the AP if it increases its own bandwidth as
+		 * we can (due to internal and FW limitations, and being
+		 * worried the AP might break) only send to what we're doing
+		 * at the moment. In this case, set last_max_bw; otherwise
+		 * if we really want to decrease our bandwidth set it to 0
+		 * to indicate no updates are needed if the AP changes.
+		 */
+		if (bw != IEEE80211_STA_RX_BW_MAX)
+			mld_link->rx_omi.last_max_bw = apply_bw;
+		else
+			mld_link->rx_omi.last_max_bw = 0;
+	} else {
+		/* Otherwise, if we're already trying to do maximum and
+		 * the AP is changing, set last_max_bw to the new max the
+		 * AP is using, we'll only get to this code path if the
+		 * new bandwidth of the AP is bigger than what we sent it
+		 * previously. This avoids repeatedly sending updates if
+		 * it changes bandwidth, only doing it once on an increase.
+		 */
+		mld_link->rx_omi.last_max_bw = apply_bw;
+	}
+
+	if (ieee80211_prepare_rx_omi_bw(link_sta, bw)) {
+		mld_link->rx_omi.bw_in_progress = apply_bw;
+		iwl_mld_change_link_omi_bw(mld, link_conf, apply_bw);
+	}
+}
+
+static void iwl_mld_omi_bw_finished_work(struct wiphy *wiphy,
+					 struct wiphy_work *work)
+{
+	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_link *mld_link =
+		container_of(work, typeof(*mld_link), rx_omi.finished_work.work);
+	enum ieee80211_sta_rx_bandwidth desired_bw, switched_to_bw;
+	struct ieee80211_vif *vif = mld_link->vif;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_link_sta *link_sta;
+
+	if (!mld_vif->ap_sta)
+		return;
+
+	link_sta = wiphy_dereference(mld->wiphy,
+				     mld_vif->ap_sta->link[mld_link->link_id]);
+	if (WARN_ON_ONCE(!link_sta))
+		return;
+
+	link_conf = link_conf_dereference_protected(vif, link_sta->link_id);
+	if (WARN_ON_ONCE(!link_conf))
+		return;
+
+	if (WARN_ON(!mld_link->rx_omi.bw_in_progress))
+		return;
+
+	desired_bw = mld_link->rx_omi.desired_bw;
+	switched_to_bw = mld_link->rx_omi.bw_in_progress;
+
+	ieee80211_finalize_rx_omi_bw(link_sta);
+	mld_link->rx_omi.bw_in_progress = 0;
+
+	if (desired_bw != switched_to_bw)
+		iwl_mld_omi_bw_update(mld, link_conf, mld_link, link_sta,
+				      desired_bw, false);
+}
+
+static struct ieee80211_vif *
+iwl_mld_get_omi_bw_reduction_pointers(struct iwl_mld *mld,
+				      struct ieee80211_link_sta **link_sta,
+				      struct iwl_mld_link **mld_link)
+{
+	struct iwl_mld_vif *mld_vif;
+	struct ieee80211_vif *vif;
+	int n_link_stas = 0;
+
+	*link_sta = NULL;
+
+	if (mld->trans->trans_cfg->device_family < IWL_DEVICE_FAMILY_SC)
+		return NULL;
+
+	vif = iwl_mld_get_bss_vif(mld);
+	if (!vif)
+		return NULL;
+
+	for (int i = 0; i < ARRAY_SIZE(mld->fw_id_to_link_sta); i++) {
+		struct ieee80211_link_sta *tmp;
+
+		tmp = wiphy_dereference(mld->wiphy, mld->fw_id_to_link_sta[i]);
+		if (IS_ERR_OR_NULL(tmp))
+			continue;
+
+		n_link_stas++;
+		*link_sta = tmp;
+	}
+
+	/* can't do anything if we have TDLS peers or EMLSR */
+	if (n_link_stas != 1)
+		return NULL;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	*mld_link = iwl_mld_link_dereference_check(mld_vif,
+						   (*link_sta)->link_id);
+	if (WARN_ON(!*mld_link))
+		return NULL;
+
+	return vif;
+}
+
+void iwl_mld_omi_ap_changed_bw(struct iwl_mld *mld,
+			       struct ieee80211_bss_conf *link_conf,
+			       enum ieee80211_sta_rx_bandwidth bw)
+{
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_link *mld_link;
+	struct ieee80211_vif *vif;
+
+	vif = iwl_mld_get_omi_bw_reduction_pointers(mld, &link_sta, &mld_link);
+	if (!vif)
+		return;
+
+	if (WARN_ON(link_conf->vif != vif))
+		return;
+
+	/* This is 0 if we requested an OMI BW reduction and don't want to
+	 * be sending an OMI when the AP's bandwidth changes.
+	 */
+	if (!mld_link->rx_omi.last_max_bw)
+		return;
+
+	/* We only need to tell the AP if it increases BW over what we last
+	 * told it we were using, if it reduces then our last OMI to it will
+	 * not get used anyway (e.g. we said we want 160 but it's doing 80.)
+	 */
+	if (bw < mld_link->rx_omi.last_max_bw)
+		return;
+
+	iwl_mld_omi_bw_update(mld, link_conf, mld_link, link_sta, bw, true);
+}
+
+void iwl_mld_handle_omi_status_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt)
+{
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_link *mld_link;
+	struct ieee80211_vif *vif;
+
+	vif = iwl_mld_get_omi_bw_reduction_pointers(mld, &link_sta, &mld_link);
+	if (IWL_FW_CHECK(mld, !vif, "unexpected OMI notification\n"))
+		return;
+
+	if (IWL_FW_CHECK(mld, !mld_link->rx_omi.bw_in_progress,
+			 "OMI notification when not requested\n"))
+		return;
+
+	wiphy_delayed_work_queue(mld->hw->wiphy,
+				 &mld_link->rx_omi.finished_work,
+				 msecs_to_jiffies(IWL_MLD_OMI_AP_SETTLE_DELAY));
+}
+
+void iwl_mld_leave_omi_bw_reduction(struct iwl_mld *mld)
+{
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_link *mld_link;
+	struct ieee80211_vif *vif;
+
+	vif = iwl_mld_get_omi_bw_reduction_pointers(mld, &link_sta, &mld_link);
+	if (!vif)
+		return;
+
+	link_conf = link_conf_dereference_protected(vif, link_sta->link_id);
+	if (WARN_ON_ONCE(!link_conf))
+		return;
+
+	if (!link_conf->he_support)
+		return;
+
+	mld_link->rx_omi.exit_ts = jiffies;
+
+	iwl_mld_omi_bw_update(mld, link_conf, mld_link, link_sta,
+			      IEEE80211_STA_RX_BW_MAX, false);
+}
+
+void iwl_mld_check_omi_bw_reduction(struct iwl_mld *mld)
+{
+	enum ieee80211_sta_rx_bandwidth bw = IEEE80211_STA_RX_BW_MAX;
+	struct ieee80211_chanctx_conf *chanctx;
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_link_sta *link_sta;
+	struct cfg80211_chan_def chandef;
+	struct iwl_mld_link *mld_link;
+	struct iwl_mld_vif *mld_vif;
+	struct ieee80211_vif *vif;
+	struct iwl_mld_phy *phy;
+	u16 punctured;
+	int exit_thr;
+
+	/* not allowed in CAM mode */
+	if (iwlmld_mod_params.power_scheme == IWL_POWER_SCHEME_CAM)
+		return;
+
+	/* must have one BSS connection (no P2P), no TDLS, nor EMLSR */
+	vif = iwl_mld_get_omi_bw_reduction_pointers(mld, &link_sta, &mld_link);
+	if (!vif)
+		return;
+
+	link_conf = link_conf_dereference_protected(vif, link_sta->link_id);
+	if (WARN_ON_ONCE(!link_conf))
+		return;
+
+	if (!link_conf->he_support)
+		return;
+
+	chanctx = wiphy_dereference(mld->wiphy, mld_link->chan_ctx);
+	if (WARN_ON(!chanctx))
+		return;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	if (!mld_vif->authorized)
+		goto apply;
+
+	/* must not be in low-latency mode */
+	if (iwl_mld_vif_low_latency(mld_vif))
+		goto apply;
+
+	chandef = link_conf->chanreq.oper;
+
+	switch (chandef.width) {
+	case NL80211_CHAN_WIDTH_320:
+		exit_thr = IWL_MLD_OMI_EXIT_CHAN_LOAD_320;
+		break;
+	case NL80211_CHAN_WIDTH_160:
+		exit_thr = IWL_MLD_OMI_EXIT_CHAN_LOAD_160;
+		break;
+	default:
+		/* since we reduce to 80 MHz, must have more to start with */
+		goto apply;
+	}
+
+	/* not to be done if primary 80 MHz is punctured */
+	if (cfg80211_chandef_primary(&chandef, NL80211_CHAN_WIDTH_80,
+				     &punctured) < 0 ||
+	    punctured != 0)
+		goto apply;
+
+	phy = iwl_mld_phy_from_mac80211(chanctx);
+
+	if (phy->channel_load_by_us > exit_thr) {
+		/* send OMI for max bandwidth */
+		goto apply;
+	}
+
+	if (phy->channel_load_by_us > IWL_MLD_OMI_ENTER_CHAN_LOAD) {
+		/* no changes between enter/exit thresholds */
+		return;
+	}
+
+	if (time_is_before_jiffies(mld_link->rx_omi.exit_ts +
+				   msecs_to_jiffies(IWL_MLD_OMI_EXIT_PROTECTION)))
+		return;
+
+	/* reduce bandwidth to 80 MHz to save power */
+	bw = IEEE80211_STA_RX_BW_80;
+apply:
+	iwl_mld_omi_bw_update(mld, link_conf, mld_link, link_sta, bw, false);
+}
+
+IWL_MLD_ALLOC_FN(link, bss_conf)
+
+/* Constructor function for struct iwl_mld_link */
+static int
+iwl_mld_init_link(struct iwl_mld *mld, struct ieee80211_bss_conf *link,
+		  struct iwl_mld_link *mld_link)
+{
+	mld_link->vif = link->vif;
+	mld_link->link_id = link->link_id;
+
+	iwl_mld_init_internal_sta(&mld_link->bcast_sta);
+	iwl_mld_init_internal_sta(&mld_link->mcast_sta);
+	iwl_mld_init_internal_sta(&mld_link->aux_sta);
+
+	wiphy_delayed_work_init(&mld_link->rx_omi.finished_work,
+				iwl_mld_omi_bw_finished_work);
+
+	return iwl_mld_allocate_link_fw_id(mld, &mld_link->fw_id, link);
+}
+
+/* Initializes the link structure, maps fw id to the ieee80211_bss_conf, and
+ * adds a link to the fw
+ */
+int iwl_mld_add_link(struct iwl_mld *mld,
+		     struct ieee80211_bss_conf *bss_conf)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif);
+	struct iwl_mld_link *link = iwl_mld_link_from_mac80211(bss_conf);
+	bool is_deflink = bss_conf == &bss_conf->vif->bss_conf;
+	int ret;
+
+	if (!link) {
+		if (is_deflink)
+			link = &mld_vif->deflink;
+		else
+			link = kzalloc(sizeof(*link), GFP_KERNEL);
+	} else {
+		WARN_ON(!mld->fw_status.in_hw_restart);
+	}
+
+	ret = iwl_mld_init_link(mld, bss_conf, link);
+	if (ret)
+		goto free;
+
+	rcu_assign_pointer(mld_vif->link[bss_conf->link_id], link);
+
+	ret = iwl_mld_add_link_to_fw(mld, bss_conf);
+	if (ret) {
+		RCU_INIT_POINTER(mld->fw_id_to_bss_conf[link->fw_id], NULL);
+		RCU_INIT_POINTER(mld_vif->link[bss_conf->link_id], NULL);
+		goto free;
+	}
+
+	return ret;
+
+free:
+	if (!is_deflink)
+		kfree(link);
+	return ret;
+}
+
+/* Remove link from fw, unmap the bss_conf, and destroy the link structure */
+int iwl_mld_remove_link(struct iwl_mld *mld,
+			struct ieee80211_bss_conf *bss_conf)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif);
+	struct iwl_mld_link *link = iwl_mld_link_from_mac80211(bss_conf);
+	bool is_deflink = link == &mld_vif->deflink;
+	int ret;
+
+	if (WARN_ON(!link || link->active))
+		return -EINVAL;
+
+	ret = iwl_mld_rm_link_from_fw(mld, bss_conf);
+	/* Continue cleanup on failure */
+
+	if (!is_deflink)
+		kfree_rcu(link, rcu_head);
+
+	RCU_INIT_POINTER(mld_vif->link[bss_conf->link_id], NULL);
+
+	wiphy_delayed_work_cancel(mld->wiphy, &link->rx_omi.finished_work);
+
+	if (WARN_ON(link->fw_id >= mld->fw->ucode_capa.num_links))
+		return -EINVAL;
+
+	RCU_INIT_POINTER(mld->fw_id_to_bss_conf[link->fw_id], NULL);
+
+	return ret;
+}
+
+void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt)
+{
+	const struct iwl_missed_beacons_notif *notif = (const void *)pkt->data;
+	union iwl_dbg_tlv_tp_data tp_data = { .fw_pkt = pkt };
+	u32 link_id = le32_to_cpu(notif->link_id);
+	u32 missed_bcon = le32_to_cpu(notif->consec_missed_beacons);
+	u32 missed_bcon_since_rx =
+		le32_to_cpu(notif->consec_missed_beacons_since_last_rx);
+	u32 scnd_lnk_bcn_lost =
+		le32_to_cpu(notif->consec_missed_beacons_other_link);
+	struct ieee80211_bss_conf *link_conf =
+		iwl_mld_fw_id_to_link_conf(mld, link_id);
+	u32 bss_param_ch_cnt_link_id;
+	struct ieee80211_vif *vif;
+
+	if (WARN_ON(!link_conf))
+		return;
+
+	vif = link_conf->vif;
+	bss_param_ch_cnt_link_id = link_conf->bss_param_ch_cnt_link_id;
+
+	IWL_DEBUG_INFO(mld,
+		       "missed bcn link_id=%u, %u consecutive=%u\n",
+		       link_id, missed_bcon, missed_bcon_since_rx);
+
+	if (WARN_ON(!vif))
+		return;
+
+	mld->trans->dbg.dump_file_name_ext_valid = true;
+	snprintf(mld->trans->dbg.dump_file_name_ext, IWL_FW_INI_MAX_NAME,
+		 "LinkId_%d_MacType_%d", link_id,
+		 iwl_mld_mac80211_iftype_to_fw(vif));
+
+	iwl_dbg_tlv_time_point(&mld->fwrt,
+			       IWL_FW_INI_TIME_POINT_MISSED_BEACONS, &tp_data);
+
+	if (missed_bcon >= IWL_MLD_MISSED_BEACONS_THRESHOLD_LONG) {
+		if (missed_bcon_since_rx >=
+		    IWL_MLD_MISSED_BEACONS_SINCE_RX_THOLD) {
+			ieee80211_connection_loss(vif);
+			return;
+		}
+		IWL_WARN(mld,
+			 "missed beacons exceeds threshold, but receiving data. Stay connected, Expect bugs.\n");
+		return;
+	}
+
+	if (missed_bcon_since_rx > IWL_MLD_MISSED_BEACONS_THRESHOLD) {
+		ieee80211_cqm_beacon_loss_notify(vif, GFP_ATOMIC);
+
+		/* try to switch links, no-op if we don't have MLO */
+		iwl_mld_trigger_link_selection(mld, vif);
+	}
+
+	/* no more logic if we're not in EMLSR */
+	if (hweight16(vif->active_links) <= 1)
+		return;
+
+	/* We are processing a notification before link activation */
+	if (le32_to_cpu(notif->other_link_id) == FW_CTXT_ID_INVALID)
+		return;
+
+	/* Exit EMLSR if we lost more than
+	 * IWL_MLD_MISSED_BEACONS_EXIT_ESR_THRESH beacons on boths links
+	 * OR more than IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH on current link.
+	 * OR more than IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_BSS_PARAM_CHANGED
+	 * on current link and the link's bss_param_ch_count has changed on
+	 * the other link's beacon.
+	 */
+	if ((missed_bcon >= IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS &&
+	     scnd_lnk_bcn_lost >= IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_2_LINKS) ||
+	    missed_bcon >= IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH ||
+	    (bss_param_ch_cnt_link_id != link_id &&
+	     missed_bcon >=
+	     IWL_MLD_BCN_LOSS_EXIT_ESR_THRESH_BSS_PARAM_CHANGED)) {
+		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_MISSED_BEACON,
+				   iwl_mld_get_primary_link(vif));
+	}
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_handle_missed_beacon_notif);
+
+bool iwl_mld_cancel_missed_beacon_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt,
+					u32 removed_link_id)
+{
+	struct iwl_missed_beacons_notif *notif = (void *)pkt->data;
+
+	if (le32_to_cpu(notif->other_link_id) == removed_link_id) {
+		/* Second link is being removed. Don't cancel the notification,
+		 * but mark second link as invalid.
+		 */
+		notif->other_link_id = cpu_to_le32(FW_CTXT_ID_INVALID);
+	}
+
+	/* If the primary link is removed, cancel the notification */
+	return le32_to_cpu(notif->link_id) == removed_link_id;
+}
+
+int iwl_mld_link_set_associated(struct iwl_mld *mld, struct ieee80211_vif *vif,
+				struct ieee80211_bss_conf *link)
+{
+	return iwl_mld_change_link_in_fw(mld, link, LINK_CONTEXT_MODIFY_ALL &
+					 ~(LINK_CONTEXT_MODIFY_ACTIVE |
+					   LINK_CONTEXT_MODIFY_EHT_PARAMS));
+}
+
+struct iwl_mld_rssi_to_grade {
+	s8 rssi[2];
+	u16 grade;
+};
+
+#define RSSI_TO_GRADE_LINE(_lb, _hb_uhb, _grade) \
+	{ \
+		.rssi = {_lb, _hb_uhb}, \
+		.grade = _grade \
+	}
+
+/*
+ * This array must be sorted by increasing RSSI for proper functionality.
+ * The grades are actually estimated throughput, represented as fixed-point
+ * with a scale factor of 1/10.
+ */
+static const struct iwl_mld_rssi_to_grade rssi_to_grade_map[] = {
+	RSSI_TO_GRADE_LINE(-85, -89, 172),
+	RSSI_TO_GRADE_LINE(-83, -86, 344),
+	RSSI_TO_GRADE_LINE(-82, -85, 516),
+	RSSI_TO_GRADE_LINE(-80, -83, 688),
+	RSSI_TO_GRADE_LINE(-77, -79, 1032),
+	RSSI_TO_GRADE_LINE(-73, -76, 1376),
+	RSSI_TO_GRADE_LINE(-70, -74, 1548),
+	RSSI_TO_GRADE_LINE(-69, -72, 1720),
+	RSSI_TO_GRADE_LINE(-65, -68, 2064),
+	RSSI_TO_GRADE_LINE(-61, -66, 2294),
+	RSSI_TO_GRADE_LINE(-58, -61, 2580),
+	RSSI_TO_GRADE_LINE(-55, -58, 2868),
+	RSSI_TO_GRADE_LINE(-46, -55, 3098),
+	RSSI_TO_GRADE_LINE(-43, -54, 3442)
+};
+
+#define MAX_GRADE (rssi_to_grade_map[ARRAY_SIZE(rssi_to_grade_map) - 1].grade)
+
+#define DEFAULT_CHAN_LOAD_2GHZ	30
+#define DEFAULT_CHAN_LOAD_5GHZ	15
+#define DEFAULT_CHAN_LOAD_6GHZ	0
+
+/* Factors calculation is done with fixed-point with a scaling factor of 1/256 */
+#define SCALE_FACTOR 256
+#define MAX_CHAN_LOAD 256
+
+static unsigned int
+iwl_mld_get_n_subchannels(const struct ieee80211_bss_conf *link_conf)
+{
+	enum nl80211_chan_width chan_width =
+		link_conf->chanreq.oper.width;
+	int mhz = nl80211_chan_width_to_mhz(chan_width);
+	unsigned int n_subchannels;
+
+	if (WARN_ONCE(mhz < 20 || mhz > 320,
+		      "Invalid channel width : (%d)\n", mhz))
+		return 1;
+
+	/* total number of subchannels */
+	n_subchannels = mhz / 20;
+
+	/* No puncturing if less than 80 MHz */
+	if (mhz >= 80)
+		n_subchannels -= hweight16(link_conf->chanreq.oper.punctured);
+
+	return n_subchannels;
+}
+
+static int
+iwl_mld_get_chan_load_from_element(struct iwl_mld *mld,
+				   struct ieee80211_bss_conf *link_conf)
+{
+	struct ieee80211_vif *vif = link_conf->vif;
+	const struct cfg80211_bss_ies *ies;
+	const struct element *bss_load_elem = NULL;
+	const struct ieee80211_bss_load_elem *bss_load;
+
+	guard(rcu)();
+
+	if (ieee80211_vif_link_active(vif, link_conf->link_id))
+		ies = rcu_dereference(link_conf->bss->beacon_ies);
+	else
+		ies = rcu_dereference(link_conf->bss->ies);
+
+	if (ies)
+		bss_load_elem = cfg80211_find_elem(WLAN_EID_QBSS_LOAD,
+						   ies->data, ies->len);
+
+	if (!bss_load_elem ||
+	    bss_load_elem->datalen != sizeof(*bss_load))
+		return -EINVAL;
+
+	bss_load = (const void *)bss_load_elem->data;
+
+	return bss_load->channel_util;
+}
+
+static unsigned int
+iwl_mld_get_chan_load_by_us(struct iwl_mld *mld,
+			    struct ieee80211_bss_conf *link_conf,
+			    bool expect_active_link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link_conf);
+	struct ieee80211_chanctx_conf *chan_ctx;
+	struct iwl_mld_phy *phy;
+
+	if (!mld_link || !mld_link->active) {
+		WARN_ON(expect_active_link);
+		return 0;
+	}
+
+	if (WARN_ONCE(!rcu_access_pointer(mld_link->chan_ctx),
+		      "Active link (%u) without channel ctxt assigned!\n",
+		      link_conf->link_id))
+		return 0;
+
+	chan_ctx = wiphy_dereference(mld->wiphy, mld_link->chan_ctx);
+	phy = iwl_mld_phy_from_mac80211(chan_ctx);
+
+	return phy->channel_load_by_us;
+}
+
+/* Returns error if the channel utilization element is invalid/unavailable */
+int iwl_mld_get_chan_load_by_others(struct iwl_mld *mld,
+				    struct ieee80211_bss_conf *link_conf,
+				    bool expect_active_link)
+{
+	int chan_load;
+	unsigned int chan_load_by_us;
+
+	/* get overall load */
+	chan_load = iwl_mld_get_chan_load_from_element(mld, link_conf);
+	if (chan_load < 0)
+		return chan_load;
+
+	chan_load_by_us = iwl_mld_get_chan_load_by_us(mld, link_conf,
+						      expect_active_link);
+
+	/* channel load by us is given in percentage */
+	chan_load_by_us =
+		NORMALIZE_PERCENT_TO_255(chan_load_by_us);
+
+	/* Use only values that firmware sends that can possibly be valid */
+	if (chan_load_by_us <= chan_load)
+		chan_load -= chan_load_by_us;
+
+	return chan_load;
+}
+
+static unsigned int
+iwl_mld_get_default_chan_load(struct ieee80211_bss_conf *link_conf)
+{
+	enum nl80211_band band = link_conf->chanreq.oper.chan->band;
+
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		return DEFAULT_CHAN_LOAD_2GHZ;
+	case NL80211_BAND_5GHZ:
+		return DEFAULT_CHAN_LOAD_5GHZ;
+	case NL80211_BAND_6GHZ:
+		return DEFAULT_CHAN_LOAD_6GHZ;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+unsigned int iwl_mld_get_chan_load(struct iwl_mld *mld,
+				   struct ieee80211_bss_conf *link_conf)
+{
+	int chan_load;
+
+	chan_load = iwl_mld_get_chan_load_by_others(mld, link_conf, false);
+	if (chan_load >= 0)
+		return chan_load;
+
+	/* No information from the element, take the defaults */
+	chan_load = iwl_mld_get_default_chan_load(link_conf);
+
+	/* The defaults are given in percentage */
+	return NORMALIZE_PERCENT_TO_255(chan_load);
+}
+
+static unsigned int
+iwl_mld_get_avail_chan_load(struct iwl_mld *mld,
+			    struct ieee80211_bss_conf *link_conf)
+{
+	return MAX_CHAN_LOAD - iwl_mld_get_chan_load(mld, link_conf);
+}
+
+/* This function calculates the grade of a link. Returns 0 in error case */
+unsigned int iwl_mld_get_link_grade(struct iwl_mld *mld,
+				    struct ieee80211_bss_conf *link_conf)
+{
+	enum nl80211_band band;
+	int rssi_idx;
+	s32 link_rssi;
+	unsigned int grade = MAX_GRADE;
+
+	if (WARN_ON_ONCE(!link_conf))
+		return 0;
+
+	band = link_conf->chanreq.oper.chan->band;
+	if (WARN_ONCE(band != NL80211_BAND_2GHZ &&
+		      band != NL80211_BAND_5GHZ &&
+		      band != NL80211_BAND_6GHZ,
+		      "Invalid band (%u)\n", band))
+		return 0;
+
+	link_rssi = MBM_TO_DBM(link_conf->bss->signal);
+	/*
+	 * For 6 GHz the RSSI of the beacons is lower than
+	 * the RSSI of the data.
+	 */
+	if (band == NL80211_BAND_6GHZ && link_rssi)
+		link_rssi += 4;
+
+	rssi_idx = band == NL80211_BAND_2GHZ ? 0 : 1;
+
+	/* No valid RSSI - take the lowest grade */
+	if (!link_rssi)
+		link_rssi = rssi_to_grade_map[0].rssi[rssi_idx];
+
+	IWL_DEBUG_EHT(mld,
+		      "Calculating grade of link %d: band = %d, bandwidth = %d, punctured subchannels =0x%x RSSI = %d\n",
+		      link_conf->link_id, band,
+		      link_conf->chanreq.oper.width,
+		      link_conf->chanreq.oper.punctured, link_rssi);
+
+	/* Get grade based on RSSI */
+	for (int i = 0; i < ARRAY_SIZE(rssi_to_grade_map); i++) {
+		const struct iwl_mld_rssi_to_grade *line =
+			&rssi_to_grade_map[i];
+
+		if (link_rssi > line->rssi[rssi_idx])
+			continue;
+		grade = line->grade;
+		break;
+	}
+
+	/* Apply the channel load and puncturing factors */
+	grade = grade * iwl_mld_get_avail_chan_load(mld, link_conf) / SCALE_FACTOR;
+	grade = grade * iwl_mld_get_n_subchannels(link_conf);
+
+	IWL_DEBUG_EHT(mld, "Link %d's grade: %d\n", link_conf->link_id, grade);
+
+	return grade;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_get_link_grade);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.h b/drivers/net/wireless/intel/iwlwifi/mld/link.h
new file mode 100644
index 0000000000000..3a4f3ac990d7e
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.h
@@ -0,0 +1,153 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_link_h__
+#define __iwl_mld_link_h__
+
+#include <net/mac80211.h>
+
+#include "mld.h"
+#include "sta.h"
+
+/**
+ * struct iwl_probe_resp_data - data for NoA/CSA updates
+ * @rcu_head: used for freeing the data on update
+ * @notif: notification data
+ * @noa_len: length of NoA attribute, calculated from the notification
+ */
+struct iwl_probe_resp_data {
+	struct rcu_head rcu_head;
+	struct iwl_probe_resp_data_notif notif;
+	int noa_len;
+};
+
+/**
+ * struct iwl_mld_link - link configuration parameters
+ *
+ * @rcu_head: RCU head for freeing this data.
+ * @fw_id: the fw id of the link.
+ * @active: if the link is active or not.
+ * @queue_params: QoS data from mac80211. This is updated with a call to
+ *	drv_conf_tx per each AC, and then notified once with BSS_CHANGED_QOS.
+ *	So we store it here and then send one link cmd for all the ACs.
+ * @chan_ctx: pointer to the channel context assigned to the link. If a link
+ *	has an assigned channel context it means that it is active.
+ * @he_ru_2mhz_block: 26-tone RU OFDMA transmissions should be blocked.
+ * @igtk: fw can only have one IGTK at a time, whereas mac80211 can have two.
+ *	This tracks the one IGTK that currently exists in FW.
+ * @vif: the vif this link belongs to
+ * @bcast_sta: station used for broadcast packets. Used in AP, GO and IBSS.
+ * @mcast_sta: station used for multicast packets. Used in AP, GO and IBSS.
+ * @aux_sta: station used for remain on channel. Used in P2P device.
+ * @link_id: over the air link ID
+ * @ap_early_keys: The firmware cannot install keys before bcast/mcast STAs,
+ *	but higher layers work differently, so we store the keys here for
+ *	later installation.
+ * @silent_deactivation: next deactivation needs to be silent.
+ * @probe_resp_data: data from FW notification to store NOA related data to be
+ *	inserted into probe response.
+ * @rx_omi: data for BW reduction with OMI
+ * @rx_omi.bw_in_progress: update is in progress (indicates target BW)
+ * @rx_omi.exit_ts: timestamp of last exit
+ * @rx_omi.finished_work: work for the delayed reaction to the firmware saying
+ *	the change was applied, and for then applying a new mode if it was
+ *	updated while waiting for firmware/AP settle delay.
+ * @rx_omi.desired_bw: desired bandwidth
+ * @rx_omi.last_max_bw: last maximum BW used by firmware, for AP BW changes
+ */
+struct iwl_mld_link {
+	struct rcu_head rcu_head;
+
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		u8 fw_id;
+		bool active;
+		struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];
+		struct ieee80211_chanctx_conf __rcu *chan_ctx;
+		bool he_ru_2mhz_block;
+		struct ieee80211_key_conf *igtk;
+	);
+	/* And here fields that survive a fw restart */
+	struct ieee80211_vif *vif;
+	struct iwl_mld_int_sta bcast_sta;
+	struct iwl_mld_int_sta mcast_sta;
+	struct iwl_mld_int_sta aux_sta;
+	u8 link_id;
+
+	struct {
+		struct wiphy_delayed_work finished_work;
+		unsigned long exit_ts;
+		enum ieee80211_sta_rx_bandwidth bw_in_progress,
+						desired_bw,
+						last_max_bw;
+	} rx_omi;
+
+	/* we can only have 2 GTK + 2 IGTK + 2 BIGTK active at a time */
+	struct ieee80211_key_conf *ap_early_keys[6];
+	bool silent_deactivation;
+	struct iwl_probe_resp_data __rcu *probe_resp_data;
+};
+
+/* Cleanup function for struct iwl_mld_phy, will be called in restart */
+static inline void
+iwl_mld_cleanup_link(struct iwl_mld *mld, struct iwl_mld_link *link)
+{
+	struct iwl_probe_resp_data *probe_data;
+
+	probe_data = wiphy_dereference(mld->wiphy, link->probe_resp_data);
+	RCU_INIT_POINTER(link->probe_resp_data, NULL);
+	if (probe_data)
+		kfree_rcu(probe_data, rcu_head);
+
+	CLEANUP_STRUCT(link);
+	if (link->bcast_sta.sta_id != IWL_INVALID_STA)
+		iwl_mld_free_internal_sta(mld, &link->bcast_sta);
+	if (link->mcast_sta.sta_id != IWL_INVALID_STA)
+		iwl_mld_free_internal_sta(mld, &link->mcast_sta);
+	if (link->aux_sta.sta_id != IWL_INVALID_STA)
+		iwl_mld_free_internal_sta(mld, &link->aux_sta);
+}
+
+/* Convert a percentage from [0,100] to [0,255] */
+#define NORMALIZE_PERCENT_TO_255(percentage) ((percentage) * 256 / 100)
+
+int iwl_mld_add_link(struct iwl_mld *mld,
+		     struct ieee80211_bss_conf *bss_conf);
+int iwl_mld_remove_link(struct iwl_mld *mld,
+			struct ieee80211_bss_conf *bss_conf);
+int iwl_mld_activate_link(struct iwl_mld *mld,
+			  struct ieee80211_bss_conf *link);
+void iwl_mld_deactivate_link(struct iwl_mld *mld,
+			     struct ieee80211_bss_conf *link);
+int iwl_mld_change_link_omi_bw(struct iwl_mld *mld,
+			       struct ieee80211_bss_conf *link,
+			       enum ieee80211_sta_rx_bandwidth bw);
+int iwl_mld_change_link_in_fw(struct iwl_mld *mld,
+			      struct ieee80211_bss_conf *link, u32 changes);
+void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt);
+bool iwl_mld_cancel_missed_beacon_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt,
+					u32 removed_link_id);
+int iwl_mld_link_set_associated(struct iwl_mld *mld, struct ieee80211_vif *vif,
+				struct ieee80211_bss_conf *link);
+
+unsigned int iwl_mld_get_link_grade(struct iwl_mld *mld,
+				    struct ieee80211_bss_conf *link_conf);
+
+unsigned int iwl_mld_get_chan_load(struct iwl_mld *mld,
+				   struct ieee80211_bss_conf *link_conf);
+
+int iwl_mld_get_chan_load_by_others(struct iwl_mld *mld,
+				    struct ieee80211_bss_conf *link_conf,
+				    bool expect_active_link);
+void iwl_mld_handle_omi_status_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt);
+void iwl_mld_leave_omi_bw_reduction(struct iwl_mld *mld);
+void iwl_mld_check_omi_bw_reduction(struct iwl_mld *mld);
+void iwl_mld_omi_ap_changed_bw(struct iwl_mld *mld,
+			       struct ieee80211_bss_conf *link_conf,
+			       enum ieee80211_sta_rx_bandwidth bw);
+
+#endif /* __iwl_mld_link_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
new file mode 100644
index 0000000000000..439fc10a4a412
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
@@ -0,0 +1,335 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include "mld.h"
+#include "iface.h"
+#include "low_latency.h"
+#include "hcmd.h"
+#include "power.h"
+
+#define MLD_LL_WK_INTERVAL_MSEC 500
+#define MLD_LL_PERIOD (HZ * MLD_LL_WK_INTERVAL_MSEC / 1000)
+#define MLD_LL_ACTIVE_WK_PERIOD (HZ * 10)
+
+/* packets/MLD_LL_WK_PERIOD seconds */
+#define MLD_LL_ENABLE_THRESH 100
+
+static bool iwl_mld_calc_low_latency(struct iwl_mld *mld,
+				     unsigned long timestamp)
+{
+	struct iwl_mld_low_latency *ll = &mld->low_latency;
+	bool global_low_latency = false;
+	u8 num_rx_q = mld->trans->num_rx_queues;
+
+	for (int mac_id = 0; mac_id < NUM_MAC_INDEX_DRIVER; mac_id++) {
+		u32 total_vo_vi_pkts = 0;
+		bool ll_period_expired;
+
+		/* If it's not initialized yet, it means we have not yet
+		 * received/transmitted any vo/vi packet on this MAC.
+		 */
+		if (!ll->window_start[mac_id])
+			continue;
+
+		ll_period_expired =
+			time_after(timestamp, ll->window_start[mac_id] +
+				   MLD_LL_ACTIVE_WK_PERIOD);
+
+		if (ll_period_expired)
+			ll->window_start[mac_id] = timestamp;
+
+		for (int q = 0; q < num_rx_q; q++) {
+			struct iwl_mld_low_latency_packets_counters *counters =
+				&mld->low_latency.pkts_counters[q];
+
+			spin_lock_bh(&counters->lock);
+
+			total_vo_vi_pkts += counters->vo_vi[mac_id];
+
+			if (ll_period_expired)
+				counters->vo_vi[mac_id] = 0;
+
+			spin_unlock_bh(&counters->lock);
+		}
+
+		/* enable immediately with enough packets but defer
+		 * disabling only if the low-latency period expired and
+		 * below threshold.
+		 */
+		if (total_vo_vi_pkts > MLD_LL_ENABLE_THRESH)
+			mld->low_latency.result[mac_id] = true;
+		else if (ll_period_expired)
+			mld->low_latency.result[mac_id] = false;
+
+		global_low_latency |= mld->low_latency.result[mac_id];
+	}
+
+	return global_low_latency;
+}
+
+static void iwl_mld_low_latency_iter(void *_data, u8 *mac,
+				     struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = _data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	bool prev = mld_vif->low_latency_causes & LOW_LATENCY_TRAFFIC;
+	bool low_latency;
+
+	if (WARN_ON(mld_vif->fw_id >= ARRAY_SIZE(mld->low_latency.result)))
+		return;
+
+	low_latency = mld->low_latency.result[mld_vif->fw_id];
+
+	if (prev != low_latency)
+		iwl_mld_vif_update_low_latency(mld, vif, low_latency,
+					       LOW_LATENCY_TRAFFIC);
+}
+
+static void iwl_mld_low_latency_wk(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld *mld = container_of(wk, struct iwl_mld,
+					   low_latency.work.work);
+	unsigned long timestamp = jiffies;
+	bool low_latency_active;
+
+	if (mld->fw_status.in_hw_restart)
+		return;
+
+	/* It is assumed that the work was scheduled only after checking
+	 * at least MLD_LL_PERIOD has passed since the last update.
+	 */
+
+	low_latency_active = iwl_mld_calc_low_latency(mld, timestamp);
+
+	/* Update the timestamp now after the low-latency calculation */
+	mld->low_latency.timestamp = timestamp;
+
+	/* If low-latency is active we need to force re-evaluation after
+	 * 10 seconds, so that we can disable low-latency when
+	 * the low-latency traffic ends.
+	 *
+	 * Otherwise, we don't need to run the work because there is nothing to
+	 * disable.
+	 *
+	 * Note that this has no impact on the regular scheduling of the
+	 * updates triggered by traffic - those happen whenever the
+	 * MLD_LL_PERIOD timeout expire.
+	 */
+	if (low_latency_active)
+		wiphy_delayed_work_queue(mld->wiphy, &mld->low_latency.work,
+					 MLD_LL_ACTIVE_WK_PERIOD);
+
+	ieee80211_iterate_active_interfaces(mld->hw,
+					    IEEE80211_IFACE_ITER_NORMAL,
+					    iwl_mld_low_latency_iter, mld);
+}
+
+int iwl_mld_low_latency_init(struct iwl_mld *mld)
+{
+	struct iwl_mld_low_latency *ll = &mld->low_latency;
+	unsigned long ts = jiffies;
+
+	ll->pkts_counters = kcalloc(mld->trans->num_rx_queues,
+				    sizeof(*ll->pkts_counters), GFP_KERNEL);
+	if (!ll->pkts_counters)
+		return -ENOMEM;
+
+	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+		spin_lock_init(&ll->pkts_counters[q].lock);
+
+	wiphy_delayed_work_init(&ll->work, iwl_mld_low_latency_wk);
+
+	ll->timestamp = ts;
+
+	/* The low-latency window_start will be initialized per-MAC on
+	 * the first vo/vi packet received/transmitted.
+	 */
+
+	return 0;
+}
+
+void iwl_mld_low_latency_free(struct iwl_mld *mld)
+{
+	struct iwl_mld_low_latency *ll = &mld->low_latency;
+
+	kfree(ll->pkts_counters);
+	ll->pkts_counters = NULL;
+}
+
+void iwl_mld_low_latency_restart_cleanup(struct iwl_mld *mld)
+{
+	struct iwl_mld_low_latency *ll = &mld->low_latency;
+
+	ll->timestamp = jiffies;
+
+	memset(ll->window_start, 0, sizeof(ll->window_start));
+	memset(ll->result, 0, sizeof(ll->result));
+
+	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+		memset(ll->pkts_counters[q].vo_vi, 0,
+		       sizeof(ll->pkts_counters[q].vo_vi));
+}
+
+static int iwl_mld_send_low_latency_cmd(struct iwl_mld *mld, bool low_latency,
+					u16 mac_id)
+{
+	struct iwl_mac_low_latency_cmd cmd = {
+		.mac_id = cpu_to_le32(mac_id)
+	};
+	u16 cmd_id = WIDE_ID(MAC_CONF_GROUP, LOW_LATENCY_CMD);
+	int ret;
+
+	if (low_latency) {
+		/* Currently we don't care about the direction */
+		cmd.low_latency_rx = 1;
+		cmd.low_latency_tx = 1;
+	}
+
+	ret = iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to send low latency command\n");
+
+	return ret;
+}
+
+static void iwl_mld_vif_set_low_latency(struct iwl_mld_vif *mld_vif, bool set,
+					enum iwl_mld_low_latency_cause cause)
+{
+	if (set)
+		mld_vif->low_latency_causes |= cause;
+	else
+		mld_vif->low_latency_causes &= ~cause;
+}
+
+void iwl_mld_vif_update_low_latency(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif,
+				    bool low_latency,
+				    enum iwl_mld_low_latency_cause cause)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	bool prev;
+
+	prev = iwl_mld_vif_low_latency(mld_vif);
+	iwl_mld_vif_set_low_latency(mld_vif, low_latency, cause);
+
+	low_latency = iwl_mld_vif_low_latency(mld_vif);
+	if (low_latency == prev)
+		return;
+
+	if (iwl_mld_send_low_latency_cmd(mld, low_latency, mld_vif->fw_id)) {
+		/* revert to previous low-latency state */
+		iwl_mld_vif_set_low_latency(mld_vif, prev, cause);
+		return;
+	}
+
+	if (low_latency)
+		iwl_mld_leave_omi_bw_reduction(mld);
+
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_P2P_CLIENT)
+		return;
+
+	iwl_mld_update_mac_power(mld, vif, false);
+}
+
+static bool iwl_mld_is_vo_vi_pkt(struct ieee80211_hdr *hdr)
+{
+	u8 tid;
+	static const u8 tid_to_mac80211_ac[] = {
+		IEEE80211_AC_BE,
+		IEEE80211_AC_BK,
+		IEEE80211_AC_BK,
+		IEEE80211_AC_BE,
+		IEEE80211_AC_VI,
+		IEEE80211_AC_VI,
+		IEEE80211_AC_VO,
+		IEEE80211_AC_VO,
+	};
+
+	if (!hdr || !ieee80211_is_data_qos(hdr->frame_control))
+		return false;
+
+	tid = ieee80211_get_tid(hdr);
+	if (tid >= IWL_MAX_TID_COUNT)
+		return false;
+
+	return tid_to_mac80211_ac[tid] < IEEE80211_AC_VI;
+}
+
+void iwl_mld_low_latency_update_counters(struct iwl_mld *mld,
+					 struct ieee80211_hdr *hdr,
+					 struct ieee80211_sta *sta,
+					 u8 queue)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(mld_sta->vif);
+	struct iwl_mld_low_latency_packets_counters *counters;
+	unsigned long ts = jiffies ? jiffies : 1;
+	u8 fw_id = mld_vif->fw_id;
+
+	/* we should have failed op mode init if NULL */
+	if (WARN_ON_ONCE(!mld->low_latency.pkts_counters))
+		return;
+
+	if (WARN_ON_ONCE(fw_id >= ARRAY_SIZE(counters->vo_vi) ||
+			 queue >= mld->trans->num_rx_queues))
+		return;
+
+	if (mld->low_latency.stopped)
+		return;
+
+	if (!iwl_mld_is_vo_vi_pkt(hdr))
+		return;
+
+	counters = &mld->low_latency.pkts_counters[queue];
+
+	spin_lock_bh(&counters->lock);
+	counters->vo_vi[fw_id]++;
+	spin_unlock_bh(&counters->lock);
+
+	/* Initialize the window_start on the first vo/vi packet */
+	if (!mld->low_latency.window_start[fw_id])
+		mld->low_latency.window_start[fw_id] = ts;
+
+	if (time_is_before_jiffies(mld->low_latency.timestamp + MLD_LL_PERIOD))
+		wiphy_delayed_work_queue(mld->wiphy, &mld->low_latency.work,
+					 0);
+}
+
+void iwl_mld_low_latency_stop(struct iwl_mld *mld)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	mld->low_latency.stopped = true;
+
+	wiphy_delayed_work_cancel(mld->wiphy, &mld->low_latency.work);
+}
+
+void iwl_mld_low_latency_restart(struct iwl_mld *mld)
+{
+	struct iwl_mld_low_latency *ll = &mld->low_latency;
+	bool low_latency = false;
+	unsigned long ts = jiffies;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ll->timestamp = ts;
+	mld->low_latency.stopped = false;
+
+	for (int mac = 0; mac < NUM_MAC_INDEX_DRIVER; mac++) {
+		ll->window_start[mac] = 0;
+		low_latency |= ll->result[mac];
+
+		for (int q = 0; q < mld->trans->num_rx_queues; q++) {
+			spin_lock_bh(&ll->pkts_counters[q].lock);
+			ll->pkts_counters[q].vo_vi[mac] = 0;
+			spin_unlock_bh(&ll->pkts_counters[q].lock);
+		}
+	}
+
+	/* if low latency is active, force re-evaluation to cover the case of
+	 * no traffic.
+	 */
+	if (low_latency)
+		wiphy_delayed_work_queue(mld->wiphy, &ll->work, MLD_LL_PERIOD);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.h b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.h
new file mode 100644
index 0000000000000..f59684d235af1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_low_latency_h__
+#define __iwl_mld_low_latency_h__
+
+/**
+ * struct iwl_mld_low_latency_packets_counters - Packets counters
+ * @lock: synchronize the counting in data path against the worker
+ * @vo_vi: per-mac, counts the number of TX and RX voice and video packets
+ */
+struct iwl_mld_low_latency_packets_counters {
+	spinlock_t lock;
+	u32 vo_vi[NUM_MAC_INDEX_DRIVER];
+} ____cacheline_aligned_in_smp;
+
+/**
+ * enum iwl_mld_low_latency_cause - low-latency set causes
+ *
+ * @LOW_LATENCY_TRAFFIC: indicates low-latency traffic was detected
+ * @LOW_LATENCY_DEBUGFS: low-latency mode set from debugfs
+ * @LOW_LATENCY_VIF_TYPE: low-latency mode set because of vif type (AP)
+ */
+enum iwl_mld_low_latency_cause {
+	LOW_LATENCY_TRAFFIC	= BIT(0),
+	LOW_LATENCY_DEBUGFS	= BIT(1),
+	LOW_LATENCY_VIF_TYPE	= BIT(2),
+};
+
+/**
+ * struct iwl_mld_low_latency - Manage low-latency detection and activation.
+ * @work: this work is used to detect low-latency by monitoring the number of
+ *	voice and video packets transmitted in a period of time. If the
+ *	threshold is reached, low-latency is activated. When active,
+ *	it is deactivated if the threshold is not reached within a
+ *	10-second period.
+ * @timestamp: timestamp of the last update.
+ * @window_start: per-mac, timestamp of the start of the current window. when
+ *	the window is over, the counters are reset.
+ * @pkts_counters: per-queue array voice/video packet counters
+ * @result: per-mac latest low-latency result
+ * @stopped: if true, ignore the requests to update the counters
+ */
+struct iwl_mld_low_latency {
+	struct wiphy_delayed_work work;
+	unsigned long timestamp;
+	unsigned long window_start[NUM_MAC_INDEX_DRIVER];
+	struct iwl_mld_low_latency_packets_counters *pkts_counters;
+	bool result[NUM_MAC_INDEX_DRIVER];
+	bool stopped;
+};
+
+int iwl_mld_low_latency_init(struct iwl_mld *mld);
+void iwl_mld_low_latency_free(struct iwl_mld *mld);
+void iwl_mld_low_latency_restart_cleanup(struct iwl_mld *mld);
+void iwl_mld_vif_update_low_latency(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif,
+				    bool low_latency,
+				    enum iwl_mld_low_latency_cause cause);
+void iwl_mld_low_latency_update_counters(struct iwl_mld *mld,
+					 struct ieee80211_hdr *hdr,
+					 struct ieee80211_sta *sta,
+					 u8 queue);
+void iwl_mld_low_latency_stop(struct iwl_mld *mld);
+void iwl_mld_low_latency_restart(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_low_latency_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
new file mode 100644
index 0000000000000..d73bd0179f7dc
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -0,0 +1,2671 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <net/mac80211.h>
+#include <linux/ip.h>
+
+#include "mld.h"
+#include "mac80211.h"
+#include "phy.h"
+#include "iface.h"
+#include "power.h"
+#include "sta.h"
+#include "agg.h"
+#include "scan.h"
+#include "d3.h"
+#include "tlc.h"
+#include "key.h"
+#include "ap.h"
+#include "tx.h"
+#include "roc.h"
+#include "mlo.h"
+#include "stats.h"
+#include "ftm-initiator.h"
+#include "low_latency.h"
+#include "fw/api/scan.h"
+#include "fw/api/context.h"
+#include "fw/api/filter.h"
+#include "fw/api/sta.h"
+#include "fw/api/tdls.h"
+#ifdef CONFIG_PM_SLEEP
+#include "fw/api/d3.h"
+#endif /* CONFIG_PM_SLEEP */
+#include "iwl-trans.h"
+
+#define IWL_MLD_LIMITS(ap)					\
+	{							\
+		.max = 2,					\
+		.types = BIT(NL80211_IFTYPE_STATION),		\
+	},							\
+	{							\
+		.max = 1,					\
+		.types = ap |					\
+			 BIT(NL80211_IFTYPE_P2P_CLIENT) |	\
+			 BIT(NL80211_IFTYPE_P2P_GO),		\
+	},							\
+	{							\
+		.max = 1,					\
+		.types = BIT(NL80211_IFTYPE_P2P_DEVICE),	\
+	}
+
+static const struct ieee80211_iface_limit iwl_mld_limits[] = {
+	IWL_MLD_LIMITS(0)
+};
+
+static const struct ieee80211_iface_limit iwl_mld_limits_ap[] = {
+	IWL_MLD_LIMITS(BIT(NL80211_IFTYPE_AP))
+};
+
+static const struct ieee80211_iface_combination
+iwl_mld_iface_combinations[] = {
+	{
+		.num_different_channels = 2,
+		.max_interfaces = 4,
+		.limits = iwl_mld_limits,
+		.n_limits = ARRAY_SIZE(iwl_mld_limits),
+	},
+	{
+		.num_different_channels = 1,
+		.max_interfaces = 4,
+		.limits = iwl_mld_limits_ap,
+		.n_limits = ARRAY_SIZE(iwl_mld_limits_ap),
+	},
+};
+
+static const u8 if_types_ext_capa_sta[] = {
+	 [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
+	 [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
+	 [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF |
+	       WLAN_EXT_CAPA8_MAX_MSDU_IN_AMSDU_LSB,
+	 [8] = WLAN_EXT_CAPA9_MAX_MSDU_IN_AMSDU_MSB,
+	 [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT,
+};
+
+#define IWL_MLD_EMLSR_CAPA	(IEEE80211_EML_CAP_EMLSR_SUPP | \
+				 IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US << \
+					__bf_shf(IEEE80211_EML_CAP_EMLSR_PADDING_DELAY) | \
+				 IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US << \
+					__bf_shf(IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY))
+#define IWL_MLD_CAPA_OPS (FIELD_PREP_CONST( \
+			IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP, \
+			IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME) | \
+			IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT)
+
+static const struct wiphy_iftype_ext_capab iftypes_ext_capa[] = {
+	{
+		.iftype = NL80211_IFTYPE_STATION,
+		.extended_capabilities = if_types_ext_capa_sta,
+		.extended_capabilities_mask = if_types_ext_capa_sta,
+		.extended_capabilities_len = sizeof(if_types_ext_capa_sta),
+		/* relevant only if EHT is supported */
+		.eml_capabilities = IWL_MLD_EMLSR_CAPA,
+		.mld_capa_and_ops = IWL_MLD_CAPA_OPS,
+	},
+};
+
+static void iwl_mld_hw_set_addresses(struct iwl_mld *mld)
+{
+	struct wiphy *wiphy = mld->wiphy;
+	int num_addrs = 1;
+
+	/* Extract MAC address */
+	memcpy(mld->addresses[0].addr, mld->nvm_data->hw_addr, ETH_ALEN);
+	wiphy->addresses = mld->addresses;
+	wiphy->n_addresses = 1;
+
+	/* Extract additional MAC addresses if available */
+	if (mld->nvm_data->n_hw_addrs > 1)
+		num_addrs = min(mld->nvm_data->n_hw_addrs,
+				IWL_MLD_MAX_ADDRESSES);
+
+	for (int i = 1; i < num_addrs; i++) {
+		memcpy(mld->addresses[i].addr,
+		       mld->addresses[i - 1].addr,
+		       ETH_ALEN);
+		mld->addresses[i].addr[ETH_ALEN - 1]++;
+		wiphy->n_addresses++;
+	}
+}
+
+static void iwl_mld_hw_set_channels(struct iwl_mld *mld)
+{
+	struct wiphy *wiphy = mld->wiphy;
+	struct ieee80211_supported_band *bands = mld->nvm_data->bands;
+
+	wiphy->bands[NL80211_BAND_2GHZ] = &bands[NL80211_BAND_2GHZ];
+	wiphy->bands[NL80211_BAND_5GHZ] = &bands[NL80211_BAND_5GHZ];
+
+	if (bands[NL80211_BAND_6GHZ].n_channels)
+		wiphy->bands[NL80211_BAND_6GHZ] = &bands[NL80211_BAND_6GHZ];
+}
+
+static void iwl_mld_hw_set_security(struct iwl_mld *mld)
+{
+	struct ieee80211_hw *hw = mld->hw;
+	static const u32 mld_ciphers[] = {
+		WLAN_CIPHER_SUITE_WEP40,
+		WLAN_CIPHER_SUITE_WEP104,
+		WLAN_CIPHER_SUITE_TKIP,
+		WLAN_CIPHER_SUITE_CCMP,
+		WLAN_CIPHER_SUITE_GCMP,
+		WLAN_CIPHER_SUITE_GCMP_256,
+		WLAN_CIPHER_SUITE_AES_CMAC,
+		WLAN_CIPHER_SUITE_BIP_GMAC_128,
+		WLAN_CIPHER_SUITE_BIP_GMAC_256
+	};
+
+	hw->wiphy->n_cipher_suites = ARRAY_SIZE(mld_ciphers);
+	hw->wiphy->cipher_suites = mld_ciphers;
+
+	ieee80211_hw_set(hw, MFP_CAPABLE);
+	wiphy_ext_feature_set(hw->wiphy,
+			      NL80211_EXT_FEATURE_BEACON_PROTECTION);
+}
+
+static void iwl_mld_hw_set_regulatory(struct iwl_mld *mld)
+{
+	struct wiphy *wiphy = mld->wiphy;
+
+	wiphy->regulatory_flags |= REGULATORY_WIPHY_SELF_MANAGED;
+	wiphy->regulatory_flags |= REGULATORY_ENABLE_RELAX_NO_IR;
+}
+
+static void iwl_mld_hw_set_antennas(struct iwl_mld *mld)
+{
+	struct wiphy *wiphy = mld->wiphy;
+
+	wiphy->available_antennas_tx = iwl_mld_get_valid_tx_ant(mld);
+	wiphy->available_antennas_rx = iwl_mld_get_valid_rx_ant(mld);
+}
+
+static void iwl_mld_hw_set_pm(struct iwl_mld *mld)
+{
+#ifdef CONFIG_PM_SLEEP
+	struct wiphy *wiphy = mld->wiphy;
+
+	if (!device_can_wakeup(mld->trans->dev))
+		return;
+
+	mld->wowlan.flags |= WIPHY_WOWLAN_MAGIC_PKT |
+			     WIPHY_WOWLAN_DISCONNECT |
+			     WIPHY_WOWLAN_EAP_IDENTITY_REQ |
+			     WIPHY_WOWLAN_RFKILL_RELEASE |
+			     WIPHY_WOWLAN_NET_DETECT |
+			     WIPHY_WOWLAN_SUPPORTS_GTK_REKEY |
+			     WIPHY_WOWLAN_GTK_REKEY_FAILURE |
+			     WIPHY_WOWLAN_4WAY_HANDSHAKE;
+
+	mld->wowlan.n_patterns = IWL_WOWLAN_MAX_PATTERNS;
+	mld->wowlan.pattern_min_len = IWL_WOWLAN_MIN_PATTERN_LEN;
+	mld->wowlan.pattern_max_len = IWL_WOWLAN_MAX_PATTERN_LEN;
+	mld->wowlan.max_nd_match_sets = IWL_SCAN_MAX_PROFILES_V2;
+
+	wiphy->wowlan = &mld->wowlan;
+#endif /* CONFIG_PM_SLEEP */
+}
+
+static void iwl_mac_hw_set_radiotap(struct iwl_mld *mld)
+{
+	struct ieee80211_hw *hw = mld->hw;
+
+	hw->radiotap_mcs_details |= IEEE80211_RADIOTAP_MCS_HAVE_FEC |
+				    IEEE80211_RADIOTAP_MCS_HAVE_STBC;
+
+	hw->radiotap_vht_details |= IEEE80211_RADIOTAP_VHT_KNOWN_STBC |
+				    IEEE80211_RADIOTAP_VHT_KNOWN_BEAMFORMED;
+
+	hw->radiotap_timestamp.units_pos =
+		IEEE80211_RADIOTAP_TIMESTAMP_UNIT_US |
+		IEEE80211_RADIOTAP_TIMESTAMP_SPOS_PLCP_SIG_ACQ;
+
+	/* this is the case for CCK frames, it's better (only 8) for OFDM */
+	hw->radiotap_timestamp.accuracy = 22;
+}
+
+static void iwl_mac_hw_set_flags(struct iwl_mld *mld)
+{
+	struct ieee80211_hw *hw = mld->hw;
+
+	ieee80211_hw_set(hw, USES_RSS);
+	ieee80211_hw_set(hw, HANDLES_QUIET_CSA);
+	ieee80211_hw_set(hw, AP_LINK_PS);
+	ieee80211_hw_set(hw, SIGNAL_DBM);
+	ieee80211_hw_set(hw, SPECTRUM_MGMT);
+	ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS);
+	ieee80211_hw_set(hw, WANT_MONITOR_VIF);
+	ieee80211_hw_set(hw, SUPPORTS_PS);
+	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
+	ieee80211_hw_set(hw, AMPDU_AGGREGATION);
+	ieee80211_hw_set(hw, CONNECTION_MONITOR);
+	ieee80211_hw_set(hw, CHANCTX_STA_CSA);
+	ieee80211_hw_set(hw, SUPPORT_FAST_XMIT);
+	ieee80211_hw_set(hw, SUPPORTS_CLONED_SKBS);
+	ieee80211_hw_set(hw, NEEDS_UNIQUE_STA_ADDR);
+	ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
+	ieee80211_hw_set(hw, BUFF_MMPDU_TXQ);
+	ieee80211_hw_set(hw, STA_MMPDU_TXQ);
+	ieee80211_hw_set(hw, TX_AMSDU);
+	ieee80211_hw_set(hw, TX_FRAG_LIST);
+	ieee80211_hw_set(hw, TX_AMPDU_SETUP_IN_HW);
+	ieee80211_hw_set(hw, HAS_RATE_CONTROL);
+	ieee80211_hw_set(hw, SUPPORTS_REORDERING_BUFFER);
+	ieee80211_hw_set(hw, DISALLOW_PUNCTURING_5GHZ);
+	ieee80211_hw_set(hw, SINGLE_SCAN_ON_ALL_BANDS);
+	ieee80211_hw_set(hw, SUPPORTS_AMSDU_IN_AMPDU);
+	ieee80211_hw_set(hw, TDLS_WIDER_BW);
+}
+
+static void iwl_mac_hw_set_wiphy(struct iwl_mld *mld)
+{
+	struct ieee80211_hw *hw = mld->hw;
+	struct wiphy *wiphy = hw->wiphy;
+	const struct iwl_ucode_capabilities *ucode_capa = &mld->fw->ucode_capa;
+
+	snprintf(wiphy->fw_version,
+		 sizeof(wiphy->fw_version),
+		 "%.31s", mld->fw->fw_version);
+
+	wiphy->interface_modes = BIT(NL80211_IFTYPE_STATION) |
+				 BIT(NL80211_IFTYPE_P2P_CLIENT) |
+				 BIT(NL80211_IFTYPE_AP) |
+				 BIT(NL80211_IFTYPE_P2P_GO) |
+				 BIT(NL80211_IFTYPE_P2P_DEVICE) |
+				 BIT(NL80211_IFTYPE_ADHOC);
+
+	wiphy->features |= NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR |
+			   NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR |
+			   NL80211_FEATURE_ND_RANDOM_MAC_ADDR |
+			   NL80211_FEATURE_HT_IBSS |
+			   NL80211_FEATURE_P2P_GO_CTWIN |
+			   NL80211_FEATURE_LOW_PRIORITY_SCAN |
+			   NL80211_FEATURE_P2P_GO_OPPPS |
+			   NL80211_FEATURE_AP_MODE_CHAN_WIDTH_CHANGE |
+			   NL80211_FEATURE_SUPPORTS_WMM_ADMISSION |
+			   NL80211_FEATURE_TX_POWER_INSERTION |
+			   NL80211_FEATURE_DS_PARAM_SET_IE_IN_PROBES;
+
+	wiphy->flags |= WIPHY_FLAG_IBSS_RSN |
+			WIPHY_FLAG_AP_UAPSD |
+			WIPHY_FLAG_HAS_CHANNEL_SWITCH |
+			WIPHY_FLAG_SPLIT_SCAN_6GHZ |
+			WIPHY_FLAG_SUPPORTS_TDLS |
+			WIPHY_FLAG_SUPPORTS_EXT_KEK_KCK;
+
+	if (mld->nvm_data->sku_cap_11be_enable &&
+	    !iwlwifi_mod_params.disable_11ax &&
+	    !iwlwifi_mod_params.disable_11be)
+		wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
+
+	/* the firmware uses u8 for num of iterations, but 0xff is saved for
+	 * infinite loop, so the maximum number of iterations is actually 254.
+	 */
+	wiphy->max_sched_scan_plan_iterations = 254;
+	wiphy->max_sched_scan_ie_len = iwl_mld_scan_max_template_size();
+	wiphy->max_scan_ie_len = iwl_mld_scan_max_template_size();
+	wiphy->max_sched_scan_ssids = PROBE_OPTION_MAX;
+	wiphy->max_scan_ssids = PROBE_OPTION_MAX;
+	wiphy->max_sched_scan_plans = IWL_MAX_SCHED_SCAN_PLANS;
+	wiphy->max_sched_scan_reqs = 1;
+	wiphy->max_sched_scan_plan_interval = U16_MAX;
+	wiphy->max_match_sets = IWL_SCAN_MAX_PROFILES_V2;
+
+	wiphy->max_remain_on_channel_duration = 10000;
+
+	wiphy->hw_version = mld->trans->hw_id;
+
+	wiphy->hw_timestamp_max_peers = 1;
+
+	wiphy->iface_combinations = iwl_mld_iface_combinations;
+	wiphy->n_iface_combinations = ARRAY_SIZE(iwl_mld_iface_combinations);
+
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_VHT_IBSS);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_DFS_CONCURRENT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BEACON_RATE_LEGACY);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SCAN_START_TIME);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_BSS_PARENT_TSF);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SCAN_MIN_PREQ_CONTENT);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_ACCEPT_BCAST_PROBE_RESP);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_FILS_MAX_CHANNEL_TIME);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_OCE_PROBE_REQ_HIGH_TX_RATE);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_MU_MIMO_AIR_SNIFFER);
+	wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_SPP_AMSDU_SUPPORT);
+
+	if (fw_has_capa(ucode_capa, IWL_UCODE_TLV_CAPA_PROTECTED_TWT))
+		wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_PROTECTED_TWT);
+
+	wiphy->iftype_ext_capab = NULL;
+	wiphy->num_iftype_ext_capab = 0;
+
+	if (!iwlwifi_mod_params.disable_11ax) {
+		wiphy->iftype_ext_capab = iftypes_ext_capa;
+		wiphy->num_iftype_ext_capab = ARRAY_SIZE(iftypes_ext_capa);
+
+		ieee80211_hw_set(hw, SUPPORTS_MULTI_BSSID);
+		ieee80211_hw_set(hw, SUPPORTS_ONLY_HE_MULTI_BSSID);
+	}
+
+	if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM)
+		wiphy->flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
+	else
+		wiphy->flags &= ~WIPHY_FLAG_PS_ON_BY_DEFAULT;
+}
+
+static void iwl_mac_hw_set_misc(struct iwl_mld *mld)
+{
+	struct ieee80211_hw *hw = mld->hw;
+
+	hw->queues = IEEE80211_NUM_ACS;
+
+	hw->netdev_features = NETIF_F_HIGHDMA | NETIF_F_SG;
+	hw->netdev_features |= mld->cfg->features;
+
+	hw->max_tx_fragments = mld->trans->max_skb_frags;
+	hw->max_listen_interval = IWL_MLD_CONN_LISTEN_INTERVAL;
+
+	hw->uapsd_max_sp_len = IEEE80211_WMM_IE_STA_QOSINFO_SP_ALL;
+	hw->uapsd_queues = IEEE80211_WMM_IE_STA_QOSINFO_AC_VO |
+			   IEEE80211_WMM_IE_STA_QOSINFO_AC_VI |
+			   IEEE80211_WMM_IE_STA_QOSINFO_AC_BK |
+			   IEEE80211_WMM_IE_STA_QOSINFO_AC_BE;
+
+	hw->chanctx_data_size = sizeof(struct iwl_mld_phy);
+	hw->vif_data_size = sizeof(struct iwl_mld_vif);
+	hw->sta_data_size = sizeof(struct iwl_mld_sta);
+	hw->txq_data_size = sizeof(struct iwl_mld_txq);
+
+	/* TODO: Remove this division when IEEE80211_MAX_AMPDU_BUF_EHT size
+	 * is supported.
+	 * Note: ensure that IWL_DEFAULT_QUEUE_SIZE_EHT is updated accordingly.
+	 */
+	hw->max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF_EHT / 2;
+}
+
+static int iwl_mld_hw_verify_preconditions(struct iwl_mld *mld)
+{
+	/* 11ax is expected to be enabled for all supported devices */
+	if (WARN_ON(!mld->nvm_data->sku_cap_11ax_enable))
+		return -EINVAL;
+
+	/* LAR is expected to be enabled for all supported devices */
+	if (WARN_ON(!mld->nvm_data->lar_enabled))
+		return -EINVAL;
+
+	/* All supported devices are currently using version 3 of the cmd.
+	 * Since version 3, IWL_SCAN_MAX_PROFILES_V2 shall be used where
+	 * necessary.
+	 */
+	if (WARN_ON(iwl_fw_lookup_cmd_ver(mld->fw,
+					  SCAN_OFFLOAD_UPDATE_PROFILES_CMD,
+					  IWL_FW_CMD_VER_UNKNOWN) != 3))
+		return -EINVAL;
+
+	return 0;
+}
+
+int iwl_mld_register_hw(struct iwl_mld *mld)
+{
+	/* verify once essential preconditions required for setting
+	 * the hw capabilities
+	 */
+	if (iwl_mld_hw_verify_preconditions(mld))
+		return -EINVAL;
+
+	iwl_mld_hw_set_addresses(mld);
+	iwl_mld_hw_set_channels(mld);
+	iwl_mld_hw_set_security(mld);
+	iwl_mld_hw_set_regulatory(mld);
+	iwl_mld_hw_set_pm(mld);
+	iwl_mld_hw_set_antennas(mld);
+	iwl_mac_hw_set_radiotap(mld);
+	iwl_mac_hw_set_flags(mld);
+	iwl_mac_hw_set_wiphy(mld);
+	iwl_mac_hw_set_misc(mld);
+
+	SET_IEEE80211_DEV(mld->hw, mld->trans->dev);
+
+	return ieee80211_register_hw(mld->hw);
+}
+
+static void
+iwl_mld_mac80211_tx(struct ieee80211_hw *hw,
+		    struct ieee80211_tx_control *control, struct sk_buff *skb)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct ieee80211_sta *sta = control->sta;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	u32 link_id = u32_get_bits(info->control.flags,
+				   IEEE80211_TX_CTRL_MLO_LINK);
+
+	/* In AP mode, mgmt frames are sent on the bcast station,
+	 * so the FW can't translate the MLD addr to the link addr. Do it here
+	 */
+	if (ieee80211_is_mgmt(hdr->frame_control) && sta &&
+	    link_id != IEEE80211_LINK_UNSPECIFIED &&
+	    !ieee80211_is_probe_resp(hdr->frame_control)) {
+		/* translate MLD addresses to LINK addresses */
+		struct ieee80211_link_sta *link_sta =
+			rcu_dereference(sta->link[link_id]);
+		struct ieee80211_bss_conf *link_conf =
+			rcu_dereference(info->control.vif->link_conf[link_id]);
+		struct ieee80211_mgmt *mgmt;
+
+		if (WARN_ON(!link_sta || !link_conf)) {
+			ieee80211_free_txskb(hw, skb);
+			return;
+		}
+
+		mgmt = (void *)hdr;
+		memcpy(mgmt->da, link_sta->addr, ETH_ALEN);
+		memcpy(mgmt->sa, link_conf->addr, ETH_ALEN);
+		memcpy(mgmt->bssid, link_conf->bssid, ETH_ALEN);
+	}
+
+	iwl_mld_tx_skb(mld, skb, NULL);
+}
+
+static void
+iwl_mld_restart_cleanup(struct iwl_mld *mld)
+{
+	iwl_cleanup_mld(mld);
+
+	ieee80211_iterate_interfaces(mld->hw, IEEE80211_IFACE_ITER_ACTIVE,
+				     iwl_mld_cleanup_vif, NULL);
+
+	ieee80211_iterate_stations_atomic(mld->hw,
+					  iwl_mld_cleanup_sta, NULL);
+
+	iwl_mld_ftm_restart_cleanup(mld);
+}
+
+static
+int iwl_mld_mac80211_start(struct ieee80211_hw *hw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+	bool in_d3 = false;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+#ifdef CONFIG_PM_SLEEP
+	/* Unless the host goes into hibernate the FW always stays on and
+	 * the d3_resume flow is used. When wowlan is configured, mac80211
+	 * would call it's resume callback and the wowlan_resume flow
+	 * would be used.
+	 */
+
+	in_d3 = mld->fw_status.in_d3;
+	if (in_d3) {
+		/* mac80211 already cleaned up the state, no need for cleanup */
+		ret = iwl_mld_no_wowlan_resume(mld);
+		if (ret)
+			iwl_mld_stop_fw(mld);
+	}
+#endif /* CONFIG_PM_SLEEP */
+
+	if (mld->fw_status.in_hw_restart) {
+		iwl_mld_stop_fw(mld);
+		iwl_mld_restart_cleanup(mld);
+	}
+
+	if (!in_d3 || ret) {
+		ret = iwl_mld_start_fw(mld);
+		if (ret)
+			goto error;
+	}
+
+	mld->scan.last_start_time_jiffies = jiffies;
+
+	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_POST_INIT,
+			       NULL);
+	iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_POINT_PERIODIC,
+			       NULL);
+
+	return 0;
+
+error:
+	/* If we failed to restart the hw, there is nothing useful
+	 * we can do but indicate we are no longer in restart.
+	 */
+	mld->fw_status.in_hw_restart = false;
+
+	return ret;
+}
+
+static
+void iwl_mld_mac80211_stop(struct ieee80211_hw *hw, bool suspend)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	wiphy_work_cancel(mld->wiphy, &mld->add_txqs_wk);
+
+	/* if the suspend flow fails the fw is in error. Stop it here, and it
+	 * will be started upon wakeup
+	 */
+	if (!suspend || iwl_mld_no_wowlan_suspend(mld))
+		iwl_mld_stop_fw(mld);
+
+	/* HW is stopped, no more coming RX. OTOH, the worker can't run as the
+	 * wiphy lock is held. Cancel it in case it was scheduled just before
+	 * we stopped the HW.
+	 */
+	wiphy_work_cancel(mld->wiphy, &mld->async_handlers_wk);
+
+	/* Empty out the list, as the worker won't do that */
+	iwl_mld_purge_async_handlers_list(mld);
+
+	/* Clear in_hw_restart flag when stopping the hw, as mac80211 won't
+	 * execute the restart.
+	 */
+	mld->fw_status.in_hw_restart = false;
+
+	/* We shouldn't have any UIDs still set. Loop over all the UIDs to
+	 * make sure there's nothing left there and warn if any is found.
+	 */
+	for (int i = 0; i < ARRAY_SIZE(mld->scan.uid_status); i++)
+		if (WARN_ONCE(mld->scan.uid_status[i],
+			      "UMAC scan UID %d status was not cleaned (0x%x 0x%x)\n",
+			      i, mld->scan.uid_status[i], mld->scan.status))
+			mld->scan.uid_status[i] = 0;
+}
+
+static
+int iwl_mld_mac80211_config(struct ieee80211_hw *hw, u32 changed)
+{
+	return 0;
+}
+
+static
+int iwl_mld_mac80211_add_interface(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* Construct mld_vif, add it to fw, and map its ID to ieee80211_vif */
+	ret = iwl_mld_add_vif(mld, vif);
+	if (ret)
+		return ret;
+
+	/*
+	 * Add the default link, but not if this is an MLD vif as that implies
+	 * the HW is restarting and it will be configured by change_vif_links.
+	 */
+	if (!ieee80211_vif_is_mld(vif))
+		ret = iwl_mld_add_link(mld, &vif->bss_conf);
+	if (ret)
+		goto err;
+
+	if (vif->type == NL80211_IFTYPE_STATION) {
+		vif->driver_flags |= IEEE80211_VIF_REMOVE_AP_AFTER_DISASSOC;
+		if (!vif->p2p)
+			vif->driver_flags |= IEEE80211_VIF_BEACON_FILTER |
+					     IEEE80211_VIF_SUPPORTS_CQM_RSSI;
+	}
+
+	if (vif->p2p || iwl_fw_lookup_cmd_ver(mld->fw, PHY_CONTEXT_CMD, 0) < 5)
+		vif->driver_flags |= IEEE80211_VIF_IGNORE_OFDMA_WIDER_BW;
+
+	/*
+	 * For an MLD vif (in restart) we may not have a link; delay the call
+	 * the initial change_vif_links.
+	 */
+	if (vif->type == NL80211_IFTYPE_STATION &&
+	    !ieee80211_vif_is_mld(vif))
+		iwl_mld_update_mac_power(mld, vif, false);
+
+	if (vif->type == NL80211_IFTYPE_MONITOR) {
+		mld->monitor.on = true;
+		ieee80211_hw_set(mld->hw, RX_INCLUDES_FCS);
+	}
+
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
+		mld->p2p_device_vif = vif;
+
+	return 0;
+
+err:
+	iwl_mld_rm_vif(mld, vif);
+	return ret;
+}
+
+static
+void iwl_mld_mac80211_remove_interface(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_STATION)
+		vif->driver_flags &= ~(IEEE80211_VIF_BEACON_FILTER |
+				       IEEE80211_VIF_SUPPORTS_CQM_RSSI);
+
+	if (vif->type == NL80211_IFTYPE_MONITOR) {
+		__clear_bit(IEEE80211_HW_RX_INCLUDES_FCS, mld->hw->flags);
+		mld->monitor.on = false;
+	}
+
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
+		mld->p2p_device_vif = NULL;
+
+	iwl_mld_remove_link(mld, &vif->bss_conf);
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	debugfs_remove(iwl_mld_vif_from_mac80211(vif)->dbgfs_slink);
+#endif
+
+	iwl_mld_rm_vif(mld, vif);
+}
+
+struct iwl_mld_mc_iter_data {
+	struct iwl_mld *mld;
+	int port_id;
+};
+
+static void iwl_mld_mc_iface_iterator(void *data, u8 *mac,
+				      struct ieee80211_vif *vif)
+{
+	struct iwl_mld_mc_iter_data *mc_data = data;
+	struct iwl_mld *mld = mc_data->mld;
+	struct iwl_mcast_filter_cmd *cmd = mld->mcast_filter_cmd;
+	struct iwl_host_cmd hcmd = {
+		.id = MCAST_FILTER_CMD,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+	int ret, len;
+
+	/* If we don't have free ports, mcast frames will be dropped */
+	if (WARN_ON_ONCE(mc_data->port_id >= MAX_PORT_ID_NUM))
+		return;
+
+	if (vif->type != NL80211_IFTYPE_STATION || !vif->cfg.assoc)
+		return;
+
+	cmd->port_id = mc_data->port_id++;
+	ether_addr_copy(cmd->bssid, vif->bss_conf.bssid);
+	len = roundup(sizeof(*cmd) + cmd->count * ETH_ALEN, 4);
+
+	hcmd.len[0] = len;
+	hcmd.data[0] = cmd;
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (ret)
+		IWL_ERR(mld, "mcast filter cmd error. ret=%d\n", ret);
+}
+
+void iwl_mld_recalc_multicast_filter(struct iwl_mld *mld)
+{
+	struct iwl_mld_mc_iter_data iter_data = {
+		.mld = mld,
+	};
+
+	if (WARN_ON_ONCE(!mld->mcast_filter_cmd))
+		return;
+
+	ieee80211_iterate_active_interfaces(mld->hw,
+					    IEEE80211_IFACE_ITER_NORMAL,
+					    iwl_mld_mc_iface_iterator,
+					    &iter_data);
+}
+
+static u64
+iwl_mld_mac80211_prepare_multicast(struct ieee80211_hw *hw,
+				   struct netdev_hw_addr_list *mc_list)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mcast_filter_cmd *cmd;
+	struct netdev_hw_addr *addr;
+	int addr_count = netdev_hw_addr_list_count(mc_list);
+	bool pass_all = addr_count > MAX_MCAST_FILTERING_ADDRESSES;
+	int len;
+
+	if (pass_all)
+		addr_count = 0;
+
+	/* len must be a multiple of 4 */
+	len = roundup(sizeof(*cmd) + addr_count * ETH_ALEN, 4);
+	cmd = kzalloc(len, GFP_ATOMIC);
+	if (!cmd)
+		return 0;
+
+	if (pass_all) {
+		cmd->pass_all = 1;
+		goto out;
+	}
+
+	netdev_hw_addr_list_for_each(addr, mc_list) {
+		IWL_DEBUG_MAC80211(mld, "mcast addr (%d): %pM\n",
+				   cmd->count, addr->addr);
+		ether_addr_copy(&cmd->addr_list[cmd->count * ETH_ALEN],
+				addr->addr);
+		cmd->count++;
+	}
+
+out:
+	return (u64)(unsigned long)cmd;
+}
+
+static
+void iwl_mld_mac80211_configure_filter(struct ieee80211_hw *hw,
+				       unsigned int changed_flags,
+				       unsigned int *total_flags,
+				       u64 multicast)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mcast_filter_cmd *cmd = (void *)(unsigned long)multicast;
+
+	/* Replace previous configuration */
+	kfree(mld->mcast_filter_cmd);
+	mld->mcast_filter_cmd = cmd;
+
+	if (!cmd)
+		goto out;
+
+	if (changed_flags & FIF_ALLMULTI)
+		cmd->pass_all = !!(*total_flags & FIF_ALLMULTI);
+
+	if (cmd->pass_all)
+		cmd->count = 0;
+
+	iwl_mld_recalc_multicast_filter(mld);
+out:
+	*total_flags = 0;
+}
+
+static
+void iwl_mld_mac80211_wake_tx_queue(struct ieee80211_hw *hw,
+				    struct ieee80211_txq *txq)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_txq *mld_txq = iwl_mld_txq_from_mac80211(txq);
+
+	if (likely(mld_txq->status.allocated) || !txq->sta) {
+		iwl_mld_tx_from_txq(mld, txq);
+		return;
+	}
+
+	/* We don't support TSPEC tids. %IEEE80211_NUM_TIDS is for mgmt */
+	if (txq->tid != IEEE80211_NUM_TIDS && txq->tid >= IWL_MAX_TID_COUNT) {
+		IWL_DEBUG_MAC80211(mld, "TID %d is not supported\n", txq->tid);
+		return;
+	}
+
+	/* The worker will handle any packets we leave on the txq now */
+
+	spin_lock_bh(&mld->add_txqs_lock);
+	/* The list is being deleted only after the queue is fully allocated. */
+	if (list_empty(&mld_txq->list) &&
+	    /* recheck under lock, otherwise it can be added twice */
+	    !mld_txq->status.allocated) {
+		list_add_tail(&mld_txq->list, &mld->txqs_to_add);
+		wiphy_work_queue(mld->wiphy, &mld->add_txqs_wk);
+	}
+	spin_unlock_bh(&mld->add_txqs_lock);
+}
+
+static void iwl_mld_teardown_tdls_peers(struct iwl_mld *mld)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for (int i = 0; i < mld->fw->ucode_capa.num_stations; i++) {
+		struct ieee80211_link_sta *link_sta;
+		struct iwl_mld_sta *mld_sta;
+
+		link_sta = wiphy_dereference(mld->wiphy,
+					     mld->fw_id_to_link_sta[i]);
+		if (IS_ERR_OR_NULL(link_sta))
+			continue;
+
+		if (!link_sta->sta->tdls)
+			continue;
+
+		mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+
+		ieee80211_tdls_oper_request(mld_sta->vif, link_sta->addr,
+					    NL80211_TDLS_TEARDOWN,
+					    WLAN_REASON_TDLS_TEARDOWN_UNSPECIFIED,
+					    GFP_KERNEL);
+	}
+}
+
+static
+int iwl_mld_add_chanctx(struct ieee80211_hw *hw,
+			struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+	int fw_id = iwl_mld_allocate_fw_phy_id(mld);
+	int ret;
+
+	if (fw_id < 0)
+		return fw_id;
+
+	phy->fw_id = fw_id;
+	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
+
+	ret = iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_ADD);
+	if (ret) {
+		mld->used_phy_ids &= ~BIT(phy->fw_id);
+		return ret;
+	}
+
+	if (hweight8(mld->used_phy_ids) > 1)
+		iwl_mld_teardown_tdls_peers(mld);
+
+	return 0;
+}
+
+static
+void iwl_mld_remove_chanctx(struct ieee80211_hw *hw,
+			    struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+
+	iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_REMOVE);
+	mld->used_phy_ids &= ~BIT(phy->fw_id);
+}
+
+static
+void iwl_mld_change_chanctx(struct ieee80211_hw *hw,
+			    struct ieee80211_chanctx_conf *ctx, u32 changed)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+	struct cfg80211_chan_def *chandef =
+		iwl_mld_get_chandef_from_chanctx(ctx);
+
+	/* We don't care about these */
+	if (!(changed & ~(IEEE80211_CHANCTX_CHANGE_RX_CHAINS |
+			  IEEE80211_CHANCTX_CHANGE_RADAR |
+			  IEEE80211_CHANCTX_CHANGE_CHANNEL)))
+		return;
+
+	/* Check if a FW update is required */
+
+	if (changed & IEEE80211_CHANCTX_CHANGE_AP)
+		goto update;
+
+	if (chandef->chan == phy->chandef.chan &&
+	    chandef->center_freq1 == phy->chandef.center_freq1 &&
+	    chandef->punctured == phy->chandef.punctured) {
+		/* Check if we are toggling between HT and non-HT, no-op */
+		if (phy->chandef.width == chandef->width ||
+		    (phy->chandef.width <= NL80211_CHAN_WIDTH_20 &&
+		     chandef->width <= NL80211_CHAN_WIDTH_20))
+			return;
+	}
+update:
+	phy->chandef = *chandef;
+
+	iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_MODIFY);
+}
+
+static u8
+iwl_mld_chandef_get_primary_80(struct cfg80211_chan_def *chandef)
+{
+	int data_start;
+	int control_start;
+	int bw;
+
+	if (chandef->width == NL80211_CHAN_WIDTH_320)
+		bw = 320;
+	else if (chandef->width == NL80211_CHAN_WIDTH_160)
+		bw = 160;
+	else
+		return 0;
+
+	/* data is bw wide so the start is half the width */
+	data_start = chandef->center_freq1 - bw / 2;
+	/* control is 20Mhz width */
+	control_start = chandef->chan->center_freq - 10;
+
+	return (control_start - data_start) / 80;
+}
+
+static bool iwl_mld_can_activate_link(struct iwl_mld *mld,
+				      struct ieee80211_vif *vif,
+				      struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_link_sta *link_sta;
+
+	/* In association, we activate the assoc link before adding the STA. */
+	if (!mld_vif->ap_sta || !vif->cfg.assoc)
+		return true;
+
+	mld_sta = iwl_mld_sta_from_mac80211(mld_vif->ap_sta);
+
+	/* When switching links, we need to wait with the activation until the
+	 * STA was added to the FW. It'll be activated in
+	 * iwl_mld_update_link_stas
+	 */
+	link_sta = wiphy_dereference(mld->wiphy, mld_sta->link[link->link_id]);
+
+	/* In restart we can have a link_sta that doesn't exist in FW yet */
+	return link_sta && link_sta->in_fw;
+}
+
+static
+int iwl_mld_assign_vif_chanctx(struct ieee80211_hw *hw,
+			       struct ieee80211_vif *vif,
+			       struct ieee80211_bss_conf *link,
+			       struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	unsigned int n_active = iwl_mld_count_active_links(mld, vif);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	/* if the assigned one was not counted yet, count it now */
+	if (!rcu_access_pointer(mld_link->chan_ctx)) {
+		n_active++;
+
+		/* Track addition of non-BSS link */
+		if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION) {
+			ret = iwl_mld_emlsr_check_non_bss_block(mld, 1);
+			if (ret)
+				return ret;
+		}
+	}
+
+	/* for AP, mac parameters such as HE support are updated at this stage. */
+	if (vif->type == NL80211_IFTYPE_AP) {
+		ret = iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+
+		if (ret) {
+			IWL_ERR(mld, "failed to update MAC %pM\n", vif->addr);
+			return -EINVAL;
+		}
+	}
+
+	rcu_assign_pointer(mld_link->chan_ctx, ctx);
+
+	if (n_active > 1) {
+		struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+		iwl_mld_leave_omi_bw_reduction(mld);
+
+		/* Indicate to mac80211 that EML is enabled */
+		vif->driver_flags |= IEEE80211_VIF_EML_ACTIVE;
+
+		if (vif->active_links & BIT(mld_vif->emlsr.selected_links))
+			mld_vif->emlsr.primary = mld_vif->emlsr.selected_primary;
+		else
+			mld_vif->emlsr.primary = __ffs(vif->active_links);
+
+		iwl_dbg_tlv_time_point(&mld->fwrt, IWL_FW_INI_TIME_ESR_LINK_UP,
+				       NULL);
+	}
+
+	/* First send the link command with the phy context ID.
+	 * Now that we have the phy, we know the band so also the rates
+	 */
+	ret = iwl_mld_change_link_in_fw(mld, link,
+					LINK_CONTEXT_MODIFY_RATES_INFO);
+	if (ret)
+		goto err;
+
+	/* TODO: Initialize rate control for the AP station, since we might be
+	 * doing a link switch here - we cannot initialize it before since
+	 * this needs the phy context assigned (and in FW?), and we cannot
+	 * do it later because it needs to be initialized as soon as we're
+	 * able to TX on the link, i.e. when active. (task=link-switch)
+	 */
+
+	/* Now activate the link */
+	if (iwl_mld_can_activate_link(mld, vif, link)) {
+		ret = iwl_mld_activate_link(mld, link);
+		if (ret)
+			goto err;
+	}
+
+	if (vif->type == NL80211_IFTYPE_STATION)
+		iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link);
+
+	if (vif->type == NL80211_IFTYPE_MONITOR) {
+		/* TODO: task=sniffer add sniffer station */
+		mld->monitor.p80 =
+			iwl_mld_chandef_get_primary_80(&vif->bss_conf.chanreq.oper);
+	}
+
+	return 0;
+err:
+	RCU_INIT_POINTER(mld_link->chan_ctx, NULL);
+	return ret;
+}
+
+static
+void iwl_mld_unassign_vif_chanctx(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_bss_conf *link,
+				  struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	unsigned int n_active = iwl_mld_count_active_links(mld, vif);
+
+	if (WARN_ON(!mld_link))
+		return;
+
+	/* Track removal of non-BSS link */
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION)
+		iwl_mld_emlsr_check_non_bss_block(mld, -1);
+
+	iwl_mld_deactivate_link(mld, link);
+
+	/* TODO: task=sniffer remove sniffer station */
+
+	if (n_active > 1) {
+		/* Indicate to mac80211 that EML is disabled */
+		vif->driver_flags &= ~IEEE80211_VIF_EML_ACTIVE;
+
+		iwl_dbg_tlv_time_point(&mld->fwrt,
+				       IWL_FW_INI_TIME_ESR_LINK_DOWN,
+				       NULL);
+	}
+
+	RCU_INIT_POINTER(mld_link->chan_ctx, NULL);
+
+	/* in the non-MLO case, remove/re-add the link to clean up FW state.
+	 * In MLO, it'll be done in drv_change_vif_link
+	 */
+	if (!ieee80211_vif_is_mld(vif) && !mld_vif->ap_sta &&
+	    !WARN_ON_ONCE(vif->cfg.assoc) &&
+	    vif->type != NL80211_IFTYPE_AP && !mld->fw_status.in_hw_restart) {
+		iwl_mld_remove_link(mld, link);
+		iwl_mld_add_link(mld, link);
+	}
+}
+
+static
+int iwl_mld_mac80211_set_rts_threshold(struct ieee80211_hw *hw, u32 value)
+{
+	return 0;
+}
+
+static void
+iwl_mld_link_info_changed_ap_ibss(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_bss_conf *link,
+				  u64 changes)
+{
+	u32 link_changes = 0;
+
+	if (changes & BSS_CHANGED_ERP_SLOT)
+		link_changes |= LINK_CONTEXT_MODIFY_RATES_INFO;
+
+	if (changes & (BSS_CHANGED_ERP_CTS_PROT | BSS_CHANGED_HT))
+		link_changes |= LINK_CONTEXT_MODIFY_PROTECT_FLAGS;
+
+	if (changes & (BSS_CHANGED_QOS | BSS_CHANGED_BANDWIDTH))
+		link_changes |= LINK_CONTEXT_MODIFY_QOS_PARAMS;
+
+	if (changes & BSS_CHANGED_HE_BSS_COLOR)
+		link_changes |= LINK_CONTEXT_MODIFY_HE_PARAMS;
+
+	if (link_changes)
+		iwl_mld_change_link_in_fw(mld, link, link_changes);
+
+	if (changes & BSS_CHANGED_BEACON)
+		iwl_mld_update_beacon_template(mld, vif, link);
+}
+
+static
+u32 iwl_mld_link_changed_mapping(struct iwl_mld *mld,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_bss_conf *link_conf,
+				 u64 changes)
+{
+	u32 link_changes = 0;
+	bool has_he, has_eht;
+
+	if (changes & BSS_CHANGED_QOS && vif->cfg.assoc && link_conf->qos)
+		link_changes |= LINK_CONTEXT_MODIFY_QOS_PARAMS;
+
+	if (changes & (BSS_CHANGED_ERP_PREAMBLE | BSS_CHANGED_BASIC_RATES |
+		       BSS_CHANGED_ERP_SLOT))
+		link_changes |= LINK_CONTEXT_MODIFY_RATES_INFO;
+
+	if (changes & (BSS_CHANGED_HT | BSS_CHANGED_ERP_CTS_PROT))
+		link_changes |= LINK_CONTEXT_MODIFY_PROTECT_FLAGS;
+
+	/* TODO: task=MLO check mac80211's HE flags and if command is needed
+	 * every time there's a link change. Currently used flags are
+	 * BSS_CHANGED_HE_OBSS_PD and BSS_CHANGED_HE_BSS_COLOR.
+	 */
+	has_he = link_conf->he_support && !iwlwifi_mod_params.disable_11ax;
+	has_eht = link_conf->eht_support && !iwlwifi_mod_params.disable_11be;
+
+	if (vif->cfg.assoc && (has_he || has_eht)) {
+		IWL_DEBUG_MAC80211(mld, "Associated in HE mode\n");
+		link_changes |= LINK_CONTEXT_MODIFY_HE_PARAMS;
+	}
+
+	return link_changes;
+}
+
+static void
+iwl_mld_mac80211_link_info_changed_sta(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_bss_conf *link_conf,
+				       u64 changes)
+{
+	u32 link_changes = iwl_mld_link_changed_mapping(mld, vif, link_conf,
+							changes);
+
+	if (link_changes)
+		iwl_mld_change_link_in_fw(mld, link_conf, link_changes);
+
+	if (changes & BSS_CHANGED_TPE)
+		iwl_mld_send_ap_tx_power_constraint_cmd(mld, vif, link_conf);
+
+	if (changes & BSS_CHANGED_BEACON_INFO)
+		iwl_mld_update_mac_power(mld, vif, false);
+
+	/* The firmware will wait quite a while after association before it
+	 * starts filtering the beacons. We can safely enable beacon filtering
+	 * upon CQM configuration, even if we didn't get a beacon yet.
+	 */
+	if (changes & (BSS_CHANGED_CQM | BSS_CHANGED_BEACON_INFO))
+		iwl_mld_enable_beacon_filter(mld, link_conf, false);
+
+	/* If we have used OMI before to reduce bandwidth to 80 MHz and then
+	 * increased to 160 MHz again, and then the AP changes to 320 MHz, it
+	 * will think that we're limited to 160 MHz right now. Update it by
+	 * requesting a new OMI bandwidth.
+	 */
+	if (changes & BSS_CHANGED_BANDWIDTH) {
+		enum ieee80211_sta_rx_bandwidth bw;
+
+		bw = ieee80211_chan_width_to_rx_bw(link_conf->chanreq.oper.width);
+
+		iwl_mld_omi_ap_changed_bw(mld, link_conf, bw);
+	}
+
+	if (changes & BSS_CHANGED_BANDWIDTH)
+		iwl_mld_emlsr_check_equal_bw(mld, vif, link_conf);
+}
+
+static int iwl_mld_update_mu_groups(struct iwl_mld *mld,
+				    struct ieee80211_bss_conf *link_conf)
+{
+	struct iwl_mu_group_mgmt_cmd cmd = {};
+
+	BUILD_BUG_ON(sizeof(cmd.membership_status) !=
+		     sizeof(link_conf->mu_group.membership));
+	BUILD_BUG_ON(sizeof(cmd.user_position) !=
+		     sizeof(link_conf->mu_group.position));
+
+	memcpy(cmd.membership_status, link_conf->mu_group.membership,
+	       WLAN_MEMBERSHIP_LEN);
+	memcpy(cmd.user_position, link_conf->mu_group.position,
+	       WLAN_USER_POSITION_LEN);
+
+	return iwl_mld_send_cmd_pdu(mld,
+				    WIDE_ID(DATA_PATH_GROUP,
+					    UPDATE_MU_GROUPS_CMD),
+				    &cmd);
+}
+
+static void
+iwl_mld_mac80211_link_info_changed(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_bss_conf *link_conf,
+				   u64 changes)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		iwl_mld_mac80211_link_info_changed_sta(mld, vif, link_conf,
+						       changes);
+		break;
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_ADHOC:
+		iwl_mld_link_info_changed_ap_ibss(mld, vif, link_conf,
+						  changes);
+		break;
+	case NL80211_IFTYPE_MONITOR:
+		/* The firmware tracks this on its own in STATION mode, but
+		 * obviously not in sniffer mode.
+		 */
+		if (changes & BSS_CHANGED_MU_GROUPS)
+			iwl_mld_update_mu_groups(mld, link_conf);
+		break;
+	default:
+		/* shouldn't happen */
+		WARN_ON_ONCE(1);
+	}
+
+	/* We now know our BSSID, we can configure the MAC context with
+	 * eht_support if needed.
+	 */
+	if (changes & BSS_CHANGED_BSSID)
+		iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+
+	if (changes & BSS_CHANGED_TXPOWER)
+		iwl_mld_set_tx_power(mld, link_conf, link_conf->txpower);
+}
+
+static
+void iwl_mld_mac80211_vif_cfg_changed(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif,
+				      u64 changes)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	if (changes & BSS_CHANGED_ASSOC) {
+		ret = iwl_mld_mac_fw_action(mld, vif, FW_CTXT_ACTION_MODIFY);
+		if (ret)
+			IWL_ERR(mld, "failed to update context\n");
+
+		if (vif->cfg.assoc) {
+			/* Clear statistics to get clean beacon counter, and
+			 * ask for periodic statistics, as they are needed for
+			 * link selection and RX OMI decisions.
+			 */
+			iwl_mld_clear_stats_in_fw(mld);
+			iwl_mld_request_periodic_fw_stats(mld, true);
+
+			iwl_mld_set_vif_associated(mld, vif);
+		} else {
+			iwl_mld_request_periodic_fw_stats(mld, false);
+		}
+	}
+
+	if (changes & BSS_CHANGED_PS) {
+		/* Send both device-level and MAC-level power commands since the
+		 * firmware checks the POWER_TABLE_CMD's POWER_SAVE_EN bit to
+		 * determine SMPS mode.
+		 */
+		iwl_mld_update_device_power(mld, false);
+		iwl_mld_update_mac_power(mld, vif, false);
+	}
+
+	/* TODO: task=MLO BSS_CHANGED_MLD_VALID_LINKS/CHANGED_MLD_TTLM */
+}
+
+static int
+iwl_mld_mac80211_hw_scan(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif,
+			 struct ieee80211_scan_request *hw_req)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	if (WARN_ON(!hw_req->req.n_channels ||
+		    hw_req->req.n_channels >
+		    mld->fw->ucode_capa.n_scan_channels))
+		return -EINVAL;
+
+	return iwl_mld_regular_scan_start(mld, vif, &hw_req->req, &hw_req->ies);
+}
+
+static void
+iwl_mld_mac80211_cancel_hw_scan(struct ieee80211_hw *hw,
+				struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	/* Due to a race condition, it's possible that mac80211 asks
+	 * us to stop a hw_scan when it's already stopped. This can
+	 * happen, for instance, if we stopped the scan ourselves,
+	 * called ieee80211_scan_completed() and the userspace called
+	 * cancel scan before ieee80211_scan_work() could run.
+	 * To handle that, simply return if the scan is not running.
+	 */
+	if (mld->scan.status & IWL_MLD_SCAN_REGULAR)
+		iwl_mld_scan_stop(mld, IWL_MLD_SCAN_REGULAR, true);
+}
+
+static int
+iwl_mld_mac80211_sched_scan_start(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct cfg80211_sched_scan_request *req,
+				  struct ieee80211_scan_ies *ies)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	return iwl_mld_sched_scan_start(mld, vif, req, ies, IWL_MLD_SCAN_SCHED);
+}
+
+static int
+iwl_mld_mac80211_sched_scan_stop(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	/* Due to a race condition, it's possible that mac80211 asks
+	 * us to stop a sched_scan when it's already stopped. This
+	 * can happen, for instance, if we stopped the scan ourselves,
+	 * called ieee80211_sched_scan_stopped() and the userspace called
+	 * stop sched scan before ieee80211_sched_scan_stopped_work()
+	 * could run. To handle this, simply return if the scan is
+	 * not running.
+	 */
+	if (!(mld->scan.status & IWL_MLD_SCAN_SCHED))
+		return 0;
+
+	return iwl_mld_scan_stop(mld, IWL_MLD_SCAN_SCHED, false);
+}
+
+static void
+iwl_mld_restart_complete_vif(void *data, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_bss_conf *link_conf;
+	struct iwl_mld *mld = data;
+	int link_id;
+
+	for_each_vif_active_link(vif, link_conf, link_id) {
+		enum ieee80211_sta_rx_bandwidth bw;
+		struct iwl_mld_link *mld_link;
+
+		mld_link = wiphy_dereference(mld->wiphy,
+					     mld_vif->link[link_id]);
+
+		if (WARN_ON_ONCE(!mld_link))
+			continue;
+
+		bw = mld_link->rx_omi.bw_in_progress;
+		if (bw)
+			iwl_mld_change_link_omi_bw(mld, link_conf, bw);
+	}
+}
+
+static void
+iwl_mld_mac80211_reconfig_complete(struct ieee80211_hw *hw,
+				   enum ieee80211_reconfig_type reconfig_type)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	switch (reconfig_type) {
+	case IEEE80211_RECONFIG_TYPE_RESTART:
+		mld->fw_status.in_hw_restart = false;
+		iwl_mld_send_recovery_cmd(mld, ERROR_RECOVERY_END_OF_RECOVERY);
+
+		ieee80211_iterate_interfaces(mld->hw,
+					     IEEE80211_IFACE_ITER_NORMAL,
+					     iwl_mld_restart_complete_vif, mld);
+
+		iwl_trans_finish_sw_reset(mld->trans);
+		/* no need to lock, adding in parallel would schedule too */
+		if (!list_empty(&mld->txqs_to_add))
+			wiphy_work_queue(mld->wiphy, &mld->add_txqs_wk);
+
+		IWL_INFO(mld, "restart completed\n");
+		break;
+	case IEEE80211_RECONFIG_TYPE_SUSPEND:
+		break;
+	}
+}
+
+static
+void iwl_mld_mac80211_mgd_prepare_tx(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_prep_tx_info *info)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	u32 duration = IWL_MLD_SESSION_PROTECTION_ASSOC_TIME_MS;
+
+	/* After a successful association the connection is etalibeshed
+	 * and we can rely on the quota to send the disassociation frame.
+	 */
+	if (info->was_assoc)
+		return;
+
+	if (info->duration > duration)
+		duration = info->duration;
+
+	iwl_mld_schedule_session_protection(mld, vif, duration,
+					    IWL_MLD_SESSION_PROTECTION_MIN_TIME_MS,
+					    info->link_id);
+}
+
+static
+void iwl_mld_mac_mgd_complete_tx(struct ieee80211_hw *hw,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_prep_tx_info *info)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	/* Successful authentication is the only case that requires to let
+	 * the session protection go. We'll need it for the upcoming
+	 * association. For all the other cases, we need to cancel the session
+	 * protection.
+	 * After successful association the connection is established and
+	 * further mgd tx can rely on the quota.
+	 */
+	if (info->success && info->subtype == IEEE80211_STYPE_AUTH)
+		return;
+
+	/* The firmware will be on medium after we configure the vif as
+	 * associated. Removing the session protection allows the firmware
+	 * to stop being on medium. In order to ensure the continuity of our
+	 * presence on medium, we need first to configure the vif as associated
+	 * and only then, remove the session protection.
+	 * Currently, mac80211 calls vif_cfg_changed() first and then,
+	 * drv_mgd_complete_tx(). Ensure that this assumption stays true by
+	 * a warning.
+	 */
+	WARN_ON(info->success &&
+		(info->subtype == IEEE80211_STYPE_ASSOC_REQ ||
+		 info->subtype == IEEE80211_STYPE_REASSOC_REQ) &&
+		!vif->cfg.assoc);
+
+	iwl_mld_cancel_session_protection(mld, vif, info->link_id);
+}
+
+static int
+iwl_mld_mac80211_conf_tx(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif,
+			 unsigned int link_id, u16 ac,
+			 const struct ieee80211_tx_queue_params *params)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	link = iwl_mld_link_dereference_check(mld_vif, link_id);
+	if (!link)
+		return -EINVAL;
+
+	link->queue_params[ac] = *params;
+
+	/* No need to update right away, we'll get BSS_CHANGED_QOS
+	 * The exception is P2P_DEVICE interface which needs immediate update.
+	 */
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE)
+		iwl_mld_change_link_in_fw(mld, &vif->bss_conf,
+					  LINK_CONTEXT_MODIFY_QOS_PARAMS);
+
+	return 0;
+}
+
+static void iwl_mld_set_uapsd(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	vif->driver_flags &= ~IEEE80211_VIF_SUPPORTS_UAPSD;
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	if (vif->p2p &&
+	    !(iwlwifi_mod_params.uapsd_disable & IWL_DISABLE_UAPSD_P2P_CLIENT))
+		vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
+
+	if (!vif->p2p &&
+	    !(iwlwifi_mod_params.uapsd_disable & IWL_DISABLE_UAPSD_BSS))
+		vif->driver_flags |= IEEE80211_VIF_SUPPORTS_UAPSD;
+}
+
+int iwl_mld_tdls_sta_count(struct iwl_mld *mld)
+{
+	int count = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for (int i = 0; i < mld->fw->ucode_capa.num_stations; i++) {
+		struct ieee80211_link_sta *link_sta;
+
+		link_sta = wiphy_dereference(mld->wiphy,
+					     mld->fw_id_to_link_sta[i]);
+		if (IS_ERR_OR_NULL(link_sta))
+			continue;
+
+		if (!link_sta->sta->tdls)
+			continue;
+
+		count++;
+	}
+
+	return count;
+}
+
+static void iwl_mld_check_he_obss_narrow_bw_ru_iter(struct wiphy *wiphy,
+						    struct cfg80211_bss *bss,
+						    void *_data)
+{
+	bool *tolerated = _data;
+	const struct cfg80211_bss_ies *ies;
+	const struct element *elem;
+
+	rcu_read_lock();
+	ies = rcu_dereference(bss->ies);
+	elem = cfg80211_find_elem(WLAN_EID_EXT_CAPABILITY, ies->data,
+				  ies->len);
+
+	if (!elem || elem->datalen < 10 ||
+	    !(elem->data[10] &
+	      WLAN_EXT_CAPA10_OBSS_NARROW_BW_RU_TOLERANCE_SUPPORT)) {
+		*tolerated = false;
+	}
+	rcu_read_unlock();
+}
+
+static void
+iwl_mld_check_he_obss_narrow_bw_ru(struct iwl_mld *mld,
+				   struct iwl_mld_link *mld_link,
+				   struct ieee80211_bss_conf *link_conf)
+{
+	bool tolerated = true;
+
+	if (WARN_ON_ONCE(!link_conf->chanreq.oper.chan))
+		return;
+
+	if (!(link_conf->chanreq.oper.chan->flags & IEEE80211_CHAN_RADAR)) {
+		mld_link->he_ru_2mhz_block = false;
+		return;
+	}
+
+	cfg80211_bss_iter(mld->wiphy, &link_conf->chanreq.oper,
+			  iwl_mld_check_he_obss_narrow_bw_ru_iter, &tolerated);
+
+	/* If there is at least one AP on radar channel that cannot
+	 * tolerate 26-tone RU UL OFDMA transmissions using HE TB PPDU.
+	 */
+	mld_link->he_ru_2mhz_block = !tolerated;
+}
+
+static void iwl_mld_link_set_2mhz_block(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta)
+{
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
+
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct ieee80211_bss_conf *link_conf =
+			link_conf_dereference_protected(vif, link_id);
+		struct iwl_mld_link *mld_link =
+			iwl_mld_link_from_mac80211(link_conf);
+
+		if (WARN_ON(!link_conf || !mld_link))
+			continue;
+
+		if (link_sta->he_cap.has_he)
+			iwl_mld_check_he_obss_narrow_bw_ru(mld, mld_link,
+							   link_conf);
+	}
+}
+
+static int iwl_mld_move_sta_state_up(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta,
+				     enum ieee80211_sta_state old_state,
+				     enum ieee80211_sta_state new_state)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int tdls_count = 0;
+	int ret;
+
+	if (old_state == IEEE80211_STA_NOTEXIST &&
+	    new_state == IEEE80211_STA_NONE) {
+		if (sta->tdls) {
+			if (vif->p2p || hweight8(mld->used_phy_ids) != 1)
+				return -EBUSY;
+
+			tdls_count = iwl_mld_tdls_sta_count(mld);
+			if (tdls_count >= IWL_TDLS_STA_COUNT)
+				return -EBUSY;
+		}
+
+		/*
+		 * If this is the first STA (i.e. the AP) it won't do
+		 * anything, otherwise must leave for any new STA on
+		 * any other interface, or for TDLS, etc.
+		 * Need to call this _before_ adding the STA so it can
+		 * look up the one STA to use to ask mac80211 to leave
+		 * OMI; in the unlikely event that adding the new STA
+		 * then fails we'll just re-enter OMI later (via the
+		 * statistics notification handling.)
+		 */
+		iwl_mld_leave_omi_bw_reduction(mld);
+
+		ret = iwl_mld_add_sta(mld, sta, vif, STATION_TYPE_PEER);
+		if (ret)
+			return ret;
+
+		/* just added first TDLS STA, so disable PM */
+		if (sta->tdls && tdls_count == 0)
+			iwl_mld_update_mac_power(mld, vif, false);
+
+		if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
+			mld_vif->ap_sta = sta;
+
+		/* Initialize TLC here already - this really tells
+		 * the firmware only what the supported legacy rates are
+		 * (may be) since it's initialized already from what the
+		 * AP advertised in the beacon/probe response. This will
+		 * allow the firmware to send auth/assoc frames with one
+		 * of the supported rates already, rather than having to
+		 * use a mandatory rate.
+		 * If we're the AP, we'll just assume mandatory rates at
+		 * this point, but we know nothing about the STA anyway.
+		 */
+		iwl_mld_config_tlc(mld, vif, sta);
+
+		return ret;
+	} else if (old_state == IEEE80211_STA_NONE &&
+		   new_state == IEEE80211_STA_AUTH) {
+		iwl_mld_set_uapsd(mld, vif);
+		return 0;
+	} else if (old_state == IEEE80211_STA_AUTH &&
+		   new_state == IEEE80211_STA_ASSOC) {
+		ret = iwl_mld_update_all_link_stations(mld, sta);
+
+		if (vif->type == NL80211_IFTYPE_STATION)
+			iwl_mld_link_set_2mhz_block(mld, vif, sta);
+		/* Now the link_sta's capabilities are set, update the FW */
+		iwl_mld_config_tlc(mld, vif, sta);
+
+		if (vif->type == NL80211_IFTYPE_AP) {
+			/* Update MAC_CFG_FILTER_ACCEPT_BEACON if at least
+			 * one sta is associated
+			 */
+			if (++mld_vif->num_associated_stas == 1)
+				ret = iwl_mld_mac_fw_action(mld, vif,
+							    FW_CTXT_ACTION_MODIFY);
+		}
+
+		return ret;
+	} else if (old_state == IEEE80211_STA_ASSOC &&
+		   new_state == IEEE80211_STA_AUTHORIZED) {
+		ret = 0;
+
+		if (!sta->tdls) {
+			mld_vif->authorized = true;
+
+			/* Ensure any block due to a non-BSS link is synced */
+			iwl_mld_emlsr_check_non_bss_block(mld, 0);
+
+			/* Block EMLSR until a certain throughput it reached */
+			if (!mld->fw_status.in_hw_restart &&
+			    IWL_MLD_ENTER_EMLSR_TPT_THRESH > 0)
+				iwl_mld_block_emlsr(mld_vif->mld, vif,
+						    IWL_MLD_EMLSR_BLOCKED_TPT,
+						    0);
+
+			/* Wait for the FW to send a recommendation */
+			iwl_mld_block_emlsr(mld, vif,
+					    IWL_MLD_EMLSR_BLOCKED_FW, 0);
+
+			/* clear COEX_HIGH_PRIORITY_ENABLE */
+			ret = iwl_mld_mac_fw_action(mld, vif,
+						    FW_CTXT_ACTION_MODIFY);
+			if (ret)
+				return ret;
+		}
+
+		/* MFP is set by default before the station is authorized.
+		 * Clear it here in case it's not used.
+		 */
+		if (!sta->mfp)
+			ret = iwl_mld_update_all_link_stations(mld, sta);
+
+		/* We can use wide bandwidth now, not only 20 MHz */
+		iwl_mld_config_tlc(mld, vif, sta);
+
+		return ret;
+	} else {
+		return -EINVAL;
+	}
+}
+
+static int iwl_mld_move_sta_state_down(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *sta,
+				       enum ieee80211_sta_state old_state,
+				       enum ieee80211_sta_state new_state)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	if (old_state == IEEE80211_STA_AUTHORIZED &&
+	    new_state == IEEE80211_STA_ASSOC) {
+		if (!sta->tdls) {
+			mld_vif->authorized = false;
+
+			memset(&mld_vif->emlsr.zeroed_on_not_authorized, 0,
+			       sizeof(mld_vif->emlsr.zeroed_on_not_authorized));
+
+			wiphy_delayed_work_cancel(mld->wiphy,
+						  &mld_vif->emlsr.prevent_done_wk);
+			wiphy_delayed_work_cancel(mld->wiphy,
+						  &mld_vif->emlsr.tmp_non_bss_done_wk);
+			wiphy_work_cancel(mld->wiphy, &mld_vif->emlsr.unblock_tpt_wk);
+			wiphy_delayed_work_cancel(mld->wiphy,
+						  &mld_vif->emlsr.check_tpt_wk);
+
+			iwl_mld_reset_cca_40mhz_workaround(mld, vif);
+		}
+
+		/* once we move into assoc state, need to update the FW to
+		 * stop using wide bandwidth
+		 */
+		iwl_mld_config_tlc(mld, vif, sta);
+	} else if (old_state == IEEE80211_STA_ASSOC &&
+		   new_state == IEEE80211_STA_AUTH) {
+		if (vif->type == NL80211_IFTYPE_AP &&
+		    !WARN_ON(!mld_vif->num_associated_stas)) {
+			/* Update MAC_CFG_FILTER_ACCEPT_BEACON if the last sta
+			 * is disassociating
+			 */
+			if (--mld_vif->num_associated_stas == 0)
+				iwl_mld_mac_fw_action(mld, vif,
+						      FW_CTXT_ACTION_MODIFY);
+		}
+	} else if (old_state == IEEE80211_STA_AUTH &&
+		   new_state == IEEE80211_STA_NONE) {
+		/* nothing */
+	} else if (old_state == IEEE80211_STA_NONE &&
+		   new_state == IEEE80211_STA_NOTEXIST) {
+		iwl_mld_remove_sta(mld, sta);
+
+		if (sta->tdls && iwl_mld_tdls_sta_count(mld) == 0) {
+			/* just removed last TDLS STA, so enable PM */
+			iwl_mld_update_mac_power(mld, vif, false);
+		}
+	} else {
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int iwl_mld_mac80211_sta_state(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif,
+				      struct ieee80211_sta *sta,
+				      enum ieee80211_sta_state old_state,
+				      enum ieee80211_sta_state new_state)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	IWL_DEBUG_MAC80211(mld, "station %pM state change %d->%d\n",
+			   sta->addr, old_state, new_state);
+
+	mld_sta->sta_state = new_state;
+
+	if (old_state < new_state)
+		return iwl_mld_move_sta_state_up(mld, vif, sta, old_state,
+						 new_state);
+	else
+		return iwl_mld_move_sta_state_down(mld, vif, sta, old_state,
+						   new_state);
+}
+
+static void iwl_mld_mac80211_flush(struct ieee80211_hw *hw,
+				   struct ieee80211_vif *vif,
+				   u32 queues, bool drop)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	/* Make sure we're done with the deferred traffic before flushing */
+	iwl_mld_add_txq_list(mld);
+
+	for (int i = 0; i < mld->fw->ucode_capa.num_stations; i++) {
+		struct ieee80211_link_sta *link_sta =
+			wiphy_dereference(mld->wiphy,
+					  mld->fw_id_to_link_sta[i]);
+
+		if (IS_ERR_OR_NULL(link_sta))
+			continue;
+
+		/* Check that the sta belongs to the given vif */
+		if (vif && vif != iwl_mld_sta_from_mac80211(link_sta->sta)->vif)
+			continue;
+
+		if (drop)
+			iwl_mld_flush_sta_txqs(mld, link_sta->sta);
+		else
+			iwl_mld_wait_sta_txqs_empty(mld, link_sta->sta);
+	}
+}
+
+static void iwl_mld_mac80211_flush_sta(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *sta)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	iwl_mld_flush_sta_txqs(mld, sta);
+}
+
+static int
+iwl_mld_mac80211_ampdu_action(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_ampdu_params *params)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct ieee80211_sta *sta = params->sta;
+	enum ieee80211_ampdu_mlme_action action = params->action;
+	u16 tid = params->tid;
+	u16 ssn = params->ssn;
+	u16 buf_size = params->buf_size;
+	u16 timeout = params->timeout;
+	int ret;
+
+	IWL_DEBUG_HT(mld, "A-MPDU action on addr %pM tid: %d action: %d\n",
+		     sta->addr, tid, action);
+
+	switch (action) {
+	case IEEE80211_AMPDU_RX_START:
+		ret = iwl_mld_ampdu_rx_start(mld, sta, tid, ssn, buf_size,
+					     timeout);
+		break;
+	case IEEE80211_AMPDU_RX_STOP:
+		ret = iwl_mld_ampdu_rx_stop(mld, sta, tid);
+		break;
+	default:
+		/* The mac80211 TX_AMPDU_SETUP_IN_HW flag is set for all
+		 * devices, since all support TX A-MPDU offload in hardware.
+		 * Therefore, no TX action should be requested here.
+		 */
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+
+	return ret;
+}
+
+static bool iwl_mld_can_hw_csum(struct sk_buff *skb)
+{
+	u8 protocol = ip_hdr(skb)->protocol;
+
+	return protocol == IPPROTO_TCP || protocol == IPPROTO_UDP;
+}
+
+static bool iwl_mld_mac80211_can_aggregate(struct ieee80211_hw *hw,
+					   struct sk_buff *head,
+					   struct sk_buff *skb)
+{
+	if (!IS_ENABLED(CONFIG_INET))
+		return false;
+
+	/* For now don't aggregate IPv6 in AMSDU */
+	if (skb->protocol != htons(ETH_P_IP))
+		return false;
+
+	/* Allow aggregation only if both frames have the same HW csum offload
+	 * capability, ensuring consistent HW or SW csum handling in A-MSDU.
+	 */
+	return iwl_mld_can_hw_csum(skb) == iwl_mld_can_hw_csum(head);
+}
+
+static void iwl_mld_mac80211_sync_rx_queues(struct ieee80211_hw *hw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	iwl_mld_sync_rx_queues(mld, IWL_MLD_RXQ_EMPTY, NULL, 0);
+}
+
+static void iwl_mld_sta_rc_update(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_link_sta *link_sta,
+				  u32 changed)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	if (changed & (IEEE80211_RC_BW_CHANGED |
+		       IEEE80211_RC_SUPP_RATES_CHANGED |
+		       IEEE80211_RC_NSS_CHANGED)) {
+		struct ieee80211_bss_conf *link =
+			link_conf_dereference_check(vif, link_sta->link_id);
+
+		if (WARN_ON(!link))
+			return;
+
+		iwl_mld_config_tlc_link(mld, vif, link, link_sta);
+	}
+}
+
+static void iwl_mld_set_wakeup(struct ieee80211_hw *hw, bool enabled)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	device_set_wakeup_enable(mld->trans->dev, enabled);
+}
+
+/* Returns 0 on success. 1 if failed to suspend with wowlan:
+ * If the circumstances didn't satisfy the conditions for suspension
+ * with wowlan, mac80211 would use the no_wowlan flow.
+ * If an error had occurred we update the trans status and state here
+ * and the result will be stopping the FW.
+ */
+static int
+iwl_mld_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	iwl_fw_runtime_suspend(&mld->fwrt);
+
+	ret = iwl_mld_wowlan_suspend(mld, wowlan);
+	if (ret) {
+		if (ret < 0) {
+			mld->trans->state = IWL_TRANS_NO_FW;
+			set_bit(STATUS_FW_ERROR, &mld->trans->status);
+		}
+		return 1;
+	}
+
+	if (iwl_mld_no_wowlan_suspend(mld))
+		return 1;
+
+	return 0;
+}
+
+static int iwl_mld_resume(struct ieee80211_hw *hw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	ret = iwl_mld_wowlan_resume(mld);
+	if (ret)
+		return ret;
+
+	iwl_fw_runtime_resume(&mld->fwrt);
+
+	iwl_mld_low_latency_restart(mld);
+
+	return 0;
+}
+
+static int iwl_mld_alloc_ptk_pn(struct iwl_mld *mld,
+				struct iwl_mld_sta *mld_sta,
+				struct ieee80211_key_conf *key,
+				struct iwl_mld_ptk_pn **ptk_pn)
+{
+	u8 num_rx_queues = mld->trans->num_rx_queues;
+	int keyidx = key->keyidx;
+	struct ieee80211_key_seq seq;
+
+	if (WARN_ON(keyidx >= ARRAY_SIZE(mld_sta->ptk_pn)))
+		return -EINVAL;
+
+	WARN_ON(rcu_access_pointer(mld_sta->ptk_pn[keyidx]));
+	*ptk_pn = kzalloc(struct_size(*ptk_pn, q, num_rx_queues),
+			  GFP_KERNEL);
+	if (!*ptk_pn)
+		return -ENOMEM;
+
+	for (u8 tid = 0; tid < IWL_MAX_TID_COUNT; tid++) {
+		ieee80211_get_key_rx_seq(key, tid, &seq);
+		for (u8 q = 0; q < num_rx_queues; q++)
+			memcpy((*ptk_pn)->q[q].pn[tid], seq.ccmp.pn,
+			       IEEE80211_CCMP_PN_LEN);
+	}
+
+	rcu_assign_pointer(mld_sta->ptk_pn[keyidx], *ptk_pn);
+
+	return 0;
+}
+
+static int iwl_mld_set_key_add(struct iwl_mld *mld,
+			       struct ieee80211_vif *vif,
+			       struct ieee80211_sta *sta,
+			       struct ieee80211_key_conf *key)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_sta *mld_sta =
+		sta ? iwl_mld_sta_from_mac80211(sta) : NULL;
+	struct iwl_mld_ptk_pn *ptk_pn = NULL;
+	int keyidx = key->keyidx;
+	int ret;
+
+	/* Will be set to 0 if added successfully */
+	key->hw_key_idx = STA_KEY_IDX_INVALID;
+
+	switch (key->cipher) {
+	case WLAN_CIPHER_SUITE_WEP40:
+	case WLAN_CIPHER_SUITE_WEP104:
+		IWL_DEBUG_MAC80211(mld, "Use SW encryption for WEP\n");
+		return -EOPNOTSUPP;
+	case WLAN_CIPHER_SUITE_TKIP:
+		if (vif->type == NL80211_IFTYPE_STATION) {
+			key->flags |= IEEE80211_KEY_FLAG_PUT_MIC_SPACE;
+			break;
+		}
+		IWL_DEBUG_MAC80211(mld, "Use SW encryption for TKIP\n");
+		return -EOPNOTSUPP;
+	case WLAN_CIPHER_SUITE_CCMP:
+	case WLAN_CIPHER_SUITE_GCMP:
+	case WLAN_CIPHER_SUITE_GCMP_256:
+	case WLAN_CIPHER_SUITE_AES_CMAC:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	if (vif->type == NL80211_IFTYPE_STATION &&
+	    (keyidx == 6 || keyidx == 7))
+		rcu_assign_pointer(mld_vif->bigtks[keyidx - 6], key);
+
+	/* After exiting from RFKILL, hostapd configures GTK/ITGK before the
+	 * AP is started, but those keys can't be sent to the FW before the
+	 * MCAST/BCAST STAs are added to it (which happens upon AP start).
+	 * Store it here to be sent later when the AP is started.
+	 */
+	if ((vif->type == NL80211_IFTYPE_ADHOC ||
+	     vif->type == NL80211_IFTYPE_AP) && !sta &&
+	     !mld_vif->ap_ibss_active)
+		return iwl_mld_store_ap_early_key(mld, key, mld_vif);
+
+	if (!mld->fw_status.in_hw_restart && mld_sta &&
+	    key->flags & IEEE80211_KEY_FLAG_PAIRWISE &&
+	    (key->cipher == WLAN_CIPHER_SUITE_CCMP ||
+	     key->cipher == WLAN_CIPHER_SUITE_GCMP ||
+	     key->cipher == WLAN_CIPHER_SUITE_GCMP_256)) {
+		ret = iwl_mld_alloc_ptk_pn(mld, mld_sta, key, &ptk_pn);
+		if (ret)
+			return ret;
+	}
+
+	IWL_DEBUG_MAC80211(mld, "set hwcrypto key (sta:%pM, id:%d)\n",
+			   sta ? sta->addr : NULL, keyidx);
+
+	ret = iwl_mld_add_key(mld, vif, sta, key);
+	if (ret) {
+		IWL_WARN(mld, "set key failed (%d)\n", ret);
+		if (ptk_pn) {
+			RCU_INIT_POINTER(mld_sta->ptk_pn[keyidx], NULL);
+			kfree(ptk_pn);
+		}
+
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void iwl_mld_set_key_remove(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct ieee80211_sta *sta,
+				   struct ieee80211_key_conf *key)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_sta *mld_sta =
+		sta ? iwl_mld_sta_from_mac80211(sta) : NULL;
+	int keyidx = key->keyidx;
+
+	if (vif->type == NL80211_IFTYPE_STATION &&
+	    (keyidx == 6 || keyidx == 7))
+		RCU_INIT_POINTER(mld_vif->bigtks[keyidx - 6], NULL);
+
+	if (mld_sta && key->flags & IEEE80211_KEY_FLAG_PAIRWISE &&
+	    (key->cipher == WLAN_CIPHER_SUITE_CCMP ||
+	     key->cipher == WLAN_CIPHER_SUITE_GCMP ||
+	     key->cipher == WLAN_CIPHER_SUITE_GCMP_256)) {
+		struct iwl_mld_ptk_pn *ptk_pn;
+
+		if (WARN_ON(keyidx >= ARRAY_SIZE(mld_sta->ptk_pn)))
+			return;
+
+		ptk_pn = wiphy_dereference(mld->wiphy,
+					   mld_sta->ptk_pn[keyidx]);
+		RCU_INIT_POINTER(mld_sta->ptk_pn[keyidx], NULL);
+		if (!WARN_ON(!ptk_pn))
+			kfree_rcu(ptk_pn, rcu_head);
+	}
+
+	/* if this key was stored to be added later to the FW - free it here */
+	if (!(key->flags & IEEE80211_KEY_FLAG_PAIRWISE))
+		iwl_mld_free_ap_early_key(mld, key, mld_vif);
+
+	/* We already removed it */
+	if (key->hw_key_idx == STA_KEY_IDX_INVALID)
+		return;
+
+	IWL_DEBUG_MAC80211(mld, "disable hwcrypto key\n");
+
+	iwl_mld_remove_key(mld, vif, sta, key);
+}
+
+static int iwl_mld_mac80211_set_key(struct ieee80211_hw *hw,
+				    enum set_key_cmd cmd,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta,
+				    struct ieee80211_key_conf *key)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	switch (cmd) {
+	case SET_KEY:
+		ret = iwl_mld_set_key_add(mld, vif, sta, key);
+		if (ret)
+			ret = -EOPNOTSUPP;
+		break;
+	case DISABLE_KEY:
+		iwl_mld_set_key_remove(mld, vif, sta, key);
+		ret = 0;
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static int
+iwl_mld_pre_channel_switch(struct ieee80211_hw *hw,
+			   struct ieee80211_vif *vif,
+			   struct ieee80211_channel_switch *chsw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *mld_link =
+		iwl_mld_link_dereference_check(mld_vif, chsw->link_id);
+	u8 primary;
+	int selected;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	IWL_DEBUG_MAC80211(mld, "pre CSA to freq %d\n",
+			   chsw->chandef.center_freq1);
+
+	if (!iwl_mld_emlsr_active(vif))
+		return 0;
+
+	primary = iwl_mld_get_primary_link(vif);
+
+	/* stay on the primary link unless it is undergoing a CSA with quiet */
+	if (chsw->link_id == primary && chsw->block_tx)
+		selected = iwl_mld_get_other_link(vif, primary);
+	else
+		selected = primary;
+
+	/* Remember to tell the firmware that this link can't tx
+	 * Note that this logic seems to be unrelated to emlsr, but it
+	 * really is needed only when emlsr is active. When we have a
+	 * single link, the firmware will handle all this on its own.
+	 * In multi-link scenarios, we can learn about the CSA from
+	 * another link and this logic is too complex for the firmware
+	 * to track.
+	 * Since we want to de-activate the link that got a CSA with mode=1,
+	 * we need to tell the firmware not to send any frame on that link
+	 * as the firmware may not be aware that link is under a CSA
+	 * with mode=1 (no Tx allowed).
+	 */
+	mld_link->silent_deactivation = chsw->block_tx;
+	iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_CSA, selected);
+
+	return 0;
+}
+
+static void
+iwl_mld_channel_switch(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif,
+		       struct ieee80211_channel_switch *chsw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	/* By implementing this operation, we prevent mac80211 from
+	 * starting its own channel switch timer, so that we can call
+	 * ieee80211_chswitch_done() ourselves at the right time
+	 * (Upon receiving the channel_switch_start notification from the fw)
+	 */
+	IWL_DEBUG_MAC80211(mld,
+			   "dummy channel switch op\n");
+}
+
+static int
+iwl_mld_post_channel_switch(struct ieee80211_hw *hw,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_bss_conf *link_conf)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link_conf);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	WARN_ON(mld_link->silent_deactivation);
+
+	return 0;
+}
+
+static void
+iwl_mld_abort_channel_switch(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link_conf);
+
+	IWL_DEBUG_MAC80211(mld,
+			   "abort channel switch op\n");
+	mld_link->silent_deactivation = false;
+}
+
+static int
+iwl_mld_switch_vif_chanctx_swap(struct ieee80211_hw *hw,
+				struct ieee80211_vif_chanctx_switch *vifs)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	iwl_mld_unassign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+				     vifs[0].old_ctx);
+	iwl_mld_remove_chanctx(hw, vifs[0].old_ctx);
+
+	ret = iwl_mld_add_chanctx(hw, vifs[0].new_ctx);
+	if (ret) {
+		IWL_ERR(mld, "failed to add new_ctx during channel switch\n");
+		goto out_reassign;
+	}
+
+	ret = iwl_mld_assign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+					 vifs[0].new_ctx);
+	if (ret) {
+		IWL_ERR(mld,
+			"failed to assign new_ctx during channel switch\n");
+		goto out_remove;
+	}
+
+	return 0;
+
+ out_remove:
+	iwl_mld_remove_chanctx(hw, vifs[0].new_ctx);
+ out_reassign:
+	if (iwl_mld_add_chanctx(hw, vifs[0].old_ctx)) {
+		IWL_ERR(mld, "failed to add old_ctx after failure\n");
+		return ret;
+	}
+
+	if (iwl_mld_assign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+				       vifs[0].old_ctx))
+		IWL_ERR(mld, "failed to reassign old_ctx after failure\n");
+
+	return ret;
+}
+
+static int
+iwl_mld_switch_vif_chanctx_reassign(struct ieee80211_hw *hw,
+				    struct ieee80211_vif_chanctx_switch *vifs)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int ret;
+
+	iwl_mld_unassign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+				     vifs[0].old_ctx);
+	ret = iwl_mld_assign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+					 vifs[0].new_ctx);
+	if (ret) {
+		IWL_ERR(mld,
+			"failed to assign new_ctx during channel switch\n");
+		goto out_reassign;
+	}
+
+	return 0;
+
+out_reassign:
+	if (iwl_mld_assign_vif_chanctx(hw, vifs[0].vif, vifs[0].link_conf,
+				       vifs[0].old_ctx))
+		IWL_ERR(mld, "failed to reassign old_ctx after failure\n");
+
+	return ret;
+}
+
+static int
+iwl_mld_switch_vif_chanctx(struct ieee80211_hw *hw,
+			   struct ieee80211_vif_chanctx_switch *vifs,
+			   int n_vifs,
+			   enum ieee80211_chanctx_switch_mode mode)
+{
+	int ret;
+
+	/* we only support a single-vif right now */
+	if (n_vifs > 1)
+		return -EOPNOTSUPP;
+
+	switch (mode) {
+	case CHANCTX_SWMODE_SWAP_CONTEXTS:
+		ret = iwl_mld_switch_vif_chanctx_swap(hw, vifs);
+		break;
+	case CHANCTX_SWMODE_REASSIGN_VIF:
+		ret = iwl_mld_switch_vif_chanctx_reassign(hw, vifs);
+		break;
+	default:
+		ret = -EOPNOTSUPP;
+		break;
+	}
+
+	return ret;
+}
+
+static void iwl_mld_sta_pre_rcu_remove(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_sta *sta)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link_sta *mld_link_sta;
+	u8 link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* This is called before mac80211 does RCU synchronisation,
+	 * so here we already invalidate our internal RCU-protected
+	 * station pointer. The rest of the code will thus no longer
+	 * be able to find the station this way, and we don't rely
+	 * on further RCU synchronisation after the sta_state()
+	 * callback deleted the station.
+	 */
+	for_each_mld_link_sta(mld_sta, mld_link_sta, link_id)
+		RCU_INIT_POINTER(mld->fw_id_to_link_sta[mld_link_sta->fw_id],
+				 NULL);
+
+	if (sta == mld_vif->ap_sta)
+		mld_vif->ap_sta = NULL;
+}
+
+static void
+iwl_mld_mac80211_mgd_protect_tdls_discover(struct ieee80211_hw *hw,
+					   struct ieee80211_vif *vif,
+					   unsigned int link_id)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct ieee80211_bss_conf *link_conf;
+	u32 duration;
+	int ret;
+
+	link_conf = wiphy_dereference(hw->wiphy, vif->link_conf[link_id]);
+	if (WARN_ON_ONCE(!link_conf))
+		return;
+
+	/* Protect the session to hear the TDLS setup response on the channel */
+
+	duration = 2 * link_conf->dtim_period * link_conf->beacon_int;
+
+	ret = iwl_mld_start_session_protection(mld, vif, duration, duration,
+					       link_id, HZ / 5);
+	if (ret)
+		IWL_ERR(mld,
+			"Failed to start session protection for TDLS: %d\n",
+			ret);
+}
+
+static bool iwl_mld_can_activate_links(struct ieee80211_hw *hw,
+				       struct ieee80211_vif *vif,
+				       u16 desired_links)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	int n_links = hweight16(desired_links);
+
+	/* Check if HW supports the wanted number of links */
+	return n_links <= iwl_mld_max_active_links(mld, vif);
+}
+
+static int
+iwl_mld_change_vif_links(struct ieee80211_hw *hw,
+			 struct ieee80211_vif *vif,
+			 u16 old_links, u16 new_links,
+			 struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS])
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct ieee80211_bss_conf *link_conf;
+	u16 removed = old_links & ~new_links;
+	u16 added = new_links & ~old_links;
+	int err;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/*
+	 * No bits designate non-MLO mode. We can handle MLO exit/enter by
+	 * simply mapping that to link ID zero internally.
+	 * Note that mac80211 does such a non-MLO to MLO switch during restart
+	 * if it was in MLO before. In that case, we do not have a link to
+	 * remove.
+	 */
+	if (old_links == 0 && !mld->fw_status.in_hw_restart)
+		removed |= BIT(0);
+
+	if (new_links == 0)
+		added |= BIT(0);
+
+	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
+		if (removed & BIT(i)) {
+			link_conf = old[i];
+
+			err = iwl_mld_remove_link(mld, link_conf);
+			if (err)
+				return err;
+		}
+	}
+
+	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
+		if (added & BIT(i)) {
+			link_conf = link_conf_dereference_protected(vif, i);
+			if (WARN_ON(!link_conf))
+				return -EINVAL;
+
+			err = iwl_mld_add_link(mld, link_conf);
+			if (err)
+				goto remove_added_links;
+		}
+	}
+
+	/*
+	 * Ensure we always have a valid primary_link. When using multiple
+	 * links the proper value is set in assign_vif_chanctx.
+	 */
+	mld_vif->emlsr.primary = new_links ? __ffs(new_links) : 0;
+
+	/*
+	 * Special MLO restart case. We did not have a link when the interface
+	 * was added, so do the power configuration now.
+	 */
+	if (old_links == 0 && mld->fw_status.in_hw_restart)
+		iwl_mld_update_mac_power(mld, vif, false);
+
+	return 0;
+
+remove_added_links:
+	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
+		if (!(added & BIT(i)))
+			continue;
+
+		link_conf = link_conf_dereference_protected(vif, i);
+		if (!link_conf || !iwl_mld_link_from_mac80211(link_conf))
+			continue;
+
+		iwl_mld_remove_link(mld, link_conf);
+	}
+
+	return err;
+}
+
+static int iwl_mld_change_sta_links(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    struct ieee80211_sta *sta,
+				    u16 old_links, u16 new_links)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	return iwl_mld_update_link_stas(mld, vif, sta, old_links, new_links);
+}
+
+static int iwl_mld_mac80211_join_ibss(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif)
+{
+	return iwl_mld_start_ap_ibss(hw, vif, &vif->bss_conf);
+}
+
+static void iwl_mld_mac80211_leave_ibss(struct ieee80211_hw *hw,
+					struct ieee80211_vif *vif)
+{
+	return iwl_mld_stop_ap_ibss(hw, vif, &vif->bss_conf);
+}
+
+static int iwl_mld_mac80211_tx_last_beacon(struct ieee80211_hw *hw)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	return mld->ibss_manager;
+}
+
+#define IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS_TIMEOUT (5 * HZ)
+
+static void iwl_mld_vif_iter_emlsr_block_tmp_non_bss(void *_data, u8 *mac,
+						     struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	if (!iwl_mld_vif_has_emlsr_cap(vif))
+		return;
+
+	ret = iwl_mld_block_emlsr_sync(mld_vif->mld, vif,
+				       IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS,
+				       iwl_mld_get_primary_link(vif));
+	if (ret)
+		return;
+
+	wiphy_delayed_work_queue(mld_vif->mld->wiphy,
+				 &mld_vif->emlsr.tmp_non_bss_done_wk,
+				 IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS_TIMEOUT);
+}
+
+static void iwl_mld_prep_add_interface(struct ieee80211_hw *hw,
+				       enum nl80211_iftype type)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	IWL_DEBUG_MAC80211(mld, "prep_add_interface: type=%u\n", type);
+
+	if (!(type == NL80211_IFTYPE_AP ||
+	      type == NL80211_IFTYPE_P2P_GO ||
+	      type == NL80211_IFTYPE_P2P_CLIENT))
+		return;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_block_tmp_non_bss,
+						NULL);
+}
+
+static int iwl_mld_set_hw_timestamp(struct ieee80211_hw *hw,
+				    struct ieee80211_vif *vif,
+				    struct cfg80211_set_hw_timestamp *hwts)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	u32 protocols = 0;
+
+	/* HW timestamping is only supported for a specific station */
+	if (!hwts->macaddr)
+		return -EOPNOTSUPP;
+
+	if (hwts->enable)
+		protocols =
+			IWL_TIME_SYNC_PROTOCOL_TM | IWL_TIME_SYNC_PROTOCOL_FTM;
+
+	return iwl_mld_time_sync_config(mld, hwts->macaddr, protocols);
+}
+
+static int iwl_mld_start_pmsr(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct cfg80211_pmsr_request *request)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+
+	return iwl_mld_ftm_start(mld, vif, request);
+}
+
+const struct ieee80211_ops iwl_mld_hw_ops = {
+	.tx = iwl_mld_mac80211_tx,
+	.start = iwl_mld_mac80211_start,
+	.stop = iwl_mld_mac80211_stop,
+	.config = iwl_mld_mac80211_config,
+	.add_interface = iwl_mld_mac80211_add_interface,
+	.remove_interface = iwl_mld_mac80211_remove_interface,
+	.conf_tx = iwl_mld_mac80211_conf_tx,
+	.prepare_multicast = iwl_mld_mac80211_prepare_multicast,
+	.configure_filter = iwl_mld_mac80211_configure_filter,
+	.reconfig_complete = iwl_mld_mac80211_reconfig_complete,
+	.wake_tx_queue = iwl_mld_mac80211_wake_tx_queue,
+	.add_chanctx = iwl_mld_add_chanctx,
+	.remove_chanctx = iwl_mld_remove_chanctx,
+	.change_chanctx = iwl_mld_change_chanctx,
+	.assign_vif_chanctx = iwl_mld_assign_vif_chanctx,
+	.unassign_vif_chanctx = iwl_mld_unassign_vif_chanctx,
+	.set_rts_threshold = iwl_mld_mac80211_set_rts_threshold,
+	.link_info_changed = iwl_mld_mac80211_link_info_changed,
+	.vif_cfg_changed = iwl_mld_mac80211_vif_cfg_changed,
+	.set_key = iwl_mld_mac80211_set_key,
+	.hw_scan = iwl_mld_mac80211_hw_scan,
+	.cancel_hw_scan = iwl_mld_mac80211_cancel_hw_scan,
+	.sched_scan_start = iwl_mld_mac80211_sched_scan_start,
+	.sched_scan_stop = iwl_mld_mac80211_sched_scan_stop,
+	.mgd_prepare_tx = iwl_mld_mac80211_mgd_prepare_tx,
+	.mgd_complete_tx = iwl_mld_mac_mgd_complete_tx,
+	.sta_state = iwl_mld_mac80211_sta_state,
+	.sta_statistics = iwl_mld_mac80211_sta_statistics,
+	.flush = iwl_mld_mac80211_flush,
+	.flush_sta = iwl_mld_mac80211_flush_sta,
+	.ampdu_action = iwl_mld_mac80211_ampdu_action,
+	.can_aggregate_in_amsdu = iwl_mld_mac80211_can_aggregate,
+	.sync_rx_queues = iwl_mld_mac80211_sync_rx_queues,
+	.link_sta_rc_update = iwl_mld_sta_rc_update,
+	.start_ap = iwl_mld_start_ap_ibss,
+	.stop_ap = iwl_mld_stop_ap_ibss,
+	.pre_channel_switch = iwl_mld_pre_channel_switch,
+	.channel_switch = iwl_mld_channel_switch,
+	.post_channel_switch = iwl_mld_post_channel_switch,
+	.abort_channel_switch = iwl_mld_abort_channel_switch,
+	.switch_vif_chanctx = iwl_mld_switch_vif_chanctx,
+	.sta_pre_rcu_remove = iwl_mld_sta_pre_rcu_remove,
+	.remain_on_channel = iwl_mld_start_roc,
+	.cancel_remain_on_channel = iwl_mld_cancel_roc,
+	.can_activate_links = iwl_mld_can_activate_links,
+	.change_vif_links = iwl_mld_change_vif_links,
+	.change_sta_links = iwl_mld_change_sta_links,
+#ifdef CONFIG_PM_SLEEP
+	.suspend = iwl_mld_suspend,
+	.resume = iwl_mld_resume,
+	.set_wakeup = iwl_mld_set_wakeup,
+	.set_rekey_data = iwl_mld_set_rekey_data,
+#if IS_ENABLED(CONFIG_IPV6)
+	.ipv6_addr_change = iwl_mld_ipv6_addr_change,
+#endif /* IS_ENABLED(CONFIG_IPV6) */
+#endif /* CONFIG_PM_SLEEP */
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	.vif_add_debugfs = iwl_mld_add_vif_debugfs,
+	.link_add_debugfs = iwl_mld_add_link_debugfs,
+	.link_sta_add_debugfs = iwl_mld_add_link_sta_debugfs,
+#endif
+	.mgd_protect_tdls_discover = iwl_mld_mac80211_mgd_protect_tdls_discover,
+	.join_ibss = iwl_mld_mac80211_join_ibss,
+	.leave_ibss = iwl_mld_mac80211_leave_ibss,
+	.tx_last_beacon = iwl_mld_mac80211_tx_last_beacon,
+	.prep_add_interface = iwl_mld_prep_add_interface,
+	.set_hw_timestamp = iwl_mld_set_hw_timestamp,
+	.start_pmsr = iwl_mld_start_pmsr,
+};
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.h b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.h
new file mode 100644
index 0000000000000..aad04d7b2617d
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_mac80211_h__
+#define __iwl_mld_mac80211_h__
+
+#include "mld.h"
+
+int iwl_mld_register_hw(struct iwl_mld *mld);
+void iwl_mld_recalc_multicast_filter(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_mac80211_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mcc.c b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c
new file mode 100644
index 0000000000000..daca14e208bde
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mcc.c
@@ -0,0 +1,329 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+
+#include <net/cfg80211.h>
+#include <net/mac80211.h>
+
+#include <fw/dbg.h>
+#include <iwl-nvm-parse.h>
+
+#include "mld.h"
+#include "hcmd.h"
+#include "mcc.h"
+
+/* It is the caller's responsibility to free the pointer returned here */
+static struct iwl_mcc_update_resp_v8 *
+iwl_mld_parse_mcc_update_resp_v8(const struct iwl_rx_packet *pkt)
+{
+	const struct iwl_mcc_update_resp_v8 *mcc_resp_v8 = (const void *)pkt->data;
+	int n_channels = __le32_to_cpu(mcc_resp_v8->n_channels);
+	struct iwl_mcc_update_resp_v8 *resp_cp;
+	int notif_len = struct_size(resp_cp, channels, n_channels);
+
+	if (iwl_rx_packet_payload_len(pkt) != notif_len)
+		return ERR_PTR(-EINVAL);
+
+	resp_cp = kmemdup(mcc_resp_v8, notif_len, GFP_KERNEL);
+	if (!resp_cp)
+		return ERR_PTR(-ENOMEM);
+
+	return resp_cp;
+}
+
+/* It is the caller's responsibility to free the pointer returned here */
+static struct iwl_mcc_update_resp_v8 *
+iwl_mld_parse_mcc_update_resp_v5_v6(const struct iwl_rx_packet *pkt)
+{
+	const struct iwl_mcc_update_resp_v4 *mcc_resp_v4 = (const void *)pkt->data;
+	struct iwl_mcc_update_resp_v8 *resp_cp;
+	int n_channels = __le32_to_cpu(mcc_resp_v4->n_channels);
+	int resp_len;
+
+	if (iwl_rx_packet_payload_len(pkt) !=
+	    struct_size(mcc_resp_v4, channels, n_channels))
+		return ERR_PTR(-EINVAL);
+
+	resp_len = struct_size(resp_cp, channels, n_channels);
+	resp_cp = kzalloc(resp_len, GFP_KERNEL);
+	if (!resp_cp)
+		return ERR_PTR(-ENOMEM);
+
+	resp_cp->status = mcc_resp_v4->status;
+	resp_cp->mcc = mcc_resp_v4->mcc;
+	resp_cp->cap = cpu_to_le32(le16_to_cpu(mcc_resp_v4->cap));
+	resp_cp->source_id = mcc_resp_v4->source_id;
+	resp_cp->geo_info = mcc_resp_v4->geo_info;
+	resp_cp->n_channels = mcc_resp_v4->n_channels;
+	memcpy(resp_cp->channels, mcc_resp_v4->channels,
+	       n_channels * sizeof(__le32));
+
+	return resp_cp;
+}
+
+/* It is the caller's responsibility to free the pointer returned here */
+static struct iwl_mcc_update_resp_v8 *
+iwl_mld_update_mcc(struct iwl_mld *mld, const char *alpha2,
+		   enum iwl_mcc_source src_id)
+{
+	int resp_ver = iwl_fw_lookup_notif_ver(mld->fw, LONG_GROUP,
+					       MCC_UPDATE_CMD, 0);
+	struct iwl_mcc_update_cmd mcc_update_cmd = {
+		.mcc = cpu_to_le16(alpha2[0] << 8 | alpha2[1]),
+		.source_id = (u8)src_id,
+	};
+	struct iwl_mcc_update_resp_v8 *resp_cp;
+	struct iwl_rx_packet *pkt;
+	struct iwl_host_cmd cmd = {
+		.id = MCC_UPDATE_CMD,
+		.flags = CMD_WANT_SKB,
+		.data = { &mcc_update_cmd },
+		.len[0] = sizeof(mcc_update_cmd),
+	};
+	int ret;
+	u16 mcc;
+
+	IWL_DEBUG_LAR(mld, "send MCC update to FW with '%c%c' src = %d\n",
+		      alpha2[0], alpha2[1], src_id);
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret)
+		return ERR_PTR(ret);
+
+	pkt = cmd.resp_pkt;
+
+	/* For Wifi-7 radios, we get version 8
+	 * For Wifi-6E radios, we get version 6
+	 * For Wifi-6 radios, we get version 5, but 5, 6, and 4 are compatible.
+	 */
+	switch (resp_ver) {
+	case 5:
+	case 6:
+		resp_cp = iwl_mld_parse_mcc_update_resp_v5_v6(pkt);
+		break;
+	case 8:
+		resp_cp = iwl_mld_parse_mcc_update_resp_v8(pkt);
+		break;
+	default:
+		IWL_FW_CHECK_FAILED(mld, "Unknown MCC_UPDATE_CMD version %d\n", resp_ver);
+		resp_cp = ERR_PTR(-EINVAL);
+	}
+
+	if (IS_ERR(resp_cp))
+		goto exit;
+
+	mcc = le16_to_cpu(resp_cp->mcc);
+
+	IWL_FW_CHECK(mld, !mcc, "mcc can't be 0: %d\n", mcc);
+
+	IWL_DEBUG_LAR(mld,
+		      "MCC response status: 0x%x. new MCC: 0x%x ('%c%c')\n",
+		      le32_to_cpu(resp_cp->status), mcc, mcc >> 8, mcc & 0xff);
+
+exit:
+	iwl_free_resp(&cmd);
+	return resp_cp;
+}
+
+/* It is the caller's responsibility to free the pointer returned here */
+struct ieee80211_regdomain *
+iwl_mld_get_regdomain(struct iwl_mld *mld,
+		      const char *alpha2,
+		      enum iwl_mcc_source src_id,
+		      bool *changed)
+{
+	struct ieee80211_regdomain *regd = NULL;
+	struct iwl_mcc_update_resp_v8 *resp;
+	u8 resp_ver = iwl_fw_lookup_notif_ver(mld->fw, IWL_ALWAYS_LONG_GROUP,
+					      MCC_UPDATE_CMD, 0);
+
+	IWL_DEBUG_LAR(mld, "Getting regdomain data for %s from FW\n", alpha2);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	resp = iwl_mld_update_mcc(mld, alpha2, src_id);
+	if (IS_ERR(resp)) {
+		IWL_DEBUG_LAR(mld, "Could not get update from FW %ld\n",
+			      PTR_ERR(resp));
+		resp = NULL;
+		goto out;
+	}
+
+	if (changed) {
+		u32 status = le32_to_cpu(resp->status);
+
+		*changed = (status == MCC_RESP_NEW_CHAN_PROFILE ||
+			    status == MCC_RESP_ILLEGAL);
+	}
+	IWL_DEBUG_LAR(mld, "MCC update response version: %d\n", resp_ver);
+
+	regd = iwl_parse_nvm_mcc_info(mld->trans->dev, mld->cfg,
+				      __le32_to_cpu(resp->n_channels),
+				      resp->channels,
+				      __le16_to_cpu(resp->mcc),
+				      __le16_to_cpu(resp->geo_info),
+				      le32_to_cpu(resp->cap), resp_ver);
+
+	if (IS_ERR(regd)) {
+		IWL_DEBUG_LAR(mld, "Could not get parse update from FW %ld\n",
+			      PTR_ERR(regd));
+		goto out;
+	}
+
+	IWL_DEBUG_LAR(mld, "setting alpha2 from FW to %s (0x%x, 0x%x) src=%d\n",
+		      regd->alpha2, regd->alpha2[0],
+		      regd->alpha2[1], resp->source_id);
+
+	mld->mcc_src = resp->source_id;
+
+	if (!iwl_puncturing_is_allowed_in_bios(mld->bios_enable_puncturing,
+					       le16_to_cpu(resp->mcc)))
+		ieee80211_hw_set(mld->hw, DISALLOW_PUNCTURING);
+	else
+		__clear_bit(IEEE80211_HW_DISALLOW_PUNCTURING, mld->hw->flags);
+
+out:
+	kfree(resp);
+	return regd;
+}
+
+/* It is the caller's responsibility to free the pointer returned here */
+static struct ieee80211_regdomain *
+iwl_mld_get_current_regdomain(struct iwl_mld *mld,
+			      bool *changed)
+{
+	return iwl_mld_get_regdomain(mld, "ZZ",
+				     MCC_SOURCE_GET_CURRENT, changed);
+}
+
+void iwl_mld_update_changed_regdomain(struct iwl_mld *mld)
+{
+	struct ieee80211_regdomain *regd;
+	bool changed;
+
+	regd = iwl_mld_get_current_regdomain(mld, &changed);
+
+	if (IS_ERR_OR_NULL(regd))
+		return;
+
+	if (changed)
+		regulatory_set_wiphy_regd(mld->wiphy, regd);
+	kfree(regd);
+}
+
+static int iwl_mld_apply_last_mcc(struct iwl_mld *mld,
+				  const char *alpha2)
+{
+	struct ieee80211_regdomain *regd;
+	u32 used_src;
+	bool changed;
+	int ret;
+
+	/* save the last source in case we overwrite it below */
+	used_src = mld->mcc_src;
+
+	/* Notify the firmware we support wifi location updates */
+	regd = iwl_mld_get_current_regdomain(mld, NULL);
+	if (!IS_ERR_OR_NULL(regd))
+		kfree(regd);
+
+	/* Now set our last stored MCC and source */
+	regd = iwl_mld_get_regdomain(mld, alpha2, used_src,
+				     &changed);
+	if (IS_ERR_OR_NULL(regd))
+		return -EIO;
+
+	/* update cfg80211 if the regdomain was changed */
+	if (changed)
+		ret = regulatory_set_wiphy_regd_sync(mld->wiphy, regd);
+	else
+		ret = 0;
+
+	kfree(regd);
+	return ret;
+}
+
+int iwl_mld_init_mcc(struct iwl_mld *mld)
+{
+	const struct ieee80211_regdomain *r;
+	struct ieee80211_regdomain *regd;
+	char mcc[3];
+	int retval;
+
+	/* try to replay the last set MCC to FW */
+	r = wiphy_dereference(mld->wiphy, mld->wiphy->regd);
+
+	if (r)
+		return iwl_mld_apply_last_mcc(mld, r->alpha2);
+
+	regd = iwl_mld_get_current_regdomain(mld, NULL);
+	if (IS_ERR_OR_NULL(regd))
+		return -EIO;
+
+	if (!iwl_bios_get_mcc(&mld->fwrt, mcc)) {
+		kfree(regd);
+		regd = iwl_mld_get_regdomain(mld, mcc, MCC_SOURCE_BIOS, NULL);
+		if (IS_ERR_OR_NULL(regd))
+			return -EIO;
+	}
+
+	retval = regulatory_set_wiphy_regd_sync(mld->wiphy, regd);
+
+	kfree(regd);
+	return retval;
+}
+
+static void iwl_mld_find_assoc_vif_iterator(void *data, u8 *mac,
+					    struct ieee80211_vif *vif)
+{
+	bool *assoc = data;
+
+	if (vif->type == NL80211_IFTYPE_STATION &&
+	    vif->cfg.assoc)
+		*assoc = true;
+}
+
+static bool iwl_mld_is_a_vif_assoc(struct iwl_mld *mld)
+{
+	bool assoc = false;
+
+	ieee80211_iterate_active_interfaces_atomic(mld->hw,
+						   IEEE80211_IFACE_ITER_NORMAL,
+						   iwl_mld_find_assoc_vif_iterator,
+						   &assoc);
+	return assoc;
+}
+
+void iwl_mld_handle_update_mcc(struct iwl_mld *mld, struct iwl_rx_packet *pkt)
+{
+	struct iwl_mcc_chub_notif *notif = (void *)pkt->data;
+	enum iwl_mcc_source src;
+	char mcc[3];
+	struct ieee80211_regdomain *regd;
+	bool changed;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (iwl_mld_is_a_vif_assoc(mld) &&
+	    notif->source_id == MCC_SOURCE_WIFI) {
+		IWL_DEBUG_LAR(mld, "Ignore mcc update while associated\n");
+		return;
+	}
+
+	mcc[0] = le16_to_cpu(notif->mcc) >> 8;
+	mcc[1] = le16_to_cpu(notif->mcc) & 0xff;
+	mcc[2] = '\0';
+	src = notif->source_id;
+
+	IWL_DEBUG_LAR(mld,
+		      "RX: received chub update mcc cmd (mcc '%s' src %d)\n",
+		      mcc, src);
+	regd = iwl_mld_get_regdomain(mld, mcc, src, &changed);
+	if (IS_ERR_OR_NULL(regd))
+		return;
+
+	if (changed)
+		regulatory_set_wiphy_regd(mld->hw->wiphy, regd);
+	kfree(regd);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mcc.h b/drivers/net/wireless/intel/iwlwifi/mld/mcc.h
new file mode 100644
index 0000000000000..2b31e5b5e2edf
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mcc.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_mcc_h__
+#define __iwl_mld_mcc_h__
+
+int iwl_mld_init_mcc(struct iwl_mld *mld);
+void iwl_mld_handle_update_mcc(struct iwl_mld *mld, struct iwl_rx_packet *pkt);
+void iwl_mld_update_changed_regdomain(struct iwl_mld *mld);
+struct ieee80211_regdomain *
+iwl_mld_get_regdomain(struct iwl_mld *mld,
+		      const char *alpha2,
+		      enum iwl_mcc_source src_id,
+		      bool *changed);
+
+#endif /* __iwl_mld_mcc_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
new file mode 100644
index 0000000000000..adc3d23aa019f
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -0,0 +1,707 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <net/mac80211.h>
+
+#include "fw/api/rx.h"
+#include "fw/api/datapath.h"
+#include "fw/api/commands.h"
+#include "fw/api/offload.h"
+#include "fw/api/coex.h"
+#include "fw/dbg.h"
+#include "fw/uefi.h"
+
+#include "mld.h"
+#include "mlo.h"
+#include "mac80211.h"
+#include "led.h"
+#include "scan.h"
+#include "tx.h"
+#include "sta.h"
+#include "regulatory.h"
+#include "thermal.h"
+#include "low_latency.h"
+#include "hcmd.h"
+#include "fw/api/location.h"
+
+#define DRV_DESCRIPTION "Intel(R) MLD wireless driver for Linux"
+MODULE_DESCRIPTION(DRV_DESCRIPTION);
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("IWLWIFI");
+
+static const struct iwl_op_mode_ops iwl_mld_ops;
+
+static int __init iwl_mld_init(void)
+{
+	int ret = iwl_opmode_register("iwlmld", &iwl_mld_ops);
+
+	if (ret)
+		pr_err("Unable to register MLD op_mode: %d\n", ret);
+
+	return ret;
+}
+module_init(iwl_mld_init);
+
+static void __exit iwl_mld_exit(void)
+{
+	iwl_opmode_deregister("iwlmld");
+}
+module_exit(iwl_mld_exit);
+
+VISIBLE_IF_IWLWIFI_KUNIT
+void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
+		       const struct iwl_cfg *cfg, const struct iwl_fw *fw,
+		       struct ieee80211_hw *hw, struct dentry *dbgfs_dir)
+{
+	mld->dev = trans->dev;
+	mld->trans = trans;
+	mld->cfg = cfg;
+	mld->fw = fw;
+	mld->hw = hw;
+	mld->wiphy = hw->wiphy;
+	mld->debugfs_dir = dbgfs_dir;
+
+	iwl_notification_wait_init(&mld->notif_wait);
+
+	/* Setup async RX handling */
+	spin_lock_init(&mld->async_handlers_lock);
+	INIT_LIST_HEAD(&mld->async_handlers_list);
+	wiphy_work_init(&mld->async_handlers_wk,
+			iwl_mld_async_handlers_wk);
+
+	/* Dynamic Queue Allocation */
+	spin_lock_init(&mld->add_txqs_lock);
+	INIT_LIST_HEAD(&mld->txqs_to_add);
+	wiphy_work_init(&mld->add_txqs_wk, iwl_mld_add_txqs_wk);
+
+	/* Setup RX queues sync wait queue */
+	init_waitqueue_head(&mld->rxq_sync.waitq);
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_construct_mld);
+
+static void __acquires(&mld->wiphy->mtx)
+iwl_mld_fwrt_dump_start(void *ctx)
+{
+	struct iwl_mld *mld = ctx;
+
+	wiphy_lock(mld->wiphy);
+}
+
+static void __releases(&mld->wiphy->mtx)
+iwl_mld_fwrt_dump_end(void *ctx)
+{
+	struct iwl_mld *mld = ctx;
+
+	wiphy_unlock(mld->wiphy);
+}
+
+static bool iwl_mld_d3_debug_enable(void *ctx)
+{
+	return IWL_MLD_D3_DEBUG;
+}
+
+static int iwl_mld_fwrt_send_hcmd(void *ctx, struct iwl_host_cmd *host_cmd)
+{
+	struct iwl_mld *mld = (struct iwl_mld *)ctx;
+	int ret;
+
+	wiphy_lock(mld->wiphy);
+	ret = iwl_mld_send_cmd(mld, host_cmd);
+	wiphy_unlock(mld->wiphy);
+
+	return ret;
+}
+
+static const struct iwl_fw_runtime_ops iwl_mld_fwrt_ops = {
+	.dump_start = iwl_mld_fwrt_dump_start,
+	.dump_end = iwl_mld_fwrt_dump_end,
+	.send_hcmd = iwl_mld_fwrt_send_hcmd,
+	.d3_debug_enable = iwl_mld_d3_debug_enable,
+};
+
+static void
+iwl_mld_construct_fw_runtime(struct iwl_mld *mld, struct iwl_trans *trans,
+			     const struct iwl_fw *fw,
+			     struct dentry *debugfs_dir)
+{
+	iwl_fw_runtime_init(&mld->fwrt, trans, fw, &iwl_mld_fwrt_ops, mld,
+			    NULL, NULL, debugfs_dir);
+
+	iwl_fw_set_current_image(&mld->fwrt, IWL_UCODE_REGULAR);
+}
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_legacy_names[] = {
+	HCMD_NAME(UCODE_ALIVE_NTFY),
+	HCMD_NAME(INIT_COMPLETE_NOTIF),
+	HCMD_NAME(PHY_CONTEXT_CMD),
+	HCMD_NAME(SCAN_CFG_CMD),
+	HCMD_NAME(SCAN_REQ_UMAC),
+	HCMD_NAME(SCAN_ABORT_UMAC),
+	HCMD_NAME(SCAN_COMPLETE_UMAC),
+	HCMD_NAME(TX_CMD),
+	HCMD_NAME(TXPATH_FLUSH),
+	HCMD_NAME(LEDS_CMD),
+	HCMD_NAME(WNM_80211V_TIMING_MEASUREMENT_NOTIFICATION),
+	HCMD_NAME(WNM_80211V_TIMING_MEASUREMENT_CONFIRM_NOTIFICATION),
+	HCMD_NAME(SCAN_OFFLOAD_UPDATE_PROFILES_CMD),
+	HCMD_NAME(POWER_TABLE_CMD),
+	HCMD_NAME(PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION),
+	HCMD_NAME(BEACON_NOTIFICATION),
+	HCMD_NAME(BEACON_TEMPLATE_CMD),
+	HCMD_NAME(TX_ANT_CONFIGURATION_CMD),
+	HCMD_NAME(REDUCE_TX_POWER_CMD),
+	HCMD_NAME(MISSED_BEACONS_NOTIFICATION),
+	HCMD_NAME(MAC_PM_POWER_TABLE),
+	HCMD_NAME(MFUART_LOAD_NOTIFICATION),
+	HCMD_NAME(RSS_CONFIG_CMD),
+	HCMD_NAME(SCAN_ITERATION_COMPLETE_UMAC),
+	HCMD_NAME(REPLY_RX_MPDU_CMD),
+	HCMD_NAME(BA_NOTIF),
+	HCMD_NAME(MCC_UPDATE_CMD),
+	HCMD_NAME(MCC_CHUB_UPDATE_CMD),
+	HCMD_NAME(MCAST_FILTER_CMD),
+	HCMD_NAME(REPLY_BEACON_FILTERING_CMD),
+	HCMD_NAME(PROT_OFFLOAD_CONFIG_CMD),
+	HCMD_NAME(MATCH_FOUND_NOTIFICATION),
+	HCMD_NAME(WOWLAN_PATTERNS),
+	HCMD_NAME(WOWLAN_CONFIGURATION),
+	HCMD_NAME(WOWLAN_TSC_RSC_PARAM),
+	HCMD_NAME(WOWLAN_KEK_KCK_MATERIAL),
+	HCMD_NAME(DEBUG_HOST_COMMAND),
+	HCMD_NAME(LDBG_CONFIG_CMD),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_system_names[] = {
+	HCMD_NAME(SHARED_MEM_CFG_CMD),
+	HCMD_NAME(SOC_CONFIGURATION_CMD),
+	HCMD_NAME(INIT_EXTENDED_CFG_CMD),
+	HCMD_NAME(FW_ERROR_RECOVERY_CMD),
+	HCMD_NAME(RFI_GET_FREQ_TABLE_CMD),
+	HCMD_NAME(SYSTEM_STATISTICS_CMD),
+	HCMD_NAME(SYSTEM_STATISTICS_END_NOTIF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_reg_and_nvm_names[] = {
+	HCMD_NAME(LARI_CONFIG_CHANGE),
+	HCMD_NAME(NVM_GET_INFO),
+	HCMD_NAME(TAS_CONFIG),
+	HCMD_NAME(SAR_OFFSET_MAPPING_TABLE_CMD),
+	HCMD_NAME(MCC_ALLOWED_AP_TYPE_CMD),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_debug_names[] = {
+	HCMD_NAME(HOST_EVENT_CFG),
+	HCMD_NAME(DBGC_SUSPEND_RESUME),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_mac_conf_names[] = {
+	HCMD_NAME(LOW_LATENCY_CMD),
+	HCMD_NAME(SESSION_PROTECTION_CMD),
+	HCMD_NAME(MAC_CONFIG_CMD),
+	HCMD_NAME(LINK_CONFIG_CMD),
+	HCMD_NAME(STA_CONFIG_CMD),
+	HCMD_NAME(AUX_STA_CMD),
+	HCMD_NAME(STA_REMOVE_CMD),
+	HCMD_NAME(ROC_CMD),
+	HCMD_NAME(MISSED_BEACONS_NOTIF),
+	HCMD_NAME(EMLSR_TRANS_FAIL_NOTIF),
+	HCMD_NAME(ROC_NOTIF),
+	HCMD_NAME(CHANNEL_SWITCH_ERROR_NOTIF),
+	HCMD_NAME(SESSION_PROTECTION_NOTIF),
+	HCMD_NAME(PROBE_RESPONSE_DATA_NOTIF),
+	HCMD_NAME(CHANNEL_SWITCH_START_NOTIF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_data_path_names[] = {
+	HCMD_NAME(TRIGGER_RX_QUEUES_NOTIF_CMD),
+	HCMD_NAME(WNM_PLATFORM_PTM_REQUEST_CMD),
+	HCMD_NAME(WNM_80211V_TIMING_MEASUREMENT_CONFIG_CMD),
+	HCMD_NAME(RFH_QUEUE_CONFIG_CMD),
+	HCMD_NAME(TLC_MNG_CONFIG_CMD),
+	HCMD_NAME(RX_BAID_ALLOCATION_CONFIG_CMD),
+	HCMD_NAME(SCD_QUEUE_CONFIG_CMD),
+	HCMD_NAME(OMI_SEND_STATUS_NOTIF),
+	HCMD_NAME(ESR_MODE_NOTIF),
+	HCMD_NAME(MONITOR_NOTIF),
+	HCMD_NAME(TLC_MNG_UPDATE_NOTIF),
+	HCMD_NAME(MU_GROUP_MGMT_NOTIF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_location_names[] = {
+	HCMD_NAME(TOF_RANGE_REQ_CMD),
+	HCMD_NAME(TOF_RANGE_RESPONSE_NOTIF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_phy_names[] = {
+	HCMD_NAME(CMD_DTS_MEASUREMENT_TRIGGER_WIDE),
+	HCMD_NAME(CTDP_CONFIG_CMD),
+	HCMD_NAME(TEMP_REPORTING_THRESHOLDS_CMD),
+	HCMD_NAME(PER_CHAIN_LIMIT_OFFSET_CMD),
+	HCMD_NAME(CT_KILL_NOTIFICATION),
+	HCMD_NAME(DTS_MEASUREMENT_NOTIF_WIDE),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_statistics_names[] = {
+	HCMD_NAME(STATISTICS_OPER_NOTIF),
+	HCMD_NAME(STATISTICS_OPER_PART1_NOTIF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_prot_offload_names[] = {
+	HCMD_NAME(STORED_BEACON_NTF),
+};
+
+/* Please keep this array *SORTED* by hex value.
+ * Access is done through binary search
+ */
+static const struct iwl_hcmd_names iwl_mld_coex_names[] = {
+	HCMD_NAME(PROFILE_NOTIF),
+};
+
+VISIBLE_IF_IWLWIFI_KUNIT
+const struct iwl_hcmd_arr iwl_mld_groups[] = {
+	[LEGACY_GROUP] = HCMD_ARR(iwl_mld_legacy_names),
+	[LONG_GROUP] = HCMD_ARR(iwl_mld_legacy_names),
+	[SYSTEM_GROUP] = HCMD_ARR(iwl_mld_system_names),
+	[MAC_CONF_GROUP] = HCMD_ARR(iwl_mld_mac_conf_names),
+	[DATA_PATH_GROUP] = HCMD_ARR(iwl_mld_data_path_names),
+	[LOCATION_GROUP] = HCMD_ARR(iwl_mld_location_names),
+	[REGULATORY_AND_NVM_GROUP] = HCMD_ARR(iwl_mld_reg_and_nvm_names),
+	[DEBUG_GROUP] = HCMD_ARR(iwl_mld_debug_names),
+	[PHY_OPS_GROUP] = HCMD_ARR(iwl_mld_phy_names),
+	[STATISTICS_GROUP] = HCMD_ARR(iwl_mld_statistics_names),
+	[PROT_OFFLOAD_GROUP] = HCMD_ARR(iwl_mld_prot_offload_names),
+	[BT_COEX_GROUP] = HCMD_ARR(iwl_mld_coex_names),
+};
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_groups);
+
+#if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
+const unsigned int global_iwl_mld_goups_size = ARRAY_SIZE(iwl_mld_groups);
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(global_iwl_mld_goups_size);
+#endif
+
+static void
+iwl_mld_configure_trans(struct iwl_op_mode *op_mode)
+{
+	const struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	static const u8 no_reclaim_cmds[] = {TX_CMD};
+	struct iwl_trans_config trans_cfg = {
+		.op_mode = op_mode,
+		/* Rx is not supported yet, but add it to avoid warnings */
+		.rx_buf_size = iwl_amsdu_size_to_rxb_size(),
+		.command_groups = iwl_mld_groups,
+		.command_groups_size = ARRAY_SIZE(iwl_mld_groups),
+		.fw_reset_handshake = true,
+		.queue_alloc_cmd_ver =
+			iwl_fw_lookup_cmd_ver(mld->fw,
+					      WIDE_ID(DATA_PATH_GROUP,
+						      SCD_QUEUE_CONFIG_CMD),
+					      0),
+		.no_reclaim_cmds = no_reclaim_cmds,
+		.n_no_reclaim_cmds = ARRAY_SIZE(no_reclaim_cmds),
+		.cb_data_offs = offsetof(struct ieee80211_tx_info,
+					 driver_data[2]),
+	};
+	struct iwl_trans *trans = mld->trans;
+
+	trans->rx_mpdu_cmd = REPLY_RX_MPDU_CMD;
+	trans->iml = mld->fw->iml;
+	trans->iml_len = mld->fw->iml_len;
+	trans->wide_cmd_header = true;
+
+	iwl_trans_configure(trans, &trans_cfg);
+}
+
+/*
+ *****************************************************
+ * op mode ops functions
+ *****************************************************
+ */
+
+#define NUM_FW_LOAD_RETRIES	3
+static struct iwl_op_mode *
+iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
+		      const struct iwl_fw *fw, struct dentry *dbgfs_dir)
+{
+	struct ieee80211_hw *hw;
+	struct iwl_op_mode *op_mode;
+	struct iwl_mld *mld;
+	u32 eckv_value;
+	int ret;
+
+	/* Allocate and initialize a new hardware device */
+	hw = ieee80211_alloc_hw(sizeof(struct iwl_op_mode) +
+				sizeof(struct iwl_mld),
+				&iwl_mld_hw_ops);
+	if (!hw)
+		return ERR_PTR(-ENOMEM);
+
+	op_mode = hw->priv;
+
+	op_mode->ops = &iwl_mld_ops;
+
+	mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	iwl_construct_mld(mld, trans, cfg, fw, hw, dbgfs_dir);
+
+	iwl_mld_construct_fw_runtime(mld, trans, fw, dbgfs_dir);
+
+	iwl_mld_get_bios_tables(mld);
+	iwl_uefi_get_sgom_table(trans, &mld->fwrt);
+	iwl_uefi_get_step_table(trans);
+	if (iwl_bios_get_eckv(&mld->fwrt, &eckv_value))
+		IWL_DEBUG_RADIO(mld, "ECKV table doesn't exist in BIOS\n");
+	else
+		trans->ext_32khz_clock_valid = !!eckv_value;
+	iwl_bios_setup_step(trans, &mld->fwrt);
+	mld->bios_enable_puncturing = iwl_uefi_get_puncturing(&mld->fwrt);
+
+	/* Configure transport layer with the opmode specific params */
+	iwl_mld_configure_trans(op_mode);
+
+	/* Needed for sending commands */
+	wiphy_lock(mld->wiphy);
+
+	for (int i = 0; i < NUM_FW_LOAD_RETRIES; i++) {
+		ret = iwl_mld_load_fw(mld);
+		if (!ret)
+			break;
+	}
+
+	if (ret) {
+		wiphy_unlock(mld->wiphy);
+		iwl_fw_flush_dumps(&mld->fwrt);
+		goto free_hw;
+	}
+
+	iwl_mld_stop_fw(mld);
+
+	wiphy_unlock(mld->wiphy);
+
+	ret = iwl_mld_leds_init(mld);
+	if (ret)
+		goto free_nvm;
+
+	ret = iwl_mld_alloc_scan_cmd(mld);
+	if (ret)
+		goto leds_exit;
+
+	ret = iwl_mld_low_latency_init(mld);
+	if (ret)
+		goto free_scan_cmd;
+
+	ret = iwl_mld_register_hw(mld);
+	if (ret)
+		goto low_latency_free;
+
+	iwl_mld_toggle_tx_ant(mld, &mld->mgmt_tx_ant);
+
+	iwl_mld_add_debugfs_files(mld, dbgfs_dir);
+	iwl_mld_thermal_initialize(mld);
+
+	iwl_mld_ptp_init(mld);
+
+	return op_mode;
+
+low_latency_free:
+	iwl_mld_low_latency_free(mld);
+free_scan_cmd:
+	kfree(mld->scan.cmd);
+leds_exit:
+	iwl_mld_leds_exit(mld);
+free_nvm:
+	kfree(mld->nvm_data);
+free_hw:
+	ieee80211_free_hw(mld->hw);
+	return ERR_PTR(ret);
+}
+
+static void
+iwl_op_mode_mld_stop(struct iwl_op_mode *op_mode)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	iwl_mld_ptp_remove(mld);
+	iwl_mld_leds_exit(mld);
+
+	wiphy_lock(mld->wiphy);
+	iwl_mld_thermal_exit(mld);
+	iwl_mld_low_latency_stop(mld);
+	iwl_mld_deinit_time_sync(mld);
+	wiphy_unlock(mld->wiphy);
+
+	ieee80211_unregister_hw(mld->hw);
+
+	iwl_fw_runtime_free(&mld->fwrt);
+	iwl_mld_low_latency_free(mld);
+
+	iwl_trans_op_mode_leave(mld->trans);
+
+	kfree(mld->nvm_data);
+	kfree(mld->scan.cmd);
+	kfree(mld->error_recovery_buf);
+	kfree(mld->mcast_filter_cmd);
+
+	ieee80211_free_hw(mld->hw);
+}
+
+static void iwl_mld_queue_state_change(struct iwl_op_mode *op_mode,
+				       int hw_queue, bool queue_full)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	struct ieee80211_txq *txq;
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_txq *mld_txq;
+
+	rcu_read_lock();
+
+	txq = rcu_dereference(mld->fw_id_to_txq[hw_queue]);
+	if (!txq) {
+		rcu_read_unlock();
+
+		if (queue_full) {
+			/* An internal queue is not expected to become full */
+			IWL_WARN(mld,
+				 "Internal hw_queue %d is full! stopping all queues\n",
+				 hw_queue);
+			/* Stop all queues, as an internal queue is not
+			 * mapped to a mac80211 one
+			 */
+			ieee80211_stop_queues(mld->hw);
+		} else {
+			ieee80211_wake_queues(mld->hw);
+		}
+
+		return;
+	}
+
+	mld_txq = iwl_mld_txq_from_mac80211(txq);
+	mld_sta = txq->sta ? iwl_mld_sta_from_mac80211(txq->sta) : NULL;
+
+	mld_txq->status.stop_full = queue_full;
+
+	if (!queue_full && mld_sta &&
+	    mld_sta->sta_state != IEEE80211_STA_NOTEXIST) {
+		local_bh_disable();
+		iwl_mld_tx_from_txq(mld, txq);
+		local_bh_enable();
+	}
+
+	rcu_read_unlock();
+}
+
+static void
+iwl_mld_queue_full(struct iwl_op_mode *op_mode, int hw_queue)
+{
+	iwl_mld_queue_state_change(op_mode, hw_queue, true);
+}
+
+static void
+iwl_mld_queue_not_full(struct iwl_op_mode *op_mode, int hw_queue)
+{
+	iwl_mld_queue_state_change(op_mode, hw_queue, false);
+}
+
+static bool
+iwl_mld_set_hw_rfkill_state(struct iwl_op_mode *op_mode, bool state)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	iwl_mld_set_hwkill(mld, state);
+
+	return false;
+}
+
+static void
+iwl_mld_free_skb(struct iwl_op_mode *op_mode, struct sk_buff *skb)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+	iwl_trans_free_tx_cmd(mld->trans, info->driver_data[1]);
+	ieee80211_free_txskb(mld->hw, skb);
+}
+
+static void iwl_mld_read_error_recovery_buffer(struct iwl_mld *mld)
+{
+	u32 src_size = mld->fw->ucode_capa.error_log_size;
+	u32 src_addr = mld->fw->ucode_capa.error_log_addr;
+	u8 *recovery_buf;
+	int ret;
+
+	/* no recovery buffer size defined in a TLV */
+	if (!src_size)
+		return;
+
+	recovery_buf = kzalloc(src_size, GFP_ATOMIC);
+	if (!recovery_buf)
+		return;
+
+	ret = iwl_trans_read_mem_bytes(mld->trans, src_addr,
+				       recovery_buf, src_size);
+	if (ret) {
+		IWL_ERR(mld, "Failed to read error recovery buffer (%d)\n",
+			ret);
+		kfree(recovery_buf);
+		return;
+	}
+
+	mld->error_recovery_buf = recovery_buf;
+}
+
+static void iwl_mld_restart_nic(struct iwl_mld *mld)
+{
+	iwl_mld_read_error_recovery_buffer(mld);
+
+	mld->fwrt.trans->dbg.restart_required = false;
+
+	ieee80211_restart_hw(mld->hw);
+}
+
+static void
+iwl_mld_nic_error(struct iwl_op_mode *op_mode,
+		  enum iwl_fw_error_type type)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	bool trans_dead = test_bit(STATUS_TRANS_DEAD, &mld->trans->status);
+
+	if (type == IWL_ERR_TYPE_CMD_QUEUE_FULL)
+		IWL_ERR(mld, "Command queue full!\n");
+	else if (!trans_dead && !mld->fw_status.do_not_dump_once)
+		iwl_fwrt_dump_error_logs(&mld->fwrt);
+
+	mld->fw_status.do_not_dump_once = false;
+
+	/* It is necessary to abort any os scan here because mac80211 requires
+	 * having the scan cleared before restarting.
+	 * We'll reset the scan_status to NONE in restart cleanup in
+	 * the next drv_start() call from mac80211. If ieee80211_hw_restart
+	 * isn't called scan status will stay busy.
+	 */
+	iwl_mld_report_scan_aborted(mld);
+
+	/*
+	 * This should be first thing before trying to collect any
+	 * data to avoid endless loops if any HW error happens while
+	 * collecting debug data.
+	 * It might not actually be true that we'll restart, but the
+	 * setting doesn't matter if we're going to be unbound either.
+	 */
+	if (type != IWL_ERR_TYPE_RESET_HS_TIMEOUT)
+		mld->fw_status.in_hw_restart = true;
+}
+
+static void iwl_mld_dump_error(struct iwl_op_mode *op_mode,
+			       struct iwl_fw_error_dump_mode *mode)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	/* if we come in from opmode we have the mutex held */
+	if (mode->context == IWL_ERR_CONTEXT_FROM_OPMODE) {
+		lockdep_assert_wiphy(mld->wiphy);
+		iwl_fw_error_collect(&mld->fwrt);
+	} else {
+		wiphy_lock(mld->wiphy);
+		if (mode->context != IWL_ERR_CONTEXT_ABORT)
+			iwl_fw_error_collect(&mld->fwrt);
+		wiphy_unlock(mld->wiphy);
+	}
+}
+
+static bool iwl_mld_sw_reset(struct iwl_op_mode *op_mode,
+			     enum iwl_fw_error_type type)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	/* Do restart only in the following conditions are met:
+	 * - we consider the FW as running
+	 * - The trigger that brought us here is defined as one that requires
+	 *   a restart (in the debug TLVs)
+	 */
+	if (!mld->fw_status.running || !mld->fwrt.trans->dbg.restart_required)
+		return false;
+
+	iwl_mld_restart_nic(mld);
+	return true;
+}
+
+static void
+iwl_mld_time_point(struct iwl_op_mode *op_mode,
+		   enum iwl_fw_ini_time_point tp_id,
+		   union iwl_dbg_tlv_tp_data *tp_data)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	iwl_dbg_tlv_time_point(&mld->fwrt, tp_id, tp_data);
+}
+
+#ifdef CONFIG_PM_SLEEP
+static void iwl_mld_device_powered_off(struct iwl_op_mode *op_mode)
+{
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+
+	wiphy_lock(mld->wiphy);
+	mld->trans->system_pm_mode = IWL_PLAT_PM_MODE_DISABLED;
+	iwl_mld_stop_fw(mld);
+	mld->fw_status.in_d3 = false;
+	wiphy_unlock(mld->wiphy);
+}
+#else
+static void iwl_mld_device_powered_off(struct iwl_op_mode *op_mode)
+{}
+#endif
+
+static const struct iwl_op_mode_ops iwl_mld_ops = {
+	.start = iwl_op_mode_mld_start,
+	.stop = iwl_op_mode_mld_stop,
+	.rx = iwl_mld_rx,
+	.rx_rss = iwl_mld_rx_rss,
+	.queue_full = iwl_mld_queue_full,
+	.queue_not_full = iwl_mld_queue_not_full,
+	.hw_rf_kill = iwl_mld_set_hw_rfkill_state,
+	.free_skb = iwl_mld_free_skb,
+	.nic_error = iwl_mld_nic_error,
+	.dump_error = iwl_mld_dump_error,
+	.sw_reset = iwl_mld_sw_reset,
+	.time_point = iwl_mld_time_point,
+	.device_powered_off = pm_sleep_ptr(iwl_mld_device_powered_off),
+};
+
+struct iwl_mld_mod_params iwlmld_mod_params = {
+	.power_scheme = IWL_POWER_SCHEME_BPS,
+};
+
+module_param_named(power_scheme, iwlmld_mod_params.power_scheme, int, 0444);
+MODULE_PARM_DESC(power_scheme,
+		 "power management scheme: 1-active, 2-balanced, default: 2");
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
new file mode 100644
index 0000000000000..6eda6081c8b41
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -0,0 +1,584 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_h__
+#define __iwl_mld_h__
+
+#include <linux/leds.h>
+#include <net/mac80211.h>
+
+#include "iwl-trans.h"
+#include "iwl-op-mode.h"
+#include "fw/runtime.h"
+#include "fw/notif-wait.h"
+#include "fw/api/commands.h"
+#include "fw/api/scan.h"
+#include "fw/api/mac-cfg.h"
+#include "fw/api/mac.h"
+#include "fw/api/phy-ctxt.h"
+#include "fw/api/datapath.h"
+#include "fw/api/rx.h"
+#include "fw/api/rs.h"
+#include "fw/api/context.h"
+#include "fw/api/coex.h"
+#include "fw/api/location.h"
+
+#include "fw/dbg.h"
+
+#include "notif.h"
+#include "scan.h"
+#include "rx.h"
+#include "thermal.h"
+#include "low_latency.h"
+#include "constants.h"
+#include "ptp.h"
+#include "time_sync.h"
+
+/**
+ * DOC: Introduction
+ *
+ * iwlmld is an operation mode (a.k.a. op_mode) for Intel wireless devices.
+ * It is used for devices that ship after 2024 which typically support
+ * the WiFi-7 features. MLD stands for multi-link device. Note that there are
+ * devices that do not support WiFi-7 or even WiFi 6E and yet use iwlmld, but
+ * the firmware APIs used in this driver are WiFi-7 compatible.
+ *
+ * In the architecture of iwlwifi, an op_mode is a layer that translates
+ * mac80211's APIs into commands for the firmware and, of course, notifications
+ * from the firmware to mac80211's APIs. An op_mode must implement the
+ * interface defined in iwl-op-mode.h to interact with the transport layer
+ * which allows to send and receive data to the device, start the hardware,
+ * etc...
+ */
+
+/**
+ * DOC: Locking policy
+ *
+ * iwlmld has a very simple locking policy: it doesn't have any mutexes. It
+ * relies on cfg80211's wiphy->mtx and takes the lock when needed. All the
+ * control flows originating from mac80211 already acquired the lock, so that
+ * part is trivial, but also notifications that are received from the firmware
+ * and handled asynchronously are handled only after having taken the lock.
+ * This is described in notif.c.
+ * There are spin_locks needed to synchronize with the data path, around the
+ * allocation of the queues, for example.
+ */
+
+/**
+ * DOC: Debugfs
+ *
+ * iwlmld adds its share of debugfs hooks and its handlers are synchronized
+ * with the wiphy_lock using wiphy_locked_debugfs. This avoids races against
+ * resources deletion while the debugfs hook is being used.
+ */
+
+/**
+ * DOC: Main resources
+ *
+ * iwlmld is designed with the life cycle of the resource in mind. The
+ * resources are:
+ *
+ *  - struct iwl_mld (matches mac80211's struct ieee80211_hw)
+ *
+ *  - struct iwl_mld_vif (matches macu80211's struct ieee80211_vif)
+ *    iwl_mld_vif contains an array of pointers to struct iwl_mld_link
+ *    which describe the links for this vif.
+ *
+ *  - struct iwl_mld_sta (matches mac80211's struct ieee80211_sta)
+ *    iwl_mld_sta contains an array of points to struct iwl_mld_link_sta
+ *    which describes the link stations for this station
+ *
+ * Each object has properties that can survive a firmware reset or not.
+ * Asynchronous firmware notifications can declare themselves as dependent on a
+ * certain instance of those resources and that means that the notifications
+ * will be cancelled once the instance is destroyed.
+ */
+
+#define IWL_MLD_MAX_ADDRESSES		5
+
+/**
+ * struct iwl_mld - MLD op mode
+ *
+ * @fw_id_to_bss_conf: maps a fw id of a link to the corresponding
+ *	ieee80211_bss_conf.
+ * @fw_id_to_vif: maps a fw id of a MAC context to the corresponding
+ *	ieee80211_vif. Mapping is valid only when the MAC exists in the fw.
+ * @fw_id_to_txq: maps a fw id of a txq to the corresponding
+ *	ieee80211_txq.
+ * @used_phy_ids: a bitmap of the phy IDs used. If a bit is set, it means
+ *	that the index of this bit is already used as a PHY id.
+ * @num_igtks: the number if iGTKs that were sent to the FW.
+ * @monitor: monitor related data
+ * @monitor.on: does a monitor vif exist (singleton hence bool)
+ * @monitor.ampdu_ref: the id of the A-MPDU for sniffer
+ * @monitor.ampdu_toggle: the state of the previous packet to track A-MPDU
+ * @monitor.cur_aid: current association id tracked by the sniffer
+ * @monitor.cur_bssid: current bssid tracked by the sniffer
+ * @monitor.p80: primary channel position relative to he whole bandwidth, in
+ * steps of 80 MHz
+ * @fw_id_to_link_sta: maps a fw id of a sta to the corresponding
+ *	ieee80211_link_sta. This is not cleaned up on restart since we want to
+ *	preserve the fw sta ids during a restart (for SN/PN restoring).
+ *	FW ids of internal stations will be mapped to ERR_PTR, and will be
+ *	re-allocated during a restart, so make sure to free it in restart
+ *	cleanup using iwl_mld_free_internal_sta
+ * @netdetect: indicates the FW is in suspend mode with netdetect configured
+ * @p2p_device_vif: points to the p2p device vif if exists
+ * @bt_is_active: indicates that BT is active
+ * @dev: pointer to device struct. For printing purposes
+ * @trans: pointer to the transport layer
+ * @cfg: pointer to the device configuration
+ * @fw: a pointer to the fw object
+ * @hw: pointer to the hw object.
+ * @wiphy: a pointer to the wiphy struct, for easier access to it.
+ * @nvm_data: pointer to the nvm_data that includes all our capabilities
+ * @fwrt: fw runtime data
+ * @debugfs_dir: debugfs directory
+ * @notif_wait: notification wait related data.
+ * @async_handlers_list: a list of all async RX handlers. When a notifciation
+ *	with an async handler is received, it is added to this list.
+ *	When &async_handlers_wk runs - it runs these handlers one by one.
+ * @async_handlers_lock: a lock for &async_handlers_list. Sync
+ *	&async_handlers_wk and RX notifcation path.
+ * @async_handlers_wk: A work to run all async RX handlers from
+ *	&async_handlers_list.
+ * @ct_kill_exit_wk: worker to exit thermal kill
+ * @fw_status: bitmap of fw status bits
+ * @running: true if the firmware is running
+ * @do_not_dump_once: true if firmware dump must be prevented once
+ * @in_d3: indicates FW is in suspend mode and should be resumed
+ * @in_hw_restart: indicates that we are currently in restart flow.
+ *	rather than restarted. Should be unset upon restart.
+ * @radio_kill: bitmap of radio kill status
+ * @radio_kill.hw: radio is killed by hw switch
+ * @radio_kill.ct: radio is killed because the device it too hot
+ * @addresses: device MAC addresses.
+ * @scan: instance of the scan object
+ * @wowlan: WoWLAN support data.
+ * @led: the led device
+ * @mcc_src: the source id of the MCC, comes from the firmware
+ * @bios_enable_puncturing: is puncturing enabled by bios
+ * @fw_id_to_ba: maps a fw (BA) id to a corresponding Block Ack session data.
+ * @num_rx_ba_sessions: tracks the number of active Rx Block Ack (BA) sessions.
+ *	the driver ensures that new BA sessions are blocked once the maximum
+ *	supported by the firmware is reached, preventing firmware asserts.
+ * @rxq_sync: manages RX queue sync state
+ * @txqs_to_add: a list of &ieee80211_txq's to allocate in &add_txqs_wk
+ * @add_txqs_wk: a worker to allocate txqs.
+ * @add_txqs_lock: to lock the &txqs_to_add list.
+ * @error_recovery_buf: pointer to the recovery buffer that will be read
+ *	from firmware upon fw/hw error and sent back to the firmware in
+ *	reconfig flow (after NIC reset).
+ * @mcast_filter_cmd: pointer to the multicast filter command.
+ * @mgmt_tx_ant: stores the last TX antenna index; used for setting
+ *	TX rate_n_flags for non-STA mgmt frames (toggles on every TX failure).
+ * @low_latency: low-latency manager.
+ * @tzone: thermal zone device's data
+ * @cooling_dev: cooling device's related data
+ * @ibss_manager: in IBSS mode (only one vif can be active), indicates what
+ *	firmware indicated about having transmitted the last beacon, i.e.
+ *	being IBSS manager for that time and needing to respond to probe
+ *	requests
+ * @ptp_data: data of the PTP clock
+ * @time_sync: time sync data.
+ * @ftm_initiator: FTM initiator data
+ */
+struct iwl_mld {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		struct ieee80211_bss_conf __rcu *fw_id_to_bss_conf[IWL_FW_MAX_LINK_ID + 1];
+		struct ieee80211_vif __rcu *fw_id_to_vif[NUM_MAC_INDEX_DRIVER];
+		struct ieee80211_txq __rcu *fw_id_to_txq[IWL_MAX_TVQM_QUEUES];
+		u8 used_phy_ids: NUM_PHY_CTX;
+		u8 num_igtks;
+		struct {
+			bool on;
+			u32 ampdu_ref;
+			bool ampdu_toggle;
+			u8 p80;
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+			__le16 cur_aid;
+			u8 cur_bssid[ETH_ALEN];
+#endif
+		} monitor;
+#ifdef CONFIG_PM_SLEEP
+		bool netdetect;
+#endif /* CONFIG_PM_SLEEP */
+		struct ieee80211_vif *p2p_device_vif;
+		bool bt_is_active;
+	);
+	struct ieee80211_link_sta __rcu *fw_id_to_link_sta[IWL_STATION_COUNT_MAX];
+	/* And here fields that survive a fw restart */
+	struct device *dev;
+	struct iwl_trans *trans;
+	const struct iwl_cfg *cfg;
+	const struct iwl_fw *fw;
+	struct ieee80211_hw *hw;
+	struct wiphy *wiphy;
+	struct iwl_nvm_data *nvm_data;
+	struct iwl_fw_runtime fwrt;
+	struct dentry *debugfs_dir;
+	struct iwl_notif_wait_data notif_wait;
+	struct list_head async_handlers_list;
+	spinlock_t async_handlers_lock;
+	struct wiphy_work async_handlers_wk;
+	struct wiphy_delayed_work ct_kill_exit_wk;
+
+	struct {
+		u32 running:1,
+		    do_not_dump_once:1,
+#ifdef CONFIG_PM_SLEEP
+		    in_d3:1,
+#endif
+		    in_hw_restart:1;
+
+	} fw_status;
+
+	struct {
+		u32 hw:1,
+		    ct:1;
+	} radio_kill;
+
+	struct mac_address addresses[IWL_MLD_MAX_ADDRESSES];
+	struct iwl_mld_scan scan;
+#ifdef CONFIG_PM_SLEEP
+	struct wiphy_wowlan_support wowlan;
+#endif /* CONFIG_PM_SLEEP */
+#ifdef CONFIG_IWLWIFI_LEDS
+	struct led_classdev led;
+#endif
+	enum iwl_mcc_source mcc_src;
+	bool bios_enable_puncturing;
+
+	struct iwl_mld_baid_data __rcu *fw_id_to_ba[IWL_MAX_BAID];
+	u8 num_rx_ba_sessions;
+
+	struct iwl_mld_rx_queues_sync rxq_sync;
+
+	struct list_head txqs_to_add;
+	struct wiphy_work add_txqs_wk;
+	spinlock_t add_txqs_lock;
+
+	u8 *error_recovery_buf;
+	struct iwl_mcast_filter_cmd *mcast_filter_cmd;
+
+	u8 mgmt_tx_ant;
+
+	struct iwl_mld_low_latency low_latency;
+
+	bool ibss_manager;
+#ifdef CONFIG_THERMAL
+	struct thermal_zone_device *tzone;
+	struct iwl_mld_cooling_device cooling_dev;
+#endif
+
+	struct ptp_data ptp_data;
+
+	struct iwl_mld_time_sync_data __rcu *time_sync;
+
+	struct {
+		struct cfg80211_pmsr_request *req;
+		struct wireless_dev *req_wdev;
+		int responses[IWL_TOF_MAX_APS];
+	} ftm_initiator;
+};
+
+/* memset the part of the struct that requires cleanup on restart */
+#define CLEANUP_STRUCT(_ptr)                             \
+	memset((void *)&(_ptr)->zeroed_on_hw_restart, 0, \
+	       sizeof((_ptr)->zeroed_on_hw_restart))
+
+/* Cleanup function for struct iwl_mld_vif, will be called in restart */
+static inline void
+iwl_cleanup_mld(struct iwl_mld *mld)
+{
+	CLEANUP_STRUCT(mld);
+	CLEANUP_STRUCT(&mld->scan);
+
+	mld->fw_status.in_d3 = false;
+
+	iwl_mld_low_latency_restart_cleanup(mld);
+
+	/* Empty the list of async notification handlers so we won't process
+	 * notifications from the dead fw after the reconfig flow.
+	 */
+	iwl_mld_purge_async_handlers_list(mld);
+}
+
+enum iwl_power_scheme {
+	IWL_POWER_SCHEME_CAM = 1,
+	IWL_POWER_SCHEME_BPS,
+};
+
+/**
+ * struct iwl_mld_mod_params - module parameters for iwlmld
+ * @power_scheme: one of enum iwl_power_scheme
+ */
+struct iwl_mld_mod_params {
+	int power_scheme;
+};
+
+extern struct iwl_mld_mod_params iwlmld_mod_params;
+
+/* Extract MLD priv from op_mode */
+#define IWL_OP_MODE_GET_MLD(_iwl_op_mode)		\
+	((struct iwl_mld *)(_iwl_op_mode)->op_mode_specific)
+
+#define IWL_MAC80211_GET_MLD(_hw)			\
+	IWL_OP_MODE_GET_MLD((struct iwl_op_mode *)((_hw)->priv))
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+void
+iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir);
+#else
+static inline void
+iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir)
+{}
+#endif
+
+int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld);
+int iwl_mld_load_fw(struct iwl_mld *mld);
+void iwl_mld_stop_fw(struct iwl_mld *mld);
+int iwl_mld_start_fw(struct iwl_mld *mld);
+void iwl_mld_send_recovery_cmd(struct iwl_mld *mld, u32 flags);
+
+static inline void iwl_mld_set_ctkill(struct iwl_mld *mld, bool state)
+{
+	mld->radio_kill.ct = state;
+
+	wiphy_rfkill_set_hw_state(mld->wiphy,
+				  mld->radio_kill.hw || mld->radio_kill.ct);
+}
+
+static inline void iwl_mld_set_hwkill(struct iwl_mld *mld, bool state)
+{
+	mld->radio_kill.hw = state;
+
+	wiphy_rfkill_set_hw_state(mld->wiphy,
+				  mld->radio_kill.hw || mld->radio_kill.ct);
+}
+
+static inline u8 iwl_mld_get_valid_tx_ant(const struct iwl_mld *mld)
+{
+	u8 tx_ant = mld->fw->valid_tx_ant;
+
+	if (mld->nvm_data && mld->nvm_data->valid_tx_ant)
+		tx_ant &= mld->nvm_data->valid_tx_ant;
+
+	return tx_ant;
+}
+
+static inline u8 iwl_mld_get_valid_rx_ant(const struct iwl_mld *mld)
+{
+	u8 rx_ant = mld->fw->valid_rx_ant;
+
+	if (mld->nvm_data && mld->nvm_data->valid_rx_ant)
+		rx_ant &= mld->nvm_data->valid_rx_ant;
+
+	return rx_ant;
+}
+
+static inline u8 iwl_mld_nl80211_band_to_fw(enum nl80211_band band)
+{
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		return PHY_BAND_24;
+	case NL80211_BAND_5GHZ:
+		return PHY_BAND_5;
+	case NL80211_BAND_6GHZ:
+		return PHY_BAND_6;
+	default:
+		WARN_ONCE(1, "Unsupported band (%u)\n", band);
+		return PHY_BAND_5;
+	}
+}
+
+static inline u8 iwl_mld_phy_band_to_nl80211(u8 phy_band)
+{
+	switch (phy_band) {
+	case PHY_BAND_24:
+		return NL80211_BAND_2GHZ;
+	case PHY_BAND_5:
+		return NL80211_BAND_5GHZ;
+	case PHY_BAND_6:
+		return NL80211_BAND_6GHZ;
+	default:
+		WARN_ONCE(1, "Unsupported phy band (%u)\n", phy_band);
+		return NL80211_BAND_5GHZ;
+	}
+}
+
+static inline int
+iwl_mld_legacy_hw_idx_to_mac80211_idx(u32 rate_n_flags,
+				      enum nl80211_band band)
+{
+	int format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
+	int rate = rate_n_flags & RATE_LEGACY_RATE_MSK;
+	bool is_lb = band == NL80211_BAND_2GHZ;
+
+	if (format == RATE_MCS_LEGACY_OFDM_MSK)
+		return is_lb ? rate + IWL_FIRST_OFDM_RATE : rate;
+
+	/* CCK is not allowed in 5 GHz */
+	return is_lb ? rate : -1;
+}
+
+extern const struct ieee80211_ops iwl_mld_hw_ops;
+
+/**
+ * enum iwl_rx_handler_context: context for Rx handler
+ * @RX_HANDLER_SYNC: this means that it will be called in the Rx path
+ *	which can't acquire the wiphy->mutex.
+ * @RX_HANDLER_ASYNC: If the handler needs to hold wiphy->mutex
+ *	(and only in this case!), it should be set as ASYNC. In that case,
+ *	it will be called from a worker with wiphy->mutex held.
+ */
+enum iwl_rx_handler_context {
+	RX_HANDLER_SYNC,
+	RX_HANDLER_ASYNC,
+};
+
+/**
+ * struct iwl_rx_handler: handler for FW notification
+ * @val_fn: input validation function.
+ * @sizes: an array that mapps a version to the expected size.
+ * @fn: the function is called when notification is handled
+ * @cmd_id: command id
+ * @n_sizes: number of elements in &sizes.
+ * @context: see &iwl_rx_handler_context
+ * @obj_type: the type of the object that this handler is related to.
+ *	See &iwl_mld_object_type. Use IWL_MLD_OBJECT_TYPE_NONE if not related.
+ * @cancel: function to cancel the notification. valid only if obj_type is not
+ *	IWL_MLD_OBJECT_TYPE_NONE.
+ */
+struct iwl_rx_handler {
+	union {
+		bool (*val_fn)(struct iwl_mld *mld, struct iwl_rx_packet *pkt);
+		const struct iwl_notif_struct_size *sizes;
+	};
+	void (*fn)(struct iwl_mld *mld, struct iwl_rx_packet *pkt);
+	u16 cmd_id;
+	u8 n_sizes;
+	u8 context;
+	enum iwl_mld_object_type obj_type;
+	bool (*cancel)(struct iwl_mld *mld, struct iwl_rx_packet *pkt,
+		       u32 obj_id);
+};
+
+/**
+ * struct iwl_notif_struct_size: map a notif ver to the expected size
+ *
+ * @size: the size to expect
+ * @ver: the version of the notification
+ */
+struct iwl_notif_struct_size {
+	u32 size:24, ver:8;
+};
+
+#if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
+extern const struct iwl_hcmd_arr iwl_mld_groups[];
+extern const unsigned int global_iwl_mld_goups_size;
+extern const struct iwl_rx_handler iwl_mld_rx_handlers[];
+extern const unsigned int iwl_mld_rx_handlers_num;
+
+bool
+iwl_mld_is_dup(struct iwl_mld *mld, struct ieee80211_sta *sta,
+	       struct ieee80211_hdr *hdr,
+	       const struct iwl_rx_mpdu_desc *mpdu_desc,
+	       struct ieee80211_rx_status *rx_status, int queue);
+
+void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
+		       const struct iwl_cfg *cfg, const struct iwl_fw *fw,
+		       struct ieee80211_hw *hw, struct dentry *dbgfs_dir);
+#endif
+
+#define IWL_MLD_INVALID_FW_ID 0xff
+
+#define IWL_MLD_ALLOC_FN(_type, _mac80211_type)						\
+static int										\
+iwl_mld_allocate_##_type##_fw_id(struct iwl_mld *mld,					\
+				 u8 *fw_id,				\
+				 struct ieee80211_##_mac80211_type *mac80211_ptr)	\
+{											\
+	u8 rand = IWL_MLD_DIS_RANDOM_FW_ID ? 0 : get_random_u8();			\
+	u8 arr_sz = ARRAY_SIZE(mld->fw_id_to_##_mac80211_type);				\
+	if (__builtin_types_compatible_p(typeof(*mac80211_ptr),				\
+					 struct ieee80211_link_sta))			\
+		arr_sz = mld->fw->ucode_capa.num_stations;				\
+	if (__builtin_types_compatible_p(typeof(*mac80211_ptr),				\
+					 struct ieee80211_bss_conf))			\
+		arr_sz = mld->fw->ucode_capa.num_links;					\
+	for (int i = 0; i < arr_sz; i++) {						\
+		u8 idx = (i + rand) % arr_sz;						\
+		if (rcu_access_pointer(mld->fw_id_to_##_mac80211_type[idx]))		\
+			continue;							\
+		IWL_DEBUG_INFO(mld, "Allocated at index %d / %d\n", idx, arr_sz);	\
+		*fw_id = idx;								\
+		rcu_assign_pointer(mld->fw_id_to_##_mac80211_type[idx], mac80211_ptr);	\
+		return 0;								\
+	}										\
+	return -ENOSPC;									\
+}
+
+static inline struct ieee80211_bss_conf *
+iwl_mld_fw_id_to_link_conf(struct iwl_mld *mld, u8 fw_link_id)
+{
+	if (IWL_FW_CHECK(mld, fw_link_id >= mld->fw->ucode_capa.num_links,
+			 "Invalid fw_link_id: %d\n", fw_link_id))
+		return NULL;
+
+	return wiphy_dereference(mld->wiphy,
+				 mld->fw_id_to_bss_conf[fw_link_id]);
+}
+
+#define MSEC_TO_TU(_msec)	((_msec) * 1000 / 1024)
+
+void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
+			     struct ieee80211_vif *vif);
+void iwl_mld_add_link_debugfs(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link_conf,
+			      struct dentry *dir);
+void iwl_mld_add_link_sta_debugfs(struct ieee80211_hw *hw,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_link_sta *link_sta,
+				  struct dentry *dir);
+
+/* Utilities */
+
+static inline u8 iwl_mld_mac80211_ac_to_fw_tx_fifo(enum ieee80211_ac_numbers ac)
+{
+	static const u8 mac80211_ac_to_fw_tx_fifo[] = {
+		IWL_BZ_EDCA_TX_FIFO_VO,
+		IWL_BZ_EDCA_TX_FIFO_VI,
+		IWL_BZ_EDCA_TX_FIFO_BE,
+		IWL_BZ_EDCA_TX_FIFO_BK,
+		IWL_BZ_TRIG_TX_FIFO_VO,
+		IWL_BZ_TRIG_TX_FIFO_VI,
+		IWL_BZ_TRIG_TX_FIFO_BE,
+		IWL_BZ_TRIG_TX_FIFO_BK,
+	};
+	return mac80211_ac_to_fw_tx_fifo[ac];
+}
+
+static inline u32
+iwl_mld_get_lmac_id(struct iwl_mld *mld, enum nl80211_band band)
+{
+	if (!fw_has_capa(&mld->fw->ucode_capa,
+			 IWL_UCODE_TLV_CAPA_CDB_SUPPORT) ||
+	    band == NL80211_BAND_2GHZ)
+		return IWL_LMAC_24G_INDEX;
+	return IWL_LMAC_5G_INDEX;
+}
+
+/* Check if we had an error, but reconfig flow didn't start yet */
+static inline bool iwl_mld_error_before_recovery(struct iwl_mld *mld)
+{
+	return mld->fw_status.in_hw_restart &&
+		!iwl_trans_fw_running(mld->trans);
+}
+
+int iwl_mld_tdls_sta_count(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
new file mode 100644
index 0000000000000..99c8501129b8f
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -0,0 +1,994 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include "mlo.h"
+
+/* Block reasons helper */
+#define HANDLE_EMLSR_BLOCKED_REASONS(HOW)	\
+	HOW(PREVENTION)			\
+	HOW(WOWLAN)			\
+	HOW(FW)				\
+	HOW(ROC)			\
+	HOW(NON_BSS)			\
+	HOW(TMP_NON_BSS)		\
+	HOW(TPT)
+
+static const char *
+iwl_mld_get_emlsr_blocked_string(enum iwl_mld_emlsr_blocked blocked)
+{
+	/* Using switch without "default" will warn about missing entries  */
+	switch (blocked) {
+#define REASON_CASE(x) case IWL_MLD_EMLSR_BLOCKED_##x: return #x;
+	HANDLE_EMLSR_BLOCKED_REASONS(REASON_CASE)
+#undef REASON_CASE
+	}
+
+	return "ERROR";
+}
+
+static void iwl_mld_print_emlsr_blocked(struct iwl_mld *mld, u32 mask)
+{
+#define NAME_FMT(x) "%s"
+#define NAME_PR(x) (mask & IWL_MLD_EMLSR_BLOCKED_##x) ? "[" #x "]" : "",
+	IWL_DEBUG_INFO(mld,
+		       "EMLSR blocked = " HANDLE_EMLSR_BLOCKED_REASONS(NAME_FMT)
+		       " (0x%x)\n",
+		       HANDLE_EMLSR_BLOCKED_REASONS(NAME_PR)
+		       mask);
+#undef NAME_FMT
+#undef NAME_PR
+}
+
+/* Exit reasons helper */
+#define HANDLE_EMLSR_EXIT_REASONS(HOW)	\
+	HOW(BLOCK)			\
+	HOW(MISSED_BEACON)		\
+	HOW(FAIL_ENTRY)			\
+	HOW(CSA)			\
+	HOW(EQUAL_BAND)			\
+	HOW(BANDWIDTH)			\
+	HOW(LOW_RSSI)			\
+	HOW(LINK_USAGE)			\
+	HOW(BT_COEX)			\
+	HOW(CHAN_LOAD)			\
+	HOW(RFI)
+
+static const char *
+iwl_mld_get_emlsr_exit_string(enum iwl_mld_emlsr_exit exit)
+{
+	/* Using switch without "default" will warn about missing entries  */
+	switch (exit) {
+#define REASON_CASE(x) case IWL_MLD_EMLSR_EXIT_##x: return #x;
+	HANDLE_EMLSR_EXIT_REASONS(REASON_CASE)
+#undef REASON_CASE
+	}
+
+	return "ERROR";
+}
+
+static void iwl_mld_print_emlsr_exit(struct iwl_mld *mld, u32 mask)
+{
+#define NAME_FMT(x) "%s"
+#define NAME_PR(x) (mask & IWL_MLD_EMLSR_EXIT_##x) ? "[" #x "]" : "",
+	IWL_DEBUG_INFO(mld,
+		       "EMLSR exit = " HANDLE_EMLSR_EXIT_REASONS(NAME_FMT)
+		       " (0x%x)\n",
+		       HANDLE_EMLSR_EXIT_REASONS(NAME_PR)
+		       mask);
+#undef NAME_FMT
+#undef NAME_PR
+}
+
+void iwl_mld_emlsr_prevent_done_wk(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld_vif *mld_vif = container_of(wk, struct iwl_mld_vif,
+						   emlsr.prevent_done_wk.work);
+	struct ieee80211_vif *vif =
+		container_of((void *)mld_vif, struct ieee80211_vif, drv_priv);
+
+	if (WARN_ON(!(mld_vif->emlsr.blocked_reasons &
+		      IWL_MLD_EMLSR_BLOCKED_PREVENTION)))
+		return;
+
+	iwl_mld_unblock_emlsr(mld_vif->mld, vif,
+			      IWL_MLD_EMLSR_BLOCKED_PREVENTION);
+}
+
+void iwl_mld_emlsr_tmp_non_bss_done_wk(struct wiphy *wiphy,
+				       struct wiphy_work *wk)
+{
+	struct iwl_mld_vif *mld_vif = container_of(wk, struct iwl_mld_vif,
+						   emlsr.prevent_done_wk.work);
+	struct ieee80211_vif *vif =
+		container_of((void *)mld_vif, struct ieee80211_vif, drv_priv);
+
+	if (WARN_ON(!(mld_vif->emlsr.blocked_reasons &
+		      IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS)))
+		return;
+
+	iwl_mld_unblock_emlsr(mld_vif->mld, vif,
+			      IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS);
+}
+
+#define IWL_MLD_TRIGGER_LINK_SEL_TIME	(HZ * IWL_MLD_TRIGGER_LINK_SEL_TIME_SEC)
+#define IWL_MLD_SCAN_EXPIRE_TIME	(HZ * IWL_MLD_SCAN_EXPIRE_TIME_SEC)
+
+/* Exit reasons that can cause longer EMLSR prevention */
+#define IWL_MLD_PREVENT_EMLSR_REASONS	(IWL_MLD_EMLSR_EXIT_MISSED_BEACON | \
+					 IWL_MLD_EMLSR_EXIT_LINK_USAGE)
+#define IWL_MLD_PREVENT_EMLSR_TIMEOUT	(HZ * 400)
+
+#define IWL_MLD_EMLSR_PREVENT_SHORT	(HZ * 300)
+#define IWL_MLD_EMLSR_PREVENT_LONG	(HZ * 600)
+
+static void iwl_mld_check_emlsr_prevention(struct iwl_mld *mld,
+					   struct iwl_mld_vif *mld_vif,
+					   enum iwl_mld_emlsr_exit reason)
+{
+	unsigned long delay;
+
+	/*
+	 * Reset the counter if more than 400 seconds have passed between one
+	 * exit and the other, or if we exited due to a different reason.
+	 * Will also reset the counter after the long prevention is done.
+	 */
+	if (time_after(jiffies, mld_vif->emlsr.last_exit_ts +
+				IWL_MLD_PREVENT_EMLSR_TIMEOUT) ||
+	    mld_vif->emlsr.last_exit_reason != reason)
+		mld_vif->emlsr.exit_repeat_count = 0;
+
+	mld_vif->emlsr.last_exit_reason = reason;
+	mld_vif->emlsr.last_exit_ts = jiffies;
+	mld_vif->emlsr.exit_repeat_count++;
+
+	/*
+	 * Do not add a prevention when the reason was a block. For a block,
+	 * EMLSR will be enabled again on unblock.
+	 */
+	if (reason == IWL_MLD_EMLSR_EXIT_BLOCK)
+		return;
+
+	/* Set prevention for a minimum of 30 seconds */
+	mld_vif->emlsr.blocked_reasons |= IWL_MLD_EMLSR_BLOCKED_PREVENTION;
+	delay = IWL_MLD_TRIGGER_LINK_SEL_TIME;
+
+	/* Handle repeats for reasons that can cause long prevention */
+	if (mld_vif->emlsr.exit_repeat_count > 1 &&
+	    reason & IWL_MLD_PREVENT_EMLSR_REASONS) {
+		if (mld_vif->emlsr.exit_repeat_count == 2)
+			delay = IWL_MLD_EMLSR_PREVENT_SHORT;
+		else
+			delay = IWL_MLD_EMLSR_PREVENT_LONG;
+
+		/*
+		 * The timeouts are chosen so that this will not happen, i.e.
+		 * IWL_MLD_EMLSR_PREVENT_LONG > IWL_MLD_PREVENT_EMLSR_TIMEOUT
+		 */
+		WARN_ON(mld_vif->emlsr.exit_repeat_count > 3);
+	}
+
+	IWL_DEBUG_INFO(mld,
+		       "Preventing EMLSR for %ld seconds due to %u exits with the reason = %s (0x%x)\n",
+		       delay / HZ, mld_vif->emlsr.exit_repeat_count,
+		       iwl_mld_get_emlsr_exit_string(reason), reason);
+
+	wiphy_delayed_work_queue(mld->wiphy,
+				 &mld_vif->emlsr.prevent_done_wk, delay);
+}
+
+static int _iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			       enum iwl_mld_emlsr_exit exit, u8 link_to_keep,
+			       bool sync)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	u16 new_active_links;
+	int ret = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* On entry failure need to exit anyway, even if entered from debugfs */
+	if (exit != IWL_MLD_EMLSR_EXIT_FAIL_ENTRY && !IWL_MLD_AUTO_EML_ENABLE)
+		return 0;
+
+	/* Ignore exit request if EMLSR is not active */
+	if (!iwl_mld_emlsr_active(vif))
+		return 0;
+
+	if (WARN_ON(!ieee80211_vif_is_mld(vif) || !mld_vif->authorized))
+		return 0;
+
+	if (WARN_ON(!(vif->active_links & BIT(link_to_keep))))
+		link_to_keep = __ffs(vif->active_links);
+
+	new_active_links = BIT(link_to_keep);
+	IWL_DEBUG_INFO(mld,
+		       "Exiting EMLSR. reason = %s (0x%x). Current active links=0x%x, new active links = 0x%x\n",
+		       iwl_mld_get_emlsr_exit_string(exit), exit,
+		       vif->active_links, new_active_links);
+
+	if (sync)
+		ret = ieee80211_set_active_links(vif, new_active_links);
+	else
+		ieee80211_set_active_links_async(vif, new_active_links);
+
+	/* Update latest exit reason and check EMLSR prevention */
+	iwl_mld_check_emlsr_prevention(mld, mld_vif, exit);
+
+	return ret;
+}
+
+void iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			enum iwl_mld_emlsr_exit exit, u8 link_to_keep)
+{
+	_iwl_mld_exit_emlsr(mld, vif, exit, link_to_keep, false);
+}
+
+static int _iwl_mld_emlsr_block(struct iwl_mld *mld, struct ieee80211_vif *vif,
+				enum iwl_mld_emlsr_blocked reason,
+				u8 link_to_keep, bool sync)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!IWL_MLD_AUTO_EML_ENABLE || !iwl_mld_vif_has_emlsr_cap(vif))
+		return 0;
+
+	if (mld_vif->emlsr.blocked_reasons & reason)
+		return 0;
+
+	mld_vif->emlsr.blocked_reasons |= reason;
+
+	IWL_DEBUG_INFO(mld,
+		       "Blocking EMLSR mode. reason = %s (0x%x)\n",
+		       iwl_mld_get_emlsr_blocked_string(reason), reason);
+	iwl_mld_print_emlsr_blocked(mld, mld_vif->emlsr.blocked_reasons);
+
+	if (reason == IWL_MLD_EMLSR_BLOCKED_TPT)
+		wiphy_delayed_work_cancel(mld_vif->mld->wiphy,
+					  &mld_vif->emlsr.check_tpt_wk);
+
+	return _iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_BLOCK,
+				   link_to_keep, sync);
+}
+
+void iwl_mld_block_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			 enum iwl_mld_emlsr_blocked reason, u8 link_to_keep)
+{
+	_iwl_mld_emlsr_block(mld, vif, reason, link_to_keep, false);
+}
+
+int iwl_mld_block_emlsr_sync(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			     enum iwl_mld_emlsr_blocked reason, u8 link_to_keep)
+{
+	return _iwl_mld_emlsr_block(mld, vif, reason, link_to_keep, true);
+}
+
+static void _iwl_mld_select_links(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif);
+
+void iwl_mld_trigger_link_selection(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif)
+{
+	bool last_scan_was_recent =
+		time_before(jiffies, mld->scan.last_mlo_scan_jiffies +
+				     IWL_MLD_SCAN_EXPIRE_TIME);
+
+	if (last_scan_was_recent) {
+		IWL_DEBUG_EHT(mld, "MLO scan was recent, skip.\n");
+		_iwl_mld_select_links(mld, vif);
+	} else {
+		IWL_DEBUG_EHT(mld, "Doing link selection after MLO scan\n");
+		iwl_mld_int_mlo_scan(mld, vif);
+	}
+}
+
+void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			   enum iwl_mld_emlsr_blocked reason)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!IWL_MLD_AUTO_EML_ENABLE || !iwl_mld_vif_has_emlsr_cap(vif))
+		return;
+
+	if (!(mld_vif->emlsr.blocked_reasons & reason))
+		return;
+
+	mld_vif->emlsr.blocked_reasons &= ~reason;
+
+	IWL_DEBUG_INFO(mld,
+		       "Unblocking EMLSR mode. reason = %s (0x%x)\n",
+		       iwl_mld_get_emlsr_blocked_string(reason), reason);
+	iwl_mld_print_emlsr_blocked(mld, mld_vif->emlsr.blocked_reasons);
+
+	if (reason == IWL_MLD_EMLSR_BLOCKED_TPT)
+		wiphy_delayed_work_queue(mld_vif->mld->wiphy,
+					 &mld_vif->emlsr.check_tpt_wk,
+					 round_jiffies_relative(IWL_MLD_TPT_COUNT_WINDOW));
+
+	if (mld_vif->emlsr.blocked_reasons)
+		return;
+
+	IWL_DEBUG_INFO(mld, "EMLSR is unblocked\n");
+	iwl_mld_trigger_link_selection(mld, vif);
+}
+
+static void
+iwl_mld_vif_iter_emlsr_mode_notif(void *data, u8 *mac,
+				  struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_esr_mode_notif *notif = (void *)data;
+
+	if (!iwl_mld_vif_has_emlsr_cap(vif))
+		return;
+
+	switch (le32_to_cpu(notif->action)) {
+	case ESR_RECOMMEND_ENTER:
+		iwl_mld_unblock_emlsr(mld_vif->mld, vif,
+				      IWL_MLD_EMLSR_BLOCKED_FW);
+		break;
+	case ESR_RECOMMEND_LEAVE:
+		iwl_mld_block_emlsr(mld_vif->mld, vif,
+				    IWL_MLD_EMLSR_BLOCKED_FW,
+				    iwl_mld_get_primary_link(vif));
+		break;
+	case ESR_FORCE_LEAVE:
+	default:
+		/* ESR_FORCE_LEAVE should not happen at this point */
+		IWL_WARN(mld_vif->mld, "Unexpected EMLSR notification: %d\n",
+			 le32_to_cpu(notif->action));
+	}
+}
+
+void iwl_mld_handle_emlsr_mode_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt)
+{
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_mode_notif,
+						pkt->data);
+}
+
+static void
+iwl_mld_vif_iter_disconnect_emlsr(void *data, u8 *mac,
+				  struct ieee80211_vif *vif)
+{
+	if (!iwl_mld_vif_has_emlsr_cap(vif))
+		return;
+
+	ieee80211_connection_loss(vif);
+}
+
+void iwl_mld_handle_emlsr_trans_fail_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt)
+{
+	const struct iwl_esr_trans_fail_notif *notif = (const void *)pkt->data;
+	u32 fw_link_id = le32_to_cpu(notif->link_id);
+	struct ieee80211_bss_conf *bss_conf =
+		iwl_mld_fw_id_to_link_conf(mld, fw_link_id);
+
+	IWL_DEBUG_INFO(mld, "Failed to %s EMLSR on link %d (FW: %d), reason %d\n",
+		       le32_to_cpu(notif->activation) ? "enter" : "exit",
+		       bss_conf ? bss_conf->link_id : -1,
+		       le32_to_cpu(notif->link_id),
+		       le32_to_cpu(notif->err_code));
+
+	if (IWL_FW_CHECK(mld, !bss_conf,
+			 "FW reported failure to %sactivate EMLSR on a non-existing link: %d\n",
+			 le32_to_cpu(notif->activation) ? "" : "de",
+			 fw_link_id)) {
+		ieee80211_iterate_active_interfaces_mtx(
+			mld->hw, IEEE80211_IFACE_ITER_NORMAL,
+			iwl_mld_vif_iter_disconnect_emlsr, NULL);
+		return;
+	}
+
+	/* Disconnect if we failed to deactivate a link */
+	if (!le32_to_cpu(notif->activation)) {
+		ieee80211_connection_loss(bss_conf->vif);
+		return;
+	}
+
+	/*
+	 * We failed to activate the second link, go back to the link specified
+	 * by the firmware as that is the one that is still valid now.
+	 */
+	iwl_mld_exit_emlsr(mld, bss_conf->vif, IWL_MLD_EMLSR_EXIT_FAIL_ENTRY,
+			   bss_conf->link_id);
+}
+
+/* Active non-station link tracking */
+static void iwl_mld_count_non_bss_links(void *_data, u8 *mac,
+					struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int *count = _data;
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_STATION)
+		return;
+
+	*count += iwl_mld_count_active_links(mld_vif->mld, vif);
+}
+
+struct iwl_mld_update_emlsr_block_data {
+	bool block;
+	int result;
+};
+
+static void
+iwl_mld_vif_iter_update_emlsr_non_bss_block(void *_data, u8 *mac,
+					    struct ieee80211_vif *vif)
+{
+	struct iwl_mld_update_emlsr_block_data *data = _data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	if (data->block) {
+		ret = iwl_mld_block_emlsr_sync(mld_vif->mld, vif,
+					       IWL_MLD_EMLSR_BLOCKED_NON_BSS,
+					       iwl_mld_get_primary_link(vif));
+		if (ret)
+			data->result = ret;
+	} else {
+		iwl_mld_unblock_emlsr(mld_vif->mld, vif,
+				      IWL_MLD_EMLSR_BLOCKED_NON_BSS);
+	}
+}
+
+int iwl_mld_emlsr_check_non_bss_block(struct iwl_mld *mld,
+				      int pending_link_changes)
+{
+	/* An active link of a non-station vif blocks EMLSR. Upon activation
+	 * block EMLSR on the bss vif. Upon deactivation, check if this link
+	 * was the last non-station link active, and if so unblock the bss vif
+	 */
+	struct iwl_mld_update_emlsr_block_data block_data = {};
+	int count = pending_link_changes;
+
+	/* No need to count if we are activating a non-BSS link */
+	if (count <= 0)
+		ieee80211_iterate_active_interfaces_mtx(mld->hw,
+							IEEE80211_IFACE_ITER_NORMAL,
+							iwl_mld_count_non_bss_links,
+							&count);
+
+	/*
+	 * We could skip updating it if the block change did not change (and
+	 * pending_link_changes is non-zero).
+	 */
+	block_data.block = !!count;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_update_emlsr_non_bss_block,
+						&block_data);
+
+	return block_data.result;
+}
+
+#define EMLSR_SEC_LINK_MIN_PERC 10
+#define EMLSR_MIN_TX 3000
+#define EMLSR_MIN_RX 400
+
+void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld_vif *mld_vif = container_of(wk, struct iwl_mld_vif,
+						   emlsr.check_tpt_wk.work);
+	struct ieee80211_vif *vif =
+		container_of((void *)mld_vif, struct ieee80211_vif, drv_priv);
+	struct iwl_mld *mld = mld_vif->mld;
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_link *sec_link;
+	unsigned long total_tx = 0, total_rx = 0;
+	unsigned long sec_link_tx = 0, sec_link_rx = 0;
+	u8 sec_link_tx_perc, sec_link_rx_perc;
+	s8 sec_link_id;
+
+	if (!iwl_mld_vif_has_emlsr_cap(vif) || !mld_vif->ap_sta)
+		return;
+
+	mld_sta = iwl_mld_sta_from_mac80211(mld_vif->ap_sta);
+
+	/* We only count for the AP sta in a MLO connection */
+	if (!mld_sta->mpdu_counters)
+		return;
+
+	/* This wk should only run when the TPT blocker isn't set.
+	 * When the blocker is set, the decision to remove it, as well as
+	 * clearing the counters is done in DP (to avoid having a wk every
+	 * 5 seconds when idle. When the blocker is unset, we are not idle anyway)
+	 */
+	if (WARN_ON(mld_vif->emlsr.blocked_reasons & IWL_MLD_EMLSR_BLOCKED_TPT))
+		return;
+	/*
+	 * TPT is unblocked, need to check if the TPT criteria is still met.
+	 *
+	 * If EMLSR is active, then we also need to check the secondar link
+	 * requirements.
+	 */
+	if (iwl_mld_emlsr_active(vif)) {
+		sec_link_id = iwl_mld_get_other_link(vif, iwl_mld_get_primary_link(vif));
+		sec_link = iwl_mld_link_dereference_check(mld_vif, sec_link_id);
+		if (WARN_ON_ONCE(!sec_link))
+			return;
+		/* We need the FW ID here */
+		sec_link_id = sec_link->fw_id;
+	} else {
+		sec_link_id = -1;
+	}
+
+	/* Sum up RX and TX MPDUs from the different queues/links */
+	for (int q = 0; q < mld->trans->num_rx_queues; q++) {
+		struct iwl_mld_per_q_mpdu_counter *queue_counter =
+			&mld_sta->mpdu_counters[q];
+
+		spin_lock_bh(&queue_counter->lock);
+
+		/* The link IDs that doesn't exist will contain 0 */
+		for (int link = 0;
+		     link < ARRAY_SIZE(queue_counter->per_link);
+		     link++) {
+			total_tx += queue_counter->per_link[link].tx;
+			total_rx += queue_counter->per_link[link].rx;
+		}
+
+		if (sec_link_id != -1) {
+			sec_link_tx += queue_counter->per_link[sec_link_id].tx;
+			sec_link_rx += queue_counter->per_link[sec_link_id].rx;
+		}
+
+		memset(queue_counter->per_link, 0,
+		       sizeof(queue_counter->per_link));
+
+		spin_unlock_bh(&queue_counter->lock);
+	}
+
+	IWL_DEBUG_INFO(mld, "total Tx MPDUs: %ld. total Rx MPDUs: %ld\n",
+		       total_tx, total_rx);
+
+	/* If we don't have enough MPDUs - exit EMLSR */
+	if (total_tx < IWL_MLD_ENTER_EMLSR_TPT_THRESH &&
+	    total_rx < IWL_MLD_ENTER_EMLSR_TPT_THRESH) {
+		iwl_mld_block_emlsr(mld, vif, IWL_MLD_EMLSR_BLOCKED_TPT,
+				    iwl_mld_get_primary_link(vif));
+		return;
+	}
+
+	/* EMLSR is not active */
+	if (sec_link_id == -1)
+		return;
+
+	IWL_DEBUG_INFO(mld, "Secondary Link %d: Tx MPDUs: %ld. Rx MPDUs: %ld\n",
+		       sec_link_id, sec_link_tx, sec_link_rx);
+
+	/* Calculate the percentage of the secondary link TX/RX */
+	sec_link_tx_perc = total_tx ? sec_link_tx * 100 / total_tx : 0;
+	sec_link_rx_perc = total_rx ? sec_link_rx * 100 / total_rx : 0;
+
+	/*
+	 * The TX/RX percentage is checked only if it exceeds the required
+	 * minimum. In addition, RX is checked only if the TX check failed.
+	 */
+	if ((total_tx > EMLSR_MIN_TX &&
+	     sec_link_tx_perc < EMLSR_SEC_LINK_MIN_PERC) ||
+	    (total_rx > EMLSR_MIN_RX &&
+	     sec_link_rx_perc < EMLSR_SEC_LINK_MIN_PERC)) {
+		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_LINK_USAGE,
+				   iwl_mld_get_primary_link(vif));
+		return;
+	}
+
+	/* Check again when the next window ends  */
+	wiphy_delayed_work_queue(mld_vif->mld->wiphy,
+				 &mld_vif->emlsr.check_tpt_wk,
+				 round_jiffies_relative(IWL_MLD_TPT_COUNT_WINDOW));
+}
+
+void iwl_mld_emlsr_unblock_tpt_wk(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld_vif *mld_vif = container_of(wk, struct iwl_mld_vif,
+						   emlsr.unblock_tpt_wk);
+	struct ieee80211_vif *vif =
+		container_of((void *)mld_vif, struct ieee80211_vif, drv_priv);
+
+	iwl_mld_unblock_emlsr(mld_vif->mld, vif, IWL_MLD_EMLSR_BLOCKED_TPT);
+}
+
+/*
+ * Link selection
+ */
+struct iwl_mld_link_sel_data {
+	u8 link_id;
+	const struct cfg80211_chan_def *chandef;
+	s32 signal;
+	u16 grade;
+};
+
+s8 iwl_mld_get_emlsr_rssi_thresh(struct iwl_mld *mld,
+				 const struct cfg80211_chan_def *chandef,
+				 bool low)
+{
+	if (WARN_ON(chandef->chan->band != NL80211_BAND_2GHZ &&
+		    chandef->chan->band != NL80211_BAND_5GHZ &&
+		    chandef->chan->band != NL80211_BAND_6GHZ))
+		return S8_MAX;
+
+#define RSSI_THRESHOLD(_low, _bw)			\
+	(_low) ? IWL_MLD_LOW_RSSI_THRESH_##_bw##MHZ	\
+	       : IWL_MLD_HIGH_RSSI_THRESH_##_bw##MHZ
+
+	switch (chandef->width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+	/* 320 MHz has the same thresholds as 20 MHz */
+	case NL80211_CHAN_WIDTH_320:
+		return RSSI_THRESHOLD(low, 20);
+	case NL80211_CHAN_WIDTH_40:
+		return RSSI_THRESHOLD(low, 40);
+	case NL80211_CHAN_WIDTH_80:
+		return RSSI_THRESHOLD(low, 80);
+	case NL80211_CHAN_WIDTH_160:
+		return RSSI_THRESHOLD(low, 160);
+	default:
+		WARN_ON(1);
+		return S8_MAX;
+	}
+#undef RSSI_THRESHOLD
+}
+
+static u32
+iwl_mld_emlsr_disallowed_with_link(struct iwl_mld *mld,
+				   struct ieee80211_vif *vif,
+				   struct iwl_mld_link_sel_data *link,
+				   bool primary)
+{
+	struct wiphy *wiphy = mld->wiphy;
+	struct ieee80211_bss_conf *conf;
+	enum iwl_mld_emlsr_exit ret = 0;
+
+	conf = wiphy_dereference(wiphy, vif->link_conf[link->link_id]);
+	if (WARN_ON_ONCE(!conf))
+		return false;
+
+	if (link->chandef->chan->band == NL80211_BAND_2GHZ && mld->bt_is_active)
+		ret |= IWL_MLD_EMLSR_EXIT_BT_COEX;
+
+	if (link->signal <
+	    iwl_mld_get_emlsr_rssi_thresh(mld, link->chandef, false))
+		ret |= IWL_MLD_EMLSR_EXIT_LOW_RSSI;
+
+	if (conf->csa_active)
+		ret |= IWL_MLD_EMLSR_EXIT_CSA;
+
+	if (ret) {
+		IWL_DEBUG_INFO(mld,
+			       "Link %d is not allowed for EMLSR as %s\n",
+			       link->link_id,
+			       primary ? "primary" : "secondary");
+		iwl_mld_print_emlsr_exit(mld, ret);
+	}
+
+	return ret;
+}
+
+static u8
+iwl_mld_set_link_sel_data(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct iwl_mld_link_sel_data *data,
+			  unsigned long usable_links,
+			  u8 *best_link_idx)
+{
+	u8 n_data = 0;
+	u16 max_grade = 0;
+	unsigned long link_id;
+
+	/*
+	 * TODO: don't select links that weren't discovered in the last scan
+	 * This requires mac80211 (or cfg80211) changes to forward/track when
+	 * a BSS was last updated. cfg80211 already tracks this information but
+	 * it is not exposed within the kernel.
+	 */
+	for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *link_conf =
+			link_conf_dereference_protected(vif, link_id);
+
+		if (WARN_ON_ONCE(!link_conf))
+			continue;
+
+		/* Ignore any BSS that was not seen in the last 5 seconds */
+		if (ktime_before(link_conf->bss->ts_boottime,
+				 ktime_sub_ns(ktime_get_boottime_ns(),
+					      (u64)5 * NSEC_PER_SEC)))
+			continue;
+
+		data[n_data].link_id = link_id;
+		data[n_data].chandef = &link_conf->chanreq.oper;
+		data[n_data].signal = MBM_TO_DBM(link_conf->bss->signal);
+		data[n_data].grade = iwl_mld_get_link_grade(mld, link_conf);
+
+		if (n_data == 0 || data[n_data].grade > max_grade) {
+			max_grade = data[n_data].grade;
+			*best_link_idx = n_data;
+		}
+		n_data++;
+	}
+
+	return n_data;
+}
+
+static bool
+iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
+			 struct iwl_mld_link_sel_data *a,
+			 struct iwl_mld_link_sel_data *b)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = mld_vif->mld;
+	enum iwl_mld_emlsr_exit ret = 0;
+
+	/* Per-link considerations */
+	if (iwl_mld_emlsr_disallowed_with_link(mld, vif, a, true) ||
+	    iwl_mld_emlsr_disallowed_with_link(mld, vif, b, false))
+		return false;
+
+	if (a->chandef->chan->band == b->chandef->chan->band) {
+		ret |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
+	} else if (a->chandef->width != b->chandef->width) {
+		/* TODO: task=EMLSR task=statistics
+		 * replace BANDWIDTH exit reason with channel load criteria
+		 */
+		ret |= IWL_MLD_EMLSR_EXIT_BANDWIDTH;
+	}
+
+	if (ret) {
+		IWL_DEBUG_INFO(mld,
+			       "Links %d and %d are not a valid pair for EMLSR\n",
+			       a->link_id, b->link_id);
+		IWL_DEBUG_INFO(mld,
+			       "Links bandwidth are: %d and %d\n",
+			       nl80211_chan_width_to_mhz(a->chandef->width),
+			       nl80211_chan_width_to_mhz(b->chandef->width));
+		iwl_mld_print_emlsr_exit(mld, ret);
+		return false;
+	}
+
+	return true;
+}
+
+/* Calculation is done with fixed-point with a scaling factor of 1/256 */
+#define SCALE_FACTOR 256
+
+/*
+ * Returns the combined grade of two given links.
+ * Returns 0 if EMLSR is not allowed with these 2 links.
+ */
+static
+unsigned int iwl_mld_get_emlsr_grade(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif,
+				     struct iwl_mld_link_sel_data *a,
+				     struct iwl_mld_link_sel_data *b,
+				     u8 *primary_id)
+{
+	struct ieee80211_bss_conf *primary_conf;
+	struct wiphy *wiphy = ieee80211_vif_to_wdev(vif)->wiphy;
+	unsigned int primary_load;
+
+	lockdep_assert_wiphy(wiphy);
+
+	/* a is always primary, b is always secondary */
+	if (b->grade > a->grade)
+		swap(a, b);
+
+	*primary_id = a->link_id;
+
+	if (!iwl_mld_valid_emlsr_pair(vif, a, b))
+		return 0;
+
+	primary_conf = wiphy_dereference(wiphy, vif->link_conf[*primary_id]);
+
+	if (WARN_ON_ONCE(!primary_conf))
+		return 0;
+
+	primary_load = iwl_mld_get_chan_load(mld, primary_conf);
+
+	/* The more the primary link is loaded, the more worthwhile EMLSR becomes */
+	return a->grade + ((b->grade * primary_load) / SCALE_FACTOR);
+}
+
+static void _iwl_mld_select_links(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif)
+{
+	struct iwl_mld_link_sel_data data[IEEE80211_MLD_MAX_NUM_LINKS];
+	struct iwl_mld_link_sel_data *best_link;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int max_active_links = iwl_mld_max_active_links(mld, vif);
+	u16 new_active, usable_links = ieee80211_vif_usable_links(vif);
+	u8 best_idx, new_primary, n_data;
+	u16 max_grade;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!mld_vif->authorized || hweight16(usable_links) <= 1)
+		return;
+
+	if (WARN(time_before(mld->scan.last_mlo_scan_jiffies,
+			     jiffies - IWL_MLD_SCAN_EXPIRE_TIME),
+		"Last MLO scan was too long ago, can't select links\n"))
+		return;
+
+	/* The logic below is simple and not suited for more than 2 links */
+	WARN_ON_ONCE(max_active_links > 2);
+
+	n_data = iwl_mld_set_link_sel_data(mld, vif, data, usable_links,
+					   &best_idx);
+
+	if (WARN(!n_data, "Couldn't find a valid grade for any link!\n"))
+		return;
+
+	/* Default to selecting the single best link */
+	best_link = &data[best_idx];
+	new_primary = best_link->link_id;
+	new_active = BIT(best_link->link_id);
+	max_grade = best_link->grade;
+
+	/* If EMLSR is not possible, activate the best link */
+	if (max_active_links == 1 || n_data == 1 ||
+	    !iwl_mld_vif_has_emlsr_cap(vif) || !IWL_MLD_AUTO_EML_ENABLE ||
+	    mld_vif->emlsr.blocked_reasons)
+		goto set_active;
+
+	/* Try to find the best link combination */
+	for (u8 a = 0; a < n_data; a++) {
+		for (u8 b = a + 1; b < n_data; b++) {
+			u8 best_in_pair;
+			u16 emlsr_grade =
+				iwl_mld_get_emlsr_grade(mld, vif,
+							&data[a], &data[b],
+							&best_in_pair);
+
+			/*
+			 * Prefer (new) EMLSR combination to prefer EMLSR over
+			 * a single link.
+			 */
+			if (emlsr_grade < max_grade)
+				continue;
+
+			max_grade = emlsr_grade;
+			new_primary = best_in_pair;
+			new_active = BIT(data[a].link_id) |
+				     BIT(data[b].link_id);
+		}
+	}
+
+set_active:
+	IWL_DEBUG_INFO(mld, "Link selection result: 0x%x. Primary = %d\n",
+		       new_active, new_primary);
+
+	mld_vif->emlsr.selected_primary = new_primary;
+	mld_vif->emlsr.selected_links = new_active;
+
+	ieee80211_set_active_links_async(vif, new_active);
+}
+
+static void iwl_mld_vif_iter_select_links(void *_data, u8 *mac,
+					  struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = mld_vif->mld;
+
+	_iwl_mld_select_links(mld, vif);
+}
+
+void iwl_mld_select_links(struct iwl_mld *mld)
+{
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_select_links,
+						NULL);
+}
+
+void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_bss_conf *link)
+{
+	u8 other_link_id = iwl_mld_get_other_link(vif, link->link_id);
+	struct ieee80211_bss_conf *other_link =
+		link_conf_dereference_check(vif, other_link_id);
+
+	if (!ieee80211_vif_link_active(vif, link->link_id) ||
+	    !iwl_mld_emlsr_active(vif) ||
+	    WARN_ON(link->link_id == other_link_id || !other_link))
+		return;
+
+	if (link->chanreq.oper.width != other_link->chanreq.oper.width)
+		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_BANDWIDTH,
+				   iwl_mld_get_primary_link(vif));
+}
+
+static void iwl_mld_emlsr_check_bt_iter(void *_data, u8 *mac,
+					struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld *mld = mld_vif->mld;
+	struct ieee80211_bss_conf *link;
+	unsigned int link_id;
+
+	if (!mld->bt_is_active) {
+		iwl_mld_retry_emlsr(mld, vif);
+		return;
+	}
+
+	/* BT is turned ON but we are not in EMLSR, nothing to do */
+	if (!iwl_mld_emlsr_active(vif))
+		return;
+
+	/* In EMLSR and BT is turned ON */
+
+	for_each_vif_active_link(vif, link, link_id) {
+		if (WARN_ON(!link->chanreq.oper.chan))
+			continue;
+
+		if (link->chanreq.oper.chan->band == NL80211_BAND_2GHZ) {
+			iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_BT_COEX,
+					   iwl_mld_get_primary_link(vif));
+			return;
+		}
+	}
+}
+
+void iwl_mld_emlsr_check_bt(struct iwl_mld *mld)
+{
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_emlsr_check_bt_iter,
+						NULL);
+}
+
+static void iwl_mld_emlsr_check_chan_load_iter(void *_data, u8 *mac,
+					       struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = (struct iwl_mld *)_data;
+	struct ieee80211_bss_conf *prim_link;
+	unsigned int prim_link_id;
+	int chan_load;
+
+	if (!iwl_mld_emlsr_active(vif))
+		return;
+
+	prim_link_id = iwl_mld_get_primary_link(vif);
+	prim_link = link_conf_dereference_protected(vif, prim_link_id);
+	if (WARN_ON(!prim_link))
+		return;
+
+	chan_load = iwl_mld_get_chan_load_by_others(mld, prim_link, true);
+
+	if (chan_load < 0)
+		return;
+
+	/* chan_load is in range [0,255] */
+	if (chan_load < NORMALIZE_PERCENT_TO_255(IWL_MLD_CHAN_LOAD_THRESH))
+		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
+				   prim_link_id);
+}
+
+void iwl_mld_emlsr_check_chan_load(struct iwl_mld *mld)
+{
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_emlsr_check_chan_load_iter,
+						(void *)(uintptr_t)mld);
+}
+
+void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	if (!iwl_mld_vif_has_emlsr_cap(vif) || iwl_mld_emlsr_active(vif) ||
+	    mld_vif->emlsr.blocked_reasons)
+		return;
+
+	iwl_mld_trigger_link_selection(mld, vif);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
new file mode 100644
index 0000000000000..fd1abe8e6084a
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_mlo_h__
+#define __iwl_mld_mlo_h__
+
+#include <linux/ieee80211.h>
+#include <linux/types.h>
+#include <net/mac80211.h>
+#include "iwl-config.h"
+#include "iwl-trans.h"
+#include "iface.h"
+
+struct iwl_mld;
+
+void iwl_mld_emlsr_prevent_done_wk(struct wiphy *wiphy, struct wiphy_work *wk);
+void iwl_mld_emlsr_tmp_non_bss_done_wk(struct wiphy *wiphy,
+				       struct wiphy_work *wk);
+
+static inline bool iwl_mld_emlsr_active(struct ieee80211_vif *vif)
+{
+	/* Set on phy context activation, so should be a good proxy */
+	return !!(vif->driver_flags & IEEE80211_VIF_EML_ACTIVE);
+}
+
+static inline bool iwl_mld_vif_has_emlsr_cap(struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	/* We only track/permit EMLSR state once authorized */
+	if (!mld_vif->authorized)
+		return false;
+
+	/* No EMLSR on dual radio devices */
+	return ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_STATION &&
+	       ieee80211_vif_is_mld(vif) &&
+	       vif->cfg.eml_cap & IEEE80211_EML_CAP_EMLSR_SUPP &&
+	       !CSR_HW_RFID_IS_CDB(mld_vif->mld->trans->hw_rf_id);
+}
+
+static inline int
+iwl_mld_max_active_links(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	if (vif->type == NL80211_IFTYPE_AP)
+		return mld->fw->ucode_capa.num_beacons;
+
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_STATION)
+		return IWL_FW_MAX_ACTIVE_LINKS_NUM;
+
+	/* For now, do not accept more links on other interface types */
+	return 1;
+}
+
+static inline int
+iwl_mld_count_active_links(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *mld_link;
+	int n_active = 0;
+
+	for_each_mld_vif_valid_link(mld_vif, mld_link) {
+		if (rcu_access_pointer(mld_link->chan_ctx))
+			n_active++;
+	}
+
+	return n_active;
+}
+
+static inline u8 iwl_mld_get_primary_link(struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	lockdep_assert_wiphy(mld_vif->mld->wiphy);
+
+	if (!ieee80211_vif_is_mld(vif) || WARN_ON(!vif->active_links))
+		return 0;
+
+	/* In AP mode, there is no primary link */
+	if (vif->type == NL80211_IFTYPE_AP)
+		return __ffs(vif->active_links);
+
+	if (iwl_mld_emlsr_active(vif) &&
+	    !WARN_ON(!(BIT(mld_vif->emlsr.primary) & vif->active_links)))
+		return mld_vif->emlsr.primary;
+
+	return __ffs(vif->active_links);
+}
+
+/*
+ * For non-MLO/single link, this will return the deflink/single active link,
+ * respectively
+ */
+static inline u8 iwl_mld_get_other_link(struct ieee80211_vif *vif, u8 link_id)
+{
+	switch (hweight16(vif->active_links)) {
+	case 0:
+		return 0;
+	default:
+		WARN_ON(1);
+		fallthrough;
+	case 1:
+		return __ffs(vif->active_links);
+	case 2:
+		return __ffs(vif->active_links & ~BIT(link_id));
+	}
+}
+
+s8 iwl_mld_get_emlsr_rssi_thresh(struct iwl_mld *mld,
+				 const struct cfg80211_chan_def *chandef,
+				 bool low);
+
+/* EMLSR block/unblock and exit */
+void iwl_mld_block_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			 enum iwl_mld_emlsr_blocked reason, u8 link_to_keep);
+int iwl_mld_block_emlsr_sync(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			     enum iwl_mld_emlsr_blocked reason, u8 link_to_keep);
+void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			   enum iwl_mld_emlsr_blocked reason);
+void iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			enum iwl_mld_emlsr_exit exit, u8 link_to_keep);
+
+int iwl_mld_emlsr_check_non_bss_block(struct iwl_mld *mld,
+				      int pending_link_changes);
+
+void iwl_mld_handle_emlsr_mode_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt);
+void iwl_mld_handle_emlsr_trans_fail_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt);
+
+void iwl_mld_emlsr_check_tpt(struct wiphy *wiphy, struct wiphy_work *wk);
+void iwl_mld_emlsr_unblock_tpt_wk(struct wiphy *wiphy, struct wiphy_work *wk);
+
+void iwl_mld_select_links(struct iwl_mld *mld);
+
+void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif,
+				  struct ieee80211_bss_conf *link);
+
+void iwl_mld_emlsr_check_bt(struct iwl_mld *mld);
+
+void iwl_mld_emlsr_check_chan_load(struct iwl_mld *mld);
+
+void iwl_mld_trigger_link_selection(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif);
+
+/**
+ * iwl_mld_retry_emlsr - Retry entering EMLSR
+ * @mld: MLD context
+ * @vif: VIF to retry EMLSR on
+ *
+ * Retry entering EMLSR on the given VIF.
+ * Use this if one of the parameters that can prevent EMLSR has changed.
+ */
+void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif);
+
+#endif /* __iwl_mld_mlo_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
new file mode 100644
index 0000000000000..06caedf9b0ba1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
@@ -0,0 +1,758 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "mld.h"
+#include "notif.h"
+#include "scan.h"
+#include "iface.h"
+#include "mlo.h"
+#include "iwl-trans.h"
+#include "fw/file.h"
+#include "fw/dbg.h"
+#include "fw/api/cmdhdr.h"
+#include "fw/api/mac-cfg.h"
+#include "session-protect.h"
+#include "fw/api/time-event.h"
+#include "fw/api/tx.h"
+#include "fw/api/rs.h"
+#include "fw/api/offload.h"
+#include "fw/api/stats.h"
+#include "fw/api/rfi.h"
+#include "fw/api/coex.h"
+
+#include "mcc.h"
+#include "link.h"
+#include "tx.h"
+#include "rx.h"
+#include "tlc.h"
+#include "agg.h"
+#include "mac80211.h"
+#include "thermal.h"
+#include "roc.h"
+#include "stats.h"
+#include "coex.h"
+#include "time_sync.h"
+#include "ftm-initiator.h"
+
+/* Please use this in an increasing order of the versions */
+#define CMD_VER_ENTRY(_ver, _struct)			\
+	{ .size = sizeof(struct _struct), .ver = _ver },
+#define CMD_VERSIONS(name, ...)				\
+	static const struct iwl_notif_struct_size	\
+	iwl_notif_struct_sizes_##name[] = { __VA_ARGS__ };
+
+#define RX_HANDLER_NO_OBJECT(_grp, _cmd, _name, _context)		\
+	{.cmd_id = WIDE_ID(_grp, _cmd),					\
+	 .context = _context,						\
+	 .fn = iwl_mld_handle_##_name,					\
+	 .sizes = iwl_notif_struct_sizes_##_name,			\
+	 .n_sizes = ARRAY_SIZE(iwl_notif_struct_sizes_##_name),		\
+	},
+
+/* Use this for Rx handlers that do not need notification validation */
+#define RX_HANDLER_NO_VAL(_grp, _cmd, _name, _context)			\
+	{.cmd_id = WIDE_ID(_grp, _cmd),					\
+	 .context = _context,						\
+	 .fn = iwl_mld_handle_##_name,					\
+	},
+
+#define RX_HANDLER_VAL_FN(_grp, _cmd, _name, _context)			\
+	{ .cmd_id = WIDE_ID(_grp, _cmd),				\
+	  .context = _context,						\
+	  .fn = iwl_mld_handle_##_name,					\
+	  .val_fn = iwl_mld_validate_##_name,				\
+	},
+
+#define DEFINE_SIMPLE_CANCELLATION(name, notif_struct, id_member)		\
+static bool iwl_mld_cancel_##name##_notif(struct iwl_mld *mld,			\
+					  struct iwl_rx_packet *pkt,		\
+					  u32 obj_id)				\
+{										\
+	const struct notif_struct *notif = (const void *)pkt->data;		\
+										\
+	return obj_id == _Generic((notif)->id_member,				\
+				  __le32: le32_to_cpu((notif)->id_member),	\
+				  __le16: le16_to_cpu((notif)->id_member),	\
+				  u8: (notif)->id_member);			\
+}
+
+static bool iwl_mld_always_cancel(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt,
+				  u32 obj_id)
+{
+	return true;
+}
+
+/* Currently only defined for the RX_HANDLER_SIZES options. Use this for
+ * notifications that belong to a specific object, and that should be
+ * canceled when the object is removed
+ */
+#define RX_HANDLER_OF_OBJ(_grp, _cmd, _name, _obj_type)			\
+	{.cmd_id = WIDE_ID(_grp, _cmd),					\
+	/* Only async handlers can be canceled */			\
+	 .context = RX_HANDLER_ASYNC,					\
+	 .fn = iwl_mld_handle_##_name,					\
+	 .sizes = iwl_notif_struct_sizes_##_name,			\
+	 .n_sizes = ARRAY_SIZE(iwl_notif_struct_sizes_##_name),		\
+	 .obj_type = IWL_MLD_OBJECT_TYPE_##_obj_type,			\
+	 .cancel = iwl_mld_cancel_##_name,				\
+	 },
+
+#define RX_HANDLER_OF_LINK(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, LINK)			\
+
+#define RX_HANDLER_OF_VIF(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, VIF)			\
+
+#define RX_HANDLER_OF_STA(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, STA)			\
+
+#define RX_HANDLER_OF_ROC(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, ROC)
+
+#define RX_HANDLER_OF_SCAN(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, SCAN)
+
+#define RX_HANDLER_OF_FTM_REQ(_grp, _cmd, _name)				\
+	RX_HANDLER_OF_OBJ(_grp, _cmd, _name, FTM_REQ)
+
+static void iwl_mld_handle_mfuart_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt)
+{
+	struct iwl_mfuart_load_notif *mfuart_notif = (void *)pkt->data;
+
+	IWL_DEBUG_INFO(mld,
+		       "MFUART: installed ver: 0x%08x, external ver: 0x%08x\n",
+		       le32_to_cpu(mfuart_notif->installed_ver),
+		       le32_to_cpu(mfuart_notif->external_ver));
+	IWL_DEBUG_INFO(mld,
+		       "MFUART: status: 0x%08x, duration: 0x%08x image size: 0x%08x\n",
+		       le32_to_cpu(mfuart_notif->status),
+		       le32_to_cpu(mfuart_notif->duration),
+		       le32_to_cpu(mfuart_notif->image_size));
+}
+
+static void iwl_mld_mu_mimo_iface_iterator(void *_data, u8 *mac,
+					   struct ieee80211_vif *vif)
+{
+	struct ieee80211_bss_conf *bss_conf = &vif->bss_conf;
+	unsigned int link_id = 0;
+
+	if (WARN(hweight16(vif->active_links) > 1,
+		 "no support for this notif while in EMLSR 0x%x\n",
+		 vif->active_links))
+		return;
+
+	if (ieee80211_vif_is_mld(vif)) {
+		link_id = __ffs(vif->active_links);
+		bss_conf = link_conf_dereference_check(vif, link_id);
+	}
+
+	if (!WARN_ON(!bss_conf) && bss_conf->mu_mimo_owner) {
+		const struct iwl_mu_group_mgmt_notif *notif = _data;
+
+		BUILD_BUG_ON(sizeof(notif->membership_status) !=
+			     WLAN_MEMBERSHIP_LEN);
+		BUILD_BUG_ON(sizeof(notif->user_position) !=
+			     WLAN_USER_POSITION_LEN);
+
+		/* MU-MIMO Group Id action frame is little endian. We treat
+		 * the data received from firmware as if it came from the
+		 * action frame, so no conversion is needed.
+		 */
+		ieee80211_update_mu_groups(vif, link_id,
+					   (u8 *)&notif->membership_status,
+					   (u8 *)&notif->user_position);
+	}
+}
+
+/* This handler is called in SYNC mode because it needs to be serialized with
+ * Rx as specified in ieee80211_update_mu_groups()'s documentation.
+ */
+static void iwl_mld_handle_mu_mimo_grp_notif(struct iwl_mld *mld,
+					     struct iwl_rx_packet *pkt)
+{
+	struct iwl_mu_group_mgmt_notif *notif = (void *)pkt->data;
+
+	ieee80211_iterate_active_interfaces_atomic(mld->hw,
+						   IEEE80211_IFACE_ITER_NORMAL,
+						   iwl_mld_mu_mimo_iface_iterator,
+						   notif);
+}
+
+static void
+iwl_mld_handle_stored_beacon_notif(struct iwl_mld *mld,
+				   struct iwl_rx_packet *pkt)
+{
+	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
+	struct iwl_stored_beacon_notif *sb = (void *)pkt->data;
+	struct ieee80211_rx_status rx_status = {};
+	struct sk_buff *skb;
+	u32 size = le32_to_cpu(sb->common.byte_count);
+
+	if (size == 0)
+		return;
+
+	if (pkt_len < struct_size(sb, data, size))
+		return;
+
+	skb = alloc_skb(size, GFP_ATOMIC);
+	if (!skb) {
+		IWL_ERR(mld, "alloc_skb failed\n");
+		return;
+	}
+
+	/* update rx_status according to the notification's metadata */
+	rx_status.mactime = le64_to_cpu(sb->common.tsf);
+	/* TSF as indicated by the firmware  is at INA time */
+	rx_status.flag |= RX_FLAG_MACTIME_PLCP_START;
+	rx_status.device_timestamp = le32_to_cpu(sb->common.system_time);
+	rx_status.band =
+		iwl_mld_phy_band_to_nl80211(le16_to_cpu(sb->common.band));
+	rx_status.freq =
+		ieee80211_channel_to_frequency(le16_to_cpu(sb->common.channel),
+					       rx_status.band);
+
+	/* copy the data */
+	skb_put_data(skb, sb->data, size);
+	memcpy(IEEE80211_SKB_RXCB(skb), &rx_status, sizeof(rx_status));
+
+	/* pass it as regular rx to mac80211 */
+	ieee80211_rx_napi(mld->hw, NULL, skb, NULL);
+}
+
+static void
+iwl_mld_handle_channel_switch_start_notif(struct iwl_mld *mld,
+					  struct iwl_rx_packet *pkt)
+{
+	struct iwl_channel_switch_start_notif *notif = (void *)pkt->data;
+	u32 link_id = le32_to_cpu(notif->link_id);
+	struct ieee80211_bss_conf *link_conf =
+		iwl_mld_fw_id_to_link_conf(mld, link_id);
+	struct ieee80211_vif *vif;
+
+	if (WARN_ON(!link_conf))
+		return;
+
+	vif = link_conf->vif;
+
+	IWL_DEBUG_INFO(mld,
+		       "CSA Start Notification with vif type: %d, link_id: %d\n",
+		       vif->type,
+		       link_conf->link_id);
+
+	switch (vif->type) {
+	case NL80211_IFTYPE_AP:
+		/* We don't support canceling a CSA as it was advertised
+		 * by the AP itself
+		 */
+		if (!link_conf->csa_active)
+			return;
+
+		ieee80211_csa_finish(vif, link_conf->link_id);
+		break;
+	case NL80211_IFTYPE_STATION:
+		if (!link_conf->csa_active) {
+			/* Either unexpected cs notif or mac80211 chose to
+			 * ignore, for example in channel switch to same channel
+			 */
+			struct iwl_cancel_channel_switch_cmd cmd = {
+				.id = cpu_to_le32(link_id),
+			};
+
+			if (iwl_mld_send_cmd_pdu(mld,
+						 WIDE_ID(MAC_CONF_GROUP,
+							 CANCEL_CHANNEL_SWITCH_CMD),
+						 &cmd))
+				IWL_ERR(mld,
+					"Failed to cancel the channel switch\n");
+			return;
+		}
+
+		ieee80211_chswitch_done(vif, true, link_conf->link_id);
+		break;
+
+	default:
+		WARN(1, "CSA on invalid vif type: %d", vif->type);
+	}
+}
+
+static void
+iwl_mld_handle_channel_switch_error_notif(struct iwl_mld *mld,
+					  struct iwl_rx_packet *pkt)
+{
+	struct iwl_channel_switch_error_notif *notif = (void *)pkt->data;
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_vif *vif;
+	u32 link_id = le32_to_cpu(notif->link_id);
+	u32 csa_err_mask = le32_to_cpu(notif->csa_err_mask);
+
+	link_conf = iwl_mld_fw_id_to_link_conf(mld, link_id);
+	if (WARN_ON(!link_conf))
+		return;
+
+	vif = link_conf->vif;
+
+	IWL_DEBUG_INFO(mld, "FW reports CSA error: id=%u, csa_err_mask=%u\n",
+		       link_id, csa_err_mask);
+
+	if (csa_err_mask & (CS_ERR_COUNT_ERROR |
+			    CS_ERR_LONG_DELAY_AFTER_CS |
+			    CS_ERR_TX_BLOCK_TIMER_EXPIRED))
+		ieee80211_channel_switch_disconnect(vif);
+}
+
+static void iwl_mld_handle_beacon_notification(struct iwl_mld *mld,
+					       struct iwl_rx_packet *pkt)
+{
+	struct iwl_extended_beacon_notif *beacon = (void *)pkt->data;
+
+	mld->ibss_manager = !!beacon->ibss_mgr_status;
+}
+
+/**
+ * DOC: Notification versioning
+ *
+ * The firmware's notifications change from time to time. In order to
+ * differentiate between different versions of the same notification, the
+ * firmware advertises the version of each notification.
+ * Here are listed all the notifications that are supported. Several versions
+ * of the same notification can be allowed at the same time:
+ *
+ * CMD_VERSION(my_multi_version_notif,
+ *	       CMD_VER_ENTRY(1, iwl_my_multi_version_notif_ver1)
+ *	       CMD_VER_ENTRY(2, iwl_my_multi_version_notif_ver2)
+ *
+ * etc...
+ *
+ * The driver will enforce that the notification coming from the firmware
+ * has its version listed here and it'll also enforce that the firmware sent
+ * at least enough bytes to cover the structure listed in the CMD_VER_ENTRY.
+ */
+
+CMD_VERSIONS(scan_complete_notif,
+	     CMD_VER_ENTRY(1, iwl_umac_scan_complete))
+CMD_VERSIONS(scan_iter_complete_notif,
+	     CMD_VER_ENTRY(2, iwl_umac_scan_iter_complete_notif))
+CMD_VERSIONS(mfuart_notif,
+	     CMD_VER_ENTRY(2, iwl_mfuart_load_notif))
+CMD_VERSIONS(update_mcc,
+	     CMD_VER_ENTRY(1, iwl_mcc_chub_notif))
+CMD_VERSIONS(session_prot_notif,
+	     CMD_VER_ENTRY(3, iwl_session_prot_notif))
+CMD_VERSIONS(missed_beacon_notif,
+	     CMD_VER_ENTRY(5, iwl_missed_beacons_notif))
+CMD_VERSIONS(tx_resp_notif,
+	     CMD_VER_ENTRY(8, iwl_tx_resp))
+CMD_VERSIONS(compressed_ba_notif,
+	     CMD_VER_ENTRY(5, iwl_compressed_ba_notif))
+CMD_VERSIONS(tlc_notif,
+	     CMD_VER_ENTRY(3, iwl_tlc_update_notif))
+CMD_VERSIONS(mu_mimo_grp_notif,
+	     CMD_VER_ENTRY(1, iwl_mu_group_mgmt_notif))
+CMD_VERSIONS(channel_switch_start_notif,
+	     CMD_VER_ENTRY(3, iwl_channel_switch_start_notif))
+CMD_VERSIONS(channel_switch_error_notif,
+	     CMD_VER_ENTRY(2, iwl_channel_switch_error_notif))
+CMD_VERSIONS(ct_kill_notif,
+	     CMD_VER_ENTRY(2, ct_kill_notif))
+CMD_VERSIONS(temp_notif,
+	     CMD_VER_ENTRY(2, iwl_dts_measurement_notif))
+CMD_VERSIONS(stored_beacon_notif,
+	     CMD_VER_ENTRY(4, iwl_stored_beacon_notif))
+CMD_VERSIONS(roc_notif,
+	     CMD_VER_ENTRY(1, iwl_roc_notif))
+CMD_VERSIONS(probe_resp_data_notif,
+	     CMD_VER_ENTRY(1, iwl_probe_resp_data_notif))
+CMD_VERSIONS(datapath_monitor_notif,
+	     CMD_VER_ENTRY(1, iwl_datapath_monitor_notif))
+CMD_VERSIONS(stats_oper_notif,
+	     CMD_VER_ENTRY(3, iwl_system_statistics_notif_oper))
+CMD_VERSIONS(stats_oper_part1_notif,
+	     CMD_VER_ENTRY(4, iwl_system_statistics_part1_notif_oper))
+CMD_VERSIONS(bt_coex_notif,
+	     CMD_VER_ENTRY(1, iwl_bt_coex_profile_notif))
+CMD_VERSIONS(beacon_notification,
+	     CMD_VER_ENTRY(6, iwl_extended_beacon_notif))
+CMD_VERSIONS(emlsr_mode_notif,
+	     CMD_VER_ENTRY(1, iwl_esr_mode_notif))
+CMD_VERSIONS(emlsr_trans_fail_notif,
+	     CMD_VER_ENTRY(1, iwl_esr_trans_fail_notif))
+CMD_VERSIONS(uapsd_misbehaving_ap_notif,
+	     CMD_VER_ENTRY(1, iwl_uapsd_misbehaving_ap_notif))
+CMD_VERSIONS(time_msmt_notif,
+	     CMD_VER_ENTRY(1, iwl_time_msmt_notify))
+CMD_VERSIONS(time_sync_confirm_notif,
+	     CMD_VER_ENTRY(1, iwl_time_msmt_cfm_notify))
+CMD_VERSIONS(omi_status_notif,
+	     CMD_VER_ENTRY(1, iwl_omi_send_status_notif))
+CMD_VERSIONS(ftm_resp_notif, CMD_VER_ENTRY(9, iwl_tof_range_rsp_ntfy))
+
+DEFINE_SIMPLE_CANCELLATION(session_prot, iwl_session_prot_notif, mac_link_id)
+DEFINE_SIMPLE_CANCELLATION(tlc, iwl_tlc_update_notif, sta_id)
+DEFINE_SIMPLE_CANCELLATION(channel_switch_start,
+			   iwl_channel_switch_start_notif, link_id)
+DEFINE_SIMPLE_CANCELLATION(channel_switch_error,
+			   iwl_channel_switch_error_notif, link_id)
+DEFINE_SIMPLE_CANCELLATION(datapath_monitor, iwl_datapath_monitor_notif,
+			   link_id)
+DEFINE_SIMPLE_CANCELLATION(roc, iwl_roc_notif, activity)
+DEFINE_SIMPLE_CANCELLATION(scan_complete, iwl_umac_scan_complete, uid)
+DEFINE_SIMPLE_CANCELLATION(probe_resp_data, iwl_probe_resp_data_notif,
+			   mac_id)
+DEFINE_SIMPLE_CANCELLATION(uapsd_misbehaving_ap, iwl_uapsd_misbehaving_ap_notif,
+			   mac_id)
+#define iwl_mld_cancel_omi_status_notif iwl_mld_always_cancel
+DEFINE_SIMPLE_CANCELLATION(ftm_resp, iwl_tof_range_rsp_ntfy, request_id)
+
+/**
+ * DOC: Handlers for fw notifications
+ *
+ * Here are listed the notifications IDs (including the group ID), the handler
+ * of the notification and how it should be called:
+ *
+ *  - RX_HANDLER_SYNC: will be called as part of the Rx path
+ *  - RX_HANDLER_ASYNC: will be handled in a working with the wiphy_lock held
+ *
+ * This means that if the firmware sends two notifications A and B in that
+ * order and notification A is RX_HANDLER_ASYNC and notification is
+ * RX_HANDLER_SYNC, the handler of B will likely be called before the handler
+ * of A.
+ *
+ * This list should be in order of frequency for performance purposes.
+ * The handler can be one from two contexts, see &iwl_rx_handler_context
+ *
+ * A handler can declare that it relies on a specific object in which case it
+ * can be cancelled in case the object is deleted. In order to use this
+ * mechanism, a cancellation function is needed. The cancellation function must
+ * receive an object id (the index of that object in the firmware) and a
+ * notification payload. It'll return true if that specific notification should
+ * be cancelled upon the obliteration of the specific instance of the object.
+ *
+ * DEFINE_SIMPLE_CANCELLATION allows to easily create a cancellation function
+ * that wills simply return true if a given object id matches the object id in
+ * the firmware notification.
+ */
+
+VISIBLE_IF_IWLWIFI_KUNIT
+const struct iwl_rx_handler iwl_mld_rx_handlers[] = {
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, TX_CMD, tx_resp_notif,
+			     RX_HANDLER_SYNC)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, BA_NOTIF, compressed_ba_notif,
+			     RX_HANDLER_SYNC)
+	RX_HANDLER_OF_SCAN(LEGACY_GROUP, SCAN_COMPLETE_UMAC,
+			   scan_complete_notif)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, SCAN_ITERATION_COMPLETE_UMAC,
+			     scan_iter_complete_notif,
+			     RX_HANDLER_SYNC)
+	RX_HANDLER_NO_VAL(LEGACY_GROUP, MATCH_FOUND_NOTIFICATION,
+			  match_found_notif, RX_HANDLER_SYNC)
+
+	RX_HANDLER_NO_OBJECT(STATISTICS_GROUP, STATISTICS_OPER_NOTIF,
+			     stats_oper_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_NO_OBJECT(STATISTICS_GROUP, STATISTICS_OPER_PART1_NOTIF,
+			     stats_oper_part1_notif, RX_HANDLER_ASYNC)
+
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, MFUART_LOAD_NOTIFICATION,
+			     mfuart_notif, RX_HANDLER_SYNC)
+
+	RX_HANDLER_NO_OBJECT(PHY_OPS_GROUP, DTS_MEASUREMENT_NOTIF_WIDE,
+			     temp_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_OF_LINK(MAC_CONF_GROUP, SESSION_PROTECTION_NOTIF,
+			   session_prot_notif)
+	RX_HANDLER_OF_LINK(MAC_CONF_GROUP, MISSED_BEACONS_NOTIF,
+			   missed_beacon_notif)
+	RX_HANDLER_OF_STA(DATA_PATH_GROUP, TLC_MNG_UPDATE_NOTIF, tlc_notif)
+	RX_HANDLER_OF_LINK(MAC_CONF_GROUP, CHANNEL_SWITCH_START_NOTIF,
+			   channel_switch_start_notif)
+	RX_HANDLER_OF_LINK(MAC_CONF_GROUP, CHANNEL_SWITCH_ERROR_NOTIF,
+			   channel_switch_error_notif)
+	RX_HANDLER_OF_ROC(MAC_CONF_GROUP, ROC_NOTIF, roc_notif)
+	RX_HANDLER_NO_OBJECT(DATA_PATH_GROUP, MU_GROUP_MGMT_NOTIF,
+			     mu_mimo_grp_notif, RX_HANDLER_SYNC)
+	RX_HANDLER_NO_OBJECT(PROT_OFFLOAD_GROUP, STORED_BEACON_NTF,
+			     stored_beacon_notif, RX_HANDLER_SYNC)
+	RX_HANDLER_OF_VIF(MAC_CONF_GROUP, PROBE_RESPONSE_DATA_NOTIF,
+			  probe_resp_data_notif)
+	RX_HANDLER_NO_OBJECT(PHY_OPS_GROUP, CT_KILL_NOTIFICATION,
+			     ct_kill_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_OF_LINK(DATA_PATH_GROUP, MONITOR_NOTIF,
+			   datapath_monitor_notif)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, MCC_CHUB_UPDATE_CMD, update_mcc,
+			     RX_HANDLER_ASYNC)
+	RX_HANDLER_NO_OBJECT(BT_COEX_GROUP, PROFILE_NOTIF,
+			     bt_coex_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP, BEACON_NOTIFICATION,
+			     beacon_notification, RX_HANDLER_ASYNC)
+	RX_HANDLER_NO_OBJECT(DATA_PATH_GROUP, ESR_MODE_NOTIF,
+			     emlsr_mode_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_NO_OBJECT(MAC_CONF_GROUP, EMLSR_TRANS_FAIL_NOTIF,
+			     emlsr_trans_fail_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_OF_VIF(LEGACY_GROUP, PSM_UAPSD_AP_MISBEHAVING_NOTIFICATION,
+			  uapsd_misbehaving_ap_notif)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP,
+			     WNM_80211V_TIMING_MEASUREMENT_NOTIFICATION,
+			     time_msmt_notif, RX_HANDLER_SYNC)
+	RX_HANDLER_NO_OBJECT(LEGACY_GROUP,
+			     WNM_80211V_TIMING_MEASUREMENT_CONFIRM_NOTIFICATION,
+			     time_sync_confirm_notif, RX_HANDLER_ASYNC)
+	RX_HANDLER_OF_LINK(DATA_PATH_GROUP, OMI_SEND_STATUS_NOTIF,
+			   omi_status_notif)
+	RX_HANDLER_OF_FTM_REQ(LOCATION_GROUP, TOF_RANGE_RESPONSE_NOTIF,
+			      ftm_resp_notif)
+};
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_rx_handlers);
+
+#if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
+const unsigned int iwl_mld_rx_handlers_num = ARRAY_SIZE(iwl_mld_rx_handlers);
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_rx_handlers_num);
+#endif
+
+static bool
+iwl_mld_notif_is_valid(struct iwl_mld *mld, struct iwl_rx_packet *pkt,
+		       const struct iwl_rx_handler *handler)
+{
+	unsigned int size = iwl_rx_packet_payload_len(pkt);
+	size_t notif_ver;
+
+	/* If n_sizes == 0, it indicates that a validation function may be used
+	 * or that no validation is required.
+	 */
+	if (!handler->n_sizes) {
+		if (handler->val_fn)
+			return handler->val_fn(mld, pkt);
+		return true;
+	}
+
+	notif_ver = iwl_fw_lookup_notif_ver(mld->fw,
+					    iwl_cmd_groupid(handler->cmd_id),
+					    iwl_cmd_opcode(handler->cmd_id),
+					    IWL_FW_CMD_VER_UNKNOWN);
+
+	for (int i = 0; i < handler->n_sizes; i++) {
+		if (handler->sizes[i].ver != notif_ver)
+			continue;
+
+		if (IWL_FW_CHECK(mld, size < handler->sizes[i].size,
+				 "unexpected notification 0x%04x size %d, need %d\n",
+				 handler->cmd_id, size, handler->sizes[i].size))
+			return false;
+		return true;
+	}
+
+	IWL_FW_CHECK_FAILED(mld,
+			    "notif 0x%04x ver %zu missing expected size, use version %u size\n",
+			    handler->cmd_id, notif_ver,
+			    handler->sizes[handler->n_sizes - 1].ver);
+
+	return size < handler->sizes[handler->n_sizes - 1].size;
+}
+
+struct iwl_async_handler_entry {
+	struct list_head list;
+	struct iwl_rx_cmd_buffer rxb;
+	const struct iwl_rx_handler *rx_h;
+};
+
+static void
+iwl_mld_log_async_handler_op(struct iwl_mld *mld, const char *op,
+			     struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+
+	IWL_DEBUG_HC(mld,
+		     "%s async handler for notif %s (%.2x.%2x, seq 0x%x)\n",
+		     op, iwl_get_cmd_string(mld->trans,
+		     WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd)),
+		     pkt->hdr.group_id, pkt->hdr.cmd,
+		     le16_to_cpu(pkt->hdr.sequence));
+}
+
+static void iwl_mld_rx_notif(struct iwl_mld *mld,
+			     struct iwl_rx_cmd_buffer *rxb,
+			     struct iwl_rx_packet *pkt)
+{
+	for (int i = 0; i < ARRAY_SIZE(iwl_mld_rx_handlers); i++) {
+		const struct iwl_rx_handler *rx_h = &iwl_mld_rx_handlers[i];
+		struct iwl_async_handler_entry *entry;
+
+		if (rx_h->cmd_id != WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd))
+			continue;
+
+		if (!iwl_mld_notif_is_valid(mld, pkt, rx_h))
+			return;
+
+		if (rx_h->context == RX_HANDLER_SYNC) {
+			rx_h->fn(mld, pkt);
+			break;
+		}
+
+		entry = kzalloc(sizeof(*entry), GFP_ATOMIC);
+		/* we can't do much... */
+		if (!entry)
+			return;
+
+		/* Set the async handler entry */
+		entry->rxb._page = rxb_steal_page(rxb);
+		entry->rxb._offset = rxb->_offset;
+		entry->rxb._rx_page_order = rxb->_rx_page_order;
+
+		entry->rx_h = rx_h;
+
+		/* Add it to the list and queue the work */
+		spin_lock(&mld->async_handlers_lock);
+		list_add_tail(&entry->list, &mld->async_handlers_list);
+		spin_unlock(&mld->async_handlers_lock);
+
+		wiphy_work_queue(mld->hw->wiphy,
+				 &mld->async_handlers_wk);
+
+		iwl_mld_log_async_handler_op(mld, "Queued", rxb);
+		break;
+	}
+
+	iwl_notification_wait_notify(&mld->notif_wait, pkt);
+}
+
+void iwl_mld_rx(struct iwl_op_mode *op_mode, struct napi_struct *napi,
+		struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	u16 cmd_id = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
+
+	if (likely(cmd_id == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD)))
+		iwl_mld_rx_mpdu(mld, napi, rxb, 0);
+	else if (cmd_id == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE))
+		iwl_mld_handle_frame_release_notif(mld, napi, pkt, 0);
+	else if (cmd_id == WIDE_ID(LEGACY_GROUP, BAR_FRAME_RELEASE))
+		iwl_mld_handle_bar_frame_release_notif(mld, napi, pkt, 0);
+	else if (unlikely(cmd_id == WIDE_ID(DATA_PATH_GROUP,
+					    RX_QUEUES_NOTIFICATION)))
+		iwl_mld_handle_rx_queues_sync_notif(mld, napi, pkt, 0);
+	else if (cmd_id == WIDE_ID(DATA_PATH_GROUP, RX_NO_DATA_NOTIF))
+		iwl_mld_rx_monitor_no_data(mld, napi, pkt, 0);
+	else
+		iwl_mld_rx_notif(mld, rxb, pkt);
+}
+
+void iwl_mld_rx_rss(struct iwl_op_mode *op_mode, struct napi_struct *napi,
+		    struct iwl_rx_cmd_buffer *rxb, unsigned int queue)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_mld *mld = IWL_OP_MODE_GET_MLD(op_mode);
+	u16 cmd_id = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
+
+	if (unlikely(queue >= mld->trans->num_rx_queues))
+		return;
+
+	if (likely(cmd_id == WIDE_ID(LEGACY_GROUP, REPLY_RX_MPDU_CMD)))
+		iwl_mld_rx_mpdu(mld, napi, rxb, queue);
+	else if (unlikely(cmd_id == WIDE_ID(DATA_PATH_GROUP,
+					    RX_QUEUES_NOTIFICATION)))
+		iwl_mld_handle_rx_queues_sync_notif(mld, napi, pkt, queue);
+	else if (unlikely(cmd_id == WIDE_ID(LEGACY_GROUP, FRAME_RELEASE)))
+		iwl_mld_handle_frame_release_notif(mld, napi, pkt, queue);
+}
+
+void iwl_mld_delete_handlers(struct iwl_mld *mld, const u16 *cmds, int n_cmds)
+{
+	struct iwl_async_handler_entry *entry, *tmp;
+
+	spin_lock_bh(&mld->async_handlers_lock);
+	list_for_each_entry_safe(entry, tmp, &mld->async_handlers_list, list) {
+		bool match = false;
+
+		for (int i = 0; i < n_cmds; i++) {
+			if (entry->rx_h->cmd_id == cmds[i]) {
+				match = true;
+				break;
+			}
+		}
+
+		if (!match)
+			continue;
+
+		iwl_mld_log_async_handler_op(mld, "Delete", &entry->rxb);
+		iwl_free_rxb(&entry->rxb);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+	spin_unlock_bh(&mld->async_handlers_lock);
+}
+
+void iwl_mld_async_handlers_wk(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld *mld =
+		container_of(wk, struct iwl_mld, async_handlers_wk);
+	struct iwl_async_handler_entry *entry, *tmp;
+	LIST_HEAD(local_list);
+
+	/* Sync with Rx path with a lock. Remove all the entries from this
+	 * list, add them to a local one (lock free), and then handle them.
+	 */
+	spin_lock_bh(&mld->async_handlers_lock);
+	list_splice_init(&mld->async_handlers_list, &local_list);
+	spin_unlock_bh(&mld->async_handlers_lock);
+
+	list_for_each_entry_safe(entry, tmp, &local_list, list) {
+		iwl_mld_log_async_handler_op(mld, "Handle", &entry->rxb);
+		entry->rx_h->fn(mld, rxb_addr(&entry->rxb));
+		iwl_free_rxb(&entry->rxb);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
+
+void iwl_mld_purge_async_handlers_list(struct iwl_mld *mld)
+{
+	struct iwl_async_handler_entry *entry, *tmp;
+
+	spin_lock_bh(&mld->async_handlers_lock);
+	list_for_each_entry_safe(entry, tmp, &mld->async_handlers_list, list) {
+		iwl_mld_log_async_handler_op(mld, "Purged", &entry->rxb);
+		iwl_free_rxb(&entry->rxb);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+	spin_unlock_bh(&mld->async_handlers_lock);
+}
+
+void iwl_mld_cancel_notifications_of_object(struct iwl_mld *mld,
+					    enum iwl_mld_object_type obj_type,
+					    u32 obj_id)
+{
+	struct iwl_async_handler_entry *entry, *tmp;
+	LIST_HEAD(cancel_list);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (WARN_ON(obj_type == IWL_MLD_OBJECT_TYPE_NONE))
+		return;
+
+	/* Sync with RX path and remove matching entries from the async list */
+	spin_lock_bh(&mld->async_handlers_lock);
+	list_for_each_entry_safe(entry, tmp, &mld->async_handlers_list, list) {
+		const struct iwl_rx_handler *rx_h = entry->rx_h;
+
+		if (rx_h->obj_type != obj_type || WARN_ON(!rx_h->cancel))
+			continue;
+
+		if (rx_h->cancel(mld, rxb_addr(&entry->rxb), obj_id)) {
+			iwl_mld_log_async_handler_op(mld, "Cancel", &entry->rxb);
+			list_del(&entry->list);
+			list_add_tail(&entry->list, &cancel_list);
+		}
+	}
+
+	spin_unlock_bh(&mld->async_handlers_lock);
+
+	/* Free the matching entries outside of the spinlock */
+	list_for_each_entry_safe(entry, tmp, &cancel_list, list) {
+		iwl_free_rxb(&entry->rxb);
+		list_del(&entry->list);
+		kfree(entry);
+	}
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.h b/drivers/net/wireless/intel/iwlwifi/mld/notif.h
new file mode 100644
index 0000000000000..2eaa1d4e138ee
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_notif_h__
+#define __iwl_mld_notif_h__
+
+struct iwl_mld;
+
+void iwl_mld_rx(struct iwl_op_mode *op_mode, struct napi_struct *napi,
+		struct iwl_rx_cmd_buffer *rxb);
+
+void iwl_mld_rx_rss(struct iwl_op_mode *op_mode, struct napi_struct *napi,
+		    struct iwl_rx_cmd_buffer *rxb, unsigned int queue);
+
+void iwl_mld_async_handlers_wk(struct wiphy *wiphy, struct wiphy_work *wk);
+
+void iwl_mld_purge_async_handlers_list(struct iwl_mld *mld);
+
+enum iwl_mld_object_type {
+	IWL_MLD_OBJECT_TYPE_NONE,
+	IWL_MLD_OBJECT_TYPE_LINK,
+	IWL_MLD_OBJECT_TYPE_STA,
+	IWL_MLD_OBJECT_TYPE_VIF,
+	IWL_MLD_OBJECT_TYPE_ROC,
+	IWL_MLD_OBJECT_TYPE_SCAN,
+	IWL_MLD_OBJECT_TYPE_FTM_REQ,
+};
+
+void iwl_mld_cancel_notifications_of_object(struct iwl_mld *mld,
+					    enum iwl_mld_object_type obj_type,
+					    u32 obj_id);
+void iwl_mld_delete_handlers(struct iwl_mld *mld, const u16 *cmds, int n_cmds);
+
+#endif /* __iwl_mld_notif_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.c b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
new file mode 100644
index 0000000000000..c38f101628de3
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
@@ -0,0 +1,116 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include <net/mac80211.h>
+
+#include "phy.h"
+#include "hcmd.h"
+#include "fw/api/phy-ctxt.h"
+
+int iwl_mld_allocate_fw_phy_id(struct iwl_mld *mld)
+{
+	int id;
+	unsigned long used = mld->used_phy_ids;
+
+	for_each_clear_bit(id, &used, NUM_PHY_CTX) {
+		mld->used_phy_ids |= BIT(id);
+		return id;
+	}
+
+	return -ENOSPC;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_allocate_fw_phy_id);
+
+struct cfg80211_chan_def *
+iwl_mld_get_chandef_from_chanctx(struct ieee80211_chanctx_conf *ctx)
+{
+	bool use_def = cfg80211_channel_is_psc(ctx->def.chan) ||
+		(ctx->def.chan->band == NL80211_BAND_6GHZ &&
+		 ctx->def.width >= NL80211_CHAN_WIDTH_80);
+
+	return use_def ? &ctx->def : &ctx->min_def;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_get_chandef_from_chanctx);
+
+static u8
+iwl_mld_nl80211_width_to_fw(enum nl80211_chan_width width)
+{
+	switch (width) {
+	case NL80211_CHAN_WIDTH_20_NOHT:
+	case NL80211_CHAN_WIDTH_20:
+		return IWL_PHY_CHANNEL_MODE20;
+	case NL80211_CHAN_WIDTH_40:
+		return IWL_PHY_CHANNEL_MODE40;
+	case NL80211_CHAN_WIDTH_80:
+		return IWL_PHY_CHANNEL_MODE80;
+	case NL80211_CHAN_WIDTH_160:
+		return IWL_PHY_CHANNEL_MODE160;
+	case NL80211_CHAN_WIDTH_320:
+		return IWL_PHY_CHANNEL_MODE320;
+	default:
+		WARN(1, "Invalid channel width=%u", width);
+		return IWL_PHY_CHANNEL_MODE20;
+	}
+}
+
+/* Maps the driver specific control channel position (relative to the center
+ * freq) definitions to the fw values
+ */
+u8 iwl_mld_get_fw_ctrl_pos(const struct cfg80211_chan_def *chandef)
+{
+	int offs = chandef->chan->center_freq - chandef->center_freq1;
+	int abs_offs = abs(offs);
+	u8 ret;
+
+	if (offs == 0) {
+		/* The FW is expected to check the control channel position only
+		 * when in HT/VHT and the channel width is not 20MHz. Return
+		 * this value as the default one.
+		 */
+		return 0;
+	}
+
+	/* this results in a value 0-7, i.e. fitting into 0b0111 */
+	ret = (abs_offs - 10) / 20;
+	/* But we need the value to be in 0b1011 because 0b0100 is
+	 * IWL_PHY_CTRL_POS_ABOVE, so shift bit 2 up to land in
+	 * IWL_PHY_CTRL_POS_OFFS_EXT (0b1000)
+	 */
+	ret = (ret & IWL_PHY_CTRL_POS_OFFS_MSK) |
+	      ((ret & BIT(2)) << 1);
+	/* and add the above bit */
+	ret |= (offs > 0) * IWL_PHY_CTRL_POS_ABOVE;
+
+	return ret;
+}
+
+int iwl_mld_phy_fw_action(struct iwl_mld *mld,
+			  struct ieee80211_chanctx_conf *ctx, u32 action)
+{
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+	struct cfg80211_chan_def *chandef = &phy->chandef;
+	struct iwl_phy_context_cmd cmd = {
+		.id_and_color = cpu_to_le32(phy->fw_id),
+		.action = cpu_to_le32(action),
+		.puncture_mask = cpu_to_le16(chandef->punctured),
+		/* Channel info */
+		.ci.channel = cpu_to_le32(chandef->chan->hw_value),
+		.ci.band = iwl_mld_nl80211_band_to_fw(chandef->chan->band),
+		.ci.width = iwl_mld_nl80211_width_to_fw(chandef->width),
+		.ci.ctrl_pos = iwl_mld_get_fw_ctrl_pos(chandef),
+	};
+	int ret;
+
+	if (ctx->ap.chan) {
+		cmd.sbb_bandwidth =
+			iwl_mld_nl80211_width_to_fw(ctx->ap.width);
+		cmd.sbb_ctrl_channel_loc = iwl_mld_get_fw_ctrl_pos(&ctx->ap);
+	}
+
+	ret = iwl_mld_send_cmd_pdu(mld, PHY_CONTEXT_CMD, &cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to send PHY_CONTEXT_CMD ret = %d\n", ret);
+
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.h b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
new file mode 100644
index 0000000000000..3dfb8ca994e2e
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_phy_h__
+#define __iwl_mld_phy_h__
+
+#include "mld.h"
+
+/**
+ * struct iwl_mld_phy - PHY configuration parameters
+ *
+ * @fw_id: fw id of the phy.
+ * @chandef: the last chandef that mac80211 configured the driver
+ *	with. Used to detect a no-op when the chanctx changes.
+ * @channel_load_by_us: channel load on this channel caused by
+ *	the NIC itself, as indicated by firmware
+ */
+struct iwl_mld_phy {
+	/* Add here fields that need clean up on hw restart */
+	struct_group(zeroed_on_hw_restart,
+		u8 fw_id;
+		struct cfg80211_chan_def chandef;
+	);
+	/* And here fields that survive a hw restart */
+	u32 channel_load_by_us;
+};
+
+static inline struct iwl_mld_phy *
+iwl_mld_phy_from_mac80211(struct ieee80211_chanctx_conf *channel)
+{
+	return (void *)channel->drv_priv;
+}
+
+/* Cleanup function for struct iwl_mld_phy, will be called in restart */
+static inline void
+iwl_mld_cleanup_phy(struct iwl_mld *mld, struct iwl_mld_phy *phy)
+{
+	CLEANUP_STRUCT(phy);
+}
+
+int iwl_mld_allocate_fw_phy_id(struct iwl_mld *mld);
+int iwl_mld_phy_fw_action(struct iwl_mld *mld,
+			  struct ieee80211_chanctx_conf *ctx, u32 action);
+struct cfg80211_chan_def *
+iwl_mld_get_chandef_from_chanctx(struct ieee80211_chanctx_conf *ctx);
+u8 iwl_mld_get_fw_ctrl_pos(const struct cfg80211_chan_def *chandef);
+
+#endif /* __iwl_mld_phy_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/power.c b/drivers/net/wireless/intel/iwlwifi/mld/power.c
new file mode 100644
index 0000000000000..ed7c0319f239b
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/power.c
@@ -0,0 +1,395 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include <net/mac80211.h>
+
+#include "mld.h"
+#include "hcmd.h"
+#include "power.h"
+#include "iface.h"
+#include "link.h"
+#include "constants.h"
+
+static void iwl_mld_vif_ps_iterator(void *data, u8 *mac,
+				    struct ieee80211_vif *vif)
+{
+	bool *ps_enable = (bool *)data;
+
+	if (vif->type != NL80211_IFTYPE_STATION)
+		return;
+
+	*ps_enable &= vif->cfg.ps;
+}
+
+int iwl_mld_update_device_power(struct iwl_mld *mld, bool d3)
+{
+	struct iwl_device_power_cmd cmd = {};
+	bool enable_ps = false;
+
+	if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM) {
+		enable_ps = true;
+
+		/* Disable power save if any STA interface has
+		 * power save turned off
+		 */
+		ieee80211_iterate_active_interfaces_mtx(mld->hw,
+							IEEE80211_IFACE_ITER_NORMAL,
+							iwl_mld_vif_ps_iterator,
+							&enable_ps);
+	}
+
+	if (enable_ps)
+		cmd.flags |=
+			cpu_to_le16(DEVICE_POWER_FLAGS_POWER_SAVE_ENA_MSK);
+
+	if (d3)
+		cmd.flags |=
+			cpu_to_le16(DEVICE_POWER_FLAGS_NO_SLEEP_TILL_D3_MSK);
+
+	IWL_DEBUG_POWER(mld,
+			"Sending device power command with flags = 0x%X\n",
+			cmd.flags);
+
+	return iwl_mld_send_cmd_pdu(mld, POWER_TABLE_CMD, &cmd);
+}
+
+int iwl_mld_enable_beacon_filter(struct iwl_mld *mld,
+				 const struct ieee80211_bss_conf *link_conf,
+				 bool d3)
+{
+	struct iwl_beacon_filter_cmd cmd = {
+		IWL_BF_CMD_CONFIG_DEFAULTS,
+		.bf_enable_beacon_filter = cpu_to_le32(1),
+		.ba_enable_beacon_abort = cpu_to_le32(1),
+	};
+
+	if (ieee80211_vif_type_p2p(link_conf->vif) != NL80211_IFTYPE_STATION)
+		return 0;
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	if (iwl_mld_vif_from_mac80211(link_conf->vif)->disable_bf)
+		return 0;
+#endif
+
+	if (link_conf->cqm_rssi_thold) {
+		cmd.bf_energy_delta =
+			cpu_to_le32(link_conf->cqm_rssi_hyst);
+		/* fw uses an absolute value for this */
+		cmd.bf_roaming_state =
+			cpu_to_le32(-link_conf->cqm_rssi_thold);
+	}
+
+	if (d3)
+		cmd.ba_escape_timer = cpu_to_le32(IWL_BA_ESCAPE_TIMER_D3);
+
+	return iwl_mld_send_cmd_pdu(mld, REPLY_BEACON_FILTERING_CMD,
+				    &cmd);
+}
+
+int iwl_mld_disable_beacon_filter(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif)
+{
+	struct iwl_beacon_filter_cmd cmd = {};
+
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION)
+		return 0;
+
+	return iwl_mld_send_cmd_pdu(mld, REPLY_BEACON_FILTERING_CMD,
+				    &cmd);
+}
+
+static bool iwl_mld_power_is_radar(struct iwl_mld *mld,
+				   const struct ieee80211_bss_conf *link_conf)
+{
+	const struct ieee80211_chanctx_conf *chanctx_conf;
+
+	chanctx_conf = wiphy_dereference(mld->wiphy, link_conf->chanctx_conf);
+
+	if (WARN_ON(!chanctx_conf))
+		return false;
+
+	return chanctx_conf->def.chan->flags & IEEE80211_CHAN_RADAR;
+}
+
+static void iwl_mld_power_configure_uapsd(struct iwl_mld *mld,
+					  struct iwl_mld_link *link,
+					  struct iwl_mac_power_cmd *cmd,
+					  bool ps_poll)
+{
+	bool tid_found = false;
+
+	cmd->rx_data_timeout_uapsd =
+		cpu_to_le32(IWL_MLD_UAPSD_RX_DATA_TIMEOUT);
+	cmd->tx_data_timeout_uapsd =
+		cpu_to_le32(IWL_MLD_UAPSD_TX_DATA_TIMEOUT);
+
+	 /* set advanced pm flag with no uapsd ACs to enable ps-poll */
+	if (ps_poll) {
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_ADVANCE_PM_ENA_MSK);
+		return;
+	}
+
+	for (enum ieee80211_ac_numbers ac = IEEE80211_AC_VO;
+	     ac <= IEEE80211_AC_BK;
+	     ac++) {
+		if (!link->queue_params[ac].uapsd)
+			continue;
+
+		cmd->flags |=
+			cpu_to_le16(POWER_FLAGS_ADVANCE_PM_ENA_MSK |
+				    POWER_FLAGS_UAPSD_MISBEHAVING_ENA_MSK);
+
+		cmd->uapsd_ac_flags |= BIT(ac);
+
+		/* QNDP TID - the highest TID with no admission control */
+		if (!tid_found && !link->queue_params[ac].acm) {
+			tid_found = true;
+			switch (ac) {
+			case IEEE80211_AC_VO:
+				cmd->qndp_tid = 6;
+				break;
+			case IEEE80211_AC_VI:
+				cmd->qndp_tid = 5;
+				break;
+			case IEEE80211_AC_BE:
+				cmd->qndp_tid = 0;
+				break;
+			case IEEE80211_AC_BK:
+				cmd->qndp_tid = 1;
+				break;
+			}
+		}
+	}
+
+	if (cmd->uapsd_ac_flags == (BIT(IEEE80211_AC_VO) |
+				    BIT(IEEE80211_AC_VI) |
+				    BIT(IEEE80211_AC_BE) |
+				    BIT(IEEE80211_AC_BK))) {
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_SNOOZE_ENA_MSK);
+		cmd->snooze_interval = cpu_to_le16(IWL_MLD_PS_SNOOZE_INTERVAL);
+		cmd->snooze_window = cpu_to_le16(IWL_MLD_PS_SNOOZE_WINDOW);
+	}
+
+	cmd->uapsd_max_sp = mld->hw->uapsd_max_sp_len;
+}
+
+static void
+iwl_mld_power_config_skip_dtim(struct iwl_mld *mld,
+			       const struct ieee80211_bss_conf *link_conf,
+			       struct iwl_mac_power_cmd *cmd)
+{
+	unsigned int dtimper_tu;
+	unsigned int dtimper;
+	unsigned int skip;
+
+	dtimper = link_conf->dtim_period ?: 1;
+	dtimper_tu = dtimper * link_conf->beacon_int;
+
+	if (dtimper >= 10 || iwl_mld_power_is_radar(mld, link_conf))
+		return;
+
+	if (WARN_ON(!dtimper_tu))
+		return;
+
+	/* configure skip over dtim up to 900 TU DTIM interval */
+	skip = max_t(int, 1, 900 / dtimper_tu);
+
+	cmd->skip_dtim_periods = skip;
+	cmd->flags |= cpu_to_le16(POWER_FLAGS_SKIP_OVER_DTIM_MSK);
+}
+
+#define POWER_KEEP_ALIVE_PERIOD_SEC    25
+static void iwl_mld_power_build_cmd(struct iwl_mld *mld,
+				    struct ieee80211_vif *vif,
+				    struct iwl_mac_power_cmd *cmd,
+				    bool d3)
+{
+	int dtimper, bi;
+	int keep_alive;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct ieee80211_bss_conf *link_conf = &vif->bss_conf;
+	struct iwl_mld_link *link = &mld_vif->deflink;
+	bool ps_poll = false;
+
+	cmd->id_and_color = cpu_to_le32(mld_vif->fw_id);
+
+	if (ieee80211_vif_is_mld(vif)) {
+		int link_id;
+
+		if (WARN_ON(!vif->active_links))
+			return;
+
+		/* The firmware consumes one single configuration for the vif
+		 * and can't differentiate between links, just pick the lowest
+		 * link_id's configuration and use that.
+		 */
+		link_id = __ffs(vif->active_links);
+		link_conf = link_conf_dereference_check(vif, link_id);
+		link = iwl_mld_link_dereference_check(mld_vif, link_id);
+
+		if (WARN_ON(!link_conf || !link))
+			return;
+	}
+	dtimper = link_conf->dtim_period;
+	bi = link_conf->beacon_int;
+
+	/* Regardless of power management state the driver must set
+	 * keep alive period. FW will use it for sending keep alive NDPs
+	 * immediately after association. Check that keep alive period
+	 * is at least 3 * DTIM
+	 */
+	keep_alive = DIV_ROUND_UP(ieee80211_tu_to_usec(3 * dtimper * bi),
+				  USEC_PER_SEC);
+	keep_alive = max(keep_alive, POWER_KEEP_ALIVE_PERIOD_SEC);
+	cmd->keep_alive_seconds = cpu_to_le16(keep_alive);
+
+	if (iwlmld_mod_params.power_scheme != IWL_POWER_SCHEME_CAM)
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_POWER_SAVE_ENA_MSK);
+
+	if (!vif->cfg.ps || iwl_mld_tdls_sta_count(mld) > 0)
+		return;
+
+	cmd->flags |= cpu_to_le16(POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK);
+
+	/* firmware supports LPRX for beacons at rate 1 Mbps or 6 Mbps only */
+	if (link_conf->beacon_rate &&
+	    (link_conf->beacon_rate->bitrate == 10 ||
+	     link_conf->beacon_rate->bitrate == 60)) {
+		cmd->flags |= cpu_to_le16(POWER_FLAGS_LPRX_ENA_MSK);
+		cmd->lprx_rssi_threshold = POWER_LPRX_RSSI_THRESHOLD;
+	}
+
+	if (d3) {
+		iwl_mld_power_config_skip_dtim(mld, link_conf, cmd);
+		cmd->rx_data_timeout =
+			cpu_to_le32(IWL_MLD_WOWLAN_PS_RX_DATA_TIMEOUT);
+		cmd->tx_data_timeout =
+			cpu_to_le32(IWL_MLD_WOWLAN_PS_TX_DATA_TIMEOUT);
+	} else if (iwl_mld_vif_low_latency(mld_vif) && vif->p2p) {
+		cmd->tx_data_timeout =
+			cpu_to_le32(IWL_MLD_SHORT_PS_TX_DATA_TIMEOUT);
+		cmd->rx_data_timeout =
+			cpu_to_le32(IWL_MLD_SHORT_PS_RX_DATA_TIMEOUT);
+	} else {
+		cmd->rx_data_timeout =
+			cpu_to_le32(IWL_MLD_DEFAULT_PS_RX_DATA_TIMEOUT);
+		cmd->tx_data_timeout =
+			cpu_to_le32(IWL_MLD_DEFAULT_PS_TX_DATA_TIMEOUT);
+	}
+
+	/* uAPSD is only enabled for specific certifications. For those cases,
+	 * mac80211 will allow uAPSD. Always call iwl_mld_power_configure_uapsd
+	 * which will look at what mac80211 is saying.
+	 */
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	ps_poll = mld_vif->use_ps_poll;
+#endif
+	iwl_mld_power_configure_uapsd(mld, link, cmd, ps_poll);
+}
+
+int iwl_mld_update_mac_power(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			     bool d3)
+{
+	struct iwl_mac_power_cmd cmd = {};
+
+	iwl_mld_power_build_cmd(mld, vif, &cmd, d3);
+
+	return iwl_mld_send_cmd_pdu(mld, MAC_PM_POWER_TABLE, &cmd);
+}
+
+static void
+iwl_mld_tpe_sta_cmd_data(struct iwl_txpower_constraints_cmd *cmd,
+			 const struct ieee80211_bss_conf *link)
+{
+	u8 i;
+
+	/* NOTE: the 0 here is IEEE80211_TPE_CAT_6GHZ_DEFAULT,
+	 * we fully ignore IEEE80211_TPE_CAT_6GHZ_SUBORDINATE
+	 */
+
+	BUILD_BUG_ON(ARRAY_SIZE(cmd->psd_pwr) !=
+		     ARRAY_SIZE(link->tpe.psd_local[0].power));
+
+	/* if not valid, mac80211 puts default (max value) */
+	for (i = 0; i < ARRAY_SIZE(cmd->psd_pwr); i++)
+		cmd->psd_pwr[i] = min(link->tpe.psd_local[0].power[i],
+				      link->tpe.psd_reg_client[0].power[i]);
+
+	BUILD_BUG_ON(ARRAY_SIZE(cmd->eirp_pwr) !=
+		     ARRAY_SIZE(link->tpe.max_local[0].power));
+
+	for (i = 0; i < ARRAY_SIZE(cmd->eirp_pwr); i++)
+		cmd->eirp_pwr[i] = min(link->tpe.max_local[0].power[i],
+				       link->tpe.max_reg_client[0].power[i]);
+}
+
+void
+iwl_mld_send_ap_tx_power_constraint_cmd(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct ieee80211_bss_conf *link)
+{
+	struct iwl_txpower_constraints_cmd cmd = {};
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!mld_link->active)
+		return;
+
+	if (link->chanreq.oper.chan->band != NL80211_BAND_6GHZ)
+		return;
+
+	cmd.link_id = cpu_to_le16(mld_link->fw_id);
+	memset(cmd.psd_pwr, DEFAULT_TPE_TX_POWER, sizeof(cmd.psd_pwr));
+	memset(cmd.eirp_pwr, DEFAULT_TPE_TX_POWER, sizeof(cmd.eirp_pwr));
+
+	if (vif->type == NL80211_IFTYPE_AP) {
+		cmd.ap_type = cpu_to_le16(IWL_6GHZ_AP_TYPE_VLP);
+	} else if (link->power_type == IEEE80211_REG_UNSET_AP) {
+		return;
+	} else {
+		cmd.ap_type = cpu_to_le16(link->power_type - 1);
+		iwl_mld_tpe_sta_cmd_data(&cmd, link);
+	}
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(PHY_OPS_GROUP,
+					   AP_TX_POWER_CONSTRAINTS_CMD),
+				   &cmd);
+	if (ret)
+		IWL_ERR(mld,
+			"failed to send AP_TX_POWER_CONSTRAINTS_CMD (%d)\n",
+			ret);
+}
+
+int iwl_mld_set_tx_power(struct iwl_mld *mld,
+			 struct ieee80211_bss_conf *link_conf,
+			 s16 tx_power)
+{
+	u32 cmd_id = REDUCE_TX_POWER_CMD;
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link_conf);
+	u16 u_tx_power = tx_power == IWL_DEFAULT_MAX_TX_POWER ?
+		IWL_DEV_MAX_TX_POWER : 8 * tx_power;
+	struct iwl_dev_tx_power_cmd cmd = {
+		/* Those fields sit on the same place for v9 and v10 */
+		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_LINK),
+		.common.pwr_restriction = cpu_to_le16(u_tx_power),
+	};
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mld->fw, cmd_id,
+					   IWL_FW_CMD_VER_UNKNOWN);
+	int len = sizeof(cmd.common);
+
+	if (WARN_ON(!mld_link))
+		return -ENODEV;
+
+	cmd.common.link_id = cpu_to_le32(mld_link->fw_id);
+
+	if (cmd_ver == 10)
+		len += sizeof(cmd.v10);
+	else if (cmd_ver == 9)
+		len += sizeof(cmd.v9);
+
+	return iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd, len);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/power.h b/drivers/net/wireless/intel/iwlwifi/mld/power.h
new file mode 100644
index 0000000000000..05ce27bef1067
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/power.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_power_h__
+#define __iwl_mld_power_h__
+
+#include <net/mac80211.h>
+
+#include "mld.h"
+
+int iwl_mld_update_device_power(struct iwl_mld *mld, bool d3);
+
+int iwl_mld_enable_beacon_filter(struct iwl_mld *mld,
+				 const struct ieee80211_bss_conf *link_conf,
+				 bool d3);
+
+int iwl_mld_disable_beacon_filter(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif);
+
+int iwl_mld_update_mac_power(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			     bool d3);
+
+void
+iwl_mld_send_ap_tx_power_constraint_cmd(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct ieee80211_bss_conf *link);
+
+int iwl_mld_set_tx_power(struct iwl_mld *mld,
+			 struct ieee80211_bss_conf *link_conf,
+			 s16 tx_power);
+
+#endif /* __iwl_mld_power_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.c b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c
new file mode 100644
index 0000000000000..d5c3f853d96c1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.c
@@ -0,0 +1,321 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+
+#include "mld.h"
+#include "iwl-debug.h"
+#include "hcmd.h"
+#include "ptp.h"
+#include <linux/timekeeping.h>
+
+/* The scaled_ppm parameter is ppm (parts per million) with a 16-bit fractional
+ * part, which means that a value of 1 in one of those fields actually means
+ * 2^-16 ppm, and 2^16=65536 is 1 ppm.
+ */
+#define PTP_SCALE_FACTOR	65536000000ULL
+
+#define IWL_PTP_GP2_WRAP	0x100000000ULL
+#define IWL_PTP_WRAP_TIME	(3600 * HZ)
+#define IWL_PTP_WRAP_THRESHOLD_USEC	(5000)
+
+static int iwl_mld_get_systime(struct iwl_mld *mld, u32 *gp2)
+{
+	*gp2 = iwl_read_prph(mld->trans, mld->trans->cfg->gp2_reg_addr);
+
+	if (*gp2 == 0x5a5a5a5a)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void iwl_mld_ptp_update_new_read(struct iwl_mld *mld, u32 gp2)
+{
+	IWL_DEBUG_PTP(mld, "PTP: last_gp2=%u, new gp2 read=%u\n",
+		      mld->ptp_data.last_gp2, gp2);
+
+	/* If the difference is above the threshold, assume it's a wraparound.
+	 * Otherwise assume it's an old read and ignore it.
+	 */
+	if (gp2 < mld->ptp_data.last_gp2) {
+		if (mld->ptp_data.last_gp2 - gp2 <
+		    IWL_PTP_WRAP_THRESHOLD_USEC) {
+			IWL_DEBUG_PTP(mld,
+				      "PTP: ignore old read (gp2=%u, last_gp2=%u)\n",
+				      gp2, mld->ptp_data.last_gp2);
+			return;
+		}
+
+		mld->ptp_data.wrap_counter++;
+		IWL_DEBUG_PTP(mld,
+			      "PTP: wraparound detected (new counter=%u)\n",
+			      mld->ptp_data.wrap_counter);
+	}
+
+	mld->ptp_data.last_gp2 = gp2;
+	schedule_delayed_work(&mld->ptp_data.dwork, IWL_PTP_WRAP_TIME);
+}
+
+u64 iwl_mld_ptp_get_adj_time(struct iwl_mld *mld, u64 base_time_ns)
+{
+	struct ptp_data *data = &mld->ptp_data;
+	u64 scale_time_gp2_ns = mld->ptp_data.scale_update_gp2 * NSEC_PER_USEC;
+	u64 res;
+	u64 diff;
+	s64 scaled_diff;
+
+	lockdep_assert_held(&data->lock);
+
+	iwl_mld_ptp_update_new_read(mld,
+				    div64_u64(base_time_ns, NSEC_PER_USEC));
+
+	base_time_ns = base_time_ns +
+		(data->wrap_counter * IWL_PTP_GP2_WRAP * NSEC_PER_USEC);
+
+	/* It is possible that a GP2 timestamp was received from fw before the
+	 * last scale update.
+	 */
+	if (base_time_ns < scale_time_gp2_ns) {
+		diff = scale_time_gp2_ns - base_time_ns;
+		scaled_diff = -mul_u64_u64_div_u64(diff,
+						   data->scaled_freq,
+						   PTP_SCALE_FACTOR);
+	} else {
+		diff = base_time_ns - scale_time_gp2_ns;
+		scaled_diff = mul_u64_u64_div_u64(diff,
+						  data->scaled_freq,
+						  PTP_SCALE_FACTOR);
+	}
+
+	IWL_DEBUG_PTP(mld, "base_time=%llu diff ns=%llu scaled_diff_ns=%lld\n",
+		      (unsigned long long)base_time_ns,
+		      (unsigned long long)diff, (long long)scaled_diff);
+
+	res = data->scale_update_adj_time_ns + data->delta + scaled_diff;
+
+	IWL_DEBUG_PTP(mld, "scale_update_ns=%llu delta=%lld adj=%llu\n",
+		      (unsigned long long)data->scale_update_adj_time_ns,
+		      (long long)data->delta, (unsigned long long)res);
+	return res;
+}
+
+static int iwl_mld_ptp_gettime(struct ptp_clock_info *ptp,
+			       struct timespec64 *ts)
+{
+	struct iwl_mld *mld = container_of(ptp, struct iwl_mld,
+					   ptp_data.ptp_clock_info);
+	struct ptp_data *data = &mld->ptp_data;
+	u32 gp2;
+	u64 ns;
+
+	if (iwl_mld_get_systime(mld, &gp2)) {
+		IWL_DEBUG_PTP(mld, "PTP: gettime: failed to read systime\n");
+		return -EIO;
+	}
+
+	spin_lock_bh(&data->lock);
+	ns = iwl_mld_ptp_get_adj_time(mld, (u64)gp2 * NSEC_PER_USEC);
+	spin_unlock_bh(&data->lock);
+
+	*ts = ns_to_timespec64(ns);
+	return 0;
+}
+
+static int iwl_mld_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta)
+{
+	struct iwl_mld *mld = container_of(ptp, struct iwl_mld,
+					   ptp_data.ptp_clock_info);
+	struct ptp_data *data = &mld->ptp_data;
+
+	spin_lock_bh(&data->lock);
+	data->delta += delta;
+	IWL_DEBUG_PTP(mld, "delta=%lld, new delta=%lld\n", (long long)delta,
+		      (long long)data->delta);
+	spin_unlock_bh(&data->lock);
+	return 0;
+}
+
+static int iwl_mld_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm)
+{
+	struct iwl_mld *mld = container_of(ptp, struct iwl_mld,
+					   ptp_data.ptp_clock_info);
+	struct ptp_data *data = &mld->ptp_data;
+	u32 gp2;
+
+	/* Must call iwl_mld_ptp_get_adj_time() before updating
+	 * data->scale_update_gp2 or data->scaled_freq since
+	 * scale_update_adj_time_ns should reflect the previous scaled_freq.
+	 */
+	if (iwl_mld_get_systime(mld, &gp2)) {
+		IWL_DEBUG_PTP(mld, "adjfine: failed to read systime\n");
+		return -EBUSY;
+	}
+
+	spin_lock_bh(&data->lock);
+	data->scale_update_adj_time_ns =
+		iwl_mld_ptp_get_adj_time(mld, gp2 * NSEC_PER_USEC);
+	data->scale_update_gp2 = gp2;
+
+	/* scale_update_adj_time_ns now relects the configured delta, the
+	 * wrap_counter and the previous scaled frequency. Thus delta and
+	 * wrap_counter should be reset, and the scale frequency is updated
+	 * to the new frequency.
+	 */
+	data->delta = 0;
+	data->wrap_counter = 0;
+	data->scaled_freq = PTP_SCALE_FACTOR + scaled_ppm;
+	IWL_DEBUG_PTP(mld, "adjfine: scaled_ppm=%ld new=%llu\n",
+		      scaled_ppm, (unsigned long long)data->scaled_freq);
+	spin_unlock_bh(&data->lock);
+	return 0;
+}
+
+static void iwl_mld_ptp_work(struct work_struct *wk)
+{
+	struct iwl_mld *mld = container_of(wk, struct iwl_mld,
+					   ptp_data.dwork.work);
+	struct ptp_data *data = &mld->ptp_data;
+	u32 gp2;
+
+	spin_lock_bh(&data->lock);
+	if (!iwl_mld_get_systime(mld, &gp2))
+		iwl_mld_ptp_update_new_read(mld, gp2);
+	else
+		IWL_DEBUG_PTP(mld, "PTP work: failed to read GP2\n");
+	spin_unlock_bh(&data->lock);
+}
+
+static int
+iwl_mld_get_crosstimestamp_fw(struct iwl_mld *mld, u32 *gp2, u64 *sys_time)
+{
+	struct iwl_synced_time_cmd synced_time_cmd = {
+		.operation = cpu_to_le32(IWL_SYNCED_TIME_OPERATION_READ_BOTH)
+	};
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(DATA_PATH_GROUP, WNM_PLATFORM_PTM_REQUEST_CMD),
+		.flags = CMD_WANT_SKB,
+		.data[0] = &synced_time_cmd,
+		.len[0] = sizeof(synced_time_cmd),
+	};
+	struct iwl_synced_time_rsp *resp;
+	struct iwl_rx_packet *pkt;
+	int ret;
+	u64 gp2_10ns;
+
+	wiphy_lock(mld->wiphy);
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	wiphy_unlock(mld->wiphy);
+	if (ret)
+		return ret;
+
+	pkt = cmd.resp_pkt;
+
+	if (iwl_rx_packet_payload_len(pkt) != sizeof(*resp)) {
+		IWL_DEBUG_PTP(mld, "PTP: Invalid PTM command response\n");
+		iwl_free_resp(&cmd);
+		return -EIO;
+	}
+
+	resp = (void *)pkt->data;
+
+	gp2_10ns = (u64)le32_to_cpu(resp->gp2_timestamp_hi) << 32 |
+		le32_to_cpu(resp->gp2_timestamp_lo);
+	*gp2 = div_u64(gp2_10ns, 100);
+
+	*sys_time = (u64)le32_to_cpu(resp->platform_timestamp_hi) << 32 |
+		le32_to_cpu(resp->platform_timestamp_lo);
+
+	iwl_free_resp(&cmd);
+	return ret;
+}
+
+static int
+iwl_mld_phc_get_crosstimestamp(struct ptp_clock_info *ptp,
+			       struct system_device_crosststamp *xtstamp)
+{
+	struct iwl_mld *mld = container_of(ptp, struct iwl_mld,
+					   ptp_data.ptp_clock_info);
+	struct ptp_data *data = &mld->ptp_data;
+	int ret = 0;
+	/* Raw value read from GP2 register in usec */
+	u32 gp2;
+	/* GP2 value in ns*/
+	s64 gp2_ns;
+	/* System (wall) time */
+	ktime_t sys_time;
+
+	memset(xtstamp, 0, sizeof(struct system_device_crosststamp));
+
+	ret = iwl_mld_get_crosstimestamp_fw(mld, &gp2, &sys_time);
+	if (ret) {
+		IWL_DEBUG_PTP(mld,
+			      "PTP: fw get_crosstimestamp failed (ret=%d)\n",
+			      ret);
+		return ret;
+	}
+
+	spin_lock_bh(&data->lock);
+	gp2_ns = iwl_mld_ptp_get_adj_time(mld, (u64)gp2 * NSEC_PER_USEC);
+	spin_unlock_bh(&data->lock);
+
+	IWL_DEBUG_PTP(mld,
+		      "Got Sync Time: GP2:%u, last_GP2: %u, GP2_ns: %lld, sys_time: %lld\n",
+		      gp2, mld->ptp_data.last_gp2, gp2_ns, (s64)sys_time);
+
+	/* System monotonic raw time is not used */
+	xtstamp->device = ns_to_ktime(gp2_ns);
+	xtstamp->sys_realtime = sys_time;
+
+	return ret;
+}
+
+void iwl_mld_ptp_init(struct iwl_mld *mld)
+{
+	if (WARN_ON(mld->ptp_data.ptp_clock))
+		return;
+
+	spin_lock_init(&mld->ptp_data.lock);
+	INIT_DELAYED_WORK(&mld->ptp_data.dwork, iwl_mld_ptp_work);
+
+	mld->ptp_data.ptp_clock_info.owner = THIS_MODULE;
+	mld->ptp_data.ptp_clock_info.gettime64 = iwl_mld_ptp_gettime;
+	mld->ptp_data.ptp_clock_info.max_adj = 0x7fffffff;
+	mld->ptp_data.ptp_clock_info.adjtime = iwl_mld_ptp_adjtime;
+	mld->ptp_data.ptp_clock_info.adjfine = iwl_mld_ptp_adjfine;
+	mld->ptp_data.scaled_freq = PTP_SCALE_FACTOR;
+	mld->ptp_data.ptp_clock_info.getcrosststamp =
+					iwl_mld_phc_get_crosstimestamp;
+
+	/* Give a short 'friendly name' to identify the PHC clock */
+	snprintf(mld->ptp_data.ptp_clock_info.name,
+		 sizeof(mld->ptp_data.ptp_clock_info.name),
+		 "%s", "iwlwifi-PTP");
+
+	mld->ptp_data.ptp_clock =
+		ptp_clock_register(&mld->ptp_data.ptp_clock_info, mld->dev);
+
+	if (IS_ERR_OR_NULL(mld->ptp_data.ptp_clock)) {
+		IWL_ERR(mld, "Failed to register PHC clock (%ld)\n",
+			PTR_ERR(mld->ptp_data.ptp_clock));
+		mld->ptp_data.ptp_clock = NULL;
+	} else {
+		IWL_INFO(mld, "Registered PHC clock: %s, with index: %d\n",
+			 mld->ptp_data.ptp_clock_info.name,
+			 ptp_clock_index(mld->ptp_data.ptp_clock));
+	}
+}
+
+void iwl_mld_ptp_remove(struct iwl_mld *mld)
+{
+	if (mld->ptp_data.ptp_clock) {
+		IWL_INFO(mld, "Unregistering PHC clock: %s, with index: %d\n",
+			 mld->ptp_data.ptp_clock_info.name,
+			 ptp_clock_index(mld->ptp_data.ptp_clock));
+
+		ptp_clock_unregister(mld->ptp_data.ptp_clock);
+		mld->ptp_data.ptp_clock = NULL;
+		mld->ptp_data.last_gp2 = 0;
+		mld->ptp_data.wrap_counter = 0;
+		cancel_delayed_work_sync(&mld->ptp_data.dwork);
+	}
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ptp.h b/drivers/net/wireless/intel/iwlwifi/mld/ptp.h
new file mode 100644
index 0000000000000..f3d18dd304e53
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ptp.h
@@ -0,0 +1,45 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#ifndef __iwl_mld_ptp_h__
+#define __iwl_mld_ptp_h__
+
+#include <linux/ptp_clock_kernel.h>
+
+/**
+ * struct ptp_data - PTP hardware clock data
+ *
+ * @ptp_clock: struct ptp_clock pointer returned by the ptp_clock_register()
+ *	function.
+ * @ptp_clock_info: struct ptp_clock_info that describes a PTP hardware clock
+ * @lock: protects the time adjustments data
+ * @delta: delta between hardware clock and ptp clock in nanoseconds
+ * @scale_update_gp2: GP2 time when the scale was last updated
+ * @scale_update_adj_time_ns: adjusted time when the scale was last updated,
+ *	in nanoseconds
+ * @scaled_freq: clock frequency offset, scaled to 65536000000
+ * @last_gp2: the last GP2 reading from the hardware, used for tracking GP2
+ *	wraparounds
+ * @wrap_counter: number of wraparounds since scale_update_adj_time_ns
+ * @dwork: worker scheduled every 1 hour to detect workarounds
+ */
+struct ptp_data {
+	struct ptp_clock *ptp_clock;
+	struct ptp_clock_info ptp_clock_info;
+
+	spinlock_t lock;
+	s64 delta;
+	u32 scale_update_gp2;
+	u64 scale_update_adj_time_ns;
+	u64 scaled_freq;
+	u32 last_gp2;
+	u32 wrap_counter;
+	struct delayed_work dwork;
+};
+
+void iwl_mld_ptp_init(struct iwl_mld *mld);
+void iwl_mld_ptp_remove(struct iwl_mld *mld);
+u64 iwl_mld_ptp_get_adj_time(struct iwl_mld *mld, u64 base_time_ns);
+
+#endif /* __iwl_mld_ptp_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
new file mode 100644
index 0000000000000..a75af8c1e8ab0
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.c
@@ -0,0 +1,393 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <linux/dmi.h>
+
+#include "fw/regulatory.h"
+#include "fw/acpi.h"
+#include "fw/uefi.h"
+
+#include "regulatory.h"
+#include "mld.h"
+#include "hcmd.h"
+
+void iwl_mld_get_bios_tables(struct iwl_mld *mld)
+{
+	int ret;
+
+	iwl_acpi_get_guid_lock_status(&mld->fwrt);
+
+	ret = iwl_bios_get_ppag_table(&mld->fwrt);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mld,
+				"PPAG BIOS table invalid or unavailable. (%d)\n",
+				ret);
+	}
+
+	ret = iwl_bios_get_wrds_table(&mld->fwrt);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mld,
+				"WRDS SAR BIOS table invalid or unavailable. (%d)\n",
+				ret);
+
+		/* If not available, don't fail and don't bother with EWRD and
+		 * WGDS
+		 */
+
+		if (!iwl_bios_get_wgds_table(&mld->fwrt)) {
+			/* If basic SAR is not available, we check for WGDS,
+			 * which should *not* be available either. If it is
+			 * available, issue an error, because we can't use SAR
+			 * Geo without basic SAR.
+			 */
+			IWL_ERR(mld, "BIOS contains WGDS but no WRDS\n");
+		}
+
+	} else {
+		ret = iwl_bios_get_ewrd_table(&mld->fwrt);
+		/* If EWRD is not available, we can still use
+		 * WRDS, so don't fail.
+		 */
+		if (ret < 0)
+			IWL_DEBUG_RADIO(mld,
+					"EWRD SAR BIOS table invalid or unavailable. (%d)\n",
+					ret);
+
+		ret = iwl_bios_get_wgds_table(&mld->fwrt);
+		if (ret < 0)
+			IWL_DEBUG_RADIO(mld,
+					"Geo SAR BIOS table invalid or unavailable. (%d)\n",
+					ret);
+		/* we don't fail if the table is not available */
+	}
+
+	ret = iwl_uefi_get_uats_table(mld->trans, &mld->fwrt);
+	if (ret)
+		IWL_DEBUG_RADIO(mld, "failed to read UATS table (%d)\n", ret);
+}
+
+static int iwl_mld_geo_sar_init(struct iwl_mld *mld)
+{
+	u32 cmd_id = WIDE_ID(PHY_OPS_GROUP, PER_CHAIN_LIMIT_OFFSET_CMD);
+	union iwl_geo_tx_power_profiles_cmd cmd;
+	u16 len;
+	u32 n_bands;
+	__le32 sk = cpu_to_le32(0);
+	int ret;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mld->fw, cmd_id,
+					   IWL_FW_CMD_VER_UNKNOWN);
+
+	BUILD_BUG_ON(offsetof(struct iwl_geo_tx_power_profiles_cmd_v4, ops) !=
+		     offsetof(struct iwl_geo_tx_power_profiles_cmd_v5, ops));
+
+	cmd.v4.ops = cpu_to_le32(IWL_PER_CHAIN_OFFSET_SET_TABLES);
+
+	/* Only set to South Korea if the table revision is 1 */
+	if (mld->fwrt.geo_rev == 1)
+		sk = cpu_to_le32(1);
+
+	if (cmd_ver == 5) {
+		len = sizeof(cmd.v5);
+		n_bands = ARRAY_SIZE(cmd.v5.table[0]);
+		cmd.v5.table_revision = sk;
+	} else if (cmd_ver == 4) {
+		len = sizeof(cmd.v4);
+		n_bands = ARRAY_SIZE(cmd.v4.table[0]);
+		cmd.v4.table_revision = sk;
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	BUILD_BUG_ON(offsetof(struct iwl_geo_tx_power_profiles_cmd_v4, table) !=
+		     offsetof(struct iwl_geo_tx_power_profiles_cmd_v5, table));
+	/* the table is at the same position for all versions, so set use v4 */
+	ret = iwl_sar_geo_fill_table(&mld->fwrt, &cmd.v4.table[0][0],
+				     n_bands, BIOS_GEO_MAX_PROFILE_NUM);
+
+	/* It is a valid scenario to not support SAR, or miss wgds table,
+	 * but in that case there is no need to send the command.
+	 */
+	if (ret)
+		return 0;
+
+	return iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd, len);
+}
+
+int iwl_mld_config_sar_profile(struct iwl_mld *mld, int prof_a, int prof_b)
+{
+	u32 cmd_id = REDUCE_TX_POWER_CMD;
+	struct iwl_dev_tx_power_cmd cmd = {
+		.common.set_mode = cpu_to_le32(IWL_TX_POWER_MODE_SET_CHAINS),
+	};
+	__le16 *per_chain;
+	int ret;
+	u16 len = sizeof(cmd.common);
+	u32 n_subbands;
+	u8 cmd_ver = iwl_fw_lookup_cmd_ver(mld->fw, cmd_id,
+					   IWL_FW_CMD_VER_UNKNOWN);
+
+	if (cmd_ver == 10) {
+		len += sizeof(cmd.v10);
+		n_subbands = IWL_NUM_SUB_BANDS_V2;
+		per_chain = &cmd.v10.per_chain[0][0][0];
+		cmd.v10.flags =
+			cpu_to_le32(mld->fwrt.reduced_power_flags);
+	} else if (cmd_ver == 9) {
+		len += sizeof(cmd.v9);
+		n_subbands = IWL_NUM_SUB_BANDS_V1;
+		per_chain = &cmd.v9.per_chain[0][0];
+	} else {
+		return -EOPNOTSUPP;
+	}
+
+	/* TODO: CDB - support IWL_NUM_CHAIN_TABLES_V2 */
+	ret = iwl_sar_fill_profile(&mld->fwrt, per_chain,
+				   IWL_NUM_CHAIN_TABLES,
+				   n_subbands, prof_a, prof_b);
+	/* return on error or if the profile is disabled (positive number) */
+	if (ret)
+		return ret;
+
+	return iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd, len);
+}
+
+int iwl_mld_init_sar(struct iwl_mld *mld)
+{
+	int chain_a_prof = 1;
+	int chain_b_prof = 1;
+	int ret;
+
+	/* If no profile was chosen by the user yet, choose profile 1 (WRDS) as
+	 * default for both chains
+	 */
+	if (mld->fwrt.sar_chain_a_profile && mld->fwrt.sar_chain_b_profile) {
+		chain_a_prof = mld->fwrt.sar_chain_a_profile;
+		chain_b_prof = mld->fwrt.sar_chain_b_profile;
+	}
+
+	ret = iwl_mld_config_sar_profile(mld, chain_a_prof, chain_b_prof);
+	if (ret < 0)
+		return ret;
+
+	if (ret)
+		return 0;
+
+	return iwl_mld_geo_sar_init(mld);
+}
+
+int iwl_mld_init_sgom(struct iwl_mld *mld)
+{
+	int ret;
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(REGULATORY_AND_NVM_GROUP,
+			      SAR_OFFSET_MAPPING_TABLE_CMD),
+		.data[0] = &mld->fwrt.sgom_table,
+		.len[0] =  sizeof(mld->fwrt.sgom_table),
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+
+	if (!mld->fwrt.sgom_enabled) {
+		IWL_DEBUG_RADIO(mld, "SGOM table is disabled\n");
+		return 0;
+	}
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret)
+		IWL_ERR(mld,
+			"failed to send SAR_OFFSET_MAPPING_CMD (%d)\n", ret);
+
+	return ret;
+}
+
+static int iwl_mld_ppag_send_cmd(struct iwl_mld *mld)
+{
+	union iwl_ppag_table_cmd cmd = {};
+	int ret, len;
+
+	ret = iwl_fill_ppag_table(&mld->fwrt, &cmd, &len);
+	/* Not supporting PPAG table is a valid scenario */
+	if (ret < 0)
+		return 0;
+
+	IWL_DEBUG_RADIO(mld, "Sending PER_PLATFORM_ANT_GAIN_CMD\n");
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(PHY_OPS_GROUP,
+						PER_PLATFORM_ANT_GAIN_CMD),
+				   &cmd, len);
+	if (ret < 0)
+		IWL_ERR(mld, "failed to send PER_PLATFORM_ANT_GAIN_CMD (%d)\n",
+			ret);
+
+	return ret;
+}
+
+int iwl_mld_init_ppag(struct iwl_mld *mld)
+{
+	/* no need to read the table, done in INIT stage */
+
+	if (!(iwl_is_ppag_approved(&mld->fwrt)))
+		return 0;
+
+	return iwl_mld_ppag_send_cmd(mld);
+}
+
+void iwl_mld_configure_lari(struct iwl_mld *mld)
+{
+	struct iwl_fw_runtime *fwrt = &mld->fwrt;
+	struct iwl_lari_config_change_cmd cmd = {
+		.config_bitmap = iwl_get_lari_config_bitmap(fwrt),
+	};
+	int ret;
+	u32 value;
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_11AX_ENABLEMENT, &value);
+	if (!ret)
+		cmd.oem_11ax_allow_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_UNII4_CHAN, &value);
+	if (!ret)
+		cmd.oem_unii4_allow_bitmap =
+			cpu_to_le32(value &= DSM_UNII4_ALLOW_BITMAP);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ACTIVATE_CHANNEL, &value);
+	if (!ret)
+		cmd.chan_state_active_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_6E, &value);
+	if (!ret)
+		cmd.oem_uhb_allow_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_FORCE_DISABLE_CHANNELS, &value);
+	if (!ret)
+		cmd.force_disable_channels_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENERGY_DETECTION_THRESHOLD,
+			       &value);
+	if (!ret)
+		cmd.edt_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_wbem(fwrt, &value);
+	if (!ret)
+		cmd.oem_320mhz_allow_bitmap = cpu_to_le32(value);
+
+	ret = iwl_bios_get_dsm(fwrt, DSM_FUNC_ENABLE_11BE, &value);
+	if (!ret)
+		cmd.oem_11be_allow_bitmap = cpu_to_le32(value);
+
+	if (!cmd.config_bitmap &&
+	    !cmd.oem_uhb_allow_bitmap &&
+	    !cmd.oem_11ax_allow_bitmap &&
+	    !cmd.oem_unii4_allow_bitmap &&
+	    !cmd.chan_state_active_bitmap &&
+	    !cmd.force_disable_channels_bitmap &&
+	    !cmd.edt_bitmap &&
+	    !cmd.oem_320mhz_allow_bitmap &&
+	    !cmd.oem_11be_allow_bitmap)
+		return;
+
+	IWL_DEBUG_RADIO(mld,
+			"sending LARI_CONFIG_CHANGE, config_bitmap=0x%x, oem_11ax_allow_bitmap=0x%x\n",
+			le32_to_cpu(cmd.config_bitmap),
+			le32_to_cpu(cmd.oem_11ax_allow_bitmap));
+	IWL_DEBUG_RADIO(mld,
+			"sending LARI_CONFIG_CHANGE, oem_unii4_allow_bitmap=0x%x, chan_state_active_bitmap=0x%x\n",
+			le32_to_cpu(cmd.oem_unii4_allow_bitmap),
+			le32_to_cpu(cmd.chan_state_active_bitmap));
+	IWL_DEBUG_RADIO(mld,
+			"sending LARI_CONFIG_CHANGE, oem_uhb_allow_bitmap=0x%x, force_disable_channels_bitmap=0x%x\n",
+			le32_to_cpu(cmd.oem_uhb_allow_bitmap),
+			le32_to_cpu(cmd.force_disable_channels_bitmap));
+	IWL_DEBUG_RADIO(mld,
+			"sending LARI_CONFIG_CHANGE, edt_bitmap=0x%x, oem_320mhz_allow_bitmap=0x%x\n",
+			le32_to_cpu(cmd.edt_bitmap),
+			le32_to_cpu(cmd.oem_320mhz_allow_bitmap));
+	IWL_DEBUG_RADIO(mld,
+			"sending LARI_CONFIG_CHANGE, oem_11be_allow_bitmap=0x%x\n",
+			le32_to_cpu(cmd.oem_11be_allow_bitmap));
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(REGULATORY_AND_NVM_GROUP,
+						LARI_CONFIG_CHANGE), &cmd);
+	if (ret)
+		IWL_DEBUG_RADIO(mld,
+				"Failed to send LARI_CONFIG_CHANGE (%d)\n",
+				ret);
+}
+
+void iwl_mld_init_uats(struct iwl_mld *mld)
+{
+	int ret;
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(REGULATORY_AND_NVM_GROUP,
+			      MCC_ALLOWED_AP_TYPE_CMD),
+		.data[0] = &mld->fwrt.uats_table,
+		.len[0] =  sizeof(mld->fwrt.uats_table),
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+
+	if (!mld->fwrt.uats_valid)
+		return;
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret)
+		IWL_ERR(mld, "failed to send MCC_ALLOWED_AP_TYPE_CMD (%d)\n",
+			ret);
+}
+
+void iwl_mld_init_tas(struct iwl_mld *mld)
+{
+	int ret;
+	struct iwl_tas_data data = {};
+	struct iwl_tas_config_cmd cmd = {};
+	u32 cmd_id = WIDE_ID(REGULATORY_AND_NVM_GROUP, TAS_CONFIG);
+
+	BUILD_BUG_ON(ARRAY_SIZE(data.block_list_array) !=
+		     IWL_WTAS_BLACK_LIST_MAX);
+	BUILD_BUG_ON(ARRAY_SIZE(cmd.block_list_array) !=
+		     IWL_WTAS_BLACK_LIST_MAX);
+
+	if (!fw_has_capa(&mld->fw->ucode_capa, IWL_UCODE_TLV_CAPA_TAS_CFG)) {
+		IWL_DEBUG_RADIO(mld, "TAS not enabled in FW\n");
+		return;
+	}
+
+	ret = iwl_bios_get_tas_table(&mld->fwrt, &data);
+	if (ret < 0) {
+		IWL_DEBUG_RADIO(mld,
+				"TAS table invalid or unavailable. (%d)\n",
+				ret);
+		return;
+	}
+
+	if (!iwl_is_tas_approved()) {
+		IWL_DEBUG_RADIO(mld,
+				"System vendor '%s' is not in the approved list, disabling TAS in US and Canada.\n",
+				dmi_get_system_info(DMI_SYS_VENDOR) ?: "<unknown>");
+		if ((!iwl_add_mcc_to_tas_block_list(data.block_list_array,
+						    &data.block_list_size,
+						    IWL_MCC_US)) ||
+		    (!iwl_add_mcc_to_tas_block_list(data.block_list_array,
+						    &data.block_list_size,
+						    IWL_MCC_CANADA))) {
+			IWL_DEBUG_RADIO(mld,
+					"Unable to add US/Canada to TAS block list, disabling TAS\n");
+			return;
+		}
+	} else {
+		IWL_DEBUG_RADIO(mld,
+				"System vendor '%s' is in the approved list.\n",
+				dmi_get_system_info(DMI_SYS_VENDOR) ?: "<unknown>");
+	}
+
+	cmd.block_list_size = cpu_to_le16(data.block_list_size);
+	for (u8 i = 0; i < data.block_list_size; i++)
+		cmd.block_list_array[i] =
+			cpu_to_le16(data.block_list_array[i]);
+	cmd.tas_config_info.table_source = data.table_source;
+	cmd.tas_config_info.table_revision = data.table_revision;
+	cmd.tas_config_info.value = cpu_to_le32(data.tas_selection);
+
+	ret = iwl_mld_send_cmd_pdu(mld, cmd_id, &cmd);
+	if (ret)
+		IWL_DEBUG_RADIO(mld, "failed to send TAS_CONFIG (%d)\n", ret);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/regulatory.h b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.h
new file mode 100644
index 0000000000000..3b01c645adda3
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/regulatory.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_regulatory_h__
+#define __iwl_mld_regulatory_h__
+
+#include "mld.h"
+
+void iwl_mld_get_bios_tables(struct iwl_mld *mld);
+void iwl_mld_configure_lari(struct iwl_mld *mld);
+void iwl_mld_init_uats(struct iwl_mld *mld);
+void iwl_mld_init_tas(struct iwl_mld *mld);
+
+int iwl_mld_init_ppag(struct iwl_mld *mld);
+
+int iwl_mld_init_sgom(struct iwl_mld *mld);
+
+int iwl_mld_init_sar(struct iwl_mld *mld);
+
+int iwl_mld_config_sar_profile(struct iwl_mld *mld, int prof_a, int prof_b);
+
+#endif /* __iwl_mld_regulatory_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.c b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
new file mode 100644
index 0000000000000..b87faca23cebe
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/roc.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 - 2025 Intel Corporation
+ */
+#include <net/cfg80211.h>
+#include <net/mac80211.h>
+
+#include "mld.h"
+#include "roc.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "sta.h"
+#include "mlo.h"
+
+#include "fw/api/context.h"
+#include "fw/api/time-event.h"
+
+#define AUX_ROC_MAX_DELAY MSEC_TO_TU(200)
+
+static void
+iwl_mld_vif_iter_emlsr_block_roc(void *data, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int *result = data;
+	int ret;
+
+	ret = iwl_mld_block_emlsr_sync(mld_vif->mld, vif,
+				       IWL_MLD_EMLSR_BLOCKED_ROC,
+				       iwl_mld_get_primary_link(vif));
+	if (ret)
+		*result = ret;
+}
+
+int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_channel *channel, int duration,
+		      enum ieee80211_roc_type type)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_int_sta *aux_sta;
+	struct iwl_roc_req cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
+	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
+				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
+	enum iwl_roc_activity activity;
+	int ret = 0;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_block_roc,
+						&ret);
+	if (ret)
+		return ret;
+
+	/* TODO: task=Hotspot 2.0 */
+	if (vif->type != NL80211_IFTYPE_P2P_DEVICE) {
+		IWL_ERR(mld, "NOT SUPPORTED: ROC on vif->type %d\n",
+			vif->type);
+
+		return -EOPNOTSUPP;
+	}
+
+	switch (type) {
+	case IEEE80211_ROC_TYPE_NORMAL:
+		activity = ROC_ACTIVITY_P2P_DISC;
+		break;
+	case IEEE80211_ROC_TYPE_MGMT_TX:
+		activity = ROC_ACTIVITY_P2P_NEG;
+		break;
+	default:
+		WARN_ONCE(1, "Got an invalid P2P ROC type\n");
+		return -EINVAL;
+	}
+
+	if (WARN_ON(mld_vif->roc_activity != ROC_NUM_ACTIVITIES))
+		return -EBUSY;
+
+	/* No MLO on P2P device */
+	aux_sta = &mld_vif->deflink.aux_sta;
+
+	ret = iwl_mld_add_aux_sta(mld, aux_sta);
+	if (ret)
+		return ret;
+
+	cmd.activity = cpu_to_le32(activity);
+	cmd.sta_id = cpu_to_le32(aux_sta->sta_id);
+	cmd.channel_info.channel = cpu_to_le32(channel->hw_value);
+	cmd.channel_info.band = iwl_mld_nl80211_band_to_fw(channel->band);
+	cmd.channel_info.width = IWL_PHY_CHANNEL_MODE20;
+	/* TODO: task=Hotspot 2.0, revisit those parameters when we add an ROC
+	 * on the BSS vif
+	 */
+	cmd.max_delay = cpu_to_le32(AUX_ROC_MAX_DELAY);
+	cmd.duration = cpu_to_le32(MSEC_TO_TU(duration));
+
+	memcpy(cmd.node_addr, vif->addr, ETH_ALEN);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
+				   &cmd, cmd_len);
+	if (ret) {
+		IWL_ERR(mld, "Couldn't send the ROC_CMD\n");
+		return ret;
+	}
+	mld_vif->roc_activity = activity;
+
+	return 0;
+}
+
+static void
+iwl_mld_vif_iter_emlsr_unblock_roc(void *data, u8 *mac,
+				   struct ieee80211_vif *vif)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	iwl_mld_unblock_emlsr(mld_vif->mld, vif, IWL_MLD_EMLSR_BLOCKED_ROC);
+}
+
+static void iwl_mld_destroy_roc(struct iwl_mld *mld,
+				struct ieee80211_vif *vif,
+				struct iwl_mld_vif *mld_vif)
+{
+	mld_vif->roc_activity = ROC_NUM_ACTIVITIES;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_vif_iter_emlsr_unblock_roc,
+						NULL);
+
+	/* wait until every tx has seen that roc_activity has been reset */
+	synchronize_net();
+	/* from here, no new tx will be added
+	 * we can flush the Tx on the queues
+	 */
+
+	iwl_mld_flush_link_sta_txqs(mld, mld_vif->deflink.aux_sta.sta_id);
+
+	iwl_mld_remove_aux_sta(mld, vif, &vif->bss_conf);
+}
+
+int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif)
+{
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_roc_req cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+	};
+	u8 ver = iwl_fw_lookup_cmd_ver(mld->fw,
+				       WIDE_ID(MAC_CONF_GROUP, ROC_CMD), 0);
+	u16 cmd_len = ver < 6 ? sizeof(struct iwl_roc_req_v5) : sizeof(cmd);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* TODO: task=Hotspot 2.0 */
+	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
+		return -EOPNOTSUPP;
+
+	/* No roc activity running it's probably already done */
+	if (mld_vif->roc_activity == ROC_NUM_ACTIVITIES)
+		return 0;
+
+	cmd.activity = cpu_to_le32(mld_vif->roc_activity);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, ROC_CMD),
+				   &cmd, cmd_len);
+	if (ret)
+		IWL_ERR(mld, "Couldn't send the command to cancel the ROC\n");
+
+	/* We may have raced with the firmware expiring the ROC instance at
+	 * this very moment. In that case, we can have a notification in the
+	 * async processing queue. However, none can arrive _after_ this as
+	 * ROC_CMD was sent synchronously, i.e. we waited for a response and
+	 * the firmware cannot refer to this ROC after the response. Thus,
+	 * if we just cancel the notification (if there's one) we'll be at a
+	 * clean state for any possible next ROC.
+	 */
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_ROC,
+					       mld_vif->roc_activity);
+
+	iwl_mld_destroy_roc(mld, vif, mld_vif);
+
+	return 0;
+}
+
+void iwl_mld_handle_roc_notif(struct iwl_mld *mld,
+			      struct iwl_rx_packet *pkt)
+{
+	const struct iwl_roc_notif *notif = (void *)pkt->data;
+	u32 activity = le32_to_cpu(notif->activity);
+	/* TODO: task=Hotspot 2.0 - roc can run on BSS */
+	struct ieee80211_vif *vif = mld->p2p_device_vif;
+	struct iwl_mld_vif *mld_vif;
+
+	if (WARN_ON(!vif))
+		return;
+
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	/* It is possible that the ROC was canceled
+	 * but the notification was already fired.
+	 */
+	if (mld_vif->roc_activity != activity)
+		return;
+
+	if (le32_to_cpu(notif->success) &&
+	    le32_to_cpu(notif->started)) {
+		/* We had a successful start */
+		ieee80211_ready_on_channel(mld->hw);
+	} else {
+		/* ROC was not successful, tell the firmware to remove it */
+		if (le32_to_cpu(notif->started))
+			iwl_mld_cancel_roc(mld->hw, vif);
+		else
+			iwl_mld_destroy_roc(mld, vif, mld_vif);
+		/* we need to let know mac80211 about end OR
+		 * an unsuccessful start
+		 */
+		ieee80211_remain_on_channel_expired(mld->hw);
+	}
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/roc.h b/drivers/net/wireless/intel/iwlwifi/mld/roc.h
new file mode 100644
index 0000000000000..985d7f20a3d7f
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/roc.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_roc_h__
+#define __iwl_mld_roc_h__
+
+#include <net/mac80211.h>
+
+int iwl_mld_start_roc(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		      struct ieee80211_channel *channel, int duration,
+		      enum ieee80211_roc_type type);
+
+int iwl_mld_cancel_roc(struct ieee80211_hw *hw,
+		       struct ieee80211_vif *vif);
+
+void iwl_mld_handle_roc_notif(struct iwl_mld *mld,
+			      struct iwl_rx_packet *pkt);
+
+#endif /* __iwl_mld_roc_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/rx.c b/drivers/net/wireless/intel/iwlwifi/mld/rx.c
new file mode 100644
index 0000000000000..c4f189bcece21
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/rx.c
@@ -0,0 +1,2060 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <net/mac80211.h>
+#include <kunit/static_stub.h>
+
+#include "mld.h"
+#include "sta.h"
+#include "agg.h"
+#include "rx.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "time_sync.h"
+#include "fw/dbg.h"
+#include "fw/api/rx.h"
+
+/* stores relevant PHY data fields extracted from iwl_rx_mpdu_desc */
+struct iwl_mld_rx_phy_data {
+	enum iwl_rx_phy_info_type info_type;
+	__le32 data0;
+	__le32 data1;
+	__le32 data2;
+	__le32 data3;
+	__le32 eht_data4;
+	__le32 data5;
+	__le16 data4;
+	bool first_subframe;
+	bool with_data;
+	__le32 rx_vec[4];
+	u32 rate_n_flags;
+	u32 gp2_on_air_rise;
+	u16 phy_info;
+	u8 energy_a, energy_b;
+	u8 channel;
+};
+
+static void
+iwl_mld_fill_phy_data(struct iwl_rx_mpdu_desc *desc,
+		      struct iwl_mld_rx_phy_data *phy_data)
+{
+	phy_data->phy_info = le16_to_cpu(desc->phy_info);
+	phy_data->rate_n_flags = le32_to_cpu(desc->v3.rate_n_flags);
+	phy_data->gp2_on_air_rise = le32_to_cpu(desc->v3.gp2_on_air_rise);
+	phy_data->channel = desc->v3.channel;
+	phy_data->energy_a = desc->v3.energy_a;
+	phy_data->energy_b = desc->v3.energy_b;
+	phy_data->data0 = desc->v3.phy_data0;
+	phy_data->data1 = desc->v3.phy_data1;
+	phy_data->data2 = desc->v3.phy_data2;
+	phy_data->data3 = desc->v3.phy_data3;
+	phy_data->data4 = desc->phy_data4;
+	phy_data->eht_data4 = desc->phy_eht_data4;
+	phy_data->data5 = desc->v3.phy_data5;
+	phy_data->with_data = true;
+}
+
+static inline int iwl_mld_check_pn(struct iwl_mld *mld, struct sk_buff *skb,
+				   int queue, struct ieee80211_sta *sta)
+{
+	struct ieee80211_hdr *hdr = (void *)skb_mac_header(skb);
+	struct ieee80211_rx_status *stats = IEEE80211_SKB_RXCB(skb);
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_ptk_pn *ptk_pn;
+	int res;
+	u8 tid, keyidx;
+	u8 pn[IEEE80211_CCMP_PN_LEN];
+	u8 *extiv;
+
+	/* multicast and non-data only arrives on default queue; avoid checking
+	 * for default queue - we don't want to replicate all the logic that's
+	 * necessary for checking the PN on fragmented frames, leave that
+	 * to mac80211
+	 */
+	if (queue == 0 || !ieee80211_is_data(hdr->frame_control) ||
+	    is_multicast_ether_addr(hdr->addr1))
+		return 0;
+
+	if (!(stats->flag & RX_FLAG_DECRYPTED))
+		return 0;
+
+	/* if we are here - this for sure is either CCMP or GCMP */
+	if (!sta) {
+		IWL_DEBUG_DROP(mld,
+			       "expected hw-decrypted unicast frame for station\n");
+		return -1;
+	}
+
+	mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	extiv = (u8 *)hdr + ieee80211_hdrlen(hdr->frame_control);
+	keyidx = extiv[3] >> 6;
+
+	ptk_pn = rcu_dereference(mld_sta->ptk_pn[keyidx]);
+	if (!ptk_pn)
+		return -1;
+
+	if (ieee80211_is_data_qos(hdr->frame_control))
+		tid = ieee80211_get_tid(hdr);
+	else
+		tid = 0;
+
+	/* we don't use HCCA/802.11 QoS TSPECs, so drop such frames */
+	if (tid >= IWL_MAX_TID_COUNT)
+		return -1;
+
+	/* load pn */
+	pn[0] = extiv[7];
+	pn[1] = extiv[6];
+	pn[2] = extiv[5];
+	pn[3] = extiv[4];
+	pn[4] = extiv[1];
+	pn[5] = extiv[0];
+
+	res = memcmp(pn, ptk_pn->q[queue].pn[tid], IEEE80211_CCMP_PN_LEN);
+	if (res < 0)
+		return -1;
+	if (!res && !(stats->flag & RX_FLAG_ALLOW_SAME_PN))
+		return -1;
+
+	memcpy(ptk_pn->q[queue].pn[tid], pn, IEEE80211_CCMP_PN_LEN);
+	stats->flag |= RX_FLAG_PN_VALIDATED;
+
+	return 0;
+}
+
+/* iwl_mld_pass_packet_to_mac80211 - passes the packet for mac80211 */
+void iwl_mld_pass_packet_to_mac80211(struct iwl_mld *mld,
+				     struct napi_struct *napi,
+				     struct sk_buff *skb, int queue,
+				     struct ieee80211_sta *sta)
+{
+	KUNIT_STATIC_STUB_REDIRECT(iwl_mld_pass_packet_to_mac80211,
+				   mld, napi, skb, queue, sta);
+
+	if (unlikely(iwl_mld_check_pn(mld, skb, queue, sta))) {
+		kfree_skb(skb);
+		return;
+	}
+
+	ieee80211_rx_napi(mld->hw, sta, skb, napi);
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_pass_packet_to_mac80211);
+
+static void iwl_mld_fill_signal(struct iwl_mld *mld,
+				struct ieee80211_rx_status *rx_status,
+				struct iwl_mld_rx_phy_data *phy_data)
+{
+	u32 rate_n_flags = phy_data->rate_n_flags;
+	int energy_a = phy_data->energy_a;
+	int energy_b = phy_data->energy_b;
+	int max_energy;
+
+	energy_a = energy_a ? -energy_a : S8_MIN;
+	energy_b = energy_b ? -energy_b : S8_MIN;
+	max_energy = max(energy_a, energy_b);
+
+	IWL_DEBUG_STATS(mld, "energy in A %d B %d, and max %d\n",
+			energy_a, energy_b, max_energy);
+
+	rx_status->signal = max_energy;
+	rx_status->chains =
+	    (rate_n_flags & RATE_MCS_ANT_AB_MSK) >> RATE_MCS_ANT_POS;
+	rx_status->chain_signal[0] = energy_a;
+	rx_status->chain_signal[1] = energy_b;
+}
+
+static void
+iwl_mld_decode_he_phy_ru_alloc(struct iwl_mld_rx_phy_data *phy_data,
+			       struct ieee80211_radiotap_he *he,
+			       struct ieee80211_radiotap_he_mu *he_mu,
+			       struct ieee80211_rx_status *rx_status)
+{
+	/* Unfortunately, we have to leave the mac80211 data
+	 * incorrect for the case that we receive an HE-MU
+	 * transmission and *don't* have the HE phy data (due
+	 * to the bits being used for TSF). This shouldn't
+	 * happen though as management frames where we need
+	 * the TSF/timers are not be transmitted in HE-MU.
+	 */
+	u8 ru = le32_get_bits(phy_data->data1, IWL_RX_PHY_DATA1_HE_RU_ALLOC_MASK);
+	u32 rate_n_flags = phy_data->rate_n_flags;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+	u8 offs = 0;
+
+	rx_status->bw = RATE_INFO_BW_HE_RU;
+
+	he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN);
+
+	switch (ru) {
+	case 0 ... 36:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_26;
+		offs = ru;
+		break;
+	case 37 ... 52:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_52;
+		offs = ru - 37;
+		break;
+	case 53 ... 60:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+		offs = ru - 53;
+		break;
+	case 61 ... 64:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_242;
+		offs = ru - 61;
+		break;
+	case 65 ... 66:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_484;
+		offs = ru - 65;
+		break;
+	case 67:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_996;
+		break;
+	case 68:
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_2x996;
+		break;
+	}
+	he->data2 |= le16_encode_bits(offs,
+				      IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET);
+	he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_KNOWN |
+				 IEEE80211_RADIOTAP_HE_DATA2_RU_OFFSET_KNOWN);
+	if (phy_data->data1 & cpu_to_le32(IWL_RX_PHY_DATA1_HE_RU_ALLOC_SEC80))
+		he->data2 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRISEC_80_SEC);
+
+#define CHECK_BW(bw) \
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_ ## bw ## MHZ != \
+		     RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS); \
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_ ## bw ## MHZ != \
+		     RATE_MCS_CHAN_WIDTH_##bw >> RATE_MCS_CHAN_WIDTH_POS)
+	CHECK_BW(20);
+	CHECK_BW(40);
+	CHECK_BW(80);
+	CHECK_BW(160);
+
+	if (he_mu)
+		he_mu->flags2 |=
+			le16_encode_bits(u32_get_bits(rate_n_flags,
+						      RATE_MCS_CHAN_WIDTH_MSK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW);
+	else if (he_type == RATE_MCS_HE_TYPE_TRIG)
+		he->data6 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW_KNOWN) |
+			le16_encode_bits(u32_get_bits(rate_n_flags,
+						      RATE_MCS_CHAN_WIDTH_MSK),
+					 IEEE80211_RADIOTAP_HE_DATA6_TB_PPDU_BW);
+}
+
+static void
+iwl_mld_decode_he_mu_ext(struct iwl_mld_rx_phy_data *phy_data,
+			 struct ieee80211_radiotap_he_mu *he_mu)
+{
+	u32 phy_data2 = le32_to_cpu(phy_data->data2);
+	u32 phy_data3 = le32_to_cpu(phy_data->data3);
+	u16 phy_data4 = le16_to_cpu(phy_data->data4);
+	u32 rate_n_flags = phy_data->rate_n_flags;
+
+	if (u32_get_bits(phy_data4, IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CRC_OK)) {
+		he_mu->flags1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_RU_KNOWN |
+				    IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU_KNOWN);
+
+		he_mu->flags1 |=
+			le16_encode_bits(u32_get_bits(phy_data4,
+						      IWL_RX_PHY_DATA4_HE_MU_EXT_CH1_CTR_RU),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH1_CTR_26T_RU);
+
+		he_mu->ru_ch1[0] = u32_get_bits(phy_data2,
+						IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU0);
+		he_mu->ru_ch1[1] = u32_get_bits(phy_data3,
+						IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU1);
+		he_mu->ru_ch1[2] = u32_get_bits(phy_data2,
+						IWL_RX_PHY_DATA2_HE_MU_EXT_CH1_RU2);
+		he_mu->ru_ch1[3] = u32_get_bits(phy_data3,
+						IWL_RX_PHY_DATA3_HE_MU_EXT_CH1_RU3);
+	}
+
+	if (u32_get_bits(phy_data4, IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CRC_OK) &&
+	    (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) != RATE_MCS_CHAN_WIDTH_20) {
+		he_mu->flags1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_RU_KNOWN |
+				    IEEE80211_RADIOTAP_HE_MU_FLAGS1_CH2_CTR_26T_RU_KNOWN);
+
+		he_mu->flags2 |=
+			le16_encode_bits(u32_get_bits(phy_data4,
+						      IWL_RX_PHY_DATA4_HE_MU_EXT_CH2_CTR_RU),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_CH2_CTR_26T_RU);
+
+		he_mu->ru_ch2[0] = u32_get_bits(phy_data2,
+						IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU0);
+		he_mu->ru_ch2[1] = u32_get_bits(phy_data3,
+						IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU1);
+		he_mu->ru_ch2[2] = u32_get_bits(phy_data2,
+						IWL_RX_PHY_DATA2_HE_MU_EXT_CH2_RU2);
+		he_mu->ru_ch2[3] = u32_get_bits(phy_data3,
+						IWL_RX_PHY_DATA3_HE_MU_EXT_CH2_RU3);
+	}
+}
+
+static void
+iwl_mld_decode_he_phy_data(struct iwl_mld_rx_phy_data *phy_data,
+			   struct ieee80211_radiotap_he *he,
+			   struct ieee80211_radiotap_he_mu *he_mu,
+			   struct ieee80211_rx_status *rx_status,
+			   int queue)
+{
+	switch (phy_data->info_type) {
+	case IWL_RX_PHY_INFO_TYPE_NONE:
+	case IWL_RX_PHY_INFO_TYPE_CCK:
+	case IWL_RX_PHY_INFO_TYPE_OFDM_LGCY:
+	case IWL_RX_PHY_INFO_TYPE_HT:
+	case IWL_RX_PHY_INFO_TYPE_VHT_SU:
+	case IWL_RX_PHY_INFO_TYPE_VHT_MU:
+	case IWL_RX_PHY_INFO_TYPE_EHT_MU:
+	case IWL_RX_PHY_INFO_TYPE_EHT_TB:
+	case IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT:
+		return;
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE2_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE3_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE4_KNOWN);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE1),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE1);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE2),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE2);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE3),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE3);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data2,
+							    IWL_RX_PHY_DATA2_HE_TB_EXT_SPTL_REUSE4),
+					      IEEE80211_RADIOTAP_HE_DATA4_TB_SPTL_REUSE4);
+		fallthrough;
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+		/* HE common */
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_LDPC_XSYMSEG_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_DOPPLER_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA1_BSS_COLOR_KNOWN);
+		he->data2 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_PRE_FEC_PAD_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_PE_DISAMBIG_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_TXOP_KNOWN |
+					 IEEE80211_RADIOTAP_HE_DATA2_NUM_LTF_SYMS_KNOWN);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_BSS_COLOR_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA3_BSS_COLOR);
+		if (phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB &&
+		    phy_data->info_type != IWL_RX_PHY_INFO_TYPE_HE_TB_EXT) {
+			he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_UL_DL_KNOWN);
+			he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_UPLINK),
+						      IEEE80211_RADIOTAP_HE_DATA3_UL_DL);
+		}
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_LDPC_EXT_SYM),
+					      IEEE80211_RADIOTAP_HE_DATA3_LDPC_XSYMSEG);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_PRE_FEC_PAD_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA5_PRE_FEC_PAD);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_PE_DISAMBIG),
+					      IEEE80211_RADIOTAP_HE_DATA5_PE_DISAMBIG);
+		he->data5 |= le16_encode_bits(le32_get_bits(phy_data->data1,
+							    IWL_RX_PHY_DATA1_HE_LTF_NUM_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA5_NUM_LTF_SYMS);
+		he->data6 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_TXOP_DUR_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA6_TXOP);
+		he->data6 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_DOPPLER),
+					      IEEE80211_RADIOTAP_HE_DATA6_DOPPLER);
+		break;
+	}
+
+	switch (phy_data->info_type) {
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_SPTL_REUSE_KNOWN);
+		he->data4 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_SPATIAL_REUSE_MASK),
+					      IEEE80211_RADIOTAP_HE_DATA4_SU_MU_SPTL_REUSE);
+		break;
+	default:
+		/* nothing here */
+		break;
+	}
+
+	switch (phy_data->info_type) {
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+		he_mu->flags1 |=
+			le16_encode_bits(le16_get_bits(phy_data->data4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_DCM),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM);
+		he_mu->flags1 |=
+			le16_encode_bits(le16_get_bits(phy_data->data4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_SIGB_MCS_MASK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS);
+		he_mu->flags2 |=
+			le16_encode_bits(le16_get_bits(phy_data->data4,
+						       IWL_RX_PHY_DATA4_HE_MU_EXT_PREAMBLE_PUNC_TYPE_MASK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW);
+		iwl_mld_decode_he_mu_ext(phy_data, he_mu);
+		fallthrough;
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+		he_mu->flags2 |=
+			le16_encode_bits(le32_get_bits(phy_data->data1,
+						       IWL_RX_PHY_DATA1_HE_MU_SIBG_SYM_OR_USER_NUM_MASK),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_SYMS_USERS);
+		he_mu->flags2 |=
+			le16_encode_bits(le32_get_bits(phy_data->data1,
+						       IWL_RX_PHY_DATA1_HE_MU_SIGB_COMPRESSION),
+					 IEEE80211_RADIOTAP_HE_MU_FLAGS2_SIG_B_COMP);
+		fallthrough;
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+		iwl_mld_decode_he_phy_ru_alloc(phy_data, he, he_mu, rx_status);
+		break;
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+		he->data1 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BEAM_CHANGE_KNOWN);
+		he->data3 |= le16_encode_bits(le32_get_bits(phy_data->data0,
+							    IWL_RX_PHY_DATA0_HE_BEAM_CHNG),
+					      IEEE80211_RADIOTAP_HE_DATA3_BEAM_CHANGE);
+		break;
+	default:
+		/* nothing */
+		break;
+	}
+}
+
+static void iwl_mld_rx_he(struct iwl_mld *mld, struct sk_buff *skb,
+			  struct iwl_mld_rx_phy_data *phy_data,
+			  int queue)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_radiotap_he *he = NULL;
+	struct ieee80211_radiotap_he_mu *he_mu = NULL;
+	u32 rate_n_flags = phy_data->rate_n_flags;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+	u8 ltf;
+	static const struct ieee80211_radiotap_he known = {
+		.data1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_DATA_MCS_KNOWN |
+				     IEEE80211_RADIOTAP_HE_DATA1_DATA_DCM_KNOWN |
+				     IEEE80211_RADIOTAP_HE_DATA1_STBC_KNOWN	|
+				     IEEE80211_RADIOTAP_HE_DATA1_CODING_KNOWN),
+		.data2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA2_GI_KNOWN |
+				     IEEE80211_RADIOTAP_HE_DATA2_TXBF_KNOWN),
+	};
+	static const struct ieee80211_radiotap_he_mu mu_known = {
+		.flags1 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_MCS_KNOWN |
+				      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_DCM_KNOWN |
+				      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_SYMS_USERS_KNOWN |
+				      IEEE80211_RADIOTAP_HE_MU_FLAGS1_SIG_B_COMP_KNOWN),
+		.flags2 = cpu_to_le16(IEEE80211_RADIOTAP_HE_MU_FLAGS2_PUNC_FROM_SIG_A_BW_KNOWN |
+				      IEEE80211_RADIOTAP_HE_MU_FLAGS2_BW_FROM_SIG_A_BW_KNOWN),
+	};
+	u16 phy_info = phy_data->phy_info;
+
+	he = skb_put_data(skb, &known, sizeof(known));
+	rx_status->flag |= RX_FLAG_RADIOTAP_HE;
+
+	if (phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU ||
+	    phy_data->info_type == IWL_RX_PHY_INFO_TYPE_HE_MU_EXT) {
+		he_mu = skb_put_data(skb, &mu_known, sizeof(mu_known));
+		rx_status->flag |= RX_FLAG_RADIOTAP_HE_MU;
+	}
+
+	/* report the AMPDU-EOF bit on single frames */
+	if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
+		rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
+		rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+		if (phy_data->data0 & cpu_to_le32(IWL_RX_PHY_DATA0_HE_DELIM_EOF))
+			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
+	}
+
+	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		iwl_mld_decode_he_phy_data(phy_data, he, he_mu, rx_status,
+					   queue);
+
+	/* update aggregation data for monitor sake on default queue */
+	if (!queue && (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD) &&
+	    (phy_info & IWL_RX_MPDU_PHY_AMPDU) && phy_data->first_subframe) {
+		rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+		if (phy_data->data0 & cpu_to_le32(IWL_RX_PHY_DATA0_EHT_DELIM_EOF))
+			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
+	}
+
+	if (he_type == RATE_MCS_HE_TYPE_EXT_SU &&
+	    rate_n_flags & RATE_MCS_HE_106T_MSK) {
+		rx_status->bw = RATE_INFO_BW_HE_RU;
+		rx_status->he_ru = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+	}
+
+	/* actually data is filled in mac80211 */
+	if (he_type == RATE_MCS_HE_TYPE_SU ||
+	    he_type == RATE_MCS_HE_TYPE_EXT_SU)
+		he->data1 |=
+			cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA1_BW_RU_ALLOC_KNOWN);
+
+#define CHECK_TYPE(F)							\
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F !=	\
+		     (RATE_MCS_HE_TYPE_ ## F >> RATE_MCS_HE_TYPE_POS))
+
+	CHECK_TYPE(SU);
+	CHECK_TYPE(EXT_SU);
+	CHECK_TYPE(MU);
+	CHECK_TYPE(TRIG);
+
+	he->data1 |= cpu_to_le16(he_type >> RATE_MCS_HE_TYPE_POS);
+
+	if (rate_n_flags & RATE_MCS_BF_MSK)
+		he->data5 |= cpu_to_le16(IEEE80211_RADIOTAP_HE_DATA5_TXBF);
+
+	switch ((rate_n_flags & RATE_MCS_HE_GI_LTF_MSK) >>
+		RATE_MCS_HE_GI_LTF_POS) {
+	case 0:
+		if (he_type == RATE_MCS_HE_TYPE_TRIG)
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+		else
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+		if (he_type == RATE_MCS_HE_TYPE_MU)
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+		else
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X;
+		break;
+	case 1:
+		if (he_type == RATE_MCS_HE_TYPE_TRIG)
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+		else
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X;
+		break;
+	case 2:
+		if (he_type == RATE_MCS_HE_TYPE_TRIG) {
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+		} else {
+			rx_status->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X;
+		}
+		break;
+	case 3:
+		rx_status->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+		break;
+	case 4:
+		rx_status->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+		break;
+	default:
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN;
+	}
+
+	he->data5 |= le16_encode_bits(ltf,
+				      IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE);
+}
+
+static void iwl_mld_decode_lsig(struct sk_buff *skb,
+				struct iwl_mld_rx_phy_data *phy_data)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_radiotap_lsig *lsig;
+
+	switch (phy_data->info_type) {
+	case IWL_RX_PHY_INFO_TYPE_HT:
+	case IWL_RX_PHY_INFO_TYPE_VHT_SU:
+	case IWL_RX_PHY_INFO_TYPE_VHT_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_SU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU:
+	case IWL_RX_PHY_INFO_TYPE_HE_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_HE_TB:
+	case IWL_RX_PHY_INFO_TYPE_EHT_MU:
+	case IWL_RX_PHY_INFO_TYPE_EHT_TB:
+	case IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT:
+	case IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT:
+		lsig = skb_put(skb, sizeof(*lsig));
+		lsig->data1 = cpu_to_le16(IEEE80211_RADIOTAP_LSIG_DATA1_LENGTH_KNOWN);
+		lsig->data2 = le16_encode_bits(le32_get_bits(phy_data->data1,
+							     IWL_RX_PHY_DATA1_LSIG_LEN_MASK),
+					       IEEE80211_RADIOTAP_LSIG_DATA2_LENGTH);
+		rx_status->flag |= RX_FLAG_RADIOTAP_LSIG;
+		break;
+	default:
+		break;
+	}
+}
+
+/* Put a TLV on the skb and return data pointer
+ *
+ * Also pad the len to 4 and zero out all data part
+ */
+static void *
+iwl_mld_radiotap_put_tlv(struct sk_buff *skb, u16 type, u16 len)
+{
+	struct ieee80211_radiotap_tlv *tlv;
+
+	tlv = skb_put(skb, sizeof(*tlv));
+	tlv->type = cpu_to_le16(type);
+	tlv->len = cpu_to_le16(len);
+	return skb_put_zero(skb, ALIGN(len, 4));
+}
+
+#define LE32_DEC_ENC(value, dec_bits, enc_bits) \
+	le32_encode_bits(le32_get_bits(value, dec_bits), enc_bits)
+
+#define IWL_MLD_ENC_USIG_VALUE_MASK(usig, in_value, dec_bits, enc_bits) do { \
+	typeof(enc_bits) _enc_bits = enc_bits; \
+	typeof(usig) _usig = usig; \
+	(_usig)->mask |= cpu_to_le32(_enc_bits); \
+	(_usig)->value |= LE32_DEC_ENC(in_value, dec_bits, _enc_bits); \
+} while (0)
+
+#define __IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru) \
+	eht->data[(rt_data)] |= \
+		(cpu_to_le32 \
+		 (IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru ## _KNOWN) | \
+		 LE32_DEC_ENC(data ## fw_data, \
+			      IWL_RX_PHY_DATA ## fw_data ## _EHT_MU_EXT_RU_ALLOC_ ## fw_ru, \
+			      IEEE80211_RADIOTAP_EHT_DATA ## rt_data ## _RU_ALLOC_CC_ ## rt_ru))
+
+#define _IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru)	\
+	__IWL_MLD_ENC_EHT_RU(rt_data, rt_ru, fw_data, fw_ru)
+
+#define IEEE80211_RADIOTAP_RU_DATA_1_1_1	1
+#define IEEE80211_RADIOTAP_RU_DATA_2_1_1	2
+#define IEEE80211_RADIOTAP_RU_DATA_1_1_2	2
+#define IEEE80211_RADIOTAP_RU_DATA_2_1_2	2
+#define IEEE80211_RADIOTAP_RU_DATA_1_2_1	3
+#define IEEE80211_RADIOTAP_RU_DATA_2_2_1	3
+#define IEEE80211_RADIOTAP_RU_DATA_1_2_2	3
+#define IEEE80211_RADIOTAP_RU_DATA_2_2_2	4
+
+#define IWL_RX_RU_DATA_A1			2
+#define IWL_RX_RU_DATA_A2			2
+#define IWL_RX_RU_DATA_B1			2
+#define IWL_RX_RU_DATA_B2			4
+#define IWL_RX_RU_DATA_C1			3
+#define IWL_RX_RU_DATA_C2			3
+#define IWL_RX_RU_DATA_D1			4
+#define IWL_RX_RU_DATA_D2			4
+
+#define IWL_MLD_ENC_EHT_RU(rt_ru, fw_ru)				\
+	_IWL_MLD_ENC_EHT_RU(IEEE80211_RADIOTAP_RU_DATA_ ## rt_ru,	\
+			    rt_ru,					\
+			    IWL_RX_RU_DATA_ ## fw_ru,			\
+			    fw_ru)
+
+static void iwl_mld_decode_eht_ext_mu(struct iwl_mld *mld,
+				      struct iwl_mld_rx_phy_data *phy_data,
+				      struct ieee80211_rx_status *rx_status,
+				      struct ieee80211_radiotap_eht *eht,
+				      struct ieee80211_radiotap_eht_usig *usig)
+{
+	if (phy_data->with_data) {
+		__le32 data1 = phy_data->data1;
+		__le32 data2 = phy_data->data2;
+		__le32 data3 = phy_data->data3;
+		__le32 data4 = phy_data->eht_data4;
+		__le32 data5 = phy_data->data5;
+		u32 phy_bw = phy_data->rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK;
+
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5,
+					    IWL_RX_PHY_DATA5_EHT_TYPE_AND_COMP,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5,
+					    IWL_RX_PHY_DATA5_EHT_MU_PUNC_CH_CODE,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data4,
+					    IWL_RX_PHY_DATA4_EHT_MU_EXT_SIGB_MCS,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS);
+		IWL_MLD_ENC_USIG_VALUE_MASK
+			(usig, data1, IWL_RX_PHY_DATA1_EHT_MU_NUM_SIG_SYM_USIGA2,
+			 IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS);
+
+		eht->user_info[0] |=
+			cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID_KNOWN) |
+			LE32_DEC_ENC(data5, IWL_RX_PHY_DATA5_EHT_MU_STA_ID_USR,
+				     IEEE80211_RADIOTAP_EHT_USER_INFO_STA_ID);
+
+		eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_NR_NON_OFDMA_USERS_M);
+		eht->data[7] |= LE32_DEC_ENC
+			(data5, IWL_RX_PHY_DATA5_EHT_MU_NUM_USR_NON_OFDMA,
+			 IEEE80211_RADIOTAP_EHT_DATA7_NUM_OF_NON_OFDMA_USERS);
+
+		/*
+		 * Hardware labels the content channels/RU allocation values
+		 * as follows:
+		 *           Content Channel 1		Content Channel 2
+		 *   20 MHz: A1
+		 *   40 MHz: A1				B1
+		 *   80 MHz: A1 C1			B1 D1
+		 *  160 MHz: A1 C1 A2 C2		B1 D1 B2 D2
+		 *  320 MHz: A1 C1 A2 C2 A3 C3 A4 C4	B1 D1 B2 D2 B3 D3 B4 D4
+		 *
+		 * However firmware can only give us A1-D2, so the higher
+		 * frequencies are missing.
+		 */
+
+		switch (phy_bw) {
+		case RATE_MCS_CHAN_WIDTH_320:
+			/* additional values are missing in RX metadata */
+			fallthrough;
+		case RATE_MCS_CHAN_WIDTH_160:
+			/* content channel 1 */
+			IWL_MLD_ENC_EHT_RU(1_2_1, A2);
+			IWL_MLD_ENC_EHT_RU(1_2_2, C2);
+			/* content channel 2 */
+			IWL_MLD_ENC_EHT_RU(2_2_1, B2);
+			IWL_MLD_ENC_EHT_RU(2_2_2, D2);
+			fallthrough;
+		case RATE_MCS_CHAN_WIDTH_80:
+			/* content channel 1 */
+			IWL_MLD_ENC_EHT_RU(1_1_2, C1);
+			/* content channel 2 */
+			IWL_MLD_ENC_EHT_RU(2_1_2, D1);
+			fallthrough;
+		case RATE_MCS_CHAN_WIDTH_40:
+			/* content channel 2 */
+			IWL_MLD_ENC_EHT_RU(2_1_1, B1);
+			fallthrough;
+		case RATE_MCS_CHAN_WIDTH_20:
+			IWL_MLD_ENC_EHT_RU(1_1_1, A1);
+			break;
+		}
+	} else {
+		__le32 usig_a1 = phy_data->rx_vec[0];
+		__le32 usig_a2 = phy_data->rx_vec[1];
+
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1,
+					    IWL_RX_USIG_A1_DISREGARD,
+					    IEEE80211_RADIOTAP_EHT_USIG1_MU_B20_B24_DISREGARD);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1,
+					    IWL_RX_USIG_A1_VALIDATE,
+					    IEEE80211_RADIOTAP_EHT_USIG1_MU_B25_VALIDATE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_PPDU_TYPE,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B0_B1_PPDU_TYPE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B2,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B2_VALIDATE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_PUNC_CHANNEL,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B3_B7_PUNCTURED_INFO);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B8,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B8_VALIDATE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_SIG_MCS,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B9_B10_SIG_MCS);
+		IWL_MLD_ENC_USIG_VALUE_MASK
+			(usig, usig_a2, IWL_RX_USIG_A2_EHT_SIG_SYM_NUM,
+			 IEEE80211_RADIOTAP_EHT_USIG2_MU_B11_B15_EHT_SIG_SYMBOLS);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_CRC_OK,
+					    IEEE80211_RADIOTAP_EHT_USIG2_MU_B16_B19_CRC);
+	}
+}
+
+static void iwl_mld_decode_eht_ext_tb(struct iwl_mld *mld,
+				      struct iwl_mld_rx_phy_data *phy_data,
+				      struct ieee80211_rx_status *rx_status,
+				      struct ieee80211_radiotap_eht *eht,
+				      struct ieee80211_radiotap_eht_usig *usig)
+{
+	if (phy_data->with_data) {
+		__le32 data5 = phy_data->data5;
+
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5,
+					    IWL_RX_PHY_DATA5_EHT_TYPE_AND_COMP,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5,
+					    IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE1,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1);
+
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, data5,
+					    IWL_RX_PHY_DATA5_EHT_TB_SPATIAL_REUSE2,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2);
+	} else {
+		__le32 usig_a1 = phy_data->rx_vec[0];
+		__le32 usig_a2 = phy_data->rx_vec[1];
+
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a1,
+					    IWL_RX_USIG_A1_DISREGARD,
+					    IEEE80211_RADIOTAP_EHT_USIG1_TB_B20_B25_DISREGARD);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_PPDU_TYPE,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B0_B1_PPDU_TYPE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_USIG2_VALIDATE_B2,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B2_VALIDATE);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_TRIG_SPATIAL_REUSE_1,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B3_B6_SPATIAL_REUSE_1);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_TRIG_SPATIAL_REUSE_2,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B7_B10_SPATIAL_REUSE_2);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_TRIG_USIG2_DISREGARD,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B11_B15_DISREGARD);
+		IWL_MLD_ENC_USIG_VALUE_MASK(usig, usig_a2,
+					    IWL_RX_USIG_A2_EHT_CRC_OK,
+					    IEEE80211_RADIOTAP_EHT_USIG2_TB_B16_B19_CRC);
+	}
+}
+
+static void iwl_mld_decode_eht_ru(struct iwl_mld *mld,
+				  struct ieee80211_rx_status *rx_status,
+				  struct ieee80211_radiotap_eht *eht)
+{
+	u32 ru = le32_get_bits(eht->data[8],
+			       IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B7_B1);
+	enum nl80211_eht_ru_alloc nl_ru;
+
+	/* Using D1.5 Table 9-53a - Encoding of PS160 and RU Allocation subfields
+	 * in an EHT variant User Info field
+	 */
+
+	switch (ru) {
+	case 0 ... 36:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_26;
+		break;
+	case 37 ... 52:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_52;
+		break;
+	case 53 ... 60:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_106;
+		break;
+	case 61 ... 64:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_242;
+		break;
+	case 65 ... 66:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_484;
+		break;
+	case 67:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_996;
+		break;
+	case 68:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_2x996;
+		break;
+	case 69:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_4x996;
+		break;
+	case 70 ... 81:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_52P26;
+		break;
+	case 82 ... 89:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_106P26;
+		break;
+	case 90 ... 93:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_484P242;
+		break;
+	case 94 ... 95:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_996P484;
+		break;
+	case 96 ... 99:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_996P484P242;
+		break;
+	case 100 ... 103:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_2x996P484;
+		break;
+	case 104:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_3x996;
+		break;
+	case 105 ... 106:
+		nl_ru = NL80211_RATE_INFO_EHT_RU_ALLOC_3x996P484;
+		break;
+	default:
+		return;
+	}
+
+	rx_status->bw = RATE_INFO_BW_EHT_RU;
+	rx_status->eht.ru = nl_ru;
+}
+
+static void iwl_mld_decode_eht_phy_data(struct iwl_mld *mld,
+					struct iwl_mld_rx_phy_data *phy_data,
+					struct ieee80211_rx_status *rx_status,
+					struct ieee80211_radiotap_eht *eht,
+					struct ieee80211_radiotap_eht_usig *usig)
+
+{
+	__le32 data0 = phy_data->data0;
+	__le32 data1 = phy_data->data1;
+	__le32 usig_a1 = phy_data->rx_vec[0];
+	u8 info_type = phy_data->info_type;
+
+	/* Not in EHT range */
+	if (info_type < IWL_RX_PHY_INFO_TYPE_EHT_MU ||
+	    info_type > IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT)
+		return;
+
+	usig->common |= cpu_to_le32
+		(IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL_KNOWN |
+		 IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR_KNOWN);
+	if (phy_data->with_data) {
+		usig->common |= LE32_DEC_ENC(data0,
+					     IWL_RX_PHY_DATA0_EHT_UPLINK,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL);
+		usig->common |= LE32_DEC_ENC(data0,
+					     IWL_RX_PHY_DATA0_EHT_BSS_COLOR_MASK,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR);
+	} else {
+		usig->common |= LE32_DEC_ENC(usig_a1,
+					     IWL_RX_USIG_A1_UL_FLAG,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_UL_DL);
+		usig->common |= LE32_DEC_ENC(usig_a1,
+					     IWL_RX_USIG_A1_BSS_COLOR,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_BSS_COLOR);
+	}
+
+	usig->common |=
+		cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_CHECKED);
+	usig->common |=
+		LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_VALIDATE,
+			     IEEE80211_RADIOTAP_EHT_USIG_COMMON_VALIDATE_BITS_OK);
+
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_SPATIAL_REUSE);
+	eht->data[0] |= LE32_DEC_ENC(data0,
+				     IWL_RX_PHY_DATA0_ETH_SPATIAL_REUSE_MASK,
+				     IEEE80211_RADIOTAP_EHT_DATA0_SPATIAL_REUSE);
+
+	/* All RU allocating size/index is in TB format */
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_RU_ALLOC_TB_FMT);
+	eht->data[8] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PS160,
+				     IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_PS_160);
+	eht->data[8] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_RU_ALLOC_B0,
+				     IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B0);
+	eht->data[8] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_RU_ALLOC_B1_B7,
+				     IEEE80211_RADIOTAP_EHT_DATA8_RU_ALLOC_TB_FMT_B7_B1);
+
+	iwl_mld_decode_eht_ru(mld, rx_status, eht);
+
+	/* We only get here in case of IWL_RX_MPDU_PHY_TSF_OVERLOAD is set
+	 * which is on only in case of monitor mode so no need to check monitor
+	 * mode
+	 */
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PRIMARY_80);
+	eht->data[1] |=
+		le32_encode_bits(mld->monitor.p80,
+				 IEEE80211_RADIOTAP_EHT_DATA1_PRIMARY_80);
+
+	usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP_KNOWN);
+	if (phy_data->with_data)
+		usig->common |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_TXOP_DUR_MASK,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP);
+	else
+		usig->common |= LE32_DEC_ENC(usig_a1, IWL_RX_USIG_A1_TXOP_DURATION,
+					     IEEE80211_RADIOTAP_EHT_USIG_COMMON_TXOP);
+
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_LDPC_EXTRA_SYM_OM);
+	eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_LDPC_EXT_SYM,
+				     IEEE80211_RADIOTAP_EHT_DATA0_LDPC_EXTRA_SYM_OM);
+
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PRE_PADD_FACOR_OM);
+	eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PRE_FEC_PAD_MASK,
+				    IEEE80211_RADIOTAP_EHT_DATA0_PRE_PADD_FACOR_OM);
+
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_PE_DISAMBIGUITY_OM);
+	eht->data[0] |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PE_DISAMBIG,
+				     IEEE80211_RADIOTAP_EHT_DATA0_PE_DISAMBIGUITY_OM);
+
+	/* TODO: what about IWL_RX_PHY_DATA0_EHT_BW320_SLOT */
+
+	if (!le32_get_bits(data0, IWL_RX_PHY_DATA0_EHT_SIGA_CRC_OK))
+		usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BAD_USIG_CRC);
+
+	usig->common |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER_KNOWN);
+	usig->common |= LE32_DEC_ENC(data0, IWL_RX_PHY_DATA0_EHT_PHY_VER,
+				     IEEE80211_RADIOTAP_EHT_USIG_COMMON_PHY_VER);
+
+	/*
+	 * TODO: what about TB - IWL_RX_PHY_DATA1_EHT_TB_PILOT_TYPE,
+	 *			 IWL_RX_PHY_DATA1_EHT_TB_LOW_SS
+	 */
+
+	eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_EHT_LTF);
+	eht->data[0] |= LE32_DEC_ENC(data1, IWL_RX_PHY_DATA1_EHT_SIG_LTF_NUM,
+				     IEEE80211_RADIOTAP_EHT_DATA0_EHT_LTF);
+
+	if (info_type == IWL_RX_PHY_INFO_TYPE_EHT_TB_EXT ||
+	    info_type == IWL_RX_PHY_INFO_TYPE_EHT_TB)
+		iwl_mld_decode_eht_ext_tb(mld, phy_data, rx_status, eht, usig);
+
+	if (info_type == IWL_RX_PHY_INFO_TYPE_EHT_MU_EXT ||
+	    info_type == IWL_RX_PHY_INFO_TYPE_EHT_MU)
+		iwl_mld_decode_eht_ext_mu(mld, phy_data, rx_status, eht, usig);
+}
+
+static void iwl_mld_rx_eht(struct iwl_mld *mld, struct sk_buff *skb,
+			   struct iwl_mld_rx_phy_data *phy_data,
+			   int queue)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_radiotap_eht *eht;
+	struct ieee80211_radiotap_eht_usig *usig;
+	size_t eht_len = sizeof(*eht);
+
+	u32 rate_n_flags = phy_data->rate_n_flags;
+	u32 he_type = rate_n_flags & RATE_MCS_HE_TYPE_MSK;
+	/* EHT and HE have the same values for LTF */
+	u8 ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN;
+	u16 phy_info = phy_data->phy_info;
+	u32 bw;
+
+	/* u32 for 1 user_info */
+	if (phy_data->with_data)
+		eht_len += sizeof(u32);
+
+	eht = iwl_mld_radiotap_put_tlv(skb, IEEE80211_RADIOTAP_EHT, eht_len);
+
+	usig = iwl_mld_radiotap_put_tlv(skb, IEEE80211_RADIOTAP_EHT_USIG,
+					sizeof(*usig));
+	rx_status->flag |= RX_FLAG_RADIOTAP_TLV_AT_END;
+	usig->common |=
+		cpu_to_le32(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW_KNOWN);
+
+	/* specific handling for 320MHz */
+	bw = u32_get_bits(rate_n_flags, RATE_MCS_CHAN_WIDTH_MSK);
+	if (bw == RATE_MCS_CHAN_WIDTH_320_VAL)
+		bw += le32_get_bits(phy_data->data0,
+				    IWL_RX_PHY_DATA0_EHT_BW320_SLOT);
+
+	usig->common |= cpu_to_le32
+		(FIELD_PREP(IEEE80211_RADIOTAP_EHT_USIG_COMMON_BW, bw));
+
+	/* report the AMPDU-EOF bit on single frames */
+	if (!queue && !(phy_info & IWL_RX_MPDU_PHY_AMPDU)) {
+		rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
+		rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT_KNOWN;
+		if (phy_data->data0 &
+		    cpu_to_le32(IWL_RX_PHY_DATA0_EHT_DELIM_EOF))
+			rx_status->flag |= RX_FLAG_AMPDU_EOF_BIT;
+	}
+
+	if (phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD)
+		iwl_mld_decode_eht_phy_data(mld, phy_data, rx_status, eht, usig);
+
+#define CHECK_TYPE(F)							\
+	BUILD_BUG_ON(IEEE80211_RADIOTAP_HE_DATA1_FORMAT_ ## F !=	\
+		     (RATE_MCS_HE_TYPE_ ## F >> RATE_MCS_HE_TYPE_POS))
+
+	CHECK_TYPE(SU);
+	CHECK_TYPE(EXT_SU);
+	CHECK_TYPE(MU);
+	CHECK_TYPE(TRIG);
+
+	switch (u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK)) {
+	case 0:
+		if (he_type == RATE_MCS_HE_TYPE_TRIG) {
+			rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_1_6;
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_1X;
+		} else {
+			rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_0_8;
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X;
+		}
+		break;
+	case 1:
+		rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_1_6;
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_2X;
+		break;
+	case 2:
+		ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+		if (he_type == RATE_MCS_HE_TYPE_TRIG)
+			rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_3_2;
+		else
+			rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_0_8;
+		break;
+	case 3:
+		if (he_type != RATE_MCS_HE_TYPE_TRIG) {
+			ltf = IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_4X;
+			rx_status->eht.gi = NL80211_RATE_INFO_EHT_GI_3_2;
+		}
+		break;
+	default:
+		/* nothing here */
+		break;
+	}
+
+	if (ltf != IEEE80211_RADIOTAP_HE_DATA5_LTF_SIZE_UNKNOWN) {
+		eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_GI);
+		eht->data[0] |= cpu_to_le32
+			(FIELD_PREP(IEEE80211_RADIOTAP_EHT_DATA0_LTF,
+				    ltf) |
+			 FIELD_PREP(IEEE80211_RADIOTAP_EHT_DATA0_GI,
+				    rx_status->eht.gi));
+	}
+
+	if (!phy_data->with_data) {
+		eht->known |= cpu_to_le32(IEEE80211_RADIOTAP_EHT_KNOWN_NSS_S |
+					  IEEE80211_RADIOTAP_EHT_KNOWN_BEAMFORMED_S);
+		eht->data[7] |=
+			le32_encode_bits(le32_get_bits(phy_data->rx_vec[2],
+						       RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK),
+					 IEEE80211_RADIOTAP_EHT_DATA7_NSS_S);
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			eht->data[7] |=
+				cpu_to_le32(IEEE80211_RADIOTAP_EHT_DATA7_BEAMFORMED_S);
+	} else {
+		eht->user_info[0] |=
+			cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_MCS_KNOWN |
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_CODING_KNOWN |
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_KNOWN_O |
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_BEAMFORMING_KNOWN_O |
+				    IEEE80211_RADIOTAP_EHT_USER_INFO_DATA_FOR_USER);
+
+		if (rate_n_flags & RATE_MCS_BF_MSK)
+			eht->user_info[0] |=
+				cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_BEAMFORMING_O);
+
+		if (rate_n_flags & RATE_MCS_LDPC_MSK)
+			eht->user_info[0] |=
+				cpu_to_le32(IEEE80211_RADIOTAP_EHT_USER_INFO_CODING);
+
+		eht->user_info[0] |= cpu_to_le32
+			(FIELD_PREP(IEEE80211_RADIOTAP_EHT_USER_INFO_MCS,
+				    u32_get_bits(rate_n_flags,
+						 RATE_VHT_MCS_RATE_CODE_MSK)) |
+			 FIELD_PREP(IEEE80211_RADIOTAP_EHT_USER_INFO_NSS_O,
+				    u32_get_bits(rate_n_flags,
+						 RATE_MCS_NSS_MSK)));
+	}
+}
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+static void iwl_mld_add_rtap_sniffer_config(struct iwl_mld *mld,
+					    struct sk_buff *skb)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	struct ieee80211_radiotap_vendor_content *radiotap;
+	const u16 vendor_data_len = sizeof(mld->monitor.cur_aid);
+
+	if (!mld->monitor.cur_aid)
+		return;
+
+	radiotap =
+		iwl_mld_radiotap_put_tlv(skb,
+					 IEEE80211_RADIOTAP_VENDOR_NAMESPACE,
+					 sizeof(*radiotap) + vendor_data_len);
+
+	/* Intel OUI */
+	radiotap->oui[0] = 0xf6;
+	radiotap->oui[1] = 0x54;
+	radiotap->oui[2] = 0x25;
+	/* radiotap sniffer config sub-namespace */
+	radiotap->oui_subtype = 1;
+	radiotap->vendor_type = 0;
+
+	/* fill the data now */
+	memcpy(radiotap->data, &mld->monitor.cur_aid,
+	       sizeof(mld->monitor.cur_aid));
+
+	rx_status->flag |= RX_FLAG_RADIOTAP_TLV_AT_END;
+}
+#endif
+
+static void iwl_mld_rx_fill_status(struct iwl_mld *mld, struct sk_buff *skb,
+				   struct iwl_mld_rx_phy_data *phy_data,
+				   struct iwl_rx_mpdu_desc *mpdu_desc,
+				   struct ieee80211_hdr *hdr,
+				   int queue)
+{
+	struct ieee80211_rx_status *rx_status = IEEE80211_SKB_RXCB(skb);
+	u32 format = phy_data->rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
+	u32 rate_n_flags = phy_data->rate_n_flags;
+	u8 stbc = u32_get_bits(rate_n_flags, RATE_MCS_STBC_MSK);
+	bool is_sgi = rate_n_flags & RATE_MCS_SGI_MSK;
+
+	if (WARN_ON_ONCE(phy_data->with_data && (!mpdu_desc || !hdr)))
+		return;
+
+	/* Keep packets with CRC errors (and with overrun) for monitor mode
+	 * (otherwise the firmware discards them) but mark them as bad.
+	 */
+	if (phy_data->with_data &&
+	    (!(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_CRC_OK)) ||
+	     !(mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_OVERRUN_OK)))) {
+		IWL_DEBUG_RX(mld, "Bad CRC or FIFO: 0x%08X.\n",
+			     le32_to_cpu(mpdu_desc->status));
+		rx_status->flag |= RX_FLAG_FAILED_FCS_CRC;
+	}
+
+	phy_data->info_type = IWL_RX_PHY_INFO_TYPE_NONE;
+
+	if (phy_data->with_data &&
+	    likely(!(phy_data->phy_info & IWL_RX_MPDU_PHY_TSF_OVERLOAD))) {
+		rx_status->mactime =
+			le64_to_cpu(mpdu_desc->v3.tsf_on_air_rise);
+
+		/* TSF as indicated by the firmware is at INA time */
+		rx_status->flag |= RX_FLAG_MACTIME_PLCP_START;
+	} else {
+		phy_data->info_type =
+			le32_get_bits(phy_data->data1,
+				      IWL_RX_PHY_DATA1_INFO_TYPE_MASK);
+	}
+
+	/* management stuff on default queue */
+	if (!queue && phy_data->with_data &&
+	    unlikely(ieee80211_is_beacon(hdr->frame_control) ||
+		     ieee80211_is_probe_resp(hdr->frame_control))) {
+		rx_status->boottime_ns = ktime_get_boottime_ns();
+
+		if (mld->scan.pass_all_sched_res == SCHED_SCAN_PASS_ALL_STATE_ENABLED)
+			mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_FOUND;
+	}
+
+	/* set the preamble flag if appropriate */
+	if (format == RATE_MCS_CCK_MSK &&
+	    phy_data->phy_info & IWL_RX_MPDU_PHY_SHORT_PREAMBLE)
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORTPRE;
+
+	iwl_mld_fill_signal(mld, rx_status, phy_data);
+
+	/* This may be overridden by iwl_mld_rx_he() to HE_RU */
+	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
+	case RATE_MCS_CHAN_WIDTH_20:
+		break;
+	case RATE_MCS_CHAN_WIDTH_40:
+		rx_status->bw = RATE_INFO_BW_40;
+		break;
+	case RATE_MCS_CHAN_WIDTH_80:
+		rx_status->bw = RATE_INFO_BW_80;
+		break;
+	case RATE_MCS_CHAN_WIDTH_160:
+		rx_status->bw = RATE_INFO_BW_160;
+		break;
+	case RATE_MCS_CHAN_WIDTH_320:
+		rx_status->bw = RATE_INFO_BW_320;
+		break;
+	}
+
+	/* must be before L-SIG data */
+	if (format == RATE_MCS_HE_MSK)
+		iwl_mld_rx_he(mld, skb, phy_data, queue);
+
+	iwl_mld_decode_lsig(skb, phy_data);
+
+	rx_status->device_timestamp = phy_data->gp2_on_air_rise;
+
+	/* using TLV format and must be after all fixed len fields */
+	if (format == RATE_MCS_EHT_MSK)
+		iwl_mld_rx_eht(mld, skb, phy_data, queue);
+
+#ifdef CONFIG_IWLWIFI_DEBUGFS
+	if (unlikely(mld->monitor.on))
+		iwl_mld_add_rtap_sniffer_config(mld, skb);
+#endif
+
+	if (format != RATE_MCS_CCK_MSK && is_sgi)
+		rx_status->enc_flags |= RX_ENC_FLAG_SHORT_GI;
+
+	if (rate_n_flags & RATE_MCS_LDPC_MSK)
+		rx_status->enc_flags |= RX_ENC_FLAG_LDPC;
+
+	switch (format) {
+	case RATE_MCS_HT_MSK:
+		rx_status->encoding = RX_ENC_HT;
+		rx_status->rate_idx = RATE_HT_MCS_INDEX(rate_n_flags);
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+		break;
+	case RATE_MCS_VHT_MSK:
+	case RATE_MCS_HE_MSK:
+	case RATE_MCS_EHT_MSK:
+		if (format == RATE_MCS_VHT_MSK) {
+			rx_status->encoding = RX_ENC_VHT;
+		} else if (format == RATE_MCS_HE_MSK) {
+			rx_status->encoding = RX_ENC_HE;
+			rx_status->he_dcm =
+				!!(rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK);
+		} else if (format == RATE_MCS_EHT_MSK) {
+			rx_status->encoding = RX_ENC_EHT;
+		}
+
+		rx_status->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1;
+		rx_status->rate_idx = rate_n_flags & RATE_MCS_CODE_MSK;
+		rx_status->enc_flags |= stbc << RX_ENC_FLAG_STBC_SHIFT;
+		break;
+	default: {
+		int rate =
+		    iwl_mld_legacy_hw_idx_to_mac80211_idx(rate_n_flags,
+							  rx_status->band);
+
+		/* valid rate */
+		if (rate >= 0 && rate <= 0xFF) {
+			rx_status->rate_idx = rate;
+			break;
+		}
+
+		/* invalid rate */
+		rx_status->rate_idx = 0;
+
+		if (net_ratelimit())
+			IWL_ERR(mld, "invalid rate_n_flags=0x%x, band=%d\n",
+				rate_n_flags, rx_status->band);
+		break;
+		}
+	}
+}
+
+/* iwl_mld_create_skb adds the rxb to a new skb */
+static int iwl_mld_build_rx_skb(struct iwl_mld *mld, struct sk_buff *skb,
+				struct ieee80211_hdr *hdr, u16 len,
+				u8 crypt_len, struct iwl_rx_cmd_buffer *rxb)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_rx_mpdu_desc *desc = (void *)pkt->data;
+	unsigned int headlen, fraglen, pad_len = 0;
+	unsigned int hdrlen = ieee80211_hdrlen(hdr->frame_control);
+	u8 mic_crc_len = u8_get_bits(desc->mac_flags1,
+				     IWL_RX_MPDU_MFLG1_MIC_CRC_LEN_MASK) << 1;
+
+	if (desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) {
+		len -= 2;
+		pad_len = 2;
+	}
+
+	/* For non monitor interface strip the bytes the RADA might not have
+	 * removed (it might be disabled, e.g. for mgmt frames). As a monitor
+	 * interface cannot exist with other interfaces, this removal is safe
+	 * and sufficient, in monitor mode there's no decryption being done.
+	 */
+	if (len > mic_crc_len && !ieee80211_hw_check(mld->hw, RX_INCLUDES_FCS))
+		len -= mic_crc_len;
+
+	/* If frame is small enough to fit in skb->head, pull it completely.
+	 * If not, only pull ieee80211_hdr (including crypto if present, and
+	 * an additional 8 bytes for SNAP/ethertype, see below) so that
+	 * splice() or TCP coalesce are more efficient.
+	 *
+	 * Since, in addition, ieee80211_data_to_8023() always pull in at
+	 * least 8 bytes (possibly more for mesh) we can do the same here
+	 * to save the cost of doing it later. That still doesn't pull in
+	 * the actual IP header since the typical case has a SNAP header.
+	 * If the latter changes (there are efforts in the standards group
+	 * to do so) we should revisit this and ieee80211_data_to_8023().
+	 */
+	headlen = (len <= skb_tailroom(skb)) ? len : hdrlen + crypt_len + 8;
+
+	/* The firmware may align the packet to DWORD.
+	 * The padding is inserted after the IV.
+	 * After copying the header + IV skip the padding if
+	 * present before copying packet data.
+	 */
+	hdrlen += crypt_len;
+
+	if (unlikely(headlen < hdrlen))
+		return -EINVAL;
+
+	/* Since data doesn't move data while putting data on skb and that is
+	 * the only way we use, data + len is the next place that hdr would
+	 * be put
+	 */
+	skb_set_mac_header(skb, skb->len);
+	skb_put_data(skb, hdr, hdrlen);
+	skb_put_data(skb, (u8 *)hdr + hdrlen + pad_len, headlen - hdrlen);
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		struct {
+			u8 hdr[6];
+			__be16 type;
+		} __packed *shdr = (void *)((u8 *)hdr + hdrlen + pad_len);
+
+		if (unlikely(headlen - hdrlen < sizeof(*shdr) ||
+			     !ether_addr_equal(shdr->hdr, rfc1042_header) ||
+			     (shdr->type != htons(ETH_P_IP) &&
+			      shdr->type != htons(ETH_P_ARP) &&
+			      shdr->type != htons(ETH_P_IPV6) &&
+			      shdr->type != htons(ETH_P_8021Q) &&
+			      shdr->type != htons(ETH_P_PAE) &&
+			      shdr->type != htons(ETH_P_TDLS))))
+			skb->ip_summed = CHECKSUM_NONE;
+	}
+
+	fraglen = len - headlen;
+
+	if (fraglen) {
+		int offset = (u8 *)hdr + headlen + pad_len -
+			     (u8 *)rxb_addr(rxb) + rxb_offset(rxb);
+
+		skb_add_rx_frag(skb, 0, rxb_steal_page(rxb), offset,
+				fraglen, rxb->truesize);
+	}
+
+	return 0;
+}
+
+/* returns true if a packet is a duplicate or invalid tid and
+ * should be dropped. Updates AMSDU PN tracking info
+ */
+VISIBLE_IF_IWLWIFI_KUNIT
+bool
+iwl_mld_is_dup(struct iwl_mld *mld, struct ieee80211_sta *sta,
+	       struct ieee80211_hdr *hdr,
+	       const struct iwl_rx_mpdu_desc *mpdu_desc,
+	       struct ieee80211_rx_status *rx_status, int queue)
+{
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_rxq_dup_data *dup_data;
+	u8 tid, sub_frame_idx;
+
+	if (WARN_ON(!sta))
+		return false;
+
+	mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	if (WARN_ON_ONCE(!mld_sta->dup_data))
+		return false;
+
+	dup_data = &mld_sta->dup_data[queue];
+
+	/* Drop duplicate 802.11 retransmissions
+	 * (IEEE 802.11-2020: 10.3.2.14 "Duplicate detection and recovery")
+	 */
+	if (ieee80211_is_ctl(hdr->frame_control) ||
+	    ieee80211_is_any_nullfunc(hdr->frame_control) ||
+	    is_multicast_ether_addr(hdr->addr1))
+		return false;
+
+	if (ieee80211_is_data_qos(hdr->frame_control)) {
+		/* frame has qos control */
+		tid = ieee80211_get_tid(hdr);
+		if (tid >= IWL_MAX_TID_COUNT)
+			return true;
+	} else {
+		tid = IWL_MAX_TID_COUNT;
+	}
+
+	/* If this wasn't a part of an A-MSDU the sub-frame index will be 0 */
+	sub_frame_idx = mpdu_desc->amsdu_info &
+		IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
+
+	if (IWL_FW_CHECK(mld,
+			 sub_frame_idx > 0 &&
+			 !(mpdu_desc->mac_flags2 & IWL_RX_MPDU_MFLG2_AMSDU),
+			 "got sub_frame_idx=%d but A-MSDU flag is not set\n",
+			 sub_frame_idx))
+		return true;
+
+	if (unlikely(ieee80211_has_retry(hdr->frame_control) &&
+		     dup_data->last_seq[tid] == hdr->seq_ctrl &&
+		     dup_data->last_sub_frame_idx[tid] >= sub_frame_idx))
+		return true;
+
+	/* Allow same PN as the first subframe for following sub frames */
+	if (dup_data->last_seq[tid] == hdr->seq_ctrl &&
+	    sub_frame_idx > dup_data->last_sub_frame_idx[tid])
+		rx_status->flag |= RX_FLAG_ALLOW_SAME_PN;
+
+	dup_data->last_seq[tid] = hdr->seq_ctrl;
+	dup_data->last_sub_frame_idx[tid] = sub_frame_idx;
+
+	rx_status->flag |= RX_FLAG_DUP_VALIDATED;
+
+	return false;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_is_dup);
+
+static void iwl_mld_update_last_rx_timestamp(struct iwl_mld *mld, u8 baid)
+{
+	unsigned long now = jiffies;
+	unsigned long timeout;
+	struct iwl_mld_baid_data *ba_data;
+
+	ba_data = rcu_dereference(mld->fw_id_to_ba[baid]);
+	if (!ba_data) {
+		IWL_DEBUG_HT(mld, "BAID %d not found in map\n", baid);
+		return;
+	}
+
+	if (!ba_data->timeout)
+		return;
+
+	/* To minimize cache bouncing between RX queues, avoid frequent updates
+	 * to last_rx_timestamp. update it only when the timeout period has
+	 * passed. The worst-case scenario is the session expiring after
+	 * approximately 2 * timeout, which is negligible (the update is
+	 * atomic).
+	 */
+	timeout = TU_TO_JIFFIES(ba_data->timeout);
+	if (time_is_before_jiffies(ba_data->last_rx_timestamp + timeout))
+		ba_data->last_rx_timestamp = now;
+}
+
+/* Processes received packets for a station.
+ * Sets *drop to true if the packet should be dropped.
+ * Returns the station if found, or NULL otherwise.
+ */
+static struct ieee80211_sta *
+iwl_mld_rx_with_sta(struct iwl_mld *mld, struct ieee80211_hdr *hdr,
+		    struct sk_buff *skb,
+		    const struct iwl_rx_mpdu_desc *mpdu_desc,
+		    const struct iwl_rx_packet *pkt, int queue, bool *drop)
+{
+	struct ieee80211_sta *sta = NULL;
+	struct ieee80211_link_sta *link_sta = NULL;
+	struct ieee80211_rx_status *rx_status;
+	u8 baid;
+
+	if (mpdu_desc->status & cpu_to_le32(IWL_RX_MPDU_STATUS_SRC_STA_FOUND)) {
+		u8 sta_id = le32_get_bits(mpdu_desc->status,
+					  IWL_RX_MPDU_STATUS_STA_ID);
+
+		if (IWL_FW_CHECK(mld,
+				 sta_id >= mld->fw->ucode_capa.num_stations,
+				 "rx_mpdu: invalid sta_id %d\n", sta_id))
+			return NULL;
+
+		link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]);
+		if (!IS_ERR_OR_NULL(link_sta))
+			sta = link_sta->sta;
+	} else if (!is_multicast_ether_addr(hdr->addr2)) {
+		/* Passing NULL is fine since we prevent two stations with the
+		 * same address from being added.
+		 */
+		sta = ieee80211_find_sta_by_ifaddr(mld->hw, hdr->addr2, NULL);
+	}
+
+	/* we may not have any station yet */
+	if (!sta)
+		return NULL;
+
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
+	if (link_sta && sta->valid_links) {
+		rx_status->link_valid = true;
+		rx_status->link_id = link_sta->link_id;
+	}
+
+	/* fill checksum */
+	if (ieee80211_is_data(hdr->frame_control) &&
+	    pkt->len_n_flags & cpu_to_le32(FH_RSCSR_RPA_EN)) {
+		u16 hwsum = be16_to_cpu(mpdu_desc->v3.raw_xsum);
+
+		skb->ip_summed = CHECKSUM_COMPLETE;
+		skb->csum = csum_unfold(~(__force __sum16)hwsum);
+	}
+
+	if (iwl_mld_is_dup(mld, sta, hdr, mpdu_desc, rx_status, queue)) {
+		IWL_DEBUG_DROP(mld, "Dropping duplicate packet 0x%x\n",
+			       le16_to_cpu(hdr->seq_ctrl));
+		*drop = true;
+		return NULL;
+	}
+
+	baid = le32_get_bits(mpdu_desc->reorder_data,
+			     IWL_RX_MPDU_REORDER_BAID_MASK);
+	if (baid != IWL_RX_REORDER_DATA_INVALID_BAID)
+		iwl_mld_update_last_rx_timestamp(mld, baid);
+
+	if (link_sta && ieee80211_is_data(hdr->frame_control)) {
+		u8 sub_frame_idx = mpdu_desc->amsdu_info &
+			IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
+
+		/* 0 means not an A-MSDU, and 1 means a new A-MSDU */
+		if (!sub_frame_idx || sub_frame_idx == 1)
+			iwl_mld_count_mpdu_rx(link_sta, queue, 1);
+
+		if (!is_multicast_ether_addr(hdr->addr1))
+			iwl_mld_low_latency_update_counters(mld, hdr, sta,
+							    queue);
+	}
+
+	return sta;
+}
+
+#define KEY_IDX_LEN 2
+
+static int iwl_mld_rx_mgmt_prot(struct ieee80211_sta *sta,
+				struct ieee80211_hdr *hdr,
+				struct ieee80211_rx_status *rx_status,
+				u32 mpdu_status,
+				u32 mpdu_len)
+{
+	struct wireless_dev *wdev;
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_vif *mld_vif;
+	u8 keyidx;
+	struct ieee80211_key_conf *key;
+	const u8 *frame = (void *)hdr;
+
+	if ((mpdu_status & IWL_RX_MPDU_STATUS_SEC_MASK) ==
+	     IWL_RX_MPDU_STATUS_SEC_NONE)
+		return 0;
+
+	/* For non-beacon, we don't really care. But beacons may
+	 * be filtered out, and we thus need the firmware's replay
+	 * detection, otherwise beacons the firmware previously
+	 * filtered could be replayed, or something like that, and
+	 * it can filter a lot - though usually only if nothing has
+	 * changed.
+	 */
+	if (!ieee80211_is_beacon(hdr->frame_control))
+		return 0;
+
+	if (!sta)
+		return -1;
+
+	mld_sta = iwl_mld_sta_from_mac80211(sta);
+	mld_vif = iwl_mld_vif_from_mac80211(mld_sta->vif);
+
+	/* key mismatch - will also report !MIC_OK but we shouldn't count it */
+	if (!(mpdu_status & IWL_RX_MPDU_STATUS_KEY_VALID))
+		goto report;
+
+	/* good cases */
+	if (likely(mpdu_status & IWL_RX_MPDU_STATUS_MIC_OK &&
+		   !(mpdu_status & IWL_RX_MPDU_STATUS_REPLAY_ERROR))) {
+		rx_status->flag |= RX_FLAG_DECRYPTED;
+		return 0;
+	}
+
+	/* both keys will have the same cipher and MIC length, use
+	 * whichever one is available
+	 */
+	key = rcu_dereference(mld_vif->bigtks[0]);
+	if (!key) {
+		key = rcu_dereference(mld_vif->bigtks[1]);
+		if (!key)
+			goto report;
+	}
+
+	if (mpdu_len < key->icv_len + IEEE80211_GMAC_PN_LEN + KEY_IDX_LEN)
+		goto report;
+
+	/* get the real key ID */
+	keyidx = frame[mpdu_len - key->icv_len - IEEE80211_GMAC_PN_LEN - KEY_IDX_LEN];
+	/* and if that's the other key, look it up */
+	if (keyidx != key->keyidx) {
+		/* shouldn't happen since firmware checked, but be safe
+		 * in case the MIC length is wrong too, for example
+		 */
+		if (keyidx != 6 && keyidx != 7)
+			return -1;
+
+		key = rcu_dereference(mld_vif->bigtks[keyidx - 6]);
+		if (!key)
+			goto report;
+	}
+
+	/* Report status to mac80211 */
+	if (!(mpdu_status & IWL_RX_MPDU_STATUS_MIC_OK))
+		ieee80211_key_mic_failure(key);
+	else if (mpdu_status & IWL_RX_MPDU_STATUS_REPLAY_ERROR)
+		ieee80211_key_replay(key);
+report:
+	wdev = ieee80211_vif_to_wdev(mld_sta->vif);
+	if (wdev->netdev)
+		cfg80211_rx_unprot_mlme_mgmt(wdev->netdev, (void *)hdr,
+					     mpdu_len);
+
+	return -1;
+}
+
+static int iwl_mld_rx_crypto(struct iwl_mld *mld,
+			     struct ieee80211_sta *sta,
+			     struct ieee80211_hdr *hdr,
+			     struct ieee80211_rx_status *rx_status,
+			     struct iwl_rx_mpdu_desc *desc, int queue,
+			     u32 pkt_flags, u8 *crypto_len)
+{
+	u32 status = le32_to_cpu(desc->status);
+
+	if (unlikely(ieee80211_is_mgmt(hdr->frame_control) &&
+		     !ieee80211_has_protected(hdr->frame_control)))
+		return iwl_mld_rx_mgmt_prot(sta, hdr, rx_status, status,
+					    le16_to_cpu(desc->mpdu_len));
+
+	if (!ieee80211_has_protected(hdr->frame_control) ||
+	    (status & IWL_RX_MPDU_STATUS_SEC_MASK) ==
+	    IWL_RX_MPDU_STATUS_SEC_NONE)
+		return 0;
+
+	switch (status & IWL_RX_MPDU_STATUS_SEC_MASK) {
+	case IWL_RX_MPDU_STATUS_SEC_CCM:
+	case IWL_RX_MPDU_STATUS_SEC_GCM:
+		BUILD_BUG_ON(IEEE80211_CCMP_PN_LEN != IEEE80211_GCMP_PN_LEN);
+		if (!(status & IWL_RX_MPDU_STATUS_MIC_OK)) {
+			IWL_DEBUG_DROP(mld,
+				       "Dropping packet, bad MIC (CCM/GCM)\n");
+			return -1;
+		}
+
+		rx_status->flag |= RX_FLAG_DECRYPTED | RX_FLAG_MIC_STRIPPED;
+		*crypto_len = IEEE80211_CCMP_HDR_LEN;
+		return 0;
+	case IWL_RX_MPDU_STATUS_SEC_TKIP:
+		if (!(status & IWL_RX_MPDU_STATUS_ICV_OK))
+			return -1;
+
+		if (!(status & RX_MPDU_RES_STATUS_MIC_OK))
+			rx_status->flag |= RX_FLAG_MMIC_ERROR;
+
+		if (pkt_flags & FH_RSCSR_RADA_EN) {
+			rx_status->flag |= RX_FLAG_ICV_STRIPPED;
+			rx_status->flag |= RX_FLAG_MMIC_STRIPPED;
+		}
+
+		*crypto_len = IEEE80211_TKIP_IV_LEN;
+		rx_status->flag |= RX_FLAG_DECRYPTED;
+		return 0;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static void iwl_mld_rx_update_ampdu_ref(struct iwl_mld *mld,
+					struct iwl_mld_rx_phy_data *phy_data,
+					struct ieee80211_rx_status *rx_status)
+{
+	bool toggle_bit =
+		phy_data->phy_info & IWL_RX_MPDU_PHY_AMPDU_TOGGLE;
+
+	rx_status->flag |= RX_FLAG_AMPDU_DETAILS;
+	/* Toggle is switched whenever new aggregation starts. Make
+	 * sure ampdu_reference is never 0 so we can later use it to
+	 * see if the frame was really part of an A-MPDU or not.
+	 */
+	if (toggle_bit != mld->monitor.ampdu_toggle) {
+		mld->monitor.ampdu_ref++;
+		if (mld->monitor.ampdu_ref == 0)
+			mld->monitor.ampdu_ref++;
+		mld->monitor.ampdu_toggle = toggle_bit;
+		phy_data->first_subframe = true;
+	}
+	rx_status->ampdu_reference = mld->monitor.ampdu_ref;
+}
+
+static void
+iwl_mld_fill_rx_status_band_freq(struct iwl_mld_rx_phy_data *phy_data,
+				 struct iwl_rx_mpdu_desc *mpdu_desc,
+				 struct ieee80211_rx_status *rx_status)
+{
+	enum nl80211_band band;
+
+	band = BAND_IN_RX_STATUS(mpdu_desc->mac_phy_idx);
+	rx_status->band = iwl_mld_phy_band_to_nl80211(band);
+	rx_status->freq = ieee80211_channel_to_frequency(phy_data->channel,
+							 rx_status->band);
+}
+
+void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
+		     struct iwl_rx_cmd_buffer *rxb, int queue)
+{
+	struct iwl_rx_packet *pkt = rxb_addr(rxb);
+	struct iwl_mld_rx_phy_data phy_data = {};
+	struct iwl_rx_mpdu_desc *mpdu_desc = (void *)pkt->data;
+	struct ieee80211_sta *sta;
+	struct ieee80211_hdr *hdr;
+	struct sk_buff *skb;
+	size_t mpdu_desc_size = sizeof(*mpdu_desc);
+	bool drop = false;
+	u8 crypto_len = 0;
+	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+	u32 mpdu_len;
+	enum iwl_mld_reorder_result reorder_res;
+	struct ieee80211_rx_status *rx_status;
+
+	if (unlikely(mld->fw_status.in_hw_restart))
+		return;
+
+	if (IWL_FW_CHECK(mld, pkt_len < mpdu_desc_size,
+			 "Bad REPLY_RX_MPDU_CMD size (%d)\n", pkt_len))
+		return;
+
+	mpdu_len = le16_to_cpu(mpdu_desc->mpdu_len);
+
+	if (IWL_FW_CHECK(mld, mpdu_len + mpdu_desc_size > pkt_len,
+			 "FW lied about packet len (%d)\n", pkt_len))
+		return;
+
+	/* Don't use dev_alloc_skb(), we'll have enough headroom once
+	 * ieee80211_hdr pulled.
+	 */
+	skb = alloc_skb(128, GFP_ATOMIC);
+	if (!skb) {
+		IWL_ERR(mld, "alloc_skb failed\n");
+		return;
+	}
+
+	hdr = (void *)(pkt->data + mpdu_desc_size);
+
+	iwl_mld_fill_phy_data(mpdu_desc, &phy_data);
+
+	if (mpdu_desc->mac_flags2 & IWL_RX_MPDU_MFLG2_PAD) {
+		/* If the device inserted padding it means that (it thought)
+		 * the 802.11 header wasn't a multiple of 4 bytes long. In
+		 * this case, reserve two bytes at the start of the SKB to
+		 * align the payload properly in case we end up copying it.
+		 */
+		skb_reserve(skb, 2);
+	}
+
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
+	/* this is needed early */
+	iwl_mld_fill_rx_status_band_freq(&phy_data, mpdu_desc, rx_status);
+
+	rcu_read_lock();
+
+	sta = iwl_mld_rx_with_sta(mld, hdr, skb, mpdu_desc, pkt, queue, &drop);
+	if (drop)
+		goto drop;
+
+	/* update aggregation data for monitor sake on default queue */
+	if (!queue && (phy_data.phy_info & IWL_RX_MPDU_PHY_AMPDU))
+		iwl_mld_rx_update_ampdu_ref(mld, &phy_data, rx_status);
+
+	iwl_mld_rx_fill_status(mld, skb, &phy_data, mpdu_desc, hdr, queue);
+
+	if (iwl_mld_rx_crypto(mld, sta, hdr, rx_status, mpdu_desc, queue,
+			      le32_to_cpu(pkt->len_n_flags), &crypto_len))
+		goto drop;
+
+	if (iwl_mld_build_rx_skb(mld, skb, hdr, mpdu_len, crypto_len, rxb))
+		goto drop;
+
+	/* time sync frame is saved and will be released later when the
+	 * notification with the timestamps arrives.
+	 */
+	if (iwl_mld_time_sync_frame(mld, skb, hdr->addr2))
+		goto out;
+
+	reorder_res = iwl_mld_reorder(mld, napi, queue, sta, skb, mpdu_desc);
+	switch (reorder_res) {
+	case IWL_MLD_PASS_SKB:
+		break;
+	case IWL_MLD_DROP_SKB:
+		goto drop;
+	case IWL_MLD_BUFFERED_SKB:
+		goto out;
+	default:
+		WARN_ON(1);
+		goto drop;
+	}
+
+	iwl_mld_pass_packet_to_mac80211(mld, napi, skb, queue, sta);
+
+	goto out;
+
+drop:
+	kfree_skb(skb);
+out:
+	rcu_read_unlock();
+}
+
+#define SYNC_RX_QUEUE_TIMEOUT (HZ)
+void iwl_mld_sync_rx_queues(struct iwl_mld *mld,
+			    enum iwl_mld_internal_rxq_notif_type type,
+			    const void *notif_payload, u32 notif_payload_size)
+{
+	u8 num_rx_queues = mld->trans->num_rx_queues;
+	struct {
+		struct iwl_rxq_sync_cmd sync_cmd;
+		struct iwl_mld_internal_rxq_notif notif;
+	} __packed cmd = {
+		.sync_cmd.rxq_mask = cpu_to_le32(BIT(num_rx_queues) - 1),
+		.sync_cmd.count =
+			cpu_to_le32(sizeof(struct iwl_mld_internal_rxq_notif) +
+				    notif_payload_size),
+		.notif.type = type,
+		.notif.cookie = mld->rxq_sync.cookie,
+	};
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(DATA_PATH_GROUP, TRIGGER_RX_QUEUES_NOTIF_CMD),
+		.data[0] = &cmd,
+		.len[0] = sizeof(cmd),
+		.data[1] = notif_payload,
+		.len[1] = notif_payload_size,
+	};
+	int ret;
+
+	/* size must be a multiple of DWORD */
+	if (WARN_ON(cmd.sync_cmd.count & cpu_to_le32(3)))
+		return;
+
+	mld->rxq_sync.state = (1 << num_rx_queues) - 1;
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (ret) {
+		IWL_ERR(mld, "Failed to trigger RX queues sync (%d)\n", ret);
+		goto out;
+	}
+
+	ret = wait_event_timeout(mld->rxq_sync.waitq,
+				 READ_ONCE(mld->rxq_sync.state) == 0,
+				 SYNC_RX_QUEUE_TIMEOUT);
+	WARN_ONCE(!ret, "RXQ sync failed: state=0x%lx, cookie=%d\n",
+		  mld->rxq_sync.state, mld->rxq_sync.cookie);
+
+out:
+	mld->rxq_sync.state = 0;
+	mld->rxq_sync.cookie++;
+}
+
+void iwl_mld_handle_rx_queues_sync_notif(struct iwl_mld *mld,
+					 struct napi_struct *napi,
+					 struct iwl_rx_packet *pkt, int queue)
+{
+	struct iwl_rxq_sync_notification *notif;
+	struct iwl_mld_internal_rxq_notif *internal_notif;
+	u32 len = iwl_rx_packet_payload_len(pkt);
+	size_t combined_notif_len = sizeof(*notif) + sizeof(*internal_notif);
+
+	notif = (void *)pkt->data;
+	internal_notif = (void *)notif->payload;
+
+	if (IWL_FW_CHECK(mld, len < combined_notif_len,
+			 "invalid notification size %u (%zu)\n",
+			 len, combined_notif_len))
+		return;
+
+	len -= combined_notif_len;
+
+	if (IWL_FW_CHECK(mld, mld->rxq_sync.cookie != internal_notif->cookie,
+			 "received expired RX queue sync message (cookie=%d expected=%d q[%d])\n",
+			 internal_notif->cookie, mld->rxq_sync.cookie, queue))
+		return;
+
+	switch (internal_notif->type) {
+	case IWL_MLD_RXQ_EMPTY:
+		IWL_FW_CHECK(mld, len,
+			     "invalid empty notification size %d\n", len);
+		break;
+	case IWL_MLD_RXQ_NOTIF_DEL_BA:
+		if (IWL_FW_CHECK(mld, len != sizeof(struct iwl_mld_delba_data),
+				 "invalid delba notification size %u (%zu)\n",
+				 len, sizeof(struct iwl_mld_delba_data)))
+			break;
+		iwl_mld_del_ba(mld, queue, (void *)internal_notif->payload);
+		break;
+	default:
+		WARN_ON_ONCE(1);
+	}
+
+	IWL_FW_CHECK(mld, !test_and_clear_bit(queue, &mld->rxq_sync.state),
+		     "RXQ sync: queue %d responded a second time!\n", queue);
+
+	if (READ_ONCE(mld->rxq_sync.state) == 0)
+		wake_up(&mld->rxq_sync.waitq);
+}
+
+void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
+				struct iwl_rx_packet *pkt, int queue)
+{
+	struct iwl_rx_no_data_ver_3 *desc;
+	struct iwl_mld_rx_phy_data phy_data;
+	struct ieee80211_rx_status *rx_status;
+	struct sk_buff *skb;
+	u32 format, rssi;
+
+	if (unlikely(mld->fw_status.in_hw_restart))
+		return;
+
+	if (IWL_FW_CHECK(mld, iwl_rx_packet_payload_len(pkt) < sizeof(*desc),
+			 "Bad RX_NO_DATA_NOTIF size (%d)\n",
+			 iwl_rx_packet_payload_len(pkt)))
+		return;
+
+	desc = (void *)pkt->data;
+
+	rssi = le32_to_cpu(desc->rssi);
+	phy_data.energy_a = u32_get_bits(rssi, RX_NO_DATA_CHAIN_A_MSK);
+	phy_data.energy_b = u32_get_bits(rssi, RX_NO_DATA_CHAIN_B_MSK);
+	phy_data.channel = u32_get_bits(rssi, RX_NO_DATA_CHANNEL_MSK);
+	phy_data.data0 = desc->phy_info[0];
+	phy_data.data1 = desc->phy_info[1];
+	phy_data.phy_info = IWL_RX_MPDU_PHY_TSF_OVERLOAD;
+	phy_data.gp2_on_air_rise = le32_to_cpu(desc->on_air_rise_time);
+	phy_data.rate_n_flags = le32_to_cpu(desc->rate);
+	phy_data.with_data = false;
+
+	BUILD_BUG_ON(sizeof(phy_data.rx_vec) != sizeof(desc->rx_vec));
+	memcpy(phy_data.rx_vec, desc->rx_vec, sizeof(phy_data.rx_vec));
+
+	format = phy_data.rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
+
+	/* Don't use dev_alloc_skb(), we'll have enough headroom once
+	 * ieee80211_hdr pulled.
+	 */
+	skb = alloc_skb(128, GFP_ATOMIC);
+	if (!skb) {
+		IWL_ERR(mld, "alloc_skb failed\n");
+		return;
+	}
+
+	rx_status = IEEE80211_SKB_RXCB(skb);
+
+	/* 0-length PSDU */
+	rx_status->flag |= RX_FLAG_NO_PSDU;
+
+	/* mark as failed PLCP on any errors to skip checks in mac80211 */
+	if (le32_get_bits(desc->info, RX_NO_DATA_INFO_ERR_MSK) !=
+	    RX_NO_DATA_INFO_ERR_NONE)
+		rx_status->flag |= RX_FLAG_FAILED_PLCP_CRC;
+
+	switch (le32_get_bits(desc->info, RX_NO_DATA_INFO_TYPE_MSK)) {
+	case RX_NO_DATA_INFO_TYPE_NDP:
+		rx_status->zero_length_psdu_type =
+			IEEE80211_RADIOTAP_ZERO_LEN_PSDU_SOUNDING;
+		break;
+	case RX_NO_DATA_INFO_TYPE_MU_UNMATCHED:
+	case RX_NO_DATA_INFO_TYPE_TB_UNMATCHED:
+		rx_status->zero_length_psdu_type =
+			IEEE80211_RADIOTAP_ZERO_LEN_PSDU_NOT_CAPTURED;
+		break;
+	default:
+		rx_status->zero_length_psdu_type =
+			IEEE80211_RADIOTAP_ZERO_LEN_PSDU_VENDOR;
+		break;
+	}
+
+	rx_status->band = phy_data.channel > 14 ? NL80211_BAND_5GHZ :
+		NL80211_BAND_2GHZ;
+
+	rx_status->freq = ieee80211_channel_to_frequency(phy_data.channel,
+							 rx_status->band);
+
+	iwl_mld_rx_fill_status(mld, skb, &phy_data, NULL, NULL, queue);
+
+	/* No more radiotap info should be added after this point.
+	 * Mark it as mac header for upper layers to know where
+	 * the radiotap header ends.
+	 */
+	skb_set_mac_header(skb, skb->len);
+
+	/* Override the nss from the rx_vec since the rate_n_flags has
+	 * only 1 bit for the nss which gives a max of 2 ss but there
+	 * may be up to 8 spatial streams.
+	 */
+	switch (format) {
+	case RATE_MCS_VHT_MSK:
+		rx_status->nss =
+			le32_get_bits(desc->rx_vec[0],
+				      RX_NO_DATA_RX_VEC0_VHT_NSTS_MSK) + 1;
+		break;
+	case RATE_MCS_HE_MSK:
+		rx_status->nss =
+			le32_get_bits(desc->rx_vec[0],
+				      RX_NO_DATA_RX_VEC0_HE_NSTS_MSK) + 1;
+		break;
+	case RATE_MCS_EHT_MSK:
+		rx_status->nss =
+			le32_get_bits(desc->rx_vec[2],
+				      RX_NO_DATA_RX_VEC2_EHT_NSTS_MSK) + 1;
+	}
+
+	/* pass the packet to mac80211 */
+	rcu_read_lock();
+	ieee80211_rx_napi(mld->hw, NULL, skb, napi);
+	rcu_read_unlock();
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/rx.h b/drivers/net/wireless/intel/iwlwifi/mld/rx.h
new file mode 100644
index 0000000000000..2beabd7e70b15
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/rx.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_rx_h__
+#define __iwl_mld_rx_h__
+
+#include "mld.h"
+
+/**
+ * enum iwl_mld_internal_rxq_notif_type - RX queue sync notif types
+ *
+ * @IWL_MLD_RXQ_EMPTY: empty sync notification
+ * @IWL_MLD_RXQ_NOTIF_DEL_BA: notify RSS queues of delBA
+ */
+enum iwl_mld_internal_rxq_notif_type {
+	IWL_MLD_RXQ_EMPTY,
+	IWL_MLD_RXQ_NOTIF_DEL_BA,
+};
+
+/**
+ * struct iwl_mld_internal_rxq_notif - @iwl_rxq_sync_cmd internal data.
+ * This data is echoed by the firmware to all RSS queues and should be DWORD
+ * aligned. FW is agnostic to the data, so there are no endianness requirements
+ *
+ * @type: one of &iwl_mld_internal_rxq_notif_type
+ * @cookie: unique internal cookie to identify old notifications
+ * @reserved: reserved for alignment
+ * @payload: data to send to RX queues based on the type (may be empty)
+ */
+struct iwl_mld_internal_rxq_notif {
+	u8 type;
+	u8 reserved[3];
+	u32 cookie;
+	u8 payload[];
+} __packed;
+
+/**
+ * struct iwl_mld_rx_queues_sync - RX queues sync data
+ *
+ * @waitq: wait queue for RX queues sync completion
+ * @cookie: unique id to correlate sync requests with responses
+ * @state: bitmask representing the sync state of RX queues
+ *	all RX queues bits are set before sending the command, and the
+ *	corresponding queue bit cleared upon handling the notification
+ */
+struct iwl_mld_rx_queues_sync {
+	wait_queue_head_t waitq;
+	u32 cookie;
+	unsigned long state;
+};
+
+void iwl_mld_rx_mpdu(struct iwl_mld *mld, struct napi_struct *napi,
+		     struct iwl_rx_cmd_buffer *rxb, int queue);
+
+void iwl_mld_sync_rx_queues(struct iwl_mld *mld,
+			    enum iwl_mld_internal_rxq_notif_type type,
+			    const void *notif_payload, u32 notif_payload_size);
+
+void iwl_mld_handle_rx_queues_sync_notif(struct iwl_mld *mld,
+					 struct napi_struct *napi,
+					 struct iwl_rx_packet *pkt, int queue);
+
+void iwl_mld_pass_packet_to_mac80211(struct iwl_mld *mld,
+				     struct napi_struct *napi,
+				     struct sk_buff *skb, int queue,
+				     struct ieee80211_sta *sta);
+
+void iwl_mld_rx_monitor_no_data(struct iwl_mld *mld, struct napi_struct *napi,
+				struct iwl_rx_packet *pkt, int queue);
+
+#endif /* __iwl_mld_agg_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.c b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
new file mode 100644
index 0000000000000..5f4ede92028b4
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
@@ -0,0 +1,2006 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include <linux/crc32.h>
+
+#include "mld.h"
+#include "scan.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "phy.h"
+#include "mlo.h"
+
+#include "fw/api/scan.h"
+#include "fw/dbg.h"
+
+#define IWL_SCAN_DWELL_ACTIVE 10
+#define IWL_SCAN_DWELL_PASSIVE 110
+#define IWL_SCAN_NUM_OF_FRAGS 3
+
+/* adaptive dwell max budget time [TU] for full scan */
+#define IWL_SCAN_ADWELL_MAX_BUDGET_FULL_SCAN 300
+
+/* adaptive dwell max budget time [TU] for directed scan */
+#define IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN 100
+
+/* adaptive dwell default high band APs number */
+#define IWL_SCAN_ADWELL_DEFAULT_HB_N_APS 8
+
+/* adaptive dwell default low band APs number */
+#define IWL_SCAN_ADWELL_DEFAULT_LB_N_APS 2
+
+/* adaptive dwell default APs number for P2P social channels (1, 6, 11) */
+#define IWL_SCAN_ADWELL_DEFAULT_N_APS_SOCIAL 10
+
+/* adaptive dwell number of APs override for P2P friendly GO channels */
+#define IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY 10
+
+/* adaptive dwell number of APs override for P2P social channels */
+#define IWL_SCAN_ADWELL_N_APS_SOCIAL_CHS 2
+
+/* adaptive dwell number of APs override mask for p2p friendly GO */
+#define IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY_BIT BIT(20)
+
+/* adaptive dwell number of APs override mask for social channels */
+#define IWL_SCAN_ADWELL_N_APS_SOCIAL_CHS_BIT BIT(21)
+
+#define SCAN_TIMEOUT_MSEC (30000 * HZ)
+
+/* minimal number of 2GHz and 5GHz channels in the regular scan request */
+#define IWL_MLD_6GHZ_PASSIVE_SCAN_MIN_CHANS 4
+
+enum iwl_mld_scan_type {
+	IWL_SCAN_TYPE_NOT_SET,
+	IWL_SCAN_TYPE_UNASSOC,
+	IWL_SCAN_TYPE_WILD,
+	IWL_SCAN_TYPE_MILD,
+	IWL_SCAN_TYPE_FRAGMENTED,
+	IWL_SCAN_TYPE_FAST_BALANCE,
+};
+
+struct iwl_mld_scan_timing_params {
+	u32 suspend_time;
+	u32 max_out_time;
+};
+
+static const struct iwl_mld_scan_timing_params scan_timing[] = {
+	[IWL_SCAN_TYPE_UNASSOC] = {
+		.suspend_time = 0,
+		.max_out_time = 0,
+	},
+	[IWL_SCAN_TYPE_WILD] = {
+		.suspend_time = 30,
+		.max_out_time = 120,
+	},
+	[IWL_SCAN_TYPE_MILD] = {
+		.suspend_time = 120,
+		.max_out_time = 120,
+	},
+	[IWL_SCAN_TYPE_FRAGMENTED] = {
+		.suspend_time = 95,
+		.max_out_time = 44,
+	},
+	[IWL_SCAN_TYPE_FAST_BALANCE] = {
+		.suspend_time = 30,
+		.max_out_time = 37,
+	},
+};
+
+struct iwl_mld_scan_params {
+	enum iwl_mld_scan_type type;
+	u32 n_channels;
+	u16 delay;
+	int n_ssids;
+	struct cfg80211_ssid *ssids;
+	struct ieee80211_channel **channels;
+	u32 flags;
+	u8 *mac_addr;
+	u8 *mac_addr_mask;
+	bool no_cck;
+	bool pass_all;
+	int n_match_sets;
+	struct iwl_scan_probe_req preq;
+	struct cfg80211_match_set *match_sets;
+	int n_scan_plans;
+	struct cfg80211_sched_scan_plan *scan_plans;
+	bool iter_notif;
+	bool respect_p2p_go;
+	u8 fw_link_id;
+	struct cfg80211_scan_6ghz_params *scan_6ghz_params;
+	u32 n_6ghz_params;
+	bool scan_6ghz;
+	bool enable_6ghz_passive;
+	u8 bssid[ETH_ALEN] __aligned(2);
+};
+
+struct iwl_mld_scan_respect_p2p_go_iter_data {
+	struct ieee80211_vif *current_vif;
+	bool p2p_go;
+};
+
+static void iwl_mld_scan_respect_p2p_go_iter(void *_data, u8 *mac,
+					     struct ieee80211_vif *vif)
+{
+	struct iwl_mld_scan_respect_p2p_go_iter_data *data = _data;
+
+	/* exclude the given vif */
+	if (vif == data->current_vif)
+		return;
+
+	/* TODO: CDB check the band of the GO */
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_P2P_GO &&
+	    iwl_mld_vif_from_mac80211(vif)->ap_ibss_active)
+		data->p2p_go = true;
+}
+
+static bool iwl_mld_get_respect_p2p_go(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif,
+				       bool low_latency)
+{
+	struct iwl_mld_scan_respect_p2p_go_iter_data data = {
+		.current_vif = vif,
+		.p2p_go = false,
+	};
+
+	if (!low_latency)
+		return false;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_scan_respect_p2p_go_iter,
+						&data);
+
+	return data.p2p_go;
+}
+
+struct iwl_mld_scan_iter_data {
+	struct ieee80211_vif *current_vif;
+	bool active_vif;
+	bool is_dcm_with_p2p_go;
+	bool global_low_latency;
+};
+
+static void iwl_mld_scan_iterator(void *_data, u8 *mac,
+				  struct ieee80211_vif *vif)
+{
+	struct iwl_mld_scan_iter_data *data = _data;
+	struct ieee80211_vif *curr_vif = data->current_vif;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_vif *curr_mld_vif;
+	unsigned long curr_vif_active_links;
+	u16 link_id;
+
+	data->global_low_latency |= iwl_mld_vif_low_latency(mld_vif);
+
+	if ((ieee80211_vif_is_mld(vif) && vif->active_links) ||
+	    (vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+	     mld_vif->deflink.active))
+		data->active_vif = true;
+
+	if (vif == curr_vif)
+		return;
+
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_P2P_GO)
+		return;
+
+	/* Currently P2P GO can't be AP MLD so the logic below assumes that */
+	WARN_ON_ONCE(ieee80211_vif_is_mld(vif));
+
+	curr_vif_active_links =
+		ieee80211_vif_is_mld(curr_vif) ? curr_vif->active_links : 1;
+
+	curr_mld_vif = iwl_mld_vif_from_mac80211(curr_vif);
+
+	for_each_set_bit(link_id, &curr_vif_active_links,
+			 IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct iwl_mld_link *curr_mld_link =
+			iwl_mld_link_dereference_check(curr_mld_vif, link_id);
+
+		if (WARN_ON(!curr_mld_link))
+			return;
+
+		if (rcu_access_pointer(curr_mld_link->chan_ctx) &&
+		    rcu_access_pointer(mld_vif->deflink.chan_ctx) !=
+		    rcu_access_pointer(curr_mld_link->chan_ctx)) {
+			data->is_dcm_with_p2p_go = true;
+			return;
+		}
+	}
+}
+
+static enum
+iwl_mld_scan_type iwl_mld_get_scan_type(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct iwl_mld_scan_iter_data *data)
+{
+	enum iwl_mld_traffic_load load = mld->scan.traffic_load.status;
+
+	/* A scanning AP interface probably wants to generate a survey to do
+	 * ACS (automatic channel selection).
+	 * Force a non-fragmented scan in that case.
+	 */
+	if (ieee80211_vif_type_p2p(vif) == NL80211_IFTYPE_AP)
+		return IWL_SCAN_TYPE_WILD;
+
+	if (!data->active_vif)
+		return IWL_SCAN_TYPE_UNASSOC;
+
+	if ((load == IWL_MLD_TRAFFIC_HIGH || data->global_low_latency) &&
+	    vif->type != NL80211_IFTYPE_P2P_DEVICE)
+		return IWL_SCAN_TYPE_FRAGMENTED;
+
+	/* In case of DCM with P2P GO set all scan requests as
+	 * fast-balance scan
+	 */
+	if (vif->type == NL80211_IFTYPE_STATION &&
+	    data->is_dcm_with_p2p_go)
+		return IWL_SCAN_TYPE_FAST_BALANCE;
+
+	if (load >= IWL_MLD_TRAFFIC_MEDIUM || data->global_low_latency)
+		return IWL_SCAN_TYPE_MILD;
+
+	return IWL_SCAN_TYPE_WILD;
+}
+
+static u8 *
+iwl_mld_scan_add_2ghz_elems(struct iwl_mld *mld, const u8 *ies,
+			    size_t len, u8 *const pos)
+{
+	static const u8 before_ds_params[] = {
+	    WLAN_EID_SSID,
+	    WLAN_EID_SUPP_RATES,
+	    WLAN_EID_REQUEST,
+	    WLAN_EID_EXT_SUPP_RATES,
+	};
+	size_t offs;
+	u8 *newpos = pos;
+
+	offs = ieee80211_ie_split(ies, len,
+				  before_ds_params,
+				  ARRAY_SIZE(before_ds_params),
+				  0);
+
+	memcpy(newpos, ies, offs);
+	newpos += offs;
+
+	/* Add a placeholder for DS Parameter Set element */
+	*newpos++ = WLAN_EID_DS_PARAMS;
+	*newpos++ = 1;
+	*newpos++ = 0;
+
+	memcpy(newpos, ies + offs, len - offs);
+	newpos += len - offs;
+
+	return newpos;
+}
+
+static void
+iwl_mld_scan_add_tpc_report_elem(u8 *pos)
+{
+	pos[0] = WLAN_EID_VENDOR_SPECIFIC;
+	pos[1] = WFA_TPC_IE_LEN - 2;
+	pos[2] = (WLAN_OUI_MICROSOFT >> 16) & 0xff;
+	pos[3] = (WLAN_OUI_MICROSOFT >> 8) & 0xff;
+	pos[4] = WLAN_OUI_MICROSOFT & 0xff;
+	pos[5] = WLAN_OUI_TYPE_MICROSOFT_TPC;
+	pos[6] = 0;
+	/* pos[7] - tx power will be inserted by the FW */
+	pos[7] = 0;
+	pos[8] = 0;
+}
+
+static u32
+iwl_mld_scan_ooc_priority(enum iwl_mld_scan_status scan_status)
+{
+	if (scan_status == IWL_MLD_SCAN_REGULAR)
+		return IWL_SCAN_PRIORITY_EXT_6;
+	if (scan_status == IWL_MLD_SCAN_INT_MLO)
+		return IWL_SCAN_PRIORITY_EXT_4;
+
+	return IWL_SCAN_PRIORITY_EXT_2;
+}
+
+static bool
+iwl_mld_scan_is_regular(struct iwl_mld_scan_params *params)
+{
+	return params->n_scan_plans == 1 &&
+		params->scan_plans[0].iterations == 1;
+}
+
+static bool
+iwl_mld_scan_is_fragmented(enum iwl_mld_scan_type type)
+{
+	return (type == IWL_SCAN_TYPE_FRAGMENTED ||
+		type == IWL_SCAN_TYPE_FAST_BALANCE);
+}
+
+static int
+iwl_mld_scan_uid_by_status(struct iwl_mld *mld, int status)
+{
+	for (int i = 0; i < ARRAY_SIZE(mld->scan.uid_status); i++)
+		if (mld->scan.uid_status[i] == status)
+			return i;
+
+	return -ENOENT;
+}
+
+static const char *
+iwl_mld_scan_ebs_status_str(enum iwl_scan_ebs_status status)
+{
+	switch (status) {
+	case IWL_SCAN_EBS_SUCCESS:
+		return "successful";
+	case IWL_SCAN_EBS_INACTIVE:
+		return "inactive";
+	case IWL_SCAN_EBS_FAILED:
+	case IWL_SCAN_EBS_CHAN_NOT_FOUND:
+	default:
+		return "failed";
+	}
+}
+
+static int
+iwl_mld_scan_ssid_exist(u8 *ssid, u8 ssid_len, struct iwl_ssid_ie *ssid_list)
+{
+	for (int i = 0; i < PROBE_OPTION_MAX; i++) {
+		if (!ssid_list[i].len)
+			return -1;
+		if (ssid_list[i].len == ssid_len &&
+		    !memcmp(ssid_list[i].ssid, ssid, ssid_len))
+			return i;
+	}
+
+	return -1;
+}
+
+static bool
+iwl_mld_scan_fits(struct iwl_mld *mld, int n_ssids,
+		  struct ieee80211_scan_ies *ies, int n_channels)
+{
+	return ((n_ssids <= PROBE_OPTION_MAX) &&
+		(n_channels <= mld->fw->ucode_capa.n_scan_channels) &
+		(ies->common_ie_len + ies->len[NL80211_BAND_2GHZ] +
+		 ies->len[NL80211_BAND_5GHZ] + ies->len[NL80211_BAND_6GHZ] <=
+		 iwl_mld_scan_max_template_size()));
+}
+
+static void
+iwl_mld_scan_build_probe_req(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			     struct ieee80211_scan_ies *ies,
+			     struct iwl_mld_scan_params *params)
+{
+	struct ieee80211_mgmt *frame = (void *)params->preq.buf;
+	u8 *pos, *newpos;
+	const u8 *mac_addr = params->flags & NL80211_SCAN_FLAG_RANDOM_ADDR ?
+		params->mac_addr : NULL;
+
+	if (mac_addr)
+		get_random_mask_addr(frame->sa, mac_addr,
+				     params->mac_addr_mask);
+	else
+		memcpy(frame->sa, vif->addr, ETH_ALEN);
+
+	frame->frame_control = cpu_to_le16(IEEE80211_STYPE_PROBE_REQ);
+	eth_broadcast_addr(frame->da);
+	ether_addr_copy(frame->bssid, params->bssid);
+	frame->seq_ctrl = 0;
+
+	pos = frame->u.probe_req.variable;
+	*pos++ = WLAN_EID_SSID;
+	*pos++ = 0;
+
+	params->preq.mac_header.offset = 0;
+	params->preq.mac_header.len = cpu_to_le16(24 + 2);
+
+	/* Insert DS parameter set element on 2.4 GHz band */
+	newpos = iwl_mld_scan_add_2ghz_elems(mld,
+					     ies->ies[NL80211_BAND_2GHZ],
+					     ies->len[NL80211_BAND_2GHZ],
+					     pos);
+	params->preq.band_data[0].offset = cpu_to_le16(pos - params->preq.buf);
+	params->preq.band_data[0].len = cpu_to_le16(newpos - pos);
+	pos = newpos;
+
+	memcpy(pos, ies->ies[NL80211_BAND_5GHZ],
+	       ies->len[NL80211_BAND_5GHZ]);
+	params->preq.band_data[1].offset = cpu_to_le16(pos - params->preq.buf);
+	params->preq.band_data[1].len =
+	    cpu_to_le16(ies->len[NL80211_BAND_5GHZ]);
+	pos += ies->len[NL80211_BAND_5GHZ];
+
+	memcpy(pos, ies->ies[NL80211_BAND_6GHZ],
+	       ies->len[NL80211_BAND_6GHZ]);
+	params->preq.band_data[2].offset = cpu_to_le16(pos - params->preq.buf);
+	params->preq.band_data[2].len =
+		cpu_to_le16(ies->len[NL80211_BAND_6GHZ]);
+	pos += ies->len[NL80211_BAND_6GHZ];
+
+	memcpy(pos, ies->common_ies, ies->common_ie_len);
+	params->preq.common_data.offset = cpu_to_le16(pos - params->preq.buf);
+
+	iwl_mld_scan_add_tpc_report_elem(pos + ies->common_ie_len);
+	params->preq.common_data.len = cpu_to_le16(ies->common_ie_len +
+						   WFA_TPC_IE_LEN);
+}
+
+static u16
+iwl_mld_scan_get_cmd_gen_flags(struct iwl_mld *mld,
+			       struct iwl_mld_scan_params *params,
+			       struct ieee80211_vif *vif,
+			       enum iwl_mld_scan_status scan_status)
+{
+	u16 flags = 0;
+
+	/* If no direct SSIDs are provided perform a passive scan. Otherwise,
+	 * if there is a single SSID which is not the broadcast SSID, assume
+	 * that the scan is intended for roaming purposes and thus enable Rx on
+	 * all chains to improve chances of hearing the beacons/probe responses.
+	 */
+	if (params->n_ssids == 0)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_FORCE_PASSIVE;
+	else if (params->n_ssids == 1 && params->ssids[0].ssid_len)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_USE_ALL_RX_CHAINS;
+
+	if (params->pass_all)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_PASS_ALL;
+	else
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_MATCH;
+
+	if (iwl_mld_scan_is_fragmented(params->type))
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_FRAGMENTED_LMAC1;
+
+	if (!iwl_mld_scan_is_regular(params))
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_PERIODIC;
+
+	if (params->iter_notif ||
+	    mld->scan.pass_all_sched_res == SCHED_SCAN_PASS_ALL_STATE_ENABLED)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_NTFY_ITER_COMPLETE;
+
+	if (scan_status == IWL_MLD_SCAN_SCHED ||
+	    scan_status == IWL_MLD_SCAN_NETDETECT)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_PREEMPTIVE;
+
+	if (params->flags & (NL80211_SCAN_FLAG_ACCEPT_BCAST_PROBE_RESP |
+			     NL80211_SCAN_FLAG_OCE_PROBE_REQ_HIGH_TX_RATE |
+			     NL80211_SCAN_FLAG_FILS_MAX_CHANNEL_TIME))
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_OCE;
+
+	if ((scan_status == IWL_MLD_SCAN_SCHED ||
+	     scan_status == IWL_MLD_SCAN_NETDETECT) &&
+	    params->flags & NL80211_SCAN_FLAG_COLOCATED_6GHZ)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_TRIGGER_UHB_SCAN;
+
+	if (params->enable_6ghz_passive)
+		flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_6GHZ_PASSIVE_SCAN;
+
+	flags |= IWL_UMAC_SCAN_GEN_FLAGS_V2_ADAPTIVE_DWELL;
+
+	return flags;
+}
+
+static u8
+iwl_mld_scan_get_cmd_gen_flags2(struct iwl_mld *mld,
+				struct iwl_mld_scan_params *params,
+				struct ieee80211_vif *vif, u16 gen_flags)
+{
+	u8 flags = 0;
+
+	/* TODO: CDB */
+	if (params->respect_p2p_go)
+		flags |= IWL_UMAC_SCAN_GEN_PARAMS_FLAGS2_RESPECT_P2P_GO_LB |
+			IWL_UMAC_SCAN_GEN_PARAMS_FLAGS2_RESPECT_P2P_GO_HB;
+
+	if (params->scan_6ghz)
+		flags |= IWL_UMAC_SCAN_GEN_PARAMS_FLAGS2_DONT_TOGGLE_ANT;
+
+	return flags;
+}
+
+static void
+iwl_mld_scan_cmd_set_dwell(struct iwl_mld *mld,
+			   struct iwl_scan_general_params_v11 *gp,
+			   struct iwl_mld_scan_params *params)
+{
+	const struct iwl_mld_scan_timing_params *timing =
+		&scan_timing[params->type];
+
+	gp->adwell_default_social_chn =
+	    IWL_SCAN_ADWELL_DEFAULT_N_APS_SOCIAL;
+	gp->adwell_default_2g = IWL_SCAN_ADWELL_DEFAULT_LB_N_APS;
+	gp->adwell_default_5g = IWL_SCAN_ADWELL_DEFAULT_HB_N_APS;
+
+	if (params->n_ssids && params->ssids[0].ssid_len)
+		gp->adwell_max_budget =
+			cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_DIRECTED_SCAN);
+	else
+		gp->adwell_max_budget =
+			cpu_to_le16(IWL_SCAN_ADWELL_MAX_BUDGET_FULL_SCAN);
+
+	gp->scan_priority = cpu_to_le32(IWL_SCAN_PRIORITY_EXT_6);
+
+	gp->max_out_of_time[SCAN_LB_LMAC_IDX] = cpu_to_le32(timing->max_out_time);
+	gp->suspend_time[SCAN_LB_LMAC_IDX] = cpu_to_le32(timing->suspend_time);
+
+	gp->active_dwell[SCAN_LB_LMAC_IDX] = IWL_SCAN_DWELL_ACTIVE;
+	gp->passive_dwell[SCAN_LB_LMAC_IDX] = IWL_SCAN_DWELL_PASSIVE;
+	gp->active_dwell[SCAN_HB_LMAC_IDX] = IWL_SCAN_DWELL_ACTIVE;
+	gp->passive_dwell[SCAN_HB_LMAC_IDX] = IWL_SCAN_DWELL_PASSIVE;
+
+	IWL_DEBUG_SCAN(mld,
+		       "Scan: adwell_max_budget=%d max_out_of_time=%d suspend_time=%d\n",
+		       gp->adwell_max_budget,
+		       gp->max_out_of_time[SCAN_LB_LMAC_IDX],
+		       gp->suspend_time[SCAN_LB_LMAC_IDX]);
+}
+
+static void
+iwl_mld_scan_cmd_set_gen_params(struct iwl_mld *mld,
+				struct iwl_mld_scan_params *params,
+				struct ieee80211_vif *vif,
+				struct iwl_scan_general_params_v11 *gp,
+				enum iwl_mld_scan_status scan_status)
+{
+	u16 gen_flags = iwl_mld_scan_get_cmd_gen_flags(mld, params, vif,
+						       scan_status);
+	u8 gen_flags2 = iwl_mld_scan_get_cmd_gen_flags2(mld, params, vif,
+							gen_flags);
+
+	IWL_DEBUG_SCAN(mld, "General: flags=0x%x, flags2=0x%x\n",
+		       gen_flags, gen_flags2);
+
+	gp->flags = cpu_to_le16(gen_flags);
+	gp->flags2 = gen_flags2;
+
+	iwl_mld_scan_cmd_set_dwell(mld, gp, params);
+
+	if (gen_flags & IWL_UMAC_SCAN_GEN_FLAGS_V2_FRAGMENTED_LMAC1)
+		gp->num_of_fragments[SCAN_LB_LMAC_IDX] = IWL_SCAN_NUM_OF_FRAGS;
+
+	if (params->fw_link_id != IWL_MLD_INVALID_FW_ID)
+		gp->scan_start_mac_or_link_id = params->fw_link_id;
+}
+
+static int
+iwl_mld_scan_cmd_set_sched_params(struct iwl_mld_scan_params *params,
+				  struct iwl_scan_umac_schedule *schedule,
+				  __le16 *delay)
+{
+	if (WARN_ON(!params->n_scan_plans ||
+		    params->n_scan_plans > IWL_MAX_SCHED_SCAN_PLANS))
+		return -EINVAL;
+
+	for (int i = 0; i < params->n_scan_plans; i++) {
+		struct cfg80211_sched_scan_plan *scan_plan =
+		    &params->scan_plans[i];
+
+		schedule[i].iter_count = scan_plan->iterations;
+		schedule[i].interval =
+		    cpu_to_le16(scan_plan->interval);
+	}
+
+	/* If the number of iterations of the last scan plan is set to zero,
+	 * it should run infinitely. However, this is not always the case.
+	 * For example, when regular scan is requested the driver sets one scan
+	 * plan with one iteration.
+	 */
+	if (!schedule[params->n_scan_plans - 1].iter_count)
+		schedule[params->n_scan_plans - 1].iter_count = 0xff;
+
+	*delay = cpu_to_le16(params->delay);
+
+	return 0;
+}
+
+/* We insert the SSIDs in an inverted order, because the FW will
+ * invert it back.
+ */
+static void
+iwl_mld_scan_cmd_build_ssids(struct iwl_mld_scan_params *params,
+			     struct iwl_ssid_ie *ssids, u32 *ssid_bitmap)
+{
+	int i, j;
+	int index;
+	u32 tmp_bitmap = 0;
+
+	/* copy SSIDs from match list. iwl_config_sched_scan_profiles()
+	 * uses the order of these ssids to config match list.
+	 */
+	for (i = 0, j = params->n_match_sets - 1;
+	     j >= 0 && i < PROBE_OPTION_MAX;
+	     i++, j--) {
+		/* skip empty SSID match_sets */
+		if (!params->match_sets[j].ssid.ssid_len)
+			continue;
+
+		ssids[i].id = WLAN_EID_SSID;
+		ssids[i].len = params->match_sets[j].ssid.ssid_len;
+		memcpy(ssids[i].ssid, params->match_sets[j].ssid.ssid,
+		       ssids[i].len);
+	}
+
+	/* add SSIDs from scan SSID list */
+	for (j = params->n_ssids - 1;
+	     j >= 0 && i < PROBE_OPTION_MAX;
+	     i++, j--) {
+		index = iwl_mld_scan_ssid_exist(params->ssids[j].ssid,
+						params->ssids[j].ssid_len,
+						ssids);
+		if (index < 0) {
+			ssids[i].id = WLAN_EID_SSID;
+			ssids[i].len = params->ssids[j].ssid_len;
+			memcpy(ssids[i].ssid, params->ssids[j].ssid,
+			       ssids[i].len);
+			tmp_bitmap |= BIT(i);
+		} else {
+			tmp_bitmap |= BIT(index);
+		}
+	}
+
+	if (ssid_bitmap)
+		*ssid_bitmap = tmp_bitmap;
+}
+
+static void
+iwl_mld_scan_fill_6g_chan_list(struct iwl_mld_scan_params *params,
+			       struct iwl_scan_probe_params_v4 *pp)
+{
+	int j, idex_s = 0, idex_b = 0;
+	struct cfg80211_scan_6ghz_params *scan_6ghz_params =
+		params->scan_6ghz_params;
+
+	for (j = 0;
+	     j < params->n_ssids && idex_s < SCAN_SHORT_SSID_MAX_SIZE;
+	     j++) {
+		if (!params->ssids[j].ssid_len)
+			continue;
+
+		pp->short_ssid[idex_s] =
+			cpu_to_le32(~crc32_le(~0, params->ssids[j].ssid,
+					      params->ssids[j].ssid_len));
+
+		/* hidden 6ghz scan */
+		pp->direct_scan[idex_s].id = WLAN_EID_SSID;
+		pp->direct_scan[idex_s].len = params->ssids[j].ssid_len;
+		memcpy(pp->direct_scan[idex_s].ssid, params->ssids[j].ssid,
+		       params->ssids[j].ssid_len);
+		idex_s++;
+	}
+
+	/* Populate the arrays of the short SSIDs and the BSSIDs using the 6GHz
+	 * collocated parameters. This might not be optimal, as this processing
+	 * does not (yet) correspond to the actual channels, so it is possible
+	 * that some entries would be left out.
+	 */
+	for (j = 0; j < params->n_6ghz_params; j++) {
+		int k;
+
+		/* First, try to place the short SSID */
+		if (scan_6ghz_params[j].short_ssid_valid) {
+			for (k = 0; k < idex_s; k++) {
+				if (pp->short_ssid[k] ==
+				    cpu_to_le32(scan_6ghz_params[j].short_ssid))
+					break;
+			}
+
+			if (k == idex_s && idex_s < SCAN_SHORT_SSID_MAX_SIZE) {
+				pp->short_ssid[idex_s++] =
+					cpu_to_le32(scan_6ghz_params[j].short_ssid);
+			}
+		}
+
+		/* try to place BSSID for the same entry */
+		for (k = 0; k < idex_b; k++) {
+			if (!memcmp(&pp->bssid_array[k],
+				    scan_6ghz_params[j].bssid, ETH_ALEN))
+				break;
+		}
+
+		if (k == idex_b && idex_b < SCAN_BSSID_MAX_SIZE &&
+		    !WARN_ONCE(!is_valid_ether_addr(scan_6ghz_params[j].bssid),
+			       "scan: invalid BSSID at index %u, index_b=%u\n",
+			       j, idex_b)) {
+			memcpy(&pp->bssid_array[idex_b++],
+			       scan_6ghz_params[j].bssid, ETH_ALEN);
+		}
+	}
+
+	pp->short_ssid_num = idex_s;
+	pp->bssid_num = idex_b;
+}
+
+static void
+iwl_mld_scan_cmd_set_probe_params(struct iwl_mld_scan_params *params,
+				  struct iwl_scan_probe_params_v4 *pp,
+				  u32 *bitmap_ssid)
+{
+	pp->preq = params->preq;
+
+	if (params->scan_6ghz) {
+		iwl_mld_scan_fill_6g_chan_list(params, pp);
+		return;
+	}
+
+	/* relevant only for 2.4 GHz /5 GHz scan */
+	iwl_mld_scan_cmd_build_ssids(params, pp->direct_scan, bitmap_ssid);
+}
+
+static bool
+iwl_mld_scan_use_ebs(struct iwl_mld *mld, struct ieee80211_vif *vif,
+		     bool low_latency)
+{
+	const struct iwl_ucode_capabilities *capa = &mld->fw->ucode_capa;
+
+	/* We can only use EBS if:
+	 *	1. the feature is supported.
+	 *	2. the last EBS was successful.
+	 *	3. it's not a p2p find operation.
+	 *	4. we are not in low latency mode,
+	 *	   or if fragmented ebs is supported by the FW
+	 *	5. the VIF is not an AP interface (scan wants survey results)
+	 */
+	return ((capa->flags & IWL_UCODE_TLV_FLAGS_EBS_SUPPORT) &&
+		!mld->scan.last_ebs_failed &&
+		vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+		(!low_latency || fw_has_api(capa, IWL_UCODE_TLV_API_FRAG_EBS)) &&
+		ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_AP);
+}
+
+static u8
+iwl_mld_scan_cmd_set_chan_flags(struct iwl_mld *mld,
+				struct iwl_mld_scan_params *params,
+				struct ieee80211_vif *vif,
+				bool low_latency)
+{
+	u8 flags = 0;
+
+	flags |= IWL_SCAN_CHANNEL_FLAG_ENABLE_CHAN_ORDER;
+
+	if (iwl_mld_scan_use_ebs(mld, vif, low_latency))
+		flags |= IWL_SCAN_CHANNEL_FLAG_EBS |
+			 IWL_SCAN_CHANNEL_FLAG_EBS_ACCURATE |
+			 IWL_SCAN_CHANNEL_FLAG_CACHE_ADD;
+
+	/* set fragmented ebs for fragmented scan */
+	if (iwl_mld_scan_is_fragmented(params->type))
+		flags |= IWL_SCAN_CHANNEL_FLAG_EBS_FRAG;
+
+	/* Force EBS in case the scan is a fragmented and there is a need
+	 * to take P2P GO operation into consideration during scan operation.
+	 */
+	/* TODO: CDB */
+	if (iwl_mld_scan_is_fragmented(params->type) &&
+	    params->respect_p2p_go) {
+		IWL_DEBUG_SCAN(mld, "Respect P2P GO. Force EBS\n");
+		flags |= IWL_SCAN_CHANNEL_FLAG_FORCE_EBS;
+	}
+
+	return flags;
+}
+
+static const u8 p2p_go_friendly_chs[] = {
+	36, 40, 44, 48, 149, 153, 157, 161, 165,
+};
+
+static const u8 social_chs[] = {
+	1, 6, 11
+};
+
+static u32 iwl_mld_scan_ch_n_aps_flag(enum nl80211_iftype vif_type, u8 ch_id)
+{
+	if (vif_type != NL80211_IFTYPE_P2P_DEVICE)
+		return 0;
+
+	for (int i = 0; i < ARRAY_SIZE(p2p_go_friendly_chs); i++) {
+		if (ch_id == p2p_go_friendly_chs[i])
+			return IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY_BIT;
+	}
+
+	for (int i = 0; i < ARRAY_SIZE(social_chs); i++) {
+		if (ch_id == social_chs[i])
+			return IWL_SCAN_ADWELL_N_APS_SOCIAL_CHS_BIT;
+	}
+
+	return 0;
+}
+
+static void
+iwl_mld_scan_cmd_set_channels(struct iwl_mld *mld,
+			      struct ieee80211_channel **channels,
+			      struct iwl_scan_channel_params_v7 *cp,
+			      int n_channels, u32 flags,
+			      enum nl80211_iftype vif_type)
+{
+	for (int i = 0; i < n_channels; i++) {
+		enum nl80211_band band = channels[i]->band;
+		struct iwl_scan_channel_cfg_umac *cfg = &cp->channel_config[i];
+		u8 iwl_band = iwl_mld_nl80211_band_to_fw(band);
+		u32 n_aps_flag =
+			iwl_mld_scan_ch_n_aps_flag(vif_type,
+						   channels[i]->hw_value);
+
+		if (IWL_MLD_ADAPTIVE_DWELL_NUM_APS_OVERRIDE)
+			n_aps_flag = IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY_BIT;
+
+		cfg->flags = cpu_to_le32(flags | n_aps_flag);
+		cfg->channel_num = channels[i]->hw_value;
+		if (cfg80211_channel_is_psc(channels[i]))
+			cfg->flags = 0;
+
+		if (band == NL80211_BAND_6GHZ) {
+			/* 6 GHz channels should only appear in a scan request
+			 * that has scan_6ghz set. The only exception is MLO
+			 * scan, which has to be passive.
+			 */
+			WARN_ON_ONCE(cfg->flags != 0);
+			cfg->flags =
+				cpu_to_le32(IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE);
+		}
+
+		cfg->v2.iter_count = 1;
+		cfg->v2.iter_interval = 0;
+		cfg->flags |= cpu_to_le32(iwl_band <<
+					  IWL_CHAN_CFG_FLAGS_BAND_POS);
+	}
+}
+
+static u8
+iwl_mld_scan_cfg_channels_6g(struct iwl_mld *mld,
+			     struct iwl_mld_scan_params *params,
+			     u32 n_channels,
+			     struct iwl_scan_probe_params_v4 *pp,
+			     struct iwl_scan_channel_params_v7 *cp,
+			     enum nl80211_iftype vif_type)
+{
+	struct cfg80211_scan_6ghz_params *scan_6ghz_params =
+		params->scan_6ghz_params;
+	u32 i;
+	u8 ch_cnt;
+
+	for (i = 0, ch_cnt = 0; i < params->n_channels; i++) {
+		struct iwl_scan_channel_cfg_umac *cfg =
+			&cp->channel_config[ch_cnt];
+
+		u32 s_ssid_bitmap = 0, bssid_bitmap = 0, flags = 0;
+		u8 k, n_s_ssids = 0, n_bssids = 0;
+		u8 max_s_ssids, max_bssids;
+		bool force_passive = false, found = false, allow_passive = true,
+		     unsolicited_probe_on_chan = false, psc_no_listen = false;
+		s8 psd_20 = IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED;
+
+		/* Avoid performing passive scan on non PSC channels unless the
+		 * scan is specifically a passive scan, i.e., no SSIDs
+		 * configured in the scan command.
+		 */
+		if (!cfg80211_channel_is_psc(params->channels[i]) &&
+		    !params->n_6ghz_params && params->n_ssids)
+			continue;
+
+		cfg->channel_num = params->channels[i]->hw_value;
+		cfg->flags |=
+			cpu_to_le32(PHY_BAND_6 << IWL_CHAN_CFG_FLAGS_BAND_POS);
+
+		cfg->v5.iter_count = 1;
+		cfg->v5.iter_interval = 0;
+
+		for (u32 j = 0; j < params->n_6ghz_params; j++) {
+			s8 tmp_psd_20;
+
+			if (!(scan_6ghz_params[j].channel_idx == i))
+				continue;
+
+			unsolicited_probe_on_chan |=
+				scan_6ghz_params[j].unsolicited_probe;
+
+			/* Use the highest PSD value allowed as advertised by
+			 * APs for this channel
+			 */
+			tmp_psd_20 = scan_6ghz_params[j].psd_20;
+			if (tmp_psd_20 !=
+			    IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED &&
+			    (psd_20 ==
+			     IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED ||
+			     psd_20 < tmp_psd_20))
+				psd_20 = tmp_psd_20;
+
+			psc_no_listen |= scan_6ghz_params[j].psc_no_listen;
+		}
+
+		/* In the following cases apply passive scan:
+		 * 1. Non fragmented scan:
+		 *	- PSC channel with NO_LISTEN_FLAG on should be treated
+		 *	  like non PSC channel
+		 *	- Non PSC channel with more than 3 short SSIDs or more
+		 *	  than 9 BSSIDs.
+		 *	- Non PSC Channel with unsolicited probe response and
+		 *	  more than 2 short SSIDs or more than 6 BSSIDs.
+		 *	- PSC channel with more than 2 short SSIDs or more than
+		 *	  6 BSSIDs.
+		 * 2. Fragmented scan:
+		 *	- PSC channel with more than 1 SSID or 3 BSSIDs.
+		 *	- Non PSC channel with more than 2 SSIDs or 6 BSSIDs.
+		 *	- Non PSC channel with unsolicited probe response and
+		 *	  more than 1 SSID or more than 3 BSSIDs.
+		 */
+		if (!iwl_mld_scan_is_fragmented(params->type)) {
+			if (!cfg80211_channel_is_psc(params->channels[i]) ||
+			    psc_no_listen) {
+				if (unsolicited_probe_on_chan) {
+					max_s_ssids = 2;
+					max_bssids = 6;
+				} else {
+					max_s_ssids = 3;
+					max_bssids = 9;
+				}
+			} else {
+				max_s_ssids = 2;
+				max_bssids = 6;
+			}
+		} else if (cfg80211_channel_is_psc(params->channels[i])) {
+			max_s_ssids = 1;
+			max_bssids = 3;
+		} else {
+			if (unsolicited_probe_on_chan) {
+				max_s_ssids = 1;
+				max_bssids = 3;
+			} else {
+				max_s_ssids = 2;
+				max_bssids = 6;
+			}
+		}
+
+		/* To optimize the scan time, i.e., reduce the scan dwell time
+		 * on each channel, the below logic tries to set 3 direct BSSID
+		 * probe requests for each broadcast probe request with a short
+		 * SSID.
+		 */
+		for (u32 j = 0; j < params->n_6ghz_params; j++) {
+			if (!(scan_6ghz_params[j].channel_idx == i))
+				continue;
+
+			found = false;
+
+			for (k = 0;
+			     k < pp->short_ssid_num && n_s_ssids < max_s_ssids;
+			     k++) {
+				if (!scan_6ghz_params[j].unsolicited_probe &&
+				    le32_to_cpu(pp->short_ssid[k]) ==
+				    scan_6ghz_params[j].short_ssid) {
+					/* Relevant short SSID bit set */
+					if (s_ssid_bitmap & BIT(k)) {
+						found = true;
+						break;
+					}
+
+					/* Prefer creating BSSID entries unless
+					 * the short SSID probe can be done in
+					 * the same channel dwell iteration.
+					 *
+					 * We also need to create a short SSID
+					 * entry for any hidden AP.
+					 */
+					if (3 * n_s_ssids > n_bssids &&
+					    !pp->direct_scan[k].len)
+						break;
+
+					/* Hidden AP, cannot do passive scan */
+					if (pp->direct_scan[k].len)
+						allow_passive = false;
+
+					s_ssid_bitmap |= BIT(k);
+					n_s_ssids++;
+					found = true;
+					break;
+				}
+			}
+
+			if (found)
+				continue;
+
+			for (k = 0; k < pp->bssid_num; k++) {
+				if (memcmp(&pp->bssid_array[k],
+					   scan_6ghz_params[j].bssid,
+					   ETH_ALEN))
+					continue;
+
+				if (bssid_bitmap & BIT(k))
+					break;
+
+				if (n_bssids < max_bssids) {
+					bssid_bitmap |= BIT(k);
+					n_bssids++;
+				} else {
+					force_passive = TRUE;
+				}
+
+				break;
+			}
+		}
+
+		if (cfg80211_channel_is_psc(params->channels[i]) &&
+		    psc_no_listen)
+			flags |= IWL_UHB_CHAN_CFG_FLAG_PSC_CHAN_NO_LISTEN;
+
+		if (unsolicited_probe_on_chan)
+			flags |= IWL_UHB_CHAN_CFG_FLAG_UNSOLICITED_PROBE_RES;
+
+		if ((allow_passive && force_passive) ||
+		    (!(bssid_bitmap | s_ssid_bitmap) &&
+		     !cfg80211_channel_is_psc(params->channels[i])))
+			flags |= IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE;
+		else
+			flags |= bssid_bitmap | (s_ssid_bitmap << 16);
+
+		cfg->flags |= cpu_to_le32(flags);
+		cfg->v5.psd_20 = psd_20;
+
+		ch_cnt++;
+	}
+
+	if (params->n_channels > ch_cnt)
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz: reducing number channels: (%u->%u)\n",
+			       params->n_channels, ch_cnt);
+
+	return ch_cnt;
+}
+
+static int
+iwl_mld_scan_cmd_set_6ghz_chan_params(struct iwl_mld *mld,
+				      struct iwl_mld_scan_params *params,
+				      struct ieee80211_vif *vif,
+				      struct iwl_scan_req_params_v17 *scan_p,
+				      enum iwl_mld_scan_status scan_status)
+{
+	struct iwl_scan_channel_params_v7 *chan_p = &scan_p->channel_params;
+	struct iwl_scan_probe_params_v4 *probe_p = &scan_p->probe_params;
+
+	chan_p->flags = iwl_mld_scan_get_cmd_gen_flags(mld, params, vif,
+						       scan_status);
+	chan_p->count = iwl_mld_scan_cfg_channels_6g(mld, params,
+						     params->n_channels,
+						     probe_p, chan_p,
+						     vif->type);
+	if (!chan_p->count)
+		return -EINVAL;
+
+	if (!params->n_ssids ||
+	    (params->n_ssids == 1 && !params->ssids[0].ssid_len))
+		chan_p->flags |= IWL_SCAN_CHANNEL_FLAG_6G_PSC_NO_FILTER;
+
+	return 0;
+}
+
+static int
+iwl_mld_scan_cmd_set_chan_params(struct iwl_mld *mld,
+				 struct iwl_mld_scan_params *params,
+				 struct ieee80211_vif *vif,
+				 struct iwl_scan_req_params_v17 *scan_p,
+				 bool low_latency,
+				 enum iwl_mld_scan_status scan_status,
+				 u32 channel_cfg_flags)
+{
+	struct iwl_scan_channel_params_v7 *cp = &scan_p->channel_params;
+	struct ieee80211_supported_band *sband =
+		&mld->nvm_data->bands[NL80211_BAND_6GHZ];
+
+	cp->n_aps_override[0] = IWL_SCAN_ADWELL_N_APS_GO_FRIENDLY;
+	cp->n_aps_override[1] = IWL_SCAN_ADWELL_N_APS_SOCIAL_CHS;
+
+	if (IWL_MLD_ADAPTIVE_DWELL_NUM_APS_OVERRIDE)
+		cp->n_aps_override[0] = IWL_MLD_ADAPTIVE_DWELL_NUM_APS_OVERRIDE;
+
+	if (params->scan_6ghz)
+		return iwl_mld_scan_cmd_set_6ghz_chan_params(mld, params,
+							     vif, scan_p,
+							     scan_status);
+
+	/* relevant only for 2.4 GHz/5 GHz scan */
+	cp->flags = iwl_mld_scan_cmd_set_chan_flags(mld, params, vif,
+						    low_latency);
+	cp->count = params->n_channels;
+
+	iwl_mld_scan_cmd_set_channels(mld, params->channels, cp,
+				      params->n_channels, channel_cfg_flags,
+				      vif->type);
+
+	if (!params->enable_6ghz_passive)
+		return 0;
+
+	/* fill 6 GHz passive scan cfg */
+	for (int i = 0; i < sband->n_channels; i++) {
+		struct ieee80211_channel *channel =
+			&sband->channels[i];
+		struct iwl_scan_channel_cfg_umac *cfg =
+			&cp->channel_config[cp->count];
+
+		if (!cfg80211_channel_is_psc(channel))
+			continue;
+
+		cfg->channel_num = channel->hw_value;
+		cfg->v5.iter_count = 1;
+		cfg->v5.iter_interval = 0;
+		cfg->v5.psd_20 =
+			IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED;
+		cfg->flags = cpu_to_le32(PHY_BAND_6 <<
+					 IWL_CHAN_CFG_FLAGS_BAND_POS);
+		cp->count++;
+	}
+
+	return 0;
+}
+
+static int
+iwl_mld_scan_build_cmd(struct iwl_mld *mld, struct ieee80211_vif *vif,
+		       struct iwl_mld_scan_params *params,
+		       enum iwl_mld_scan_status scan_status,
+		       bool low_latency)
+{
+	struct iwl_scan_req_umac_v17 *cmd = mld->scan.cmd;
+	struct iwl_scan_req_params_v17 *scan_p = &cmd->scan_params;
+	u32 bitmap_ssid = 0;
+	int uid, ret;
+
+	memset(mld->scan.cmd, 0, mld->scan.cmd_size);
+
+	/* find a free UID entry */
+	uid = iwl_mld_scan_uid_by_status(mld, IWL_MLD_SCAN_NONE);
+	if (uid < 0)
+		return uid;
+
+	cmd->uid = cpu_to_le32(uid);
+	cmd->ooc_priority =
+		cpu_to_le32(iwl_mld_scan_ooc_priority(scan_status));
+
+	iwl_mld_scan_cmd_set_gen_params(mld, params, vif,
+					&scan_p->general_params, scan_status);
+
+	ret = iwl_mld_scan_cmd_set_sched_params(params,
+						scan_p->periodic_params.schedule,
+						&scan_p->periodic_params.delay);
+	if (ret)
+		return ret;
+
+	iwl_mld_scan_cmd_set_probe_params(params, &scan_p->probe_params,
+					  &bitmap_ssid);
+
+	ret = iwl_mld_scan_cmd_set_chan_params(mld, params, vif, scan_p,
+					       low_latency, scan_status,
+					       bitmap_ssid);
+	if (ret)
+		return ret;
+
+	return uid;
+}
+
+static bool
+iwl_mld_scan_pass_all(struct iwl_mld *mld,
+		      struct cfg80211_sched_scan_request *req)
+{
+	if (req->n_match_sets && req->match_sets[0].ssid.ssid_len) {
+		IWL_DEBUG_SCAN(mld,
+			       "Sending scheduled scan with filtering, n_match_sets %d\n",
+			       req->n_match_sets);
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
+		return false;
+	}
+
+	IWL_DEBUG_SCAN(mld, "Sending Scheduled scan without filtering\n");
+	mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_ENABLED;
+
+	return true;
+}
+
+static int
+iwl_mld_config_sched_scan_profiles(struct iwl_mld *mld,
+				   struct cfg80211_sched_scan_request *req)
+{
+	struct iwl_host_cmd hcmd = {
+		.id = SCAN_OFFLOAD_UPDATE_PROFILES_CMD,
+		.dataflags[0] = IWL_HCMD_DFL_NOCOPY,
+	};
+	struct iwl_scan_offload_profile *profile;
+	struct iwl_scan_offload_profile_cfg_data *cfg_data;
+	struct iwl_scan_offload_profile_cfg *profile_cfg;
+	struct iwl_scan_offload_blocklist *blocklist;
+	u32 blocklist_size = IWL_SCAN_MAX_BLACKLIST_LEN * sizeof(*blocklist);
+	u32 cmd_size = blocklist_size + sizeof(*profile_cfg);
+	u8 *cmd;
+	int ret;
+
+	if (WARN_ON(req->n_match_sets > IWL_SCAN_MAX_PROFILES_V2))
+		return -EIO;
+
+	cmd = kzalloc(cmd_size, GFP_KERNEL);
+	if (!cmd)
+		return -ENOMEM;
+
+	hcmd.data[0] = cmd;
+	hcmd.len[0] = cmd_size;
+
+	blocklist = (struct iwl_scan_offload_blocklist *)cmd;
+	profile_cfg = (struct iwl_scan_offload_profile_cfg *)(cmd + blocklist_size);
+
+	/* No blocklist configuration */
+	cfg_data = &profile_cfg->data;
+	cfg_data->num_profiles = req->n_match_sets;
+	cfg_data->active_clients = SCAN_CLIENT_SCHED_SCAN;
+	cfg_data->pass_match = SCAN_CLIENT_SCHED_SCAN;
+	cfg_data->match_notify = SCAN_CLIENT_SCHED_SCAN;
+
+	if (!req->n_match_sets || !req->match_sets[0].ssid.ssid_len)
+		cfg_data->any_beacon_notify = SCAN_CLIENT_SCHED_SCAN;
+
+	for (int i = 0; i < req->n_match_sets; i++) {
+		profile = &profile_cfg->profiles[i];
+
+		/* Support any cipher and auth algorithm */
+		profile->unicast_cipher = 0xff;
+		profile->auth_alg = IWL_AUTH_ALGO_UNSUPPORTED |
+			IWL_AUTH_ALGO_NONE | IWL_AUTH_ALGO_PSK |
+			IWL_AUTH_ALGO_8021X | IWL_AUTH_ALGO_SAE |
+			IWL_AUTH_ALGO_8021X_SHA384 | IWL_AUTH_ALGO_OWE;
+		profile->network_type = IWL_NETWORK_TYPE_ANY;
+		profile->band_selection = IWL_SCAN_OFFLOAD_SELECT_ANY;
+		profile->client_bitmap = SCAN_CLIENT_SCHED_SCAN;
+		profile->ssid_index = i;
+	}
+
+	IWL_DEBUG_SCAN(mld,
+		       "Sending scheduled scan profile config (n_match_sets=%u)\n",
+		       req->n_match_sets);
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+
+	kfree(cmd);
+
+	return ret;
+}
+
+static int
+iwl_mld_sched_scan_handle_non_psc_channels(struct iwl_mld_scan_params *params,
+					   bool *non_psc_included)
+{
+	int i, j;
+
+	*non_psc_included = false;
+	/* for 6 GHZ band only PSC channels need to be added */
+	for (i = 0; i < params->n_channels; i++) {
+		struct ieee80211_channel *channel = params->channels[i];
+
+		if (channel->band == NL80211_BAND_6GHZ &&
+		    !cfg80211_channel_is_psc(channel)) {
+			*non_psc_included = true;
+			break;
+		}
+	}
+
+	if (!*non_psc_included)
+		return 0;
+
+	params->channels =
+		kmemdup(params->channels,
+			sizeof(params->channels[0]) * params->n_channels,
+			GFP_KERNEL);
+	if (!params->channels)
+		return -ENOMEM;
+
+	for (i = j = 0; i < params->n_channels; i++) {
+		if (params->channels[i]->band == NL80211_BAND_6GHZ &&
+		    !cfg80211_channel_is_psc(params->channels[i]))
+			continue;
+		params->channels[j++] = params->channels[i];
+	}
+
+	params->n_channels = j;
+
+	return 0;
+}
+
+static void
+iwl_mld_scan_6ghz_passive_scan(struct iwl_mld *mld,
+			       struct iwl_mld_scan_params *params,
+			       struct ieee80211_vif *vif)
+{
+	struct ieee80211_supported_band *sband =
+		&mld->nvm_data->bands[NL80211_BAND_6GHZ];
+	u32 n_disabled, i;
+
+	params->enable_6ghz_passive = false;
+
+	/* 6 GHz passive scan may be enabled in the first 2.4 GHz/5 GHz scan
+	 * phase to discover geo location if no AP's are found. Skip it when
+	 * we're in the 6 GHz scan phase.
+	 */
+	if (params->scan_6ghz)
+		return;
+
+	/* 6 GHz passive scan allowed only on station interface  */
+	if (vif->type != NL80211_IFTYPE_STATION) {
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz passive scan: not station interface\n");
+		return;
+	}
+
+	/* 6 GHz passive scan is allowed in a defined time interval following
+	 * HW reset or resume flow, or while not associated and a large
+	 * interval has passed since the last 6 GHz passive scan.
+	 */
+	if ((vif->cfg.assoc ||
+	     time_after(mld->scan.last_6ghz_passive_jiffies +
+			(IWL_MLD_6GHZ_PASSIVE_SCAN_TIMEOUT * HZ), jiffies)) &&
+	    (time_before(mld->scan.last_start_time_jiffies +
+			 (IWL_MLD_6GHZ_PASSIVE_SCAN_ASSOC_TIMEOUT * HZ),
+			 jiffies))) {
+		IWL_DEBUG_SCAN(mld, "6GHz passive scan: %s\n",
+			       vif->cfg.assoc ? "associated" :
+			       "timeout did not expire");
+		return;
+	}
+
+	/* not enough channels in the regular scan request */
+	if (params->n_channels < IWL_MLD_6GHZ_PASSIVE_SCAN_MIN_CHANS) {
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz passive scan: not enough channels %d\n",
+			       params->n_channels);
+		return;
+	}
+
+	for (i = 0; i < params->n_ssids; i++) {
+		if (!params->ssids[i].ssid_len)
+			break;
+	}
+
+	/* not a wildcard scan, so cannot enable passive 6 GHz scan */
+	if (i == params->n_ssids) {
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz passive scan: no wildcard SSID\n");
+		return;
+	}
+
+	if (!sband || !sband->n_channels) {
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz passive scan: no 6GHz channels\n");
+		return;
+	}
+
+	for (i = 0, n_disabled = 0; i < sband->n_channels; i++) {
+		if (sband->channels[i].flags & (IEEE80211_CHAN_DISABLED))
+			n_disabled++;
+	}
+
+	/* Not all the 6 GHz channels are disabled, so no need for 6 GHz
+	 * passive scan
+	 */
+	if (n_disabled != sband->n_channels) {
+		IWL_DEBUG_SCAN(mld,
+			       "6GHz passive scan: 6GHz channels enabled\n");
+		return;
+	}
+
+	/* all conditions to enable 6 GHz passive scan are satisfied */
+	IWL_DEBUG_SCAN(mld, "6GHz passive scan: can be enabled\n");
+	params->enable_6ghz_passive = true;
+}
+
+static void
+iwl_mld_scan_set_link_id(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			 struct iwl_mld_scan_params *params,
+			 s8 tsf_report_link_id,
+			 enum iwl_mld_scan_status scan_status)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link;
+
+	if (tsf_report_link_id < 0) {
+		if (vif->active_links)
+			tsf_report_link_id = __ffs(vif->active_links);
+		else
+			tsf_report_link_id = 0;
+	}
+
+	link = iwl_mld_link_dereference_check(mld_vif, tsf_report_link_id);
+	if (!WARN_ON(!link)) {
+		params->fw_link_id = link->fw_id;
+		/* we to store fw_link_id only for regular scan,
+		 * and use it in scan complete notif
+		 */
+		if (scan_status == IWL_MLD_SCAN_REGULAR)
+			mld->scan.fw_link_id = link->fw_id;
+	} else {
+		mld->scan.fw_link_id = IWL_MLD_INVALID_FW_ID;
+		params->fw_link_id = IWL_MLD_INVALID_FW_ID;
+	}
+}
+
+static int
+_iwl_mld_single_scan_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			   struct cfg80211_scan_request *req,
+			   struct ieee80211_scan_ies *ies,
+			   enum iwl_mld_scan_status scan_status)
+{
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(LONG_GROUP, SCAN_REQ_UMAC),
+		.len = { mld->scan.cmd_size, },
+		.data = { mld->scan.cmd, },
+		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
+	};
+	struct iwl_mld_scan_iter_data scan_iter_data = {
+		.current_vif = vif,
+	};
+	struct cfg80211_sched_scan_plan scan_plan = {.iterations = 1};
+	struct iwl_mld_scan_params params = {};
+	int ret, uid;
+
+	/* we should have failed registration if scan_cmd was NULL */
+	if (WARN_ON(!mld->scan.cmd))
+		return -ENOMEM;
+
+	if (!iwl_mld_scan_fits(mld, req->n_ssids, ies, req->n_channels))
+		return -ENOBUFS;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_scan_iterator,
+						&scan_iter_data);
+
+	params.type = iwl_mld_get_scan_type(mld, vif, &scan_iter_data);
+	params.n_ssids = req->n_ssids;
+	params.flags = req->flags;
+	params.n_channels = req->n_channels;
+	params.delay = 0;
+	params.ssids = req->ssids;
+	params.channels = req->channels;
+	params.mac_addr = req->mac_addr;
+	params.mac_addr_mask = req->mac_addr_mask;
+	params.no_cck = req->no_cck;
+	params.pass_all = true;
+	params.n_match_sets = 0;
+	params.match_sets = NULL;
+	params.scan_plans = &scan_plan;
+	params.n_scan_plans = 1;
+
+	params.n_6ghz_params = req->n_6ghz_params;
+	params.scan_6ghz_params = req->scan_6ghz_params;
+	params.scan_6ghz = req->scan_6ghz;
+
+	ether_addr_copy(params.bssid, req->bssid);
+	/* TODO: CDB - per-band flag */
+	params.respect_p2p_go =
+		iwl_mld_get_respect_p2p_go(mld, vif,
+					   scan_iter_data.global_low_latency);
+
+	if (req->duration)
+		params.iter_notif = true;
+
+	iwl_mld_scan_set_link_id(mld, vif, &params, req->tsf_report_link_id,
+				 scan_status);
+
+	iwl_mld_scan_build_probe_req(mld, vif, ies, &params);
+
+	iwl_mld_scan_6ghz_passive_scan(mld, &params, vif);
+
+	uid = iwl_mld_scan_build_cmd(mld, vif, &params, scan_status,
+				     scan_iter_data.global_low_latency);
+	if (uid < 0)
+		return uid;
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (ret) {
+		IWL_ERR(mld, "Scan failed! ret %d\n", ret);
+		return ret;
+	}
+
+	IWL_DEBUG_SCAN(mld, "Scan request send success: status=%u, uid=%u\n",
+		       scan_status, uid);
+
+	mld->scan.uid_status[uid] = scan_status;
+	mld->scan.status |= scan_status;
+
+	if (params.enable_6ghz_passive)
+		mld->scan.last_6ghz_passive_jiffies = jiffies;
+
+	return 0;
+}
+
+static int
+iwl_mld_scan_send_abort_cmd_status(struct iwl_mld *mld, int uid, u32 *status)
+{
+	struct iwl_umac_scan_abort abort_cmd = {
+		.uid = cpu_to_le32(uid),
+	};
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(LONG_GROUP, SCAN_ABORT_UMAC),
+		.flags = CMD_WANT_SKB,
+		.data = { &abort_cmd },
+		.len[0] = sizeof(abort_cmd),
+	};
+	struct iwl_rx_packet *pkt;
+	struct iwl_cmd_response *resp;
+	u32 resp_len;
+	int ret;
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret)
+		return ret;
+
+	pkt = cmd.resp_pkt;
+
+	resp_len = iwl_rx_packet_payload_len(pkt);
+	if (IWL_FW_CHECK(mld, resp_len != sizeof(*resp),
+			 "Scan Abort: unexpected response length %d\n",
+			 resp_len)) {
+		ret = -EIO;
+		goto out;
+	}
+
+	resp = (void *)pkt->data;
+	*status = le32_to_cpu(resp->status);
+
+out:
+	iwl_free_resp(&cmd);
+	return ret;
+}
+
+static int
+iwl_mld_scan_abort(struct iwl_mld *mld, int type, int uid, bool *wait)
+{
+	enum iwl_umac_scan_abort_status status;
+	int ret;
+
+	*wait = true;
+
+	IWL_DEBUG_SCAN(mld, "Sending scan abort, uid %u\n", uid);
+
+	ret = iwl_mld_scan_send_abort_cmd_status(mld, uid, &status);
+
+	IWL_DEBUG_SCAN(mld, "Scan abort: ret=%d status=%u\n", ret, status);
+
+	/* We don't need to wait to scan complete in the following cases:
+	 * 1. Driver failed to send the scan abort cmd.
+	 * 2. The FW is no longer familiar with the scan that needs to be
+	 *    stopped. It is expected that the scan complete notification was
+	 *    already received but not yet processed.
+	 *
+	 * In both cases the flow should continue similar to the case that the
+	 * scan was really aborted.
+	 */
+	if (ret || status == IWL_UMAC_SCAN_ABORT_STATUS_NOT_FOUND)
+		*wait = false;
+
+	return ret;
+}
+
+static int
+iwl_mld_scan_stop_wait(struct iwl_mld *mld, int type, int uid)
+{
+	struct iwl_notification_wait wait_scan_done;
+	static const u16 scan_comp_notif[] = { SCAN_COMPLETE_UMAC };
+	bool wait = true;
+	int ret;
+
+	iwl_init_notification_wait(&mld->notif_wait, &wait_scan_done,
+				   scan_comp_notif,
+				   ARRAY_SIZE(scan_comp_notif),
+				   NULL, NULL);
+
+	IWL_DEBUG_SCAN(mld, "Preparing to stop scan, type=%x\n", type);
+
+	ret = iwl_mld_scan_abort(mld, type, uid, &wait);
+	if (ret) {
+		IWL_DEBUG_SCAN(mld, "couldn't stop scan type=%d\n", type);
+		goto return_no_wait;
+	}
+
+	if (!wait) {
+		IWL_DEBUG_SCAN(mld, "no need to wait for scan type=%d\n", type);
+		goto return_no_wait;
+	}
+
+	return iwl_wait_notification(&mld->notif_wait, &wait_scan_done, HZ);
+
+return_no_wait:
+	iwl_remove_notification(&mld->notif_wait, &wait_scan_done);
+	return ret;
+}
+
+int iwl_mld_sched_scan_start(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct cfg80211_sched_scan_request *req,
+			     struct ieee80211_scan_ies *ies,
+			     int type)
+{
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(LONG_GROUP, SCAN_REQ_UMAC),
+		.len = { mld->scan.cmd_size, },
+		.data = { mld->scan.cmd, },
+		.dataflags = { IWL_HCMD_DFL_NOCOPY, },
+	};
+	struct iwl_mld_scan_params params = {};
+	struct iwl_mld_scan_iter_data scan_iter_data = {
+		.current_vif = vif,
+	};
+	bool non_psc_included = false;
+	int ret, uid;
+
+	/* we should have failed registration if scan_cmd was NULL */
+	if (WARN_ON(!mld->scan.cmd))
+		return -ENOMEM;
+
+	/* FW supports only a single periodic scan */
+	if (mld->scan.status & (IWL_MLD_SCAN_SCHED | IWL_MLD_SCAN_NETDETECT))
+		return -EBUSY;
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_scan_iterator,
+						&scan_iter_data);
+
+	params.type = iwl_mld_get_scan_type(mld, vif, &scan_iter_data);
+	params.flags = req->flags;
+	params.n_ssids = req->n_ssids;
+	params.ssids = req->ssids;
+	params.n_channels = req->n_channels;
+	params.channels = req->channels;
+	params.mac_addr = req->mac_addr;
+	params.mac_addr_mask = req->mac_addr_mask;
+	params.no_cck = false;
+	params.pass_all =  iwl_mld_scan_pass_all(mld, req);
+	params.n_match_sets = req->n_match_sets;
+	params.match_sets = req->match_sets;
+	params.n_scan_plans = req->n_scan_plans;
+	params.scan_plans = req->scan_plans;
+	/* TODO: CDB - per-band flag */
+	params.respect_p2p_go =
+		iwl_mld_get_respect_p2p_go(mld, vif,
+					   scan_iter_data.global_low_latency);
+
+	/* UMAC scan supports up to 16-bit delays, trim it down to 16-bits */
+	params.delay = req->delay > U16_MAX ? U16_MAX : req->delay;
+
+	eth_broadcast_addr(params.bssid);
+
+	ret = iwl_mld_config_sched_scan_profiles(mld, req);
+	if (ret)
+		return ret;
+
+	iwl_mld_scan_build_probe_req(mld, vif, ies, &params);
+
+	ret = iwl_mld_sched_scan_handle_non_psc_channels(&params,
+							 &non_psc_included);
+	if (ret)
+		goto out;
+
+	if (!iwl_mld_scan_fits(mld, req->n_ssids, ies, params.n_channels)) {
+		ret = -ENOBUFS;
+		goto out;
+	}
+
+	uid = iwl_mld_scan_build_cmd(mld, vif, &params, type,
+				     scan_iter_data.global_low_latency);
+	if (uid < 0) {
+		ret = uid;
+		goto out;
+	}
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (!ret) {
+		IWL_DEBUG_SCAN(mld,
+			       "Sched scan request send success: type=%u, uid=%u\n",
+			       type, uid);
+		mld->scan.uid_status[uid] = type;
+		mld->scan.status |= type;
+	} else {
+		IWL_ERR(mld, "Sched scan failed! ret %d\n", ret);
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
+	}
+
+out:
+	if (non_psc_included)
+		kfree(params.channels);
+	return ret;
+}
+
+int iwl_mld_scan_stop(struct iwl_mld *mld, int type, bool notify)
+{
+	int uid, ret;
+
+	IWL_DEBUG_SCAN(mld,
+		       "Request to stop scan: type=0x%x, status=0x%x\n",
+		       type, mld->scan.status);
+
+	if (!(mld->scan.status & type))
+		return 0;
+
+	uid = iwl_mld_scan_uid_by_status(mld, type);
+	/* must be valid, we just checked it's running */
+	if (WARN_ON_ONCE(uid < 0))
+		return uid;
+
+	ret = iwl_mld_scan_stop_wait(mld, type, uid);
+	if (ret)
+		IWL_DEBUG_SCAN(mld, "Failed to stop scan\n");
+
+	/* Clear the scan status so the next scan requests will
+	 * succeed and mark the scan as stopping, so that the Rx
+	 * handler doesn't do anything, as the scan was stopped from
+	 * above. Also remove the handler to not notify mac80211
+	 * erroneously after a new scan starts, for example.
+	 */
+	mld->scan.status &= ~type;
+	mld->scan.uid_status[uid] = IWL_MLD_SCAN_NONE;
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_SCAN,
+					       uid);
+
+	if (type == IWL_MLD_SCAN_REGULAR) {
+		if (notify) {
+			struct cfg80211_scan_info info = {
+				.aborted = true,
+			};
+
+			ieee80211_scan_completed(mld->hw, &info);
+		}
+	} else if (notify) {
+		ieee80211_sched_scan_stopped(mld->hw);
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
+	}
+
+	return ret;
+}
+
+int iwl_mld_regular_scan_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			       struct cfg80211_scan_request *req,
+			       struct ieee80211_scan_ies *ies)
+{
+	return _iwl_mld_single_scan_start(mld, vif, req, ies,
+					  IWL_MLD_SCAN_REGULAR);
+}
+
+static void iwl_mld_int_mlo_scan_start(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif,
+				       struct ieee80211_channel **channels,
+				       size_t n_channels)
+{
+	struct cfg80211_scan_request *req __free(kfree) = NULL;
+	struct ieee80211_scan_ies ies = {};
+	size_t size;
+	int ret;
+
+	IWL_DEBUG_SCAN(mld, "Starting Internal MLO scan: n_channels=%zu\n",
+		       n_channels);
+
+	size = struct_size(req, channels, n_channels);
+	req = kzalloc(size, GFP_KERNEL);
+	if (!req)
+		return;
+
+	/* set the requested channels */
+	for (int i = 0; i < n_channels; i++)
+		req->channels[i] = channels[i];
+
+	req->n_channels = n_channels;
+
+	/* set the rates */
+	for (int i = 0; i < NUM_NL80211_BANDS; i++)
+		if (mld->wiphy->bands[i])
+			req->rates[i] =
+				(1 << mld->wiphy->bands[i]->n_bitrates) - 1;
+
+	req->wdev = ieee80211_vif_to_wdev(vif);
+	req->wiphy = mld->wiphy;
+	req->scan_start = jiffies;
+	req->tsf_report_link_id = -1;
+
+	ret = _iwl_mld_single_scan_start(mld, vif, req, &ies,
+					 IWL_MLD_SCAN_INT_MLO);
+
+	IWL_DEBUG_SCAN(mld, "Internal MLO scan: ret=%d\n", ret);
+}
+
+void iwl_mld_int_mlo_scan(struct iwl_mld *mld, struct ieee80211_vif *vif)
+{
+	struct ieee80211_channel *channels[IEEE80211_MLD_MAX_NUM_LINKS];
+	unsigned long usable_links = ieee80211_vif_usable_links(vif);
+	size_t n_channels = 0;
+	u8 link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (!vif->cfg.assoc || !ieee80211_vif_is_mld(vif) ||
+	    hweight16(vif->valid_links) == 1)
+		return;
+
+	if (mld->scan.status & IWL_MLD_SCAN_INT_MLO) {
+		IWL_DEBUG_SCAN(mld, "Internal MLO scan is already running\n");
+		return;
+	}
+
+	for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *link_conf =
+			link_conf_dereference_check(vif, link_id);
+
+		if (WARN_ON_ONCE(!link_conf))
+			continue;
+
+		channels[n_channels++] = link_conf->chanreq.oper.chan;
+	}
+
+	if (!n_channels)
+		return;
+
+	iwl_mld_int_mlo_scan_start(mld, vif, channels, n_channels);
+}
+
+void iwl_mld_handle_scan_iter_complete_notif(struct iwl_mld *mld,
+					     struct iwl_rx_packet *pkt)
+{
+	struct iwl_umac_scan_iter_complete_notif *notif = (void *)pkt->data;
+	u32 uid = __le32_to_cpu(notif->uid);
+
+	if (IWL_FW_CHECK(mld, uid >= ARRAY_SIZE(mld->scan.uid_status),
+			 "FW reports out-of-range scan UID %d\n", uid))
+		return;
+
+	if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_REGULAR)
+		mld->scan.start_tsf = le64_to_cpu(notif->start_tsf);
+
+	IWL_DEBUG_SCAN(mld,
+		       "UMAC Scan iteration complete: status=0x%x scanned_channels=%d\n",
+		       notif->status, notif->scanned_channels);
+
+	if (mld->scan.pass_all_sched_res == SCHED_SCAN_PASS_ALL_STATE_FOUND) {
+		IWL_DEBUG_SCAN(mld, "Pass all scheduled scan results found\n");
+		ieee80211_sched_scan_results(mld->hw);
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_ENABLED;
+	}
+
+	IWL_DEBUG_SCAN(mld,
+		       "UMAC Scan iteration complete: scan started at %llu (TSF)\n",
+		       le64_to_cpu(notif->start_tsf));
+}
+
+void iwl_mld_handle_match_found_notif(struct iwl_mld *mld,
+				      struct iwl_rx_packet *pkt)
+{
+	IWL_DEBUG_SCAN(mld, "Scheduled scan results\n");
+	ieee80211_sched_scan_results(mld->hw);
+}
+
+void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt)
+{
+	struct iwl_umac_scan_complete *notif = (void *)pkt->data;
+	bool aborted = (notif->status == IWL_SCAN_OFFLOAD_ABORTED);
+	u32 uid = __le32_to_cpu(notif->uid);
+
+	if (IWL_FW_CHECK(mld, uid >= ARRAY_SIZE(mld->scan.uid_status),
+			 "FW reports out-of-range scan UID %d\n", uid))
+		return;
+
+	IWL_DEBUG_SCAN(mld,
+		       "Scan completed: uid=%u type=%u, status=%s, EBS=%s\n",
+		       uid, mld->scan.uid_status[uid],
+		       notif->status == IWL_SCAN_OFFLOAD_COMPLETED ?
+				"completed" : "aborted",
+		       iwl_mld_scan_ebs_status_str(notif->ebs_status));
+	IWL_DEBUG_SCAN(mld, "Scan completed: scan_status=0x%x\n",
+		       mld->scan.status);
+	IWL_DEBUG_SCAN(mld,
+		       "Scan completed: line=%u, iter=%u, elapsed time=%u\n",
+		       notif->last_schedule, notif->last_iter,
+		       __le32_to_cpu(notif->time_from_last_iter));
+
+	if (IWL_FW_CHECK(mld, !(mld->scan.uid_status[uid] & mld->scan.status),
+			 "FW reports scan UID %d we didn't trigger\n", uid))
+		return;
+
+	/* if the scan is already stopping, we don't need to notify mac80211 */
+	if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_REGULAR) {
+		struct cfg80211_scan_info info = {
+			.aborted = aborted,
+			.scan_start_tsf = mld->scan.start_tsf,
+		};
+		int fw_link_id = mld->scan.fw_link_id;
+		struct ieee80211_bss_conf *link_conf = NULL;
+
+		if (fw_link_id != IWL_MLD_INVALID_FW_ID)
+			link_conf =
+				wiphy_dereference(mld->wiphy,
+						  mld->fw_id_to_bss_conf[fw_link_id]);
+
+		/* It is possible that by the time the scan is complete the
+		 * link was already removed and is not valid.
+		 */
+		if (link_conf)
+			ether_addr_copy(info.tsf_bssid, link_conf->bssid);
+		else
+			IWL_DEBUG_SCAN(mld, "Scan link is no longer valid\n");
+
+		ieee80211_scan_completed(mld->hw, &info);
+	} else if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_SCHED) {
+		ieee80211_sched_scan_stopped(mld->hw);
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
+	} else if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_INT_MLO) {
+		IWL_DEBUG_SCAN(mld, "Internal MLO scan completed\n");
+		mld->scan.last_mlo_scan_jiffies = jiffies;
+
+		/*
+		 * We limit link selection to internal MLO scans as otherwise
+		 * we do not know whether all channels were covered.
+		 */
+		iwl_mld_select_links(mld);
+	}
+
+	mld->scan.status &= ~mld->scan.uid_status[uid];
+
+	IWL_DEBUG_SCAN(mld, "Scan completed: after update: scan_status=0x%x\n",
+		       mld->scan.status);
+
+	mld->scan.uid_status[uid] = IWL_MLD_SCAN_NONE;
+
+	if (notif->ebs_status != IWL_SCAN_EBS_SUCCESS &&
+	    notif->ebs_status != IWL_SCAN_EBS_INACTIVE)
+		mld->scan.last_ebs_failed = true;
+}
+
+/* This function is used in nic restart flow, to inform mac80211 about scans
+ * that were aborted by restart flow or by an assert.
+ */
+void iwl_mld_report_scan_aborted(struct iwl_mld *mld)
+{
+	int uid;
+
+	uid = iwl_mld_scan_uid_by_status(mld, IWL_MLD_SCAN_REGULAR);
+	if (uid >= 0) {
+		struct cfg80211_scan_info info = {
+			.aborted = true,
+		};
+
+		ieee80211_scan_completed(mld->hw, &info);
+		mld->scan.uid_status[uid] = IWL_MLD_SCAN_NONE;
+	}
+
+	uid = iwl_mld_scan_uid_by_status(mld, IWL_MLD_SCAN_SCHED);
+	if (uid >= 0) {
+		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
+		mld->scan.uid_status[uid] = IWL_MLD_SCAN_NONE;
+
+		/* sched scan will be restarted by mac80211 in reconfig.
+		 * report to mac80211 that sched scan stopped only if we won't
+		 * restart the firmware.
+		 */
+		if (!iwlwifi_mod_params.fw_restart)
+			ieee80211_sched_scan_stopped(mld->hw);
+	}
+
+	uid = iwl_mld_scan_uid_by_status(mld, IWL_MLD_SCAN_INT_MLO);
+	if (uid >= 0) {
+		IWL_DEBUG_SCAN(mld, "Internal MLO scan aborted\n");
+		mld->scan.uid_status[uid] = IWL_MLD_SCAN_NONE;
+	}
+
+	BUILD_BUG_ON(IWL_MLD_SCAN_NONE != 0);
+	memset(mld->scan.uid_status, 0, sizeof(mld->scan.uid_status));
+}
+
+int iwl_mld_alloc_scan_cmd(struct iwl_mld *mld)
+{
+	u8 scan_cmd_ver = iwl_fw_lookup_cmd_ver(mld->fw, SCAN_REQ_UMAC,
+						IWL_FW_CMD_VER_UNKNOWN);
+	size_t scan_cmd_size;
+
+	if (scan_cmd_ver == 17) {
+		scan_cmd_size = sizeof(struct iwl_scan_req_umac_v17);
+	} else {
+		IWL_ERR(mld, "Unexpected scan cmd version %d\n", scan_cmd_ver);
+		return -EINVAL;
+	}
+
+	mld->scan.cmd = kmalloc(scan_cmd_size, GFP_KERNEL);
+	if (!mld->scan.cmd)
+		return -ENOMEM;
+
+	mld->scan.cmd_size = scan_cmd_size;
+
+	return 0;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.h b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
new file mode 100644
index 0000000000000..cb589e0023193
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifndef __iwl_mld_scan_h__
+#define __iwl_mld_scan_h__
+
+int iwl_mld_alloc_scan_cmd(struct iwl_mld *mld);
+
+int iwl_mld_regular_scan_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			       struct cfg80211_scan_request *req,
+			       struct ieee80211_scan_ies *ies);
+
+void iwl_mld_int_mlo_scan(struct iwl_mld *mld, struct ieee80211_vif *vif);
+
+void iwl_mld_handle_scan_iter_complete_notif(struct iwl_mld *mld,
+					     struct iwl_rx_packet *pkt);
+
+int iwl_mld_scan_stop(struct iwl_mld *mld, int type, bool notify);
+
+int iwl_mld_sched_scan_start(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct cfg80211_sched_scan_request *req,
+			     struct ieee80211_scan_ies *ies,
+			     int type);
+
+void iwl_mld_handle_match_found_notif(struct iwl_mld *mld,
+				      struct iwl_rx_packet *pkt);
+
+void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt);
+
+#define WFA_TPC_IE_LEN 9
+
+static inline int iwl_mld_scan_max_template_size(void)
+{
+#define MAC_HDR_LEN 24
+#define DS_IE_LEN 3
+#define SSID_IE_LEN 2
+
+/* driver create the 802.11 header, WFA TPC IE, DS parameter and SSID IE */
+#define DRIVER_TOTAL_IES_LEN \
+	(MAC_HDR_LEN + WFA_TPC_IE_LEN + DS_IE_LEN + SSID_IE_LEN)
+
+	BUILD_BUG_ON(SCAN_OFFLOAD_PROBE_REQ_SIZE < DRIVER_TOTAL_IES_LEN);
+
+	return SCAN_OFFLOAD_PROBE_REQ_SIZE - DRIVER_TOTAL_IES_LEN;
+}
+
+void iwl_mld_report_scan_aborted(struct iwl_mld *mld);
+
+enum iwl_mld_scan_status {
+	IWL_MLD_SCAN_NONE		= 0,
+	IWL_MLD_SCAN_REGULAR		= BIT(0),
+	IWL_MLD_SCAN_SCHED		= BIT(1),
+	IWL_MLD_SCAN_NETDETECT		= BIT(2),
+	IWL_MLD_SCAN_INT_MLO		= BIT(3),
+};
+
+/* enum iwl_mld_pass_all_sched_results_states - Defines the states for
+ * handling/passing scheduled scan results to mac80211
+ * @SCHED_SCAN_PASS_ALL_STATE_DISABLED: Don't pass all scan results, only when
+ *	a match found.
+ * @SCHED_SCAN_PASS_ALL_STATE_ENABLED: Pass all scan results is enabled
+ *	(no filtering).
+ * @SCHED_SCAN_PASS_ALL_STATE_FOUND: A scan result is found, pass it on the
+ *	next scan iteration complete notification.
+ */
+enum iwl_mld_pass_all_sched_results_states {
+	SCHED_SCAN_PASS_ALL_STATE_DISABLED,
+	SCHED_SCAN_PASS_ALL_STATE_ENABLED,
+	SCHED_SCAN_PASS_ALL_STATE_FOUND,
+};
+
+/**
+ * enum iwl_mld_traffic_load - Levels of traffic load
+ *
+ * @IWL_MLD_TRAFFIC_LOW: low traffic load
+ * @IWL_MLD_TRAFFIC_MEDIUM: medium traffic load
+ * @IWL_MLD_TRAFFIC_HIGH: high traffic load
+ */
+enum iwl_mld_traffic_load {
+	IWL_MLD_TRAFFIC_LOW,
+	IWL_MLD_TRAFFIC_MEDIUM,
+	IWL_MLD_TRAFFIC_HIGH,
+};
+
+/**
+ * struct iwl_mld_scan - Scan data
+ * @status: scan status, a combination of %enum iwl_mld_scan_status,
+ *	reflects the %scan.uid_status array.
+ * @uid_status: array to track the scan status per uid.
+ * @start_tsf: start time of last scan in TSF of the link that requested
+ *	the scan.
+ * @last_ebs_failed: true if the last EBS (Energy Based Scan) failed.
+ * @pass_all_sched_res: see %enum iwl_mld_pass_all_sched_results_states.
+ * @fw_link_id: the current (regular) scan fw link id, used by scan
+ *	complete notif.
+ * @traffic_load: traffic load related data
+ * @traffic_load.last_stats_ts_usec: The timestamp of the last statistics
+ *	notification, used to calculate the elapsed time between two
+ *	notifications and determine the traffic load
+ * @traffic_load.status: The current traffic load status, see
+ *	&enum iwl_mld_traffic_load
+ * @cmd_size: size of %cmd.
+ * @cmd: pointer to scan cmd buffer (allocated once in op mode start).
+ * @last_6ghz_passive_jiffies: stores the last 6GHz passive scan time
+ *	in jiffies.
+ * @last_start_time_jiffies: stores the last start time in jiffies
+ *	(interface up/reset/resume).
+ * @last_mlo_scan_jiffies: end time of the last MLO scan in jiffies.
+ */
+struct iwl_mld_scan {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		unsigned int status;
+		u32 uid_status[IWL_MAX_UMAC_SCANS];
+		u64 start_tsf;
+		bool last_ebs_failed;
+		enum iwl_mld_pass_all_sched_results_states pass_all_sched_res;
+		u8 fw_link_id;
+		struct {
+			u32 last_stats_ts_usec;
+			enum iwl_mld_traffic_load status;
+		} traffic_load;
+	);
+	/* And here fields that survive a fw restart */
+	size_t cmd_size;
+	void *cmd;
+	unsigned long last_6ghz_passive_jiffies;
+	unsigned long last_start_time_jiffies;
+	unsigned long last_mlo_scan_jiffies;
+};
+
+#endif /* __iwl_mld_scan_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/session-protect.c b/drivers/net/wireless/intel/iwlwifi/mld/session-protect.c
new file mode 100644
index 0000000000000..dbb5615dc3f64
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/session-protect.c
@@ -0,0 +1,222 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include "session-protect.h"
+#include "fw/api/time-event.h"
+#include "fw/api/context.h"
+#include "iface.h"
+#include <net/mac80211.h>
+
+void iwl_mld_handle_session_prot_notif(struct iwl_mld *mld,
+				       struct iwl_rx_packet *pkt)
+{
+	struct iwl_session_prot_notif *notif = (void *)pkt->data;
+	int fw_link_id = le32_to_cpu(notif->mac_link_id);
+	struct ieee80211_bss_conf *link_conf =
+		iwl_mld_fw_id_to_link_conf(mld, fw_link_id);
+	struct ieee80211_vif *vif;
+	struct iwl_mld_vif *mld_vif;
+	struct iwl_mld_session_protect *session_protect;
+
+	if (WARN_ON(!link_conf))
+		return;
+
+	vif = link_conf->vif;
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	session_protect = &mld_vif->session_protect;
+
+	if (!le32_to_cpu(notif->status)) {
+		memset(session_protect, 0, sizeof(*session_protect));
+	} else if (le32_to_cpu(notif->start)) {
+		/* End_jiffies indicates an active session */
+		session_protect->session_requested = false;
+		session_protect->end_jiffies =
+			TU_TO_EXP_TIME(session_protect->duration);
+		/* !session_protect->end_jiffies means inactive session */
+		if (!session_protect->end_jiffies)
+			session_protect->end_jiffies = 1;
+	} else {
+		memset(session_protect, 0, sizeof(*session_protect));
+	}
+}
+
+static int _iwl_mld_schedule_session_protection(struct iwl_mld *mld,
+						struct ieee80211_vif *vif,
+						u32 duration, u32 min_duration,
+						int link_id)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link =
+		iwl_mld_link_dereference_check(mld_vif, link_id);
+	struct iwl_mld_session_protect *session_protect =
+		&mld_vif->session_protect;
+	struct iwl_session_prot_cmd cmd = {
+		.id_and_color = cpu_to_le32(link->fw_id),
+		.action = cpu_to_le32(FW_CTXT_ACTION_ADD),
+		.conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC),
+		.duration_tu = cpu_to_le32(MSEC_TO_TU(duration)),
+	};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	WARN(hweight16(vif->active_links) > 1,
+	     "Session protection isn't allowed with more than one active link");
+
+	if (session_protect->end_jiffies &&
+	    time_after(session_protect->end_jiffies,
+		       TU_TO_EXP_TIME(min_duration))) {
+		IWL_DEBUG_TE(mld, "We have ample in the current session: %u\n",
+			     jiffies_to_msecs(session_protect->end_jiffies -
+					      jiffies));
+		return -EALREADY;
+	}
+
+	IWL_DEBUG_TE(mld, "Add a new session protection, duration %d TU\n",
+		     le32_to_cpu(cmd.duration_tu));
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP,
+						SESSION_PROTECTION_CMD), &cmd);
+
+	if (ret)
+		return ret;
+
+	/* end_jiffies will be updated when handling session_prot_notif */
+	session_protect->end_jiffies = 0;
+	session_protect->duration = duration;
+	session_protect->session_requested = true;
+
+	return 0;
+}
+
+void iwl_mld_schedule_session_protection(struct iwl_mld *mld,
+					 struct ieee80211_vif *vif,
+					 u32 duration, u32 min_duration,
+					 int link_id)
+{
+	int ret;
+
+	ret = _iwl_mld_schedule_session_protection(mld, vif, duration,
+						   min_duration, link_id);
+	if (ret && ret != -EALREADY)
+		IWL_ERR(mld,
+			"Couldn't send the SESSION_PROTECTION_CMD (%d)\n",
+			ret);
+}
+
+struct iwl_mld_session_start_data {
+	struct iwl_mld *mld;
+	struct ieee80211_bss_conf *link_conf;
+	bool success;
+};
+
+static bool iwl_mld_session_start_fn(struct iwl_notif_wait_data *notif_wait,
+				     struct iwl_rx_packet *pkt, void *_data)
+{
+	struct iwl_session_prot_notif *notif = (void *)pkt->data;
+	unsigned int pkt_len = iwl_rx_packet_payload_len(pkt);
+	struct iwl_mld_session_start_data *data = _data;
+	struct ieee80211_bss_conf *link_conf;
+	struct iwl_mld *mld = data->mld;
+	int fw_link_id;
+
+	if (IWL_FW_CHECK(mld, pkt_len < sizeof(*notif),
+			 "short session prot notif (%d)\n",
+			 pkt_len))
+		return false;
+
+	fw_link_id = le32_to_cpu(notif->mac_link_id);
+	link_conf = iwl_mld_fw_id_to_link_conf(mld, fw_link_id);
+
+	if (link_conf != data->link_conf)
+		return false;
+
+	if (!le32_to_cpu(notif->status))
+		return true;
+
+	if (notif->start) {
+		data->success = true;
+		return true;
+	}
+
+	return false;
+}
+
+int iwl_mld_start_session_protection(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif,
+				     u32 duration, u32 min_duration,
+				     int link_id, unsigned long timeout)
+{
+	static const u16 start_notif[] = { SESSION_PROTECTION_NOTIF };
+	struct iwl_notification_wait start_wait;
+	struct iwl_mld_session_start_data data = {
+		.mld = mld,
+		.link_conf = wiphy_dereference(mld->wiphy,
+					       vif->link_conf[link_id]),
+	};
+	int ret;
+
+	if (WARN_ON(!data.link_conf))
+		return -EINVAL;
+
+	iwl_init_notification_wait(&mld->notif_wait, &start_wait,
+				   start_notif, ARRAY_SIZE(start_notif),
+				   iwl_mld_session_start_fn, &data);
+
+	ret = _iwl_mld_schedule_session_protection(mld, vif, duration,
+						   min_duration, link_id);
+
+	if (ret) {
+		iwl_remove_notification(&mld->notif_wait, &start_wait);
+		return ret == -EALREADY ? 0 : ret;
+	}
+
+	ret = iwl_wait_notification(&mld->notif_wait, &start_wait, timeout);
+	if (ret)
+		return ret;
+	return data.success ? 0 : -EIO;
+}
+
+int iwl_mld_cancel_session_protection(struct iwl_mld *mld,
+				      struct ieee80211_vif *vif,
+				      int link_id)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link =
+		iwl_mld_link_dereference_check(mld_vif, link_id);
+	struct iwl_mld_session_protect *session_protect =
+		&mld_vif->session_protect;
+	struct iwl_session_prot_cmd cmd = {
+		.action = cpu_to_le32(FW_CTXT_ACTION_REMOVE),
+		.conf_id = cpu_to_le32(SESSION_PROTECT_CONF_ASSOC),
+	};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* If there isn't an active session or a requested one for this
+	 * link do nothing
+	 */
+	if (!session_protect->session_requested &&
+	    !session_protect->end_jiffies)
+		return 0;
+
+	if (WARN_ON(!link))
+		return -EINVAL;
+
+	cmd.id_and_color = cpu_to_le32(link->fw_id);
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(MAC_CONF_GROUP,
+					   SESSION_PROTECTION_CMD), &cmd);
+	if (ret) {
+		IWL_ERR(mld,
+			"Couldn't send the SESSION_PROTECTION_CMD\n");
+		return ret;
+	}
+
+	memset(session_protect, 0, sizeof(*session_protect));
+
+	return 0;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/session-protect.h b/drivers/net/wireless/intel/iwlwifi/mld/session-protect.h
new file mode 100644
index 0000000000000..642bec8451a16
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/session-protect.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#ifndef __session_protect_h__
+#define __session_protect_h__
+
+#include "mld.h"
+#include "hcmd.h"
+#include <net/mac80211.h>
+#include "fw/api/mac-cfg.h"
+
+/**
+ * DOC: session protection
+ *
+ * Session protection is an API from the firmware that allows the driver to
+ * request time on medium. This is needed before the association when we need
+ * to be on medium for the association frame exchange. Once we configure the
+ * firmware as 'associated', the firmware will allocate time on medium without
+ * needed a session protection.
+ *
+ * TDLS discover uses this API as well even after association to ensure that
+ * other activities internal to the firmware will not interrupt our presence
+ * on medium.
+ */
+
+/**
+ * struct iwl_mld_session_protect - session protection parameters
+ * @end_jiffies: expected end_jiffies of current session protection.
+ *	0 if not active
+ * @duration: the duration in tu of current session
+ * @session_requested: A session protection command was sent and wasn't yet
+ *	answered
+ */
+struct iwl_mld_session_protect {
+	unsigned long end_jiffies;
+	u32 duration;
+	bool session_requested;
+};
+
+#define IWL_MLD_SESSION_PROTECTION_ASSOC_TIME_MS 900
+#define IWL_MLD_SESSION_PROTECTION_MIN_TIME_MS 400
+
+/**
+ * iwl_mld_handle_session_prot_notif - handles %SESSION_PROTECTION_NOTIF
+ * @mld: the mld component
+ * @pkt: the RX packet containing the notification
+ */
+void iwl_mld_handle_session_prot_notif(struct iwl_mld *mld,
+				       struct iwl_rx_packet *pkt);
+
+/**
+ * iwl_mld_schedule_session_protection - schedule a session protection
+ * @mld: the mld component
+ * @vif: the virtual interface for which the protection issued
+ * @duration: the requested duration of the protection
+ * @min_duration: the minimum duration of the protection
+ * @link_id: The link to schedule a session protection for
+ */
+void iwl_mld_schedule_session_protection(struct iwl_mld *mld,
+					 struct ieee80211_vif *vif,
+					 u32 duration, u32 min_duration,
+					 int link_id);
+
+/**
+ * iwl_mld_start_session_protection - start a session protection
+ * @mld: the mld component
+ * @vif: the virtual interface for which the protection issued
+ * @duration: the requested duration of the protection
+ * @min_duration: the minimum duration of the protection
+ * @link_id: The link to schedule a session protection for
+ * @timeout: timeout for waiting
+ *
+ * This schedules the session protection, and waits for it to start
+ * (with timeout)
+ *
+ * Returns: 0 if successful, error code otherwise
+ */
+int iwl_mld_start_session_protection(struct iwl_mld *mld,
+				     struct ieee80211_vif *vif,
+				     u32 duration, u32 min_duration,
+				     int link_id, unsigned long timeout);
+
+/**
+ * iwl_mld_cancel_session_protection - cancel the session protection.
+ * @mld: the mld component
+ * @vif: the virtual interface for which the session is issued
+ * @link_id: cancel the session protection for given link
+ *
+ * This functions cancels the session protection which is an act of good
+ * citizenship. If it is not needed any more it should be canceled because
+ * the other mac contexts wait for the medium during that time.
+ *
+ * Returns: 0 if successful, error code otherwise
+ *
+ */
+int iwl_mld_cancel_session_protection(struct iwl_mld *mld,
+				      struct ieee80211_vif *vif,
+				      int link_id);
+
+#endif /* __session_protect_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.c b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
new file mode 100644
index 0000000000000..f266a81dd29b9
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
@@ -0,0 +1,1265 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include <linux/ieee80211.h>
+#include <kunit/static_stub.h>
+
+#include "sta.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "mlo.h"
+#include "key.h"
+#include "agg.h"
+#include "tlc.h"
+#include "fw/api/sta.h"
+#include "fw/api/mac.h"
+#include "fw/api/rx.h"
+
+int iwl_mld_fw_sta_id_from_link_sta(struct iwl_mld *mld,
+				    struct ieee80211_link_sta *link_sta)
+{
+	struct iwl_mld_link_sta *mld_link_sta;
+
+	/* This function should only be used with the wiphy lock held,
+	 * In other cases, it is not guaranteed that the link_sta will exist
+	 * in the driver too, and it is checked here.
+	 */
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* This is not meant to be called with a NULL pointer */
+	if (WARN_ON(!link_sta))
+		return -ENOENT;
+
+	mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+	if (!mld_link_sta) {
+		WARN_ON(!iwl_mld_error_before_recovery(mld));
+		return -ENOENT;
+	}
+
+	return mld_link_sta->fw_id;
+}
+
+static void
+iwl_mld_fill_ampdu_size_and_dens(struct ieee80211_link_sta *link_sta,
+				 struct ieee80211_bss_conf *link,
+				 __le32 *tx_ampdu_max_size,
+				 __le32 *tx_ampdu_spacing)
+{
+	u32 agg_size = 0, mpdu_dens = 0;
+
+	if (WARN_ON(!link_sta || !link))
+		return;
+
+	/* Note that we always use only legacy & highest supported PPDUs, so
+	 * of Draft P802.11be D.30 Table 10-12a--Fields used for calculating
+	 * the maximum A-MPDU size of various PPDU types in different bands,
+	 * we only need to worry about the highest supported PPDU type here.
+	 */
+
+	if (link_sta->ht_cap.ht_supported) {
+		agg_size = link_sta->ht_cap.ampdu_factor;
+		mpdu_dens = link_sta->ht_cap.ampdu_density;
+	}
+
+	if (link->chanreq.oper.chan->band == NL80211_BAND_6GHZ) {
+		/* overwrite HT values on 6 GHz */
+		mpdu_dens =
+			le16_get_bits(link_sta->he_6ghz_capa.capa,
+				      IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START);
+		agg_size =
+			le16_get_bits(link_sta->he_6ghz_capa.capa,
+				      IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP);
+	} else if (link_sta->vht_cap.vht_supported) {
+		/* if VHT supported overwrite HT value */
+		agg_size =
+			u32_get_bits(link_sta->vht_cap.cap,
+				     IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK);
+	}
+
+	/* D6.0 10.12.2 A-MPDU length limit rules
+	 * A STA indicates the maximum length of the A-MPDU preEOF padding
+	 * that it can receive in an HE PPDU in the Maximum A-MPDU Length
+	 * Exponent field in its HT Capabilities, VHT Capabilities,
+	 * and HE 6 GHz Band Capabilities elements (if present) and the
+	 * Maximum AMPDU Length Exponent Extension field in its HE
+	 * Capabilities element
+	 */
+	if (link_sta->he_cap.has_he)
+		agg_size +=
+			u8_get_bits(link_sta->he_cap.he_cap_elem.mac_cap_info[3],
+				    IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK);
+
+	if (link_sta->eht_cap.has_eht)
+		agg_size +=
+			u8_get_bits(link_sta->eht_cap.eht_cap_elem.mac_cap_info[1],
+				    IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK);
+
+	/* Limit to max A-MPDU supported by FW */
+	agg_size = min_t(u32, agg_size,
+			 STA_FLG_MAX_AGG_SIZE_4M >> STA_FLG_MAX_AGG_SIZE_SHIFT);
+
+	*tx_ampdu_max_size = cpu_to_le32(agg_size);
+	*tx_ampdu_spacing = cpu_to_le32(mpdu_dens);
+}
+
+static u8 iwl_mld_get_uapsd_acs(struct ieee80211_sta *sta)
+{
+	u8 uapsd_acs = 0;
+
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BK)
+		uapsd_acs |= BIT(AC_BK);
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_BE)
+		uapsd_acs |= BIT(AC_BE);
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VI)
+		uapsd_acs |= BIT(AC_VI);
+	if (sta->uapsd_queues & IEEE80211_WMM_IE_STA_QOSINFO_AC_VO)
+		uapsd_acs |= BIT(AC_VO);
+
+	return uapsd_acs | uapsd_acs << 4;
+}
+
+static u8 iwl_mld_he_get_ppe_val(u8 *ppe, u8 ppe_pos_bit)
+{
+	u8 byte_num = ppe_pos_bit / 8;
+	u8 bit_num = ppe_pos_bit % 8;
+	u8 residue_bits;
+	u8 res;
+
+	if (bit_num <= 5)
+		return (ppe[byte_num] >> bit_num) &
+		       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE) - 1);
+
+	/* If bit_num > 5, we have to combine bits with next byte.
+	 * Calculate how many bits we need to take from current byte (called
+	 * here "residue_bits"), and add them to bits from next byte.
+	 */
+
+	residue_bits = 8 - bit_num;
+
+	res = (ppe[byte_num + 1] &
+	       (BIT(IEEE80211_PPE_THRES_INFO_PPET_SIZE - residue_bits) - 1)) <<
+	      residue_bits;
+	res += (ppe[byte_num] >> bit_num) & (BIT(residue_bits) - 1);
+
+	return res;
+}
+
+static void iwl_mld_parse_ppe(struct iwl_mld *mld,
+			      struct iwl_he_pkt_ext_v2 *pkt_ext, u8 nss,
+			      u8 ru_index_bitmap, u8 *ppe, u8 ppe_pos_bit,
+			      bool inheritance)
+{
+	/* FW currently supports only nss == MAX_HE_SUPP_NSS
+	 *
+	 * If nss > MAX: we can ignore values we don't support
+	 * If nss < MAX: we can set zeros in other streams
+	 */
+	if (nss > MAX_HE_SUPP_NSS) {
+		IWL_DEBUG_INFO(mld, "Got NSS = %d - trimming to %d\n", nss,
+			       MAX_HE_SUPP_NSS);
+		nss = MAX_HE_SUPP_NSS;
+	}
+
+	for (int i = 0; i < nss; i++) {
+		u8 ru_index_tmp = ru_index_bitmap << 1;
+		u8 low_th = IWL_HE_PKT_EXT_NONE, high_th = IWL_HE_PKT_EXT_NONE;
+
+		for (u8 bw = 0;
+		     bw < ARRAY_SIZE(pkt_ext->pkt_ext_qam_th[i]);
+		     bw++) {
+			ru_index_tmp >>= 1;
+
+			/* According to the 11be spec, if for a specific BW the PPE Thresholds
+			 * isn't present - it should inherit the thresholds from the last
+			 * BW for which we had PPE Thresholds. In 11ax though, we don't have
+			 * this inheritance - continue in this case
+			 */
+			if (!(ru_index_tmp & 1)) {
+				if (inheritance)
+					goto set_thresholds;
+				else
+					continue;
+			}
+
+			high_th = iwl_mld_he_get_ppe_val(ppe, ppe_pos_bit);
+			ppe_pos_bit += IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+			low_th = iwl_mld_he_get_ppe_val(ppe, ppe_pos_bit);
+			ppe_pos_bit += IEEE80211_PPE_THRES_INFO_PPET_SIZE;
+
+set_thresholds:
+			pkt_ext->pkt_ext_qam_th[i][bw][0] = low_th;
+			pkt_ext->pkt_ext_qam_th[i][bw][1] = high_th;
+		}
+	}
+}
+
+static void iwl_mld_set_pkt_ext_from_he_ppe(struct iwl_mld *mld,
+					    struct ieee80211_link_sta *link_sta,
+					    struct iwl_he_pkt_ext_v2 *pkt_ext,
+					    bool inheritance)
+{
+	u8 nss = (link_sta->he_cap.ppe_thres[0] &
+		  IEEE80211_PPE_THRES_NSS_MASK) + 1;
+	u8 *ppe = &link_sta->he_cap.ppe_thres[0];
+	u8 ru_index_bitmap =
+		u8_get_bits(*ppe,
+			    IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+	/* Starting after PPE header */
+	u8 ppe_pos_bit = IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE;
+
+	iwl_mld_parse_ppe(mld, pkt_ext, nss, ru_index_bitmap, ppe, ppe_pos_bit,
+			  inheritance);
+}
+
+static int
+iwl_mld_set_pkt_ext_from_nominal_padding(struct iwl_he_pkt_ext_v2 *pkt_ext,
+					 u8 nominal_padding)
+{
+	int low_th = -1;
+	int high_th = -1;
+
+	/* all the macros are the same for EHT and HE */
+	switch (nominal_padding) {
+	case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US:
+		low_th = IWL_HE_PKT_EXT_NONE;
+		high_th = IWL_HE_PKT_EXT_NONE;
+		break;
+	case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US:
+		low_th = IWL_HE_PKT_EXT_BPSK;
+		high_th = IWL_HE_PKT_EXT_NONE;
+		break;
+	case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US:
+	case IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US:
+		low_th = IWL_HE_PKT_EXT_NONE;
+		high_th = IWL_HE_PKT_EXT_BPSK;
+		break;
+	}
+
+	if (low_th < 0 || high_th < 0)
+		return -EINVAL;
+
+	/* Set the PPE thresholds accordingly */
+	for (int i = 0; i < MAX_HE_SUPP_NSS; i++) {
+		for (u8 bw = 0;
+			bw < ARRAY_SIZE(pkt_ext->pkt_ext_qam_th[i]);
+			bw++) {
+			pkt_ext->pkt_ext_qam_th[i][bw][0] = low_th;
+			pkt_ext->pkt_ext_qam_th[i][bw][1] = high_th;
+		}
+	}
+
+	return 0;
+}
+
+static void iwl_mld_get_optimal_ppe_info(struct iwl_he_pkt_ext_v2 *pkt_ext,
+					 u8 nominal_padding)
+{
+	for (int i = 0; i < MAX_HE_SUPP_NSS; i++) {
+		for (u8 bw = 0; bw < ARRAY_SIZE(pkt_ext->pkt_ext_qam_th[i]);
+		     bw++) {
+			u8 *qam_th = &pkt_ext->pkt_ext_qam_th[i][bw][0];
+
+			if (nominal_padding >
+			    IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US &&
+			    qam_th[1] == IWL_HE_PKT_EXT_NONE)
+				qam_th[1] = IWL_HE_PKT_EXT_4096QAM;
+			else if (nominal_padding ==
+				 IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US &&
+				 qam_th[0] == IWL_HE_PKT_EXT_NONE &&
+				 qam_th[1] == IWL_HE_PKT_EXT_NONE)
+				qam_th[0] = IWL_HE_PKT_EXT_4096QAM;
+		}
+	}
+}
+
+static void iwl_mld_fill_pkt_ext(struct iwl_mld *mld,
+				 struct ieee80211_link_sta *link_sta,
+				 struct iwl_he_pkt_ext_v2 *pkt_ext)
+{
+	if (WARN_ON(!link_sta))
+		return;
+
+	/* Initialize the PPE thresholds to "None" (7), as described in Table
+	 * 9-262ac of 80211.ax/D3.0.
+	 */
+	memset(pkt_ext, IWL_HE_PKT_EXT_NONE, sizeof(*pkt_ext));
+
+	if (link_sta->eht_cap.has_eht) {
+		u8 nominal_padding =
+			u8_get_bits(link_sta->eht_cap.eht_cap_elem.phy_cap_info[5],
+				    IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK);
+
+		/* If PPE Thresholds exists, parse them into a FW-familiar
+		 * format.
+		 */
+		if (link_sta->eht_cap.eht_cap_elem.phy_cap_info[5] &
+		    IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) {
+			u8 nss = (link_sta->eht_cap.eht_ppe_thres[0] &
+				IEEE80211_EHT_PPE_THRES_NSS_MASK) + 1;
+			u8 *ppe = &link_sta->eht_cap.eht_ppe_thres[0];
+			u8 ru_index_bitmap =
+				u16_get_bits(*ppe,
+					     IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+			 /* Starting after PPE header */
+			u8 ppe_pos_bit = IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE;
+
+			iwl_mld_parse_ppe(mld, pkt_ext, nss, ru_index_bitmap,
+					  ppe, ppe_pos_bit, true);
+		/* EHT PPE Thresholds doesn't exist - set the API according to
+		 * HE PPE Tresholds
+		 */
+		} else if (link_sta->he_cap.he_cap_elem.phy_cap_info[6] &
+			   IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
+			/* Even though HE Capabilities IE doesn't contain PPE
+			 * Thresholds for BW 320Mhz, thresholds for this BW will
+			 * be filled in with the same values as 160Mhz, due to
+			 * the inheritance, as required.
+			 */
+			iwl_mld_set_pkt_ext_from_he_ppe(mld, link_sta, pkt_ext,
+							true);
+
+			/* According to the requirements, for MCSs 12-13 the
+			 * maximum value between HE PPE Threshold and Common
+			 * Nominal Packet Padding needs to be taken
+			 */
+			iwl_mld_get_optimal_ppe_info(pkt_ext, nominal_padding);
+
+		/* if PPE Thresholds doesn't present in both EHT IE and HE IE -
+		 * take the Thresholds from Common Nominal Packet Padding field
+		 */
+		} else {
+			iwl_mld_set_pkt_ext_from_nominal_padding(pkt_ext,
+								 nominal_padding);
+		}
+	} else if (link_sta->he_cap.has_he) {
+		/* If PPE Thresholds exist, parse them into a FW-familiar format. */
+		if (link_sta->he_cap.he_cap_elem.phy_cap_info[6] &
+			IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
+			iwl_mld_set_pkt_ext_from_he_ppe(mld, link_sta, pkt_ext,
+							false);
+		/* PPE Thresholds doesn't exist - set the API PPE values
+		 * according to Common Nominal Packet Padding field.
+		 */
+		} else {
+			u8 nominal_padding =
+				u8_get_bits(link_sta->he_cap.he_cap_elem.phy_cap_info[9],
+					    IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK);
+			if (nominal_padding != IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED)
+				iwl_mld_set_pkt_ext_from_nominal_padding(pkt_ext,
+									 nominal_padding);
+		}
+	}
+
+	for (int i = 0; i < MAX_HE_SUPP_NSS; i++) {
+		for (int bw = 0;
+		     bw < ARRAY_SIZE(*pkt_ext->pkt_ext_qam_th[i]);
+		     bw++) {
+			u8 *qam_th =
+				&pkt_ext->pkt_ext_qam_th[i][bw][0];
+
+			IWL_DEBUG_HT(mld,
+				     "PPE table: nss[%d] bw[%d] PPET8 = %d, PPET16 = %d\n",
+				     i, bw, qam_th[0], qam_th[1]);
+		}
+	}
+}
+
+static u32 iwl_mld_get_htc_flags(struct ieee80211_link_sta *link_sta)
+{
+	u8 *mac_cap_info =
+		&link_sta->he_cap.he_cap_elem.mac_cap_info[0];
+	u32 htc_flags = 0;
+
+	if (mac_cap_info[0] & IEEE80211_HE_MAC_CAP0_HTC_HE)
+		htc_flags |= IWL_HE_HTC_SUPPORT;
+	if ((mac_cap_info[1] & IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION) ||
+	    (mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION)) {
+		u8 link_adap =
+			((mac_cap_info[2] &
+			  IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION) << 1) +
+			 (mac_cap_info[1] &
+			  IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION);
+
+		if (link_adap == 2)
+			htc_flags |=
+				IWL_HE_HTC_LINK_ADAP_UNSOLICITED;
+		else if (link_adap == 3)
+			htc_flags |= IWL_HE_HTC_LINK_ADAP_BOTH;
+	}
+	if (mac_cap_info[2] & IEEE80211_HE_MAC_CAP2_BSR)
+		htc_flags |= IWL_HE_HTC_BSR_SUPP;
+	if (mac_cap_info[3] & IEEE80211_HE_MAC_CAP3_OMI_CONTROL)
+		htc_flags |= IWL_HE_HTC_OMI_SUPP;
+	if (mac_cap_info[4] & IEEE80211_HE_MAC_CAP4_BQR)
+		htc_flags |= IWL_HE_HTC_BQR_SUPP;
+
+	return htc_flags;
+}
+
+static int iwl_mld_send_sta_cmd(struct iwl_mld *mld,
+				const struct iwl_sta_cfg_cmd *cmd)
+{
+	int ret = iwl_mld_send_cmd_pdu(mld,
+				       WIDE_ID(MAC_CONF_GROUP, STA_CONFIG_CMD),
+				       cmd);
+	if (ret)
+		IWL_ERR(mld, "STA_CONFIG_CMD send failed, ret=0x%x\n", ret);
+	return ret;
+}
+
+static int
+iwl_mld_add_modify_sta_cmd(struct iwl_mld *mld,
+			   struct ieee80211_link_sta *link_sta)
+{
+	struct ieee80211_sta *sta = link_sta->sta;
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_bss_conf *link;
+	struct iwl_mld_link *mld_link;
+	struct iwl_sta_cfg_cmd cmd = {};
+	int fw_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	link = link_conf_dereference_protected(mld_sta->vif,
+					       link_sta->link_id);
+
+	mld_link = iwl_mld_link_from_mac80211(link);
+
+	if (WARN_ON(!link || !mld_link) || fw_id < 0)
+		return -EINVAL;
+
+	cmd.sta_id = cpu_to_le32(fw_id);
+	cmd.station_type = cpu_to_le32(mld_sta->sta_type);
+	cmd.link_id = cpu_to_le32(mld_link->fw_id);
+
+	memcpy(&cmd.peer_mld_address, sta->addr, ETH_ALEN);
+	memcpy(&cmd.peer_link_address, link_sta->addr, ETH_ALEN);
+
+	if (mld_sta->sta_state >= IEEE80211_STA_ASSOC)
+		cmd.assoc_id = cpu_to_le32(sta->aid);
+
+	if (sta->mfp || mld_sta->sta_state < IEEE80211_STA_AUTHORIZED)
+		cmd.mfp = cpu_to_le32(1);
+
+	switch (link_sta->rx_nss) {
+	case 1:
+		cmd.mimo = cpu_to_le32(0);
+		break;
+	case 2 ... 8:
+		cmd.mimo = cpu_to_le32(1);
+		break;
+	}
+
+	switch (link_sta->smps_mode) {
+	case IEEE80211_SMPS_AUTOMATIC:
+	case IEEE80211_SMPS_NUM_MODES:
+		WARN_ON(1);
+		break;
+	case IEEE80211_SMPS_STATIC:
+		/* override NSS */
+		cmd.mimo = cpu_to_le32(0);
+		break;
+	case IEEE80211_SMPS_DYNAMIC:
+		cmd.mimo_protection = cpu_to_le32(1);
+		break;
+	case IEEE80211_SMPS_OFF:
+		/* nothing */
+		break;
+	}
+
+	iwl_mld_fill_ampdu_size_and_dens(link_sta, link,
+					 &cmd.tx_ampdu_max_size,
+					 &cmd.tx_ampdu_spacing);
+
+	if (sta->wme) {
+		cmd.sp_length =
+			cpu_to_le32(sta->max_sp ? sta->max_sp * 2 : 128);
+		cmd.uapsd_acs = cpu_to_le32(iwl_mld_get_uapsd_acs(sta));
+	}
+
+	if (link_sta->he_cap.has_he) {
+		cmd.trig_rnd_alloc =
+			cpu_to_le32(link->uora_exists ? 1 : 0);
+
+		/* PPE Thresholds */
+		iwl_mld_fill_pkt_ext(mld, link_sta, &cmd.pkt_ext);
+
+		/* HTC flags */
+		cmd.htc_flags =
+			cpu_to_le32(iwl_mld_get_htc_flags(link_sta));
+
+		if (link_sta->he_cap.he_cap_elem.mac_cap_info[2] &
+		    IEEE80211_HE_MAC_CAP2_ACK_EN)
+			cmd.ack_enabled = cpu_to_le32(1);
+	}
+
+	return iwl_mld_send_sta_cmd(mld, &cmd);
+}
+
+IWL_MLD_ALLOC_FN(link_sta, link_sta)
+
+static int
+iwl_mld_add_link_sta(struct iwl_mld *mld, struct ieee80211_link_sta *link_sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+	struct iwl_mld_link_sta *mld_link_sta;
+	int ret;
+	u8 fw_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* We will fail to add it to the FW anyway */
+	if (iwl_mld_error_before_recovery(mld))
+		return -ENODEV;
+
+	mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+
+	/* We need to preserve the fw sta ids during a restart, since the fw
+	 * will recover SN/PN for them, this is why the mld_link_sta exists.
+	 */
+	if (mld_link_sta) {
+		/* But if we are not restarting, this is not OK */
+		WARN_ON(!mld->fw_status.in_hw_restart);
+
+		/* Avoid adding a STA that is already in FW to avoid an assert */
+		if (WARN_ON(mld_link_sta->in_fw))
+			return -EINVAL;
+
+		fw_id = mld_link_sta->fw_id;
+		goto add_to_fw;
+	}
+
+	/* Allocate a fw id and map it to the link_sta */
+	ret = iwl_mld_allocate_link_sta_fw_id(mld, &fw_id, link_sta);
+	if (ret)
+		return ret;
+
+	if (link_sta == &link_sta->sta->deflink) {
+		mld_link_sta = &mld_sta->deflink;
+	} else {
+		mld_link_sta = kzalloc(sizeof(*mld_link_sta), GFP_KERNEL);
+		if (!mld_link_sta)
+			return -ENOMEM;
+	}
+
+	mld_link_sta->fw_id = fw_id;
+	rcu_assign_pointer(mld_sta->link[link_sta->link_id], mld_link_sta);
+
+add_to_fw:
+	ret = iwl_mld_add_modify_sta_cmd(mld, link_sta);
+	if (ret) {
+		RCU_INIT_POINTER(mld->fw_id_to_link_sta[fw_id], NULL);
+		RCU_INIT_POINTER(mld_sta->link[link_sta->link_id], NULL);
+		if (link_sta != &link_sta->sta->deflink)
+			kfree(mld_link_sta);
+		return ret;
+	}
+	mld_link_sta->in_fw = true;
+
+	return 0;
+}
+
+static int iwl_mld_rm_sta_from_fw(struct iwl_mld *mld, u8 fw_sta_id)
+{
+	struct iwl_remove_sta_cmd cmd = {
+		.sta_id = cpu_to_le32(fw_sta_id),
+	};
+	int ret;
+
+	ret = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(MAC_CONF_GROUP, STA_REMOVE_CMD),
+				   &cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to remove station. Id=%d\n", fw_sta_id);
+
+	return ret;
+}
+
+static void
+iwl_mld_remove_link_sta(struct iwl_mld *mld,
+			struct ieee80211_link_sta *link_sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+	struct iwl_mld_link_sta *mld_link_sta =
+		iwl_mld_link_sta_from_mac80211(link_sta);
+
+	if (WARN_ON(!mld_link_sta))
+		return;
+
+	iwl_mld_rm_sta_from_fw(mld, mld_link_sta->fw_id);
+	mld_link_sta->in_fw = false;
+
+	/* Now that the STA doesn't exist in FW, we don't expect any new
+	 * notifications for it. Cancel the ones that are already pending
+	 */
+	iwl_mld_cancel_notifications_of_object(mld, IWL_MLD_OBJECT_TYPE_STA,
+					       mld_link_sta->fw_id);
+
+	/* This will not be done upon reconfig, so do it also when
+	 * failed to remove from fw
+	 */
+	RCU_INIT_POINTER(mld->fw_id_to_link_sta[mld_link_sta->fw_id], NULL);
+	RCU_INIT_POINTER(mld_sta->link[link_sta->link_id], NULL);
+	if (mld_link_sta != &mld_sta->deflink)
+		kfree_rcu(mld_link_sta, rcu_head);
+}
+
+int iwl_mld_update_all_link_stations(struct iwl_mld *mld,
+				     struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_link_sta *link_sta;
+	int link_id;
+
+	for_each_sta_active_link(mld_sta->vif, sta, link_sta, link_id) {
+		int ret = iwl_mld_add_modify_sta_cmd(mld, link_sta);
+
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static void iwl_mld_destroy_sta(struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	kfree(mld_sta->dup_data);
+	kfree(mld_sta->mpdu_counters);
+}
+
+static int
+iwl_mld_alloc_dup_data(struct iwl_mld *mld, struct iwl_mld_sta *mld_sta)
+{
+	struct iwl_mld_rxq_dup_data *dup_data;
+
+	if (mld->fw_status.in_hw_restart)
+		return 0;
+
+	dup_data = kcalloc(mld->trans->num_rx_queues, sizeof(*dup_data),
+			   GFP_KERNEL);
+	if (!dup_data)
+		return -ENOMEM;
+
+	/* Initialize all the last_seq values to 0xffff which can never
+	 * compare equal to the frame's seq_ctrl in the check in
+	 * iwl_mld_is_dup() since the lower 4 bits are the fragment
+	 * number and fragmented packets don't reach that function.
+	 *
+	 * This thus allows receiving a packet with seqno 0 and the
+	 * retry bit set as the very first packet on a new TID.
+	 */
+	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+		memset(dup_data[q].last_seq, 0xff,
+		       sizeof(dup_data[q].last_seq));
+	mld_sta->dup_data = dup_data;
+
+	return 0;
+}
+
+static void iwl_mld_alloc_mpdu_counters(struct iwl_mld *mld,
+					struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_vif *vif = mld_sta->vif;
+
+	if (mld->fw_status.in_hw_restart)
+		return;
+
+	/* MPDUs are counted only when EMLSR is possible */
+	if (ieee80211_vif_type_p2p(vif) != NL80211_IFTYPE_STATION ||
+	    sta->tdls || !ieee80211_vif_is_mld(vif))
+		return;
+
+	mld_sta->mpdu_counters = kcalloc(mld->trans->num_rx_queues,
+					 sizeof(*mld_sta->mpdu_counters),
+					 GFP_KERNEL);
+	if (!mld_sta->mpdu_counters)
+		return;
+
+	for (int q = 0; q < mld->trans->num_rx_queues; q++)
+		spin_lock_init(&mld_sta->mpdu_counters[q].lock);
+}
+
+static int
+iwl_mld_init_sta(struct iwl_mld *mld, struct ieee80211_sta *sta,
+		 struct ieee80211_vif *vif, enum iwl_fw_sta_type type)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	mld_sta->vif = vif;
+	mld_sta->sta_type = type;
+	mld_sta->mld = mld;
+
+	if (!mld->fw_status.in_hw_restart)
+		for (int i = 0; i < ARRAY_SIZE(sta->txq); i++)
+			iwl_mld_init_txq(iwl_mld_txq_from_mac80211(sta->txq[i]));
+
+	iwl_mld_alloc_mpdu_counters(mld, sta);
+
+	iwl_mld_toggle_tx_ant(mld, &mld_sta->data_tx_ant);
+
+	return iwl_mld_alloc_dup_data(mld, mld_sta);
+}
+
+int iwl_mld_add_sta(struct iwl_mld *mld, struct ieee80211_sta *sta,
+		    struct ieee80211_vif *vif, enum iwl_fw_sta_type type)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_link_sta *link_sta;
+	int link_id;
+	int ret;
+
+	ret = iwl_mld_init_sta(mld, sta, vif, type);
+	if (ret)
+		return ret;
+
+	/* We could have add only the deflink link_sta, but it will not work
+	 * in the restart case if the single link that is active during
+	 * reconfig is not the deflink one.
+	 */
+	for_each_sta_active_link(mld_sta->vif, sta, link_sta, link_id) {
+		ret = iwl_mld_add_link_sta(mld, link_sta);
+		if (ret)
+			goto destroy_sta;
+	}
+
+	return 0;
+
+destroy_sta:
+	iwl_mld_destroy_sta(sta);
+
+	return ret;
+}
+
+void iwl_mld_flush_sta_txqs(struct iwl_mld *mld, struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_link_sta *link_sta;
+	int link_id;
+
+	for_each_sta_active_link(mld_sta->vif, sta, link_sta, link_id) {
+		int fw_sta_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
+
+		if (fw_sta_id < 0)
+			continue;
+
+		iwl_mld_flush_link_sta_txqs(mld, fw_sta_id);
+	}
+}
+
+void iwl_mld_wait_sta_txqs_empty(struct iwl_mld *mld, struct ieee80211_sta *sta)
+{
+	/* Avoid a warning in iwl_trans_wait_txq_empty if are anyway on the way
+	 * to a restart.
+	 */
+	if (iwl_mld_error_before_recovery(mld))
+		return;
+
+	for (int i = 0; i < ARRAY_SIZE(sta->txq); i++) {
+		struct iwl_mld_txq *mld_txq =
+			iwl_mld_txq_from_mac80211(sta->txq[i]);
+
+		if (!mld_txq->status.allocated)
+			continue;
+
+		iwl_trans_wait_txq_empty(mld->trans, mld_txq->fw_id);
+	}
+}
+
+void iwl_mld_remove_sta(struct iwl_mld *mld, struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct ieee80211_vif *vif = mld_sta->vif;
+	struct ieee80211_link_sta *link_sta;
+	u8 link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* Tell the HW to flush the queues */
+	iwl_mld_flush_sta_txqs(mld, sta);
+
+	/* Wait for trans to empty its queues */
+	iwl_mld_wait_sta_txqs_empty(mld, sta);
+
+	/* Now we can remove the queues */
+	for (int i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		iwl_mld_remove_txq(mld, sta->txq[i]);
+
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		/* Mac8011 will remove the groupwise keys after the sta is
+		 * removed, but FW expects all the keys to be removed before
+		 * the STA is, so remove them all here.
+		 */
+		if (vif->type == NL80211_IFTYPE_STATION)
+			iwl_mld_remove_ap_keys(mld, vif, sta, link_id);
+
+		/* Remove the link_sta */
+		iwl_mld_remove_link_sta(mld, link_sta);
+	}
+
+	iwl_mld_destroy_sta(sta);
+}
+
+u32 iwl_mld_fw_sta_id_mask(struct iwl_mld *mld, struct ieee80211_sta *sta)
+{
+	struct ieee80211_vif *vif = iwl_mld_sta_from_mac80211(sta)->vif;
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
+	u32 result = 0;
+
+	KUNIT_STATIC_STUB_REDIRECT(iwl_mld_fw_sta_id_mask, mld, sta);
+
+	/* This function should only be used with the wiphy lock held,
+	 * In other cases, it is not guaranteed that the link_sta will exist
+	 * in the driver too, and it is checked in
+	 * iwl_mld_fw_sta_id_from_link_sta.
+	 */
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		int fw_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
+
+		if (!(fw_id < 0))
+			result |= BIT(fw_id);
+	}
+
+	return result;
+}
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_fw_sta_id_mask);
+
+static void iwl_mld_count_mpdu(struct ieee80211_link_sta *link_sta, int queue,
+			       u32 count, bool tx)
+{
+	struct iwl_mld_per_q_mpdu_counter *queue_counter;
+	struct iwl_mld_per_link_mpdu_counter *link_counter;
+	struct iwl_mld_vif *mld_vif;
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_link *mld_link;
+	struct iwl_mld *mld;
+	int total_mpdus = 0;
+
+	if (WARN_ON(!link_sta))
+		return;
+
+	mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+	if (!mld_sta->mpdu_counters)
+		return;
+
+	mld_vif = iwl_mld_vif_from_mac80211(mld_sta->vif);
+	mld_link = iwl_mld_link_dereference_check(mld_vif, link_sta->link_id);
+
+	if (WARN_ON_ONCE(!mld_link))
+		return;
+
+	queue_counter = &mld_sta->mpdu_counters[queue];
+
+	mld = mld_vif->mld;
+
+	/* If it the window is over, first clear the counters.
+	 * When we are not blocked by TPT, the window is managed by check_tpt_wk
+	 */
+	if ((mld_vif->emlsr.blocked_reasons & IWL_MLD_EMLSR_BLOCKED_TPT) &&
+	    time_is_before_jiffies(queue_counter->window_start_time +
+					IWL_MLD_TPT_COUNT_WINDOW)) {
+		memset(queue_counter->per_link, 0,
+		       sizeof(queue_counter->per_link));
+		queue_counter->window_start_time = jiffies;
+
+		IWL_DEBUG_INFO(mld, "MPDU counters are cleared\n");
+	}
+
+	link_counter = &queue_counter->per_link[mld_link->fw_id];
+
+	spin_lock_bh(&queue_counter->lock);
+
+	/* Update the statistics for this TPT measurement window */
+	if (tx)
+		link_counter->tx += count;
+	else
+		link_counter->rx += count;
+
+	/*
+	 * Next, evaluate whether we should queue an unblock,
+	 * skip this if we are not blocked due to low throughput.
+	 */
+	if (!(mld_vif->emlsr.blocked_reasons & IWL_MLD_EMLSR_BLOCKED_TPT))
+		goto unlock;
+
+	for (int i = 0; i <= IWL_FW_MAX_LINK_ID; i++)
+		total_mpdus += tx ? queue_counter->per_link[i].tx :
+				    queue_counter->per_link[i].rx;
+
+	/* Unblock is already queued if the threshold was reached before */
+	if (total_mpdus - count >= IWL_MLD_ENTER_EMLSR_TPT_THRESH)
+		goto unlock;
+
+	if (total_mpdus >= IWL_MLD_ENTER_EMLSR_TPT_THRESH)
+		wiphy_work_queue(mld->wiphy, &mld_vif->emlsr.unblock_tpt_wk);
+
+unlock:
+	spin_unlock_bh(&queue_counter->lock);
+}
+
+/* must be called under rcu_read_lock() */
+void iwl_mld_count_mpdu_rx(struct ieee80211_link_sta *link_sta, int queue,
+			   u32 count)
+{
+	iwl_mld_count_mpdu(link_sta, queue, count, false);
+}
+
+/* must be called under rcu_read_lock() */
+void iwl_mld_count_mpdu_tx(struct ieee80211_link_sta *link_sta, u32 count)
+{
+	/* use queue 0 for all TX */
+	iwl_mld_count_mpdu(link_sta, 0, count, true);
+}
+
+static int iwl_mld_allocate_internal_txq(struct iwl_mld *mld,
+					 struct iwl_mld_int_sta *internal_sta,
+					 u8 tid)
+{
+	u32 sta_mask = BIT(internal_sta->sta_id);
+	int queue, size;
+
+	size = max_t(u32, IWL_MGMT_QUEUE_SIZE,
+		     mld->trans->cfg->min_txq_size);
+
+	queue = iwl_trans_txq_alloc(mld->trans, 0, sta_mask, tid, size,
+				    IWL_WATCHDOG_DISABLED);
+
+	if (queue >= 0)
+		IWL_DEBUG_TX_QUEUES(mld,
+				    "Enabling TXQ #%d for sta mask 0x%x tid %d\n",
+				    queue, sta_mask, tid);
+	return queue;
+}
+
+static int iwl_mld_send_aux_sta_cmd(struct iwl_mld *mld,
+				    const struct iwl_mld_int_sta *internal_sta)
+{
+	struct iwl_aux_sta_cmd cmd = {
+		.sta_id = cpu_to_le32(internal_sta->sta_id),
+		/* TODO: CDB - properly set the lmac_id */
+		.lmac_id = cpu_to_le32(IWL_LMAC_24G_INDEX),
+	};
+
+	return iwl_mld_send_cmd_pdu(mld, WIDE_ID(MAC_CONF_GROUP, AUX_STA_CMD),
+				    &cmd);
+}
+
+static int
+iwl_mld_add_internal_sta_to_fw(struct iwl_mld *mld,
+			       const struct iwl_mld_int_sta *internal_sta,
+			       u8 fw_link_id,
+			       const u8 *addr)
+{
+	struct iwl_sta_cfg_cmd cmd = {};
+
+	if (internal_sta->sta_type == STATION_TYPE_AUX)
+		return iwl_mld_send_aux_sta_cmd(mld, internal_sta);
+
+	cmd.sta_id = cpu_to_le32((u8)internal_sta->sta_id);
+	cmd.link_id = cpu_to_le32(fw_link_id);
+	cmd.station_type = cpu_to_le32(internal_sta->sta_type);
+
+	/* FW doesn't allow to add a IGTK/BIGTK if the sta isn't marked as MFP.
+	 * On the other hand, FW will never check this flag during RX since
+	 * an AP/GO doesn't receive protected broadcast management frames.
+	 * So, we can set it unconditionally.
+	 */
+	if (internal_sta->sta_type == STATION_TYPE_BCAST_MGMT)
+		cmd.mfp = cpu_to_le32(1);
+
+	if (addr) {
+		memcpy(cmd.peer_mld_address, addr, ETH_ALEN);
+		memcpy(cmd.peer_link_address, addr, ETH_ALEN);
+	}
+
+	return iwl_mld_send_sta_cmd(mld, &cmd);
+}
+
+static int iwl_mld_add_internal_sta(struct iwl_mld *mld,
+				    struct iwl_mld_int_sta *internal_sta,
+				    enum iwl_fw_sta_type sta_type,
+				    u8 fw_link_id, const u8 *addr, u8 tid)
+{
+	int ret, queue_id;
+
+	ret = iwl_mld_allocate_link_sta_fw_id(mld,
+					      &internal_sta->sta_id,
+					      ERR_PTR(-EINVAL));
+	if (ret)
+		return ret;
+
+	internal_sta->sta_type = sta_type;
+
+	ret = iwl_mld_add_internal_sta_to_fw(mld, internal_sta, fw_link_id,
+					     addr);
+	if (ret)
+		goto err;
+
+	queue_id = iwl_mld_allocate_internal_txq(mld, internal_sta, tid);
+	if (queue_id < 0) {
+		iwl_mld_rm_sta_from_fw(mld, internal_sta->sta_id);
+		ret = queue_id;
+		goto err;
+	}
+
+	internal_sta->queue_id = queue_id;
+
+	return 0;
+err:
+	iwl_mld_free_internal_sta(mld, internal_sta);
+	return ret;
+}
+
+int iwl_mld_add_bcast_sta(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	const u8 bcast_addr[] = {0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF};
+	const u8 *addr;
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+		    vif->type != NL80211_IFTYPE_ADHOC))
+		return -EINVAL;
+
+	addr = vif->type == NL80211_IFTYPE_ADHOC ? link->bssid : bcast_addr;
+
+	return iwl_mld_add_internal_sta(mld, &mld_link->bcast_sta,
+					STATION_TYPE_BCAST_MGMT,
+					mld_link->fw_id, addr,
+					IWL_MGMT_TID);
+}
+
+int iwl_mld_add_mcast_sta(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+	const u8 mcast_addr[] = {0x03, 0x00, 0x00, 0x00, 0x00, 0x00};
+
+	if (WARN_ON(!mld_link))
+		return -EINVAL;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+		    vif->type != NL80211_IFTYPE_ADHOC))
+		return -EINVAL;
+
+	return iwl_mld_add_internal_sta(mld, &mld_link->mcast_sta,
+					STATION_TYPE_MCAST,
+					mld_link->fw_id, mcast_addr, 0);
+}
+
+int iwl_mld_add_aux_sta(struct iwl_mld *mld,
+			struct iwl_mld_int_sta *internal_sta)
+{
+	return iwl_mld_add_internal_sta(mld, internal_sta, STATION_TYPE_AUX,
+					0, NULL, IWL_MAX_TID_COUNT);
+}
+
+static void iwl_mld_remove_internal_sta(struct iwl_mld *mld,
+					struct iwl_mld_int_sta *internal_sta,
+					bool flush, u8 tid)
+{
+	if (WARN_ON_ONCE(internal_sta->sta_id == IWL_INVALID_STA ||
+			 internal_sta->queue_id == IWL_MLD_INVALID_QUEUE))
+		return;
+
+	if (flush)
+		iwl_mld_flush_link_sta_txqs(mld, internal_sta->sta_id);
+
+	iwl_mld_free_txq(mld, BIT(internal_sta->sta_id),
+			 tid, internal_sta->queue_id);
+
+	iwl_mld_rm_sta_from_fw(mld, internal_sta->sta_id);
+
+	iwl_mld_free_internal_sta(mld, internal_sta);
+}
+
+void iwl_mld_remove_bcast_sta(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+
+	if (WARN_ON(!mld_link))
+		return;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+		    vif->type != NL80211_IFTYPE_ADHOC))
+		return;
+
+	iwl_mld_remove_internal_sta(mld, &mld_link->bcast_sta, true,
+				    IWL_MGMT_TID);
+}
+
+void iwl_mld_remove_mcast_sta(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+
+	if (WARN_ON(!mld_link))
+		return;
+
+	if (WARN_ON(vif->type != NL80211_IFTYPE_AP &&
+		    vif->type != NL80211_IFTYPE_ADHOC))
+		return;
+
+	iwl_mld_remove_internal_sta(mld, &mld_link->mcast_sta, true, 0);
+}
+
+void iwl_mld_remove_aux_sta(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_bss_conf *link)
+{
+	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
+
+	if (WARN_ON(!mld_link))
+		return;
+
+	/* TODO: Hotspot 2.0 */
+	if (WARN_ON(vif->type != NL80211_IFTYPE_P2P_DEVICE))
+		return;
+
+	iwl_mld_remove_internal_sta(mld, &mld_link->aux_sta, false,
+				    IWL_MAX_TID_COUNT);
+}
+
+static int iwl_mld_update_sta_resources(struct iwl_mld *mld,
+					struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta,
+					u32 old_sta_mask,
+					u32 new_sta_mask)
+{
+	int ret;
+
+	ret = iwl_mld_update_sta_txqs(mld, sta, old_sta_mask, new_sta_mask);
+	if (ret)
+		return ret;
+
+	ret = iwl_mld_update_sta_keys(mld, vif, sta, old_sta_mask, new_sta_mask);
+	if (ret)
+		return ret;
+
+	return iwl_mld_update_sta_baids(mld, old_sta_mask, new_sta_mask);
+}
+
+int iwl_mld_update_link_stas(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *sta,
+			     u16 old_links, u16 new_links)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_link_sta *mld_link_sta;
+	unsigned long links_to_add = ~old_links & new_links;
+	unsigned long links_to_rem = old_links & ~new_links;
+	unsigned long old_links_long = old_links;
+	unsigned long sta_mask_added = 0;
+	u32 current_sta_mask = 0, sta_mask_to_rem = 0;
+	unsigned int link_id, sta_id;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for_each_set_bit(link_id, &old_links_long,
+			 IEEE80211_MLD_MAX_NUM_LINKS) {
+		mld_link_sta =
+			iwl_mld_link_sta_dereference_check(mld_sta, link_id);
+
+		if (WARN_ON(!mld_link_sta))
+			return -EINVAL;
+
+		current_sta_mask |= BIT(mld_link_sta->fw_id);
+		if (links_to_rem & BIT(link_id))
+			sta_mask_to_rem |= BIT(mld_link_sta->fw_id);
+	}
+
+	if (sta_mask_to_rem) {
+		ret = iwl_mld_update_sta_resources(mld, vif, sta,
+						   current_sta_mask,
+						   current_sta_mask &
+							~sta_mask_to_rem);
+		if (ret)
+			return ret;
+
+		current_sta_mask &= ~sta_mask_to_rem;
+	}
+
+	for_each_set_bit(link_id, &links_to_rem, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_link_sta *link_sta =
+			link_sta_dereference_protected(sta, link_id);
+
+		if (WARN_ON(!link_sta))
+			return -EINVAL;
+
+		iwl_mld_remove_link_sta(mld, link_sta);
+	}
+
+	for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_link_sta *link_sta =
+			link_sta_dereference_protected(sta, link_id);
+		struct ieee80211_bss_conf *link;
+
+		if (WARN_ON(!link_sta))
+			return -EINVAL;
+
+		ret = iwl_mld_add_link_sta(mld, link_sta);
+		if (ret)
+			goto remove_added_link_stas;
+
+		mld_link_sta =
+			iwl_mld_link_sta_dereference_check(mld_sta,
+							   link_id);
+
+		link = link_conf_dereference_protected(mld_sta->vif,
+						       link_sta->link_id);
+		iwl_mld_config_tlc_link(mld, vif, link, link_sta);
+
+		sta_mask_added |= BIT(mld_link_sta->fw_id);
+	}
+
+	if (sta_mask_added) {
+		ret = iwl_mld_update_sta_resources(mld, vif, sta,
+						   current_sta_mask,
+						   current_sta_mask |
+							sta_mask_added);
+		if (ret)
+			goto remove_added_link_stas;
+	}
+
+	/* We couldn't activate the links before it has a STA. Now we can */
+	for_each_set_bit(link_id, &links_to_add, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *link =
+			link_conf_dereference_protected(mld_sta->vif, link_id);
+
+		if (WARN_ON(!link))
+			continue;
+
+		iwl_mld_activate_link(mld, link);
+	}
+
+	return 0;
+
+remove_added_link_stas:
+	for_each_set_bit(sta_id, &sta_mask_added, mld->fw->ucode_capa.num_stations) {
+		struct ieee80211_link_sta *link_sta =
+			wiphy_dereference(mld->wiphy,
+					  mld->fw_id_to_link_sta[sta_id]);
+
+		if (WARN_ON(!link_sta))
+			continue;
+
+		iwl_mld_remove_link_sta(mld, link_sta);
+	}
+
+	return ret;
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.h b/drivers/net/wireless/intel/iwlwifi/mld/sta.h
new file mode 100644
index 0000000000000..ddcffd7b9fde1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.h
@@ -0,0 +1,266 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#ifndef __iwl_mld_sta_h__
+#define __iwl_mld_sta_h__
+
+#include <net/mac80211.h>
+
+#include "mld.h"
+#include "tx.h"
+
+/**
+ * struct iwl_mld_rxq_dup_data - Duplication detection data, per STA & Rx queue
+ * @last_seq: last sequence per tid.
+ * @last_sub_frame_idx: the index of the last subframe in an A-MSDU. This value
+ *	will be zero if the packet is not part of an A-MSDU.
+ */
+struct iwl_mld_rxq_dup_data {
+	__le16 last_seq[IWL_MAX_TID_COUNT + 1];
+	u8 last_sub_frame_idx[IWL_MAX_TID_COUNT + 1];
+} ____cacheline_aligned_in_smp;
+
+/**
+ * struct iwl_mld_link_sta - link-level station
+ *
+ * This represents the link-level sta - the driver level equivalent to the
+ * ieee80211_link_sta
+ *
+ * @last_rate_n_flags: rate_n_flags from the last &iwl_tlc_update_notif
+ * @signal_avg: the signal average coming from the firmware
+ * @in_fw: whether the link STA is uploaded to the FW (false during restart)
+ * @rcu_head: RCU head for freeing this object
+ * @fw_id: the FW id of this link sta.
+ */
+struct iwl_mld_link_sta {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		u32 last_rate_n_flags;
+		bool in_fw;
+		s8 signal_avg;
+	);
+	/* And here fields that survive a fw restart */
+	struct rcu_head rcu_head;
+	u32 fw_id;
+};
+
+#define iwl_mld_link_sta_dereference_check(mld_sta, link_id)		\
+	rcu_dereference_check((mld_sta)->link[link_id],			\
+			      lockdep_is_held(&mld_sta->mld->wiphy->mtx))
+
+#define for_each_mld_link_sta(mld_sta, link_sta, link_id)		\
+	for (link_id = 0; link_id < ARRAY_SIZE((mld_sta)->link);	\
+	     link_id++)							\
+		if ((link_sta =						\
+			iwl_mld_link_sta_dereference_check(mld_sta, link_id)))
+
+#define IWL_NUM_DEFAULT_KEYS 4
+
+/* struct iwl_mld_ptk_pn - Holds Packet Number (PN) per TID.
+ * @rcu_head: RCU head for freeing this data.
+ * @pn: Array storing PN for each TID.
+ */
+struct iwl_mld_ptk_pn {
+	struct rcu_head rcu_head;
+	struct {
+		u8 pn[IWL_MAX_TID_COUNT][IEEE80211_CCMP_PN_LEN];
+	} ____cacheline_aligned_in_smp q[];
+};
+
+/**
+ * struct iwl_mld_per_link_mpdu_counter - per-link TX/RX MPDU counters
+ *
+ * @tx: Number of TX MPDUs.
+ * @rx: Number of RX MPDUs.
+ */
+struct iwl_mld_per_link_mpdu_counter {
+	u32 tx;
+	u32 rx;
+};
+
+/**
+ * struct iwl_mld_per_q_mpdu_counter - per-queue MPDU counter
+ *
+ * @lock: Needed to protect the counters when modified from statistics.
+ * @per_link: per-link counters.
+ * @window_start_time: timestamp of the counting-window start
+ */
+struct iwl_mld_per_q_mpdu_counter {
+	spinlock_t lock;
+	struct iwl_mld_per_link_mpdu_counter per_link[IWL_FW_MAX_LINK_ID + 1];
+	unsigned long window_start_time;
+} ____cacheline_aligned_in_smp;
+
+/**
+ * struct iwl_mld_sta - representation of a station in the driver.
+ *
+ * This represent the MLD-level sta, and will not be added to the FW.
+ * Embedded in ieee80211_sta.
+ *
+ * @vif: pointer the vif object.
+ * @sta_state: station state according to enum %ieee80211_sta_state
+ * @sta_type: type of this station. See &enum iwl_fw_sta_type
+ * @mld: a pointer to the iwl_mld object
+ * @dup_data: per queue duplicate packet detection data
+ * @data_tx_ant: stores the last TX antenna index; used for setting
+ *	TX rate_n_flags for injected data frames (toggles on every TX failure).
+ * @tid_to_baid: a simple map of TID to Block-Ack fw id
+ * @deflink: This holds the default link STA information, for non MLO STA all
+ *	link specific STA information is accessed through @deflink or through
+ *	link[0] which points to address of @deflink. For MLO Link STA
+ *	the first added link STA will point to deflink.
+ * @link: reference to Link Sta entries. For Non MLO STA, except 1st link,
+ *	i.e link[0] all links would be assigned to NULL by default and
+ *	would access link information via @deflink or link[0]. For MLO
+ *	STA, first link STA being added will point its link pointer to
+ *	@deflink address and remaining would be allocated and the address
+ *	would be assigned to link[link_id] where link_id is the id assigned
+ *	by the AP.
+ * @ptk_pn: Array of pointers to PTK PN data, used to track the Packet Number
+ *	per key index and per queue (TID).
+ * @mpdu_counters: RX/TX MPDUs counters for each queue.
+ */
+struct iwl_mld_sta {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		enum ieee80211_sta_state sta_state;
+		enum iwl_fw_sta_type sta_type;
+	);
+	/* And here fields that survive a fw restart */
+	struct iwl_mld *mld;
+	struct ieee80211_vif *vif;
+	struct iwl_mld_rxq_dup_data *dup_data;
+	u8 tid_to_baid[IWL_MAX_TID_COUNT];
+	u8 data_tx_ant;
+
+	struct iwl_mld_link_sta deflink;
+	struct iwl_mld_link_sta __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
+	struct iwl_mld_ptk_pn __rcu *ptk_pn[IWL_NUM_DEFAULT_KEYS];
+	struct iwl_mld_per_q_mpdu_counter *mpdu_counters;
+};
+
+static inline struct iwl_mld_sta *
+iwl_mld_sta_from_mac80211(struct ieee80211_sta *sta)
+{
+	return (void *)sta->drv_priv;
+}
+
+static inline void
+iwl_mld_cleanup_sta(void *data, struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_link_sta *mld_link_sta;
+	u8 link_id;
+
+	for (int i = 0; i < ARRAY_SIZE(sta->txq); i++)
+		CLEANUP_STRUCT(iwl_mld_txq_from_mac80211(sta->txq[i]));
+
+	for_each_mld_link_sta(mld_sta, mld_link_sta, link_id) {
+		CLEANUP_STRUCT(mld_link_sta);
+
+		if (!ieee80211_vif_is_mld(mld_sta->vif)) {
+			/* not an MLD STA; only has the deflink with ID zero */
+			WARN_ON(link_id);
+			continue;
+		}
+
+		if (mld_sta->vif->active_links & BIT(link_id))
+			continue;
+
+		/* Should not happen as link removal should always succeed */
+		WARN_ON(1);
+		RCU_INIT_POINTER(mld_sta->link[link_id], NULL);
+		RCU_INIT_POINTER(mld_sta->mld->fw_id_to_link_sta[mld_link_sta->fw_id],
+				 NULL);
+		if (mld_link_sta != &mld_sta->deflink)
+			kfree_rcu(mld_link_sta, rcu_head);
+	}
+
+	CLEANUP_STRUCT(mld_sta);
+}
+
+static inline struct iwl_mld_link_sta *
+iwl_mld_link_sta_from_mac80211(struct ieee80211_link_sta *link_sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+
+	return iwl_mld_link_sta_dereference_check(mld_sta, link_sta->link_id);
+}
+
+int iwl_mld_add_sta(struct iwl_mld *mld, struct ieee80211_sta *sta,
+		    struct ieee80211_vif *vif, enum iwl_fw_sta_type type);
+void iwl_mld_remove_sta(struct iwl_mld *mld, struct ieee80211_sta *sta);
+int iwl_mld_fw_sta_id_from_link_sta(struct iwl_mld *mld,
+				    struct ieee80211_link_sta *link_sta);
+u32 iwl_mld_fw_sta_id_mask(struct iwl_mld *mld, struct ieee80211_sta *sta);
+int iwl_mld_update_all_link_stations(struct iwl_mld *mld,
+				     struct ieee80211_sta *sta);
+void iwl_mld_flush_sta_txqs(struct iwl_mld *mld, struct ieee80211_sta *sta);
+void iwl_mld_wait_sta_txqs_empty(struct iwl_mld *mld,
+				 struct ieee80211_sta *sta);
+void iwl_mld_count_mpdu_rx(struct ieee80211_link_sta *link_sta, int queue,
+			   u32 count);
+void iwl_mld_count_mpdu_tx(struct ieee80211_link_sta *link_sta, u32 count);
+
+/**
+ * struct iwl_mld_int_sta - representation of an internal station
+ * (a station that exist in FW and in driver, but not in mac80211)
+ *
+ * @sta_id: the index of the station in the fw
+ * @queue_id: the if of the queue used by the station
+ * @sta_type: station type. One of &iwl_fw_sta_type
+ */
+struct iwl_mld_int_sta {
+	u8 sta_id;
+	u32 queue_id;
+	enum iwl_fw_sta_type sta_type;
+};
+
+static inline void
+iwl_mld_init_internal_sta(struct iwl_mld_int_sta *internal_sta)
+{
+	internal_sta->sta_id = IWL_INVALID_STA;
+	internal_sta->queue_id = IWL_MLD_INVALID_QUEUE;
+}
+
+static inline void
+iwl_mld_free_internal_sta(struct iwl_mld *mld,
+			  struct iwl_mld_int_sta *internal_sta)
+{
+	if (WARN_ON(internal_sta->sta_id == IWL_INVALID_STA))
+		return;
+
+	RCU_INIT_POINTER(mld->fw_id_to_link_sta[internal_sta->sta_id], NULL);
+	iwl_mld_init_internal_sta(internal_sta);
+}
+
+int iwl_mld_add_bcast_sta(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link);
+
+int iwl_mld_add_mcast_sta(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_bss_conf *link);
+
+int iwl_mld_add_aux_sta(struct iwl_mld *mld,
+			struct iwl_mld_int_sta *internal_sta);
+
+void iwl_mld_remove_bcast_sta(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link);
+
+void iwl_mld_remove_mcast_sta(struct iwl_mld *mld,
+			      struct ieee80211_vif *vif,
+			      struct ieee80211_bss_conf *link);
+
+void iwl_mld_remove_aux_sta(struct iwl_mld *mld,
+			    struct ieee80211_vif *vif,
+			    struct ieee80211_bss_conf *link);
+
+int iwl_mld_update_link_stas(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_sta *sta,
+			     u16 old_links, u16 new_links);
+#endif /* __iwl_mld_sta_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
new file mode 100644
index 0000000000000..842b9b9fdd8c7
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -0,0 +1,509 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#include "mld.h"
+#include "stats.h"
+#include "sta.h"
+#include "mlo.h"
+#include "hcmd.h"
+#include "iface.h"
+#include "scan.h"
+#include "phy.h"
+#include "fw/api/stats.h"
+
+static int iwl_mld_send_fw_stats_cmd(struct iwl_mld *mld, u32 cfg_mask,
+				     u32 cfg_time, u32 type_mask)
+{
+	u32 cmd_id = WIDE_ID(SYSTEM_GROUP, SYSTEM_STATISTICS_CMD);
+	struct iwl_system_statistics_cmd stats_cmd = {
+		.cfg_mask = cpu_to_le32(cfg_mask),
+		.config_time_sec = cpu_to_le32(cfg_time),
+		.type_id_mask = cpu_to_le32(type_mask),
+	};
+
+	return iwl_mld_send_cmd_pdu(mld, cmd_id, &stats_cmd);
+}
+
+int iwl_mld_clear_stats_in_fw(struct iwl_mld *mld)
+{
+	u32 cfg_mask = IWL_STATS_CFG_FLG_ON_DEMAND_NTFY_MSK;
+	u32 type_mask = IWL_STATS_NTFY_TYPE_ID_OPER |
+			IWL_STATS_NTFY_TYPE_ID_OPER_PART1;
+
+	return iwl_mld_send_fw_stats_cmd(mld, cfg_mask, 0, type_mask);
+}
+
+static void
+iwl_mld_fill_stats_from_oper_notif(struct iwl_mld *mld,
+				   struct iwl_rx_packet *pkt,
+				   u8 fw_sta_id, struct station_info *sinfo)
+{
+	const struct iwl_system_statistics_notif_oper *notif =
+		(void *)&pkt->data;
+	const struct iwl_stats_ntfy_per_sta *per_sta =
+		&notif->per_sta[fw_sta_id];
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_link_sta *mld_link_sta;
+
+	/* 0 isn't a valid value, but FW might send 0.
+	 * In that case, set the latest non-zero value we stored
+	 */
+	rcu_read_lock();
+
+	link_sta = rcu_dereference(mld->fw_id_to_link_sta[fw_sta_id]);
+	if (IS_ERR_OR_NULL(link_sta))
+		goto unlock;
+
+	mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+	if (WARN_ON(!mld_link_sta))
+		goto unlock;
+
+	if (per_sta->average_energy)
+		mld_link_sta->signal_avg =
+			-(s8)le32_to_cpu(per_sta->average_energy);
+
+	sinfo->signal_avg = mld_link_sta->signal_avg;
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_SIGNAL_AVG);
+
+unlock:
+	rcu_read_unlock();
+}
+
+struct iwl_mld_stats_data {
+	u8 fw_sta_id;
+	struct station_info *sinfo;
+	struct iwl_mld *mld;
+};
+
+static bool iwl_mld_wait_stats_handler(struct iwl_notif_wait_data *notif_data,
+				       struct iwl_rx_packet *pkt, void *data)
+{
+	struct iwl_mld_stats_data *stats_data = data;
+	u16 cmd = WIDE_ID(pkt->hdr.group_id, pkt->hdr.cmd);
+
+	switch (cmd) {
+	case WIDE_ID(STATISTICS_GROUP, STATISTICS_OPER_NOTIF):
+		iwl_mld_fill_stats_from_oper_notif(stats_data->mld, pkt,
+						   stats_data->fw_sta_id,
+						   stats_data->sinfo);
+		break;
+	case WIDE_ID(STATISTICS_GROUP, STATISTICS_OPER_PART1_NOTIF):
+		break;
+	case WIDE_ID(SYSTEM_GROUP, SYSTEM_STATISTICS_END_NOTIF):
+		return true;
+	}
+
+	return false;
+}
+
+static int
+iwl_mld_fw_stats_to_mac80211(struct iwl_mld *mld, struct iwl_mld_sta *mld_sta,
+			     struct station_info *sinfo)
+{
+	u32 cfg_mask = IWL_STATS_CFG_FLG_ON_DEMAND_NTFY_MSK |
+		       IWL_STATS_CFG_FLG_RESET_MSK;
+	u32 type_mask = IWL_STATS_NTFY_TYPE_ID_OPER |
+			IWL_STATS_NTFY_TYPE_ID_OPER_PART1;
+	static const u16 notifications[] = {
+		WIDE_ID(STATISTICS_GROUP, STATISTICS_OPER_NOTIF),
+		WIDE_ID(STATISTICS_GROUP, STATISTICS_OPER_PART1_NOTIF),
+		WIDE_ID(SYSTEM_GROUP, SYSTEM_STATISTICS_END_NOTIF),
+	};
+	struct iwl_mld_stats_data wait_stats_data = {
+		/* We don't support drv_sta_statistics in EMLSR */
+		.fw_sta_id = mld_sta->deflink.fw_id,
+		.sinfo = sinfo,
+		.mld = mld,
+	};
+	struct iwl_notification_wait stats_wait;
+	int ret;
+
+	iwl_init_notification_wait(&mld->notif_wait, &stats_wait,
+				   notifications, ARRAY_SIZE(notifications),
+				   iwl_mld_wait_stats_handler,
+				   &wait_stats_data);
+
+	ret = iwl_mld_send_fw_stats_cmd(mld, cfg_mask, 0, type_mask);
+	if (ret) {
+		iwl_remove_notification(&mld->notif_wait, &stats_wait);
+		return ret;
+	}
+
+	/* Wait 500ms for OPERATIONAL, PART1, and END notifications,
+	 * which should be sufficient for the firmware to gather data
+	 * from all LMACs and send notifications to the host.
+	 */
+	ret = iwl_wait_notification(&mld->notif_wait, &stats_wait, HZ / 2);
+	if (ret)
+		return ret;
+
+	/* When periodic statistics are sent, FW will clear its statistics DB.
+	 * If the statistics request here happens shortly afterwards,
+	 * the response will contain data collected over a short time
+	 * interval. The response we got here shouldn't be processed by
+	 * the general statistics processing because it's incomplete.
+	 * So, we delete it from the list so it won't be processed.
+	 */
+	iwl_mld_delete_handlers(mld, notifications, ARRAY_SIZE(notifications));
+
+	return 0;
+}
+
+#define PERIODIC_STATS_SECONDS 5
+
+int iwl_mld_request_periodic_fw_stats(struct iwl_mld *mld, bool enable)
+{
+	u32 cfg_mask = enable ? 0 : IWL_STATS_CFG_FLG_DISABLE_NTFY_MSK;
+	u32 type_mask = enable ? (IWL_STATS_NTFY_TYPE_ID_OPER |
+				  IWL_STATS_NTFY_TYPE_ID_OPER_PART1) : 0;
+	u32 cfg_time = enable ? PERIODIC_STATS_SECONDS : 0;
+
+	return iwl_mld_send_fw_stats_cmd(mld, cfg_mask, cfg_time, type_mask);
+}
+
+static void iwl_mld_sta_stats_fill_txrate(struct iwl_mld_sta *mld_sta,
+					  struct station_info *sinfo)
+{
+	struct rate_info *rinfo = &sinfo->txrate;
+	u32 rate_n_flags = mld_sta->deflink.last_rate_n_flags;
+	u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
+	u32 gi_ltf;
+
+	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
+
+	switch (rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK) {
+	case RATE_MCS_CHAN_WIDTH_20:
+		rinfo->bw = RATE_INFO_BW_20;
+		break;
+	case RATE_MCS_CHAN_WIDTH_40:
+		rinfo->bw = RATE_INFO_BW_40;
+		break;
+	case RATE_MCS_CHAN_WIDTH_80:
+		rinfo->bw = RATE_INFO_BW_80;
+		break;
+	case RATE_MCS_CHAN_WIDTH_160:
+		rinfo->bw = RATE_INFO_BW_160;
+		break;
+	case RATE_MCS_CHAN_WIDTH_320:
+		rinfo->bw = RATE_INFO_BW_320;
+		break;
+	}
+
+	if (format == RATE_MCS_CCK_MSK || format == RATE_MCS_LEGACY_OFDM_MSK) {
+		int rate = u32_get_bits(rate_n_flags, RATE_LEGACY_RATE_MSK);
+
+		/* add the offset needed to get to the legacy ofdm indices */
+		if (format == RATE_MCS_LEGACY_OFDM_MSK)
+			rate += IWL_FIRST_OFDM_RATE;
+
+		switch (rate) {
+		case IWL_RATE_1M_INDEX:
+			rinfo->legacy = 10;
+			break;
+		case IWL_RATE_2M_INDEX:
+			rinfo->legacy = 20;
+			break;
+		case IWL_RATE_5M_INDEX:
+			rinfo->legacy = 55;
+			break;
+		case IWL_RATE_11M_INDEX:
+			rinfo->legacy = 110;
+			break;
+		case IWL_RATE_6M_INDEX:
+			rinfo->legacy = 60;
+			break;
+		case IWL_RATE_9M_INDEX:
+			rinfo->legacy = 90;
+			break;
+		case IWL_RATE_12M_INDEX:
+			rinfo->legacy = 120;
+			break;
+		case IWL_RATE_18M_INDEX:
+			rinfo->legacy = 180;
+			break;
+		case IWL_RATE_24M_INDEX:
+			rinfo->legacy = 240;
+			break;
+		case IWL_RATE_36M_INDEX:
+			rinfo->legacy = 360;
+			break;
+		case IWL_RATE_48M_INDEX:
+			rinfo->legacy = 480;
+			break;
+		case IWL_RATE_54M_INDEX:
+			rinfo->legacy = 540;
+		}
+		return;
+	}
+
+	rinfo->nss = u32_get_bits(rate_n_flags, RATE_MCS_NSS_MSK) + 1;
+
+	if (format == RATE_MCS_HT_MSK)
+		rinfo->mcs = RATE_HT_MCS_INDEX(rate_n_flags);
+	else
+		rinfo->mcs = u32_get_bits(rate_n_flags, RATE_MCS_CODE_MSK);
+
+	if (rate_n_flags & RATE_MCS_SGI_MSK)
+		rinfo->flags |= RATE_INFO_FLAGS_SHORT_GI;
+
+	switch (format) {
+	case RATE_MCS_EHT_MSK:
+		rinfo->flags |= RATE_INFO_FLAGS_EHT_MCS;
+		break;
+	case RATE_MCS_HE_MSK:
+		gi_ltf = u32_get_bits(rate_n_flags, RATE_MCS_HE_GI_LTF_MSK);
+
+		rinfo->flags |= RATE_INFO_FLAGS_HE_MCS;
+
+		if (rate_n_flags & RATE_MCS_HE_106T_MSK) {
+			rinfo->bw = RATE_INFO_BW_HE_RU;
+			rinfo->he_ru_alloc = NL80211_RATE_INFO_HE_RU_ALLOC_106;
+		}
+
+		switch (rate_n_flags & RATE_MCS_HE_TYPE_MSK) {
+		case RATE_MCS_HE_TYPE_SU:
+		case RATE_MCS_HE_TYPE_EXT_SU:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else if (gi_ltf == 2)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else if (gi_ltf == 3)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			break;
+		case RATE_MCS_HE_TYPE_MU:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_0_8;
+			else if (gi_ltf == 2)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		case RATE_MCS_HE_TYPE_TRIG:
+			if (gi_ltf == 0 || gi_ltf == 1)
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_1_6;
+			else
+				rinfo->he_gi = NL80211_RATE_INFO_HE_GI_3_2;
+			break;
+		}
+
+		if (rate_n_flags & RATE_HE_DUAL_CARRIER_MODE_MSK)
+			rinfo->he_dcm = 1;
+		break;
+	case RATE_MCS_HT_MSK:
+		rinfo->flags |= RATE_INFO_FLAGS_MCS;
+		break;
+	case RATE_MCS_VHT_MSK:
+		rinfo->flags |= RATE_INFO_FLAGS_VHT_MCS;
+		break;
+	}
+}
+
+void iwl_mld_mac80211_sta_statistics(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta,
+				     struct station_info *sinfo)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+	/* This API is not EMLSR ready, so we cannot provide complete
+	 * information if EMLSR is active
+	 */
+	if (hweight16(vif->active_links) > 1)
+		return;
+
+	if (iwl_mld_fw_stats_to_mac80211(mld_sta->mld, mld_sta, sinfo))
+		return;
+
+	iwl_mld_sta_stats_fill_txrate(mld_sta, sinfo);
+
+	/* TODO: NL80211_STA_INFO_BEACON_RX */
+
+	/* TODO: NL80211_STA_INFO_BEACON_SIGNAL_AVG */
+}
+
+#define IWL_MLD_TRAFFIC_LOAD_MEDIUM_THRESH	10 /* percentage */
+#define IWL_MLD_TRAFFIC_LOAD_HIGH_THRESH	50 /* percentage */
+#define IWL_MLD_TRAFFIC_LOAD_MIN_WINDOW_USEC	(500 * 1000)
+
+static u8 iwl_mld_stats_load_percentage(u32 last_ts_usec, u32 curr_ts_usec,
+					u32 total_airtime_usec)
+{
+	u32 elapsed_usec = curr_ts_usec - last_ts_usec;
+
+	if (elapsed_usec < IWL_MLD_TRAFFIC_LOAD_MIN_WINDOW_USEC)
+		return 0;
+
+	return (100 * total_airtime_usec / elapsed_usec);
+}
+
+static void iwl_mld_stats_recalc_traffic_load(struct iwl_mld *mld,
+					      u32 total_airtime_usec,
+					      u32 curr_ts_usec)
+{
+	u32 last_ts_usec = mld->scan.traffic_load.last_stats_ts_usec;
+	u8 load_prec;
+
+	/* Skip the calculation as this is the first notification received */
+	if (!last_ts_usec)
+		goto out;
+
+	load_prec = iwl_mld_stats_load_percentage(last_ts_usec, curr_ts_usec,
+						  total_airtime_usec);
+
+	if (load_prec > IWL_MLD_TRAFFIC_LOAD_HIGH_THRESH)
+		mld->scan.traffic_load.status = IWL_MLD_TRAFFIC_HIGH;
+	else if (load_prec > IWL_MLD_TRAFFIC_LOAD_MEDIUM_THRESH)
+		mld->scan.traffic_load.status = IWL_MLD_TRAFFIC_MEDIUM;
+	else
+		mld->scan.traffic_load.status = IWL_MLD_TRAFFIC_LOW;
+
+out:
+	mld->scan.traffic_load.last_stats_ts_usec = curr_ts_usec;
+}
+
+static void iwl_mld_update_link_sig(struct ieee80211_vif *vif, int sig,
+				    struct ieee80211_bss_conf *bss_conf)
+{
+	struct iwl_mld *mld = iwl_mld_vif_from_mac80211(vif)->mld;
+	int exit_emlsr_thresh;
+
+	if (sig == 0) {
+		IWL_DEBUG_RX(mld, "RSSI is 0 - skip signal based decision\n");
+		return;
+	}
+
+	/* TODO: task=statistics handle CQM notifications */
+
+	if (!iwl_mld_vif_has_emlsr_cap(vif))
+		return;
+
+	/* Handle inactive EMLSR, check whether to switch links */
+	if (!iwl_mld_emlsr_active(vif)) {
+		if (sig < IWL_MLD_LOW_RSSI_MLO_SCAN_THRESH)
+			iwl_mld_trigger_link_selection(mld, vif);
+		return;
+	}
+
+	/* We are in EMLSR, check if we need to exit */
+	exit_emlsr_thresh =
+		iwl_mld_get_emlsr_rssi_thresh(mld, &bss_conf->chanreq.oper,
+					      true);
+
+	if (sig < exit_emlsr_thresh)
+		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_LOW_RSSI,
+				   iwl_mld_get_other_link(vif,
+							  bss_conf->link_id));
+}
+
+static void
+iwl_mld_process_per_link_stats(struct iwl_mld *mld,
+			       const struct iwl_stats_ntfy_per_link *per_link,
+			       u32 curr_ts_usec)
+{
+	u32 total_airtime_usec = 0;
+
+	for (u32 fw_id = 0;
+	     fw_id < ARRAY_SIZE(mld->fw_id_to_bss_conf);
+	     fw_id++) {
+		const struct iwl_stats_ntfy_per_link *link_stats;
+		struct ieee80211_bss_conf *bss_conf;
+		int sig;
+
+		bss_conf = wiphy_dereference(mld->wiphy,
+					     mld->fw_id_to_bss_conf[fw_id]);
+		if (!bss_conf || bss_conf->vif->type != NL80211_IFTYPE_STATION)
+			continue;
+
+		link_stats = &per_link[fw_id];
+
+		total_airtime_usec += le32_to_cpu(link_stats->air_time);
+
+		sig = -le32_to_cpu(link_stats->beacon_filter_average_energy);
+		iwl_mld_update_link_sig(bss_conf->vif, sig, bss_conf);
+
+		/* TODO: parse more fields here (task=statistics)*/
+	}
+
+	iwl_mld_stats_recalc_traffic_load(mld, total_airtime_usec,
+					  curr_ts_usec);
+}
+
+static void
+iwl_mld_process_per_sta_stats(struct iwl_mld *mld,
+			      const struct iwl_stats_ntfy_per_sta *per_sta)
+{
+	for (int i = 0; i < mld->fw->ucode_capa.num_stations; i++) {
+		struct ieee80211_link_sta *link_sta =
+			wiphy_dereference(mld->wiphy,
+					  mld->fw_id_to_link_sta[i]);
+		struct iwl_mld_link_sta *mld_link_sta;
+		s8 avg_energy =
+			-(s8)le32_to_cpu(per_sta[i].average_energy);
+
+		if (IS_ERR_OR_NULL(link_sta) || !avg_energy)
+			continue;
+
+		mld_link_sta = iwl_mld_link_sta_from_mac80211(link_sta);
+		if (WARN_ON(!mld_link_sta))
+			continue;
+
+		mld_link_sta->signal_avg = avg_energy;
+	}
+}
+
+static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
+				       struct ieee80211_chanctx_conf *ctx,
+				       void *data)
+{
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+	const struct iwl_stats_ntfy_per_phy *per_phy = data;
+
+	if (WARN_ON(phy->fw_id >= IWL_STATS_MAX_PHY_OPERATIONAL))
+		return;
+
+	phy->channel_load_by_us =
+		le32_to_cpu(per_phy[phy->fw_id].channel_load_by_us);
+
+	/* TODO: channel load not by us (task=statistics) */
+}
+
+static void
+iwl_mld_process_per_phy_stats(struct iwl_mld *mld,
+			      const struct iwl_stats_ntfy_per_phy *per_phy)
+{
+	ieee80211_iter_chan_contexts_mtx(mld->hw,
+					 iwl_mld_fill_chanctx_stats,
+					 (void *)(uintptr_t)per_phy);
+
+	/* channel_load_by_us may have been updated, so recheck */
+	iwl_mld_emlsr_check_chan_load(mld);
+}
+
+void iwl_mld_handle_stats_oper_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt)
+{
+	const struct iwl_system_statistics_notif_oper *stats =
+		(void *)&pkt->data;
+	u32 curr_ts_usec = le32_to_cpu(stats->time_stamp);
+
+	BUILD_BUG_ON(ARRAY_SIZE(stats->per_sta) != IWL_STATION_COUNT_MAX);
+	BUILD_BUG_ON(ARRAY_SIZE(stats->per_link) <
+		     ARRAY_SIZE(mld->fw_id_to_bss_conf));
+
+	iwl_mld_process_per_link_stats(mld, stats->per_link, curr_ts_usec);
+	iwl_mld_process_per_sta_stats(mld, stats->per_sta);
+	iwl_mld_process_per_phy_stats(mld, stats->per_phy);
+
+	iwl_mld_check_omi_bw_reduction(mld);
+}
+
+void iwl_mld_handle_stats_oper_part1_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt)
+{
+	/* TODO */
+}
+
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.h b/drivers/net/wireless/intel/iwlwifi/mld/stats.h
new file mode 100644
index 0000000000000..de434e66d5555
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_stats_h__
+#define __iwl_mld_stats_h__
+
+int iwl_mld_request_periodic_fw_stats(struct iwl_mld *mld, bool enable);
+
+void iwl_mld_mac80211_sta_statistics(struct ieee80211_hw *hw,
+				     struct ieee80211_vif *vif,
+				     struct ieee80211_sta *sta,
+				     struct station_info *sinfo);
+
+void iwl_mld_handle_stats_oper_notif(struct iwl_mld *mld,
+				     struct iwl_rx_packet *pkt);
+void iwl_mld_handle_stats_oper_part1_notif(struct iwl_mld *mld,
+					   struct iwl_rx_packet *pkt);
+
+int iwl_mld_clear_stats_in_fw(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_stats_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile b/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
new file mode 100644
index 0000000000000..36317feb923ba
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/Makefile
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+iwlmld-tests-y += module.o hcmd.o utils.o link.o rx.o agg.o link-selection.o
+
+ccflags-y += -I$(src)/../
+obj-$(CONFIG_IWLWIFI_KUNIT_TESTS) += iwlmld-tests.o
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
new file mode 100644
index 0000000000000..1fd664be1a7c2
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/agg.c
@@ -0,0 +1,663 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <kunit/test.h>
+#include <kunit/static_stub.h>
+#include <kunit/skbuff.h>
+
+#include "utils.h"
+#include "mld.h"
+#include "sta.h"
+#include "agg.h"
+#include "rx.h"
+
+#define FC_QOS_DATA (IEEE80211_FTYPE_DATA | IEEE80211_STYPE_QOS_DATA)
+#define BA_WINDOW_SIZE 64
+#define QUEUE 0
+
+static const struct reorder_buffer_case {
+	const char *desc;
+	struct {
+		/* ieee80211_hdr fields */
+		u16 fc;
+		u8 tid;
+		bool multicast;
+		/* iwl_rx_mpdu_desc fields */
+		u16 nssn;
+		/* used also for setting hdr::seq_ctrl */
+		u16 sn;
+		u8 baid;
+		bool amsdu;
+		bool last_subframe;
+		bool old_sn;
+		bool dup;
+	} rx_pkt;
+	struct {
+		bool valid;
+		u16 head_sn;
+		u8 baid;
+		u16 num_entries;
+		/* The test prepares the reorder buffer with fake skbs based
+		 * on the sequence numbers provided in @entries array.
+		 */
+		struct {
+			u16 sn;
+			/* Set add_subframes > 0 to simulate an A-MSDU by
+			 * queueing additional @add_subframes skbs in the
+			 * appropriate reorder buffer entry (based on the @sn)
+			 */
+			u8 add_subframes;
+		} entries[BA_WINDOW_SIZE];
+	} reorder_buf_state;
+	struct {
+		enum iwl_mld_reorder_result reorder_res;
+		u16 head_sn;
+		u16 num_stored;
+		u16 skb_release_order[BA_WINDOW_SIZE];
+		u16 skb_release_order_count;
+	} expected;
+} reorder_buffer_cases[] = {
+	{
+		.desc = "RX packet with invalid BAID",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.baid = IWL_RX_REORDER_DATA_INVALID_BAID,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+		},
+		.expected = {
+			/* Invalid BAID should not be buffered. The frame is
+			 * passed to the network stack immediately.
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+			.num_stored = 0,
+		},
+	},
+	{
+		.desc = "RX Multicast packet",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.multicast = true,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+		},
+		.expected = {
+			/* Multicast packets are not buffered. The packet is
+			 * passed to the network stack immediately.
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+			.num_stored = 0,
+		},
+	},
+	{
+		.desc = "RX non-QoS data",
+		.rx_pkt = {
+			.fc = IEEE80211_FTYPE_DATA,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+		},
+		.expected = {
+			/* non-QoS data frames do not require reordering.
+			 * The packet is passed to the network stack
+			 * immediately.
+			 */
+		.reorder_res = IWL_MLD_PASS_SKB,
+		},
+	},
+	{
+		.desc = "RX old SN packet, reorder buffer is not yet valid",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.old_sn = true,
+		},
+		.reorder_buf_state = {
+			.valid = false,
+		},
+		.expected = {
+			/* The buffer is invalid and the RX packet has an old
+			 * SN. The packet is passed to the network stack
+			 * immediately.
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+		},
+	},
+	{
+		.desc = "RX old SN packet, reorder buffer valid",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.old_sn = true,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+		},
+		.expected = {
+			/* The buffer is valid and the RX packet has an old SN.
+			 * The packet should be dropped.
+			 */
+			.reorder_res = IWL_MLD_DROP_SKB,
+			.num_stored = 0,
+			.head_sn = 100,
+		},
+	},
+	{
+		.desc = "RX duplicate packet",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.dup = true,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+		},
+		.expected = {
+			/* Duplicate packets should be dropped */
+			.reorder_res = IWL_MLD_DROP_SKB,
+			.num_stored = 0,
+			.head_sn = 100,
+		},
+	},
+	{
+		.desc = "RX In-order packet, sn < nssn",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 100,
+			.nssn = 101,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+		},
+		.expected = {
+			/* 1. Reorder buffer is empty.
+			 * 2. RX packet SN is in order and less than NSSN.
+			 * Packet is released to the network stack immediately
+			 * and buffer->head_sn is updated to NSSN.
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+			.num_stored = 0,
+			.head_sn = 101,
+		},
+	},
+	{
+		.desc = "RX In-order packet, sn == head_sn",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 101,
+			.nssn = 100,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 101,
+		},
+		.expected = {
+			/* 1. Reorder buffer is empty.
+			 * 2. RX packet SN is equal to buffer->head_sn.
+			 * Packet is released to the network stack immediately
+			 * and buffer->head_sn is incremented.
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+			.num_stored = 0,
+			.head_sn = 102,
+		},
+	},
+	{
+		.desc = "RX In-order packet, IEEE80211_MAX_SN wrap around",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = IEEE80211_MAX_SN,
+			.nssn = IEEE80211_MAX_SN - 1,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = IEEE80211_MAX_SN,
+		},
+		.expected = {
+			/* 1. Reorder buffer is empty.
+			 * 2. RX SN == buffer->head_sn == IEEE80211_MAX_SN
+			 * Packet is released to the network stack immediately
+			 * and buffer->head_sn is incremented correctly (wraps
+			 * around to 0).
+			 */
+			.reorder_res = IWL_MLD_PASS_SKB,
+			.num_stored = 0,
+			.head_sn = 0,
+		},
+	},
+	{
+		.desc = "RX Out-of-order packet, pending packet in buffer",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 100,
+			.nssn = 102,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 1,
+			.entries[0].sn = 101,
+		},
+		.expected = {
+			/* 1. Reorder buffer contains one packet with SN=101.
+			 * 2. RX packet SN = buffer->head_sn.
+			 * Both packets are released (in order) to the network
+			 * stack as there are no gaps.
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 0,
+			.head_sn = 102,
+			.skb_release_order = {100, 101},
+			.skb_release_order_count = 2,
+		},
+	},
+	{
+		.desc = "RX Out-of-order packet, pending packet in buffer (wrap around)",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 0,
+			.nssn = 1,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = IEEE80211_MAX_SN - 1,
+			.num_entries = 1,
+			.entries[0].sn = IEEE80211_MAX_SN,
+		},
+		.expected = {
+			/* 1. Reorder buffer contains one packet with
+			 *    SN=IEEE80211_MAX_SN.
+			 * 2. RX Packet SN = 0 (after wrap around)
+			 * Both packets are released (in order) to the network
+			 * stack as there are no gaps.
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 0,
+			.head_sn = 1,
+			.skb_release_order = { 4095, 0 },
+			.skb_release_order_count = 2,
+		},
+	},
+	{
+		.desc = "RX Out-of-order packet, filling 1/2 holes in buffer, release RX packet",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 100,
+			.nssn = 101,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 1,
+			.entries[0].sn = 102,
+		},
+		.expected = {
+			/* 1. Reorder buffer contains one packet with SN=102.
+			 * 2. There are 2 holes at SN={100, 101}.
+			 * Only the RX packet (SN=100) is released, there is
+			 * still a hole at 101.
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 1,
+			.head_sn = 101,
+			.skb_release_order = {100},
+			.skb_release_order_count = 1,
+		},
+	},
+	{
+		.desc = "RX Out-of-order packet, filling 1/2 holes, release 2 packets",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 102,
+			.nssn = 103,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 3,
+			.entries[0].sn = 101,
+			.entries[1].sn = 104,
+			.entries[2].sn = 105,
+		},
+		.expected = {
+			/* 1. Reorder buffer contains three packets.
+			 * 2. RX packet fills one of two holes (at SN=102).
+			 * Two packets are released (until the next hole at
+			 * SN=103).
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 2,
+			.head_sn = 103,
+			.skb_release_order = {101, 102},
+			.skb_release_order_count = 2,
+		},
+	},
+		{
+		.desc = "RX Out-of-order packet, filling 1/1 holes, no packets released",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 102,
+			.nssn = 100,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 3,
+			.entries[0].sn = 101,
+			.entries[1].sn = 103,
+			.entries[2].sn = 104,
+		},
+		.expected = {
+			/* 1. Reorder buffer contains three packets:
+			 *    SN={101, 103, 104}.
+			 * 2. RX packet fills a hole (SN=102), but NSSN is
+			 *    smaller than buffered frames.
+			 * No packets can be released yet and buffer->head_sn
+			 * is not updated.
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 4,
+			.head_sn = 100,
+		},
+	},
+	{
+		.desc = "RX In-order A-MSDU, last subframe",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 100,
+			.nssn = 101,
+			.amsdu = true,
+			.last_subframe = true,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 1,
+			.entries[0] = {
+				.sn = 100,
+				.add_subframes = 1,
+			},
+		},
+		.expected = {
+			/* 1. Reorder buffer contains a 2-sub frames A-MSDU
+			 *    at SN=100.
+			 * 2. RX packet is the last SN=100 A-MSDU subframe
+			 * All packets are released in order (3 x SN=100).
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 0,
+			.head_sn = 101,
+			.skb_release_order = {100, 100, 100},
+			.skb_release_order_count = 3,
+		},
+	},
+	{
+		.desc = "RX In-order A-MSDU, not the last subframe",
+		.rx_pkt = {
+			.fc = FC_QOS_DATA,
+			.sn = 100,
+			.nssn = 101,
+			.amsdu = true,
+			.last_subframe = false,
+		},
+		.reorder_buf_state = {
+			.valid = true,
+			.head_sn = 100,
+			.num_entries = 1,
+			.entries[0] = {
+				.sn = 100,
+				.add_subframes = 1,
+			},
+		},
+		.expected = {
+			/* 1. Reorder buffer contains a 2-sub frames A-MSDU
+			 *    at SN=100.
+			 * 2. RX packet additional SN=100 A-MSDU subframe,
+			 *    but not the last one
+			 * No packets are released and head_sn is not updated.
+			 */
+			.reorder_res = IWL_MLD_BUFFERED_SKB,
+			.num_stored = 3,
+			.head_sn = 100,
+		},
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(test_reorder_buffer, reorder_buffer_cases, desc);
+
+static struct sk_buff_head g_released_skbs;
+static u16 g_num_released_skbs;
+
+/* Add released skbs from reorder buffer to a global list; This allows us
+ * to verify the correct release order of packets after they pass through the
+ * simulated reorder logic.
+ */
+static void
+fake_iwl_mld_pass_packet_to_mac80211(struct iwl_mld *mld,
+				     struct napi_struct *napi,
+				     struct sk_buff *skb, int queue,
+				     struct ieee80211_sta *sta)
+{
+	__skb_queue_tail(&g_released_skbs, skb);
+	g_num_released_skbs++;
+}
+
+static u32
+fake_iwl_mld_fw_sta_id_mask(struct iwl_mld *mld, struct ieee80211_sta *sta)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld_link_sta *mld_link_sta;
+	u8 link_id;
+	u32 sta_mask = 0;
+
+	/* This is the expectation in the real function */
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* We can't use for_each_sta_active_link */
+	for_each_mld_link_sta(mld_sta, mld_link_sta, link_id)
+		sta_mask |= BIT(mld_link_sta->fw_id);
+	return sta_mask;
+}
+
+static struct iwl_rx_mpdu_desc *setup_mpdu_desc(void)
+{
+	struct kunit *test = kunit_get_current_test();
+	const struct reorder_buffer_case *param =
+		(const void *)(test->param_value);
+	struct iwl_rx_mpdu_desc *mpdu_desc;
+
+	KUNIT_ALLOC_AND_ASSERT(test, mpdu_desc);
+
+	mpdu_desc->reorder_data |=
+		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_BAID_MASK,
+				       param->rx_pkt.baid));
+	mpdu_desc->reorder_data |=
+		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_SN_MASK,
+				       param->rx_pkt.sn));
+	mpdu_desc->reorder_data |=
+		cpu_to_le32(FIELD_PREP(IWL_RX_MPDU_REORDER_NSSN_MASK,
+				       param->rx_pkt.nssn));
+	if (param->rx_pkt.old_sn)
+		mpdu_desc->reorder_data |=
+			cpu_to_le32(IWL_RX_MPDU_REORDER_BA_OLD_SN);
+
+	if (param->rx_pkt.dup)
+		mpdu_desc->status |= cpu_to_le32(IWL_RX_MPDU_STATUS_DUPLICATE);
+
+	if (param->rx_pkt.amsdu) {
+		mpdu_desc->mac_flags2 |= IWL_RX_MPDU_MFLG2_AMSDU;
+		if (param->rx_pkt.last_subframe)
+			mpdu_desc->amsdu_info |=
+				IWL_RX_MPDU_AMSDU_LAST_SUBFRAME;
+	}
+
+	return mpdu_desc;
+}
+
+static struct sk_buff *alloc_and_setup_skb(u16 fc, u16 seq_ctrl, u8 tid,
+					   bool mcast)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_hdr hdr = {
+		.frame_control = cpu_to_le16(fc),
+		.seq_ctrl = cpu_to_le16(seq_ctrl),
+	};
+	struct sk_buff *skb;
+
+	skb = kunit_zalloc_skb(test, 128, GFP_KERNEL);
+	KUNIT_ASSERT_NOT_NULL(test, skb);
+
+	if (ieee80211_is_data_qos(hdr.frame_control)) {
+		u8 *qc = ieee80211_get_qos_ctl(&hdr);
+
+		qc[0] = tid & IEEE80211_QOS_CTL_TID_MASK;
+	}
+
+	if (mcast)
+		hdr.addr1[0] = 0x1;
+
+	skb_set_mac_header(skb, skb->len);
+	skb_put_data(skb, &hdr, ieee80211_hdrlen(hdr.frame_control));
+
+	return skb;
+}
+
+static struct iwl_mld_reorder_buffer *
+setup_reorder_buffer(struct iwl_mld_baid_data *baid_data)
+{
+	struct kunit *test = kunit_get_current_test();
+	const struct reorder_buffer_case *param =
+		(const void *)(test->param_value);
+	struct iwl_mld_reorder_buffer *buffer = baid_data->reorder_buf;
+	struct iwl_mld_reorder_buf_entry *entries = baid_data->entries;
+	struct sk_buff *fake_skb;
+
+	buffer->valid = param->reorder_buf_state.valid;
+	buffer->head_sn = param->reorder_buf_state.head_sn;
+	buffer->queue = QUEUE;
+
+	for (int i = 0; i < baid_data->buf_size; i++)
+		__skb_queue_head_init(&entries[i].frames);
+
+	for (int i = 0; i < param->reorder_buf_state.num_entries; i++) {
+		u16 sn = param->reorder_buf_state.entries[i].sn;
+		int index = sn % baid_data->buf_size;
+		u8 add_subframes =
+			param->reorder_buf_state.entries[i].add_subframes;
+		/* create 1 skb per entry + additional skbs per num of
+		 * requested subframes
+		 */
+		u8 num_skbs = 1 + add_subframes;
+
+		for (int j = 0; j < num_skbs; j++) {
+			fake_skb = alloc_and_setup_skb(FC_QOS_DATA, sn, 0,
+						       false);
+			__skb_queue_tail(&entries[index].frames, fake_skb);
+			buffer->num_stored++;
+		}
+	}
+
+	return buffer;
+}
+
+static struct iwl_mld_reorder_buffer *setup_ba_data(struct ieee80211_sta *sta)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	const struct reorder_buffer_case *param =
+		(const void *)(test->param_value);
+	struct iwl_mld_baid_data *baid_data = NULL;
+	struct iwl_mld_reorder_buffer *buffer;
+	u32 reorder_buf_size = BA_WINDOW_SIZE * sizeof(baid_data->entries[0]);
+	u8 baid = param->reorder_buf_state.baid;
+
+	/* Assuming only 1 RXQ */
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, baid_data,
+				    sizeof(*baid_data) + reorder_buf_size);
+
+	baid_data->baid = baid;
+	baid_data->tid = param->rx_pkt.tid;
+	baid_data->buf_size = BA_WINDOW_SIZE;
+
+	wiphy_lock(mld->wiphy);
+	baid_data->sta_mask = iwl_mld_fw_sta_id_mask(mld, sta);
+	wiphy_unlock(mld->wiphy);
+
+	baid_data->entries_per_queue = BA_WINDOW_SIZE;
+
+	buffer = setup_reorder_buffer(baid_data);
+
+	KUNIT_EXPECT_NULL(test, rcu_access_pointer(mld->fw_id_to_ba[baid]));
+	rcu_assign_pointer(mld->fw_id_to_ba[baid], baid_data);
+
+	return buffer;
+}
+
+static void test_reorder_buffer(struct kunit *test)
+{
+	struct iwl_mld *mld = test->priv;
+	const struct reorder_buffer_case *param =
+		(const void *)(test->param_value);
+	struct iwl_rx_mpdu_desc *mpdu_desc;
+	struct ieee80211_vif *vif;
+	struct ieee80211_sta *sta;
+	struct sk_buff *skb;
+	struct iwl_mld_reorder_buffer *buffer;
+	enum iwl_mld_reorder_result reorder_res;
+	u16 skb_release_order_count = param->expected.skb_release_order_count;
+	u16 skb_idx = 0;
+
+	/* Init globals and activate stubs */
+	__skb_queue_head_init(&g_released_skbs);
+	g_num_released_skbs = 0;
+	kunit_activate_static_stub(test, iwl_mld_fw_sta_id_mask,
+				   fake_iwl_mld_fw_sta_id_mask);
+	kunit_activate_static_stub(test, iwl_mld_pass_packet_to_mac80211,
+				   fake_iwl_mld_pass_packet_to_mac80211);
+
+	vif = iwlmld_kunit_add_vif(false, NL80211_IFTYPE_STATION);
+	sta = iwlmld_kunit_setup_sta(vif, IEEE80211_STA_AUTHORIZED, -1);
+
+	/* Prepare skb, mpdu_desc, BA data and the reorder buffer */
+	skb = alloc_and_setup_skb(param->rx_pkt.fc, param->rx_pkt.sn,
+				  param->rx_pkt.tid, param->rx_pkt.multicast);
+	buffer = setup_ba_data(sta);
+	mpdu_desc = setup_mpdu_desc();
+
+	rcu_read_lock();
+	reorder_res = iwl_mld_reorder(mld, NULL, QUEUE, sta, skb, mpdu_desc);
+	rcu_read_unlock();
+
+	KUNIT_ASSERT_EQ(test, reorder_res, param->expected.reorder_res);
+	KUNIT_ASSERT_EQ(test, buffer->num_stored, param->expected.num_stored);
+	KUNIT_ASSERT_EQ(test, buffer->head_sn, param->expected.head_sn);
+
+	/* Verify skbs release order */
+	KUNIT_ASSERT_EQ(test, skb_release_order_count, g_num_released_skbs);
+	while ((skb = __skb_dequeue(&g_released_skbs))) {
+		struct ieee80211_hdr *hdr = (void *)skb_mac_header(skb);
+
+		KUNIT_ASSERT_EQ(test, le16_to_cpu(hdr->seq_ctrl),
+				param->expected.skb_release_order[skb_idx]);
+		skb_idx++;
+	}
+	KUNIT_ASSERT_EQ(test, skb_idx, skb_release_order_count);
+}
+
+static struct kunit_case reorder_buffer_test_cases[] = {
+	KUNIT_CASE_PARAM(test_reorder_buffer, test_reorder_buffer_gen_params),
+	{},
+};
+
+static struct kunit_suite reorder_buffer = {
+	.name = "iwlmld-reorder-buffer",
+	.test_cases = reorder_buffer_test_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(reorder_buffer);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
new file mode 100644
index 0000000000000..4e189bf8b3fb4
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/hcmd.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <kunit/test.h>
+
+#include <iwl-trans.h>
+#include "mld.h"
+
+MODULE_IMPORT_NS("EXPORTED_FOR_KUNIT_TESTING");
+
+static void test_hcmd_names_sorted(struct kunit *test)
+{
+	int i;
+
+	for (i = 0; i < global_iwl_mld_goups_size; i++) {
+		const struct iwl_hcmd_arr *arr = &iwl_mld_groups[i];
+		int j;
+
+		if (!arr->arr)
+			continue;
+		for (j = 0; j < arr->size - 1; j++)
+			KUNIT_EXPECT_LE(test, arr->arr[j].cmd_id,
+					arr->arr[j + 1].cmd_id);
+	}
+}
+
+static void test_hcmd_names_for_rx(struct kunit *test)
+{
+	static struct iwl_trans t = {
+		.command_groups = iwl_mld_groups,
+	};
+
+	t.command_groups_size = global_iwl_mld_goups_size;
+
+	for (unsigned int i = 0; i < iwl_mld_rx_handlers_num; i++) {
+		const struct iwl_rx_handler *rxh;
+		const char *name;
+
+		rxh = &iwl_mld_rx_handlers[i];
+
+		name = iwl_get_cmd_string(&t, rxh->cmd_id);
+		KUNIT_EXPECT_NOT_NULL(test, name);
+		KUNIT_EXPECT_NE_MSG(test, strcmp(name, "UNKNOWN"), 0,
+				    "ID 0x%04x is UNKNOWN", rxh->cmd_id);
+	}
+}
+
+static struct kunit_case hcmd_names_cases[] = {
+	KUNIT_CASE(test_hcmd_names_sorted),
+	KUNIT_CASE(test_hcmd_names_for_rx),
+	{},
+};
+
+static struct kunit_suite hcmd_names = {
+	.name = "iwlmld-hcmd-names",
+	.test_cases = hcmd_names_cases,
+};
+
+kunit_test_suite(hcmd_names);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
new file mode 100644
index 0000000000000..d835550c1a6bd
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
@@ -0,0 +1,171 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for link selection functions
+ *
+ * Copyright (C) 2025 Intel Corporation
+ */
+#include <kunit/static_stub.h>
+
+#include "utils.h"
+#include "mld.h"
+#include "link.h"
+#include "iface.h"
+#include "phy.h"
+
+static const struct link_grading_test_case {
+	const char *desc;
+	struct {
+		struct {
+			u8 link_id;
+			const struct cfg80211_chan_def *chandef;
+			bool active;
+			s32 signal;
+			bool has_chan_util_elem;
+			u8 chan_util; /* 0-255 , used only if has_chan_util_elem is true */
+			u8 chan_load_by_us; /* 0-100, used only if active is true */;
+		} link;
+	} input;
+	unsigned int expected_grade;
+} link_grading_cases[] = {
+	{
+		.desc = "channel util of 128 (50%)",
+		.input.link = {
+			.link_id = 0,
+			.chandef = &chandef_2ghz,
+			.active = false,
+			.has_chan_util_elem = true,
+			.chan_util = 128,
+		},
+		.expected_grade = 86,
+	},
+	{
+		.desc = "channel util of 180 (70%)",
+		.input.link = {
+			.link_id = 0,
+			.chandef = &chandef_2ghz,
+			.active = false,
+			.has_chan_util_elem = true,
+			.chan_util = 180,
+		},
+		.expected_grade = 51,
+	},
+	{
+		.desc = "channel util of 180 (70%), channel load by us of 10%",
+		.input.link = {
+			.link_id = 0,
+			.chandef = &chandef_2ghz,
+			.has_chan_util_elem = true,
+			.chan_util = 180,
+			.active = true,
+			.chan_load_by_us = 10,
+		},
+		.expected_grade = 67,
+	},
+		{
+		.desc = "no channel util element",
+		.input.link = {
+			.link_id = 0,
+			.chandef = &chandef_2ghz,
+			.active = true,
+		},
+		.expected_grade = 120,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(link_grading, link_grading_cases, desc);
+
+static void setup_link(struct ieee80211_bss_conf *link)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	const struct link_grading_test_case *test_param =
+		(const void *)(test->param_value);
+
+	KUNIT_ALLOC_AND_ASSERT(test, link->bss);
+
+	link->bss->signal = DBM_TO_MBM(test_param->input.link.signal);
+
+	link->chanreq.oper = *test_param->input.link.chandef;
+
+	if (test_param->input.link.has_chan_util_elem) {
+		struct cfg80211_bss_ies *ies;
+		struct ieee80211_bss_load_elem bss_load = {
+			.channel_util = test_param->input.link.chan_util,
+		};
+		struct element *elem =
+			iwlmld_kunit_gen_element(WLAN_EID_QBSS_LOAD,
+						 &bss_load,
+						 sizeof(bss_load));
+		unsigned int elem_len = sizeof(*elem) + sizeof(bss_load);
+
+		KUNIT_ALLOC_AND_ASSERT_SIZE(test, ies, sizeof(*ies) + elem_len);
+		memcpy(ies->data, elem, elem_len);
+		ies->len = elem_len;
+		rcu_assign_pointer(link->bss->beacon_ies, ies);
+		rcu_assign_pointer(link->bss->ies, ies);
+	}
+
+	if (test_param->input.link.active) {
+		struct ieee80211_chanctx_conf *chan_ctx =
+			wiphy_dereference(mld->wiphy, link->chanctx_conf);
+		struct iwl_mld_phy *phy;
+
+		KUNIT_ASSERT_NOT_NULL(test, chan_ctx);
+
+		phy = iwl_mld_phy_from_mac80211(chan_ctx);
+
+		phy->channel_load_by_us = test_param->input.link.chan_load_by_us;
+	}
+}
+
+static void test_link_grading(struct kunit *test)
+{
+	struct iwl_mld *mld = test->priv;
+	const struct link_grading_test_case *test_param =
+		(const void *)(test->param_value);
+	struct ieee80211_vif *vif;
+	struct ieee80211_bss_conf *link;
+	unsigned int actual_grade;
+	u8 assoc_link_id;
+	/* Extract test case parameters */
+	u8 link_id = test_param->input.link.link_id;
+	enum nl80211_band band = test_param->input.link.chandef->chan->band;
+	bool active = test_param->input.link.active;
+	u16 valid_links;
+
+	/* If the link is not active, use a different link as the assoc link */
+	if (active) {
+		assoc_link_id = link_id;
+		valid_links = BIT(link_id);
+	} else {
+		assoc_link_id = BIT(ffz(BIT(link_id)));
+		valid_links = BIT(assoc_link_id) | BIT(link_id);
+	}
+
+	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, assoc_link_id, band);
+
+	wiphy_lock(mld->wiphy);
+	link = wiphy_dereference(mld->wiphy, vif->link_conf[link_id]);
+	KUNIT_ASSERT_NOT_NULL(test, link);
+
+	setup_link(link);
+
+	actual_grade = iwl_mld_get_link_grade(mld, link);
+	wiphy_unlock(mld->wiphy);
+
+	/* Assert that the returned grade matches the expected grade */
+	KUNIT_EXPECT_EQ(test, actual_grade, test_param->expected_grade);
+}
+
+static struct kunit_case link_selection_cases[] = {
+	KUNIT_CASE_PARAM(test_link_grading, link_grading_gen_params),
+	{},
+};
+
+static struct kunit_suite link_selection = {
+	.name = "iwlmld-link-selection-tests",
+	.test_cases = link_selection_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(link_selection);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
new file mode 100644
index 0000000000000..6e251dbc1dfe1
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <kunit/static_stub.h>
+
+#include "utils.h"
+#include "mld.h"
+#include "link.h"
+#include "iface.h"
+#include "fw/api/mac-cfg.h"
+
+static const struct missed_beacon_test_case {
+	const char *desc;
+	struct {
+		struct iwl_missed_beacons_notif notif;
+		bool emlsr;
+	} input;
+	struct {
+		bool disconnected;
+		bool emlsr;
+	} output;
+} missed_beacon_cases[] = {
+	{
+		.desc = "no EMLSR, no disconnect",
+		.input.notif = {
+			.consec_missed_beacons = cpu_to_le32(4),
+		},
+	},
+	{
+		.desc = "no EMLSR, no beacon loss since Rx, no disconnect",
+		.input.notif = {
+			.consec_missed_beacons = cpu_to_le32(20),
+		},
+	},
+	{
+		.desc = "no EMLSR, beacon loss since Rx, disconnect",
+		.input.notif = {
+			.consec_missed_beacons = cpu_to_le32(20),
+			.consec_missed_beacons_since_last_rx =
+				cpu_to_le32(10),
+		},
+		.output.disconnected = true,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(test_missed_beacon, missed_beacon_cases, desc);
+
+static void fake_ieee80211_connection_loss(struct ieee80211_vif *vif)
+{
+	vif->cfg.assoc = false;
+}
+
+static void test_missed_beacon(struct kunit *test)
+{
+	struct iwl_mld *mld = test->priv;
+	struct iwl_missed_beacons_notif *notif;
+	const struct missed_beacon_test_case *test_param =
+		(const void *)(test->param_value);
+	struct ieee80211_vif *vif;
+	struct iwl_rx_packet *pkt;
+
+	kunit_activate_static_stub(test, ieee80211_connection_loss,
+				   fake_ieee80211_connection_loss);
+	pkt = iwl_mld_kunit_create_pkt(test_param->input.notif);
+	notif = (void *)pkt->data;
+
+	if (test_param->input.emlsr) {
+		vif = iwlmld_kunit_assoc_emlsr(0x3, NL80211_BAND_5GHZ,
+					       NL80211_BAND_6GHZ);
+	} else {
+		struct iwl_mld_vif *mld_vif;
+
+		vif = iwlmld_kunit_setup_non_mlo_assoc(NL80211_BAND_6GHZ);
+		mld_vif = iwl_mld_vif_from_mac80211(vif);
+		notif->link_id = cpu_to_le32(mld_vif->deflink.fw_id);
+	}
+
+	wiphy_lock(mld->wiphy);
+
+	iwl_mld_handle_missed_beacon_notif(mld, pkt);
+
+	wiphy_unlock(mld->wiphy);
+
+	KUNIT_ASSERT_NE(test, vif->cfg.assoc, test_param->output.disconnected);
+
+	/* TODO: add test cases for esr and check */
+}
+
+static struct kunit_case link_cases[] = {
+	KUNIT_CASE_PARAM(test_missed_beacon, test_missed_beacon_gen_params),
+	{},
+};
+
+static struct kunit_suite link = {
+	.name = "iwlmld-link",
+	.test_cases = link_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(link);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/module.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/module.c
new file mode 100644
index 0000000000000..5d9818587b238
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/module.c
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * This is just module boilerplate for the iwlmld kunit module.
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <linux/module.h>
+
+MODULE_IMPORT_NS("IWLWIFI");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("kunit tests for iwlmld");
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/rx.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/rx.c
new file mode 100644
index 0000000000000..20cb4e03ab413
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/rx.c
@@ -0,0 +1,353 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2024 Intel Corporation
+ */
+#include <kunit/test.h>
+#include "utils.h"
+#include "iwl-trans.h"
+#include "mld.h"
+#include "sta.h"
+
+static const struct is_dup_case {
+	const char *desc;
+	struct {
+		/* ieee80211_hdr fields */
+		__le16 fc;
+		__le16 seq;
+		u8 tid;
+		bool multicast;
+		/* iwl_rx_mpdu_desc fields */
+		bool is_amsdu;
+		u8 sub_frame_idx;
+	} rx_pkt;
+	struct {
+		__le16 last_seq;
+		u8 last_sub_frame_idx;
+		u8 tid;
+	} dup_data_state;
+	struct {
+		bool is_dup;
+		u32 rx_status_flag;
+	} result;
+} is_dup_cases[] = {
+	{
+		.desc = "Control frame",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_CTL),
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = 0,
+		}
+	},
+	{
+		.desc = "Null func frame",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_NULLFUNC),
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = 0,
+		}
+	},
+	{
+		.desc = "Multicast data",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA),
+			.multicast = true,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = 0,
+		}
+	},
+	{
+		.desc = "QoS null func frame",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_NULLFUNC),
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = 0,
+		}
+	},
+	{
+		.desc = "QoS data new sequence",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x101),
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "QoS data same sequence, no retry",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x100),
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "QoS data same sequence, has retry",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA |
+					    IEEE80211_FCTL_RETRY),
+			.seq = __cpu_to_le16(0x100),
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = true,
+			.rx_status_flag = 0,
+		},
+	},
+	{
+		.desc = "QoS data invalid tid",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x100),
+			.tid = IWL_MAX_TID_COUNT + 1,
+		},
+		.result = {
+			.is_dup = true,
+			.rx_status_flag = 0,
+		},
+	},
+	{
+		.desc = "non-QoS data, same sequence, same tid, no retry",
+		.rx_pkt = {
+			/* Driver will use tid = IWL_MAX_TID_COUNT */
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA),
+			.seq = __cpu_to_le16(0x100),
+		},
+		.dup_data_state = {
+			.tid = IWL_MAX_TID_COUNT,
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "non-QoS data, same sequence, same tid, has retry",
+		.rx_pkt = {
+			/* Driver will use tid = IWL_MAX_TID_COUNT */
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_FCTL_RETRY),
+			.seq = __cpu_to_le16(0x100),
+		},
+		.dup_data_state = {
+			.tid = IWL_MAX_TID_COUNT,
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = true,
+			.rx_status_flag = 0,
+		},
+	},
+	{
+		.desc = "non-QoS data, same sequence on different tid's",
+		.rx_pkt = {
+			/* Driver will use tid = IWL_MAX_TID_COUNT */
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA),
+			.seq = __cpu_to_le16(0x100),
+		},
+		.dup_data_state = {
+			.tid = 7,
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "A-MSDU new subframe, allow same PN",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x100),
+			.is_amsdu = true,
+			.sub_frame_idx = 1,
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_ALLOW_SAME_PN |
+					  RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "A-MSDU subframe with smaller idx, disallow same PN",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x100),
+			.is_amsdu = true,
+			.sub_frame_idx = 1,
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 2,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "A-MSDU same subframe, no retry, disallow same PN",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA),
+			.seq = __cpu_to_le16(0x100),
+			.is_amsdu = true,
+			.sub_frame_idx = 0,
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = false,
+			.rx_status_flag = RX_FLAG_DUP_VALIDATED,
+		},
+	},
+	{
+		.desc = "A-MSDU same subframe, has retry",
+		.rx_pkt = {
+			.fc = __cpu_to_le16(IEEE80211_FTYPE_DATA |
+					    IEEE80211_STYPE_QOS_DATA |
+					    IEEE80211_FCTL_RETRY),
+			.seq = __cpu_to_le16(0x100),
+			.is_amsdu = true,
+			.sub_frame_idx = 0,
+		},
+		.dup_data_state = {
+			.last_seq = __cpu_to_le16(0x100),
+			.last_sub_frame_idx = 0,
+		},
+		.result = {
+			.is_dup = true,
+			.rx_status_flag = 0,
+		},
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(test_is_dup, is_dup_cases, desc);
+
+static void
+setup_dup_data_state(struct ieee80211_sta *sta)
+{
+	struct kunit *test = kunit_get_current_test();
+	const struct is_dup_case *param = (const void *)(test->param_value);
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	u8 tid = param->dup_data_state.tid;
+	struct iwl_mld_rxq_dup_data *dup_data;
+
+	/* Allocate dup_data only for 1 queue */
+	KUNIT_ALLOC_AND_ASSERT(test, dup_data);
+
+	/* Initialize dup data, see iwl_mld_alloc_dup_data */
+	memset(dup_data->last_seq, 0xff, sizeof(dup_data->last_seq));
+
+	dup_data->last_seq[tid] = param->dup_data_state.last_seq;
+	dup_data->last_sub_frame_idx[tid] =
+		param->dup_data_state.last_sub_frame_idx;
+
+	mld_sta->dup_data = dup_data;
+}
+
+static void setup_rx_pkt(const struct is_dup_case *param,
+			 struct ieee80211_hdr *hdr,
+			 struct iwl_rx_mpdu_desc *mpdu_desc)
+{
+	u8 tid = param->rx_pkt.tid;
+
+	/* Set "new rx packet" header */
+	hdr->frame_control = param->rx_pkt.fc;
+	hdr->seq_ctrl = param->rx_pkt.seq;
+
+	if (ieee80211_is_data_qos(hdr->frame_control)) {
+		u8 *qc = ieee80211_get_qos_ctl(hdr);
+
+		qc[0] = tid & IEEE80211_QOS_CTL_TID_MASK;
+	}
+
+	if (param->rx_pkt.multicast)
+		hdr->addr1[0] = 0x1;
+
+	/* Set mpdu_desc */
+	mpdu_desc->amsdu_info = param->rx_pkt.sub_frame_idx &
+				IWL_RX_MPDU_AMSDU_SUBFRAME_IDX_MASK;
+	if (param->rx_pkt.is_amsdu)
+		mpdu_desc->mac_flags2 |= IWL_RX_MPDU_MFLG2_AMSDU;
+}
+
+static void test_is_dup(struct kunit *test)
+{
+	const struct is_dup_case *param = (const void *)(test->param_value);
+	struct iwl_mld *mld = test->priv;
+	struct iwl_rx_mpdu_desc mpdu_desc = { };
+	struct ieee80211_rx_status rx_status = { };
+	struct ieee80211_vif *vif;
+	struct ieee80211_sta *sta;
+	struct ieee80211_hdr hdr;
+
+	vif = iwlmld_kunit_add_vif(false, NL80211_IFTYPE_STATION);
+	sta = iwlmld_kunit_setup_sta(vif, IEEE80211_STA_AUTHORIZED, -1);
+
+	/* Prepare test case state */
+	setup_dup_data_state(sta);
+	setup_rx_pkt(param, &hdr, &mpdu_desc);
+
+	KUNIT_EXPECT_EQ(test,
+			iwl_mld_is_dup(mld, sta, &hdr, &mpdu_desc, &rx_status,
+				       0), /* assuming only 1 queue */
+			param->result.is_dup);
+	KUNIT_EXPECT_EQ(test, rx_status.flag, param->result.rx_status_flag);
+}
+
+static struct kunit_case is_dup_test_cases[] = {
+	KUNIT_CASE_PARAM(test_is_dup, test_is_dup_gen_params),
+	{},
+};
+
+static struct kunit_suite is_dup = {
+	.name = "iwlmld-rx-is-dup",
+	.test_cases = is_dup_test_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(is_dup);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
new file mode 100644
index 0000000000000..a8c1e6c721388
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -0,0 +1,475 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * KUnit tests for channel helper functions
+ *
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#include <kunit/test.h>
+#include <kunit/test-bug.h>
+
+#include "utils.h"
+
+#include <linux/device.h>
+
+#include "fw/api/scan.h"
+#include "fw/api/mac-cfg.h"
+#include "iwl-trans.h"
+#include "mld.h"
+#include "iface.h"
+#include "link.h"
+#include "phy.h"
+#include "sta.h"
+
+int iwlmld_kunit_test_init(struct kunit *test)
+{
+	struct iwl_mld *mld;
+	struct iwl_trans *trans;
+	const struct iwl_cfg *cfg;
+	struct iwl_fw *fw;
+	struct ieee80211_hw *hw;
+
+	KUNIT_ALLOC_AND_ASSERT(test, trans);
+	KUNIT_ALLOC_AND_ASSERT(test, trans->dev);
+	KUNIT_ALLOC_AND_ASSERT(test, cfg);
+	KUNIT_ALLOC_AND_ASSERT(test, fw);
+	KUNIT_ALLOC_AND_ASSERT(test, hw);
+	KUNIT_ALLOC_AND_ASSERT(test, hw->wiphy);
+
+	mutex_init(&hw->wiphy->mtx);
+
+	/* Allocate and initialize the mld structure */
+	KUNIT_ALLOC_AND_ASSERT(test, mld);
+	iwl_construct_mld(mld, trans, cfg, fw, hw, NULL);
+
+	fw->ucode_capa.num_stations = IWL_STATION_COUNT_MAX;
+	fw->ucode_capa.num_links = IWL_FW_MAX_LINK_ID + 1;
+
+	mld->fwrt.trans = trans;
+	mld->fwrt.fw = fw;
+	mld->fwrt.dev = trans->dev;
+
+	/* TODO: add priv_size to hw allocation and setup hw->priv to enable
+	 * testing mac80211 callbacks
+	 */
+
+	KUNIT_ALLOC_AND_ASSERT(test, mld->nvm_data);
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, mld->scan.cmd,
+				    sizeof(struct iwl_scan_req_umac_v17));
+	mld->scan.cmd_size = sizeof(struct iwl_scan_req_umac_v17);
+
+	/* This is not the state at the end of the regular opmode_start,
+	 * but it is more common to need it. Explicitly undo this if needed.
+	 */
+	mld->trans->state = IWL_TRANS_FW_ALIVE;
+	mld->fw_status.running = true;
+
+	/* Avoid passing mld struct around */
+	test->priv = mld;
+	return 0;
+}
+
+IWL_MLD_ALLOC_FN(link, bss_conf)
+
+static void iwlmld_kunit_init_link(struct ieee80211_vif *vif,
+				   struct ieee80211_bss_conf *link,
+				   struct iwl_mld_link *mld_link, int link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	int ret;
+
+	/* setup mac80211 link */
+	rcu_assign_pointer(vif->link_conf[link_id], link);
+	link->link_id = link_id;
+	link->vif = vif;
+	link->beacon_int = 100;
+	link->dtim_period = 3;
+	link->qos = true;
+
+	/* and mld_link */
+	ret = iwl_mld_allocate_link_fw_id(mld, &mld_link->fw_id, link);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	rcu_assign_pointer(mld_vif->link[link_id], mld_link);
+	rcu_assign_pointer(vif->link_conf[link_id], link);
+}
+
+IWL_MLD_ALLOC_FN(vif, vif)
+
+/* Helper function to add and initialize a VIF for KUnit tests */
+struct ieee80211_vif *iwlmld_kunit_add_vif(bool mlo, enum nl80211_iftype type)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_vif *vif;
+	struct iwl_mld_vif *mld_vif;
+	int ret;
+
+	/* TODO: support more types */
+	KUNIT_ASSERT_EQ(test, type, NL80211_IFTYPE_STATION);
+
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, vif,
+				    sizeof(*vif) + sizeof(*mld_vif));
+
+	vif->type = type;
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+	mld_vif->mld = mld;
+
+	ret = iwl_mld_allocate_vif_fw_id(mld, &mld_vif->fw_id, vif);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+
+	/* TODO: revisit (task=EHT) */
+	if (mlo)
+		return vif;
+
+	/* Initialize the default link */
+	iwlmld_kunit_init_link(vif, &vif->bss_conf, &mld_vif->deflink, 0);
+
+	return vif;
+}
+
+/* Use only for MLO vif */
+struct ieee80211_bss_conf *
+iwlmld_kunit_add_link(struct ieee80211_vif *vif, int link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_bss_conf *link;
+	struct iwl_mld_link *mld_link;
+
+	KUNIT_ALLOC_AND_ASSERT(test, link);
+	KUNIT_ALLOC_AND_ASSERT(test, mld_link);
+
+	iwlmld_kunit_init_link(vif, link, mld_link, link_id);
+	vif->valid_links |= BIT(link_id);
+
+	return link;
+}
+
+struct ieee80211_chanctx_conf *
+iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_chanctx_conf *ctx;
+	struct iwl_mld_phy *phy;
+	int fw_id;
+
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, ctx, sizeof(*ctx) + sizeof(*phy));
+
+	/* Setup the chanctx conf */
+	ctx->def = *def;
+	ctx->min_def = *def;
+	ctx->ap = *def;
+
+	/* and the iwl_mld_phy */
+	phy = iwl_mld_phy_from_mac80211(ctx);
+
+	fw_id = iwl_mld_allocate_fw_phy_id(mld);
+	KUNIT_ASSERT_GE(test, fw_id, 0);
+
+	phy->fw_id = fw_id;
+	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
+
+	return ctx;
+}
+
+void iwlmld_kunit_assign_chanctx_to_link(struct ieee80211_vif *vif,
+					 struct ieee80211_bss_conf *link,
+					 struct ieee80211_chanctx_conf *ctx)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct iwl_mld_link *mld_link;
+
+	KUNIT_EXPECT_NULL(test, rcu_access_pointer(link->chanctx_conf));
+	rcu_assign_pointer(link->chanctx_conf, ctx);
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	mld_link = iwl_mld_link_from_mac80211(link);
+
+	KUNIT_EXPECT_NULL(test, rcu_access_pointer(mld_link->chan_ctx));
+	KUNIT_EXPECT_FALSE(test, mld_link->active);
+
+	rcu_assign_pointer(mld_link->chan_ctx, ctx);
+	mld_link->active = true;
+
+	if (ieee80211_vif_is_mld(vif))
+		vif->active_links |= BIT(link->link_id);
+}
+
+IWL_MLD_ALLOC_FN(link_sta, link_sta)
+
+static void iwlmld_kunit_add_link_sta(struct ieee80211_sta *sta,
+				      struct ieee80211_link_sta *link_sta,
+				      struct iwl_mld_link_sta *mld_link_sta,
+				      u8 link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+	struct iwl_mld *mld = test->priv;
+	u8 fw_id;
+	int ret;
+
+	/* initialize mac80211's link_sta */
+	link_sta->link_id = link_id;
+	rcu_assign_pointer(sta->link[link_id], link_sta);
+
+	link_sta->sta = sta;
+
+	/* and the iwl_mld_link_sta */
+	ret = iwl_mld_allocate_link_sta_fw_id(mld, &fw_id, link_sta);
+	KUNIT_ASSERT_EQ(test, ret, 0);
+	mld_link_sta->fw_id = fw_id;
+
+	rcu_assign_pointer(mld_sta->link[link_id], mld_link_sta);
+}
+
+static struct ieee80211_link_sta *
+iwlmld_kunit_alloc_link_sta(struct ieee80211_sta *sta, int link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_link_sta *mld_link_sta;
+
+	/* Only valid for MLO */
+	KUNIT_ASSERT_TRUE(test, sta->valid_links);
+
+	KUNIT_ALLOC_AND_ASSERT(test, link_sta);
+	KUNIT_ALLOC_AND_ASSERT(test, mld_link_sta);
+
+	iwlmld_kunit_add_link_sta(sta, link_sta, mld_link_sta, link_id);
+
+	sta->valid_links |= BIT(link_id);
+
+	return link_sta;
+}
+
+/* Allocate and initialize a STA with the first link_sta */
+static struct ieee80211_sta *
+iwlmld_kunit_add_sta(struct ieee80211_vif *vif, int link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_sta *sta;
+	struct iwl_mld_sta *mld_sta;
+
+	/* Allocate memory for ieee80211_sta with embedded iwl_mld_sta */
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, sta, sizeof(*sta) + sizeof(*mld_sta));
+
+	/* TODO: allocate and initialize the TXQs ? */
+
+	mld_sta = iwl_mld_sta_from_mac80211(sta);
+	mld_sta->vif = vif;
+	mld_sta->mld = test->priv;
+
+	/* TODO: adjust for internal stations */
+	mld_sta->sta_type = STATION_TYPE_PEER;
+
+	if (link_id >= 0) {
+		iwlmld_kunit_add_link_sta(sta, &sta->deflink,
+					  &mld_sta->deflink, link_id);
+		sta->valid_links = BIT(link_id);
+	} else {
+		iwlmld_kunit_add_link_sta(sta, &sta->deflink,
+					  &mld_sta->deflink, 0);
+	}
+	return sta;
+}
+
+/* Move s STA to a state */
+static void iwlmld_kunit_move_sta_state(struct ieee80211_vif *vif,
+					struct ieee80211_sta *sta,
+					enum ieee80211_sta_state state)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld_sta *mld_sta;
+	struct iwl_mld_vif *mld_vif;
+
+	/* The sta will be removed automatically at the end of the test */
+	KUNIT_ASSERT_NE(test, state, IEEE80211_STA_NOTEXIST);
+
+	mld_sta = iwl_mld_sta_from_mac80211(sta);
+	mld_sta->sta_state = state;
+
+	mld_vif = iwl_mld_vif_from_mac80211(mld_sta->vif);
+	mld_vif->authorized = state == IEEE80211_STA_AUTHORIZED;
+
+	if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
+		mld_vif->ap_sta = sta;
+}
+
+struct ieee80211_sta *iwlmld_kunit_setup_sta(struct ieee80211_vif *vif,
+					     enum ieee80211_sta_state state,
+					     int link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_sta *sta;
+
+	/* The sta will be removed automatically at the end of the test */
+	KUNIT_ASSERT_NE(test, state, IEEE80211_STA_NOTEXIST);
+
+	/* First - allocate and init the STA */
+	sta = iwlmld_kunit_add_sta(vif, link_id);
+
+	/* Now move it all the way to the wanted state */
+	for (enum ieee80211_sta_state _state = IEEE80211_STA_NONE;
+	     _state <= state; _state++)
+		iwlmld_kunit_move_sta_state(vif, sta, state);
+
+	return sta;
+}
+
+static void iwlmld_kunit_set_vif_associated(struct ieee80211_vif *vif)
+{
+	/* TODO: setup chanreq */
+	/* TODO setup capabilities */
+
+	vif->cfg.assoc = 1;
+}
+
+static struct ieee80211_vif *
+iwlmld_kunit_setup_assoc(bool mlo, u8 link_id, enum nl80211_band band)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_vif *vif;
+	struct ieee80211_bss_conf *link;
+	struct ieee80211_chanctx_conf *chan_ctx;
+
+	KUNIT_ASSERT_TRUE(test, mlo || link_id == 0);
+
+	vif = iwlmld_kunit_add_vif(mlo, NL80211_IFTYPE_STATION);
+
+	if (mlo)
+		link = iwlmld_kunit_add_link(vif, link_id);
+	else
+		link = &vif->bss_conf;
+
+	chan_ctx = iwlmld_kunit_add_chanctx(band);
+
+	wiphy_lock(mld->wiphy);
+	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
+	wiphy_unlock(mld->wiphy);
+
+	/* The AP sta will now be pointer to by mld_vif->ap_sta */
+	iwlmld_kunit_setup_sta(vif, IEEE80211_STA_AUTHORIZED, link_id);
+
+	iwlmld_kunit_set_vif_associated(vif);
+
+	return vif;
+}
+
+struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
+						   u8 assoc_link_id,
+						   enum nl80211_band band)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct ieee80211_vif *vif;
+
+	KUNIT_ASSERT_TRUE(test,
+			  hweight16(valid_links) == 1 ||
+			  hweight16(valid_links) == 2);
+	KUNIT_ASSERT_TRUE(test, valid_links & BIT(assoc_link_id));
+
+	vif = iwlmld_kunit_setup_assoc(true, assoc_link_id, band);
+
+	/* Add the other link, if applicable */
+	if (hweight16(valid_links) > 1) {
+		u8 other_link_id = ffs(valid_links & ~BIT(assoc_link_id)) - 1;
+
+		iwlmld_kunit_add_link(vif, other_link_id);
+	}
+
+	return vif;
+}
+
+struct ieee80211_vif *iwlmld_kunit_setup_non_mlo_assoc(enum nl80211_band band)
+{
+	return iwlmld_kunit_setup_assoc(false, 0, band);
+}
+
+struct iwl_rx_packet *
+_iwl_mld_kunit_create_pkt(const void *notif, size_t notif_sz)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_rx_packet *pkt;
+
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, pkt, sizeof(pkt) + notif_sz);
+
+	memcpy(pkt->data, notif, notif_sz);
+	pkt->len_n_flags = cpu_to_le32(sizeof(pkt->hdr) + notif_sz);
+
+	return pkt;
+}
+
+struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
+					       enum nl80211_band band1,
+					       enum nl80211_band band2)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_vif *vif;
+	struct ieee80211_bss_conf *link;
+	struct ieee80211_chanctx_conf *chan_ctx;
+	struct ieee80211_sta *sta;
+	struct iwl_mld_vif *mld_vif;
+	u8 assoc_link_id, other_link_id;
+
+	KUNIT_ASSERT_TRUE(test, hweight16(valid_links) == 2);
+
+	assoc_link_id = ffs(valid_links) - 1;
+	other_link_id = ffs(valid_links & ~BIT(assoc_link_id)) - 1;
+
+	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, assoc_link_id, band1);
+	mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	/* Activate second link */
+	wiphy_lock(mld->wiphy);
+
+	link = wiphy_dereference(mld->wiphy, vif->link_conf[other_link_id]);
+	KUNIT_EXPECT_NOT_NULL(test, link);
+
+	chan_ctx = iwlmld_kunit_add_chanctx(band2);
+	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
+
+	wiphy_unlock(mld->wiphy);
+
+	/* And other link sta */
+	sta = mld_vif->ap_sta;
+	KUNIT_EXPECT_NOT_NULL(test, sta);
+
+	iwlmld_kunit_alloc_link_sta(sta, other_link_id);
+
+	return vif;
+}
+
+struct element *iwlmld_kunit_gen_element(u8 id, const void *data, size_t len)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct element *elem;
+
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, elem, sizeof(*elem) + len);
+
+	elem->id = id;
+	elem->datalen = len;
+	memcpy(elem->data, data, len);
+
+	return elem;
+}
+
+struct iwl_mld_phy *iwlmld_kunit_get_phy_of_link(struct ieee80211_vif *vif,
+						 u8 link_id)
+{
+	struct kunit *test = kunit_get_current_test();
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_chanctx_conf *chanctx;
+	struct ieee80211_bss_conf *link =
+		wiphy_dereference(mld->wiphy, vif->link_conf[link_id]);
+
+	KUNIT_EXPECT_NOT_NULL(test, link);
+
+	chanctx = wiphy_dereference(mld->wiphy, link->chanctx_conf);
+	KUNIT_EXPECT_NOT_NULL(test, chanctx);
+
+	return iwl_mld_phy_from_mac80211(chanctx);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
new file mode 100644
index 0000000000000..9b1f2ada997f3
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+
+#ifndef __iwl_mld_kunit_utils_h__
+#define __iwl_mld_kunit_utils_h__
+
+#include <net/mac80211.h>
+#include <kunit/test-bug.h>
+
+struct iwl_mld;
+
+int iwlmld_kunit_test_init(struct kunit *test);
+
+enum nl80211_iftype;
+
+struct ieee80211_vif *iwlmld_kunit_add_vif(bool mlo, enum nl80211_iftype type);
+
+struct ieee80211_bss_conf *
+iwlmld_kunit_add_link(struct ieee80211_vif *vif, int link_id);
+
+#define KUNIT_ALLOC_AND_ASSERT_SIZE(test, ptr, size)			\
+do {									\
+	(ptr) = kunit_kzalloc((test), (size), GFP_KERNEL);		\
+	KUNIT_ASSERT_NOT_NULL((test), (ptr));				\
+} while (0)
+
+#define KUNIT_ALLOC_AND_ASSERT(test, ptr)				\
+	KUNIT_ALLOC_AND_ASSERT_SIZE(test, ptr, sizeof(*(ptr)))
+
+#define CHANNEL(_name, _band, _freq)				\
+static struct ieee80211_channel _name = {			\
+	.band = (_band),					\
+	.center_freq = (_freq),					\
+	.hw_value = (_freq),					\
+}
+
+#define CHANDEF(_name, _channel, _freq1, _width)		\
+__maybe_unused static struct cfg80211_chan_def _name = {	\
+	.chan = &(_channel),					\
+	.center_freq1 = (_freq1),				\
+	.width = (_width),					\
+}
+
+CHANNEL(chan_2ghz, NL80211_BAND_2GHZ, 2412);
+CHANNEL(chan_5ghz, NL80211_BAND_5GHZ, 5200);
+CHANNEL(chan_6ghz, NL80211_BAND_6GHZ, 6115);
+/* Feel free to add more */
+
+CHANDEF(chandef_2ghz, chan_2ghz, 2412, NL80211_CHAN_WIDTH_20);
+CHANDEF(chandef_5ghz, chan_5ghz, 5200, NL80211_CHAN_WIDTH_40);
+CHANDEF(chandef_6ghz, chan_6ghz, 6115, NL80211_CHAN_WIDTH_160);
+/* Feel free to add more */
+
+//struct cfg80211_chan_def;
+
+struct ieee80211_chanctx_conf *
+iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def);
+
+static inline struct ieee80211_chanctx_conf *
+iwlmld_kunit_add_chanctx(enum nl80211_band band)
+{
+	struct cfg80211_chan_def *chandef;
+
+	switch (band) {
+	case NL80211_BAND_2GHZ:
+		chandef = &chandef_2ghz;
+		break;
+	case NL80211_BAND_5GHZ:
+		chandef = &chandef_5ghz;
+		break;
+	default:
+	case NL80211_BAND_6GHZ:
+		chandef = &chandef_6ghz;
+		break;
+	}
+
+	return iwlmld_kunit_add_chanctx_from_def(chandef);
+}
+
+void iwlmld_kunit_assign_chanctx_to_link(struct ieee80211_vif *vif,
+					 struct ieee80211_bss_conf *link,
+					 struct ieee80211_chanctx_conf *ctx);
+
+/* Allocate a sta, initialize it and move it to the wanted state */
+struct ieee80211_sta *iwlmld_kunit_setup_sta(struct ieee80211_vif *vif,
+					     enum ieee80211_sta_state state,
+					     int link_id);
+
+struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
+						   u8 assoc_link_id,
+						   enum nl80211_band band);
+struct ieee80211_vif *iwlmld_kunit_setup_non_mlo_assoc(enum nl80211_band band);
+
+struct iwl_rx_packet *
+_iwl_mld_kunit_create_pkt(const void *notif, size_t notif_sz);
+
+#define iwl_mld_kunit_create_pkt(_notif)	\
+	_iwl_mld_kunit_create_pkt(&(_notif), sizeof(_notif))
+
+struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
+					       enum nl80211_band band1,
+					       enum nl80211_band band2);
+
+struct element *iwlmld_kunit_gen_element(u8 id, const void *data, size_t len);
+
+/**
+ * iwlmld_kunit_get_phy_of_link - Get the phy of a link
+ *
+ * @vif: The vif to get the phy from.
+ * @link_id: The id of the link to get the phy for.
+ *
+ * given a vif and link id, return the phy pointer of that link.
+ * This assumes that the link exists, and that it had a chanctx
+ * assigned.
+ * If this is not the case, the test will fail.
+ *
+ * Return: phy pointer.
+ */
+struct iwl_mld_phy *iwlmld_kunit_get_phy_of_link(struct ieee80211_vif *vif,
+						 u8 link_id);
+
+#endif /* __iwl_mld_kunit_utils_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/thermal.c b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c
new file mode 100644
index 0000000000000..1909953a9be98
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/thermal.c
@@ -0,0 +1,438 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024-2025 Intel Corporation
+ */
+#ifdef CONFIG_THERMAL
+#include <linux/sort.h>
+#include <linux/thermal.h>
+#endif
+
+#include "fw/api/phy.h"
+
+#include "thermal.h"
+#include "mld.h"
+#include "hcmd.h"
+
+#define IWL_MLD_CT_KILL_DURATION (5 * HZ)
+
+void iwl_mld_handle_ct_kill_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt)
+{
+	const struct ct_kill_notif *notif = (const void *)pkt->data;
+
+	IWL_ERR(mld,
+		"CT Kill notification: temp = %d, DTS = 0x%x, Scheme 0x%x - Enter CT Kill\n",
+		le16_to_cpu(notif->temperature), notif->dts,
+		notif->scheme);
+
+	iwl_mld_set_ctkill(mld, true);
+
+	wiphy_delayed_work_queue(mld->wiphy, &mld->ct_kill_exit_wk,
+				 round_jiffies_relative(IWL_MLD_CT_KILL_DURATION));
+}
+
+static void iwl_mld_exit_ctkill(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld *mld;
+
+	mld = container_of(wk, struct iwl_mld, ct_kill_exit_wk.work);
+
+	IWL_ERR(mld, "Exit CT Kill\n");
+	iwl_mld_set_ctkill(mld, false);
+}
+
+void iwl_mld_handle_temp_notif(struct iwl_mld *mld, struct iwl_rx_packet *pkt)
+{
+	const struct iwl_dts_measurement_notif *notif =
+		(const void *)pkt->data;
+	int temp;
+	u32 ths_crossed;
+
+	temp = le32_to_cpu(notif->temp);
+
+	/* shouldn't be negative, but since it's s32, make sure it isn't */
+	if (IWL_FW_CHECK(mld, temp < 0, "negative temperature %d\n", temp))
+		return;
+
+	ths_crossed = le32_to_cpu(notif->threshold_idx);
+
+	/* 0xFF in ths_crossed means the notification is not related
+	 * to a trip, so we can ignore it here.
+	 */
+	if (ths_crossed == 0xFF)
+		return;
+
+	IWL_DEBUG_TEMP(mld, "Temp = %d Threshold crossed = %d\n",
+		       temp, ths_crossed);
+
+	if (IWL_FW_CHECK(mld, ths_crossed >= IWL_MAX_DTS_TRIPS,
+			 "bad threshold: %d\n", ths_crossed))
+		return;
+
+#ifdef CONFIG_THERMAL
+	if (mld->tzone)
+		thermal_zone_device_update(mld->tzone, THERMAL_TRIP_VIOLATED);
+#endif /* CONFIG_THERMAL */
+}
+
+#ifdef CONFIG_THERMAL
+static int iwl_mld_get_temp(struct iwl_mld *mld, s32 *temp)
+{
+	struct iwl_host_cmd cmd = {
+		.id = WIDE_ID(PHY_OPS_GROUP, CMD_DTS_MEASUREMENT_TRIGGER_WIDE),
+		.flags = CMD_WANT_SKB,
+	};
+	const struct iwl_dts_measurement_resp *resp;
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret) {
+		IWL_ERR(mld,
+			"Failed to send the temperature measurement command (err=%d)\n",
+			ret);
+		return ret;
+	}
+
+	if (iwl_rx_packet_payload_len(cmd.resp_pkt) < sizeof(*resp)) {
+		IWL_ERR(mld,
+			"Failed to get a valid response to DTS measurement\n");
+		ret = -EIO;
+		goto free_resp;
+	}
+
+	resp = (const void *)cmd.resp_pkt->data;
+	*temp = le32_to_cpu(resp->temp);
+
+	IWL_DEBUG_TEMP(mld,
+		       "Got temperature measurement response: temp=%d\n",
+		       *temp);
+
+free_resp:
+	iwl_free_resp(&cmd);
+	return ret;
+}
+
+static int compare_temps(const void *a, const void *b)
+{
+	return ((s16)le16_to_cpu(*(__le16 *)a) -
+		(s16)le16_to_cpu(*(__le16 *)b));
+}
+
+struct iwl_trip_walk_data {
+	__le16 *thresholds;
+	int count;
+};
+
+static int iwl_trip_temp_iter(struct thermal_trip *trip, void *arg)
+{
+	struct iwl_trip_walk_data *twd = arg;
+
+	if (trip->temperature == THERMAL_TEMP_INVALID)
+		return 0;
+
+	twd->thresholds[twd->count++] =
+		cpu_to_le16((s16)(trip->temperature / 1000));
+	return 0;
+}
+#endif
+
+int iwl_mld_config_temp_report_ths(struct iwl_mld *mld)
+{
+	struct temp_report_ths_cmd cmd = {0};
+	int ret;
+#ifdef CONFIG_THERMAL
+	struct iwl_trip_walk_data twd = {
+		.thresholds = cmd.thresholds,
+		.count = 0
+	};
+
+	if (!mld->tzone)
+		goto send;
+
+	/* The thermal core holds an array of temperature trips that are
+	 * unsorted and uncompressed, the FW should get it compressed and
+	 * sorted.
+	 */
+
+	/* compress trips to cmd array, remove uninitialized values*/
+	for_each_thermal_trip(mld->tzone, iwl_trip_temp_iter, &twd);
+
+	cmd.num_temps = cpu_to_le32(twd.count);
+	if (twd.count)
+		sort(cmd.thresholds, twd.count, sizeof(s16),
+		     compare_temps, NULL);
+
+send:
+#endif
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(PHY_OPS_GROUP,
+						TEMP_REPORTING_THRESHOLDS_CMD),
+				   &cmd);
+	if (ret)
+		IWL_ERR(mld, "TEMP_REPORT_THS_CMD command failed (err=%d)\n",
+			ret);
+
+	return ret;
+}
+
+#ifdef CONFIG_THERMAL
+static int iwl_mld_tzone_get_temp(struct thermal_zone_device *device,
+				  int *temperature)
+{
+	struct iwl_mld *mld = thermal_zone_device_priv(device);
+	int temp;
+	int ret = 0;
+
+	wiphy_lock(mld->wiphy);
+
+	if (!mld->fw_status.running) {
+		/* Tell the core that there is no valid temperature value to
+		 * return, but it need not worry about this.
+		 */
+		*temperature = THERMAL_TEMP_INVALID;
+		goto unlock;
+	}
+
+	ret = iwl_mld_get_temp(mld, &temp);
+	if (ret)
+		goto unlock;
+
+	*temperature = temp * 1000;
+unlock:
+	wiphy_unlock(mld->wiphy);
+	return ret;
+}
+
+static int iwl_mld_tzone_set_trip_temp(struct thermal_zone_device *device,
+				       const struct thermal_trip *trip,
+				       int temp)
+{
+	struct iwl_mld *mld = thermal_zone_device_priv(device);
+	int ret;
+
+	wiphy_lock(mld->wiphy);
+
+	if (!mld->fw_status.running) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	if ((temp / 1000) > S16_MAX) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ret = iwl_mld_config_temp_report_ths(mld);
+unlock:
+	wiphy_unlock(mld->wiphy);
+	return ret;
+}
+
+static  struct thermal_zone_device_ops tzone_ops = {
+	.get_temp = iwl_mld_tzone_get_temp,
+	.set_trip_temp = iwl_mld_tzone_set_trip_temp,
+};
+
+static void iwl_mld_thermal_zone_register(struct iwl_mld *mld)
+{
+	int ret;
+	char name[16];
+	static atomic_t counter = ATOMIC_INIT(0);
+	struct thermal_trip trips[IWL_MAX_DTS_TRIPS] = {
+		[0 ... IWL_MAX_DTS_TRIPS - 1] = {
+			.temperature = THERMAL_TEMP_INVALID,
+			.type = THERMAL_TRIP_PASSIVE,
+			.flags = THERMAL_TRIP_FLAG_RW_TEMP,
+		},
+	};
+
+	BUILD_BUG_ON(ARRAY_SIZE(name) >= THERMAL_NAME_LENGTH);
+
+	sprintf(name, "iwlwifi_%u", atomic_inc_return(&counter) & 0xFF);
+	mld->tzone =
+		thermal_zone_device_register_with_trips(name, trips,
+							IWL_MAX_DTS_TRIPS,
+							mld, &tzone_ops,
+							NULL, 0, 0);
+	if (IS_ERR(mld->tzone)) {
+		IWL_DEBUG_TEMP(mld,
+			       "Failed to register to thermal zone (err = %ld)\n",
+			       PTR_ERR(mld->tzone));
+		mld->tzone = NULL;
+		return;
+	}
+
+	ret = thermal_zone_device_enable(mld->tzone);
+	if (ret) {
+		IWL_DEBUG_TEMP(mld, "Failed to enable thermal zone\n");
+		thermal_zone_device_unregister(mld->tzone);
+	}
+}
+
+/* budget in mWatt */
+static const u32 iwl_mld_cdev_budgets[] = {
+	2400,	/* cooling state 0 */
+	2000,	/* cooling state 1 */
+	1800,	/* cooling state 2 */
+	1600,	/* cooling state 3 */
+	1400,	/* cooling state 4 */
+	1200,	/* cooling state 5 */
+	1000,	/* cooling state 6 */
+	900,	/* cooling state 7 */
+	800,	/* cooling state 8 */
+	700,	/* cooling state 9 */
+	650,	/* cooling state 10 */
+	600,	/* cooling state 11 */
+	550,	/* cooling state 12 */
+	500,	/* cooling state 13 */
+	450,	/* cooling state 14 */
+	400,	/* cooling state 15 */
+	350,	/* cooling state 16 */
+	300,	/* cooling state 17 */
+	250,	/* cooling state 18 */
+	200,	/* cooling state 19 */
+	150,	/* cooling state 20 */
+};
+
+int iwl_mld_config_ctdp(struct iwl_mld *mld, u32 state,
+			enum iwl_ctdp_cmd_operation op)
+{
+	struct iwl_ctdp_cmd cmd = {
+		.operation = cpu_to_le32(op),
+		.budget = cpu_to_le32(iwl_mld_cdev_budgets[state]),
+		.window_size = 0,
+	};
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	ret = iwl_mld_send_cmd_pdu(mld, WIDE_ID(PHY_OPS_GROUP, CTDP_CONFIG_CMD),
+				   &cmd);
+
+	if (ret) {
+		IWL_ERR(mld, "cTDP command failed (err=%d)\n", ret);
+		return ret;
+	}
+
+	if (op == CTDP_CMD_OPERATION_START)
+		mld->cooling_dev.cur_state = state;
+
+	return 0;
+}
+
+static int iwl_mld_tcool_get_max_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	*state = ARRAY_SIZE(iwl_mld_cdev_budgets) - 1;
+
+	return 0;
+}
+
+static int iwl_mld_tcool_get_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long *state)
+{
+	struct iwl_mld *mld = (struct iwl_mld *)(cdev->devdata);
+
+	*state = mld->cooling_dev.cur_state;
+
+	return 0;
+}
+
+static int iwl_mld_tcool_set_cur_state(struct thermal_cooling_device *cdev,
+				       unsigned long new_state)
+{
+	struct iwl_mld *mld = (struct iwl_mld *)(cdev->devdata);
+	int ret;
+
+	wiphy_lock(mld->wiphy);
+
+	if (!mld->fw_status.running) {
+		ret = -EIO;
+		goto unlock;
+	}
+
+	if (new_state >= ARRAY_SIZE(iwl_mld_cdev_budgets)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
+
+	ret = iwl_mld_config_ctdp(mld, new_state, CTDP_CMD_OPERATION_START);
+
+unlock:
+	wiphy_unlock(mld->wiphy);
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops tcooling_ops = {
+	.get_max_state = iwl_mld_tcool_get_max_state,
+	.get_cur_state = iwl_mld_tcool_get_cur_state,
+	.set_cur_state = iwl_mld_tcool_set_cur_state,
+};
+
+static void iwl_mld_cooling_device_register(struct iwl_mld *mld)
+{
+	char name[] = "iwlwifi";
+
+	BUILD_BUG_ON(ARRAY_SIZE(name) >= THERMAL_NAME_LENGTH);
+
+	mld->cooling_dev.cdev =
+		thermal_cooling_device_register(name,
+						mld,
+						&tcooling_ops);
+
+	if (IS_ERR(mld->cooling_dev.cdev)) {
+		IWL_DEBUG_TEMP(mld,
+			       "Failed to register to cooling device (err = %ld)\n",
+			       PTR_ERR(mld->cooling_dev.cdev));
+		mld->cooling_dev.cdev = NULL;
+		return;
+	}
+}
+
+static void iwl_mld_thermal_zone_unregister(struct iwl_mld *mld)
+{
+	if (!mld->tzone)
+		return;
+
+	IWL_DEBUG_TEMP(mld, "Thermal zone device unregister\n");
+	if (mld->tzone) {
+		thermal_zone_device_unregister(mld->tzone);
+		mld->tzone = NULL;
+	}
+}
+
+static void iwl_mld_cooling_device_unregister(struct iwl_mld *mld)
+{
+	if (!mld->cooling_dev.cdev)
+		return;
+
+	IWL_DEBUG_TEMP(mld, "Cooling device unregister\n");
+	if (mld->cooling_dev.cdev) {
+		thermal_cooling_device_unregister(mld->cooling_dev.cdev);
+		mld->cooling_dev.cdev = NULL;
+	}
+}
+#endif /* CONFIG_THERMAL */
+
+void iwl_mld_thermal_initialize(struct iwl_mld *mld)
+{
+	wiphy_delayed_work_init(&mld->ct_kill_exit_wk, iwl_mld_exit_ctkill);
+
+#ifdef CONFIG_THERMAL
+	iwl_mld_cooling_device_register(mld);
+	iwl_mld_thermal_zone_register(mld);
+#endif
+}
+
+void iwl_mld_thermal_exit(struct iwl_mld *mld)
+{
+	wiphy_delayed_work_cancel(mld->wiphy, &mld->ct_kill_exit_wk);
+
+#ifdef CONFIG_THERMAL
+	iwl_mld_cooling_device_unregister(mld);
+	iwl_mld_thermal_zone_unregister(mld);
+#endif
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/thermal.h b/drivers/net/wireless/intel/iwlwifi/mld/thermal.h
new file mode 100644
index 0000000000000..8c8893331b05c
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/thermal.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_thermal_h__
+#define __iwl_mld_thermal_h__
+
+#include "iwl-trans.h"
+
+struct iwl_mld;
+
+#ifdef CONFIG_THERMAL
+#include <linux/thermal.h>
+
+/*
+ * struct iwl_mld_cooling_device
+ * @cur_state: current state
+ * @cdev: struct thermal cooling device
+ */
+struct iwl_mld_cooling_device {
+	u32 cur_state;
+	struct thermal_cooling_device *cdev;
+};
+
+int iwl_mld_config_ctdp(struct iwl_mld *mld, u32 state,
+			enum iwl_ctdp_cmd_operation op);
+#endif
+
+void iwl_mld_handle_temp_notif(struct iwl_mld *mld, struct iwl_rx_packet *pkt);
+void iwl_mld_handle_ct_kill_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt);
+int iwl_mld_config_temp_report_ths(struct iwl_mld *mld);
+void iwl_mld_thermal_initialize(struct iwl_mld *mld);
+void iwl_mld_thermal_exit(struct iwl_mld *mld);
+
+#endif /* __iwl_mld_thermal_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/time_sync.c b/drivers/net/wireless/intel/iwlwifi/mld/time_sync.c
new file mode 100644
index 0000000000000..50799f9bfccba
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/time_sync.c
@@ -0,0 +1,240 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+
+#include "mld.h"
+#include "hcmd.h"
+#include "ptp.h"
+#include "time_sync.h"
+#include <linux/ieee80211.h>
+
+static int iwl_mld_init_time_sync(struct iwl_mld *mld, u32 protocols,
+				  const u8 *addr)
+{
+	struct iwl_mld_time_sync_data *time_sync = kzalloc(sizeof(*time_sync),
+							   GFP_KERNEL);
+
+	if (!time_sync)
+		return -ENOMEM;
+
+	time_sync->active_protocols = protocols;
+	ether_addr_copy(time_sync->peer_addr, addr);
+	skb_queue_head_init(&time_sync->frame_list);
+	rcu_assign_pointer(mld->time_sync, time_sync);
+
+	return 0;
+}
+
+int iwl_mld_time_sync_fw_config(struct iwl_mld *mld)
+{
+	struct iwl_time_sync_cfg_cmd cmd = {};
+	struct iwl_mld_time_sync_data *time_sync;
+	int err;
+
+	time_sync = wiphy_dereference(mld->wiphy, mld->time_sync);
+	if (!time_sync)
+		return -EINVAL;
+
+	cmd.protocols = cpu_to_le32(time_sync->active_protocols);
+	ether_addr_copy(cmd.peer_addr, time_sync->peer_addr);
+
+	err = iwl_mld_send_cmd_pdu(mld,
+				   WIDE_ID(DATA_PATH_GROUP,
+					   WNM_80211V_TIMING_MEASUREMENT_CONFIG_CMD),
+				   &cmd);
+	if (err)
+		IWL_ERR(mld, "Failed to send time sync cfg cmd: %d\n", err);
+
+	return err;
+}
+
+int iwl_mld_time_sync_config(struct iwl_mld *mld, const u8 *addr, u32 protocols)
+{
+	struct iwl_mld_time_sync_data *time_sync;
+	int err;
+
+	time_sync = wiphy_dereference(mld->wiphy, mld->time_sync);
+
+	/* The fw only supports one peer. We do allow reconfiguration of the
+	 * same peer for cases of fw reset etc.
+	 */
+	if (time_sync && time_sync->active_protocols &&
+	    !ether_addr_equal(addr, time_sync->peer_addr)) {
+		IWL_DEBUG_INFO(mld, "Time sync: reject config for peer: %pM\n",
+			       addr);
+		return -ENOBUFS;
+	}
+
+	if (protocols & ~(IWL_TIME_SYNC_PROTOCOL_TM |
+			  IWL_TIME_SYNC_PROTOCOL_FTM))
+		return -EINVAL;
+
+	IWL_DEBUG_INFO(mld, "Time sync: set peer addr=%pM\n", addr);
+
+	iwl_mld_deinit_time_sync(mld);
+	err = iwl_mld_init_time_sync(mld, protocols, addr);
+	if (err)
+		return err;
+
+	err = iwl_mld_time_sync_fw_config(mld);
+	return err;
+}
+
+void iwl_mld_deinit_time_sync(struct iwl_mld *mld)
+{
+	struct iwl_mld_time_sync_data *time_sync =
+		wiphy_dereference(mld->wiphy, mld->time_sync);
+
+	if (!time_sync)
+		return;
+
+	RCU_INIT_POINTER(mld->time_sync, NULL);
+	skb_queue_purge(&time_sync->frame_list);
+	kfree_rcu(time_sync, rcu_head);
+}
+
+bool iwl_mld_time_sync_frame(struct iwl_mld *mld, struct sk_buff *skb, u8 *addr)
+{
+	struct iwl_mld_time_sync_data *time_sync;
+
+	rcu_read_lock();
+	time_sync = rcu_dereference(mld->time_sync);
+	if (time_sync && ether_addr_equal(time_sync->peer_addr, addr) &&
+	    (ieee80211_is_timing_measurement(skb) || ieee80211_is_ftm(skb))) {
+		skb_queue_tail(&time_sync->frame_list, skb);
+		rcu_read_unlock();
+		return true;
+	}
+	rcu_read_unlock();
+
+	return false;
+}
+
+static bool iwl_mld_is_skb_match(struct sk_buff *skb, u8 *addr, u8 dialog_token)
+{
+	struct ieee80211_mgmt *mgmt = (void *)skb->data;
+	u8 skb_dialog_token;
+
+	if (ieee80211_is_timing_measurement(skb))
+		skb_dialog_token = mgmt->u.action.u.wnm_timing_msr.dialog_token;
+	else
+		skb_dialog_token = mgmt->u.action.u.ftm.dialog_token;
+
+	if ((ether_addr_equal(mgmt->sa, addr) ||
+	     ether_addr_equal(mgmt->da, addr)) &&
+	    skb_dialog_token == dialog_token)
+		return true;
+
+	return false;
+}
+
+static struct sk_buff *iwl_mld_time_sync_find_skb(struct iwl_mld *mld, u8 *addr,
+						  u8 dialog_token)
+{
+	struct iwl_mld_time_sync_data *time_sync;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+
+	time_sync = rcu_dereference(mld->time_sync);
+	if (IWL_FW_CHECK(mld, !time_sync,
+			 "Time sync notification but time sync is not initialized\n")) {
+		rcu_read_unlock();
+		return NULL;
+	}
+
+	/* The notifications are expected to arrive in the same order of the
+	 * frames. If the incoming notification doesn't match the first SKB
+	 * in the queue, it means there was no time sync notification for this
+	 * SKB and it can be dropped.
+	 */
+	while ((skb = skb_dequeue(&time_sync->frame_list))) {
+		if (iwl_mld_is_skb_match(skb, addr, dialog_token))
+			break;
+
+		kfree_skb(skb);
+		skb = NULL;
+		IWL_DEBUG_DROP(mld,
+			       "Time sync: drop SKB without matching notification\n");
+	}
+	rcu_read_unlock();
+
+	return skb;
+}
+
+static u64 iwl_mld_get_64_bit(__le32 high, __le32 low)
+{
+	return ((u64)le32_to_cpu(high) << 32) | le32_to_cpu(low);
+}
+
+void iwl_mld_handle_time_msmt_notif(struct iwl_mld *mld,
+				    struct iwl_rx_packet *pkt)
+{
+	struct ptp_data *data = &mld->ptp_data;
+	struct iwl_time_msmt_notify *notif = (void *)pkt->data;
+	struct ieee80211_rx_status *rx_status;
+	struct skb_shared_hwtstamps *shwt;
+	u64 ts_10ns;
+	struct sk_buff *skb =
+		iwl_mld_time_sync_find_skb(mld, notif->peer_addr,
+					   le32_to_cpu(notif->dialog_token));
+	u64 adj_time;
+
+	if (IWL_FW_CHECK(mld, !skb, "Time sync event but no pending skb\n"))
+		return;
+
+	spin_lock_bh(&data->lock);
+	ts_10ns = iwl_mld_get_64_bit(notif->t2_hi, notif->t2_lo);
+	adj_time = iwl_mld_ptp_get_adj_time(mld, ts_10ns * 10);
+	shwt = skb_hwtstamps(skb);
+	shwt->hwtstamp = ktime_set(0, adj_time);
+
+	ts_10ns = iwl_mld_get_64_bit(notif->t3_hi, notif->t3_lo);
+	adj_time = iwl_mld_ptp_get_adj_time(mld, ts_10ns * 10);
+	rx_status = IEEE80211_SKB_RXCB(skb);
+	rx_status->ack_tx_hwtstamp = ktime_set(0, adj_time);
+	spin_unlock_bh(&data->lock);
+
+	IWL_DEBUG_INFO(mld,
+		       "Time sync: RX event - report frame t2=%llu t3=%llu\n",
+		       ktime_to_ns(shwt->hwtstamp),
+		       ktime_to_ns(rx_status->ack_tx_hwtstamp));
+	ieee80211_rx_napi(mld->hw, NULL, skb, NULL);
+}
+
+void iwl_mld_handle_time_sync_confirm_notif(struct iwl_mld *mld,
+					    struct iwl_rx_packet *pkt)
+{
+	struct ptp_data *data = &mld->ptp_data;
+	struct iwl_time_msmt_cfm_notify *notif = (void *)pkt->data;
+	struct ieee80211_tx_status status = {};
+	struct skb_shared_hwtstamps *shwt;
+	u64 ts_10ns, adj_time;
+
+	status.skb =
+		iwl_mld_time_sync_find_skb(mld, notif->peer_addr,
+					   le32_to_cpu(notif->dialog_token));
+
+	if (IWL_FW_CHECK(mld, !status.skb,
+			 "Time sync confirm but no pending skb\n"))
+		return;
+
+	spin_lock_bh(&data->lock);
+	ts_10ns = iwl_mld_get_64_bit(notif->t1_hi, notif->t1_lo);
+	adj_time = iwl_mld_ptp_get_adj_time(mld, ts_10ns * 10);
+	shwt = skb_hwtstamps(status.skb);
+	shwt->hwtstamp = ktime_set(0, adj_time);
+
+	ts_10ns = iwl_mld_get_64_bit(notif->t4_hi, notif->t4_lo);
+	adj_time = iwl_mld_ptp_get_adj_time(mld, ts_10ns * 10);
+	status.info = IEEE80211_SKB_CB(status.skb);
+	status.ack_hwtstamp = ktime_set(0, adj_time);
+	spin_unlock_bh(&data->lock);
+
+	IWL_DEBUG_INFO(mld,
+		       "Time sync: TX event - report frame t1=%llu t4=%llu\n",
+		       ktime_to_ns(shwt->hwtstamp),
+		       ktime_to_ns(status.ack_hwtstamp));
+	ieee80211_tx_status_ext(mld->hw, &status);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/time_sync.h b/drivers/net/wireless/intel/iwlwifi/mld/time_sync.h
new file mode 100644
index 0000000000000..2d4c5512e9615
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/time_sync.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2025 Intel Corporation
+ */
+#ifndef __iwl_mld_time_sync_h__
+#define __iwl_mld_time_sync_h__
+
+struct iwl_mld_time_sync_data {
+	struct rcu_head rcu_head;
+	u8 peer_addr[ETH_ALEN];
+	u32 active_protocols;
+	struct sk_buff_head frame_list;
+};
+
+int iwl_mld_time_sync_config(struct iwl_mld *mld, const u8 *addr,
+			     u32 protocols);
+int iwl_mld_time_sync_fw_config(struct iwl_mld *mld);
+void iwl_mld_deinit_time_sync(struct iwl_mld *mld);
+void iwl_mld_handle_time_msmt_notif(struct iwl_mld *mld,
+				    struct iwl_rx_packet *pkt);
+bool iwl_mld_time_sync_frame(struct iwl_mld *mld, struct sk_buff *skb,
+			     u8 *addr);
+void iwl_mld_handle_time_sync_confirm_notif(struct iwl_mld *mld,
+					    struct iwl_rx_packet *pkt);
+
+#endif /* __iwl_mld_time_sync_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tlc.c b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
new file mode 100644
index 0000000000000..85ec358f1417d
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
@@ -0,0 +1,717 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+
+#include <net/mac80211.h>
+
+#include "tlc.h"
+#include "hcmd.h"
+#include "sta.h"
+
+#include "fw/api/rs.h"
+#include "fw/api/context.h"
+#include "fw/api/dhc.h"
+
+static u8 iwl_mld_fw_bw_from_sta_bw(const struct ieee80211_link_sta *link_sta)
+{
+	switch (link_sta->bandwidth) {
+	case IEEE80211_STA_RX_BW_320:
+		return IWL_TLC_MNG_CH_WIDTH_320MHZ;
+	case IEEE80211_STA_RX_BW_160:
+		return IWL_TLC_MNG_CH_WIDTH_160MHZ;
+	case IEEE80211_STA_RX_BW_80:
+		return IWL_TLC_MNG_CH_WIDTH_80MHZ;
+	case IEEE80211_STA_RX_BW_40:
+		return IWL_TLC_MNG_CH_WIDTH_40MHZ;
+	case IEEE80211_STA_RX_BW_20:
+	default:
+		return IWL_TLC_MNG_CH_WIDTH_20MHZ;
+	}
+}
+
+static __le16
+iwl_mld_get_tlc_cmd_flags(struct iwl_mld *mld,
+			  struct ieee80211_vif *vif,
+			  struct ieee80211_link_sta *link_sta,
+			  const struct ieee80211_sta_he_cap *own_he_cap,
+			  const struct ieee80211_sta_eht_cap *own_eht_cap)
+{
+	struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
+	struct ieee80211_sta_vht_cap *vht_cap = &link_sta->vht_cap;
+	struct ieee80211_sta_he_cap *he_cap = &link_sta->he_cap;
+	bool has_vht = vht_cap->vht_supported;
+	u16 flags = 0;
+
+	/* STBC flags */
+	if (mld->cfg->ht_params->stbc &&
+	    (hweight8(iwl_mld_get_valid_tx_ant(mld)) > 1)) {
+		if (he_cap->has_he && he_cap->he_cap_elem.phy_cap_info[2] &
+				      IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ)
+			flags |= IWL_TLC_MNG_CFG_FLAGS_STBC_MSK;
+		else if (vht_cap->cap & IEEE80211_VHT_CAP_RXSTBC_MASK)
+			flags |= IWL_TLC_MNG_CFG_FLAGS_STBC_MSK;
+		else if (ht_cap->cap & IEEE80211_HT_CAP_RX_STBC)
+			flags |= IWL_TLC_MNG_CFG_FLAGS_STBC_MSK;
+	}
+
+	/* LDPC */
+	if (mld->cfg->ht_params->ldpc &&
+	    ((ht_cap->cap & IEEE80211_HT_CAP_LDPC_CODING) ||
+	     (has_vht && (vht_cap->cap & IEEE80211_VHT_CAP_RXLDPC))))
+		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
+
+	if (he_cap->has_he && (he_cap->he_cap_elem.phy_cap_info[1] &
+	    IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD))
+		flags |= IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
+
+	if (own_he_cap &&
+	    !(own_he_cap->he_cap_elem.phy_cap_info[1] &
+			IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD))
+		flags &= ~IWL_TLC_MNG_CFG_FLAGS_LDPC_MSK;
+
+	/* DCM */
+	if (he_cap->has_he &&
+	    (he_cap->he_cap_elem.phy_cap_info[3] &
+	     IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK &&
+	     own_he_cap &&
+	     own_he_cap->he_cap_elem.phy_cap_info[3] &
+			IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK))
+		flags |= IWL_TLC_MNG_CFG_FLAGS_HE_DCM_NSS_1_MSK;
+
+	/* Extra EHT LTF */
+	if (own_eht_cap &&
+	    own_eht_cap->eht_cap_elem.phy_cap_info[5] &
+		IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF &&
+	    link_sta->eht_cap.has_eht &&
+	    link_sta->eht_cap.eht_cap_elem.phy_cap_info[5] &
+	    IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF) {
+		flags |= IWL_TLC_MNG_CFG_FLAGS_EHT_EXTRA_LTF_MSK;
+	}
+
+	return cpu_to_le16(flags);
+}
+
+static u8 iwl_mld_get_fw_chains(struct iwl_mld *mld)
+{
+	u8 chains = iwl_mld_get_valid_tx_ant(mld);
+	u8 fw_chains = 0;
+
+	if (chains & ANT_A)
+		fw_chains |= IWL_TLC_MNG_CHAIN_A_MSK;
+	if (chains & ANT_B)
+		fw_chains |= IWL_TLC_MNG_CHAIN_B_MSK;
+
+	return fw_chains;
+}
+
+static u8 iwl_mld_get_fw_sgi(struct ieee80211_link_sta *link_sta)
+{
+	struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
+	struct ieee80211_sta_vht_cap *vht_cap = &link_sta->vht_cap;
+	struct ieee80211_sta_he_cap *he_cap = &link_sta->he_cap;
+	u8 sgi_chwidths = 0;
+
+	/* If the association supports HE, HT/VHT rates will never be used for
+	 * Tx and therefor there's no need to set the
+	 * sgi-per-channel-width-support bits
+	 */
+	if (he_cap->has_he)
+		return 0;
+
+	if (ht_cap->cap & IEEE80211_HT_CAP_SGI_20)
+		sgi_chwidths |= BIT(IWL_TLC_MNG_CH_WIDTH_20MHZ);
+	if (ht_cap->cap & IEEE80211_HT_CAP_SGI_40)
+		sgi_chwidths |= BIT(IWL_TLC_MNG_CH_WIDTH_40MHZ);
+	if (vht_cap->cap & IEEE80211_VHT_CAP_SHORT_GI_80)
+		sgi_chwidths |= BIT(IWL_TLC_MNG_CH_WIDTH_80MHZ);
+	if (vht_cap->cap & IEEE80211_VHT_CAP_SHORT_GI_160)
+		sgi_chwidths |= BIT(IWL_TLC_MNG_CH_WIDTH_160MHZ);
+
+	return sgi_chwidths;
+}
+
+static int
+iwl_mld_get_highest_fw_mcs(const struct ieee80211_sta_vht_cap *vht_cap,
+			   int nss)
+{
+	u16 rx_mcs = le16_to_cpu(vht_cap->vht_mcs.rx_mcs_map) &
+		(0x3 << (2 * (nss - 1)));
+	rx_mcs >>= (2 * (nss - 1));
+
+	switch (rx_mcs) {
+	case IEEE80211_VHT_MCS_SUPPORT_0_7:
+		return IWL_TLC_MNG_HT_RATE_MCS7;
+	case IEEE80211_VHT_MCS_SUPPORT_0_8:
+		return IWL_TLC_MNG_HT_RATE_MCS8;
+	case IEEE80211_VHT_MCS_SUPPORT_0_9:
+		return IWL_TLC_MNG_HT_RATE_MCS9;
+	default:
+		WARN_ON_ONCE(1);
+		break;
+	}
+
+	return 0;
+}
+
+static void
+iwl_mld_fill_vht_rates(const struct ieee80211_link_sta *link_sta,
+		       const struct ieee80211_sta_vht_cap *vht_cap,
+		       struct iwl_tlc_config_cmd_v4 *cmd)
+{
+	u16 supp;
+	int i, highest_mcs;
+	u8 max_nss = link_sta->rx_nss;
+	struct ieee80211_vht_cap ieee_vht_cap = {
+		.vht_cap_info = cpu_to_le32(vht_cap->cap),
+		.supp_mcs = vht_cap->vht_mcs,
+	};
+
+	/* the station support only a single receive chain */
+	if (link_sta->smps_mode == IEEE80211_SMPS_STATIC)
+		max_nss = 1;
+
+	for (i = 0; i < max_nss && i < IWL_TLC_NSS_MAX; i++) {
+		int nss = i + 1;
+
+		highest_mcs = iwl_mld_get_highest_fw_mcs(vht_cap, nss);
+		if (!highest_mcs)
+			continue;
+
+		supp = BIT(highest_mcs + 1) - 1;
+		if (link_sta->bandwidth == IEEE80211_STA_RX_BW_20)
+			supp &= ~BIT(IWL_TLC_MNG_HT_RATE_MCS9);
+
+		cmd->ht_rates[i][IWL_TLC_MCS_PER_BW_80] = cpu_to_le16(supp);
+		/* Check if VHT extended NSS indicates that the bandwidth/NSS
+		 * configuration is supported - only for MCS 0 since we already
+		 * decoded the MCS bits anyway ourselves.
+		 */
+		if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160 &&
+		    ieee80211_get_vht_max_nss(&ieee_vht_cap,
+					      IEEE80211_VHT_CHANWIDTH_160MHZ,
+					      0, true, nss) >= nss)
+			cmd->ht_rates[i][IWL_TLC_MCS_PER_BW_160] =
+				cmd->ht_rates[i][IWL_TLC_MCS_PER_BW_80];
+	}
+}
+
+static u16 iwl_mld_he_mac80211_mcs_to_fw_mcs(u16 mcs)
+{
+	switch (mcs) {
+	case IEEE80211_HE_MCS_SUPPORT_0_7:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS7 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_9:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS9 + 1) - 1;
+	case IEEE80211_HE_MCS_SUPPORT_0_11:
+		return BIT(IWL_TLC_MNG_HT_RATE_MCS11 + 1) - 1;
+	case IEEE80211_HE_MCS_NOT_SUPPORTED:
+		return 0;
+	}
+
+	WARN(1, "invalid HE MCS %d\n", mcs);
+	return 0;
+}
+
+static void
+iwl_mld_fill_he_rates(const struct ieee80211_link_sta *link_sta,
+		      const struct ieee80211_sta_he_cap *own_he_cap,
+		      struct iwl_tlc_config_cmd_v4 *cmd)
+{
+	const struct ieee80211_sta_he_cap *he_cap = &link_sta->he_cap;
+	u16 mcs_160 = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_160);
+	u16 mcs_80 = le16_to_cpu(he_cap->he_mcs_nss_supp.rx_mcs_80);
+	u16 tx_mcs_80 = le16_to_cpu(own_he_cap->he_mcs_nss_supp.tx_mcs_80);
+	u16 tx_mcs_160 = le16_to_cpu(own_he_cap->he_mcs_nss_supp.tx_mcs_160);
+	int i;
+	u8 nss = link_sta->rx_nss;
+
+	/* the station support only a single receive chain */
+	if (link_sta->smps_mode == IEEE80211_SMPS_STATIC)
+		nss = 1;
+
+	for (i = 0; i < nss && i < IWL_TLC_NSS_MAX; i++) {
+		u16 _mcs_160 = (mcs_160 >> (2 * i)) & 0x3;
+		u16 _mcs_80 = (mcs_80 >> (2 * i)) & 0x3;
+		u16 _tx_mcs_160 = (tx_mcs_160 >> (2 * i)) & 0x3;
+		u16 _tx_mcs_80 = (tx_mcs_80 >> (2 * i)) & 0x3;
+
+		/* If one side doesn't support - mark both as not supporting */
+		if (_mcs_80 == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+		    _tx_mcs_80 == IEEE80211_HE_MCS_NOT_SUPPORTED) {
+			_mcs_80 = IEEE80211_HE_MCS_NOT_SUPPORTED;
+			_tx_mcs_80 = IEEE80211_HE_MCS_NOT_SUPPORTED;
+		}
+		if (_mcs_80 > _tx_mcs_80)
+			_mcs_80 = _tx_mcs_80;
+		cmd->ht_rates[i][IWL_TLC_MCS_PER_BW_80] =
+			cpu_to_le16(iwl_mld_he_mac80211_mcs_to_fw_mcs(_mcs_80));
+
+		/* If one side doesn't support - mark both as not supporting */
+		if (_mcs_160 == IEEE80211_HE_MCS_NOT_SUPPORTED ||
+		    _tx_mcs_160 == IEEE80211_HE_MCS_NOT_SUPPORTED) {
+			_mcs_160 = IEEE80211_HE_MCS_NOT_SUPPORTED;
+			_tx_mcs_160 = IEEE80211_HE_MCS_NOT_SUPPORTED;
+		}
+		if (_mcs_160 > _tx_mcs_160)
+			_mcs_160 = _tx_mcs_160;
+		cmd->ht_rates[i][IWL_TLC_MCS_PER_BW_160] =
+			cpu_to_le16(iwl_mld_he_mac80211_mcs_to_fw_mcs(_mcs_160));
+	}
+}
+
+static void iwl_mld_set_eht_mcs(__le16 ht_rates[][3],
+				enum IWL_TLC_MCS_PER_BW bw,
+				u8 max_nss, u16 mcs_msk)
+{
+	if (max_nss >= 2)
+		ht_rates[IWL_TLC_NSS_2][bw] |= cpu_to_le16(mcs_msk);
+
+	if (max_nss >= 1)
+		ht_rates[IWL_TLC_NSS_1][bw] |= cpu_to_le16(mcs_msk);
+}
+
+static const
+struct ieee80211_eht_mcs_nss_supp_bw *
+iwl_mld_get_eht_mcs_of_bw(enum IWL_TLC_MCS_PER_BW bw,
+			  const struct ieee80211_eht_mcs_nss_supp *eht_mcs)
+{
+	switch (bw) {
+	case IWL_TLC_MCS_PER_BW_80:
+		return &eht_mcs->bw._80;
+	case IWL_TLC_MCS_PER_BW_160:
+		return &eht_mcs->bw._160;
+	case IWL_TLC_MCS_PER_BW_320:
+		return &eht_mcs->bw._320;
+	default:
+		return NULL;
+	}
+}
+
+static u8 iwl_mld_get_eht_max_nss(u8 rx_nss, u8 tx_nss)
+{
+	u8 tx = u8_get_bits(tx_nss, IEEE80211_EHT_MCS_NSS_TX);
+	u8 rx = u8_get_bits(rx_nss, IEEE80211_EHT_MCS_NSS_RX);
+	/* the max nss that can be used,
+	 * is the min with our tx capa and the peer rx capa.
+	 */
+	return min(tx, rx);
+}
+
+#define MAX_NSS_MCS(mcs_num, rx, tx) \
+	iwl_mld_get_eht_max_nss((rx)->rx_tx_mcs ##mcs_num## _max_nss, \
+				(tx)->rx_tx_mcs ##mcs_num## _max_nss)
+
+static void
+iwl_mld_fill_eht_rates(struct ieee80211_vif *vif,
+		       const struct ieee80211_link_sta *link_sta,
+		       const struct ieee80211_sta_he_cap *own_he_cap,
+		       const struct ieee80211_sta_eht_cap *own_eht_cap,
+		       struct iwl_tlc_config_cmd_v4 *cmd)
+{
+	/* peer RX mcs capa */
+	const struct ieee80211_eht_mcs_nss_supp *eht_rx_mcs =
+		&link_sta->eht_cap.eht_mcs_nss_supp;
+	/* our TX mcs capa */
+	const struct ieee80211_eht_mcs_nss_supp *eht_tx_mcs =
+		&own_eht_cap->eht_mcs_nss_supp;
+
+	enum IWL_TLC_MCS_PER_BW bw;
+	struct ieee80211_eht_mcs_nss_supp_20mhz_only mcs_rx_20;
+	struct ieee80211_eht_mcs_nss_supp_20mhz_only mcs_tx_20;
+
+	/* peer is 20 MHz only */
+	if (vif->type == NL80211_IFTYPE_AP &&
+	    !(link_sta->he_cap.he_cap_elem.phy_cap_info[0] &
+	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) {
+		mcs_rx_20 = eht_rx_mcs->only_20mhz;
+	} else {
+		mcs_rx_20.rx_tx_mcs7_max_nss =
+			eht_rx_mcs->bw._80.rx_tx_mcs9_max_nss;
+		mcs_rx_20.rx_tx_mcs9_max_nss =
+			eht_rx_mcs->bw._80.rx_tx_mcs9_max_nss;
+		mcs_rx_20.rx_tx_mcs11_max_nss =
+			eht_rx_mcs->bw._80.rx_tx_mcs11_max_nss;
+		mcs_rx_20.rx_tx_mcs13_max_nss =
+			eht_rx_mcs->bw._80.rx_tx_mcs13_max_nss;
+	}
+
+	/* NIC is capable of 20 MHz only */
+	if (!(own_he_cap->he_cap_elem.phy_cap_info[0] &
+	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL)) {
+		mcs_tx_20 = eht_tx_mcs->only_20mhz;
+	} else {
+		mcs_tx_20.rx_tx_mcs7_max_nss =
+			eht_tx_mcs->bw._80.rx_tx_mcs9_max_nss;
+		mcs_tx_20.rx_tx_mcs9_max_nss =
+			eht_tx_mcs->bw._80.rx_tx_mcs9_max_nss;
+		mcs_tx_20.rx_tx_mcs11_max_nss =
+			eht_tx_mcs->bw._80.rx_tx_mcs11_max_nss;
+		mcs_tx_20.rx_tx_mcs13_max_nss =
+			eht_tx_mcs->bw._80.rx_tx_mcs13_max_nss;
+	}
+
+	/* rates for 20/40/80 MHz */
+	bw = IWL_TLC_MCS_PER_BW_80;
+	iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+			    MAX_NSS_MCS(7, &mcs_rx_20, &mcs_tx_20),
+			    GENMASK(7, 0));
+	iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+			    MAX_NSS_MCS(9, &mcs_rx_20, &mcs_tx_20),
+			    GENMASK(9, 8));
+	iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+			    MAX_NSS_MCS(11, &mcs_rx_20, &mcs_tx_20),
+			    GENMASK(11, 10));
+	iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+			    MAX_NSS_MCS(13, &mcs_rx_20, &mcs_tx_20),
+			    GENMASK(13, 12));
+
+	/* rates for 160/320 MHz */
+	for (bw = IWL_TLC_MCS_PER_BW_160; bw <= IWL_TLC_MCS_PER_BW_320; bw++) {
+		const struct ieee80211_eht_mcs_nss_supp_bw *mcs_rx =
+			iwl_mld_get_eht_mcs_of_bw(bw, eht_rx_mcs);
+		const struct ieee80211_eht_mcs_nss_supp_bw *mcs_tx =
+			iwl_mld_get_eht_mcs_of_bw(bw, eht_tx_mcs);
+
+		/* got unsupported index for bw */
+		if (!mcs_rx || !mcs_tx)
+			continue;
+
+		/* break out if we don't support the bandwidth */
+		if (cmd->max_ch_width < (bw + IWL_TLC_MNG_CH_WIDTH_80MHZ))
+			break;
+
+		iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+				    MAX_NSS_MCS(9, mcs_rx, mcs_tx),
+				    GENMASK(9, 0));
+		iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+				    MAX_NSS_MCS(11, mcs_rx, mcs_tx),
+				    GENMASK(11, 10));
+		iwl_mld_set_eht_mcs(cmd->ht_rates, bw,
+				    MAX_NSS_MCS(13, mcs_rx, mcs_tx),
+				    GENMASK(13, 12));
+	}
+
+	/* the station support only a single receive chain */
+	if (link_sta->smps_mode == IEEE80211_SMPS_STATIC ||
+	    link_sta->rx_nss < 2)
+		memset(cmd->ht_rates[IWL_TLC_NSS_2], 0,
+		       sizeof(cmd->ht_rates[IWL_TLC_NSS_2]));
+}
+
+static void
+iwl_mld_fill_supp_rates(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			struct ieee80211_link_sta *link_sta,
+			struct ieee80211_supported_band *sband,
+			const struct ieee80211_sta_he_cap *own_he_cap,
+			const struct ieee80211_sta_eht_cap *own_eht_cap,
+			struct iwl_tlc_config_cmd_v4 *cmd)
+{
+	int i;
+	u16 non_ht_rates = 0;
+	unsigned long rates_bitmap;
+	const struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
+	const struct ieee80211_sta_vht_cap *vht_cap = &link_sta->vht_cap;
+	const struct ieee80211_sta_he_cap *he_cap = &link_sta->he_cap;
+
+	/* non HT rates */
+	rates_bitmap = link_sta->supp_rates[sband->band];
+	for_each_set_bit(i, &rates_bitmap, BITS_PER_LONG)
+		non_ht_rates |= BIT(sband->bitrates[i].hw_value);
+
+	cmd->non_ht_rates = cpu_to_le16(non_ht_rates);
+	cmd->mode = IWL_TLC_MNG_MODE_NON_HT;
+
+	if (link_sta->eht_cap.has_eht && own_he_cap && own_eht_cap) {
+		cmd->mode = IWL_TLC_MNG_MODE_EHT;
+		iwl_mld_fill_eht_rates(vif, link_sta, own_he_cap,
+				       own_eht_cap, cmd);
+	} else if (he_cap->has_he && own_he_cap) {
+		cmd->mode = IWL_TLC_MNG_MODE_HE;
+		iwl_mld_fill_he_rates(link_sta, own_he_cap, cmd);
+	} else if (vht_cap->vht_supported) {
+		cmd->mode = IWL_TLC_MNG_MODE_VHT;
+		iwl_mld_fill_vht_rates(link_sta, vht_cap, cmd);
+	} else if (ht_cap->ht_supported) {
+		cmd->mode = IWL_TLC_MNG_MODE_HT;
+		cmd->ht_rates[IWL_TLC_NSS_1][IWL_TLC_MCS_PER_BW_80] =
+			cpu_to_le16(ht_cap->mcs.rx_mask[0]);
+
+		/* the station support only a single receive chain */
+		if (link_sta->smps_mode == IEEE80211_SMPS_STATIC)
+			cmd->ht_rates[IWL_TLC_NSS_2][IWL_TLC_MCS_PER_BW_80] =
+				0;
+		else
+			cmd->ht_rates[IWL_TLC_NSS_2][IWL_TLC_MCS_PER_BW_80] =
+				cpu_to_le16(ht_cap->mcs.rx_mask[1]);
+	}
+}
+
+static void iwl_mld_send_tlc_cmd(struct iwl_mld *mld,
+				 struct ieee80211_vif *vif,
+				 struct ieee80211_link_sta *link_sta,
+				 enum nl80211_band band)
+{
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+	struct ieee80211_supported_band *sband = mld->hw->wiphy->bands[band];
+	const struct ieee80211_sta_he_cap *own_he_cap =
+		ieee80211_get_he_iftype_cap_vif(sband, vif);
+	const struct ieee80211_sta_eht_cap *own_eht_cap =
+		ieee80211_get_eht_iftype_cap_vif(sband, vif);
+	struct iwl_tlc_config_cmd_v4 cmd = {
+		/* For AP mode, use 20 MHz until the STA is authorized */
+		.max_ch_width = mld_sta->sta_state > IEEE80211_STA_ASSOC ?
+			iwl_mld_fw_bw_from_sta_bw(link_sta) :
+			IWL_TLC_MNG_CH_WIDTH_20MHZ,
+		.flags = iwl_mld_get_tlc_cmd_flags(mld, vif, link_sta,
+						   own_he_cap, own_eht_cap),
+		.chains = iwl_mld_get_fw_chains(mld),
+		.sgi_ch_width_supp = iwl_mld_get_fw_sgi(link_sta),
+		.max_mpdu_len = cpu_to_le16(link_sta->agg.max_rc_amsdu_len),
+	};
+	int fw_sta_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
+	int ret;
+
+	if (fw_sta_id < 0)
+		return;
+
+	cmd.sta_id = fw_sta_id;
+
+	iwl_mld_fill_supp_rates(mld, vif, link_sta, sband,
+				own_he_cap, own_eht_cap,
+				&cmd);
+
+	IWL_DEBUG_RATE(mld,
+		       "TLC CONFIG CMD, sta_id=%d, max_ch_width=%d, mode=%d\n",
+		       cmd.sta_id, cmd.max_ch_width, cmd.mode);
+
+	/* Send async since this can be called within a RCU-read section */
+	ret = iwl_mld_send_cmd_with_flags_pdu(mld, WIDE_ID(DATA_PATH_GROUP,
+							   TLC_MNG_CONFIG_CMD),
+					      CMD_ASYNC, &cmd);
+	if (ret)
+		IWL_ERR(mld, "Failed to send TLC cmd (%d)\n", ret);
+}
+
+static void iwl_mld_recalc_amsdu_len(struct iwl_mld *mld,
+				     struct ieee80211_link_sta *link_sta)
+{
+	const struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
+
+	/* For EHT, HE and VHT - we can use the value as it was calculated by
+	 * mac80211.
+	 */
+	if (link_sta->eht_cap.has_eht || link_sta->he_cap.has_he ||
+	    link_sta->vht_cap.vht_supported)
+		goto recalc;
+
+	/* But for HT, mac80211 doesn't enforce to 4095, so force it here */
+	if (ht_cap->ht_supported && ht_cap->cap & IEEE80211_HT_CAP_MAX_AMSDU)
+		/* Agg is offloaded, so we need to assume that agg are enabled
+		 * and max mpdu in ampdu is 4095 (spec 802.11-2016 9.3.2.1)
+		 */
+		link_sta->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA;
+
+recalc:
+	link_sta->agg.max_rc_amsdu_len = link_sta->agg.max_amsdu_len;
+	ieee80211_sta_recalc_aggregates(link_sta->sta);
+}
+
+int iwl_mld_send_tlc_dhc(struct iwl_mld *mld, u8 sta_id, u32 type, u32 data)
+{
+	struct {
+		struct iwl_dhc_cmd dhc;
+		struct iwl_dhc_tlc_cmd tlc;
+	} __packed cmd = {
+		.tlc.sta_id = sta_id,
+		.tlc.type = cpu_to_le32(type),
+		.tlc.data[0] = cpu_to_le32(data),
+		.dhc.length = cpu_to_le32(sizeof(cmd.tlc) >> 2),
+		.dhc.index_and_mask =
+			cpu_to_le32(DHC_TABLE_INTEGRATION | DHC_TARGET_UMAC |
+				    DHC_INTEGRATION_TLC_DEBUG_CONFIG),
+	};
+	int ret;
+
+	ret = iwl_mld_send_cmd_with_flags_pdu(mld,
+					      WIDE_ID(IWL_ALWAYS_LONG_GROUP,
+						      DEBUG_HOST_COMMAND),
+					      CMD_ASYNC, &cmd);
+	IWL_DEBUG_RATE(mld, "sta_id %d, type: 0x%X, value: 0x%X, ret%d\n",
+		       sta_id, type, data, ret);
+	return ret;
+}
+
+void iwl_mld_config_tlc_link(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf,
+			     struct ieee80211_link_sta *link_sta)
+{
+	enum nl80211_band band;
+
+	if (WARN_ON_ONCE(!link_conf->chanreq.oper.chan))
+		return;
+
+	band = link_conf->chanreq.oper.chan->band;
+
+	iwl_mld_recalc_amsdu_len(mld, link_sta);
+
+	iwl_mld_send_tlc_cmd(mld, vif, link_sta, band);
+}
+
+void iwl_mld_config_tlc(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta)
+{
+	struct ieee80211_bss_conf *link;
+	int link_id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for_each_vif_active_link(vif, link, link_id) {
+		struct ieee80211_link_sta *link_sta =
+			link_sta_dereference_check(sta, link_id);
+
+		if (!link || !link_sta)
+			continue;
+
+		iwl_mld_config_tlc_link(mld, vif, link, link_sta);
+	}
+}
+
+static u16
+iwl_mld_get_amsdu_size_of_tid(struct iwl_mld *mld,
+			      struct ieee80211_link_sta *link_sta,
+			      unsigned int tid)
+{
+	struct ieee80211_sta *sta = link_sta->sta;
+	struct ieee80211_vif *vif = iwl_mld_sta_from_mac80211(sta)->vif;
+	const u8 tid_to_mac80211_ac[] = {
+		IEEE80211_AC_BE,
+		IEEE80211_AC_BK,
+		IEEE80211_AC_BK,
+		IEEE80211_AC_BE,
+		IEEE80211_AC_VI,
+		IEEE80211_AC_VI,
+		IEEE80211_AC_VO,
+		IEEE80211_AC_VO,
+	};
+	unsigned int result = link_sta->agg.max_rc_amsdu_len;
+	u8 ac, txf, lmac;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* Don't send an AMSDU that will be longer than the TXF.
+	 * Add a security margin of 256 for the TX command + headers.
+	 * We also want to have the start of the next packet inside the
+	 * fifo to be able to send bursts.
+	 */
+
+	if (WARN_ON(tid >= ARRAY_SIZE(tid_to_mac80211_ac)))
+		return 0;
+
+	ac = tid_to_mac80211_ac[tid];
+
+	/* For HE redirect to trigger based fifos */
+	if (link_sta->he_cap.has_he)
+		ac += 4;
+
+	txf = iwl_mld_mac80211_ac_to_fw_tx_fifo(ac);
+
+	/* Only one link: take the lmac according to the band */
+	if (hweight16(sta->valid_links) <= 1) {
+		enum nl80211_band band;
+		struct ieee80211_bss_conf *link =
+			wiphy_dereference(mld->wiphy,
+					  vif->link_conf[link_sta->link_id]);
+
+		if (WARN_ON(!link || !link->chanreq.oper.chan))
+			band = NL80211_BAND_2GHZ;
+		else
+			band = link->chanreq.oper.chan->band;
+		lmac = iwl_mld_get_lmac_id(mld, band);
+
+	/* More than one link but with 2 lmacs: take the minimum */
+	} else if (fw_has_capa(&mld->fw->ucode_capa,
+			       IWL_UCODE_TLV_CAPA_CDB_SUPPORT)) {
+		lmac = IWL_LMAC_5G_INDEX;
+		result = min_t(unsigned int, result,
+			       mld->fwrt.smem_cfg.lmac[lmac].txfifo_size[txf] - 256);
+		lmac = IWL_LMAC_24G_INDEX;
+	/* More than one link but only one lmac */
+	} else {
+		lmac = IWL_LMAC_24G_INDEX;
+	}
+
+	return min_t(unsigned int, result,
+		     mld->fwrt.smem_cfg.lmac[lmac].txfifo_size[txf] - 256);
+}
+
+void iwl_mld_handle_tlc_notif(struct iwl_mld *mld,
+			      struct iwl_rx_packet *pkt)
+{
+	struct iwl_tlc_update_notif *notif = (void *)pkt->data;
+	struct ieee80211_link_sta *link_sta;
+	u32 flags = le32_to_cpu(notif->flags);
+	u32 enabled;
+	u16 size;
+
+	if (IWL_FW_CHECK(mld, notif->sta_id >= mld->fw->ucode_capa.num_stations,
+			 "Invalid sta id (%d) in TLC notification\n",
+			 notif->sta_id))
+		return;
+
+	link_sta = wiphy_dereference(mld->wiphy,
+				     mld->fw_id_to_link_sta[notif->sta_id]);
+
+	if (WARN(IS_ERR_OR_NULL(link_sta),
+		 "link_sta of sta id (%d) doesn't exist\n", notif->sta_id))
+		return;
+
+	if (flags & IWL_TLC_NOTIF_FLAG_RATE) {
+		struct iwl_mld_link_sta *mld_link_sta =
+			iwl_mld_link_sta_from_mac80211(link_sta);
+		char pretty_rate[100];
+
+		if (WARN_ON(!mld_link_sta))
+			return;
+
+		mld_link_sta->last_rate_n_flags = le32_to_cpu(notif->rate);
+
+		rs_pretty_print_rate(pretty_rate, sizeof(pretty_rate),
+				     mld_link_sta->last_rate_n_flags);
+		IWL_DEBUG_RATE(mld, "TLC notif: new rate = %s\n", pretty_rate);
+	}
+
+	/* We are done processing the notif */
+	if (!(flags & IWL_TLC_NOTIF_FLAG_AMSDU))
+		return;
+
+	enabled = le32_to_cpu(notif->amsdu_enabled);
+	size = le32_to_cpu(notif->amsdu_size);
+
+	if (size < 2000) {
+		size = 0;
+		enabled = 0;
+	}
+
+	if (IWL_FW_CHECK(mld, size > link_sta->agg.max_amsdu_len,
+			 "Invalid AMSDU len in TLC notif: %d (Max AMSDU len: %d)\n",
+			 size, link_sta->agg.max_amsdu_len))
+		return;
+
+	link_sta->agg.max_rc_amsdu_len = size;
+
+	for (int i = 0; i < IWL_MAX_TID_COUNT; i++) {
+		if (enabled & BIT(i))
+			link_sta->agg.max_tid_amsdu_len[i] =
+				iwl_mld_get_amsdu_size_of_tid(mld, link_sta, i);
+		else
+			link_sta->agg.max_tid_amsdu_len[i] = 0;
+	}
+
+	ieee80211_sta_recalc_aggregates(link_sta->sta);
+
+	IWL_DEBUG_RATE(mld,
+		       "AMSDU update. AMSDU size: %d, AMSDU selected size: %d, AMSDU TID bitmap 0x%X\n",
+		       le32_to_cpu(notif->amsdu_size), size, enabled);
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tlc.h b/drivers/net/wireless/intel/iwlwifi/mld/tlc.h
new file mode 100644
index 0000000000000..c32f42e8840bb
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tlc.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_tlc_h__
+#define __iwl_mld_tlc_h__
+
+#include "mld.h"
+
+void iwl_mld_config_tlc_link(struct iwl_mld *mld,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf,
+			     struct ieee80211_link_sta *link_sta);
+
+void iwl_mld_config_tlc(struct iwl_mld *mld, struct ieee80211_vif *vif,
+			struct ieee80211_sta *sta);
+
+void iwl_mld_handle_tlc_notif(struct iwl_mld *mld,
+			      struct iwl_rx_packet *pkt);
+
+int iwl_mld_send_tlc_dhc(struct iwl_mld *mld, u8 sta_id, u32 type, u32 data);
+
+#endif /* __iwl_mld_tlc_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.c b/drivers/net/wireless/intel/iwlwifi/mld/tx.c
new file mode 100644
index 0000000000000..543abe72e4652
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.c
@@ -0,0 +1,1374 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/*
+ * Copyright (C) 2024 - 2025 Intel Corporation
+ */
+#include <net/ip.h>
+
+#include "tx.h"
+#include "sta.h"
+#include "hcmd.h"
+#include "iwl-utils.h"
+#include "iface.h"
+
+#include "fw/dbg.h"
+
+#include "fw/api/tx.h"
+#include "fw/api/rs.h"
+#include "fw/api/txq.h"
+#include "fw/api/datapath.h"
+#include "fw/api/time-event.h"
+
+#define MAX_ANT_NUM 2
+
+/* Toggles between TX antennas. Receives the bitmask of valid TX antennas and
+ * the *index* used for the last TX, and returns the next valid *index* to use.
+ * In order to set it in the tx_cmd, must do BIT(idx).
+ */
+static u8 iwl_mld_next_ant(u8 valid, u8 last_idx)
+{
+	u8 index = last_idx;
+
+	for (int i = 0; i < MAX_ANT_NUM; i++) {
+		index = (index + 1) % MAX_ANT_NUM;
+		if (valid & BIT(index))
+			return index;
+	}
+
+	WARN_ONCE(1, "Failed to toggle between antennas 0x%x", valid);
+
+	return last_idx;
+}
+
+void iwl_mld_toggle_tx_ant(struct iwl_mld *mld, u8 *ant)
+{
+	*ant = iwl_mld_next_ant(iwl_mld_get_valid_tx_ant(mld), *ant);
+}
+
+static int
+iwl_mld_get_queue_size(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	struct ieee80211_sta *sta = txq->sta;
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
+	int max_size = IWL_DEFAULT_QUEUE_SIZE;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for_each_sta_active_link(txq->vif, sta, link_sta, link_id) {
+		if (link_sta->eht_cap.has_eht) {
+			max_size = IWL_DEFAULT_QUEUE_SIZE_EHT;
+			break;
+		}
+
+		if (link_sta->he_cap.has_he)
+			max_size = IWL_DEFAULT_QUEUE_SIZE_HE;
+	}
+
+	return max_size;
+}
+
+static int iwl_mld_allocate_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	u8 tid = txq->tid == IEEE80211_NUM_TIDS ? IWL_MGMT_TID : txq->tid;
+	u32 fw_sta_mask = iwl_mld_fw_sta_id_mask(mld, txq->sta);
+	/* We can't know when the station is asleep or awake, so we
+	 * must disable the queue hang detection.
+	 */
+	unsigned int watchdog_timeout = txq->vif->type == NL80211_IFTYPE_AP ?
+				IWL_WATCHDOG_DISABLED :
+				mld->trans->trans_cfg->base_params->wd_timeout;
+	int queue, size;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (tid == IWL_MGMT_TID)
+		size = max_t(u32, IWL_MGMT_QUEUE_SIZE,
+			     mld->trans->cfg->min_txq_size);
+	else
+		size = iwl_mld_get_queue_size(mld, txq);
+
+	queue = iwl_trans_txq_alloc(mld->trans, 0, fw_sta_mask, tid, size,
+				    watchdog_timeout);
+
+	if (queue >= 0)
+		IWL_DEBUG_TX_QUEUES(mld,
+				    "Enabling TXQ #%d for sta mask 0x%x tid %d\n",
+				    queue, fw_sta_mask, tid);
+	return queue;
+}
+
+static int iwl_mld_add_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	struct iwl_mld_txq *mld_txq = iwl_mld_txq_from_mac80211(txq);
+	int id;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	/* This will alse send the SCD_QUEUE_CONFIG_CMD */
+	id = iwl_mld_allocate_txq(mld, txq);
+	if (id < 0)
+		return id;
+
+	mld_txq->fw_id = id;
+	mld_txq->status.allocated = true;
+
+	rcu_assign_pointer(mld->fw_id_to_txq[id], txq);
+
+	return 0;
+}
+
+void iwl_mld_add_txq_list(struct iwl_mld *mld)
+{
+	lockdep_assert_wiphy(mld->wiphy);
+
+	while (!list_empty(&mld->txqs_to_add)) {
+		struct ieee80211_txq *txq;
+		struct iwl_mld_txq *mld_txq =
+			list_first_entry(&mld->txqs_to_add, struct iwl_mld_txq,
+					 list);
+		int failed;
+
+		txq = container_of((void *)mld_txq, struct ieee80211_txq,
+				   drv_priv);
+
+		failed = iwl_mld_add_txq(mld, txq);
+
+		local_bh_disable();
+		spin_lock(&mld->add_txqs_lock);
+		list_del_init(&mld_txq->list);
+		spin_unlock(&mld->add_txqs_lock);
+		/* If the queue allocation failed, we can't transmit. Leave the
+		 * frames on the txq, maybe the attempt to allocate the queue
+		 * will succeed.
+		 */
+		if (!failed)
+			iwl_mld_tx_from_txq(mld, txq);
+		local_bh_enable();
+	}
+}
+
+void iwl_mld_add_txqs_wk(struct wiphy *wiphy, struct wiphy_work *wk)
+{
+	struct iwl_mld *mld = container_of(wk, struct iwl_mld,
+					   add_txqs_wk);
+
+	/* will reschedule to run after restart */
+	if (mld->fw_status.in_hw_restart)
+		return;
+
+	iwl_mld_add_txq_list(mld);
+}
+
+void
+iwl_mld_free_txq(struct iwl_mld *mld, u32 fw_sta_mask, u32 tid, u32 queue_id)
+{
+	struct iwl_scd_queue_cfg_cmd remove_cmd = {
+		.operation = cpu_to_le32(IWL_SCD_QUEUE_REMOVE),
+		.u.remove.tid = cpu_to_le32(tid),
+		.u.remove.sta_mask = cpu_to_le32(fw_sta_mask),
+	};
+
+	iwl_mld_send_cmd_pdu(mld,
+			     WIDE_ID(DATA_PATH_GROUP, SCD_QUEUE_CONFIG_CMD),
+			     &remove_cmd);
+
+	iwl_trans_txq_free(mld->trans, queue_id);
+}
+
+void iwl_mld_remove_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	struct iwl_mld_txq *mld_txq = iwl_mld_txq_from_mac80211(txq);
+	u32 sta_msk, tid;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	spin_lock_bh(&mld->add_txqs_lock);
+	if (!list_empty(&mld_txq->list))
+		list_del_init(&mld_txq->list);
+	spin_unlock_bh(&mld->add_txqs_lock);
+
+	if (!mld_txq->status.allocated ||
+	    WARN_ON(mld_txq->fw_id >= ARRAY_SIZE(mld->fw_id_to_txq)))
+		return;
+
+	sta_msk = iwl_mld_fw_sta_id_mask(mld, txq->sta);
+
+	tid = txq->tid == IEEE80211_NUM_TIDS ? IWL_MGMT_TID :
+					       txq->tid;
+
+	iwl_mld_free_txq(mld, sta_msk, tid, mld_txq->fw_id);
+
+	RCU_INIT_POINTER(mld->fw_id_to_txq[mld_txq->fw_id], NULL);
+	mld_txq->status.allocated = false;
+}
+
+#define OPT_HDR(type, skb, off) \
+	(type *)(skb_network_header(skb) + (off))
+
+static __le32
+iwl_mld_get_offload_assist(struct sk_buff *skb, bool amsdu)
+{
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	u16 mh_len = ieee80211_hdrlen(hdr->frame_control);
+	u16 offload_assist = 0;
+#if IS_ENABLED(CONFIG_INET)
+	u8 protocol = 0;
+
+	/* Do not compute checksum if already computed */
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		goto out;
+
+	/* We do not expect to be requested to csum stuff we do not support */
+
+	/* TBD: do we also need to check
+	 * !(mvm->hw->netdev_features & IWL_TX_CSUM_NETIF_FLAGS) now that all
+	 * the devices we support has this flags?
+	 */
+	if (WARN_ONCE(skb->protocol != htons(ETH_P_IP) &&
+		      skb->protocol != htons(ETH_P_IPV6),
+		      "No support for requested checksum\n")) {
+		skb_checksum_help(skb);
+		goto out;
+	}
+
+	if (skb->protocol == htons(ETH_P_IP)) {
+		protocol = ip_hdr(skb)->protocol;
+	} else {
+#if IS_ENABLED(CONFIG_IPV6)
+		struct ipv6hdr *ipv6h =
+			(struct ipv6hdr *)skb_network_header(skb);
+		unsigned int off = sizeof(*ipv6h);
+
+		protocol = ipv6h->nexthdr;
+		while (protocol != NEXTHDR_NONE && ipv6_ext_hdr(protocol)) {
+			struct ipv6_opt_hdr *hp;
+
+			/* only supported extension headers */
+			if (protocol != NEXTHDR_ROUTING &&
+			    protocol != NEXTHDR_HOP &&
+			    protocol != NEXTHDR_DEST) {
+				skb_checksum_help(skb);
+				goto out;
+			}
+
+			hp = OPT_HDR(struct ipv6_opt_hdr, skb, off);
+			protocol = hp->nexthdr;
+			off += ipv6_optlen(hp);
+		}
+		/* if we get here - protocol now should be TCP/UDP */
+#endif
+	}
+
+	if (protocol != IPPROTO_TCP && protocol != IPPROTO_UDP) {
+		WARN_ON_ONCE(1);
+		skb_checksum_help(skb);
+		goto out;
+	}
+
+	/* enable L4 csum */
+	offload_assist |= BIT(TX_CMD_OFFLD_L4_EN);
+
+	/* Set offset to IP header (snap).
+	 * We don't support tunneling so no need to take care of inner header.
+	 * Size is in words.
+	 */
+	offload_assist |= (4 << TX_CMD_OFFLD_IP_HDR);
+
+	/* Do IPv4 csum for AMSDU only (no IP csum for Ipv6) */
+	if (skb->protocol == htons(ETH_P_IP) && amsdu) {
+		ip_hdr(skb)->check = 0;
+		offload_assist |= BIT(TX_CMD_OFFLD_L3_EN);
+	}
+
+	/* reset UDP/TCP header csum */
+	if (protocol == IPPROTO_TCP)
+		tcp_hdr(skb)->check = 0;
+	else
+		udp_hdr(skb)->check = 0;
+
+out:
+#endif
+	mh_len /= 2;
+	offload_assist |= mh_len << TX_CMD_OFFLD_MH_SIZE;
+
+	if (amsdu)
+		offload_assist |= BIT(TX_CMD_OFFLD_AMSDU);
+	else if (ieee80211_hdrlen(hdr->frame_control) % 4)
+		/* padding is inserted later in transport */
+		offload_assist |= BIT(TX_CMD_OFFLD_PAD);
+
+	return cpu_to_le32(offload_assist);
+}
+
+static void iwl_mld_get_basic_rates_and_band(struct iwl_mld *mld,
+					     struct ieee80211_vif *vif,
+					     struct ieee80211_tx_info *info,
+					     unsigned long *basic_rates,
+					     u8 *band)
+{
+	u32 link_id = u32_get_bits(info->control.flags,
+				   IEEE80211_TX_CTRL_MLO_LINK);
+
+	*basic_rates = vif->bss_conf.basic_rates;
+	*band = info->band;
+
+	if (link_id == IEEE80211_LINK_UNSPECIFIED &&
+	    ieee80211_vif_is_mld(vif)) {
+		/* shouldn't do this when >1 link is active */
+		WARN_ON(hweight16(vif->active_links) != 1);
+		link_id = __ffs(vif->active_links);
+	}
+
+	if (link_id < IEEE80211_LINK_UNSPECIFIED) {
+		struct ieee80211_bss_conf *link_conf;
+
+		rcu_read_lock();
+		link_conf = rcu_dereference(vif->link_conf[link_id]);
+		if (link_conf) {
+			*basic_rates = link_conf->basic_rates;
+			if (link_conf->chanreq.oper.chan)
+				*band = link_conf->chanreq.oper.chan->band;
+		}
+		rcu_read_unlock();
+	}
+}
+
+u8 iwl_mld_get_lowest_rate(struct iwl_mld *mld,
+			   struct ieee80211_tx_info *info,
+			   struct ieee80211_vif *vif)
+{
+	struct ieee80211_supported_band *sband;
+	u16 lowest_cck = IWL_RATE_COUNT, lowest_ofdm = IWL_RATE_COUNT;
+	unsigned long basic_rates;
+	u8 band, rate;
+	u32 i;
+
+	iwl_mld_get_basic_rates_and_band(mld, vif, info, &basic_rates, &band);
+
+	sband = mld->hw->wiphy->bands[band];
+	for_each_set_bit(i, &basic_rates, BITS_PER_LONG) {
+		u16 hw = sband->bitrates[i].hw_value;
+
+		if (hw >= IWL_FIRST_OFDM_RATE) {
+			if (lowest_ofdm > hw)
+				lowest_ofdm = hw;
+		} else if (lowest_cck > hw) {
+			lowest_cck = hw;
+		}
+	}
+
+	if (band == NL80211_BAND_2GHZ && !vif->p2p &&
+	    vif->type != NL80211_IFTYPE_P2P_DEVICE &&
+	    !(info->flags & IEEE80211_TX_CTL_NO_CCK_RATE)) {
+		if (lowest_cck != IWL_RATE_COUNT)
+			rate = lowest_cck;
+		else if (lowest_ofdm != IWL_RATE_COUNT)
+			rate = lowest_ofdm;
+		else
+			rate = IWL_FIRST_CCK_RATE;
+	} else if (lowest_ofdm != IWL_RATE_COUNT) {
+		rate = lowest_ofdm;
+	} else {
+		rate = IWL_FIRST_OFDM_RATE;
+	}
+
+	return rate;
+}
+
+static u32 iwl_mld_mac80211_rate_idx_to_fw(struct iwl_mld *mld,
+					   struct ieee80211_tx_info *info,
+					   int rate_idx)
+{
+	u32 rate_flags = 0;
+	u8 rate_plcp;
+
+	/* if the rate isn't a well known legacy rate, take the lowest one */
+	if (rate_idx < 0 || rate_idx >= IWL_RATE_COUNT_LEGACY)
+		rate_idx = iwl_mld_get_lowest_rate(mld, info,
+						   info->control.vif);
+
+	WARN_ON_ONCE(rate_idx < 0);
+
+	/* Set CCK or OFDM flag */
+	if (rate_idx <= IWL_LAST_CCK_RATE)
+		rate_flags |= RATE_MCS_CCK_MSK;
+	else
+		rate_flags |= RATE_MCS_LEGACY_OFDM_MSK;
+
+	/* Legacy rates are indexed:
+	 * 0 - 3 for CCK and 0 - 7 for OFDM
+	 */
+	rate_plcp = (rate_idx >= IWL_FIRST_OFDM_RATE ?
+		     rate_idx - IWL_FIRST_OFDM_RATE : rate_idx);
+
+	return (u32)rate_plcp | rate_flags;
+}
+
+static u32 iwl_mld_get_tx_ant(struct iwl_mld *mld,
+			      struct ieee80211_tx_info *info,
+			      struct ieee80211_sta *sta, __le16 fc)
+{
+	if (sta && ieee80211_is_data(fc)) {
+		struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(sta);
+
+		return BIT(mld_sta->data_tx_ant) << RATE_MCS_ANT_POS;
+	}
+
+	return BIT(mld->mgmt_tx_ant) << RATE_MCS_ANT_POS;
+}
+
+static u32 iwl_mld_get_inject_tx_rate(struct iwl_mld *mld,
+				      struct ieee80211_tx_info *info,
+				      struct ieee80211_sta *sta,
+				      __le16 fc)
+{
+	struct ieee80211_tx_rate *rate = &info->control.rates[0];
+	u32 result;
+
+	/* we only care about legacy/HT/VHT so far, so we can
+	 * build in v1 and use iwl_new_rate_from_v1()
+	 * FIXME: in newer devices we only support the new rates, build
+	 * the rate_n_flags in the new format here instead of using v1 and
+	 * converting it.
+	 */
+
+	if (rate->flags & IEEE80211_TX_RC_VHT_MCS) {
+		u8 mcs = ieee80211_rate_get_vht_mcs(rate);
+		u8 nss = ieee80211_rate_get_vht_nss(rate);
+
+		result = RATE_MCS_VHT_MSK_V1;
+		result |= u32_encode_bits(mcs, RATE_VHT_MCS_RATE_CODE_MSK);
+		result |= u32_encode_bits(nss, RATE_MCS_NSS_MSK);
+
+		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+			result |= RATE_MCS_SGI_MSK_V1;
+
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+		else if (rate->flags & IEEE80211_TX_RC_80_MHZ_WIDTH)
+			result |= u32_encode_bits(2, RATE_MCS_CHAN_WIDTH_MSK_V1);
+		else if (rate->flags & IEEE80211_TX_RC_160_MHZ_WIDTH)
+			result |= u32_encode_bits(3, RATE_MCS_CHAN_WIDTH_MSK_V1);
+
+		result = iwl_new_rate_from_v1(result);
+	} else if (rate->flags & IEEE80211_TX_RC_MCS) {
+		result = RATE_MCS_HT_MSK_V1;
+		result |= u32_encode_bits(rate->idx,
+					  RATE_HT_MCS_RATE_CODE_MSK_V1 |
+					  RATE_HT_MCS_NSS_MSK_V1);
+		if (rate->flags & IEEE80211_TX_RC_SHORT_GI)
+			result |= RATE_MCS_SGI_MSK_V1;
+		if (rate->flags & IEEE80211_TX_RC_40_MHZ_WIDTH)
+			result |= u32_encode_bits(1, RATE_MCS_CHAN_WIDTH_MSK_V1);
+		if (info->flags & IEEE80211_TX_CTL_LDPC)
+			result |= RATE_MCS_LDPC_MSK_V1;
+		if (u32_get_bits(info->flags, IEEE80211_TX_CTL_STBC))
+			result |= RATE_MCS_STBC_MSK;
+
+		result = iwl_new_rate_from_v1(result);
+	} else {
+		result = iwl_mld_mac80211_rate_idx_to_fw(mld, info, rate->idx);
+	}
+
+	if (info->control.antennas)
+		result |= u32_encode_bits(info->control.antennas,
+					  RATE_MCS_ANT_AB_MSK);
+	else
+		result |= iwl_mld_get_tx_ant(mld, info, sta, fc);
+
+	return result;
+}
+
+static u32 iwl_mld_get_tx_rate_n_flags(struct iwl_mld *mld,
+				       struct ieee80211_tx_info *info,
+				       struct ieee80211_sta *sta, __le16 fc)
+{
+	if (unlikely(info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT))
+		return iwl_mld_get_inject_tx_rate(mld, info, sta, fc);
+
+	return iwl_mld_mac80211_rate_idx_to_fw(mld, info, -1) |
+		iwl_mld_get_tx_ant(mld, info, sta, fc);
+}
+
+static void
+iwl_mld_fill_tx_cmd_hdr(struct iwl_tx_cmd_gen3 *tx_cmd,
+			struct sk_buff *skb, bool amsdu)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct ieee80211_vif *vif;
+
+	/* Copy MAC header from skb into command buffer */
+	memcpy(tx_cmd->hdr, hdr, ieee80211_hdrlen(hdr->frame_control));
+
+	if (!amsdu || !skb_is_gso(skb))
+		return;
+
+	/* As described in IEEE sta 802.11-2020, table 9-30 (Address
+	 * field contents), A-MSDU address 3 should contain the BSSID
+	 * address.
+	 *
+	 * In TSO, the skb header address 3 contains the original address 3 to
+	 * correctly create all the A-MSDU subframes headers from it.
+	 * Override now the address 3 in the command header with the BSSID.
+	 *
+	 * Note: we fill in the MLD address, but the firmware will do the
+	 * necessary translation to link address after encryption.
+	 */
+	vif = info->control.vif;
+	switch (vif->type) {
+	case NL80211_IFTYPE_STATION:
+		ether_addr_copy(tx_cmd->hdr->addr3, vif->cfg.ap_addr);
+		break;
+	case NL80211_IFTYPE_AP:
+		ether_addr_copy(tx_cmd->hdr->addr3, vif->addr);
+		break;
+	default:
+		break;
+	}
+}
+
+static void
+iwl_mld_fill_tx_cmd(struct iwl_mld *mld, struct sk_buff *skb,
+		    struct iwl_device_tx_cmd *dev_tx_cmd,
+		    struct ieee80211_sta *sta)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct iwl_mld_sta *mld_sta = sta ? iwl_mld_sta_from_mac80211(sta) :
+					    NULL;
+	struct iwl_tx_cmd_gen3 *tx_cmd;
+	bool amsdu = ieee80211_is_data_qos(hdr->frame_control) &&
+		     (*ieee80211_get_qos_ctl(hdr) &
+		      IEEE80211_QOS_CTL_A_MSDU_PRESENT);
+	u32 rate_n_flags = 0;
+	u16 flags = 0;
+
+	dev_tx_cmd->hdr.cmd = TX_CMD;
+
+	if (!info->control.hw_key)
+		flags |= IWL_TX_FLAGS_ENCRYPT_DIS;
+
+	/* For data and mgmt packets rate info comes from the fw.
+	 * Only set rate/antenna for injected frames with fixed rate, or
+	 * when no sta is given.
+	 */
+	if (unlikely(!sta ||
+		     info->control.flags & IEEE80211_TX_CTRL_RATE_INJECT)) {
+		flags |= IWL_TX_FLAGS_CMD_RATE;
+		rate_n_flags = iwl_mld_get_tx_rate_n_flags(mld, info, sta,
+							   hdr->frame_control);
+	} else if (!ieee80211_is_data(hdr->frame_control) ||
+		   (mld_sta &&
+		    mld_sta->sta_state < IEEE80211_STA_AUTHORIZED)) {
+		/* These are important frames */
+		flags |= IWL_TX_FLAGS_HIGH_PRI;
+	}
+
+	tx_cmd = (void *)dev_tx_cmd->payload;
+
+	iwl_mld_fill_tx_cmd_hdr(tx_cmd, skb, amsdu);
+
+	tx_cmd->offload_assist = iwl_mld_get_offload_assist(skb, amsdu);
+
+	/* Total # bytes to be transmitted */
+	tx_cmd->len = cpu_to_le16((u16)skb->len);
+
+	tx_cmd->flags = cpu_to_le16(flags);
+
+	tx_cmd->rate_n_flags = cpu_to_le32(rate_n_flags);
+}
+
+/* Caller of this need to check that info->control.vif is not NULL */
+static struct iwl_mld_link *
+iwl_mld_get_link_from_tx_info(struct ieee80211_tx_info *info)
+{
+	struct iwl_mld_vif *mld_vif =
+		iwl_mld_vif_from_mac80211(info->control.vif);
+	u32 link_id = u32_get_bits(info->control.flags,
+				   IEEE80211_TX_CTRL_MLO_LINK);
+
+	if (link_id == IEEE80211_LINK_UNSPECIFIED) {
+		if (info->control.vif->active_links)
+			link_id = ffs(info->control.vif->active_links) - 1;
+		else
+			link_id = 0;
+	}
+
+	return rcu_dereference(mld_vif->link[link_id]);
+}
+
+static int
+iwl_mld_get_tx_queue_id(struct iwl_mld *mld, struct ieee80211_txq *txq,
+			struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	__le16 fc = hdr->frame_control;
+	struct iwl_mld_vif *mld_vif;
+	struct iwl_mld_link *link;
+
+	if (txq && txq->sta)
+		return iwl_mld_txq_from_mac80211(txq)->fw_id;
+
+	if (!info->control.vif)
+		return IWL_MLD_INVALID_QUEUE;
+
+	switch (info->control.vif->type) {
+	case NL80211_IFTYPE_AP:
+	case NL80211_IFTYPE_ADHOC:
+		link = iwl_mld_get_link_from_tx_info(info);
+
+		if (WARN_ON(!link))
+			break;
+
+		/* ucast disassociate/deauth frames without a station might
+		 * happen, especially with reason 7 ("Class 3 frame received
+		 * from nonassociated STA").
+		 */
+		if (ieee80211_is_mgmt(fc) &&
+		    (!ieee80211_is_bufferable_mmpdu(skb) ||
+		     ieee80211_is_deauth(fc) || ieee80211_is_disassoc(fc)))
+			return link->bcast_sta.queue_id;
+
+		if (is_multicast_ether_addr(hdr->addr1) &&
+		    !ieee80211_has_order(fc))
+			return link->mcast_sta.queue_id;
+
+		WARN_ONCE(info->control.vif->type != NL80211_IFTYPE_ADHOC,
+			  "Couldn't find a TXQ. fc=0x%02x", le16_to_cpu(fc));
+		return link->bcast_sta.queue_id;
+	case NL80211_IFTYPE_P2P_DEVICE:
+		mld_vif = iwl_mld_vif_from_mac80211(info->control.vif);
+
+		if (mld_vif->roc_activity == ROC_NUM_ACTIVITIES) {
+			IWL_DEBUG_DROP(mld, "Drop tx outside ROC\n");
+			return IWL_MLD_INVALID_DROP_TX;
+		}
+
+		WARN_ON(!ieee80211_is_mgmt(fc));
+
+		return mld_vif->deflink.aux_sta.queue_id;
+	default:
+		/* TODO: consider monitor (task=monitor) */
+		WARN_ONCE(1, "Unsupported vif type\n");
+		break;
+	}
+
+	return IWL_MLD_INVALID_QUEUE;
+}
+
+static void iwl_mld_probe_resp_set_noa(struct iwl_mld *mld,
+				       struct sk_buff *skb)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct iwl_mld_link *mld_link =
+		&iwl_mld_vif_from_mac80211(info->control.vif)->deflink;
+	struct iwl_probe_resp_data *resp_data;
+	u8 *pos;
+
+	if (!info->control.vif->p2p)
+		return;
+
+	rcu_read_lock();
+
+	resp_data = rcu_dereference(mld_link->probe_resp_data);
+	if (!resp_data)
+		goto out;
+
+	if (!resp_data->notif.noa_active)
+		goto out;
+
+	if (skb_tailroom(skb) < resp_data->noa_len) {
+		if (pskb_expand_head(skb, 0, resp_data->noa_len, GFP_ATOMIC)) {
+			IWL_ERR(mld,
+				"Failed to reallocate probe resp\n");
+			goto out;
+		}
+	}
+
+	pos = skb_put(skb, resp_data->noa_len);
+
+	*pos++ = WLAN_EID_VENDOR_SPECIFIC;
+	/* Set length of IE body (not including ID and length itself) */
+	*pos++ = resp_data->noa_len - 2;
+	*pos++ = (WLAN_OUI_WFA >> 16) & 0xff;
+	*pos++ = (WLAN_OUI_WFA >> 8) & 0xff;
+	*pos++ = WLAN_OUI_WFA & 0xff;
+	*pos++ = WLAN_OUI_TYPE_WFA_P2P;
+
+	memcpy(pos, &resp_data->notif.noa_attr,
+	       resp_data->noa_len - sizeof(struct ieee80211_vendor_ie));
+
+out:
+	rcu_read_unlock();
+}
+
+/* This function must be called with BHs disabled */
+static int iwl_mld_tx_mpdu(struct iwl_mld *mld, struct sk_buff *skb,
+			   struct ieee80211_txq *txq)
+{
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct ieee80211_sta *sta = txq ? txq->sta : NULL;
+	struct iwl_device_tx_cmd *dev_tx_cmd;
+	int queue = iwl_mld_get_tx_queue_id(mld, txq, skb);
+	u8 tid = IWL_MAX_TID_COUNT;
+
+	if (WARN_ONCE(queue == IWL_MLD_INVALID_QUEUE, "Invalid TX Queue id") ||
+	    queue == IWL_MLD_INVALID_DROP_TX)
+		return -1;
+
+	if (unlikely(ieee80211_is_any_nullfunc(hdr->frame_control)))
+		return -1;
+
+	dev_tx_cmd = iwl_trans_alloc_tx_cmd(mld->trans);
+	if (unlikely(!dev_tx_cmd))
+		return -1;
+
+	if (unlikely(ieee80211_is_probe_resp(hdr->frame_control))) {
+		if (IWL_MLD_NON_TRANSMITTING_AP)
+			return -1;
+
+		iwl_mld_probe_resp_set_noa(mld, skb);
+	}
+
+	iwl_mld_fill_tx_cmd(mld, skb, dev_tx_cmd, sta);
+
+	if (ieee80211_is_data(hdr->frame_control)) {
+		if (ieee80211_is_data_qos(hdr->frame_control))
+			tid = ieee80211_get_tid(hdr);
+		else
+			tid = IWL_TID_NON_QOS;
+	}
+
+	IWL_DEBUG_TX(mld, "TX TID:%d from Q:%d len %d\n",
+		     tid, queue, skb->len);
+
+	/* From now on, we cannot access info->control */
+	memset(&info->status, 0, sizeof(info->status));
+	memset(info->driver_data, 0, sizeof(info->driver_data));
+
+	info->driver_data[1] = dev_tx_cmd;
+
+	if (iwl_trans_tx(mld->trans, skb, dev_tx_cmd, queue))
+		goto err;
+
+	/* Update low-latency counter when a packet is queued instead
+	 * of after TX, it makes sense for early low-latency detection
+	 */
+	if (sta)
+		iwl_mld_low_latency_update_counters(mld, hdr, sta, 0);
+
+	return 0;
+
+err:
+	iwl_trans_free_tx_cmd(mld->trans, dev_tx_cmd);
+	IWL_DEBUG_TX(mld, "TX from Q:%d dropped\n", queue);
+	return -1;
+}
+
+#ifdef CONFIG_INET
+
+/* This function handles the segmentation of a large TSO packet into multiple
+ * MPDUs, ensuring that the resulting segments conform to AMSDU limits and
+ * constraints.
+ */
+static int iwl_mld_tx_tso_segment(struct iwl_mld *mld, struct sk_buff *skb,
+				  struct ieee80211_sta *sta,
+				  struct sk_buff_head *mpdus_skbs)
+{
+	struct ieee80211_hdr *hdr = (void *)skb->data;
+	netdev_features_t netdev_flags = NETIF_F_CSUM_MASK | NETIF_F_SG;
+	unsigned int mss = skb_shinfo(skb)->gso_size;
+	unsigned int num_subframes, tcp_payload_len, subf_len;
+	u16 snap_ip_tcp, pad, max_tid_amsdu_len;
+	u8 tid;
+
+	snap_ip_tcp = 8 + skb_network_header_len(skb) + tcp_hdrlen(skb);
+
+	if (!ieee80211_is_data_qos(hdr->frame_control) ||
+	    !sta->cur->max_rc_amsdu_len)
+		return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs);
+
+	/* Do not build AMSDU for IPv6 with extension headers.
+	 * Ask stack to segment and checksum the generated MPDUs for us.
+	 */
+	if (skb->protocol == htons(ETH_P_IPV6) &&
+	    ((struct ipv6hdr *)skb_network_header(skb))->nexthdr !=
+	    IPPROTO_TCP) {
+		netdev_flags &= ~NETIF_F_CSUM_MASK;
+		return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs);
+	}
+
+	tid = ieee80211_get_tid(hdr);
+	if (WARN_ON_ONCE(tid >= IWL_MAX_TID_COUNT))
+		return -EINVAL;
+
+	max_tid_amsdu_len = sta->cur->max_tid_amsdu_len[tid];
+	if (!max_tid_amsdu_len)
+		return iwl_tx_tso_segment(skb, 1, netdev_flags, mpdus_skbs);
+
+	/* Sub frame header + SNAP + IP header + TCP header + MSS */
+	subf_len = sizeof(struct ethhdr) + snap_ip_tcp + mss;
+	pad = (4 - subf_len) & 0x3;
+
+	/* If we have N subframes in the A-MSDU, then the A-MSDU's size is
+	 * N * subf_len + (N - 1) * pad.
+	 */
+	num_subframes = (max_tid_amsdu_len + pad) / (subf_len + pad);
+
+	if (sta->max_amsdu_subframes &&
+	    num_subframes > sta->max_amsdu_subframes)
+		num_subframes = sta->max_amsdu_subframes;
+
+	tcp_payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) -
+		tcp_hdrlen(skb) + skb->data_len;
+
+	/* Make sure we have enough TBs for the A-MSDU:
+	 *	2 for each subframe
+	 *	1 more for each fragment
+	 *	1 more for the potential data in the header
+	 */
+	if ((num_subframes * 2 + skb_shinfo(skb)->nr_frags + 1) >
+	    mld->trans->max_skb_frags)
+		num_subframes = 1;
+
+	if (num_subframes > 1)
+		*ieee80211_get_qos_ctl(hdr) |= IEEE80211_QOS_CTL_A_MSDU_PRESENT;
+
+	/* This skb fits in one single A-MSDU */
+	if (tcp_payload_len <= num_subframes * mss) {
+		__skb_queue_tail(mpdus_skbs, skb);
+		return 0;
+	}
+
+	/* Trick the segmentation function to make it create SKBs that can fit
+	 * into one A-MSDU.
+	 */
+	return iwl_tx_tso_segment(skb, num_subframes, netdev_flags, mpdus_skbs);
+}
+
+/* Manages TSO (TCP Segmentation Offload) packet transmission by segmenting
+ * large packets when necessary and transmitting each segment as MPDU.
+ */
+static int iwl_mld_tx_tso(struct iwl_mld *mld, struct sk_buff *skb,
+			  struct ieee80211_txq *txq)
+{
+	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+	struct sk_buff *orig_skb = skb;
+	struct sk_buff_head mpdus_skbs;
+	unsigned int payload_len;
+	int ret;
+
+	if (WARN_ON(!txq || !txq->sta))
+		return -1;
+
+	payload_len = skb_tail_pointer(skb) - skb_transport_header(skb) -
+		tcp_hdrlen(skb) + skb->data_len;
+
+	if (payload_len <= skb_shinfo(skb)->gso_size)
+		return iwl_mld_tx_mpdu(mld, skb, txq);
+
+	if (!info->control.vif)
+		return -1;
+
+	__skb_queue_head_init(&mpdus_skbs);
+
+	ret = iwl_mld_tx_tso_segment(mld, skb, txq->sta, &mpdus_skbs);
+	if (ret)
+		return ret;
+
+	WARN_ON(skb_queue_empty(&mpdus_skbs));
+
+	while (!skb_queue_empty(&mpdus_skbs)) {
+		skb = __skb_dequeue(&mpdus_skbs);
+
+		ret = iwl_mld_tx_mpdu(mld, skb, txq);
+		if (!ret)
+			continue;
+
+		/* Free skbs created as part of TSO logic that have not yet
+		 * been dequeued
+		 */
+		__skb_queue_purge(&mpdus_skbs);
+
+		/* skb here is not necessarily same as skb that entered
+		 * this method, so free it explicitly.
+		 */
+		if (skb == orig_skb)
+			ieee80211_free_txskb(mld->hw, skb);
+		else
+			kfree_skb(skb);
+
+		/* there was error, but we consumed skb one way or
+		 * another, so return 0
+		 */
+		return 0;
+	}
+
+	return 0;
+}
+#else
+static int iwl_mld_tx_tso(struct iwl_mld *mld, struct sk_buff *skb,
+			  struct ieee80211_txq *txq)
+{
+	/* Impossible to get TSO without CONFIG_INET */
+	WARN_ON(1);
+
+	return -1;
+}
+#endif /* CONFIG_INET */
+
+void iwl_mld_tx_skb(struct iwl_mld *mld, struct sk_buff *skb,
+		    struct ieee80211_txq *txq)
+{
+	if (skb_is_gso(skb)) {
+		if (!iwl_mld_tx_tso(mld, skb, txq))
+			return;
+		goto err;
+	}
+
+	if (likely(!iwl_mld_tx_mpdu(mld, skb, txq)))
+		return;
+
+err:
+	ieee80211_free_txskb(mld->hw, skb);
+}
+
+void iwl_mld_tx_from_txq(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	struct iwl_mld_txq *mld_txq = iwl_mld_txq_from_mac80211(txq);
+	struct sk_buff *skb = NULL;
+	u8 zero_addr[ETH_ALEN] = {};
+
+	/*
+	 * No need for threads to be pending here, they can leave the first
+	 * taker all the work.
+	 *
+	 * mld_txq->tx_request logic:
+	 *
+	 * If 0, no one is currently TXing, set to 1 to indicate current thread
+	 * will now start TX and other threads should quit.
+	 *
+	 * If 1, another thread is currently TXing, set to 2 to indicate to
+	 * that thread that there was another request. Since that request may
+	 * have raced with the check whether the queue is empty, the TXing
+	 * thread should check the queue's status one more time before leaving.
+	 * This check is done in order to not leave any TX hanging in the queue
+	 * until the next TX invocation (which may not even happen).
+	 *
+	 * If 2, another thread is currently TXing, and it will already double
+	 * check the queue, so do nothing.
+	 */
+	if (atomic_fetch_add_unless(&mld_txq->tx_request, 1, 2))
+		return;
+
+	rcu_read_lock();
+	do {
+		while (likely(!mld_txq->status.stop_full) &&
+		       (skb = ieee80211_tx_dequeue(mld->hw, txq)))
+			iwl_mld_tx_skb(mld, skb, txq);
+	} while (atomic_dec_return(&mld_txq->tx_request));
+
+	IWL_DEBUG_TX(mld, "TXQ of sta %pM tid %d is now empty\n",
+		     txq->sta ? txq->sta->addr : zero_addr, txq->tid);
+
+	rcu_read_unlock();
+}
+
+static void iwl_mld_hwrate_to_tx_rate(u32 rate_n_flags,
+				      struct ieee80211_tx_info *info)
+{
+	enum nl80211_band band = info->band;
+	struct ieee80211_tx_rate *tx_rate = &info->status.rates[0];
+	u32 sgi = rate_n_flags & RATE_MCS_SGI_MSK;
+	u32 chan_width = rate_n_flags & RATE_MCS_CHAN_WIDTH_MSK;
+	u32 format = rate_n_flags & RATE_MCS_MOD_TYPE_MSK;
+
+	if (sgi)
+		tx_rate->flags |= IEEE80211_TX_RC_SHORT_GI;
+
+	switch (chan_width) {
+	case RATE_MCS_CHAN_WIDTH_20:
+		break;
+	case RATE_MCS_CHAN_WIDTH_40:
+		tx_rate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
+		break;
+	case RATE_MCS_CHAN_WIDTH_80:
+		tx_rate->flags |= IEEE80211_TX_RC_80_MHZ_WIDTH;
+		break;
+	case RATE_MCS_CHAN_WIDTH_160:
+		tx_rate->flags |= IEEE80211_TX_RC_160_MHZ_WIDTH;
+		break;
+	default:
+		break;
+	}
+
+	switch (format) {
+	case RATE_MCS_HT_MSK:
+		tx_rate->flags |= IEEE80211_TX_RC_MCS;
+		tx_rate->idx = RATE_HT_MCS_INDEX(rate_n_flags);
+		break;
+	case RATE_MCS_VHT_MSK:
+		ieee80211_rate_set_vht(tx_rate,
+				       rate_n_flags & RATE_MCS_CODE_MSK,
+				       FIELD_GET(RATE_MCS_NSS_MSK,
+						 rate_n_flags) + 1);
+		tx_rate->flags |= IEEE80211_TX_RC_VHT_MCS;
+		break;
+	case RATE_MCS_HE_MSK:
+		/* mac80211 cannot do this without ieee80211_tx_status_ext()
+		 * but it only matters for radiotap
+		 */
+		tx_rate->idx = 0;
+		break;
+	default:
+		tx_rate->idx =
+			iwl_mld_legacy_hw_idx_to_mac80211_idx(rate_n_flags,
+							      band);
+		break;
+	}
+}
+
+void iwl_mld_handle_tx_resp_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt)
+{
+	struct iwl_tx_resp *tx_resp = (void *)pkt->data;
+	int txq_id = le16_to_cpu(tx_resp->tx_queue);
+	struct agg_tx_status *agg_status = &tx_resp->status;
+	u32 status = le16_to_cpu(agg_status->status);
+	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+	size_t notif_size = sizeof(*tx_resp) + sizeof(u32);
+	int sta_id = IWL_TX_RES_GET_RA(tx_resp->ra_tid);
+	int tid = IWL_TX_RES_GET_TID(tx_resp->ra_tid);
+	struct ieee80211_link_sta *link_sta;
+	struct iwl_mld_sta *mld_sta;
+	u16 ssn;
+	struct sk_buff_head skbs;
+	u8 skb_freed = 0;
+	bool mgmt = false;
+	bool tx_failure = (status & TX_STATUS_MSK) != TX_STATUS_SUCCESS;
+
+	if (IWL_FW_CHECK(mld, tx_resp->frame_count != 1,
+			 "Invalid tx_resp notif frame_count (%d)\n",
+			 tx_resp->frame_count))
+		return;
+
+	/* validate the size of the variable part of the notif */
+	if (IWL_FW_CHECK(mld, notif_size != pkt_len,
+			 "Invalid tx_resp notif size (expected=%zu got=%u)\n",
+			 notif_size, pkt_len))
+		return;
+
+	ssn = le32_to_cpup((__le32 *)agg_status +
+			   tx_resp->frame_count) & 0xFFFF;
+
+	__skb_queue_head_init(&skbs);
+
+	/* we can free until ssn % q.n_bd not inclusive */
+	iwl_trans_reclaim(mld->trans, txq_id, ssn, &skbs, false);
+
+	while (!skb_queue_empty(&skbs)) {
+		struct sk_buff *skb = __skb_dequeue(&skbs);
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+		struct ieee80211_hdr *hdr = (void *)skb->data;
+
+		skb_freed++;
+
+		iwl_trans_free_tx_cmd(mld->trans, info->driver_data[1]);
+
+		memset(&info->status, 0, sizeof(info->status));
+
+		info->flags &= ~(IEEE80211_TX_STAT_ACK | IEEE80211_TX_STAT_TX_FILTERED);
+
+		/* inform mac80211 about what happened with the frame */
+		switch (status & TX_STATUS_MSK) {
+		case TX_STATUS_SUCCESS:
+		case TX_STATUS_DIRECT_DONE:
+			info->flags |= IEEE80211_TX_STAT_ACK;
+			break;
+		default:
+			break;
+		}
+
+		/* If we are freeing multiple frames, mark all the frames
+		 * but the first one as acked, since they were acknowledged
+		 * before
+		 */
+		if (skb_freed > 1)
+			info->flags |= IEEE80211_TX_STAT_ACK;
+
+		if (tx_failure) {
+			enum iwl_fw_ini_time_point tp =
+				IWL_FW_INI_TIME_POINT_TX_FAILED;
+
+			if (ieee80211_is_action(hdr->frame_control))
+				tp = IWL_FW_INI_TIME_POINT_TX_WFD_ACTION_FRAME_FAILED;
+			else if (ieee80211_is_mgmt(hdr->frame_control))
+				mgmt = true;
+
+			iwl_dbg_tlv_time_point(&mld->fwrt, tp, NULL);
+		}
+
+		iwl_mld_hwrate_to_tx_rate(le32_to_cpu(tx_resp->initial_rate),
+					  info);
+
+		if (likely(!iwl_mld_time_sync_frame(mld, skb, hdr->addr1)))
+			ieee80211_tx_status_skb(mld->hw, skb);
+	}
+
+	IWL_DEBUG_TX_REPLY(mld,
+			   "TXQ %d status 0x%08x ssn=%d initial_rate 0x%x retries %d\n",
+			   txq_id, status, ssn, le32_to_cpu(tx_resp->initial_rate),
+			   tx_resp->failure_frame);
+
+	if (tx_failure && mgmt)
+		iwl_mld_toggle_tx_ant(mld, &mld->mgmt_tx_ant);
+
+	if (IWL_FW_CHECK(mld, sta_id >= mld->fw->ucode_capa.num_stations,
+			 "Got invalid sta_id (%d)\n", sta_id))
+		return;
+
+	rcu_read_lock();
+
+	link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]);
+	if (!link_sta) {
+		/* This can happen if the TX cmd was sent before pre_rcu_remove
+		 * but the TX response was received after
+		 */
+		IWL_DEBUG_TX_REPLY(mld,
+				   "Got valid sta_id (%d) but sta is NULL\n",
+				   sta_id);
+		goto out;
+	}
+
+	if (IS_ERR(link_sta))
+		goto out;
+
+	mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
+
+	if (tx_failure && mld_sta->sta_state < IEEE80211_STA_AUTHORIZED)
+		iwl_mld_toggle_tx_ant(mld, &mld_sta->data_tx_ant);
+
+	if (tid < IWL_MAX_TID_COUNT)
+		iwl_mld_count_mpdu_tx(link_sta, 1);
+
+out:
+	rcu_read_unlock();
+}
+
+static void iwl_mld_tx_reclaim_txq(struct iwl_mld *mld, int txq, int index,
+				   bool in_flush)
+{
+	struct sk_buff_head reclaimed_skbs;
+
+	__skb_queue_head_init(&reclaimed_skbs);
+
+	iwl_trans_reclaim(mld->trans, txq, index, &reclaimed_skbs, in_flush);
+
+	while (!skb_queue_empty(&reclaimed_skbs)) {
+		struct sk_buff *skb = __skb_dequeue(&reclaimed_skbs);
+		struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+
+		iwl_trans_free_tx_cmd(mld->trans, info->driver_data[1]);
+
+		memset(&info->status, 0, sizeof(info->status));
+
+		/* Packet was transmitted successfully, failures come as single
+		 * frames because before failing a frame the firmware transmits
+		 * it without aggregation at least once.
+		 */
+		if (!in_flush)
+			info->flags |= IEEE80211_TX_STAT_ACK;
+		else
+			info->flags &= ~IEEE80211_TX_STAT_ACK;
+
+		ieee80211_tx_status_skb(mld->hw, skb);
+	}
+}
+
+int iwl_mld_flush_link_sta_txqs(struct iwl_mld *mld, u32 fw_sta_id)
+{
+	struct iwl_tx_path_flush_cmd_rsp *rsp;
+	struct iwl_tx_path_flush_cmd flush_cmd = {
+		.sta_id = cpu_to_le32(fw_sta_id),
+		.tid_mask = cpu_to_le16(0xffff),
+	};
+	struct iwl_host_cmd cmd = {
+		.id = TXPATH_FLUSH,
+		.len = { sizeof(flush_cmd), },
+		.data = { &flush_cmd, },
+		.flags = CMD_WANT_SKB,
+	};
+	int ret, num_flushed_queues;
+	u32 resp_len;
+
+	IWL_DEBUG_TX_QUEUES(mld, "flush for sta id %d tid mask 0x%x\n",
+			    fw_sta_id, 0xffff);
+
+	ret = iwl_mld_send_cmd(mld, &cmd);
+	if (ret) {
+		IWL_ERR(mld, "Failed to send flush command (%d)\n", ret);
+		return ret;
+	}
+
+	resp_len = iwl_rx_packet_payload_len(cmd.resp_pkt);
+	if (IWL_FW_CHECK(mld, resp_len != sizeof(*rsp),
+			 "Invalid TXPATH_FLUSH response len: %d\n",
+			 resp_len)) {
+		ret = -EIO;
+		goto free_rsp;
+	}
+
+	rsp = (void *)cmd.resp_pkt->data;
+
+	if (IWL_FW_CHECK(mld, le16_to_cpu(rsp->sta_id) != fw_sta_id,
+			 "sta_id %d != rsp_sta_id %d\n", fw_sta_id,
+			 le16_to_cpu(rsp->sta_id))) {
+		ret = -EIO;
+		goto free_rsp;
+	}
+
+	num_flushed_queues = le16_to_cpu(rsp->num_flushed_queues);
+	if (IWL_FW_CHECK(mld, num_flushed_queues > IWL_TX_FLUSH_QUEUE_RSP,
+			 "num_flushed_queues %d\n", num_flushed_queues)) {
+		ret = -EIO;
+		goto free_rsp;
+	}
+
+	for (int i = 0; i < num_flushed_queues; i++) {
+		struct iwl_flush_queue_info *queue_info = &rsp->queues[i];
+		int read_after = le16_to_cpu(queue_info->read_after_flush);
+		int txq_id = le16_to_cpu(queue_info->queue_num);
+
+		if (IWL_FW_CHECK(mld,
+				 txq_id >= ARRAY_SIZE(mld->fw_id_to_txq),
+				 "Invalid txq id %d\n", txq_id))
+			continue;
+
+		IWL_DEBUG_TX_QUEUES(mld,
+				    "tid %d txq_id %d read-before %d read-after %d\n",
+				    le16_to_cpu(queue_info->tid), txq_id,
+				    le16_to_cpu(queue_info->read_before_flush),
+				    read_after);
+
+		iwl_mld_tx_reclaim_txq(mld, txq_id, read_after, true);
+	}
+
+free_rsp:
+	iwl_free_resp(&cmd);
+	return ret;
+}
+
+int iwl_mld_ensure_queue(struct iwl_mld *mld, struct ieee80211_txq *txq)
+{
+	struct iwl_mld_txq *mld_txq = iwl_mld_txq_from_mac80211(txq);
+	int ret;
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	if (likely(mld_txq->status.allocated))
+		return 0;
+
+	ret = iwl_mld_add_txq(mld, txq);
+
+	spin_lock_bh(&mld->add_txqs_lock);
+	if (!list_empty(&mld_txq->list))
+		list_del_init(&mld_txq->list);
+	spin_unlock_bh(&mld->add_txqs_lock);
+
+	return ret;
+}
+
+int iwl_mld_update_sta_txqs(struct iwl_mld *mld,
+			    struct ieee80211_sta *sta,
+			    u32 old_sta_mask, u32 new_sta_mask)
+{
+	struct iwl_scd_queue_cfg_cmd cmd = {
+		.operation = cpu_to_le32(IWL_SCD_QUEUE_MODIFY),
+		.u.modify.old_sta_mask = cpu_to_le32(old_sta_mask),
+		.u.modify.new_sta_mask = cpu_to_le32(new_sta_mask),
+	};
+
+	lockdep_assert_wiphy(mld->wiphy);
+
+	for (int tid = 0; tid <= IWL_MAX_TID_COUNT; tid++) {
+		struct ieee80211_txq *txq =
+			sta->txq[tid != IWL_MAX_TID_COUNT ?
+					tid : IEEE80211_NUM_TIDS];
+		struct iwl_mld_txq *mld_txq =
+			iwl_mld_txq_from_mac80211(txq);
+		int ret;
+
+		if (!mld_txq->status.allocated)
+			continue;
+
+		if (tid == IWL_MAX_TID_COUNT)
+			cmd.u.modify.tid = cpu_to_le32(IWL_MGMT_TID);
+		else
+			cmd.u.modify.tid = cpu_to_le32(tid);
+
+		ret = iwl_mld_send_cmd_pdu(mld,
+					   WIDE_ID(DATA_PATH_GROUP,
+						   SCD_QUEUE_CONFIG_CMD),
+					   &cmd);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+void iwl_mld_handle_compressed_ba_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt)
+{
+	struct iwl_compressed_ba_notif *ba_res = (void *)pkt->data;
+	u32 pkt_len = iwl_rx_packet_payload_len(pkt);
+	u16 tfd_cnt = le16_to_cpu(ba_res->tfd_cnt);
+	u8 sta_id = ba_res->sta_id;
+	struct ieee80211_link_sta *link_sta;
+
+	if (!tfd_cnt)
+		return;
+
+	if (IWL_FW_CHECK(mld, struct_size(ba_res, tfd, tfd_cnt) > pkt_len,
+			 "Short BA notif (tfd_cnt=%d, size:0x%x)\n",
+			 tfd_cnt, pkt_len))
+		return;
+
+	IWL_DEBUG_TX_REPLY(mld,
+			   "BA notif received from sta_id=%d, flags=0x%x, sent:%d, acked:%d\n",
+			   sta_id, le32_to_cpu(ba_res->flags),
+			   le16_to_cpu(ba_res->txed),
+			   le16_to_cpu(ba_res->done));
+
+	for (int i = 0; i < tfd_cnt; i++) {
+		struct iwl_compressed_ba_tfd *ba_tfd = &ba_res->tfd[i];
+		int txq_id = le16_to_cpu(ba_tfd->q_num);
+		int index = le16_to_cpu(ba_tfd->tfd_index);
+
+		if (IWL_FW_CHECK(mld,
+				 txq_id >= ARRAY_SIZE(mld->fw_id_to_txq),
+				 "Invalid txq id %d\n", txq_id))
+			continue;
+
+		iwl_mld_tx_reclaim_txq(mld, txq_id, index, false);
+	}
+
+	if (IWL_FW_CHECK(mld, sta_id >= mld->fw->ucode_capa.num_stations,
+			 "Got invalid sta_id (%d)\n", sta_id))
+		return;
+
+	rcu_read_lock();
+
+	link_sta = rcu_dereference(mld->fw_id_to_link_sta[sta_id]);
+	if (IWL_FW_CHECK(mld, IS_ERR_OR_NULL(link_sta),
+			 "Got valid sta_id (%d) but link_sta is NULL\n",
+			 sta_id))
+		goto out;
+
+	iwl_mld_count_mpdu_tx(link_sta, le16_to_cpu(ba_res->txed));
+out:
+	rcu_read_unlock();
+}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tx.h b/drivers/net/wireless/intel/iwlwifi/mld/tx.h
new file mode 100644
index 0000000000000..520f15f9d33ca
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tx.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2024 Intel Corporation
+ */
+#ifndef __iwl_mld_tx_h__
+#define __iwl_mld_tx_h__
+
+#include "mld.h"
+
+#define IWL_MLD_INVALID_QUEUE		0xFFFF
+#define IWL_MLD_INVALID_DROP_TX		0xFFFE
+
+/**
+ * struct iwl_mld_txq - TX Queue data
+ *
+ * @fw_id: the fw id of this txq. Only valid when &status.allocated is true.
+ * @status: bitmap of the txq status
+ * @status.allocated: Indicates that the queue was allocated.
+ * @status.stop_full: Indicates that the queue is full and should stop TXing.
+ * @list: list pointer, for &mld::txqs_to_add
+ * @tx_request: makes sure that if there are multiple threads that want to tx
+ *	from this txq, only one of them will do all the TXing.
+ *	This is needed to avoid spinning the trans txq lock, which is expensive
+ */
+struct iwl_mld_txq {
+	/* Add here fields that need clean up on restart */
+	struct_group(zeroed_on_hw_restart,
+		u16 fw_id;
+		struct {
+			u8 allocated:1;
+			u8 stop_full:1;
+		} status;
+	);
+	struct list_head list;
+	atomic_t tx_request;
+	/* And here fields that survive a fw restart */
+};
+
+static inline void iwl_mld_init_txq(struct iwl_mld_txq *mld_txq)
+{
+	INIT_LIST_HEAD(&mld_txq->list);
+	atomic_set(&mld_txq->tx_request, 0);
+}
+
+static inline struct iwl_mld_txq *
+iwl_mld_txq_from_mac80211(struct ieee80211_txq *txq)
+{
+	return (void *)txq->drv_priv;
+}
+
+void iwl_mld_add_txqs_wk(struct wiphy *wiphy, struct wiphy_work *wk);
+void iwl_mld_remove_txq(struct iwl_mld *mld, struct ieee80211_txq *txq);
+void iwl_mld_add_txq_list(struct iwl_mld *mld);
+void
+iwl_mld_free_txq(struct iwl_mld *mld, u32 fw_sta_mask, u32 tid, u32 queue_id);
+void iwl_mld_tx_from_txq(struct iwl_mld *mld, struct ieee80211_txq *txq);
+void iwl_mld_handle_tx_resp_notif(struct iwl_mld *mld,
+				  struct iwl_rx_packet *pkt);
+int iwl_mld_flush_link_sta_txqs(struct iwl_mld *mld, u32 fw_sta_id);
+int iwl_mld_ensure_queue(struct iwl_mld *mld, struct ieee80211_txq *txq);
+
+int iwl_mld_update_sta_txqs(struct iwl_mld *mld,
+			    struct ieee80211_sta *sta,
+			    u32 old_sta_mask, u32 new_sta_mask);
+
+void iwl_mld_handle_compressed_ba_notif(struct iwl_mld *mld,
+					struct iwl_rx_packet *pkt);
+void iwl_mld_toggle_tx_ant(struct iwl_mld *mld, u8 *ant);
+
+u8 iwl_mld_get_lowest_rate(struct iwl_mld *mld,
+			   struct ieee80211_tx_info *info,
+			   struct ieee80211_vif *vif);
+
+void iwl_mld_tx_skb(struct iwl_mld *mld, struct sk_buff *skb,
+		    struct ieee80211_txq *txq);
+
+#endif /* __iwl_mld_tx_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index cd347cd8176a7..03f7eb46bbc78 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -498,7 +498,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 /* Ma devices */
 	{IWL_PCI_DEVICE(0x2729, PCI_ANY_ID, iwl_ma_trans_cfg)},
 	{IWL_PCI_DEVICE(0x7E40, PCI_ANY_ID, iwl_ma_trans_cfg)},
-
+#endif /* CONFIG_IWLMVM */
+#if IS_ENABLED(CONFIG_IWLMLD)
 /* Bz devices */
 	{IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_gl_trans_cfg)},
 	{IWL_PCI_DEVICE(0xA840, 0x0000, iwl_bz_trans_cfg)},
@@ -543,7 +544,7 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
 
 /* Dr devices */
 	{IWL_PCI_DEVICE(0x272F, PCI_ANY_ID, iwl_dr_trans_cfg)},
-#endif /* CONFIG_IWLMVM */
+#endif /* CONFIG_IWLMLD */
 
 	{0}
 };
@@ -1109,6 +1110,8 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		      80, IWL_CFG_CORES_BT, IWL_CFG_NO_CDB,
 		      iwlax210_2ax_cfg_so_jf_b0, iwl9462_name),
 
+#endif /* CONFIG_IWLMVM */
+#if IS_ENABLED(CONFIG_IWLMLD)
 /* Bz */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_BZ, IWL_CFG_ANY,
@@ -1230,7 +1233,7 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 		      IWL_CFG_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_br, iwl_br_name),
-#endif /* CONFIG_IWLMVM */
+#endif /* CONFIG_IWLMLD */
 };
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_dev_info_table);
 

From 0d3e0dfd68fb9e6b0ec865be9f3377cc3ff55733 Mon Sep 17 00:00:00 2001
From: Jarkko Sakkinen <jarkko@kernel.org>
Date: Wed, 5 Mar 2025 07:00:05 +0200
Subject: [PATCH 1571/2753] x86/sgx: Fix size overflows in sgx_encl_create()

The total size calculated for EPC can overflow u64 given the added up page
for SECS.  Further, the total size calculated for shmem can overflow even
when the EPC size stays within limits of u64, given that it adds the extra
space for 128 byte PCMD structures (one for each page).

Address this by pre-evaluating the micro-architectural requirement of
SGX: the address space size must be power of two. This is eventually
checked up by ECREATE but the pre-check has the additional benefit of
making sure that there is some space for additional data.

Fixes: 888d24911787 ("x86/sgx: Add SGX_IOC_ENCLAVE_CREATE")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Dave Hansen <dave.hansen@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: https://lore.kernel.org/r/20250305050006.43896-1-jarkko@kernel.org

Closes: https://lore.kernel.org/linux-sgx/c87e01a0-e7dd-4749-a348-0980d3444f04@stanley.mountain/
---
 arch/x86/kernel/cpu/sgx/ioctl.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index b65ab214bdf57..776a20172867e 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -64,6 +64,13 @@ static int sgx_encl_create(struct sgx_encl *encl, struct sgx_secs *secs)
 	struct file *backing;
 	long ret;
 
+	/*
+	 * ECREATE would detect this too, but checking here also ensures
+	 * that the 'encl_size' calculations below can never overflow.
+	 */
+	if (!is_power_of_2(secs->size))
+		return -EINVAL;
+
 	va_page = sgx_encl_grow(encl, true);
 	if (IS_ERR(va_page))
 		return PTR_ERR(va_page);

From ca0dedaff92307591f66c9206933fbdfe87add10 Mon Sep 17 00:00:00 2001
From: Kailang Yang <kailang@realtek.com>
Date: Wed, 5 Mar 2025 13:54:34 +0800
Subject: [PATCH 1572/2753] ALSA: hda/realtek: update ALC222 depop optimize

Add ALC222 its own depop functions for alc_init and alc_shutup.

[note: this fixes pop noise issues on the models with two headphone
 jacks -- tiwai ]

Signed-off-by: Kailang Yang <kailang@realtek.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 76 +++++++++++++++++++++++++++++++++++
 1 file changed, 76 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 697a38e41e166..4ca457e7ca9dd 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -3843,6 +3843,79 @@ static void alc225_shutup(struct hda_codec *codec)
 	}
 }
 
+static void alc222_init(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
+	bool hp1_pin_sense, hp2_pin_sense;
+
+	if (!hp_pin)
+		return;
+
+	msleep(30);
+
+	hp1_pin_sense = snd_hda_jack_detect(codec, hp_pin);
+	hp2_pin_sense = snd_hda_jack_detect(codec, 0x14);
+
+	if (hp1_pin_sense || hp2_pin_sense) {
+		msleep(2);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+		msleep(75);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+
+		msleep(75);
+	}
+}
+
+static void alc222_shutup(struct hda_codec *codec)
+{
+	struct alc_spec *spec = codec->spec;
+	hda_nid_t hp_pin = alc_get_hp_pin(spec);
+	bool hp1_pin_sense, hp2_pin_sense;
+
+	if (!hp_pin)
+		hp_pin = 0x21;
+
+	hp1_pin_sense = snd_hda_jack_detect(codec, hp_pin);
+	hp2_pin_sense = snd_hda_jack_detect(codec, 0x14);
+
+	if (hp1_pin_sense || hp2_pin_sense) {
+		msleep(2);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+
+		msleep(75);
+
+		if (hp1_pin_sense)
+			snd_hda_codec_write(codec, hp_pin, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+		if (hp2_pin_sense)
+			snd_hda_codec_write(codec, 0x14, 0,
+				    AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+
+		msleep(75);
+	}
+	alc_auto_setup_eapd(codec, false);
+	alc_shutup_pins(codec);
+}
+
 static void alc_default_init(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
@@ -11907,8 +11980,11 @@ static int patch_alc269(struct hda_codec *codec)
 		spec->codec_variant = ALC269_TYPE_ALC300;
 		spec->gen.mixer_nid = 0; /* no loopback on ALC300 */
 		break;
+	case 0x10ec0222:
 	case 0x10ec0623:
 		spec->codec_variant = ALC269_TYPE_ALC623;
+		spec->shutup = alc222_shutup;
+		spec->init_hook = alc222_init;
 		break;
 	case 0x10ec0700:
 	case 0x10ec0701:

From 1ee5aa765c22a0577ec552d460bf2035300b4b51 Mon Sep 17 00:00:00 2001
From: Hoku Ishibe <me@hokuishi.be>
Date: Sun, 23 Feb 2025 21:05:17 -0500
Subject: [PATCH 1573/2753] ALSA: hda: intel: Add Dell ALC3271 to power_save
 denylist

Dell XPS 13 7390 with the Realtek ALC3271 codec experiences
persistent humming noise when the power_save mode is enabled.
This issue occurs when the codec enters power saving mode,
leading to unwanted noise from the speakers.

This patch adds the affected model (PCI ID 0x1028:0x0962) to the
power_save denylist to ensure power_save is disabled by default,
preventing power-off related noise issues.

Steps to Reproduce
1. Boot the system with `snd_hda_intel` loaded.
2. Verify that `power_save` mode is enabled:
```sh
cat /sys/module/snd_hda_intel/parameters/power_save
````
output: 10 (default power save timeout)
3. Wait for the power save timeout
4. Observe a persistent humming noise from the speakers
5. Disable `power_save` manually:
```sh
echo 0 | sudo tee /sys/module/snd_hda_intel/parameters/power_save
````
6. Confirm that the noise disappears immediately.

This issue has been observed on my system, and this patch
successfully eliminates the unwanted noise. If other users
experience similar issues, additional reports would be helpful.

Signed-off-by: Hoku Ishibe <me@hokuishi.be>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20250224020517.51035-1-me@hokuishi.be
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/hda_intel.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 67540e0373099..e67c22c59f02b 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2232,6 +2232,8 @@ static const struct snd_pci_quirk power_save_denylist[] = {
 	SND_PCI_QUIRK(0x1631, 0xe017, "Packard Bell NEC IMEDIA 5204", 0),
 	/* KONTRON SinglePC may cause a stall at runtime resume */
 	SND_PCI_QUIRK(0x1734, 0x1232, "KONTRON SinglePC", 0),
+	/* Dell ALC3271 */
+	SND_PCI_QUIRK(0x1028, 0x0962, "Dell ALC3271", 0),
 	{}
 };
 

From 50dc696c3a482ea35bd0691f728d47e40b668483 Mon Sep 17 00:00:00 2001
From: Aiden Ma <jiaheng.ma@foxmail.com>
Date: Tue, 4 Mar 2025 19:54:01 +0800
Subject: [PATCH 1574/2753] doc: correcting two prefix errors in idmappings.rst

Add the 'k' prefix to id 21000. And id `u1000` in the third
idmapping should be mapped to `k31000`, not `u31000`.

Signed-off-by: Aiden Ma <jiaheng.ma@foxmail.com>
Link: https://lore.kernel.org/r/tencent_4E7B1F143E8051530C21FCADF4E014DCBB06@qq.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/idmappings.rst | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/Documentation/filesystems/idmappings.rst b/Documentation/filesystems/idmappings.rst
index 77930c77fcfe6..2a206129f8284 100644
--- a/Documentation/filesystems/idmappings.rst
+++ b/Documentation/filesystems/idmappings.rst
@@ -63,8 +63,8 @@ what id ``k11000`` corresponds to in the second or third idmapping. The
 straightforward algorithm to use is to apply the inverse of the first idmapping,
 mapping ``k11000`` up to ``u1000``. Afterwards, we can map ``u1000`` down using
 either the second idmapping mapping or third idmapping mapping. The second
-idmapping would map ``u1000`` down to ``21000``. The third idmapping would map
-``u1000`` down to ``u31000``.
+idmapping would map ``u1000`` down to ``k21000``. The third idmapping would map
+``u1000`` down to ``k31000``.
 
 If we were given the same task for the following three idmappings::
 

From 9ba93cb8212d62bccd8b41b8adb6656abf37280a Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 5 Mar 2025 10:28:41 +0530
Subject: [PATCH 1575/2753] platform/x86/amd/pmf: Propagate PMF-TA return codes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In the amd_pmf_invoke_cmd_init() function within the PMF driver ensure
that the actual result from the PMF-TA is returned rather than a generic
EIO. This change allows for proper handling of errors originating from the
PMF-TA.

Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Co-developed-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250305045842.4117767-1-Shyam-sundar.S-k@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index 8c88769ea1d87..b404764550c4c 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -323,7 +323,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 	} else {
 		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
 		dev->smart_pc_enabled = false;
-		return -EIO;
+		return res;
 	}
 
 	return 0;

From 376a8c2a144397d9cf2a67d403dd64f4a7ff9104 Mon Sep 17 00:00:00 2001
From: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Date: Wed, 5 Mar 2025 10:28:42 +0530
Subject: [PATCH 1576/2753] platform/x86/amd/pmf: Update PMF Driver for
 Compatibility with new PMF-TA
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PMF driver allocates a shared memory buffer using
tee_shm_alloc_kernel_buf() for communication with the PMF-TA.

The latest PMF-TA version introduces new structures with OEM debug
information and additional policy input conditions for evaluating the
policy binary. Consequently, the shared memory size must be increased to
ensure compatibility between the PMF driver and the updated PMF-TA.

To do so, introduce the new PMF-TA UUID and update the PMF shared memory
configuration to ensure compatibility with the latest PMF-TA version.
Additionally, export the TA UUID.

These updates will result in modifications to the prototypes of
amd_pmf_tee_init() and amd_pmf_ta_open_session().

Link: https://lore.kernel.org/all/55ac865f-b1c7-fa81-51c4-d211c7963e7e@linux.intel.com/
Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
Co-developed-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Patil Rajesh Reddy <Patil.Reddy@amd.com>
Signed-off-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250305045842.4117767-2-Shyam-sundar.S-k@amd.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/pmf.h    |  5 ++-
 drivers/platform/x86/amd/pmf/tee-if.c | 50 +++++++++++++++++++--------
 2 files changed, 40 insertions(+), 15 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h
index 41b2b91b8fdc6..e6bdee68ccf34 100644
--- a/drivers/platform/x86/amd/pmf/pmf.h
+++ b/drivers/platform/x86/amd/pmf/pmf.h
@@ -106,9 +106,12 @@ struct cookie_header {
 #define PMF_TA_IF_VERSION_MAJOR				1
 #define TA_PMF_ACTION_MAX					32
 #define TA_PMF_UNDO_MAX						8
-#define TA_OUTPUT_RESERVED_MEM				906
+#define TA_OUTPUT_RESERVED_MEM				922
 #define MAX_OPERATION_PARAMS					4
 
+#define TA_ERROR_CRYPTO_INVALID_PARAM				0x20002
+#define TA_ERROR_CRYPTO_BIN_TOO_LARGE				0x2000d
+
 #define PMF_IF_V1		1
 #define PMF_IF_V2		2
 
diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index b404764550c4c..ceaff1ebb7b93 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -27,8 +27,11 @@ module_param(pb_side_load, bool, 0444);
 MODULE_PARM_DESC(pb_side_load, "Sideload policy binaries debug policy failures");
 #endif
 
-static const uuid_t amd_pmf_ta_uuid = UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d,
-						0xb1, 0x2d, 0xc5, 0x29, 0xb1, 0x3d, 0x85, 0x43);
+static const uuid_t amd_pmf_ta_uuid[] = { UUID_INIT(0xd9b39bf2, 0x66bd, 0x4154, 0xaf, 0xb8, 0x8a,
+						    0xcc, 0x2b, 0x2b, 0x60, 0xd6),
+					  UUID_INIT(0x6fd93b77, 0x3fb8, 0x524d, 0xb1, 0x2d, 0xc5,
+						    0x29, 0xb1, 0x3d, 0x85, 0x43),
+					};
 
 static const char *amd_pmf_uevent_as_str(unsigned int state)
 {
@@ -321,7 +324,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev)
 		 */
 		schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3));
 	} else {
-		dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res);
+		dev_dbg(dev->dev, "ta invoke cmd init failed err: %x\n", res);
 		dev->smart_pc_enabled = false;
 		return res;
 	}
@@ -390,12 +393,12 @@ static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const voi
 	return ver->impl_id == TEE_IMPL_ID_AMDTEE;
 }
 
-static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id)
+static int amd_pmf_ta_open_session(struct tee_context *ctx, u32 *id, const uuid_t *uuid)
 {
 	struct tee_ioctl_open_session_arg sess_arg = {};
 	int rc;
 
-	export_uuid(sess_arg.uuid, &amd_pmf_ta_uuid);
+	export_uuid(sess_arg.uuid, uuid);
 	sess_arg.clnt_login = TEE_IOCTL_LOGIN_PUBLIC;
 	sess_arg.num_params = 0;
 
@@ -434,7 +437,7 @@ static int amd_pmf_register_input_device(struct amd_pmf_dev *dev)
 	return 0;
 }
 
-static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
+static int amd_pmf_tee_init(struct amd_pmf_dev *dev, const uuid_t *uuid)
 {
 	u32 size;
 	int ret;
@@ -445,7 +448,7 @@ static int amd_pmf_tee_init(struct amd_pmf_dev *dev)
 		return PTR_ERR(dev->tee_ctx);
 	}
 
-	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id);
+	ret = amd_pmf_ta_open_session(dev->tee_ctx, &dev->session_id, uuid);
 	if (ret) {
 		dev_err(dev->dev, "Failed to open TA session (%d)\n", ret);
 		ret = -EINVAL;
@@ -489,7 +492,8 @@ static void amd_pmf_tee_deinit(struct amd_pmf_dev *dev)
 
 int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 {
-	int ret;
+	bool status;
+	int ret, i;
 
 	ret = apmf_check_smart_pc(dev);
 	if (ret) {
@@ -502,10 +506,6 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		return -ENODEV;
 	}
 
-	ret = amd_pmf_tee_init(dev);
-	if (ret)
-		return ret;
-
 	INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd);
 
 	ret = amd_pmf_set_dram_addr(dev, true);
@@ -534,8 +534,30 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 		goto error;
 	}
 
-	ret = amd_pmf_start_policy_engine(dev);
-	if (ret)
+	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
+		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
+		if (ret)
+			return ret;
+
+		ret = amd_pmf_start_policy_engine(dev);
+		switch (ret) {
+		case TA_PMF_TYPE_SUCCESS:
+			status = true;
+			break;
+		case TA_ERROR_CRYPTO_INVALID_PARAM:
+		case TA_ERROR_CRYPTO_BIN_TOO_LARGE:
+			amd_pmf_tee_deinit(dev);
+			status = false;
+			break;
+		default:
+			goto error;
+		}
+
+		if (status)
+			break;
+	}
+
+	if (!status && !pb_side_load)
 		goto error;
 
 	if (pb_side_load)

From 385eff211ee0efa95c8ce9d7c7b1d8d79d5d7330 Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Thu, 27 Feb 2025 21:12:25 +0800
Subject: [PATCH 1577/2753] wifi: rtw89: fw: use struct to fill role_maintain
 H2C command

The role_maintain H2C command is to align operating mode of WiFi role,
such as STA or AP modes, between driver and firmware.

Use a struct to fill fields of this H2C command.

Don't change logic at all.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250227131228.8457-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 22 +++++++++++--------
 drivers/net/wireless/realtek/rtw89/fw.h | 28 +++++++++----------------
 2 files changed, 23 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index b843d259fbfa8..3e4a3200358a1 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3901,14 +3901,15 @@ int rtw89_fw_h2c_update_beacon_be(struct rtw89_dev *rtwdev,
 }
 EXPORT_SYMBOL(rtw89_fw_h2c_update_beacon_be);
 
-#define H2C_ROLE_MAINTAIN_LEN 4
 int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev,
 			       struct rtw89_vif_link *rtwvif_link,
 			       struct rtw89_sta_link *rtwsta_link,
 			       enum rtw89_upd_mode upd_mode)
 {
-	struct sk_buff *skb;
 	u8 mac_id = rtwsta_link ? rtwsta_link->mac_id : rtwvif_link->mac_id;
+	struct rtw89_h2c_role_maintain *h2c;
+	u32 len = sizeof(*h2c);
+	struct sk_buff *skb;
 	u8 self_role;
 	int ret;
 
@@ -3921,21 +3922,24 @@ int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev,
 		self_role = rtwvif_link->self_role;
 	}
 
-	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, H2C_ROLE_MAINTAIN_LEN);
+	skb = rtw89_fw_h2c_alloc_skb_with_hdr(rtwdev, len);
 	if (!skb) {
 		rtw89_err(rtwdev, "failed to alloc skb for h2c join\n");
 		return -ENOMEM;
 	}
-	skb_put(skb, H2C_ROLE_MAINTAIN_LEN);
-	SET_FWROLE_MAINTAIN_MACID(skb->data, mac_id);
-	SET_FWROLE_MAINTAIN_SELF_ROLE(skb->data, self_role);
-	SET_FWROLE_MAINTAIN_UPD_MODE(skb->data, upd_mode);
-	SET_FWROLE_MAINTAIN_WIFI_ROLE(skb->data, rtwvif_link->wifi_role);
+	skb_put(skb, len);
+	h2c = (struct rtw89_h2c_role_maintain *)skb->data;
+
+	h2c->w0 = le32_encode_bits(mac_id, RTW89_H2C_ROLE_MAINTAIN_W0_MACID) |
+		  le32_encode_bits(self_role, RTW89_H2C_ROLE_MAINTAIN_W0_SELF_ROLE) |
+		  le32_encode_bits(upd_mode, RTW89_H2C_ROLE_MAINTAIN_W0_UPD_MODE) |
+		  le32_encode_bits(rtwvif_link->wifi_role,
+				   RTW89_H2C_ROLE_MAINTAIN_W0_WIFI_ROLE);
 
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_MAC, H2C_CL_MAC_MEDIA_RPT,
 			      H2C_FUNC_MAC_FWROLE_MAINTAIN, 0, 1,
-			      H2C_ROLE_MAINTAIN_LEN);
+			      len);
 
 	ret = rtw89_h2c_tx(rtwdev, skb, false);
 	if (ret) {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index 1c53c1e224396..e0faed0761509 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -1591,25 +1591,17 @@ struct rtw89_h2c_bcn_upd_be {
 #define RTW89_H2C_BCN_UPD_BE_W7_ECSA_OFST GENMASK(30, 16)
 #define RTW89_H2C_BCN_UPD_BE_W7_PROTECTION_KEY_ID BIT(31)
 
-static inline void SET_FWROLE_MAINTAIN_MACID(void *h2c, u32 val)
-{
-	le32p_replace_bits((__le32 *)h2c, val, GENMASK(7, 0));
-}
-
-static inline void SET_FWROLE_MAINTAIN_SELF_ROLE(void *h2c, u32 val)
-{
-	le32p_replace_bits((__le32 *)h2c, val, GENMASK(9, 8));
-}
-
-static inline void SET_FWROLE_MAINTAIN_UPD_MODE(void *h2c, u32 val)
-{
-	le32p_replace_bits((__le32 *)h2c, val, GENMASK(12, 10));
-}
+struct rtw89_h2c_role_maintain {
+	__le32 w0;
+};
 
-static inline void SET_FWROLE_MAINTAIN_WIFI_ROLE(void *h2c, u32 val)
-{
-	le32p_replace_bits((__le32 *)h2c, val, GENMASK(16, 13));
-}
+#define RTW89_H2C_ROLE_MAINTAIN_W0_MACID GENMASK(7, 0)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_SELF_ROLE GENMASK(9, 8)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_UPD_MODE GENMASK(12, 10)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_WIFI_ROLE GENMASK(16, 13)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_BAND GENMASK(18, 17)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_PORT GENMASK(21, 19)
+#define RTW89_H2C_ROLE_MAINTAIN_W0_MACID_EXT GENMASK(31, 24)
 
 enum rtw89_fw_sta_type { /* value of RTW89_H2C_JOININFO_W1_STA_TYPE */
 	RTW89_FW_N_AC_STA = 0,

From b521af1dcdc319ec966563c2060bdf515401577f Mon Sep 17 00:00:00 2001
From: Po-Hao Huang <phhuang@realtek.com>
Date: Thu, 27 Feb 2025 21:12:26 +0800
Subject: [PATCH 1578/2753] wifi: rtw89: fw: update role_maintain H2C command
 for roles operating on band 1

Add new fields band and port ID to make chips operating on the band and
port ID other than 0, so that multiple vif(s) can be working at the
same time.

Signed-off-by: Po-Hao Huang <phhuang@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250227131228.8457-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 3e4a3200358a1..1965a62746c2f 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -3934,7 +3934,10 @@ int rtw89_fw_h2c_role_maintain(struct rtw89_dev *rtwdev,
 		  le32_encode_bits(self_role, RTW89_H2C_ROLE_MAINTAIN_W0_SELF_ROLE) |
 		  le32_encode_bits(upd_mode, RTW89_H2C_ROLE_MAINTAIN_W0_UPD_MODE) |
 		  le32_encode_bits(rtwvif_link->wifi_role,
-				   RTW89_H2C_ROLE_MAINTAIN_W0_WIFI_ROLE);
+				   RTW89_H2C_ROLE_MAINTAIN_W0_WIFI_ROLE) |
+		  le32_encode_bits(rtwvif_link->mac_idx,
+				   RTW89_H2C_ROLE_MAINTAIN_W0_BAND) |
+		  le32_encode_bits(rtwvif_link->port, RTW89_H2C_ROLE_MAINTAIN_W0_PORT);
 
 	rtw89_h2c_pkt_set_hdr(rtwdev, skb, FWCMD_TYPE_H2C,
 			      H2C_CAT_MAC, H2C_CL_MAC_MEDIA_RPT,

From 88b46320fc9d915aa0c1c765db5ccd2db12fe92e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 27 Feb 2025 21:12:27 +0800
Subject: [PATCH 1579/2753] wifi: rtw89: fw: correct debug message format in
 rtw89_build_txpwr_trk_tbl_from_elm()

The format should be "%08x". Fix the mistakes.

Fixes: d60e73e5dd70 ("wifi: rtw89: fw: load TX power track tables from fw_element")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250227131228.8457-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 1965a62746c2f..15d6bda1fcf00 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -1099,7 +1099,7 @@ int rtw89_build_txpwr_trk_tbl_from_elm(struct rtw89_dev *rtwdev,
 	bitmap = le32_to_cpu(elm->u.txpwr_trk.bitmap);
 
 	if ((bitmap & needed_bitmap) != needed_bitmap) {
-		rtw89_warn(rtwdev, "needed txpwr trk bitmap %08x but %0x8x\n",
+		rtw89_warn(rtwdev, "needed txpwr trk bitmap %08x but %08x\n",
 			   needed_bitmap, bitmap);
 		return -ENOENT;
 	}

From ad26d0dcb3bd5864c5295746bd4fef6376911da6 Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 27 Feb 2025 21:12:28 +0800
Subject: [PATCH 1580/2753] wifi: rtw89: fw: don't reject firmware in blacklist
 to prevent breaking users

Once update driver blacklist of firmware, users' firmware might be in
the list, and then driver stops working. Since breaking users is not
expected, report a significant message instead of stopping.

Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250227131228.8457-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/fw.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index 15d6bda1fcf00..d0a246f415ffc 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -372,7 +372,7 @@ static int __check_secure_blacklist(struct rtw89_dev *rtwdev,
 		return 0;
 
 	if (!chip_blacklist) {
-		rtw89_err(rtwdev, "chip no blacklist for secure firmware\n");
+		rtw89_warn(rtwdev, "chip no blacklist for secure firmware\n");
 		return -ENOENT;
 	}
 
@@ -380,14 +380,14 @@ static int __check_secure_blacklist(struct rtw89_dev *rtwdev,
 	bit_mask = BIT(section_content->blacklist.bit_in_chip_list & 0x7);
 
 	if (section_content->blacklist.ver > chip_blacklist->ver) {
-		rtw89_err(rtwdev, "chip blacklist out of date (%u, %u)\n",
-			  section_content->blacklist.ver, chip_blacklist->ver);
+		rtw89_warn(rtwdev, "chip blacklist out of date (%u, %u)\n",
+			   section_content->blacklist.ver, chip_blacklist->ver);
 		return -EINVAL;
 	}
 
 	if (chip_blacklist->list[byte_idx] & bit_mask) {
-		rtw89_err(rtwdev, "firmware %u in chip blacklist\n",
-			  section_content->blacklist.ver);
+		rtw89_warn(rtwdev, "firmware %u in chip blacklist\n",
+			   section_content->blacklist.ver);
 		return -EPERM;
 	}
 
@@ -427,7 +427,10 @@ static int __parse_security_section(struct rtw89_dev *rtwdev,
 		info->secure_section_exist = true;
 	}
 
-	return __check_secure_blacklist(rtwdev, info, section_info, content);
+	ret = __check_secure_blacklist(rtwdev, info, section_info, content);
+	WARN_ONCE(ret, "Current firmware in blacklist. Please update firmware.\n");
+
+	return 0;
 }
 
 static int rtw89_fw_hdr_parser_v1(struct rtw89_dev *rtwdev, const u8 *fw, u32 len,

From 3218f5bd8e2e4abc156493f8121b8db53b49ee9e Mon Sep 17 00:00:00 2001
From: Ping-Ke Shih <pkshih@realtek.com>
Date: Thu, 27 Feb 2025 21:19:07 +0800
Subject: [PATCH 1581/2753] wifi: rtw89: pci: correct ISR RDU bit for 8922AE

The interrupt status (ISR) bits of RX desc unavailable (RDU) for 8922AE
are B_BE_RDU_CH1_INT_V1 and B_BE_RDU_CH0_INT_V1. With wrong bits, if it
happens, driver can't recognize the situation and prompt a message.
Fix the definition accordingly.

Fixes: aa70f76120ee ("wifi: rtw89: pci: generalize interrupt status bits of interrupt handlers")
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250227131907.9864-1-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/pci.h    | 56 +++++++++++----------
 drivers/net/wireless/realtek/rtw89/pci_be.c |  2 +-
 2 files changed, 30 insertions(+), 28 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/pci.h b/drivers/net/wireless/realtek/rtw89/pci.h
index 4d11c3dd60a5d..79fef5f901408 100644
--- a/drivers/net/wireless/realtek/rtw89/pci.h
+++ b/drivers/net/wireless/realtek/rtw89/pci.h
@@ -455,34 +455,36 @@
 #define B_BE_RX0DMA_INT_EN BIT(0)
 
 #define R_BE_HAXI_HISR00 0xB0B4
-#define B_BE_RDU_CH6_INT BIT(28)
-#define B_BE_RDU_CH5_INT BIT(27)
-#define B_BE_RDU_CH4_INT BIT(26)
-#define B_BE_RDU_CH2_INT BIT(25)
-#define B_BE_RDU_CH1_INT BIT(24)
-#define B_BE_RDU_CH0_INT BIT(23)
-#define B_BE_RXDMA_STUCK_INT BIT(22)
-#define B_BE_TXDMA_STUCK_INT BIT(21)
-#define B_BE_TXDMA_CH14_INT BIT(20)
-#define B_BE_TXDMA_CH13_INT BIT(19)
-#define B_BE_TXDMA_CH12_INT BIT(18)
-#define B_BE_TXDMA_CH11_INT BIT(17)
-#define B_BE_TXDMA_CH10_INT BIT(16)
-#define B_BE_TXDMA_CH9_INT BIT(15)
-#define B_BE_TXDMA_CH8_INT BIT(14)
-#define B_BE_TXDMA_CH7_INT BIT(13)
-#define B_BE_TXDMA_CH6_INT BIT(12)
-#define B_BE_TXDMA_CH5_INT BIT(11)
-#define B_BE_TXDMA_CH4_INT BIT(10)
-#define B_BE_TXDMA_CH3_INT BIT(9)
-#define B_BE_TXDMA_CH2_INT BIT(8)
-#define B_BE_TXDMA_CH1_INT BIT(7)
-#define B_BE_TXDMA_CH0_INT BIT(6)
-#define B_BE_RPQ1DMA_INT BIT(5)
-#define B_BE_RX1P1DMA_INT BIT(4)
+#define B_BE_RDU_CH5_INT_V1 BIT(30)
+#define B_BE_RDU_CH4_INT_V1 BIT(29)
+#define B_BE_RDU_CH3_INT_V1 BIT(28)
+#define B_BE_RDU_CH2_INT_V1 BIT(27)
+#define B_BE_RDU_CH1_INT_V1 BIT(26)
+#define B_BE_RDU_CH0_INT_V1 BIT(25)
+#define B_BE_RXDMA_STUCK_INT_V1 BIT(24)
+#define B_BE_TXDMA_STUCK_INT_V1 BIT(23)
+#define B_BE_TXDMA_CH14_INT_V1 BIT(22)
+#define B_BE_TXDMA_CH13_INT_V1 BIT(21)
+#define B_BE_TXDMA_CH12_INT_V1 BIT(20)
+#define B_BE_TXDMA_CH11_INT_V1 BIT(19)
+#define B_BE_TXDMA_CH10_INT_V1 BIT(18)
+#define B_BE_TXDMA_CH9_INT_V1 BIT(17)
+#define B_BE_TXDMA_CH8_INT_V1 BIT(16)
+#define B_BE_TXDMA_CH7_INT_V1 BIT(15)
+#define B_BE_TXDMA_CH6_INT_V1 BIT(14)
+#define B_BE_TXDMA_CH5_INT_V1 BIT(13)
+#define B_BE_TXDMA_CH4_INT_V1 BIT(12)
+#define B_BE_TXDMA_CH3_INT_V1 BIT(11)
+#define B_BE_TXDMA_CH2_INT_V1 BIT(10)
+#define B_BE_TXDMA_CH1_INT_V1 BIT(9)
+#define B_BE_TXDMA_CH0_INT_V1 BIT(8)
+#define B_BE_RX1P1DMA_INT_V1 BIT(7)
+#define B_BE_RX0P1DMA_INT_V1 BIT(6)
+#define B_BE_RO1DMA_INT BIT(5)
+#define B_BE_RP1DMA_INT BIT(4)
 #define B_BE_RX1DMA_INT BIT(3)
-#define B_BE_RPQ0DMA_INT BIT(2)
-#define B_BE_RX0P1DMA_INT BIT(1)
+#define B_BE_RO0DMA_INT BIT(2)
+#define B_BE_RP0DMA_INT BIT(1)
 #define B_BE_RX0DMA_INT BIT(0)
 
 /* TX/RX */
diff --git a/drivers/net/wireless/realtek/rtw89/pci_be.c b/drivers/net/wireless/realtek/rtw89/pci_be.c
index cd39eebe81861..12e6a0cbb889b 100644
--- a/drivers/net/wireless/realtek/rtw89/pci_be.c
+++ b/drivers/net/wireless/realtek/rtw89/pci_be.c
@@ -666,7 +666,7 @@ SIMPLE_DEV_PM_OPS(rtw89_pm_ops_be, rtw89_pci_suspend_be, rtw89_pci_resume_be);
 EXPORT_SYMBOL(rtw89_pm_ops_be);
 
 const struct rtw89_pci_gen_def rtw89_pci_gen_be = {
-	.isr_rdu = B_BE_RDU_CH1_INT | B_BE_RDU_CH0_INT,
+	.isr_rdu = B_BE_RDU_CH1_INT_V1 | B_BE_RDU_CH0_INT_V1,
 	.isr_halt_c2h = B_BE_HALT_C2H_INT,
 	.isr_wdt_timeout = B_BE_WDT_TIMEOUT_INT,
 	.isr_clear_rpq = {R_BE_PCIE_DMA_ISR, B_BE_PCIE_RX_RPQ0_ISR_V1},

From 12f65d1203507f7db3ba59930fe29a3b8eee9945 Mon Sep 17 00:00:00 2001
From: Koichiro Den <koichiro.den@canonical.com>
Date: Mon, 24 Feb 2025 23:31:26 +0900
Subject: [PATCH 1582/2753] gpio: aggregator: protect driver attr handlers
 against module unload

Both new_device_store and delete_device_store touch module global
resources (e.g. gpio_aggregator_lock). To prevent race conditions with
module unload, a reference needs to be held.

Add try_module_get() in these handlers.

For new_device_store, this eliminates what appears to be the most dangerous
scenario: if an id is allocated from gpio_aggregator_idr but
platform_device_register has not yet been called or completed, a concurrent
module unload could fail to unregister/delete the device, leaving behind a
dangling platform device/GPIO forwarder. This can result in various issues.
The following simple reproducer demonstrates these problems:

  #!/bin/bash
  while :; do
    # note: whether 'gpiochip0 0' exists or not does not matter.
    echo 'gpiochip0 0' > /sys/bus/platform/drivers/gpio-aggregator/new_device
  done &
  while :; do
    modprobe gpio-aggregator
    modprobe -r gpio-aggregator
  done &
  wait

  Starting with the following warning, several kinds of warnings will appear
  and the system may become unstable:

  ------------[ cut here ]------------
  list_del corruption, ffff888103e2e980->next is LIST_POISON1 (dead000000000100)
  WARNING: CPU: 1 PID: 1327 at lib/list_debug.c:56 __list_del_entry_valid_or_report+0xa3/0x120
  [...]
  RIP: 0010:__list_del_entry_valid_or_report+0xa3/0x120
  [...]
  Call Trace:
   <TASK>
   ? __list_del_entry_valid_or_report+0xa3/0x120
   ? __warn.cold+0x93/0xf2
   ? __list_del_entry_valid_or_report+0xa3/0x120
   ? report_bug+0xe6/0x170
   ? __irq_work_queue_local+0x39/0xe0
   ? handle_bug+0x58/0x90
   ? exc_invalid_op+0x13/0x60
   ? asm_exc_invalid_op+0x16/0x20
   ? __list_del_entry_valid_or_report+0xa3/0x120
   gpiod_remove_lookup_table+0x22/0x60
   new_device_store+0x315/0x350 [gpio_aggregator]
   kernfs_fop_write_iter+0x137/0x1f0
   vfs_write+0x262/0x430
   ksys_write+0x60/0xd0
   do_syscall_64+0x6c/0x180
   entry_SYSCALL_64_after_hwframe+0x76/0x7e
   [...]
   </TASK>
  ---[ end trace 0000000000000000 ]---

Fixes: 828546e24280 ("gpio: Add GPIO Aggregator")
Cc: stable@vger.kernel.org
Signed-off-by: Koichiro Den <koichiro.den@canonical.com>
Link: https://lore.kernel.org/r/20250224143134.3024598-2-koichiro.den@canonical.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-aggregator.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c
index 65f41cc3eafcc..d668ddb2e81d3 100644
--- a/drivers/gpio/gpio-aggregator.c
+++ b/drivers/gpio/gpio-aggregator.c
@@ -119,10 +119,15 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	struct platform_device *pdev;
 	int res, id;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	/* kernfs guarantees string termination, so count + 1 is safe */
 	aggr = kzalloc(sizeof(*aggr) + count + 1, GFP_KERNEL);
-	if (!aggr)
-		return -ENOMEM;
+	if (!aggr) {
+		res = -ENOMEM;
+		goto put_module;
+	}
 
 	memcpy(aggr->args, buf, count + 1);
 
@@ -161,6 +166,7 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	}
 
 	aggr->pdev = pdev;
+	module_put(THIS_MODULE);
 	return count;
 
 remove_table:
@@ -175,6 +181,8 @@ static ssize_t new_device_store(struct device_driver *driver, const char *buf,
 	kfree(aggr->lookups);
 free_ga:
 	kfree(aggr);
+put_module:
+	module_put(THIS_MODULE);
 	return res;
 }
 
@@ -203,13 +211,19 @@ static ssize_t delete_device_store(struct device_driver *driver,
 	if (error)
 		return error;
 
+	if (!try_module_get(THIS_MODULE))
+		return -ENOENT;
+
 	mutex_lock(&gpio_aggregator_lock);
 	aggr = idr_remove(&gpio_aggregator_idr, id);
 	mutex_unlock(&gpio_aggregator_lock);
-	if (!aggr)
+	if (!aggr) {
+		module_put(THIS_MODULE);
 		return -ENOENT;
+	}
 
 	gpio_aggregator_free(aggr);
+	module_put(THIS_MODULE);
 	return count;
 }
 static DRIVER_ATTR_WO(delete_device);

From f02c41f87cfe61440c18bf77d1ef0a884b9ee2b5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Niklas=20S=C3=B6derlund?=
 <niklas.soderlund+renesas@ragnatech.se>
Date: Tue, 21 Jan 2025 14:58:33 +0100
Subject: [PATCH 1583/2753] gpio: rcar: Use raw_spinlock to protect register
 access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use raw_spinlock in order to fix spurious messages about invalid context
when spinlock debugging is enabled. The lock is only used to serialize
register access.

    [    4.239592] =============================
    [    4.239595] [ BUG: Invalid wait context ]
    [    4.239599] 6.13.0-rc7-arm64-renesas-05496-gd088502a519f #35 Not tainted
    [    4.239603] -----------------------------
    [    4.239606] kworker/u8:5/76 is trying to lock:
    [    4.239609] ffff0000091898a0 (&p->lock){....}-{3:3}, at: gpio_rcar_config_interrupt_input_mode+0x34/0x164
    [    4.239641] other info that might help us debug this:
    [    4.239643] context-{5:5}
    [    4.239646] 5 locks held by kworker/u8:5/76:
    [    4.239651]  #0: ffff0000080fb148 ((wq_completion)async){+.+.}-{0:0}, at: process_one_work+0x190/0x62c
    [    4.250180] OF: /soc/sound@ec500000/ports/port@0/endpoint: Read of boolean property 'frame-master' with a value.
    [    4.254094]  #1: ffff80008299bd80 ((work_completion)(&entry->work)){+.+.}-{0:0}, at: process_one_work+0x1b8/0x62c
    [    4.254109]  #2: ffff00000920c8f8
    [    4.258345] OF: /soc/sound@ec500000/ports/port@1/endpoint: Read of boolean property 'bitclock-master' with a value.
    [    4.264803]  (&dev->mutex){....}-{4:4}, at: __device_attach_async_helper+0x3c/0xdc
    [    4.264820]  #3: ffff00000a50ca40 (request_class#2){+.+.}-{4:4}, at: __setup_irq+0xa0/0x690
    [    4.264840]  #4:
    [    4.268872] OF: /soc/sound@ec500000/ports/port@1/endpoint: Read of boolean property 'frame-master' with a value.
    [    4.273275] ffff00000a50c8c8 (lock_class){....}-{2:2}, at: __setup_irq+0xc4/0x690
    [    4.296130] renesas_sdhi_internal_dmac ee100000.mmc: mmc1 base at 0x00000000ee100000, max clock rate 200 MHz
    [    4.304082] stack backtrace:
    [    4.304086] CPU: 1 UID: 0 PID: 76 Comm: kworker/u8:5 Not tainted 6.13.0-rc7-arm64-renesas-05496-gd088502a519f #35
    [    4.304092] Hardware name: Renesas Salvator-X 2nd version board based on r8a77965 (DT)
    [    4.304097] Workqueue: async async_run_entry_fn
    [    4.304106] Call trace:
    [    4.304110]  show_stack+0x14/0x20 (C)
    [    4.304122]  dump_stack_lvl+0x6c/0x90
    [    4.304131]  dump_stack+0x14/0x1c
    [    4.304138]  __lock_acquire+0xdfc/0x1584
    [    4.426274]  lock_acquire+0x1c4/0x33c
    [    4.429942]  _raw_spin_lock_irqsave+0x5c/0x80
    [    4.434307]  gpio_rcar_config_interrupt_input_mode+0x34/0x164
    [    4.440061]  gpio_rcar_irq_set_type+0xd4/0xd8
    [    4.444422]  __irq_set_trigger+0x5c/0x178
    [    4.448435]  __setup_irq+0x2e4/0x690
    [    4.452012]  request_threaded_irq+0xc4/0x190
    [    4.456285]  devm_request_threaded_irq+0x7c/0xf4
    [    4.459398] ata1: link resume succeeded after 1 retries
    [    4.460902]  mmc_gpiod_request_cd_irq+0x68/0xe0
    [    4.470660]  mmc_start_host+0x50/0xac
    [    4.474327]  mmc_add_host+0x80/0xe4
    [    4.477817]  tmio_mmc_host_probe+0x2b0/0x440
    [    4.482094]  renesas_sdhi_probe+0x488/0x6f4
    [    4.486281]  renesas_sdhi_internal_dmac_probe+0x60/0x78
    [    4.491509]  platform_probe+0x64/0xd8
    [    4.495178]  really_probe+0xb8/0x2a8
    [    4.498756]  __driver_probe_device+0x74/0x118
    [    4.503116]  driver_probe_device+0x3c/0x154
    [    4.507303]  __device_attach_driver+0xd4/0x160
    [    4.511750]  bus_for_each_drv+0x84/0xe0
    [    4.515588]  __device_attach_async_helper+0xb0/0xdc
    [    4.520470]  async_run_entry_fn+0x30/0xd8
    [    4.524481]  process_one_work+0x210/0x62c
    [    4.528494]  worker_thread+0x1ac/0x340
    [    4.532245]  kthread+0x10c/0x110
    [    4.535476]  ret_from_fork+0x10/0x20

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250121135833.3769310-1-niklas.soderlund+renesas@ragnatech.se
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 2ecee3269a0cc..8e0544e924886 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -40,7 +40,7 @@ struct gpio_rcar_info {
 
 struct gpio_rcar_priv {
 	void __iomem *base;
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	struct device *dev;
 	struct gpio_chip gpio_chip;
 	unsigned int irq_parent;
@@ -123,7 +123,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	 * "Setting Level-Sensitive Interrupt Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive or negative logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, hwirq, !active_high_rising_edge);
@@ -142,7 +142,7 @@ static void gpio_rcar_config_interrupt_input_mode(struct gpio_rcar_priv *p,
 	if (!level_trigger)
 		gpio_rcar_write(p, INTCLR, BIT(hwirq));
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_irq_set_type(struct irq_data *d, unsigned int type)
@@ -246,7 +246,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	 * "Setting General Input Mode"
 	 */
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 
 	/* Configure positive logic in POSNEG */
 	gpio_rcar_modify_bit(p, POSNEG, gpio, false);
@@ -261,7 +261,7 @@ static void gpio_rcar_config_general_input_output_mode(struct gpio_chip *chip,
 	if (p->info.has_outdtsel && output)
 		gpio_rcar_modify_bit(p, OUTDTSEL, gpio, false);
 
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_request(struct gpio_chip *chip, unsigned offset)
@@ -347,7 +347,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 		return 0;
 	}
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	outputs = gpio_rcar_read(p, INOUTSEL);
 	m = outputs & bankmask;
 	if (m)
@@ -356,7 +356,7 @@ static int gpio_rcar_get_multiple(struct gpio_chip *chip, unsigned long *mask,
 	m = ~outputs & bankmask;
 	if (m)
 		val |= gpio_rcar_read(p, INDT) & m;
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 
 	bits[0] = val;
 	return 0;
@@ -367,9 +367,9 @@ static void gpio_rcar_set(struct gpio_chip *chip, unsigned offset, int value)
 	struct gpio_rcar_priv *p = gpiochip_get_data(chip);
 	unsigned long flags;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	gpio_rcar_modify_bit(p, OUTDT, offset, value);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
@@ -386,12 +386,12 @@ static void gpio_rcar_set_multiple(struct gpio_chip *chip, unsigned long *mask,
 	if (!bankmask)
 		return;
 
-	spin_lock_irqsave(&p->lock, flags);
+	raw_spin_lock_irqsave(&p->lock, flags);
 	val = gpio_rcar_read(p, OUTDT);
 	val &= ~bankmask;
 	val |= (bankmask & bits[0]);
 	gpio_rcar_write(p, OUTDT, val);
-	spin_unlock_irqrestore(&p->lock, flags);
+	raw_spin_unlock_irqrestore(&p->lock, flags);
 }
 
 static int gpio_rcar_direction_output(struct gpio_chip *chip, unsigned offset,
@@ -505,7 +505,7 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	p->dev = dev;
-	spin_lock_init(&p->lock);
+	raw_spin_lock_init(&p->lock);
 
 	/* Get device configuration from DT node */
 	ret = gpio_rcar_parse_dt(p, &npins);

From e859d375d1694488015e6804bfeea527a0b25b9f Mon Sep 17 00:00:00 2001
From: Wojtek Wasko <wwasko@nvidia.com>
Date: Mon, 3 Mar 2025 18:13:43 +0200
Subject: [PATCH 1584/2753] posix-clock: Store file pointer in struct
 posix_clock_context

File descriptor based pc_clock_*() operations of dynamic posix clocks
have access to the file pointer and implement permission checks in the
generic code before invoking the relevant dynamic clock callback.

Character device operations (open, read, poll, ioctl) do not implement a
generic permission control and the dynamic clock callbacks have no
access to the file pointer to implement them.

Extend struct posix_clock_context with a struct file pointer and
initialize it in posix_clock_open(), so that all dynamic clock callbacks
can access it.

Acked-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Wojtek Wasko <wwasko@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/posix-clock.h | 6 +++++-
 kernel/time/posix-clock.c   | 1 +
 2 files changed, 6 insertions(+), 1 deletion(-)

diff --git a/include/linux/posix-clock.h b/include/linux/posix-clock.h
index ef8619f489203..a500d3160fe8c 100644
--- a/include/linux/posix-clock.h
+++ b/include/linux/posix-clock.h
@@ -95,10 +95,13 @@ struct posix_clock {
  * struct posix_clock_context - represents clock file operations context
  *
  * @clk:              Pointer to the clock
+ * @fp:               Pointer to the file used to open the clock
  * @private_clkdata:  Pointer to user data
  *
  * Drivers should use struct posix_clock_context during specific character
- * device file operation methods to access the posix clock.
+ * device file operation methods to access the posix clock. In particular,
+ * the file pointer can be used to verify correct access mode for ioctl()
+ * calls.
  *
  * Drivers can store a private data structure during the open operation
  * if they have specific information that is required in other file
@@ -106,6 +109,7 @@ struct posix_clock {
  */
 struct posix_clock_context {
 	struct posix_clock *clk;
+	struct file *fp;
 	void *private_clkdata;
 };
 
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 1af0bb2cc45c0..4e114e34a6e0a 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -129,6 +129,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
 		goto out;
 	}
 	pccontext->clk = clk;
+	pccontext->fp = fp;
 	if (clk->ops.open) {
 		err = clk->ops.open(pccontext, fp->f_mode);
 		if (err) {

From b4e53b15c04e3852949003752f48f7a14ae39e86 Mon Sep 17 00:00:00 2001
From: Wojtek Wasko <wwasko@nvidia.com>
Date: Mon, 3 Mar 2025 18:13:44 +0200
Subject: [PATCH 1585/2753] ptp: Add PHC file mode checks. Allow RO adjtime()
 without FMODE_WRITE.
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Many devices implement highly accurate clocks, which the kernel manages
as PTP Hardware Clocks (PHCs). Userspace applications rely on these
clocks to timestamp events, trace workload execution, correlate
timescales across devices, and keep various clocks in sync.

The kernel’s current implementation of PTP clocks does not enforce file
permissions checks for most device operations except for POSIX clock
operations, where file mode is verified in the POSIX layer before
forwarding the call to the PTP subsystem. Consequently, it is common
practice to not give unprivileged userspace applications any access to
PTP clocks whatsoever by giving the PTP chardevs 600 permissions. An
example of users running into this limitation is documented in [1].
Additionally, POSIX layer requires WRITE permission even for readonly
adjtime() calls which are used in PTP layer to return current frequency
offset applied to the PHC.

Add permission checks for functions that modify the state of a PTP
device. Continue enforcing permission checks for POSIX clock operations
(settime, adjtime) in the POSIX layer. Only require WRITE access for
dynamic clocks adjtime() if any flags are set in the modes field.

[1] https://lists.nwtime.org/sympa/arc/linuxptp-users/2024-01/msg00036.html

Changes in v4:
- Require FMODE_WRITE in ajtime() only for calls modifying the clock in
  any way.

Acked-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Wojtek Wasko <wwasko@nvidia.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/ptp/ptp_chardev.c | 16 ++++++++++++++++
 kernel/time/posix-clock.c |  2 +-
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/ptp/ptp_chardev.c b/drivers/ptp/ptp_chardev.c
index bf6468c56419c..4380e6ddb8495 100644
--- a/drivers/ptp/ptp_chardev.c
+++ b/drivers/ptp/ptp_chardev.c
@@ -205,6 +205,10 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 
 	case PTP_EXTTS_REQUEST:
 	case PTP_EXTTS_REQUEST2:
+		if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) {
+			err = -EACCES;
+			break;
+		}
 		memset(&req, 0, sizeof(req));
 
 		if (copy_from_user(&req.extts, (void __user *)arg,
@@ -246,6 +250,10 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 
 	case PTP_PEROUT_REQUEST:
 	case PTP_PEROUT_REQUEST2:
+		if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) {
+			err = -EACCES;
+			break;
+		}
 		memset(&req, 0, sizeof(req));
 
 		if (copy_from_user(&req.perout, (void __user *)arg,
@@ -314,6 +322,10 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 
 	case PTP_ENABLE_PPS:
 	case PTP_ENABLE_PPS2:
+		if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) {
+			err = -EACCES;
+			break;
+		}
 		memset(&req, 0, sizeof(req));
 
 		if (!capable(CAP_SYS_TIME))
@@ -456,6 +468,10 @@ long ptp_ioctl(struct posix_clock_context *pccontext, unsigned int cmd,
 
 	case PTP_PIN_SETFUNC:
 	case PTP_PIN_SETFUNC2:
+		if ((pccontext->fp->f_mode & FMODE_WRITE) == 0) {
+			err = -EACCES;
+			break;
+		}
 		if (copy_from_user(&pd, (void __user *)arg, sizeof(pd))) {
 			err = -EFAULT;
 			break;
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index 4e114e34a6e0a..fe963384d5c2a 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -252,7 +252,7 @@ static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx)
 	if (err)
 		return err;
 
-	if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
+	if (tx->modes && (cd.fp->f_mode & FMODE_WRITE) == 0) {
 		err = -EACCES;
 		goto out;
 	}

From 76868642e42795353106197abf9c607ad80f4c9e Mon Sep 17 00:00:00 2001
From: Wojtek Wasko <wwasko@nvidia.com>
Date: Mon, 3 Mar 2025 18:13:45 +0200
Subject: [PATCH 1586/2753] testptp: Add option to open PHC in readonly mode

PTP Hardware Clocks no longer require WRITE permission to perform
readonly operations, such as listing device capabilities or listening to
EXTTS events once they have been enabled by a process with WRITE
permissions.

Add '-r' option to testptp to open the PHC in readonly mode instead of
the default read-write mode. Skip enabling EXTTS if readonly mode is
requested.

Acked-by: Richard Cochran <richardcochran@gmail.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Wojtek Wasko <wwasko@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/ptp/testptp.c | 37 +++++++++++++++++----------
 1 file changed, 23 insertions(+), 14 deletions(-)

diff --git a/tools/testing/selftests/ptp/testptp.c b/tools/testing/selftests/ptp/testptp.c
index 58064151f2c89..edc08a4433fd4 100644
--- a/tools/testing/selftests/ptp/testptp.c
+++ b/tools/testing/selftests/ptp/testptp.c
@@ -140,6 +140,7 @@ static void usage(char *progname)
 		" -H val     set output phase to 'val' nanoseconds (requires -p)\n"
 		" -w val     set output pulse width to 'val' nanoseconds (requires -p)\n"
 		" -P val     enable or disable (val=1|0) the system clock PPS\n"
+		" -r         open the ptp clock in readonly mode\n"
 		" -s         set the ptp clock time from the system time\n"
 		" -S         set the system time from the ptp clock time\n"
 		" -t val     shift the ptp clock time by 'val' seconds\n"
@@ -188,6 +189,7 @@ int main(int argc, char *argv[])
 	int pin_index = -1, pin_func;
 	int pps = -1;
 	int seconds = 0;
+	int readonly = 0;
 	int settime = 0;
 	int channel = -1;
 	clockid_t ext_clockid = CLOCK_REALTIME;
@@ -200,7 +202,7 @@ int main(int argc, char *argv[])
 
 	progname = strrchr(argv[0], '/');
 	progname = progname ? 1+progname : argv[0];
-	while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:sSt:T:w:x:Xy:z"))) {
+	while (EOF != (c = getopt(argc, argv, "cd:e:f:F:ghH:i:k:lL:n:o:p:P:rsSt:T:w:x:Xy:z"))) {
 		switch (c) {
 		case 'c':
 			capabilities = 1;
@@ -252,6 +254,9 @@ int main(int argc, char *argv[])
 		case 'P':
 			pps = atoi(optarg);
 			break;
+		case 'r':
+			readonly = 1;
+			break;
 		case 's':
 			settime = 1;
 			break;
@@ -308,7 +313,7 @@ int main(int argc, char *argv[])
 		}
 	}
 
-	fd = open(device, O_RDWR);
+	fd = open(device, readonly ? O_RDONLY : O_RDWR);
 	if (fd < 0) {
 		fprintf(stderr, "opening %s: %s\n", device, strerror(errno));
 		return -1;
@@ -436,14 +441,16 @@ int main(int argc, char *argv[])
 	}
 
 	if (extts) {
-		memset(&extts_request, 0, sizeof(extts_request));
-		extts_request.index = index;
-		extts_request.flags = PTP_ENABLE_FEATURE;
-		if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
-			perror("PTP_EXTTS_REQUEST");
-			extts = 0;
-		} else {
-			puts("external time stamp request okay");
+		if (!readonly) {
+			memset(&extts_request, 0, sizeof(extts_request));
+			extts_request.index = index;
+			extts_request.flags = PTP_ENABLE_FEATURE;
+			if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+				perror("PTP_EXTTS_REQUEST");
+				extts = 0;
+			} else {
+				puts("external time stamp request okay");
+			}
 		}
 		for (; extts; extts--) {
 			cnt = read(fd, &event, sizeof(event));
@@ -455,10 +462,12 @@ int main(int argc, char *argv[])
 			       event.t.sec, event.t.nsec);
 			fflush(stdout);
 		}
-		/* Disable the feature again. */
-		extts_request.flags = 0;
-		if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
-			perror("PTP_EXTTS_REQUEST");
+		if (!readonly) {
+			/* Disable the feature again. */
+			extts_request.flags = 0;
+			if (ioctl(fd, PTP_EXTTS_REQUEST, &extts_request)) {
+				perror("PTP_EXTTS_REQUEST");
+			}
 		}
 	}
 

From 6697f819a10b238ccf01998c3f203d65d8374696 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Fri, 22 Nov 2024 10:50:55 +0800
Subject: [PATCH 1587/2753] exfat: fix just enough dentries but allocate a new
 cluster to dir

This commit fixes the condition for allocating cluster to parent
directory to avoid allocating new cluster to parent directory when
there are just enough empty directory entries at the end of the
parent directory.

Fixes: af02c72d0b62 ("exfat: convert exfat_find_empty_entry() to use dentry cache")
Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 691dd77b6ab5f..5b16181a4c2e9 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -232,7 +232,7 @@ static int exfat_search_empty_slot(struct super_block *sb,
 		dentry = 0;
 	}
 
-	while (dentry + num_entries < total_entries &&
+	while (dentry + num_entries <= total_entries &&
 	       clu.dir != EXFAT_EOF_CLUSTER) {
 		i = dentry & (dentries_per_clu - 1);
 

From 9da33619e0ca53627641bc97d1b93ec741299111 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Fri, 31 Jan 2025 12:55:55 +0900
Subject: [PATCH 1588/2753] exfat: fix soft lockup in exfat_clear_bitmap

bitmap clear loop will take long time in __exfat_free_cluster()
if data size of file/dir enty is invalid.
If cluster bit in bitmap is already clear, stop clearing bitmap go to
out of loop.

Fixes: 31023864e67a ("exfat: add fat entry operations")
Reported-by: Kun Hu <huk23@m.fudan.edu.cn>, Jiaji Qin <jjtan24@m.fudan.edu.cn>
Reviewed-by: Sungjong Seo <sj1557.seo@samsung.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/balloc.c   | 10 ++++++++--
 fs/exfat/exfat_fs.h |  2 +-
 fs/exfat/fatent.c   | 11 +++++++----
 3 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/fs/exfat/balloc.c b/fs/exfat/balloc.c
index ce9be95c9172f..9ff825f1502d5 100644
--- a/fs/exfat/balloc.c
+++ b/fs/exfat/balloc.c
@@ -141,7 +141,7 @@ int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync)
 	return 0;
 }
 
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 {
 	int i, b;
 	unsigned int ent_idx;
@@ -150,13 +150,17 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 	struct exfat_mount_options *opts = &sbi->options;
 
 	if (!is_valid_cluster(sbi, clu))
-		return;
+		return -EIO;
 
 	ent_idx = CLUSTER_TO_BITMAP_ENT(clu);
 	i = BITMAP_OFFSET_SECTOR_INDEX(sb, ent_idx);
 	b = BITMAP_OFFSET_BIT_IN_SECTOR(sb, ent_idx);
 
+	if (!test_bit_le(b, sbi->vol_amap[i]->b_data))
+		return -EIO;
+
 	clear_bit_le(b, sbi->vol_amap[i]->b_data);
+
 	exfat_update_bh(sbi->vol_amap[i], sync);
 
 	if (opts->discard) {
@@ -171,6 +175,8 @@ void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync)
 			opts->discard = 0;
 		}
 	}
+
+	return 0;
 }
 
 /*
diff --git a/fs/exfat/exfat_fs.h b/fs/exfat/exfat_fs.h
index 78be6964a8a08..d30ce18a88b7a 100644
--- a/fs/exfat/exfat_fs.h
+++ b/fs/exfat/exfat_fs.h
@@ -456,7 +456,7 @@ int exfat_count_num_clusters(struct super_block *sb,
 int exfat_load_bitmap(struct super_block *sb);
 void exfat_free_bitmap(struct exfat_sb_info *sbi);
 int exfat_set_bitmap(struct inode *inode, unsigned int clu, bool sync);
-void exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
+int exfat_clear_bitmap(struct inode *inode, unsigned int clu, bool sync);
 unsigned int exfat_find_free_bitmap(struct super_block *sb, unsigned int clu);
 int exfat_count_used_clusters(struct super_block *sb, unsigned int *ret_count);
 int exfat_trim_fs(struct inode *inode, struct fstrim_range *range);
diff --git a/fs/exfat/fatent.c b/fs/exfat/fatent.c
index 9e5492ac409b0..6f3651c6ca91e 100644
--- a/fs/exfat/fatent.c
+++ b/fs/exfat/fatent.c
@@ -175,6 +175,7 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 		BITMAP_OFFSET_SECTOR_INDEX(sb, CLUSTER_TO_BITMAP_ENT(clu));
 
 	if (p_chain->flags == ALLOC_NO_FAT_CHAIN) {
+		int err;
 		unsigned int last_cluster = p_chain->dir + p_chain->size - 1;
 		do {
 			bool sync = false;
@@ -189,7 +190,9 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 				cur_cmap_i = next_cmap_i;
 			}
 
-			exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			err = exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			if (err)
+				break;
 			clu++;
 			num_clusters++;
 		} while (num_clusters < p_chain->size);
@@ -210,12 +213,13 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 				cur_cmap_i = next_cmap_i;
 			}
 
-			exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode)));
+			if (exfat_clear_bitmap(inode, clu, (sync && IS_DIRSYNC(inode))))
+				break;
 			clu = n_clu;
 			num_clusters++;
 
 			if (err)
-				goto dec_used_clus;
+				break;
 
 			if (num_clusters >= sbi->num_clusters - EXFAT_FIRST_CLUSTER) {
 				/*
@@ -229,7 +233,6 @@ static int __exfat_free_cluster(struct inode *inode, struct exfat_chain *p_chain
 		} while (clu != EXFAT_EOF_CLUSTER);
 	}
 
-dec_used_clus:
 	sbi->used_clusters -= num_clusters;
 	return 0;
 }

From fda94a9919fd632033979ad7765a99ae3cab9289 Mon Sep 17 00:00:00 2001
From: Eric Sandeen <sandeen@redhat.com>
Date: Tue, 11 Feb 2025 14:14:21 -0600
Subject: [PATCH 1589/2753] exfat: short-circuit zero-byte writes in
 exfat_file_write_iter

When generic_write_checks() returns zero, it means that
iov_iter_count() is zero, and there is no work to do.

Simply return success like all other filesystems do, rather than
proceeding down the write path, which today yields an -EFAULT in
generic_perform_write() via the
(fault_in_iov_iter_readable(i, bytes) == bytes) check when bytes
== 0.

Fixes: 11a347fb6cef ("exfat: change to get file size from DataLength")
Reported-by: Noah <kernel-org-10@maxgrass.eu>
Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Reviewed-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/file.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 05b51e7217838..807349d8ea050 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -587,7 +587,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	valid_size = ei->valid_size;
 
 	ret = generic_write_checks(iocb, iter);
-	if (ret < 0)
+	if (ret <= 0)
 		goto unlock;
 
 	if (iocb->ki_flags & IOCB_DIRECT) {

From 13940cef95491472760ca261b6713692ece9b946 Mon Sep 17 00:00:00 2001
From: Yuezhang Mo <Yuezhang.Mo@sony.com>
Date: Sat, 8 Feb 2025 17:16:58 +0800
Subject: [PATCH 1590/2753] exfat: add a check for invalid data size

Add a check for invalid data size to avoid corrupted filesystem
from being further corrupted.

Signed-off-by: Yuezhang Mo <Yuezhang.Mo@sony.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
---
 fs/exfat/namei.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/fs/exfat/namei.c b/fs/exfat/namei.c
index 5b16181a4c2e9..8b30027d82512 100644
--- a/fs/exfat/namei.c
+++ b/fs/exfat/namei.c
@@ -646,6 +646,11 @@ static int exfat_find(struct inode *dir, struct qstr *qname,
 	info->valid_size = le64_to_cpu(ep2->dentry.stream.valid_size);
 	info->size = le64_to_cpu(ep2->dentry.stream.size);
 
+	if (unlikely(EXFAT_B_TO_CLU_ROUND_UP(info->size, sbi) > sbi->used_clusters)) {
+		exfat_fs_error(sb, "data size is invalid(%lld)", info->size);
+		return -EIO;
+	}
+
 	info->start_clu = le32_to_cpu(ep2->dentry.stream.start_clu);
 	if (!is_valid_cluster(sbi, info->start_clu) && info->size) {
 		exfat_warn(sb, "start_clu is invalid cluster(0x%x)",

From 3c9231ea6497dfc50ac0ef69fff484da27d0df66 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Tue, 4 Mar 2025 08:44:29 +0800
Subject: [PATCH 1591/2753] net-timestamp: support TCP GSO case for a few
 missing flags

When I read through the TSO codes, I found out that we probably
miss initializing the tx_flags of last seg when TSO is turned
off, which means at the following points no more timestamp
(for this last one) will be generated. There are three flags
to be handled in this patch:
1. SKBTX_HW_TSTAMP
2. SKBTX_BPF
3. SKBTX_SCHED_TSTAMP
Note that SKBTX_BPF[1] was added in 6.14.0-rc2 by commit
6b98ec7e882af ("bpf: Add BPF_SOCK_OPS_TSTAMP_SCHED_CB callback")
and only belongs to net-next branch material for now. The common
issue of the above three flags can be fixed by this single patch.

This patch initializes the tx_flags to SKBTX_ANY_TSTAMP like what
the UDP GSO does to make the newly segmented last skb inherit the
tx_flags so that requested timestamp will be generated in each
certain layer, or else that last one has zero value of tx_flags
which leads to no timestamp at all.

Fixes: 4ed2d765dfacc ("net-timestamp: TCP timestamping")
Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 2308665b51c53..2dfac79dc78b8 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -13,12 +13,15 @@
 #include <net/tcp.h>
 #include <net/protocol.h>
 
-static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
+static void tcp_gso_tstamp(struct sk_buff *skb, struct sk_buff *gso_skb,
 			   unsigned int seq, unsigned int mss)
 {
+	u32 flags = skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP;
+	u32 ts_seq = skb_shinfo(gso_skb)->tskey;
+
 	while (skb) {
 		if (before(ts_seq, seq + mss)) {
-			skb_shinfo(skb)->tx_flags |= SKBTX_SW_TSTAMP;
+			skb_shinfo(skb)->tx_flags |= flags;
 			skb_shinfo(skb)->tskey = ts_seq;
 			return;
 		}
@@ -193,8 +196,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	th = tcp_hdr(skb);
 	seq = ntohl(th->seq);
 
-	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_SW_TSTAMP))
-		tcp_gso_tstamp(segs, skb_shinfo(gso_skb)->tskey, seq, mss);
+	if (unlikely(skb_shinfo(gso_skb)->tx_flags & SKBTX_ANY_TSTAMP))
+		tcp_gso_tstamp(segs, gso_skb, seq, mss);
 
 	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 

From 927e6bec5cf3624665b0a2e9f64a1d32f3d22cdd Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Wed, 5 Mar 2025 21:41:13 +0800
Subject: [PATCH 1592/2753] ASoC: rt1320: set wake_capable = 0 explicitly
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

"generic_new_peripheral_assigned: invalid dev_num 1, wake supported 1"
is reported by our internal CI test.

Rt1320's wake feature is not used in Linux and that's why it is not in
the wake_capable_list[] list in intel_auxdevice.c.
However, BIOS may set it as wake-capable. Overwrite wake_capable to 0
in the codec driver to align with wake_capable_list[].

Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Péter Ujfalusi <peter.ujfalusi@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Acked-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20250305134113.201326-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt1320-sdw.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/sound/soc/codecs/rt1320-sdw.c b/sound/soc/codecs/rt1320-sdw.c
index 3510c3819074b..d83b236a04503 100644
--- a/sound/soc/codecs/rt1320-sdw.c
+++ b/sound/soc/codecs/rt1320-sdw.c
@@ -535,6 +535,9 @@ static int rt1320_read_prop(struct sdw_slave *slave)
 	/* set the timeout values */
 	prop->clk_stop_timeout = 64;
 
+	/* BIOS may set wake_capable. Make sure it is 0 as wake events are disabled. */
+	prop->wake_capable = 0;
+
 	return 0;
 }
 

From 5ac60242b0173be83709603ebaf27a473f16c4e4 Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Tue, 4 Mar 2025 14:34:26 -0700
Subject: [PATCH 1593/2753] ublk: set_params: properly check if parameters can
 be applied

The parameters set by the set_params call are only applied to the block
device in the start_dev call. So if a device has already been started, a
subsequently issued set_params on that device will not have the desired
effect, and should return an error. There is an existing check for this
- set_params fails on devices in the LIVE state. But this check is not
sufficient to cover the recovery case. In this case, the device will be
in the QUIESCED or FAIL_IO states, so set_params will succeed. But this
success is misleading, because the parameters will not be applied, since
the device has already been started (by a previous ublk server). The bit
UB_STATE_USED is set on completion of the start_dev; use it to detect
and fail set_params commands which arrive too late to be applied (after
start_dev).

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Fixes: 0aa73170eba5 ("ublk_drv: add SET_PARAMS/GET_PARAMS control command")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250304-set_params-v1-1-17b5e0887606@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/ublk_drv.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
index 529085181f355..ca9a67b5b537a 100644
--- a/drivers/block/ublk_drv.c
+++ b/drivers/block/ublk_drv.c
@@ -2715,9 +2715,12 @@ static int ublk_ctrl_set_params(struct ublk_device *ub,
 	if (ph.len > sizeof(struct ublk_params))
 		ph.len = sizeof(struct ublk_params);
 
-	/* parameters can only be changed when device isn't live */
 	mutex_lock(&ub->mutex);
-	if (ub->dev_info.state == UBLK_S_DEV_LIVE) {
+	if (test_bit(UB_STATE_USED, &ub->state)) {
+		/*
+		 * Parameters can only be changed when device hasn't
+		 * been started yet
+		 */
 		ret = -EACCES;
 	} else if (copy_from_user(&ub->params, argp, ph.len)) {
 		ret = -EFAULT;

From e06472bab2a5393430cc2fbc3211cd3602422c1e Mon Sep 17 00:00:00 2001
From: Olivier Gayot <olivier.gayot@canonical.com>
Date: Wed, 5 Mar 2025 10:21:54 +0800
Subject: [PATCH 1594/2753] block: fix conversion of GPT partition name to
 7-bit
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The utf16_le_to_7bit function claims to, naively, convert a UTF-16
string to a 7-bit ASCII string. By naively, we mean that it:
 * drops the first byte of every character in the original UTF-16 string
 * checks if all characters are printable, and otherwise replaces them
   by exclamation mark "!".

This means that theoretically, all characters outside the 7-bit ASCII
range should be replaced by another character. Examples:

 * lower-case alpha (ɒ) 0x0252 becomes 0x52 (R)
 * ligature OE (œ) 0x0153 becomes 0x53 (S)
 * hangul letter pieup (ㅂ) 0x3142 becomes 0x42 (B)
 * upper-case gamma (Ɣ) 0x0194 becomes 0x94 (not printable) so gets
   replaced by "!"

The result of this conversion for the GPT partition name is passed to
user-space as PARTNAME via udev, which is confusing and feels questionable.

However, there is a flaw in the conversion function itself. By dropping
one byte of each character and using isprint() to check if the remaining
byte corresponds to a printable character, we do not actually guarantee
that the resulting character is 7-bit ASCII.

This happens because we pass 8-bit characters to isprint(), which
in the kernel returns 1 for many values > 0x7f - as defined in ctype.c.

This results in many values which should be replaced by "!" to be kept
as-is, despite not being valid 7-bit ASCII. Examples:

 * e with acute accent (é) 0x00E9 becomes 0xE9 - kept as-is because
   isprint(0xE9) returns 1.
 * euro sign (€) 0x20AC becomes 0xAC - kept as-is because isprint(0xAC)
   returns 1.

This way has broken pyudev utility[1], fixes it by using a mask of 7 bits
instead of 8 bits before calling isprint.

Link: https://github.com/pyudev/pyudev/issues/490#issuecomment-2685794648 [1]
Link: https://lore.kernel.org/linux-block/4cac90c2-e414-4ebb-ae62-2a4589d9dc6e@canonical.com/
Cc: Mulhern <amulhern@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: stable@vger.kernel.org
Signed-off-by: Olivier Gayot <olivier.gayot@canonical.com>
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20250305022154.3903128-1-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/partitions/efi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/partitions/efi.c b/block/partitions/efi.c
index 5e9be13a56a82..7acba66eed481 100644
--- a/block/partitions/efi.c
+++ b/block/partitions/efi.c
@@ -682,7 +682,7 @@ static void utf16_le_to_7bit(const __le16 *in, unsigned int size, u8 *out)
 	out[size] = 0;
 
 	while (i < size) {
-		u8 c = le16_to_cpu(in[i]) & 0xff;
+		u8 c = le16_to_cpu(in[i]) & 0x7f;
 
 		if (c && !isprint(c))
 			c = '!';

From ef17b519088ee0c167cf507820609732ec8bad1a Mon Sep 17 00:00:00 2001
From: Xianwei Zhao <xianwei.zhao@amlogic.com>
Date: Mon, 3 Mar 2025 17:06:05 +0800
Subject: [PATCH 1595/2753] pmdomain: amlogic: fix T7 ISP secpower

ISP and MIPI_ISP, these two have a parent-child relationship,
ISP depends on MIPI_ISP.

Fixes: ca75e4b214c6 ("pmdomain: amlogic: Add support for T7 power domains controller")
Signed-off-by: Xianwei Zhao <xianwei.zhao@amlogic.com>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250303-fix-t7-pwrc-v1-1-b563612bcd86@amlogic.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/amlogic/meson-secure-pwrc.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/pmdomain/amlogic/meson-secure-pwrc.c b/drivers/pmdomain/amlogic/meson-secure-pwrc.c
index 42ce41a2fe3a0..ff76ea36835e5 100644
--- a/drivers/pmdomain/amlogic/meson-secure-pwrc.c
+++ b/drivers/pmdomain/amlogic/meson-secure-pwrc.c
@@ -221,7 +221,7 @@ static const struct meson_secure_pwrc_domain_desc t7_pwrc_domains[] = {
 	SEC_PD(T7_VI_CLK2,	0),
 	/* ETH is for ethernet online wakeup, and should be always on */
 	SEC_PD(T7_ETH,		GENPD_FLAG_ALWAYS_ON),
-	SEC_PD(T7_ISP,		0),
+	TOP_PD(T7_ISP,		0, PWRC_T7_MIPI_ISP_ID),
 	SEC_PD(T7_MIPI_ISP,	0),
 	TOP_PD(T7_GDC,		0, PWRC_T7_NIC3_ID),
 	TOP_PD(T7_DEWARP,	0, PWRC_T7_NIC3_ID),

From 3be83ee9de0298f8321aa0b148d8f9995102e40f Mon Sep 17 00:00:00 2001
From: Larysa Zaremba <larysa.zaremba@intel.com>
Date: Mon, 9 Dec 2024 15:08:53 +0100
Subject: [PATCH 1596/2753] ice: do not configure destination override for
 switchdev

After switchdev is enabled and disabled later, LLDP packets sending stops,
despite working perfectly fine before and during switchdev state.
To reproduce (creating/destroying VF is what triggers the reconfiguration):

devlink dev eswitch set pci/<address> mode switchdev
echo '2' > /sys/class/net/<ifname>/device/sriov_numvfs
echo '0' > /sys/class/net/<ifname>/device/sriov_numvfs

This happens because LLDP relies on the destination override functionality.
It needs to 1) set a flag in the descriptor, 2) set the VSI permission to
make it valid. The permissions are set when the PF VSI is first configured,
but switchdev then enables it for the uplink VSI (which is always the PF)
once more when configured and disables when deconfigured, which leads to
software-generated LLDP packets being blocked.

Do not modify the destination override permissions when configuring
switchdev, as the enabled state is the default configuration that is never
modified.

Fixes: 1a1c40df2e80 ("ice: set and release switchdev environment")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Larysa Zaremba <larysa.zaremba@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_eswitch.c |  6 ------
 drivers/net/ethernet/intel/ice/ice_lib.c     | 18 ------------------
 drivers/net/ethernet/intel/ice/ice_lib.h     |  4 ----
 3 files changed, 28 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_eswitch.c b/drivers/net/ethernet/intel/ice/ice_eswitch.c
index d649c197cf673..ed21d7f55ac11 100644
--- a/drivers/net/ethernet/intel/ice/ice_eswitch.c
+++ b/drivers/net/ethernet/intel/ice/ice_eswitch.c
@@ -49,9 +49,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 	if (vlan_ops->dis_rx_filtering(uplink_vsi))
 		goto err_vlan_filtering;
 
-	if (ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_set_allow_override))
-		goto err_override_uplink;
-
 	if (ice_vsi_update_local_lb(uplink_vsi, true))
 		goto err_override_local_lb;
 
@@ -63,8 +60,6 @@ static int ice_eswitch_setup_env(struct ice_pf *pf)
 err_up:
 	ice_vsi_update_local_lb(uplink_vsi, false);
 err_override_local_lb:
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
-err_override_uplink:
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 err_vlan_filtering:
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
@@ -275,7 +270,6 @@ static void ice_eswitch_release_env(struct ice_pf *pf)
 	vlan_ops = ice_get_compat_vsi_vlan_ops(uplink_vsi);
 
 	ice_vsi_update_local_lb(uplink_vsi, false);
-	ice_vsi_update_security(uplink_vsi, ice_vsi_ctx_clear_allow_override);
 	vlan_ops->ena_rx_filtering(uplink_vsi);
 	ice_cfg_dflt_vsi(uplink_vsi->port_info, uplink_vsi->idx, false,
 			 ICE_FLTR_TX);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 38a1c8372180b..d0faa087793da 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3936,24 +3936,6 @@ void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx)
 				 ICE_AQ_VSI_SEC_TX_PRUNE_ENA_S);
 }
 
-/**
- * ice_vsi_ctx_set_allow_override - allow destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
-/**
- * ice_vsi_ctx_clear_allow_override - turn off destination override on VSI
- * @ctx: pointer to VSI ctx structure
- */
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx)
-{
-	ctx->info.sec_flags &= ~ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD;
-}
-
 /**
  * ice_vsi_update_local_lb - update sw block in VSI with local loopback bit
  * @vsi: pointer to VSI structure
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
index eabb35834a245..b4c9cb28a016e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.h
+++ b/drivers/net/ethernet/intel/ice/ice_lib.h
@@ -105,10 +105,6 @@ ice_vsi_update_security(struct ice_vsi *vsi, void (*fill)(struct ice_vsi_ctx *))
 void ice_vsi_ctx_set_antispoof(struct ice_vsi_ctx *ctx);
 
 void ice_vsi_ctx_clear_antispoof(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_set_allow_override(struct ice_vsi_ctx *ctx);
-
-void ice_vsi_ctx_clear_allow_override(struct ice_vsi_ctx *ctx);
 int ice_vsi_update_local_lb(struct ice_vsi *vsi, bool set);
 int ice_vsi_add_vlan_zero(struct ice_vsi *vsi);
 int ice_vsi_del_vlan_zero(struct ice_vsi *vsi);

From 3b4035ddbfc8e4521f85569998a7569668cccf51 Mon Sep 17 00:00:00 2001
From: Zecheng Li <zecheng@google.com>
Date: Tue, 4 Mar 2025 21:40:31 +0000
Subject: [PATCH 1597/2753] sched/fair: Fix potential memory corruption in
 child_cfs_rq_on_list

child_cfs_rq_on_list attempts to convert a 'prev' pointer to a cfs_rq.
This 'prev' pointer can originate from struct rq's leaf_cfs_rq_list,
making the conversion invalid and potentially leading to memory
corruption. Depending on the relative positions of leaf_cfs_rq_list and
the task group (tg) pointer within the struct, this can cause a memory
fault or access garbage data.

The issue arises in list_add_leaf_cfs_rq, where both
cfs_rq->leaf_cfs_rq_list and rq->leaf_cfs_rq_list are added to the same
leaf list. Also, rq->tmp_alone_branch can be set to rq->leaf_cfs_rq_list.

This adds a check `if (prev == &rq->leaf_cfs_rq_list)` after the main
conditional in child_cfs_rq_on_list. This ensures that the container_of
operation will convert a correct cfs_rq struct.

This check is sufficient because only cfs_rqs on the same CPU are added
to the list, so verifying the 'prev' pointer against the current rq's list
head is enough.

Fixes a potential memory corruption issue that due to current struct
layout might not be manifesting as a crash but could lead to unpredictable
behavior when the layout changes.

Fixes: fdaba61ef8a2 ("sched/fair: Ensure that the CFS parent is added after unthrottling")
Signed-off-by: Zecheng Li <zecheng@google.com>
Reviewed-and-tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250304214031.2882646-1-zecheng@google.com
---
 kernel/sched/fair.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1c0ef435a7aae..c798d27952431 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4045,15 +4045,17 @@ static inline bool child_cfs_rq_on_list(struct cfs_rq *cfs_rq)
 {
 	struct cfs_rq *prev_cfs_rq;
 	struct list_head *prev;
+	struct rq *rq = rq_of(cfs_rq);
 
 	if (cfs_rq->on_list) {
 		prev = cfs_rq->leaf_cfs_rq_list.prev;
 	} else {
-		struct rq *rq = rq_of(cfs_rq);
-
 		prev = rq->tmp_alone_branch;
 	}
 
+	if (prev == &rq->leaf_cfs_rq_list)
+		return false;
+
 	prev_cfs_rq = container_of(prev, struct cfs_rq, leaf_cfs_rq_list);
 
 	return (prev_cfs_rq->tg->parent == cfs_rq->tg);

From 23d97f18901ef5e4e264e3b1777fe65c760186b5 Mon Sep 17 00:00:00 2001
From: Grzegorz Nitka <grzegorz.nitka@intel.com>
Date: Thu, 23 Jan 2025 09:15:39 +0100
Subject: [PATCH 1598/2753] ice: fix memory leak in aRFS after reset

Fix aRFS (accelerated Receive Flow Steering) structures memory leak by
adding a checker to verify if aRFS memory is already allocated while
configuring VSI. aRFS objects are allocated in two cases:
- as part of VSI initialization (at probe), and
- as part of reset handling

However, VSI reconfiguration executed during reset involves memory
allocation one more time, without prior releasing already allocated
resources. This led to the memory leak with the following signature:

[root@os-delivery ~]# cat /sys/kernel/debug/kmemleak
unreferenced object 0xff3c1ca7252e6000 (size 8192):
  comm "kworker/0:0", pid 8, jiffies 4296833052
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 0):
    [<ffffffff991ec485>] __kmalloc_cache_noprof+0x275/0x340
    [<ffffffffc0a6e06a>] ice_init_arfs+0x3a/0xe0 [ice]
    [<ffffffffc09f1027>] ice_vsi_cfg_def+0x607/0x850 [ice]
    [<ffffffffc09f244b>] ice_vsi_setup+0x5b/0x130 [ice]
    [<ffffffffc09c2131>] ice_init+0x1c1/0x460 [ice]
    [<ffffffffc09c64af>] ice_probe+0x2af/0x520 [ice]
    [<ffffffff994fbcd3>] local_pci_probe+0x43/0xa0
    [<ffffffff98f07103>] work_for_cpu_fn+0x13/0x20
    [<ffffffff98f0b6d9>] process_one_work+0x179/0x390
    [<ffffffff98f0c1e9>] worker_thread+0x239/0x340
    [<ffffffff98f14abc>] kthread+0xcc/0x100
    [<ffffffff98e45a6d>] ret_from_fork+0x2d/0x50
    [<ffffffff98e083ba>] ret_from_fork_asm+0x1a/0x30
    ...

Fixes: 28bf26724fdb ("ice: Implement aRFS")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_arfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_arfs.c b/drivers/net/ethernet/intel/ice/ice_arfs.c
index 7cee365cc7d16..405ddd17de1bf 100644
--- a/drivers/net/ethernet/intel/ice/ice_arfs.c
+++ b/drivers/net/ethernet/intel/ice/ice_arfs.c
@@ -511,7 +511,7 @@ void ice_init_arfs(struct ice_vsi *vsi)
 	struct hlist_head *arfs_fltr_list;
 	unsigned int i;
 
-	if (!vsi || vsi->type != ICE_VSI_PF)
+	if (!vsi || vsi->type != ICE_VSI_PF || ice_is_arfs_active(vsi))
 		return;
 
 	arfs_fltr_list = kcalloc(ICE_MAX_ARFS_LIST, sizeof(*arfs_fltr_list),

From dce97cb0a3e34204c0b99345418a714eac85953f Mon Sep 17 00:00:00 2001
From: Marcin Szycik <marcin.szycik@linux.intel.com>
Date: Thu, 2 Jan 2025 20:07:52 +0100
Subject: [PATCH 1599/2753] ice: Fix switchdev slow-path in LAG

Ever since removing switchdev control VSI and using PF for port
representor Tx/Rx, switchdev slow-path has been working improperly after
failover in SR-IOV LAG. LAG assumes that the first uplink to be added to
the aggregate will own VFs and have switchdev configured. After
failing-over to the other uplink, representors are still configured to
Tx through the uplink they are set up on, which fails because that
uplink is now down.

On failover, update all PRs on primary uplink to use the currently
active uplink for Tx. Call netif_keep_dst(), as the secondary uplink
might not be in switchdev mode. Also make sure to call
ice_eswitch_set_target_vsi() if uplink is in LAG.

On the Rx path, representors are already working properly, because
default Tx from VFs is set to PF owning the eswitch. After failover the
same PF is receiving traffic from VFs, even though link is down.

Fixes: defd52455aee ("ice: do Tx through PF netdev in slow-path")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Marcin Szycik <marcin.szycik@linux.intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Tested-by: Sujai Buvaneswaran <sujai.buvaneswaran@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_lag.c  | 27 +++++++++++++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.c |  4 +++-
 2 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index 1ccb572ce285d..22371011c2492 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1000,6 +1000,28 @@ static void ice_lag_link(struct ice_lag *lag)
 	netdev_info(lag->netdev, "Shared SR-IOV resources in bond are active\n");
 }
 
+/**
+ * ice_lag_config_eswitch - configure eswitch to work with LAG
+ * @lag: lag info struct
+ * @netdev: active network interface device struct
+ *
+ * Updates all port representors in eswitch to use @netdev for Tx.
+ *
+ * Configures the netdev to keep dst metadata (also used in representor Tx).
+ * This is required for an uplink without switchdev mode configured.
+ */
+static void ice_lag_config_eswitch(struct ice_lag *lag,
+				   struct net_device *netdev)
+{
+	struct ice_repr *repr;
+	unsigned long id;
+
+	xa_for_each(&lag->pf->eswitch.reprs, id, repr)
+		repr->dst->u.port_info.lower_dev = netdev;
+
+	netif_keep_dst(netdev);
+}
+
 /**
  * ice_lag_unlink - handle unlink event
  * @lag: LAG info struct
@@ -1021,6 +1043,9 @@ static void ice_lag_unlink(struct ice_lag *lag)
 			ice_lag_move_vf_nodes(lag, act_port, pri_port);
 		lag->primary = false;
 		lag->active_port = ICE_LAG_INVALID_PORT;
+
+		/* Config primary's eswitch back to normal operation. */
+		ice_lag_config_eswitch(lag, lag->netdev);
 	} else {
 		struct ice_lag *primary_lag;
 
@@ -1419,6 +1444,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 				ice_lag_move_vf_nodes(lag, prim_port,
 						      event_port);
 			lag->active_port = event_port;
+			ice_lag_config_eswitch(lag, event_netdev);
 			return;
 		}
 
@@ -1428,6 +1454,7 @@ static void ice_lag_monitor_active(struct ice_lag *lag, void *ptr)
 		/* new active port */
 		ice_lag_move_vf_nodes(lag, lag->active_port, event_port);
 		lag->active_port = event_port;
+		ice_lag_config_eswitch(lag, event_netdev);
 	} else {
 		/* port not set as currently active (e.g. new active port
 		 * has already claimed the nodes and filters
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 9c9ea4c1b93b7..380ba1e8b3b2c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -2424,7 +2424,9 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 					ICE_TXD_CTX_QW1_CMD_S);
 
 	ice_tstamp(tx_ring, skb, first, &offload);
-	if (ice_is_switchdev_running(vsi->back) && vsi->type != ICE_VSI_SF)
+	if ((ice_is_switchdev_running(vsi->back) ||
+	     ice_lag_is_switchdev_running(vsi->back)) &&
+	    vsi->type != ICE_VSI_SF)
 		ice_eswitch_set_target_vsi(skb, &offload);
 
 	if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) {

From 374c9faac5a763a05bc3f68ad9f73dab3c6aec90 Mon Sep 17 00:00:00 2001
From: Ma Ke <make24@iscas.ac.cn>
Date: Wed, 26 Feb 2025 16:37:31 +0800
Subject: [PATCH 1600/2753] drm/amd/display: Fix null check for
 pipe_ctx->plane_state in resource_build_scaling_params

Null pointer dereference issue could occur when pipe_ctx->plane_state
is null. The fix adds a check to ensure 'pipe_ctx->plane_state' is not
null before accessing. This prevents a null pointer dereference.

Found by code review.

Fixes: 3be5262e353b ("drm/amd/display: Rename more dc_surface stuff to plane_state")
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Ma Ke <make24@iscas.ac.cn>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 63e6a77ccf239337baa9b1e7787cde9fa0462092)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index 520a34a42827b..a45037cb4cc01 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -1455,7 +1455,8 @@ bool resource_build_scaling_params(struct pipe_ctx *pipe_ctx)
 	DC_LOGGER_INIT(pipe_ctx->stream->ctx->logger);
 
 	/* Invalid input */
-	if (!plane_state->dst_rect.width ||
+	if (!plane_state ||
+			!plane_state->dst_rect.width ||
 			!plane_state->dst_rect.height ||
 			!plane_state->src_rect.width ||
 			!plane_state->src_rect.height) {

From 2a3e89a14864090ee4804fcec655ffc15fabf45c Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Wed, 19 Feb 2025 14:30:39 +0100
Subject: [PATCH 1601/2753] ice: register devlink prior to creating health
 reporters

ice_health_init() was introduced in the commit 2a82874a3b7b ("ice: add
Tx hang devlink health reporter"). The call to it should have been put
after ice_devlink_register(). It went unnoticed until next reporter by
Konrad, which receives events from FW. FW is reporting all events, also
from prior driver load, and thus it is not unlikely to have something
at the very beginning. And that results in a splat:
[   24.455950]  ? devlink_recover_notify.constprop.0+0x198/0x1b0
[   24.455973]  devlink_health_report+0x5d/0x2a0
[   24.455976]  ? __pfx_ice_health_status_lookup_compare+0x10/0x10 [ice]
[   24.456044]  ice_process_health_status_event+0x1b7/0x200 [ice]

Do the analogous thing for deinit patch.

Fixes: 85d6164ec56d ("ice: add fw and port health reporters")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Konrad Knitter <konrad.knitter@intel.com>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Tested-by: Sunitha Mekala <sunithax.d.mekala@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index c3a0fb97c5ee4..e13bd5a6cb6c4 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -5065,16 +5065,16 @@ static int ice_init_devlink(struct ice_pf *pf)
 		return err;
 
 	ice_devlink_init_regions(pf);
-	ice_health_init(pf);
 	ice_devlink_register(pf);
+	ice_health_init(pf);
 
 	return 0;
 }
 
 static void ice_deinit_devlink(struct ice_pf *pf)
 {
-	ice_devlink_unregister(pf);
 	ice_health_deinit(pf);
+	ice_devlink_unregister(pf);
 	ice_devlink_destroy_regions(pf);
 	ice_devlink_unregister_params(pf);
 }

From fd617ea3b79d2116d53f76cdb5a3601c0ba6e42f Mon Sep 17 00:00:00 2001
From: Andrew Martin <Andrew.Martin@amd.com>
Date: Fri, 28 Feb 2025 11:26:48 -0500
Subject: [PATCH 1602/2753] drm/amdkfd: Fix NULL Pointer Dereference in KFD
 queue

Through KFD IOCTL Fuzzing we encountered a NULL pointer derefrence
when calling kfd_queue_acquire_buffers.

Fixes: 629568d25fea ("drm/amdkfd: Validate queue cwsr area and eop buffer size")
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Reviewed-by: Philip Yang <Philip.Yang@amd.com>
Signed-off-by: Andrew Martin <Andrew.Martin@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 049e5bf3c8406f87c3d8e1958e0a16804fa1d530)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_queue.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
index ecccd7adbab4d..24396a2c77bd0 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_queue.c
@@ -266,8 +266,8 @@ int kfd_queue_acquire_buffers(struct kfd_process_device *pdd, struct queue_prope
 	/* EOP buffer is not required for all ASICs */
 	if (properties->eop_ring_buffer_address) {
 		if (properties->eop_ring_buffer_size != topo_dev->node_props.eop_buffer_size) {
-			pr_debug("queue eop bo size 0x%lx not equal to node eop buf size 0x%x\n",
-				properties->eop_buf_bo->tbo.base.size,
+			pr_debug("queue eop bo size 0x%x not equal to node eop buf size 0x%x\n",
+				properties->eop_ring_buffer_size,
 				topo_dev->node_props.eop_buffer_size);
 			err = -EINVAL;
 			goto out_err_unreserve;

From c27c66afc449b80f3b4b84d123358c0248f2cf63 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Mar 2025 07:08:09 -1000
Subject: [PATCH 1603/2753] fs/pipe: Fix pipe_occupancy() with 16-bit indexes

The pipe_occupancy() logic implicitly relied on the natural unsigned
modulo arithmetic in C, but that doesn't work for the new 'pipe_index_t'
case, since any arithmetic will be done in 'int' (and here we had also
made it 'unsigned int' due to the function call boundary).

So make the modulo arithmetic explicit by casting the result to the
proper type.

Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Manfred Spraul <manfred@colorfullife.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Cc: Alexey Gladkov <legion@kernel.org>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/all/CAHk-=wjyHsGLx=rxg6PKYBNkPYAejgo7=CbyL3=HGLZLsAaJFQ@mail.gmail.com/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 3cc4f8eab853f..1f013ed7577ef 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -192,7 +192,7 @@ static inline bool pipe_empty(unsigned int head, unsigned int tail)
  */
 static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
 {
-	return head - tail;
+	return (pipe_index_t)(head - tail);
 }
 
 /**

From cfced12f5100e50d56bc587299393fd33c1169a9 Mon Sep 17 00:00:00 2001
From: K Prateek Nayak <kprateek.nayak@amd.com>
Date: Wed, 5 Mar 2025 11:23:01 +0000
Subject: [PATCH 1604/2753] include/linux/pipe_fs_i: Add htmldoc annotation for
 "head_tail" member

Add htmldoc annotation for the newly introduced "head_tail" member
describing it to be a union of the pipe_inode_info's @head and @tail
members.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/lkml/20250305204609.5e64768e@canb.auug.org.au/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")
Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 1 +
 1 file changed, 1 insertion(+)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 1f013ed7577ef..05ccbc5d01294 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -65,6 +65,7 @@ union pipe_index {
  *	@wr_wait: writer wait point in case of full pipe
  *	@head: The point of buffer production
  *	@tail: The point of buffer consumption
+ *	@head_tail: unsigned long union of @head and @tail
  *	@note_loss: The next read() should insert a data-lost message
  *	@max_usage: The maximum number of slots that may be used in the ring
  *	@ring_size: total number of buffers (should be a power of 2)

From 0eba2a7e858907a746ba69cd002eb9eb4dbd7bf3 Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Fri, 28 Feb 2025 15:14:56 +0000
Subject: [PATCH 1605/2753] ASoC: ops: Consistently treat platform_max as
 control value

This reverts commit 9bdd10d57a88 ("ASoC: ops: Shift tested values in
snd_soc_put_volsw() by +min"), and makes some additional related
updates.

There are two ways the platform_max could be interpreted; the maximum
register value, or the maximum value the control can be set to. The
patch moved from treating the value as a control value to a register
one. When the patch was applied it was technically correct as
snd_soc_limit_volume() also used the register interpretation. However,
even then most of the other usages treated platform_max as a
control value, and snd_soc_limit_volume() has since been updated to
also do so in commit fb9ad24485087 ("ASoC: ops: add correct range
check for limiting volume"). That patch however, missed updating
snd_soc_put_volsw() back to the control interpretation, and fixing
snd_soc_info_volsw_range(). The control interpretation makes more
sense as limiting is typically done from the machine driver, so it is
appropriate to use the customer facing representation rather than the
internal codec representation. Update all the code to consistently use
this interpretation of platform_max.

Finally, also add some comments to the soc_mixer_control struct to
hopefully avoid further patches switching between the two approaches.

Fixes: fb9ad24485087 ("ASoC: ops: add correct range check for limiting volume")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250228151456.3703342-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/sound/soc.h |  5 ++++-
 sound/soc/soc-ops.c | 15 +++++++--------
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/include/sound/soc.h b/include/sound/soc.h
index fcdb5adfcd5ec..b3e84bc47c6fd 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -1261,7 +1261,10 @@ void snd_soc_close_delayed_work(struct snd_soc_pcm_runtime *rtd);
 
 /* mixer control */
 struct soc_mixer_control {
-	int min, max, platform_max;
+	/* Minimum and maximum specified as written to the hardware */
+	int min, max;
+	/* Limited maximum value specified as presented through the control */
+	int platform_max;
 	int reg, rreg;
 	unsigned int shift, rshift;
 	unsigned int sign_bit;
diff --git a/sound/soc/soc-ops.c b/sound/soc/soc-ops.c
index 19928f098d8dc..b0e4e4168f38d 100644
--- a/sound/soc/soc-ops.c
+++ b/sound/soc/soc-ops.c
@@ -337,7 +337,7 @@ int snd_soc_put_volsw(struct snd_kcontrol *kcontrol,
 	if (ucontrol->value.integer.value[0] < 0)
 		return -EINVAL;
 	val = ucontrol->value.integer.value[0];
-	if (mc->platform_max && ((int)val + min) > mc->platform_max)
+	if (mc->platform_max && val > mc->platform_max)
 		return -EINVAL;
 	if (val > max - min)
 		return -EINVAL;
@@ -350,7 +350,7 @@ int snd_soc_put_volsw(struct snd_kcontrol *kcontrol,
 		if (ucontrol->value.integer.value[1] < 0)
 			return -EINVAL;
 		val2 = ucontrol->value.integer.value[1];
-		if (mc->platform_max && ((int)val2 + min) > mc->platform_max)
+		if (mc->platform_max && val2 > mc->platform_max)
 			return -EINVAL;
 		if (val2 > max - min)
 			return -EINVAL;
@@ -503,17 +503,16 @@ int snd_soc_info_volsw_range(struct snd_kcontrol *kcontrol,
 {
 	struct soc_mixer_control *mc =
 		(struct soc_mixer_control *)kcontrol->private_value;
-	int platform_max;
-	int min = mc->min;
+	int max;
 
-	if (!mc->platform_max)
-		mc->platform_max = mc->max;
-	platform_max = mc->platform_max;
+	max = mc->max - mc->min;
+	if (mc->platform_max && mc->platform_max < max)
+		max = mc->platform_max;
 
 	uinfo->type = SNDRV_CTL_ELEM_TYPE_INTEGER;
 	uinfo->count = snd_soc_volsw_is_stereo(mc) ? 2 : 1;
 	uinfo->value.integer.min = 0;
-	uinfo->value.integer.max = platform_max - min;
+	uinfo->value.integer.max = max;
 
 	return 0;
 }

From 29ffeb73b216ce3eff10229eb077cf9b7812119d Mon Sep 17 00:00:00 2001
From: Richard Thier <u9vata@gmail.com>
Date: Mon, 17 Jun 2019 23:46:27 +0200
Subject: [PATCH 1606/2753] drm/radeon: Fix rs400_gpu_init for ATI mobility
 radeon Xpress 200M
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

num_gb_pipes was set to a wrong value using r420_pipe_config

This have lead to HyperZ glitches on fast Z clearing.

Closes: https://bugs.freedesktop.org/show_bug.cgi?id=110897
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Richard Thier <u9vata@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 044e59a85c4d84e3c8d004c486e5c479640563a6)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/radeon/r300.c        |  3 ++-
 drivers/gpu/drm/radeon/radeon_asic.h |  1 +
 drivers/gpu/drm/radeon/rs400.c       | 18 ++++++++++++++++--
 3 files changed, 19 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/radeon/r300.c b/drivers/gpu/drm/radeon/r300.c
index 05c13102a8cb8..d22889fbfa9c8 100644
--- a/drivers/gpu/drm/radeon/r300.c
+++ b/drivers/gpu/drm/radeon/r300.c
@@ -359,7 +359,8 @@ int r300_mc_wait_for_idle(struct radeon_device *rdev)
 	return -1;
 }
 
-static void r300_gpu_init(struct radeon_device *rdev)
+/* rs400_gpu_init also calls this! */
+void r300_gpu_init(struct radeon_device *rdev)
 {
 	uint32_t gb_tile_config, tmp;
 
diff --git a/drivers/gpu/drm/radeon/radeon_asic.h b/drivers/gpu/drm/radeon/radeon_asic.h
index 1e00f6b99f94b..8f5e07834fcc6 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.h
+++ b/drivers/gpu/drm/radeon/radeon_asic.h
@@ -165,6 +165,7 @@ void r200_set_safe_registers(struct radeon_device *rdev);
  */
 extern int r300_init(struct radeon_device *rdev);
 extern void r300_fini(struct radeon_device *rdev);
+extern void r300_gpu_init(struct radeon_device *rdev);
 extern int r300_suspend(struct radeon_device *rdev);
 extern int r300_resume(struct radeon_device *rdev);
 extern int r300_asic_reset(struct radeon_device *rdev, bool hard);
diff --git a/drivers/gpu/drm/radeon/rs400.c b/drivers/gpu/drm/radeon/rs400.c
index d6c18fd740ec6..13cd0a688a65c 100644
--- a/drivers/gpu/drm/radeon/rs400.c
+++ b/drivers/gpu/drm/radeon/rs400.c
@@ -256,8 +256,22 @@ int rs400_mc_wait_for_idle(struct radeon_device *rdev)
 
 static void rs400_gpu_init(struct radeon_device *rdev)
 {
-	/* FIXME: is this correct ? */
-	r420_pipes_init(rdev);
+	/* Earlier code was calling r420_pipes_init and then
+	 * rs400_mc_wait_for_idle(rdev). The problem is that
+	 * at least on my Mobility Radeon Xpress 200M RC410 card
+	 * that ends up in this code path ends up num_gb_pipes == 3
+	 * while the card seems to have only one pipe. With the
+	 * r420 pipe initialization method.
+	 *
+	 * Problems shown up as HyperZ glitches, see:
+	 * https://bugs.freedesktop.org/show_bug.cgi?id=110897
+	 *
+	 * Delegating initialization to r300 code seems to work
+	 * and results in proper pipe numbers. The rs400 cards
+	 * are said to be not r400, but r300 kind of cards.
+	 */
+	r300_gpu_init(rdev);
+
 	if (rs400_mc_wait_for_idle(rdev)) {
 		pr_warn("rs400: Failed to wait MC idle while programming pipes. Bad things might happen. %08x\n",
 			RREG32(RADEON_MC_STATUS));

From da552bda987420e877500fdd90bd0172e3bf412b Mon Sep 17 00:00:00 2001
From: Kenneth Feng <kenneth.feng@amd.com>
Date: Fri, 28 Feb 2025 17:02:11 +0800
Subject: [PATCH 1607/2753] drm/amd/pm: always allow ih interrupt from fw

always allow ih interrupt from fw on smu v14 based on
the interface requirement

Signed-off-by: Kenneth Feng <kenneth.feng@amd.com>
Reviewed-by: Yang Wang <kevinyang.wang@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit a3199eba46c54324193607d9114a1e321292d7a1)
Cc: stable@vger.kernel.org # 6.12.x
---
 drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
index 9b2f4fe1578b8..ddb6444406d28 100644
--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
+++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0.c
@@ -1895,16 +1895,6 @@ static int smu_v14_0_allow_ih_interrupt(struct smu_context *smu)
 				    NULL);
 }
 
-static int smu_v14_0_process_pending_interrupt(struct smu_context *smu)
-{
-	int ret = 0;
-
-	if (smu_cmn_feature_is_enabled(smu, SMU_FEATURE_ACDC_BIT))
-		ret = smu_v14_0_allow_ih_interrupt(smu);
-
-	return ret;
-}
-
 int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 {
 	int ret = 0;
@@ -1916,7 +1906,7 @@ int smu_v14_0_enable_thermal_alert(struct smu_context *smu)
 	if (ret)
 		return ret;
 
-	return smu_v14_0_process_pending_interrupt(smu);
+	return smu_v14_0_allow_ih_interrupt(smu);
 }
 
 int smu_v14_0_disable_thermal_alert(struct smu_context *smu)

From 0d2d0f3d93ddd6556f23c917d910becd9925ddeb Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Wed, 5 Mar 2025 07:35:40 -1000
Subject: [PATCH 1608/2753] fs/pipe: remove buggy and unused 'helper' function

While looking for incorrect users of the pipe head/tail fields (see
commit c27c66afc449: "fs/pipe: Fix pipe_occupancy() with 16-bit
indexes"), I found a bug in pipe_discard_from() that looked entirely
broken.

However, the fix is trivial: this buggy function isn't actually called
by anything, so let's just remove it ASAP.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 05ccbc5d01294..e572e6fc4f81f 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -281,15 +281,6 @@ static inline bool pipe_buf_try_steal(struct pipe_inode_info *pipe,
 	return buf->ops->try_steal(pipe, buf);
 }
 
-static inline void pipe_discard_from(struct pipe_inode_info *pipe,
-		unsigned int old_head)
-{
-	unsigned int mask = pipe->ring_size - 1;
-
-	while (pipe->head > old_head)
-		pipe_buf_release(pipe, &pipe->bufs[--pipe->head & mask]);
-}
-
 /* Differs from PIPE_BUF in that PIPE_SIZE is the length of the actual
    memory allocation, whereas PIPE_BUF makes atomicity guarantees.  */
 #define PIPE_SIZE		PAGE_SIZE

From 528361c49962708a60f51a1afafeb00987cebedf Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 5 Mar 2025 18:52:59 +0300
Subject: [PATCH 1609/2753] nvme-tcp: fix signedness bug in
 nvme_tcp_init_connection()

The kernel_recvmsg() function returns an int which could be either
negative error codes or the number of bytes received.  The problem is
that the condition:

        if (ret < sizeof(*icresp)) {

is type promoted to type unsigned long and negative values are treated
as high positive values which is success, when they should be treated as
failure.  Handle invalid positive returns separately from negative
error codes to avoid this problem.

Fixes: 578539e09690 ("nvme-tcp: fix connect failure on receiving partial ICResp PDU")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/tcp.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c
index 23f11527d29d0..327f3f2f5399c 100644
--- a/drivers/nvme/host/tcp.c
+++ b/drivers/nvme/host/tcp.c
@@ -1521,11 +1521,11 @@ static int nvme_tcp_init_connection(struct nvme_tcp_queue *queue)
 	msg.msg_flags = MSG_WAITALL;
 	ret = kernel_recvmsg(queue->sock, &msg, &iov, 1,
 			iov.iov_len, msg.msg_flags);
-	if (ret < sizeof(*icresp)) {
+	if (ret >= 0 && ret < sizeof(*icresp))
+		ret = -ECONNRESET;
+	if (ret < 0) {
 		pr_warn("queue %d: failed to receive icresp, error %d\n",
 			nvme_tcp_queue_id(queue), ret);
-		if (ret >= 0)
-			ret = -ECONNRESET;
 		goto free_icresp;
 	}
 	ret = -ENOTCONN;

From f2c11231b57b5163bf16cdfd65271d53d61dd996 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:45 +0000
Subject: [PATCH 1610/2753] ALSA: hda/realtek: Add support for ASUS ROG Strix
 G814 Laptop using CS35L41 HDA

Add support for ASUS G814PH/PM/PP and G814FH/FM/FP.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C.

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-2-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 4ca457e7ca9dd..e7612ab492172 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,6 +10784,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x3e00, "ASUS G814FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3e20, "ASUS G814PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e30, "ASUS TP3607SA", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3ee0, "ASUS Strix G815_JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3ef0, "ASUS Strix G635LR_LW_LX", ALC287_FIXUP_TAS2781_I2C),

From 16dc157346dd4404b02b42e73b88604be3652039 Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:46 +0000
Subject: [PATCH 1611/2753] ALSA: hda/realtek: Add support for ASUS ROG Strix
 GA603 Laptops using CS35L41 HDA

Add support for ASUS GA603KP, GA603KM and GA603KH.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-3-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index e7612ab492172..aa9b6e474f69b 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,6 +10784,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+	SND_PCI_QUIRK(0x1043, 0x3d78, "ASUS GA603KH", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3d88, "ASUS GA603KM", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e00, "ASUS G814FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e20, "ASUS G814PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3e30, "ASUS TP3607SA", ALC287_FIXUP_TAS2781_I2C),

From 9120b2b4ad0dad2f6bbb6bcacd0456f806fda62d Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:47 +0000
Subject: [PATCH 1612/2753] ALSA: hda/realtek: Add support for ASUS ROG Strix
 G614 Laptops using CS35L41 HDA

Add support for ASUS G614PH/PM/PP and G614FH/FM/FP.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-4-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index aa9b6e474f69b..c2ebcd2958c3f 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10676,7 +10676,9 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x8e1a, "HP ZBook Firefly 14 G12A", ALC285_FIXUP_HP_GPIO_LED),
 	SND_PCI_QUIRK(0x1043, 0x103e, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x103f, "ASUS TX300", ALC282_FIXUP_ASUS_TX300),
+	SND_PCI_QUIRK(0x1043, 0x1054, "ASUS G614FH/FM/FP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x106d, "Asus K53BE", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1074, "ASUS G614PH/PM/PP", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x10a1, "ASUS UX391UA", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x10a4, "ASUS TP3407SA", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x10c0, "ASUS X540SA", ALC256_FIXUP_ASUS_MIC),

From 859a11917001424776e1cca02b762efcabb4044e Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:48 +0000
Subject: [PATCH 1613/2753] ALSA: hda/realtek: Add support for various ASUS
 Laptops using CS35L41 HDA

Add support for ASUS B3405CVA, B5405CVA, B5605CVA, B3605CVA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-5-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index c2ebcd2958c3f..bf89900ec5f50 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10692,6 +10692,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x125e, "ASUS Q524UQK", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1271, "ASUS X430UN", ALC256_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1290, "ASUS X441SA", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
+	SND_PCI_QUIRK(0x1043, 0x1294, "ASUS B3405CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
 	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
@@ -10779,6 +10780,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1f63, "ASUS P5405CSA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
+	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
@@ -10797,6 +10799,8 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3f10, "ASUS Strix G835LR_LW_LX", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3f20, "ASUS Strix G615LR_LW", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x3f30, "ASUS Strix G815LR_LW", ALC287_FIXUP_TAS2781_I2C),
+	SND_PCI_QUIRK(0x1043, 0x3fd0, "ASUS B3605CVA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3ff0, "ASUS B5405CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
 	SND_PCI_QUIRK(0x1043, 0x8398, "ASUS P1005", ALC269_FIXUP_STEREO_DMIC),

From 7ab61d0a9a35e32497bcf2233310fec79ee3338f Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:49 +0000
Subject: [PATCH 1614/2753] ALSA: hda/realtek: Add support for ASUS B3405 and
 B3605 Laptops using CS35L41 HDA

Add support for ASUS B3405CCA / P3405CCA, B3605CCA / P3605CCA,
B3405CCA, B3605CCA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-6-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index bf89900ec5f50..53d2a267d7989 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10696,6 +10696,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x12a0, "ASUS X441UV", ALC233_FIXUP_EAPD_COEF_AND_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x12a3, "Asus N7691ZM", ALC269_FIXUP_ASUS_N7601ZM),
 	SND_PCI_QUIRK(0x1043, 0x12af, "ASUS UX582ZS", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x12b4, "ASUS B3405CCA / P3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x12e0, "ASUS X541SA", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x12f0, "ASUS X541UV", ALC256_FIXUP_ASUS_MIC),
 	SND_PCI_QUIRK(0x1043, 0x1313, "Asus K42JZ", ALC269VB_FIXUP_ASUS_MIC_NO_PRESENCE),
@@ -10782,7 +10783,10 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x1fb3, "ASUS ROG Flow Z13 GZ302EA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
+	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
+	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From c86dd79a7c338fff9bebb9503857e07db9845eca Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:50 +0000
Subject: [PATCH 1615/2753] ALSA: hda/realtek: Add support for ASUS B5405 and
 B5605 Laptops using CS35L41 HDA

Add support for ASUS B5605CCA and B5405CCA.

Laptops use 2 CS35L41 Amps with HDA, using Internal boost, with SPI

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-7-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 53d2a267d7989..f67ab69c9997c 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10784,8 +10784,12 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x3011, "ASUS B5605CVA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
 	SND_PCI_QUIRK(0x1043, 0x3061, "ASUS B3405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x3071, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x30c1, "ASUS B3605CCA / P3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30d1, "ASUS B5405CCA", ALC245_FIXUP_CS35L41_SPI_2),
+	SND_PCI_QUIRK(0x1043, 0x30e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31d0, "ASUS Zen AIO 27 Z272SD_A272SD", ALC274_FIXUP_ASUS_ZEN_AIO_27),
+	SND_PCI_QUIRK(0x1043, 0x31e1, "ASUS B5605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x31f1, "ASUS B3605CCA", ALC245_FIXUP_CS35L41_SPI_2),
 	SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
 	SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),

From 8463d2adbe1901247937fcdfe4b525130f6db10b Mon Sep 17 00:00:00 2001
From: Stefan Binding <sbinding@opensource.cirrus.com>
Date: Wed, 5 Mar 2025 17:06:51 +0000
Subject: [PATCH 1616/2753] ALSA: hda/realtek: Add support for ASUS Zenbook
 UM3406KA Laptops using CS35L41 HDA

Laptop uses 2 CS35L41 Amps with HDA, using External boost with I2C

Signed-off-by: Stefan Binding <sbinding@opensource.cirrus.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Link: https://patch.msgid.link/20250305170714.755794-8-sbinding@opensource.cirrus.com
---
 sound/pci/hda/patch_realtek.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index f67ab69c9997c..d2a1f836dbbf7 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10686,6 +10686,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x1043, 0x10d3, "ASUS K6500ZC", ALC294_FIXUP_ASUS_SPK),
 	SND_PCI_QUIRK(0x1043, 0x1154, "ASUS TP3607SH", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x115d, "Asus 1015E", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+	SND_PCI_QUIRK(0x1043, 0x1194, "ASUS UM3406KA", ALC287_FIXUP_CS35L41_I2C_2),
 	SND_PCI_QUIRK(0x1043, 0x11c0, "ASUS X556UR", ALC255_FIXUP_ASUS_MIC_NO_PRESENCE),
 	SND_PCI_QUIRK(0x1043, 0x1204, "ASUS Strix G615JHR_JMR_JPR", ALC287_FIXUP_TAS2781_I2C),
 	SND_PCI_QUIRK(0x1043, 0x1214, "ASUS Strix G615LH_LM_LP", ALC287_FIXUP_TAS2781_I2C),

From f2052a4a62465c0037aef7ea7426bffdb3531e41 Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Mon, 3 Mar 2025 13:11:21 +0000
Subject: [PATCH 1617/2753] clk: samsung: gs101: fix synchronous external abort
 in samsung_clk_save()

EARLY_WAKEUP_SW_TRIG_*_SET and EARLY_WAKEUP_SW_TRIG_*_CLEAR
registers are only writeable. Attempting to read these registers
during samsung_clk_save() causes a synchronous external abort.

Remove these 8 registers from cmu_top_clk_regs[] array so that
system suspend gets further.

Note: the code path can be exercised using the following command:
echo mem > /sys/power/state

Fixes: 2c597bb7d66a ("clk: samsung: clk-gs101: Add cmu_top, cmu_misc and cmu_apm support")
Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250303-clk-suspend-fix-v1-1-c2edaf66260f@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/clk/samsung/clk-gs101.c | 8 --------
 1 file changed, 8 deletions(-)

diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c
index 86b39edba1227..08b867ae3ed9d 100644
--- a/drivers/clk/samsung/clk-gs101.c
+++ b/drivers/clk/samsung/clk-gs101.c
@@ -382,17 +382,9 @@ static const unsigned long cmu_top_clk_regs[] __initconst = {
 	EARLY_WAKEUP_DPU_DEST,
 	EARLY_WAKEUP_CSIS_DEST,
 	EARLY_WAKEUP_SW_TRIG_APM,
-	EARLY_WAKEUP_SW_TRIG_APM_SET,
-	EARLY_WAKEUP_SW_TRIG_APM_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_CLUSTER0,
-	EARLY_WAKEUP_SW_TRIG_CLUSTER0_SET,
-	EARLY_WAKEUP_SW_TRIG_CLUSTER0_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_DPU,
-	EARLY_WAKEUP_SW_TRIG_DPU_SET,
-	EARLY_WAKEUP_SW_TRIG_DPU_CLEAR,
 	EARLY_WAKEUP_SW_TRIG_CSIS,
-	EARLY_WAKEUP_SW_TRIG_CSIS_SET,
-	EARLY_WAKEUP_SW_TRIG_CSIS_CLEAR,
 	CLK_CON_MUX_MUX_CLKCMU_BO_BUS,
 	CLK_CON_MUX_MUX_CLKCMU_BUS0_BUS,
 	CLK_CON_MUX_MUX_CLKCMU_BUS1_BUS,

From 53517a70873c7a91675f7244768aad5006cc45de Mon Sep 17 00:00:00 2001
From: Varada Pavani <v.pavani@samsung.com>
Date: Tue, 25 Feb 2025 18:49:18 +0530
Subject: [PATCH 1618/2753] clk: samsung: update PLL locktime for PLL142XX used
 on FSD platform

Currently PLL142XX locktime is 270. As per spec, it should be 150. Hence
update PLL142XX controller locktime to 150.

Cc: stable@vger.kernel.org
Fixes: 4f346005aaed ("clk: samsung: fsd: Add initial clock support")
Signed-off-by: Varada Pavani <v.pavani@samsung.com>
Link: https://lore.kernel.org/r/20250225131918.50925-3-v.pavani@samsung.com
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/clk/samsung/clk-pll.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/samsung/clk-pll.c b/drivers/clk/samsung/clk-pll.c
index 2e94bba6c3966..023a25af73c47 100644
--- a/drivers/clk/samsung/clk-pll.c
+++ b/drivers/clk/samsung/clk-pll.c
@@ -206,6 +206,7 @@ static const struct clk_ops samsung_pll3000_clk_ops = {
  */
 /* Maximum lock time can be 270 * PDIV cycles */
 #define PLL35XX_LOCK_FACTOR	(270)
+#define PLL142XX_LOCK_FACTOR	(150)
 
 #define PLL35XX_MDIV_MASK       (0x3FF)
 #define PLL35XX_PDIV_MASK       (0x3F)
@@ -272,7 +273,11 @@ static int samsung_pll35xx_set_rate(struct clk_hw *hw, unsigned long drate,
 	}
 
 	/* Set PLL lock time. */
-	writel_relaxed(rate->pdiv * PLL35XX_LOCK_FACTOR,
+	if (pll->type == pll_142xx)
+		writel_relaxed(rate->pdiv * PLL142XX_LOCK_FACTOR,
+			pll->lock_reg);
+	else
+		writel_relaxed(rate->pdiv * PLL35XX_LOCK_FACTOR,
 			pll->lock_reg);
 
 	/* Change PLL PMS values */

From e775e2a060d99180edc5366fb9f4299d0f07b66c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:55 +0100
Subject: [PATCH 1619/2753] drm/xe/vm: Validate userptr during gpu vma
 prefetching
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If a userptr vma subject to prefetching was already invalidated
or invalidated during the prefetch operation, the operation would
repeatedly return -EAGAIN which would typically cause an infinite
loop.

Validate the userptr to ensure this doesn't happen.

v2:
- Don't fallthrough from UNMAP to PREFETCH (Matthew Brost)

Fixes: 5bd24e78829a ("drm/xe/vm: Subclass userptr vmas")
Fixes: 617eebb9c480 ("drm/xe: Fix array of binds")
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: <stable@vger.kernel.org> # v6.9+
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit 03c346d4d0d85d210d549d43c8cfb3dfb7f20e0a)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index 30259eba450b5..d2cd227e4d694 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -2286,8 +2286,17 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct drm_gpuva_ops *ops,
 			break;
 		}
 		case DRM_GPUVA_OP_UNMAP:
+			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
+			break;
 		case DRM_GPUVA_OP_PREFETCH:
-			/* FIXME: Need to skip some prefetch ops */
+			vma = gpuva_to_vma(op->base.prefetch.va);
+
+			if (xe_vma_is_userptr(vma)) {
+				err = xe_vma_userptr_pin_pages(to_userptr_vma(vma));
+				if (err)
+					return err;
+			}
+
 			xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask);
 			break;
 		default:

From 1414d95d5805b1dc221d22db9b8dc5287ef083bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:56 +0100
Subject: [PATCH 1620/2753] drm/xe/vm: Fix a misplaced #endif
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix a (harmless) misplaced #endif leading to declarations
appearing multiple times.

Fixes: 0eb2a18a8fad ("drm/xe: Implement VM snapshot support for BO's and userptr")
Cc: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Cc: José Roberto de Souza <jose.souza@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit fcc20a4c752214b3e25632021c57d7d1d71ee1dd)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 23adb74428815..256a837c2704a 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -274,9 +274,9 @@ static inline void vm_dbg(const struct drm_device *dev,
 			  const char *format, ...)
 { /* noop */ }
 #endif
-#endif
 
 struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
 void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
 void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
 void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+#endif

From 84211b1c0db6b9dbe0020fa97192fb9661617f24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 28 Feb 2025 08:30:57 +0100
Subject: [PATCH 1621/2753] drm/xe: Fix fault mode invalidation with unbind
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix fault mode invalidation racing with unbind leading to the
PTE zapping potentially traversing an invalid page-table tree.
Do this by holding the notifier lock across PTE zapping. This
might transfer any contention waiting on the notifier seqlock
read side to the notifier lock read side, but that shouldn't be
a major problem.

At the same time get rid of the open-coded invalidation in the bind
code by relying on the notifier even when the vma bind is not
yet committed.

Finally let userptr invalidation call a dedicated xe_vm function
performing a full invalidation.

Fixes: e8babb280b5e ("drm/xe: Convert multiple bind ops into single job")
Cc: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.12+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit 100a5b8dadfca50d91d9a4c9fc01431b42a25cab)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c       | 38 ++++----------
 drivers/gpu/drm/xe/xe_vm.c       | 85 +++++++++++++++++++++-----------
 drivers/gpu/drm/xe/xe_vm.h       |  8 +++
 drivers/gpu/drm/xe/xe_vm_types.h |  4 +-
 4 files changed, 75 insertions(+), 60 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 1ddcc7e79a93e..12a627a23eb45 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -1213,42 +1213,22 @@ static int vma_check_userptr(struct xe_vm *vm, struct xe_vma *vma,
 		return 0;
 
 	uvma = to_userptr_vma(vma);
-	notifier_seq = uvma->userptr.notifier_seq;
+	if (xe_pt_userptr_inject_eagain(uvma))
+		xe_vma_userptr_force_invalidate(uvma);
 
-	if (uvma->userptr.initial_bind && !xe_vm_in_fault_mode(vm))
-		return 0;
+	notifier_seq = uvma->userptr.notifier_seq;
 
 	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
-				     notifier_seq) &&
-	    !xe_pt_userptr_inject_eagain(uvma))
+				     notifier_seq))
 		return 0;
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm))
 		return -EAGAIN;
-	} else {
-		spin_lock(&vm->userptr.invalidated_lock);
-		list_move_tail(&uvma->userptr.invalidate_link,
-			       &vm->userptr.invalidated);
-		spin_unlock(&vm->userptr.invalidated_lock);
-
-		if (xe_vm_in_preempt_fence_mode(vm)) {
-			struct dma_resv_iter cursor;
-			struct dma_fence *fence;
-			long err;
-
-			dma_resv_iter_begin(&cursor, xe_vm_resv(vm),
-					    DMA_RESV_USAGE_BOOKKEEP);
-			dma_resv_for_each_fence_unlocked(&cursor, fence)
-				dma_fence_enable_sw_signaling(fence);
-			dma_resv_iter_end(&cursor);
-
-			err = dma_resv_wait_timeout(xe_vm_resv(vm),
-						    DMA_RESV_USAGE_BOOKKEEP,
-						    false, MAX_SCHEDULE_TIMEOUT);
-			XE_WARN_ON(err <= 0);
-		}
-	}
 
+	/*
+	 * Just continue the operation since exec or rebind worker
+	 * will take care of rebinding.
+	 */
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d2cd227e4d694..d54aaa5eaff38 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -579,51 +579,26 @@ static void preempt_rebind_work_func(struct work_struct *w)
 	trace_xe_vm_rebind_worker_exit(vm);
 }
 
-static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
-				   const struct mmu_notifier_range *range,
-				   unsigned long cur_seq)
+static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uvma)
 {
-	struct xe_userptr *userptr = container_of(mni, typeof(*userptr), notifier);
-	struct xe_userptr_vma *uvma = container_of(userptr, typeof(*uvma), userptr);
+	struct xe_userptr *userptr = &uvma->userptr;
 	struct xe_vma *vma = &uvma->vma;
-	struct xe_vm *vm = xe_vma_vm(vma);
 	struct dma_resv_iter cursor;
 	struct dma_fence *fence;
 	long err;
 
-	xe_assert(vm->xe, xe_vma_is_userptr(vma));
-	trace_xe_vma_userptr_invalidate(vma);
-
-	if (!mmu_notifier_range_blockable(range))
-		return false;
-
-	vm_dbg(&xe_vma_vm(vma)->xe->drm,
-	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
-		xe_vma_start(vma), xe_vma_size(vma));
-
-	down_write(&vm->userptr.notifier_lock);
-	mmu_interval_set_seq(mni, cur_seq);
-
-	/* No need to stop gpu access if the userptr is not yet bound. */
-	if (!userptr->initial_bind) {
-		up_write(&vm->userptr.notifier_lock);
-		return true;
-	}
-
 	/*
 	 * Tell exec and rebind worker they need to repin and rebind this
 	 * userptr.
 	 */
 	if (!xe_vm_in_fault_mode(vm) &&
-	    !(vma->gpuva.flags & XE_VMA_DESTROYED) && vma->tile_present) {
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
 		spin_lock(&vm->userptr.invalidated_lock);
 		list_move_tail(&userptr->invalidate_link,
 			       &vm->userptr.invalidated);
 		spin_unlock(&vm->userptr.invalidated_lock);
 	}
 
-	up_write(&vm->userptr.notifier_lock);
-
 	/*
 	 * Preempt fences turn into schedule disables, pipeline these.
 	 * Note that even in fault mode, we need to wait for binds and
@@ -641,11 +616,35 @@ static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
 				    false, MAX_SCHEDULE_TIMEOUT);
 	XE_WARN_ON(err <= 0);
 
-	if (xe_vm_in_fault_mode(vm)) {
+	if (xe_vm_in_fault_mode(vm) && userptr->initial_bind) {
 		err = xe_vm_invalidate_vma(vma);
 		XE_WARN_ON(err);
 	}
+}
 
+static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
+				   const struct mmu_notifier_range *range,
+				   unsigned long cur_seq)
+{
+	struct xe_userptr_vma *uvma = container_of(mni, typeof(*uvma), userptr.notifier);
+	struct xe_vma *vma = &uvma->vma;
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_assert(vm->xe, xe_vma_is_userptr(vma));
+	trace_xe_vma_userptr_invalidate(vma);
+
+	if (!mmu_notifier_range_blockable(range))
+		return false;
+
+	vm_dbg(&xe_vma_vm(vma)->xe->drm,
+	       "NOTIFIER: addr=0x%016llx, range=0x%016llx",
+		xe_vma_start(vma), xe_vma_size(vma));
+
+	down_write(&vm->userptr.notifier_lock);
+	mmu_interval_set_seq(mni, cur_seq);
+
+	__vma_userptr_invalidate(vm, uvma);
+	up_write(&vm->userptr.notifier_lock);
 	trace_xe_vma_userptr_invalidate_complete(vma);
 
 	return true;
@@ -655,6 +654,34 @@ static const struct mmu_interval_notifier_ops vma_userptr_notifier_ops = {
 	.invalidate = vma_userptr_invalidate,
 };
 
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+/**
+ * xe_vma_userptr_force_invalidate() - force invalidate a userptr
+ * @uvma: The userptr vma to invalidate
+ *
+ * Perform a forced userptr invalidation for testing purposes.
+ */
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	/* Protect against concurrent userptr pinning */
+	lockdep_assert_held(&vm->lock);
+	/* Protect against concurrent notifiers */
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+	/*
+	 * Protect against concurrent instances of this function and
+	 * the critical exec sections
+	 */
+	xe_vm_assert_held(vm);
+
+	if (!mmu_interval_read_retry(&uvma->userptr.notifier,
+				     uvma->userptr.notifier_seq))
+		uvma->userptr.notifier_seq -= 2;
+	__vma_userptr_invalidate(vm, uvma);
+}
+#endif
+
 int xe_vm_userptr_pin(struct xe_vm *vm)
 {
 	struct xe_userptr_vma *uvma, *next;
diff --git a/drivers/gpu/drm/xe/xe_vm.h b/drivers/gpu/drm/xe/xe_vm.h
index 256a837c2704a..b882bfb31bd05 100644
--- a/drivers/gpu/drm/xe/xe_vm.h
+++ b/drivers/gpu/drm/xe/xe_vm.h
@@ -279,4 +279,12 @@ struct xe_vm_snapshot *xe_vm_snapshot_capture(struct xe_vm *vm);
 void xe_vm_snapshot_capture_delayed(struct xe_vm_snapshot *snap);
 void xe_vm_snapshot_print(struct xe_vm_snapshot *snap, struct drm_printer *p);
 void xe_vm_snapshot_free(struct xe_vm_snapshot *snap);
+
+#if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
+void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma);
+#else
+static inline void xe_vma_userptr_force_invalidate(struct xe_userptr_vma *uvma)
+{
+}
+#endif
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index 7f9a303e51d89..d2511819cdf43 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -227,8 +227,8 @@ struct xe_vm {
 		 * up for revalidation. Protected from access with the
 		 * @invalidated_lock. Removing items from the list
 		 * additionally requires @lock in write mode, and adding
-		 * items to the list requires the @userptr.notifer_lock in
-		 * write mode.
+		 * items to the list requires either the @userptr.notifer_lock in
+		 * write mode, OR @lock in write mode.
 		 */
 		struct list_head invalidated;
 	} userptr;

From ae482ec8cd1a85bde3307f71921a7780086fbec0 Mon Sep 17 00:00:00 2001
From: Matthew Brost <matthew.brost@intel.com>
Date: Fri, 28 Feb 2025 08:30:58 +0100
Subject: [PATCH 1622/2753] drm/xe: Add staging tree for VM binds
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Concurrent VM bind staging and zapping of PTEs from a userptr notifier
do not work because the view of PTEs is not stable. VM binds cannot
acquire the notifier lock during staging, as memory allocations are
required. To resolve this race condition, use a staging tree for VM
binds that is committed only under the userptr notifier lock during the
final step of the bind. This ensures a consistent view of the PTEs in
the userptr notifier.

A follow up may only use staging for VM in fault mode as this is the
only mode in which the above race exists.

v3:
 - Drop zap PTE change (Thomas)
 - s/xe_pt_entry/xe_pt_entry_staging (Thomas)

Suggested-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Cc: <stable@vger.kernel.org>
Fixes: e8babb280b5e ("drm/xe: Convert multiple bind ops into single job")
Fixes: a708f6501c69 ("drm/xe: Update PT layer with better error handling")
Signed-off-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250228073058.59510-5-thomas.hellstrom@linux.intel.com
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
(cherry picked from commit 6f39b0c5ef0385eae586760d10b9767168037aa5)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pt.c      | 58 +++++++++++++++++++++++----------
 drivers/gpu/drm/xe/xe_pt_walk.c |  3 +-
 drivers/gpu/drm/xe/xe_pt_walk.h |  4 +++
 3 files changed, 46 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_pt.c b/drivers/gpu/drm/xe/xe_pt.c
index 12a627a23eb45..dc24baa840924 100644
--- a/drivers/gpu/drm/xe/xe_pt.c
+++ b/drivers/gpu/drm/xe/xe_pt.c
@@ -28,6 +28,8 @@ struct xe_pt_dir {
 	struct xe_pt pt;
 	/** @children: Array of page-table child nodes */
 	struct xe_ptw *children[XE_PDES];
+	/** @staging: Array of page-table staging nodes */
+	struct xe_ptw *staging[XE_PDES];
 };
 
 #if IS_ENABLED(CONFIG_DRM_XE_DEBUG_VM)
@@ -48,9 +50,10 @@ static struct xe_pt_dir *as_xe_pt_dir(struct xe_pt *pt)
 	return container_of(pt, struct xe_pt_dir, pt);
 }
 
-static struct xe_pt *xe_pt_entry(struct xe_pt_dir *pt_dir, unsigned int index)
+static struct xe_pt *
+xe_pt_entry_staging(struct xe_pt_dir *pt_dir, unsigned int index)
 {
-	return container_of(pt_dir->children[index], struct xe_pt, base);
+	return container_of(pt_dir->staging[index], struct xe_pt, base);
 }
 
 static u64 __xe_pt_empty_pte(struct xe_tile *tile, struct xe_vm *vm,
@@ -125,6 +128,7 @@ struct xe_pt *xe_pt_create(struct xe_vm *vm, struct xe_tile *tile,
 	}
 	pt->bo = bo;
 	pt->base.children = level ? as_xe_pt_dir(pt)->children : NULL;
+	pt->base.staging = level ? as_xe_pt_dir(pt)->staging : NULL;
 
 	if (vm->xef)
 		xe_drm_client_add_bo(vm->xef->client, pt->bo);
@@ -206,8 +210,8 @@ void xe_pt_destroy(struct xe_pt *pt, u32 flags, struct llist_head *deferred)
 		struct xe_pt_dir *pt_dir = as_xe_pt_dir(pt);
 
 		for (i = 0; i < XE_PDES; i++) {
-			if (xe_pt_entry(pt_dir, i))
-				xe_pt_destroy(xe_pt_entry(pt_dir, i), flags,
+			if (xe_pt_entry_staging(pt_dir, i))
+				xe_pt_destroy(xe_pt_entry_staging(pt_dir, i), flags,
 					      deferred);
 		}
 	}
@@ -376,8 +380,10 @@ xe_pt_insert_entry(struct xe_pt_stage_bind_walk *xe_walk, struct xe_pt *parent,
 		/* Continue building a non-connected subtree. */
 		struct iosys_map *map = &parent->bo->vmap;
 
-		if (unlikely(xe_child))
+		if (unlikely(xe_child)) {
 			parent->base.children[offset] = &xe_child->base;
+			parent->base.staging[offset] = &xe_child->base;
+		}
 
 		xe_pt_write(xe_walk->vm->xe, map, offset, pte);
 		parent->num_live++;
@@ -614,6 +620,7 @@ xe_pt_stage_bind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_bind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.vm = xe_vma_vm(vma),
 		.tile = tile,
@@ -873,7 +880,7 @@ static void xe_pt_cancel_bind(struct xe_vma *vma,
 	}
 }
 
-static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+static void xe_pt_commit_prepare_locks_assert(struct xe_vma *vma)
 {
 	struct xe_vm *vm = xe_vma_vm(vma);
 
@@ -885,6 +892,16 @@ static void xe_pt_commit_locks_assert(struct xe_vma *vma)
 	xe_vm_assert_held(vm);
 }
 
+static void xe_pt_commit_locks_assert(struct xe_vma *vma)
+{
+	struct xe_vm *vm = xe_vma_vm(vma);
+
+	xe_pt_commit_prepare_locks_assert(vma);
+
+	if (xe_vma_is_userptr(vma))
+		lockdep_assert_held_read(&vm->userptr.notifier_lock);
+}
+
 static void xe_pt_commit(struct xe_vma *vma,
 			 struct xe_vm_pgtable_update *entries,
 			 u32 num_entries, struct llist_head *deferred)
@@ -895,13 +912,17 @@ static void xe_pt_commit(struct xe_vma *vma,
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
+		struct xe_pt_dir *pt_dir;
 
 		if (!pt->level)
 			continue;
 
+		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
+			int j_ = j + entries[i].ofs;
 
+			pt_dir->children[j_] = pt_dir->staging[j_];
 			xe_pt_destroy(oldpte, xe_vma_vm(vma)->flags, deferred);
 		}
 	}
@@ -913,7 +934,7 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_pt *pt = entries[i].pt;
@@ -928,10 +949,10 @@ static void xe_pt_abort_bind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = 0; j < entries[i].qwords; j++) {
 			u32 j_ = j + entries[i].ofs;
-			struct xe_pt *newpte = xe_pt_entry(pt_dir, j_);
+			struct xe_pt *newpte = xe_pt_entry_staging(pt_dir, j_);
 			struct xe_pt *oldpte = entries[i].pt_entries[j].pt;
 
-			pt_dir->children[j_] = oldpte ? &oldpte->base : 0;
+			pt_dir->staging[j_] = oldpte ? &oldpte->base : 0;
 			xe_pt_destroy(newpte, xe_vma_vm(vma)->flags, NULL);
 		}
 	}
@@ -943,7 +964,7 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 {
 	u32 i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; i++) {
 		struct xe_pt *pt = entries[i].pt;
@@ -961,10 +982,10 @@ static void xe_pt_commit_prepare_bind(struct xe_vma *vma,
 			struct xe_pt *newpte = entries[i].pt_entries[j].pt;
 			struct xe_pt *oldpte = NULL;
 
-			if (xe_pt_entry(pt_dir, j_))
-				oldpte = xe_pt_entry(pt_dir, j_);
+			if (xe_pt_entry_staging(pt_dir, j_))
+				oldpte = xe_pt_entry_staging(pt_dir, j_);
 
-			pt_dir->children[j_] = &newpte->base;
+			pt_dir->staging[j_] = &newpte->base;
 			entries[i].pt_entries[j].pt = oldpte;
 		}
 	}
@@ -1494,6 +1515,7 @@ static unsigned int xe_pt_stage_unbind(struct xe_tile *tile, struct xe_vma *vma,
 			.ops = &xe_pt_stage_unbind_ops,
 			.shifts = xe_normal_pt_shifts,
 			.max_level = XE_PT_HIGHEST_LEVEL,
+			.staging = true,
 		},
 		.tile = tile,
 		.modified_start = xe_vma_start(vma),
@@ -1535,7 +1557,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = num_entries - 1; i >= 0; --i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1548,7 +1570,7 @@ static void xe_pt_abort_unbind(struct xe_vma *vma,
 			continue;
 
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++)
-			pt_dir->children[j] =
+			pt_dir->staging[j] =
 				entries[i].pt_entries[j - entry->ofs].pt ?
 				&entries[i].pt_entries[j - entry->ofs].pt->base : NULL;
 	}
@@ -1561,7 +1583,7 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 {
 	int i, j;
 
-	xe_pt_commit_locks_assert(vma);
+	xe_pt_commit_prepare_locks_assert(vma);
 
 	for (i = 0; i < num_entries; ++i) {
 		struct xe_vm_pgtable_update *entry = &entries[i];
@@ -1575,8 +1597,8 @@ xe_pt_commit_prepare_unbind(struct xe_vma *vma,
 		pt_dir = as_xe_pt_dir(pt);
 		for (j = entry->ofs; j < entry->ofs + entry->qwords; j++) {
 			entry->pt_entries[j - entry->ofs].pt =
-				xe_pt_entry(pt_dir, j);
-			pt_dir->children[j] = NULL;
+				xe_pt_entry_staging(pt_dir, j);
+			pt_dir->staging[j] = NULL;
 		}
 	}
 }
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.c b/drivers/gpu/drm/xe/xe_pt_walk.c
index b8b3d2aea4923..be602a763ff32 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.c
+++ b/drivers/gpu/drm/xe/xe_pt_walk.c
@@ -74,7 +74,8 @@ int xe_pt_walk_range(struct xe_ptw *parent, unsigned int level,
 		     u64 addr, u64 end, struct xe_pt_walk *walk)
 {
 	pgoff_t offset = xe_pt_offset(addr, level, walk);
-	struct xe_ptw **entries = parent->children ? parent->children : NULL;
+	struct xe_ptw **entries = walk->staging ? (parent->staging ?: NULL) :
+		(parent->children ?: NULL);
 	const struct xe_pt_walk_ops *ops = walk->ops;
 	enum page_walk_action action;
 	struct xe_ptw *child;
diff --git a/drivers/gpu/drm/xe/xe_pt_walk.h b/drivers/gpu/drm/xe/xe_pt_walk.h
index 5ecc4d2f0f653..5c02c244f7de3 100644
--- a/drivers/gpu/drm/xe/xe_pt_walk.h
+++ b/drivers/gpu/drm/xe/xe_pt_walk.h
@@ -11,12 +11,14 @@
 /**
  * struct xe_ptw - base class for driver pagetable subclassing.
  * @children: Pointer to an array of children if any.
+ * @staging: Pointer to an array of staging if any.
  *
  * Drivers could subclass this, and if it's a page-directory, typically
  * embed an array of xe_ptw pointers.
  */
 struct xe_ptw {
 	struct xe_ptw **children;
+	struct xe_ptw **staging;
 };
 
 /**
@@ -41,6 +43,8 @@ struct xe_pt_walk {
 	 * as shared pagetables.
 	 */
 	bool shared_pt_mode;
+	/** @staging: Walk staging PT structure */
+	bool staging;
 };
 
 /**

From e3e2e7fc4cd8414c9a966ef1b344db543f8614f4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:40 +0100
Subject: [PATCH 1623/2753] drm/xe/hmm: Style- and include fixes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add proper #ifndef around the xe_hmm.h header, proper spacing
and since the documentation mostly follows kerneldoc format,
make it kerneldoc. Also prepare for upcoming -stable fixes.

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-2-thomas.hellstrom@linux.intel.com
(cherry picked from commit bbe2b06b55bc061c8fcec034ed26e88287f39143)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 9 +++------
 drivers/gpu/drm/xe/xe_hmm.h | 5 +++++
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 2e4ae61567d8d..6ddcf88d8a393 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -19,11 +19,10 @@ static u64 xe_npages_in_range(unsigned long start, unsigned long end)
 	return (end - start) >> PAGE_SHIFT;
 }
 
-/*
+/**
  * xe_mark_range_accessed() - mark a range is accessed, so core mm
  * have such information for memory eviction or write back to
  * hard disk
- *
  * @range: the range to mark
  * @write: if write to this range, we mark pages in this range
  * as dirty
@@ -43,11 +42,10 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
 	}
 }
 
-/*
+/**
  * xe_build_sg() - build a scatter gather table for all the physical pages/pfn
  * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
  * and will be used to program GPU page table later.
- *
  * @xe: the xe device who will access the dma-address in sg table
  * @range: the hmm range that we build the sg table from. range->hmm_pfns[]
  * has the pfn numbers of pages that back up this hmm address range.
@@ -112,9 +110,8 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 	return ret;
 }
 
-/*
+/**
  * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
- *
  * @uvma: the userptr vma which hold the scatter gather table
  *
  * With function xe_userptr_populate_range, we allocate storage of
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 909dc2bdcd97e..9602cb7d976dd 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -3,9 +3,14 @@
  * Copyright © 2024 Intel Corporation
  */
 
+#ifndef _XE_HMM_H_
+#define _XE_HMM_H_
+
 #include <linux/types.h>
 
 struct xe_userptr_vma;
 
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
+
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+#endif

From 0a98219bcc961edd3388960576e4353e123b4a51 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:41 +0100
Subject: [PATCH 1624/2753] drm/xe/hmm: Don't dereference struct page pointers
 without notifier lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The pnfs that we obtain from hmm_range_fault() point to pages that
we don't have a reference on, and the guarantee that they are still
in the cpu page-tables is that the notifier lock must be held and the
notifier seqno is still valid.

So while building the sg table and marking the pages accesses / dirty
we need to hold this lock with a validated seqno.

However, the lock is reclaim tainted which makes
sg_alloc_table_from_pages_segment() unusable, since it internally
allocates memory.

Instead build the sg-table manually. For the non-iommu case
this might lead to fewer coalesces, but if that's a problem it can
be fixed up later in the resource cursor code. For the iommu case,
the whole sg-table may still be coalesced to a single contigous
device va region.

This avoids marking pages that we don't own dirty and accessed, and
it also avoid dereferencing struct pages that we don't own.

v2:
- Use assert to check whether hmm pfns are valid (Matthew Auld)
- Take into account that large pages may cross range boundaries
  (Matthew Auld)

v3:
- Don't unnecessarily check for a non-freed sg-table. (Matthew Auld)
- Add a missing up_read() in an error path. (Matthew Auld)

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-3-thomas.hellstrom@linux.intel.com
(cherry picked from commit ea3e66d280ce2576664a862693d1da8fd324c317)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 112 +++++++++++++++++++++++++++---------
 1 file changed, 86 insertions(+), 26 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 6ddcf88d8a393..be284b852307e 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -42,6 +42,42 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
 	}
 }
 
+static int xe_alloc_sg(struct xe_device *xe, struct sg_table *st,
+		       struct hmm_range *range, struct rw_semaphore *notifier_sem)
+{
+	unsigned long i, npages, hmm_pfn;
+	unsigned long num_chunks = 0;
+	int ret;
+
+	/* HMM docs says this is needed. */
+	ret = down_read_interruptible(notifier_sem);
+	if (ret)
+		return ret;
+
+	if (mmu_interval_read_retry(range->notifier, range->notifier_seq)) {
+		up_read(notifier_sem);
+		return -EAGAIN;
+	}
+
+	npages = xe_npages_in_range(range->start, range->end);
+	for (i = 0; i < npages;) {
+		unsigned long len;
+
+		hmm_pfn = range->hmm_pfns[i];
+		xe_assert(xe, hmm_pfn & HMM_PFN_VALID);
+
+		len = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+
+		/* If order > 0 the page may extend beyond range->start */
+		len -= (hmm_pfn & ~HMM_PFN_FLAGS) & (len - 1);
+		i += len;
+		num_chunks++;
+	}
+	up_read(notifier_sem);
+
+	return sg_alloc_table(st, num_chunks, GFP_KERNEL);
+}
+
 /**
  * xe_build_sg() - build a scatter gather table for all the physical pages/pfn
  * in a hmm_range. dma-map pages if necessary. dma-address is save in sg table
@@ -50,6 +86,7 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
  * @range: the hmm range that we build the sg table from. range->hmm_pfns[]
  * has the pfn numbers of pages that back up this hmm address range.
  * @st: pointer to the sg table.
+ * @notifier_sem: The xe notifier lock.
  * @write: whether we write to this range. This decides dma map direction
  * for system pages. If write we map it bi-diretional; otherwise
  * DMA_TO_DEVICE
@@ -76,38 +113,41 @@ static void xe_mark_range_accessed(struct hmm_range *range, bool write)
  * Returns 0 if successful; -ENOMEM if fails to allocate memory
  */
 static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
-		       struct sg_table *st, bool write)
+		       struct sg_table *st,
+		       struct rw_semaphore *notifier_sem,
+		       bool write)
 {
+	unsigned long npages = xe_npages_in_range(range->start, range->end);
 	struct device *dev = xe->drm.dev;
-	struct page **pages;
-	u64 i, npages;
-	int ret;
+	struct scatterlist *sgl;
+	struct page *page;
+	unsigned long i, j;
 
-	npages = xe_npages_in_range(range->start, range->end);
-	pages = kvmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
-	if (!pages)
-		return -ENOMEM;
+	lockdep_assert_held(notifier_sem);
 
-	for (i = 0; i < npages; i++) {
-		pages[i] = hmm_pfn_to_page(range->hmm_pfns[i]);
-		xe_assert(xe, !is_device_private_page(pages[i]));
-	}
+	i = 0;
+	for_each_sg(st->sgl, sgl, st->nents, j) {
+		unsigned long hmm_pfn, size;
 
-	ret = sg_alloc_table_from_pages_segment(st, pages, npages, 0, npages << PAGE_SHIFT,
-						xe_sg_segment_size(dev), GFP_KERNEL);
-	if (ret)
-		goto free_pages;
+		hmm_pfn = range->hmm_pfns[i];
+		page = hmm_pfn_to_page(hmm_pfn);
+		xe_assert(xe, !is_device_private_page(page));
+
+		size = 1UL << hmm_pfn_to_map_order(hmm_pfn);
+		size -= page_to_pfn(page) & (size - 1);
+		i += size;
 
-	ret = dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
-			      DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
-	if (ret) {
-		sg_free_table(st);
-		st = NULL;
+		if (unlikely(j == st->nents - 1)) {
+			if (i > npages)
+				size -= (i - npages);
+			sg_mark_end(sgl);
+		}
+		sg_set_page(sgl, page, size << PAGE_SHIFT, 0);
 	}
+	xe_assert(xe, i == npages);
 
-free_pages:
-	kvfree(pages);
-	return ret;
+	return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
+			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
 }
 
 /**
@@ -237,16 +277,36 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 	if (ret)
 		goto free_pfns;
 
-	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt, write);
+	ret = xe_alloc_sg(vm->xe, &userptr->sgt, &hmm_range, &vm->userptr.notifier_lock);
 	if (ret)
 		goto free_pfns;
 
+	ret = down_read_interruptible(&vm->userptr.notifier_lock);
+	if (ret)
+		goto free_st;
+
+	if (mmu_interval_read_retry(hmm_range.notifier, hmm_range.notifier_seq)) {
+		ret = -EAGAIN;
+		goto out_unlock;
+	}
+
+	ret = xe_build_sg(vm->xe, &hmm_range, &userptr->sgt,
+			  &vm->userptr.notifier_lock, write);
+	if (ret)
+		goto out_unlock;
+
 	xe_mark_range_accessed(&hmm_range, write);
 	userptr->sg = &userptr->sgt;
 	userptr->notifier_seq = hmm_range.notifier_seq;
+	up_read(&vm->userptr.notifier_lock);
+	kvfree(pfns);
+	return 0;
 
+out_unlock:
+	up_read(&vm->userptr.notifier_lock);
+free_st:
+	sg_free_table(&userptr->sgt);
 free_pfns:
 	kvfree(pfns);
 	return ret;
 }
-

From 333b8906336174478efbbfc1e24a89e3397ffe65 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Tue, 4 Mar 2025 18:33:42 +0100
Subject: [PATCH 1625/2753] drm/xe/userptr: Unmap userptrs in the mmu notifier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If userptr pages are freed after a call to the xe mmu notifier,
the device will not be blocked out from theoretically accessing
these pages unless they are also unmapped from the iommu, and
this violates some aspects of the iommu-imposed security.

Ensure that userptrs are unmapped in the mmu notifier to
mitigate this. A naive attempt would try to free the sg table, but
the sg table itself may be accessed by a concurrent bind
operation, so settle for only unmapping.

v3:
- Update lockdep asserts.
- Fix a typo (Matthew Auld)

Fixes: 81e058a3e7fd ("drm/xe: Introduce helper to populate userptr")
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: <stable@vger.kernel.org> # v6.10+
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Acked-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304173342.22009-4-thomas.hellstrom@linux.intel.com
(cherry picked from commit ba767b9d01a2c552d76cf6f46b125d50ec4147a6)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c      | 51 ++++++++++++++++++++++++++------
 drivers/gpu/drm/xe/xe_hmm.h      |  2 ++
 drivers/gpu/drm/xe/xe_vm.c       |  4 +++
 drivers/gpu/drm/xe/xe_vm_types.h |  4 +++
 4 files changed, 52 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index be284b852307e..392102515f3d8 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -150,6 +150,45 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);
 }
 
+static void xe_hmm_userptr_set_mapped(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vm *vm = xe_vma_vm(&uvma->vma);
+
+	lockdep_assert_held_write(&vm->lock);
+	lockdep_assert_held(&vm->userptr.notifier_lock);
+
+	mutex_lock(&userptr->unmap_mutex);
+	xe_assert(vm->xe, !userptr->mapped);
+	userptr->mapped = true;
+	mutex_unlock(&userptr->unmap_mutex);
+}
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma)
+{
+	struct xe_userptr *userptr = &uvma->userptr;
+	struct xe_vma *vma = &uvma->vma;
+	bool write = !xe_vma_read_only(vma);
+	struct xe_vm *vm = xe_vma_vm(vma);
+	struct xe_device *xe = vm->xe;
+
+	if (!lockdep_is_held_type(&vm->userptr.notifier_lock, 0) &&
+	    !lockdep_is_held_type(&vm->lock, 0) &&
+	    !(vma->gpuva.flags & XE_VMA_DESTROYED)) {
+		/* Don't unmap in exec critical section. */
+		xe_vm_assert_held(vm);
+		/* Don't unmap while mapping the sg. */
+		lockdep_assert_held(&vm->lock);
+	}
+
+	mutex_lock(&userptr->unmap_mutex);
+	if (userptr->sg && userptr->mapped)
+		dma_unmap_sgtable(xe->drm.dev, userptr->sg,
+				  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
+	userptr->mapped = false;
+	mutex_unlock(&userptr->unmap_mutex);
+}
+
 /**
  * xe_hmm_userptr_free_sg() - Free the scatter gather table of userptr
  * @uvma: the userptr vma which hold the scatter gather table
@@ -161,16 +200,9 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma)
 {
 	struct xe_userptr *userptr = &uvma->userptr;
-	struct xe_vma *vma = &uvma->vma;
-	bool write = !xe_vma_read_only(vma);
-	struct xe_vm *vm = xe_vma_vm(vma);
-	struct xe_device *xe = vm->xe;
-	struct device *dev = xe->drm.dev;
-
-	xe_assert(xe, userptr->sg);
-	dma_unmap_sgtable(dev, userptr->sg,
-			  write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE, 0);
 
+	xe_assert(xe_vma_vm(&uvma->vma)->xe, userptr->sg);
+	xe_hmm_userptr_unmap(uvma);
 	sg_free_table(userptr->sg);
 	userptr->sg = NULL;
 }
@@ -297,6 +329,7 @@ int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma,
 
 	xe_mark_range_accessed(&hmm_range, write);
 	userptr->sg = &userptr->sgt;
+	xe_hmm_userptr_set_mapped(uvma);
 	userptr->notifier_seq = hmm_range.notifier_seq;
 	up_read(&vm->userptr.notifier_lock);
 	kvfree(pfns);
diff --git a/drivers/gpu/drm/xe/xe_hmm.h b/drivers/gpu/drm/xe/xe_hmm.h
index 9602cb7d976dd..0ea98d8e7bbc7 100644
--- a/drivers/gpu/drm/xe/xe_hmm.h
+++ b/drivers/gpu/drm/xe/xe_hmm.h
@@ -13,4 +13,6 @@ struct xe_userptr_vma;
 int xe_hmm_userptr_populate_range(struct xe_userptr_vma *uvma, bool is_mm_mmap_locked);
 
 void xe_hmm_userptr_free_sg(struct xe_userptr_vma *uvma);
+
+void xe_hmm_userptr_unmap(struct xe_userptr_vma *uvma);
 #endif
diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index d54aaa5eaff38..ec6ec18ab3faa 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -620,6 +620,8 @@ static void __vma_userptr_invalidate(struct xe_vm *vm, struct xe_userptr_vma *uv
 		err = xe_vm_invalidate_vma(vma);
 		XE_WARN_ON(err);
 	}
+
+	xe_hmm_userptr_unmap(uvma);
 }
 
 static bool vma_userptr_invalidate(struct mmu_interval_notifier *mni,
@@ -1039,6 +1041,7 @@ static struct xe_vma *xe_vma_create(struct xe_vm *vm,
 			INIT_LIST_HEAD(&userptr->invalidate_link);
 			INIT_LIST_HEAD(&userptr->repin_link);
 			vma->gpuva.gem.offset = bo_offset_or_userptr;
+			mutex_init(&userptr->unmap_mutex);
 
 			err = mmu_interval_notifier_insert(&userptr->notifier,
 							   current->mm,
@@ -1080,6 +1083,7 @@ static void xe_vma_destroy_late(struct xe_vma *vma)
 		 * them anymore
 		 */
 		mmu_interval_notifier_remove(&userptr->notifier);
+		mutex_destroy(&userptr->unmap_mutex);
 		xe_vm_put(vm);
 	} else if (xe_vma_is_null(vma)) {
 		xe_vm_put(vm);
diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h
index d2511819cdf43..a4b4091cfd0da 100644
--- a/drivers/gpu/drm/xe/xe_vm_types.h
+++ b/drivers/gpu/drm/xe/xe_vm_types.h
@@ -59,12 +59,16 @@ struct xe_userptr {
 	struct sg_table *sg;
 	/** @notifier_seq: notifier sequence number */
 	unsigned long notifier_seq;
+	/** @unmap_mutex: Mutex protecting dma-unmapping */
+	struct mutex unmap_mutex;
 	/**
 	 * @initial_bind: user pointer has been bound at least once.
 	 * write: vm->userptr.notifier_lock in read mode and vm->resv held.
 	 * read: vm->userptr.notifier_lock in write mode or vm->resv held.
 	 */
 	bool initial_bind;
+	/** @mapped: Whether the @sgt sg-table is dma-mapped. Protected by @unmap_mutex. */
+	bool mapped;
 #if IS_ENABLED(CONFIG_DRM_XE_USERPTR_INVAL_INJECT)
 	u32 divisor;
 #endif

From bcb0fda3c2da9fe4721d3e73d80e778c038e7d27 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Wed, 5 Mar 2025 14:03:34 -0700
Subject: [PATCH 1626/2753] io_uring/rw: ensure reissue path is correctly
 handled for IOPOLL

The IOPOLL path posts CQEs when the io_kiocb is marked as completed,
so it cannot rely on the usual retry that non-IOPOLL requests do for
read/write requests.

If -EAGAIN is received and the request should be retried, go through
the normal completion path and let the normal flush logic catch it and
reissue it, like what is done for !IOPOLL reads or writes.

Fixes: d803d123948f ("io_uring/rw: handle -EAGAIN retry at IO completion time")
Reported-by: John Garry <john.g.garry@oracle.com>
Link: https://lore.kernel.org/io-uring/2b43ccfa-644d-4a09-8f8f-39ad71810f41@oracle.com/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 io_uring/rw.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/io_uring/rw.c b/io_uring/rw.c
index 9edc6baebd01c..e5528cebcd066 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -560,11 +560,10 @@ static void io_complete_rw_iopoll(struct kiocb *kiocb, long res)
 	if (kiocb->ki_flags & IOCB_WRITE)
 		io_req_end_write(req);
 	if (unlikely(res != req->cqe.res)) {
-		if (res == -EAGAIN && io_rw_should_reissue(req)) {
+		if (res == -EAGAIN && io_rw_should_reissue(req))
 			req->flags |= REQ_F_REISSUE | REQ_F_BL_NO_RECYCLE;
-			return;
-		}
-		req->cqe.res = res;
+		else
+			req->cqe.res = res;
 	}
 
 	/* order with io_iopoll_complete() checking ->iopoll_completed */

From df08c94baafb001de6cf44bb7098bb557f36c335 Mon Sep 17 00:00:00 2001
From: Nicklas Bo Jensen <njensen@akamai.com>
Date: Thu, 27 Feb 2025 13:32:34 +0000
Subject: [PATCH 1627/2753] netfilter: nf_conncount: garbage collection is not
 skipped when jiffies wrap around

nf_conncount is supposed to skip garbage collection if it has already
run garbage collection in the same jiffy. Unfortunately, this is broken
when jiffies wrap around which this patch fixes.

The problem is that last_gc in the nf_conncount_list struct is an u32,
but jiffies is an unsigned long which is 8 bytes on my systems. When
those two are compared it only works until last_gc wraps around.

See bug report: https://bugzilla.netfilter.org/show_bug.cgi?id=1778
for more details.

Fixes: d265929930e2 ("netfilter: nf_conncount: reduce unnecessary GC")
Signed-off-by: Nicklas Bo Jensen <njensen@akamai.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index 4890af4dc263f..ebe38ed2e6f4f 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -132,7 +132,7 @@ static int __nf_conncount_add(struct net *net,
 	struct nf_conn *found_ct;
 	unsigned int collect = 0;
 
-	if (time_is_after_eq_jiffies((unsigned long)list->last_gc))
+	if ((u32)jiffies == list->last_gc)
 		goto add_new_node;
 
 	/* check the saved connections */
@@ -234,7 +234,7 @@ bool nf_conncount_gc_list(struct net *net,
 	bool ret = false;
 
 	/* don't bother if we just did GC */
-	if (time_is_after_eq_jiffies((unsigned long)READ_ONCE(list->last_gc)))
+	if ((u32)jiffies == READ_ONCE(list->last_gc))
 		return false;
 
 	/* don't bother if other cpu is already doing GC */

From 374908a15af4cd60862ebc51a6e012ace2212c76 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Mon, 3 Mar 2025 18:10:30 +0100
Subject: [PATCH 1628/2753] rust: remove leftover mentions of the `alloc` crate

In commit 392e34b6bc22 ("kbuild: rust: remove the `alloc` crate and
`GlobalAlloc`") we stopped using the upstream `alloc` crate.

Thus remove a few leftover mentions treewide.

Cc: stable@vger.kernel.org # Also to 6.12.y after the `alloc` backport lands
Fixes: 392e34b6bc22 ("kbuild: rust: remove the `alloc` crate and `GlobalAlloc`")
Reviewed-by: Danilo Krummrich <dakr@kernel.org>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250303171030.1081134-1-ojeda@kernel.org
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/quick-start.rst | 2 +-
 rust/kernel/lib.rs                 | 2 +-
 scripts/rustdoc_test_gen.rs        | 4 ++--
 3 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/Documentation/rust/quick-start.rst b/Documentation/rust/quick-start.rst
index 4aa50e5fcb8c0..6d2607870ba44 100644
--- a/Documentation/rust/quick-start.rst
+++ b/Documentation/rust/quick-start.rst
@@ -145,7 +145,7 @@ Rust standard library source
 ****************************
 
 The Rust standard library source is required because the build system will
-cross-compile ``core`` and ``alloc``.
+cross-compile ``core``.
 
 If ``rustup`` is being used, run::
 
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 398242f92a961..7697c60b2d1a6 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -6,7 +6,7 @@
 //! usage by Rust code in the kernel and is shared by all of them.
 //!
 //! In other words, all the rest of the Rust code in the kernel (e.g. kernel
-//! modules written in Rust) depends on [`core`], [`alloc`] and this crate.
+//! modules written in Rust) depends on [`core`] and this crate.
 //!
 //! If you need a kernel C API that is not ported or wrapped yet here, then
 //! do so first instead of bypassing this crate.
diff --git a/scripts/rustdoc_test_gen.rs b/scripts/rustdoc_test_gen.rs
index 5ebd42ae4a3fd..76aaa8329413d 100644
--- a/scripts/rustdoc_test_gen.rs
+++ b/scripts/rustdoc_test_gen.rs
@@ -15,8 +15,8 @@
 //!   - Test code should be able to define functions and call them, without having to carry
 //!     the context.
 //!
-//!   - Later on, we may want to be able to test non-kernel code (e.g. `core`, `alloc` or
-//!     third-party crates) which likely use the standard library `assert*!` macros.
+//!   - Later on, we may want to be able to test non-kernel code (e.g. `core` or third-party
+//!     crates) which likely use the standard library `assert*!` macros.
 //!
 //! For this reason, instead of the passed context, `kunit_get_current_test()` is used instead
 //! (i.e. `current->kunit_test`).

From df27cef153603b18a7d094b53cc3d5264ff32797 Mon Sep 17 00:00:00 2001
From: Benno Lossin <benno.lossin@proton.me>
Date: Wed, 5 Mar 2025 13:29:01 +0000
Subject: [PATCH 1629/2753] rust: init: fix `Zeroable` implementation for
 `Option<NonNull<T>>` and `Option<KBox<T>>`

According to [1], `NonNull<T>` and `#[repr(transparent)]` wrapper types
such as our custom `KBox<T>` have the null pointer optimization only if
`T: Sized`. Thus remove the `Zeroable` implementation for the unsized
case.

Link: https://doc.rust-lang.org/stable/std/option/index.html#representation [1]
Reported-by: Alice Ryhl <aliceryhl@google.com>
Closes: https://lore.kernel.org/rust-for-linux/CAH5fLghL+qzrD8KiCF1V3vf2YcC6aWySzkmaE2Zzrnh1gKj-hw@mail.gmail.com/
Cc: stable@vger.kernel.org # v6.12+ (a custom patch will be needed for 6.6.y)
Fixes: 38cde0bd7b67 ("rust: init: add `Zeroable` trait and `init::zeroed` function")
Signed-off-by: Benno Lossin <benno.lossin@proton.me>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250305132836.2145476-1-benno.lossin@proton.me
[ Added Closes tag and moved up the Reported-by one. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/init.rs | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 7fd1ea8265a55..8bbd5e3398fcb 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -1418,17 +1418,14 @@ impl_zeroable! {
     // SAFETY: `T: Zeroable` and `UnsafeCell` is `repr(transparent)`.
     {<T: ?Sized + Zeroable>} UnsafeCell<T>,
 
-    // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee).
+    // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee:
+    // https://doc.rust-lang.org/stable/std/option/index.html#representation).
     Option<NonZeroU8>, Option<NonZeroU16>, Option<NonZeroU32>, Option<NonZeroU64>,
     Option<NonZeroU128>, Option<NonZeroUsize>,
     Option<NonZeroI8>, Option<NonZeroI16>, Option<NonZeroI32>, Option<NonZeroI64>,
     Option<NonZeroI128>, Option<NonZeroIsize>,
-
-    // SAFETY: All zeros is equivalent to `None` (option layout optimization guarantee).
-    //
-    // In this case we are allowed to use `T: ?Sized`, since all zeros is the `None` variant.
-    {<T: ?Sized>} Option<NonNull<T>>,
-    {<T: ?Sized>} Option<KBox<T>>,
+    {<T>} Option<NonNull<T>>,
+    {<T>} Option<KBox<T>>,
 
     // SAFETY: `null` pointer is valid.
     //

From ff64846bee0e7e3e7bc9363ebad3bab42dd27e24 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Thu, 13 Feb 2025 06:34:18 -0500
Subject: [PATCH 1630/2753] rust: alloc: satisfy POSIX alignment requirement

ISO C's `aligned_alloc` is partially implementation-defined; on some
systems it inherits stricter requirements from POSIX's `posix_memalign`.

This causes the call added in commit dd09538fb409 ("rust: alloc:
implement `Cmalloc` in module allocator_test") to fail on macOS because
it doesn't meet the requirements of `posix_memalign`.

Adjust the call to meet the POSIX requirement and add a comment. This
fixes failures in `make rusttest` on macOS.

Acked-by: Danilo Krummrich <dakr@kernel.org>
Cc: stable@vger.kernel.org
Fixes: dd09538fb409 ("rust: alloc: implement `Cmalloc` in module allocator_test")
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Link: https://lore.kernel.org/r/20250213-aligned-alloc-v7-1-d2a2d0be164b@gmail.com
[ Added Cc: stable. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/alloc/allocator_test.rs | 18 ++++++++++++++++++
 1 file changed, 18 insertions(+)

diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs
index e3240d16040bd..c37d4c0c64e9f 100644
--- a/rust/kernel/alloc/allocator_test.rs
+++ b/rust/kernel/alloc/allocator_test.rs
@@ -62,6 +62,24 @@ unsafe impl Allocator for Cmalloc {
             ));
         }
 
+        // ISO C (ISO/IEC 9899:2011) defines `aligned_alloc`:
+        //
+        // > The value of alignment shall be a valid alignment supported by the implementation
+        // [...].
+        //
+        // As an example of the "supported by the implementation" requirement, POSIX.1-2001 (IEEE
+        // 1003.1-2001) defines `posix_memalign`:
+        //
+        // > The value of alignment shall be a power of two multiple of sizeof (void *).
+        //
+        // and POSIX-based implementations of `aligned_alloc` inherit this requirement. At the time
+        // of writing, this is known to be the case on macOS (but not in glibc).
+        //
+        // Satisfy the stricter requirement to avoid spurious test failures on some platforms.
+        let min_align = core::mem::size_of::<*const crate::ffi::c_void>();
+        let layout = layout.align_to(min_align).map_err(|_| AllocError)?;
+        let layout = layout.pad_to_align();
+
         // SAFETY: Returns either NULL or a pointer to a memory allocation that satisfies or
         // exceeds the given size and alignment requirements.
         let dst = unsafe { libc_aligned_alloc(layout.align(), layout.size()) } as *mut u8;

From f2e413f00ebec10a8725b1b75b1b523c561bd403 Mon Sep 17 00:00:00 2001
From: Alban Kurti <kurti@invicto.ai>
Date: Thu, 6 Feb 2025 21:07:52 +0000
Subject: [PATCH 1631/2753] rust: docs: add missing newline to printing macro
 examples

Fix adding a newline at the end of the usage of pr_info! in the
documentation

Fixes: e3c3d34507c7 ("docs: rust: Add description of Rust documentation test as KUnit ones")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Reviewed-by: David Gow <davidgow@google.com>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-1-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 Documentation/rust/testing.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/rust/testing.rst b/Documentation/rust/testing.rst
index 568b71b415a45..180b886e0f1ee 100644
--- a/Documentation/rust/testing.rst
+++ b/Documentation/rust/testing.rst
@@ -97,7 +97,7 @@ operator are also supported as usual, e.g.:
 
 	/// ```
 	/// # use kernel::{spawn_work_item, workqueue};
-	/// spawn_work_item!(workqueue::system(), || pr_info!("x"))?;
+	/// spawn_work_item!(workqueue::system(), || pr_info!("x\n"))?;
 	/// # Ok::<(), Error>(())
 	/// ```
 

From 6f5c36f56d475732981dcf624e0ac0cc7c8984c8 Mon Sep 17 00:00:00 2001
From: Alban Kurti <kurti@invicto.ai>
Date: Thu, 6 Feb 2025 21:07:53 +0000
Subject: [PATCH 1632/2753] rust: error: add missing newline to pr_warn! calls

Added missing newline at the end of pr_warn! usage
so the log is not missed.

Fixes: 6551a7fe0acb ("rust: error: Add Error::from_errno{_unchecked}()")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-2-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/error.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/error.rs b/rust/kernel/error.rs
index f6ecf09cb65f4..a194d83e6835c 100644
--- a/rust/kernel/error.rs
+++ b/rust/kernel/error.rs
@@ -107,7 +107,7 @@ impl Error {
         } else {
             // TODO: Make it a `WARN_ONCE` once available.
             crate::pr_warn!(
-                "attempted to create `Error` with out of range `errno`: {}",
+                "attempted to create `Error` with out of range `errno`: {}\n",
                 errno
             );
             code::EINVAL

From b63263555eaafbf9ab1a82f2020bbee872d83759 Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:17 +0800
Subject: [PATCH 1633/2753] net: phylink: use pl->link_interface in
 phylink_expects_phy()

The phylink_expects_phy() function allows MAC drivers to check if they are
expecting a PHY to attach. The checking condition in phylink_expects_phy()
aims to achieve the same result as the checking condition in
phylink_attach_phy().

However, the checking condition in phylink_expects_phy() uses
pl->link_config.interface, while phylink_attach_phy() uses
pl->link_interface.

Initially, both pl->link_interface and pl->link_config.interface are set
to SGMII, and pl->cfg_link_an_mode is set to MLO_AN_INBAND.

When the interface switches from SGMII to 2500BASE-X,
pl->link_config.interface is updated by phylink_major_config().
At this point, pl->cfg_link_an_mode remains MLO_AN_INBAND, and
pl->link_config.interface is set to 2500BASE-X.
Subsequently, when the STMMAC interface is taken down
administratively and brought back up, it is blocked by
phylink_expects_phy().

Since phylink_expects_phy() and phylink_attach_phy() aim to achieve the
same result, phylink_expects_phy() should check pl->link_interface,
which never changes, instead of pl->link_config.interface, which is
updated by phylink_major_config().

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-2-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index a3b186ab38546..a3f64b6d2d34e 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2044,7 +2044,7 @@ bool phylink_expects_phy(struct phylink *pl)
 {
 	if (pl->cfg_link_an_mode == MLO_AN_FIXED ||
 	    (pl->cfg_link_an_mode == MLO_AN_INBAND &&
-	     phy_interface_mode_is_8023z(pl->link_config.interface)))
+	     phy_interface_mode_is_8023z(pl->link_interface)))
 		return false;
 	return true;
 }

From 065d3cef99a10385d1c82919a612722dfdac90cc Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:18 +0800
Subject: [PATCH 1634/2753] net: pcs: xpcs: re-initiate clause 37
 Auto-negotiation

The xpcs_switch_interface_mode function was introduced to handle
interface switching.

According to the XPCS datasheet, a soft reset is required to initiate
Clause 37 auto-negotiation when the XPCS switches interface modes.

When the interface mode switches from 2500BASE-X to SGMII,
re-initiating Clause 37 auto-negotiation is required for the SGMII
interface mode to function properly.

Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-3-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pcs/pcs-xpcs.c | 25 +++++++++++++++++++++----
 1 file changed, 21 insertions(+), 4 deletions(-)

diff --git a/drivers/net/pcs/pcs-xpcs.c b/drivers/net/pcs/pcs-xpcs.c
index e32dec4b812ec..3d1bd5aac0937 100644
--- a/drivers/net/pcs/pcs-xpcs.c
+++ b/drivers/net/pcs/pcs-xpcs.c
@@ -602,12 +602,33 @@ static void xpcs_get_interfaces(struct dw_xpcs *xpcs, unsigned long *interfaces)
 		__set_bit(compat->interface, interfaces);
 }
 
+static int xpcs_switch_interface_mode(struct dw_xpcs *xpcs,
+				      phy_interface_t interface)
+{
+	int ret = 0;
+
+	if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID) {
+		ret = txgbe_xpcs_switch_mode(xpcs, interface);
+	} else if (xpcs->interface != interface) {
+		if (interface == PHY_INTERFACE_MODE_SGMII)
+			xpcs->need_reset = true;
+		xpcs->interface = interface;
+	}
+
+	return ret;
+}
+
 static void xpcs_pre_config(struct phylink_pcs *pcs, phy_interface_t interface)
 {
 	struct dw_xpcs *xpcs = phylink_pcs_to_xpcs(pcs);
 	const struct dw_xpcs_compat *compat;
 	int ret;
 
+	ret = xpcs_switch_interface_mode(xpcs, interface);
+	if (ret)
+		dev_err(&xpcs->mdiodev->dev, "switch interface failed: %pe\n",
+			ERR_PTR(ret));
+
 	if (!xpcs->need_reset)
 		return;
 
@@ -799,10 +820,6 @@ static int xpcs_do_config(struct dw_xpcs *xpcs, phy_interface_t interface,
 		return -ENODEV;
 
 	if (xpcs->info.pma == WX_TXGBE_XPCS_PMA_10G_ID) {
-		ret = txgbe_xpcs_switch_mode(xpcs, interface);
-		if (ret)
-			return ret;
-
 		/* Wangxun devices need backplane CL37 AN enabled for
 		 * SGMII and 1000base-X
 		 */

From 7e2f7e25f6ffc229fd5be0488e1d8aac7bdd80e8 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:19 +0800
Subject: [PATCH 1635/2753] arch: x86: add IPC mailbox accessor function and
 add SoC register access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Exports intel_pmc_ipc() for host access to the PMC IPC mailbox
- Enables the host to access specific SoC registers through the PMC
firmware using IPC commands. This access method is necessary for
registers that are not available through direct Memory-Mapped I/O (MMIO),
which is used for other accessible parts of the PMC.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Signed-off-by: Chao Qin <chao.qin@intel.com>
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-4-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS                                   |  1 +
 .../linux/platform_data/x86/intel_pmc_ipc.h   | 94 +++++++++++++++++++
 2 files changed, 95 insertions(+)
 create mode 100644 include/linux/platform_data/x86/intel_pmc_ipc.h

diff --git a/MAINTAINERS b/MAINTAINERS
index 7078199fcebf2..2eccaff95ca2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11862,6 +11862,7 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-platform-intel-pmc
 F:	drivers/platform/x86/intel/pmc/
+F:	linux/platform_data/x86/intel_pmc_ipc.h
 
 INTEL PMIC GPIO DRIVERS
 M:	Andy Shevchenko <andy@kernel.org>
diff --git a/include/linux/platform_data/x86/intel_pmc_ipc.h b/include/linux/platform_data/x86/intel_pmc_ipc.h
new file mode 100644
index 0000000000000..6e603a8c075f9
--- /dev/null
+++ b/include/linux/platform_data/x86/intel_pmc_ipc.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Intel Core SoC Power Management Controller Header File
+ *
+ * Copyright (c) 2025, Intel Corporation.
+ * All Rights Reserved.
+ *
+ */
+#ifndef INTEL_PMC_IPC_H
+#define INTEL_PMC_IPC_H
+#include <linux/acpi.h>
+
+#define IPC_SOC_REGISTER_ACCESS			0xAA
+#define IPC_SOC_SUB_CMD_READ			0x00
+#define IPC_SOC_SUB_CMD_WRITE			0x01
+#define PMC_IPCS_PARAM_COUNT			7
+#define VALID_IPC_RESPONSE			5
+
+struct pmc_ipc_cmd {
+	u32 cmd;
+	u32 sub_cmd;
+	u32 size;
+	u32 wbuf[4];
+};
+
+struct pmc_ipc_rbuf {
+	u32 buf[4];
+};
+
+/**
+ * intel_pmc_ipc() - PMC IPC Mailbox accessor
+ * @ipc_cmd:  Prepared input command to send
+ * @rbuf:     Allocated array for returned IPC data
+ *
+ * Return: 0 on success. Non-zero on mailbox error
+ */
+static inline int intel_pmc_ipc(struct pmc_ipc_cmd *ipc_cmd, struct pmc_ipc_rbuf *rbuf)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object params[PMC_IPCS_PARAM_COUNT] = {
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+		{.type = ACPI_TYPE_INTEGER,},
+	};
+	struct acpi_object_list arg_list = { PMC_IPCS_PARAM_COUNT, params };
+	union acpi_object *obj;
+	int status;
+
+	if (!ipc_cmd || !rbuf)
+		return -EINVAL;
+
+	/*
+	 * 0: IPC Command
+	 * 1: IPC Sub Command
+	 * 2: Size
+	 * 3-6: Write Buffer for offset
+	 */
+	params[0].integer.value = ipc_cmd->cmd;
+	params[1].integer.value = ipc_cmd->sub_cmd;
+	params[2].integer.value = ipc_cmd->size;
+	params[3].integer.value = ipc_cmd->wbuf[0];
+	params[4].integer.value = ipc_cmd->wbuf[1];
+	params[5].integer.value = ipc_cmd->wbuf[2];
+	params[6].integer.value = ipc_cmd->wbuf[3];
+
+	status = acpi_evaluate_object(NULL, "\\IPCS", &arg_list, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	obj = buffer.pointer;
+
+	if (obj && obj->type == ACPI_TYPE_PACKAGE &&
+	    obj->package.count == VALID_IPC_RESPONSE) {
+		const union acpi_object *objs = obj->package.elements;
+
+		if ((u8)objs[0].integer.value != 0)
+			return -EINVAL;
+
+		rbuf->buf[0] = objs[1].integer.value;
+		rbuf->buf[1] = objs[2].integer.value;
+		rbuf->buf[2] = objs[3].integer.value;
+		rbuf->buf[3] = objs[4].integer.value;
+	} else {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+#endif /* INTEL_PMC_IPC_H */

From e654cfc718d451bdf6c1554efc945171239f03f5 Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:20 +0800
Subject: [PATCH 1636/2753] net: stmmac: configure SerDes on mac_finish

SerDes will configure according to the provided interface mode after
finish a major reconfiguration of the interface mode.

Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-5-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 13 +++++++++++++
 include/linux/stmmac.h                            |  4 ++++
 2 files changed, 17 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index aec230353ac48..1a928e21b2865 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1129,6 +1129,18 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 	return 0;
 }
 
+static int stmmac_mac_finish(struct phylink_config *config, unsigned int mode,
+			     phy_interface_t interface)
+{
+	struct net_device *ndev = to_net_dev(config->dev);
+	struct stmmac_priv *priv = netdev_priv(ndev);
+
+	if (priv->plat->mac_finish)
+		priv->plat->mac_finish(ndev, priv->plat->bsp_priv, mode, interface);
+
+	return 0;
+}
+
 static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
 	.mac_get_caps = stmmac_mac_get_caps,
 	.mac_select_pcs = stmmac_mac_select_pcs,
@@ -1137,6 +1149,7 @@ static const struct phylink_mac_ops stmmac_phylink_mac_ops = {
 	.mac_link_up = stmmac_mac_link_up,
 	.mac_disable_tx_lpi = stmmac_mac_disable_tx_lpi,
 	.mac_enable_tx_lpi = stmmac_mac_enable_tx_lpi,
+	.mac_finish = stmmac_mac_finish,
 };
 
 /**
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index cd0d1383df872..b6f03ab125957 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -239,6 +239,10 @@ struct plat_stmmacenet_data {
 	int (*serdes_powerup)(struct net_device *ndev, void *priv);
 	void (*serdes_powerdown)(struct net_device *ndev, void *priv);
 	void (*speed_mode_2500)(struct net_device *ndev, void *priv);
+	int (*mac_finish)(struct net_device *ndev,
+			  void *priv,
+			  unsigned int mode,
+			  phy_interface_t interface);
 	void (*ptp_clk_freq_config)(struct stmmac_priv *priv);
 	int (*init)(struct platform_device *pdev, void *priv);
 	void (*exit)(struct platform_device *pdev, void *priv);

From a42f6b3f1cc164781af144a71684d50b2d7d36f2 Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:21 +0800
Subject: [PATCH 1637/2753] net: stmmac: configure SerDes according to the
 interface mode

Intel platform will configure the SerDes through PMC API based on the
provided interface mode.

This patch adds several new functions below:-
- intel_tsn_lane_is_available(): This new function reads FIA lane
  ownership registers and common lane registers through IPC commands
  to know which lane the mGbE port is assigned to.
- intel_mac_finish(): To configure the SerDes based on the assigned
  lane and latest interface mode, it sends IPC command to the PMC through
  PMC driver/API. The PMC acts as a proxy for R/W on behalf of the driver.
- intel_set_reg_access(): Set the register access to the available TSN
  interface.

Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-6-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig   |   1 +
 .../net/ethernet/stmicro/stmmac/dwmac-intel.c | 179 +++++++++++++++++-
 .../net/ethernet/stmicro/stmmac/dwmac-intel.h |  29 +++
 3 files changed, 204 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index 4cc85a36a1ab6..c5f94a67b3f2f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -307,6 +307,7 @@ config DWMAC_INTEL
 	default X86
 	depends on X86 && STMMAC_ETH && PCI
 	depends on COMMON_CLK
+	depends on ACPI
 	help
 	  This selects the Intel platform specific bus support for the
 	  stmmac driver. This driver is used for Intel Quark/EHL/TGL.
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 48acba5eb178e..f73a48f985819 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -5,15 +5,30 @@
 #include <linux/clk-provider.h>
 #include <linux/pci.h>
 #include <linux/dmi.h>
+#include <linux/platform_data/x86/intel_pmc_ipc.h>
 #include "dwmac-intel.h"
 #include "dwmac4.h"
 #include "stmmac.h"
 #include "stmmac_ptp.h"
 
+struct pmc_serdes_regs {
+	u8 index;
+	u32 val;
+};
+
+struct pmc_serdes_reg_info {
+	const struct pmc_serdes_regs *regs;
+	u8 num_regs;
+};
+
 struct intel_priv_data {
 	int mdio_adhoc_addr;	/* mdio address for serdes & etc */
 	unsigned long crossts_adj;
 	bool is_pse;
+	const int *tsn_lane_regs;
+	int max_tsn_lane_regs;
+	struct pmc_serdes_reg_info pid_1g;
+	struct pmc_serdes_reg_info pid_2p5g;
 };
 
 /* This struct is used to associate PCI Function of MAC controller on a board,
@@ -35,6 +50,44 @@ struct stmmac_pci_info {
 	int (*setup)(struct pci_dev *pdev, struct plat_stmmacenet_data *plat);
 };
 
+static const struct pmc_serdes_regs pid_modphy3_1g_regs[] = {
+	{ PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_1G },
+	{ PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_1G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy3_2p5g_regs[] = {
+	{ PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_2P5G },
+	{ PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy1_1g_regs[] = {
+	{ PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_1G },
+	{ PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_1G },
+	{}
+};
+
+static const struct pmc_serdes_regs pid_modphy1_2p5g_regs[] = {
+	{ PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0,	B_MODPHY_PCR_LCPLL_DWORD0_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2,	N_MODPHY_PCR_LCPLL_DWORD2_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7,	N_MODPHY_PCR_LCPLL_DWORD7_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10,	N_MODPHY_PCR_LPPLL_DWORD10_2P5G },
+	{ PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30,	N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G },
+	{}
+};
+
+static const int ehl_tsn_lane_regs[] = {7, 8, 9, 10, 11};
+
 static int stmmac_pci_find_phy_addr(struct pci_dev *pdev,
 				    const struct dmi_system_id *dmi_list)
 {
@@ -93,7 +146,7 @@ static int intel_serdes_powerup(struct net_device *ndev, void *priv_data)
 	data &= ~SERDES_RATE_MASK;
 	data &= ~SERDES_PCLK_MASK;
 
-	if (priv->plat->max_speed == 2500)
+	if (priv->plat->phy_interface == PHY_INTERFACE_MODE_2500BASEX)
 		data |= SERDES_RATE_PCIE_GEN2 << SERDES_RATE_PCIE_SHIFT |
 			SERDES_PCLK_37p5MHZ << SERDES_PCLK_SHIFT;
 	else
@@ -415,6 +468,95 @@ static void intel_mgbe_pse_crossts_adj(struct intel_priv_data *intel_priv,
 	}
 }
 
+static int intel_tsn_lane_is_available(struct net_device *ndev,
+				       struct intel_priv_data *intel_priv)
+{
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	struct pmc_ipc_cmd tmp = {};
+	struct pmc_ipc_rbuf rbuf = {};
+	int ret = 0, i, j;
+	const int max_fia_regs = 5;
+
+	tmp.cmd = IPC_SOC_REGISTER_ACCESS;
+	tmp.sub_cmd = IPC_SOC_SUB_CMD_READ;
+
+	for (i = 0; i < max_fia_regs; i++) {
+		tmp.wbuf[0] = R_PCH_FIA_15_PCR_LOS1_REG_BASE + i;
+
+		ret = intel_pmc_ipc(&tmp, &rbuf);
+		if (ret < 0) {
+			netdev_info(priv->dev, "Failed to read from PMC.\n");
+			return ret;
+		}
+
+		for (j = 0; j <= intel_priv->max_tsn_lane_regs; j++)
+			if ((rbuf.buf[0] >>
+				(4 * (intel_priv->tsn_lane_regs[j] % 8)) &
+					B_PCH_FIA_PCR_L0O) == 0xB)
+				return ret;
+	}
+
+	return ret;
+}
+
+static int intel_set_reg_access(const struct pmc_serdes_regs *regs, int max_regs)
+{
+	int ret = 0, i;
+
+	for (i = 0; i < max_regs; i++) {
+		struct pmc_ipc_cmd tmp = {};
+		struct pmc_ipc_rbuf rbuf = {};
+
+		tmp.cmd = IPC_SOC_REGISTER_ACCESS;
+		tmp.sub_cmd = IPC_SOC_SUB_CMD_WRITE;
+		tmp.wbuf[0] = (u32)regs[i].index;
+		tmp.wbuf[1] = regs[i].val;
+
+		ret = intel_pmc_ipc(&tmp, &rbuf);
+		if (ret < 0)
+			return ret;
+	}
+
+	return ret;
+}
+
+static int intel_mac_finish(struct net_device *ndev,
+			    void *intel_data,
+			    unsigned int mode,
+			    phy_interface_t interface)
+{
+	struct intel_priv_data *intel_priv = intel_data;
+	struct stmmac_priv *priv = netdev_priv(ndev);
+	const struct pmc_serdes_regs *regs;
+	int max_regs = 0;
+	int ret = 0;
+
+	ret = intel_tsn_lane_is_available(ndev, intel_priv);
+	if (ret < 0) {
+		netdev_info(priv->dev, "No TSN lane available to set the registers.\n");
+		return ret;
+	}
+
+	if (interface == PHY_INTERFACE_MODE_2500BASEX) {
+		regs = intel_priv->pid_2p5g.regs;
+		max_regs = intel_priv->pid_2p5g.num_regs;
+	} else {
+		regs = intel_priv->pid_1g.regs;
+		max_regs = intel_priv->pid_1g.num_regs;
+	}
+
+	ret = intel_set_reg_access(regs, max_regs);
+	if (ret < 0)
+		return ret;
+
+	priv->plat->phy_interface = interface;
+
+	intel_serdes_powerdown(ndev, intel_priv);
+	intel_serdes_powerup(ndev, intel_priv);
+
+	return ret;
+}
+
 static void common_default_data(struct plat_stmmacenet_data *plat)
 {
 	plat->clk_csr = 2;	/* clk_csr_i = 20-35MHz & MDC = clk_csr_i/16 */
@@ -624,6 +766,8 @@ static int intel_mgbe_common_data(struct pci_dev *pdev,
 static int ehl_common_data(struct pci_dev *pdev,
 			   struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->rx_queues_to_use = 8;
 	plat->tx_queues_to_use = 8;
 	plat->flags |= STMMAC_FLAG_USE_PHY_WOL;
@@ -639,20 +783,29 @@ static int ehl_common_data(struct pci_dev *pdev,
 	plat->safety_feat_cfg->prtyen = 0;
 	plat->safety_feat_cfg->tmouten = 0;
 
+	intel_priv->tsn_lane_regs = ehl_tsn_lane_regs;
+	intel_priv->max_tsn_lane_regs = ARRAY_SIZE(ehl_tsn_lane_regs);
+
 	return intel_mgbe_common_data(pdev, plat);
 }
 
 static int ehl_sgmii_data(struct pci_dev *pdev,
 			  struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->bus_id = 1;
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
-
+	plat->mac_finish = intel_mac_finish;
 	plat->clk_ptp_rate = 204800000;
 
+	intel_priv->pid_1g.regs = pid_modphy3_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy3_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy3_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy3_2p5g_regs);
+
 	return ehl_common_data(pdev, plat);
 }
 
@@ -705,10 +858,18 @@ static struct stmmac_pci_info ehl_pse0_rgmii1g_info = {
 static int ehl_pse0_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
 	return ehl_pse0_common_data(pdev, plat);
 }
 
@@ -746,10 +907,18 @@ static struct stmmac_pci_info ehl_pse1_rgmii1g_info = {
 static int ehl_pse1_sgmii1g_data(struct pci_dev *pdev,
 				 struct plat_stmmacenet_data *plat)
 {
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
 	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
-	plat->speed_mode_2500 = intel_speed_mode_2500;
 	plat->serdes_powerup = intel_serdes_powerup;
 	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
 	return ehl_pse1_common_data(pdev, plat);
 }
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
index 0a37987478c15..a12f8e65f89f1 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.h
@@ -50,4 +50,33 @@
 #define PCH_PTP_CLK_FREQ_19_2MHZ	(GMAC_GPO0)
 #define PCH_PTP_CLK_FREQ_200MHZ		(0)
 
+/* Modphy Register index */
+#define R_PCH_FIA_15_PCR_LOS1_REG_BASE			8
+#define R_PCH_FIA_15_PCR_LOS2_REG_BASE			9
+#define R_PCH_FIA_15_PCR_LOS3_REG_BASE			10
+#define R_PCH_FIA_15_PCR_LOS4_REG_BASE			11
+#define R_PCH_FIA_15_PCR_LOS5_REG_BASE			12
+#define B_PCH_FIA_PCR_L0O				GENMASK(3, 0)
+#define PID_MODPHY1_B_MODPHY_PCR_LCPLL_DWORD0		13
+#define PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD2		14
+#define PID_MODPHY1_N_MODPHY_PCR_LCPLL_DWORD7		15
+#define PID_MODPHY1_N_MODPHY_PCR_LPPLL_DWORD10		16
+#define PID_MODPHY1_N_MODPHY_PCR_CMN_ANA_DWORD30	17
+#define PID_MODPHY3_B_MODPHY_PCR_LCPLL_DWORD0		18
+#define PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD2		19
+#define PID_MODPHY3_N_MODPHY_PCR_LCPLL_DWORD7		20
+#define PID_MODPHY3_N_MODPHY_PCR_LPPLL_DWORD10		21
+#define PID_MODPHY3_N_MODPHY_PCR_CMN_ANA_DWORD30	22
+
+#define B_MODPHY_PCR_LCPLL_DWORD0_1G		0x46AAAA41
+#define N_MODPHY_PCR_LCPLL_DWORD2_1G		0x00000139
+#define N_MODPHY_PCR_LCPLL_DWORD7_1G		0x002A0003
+#define N_MODPHY_PCR_LPPLL_DWORD10_1G		0x00170008
+#define N_MODPHY_PCR_CMN_ANA_DWORD30_1G		0x0000D4AC
+#define B_MODPHY_PCR_LCPLL_DWORD0_2P5G		0x58555551
+#define N_MODPHY_PCR_LCPLL_DWORD2_2P5G		0x0000012D
+#define N_MODPHY_PCR_LCPLL_DWORD7_2P5G		0x001F0003
+#define N_MODPHY_PCR_LPPLL_DWORD10_2P5G		0x00170008
+#define N_MODPHY_PCR_CMN_ANA_DWORD30_2P5G	0x8200ACAC
+
 #endif /* __DWMAC_INTEL_H__ */

From 7598ef621a43f0c8d4c2d0e6220c484bdb7b3ee7 Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Thu, 27 Feb 2025 20:15:22 +0800
Subject: [PATCH 1638/2753] net: stmmac: interface switching support for ADL-N
 platform

The intel_config_serdes function was provided to handle interface mode
changes for the ADL-N platform.

The Modphy register lane was provided to configure the serdes when
changing interface modes.

Signed-off-by: Michael Sit Wei Hong <michael.wei.hong.sit@intel.com>
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Link: https://patch.msgid.link/20250227121522.1802832-7-yong.liang.choong@linux.intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/dwmac-intel.c | 52 ++++++++++++++++++-
 1 file changed, 51 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index f73a48f985819..9c8de47ee149f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -87,6 +87,7 @@ static const struct pmc_serdes_regs pid_modphy1_2p5g_regs[] = {
 };
 
 static const int ehl_tsn_lane_regs[] = {7, 8, 9, 10, 11};
+static const int adln_tsn_lane_regs[] = {6};
 
 static int stmmac_pci_find_phy_addr(struct pci_dev *pdev,
 				    const struct dmi_system_id *dmi_list)
@@ -1004,6 +1005,55 @@ static int adls_sgmii_phy1_data(struct pci_dev *pdev,
 static struct stmmac_pci_info adls_sgmii1g_phy1_info = {
 	.setup = adls_sgmii_phy1_data,
 };
+
+static int adln_common_data(struct pci_dev *pdev,
+			    struct plat_stmmacenet_data *plat)
+{
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
+	plat->rx_queues_to_use = 6;
+	plat->tx_queues_to_use = 4;
+	plat->clk_ptp_rate = 204800000;
+
+	plat->safety_feat_cfg->tsoee = 1;
+	plat->safety_feat_cfg->mrxpee = 0;
+	plat->safety_feat_cfg->mestee = 1;
+	plat->safety_feat_cfg->mrxee = 1;
+	plat->safety_feat_cfg->mtxee = 1;
+	plat->safety_feat_cfg->epsi = 0;
+	plat->safety_feat_cfg->edpp = 0;
+	plat->safety_feat_cfg->prtyen = 0;
+	plat->safety_feat_cfg->tmouten = 0;
+
+	intel_priv->tsn_lane_regs = adln_tsn_lane_regs;
+	intel_priv->max_tsn_lane_regs = ARRAY_SIZE(adln_tsn_lane_regs);
+
+	return intel_mgbe_common_data(pdev, plat);
+}
+
+static int adln_sgmii_phy0_data(struct pci_dev *pdev,
+				struct plat_stmmacenet_data *plat)
+{
+	struct intel_priv_data *intel_priv = plat->bsp_priv;
+
+	plat->bus_id = 1;
+	plat->phy_interface = PHY_INTERFACE_MODE_SGMII;
+	plat->serdes_powerup = intel_serdes_powerup;
+	plat->serdes_powerdown = intel_serdes_powerdown;
+	plat->mac_finish = intel_mac_finish;
+
+	intel_priv->pid_1g.regs = pid_modphy1_1g_regs;
+	intel_priv->pid_1g.num_regs = ARRAY_SIZE(pid_modphy1_1g_regs);
+	intel_priv->pid_2p5g.regs = pid_modphy1_2p5g_regs;
+	intel_priv->pid_2p5g.num_regs = ARRAY_SIZE(pid_modphy1_2p5g_regs);
+
+	return adln_common_data(pdev, plat);
+}
+
+static struct stmmac_pci_info adln_sgmii1g_phy0_info = {
+	.setup = adln_sgmii_phy0_data,
+};
+
 static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = {
 	{
 		.func = 6,
@@ -1386,7 +1436,7 @@ static const struct pci_device_id intel_eth_pci_id_table[] = {
 	{ PCI_DEVICE_DATA(INTEL, TGLH_SGMII1G_1, &tgl_sgmii1g_phy1_info) },
 	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_0, &adls_sgmii1g_phy0_info) },
 	{ PCI_DEVICE_DATA(INTEL, ADLS_SGMII1G_1, &adls_sgmii1g_phy1_info) },
-	{ PCI_DEVICE_DATA(INTEL, ADLN_SGMII1G, &tgl_sgmii1g_phy0_info) },
+	{ PCI_DEVICE_DATA(INTEL, ADLN_SGMII1G, &adln_sgmii1g_phy0_info) },
 	{ PCI_DEVICE_DATA(INTEL, RPLP_SGMII1G, &tgl_sgmii1g_phy0_info) },
 	{}
 };

From 61dc9cae8727ea422e1fcbcc37a3d9ba2ff51c91 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:14:02 +0100
Subject: [PATCH 1639/2753] net: phy: move PHY package code from phy_device.c
 to own source file

This patch is the first step in moving the PHY package related code
to its own source file. No functional change intended.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/57df5c19-fbcd-45a7-9afd-cd4f74d7fa76@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/Makefile      |   3 +-
 drivers/net/phy/phy_device.c  | 237 ---------------------------------
 drivers/net/phy/phy_package.c | 244 ++++++++++++++++++++++++++++++++++
 3 files changed, 246 insertions(+), 238 deletions(-)
 create mode 100644 drivers/net/phy/phy_package.c

diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index c8dac6e922780..8f9ba5e8290de 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -2,7 +2,8 @@
 # Makefile for Linux PHY drivers
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
-				   linkmode.o phy_link_topology.o
+				   linkmode.o phy_link_topology.o \
+				   phy_package.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
 ifdef CONFIG_MDIO_DEVICE
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index a38d399f244bb..b2d32fbc8c850 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1686,243 +1686,6 @@ bool phy_driver_is_genphy_10g(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
 
-/**
- * phy_package_join - join a common PHY group
- * @phydev: target phy_device struct
- * @base_addr: cookie and base PHY address of PHY package for offset
- *   calculation of global register access
- * @priv_size: if non-zero allocate this amount of bytes for private data
- *
- * This joins a PHY group and provides a shared storage for all phydevs in
- * this group. This is intended to be used for packages which contain
- * more than one PHY, for example a quad PHY transceiver.
- *
- * The base_addr parameter serves as cookie which has to have the same values
- * for all members of one group and as the base PHY address of the PHY package
- * for offset calculation to access generic registers of a PHY package.
- * Usually, one of the PHY addresses of the different PHYs in the package
- * provides access to these global registers.
- * The address which is given here, will be used in the phy_package_read()
- * and phy_package_write() convenience functions as base and added to the
- * passed offset in those functions.
- *
- * This will set the shared pointer of the phydev to the shared storage.
- * If this is the first call for a this cookie the shared storage will be
- * allocated. If priv_size is non-zero, the given amount of bytes are
- * allocated for the priv member.
- *
- * Returns < 1 on error, 0 on success. Esp. calling phy_package_join()
- * with the same cookie but a different priv_size is an error.
- */
-int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size)
-{
-	struct mii_bus *bus = phydev->mdio.bus;
-	struct phy_package_shared *shared;
-	int ret;
-
-	if (base_addr < 0 || base_addr >= PHY_MAX_ADDR)
-		return -EINVAL;
-
-	mutex_lock(&bus->shared_lock);
-	shared = bus->shared[base_addr];
-	if (!shared) {
-		ret = -ENOMEM;
-		shared = kzalloc(sizeof(*shared), GFP_KERNEL);
-		if (!shared)
-			goto err_unlock;
-		if (priv_size) {
-			shared->priv = kzalloc(priv_size, GFP_KERNEL);
-			if (!shared->priv)
-				goto err_free;
-			shared->priv_size = priv_size;
-		}
-		shared->base_addr = base_addr;
-		shared->np = NULL;
-		refcount_set(&shared->refcnt, 1);
-		bus->shared[base_addr] = shared;
-	} else {
-		ret = -EINVAL;
-		if (priv_size && priv_size != shared->priv_size)
-			goto err_unlock;
-		refcount_inc(&shared->refcnt);
-	}
-	mutex_unlock(&bus->shared_lock);
-
-	phydev->shared = shared;
-
-	return 0;
-
-err_free:
-	kfree(shared);
-err_unlock:
-	mutex_unlock(&bus->shared_lock);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(phy_package_join);
-
-/**
- * of_phy_package_join - join a common PHY group in PHY package
- * @phydev: target phy_device struct
- * @priv_size: if non-zero allocate this amount of bytes for private data
- *
- * This is a variant of phy_package_join for PHY package defined in DT.
- *
- * The parent node of the @phydev is checked as a valid PHY package node
- * structure (by matching the node name "ethernet-phy-package") and the
- * base_addr for the PHY package is passed to phy_package_join.
- *
- * With this configuration the shared struct will also have the np value
- * filled to use additional DT defined properties in PHY specific
- * probe_once and config_init_once PHY package OPs.
- *
- * Returns < 0 on error, 0 on success. Esp. calling phy_package_join()
- * with the same cookie but a different priv_size is an error. Or a parent
- * node is not detected or is not valid or doesn't match the expected node
- * name for PHY package.
- */
-int of_phy_package_join(struct phy_device *phydev, size_t priv_size)
-{
-	struct device_node *node = phydev->mdio.dev.of_node;
-	struct device_node *package_node;
-	u32 base_addr;
-	int ret;
-
-	if (!node)
-		return -EINVAL;
-
-	package_node = of_get_parent(node);
-	if (!package_node)
-		return -EINVAL;
-
-	if (!of_node_name_eq(package_node, "ethernet-phy-package")) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	if (of_property_read_u32(package_node, "reg", &base_addr)) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	ret = phy_package_join(phydev, base_addr, priv_size);
-	if (ret)
-		goto exit;
-
-	phydev->shared->np = package_node;
-
-	return 0;
-exit:
-	of_node_put(package_node);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(of_phy_package_join);
-
-/**
- * phy_package_leave - leave a common PHY group
- * @phydev: target phy_device struct
- *
- * This leaves a PHY group created by phy_package_join(). If this phydev
- * was the last user of the shared data between the group, this data is
- * freed. Resets the phydev->shared pointer to NULL.
- */
-void phy_package_leave(struct phy_device *phydev)
-{
-	struct phy_package_shared *shared = phydev->shared;
-	struct mii_bus *bus = phydev->mdio.bus;
-
-	if (!shared)
-		return;
-
-	/* Decrease the node refcount on leave if present */
-	if (shared->np)
-		of_node_put(shared->np);
-
-	if (refcount_dec_and_mutex_lock(&shared->refcnt, &bus->shared_lock)) {
-		bus->shared[shared->base_addr] = NULL;
-		mutex_unlock(&bus->shared_lock);
-		kfree(shared->priv);
-		kfree(shared);
-	}
-
-	phydev->shared = NULL;
-}
-EXPORT_SYMBOL_GPL(phy_package_leave);
-
-static void devm_phy_package_leave(struct device *dev, void *res)
-{
-	phy_package_leave(*(struct phy_device **)res);
-}
-
-/**
- * devm_phy_package_join - resource managed phy_package_join()
- * @dev: device that is registering this PHY package
- * @phydev: target phy_device struct
- * @base_addr: cookie and base PHY address of PHY package for offset
- *   calculation of global register access
- * @priv_size: if non-zero allocate this amount of bytes for private data
- *
- * Managed phy_package_join(). Shared storage fetched by this function,
- * phy_package_leave() is automatically called on driver detach. See
- * phy_package_join() for more information.
- */
-int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int base_addr, size_t priv_size)
-{
-	struct phy_device **ptr;
-	int ret;
-
-	ptr = devres_alloc(devm_phy_package_leave, sizeof(*ptr),
-			   GFP_KERNEL);
-	if (!ptr)
-		return -ENOMEM;
-
-	ret = phy_package_join(phydev, base_addr, priv_size);
-
-	if (!ret) {
-		*ptr = phydev;
-		devres_add(dev, ptr);
-	} else {
-		devres_free(ptr);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(devm_phy_package_join);
-
-/**
- * devm_of_phy_package_join - resource managed of_phy_package_join()
- * @dev: device that is registering this PHY package
- * @phydev: target phy_device struct
- * @priv_size: if non-zero allocate this amount of bytes for private data
- *
- * Managed of_phy_package_join(). Shared storage fetched by this function,
- * phy_package_leave() is automatically called on driver detach. See
- * of_phy_package_join() for more information.
- */
-int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev,
-			     size_t priv_size)
-{
-	struct phy_device **ptr;
-	int ret;
-
-	ptr = devres_alloc(devm_phy_package_leave, sizeof(*ptr),
-			   GFP_KERNEL);
-	if (!ptr)
-		return -ENOMEM;
-
-	ret = of_phy_package_join(phydev, priv_size);
-
-	if (!ret) {
-		*ptr = phydev;
-		devres_add(dev, ptr);
-	} else {
-		devres_free(ptr);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(devm_of_phy_package_join);
-
 /**
  * phy_detach - detach a PHY device from its network device
  * @phydev: target phy_device struct
diff --git a/drivers/net/phy/phy_package.c b/drivers/net/phy/phy_package.c
new file mode 100644
index 0000000000000..260469f027c84
--- /dev/null
+++ b/drivers/net/phy/phy_package.c
@@ -0,0 +1,244 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PHY package support
+ */
+
+#include <linux/of.h>
+#include <linux/phy.h>
+
+/**
+ * phy_package_join - join a common PHY group
+ * @phydev: target phy_device struct
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
+ * @priv_size: if non-zero allocate this amount of bytes for private data
+ *
+ * This joins a PHY group and provides a shared storage for all phydevs in
+ * this group. This is intended to be used for packages which contain
+ * more than one PHY, for example a quad PHY transceiver.
+ *
+ * The base_addr parameter serves as cookie which has to have the same values
+ * for all members of one group and as the base PHY address of the PHY package
+ * for offset calculation to access generic registers of a PHY package.
+ * Usually, one of the PHY addresses of the different PHYs in the package
+ * provides access to these global registers.
+ * The address which is given here, will be used in the phy_package_read()
+ * and phy_package_write() convenience functions as base and added to the
+ * passed offset in those functions.
+ *
+ * This will set the shared pointer of the phydev to the shared storage.
+ * If this is the first call for a this cookie the shared storage will be
+ * allocated. If priv_size is non-zero, the given amount of bytes are
+ * allocated for the priv member.
+ *
+ * Returns < 1 on error, 0 on success. Esp. calling phy_package_join()
+ * with the same cookie but a different priv_size is an error.
+ */
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size)
+{
+	struct mii_bus *bus = phydev->mdio.bus;
+	struct phy_package_shared *shared;
+	int ret;
+
+	if (base_addr < 0 || base_addr >= PHY_MAX_ADDR)
+		return -EINVAL;
+
+	mutex_lock(&bus->shared_lock);
+	shared = bus->shared[base_addr];
+	if (!shared) {
+		ret = -ENOMEM;
+		shared = kzalloc(sizeof(*shared), GFP_KERNEL);
+		if (!shared)
+			goto err_unlock;
+		if (priv_size) {
+			shared->priv = kzalloc(priv_size, GFP_KERNEL);
+			if (!shared->priv)
+				goto err_free;
+			shared->priv_size = priv_size;
+		}
+		shared->base_addr = base_addr;
+		shared->np = NULL;
+		refcount_set(&shared->refcnt, 1);
+		bus->shared[base_addr] = shared;
+	} else {
+		ret = -EINVAL;
+		if (priv_size && priv_size != shared->priv_size)
+			goto err_unlock;
+		refcount_inc(&shared->refcnt);
+	}
+	mutex_unlock(&bus->shared_lock);
+
+	phydev->shared = shared;
+
+	return 0;
+
+err_free:
+	kfree(shared);
+err_unlock:
+	mutex_unlock(&bus->shared_lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(phy_package_join);
+
+/**
+ * of_phy_package_join - join a common PHY group in PHY package
+ * @phydev: target phy_device struct
+ * @priv_size: if non-zero allocate this amount of bytes for private data
+ *
+ * This is a variant of phy_package_join for PHY package defined in DT.
+ *
+ * The parent node of the @phydev is checked as a valid PHY package node
+ * structure (by matching the node name "ethernet-phy-package") and the
+ * base_addr for the PHY package is passed to phy_package_join.
+ *
+ * With this configuration the shared struct will also have the np value
+ * filled to use additional DT defined properties in PHY specific
+ * probe_once and config_init_once PHY package OPs.
+ *
+ * Returns < 0 on error, 0 on success. Esp. calling phy_package_join()
+ * with the same cookie but a different priv_size is an error. Or a parent
+ * node is not detected or is not valid or doesn't match the expected node
+ * name for PHY package.
+ */
+int of_phy_package_join(struct phy_device *phydev, size_t priv_size)
+{
+	struct device_node *node = phydev->mdio.dev.of_node;
+	struct device_node *package_node;
+	u32 base_addr;
+	int ret;
+
+	if (!node)
+		return -EINVAL;
+
+	package_node = of_get_parent(node);
+	if (!package_node)
+		return -EINVAL;
+
+	if (!of_node_name_eq(package_node, "ethernet-phy-package")) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	if (of_property_read_u32(package_node, "reg", &base_addr)) {
+		ret = -EINVAL;
+		goto exit;
+	}
+
+	ret = phy_package_join(phydev, base_addr, priv_size);
+	if (ret)
+		goto exit;
+
+	phydev->shared->np = package_node;
+
+	return 0;
+exit:
+	of_node_put(package_node);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(of_phy_package_join);
+
+/**
+ * phy_package_leave - leave a common PHY group
+ * @phydev: target phy_device struct
+ *
+ * This leaves a PHY group created by phy_package_join(). If this phydev
+ * was the last user of the shared data between the group, this data is
+ * freed. Resets the phydev->shared pointer to NULL.
+ */
+void phy_package_leave(struct phy_device *phydev)
+{
+	struct phy_package_shared *shared = phydev->shared;
+	struct mii_bus *bus = phydev->mdio.bus;
+
+	if (!shared)
+		return;
+
+	/* Decrease the node refcount on leave if present */
+	if (shared->np)
+		of_node_put(shared->np);
+
+	if (refcount_dec_and_mutex_lock(&shared->refcnt, &bus->shared_lock)) {
+		bus->shared[shared->base_addr] = NULL;
+		mutex_unlock(&bus->shared_lock);
+		kfree(shared->priv);
+		kfree(shared);
+	}
+
+	phydev->shared = NULL;
+}
+EXPORT_SYMBOL_GPL(phy_package_leave);
+
+static void devm_phy_package_leave(struct device *dev, void *res)
+{
+	phy_package_leave(*(struct phy_device **)res);
+}
+
+/**
+ * devm_phy_package_join - resource managed phy_package_join()
+ * @dev: device that is registering this PHY package
+ * @phydev: target phy_device struct
+ * @base_addr: cookie and base PHY address of PHY package for offset
+ *   calculation of global register access
+ * @priv_size: if non-zero allocate this amount of bytes for private data
+ *
+ * Managed phy_package_join(). Shared storage fetched by this function,
+ * phy_package_leave() is automatically called on driver detach. See
+ * phy_package_join() for more information.
+ */
+int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
+			  int base_addr, size_t priv_size)
+{
+	struct phy_device **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_phy_package_leave, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = phy_package_join(phydev, base_addr, priv_size);
+
+	if (!ret) {
+		*ptr = phydev;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_phy_package_join);
+
+/**
+ * devm_of_phy_package_join - resource managed of_phy_package_join()
+ * @dev: device that is registering this PHY package
+ * @phydev: target phy_device struct
+ * @priv_size: if non-zero allocate this amount of bytes for private data
+ *
+ * Managed of_phy_package_join(). Shared storage fetched by this function,
+ * phy_package_leave() is automatically called on driver detach. See
+ * of_phy_package_join() for more information.
+ */
+int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev,
+			     size_t priv_size)
+{
+	struct phy_device **ptr;
+	int ret;
+
+	ptr = devres_alloc(devm_phy_package_leave, sizeof(*ptr),
+			   GFP_KERNEL);
+	if (!ptr)
+		return -ENOMEM;
+
+	ret = of_phy_package_join(phydev, priv_size);
+
+	if (!ret) {
+		*ptr = phydev;
+		devres_add(dev, ptr);
+	} else {
+		devres_free(ptr);
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_of_phy_package_join);

From 2c8cd9783f464958fc6c10bc70715c3676f50f23 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:15:09 +0100
Subject: [PATCH 1640/2753] net: phy: add getters for public members in struct
 phy_package_shared

Add getters for public members, this prepares for making struct
phy_package_shared private to phylib. Declare the getters in a new header
file phylib.h, which will be used by PHY drivers only.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/c6da0b27-4479-4717-9e16-643821b76bd8@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_package.c | 14 ++++++++++++++
 drivers/net/phy/phylib.h      | 15 +++++++++++++++
 2 files changed, 29 insertions(+)
 create mode 100644 drivers/net/phy/phylib.h

diff --git a/drivers/net/phy/phy_package.c b/drivers/net/phy/phy_package.c
index 260469f027c84..873420e58f020 100644
--- a/drivers/net/phy/phy_package.c
+++ b/drivers/net/phy/phy_package.c
@@ -6,6 +6,20 @@
 #include <linux/of.h>
 #include <linux/phy.h>
 
+#include "phylib.h"
+
+struct device_node *phy_package_get_node(struct phy_device *phydev)
+{
+	return phydev->shared->np;
+}
+EXPORT_SYMBOL_GPL(phy_package_get_node);
+
+void *phy_package_get_priv(struct phy_device *phydev)
+{
+	return phydev->shared->priv;
+}
+EXPORT_SYMBOL_GPL(phy_package_get_priv);
+
 /**
  * phy_package_join - join a common PHY group
  * @phydev: target phy_device struct
diff --git a/drivers/net/phy/phylib.h b/drivers/net/phy/phylib.h
new file mode 100644
index 0000000000000..a42e1fc079cb0
--- /dev/null
+++ b/drivers/net/phy/phylib.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * phylib header
+ */
+
+#ifndef __PHYLIB_H
+#define __PHYLIB_H
+
+struct device_node;
+struct phy_device;
+
+struct device_node *phy_package_get_node(struct phy_device *phydev);
+void *phy_package_get_priv(struct phy_device *phydev);
+
+#endif /* __PHYLIB_H */

From 947030f3c32bcc51a24efd35599da2133154d40e Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:16:00 +0100
Subject: [PATCH 1641/2753] net: phy: qca807x: use new phy_package_shared
 getters

Use the new getters for members of struct phy_package_shared.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/b6402789-45d2-49d6-835f-ed584bce5b2f@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/qcom/qca807x.c | 16 +++++++---------
 1 file changed, 7 insertions(+), 9 deletions(-)

diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index 2ad8c2586d643..1af6b5ead74bf 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -15,6 +15,7 @@
 #include <linux/gpio/driver.h>
 #include <linux/sfp.h>
 
+#include "../phylib.h"
 #include "qcom.h"
 
 #define QCA807X_CHIP_CONFIGURATION				0x1f
@@ -486,13 +487,13 @@ static int qca807x_read_status(struct phy_device *phydev)
 
 static int qca807x_phy_package_probe_once(struct phy_device *phydev)
 {
-	struct phy_package_shared *shared = phydev->shared;
-	struct qca807x_shared_priv *priv = shared->priv;
+	struct qca807x_shared_priv *priv = phy_package_get_priv(phydev);
+	struct device_node *np = phy_package_get_node(phydev);
 	unsigned int tx_drive_strength;
 	const char *package_mode_name;
 
 	/* Default to 600mw if not defined */
-	if (of_property_read_u32(shared->np, "qcom,tx-drive-strength-milliwatt",
+	if (of_property_read_u32(np, "qcom,tx-drive-strength-milliwatt",
 				 &tx_drive_strength))
 		tx_drive_strength = 600;
 
@@ -541,7 +542,7 @@ static int qca807x_phy_package_probe_once(struct phy_device *phydev)
 	}
 
 	priv->package_mode = PHY_INTERFACE_MODE_NA;
-	if (!of_property_read_string(shared->np, "qcom,package-mode",
+	if (!of_property_read_string(np, "qcom,package-mode",
 				     &package_mode_name)) {
 		if (!strcasecmp(package_mode_name,
 				phy_modes(PHY_INTERFACE_MODE_PSGMII)))
@@ -558,8 +559,7 @@ static int qca807x_phy_package_probe_once(struct phy_device *phydev)
 
 static int qca807x_phy_package_config_init_once(struct phy_device *phydev)
 {
-	struct phy_package_shared *shared = phydev->shared;
-	struct qca807x_shared_priv *priv = shared->priv;
+	struct qca807x_shared_priv *priv = phy_package_get_priv(phydev);
 	int val, ret;
 
 	/* Make sure PHY follow PHY package mode if enforced */
@@ -708,7 +708,6 @@ static int qca807x_probe(struct phy_device *phydev)
 	struct device_node *node = phydev->mdio.dev.of_node;
 	struct qca807x_shared_priv *shared_priv;
 	struct device *dev = &phydev->mdio.dev;
-	struct phy_package_shared *shared;
 	struct qca807x_priv *priv;
 	int ret;
 
@@ -722,8 +721,7 @@ static int qca807x_probe(struct phy_device *phydev)
 			return ret;
 	}
 
-	shared = phydev->shared;
-	shared_priv = shared->priv;
+	shared_priv = phy_package_get_priv(phydev);
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)

From 890fe6841d8107a1d1bfebe9b61f9c81f483ee42 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:16:43 +0100
Subject: [PATCH 1642/2753] net: phy: micrel: use new phy_package_shared
 getters

Use the new getters for members of struct phy_package_shared.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/18e5d29e-fb96-4771-92e4-689e0c992177@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/micrel.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 9c0b1c229af64..289e1d56aa655 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -34,6 +34,8 @@
 #include <linux/net_tstamp.h>
 #include <linux/gpio/consumer.h>
 
+#include "phylib.h"
+
 /* Operation Mode Strap Override */
 #define MII_KSZPHY_OMSO				0x16
 #define KSZPHY_OMSO_FACTORY_TEST		BIT(15)
@@ -2631,8 +2633,7 @@ static void lan8814_ptp_tx_ts_get(struct phy_device *phydev,
 static int lan8814_ts_info(struct mii_timestamper *mii_ts, struct kernel_ethtool_ts_info *info)
 {
 	struct kszphy_ptp_priv *ptp_priv = container_of(mii_ts, struct kszphy_ptp_priv, mii_ts);
-	struct phy_device *phydev = ptp_priv->phydev;
-	struct lan8814_shared_priv *shared = phydev->shared->priv;
+	struct lan8814_shared_priv *shared = phy_package_get_priv(ptp_priv->phydev);
 
 	info->so_timestamping = SOF_TIMESTAMPING_TX_HARDWARE |
 				SOF_TIMESTAMPING_RX_HARDWARE |
@@ -3653,7 +3654,7 @@ static int lan8814_gpio_process_cap(struct lan8814_shared_priv *shared)
 
 static int lan8814_handle_gpio_interrupt(struct phy_device *phydev, u16 status)
 {
-	struct lan8814_shared_priv *shared = phydev->shared->priv;
+	struct lan8814_shared_priv *shared = phy_package_get_priv(phydev);
 	int ret;
 
 	mutex_lock(&shared->shared_lock);
@@ -3864,7 +3865,7 @@ static void lan8814_ptp_init(struct phy_device *phydev)
 
 static int lan8814_ptp_probe_once(struct phy_device *phydev)
 {
-	struct lan8814_shared_priv *shared = phydev->shared->priv;
+	struct lan8814_shared_priv *shared = phy_package_get_priv(phydev);
 
 	/* Initialise shared lock for clock*/
 	mutex_init(&shared->shared_lock);

From dc5a6164fedacdcdbb51a2a340ca264191a5b82c Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:17:18 +0100
Subject: [PATCH 1643/2753] net: phy: mediatek: use new phy_package_shared
 getters

Use the new getters for members of struct phy_package_shared.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/356a257f-68d0-47bc-a474-4dafaeaa149f@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mediatek/mtk-ge-soc.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/mediatek/mtk-ge-soc.c b/drivers/net/phy/mediatek/mtk-ge-soc.c
index 9de6fbb45564e..175cf5239bba8 100644
--- a/drivers/net/phy/mediatek/mtk-ge-soc.c
+++ b/drivers/net/phy/mediatek/mtk-ge-soc.c
@@ -8,6 +8,7 @@
 #include <linux/phy.h>
 #include <linux/regmap.h>
 
+#include "../phylib.h"
 #include "mtk.h"
 
 #define MTK_GPHY_ID_MT7981			0x03a29461
@@ -1278,7 +1279,7 @@ static int mt798x_phy_led_hw_control_set(struct phy_device *phydev, u8 index,
 
 static bool mt7988_phy_led_get_polarity(struct phy_device *phydev, int led_num)
 {
-	struct mtk_socphy_shared *priv = phydev->shared->priv;
+	struct mtk_socphy_shared *priv = phy_package_get_priv(phydev);
 	u32 polarities;
 
 	if (led_num == 0)
@@ -1317,7 +1318,7 @@ static int mt7988_phy_fix_leds_polarities(struct phy_device *phydev)
 static int mt7988_phy_probe_shared(struct phy_device *phydev)
 {
 	struct device_node *np = dev_of_node(&phydev->mdio.bus->dev);
-	struct mtk_socphy_shared *shared = phydev->shared->priv;
+	struct mtk_socphy_shared *shared = phy_package_get_priv(phydev);
 	struct regmap *regmap;
 	u32 reg;
 	int ret;
@@ -1368,7 +1369,7 @@ static int mt7988_phy_probe(struct phy_device *phydev)
 			return err;
 	}
 
-	shared = phydev->shared->priv;
+	shared = phy_package_get_priv(phydev);
 	priv = &shared->priv[phydev->mdio.addr];
 
 	phydev->priv = priv;

From e0327e9f859771a687884285c3ecc942eeae016a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:17:54 +0100
Subject: [PATCH 1644/2753] net: phy: mscc: use new phy_package_shared getters

Use the new getters for members of struct phy_package_shared.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/61ee43ec-be20-4be1-bfad-d18d2a4fae2b@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mscc/mscc_ptp.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/phy/mscc/mscc_ptp.c b/drivers/net/phy/mscc/mscc_ptp.c
index 738a8822fcf01..ed8fb14a7f215 100644
--- a/drivers/net/phy/mscc/mscc_ptp.c
+++ b/drivers/net/phy/mscc/mscc_ptp.c
@@ -17,6 +17,7 @@
 #include <linux/udp.h>
 #include <linux/unaligned.h>
 
+#include "../phylib.h"
 #include "mscc.h"
 #include "mscc_ptp.h"
 
@@ -645,11 +646,12 @@ static int __vsc85xx_gettime(struct ptp_clock_info *info, struct timespec64 *ts)
 {
 	struct vsc85xx_ptp *ptp = container_of(info, struct vsc85xx_ptp, caps);
 	struct phy_device *phydev = ptp->phydev;
-	struct vsc85xx_shared_private *shared =
-		(struct vsc85xx_shared_private *)phydev->shared->priv;
 	struct vsc8531_private *priv = phydev->priv;
+	struct vsc85xx_shared_private *shared;
 	u32 val;
 
+	shared = phy_package_get_priv(phydev);
+
 	val = vsc85xx_ts_read_csr(phydev, PROCESSOR, MSCC_PHY_PTP_LTC_CTRL);
 	val |= PTP_LTC_CTRL_SAVE_ENA;
 	vsc85xx_ts_write_csr(phydev, PROCESSOR, MSCC_PHY_PTP_LTC_CTRL, val);
@@ -696,11 +698,12 @@ static int __vsc85xx_settime(struct ptp_clock_info *info,
 {
 	struct vsc85xx_ptp *ptp = container_of(info, struct vsc85xx_ptp, caps);
 	struct phy_device *phydev = ptp->phydev;
-	struct vsc85xx_shared_private *shared =
-		(struct vsc85xx_shared_private *)phydev->shared->priv;
 	struct vsc8531_private *priv = phydev->priv;
+	struct vsc85xx_shared_private *shared;
 	u32 val;
 
+	shared = phy_package_get_priv(phydev);
+
 	vsc85xx_ts_write_csr(phydev, PROCESSOR, MSCC_PHY_PTP_LTC_LOAD_SEC_MSB,
 			     PTP_LTC_LOAD_SEC_MSB(ts->tv_sec));
 	vsc85xx_ts_write_csr(phydev, PROCESSOR, MSCC_PHY_PTP_LTC_LOAD_SEC_LSB,
@@ -1580,8 +1583,7 @@ int vsc8584_ptp_probe(struct phy_device *phydev)
 
 int vsc8584_ptp_probe_once(struct phy_device *phydev)
 {
-	struct vsc85xx_shared_private *shared =
-		(struct vsc85xx_shared_private *)phydev->shared->priv;
+	struct vsc85xx_shared_private *shared = phy_package_get_priv(phydev);
 
 	/* Initialize shared GPIO lock */
 	mutex_init(&shared->gpio_lock);

From e7f984e925d23f8fd0469e344a8dc225e1a1b0ab Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:18:46 +0100
Subject: [PATCH 1645/2753] net: phy: move PHY package related code from phy.h
 to phy_package.c

Move PHY package related inline functions from phy.h to phy_package.c.
While doing so remove locked versions phy_package_read() and
phy_package_write() which have no user.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/a4518379-7a5d-45f3-831c-b7fde6512c65@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/bcm54140.c        |  1 +
 drivers/net/phy/mscc/mscc_main.c  |  2 +
 drivers/net/phy/phy-core.c        |  1 +
 drivers/net/phy/phy_package.c     | 61 ++++++++++++++++++++++
 drivers/net/phy/phylib-internal.h |  2 +
 drivers/net/phy/phylib.h          |  6 +++
 include/linux/phy.h               | 86 -------------------------------
 7 files changed, 73 insertions(+), 86 deletions(-)

diff --git a/drivers/net/phy/bcm54140.c b/drivers/net/phy/bcm54140.c
index 7969345f6b355..a8edf45fd7335 100644
--- a/drivers/net/phy/bcm54140.c
+++ b/drivers/net/phy/bcm54140.c
@@ -10,6 +10,7 @@
 #include <linux/module.h>
 #include <linux/phy.h>
 
+#include "phylib.h"
 #include "bcm-phy-lib.h"
 
 /* RDB per-port registers
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index 19cf12ee8990f..7ff975efd8e7a 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -17,6 +17,8 @@
 #include <linux/of.h>
 #include <linux/netdevice.h>
 #include <dt-bindings/net/mscc-phy-vsc8531.h>
+
+#include "../phylib.h"
 #include "mscc_serdes.h"
 #include "mscc.h"
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index b1c1670de23b0..154d29be6293a 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -6,6 +6,7 @@
 #include <linux/phy.h>
 #include <linux/of.h>
 
+#include "phylib.h"
 #include "phylib-internal.h"
 
 /**
diff --git a/drivers/net/phy/phy_package.c b/drivers/net/phy/phy_package.c
index 873420e58f020..12c92d26ee0b9 100644
--- a/drivers/net/phy/phy_package.c
+++ b/drivers/net/phy/phy_package.c
@@ -7,6 +7,7 @@
 #include <linux/phy.h>
 
 #include "phylib.h"
+#include "phylib-internal.h"
 
 struct device_node *phy_package_get_node(struct phy_device *phydev)
 {
@@ -20,6 +21,66 @@ void *phy_package_get_priv(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(phy_package_get_priv);
 
+int phy_package_address(struct phy_device *phydev, unsigned int addr_offset)
+{
+	struct phy_package_shared *shared = phydev->shared;
+	u8 base_addr = shared->base_addr;
+
+	if (addr_offset >= PHY_MAX_ADDR - base_addr)
+		return -EIO;
+
+	/* we know that addr will be in the range 0..31 and thus the
+	 * implicit cast to a signed int is not a problem.
+	 */
+	return base_addr + addr_offset;
+}
+
+int __phy_package_read(struct phy_device *phydev, unsigned int addr_offset,
+		       u32 regnum)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	return __mdiobus_read(phydev->mdio.bus, addr, regnum);
+}
+EXPORT_SYMBOL_GPL(__phy_package_read);
+
+int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset,
+			u32 regnum, u16 val)
+{
+	int addr = phy_package_address(phydev, addr_offset);
+
+	if (addr < 0)
+		return addr;
+
+	return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
+}
+EXPORT_SYMBOL_GPL(__phy_package_write);
+
+static bool __phy_package_set_once(struct phy_device *phydev, unsigned int b)
+{
+	struct phy_package_shared *shared = phydev->shared;
+
+	if (!shared)
+		return false;
+
+	return !test_and_set_bit(b, &shared->flags);
+}
+
+bool phy_package_init_once(struct phy_device *phydev)
+{
+	return __phy_package_set_once(phydev, 0);
+}
+EXPORT_SYMBOL_GPL(phy_package_init_once);
+
+bool phy_package_probe_once(struct phy_device *phydev)
+{
+	return __phy_package_set_once(phydev, 1);
+}
+EXPORT_SYMBOL_GPL(phy_package_probe_once);
+
 /**
  * phy_package_join - join a common PHY group
  * @phydev: target phy_device struct
diff --git a/drivers/net/phy/phylib-internal.h b/drivers/net/phy/phylib-internal.h
index dc9592c6bb8e7..afac2bd15b502 100644
--- a/drivers/net/phy/phylib-internal.h
+++ b/drivers/net/phy/phylib-internal.h
@@ -20,6 +20,8 @@ void of_set_phy_timing_role(struct phy_device *phydev);
 int phy_speed_down_core(struct phy_device *phydev);
 void phy_check_downshift(struct phy_device *phydev);
 
+int phy_package_address(struct phy_device *phydev, unsigned int addr_offset);
+
 int genphy_c45_read_eee_adv(struct phy_device *phydev, unsigned long *adv);
 
 #endif /* __PHYLIB_INTERNAL_H */
diff --git a/drivers/net/phy/phylib.h b/drivers/net/phy/phylib.h
index a42e1fc079cb0..06c50d275b906 100644
--- a/drivers/net/phy/phylib.h
+++ b/drivers/net/phy/phylib.h
@@ -11,5 +11,11 @@ struct phy_device;
 
 struct device_node *phy_package_get_node(struct phy_device *phydev);
 void *phy_package_get_priv(struct phy_device *phydev);
+int __phy_package_read(struct phy_device *phydev, unsigned int addr_offset,
+		       u32 regnum);
+int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset,
+			u32 regnum, u16 val);
+bool phy_package_init_once(struct phy_device *phydev);
+bool phy_package_probe_once(struct phy_device *phydev);
 
 #endif /* __PHYLIB_H */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 7bfbae51070a8..2b12d1bef3cc9 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -350,10 +350,6 @@ struct phy_package_shared {
 	void *priv;
 };
 
-/* used as bit number in atomic bitops */
-#define PHY_SHARED_F_INIT_DONE  0
-#define PHY_SHARED_F_PROBE_DONE 1
-
 /**
  * struct mii_bus - Represents an MDIO bus
  *
@@ -2149,67 +2145,6 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct kernel_hwtstamp_config *config,
 		       struct netlink_ext_ack *extack);
 
-static inline int phy_package_address(struct phy_device *phydev,
-				      unsigned int addr_offset)
-{
-	struct phy_package_shared *shared = phydev->shared;
-	u8 base_addr = shared->base_addr;
-
-	if (addr_offset >= PHY_MAX_ADDR - base_addr)
-		return -EIO;
-
-	/* we know that addr will be in the range 0..31 and thus the
-	 * implicit cast to a signed int is not a problem.
-	 */
-	return base_addr + addr_offset;
-}
-
-static inline int phy_package_read(struct phy_device *phydev,
-				   unsigned int addr_offset, u32 regnum)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-
-	if (addr < 0)
-		return addr;
-
-	return mdiobus_read(phydev->mdio.bus, addr, regnum);
-}
-
-static inline int __phy_package_read(struct phy_device *phydev,
-				     unsigned int addr_offset, u32 regnum)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-
-	if (addr < 0)
-		return addr;
-
-	return __mdiobus_read(phydev->mdio.bus, addr, regnum);
-}
-
-static inline int phy_package_write(struct phy_device *phydev,
-				    unsigned int addr_offset, u32 regnum,
-				    u16 val)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-
-	if (addr < 0)
-		return addr;
-
-	return mdiobus_write(phydev->mdio.bus, addr, regnum, val);
-}
-
-static inline int __phy_package_write(struct phy_device *phydev,
-				      unsigned int addr_offset, u32 regnum,
-				      u16 val)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-
-	if (addr < 0)
-		return addr;
-
-	return __mdiobus_write(phydev->mdio.bus, addr, regnum, val);
-}
-
 int __phy_package_read_mmd(struct phy_device *phydev,
 			   unsigned int addr_offset, int devad,
 			   u32 regnum);
@@ -2226,27 +2161,6 @@ int phy_package_write_mmd(struct phy_device *phydev,
 			  unsigned int addr_offset, int devad,
 			  u32 regnum, u16 val);
 
-static inline bool __phy_package_set_once(struct phy_device *phydev,
-					  unsigned int b)
-{
-	struct phy_package_shared *shared = phydev->shared;
-
-	if (!shared)
-		return false;
-
-	return !test_and_set_bit(b, &shared->flags);
-}
-
-static inline bool phy_package_init_once(struct phy_device *phydev)
-{
-	return __phy_package_set_once(phydev, PHY_SHARED_F_INIT_DONE);
-}
-
-static inline bool phy_package_probe_once(struct phy_device *phydev)
-{
-	return __phy_package_set_once(phydev, PHY_SHARED_F_PROBE_DONE);
-}
-
 extern const struct bus_type mdio_bus_type;
 
 struct mdio_board_info {

From a4002849776948f257d564944e8fd7a727362ed9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Mon, 3 Mar 2025 21:19:25 +0100
Subject: [PATCH 1646/2753] net: phy: remove remaining PHY package related
 definitions from phy.h

Move definition of struct phy_package_shared to phy_package.c, and
move remaining PHY package related declarations from phy.h to
phylib.h, thus making them accessible for PHY drivers only.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/211e14b6-e2f8-43d7-b533-3628ec548456@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_package.c | 31 ++++++++++++++++++++++++++++
 drivers/net/phy/phylib.h      |  7 +++++++
 include/linux/phy.h           | 38 -----------------------------------
 3 files changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/net/phy/phy_package.c b/drivers/net/phy/phy_package.c
index 12c92d26ee0b9..c738f76e8664b 100644
--- a/drivers/net/phy/phy_package.c
+++ b/drivers/net/phy/phy_package.c
@@ -9,6 +9,37 @@
 #include "phylib.h"
 #include "phylib-internal.h"
 
+/**
+ * struct phy_package_shared - Shared information in PHY packages
+ * @base_addr: Base PHY address of PHY package used to combine PHYs
+ *   in one package and for offset calculation of phy_package_read/write
+ * @np: Pointer to the Device Node if PHY package defined in DT
+ * @refcnt: Number of PHYs connected to this shared data
+ * @flags: Initialization of PHY package
+ * @priv_size: Size of the shared private data @priv
+ * @priv: Driver private data shared across a PHY package
+ *
+ * Represents a shared structure between different phydev's in the same
+ * package, for example a quad PHY. See phy_package_join() and
+ * phy_package_leave().
+ */
+struct phy_package_shared {
+	u8 base_addr;
+	/* With PHY package defined in DT this points to the PHY package node */
+	struct device_node *np;
+	refcount_t refcnt;
+	unsigned long flags;
+	size_t priv_size;
+
+	/* private data pointer */
+	/* note that this pointer is shared between different phydevs and
+	 * the user has to take care of appropriate locking. It is allocated
+	 * and freed automatically by phy_package_join() and
+	 * phy_package_leave().
+	 */
+	void *priv;
+};
+
 struct device_node *phy_package_get_node(struct phy_device *phydev)
 {
 	return phydev->shared->np;
diff --git a/drivers/net/phy/phylib.h b/drivers/net/phy/phylib.h
index 06c50d275b906..f0e499fed1f71 100644
--- a/drivers/net/phy/phylib.h
+++ b/drivers/net/phy/phylib.h
@@ -17,5 +17,12 @@ int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset,
 			u32 regnum, u16 val);
 bool phy_package_init_once(struct phy_device *phydev);
 bool phy_package_probe_once(struct phy_device *phydev);
+int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
+int of_phy_package_join(struct phy_device *phydev, size_t priv_size);
+void phy_package_leave(struct phy_device *phydev);
+int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
+			  int base_addr, size_t priv_size);
+int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev,
+			     size_t priv_size);
 
 #endif /* __PHYLIB_H */
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 2b12d1bef3cc9..c4a6385faf41c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -319,37 +319,6 @@ struct mdio_bus_stats {
 	struct u64_stats_sync syncp;
 };
 
-/**
- * struct phy_package_shared - Shared information in PHY packages
- * @base_addr: Base PHY address of PHY package used to combine PHYs
- *   in one package and for offset calculation of phy_package_read/write
- * @np: Pointer to the Device Node if PHY package defined in DT
- * @refcnt: Number of PHYs connected to this shared data
- * @flags: Initialization of PHY package
- * @priv_size: Size of the shared private data @priv
- * @priv: Driver private data shared across a PHY package
- *
- * Represents a shared structure between different phydev's in the same
- * package, for example a quad PHY. See phy_package_join() and
- * phy_package_leave().
- */
-struct phy_package_shared {
-	u8 base_addr;
-	/* With PHY package defined in DT this points to the PHY package node */
-	struct device_node *np;
-	refcount_t refcnt;
-	unsigned long flags;
-	size_t priv_size;
-
-	/* private data pointer */
-	/* note that this pointer is shared between different phydevs and
-	 * the user has to take care of appropriate locking. It is allocated
-	 * and freed automatically by phy_package_join() and
-	 * phy_package_leave().
-	 */
-	void *priv;
-};
-
 /**
  * struct mii_bus - Represents an MDIO bus
  *
@@ -2109,13 +2078,6 @@ int phy_ethtool_get_link_ksettings(struct net_device *ndev,
 int phy_ethtool_set_link_ksettings(struct net_device *ndev,
 				   const struct ethtool_link_ksettings *cmd);
 int phy_ethtool_nway_reset(struct net_device *ndev);
-int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
-int of_phy_package_join(struct phy_device *phydev, size_t priv_size);
-void phy_package_leave(struct phy_device *phydev);
-int devm_phy_package_join(struct device *dev, struct phy_device *phydev,
-			  int base_addr, size_t priv_size);
-int devm_of_phy_package_join(struct device *dev, struct phy_device *phydev,
-			     size_t priv_size);
 
 int __init mdio_bus_init(void);
 void mdio_bus_exit(void);

From ccc2f5a436fbb0ae1fb598932a9b8e48423c1959 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 09:50:23 +0100
Subject: [PATCH 1647/2753] net: dsa: mt7530: Fix traffic flooding for MMIO
 devices

On MMIO devices (e.g. MT7988 or EN7581) unicast traffic received on lanX
port is flooded on all other user ports if the DSA switch is configured
without VLAN support since PORT_MATRIX in PCR regs contains all user
ports. Similar to MDIO devices (e.g. MT7530 and MT7531) fix the issue
defining default VLAN-ID 0 for MT7530 MMIO devices.

Fixes: 110c18bfed414 ("net: dsa: mt7530: introduce driver for MT7988 built-in switch")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://patch.msgid.link/20250304-mt7988-flooding-fix-v1-1-905523ae83e9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mt7530.c | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index 1c83af805209c..5883eb93efb11 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2591,7 +2591,8 @@ mt7531_setup_common(struct dsa_switch *ds)
 	if (ret < 0)
 		return ret;
 
-	return 0;
+	/* Setup VLAN ID 0 for VLAN-unaware bridges */
+	return mt7530_setup_vlan0(priv);
 }
 
 static int
@@ -2687,11 +2688,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;
 
-	/* Setup VLAN ID 0 for VLAN-unaware bridges */
-	ret = mt7530_setup_vlan0(priv);
-	if (ret)
-		return ret;
-
 	ds->assisted_learning_on_cpu_port = true;
 	ds->mtu_enforcement_ingress = true;
 

From f130a0cc1b4ff1ef28a307428d40436032e2b66e Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 4 Mar 2025 12:59:18 +0000
Subject: [PATCH 1648/2753] inet: fix lwtunnel_valid_encap_type() lock
 imbalance

After blamed commit rtm_to_fib_config() now calls
lwtunnel_valid_encap_type{_attr}() without RTNL held,
triggering an unlock balance in __rtnl_unlock,
as reported by syzbot [1]

IPv6 and rtm_to_nh_config() are not yet converted.

Add a temporary @rtnl_is_held parameter to lwtunnel_valid_encap_type()
and lwtunnel_valid_encap_type_attr().

While we are at it replace the two rcu_dereference()
in lwtunnel_valid_encap_type() with more appropriate
rcu_access_pointer().

[1]
syz-executor245/5836 is trying to release lock (rtnl_mutex) at:
 [<ffffffff89d0e38c>] __rtnl_unlock+0x6c/0xf0 net/core/rtnetlink.c:142
but there are no more locks to release!

other info that might help us debug this:
no locks held by syz-executor245/5836.

stack backtrace:
CPU: 0 UID: 0 PID: 5836 Comm: syz-executor245 Not tainted 6.14.0-rc4-syzkaller-00873-g3424291dd242 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:94 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
  print_unlock_imbalance_bug+0x25b/0x2d0 kernel/locking/lockdep.c:5289
  __lock_release kernel/locking/lockdep.c:5518 [inline]
  lock_release+0x47e/0xa30 kernel/locking/lockdep.c:5872
  __mutex_unlock_slowpath+0xec/0x800 kernel/locking/mutex.c:891
  __rtnl_unlock+0x6c/0xf0 net/core/rtnetlink.c:142
  lwtunnel_valid_encap_type+0x38a/0x5f0 net/core/lwtunnel.c:169
  lwtunnel_valid_encap_type_attr+0x113/0x270 net/core/lwtunnel.c:209
  rtm_to_fib_config+0x949/0x14e0 net/ipv4/fib_frontend.c:808
  inet_rtm_newroute+0xf6/0x2a0 net/ipv4/fib_frontend.c:917
  rtnetlink_rcv_msg+0x791/0xcf0 net/core/rtnetlink.c:6919
  netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2534
  netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline]
  netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1339
  netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1883
  sock_sendmsg_nosec net/socket.c:709 [inline]

Fixes: 1dd2af7963e9 ("ipv4: fib: Convert RTM_NEWROUTE and RTM_DELROUTE to per-netns RTNL.")
Reported-by: syzbot+3f18ef0f7df107a3f6a0@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67c6f87a.050a0220.38b91b.0147.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250304125918.2763514-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/lwtunnel.h  | 12 ++++++++----
 net/core/lwtunnel.c     | 23 ++++++++++++-----------
 net/ipv4/fib_frontend.c |  4 ++--
 net/ipv4/nexthop.c      |  3 ++-
 net/ipv6/route.c        |  6 ++++--
 5 files changed, 28 insertions(+), 20 deletions(-)

diff --git a/include/net/lwtunnel.h b/include/net/lwtunnel.h
index 53bd2d02a4f0d..39cd50300a189 100644
--- a/include/net/lwtunnel.h
+++ b/include/net/lwtunnel.h
@@ -116,9 +116,11 @@ int lwtunnel_encap_add_ops(const struct lwtunnel_encap_ops *op,
 int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 			   unsigned int num);
 int lwtunnel_valid_encap_type(u16 encap_type,
-			      struct netlink_ext_ack *extack);
+			      struct netlink_ext_ack *extack,
+			      bool rtnl_is_held);
 int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
-				   struct netlink_ext_ack *extack);
+				   struct netlink_ext_ack *extack,
+				   bool rtnl_is_held);
 int lwtunnel_build_state(struct net *net, u16 encap_type,
 			 struct nlattr *encap,
 			 unsigned int family, const void *cfg,
@@ -201,13 +203,15 @@ static inline int lwtunnel_encap_del_ops(const struct lwtunnel_encap_ops *op,
 }
 
 static inline int lwtunnel_valid_encap_type(u16 encap_type,
-					    struct netlink_ext_ack *extack)
+					    struct netlink_ext_ack *extack,
+					    bool rtnl_is_held)
 {
 	NL_SET_ERR_MSG(extack, "CONFIG_LWTUNNEL is not enabled in this kernel");
 	return -EOPNOTSUPP;
 }
 static inline int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int len,
-						 struct netlink_ext_ack *extack)
+						 struct netlink_ext_ack *extack,
+						 bool rtnl_is_held)
 {
 	/* return 0 since we are not walking attr looking for
 	 * RTA_ENCAP_TYPE attribute on nexthops.
diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 711cd3b4347a7..6d3833269c2b4 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -147,7 +147,8 @@ int lwtunnel_build_state(struct net *net, u16 encap_type,
 }
 EXPORT_SYMBOL_GPL(lwtunnel_build_state);
 
-int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
+int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack,
+			      bool rtnl_is_held)
 {
 	const struct lwtunnel_encap_ops *ops;
 	int ret = -EINVAL;
@@ -158,21 +159,19 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
 		return ret;
 	}
 
-	rcu_read_lock();
-	ops = rcu_dereference(lwtun_encaps[encap_type]);
-	rcu_read_unlock();
+	ops = rcu_access_pointer(lwtun_encaps[encap_type]);
 #ifdef CONFIG_MODULES
 	if (!ops) {
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			__rtnl_unlock();
+			if (rtnl_is_held)
+				__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
-			rtnl_lock();
+			if (rtnl_is_held)
+				rtnl_lock();
 
-			rcu_read_lock();
-			ops = rcu_dereference(lwtun_encaps[encap_type]);
-			rcu_read_unlock();
+			ops = rcu_access_pointer(lwtun_encaps[encap_type]);
 		}
 	}
 #endif
@@ -185,7 +184,8 @@ int lwtunnel_valid_encap_type(u16 encap_type, struct netlink_ext_ack *extack)
 EXPORT_SYMBOL_GPL(lwtunnel_valid_encap_type);
 
 int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
-				   struct netlink_ext_ack *extack)
+				   struct netlink_ext_ack *extack,
+				   bool rtnl_is_held)
 {
 	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
 	struct nlattr *nla_entype;
@@ -207,7 +207,8 @@ int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining,
 				encap_type = nla_get_u16(nla_entype);
 
 				if (lwtunnel_valid_encap_type(encap_type,
-							      extack) != 0)
+							      extack,
+							      rtnl_is_held) != 0)
 					return -EOPNOTSUPP;
 			}
 		}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 6de77415b5b30..3f4e629998fab 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -807,7 +807,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_MULTIPATH:
 			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
 							     nla_len(attr),
-							     extack);
+							     extack, false);
 			if (err < 0)
 				goto errout;
 			cfg->fc_mp = nla_data(attr);
@@ -825,7 +825,7 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
 			err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
-							extack);
+							extack, false);
 			if (err < 0)
 				goto errout;
 			break;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 09a3d73b45baa..01df7dd795f01 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3187,7 +3187,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 		}
 
 		cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]);
-		err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack);
+		err = lwtunnel_valid_encap_type(cfg->nh_encap_type,
+						extack, true);
 		if (err < 0)
 			goto out;
 
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ef2d23a1e3d53..fb2e99a565291 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -5128,7 +5128,8 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
 
 		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
-						     cfg->fc_mp_len, extack);
+						     cfg->fc_mp_len,
+						     extack, true);
 		if (err < 0)
 			goto errout;
 	}
@@ -5147,7 +5148,8 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
-		err = lwtunnel_valid_encap_type(cfg->fc_encap_type, extack);
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
+						extack, true);
 		if (err < 0)
 			goto errout;
 	}

From 0a7565ee6ec31eb16c0476adbfc1af3f2271cb6b Mon Sep 17 00:00:00 2001
From: John Hubbard <jhubbard@nvidia.com>
Date: Thu, 13 Feb 2025 19:38:50 -0800
Subject: [PATCH 1649/2753] Revert "selftests/mm: remove local __NR_*
 definitions"

This reverts commit a5c6bc590094a1a73cf6fa3f505e1945d2bf2461.

The general approach described in commit e076eaca5906 ("selftests: break
the dependency upon local header files") was taken one step too far here:
it should not have been extended to include the syscall numbers.  This is
because doing so would require per-arch support in tools/include/uapi, and
no such support exists.

This revert fixes two separate reports of test failures, from Dave
Hansen[1], and Li Wang[2].  An excerpt of Dave's report:

Before this commit (a5c6bc590094a1a73cf6fa3f505e1945d2bf2461) things are
fine.  But after, I get:

	running PKEY tests for unsupported CPU/OS

An excerpt of Li's report:

    I just found that mlock2_() return a wrong value in mlock2-test

[1] https://lore.kernel.org/dc585017-6740-4cab-a536-b12b37a7582d@intel.com
[2] https://lore.kernel.org/CAEemH2eW=UMu9+turT2jRie7+6ewUazXmA6kL+VBo3cGDGU6RA@mail.gmail.com

Link: https://lkml.kernel.org/r/20250214033850.235171-1-jhubbard@nvidia.com
Fixes: a5c6bc590094 ("selftests/mm: remove local __NR_* definitions")
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Li Wang <liwang@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Andrei Vagin <avagin@google.com>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rich Felker <dalias@libc.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/hugepage-mremap.c      |  2 +-
 tools/testing/selftests/mm/ksm_functional_tests.c |  8 +++++++-
 tools/testing/selftests/mm/memfd_secret.c         | 14 +++++++++++++-
 tools/testing/selftests/mm/mkdirty.c              |  8 +++++++-
 tools/testing/selftests/mm/mlock2.h               |  1 -
 tools/testing/selftests/mm/protection_keys.c      |  2 +-
 tools/testing/selftests/mm/uffd-common.c          |  4 ++++
 tools/testing/selftests/mm/uffd-stress.c          | 15 ++++++++++++++-
 tools/testing/selftests/mm/uffd-unit-tests.c      | 14 +++++++++++++-
 9 files changed, 60 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/mm/hugepage-mremap.c b/tools/testing/selftests/mm/hugepage-mremap.c
index ada9156cc497b..c463d1c09c9b4 100644
--- a/tools/testing/selftests/mm/hugepage-mremap.c
+++ b/tools/testing/selftests/mm/hugepage-mremap.c
@@ -15,7 +15,7 @@
 #define _GNU_SOURCE
 #include <stdlib.h>
 #include <stdio.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/mman.h>
 #include <errno.h>
 #include <fcntl.h> /* Definition of O_* constants */
diff --git a/tools/testing/selftests/mm/ksm_functional_tests.c b/tools/testing/selftests/mm/ksm_functional_tests.c
index 66b4e111b5a27..b61803e36d1cf 100644
--- a/tools/testing/selftests/mm/ksm_functional_tests.c
+++ b/tools/testing/selftests/mm/ksm_functional_tests.c
@@ -11,7 +11,7 @@
 #include <string.h>
 #include <stdbool.h>
 #include <stdint.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <sys/mman.h>
@@ -369,6 +369,7 @@ static void test_unmerge_discarded(void)
 	munmap(map, size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_unmerge_uffd_wp(void)
 {
 	struct uffdio_writeprotect uffd_writeprotect;
@@ -429,6 +430,7 @@ static void test_unmerge_uffd_wp(void)
 unmap:
 	munmap(map, size);
 }
+#endif
 
 /* Verify that KSM can be enabled / queried with prctl. */
 static void test_prctl(void)
@@ -684,7 +686,9 @@ int main(int argc, char **argv)
 		exit(test_child_ksm());
 	}
 
+#ifdef __NR_userfaultfd
 	tests++;
+#endif
 
 	ksft_print_header();
 	ksft_set_plan(tests);
@@ -696,7 +700,9 @@ int main(int argc, char **argv)
 	test_unmerge();
 	test_unmerge_zero_pages();
 	test_unmerge_discarded();
+#ifdef __NR_userfaultfd
 	test_unmerge_uffd_wp();
+#endif
 
 	test_prot_none();
 
diff --git a/tools/testing/selftests/mm/memfd_secret.c b/tools/testing/selftests/mm/memfd_secret.c
index 74c911aa3aea9..9a0597310a765 100644
--- a/tools/testing/selftests/mm/memfd_secret.c
+++ b/tools/testing/selftests/mm/memfd_secret.c
@@ -17,7 +17,7 @@
 
 #include <stdlib.h>
 #include <string.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <errno.h>
 #include <stdio.h>
 #include <fcntl.h>
@@ -28,6 +28,8 @@
 #define pass(fmt, ...) ksft_test_result_pass(fmt, ##__VA_ARGS__)
 #define skip(fmt, ...) ksft_test_result_skip(fmt, ##__VA_ARGS__)
 
+#ifdef __NR_memfd_secret
+
 #define PATTERN	0x55
 
 static const int prot = PROT_READ | PROT_WRITE;
@@ -332,3 +334,13 @@ int main(int argc, char *argv[])
 
 	ksft_finished();
 }
+
+#else /* __NR_memfd_secret */
+
+int main(int argc, char *argv[])
+{
+	printf("skip: skipping memfd_secret test (missing __NR_memfd_secret)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_memfd_secret */
diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c
index af2fce496912b..09feeb4536460 100644
--- a/tools/testing/selftests/mm/mkdirty.c
+++ b/tools/testing/selftests/mm/mkdirty.c
@@ -9,7 +9,7 @@
  */
 #include <fcntl.h>
 #include <signal.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <string.h>
 #include <errno.h>
 #include <stdlib.h>
@@ -265,6 +265,7 @@ static void test_pte_mapped_thp(void)
 	munmap(mmap_mem, mmap_size);
 }
 
+#ifdef __NR_userfaultfd
 static void test_uffdio_copy(void)
 {
 	struct uffdio_register uffdio_register;
@@ -322,6 +323,7 @@ static void test_uffdio_copy(void)
 	munmap(dst, pagesize);
 	free(src);
 }
+#endif /* __NR_userfaultfd */
 
 int main(void)
 {
@@ -334,7 +336,9 @@ int main(void)
 			       thpsize / 1024);
 		tests += 3;
 	}
+#ifdef __NR_userfaultfd
 	tests += 1;
+#endif /* __NR_userfaultfd */
 
 	ksft_print_header();
 	ksft_set_plan(tests);
@@ -364,7 +368,9 @@ int main(void)
 	if (thpsize)
 		test_pte_mapped_thp();
 	/* Placing a fresh page via userfaultfd may set the PTE dirty. */
+#ifdef __NR_userfaultfd
 	test_uffdio_copy();
+#endif /* __NR_userfaultfd */
 
 	err = ksft_get_fail_cnt();
 	if (err)
diff --git a/tools/testing/selftests/mm/mlock2.h b/tools/testing/selftests/mm/mlock2.h
index 1e5731bab499a..4417eaa5cfb78 100644
--- a/tools/testing/selftests/mm/mlock2.h
+++ b/tools/testing/selftests/mm/mlock2.h
@@ -3,7 +3,6 @@
 #include <errno.h>
 #include <stdio.h>
 #include <stdlib.h>
-#include <asm-generic/unistd.h>
 
 static int mlock2_(void *start, size_t len, int flags)
 {
diff --git a/tools/testing/selftests/mm/protection_keys.c b/tools/testing/selftests/mm/protection_keys.c
index a4683f2476f27..35565af308af6 100644
--- a/tools/testing/selftests/mm/protection_keys.c
+++ b/tools/testing/selftests/mm/protection_keys.c
@@ -42,7 +42,7 @@
 #include <sys/wait.h>
 #include <sys/stat.h>
 #include <fcntl.h>
-#include <asm-generic/unistd.h>
+#include <unistd.h>
 #include <sys/ptrace.h>
 #include <setjmp.h>
 
diff --git a/tools/testing/selftests/mm/uffd-common.c b/tools/testing/selftests/mm/uffd-common.c
index 717539eddf987..7ad6ba660c7d6 100644
--- a/tools/testing/selftests/mm/uffd-common.c
+++ b/tools/testing/selftests/mm/uffd-common.c
@@ -673,7 +673,11 @@ int uffd_open_dev(unsigned int flags)
 
 int uffd_open_sys(unsigned int flags)
 {
+#ifdef __NR_userfaultfd
 	return syscall(__NR_userfaultfd, flags);
+#else
+	return -1;
+#endif
 }
 
 int uffd_open(unsigned int flags)
diff --git a/tools/testing/selftests/mm/uffd-stress.c b/tools/testing/selftests/mm/uffd-stress.c
index a4b83280998ab..944d559ade21f 100644
--- a/tools/testing/selftests/mm/uffd-stress.c
+++ b/tools/testing/selftests/mm/uffd-stress.c
@@ -33,10 +33,11 @@
  * pthread_mutex_lock will also verify the atomicity of the memory
  * transfer (UFFDIO_COPY).
  */
-#include <asm-generic/unistd.h>
+
 #include "uffd-common.h"
 
 uint64_t features;
+#ifdef __NR_userfaultfd
 
 #define BOUNCE_RANDOM		(1<<0)
 #define BOUNCE_RACINGFAULTS	(1<<1)
@@ -471,3 +472,15 @@ int main(int argc, char **argv)
 	       nr_pages, nr_pages_per_cpu);
 	return userfaultfd_stress();
 }
+
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("skip: Skipping userfaultfd test (missing __NR_userfaultfd)\n");
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */
diff --git a/tools/testing/selftests/mm/uffd-unit-tests.c b/tools/testing/selftests/mm/uffd-unit-tests.c
index 9ff71fa1f9bf0..74c8bc02b5063 100644
--- a/tools/testing/selftests/mm/uffd-unit-tests.c
+++ b/tools/testing/selftests/mm/uffd-unit-tests.c
@@ -5,11 +5,12 @@
  *  Copyright (C) 2015-2023  Red Hat, Inc.
  */
 
-#include <asm-generic/unistd.h>
 #include "uffd-common.h"
 
 #include "../../../../mm/gup_test.h"
 
+#ifdef __NR_userfaultfd
+
 /* The unit test doesn't need a large or random size, make it 32MB for now */
 #define  UFFD_TEST_MEM_SIZE               (32UL << 20)
 
@@ -1558,3 +1559,14 @@ int main(int argc, char *argv[])
 	return ksft_get_fail_cnt() ? KSFT_FAIL : KSFT_PASS;
 }
 
+#else /* __NR_userfaultfd */
+
+#warning "missing __NR_userfaultfd definition"
+
+int main(void)
+{
+	printf("Skipping %s (missing __NR_userfaultfd)\n", __file__);
+	return KSFT_SKIP;
+}
+
+#endif /* __NR_userfaultfd */

From 349db086a66051bc6114b64b4446787c20ac3f00 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Mon, 17 Feb 2025 10:23:04 -0800
Subject: [PATCH 1650/2753] selftests/damon/damos_quota_goal: handle minimum
 quota that cannot be further reduced

damos_quota_goal.py selftest see if DAMOS quota goals tuning feature
increases or reduces the effective size quota for given score as expected.
The tuning feature sets the minimum quota size as one byte, so if the
effective size quota is already one, we cannot expect it further be
reduced.  However the test is not aware of the edge case, and fails since
it shown no expected change of the effective quota.  Handle the case by
updating the failure logic for no change to see if it was the case, and
simply skips to next test input.

Link: https://lkml.kernel.org/r/20250217182304.45215-1-sj@kernel.org
Fixes: f1c07c0a1662 ("selftests/damon: add a test for DAMOS quota goal")
Signed-off-by: SeongJae Park <sj@kernel.org>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202502171423.b28a918d-lkp@intel.com
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>	[6.10.x]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damos_quota_goal.py | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/tools/testing/selftests/damon/damos_quota_goal.py b/tools/testing/selftests/damon/damos_quota_goal.py
index 18246f3b62f7e..f76e0412b564c 100755
--- a/tools/testing/selftests/damon/damos_quota_goal.py
+++ b/tools/testing/selftests/damon/damos_quota_goal.py
@@ -63,6 +63,9 @@ def main():
             if last_effective_bytes != 0 else -1.0))
 
         if last_effective_bytes == goal.effective_bytes:
+            # effective quota was already minimum that cannot be more reduced
+            if expect_increase is False and last_effective_bytes == 1:
+                continue
             print('efective bytes not changed: %d' % goal.effective_bytes)
             exit(1)
 

From 7277dd0a0ba4f8259f7abe37c4b7280fbfc2a182 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Tue, 18 Feb 2025 00:00:17 +0800
Subject: [PATCH 1651/2753] m68k: sun3: add check for __pgd_alloc()

Add check for the return value of __pgd_alloc() in pgd_alloc() to prevent
null pointer dereference.

Link: https://lkml.kernel.org/r/20250217160017.2375536-1-haoxiang_li2024@163.com
Fixes: a9b3c355c2e6 ("asm-generic: pgalloc: provide generic __pgd_{alloc,free}")
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Geert Uytterhoeven <geert@linux-m68k.org>
Acked-by: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Sam Creasey <sammy@sammy.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/m68k/include/asm/sun3_pgalloc.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/arch/m68k/include/asm/sun3_pgalloc.h b/arch/m68k/include/asm/sun3_pgalloc.h
index f1ae4ed890db5..80afc3a187249 100644
--- a/arch/m68k/include/asm/sun3_pgalloc.h
+++ b/arch/m68k/include/asm/sun3_pgalloc.h
@@ -44,8 +44,10 @@ static inline pgd_t * pgd_alloc(struct mm_struct *mm)
 	pgd_t *new_pgd;
 
 	new_pgd = __pgd_alloc(mm, 0);
-	memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
-	memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	if (likely(new_pgd != NULL)) {
+		memcpy(new_pgd, swapper_pg_dir, PAGE_SIZE);
+		memset(new_pgd, 0, (PAGE_OFFSET >> PGDIR_SHIFT));
+	}
 	return new_pgd;
 }
 

From a564ccfe300fa6a065beda06ab7f3c140d6b4d63 Mon Sep 17 00:00:00 2001
From: Qi Zheng <zhengqi.arch@bytedance.com>
Date: Mon, 17 Feb 2025 10:49:24 +0800
Subject: [PATCH 1652/2753] arm: pgtable: fix NULL pointer dereference issue

When update_mmu_cache_range() is called by update_mmu_cache(), the vmf
parameter is NULL, which will cause a NULL pointer dereference issue in
adjust_pte():

Unable to handle kernel NULL pointer dereference at virtual address 00000030 when read
Hardware name: Atmel AT91SAM9
PC is at update_mmu_cache_range+0x1e0/0x278
LR is at pte_offset_map_rw_nolock+0x18/0x2c
Call trace:
 update_mmu_cache_range from remove_migration_pte+0x29c/0x2ec
 remove_migration_pte from rmap_walk_file+0xcc/0x130
 rmap_walk_file from remove_migration_ptes+0x90/0xa4
 remove_migration_ptes from migrate_pages_batch+0x6d4/0x858
 migrate_pages_batch from migrate_pages+0x188/0x488
 migrate_pages from compact_zone+0x56c/0x954
 compact_zone from compact_node+0x90/0xf0
 compact_node from kcompactd+0x1d4/0x204
 kcompactd from kthread+0x120/0x12c
 kthread from ret_from_fork+0x14/0x38
Exception stack(0xc0d8bfb0 to 0xc0d8bff8)

To fix it, do not rely on whether 'ptl' is equal to decide whether to hold
the pte lock, but decide it by whether CONFIG_SPLIT_PTE_PTLOCKS is
enabled.  In addition, if two vmas map to the same PTE page, there is no
need to hold the pte lock again, otherwise a deadlock will occur.  Just
add the need_lock parameter to let adjust_pte() know this information.

Link: https://lkml.kernel.org/r/20250217024924.57996-1-zhengqi.arch@bytedance.com
Fixes: fc9c45b71f43 ("arm: adjust_pte() use pte_offset_map_rw_nolock()")
Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reported-by: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Closes: https://lore.kernel.org/lkml/CAM1KZSmZ2T_riHvay+7cKEFxoPgeVpHkVFTzVVEQ1BO0cLkHEQ@mail.gmail.com/
Acked-by: David Hildenbrand <david@redhat.com>
Tested-by: Ezra Buehler <ezra.buehler@husqvarnagroup.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Russel King <linux@armlinux.org.uk>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm/mm/fault-armv.c | 37 +++++++++++++++++++++++++------------
 1 file changed, 25 insertions(+), 12 deletions(-)

diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 2bec87c3327d2..39fd5df733178 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -62,7 +62,7 @@ static int do_adjust_pte(struct vm_area_struct *vma, unsigned long address,
 }
 
 static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
-		      unsigned long pfn, struct vm_fault *vmf)
+		      unsigned long pfn, bool need_lock)
 {
 	spinlock_t *ptl;
 	pgd_t *pgd;
@@ -99,12 +99,11 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 	if (!pte)
 		return 0;
 
-	/*
-	 * If we are using split PTE locks, then we need to take the page
-	 * lock here.  Otherwise we are using shared mm->page_table_lock
-	 * which is already locked, thus cannot take it.
-	 */
-	if (ptl != vmf->ptl) {
+	if (need_lock) {
+		/*
+		 * Use nested version here to indicate that we are already
+		 * holding one similar spinlock.
+		 */
 		spin_lock_nested(ptl, SINGLE_DEPTH_NESTING);
 		if (unlikely(!pmd_same(pmdval, pmdp_get_lockless(pmd)))) {
 			pte_unmap_unlock(pte, ptl);
@@ -114,7 +113,7 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 	ret = do_adjust_pte(vma, address, pfn, pte);
 
-	if (ptl != vmf->ptl)
+	if (need_lock)
 		spin_unlock(ptl);
 	pte_unmap(pte);
 
@@ -123,9 +122,10 @@ static int adjust_pte(struct vm_area_struct *vma, unsigned long address,
 
 static void
 make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
-	      unsigned long addr, pte_t *ptep, unsigned long pfn,
-	      struct vm_fault *vmf)
+	      unsigned long addr, pte_t *ptep, unsigned long pfn)
 {
+	const unsigned long pmd_start_addr = ALIGN_DOWN(addr, PMD_SIZE);
+	const unsigned long pmd_end_addr = pmd_start_addr + PMD_SIZE;
 	struct mm_struct *mm = vma->vm_mm;
 	struct vm_area_struct *mpnt;
 	unsigned long offset;
@@ -141,6 +141,14 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 	 */
 	flush_dcache_mmap_lock(mapping);
 	vma_interval_tree_foreach(mpnt, &mapping->i_mmap, pgoff, pgoff) {
+		/*
+		 * If we are using split PTE locks, then we need to take the pte
+		 * lock. Otherwise we are using shared mm->page_table_lock which
+		 * is already locked, thus cannot take it.
+		 */
+		bool need_lock = IS_ENABLED(CONFIG_SPLIT_PTE_PTLOCKS);
+		unsigned long mpnt_addr;
+
 		/*
 		 * If this VMA is not in our MM, we can ignore it.
 		 * Note that we intentionally mask out the VMA
@@ -151,7 +159,12 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
 		if (!(mpnt->vm_flags & VM_MAYSHARE))
 			continue;
 		offset = (pgoff - mpnt->vm_pgoff) << PAGE_SHIFT;
-		aliases += adjust_pte(mpnt, mpnt->vm_start + offset, pfn, vmf);
+		mpnt_addr = mpnt->vm_start + offset;
+
+		/* Avoid deadlocks by not grabbing the same PTE lock again. */
+		if (mpnt_addr >= pmd_start_addr && mpnt_addr < pmd_end_addr)
+			need_lock = false;
+		aliases += adjust_pte(mpnt, mpnt_addr, pfn, need_lock);
 	}
 	flush_dcache_mmap_unlock(mapping);
 	if (aliases)
@@ -194,7 +207,7 @@ void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma,
 		__flush_dcache_folio(mapping, folio);
 	if (mapping) {
 		if (cache_is_vivt())
-			make_coherent(mapping, vma, addr, ptep, pfn, vmf);
+			make_coherent(mapping, vma, addr, ptep, pfn);
 		else if (vma->vm_flags & VM_EXEC)
 			__flush_icache_all();
 	}

From b81679b1633aa43c0d973adfa816d78c1ed0d032 Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:27 +0800
Subject: [PATCH 1653/2753] mm: memory-failure: update ttu flag inside
 unmap_poisoned_folio

Patch series "mm: memory_failure: unmap poisoned folio during migrate
properly", v3.

Fix two bugs during folio migration if the folio is poisoned.


This patch (of 3):

Commit 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to
TTU_HWPOISON") introduce TTU_HWPOISON to replace TTU_IGNORE_HWPOISON in
order to stop send SIGBUS signal when accessing an error page after a
memory error on a clean folio.  However during page migration, anon folio
must be set with TTU_HWPOISON during unmap_*().  For pagecache we need
some policy just like the one in hwpoison_user_mappings to set this flag.
So move this policy from hwpoison_user_mappings to unmap_poisoned_folio to
handle this warning properly.

Warning will be produced during unamp poison folio with the following log:

  ------------[ cut here ]------------
  WARNING: CPU: 1 PID: 365 at mm/rmap.c:1847 try_to_unmap_one+0x8fc/0xd3c
  Modules linked in:
  CPU: 1 UID: 0 PID: 365 Comm: bash Tainted: G        W          6.13.0-rc1-00018-gacdb4bbda7ab #42
  Tainted: [W]=WARN
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  pstate: 20400005 (nzCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : try_to_unmap_one+0x8fc/0xd3c
  lr : try_to_unmap_one+0x3dc/0xd3c
  Call trace:
   try_to_unmap_one+0x8fc/0xd3c (P)
   try_to_unmap_one+0x3dc/0xd3c (L)
   rmap_walk_anon+0xdc/0x1f8
   rmap_walk+0x3c/0x58
   try_to_unmap+0x88/0x90
   unmap_poisoned_folio+0x30/0xa8
   do_migrate_range+0x4a0/0x568
   offline_pages+0x5a4/0x670
   memory_block_action+0x17c/0x374
   memory_subsys_offline+0x3c/0x78
   device_offline+0xa4/0xd0
   state_store+0x8c/0xf0
   dev_attr_store+0x18/0x2c
   sysfs_kf_write+0x44/0x54
   kernfs_fop_write_iter+0x118/0x1a8
   vfs_write+0x3a8/0x4bc
   ksys_write+0x6c/0xf8
   __arm64_sys_write+0x1c/0x28
   invoke_syscall+0x44/0x100
   el0_svc_common.constprop.0+0x40/0xe0
   do_el0_svc+0x1c/0x28
   el0_svc+0x30/0xd0
   el0t_64_sync_handler+0xc8/0xcc
   el0t_64_sync+0x198/0x19c
  ---[ end trace 0000000000000000 ]---

[mawupeng1@huawei.com: unmap_poisoned_folio(): remove shadowed local `mapping', per Miaohe]
  Link: https://lkml.kernel.org/r/20250219060653.3849083-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-1-mawupeng1@huawei.com
Link: https://lkml.kernel.org/r/20250217014329.3610326-2-mawupeng1@huawei.com
Fixes: 6da6b1d4a7df ("mm/hwpoison: convert TTU_IGNORE_HWPOISON to TTU_HWPOISON")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Ma Wupeng <mawupeng1@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/internal.h       |  5 ++--
 mm/memory-failure.c | 63 ++++++++++++++++++++++-----------------------
 mm/memory_hotplug.c |  3 ++-
 3 files changed, 36 insertions(+), 35 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 109ef30fee11f..20b3535935a31 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1115,7 +1115,7 @@ static inline int find_next_best_node(int node, nodemask_t *used_node_mask)
  * mm/memory-failure.c
  */
 #ifdef CONFIG_MEMORY_FAILURE
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu);
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill);
 void shake_folio(struct folio *folio);
 extern int hwpoison_filter(struct page *p);
 
@@ -1138,8 +1138,9 @@ unsigned long page_mapped_in_vma(const struct page *page,
 		struct vm_area_struct *vma);
 
 #else
-static inline void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+static inline int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
+	return -EBUSY;
 }
 #endif
 
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 995a15eb67e2c..327e02fdc029d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1556,11 +1556,35 @@ static int get_hwpoison_page(struct page *p, unsigned long flags)
 	return ret;
 }
 
-void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
+int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill)
 {
-	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
-		struct address_space *mapping;
+	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
+	struct address_space *mapping;
+
+	if (folio_test_swapcache(folio)) {
+		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
+		ttu &= ~TTU_HWPOISON;
+	}
 
+	/*
+	 * Propagate the dirty bit from PTEs to struct page first, because we
+	 * need this to decide if we should kill or just drop the page.
+	 * XXX: the dirty test could be racy: set_page_dirty() may not always
+	 * be called inside page lock (it's recommended but not enforced).
+	 */
+	mapping = folio_mapping(folio);
+	if (!must_kill && !folio_test_dirty(folio) && mapping &&
+	    mapping_can_writeback(mapping)) {
+		if (folio_mkclean(folio)) {
+			folio_set_dirty(folio);
+		} else {
+			ttu &= ~TTU_HWPOISON;
+			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
+				pfn);
+		}
+	}
+
+	if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) {
 		/*
 		 * For hugetlb folios in shared mappings, try_to_unmap
 		 * could potentially call huge_pmd_unshare.  Because of
@@ -1572,7 +1596,7 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 		if (!mapping) {
 			pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n",
 				folio_pfn(folio));
-			return;
+			return -EBUSY;
 		}
 
 		try_to_unmap(folio, ttu|TTU_RMAP_LOCKED);
@@ -1580,6 +1604,8 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 	} else {
 		try_to_unmap(folio, ttu);
 	}
+
+	return folio_mapped(folio) ? -EBUSY : 0;
 }
 
 /*
@@ -1589,8 +1615,6 @@ void unmap_poisoned_folio(struct folio *folio, enum ttu_flags ttu)
 static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 		unsigned long pfn, int flags)
 {
-	enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON;
-	struct address_space *mapping;
 	LIST_HEAD(tokill);
 	bool unmap_success;
 	int forcekill;
@@ -1613,29 +1637,6 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	if (!folio_mapped(folio))
 		return true;
 
-	if (folio_test_swapcache(folio)) {
-		pr_err("%#lx: keeping poisoned page in swap cache\n", pfn);
-		ttu &= ~TTU_HWPOISON;
-	}
-
-	/*
-	 * Propagate the dirty bit from PTEs to struct page first, because we
-	 * need this to decide if we should kill or just drop the page.
-	 * XXX: the dirty test could be racy: set_page_dirty() may not always
-	 * be called inside page lock (it's recommended but not enforced).
-	 */
-	mapping = folio_mapping(folio);
-	if (!(flags & MF_MUST_KILL) && !folio_test_dirty(folio) && mapping &&
-	    mapping_can_writeback(mapping)) {
-		if (folio_mkclean(folio)) {
-			folio_set_dirty(folio);
-		} else {
-			ttu &= ~TTU_HWPOISON;
-			pr_info("%#lx: corrupted page was clean: dropped without side effects\n",
-				pfn);
-		}
-	}
-
 	/*
 	 * First collect all the processes that have the page
 	 * mapped in dirty form.  This has to be done before try_to_unmap,
@@ -1643,9 +1644,7 @@ static bool hwpoison_user_mappings(struct folio *folio, struct page *p,
 	 */
 	collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
 
-	unmap_poisoned_folio(folio, ttu);
-
-	unmap_success = !folio_mapped(folio);
+	unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL);
 	if (!unmap_success)
 		pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n",
 		       pfn, folio_mapcount(folio));
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e3655f07dd6e3..e7e47838fd494 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1833,7 +1833,8 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (WARN_ON(folio_test_lru(folio)))
 				folio_isolate_lru(folio);
 			if (folio_mapped(folio))
-				unmap_poisoned_folio(folio, TTU_IGNORE_MLOCK);
+				unmap_poisoned_folio(folio, pfn, false);
+
 			continue;
 		}
 

From 773b9a6aa6d38894b95088e3ed6f8a701d9f50fd Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:28 +0800
Subject: [PATCH 1654/2753] mm: memory-hotplug: check folio ref count first in
 do_migrate_range

If a folio has an increased reference count, folio_try_get() will acquire
it, perform necessary operations, and then release it.  In the case of a
poisoned folio without an elevated reference count (which is unlikely for
memory-failure), folio_try_get() will simply bypass it.

Therefore, relocate the folio_try_get() function, responsible for checking
and acquiring this reference count at first.

Link: https://lkml.kernel.org/r/20250217014329.3610326-3-mawupeng1@huawei.com
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 20 +++++++-------------
 1 file changed, 7 insertions(+), 13 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e7e47838fd494..a6abd8d4a09c6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1822,12 +1822,12 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		if (folio_test_large(folio))
 			pfn = folio_pfn(folio) + folio_nr_pages(folio) - 1;
 
-		/*
-		 * HWPoison pages have elevated reference counts so the migration would
-		 * fail on them. It also doesn't make any sense to migrate them in the
-		 * first place. Still try to unmap such a page in case it is still mapped
-		 * (keep the unmap as the catch all safety net).
-		 */
+		if (!folio_try_get(folio))
+			continue;
+
+		if (unlikely(page_folio(page) != folio))
+			goto put_folio;
+
 		if (folio_test_hwpoison(folio) ||
 		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
 			if (WARN_ON(folio_test_lru(folio)))
@@ -1835,14 +1835,8 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 			if (folio_mapped(folio))
 				unmap_poisoned_folio(folio, pfn, false);
 
-			continue;
-		}
-
-		if (!folio_try_get(folio))
-			continue;
-
-		if (unlikely(page_folio(page) != folio))
 			goto put_folio;
+		}
 
 		if (!isolate_folio_to_list(folio, &source)) {
 			if (__ratelimit(&migrate_rs)) {

From af288a426c3e3552b62595c6138ec6371a17dbba Mon Sep 17 00:00:00 2001
From: Ma Wupeng <mawupeng1@huawei.com>
Date: Mon, 17 Feb 2025 09:43:29 +0800
Subject: [PATCH 1655/2753] hwpoison, memory_hotplug: lock folio before unmap
 hwpoisoned folio

Commit b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to
be offlined) add page poison checks in do_migrate_range in order to make
offline hwpoisoned page possible by introducing isolate_lru_page and
try_to_unmap for hwpoisoned page.  However folio lock must be held before
calling try_to_unmap.  Add it to fix this problem.

Warning will be produced if folio is not locked during unmap:

  ------------[ cut here ]------------
  kernel BUG at ./include/linux/swapops.h:400!
  Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
  Modules linked in:
  CPU: 4 UID: 0 PID: 411 Comm: bash Tainted: G        W          6.13.0-rc1-00016-g3c434c7ee82a-dirty #41
  Tainted: [W]=WARN
  Hardware name: QEMU QEMU Virtual Machine, BIOS 0.0.0 02/06/2015
  pstate: 40400005 (nZcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
  pc : try_to_unmap_one+0xb08/0xd3c
  lr : try_to_unmap_one+0x3dc/0xd3c
  Call trace:
   try_to_unmap_one+0xb08/0xd3c (P)
   try_to_unmap_one+0x3dc/0xd3c (L)
   rmap_walk_anon+0xdc/0x1f8
   rmap_walk+0x3c/0x58
   try_to_unmap+0x88/0x90
   unmap_poisoned_folio+0x30/0xa8
   do_migrate_range+0x4a0/0x568
   offline_pages+0x5a4/0x670
   memory_block_action+0x17c/0x374
   memory_subsys_offline+0x3c/0x78
   device_offline+0xa4/0xd0
   state_store+0x8c/0xf0
   dev_attr_store+0x18/0x2c
   sysfs_kf_write+0x44/0x54
   kernfs_fop_write_iter+0x118/0x1a8
   vfs_write+0x3a8/0x4bc
   ksys_write+0x6c/0xf8
   __arm64_sys_write+0x1c/0x28
   invoke_syscall+0x44/0x100
   el0_svc_common.constprop.0+0x40/0xe0
   do_el0_svc+0x1c/0x28
   el0_svc+0x30/0xd0
   el0t_64_sync_handler+0xc8/0xcc
   el0t_64_sync+0x198/0x19c
  Code: f9407be0 b5fff320 d4210000 17ffff97 (d4210000)
  ---[ end trace 0000000000000000 ]---

Link: https://lkml.kernel.org/r/20250217014329.3610326-4-mawupeng1@huawei.com
Fixes: b15c87263a69 ("hwpoison, memory_hotplug: allow hwpoisoned pages to be offlined")
Signed-off-by: Ma Wupeng <mawupeng1@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory_hotplug.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a6abd8d4a09c6..16cf9e17077e3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1832,8 +1832,11 @@ static void do_migrate_range(unsigned long start_pfn, unsigned long end_pfn)
 		    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio))) {
 			if (WARN_ON(folio_test_lru(folio)))
 				folio_isolate_lru(folio);
-			if (folio_mapped(folio))
+			if (folio_mapped(folio)) {
+				folio_lock(folio);
 				unmap_poisoned_folio(folio, pfn, false);
+				folio_unlock(folio);
+			}
 
 			goto put_folio;
 		}

From 04ec365e3fdf136ba5f9053b02fb6c3368a22e83 Mon Sep 17 00:00:00 2001
From: Ujwal Kundur <ujwal.kundur@gmail.com>
Date: Sat, 15 Feb 2025 16:21:07 +0530
Subject: [PATCH 1656/2753] Documentation: fix doc link to fault-injection.rst

Fix incorrect reference to fault-injection docs

Link: https://lkml.kernel.org/r/20250215105106.734-1-ujwal.kundur@gmail.com
Signed-off-by: Ujwal Kundur <ujwal.kundur@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 lib/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 1af972a92d06f..35796c290ca35 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2103,7 +2103,7 @@ config FAIL_SKB_REALLOC
 	  reallocated, catching possible invalid pointers to the skb.
 
 	  For more information, check
-	  Documentation/dev-tools/fault-injection/fault-injection.rst
+	  Documentation/fault-injection/fault-injection.rst
 
 config FAULT_INJECTION_CONFIGFS
 	bool "Configfs interface for fault-injection capabilities"

From 19fac3c93991502a22c5132824c40b6a2e64b136 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 18 Feb 2025 10:14:11 +0100
Subject: [PATCH 1657/2753] dma: kmsan: export kmsan_handle_dma() for modules

kmsan_handle_dma() is used by virtio_ring() which can be built as a
module.  kmsan_handle_dma() needs to be exported otherwise building the
virtio_ring fails.

Export kmsan_handle_dma for modules.

Link: https://lkml.kernel.org/r/20250218091411.MMS3wBN9@linutronix.de
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202502150634.qjxwSeJR-lkp@intel.com/
Fixes: 7ade4f10779c ("dma: kmsan: unpoison DMA mappings")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Alexander Potapenko <glider@google.com>
Cc: Dmitriy Vyukov <dvyukov@google.com>
Cc: Macro Elver <elver@google.com>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/kmsan/hooks.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 3ea50f09311fd..3df45c25c1f62 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -357,6 +357,7 @@ void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
 		size -= to_go;
 	}
 }
+EXPORT_SYMBOL_GPL(kmsan_handle_dma);
 
 void kmsan_handle_dma_sg(struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir)

From c3e998398de48a7528842f05858a3a6bb21002e6 Mon Sep 17 00:00:00 2001
From: gao xu <gaoxu2@honor.com>
Date: Wed, 19 Feb 2025 01:56:28 +0000
Subject: [PATCH 1658/2753] mm: fix possible NULL pointer dereference in
 __swap_duplicate

Add a NULL check on the return value of swp_swap_info in __swap_duplicate
to prevent crashes caused by NULL pointer dereference.

The reason why swp_swap_info() returns NULL is unclear; it may be due
to CPU cache issues or DDR bit flips.  The probability of this issue is
very small - it has been observed to occur approximately 1 in 500,000
times per week.  The stack info we encountered is as follows:

Unable to handle kernel NULL pointer dereference at virtual address
0000000000000058
[RB/E]rb_sreason_str_set: sreason_str set null_pointer
Mem abort info:
  ESR = 0x0000000096000005
  EC = 0x25: DABT (current EL), IL = 32 bits
  SET = 0, FnV = 0
  EA = 0, S1PTW = 0
  FSC = 0x05: level 1 translation fault
Data abort info:
  ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
  CM = 0, WnR = 0, TnD = 0, TagAccess = 0
  GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
user pgtable: 4k pages, 39-bit VAs, pgdp=00000008a80e5000
[0000000000000058] pgd=0000000000000000, p4d=0000000000000000,
pud=0000000000000000
Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP
Skip md ftrace buffer dump for: 0x1609e0
...
pc : swap_duplicate+0x44/0x164
lr : copy_page_range+0x508/0x1e78
sp : ffffffc0f2a699e0
x29: ffffffc0f2a699e0 x28: ffffff8a5b28d388 x27: ffffff8b06603388
x26: ffffffdf7291fe70 x25: 0000000000000006 x24: 0000000000100073
x23: 00000000002d2d2f x22: 0000000000000008 x21: 0000000000000000
x20: 00000000002d2d2f x19: 18000000002d2d2f x18: ffffffdf726faec0
x17: 0000000000000000 x16: 0010000000000001 x15: 0040000000000001
x14: 0400000000000001 x13: ff7ffffffffffb7f x12: ffeffffffffffbff
x11: ffffff8a5c7e1898 x10: 0000000000000018 x9 : 0000000000000006
x8 : 1800000000000000 x7 : 0000000000000000 x6 : ffffff8057c01f10
x5 : 000000000000a318 x4 : 0000000000000000 x3 : 0000000000000000
x2 : 0000006daf200000 x1 : 0000000000000001 x0 : 18000000002d2d2f
Call trace:
 swap_duplicate+0x44/0x164
 copy_page_range+0x508/0x1e78
 copy_process+0x1278/0x21cc
 kernel_clone+0x90/0x438
 __arm64_sys_clone+0x5c/0x8c
 invoke_syscall+0x58/0x110
 do_el0_svc+0x8c/0xe0
 el0_svc+0x38/0x9c
 el0t_64_sync_handler+0x44/0xec
 el0t_64_sync+0x1a8/0x1ac
Code: 9139c35a 71006f3f 54000568 f8797b55 (f9402ea8)
---[ end trace 0000000000000000 ]---
Kernel panic - not syncing: Oops: Fatal exception
SMP: stopping secondary CPUs

The patch seems to only provide a workaround, but there are no more
effective software solutions to handle the bit flips problem.  This path
will change the issue from a system crash to a process exception, thereby
reducing the impact on the entire machine.

akpm: this is probably a kernel bug, but this patch keeps the system
running and doesn't reduce that bug's debuggability.

Link: https://lkml.kernel.org/r/e223b0e6ba2f4924984b1917cc717bd5@honor.com
Signed-off-by: gao xu <gaoxu2@honor.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Yosry Ahmed <yosry.ahmed@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index ba19430dd4ead..fab99d67026aa 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3542,6 +3542,10 @@ static int __swap_duplicate(swp_entry_t entry, unsigned char usage, int nr)
 	int err, i;
 
 	si = swp_swap_info(entry);
+	if (WARN_ON_ONCE(!si)) {
+		pr_err("%s%08lx\n", Bad_file, entry.val);
+		return -EINVAL;
+	}
 
 	offset = swp_offset(entry);
 	VM_WARN_ON(nr > SWAPFILE_CLUSTER - offset % SWAPFILE_CLUSTER);

From 67bab13307c83fb742c2556b06cdc39dbad27f07 Mon Sep 17 00:00:00 2001
From: Ge Yang <yangge1116@126.com>
Date: Wed, 19 Feb 2025 11:46:44 +0800
Subject: [PATCH 1659/2753] mm/hugetlb: wait for hugetlb folios to be freed

Since the introduction of commit c77c0a8ac4c52 ("mm/hugetlb: defer freeing
of huge pages if in non-task context"), which supports deferring the
freeing of hugetlb pages, the allocation of contiguous memory through
cma_alloc() may fail probabilistically.

In the CMA allocation process, if it is found that the CMA area is
occupied by in-use hugetlb folios, these in-use hugetlb folios need to be
migrated to another location.  When there are no available hugetlb folios
in the free hugetlb pool during the migration of in-use hugetlb folios,
new folios are allocated from the buddy system.  A temporary state is set
on the newly allocated folio.  Upon completion of the hugetlb folio
migration, the temporary state is transferred from the new folios to the
old folios.  Normally, when the old folios with the temporary state are
freed, it is directly released back to the buddy system.  However, due to
the deferred freeing of hugetlb pages, the PageBuddy() check fails,
ultimately leading to the failure of cma_alloc().

Here is a simplified call trace illustrating the process:
cma_alloc()
    ->__alloc_contig_migrate_range() // Migrate in-use hugetlb folios
        ->unmap_and_move_huge_page()
            ->folio_putback_hugetlb() // Free old folios
    ->test_pages_isolated()
        ->__test_page_isolated_in_pageblock()
             ->PageBuddy(page) // Check if the page is in buddy

To resolve this issue, we have implemented a function named
wait_for_freed_hugetlb_folios().  This function ensures that the hugetlb
folios are properly released back to the buddy system after their
migration is completed.  By invoking wait_for_freed_hugetlb_folios()
before calling PageBuddy(), we ensure that PageBuddy() will succeed.

Link: https://lkml.kernel.org/r/1739936804-18199-1-git-send-email-yangge1116@126.com
Fixes: c77c0a8ac4c5 ("mm/hugetlb: defer freeing of huge pages if in non-task context")
Signed-off-by: Ge Yang <yangge1116@126.com>
Reviewed-by: Muchun Song <muchun.song@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  5 +++++
 mm/hugetlb.c            |  8 ++++++++
 mm/page_isolation.c     | 10 ++++++++++
 3 files changed, 23 insertions(+)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index ec8c0ccc8f959..dbe76d4f1bfc8 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -682,6 +682,7 @@ struct huge_bootmem_page {
 
 int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
 int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
+void wait_for_freed_hugetlb_folios(void);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
@@ -1066,6 +1067,10 @@ static inline int replace_free_hugepage_folios(unsigned long start_pfn,
 	return 0;
 }
 
+static inline void wait_for_freed_hugetlb_folios(void)
+{
+}
+
 static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 					   unsigned long addr,
 					   bool cow_from_owner)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 163190e89ea16..811b29f77abf8 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2943,6 +2943,14 @@ int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn)
 	return ret;
 }
 
+void wait_for_freed_hugetlb_folios(void)
+{
+	if (llist_empty(&hpage_freelist))
+		return;
+
+	flush_work(&free_hpage_work);
+}
+
 typedef enum {
 	/*
 	 * For either 0/1: we checked the per-vma resv map, and one resv
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index c608e9d728655..a051a29e95ad0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -607,6 +607,16 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	struct zone *zone;
 	int ret;
 
+	/*
+	 * Due to the deferred freeing of hugetlb folios, the hugepage folios may
+	 * not immediately release to the buddy system. This can cause PageBuddy()
+	 * to fail in __test_page_isolated_in_pageblock(). To ensure that the
+	 * hugetlb folios are properly released back to the buddy system, we
+	 * invoke the wait_for_freed_hugetlb_folios() function to wait for the
+	 * release to complete.
+	 */
+	wait_for_freed_hugetlb_folios();
+
 	/*
 	 * Note: pageblock_nr_pages != MAX_PAGE_ORDER. Then, chunks of free
 	 * pages are not aligned to pageblock_nr_pages.

From 47b16d0462a460000b8f05dfb1292377ac48f3ca Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Sat, 22 Feb 2025 16:19:52 +0000
Subject: [PATCH 1660/2753] mm: abort vma_modify() on merge out of memory
 failure

The remainder of vma_modify() relies upon the vmg state remaining pristine
after a merge attempt.

Usually this is the case, however in the one edge case scenario of a merge
attempt failing not due to the specified range being unmergeable, but
rather due to an out of memory error arising when attempting to commit the
merge, this assumption becomes untrue.

This results in vmg->start, end being modified, and thus the proceeding
attempts to split the VMA will be done with invalid start/end values.

Thankfully, it is likely practically impossible for us to hit this in
reality, as it would require a maple tree node pre-allocation failure that
would likely never happen due to it being 'too small to fail', i.e.  the
kernel would simply keep retrying reclaim until it succeeded.

However, this scenario remains theoretically possible, and what we are
doing here is wrong so we must correct it.

The safest option is, when this scenario occurs, to simply give up the
operation.  If we cannot allocate memory to merge, then we cannot allocate
memory to split either (perhaps moreso!).

Any scenario where this would be happening would be under very extreme
(likely fatal) memory pressure, so it's best we give up early.

So there is no doubt it is appropriate to simply bail out in this
scenario.

However, in general we must if at all possible never assume VMG state is
stable after a merge attempt, since merge operations update VMG fields.
As a result, additionally also make this clear by storing start, end in
local variables.

The issue was reported originally by syzkaller, and by Brad Spengler (via
an off-list discussion), and in both instances it manifested as a
triggering of the assert:

	VM_WARN_ON_VMG(start >= end, vmg);

In vma_merge_existing_range().

It seems at least one scenario in which this is occurring is one in which
the merge being attempted is due to an madvise() across multiple VMAs
which looks like this:

        start     end
          |<------>|
     |----------|------|
     |   vma    | next |
     |----------|------|

When madvise_walk_vmas() is invoked, we first find vma in the above
(determining prev to be equal to vma as we are offset into vma), and then
enter the loop.

We determine the end of vma that forms part of the range we are
madvise()'ing by setting 'tmp' to this value:

		/* Here vma->vm_start <= start < (end|vma->vm_end) */
		tmp = vma->vm_end;

We then invoke the madvise() operation via visit(), letting prev get
updated to point to vma as part of the operation:

		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
		error = visit(vma, &prev, start, tmp, arg);

Where the visit() function pointer in this instance is
madvise_vma_behavior().

As observed in syzkaller reports, it is ultimately madvise_update_vma()
that is invoked, calling vma_modify_flags_name() and vma_modify() in turn.

Then, in vma_modify(), we attempt the merge:

	merged = vma_merge_existing_range(vmg);
	if (merged)
		return merged;

We invoke this with vmg->start, end set to start, tmp as such:

        start  tmp
          |<--->|
     |----------|------|
     |   vma    | next |
     |----------|------|

We find ourselves in the merge right scenario, but the one in which we
cannot remove the middle (we are offset into vma).

Here we have a special case where vmg->start, end get set to perhaps
unintuitive values - we intended to shrink the middle VMA and expand the
next.

This means vmg->start, end are set to...  vma->vm_start, start.

Now the commit_merge() fails, and vmg->start, end are left like this.
This means we return to the rest of vma_modify() with vmg->start, end
(here denoted as start', end') set as:

  start' end'
     |<-->|
     |----------|------|
     |   vma    | next |
     |----------|------|

So we now erroneously try to split accordingly.  This is where the
unfortunate stuff begins.

We start with:

	/* Split any preceding portion of the VMA. */
	if (vma->vm_start < vmg->start) {
		...
	}

This doesn't trigger as we are no longer offset into vma at the start.

But then we invoke:

	/* Split any trailing portion of the VMA. */
	if (vma->vm_end > vmg->end) {
		...
	}

Which does get invoked. This leaves us with:

  start' end'
     |<-->|
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|

We then return ultimately to madvise_walk_vmas().  Here 'new' is unknown,
and putting back the values known in this function we are faced with:

        start tmp end
          |     |  |
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|
      prev

Then:

		start = tmp;

So:

             start end
                |  |
     |----|-----|------|
     | vma| new | next |
     |----|-----|------|
      prev

The following code does not cause anything to happen:

		if (prev && start < prev->vm_end)
			start = prev->vm_end;
		if (start >= end)
			break;

And then we invoke:

		if (prev)
			vma = find_vma(mm, prev->vm_end);

Which is where a problem occurs - we don't know about 'new' so we
essentially look for the vma after prev, which is new, whereas we actually
intended to discover next!

So we end up with:

             start end
                |  |
     |----|-----|------|
     |prev| vma | next |
     |----|-----|------|

And we have successfully bypassed all of the checks madvise_walk_vmas()
has to ensure early exit should we end up moving out of range.

We loop around, and hit:

		/* Here vma->vm_start <= start < (end|vma->vm_end) */
		tmp = vma->vm_end;

Oh dear. Now we have:

              tmp
             start end
                |  |
     |----|-----|------|
     |prev| vma | next |
     |----|-----|------|

We then invoke:

		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
		error = visit(vma, &prev, start, tmp, arg);

Where start == tmp. That is, a zero range. This is not good.

We invoke visit() which is madvise_vma_behavior() which does not check the
range (for good reason, it assumes all checks have been done before it was
called), which in turn finally calls madvise_update_vma().

The madvise_update_vma() function calls vma_modify_flags_name() in turn,
which ultimately invokes vma_modify() with...  start == end.

vma_modify() calls vma_merge_existing_range() and finally we hit:

	VM_WARN_ON_VMG(start >= end, vmg);

Which triggers, as start == end.

While it might be useful to add some CONFIG_DEBUG_VM asserts in these
instances to catch this kind of error, since we have just eliminated any
possibility of that happening, we will add such asserts separately as to
reduce churn and aid backporting.

Link: https://lkml.kernel.org/r/20250222161952.41957-1-lorenzo.stoakes@oracle.com
Fixes: 2f1c6611b0a8 ("mm: introduce vma_merge_struct and abstract vma_merge(),vma_modify()")
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Tested-by: Brad Spengler <brad.spengler@opensrcsec.com>
Reported-by: Brad Spengler <brad.spengler@opensrcsec.com>
Reported-by: syzbot+46423ed8fa1f1148c6e4@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-mm/6774c98f.050a0220.25abdd.0991.GAE@google.com/
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vma.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/mm/vma.c b/mm/vma.c
index af1d549b179c9..96bcb372c90e4 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -1509,24 +1509,28 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 {
 	struct vm_area_struct *vma = vmg->vma;
+	unsigned long start = vmg->start;
+	unsigned long end = vmg->end;
 	struct vm_area_struct *merged;
 
 	/* First, try to merge. */
 	merged = vma_merge_existing_range(vmg);
 	if (merged)
 		return merged;
+	if (vmg_nomem(vmg))
+		return ERR_PTR(-ENOMEM);
 
 	/* Split any preceding portion of the VMA. */
-	if (vma->vm_start < vmg->start) {
-		int err = split_vma(vmg->vmi, vma, vmg->start, 1);
+	if (vma->vm_start < start) {
+		int err = split_vma(vmg->vmi, vma, start, 1);
 
 		if (err)
 			return ERR_PTR(err);
 	}
 
 	/* Split any trailing portion of the VMA. */
-	if (vma->vm_end > vmg->end) {
-		int err = split_vma(vmg->vmi, vma, vmg->end, 0);
+	if (vma->vm_end > end) {
+		int err = split_vma(vmg->vmi, vma, end, 0);
 
 		if (err)
 			return ERR_PTR(err);

From 51f271c1940fc9a5f77931ec603b457ea293bd56 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Mon, 24 Feb 2025 19:39:10 +0800
Subject: [PATCH 1661/2753] mm: swap: add back full cluster when no entry is
 reclaimed

If no swap cache is reclaimed, cluster taken off from full_clusters list
will not be put in any list and we can't reclaime HAS_CACHE slots
efficiently.  Do relocate_cluster for such cluster to avoid inefficiency.

Link: https://lkml.kernel.org/r/20250224113910.522439-1-shikemeng@huaweicloud.com
Fixes: 3b644773eefd ("mm, swap: reduce contention on device lock")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index fab99d67026aa..a6c41c7ffb037 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -858,6 +858,10 @@ static void swap_reclaim_full_clusters(struct swap_info_struct *si, bool force)
 			offset++;
 		}
 
+		/* in case no swap cache is reclaimed */
+		if (ci->flags == CLUSTER_FLAG_NONE)
+			relocate_cluster(si, ci);
+
 		unlock_cluster(ci);
 		if (to_scan <= 0)
 			break;

From 7a2e7ae5d13658ada38898e5a3a8a40a7910db06 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Sun, 23 Feb 2025 00:08:46 +0800
Subject: [PATCH 1662/2753] mm: swap: use correct step in loop to wait all
 clusters in wait_for_allocation()

Use correct step in loop to wait all clusters in wait_for_allocation().
If we miss some cluster in wait_for_allocation(), use after free may occur
as follows:

shmem_writepage                  swapoff
 folio_alloc_swap
  get_swap_pages
   scan_swap_map_slots
    cluster_alloc_swap_entry
     alloc_swap_scan_cluster
      cluster_alloc_range
       /* SWP_WRITEOK is valid */
       if (!(si->flags & SWP_WRITEOK))

                                  ...
                                  del_from_avail_list(p, true);
                                  ...
                                  /* miss the cluster in shmem_writepage */
                                  wait_for_allocation()
                                  ...
                                  try_to_unuse()

       memset(si->swap_map + start, usage, nr_pages);
       swap_range_alloc(si, nr_pages);
       ci->count += nr_pages;
       /* return a valid entry */

                                  ...
                                  exit_swap_address_space(p->type);
                                  ...

 ...
 add_to_swap_cache
  /* dereference swap_address_space(entry) which is NULL */
  xas_lock_irq(&xas);

Link: https://lkml.kernel.org/r/20250222160850.505274-3-shikemeng@huaweicloud.com
Fixes: 9a0ddeb79880 ("mm, swap: hold a reference during scan and cleanup flag usage")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index a6c41c7ffb037..6460b6cb36c99 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -2645,7 +2645,6 @@ static void wait_for_allocation(struct swap_info_struct *si)
 	for (offset = 0; offset < end; offset += SWAPFILE_CLUSTER) {
 		ci = lock_cluster(si, offset);
 		unlock_cluster(ci);
-		offset += SWAPFILE_CLUSTER;
 	}
 }
 

From 57d910cffaa0be981f558ff603e2d896b36b8241 Mon Sep 17 00:00:00 2001
From: Kemeng Shi <shikemeng@huaweicloud.com>
Date: Sun, 23 Feb 2025 00:08:47 +0800
Subject: [PATCH 1663/2753] mm, swap: avoid BUG_ON in relocate_cluster()

If allocation is racy with swapoff, we may call free_cluster for cluster
already in free list and trigger BUG_ON() as following:

Allocation                        Swapoff
cluster_alloc_swap_entry
 ...
 /* may get a free cluster with offset */
 offset = xxx;
 if (offset)
  ci = lock_cluster(si, offset);

                                  ...
                                   del_from_avail_list(p, true);
                                    si->flags &= ~SWP_WRITEOK;

  alloc_swap_scan_cluster(si, ci, ...)
   ...
   /* failed to alloc entry from free entry */
   if (!cluster_alloc_range(...))
    break;
   ...
   /* add back a free cluster */
   relocate_cluster(si, ci);
    if (!ci->count)
     free_cluster(si, ci);
      VM_BUG_ON(ci->flags == CLUSTER_FLAG_FREE);

To prevent the BUG_ON(), call free_cluster() for free cluster to move the
cluster to tail of list.

Check cluster is not free before calling free_cluster() in
relocate_cluster() to avoid BUG_ON().

Link: https://lkml.kernel.org/r/20250222160850.505274-4-shikemeng@huaweicloud.com
Fixes: 3b644773eefd ("mm, swap: reduce contention on device lock")
Signed-off-by: Kemeng Shi <shikemeng@huaweicloud.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/swapfile.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index 6460b6cb36c99..df7c4e8b089ca 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -653,7 +653,8 @@ static void relocate_cluster(struct swap_info_struct *si,
 		return;
 
 	if (!ci->count) {
-		free_cluster(si, ci);
+		if (ci->flags != CLUSTER_FLAG_FREE)
+			free_cluster(si, ci);
 	} else if (ci->count != SWAPFILE_CLUSTER) {
 		if (ci->flags != CLUSTER_FLAG_FRAG)
 			move_cluster(si, ci, &si->frag_clusters[ci->order],

From ce6d9c1c2b5cc785016faa11b48b6cd317eb367e Mon Sep 17 00:00:00 2001
From: Mike Snitzer <snitzer@kernel.org>
Date: Mon, 24 Feb 2025 21:20:02 -0500
Subject: [PATCH 1664/2753] NFS: fix nfs_release_folio() to not deadlock via
 kcompactd writeback

Add PF_KCOMPACTD flag and current_is_kcompactd() helper to check for it so
nfs_release_folio() can skip calling nfs_wb_folio() from kcompactd.

Otherwise NFS can deadlock waiting for kcompactd enduced writeback which
recurses back to NFS (which triggers writeback to NFSD via NFS loopback
mount on the same host, NFSD blocks waiting for XFS's call to
__filemap_get_folio):

6070.550357] INFO: task kcompactd0:58 blocked for more than 4435 seconds.

{---
[58] "kcompactd0"
[<0>] folio_wait_bit+0xe8/0x200
[<0>] folio_wait_writeback+0x2b/0x80
[<0>] nfs_wb_folio+0x80/0x1b0 [nfs]
[<0>] nfs_release_folio+0x68/0x130 [nfs]
[<0>] split_huge_page_to_list_to_order+0x362/0x840
[<0>] migrate_pages_batch+0x43d/0xb90
[<0>] migrate_pages_sync+0x9a/0x240
[<0>] migrate_pages+0x93c/0x9f0
[<0>] compact_zone+0x8e2/0x1030
[<0>] compact_node+0xdb/0x120
[<0>] kcompactd+0x121/0x2e0
[<0>] kthread+0xcf/0x100
[<0>] ret_from_fork+0x31/0x40
[<0>] ret_from_fork_asm+0x1a/0x30
---}

[akpm@linux-foundation.org: fix build]
Link: https://lkml.kernel.org/r/20250225022002.26141-1-snitzer@kernel.org
Fixes: 96780ca55e3c ("NFS: fix up nfs_release_folio() to try to release the page")
Signed-off-by: Mike Snitzer <snitzer@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/nfs/file.c              | 3 ++-
 include/linux/compaction.h | 5 +++++
 include/linux/sched.h      | 2 +-
 mm/compaction.c            | 3 +++
 4 files changed, 11 insertions(+), 2 deletions(-)

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 1bb646752e466..033feeab8c346 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -29,6 +29,7 @@
 #include <linux/pagemap.h>
 #include <linux/gfp.h>
 #include <linux/swap.h>
+#include <linux/compaction.h>
 
 #include <linux/uaccess.h>
 #include <linux/filelock.h>
@@ -457,7 +458,7 @@ static bool nfs_release_folio(struct folio *folio, gfp_t gfp)
 	/* If the private flag is set, then the folio is not freeable */
 	if (folio_test_private(folio)) {
 		if ((current_gfp_context(gfp) & GFP_KERNEL) != GFP_KERNEL ||
-		    current_is_kswapd())
+		    current_is_kswapd() || current_is_kcompactd())
 			return false;
 		if (nfs_wb_folio(folio->mapping->host, folio) < 0)
 			return false;
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index e947764960496..7bf0c521db634 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order)
 	return 2UL << order;
 }
 
+static inline int current_is_kcompactd(void)
+{
+	return current->flags & PF_KCOMPACTD;
+}
+
 #ifdef CONFIG_COMPACTION
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 9632e3318e0d6..9c15365a30c08 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1701,7 +1701,7 @@ extern struct pid *cad_pid;
 #define PF_USED_MATH		0x00002000	/* If unset the fpu must be initialized before use */
 #define PF_USER_WORKER		0x00004000	/* Kernel thread cloned from userspace thread */
 #define PF_NOFREEZE		0x00008000	/* This thread should not be frozen */
-#define PF__HOLE__00010000	0x00010000
+#define PF_KCOMPACTD		0x00010000	/* I am kcompactd */
 #define PF_KSWAPD		0x00020000	/* I am kswapd */
 #define PF_MEMALLOC_NOFS	0x00040000	/* All allocations inherit GFP_NOFS. See memalloc_nfs_save() */
 #define PF_MEMALLOC_NOIO	0x00080000	/* All allocations inherit GFP_NOIO. See memalloc_noio_save() */
diff --git a/mm/compaction.c b/mm/compaction.c
index 12ed8425fa175..a3203d97123ea 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -3181,6 +3181,7 @@ static int kcompactd(void *p)
 	long default_timeout = msecs_to_jiffies(HPAGE_FRAG_CHECK_INTERVAL_MSEC);
 	long timeout = default_timeout;
 
+	current->flags |= PF_KCOMPACTD;
 	set_freezable();
 
 	pgdat->kcompactd_max_order = 0;
@@ -3237,6 +3238,8 @@ static int kcompactd(void *p)
 			pgdat->proactive_compact_trigger = false;
 	}
 
+	current->flags &= ~PF_KCOMPACTD;
+
 	return 0;
 }
 

From c29564d8b46f64f5e6e6f1c9c02f7761b7b90963 Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Fri, 21 Feb 2025 15:16:25 +0800
Subject: [PATCH 1665/2753] include/linux/log2.h: mark is_power_of_2() with
 __always_inline

When building kernel with randconfig, there is an error:

In function `kvm_is_cr4_bit_set',inlined from
`kvm_update_cpuid_runtime' at arch/x86/kvm/cpuid.c:310:9:

include/linux/compiler_types.h:542:38: error: call to
`__compiletime_assert_380' declared with attribute error:
BUILD_BUG_ON failed: !is_power_of_2(cr4_bit).

'!is_power_of_2(X86_CR4_OSXSAVE)' is False, but gcc treats is_power_of_2()
as non-inline function and a compilation error happens. Fix this by marking
is_power_of_2() with __always_inline.

Link: https://lkml.kernel.org/r/20250221071624.1356899-1-suhui@nfschina.com
Signed-off-by: Su Hui <suhui@nfschina.com>
Cc: Binbin Wu <binbin.wu@linux.intel.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Sean Christopherson <seanjc@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/log2.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/log2.h b/include/linux/log2.h
index 9f30d087a1281..1366cb688a6d9 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -41,7 +41,7 @@ int __ilog2_u64(u64 n)
  * *not* considered a power of two.
  * Return: true if @n is a power of 2, otherwise false.
  */
-static inline __attribute__((const))
+static __always_inline __attribute__((const))
 bool is_power_of_2(unsigned long n)
 {
 	return (n != 0 && ((n & (n - 1)) == 0));

From 1c684d77dfbcf926e0dd28f6d260e8fdd8a58e85 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:31 -0800
Subject: [PATCH 1666/2753] selftests/damon/damos_quota: make real expectation
 of quota exceeds

Patch series "selftests/damon: three fixes for false results".

Fix three DAMON selftest bugs that cause two and one false positive
failures and successes.


This patch (of 3):

damos_quota.py assumes the quota will always exceeded.  But whether quota
will be exceeded or not depend on the monitoring results.  Actually the
monitored workload has chaning access pattern and hence sometimes the
quota may not really be exceeded.  As a result, false positive test
failures happen.  Expect how much time the quota will be exceeded by
checking the monitoring results, and use it instead of the naive
assumption.

Link: https://lkml.kernel.org/r/20250225222333.505646-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20250225222333.505646-2-sj@kernel.org
Fixes: 51f58c9da14b ("selftests/damon: add a test for DAMOS quota")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damos_quota.py | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/damon/damos_quota.py b/tools/testing/selftests/damon/damos_quota.py
index 7d4c6bb2e3cd2..57c4937aaed28 100755
--- a/tools/testing/selftests/damon/damos_quota.py
+++ b/tools/testing/selftests/damon/damos_quota.py
@@ -51,16 +51,19 @@ def main():
         nr_quota_exceeds = scheme.stats.qt_exceeds
 
     wss_collected.sort()
+    nr_expected_quota_exceeds = 0
     for wss in wss_collected:
         if wss > sz_quota:
             print('quota is not kept: %s > %s' % (wss, sz_quota))
             print('collected samples are as below')
             print('\n'.join(['%d' % wss for wss in wss_collected]))
             exit(1)
+        if wss == sz_quota:
+            nr_expected_quota_exceeds += 1
 
-    if nr_quota_exceeds < len(wss_collected):
-        print('quota is not always exceeded: %d > %d' %
-              (len(wss_collected), nr_quota_exceeds))
+    if nr_quota_exceeds < nr_expected_quota_exceeds:
+        print('quota is exceeded less than expected: %d < %d' %
+              (nr_quota_exceeds, nr_expected_quota_exceeds))
         exit(1)
 
 if __name__ == '__main__':

From 695469c07a65547acb6e229b3fdf6aaa881817e3 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:32 -0800
Subject: [PATCH 1667/2753] selftests/damon/damon_nr_regions: set ops update
 for merge results check to 100ms

damon_nr_regions.py updates max_nr_regions to a number smaller than
expected number of real regions and confirms DAMON respect the harsh
limit.  To give time for DAMON to make changes for the regions, 3
aggregation intervals (300 milliseconds) are given.

The internal mechanism works with not only the max_nr_regions, but also
sz_limit, though.  It avoids merging region if that casn make region of
size larger than sz_limit.  In the test, sz_limit is set too small to
achive the new max_nr_regions, unless it is updated for the new
min_nr_regions.  But the update is done only once per operations set
update interval, which is one second by default.

Hence, the test randomly incurs false positive failures.  Fix it by
setting the ops interval same to aggregation interval, to make sure
sz_limit is updated by the time of the check.

Link: https://lkml.kernel.org/r/20250225222333.505646-3-sj@kernel.org
Fixes: 8bf890c81612 ("selftests/damon/damon_nr_regions: test online-tuned max_nr_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damon_nr_regions.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/damon/damon_nr_regions.py b/tools/testing/selftests/damon/damon_nr_regions.py
index 2e8a74aff5431..6f1c1d88e3091 100755
--- a/tools/testing/selftests/damon/damon_nr_regions.py
+++ b/tools/testing/selftests/damon/damon_nr_regions.py
@@ -109,6 +109,7 @@ def main():
     attrs = kdamonds.kdamonds[0].contexts[0].monitoring_attrs
     attrs.min_nr_regions = 3
     attrs.max_nr_regions = 7
+    attrs.update_us = 100000
     err = kdamonds.kdamonds[0].commit()
     if err is not None:
         proc.terminate()

From 582ccf78f6090d88b1c7066b1e90b3d9ec952d08 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 25 Feb 2025 14:23:33 -0800
Subject: [PATCH 1668/2753] selftests/damon/damon_nr_regions: sort collected
 regiosn before checking with min/max boundaries

damon_nr_regions.py starts DAMON, periodically collect number of regions
in snapshots, and see if it is in the requested range.  The check code
assumes the numbers are sorted on the collection list, but there is no
such guarantee.  Hence this can result in false positive test success.
Sort the list before doing the check.

Link: https://lkml.kernel.org/r/20250225222333.505646-4-sj@kernel.org
Fixes: 781497347d1b ("selftests/damon: implement test for min/max_nr_regions")
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/damon/damon_nr_regions.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/damon/damon_nr_regions.py b/tools/testing/selftests/damon/damon_nr_regions.py
index 6f1c1d88e3091..58f3291fed12a 100755
--- a/tools/testing/selftests/damon/damon_nr_regions.py
+++ b/tools/testing/selftests/damon/damon_nr_regions.py
@@ -65,6 +65,7 @@ def test_nr_regions(real_nr_regions, min_nr_regions, max_nr_regions):
 
     test_name = 'nr_regions test with %d/%d/%d real/min/max nr_regions' % (
             real_nr_regions, min_nr_regions, max_nr_regions)
+    collected_nr_regions.sort()
     if (collected_nr_regions[0] < min_nr_regions or
         collected_nr_regions[-1] > max_nr_regions):
         print('fail %s' % test_name)

From c50f8e6053b0503375c2975bf47f182445aebb4c Mon Sep 17 00:00:00 2001
From: Barry Song <v-songbaohua@oppo.com>
Date: Wed, 26 Feb 2025 13:14:00 +1300
Subject: [PATCH 1669/2753] mm: fix kernel BUG when userfaultfd_move encounters
 swapcache

userfaultfd_move() checks whether the PTE entry is present or a
swap entry.

- If the PTE entry is present, move_present_pte() handles folio
  migration by setting:

  src_folio->index = linear_page_index(dst_vma, dst_addr);

- If the PTE entry is a swap entry, move_swap_pte() simply copies
  the PTE to the new dst_addr.

This approach is incorrect because, even if the PTE is a swap entry,
it can still reference a folio that remains in the swap cache.

This creates a race window between steps 2 and 4.
 1. add_to_swap: The folio is added to the swapcache.
 2. try_to_unmap: PTEs are converted to swap entries.
 3. pageout: The folio is written back.
 4. Swapcache is cleared.
If userfaultfd_move() occurs in the window between steps 2 and 4,
after the swap PTE has been moved to the destination, accessing the
destination triggers do_swap_page(), which may locate the folio in
the swapcache. However, since the folio's index has not been updated
to match the destination VMA, do_swap_page() will detect a mismatch.

This can result in two critical issues depending on the system
configuration.

If KSM is disabled, both small and large folios can trigger a BUG
during the add_rmap operation due to:

 page_pgoff(folio, page) != linear_page_index(vma, address)

[   13.336953] page: refcount:6 mapcount:1 mapping:00000000f43db19c index:0xffffaf150 pfn:0x4667c
[   13.337520] head: order:2 mapcount:1 entire_mapcount:0 nr_pages_mapped:1 pincount:0
[   13.337716] memcg:ffff00000405f000
[   13.337849] anon flags: 0x3fffc0000020459(locked|uptodate|dirty|owner_priv_1|head|swapbacked|node=0|zone=0|lastcpupid=0xffff)
[   13.338630] raw: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
[   13.338831] raw: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
[   13.339031] head: 03fffc0000020459 ffff80008507b538 ffff80008507b538 ffff000006260361
[   13.339204] head: 0000000ffffaf150 0000000000004000 0000000600000000 ffff00000405f000
[   13.339375] head: 03fffc0000000202 fffffdffc0199f01 ffffffff00000000 0000000000000001
[   13.339546] head: 0000000000000004 0000000000000000 00000000ffffffff 0000000000000000
[   13.339736] page dumped because: VM_BUG_ON_PAGE(page_pgoff(folio, page) != linear_page_index(vma, address))
[   13.340190] ------------[ cut here ]------------
[   13.340316] kernel BUG at mm/rmap.c:1380!
[   13.340683] Internal error: Oops - BUG: 00000000f2000800 [#1] PREEMPT SMP
[   13.340969] Modules linked in:
[   13.341257] CPU: 1 UID: 0 PID: 107 Comm: a.out Not tainted 6.14.0-rc3-gcf42737e247a-dirty #299
[   13.341470] Hardware name: linux,dummy-virt (DT)
[   13.341671] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[   13.341815] pc : __page_check_anon_rmap+0xa0/0xb0
[   13.341920] lr : __page_check_anon_rmap+0xa0/0xb0
[   13.342018] sp : ffff80008752bb20
[   13.342093] x29: ffff80008752bb20 x28: fffffdffc0199f00 x27: 0000000000000001
[   13.342404] x26: 0000000000000000 x25: 0000000000000001 x24: 0000000000000001
[   13.342575] x23: 0000ffffaf0d0000 x22: 0000ffffaf0d0000 x21: fffffdffc0199f00
[   13.342731] x20: fffffdffc0199f00 x19: ffff000006210700 x18: 00000000ffffffff
[   13.342881] x17: 6c203d2120296567 x16: 6170202c6f696c6f x15: 662866666f67705f
[   13.343033] x14: 6567617028454741 x13: 2929737365726464 x12: ffff800083728ab0
[   13.343183] x11: ffff800082996bf8 x10: 0000000000000fd7 x9 : ffff80008011bc40
[   13.343351] x8 : 0000000000017fe8 x7 : 00000000fffff000 x6 : ffff8000829eebf8
[   13.343498] x5 : c0000000fffff000 x4 : 0000000000000000 x3 : 0000000000000000
[   13.343645] x2 : 0000000000000000 x1 : ffff0000062db980 x0 : 000000000000005f
[   13.343876] Call trace:
[   13.344045]  __page_check_anon_rmap+0xa0/0xb0 (P)
[   13.344234]  folio_add_anon_rmap_ptes+0x22c/0x320
[   13.344333]  do_swap_page+0x1060/0x1400
[   13.344417]  __handle_mm_fault+0x61c/0xbc8
[   13.344504]  handle_mm_fault+0xd8/0x2e8
[   13.344586]  do_page_fault+0x20c/0x770
[   13.344673]  do_translation_fault+0xb4/0xf0
[   13.344759]  do_mem_abort+0x48/0xa0
[   13.344842]  el0_da+0x58/0x130
[   13.344914]  el0t_64_sync_handler+0xc4/0x138
[   13.345002]  el0t_64_sync+0x1ac/0x1b0
[   13.345208] Code: aa1503e0 f000f801 910f6021 97ff5779 (d4210000)
[   13.345504] ---[ end trace 0000000000000000 ]---
[   13.345715] note: a.out[107] exited with irqs disabled
[   13.345954] note: a.out[107] exited with preempt_count 2

If KSM is enabled, Peter Xu also discovered that do_swap_page() may
trigger an unexpected CoW operation for small folios because
ksm_might_need_to_copy() allocates a new folio when the folio index
does not match linear_page_index(vma, addr).

This patch also checks the swapcache when handling swap entries. If a
match is found in the swapcache, it processes it similarly to a present
PTE.
However, there are some differences. For example, the folio is no longer
exclusive because folio_try_share_anon_rmap_pte() is performed during
unmapping.
Furthermore, in the case of swapcache, the folio has already been
unmapped, eliminating the risk of concurrent rmap walks and removing the
need to acquire src_folio's anon_vma or lock.

Note that for large folios, in the swapcache handling path, we directly
return -EBUSY since split_folio() will return -EBUSY regardless if
the folio is under writeback or unmapped. This is not an urgent issue,
so a follow-up patch may address it separately.

[v-songbaohua@oppo.com: minor cleanup according to Peter Xu]
  Link: https://lkml.kernel.org/r/20250226024411.47092-1-21cnbao@gmail.com
Link: https://lkml.kernel.org/r/20250226001400.9129-1-21cnbao@gmail.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Brian Geffon <bgeffon@google.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport (IBM) <rppt@kernel.org>
Cc: Nicolas Geoffray <ngeoffray@google.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: ZhangPeng <zhangpeng362@huawei.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 74 ++++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 66 insertions(+), 8 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index af3dfc3633dbe..c45b672e10d17 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -18,6 +18,7 @@
 #include <asm/tlbflush.h>
 #include <asm/tlb.h>
 #include "internal.h"
+#include "swap.h"
 
 static __always_inline
 bool validate_dst_vma(struct vm_area_struct *dst_vma, unsigned long dst_end)
@@ -1076,16 +1077,14 @@ static int move_present_pte(struct mm_struct *mm,
 	return err;
 }
 
-static int move_swap_pte(struct mm_struct *mm,
+static int move_swap_pte(struct mm_struct *mm, struct vm_area_struct *dst_vma,
 			 unsigned long dst_addr, unsigned long src_addr,
 			 pte_t *dst_pte, pte_t *src_pte,
 			 pte_t orig_dst_pte, pte_t orig_src_pte,
 			 pmd_t *dst_pmd, pmd_t dst_pmdval,
-			 spinlock_t *dst_ptl, spinlock_t *src_ptl)
+			 spinlock_t *dst_ptl, spinlock_t *src_ptl,
+			 struct folio *src_folio)
 {
-	if (!pte_swp_exclusive(orig_src_pte))
-		return -EBUSY;
-
 	double_pt_lock(dst_ptl, src_ptl);
 
 	if (!is_pte_pages_stable(dst_pte, src_pte, orig_dst_pte, orig_src_pte,
@@ -1094,6 +1093,16 @@ static int move_swap_pte(struct mm_struct *mm,
 		return -EAGAIN;
 	}
 
+	/*
+	 * The src_folio resides in the swapcache, requiring an update to its
+	 * index and mapping to align with the dst_vma, where a swap-in may
+	 * occur and hit the swapcache after moving the PTE.
+	 */
+	if (src_folio) {
+		folio_move_anon_rmap(src_folio, dst_vma);
+		src_folio->index = linear_page_index(dst_vma, dst_addr);
+	}
+
 	orig_src_pte = ptep_get_and_clear(mm, src_addr, src_pte);
 	set_pte_at(mm, dst_addr, dst_pte, orig_src_pte);
 	double_pt_unlock(dst_ptl, src_ptl);
@@ -1141,6 +1150,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			  __u64 mode)
 {
 	swp_entry_t entry;
+	struct swap_info_struct *si = NULL;
 	pte_t orig_src_pte, orig_dst_pte;
 	pte_t src_folio_pte;
 	spinlock_t *src_ptl, *dst_ptl;
@@ -1322,6 +1332,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				       orig_dst_pte, orig_src_pte, dst_pmd,
 				       dst_pmdval, dst_ptl, src_ptl, src_folio);
 	} else {
+		struct folio *folio = NULL;
+
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
 			if (is_migration_entry(entry)) {
@@ -1335,9 +1347,53 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			goto out;
 		}
 
-		err = move_swap_pte(mm, dst_addr, src_addr, dst_pte, src_pte,
-				    orig_dst_pte, orig_src_pte, dst_pmd,
-				    dst_pmdval, dst_ptl, src_ptl);
+		if (!pte_swp_exclusive(orig_src_pte)) {
+			err = -EBUSY;
+			goto out;
+		}
+
+		si = get_swap_device(entry);
+		if (unlikely(!si)) {
+			err = -EAGAIN;
+			goto out;
+		}
+		/*
+		 * Verify the existence of the swapcache. If present, the folio's
+		 * index and mapping must be updated even when the PTE is a swap
+		 * entry. The anon_vma lock is not taken during this process since
+		 * the folio has already been unmapped, and the swap entry is
+		 * exclusive, preventing rmap walks.
+		 *
+		 * For large folios, return -EBUSY immediately, as split_folio()
+		 * also returns -EBUSY when attempting to split unmapped large
+		 * folios in the swapcache. This issue needs to be resolved
+		 * separately to allow proper handling.
+		 */
+		if (!src_folio)
+			folio = filemap_get_folio(swap_address_space(entry),
+					swap_cache_index(entry));
+		if (!IS_ERR_OR_NULL(folio)) {
+			if (folio_test_large(folio)) {
+				err = -EBUSY;
+				folio_put(folio);
+				goto out;
+			}
+			src_folio = folio;
+			src_folio_pte = orig_src_pte;
+			if (!folio_trylock(src_folio)) {
+				pte_unmap(&orig_src_pte);
+				pte_unmap(&orig_dst_pte);
+				src_pte = dst_pte = NULL;
+				put_swap_device(si);
+				si = NULL;
+				/* now we can block and wait */
+				folio_lock(src_folio);
+				goto retry;
+			}
+		}
+		err = move_swap_pte(mm, dst_vma, dst_addr, src_addr, dst_pte, src_pte,
+				orig_dst_pte, orig_src_pte, dst_pmd, dst_pmdval,
+				dst_ptl, src_ptl, src_folio);
 	}
 
 out:
@@ -1354,6 +1410,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 	if (src_pte)
 		pte_unmap(src_pte);
 	mmu_notifier_invalidate_range_end(&range);
+	if (si)
+		put_swap_device(si);
 
 	return err;
 }

From 058313515d5aab10d0a01dd634f92ed4a4e71d4c Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Tue, 25 Feb 2025 17:52:55 +0800
Subject: [PATCH 1670/2753] mm: shmem: fix potential data corruption during
 shmem swapin

Alex and Kairui reported some issues (system hang or data corruption) when
swapping out or swapping in large shmem folios.  This is especially easy
to reproduce when the tmpfs is mount with the 'huge=within_size'
parameter.  Thanks to Kairui's reproducer, the issue can be easily
replicated.

The root cause of the problem is that swap readahead may asynchronously
swap in order 0 folios into the swap cache, while the shmem mapping can
still store large swap entries.  Then an order 0 folio is inserted into
the shmem mapping without splitting the large swap entry, which overwrites
the original large swap entry, leading to data corruption.

When getting a folio from the swap cache, we should split the large swap
entry stored in the shmem mapping if the orders do not match, to fix this
issue.

Link: https://lkml.kernel.org/r/2fe47c557e74e9df5fe2437ccdc6c9115fa1bf70.1740476943.git.baolin.wang@linux.alibaba.com
Fixes: 809bc86517cc ("mm: shmem: support large folio swap out")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Alex Xu (Hello71) <alex_y_xu@yahoo.ca>
Reported-by: Kairui Song <ryncsn@gmail.com>
Closes: https://lore.kernel.org/all/1738717785.im3r5g2vxc.none@localhost/
Tested-by: Kairui Song <kasong@tencent.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Matthew Wilcow <willy@infradead.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/shmem.c | 31 +++++++++++++++++++++++++++----
 1 file changed, 27 insertions(+), 4 deletions(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index 4ea6109a80431..cebbac97a2219 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2253,7 +2253,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	struct folio *folio = NULL;
 	bool skip_swapcache = false;
 	swp_entry_t swap;
-	int error, nr_pages;
+	int error, nr_pages, order, split_order;
 
 	VM_BUG_ON(!*foliop || !xa_is_value(*foliop));
 	swap = radix_to_swp_entry(*foliop);
@@ -2272,10 +2272,9 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 
 	/* Look it up and read it in.. */
 	folio = swap_cache_get_folio(swap, NULL, 0);
+	order = xa_get_order(&mapping->i_pages, index);
 	if (!folio) {
-		int order = xa_get_order(&mapping->i_pages, index);
 		bool fallback_order0 = false;
-		int split_order;
 
 		/* Or update major stats only when swapin succeeds?? */
 		if (fault_type) {
@@ -2339,6 +2338,29 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 			error = -ENOMEM;
 			goto failed;
 		}
+	} else if (order != folio_order(folio)) {
+		/*
+		 * Swap readahead may swap in order 0 folios into swapcache
+		 * asynchronously, while the shmem mapping can still stores
+		 * large swap entries. In such cases, we should split the
+		 * large swap entry to prevent possible data corruption.
+		 */
+		split_order = shmem_split_large_entry(inode, index, swap, gfp);
+		if (split_order < 0) {
+			error = split_order;
+			goto failed;
+		}
+
+		/*
+		 * If the large swap entry has already been split, it is
+		 * necessary to recalculate the new swap entry based on
+		 * the old order alignment.
+		 */
+		if (split_order > 0) {
+			pgoff_t offset = index - round_down(index, 1 << split_order);
+
+			swap = swp_entry(swp_type(swap), swp_offset(swap) + offset);
+		}
 	}
 
 alloced:
@@ -2346,7 +2368,8 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
 	folio_lock(folio);
 	if ((!skip_swapcache && !folio_test_swapcache(folio)) ||
 	    folio->swap.val != swap.val ||
-	    !shmem_confirm_swap(mapping, index, swap)) {
+	    !shmem_confirm_swap(mapping, index, swap) ||
+	    xa_get_order(&mapping->i_pages, index) != folio_order(folio)) {
 		error = -EEXIST;
 		goto unlock;
 	}

From ea6de4f8f8f32e54662118a97c441a6ad7b24345 Mon Sep 17 00:00:00 2001
From: Sun YangKai <sunk67188@gmail.com>
Date: Wed, 26 Feb 2025 23:32:43 +0800
Subject: [PATCH 1671/2753] mm: zswap: use ATOMIC_LONG_INIT to initialize
 zswap_stored_pages

This is currently the only atomic_long_t variable initialized by
ATOMIC_INIT macro found in the kernel by using `grep -r atomic_long_t |
grep ATOMIC_INIT`

This was introduced in 6e1fa555ec77, in which we modified the type of
zswap_stored_pages to atomic_long_t, but didn't change the initialization.

Link: https://lkml.kernel.org/r/20250226153253.19179-1-sunk67188@gmail.com
Fixes: 6e1fa555ec77 ("mm: zswap: modify zswap_stored_pages to be atomic_long_t")
Signed-off-by: Sun YangKai <sunk67188@gmail.com>
Acked-by: Yosry Ahmed <yosry.ahmed@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/zswap.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index ac9d299e7d0c1..23365e76a3ce3 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -43,7 +43,7 @@
 * statistics
 **********************************/
 /* The number of compressed pages currently stored in zswap */
-atomic_long_t zswap_stored_pages = ATOMIC_INIT(0);
+atomic_long_t zswap_stored_pages = ATOMIC_LONG_INIT(0);
 
 /*
  * The statistics below are not protected from concurrent access for

From 37b338eed10581784e854d4262da05c8d960c748 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 26 Feb 2025 10:55:08 -0800
Subject: [PATCH 1672/2753] userfaultfd: do not block on locking a large folio
 with raised refcount

Lokesh recently raised an issue about UFFDIO_MOVE getting into a deadlock
state when it goes into split_folio() with raised folio refcount.
split_folio() expects the reference count to be exactly mapcount +
num_pages_in_folio + 1 (see can_split_folio()) and fails with EAGAIN
otherwise.

If multiple processes are trying to move the same large folio, they raise
the refcount (all tasks succeed in that) then one of them succeeds in
locking the folio, while others will block in folio_lock() while keeping
the refcount raised.  The winner of this race will proceed with calling
split_folio() and will fail returning EAGAIN to the caller and unlocking
the folio.  The next competing process will get the folio locked and will
go through the same flow.  In the meantime the original winner will be
retried and will block in folio_lock(), getting into the queue of waiting
processes only to repeat the same path.  All this results in a livelock.

An easy fix would be to avoid waiting for the folio lock while holding
folio refcount, similar to madvise_free_huge_pmd() where folio lock is
acquired before raising the folio refcount.  Since we lock and take a
refcount of the folio while holding the PTE lock, changing the order of
these operations should not break anything.

Modify move_pages_pte() to try locking the folio first and if that fails
and the folio is large then return EAGAIN without touching the folio
refcount.  If the folio is single-page then split_folio() is not called,
so we don't have this issue.  Lokesh has a reproducer [1] and I verified
that this change fixes the issue.

[1] https://github.com/lokeshgidra/uffd_move_ioctl_deadlock

[akpm@linux-foundation.org: reflow comment to 80 cols, s/end/end up/]
Link: https://lkml.kernel.org/r/20250226185510.2732648-2-surenb@google.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: Lokesh Gidra <lokeshgidra@google.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Acked-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index c45b672e10d17..f5c6b3454f76b 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1250,6 +1250,7 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		 */
 		if (!src_folio) {
 			struct folio *folio;
+			bool locked;
 
 			/*
 			 * Pin the page while holding the lock to be sure the
@@ -1269,12 +1270,26 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				goto out;
 			}
 
+			locked = folio_trylock(folio);
+			/*
+			 * We avoid waiting for folio lock with a raised
+			 * refcount for large folios because extra refcounts
+			 * will result in split_folio() failing later and
+			 * retrying.  If multiple tasks are trying to move a
+			 * large folio we can end up livelocking.
+			 */
+			if (!locked && folio_test_large(folio)) {
+				spin_unlock(src_ptl);
+				err = -EAGAIN;
+				goto out;
+			}
+
 			folio_get(folio);
 			src_folio = folio;
 			src_folio_pte = orig_src_pte;
 			spin_unlock(src_ptl);
 
-			if (!folio_trylock(src_folio)) {
+			if (!locked) {
 				pte_unmap(&orig_src_pte);
 				pte_unmap(&orig_dst_pte);
 				src_pte = dst_pte = NULL;

From 927e926d72d9155fde3264459fe9bfd7b5e40d28 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Wed, 26 Feb 2025 10:55:09 -0800
Subject: [PATCH 1673/2753] userfaultfd: fix PTE unmapping stack-allocated PTE
 copies

Current implementation of move_pages_pte() copies source and destination
PTEs in order to detect concurrent changes to PTEs involved in the move.
However these copies are also used to unmap the PTEs, which will fail if
CONFIG_HIGHPTE is enabled because the copies are allocated on the stack.
Fix this by using the actual PTEs which were kmap()ed.

Link: https://lkml.kernel.org/r/20250226185510.2732648-3-surenb@google.com
Fixes: adef440691ba ("userfaultfd: UFFDIO_MOVE uABI")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Barry Song <21cnbao@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@Oracle.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/userfaultfd.c | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index f5c6b3454f76b..d06453fa8abae 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1290,8 +1290,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			spin_unlock(src_ptl);
 
 			if (!locked) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				folio_lock(src_folio);
@@ -1307,8 +1307,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		/* at this point we have src_folio locked */
 		if (folio_test_large(src_folio)) {
 			/* split_folio() can block */
-			pte_unmap(&orig_src_pte);
-			pte_unmap(&orig_dst_pte);
+			pte_unmap(src_pte);
+			pte_unmap(dst_pte);
 			src_pte = dst_pte = NULL;
 			err = split_folio(src_folio);
 			if (err)
@@ -1333,8 +1333,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 				goto out;
 			}
 			if (!anon_vma_trylock_write(src_anon_vma)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				/* now we can block and wait */
 				anon_vma_lock_write(src_anon_vma);
@@ -1352,8 +1352,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 		entry = pte_to_swp_entry(orig_src_pte);
 		if (non_swap_entry(entry)) {
 			if (is_migration_entry(entry)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				migration_entry_wait(mm, src_pmd, src_addr);
 				err = -EAGAIN;
@@ -1396,8 +1396,8 @@ static int move_pages_pte(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd,
 			src_folio = folio;
 			src_folio_pte = orig_src_pte;
 			if (!folio_trylock(src_folio)) {
-				pte_unmap(&orig_src_pte);
-				pte_unmap(&orig_dst_pte);
+				pte_unmap(src_pte);
+				pte_unmap(dst_pte);
 				src_pte = dst_pte = NULL;
 				put_swap_device(si);
 				si = NULL;

From adae46ac1e38a288b14f0298e27412adcba83f8e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ricardo=20Ca=C3=B1uelo=20Navarro?= <rcn@igalia.com>
Date: Wed, 26 Feb 2025 13:26:27 +0100
Subject: [PATCH 1674/2753] mm: shmem: remove unnecessary warning in
 shmem_writepage()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Although the scenario where shmem_writepage() is called with info->flags &
VM_LOCKED is unlikely to happen, it's still possible, as evidenced by
syzbot [1].  However, the warning in this case isn't necessary because the
situation is already handled correctly [2].

[2] https://lore.kernel.org/lkml/8afe1f7f-31a2-4fc0-1fbd-f9ba8a116fe3@google.com/

Link: https://lkml.kernel.org/r/20250226-20250221-warning-in-shmem_writepage-v1-1-5ad19420e17e@igalia.com
Fixes: 9a976f0c847b ("shmem: skip page split if we're not reclaiming")
Signed-off-by: Ricardo Cañuelo Navarro <rcn@igalia.com>
Reported-by: Pengfei Xu <pengfei.xu@intel.com>
Closes: https://lore.kernel.org/lkml/ZZ9PShXjKJkVelNm@xpf.sh.intel.com/ [1]
Suggested-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Florent Revest <revest@chromium.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Florent Revest <revest@chromium.org>
Cc: Luis Chamberalin <mcgrof@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/shmem.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/shmem.c b/mm/shmem.c
index cebbac97a2219..3fcd1690eedd7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1548,7 +1548,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc)
 	if (WARN_ON_ONCE(!wbc->for_reclaim))
 		goto redirty;
 
-	if (WARN_ON_ONCE((info->flags & VM_LOCKED) || sbinfo->noswap))
+	if ((info->flags & VM_LOCKED) || sbinfo->noswap)
 		goto redirty;
 
 	if (!total_swap_pages)

From 3685024edd270f7c791f993157d65d3c928f3d6e Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Wed, 26 Feb 2025 12:16:09 +0000
Subject: [PATCH 1675/2753] mm: don't skip arch_sync_kernel_mappings() in error
 paths

Fix callers that previously skipped calling arch_sync_kernel_mappings() if
an error occurred during a pgtable update.  The call is still required to
sync any pgtable updates that may have occurred prior to hitting the error
condition.

These are theoretical bugs discovered during code review.

Link: https://lkml.kernel.org/r/20250226121610.2401743-1-ryan.roberts@arm.com
Fixes: 2ba3e6947aed ("mm/vmalloc: track which page-table levels were modified")
Fixes: 0c95cba49255 ("mm: apply_to_pte_range warn and fail if a large pte is encountered")
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christop Hellwig <hch@infradead.org>
Cc: "Uladzislau Rezki (Sony)" <urezki@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c  | 6 ++++--
 mm/vmalloc.c | 4 ++--
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index b4d3d4893267c..55d0d49546273 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -3051,8 +3051,10 @@ static int __apply_to_page_range(struct mm_struct *mm, unsigned long addr,
 		next = pgd_addr_end(addr, end);
 		if (pgd_none(*pgd) && !create)
 			continue;
-		if (WARN_ON_ONCE(pgd_leaf(*pgd)))
-			return -EINVAL;
+		if (WARN_ON_ONCE(pgd_leaf(*pgd))) {
+			err = -EINVAL;
+			break;
+		}
 		if (!pgd_none(*pgd) && WARN_ON_ONCE(pgd_bad(*pgd))) {
 			if (!create)
 				continue;
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a6e7acebe9adf..61981ee1c9d2f 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -586,13 +586,13 @@ static int vmap_small_pages_range_noflush(unsigned long addr, unsigned long end,
 			mask |= PGTBL_PGD_MODIFIED;
 		err = vmap_pages_p4d_range(pgd, addr, next, prot, pages, &nr, &mask);
 		if (err)
-			return err;
+			break;
 	} while (pgd++, addr = next, addr != end);
 
 	if (mask & ARCH_PAGE_TABLE_SYNC_MASK)
 		arch_sync_kernel_mappings(start, end);
 
-	return 0;
+	return err;
 }
 
 /*

From 34b82f33cf3f03bc39e9a205a913d790e1520ade Mon Sep 17 00:00:00 2001
From: Brian Geffon <bgeffon@google.com>
Date: Wed, 26 Feb 2025 11:23:41 -0500
Subject: [PATCH 1676/2753] mm: fix finish_fault() handling for large folios

When handling faults for anon shmem finish_fault() will attempt to install
ptes for the entire folio.  Unfortunately if it encounters a single
non-pte_none entry in that range it will bail, even if the pte that
triggered the fault is still pte_none.  When this situation happens the
fault will be retried endlessly never making forward progress.

This patch fixes this behavior and if it detects that a pte in the range
is not pte_none it will fall back to setting a single pte.

[bgeffon@google.com: tweak whitespace]
  Link: https://lkml.kernel.org/r/20250227133236.1296853-1-bgeffon@google.com
Link: https://lkml.kernel.org/r/20250226162341.915535-1-bgeffon@google.com
Fixes: 43e027e41423 ("mm: memory: extend finish_fault() to support large folio")
Signed-off-by: Brian Geffon <bgeffon@google.com>
Suggested-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reported-by: Marek Maslanka <mmaslanka@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickens <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memory.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index 55d0d49546273..b9661ccfa64fd 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -5185,7 +5185,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
 		      !(vma->vm_flags & VM_SHARED);
 	int type, nr_pages;
-	unsigned long addr = vmf->address;
+	unsigned long addr;
+	bool needs_fallback = false;
+
+fallback:
+	addr = vmf->address;
 
 	/* Did we COW the page? */
 	if (is_cow)
@@ -5224,7 +5228,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	 * approach also applies to non-anonymous-shmem faults to avoid
 	 * inflating the RSS of the process.
 	 */
-	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) {
+	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) ||
+	    unlikely(needs_fallback)) {
 		nr_pages = 1;
 	} else if (nr_pages > 1) {
 		pgoff_t idx = folio_page_idx(folio, page);
@@ -5260,9 +5265,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_NOPAGE;
 		goto unlock;
 	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
-		update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
-		ret = VM_FAULT_NOPAGE;
-		goto unlock;
+		needs_fallback = true;
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		goto fallback;
 	}
 
 	folio_ref_add(folio, nr_pages - 1);

From eae116d1f0449ade3269ca47a67432622f5c6438 Mon Sep 17 00:00:00 2001
From: Gabriel Krisman Bertazi <krisman@suse.de>
Date: Tue, 25 Feb 2025 22:22:58 -0500
Subject: [PATCH 1677/2753] Revert "mm/page_alloc.c: don't show protection in
 zone's ->lowmem_reserve[] for empty zone"

Commit 96a5c186efff ("mm/page_alloc.c: don't show protection in zone's
->lowmem_reserve[] for empty zone") removes the protection of lower zones
from allocations targeting memory-less high zones.  This had an unintended
impact on the pattern of reclaims because it makes the high-zone-targeted
allocation more likely to succeed in lower zones, which adds pressure to
said zones.  I.e, the following corresponding checks in
zone_watermark_ok/zone_watermark_fast are less likely to trigger:

        if (free_pages <= min + z->lowmem_reserve[highest_zoneidx])
                return false;

As a result, we are observing an increase in reclaim and kswapd scans, due
to the increased pressure.  This was initially observed as increased
latency in filesystem operations when benchmarking with fio on a machine
with some memory-less zones, but it has since been associated with
increased contention in locks related to memory reclaim.  By reverting
this patch, the original performance was recovered on that machine.

The original commit was introduced as a clarification of the
/proc/zoneinfo output, so it doesn't seem there are usecases depending on
it, making the revert a simple solution.

For reference, I collected vmstat with and without this patch on a freshly
booted system running intensive randread io from an nvme for 5 minutes.  I
got:

rpm-6.12.0-slfo.1.2 ->  pgscan_kswapd 5629543865
Patched             ->  pgscan_kswapd 33580844

33M scans is similar to what we had in kernels predating this patch.
These numbers is fairly representative of the workload on this machine, as
measured in several runs.  So we are talking about a 2-order of magnitude
increase.

Link: https://lkml.kernel.org/r/20250226032258.234099-1-krisman@suse.de
Fixes: 96a5c186efff ("mm/page_alloc.c: don't show protection in zone's ->lowmem_reserve[] for empty zone")
Signed-off-by: Gabriel Krisman Bertazi <krisman@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Baoquan He <bhe@redhat.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page_alloc.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 579789600a3c7..fe986e6de7a01 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5849,11 +5849,10 @@ static void setup_per_zone_lowmem_reserve(void)
 
 			for (j = i + 1; j < MAX_NR_ZONES; j++) {
 				struct zone *upper_zone = &pgdat->node_zones[j];
-				bool empty = !zone_managed_pages(upper_zone);
 
 				managed_pages += zone_managed_pages(upper_zone);
 
-				if (clear || empty)
+				if (clear)
 					zone->lowmem_reserve[j] = 0;
 				else
 					zone->lowmem_reserve[j] = managed_pages / ratio;

From 88f5a9a945bf25df1f90032baf95457370c2206e Mon Sep 17 00:00:00 2001
From: Sumit Garg <sumit.garg@linaro.org>
Date: Thu, 27 Feb 2025 17:02:28 +0530
Subject: [PATCH 1678/2753] MAINTAINERS: .mailmap: update Sumit Garg's email
 address

Update Sumit Garg's email address to @kernel.org.

Link: https://lkml.kernel.org/r/20250227113228.1809449-1-sumit.garg@linaro.org
Signed-off-by: Sumit Garg <sumit.garg@linaro.org>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Jens Wiklander <jens.wiklander@linaro.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 .mailmap    | 1 +
 MAINTAINERS | 6 +++---
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/.mailmap b/.mailmap
index a897c16d3baef..4a93909286d8b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -689,6 +689,7 @@ Subbaraman Narayanamurthy <quic_subbaram@quicinc.com> <subbaram@codeaurora.org>
 Subhash Jadavani <subhashj@codeaurora.org>
 Sudarshan Rajagopalan <quic_sudaraja@quicinc.com> <sudaraja@codeaurora.org>
 Sudeep Holla <sudeep.holla@arm.com> Sudeep KarkadaNagesha <sudeep.karkadanagesha@arm.com>
+Sumit Garg <sumit.garg@kernel.org> <sumit.garg@linaro.org>
 Sumit Semwal <sumit.semwal@ti.com>
 Surabhi Vishnoi <quic_svishnoi@quicinc.com> <svishnoi@codeaurora.org>
 Sven Eckelmann <sven@narfation.org> <seckelmann@datto.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 4e17764cb6ed4..5e1be7b25912e 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -12864,7 +12864,7 @@ F:	include/keys/trusted_dcp.h
 F:	security/keys/trusted-keys/trusted_dcp.c
 
 KEYS-TRUSTED-TEE
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	linux-integrity@vger.kernel.org
 L:	keyrings@vger.kernel.org
 S:	Supported
@@ -17658,7 +17658,7 @@ F:	Documentation/ABI/testing/sysfs-bus-optee-devices
 F:	drivers/tee/optee/
 
 OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER
-M:	Sumit Garg <sumit.garg@linaro.org>
+M:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	drivers/char/hw_random/optee-rng.c
@@ -23268,7 +23268,7 @@ F:	include/media/i2c/tw9910.h
 
 TEE SUBSYSTEM
 M:	Jens Wiklander <jens.wiklander@linaro.org>
-R:	Sumit Garg <sumit.garg@linaro.org>
+R:	Sumit Garg <sumit.garg@kernel.org>
 L:	op-tee@lists.trustedfirmware.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-class-tee

From b2ef51c74b0171fde7eb69b6152d3d2f743ef269 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 27 Feb 2025 15:34:09 +0800
Subject: [PATCH 1679/2753] rapidio: fix an API misues when rio_add_net() fails

rio_add_net() calls device_register() and fails when device_register()
fails.  Thus, put_device() should be used rather than kfree().  Add
"mport->net = NULL;" to avoid a use after free issue.

Link: https://lkml.kernel.org/r/20250227073409.3696854-1-haoxiang_li2024@163.com
Fixes: e8de370188d0 ("rapidio: add mport char device driver")
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Reviewed-by: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Yang Yingliang <yangyingliang@huawei.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/rapidio/devices/rio_mport_cdev.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/rapidio/devices/rio_mport_cdev.c b/drivers/rapidio/devices/rio_mport_cdev.c
index 27afbb9d544b7..cbf531d0ba688 100644
--- a/drivers/rapidio/devices/rio_mport_cdev.c
+++ b/drivers/rapidio/devices/rio_mport_cdev.c
@@ -1742,7 +1742,8 @@ static int rio_mport_add_riodev(struct mport_cdev_priv *priv,
 		err = rio_add_net(net);
 		if (err) {
 			rmcd_debug(RDEV, "failed to register net, err=%d", err);
-			kfree(net);
+			put_device(&net->dev);
+			mport->net = NULL;
 			goto cleanup;
 		}
 	}

From e842f9a1edf306bf36fe2a4d847a0b0d458770de Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Thu, 27 Feb 2025 12:11:31 +0800
Subject: [PATCH 1680/2753] rapidio: add check for rio_add_net() in
 rio_scan_alloc_net()

The return value of rio_add_net() should be checked.  If it fails,
put_device() should be called to free the memory and give up the reference
initialized in rio_add_net().

Link: https://lkml.kernel.org/r/20250227041131.3680761-1-haoxiang_li2024@163.com
Fixes: e6b585ca6e81 ("rapidio: move net allocation into core code")
Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Cc: Alexandre Bounine <alex.bou9@gmail.com>
Cc: Matt Porter <mporter@kernel.crashing.org>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/rapidio/rio-scan.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/rapidio/rio-scan.c b/drivers/rapidio/rio-scan.c
index fdcf742b2adbc..c12941f71e2cb 100644
--- a/drivers/rapidio/rio-scan.c
+++ b/drivers/rapidio/rio-scan.c
@@ -871,7 +871,10 @@ static struct rio_net *rio_scan_alloc_net(struct rio_mport *mport,
 		dev_set_name(&net->dev, "rnet_%d", net->id);
 		net->dev.parent = &mport->dev;
 		net->dev.release = rio_scan_release_dev;
-		rio_add_net(net);
+		if (rio_add_net(net)) {
+			put_device(&net->dev);
+			net = NULL;
+		}
 	}
 
 	return net;

From 8fe9ed44dc29fba0786b7e956d2e87179e407582 Mon Sep 17 00:00:00 2001
From: Hao Zhang <zhanghao1@kylinos.cn>
Date: Thu, 27 Feb 2025 11:41:29 +0800
Subject: [PATCH 1681/2753] mm/page_alloc: fix uninitialized variable

The variable "compact_result" is not initialized in function
__alloc_pages_slowpath().  It causes should_compact_retry() to use an
uninitialized value.

Initialize variable "compact_result" with the value COMPACT_SKIPPED.

BUG: KMSAN: uninit-value in __alloc_pages_slowpath+0xee8/0x16c0 mm/page_alloc.c:4416
 __alloc_pages_slowpath+0xee8/0x16c0 mm/page_alloc.c:4416
 __alloc_frozen_pages_noprof+0xa4c/0xe00 mm/page_alloc.c:4752
 alloc_pages_mpol+0x4cd/0x890 mm/mempolicy.c:2270
 alloc_frozen_pages_noprof mm/mempolicy.c:2341 [inline]
 alloc_pages_noprof mm/mempolicy.c:2361 [inline]
 folio_alloc_noprof+0x1dc/0x350 mm/mempolicy.c:2371
 filemap_alloc_folio_noprof+0xa6/0x440 mm/filemap.c:1019
 __filemap_get_folio+0xb9a/0x1840 mm/filemap.c:1970
 grow_dev_folio fs/buffer.c:1039 [inline]
 grow_buffers fs/buffer.c:1105 [inline]
 __getblk_slow fs/buffer.c:1131 [inline]
 bdev_getblk+0x2c9/0xab0 fs/buffer.c:1431
 getblk_unmovable include/linux/buffer_head.h:369 [inline]
 ext4_getblk+0x3b7/0xe50 fs/ext4/inode.c:864
 ext4_bread_batch+0x9f/0x7d0 fs/ext4/inode.c:933
 __ext4_find_entry+0x1ebb/0x36c0 fs/ext4/namei.c:1627
 ext4_lookup_entry fs/ext4/namei.c:1729 [inline]
 ext4_lookup+0x189/0xb40 fs/ext4/namei.c:1797
 __lookup_slow+0x538/0x710 fs/namei.c:1793
 lookup_slow+0x6a/0xd0 fs/namei.c:1810
 walk_component fs/namei.c:2114 [inline]
 link_path_walk+0xf29/0x1420 fs/namei.c:2479
 path_openat+0x30f/0x6250 fs/namei.c:3985
 do_filp_open+0x268/0x600 fs/namei.c:4016
 do_sys_openat2+0x1bf/0x2f0 fs/open.c:1428
 do_sys_open fs/open.c:1443 [inline]
 __do_sys_openat fs/open.c:1459 [inline]
 __se_sys_openat fs/open.c:1454 [inline]
 __x64_sys_openat+0x2a1/0x310 fs/open.c:1454
 x64_sys_call+0x36f5/0x3c30 arch/x86/include/generated/asm/syscalls_64.h:258
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x1e0 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Local variable compact_result created at:
 __alloc_pages_slowpath+0x66/0x16c0 mm/page_alloc.c:4218
 __alloc_frozen_pages_noprof+0xa4c/0xe00 mm/page_alloc.c:4752

Link: https://lkml.kernel.org/r/tencent_ED1032321D6510B145CDBA8CBA0093178E09@qq.com
Reported-by: syzbot+0cfd5e38e96a5596f2b6@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=0cfd5e38e96a5596f2b6
Signed-off-by: Hao Zhang <zhanghao1@kylinos.cn>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page_alloc.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fe986e6de7a01..94917c729120f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4243,6 +4243,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 restart:
 	compaction_retries = 0;
 	no_progress_loops = 0;
+	compact_result = COMPACT_SKIPPED;
 	compact_priority = DEF_COMPACT_PRIORITY;
 	cpuset_mems_cookie = read_mems_allowed_begin();
 	zonelist_iter_cookie = zonelist_iter_begin();

From 80da96d735094ea22985ced98bc57fe3a4422921 Mon Sep 17 00:00:00 2001
From: Takashi Iwai <tiwai@suse.de>
Date: Tue, 4 Mar 2025 14:41:57 +0100
Subject: [PATCH 1682/2753] drm/bochs: Fix DPMS regression

The recent rewrite with the use of regular atomic helpers broke the
DPMS unblanking on X11.  Fix it by moving the call of
bochs_hw_blank(false) from CRTC mode_set_nofb() to atomic_enable().

Fixes: 2037174993c8 ("drm/bochs: Use regular atomic helpers")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1238209
Signed-off-by: Takashi Iwai <tiwai@suse.de>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Link: https://patchwork.freedesktop.org/patch/msgid/20250304134203.20534-1-tiwai@suse.de
---
 drivers/gpu/drm/tiny/bochs.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/tiny/bochs.c b/drivers/gpu/drm/tiny/bochs.c
index c67e1f9067859..8706763af8fba 100644
--- a/drivers/gpu/drm/tiny/bochs.c
+++ b/drivers/gpu/drm/tiny/bochs.c
@@ -335,8 +335,6 @@ static void bochs_hw_setmode(struct bochs_device *bochs, struct drm_display_mode
 			 bochs->xres, bochs->yres, bochs->bpp,
 			 bochs->yres_virtual);
 
-	bochs_hw_blank(bochs, false);
-
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_ENABLE,      0);
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_BPP,         bochs->bpp);
 	bochs_dispi_write(bochs, VBE_DISPI_INDEX_XRES,        bochs->xres);
@@ -506,6 +504,9 @@ static int bochs_crtc_helper_atomic_check(struct drm_crtc *crtc,
 static void bochs_crtc_helper_atomic_enable(struct drm_crtc *crtc,
 					    struct drm_atomic_state *state)
 {
+	struct bochs_device *bochs = to_bochs_device(crtc->dev);
+
+	bochs_hw_blank(bochs, false);
 }
 
 static void bochs_crtc_helper_atomic_disable(struct drm_crtc *crtc,

From 556f93b90c1872ad85e216e613c0b33803e621cb Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Tue, 4 Mar 2025 14:02:46 +0000
Subject: [PATCH 1683/2753] RDMA/mlx5: Handle errors returned from
 mlx5r_ib_rate()

In function create_ib_ah() the following line attempts
to left shift the return value of mlx5r_ib_rate() by 4
and store it in the stat_rate_sl member of av:

However the code overlooks the fact that mlx5r_ib_rate()
may return -EINVAL if the rate passed to it is less than
IB_RATE_2_5_GBPS or greater than IB_RATE_800_GBPS.

Because of this, the code may invoke undefined behaviour when
shifting a signed negative value when doing "-EINVAL << 4".

To fix this check for errors before assigning stat_rate_sl and
propagate any error value to the callers.

Fixes: c534ffda781f ("RDMA/mlx5: Fix AH static rate parsing")
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Link: https://patch.msgid.link/20250304140246.205919-1-qasdev00@gmail.com
Reviewed-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/ah.c | 14 +++++++++-----
 1 file changed, 9 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/ah.c b/drivers/infiniband/hw/mlx5/ah.c
index 99036afb3aef0..531a57f9ee7e8 100644
--- a/drivers/infiniband/hw/mlx5/ah.c
+++ b/drivers/infiniband/hw/mlx5/ah.c
@@ -50,11 +50,12 @@ static __be16 mlx5_ah_get_udp_sport(const struct mlx5_ib_dev *dev,
 	return sport;
 }
 
-static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
+static int create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 			 struct rdma_ah_init_attr *init_attr)
 {
 	struct rdma_ah_attr *ah_attr = init_attr->ah_attr;
 	enum ib_gid_type gid_type;
+	int rate_val;
 
 	if (rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH) {
 		const struct ib_global_route *grh = rdma_ah_read_grh(ah_attr);
@@ -67,8 +68,10 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.tclass = grh->traffic_class;
 	}
 
-	ah->av.stat_rate_sl =
-		(mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr)) << 4);
+	rate_val = mlx5r_ib_rate(dev, rdma_ah_get_static_rate(ah_attr));
+	if (rate_val < 0)
+		return rate_val;
+	ah->av.stat_rate_sl = rate_val << 4;
 
 	if (ah_attr->type == RDMA_AH_ATTR_TYPE_ROCE) {
 		if (init_attr->xmit_slave)
@@ -89,6 +92,8 @@ static void create_ib_ah(struct mlx5_ib_dev *dev, struct mlx5_ib_ah *ah,
 		ah->av.fl_mlid = rdma_ah_get_path_bits(ah_attr) & 0x7f;
 		ah->av.stat_rate_sl |= (rdma_ah_get_sl(ah_attr) & 0xf);
 	}
+
+	return 0;
 }
 
 int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
@@ -121,8 +126,7 @@ int mlx5_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
 			return err;
 	}
 
-	create_ib_ah(dev, ah, init_attr);
-	return 0;
+	return create_ib_ah(dev, ah, init_attr);
 }
 
 int mlx5_ib_query_ah(struct ib_ah *ibah, struct rdma_ah_attr *ah_attr)

From d385c8bceb14665e935419334aa3d3fac2f10456 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Michal=20Koutn=C3=BD?= <mkoutny@suse.com>
Date: Wed, 5 Mar 2025 15:58:49 +0100
Subject: [PATCH 1684/2753] pid: Do not set pid_max in new pid namespaces
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is already difficult for users to troubleshoot which of multiple pid
limits restricts their workload. The per-(hierarchical-)NS pid_max would
contribute to the confusion.
Also, the implementation copies the limit upon creation from
parent, this pattern showed cumbersome with some attributes in legacy
cgroup controllers -- it's subject to race condition between parent's
limit modification and children creation and once copied it must be
changed in the descendant.

Let's do what other places do (ucounts or cgroup limits) -- create new
pid namespaces without any limit at all. The global limit (actually any
ancestor's limit) is still effectively in place, we avoid the
set/unshare race and bumps of global (ancestral) limit have the desired
effect on pid namespace that do not care.

Link: https://lore.kernel.org/r/20240408145819.8787-1-mkoutny@suse.com/
Link: https://lore.kernel.org/r/20250221170249.890014-1-mkoutny@suse.com/
Fixes: 7863dcc72d0f4 ("pid: allow pid_max to be set per pid namespace")
Signed-off-by: Michal Koutný <mkoutny@suse.com>
Link: https://lore.kernel.org/r/20250305145849.55491-1-mkoutny@suse.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 kernel/pid_namespace.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 8f6cfec87555a..7098ed44e717d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -107,7 +107,7 @@ static struct pid_namespace *create_pid_namespace(struct user_namespace *user_ns
 		goto out_free_idr;
 	ns->ns.ops = &pidns_operations;
 
-	ns->pid_max = parent_pid_ns->pid_max;
+	ns->pid_max = PID_MAX_LIMIT;
 	err = register_pidns_sysctls(ns);
 	if (err)
 		goto out_free_inum;

From 14672f059d83f591afb2ee1fff56858efe055e5a Mon Sep 17 00:00:00 2001
From: Shrikanth Hegde <sshegde@linux.ibm.com>
Date: Thu, 6 Mar 2025 10:59:53 +0530
Subject: [PATCH 1685/2753] sched/deadline: Use online cpus for validating
 runtime

The ftrace selftest reported a failure because writing -1 to
sched_rt_runtime_us returns -EBUSY. This happens when the possible
CPUs are different from active CPUs.

Active CPUs are part of one root domain, while remaining CPUs are part
of def_root_domain. Since active cpumask is being used, this results in
cpus=0 when a non active CPUs is used in the loop.

Fix it by looping over the online CPUs instead for validating the
bandwidth calculations.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20250306052954.452005-2-sshegde@linux.ibm.com
---
 kernel/sched/deadline.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 38e4537790af7..ff4df16b5186d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3189,7 +3189,7 @@ int sched_dl_global_validate(void)
 	 * value smaller than the currently allocated bandwidth in
 	 * any of the root_domains.
 	 */
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		rcu_read_lock_sched();
 
 		if (dl_bw_visited(cpu, gen))

From b1536481c81fb604074da799e4f2d2038a1663f7 Mon Sep 17 00:00:00 2001
From: Shrikanth Hegde <sshegde@linux.ibm.com>
Date: Thu, 6 Mar 2025 10:59:54 +0530
Subject: [PATCH 1686/2753] sched/rt: Update limit of sched_rt sysctl in
 documentation

By default fair_server dl_server allocates 5% of the bandwidth to the root
domain. Due to this writing any value less than 5% fails due to -EBUSY:

  $ cat /proc/sys/kernel/sched_rt_period_us
  1000000

  $ echo 49999 > /proc/sys/kernel/sched_rt_runtime_us
  -bash: echo: write error: Device or resource busy

  $ echo 50000 > /proc/sys/kernel/sched_rt_runtime_us
  $

Since the sched_rt_runtime_us allows -1 as the minimum, put this
restriction in the documentation.

One should check average of runtime/period in
/sys/kernel/debug/sched/fair_server/cpuX/* for exact value.

Signed-off-by: Shrikanth Hegde <sshegde@linux.ibm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lore.kernel.org/r/20250306052954.452005-3-sshegde@linux.ibm.com
---
 Documentation/scheduler/sched-rt-group.rst | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/Documentation/scheduler/sched-rt-group.rst b/Documentation/scheduler/sched-rt-group.rst
index 80b05a3009ea2..ab464335d3204 100644
--- a/Documentation/scheduler/sched-rt-group.rst
+++ b/Documentation/scheduler/sched-rt-group.rst
@@ -102,6 +102,9 @@ The system wide settings are configured under the /proc virtual file system:
   * sched_rt_period_us takes values from 1 to INT_MAX.
   * sched_rt_runtime_us takes values from -1 to sched_rt_period_us.
   * A run time of -1 specifies runtime == period, ie. no limit.
+  * sched_rt_runtime_us/sched_rt_period_us > 0.05 inorder to preserve
+    bandwidth for fair dl_server. For accurate value check average of
+    runtime/period in /sys/kernel/debug/sched/fair_server/cpuX/
 
 
 2.2 Default behaviour

From cf7ee25e70c6edfac4553d6b671e8b19db1d9573 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Tue, 4 Mar 2025 13:59:51 +0800
Subject: [PATCH 1687/2753] mctp i3c: handle NULL header address

daddr can be NULL if there is no neighbour table entry present,
in that case the tx packet should be dropped.

saddr will usually be set by MCTP core, but check for NULL in case a
packet is transmitted by a different protocol.

Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Fixes: c8755b29b58e ("mctp i3c: MCTP I3C driver")
Link: https://patch.msgid.link/20250304-mctp-i3c-null-v1-1-4416bbd56540@codeconstruct.com.au
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/mctp/mctp-i3c.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c
index d247fe483c588..c1e72253063b5 100644
--- a/drivers/net/mctp/mctp-i3c.c
+++ b/drivers/net/mctp/mctp-i3c.c
@@ -507,6 +507,9 @@ static int mctp_i3c_header_create(struct sk_buff *skb, struct net_device *dev,
 {
 	struct mctp_i3c_internal_hdr *ihdr;
 
+	if (!daddr || !saddr)
+		return -EINVAL;
+
 	skb_push(skb, sizeof(struct mctp_i3c_internal_hdr));
 	skb_reset_mac_header(skb);
 	ihdr = (void *)skb_mac_header(skb);

From 0e7633d7b95b67f1758aea19f8e85621c5f506a3 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Tue, 4 Mar 2025 19:10:39 +0100
Subject: [PATCH 1688/2753] net: ipv6: fix dst ref loop in ila lwtunnel

This patch follows commit 92191dd10730 ("net: ipv6: fix dst ref loops in
rpl, seg6 and ioam6 lwtunnels") and, on a second thought, the same patch
is also needed for ila (even though the config that triggered the issue
was pathological, but still, we don't want that to happen).

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250304181039.35951-1-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ila/ila_lwt.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ff7e734e335b0..ac4bcc623603a 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -88,7 +88,8 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 		}
 
-		if (ilwt->connected) {
+		/* cache only if we don't create a dst reference loop */
+		if (ilwt->connected && orig_dst->lwtstate != dst->lwtstate) {
 			local_bh_disable();
 			dst_cache_set_ip6(&ilwt->dst_cache, dst, &fl6.saddr);
 			local_bh_enable();

From 5da15a9c11c1c47ef573e6805b60a7d8a1687a2a Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Wed, 5 Mar 2025 09:16:55 +0100
Subject: [PATCH 1689/2753] net: ipv6: fix missing dst ref drop in ila lwtunnel

Add missing skb_dst_drop() to drop reference to the old dst before
adding the new dst to the skb.

Fixes: 79ff2fc31e0f ("ila: Cache a route to translated address")
Cc: Tom Herbert <tom@herbertland.com>
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250305081655.19032-1-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ila/ila_lwt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/ipv6/ila/ila_lwt.c b/net/ipv6/ila/ila_lwt.c
index ac4bcc623603a..7d574f5132e2f 100644
--- a/net/ipv6/ila/ila_lwt.c
+++ b/net/ipv6/ila/ila_lwt.c
@@ -96,6 +96,7 @@ static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 		}
 	}
 
+	skb_dst_drop(skb);
 	skb_dst_set(skb, dst);
 	return dst_output(net, sk, skb);
 

From 9a665fe3d967fe46edb4fd2497c7a5cc2dac2f55 Mon Sep 17 00:00:00 2001
From: Johan Hovold <johan@kernel.org>
Date: Thu, 6 Mar 2025 11:44:41 +0100
Subject: [PATCH 1690/2753] USB: serial: option: match on interface class for
 Telit FN990B

The device id entries for Telit FN990B ended up matching only on the
interface protocol. While this works, the protocol is qualified by the
interface class (and subclass) which should have been included.

Switch to matching using USB_DEVICE_AND_INTERFACE_INFO() while keeping
the entries sorted also by protocol for consistency.

Link: https://lore.kernel.org/20250227110655.3647028-2-fabio.porcedda@gmail.com/
Cc: Fabio Porcedda <fabio.porcedda@gmail.com>
Cc: Daniele Palmas <dnlplm@gmail.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 58bd54e8c483a..1ea2870725aca 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1394,22 +1394,22 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c8, 0xff),	/* Telit FE910C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x60) },	/* Telit FN990B (rmnet) */
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x40) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d0, 0x30),
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x30),	/* Telit FN990B (rmnet) */
 	  .driver_info = NCTRL(5) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x60) },	/* Telit FN990B (MBIM) */
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x40) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d1, 0x30),
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d0, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x30),	/* Telit FN990B (MBIM) */
 	  .driver_info = NCTRL(6) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x60) },	/* Telit FN990B (RNDIS) */
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x40) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d2, 0x30),
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d1, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x30),	/* Telit FN990B (RNDIS) */
 	  .driver_info = NCTRL(6) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x60) },	/* Telit FN990B (ECM) */
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x40) },
-	{ USB_DEVICE_INTERFACE_PROTOCOL(TELIT_VENDOR_ID, 0x10d3, 0x30),
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d2, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x30),	/* Telit FN990B (ECM) */
 	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10d3, 0xff, 0xff, 0x60) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910),
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(3) },
 	{ USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_ME910_DUAL_MODEM),

From 4981bb50392b7515b765da28cf8768ce624c2670 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Tue, 4 Mar 2025 10:19:38 +0100
Subject: [PATCH 1691/2753] USB: serial: option: add Telit Cinterion FE990B
 compositions

Add the following Telit Cinterion FE990B40 compositions:

0x10b0: rmnet + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#=  7 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10b0 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FE990
S:  SerialNumber=28c2595e
C:  #Ifs= 9 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 6 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x10b1: MBIM + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#=  8 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10b1 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FE990
S:  SerialNumber=28c2595e
C:  #Ifs=10 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=0e Prot=00 Driver=cdc_mbim
E:  Ad=82(I) Atr=03(Int.) MxPS=  64 Ivl=32ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=02 Driver=cdc_mbim
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x10b2: RNDIS + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#=  9 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10b2 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FE990
S:  SerialNumber=28c2595e
C:  #Ifs=10 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=ef(misc ) Sub=04 Prot=01 Driver=rndis_host
E:  Ad=82(I) Atr=03(Int.) MxPS=   8 Ivl=32ms
I:  If#= 1 Alt= 0 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=rndis_host
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

0x10b3: ECM + tty (AT/NMEA) + tty (AT) + tty (AT) + tty (AT) +
        tty (diag) + DPL + QDSS (Qualcomm Debug SubSystem) + adb
T:  Bus=01 Lev=01 Prnt=01 Port=01 Cnt=01 Dev#= 11 Spd=480  MxCh= 0
D:  Ver= 2.10 Cls=00(>ifc ) Sub=00 Prot=00 MxPS=64 #Cfgs=  1
P:  Vendor=1bc7 ProdID=10b3 Rev=05.15
S:  Manufacturer=Telit Cinterion
S:  Product=FE990
S:  SerialNumber=28c2595e
C:  #Ifs=10 Cfg#= 1 Atr=e0 MxPwr=500mA
I:  If#= 0 Alt= 0 #EPs= 1 Cls=02(commc) Sub=06 Prot=00 Driver=cdc_ether
E:  Ad=82(I) Atr=03(Int.) MxPS=  16 Ivl=32ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=0a(data ) Sub=00 Prot=00 Driver=cdc_ether
E:  Ad=01(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=81(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=60 Driver=option
E:  Ad=02(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=83(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=84(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 3 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=03(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=85(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=86(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 4 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=04(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=87(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=88(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 5 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option
E:  Ad=05(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=89(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8a(I) Atr=03(Int.) MxPS=  10 Ivl=32ms
I:  If#= 6 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option
E:  Ad=06(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8b(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 7 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=80 Driver=(none)
E:  Ad=8c(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 8 Alt= 0 #EPs= 1 Cls=ff(vend.) Sub=ff Prot=70 Driver=(none)
E:  Ad=8d(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms
I:  If#= 9 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=42 Prot=01 Driver=(none)
E:  Ad=07(O) Atr=02(Bulk) MxPS= 512 Ivl=0ms
E:  Ad=8e(I) Atr=02(Bulk) MxPS= 512 Ivl=0ms

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Reviewed-by: Daniele Palmas <dnlplm@gmail.com>
[ johan: use USB_DEVICE_AND_INTERFACE_INFO() and sort by protocol ]
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 1ea2870725aca..aeb71d96a8287 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1388,6 +1388,22 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = RSVD(0) | NCTRL(2) | RSVD(3) | RSVD(4) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10aa, 0xff),	/* Telit FN920C04 (MBIM) */
 	  .driver_info = NCTRL(3) | RSVD(4) | RSVD(5) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x30),	/* Telit FE990B (rmnet) */
+	  .driver_info = NCTRL(5) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b0, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x30),	/* Telit FE990B (MBIM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b1, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x30),	/* Telit FE990B (RNDIS) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b2, 0xff, 0xff, 0x60) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x30),	/* Telit FE990B (ECM) */
+	  .driver_info = NCTRL(6) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x40) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(TELIT_VENDOR_ID, 0x10b3, 0xff, 0xff, 0x60) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c0, 0xff),	/* Telit FE910C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10c4, 0xff),	/* Telit FE910C04 (rmnet) */

From 6232f0d8e100a26275bbd773fc56a60af2c95322 Mon Sep 17 00:00:00 2001
From: Fabio Porcedda <fabio.porcedda@gmail.com>
Date: Tue, 4 Mar 2025 10:19:39 +0100
Subject: [PATCH 1692/2753] USB: serial: option: fix Telit Cinterion FE990A
 name

The correct name for FE990 is FE990A so use it in order to avoid
confusion with FE990B.

Cc: stable@vger.kernel.org
Signed-off-by: Fabio Porcedda <fabio.porcedda@gmail.com>
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/option.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index aeb71d96a8287..5cd26dac2069f 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -1368,13 +1368,13 @@ static const struct usb_device_id option_ids[] = {
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff),	/* Telit FN990A (PCIe) */
 	  .driver_info = RSVD(0) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990 (rmnet) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff),	/* Telit FE990A (rmnet) */
 	  .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990 (MBIM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff),	/* Telit FE990A (MBIM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff),	/* Telit FE990 (RNDIS) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1082, 0xff),	/* Telit FE990A (RNDIS) */
 	  .driver_info = NCTRL(2) | RSVD(3) },
-	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff),	/* Telit FE990 (ECM) */
+	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1083, 0xff),	/* Telit FE990A (ECM) */
 	  .driver_info = NCTRL(0) | RSVD(1) },
 	{ USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x10a0, 0xff),	/* Telit FN20C04 (rmnet) */
 	  .driver_info = RSVD(0) | NCTRL(3) },

From 9af152dcf1a06f589f44a74da4ad67e365d4db9a Mon Sep 17 00:00:00 2001
From: Ivan Abramov <i.abramov@mt-integration.ru>
Date: Thu, 6 Mar 2025 14:20:45 +0300
Subject: [PATCH 1693/2753] drm/gma500: Add NULL check for pci_gfx_root in
 mid_get_vbt_data()

Since pci_get_domain_bus_and_slot() can return NULL, add NULL check for
pci_gfx_root in the mid_get_vbt_data().

This change is similar to the checks implemented in mid_get_fuse_settings()
and mid_get_pci_revID(), which were introduced by commit 0cecdd818cd7
("gma500: Final enables for Oaktrail") as "additional minor
bulletproofing".

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: f910b411053f ("gma500: Add the glue to the various BIOS and firmware interfaces")
Signed-off-by: Ivan Abramov <i.abramov@mt-integration.ru>
Signed-off-by: Patrik Jakobsson <patrik.r.jakobsson@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306112046.17144-1-i.abramov@mt-integration.ru
---
 drivers/gpu/drm/gma500/mid_bios.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/gpu/drm/gma500/mid_bios.c b/drivers/gpu/drm/gma500/mid_bios.c
index 7e76790c6a81f..cba97d7db131d 100644
--- a/drivers/gpu/drm/gma500/mid_bios.c
+++ b/drivers/gpu/drm/gma500/mid_bios.c
@@ -279,6 +279,11 @@ static void mid_get_vbt_data(struct drm_psb_private *dev_priv)
 					    0, PCI_DEVFN(2, 0));
 	int ret = -1;
 
+	if (pci_gfx_root == NULL) {
+		WARN_ON(1);
+		return;
+	}
+
 	/* Get the address of the platform config vbt */
 	pci_read_config_dword(pci_gfx_root, 0xFC, &addr);
 	pci_dev_put(pci_gfx_root);

From b5e3956535466187657563b754ba0f1da8626c7f Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Thu, 6 Mar 2025 14:39:51 +0800
Subject: [PATCH 1694/2753] kbuild: install-extmod-build: Fix build when
 specifying KBUILD_OUTPUT

Since commit 5f73e7d0386d ("kbuild: refactor cross-compiling
linux-headers package"), the linux-headers pacman package fails
to build when "O=" is set. The build system complains:

/mnt/chroot/linux/scripts/Makefile.build:41: mnt/chroots/linux-mainline/pacman/linux-upstream/pkg/linux-upstream-headers/usr//lib/modules/6.14.0-rc3-00350-g771dba31fffc/build/scripts/Makefile: No such file or directory

This is because the "srcroot" variable is set to "." and the
"build" variable is set to the absolute path. This makes the
"src" variables point to wrong directory.

Change the "build" variable to a relative path to "." to
fix build.

Fixes: 5f73e7d0386d ("kbuild: refactor cross-compiling linux-headers package")
Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
 scripts/package/install-extmod-build | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/scripts/package/install-extmod-build b/scripts/package/install-extmod-build
index 2966473b46609..b96538787f3d9 100755
--- a/scripts/package/install-extmod-build
+++ b/scripts/package/install-extmod-build
@@ -63,7 +63,7 @@ if [ "${CC}" != "${HOSTCC}" ]; then
 	# Clear VPATH and srcroot because the source files reside in the output
 	# directory.
 	# shellcheck disable=SC2016 # $(MAKE) and $(build) will be expanded by Make
-	"${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"${destdir}"/scripts
+	"${MAKE}" run-command KBUILD_RUN_COMMAND='+$(MAKE) HOSTCC='"${CC}"' VPATH= srcroot=. $(build)='"$(realpath --relative-base=. "${destdir}")"/scripts
 
 	rm -f "${destdir}/scripts/Kbuild"
 fi

From fb8286562ecfb585e26b033c5e32e6fb85efb0b3 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Thu, 6 Mar 2025 04:05:26 +0100
Subject: [PATCH 1695/2753] netfilter: nf_tables: make destruction work queue
 pernet

The call to flush_work before tearing down a table from the netlink
notifier was supposed to make sure that all earlier updates (e.g. rule
add) that might reference that table have been processed.

Unfortunately, flush_work() waits for the last queued instance.
This could be an instance that is different from the one that we must
wait for.

This is because transactions are protected with a pernet mutex, but the
work item is global, so holding the transaction mutex doesn't prevent
another netns from queueing more work.

Make the work item pernet so that flush_work() will wait for all
transactions queued from this netns.

A welcome side effect is that we no longer need to wait for transaction
objects from foreign netns.

The gc work queue is still global.  This seems to be ok because nft_set
structures are reference counted and each container structure owns a
reference on the net namespace.

The destroy_list is still protected by a global spinlock rather than
pernet one but the hold time is very short anyway.

v2: call cancel_work_sync before reaping the remaining tables (Pablo).

Fixes: 9f6958ba2e90 ("netfilter: nf_tables: unconditionally flush pending work before notifier")
Reported-by: syzbot+5d8c5789c8cb076b2c25@syzkaller.appspotmail.com
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nf_tables.h |  4 +++-
 net/netfilter/nf_tables_api.c     | 24 ++++++++++++++----------
 net/netfilter/nft_compat.c        |  8 ++++----
 3 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 60d5dcdb289c9..803d5f1601f9d 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -1891,7 +1891,7 @@ void nft_chain_filter_fini(void);
 void __init nft_chain_route_init(void);
 void nft_chain_route_fini(void);
 
-void nf_tables_trans_destroy_flush_work(void);
+void nf_tables_trans_destroy_flush_work(struct net *net);
 
 int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result);
 __be64 nf_jiffies64_to_msecs(u64 input);
@@ -1905,6 +1905,7 @@ static inline int nft_request_module(struct net *net, const char *fmt, ...) { re
 struct nftables_pernet {
 	struct list_head	tables;
 	struct list_head	commit_list;
+	struct list_head	destroy_list;
 	struct list_head	commit_set_list;
 	struct list_head	binding_list;
 	struct list_head	module_list;
@@ -1915,6 +1916,7 @@ struct nftables_pernet {
 	unsigned int		base_seq;
 	unsigned int		gc_seq;
 	u8			validate_state;
+	struct work_struct	destroy_work;
 };
 
 extern unsigned int nf_tables_net_id;
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index a34de9c17cf10..c2df81b7e9505 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -34,7 +34,6 @@ unsigned int nf_tables_net_id __read_mostly;
 static LIST_HEAD(nf_tables_expressions);
 static LIST_HEAD(nf_tables_objects);
 static LIST_HEAD(nf_tables_flowtables);
-static LIST_HEAD(nf_tables_destroy_list);
 static LIST_HEAD(nf_tables_gc_list);
 static DEFINE_SPINLOCK(nf_tables_destroy_list_lock);
 static DEFINE_SPINLOCK(nf_tables_gc_list_lock);
@@ -125,7 +124,6 @@ static void nft_validate_state_update(struct nft_table *table, u8 new_validate_s
 	table->validate_state = new_validate_state;
 }
 static void nf_tables_trans_destroy_work(struct work_struct *w);
-static DECLARE_WORK(trans_destroy_work, nf_tables_trans_destroy_work);
 
 static void nft_trans_gc_work(struct work_struct *work);
 static DECLARE_WORK(trans_gc_work, nft_trans_gc_work);
@@ -10006,11 +10004,12 @@ static void nft_commit_release(struct nft_trans *trans)
 
 static void nf_tables_trans_destroy_work(struct work_struct *w)
 {
+	struct nftables_pernet *nft_net = container_of(w, struct nftables_pernet, destroy_work);
 	struct nft_trans *trans, *next;
 	LIST_HEAD(head);
 
 	spin_lock(&nf_tables_destroy_list_lock);
-	list_splice_init(&nf_tables_destroy_list, &head);
+	list_splice_init(&nft_net->destroy_list, &head);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
 	if (list_empty(&head))
@@ -10024,9 +10023,11 @@ static void nf_tables_trans_destroy_work(struct work_struct *w)
 	}
 }
 
-void nf_tables_trans_destroy_flush_work(void)
+void nf_tables_trans_destroy_flush_work(struct net *net)
 {
-	flush_work(&trans_destroy_work);
+	struct nftables_pernet *nft_net = nft_pernet(net);
+
+	flush_work(&nft_net->destroy_work);
 }
 EXPORT_SYMBOL_GPL(nf_tables_trans_destroy_flush_work);
 
@@ -10484,11 +10485,11 @@ static void nf_tables_commit_release(struct net *net)
 
 	trans->put_net = true;
 	spin_lock(&nf_tables_destroy_list_lock);
-	list_splice_tail_init(&nft_net->commit_list, &nf_tables_destroy_list);
+	list_splice_tail_init(&nft_net->commit_list, &nft_net->destroy_list);
 	spin_unlock(&nf_tables_destroy_list_lock);
 
 	nf_tables_module_autoload_cleanup(net);
-	schedule_work(&trans_destroy_work);
+	schedule_work(&nft_net->destroy_work);
 
 	mutex_unlock(&nft_net->commit_mutex);
 }
@@ -11853,7 +11854,7 @@ static int nft_rcv_nl_event(struct notifier_block *this, unsigned long event,
 
 	gc_seq = nft_gc_seq_begin(nft_net);
 
-	nf_tables_trans_destroy_flush_work();
+	nf_tables_trans_destroy_flush_work(net);
 again:
 	list_for_each_entry(table, &nft_net->tables, list) {
 		if (nft_table_has_owner(table) &&
@@ -11895,6 +11896,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 
 	INIT_LIST_HEAD(&nft_net->tables);
 	INIT_LIST_HEAD(&nft_net->commit_list);
+	INIT_LIST_HEAD(&nft_net->destroy_list);
 	INIT_LIST_HEAD(&nft_net->commit_set_list);
 	INIT_LIST_HEAD(&nft_net->binding_list);
 	INIT_LIST_HEAD(&nft_net->module_list);
@@ -11903,6 +11905,7 @@ static int __net_init nf_tables_init_net(struct net *net)
 	nft_net->base_seq = 1;
 	nft_net->gc_seq = 0;
 	nft_net->validate_state = NFT_VALIDATE_SKIP;
+	INIT_WORK(&nft_net->destroy_work, nf_tables_trans_destroy_work);
 
 	return 0;
 }
@@ -11931,14 +11934,17 @@ static void __net_exit nf_tables_exit_net(struct net *net)
 	if (!list_empty(&nft_net->module_list))
 		nf_tables_module_autoload_cleanup(net);
 
+	cancel_work_sync(&nft_net->destroy_work);
 	__nft_release_tables(net);
 
 	nft_gc_seq_end(nft_net, gc_seq);
 
 	mutex_unlock(&nft_net->commit_mutex);
+
 	WARN_ON_ONCE(!list_empty(&nft_net->tables));
 	WARN_ON_ONCE(!list_empty(&nft_net->module_list));
 	WARN_ON_ONCE(!list_empty(&nft_net->notify_list));
+	WARN_ON_ONCE(!list_empty(&nft_net->destroy_list));
 }
 
 static void nf_tables_exit_batch(struct list_head *net_exit_list)
@@ -12029,10 +12035,8 @@ static void __exit nf_tables_module_exit(void)
 	unregister_netdevice_notifier(&nf_tables_flowtable_notifier);
 	nft_chain_filter_fini();
 	nft_chain_route_fini();
-	nf_tables_trans_destroy_flush_work();
 	unregister_pernet_subsys(&nf_tables_net_ops);
 	cancel_work_sync(&trans_gc_work);
-	cancel_work_sync(&trans_destroy_work);
 	rcu_barrier();
 	rhltable_destroy(&nft_objname_ht);
 	nf_tables_core_module_exit();
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 7ca4f0d21fe2a..72711d62fddfa 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -228,7 +228,7 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv)
 	return 0;
 }
 
-static void nft_compat_wait_for_destructors(void)
+static void nft_compat_wait_for_destructors(struct net *net)
 {
 	/* xtables matches or targets can have side effects, e.g.
 	 * creation/destruction of /proc files.
@@ -236,7 +236,7 @@ static void nft_compat_wait_for_destructors(void)
 	 * work queue.  If we have pending invocations we thus
 	 * need to wait for those to finish.
 	 */
-	nf_tables_trans_destroy_flush_work();
+	nf_tables_trans_destroy_flush_work(net);
 }
 
 static int
@@ -262,7 +262,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv);
 
-	nft_compat_wait_for_destructors();
+	nft_compat_wait_for_destructors(ctx->net);
 
 	ret = xt_check_target(&par, size, proto, inv);
 	if (ret < 0) {
@@ -515,7 +515,7 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 
 	nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv);
 
-	nft_compat_wait_for_destructors();
+	nft_compat_wait_for_destructors(ctx->net);
 
 	return xt_check_match(&par, size, proto, inv);
 }

From e26f1cfeac6712516bfeed80890da664f4f2e88a Mon Sep 17 00:00:00 2001
From: Charles Keepax <ckeepax@opensource.cirrus.com>
Date: Thu, 6 Mar 2025 13:32:54 +0000
Subject: [PATCH 1696/2753] ASoC: cs42l43: Fix maximum ADC Volume

The range of ADC volume is -1 -> 3 (-6 to 18dB) so the number of levels
should actually be 4.

Fixes: fc918cbe874e ("ASoC: cs42l43: Add support for the cs42l43")
Signed-off-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250306133254.1861046-1-ckeepax@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index 4257dbefe9dd1..d307b56a7f38e 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -1146,7 +1146,7 @@ static const struct snd_kcontrol_new cs42l43_controls[] = {
 
 	SOC_DOUBLE_R_SX_TLV("ADC Volume", CS42L43_ADC_B_CTRL1, CS42L43_ADC_B_CTRL2,
 			    CS42L43_ADC_PGA_GAIN_SHIFT,
-			    0xF, 5, cs42l43_adc_tlv),
+			    0xF, 4, cs42l43_adc_tlv),
 
 	SOC_DOUBLE("PDM1 Invert Switch", CS42L43_DMIC_PDM_CTRL,
 		   CS42L43_PDM1L_INV_SHIFT, CS42L43_PDM1R_INV_SHIFT, 1, 0),

From 35d99c68af40a8ca175babc5a89ef7e2226fb3ca Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Mon, 3 Mar 2025 10:42:33 +0800
Subject: [PATCH 1697/2753] btrfs: fix a leaked chunk map issue in
 read_one_chunk()

Add btrfs_free_chunk_map() to free the memory allocated
by btrfs_alloc_chunk_map() if btrfs_add_chunk_map() fails.

Fixes: 7dc66abb5a47 ("btrfs: use a dedicated data structure for chunk maps")
CC: stable@vger.kernel.org
Reviewed-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Signed-off-by: David Sterba <dsterba@suse.com>
---
 fs/btrfs/volumes.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index f6ae76815e4b5..6f8dcf59b5257 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -7151,6 +7151,7 @@ static int read_one_chunk(struct btrfs_key *key, struct extent_buffer *leaf,
 		btrfs_err(fs_info,
 			  "failed to add chunk map, start=%llu len=%llu: %d",
 			  map->start, map->chunk_len, ret);
+		btrfs_free_chunk_map(map);
 	}
 
 	return ret;

From 391b41f983bf7ff853de44704d8e14e7cc648a9b Mon Sep 17 00:00:00 2001
From: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Date: Wed, 5 Mar 2025 16:37:50 +0000
Subject: [PATCH 1698/2753] gpio: rcar: Fix missing of_node_put() call

of_parse_phandle_with_fixed_args() requires its caller to
call into of_node_put() on the node pointer from the output
structure, but such a call is currently missing.

Call into of_node_put() to rectify that.

Fixes: 159f8a0209af ("gpio-rcar: Add DT support")
Signed-off-by: Fabrizio Castro <fabrizio.castro.jz@renesas.com>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://lore.kernel.org/r/20250305163753.34913-2-fabrizio.castro.jz@renesas.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-rcar.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index 8e0544e924886..a7a1cdf7ac66d 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -468,7 +468,12 @@ static int gpio_rcar_parse_dt(struct gpio_rcar_priv *p, unsigned int *npins)
 	p->info = *info;
 
 	ret = of_parse_phandle_with_fixed_args(np, "gpio-ranges", 3, 0, &args);
-	*npins = ret == 0 ? args.args[2] : RCAR_MAX_GPIO_PER_BANK;
+	if (ret) {
+		*npins = RCAR_MAX_GPIO_PER_BANK;
+	} else {
+		*npins = args.args[2];
+		of_node_put(args.np);
+	}
 
 	if (*npins == 0 || *npins > RCAR_MAX_GPIO_PER_BANK) {
 		dev_warn(p->dev, "Invalid number of gpio lines %u, using %u\n",

From 98f3ab18a0a55aa1ff2cd6b74bd0c02c8f76f17e Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 5 Feb 2025 13:11:33 +0100
Subject: [PATCH 1699/2753] ARM: OMAP1: select CONFIG_GENERIC_IRQ_CHIP

When GENERIC_IRQ_CHIP is disabled, OMAP1 kernels fail to link:

arm-linux-gnueabi-ld: arch/arm/mach-omap1/irq.o: in function `omap1_init_irq':
irq.c:(.init.text+0x1e8): undefined reference to `irq_alloc_generic_chip'
arm-linux-gnueabi-ld: irq.c:(.init.text+0x228): undefined reference to `irq_setup_generic_chip'
arm-linux-gnueabi-ld: irq.c:(.init.text+0x2a8): undefined reference to `irq_gc_set_wake'
arm-linux-gnueabi-ld: irq.c:(.init.text+0x2b0): undefined reference to `irq_gc_mask_set_bit'
arm-linux-gnueabi-ld: irq.c:(.init.text+0x2b4): undefined reference to `irq_gc_mask_clr_bit'

This has apparently been the case for many years, but I never caught it
in randconfig builds until now, as there are dozens of other drivers
that also 'select GENERIC_IRQ_CHIP' and statistically there is almost
always one of them enabled.

Fixes: 55b447744389 ("ARM: OMAP1: Switch to use generic irqchip in preparation for sparse IRQ")
Link: https://lore.kernel.org/r/20250205121151.289535-1-arnd@kernel.org
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-omap1/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index a643b71e30a35..08ec6bd84ada5 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -8,6 +8,7 @@ menuconfig ARCH_OMAP1
 	select ARCH_OMAP
 	select CLKSRC_MMIO
 	select FORCE_PCI if PCCARD
+	select GENERIC_IRQ_CHIP
 	select GPIOLIB
 	help
 	  Support for older TI OMAP1 (omap7xx, omap15xx or omap16xx)

From ff712188daa3fe3ce7e11e530b4dca3826dae14a Mon Sep 17 00:00:00 2001
From: Miao Li <limiao@kylinos.cn>
Date: Tue, 4 Mar 2025 15:07:57 +0800
Subject: [PATCH 1700/2753] usb: quirks: Add DELAY_INIT and NO_LPM for Prolific
 Mass Storage Card Reader

When used on Huawei hisi platforms, Prolific Mass Storage Card Reader
which the VID:PID is in 067b:2731 might fail to enumerate at boot time
and doesn't work well with LPM enabled, combination quirks:
	USB_QUIRK_DELAY_INIT + USB_QUIRK_NO_LPM
fixed the problems.

Signed-off-by: Miao Li <limiao@kylinos.cn>
Cc: stable <stable@kernel.org>
Link: https://lore.kernel.org/r/20250304070757.139473-1-limiao870622@163.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/quirks.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/usb/core/quirks.c b/drivers/usb/core/quirks.c
index dfcfc142bd5e1..8efbacc5bc341 100644
--- a/drivers/usb/core/quirks.c
+++ b/drivers/usb/core/quirks.c
@@ -341,6 +341,10 @@ static const struct usb_device_id usb_quirk_list[] = {
 	{ USB_DEVICE(0x0638, 0x0a13), .driver_info =
 	  USB_QUIRK_STRING_FETCH_255 },
 
+	/* Prolific Single-LUN Mass Storage Card Reader */
+	{ USB_DEVICE(0x067b, 0x2731), .driver_info = USB_QUIRK_DELAY_INIT |
+	  USB_QUIRK_NO_LPM },
+
 	/* Saitek Cyborg Gold Joystick */
 	{ USB_DEVICE(0x06a3, 0x0006), .driver_info =
 			USB_QUIRK_CONFIG_INTF_STRINGS },

From b13abcb7ddd8d38de769486db5bd917537b32ab1 Mon Sep 17 00:00:00 2001
From: Andrei Kuchynski <akuchynski@chromium.org>
Date: Wed, 5 Mar 2025 11:17:39 +0000
Subject: [PATCH 1701/2753] usb: typec: ucsi: Fix NULL pointer access

Resources should be released only after all threads that utilize them
have been destroyed.
This commit ensures that resources are not released prematurely by waiting
for the associated workqueue to complete before deallocating them.

Cc: stable <stable@kernel.org>
Fixes: b9aa02ca39a4 ("usb: typec: ucsi: Add polling mechanism for partner tasks like alt mode checking")
Signed-off-by: Andrei Kuchynski <akuchynski@chromium.org>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250305111739.1489003-2-akuchynski@chromium.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/ucsi/ucsi.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
index 7a56d3f840d75..2a2915b0a645f 100644
--- a/drivers/usb/typec/ucsi/ucsi.c
+++ b/drivers/usb/typec/ucsi/ucsi.c
@@ -1825,11 +1825,11 @@ static int ucsi_init(struct ucsi *ucsi)
 
 err_unregister:
 	for (con = connector; con->port; con++) {
+		if (con->wq)
+			destroy_workqueue(con->wq);
 		ucsi_unregister_partner(con);
 		ucsi_unregister_altmodes(con, UCSI_RECIPIENT_CON);
 		ucsi_unregister_port_psy(con);
-		if (con->wq)
-			destroy_workqueue(con->wq);
 
 		usb_power_delivery_unregister_capabilities(con->port_sink_caps);
 		con->port_sink_caps = NULL;
@@ -2013,10 +2013,6 @@ void ucsi_unregister(struct ucsi *ucsi)
 
 	for (i = 0; i < ucsi->cap.num_connectors; i++) {
 		cancel_work_sync(&ucsi->connector[i].work);
-		ucsi_unregister_partner(&ucsi->connector[i]);
-		ucsi_unregister_altmodes(&ucsi->connector[i],
-					 UCSI_RECIPIENT_CON);
-		ucsi_unregister_port_psy(&ucsi->connector[i]);
 
 		if (ucsi->connector[i].wq) {
 			struct ucsi_work *uwork;
@@ -2032,6 +2028,11 @@ void ucsi_unregister(struct ucsi *ucsi)
 			destroy_workqueue(ucsi->connector[i].wq);
 		}
 
+		ucsi_unregister_partner(&ucsi->connector[i]);
+		ucsi_unregister_altmodes(&ucsi->connector[i],
+					 UCSI_RECIPIENT_CON);
+		ucsi_unregister_port_psy(&ucsi->connector[i]);
+
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_sink_caps);
 		ucsi->connector[i].port_sink_caps = NULL;
 		usb_power_delivery_unregister_capabilities(ucsi->connector[i].port_source_caps);

From 74d42bdb3a4673b1c10d1f457184e4d3c9cb0196 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:30:42 -1000
Subject: [PATCH 1702/2753] fs/pipe: express 'pipe_empty()' in terms of
 'pipe_occupancy()'

That's what 'pipe_full()' does, so it's more consistent. But more
importantly it gets the type limits right when the pipe head and tail
are no longer necessarily 'unsigned int'.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/pipe_fs_i.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index e572e6fc4f81f..4d0a2267e6efc 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -177,23 +177,23 @@ static inline bool pipe_has_watch_queue(const struct pipe_inode_info *pipe)
 }
 
 /**
- * pipe_empty - Return true if the pipe is empty
+ * pipe_occupancy - Return number of slots used in the pipe
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline bool pipe_empty(unsigned int head, unsigned int tail)
+static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
 {
-	return head == tail;
+	return (pipe_index_t)(head - tail);
 }
 
 /**
- * pipe_occupancy - Return number of slots used in the pipe
+ * pipe_empty - Return true if the pipe is empty
  * @head: The pipe ring head pointer
  * @tail: The pipe ring tail pointer
  */
-static inline unsigned int pipe_occupancy(unsigned int head, unsigned int tail)
+static inline bool pipe_empty(unsigned int head, unsigned int tail)
 {
-	return (pipe_index_t)(head - tail);
+	return !pipe_occupancy(head, tail);
 }
 
 /**

From d810d4c27bf34c719243bab9feb0d843edc09fd7 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:33:58 -1000
Subject: [PATCH 1703/2753] fs/pipe: do not open-code pipe head/tail logic in
 FIONREAD

Rasmus points out that we do indeed have other cases of breakage from
the type changes that were introduced on 32-bit targets in order to read
the pipe head and tail values atomically (commit 3d252160b818: "fs/pipe:
Read pipe->{head,tail} atomically outside pipe->mutex").

Fix it up by using the proper helper functions that now deal with the
pipe buffer index types properly.  This makes the code simpler and more
obvious.

The compiler does the CSE and loop hoisting of the pipe ring size
masking that we used to do manually, so open-coding this was never a
good idea.

Reported-by: Rasmus Villemoes <ravi@prevas.dk>
Link: https://lore.kernel.org/all/87cyeu5zgk.fsf@prevas.dk/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/pipe.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/fs/pipe.c b/fs/pipe.c
index e8e6698f36981..5c872775a6db9 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -614,7 +614,7 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct pipe_inode_info *pipe = filp->private_data;
-	unsigned int count, head, tail, mask;
+	unsigned int count, head, tail;
 
 	switch (cmd) {
 	case FIONREAD:
@@ -622,10 +622,9 @@ static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		count = 0;
 		head = pipe->head;
 		tail = pipe->tail;
-		mask = pipe->ring_size - 1;
 
-		while (tail != head) {
-			count += pipe->bufs[tail & mask].len;
+		while (!pipe_empty(head, tail)) {
+			count += pipe_buf(pipe, tail)->len;
 			tail++;
 		}
 		mutex_unlock(&pipe->mutex);

From ebb0f38bb47f74b29e267babdbcd2c47d5292aa8 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 07:53:25 -1000
Subject: [PATCH 1704/2753] fs/pipe: fix pipe buffer index use in FUSE

This was another case that Rasmus pointed out where the direct access to
the pipe head and tail pointers broke on 32-bit configurations due to
the type changes.

As with the pipe FIONREAD case, fix it by using the appropriate helper
functions that deal with the right pipe index sizing.

Reported-by: Rasmus Villemoes <ravi@prevas.dk>
Link: https://lore.kernel.org/all/878qpi5wz4.fsf@prevas.dk/
Fixes: 3d252160b818 ("fs/pipe: Read pipe->{head,tail} atomically outside pipe->mutex")Cc: Oleg >
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Cc: Swapnil Sapkal <swapnil.sapkal@amd.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 fs/fuse/dev.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 2b2d1b7555444..3c9caafca9e29 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -2107,7 +2107,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 				     struct file *out, loff_t *ppos,
 				     size_t len, unsigned int flags)
 {
-	unsigned int head, tail, mask, count;
+	unsigned int head, tail, count;
 	unsigned nbuf;
 	unsigned idx;
 	struct pipe_buffer *bufs;
@@ -2124,8 +2124,7 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	head = pipe->head;
 	tail = pipe->tail;
-	mask = pipe->ring_size - 1;
-	count = head - tail;
+	count = pipe_occupancy(head, tail);
 
 	bufs = kvmalloc_array(count, sizeof(struct pipe_buffer), GFP_KERNEL);
 	if (!bufs) {
@@ -2135,8 +2134,8 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 
 	nbuf = 0;
 	rem = 0;
-	for (idx = tail; idx != head && rem < len; idx++)
-		rem += pipe->bufs[idx & mask].len;
+	for (idx = tail; !pipe_empty(head, idx) && rem < len; idx++)
+		rem += pipe_buf(pipe, idx)->len;
 
 	ret = -EINVAL;
 	if (rem < len)
@@ -2147,10 +2146,10 @@ static ssize_t fuse_dev_splice_write(struct pipe_inode_info *pipe,
 		struct pipe_buffer *ibuf;
 		struct pipe_buffer *obuf;
 
-		if (WARN_ON(nbuf >= count || tail == head))
+		if (WARN_ON(nbuf >= count || pipe_empty(head, tail)))
 			goto out_free;
 
-		ibuf = &pipe->bufs[tail & mask];
+		ibuf = pipe_buf(pipe, tail);
 		obuf = &bufs[nbuf];
 
 		if (rem >= ibuf->len) {

From 6933c1067fe6df8ddb34dd68bdb2aa172cbd08c8 Mon Sep 17 00:00:00 2001
From: Alban Kurti <kurti@invicto.ai>
Date: Thu, 6 Feb 2025 21:07:54 +0000
Subject: [PATCH 1705/2753] rust: init: add missing newline to pr_info! calls

Several pr_info! calls in rust/kernel/init.rs (both in code examples
and macro documentation) were missing a newline, causing logs to
run together. This commit updates these calls to include a trailing
newline, improving readability and consistency with the C side.

Fixes: 6841d45a3030 ("rust: init: add `stack_pin_init!` macro")
Fixes: 7f8977a7fe6d ("rust: init: add `{pin_}chain` functions to `{Pin}Init<T, E>`")
Fixes: d0fdc3961270 ("rust: init: add `PinnedDrop` trait and macros")
Fixes: 4af84c6a85c6 ("rust: init: update expanded macro explanation")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-3-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. Added
  one more Fixes tag (still same set of stable kernels). - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/init.rs        | 12 ++++++------
 rust/kernel/init/macros.rs |  6 +++---
 2 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/rust/kernel/init.rs b/rust/kernel/init.rs
index 8bbd5e3398fcb..e25d047f3c827 100644
--- a/rust/kernel/init.rs
+++ b/rust/kernel/init.rs
@@ -259,7 +259,7 @@ pub mod macros;
 ///     },
 /// }));
 /// let foo: Pin<&mut Foo> = foo;
-/// pr_info!("a: {}", &*foo.a.lock());
+/// pr_info!("a: {}\n", &*foo.a.lock());
 /// ```
 ///
 /// # Syntax
@@ -319,7 +319,7 @@ macro_rules! stack_pin_init {
 ///     }, GFP_KERNEL)?,
 /// }));
 /// let foo = foo.unwrap();
-/// pr_info!("a: {}", &*foo.a.lock());
+/// pr_info!("a: {}\n", &*foo.a.lock());
 /// ```
 ///
 /// ```rust,ignore
@@ -352,7 +352,7 @@ macro_rules! stack_pin_init {
 ///         x: 64,
 ///     }, GFP_KERNEL)?,
 /// }));
-/// pr_info!("a: {}", &*foo.a.lock());
+/// pr_info!("a: {}\n", &*foo.a.lock());
 /// # Ok::<_, AllocError>(())
 /// ```
 ///
@@ -882,7 +882,7 @@ pub unsafe trait PinInit<T: ?Sized, E = Infallible>: Sized {
     ///
     /// impl Foo {
     ///     fn setup(self: Pin<&mut Self>) {
-    ///         pr_info!("Setting up foo");
+    ///         pr_info!("Setting up foo\n");
     ///     }
     /// }
     ///
@@ -986,7 +986,7 @@ pub unsafe trait Init<T: ?Sized, E = Infallible>: PinInit<T, E> {
     ///
     /// impl Foo {
     ///     fn setup(&mut self) {
-    ///         pr_info!("Setting up foo");
+    ///         pr_info!("Setting up foo\n");
     ///     }
     /// }
     ///
@@ -1336,7 +1336,7 @@ impl<T> InPlaceWrite<T> for UniqueArc<MaybeUninit<T>> {
 /// #[pinned_drop]
 /// impl PinnedDrop for Foo {
 ///     fn drop(self: Pin<&mut Self>) {
-///         pr_info!("Foo is being dropped!");
+///         pr_info!("Foo is being dropped!\n");
 ///     }
 /// }
 /// ```
diff --git a/rust/kernel/init/macros.rs b/rust/kernel/init/macros.rs
index 1fd146a832416..b7213962a6a5a 100644
--- a/rust/kernel/init/macros.rs
+++ b/rust/kernel/init/macros.rs
@@ -45,7 +45,7 @@
 //! #[pinned_drop]
 //! impl PinnedDrop for Foo {
 //!     fn drop(self: Pin<&mut Self>) {
-//!         pr_info!("{self:p} is getting dropped.");
+//!         pr_info!("{self:p} is getting dropped.\n");
 //!     }
 //! }
 //!
@@ -412,7 +412,7 @@
 //! #[pinned_drop]
 //! impl PinnedDrop for Foo {
 //!     fn drop(self: Pin<&mut Self>) {
-//!         pr_info!("{self:p} is getting dropped.");
+//!         pr_info!("{self:p} is getting dropped.\n");
 //!     }
 //! }
 //! ```
@@ -423,7 +423,7 @@
 //! // `unsafe`, full path and the token parameter are added, everything else stays the same.
 //! unsafe impl ::kernel::init::PinnedDrop for Foo {
 //!     fn drop(self: Pin<&mut Self>, _: ::kernel::init::__internal::OnlyCallFromDrop) {
-//!         pr_info!("{self:p} is getting dropped.");
+//!         pr_info!("{self:p} is getting dropped.\n");
 //!     }
 //! }
 //! ```

From 50c3e77eb3712a039760345999709ee0fad83447 Mon Sep 17 00:00:00 2001
From: Alban Kurti <kurti@invicto.ai>
Date: Thu, 6 Feb 2025 21:07:55 +0000
Subject: [PATCH 1706/2753] rust: sync: add missing newline in locked_by log
 example

The pr_info! example in rust/kernel/sync/locked_by.rs was missing
a newline. This patch appends the missing newline to ensure
that log messages for locked resources display correctly.

Fixes: 7b1f55e3a984 ("rust: sync: introduce `LockedBy`")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-4-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/sync/locked_by.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/sync/locked_by.rs b/rust/kernel/sync/locked_by.rs
index a7b244675c2b9..61f100a45b350 100644
--- a/rust/kernel/sync/locked_by.rs
+++ b/rust/kernel/sync/locked_by.rs
@@ -55,7 +55,7 @@ use core::{cell::UnsafeCell, mem::size_of, ptr};
 /// fn print_bytes_used(dir: &Directory, file: &File) {
 ///     let guard = dir.inner.lock();
 ///     let inner_file = file.inner.access(&guard);
-///     pr_info!("{} {}", guard.bytes_used, inner_file.bytes_used);
+///     pr_info!("{} {}\n", guard.bytes_used, inner_file.bytes_used);
 /// }
 ///
 /// /// Increments `bytes_used` for both the directory and file.

From 0ea4c3906416cefd6ae7ae5e93af9f2ef1b8c39b Mon Sep 17 00:00:00 2001
From: Alban Kurti <kurti@invicto.ai>
Date: Thu, 6 Feb 2025 21:07:56 +0000
Subject: [PATCH 1707/2753] rust: workqueue: add missing newline to pr_info!
 examples

The documentation examples in rust/kernel/workqueue.rs use pr_info!
calls that lack a trailing newline. To maintain consistency with
kernel logging practices, this patch adds the newline to all
affected examples.

Fixes: 15b286d1fd05 ("rust: workqueue: add examples")
Reported-by: Miguel Ojeda <ojeda@kernel.org>
Link: https://github.com/Rust-for-Linux/linux/issues/1139
Signed-off-by: Alban Kurti <kurti@invicto.ai>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250206-printing_fix-v3-5-a85273b501ae@invicto.ai
[ Replaced Closes with Link since it fixes part of the issue. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/workqueue.rs | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs
index 0cd100d2aefb4..b7be224cdf4bb 100644
--- a/rust/kernel/workqueue.rs
+++ b/rust/kernel/workqueue.rs
@@ -60,7 +60,7 @@
 //!     type Pointer = Arc<MyStruct>;
 //!
 //!     fn run(this: Arc<MyStruct>) {
-//!         pr_info!("The value is: {}", this.value);
+//!         pr_info!("The value is: {}\n", this.value);
 //!     }
 //! }
 //!
@@ -108,7 +108,7 @@
 //!     type Pointer = Arc<MyStruct>;
 //!
 //!     fn run(this: Arc<MyStruct>) {
-//!         pr_info!("The value is: {}", this.value_1);
+//!         pr_info!("The value is: {}\n", this.value_1);
 //!     }
 //! }
 //!
@@ -116,7 +116,7 @@
 //!     type Pointer = Arc<MyStruct>;
 //!
 //!     fn run(this: Arc<MyStruct>) {
-//!         pr_info!("The second value is: {}", this.value_2);
+//!         pr_info!("The second value is: {}\n", this.value_2);
 //!     }
 //! }
 //!

From c2315ebb0588f58a256d8411ac076e7350d830b2 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:33 +0000
Subject: [PATCH 1708/2753] net: tun: Enable XDP metadata support

Enable the support for the bpf_xdp_adjust_meta helper function for XDP
buffers initialized by the tun driver. This allows to reserve a metadata
area that is useful to pass any information from one XDP program to
another one, for example when using tail-calls.

Whether this helper function can be used in an XDP program depends on
how the xdp_buff was initialized. Most net drivers initialize the
xdp_buff in a way, that allows bpf_xdp_adjust_meta to be used. In case
of the tun driver, this is currently not the case.

There are two code paths in the tun driver that lead to a
bpf_prog_run_xdp and where metadata support should be enabled:

1. tun_build_skb, which is called by tun_get_user and is used when
   writing packets from userspace into the device. In this case, the
   xdp_buff created in tun_build_skb has no support for
   bpf_xdp_adjust_meta and calls of that helper function result in
   ENOTSUPP.

   For this code path, it's sufficient to set the meta_valid argument of
   the xdp_prepare_buff call. The reserved headroom is large enough
   already.

2. tun_xdp_one, which is called by tun_sendmsg which again is called by
   other drivers (e.g. vhost_net). When the TUN_MSG_PTR mode is used,
   another driver may pass a batch of xdp_buffs to the tun driver. In
   this case, that other driver is the one initializing the xdp_buff.

   See commit 043d222f93ab ("tuntap: accept an array of XDP buffs
   through sendmsg()") for details.

   For now, the vhost_net driver is the only one using TUN_MSG_PTR and
   it already initializes the xdp_buffs with metadata support and
   sufficient headroom. But the tun driver disables it again, so the
   xdp_set_data_meta_invalid call has to be removed.

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250305213438.3863922-2-marcus.wichelmann@hetzner-cloud.de
---
 drivers/net/tun.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d8f4d3e996a7a..cd463833a0add 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1644,7 +1644,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 		u32 act;
 
 		xdp_init_buff(&xdp, buflen, &tfile->xdp_rxq);
-		xdp_prepare_buff(&xdp, buf, pad, len, false);
+		xdp_prepare_buff(&xdp, buf, pad, len, true);
 
 		act = bpf_prog_run_xdp(xdp_prog, &xdp);
 		if (act == XDP_REDIRECT || act == XDP_TX) {
@@ -2368,7 +2368,6 @@ static int tun_xdp_one(struct tun_struct *tun,
 		}
 
 		xdp_init_buff(xdp, buflen, &tfile->xdp_rxq);
-		xdp_set_data_meta_invalid(xdp);
 
 		act = bpf_prog_run_xdp(xdp_prog, xdp);
 		ret = tun_xdp_act(tun, xdp_prog, xdp, act);

From 0ca23a4d64ce6db0ec1e1f66559c115eb100e426 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:34 +0000
Subject: [PATCH 1709/2753] net: tun: Enable transfer of XDP metadata to skb

When the XDP metadata area was used, it is expected that the same
metadata can also be accessed from TC, as can be read in the description
of the bpf_xdp_adjust_meta helper function. In the tun driver, this was
not yet implemented.

To make this work, the skb that is being built on XDP_PASS should know
of the current size of the metadata area. This is ensured by adding
calls to skb_metadata_set. For the tun_xdp_one code path, an additional
check is necessary to handle the case where the externally initialized
xdp_buff has no metadata support (xdp->data_meta == xdp->data + 1).

More information about this feature can be found in the commit message
of commit de8f3a83b0a0 ("bpf: add meta pointer for direct access").

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250305213438.3863922-3-marcus.wichelmann@hetzner-cloud.de
---
 drivers/net/tun.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index cd463833a0add..f75f912a0225f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1535,7 +1535,8 @@ static bool tun_can_build_skb(struct tun_struct *tun, struct tun_file *tfile,
 
 static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
 				       struct page_frag *alloc_frag, char *buf,
-				       int buflen, int len, int pad)
+				       int buflen, int len, int pad,
+				       int metasize)
 {
 	struct sk_buff *skb = build_skb(buf, buflen);
 
@@ -1544,6 +1545,8 @@ static struct sk_buff *__tun_build_skb(struct tun_file *tfile,
 
 	skb_reserve(skb, pad);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb_set_owner_w(skb, tfile->socket.sk);
 
 	get_page(alloc_frag->page);
@@ -1603,6 +1606,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	char *buf;
 	size_t copied;
 	int pad = TUN_RX_PAD;
+	int metasize = 0;
 	int err = 0;
 
 	rcu_read_lock();
@@ -1630,7 +1634,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 	if (hdr->gso_type || !xdp_prog) {
 		*skb_xdp = 1;
 		return __tun_build_skb(tfile, alloc_frag, buf, buflen, len,
-				       pad);
+				       pad, metasize);
 	}
 
 	*skb_xdp = 0;
@@ -1665,12 +1669,18 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun,
 
 		pad = xdp.data - xdp.data_hard_start;
 		len = xdp.data_end - xdp.data;
+
+		/* It is known that the xdp_buff was prepared with metadata
+		 * support, so the metasize will never be negative.
+		 */
+		metasize = xdp.data - xdp.data_meta;
 	}
 	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock();
 	local_bh_enable();
 
-	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad);
+	return __tun_build_skb(tfile, alloc_frag, buf, buflen, len, pad,
+			       metasize);
 
 out:
 	bpf_net_ctx_clear(bpf_net_ctx);
@@ -2353,6 +2363,7 @@ static int tun_xdp_one(struct tun_struct *tun,
 	struct sk_buff_head *queue;
 	u32 rxhash = 0, act;
 	int buflen = hdr->buflen;
+	int metasize = 0;
 	int ret = 0;
 	bool skb_xdp = false;
 	struct page *page;
@@ -2407,6 +2418,14 @@ static int tun_xdp_one(struct tun_struct *tun,
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
 
+	/* The externally provided xdp_buff may have no metadata support, which
+	 * is marked by xdp->data_meta being xdp->data + 1. This will lead to a
+	 * metasize of -1 and is the reason why the condition checks for > 0.
+	 */
+	metasize = xdp->data - xdp->data_meta;
+	if (metasize > 0)
+		skb_metadata_set(skb, metasize);
+
 	if (tun_vnet_hdr_to_skb(tun->flags, skb, gso)) {
 		atomic_long_inc(&tun->rx_frame_errors);
 		kfree_skb(skb);

From d5ca409c86d35ebe60fad08ed554797abd8e53c0 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:35 +0000
Subject: [PATCH 1710/2753] selftests/bpf: Move open_tuntap to network helpers

To test the XDP metadata functionality of the tun driver, it's necessary
to create a new tap device first. A helper function for this already
exists in lwt_helpers.h. Move it to the common network helpers header,
so it can be reused in other tests.

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250305213438.3863922-4-marcus.wichelmann@hetzner-cloud.de
---
 tools/testing/selftests/bpf/network_helpers.c | 28 ++++++++++++++++++
 tools/testing/selftests/bpf/network_helpers.h |  3 ++
 .../selftests/bpf/prog_tests/lwt_helpers.h    | 29 -------------------
 3 files changed, 31 insertions(+), 29 deletions(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 80844a5fb1fee..fcee2c4a637a5 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -548,6 +548,34 @@ void close_netns(struct nstoken *token)
 	free(token);
 }
 
+int open_tuntap(const char *dev_name, bool need_mac)
+{
+	int err = 0;
+	struct ifreq ifr;
+	int fd = open("/dev/net/tun", O_RDWR);
+
+	if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)"))
+		return -1;
+
+	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
+	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
+	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
+
+	err = ioctl(fd, TUNSETIFF, &ifr);
+	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
+		close(fd);
+		return -1;
+	}
+
+	err = fcntl(fd, F_SETFL, O_NONBLOCK);
+	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
 int get_socket_local_port(int sock_fd)
 {
 	struct sockaddr_storage addr;
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index ebec8a8d6f81e..9235976d0c504 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -8,6 +8,7 @@
 typedef __u16 __sum16;
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
+#include <linux/if_tun.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/ethtool.h>
@@ -85,6 +86,8 @@ int get_socket_local_port(int sock_fd);
 int get_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param);
 int set_hw_ring_size(char *ifname, struct ethtool_ringparam *ring_param);
 
+int open_tuntap(const char *dev_name, bool need_mac);
+
 struct nstoken;
 /**
  * open_netns() - Switch to specified network namespace by name.
diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
index fb1eb8c673617..ccec0fcdabc11 100644
--- a/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
+++ b/tools/testing/selftests/bpf/prog_tests/lwt_helpers.h
@@ -5,7 +5,6 @@
 
 #include <time.h>
 #include <net/if.h>
-#include <linux/if_tun.h>
 #include <linux/icmp.h>
 
 #include "test_progs.h"
@@ -37,34 +36,6 @@ static inline int netns_delete(void)
 	return system("ip netns del " NETNS ">/dev/null 2>&1");
 }
 
-static int open_tuntap(const char *dev_name, bool need_mac)
-{
-	int err = 0;
-	struct ifreq ifr;
-	int fd = open("/dev/net/tun", O_RDWR);
-
-	if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)"))
-		return -1;
-
-	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);
-	strncpy(ifr.ifr_name, dev_name, IFNAMSIZ - 1);
-	ifr.ifr_name[IFNAMSIZ - 1] = '\0';
-
-	err = ioctl(fd, TUNSETIFF, &ifr);
-	if (!ASSERT_OK(err, "ioctl(TUNSETIFF)")) {
-		close(fd);
-		return -1;
-	}
-
-	err = fcntl(fd, F_SETFL, O_NONBLOCK);
-	if (!ASSERT_OK(err, "fcntl(O_NONBLOCK)")) {
-		close(fd);
-		return -1;
-	}
-
-	return fd;
-}
-
 #define ICMP_PAYLOAD_SIZE     100
 
 /* Match an ICMP packet with payload len ICMP_PAYLOAD_SIZE */

From b46aa22b66d3283d2b312269dd5f17e6637f02a4 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:36 +0000
Subject: [PATCH 1711/2753] selftests/bpf: Refactor xdp_context_functional test
 and bpf program

The existing XDP metadata test works by creating a veth pair and
attaching XDP & TC programs that drop the packet when the condition of
the test isn't fulfilled. The test then pings through the veth pair and
succeeds when the ping comes through.

While this test works great for a veth pair, it is hard to replicate for
tap devices to test the XDP metadata support of them. A similar test for
the tun driver would either involve logic to reply to the ping request,
or would have to capture the packet to check if it was dropped or not.

To make the testing of other drivers easier while still maximizing code
reuse, this commit refactors the existing xdp_context_functional test to
use a test_result map. Instead of conditionally passing or dropping the
packet, the TC program is changed to copy the received metadata into the
value of that single-entry array map. Tests can then verify that the map
value matches the expectation.

This testing logic is easy to adapt to other network drivers as the only
remaining requirement is that there is some way to send a custom
Ethernet packet through it that triggers the XDP & TC programs.

The Ethernet header of that custom packet is all-zero, because it is not
required to be valid for the test to work. The zero ethertype also helps
to filter out packets that are not related to the test and would
otherwise interfere with it.

The payload of the Ethernet packet is used as the test data that is
expected to be passed as metadata from the XDP to the TC program and
written to the map. It has a fixed size of 32 bytes which is a
reasonable size that should be supported by both drivers. Additional
packet headers are not necessary for the test and were therefore skipped
to keep the testing code short.

This new testing methodology no longer requires the veth interfaces to
have IP addresses assigned, therefore these were removed.

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250305213438.3863922-5-marcus.wichelmann@hetzner-cloud.de
---
 .../bpf/prog_tests/xdp_context_test_run.c     | 79 +++++++++++++++++--
 .../selftests/bpf/progs/test_xdp_meta.c       | 53 +++++++++----
 2 files changed, 110 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index 937da9b7532a5..78ca01edb0500 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -4,13 +4,19 @@
 #include "test_xdp_context_test_run.skel.h"
 #include "test_xdp_meta.skel.h"
 
-#define TX_ADDR "10.0.0.1"
-#define RX_ADDR "10.0.0.2"
 #define RX_NAME "veth0"
 #define TX_NAME "veth1"
 #define TX_NETNS "xdp_context_tx"
 #define RX_NETNS "xdp_context_rx"
 
+#define TEST_PAYLOAD_LEN 32
+static const __u8 test_payload[TEST_PAYLOAD_LEN] = {
+	0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08,
+	0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
+	0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
+	0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38,
+};
+
 void test_xdp_context_error(int prog_fd, struct bpf_test_run_opts opts,
 			    __u32 data_meta, __u32 data, __u32 data_end,
 			    __u32 ingress_ifindex, __u32 rx_queue_index,
@@ -112,7 +118,59 @@ void test_xdp_context_test_run(void)
 	test_xdp_context_test_run__destroy(skel);
 }
 
-void test_xdp_context_functional(void)
+static int send_test_packet(int ifindex)
+{
+	int n, sock = -1;
+	__u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+
+	/* The ethernet header is not relevant for this test and doesn't need to
+	 * be meaningful.
+	 */
+	struct ethhdr eth = { 0 };
+
+	memcpy(packet, &eth, sizeof(eth));
+	memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN);
+
+	sock = socket(AF_PACKET, SOCK_RAW, IPPROTO_RAW);
+	if (!ASSERT_GE(sock, 0, "socket"))
+		goto err;
+
+	struct sockaddr_ll saddr = {
+		.sll_family = PF_PACKET,
+		.sll_ifindex = ifindex,
+		.sll_halen = ETH_ALEN
+	};
+	n = sendto(sock, packet, sizeof(packet), 0, (struct sockaddr *)&saddr,
+		   sizeof(saddr));
+	if (!ASSERT_EQ(n, sizeof(packet), "sendto"))
+		goto err;
+
+	close(sock);
+	return 0;
+
+err:
+	if (sock >= 0)
+		close(sock);
+	return -1;
+}
+
+static void assert_test_result(struct test_xdp_meta *skel)
+{
+	int err;
+	__u32 map_key = 0;
+	__u8 map_value[TEST_PAYLOAD_LEN];
+
+	err = bpf_map__lookup_elem(skel->maps.test_result, &map_key,
+				   sizeof(map_key), &map_value,
+				   TEST_PAYLOAD_LEN, BPF_ANY);
+	if (!ASSERT_OK(err, "lookup test_result"))
+		return;
+
+	ASSERT_MEMEQ(&map_value, &test_payload, TEST_PAYLOAD_LEN,
+		     "test_result map contains test payload");
+}
+
+void test_xdp_context_veth(void)
 {
 	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
 	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
@@ -120,7 +178,7 @@ void test_xdp_context_functional(void)
 	struct bpf_program *tc_prog, *xdp_prog;
 	struct test_xdp_meta *skel = NULL;
 	struct nstoken *nstoken = NULL;
-	int rx_ifindex;
+	int rx_ifindex, tx_ifindex;
 	int ret;
 
 	tx_ns = netns_new(TX_NETNS, false);
@@ -138,7 +196,6 @@ void test_xdp_context_functional(void)
 	if (!ASSERT_OK_PTR(nstoken, "setns rx_ns"))
 		goto close;
 
-	SYS(close, "ip addr add " RX_ADDR "/24 dev " RX_NAME);
 	SYS(close, "ip link set dev " RX_NAME " up");
 
 	skel = test_xdp_meta__open_and_load();
@@ -179,9 +236,17 @@ void test_xdp_context_functional(void)
 	if (!ASSERT_OK_PTR(nstoken, "setns tx_ns"))
 		goto close;
 
-	SYS(close, "ip addr add " TX_ADDR "/24 dev " TX_NAME);
 	SYS(close, "ip link set dev " TX_NAME " up");
-	ASSERT_OK(SYS_NOFAIL("ping -c 1 " RX_ADDR), "ping");
+
+	tx_ifindex = if_nametoindex(TX_NAME);
+	if (!ASSERT_GE(tx_ifindex, 0, "if_nametoindex tx"))
+		goto close;
+
+	ret = send_test_packet(tx_ifindex);
+	if (!ASSERT_OK(ret, "send_test_packet"))
+		goto close;
+
+	assert_test_result(skel);
 
 close:
 	close_netns(nstoken);
diff --git a/tools/testing/selftests/bpf/progs/test_xdp_meta.c b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
index fe2d71ae0e717..fcf6ca14f2ea2 100644
--- a/tools/testing/selftests/bpf/progs/test_xdp_meta.c
+++ b/tools/testing/selftests/bpf/progs/test_xdp_meta.c
@@ -4,37 +4,50 @@
 
 #include <bpf/bpf_helpers.h>
 
-#define __round_mask(x, y) ((__typeof__(x))((y) - 1))
-#define round_up(x, y) ((((x) - 1) | __round_mask(x, y)) + 1)
+#define META_SIZE 32
+
 #define ctx_ptr(ctx, mem) (void *)(unsigned long)ctx->mem
 
+/* Demonstrates how metadata can be passed from an XDP program to a TC program
+ * using bpf_xdp_adjust_meta.
+ * For the sake of testing the metadata support in drivers, the XDP program uses
+ * a fixed-size payload after the Ethernet header as metadata. The TC program
+ * copies the metadata it receives into a map so it can be checked from
+ * userspace.
+ */
+
+struct {
+	__uint(type, BPF_MAP_TYPE_ARRAY);
+	__uint(max_entries, 1);
+	__type(key, __u32);
+	__uint(value_size, META_SIZE);
+} test_result SEC(".maps");
+
 SEC("tc")
 int ing_cls(struct __sk_buff *ctx)
 {
-	__u8 *data, *data_meta, *data_end;
-	__u32 diff = 0;
+	__u8 *data, *data_meta;
+	__u32 key = 0;
 
 	data_meta = ctx_ptr(ctx, data_meta);
-	data_end  = ctx_ptr(ctx, data_end);
 	data      = ctx_ptr(ctx, data);
 
-	if (data + ETH_ALEN > data_end ||
-	    data_meta + round_up(ETH_ALEN, 4) > data)
+	if (data_meta + META_SIZE > data)
 		return TC_ACT_SHOT;
 
-	diff |= ((__u32 *)data_meta)[0] ^ ((__u32 *)data)[0];
-	diff |= ((__u16 *)data_meta)[2] ^ ((__u16 *)data)[2];
+	bpf_map_update_elem(&test_result, &key, data_meta, BPF_ANY);
 
-	return diff ? TC_ACT_SHOT : TC_ACT_OK;
+	return TC_ACT_SHOT;
 }
 
 SEC("xdp")
 int ing_xdp(struct xdp_md *ctx)
 {
-	__u8 *data, *data_meta, *data_end;
+	__u8 *data, *data_meta, *data_end, *payload;
+	struct ethhdr *eth;
 	int ret;
 
-	ret = bpf_xdp_adjust_meta(ctx, -round_up(ETH_ALEN, 4));
+	ret = bpf_xdp_adjust_meta(ctx, -META_SIZE);
 	if (ret < 0)
 		return XDP_DROP;
 
@@ -42,11 +55,21 @@ int ing_xdp(struct xdp_md *ctx)
 	data_end  = ctx_ptr(ctx, data_end);
 	data      = ctx_ptr(ctx, data);
 
-	if (data + ETH_ALEN > data_end ||
-	    data_meta + round_up(ETH_ALEN, 4) > data)
+	eth = (struct ethhdr *)data;
+	payload = data + sizeof(struct ethhdr);
+
+	if (payload + META_SIZE > data_end ||
+	    data_meta + META_SIZE > data)
+		return XDP_DROP;
+
+	/* The Linux networking stack may send other packets on the test
+	 * interface that interfere with the test. Just drop them.
+	 * The test packets can be recognized by their ethertype of zero.
+	 */
+	if (eth->h_proto != 0)
 		return XDP_DROP;
 
-	__builtin_memcpy(data_meta, data, ETH_ALEN);
+	__builtin_memcpy(data_meta, payload, META_SIZE);
 	return XDP_PASS;
 }
 

From 73eeecc3cdfeb098f8859269b608589b8a919686 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:37 +0000
Subject: [PATCH 1712/2753] selftests/bpf: Add test for XDP metadata support in
 tun driver

Add a selftest that creates a tap device, attaches XDP and TC programs,
writes a packet with a test payload into the tap device and checks the
test result. This test ensures that the XDP metadata support in the tun
driver is enabled and that the metadata size is correctly passed to the
skb.

See the previous commit ("selftests/bpf: refactor xdp_context_functional
test and bpf program") for details about the test design.

The test runs in its own network namespace. This provides some extra
safety against conflicting interface names.

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250305213438.3863922-6-marcus.wichelmann@hetzner-cloud.de
---
 .../bpf/prog_tests/xdp_context_test_run.c     | 66 +++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
index 78ca01edb0500..b9d9f0a502cea 100644
--- a/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_context_test_run.c
@@ -8,6 +8,8 @@
 #define TX_NAME "veth1"
 #define TX_NETNS "xdp_context_tx"
 #define RX_NETNS "xdp_context_rx"
+#define TAP_NAME "tap0"
+#define TAP_NETNS "xdp_context_tuntap"
 
 #define TEST_PAYLOAD_LEN 32
 static const __u8 test_payload[TEST_PAYLOAD_LEN] = {
@@ -255,3 +257,67 @@ void test_xdp_context_veth(void)
 	netns_free(tx_ns);
 }
 
+void test_xdp_context_tuntap(void)
+{
+	LIBBPF_OPTS(bpf_tc_hook, tc_hook, .attach_point = BPF_TC_INGRESS);
+	LIBBPF_OPTS(bpf_tc_opts, tc_opts, .handle = 1, .priority = 1);
+	struct netns_obj *ns = NULL;
+	struct test_xdp_meta *skel = NULL;
+	__u8 packet[sizeof(struct ethhdr) + TEST_PAYLOAD_LEN];
+	int tap_fd = -1;
+	int tap_ifindex;
+	int ret;
+
+	ns = netns_new(TAP_NETNS, true);
+	if (!ASSERT_OK_PTR(ns, "create and open ns"))
+		return;
+
+	tap_fd = open_tuntap(TAP_NAME, true);
+	if (!ASSERT_GE(tap_fd, 0, "open_tuntap"))
+		goto close;
+
+	SYS(close, "ip link set dev " TAP_NAME " up");
+
+	skel = test_xdp_meta__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "open and load skeleton"))
+		goto close;
+
+	tap_ifindex = if_nametoindex(TAP_NAME);
+	if (!ASSERT_GE(tap_ifindex, 0, "if_nametoindex"))
+		goto close;
+
+	tc_hook.ifindex = tap_ifindex;
+	ret = bpf_tc_hook_create(&tc_hook);
+	if (!ASSERT_OK(ret, "bpf_tc_hook_create"))
+		goto close;
+
+	tc_opts.prog_fd = bpf_program__fd(skel->progs.ing_cls);
+	ret = bpf_tc_attach(&tc_hook, &tc_opts);
+	if (!ASSERT_OK(ret, "bpf_tc_attach"))
+		goto close;
+
+	ret = bpf_xdp_attach(tap_ifindex, bpf_program__fd(skel->progs.ing_xdp),
+			     0, NULL);
+	if (!ASSERT_GE(ret, 0, "bpf_xdp_attach"))
+		goto close;
+
+	/* The ethernet header is not relevant for this test and doesn't need to
+	 * be meaningful.
+	 */
+	struct ethhdr eth = { 0 };
+
+	memcpy(packet, &eth, sizeof(eth));
+	memcpy(packet + sizeof(eth), test_payload, TEST_PAYLOAD_LEN);
+
+	ret = write(tap_fd, packet, sizeof(packet));
+	if (!ASSERT_EQ(ret, sizeof(packet), "write packet"))
+		goto close;
+
+	assert_test_result(skel);
+
+close:
+	if (tap_fd >= 0)
+		close(tap_fd);
+	test_xdp_meta__destroy(skel);
+	netns_free(ns);
+}

From 49306d5bfc6a86e3a75f8d584cda65164fb3ed71 Mon Sep 17 00:00:00 2001
From: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Date: Wed, 5 Mar 2025 21:34:38 +0000
Subject: [PATCH 1713/2753] selftests/bpf: Fix file descriptor assertion in
 open_tuntap helper

The open_tuntap helper function uses open() to get a file descriptor for
/dev/net/tun.

The open(2) manpage writes this about its return value:

  On success, open(), openat(), and creat() return the new file
  descriptor (a nonnegative integer).  On error, -1 is returned and
  errno is set to indicate the error.

This means that the fd > 0 assertion in the open_tuntap helper is
incorrect and should rather check for fd >= 0.

When running the BPF selftests locally, this incorrect assertion was not
an issue, but the BPF kernel-patches CI failed because of this:

  open_tuntap:FAIL:open(/dev/net/tun) unexpected open(/dev/net/tun):
  actual 0 <= expected 0

Signed-off-by: Marcus Wichelmann <marcus.wichelmann@hetzner-cloud.de>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250305213438.3863922-7-marcus.wichelmann@hetzner-cloud.de
---
 tools/testing/selftests/bpf/network_helpers.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index fcee2c4a637a5..29541d486c5ef 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -554,7 +554,7 @@ int open_tuntap(const char *dev_name, bool need_mac)
 	struct ifreq ifr;
 	int fd = open("/dev/net/tun", O_RDWR);
 
-	if (!ASSERT_GT(fd, 0, "open(/dev/net/tun)"))
+	if (!ASSERT_GE(fd, 0, "open(/dev/net/tun)"))
 		return -1;
 
 	ifr.ifr_flags = IFF_NO_PI | (need_mac ? IFF_TAP : IFF_TUN);

From 169b2262205836a5d1213ff44dca2962276bece1 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 5 Mar 2025 12:55:34 +0200
Subject: [PATCH 1714/2753] ieee802154: ca8210: Use proper setters and getters
 for bitwise types

Sparse complains that the driver doesn't respect the bitwise types:

drivers/net/ieee802154/ca8210.c:1796:27: warning: incorrect type in assignment (different base types)
drivers/net/ieee802154/ca8210.c:1796:27:    expected restricted __le16 [addressable] [assigned] [usertype] pan_id
drivers/net/ieee802154/ca8210.c:1796:27:    got unsigned short [usertype]
drivers/net/ieee802154/ca8210.c:1801:25: warning: incorrect type in assignment (different base types)
drivers/net/ieee802154/ca8210.c:1801:25:    expected restricted __le16 [addressable] [assigned] [usertype] pan_id
drivers/net/ieee802154/ca8210.c:1801:25:    got unsigned short [usertype]
drivers/net/ieee802154/ca8210.c:1928:28: warning: incorrect type in argument 3 (different base types)
drivers/net/ieee802154/ca8210.c:1928:28:    expected unsigned short [usertype] dst_pan_id
drivers/net/ieee802154/ca8210.c:1928:28:    got restricted __le16 [addressable] [usertype] pan_id

Use proper setters and getters for bitwise types.

Note, in accordance with [1] the protocol is little endian.

Link: https://www.cascoda.com/wp-content/uploads/2018/11/CA-8210_datasheet_0418.pdf [1]
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/20250305105656.2133487-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/ca8210.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 753215ebc67c7..a036910f60828 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -1446,8 +1446,7 @@ static u8 mcps_data_request(
 	command.pdata.data_req.src_addr_mode = src_addr_mode;
 	command.pdata.data_req.dst.mode = dst_address_mode;
 	if (dst_address_mode != MAC_MODE_NO_ADDR) {
-		command.pdata.data_req.dst.pan_id[0] = LS_BYTE(dst_pan_id);
-		command.pdata.data_req.dst.pan_id[1] = MS_BYTE(dst_pan_id);
+		put_unaligned_le16(dst_pan_id, command.pdata.data_req.dst.pan_id);
 		if (dst_address_mode == MAC_MODE_SHORT_ADDR) {
 			command.pdata.data_req.dst.address[0] = LS_BYTE(
 				dst_addr->short_address
@@ -1795,12 +1794,12 @@ static int ca8210_skb_rx(
 	}
 	hdr.source.mode = data_ind[0];
 	dev_dbg(&priv->spi->dev, "srcAddrMode: %#03x\n", hdr.source.mode);
-	hdr.source.pan_id = *(u16 *)&data_ind[1];
+	hdr.source.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[1]));
 	dev_dbg(&priv->spi->dev, "srcPanId: %#06x\n", hdr.source.pan_id);
 	memcpy(&hdr.source.extended_addr, &data_ind[3], 8);
 	hdr.dest.mode = data_ind[11];
 	dev_dbg(&priv->spi->dev, "dstAddrMode: %#03x\n", hdr.dest.mode);
-	hdr.dest.pan_id = *(u16 *)&data_ind[12];
+	hdr.dest.pan_id = cpu_to_le16(get_unaligned_le16(&data_ind[12]));
 	dev_dbg(&priv->spi->dev, "dstPanId: %#06x\n", hdr.dest.pan_id);
 	memcpy(&hdr.dest.extended_addr, &data_ind[14], 8);
 
@@ -1927,7 +1926,7 @@ static int ca8210_skb_tx(
 	status =  mcps_data_request(
 		header.source.mode,
 		header.dest.mode,
-		header.dest.pan_id,
+		le16_to_cpu(header.dest.pan_id),
 		(union macaddr *)&header.dest.extended_addr,
 		skb->len - mac_len,
 		&skb->data[mac_len],

From 0a3e89b06d36d55392829681f63ce0c74861901b Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 5 Mar 2025 12:55:35 +0200
Subject: [PATCH 1715/2753] ieee802154: ca8210: Get platform data via
 dev_get_platdata()

Access to platform data via dev_get_platdata() getter to make code cleaner.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/20250305105656.2133487-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/net/ieee802154/ca8210.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index a036910f60828..65f042c8734b5 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -627,7 +627,8 @@ static int ca8210_spi_transfer(
  */
 static void ca8210_reset_send(struct spi_device *spi, unsigned int ms)
 {
-	struct ca8210_platform_data *pdata = spi->dev.platform_data;
+	struct device *dev = &spi->dev;
+	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
 	struct ca8210_priv *priv = spi_get_drvdata(spi);
 	long status;
 
@@ -2736,9 +2737,10 @@ static int ca8210_config_extern_clk(
  */
 static int ca8210_register_ext_clock(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
+	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
 	struct device_node *np = spi->dev.of_node;
 	struct ca8210_priv *priv = spi_get_drvdata(spi);
-	struct ca8210_platform_data *pdata = spi->dev.platform_data;
 
 	if (!np)
 		return -EFAULT;
@@ -2784,8 +2786,9 @@ static void ca8210_unregister_ext_clock(struct spi_device *spi)
  */
 static int ca8210_reset_init(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
+	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
 	int ret;
-	struct ca8210_platform_data *pdata = spi->dev.platform_data;
 
 	pdata->gpio_reset = of_get_named_gpio(
 		spi->dev.of_node,
@@ -2813,8 +2816,9 @@ static int ca8210_reset_init(struct spi_device *spi)
  */
 static int ca8210_interrupt_init(struct spi_device *spi)
 {
+	struct device *dev = &spi->dev;
+	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
 	int ret;
-	struct ca8210_platform_data *pdata = spi->dev.platform_data;
 
 	pdata->gpio_irq = of_get_named_gpio(
 		spi->dev.of_node,

From 20629a48d50ad98cb9376dedeec1e98aff092ad9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 5 Mar 2025 12:55:36 +0200
Subject: [PATCH 1716/2753] ieee802154: ca8210: Switch to using gpiod API

This updates the driver to gpiod API, and removes yet another use of
of_get_named_gpio().

With this, invert the logic of the reset pin which is active-low
and add a quirk for the legacy and incorrect device tree descriptions.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Reviewed-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/20250305105656.2133487-4-andriy.shevchenko@linux.intel.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 drivers/gpio/gpiolib-of.c       |  9 ++++++
 drivers/net/ieee802154/ca8210.c | 57 +++++++++++----------------------
 2 files changed, 28 insertions(+), 38 deletions(-)

diff --git a/drivers/gpio/gpiolib-of.c b/drivers/gpio/gpiolib-of.c
index 2e537ee979f3e..44ba1e16ed0d8 100644
--- a/drivers/gpio/gpiolib-of.c
+++ b/drivers/gpio/gpiolib-of.c
@@ -203,6 +203,15 @@ static void of_gpio_try_fixup_polarity(const struct device_node *np,
 		 */
 		{ "qi,lb60",		"rb-gpios",	true },
 #endif
+#if IS_ENABLED(CONFIG_IEEE802154_CA8210)
+		/*
+		 * According to the datasheet, the NRST pin 27 is an active-low
+		 * signal. However, the device tree schema and admittedly
+		 * the out-of-tree implementations have been used for a long
+		 * time incorrectly by describing reset GPIO as active-high.
+		 */
+		{ "cascoda,ca8210",	"reset-gpio",	false },
+#endif
 #if IS_ENABLED(CONFIG_PCI_LANTIQ)
 		/*
 		 * According to the PCI specification, the RST# pin is an
diff --git a/drivers/net/ieee802154/ca8210.c b/drivers/net/ieee802154/ca8210.c
index 65f042c8734b5..ebc4f1b18e7bc 100644
--- a/drivers/net/ieee802154/ca8210.c
+++ b/drivers/net/ieee802154/ca8210.c
@@ -52,12 +52,10 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
-#include <linux/gpio.h>
 #include <linux/ieee802154.h>
 #include <linux/io.h>
 #include <linux/kfifo.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/poll.h>
@@ -350,8 +348,8 @@ struct work_priv_container {
  * @extclockenable: true if the external clock is to be enabled
  * @extclockfreq:   frequency of the external clock
  * @extclockgpio:   ca8210 output gpio of the external clock
- * @gpio_reset:     gpio number of ca8210 reset line
- * @gpio_irq:       gpio number of ca8210 interrupt line
+ * @reset_gpio:     ca8210 reset GPIO descriptor
+ * @irq_gpio:       ca8210 interrupt GPIO descriptor
  * @irq_id:         identifier for the ca8210 irq
  *
  */
@@ -359,8 +357,8 @@ struct ca8210_platform_data {
 	bool extclockenable;
 	unsigned int extclockfreq;
 	unsigned int extclockgpio;
-	int gpio_reset;
-	int gpio_irq;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *irq_gpio;
 	int irq_id;
 };
 
@@ -632,10 +630,10 @@ static void ca8210_reset_send(struct spi_device *spi, unsigned int ms)
 	struct ca8210_priv *priv = spi_get_drvdata(spi);
 	long status;
 
-	gpio_set_value(pdata->gpio_reset, 0);
+	gpiod_set_value(pdata->reset_gpio, 1);
 	reinit_completion(&priv->ca8210_is_awake);
 	msleep(ms);
-	gpio_set_value(pdata->gpio_reset, 1);
+	gpiod_set_value(pdata->reset_gpio, 0);
 	priv->promiscuous = false;
 
 	/* Wait until wakeup indication seen */
@@ -2788,24 +2786,14 @@ static int ca8210_reset_init(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
 	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
-	int ret;
-
-	pdata->gpio_reset = of_get_named_gpio(
-		spi->dev.of_node,
-		"reset-gpio",
-		0
-	);
 
-	ret = gpio_direction_output(pdata->gpio_reset, 1);
-	if (ret < 0) {
-		dev_crit(
-			&spi->dev,
-			"Reset GPIO %d did not set to output mode\n",
-			pdata->gpio_reset
-		);
+	pdata->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(pdata->reset_gpio)) {
+		dev_crit(dev, "Reset GPIO did not set to output mode\n");
+		return PTR_ERR(pdata->reset_gpio);
 	}
 
-	return ret;
+	return 0;
 }
 
 /**
@@ -2820,20 +2808,15 @@ static int ca8210_interrupt_init(struct spi_device *spi)
 	struct ca8210_platform_data *pdata = dev_get_platdata(dev);
 	int ret;
 
-	pdata->gpio_irq = of_get_named_gpio(
-		spi->dev.of_node,
-		"irq-gpio",
-		0
-	);
+	pdata->irq_gpio = devm_gpiod_get(dev, "irq", GPIOD_IN);
+	if (IS_ERR(pdata->irq_gpio)) {
+		dev_crit(dev, "Could not retrieve IRQ GPIO\n");
+		return PTR_ERR(pdata->irq_gpio);
+	}
 
-	pdata->irq_id = gpio_to_irq(pdata->gpio_irq);
+	pdata->irq_id = gpiod_to_irq(pdata->irq_gpio);
 	if (pdata->irq_id < 0) {
-		dev_crit(
-			&spi->dev,
-			"Could not get irq for gpio pin %d\n",
-			pdata->gpio_irq
-		);
-		gpio_free(pdata->gpio_irq);
+		dev_crit(dev, "Could not get irq for IRQ GPIO\n");
 		return pdata->irq_id;
 	}
 
@@ -2844,10 +2827,8 @@ static int ca8210_interrupt_init(struct spi_device *spi)
 		"ca8210-irq",
 		spi_get_drvdata(spi)
 	);
-	if (ret) {
+	if (ret)
 		dev_crit(&spi->dev, "request_irq %d failed\n", pdata->irq_id);
-		gpio_free(pdata->gpio_irq);
-	}
 
 	return ret;
 }

From a5d4d993fac4925410991eac3b427ea6b86e4872 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Wed, 5 Mar 2025 12:55:37 +0200
Subject: [PATCH 1717/2753] dt-bindings: ieee802154: ca8210: Update polarity of
 the reset pin

The code has been updated to follow what datasheet says about
the polarity of the reset pin, which is active-low. Update
the device tree bindings accordingly.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Link: https://lore.kernel.org/20250305105656.2133487-5-andriy.shevchenko@linux.intel.com
Signed-off-by: Stefan Schmidt <stefan@datenfreihafen.org>
---
 Documentation/devicetree/bindings/net/ieee802154/ca8210.txt | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt b/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
index a1046e636fa14..f1bd07a0097db 100644
--- a/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
+++ b/Documentation/devicetree/bindings/net/ieee802154/ca8210.txt
@@ -20,7 +20,7 @@ Example:
 		reg = <0>;
 		spi-max-frequency = <3000000>;
 		spi-cpol;
-		reset-gpio = <&gpio1 1 GPIO_ACTIVE_HIGH>;
+		reset-gpio = <&gpio1 1 GPIO_ACTIVE_LOW>;
 		irq-gpio = <&gpio1 2 GPIO_ACTIVE_HIGH>;
 		extclock-enable;
 		extclock-freq = 16000000;

From d4c22ec680c8db832ffc0b964c6008e65436cba8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:19 -0800
Subject: [PATCH 1718/2753] net: hold netdev instance lock during
 ndo_open/ndo_stop

For the drivers that use shaper API, switch to the mode where
core stack holds the netdev lock. This affects two drivers:

* iavf - already grabs netdev lock in ndo_open/ndo_stop, so mostly
         remove these
* netdevsim - switch to _locked APIs to avoid deadlock

iavf_close diff is a bit confusing, the existing call looks like this:
  iavf_close() {
    netdev_lock()
    ..
    netdev_unlock()
    wait_event_timeout(down_waitqueue)
  }

I change it to the following:
  netdev_lock()
  iavf_close() {
    ..
    netdev_unlock()
    wait_event_timeout(down_waitqueue)
    netdev_lock() // reusing this lock call
  }
  netdev_unlock()

Since I'm reusing existing netdev_lock call, so it looks like I only
add netdev_unlock.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c | 14 ++++++-------
 drivers/net/netdevsim/netdev.c              | 14 ++++++++-----
 include/linux/netdevice.h                   | 23 +++++++++++++++++++++
 net/core/dev.c                              | 12 +++++++++++
 net/core/dev.h                              |  6 ++++--
 5 files changed, 54 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 71f11f64b13d7..9f4d223dffcfb 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -4562,22 +4562,21 @@ static int iavf_open(struct net_device *netdev)
 	struct iavf_adapter *adapter = netdev_priv(netdev);
 	int err;
 
+	netdev_assert_locked(netdev);
+
 	if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) {
 		dev_err(&adapter->pdev->dev, "Unable to open device due to PF driver failure.\n");
 		return -EIO;
 	}
 
-	netdev_lock(netdev);
 	while (!mutex_trylock(&adapter->crit_lock)) {
 		/* If we are in __IAVF_INIT_CONFIG_ADAPTER state the crit_lock
 		 * is already taken and iavf_open is called from an upper
 		 * device's notifier reacting on NETDEV_REGISTER event.
 		 * We have to leave here to avoid dead lock.
 		 */
-		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER) {
-			netdev_unlock(netdev);
+		if (adapter->state == __IAVF_INIT_CONFIG_ADAPTER)
 			return -EBUSY;
-		}
 
 		usleep_range(500, 1000);
 	}
@@ -4626,7 +4625,6 @@ static int iavf_open(struct net_device *netdev)
 	iavf_irq_enable(adapter, true);
 
 	mutex_unlock(&adapter->crit_lock);
-	netdev_unlock(netdev);
 
 	return 0;
 
@@ -4639,7 +4637,6 @@ static int iavf_open(struct net_device *netdev)
 	iavf_free_all_tx_resources(adapter);
 err_unlock:
 	mutex_unlock(&adapter->crit_lock);
-	netdev_unlock(netdev);
 
 	return err;
 }
@@ -4661,12 +4658,12 @@ static int iavf_close(struct net_device *netdev)
 	u64 aq_to_restore;
 	int status;
 
-	netdev_lock(netdev);
+	netdev_assert_locked(netdev);
+
 	mutex_lock(&adapter->crit_lock);
 
 	if (adapter->state <= __IAVF_DOWN_PENDING) {
 		mutex_unlock(&adapter->crit_lock);
-		netdev_unlock(netdev);
 		return 0;
 	}
 
@@ -4719,6 +4716,7 @@ static int iavf_close(struct net_device *netdev)
 	if (!status)
 		netdev_warn(netdev, "Device resources not yet released\n");
 
+	netdev_lock(netdev);
 	mutex_lock(&adapter->crit_lock);
 	adapter->aq_required |= aq_to_restore;
 	mutex_unlock(&adapter->crit_lock);
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index a41dc79e9c2e0..aaa3b58e2e3e1 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -402,7 +402,7 @@ static int nsim_init_napi(struct netdevsim *ns)
 	for (i = 0; i < dev->num_rx_queues; i++) {
 		rq = ns->rq[i];
 
-		netif_napi_add_config(dev, &rq->napi, nsim_poll, i);
+		netif_napi_add_config_locked(dev, &rq->napi, nsim_poll, i);
 	}
 
 	for (i = 0; i < dev->num_rx_queues; i++) {
@@ -422,7 +422,7 @@ static int nsim_init_napi(struct netdevsim *ns)
 	}
 
 	for (i = 0; i < dev->num_rx_queues; i++)
-		__netif_napi_del(&ns->rq[i]->napi);
+		__netif_napi_del_locked(&ns->rq[i]->napi);
 
 	return err;
 }
@@ -452,7 +452,7 @@ static void nsim_enable_napi(struct netdevsim *ns)
 		struct nsim_rq *rq = ns->rq[i];
 
 		netif_queue_set_napi(dev, i, NETDEV_QUEUE_TYPE_RX, &rq->napi);
-		napi_enable(&rq->napi);
+		napi_enable_locked(&rq->napi);
 	}
 }
 
@@ -461,6 +461,8 @@ static int nsim_open(struct net_device *dev)
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
+	netdev_assert_locked(dev);
+
 	err = nsim_init_napi(ns);
 	if (err)
 		return err;
@@ -478,8 +480,8 @@ static void nsim_del_napi(struct netdevsim *ns)
 	for (i = 0; i < dev->num_rx_queues; i++) {
 		struct nsim_rq *rq = ns->rq[i];
 
-		napi_disable(&rq->napi);
-		__netif_napi_del(&rq->napi);
+		napi_disable_locked(&rq->napi);
+		__netif_napi_del_locked(&rq->napi);
 	}
 	synchronize_net();
 
@@ -494,6 +496,8 @@ static int nsim_stop(struct net_device *dev)
 	struct netdevsim *ns = netdev_priv(dev);
 	struct netdevsim *peer;
 
+	netdev_assert_locked(dev);
+
 	netif_carrier_off(dev);
 	peer = rtnl_dereference(ns->peer);
 	if (peer)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7ab86ec228b7f..33066b155c842 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2753,6 +2753,29 @@ static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
 		netdev_assert_locked(dev);
 }
 
+static inline bool netdev_need_ops_lock(struct net_device *dev)
+{
+	bool ret = false;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	ret |= !!dev->netdev_ops->net_shaper_ops;
+#endif
+
+	return ret;
+}
+
+static inline void netdev_lock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+}
+
 void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
 
 static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
diff --git a/net/core/dev.c b/net/core/dev.c
index 2dc705604509e..7a327c782ea46 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1627,6 +1627,8 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (ret)
 		return ret;
 
+	netdev_lock_ops(dev);
+
 	set_bit(__LINK_STATE_START, &dev->state);
 
 	if (ops->ndo_validate_addr)
@@ -1646,6 +1648,8 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
+	netdev_unlock_ops(dev);
+
 	return ret;
 }
 
@@ -1716,11 +1720,19 @@ static void __dev_close_many(struct list_head *head)
 		 *	We allow it to be called even after a DETACH hot-plug
 		 *	event.
 		 */
+
+		/* TODO: move the lock up before clearing __LINK_STATE_START.
+		 * Generates spurious lockdep warning.
+		 */
+		netdev_lock_ops(dev);
+
 		if (ops->ndo_stop)
 			ops->ndo_stop(dev);
 
 		netif_set_up(dev, false);
 		netpoll_poll_enable(dev);
+
+		netdev_unlock_ops(dev);
 	}
 }
 
diff --git a/net/core/dev.h b/net/core/dev.h
index caa13e431a6bc..25bb9d6afbce1 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -134,9 +134,11 @@ static inline void netif_set_up(struct net_device *dev, bool value)
 	else
 		dev->flags &= ~IFF_UP;
 
-	netdev_lock(dev);
+	if (!netdev_need_ops_lock(dev))
+		netdev_lock(dev);
 	dev->up = value;
-	netdev_unlock(dev);
+	if (!netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
 }
 
 static inline void netif_set_gso_max_size(struct net_device *dev,

From c4f0f30b424e7258a777bcbcbf9006207da4854c Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:20 -0800
Subject: [PATCH 1719/2753] net: hold netdev instance lock during nft
 ndo_setup_tc

Introduce new dev_setup_tc for nft ndo_setup_tc paths.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/iavf/iavf_main.c |  2 --
 include/linux/netdevice.h                   |  2 ++
 net/core/dev.c                              | 18 ++++++++++++++++++
 net/netfilter/nf_flow_table_offload.c       |  2 +-
 net/netfilter/nf_tables_offload.c           |  2 +-
 5 files changed, 22 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 9f4d223dffcfb..032e1a58af6f1 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -3894,10 +3894,8 @@ static int __iavf_setup_tc(struct net_device *netdev, void *type_data)
 	if (test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section))
 		return 0;
 
-	netdev_lock(netdev);
 	netif_set_real_num_rx_queues(netdev, total_qps);
 	netif_set_real_num_tx_queues(netdev, total_qps);
-	netdev_unlock(netdev);
 
 	return ret;
 }
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 33066b155c842..69951eeb96d26 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3353,6 +3353,8 @@ int dev_alloc_name(struct net_device *dev, const char *name);
 int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
 void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
+int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		 void *type_data);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
diff --git a/net/core/dev.c b/net/core/dev.c
index 7a327c782ea46..57af25683ea1b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1786,6 +1786,24 @@ void dev_close(struct net_device *dev)
 }
 EXPORT_SYMBOL(dev_close);
 
+int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
+		 void *type_data)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int ret;
+
+	ASSERT_RTNL();
+
+	if (!ops->ndo_setup_tc)
+		return -EOPNOTSUPP;
+
+	netdev_lock_ops(dev);
+	ret = ops->ndo_setup_tc(dev, type, type_data);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_setup_tc);
 
 /**
  *	dev_disable_lro - disable Large Receive Offload on a device
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index e06bc36f49fe7..0ec4abded10de 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1175,7 +1175,7 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
 	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
 					 extack);
 	down_write(&flowtable->flow_block_lock);
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
+	err = dev_setup_tc(dev, TC_SETUP_FT, bo);
 	up_write(&flowtable->flow_block_lock);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index 64675f1c7f295..b761899c143cd 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -390,7 +390,7 @@ static int nft_block_offload_cmd(struct nft_base_chain *chain,
 
 	nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack);
 
-	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	err = dev_setup_tc(dev, TC_SETUP_BLOCK, &bo);
 	if (err < 0)
 		return err;
 

From 7c79cff955358c944479f341e6ddb962e613dc77 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:21 -0800
Subject: [PATCH 1720/2753] net: sched: wrap doit/dumpit methods

In preparation for grabbing netdev instance lock around qdisc
operations, introduce tc_xxx wrappers that lookup netdev
and call respective __tc_xxx helper to do the actual work.
No functional changes.

Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Saeed Mahameed <saeed@kernel.org>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_api.c | 191 ++++++++++++++++++++++++++++----------------
 1 file changed, 123 insertions(+), 68 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e3e91cf867eb9..21940f3ae66f9 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1505,27 +1505,18 @@ const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
  * Delete/get qdisc.
  */
 
-static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
-			struct netlink_ext_ack *extack)
+static int __tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			  struct netlink_ext_ack *extack,
+			  struct net_device *dev,
+			  struct nlattr *tca[TCA_MAX + 1],
+			  struct tcmsg *tcm)
 {
 	struct net *net = sock_net(skb->sk);
-	struct tcmsg *tcm = nlmsg_data(n);
-	struct nlattr *tca[TCA_MAX + 1];
-	struct net_device *dev;
-	u32 clid;
 	struct Qdisc *q = NULL;
 	struct Qdisc *p = NULL;
+	u32 clid;
 	int err;
 
-	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
-				     rtm_tca_policy, extack);
-	if (err < 0)
-		return err;
-
-	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
-	if (!dev)
-		return -ENODEV;
-
 	clid = tcm->tcm_parent;
 	if (clid) {
 		if (clid != TC_H_ROOT) {
@@ -1582,6 +1573,27 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 	return 0;
 }
 
+static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct tcmsg *tcm = nlmsg_data(n);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct net_device *dev;
+	int err;
+
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
+	if (err < 0)
+		return err;
+
+	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	return __tc_get_qdisc(skb, n, extack, dev, tca, tcm);
+}
+
 static bool req_create_or_replace(struct nlmsghdr *n)
 {
 	return (n->nlmsg_flags & NLM_F_CREATE &&
@@ -1601,35 +1613,19 @@ static bool req_change(struct nlmsghdr *n)
 		!(n->nlmsg_flags & NLM_F_EXCL));
 }
 
-/*
- * Create/change qdisc.
- */
-static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
-			   struct netlink_ext_ack *extack)
+static int __tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			     struct netlink_ext_ack *extack,
+			     struct net_device *dev,
+			     struct nlattr *tca[TCA_MAX + 1],
+			     struct tcmsg *tcm,
+			     bool *replay)
 {
-	struct net *net = sock_net(skb->sk);
-	struct tcmsg *tcm;
-	struct nlattr *tca[TCA_MAX + 1];
-	struct net_device *dev;
+	struct Qdisc *q = NULL;
+	struct Qdisc *p = NULL;
 	u32 clid;
-	struct Qdisc *q, *p;
 	int err;
 
-replay:
-	/* Reinit, just in case something touches this. */
-	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
-				     rtm_tca_policy, extack);
-	if (err < 0)
-		return err;
-
-	tcm = nlmsg_data(n);
 	clid = tcm->tcm_parent;
-	q = p = NULL;
-
-	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
-	if (!dev)
-		return -ENODEV;
-
 
 	if (clid) {
 		if (clid != TC_H_ROOT) {
@@ -1755,7 +1751,7 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 	}
 	err = qdisc_change(q, tca, extack);
 	if (err == 0)
-		qdisc_notify(net, skb, n, clid, NULL, q, extack);
+		qdisc_notify(sock_net(skb->sk), skb, n, clid, NULL, q, extack);
 	return err;
 
 create_n_graft:
@@ -1788,8 +1784,10 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 				 tca, &err, extack);
 	}
 	if (q == NULL) {
-		if (err == -EAGAIN)
-			goto replay;
+		if (err == -EAGAIN) {
+			*replay = true;
+			return 0;
+		}
 		return err;
 	}
 
@@ -1804,6 +1802,39 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 	return 0;
 }
 
+/*
+ * Create/change qdisc.
+ */
+static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
+			   struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct net_device *dev;
+	struct tcmsg *tcm;
+	bool replay;
+	int err;
+
+replay:
+	/* Reinit, just in case something touches this. */
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
+	if (err < 0)
+		return err;
+
+	tcm = nlmsg_data(n);
+	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	replay = false;
+	err = __tc_modify_qdisc(skb, n, extack, dev, tca, tcm, &replay);
+	if (replay)
+		goto replay;
+
+	return err;
+}
+
 static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb,
 			      struct netlink_callback *cb,
 			      int *q_idx_p, int s_q_idx, bool recur,
@@ -2135,15 +2166,15 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid,
 
 #endif
 
-static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
-			 struct netlink_ext_ack *extack)
+static int __tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
+			   struct netlink_ext_ack *extack,
+			   struct net_device *dev,
+			   struct nlattr *tca[TCA_MAX + 1],
+			   struct tcmsg *tcm)
 {
 	struct net *net = sock_net(skb->sk);
-	struct tcmsg *tcm = nlmsg_data(n);
-	struct nlattr *tca[TCA_MAX + 1];
-	struct net_device *dev;
-	struct Qdisc *q = NULL;
 	const struct Qdisc_class_ops *cops;
+	struct Qdisc *q = NULL;
 	unsigned long cl = 0;
 	unsigned long new_cl;
 	u32 portid;
@@ -2151,15 +2182,6 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 	u32 qid;
 	int err;
 
-	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
-				     rtm_tca_policy, extack);
-	if (err < 0)
-		return err;
-
-	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
-	if (!dev)
-		return -ENODEV;
-
 	/*
 	   parent == TC_H_UNSPEC - unspecified parent.
 	   parent == TC_H_ROOT   - class is root, which has no parent.
@@ -2268,6 +2290,27 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 	return err;
 }
 
+static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
+			 struct netlink_ext_ack *extack)
+{
+	struct net *net = sock_net(skb->sk);
+	struct tcmsg *tcm = nlmsg_data(n);
+	struct nlattr *tca[TCA_MAX + 1];
+	struct net_device *dev;
+	int err;
+
+	err = nlmsg_parse_deprecated(n, sizeof(*tcm), tca, TCA_MAX,
+				     rtm_tca_policy, extack);
+	if (err < 0)
+		return err;
+
+	dev = __dev_get_by_index(net, tcm->tcm_ifindex);
+	if (!dev)
+		return -ENODEV;
+
+	return __tc_ctl_tclass(skb, n, extack, dev, tca, tcm);
+}
+
 struct qdisc_dump_args {
 	struct qdisc_walker	w;
 	struct sk_buff		*skb;
@@ -2344,20 +2387,12 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb,
 	return 0;
 }
 
-static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
+static int __tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb,
+			    struct tcmsg *tcm, struct net_device *dev)
 {
-	struct tcmsg *tcm = nlmsg_data(cb->nlh);
-	struct net *net = sock_net(skb->sk);
 	struct netdev_queue *dev_queue;
-	struct net_device *dev;
 	int t, s_t;
 
-	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
-		return 0;
-	dev = dev_get_by_index(net, tcm->tcm_ifindex);
-	if (!dev)
-		return 0;
-
 	s_t = cb->args[0];
 	t = 0;
 
@@ -2374,10 +2409,30 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
 done:
 	cb->args[0] = t;
 
-	dev_put(dev);
 	return skb->len;
 }
 
+static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct tcmsg *tcm = nlmsg_data(cb->nlh);
+	struct net *net = sock_net(skb->sk);
+	struct net_device *dev;
+	int err;
+
+	if (nlmsg_len(cb->nlh) < sizeof(*tcm))
+		return 0;
+
+	dev = dev_get_by_index(net, tcm->tcm_ifindex);
+	if (!dev)
+		return 0;
+
+	err = __tc_dump_tclass(skb, cb, tcm, dev);
+
+	dev_put(dev);
+
+	return err;
+}
+
 #ifdef CONFIG_PROC_FS
 static int psched_show(struct seq_file *seq, void *v)
 {

From a0527ee2df3f55cd4793e83ffc07e8e2a594086b Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:22 -0800
Subject: [PATCH 1721/2753] net: hold netdev instance lock during qdisc
 ndo_setup_tc

Qdisc operations that can lead to ndo_setup_tc might need
to have an instance lock. Add netdev_lock_ops/netdev_unlock_ops
invocations for all psched_rtnl_msg_handlers operations.

Cc: Cong Wang <xiyou.wangcong@gmail.com>
Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Saeed Mahameed <saeed@kernel.org>
Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-5-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_api.c | 28 ++++++++++++++++++++++++----
 1 file changed, 24 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 21940f3ae66f9..f5101c2ffc664 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1279,9 +1279,11 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 			 * We replay the request because the device may
 			 * go away in the mean time.
 			 */
+			netdev_unlock_ops(dev);
 			rtnl_unlock();
 			request_module(NET_SCH_ALIAS_PREFIX "%s", name);
 			rtnl_lock();
+			netdev_lock_ops(dev);
 			ops = qdisc_lookup_ops(kind);
 			if (ops != NULL) {
 				/* We will try again qdisc_lookup_ops,
@@ -1591,7 +1593,11 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 	if (!dev)
 		return -ENODEV;
 
-	return __tc_get_qdisc(skb, n, extack, dev, tca, tcm);
+	netdev_lock_ops(dev);
+	err = __tc_get_qdisc(skb, n, extack, dev, tca, tcm);
+	netdev_unlock_ops(dev);
+
+	return err;
 }
 
 static bool req_create_or_replace(struct nlmsghdr *n)
@@ -1828,7 +1834,9 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n,
 		return -ENODEV;
 
 	replay = false;
+	netdev_lock_ops(dev);
 	err = __tc_modify_qdisc(skb, n, extack, dev, tca, tcm, &replay);
+	netdev_unlock_ops(dev);
 	if (replay)
 		goto replay;
 
@@ -1919,17 +1927,23 @@ static int tc_dump_qdisc(struct sk_buff *skb, struct netlink_callback *cb)
 			s_q_idx = 0;
 		q_idx = 0;
 
+		netdev_lock_ops(dev);
 		if (tc_dump_qdisc_root(rtnl_dereference(dev->qdisc),
 				       skb, cb, &q_idx, s_q_idx,
-				       true, tca[TCA_DUMP_INVISIBLE]) < 0)
+				       true, tca[TCA_DUMP_INVISIBLE]) < 0) {
+			netdev_unlock_ops(dev);
 			goto done;
+		}
 
 		dev_queue = dev_ingress_queue(dev);
 		if (dev_queue &&
 		    tc_dump_qdisc_root(rtnl_dereference(dev_queue->qdisc_sleeping),
 				       skb, cb, &q_idx, s_q_idx, false,
-				       tca[TCA_DUMP_INVISIBLE]) < 0)
+				       tca[TCA_DUMP_INVISIBLE]) < 0) {
+			netdev_unlock_ops(dev);
 			goto done;
+		}
+		netdev_unlock_ops(dev);
 
 cont:
 		idx++;
@@ -2308,7 +2322,11 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 	if (!dev)
 		return -ENODEV;
 
-	return __tc_ctl_tclass(skb, n, extack, dev, tca, tcm);
+	netdev_lock_ops(dev);
+	err = __tc_ctl_tclass(skb, n, extack, dev, tca, tcm);
+	netdev_unlock_ops(dev);
+
+	return err;
 }
 
 struct qdisc_dump_args {
@@ -2426,7 +2444,9 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb)
 	if (!dev)
 		return 0;
 
+	netdev_lock_ops(dev);
 	err = __tc_dump_tclass(skb, cb, tcm, dev);
+	netdev_unlock_ops(dev);
 
 	dev_put(dev);
 

From cae03e5bdd9e0c8570506c50f1f234da40201732 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:23 -0800
Subject: [PATCH 1722/2753] net: hold netdev instance lock during queue
 operations

For the drivers that use queue management API, switch to the mode where
core stack holds the netdev instance lock. This affects the following
drivers:
- bnxt
- gve
- netdevsim

Originally I locked only start/stop, but switched to holding the
lock over all iterations to make them look atomic to the device
(feels like it should be easier to reason about).

Reviewed-by: Eric Dumazet <edumazet@google.com>
Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-6-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c   | 16 ++++++-------
 drivers/net/ethernet/google/gve/gve_main.c  | 12 ++++++----
 drivers/net/ethernet/google/gve/gve_utils.c |  6 ++---
 drivers/net/netdevsim/netdev.c              | 25 +++++++++++++--------
 include/linux/netdevice.h                   |  2 +-
 net/core/netdev_rx_queue.c                  |  5 +++++
 6 files changed, 41 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 15c57a06ecaf4..ead9fcaad6bdd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11508,7 +11508,7 @@ static int bnxt_request_irq(struct bnxt *bp)
 		if (rc)
 			break;
 
-		netif_napi_set_irq(&bp->bnapi[i]->napi, irq->vector);
+		netif_napi_set_irq_locked(&bp->bnapi[i]->napi, irq->vector);
 		irq->requested = 1;
 
 		if (zalloc_cpumask_var(&irq->cpu_mask, GFP_KERNEL)) {
@@ -11557,9 +11557,9 @@ static void bnxt_del_napi(struct bnxt *bp)
 	for (i = 0; i < bp->cp_nr_rings; i++) {
 		struct bnxt_napi *bnapi = bp->bnapi[i];
 
-		__netif_napi_del(&bnapi->napi);
+		__netif_napi_del_locked(&bnapi->napi);
 	}
-	/* We called __netif_napi_del(), we need
+	/* We called __netif_napi_del_locked(), we need
 	 * to respect an RCU grace period before freeing napi structures.
 	 */
 	synchronize_net();
@@ -11578,12 +11578,12 @@ static void bnxt_init_napi(struct bnxt *bp)
 		cp_nr_rings--;
 	for (i = 0; i < cp_nr_rings; i++) {
 		bnapi = bp->bnapi[i];
-		netif_napi_add_config(bp->dev, &bnapi->napi, poll_fn,
-				      bnapi->index);
+		netif_napi_add_config_locked(bp->dev, &bnapi->napi, poll_fn,
+					     bnapi->index);
 	}
 	if (BNXT_CHIP_TYPE_NITRO_A0(bp)) {
 		bnapi = bp->bnapi[cp_nr_rings];
-		netif_napi_add(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
+		netif_napi_add_locked(bp->dev, &bnapi->napi, bnxt_poll_nitroa0);
 	}
 }
 
@@ -11604,7 +11604,7 @@ static void bnxt_disable_napi(struct bnxt *bp)
 			cpr->sw_stats->tx.tx_resets++;
 		if (bnapi->in_reset)
 			cpr->sw_stats->rx.rx_resets++;
-		napi_disable(&bnapi->napi);
+		napi_disable_locked(&bnapi->napi);
 	}
 }
 
@@ -11626,7 +11626,7 @@ static void bnxt_enable_napi(struct bnxt *bp)
 			INIT_WORK(&cpr->dim.work, bnxt_dim_work);
 			cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE;
 		}
-		napi_enable(&bnapi->napi);
+		napi_enable_locked(&bnapi->napi);
 	}
 }
 
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 029be8342b7b8..6dcdcaf518f4c 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1968,7 +1968,7 @@ static void gve_turndown(struct gve_priv *priv)
 			netif_queue_set_napi(priv->dev, idx,
 					     NETDEV_QUEUE_TYPE_TX, NULL);
 
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 	for (idx = 0; idx < priv->rx_cfg.num_queues; idx++) {
 		int ntfy_idx = gve_rx_idx_to_ntfy(priv, idx);
@@ -1979,7 +1979,7 @@ static void gve_turndown(struct gve_priv *priv)
 
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     NULL);
-		napi_disable(&block->napi);
+		napi_disable_locked(&block->napi);
 	}
 
 	/* Stop tx queues */
@@ -2009,7 +2009,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_tx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 
 		if (idx < priv->tx_cfg.num_queues)
 			netif_queue_set_napi(priv->dev, idx,
@@ -2037,7 +2037,7 @@ static void gve_turnup(struct gve_priv *priv)
 		if (!gve_rx_was_added_to_block(priv, idx))
 			continue;
 
-		napi_enable(&block->napi);
+		napi_enable_locked(&block->napi);
 		netif_queue_set_napi(priv->dev, idx, NETDEV_QUEUE_TYPE_RX,
 				     &block->napi);
 
@@ -2887,6 +2887,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	priv->suspend_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	if (was_up && gve_close(priv->dev)) {
 		/* If the dev was up, attempt to close, if close fails, reset */
 		gve_reset_and_teardown(priv, was_up);
@@ -2895,6 +2896,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
 		gve_teardown_priv_resources(priv);
 	}
 	priv->up_before_suspend = was_up;
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return 0;
 }
@@ -2907,7 +2909,9 @@ static int gve_resume(struct pci_dev *pdev)
 
 	priv->resume_cnt++;
 	rtnl_lock();
+	netdev_lock(netdev);
 	err = gve_reset_recovery(priv, priv->up_before_suspend);
+	netdev_unlock(netdev);
 	rtnl_unlock();
 	return err;
 }
diff --git a/drivers/net/ethernet/google/gve/gve_utils.c b/drivers/net/ethernet/google/gve/gve_utils.c
index 30fef100257e6..ace9b8698021f 100644
--- a/drivers/net/ethernet/google/gve/gve_utils.c
+++ b/drivers/net/ethernet/google/gve/gve_utils.c
@@ -110,13 +110,13 @@ void gve_add_napi(struct gve_priv *priv, int ntfy_idx,
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_add(priv->dev, &block->napi, gve_poll);
-	netif_napi_set_irq(&block->napi, block->irq);
+	netif_napi_add_locked(priv->dev, &block->napi, gve_poll);
+	netif_napi_set_irq_locked(&block->napi, block->irq);
 }
 
 void gve_remove_napi(struct gve_priv *priv, int ntfy_idx)
 {
 	struct gve_notify_block *block = &priv->ntfy_blocks[ntfy_idx];
 
-	netif_napi_del(&block->napi);
+	netif_napi_del_locked(&block->napi);
 }
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index aaa3b58e2e3e1..54d03b0628d22 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -683,7 +683,8 @@ nsim_queue_mem_alloc(struct net_device *dev, void *per_queue_mem, int idx)
 		goto err_free;
 
 	if (!ns->rq_reset_mode)
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
 
 	return 0;
 
@@ -700,7 +701,7 @@ static void nsim_queue_mem_free(struct net_device *dev, void *per_queue_mem)
 	page_pool_destroy(qmem->pp);
 	if (qmem->rq) {
 		if (!ns->rq_reset_mode)
-			netif_napi_del(&qmem->rq->napi);
+			netif_napi_del_locked(&qmem->rq->napi);
 		page_pool_destroy(qmem->rq->page_pool);
 		nsim_queue_free(qmem->rq);
 	}
@@ -712,9 +713,11 @@ nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx)
 	struct nsim_queue_mem *qmem = per_queue_mem;
 	struct netdevsim *ns = netdev_priv(dev);
 
+	netdev_assert_locked(dev);
+
 	if (ns->rq_reset_mode == 1) {
 		ns->rq[idx]->page_pool = qmem->pp;
-		napi_enable(&ns->rq[idx]->napi);
+		napi_enable_locked(&ns->rq[idx]->napi);
 		return 0;
 	}
 
@@ -722,15 +725,17 @@ nsim_queue_start(struct net_device *dev, void *per_queue_mem, int idx)
 	 * here we want to test various call orders.
 	 */
 	if (ns->rq_reset_mode == 2) {
-		netif_napi_del(&ns->rq[idx]->napi);
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
+		netif_napi_del_locked(&ns->rq[idx]->napi);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
 	} else if (ns->rq_reset_mode == 3) {
-		netif_napi_add_config(dev, &qmem->rq->napi, nsim_poll, idx);
-		netif_napi_del(&ns->rq[idx]->napi);
+		netif_napi_add_config_locked(dev, &qmem->rq->napi, nsim_poll,
+					     idx);
+		netif_napi_del_locked(&ns->rq[idx]->napi);
 	}
 
 	ns->rq[idx] = qmem->rq;
-	napi_enable(&ns->rq[idx]->napi);
+	napi_enable_locked(&ns->rq[idx]->napi);
 
 	return 0;
 }
@@ -740,7 +745,9 @@ static int nsim_queue_stop(struct net_device *dev, void *per_queue_mem, int idx)
 	struct nsim_queue_mem *qmem = per_queue_mem;
 	struct netdevsim *ns = netdev_priv(dev);
 
-	napi_disable(&ns->rq[idx]->napi);
+	netdev_assert_locked(dev);
+
+	napi_disable_locked(&ns->rq[idx]->napi);
 
 	if (ns->rq_reset_mode == 1) {
 		qmem->pp = ns->rq[idx]->page_pool;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 69951eeb96d26..abda17b15950a 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2755,7 +2755,7 @@ static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
 
 static inline bool netdev_need_ops_lock(struct net_device *dev)
 {
-	bool ret = false;
+	bool ret = !!dev->queue_mgmt_ops;
 
 #if IS_ENABLED(CONFIG_NET_SHAPER)
 	ret |= !!dev->netdev_ops->net_shaper_ops;
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index ddd54e1e72897..7419c41fd3cb9 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -30,6 +30,8 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 		goto err_free_new_mem;
 	}
 
+	netdev_lock(dev);
+
 	err = qops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
 	if (err)
 		goto err_free_old_mem;
@@ -52,6 +54,8 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 
 	qops->ndo_queue_mem_free(dev, old_mem);
 
+	netdev_unlock(dev);
+
 	kvfree(old_mem);
 	kvfree(new_mem);
 
@@ -76,6 +80,7 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	qops->ndo_queue_mem_free(dev, new_mem);
 
 err_free_old_mem:
+	netdev_unlock(dev);
 	kvfree(old_mem);
 
 err_free_new_mem:

From 7e4d784f5810bba76c4593791028e13cce4af547 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:24 -0800
Subject: [PATCH 1723/2753] net: hold netdev instance lock during rtnetlink
 operations

To preserve the atomicity, hold the lock while applying multiple
attributes. The major issue with a full conversion to the instance
lock are software nesting devices (bonding/team/vrf/etc). Those
devices call into the core stack for their lower (potentially
real hw) devices. To avoid explicitly wrapping all those places
into instance lock/unlock, introduce new API boundaries:

- (some) existing dev_xxx calls are now considered "external"
  (to drivers) APIs and they transparently grab the instance
  lock if needed (dev_api.c)
- new netif_xxx calls are internal core stack API (naming is
  sketchy, I've tried netdev_xxx_locked per Jakub's suggestion,
  but it feels a bit verbose; but happy to get back to this
  naming scheme if this is the preference)

This avoids touching most of the existing ioctl/sysfs/drivers paths.

Note the special handling of ndo_xxx_slave operations: I exploit
the fact that none of the drivers that call these functions
need/use instance lock. At the same time, they use dev_xxx
APIs, so the lower device has to be unlocked.

Changes in unregister_netdevice_many_notify (to protect dev->state
with instance lock) trigger lockdep - the loop over close_list
(mostly from cleanup_net) introduces spurious ordering issues.
netdev_lock_cmp_fn has a justification on why it's ok to suppress
for now.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-7-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  40 ++++++-
 net/core/Makefile         |   2 +-
 net/core/dev.c            | 154 +++++---------------------
 net/core/dev.h            |  13 ++-
 net/core/dev_api.c        | 224 ++++++++++++++++++++++++++++++++++++++
 net/core/rtnetlink.c      |  46 +++++---
 6 files changed, 329 insertions(+), 150 deletions(-)
 create mode 100644 net/core/dev_api.c

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index abda17b15950a..be3d09b61e959 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2620,16 +2620,35 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
+static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
+				     const struct lockdep_map *b)
+{
+	/* Only lower devices currently grab the instance lock, so no
+	 * real ordering issues can occur. In the near future, only
+	 * hardware devices will grab instance lock which also does not
+	 * involve any ordering. Suppress lockdep ordering warnings
+	 * until (if) we start grabbing instance lock on pure SW
+	 * devices (bond/team/veth/etc).
+	 */
+	if (a == b)
+		return 0;
+	return -1;
+}
+
 #define netdev_lockdep_set_classes(dev)				\
 {								\
 	static struct lock_class_key qdisc_tx_busylock_key;	\
 	static struct lock_class_key qdisc_xmit_lock_key;	\
 	static struct lock_class_key dev_addr_list_lock_key;	\
+	static struct lock_class_key dev_instance_lock_key;	\
 	unsigned int i;						\
 								\
 	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
 	lockdep_set_class(&(dev)->addr_list_lock,		\
 			  &dev_addr_list_lock_key);		\
+	lockdep_set_class(&(dev)->lock,				\
+			  &dev_instance_lock_key);		\
+	lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL);	\
 	for (i = 0; i < (dev)->num_tx_queues; i++)		\
 		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
 				  &qdisc_xmit_lock_key);	\
@@ -2776,6 +2795,12 @@ static inline void netdev_unlock_ops(struct net_device *dev)
 		netdev_unlock(dev);
 }
 
+static inline void netdev_ops_assert_locked(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		lockdep_assert_held(&dev->lock);
+}
+
 void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
 
 static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
@@ -3350,7 +3375,9 @@ struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
 bool netdev_name_in_use(struct net *net, const char *name);
 int dev_alloc_name(struct net_device *dev, const char *name);
+int netif_open(struct net_device *dev, struct netlink_ext_ack *extack);
 int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
+void netif_close(struct net_device *dev);
 void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
 int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
@@ -4211,25 +4238,26 @@ int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
 unsigned int dev_get_flags(const struct net_device *);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		       struct netlink_ext_ack *extack);
+int netif_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack);
 int dev_change_flags(struct net_device *dev, unsigned int flags,
 		     struct netlink_ext_ack *extack);
+int netif_set_alias(struct net_device *dev, const char *alias, size_t len);
 int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
-int __dev_change_net_namespace(struct net_device *dev, struct net *net,
+int netif_change_net_namespace(struct net_device *dev, struct net *net,
 			       const char *pat, int new_ifindex,
 			       struct netlink_ext_ack *extack);
-static inline
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
-			     const char *pat)
-{
-	return __dev_change_net_namespace(dev, net, pat, 0, NULL);
-}
+			     const char *pat);
 int __dev_set_mtu(struct net_device *, int);
 int dev_set_mtu(struct net_device *, int);
 int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 			      struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
+int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			       struct netlink_ext_ack *extack);
 int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
diff --git a/net/core/Makefile b/net/core/Makefile
index d9326600e289b..a10c3bd96798d 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -9,7 +9,7 @@ obj-y := sock.o request_sock.o skbuff.o datagram.o stream.o scm.o \
 
 obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 
-obj-y		     += dev.o dev_addr_lists.o dst.o netevent.o \
+obj-y		     += dev.o dev_api.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
 			sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
 			fib_notifier.o xdp.o flow_offload.o gro.o \
diff --git a/net/core/dev.c b/net/core/dev.c
index 57af25683ea1b..39b214fb462e4 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1371,15 +1371,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev,
 	return ret < 0 ? ret : 0;
 }
 
-/**
- *	dev_change_name - change name of a device
- *	@dev: device
- *	@newname: name (or format string) must be at least IFNAMSIZ
- *
- *	Change name of a device, can pass format strings "eth%d".
- *	for wildcarding.
- */
-int dev_change_name(struct net_device *dev, const char *newname)
+int netif_change_name(struct net_device *dev, const char *newname)
 {
 	struct net *net = dev_net(dev);
 	unsigned char old_assign_type;
@@ -1449,15 +1441,7 @@ int dev_change_name(struct net_device *dev, const char *newname)
 	return err;
 }
 
-/**
- *	dev_set_alias - change ifalias of a device
- *	@dev: device
- *	@alias: name up to IFALIASZ
- *	@len: limit of bytes to copy from info
- *
- *	Set ifalias for a device,
- */
-int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
+int netif_set_alias(struct net_device *dev, const char *alias, size_t len)
 {
 	struct dev_ifalias *new_alias = NULL;
 
@@ -1483,7 +1467,6 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
 
 	return len;
 }
-EXPORT_SYMBOL(dev_set_alias);
 
 /**
  *	dev_get_alias - get ifalias of a device
@@ -1627,10 +1610,10 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 	if (ret)
 		return ret;
 
-	netdev_lock_ops(dev);
-
 	set_bit(__LINK_STATE_START, &dev->state);
 
+	netdev_ops_assert_locked(dev);
+
 	if (ops->ndo_validate_addr)
 		ret = ops->ndo_validate_addr(dev);
 
@@ -1648,25 +1631,10 @@ static int __dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 		add_device_randomness(dev->dev_addr, dev->addr_len);
 	}
 
-	netdev_unlock_ops(dev);
-
 	return ret;
 }
 
-/**
- *	dev_open	- prepare an interface for use.
- *	@dev: device to open
- *	@extack: netlink extended ack
- *
- *	Takes a device from down to up state. The device's private open
- *	function is invoked and then the multicast lists are loaded. Finally
- *	the device is moved into the up state and a %NETDEV_UP message is
- *	sent to the netdev notifier chain.
- *
- *	Calling this function on an active interface is a nop. On a failure
- *	a negative errno code is returned.
- */
-int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
+int netif_open(struct net_device *dev, struct netlink_ext_ack *extack)
 {
 	int ret;
 
@@ -1682,7 +1650,6 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
 
 	return ret;
 }
-EXPORT_SYMBOL(dev_open);
 
 static void __dev_close_many(struct list_head *head)
 {
@@ -1721,18 +1688,13 @@ static void __dev_close_many(struct list_head *head)
 		 *	event.
 		 */
 
-		/* TODO: move the lock up before clearing __LINK_STATE_START.
-		 * Generates spurious lockdep warning.
-		 */
-		netdev_lock_ops(dev);
+		netdev_ops_assert_locked(dev);
 
 		if (ops->ndo_stop)
 			ops->ndo_stop(dev);
 
 		netif_set_up(dev, false);
 		netpoll_poll_enable(dev);
-
-		netdev_unlock_ops(dev);
 	}
 }
 
@@ -1765,16 +1727,7 @@ void dev_close_many(struct list_head *head, bool unlink)
 }
 EXPORT_SYMBOL(dev_close_many);
 
-/**
- *	dev_close - shutdown an interface.
- *	@dev: device to shutdown
- *
- *	This function moves an active device into down state. A
- *	%NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
- *	is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
- *	chain.
- */
-void dev_close(struct net_device *dev)
+void netif_close(struct net_device *dev)
 {
 	if (dev->flags & IFF_UP) {
 		LIST_HEAD(single);
@@ -1784,7 +1737,6 @@ void dev_close(struct net_device *dev)
 		list_del(&single);
 	}
 }
-EXPORT_SYMBOL(dev_close);
 
 int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		 void *type_data)
@@ -9479,17 +9431,8 @@ void __dev_notify_flags(struct net_device *dev, unsigned int old_flags,
 	}
 }
 
-/**
- *	dev_change_flags - change device settings
- *	@dev: device
- *	@flags: device state flags
- *	@extack: netlink extended ack
- *
- *	Change settings on device based state flags. The flags are
- *	in the userspace exported format.
- */
-int dev_change_flags(struct net_device *dev, unsigned int flags,
-		     struct netlink_ext_ack *extack)
+int netif_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack)
 {
 	int ret;
 	unsigned int changes, old_flags = dev->flags, old_gflags = dev->gflags;
@@ -9502,7 +9445,6 @@ int dev_change_flags(struct net_device *dev, unsigned int flags,
 	__dev_notify_flags(dev, old_flags, changes, 0, NULL);
 	return ret;
 }
-EXPORT_SYMBOL(dev_change_flags);
 
 int __dev_set_mtu(struct net_device *dev, int new_mtu)
 {
@@ -9534,15 +9476,15 @@ int dev_validate_mtu(struct net_device *dev, int new_mtu,
 }
 
 /**
- *	dev_set_mtu_ext - Change maximum transfer unit
+ *	netif_set_mtu_ext - Change maximum transfer unit
  *	@dev: device
  *	@new_mtu: new transfer unit
  *	@extack: netlink extended ack
  *
  *	Change the maximum transfer size of the network device.
  */
-int dev_set_mtu_ext(struct net_device *dev, int new_mtu,
-		    struct netlink_ext_ack *extack)
+int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
+		      struct netlink_ext_ack *extack)
 {
 	int err, orig_mtu;
 
@@ -9586,19 +9528,14 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	int err;
 
 	memset(&extack, 0, sizeof(extack));
-	err = dev_set_mtu_ext(dev, new_mtu, &extack);
+	err = netif_set_mtu_ext(dev, new_mtu, &extack);
 	if (err && extack._msg)
 		net_err_ratelimited("%s: %s\n", dev->name, extack._msg);
 	return err;
 }
 EXPORT_SYMBOL(dev_set_mtu);
 
-/**
- *	dev_change_tx_queue_len - Change TX queue length of a netdevice
- *	@dev: device
- *	@new_len: new tx queue length
- */
-int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
+int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 {
 	unsigned int orig_len = dev->tx_queue_len;
 	int res;
@@ -9625,12 +9562,7 @@ int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 	return res;
 }
 
-/**
- *	dev_set_group - Change group this device belongs to
- *	@dev: device
- *	@new_group: group this device should belong to
- */
-void dev_set_group(struct net_device *dev, int new_group)
+void netif_set_group(struct net_device *dev, int new_group)
 {
 	dev->group = new_group;
 }
@@ -9693,8 +9625,8 @@ EXPORT_SYMBOL(dev_set_mac_address);
 
 DECLARE_RWSEM(dev_addr_sem);
 
-int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			     struct netlink_ext_ack *extack)
+int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			       struct netlink_ext_ack *extack)
 {
 	int ret;
 
@@ -9703,7 +9635,6 @@ int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 	up_write(&dev_addr_sem);
 	return ret;
 }
-EXPORT_SYMBOL(dev_set_mac_address_user);
 
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
@@ -9733,14 +9664,7 @@ int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 }
 EXPORT_SYMBOL(dev_get_mac_address);
 
-/**
- *	dev_change_carrier - Change device carrier
- *	@dev: device
- *	@new_carrier: new value
- *
- *	Change device carrier
- */
-int dev_change_carrier(struct net_device *dev, bool new_carrier)
+int netif_change_carrier(struct net_device *dev, bool new_carrier)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
@@ -9851,13 +9775,7 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
 }
 EXPORT_SYMBOL(netdev_port_same_parent_id);
 
-/**
- *	dev_change_proto_down - set carrier according to proto_down.
- *
- *	@dev: device
- *	@proto_down: new value
- */
-int dev_change_proto_down(struct net_device *dev, bool proto_down)
+int netif_change_proto_down(struct net_device *dev, bool proto_down)
 {
 	if (!dev->change_proto_down)
 		return -EOPNOTSUPP;
@@ -9872,14 +9790,14 @@ int dev_change_proto_down(struct net_device *dev, bool proto_down)
 }
 
 /**
- *	dev_change_proto_down_reason - proto down reason
+ *	netdev_change_proto_down_reason_locked - proto down reason
  *
  *	@dev: device
  *	@mask: proto down mask
  *	@value: proto down value
  */
-void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
-				  u32 value)
+void netdev_change_proto_down_reason_locked(struct net_device *dev,
+					    unsigned long mask, u32 value)
 {
 	u32 proto_down_reason;
 	int b;
@@ -10687,6 +10605,7 @@ int __netdev_update_features(struct net_device *dev)
 	int err = -1;
 
 	ASSERT_RTNL();
+	netdev_ops_assert_locked(dev);
 
 	features = netdev_get_wanted_features(dev);
 
@@ -12036,11 +11955,14 @@ void unregister_netdevice_many_notify(struct list_head *head,
 	}
 
 	/* If device is running, close it first. */
-	list_for_each_entry(dev, head, unreg_list)
+	list_for_each_entry(dev, head, unreg_list) {
 		list_add_tail(&dev->close_list, &close_head);
+		netdev_lock_ops(dev);
+	}
 	dev_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
+		netdev_unlock_ops(dev);
 		/* And unlink it from device chain. */
 		unlist_netdevice(dev);
 		netdev_lock(dev);
@@ -12153,24 +12075,7 @@ void unregister_netdev(struct net_device *dev)
 }
 EXPORT_SYMBOL(unregister_netdev);
 
-/**
- *	__dev_change_net_namespace - move device to different nethost namespace
- *	@dev: device
- *	@net: network namespace
- *	@pat: If not NULL name pattern to try if the current device name
- *	      is already taken in the destination network namespace.
- *	@new_ifindex: If not zero, specifies device index in the target
- *	              namespace.
- *	@extack: netlink extended ack
- *
- *	This function shuts down a device interface and moves it
- *	to a new network namespace. On success 0 is returned, on
- *	a failure a netagive errno code is returned.
- *
- *	Callers must hold the rtnl semaphore.
- */
-
-int __dev_change_net_namespace(struct net_device *dev, struct net *net,
+int netif_change_net_namespace(struct net_device *dev, struct net *net,
 			       const char *pat, int new_ifindex,
 			       struct netlink_ext_ack *extack)
 {
@@ -12256,7 +12161,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 	 */
 
 	/* If device is running close it first. */
-	dev_close(dev);
+	netif_close(dev);
 
 	/* And unlink it from device chain */
 	unlist_netdevice(dev);
@@ -12338,7 +12243,6 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 out:
 	return err;
 }
-EXPORT_SYMBOL_GPL(__dev_change_net_namespace);
 
 static int dev_cpu_dead(unsigned int oldcpu)
 {
diff --git a/net/core/dev.h b/net/core/dev.h
index 25bb9d6afbce1..41b0831aba604 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -85,6 +85,7 @@ struct netdev_name_node {
 };
 
 int netdev_get_name(struct net *net, char *name, int ifindex);
+int netif_change_name(struct net_device *dev, const char *newname);
 int dev_change_name(struct net_device *dev, const char *newname);
 
 #define netdev_for_each_altname(dev, namenode)				\
@@ -98,24 +99,28 @@ int netdev_name_node_alt_destroy(struct net_device *dev, const char *name);
 
 int dev_validate_mtu(struct net_device *dev, int mtu,
 		     struct netlink_ext_ack *extack);
-int dev_set_mtu_ext(struct net_device *dev, int mtu,
-		    struct netlink_ext_ack *extack);
+int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
+		      struct netlink_ext_ack *extack);
 
 int dev_get_phys_port_id(struct net_device *dev,
 			 struct netdev_phys_item_id *ppid);
 int dev_get_phys_port_name(struct net_device *dev,
 			   char *name, size_t len);
 
+int netif_change_proto_down(struct net_device *dev, bool proto_down);
 int dev_change_proto_down(struct net_device *dev, bool proto_down);
-void dev_change_proto_down_reason(struct net_device *dev, unsigned long mask,
-				  u32 value);
+void netdev_change_proto_down_reason_locked(struct net_device *dev,
+					    unsigned long mask, u32 value);
 
 typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags);
 
+int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len);
 int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len);
+void netif_set_group(struct net_device *dev, int new_group);
 void dev_set_group(struct net_device *dev, int new_group);
+int netif_change_carrier(struct net_device *dev, bool new_carrier);
 int dev_change_carrier(struct net_device *dev, bool new_carrier);
 
 void __dev_set_rx_mode(struct net_device *dev);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
new file mode 100644
index 0000000000000..21584f57e050d
--- /dev/null
+++ b/net/core/dev_api.c
@@ -0,0 +1,224 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#include <linux/netdevice.h>
+
+#include "dev.h"
+
+/**
+ * dev_change_name() - change name of a device
+ * @dev: device
+ * @newname: name (or format string) must be at least IFNAMSIZ
+ *
+ * Change name of a device, can pass format strings "eth%d".
+ * for wildcarding.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_name(struct net_device *dev, const char *newname)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_name(dev, newname);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+
+/**
+ * dev_set_alias() - change ifalias of a device
+ * @dev: device
+ * @alias: name up to IFALIASZ
+ * @len: limit of bytes to copy from info
+ *
+ * Set ifalias for a device.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_set_alias(struct net_device *dev, const char *alias, size_t len)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_alias(dev, alias, len);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_alias);
+
+/**
+ * dev_change_flags() - change device settings
+ * @dev: device
+ * @flags: device state flags
+ * @extack: netlink extended ack
+ *
+ * Change settings on device based state flags. The flags are
+ * in the userspace exported format.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_flags(struct net_device *dev, unsigned int flags,
+		     struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_flags(dev, flags, extack);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_change_flags);
+
+/**
+ * dev_set_group() - change group this device belongs to
+ * @dev: device
+ * @new_group: group this device should belong to
+ */
+void dev_set_group(struct net_device *dev, int new_group)
+{
+	netdev_lock_ops(dev);
+	netif_set_group(dev, new_group);
+	netdev_unlock_ops(dev);
+}
+
+int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			     struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_mac_address_user(dev, sa, extack);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_mac_address_user);
+
+/**
+ * dev_change_net_namespace() - move device to different nethost namespace
+ * @dev: device
+ * @net: network namespace
+ * @pat: If not NULL name pattern to try if the current device name
+ *       is already taken in the destination network namespace.
+ *
+ * This function shuts down a device interface and moves it
+ * to a new network namespace. On success 0 is returned, on
+ * a failure a netagive errno code is returned.
+ *
+ * Callers must hold the rtnl semaphore.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_net_namespace(struct net_device *dev, struct net *net,
+			     const char *pat)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_net_namespace(dev, net, pat, 0, NULL);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_change_net_namespace);
+
+/**
+ * dev_change_carrier() - change device carrier
+ * @dev: device
+ * @new_carrier: new value
+ *
+ * Change device carrier
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_carrier(struct net_device *dev, bool new_carrier)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_carrier(dev, new_carrier);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+
+/**
+ * dev_change_tx_queue_len() - change TX queue length of a netdevice
+ * @dev: device
+ * @new_len: new tx queue length
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_tx_queue_len(dev, new_len);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+
+/**
+ * dev_change_proto_down() - set carrier according to proto_down
+ * @dev: device
+ * @proto_down: new value
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_change_proto_down(struct net_device *dev, bool proto_down)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_change_proto_down(dev, proto_down);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+
+/**
+ * dev_open() - prepare an interface for use
+ * @dev: device to open
+ * @extack: netlink extended ack
+ *
+ * Takes a device from down to up state. The device's private open
+ * function is invoked and then the multicast lists are loaded. Finally
+ * the device is moved into the up state and a %NETDEV_UP message is
+ * sent to the netdev notifier chain.
+ *
+ * Calling this function on an active interface is a nop. On a failure
+ * a negative errno code is returned.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_open(struct net_device *dev, struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_open(dev, extack);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_open);
+
+/**
+ * dev_close() - shutdown an interface
+ * @dev: device to shutdown
+ *
+ * This function moves an active device into down state. A
+ * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device
+ * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier
+ * chain.
+ */
+void dev_close(struct net_device *dev)
+{
+	netdev_lock_ops(dev);
+	netif_close(dev);
+	netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(dev_close);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index b4612d3059704..9d539c9ce1a42 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2912,12 +2912,19 @@ static int do_set_master(struct net_device *dev, int ifindex,
 	const struct net_device_ops *ops;
 	int err;
 
+	/* Release the lower lock, the upper is responsible for locking
+	 * the lower if needed. None of the existing upper devices
+	 * use netdev instance lock, so don't grab it.
+	 */
+
 	if (upper_dev) {
 		if (upper_dev->ifindex == ifindex)
 			return 0;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_del_slave) {
+			netdev_unlock_ops(dev);
 			err = ops->ndo_del_slave(upper_dev, dev);
+			netdev_lock_ops(dev);
 			if (err)
 				return err;
 		} else {
@@ -2931,7 +2938,9 @@ static int do_set_master(struct net_device *dev, int ifindex,
 			return -EINVAL;
 		ops = upper_dev->netdev_ops;
 		if (ops->ndo_add_slave) {
+			netdev_unlock_ops(dev);
 			err = ops->ndo_add_slave(upper_dev, dev, extack);
+			netdev_lock_ops(dev);
 			if (err)
 				return err;
 		} else {
@@ -2981,7 +2990,7 @@ static int do_set_proto_down(struct net_device *dev,
 		if (pdreason[IFLA_PROTO_DOWN_REASON_MASK])
 			mask = nla_get_u32(pdreason[IFLA_PROTO_DOWN_REASON_MASK]);
 
-		dev_change_proto_down_reason(dev, mask, value);
+		netdev_change_proto_down_reason_locked(dev, mask, value);
 	}
 
 	if (nl_proto_down) {
@@ -2992,8 +3001,7 @@ static int do_set_proto_down(struct net_device *dev,
 			NL_SET_ERR_MSG(extack, "Cannot clear protodown, active reasons");
 			return -EBUSY;
 		}
-		err = dev_change_proto_down(dev,
-					    proto_down);
+		err = netif_change_proto_down(dev, proto_down);
 		if (err)
 			return err;
 	}
@@ -3013,6 +3021,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	char ifname[IFNAMSIZ];
 	int err;
 
+	netdev_lock_ops(dev);
+
 	err = validate_linkmsg(dev, tb, extack);
 	if (err < 0)
 		goto errout;
@@ -3028,7 +3038,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 
 		new_ifindex = nla_get_s32_default(tb[IFLA_NEW_IFINDEX], 0);
 
-		err = __dev_change_net_namespace(dev, tgt_net, pat, new_ifindex, extack);
+		err = netif_change_net_namespace(dev, tgt_net, pat,
+						 new_ifindex, extack);
 		if (err)
 			goto errout;
 
@@ -3078,7 +3089,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 		sa->sa_family = dev->type;
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		err = dev_set_mac_address_user(dev, sa, extack);
+		err = netif_set_mac_address_user(dev, sa, extack);
 		kfree(sa);
 		if (err)
 			goto errout;
@@ -3086,14 +3097,14 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (tb[IFLA_MTU]) {
-		err = dev_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
+		err = netif_set_mtu_ext(dev, nla_get_u32(tb[IFLA_MTU]), extack);
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
 	}
 
 	if (tb[IFLA_GROUP]) {
-		dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
+		netif_set_group(dev, nla_get_u32(tb[IFLA_GROUP]));
 		status |= DO_SETLINK_NOTIFY;
 	}
 
@@ -3103,15 +3114,15 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	 * requested.
 	 */
 	if (ifm->ifi_index > 0 && ifname[0]) {
-		err = dev_change_name(dev, ifname);
+		err = netif_change_name(dev, ifname);
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
 	}
 
 	if (tb[IFLA_IFALIAS]) {
-		err = dev_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
-				    nla_len(tb[IFLA_IFALIAS]));
+		err = netif_set_alias(dev, nla_data(tb[IFLA_IFALIAS]),
+				      nla_len(tb[IFLA_IFALIAS]));
 		if (err < 0)
 			goto errout;
 		status |= DO_SETLINK_NOTIFY;
@@ -3123,8 +3134,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (ifm->ifi_flags || ifm->ifi_change) {
-		err = dev_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
-				       extack);
+		err = netif_change_flags(dev, rtnl_dev_combine_flags(dev, ifm),
+					 extack);
 		if (err < 0)
 			goto errout;
 	}
@@ -3137,7 +3148,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	}
 
 	if (tb[IFLA_CARRIER]) {
-		err = dev_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
+		err = netif_change_carrier(dev, nla_get_u8(tb[IFLA_CARRIER]));
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -3146,7 +3157,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 	if (tb[IFLA_TXQLEN]) {
 		unsigned int value = nla_get_u32(tb[IFLA_TXQLEN]);
 
-		err = dev_change_tx_queue_len(dev, value);
+		err = netif_change_tx_queue_len(dev, value);
 		if (err)
 			goto errout;
 		status |= DO_SETLINK_MODIFIED;
@@ -3377,6 +3388,8 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 					     dev->name);
 	}
 
+	netdev_unlock_ops(dev);
+
 	return err;
 }
 
@@ -3810,6 +3823,8 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 		goto out;
 	}
 
+	netdev_lock_ops(dev);
+
 	err = rtnl_configure_link(dev, ifm, portid, nlh);
 	if (err < 0)
 		goto out_unregister;
@@ -3818,9 +3833,12 @@ static int rtnl_newlink_create(struct sk_buff *skb, struct ifinfomsg *ifm,
 		if (err)
 			goto out_unregister;
 	}
+
+	netdev_unlock_ops(dev);
 out:
 	return err;
 out_unregister:
+	netdev_unlock_ops(dev);
 	if (ops->newlink) {
 		LIST_HEAD(list_kill);
 

From ffb7ed19ac0a9fa9ea79af1d7b42c03a10da98a5 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:25 -0800
Subject: [PATCH 1724/2753] net: hold netdev instance lock during ioctl
 operations

Convert all ndo_eth_ioctl invocations to dev_eth_ioctl which does the
locking. Reflow some of the dev_siocxxx to drop else clause.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-8-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c |  9 ++---
 include/linux/netdevice.h       |  3 ++
 net/8021q/vlan_dev.c            |  4 +-
 net/core/dev.c                  |  4 +-
 net/core/dev_api.c              | 30 +++++++++++++++
 net/core/dev_ioctl.c            | 67 ++++++++++++++++++++-------------
 6 files changed, 80 insertions(+), 37 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index fe7072336e8fd..cd4afeb9ad42e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -855,7 +855,6 @@ static int bond_check_dev_link(struct bonding *bond,
 			       struct net_device *slave_dev, int reporting)
 {
 	const struct net_device_ops *slave_ops = slave_dev->netdev_ops;
-	int (*ioctl)(struct net_device *, struct ifreq *, int);
 	struct ifreq ifr;
 	struct mii_ioctl_data *mii;
 
@@ -871,8 +870,7 @@ static int bond_check_dev_link(struct bonding *bond,
 			BMSR_LSTATUS : 0;
 
 	/* Ethtool can't be used, fallback to MII ioctls. */
-	ioctl = slave_ops->ndo_eth_ioctl;
-	if (ioctl) {
+	if (slave_ops->ndo_eth_ioctl) {
 		/* TODO: set pointer to correct ioctl on a per team member
 		 *       bases to make this more efficient. that is, once
 		 *       we determine the correct ioctl, we will always
@@ -888,9 +886,10 @@ static int bond_check_dev_link(struct bonding *bond,
 		/* Yes, the mii is overlaid on the ifreq.ifr_ifru */
 		strscpy_pad(ifr.ifr_name, slave_dev->name, IFNAMSIZ);
 		mii = if_mii(&ifr);
-		if (ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
+
+		if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIPHY) == 0) {
 			mii->reg_num = MII_BMSR;
-			if (ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
+			if (dev_eth_ioctl(slave_dev, &ifr, SIOCGMIIREG) == 0)
 				return mii->val_out & BMSR_LSTATUS;
 		}
 	}
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index be3d09b61e959..8d243c0ec39d1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4229,6 +4229,8 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg);
 int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 		void __user *data, bool *need_copyout);
 int dev_ifconf(struct net *net, struct ifconf __user *ifc);
+int dev_eth_ioctl(struct net_device *dev,
+		  struct ifreq *ifr, unsigned int cmd);
 int generic_hwtstamp_get_lower(struct net_device *dev,
 			       struct kernel_hwtstamp_config *kernel_cfg);
 int generic_hwtstamp_set_lower(struct net_device *dev,
@@ -4251,6 +4253,7 @@ int netif_change_net_namespace(struct net_device *dev, struct net *net,
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
 			     const char *pat);
 int __dev_set_mtu(struct net_device *, int);
+int netif_set_mtu(struct net_device *dev, int new_mtu);
 int dev_set_mtu(struct net_device *, int);
 int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 			      struct netlink_ext_ack *extack);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 91d134961357c..ee32834007168 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -377,7 +377,6 @@ static int vlan_hwtstamp_set(struct net_device *dev,
 static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
-	const struct net_device_ops *ops = real_dev->netdev_ops;
 	struct ifreq ifrr;
 	int err = -EOPNOTSUPP;
 
@@ -388,8 +387,7 @@ static int vlan_dev_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 	case SIOCGMIIPHY:
 	case SIOCGMIIREG:
 	case SIOCSMIIREG:
-		if (netif_device_present(real_dev) && ops->ndo_eth_ioctl)
-			err = ops->ndo_eth_ioctl(real_dev, &ifrr, cmd);
+		err = dev_eth_ioctl(real_dev, &ifrr, cmd);
 		break;
 	}
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 39b214fb462e4..97a4fc0889d34 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9522,7 +9522,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 	return err;
 }
 
-int dev_set_mtu(struct net_device *dev, int new_mtu)
+int netif_set_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netlink_ext_ack extack;
 	int err;
@@ -9533,7 +9533,7 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 		net_err_ratelimited("%s: %s\n", dev->name, extack._msg);
 	return err;
 }
-EXPORT_SYMBOL(dev_set_mtu);
+EXPORT_SYMBOL(netif_set_mtu);
 
 int netif_change_tx_queue_len(struct net_device *dev, unsigned long new_len)
 {
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 21584f57e050d..059413d9ef9d8 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -222,3 +222,33 @@ void dev_close(struct net_device *dev)
 	netdev_unlock_ops(dev);
 }
 EXPORT_SYMBOL(dev_close);
+
+int dev_eth_ioctl(struct net_device *dev,
+		  struct ifreq *ifr, unsigned int cmd)
+{
+	const struct net_device_ops *ops = dev->netdev_ops;
+	int ret = -ENODEV;
+
+	if (!ops->ndo_eth_ioctl)
+		return -EOPNOTSUPP;
+
+	netdev_lock_ops(dev);
+	if (netif_device_present(dev))
+		ret = ops->ndo_eth_ioctl(dev, ifr, cmd);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_eth_ioctl);
+
+int dev_set_mtu(struct net_device *dev, int new_mtu)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_mtu(dev, new_mtu);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_mtu);
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 4c2098ac9d724..d9f3505931210 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -110,7 +110,7 @@ static int dev_getifmap(struct net_device *dev, struct ifreq *ifr)
 	return 0;
 }
 
-static int dev_setifmap(struct net_device *dev, struct ifreq *ifr)
+static int netif_setifmap(struct net_device *dev, struct ifreq *ifr)
 {
 	struct compat_ifmap *cifmap = (struct compat_ifmap *)&ifr->ifr_map;
 
@@ -240,20 +240,6 @@ int net_hwtstamp_validate(const struct kernel_hwtstamp_config *cfg)
 	return 0;
 }
 
-static int dev_eth_ioctl(struct net_device *dev,
-			 struct ifreq *ifr, unsigned int cmd)
-{
-	const struct net_device_ops *ops = dev->netdev_ops;
-
-	if (!ops->ndo_eth_ioctl)
-		return -EOPNOTSUPP;
-
-	if (!netif_device_present(dev))
-		return -ENODEV;
-
-	return ops->ndo_eth_ioctl(dev, ifr, cmd);
-}
-
 /**
  * dev_get_hwtstamp_phylib() - Get hardware timestamping settings of NIC
  *	or of attached phylib PHY
@@ -305,7 +291,9 @@ static int dev_get_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 		return -ENODEV;
 
 	kernel_cfg.ifr = ifr;
+	netdev_lock_ops(dev);
 	err = dev_get_hwtstamp_phylib(dev, &kernel_cfg);
+	netdev_unlock_ops(dev);
 	if (err)
 		return err;
 
@@ -429,7 +417,9 @@ static int dev_set_hwtstamp(struct net_device *dev, struct ifreq *ifr)
 	if (!netif_device_present(dev))
 		return -ENODEV;
 
+	netdev_lock_ops(dev);
 	err = dev_set_hwtstamp_phylib(dev, &kernel_cfg, &extack);
+	netdev_unlock_ops(dev);
 	if (err)
 		return err;
 
@@ -504,10 +494,14 @@ static int dev_siocbond(struct net_device *dev,
 	const struct net_device_ops *ops = dev->netdev_ops;
 
 	if (ops->ndo_siocbond) {
+		int ret = -ENODEV;
+
+		netdev_lock_ops(dev);
 		if (netif_device_present(dev))
-			return ops->ndo_siocbond(dev, ifr, cmd);
-		else
-			return -ENODEV;
+			ret = ops->ndo_siocbond(dev, ifr, cmd);
+		netdev_unlock_ops(dev);
+
+		return ret;
 	}
 
 	return -EOPNOTSUPP;
@@ -519,10 +513,14 @@ static int dev_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
 	const struct net_device_ops *ops = dev->netdev_ops;
 
 	if (ops->ndo_siocdevprivate) {
+		int ret = -ENODEV;
+
+		netdev_lock_ops(dev);
 		if (netif_device_present(dev))
-			return ops->ndo_siocdevprivate(dev, ifr, data, cmd);
-		else
-			return -ENODEV;
+			ret = ops->ndo_siocdevprivate(dev, ifr, data, cmd);
+		netdev_unlock_ops(dev);
+
+		return ret;
 	}
 
 	return -EOPNOTSUPP;
@@ -533,10 +531,14 @@ static int dev_siocwandev(struct net_device *dev, struct if_settings *ifs)
 	const struct net_device_ops *ops = dev->netdev_ops;
 
 	if (ops->ndo_siocwandev) {
+		int ret = -ENODEV;
+
+		netdev_lock_ops(dev);
 		if (netif_device_present(dev))
-			return ops->ndo_siocwandev(dev, ifs);
-		else
-			return -ENODEV;
+			ret = ops->ndo_siocwandev(dev, ifs);
+		netdev_unlock_ops(dev);
+
+		return ret;
 	}
 
 	return -EOPNOTSUPP;
@@ -580,11 +582,16 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 		memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
 		       min(sizeof(ifr->ifr_hwaddr.sa_data_min),
 			   (size_t)dev->addr_len));
+		netdev_lock_ops(dev);
 		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+		netdev_unlock_ops(dev);
 		return 0;
 
 	case SIOCSIFMAP:
-		return dev_setifmap(dev, ifr);
+		netdev_lock_ops(dev);
+		err = netif_setifmap(dev, ifr);
+		netdev_unlock_ops(dev);
+		return err;
 
 	case SIOCADDMULTI:
 		if (!ops->ndo_set_rx_mode ||
@@ -592,7 +599,10 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 			return -EINVAL;
 		if (!netif_device_present(dev))
 			return -ENODEV;
-		return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
+		netdev_lock_ops(dev);
+		err = dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
+		netdev_unlock_ops(dev);
+		return err;
 
 	case SIOCDELMULTI:
 		if (!ops->ndo_set_rx_mode ||
@@ -600,7 +610,10 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 			return -EINVAL;
 		if (!netif_device_present(dev))
 			return -ENODEV;
-		return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
+		netdev_lock_ops(dev);
+		err = dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
+		netdev_unlock_ops(dev);
+		return err;
 
 	case SIOCSIFTXQLEN:
 		if (ifr->ifr_qlen < 0)

From ad7c7b2172c388818a111455643491d75f535e90 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:26 -0800
Subject: [PATCH 1725/2753] net: hold netdev instance lock during sysfs
 operations

Most of them are already covered by the converted dev_xxx APIs.
Add the locking wrappers for the remaining ones.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-9-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c |  7 +++-
 include/linux/netdevice.h       |  4 ++
 net/core/dev.c                  | 58 ++++++-----------------------
 net/core/dev_api.c              | 65 +++++++++++++++++++++++++++++++++
 net/core/net-sysfs.c            |  2 +
 5 files changed, 88 insertions(+), 48 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index cd4afeb9ad42e..cf0b02720dd82 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2644,10 +2644,13 @@ static int __bond_release_one(struct net_device *bond_dev,
 		dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, NULL);
 	}
 
-	if (unregister)
+	if (unregister) {
+		netdev_lock_ops(slave_dev);
 		__dev_set_mtu(slave_dev, slave->original_mtu);
-	else
+		netdev_unlock_ops(slave_dev);
+	} else {
 		dev_set_mtu(slave_dev, slave->original_mtu);
+	}
 
 	if (!netif_is_bond_master(slave_dev))
 		slave_dev->priv_flags &= ~IFF_BONDING;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8d243c0ec39d1..c61b128095881 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3382,6 +3382,7 @@ void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
 int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		 void *type_data);
+void netif_disable_lro(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
@@ -4257,6 +4258,8 @@ int netif_set_mtu(struct net_device *dev, int new_mtu);
 int dev_set_mtu(struct net_device *, int);
 int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 			      struct netlink_ext_ack *extack);
+int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			  struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
 int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
@@ -5016,6 +5019,7 @@ static inline void __dev_mc_unsync(struct net_device *dev,
 /* Functions used for secondary unicast and multicast support */
 void dev_set_rx_mode(struct net_device *dev);
 int dev_set_promiscuity(struct net_device *dev, int inc);
+int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
 int dev_set_allmulti(struct net_device *dev, int inc);
 void netdev_state_change(struct net_device *dev);
 void __netdev_notify_peers(struct net_device *dev);
diff --git a/net/core/dev.c b/net/core/dev.c
index 97a4fc0889d34..121c0449f87f7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1757,15 +1757,7 @@ int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
 }
 EXPORT_SYMBOL(dev_setup_tc);
 
-/**
- *	dev_disable_lro - disable Large Receive Offload on a device
- *	@dev: device
- *
- *	Disable Large Receive Offload (LRO) on a net device.  Must be
- *	called under RTNL.  This is needed if received packets may be
- *	forwarded to another interface.
- */
-void dev_disable_lro(struct net_device *dev)
+void netif_disable_lro(struct net_device *dev)
 {
 	struct net_device *lower_dev;
 	struct list_head *iter;
@@ -1776,10 +1768,12 @@ void dev_disable_lro(struct net_device *dev)
 	if (unlikely(dev->features & NETIF_F_LRO))
 		netdev_WARN(dev, "failed to disable LRO!\n");
 
-	netdev_for_each_lower_dev(dev, lower_dev, iter)
-		dev_disable_lro(lower_dev);
+	netdev_for_each_lower_dev(dev, lower_dev, iter) {
+		netdev_lock_ops(lower_dev);
+		netif_disable_lro(lower_dev);
+		netdev_unlock_ops(lower_dev);
+	}
 }
-EXPORT_SYMBOL(dev_disable_lro);
 
 /**
  *	dev_disable_gro_hw - disable HW Generic Receive Offload on a device
@@ -6038,7 +6032,7 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp)
 			static_branch_dec(&generic_xdp_needed_key);
 		} else if (new && !old) {
 			static_branch_inc(&generic_xdp_needed_key);
-			dev_disable_lro(dev);
+			netif_disable_lro(dev);
 			dev_disable_gro_hw(dev);
 		}
 		break;
@@ -9210,7 +9204,7 @@ int dev_set_promiscuity(struct net_device *dev, int inc)
 }
 EXPORT_SYMBOL(dev_set_promiscuity);
 
-static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify)
+int netif_set_allmulti(struct net_device *dev, int inc, bool notify)
 {
 	unsigned int old_flags = dev->flags, old_gflags = dev->gflags;
 	unsigned int allmulti, flags;
@@ -9245,25 +9239,6 @@ static int __dev_set_allmulti(struct net_device *dev, int inc, bool notify)
 	return 0;
 }
 
-/**
- *	dev_set_allmulti	- update allmulti count on a device
- *	@dev: device
- *	@inc: modifier
- *
- *	Add or remove reception of all multicast frames to a device. While the
- *	count in the device remains above zero the interface remains listening
- *	to all interfaces. Once it hits zero the device reverts back to normal
- *	filtering operation. A negative @inc value is used to drop the counter
- *	when releasing a resource needing all multicasts.
- *	Return 0 if successful or a negative errno code on error.
- */
-
-int dev_set_allmulti(struct net_device *dev, int inc)
-{
-	return __dev_set_allmulti(dev, inc, true);
-}
-EXPORT_SYMBOL(dev_set_allmulti);
-
 /*
  *	Upload unicast and multicast address lists to device and
  *	configure RX filtering. When the device doesn't support unicast
@@ -9396,7 +9371,7 @@ int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		int inc = (flags & IFF_ALLMULTI) ? 1 : -1;
 
 		dev->gflags ^= IFF_ALLMULTI;
-		__dev_set_allmulti(dev, inc, false);
+		netif_set_allmulti(dev, inc, false);
 	}
 
 	return ret;
@@ -9588,16 +9563,8 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 }
 EXPORT_SYMBOL(dev_pre_changeaddr_notify);
 
-/**
- *	dev_set_mac_address - Change Media Access Control Address
- *	@dev: device
- *	@sa: new address
- *	@extack: netlink extended ack
- *
- *	Change the hardware (MAC) address of the device
- */
-int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
-			struct netlink_ext_ack *extack)
+int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			  struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	int err;
@@ -9621,7 +9588,6 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 	add_device_randomness(dev->dev_addr, dev->addr_len);
 	return 0;
 }
-EXPORT_SYMBOL(dev_set_mac_address);
 
 DECLARE_RWSEM(dev_addr_sem);
 
@@ -9631,7 +9597,7 @@ int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 	int ret;
 
 	down_write(&dev_addr_sem);
-	ret = dev_set_mac_address(dev, sa, extack);
+	ret = netif_set_mac_address(dev, sa, extack);
 	up_write(&dev_addr_sem);
 	return ret;
 }
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 059413d9ef9d8..7bd667b34b808 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -252,3 +252,68 @@ int dev_set_mtu(struct net_device *dev, int new_mtu)
 	return ret;
 }
 EXPORT_SYMBOL(dev_set_mtu);
+
+/**
+ * dev_disable_lro() - disable Large Receive Offload on a device
+ * @dev: device
+ *
+ * Disable Large Receive Offload (LRO) on a net device.  Must be
+ * called under RTNL.  This is needed if received packets may be
+ * forwarded to another interface.
+ */
+void dev_disable_lro(struct net_device *dev)
+{
+	netdev_lock_ops(dev);
+	netif_disable_lro(dev);
+	netdev_unlock_ops(dev);
+}
+EXPORT_SYMBOL(dev_disable_lro);
+
+/**
+ * dev_set_allmulti() - update allmulti count on a device
+ * @dev: device
+ * @inc: modifier
+ *
+ * Add or remove reception of all multicast frames to a device. While the
+ * count in the device remains above zero the interface remains listening
+ * to all interfaces. Once it hits zero the device reverts back to normal
+ * filtering operation. A negative @inc value is used to drop the counter
+ * when releasing a resource needing all multicasts.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+
+int dev_set_allmulti(struct net_device *dev, int inc)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_allmulti(dev, inc, true);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_allmulti);
+
+/**
+ * dev_set_mac_address() - change Media Access Control Address
+ * @dev: device
+ * @sa: new address
+ * @extack: netlink extended ack
+ *
+ * Change the hardware (MAC) address of the device
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+			struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_mac_address(dev, sa, extack);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_mac_address);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 8d9dc048a548b..27eea34d1b416 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1483,8 +1483,10 @@ static ssize_t tx_maxrate_store(struct kobject *kobj, struct attribute *attr,
 		return err;
 
 	err = -EOPNOTSUPP;
+	netdev_lock_ops(dev);
 	if (dev->netdev_ops->ndo_set_tx_maxrate)
 		err = dev->netdev_ops->ndo_set_tx_maxrate(dev, index, rate);
+	netdev_unlock_ops(dev);
 
 	if (!err) {
 		queue->tx_maxrate = rate;

From 97246d6d21c21fb4c5235770a21855e457096a96 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:27 -0800
Subject: [PATCH 1726/2753] net: hold netdev instance lock during ndo_bpf

Cover the paths that come via bpf system call and XSK bind.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-10-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  1 +
 kernel/bpf/offload.c      |  6 ++++--
 net/core/dev.c            | 13 +++++++++++--
 net/core/dev_api.c        | 12 ++++++++++++
 net/xdp/xsk.c             |  3 +++
 net/xdp/xsk_buff_pool.c   |  2 ++
 6 files changed, 33 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c61b128095881..ca9c09dab14e6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4277,6 +4277,7 @@ struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u8 dev_xdp_prog_count(struct net_device *dev);
+int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
 u8 dev_xdp_sb_prog_count(struct net_device *dev);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 1a4fec330eaac..a10153c3be2df 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -528,10 +528,10 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&offmap->map, attr);
-
 	rtnl_lock();
-	down_write(&bpf_devs_lock);
 	offmap->netdev = __dev_get_by_index(net, attr->map_ifindex);
+	netdev_lock_ops(offmap->netdev);
+	down_write(&bpf_devs_lock);
 	err = bpf_dev_offload_check(offmap->netdev);
 	if (err)
 		goto err_unlock;
@@ -548,12 +548,14 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 
 	list_add_tail(&offmap->offloads, &ondev->maps);
 	up_write(&bpf_devs_lock);
+	netdev_unlock_ops(offmap->netdev);
 	rtnl_unlock();
 
 	return &offmap->map;
 
 err_unlock:
 	up_write(&bpf_devs_lock);
+	netdev_unlock_ops(offmap->netdev);
 	rtnl_unlock();
 	bpf_map_area_free(offmap);
 	return ERR_PTR(err);
diff --git a/net/core/dev.c b/net/core/dev.c
index 121c0449f87f7..404047d4d9432 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9852,7 +9852,7 @@ u8 dev_xdp_sb_prog_count(struct net_device *dev)
 	return count;
 }
 
-int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
+int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 {
 	if (!dev->netdev_ops->ndo_bpf)
 		return -EOPNOTSUPP;
@@ -9872,7 +9872,6 @@ int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
 
 	return dev->netdev_ops->ndo_bpf(dev, bpf);
 }
-EXPORT_SYMBOL_GPL(dev_xdp_propagate);
 
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
@@ -9902,6 +9901,8 @@ static int dev_xdp_install(struct net_device *dev, enum bpf_xdp_mode mode,
 	struct netdev_bpf xdp;
 	int err;
 
+	netdev_ops_assert_locked(dev);
+
 	if (dev->cfg->hds_config == ETHTOOL_TCP_DATA_SPLIT_ENABLED &&
 	    prog && !prog->aux->xdp_has_frags) {
 		NL_SET_ERR_MSG(extack, "unable to install XDP to device using tcp-data-split");
@@ -10134,7 +10135,9 @@ static void bpf_xdp_link_release(struct bpf_link *link)
 	 * already NULL, in which case link was already auto-detached
 	 */
 	if (xdp_link->dev) {
+		netdev_lock_ops(xdp_link->dev);
 		WARN_ON(dev_xdp_detach_link(xdp_link->dev, NULL, xdp_link));
+		netdev_unlock_ops(xdp_link->dev);
 		xdp_link->dev = NULL;
 	}
 
@@ -10216,10 +10219,12 @@ static int bpf_xdp_link_update(struct bpf_link *link, struct bpf_prog *new_prog,
 		goto out_unlock;
 	}
 
+	netdev_lock_ops(xdp_link->dev);
 	mode = dev_xdp_mode(xdp_link->dev, xdp_link->flags);
 	bpf_op = dev_xdp_bpf_op(xdp_link->dev, mode);
 	err = dev_xdp_install(xdp_link->dev, mode, bpf_op, NULL,
 			      xdp_link->flags, new_prog);
+	netdev_unlock_ops(xdp_link->dev);
 	if (err)
 		goto out_unlock;
 
@@ -11005,7 +11010,9 @@ int register_netdevice(struct net_device *dev)
 	if (ret)
 		goto err_uninit_notify;
 
+	netdev_lock_ops(dev);
 	__netdev_update_features(dev);
+	netdev_unlock_ops(dev);
 
 	/*
 	 *	Default initial state at registry is that the
@@ -11945,7 +11952,9 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		/* Shutdown queueing discipline. */
 		dev_shutdown(dev);
 		dev_tcx_uninstall(dev);
+		netdev_lock_ops(dev);
 		dev_xdp_uninstall(dev);
+		netdev_unlock_ops(dev);
 		bpf_dev_bound_netdev_unregister(dev);
 		dev_memory_provider_uninstall(dev);
 
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 7bd667b34b808..98db990ce21ce 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -317,3 +317,15 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 	return ret;
 }
 EXPORT_SYMBOL(dev_set_mac_address);
+
+int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_xdp_propagate(dev, bpf);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_xdp_propagate);
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index 84bf9f1d4bf21..f864e5d70b40a 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -1181,6 +1181,8 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		goto out_release;
 	}
 
+	netdev_lock_ops(dev);
+
 	if (!xs->rx && !xs->tx) {
 		err = -EINVAL;
 		goto out_unlock;
@@ -1315,6 +1317,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len)
 		smp_wmb();
 		WRITE_ONCE(xs->state, XSK_BOUND);
 	}
+	netdev_unlock_ops(dev);
 out_release:
 	mutex_unlock(&xs->mutex);
 	rtnl_unlock();
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index c263fb7a68dc3..0e6ca568fdeeb 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 
+#include <linux/netdevice.h>
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
 #include <net/xdp_sock_drv.h>
@@ -219,6 +220,7 @@ int xp_assign_dev(struct xsk_buff_pool *pool,
 	bpf.xsk.pool = pool;
 	bpf.xsk.queue_id = queue_id;
 
+	netdev_ops_assert_locked(netdev);
 	err = netdev->netdev_ops->ndo_bpf(netdev, &bpf);
 	if (err)
 		goto err_unreg_pool;

From 2bcf4772e45adb00649a4e9cbff14b08a144f9e3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 5 Mar 2025 08:37:28 -0800
Subject: [PATCH 1727/2753] net: ethtool: try to protect all callback with
 netdev instance lock

Protect all ethtool callbacks and PHY related state with the netdev
instance lock, for drivers which want / need to have their ops
instance-locked. Basically take the lock everywhere we take rtnl_lock.
It was tempting to take the lock in ethnl_ops_begin(), but turns
out we actually nest those calls (when generating notifications).

Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-11-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/ethtool.c |  2 --
 net/dsa/conduit.c               | 16 +++++++++++++++-
 net/ethtool/cabletest.c         | 20 ++++++++++++--------
 net/ethtool/cmis_fw_update.c    |  7 ++++++-
 net/ethtool/features.c          |  6 ++++--
 net/ethtool/ioctl.c             |  6 ++++++
 net/ethtool/module.c            |  8 +++++---
 net/ethtool/netlink.c           | 12 ++++++++++++
 net/ethtool/phy.c               | 20 ++++++++++++++------
 net/ethtool/rss.c               |  2 ++
 net/ethtool/tsinfo.c            |  9 ++++++---
 11 files changed, 82 insertions(+), 26 deletions(-)

diff --git a/drivers/net/netdevsim/ethtool.c b/drivers/net/netdevsim/ethtool.c
index 7ab358616e035..4d191a3293c74 100644
--- a/drivers/net/netdevsim/ethtool.c
+++ b/drivers/net/netdevsim/ethtool.c
@@ -107,10 +107,8 @@ nsim_set_channels(struct net_device *dev, struct ethtool_channels *ch)
 	struct netdevsim *ns = netdev_priv(dev);
 	int err;
 
-	netdev_lock(dev);
 	err = netif_set_real_num_queues(dev, ch->combined_count,
 					ch->combined_count);
-	netdev_unlock(dev);
 	if (err)
 		return err;
 
diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c
index 3dfdb3cb47dc7..f21bb2551bed2 100644
--- a/net/dsa/conduit.c
+++ b/net/dsa/conduit.c
@@ -26,7 +26,9 @@ static int dsa_conduit_get_regs_len(struct net_device *dev)
 	int len;
 
 	if (ops->get_regs_len) {
+		netdev_lock_ops(dev);
 		len = ops->get_regs_len(dev);
+		netdev_unlock_ops(dev);
 		if (len < 0)
 			return len;
 		ret += len;
@@ -57,11 +59,15 @@ static void dsa_conduit_get_regs(struct net_device *dev,
 	int len;
 
 	if (ops->get_regs_len && ops->get_regs) {
+		netdev_lock_ops(dev);
 		len = ops->get_regs_len(dev);
-		if (len < 0)
+		if (len < 0) {
+			netdev_unlock_ops(dev);
 			return;
+		}
 		regs->len = len;
 		ops->get_regs(dev, regs, data);
+		netdev_unlock_ops(dev);
 		data += regs->len;
 	}
 
@@ -91,8 +97,10 @@ static void dsa_conduit_get_ethtool_stats(struct net_device *dev,
 	int count = 0;
 
 	if (ops->get_sset_count && ops->get_ethtool_stats) {
+		netdev_lock_ops(dev);
 		count = ops->get_sset_count(dev, ETH_SS_STATS);
 		ops->get_ethtool_stats(dev, stats, data);
+		netdev_unlock_ops(dev);
 	}
 
 	if (ds->ops->get_ethtool_stats)
@@ -114,8 +122,10 @@ static void dsa_conduit_get_ethtool_phy_stats(struct net_device *dev,
 		if (count >= 0)
 			phy_ethtool_get_stats(dev->phydev, stats, data);
 	} else if (ops->get_sset_count && ops->get_ethtool_phy_stats) {
+		netdev_lock_ops(dev);
 		count = ops->get_sset_count(dev, ETH_SS_PHY_STATS);
 		ops->get_ethtool_phy_stats(dev, stats, data);
+		netdev_unlock_ops(dev);
 	}
 
 	if (count < 0)
@@ -132,11 +142,13 @@ static int dsa_conduit_get_sset_count(struct net_device *dev, int sset)
 	struct dsa_switch *ds = cpu_dp->ds;
 	int count = 0;
 
+	netdev_lock_ops(dev);
 	if (sset == ETH_SS_PHY_STATS && dev->phydev &&
 	    !ops->get_ethtool_phy_stats)
 		count = phy_ethtool_get_sset_count(dev->phydev);
 	else if (ops->get_sset_count)
 		count = ops->get_sset_count(dev, sset);
+	netdev_unlock_ops(dev);
 
 	if (count < 0)
 		count = 0;
@@ -163,6 +175,7 @@ static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset,
 	/* We do not want to be NULL-terminated, since this is a prefix */
 	pfx[sizeof(pfx) - 1] = '_';
 
+	netdev_lock_ops(dev);
 	if (stringset == ETH_SS_PHY_STATS && dev->phydev &&
 	    !ops->get_ethtool_phy_stats) {
 		mcount = phy_ethtool_get_sset_count(dev->phydev);
@@ -176,6 +189,7 @@ static void dsa_conduit_get_strings(struct net_device *dev, uint32_t stringset,
 			mcount = 0;
 		ops->get_strings(dev, stringset, data);
 	}
+	netdev_unlock_ops(dev);
 
 	if (ds->ops->get_strings) {
 		ndata = data + mcount * len;
diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index f22051f33868a..d4a79310b33f7 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -72,23 +72,24 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	phydev = ethnl_req_get_phydev(&req_info,
 				      tb[ETHTOOL_A_CABLE_TEST_HEADER],
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
-		goto out_rtnl;
+		goto out_unlock;
 	}
 
 	ops = ethtool_phy_ops;
 	if (!ops || !ops->start_cable_test) {
 		ret = -EOPNOTSUPP;
-		goto out_rtnl;
+		goto out_unlock;
 	}
 
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_unlock;
 
 	ret = ops->start_cable_test(phydev, info->extack);
 
@@ -97,7 +98,8 @@ int ethnl_act_cable_test(struct sk_buff *skb, struct genl_info *info)
 	if (!ret)
 		ethnl_cable_test_started(phydev, ETHTOOL_MSG_CABLE_TEST_NTF);
 
-out_rtnl:
+out_unlock:
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
 	return ret;
@@ -339,23 +341,24 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		goto out_dev_put;
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	phydev = ethnl_req_get_phydev(&req_info,
 				      tb[ETHTOOL_A_CABLE_TEST_TDR_HEADER],
 				      info->extack);
 	if (IS_ERR_OR_NULL(phydev)) {
 		ret = -EOPNOTSUPP;
-		goto out_rtnl;
+		goto out_unlock;
 	}
 
 	ops = ethtool_phy_ops;
 	if (!ops || !ops->start_cable_test_tdr) {
 		ret = -EOPNOTSUPP;
-		goto out_rtnl;
+		goto out_unlock;
 	}
 
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_unlock;
 
 	ret = ops->start_cable_test_tdr(phydev, info->extack, &cfg);
 
@@ -365,7 +368,8 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info)
 		ethnl_cable_test_started(phydev,
 					 ETHTOOL_MSG_CABLE_TEST_TDR_NTF);
 
-out_rtnl:
+out_unlock:
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 out_dev_put:
 	ethnl_parse_header_dev_put(&req_info);
diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c
index 48aef6220f009..946830af3e7cc 100644
--- a/net/ethtool/cmis_fw_update.c
+++ b/net/ethtool/cmis_fw_update.c
@@ -418,8 +418,13 @@ cmis_fw_update_commit_image(struct ethtool_cmis_cdb *cdb,
 static int cmis_fw_update_reset(struct net_device *dev)
 {
 	__u32 reset_data = ETH_RESET_PHY;
+	int ret;
 
-	return dev->ethtool_ops->reset(dev, &reset_data);
+	netdev_lock_ops(dev);
+	ret = dev->ethtool_ops->reset(dev, &reset_data);
+	netdev_unlock_ops(dev);
+
+	return ret;
 }
 
 void
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index b6cb101d7f19e..ccffd64d5a879 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -234,9 +234,10 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_unlock;
 	ethnl_features_to_bitmap(old_active, dev->features);
 	ethnl_features_to_bitmap(old_wanted, dev->wanted_features);
 	ret = ethnl_parse_bitset(req_wanted, req_mask, NETDEV_FEATURE_COUNT,
@@ -286,7 +287,8 @@ int ethnl_set_features(struct sk_buff *skb, struct genl_info *info)
 
 out_ops:
 	ethnl_ops_complete(dev);
-out_rtnl:
+out_unlock:
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
 	return ret;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index e95b41f40cace..496a2774100c6 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -2317,6 +2317,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 	 */
 	busy = true;
 	netdev_hold(dev, &dev_tracker, GFP_KERNEL);
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 
 	if (rc == 0) {
@@ -2331,8 +2332,10 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 
 		do {
 			rtnl_lock();
+			netdev_lock_ops(dev);
 			rc = ops->set_phys_id(dev,
 				    (i++ & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON);
+			netdev_unlock_ops(dev);
 			rtnl_unlock();
 			if (rc)
 				break;
@@ -2341,6 +2344,7 @@ static int ethtool_phys_id(struct net_device *dev, void __user *useraddr)
 	}
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	netdev_put(dev, &dev_tracker);
 	busy = false;
 
@@ -3140,6 +3144,7 @@ __dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr,
 			return -EPERM;
 	}
 
+	netdev_lock_ops(dev);
 	if (dev->dev.parent)
 		pm_runtime_get_sync(dev->dev.parent);
 
@@ -3373,6 +3378,7 @@ __dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr,
 out:
 	if (dev->dev.parent)
 		pm_runtime_put(dev->dev.parent);
+	netdev_unlock_ops(dev);
 
 	return rc;
 }
diff --git a/net/ethtool/module.c b/net/ethtool/module.c
index 6988e07bdcd6d..d3d2e135e45eb 100644
--- a/net/ethtool/module.c
+++ b/net/ethtool/module.c
@@ -419,19 +419,21 @@ int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	ret = ethnl_ops_begin(dev);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_unlock;
 
 	ret = ethnl_module_fw_flash_validate(dev, info->extack);
 	if (ret < 0)
-		goto out_rtnl;
+		goto out_unlock;
 
 	ret = module_flash_fw(dev, tb, skb, info);
 
 	ethnl_ops_complete(dev);
 
-out_rtnl:
+out_unlock:
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info);
 	return ret;
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index b4c45207fa32e..dee36f5cc2287 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -90,6 +90,8 @@ int ethnl_ops_begin(struct net_device *dev)
 	if (dev->dev.parent)
 		pm_runtime_get_sync(dev->dev.parent);
 
+	netdev_ops_assert_locked(dev);
+
 	if (!netif_device_present(dev) ||
 	    dev->reg_state >= NETREG_UNREGISTERING) {
 		ret = -ENODEV;
@@ -490,7 +492,11 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	ethnl_init_reply_data(reply_data, ops, req_info->dev);
 
 	rtnl_lock();
+	if (req_info->dev)
+		netdev_lock_ops(req_info->dev);
 	ret = ops->prepare_data(req_info, reply_data, info);
+	if (req_info->dev)
+		netdev_unlock_ops(req_info->dev);
 	rtnl_unlock();
 	if (ret < 0)
 		goto err_cleanup;
@@ -548,7 +554,9 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 
 	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
 	rtnl_lock();
+	netdev_lock_ops(ctx->req_info->dev);
 	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info);
+	netdev_unlock_ops(ctx->req_info->dev);
 	rtnl_unlock();
 	if (ret < 0)
 		goto out;
@@ -693,6 +701,7 @@ static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info)
 	dev = req_info.dev;
 
 	rtnl_lock();
+	netdev_lock_ops(dev);
 	dev->cfg_pending = kmemdup(dev->cfg, sizeof(*dev->cfg),
 				   GFP_KERNEL_ACCOUNT);
 	if (!dev->cfg_pending) {
@@ -720,6 +729,7 @@ static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info)
 	kfree(dev->cfg_pending);
 out_tie_cfg:
 	dev->cfg_pending = dev->cfg;
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 out_dev:
 	ethnl_parse_header_dev_put(&req_info);
@@ -777,6 +787,8 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd,
 	req_info->dev = dev;
 	req_info->flags |= ETHTOOL_FLAG_COMPACT_BITSETS;
 
+	netdev_ops_assert_locked(dev);
+
 	ethnl_init_reply_data(reply_data, ops, dev);
 	ret = ops->prepare_data(req_info, reply_data, &info);
 	if (ret < 0)
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index ed8f690f6bac8..2b428bc80c9b9 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -158,18 +158,19 @@ int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
 		return ret;
 
 	rtnl_lock();
+	netdev_lock_ops(req_info.base.dev);
 
 	ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack);
 	if (ret < 0)
-		goto err_unlock_rtnl;
+		goto err_unlock;
 
 	/* No PHY, return early */
 	if (!req_info.pdn)
-		goto err_unlock_rtnl;
+		goto err_unlock;
 
 	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
 	if (ret < 0)
-		goto err_unlock_rtnl;
+		goto err_unlock;
 	reply_len = ret + ethnl_reply_header_size();
 
 	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
@@ -178,13 +179,14 @@ int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
 				info, &reply_payload);
 	if (!rskb) {
 		ret = -ENOMEM;
-		goto err_unlock_rtnl;
+		goto err_unlock;
 	}
 
 	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
 	if (ret)
 		goto err_free_msg;
 
+	netdev_unlock_ops(req_info.base.dev);
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info.base);
 	genlmsg_end(rskb, reply_payload);
@@ -193,7 +195,8 @@ int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
 
 err_free_msg:
 	nlmsg_free(rskb);
-err_unlock_rtnl:
+err_unlock:
+	netdev_unlock_ops(req_info.base.dev);
 	rtnl_unlock();
 	ethnl_parse_header_dev_put(&req_info.base);
 	return ret;
@@ -290,10 +293,15 @@ int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	rtnl_lock();
 
 	if (ctx->phy_req_info->base.dev) {
-		ret = ethnl_phy_dump_one_dev(skb, ctx->phy_req_info->base.dev, cb);
+		dev = ctx->phy_req_info->base.dev;
+		netdev_lock_ops(dev);
+		ret = ethnl_phy_dump_one_dev(skb, dev, cb);
+		netdev_unlock_ops(dev);
 	} else {
 		for_each_netdev_dump(net, dev, ctx->ifindex) {
+			netdev_lock_ops(dev);
 			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
+			netdev_unlock_ops(dev);
 			if (ret)
 				break;
 
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index 58df9ad02ce8a..ec41d1d7eefe4 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -345,7 +345,9 @@ int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 		if (ctx->match_ifindex && ctx->match_ifindex != ctx->ifindex)
 			break;
 
+		netdev_lock_ops(dev);
 		ret = rss_dump_one_dev(skb, cb, dev);
+		netdev_unlock_ops(dev);
 		if (ret)
 			break;
 	}
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 691be6c445b38..73b6a89b87316 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -448,12 +448,15 @@ int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 	rtnl_lock();
 	if (ctx->req_info->base.dev) {
-		ret = ethnl_tsinfo_dump_one_net_topo(skb,
-						     ctx->req_info->base.dev,
-						     cb);
+		dev = ctx->req_info->base.dev;
+		netdev_lock_ops(dev);
+		ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb);
+		netdev_unlock_ops(dev);
 	} else {
 		for_each_netdev_dump(net, dev, ctx->pos_ifindex) {
+			netdev_lock_ops(dev);
 			ret = ethnl_tsinfo_dump_one_net_topo(skb, dev, cb);
+			netdev_unlock_ops(dev);
 			if (ret < 0 && ret != -EOPNOTSUPP)
 				break;
 			ctx->pos_phyindex = 0;

From df43d8bf10316a7c3b1e47e3cc0057a54df4a5b8 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:29 -0800
Subject: [PATCH 1728/2753] net: replace dev_addr_sem with netdev instance lock

Lockdep reports possible circular dependency in [0]. Instead of
fixing the ordering, replace global dev_addr_sem with netdev
instance lock. Most of the paths that set/get mac are RTNL
protected. Two places where it's not, convert to explicit
locking:
- sysfs address_show
- dev_get_mac_address via dev_ioctl

0: https://netdev-3.bots.linux.dev/vmksft-forwarding-dbg/results/993321/24-router-bridge-1d-lag-sh/stderr

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-12-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c         |  2 +-
 drivers/net/tun.c         |  2 +-
 include/linux/netdevice.h |  6 +----
 net/core/dev.c            | 52 ++++++++++++++++++++-------------------
 net/core/dev.h            |  3 +--
 net/core/dev_api.c        | 17 ++-----------
 net/core/dev_ioctl.c      |  2 +-
 net/core/net-sysfs.c      |  7 ++----
 net/core/rtnetlink.c      |  6 ++++-
 9 files changed, 41 insertions(+), 56 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index d4ece538f1b23..4382f5e323b06 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1017,7 +1017,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 			rtnl_unlock();
 			return -ENOLINK;
 		}
-		ret = dev_set_mac_address_user(tap->dev, &sa, NULL);
+		ret = dev_set_mac_address(tap->dev, &sa, NULL);
 		tap_put_tap_dev(tap);
 		rtnl_unlock();
 		return ret;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index d8f4d3e996a7a..1e645d5e225c0 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3175,7 +3175,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	case SIOCSIFHWADDR:
 		/* Set hw address */
-		ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL);
+		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr, NULL);
 		break;
 
 	case TUNGETSNDBUF:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca9c09dab14e6..f3e6e6f27e22c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2492,7 +2492,7 @@ struct net_device {
 	 *
 	 * Protects:
 	 *	@gro_flush_timeout, @napi_defer_hard_irqs, @napi_list,
-	 *	@net_shaper_hierarchy, @reg_state, @threaded
+	 *	@net_shaper_hierarchy, @reg_state, @threaded, @dev_addr
 	 *
 	 * Partially protects (writers must hold both @lock and rtnl_lock):
 	 *	@up
@@ -4262,10 +4262,6 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			  struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
-int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			       struct netlink_ext_ack *extack);
-int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
diff --git a/net/core/dev.c b/net/core/dev.c
index 404047d4d9432..a0f75a1d1f5a7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1058,6 +1058,28 @@ struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex)
 	return __netdev_put_lock(dev);
 }
 
+/**
+ * netdev_get_by_name_lock() - find a device by its name
+ * @net: the applicable net namespace
+ * @name: name of device
+ *
+ * Search for an interface by name. If a valid device
+ * with @name is found it will be returned with netdev->lock held.
+ * netdev_unlock() must be called to release it.
+ *
+ * Return: pointer to a device with lock held, NULL if not found.
+ */
+struct net_device *netdev_get_by_name_lock(struct net *net, const char *name)
+{
+	struct net_device *dev;
+
+	dev = dev_get_by_name(net, name);
+	if (!dev)
+		return NULL;
+
+	return __netdev_put_lock(dev);
+}
+
 struct net_device *
 netdev_xa_find_lock(struct net *net, struct net_device *dev,
 		    unsigned long *index)
@@ -9589,44 +9611,24 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 	return 0;
 }
 
-DECLARE_RWSEM(dev_addr_sem);
-
-int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			       struct netlink_ext_ack *extack)
-{
-	int ret;
-
-	down_write(&dev_addr_sem);
-	ret = netif_set_mac_address(dev, sa, extack);
-	up_write(&dev_addr_sem);
-	return ret;
-}
-
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
 	size_t size = sizeof(sa->sa_data_min);
 	struct net_device *dev;
-	int ret = 0;
 
-	down_read(&dev_addr_sem);
-	rcu_read_lock();
+	dev = netdev_get_by_name_lock(net, dev_name);
+	if (!dev)
+		return -ENODEV;
 
-	dev = dev_get_by_name_rcu(net, dev_name);
-	if (!dev) {
-		ret = -ENODEV;
-		goto unlock;
-	}
 	if (!dev->addr_len)
 		memset(sa->sa_data, 0, size);
 	else
 		memcpy(sa->sa_data, dev->dev_addr,
 		       min_t(size_t, size, dev->addr_len));
 	sa->sa_family = dev->type;
+	netdev_unlock(dev);
 
-unlock:
-	rcu_read_unlock();
-	up_read(&dev_addr_sem);
-	return ret;
+	return 0;
 }
 EXPORT_SYMBOL(dev_get_mac_address);
 
diff --git a/net/core/dev.h b/net/core/dev.h
index 41b0831aba604..b50ca645c0863 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -28,6 +28,7 @@ netdev_napi_by_id_lock(struct net *net, unsigned int napi_id);
 struct net_device *dev_get_by_napi_id(unsigned int napi_id);
 
 struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex);
+struct net_device *netdev_get_by_name_lock(struct net *net, const char *name);
 struct net_device *__netdev_put_lock(struct net_device *dev);
 struct net_device *
 netdev_xa_find_lock(struct net *net, struct net_device *dev,
@@ -69,8 +70,6 @@ extern int		weight_p;
 extern int		dev_weight_rx_bias;
 extern int		dev_weight_tx_bias;
 
-extern struct rw_semaphore dev_addr_sem;
-
 /* rtnl helpers */
 extern struct list_head net_todo_list;
 void netdev_run_todo(void);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 98db990ce21ce..655a95fb7baa6 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -82,19 +82,6 @@ void dev_set_group(struct net_device *dev, int new_group)
 	netdev_unlock_ops(dev);
 }
 
-int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			     struct netlink_ext_ack *extack)
-{
-	int ret;
-
-	netdev_lock_ops(dev);
-	ret = netif_set_mac_address_user(dev, sa, extack);
-	netdev_unlock_ops(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL(dev_set_mac_address_user);
-
 /**
  * dev_change_net_namespace() - move device to different nethost namespace
  * @dev: device
@@ -310,9 +297,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 {
 	int ret;
 
-	netdev_lock_ops(dev);
+	netdev_lock(dev);
 	ret = netif_set_mac_address(dev, sa, extack);
-	netdev_unlock_ops(dev);
+	netdev_unlock(dev);
 
 	return ret;
 }
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index d9f3505931210..296e52d1395d6 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -574,7 +574,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	case SIOCSIFHWADDR:
 		if (dev->addr_len > sizeof(struct sockaddr))
 			return -EINVAL;
-		return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL);
+		return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL);
 
 	case SIOCSIFHWBROADCAST:
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 27eea34d1b416..02d1d40b47ae3 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -262,14 +262,11 @@ static ssize_t address_show(struct device *dev, struct device_attribute *attr,
 	struct net_device *ndev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	down_read(&dev_addr_sem);
-
-	rcu_read_lock();
+	netdev_lock(ndev);
 	if (dev_isalive(ndev))
 		ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len);
-	rcu_read_unlock();
+	netdev_unlock(ndev);
 
-	up_read(&dev_addr_sem);
 	return ret;
 }
 static DEVICE_ATTR_RO(address);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9d539c9ce1a42..88a352b02bcef 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3089,7 +3089,11 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 		sa->sa_family = dev->type;
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		err = netif_set_mac_address_user(dev, sa, extack);
+		if (!netdev_need_ops_lock(dev))
+			netdev_lock(dev);
+		err = netif_set_mac_address(dev, sa, extack);
+		if (!netdev_need_ops_lock(dev))
+			netdev_unlock(dev);
 		kfree(sa);
 		if (err)
 			goto errout;

From 605ef7aec0605bd5506b31591de278d652bd0096 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:30 -0800
Subject: [PATCH 1729/2753] net: add option to request netdev instance lock

Currently only the drivers that implement shaper or queue APIs
are grabbing instance lock. Add an explicit opt-in for the
drivers that want to grab the lock without implementing the above
APIs.

There is a 3-byte hole after @up, use it:

        /* --- cacheline 47 boundary (3008 bytes) --- */
        u32                        napi_defer_hard_irqs; /*  3008     4 */
        bool                       up;                   /*  3012     1 */

        /* XXX 3 bytes hole, try to pack */

        struct mutex               lock;                 /*  3016   144 */

        /* XXX last struct has 1 hole */

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-13-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index f3e6e6f27e22c..adf201617b72f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2485,6 +2485,12 @@ struct net_device {
 	 */
 	bool			up;
 
+	/**
+	 * @request_ops_lock: request the core to run all @netdev_ops and
+	 * @ethtool_ops under the @lock.
+	 */
+	bool			request_ops_lock;
+
 	/**
 	 * @lock: netdev-scope lock, protects a small selection of fields.
 	 * Should always be taken using netdev_lock() / netdev_unlock() helpers.
@@ -2774,7 +2780,7 @@ static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
 
 static inline bool netdev_need_ops_lock(struct net_device *dev)
 {
-	bool ret = !!dev->queue_mgmt_ops;
+	bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
 
 #if IS_ENABLED(CONFIG_NET_SHAPER)
 	ret |= !!dev->netdev_ops->net_shaper_ops;

From cc34acd577f1a6ed805106bfcc9a262837dbd0da Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:31 -0800
Subject: [PATCH 1730/2753] docs: net: document new locking reality

Also clarify ndo_get_stats (that read and write paths can run
concurrently) and mention only RCU.

Cc: Saeed Mahameed <saeed@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-14-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/netdevices.rst | 65 ++++++++++++++++++++-----
 include/linux/netdevice.h               |  4 ++
 2 files changed, 56 insertions(+), 13 deletions(-)

diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index 1d37038e9fbed..d235a73648930 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -210,49 +210,55 @@ packets is preferred.
 struct net_device synchronization rules
 =======================================
 ndo_open:
-	Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
 	Context: process
 
 ndo_stop:
-	Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
 	Context: process
 	Note: netif_running() is guaranteed false
 
 ndo_do_ioctl:
 	Synchronization: rtnl_lock() semaphore.
-	Context: process
 
-        This is only called by network subsystems internally,
-        not by user space calling ioctl as it was in before
-        linux-5.14.
+	This is only called by network subsystems internally,
+	not by user space calling ioctl as it was in before
+	linux-5.14.
 
 ndo_siocbond:
-        Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
         Context: process
 
-        Used by the bonding driver for the SIOCBOND family of
-        ioctl commands.
+	Used by the bonding driver for the SIOCBOND family of
+	ioctl commands.
 
 ndo_siocwandev:
-	Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
 	Context: process
 
 	Used by the drivers/net/wan framework to handle
 	the SIOCWANDEV ioctl with the if_settings structure.
 
 ndo_siocdevprivate:
-	Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
 	Context: process
 
 	This is used to implement SIOCDEVPRIVATE ioctl helpers.
 	These should not be added to new drivers, so don't use.
 
 ndo_eth_ioctl:
-	Synchronization: rtnl_lock() semaphore.
+	Synchronization: rtnl_lock() semaphore. In addition, netdev instance
+	lock if the driver implements queue management or shaper API.
 	Context: process
 
 ndo_get_stats:
-	Synchronization: rtnl_lock() semaphore, or RCU.
+	Synchronization: RCU (can be called concurrently with the stats
+	update path).
 	Context: atomic (can't sleep under RCU)
 
 ndo_start_xmit:
@@ -284,6 +290,10 @@ ndo_set_rx_mode:
 	Synchronization: netif_addr_lock spinlock.
 	Context: BHs disabled
 
+Most ndo callbacks not specified in the list above are running
+under ``rtnl_lock``. In addition, netdev instance lock is taken as well if
+the driver implements queue management or shaper API.
+
 struct napi_struct synchronization rules
 ========================================
 napi->poll:
@@ -298,6 +308,35 @@ napi->poll:
 		 softirq
 		 will be called with interrupts disabled by netconsole.
 
+struct netdev_queue_mgmt_ops synchronization rules
+==================================================
+
+All queue management ndo callbacks are holding netdev instance lock.
+
+RTNL and netdev instance lock
+=============================
+
+Historically, all networking control operations were protected by a single
+global lock known as ``rtnl_lock``. There is an ongoing effort to replace this
+global lock with separate locks for each network namespace. Additionally,
+properties of individual netdev are increasingly protected by per-netdev locks.
+
+For device drivers that implement shaping or queue management APIs, all control
+operations will be performed under the netdev instance lock. Currently, this
+instance lock is acquired within the context of ``rtnl_lock``. The drivers
+can also explicitly request instance lock to be acquired via
+``request_ops_lock``. In the future, there will be an option for individual
+drivers to opt out of using ``rtnl_lock`` and instead perform their control
+operations directly under the netdev instance lock.
+
+Devices drivers are encouraged to rely on the instance lock where possible.
+
+For the (mostly software) drivers that need to interact with the core stack,
+there are two sets of interfaces: ``dev_xxx`` and ``netif_xxx`` (e.g.,
+``dev_set_mtu`` and ``netif_set_mtu``). The ``dev_xxx`` functions handle
+acquiring the instance lock themselves, while the ``netif_xxx`` functions
+assume that the driver has already acquired the instance lock.
+
 NETDEV_INTERNAL symbol namespace
 ================================
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index adf201617b72f..2f8560a354ba4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2505,6 +2505,10 @@ struct net_device {
 	 *
 	 * Also protects some fields in struct napi_struct.
 	 *
+	 * For the drivers that implement shaper or queue API, the scope
+	 * of this lock is expanded to cover most ndo/queue/ethtool/sysfs
+	 * operations.
+	 *
 	 * Ordering: take after rtnl_lock.
 	 */
 	struct mutex		lock;

From 004b5008016a2cc37103bf8d9968573771cd311f Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 5 Mar 2025 08:37:32 -0800
Subject: [PATCH 1731/2753] eth: bnxt: remove most dependencies on RTNL

Only devlink and sriov paths are grabbing rtnl explicitly. The rest is
covered by netdev instance lock which the core now grabs, so there is
no need to manage rtnl in most places anymore.

On the core side we can now try to drop rtnl in some places
(do_setlink for example) for the drivers that signal non-rtnl
mode (TBD).

Boot-tested and with `ethtool -L eth1 combined 24` to trigger reset.

Cc: Saeed Mahameed <saeed@kernel.org>
Reviewed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250305163732.2766420-15-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 117 +++++++++---------
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.c |   9 ++
 .../net/ethernet/broadcom/bnxt/bnxt_sriov.c   |   6 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c |  16 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c |  18 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |   3 +-
 include/linux/netdevice.h                     |   5 +
 7 files changed, 101 insertions(+), 73 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index ead9fcaad6bdd..1a1e6da777775 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5246,8 +5246,10 @@ static void bnxt_free_ntp_fltrs(struct bnxt *bp, bool all)
 {
 	int i;
 
-	/* Under rtnl_lock and all our NAPIs have been disabled.  It's
-	 * safe to delete the hash table.
+	netdev_assert_locked(bp->dev);
+
+	/* Under netdev instance lock and all our NAPIs have been disabled.
+	 * It's safe to delete the hash table.
 	 */
 	for (i = 0; i < BNXT_NTP_FLTR_HASH_SIZE; i++) {
 		struct hlist_head *head;
@@ -12789,7 +12791,6 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	return rc;
 }
 
-/* rtnl_lock held */
 int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 {
 	int rc = 0;
@@ -12805,9 +12806,9 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	return rc;
 }
 
-/* rtnl_lock held, open the NIC half way by allocating all resources, but
- * NAPI, IRQ, and TX are not enabled.  This is mainly used for offline
- * self tests.
+/* netdev instance lock held, open the NIC half way by allocating all
+ * resources, but NAPI, IRQ, and TX are not enabled.  This is mainly used
+ * for offline self tests.
  */
 int bnxt_half_open_nic(struct bnxt *bp)
 {
@@ -12842,8 +12843,8 @@ int bnxt_half_open_nic(struct bnxt *bp)
 	return rc;
 }
 
-/* rtnl_lock held, this call can only be made after a previous successful
- * call to bnxt_half_open_nic().
+/* netdev instance lock held, this call can only be made after a previous
+ * successful call to bnxt_half_open_nic().
  */
 void bnxt_half_close_nic(struct bnxt *bp)
 {
@@ -12952,10 +12953,11 @@ void bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		/* If we get here, it means firmware reset is in progress
 		 * while we are trying to close.  We can safely proceed with
-		 * the close because we are holding rtnl_lock().  Some firmware
-		 * messages may fail as we proceed to close.  We set the
-		 * ABORT_ERR flag here so that the FW reset thread will later
-		 * abort when it gets the rtnl_lock() and sees the flag.
+		 * the close because we are holding netdev instance lock.
+		 * Some firmware messages may fail as we proceed to close.
+		 * We set the ABORT_ERR flag here so that the FW reset thread
+		 * will later abort when it gets the netdev instance lock
+		 * and sees the flag.
 		 */
 		netdev_warn(bp->dev, "FW reset in progress during close, FW reset will be aborted\n");
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
@@ -13046,7 +13048,7 @@ static int bnxt_hwrm_port_phy_write(struct bnxt *bp, u16 phy_addr, u16 reg,
 	return hwrm_req_send(bp, req);
 }
 
-/* rtnl_lock held */
+/* netdev instance lock held */
 static int bnxt_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 {
 	struct mii_ioctl_data *mdio = if_mii(ifr);
@@ -13965,30 +13967,31 @@ static void bnxt_timer(struct timer_list *t)
 	mod_timer(&bp->timer, jiffies + bp->current_interval);
 }
 
-static void bnxt_rtnl_lock_sp(struct bnxt *bp)
+static void bnxt_lock_sp(struct bnxt *bp)
 {
 	/* We are called from bnxt_sp_task which has BNXT_STATE_IN_SP_TASK
 	 * set.  If the device is being closed, bnxt_close() may be holding
-	 * rtnl() and waiting for BNXT_STATE_IN_SP_TASK to clear.  So we
-	 * must clear BNXT_STATE_IN_SP_TASK before holding rtnl().
+	 * netdev instance lock and waiting for BNXT_STATE_IN_SP_TASK to clear.
+	 * So we must clear BNXT_STATE_IN_SP_TASK before holding netdev
+	 * instance lock.
 	 */
 	clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	rtnl_lock();
+	netdev_lock(bp->dev);
 }
 
-static void bnxt_rtnl_unlock_sp(struct bnxt *bp)
+static void bnxt_unlock_sp(struct bnxt *bp)
 {
 	set_bit(BNXT_STATE_IN_SP_TASK, &bp->state);
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 }
 
 /* Only called from bnxt_sp_task() */
 static void bnxt_reset(struct bnxt *bp, bool silent)
 {
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state))
 		bnxt_reset_task(bp, silent);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Only called from bnxt_sp_task() */
@@ -13996,9 +13999,9 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 {
 	int i;
 
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (!test_bit(BNXT_STATE_OPEN, &bp->state)) {
-		bnxt_rtnl_unlock_sp(bp);
+		bnxt_unlock_sp(bp);
 		return;
 	}
 	/* Disable and flush TPA before resetting the RX ring */
@@ -14037,7 +14040,7 @@ static void bnxt_rx_ring_reset(struct bnxt *bp)
 	}
 	if (bp->flags & BNXT_FLAG_TPA)
 		bnxt_set_tpa(bp, true);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_fw_fatal_close(struct bnxt *bp)
@@ -14093,7 +14096,7 @@ static bool is_bnxt_fw_ok(struct bnxt *bp)
 	return false;
 }
 
-/* rtnl_lock is acquired before calling this function */
+/* netdev instance lock is acquired before calling this function */
 static void bnxt_force_fw_reset(struct bnxt *bp)
 {
 	struct bnxt_fw_health *fw_health = bp->fw_health;
@@ -14136,9 +14139,9 @@ void bnxt_fw_exception(struct bnxt *bp)
 	netdev_warn(bp->dev, "Detected firmware fatal condition, initiating reset\n");
 	set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state);
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	bnxt_force_fw_reset(bp);
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 /* Returns the number of registered VFs, or 1 if VF configuration is pending, or
@@ -14168,7 +14171,7 @@ static int bnxt_get_registered_vfs(struct bnxt *bp)
 void bnxt_fw_reset(struct bnxt *bp)
 {
 	bnxt_ulp_stop(bp);
-	bnxt_rtnl_lock_sp(bp);
+	bnxt_lock_sp(bp);
 	if (test_bit(BNXT_STATE_OPEN, &bp->state) &&
 	    !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		struct bnxt_ptp_cfg *ptp = bp->ptp_cfg;
@@ -14214,7 +14217,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 		bnxt_queue_fw_reset_work(bp, tmo);
 	}
 fw_reset_exit:
-	bnxt_rtnl_unlock_sp(bp);
+	bnxt_unlock_sp(bp);
 }
 
 static void bnxt_chk_missed_irq(struct bnxt *bp)
@@ -14413,7 +14416,7 @@ static void bnxt_sp_task(struct work_struct *work)
 static void _bnxt_get_max_rings(struct bnxt *bp, int *max_rx, int *max_tx,
 				int *max_cp);
 
-/* Under rtnl_lock */
+/* Under netdev instance lock */
 int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs,
 		     int tx_xdp)
 {
@@ -14841,10 +14844,10 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			return;
 		}
 		bp->fw_reset_timestamp = jiffies;
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) {
 			bnxt_fw_reset_abort(bp, rc);
-			rtnl_unlock();
+			netdev_unlock(bp->dev);
 			goto ulp_start;
 		}
 		bnxt_fw_reset_close(bp);
@@ -14855,7 +14858,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV;
 			tmo = bp->fw_reset_min_dsecs * HZ / 10;
 		}
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		bnxt_queue_fw_reset_work(bp, tmo);
 		return;
 	}
@@ -14929,7 +14932,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING;
 		fallthrough;
 	case BNXT_FW_RESET_STATE_OPENING:
-		while (!rtnl_trylock()) {
+		while (!netdev_trylock(bp->dev)) {
 			bnxt_queue_fw_reset_work(bp, HZ / 10);
 			return;
 		}
@@ -14937,7 +14940,7 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		if (rc) {
 			netdev_err(bp->dev, "bnxt_open() failed during FW reset\n");
 			bnxt_fw_reset_abort(bp, rc);
-			rtnl_unlock();
+			netdev_unlock(bp->dev);
 			goto ulp_start;
 		}
 
@@ -14956,13 +14959,13 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 			bnxt_dl_health_fw_recovery_done(bp);
 			bnxt_dl_health_fw_status_update(bp, true);
 		}
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		bnxt_ulp_start(bp, 0);
 		bnxt_reenable_sriov(bp);
-		rtnl_lock();
+		netdev_lock(bp->dev);
 		bnxt_vf_reps_alloc(bp);
 		bnxt_vf_reps_open(bp);
-		rtnl_unlock();
+		netdev_unlock(bp->dev);
 		break;
 	}
 	return;
@@ -14975,9 +14978,9 @@ static void bnxt_fw_reset_task(struct work_struct *work)
 		netdev_err(bp->dev, "fw_health_status 0x%x\n", sts);
 	}
 fw_reset_abort:
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_fw_reset_abort(bp, rc);
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 ulp_start:
 	bnxt_ulp_start(bp, rc);
 }
@@ -15069,13 +15072,14 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev)
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 {
 	struct sockaddr *addr = p;
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
+	netdev_assert_locked(dev);
+
 	if (!is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 
@@ -15096,11 +15100,12 @@ static int bnxt_change_mac_addr(struct net_device *dev, void *p)
 	return rc;
 }
 
-/* rtnl_lock held */
 static int bnxt_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
+	netdev_assert_locked(dev);
+
 	if (netif_running(dev))
 		bnxt_close_nic(bp, true, false);
 
@@ -16257,7 +16262,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 {
 	int rc;
 
-	ASSERT_RTNL();
+	netdev_ops_assert_locked(bp->dev);
 	bnxt_hwrm_func_qcaps(bp);
 
 	if (netif_running(bp->dev))
@@ -16657,7 +16662,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	if (!dev)
 		return;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	bp = netdev_priv(dev);
 	if (!bp)
 		goto shutdown_exit;
@@ -16675,7 +16680,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 	}
 
 shutdown_exit:
-	rtnl_unlock();
+	netdev_unlock(dev);
 }
 
 #ifdef CONFIG_PM_SLEEP
@@ -16687,7 +16692,7 @@ static int bnxt_suspend(struct device *device)
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(dev);
 	if (netif_running(dev)) {
 		netif_device_detach(dev);
 		rc = bnxt_close(dev);
@@ -16696,7 +16701,7 @@ static int bnxt_suspend(struct device *device)
 	bnxt_ptp_clear(bp);
 	pci_disable_device(bp->pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 
@@ -16706,7 +16711,7 @@ static int bnxt_resume(struct device *device)
 	struct bnxt *bp = netdev_priv(dev);
 	int rc = 0;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	rc = pci_enable_device(bp->pdev);
 	if (rc) {
 		netdev_err(dev, "Cannot re-enable PCI device during resume, err = %d\n",
@@ -16749,7 +16754,7 @@ static int bnxt_resume(struct device *device)
 	}
 
 resume_exit:
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 	bnxt_ulp_start(bp, rc);
 	if (!rc)
 		bnxt_reenable_sriov(bp);
@@ -16784,7 +16789,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 
 	bnxt_ulp_stop(bp);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 	netif_device_detach(netdev);
 
 	if (test_and_set_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
@@ -16793,7 +16798,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	}
 
 	if (abort || state == pci_channel_io_perm_failure) {
-		rtnl_unlock();
+		netdev_unlock(netdev);
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
@@ -16812,7 +16817,7 @@ static pci_ers_result_t bnxt_io_error_detected(struct pci_dev *pdev,
 	if (pci_is_enabled(pdev))
 		pci_disable_device(pdev);
 	bnxt_free_ctx_mem(bp, false);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
 	/* Request a slot slot reset. */
 	return PCI_ERS_RESULT_NEED_RESET;
@@ -16842,7 +16847,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 	    test_bit(BNXT_STATE_PCI_CHANNEL_IO_FROZEN, &bp->state))
 		msleep(900);
 
-	rtnl_lock();
+	netdev_lock(netdev);
 
 	if (pci_enable_device(pdev)) {
 		dev_err(&pdev->dev,
@@ -16897,7 +16902,7 @@ static pci_ers_result_t bnxt_io_slot_reset(struct pci_dev *pdev)
 reset_exit:
 	clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
 	bnxt_clear_reservations(bp, true);
-	rtnl_unlock();
+	netdev_unlock(netdev);
 
 	return result;
 }
@@ -16916,7 +16921,7 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	int err;
 
 	netdev_info(bp->dev, "PCI Slot Resume\n");
-	rtnl_lock();
+	netdev_lock(netdev);
 
 	err = bnxt_hwrm_func_qcaps(bp);
 	if (!err) {
@@ -16929,7 +16934,7 @@ static void bnxt_io_resume(struct pci_dev *pdev)
 	if (!err)
 		netif_device_attach(netdev);
 
-	rtnl_unlock();
+	netdev_unlock(netdev);
 	bnxt_ulp_start(bp, err);
 	if (!err)
 		bnxt_reenable_sriov(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index ef8288fd68f4c..b06fcddfc81c8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -439,14 +439,17 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
 		bnxt_ulp_stop(bp);
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bnxt_sriov_cfg(bp)) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "reload is unsupported while VFs are allocated or being configured");
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -EOPNOTSUPP;
 		}
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			bnxt_ulp_start(bp, 0);
 			return -ENODEV;
@@ -459,6 +462,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			NL_SET_ERR_MSG_MOD(extack, "Failed to deregister");
 			if (netif_running(bp->dev))
 				dev_close(bp->dev);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			break;
 		}
@@ -479,7 +483,9 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 			return -EPERM;
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (bp->dev->reg_state == NETREG_UNREGISTERED) {
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			return -ENODEV;
 		}
@@ -493,6 +499,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to activate firmware");
 			clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
+			netdev_unlock(bp->dev);
 			rtnl_unlock();
 		}
 		break;
@@ -568,7 +575,9 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		}
 		*actions_performed |= BIT(action);
 	} else if (netif_running(bp->dev)) {
+		netdev_lock(bp->dev);
 		dev_close(bp->dev);
+		netdev_unlock(bp->dev);
 	}
 	rtnl_unlock();
 	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index 12b6ed51fd884..5ddddd89052ff 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -946,7 +946,9 @@ void bnxt_sriov_disable(struct bnxt *bp)
 
 	/* Reclaim all resources for the PF. */
 	rtnl_lock();
+	netdev_lock(bp->dev);
 	bnxt_restore_pf_fw_resources(bp);
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 }
 
@@ -956,17 +958,21 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	struct bnxt *bp = netdev_priv(dev);
 
 	rtnl_lock();
+	netdev_lock(dev);
 	if (!netif_running(dev)) {
 		netdev_warn(dev, "Reject SRIOV config request since if is down!\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) {
 		netdev_warn(dev, "Reject SRIOV config request when FW reset is in progress\n");
+		netdev_unlock(dev);
 		rtnl_unlock();
 		return 0;
 	}
 	bp->sriov_cfg = true;
+	netdev_unlock(dev);
 	rtnl_unlock();
 
 	if (pci_vfs_assigned(bp->pdev)) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index e4a7f37036edb..a8e930d5dbb09 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -112,7 +112,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	struct bnxt_ulp *ulp;
 	int rc = 0;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
 	if (!bp->irq_tbl) {
 		rc = -ENODEV;
@@ -138,7 +138,7 @@ int bnxt_register_dev(struct bnxt_en_dev *edev,
 	edev->flags |= BNXT_EN_FLAG_MSIX_REQUESTED;
 exit:
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return rc;
 }
 EXPORT_SYMBOL(bnxt_register_dev);
@@ -151,7 +151,7 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 	int i = 0;
 
 	ulp = edev->ulp_tbl;
-	rtnl_lock();
+	netdev_lock(dev);
 	mutex_lock(&edev->en_dev_lock);
 	if (ulp->msix_requested)
 		edev->flags &= ~BNXT_EN_FLAG_MSIX_REQUESTED;
@@ -169,7 +169,7 @@ void bnxt_unregister_dev(struct bnxt_en_dev *edev)
 		i++;
 	}
 	mutex_unlock(&edev->en_dev_lock);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return;
 }
 EXPORT_SYMBOL(bnxt_unregister_dev);
@@ -309,12 +309,14 @@ void bnxt_ulp_irq_stop(struct bnxt *bp)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		netdev_lock(bp->dev);
+		ops = rcu_dereference(ulp->ulp_ops);
 		if (!ops || !ops->ulp_irq_stop)
 			return;
 		if (test_bit(BNXT_STATE_FW_RESET_DET, &bp->state))
 			reset = true;
 		ops->ulp_irq_stop(ulp->handle, reset);
+		netdev_unlock(bp->dev);
 	}
 }
 
@@ -333,7 +335,8 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 		if (!ulp->msix_requested)
 			return;
 
-		ops = rtnl_dereference(ulp->ulp_ops);
+		netdev_lock(bp->dev);
+		ops = rcu_dereference(ulp->ulp_ops);
 		if (!ops || !ops->ulp_irq_restart)
 			return;
 
@@ -345,6 +348,7 @@ void bnxt_ulp_irq_restart(struct bnxt *bp, int err)
 			bnxt_fill_msix_vecs(bp, ent);
 		}
 		ops->ulp_irq_restart(ulp->handle, ent);
+		netdev_unlock(bp->dev);
 		kfree(ent);
 	}
 }
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 1467b94a6427f..619f0844e7785 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -257,8 +257,7 @@ bool bnxt_dev_is_vf_rep(struct net_device *dev)
 
 /* Called when the parent PF interface is closed:
  * As the mode transition from SWITCHDEV to LEGACY
- * happens under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happens under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_close(struct bnxt *bp)
 {
@@ -278,8 +277,7 @@ void bnxt_vf_reps_close(struct bnxt *bp)
 
 /* Called when the parent PF interface is opened (re-opened):
  * As the mode transition from SWITCHDEV to LEGACY
- * happen under the rtnl_lock() this routine is safe
- * under the rtnl_lock()
+ * happen under the netdev instance lock this routine is safe
  */
 void bnxt_vf_reps_open(struct bnxt *bp)
 {
@@ -348,7 +346,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 	/* Ensure that parent PF's and VF-reps' RX/TX has been quiesced
 	 * before proceeding with VF-rep cleanup.
 	 */
-	rtnl_lock();
+	netdev_lock(bp->dev);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		closed = true;
@@ -365,10 +363,10 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 		bnxt_open_nic(bp, false, false);
 		bp->eswitch_mode = DEVLINK_ESWITCH_MODE_SWITCHDEV;
 	}
-	rtnl_unlock();
+	netdev_unlock(bp->dev);
 
-	/* Need to call vf_reps_destroy() outside of rntl_lock
-	 * as unregister_netdev takes rtnl_lock
+	/* Need to call vf_reps_destroy() outside of netdev instance lock
+	 * as unregister_netdev takes it
 	 */
 	__bnxt_vf_reps_destroy(bp);
 }
@@ -376,7 +374,7 @@ void bnxt_vf_reps_destroy(struct bnxt *bp)
 /* Free the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 void bnxt_vf_reps_free(struct bnxt *bp)
 {
@@ -413,7 +411,7 @@ static int bnxt_alloc_vf_rep(struct bnxt *bp, struct bnxt_vf_rep *vf_rep,
 /* Allocate the VF-Reps in firmware, during firmware hot-reset processing.
  * Note that the VF-Rep netdevs are still active (not unregistered) during
  * this process. As the mode transition from SWITCHDEV to LEGACY happens
- * under the rtnl_lock() this routine is safe under the rtnl_lock().
+ * under the netdev instance lock this routine is safe.
  */
 int bnxt_vf_reps_alloc(struct bnxt *bp)
 {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index e6c64e4bd66c3..0caf6e9bccb8c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -382,13 +382,14 @@ int bnxt_xdp_xmit(struct net_device *dev, int num_frames,
 	return nxmit;
 }
 
-/* Under rtnl_lock */
 static int bnxt_xdp_set(struct bnxt *bp, struct bpf_prog *prog)
 {
 	struct net_device *dev = bp->dev;
 	int tx_xdp = 0, tx_cp, rc, tc;
 	struct bpf_prog *old;
 
+	netdev_assert_locked(dev);
+
 	if (prog && !prog->aux->xdp_has_frags &&
 	    bp->dev->mtu > BNXT_MAX_PAGE_MODE_MTU) {
 		netdev_warn(dev, "MTU %d larger than %d without XDP frag support.\n",
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 2f8560a354ba4..d206c9592b60f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2765,6 +2765,11 @@ static inline void netdev_lock(struct net_device *dev)
 	mutex_lock(&dev->lock);
 }
 
+static inline bool netdev_trylock(struct net_device *dev)
+{
+	return mutex_trylock(&dev->lock);
+}
+
 static inline void netdev_unlock(struct net_device *dev)
 {
 	mutex_unlock(&dev->lock);

From c00b413a96261faef4ce22329153c6abd4acef25 Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Thu, 6 Mar 2025 16:59:16 +0100
Subject: [PATCH 1732/2753] x86/boot: Sanitize boot params before parsing
 command line

The 5-level paging code parses the command line to look for the 'no5lvl'
string, and does so very early, before sanitize_boot_params() has been
called and has been given the opportunity to wipe bogus data from the
fields in boot_params that are not covered by struct setup_header, and
are therefore supposed to be initialized to zero by the bootloader.

This triggers an early boot crash when using syslinux-efi to boot a
recent kernel built with CONFIG_X86_5LEVEL=y and CONFIG_EFI_STUB=n, as
the 0xff padding that now fills the unused PE/COFF header is copied into
boot_params by the bootloader, and interpreted as the top half of the
command line pointer.

Fix this by sanitizing the boot_params before use. Note that there is no
harm in calling this more than once; subsequent invocations are able to
spot that the boot_params have already been cleaned up.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: <stable@vger.kernel.org> # v6.1+
Link: https://lore.kernel.org/r/20250306155915.342465-2-ardb+git@google.com
Closes: https://lore.kernel.org/all/202503041549.35913.ulrich.gemkow@ikr.uni-stuttgart.de
---
 arch/x86/boot/compressed/pgtable_64.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index c882e1f67af01..d8c5de40669d3 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "misc.h"
 #include <asm/bootparam.h>
+#include <asm/bootparam_utils.h>
 #include <asm/e820/types.h>
 #include <asm/processor.h>
 #include "pgtable.h"
@@ -107,6 +108,7 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
 	bool l5_required = false;
 
 	/* Initialize boot_params. Required for cmdline_find_option_bool(). */
+	sanitize_boot_params(bp);
 	boot_params_ptr = bp;
 
 	/*

From 33255c161ac4be003ac87c434ebc49645d18a929 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 20:07:58 -0500
Subject: [PATCH 1733/2753] bcachefs: Fix bch2_dev_journal_alloc() spuriously
 failing

Previously, we fixed journal resize spuriousl failing with
-BCH_ERR_open_buckets_empty, but initial journal allocation was missed
because it didn't invoke the "block on allocator" loop at all.

Factor out the "loop on allocator" code to fix that.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/journal.c | 59 +++++++++++++++++++++++--------------------
 1 file changed, 32 insertions(+), 27 deletions(-)

diff --git a/fs/bcachefs/journal.c b/fs/bcachefs/journal.c
index 5dabbf3c0965c..05b1250619ecc 100644
--- a/fs/bcachefs/journal.c
+++ b/fs/bcachefs/journal.c
@@ -1021,8 +1021,8 @@ struct journal_buf *bch2_next_write_buffer_flush_journal_buf(struct journal *j,
 
 /* allocate journal on a device: */
 
-static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr,
-					 bool new_fs, struct closure *cl)
+static int bch2_set_nr_journal_buckets_iter(struct bch_dev *ca, unsigned nr,
+					    bool new_fs, struct closure *cl)
 {
 	struct bch_fs *c = ca->fs;
 	struct journal_device *ja = &ca->journal;
@@ -1150,26 +1150,20 @@ static int __bch2_set_nr_journal_buckets(struct bch_dev *ca, unsigned nr,
 	return ret;
 }
 
-/*
- * Allocate more journal space at runtime - not currently making use if it, but
- * the code works:
- */
-int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
-				unsigned nr)
+static int bch2_set_nr_journal_buckets_loop(struct bch_fs *c, struct bch_dev *ca,
+					    unsigned nr, bool new_fs)
 {
 	struct journal_device *ja = &ca->journal;
-	struct closure cl;
 	int ret = 0;
 
+	struct closure cl;
 	closure_init_stack(&cl);
 
-	down_write(&c->state_lock);
-
 	/* don't handle reducing nr of buckets yet: */
 	if (nr < ja->nr)
-		goto unlock;
+		return 0;
 
-	while (ja->nr < nr) {
+	while (!ret && ja->nr < nr) {
 		struct disk_reservation disk_res = { 0, 0, 0 };
 
 		/*
@@ -1182,27 +1176,38 @@ int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
 		 * filesystem-wide allocation will succeed, this is a device
 		 * specific allocation - we can hang here:
 		 */
+		if (!new_fs) {
+			ret = bch2_disk_reservation_get(c, &disk_res,
+							bucket_to_sector(ca, nr - ja->nr), 1, 0);
+			if (ret)
+				break;
+		}
 
-		ret = bch2_disk_reservation_get(c, &disk_res,
-						bucket_to_sector(ca, nr - ja->nr), 1, 0);
-		if (ret)
-			break;
+		ret = bch2_set_nr_journal_buckets_iter(ca, nr, new_fs, &cl);
 
-		ret = __bch2_set_nr_journal_buckets(ca, nr, false, &cl);
+		if (ret == -BCH_ERR_bucket_alloc_blocked ||
+		    ret == -BCH_ERR_open_buckets_empty)
+			ret = 0; /* wait and retry */
 
 		bch2_disk_reservation_put(c, &disk_res);
-
 		closure_sync(&cl);
-
-		if (ret &&
-		    ret != -BCH_ERR_bucket_alloc_blocked &&
-		    ret != -BCH_ERR_open_buckets_empty)
-			break;
 	}
 
-	bch_err_fn(c, ret);
-unlock:
+	return ret;
+}
+
+/*
+ * Allocate more journal space at runtime - not currently making use if it, but
+ * the code works:
+ */
+int bch2_set_nr_journal_buckets(struct bch_fs *c, struct bch_dev *ca,
+				unsigned nr)
+{
+	down_write(&c->state_lock);
+	int ret = bch2_set_nr_journal_buckets_loop(c, ca, nr, false);
 	up_write(&c->state_lock);
+
+	bch_err_fn(c, ret);
 	return ret;
 }
 
@@ -1228,7 +1233,7 @@ int bch2_dev_journal_alloc(struct bch_dev *ca, bool new_fs)
 		     min(1 << 13,
 			 (1 << 24) / ca->mi.bucket_size));
 
-	ret = __bch2_set_nr_journal_buckets(ca, nr, new_fs, NULL);
+	ret = bch2_set_nr_journal_buckets_loop(ca->fs, ca, nr, new_fs);
 err:
 	bch_err_fn(ca, ret);
 	return ret;

From 8ba73f53dc5b7545776e09e6982115dcbcbabec4 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 28 Feb 2025 11:34:41 -0500
Subject: [PATCH 1734/2753] bcachefs: copygc now skips non-rw devices

There's no point in doing copygc on non-rw devices: the fragmentation
doesn't matter if we're not writing to them, and we may not have
anywhere to put the data on our other devices.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/movinggc.c | 25 ++++++++++++-------------
 1 file changed, 12 insertions(+), 13 deletions(-)

diff --git a/fs/bcachefs/movinggc.c b/fs/bcachefs/movinggc.c
index 21805509ab9e6..6718dc37c5a35 100644
--- a/fs/bcachefs/movinggc.c
+++ b/fs/bcachefs/movinggc.c
@@ -74,20 +74,14 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
 				  struct move_bucket *b, u64 time)
 {
 	struct bch_fs *c = trans->c;
-	struct btree_iter iter;
-	struct bkey_s_c k;
-	struct bch_alloc_v4 _a;
-	const struct bch_alloc_v4 *a;
-	int ret;
 
-	if (bch2_bucket_is_open(trans->c,
-				b->k.bucket.inode,
-				b->k.bucket.offset))
+	if (bch2_bucket_is_open(c, b->k.bucket.inode, b->k.bucket.offset))
 		return 0;
 
-	k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc,
-			       b->k.bucket, BTREE_ITER_cached);
-	ret = bkey_err(k);
+	struct btree_iter iter;
+	struct bkey_s_c k = bch2_bkey_get_iter(trans, &iter, BTREE_ID_alloc,
+				       b->k.bucket, BTREE_ITER_cached);
+	int ret = bkey_err(k);
 	if (ret)
 		return ret;
 
@@ -95,13 +89,18 @@ static int bch2_bucket_is_movable(struct btree_trans *trans,
 	if (!ca)
 		goto out;
 
-	a = bch2_alloc_to_v4(k, &_a);
+	if (ca->mi.state != BCH_MEMBER_STATE_rw ||
+	    !bch2_dev_is_online(ca))
+		goto out_put;
+
+	struct bch_alloc_v4 _a;
+	const struct bch_alloc_v4 *a = bch2_alloc_to_v4(k, &_a);
 	b->k.gen	= a->gen;
 	b->sectors	= bch2_bucket_sectors_dirty(*a);
 	u64 lru_idx	= alloc_lru_idx_fragmentation(*a, ca);
 
 	ret = lru_idx && lru_idx <= time;
-
+out_put:
 	bch2_dev_put(ca);
 out:
 	bch2_trans_iter_exit(trans, &iter);

From f8ece40786c9342249aa0a1b55e148ee23b2a746 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Mar 2025 13:05:50 +0000
Subject: [PATCH 1735/2753] tcp: bring back NUMA dispersion in
 inet_ehash_locks_alloc()

We have platforms with 6 NUMA nodes and 480 cpus.

inet_ehash_locks_alloc() currently allocates a single 64KB page
to hold all ehash spinlocks. This adds more pressure on a single node.

Change inet_ehash_locks_alloc() to use vmalloc() to spread
the spinlocks on all online nodes, driven by NUMA policies.

At boot time, NUMA policy is interleave=all, meaning that
tcp_hashinfo.ehash_locks gets hash dispersion on all nodes.

Tested:

lack5:~# grep inet_ehash_locks_alloc /proc/vmallocinfo
0x00000000d9aec4d1-0x00000000a828b652   69632 inet_ehash_locks_alloc+0x90/0x100 pages=16 vmalloc N0=2 N1=3 N2=3 N3=3 N4=3 N5=2

lack5:~# echo 8192 >/proc/sys/net/ipv4/tcp_child_ehash_entries
lack5:~# numactl --interleave=all unshare -n bash -c "grep inet_ehash_locks_alloc /proc/vmallocinfo"
0x000000004e99d30c-0x00000000763f3279   36864 inet_ehash_locks_alloc+0x90/0x100 pages=8 vmalloc N0=1 N1=2 N2=2 N3=1 N4=1 N5=1
0x00000000d9aec4d1-0x00000000a828b652   69632 inet_ehash_locks_alloc+0x90/0x100 pages=16 vmalloc N0=2 N1=3 N2=3 N3=3 N4=3 N5=2

lack5:~# numactl --interleave=0,5 unshare -n bash -c "grep inet_ehash_locks_alloc /proc/vmallocinfo"
0x00000000fd73a33e-0x0000000004b9a177   36864 inet_ehash_locks_alloc+0x90/0x100 pages=8 vmalloc N0=4 N5=4
0x00000000d9aec4d1-0x00000000a828b652   69632 inet_ehash_locks_alloc+0x90/0x100 pages=16 vmalloc N0=2 N1=3 N2=3 N3=3 N4=3 N5=2

lack5:~# echo 1024 >/proc/sys/net/ipv4/tcp_child_ehash_entries
lack5:~# numactl --interleave=all unshare -n bash -c "grep inet_ehash_locks_alloc /proc/vmallocinfo"
0x00000000db07d7a2-0x00000000ad697d29    8192 inet_ehash_locks_alloc+0x90/0x100 pages=1 vmalloc N2=1
0x00000000d9aec4d1-0x00000000a828b652   69632 inet_ehash_locks_alloc+0x90/0x100 pages=16 vmalloc N0=2 N1=3 N2=3 N3=3 N4=3 N5=2

Signed-off-by: Eric Dumazet <edumazet@google.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250305130550.1865988-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_hashtables.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index d1b5f45ee7184..3edbe2dad8ba4 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -1261,22 +1261,37 @@ int inet_ehash_locks_alloc(struct inet_hashinfo *hashinfo)
 {
 	unsigned int locksz = sizeof(spinlock_t);
 	unsigned int i, nblocks = 1;
+	spinlock_t *ptr = NULL;
 
-	if (locksz != 0) {
-		/* allocate 2 cache lines or at least one spinlock per cpu */
-		nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U);
-		nblocks = roundup_pow_of_two(nblocks * num_possible_cpus());
+	if (locksz == 0)
+		goto set_mask;
 
-		/* no more locks than number of hash buckets */
-		nblocks = min(nblocks, hashinfo->ehash_mask + 1);
+	/* Allocate 2 cache lines or at least one spinlock per cpu. */
+	nblocks = max(2U * L1_CACHE_BYTES / locksz, 1U) * num_possible_cpus();
 
-		hashinfo->ehash_locks = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
-		if (!hashinfo->ehash_locks)
-			return -ENOMEM;
+	/* At least one page per NUMA node. */
+	nblocks = max(nblocks, num_online_nodes() * PAGE_SIZE / locksz);
+
+	nblocks = roundup_pow_of_two(nblocks);
+
+	/* No more locks than number of hash buckets. */
+	nblocks = min(nblocks, hashinfo->ehash_mask + 1);
 
-		for (i = 0; i < nblocks; i++)
-			spin_lock_init(&hashinfo->ehash_locks[i]);
+	if (num_online_nodes() > 1) {
+		/* Use vmalloc() to allow NUMA policy to spread pages
+		 * on all available nodes if desired.
+		 */
+		ptr = vmalloc_array(nblocks, locksz);
+	}
+	if (!ptr) {
+		ptr = kvmalloc_array(nblocks, locksz, GFP_KERNEL);
+		if (!ptr)
+			return -ENOMEM;
 	}
+	for (i = 0; i < nblocks; i++)
+		spin_lock_init(&ptr[i]);
+	hashinfo->ehash_locks = ptr;
+set_mask:
 	hashinfo->ehash_locks_mask = nblocks - 1;
 	return 0;
 }

From 9544d60a2605d1500cf5c3e331a76b9eaf4538c9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Mar 2025 03:45:49 +0000
Subject: [PATCH 1736/2753] inet: change lport contribution to inet_ehashfn()
 and inet6_ehashfn()

In order to speedup __inet_hash_connect(), we want to ensure hash values
for <source address, port X, destination address, destination port>
are not randomly spread, but monotonically increasing.

Goal is to allow __inet_hash_connect() to derive the hash value
of a candidate 4-tuple with a single addition in the following
patch in the series.

Given :
  hash_0 = inet_ehashfn(saddr, 0, daddr, dport)
  hash_sport = inet_ehashfn(saddr, sport, daddr, dport)

Then (hash_sport == hash_0 + sport) for all sport values.

As far as I know, there is no security implication with this change.

After this patch, when __inet_hash_connect() has to try XXXX candidates,
the hash table buckets are contiguous and packed, allowing
a better use of cpu caches and hardware prefetchers.

Tested:

Server: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog
Client: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server

Before this patch:

  utime_start=0.271607
  utime_end=3.847111
  stime_start=18.407684
  stime_end=1997.485557
  num_transactions=1350742
  latency_min=0.014131929
  latency_max=17.895073144
  latency_mean=0.505675853
  latency_stddev=2.125164772
  num_samples=307884
  throughput=139866.80

perf top on client:

 56.86%  [kernel]       [k] __inet6_check_established
 17.96%  [kernel]       [k] __inet_hash_connect
 13.88%  [kernel]       [k] inet6_ehashfn
  2.52%  [kernel]       [k] rcu_all_qs
  2.01%  [kernel]       [k] __cond_resched
  0.41%  [kernel]       [k] _raw_spin_lock

After this patch:

  utime_start=0.286131
  utime_end=4.378886
  stime_start=11.952556
  stime_end=1991.655533
  num_transactions=1446830
  latency_min=0.001061085
  latency_max=12.075275028
  latency_mean=0.376375302
  latency_stddev=1.361969596
  num_samples=306383
  throughput=151866.56

perf top:

 50.01%  [kernel]       [k] __inet6_check_established
 20.65%  [kernel]       [k] __inet_hash_connect
 15.81%  [kernel]       [k] inet6_ehashfn
  2.92%  [kernel]       [k] rcu_all_qs
  2.34%  [kernel]       [k] __cond_resched
  0.50%  [kernel]       [k] _raw_spin_lock
  0.34%  [kernel]       [k] sched_balance_trigger
  0.24%  [kernel]       [k] queued_spin_lock_slowpath

There is indeed an increase of throughput and reduction of latency.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250305034550.879255-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/inet_hashtables.c  | 4 ++--
 net/ipv6/inet6_hashtables.c | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 3edbe2dad8ba4..ccf69b534d2e3 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -35,8 +35,8 @@ u32 inet_ehashfn(const struct net *net, const __be32 laddr,
 {
 	net_get_random_once(&inet_ehash_secret, sizeof(inet_ehash_secret));
 
-	return __inet_ehashfn(laddr, lport, faddr, fport,
-			      inet_ehash_secret + net_hash_mix(net));
+	return lport + __inet_ehashfn(laddr, 0, faddr, fport,
+				      inet_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet_ehashfn);
 
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 9be315496459f..3d95f1e75a118 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -35,8 +35,8 @@ u32 inet6_ehashfn(const struct net *net,
 	lhash = (__force u32)laddr->s6_addr32[3];
 	fhash = __ipv6_addr_jhash(faddr, tcp_ipv6_hash_secret);
 
-	return __inet6_ehashfn(lhash, lport, fhash, fport,
-			       inet6_ehash_secret + net_hash_mix(net));
+	return lport + __inet6_ehashfn(lhash, 0, fhash, fport,
+				       inet6_ehash_secret + net_hash_mix(net));
 }
 EXPORT_SYMBOL_GPL(inet6_ehashfn);
 

From d4438ce68bf145aa1d7ed03ebf3b8ece337e3f64 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 5 Mar 2025 03:45:50 +0000
Subject: [PATCH 1737/2753] inet: call inet6_ehashfn() once from
 inet6_hash_connect()

inet6_ehashfn() being called from __inet6_check_established()
has a big impact on performance, as shown in the Tested section.

After prior patch, we can compute the hash for port 0
from inet6_hash_connect(), and derive each hash in
__inet_hash_connect() from this initial hash:

hash(saddr, lport, daddr, dport) == hash(saddr, 0, daddr, dport) + lport

Apply the same principle for __inet_check_established(),
although inet_ehashfn() has a smaller cost.

Tested:

Server: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog
Client: ulimit -n 40000; neper/tcp_crr -T 200 -F 30000 -6 --nolog -c -H server

Before this patch:

  utime_start=0.286131
  utime_end=4.378886
  stime_start=11.952556
  stime_end=1991.655533
  num_transactions=1446830
  latency_min=0.001061085
  latency_max=12.075275028
  latency_mean=0.376375302
  latency_stddev=1.361969596
  num_samples=306383
  throughput=151866.56

perf top:

 50.01%  [kernel]       [k] __inet6_check_established
 20.65%  [kernel]       [k] __inet_hash_connect
 15.81%  [kernel]       [k] inet6_ehashfn
  2.92%  [kernel]       [k] rcu_all_qs
  2.34%  [kernel]       [k] __cond_resched
  0.50%  [kernel]       [k] _raw_spin_lock
  0.34%  [kernel]       [k] sched_balance_trigger
  0.24%  [kernel]       [k] queued_spin_lock_slowpath

After this patch:

  utime_start=0.315047
  utime_end=9.257617
  stime_start=7.041489
  stime_end=1923.688387
  num_transactions=3057968
  latency_min=0.003041375
  latency_max=7.056589232
  latency_mean=0.141075048    # Better latency metrics
  latency_stddev=0.526900516
  num_samples=312996
  throughput=320677.21        # 111 % increase, and 229 % for the series

perf top: inet6_ehashfn is no longer seen.

 39.67%  [kernel]       [k] __inet_hash_connect
 37.06%  [kernel]       [k] __inet6_check_established
  4.79%  [kernel]       [k] rcu_all_qs
  3.82%  [kernel]       [k] __cond_resched
  1.76%  [kernel]       [k] sched_balance_domains
  0.82%  [kernel]       [k] _raw_spin_lock
  0.81%  [kernel]       [k] sched_balance_rq
  0.81%  [kernel]       [k] sched_balance_trigger
  0.76%  [kernel]       [k] queued_spin_lock_slowpath

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250305034550.879255-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_hashtables.h |  4 +++-
 include/net/ip.h              |  2 +-
 net/ipv4/inet_hashtables.c    | 26 ++++++++++++++++++--------
 net/ipv6/inet6_hashtables.c   | 15 +++++++++++----
 4 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index f447d61d95982..949641e925398 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -527,10 +527,12 @@ static inline void sk_rcv_saddr_set(struct sock *sk, __be32 addr)
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 			struct sock *sk, u64 port_offset,
+			u32 hash_port0,
 			int (*check_established)(struct inet_timewait_death_row *,
 						 struct sock *, __u16,
 						 struct inet_timewait_sock **,
-						 bool rcu_lookup));
+						 bool rcu_lookup,
+						 u32 hash));
 
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk);
diff --git a/include/net/ip.h b/include/net/ip.h
index ce5e59957dd55..8a48ade24620b 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -357,7 +357,7 @@ static inline void inet_get_local_port_range(const struct net *net, int *low, in
 bool inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high);
 
 #ifdef CONFIG_SYSCTL
-static inline bool inet_is_local_reserved_port(struct net *net, unsigned short port)
+static inline bool inet_is_local_reserved_port(const struct net *net, unsigned short port)
 {
 	if (!net->ipv4.sysctl_local_reserved_ports)
 		return false;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index ccf69b534d2e3..5bf163f756e95 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -538,7 +538,8 @@ EXPORT_SYMBOL_GPL(__inet_lookup_established);
 static int __inet_check_established(struct inet_timewait_death_row *death_row,
 				    struct sock *sk, __u16 lport,
 				    struct inet_timewait_sock **twp,
-				    bool rcu_lookup)
+				    bool rcu_lookup,
+				    u32 hash)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -549,8 +550,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row,
 	int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	INET_ADDR_COOKIE(acookie, saddr, daddr);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	unsigned int hash = inet_ehashfn(net, daddr, lport,
-					 saddr, inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	struct inet_timewait_sock *tw = NULL;
 	const struct hlist_nulls_node *node;
@@ -1007,9 +1006,10 @@ static u32 *table_perturb;
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk, u64 port_offset,
+		u32 hash_port0,
 		int (*check_established)(struct inet_timewait_death_row *,
 			struct sock *, __u16, struct inet_timewait_sock **,
-			bool rcu_lookup))
+			bool rcu_lookup, u32 hash))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_bind_hashbucket *head, *head2;
@@ -1027,7 +1027,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 
 	if (port) {
 		local_bh_disable();
-		ret = check_established(death_row, sk, port, NULL, false);
+		ret = check_established(death_row, sk, port, NULL, false,
+					hash_port0 + port);
 		local_bh_enable();
 		return ret;
 	}
@@ -1071,7 +1072,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 				rcu_read_unlock();
 				goto next_port;
 			}
-			if (!check_established(death_row, sk, port, &tw, true))
+			if (!check_established(death_row, sk, port, &tw, true,
+					       hash_port0 + port))
 				break;
 			rcu_read_unlock();
 			goto next_port;
@@ -1090,7 +1092,8 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 					goto next_port_unlock;
 				WARN_ON(hlist_empty(&tb->bhash2));
 				if (!check_established(death_row, sk,
-						       port, &tw, false))
+						       port, &tw, false,
+						       hash_port0 + port))
 					goto ok;
 				goto next_port_unlock;
 			}
@@ -1197,11 +1200,18 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 int inet_hash_connect(struct inet_timewait_death_row *death_row,
 		      struct sock *sk)
 {
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
 	u64 port_offset = 0;
+	u32 hash_port0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet_sk_port_offset(sk);
-	return __inet_hash_connect(death_row, sk, port_offset,
+
+	hash_port0 = inet_ehashfn(net, inet->inet_rcv_saddr, 0,
+				  inet->inet_daddr, inet->inet_dport);
+
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
 				   __inet_check_established);
 }
 EXPORT_SYMBOL_GPL(inet_hash_connect);
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 3d95f1e75a118..76ee521189eb7 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -264,7 +264,8 @@ EXPORT_SYMBOL_GPL(inet6_lookup);
 static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 				     struct sock *sk, const __u16 lport,
 				     struct inet_timewait_sock **twp,
-				     bool rcu_lookup)
+				     bool rcu_lookup,
+				     u32 hash)
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	struct inet_sock *inet = inet_sk(sk);
@@ -274,8 +275,6 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row,
 	struct net *net = sock_net(sk);
 	const int sdif = l3mdev_master_ifindex_by_index(net, dif);
 	const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport);
-	const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr,
-						inet->inet_dport);
 	struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash);
 	struct inet_timewait_sock *tw = NULL;
 	const struct hlist_nulls_node *node;
@@ -354,11 +353,19 @@ static u64 inet6_sk_port_offset(const struct sock *sk)
 int inet6_hash_connect(struct inet_timewait_death_row *death_row,
 		       struct sock *sk)
 {
+	const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr;
+	const struct in6_addr *saddr = &sk->sk_v6_daddr;
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct net *net = sock_net(sk);
 	u64 port_offset = 0;
+	u32 hash_port0;
 
 	if (!inet_sk(sk)->inet_num)
 		port_offset = inet6_sk_port_offset(sk);
-	return __inet_hash_connect(death_row, sk, port_offset,
+
+	hash_port0 = inet6_ehashfn(net, daddr, 0, saddr, inet->inet_dport);
+
+	return __inet_hash_connect(death_row, sk, port_offset, hash_port0,
 				   __inet6_check_established);
 }
 EXPORT_SYMBOL_GPL(inet6_hash_connect);

From 1f6c3899833a328d42647cc3894cda3c9f9abaf8 Mon Sep 17 00:00:00 2001
From: Swathi K S <swathi.ks@samsung.com>
Date: Wed, 5 Mar 2025 14:42:45 +0530
Subject: [PATCH 1738/2753] dt-bindings: net: Add FSD EQoS device tree bindings

Add FSD Ethernet compatible in Synopsys dt-bindings document. Add FSD
Ethernet YAML schema to enable the DT validation.

Signed-off-by: Pankaj Dubey <pankaj.dubey@samsung.com>
Signed-off-by: Ravi Patel <ravi.patel@samsung.com>
Signed-off-by: Swathi K S <swathi.ks@samsung.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250305091246.106626-2-swathi.ks@samsung.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/snps,dwmac.yaml   |   5 +-
 .../bindings/net/tesla,fsd-ethqos.yaml        | 118 ++++++++++++++++++
 2 files changed, 121 insertions(+), 2 deletions(-)
 create mode 100644 Documentation/devicetree/bindings/net/tesla,fsd-ethqos.yaml

diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 91e75eb3f329b..c7004eaa8eae1 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -102,6 +102,7 @@ properties:
         - snps,dwxgmac-2.10
         - starfive,jh7100-dwmac
         - starfive,jh7110-dwmac
+        - tesla,fsd-ethqos
         - thead,th1520-gmac
 
   reg:
@@ -126,7 +127,7 @@ properties:
 
   clocks:
     minItems: 1
-    maxItems: 8
+    maxItems: 10
     additionalItems: true
     items:
       - description: GMAC main clock
@@ -138,7 +139,7 @@ properties:
 
   clock-names:
     minItems: 1
-    maxItems: 8
+    maxItems: 10
     additionalItems: true
     contains:
       enum:
diff --git a/Documentation/devicetree/bindings/net/tesla,fsd-ethqos.yaml b/Documentation/devicetree/bindings/net/tesla,fsd-ethqos.yaml
new file mode 100644
index 0000000000000..dd7481bb16e59
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/tesla,fsd-ethqos.yaml
@@ -0,0 +1,118 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/tesla,fsd-ethqos.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: FSD Ethernet Quality of Service
+
+maintainers:
+  - Swathi K S <swathi.ks@samsung.com>
+
+description:
+  Tesla ethernet devices based on dwmmac support Gigabit ethernet.
+
+allOf:
+  - $ref: snps,dwmac.yaml#
+
+properties:
+  compatible:
+    const: tesla,fsd-ethqos
+
+  reg:
+    maxItems: 1
+
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    items:
+      - const: macirq
+
+  clocks:
+    minItems: 5
+    items:
+      - description: PTP clock
+      - description: Master bus clock
+      - description: Slave bus clock
+      - description: MAC TX clock
+      - description: MAC RX clock
+      - description: Master2 bus clock
+      - description: Slave2 bus clock
+      - description: RX MUX clock
+      - description: PHY RX clock
+      - description: PERIC RGMII clock
+
+  clock-names:
+    minItems: 5
+    items:
+      - const: ptp_ref
+      - const: master_bus
+      - const: slave_bus
+      - const: tx
+      - const: rx
+      - const: master2_bus
+      - const: slave2_bus
+      - const: eqos_rxclk_mux
+      - const: eqos_phyrxclk
+      - const: dout_peric_rgmii_clk
+
+  iommus:
+    maxItems: 1
+
+  phy-mode:
+    enum:
+      - rgmii
+      - rgmii-id
+      - rgmii-rxid
+      - rgmii-txid
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - clocks
+  - clock-names
+  - iommus
+  - phy-mode
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/clock/fsd-clk.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    soc {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ethernet1: ethernet@14300000 {
+            compatible = "tesla,fsd-ethqos";
+            reg = <0x0 0x14300000 0x0 0x10000>;
+            interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+            interrupt-names = "macirq";
+            clocks = <&clock_peric PERIC_EQOS_TOP_IPCLKPORT_CLK_PTP_REF_I>,
+                     <&clock_peric PERIC_EQOS_TOP_IPCLKPORT_ACLK_I>,
+                     <&clock_peric PERIC_EQOS_TOP_IPCLKPORT_HCLK_I>,
+                     <&clock_peric PERIC_EQOS_TOP_IPCLKPORT_RGMII_CLK_I>,
+                     <&clock_peric PERIC_EQOS_TOP_IPCLKPORT_CLK_RX_I>,
+                     <&clock_peric PERIC_BUS_D_PERIC_IPCLKPORT_EQOSCLK>,
+                     <&clock_peric PERIC_BUS_P_PERIC_IPCLKPORT_EQOSCLK>,
+                     <&clock_peric PERIC_EQOS_PHYRXCLK_MUX>,
+                     <&clock_peric PERIC_EQOS_PHYRXCLK>,
+                     <&clock_peric PERIC_DOUT_RGMII_CLK>;
+            clock-names = "ptp_ref", "master_bus", "slave_bus","tx",
+                          "rx", "master2_bus", "slave2_bus", "eqos_rxclk_mux",
+                          "eqos_phyrxclk","dout_peric_rgmii_clk";
+            assigned-clocks = <&clock_peric PERIC_EQOS_PHYRXCLK_MUX>,
+                              <&clock_peric PERIC_EQOS_PHYRXCLK>;
+            assigned-clock-parents = <&clock_peric PERIC_EQOS_PHYRXCLK>;
+            pinctrl-names = "default";
+            pinctrl-0 = <&eth1_tx_clk>, <&eth1_tx_data>, <&eth1_tx_ctrl>,
+                        <&eth1_phy_intr>, <&eth1_rx_clk>, <&eth1_rx_data>,
+                        <&eth1_rx_ctrl>, <&eth1_mdio>;
+            iommus = <&smmu_peric 0x0 0x1>;
+            phy-mode = "rgmii-id";
+        };
+    };
+
+...

From ae7f6b34f5cd3acab74b1042a065b22f873c195a Mon Sep 17 00:00:00 2001
From: Swathi K S <swathi.ks@samsung.com>
Date: Wed, 5 Mar 2025 14:42:46 +0530
Subject: [PATCH 1739/2753] net: stmmac: dwc-qos: Add FSD EQoS support

The FSD SoC contains two instance of the Synopsys DWC ethernet QOS IP core.
The binding that it uses is slightly different from existing ones because
of the integration (clocks, resets).

Signed-off-by: Swathi K S <swathi.ks@samsung.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250305091246.106626-3-swathi.ks@samsung.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index 3f0f4ea6cf2e4..f18fc4f183feb 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -319,6 +319,10 @@ static const struct dwc_eth_dwmac_data tegra_eqos_data = {
 	.stmmac_clk_name = "slave_bus",
 };
 
+static const struct dwc_eth_dwmac_data fsd_eqos_data = {
+	.stmmac_clk_name = "slave_bus",
+};
+
 static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 {
 	const struct dwc_eth_dwmac_data *data;
@@ -359,7 +363,8 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev)
 	plat_dat->stmmac_clk = dwc_eth_find_clk(plat_dat,
 						data->stmmac_clk_name);
 
-	ret = data->probe(pdev, plat_dat, &stmmac_res);
+	if (data->probe)
+		ret = data->probe(pdev, plat_dat, &stmmac_res);
 	if (ret < 0) {
 		dev_err_probe(&pdev->dev, ret, "failed to probe subdriver\n");
 		clk_bulk_disable_unprepare(plat_dat->num_clks, plat_dat->clks);
@@ -400,6 +405,7 @@ static void dwc_eth_dwmac_remove(struct platform_device *pdev)
 static const struct of_device_id dwc_eth_dwmac_match[] = {
 	{ .compatible = "snps,dwc-qos-ethernet-4.10", .data = &dwc_qos_data },
 	{ .compatible = "nvidia,tegra186-eqos", .data = &tegra_eqos_data },
+	{ .compatible = "tesla,fsd-ethqos", .data = &fsd_eqos_data },
 	{ }
 };
 MODULE_DEVICE_TABLE(of, dwc_eth_dwmac_match);

From cd02ab73664dbf08dd5af8c9d3a97e8b6eb75dfc Mon Sep 17 00:00:00 2001
From: Ivan Abramov <i.abramov@mt-integration.ru>
Date: Wed, 5 Mar 2025 12:25:20 +0300
Subject: [PATCH 1740/2753] ptp: ocp: Remove redundant check in
 _signal_summary_show

In the function _signal_summary_show(), there is a NULL-check for
&bp->signal[nr], which cannot actually be NULL.

Therefore, this redundant check can be removed.

Signed-off-by: Ivan Abramov <i.abramov@mt-integration.ru>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250305092520.25817-1-i.abramov@mt-integration.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/ptp/ptp_ocp.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index b651087f426f5..34c616bd0a02f 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -3959,9 +3959,6 @@ _signal_summary_show(struct seq_file *s, struct ptp_ocp *bp, int nr)
 	bool on;
 	u32 val;
 
-	if (!signal)
-		return;
-
 	on = signal->running;
 	sprintf(label, "GEN%d", nr + 1);
 	seq_printf(s, "%7s: %s, period:%llu duty:%d%% phase:%llu pol:%d",

From 072dd84b4c5a85ac0d651aef7fe2ad4342cf4460 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Mar 2025 17:54:21 +0000
Subject: [PATCH 1741/2753] net: stmmac: mostly remove "buf_sz"

The "buf_sz" parameter is not used in the stmmac driver - there is one
place where the value of buf_sz is validated, and two places where it
is written. It is otherwise unused.

Remove these accesses. However, leave the module parameter in place as
removing it could cause module load to fail, breaking user setups.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Furong Xu <0x1207@gmail.com>
Link: https://patch.msgid.link/E1tpswn-005U6I-TU@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 1a928e21b2865..7f1421b9983fd 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -101,6 +101,7 @@ static int tc = TC_DEFAULT;
 module_param(tc, int, 0644);
 MODULE_PARM_DESC(tc, "DMA threshold control value");
 
+/* This is unused */
 #define	DEFAULT_BUFSIZE	1536
 static int buf_sz = DEFAULT_BUFSIZE;
 module_param(buf_sz, int, 0644);
@@ -218,8 +219,6 @@ static void stmmac_verify_args(void)
 {
 	if (unlikely(watchdog < 0))
 		watchdog = TX_TIMEO;
-	if (unlikely((buf_sz < DEFAULT_BUFSIZE) || (buf_sz > BUF_SIZE_16KiB)))
-		buf_sz = DEFAULT_BUFSIZE;
 	if (unlikely((pause < 0) || (pause > 0xffff)))
 		pause = PAUSE_TIME;
 
@@ -4028,7 +4027,6 @@ static int __stmmac_open(struct net_device *dev,
 		}
 	}
 
-	buf_sz = dma_conf->dma_buf_sz;
 	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
 		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
 			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
@@ -7989,9 +7987,6 @@ static int __init stmmac_cmdline_opt(char *str)
 		} else if (!strncmp(opt, "phyaddr:", 8)) {
 			if (kstrtoint(opt + 8, 0, &phyaddr))
 				goto err;
-		} else if (!strncmp(opt, "buf_sz:", 7)) {
-			if (kstrtoint(opt + 7, 0, &buf_sz))
-				goto err;
 		} else if (!strncmp(opt, "tc:", 3)) {
 			if (kstrtoint(opt + 3, 0, &tc))
 				goto err;

From 8e0e8bef484160ac01ea7bcc3122cc1f0405c982 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Wed, 5 Mar 2025 15:49:48 +0100
Subject: [PATCH 1742/2753] tcp: clamp window like before the cleanup

A recent cleanup changed the behaviour of tcp_set_window_clamp(). This
looks unintentional, and affects MPTCP selftests, e.g. some tests
re-establishing a connection after a disconnect are now unstable.

Before the cleanup, this operation was done:

  new_rcv_ssthresh = min(tp->rcv_wnd, new_window_clamp);
  tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh);

The cleanup used the 'clamp' macro which takes 3 arguments -- value,
lowest, and highest -- and returns a value between the lowest and the
highest allowable values. This then assumes ...

  lowest (rcv_ssthresh) <= highest (rcv_wnd)

... which doesn't seem to be always the case here according to the MPTCP
selftests, even when running them without MPTCP, but only TCP.

For example, when we have ...

  rcv_wnd < rcv_ssthresh < new_rcv_ssthresh

... before the cleanup, the rcv_ssthresh was not changed, while after
the cleanup, it is lowered down to rcv_wnd (highest).

During a simple test with TCP, here are the values I observed:

  new_window_clamp (val)  rcv_ssthresh (lo)  rcv_wnd (hi)
      117760   (out)         65495         <  65536
      128512   (out)         109595        >  80256  => lo > hi
      1184975  (out)         328987        <  329088

      113664   (out)         65483         <  65536
      117760   (out)         110968        <  110976
      129024   (out)         116527        >  109696 => lo > hi

Here, we can see that it is not that rare to have rcv_ssthresh (lo)
higher than rcv_wnd (hi), so having a different behaviour when the
clamp() macro is used, even without MPTCP.

Note: new_window_clamp is always out of range (rcv_ssthresh < rcv_wnd)
here, which seems to be generally the case in my tests with small
connections.

I then suggests reverting this part, not to change the behaviour.

Fixes: 863a952eb79a ("tcp: tcp_set_window_clamp() cleanup")
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/551
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Tested-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250305-net-next-fix-tcp-win-clamp-v1-1-12afb705d34e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index eb5a60c7a9ccd..46951e7493084 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3693,7 +3693,7 @@ EXPORT_SYMBOL(tcp_sock_set_keepcnt);
 
 int tcp_set_window_clamp(struct sock *sk, int val)
 {
-	u32 old_window_clamp, new_window_clamp;
+	u32 old_window_clamp, new_window_clamp, new_rcv_ssthresh;
 	struct tcp_sock *tp = tcp_sk(sk);
 
 	if (!val) {
@@ -3714,12 +3714,12 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 	/* Need to apply the reserved mem provisioning only
 	 * when shrinking the window clamp.
 	 */
-	if (new_window_clamp < old_window_clamp)
+	if (new_window_clamp < old_window_clamp) {
 		__tcp_adjust_rcv_ssthresh(sk, new_window_clamp);
-	else
-		tp->rcv_ssthresh = clamp(new_window_clamp,
-					 tp->rcv_ssthresh,
-					 tp->rcv_wnd);
+	} else {
+		new_rcv_ssthresh = min(tp->rcv_wnd, new_window_clamp);
+		tp->rcv_ssthresh = max(new_rcv_ssthresh, tp->rcv_ssthresh);
+	}
 	return 0;
 }
 

From f9d2f5ddd47cd4e8092b0dc1d4cc488d27e5e191 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 4 Mar 2025 15:32:03 -0800
Subject: [PATCH 1743/2753] selftests: net: fix error message in bpf_offload

We hit a following exception on timeout, nmaps is never set:

    Test bpftool bound info reporting (own ns)...
    Traceback (most recent call last):
      File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 1128, in <module>
        check_dev_info(False, "")
      File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 583, in check_dev_info
        maps = bpftool_map_list_wait(expected=2, ns=ns)
      File "/home/virtme/testing-1/tools/testing/selftests/net/./bpf_offload.py", line 215, in bpftool_map_list_wait
        raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))
    NameError: name 'nmaps' is not defined

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250304233204.1139251-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/bpf_offload.py | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index fd0d959914e47..4a9be8c49561f 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -207,9 +207,11 @@ def bpftool_prog_list_wait(expected=0, n_retry=20):
     raise Exception("Time out waiting for program counts to stabilize want %d, have %d" % (expected, nprogs))
 
 def bpftool_map_list_wait(expected=0, n_retry=20, ns=""):
+    nmaps = None
     for i in range(n_retry):
         maps = bpftool_map_list(ns=ns)
-        if len(maps) == expected:
+        nmaps = len(maps)
+        if nmaps == expected:
             return maps
         time.sleep(0.05)
     raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps))

From 56a586961bf89f2461ebb1b16541b7a161f63238 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 4 Mar 2025 15:32:04 -0800
Subject: [PATCH 1744/2753] selftests: net: bpf_offload: add 'libbpf_global' to
 ignored maps

After installing pahole on the CI image we have a new map created
by libbpf. Ignore it otherwise we see:

  Exception: Time out waiting for map counts to stabilize want 2, have 3

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250304233204.1139251-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/bpf_offload.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/bpf_offload.py b/tools/testing/selftests/net/bpf_offload.py
index 4a9be8c49561f..b2c271b79240b 100755
--- a/tools/testing/selftests/net/bpf_offload.py
+++ b/tools/testing/selftests/net/bpf_offload.py
@@ -712,6 +712,7 @@ def test_multi_prog(simdev, sim, obj, modename, modeid):
 base_map_names = [
     'pid_iter.rodata', # created on each bpftool invocation
     'libbpf_det_bind', # created on each bpftool invocation
+    'libbpf_global',
 ]
 
 # Check netdevsim

From 876cfb20e8892143c0c967b3657074f9131f9b5f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 5 Mar 2025 17:54:16 +0000
Subject: [PATCH 1745/2753] net: stmmac: avoid shadowing global buf_sz

stmmac_rx() declares a local variable named "buf_sz" but there is also
a global variable for a module parameter which is called the same. To
avoid confusion, rename the local variable.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Furong Xu <0x1207@gmail.com>
Link: https://patch.msgid.link/E1tpswi-005U6C-Py@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 7f1421b9983fd..767c83b0b2bb4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -5483,10 +5483,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 	struct sk_buff *skb = NULL;
 	struct stmmac_xdp_buff ctx;
 	int xdp_status = 0;
-	int buf_sz;
+	int bufsz;
 
 	dma_dir = page_pool_get_dma_dir(rx_q->page_pool);
-	buf_sz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
+	bufsz = DIV_ROUND_UP(priv->dma_conf.dma_buf_sz, PAGE_SIZE) * PAGE_SIZE;
 	limit = min(priv->dma_conf.dma_rx_size - 1, (unsigned int)limit);
 
 	if (netif_msg_rx_status(priv)) {
@@ -5599,7 +5599,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue)
 			net_prefetch(page_address(buf->page) +
 				     buf->page_offset);
 
-			xdp_init_buff(&ctx.xdp, buf_sz, &rx_q->xdp_rxq);
+			xdp_init_buff(&ctx.xdp, bufsz, &rx_q->xdp_rxq);
 			xdp_prepare_buff(&ctx.xdp, page_address(buf->page),
 					 buf->page_offset, buf1_len, true);
 

From 115ef44a98220fddfab37a39a19370497cd718b9 Mon Sep 17 00:00:00 2001
From: Jun Yang <juny24602@gmail.com>
Date: Wed, 5 Mar 2025 23:44:10 +0800
Subject: [PATCH 1746/2753] sched: address a potential NULL pointer dereference
 in the GRED scheduler.

If kzalloc in gred_init returns a NULL pointer, the code follows the
error handling path, invoking gred_destroy. This, in turn, calls
gred_offload, where memset could receive a NULL pointer as input,
potentially leading to a kernel crash.

When table->opt is NULL in gred_init(), gred_change_table_def()
is not called yet, so it is not necessary to call ->ndo_setup_tc()
in gred_offload().

Signed-off-by: Jun Yang <juny24602@gmail.com>
Reviewed-by: Cong Wang <xiyou.wangcong@gmail.com>
Fixes: f25c0515c521 ("net: sched: gred: dynamically allocate tc_gred_qopt_offload")
Link: https://patch.msgid.link/20250305154410.3505642-1-juny24602@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_gred.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c
index ab6234b4fcd54..532fde548b88f 100644
--- a/net/sched/sch_gred.c
+++ b/net/sched/sch_gred.c
@@ -913,7 +913,8 @@ static void gred_destroy(struct Qdisc *sch)
 	for (i = 0; i < table->DPs; i++)
 		gred_destroy_vq(table->tab[i]);
 
-	gred_offload(sch, TC_GRED_DESTROY);
+	if (table->opt)
+		gred_offload(sch, TC_GRED_DESTROY);
 	kfree(table->opt);
 }
 

From f732549eb303d7e382f5101b82bb6852ad4ad642 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Tue, 4 Mar 2025 11:21:27 +0000
Subject: [PATCH 1747/2753] net: stmmac: simplify phylink_suspend() and
 phylink_resume() calls

Currently, the calls to phylink's suspend and resume functions are
inside overly complex tests, and boil down to:

	if (device_may_wakeup(priv->device) && priv->plat->pmt) {
		call phylink
	} else {
		call phylink and
		if (device_may_wakeup(priv->device))
			do something else
	}

This results in phylink always being called, possibly with differing
arguments for phylink_suspend().

Simplify this code, noting that each site is slightly different due to
the order in which phylink is called and the "something else".

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/E1tpQL1-005St4-Hn@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 22 +++++++------------
 1 file changed, 8 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 767c83b0b2bb4..a3accab213b03 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7842,13 +7842,11 @@ int stmmac_suspend(struct device *dev)
 	mutex_unlock(&priv->lock);
 
 	rtnl_lock();
-	if (device_may_wakeup(priv->device) && priv->plat->pmt) {
-		phylink_suspend(priv->phylink, true);
-	} else {
-		if (device_may_wakeup(priv->device))
-			phylink_speed_down(priv->phylink, false);
-		phylink_suspend(priv->phylink, false);
-	}
+	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
+		phylink_speed_down(priv->phylink, false);
+
+	phylink_suspend(priv->phylink,
+			device_may_wakeup(priv->device) && priv->plat->pmt);
 	rtnl_unlock();
 
 	if (stmmac_fpe_supported(priv))
@@ -7938,13 +7936,9 @@ int stmmac_resume(struct device *dev)
 	}
 
 	rtnl_lock();
-	if (device_may_wakeup(priv->device) && priv->plat->pmt) {
-		phylink_resume(priv->phylink);
-	} else {
-		phylink_resume(priv->phylink);
-		if (device_may_wakeup(priv->device))
-			phylink_speed_up(priv->phylink);
-	}
+	phylink_resume(priv->phylink);
+	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
+		phylink_speed_up(priv->phylink);
 	rtnl_unlock();
 
 	rtnl_lock();

From 54d989d58d2ac87c8504c2306ba8b4957c60e8dc Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 15:21:08 +0100
Subject: [PATCH 1748/2753] net: airoha: Move min/max packet len configuration
 in airoha_dev_open()

In order to align max allowed packet size to the configured mtu, move
REG_GDM_LEN_CFG configuration in airoha_dev_open routine.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-airoha-eth-rx-sg-v1-1-283ebc61120e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index ff837168845d6..a9ed3fc2b5195 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -138,15 +138,10 @@ static void airoha_fe_maccr_init(struct airoha_eth *eth)
 {
 	int p;
 
-	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++) {
+	for (p = 1; p <= ARRAY_SIZE(eth->ports); p++)
 		airoha_fe_set(eth, REG_GDM_FWD_CFG(p),
 			      GDM_TCP_CKSUM | GDM_UDP_CKSUM | GDM_IP4_CKSUM |
 			      GDM_DROP_CRC_ERR);
-		airoha_fe_rmw(eth, REG_GDM_LEN_CFG(p),
-			      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
-			      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
-			      FIELD_PREP(GDM_LONG_LEN_MASK, 4004));
-	}
 
 	airoha_fe_rmw(eth, REG_CDM1_VLAN_CTRL, CDM1_VLAN_MASK,
 		      FIELD_PREP(CDM1_VLAN_MASK, 0x8100));
@@ -1520,9 +1515,9 @@ static void airoha_update_hw_stats(struct airoha_gdm_port *port)
 
 static int airoha_dev_open(struct net_device *dev)
 {
+	int err, len = ETH_HLEN + dev->mtu + ETH_FCS_LEN;
 	struct airoha_gdm_port *port = netdev_priv(dev);
 	struct airoha_qdma *qdma = port->qdma;
-	int err;
 
 	netif_tx_start_all_queues(dev);
 	err = airoha_set_vip_for_gdm_port(port, true);
@@ -1536,6 +1531,11 @@ static int airoha_dev_open(struct net_device *dev)
 		airoha_fe_clear(qdma->eth, REG_GDM_INGRESS_CFG(port->id),
 				GDM_STAG_EN_MASK);
 
+	airoha_fe_rmw(qdma->eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_SHORT_LEN_MASK | GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_SHORT_LEN_MASK, 60) |
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+
 	airoha_qdma_set(qdma, REG_QDMA_GLOBAL_CFG,
 			GLOBAL_CFG_TX_DMA_EN_MASK |
 			GLOBAL_CFG_RX_DMA_EN_MASK);

From e12182ddb6e712951d21a50e2c8ccd700e41a40c Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 15:21:09 +0100
Subject: [PATCH 1749/2753] net: airoha: Enable Rx Scatter-Gather

EN7581 SoC can receive 9k frames. Enable the reception of Scatter-Gather
(SG) frames.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-airoha-eth-rx-sg-v1-2-283ebc61120e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c  | 68 ++++++++++++++---------
 drivers/net/ethernet/airoha/airoha_eth.h  |  1 +
 drivers/net/ethernet/airoha/airoha_regs.h |  5 ++
 3 files changed, 48 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index a9ed3fc2b5195..54a239ab10aaa 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -615,10 +615,10 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		struct airoha_qdma_desc *desc = &q->desc[q->tail];
 		u32 hash, reason, msg1 = le32_to_cpu(desc->msg1);
 		dma_addr_t dma_addr = le32_to_cpu(desc->addr);
+		struct page *page = virt_to_head_page(e->buf);
 		u32 desc_ctrl = le32_to_cpu(desc->ctrl);
 		struct airoha_gdm_port *port;
-		struct sk_buff *skb;
-		int len, p;
+		int data_len, len, p;
 
 		if (!(desc_ctrl & QDMA_DESC_DONE_MASK))
 			break;
@@ -636,30 +636,41 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 		dma_sync_single_for_cpu(eth->dev, dma_addr,
 					SKB_WITH_OVERHEAD(q->buf_size), dir);
 
+		data_len = q->skb ? q->buf_size
+				  : SKB_WITH_OVERHEAD(q->buf_size);
+		if (data_len < len)
+			goto free_frag;
+
 		p = airoha_qdma_get_gdm_port(eth, desc);
-		if (p < 0 || !eth->ports[p]) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			continue;
-		}
+		if (p < 0 || !eth->ports[p])
+			goto free_frag;
 
 		port = eth->ports[p];
-		skb = napi_build_skb(e->buf, q->buf_size);
-		if (!skb) {
-			page_pool_put_full_page(q->page_pool,
-						virt_to_head_page(e->buf),
-						true);
-			break;
+		if (!q->skb) { /* first buffer */
+			q->skb = napi_build_skb(e->buf, q->buf_size);
+			if (!q->skb)
+				goto free_frag;
+
+			__skb_put(q->skb, len);
+			skb_mark_for_recycle(q->skb);
+			q->skb->dev = port->dev;
+			q->skb->protocol = eth_type_trans(q->skb, port->dev);
+			q->skb->ip_summed = CHECKSUM_UNNECESSARY;
+			skb_record_rx_queue(q->skb, qid);
+		} else { /* scattered frame */
+			struct skb_shared_info *shinfo = skb_shinfo(q->skb);
+			int nr_frags = shinfo->nr_frags;
+
+			if (nr_frags >= ARRAY_SIZE(shinfo->frags))
+				goto free_frag;
+
+			skb_add_rx_frag(q->skb, nr_frags, page,
+					e->buf - page_address(page), len,
+					q->buf_size);
 		}
 
-		skb_reserve(skb, 2);
-		__skb_put(skb, len);
-		skb_mark_for_recycle(skb);
-		skb->dev = port->dev;
-		skb->protocol = eth_type_trans(skb, skb->dev);
-		skb->ip_summed = CHECKSUM_UNNECESSARY;
-		skb_record_rx_queue(skb, qid);
+		if (FIELD_GET(QDMA_DESC_MORE_MASK, desc_ctrl))
+			continue;
 
 		if (netdev_uses_dsa(port->dev)) {
 			/* PPE module requires untagged packets to work
@@ -672,22 +683,27 @@ static int airoha_qdma_rx_process(struct airoha_queue *q, int budget)
 
 			if (sptag < ARRAY_SIZE(port->dsa_meta) &&
 			    port->dsa_meta[sptag])
-				skb_dst_set_noref(skb,
+				skb_dst_set_noref(q->skb,
 						  &port->dsa_meta[sptag]->dst);
 		}
 
 		hash = FIELD_GET(AIROHA_RXD4_FOE_ENTRY, msg1);
 		if (hash != AIROHA_RXD4_FOE_ENTRY)
-			skb_set_hash(skb, jhash_1word(hash, 0),
+			skb_set_hash(q->skb, jhash_1word(hash, 0),
 				     PKT_HASH_TYPE_L4);
 
 		reason = FIELD_GET(AIROHA_RXD4_PPE_CPU_REASON, msg1);
 		if (reason == PPE_CPU_REASON_HIT_UNBIND_RATE_REACHED)
 			airoha_ppe_check_skb(eth->ppe, hash);
 
-		napi_gro_receive(&q->napi, skb);
-
 		done++;
+		napi_gro_receive(&q->napi, q->skb);
+		q->skb = NULL;
+		continue;
+free_frag:
+		page_pool_put_full_page(q->page_pool, page, true);
+		dev_kfree_skb(q->skb);
+		q->skb = NULL;
 	}
 	airoha_qdma_fill_rx_queue(q);
 
@@ -762,6 +778,7 @@ static int airoha_qdma_init_rx_queue(struct airoha_queue *q,
 			FIELD_PREP(RX_RING_THR_MASK, thr));
 	airoha_qdma_rmw(qdma, REG_RX_DMA_IDX(qid), RX_RING_DMA_IDX_MASK,
 			FIELD_PREP(RX_RING_DMA_IDX_MASK, q->head));
+	airoha_qdma_set(qdma, REG_RX_SCATTER_CFG(qid), RX_RING_SG_EN_MASK);
 
 	airoha_qdma_fill_rx_queue(q);
 
@@ -1161,7 +1178,6 @@ static int airoha_qdma_hw_init(struct airoha_qdma *qdma)
 	}
 
 	airoha_qdma_wr(qdma, REG_QDMA_GLOBAL_CFG,
-		       GLOBAL_CFG_RX_2B_OFFSET_MASK |
 		       FIELD_PREP(GLOBAL_CFG_DMA_PREFERENCE_MASK, 3) |
 		       GLOBAL_CFG_CPU_TXR_RR_MASK |
 		       GLOBAL_CFG_PAYLOAD_BYTE_SWAP_MASK |
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index b7a3bd7a76b7b..dca96f1df67ee 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -176,6 +176,7 @@ struct airoha_queue {
 
 	struct napi_struct napi;
 	struct page_pool *page_pool;
+	struct sk_buff *skb;
 };
 
 struct airoha_tx_irq_queue {
diff --git a/drivers/net/ethernet/airoha/airoha_regs.h b/drivers/net/ethernet/airoha/airoha_regs.h
index 1aa06cdffe232..8146cde4e8ba3 100644
--- a/drivers/net/ethernet/airoha/airoha_regs.h
+++ b/drivers/net/ethernet/airoha/airoha_regs.h
@@ -626,10 +626,15 @@
 #define REG_RX_DELAY_INT_IDX(_n)	\
 	(((_n) < 16) ? 0x0210 + ((_n) << 5) : 0x0e10 + (((_n) - 16) << 5))
 
+#define REG_RX_SCATTER_CFG(_n)	\
+	(((_n) < 16) ? 0x0214 + ((_n) << 5) : 0x0e14 + (((_n) - 16) << 5))
+
 #define RX_DELAY_INT_MASK		GENMASK(15, 0)
 
 #define RX_RING_DMA_IDX_MASK		GENMASK(15, 0)
 
+#define RX_RING_SG_EN_MASK		BIT(0)
+
 #define REG_INGRESS_TRTCM_CFG		0x0070
 #define INGRESS_TRTCM_EN_MASK		BIT(31)
 #define INGRESS_TRTCM_MODE_MASK		BIT(30)

From 03b1b69f0662c46f258a45e4a7d7837351c11692 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 15:21:10 +0100
Subject: [PATCH 1750/2753] net: airoha: Introduce airoha_dev_change_mtu
 callback

Add airoha_dev_change_mtu callback to update the MTU of a running
device.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-airoha-eth-rx-sg-v1-3-283ebc61120e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 54a239ab10aaa..f3a61879e284a 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1705,6 +1705,20 @@ static void airoha_dev_get_stats64(struct net_device *dev,
 	} while (u64_stats_fetch_retry(&port->stats.syncp, start));
 }
 
+static int airoha_dev_change_mtu(struct net_device *dev, int mtu)
+{
+	struct airoha_gdm_port *port = netdev_priv(dev);
+	struct airoha_eth *eth = port->qdma->eth;
+	u32 len = ETH_HLEN + mtu + ETH_FCS_LEN;
+
+	airoha_fe_rmw(eth, REG_GDM_LEN_CFG(port->id),
+		      GDM_LONG_LEN_MASK,
+		      FIELD_PREP(GDM_LONG_LEN_MASK, len));
+	WRITE_ONCE(dev->mtu, mtu);
+
+	return 0;
+}
+
 static u16 airoha_dev_select_queue(struct net_device *dev, struct sk_buff *skb,
 				   struct net_device *sb_dev)
 {
@@ -2400,6 +2414,7 @@ static const struct net_device_ops airoha_netdev_ops = {
 	.ndo_init		= airoha_dev_init,
 	.ndo_open		= airoha_dev_open,
 	.ndo_stop		= airoha_dev_stop,
+	.ndo_change_mtu		= airoha_dev_change_mtu,
 	.ndo_select_queue	= airoha_dev_select_queue,
 	.ndo_start_xmit		= airoha_dev_xmit,
 	.ndo_get_stats64        = airoha_dev_get_stats64,

From 168ef0c1dee83c401896a0bca680e9f97b1ebd64 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 15:21:11 +0100
Subject: [PATCH 1751/2753] net: airoha: Increase max mtu to 9k

EN7581 SoC supports 9k maximum MTU.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-airoha-eth-rx-sg-v1-4-283ebc61120e@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index dca96f1df67ee..f66b9b736b944 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -20,7 +20,7 @@
 #define AIROHA_MAX_DSA_PORTS		7
 #define AIROHA_MAX_NUM_RSTS		3
 #define AIROHA_MAX_NUM_XSI_RSTS		5
-#define AIROHA_MAX_MTU			2000
+#define AIROHA_MAX_MTU			9216
 #define AIROHA_MAX_PACKET_SIZE		2048
 #define AIROHA_NUM_QOS_CHANNELS		4
 #define AIROHA_NUM_QOS_QUEUES		8

From 35ea4f06fd33fc32f556a0c26d1d8340497fa7f8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 15:38:05 +0100
Subject: [PATCH 1752/2753] net: airoha: Fix lan4 support in
 airoha_qdma_get_gdm_port()

EN7581 SoC supports lan{1,4} ports on MT7530 DSA switch. Fix lan4
reported value in airoha_qdma_get_gdm_port routine.

Fixes: 23020f0493270 ("net: airoha: Introduce ethernet support for EN7581 SoC")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-airoha-eth-fix-lan4-v1-1-832417da4bb5@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index f3a61879e284a..347c11b1fff5b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -589,7 +589,7 @@ static int airoha_qdma_get_gdm_port(struct airoha_eth *eth,
 
 	sport = FIELD_GET(QDMA_ETH_RXMSG_SPORT_MASK, msg1);
 	switch (sport) {
-	case 0x10 ... 0x13:
+	case 0x10 ... 0x14:
 		port = 0;
 		break;
 	case 0x2 ... 0x4:

From a202dfe31cae2f2120297a7142385d80a5577d42 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 4 Mar 2025 16:46:40 +0100
Subject: [PATCH 1753/2753] net: airoha: Enable TSO/Scatter Gather for LAN port

Set net_device vlan_features in order to enable TSO and Scatter Gather
for DSA user ports.

Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-lan-enable-tso-v1-1-b398eb9976ba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index 347c11b1fff5b..e4130576ad10b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2505,6 +2505,7 @@ static int airoha_alloc_gdm_port(struct airoha_eth *eth,
 			   NETIF_F_SG | NETIF_F_TSO |
 			   NETIF_F_HW_TC;
 	dev->features |= dev->hw_features;
+	dev->vlan_features = dev->hw_features;
 	dev->dev.of_node = np;
 	dev->irq = qdma->irq;
 	SET_NETDEV_DEV(dev, eth->dev);

From 1cc3462159babb69c84c39cb1b4e262aef3ea325 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 4 Mar 2025 10:06:15 -0800
Subject: [PATCH 1754/2753] selftests: openvswitch: don't hardcode the drop
 reason subsys

WiFi removed one of their subsys entries from drop reasons, in
commit 286e69677065 ("wifi: mac80211: Drop cooked monitor support")
SKB_DROP_REASON_SUBSYS_OPENVSWITCH is now 2 not 3.
The drop reasons are not uAPI, read the correct value
from debug info.

We need to enable vmlinux BTF, otherwise pahole needs
a few GB of memory to decode the enum name.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Acked-by: Aaron Conole <aconole@redhat.com>
Link: https://patch.msgid.link/20250304180615.945945-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/config                    |  2 ++
 .../testing/selftests/net/openvswitch/openvswitch.sh  | 11 ++++++++---
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index a86f3e752ce2f..b0d0eda829d08 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -18,6 +18,8 @@ CONFIG_DUMMY=y
 CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
+CONFIG_DEBUG_INFO_BTF=y
+CONFIG_DEBUG_INFO_BTF_MODULES=n
 CONFIG_VLAN_8021Q=y
 CONFIG_GENEVE=m
 CONFIG_IFB=y
diff --git a/tools/testing/selftests/net/openvswitch/openvswitch.sh b/tools/testing/selftests/net/openvswitch/openvswitch.sh
index 960e1ab4dd04b..3c8d3455d8e7f 100755
--- a/tools/testing/selftests/net/openvswitch/openvswitch.sh
+++ b/tools/testing/selftests/net/openvswitch/openvswitch.sh
@@ -330,6 +330,11 @@ test_psample() {
 # - drop packets and verify the right drop reason is reported
 test_drop_reason() {
 	which perf >/dev/null 2>&1 || return $ksft_skip
+	which pahole >/dev/null 2>&1 || return $ksft_skip
+
+	ovs_drop_subsys=$(pahole -C skb_drop_reason_subsys |
+			      awk '/OPENVSWITCH/ { print $3; }' |
+			      tr -d ,)
 
 	sbx_add "test_drop_reason" || return $?
 
@@ -373,7 +378,7 @@ test_drop_reason() {
 		"in_port(2),eth(),eth_type(0x0800),ipv4(src=172.31.110.20,proto=1),icmp()" 'drop'
 
 	ovs_drop_record_and_run "test_drop_reason" ip netns exec client ping -c 2 172.31.110.20
-	ovs_drop_reason_count 0x30001 # OVS_DROP_FLOW_ACTION
+	ovs_drop_reason_count 0x${ovs_drop_subsys}0001 # OVS_DROP_FLOW_ACTION
 	if [[ "$?" -ne "2" ]]; then
 		info "Did not detect expected drops: $?"
 		return 1
@@ -390,7 +395,7 @@ test_drop_reason() {
 
 	ovs_drop_record_and_run \
             "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 6000
-	ovs_drop_reason_count 0x30004 # OVS_DROP_EXPLICIT_ACTION_ERROR
+	ovs_drop_reason_count 0x${ovs_drop_subsys}0004 # OVS_DROP_EXPLICIT_ACTION_ERROR
 	if [[ "$?" -ne "1" ]]; then
 		info "Did not detect expected explicit error drops: $?"
 		return 1
@@ -398,7 +403,7 @@ test_drop_reason() {
 
 	ovs_drop_record_and_run \
             "test_drop_reason" ip netns exec client nc -i 1 -zuv 172.31.110.20 7000
-	ovs_drop_reason_count 0x30003 # OVS_DROP_EXPLICIT_ACTION
+	ovs_drop_reason_count 0x${ovs_drop_subsys}0003 # OVS_DROP_EXPLICIT_ACTION
 	if [[ "$?" -ne "1" ]]; then
 		info "Did not detect expected explicit drops: $?"
 		return 1

From e7112524e5e885181cc5ae4d258f33b9dbe0b907 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Mar 2025 08:27:51 -0800
Subject: [PATCH 1755/2753] block: Name the RQF flags enum

Commit 5f89154e8e9e3445f9b59 ("block: Use enum to define RQF_x bit
indexes") converted the RQF flags to an anonymous enum, which was
a beneficial change. This patch goes one step further by naming the enum
as "rqf_flags".

This naming enables exporting these flags to BPF clients, eliminating
the need to duplicate these flags in BPF code. Instead, BPF clients can
now access the same kernel-side values through CO:RE (Compile Once, Run
Everywhere), as shown in this example:

    rqf_stats = bpf_core_enum_value(enum rqf_flags, __RQF_STATS)

Suggested-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://lore.kernel.org/r/20250306-rqf_flags-v1-1-bbd64918b406@debian.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk-mq.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index fa2a76cc2f73d..71f4f0cc3dac6 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -28,7 +28,7 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
 typedef __u32 __bitwise req_flags_t;
 
 /* Keep rqf_name[] in sync with the definitions below */
-enum {
+enum rqf_flags {
 	/* drive already may have started this one */
 	__RQF_STARTED,
 	/* request for flush sequence */

From e5b456a14215e3c0e84844c2926861b972e03632 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Tue, 4 Mar 2025 16:27:52 +0530
Subject: [PATCH 1756/2753] net: ti: icss-iep: Add pwidth configuration for
 perout signal

icss_iep_perout_enable_hw() is a common function for generating
both pps and perout signals. When enabling pps, the application needs
to only pass enable/disable argument, whereas for perout it supports
different flags to configure the signal.

But icss_iep_perout_enable_hw() function is missing to hook the
configuration params passed by the app, causing perout to behave
same a pps (except being able to configure the period). As duty cycle
is also one feature which can configured for perout, incorporate this
in the function to get the expected signal.

Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20250304105753.1552159-2-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 47 ++++++++++++++++++++++--
 1 file changed, 44 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index d59c1744840af..2981c19c48b18 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -406,9 +406,16 @@ static void icss_iep_update_to_next_boundary(struct icss_iep *iep, u64 start_ns)
 static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 				     struct ptp_perout_request *req, int on)
 {
+	struct timespec64 ts;
+	u64 ns_width;
 	int ret;
 	u64 cmp;
 
+	/* Calculate width of the signal for PPS/PEROUT handling */
+	ts.tv_sec = req->on.sec;
+	ts.tv_nsec = req->on.nsec;
+	ns_width = timespec64_to_ns(&ts);
+
 	if (iep->ops && iep->ops->perout_enable) {
 		ret = iep->ops->perout_enable(iep->clockops_data, req, on, &cmp);
 		if (ret)
@@ -419,8 +426,9 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 			regmap_write(iep->map, ICSS_IEP_CMP1_REG0, lower_32_bits(cmp));
 			if (iep->plat_data->flags & ICSS_IEP_64BIT_COUNTER_SUPPORT)
 				regmap_write(iep->map, ICSS_IEP_CMP1_REG1, upper_32_bits(cmp));
-			/* Configure SYNC, 1ms pulse width */
-			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG, 1000000);
+			/* Configure SYNC, based on req on width */
+			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+				     div_u64(ns_width, iep->def_inc));
 			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
 			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG, 0);
 			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
@@ -447,6 +455,8 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 				   + req->period.nsec;
 			icss_iep_update_to_next_boundary(iep, start_ns);
 
+			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
+				     div_u64(ns_width, iep->def_inc));
 			/* Enable Sync in single shot mode  */
 			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
 				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
@@ -474,7 +484,36 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 static int icss_iep_perout_enable(struct icss_iep *iep,
 				  struct ptp_perout_request *req, int on)
 {
-	return -EOPNOTSUPP;
+	int ret = 0;
+
+	/* Reject requests with unsupported flags */
+	if (req->flags & ~PTP_PEROUT_DUTY_CYCLE)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&iep->ptp_clk_mutex);
+
+	if (iep->pps_enabled) {
+		ret = -EBUSY;
+		goto exit;
+	}
+
+	if (iep->perout_enabled == !!on)
+		goto exit;
+
+	/* Set default "on" time (1ms) for the signal if not passed by the app */
+	if (!(req->flags & PTP_PEROUT_DUTY_CYCLE)) {
+		req->on.sec = 0;
+		req->on.nsec = NSEC_PER_MSEC;
+	}
+
+	ret = icss_iep_perout_enable_hw(iep, req, on);
+	if (!ret)
+		iep->perout_enabled = !!on;
+
+exit:
+	mutex_unlock(&iep->ptp_clk_mutex);
+
+	return ret;
 }
 
 static void icss_iep_cap_cmp_work(struct work_struct *work)
@@ -553,6 +592,8 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
 		rq.perout.period.nsec = 0;
 		rq.perout.start.sec = ts.tv_sec + 2;
 		rq.perout.start.nsec = 0;
+		rq.perout.on.sec = 0;
+		rq.perout.on.nsec = NSEC_PER_MSEC;
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);
 	} else {
 		ret = icss_iep_perout_enable_hw(iep, &rq.perout, on);

From 220cb1be647a7ca4e60241405c66f8f612c9b046 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Tue, 4 Mar 2025 16:27:53 +0530
Subject: [PATCH 1757/2753] net: ti: icss-iep: Add phase offset configuration
 for perout signal

icss_iep_perout_enable_hw() is a common function for generating
both pps and perout signals. When enabling pps, the application needs
to only pass enable/disable argument, whereas for perout it supports
different flags to configure the signal.

In case the app passes a valid phase offset value, the signal should
start toggling after that phase offset, else start immediately or
as soon as possible. ICSS_IEP_SYNC_START_REG register take number of
clock cycles to wait before starting the signal after activation time.
Set appropriate value to this register to support phase offset.

Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20250304105753.1552159-3-m-malladi@ti.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 18 ++++++++++++++++--
 1 file changed, 16 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 2981c19c48b18..b4a34c57b7b48 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -407,6 +407,7 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 				     struct ptp_perout_request *req, int on)
 {
 	struct timespec64 ts;
+	u64 ns_start;
 	u64 ns_width;
 	int ret;
 	u64 cmp;
@@ -416,6 +417,14 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 	ts.tv_nsec = req->on.nsec;
 	ns_width = timespec64_to_ns(&ts);
 
+	if (req->flags & PTP_PEROUT_PHASE) {
+		ts.tv_sec = req->phase.sec;
+		ts.tv_nsec = req->phase.nsec;
+		ns_start = timespec64_to_ns(&ts);
+	} else {
+		ns_start = 0;
+	}
+
 	if (iep->ops && iep->ops->perout_enable) {
 		ret = iep->ops->perout_enable(iep->clockops_data, req, on, &cmp);
 		if (ret)
@@ -430,7 +439,8 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
 				     div_u64(ns_width, iep->def_inc));
 			regmap_write(iep->map, ICSS_IEP_SYNC0_PERIOD_REG, 0);
-			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG, 0);
+			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+				     div_u64(ns_start, iep->def_inc));
 			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG, 0); /* one-shot mode */
 			/* Enable CMP 1 */
 			regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
@@ -457,6 +467,8 @@ static int icss_iep_perout_enable_hw(struct icss_iep *iep,
 
 			regmap_write(iep->map, ICSS_IEP_SYNC_PWIDTH_REG,
 				     div_u64(ns_width, iep->def_inc));
+			regmap_write(iep->map, ICSS_IEP_SYNC_START_REG,
+				     div_u64(ns_start, iep->def_inc));
 			/* Enable Sync in single shot mode  */
 			regmap_write(iep->map, ICSS_IEP_SYNC_CTRL_REG,
 				     IEP_SYNC_CTRL_SYNC_N_EN(0) | IEP_SYNC_CTRL_SYNC_EN);
@@ -487,7 +499,8 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 	int ret = 0;
 
 	/* Reject requests with unsupported flags */
-	if (req->flags & ~PTP_PEROUT_DUTY_CYCLE)
+	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
+			  PTP_PEROUT_PHASE))
 		return -EOPNOTSUPP;
 
 	mutex_lock(&iep->ptp_clk_mutex);
@@ -588,6 +601,7 @@ static int icss_iep_pps_enable(struct icss_iep *iep, int on)
 	if (on) {
 		ns = icss_iep_gettime(iep, NULL);
 		ts = ns_to_timespec64(ns);
+		rq.perout.flags = 0;
 		rq.perout.period.sec = 1;
 		rq.perout.period.nsec = 0;
 		rq.perout.start.sec = ts.tv_sec + 2;

From a2f61f1db85532e72fb8a3af51b06df94bb82912 Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:15 +0200
Subject: [PATCH 1758/2753] net/mlx5: Relocate function declarations from
 port.h to mlx5_core.h

The port header is a general file under include, yet it
contains declarations for functions that are either not
exported or exported but not used outside the mlx5_core
driver.

To enhance code organization, we move these declarations
to mlx5_core.h, where they are more appropriately scoped.

This refactor removes unnecessary exported symbols and
prevents unexported functions from being inadvertently
referenced outside of the mlx5_core driver.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250304160620.417580-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   | 85 +++++++++++++++++++
 .../net/ethernet/mellanox/mlx5/core/port.c    | 20 -----
 include/linux/mlx5/port.h                     | 85 +------------------
 3 files changed, 86 insertions(+), 104 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6fef1005c469c..6278b02105dab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -114,6 +114,21 @@ struct mlx5_cmd_alias_obj_create_attr {
 	u8 access_key[ACCESS_KEY_LEN];
 };
 
+struct mlx5_port_eth_proto {
+	u32 cap;
+	u32 admin;
+	u32 oper;
+};
+
+struct mlx5_module_eeprom_query_params {
+	u16 size;
+	u16 offset;
+	u16 i2c_address;
+	u32 page;
+	u32 bank;
+	u32 module_number;
+};
+
 static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
 {
 	struct device *device = dev->device;
@@ -280,6 +295,76 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
 
+void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
+int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
+			       enum mlx5_port_status status);
+int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
+				 enum mlx5_port_status *status);
+int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
+
+int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
+int mlx5_query_port_pause(struct mlx5_core_dev *dev,
+			  u32 *rx_pause, u32 *tx_pause);
+
+int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
+int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
+			u8 *pfc_en_rx);
+
+int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
+				  u16 stall_critical_watermark,
+				  u16 stall_minor_watermark);
+int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
+				    u16 *stall_critical_watermark,
+				    u16 *stall_minor_watermark);
+
+int mlx5_max_tc(struct mlx5_core_dev *mdev);
+int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
+int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
+			    u8 prio, u8 *tc);
+int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
+int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
+			     u8 tc, u8 *tc_group);
+int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
+int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
+				u8 tc, u8 *bw_pct);
+int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				    u8 *max_bw_value,
+				    u8 *max_bw_unit);
+int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
+				   u8 *max_bw_value,
+				   u8 *max_bw_unit);
+int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
+int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
+
+int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen);
+int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen);
+int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable);
+void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
+			 bool *enabled);
+int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
+			     u16 offset, u16 size, u8 *data);
+int
+mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
+				 struct mlx5_module_eeprom_query_params *params,
+				 u8 *data);
+
+int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
+int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
+int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
+int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
+int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
+int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
+
+int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
+			      struct mlx5_port_eth_proto *eproto);
+bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
+u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
+			 bool force_legacy);
+u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
+			      bool force_legacy);
+int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
+
 #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
 			    MLX5_CAP_GEN((mdev), pps_modify) &&		\
 			    MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) &&	\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index 3995df064101d..c7d749e8e1330 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -196,7 +196,6 @@ void mlx5_toggle_port_link(struct mlx5_core_dev *dev)
 	if (ps == MLX5_PORT_UP)
 		mlx5_set_port_admin_status(dev, MLX5_PORT_UP);
 }
-EXPORT_SYMBOL_GPL(mlx5_toggle_port_link);
 
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status)
@@ -210,7 +209,6 @@ int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PAOS, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_admin_status);
 
 int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 				 enum mlx5_port_status *status)
@@ -227,7 +225,6 @@ int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
 	*status = MLX5_GET(paos_reg, out, admin_status);
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_admin_status);
 
 static void mlx5_query_port_mtu(struct mlx5_core_dev *dev, u16 *admin_mtu,
 				u16 *max_mtu, u16 *oper_mtu, u8 port)
@@ -257,7 +254,6 @@ int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				   sizeof(out), MLX5_REG_PMTU, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_mtu);
 
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu,
 			     u8 port)
@@ -447,7 +443,6 @@ int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
 
 	return mlx5_query_mcia(dev, &query, data);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom);
 
 int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 				     struct mlx5_module_eeprom_query_params *params,
@@ -467,7 +462,6 @@ int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
 
 	return mlx5_query_mcia(dev, params, data);
 }
-EXPORT_SYMBOL_GPL(mlx5_query_module_eeprom_by_page);
 
 static int mlx5_query_port_pvlc(struct mlx5_core_dev *dev, u32 *pvlc,
 				int pvlc_size,  u8 local_port)
@@ -518,7 +512,6 @@ int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pause);
 
 int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 			  u32 *rx_pause, u32 *tx_pause)
@@ -538,7 +531,6 @@ int mlx5_query_port_pause(struct mlx5_core_dev *dev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pause);
 
 int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
 				  u16 stall_critical_watermark,
@@ -597,7 +589,6 @@ int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx)
 	return mlx5_core_access_reg(dev, in, sizeof(in), out,
 				    sizeof(out), MLX5_REG_PFCC, 0, 1);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_pfc);
 
 int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 {
@@ -616,7 +607,6 @@ int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx, u8 *pfc_en_rx)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_pfc);
 
 int mlx5_max_tc(struct mlx5_core_dev *mdev)
 {
@@ -667,7 +657,6 @@ int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_prio_tc);
 
 int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 			    u8 prio, u8 *tc)
@@ -689,7 +678,6 @@ int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_prio_tc);
 
 static int mlx5_set_port_qetcr_reg(struct mlx5_core_dev *mdev, u32 *in,
 				   int inlen)
@@ -728,7 +716,6 @@ int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_group);
 
 int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 			     u8 tc, u8 *tc_group)
@@ -749,7 +736,6 @@ int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_group);
 
 int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 {
@@ -763,7 +749,6 @@ int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw)
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_tc_bw_alloc);
 
 int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 				u8 tc, u8 *bw_pct)
@@ -784,7 +769,6 @@ int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_tc_bw_alloc);
 
 int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				    u8 *max_bw_value,
@@ -808,7 +792,6 @@ int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return mlx5_set_port_qetcr_reg(mdev, in, sizeof(in));
 }
-EXPORT_SYMBOL_GPL(mlx5_modify_port_ets_rate_limit);
 
 int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 				   u8 *max_bw_value,
@@ -834,7 +817,6 @@ int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_ets_rate_limit);
 
 int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 {
@@ -845,7 +827,6 @@ int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode)
 	MLX5_SET(set_wol_rol_in, in, wol_mode, wol_mode);
 	return mlx5_cmd_exec_in(mdev, set_wol_rol, in);
 }
-EXPORT_SYMBOL_GPL(mlx5_set_port_wol);
 
 int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 {
@@ -860,7 +841,6 @@ int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode)
 
 	return err;
 }
-EXPORT_SYMBOL_GPL(mlx5_query_port_wol);
 
 int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen)
 {
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index fd625e0dd8691..58770b86f7939 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -61,15 +61,6 @@ enum mlx5_an_status {
 #define MLX5_EEPROM_PAGE_LENGTH		256
 #define MLX5_EEPROM_HIGH_PAGE_LENGTH	128
 
-struct mlx5_module_eeprom_query_params {
-	u16 size;
-	u16 offset;
-	u16 i2c_address;
-	u32 page;
-	u32 bank;
-	u32 module_number;
-};
-
 enum mlx5e_link_mode {
 	MLX5E_1000BASE_CX_SGMII	 = 0,
 	MLX5E_1000BASE_KX	 = 1,
@@ -145,12 +136,6 @@ enum mlx5_ptys_width {
 	MLX5_PTYS_WIDTH_12X	= 1 << 4,
 };
 
-struct mlx5_port_eth_proto {
-	u32 cap;
-	u32 admin;
-	u32 oper;
-};
-
 #define MLX5E_PROT_MASK(link_mode) (1U << link_mode)
 #define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
 	(ext ? MLX5_GET(reg, out, ext_##field) :	\
@@ -163,14 +148,7 @@ int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
 
 int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
 			    u16 *proto_oper, u8 local_port, u8 plane_index);
-void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
-int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
-			       enum mlx5_port_status status);
-int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
-				 enum mlx5_port_status *status);
-int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
-
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
 void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
@@ -178,65 +156,4 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
 			      u8 *vl_hw_cap, u8 local_port);
 
-int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
-int mlx5_query_port_pause(struct mlx5_core_dev *dev,
-			  u32 *rx_pause, u32 *tx_pause);
-
-int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
-int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
-			u8 *pfc_en_rx);
-
-int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
-				  u16 stall_critical_watermark,
-				  u16 stall_minor_watermark);
-int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
-				    u16 *stall_critical_watermark, u16 *stall_minor_watermark);
-
-int mlx5_max_tc(struct mlx5_core_dev *mdev);
-
-int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
-int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
-			    u8 prio, u8 *tc);
-int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
-int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
-			     u8 tc, u8 *tc_group);
-int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
-int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
-				u8 tc, u8 *bw_pct);
-int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
-				    u8 *max_bw_value,
-				    u8 *max_bw_unit);
-int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
-				   u8 *max_bw_value,
-				   u8 *max_bw_unit);
-int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
-int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
-
-int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen);
-int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen);
-int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable);
-void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
-			 bool *enabled);
-int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
-			     u16 offset, u16 size, u8 *data);
-int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
-				     struct mlx5_module_eeprom_query_params *params, u8 *data);
-
-int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
-int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
-
-int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
-int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
-int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
-int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
-
-int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
-			      struct mlx5_port_eth_proto *eproto);
-bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy);
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy);
-int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-
 #endif /* __MLX5_PORT_H__ */

From 65a5d3557184974608761b6abae0701f7e63a6de Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:16 +0200
Subject: [PATCH 1759/2753] net/mlx5: Refactor link speed handling with
 mlx5_link_info struct

Introduce struct mlx5_link_info with a speed field and change the
types of mlx5e_link_speed and mlx5e_ext_link_speed from arrays of
u32 to arrays of struct mlx5_link_info. These arrays are renamed
to mlx5e_link_info and mlx5e_ext_link_info, respectively.

This change prepares for a future patch that will introduce a lanes
field in struct mlx5_link_info and add lanes mapping alongside the
speed for each link mode in the two arrays.

Additionally, rename function mlx5_port_speed2linkmodes() to
mlx5_port_info2linkmodes() and function mlx5_port_ptys2speed()
to mlx5_port_ptys2info() and update the speed parameter/return
type to struct mlx5_link_info, in preparation for the upcoming
patch where these functions will also utilize the lanes field.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250304160620.417580-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/mellanox/mlx5/core/en/port.c |   9 +-
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  |  24 ++-
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  14 +-
 .../net/ethernet/mellanox/mlx5/core/port.c    | 144 +++++++++---------
 4 files changed, 103 insertions(+), 88 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
index f62fbfb67a1ba..6049ccf475bc4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/port.c
@@ -80,6 +80,7 @@ int mlx5_port_set_eth_ptys(struct mlx5_core_dev *dev, bool an_disable,
 int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
 	struct mlx5_port_eth_proto eproto;
+	const struct mlx5_link_info *info;
 	bool force_legacy = false;
 	bool ext;
 	int err;
@@ -94,9 +95,13 @@ int mlx5e_port_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 		if (err)
 			goto out;
 	}
-	*speed = mlx5_port_ptys2speed(mdev, eproto.oper, force_legacy);
-	if (!(*speed))
+	info = mlx5_port_ptys2info(mdev, eproto.oper, force_legacy);
+	if (!info) {
+		*speed = SPEED_UNKNOWN;
 		err = -EINVAL;
+		goto out;
+	}
+	*speed = info->speed;
 
 out:
 	return err;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3b2efde9dda24..fdb3e118c2444 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -1082,23 +1082,21 @@ static void get_speed_duplex(struct net_device *netdev,
 			     struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
-	u32 speed = SPEED_UNKNOWN;
+	const struct mlx5_link_info *info;
 	u8 duplex = DUPLEX_UNKNOWN;
+	u32 speed = SPEED_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
 
-	speed = mlx5_port_ptys2speed(priv->mdev, eth_proto_oper, force_legacy);
-	if (!speed) {
-		if (data_rate_oper)
-			speed = 100 * data_rate_oper;
-		else
-			speed = SPEED_UNKNOWN;
-		goto out;
+	info = mlx5_port_ptys2info(priv->mdev, eth_proto_oper, force_legacy);
+	if (info) {
+		speed = info->speed;
+		duplex = DUPLEX_FULL;
+	} else if (data_rate_oper) {
+		speed = 100 * data_rate_oper;
 	}
 
-	duplex = DUPLEX_FULL;
-
 out:
 	link_ksettings->base.speed = speed;
 	link_ksettings->base.duplex = duplex;
@@ -1349,6 +1347,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
 	struct mlx5_port_eth_proto eproto;
+	struct mlx5_link_info info = {};
 	const unsigned long *adver;
 	bool an_changes = false;
 	u8 an_disable_admin;
@@ -1359,7 +1358,6 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	u32 link_modes;
 	u8 an_status;
 	u8 autoneg;
-	u32 speed;
 	bool ext;
 	int err;
 
@@ -1367,7 +1365,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 
 	adver = link_ksettings->link_modes.advertising;
 	autoneg = link_ksettings->base.autoneg;
-	speed = link_ksettings->base.speed;
+	info.speed = link_ksettings->base.speed;
 
 	ext_supported = mlx5_ptys_ext_supported(mdev);
 	ext_requested = ext_link_mode_requested(adver);
@@ -1384,7 +1382,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 		goto out;
 	}
 	link_modes = autoneg == AUTONEG_ENABLE ? ethtool2ptys_adver_func(adver) :
-		mlx5_port_speed2linkmodes(mdev, speed, !ext);
+		mlx5_port_info2linkmodes(mdev, &info, !ext);
 
 	err = mlx5e_speed_validate(priv->netdev, ext, link_modes, autoneg);
 	if (err)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 6278b02105dab..9639e44f71edc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -129,6 +129,10 @@ struct mlx5_module_eeprom_query_params {
 	u32 module_number;
 };
 
+struct mlx5_link_info {
+	u32 speed;
+};
+
 static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
 {
 	struct device *device = dev->device;
@@ -359,10 +363,12 @@ int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
 			      struct mlx5_port_eth_proto *eproto);
 bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy);
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy);
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy);
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy);
 int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
 
 #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) &&		\
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index c7d749e8e1330..e1b69416f3915 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1038,56 +1038,57 @@ int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio)
 }
 
 /* speed in units of 1Mb */
-static const u32 mlx5e_link_speed[MLX5E_LINK_MODES_NUMBER] = {
-	[MLX5E_1000BASE_CX_SGMII] = 1000,
-	[MLX5E_1000BASE_KX]       = 1000,
-	[MLX5E_10GBASE_CX4]       = 10000,
-	[MLX5E_10GBASE_KX4]       = 10000,
-	[MLX5E_10GBASE_KR]        = 10000,
-	[MLX5E_20GBASE_KR2]       = 20000,
-	[MLX5E_40GBASE_CR4]       = 40000,
-	[MLX5E_40GBASE_KR4]       = 40000,
-	[MLX5E_56GBASE_R4]        = 56000,
-	[MLX5E_10GBASE_CR]        = 10000,
-	[MLX5E_10GBASE_SR]        = 10000,
-	[MLX5E_10GBASE_ER]        = 10000,
-	[MLX5E_40GBASE_SR4]       = 40000,
-	[MLX5E_40GBASE_LR4]       = 40000,
-	[MLX5E_50GBASE_SR2]       = 50000,
-	[MLX5E_100GBASE_CR4]      = 100000,
-	[MLX5E_100GBASE_SR4]      = 100000,
-	[MLX5E_100GBASE_KR4]      = 100000,
-	[MLX5E_100GBASE_LR4]      = 100000,
-	[MLX5E_100BASE_TX]        = 100,
-	[MLX5E_1000BASE_T]        = 1000,
-	[MLX5E_10GBASE_T]         = 10000,
-	[MLX5E_25GBASE_CR]        = 25000,
-	[MLX5E_25GBASE_KR]        = 25000,
-	[MLX5E_25GBASE_SR]        = 25000,
-	[MLX5E_50GBASE_CR2]       = 50000,
-	[MLX5E_50GBASE_KR2]       = 50000,
+static const struct mlx5_link_info mlx5e_link_info[MLX5E_LINK_MODES_NUMBER] = {
+	[MLX5E_1000BASE_CX_SGMII] = {.speed = 1000},
+	[MLX5E_1000BASE_KX]       = {.speed = 1000},
+	[MLX5E_10GBASE_CX4]       = {.speed = 10000},
+	[MLX5E_10GBASE_KX4]       = {.speed = 10000},
+	[MLX5E_10GBASE_KR]        = {.speed = 10000},
+	[MLX5E_20GBASE_KR2]       = {.speed = 20000},
+	[MLX5E_40GBASE_CR4]       = {.speed = 40000},
+	[MLX5E_40GBASE_KR4]       = {.speed = 40000},
+	[MLX5E_56GBASE_R4]        = {.speed = 56000},
+	[MLX5E_10GBASE_CR]        = {.speed = 10000},
+	[MLX5E_10GBASE_SR]        = {.speed = 10000},
+	[MLX5E_10GBASE_ER]        = {.speed = 10000},
+	[MLX5E_40GBASE_SR4]       = {.speed = 40000},
+	[MLX5E_40GBASE_LR4]       = {.speed = 40000},
+	[MLX5E_50GBASE_SR2]       = {.speed = 50000},
+	[MLX5E_100GBASE_CR4]      = {.speed = 100000},
+	[MLX5E_100GBASE_SR4]      = {.speed = 100000},
+	[MLX5E_100GBASE_KR4]      = {.speed = 100000},
+	[MLX5E_100GBASE_LR4]      = {.speed = 100000},
+	[MLX5E_100BASE_TX]        = {.speed = 100},
+	[MLX5E_1000BASE_T]        = {.speed = 1000},
+	[MLX5E_10GBASE_T]         = {.speed = 10000},
+	[MLX5E_25GBASE_CR]        = {.speed = 25000},
+	[MLX5E_25GBASE_KR]        = {.speed = 25000},
+	[MLX5E_25GBASE_SR]        = {.speed = 25000},
+	[MLX5E_50GBASE_CR2]       = {.speed = 50000},
+	[MLX5E_50GBASE_KR2]       = {.speed = 50000},
 };
 
-static const u32 mlx5e_ext_link_speed[MLX5E_EXT_LINK_MODES_NUMBER] = {
-	[MLX5E_SGMII_100M] = 100,
-	[MLX5E_1000BASE_X_SGMII] = 1000,
-	[MLX5E_5GBASE_R] = 5000,
-	[MLX5E_10GBASE_XFI_XAUI_1] = 10000,
-	[MLX5E_40GBASE_XLAUI_4_XLPPI_4] = 40000,
-	[MLX5E_25GAUI_1_25GBASE_CR_KR] = 25000,
-	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = 50000,
-	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR] = 50000,
-	[MLX5E_CAUI_4_100GBASE_CR4_KR4] = 100000,
-	[MLX5E_100GAUI_2_100GBASE_CR2_KR2] = 100000,
-	[MLX5E_200GAUI_4_200GBASE_CR4_KR4] = 200000,
-	[MLX5E_400GAUI_8_400GBASE_CR8] = 400000,
-	[MLX5E_100GAUI_1_100GBASE_CR_KR] = 100000,
-	[MLX5E_200GAUI_2_200GBASE_CR2_KR2] = 200000,
-	[MLX5E_400GAUI_4_400GBASE_CR4_KR4] = 400000,
-	[MLX5E_800GAUI_8_800GBASE_CR8_KR8] = 800000,
-	[MLX5E_200GAUI_1_200GBASE_CR1_KR1] = 200000,
-	[MLX5E_400GAUI_2_400GBASE_CR2_KR2] = 400000,
-	[MLX5E_800GAUI_4_800GBASE_CR4_KR4] = 800000,
+static const struct mlx5_link_info
+mlx5e_ext_link_info[MLX5E_EXT_LINK_MODES_NUMBER] = {
+	[MLX5E_SGMII_100M]			= {.speed = 100},
+	[MLX5E_1000BASE_X_SGMII]		= {.speed = 1000},
+	[MLX5E_5GBASE_R]			= {.speed = 5000},
+	[MLX5E_10GBASE_XFI_XAUI_1]		= {.speed = 10000},
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= {.speed = 40000},
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= {.speed = 25000},
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = {.speed = 50000},
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= {.speed = 50000},
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= {.speed = 100000},
+	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= {.speed = 100000},
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= {.speed = 200000},
+	[MLX5E_400GAUI_8_400GBASE_CR8]		= {.speed = 400000},
+	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= {.speed = 100000},
+	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= {.speed = 200000},
+	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= {.speed = 400000},
+	[MLX5E_800GAUI_8_800GBASE_CR8_KR8]	= {.speed = 800000},
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1]	= {.speed = 200000},
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2]	= {.speed = 400000},
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4]	= {.speed = 800000},
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
@@ -1125,44 +1126,49 @@ bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev)
 	return !!eproto.cap;
 }
 
-static void mlx5e_port_get_speed_arr(struct mlx5_core_dev *mdev,
-				     const u32 **arr, u32 *size,
-				     bool force_legacy)
+static void mlx5e_port_get_link_mode_info_arr(struct mlx5_core_dev *mdev,
+					      const struct mlx5_link_info **arr,
+					      u32 *size,
+					      bool force_legacy)
 {
 	bool ext = force_legacy ? false : mlx5_ptys_ext_supported(mdev);
 
-	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_speed) :
-		      ARRAY_SIZE(mlx5e_link_speed);
-	*arr  = ext ? mlx5e_ext_link_speed : mlx5e_link_speed;
+	*size = ext ? ARRAY_SIZE(mlx5e_ext_link_info) :
+		      ARRAY_SIZE(mlx5e_link_info);
+	*arr  = ext ? mlx5e_ext_link_info : mlx5e_link_info;
 }
 
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy)
+const struct mlx5_link_info *mlx5_port_ptys2info(struct mlx5_core_dev *mdev,
+						 u32 eth_proto_oper,
+						 bool force_legacy)
 {
 	unsigned long temp = eth_proto_oper;
-	const u32 *table;
-	u32 speed = 0;
+	const struct mlx5_link_info *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	i = find_first_bit(&temp, max_size);
 	if (i < max_size)
-		speed = table[i];
-	return speed;
+		return &table[i];
+
+	return NULL;
 }
 
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy)
+u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
+			     struct mlx5_link_info *info,
+			     bool force_legacy)
 {
+	const struct mlx5_link_info *table;
 	u32 link_modes = 0;
-	const u32 *table;
 	u32 max_size;
 	int i;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, force_legacy);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
+					  force_legacy);
 	for (i = 0; i < max_size; ++i) {
-		if (table[i] == speed)
+		if (table[i].speed == info->speed)
 			link_modes |= MLX5E_PROT_MASK(i);
 	}
 	return link_modes;
@@ -1170,9 +1176,9 @@ u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
 
 int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 {
+	const struct mlx5_link_info *table;
 	struct mlx5_port_eth_proto eproto;
 	u32 max_speed = 0;
-	const u32 *table;
 	u32 max_size;
 	bool ext;
 	int err;
@@ -1183,10 +1189,10 @@ int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed)
 	if (err)
 		return err;
 
-	mlx5e_port_get_speed_arr(mdev, &table, &max_size, false);
+	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size, false);
 	for (i = 0; i < max_size; ++i)
 		if (eproto.cap & MLX5E_PROT_MASK(i))
-			max_speed = max(max_speed, table[i]);
+			max_speed = max(max_speed, table[i].speed);
 
 	*speed = max_speed;
 	return 0;

From 7e959797f0218f8b8a5e38068a55661610eb935e Mon Sep 17 00:00:00 2001
From: Shahar Shitrit <shshitrit@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:17 +0200
Subject: [PATCH 1760/2753] net/mlx5e: Enable lanes configuration when
 auto-negotiation is off

Currently, when auto-negotiation is disabled, the driver retrieves
the speed and converts it into all link modes that correspond to
that speed. With this patch, we add the ability to set the number
of lanes, so that the combination of speed and lanes corresponds to
exactly one specific link mode for the extended bit map.

For the legacy bit map the driver sets all link modes correspond to
speed and lanes.

This change provides users with the option to set a specific link
mode, rather than enabling all link modes associated with a given
speed when auto-negotiation is off.

Signed-off-by: Shahar Shitrit <shshitrit@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250304160620.417580-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/mellanox/mlx5/core/en_ethtool.c  | 23 +++--
 .../ethernet/mellanox/mlx5/core/mlx5_core.h   |  1 +
 .../net/ethernet/mellanox/mlx5/core/port.c    | 98 ++++++++++---------
 3 files changed, 67 insertions(+), 55 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index fdb3e118c2444..fdf9e9bb99ace 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -42,6 +42,9 @@
 #include "lib/clock.h"
 #include "en/fs_ethtool.h"
 
+#define LANES_UNKNOWN		 0
+#define MAX_LANES		 8
+
 void mlx5e_ethtool_get_drvinfo(struct mlx5e_priv *priv,
 			       struct ethtool_drvinfo *drvinfo)
 {
@@ -1076,15 +1079,16 @@ static void ptys2ethtool_supported_advertised_port(struct mlx5_core_dev *mdev,
 	}
 }
 
-static void get_speed_duplex(struct net_device *netdev,
-			     u32 eth_proto_oper, bool force_legacy,
-			     u16 data_rate_oper,
-			     struct ethtool_link_ksettings *link_ksettings)
+static void get_link_properties(struct net_device *netdev,
+				u32 eth_proto_oper, bool force_legacy,
+				u16 data_rate_oper,
+				struct ethtool_link_ksettings *link_ksettings)
 {
 	struct mlx5e_priv *priv = netdev_priv(netdev);
 	const struct mlx5_link_info *info;
 	u8 duplex = DUPLEX_UNKNOWN;
 	u32 speed = SPEED_UNKNOWN;
+	u32 lanes = LANES_UNKNOWN;
 
 	if (!netif_carrier_ok(netdev))
 		goto out;
@@ -1092,14 +1096,17 @@ static void get_speed_duplex(struct net_device *netdev,
 	info = mlx5_port_ptys2info(priv->mdev, eth_proto_oper, force_legacy);
 	if (info) {
 		speed = info->speed;
+		lanes = info->lanes;
 		duplex = DUPLEX_FULL;
 	} else if (data_rate_oper) {
 		speed = 100 * data_rate_oper;
+		lanes = MAX_LANES;
 	}
 
 out:
-	link_ksettings->base.speed = speed;
 	link_ksettings->base.duplex = duplex;
+	link_ksettings->base.speed = speed;
+	link_ksettings->lanes = lanes;
 }
 
 static void get_supported(struct mlx5_core_dev *mdev, u32 eth_proto_cap,
@@ -1236,8 +1243,8 @@ static int mlx5e_ethtool_get_link_ksettings(struct mlx5e_priv *priv,
 	get_supported(mdev, eth_proto_cap, link_ksettings);
 	get_advertising(eth_proto_admin, tx_pause, rx_pause, link_ksettings,
 			admin_ext);
-	get_speed_duplex(priv->netdev, eth_proto_oper, !admin_ext,
-			 data_rate_oper, link_ksettings);
+	get_link_properties(priv->netdev, eth_proto_oper, !admin_ext,
+			    data_rate_oper, link_ksettings);
 
 	eth_proto_oper = eth_proto_oper ? eth_proto_oper : eth_proto_cap;
 	connector_type = connector_type < MLX5E_CONNECTOR_TYPE_NUMBER ?
@@ -1366,6 +1373,7 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
 	adver = link_ksettings->link_modes.advertising;
 	autoneg = link_ksettings->base.autoneg;
 	info.speed = link_ksettings->base.speed;
+	info.lanes = link_ksettings->lanes;
 
 	ext_supported = mlx5_ptys_ext_supported(mdev);
 	ext_requested = ext_link_mode_requested(adver);
@@ -2613,6 +2621,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev,
 }
 
 const struct ethtool_ops mlx5e_ethtool_ops = {
+	.cap_link_lanes_supported = true,
 	.cap_rss_ctx_supported	= true,
 	.rxfh_per_ctx_key	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 9639e44f71edc..2e02bdea8361d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -131,6 +131,7 @@ struct mlx5_module_eeprom_query_params {
 
 struct mlx5_link_info {
 	u32 speed;
+	u32 lanes;
 };
 
 static inline void mlx5_printk(struct mlx5_core_dev *dev, int level, const char *format, ...)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/port.c b/drivers/net/ethernet/mellanox/mlx5/core/port.c
index e1b69416f3915..549f1066d2a50 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/port.c
@@ -1039,56 +1039,56 @@ int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio)
 
 /* speed in units of 1Mb */
 static const struct mlx5_link_info mlx5e_link_info[MLX5E_LINK_MODES_NUMBER] = {
-	[MLX5E_1000BASE_CX_SGMII] = {.speed = 1000},
-	[MLX5E_1000BASE_KX]       = {.speed = 1000},
-	[MLX5E_10GBASE_CX4]       = {.speed = 10000},
-	[MLX5E_10GBASE_KX4]       = {.speed = 10000},
-	[MLX5E_10GBASE_KR]        = {.speed = 10000},
-	[MLX5E_20GBASE_KR2]       = {.speed = 20000},
-	[MLX5E_40GBASE_CR4]       = {.speed = 40000},
-	[MLX5E_40GBASE_KR4]       = {.speed = 40000},
-	[MLX5E_56GBASE_R4]        = {.speed = 56000},
-	[MLX5E_10GBASE_CR]        = {.speed = 10000},
-	[MLX5E_10GBASE_SR]        = {.speed = 10000},
-	[MLX5E_10GBASE_ER]        = {.speed = 10000},
-	[MLX5E_40GBASE_SR4]       = {.speed = 40000},
-	[MLX5E_40GBASE_LR4]       = {.speed = 40000},
-	[MLX5E_50GBASE_SR2]       = {.speed = 50000},
-	[MLX5E_100GBASE_CR4]      = {.speed = 100000},
-	[MLX5E_100GBASE_SR4]      = {.speed = 100000},
-	[MLX5E_100GBASE_KR4]      = {.speed = 100000},
-	[MLX5E_100GBASE_LR4]      = {.speed = 100000},
-	[MLX5E_100BASE_TX]        = {.speed = 100},
-	[MLX5E_1000BASE_T]        = {.speed = 1000},
-	[MLX5E_10GBASE_T]         = {.speed = 10000},
-	[MLX5E_25GBASE_CR]        = {.speed = 25000},
-	[MLX5E_25GBASE_KR]        = {.speed = 25000},
-	[MLX5E_25GBASE_SR]        = {.speed = 25000},
-	[MLX5E_50GBASE_CR2]       = {.speed = 50000},
-	[MLX5E_50GBASE_KR2]       = {.speed = 50000},
+	[MLX5E_1000BASE_CX_SGMII]	= {.speed = 1000, .lanes = 1},
+	[MLX5E_1000BASE_KX]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_CX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KX4]		= {.speed = 10000, .lanes = 4},
+	[MLX5E_10GBASE_KR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_20GBASE_KR2]		= {.speed = 20000, .lanes = 2},
+	[MLX5E_40GBASE_CR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_KR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_56GBASE_R4]		= {.speed = 56000, .lanes = 4},
+	[MLX5E_10GBASE_CR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_SR]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_10GBASE_ER]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_SR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_40GBASE_LR4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_50GBASE_SR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_100GBASE_CR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_SR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GBASE_LR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100BASE_TX]		= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_T]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_10GBASE_T]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_25GBASE_CR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_25GBASE_SR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GBASE_CR2]		= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GBASE_KR2]		= {.speed = 50000, .lanes = 2},
 };
 
 static const struct mlx5_link_info
 mlx5e_ext_link_info[MLX5E_EXT_LINK_MODES_NUMBER] = {
-	[MLX5E_SGMII_100M]			= {.speed = 100},
-	[MLX5E_1000BASE_X_SGMII]		= {.speed = 1000},
-	[MLX5E_5GBASE_R]			= {.speed = 5000},
-	[MLX5E_10GBASE_XFI_XAUI_1]		= {.speed = 10000},
-	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= {.speed = 40000},
-	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= {.speed = 25000},
-	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2] = {.speed = 50000},
-	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= {.speed = 50000},
-	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= {.speed = 100000},
-	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= {.speed = 100000},
-	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= {.speed = 200000},
-	[MLX5E_400GAUI_8_400GBASE_CR8]		= {.speed = 400000},
-	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= {.speed = 100000},
-	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= {.speed = 200000},
-	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= {.speed = 400000},
-	[MLX5E_800GAUI_8_800GBASE_CR8_KR8]	= {.speed = 800000},
-	[MLX5E_200GAUI_1_200GBASE_CR1_KR1]	= {.speed = 200000},
-	[MLX5E_400GAUI_2_400GBASE_CR2_KR2]	= {.speed = 400000},
-	[MLX5E_800GAUI_4_800GBASE_CR4_KR4]	= {.speed = 800000},
+	[MLX5E_SGMII_100M]			= {.speed = 100, .lanes = 1},
+	[MLX5E_1000BASE_X_SGMII]		= {.speed = 1000, .lanes = 1},
+	[MLX5E_5GBASE_R]			= {.speed = 5000, .lanes = 1},
+	[MLX5E_10GBASE_XFI_XAUI_1]		= {.speed = 10000, .lanes = 1},
+	[MLX5E_40GBASE_XLAUI_4_XLPPI_4]		= {.speed = 40000, .lanes = 4},
+	[MLX5E_25GAUI_1_25GBASE_CR_KR]		= {.speed = 25000, .lanes = 1},
+	[MLX5E_50GAUI_2_LAUI_2_50GBASE_CR2_KR2]	= {.speed = 50000, .lanes = 2},
+	[MLX5E_50GAUI_1_LAUI_1_50GBASE_CR_KR]	= {.speed = 50000, .lanes = 1},
+	[MLX5E_CAUI_4_100GBASE_CR4_KR4]		= {.speed = 100000, .lanes = 4},
+	[MLX5E_100GAUI_2_100GBASE_CR2_KR2]	= {.speed = 100000, .lanes = 2},
+	[MLX5E_200GAUI_4_200GBASE_CR4_KR4]	= {.speed = 200000, .lanes = 4},
+	[MLX5E_400GAUI_8_400GBASE_CR8]		= {.speed = 400000, .lanes = 8},
+	[MLX5E_100GAUI_1_100GBASE_CR_KR]	= {.speed = 100000, .lanes = 1},
+	[MLX5E_200GAUI_2_200GBASE_CR2_KR2]	= {.speed = 200000, .lanes = 2},
+	[MLX5E_400GAUI_4_400GBASE_CR4_KR4]	= {.speed = 400000, .lanes = 4},
+	[MLX5E_800GAUI_8_800GBASE_CR8_KR8]	= {.speed = 800000, .lanes = 8},
+	[MLX5E_200GAUI_1_200GBASE_CR1_KR1]	= {.speed = 200000, .lanes = 1},
+	[MLX5E_400GAUI_2_400GBASE_CR2_KR2]	= {.speed = 400000, .lanes = 2},
+	[MLX5E_800GAUI_4_800GBASE_CR4_KR4]	= {.speed = 800000, .lanes = 4},
 };
 
 int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
@@ -1168,8 +1168,10 @@ u32 mlx5_port_info2linkmodes(struct mlx5_core_dev *mdev,
 	mlx5e_port_get_link_mode_info_arr(mdev, &table, &max_size,
 					  force_legacy);
 	for (i = 0; i < max_size; ++i) {
-		if (table[i].speed == info->speed)
-			link_modes |= MLX5E_PROT_MASK(i);
+		if (table[i].speed == info->speed) {
+			if (!info->lanes || table[i].lanes == info->lanes)
+				link_modes |= MLX5E_PROT_MASK(i);
+		}
 	}
 	return link_modes;
 }

From 5aa2e6de86d5408ec759a817877b4399172c02e3 Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:18 +0200
Subject: [PATCH 1761/2753] net/mlx5: Lag, Enable Multiport E-Switch offloads
 on 8 ports LAG

Patch [1] added mlx5 driver support for 8 ports HCAs which are available
since ConnectX-8. Now that Multiport E-Switch is tested, we can enable
it by removing flag MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS.

[1]
commit e0e6adfe8c20 ("net/mlx5: Enable 8 ports LAG")

Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250304160620.417580-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index ffac0bd6c8952..cbde54324059f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -65,7 +65,6 @@ static int mlx5_mpesw_metadata_set(struct mlx5_lag *ldev)
 	return err;
 }
 
-#define MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS 4
 static int enable_mpesw(struct mlx5_lag *ldev)
 {
 	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
@@ -77,9 +76,6 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 		return -EINVAL;
 
 	dev0 = ldev->pf[idx].dev;
-	if (ldev->ports > MLX5_LAG_MPESW_OFFLOADS_SUPPORTED_PORTS)
-		return -EOPNOTSUPP;
-
 	if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS ||
 	    !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) ||
 	    !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) ||

From 348ed4b20546b80a67bb87b0fb32397efbae4c87 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:19 +0200
Subject: [PATCH 1762/2753] net/mlx5e: Separate address related variables to be
 in struct

Prepare the code to addition of prefix handling logic which is needed
to support matching logic based on source and/or destination network
prefixes.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250304160620.417580-6-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 32 ++++----
 .../mellanox/mlx5/core/en_accel/ipsec.h       | 26 +++----
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 75 +++++++++++--------
 3 files changed, 68 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index 501709ac310f2..beb7275d721ab 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -277,12 +277,12 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	case XFRM_DEV_OFFLOAD_IN:
 		src = attrs->dmac;
 		dst = attrs->smac;
-		pkey = &attrs->saddr.a4;
+		pkey = &attrs->addrs.saddr.a4;
 		break;
 	case XFRM_DEV_OFFLOAD_OUT:
 		src = attrs->smac;
 		dst = attrs->dmac;
-		pkey = &attrs->daddr.a4;
+		pkey = &attrs->addrs.daddr.a4;
 		break;
 	default:
 		return;
@@ -374,9 +374,10 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	attrs->spi = be32_to_cpu(x->id.spi);
 
 	/* source , destination ips */
-	memcpy(&attrs->saddr, x->props.saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, x->id.daddr.a6, sizeof(attrs->daddr));
-	attrs->family = x->props.family;
+	memcpy(&attrs->addrs.saddr, x->props.saddr.a6,
+	       sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, x->id.daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = x->props.family;
 	attrs->type = x->xso.type;
 	attrs->reqid = x->props.reqid;
 	attrs->upspec.dport = ntohs(x->sel.dport);
@@ -428,7 +429,8 @@ static int mlx5e_xfrm_validate_state(struct mlx5_core_dev *mdev,
 	}
 	if (x->encap) {
 		if (!(mlx5_ipsec_device_caps(mdev) & MLX5_IPSEC_CAP_ESPINUDP)) {
-			NL_SET_ERR_MSG_MOD(extack, "Encapsulation is not supported");
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Encapsulation is not supported");
 			return -EINVAL;
 		}
 
@@ -853,13 +855,13 @@ static int mlx5e_ipsec_netevent_event(struct notifier_block *nb,
 	xa_for_each_marked(&ipsec->sadb, idx, sa_entry, MLX5E_IPSEC_TUNNEL_SA) {
 		attrs = &sa_entry->attrs;
 
-		if (attrs->family == AF_INET) {
-			if (!neigh_key_eq32(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq32(n, &attrs->daddr.a4))
+		if (attrs->addrs.family == AF_INET) {
+			if (!neigh_key_eq32(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq32(n, &attrs->addrs.daddr.a4))
 				continue;
 		} else {
-			if (!neigh_key_eq128(n, &attrs->saddr.a4) &&
-			    !neigh_key_eq128(n, &attrs->daddr.a4))
+			if (!neigh_key_eq128(n, &attrs->addrs.saddr.a4) &&
+			    !neigh_key_eq128(n, &attrs->addrs.daddr.a4))
 				continue;
 		}
 
@@ -1035,7 +1037,7 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	 * by removing always available headers.
 	 */
 	headers = sizeof(struct ethhdr);
-	if (sa_entry->attrs.family == AF_INET)
+	if (sa_entry->attrs.addrs.family == AF_INET)
 		headers += sizeof(struct iphdr);
 	else
 		headers += sizeof(struct ipv6hdr);
@@ -1116,9 +1118,9 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 	sel = &x->selector;
 	memset(attrs, 0, sizeof(*attrs));
 
-	memcpy(&attrs->saddr, sel->saddr.a6, sizeof(attrs->saddr));
-	memcpy(&attrs->daddr, sel->daddr.a6, sizeof(attrs->daddr));
-	attrs->family = sel->family;
+	memcpy(&attrs->addrs.saddr, sel->saddr.a6, sizeof(attrs->addrs.saddr));
+	memcpy(&attrs->addrs.daddr, sel->daddr.a6, sizeof(attrs->addrs.daddr));
+	attrs->addrs.family = sel->family;
 	attrs->dir = x->xdo.dir;
 	attrs->action = x->action;
 	attrs->type = XFRM_DEV_OFFLOAD_PACKET;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index ad8db9e1fd1d0..37ef1e3311352 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -76,11 +76,7 @@ struct mlx5_replay_esn {
 	u8 trigger : 1;
 };
 
-struct mlx5_accel_esp_xfrm_attrs {
-	u32   spi;
-	u32   mode;
-	struct aes_gcm_keymat aes_gcm;
-
+struct mlx5e_ipsec_addr {
 	union {
 		__be32 a4;
 		__be32 a6[4];
@@ -90,13 +86,19 @@ struct mlx5_accel_esp_xfrm_attrs {
 		__be32 a4;
 		__be32 a6[4];
 	} daddr;
+	u8 family;
+};
 
+struct mlx5_accel_esp_xfrm_attrs {
+	u32   spi;
+	u32   mode;
+	struct aes_gcm_keymat aes_gcm;
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
 	u8 dir : 2;
 	u8 type : 2;
 	u8 drop : 1;
 	u8 encap : 1;
-	u8 family;
 	struct mlx5_replay_esn replay_esn;
 	u32 authsize;
 	u32 reqid;
@@ -279,18 +281,8 @@ struct mlx5e_ipsec_sa_entry {
 };
 
 struct mlx5_accel_pol_xfrm_attrs {
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} saddr;
-
-	union {
-		__be32 a4;
-		__be32 a6[4];
-	} daddr;
-
+	struct mlx5e_ipsec_addr addrs;
 	struct upspec upspec;
-	u8 family;
 	u8 action;
 	u8 type : 2;
 	u8 dir : 2;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index d51ace739637b..23b63dea2f7fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1484,9 +1484,12 @@ static void tx_ft_put_policy(struct mlx5e_ipsec *ipsec, u32 prio, int type)
 	mutex_unlock(&tx->ft.mutex);
 }
 
-static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr4(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = &addrs->saddr.a4;
+	__be32 *daddr = &addrs->daddr.a4;
+
 	if (!*saddr && !*daddr)
 		return;
 
@@ -1510,9 +1513,12 @@ static void setup_fte_addr4(struct mlx5_flow_spec *spec, __be32 *saddr,
 	}
 }
 
-static void setup_fte_addr6(struct mlx5_flow_spec *spec, __be32 *saddr,
-			    __be32 *daddr)
+static void setup_fte_addr6(struct mlx5_flow_spec *spec,
+			    struct mlx5e_ipsec_addr *addrs)
 {
+	__be32 *saddr = addrs->saddr.a6;
+	__be32 *daddr = addrs->daddr.a6;
+
 	if (addr6_all_zero(saddr) && addr6_all_zero(daddr))
 		return;
 
@@ -1722,7 +1728,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 	if (attrs->dir == XFRM_DEV_OFFLOAD_OUT) {
 		bfflen += sizeof(*esp_hdr) + 8;
 
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			bfflen += sizeof(*iphdr);
 			break;
@@ -1739,7 +1745,7 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		return -ENOMEM;
 
 	eth_hdr = (struct ethhdr *)reformatbf;
-	switch (attrs->family) {
+	switch (attrs->addrs.family) {
 	case AF_INET:
 		eth_hdr->h_proto = htons(ETH_P_IP);
 		break;
@@ -1762,11 +1768,11 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 		reformat_params->param_0 = attrs->authsize;
 
 		hdr = reformatbf + sizeof(*eth_hdr);
-		switch (attrs->family) {
+		switch (attrs->addrs.family) {
 		case AF_INET:
 			iphdr = (struct iphdr *)hdr;
-			memcpy(&iphdr->saddr, &attrs->saddr.a4, 4);
-			memcpy(&iphdr->daddr, &attrs->daddr.a4, 4);
+			memcpy(&iphdr->saddr, &attrs->addrs.saddr.a4, 4);
+			memcpy(&iphdr->daddr, &attrs->addrs.daddr.a4, 4);
 			iphdr->version = 4;
 			iphdr->ihl = 5;
 			iphdr->ttl = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1775,8 +1781,8 @@ setup_pkt_tunnel_reformat(struct mlx5_core_dev *mdev,
 			break;
 		case AF_INET6:
 			ipv6hdr = (struct ipv6hdr *)hdr;
-			memcpy(&ipv6hdr->saddr, &attrs->saddr.a6, 16);
-			memcpy(&ipv6hdr->daddr, &attrs->daddr.a6, 16);
+			memcpy(&ipv6hdr->saddr, &attrs->addrs.saddr.a6, 16);
+			memcpy(&ipv6hdr->daddr, &attrs->addrs.daddr.a6, 16);
 			ipv6hdr->nexthdr = IPPROTO_ESP;
 			ipv6hdr->version = 6;
 			ipv6hdr->hop_limit = IPSEC_TUNNEL_DEFAULT_TTL;
@@ -1810,7 +1816,7 @@ static int get_reformat_type(struct mlx5_accel_esp_xfrm_attrs *attrs)
 			return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP;
 		return MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT;
 	case XFRM_DEV_OFFLOAD_OUT:
-		if (attrs->family == AF_INET) {
+		if (attrs->addrs.family == AF_INET) {
 			if (attrs->encap)
 				return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4;
 			return MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4;
@@ -2003,7 +2009,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5_fc *counter;
 	int err = 0;
 
-	rx = rx_ft_get(mdev, ipsec, attrs->family, attrs->type);
+	rx = rx_ft_get(mdev, ipsec, attrs->addrs.family, attrs->type);
 	if (IS_ERR(rx))
 		return PTR_ERR(rx);
 
@@ -2013,10 +2019,10 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_spi(spec, attrs->spi, attrs->encap);
 	if (!attrs->encap)
@@ -2116,7 +2122,7 @@ static int rx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 err_mod_header:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put(ipsec, attrs->family, attrs->type);
+	rx_ft_put(ipsec, attrs->addrs.family, attrs->type);
 	return err;
 }
 
@@ -2148,10 +2154,10 @@ static int tx_add_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 
 	switch (attrs->type) {
 	case XFRM_DEV_OFFLOAD_CRYPTO:
-		if (attrs->family == AF_INET)
-			setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+		if (attrs->addrs.family == AF_INET)
+			setup_fte_addr4(spec, &attrs->addrs);
 		else
-			setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+			setup_fte_addr6(spec, &attrs->addrs);
 		setup_fte_spi(spec, attrs->spi, false);
 		setup_fte_esp(spec);
 		setup_fte_reg_a(spec);
@@ -2235,10 +2241,10 @@ static int tx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	}
 
 	tx = ipsec_tx(ipsec, attrs->type);
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -2308,12 +2314,12 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 	struct mlx5e_ipsec_rx *rx;
 	int err, dstn = 0;
 
-	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->family, attrs->prio,
-			      attrs->type);
+	ft = rx_ft_get_policy(mdev, pol_entry->ipsec, attrs->addrs.family,
+			      attrs->prio, attrs->type);
 	if (IS_ERR(ft))
 		return PTR_ERR(ft);
 
-	rx = ipsec_rx(pol_entry->ipsec, attrs->family, attrs->type);
+	rx = ipsec_rx(pol_entry->ipsec, attrs->addrs.family, attrs->type);
 
 	spec = kvzalloc(sizeof(*spec), GFP_KERNEL);
 	if (!spec) {
@@ -2321,10 +2327,10 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 		goto err_alloc;
 	}
 
-	if (attrs->family == AF_INET)
-		setup_fte_addr4(spec, &attrs->saddr.a4, &attrs->daddr.a4);
+	if (attrs->addrs.family == AF_INET)
+		setup_fte_addr4(spec, &attrs->addrs);
 	else
-		setup_fte_addr6(spec, attrs->saddr.a6, attrs->daddr.a6);
+		setup_fte_addr6(spec, &attrs->addrs);
 
 	setup_fte_no_frags(spec);
 	setup_fte_upper_proto_match(spec, &attrs->upspec);
@@ -2364,7 +2370,8 @@ static int rx_add_policy(struct mlx5e_ipsec_pol_entry *pol_entry)
 err_action:
 	kvfree(spec);
 err_alloc:
-	rx_ft_put_policy(pol_entry->ipsec, attrs->family, attrs->prio, attrs->type);
+	rx_ft_put_policy(pol_entry->ipsec, attrs->addrs.family, attrs->prio,
+			 attrs->type);
 	return err;
 }
 
@@ -2638,7 +2645,8 @@ void mlx5e_accel_ipsec_fs_del_rule(struct mlx5e_ipsec_sa_entry *sa_entry)
 		mlx5_fc_destroy(mdev, ipsec_rule->replay.fc);
 	}
 	mlx5_esw_ipsec_rx_id_mapping_remove(sa_entry);
-	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.family, sa_entry->attrs.type);
+	rx_ft_put(sa_entry->ipsec, sa_entry->attrs.addrs.family,
+		  sa_entry->attrs.type);
 }
 
 int mlx5e_accel_ipsec_fs_add_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
@@ -2674,7 +2682,8 @@ void mlx5e_accel_ipsec_fs_del_pol(struct mlx5e_ipsec_pol_entry *pol_entry)
 	mlx5e_ipsec_unblock_tc_offload(pol_entry->ipsec->mdev);
 
 	if (pol_entry->attrs.dir == XFRM_DEV_OFFLOAD_IN) {
-		rx_ft_put_policy(pol_entry->ipsec, pol_entry->attrs.family,
+		rx_ft_put_policy(pol_entry->ipsec,
+				 pol_entry->attrs.addrs.family,
 				 pol_entry->attrs.prio, pol_entry->attrs.type);
 		return;
 	}
@@ -2814,7 +2823,7 @@ bool mlx5e_ipsec_fs_tunnel_enabled(struct mlx5e_ipsec_sa_entry *sa_entry)
 	struct mlx5e_ipsec_rx *rx;
 	struct mlx5e_ipsec_tx *tx;
 
-	rx = ipsec_rx(sa_entry->ipsec, attrs->family, attrs->type);
+	rx = ipsec_rx(sa_entry->ipsec, attrs->addrs.family, attrs->type);
 	tx = ipsec_tx(sa_entry->ipsec, attrs->type);
 	if (sa_entry->attrs.dir == XFRM_DEV_OFFLOAD_OUT)
 		return tx->allow_tunnel_mode;

From ca7992f52c2cb5ef61fbfa590a2d7c926f290237 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@nvidia.com>
Date: Tue, 4 Mar 2025 18:06:20 +0200
Subject: [PATCH 1763/2753] net/mlx5e: Properly match IPsec subnet addresses

Existing match criteria didn't allow to match whole subnet and
only by specific addresses only. This caused to tunnel mode do not
forward such traffic through relevant SA.

In tunnel mode, policies look like this:
src 192.169.0.0/16 dst 192.169.0.0/16
        dir out priority 383615 ptype main
        tmpl src 192.169.101.2 dst 192.169.101.1
                proto esp spi 0xc5141c18 reqid 1 mode tunnel
        crypto offload parameters: dev eth2 mode packet

In this case, the XFRM core code handled all subnet calculations and
forwarded network address to the drivers e.g. 192.169.0.0.

For mlx5 devices, there is a need to set relevant prefix e.g. 0xFFFF00
to perform flow steering match operation.

Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250304160620.417580-7-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../mellanox/mlx5/core/en_accel/ipsec.c       | 49 +++++++++++++++++++
 .../mellanox/mlx5/core/en_accel/ipsec.h       |  9 +++-
 .../mellanox/mlx5/core/en_accel/ipsec_fs.c    | 20 +++++---
 3 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
index beb7275d721ab..782f6d51434d4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.c
@@ -303,6 +303,16 @@ static void mlx5e_ipsec_init_macs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	neigh_release(n);
 }
 
+static void mlx5e_ipsec_state_mask(struct mlx5e_ipsec_addr *addrs)
+{
+	/*
+	 * State doesn't have subnet prefixes in outer headers.
+	 * The match is performed for exaxt source/destination addresses.
+	 */
+	memset(addrs->smask.m6, 0xFF, sizeof(__be32) * 4);
+	memset(addrs->dmask.m6, 0xFF, sizeof(__be32) * 4);
+}
+
 void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 					struct mlx5_accel_esp_xfrm_attrs *attrs)
 {
@@ -378,6 +388,7 @@ void mlx5e_ipsec_build_accel_xfrm_attrs(struct mlx5e_ipsec_sa_entry *sa_entry,
 	       sizeof(attrs->addrs.saddr));
 	memcpy(&attrs->addrs.daddr, x->id.daddr.a6, sizeof(attrs->addrs.daddr));
 	attrs->addrs.family = x->props.family;
+	mlx5e_ipsec_state_mask(&attrs->addrs);
 	attrs->type = x->xso.type;
 	attrs->reqid = x->props.reqid;
 	attrs->upspec.dport = ntohs(x->sel.dport);
@@ -1046,6 +1057,43 @@ static void mlx5e_xfrm_update_stats(struct xfrm_state *x)
 	x->curlft.bytes += success_bytes - headers * success_packets;
 }
 
+static __be32 word_to_mask(int prefix)
+{
+	if (prefix < 0)
+		return 0;
+
+	if (!prefix || prefix > 31)
+		return cpu_to_be32(0xFFFFFFFF);
+
+	return cpu_to_be32(((1U << prefix) - 1) << (32 - prefix));
+}
+
+static void mlx5e_ipsec_policy_mask(struct mlx5e_ipsec_addr *addrs,
+				    struct xfrm_selector *sel)
+{
+	int i;
+
+	if (addrs->family == AF_INET) {
+		addrs->smask.m4 = word_to_mask(sel->prefixlen_s);
+		addrs->saddr.a4 &= addrs->smask.m4;
+		addrs->dmask.m4 = word_to_mask(sel->prefixlen_d);
+		addrs->daddr.a4 &= addrs->dmask.m4;
+		return;
+	}
+
+	for (i = 0; i < 4; i++) {
+		if (sel->prefixlen_s != 32 * i)
+			addrs->smask.m6[i] =
+				word_to_mask(sel->prefixlen_s - 32 * i);
+		addrs->saddr.a6[i] &= addrs->smask.m6[i];
+
+		if (sel->prefixlen_d != 32 * i)
+			addrs->dmask.m6[i] =
+				word_to_mask(sel->prefixlen_d - 32 * i);
+		addrs->daddr.a6[i] &= addrs->dmask.m6[i];
+	}
+}
+
 static int mlx5e_xfrm_validate_policy(struct mlx5_core_dev *mdev,
 				      struct xfrm_policy *x,
 				      struct netlink_ext_ack *extack)
@@ -1121,6 +1169,7 @@ mlx5e_ipsec_build_accel_pol_attrs(struct mlx5e_ipsec_pol_entry *pol_entry,
 	memcpy(&attrs->addrs.saddr, sel->saddr.a6, sizeof(attrs->addrs.saddr));
 	memcpy(&attrs->addrs.daddr, sel->daddr.a6, sizeof(attrs->addrs.daddr));
 	attrs->addrs.family = sel->family;
+	mlx5e_ipsec_policy_mask(&attrs->addrs, sel);
 	attrs->dir = x->xdo.dir;
 	attrs->action = x->action;
 	attrs->type = XFRM_DEV_OFFLOAD_PACKET;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
index 37ef1e3311352..a63c2289f8af9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h
@@ -81,11 +81,18 @@ struct mlx5e_ipsec_addr {
 		__be32 a4;
 		__be32 a6[4];
 	} saddr;
-
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} smask;
 	union {
 		__be32 a4;
 		__be32 a6[4];
 	} daddr;
+	union {
+		__be32 m4;
+		__be32 m6[4];
+	} dmask;
 	u8 family;
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
index 23b63dea2f7fe..98b6a3a623f99 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_fs.c
@@ -1488,7 +1488,9 @@ static void setup_fte_addr4(struct mlx5_flow_spec *spec,
 			    struct mlx5e_ipsec_addr *addrs)
 {
 	__be32 *saddr = &addrs->saddr.a4;
+	__be32 *smask = &addrs->smask.m4;
 	__be32 *daddr = &addrs->daddr.a4;
+	__be32 *dmask = &addrs->dmask.m4;
 
 	if (!*saddr && !*daddr)
 		return;
@@ -1501,15 +1503,15 @@ static void setup_fte_addr4(struct mlx5_flow_spec *spec,
 	if (*saddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), saddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv4_layout.ipv4), smask, 4);
 	}
 
 	if (*daddr) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), daddr, 4);
-		MLX5_SET_TO_ONES(fte_match_param, spec->match_criteria,
-				 outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv4_layout.ipv4), dmask, 4);
 	}
 }
 
@@ -1517,7 +1519,9 @@ static void setup_fte_addr6(struct mlx5_flow_spec *spec,
 			    struct mlx5e_ipsec_addr *addrs)
 {
 	__be32 *saddr = addrs->saddr.a6;
+	__be32 *smask = addrs->smask.m6;
 	__be32 *daddr = addrs->daddr.a6;
+	__be32 *dmask = addrs->dmask.m6;
 
 	if (addr6_all_zero(saddr) && addr6_all_zero(daddr))
 		return;
@@ -1530,15 +1534,15 @@ static void setup_fte_addr6(struct mlx5_flow_spec *spec,
 	if (!addr6_all_zero(saddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), saddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.src_ipv4_src_ipv6.ipv6_layout.ipv6), dmask, 16);
 	}
 
 	if (!addr6_all_zero(daddr)) {
 		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_value,
 				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), daddr, 16);
-		memset(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
-				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), 0xff, 16);
+		memcpy(MLX5_ADDR_OF(fte_match_param, spec->match_criteria,
+				    outer_headers.dst_ipv4_dst_ipv6.ipv6_layout.ipv6), smask, 16);
 	}
 }
 

From 00a7d39898c8010bfd5ff62af31ca5db34421b38 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Thu, 6 Mar 2025 18:25:35 -1000
Subject: [PATCH 1764/2753] fs/pipe: add simpler helpers for common cases

The fix to atomically read the pipe head and tail state when not holding
the pipe mutex has caused a number of headaches due to the size change
of the involved types.

It turns out that we don't have _that_ many places that access these
fields directly and were affected, but we have more than we strictly
should have, because our low-level helper functions have been designed
to have intimate knowledge of how the pipes work.

And as a result, that random noise of direct 'pipe->head' and
'pipe->tail' accesses makes it harder to pinpoint any actual potential
problem spots remaining.

For example, we didn't have a "is the pipe full" helper function, but
instead had a "given these pipe buffer indexes and this pipe size, is
the pipe full".  That's because some low-level pipe code does actually
want that much more complicated interface.

But most other places literally just want a "is the pipe full" helper,
and not having it meant that those places ended up being unnecessarily
much too aware of this all.

It would have been much better if only the very core pipe code that
cared had been the one aware of this all.

So let's fix it - better late than never.  This just introduces the
trivial wrappers for "is this pipe full or empty" and to get how many
pipe buffers are used, so that instead of writing

        if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))

the places that literally just want to know if a pipe is full can just
say

        if (pipe_is_full(pipe))

instead.  The existing trivial cases were converted with a 'sed' script.

This cuts down on the places that access pipe->head and pipe->tail
directly outside of the pipe code (and core splice code) quite a lot.

The splice code in particular still revels in doing the direct low-level
accesses, and the fuse fuse_dev_splice_write() code also seems a bit
unnecessarily eager to go very low-level, but it's at least a bit better
than it used to be.

Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 drivers/char/virtio_console.c |  4 ++--
 fs/fuse/dev.c                 |  2 +-
 fs/pipe.c                     |  6 +++---
 fs/splice.c                   | 20 ++++++++++----------
 include/linux/pipe_fs_i.h     | 27 +++++++++++++++++++++++++++
 mm/filemap.c                  |  7 +++----
 mm/shmem.c                    |  6 +++---
 7 files changed, 49 insertions(+), 23 deletions(-)

diff --git a/drivers/char/virtio_console.c b/drivers/char/virtio_console.c
index 24442485e73e7..18f92dd44d456 100644
--- a/drivers/char/virtio_console.c
+++ b/drivers/char/virtio_console.c
@@ -923,14 +923,14 @@ static ssize_t port_fops_splice_write(struct pipe_inode_info *pipe,
 
 	pipe_lock(pipe);
 	ret = 0;
-	if (pipe_empty(pipe->head, pipe->tail))
+	if (pipe_is_empty(pipe))
 		goto error_out;
 
 	ret = wait_port_writable(port, filp->f_flags & O_NONBLOCK);
 	if (ret < 0)
 		goto error_out;
 
-	occupancy = pipe_occupancy(pipe->head, pipe->tail);
+	occupancy = pipe_buf_usage(pipe);
 	buf = alloc_buf(port->portdev->vdev, 0, occupancy);
 
 	if (!buf) {
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 3c9caafca9e29..2c3a4d09e500f 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -1457,7 +1457,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 	if (ret < 0)
 		goto out;
 
-	if (pipe_occupancy(pipe->head, pipe->tail) + cs.nr_segs > pipe->max_usage) {
+	if (pipe_buf_usage(pipe) + cs.nr_segs > pipe->max_usage) {
 		ret = -EIO;
 		goto out;
 	}
diff --git a/fs/pipe.c b/fs/pipe.c
index 5c872775a6db9..4d0799e4e7196 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -394,7 +394,7 @@ pipe_read(struct kiocb *iocb, struct iov_iter *to)
 		wake_next_reader = true;
 		mutex_lock(&pipe->mutex);
 	}
-	if (pipe_empty(pipe->head, pipe->tail))
+	if (pipe_is_empty(pipe))
 		wake_next_reader = false;
 	mutex_unlock(&pipe->mutex);
 
@@ -577,11 +577,11 @@ pipe_write(struct kiocb *iocb, struct iov_iter *from)
 		kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN);
 		wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe));
 		mutex_lock(&pipe->mutex);
-		was_empty = pipe_empty(pipe->head, pipe->tail);
+		was_empty = pipe_is_empty(pipe);
 		wake_next_writer = true;
 	}
 out:
-	if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (pipe_is_full(pipe))
 		wake_next_writer = false;
 	mutex_unlock(&pipe->mutex);
 
diff --git a/fs/splice.c b/fs/splice.c
index 28cfa63aa2364..23fa5561b9441 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -331,7 +331,7 @@ ssize_t copy_splice_read(struct file *in, loff_t *ppos,
 	int i;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 	npages = DIV_ROUND_UP(len, PAGE_SIZE);
@@ -527,7 +527,7 @@ static int splice_from_pipe_next(struct pipe_inode_info *pipe, struct splice_des
 		return -ERESTARTSYS;
 
 repeat:
-	while (pipe_empty(pipe->head, pipe->tail)) {
+	while (pipe_is_empty(pipe)) {
 		if (!pipe->writers)
 			return 0;
 
@@ -820,7 +820,7 @@ ssize_t splice_to_socket(struct pipe_inode_info *pipe, struct file *out,
 		if (signal_pending(current))
 			break;
 
-		while (pipe_empty(pipe->head, pipe->tail)) {
+		while (pipe_is_empty(pipe)) {
 			ret = 0;
 			if (!pipe->writers)
 				goto out;
@@ -968,7 +968,7 @@ static ssize_t do_splice_read(struct file *in, loff_t *ppos,
 		return 0;
 
 	/* Don't try to read more the pipe has space for. */
-	p_space = pipe->max_usage - pipe_occupancy(pipe->head, pipe->tail);
+	p_space = pipe->max_usage - pipe_buf_usage(pipe);
 	len = min_t(size_t, len, p_space << PAGE_SHIFT);
 
 	if (unlikely(len > MAX_RW_COUNT))
@@ -1080,7 +1080,7 @@ ssize_t splice_direct_to_actor(struct file *in, struct splice_desc *sd,
 	more = sd->flags & SPLICE_F_MORE;
 	sd->flags |= SPLICE_F_MORE;
 
-	WARN_ON_ONCE(!pipe_empty(pipe->head, pipe->tail));
+	WARN_ON_ONCE(!pipe_is_empty(pipe));
 
 	while (len) {
 		size_t read_len;
@@ -1268,7 +1268,7 @@ static int wait_for_space(struct pipe_inode_info *pipe, unsigned flags)
 			send_sig(SIGPIPE, current, 0);
 			return -EPIPE;
 		}
-		if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+		if (!pipe_is_full(pipe))
 			return 0;
 		if (flags & SPLICE_F_NONBLOCK)
 			return -EAGAIN;
@@ -1652,13 +1652,13 @@ static int ipipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check the pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (!pipe_empty(pipe->head, pipe->tail))
+	if (!pipe_is_empty(pipe))
 		return 0;
 
 	ret = 0;
 	pipe_lock(pipe);
 
-	while (pipe_empty(pipe->head, pipe->tail)) {
+	while (pipe_is_empty(pipe)) {
 		if (signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
@@ -1688,13 +1688,13 @@ static int opipe_prep(struct pipe_inode_info *pipe, unsigned int flags)
 	 * Check pipe occupancy without the inode lock first. This function
 	 * is speculative anyways, so missing one is ok.
 	 */
-	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+	if (!pipe_is_full(pipe))
 		return 0;
 
 	ret = 0;
 	pipe_lock(pipe);
 
-	while (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	while (pipe_is_full(pipe)) {
 		if (!pipe->readers) {
 			send_sig(SIGPIPE, current, 0);
 			ret = -EPIPE;
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index 4d0a2267e6efc..b698758000f8b 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -208,6 +208,33 @@ static inline bool pipe_full(unsigned int head, unsigned int tail,
 	return pipe_occupancy(head, tail) >= limit;
 }
 
+/**
+ * pipe_is_full - Return true if the pipe is full
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_full(const struct pipe_inode_info *pipe)
+{
+	return pipe_full(pipe->head, pipe->tail, pipe->max_usage);
+}
+
+/**
+ * pipe_is_empty - Return true if the pipe is empty
+ * @pipe: the pipe
+ */
+static inline bool pipe_is_empty(const struct pipe_inode_info *pipe)
+{
+	return pipe_empty(pipe->head, pipe->tail);
+}
+
+/**
+ * pipe_buf_usage - Return how many pipe buffers are in use
+ * @pipe: the pipe
+ */
+static inline unsigned int pipe_buf_usage(const struct pipe_inode_info *pipe)
+{
+	return pipe_occupancy(pipe->head, pipe->tail);
+}
+
 /**
  * pipe_buf - Return the pipe buffer for the specified slot in the pipe ring
  * @pipe: The pipe to access
diff --git a/mm/filemap.c b/mm/filemap.c
index d4564a79eb353..2974691fdfad2 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2897,8 +2897,7 @@ size_t splice_folio_into_pipe(struct pipe_inode_info *pipe,
 	size = min(size, folio_size(folio) - offset);
 	offset %= PAGE_SIZE;
 
-	while (spliced < size &&
-	       !pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	while (spliced < size && !pipe_is_full(pipe)) {
 		struct pipe_buffer *buf = pipe_head_buf(pipe);
 		size_t part = min_t(size_t, PAGE_SIZE - offset, size - spliced);
 
@@ -2955,7 +2954,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 	iocb.ki_pos = *ppos;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 
@@ -3015,7 +3014,7 @@ ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 			total_spliced += n;
 			*ppos += n;
 			in->f_ra.prev_pos = *ppos;
-			if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+			if (pipe_is_full(pipe))
 				goto out;
 		}
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 4ea6109a80431..20032a333d80c 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3487,7 +3487,7 @@ static size_t splice_zeropage_into_pipe(struct pipe_inode_info *pipe,
 
 	size = min_t(size_t, size, PAGE_SIZE - offset);
 
-	if (!pipe_full(pipe->head, pipe->tail, pipe->max_usage)) {
+	if (!pipe_is_full(pipe)) {
 		struct pipe_buffer *buf = pipe_head_buf(pipe);
 
 		*buf = (struct pipe_buffer) {
@@ -3514,7 +3514,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 	int error = 0;
 
 	/* Work out how much data we can actually add into the pipe */
-	used = pipe_occupancy(pipe->head, pipe->tail);
+	used = pipe_buf_usage(pipe);
 	npages = max_t(ssize_t, pipe->max_usage - used, 0);
 	len = min_t(size_t, len, npages * PAGE_SIZE);
 
@@ -3601,7 +3601,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
 		total_spliced += n;
 		*ppos += n;
 		in->f_ra.prev_pos = *ppos;
-		if (pipe_full(pipe->head, pipe->tail, pipe->max_usage))
+		if (pipe_is_full(pipe))
 			break;
 
 		cond_resched();

From 72a6caf5ec8b68f025babe63118b57d892830cc1 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 4 Mar 2025 15:42:07 +0100
Subject: [PATCH 1765/2753] wifi: iwlegacy: avoid size increase

My previous patch caused a slight code size increase when DEBUG_FS is disabled,
as Stanislaw Gruszka pointed out.

Fix this with an added IS_ENABLED() check.

Fixes: cf6b9ba172dd ("wifi: iwlegacy: don't warn for unused variables with DEBUG_FS=n")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Stanislaw Gruszka <stf_xl@wp.pl>
Link: https://patch.msgid.link/20250304144210.997531-1-arnd@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlegacy/4965-rs.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlegacy/4965-rs.c b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
index f754fb979546e..0e5130d1fccd3 100644
--- a/drivers/net/wireless/intel/iwlegacy/4965-rs.c
+++ b/drivers/net/wireless/intel/iwlegacy/4965-rs.c
@@ -2495,6 +2495,9 @@ il4965_rs_dbgfs_set_mcs(struct il_lq_sta *lq_sta, u32 * rate_n_flags, int idx)
 	u8 valid_tx_ant;
 	u8 ant_sel_tx;
 
+	if (!IS_ENABLED(CONFIG_MAC80211_DEBUGFS))
+		return;
+
 	il = lq_sta->drv;
 	valid_tx_ant = il->hw_params.valid_tx_ant;
 	if (lq_sta->dbg_fixed_rate) {

From d9819f537c45bf8c35d4eaf2ff6bc337e5adc787 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
Date: Tue, 4 Mar 2025 16:32:20 +0100
Subject: [PATCH 1766/2753] wifi: wfx: align declarations between bus_spi.c and
 bus_sdio.c
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Just declare fields in the same order in bus_spi.c and bus_sdio.c

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://patch.msgid.link/20250304153224.39083-2-jerome.pouiller@silabs.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/silabs/wfx/bus_spi.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/silabs/wfx/bus_spi.c b/drivers/net/wireless/silabs/wfx/bus_spi.c
index 160b90114aad7..46278dce7ffc5 100644
--- a/drivers/net/wireless/silabs/wfx/bus_spi.c
+++ b/drivers/net/wireless/silabs/wfx/bus_spi.c
@@ -274,11 +274,11 @@ MODULE_DEVICE_TABLE(of, wfx_spi_of_match);
 #endif
 
 struct spi_driver wfx_spi_driver = {
+	.id_table = wfx_spi_id,
+	.probe = wfx_spi_probe,
+	.remove = wfx_spi_remove,
 	.driver = {
 		.name = "wfx-spi",
 		.of_match_table = of_match_ptr(wfx_spi_of_match),
 	},
-	.id_table = wfx_spi_id,
-	.probe = wfx_spi_probe,
-	.remove = wfx_spi_remove,
 };

From 813badc0e1cc76d945c3e117f47eba6c12544f6a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
Date: Tue, 4 Mar 2025 16:32:21 +0100
Subject: [PATCH 1767/2753] wifi: wfx: declare support for WoWLAN
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

WF200 is able to keep the connection with the AP alive while the host is
asleep. So, let's expose this capability to the user.

For now, we don't provide any way to control the device filtering
features. The user has to allow wake-up on any received packets and on
disconnections.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://patch.msgid.link/20250304153224.39083-3-jerome.pouiller@silabs.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/silabs/wfx/main.c | 13 +++++++++++++
 drivers/net/wireless/silabs/wfx/sta.c  | 15 +++++++++++++++
 drivers/net/wireless/silabs/wfx/sta.h  |  2 ++
 3 files changed, 30 insertions(+)

diff --git a/drivers/net/wireless/silabs/wfx/main.c b/drivers/net/wireless/silabs/wfx/main.c
index 64441c8bc4606..55573d975cf91 100644
--- a/drivers/net/wireless/silabs/wfx/main.c
+++ b/drivers/net/wireless/silabs/wfx/main.c
@@ -121,6 +121,12 @@ static const struct ieee80211_iface_combination wfx_iface_combinations[] = {
 	}
 };
 
+#ifdef CONFIG_PM
+static const struct wiphy_wowlan_support wfx_wowlan_support = {
+	.flags = WIPHY_WOWLAN_ANY | WIPHY_WOWLAN_DISCONNECT,
+};
+#endif
+
 static const struct ieee80211_ops wfx_ops = {
 	.start                   = wfx_start,
 	.stop                    = wfx_stop,
@@ -153,6 +159,10 @@ static const struct ieee80211_ops wfx_ops = {
 	.unassign_vif_chanctx    = wfx_unassign_vif_chanctx,
 	.remain_on_channel       = wfx_remain_on_channel,
 	.cancel_remain_on_channel = wfx_cancel_remain_on_channel,
+#ifdef CONFIG_PM
+	.suspend                 = wfx_suspend,
+	.resume                  = wfx_resume,
+#endif
 };
 
 bool wfx_api_older_than(struct wfx_dev *wdev, int major, int minor)
@@ -289,6 +299,9 @@ struct wfx_dev *wfx_init_common(struct device *dev, const struct wfx_platform_da
 					NL80211_PROBE_RESP_OFFLOAD_SUPPORT_P2P |
 					NL80211_PROBE_RESP_OFFLOAD_SUPPORT_80211U;
 	hw->wiphy->features |= NL80211_FEATURE_AP_SCAN;
+#ifdef CONFIG_PM
+	hw->wiphy->wowlan = &wfx_wowlan_support;
+#endif
 	hw->wiphy->flags |= WIPHY_FLAG_AP_PROBE_RESP_OFFLOAD;
 	hw->wiphy->flags |= WIPHY_FLAG_AP_UAPSD;
 	hw->wiphy->max_remain_on_channel_duration = 5000;
diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c
index 7c04810dbf3dc..9e06f8b8b90d9 100644
--- a/drivers/net/wireless/silabs/wfx/sta.c
+++ b/drivers/net/wireless/silabs/wfx/sta.c
@@ -803,6 +803,21 @@ void wfx_remove_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	}
 }
 
+#ifdef CONFIG_PM
+int wfx_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
+{
+	/* FIXME: hardware also support WIPHY_WOWLAN_MAGIC_PKT and other filters */
+	if (!wowlan->any || !wowlan->disconnect)
+		return -EINVAL;
+	return 0;
+}
+
+int wfx_resume(struct ieee80211_hw *hw)
+{
+	return 0;
+}
+#endif
+
 int wfx_start(struct ieee80211_hw *hw)
 {
 	return 0;
diff --git a/drivers/net/wireless/silabs/wfx/sta.h b/drivers/net/wireless/silabs/wfx/sta.h
index 7817c7c6f3dde..70ccc8cb7ec71 100644
--- a/drivers/net/wireless/silabs/wfx/sta.h
+++ b/drivers/net/wireless/silabs/wfx/sta.h
@@ -56,6 +56,8 @@ int wfx_assign_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 void wfx_unassign_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			      struct ieee80211_bss_conf *link_conf,
 			      struct ieee80211_chanctx_conf *conf);
+int wfx_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan);
+int wfx_resume(struct ieee80211_hw *hw);
 
 /* Hardware API Callbacks */
 void wfx_cooling_timeout_work(struct work_struct *work);

From 32bd7f4b393244e2089c656598f598edbab24ea8 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
Date: Tue, 4 Mar 2025 16:32:22 +0100
Subject: [PATCH 1768/2753] wifi: wfx: allow SPI device to wake up the host
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When the host is asleep, the device has wake up the host using the
usual SPI IRQ.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://patch.msgid.link/20250304153224.39083-4-jerome.pouiller@silabs.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/silabs/wfx/bus_spi.c | 31 ++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/silabs/wfx/bus_spi.c b/drivers/net/wireless/silabs/wfx/bus_spi.c
index 46278dce7ffc5..20b9c016b40cd 100644
--- a/drivers/net/wireless/silabs/wfx/bus_spi.c
+++ b/drivers/net/wireless/silabs/wfx/bus_spi.c
@@ -13,6 +13,7 @@
 #include <linux/interrupt.h>
 #include <linux/irq.h>
 #include <linux/of.h>
+#include <linux/pm.h>
 
 #include "bus.h"
 #include "wfx.h"
@@ -189,6 +190,26 @@ static const struct wfx_hwbus_ops wfx_spi_hwbus_ops = {
 	.align_size      = wfx_spi_align_size,
 };
 
+static int wfx_spi_suspend(struct device *dev)
+{
+	struct spi_device *func = to_spi_device(dev);
+	struct wfx_spi_priv *bus = spi_get_drvdata(func);
+
+	if (!device_may_wakeup(dev))
+		return 0;
+	flush_work(&bus->core->hif.bh);
+	return enable_irq_wake(func->irq);
+}
+
+static int wfx_spi_resume(struct device *dev)
+{
+	struct spi_device *func = to_spi_device(dev);
+
+	if (!device_may_wakeup(dev))
+		return 0;
+	return disable_irq_wake(func->irq);
+}
+
 static int wfx_spi_probe(struct spi_device *func)
 {
 	struct wfx_platform_data *pdata;
@@ -239,7 +260,12 @@ static int wfx_spi_probe(struct spi_device *func)
 	if (!bus->core)
 		return -EIO;
 
-	return wfx_probe(bus->core);
+	ret = wfx_probe(bus->core);
+	if (ret)
+		return ret;
+
+	device_set_wakeup_capable(&func->dev, true);
+	return 0;
 }
 
 static void wfx_spi_remove(struct spi_device *func)
@@ -273,6 +299,8 @@ static const struct of_device_id wfx_spi_of_match[] = {
 MODULE_DEVICE_TABLE(of, wfx_spi_of_match);
 #endif
 
+static DEFINE_SIMPLE_DEV_PM_OPS(wfx_spi_pm_ops, wfx_spi_suspend, wfx_spi_resume);
+
 struct spi_driver wfx_spi_driver = {
 	.id_table = wfx_spi_id,
 	.probe = wfx_spi_probe,
@@ -280,5 +308,6 @@ struct spi_driver wfx_spi_driver = {
 	.driver = {
 		.name = "wfx-spi",
 		.of_match_table = of_match_ptr(wfx_spi_of_match),
+		.pm = &wfx_spi_pm_ops,
 	},
 };

From 75516809af78cd73aef851d98e8d6014d149dac4 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
Date: Tue, 4 Mar 2025 16:32:23 +0100
Subject: [PATCH 1769/2753] wifi: wfx: allow SDIO device to wake up the host
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

If the device is connected with SDIO bus, it can wake up the host using
either the SDIO controller (that requires MMC_PM_WAKE_SDIO_IRQ
capability) or the out-of-bound IRQ. This patch allows both.

Obviously, the SDIO controller must be able to keep the SDIO device
powered on.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://patch.msgid.link/20250304153224.39083-5-jerome.pouiller@silabs.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/silabs/wfx/bus_sdio.c | 46 ++++++++++++++++++++++
 1 file changed, 46 insertions(+)

diff --git a/drivers/net/wireless/silabs/wfx/bus_sdio.c b/drivers/net/wireless/silabs/wfx/bus_sdio.c
index f290eecde773f..27c5d7f534a4d 100644
--- a/drivers/net/wireless/silabs/wfx/bus_sdio.c
+++ b/drivers/net/wireless/silabs/wfx/bus_sdio.c
@@ -14,6 +14,7 @@
 #include <linux/of_irq.h>
 #include <linux/irq.h>
 #include <linux/align.h>
+#include <linux/pm.h>
 
 #include "bus.h"
 #include "wfx.h"
@@ -191,9 +192,48 @@ static const struct of_device_id wfx_sdio_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, wfx_sdio_of_match);
 
+static int wfx_sdio_suspend(struct device *dev)
+{
+	struct sdio_func *func = dev_to_sdio_func(dev);
+	struct wfx_sdio_priv *bus = sdio_get_drvdata(func);
+	int ret;
+
+	if (!device_may_wakeup(dev))
+		return 0;
+
+	flush_work(&bus->core->hif.bh);
+	/* Either "wakeup-source" attribute or out-of-band IRQ is required for
+	 * WoWLAN
+	 */
+	if (bus->of_irq) {
+		ret = enable_irq_wake(bus->of_irq);
+		if (ret)
+			return ret;
+	} else {
+		ret = sdio_set_host_pm_flags(func, MMC_PM_WAKE_SDIO_IRQ);
+		if (ret)
+			return ret;
+	}
+	return sdio_set_host_pm_flags(func, MMC_PM_KEEP_POWER);
+}
+
+static int wfx_sdio_resume(struct device *dev)
+{
+	struct sdio_func *func = dev_to_sdio_func(dev);
+	struct wfx_sdio_priv *bus = sdio_get_drvdata(func);
+
+	if (!device_may_wakeup(dev))
+		return 0;
+	if (bus->of_irq)
+		return disable_irq_wake(bus->of_irq);
+	else
+		return 0;
+}
+
 static int wfx_sdio_probe(struct sdio_func *func, const struct sdio_device_id *id)
 {
 	const struct wfx_platform_data *pdata = of_device_get_match_data(&func->dev);
+	mmc_pm_flag_t pm_flag = sdio_get_host_pm_caps(func);
 	struct device_node *np = func->dev.of_node;
 	struct wfx_sdio_priv *bus;
 	int ret;
@@ -235,6 +275,9 @@ static int wfx_sdio_probe(struct sdio_func *func, const struct sdio_device_id *i
 	if (ret)
 		goto sdio_release;
 
+	if (pm_flag & MMC_PM_KEEP_POWER)
+		device_set_wakeup_capable(&func->dev, true);
+
 	return 0;
 
 sdio_release:
@@ -261,6 +304,8 @@ static const struct sdio_device_id wfx_sdio_ids[] = {
 };
 MODULE_DEVICE_TABLE(sdio, wfx_sdio_ids);
 
+static DEFINE_SIMPLE_DEV_PM_OPS(wfx_sdio_pm_ops, wfx_sdio_suspend, wfx_sdio_resume);
+
 struct sdio_driver wfx_sdio_driver = {
 	.name = "wfx-sdio",
 	.id_table = wfx_sdio_ids,
@@ -268,5 +313,6 @@ struct sdio_driver wfx_sdio_driver = {
 	.remove = wfx_sdio_remove,
 	.drv = {
 		.of_match_table = wfx_sdio_of_match,
+		.pm = &wfx_sdio_pm_ops,
 	}
 };

From fc56639937ce95a73c9876e39f8d18d1a8dd6a95 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?J=C3=A9r=C3=B4me=20Pouiller?= <jerome.pouiller@silabs.com>
Date: Tue, 4 Mar 2025 16:32:24 +0100
Subject: [PATCH 1770/2753] wifi: wfx: allow to enable WoWLAN using NL80211
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It is possible to use nl80211 to request to the driver to do allow the
required bus configuration to wake-up the host.

This patch implements the required API for nl80211.

Signed-off-by: Jérôme Pouiller <jerome.pouiller@silabs.com>
Link: https://patch.msgid.link/20250304153224.39083-6-jerome.pouiller@silabs.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/silabs/wfx/bus.h      |  1 +
 drivers/net/wireless/silabs/wfx/bus_sdio.c |  8 ++++++++
 drivers/net/wireless/silabs/wfx/bus_spi.c  |  8 ++++++++
 drivers/net/wireless/silabs/wfx/main.c     |  1 +
 drivers/net/wireless/silabs/wfx/sta.c      | 10 ++++++++++
 drivers/net/wireless/silabs/wfx/sta.h      |  1 +
 6 files changed, 29 insertions(+)

diff --git a/drivers/net/wireless/silabs/wfx/bus.h b/drivers/net/wireless/silabs/wfx/bus.h
index ccadfdd6873ce..79edaef20881a 100644
--- a/drivers/net/wireless/silabs/wfx/bus.h
+++ b/drivers/net/wireless/silabs/wfx/bus.h
@@ -28,6 +28,7 @@ struct wfx_hwbus_ops {
 	void (*lock)(void *bus_priv);
 	void (*unlock)(void *bus_priv);
 	size_t (*align_size)(void *bus_priv, size_t size);
+	void (*set_wakeup)(void *priv, bool enabled);
 };
 
 extern struct sdio_driver wfx_sdio_driver;
diff --git a/drivers/net/wireless/silabs/wfx/bus_sdio.c b/drivers/net/wireless/silabs/wfx/bus_sdio.c
index 27c5d7f534a4d..ab0793b9908f4 100644
--- a/drivers/net/wireless/silabs/wfx/bus_sdio.c
+++ b/drivers/net/wireless/silabs/wfx/bus_sdio.c
@@ -173,6 +173,13 @@ static size_t wfx_sdio_align_size(void *priv, size_t size)
 	return sdio_align_size(bus->func, size);
 }
 
+static void wfx_sdio_set_wakeup(void *priv, bool enabled)
+{
+	struct wfx_sdio_priv *bus = priv;
+
+	device_set_wakeup_enable(&bus->func->dev, enabled);
+}
+
 static const struct wfx_hwbus_ops wfx_sdio_hwbus_ops = {
 	.copy_from_io    = wfx_sdio_copy_from_io,
 	.copy_to_io      = wfx_sdio_copy_to_io,
@@ -181,6 +188,7 @@ static const struct wfx_hwbus_ops wfx_sdio_hwbus_ops = {
 	.lock            = wfx_sdio_lock,
 	.unlock          = wfx_sdio_unlock,
 	.align_size      = wfx_sdio_align_size,
+	.set_wakeup      = wfx_sdio_set_wakeup,
 };
 
 static const struct of_device_id wfx_sdio_of_match[] = {
diff --git a/drivers/net/wireless/silabs/wfx/bus_spi.c b/drivers/net/wireless/silabs/wfx/bus_spi.c
index 20b9c016b40cd..45ee19e1ecbf2 100644
--- a/drivers/net/wireless/silabs/wfx/bus_spi.c
+++ b/drivers/net/wireless/silabs/wfx/bus_spi.c
@@ -180,6 +180,13 @@ static size_t wfx_spi_align_size(void *priv, size_t size)
 	return ALIGN(size, 4);
 }
 
+static void wfx_spi_set_wakeup(void *priv, bool enabled)
+{
+	struct wfx_spi_priv *bus = priv;
+
+	device_set_wakeup_enable(&bus->func->dev, enabled);
+}
+
 static const struct wfx_hwbus_ops wfx_spi_hwbus_ops = {
 	.copy_from_io    = wfx_spi_copy_from_io,
 	.copy_to_io      = wfx_spi_copy_to_io,
@@ -188,6 +195,7 @@ static const struct wfx_hwbus_ops wfx_spi_hwbus_ops = {
 	.lock            = wfx_spi_lock,
 	.unlock          = wfx_spi_unlock,
 	.align_size      = wfx_spi_align_size,
+	.set_wakeup      = wfx_spi_set_wakeup,
 };
 
 static int wfx_spi_suspend(struct device *dev)
diff --git a/drivers/net/wireless/silabs/wfx/main.c b/drivers/net/wireless/silabs/wfx/main.c
index 55573d975cf91..a61128debbadc 100644
--- a/drivers/net/wireless/silabs/wfx/main.c
+++ b/drivers/net/wireless/silabs/wfx/main.c
@@ -162,6 +162,7 @@ static const struct ieee80211_ops wfx_ops = {
 #ifdef CONFIG_PM
 	.suspend                 = wfx_suspend,
 	.resume                  = wfx_resume,
+	.set_wakeup              = wfx_set_wakeup,
 #endif
 };
 
diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c
index 9e06f8b8b90d9..e95b9ded17d9d 100644
--- a/drivers/net/wireless/silabs/wfx/sta.c
+++ b/drivers/net/wireless/silabs/wfx/sta.c
@@ -10,6 +10,7 @@
 
 #include "sta.h"
 #include "wfx.h"
+#include "bus.h"
 #include "fwio.h"
 #include "bh.h"
 #include "key.h"
@@ -816,6 +817,15 @@ int wfx_resume(struct ieee80211_hw *hw)
 {
 	return 0;
 }
+
+void wfx_set_wakeup(struct ieee80211_hw *hw, bool enabled)
+{
+	struct wfx_dev *wdev = hw->priv;
+
+	if (enabled)
+		dev_info(wdev->dev, "support for WoWLAN is experimental\n");
+	wdev->hwbus_ops->set_wakeup(wdev->hwbus_priv, enabled);
+}
 #endif
 
 int wfx_start(struct ieee80211_hw *hw)
diff --git a/drivers/net/wireless/silabs/wfx/sta.h b/drivers/net/wireless/silabs/wfx/sta.h
index 70ccc8cb7ec71..8702eed5267f8 100644
--- a/drivers/net/wireless/silabs/wfx/sta.h
+++ b/drivers/net/wireless/silabs/wfx/sta.h
@@ -58,6 +58,7 @@ void wfx_unassign_vif_chanctx(struct ieee80211_hw *hw, struct ieee80211_vif *vif
 			      struct ieee80211_chanctx_conf *conf);
 int wfx_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan);
 int wfx_resume(struct ieee80211_hw *hw);
+void wfx_set_wakeup(struct ieee80211_hw *hw, bool enabled);
 
 /* Hardware API Callbacks */
 void wfx_cooling_timeout_work(struct work_struct *work);

From d048c84bc1d6b831ca4e3381a16fb616ad96d8db Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 6 Mar 2025 09:28:26 +0100
Subject: [PATCH 1771/2753] wifi: rework MAINTAINERS entries a bit

Since I really don't want to be CC'ed on every patch
add X: entries for all the drivers that are otherwise
covered. In some cases, add a bit more to drivers that
have other entries, mostly for the vendor directories,
but for libertas also add libertas_tf.

While at it, also add all nl80211-related (vendor)
UAPI header files to the nl80211 entry.

Link: https://patch.msgid.link/20250306092831.f7fdfe7df7b2.I7c86da443038af32e9bcbaa5f53b1e4128a0d1f9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 MAINTAINERS | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 73a6c34692740..e989ca218d379 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -124,6 +124,7 @@ F:	include/net/ieee80211_radiotap.h
 F:	include/net/iw_handler.h
 F:	include/net/wext.h
 F:	include/uapi/linux/nl80211.h
+N:	include/uapi/linux/nl80211-.*
 F:	include/uapi/linux/wireless.h
 F:	net/wireless/
 
@@ -514,7 +515,7 @@ F:	drivers/hwmon/adm1029.c
 ADM8211 WIRELESS DRIVER
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-F:	drivers/net/wireless/admtek/adm8211.*
+F:	drivers/net/wireless/admtek/
 
 ADP1050 HARDWARE MONITOR DRIVER
 M:	Radu Sabau <radu.sabau@analog.com>
@@ -6195,7 +6196,7 @@ F:	Documentation/process/cve.rst
 
 CW1200 WLAN driver
 S:	Orphan
-F:	drivers/net/wireless/st/cw1200/
+F:	drivers/net/wireless/st/
 F:	include/linux/platform_data/net-cw1200.h
 
 CX18 VIDEO4LINUX DRIVER
@@ -13983,6 +13984,7 @@ MARVELL LIBERTAS WIRELESS DRIVER
 L:	libertas-dev@lists.infradead.org
 S:	Orphan
 F:	drivers/net/wireless/marvell/libertas/
+F:	drivers/net/wireless/marvell/libertas_tf/
 
 MARVELL MACCHIATOBIN SUPPORT
 M:	Russell King <linux@armlinux.org.uk>
@@ -15652,7 +15654,7 @@ M:	Ajay Singh <ajay.kathat@microchip.com>
 M:	Claudiu Beznea <claudiu.beznea@tuxon.dev>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-F:	drivers/net/wireless/microchip/wilc1000/
+F:	drivers/net/wireless/microchip/
 
 MICROSEMI MIPS SOCS
 M:	Alexandre Belloni <alexandre.belloni@bootlin.com>
@@ -16438,6 +16440,23 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless.git
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/wireless/wireless-next.git
 F:	Documentation/devicetree/bindings/net/wireless/
 F:	drivers/net/wireless/
+X:	drivers/net/wireless/ath/
+X:	drivers/net/wireless/broadcom/
+X:	drivers/net/wireless/intel/
+X:	drivers/net/wireless/intersil/
+X:	drivers/net/wireless/marvell/
+X:	drivers/net/wireless/mediatek/mt76/
+X:	drivers/net/wireless/mediatek/mt7601u/
+X:	drivers/net/wireless/microchip/
+X:	drivers/net/wireless/purelifi/
+X:	drivers/net/wireless/quantenna/
+X:	drivers/net/wireless/ralink/
+X:	drivers/net/wireless/realtek/
+X:	drivers/net/wireless/rsi/
+X:	drivers/net/wireless/silabs/
+X:	drivers/net/wireless/st/
+X:	drivers/net/wireless/ti/
+X:	drivers/net/wireless/zydas/
 
 NETWORKING [DSA]
 M:	Andrew Lunn <andrew@lunn.ch>
@@ -17822,7 +17841,7 @@ M:	Christian Lamparter <chunkeey@googlemail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
 W:	https://wireless.wiki.kernel.org/en/users/Drivers/p54
-F:	drivers/net/wireless/intersil/p54/
+F:	drivers/net/wireless/intersil/
 
 PACKET SOCKETS
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
@@ -19099,7 +19118,7 @@ PURELIFI PLFXLC DRIVER
 M:	Srinivasan Raju <srini.raju@purelifi.com>
 L:	linux-wireless@vger.kernel.org
 S:	Supported
-F:	drivers/net/wireless/purelifi/plfxlc/
+F:	drivers/net/wireless/purelifi/
 
 PVRUSB2 VIDEO4LINUX DRIVER
 M:	Mike Isely <isely@pobox.com>
@@ -19650,7 +19669,7 @@ M:	Igor Mitsyanko <imitsyanko@quantenna.com>
 R:	Sergey Matyukevich <geomatsi@gmail.com>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/quantenna
+F:	drivers/net/wireless/quantenna/
 
 RADEON and AMDGPU DRM DRIVERS
 M:	Alex Deucher <alexander.deucher@amd.com>
@@ -19731,7 +19750,7 @@ RALINK RT2X00 WIRELESS LAN DRIVER
 M:	Stanislaw Gruszka <stf_xl@wp.pl>
 L:	linux-wireless@vger.kernel.org
 S:	Maintained
-F:	drivers/net/wireless/ralink/rt2x00/
+F:	drivers/net/wireless/ralink/
 
 RAMDISK RAM BLOCK DEVICE DRIVER
 M:	Jens Axboe <axboe@kernel.dk>
@@ -21698,7 +21717,7 @@ SILICON LABS WIRELESS DRIVERS (for WFxxx series)
 M:	Jérôme Pouiller <jerome.pouiller@silabs.com>
 S:	Supported
 F:	Documentation/devicetree/bindings/net/wireless/silabs,wfx.yaml
-F:	drivers/net/wireless/silabs/wfx/
+F:	drivers/net/wireless/silabs/
 
 SILICON MOTION SM712 FRAME BUFFER DRIVER
 M:	Sudip Mukherjee <sudipm.mukherjee@gmail.com>
@@ -26198,7 +26217,7 @@ F:	mm/zbud.c
 ZD1211RW WIRELESS DRIVER
 L:	linux-wireless@vger.kernel.org
 S:	Orphan
-F:	drivers/net/wireless/zydas/zd1211rw/
+F:	drivers/net/wireless/zydas/
 
 ZD1301 MEDIA DRIVER
 L:	linux-media@vger.kernel.org

From bbb18f7e23a3f5f56d5c8b4ee0f78f00edb3b1b2 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Thu, 6 Mar 2025 12:25:46 +0200
Subject: [PATCH 1772/2753] wifi: iwlwifi: pcie: Fix TSO preparation

The allocation of the scatter gather data structure should be done
based on the number of memory chunks that need to be mapped, and it
is not dependent on the overall payload length. Fix it.

In addition, as the skb_to_sgvec() function returns an 'int' do not
assign it to an 'unsigned int' as otherwise the error check would be
useless.

Fixes: 7f5e3038f029 ("wifi: iwlwifi: map entire SKB when sending AMSDUs")
Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250306122425.8c0e23a3d583.I3cb4d6768c9d28ce3da6cd0a6c65466176cfc1ee@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/pcie/tx.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
index 7b6071a59b694..7c1dd5cc084ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/tx.c
@@ -1869,12 +1869,12 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 				   unsigned int offset)
 {
 	struct sg_table *sgt;
-	unsigned int n_segments;
+	unsigned int n_segments = skb_shinfo(skb)->nr_frags + 1;
+	int orig_nents;
 
 	if (WARN_ON_ONCE(skb_has_frag_list(skb)))
 		return NULL;
 
-	n_segments = DIV_ROUND_UP(skb->len - offset, skb_shinfo(skb)->gso_size);
 	*hdr = iwl_pcie_get_page_hdr(trans,
 				     hdr_room + __alignof__(struct sg_table) +
 				     sizeof(struct sg_table) +
@@ -1889,11 +1889,12 @@ struct sg_table *iwl_pcie_prep_tso(struct iwl_trans *trans, struct sk_buff *skb,
 	sg_init_table(sgt->sgl, n_segments);
 
 	/* Only map the data, not the header (it is copied to the TSO page) */
-	sgt->orig_nents = skb_to_sgvec(skb, sgt->sgl, offset,
-				       skb->len - offset);
-	if (WARN_ON_ONCE(sgt->orig_nents <= 0))
+	orig_nents = skb_to_sgvec(skb, sgt->sgl, offset, skb->len - offset);
+	if (WARN_ON_ONCE(orig_nents <= 0))
 		return NULL;
 
+	sgt->orig_nents = orig_nents;
+
 	/* And map the entire SKB */
 	if (dma_map_sgtable(trans->dev, sgt, DMA_TO_DEVICE, 0) < 0)
 		return NULL;

From b8c8a03e9b7bfc06f366b75daf3d0812400e7123 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 6 Mar 2025 12:25:47 +0200
Subject: [PATCH 1773/2753] wifi: iwlwifi: mvm: fix PNVM timeout for non-MSI-X
 platforms

When MSI-X is not enabled, we mask all the interrupts in the interrupt
handler and re-enable them when the interrupt thread runs. If
STATUS_INT_ENABLED is not set, we won't re-enable in the thread.
In order to get the ALIVE interrupt, we allow the ALIVE interrupt
itself, and RX as well in order to receive the ALIVE notification (which
is received as an RX from the firmware.

The problem is that STATUS_INT_ENABLED is clear until the op_mode calls
trans_fw_alive which means that until trans_fw_alive is called, any
notification from the firmware will not be received.

This became a problem when we inserted the pnvm_load exactly between the
ALIVE and trans_fw_alive.

Fix that by calling trans_fw_alive before loading the PNVM. This will
allow to get the notification from the firmware about PNVM load being
complete and continue the flow normally.

This didn't happen on MSI-X because we don't disable the interrupts in
the ISR when MSI-X is available.

The error in the log looks like this:

iwlwifi 0000:00:03.0: Timeout waiting for PNVM load!
iwlwifi 0000:00:03.0: Failed to start RT ucode: -110
iwlwifi 0000:00:03.0: WRT: Collecting data: ini trigger 13 fired (delay=0ms).

Fixes: 70d3ca86b025 ("iwlwifi: mvm: ring the doorbell and wait for PNVM load completion")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250306122425.0f2cf207aae1.I025d8f724b44f52eadf6c19069352eb9275613a8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/fw.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
index df49dd2e2026d..d10877856049a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/fw.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -422,6 +422,8 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 	/* if reached this point, Alive notification was received */
 	iwl_mei_alive_notif(true);
 
+	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
+
 	ret = iwl_pnvm_load(mvm->trans, &mvm->notif_wait,
 			    &mvm->fw->ucode_capa);
 	if (ret) {
@@ -430,8 +432,6 @@ static int iwl_mvm_load_ucode_wait_alive(struct iwl_mvm *mvm,
 		return ret;
 	}
 
-	iwl_trans_fw_alive(mvm->trans, alive_data.scd_base_addr);
-
 	/*
 	 * Note: all the queues are enabled as part of the interface
 	 * initialization, but in firmware restart scenarios they

From 1801a94299a5c7fc1a6825e92e1ce0dc7099faa9 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 6 Mar 2025 12:25:48 +0200
Subject: [PATCH 1774/2753] wifi: iwlwifi: trans: cancel restart work on op
 mode leave

If the restart work happens to run after the opmode left
(i.e. called iwl_trans_op_mode_leave), then the opmode memory (including
its mutex) is likely to be freed already, and trans->opmode is NULL.

Although the hw is stopped in that stage, which means that this restart
got aborted (i.e. STATUS_RESET_PENDING will be cleared),
it still can access trans->opmode (NULL pointer dereference)
or the opmodes memory (which is freed).

Fix this by canceling the restart wk in iwl_trans_op_mode_leave.
Also make sure that the restart wk is really aborted.

Fixes: 7391b2a4f7db ("wifi: iwlwifi: rework firmware error handling")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250306122425.801301ba1b8b.I6f6143f550b6335b699920c5d4b2b78449607a96@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 49c8507d1a6b1..47854a36413e1 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -403,6 +403,8 @@ void iwl_trans_op_mode_leave(struct iwl_trans *trans)
 
 	iwl_trans_pcie_op_mode_leave(trans);
 
+	cancel_work_sync(&trans->restart.wk);
+
 	trans->op_mode = NULL;
 
 	trans->state = IWL_TRANS_NO_FW;

From 43e04077170799d0e6289f3e928f727e401b3d79 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 6 Mar 2025 12:37:55 +0200
Subject: [PATCH 1775/2753] wifi: mac80211: flush the station before moving it
 to UN-AUTHORIZED state

We first want to flush the station to make sure we no longer have any
frames being Tx by the station before the station is moved to
un-authorized state. Failing to do that will lead to races: a frame may
be sent after the station's state has been changed.

Since the API clearly states that the driver can't fail the sta_state()
transition down the list of state, we can easily flush the station
first, and only then call the driver's sta_state().

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250306123626.450bc40e8b04.I636ba96843c77f13309c15c9fd6eb0c5a52a7976@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/sta_info.c | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index f83268fa9f928..caa3d0236b5ec 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -4,7 +4,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2024 Intel Corporation
  */
 
 #include <linux/module.h>
@@ -1335,9 +1335,13 @@ static int _sta_info_move_state(struct sta_info *sta,
 		sta->sta.addr, new_state);
 
 	/* notify the driver before the actual changes so it can
-	 * fail the transition
+	 * fail the transition if the state is increasing.
+	 * The driver is required not to fail when the transition
+	 * is decreasing the state, so first, do all the preparation
+	 * work and only then, notify the driver.
 	 */
-	if (test_sta_flag(sta, WLAN_STA_INSERTED)) {
+	if (new_state > sta->sta_state &&
+	    test_sta_flag(sta, WLAN_STA_INSERTED)) {
 		int err = drv_sta_state(sta->local, sta->sdata, sta,
 					sta->sta_state, new_state);
 		if (err)
@@ -1413,6 +1417,16 @@ static int _sta_info_move_state(struct sta_info *sta,
 		break;
 	}
 
+	if (new_state < sta->sta_state &&
+	    test_sta_flag(sta, WLAN_STA_INSERTED)) {
+		int err = drv_sta_state(sta->local, sta->sdata, sta,
+					sta->sta_state, new_state);
+
+		WARN_ONCE(err,
+			  "Driver is not allowed to fail if the sta_state is transitioning down the list: %d\n",
+			  err);
+	}
+
 	sta->sta_state = new_state;
 
 	return 0;

From 20d5a0b9cd0ccb32e886cf6baecf14936325bf10 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 6 Mar 2025 12:37:56 +0200
Subject: [PATCH 1776/2753] wifi: mac80211: don't queue sdata::work for a
 non-running sdata

The worker really shouldn't be queued for a non-running interface.
Also, if ieee80211_setup_sdata is called between queueing and executing
the wk, it will be initialized, which will corrupt wiphy_work_list.

Fixes: f8891461a277 ("mac80211: do not start any work during reconfigure flow")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250306123626.1e02caf82640.I4949e71ed56e7186ed4968fa9ddff477473fa2f4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/util.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index 7f02bd5891eb9..fdda14c08e2b1 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -6,7 +6,7 @@
  * Copyright 2007	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  *
  * utilities for mac80211
  */
@@ -2193,8 +2193,10 @@ int ieee80211_reconfig(struct ieee80211_local *local)
 		ieee80211_reconfig_roc(local);
 
 		/* Requeue all works */
-		list_for_each_entry(sdata, &local->interfaces, list)
-			wiphy_work_queue(local->hw.wiphy, &sdata->work);
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			if (ieee80211_sdata_running(sdata))
+				wiphy_work_queue(local->hw.wiphy, &sdata->work);
+		}
 	}
 
 	ieee80211_wake_queues_by_reason(hw, IEEE80211_MAX_QUEUE_MAP,

From 2e85829ac7fbbd57b93f6cd334b6d448c9ce9db3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 6 Mar 2025 12:37:57 +0200
Subject: [PATCH 1777/2753] wifi: nl80211: fix assoc link handling

The refactoring of the assoc link handling in order to
support multi-link reconfiguration broke the setting
of the assoc link ID, and thus resulted in the wrong
BSS "use_for" value being selected. Fix that for both
association and ML reconfiguration.

Fixes: 720fa448f5a7 ("wifi: nl80211: Split the links handling of an association request")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250306123626.7b233d769c32.I62fd04a8667dd55cedb9a1c0414cc92dd098da75@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 12 ++++++++----
 1 file changed, 8 insertions(+), 4 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e87267fbb442e..aac0e7298dc7a 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -11123,6 +11123,7 @@ static struct cfg80211_bss *nl80211_assoc_bss(struct cfg80211_registered_device
 
 static int nl80211_process_links(struct cfg80211_registered_device *rdev,
 				 struct cfg80211_assoc_link *links,
+				 int assoc_link_id,
 				 const u8 *ssid, int ssid_len,
 				 struct genl_info *info)
 {
@@ -11153,7 +11154,7 @@ static int nl80211_process_links(struct cfg80211_registered_device *rdev,
 		}
 		links[link_id].bss =
 			nl80211_assoc_bss(rdev, ssid, ssid_len, attrs,
-					  link_id, link_id);
+					  assoc_link_id, link_id);
 		if (IS_ERR(links[link_id].bss)) {
 			err = PTR_ERR(links[link_id].bss);
 			links[link_id].bss = NULL;
@@ -11350,8 +11351,8 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 		req.ap_mld_addr = nla_data(info->attrs[NL80211_ATTR_MLD_ADDR]);
 		ap_addr = req.ap_mld_addr;
 
-		err = nl80211_process_links(rdev, req.links, ssid, ssid_len,
-					    info);
+		err = nl80211_process_links(rdev, req.links, req.link_id,
+					    ssid, ssid_len, info);
 		if (err)
 			goto free;
 
@@ -16506,7 +16507,10 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 
 	add_links = 0;
 	if (info->attrs[NL80211_ATTR_MLO_LINKS]) {
-		err = nl80211_process_links(rdev, links, NULL, 0, info);
+		err = nl80211_process_links(rdev, links,
+					    /* mark as MLO, but not assoc */
+					    IEEE80211_MLD_MAX_NUM_LINKS,
+					    NULL, 0, info);
 		if (err)
 			return err;
 

From 9a267ce4a3fca93a34a8881046f97bcf472228c8 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Thu, 6 Mar 2025 12:37:58 +0200
Subject: [PATCH 1778/2753] wifi: mac80211: fix SA Query processing in MLO

When MLO is used and SA Query processing isn't done by
userspace (e.g. wpa_supplicant w/o CONFIG_OCV), then
the mac80211 code kicks in but uses the wrong addresses.
Fix them.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250306123626.bab48bb49061.I9391b22f1360d20ac8c4e92604de23f27696ba8f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/rx.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c
index 1e28efe4203c0..0659ec892ec6c 100644
--- a/net/mac80211/rx.c
+++ b/net/mac80211/rx.c
@@ -6,7 +6,7 @@
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright(c) 2015 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #include <linux/jiffies.h>
@@ -3329,8 +3329,8 @@ static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata,
 		return;
 	}
 
-	if (!ether_addr_equal(mgmt->sa, sdata->deflink.u.mgd.bssid) ||
-	    !ether_addr_equal(mgmt->bssid, sdata->deflink.u.mgd.bssid)) {
+	if (!ether_addr_equal(mgmt->sa, sdata->vif.cfg.ap_addr) ||
+	    !ether_addr_equal(mgmt->bssid, sdata->vif.cfg.ap_addr)) {
 		/* Not from the current AP or not associated yet. */
 		return;
 	}
@@ -3346,9 +3346,9 @@ static void ieee80211_process_sa_query_req(struct ieee80211_sub_if_data *sdata,
 
 	skb_reserve(skb, local->hw.extra_tx_headroom);
 	resp = skb_put_zero(skb, 24);
-	memcpy(resp->da, mgmt->sa, ETH_ALEN);
+	memcpy(resp->da, sdata->vif.cfg.ap_addr, ETH_ALEN);
 	memcpy(resp->sa, sdata->vif.addr, ETH_ALEN);
-	memcpy(resp->bssid, sdata->deflink.u.mgd.bssid, ETH_ALEN);
+	memcpy(resp->bssid, sdata->vif.cfg.ap_addr, ETH_ALEN);
 	resp->frame_control = cpu_to_le16(IEEE80211_FTYPE_MGMT |
 					  IEEE80211_STYPE_ACTION);
 	skb_put(skb, 1 + sizeof(resp->u.action.u.sa_query));

From 72d520476a2fab6f3489e8388ab524985d6c4b90 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 6 Mar 2025 12:37:59 +0200
Subject: [PATCH 1779/2753] wifi: cfg80211: cancel wiphy_work before freeing
 wiphy

A wiphy_work can be queued from the moment the wiphy is allocated and
initialized (i.e. wiphy_new_nm). When a wiphy_work is queued, the
rdev::wiphy_work is getting queued.

If wiphy_free is called before the rdev::wiphy_work had a chance to run,
the wiphy memory will be freed, and then when it eventally gets to run
it'll use invalid memory.

Fix this by canceling the work before freeing the wiphy.

Fixes: a3ee4dc84c4e ("wifi: cfg80211: add a work abstraction with special semantics")
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250306123626.efd1d19f6e07.I48229f96f4067ef73f5b87302335e2fd750136c9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 12b780de8779c..828e298726335 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -1191,6 +1191,13 @@ void cfg80211_dev_free(struct cfg80211_registered_device *rdev)
 {
 	struct cfg80211_internal_bss *scan, *tmp;
 	struct cfg80211_beacon_registration *reg, *treg;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rdev->wiphy_work_lock, flags);
+	WARN_ON(!list_empty(&rdev->wiphy_work_list));
+	spin_unlock_irqrestore(&rdev->wiphy_work_lock, flags);
+	cancel_work_sync(&rdev->wiphy_work);
+
 	rfkill_destroy(rdev->wiphy.rfkill);
 	list_for_each_entry_safe(reg, treg, &rdev->beacon_registrations, list) {
 		list_del(&reg->list);

From 502843396ec2a3eb4f58a2e4618a4a85fc5e0f46 Mon Sep 17 00:00:00 2001
From: Mika Westerberg <mika.westerberg@linux.intel.com>
Date: Mon, 3 Mar 2025 19:40:29 +0200
Subject: [PATCH 1780/2753] thunderbolt: Prevent use-after-free in resume from
 hibernate

Kenneth noticed that his laptop crashes randomly when resuming from
hibernate if there is device connected and display tunneled. I was able
to reproduce this as well with the following steps:

  1. Boot the system up, nothing connected.
  2. Connect Thunderbolt 4 dock to the host.
  3. Connect monitor to the Thunderbolt 4 dock.
  4. Verify that there is picture on the screen.
  5. Enter hibernate.
  6. Exit hibernate.
  7. Wait for the system to resume.

  Expectation: System resumes just fine, the connected monitor still
               shows screen.
  Actual result: There is crash during resume, screen is blank.

What happens is that during resume from hibernate we tear down any
existing tunnels created by the boot kernel and this ends up calling
tb_dp_dprx_stop() which calls tb_tunnel_put() dropping the reference
count to zero even though we never called tb_dp_dprx_start() for it (we
never do that for discovery). This makes the discovered DP tunnel memory
to be released and any access after that causes use-after-free and
possible crash.

Fix this so that we only stop DPRX flow if it has been started in the
first place.

Reported-by: Kenneth Crudup <kenny@panix.com>
Closes: https://lore.kernel.org/linux-usb/8e175721-806f-45d6-892a-bd3356af80c9@panix.com/
Cc: stable@vger.kernel.org
Fixes: d6d458d42e1e ("thunderbolt: Handle DisplayPort tunnel activation asynchronously")
Reviewed-by: Yehezkel Bernat <YehezkelShB@gmail.com>
Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
---
 drivers/thunderbolt/tunnel.c | 11 ++++++++---
 drivers/thunderbolt/tunnel.h |  2 ++
 2 files changed, 10 insertions(+), 3 deletions(-)

diff --git a/drivers/thunderbolt/tunnel.c b/drivers/thunderbolt/tunnel.c
index 8229a6fbda5ab..717b31d787289 100644
--- a/drivers/thunderbolt/tunnel.c
+++ b/drivers/thunderbolt/tunnel.c
@@ -1009,6 +1009,8 @@ static int tb_dp_dprx_start(struct tb_tunnel *tunnel)
 	 */
 	tb_tunnel_get(tunnel);
 
+	tunnel->dprx_started = true;
+
 	if (tunnel->callback) {
 		tunnel->dprx_timeout = dprx_timeout_to_ktime(dprx_timeout);
 		queue_delayed_work(tunnel->tb->wq, &tunnel->dprx_work, 0);
@@ -1021,9 +1023,12 @@ static int tb_dp_dprx_start(struct tb_tunnel *tunnel)
 
 static void tb_dp_dprx_stop(struct tb_tunnel *tunnel)
 {
-	tunnel->dprx_canceled = true;
-	cancel_delayed_work(&tunnel->dprx_work);
-	tb_tunnel_put(tunnel);
+	if (tunnel->dprx_started) {
+		tunnel->dprx_started = false;
+		tunnel->dprx_canceled = true;
+		cancel_delayed_work(&tunnel->dprx_work);
+		tb_tunnel_put(tunnel);
+	}
 }
 
 static int tb_dp_activate(struct tb_tunnel *tunnel, bool active)
diff --git a/drivers/thunderbolt/tunnel.h b/drivers/thunderbolt/tunnel.h
index 7f6d3a18a41e8..8a0a0cb21a895 100644
--- a/drivers/thunderbolt/tunnel.h
+++ b/drivers/thunderbolt/tunnel.h
@@ -63,6 +63,7 @@ enum tb_tunnel_state {
  * @allocated_down: Allocated downstream bandwidth (only for USB3)
  * @bw_mode: DP bandwidth allocation mode registers can be used to
  *	     determine consumed and allocated bandwidth
+ * @dprx_started: DPRX negotiation was started (tb_dp_dprx_start() was called for it)
  * @dprx_canceled: Was DPRX capabilities read poll canceled
  * @dprx_timeout: If set DPRX capabilities read poll work will timeout after this passes
  * @dprx_work: Worker that is scheduled to poll completion of DPRX capabilities read
@@ -100,6 +101,7 @@ struct tb_tunnel {
 	int allocated_up;
 	int allocated_down;
 	bool bw_mode;
+	bool dprx_started;
 	bool dprx_canceled;
 	ktime_t dprx_timeout;
 	struct delayed_work dprx_work;

From 14cb5d83068ecf15d2da6f7d0e9ea9edbcbc0457 Mon Sep 17 00:00:00 2001
From: Andrew Cooper <andrew.cooper3@citrix.com>
Date: Fri, 7 Mar 2025 00:28:46 +0000
Subject: [PATCH 1781/2753] x86/amd_nb: Use rdmsr_safe() in
 amd_get_mmconfig_range()

Xen doesn't offer MSR_FAM10H_MMIO_CONF_BASE to all guests.  This results
in the following warning:

  unchecked MSR access error: RDMSR from 0xc0010058 at rIP: 0xffffffff8101d19f (xen_do_read_msr+0x7f/0xa0)
  Call Trace:
   xen_read_msr+0x1e/0x30
   amd_get_mmconfig_range+0x2b/0x80
   quirk_amd_mmconfig_area+0x28/0x100
   pnp_fixup_device+0x39/0x50
   __pnp_add_device+0xf/0x150
   pnp_add_device+0x3d/0x100
   pnpacpi_add_device_handler+0x1f9/0x280
   acpi_ns_get_device_callback+0x104/0x1c0
   acpi_ns_walk_namespace+0x1d0/0x260
   acpi_get_devices+0x8a/0xb0
   pnpacpi_init+0x50/0x80
   do_one_initcall+0x46/0x2e0
   kernel_init_freeable+0x1da/0x2f0
   kernel_init+0x16/0x1b0
   ret_from_fork+0x30/0x50
   ret_from_fork_asm+0x1b/0x30

based on quirks for a "PNP0c01" device.  Treating MMCFG as disabled is the
right course of action, so no change is needed there.

This was most likely exposed by fixing the Xen MSR accessors to not be
silently-safe.

Fixes: 3fac3734c43a ("xen/pv: support selecting safe/unsafe msr accesses")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250307002846.3026685-1-andrew.cooper3@citrix.com
---
 arch/x86/kernel/amd_nb.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 11fac09e3a8cb..67e773744edb2 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -143,7 +143,6 @@ bool __init early_is_amd_nb(u32 device)
 
 struct resource *amd_get_mmconfig_range(struct resource *res)
 {
-	u32 address;
 	u64 base, msr;
 	unsigned int segn_busn_bits;
 
@@ -151,13 +150,11 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
 		return NULL;
 
-	/* assume all cpus from fam10h have mmconfig */
-	if (boot_cpu_data.x86 < 0x10)
+	/* Assume CPUs from Fam10h have mmconfig, although not all VMs do */
+	if (boot_cpu_data.x86 < 0x10 ||
+	    rdmsrl_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
 		return NULL;
 
-	address = MSR_FAM10H_MMIO_CONF_BASE;
-	rdmsrl(address, msr);
-
 	/* mmconfig is not enabled */
 	if (!(msr & FAM10H_MMIO_CONF_ENABLE))
 		return NULL;

From ac7c06acaa3738b38e83815ac0f07140ad320f13 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Thu, 6 Mar 2025 19:17:21 +1100
Subject: [PATCH 1782/2753] virt: sev-guest: Allocate request data dynamically

Commit

  ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")

narrowed the command mutex scope to snp_send_guest_request().  However,
GET_REPORT, GET_DERIVED_KEY, and GET_EXT_REPORT share the req structure in
snp_guest_dev. Without the mutex protection, concurrent requests can overwrite
each other's data. Fix it by dynamically allocating the request structure.

Fixes: ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")
Closes: https://github.com/AMDESE/AMDSEV/issues/265
Reported-by: andreas.stuehrk@yaxi.tech
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307013700.437505-2-aik@amd.com
---
 drivers/virt/coco/sev-guest/sev-guest.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 264b6523fe52f..23ac177472beb 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -38,12 +38,6 @@ struct snp_guest_dev {
 	struct miscdevice misc;
 
 	struct snp_msg_desc *msg_desc;
-
-	union {
-		struct snp_report_req report;
-		struct snp_derived_key_req derived_key;
-		struct snp_ext_report_req ext_report;
-	} req;
 };
 
 /*
@@ -71,7 +65,7 @@ struct snp_req_resp {
 
 static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
 {
-	struct snp_report_req *report_req = &snp_dev->req.report;
+	struct snp_report_req *report_req __free(kfree) = NULL;
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_report_resp *report_resp;
 	struct snp_guest_req req = {};
@@ -80,6 +74,10 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io
 	if (!arg->req_data || !arg->resp_data)
 		return -EINVAL;
 
+	report_req = kzalloc(sizeof(*report_req), GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
 	if (copy_from_user(report_req, (void __user *)arg->req_data, sizeof(*report_req)))
 		return -EFAULT;
 
@@ -116,7 +114,7 @@ static int get_report(struct snp_guest_dev *snp_dev, struct snp_guest_request_io
 
 static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_request_ioctl *arg)
 {
-	struct snp_derived_key_req *derived_key_req = &snp_dev->req.derived_key;
+	struct snp_derived_key_req *derived_key_req __free(kfree) = NULL;
 	struct snp_derived_key_resp derived_key_resp = {0};
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_guest_req req = {};
@@ -136,6 +134,10 @@ static int get_derived_key(struct snp_guest_dev *snp_dev, struct snp_guest_reque
 	if (sizeof(buf) < resp_len)
 		return -ENOMEM;
 
+	derived_key_req = kzalloc(sizeof(*derived_key_req), GFP_KERNEL_ACCOUNT);
+	if (!derived_key_req)
+		return -ENOMEM;
+
 	if (copy_from_user(derived_key_req, (void __user *)arg->req_data,
 			   sizeof(*derived_key_req)))
 		return -EFAULT;
@@ -168,7 +170,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 			  struct snp_req_resp *io)
 
 {
-	struct snp_ext_report_req *report_req = &snp_dev->req.ext_report;
+	struct snp_ext_report_req *report_req __free(kfree) = NULL;
 	struct snp_msg_desc *mdesc = snp_dev->msg_desc;
 	struct snp_report_resp *report_resp;
 	struct snp_guest_req req = {};
@@ -178,6 +180,10 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data))
 		return -EINVAL;
 
+	report_req = kzalloc(sizeof(*report_req), GFP_KERNEL_ACCOUNT);
+	if (!report_req)
+		return -ENOMEM;
+
 	if (copy_from_sockptr(report_req, io->req_data, sizeof(*report_req)))
 		return -EFAULT;
 

From 3e385c0d6ce88ac9916dcf84267bd5855d830748 Mon Sep 17 00:00:00 2001
From: Alexey Kardashevskiy <aik@amd.com>
Date: Fri, 7 Mar 2025 12:37:00 +1100
Subject: [PATCH 1783/2753] virt: sev-guest: Move SNP Guest Request data pages
 handling under snp_cmd_mutex

Compared to the SNP Guest Request, the "Extended" version adds data pages for
receiving certificates. If not enough pages provided, the HV can report to the
VM how much is needed so the VM can reallocate and repeat.

Commit

  ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")

moved handling of the allocated/desired pages number out of scope of said
mutex and create a possibility for a race (multiple instances trying to
trigger Extended request in a VM) as there is just one instance of
snp_msg_desc per /dev/sev-guest and no locking other than snp_cmd_mutex.

Fix the issue by moving the data blob/size and the GHCB input struct
(snp_req_data) into snp_guest_req which is allocated on stack now and accessed
by the GHCB caller under that mutex.

Stop allocating SEV_FW_BLOB_MAX_SIZE in snp_msg_alloc() as only one of four
callers needs it. Free the received blob in get_ext_report() right after it is
copied to the userspace. Possible future users of snp_send_guest_request() are
likely to have different ideas about the buffer size anyways.

Fixes: ae596615d93d ("virt: sev-guest: Reduce the scope of SNP command mutex")
Signed-off-by: Alexey Kardashevskiy <aik@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Nikunj A Dadhania <nikunj@amd.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307013700.437505-3-aik@amd.com
---
 arch/x86/coco/sev/core.c                | 23 ++++++-----------
 arch/x86/include/asm/sev.h              |  6 ++---
 drivers/virt/coco/sev-guest/sev-guest.c | 34 ++++++++++++++++++++-----
 3 files changed, 39 insertions(+), 24 deletions(-)

diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 82492efc5d949..96c7bc698e6b6 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -2853,19 +2853,8 @@ struct snp_msg_desc *snp_msg_alloc(void)
 	if (!mdesc->response)
 		goto e_free_request;
 
-	mdesc->certs_data = alloc_shared_pages(SEV_FW_BLOB_MAX_SIZE);
-	if (!mdesc->certs_data)
-		goto e_free_response;
-
-	/* initial the input address for guest request */
-	mdesc->input.req_gpa = __pa(mdesc->request);
-	mdesc->input.resp_gpa = __pa(mdesc->response);
-	mdesc->input.data_gpa = __pa(mdesc->certs_data);
-
 	return mdesc;
 
-e_free_response:
-	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 e_free_request:
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
 e_unmap:
@@ -2885,7 +2874,6 @@ void snp_msg_free(struct snp_msg_desc *mdesc)
 	kfree(mdesc->ctx);
 	free_shared_pages(mdesc->response, sizeof(struct snp_guest_msg));
 	free_shared_pages(mdesc->request, sizeof(struct snp_guest_msg));
-	free_shared_pages(mdesc->certs_data, SEV_FW_BLOB_MAX_SIZE);
 	iounmap((__force void __iomem *)mdesc->secrets);
 
 	memset(mdesc, 0, sizeof(*mdesc));
@@ -3054,7 +3042,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 	 * sequence number must be incremented or the VMPCK must be deleted to
 	 * prevent reuse of the IV.
 	 */
-	rc = snp_issue_guest_request(req, &mdesc->input, rio);
+	rc = snp_issue_guest_request(req, &req->input, rio);
 	switch (rc) {
 	case -ENOSPC:
 		/*
@@ -3064,7 +3052,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 		 * order to increment the sequence number and thus avoid
 		 * IV reuse.
 		 */
-		override_npages = mdesc->input.data_npages;
+		override_npages = req->input.data_npages;
 		req->exit_code	= SVM_VMGEXIT_GUEST_REQUEST;
 
 		/*
@@ -3120,7 +3108,7 @@ static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_r
 	}
 
 	if (override_npages)
-		mdesc->input.data_npages = override_npages;
+		req->input.data_npages = override_npages;
 
 	return rc;
 }
@@ -3158,6 +3146,11 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
 	 */
 	memcpy(mdesc->request, &mdesc->secret_request, sizeof(mdesc->secret_request));
 
+	/* Initialize the input address for guest request */
+	req->input.req_gpa = __pa(mdesc->request);
+	req->input.resp_gpa = __pa(mdesc->response);
+	req->input.data_gpa = req->certs_data ? __pa(req->certs_data) : 0;
+
 	rc = __handle_guest_request(mdesc, req, rio);
 	if (rc) {
 		if (rc == -EIO &&
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index 1581246491b54..ba7999f66abe6 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -203,6 +203,9 @@ struct snp_guest_req {
 	unsigned int vmpck_id;
 	u8 msg_version;
 	u8 msg_type;
+
+	struct snp_req_data input;
+	void *certs_data;
 };
 
 /*
@@ -263,9 +266,6 @@ struct snp_msg_desc {
 	struct snp_guest_msg secret_request, secret_response;
 
 	struct snp_secrets_page *secrets;
-	struct snp_req_data input;
-
-	void *certs_data;
 
 	struct aesgcm_ctx *ctx;
 
diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
index 23ac177472beb..70fbc9a3e703d 100644
--- a/drivers/virt/coco/sev-guest/sev-guest.c
+++ b/drivers/virt/coco/sev-guest/sev-guest.c
@@ -176,6 +176,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	struct snp_guest_req req = {};
 	int ret, npages = 0, resp_len;
 	sockptr_t certs_address;
+	struct page *page;
 
 	if (sockptr_is_null(io->req_data) || sockptr_is_null(io->resp_data))
 		return -EINVAL;
@@ -209,8 +210,20 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	 * the host. If host does not supply any certs in it, then copy
 	 * zeros to indicate that certificate data was not provided.
 	 */
-	memset(mdesc->certs_data, 0, report_req->certs_len);
 	npages = report_req->certs_len >> PAGE_SHIFT;
+	page = alloc_pages(GFP_KERNEL_ACCOUNT | __GFP_ZERO,
+			   get_order(report_req->certs_len));
+	if (!page)
+		return -ENOMEM;
+
+	req.certs_data = page_address(page);
+	ret = set_memory_decrypted((unsigned long)req.certs_data, npages);
+	if (ret) {
+		pr_err("failed to mark page shared, ret=%d\n", ret);
+		__free_pages(page, get_order(report_req->certs_len));
+		return -EFAULT;
+	}
+
 cmd:
 	/*
 	 * The intermediate response buffer is used while decrypting the
@@ -219,10 +232,12 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	 */
 	resp_len = sizeof(report_resp->data) + mdesc->ctx->authsize;
 	report_resp = kzalloc(resp_len, GFP_KERNEL_ACCOUNT);
-	if (!report_resp)
-		return -ENOMEM;
+	if (!report_resp) {
+		ret = -ENOMEM;
+		goto e_free_data;
+	}
 
-	mdesc->input.data_npages = npages;
+	req.input.data_npages = npages;
 
 	req.msg_version = arg->msg_version;
 	req.msg_type = SNP_MSG_REPORT_REQ;
@@ -237,7 +252,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 
 	/* If certs length is invalid then copy the returned length */
 	if (arg->vmm_error == SNP_GUEST_VMM_ERR_INVALID_LEN) {
-		report_req->certs_len = mdesc->input.data_npages << PAGE_SHIFT;
+		report_req->certs_len = req.input.data_npages << PAGE_SHIFT;
 
 		if (copy_to_sockptr(io->req_data, report_req, sizeof(*report_req)))
 			ret = -EFAULT;
@@ -246,7 +261,7 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 	if (ret)
 		goto e_free;
 
-	if (npages && copy_to_sockptr(certs_address, mdesc->certs_data, report_req->certs_len)) {
+	if (npages && copy_to_sockptr(certs_address, req.certs_data, report_req->certs_len)) {
 		ret = -EFAULT;
 		goto e_free;
 	}
@@ -256,6 +271,13 @@ static int get_ext_report(struct snp_guest_dev *snp_dev, struct snp_guest_reques
 
 e_free:
 	kfree(report_resp);
+e_free_data:
+	if (npages) {
+		if (set_memory_encrypted((unsigned long)req.certs_data, npages))
+			WARN_ONCE(ret, "failed to restore encryption mask (leak it)\n");
+		else
+			__free_pages(page, get_order(report_req->certs_len));
+	}
 	return ret;
 }
 

From 986c2e9ca818b0b74cfc737517549fd0b80ff15d Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sun, 2 Mar 2025 00:16:01 +0100
Subject: [PATCH 1784/2753] drm/panic: use `div_ceil` to clean Clippy warning

Starting with the upcoming Rust 1.86.0 (to be released 2025-04-03),
Clippy warns:

    error: manually reimplementing `div_ceil`
       --> drivers/gpu/drm/drm_panic_qr.rs:548:26
        |
    548 |         let pad_offset = (offset + 7) / 8;
        |                          ^^^^^^^^^^^^^^^^ help: consider using `.div_ceil()`: `offset.div_ceil(8)`
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#manual_div_ceil

And similarly for `stride`. Thus apply the suggestion to both.

The behavior (and thus codegen) is not exactly equivalent [1][2], since
`div_ceil()` returns the right value for the values that currently
would overflow.

Link: https://github.com/rust-lang/rust-clippy/issues/14333 [1]
Link: https://godbolt.org/z/dPq6nGnv3 [2]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Cc: stable@vger.kernel.org # Needed in 6.12.y and 6.13.y only (Rust is pinned in older LTSs).
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250301231602.917580-1-ojeda@kernel.org
---
 drivers/gpu/drm/drm_panic_qr.rs | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index ef2d490965ba2..56692c6be2199 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -545,7 +545,7 @@ impl EncodedMsg<'_> {
         }
         self.push(&mut offset, (MODE_STOP, 4));
 
-        let pad_offset = (offset + 7) / 8;
+        let pad_offset = offset.div_ceil(8);
         for i in pad_offset..self.version.max_data() {
             self.data[i] = PADDING[(i & 1) ^ (pad_offset & 1)];
         }
@@ -659,7 +659,7 @@ struct QrImage<'a> {
 impl QrImage<'_> {
     fn new<'a, 'b>(em: &'b EncodedMsg<'b>, qrdata: &'a mut [u8]) -> QrImage<'a> {
         let width = em.version.width();
-        let stride = (width + 7) / 8;
+        let stride = width.div_ceil(8);
         let data = qrdata;
 
         let mut qr_image = QrImage {

From cba3b86974a3388b12130654809e50cd19294849 Mon Sep 17 00:00:00 2001
From: Miguel Ojeda <ojeda@kernel.org>
Date: Sun, 2 Mar 2025 00:16:02 +0100
Subject: [PATCH 1785/2753] drm/panic: fix overindented list items in
 documentation

Starting with the upcoming Rust 1.86.0 (to be released 2025-04-03),
Clippy warns:

    error: doc list item overindented
       --> drivers/gpu/drm/drm_panic_qr.rs:914:5
        |
    914 | ///    will be encoded as binary segment, otherwise it will be encoded
        |     ^^^ help: try using `  ` (2 spaces)
        |
        = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#doc_overindented_list_items

The overindentation is slightly hard to notice, since all the items
start with a backquote that makes it look OK, but it is there.

Thus fix it.

Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
Fixes: cb5164ac43d0 ("drm/panic: Add a QR code panic screen")
Cc: stable@vger.kernel.org # Needed in 6.12.y and 6.13.y only (Rust is pinned in older LTSs).
Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Jocelyn Falempe <jfalempe@redhat.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250301231602.917580-2-ojeda@kernel.org
---
 drivers/gpu/drm/drm_panic_qr.rs | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/drm_panic_qr.rs b/drivers/gpu/drm/drm_panic_qr.rs
index 56692c6be2199..08b31d75c24a1 100644
--- a/drivers/gpu/drm/drm_panic_qr.rs
+++ b/drivers/gpu/drm/drm_panic_qr.rs
@@ -911,16 +911,16 @@ impl QrImage<'_> {
 ///
 /// * `url`: The base URL of the QR code. It will be encoded as Binary segment.
 /// * `data`: A pointer to the binary data, to be encoded. if URL is NULL, it
-///    will be encoded as binary segment, otherwise it will be encoded
-///    efficiently as a numeric segment, and appended to the URL.
+///   will be encoded as binary segment, otherwise it will be encoded
+///   efficiently as a numeric segment, and appended to the URL.
 /// * `data_len`: Length of the data, that needs to be encoded, must be less
-///    than data_size.
+///   than data_size.
 /// * `data_size`: Size of data buffer, it should be at least 4071 bytes to hold
-///    a V40 QR code. It will then be overwritten with the QR code image.
+///   a V40 QR code. It will then be overwritten with the QR code image.
 /// * `tmp`: A temporary buffer that the QR code encoder will use, to write the
-///    segments and ECC.
+///   segments and ECC.
 /// * `tmp_size`: Size of the temporary buffer, it must be at least 3706 bytes
-///    long for V40.
+///   long for V40.
 ///
 /// # Safety
 ///

From 75ddcd5ad40ecd9fbc9f5a7a2ed0e1e74921db3c Mon Sep 17 00:00:00 2001
From: Hsin-chen Chuang <chharry@chromium.org>
Date: Fri, 28 Feb 2025 01:14:10 +0800
Subject: [PATCH 1786/2753] Bluetooth: btusb: Configure altsetting for
 HCI_USER_CHANNEL

Automatically configure the altsetting for HCI_USER_CHANNEL when a SCO
is connected.

The motivation is to enable the HCI_USER_CHANNEL user to send out SCO
data through USB Bluetooth chips, which is mainly used for bidirectional
audio transfer (voice call). This was not capable because:

- Per Bluetooth Core Spec v5, Vol 4, Part B, 2.1, the corresponding
  alternate setting should be set based on the air mode in order to
  transfer SCO data, but
- The Linux Bluetooth HCI_USER_CHANNEL exposes the Bluetooth Host
  Controller Interface to the user space, which is something above the
  USB layer. The user space is not able to configure the USB alt while
  keeping the channel open.

This patch intercepts the HCI_EV_SYNC_CONN_COMPLETE packets in btusb,
extracts the air mode, and configures the alt setting in btusb.

This patch is tested on ChromeOS devices. The USB Bluetooth models
(CVSD, TRANS alt3 and alt6) could work without a customized kernel.

Fixes: b16b327edb4d ("Bluetooth: btusb: add sysfs attribute to control USB alt setting")
Signed-off-by: Hsin-chen Chuang <chharry@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/Kconfig | 12 ++++++++++++
 drivers/bluetooth/btusb.c | 41 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 53 insertions(+)

diff --git a/drivers/bluetooth/Kconfig b/drivers/bluetooth/Kconfig
index 4ab32abf0f486..7771edf54fb3f 100644
--- a/drivers/bluetooth/Kconfig
+++ b/drivers/bluetooth/Kconfig
@@ -56,6 +56,18 @@ config BT_HCIBTUSB_POLL_SYNC
 	  Say Y here to enable USB poll_sync for Bluetooth USB devices by
 	  default.
 
+config BT_HCIBTUSB_AUTO_ISOC_ALT
+	bool "Automatically adjust alternate setting for Isoc endpoints"
+	depends on BT_HCIBTUSB
+	default y if CHROME_PLATFORMS
+	help
+	  Say Y here to automatically adjusting the alternate setting for
+	  HCI_USER_CHANNEL whenever a SCO link is established.
+
+	  When enabled, btusb intercepts the HCI_EV_SYNC_CONN_COMPLETE packets
+	  and configures isoc endpoint alternate setting automatically when
+	  HCI_USER_CHANNEL is in use.
+
 config BT_HCIBTUSB_BCM
 	bool "Broadcom protocol support"
 	depends on BT_HCIBTUSB
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 2a8d91963c63f..a0fc465458b2f 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -34,6 +34,7 @@ static bool force_scofix;
 static bool enable_autosuspend = IS_ENABLED(CONFIG_BT_HCIBTUSB_AUTOSUSPEND);
 static bool enable_poll_sync = IS_ENABLED(CONFIG_BT_HCIBTUSB_POLL_SYNC);
 static bool reset = true;
+static bool auto_isoc_alt = IS_ENABLED(CONFIG_BT_HCIBTUSB_AUTO_ISOC_ALT);
 
 static struct usb_driver btusb_driver;
 
@@ -1085,6 +1086,42 @@ static inline void btusb_free_frags(struct btusb_data *data)
 	spin_unlock_irqrestore(&data->rxlock, flags);
 }
 
+static void btusb_sco_connected(struct btusb_data *data, struct sk_buff *skb)
+{
+	struct hci_event_hdr *hdr = (void *) skb->data;
+	struct hci_ev_sync_conn_complete *ev =
+		(void *) skb->data + sizeof(*hdr);
+	struct hci_dev *hdev = data->hdev;
+	unsigned int notify_air_mode;
+
+	if (hci_skb_pkt_type(skb) != HCI_EVENT_PKT)
+		return;
+
+	if (skb->len < sizeof(*hdr) || hdr->evt != HCI_EV_SYNC_CONN_COMPLETE)
+		return;
+
+	if (skb->len != sizeof(*hdr) + sizeof(*ev) || ev->status)
+		return;
+
+	switch (ev->air_mode) {
+	case BT_CODEC_CVSD:
+		notify_air_mode = HCI_NOTIFY_ENABLE_SCO_CVSD;
+		break;
+
+	case BT_CODEC_TRANSPARENT:
+		notify_air_mode = HCI_NOTIFY_ENABLE_SCO_TRANSP;
+		break;
+
+	default:
+		return;
+	}
+
+	bt_dev_info(hdev, "enabling SCO with air mode %u", ev->air_mode);
+	data->sco_num = 1;
+	data->air_mode = notify_air_mode;
+	schedule_work(&data->work);
+}
+
 static int btusb_recv_event(struct btusb_data *data, struct sk_buff *skb)
 {
 	if (data->intr_interval) {
@@ -1092,6 +1129,10 @@ static int btusb_recv_event(struct btusb_data *data, struct sk_buff *skb)
 		schedule_delayed_work(&data->rx_work, 0);
 	}
 
+	/* Configure altsetting for HCI_USER_CHANNEL on SCO connected */
+	if (auto_isoc_alt && hci_dev_test_flag(data->hdev, HCI_USER_CHANNEL))
+		btusb_sco_connected(data, skb);
+
 	return data->recv_event(data->hdev, skb);
 }
 

From 8d74c9106be8da051b22f0cd81e665f17d51ba5d Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Thu, 27 Feb 2025 23:28:15 +0200
Subject: [PATCH 1787/2753] Bluetooth: SCO: fix sco_conn refcounting on
 sco_conn_ready

sco_conn refcount shall not be incremented a second time if the sk
already owns the refcount, so hold only when adding new chan.

Add sco_conn_hold() for clarity, as refcnt is never zero here due to the
sco_conn_add().

Fixes SCO socket shutdown not actually closing the SCO connection.

Fixes: ed9588554943 ("Bluetooth: SCO: remove the redundant sco_conn_put")
Signed-off-by: Pauli Virtanen <pav@iki.fi>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/sco.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index aa7bfe26cb40f..ed6846864ea93 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -107,6 +107,14 @@ static void sco_conn_put(struct sco_conn *conn)
 	kref_put(&conn->ref, sco_conn_free);
 }
 
+static struct sco_conn *sco_conn_hold(struct sco_conn *conn)
+{
+	BT_DBG("conn %p refcnt %u", conn, kref_read(&conn->ref));
+
+	kref_get(&conn->ref);
+	return conn;
+}
+
 static struct sco_conn *sco_conn_hold_unless_zero(struct sco_conn *conn)
 {
 	if (!conn)
@@ -1353,6 +1361,7 @@ static void sco_conn_ready(struct sco_conn *conn)
 		bacpy(&sco_pi(sk)->src, &conn->hcon->src);
 		bacpy(&sco_pi(sk)->dst, &conn->hcon->dst);
 
+		sco_conn_hold(conn);
 		hci_conn_hold(conn->hcon);
 		__sco_chan_add(conn, sk, parent);
 
@@ -1411,8 +1420,10 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
 		struct sco_conn *conn;
 
 		conn = sco_conn_add(hcon);
-		if (conn)
+		if (conn) {
 			sco_conn_ready(conn);
+			sco_conn_put(conn);
+		}
 	} else
 		sco_conn_del(hcon, bt_to_errno(status));
 }

From 0bdd88971519cfa8a76d1a4dde182e74cfbd5d5c Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Fri, 28 Feb 2025 13:12:54 -0500
Subject: [PATCH 1788/2753] Bluetooth: hci_event: Fix enabling passive scanning

Passive scanning shall only be enabled when disconnecting LE links,
otherwise it may start result in triggering scanning when e.g. an ISO
link disconnects:

> HCI Event: LE Meta Event (0x3e) plen 29
      LE Connected Isochronous Stream Established (0x19)
        Status: Success (0x00)
        Connection Handle: 257
        CIG Synchronization Delay: 0 us (0x000000)
        CIS Synchronization Delay: 0 us (0x000000)
        Central to Peripheral Latency: 10000 us (0x002710)
        Peripheral to Central Latency: 10000 us (0x002710)
        Central to Peripheral PHY: LE 2M (0x02)
        Peripheral to Central PHY: LE 2M (0x02)
        Number of Subevents: 1
        Central to Peripheral Burst Number: 1
        Peripheral to Central Burst Number: 1
        Central to Peripheral Flush Timeout: 2
        Peripheral to Central Flush Timeout: 2
        Central to Peripheral MTU: 320
        Peripheral to Central MTU: 160
        ISO Interval: 10.00 msec (0x0008)
...
> HCI Event: Disconnect Complete (0x05) plen 4
        Status: Success (0x00)
        Handle: 257
        Reason: Remote User Terminated Connection (0x13)
< HCI Command: LE Set Extended Scan Enable (0x08|0x0042) plen 6
        Extended scan: Enabled (0x01)
        Filter duplicates: Enabled (0x01)
        Duration: 0 msec (0x0000)
        Period: 0.00 sec (0x0000)

Fixes: 9fcb18ef3acb ("Bluetooth: Introduce LE auto connect options")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 37 ++++++++++++++++++++++---------------
 1 file changed, 22 insertions(+), 15 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 2cc7a93063501..903b0b52692aa 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -3391,23 +3391,30 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data,
 		hci_update_scan(hdev);
 	}
 
-	params = hci_conn_params_lookup(hdev, &conn->dst, conn->dst_type);
-	if (params) {
-		switch (params->auto_connect) {
-		case HCI_AUTO_CONN_LINK_LOSS:
-			if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT)
+	/* Re-enable passive scanning if disconnected device is marked
+	 * as auto-connectable.
+	 */
+	if (conn->type == LE_LINK) {
+		params = hci_conn_params_lookup(hdev, &conn->dst,
+						conn->dst_type);
+		if (params) {
+			switch (params->auto_connect) {
+			case HCI_AUTO_CONN_LINK_LOSS:
+				if (ev->reason != HCI_ERROR_CONNECTION_TIMEOUT)
+					break;
+				fallthrough;
+
+			case HCI_AUTO_CONN_DIRECT:
+			case HCI_AUTO_CONN_ALWAYS:
+				hci_pend_le_list_del_init(params);
+				hci_pend_le_list_add(params,
+						     &hdev->pend_le_conns);
+				hci_update_passive_scan(hdev);
 				break;
-			fallthrough;
 
-		case HCI_AUTO_CONN_DIRECT:
-		case HCI_AUTO_CONN_ALWAYS:
-			hci_pend_le_list_del_init(params);
-			hci_pend_le_list_add(params, &hdev->pend_le_conns);
-			hci_update_passive_scan(hdev);
-			break;
-
-		default:
-			break;
+			default:
+				break;
+			}
 		}
 	}
 

From ab6ab707a4d060a51c45fc13e3b2228d5f7c0b87 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Tue, 4 Mar 2025 10:06:10 -0500
Subject: [PATCH 1789/2753] Revert "Bluetooth: hci_core: Fix sleeping function
 called from invalid context"

This reverts commit 4d94f05558271654670d18c26c912da0c1c15549 which has
problems (see [1]) and is no longer needed since 581dd2dc168f
("Bluetooth: hci_event: Fix using rcu_read_(un)lock while iterating")
has reworked the code where the original bug has been found.

[1] Link: https://lore.kernel.org/linux-bluetooth/877c55ci1r.wl-tiwai@suse.de/T/#t
Fixes: 4d94f0555827 ("Bluetooth: hci_core: Fix sleeping function called from invalid context")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h | 108 +++++++++++--------------------
 net/bluetooth/hci_core.c         |  10 ++-
 net/bluetooth/iso.c              |   6 --
 net/bluetooth/l2cap_core.c       |  12 ++--
 net/bluetooth/rfcomm/core.c      |   6 --
 net/bluetooth/sco.c              |  12 ++--
 6 files changed, 57 insertions(+), 97 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f756fac95488a..6281063cbd8e4 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -804,6 +804,7 @@ struct hci_conn_params {
 extern struct list_head hci_dev_list;
 extern struct list_head hci_cb_list;
 extern rwlock_t hci_dev_list_lock;
+extern struct mutex hci_cb_list_lock;
 
 #define hci_dev_set_flag(hdev, nr)             set_bit((nr), (hdev)->dev_flags)
 #define hci_dev_clear_flag(hdev, nr)           clear_bit((nr), (hdev)->dev_flags)
@@ -2010,47 +2011,24 @@ struct hci_cb {
 
 	char *name;
 
-	bool (*match)		(struct hci_conn *conn);
 	void (*connect_cfm)	(struct hci_conn *conn, __u8 status);
 	void (*disconn_cfm)	(struct hci_conn *conn, __u8 status);
 	void (*security_cfm)	(struct hci_conn *conn, __u8 status,
-				 __u8 encrypt);
+								__u8 encrypt);
 	void (*key_change_cfm)	(struct hci_conn *conn, __u8 status);
 	void (*role_switch_cfm)	(struct hci_conn *conn, __u8 status, __u8 role);
 };
 
-static inline void hci_cb_lookup(struct hci_conn *conn, struct list_head *list)
-{
-	struct hci_cb *cb, *cpy;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(cb, &hci_cb_list, list) {
-		if (cb->match && cb->match(conn)) {
-			cpy = kmalloc(sizeof(*cpy), GFP_ATOMIC);
-			if (!cpy)
-				break;
-
-			*cpy = *cb;
-			INIT_LIST_HEAD(&cpy->list);
-			list_add_rcu(&cpy->list, list);
-		}
-	}
-	rcu_read_unlock();
-}
-
 static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status)
 {
-	struct list_head list;
-	struct hci_cb *cb, *tmp;
-
-	INIT_LIST_HEAD(&list);
-	hci_cb_lookup(conn, &list);
+	struct hci_cb *cb;
 
-	list_for_each_entry_safe(cb, tmp, &list, list) {
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->connect_cfm)
 			cb->connect_cfm(conn, status);
-		kfree(cb);
 	}
+	mutex_unlock(&hci_cb_list_lock);
 
 	if (conn->connect_cfm_cb)
 		conn->connect_cfm_cb(conn, status);
@@ -2058,43 +2036,22 @@ static inline void hci_connect_cfm(struct hci_conn *conn, __u8 status)
 
 static inline void hci_disconn_cfm(struct hci_conn *conn, __u8 reason)
 {
-	struct list_head list;
-	struct hci_cb *cb, *tmp;
-
-	INIT_LIST_HEAD(&list);
-	hci_cb_lookup(conn, &list);
+	struct hci_cb *cb;
 
-	list_for_each_entry_safe(cb, tmp, &list, list) {
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->disconn_cfm)
 			cb->disconn_cfm(conn, reason);
-		kfree(cb);
 	}
+	mutex_unlock(&hci_cb_list_lock);
 
 	if (conn->disconn_cfm_cb)
 		conn->disconn_cfm_cb(conn, reason);
 }
 
-static inline void hci_security_cfm(struct hci_conn *conn, __u8 status,
-				    __u8 encrypt)
-{
-	struct list_head list;
-	struct hci_cb *cb, *tmp;
-
-	INIT_LIST_HEAD(&list);
-	hci_cb_lookup(conn, &list);
-
-	list_for_each_entry_safe(cb, tmp, &list, list) {
-		if (cb->security_cfm)
-			cb->security_cfm(conn, status, encrypt);
-		kfree(cb);
-	}
-
-	if (conn->security_cfm_cb)
-		conn->security_cfm_cb(conn, status);
-}
-
 static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 {
+	struct hci_cb *cb;
 	__u8 encrypt;
 
 	if (test_bit(HCI_CONN_ENCRYPT_PEND, &conn->flags))
@@ -2102,11 +2059,20 @@ static inline void hci_auth_cfm(struct hci_conn *conn, __u8 status)
 
 	encrypt = test_bit(HCI_CONN_ENCRYPT, &conn->flags) ? 0x01 : 0x00;
 
-	hci_security_cfm(conn, status, encrypt);
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
+		if (cb->security_cfm)
+			cb->security_cfm(conn, status, encrypt);
+	}
+	mutex_unlock(&hci_cb_list_lock);
+
+	if (conn->security_cfm_cb)
+		conn->security_cfm_cb(conn, status);
 }
 
 static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status)
 {
+	struct hci_cb *cb;
 	__u8 encrypt;
 
 	if (conn->state == BT_CONFIG) {
@@ -2133,38 +2099,40 @@ static inline void hci_encrypt_cfm(struct hci_conn *conn, __u8 status)
 			conn->sec_level = conn->pending_sec_level;
 	}
 
-	hci_security_cfm(conn, status, encrypt);
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
+		if (cb->security_cfm)
+			cb->security_cfm(conn, status, encrypt);
+	}
+	mutex_unlock(&hci_cb_list_lock);
+
+	if (conn->security_cfm_cb)
+		conn->security_cfm_cb(conn, status);
 }
 
 static inline void hci_key_change_cfm(struct hci_conn *conn, __u8 status)
 {
-	struct list_head list;
-	struct hci_cb *cb, *tmp;
-
-	INIT_LIST_HEAD(&list);
-	hci_cb_lookup(conn, &list);
+	struct hci_cb *cb;
 
-	list_for_each_entry_safe(cb, tmp, &list, list) {
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->key_change_cfm)
 			cb->key_change_cfm(conn, status);
-		kfree(cb);
 	}
+	mutex_unlock(&hci_cb_list_lock);
 }
 
 static inline void hci_role_switch_cfm(struct hci_conn *conn, __u8 status,
 								__u8 role)
 {
-	struct list_head list;
-	struct hci_cb *cb, *tmp;
-
-	INIT_LIST_HEAD(&list);
-	hci_cb_lookup(conn, &list);
+	struct hci_cb *cb;
 
-	list_for_each_entry_safe(cb, tmp, &list, list) {
+	mutex_lock(&hci_cb_list_lock);
+	list_for_each_entry(cb, &hci_cb_list, list) {
 		if (cb->role_switch_cfm)
 			cb->role_switch_cfm(conn, status, role);
-		kfree(cb);
 	}
+	mutex_unlock(&hci_cb_list_lock);
 }
 
 static inline bool hci_bdaddr_is_rpa(bdaddr_t *bdaddr, u8 addr_type)
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index e7ec12437c8b1..012fc107901a6 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -57,6 +57,7 @@ DEFINE_RWLOCK(hci_dev_list_lock);
 
 /* HCI callback list */
 LIST_HEAD(hci_cb_list);
+DEFINE_MUTEX(hci_cb_list_lock);
 
 /* HCI ID Numbering */
 static DEFINE_IDA(hci_index_ida);
@@ -2972,7 +2973,9 @@ int hci_register_cb(struct hci_cb *cb)
 {
 	BT_DBG("%p name %s", cb, cb->name);
 
-	list_add_tail_rcu(&cb->list, &hci_cb_list);
+	mutex_lock(&hci_cb_list_lock);
+	list_add_tail(&cb->list, &hci_cb_list);
+	mutex_unlock(&hci_cb_list_lock);
 
 	return 0;
 }
@@ -2982,8 +2985,9 @@ int hci_unregister_cb(struct hci_cb *cb)
 {
 	BT_DBG("%p name %s", cb, cb->name);
 
-	list_del_rcu(&cb->list);
-	synchronize_rcu();
+	mutex_lock(&hci_cb_list_lock);
+	list_del(&cb->list);
+	mutex_unlock(&hci_cb_list_lock);
 
 	return 0;
 }
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 44acddf58a0cd..0cb52a3308bae 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -2187,11 +2187,6 @@ int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	return HCI_LM_ACCEPT;
 }
 
-static bool iso_match(struct hci_conn *hcon)
-{
-	return hcon->type == ISO_LINK || hcon->type == LE_LINK;
-}
-
 static void iso_connect_cfm(struct hci_conn *hcon, __u8 status)
 {
 	if (hcon->type != ISO_LINK) {
@@ -2373,7 +2368,6 @@ void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 
 static struct hci_cb iso_cb = {
 	.name		= "ISO",
-	.match		= iso_match,
 	.connect_cfm	= iso_connect_cfm,
 	.disconn_cfm	= iso_disconn_cfm,
 };
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index b22078b679726..c27ea70f71e1e 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -7182,11 +7182,6 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c,
 	return NULL;
 }
 
-static bool l2cap_match(struct hci_conn *hcon)
-{
-	return hcon->type == ACL_LINK || hcon->type == LE_LINK;
-}
-
 static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 {
 	struct hci_dev *hdev = hcon->hdev;
@@ -7194,6 +7189,9 @@ static void l2cap_connect_cfm(struct hci_conn *hcon, u8 status)
 	struct l2cap_chan *pchan;
 	u8 dst_type;
 
+	if (hcon->type != ACL_LINK && hcon->type != LE_LINK)
+		return;
+
 	BT_DBG("hcon %p bdaddr %pMR status %d", hcon, &hcon->dst, status);
 
 	if (status) {
@@ -7258,6 +7256,9 @@ int l2cap_disconn_ind(struct hci_conn *hcon)
 
 static void l2cap_disconn_cfm(struct hci_conn *hcon, u8 reason)
 {
+	if (hcon->type != ACL_LINK && hcon->type != LE_LINK)
+		return;
+
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
 	l2cap_conn_del(hcon, bt_to_errno(reason));
@@ -7565,7 +7566,6 @@ void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags)
 
 static struct hci_cb l2cap_cb = {
 	.name		= "L2CAP",
-	.match		= l2cap_match,
 	.connect_cfm	= l2cap_connect_cfm,
 	.disconn_cfm	= l2cap_disconn_cfm,
 	.security_cfm	= l2cap_security_cfm,
diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c
index 4c56ca5a216c6..ad5177e3a69b7 100644
--- a/net/bluetooth/rfcomm/core.c
+++ b/net/bluetooth/rfcomm/core.c
@@ -2134,11 +2134,6 @@ static int rfcomm_run(void *unused)
 	return 0;
 }
 
-static bool rfcomm_match(struct hci_conn *hcon)
-{
-	return hcon->type == ACL_LINK;
-}
-
 static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
 {
 	struct rfcomm_session *s;
@@ -2185,7 +2180,6 @@ static void rfcomm_security_cfm(struct hci_conn *conn, u8 status, u8 encrypt)
 
 static struct hci_cb rfcomm_cb = {
 	.name		= "RFCOMM",
-	.match		= rfcomm_match,
 	.security_cfm	= rfcomm_security_cfm
 };
 
diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index ed6846864ea93..5d1bc0d6aee03 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -1407,13 +1407,11 @@ int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags)
 	return lm;
 }
 
-static bool sco_match(struct hci_conn *hcon)
-{
-	return hcon->type == SCO_LINK || hcon->type == ESCO_LINK;
-}
-
 static void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
 {
+	if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK)
+		return;
+
 	BT_DBG("hcon %p bdaddr %pMR status %u", hcon, &hcon->dst, status);
 
 	if (!status) {
@@ -1430,6 +1428,9 @@ static void sco_connect_cfm(struct hci_conn *hcon, __u8 status)
 
 static void sco_disconn_cfm(struct hci_conn *hcon, __u8 reason)
 {
+	if (hcon->type != SCO_LINK && hcon->type != ESCO_LINK)
+		return;
+
 	BT_DBG("hcon %p reason %d", hcon, reason);
 
 	sco_conn_del(hcon, bt_to_errno(reason));
@@ -1455,7 +1456,6 @@ void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb)
 
 static struct hci_cb sco_cb = {
 	.name		= "SCO",
-	.match		= sco_match,
 	.connect_cfm	= sco_connect_cfm,
 	.disconn_cfm	= sco_disconn_cfm,
 };

From 6914f7e2e25fac9d1d2b62c208eaa5f2bf810fe9 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Thu, 6 Mar 2025 23:00:16 +0100
Subject: [PATCH 1790/2753] x86/mm: Define PTRS_PER_PMD for assembly code too

Andy reported the following build warning from head_32.S:

  In file included from arch/x86/kernel/head_32.S:29:
  arch/x86/include/asm/pgtable_32.h:59:5: error: "PTRS_PER_PMD" is not defined, evaluates to 0 [-Werror=undef]
       59 | #if PTRS_PER_PMD > 1

The reason is that on 2-level i386 paging the folded in PMD's
PTRS_PER_PMD constant is not defined in assembly headers,
only in generic MM C headers.

Instead of trying to fish out the definition from the generic
headers, just define it - it even has a comment for it already...

Reported-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/Z8oa8AUVyi2HWfo9@gmail.com
---
 arch/x86/include/asm/pgtable-2level_types.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 7f6ccff0ba727..4a12c276b1812 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -23,17 +23,17 @@ typedef union {
 #define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
 
 /*
- * traditional i386 two-level paging structure:
+ * Traditional i386 two-level paging structure:
  */
 
 #define PGDIR_SHIFT	22
 #define PTRS_PER_PGD	1024
 
-
 /*
- * the i386 is two-level, so we don't really have any
- * PMD directory physically.
+ * The i386 is two-level, so we don't really have any
+ * PMD directory physically:
  */
+#define PTRS_PER_PMD	1
 
 #define PTRS_PER_PTE	1024
 

From 966944f3711665db13e214fef6d02982c49bb972 Mon Sep 17 00:00:00 2001
From: Mitchell Levy <levymitchell0@gmail.com>
Date: Fri, 7 Mar 2025 15:27:00 -0800
Subject: [PATCH 1791/2753] rust: lockdep: Remove support for dynamically
 allocated LockClassKeys

Currently, dynamically allocated LockCLassKeys can be used from the Rust
side without having them registered. This is a soundness issue, so
remove them.

Fixes: 6ea5aa08857a ("rust: sync: introduce `LockClassKey`")
Suggested-by: Alice Ryhl <aliceryhl@google.com>
Signed-off-by: Mitchell Levy <levymitchell0@gmail.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Benno Lossin <benno.lossin@proton.me>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250307232717.1759087-11-boqun.feng@gmail.com
---
 rust/kernel/sync.rs | 16 ++++------------
 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/rust/kernel/sync.rs b/rust/kernel/sync.rs
index 3498fb344dc93..16eab9138b2ba 100644
--- a/rust/kernel/sync.rs
+++ b/rust/kernel/sync.rs
@@ -30,28 +30,20 @@ pub struct LockClassKey(Opaque<bindings::lock_class_key>);
 unsafe impl Sync for LockClassKey {}
 
 impl LockClassKey {
-    /// Creates a new lock class key.
-    pub const fn new() -> Self {
-        Self(Opaque::uninit())
-    }
-
     pub(crate) fn as_ptr(&self) -> *mut bindings::lock_class_key {
         self.0.get()
     }
 }
 
-impl Default for LockClassKey {
-    fn default() -> Self {
-        Self::new()
-    }
-}
-
 /// Defines a new static lock class and returns a pointer to it.
 #[doc(hidden)]
 #[macro_export]
 macro_rules! static_lock_class {
     () => {{
-        static CLASS: $crate::sync::LockClassKey = $crate::sync::LockClassKey::new();
+        static CLASS: $crate::sync::LockClassKey =
+            // SAFETY: lockdep expects uninitialized memory when it's handed a statically allocated
+            // lock_class_key
+            unsafe { ::core::mem::MaybeUninit::uninit().assume_init() };
         &CLASS
     }};
 }

From b3c5ec8b79bf6bc49cc4850d0949d712830283d7 Mon Sep 17 00:00:00 2001
From: Randy Dunlap <rdunlap@infradead.org>
Date: Fri, 7 Mar 2025 15:26:51 -0800
Subject: [PATCH 1792/2753] locking/rtmutex: Use the 'struct' keyword in
 kernel-doc comment

Add the "struct" keyword to prevent a kernel-doc warning:

  rtmutex_common.h:67: warning: cannot understand function prototype: 'struct rt_wake_q_head '

Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Link: https://lore.kernel.org/r/20250307232717.1759087-2-boqun.feng@gmail.com
---
 kernel/locking/rtmutex_common.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index c38a2d2d4a7ee..78dd3d8c65544 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -59,8 +59,8 @@ struct rt_mutex_waiter {
 };
 
 /**
- * rt_wake_q_head - Wrapper around regular wake_q_head to support
- *		    "sleeping" spinlocks on RT
+ * struct rt_wake_q_head - Wrapper around regular wake_q_head to support
+ *			   "sleeping" spinlocks on RT
  * @head:		The regular wake_q_head for sleeping lock variants
  * @rtlock_task:	Task pointer for RT lock (spin/rwlock) wakeups
  */

From 85b2b9c16d053364e2004883140538e73b333cdb Mon Sep 17 00:00:00 2001
From: Waiman Long <longman@redhat.com>
Date: Fri, 7 Mar 2025 15:26:52 -0800
Subject: [PATCH 1793/2753] locking/semaphore: Use wake_q to wake up processes
 outside lock critical section

A circular lock dependency splat has been seen involving down_trylock():

  ======================================================
  WARNING: possible circular locking dependency detected
  6.12.0-41.el10.s390x+debug
  ------------------------------------------------------
  dd/32479 is trying to acquire lock:
  0015a20accd0d4f8 ((console_sem).lock){-.-.}-{2:2}, at: down_trylock+0x26/0x90

  but task is already holding lock:
  000000017e461698 (&zone->lock){-.-.}-{2:2}, at: rmqueue_bulk+0xac/0x8f0

  the existing dependency chain (in reverse order) is:
  -> #4 (&zone->lock){-.-.}-{2:2}:
  -> #3 (hrtimer_bases.lock){-.-.}-{2:2}:
  -> #2 (&rq->__lock){-.-.}-{2:2}:
  -> #1 (&p->pi_lock){-.-.}-{2:2}:
  -> #0 ((console_sem).lock){-.-.}-{2:2}:

The console_sem -> pi_lock dependency is due to calling try_to_wake_up()
while holding the console_sem raw_spinlock. This dependency can be broken
by using wake_q to do the wakeup instead of calling try_to_wake_up()
under the console_sem lock. This will also make the semaphore's
raw_spinlock become a terminal lock without taking any further locks
underneath it.

The hrtimer_bases.lock is a raw_spinlock while zone->lock is a
spinlock. The hrtimer_bases.lock -> zone->lock dependency happens via
the debug_objects_fill_pool() helper function in the debugobjects code.

  -> #4 (&zone->lock){-.-.}-{2:2}:
         __lock_acquire+0xe86/0x1cc0
         lock_acquire.part.0+0x258/0x630
         lock_acquire+0xb8/0xe0
         _raw_spin_lock_irqsave+0xb4/0x120
         rmqueue_bulk+0xac/0x8f0
         __rmqueue_pcplist+0x580/0x830
         rmqueue_pcplist+0xfc/0x470
         rmqueue.isra.0+0xdec/0x11b0
         get_page_from_freelist+0x2ee/0xeb0
         __alloc_pages_noprof+0x2c2/0x520
         alloc_pages_mpol_noprof+0x1fc/0x4d0
         alloc_pages_noprof+0x8c/0xe0
         allocate_slab+0x320/0x460
         ___slab_alloc+0xa58/0x12b0
         __slab_alloc.isra.0+0x42/0x60
         kmem_cache_alloc_noprof+0x304/0x350
         fill_pool+0xf6/0x450
         debug_object_activate+0xfe/0x360
         enqueue_hrtimer+0x34/0x190
         __run_hrtimer+0x3c8/0x4c0
         __hrtimer_run_queues+0x1b2/0x260
         hrtimer_interrupt+0x316/0x760
         do_IRQ+0x9a/0xe0
         do_irq_async+0xf6/0x160

Normally a raw_spinlock to spinlock dependency is not legitimate
and will be warned if CONFIG_PROVE_RAW_LOCK_NESTING is enabled,
but debug_objects_fill_pool() is an exception as it explicitly
allows this dependency for non-PREEMPT_RT kernel without causing
PROVE_RAW_LOCK_NESTING lockdep splat. As a result, this dependency is
legitimate and not a bug.

Anyway, semaphore is the only locking primitive left that is still
using try_to_wake_up() to do wakeup inside critical section, all the
other locking primitives had been migrated to use wake_q to do wakeup
outside of the critical section. It is also possible that there are
other circular locking dependencies involving printk/console_sem or
other existing/new semaphores lurking somewhere which may show up in
the future. Let just do the migration now to wake_q to avoid headache
like this.

Reported-by: yzbot+ed801a886dfdbfe7136d@syzkaller.appspotmail.com
Signed-off-by: Waiman Long <longman@redhat.com>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250307232717.1759087-3-boqun.feng@gmail.com
---
 kernel/locking/semaphore.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/kernel/locking/semaphore.c b/kernel/locking/semaphore.c
index 34bfae72f2952..de9117c0e671e 100644
--- a/kernel/locking/semaphore.c
+++ b/kernel/locking/semaphore.c
@@ -29,6 +29,7 @@
 #include <linux/export.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
 #include <linux/semaphore.h>
 #include <linux/spinlock.h>
 #include <linux/ftrace.h>
@@ -38,7 +39,7 @@ static noinline void __down(struct semaphore *sem);
 static noinline int __down_interruptible(struct semaphore *sem);
 static noinline int __down_killable(struct semaphore *sem);
 static noinline int __down_timeout(struct semaphore *sem, long timeout);
-static noinline void __up(struct semaphore *sem);
+static noinline void __up(struct semaphore *sem, struct wake_q_head *wake_q);
 
 /**
  * down - acquire the semaphore
@@ -183,13 +184,16 @@ EXPORT_SYMBOL(down_timeout);
 void __sched up(struct semaphore *sem)
 {
 	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->lock, flags);
 	if (likely(list_empty(&sem->wait_list)))
 		sem->count++;
 	else
-		__up(sem);
+		__up(sem, &wake_q);
 	raw_spin_unlock_irqrestore(&sem->lock, flags);
+	if (!wake_q_empty(&wake_q))
+		wake_up_q(&wake_q);
 }
 EXPORT_SYMBOL(up);
 
@@ -269,11 +273,12 @@ static noinline int __sched __down_timeout(struct semaphore *sem, long timeout)
 	return __down_common(sem, TASK_UNINTERRUPTIBLE, timeout);
 }
 
-static noinline void __sched __up(struct semaphore *sem)
+static noinline void __sched __up(struct semaphore *sem,
+				  struct wake_q_head *wake_q)
 {
 	struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
 						struct semaphore_waiter, list);
 	list_del(&waiter->list);
 	waiter->up = true;
-	wake_up_process(waiter->task);
+	wake_q_add(wake_q, waiter->task);
 }

From c8be7018d47cfdf36ae6b5bedddca9fc99cd2f0b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Thu, 6 Mar 2025 18:45:34 +0000
Subject: [PATCH 1794/2753] net: phylink: Remove unused phylink_init_eee

phylink_init_eee() is currently unused.

It was last added in 2019 by
commit 86e58135bc4a ("net: phylink: add phylink_init_eee() helper")
but it didn't actually wire a use up.

It had previous been removed in 2017 by
commit 939eae25d9a5 ("phylink: remove phylink_init_eee()").

Remove it again.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250306184534.246152-1-linux@treblig.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phylink.c | 18 ------------------
 include/linux/phylink.h   |  1 -
 2 files changed, 19 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index a3f64b6d2d34e..76b1a329607bb 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -3157,24 +3157,6 @@ int phylink_get_eee_err(struct phylink *pl)
 }
 EXPORT_SYMBOL_GPL(phylink_get_eee_err);
 
-/**
- * phylink_init_eee() - init and check the EEE features
- * @pl: a pointer to a &struct phylink returned from phylink_create()
- * @clk_stop_enable: allow PHY to stop receive clock
- *
- * Must be called either with RTNL held or within mac_link_up()
- */
-int phylink_init_eee(struct phylink *pl, bool clk_stop_enable)
-{
-	int ret = -EOPNOTSUPP;
-
-	if (pl->phydev)
-		ret = phy_init_eee(pl->phydev, clk_stop_enable);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(phylink_init_eee);
-
 /**
  * phylink_ethtool_get_eee() - read the energy efficient ethernet parameters
  * @pl: a pointer to a &struct phylink returned from phylink_create()
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 08df65f6867a6..c187267a15b6c 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -714,7 +714,6 @@ void phylink_ethtool_get_pauseparam(struct phylink *,
 int phylink_ethtool_set_pauseparam(struct phylink *,
 				   struct ethtool_pauseparam *);
 int phylink_get_eee_err(struct phylink *);
-int phylink_init_eee(struct phylink *, bool);
 int phylink_ethtool_get_eee(struct phylink *link, struct ethtool_keee *eee);
 int phylink_ethtool_set_eee(struct phylink *link, struct ethtool_keee *eee);
 int phylink_mii_ioctl(struct phylink *, struct ifreq *, int);

From 114508a89ddc12b50497c03747aa3c44195ca830 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Fri, 7 Mar 2025 09:16:14 +0800
Subject: [PATCH 1795/2753] dt-bindings: net: Add support for Sophgo SG2044
 dwmac

The GMAC IP on SG2044 is almost a standard Synopsys DesignWare
MAC (version 5.30a) with some extra clock.

Add necessary compatible string for this device.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250307011623.440792-2-inochiama@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../devicetree/bindings/net/snps,dwmac.yaml   |   4 +
 .../bindings/net/sophgo,sg2044-dwmac.yaml     | 126 ++++++++++++++++++
 2 files changed, 130 insertions(+)
 create mode 100644 Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml

diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index c7004eaa8eae1..3f0aa46d798ef 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -32,6 +32,7 @@ select:
           - snps,dwmac-4.20a
           - snps,dwmac-5.10a
           - snps,dwmac-5.20
+          - snps,dwmac-5.30a
           - snps,dwxgmac
           - snps,dwxgmac-2.10
 
@@ -98,8 +99,10 @@ properties:
         - snps,dwmac-4.20a
         - snps,dwmac-5.10a
         - snps,dwmac-5.20
+        - snps,dwmac-5.30a
         - snps,dwxgmac
         - snps,dwxgmac-2.10
+        - sophgo,sg2044-dwmac
         - starfive,jh7100-dwmac
         - starfive,jh7110-dwmac
         - tesla,fsd-ethqos
@@ -632,6 +635,7 @@ allOf:
                 - snps,dwmac-4.20a
                 - snps,dwmac-5.10a
                 - snps,dwmac-5.20
+                - snps,dwmac-5.30a
                 - snps,dwxgmac
                 - snps,dwxgmac-2.10
                 - st,spear600-gmac
diff --git a/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml
new file mode 100644
index 0000000000000..4dd2dc9c678b7
--- /dev/null
+++ b/Documentation/devicetree/bindings/net/sophgo,sg2044-dwmac.yaml
@@ -0,0 +1,126 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/net/sophgo,sg2044-dwmac.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Sophgo SG2044 DWMAC glue layer
+
+maintainers:
+  - Inochi Amaoto <inochiama@gmail.com>
+
+select:
+  properties:
+    compatible:
+      contains:
+        enum:
+          - sophgo,sg2044-dwmac
+  required:
+    - compatible
+
+properties:
+  compatible:
+    items:
+      - const: sophgo,sg2044-dwmac
+      - const: snps,dwmac-5.30a
+
+  reg:
+    maxItems: 1
+
+  clocks:
+    items:
+      - description: GMAC main clock
+      - description: PTP clock
+      - description: TX clock
+
+  clock-names:
+    items:
+      - const: stmmaceth
+      - const: ptp_ref
+      - const: tx
+
+  dma-noncoherent: true
+
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    maxItems: 1
+
+  resets:
+    maxItems: 1
+
+  reset-names:
+    const: stmmaceth
+
+required:
+  - compatible
+  - reg
+  - clocks
+  - clock-names
+  - interrupts
+  - interrupt-names
+  - resets
+  - reset-names
+
+allOf:
+  - $ref: snps,dwmac.yaml#
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/irq.h>
+
+    ethernet@30006000 {
+      compatible = "sophgo,sg2044-dwmac", "snps,dwmac-5.30a";
+      reg = <0x30006000 0x4000>;
+      clocks = <&clk 151>, <&clk 152>, <&clk 154>;
+      clock-names = "stmmaceth", "ptp_ref", "tx";
+      interrupt-parent = <&intc>;
+      interrupts = <296 IRQ_TYPE_LEVEL_HIGH>;
+      interrupt-names = "macirq";
+      resets = <&rst 30>;
+      reset-names = "stmmaceth";
+      snps,multicast-filter-bins = <0>;
+      snps,perfect-filter-entries = <1>;
+      snps,aal;
+      snps,tso;
+      snps,txpbl = <32>;
+      snps,rxpbl = <32>;
+      snps,mtl-rx-config = <&gmac0_mtl_rx_setup>;
+      snps,mtl-tx-config = <&gmac0_mtl_tx_setup>;
+      snps,axi-config = <&gmac0_stmmac_axi_setup>;
+      status = "disabled";
+
+      gmac0_mtl_rx_setup: rx-queues-config {
+        snps,rx-queues-to-use = <8>;
+        snps,rx-sched-wsp;
+        queue0 {};
+        queue1 {};
+        queue2 {};
+        queue3 {};
+        queue4 {};
+        queue5 {};
+        queue6 {};
+        queue7 {};
+      };
+
+      gmac0_mtl_tx_setup: tx-queues-config {
+        snps,tx-queues-to-use = <8>;
+        queue0 {};
+        queue1 {};
+        queue2 {};
+        queue3 {};
+        queue4 {};
+        queue5 {};
+        queue6 {};
+        queue7 {};
+      };
+
+      gmac0_stmmac_axi_setup: stmmac-axi-config {
+        snps,blen = <16 8 4 0 0 0 0>;
+        snps,wr_osr_lmt = <1>;
+        snps,rd_osr_lmt = <2>;
+      };
+    };

From f8add6654d3c859e8a020e0708fdc8bf7d966623 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Fri, 7 Mar 2025 09:16:15 +0800
Subject: [PATCH 1796/2753] net: stmmac: platform: Group GMAC4 compatible check

Use of_device_compatible_match to group existing compatible
check of GMAC4 device.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Reviewed-by: Romain Gantois <romain.gantois@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250307011623.440792-3-inochiama@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../ethernet/stmicro/stmmac/stmmac_platform.c    | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index d0e61aa1a4952..4a3fe44b780d4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -405,6 +405,16 @@ static int stmmac_of_get_mac_mode(struct device_node *np)
 	return -ENODEV;
 }
 
+/* Compatible string array for all gmac4 devices */
+static const char * const stmmac_gmac4_compats[] = {
+	"snps,dwmac-4.00",
+	"snps,dwmac-4.10a",
+	"snps,dwmac-4.20a",
+	"snps,dwmac-5.10a",
+	"snps,dwmac-5.20",
+	NULL
+};
+
 /**
  * stmmac_probe_config_dt - parse device-tree driver parameters
  * @pdev: platform_device structure
@@ -538,11 +548,7 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 		plat->pmt = 1;
 	}
 
-	if (of_device_is_compatible(np, "snps,dwmac-4.00") ||
-	    of_device_is_compatible(np, "snps,dwmac-4.10a") ||
-	    of_device_is_compatible(np, "snps,dwmac-4.20a") ||
-	    of_device_is_compatible(np, "snps,dwmac-5.10a") ||
-	    of_device_is_compatible(np, "snps,dwmac-5.20")) {
+	if (of_device_compatible_match(np, stmmac_gmac4_compats)) {
 		plat->has_gmac4 = 1;
 		plat->has_gmac = 0;
 		plat->pmt = 1;

From 9ef17cafc36bbf47aa840727bc1dc3e65812776f Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Fri, 7 Mar 2025 09:16:16 +0800
Subject: [PATCH 1797/2753] net: stmmac: platform: Add snps,dwmac-5.30a IP
 compatible string

Add "snps,dwmac-5.30a" compatible string for 5.30a version that can avoid
to define some platform data in the glue layer.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Reviewed-by: Romain Gantois <romain.gantois@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250307011623.440792-4-inochiama@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 4a3fe44b780d4..8dc3bd6946c67 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -412,6 +412,7 @@ static const char * const stmmac_gmac4_compats[] = {
 	"snps,dwmac-4.20a",
 	"snps,dwmac-5.10a",
 	"snps,dwmac-5.20",
+	"snps,dwmac-5.30a",
 	NULL
 };
 

From a22221ef5dee6018c0ce285c90622b50bf5909d9 Mon Sep 17 00:00:00 2001
From: Inochi Amaoto <inochiama@gmail.com>
Date: Fri, 7 Mar 2025 09:16:17 +0800
Subject: [PATCH 1798/2753] net: stmmac: Add glue layer for Sophgo SG2044 SoC

Adds Sophgo dwmac driver support on the Sophgo SG2044 SoC.

Signed-off-by: Inochi Amaoto <inochiama@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250307011623.440792-5-inochiama@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/Kconfig   | 11 +++
 drivers/net/ethernet/stmicro/stmmac/Makefile  |  1 +
 .../ethernet/stmicro/stmmac/dwmac-sophgo.c    | 75 +++++++++++++++++++
 3 files changed, 87 insertions(+)
 create mode 100644 drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c

diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig
index c5f94a67b3f2f..3c820ef567759 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Kconfig
+++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig
@@ -181,6 +181,17 @@ config DWMAC_SOCFPGA
 	  for the stmmac device driver. This driver is used for
 	  arria5 and cyclone5 FPGA SoCs.
 
+config DWMAC_SOPHGO
+	tristate "Sophgo dwmac support"
+	depends on OF && (ARCH_SOPHGO || COMPILE_TEST)
+	default m if ARCH_SOPHGO
+	help
+	  Support for ethernet controllers on Sophgo RISC-V SoCs
+
+	  This selects the Sophgo SoC specific glue layer support
+	  for the stmmac device driver. This driver is used for the
+	  ethernet controllers on various Sophgo SoCs.
+
 config DWMAC_STARFIVE
 	tristate "StarFive dwmac support"
 	depends on OF && (ARCH_STARFIVE || COMPILE_TEST)
diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile
index b26f0e79c2b32..594883fb41644 100644
--- a/drivers/net/ethernet/stmicro/stmmac/Makefile
+++ b/drivers/net/ethernet/stmicro/stmmac/Makefile
@@ -24,6 +24,7 @@ obj-$(CONFIG_DWMAC_ROCKCHIP)	+= dwmac-rk.o
 obj-$(CONFIG_DWMAC_RZN1)	+= dwmac-rzn1.o
 obj-$(CONFIG_DWMAC_S32)		+= dwmac-s32.o
 obj-$(CONFIG_DWMAC_SOCFPGA)	+= dwmac-altr-socfpga.o
+obj-$(CONFIG_DWMAC_SOPHGO)	+= dwmac-sophgo.o
 obj-$(CONFIG_DWMAC_STARFIVE)	+= dwmac-starfive.o
 obj-$(CONFIG_DWMAC_STI)		+= dwmac-sti.o
 obj-$(CONFIG_DWMAC_STM32)	+= dwmac-stm32.o
diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c
new file mode 100644
index 0000000000000..3303784cbbf8e
--- /dev/null
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sophgo.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Sophgo DWMAC platform driver
+ *
+ * Copyright (C) 2024 Inochi Amaoto <inochiama@gmail.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/module.h>
+#include <linux/mod_devicetable.h>
+#include <linux/platform_device.h>
+
+#include "stmmac_platform.h"
+
+static int sophgo_sg2044_dwmac_init(struct platform_device *pdev,
+				    struct plat_stmmacenet_data *plat_dat,
+				    struct stmmac_resources *stmmac_res)
+{
+	plat_dat->clk_tx_i = devm_clk_get_enabled(&pdev->dev, "tx");
+	if (IS_ERR(plat_dat->clk_tx_i))
+		return dev_err_probe(&pdev->dev, PTR_ERR(plat_dat->clk_tx_i),
+				     "failed to get tx clock\n");
+
+	plat_dat->flags |= STMMAC_FLAG_SPH_DISABLE;
+	plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
+	plat_dat->multicast_filter_bins = 0;
+	plat_dat->unicast_filter_entries = 1;
+
+	return 0;
+}
+
+static int sophgo_dwmac_probe(struct platform_device *pdev)
+{
+	struct plat_stmmacenet_data *plat_dat;
+	struct stmmac_resources stmmac_res;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
+	if (ret)
+		return dev_err_probe(dev, ret,
+				     "failed to get platform resources\n");
+
+	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
+	if (IS_ERR(plat_dat))
+		return dev_err_probe(dev, PTR_ERR(plat_dat),
+				     "failed to parse DT parameters\n");
+
+	ret = sophgo_sg2044_dwmac_init(pdev, plat_dat, &stmmac_res);
+	if (ret)
+		return ret;
+
+	return stmmac_dvr_probe(dev, plat_dat, &stmmac_res);
+}
+
+static const struct of_device_id sophgo_dwmac_match[] = {
+	{ .compatible = "sophgo,sg2044-dwmac" },
+	{ /* sentinel */ }
+};
+MODULE_DEVICE_TABLE(of, sophgo_dwmac_match);
+
+static struct platform_driver sophgo_dwmac_driver = {
+	.probe  = sophgo_dwmac_probe,
+	.remove = stmmac_pltfr_remove,
+	.driver = {
+		.name = "sophgo-dwmac",
+		.pm = &stmmac_pltfr_pm_ops,
+		.of_match_table = sophgo_dwmac_match,
+	},
+};
+module_platform_driver(sophgo_dwmac_driver);
+
+MODULE_AUTHOR("Inochi Amaoto <inochiama@gmail.com>");
+MODULE_DESCRIPTION("Sophgo DWMAC platform driver");
+MODULE_LICENSE("GPL");

From 7ae495a537d1aed48c3a2eb8263c7ceb18e52a86 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 6 Mar 2025 22:13:44 -0500
Subject: [PATCH 1799/2753] selftests/net: add proc_net_pktgen to .gitignore

Ensure git doesn't pick up this new target.

Fixes: 03544faad761 ("selftest: net: add proc_net_pktgen")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250307031356.368350-1-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/.gitignore | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore
index 80dcae53ef55e..679542f565a48 100644
--- a/tools/testing/selftests/net/.gitignore
+++ b/tools/testing/selftests/net/.gitignore
@@ -21,6 +21,7 @@ msg_oob
 msg_zerocopy
 netlink-dumps
 nettest
+proc_net_pktgen
 psock_fanout
 psock_snd
 psock_tpacket

From 0a5c8b2c8ccbd5987f5d05c6ad6740cdb2e467e8 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Mar 2025 07:43:02 +0000
Subject: [PATCH 1800/2753] bpf: fix a possible NULL deref in
 bpf_map_offload_map_alloc()

Call bpf_dev_offload_check() before netdev_lock_ops().

This is needed if attr->map_ifindex is not valid.

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000197: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000cb8-0x0000000000000cbf]
 RIP: 0010:netdev_need_ops_lock include/linux/netdevice.h:2792 [inline]
 RIP: 0010:netdev_lock_ops include/linux/netdevice.h:2803 [inline]
 RIP: 0010:bpf_map_offload_map_alloc+0x19a/0x910 kernel/bpf/offload.c:533
Call Trace:
 <TASK>
  map_create+0x946/0x11c0 kernel/bpf/syscall.c:1455
  __sys_bpf+0x6d3/0x820 kernel/bpf/syscall.c:5777
  __do_sys_bpf kernel/bpf/syscall.c:5902 [inline]
  __se_sys_bpf kernel/bpf/syscall.c:5900 [inline]
  __x64_sys_bpf+0x7c/0x90 kernel/bpf/syscall.c:5900
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83

Fixes: 97246d6d21c2 ("net: hold netdev instance lock during ndo_bpf")
Reported-by: syzbot+0c7bfd8cf3aecec92708@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/67caa2b1.050a0220.15b4b9.0077.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250307074303.1497911-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 kernel/bpf/offload.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index a10153c3be2df..4f707cfe7f103 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -530,11 +530,12 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 	bpf_map_init_from_attr(&offmap->map, attr);
 	rtnl_lock();
 	offmap->netdev = __dev_get_by_index(net, attr->map_ifindex);
-	netdev_lock_ops(offmap->netdev);
-	down_write(&bpf_devs_lock);
 	err = bpf_dev_offload_check(offmap->netdev);
 	if (err)
-		goto err_unlock;
+		goto err_unlock_rtnl;
+
+	netdev_lock_ops(offmap->netdev);
+	down_write(&bpf_devs_lock);
 
 	ondev = bpf_offload_find_netdev(offmap->netdev);
 	if (!ondev) {
@@ -556,6 +557,7 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
 err_unlock:
 	up_write(&bpf_devs_lock);
 	netdev_unlock_ops(offmap->netdev);
+err_unlock_rtnl:
 	rtnl_unlock();
 	bpf_map_area_free(offmap);
 	return ERR_PTR(err);

From f36a9285828c92ff9dffd4873b8365ca8406f071 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Mar 2025 08:35:44 +0000
Subject: [PATCH 1801/2753] net: ethtool: use correct device pointer in
 ethnl_default_dump_one()

ethnl_default_dump_one() operates on the device provided in its @dev
parameter, not from ctx->req_info->dev.

syzbot reported:

Oops: general protection fault, probably for non-canonical address 0xdffffc0000000197: 0000 [#1] PREEMPT SMP KASAN PTI
KASAN: null-ptr-deref in range [0x0000000000000cb8-0x0000000000000cbf]
 RIP: 0010:netdev_need_ops_lock include/linux/netdevice.h:2792 [inline]
 RIP: 0010:netdev_lock_ops include/linux/netdevice.h:2803 [inline]
 RIP: 0010:ethnl_default_dump_one net/ethtool/netlink.c:557 [inline]
 RIP: 0010:ethnl_default_dumpit+0x447/0xd40 net/ethtool/netlink.c:593
Call Trace:
 <TASK>
  genl_dumpit+0x10d/0x1b0 net/netlink/genetlink.c:1027
  netlink_dump+0x64d/0xe10 net/netlink/af_netlink.c:2309
  __netlink_dump_start+0x5a2/0x790 net/netlink/af_netlink.c:2424
  genl_family_rcv_msg_dumpit net/netlink/genetlink.c:1076 [inline]
  genl_family_rcv_msg net/netlink/genetlink.c:1192 [inline]
  genl_rcv_msg+0x894/0xec0 net/netlink/genetlink.c:1210
  netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2534
  genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
  netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline]
  netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1339
  netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1883
  sock_sendmsg_nosec net/socket.c:709 [inline]
  __sock_sendmsg+0x221/0x270 net/socket.c:724
  ____sys_sendmsg+0x53a/0x860 net/socket.c:2564
  ___sys_sendmsg net/socket.c:2618 [inline]
  __sys_sendmsg+0x269/0x350 net/socket.c:2650

Fixes: 2bcf4772e45a ("net: ethtool: try to protect all callback with netdev instance lock")
Reported-by: syzbot+3da2442641f0c6a705a2@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/lkml/67caaf5e.050a0220.15b4b9.007a.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250307083544.1659135-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 239b5252ed2a1..70834947f474c 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -554,9 +554,9 @@ static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
 
 	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
 	rtnl_lock();
-	netdev_lock_ops(ctx->req_info->dev);
+	netdev_lock_ops(dev);
 	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info);
-	netdev_unlock_ops(ctx->req_info->dev);
+	netdev_unlock_ops(dev);
 	rtnl_unlock();
 	if (ret < 0)
 		goto out;

From aa3e360701c33eaf70936ca41cecd9882b221b46 Mon Sep 17 00:00:00 2001
From: Harshitha Ramamurthy <hramamurthy@google.com>
Date: Fri, 7 Mar 2025 00:39:05 +0000
Subject: [PATCH 1802/2753] gve: convert to use netmem for DQO RDA mode

To add netmem support to the gve driver, add a union
to the struct gve_rx_slot_page_info. netmem_ref is used for
DQO queue format's raw DMA addressing(RDA) mode. The struct
page is retained for other usecases.

Then, switch to using relevant netmem helper functions for
page pool and skb frag management.

Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Link: https://patch.msgid.link/20250307003905.601175-1-hramamurthy@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/google/gve/gve.h         |  8 ++++-
 .../ethernet/google/gve/gve_buffer_mgmt_dqo.c | 27 ++++++++-------
 drivers/net/ethernet/google/gve/gve_rx_dqo.c  | 34 ++++++++++++++-----
 3 files changed, 47 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 216d6e157befb..483c43bab3a99 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -105,7 +105,13 @@ struct gve_rx_desc_queue {
 
 /* The page info for a single slot in the RX data queue */
 struct gve_rx_slot_page_info {
-	struct page *page;
+	/* netmem is used for DQO RDA mode
+	 * page is used in all other modes
+	 */
+	union {
+		struct page *page;
+		netmem_ref netmem;
+	};
 	void *page_address;
 	u32 page_offset; /* offset to write to in page */
 	unsigned int buf_size;
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
index 403f0f335ba66..af84cb88f828c 100644
--- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -205,32 +205,33 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx,
 			   struct gve_rx_buf_state_dqo *buf_state,
 			   bool allow_direct)
 {
-	struct page *page = buf_state->page_info.page;
+	netmem_ref netmem = buf_state->page_info.netmem;
 
-	if (!page)
+	if (!netmem)
 		return;
 
-	page_pool_put_full_page(page->pp, page, allow_direct);
-	buf_state->page_info.page = NULL;
+	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, allow_direct);
+	buf_state->page_info.netmem = 0;
 }
 
 static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 				    struct gve_rx_buf_state_dqo *buf_state)
 {
 	struct gve_priv *priv = rx->gve;
-	struct page *page;
+	netmem_ref netmem;
 
 	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
-	page = page_pool_alloc(rx->dqo.page_pool,
-			       &buf_state->page_info.page_offset,
-			       &buf_state->page_info.buf_size, GFP_ATOMIC);
+	netmem = page_pool_alloc_netmem(rx->dqo.page_pool,
+					&buf_state->page_info.page_offset,
+					&buf_state->page_info.buf_size,
+					GFP_ATOMIC);
 
-	if (!page)
+	if (!netmem)
 		return -ENOMEM;
 
-	buf_state->page_info.page = page;
-	buf_state->page_info.page_address = page_address(page);
-	buf_state->addr = page_pool_get_dma_addr(page);
+	buf_state->page_info.netmem = netmem;
+	buf_state->page_info.page_address = netmem_address(netmem);
+	buf_state->addr = page_pool_get_dma_addr_netmem(netmem);
 
 	return 0;
 }
@@ -269,7 +270,7 @@ void gve_reuse_buffer(struct gve_rx_ring *rx,
 		      struct gve_rx_buf_state_dqo *buf_state)
 {
 	if (rx->dqo.page_pool) {
-		buf_state->page_info.page = NULL;
+		buf_state->page_info.netmem = 0;
 		gve_free_buf_state(rx, buf_state);
 	} else {
 		gve_dec_pagecnt_bias(&buf_state->page_info);
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index f0674a4435670..856ade0c209f6 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -476,6 +476,24 @@ static int gve_rx_copy_ondemand(struct gve_rx_ring *rx,
 	return 0;
 }
 
+static void gve_skb_add_rx_frag(struct gve_rx_ring *rx,
+				struct gve_rx_buf_state_dqo *buf_state,
+				int num_frags, u16 buf_len)
+{
+	if (rx->dqo.page_pool) {
+		skb_add_rx_frag_netmem(rx->ctx.skb_tail, num_frags,
+				       buf_state->page_info.netmem,
+				       buf_state->page_info.page_offset,
+				       buf_len,
+				       buf_state->page_info.buf_size);
+	} else {
+		skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
+				buf_state->page_info.page,
+				buf_state->page_info.page_offset,
+				buf_len, buf_state->page_info.buf_size);
+	}
+}
+
 /* Chains multi skbs for single rx packet.
  * Returns 0 if buffer is appended, -1 otherwise.
  */
@@ -513,10 +531,7 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	if (gve_rx_should_trigger_copy_ondemand(rx))
 		return gve_rx_copy_ondemand(rx, buf_state, buf_len);
 
-	skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
-			buf_state->page_info.page,
-			buf_state->page_info.page_offset,
-			buf_len, buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, num_frags, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 }
@@ -561,7 +576,12 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	/* Page might have not been used for awhile and was likely last written
 	 * by a different thread.
 	 */
-	prefetch(buf_state->page_info.page);
+	if (rx->dqo.page_pool) {
+		if (!netmem_is_net_iov(buf_state->page_info.netmem))
+			prefetch(netmem_to_page(buf_state->page_info.netmem));
+	} else {
+		prefetch(buf_state->page_info.page);
+	}
 
 	/* Copy the header into the skb in the case of header split */
 	if (hsplit) {
@@ -632,9 +652,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	if (rx->dqo.page_pool)
 		skb_mark_for_recycle(rx->ctx.skb_head);
 
-	skb_add_rx_frag(rx->ctx.skb_head, 0, buf_state->page_info.page,
-			buf_state->page_info.page_offset, buf_len,
-			buf_state->page_info.buf_size);
+	gve_skb_add_rx_frag(rx, buf_state, 0, buf_len);
 	gve_reuse_buffer(rx, buf_state);
 	return 0;
 

From 64fdb808660d5ec5108e0e8b35bc3f24de203f8c Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Fri, 7 Mar 2025 00:11:29 +0000
Subject: [PATCH 1803/2753] net: stmmac: remove write-only priv->speed

priv->speed is only ever written to in two locations, but never
read. Therefore, it serves no useful purpose. Remove this unnecessary
struct member.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tqLJJ-005aQm-Mv@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h      | 1 -
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ---
 2 files changed, 4 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index 3a00a988cb36f..d87275c1cf23b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -282,7 +282,6 @@ struct stmmac_priv {
 	/* Generic channel for NAPI */
 	struct stmmac_channel channel[STMMAC_CH_MAX];
 
-	int speed;
 	unsigned int pause_time;
 	struct mii_bus *mii;
 
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a3accab213b03..fa1d7d3a2f438 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -1027,8 +1027,6 @@ static void stmmac_mac_link_up(struct phylink_config *config,
 		}
 	}
 
-	priv->speed = speed;
-
 	if (priv->plat->fix_mac_speed)
 		priv->plat->fix_mac_speed(priv->plat->bsp_priv, speed, mode);
 
@@ -7852,7 +7850,6 @@ int stmmac_suspend(struct device *dev)
 	if (stmmac_fpe_supported(priv))
 		timer_shutdown_sync(&priv->fpe_cfg.verify_timer);
 
-	priv->speed = SPEED_UNKNOWN;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(stmmac_suspend);

From f3600c867c99a2cc8038680ecf211089c50e7971 Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Thu, 6 Mar 2025 21:55:20 +0000
Subject: [PATCH 1804/2753] netmem: prevent TX of unreadable skbs

Currently on stable trees we have support for netmem/devmem RX but not
TX. It is not safe to forward/redirect an RX unreadable netmem packet
into the device's TX path, as the device may call dma-mapping APIs on
dma addrs that should not be passed to it.

Fix this by preventing the xmit of unreadable skbs.

Tested by configuring tc redirect:

sudo tc qdisc add dev eth1 ingress
sudo tc filter add dev eth1 ingress protocol ip prio 1 flower ip_proto \
	tcp src_ip 192.168.1.12 action mirred egress redirect dev eth1

Before, I see unreadable skbs in the driver's TX path passed to dma
mapping APIs.

After, I don't see unreadable skbs in the driver's TX path passed to dma
mapping APIs.

Fixes: 65249feb6b3d ("net: add support for skbs with unreadable frags")
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250306215520.1415465-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/dev.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/core/dev.c b/net/core/dev.c
index 30da277c5a6f8..2f7f5fd9ffec7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3872,6 +3872,9 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device
 {
 	netdev_features_t features;
 
+	if (!skb_frags_readable(skb))
+		goto out_kfree_skb;
+
 	features = netif_skb_features(skb);
 	skb = validate_xmit_vlan(skb, features);
 	if (unlikely(!skb))

From d749d901b2168389f060b654fdaa08acf6b367d2 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 6 Mar 2025 23:25:29 +0200
Subject: [PATCH 1805/2753] net/mlx5: Fill out devlink dev info only for PFs

Firmware version query is supported on the PFs. Due to this
following kernel warning log is observed:

[  188.590344] mlx5_core 0000:08:00.2: mlx5_fw_version_query:816:(pid 1453): fw query isn't supported by the FW

Fix it by restricting the query and devlink info to the PF.

Fixes: 8338d9378895 ("net/mlx5: Added devlink info callback")
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Link: https://patch.msgid.link/20250306212529.429329-1-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 98d4306929f3e..a2cf3e79693dd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -46,6 +46,9 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	u32 running_fw, stored_fw;
 	int err;
 
+	if (!mlx5_core_is_pf(dev))
+		return 0;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;

From d2b41068056bc7686f1f8d1494f9359ede0b4434 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:29 -0800
Subject: [PATCH 1806/2753] net: bcmgenet: bcmgenet_hw_params clean up

The entries of the bcmgenet_hw_params array are broken out to
remove unused and duplicate entries and are made read only since
they should not change for a specific version of the GENET
hardware.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-2-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 183 ++++++++----------
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   2 +-
 2 files changed, 84 insertions(+), 101 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 3e93f957430b2..0c717a724c4e1 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) controller driver
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet: " fmt
@@ -3726,123 +3726,106 @@ static const struct net_device_ops bcmgenet_netdev_ops = {
 	.ndo_change_carrier	= bcmgenet_change_carrier,
 };
 
-/* Array of GENET hardware parameters/characteristics */
-static struct bcmgenet_hw_params bcmgenet_hw_params[] = {
-	[GENET_V1] = {
-		.tx_queues = 0,
-		.tx_bds_per_q = 0,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.hfb_offset = 0x1000,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x3000,
-		.words_per_bd = 2,
-	},
-	[GENET_V2] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 16,
-		.bp_in_mask = 0xffff,
-		.hfb_filter_cnt = 16,
-		.qtag_mask = 0x1F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x1000,
-		.hfb_reg_offset = 0x2000,
-		.rdma_offset = 0x3000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT,
-	},
-	[GENET_V3] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x10000,
-		.tdma_offset = 0x11000,
-		.words_per_bd = 2,
-		.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
-			 GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V4] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
-	[GENET_V5] = {
-		.tx_queues = 4,
-		.tx_bds_per_q = 32,
-		.rx_queues = 0,
-		.rx_bds_per_q = 0,
-		.bp_in_en_shift = 17,
-		.bp_in_mask = 0x1ffff,
-		.hfb_filter_cnt = 48,
-		.hfb_filter_size = 128,
-		.qtag_mask = 0x3F,
-		.tbuf_offset = 0x0600,
-		.hfb_offset = 0x8000,
-		.hfb_reg_offset = 0xfc00,
-		.rdma_offset = 0x2000,
-		.tdma_offset = 0x4000,
-		.words_per_bd = 3,
-		.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-			 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
-	},
+/* GENET hardware parameters/characteristics */
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v1 = {
+	.tx_queues = 0,
+	.tx_bds_per_q = 0,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.qtag_mask = 0x1F,
+	.hfb_offset = 0x1000,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x3000,
+	.words_per_bd = 2,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v2 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 16,
+	.bp_in_mask = 0xffff,
+	.hfb_filter_cnt = 16,
+	.qtag_mask = 0x1F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x1000,
+	.hfb_reg_offset = 0x2000,
+	.rdma_offset = 0x3000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 2,
+	.flags = GENET_HAS_EXT,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v3 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x10000,
+	.tdma_offset = 0x11000,
+	.words_per_bd = 2,
+	.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
+		 GENET_HAS_MOCA_LINK_DET,
+};
+
+static const struct bcmgenet_hw_params bcmgenet_hw_params_v4 = {
+	.tx_queues = 4,
+	.tx_bds_per_q = 32,
+	.rx_queues = 0,
+	.rx_bds_per_q = 0,
+	.bp_in_en_shift = 17,
+	.bp_in_mask = 0x1ffff,
+	.hfb_filter_cnt = 48,
+	.hfb_filter_size = 128,
+	.qtag_mask = 0x3F,
+	.tbuf_offset = 0x0600,
+	.hfb_offset = 0x8000,
+	.hfb_reg_offset = 0xfc00,
+	.rdma_offset = 0x2000,
+	.tdma_offset = 0x4000,
+	.words_per_bd = 3,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 /* Infer hardware parameters from the detected GENET version */
 static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 {
-	struct bcmgenet_hw_params *params;
+	const struct bcmgenet_hw_params *params;
 	u32 reg;
 	u8 major;
 	u16 gphy_rev;
 
-	if (GENET_IS_V5(priv) || GENET_IS_V4(priv)) {
-		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
-		genet_dma_ring_regs = genet_dma_ring_regs_v4;
-	} else if (GENET_IS_V3(priv)) {
+	/* default to latest values */
+	params = &bcmgenet_hw_params_v4;
+	bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
+	genet_dma_ring_regs = genet_dma_ring_regs_v4;
+	if (GENET_IS_V3(priv)) {
+		params = &bcmgenet_hw_params_v3;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v3plus;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V2(priv)) {
+		params = &bcmgenet_hw_params_v2;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v2;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	} else if (GENET_IS_V1(priv)) {
+		params = &bcmgenet_hw_params_v1;
 		bcmgenet_dma_regs = bcmgenet_dma_regs_v1;
 		genet_dma_ring_regs = genet_dma_ring_regs_v123;
 	}
-
-	/* enum genet_version starts at 1 */
-	priv->hw_params = &bcmgenet_hw_params[priv->version];
-	params = priv->hw_params;
+	priv->hw_params = params;
 
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 43b923c48b14f..1078a31ac794f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -596,7 +596,7 @@ struct bcmgenet_priv {
 	struct bcmgenet_rx_ring rx_rings[DESC_INDEX + 1];
 
 	/* other misc variables */
-	struct bcmgenet_hw_params *hw_params;
+	const struct bcmgenet_hw_params *hw_params;
 	unsigned autoneg_pause:1;
 	unsigned tx_pause:1;
 	unsigned rx_pause:1;

From 07c1a756a50b1180a085ab61819a388bbb906a95 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:30 -0800
Subject: [PATCH 1807/2753] net: bcmgenet: add bcmgenet_has_* helpers

Introduce helper functions to indicate whether the driver should
make use of a particular feature that it supports. These helpers
abstract the implementation of how the feature availability is
encoded.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-3-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 20 +++++++-------
 .../net/ethernet/broadcom/genet/bcmgenet.h    | 27 ++++++++++++++++++-
 drivers/net/ethernet/broadcom/genet/bcmmii.c  |  6 ++---
 3 files changed, 39 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0c717a724c4e1..769d920a0fc06 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -104,7 +104,7 @@ static inline void dmadesc_set_addr(struct bcmgenet_priv *priv,
 	 * the platform is explicitly configured for 64-bits/LPAE.
 	 */
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		bcmgenet_writel(upper_32_bits(addr), d + DMA_DESC_ADDRESS_HI);
 #endif
 }
@@ -1651,9 +1651,9 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 
 	case GENET_POWER_PASSIVE:
 		/* Power down LED */
-		if (priv->hw_params->flags & GENET_HAS_EXT) {
+		if (bcmgenet_has_ext(priv)) {
 			reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
-			if (GENET_IS_V5(priv) && !priv->ephy_16nm)
+			if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv))
 				reg |= EXT_PWR_DOWN_PHY_EN |
 				       EXT_PWR_DOWN_PHY_RD |
 				       EXT_PWR_DOWN_PHY_SD |
@@ -1681,7 +1681,7 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 {
 	u32 reg;
 
-	if (!(priv->hw_params->flags & GENET_HAS_EXT))
+	if (!bcmgenet_has_ext(priv))
 		return;
 
 	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
@@ -1690,7 +1690,7 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 	case GENET_POWER_PASSIVE:
 		reg &= ~(EXT_PWR_DOWN_DLL | EXT_PWR_DOWN_BIAS |
 			 EXT_ENERGY_DET_MASK);
-		if (GENET_IS_V5(priv) && !priv->ephy_16nm) {
+		if (GENET_IS_V5(priv) && !bcmgenet_has_ephy_16nm(priv)) {
 			reg &= ~(EXT_PWR_DOWN_PHY_EN |
 				 EXT_PWR_DOWN_PHY_RD |
 				 EXT_PWR_DOWN_PHY_SD |
@@ -2523,7 +2523,7 @@ static void bcmgenet_link_intr_enable(struct bcmgenet_priv *priv)
 	} else if (priv->ext_phy) {
 		int0_enable |= UMAC_IRQ_LINK_EVENT;
 	} else if (priv->phy_interface == PHY_INTERFACE_MODE_MOCA) {
-		if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+		if (bcmgenet_has_moca_link_det(priv))
 			int0_enable |= UMAC_IRQ_LINK_EVENT;
 	}
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
@@ -2588,7 +2588,7 @@ static void init_umac(struct bcmgenet_priv *priv)
 	}
 
 	/* Enable MDIO interrupts on GENET v3+ */
-	if (priv->hw_params->flags & GENET_HAS_MDIO_INTR)
+	if (bcmgenet_has_mdio_intr(priv))
 		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
 
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
@@ -3228,7 +3228,7 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 		}
 	}
 
-	if ((priv->hw_params->flags & GENET_HAS_MDIO_INTR) &&
+	if (bcmgenet_has_mdio_intr(priv) &&
 		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
 	}
@@ -3881,7 +3881,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	}
 
 #ifdef CONFIG_PHYS_ADDR_T_64BIT
-	if (!(params->flags & GENET_HAS_40BITS))
+	if (!bcmgenet_has_40bits(priv))
 		pr_warn("GENET does not support 40-bits PA\n");
 #endif
 
@@ -4060,7 +4060,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	bcmgenet_set_hw_params(priv);
 
 	err = -EIO;
-	if (priv->hw_params->flags & GENET_HAS_40BITS)
+	if (bcmgenet_has_40bits(priv))
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(40));
 	if (err)
 		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 1078a31ac794f..9b73ae55c0d68 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /*
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #ifndef __BCMGENET_H__
@@ -650,6 +650,31 @@ struct bcmgenet_priv {
 	struct ethtool_keee eee;
 };
 
+static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
+{
+	return !!(priv->hw_params->flags & GENET_HAS_40BITS);
+}
+
+static inline bool bcmgenet_has_ext(struct bcmgenet_priv *priv)
+{
+	return !!(priv->hw_params->flags & GENET_HAS_EXT);
+}
+
+static inline bool bcmgenet_has_mdio_intr(struct bcmgenet_priv *priv)
+{
+	return !!(priv->hw_params->flags & GENET_HAS_MDIO_INTR);
+}
+
+static inline bool bcmgenet_has_moca_link_det(struct bcmgenet_priv *priv)
+{
+	return !!(priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET);
+}
+
+static inline bool bcmgenet_has_ephy_16nm(struct bcmgenet_priv *priv)
+{
+	return priv->ephy_16nm;
+}
+
 #define GENET_IO_MACRO(name, offset)					\
 static inline u32 bcmgenet_##name##_readl(struct bcmgenet_priv *priv,	\
 					u32 off)			\
diff --git a/drivers/net/ethernet/broadcom/genet/bcmmii.c b/drivers/net/ethernet/broadcom/genet/bcmmii.c
index c4a3698cef66f..71c619d2bea5f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmmii.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmmii.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET MDIO routines
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #include <linux/acpi.h>
@@ -154,7 +154,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 	u32 reg = 0;
 
 	/* EXT_GPHY_CTRL is only valid for GENETv4 and onward */
-	if (GENET_IS_V4(priv) || priv->ephy_16nm) {
+	if (GENET_IS_V4(priv) || bcmgenet_has_ephy_16nm(priv)) {
 		reg = bcmgenet_ext_readl(priv, EXT_GPHY_CTRL);
 		if (enable) {
 			reg &= ~EXT_CK25_DIS;
@@ -184,7 +184,7 @@ void bcmgenet_phy_power_set(struct net_device *dev, bool enable)
 
 static void bcmgenet_moca_phy_setup(struct bcmgenet_priv *priv)
 {
-	if (priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET)
+	if (bcmgenet_has_moca_link_det(priv))
 		fixed_phy_set_link_update(priv->dev->phydev,
 					  bcmgenet_fixed_phy_link_update);
 }

From a2bdde505f14d49f00f1d122eb7f3a849bc9d3f0 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:31 -0800
Subject: [PATCH 1808/2753] net: bcmgenet: move feature flags to bcmgenet_priv

The feature flags are moved and consolidated to the primary
private driver structure and are now initialized from the
platform device data rather than the hardware parameters to
allow finer control over which platforms use which features.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-4-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 22 ++++++++++++-------
 .../net/ethernet/broadcom/genet/bcmgenet.h    | 14 ++++++------
 2 files changed, 21 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 769d920a0fc06..48830942afa8a 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3757,7 +3757,6 @@ static const struct bcmgenet_hw_params bcmgenet_hw_params_v2 = {
 	.rdma_offset = 0x3000,
 	.tdma_offset = 0x4000,
 	.words_per_bd = 2,
-	.flags = GENET_HAS_EXT,
 };
 
 static const struct bcmgenet_hw_params bcmgenet_hw_params_v3 = {
@@ -3776,8 +3775,6 @@ static const struct bcmgenet_hw_params bcmgenet_hw_params_v3 = {
 	.rdma_offset = 0x10000,
 	.tdma_offset = 0x11000,
 	.words_per_bd = 2,
-	.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
-		 GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_hw_params bcmgenet_hw_params_v4 = {
@@ -3796,8 +3793,6 @@ static const struct bcmgenet_hw_params bcmgenet_hw_params_v4 = {
 	.rdma_offset = 0x2000,
 	.tdma_offset = 0x4000,
 	.words_per_bd = 3,
-	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
-		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 /* Infer hardware parameters from the detected GENET version */
@@ -3906,7 +3901,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 struct bcmgenet_plat_data {
 	enum bcmgenet_version version;
 	u32 dma_max_burst_length;
-	bool ephy_16nm;
+	u32 flags;
 };
 
 static const struct bcmgenet_plat_data v1_plat_data = {
@@ -3917,32 +3912,43 @@ static const struct bcmgenet_plat_data v1_plat_data = {
 static const struct bcmgenet_plat_data v2_plat_data = {
 	.version = GENET_V2,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT,
 };
 
 static const struct bcmgenet_plat_data v3_plat_data = {
 	.version = GENET_V3,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_EXT | GENET_HAS_MDIO_INTR |
+		 GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v4_plat_data = {
 	.version = GENET_V4,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data v5_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm2711_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = 0x08,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET,
 };
 
 static const struct bcmgenet_plat_data bcm7712_plat_data = {
 	.version = GENET_V5,
 	.dma_max_burst_length = DMA_MAX_BURST_LENGTH,
-	.ephy_16nm = true,
+	.flags = GENET_HAS_40BITS | GENET_HAS_EXT |
+		 GENET_HAS_MDIO_INTR | GENET_HAS_MOCA_LINK_DET |
+		 GENET_HAS_EPHY_16NM,
 };
 
 static const struct of_device_id bcmgenet_match[] = {
@@ -4040,7 +4046,7 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (pdata) {
 		priv->version = pdata->version;
 		priv->dma_max_burst_length = pdata->dma_max_burst_length;
-		priv->ephy_16nm = pdata->ephy_16nm;
+		priv->flags = pdata->flags;
 	} else {
 		priv->version = pd->genet_version;
 		priv->dma_max_burst_length = DMA_MAX_BURST_LENGTH;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 9b73ae55c0d68..a7f121503ffb0 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -476,6 +476,7 @@ enum bcmgenet_version {
 #define GENET_HAS_EXT		(1 << 1)
 #define GENET_HAS_MDIO_INTR	(1 << 2)
 #define GENET_HAS_MOCA_LINK_DET	(1 << 3)
+#define GENET_HAS_EPHY_16NM	(1 << 4)
 
 /* BCMGENET hardware parameters, keep this structure nicely aligned
  * since it is going to be used in hot paths
@@ -496,7 +497,6 @@ struct bcmgenet_hw_params {
 	u32		rdma_offset;
 	u32		tdma_offset;
 	u32		words_per_bd;
-	u32		flags;
 };
 
 struct bcmgenet_skb_cb {
@@ -597,6 +597,7 @@ struct bcmgenet_priv {
 
 	/* other misc variables */
 	const struct bcmgenet_hw_params *hw_params;
+	u32 flags;
 	unsigned autoneg_pause:1;
 	unsigned tx_pause:1;
 	unsigned rx_pause:1;
@@ -615,7 +616,6 @@ struct bcmgenet_priv {
 	phy_interface_t phy_interface;
 	int phy_addr;
 	int ext_phy;
-	bool ephy_16nm;
 
 	/* Interrupt variables */
 	struct work_struct bcmgenet_irq_work;
@@ -652,27 +652,27 @@ struct bcmgenet_priv {
 
 static inline bool bcmgenet_has_40bits(struct bcmgenet_priv *priv)
 {
-	return !!(priv->hw_params->flags & GENET_HAS_40BITS);
+	return !!(priv->flags & GENET_HAS_40BITS);
 }
 
 static inline bool bcmgenet_has_ext(struct bcmgenet_priv *priv)
 {
-	return !!(priv->hw_params->flags & GENET_HAS_EXT);
+	return !!(priv->flags & GENET_HAS_EXT);
 }
 
 static inline bool bcmgenet_has_mdio_intr(struct bcmgenet_priv *priv)
 {
-	return !!(priv->hw_params->flags & GENET_HAS_MDIO_INTR);
+	return !!(priv->flags & GENET_HAS_MDIO_INTR);
 }
 
 static inline bool bcmgenet_has_moca_link_det(struct bcmgenet_priv *priv)
 {
-	return !!(priv->hw_params->flags & GENET_HAS_MOCA_LINK_DET);
+	return !!(priv->flags & GENET_HAS_MOCA_LINK_DET);
 }
 
 static inline bool bcmgenet_has_ephy_16nm(struct bcmgenet_priv *priv)
 {
-	return priv->ephy_16nm;
+	return !!(priv->flags & GENET_HAS_EPHY_16NM);
 }
 
 #define GENET_IO_MACRO(name, offset)					\

From 59a97b8184eff53997ea6a96b6dd2ec65b8bba1e Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:32 -0800
Subject: [PATCH 1809/2753] net: bcmgenet: BCM7712 is GENETv5 compatible

The major revision of the GENET core in the BCM7712 SoC was bumped
to 7 but it is compatible with the GENETv5 implementation. This
commit maps the version accordingly to avoid a warning.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-5-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 48830942afa8a..e6b2a0499edbc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3825,7 +3825,7 @@ static void bcmgenet_set_hw_params(struct bcmgenet_priv *priv)
 	/* Read GENET HW version */
 	reg = bcmgenet_sys_readl(priv, SYS_REV_CTRL);
 	major = (reg >> 24 & 0x0f);
-	if (major == 6)
+	if (major == 6 || major == 7)
 		major = 5;
 	else if (major == 5)
 		major = 4;

From f841f5ef9911f1d050c62b5ad35ae96ff238c029 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:33 -0800
Subject: [PATCH 1810/2753] net: bcmgenet: extend bcmgenet_hfb_* API

Extend the bcmgenet_hfb_* API to allow initialization and
programming of the Hardware Filter Block on GENET v1 and
GENET v2 hardware. Programming of ethtool flows is still
not supported on this older hardware.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-6-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 94 +++++++++++--------
 1 file changed, 57 insertions(+), 37 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index e6b2a0499edbc..9aeb1133ffa12 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -446,33 +446,48 @@ static void bcmgenet_hfb_enable_filter(struct bcmgenet_priv *priv, u32 f_index)
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg |= (1 << (f_index % 32));
-	bcmgenet_hfb_reg_writel(priv, reg, offset);
-	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	reg |= RBUF_HFB_EN;
-	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= (1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT)) |
+			RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS + (f_index < 32) * sizeof(u32);
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg |= (1 << (f_index % 32));
+		bcmgenet_hfb_reg_writel(priv, reg, offset);
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		reg |= RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	}
 }
 
 static void bcmgenet_hfb_disable_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 offset, reg, reg1;
 
-	offset = HFB_FLT_ENABLE_V3PLUS;
-	reg = bcmgenet_hfb_reg_readl(priv, offset);
-	reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
-	if  (f_index < 32) {
-		reg1 &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
-	} else {
-		reg &= ~(1 << (f_index % 32));
-		bcmgenet_hfb_reg_writel(priv, reg, offset);
-	}
-	if (!reg && !reg1) {
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
 		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		reg &= ~RBUF_HFB_EN;
+		reg &= ~(1 << ((f_index % 32) + RBUF_HFB_FILTER_EN_SHIFT));
+		if (!(reg & RBUF_HFB_FILTER_EN_MASK))
+			reg &= ~RBUF_HFB_EN;
 		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+	} else {
+		offset = HFB_FLT_ENABLE_V3PLUS;
+		reg = bcmgenet_hfb_reg_readl(priv, offset);
+		reg1 = bcmgenet_hfb_reg_readl(priv, offset + sizeof(u32));
+		if  (f_index < 32) {
+			reg1 &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg1, offset + sizeof(u32));
+		} else {
+			reg &= ~(1 << (f_index % 32));
+			bcmgenet_hfb_reg_writel(priv, reg, offset);
+		}
+		if (!reg && !reg1) {
+			reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+			reg &= ~RBUF_HFB_EN;
+			bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
+		}
 	}
 }
 
@@ -482,6 +497,9 @@ static void bcmgenet_hfb_set_filter_rx_queue_mapping(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		return;
+
 	offset = f_index / 8;
 	reg = bcmgenet_rdma_readl(priv, DMA_INDEX2RING_0 + offset);
 	reg &= ~(0xF << (4 * (f_index % 8)));
@@ -495,9 +513,13 @@ static void bcmgenet_hfb_set_filter_length(struct bcmgenet_priv *priv,
 	u32 offset;
 	u32 reg;
 
-	offset = HFB_FLT_LEN_V3PLUS +
-		 ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4) *
-		 sizeof(u32);
+	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
+		offset = HFB_FLT_LEN_V2;
+	else
+		offset = HFB_FLT_LEN_V3PLUS;
+
+	offset += sizeof(u32) *
+		  ((priv->hw_params->hfb_filter_cnt - 1 - f_index) / 4);
 	reg = bcmgenet_hfb_reg_readl(priv, offset);
 	reg &= ~(0xFF << (8 * (f_index % 4)));
 	reg |= ((f_length & 0xFF) << (8 * (f_index % 4)));
@@ -690,6 +712,7 @@ static void bcmgenet_hfb_clear_filter(struct bcmgenet_priv *priv, u32 f_index)
 {
 	u32 base, i;
 
+	bcmgenet_hfb_set_filter_length(priv, f_index, 0);
 	base = f_index * priv->hw_params->hfb_filter_size;
 	for (i = 0; i < priv->hw_params->hfb_filter_size; i++)
 		bcmgenet_hfb_writel(priv, 0x0, (base + i) * sizeof(u32));
@@ -699,19 +722,16 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
 {
 	u32 i;
 
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_CTRL);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS);
-	bcmgenet_hfb_reg_writel(priv, 0x0, HFB_FLT_ENABLE_V3PLUS + 4);
-
-	for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
-		bcmgenet_rdma_writel(priv, 0x0, i);
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 
-	for (i = 0; i < (priv->hw_params->hfb_filter_cnt / 4); i++)
-		bcmgenet_hfb_reg_writel(priv, 0x0,
-					HFB_FLT_LEN_V3PLUS + i * sizeof(u32));
+	if (!GENET_IS_V1(priv) && !GENET_IS_V2(priv)) {
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS);
+		bcmgenet_hfb_reg_writel(priv, 0,
+					HFB_FLT_ENABLE_V3PLUS + 4);
+		for (i = DMA_INDEX2RING_0; i <= DMA_INDEX2RING_7; i++)
+			bcmgenet_rdma_writel(priv, 0, i);
+	}
 
 	for (i = 0; i < priv->hw_params->hfb_filter_cnt; i++)
 		bcmgenet_hfb_clear_filter(priv, i);
@@ -722,9 +742,6 @@ static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
 	int i;
 
 	INIT_LIST_HEAD(&priv->rxnfc_list);
-	if (GENET_IS_V1(priv) || GENET_IS_V2(priv))
-		return;
-
 	for (i = 0; i < MAX_NUM_OF_FS_RULES; i++) {
 		INIT_LIST_HEAD(&priv->rxnfc_rules[i].list);
 		priv->rxnfc_rules[i].state = BCMGENET_RXNFC_STATE_UNUSED;
@@ -3735,8 +3752,10 @@ static const struct bcmgenet_hw_params bcmgenet_hw_params_v1 = {
 	.bp_in_en_shift = 16,
 	.bp_in_mask = 0xffff,
 	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
 	.qtag_mask = 0x1F,
 	.hfb_offset = 0x1000,
+	.hfb_reg_offset = GENET_RBUF_OFF + RBUF_HFB_CTRL_V1,
 	.rdma_offset = 0x2000,
 	.tdma_offset = 0x3000,
 	.words_per_bd = 2,
@@ -3750,6 +3769,7 @@ static const struct bcmgenet_hw_params bcmgenet_hw_params_v2 = {
 	.bp_in_en_shift = 16,
 	.bp_in_mask = 0xffff,
 	.hfb_filter_cnt = 16,
+	.hfb_filter_size = 64,
 	.qtag_mask = 0x1F,
 	.tbuf_offset = 0x0600,
 	.hfb_offset = 0x1000,

From 3b5d4f5a820d362dd46472542b2e961fb1f93515 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:34 -0800
Subject: [PATCH 1811/2753] net: bcmgenet: move DESC_INDEX flow to ring 0

The default transmit and receive packet handling is moved from
the DESC_INDEX (i.e. 16) descriptor rings to the Ring 0 queues.
This saves a fair amount of special case code by unifying the
handling.

A default dummy filter is enabled in the Hardware Filter Block
to route default receive packets to Ring 0.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-7-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 369 +++++-------------
 .../net/ethernet/broadcom/genet/bcmgenet.h    |  12 +-
 .../ethernet/broadcom/genet/bcmgenet_wol.c    |   4 +-
 3 files changed, 110 insertions(+), 275 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 9aeb1133ffa12..356d100b729d8 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -41,15 +41,13 @@
 
 #include "bcmgenet.h"
 
-/* Maximum number of hardware queues, downsized if needed */
-#define GENET_MAX_MQ_CNT	4
-
 /* Default highest priority queue for multi queue support */
-#define GENET_Q0_PRIORITY	0
+#define GENET_Q1_PRIORITY	0
+#define GENET_Q0_PRIORITY	1
 
-#define GENET_Q16_RX_BD_CNT	\
+#define GENET_Q0_RX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->rx_queues * priv->hw_params->rx_bds_per_q)
-#define GENET_Q16_TX_BD_CNT	\
+#define GENET_Q0_TX_BD_CNT	\
 	(TOTAL_DESC - priv->hw_params->tx_queues * priv->hw_params->tx_bds_per_q)
 
 #define RX_BUF_LENGTH		2048
@@ -607,7 +605,7 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 	u16 mask_16;
 	size_t size;
 
-	f = fs->location;
+	f = fs->location + 1;
 	if (fs->flow_type & FLOW_MAC_EXT) {
 		bcmgenet_hfb_insert_data(priv, f, 0,
 					 &fs->h_ext.h_dest, &fs->m_ext.h_dest,
@@ -689,19 +687,14 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 	}
 
 	bcmgenet_hfb_set_filter_length(priv, f, 2 * f_length);
-	if (!fs->ring_cookie || fs->ring_cookie == RX_CLS_FLOW_WAKE) {
-		/* Ring 0 flows can be handled by the default Descriptor Ring
-		 * We'll map them to ring 0, but don't enable the filter
-		 */
+	if (fs->ring_cookie == RX_CLS_FLOW_WAKE)
 		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, 0);
-		rule->state = BCMGENET_RXNFC_STATE_DISABLED;
-	} else {
+	else
 		/* Other Rx rings are direct mapped here */
 		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f,
 							 fs->ring_cookie);
-		bcmgenet_hfb_enable_filter(priv, f);
-		rule->state = BCMGENET_RXNFC_STATE_ENABLED;
-	}
+	bcmgenet_hfb_enable_filter(priv, f);
+	rule->state = BCMGENET_RXNFC_STATE_ENABLED;
 }
 
 /* bcmgenet_hfb_clear
@@ -735,6 +728,10 @@ static void bcmgenet_hfb_clear(struct bcmgenet_priv *priv)
 
 	for (i = 0; i < priv->hw_params->hfb_filter_cnt; i++)
 		bcmgenet_hfb_clear_filter(priv, i);
+
+	/* Enable filter 0 to send default flow to ring 0 */
+	bcmgenet_hfb_set_filter_length(priv, 0, 4);
+	bcmgenet_hfb_enable_filter(priv, 0);
 }
 
 static void bcmgenet_hfb_init(struct bcmgenet_priv *priv)
@@ -836,20 +833,16 @@ static int bcmgenet_get_coalesce(struct net_device *dev,
 	unsigned int i;
 
 	ec->tx_max_coalesced_frames =
-		bcmgenet_tdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_tdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_max_coalesced_frames =
-		bcmgenet_rdma_ring_readl(priv, DESC_INDEX,
-					 DMA_MBUF_DONE_THRESH);
+		bcmgenet_rdma_ring_readl(priv, 0, DMA_MBUF_DONE_THRESH);
 	ec->rx_coalesce_usecs =
-		bcmgenet_rdma_readl(priv, DMA_RING16_TIMEOUT) * 8192 / 1000;
+		bcmgenet_rdma_readl(priv, DMA_RING0_TIMEOUT) * 8192 / 1000;
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
 		ring = &priv->rx_rings[i];
 		ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 	}
-	ring = &priv->rx_rings[DESC_INDEX];
-	ec->use_adaptive_rx_coalesce |= ring->dim.use_dim;
 
 	return 0;
 }
@@ -919,17 +912,13 @@ static int bcmgenet_set_coalesce(struct net_device *dev,
 	/* Program all TX queues with the same values, as there is no
 	 * ethtool knob to do coalescing on a per-queue basis
 	 */
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		bcmgenet_tdma_ring_writel(priv, i,
 					  ec->tx_max_coalesced_frames,
 					  DMA_MBUF_DONE_THRESH);
-	bcmgenet_tdma_ring_writel(priv, DESC_INDEX,
-				  ec->tx_max_coalesced_frames,
-				  DMA_MBUF_DONE_THRESH);
 
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[i], ec);
-	bcmgenet_set_ring_rx_coalesce(&priv->rx_rings[DESC_INDEX], ec);
 
 	return 0;
 }
@@ -1137,7 +1126,7 @@ static const struct bcmgenet_stats bcmgenet_gstrings_stats[] = {
 	STAT_GENET_Q(1),
 	STAT_GENET_Q(2),
 	STAT_GENET_Q(3),
-	STAT_GENET_Q(16),
+	STAT_GENET_Q(4),
 };
 
 #define BCMGENET_STATS_LEN	ARRAY_SIZE(bcmgenet_gstrings_stats)
@@ -1489,10 +1478,10 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 		loc_rule = &priv->rxnfc_rules[cmd->fs.location];
 	}
 	if (loc_rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (loc_rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&loc_rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	loc_rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memcpy(&loc_rule->fs, &cmd->fs,
@@ -1522,10 +1511,10 @@ static int bcmgenet_delete_flow(struct net_device *dev,
 	}
 
 	if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
-		bcmgenet_hfb_disable_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_disable_filter(priv, cmd->fs.location + 1);
 	if (rule->state != BCMGENET_RXNFC_STATE_UNUSED) {
 		list_del(&rule->list);
-		bcmgenet_hfb_clear_filter(priv, cmd->fs.location);
+		bcmgenet_hfb_clear_filter(priv, cmd->fs.location + 1);
 	}
 	rule->state = BCMGENET_RXNFC_STATE_UNUSED;
 	memset(&rule->fs, 0, sizeof(struct ethtool_rx_flow_spec));
@@ -1776,18 +1765,6 @@ static struct enet_cb *bcmgenet_put_txcb(struct bcmgenet_priv *priv,
 	return tx_cb_ptr;
 }
 
-static inline void bcmgenet_rx_ring16_int_disable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_rx_ring16_int_enable(struct bcmgenet_rx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_RXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_rx_ring_int_disable(struct bcmgenet_rx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv,
@@ -1802,18 +1779,6 @@ static inline void bcmgenet_rx_ring_int_enable(struct bcmgenet_rx_ring *ring)
 				 INTRL2_CPU_MASK_CLEAR);
 }
 
-static inline void bcmgenet_tx_ring16_int_disable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_SET);
-}
-
-static inline void bcmgenet_tx_ring16_int_enable(struct bcmgenet_tx_ring *ring)
-{
-	bcmgenet_intrl2_0_writel(ring->priv, UMAC_IRQ_TXDMA_DONE,
-				 INTRL2_CPU_MASK_CLEAR);
-}
-
 static inline void bcmgenet_tx_ring_int_enable(struct bcmgenet_tx_ring *ring)
 {
 	bcmgenet_intrl2_1_writel(ring->priv, 1 << ring->index,
@@ -1894,12 +1859,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	struct sk_buff *skb;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX)
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_TXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	else
-		bcmgenet_intrl2_1_writel(priv, (1 << ring->index),
-					 INTRL2_CPU_CLEAR);
+	bcmgenet_intrl2_1_writel(priv, (1 << ring->index), INTRL2_CPU_CLEAR);
 
 	/* Compute how many buffers are transmitted since last xmit call */
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX)
@@ -1933,7 +1893,7 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 	ring->packets += pkts_compl;
 	ring->bytes += bytes_compl;
 
-	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->queue),
+	netdev_tx_completed_queue(netdev_get_tx_queue(dev, ring->index),
 				  pkts_compl, bytes_compl);
 
 	return txbds_processed;
@@ -1961,14 +1921,14 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 	spin_lock(&ring->lock);
 	work_done = __bcmgenet_tx_reclaim(ring->priv->dev, ring);
 	if (ring->free_bds > (MAX_SKB_FRAGS + 1)) {
-		txq = netdev_get_tx_queue(ring->priv->dev, ring->queue);
+		txq = netdev_get_tx_queue(ring->priv->dev, ring->index);
 		netif_tx_wake_queue(txq);
 	}
 	spin_unlock(&ring->lock);
 
 	if (work_done == 0) {
 		napi_complete(napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 
 		return 0;
 	}
@@ -1979,14 +1939,11 @@ static int bcmgenet_tx_poll(struct napi_struct *napi, int budget)
 static void bcmgenet_tx_reclaim_all(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	int i;
-
-	if (netif_is_multiqueue(dev)) {
-		for (i = 0; i < priv->hw_params->tx_queues; i++)
-			bcmgenet_tx_reclaim(dev, &priv->tx_rings[i]);
-	}
+	int i = 0;
 
-	bcmgenet_tx_reclaim(dev, &priv->tx_rings[DESC_INDEX]);
+	do {
+		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++]);
+	} while (i <= priv->hw_params->tx_queues && netif_is_multiqueue(dev));
 }
 
 /* Reallocate the SKB to put enough headroom in front of it and insert
@@ -2074,19 +2031,14 @@ static netdev_tx_t bcmgenet_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	index = skb_get_queue_mapping(skb);
 	/* Mapping strategy:
-	 * queue_mapping = 0, unclassified, packet xmited through ring16
-	 * queue_mapping = 1, goes to ring 0. (highest priority queue
-	 * queue_mapping = 2, goes to ring 1.
-	 * queue_mapping = 3, goes to ring 2.
-	 * queue_mapping = 4, goes to ring 3.
+	 * queue_mapping = 0, unclassified, packet xmited through ring 0
+	 * queue_mapping = 1, goes to ring 1. (highest priority queue)
+	 * queue_mapping = 2, goes to ring 2.
+	 * queue_mapping = 3, goes to ring 3.
+	 * queue_mapping = 4, goes to ring 4.
 	 */
-	if (index == 0)
-		index = DESC_INDEX;
-	else
-		index -= 1;
-
 	ring = &priv->tx_rings[index];
-	txq = netdev_get_tx_queue(dev, ring->queue);
+	txq = netdev_get_tx_queue(dev, index);
 
 	nr_frags = skb_shinfo(skb)->nr_frags;
 
@@ -2259,15 +2211,8 @@ static unsigned int bcmgenet_desc_rx(struct bcmgenet_rx_ring *ring,
 	unsigned int discards;
 
 	/* Clear status before servicing to reduce spurious interrupts */
-	if (ring->index == DESC_INDEX) {
-		bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_RXDMA_DONE,
-					 INTRL2_CPU_CLEAR);
-	} else {
-		mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
-		bcmgenet_intrl2_1_writel(priv,
-					 mask,
-					 INTRL2_CPU_CLEAR);
-	}
+	mask = 1 << (UMAC_IRQ1_RX_INTR_SHIFT + ring->index);
+	bcmgenet_intrl2_1_writel(priv, mask, INTRL2_CPU_CLEAR);
 
 	p_index = bcmgenet_rdma_ring_readl(priv, ring->index, RDMA_PROD_INDEX);
 
@@ -2416,7 +2361,7 @@ static int bcmgenet_rx_poll(struct napi_struct *napi, int budget)
 
 	if (work_done < budget) {
 		napi_complete_done(napi, work_done);
-		ring->int_enable(ring);
+		bcmgenet_rx_ring_int_enable(ring);
 	}
 
 	if (ring->dim.use_dim) {
@@ -2656,15 +2601,6 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	spin_lock_init(&ring->lock);
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->queue = 0;
-		ring->int_enable = bcmgenet_tx_ring16_int_enable;
-		ring->int_disable = bcmgenet_tx_ring16_int_disable;
-	} else {
-		ring->queue = index + 1;
-		ring->int_enable = bcmgenet_tx_ring_int_enable;
-		ring->int_disable = bcmgenet_tx_ring_int_disable;
-	}
 	ring->cbs = priv->tx_cbs + start_ptr;
 	ring->size = size;
 	ring->clean_ptr = start_ptr;
@@ -2675,8 +2611,8 @@ static void bcmgenet_init_tx_ring(struct bcmgenet_priv *priv,
 	ring->end_ptr = end_ptr - 1;
 	ring->prod_index = 0;
 
-	/* Set flow period for ring != 16 */
-	if (index != DESC_INDEX)
+	/* Set flow period for ring != 0 */
+	if (index)
 		flow_period_val = ENET_MAX_MTU_SIZE << 16;
 
 	bcmgenet_tdma_ring_writel(priv, index, 0, TDMA_PROD_INDEX);
@@ -2714,13 +2650,6 @@ static int bcmgenet_init_rx_ring(struct bcmgenet_priv *priv,
 
 	ring->priv = priv;
 	ring->index = index;
-	if (index == DESC_INDEX) {
-		ring->int_enable = bcmgenet_rx_ring16_int_enable;
-		ring->int_disable = bcmgenet_rx_ring16_int_disable;
-	} else {
-		ring->int_enable = bcmgenet_rx_ring_int_enable;
-		ring->int_disable = bcmgenet_rx_ring_int_disable;
-	}
 	ring->cbs = priv->rx_cbs + start_ptr;
 	ring->size = size;
 	ring->c_index = 0;
@@ -2766,15 +2695,11 @@ static void bcmgenet_enable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_tx_ring_int_enable(ring);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
@@ -2782,13 +2707,10 @@ static void bcmgenet_disable_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		napi_disable(&ring->napi);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
 }
 
 static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
@@ -2796,33 +2718,31 @@ static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_tx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->tx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->tx_queues; ++i) {
 		ring = &priv->tx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
-
-	ring = &priv->tx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
 }
 
 /* Initialize Tx queues
  *
- * Queues 0-3 are priority-based, each one has 32 descriptors,
- * with queue 0 being the highest priority queue.
+ * Queues 1-4 are priority-based, each one has 32 descriptors,
+ * with queue 1 being the highest priority queue.
  *
- * Queue 16 is the default Tx queue with
- * GENET_Q16_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
+ * Queue 0 is the default Tx queue with
+ * GENET_Q0_TX_BD_CNT = 256 - 4 * 32 = 128 descriptors.
  *
  * The transmit control block pool is then partitioned as follows:
- * - Tx queue 0 uses tx_cbs[0..31]
- * - Tx queue 1 uses tx_cbs[32..63]
- * - Tx queue 2 uses tx_cbs[64..95]
- * - Tx queue 3 uses tx_cbs[96..127]
- * - Tx queue 16 uses tx_cbs[128..255]
+ * - Tx queue 0 uses tx_cbs[0..127]
+ * - Tx queue 1 uses tx_cbs[128..159]
+ * - Tx queue 2 uses tx_cbs[160..191]
+ * - Tx queue 3 uses tx_cbs[192..223]
+ * - Tx queue 4 uses tx_cbs[224..255]
  */
 static void bcmgenet_init_tx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	unsigned int start = 0, end = GENET_Q0_TX_BD_CNT;
 	u32 i, dma_enable;
 	u32 dma_ctrl, ring_cfg;
 	u32 dma_priority[3] = {0, 0, 0};
@@ -2839,27 +2759,17 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);
 
 	/* Initialize Tx priority queues */
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		bcmgenet_init_tx_ring(priv, i, priv->hw_params->tx_bds_per_q,
-				      i * priv->hw_params->tx_bds_per_q,
-				      (i + 1) * priv->hw_params->tx_bds_per_q);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		bcmgenet_init_tx_ring(priv, i, end - start, start, end);
+		start = end;
+		end += priv->hw_params->tx_bds_per_q;
 		ring_cfg |= (1 << i);
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 		dma_priority[DMA_PRIO_REG_INDEX(i)] |=
-			((GENET_Q0_PRIORITY + i) << DMA_PRIO_REG_SHIFT(i));
+			(i ? GENET_Q1_PRIORITY : GENET_Q0_PRIORITY)
+			<< DMA_PRIO_REG_SHIFT(i);
 	}
 
-	/* Initialize Tx default queue 16 */
-	bcmgenet_init_tx_ring(priv, DESC_INDEX, GENET_Q16_TX_BD_CNT,
-			      priv->hw_params->tx_queues *
-			      priv->hw_params->tx_bds_per_q,
-			      TOTAL_DESC);
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
-	dma_priority[DMA_PRIO_REG_INDEX(DESC_INDEX)] |=
-		((GENET_Q0_PRIORITY + priv->hw_params->tx_queues) <<
-		 DMA_PRIO_REG_SHIFT(DESC_INDEX));
-
 	/* Set Tx queue priorities */
 	bcmgenet_tdma_writel(priv, dma_priority[0], DMA_PRIORITY_0);
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
@@ -2879,15 +2789,11 @@ static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_enable(&ring->napi);
-		ring->int_enable(ring);
+		bcmgenet_rx_ring_int_enable(ring);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_enable(&ring->napi);
-	ring->int_enable(ring);
 }
 
 static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
@@ -2895,15 +2801,11 @@ static void bcmgenet_disable_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		napi_disable(&ring->napi);
 		cancel_work_sync(&ring->dim.dim.work);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	napi_disable(&ring->napi);
-	cancel_work_sync(&ring->dim.dim.work);
 }
 
 static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
@@ -2911,13 +2813,10 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
 	unsigned int i;
 	struct bcmgenet_rx_ring *ring;
 
-	for (i = 0; i < priv->hw_params->rx_queues; ++i) {
+	for (i = 0; i <= priv->hw_params->rx_queues; ++i) {
 		ring = &priv->rx_rings[i];
 		netif_napi_del(&ring->napi);
 	}
-
-	ring = &priv->rx_rings[DESC_INDEX];
-	netif_napi_del(&ring->napi);
 }
 
 /* Initialize Rx queues
@@ -2925,15 +2824,13 @@ static void bcmgenet_fini_rx_napi(struct bcmgenet_priv *priv)
  * Queues 0-15 are priority queues. Hardware Filtering Block (HFB) can be
  * used to direct traffic to these queues.
  *
- * Queue 16 is the default Rx queue with GENET_Q16_RX_BD_CNT descriptors.
+ * Queue 0 is also the default Rx queue with GENET_Q0_RX_BD_CNT descriptors.
  */
 static int bcmgenet_init_rx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 i;
-	u32 dma_enable;
-	u32 dma_ctrl;
-	u32 ring_cfg;
+	unsigned int start = 0, end = GENET_Q0_RX_BD_CNT;
+	u32 i, dma_enable, dma_ctrl = 0, ring_cfg = 0;
 	int ret;
 
 	dma_ctrl = bcmgenet_rdma_readl(priv, DMA_CTRL);
@@ -2945,34 +2842,21 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 	ring_cfg = 0;
 
 	/* Initialize Rx priority queues */
-	for (i = 0; i < priv->hw_params->rx_queues; i++) {
-		ret = bcmgenet_init_rx_ring(priv, i,
-					    priv->hw_params->rx_bds_per_q,
-					    i * priv->hw_params->rx_bds_per_q,
-					    (i + 1) *
-					    priv->hw_params->rx_bds_per_q);
+	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
+		ret = bcmgenet_init_rx_ring(priv, i, end - start, start, end);
 		if (ret)
 			return ret;
 
+		start = end;
+		end += priv->hw_params->rx_bds_per_q;
 		ring_cfg |= (1 << i);
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	}
 
-	/* Initialize Rx default queue 16 */
-	ret = bcmgenet_init_rx_ring(priv, DESC_INDEX, GENET_Q16_RX_BD_CNT,
-				    priv->hw_params->rx_queues *
-				    priv->hw_params->rx_bds_per_q,
-				    TOTAL_DESC);
-	if (ret)
-		return ret;
-
-	ring_cfg |= (1 << DESC_INDEX);
-	dma_ctrl |= (1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT));
-
-	/* Enable rings */
+	/* Configure Rx queues as descriptor rings */
 	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
 
-	/* Configure ring as descriptor ring and re-enable DMA if enabled */
+	/* Enable Rx rings */
 	if (dma_enable)
 		dma_ctrl |= DMA_EN;
 	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
@@ -3031,14 +2915,14 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 	}
 
 	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
 	reg &= ~dma_ctrl;
 	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
 
 	dma_ctrl = 0;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
 	reg &= ~dma_ctrl;
@@ -3059,14 +2943,11 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 		dev_kfree_skb(bcmgenet_free_tx_cb(&priv->pdev->dev,
 						  priv->tx_cbs + i));
 
-	for (i = 0; i < priv->hw_params->tx_queues; i++) {
-		txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[i].queue);
+	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
+		txq = netdev_get_tx_queue(priv->dev, i);
 		netdev_tx_reset_queue(txq);
 	}
 
-	txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[DESC_INDEX].queue);
-	netdev_tx_reset_queue(txq);
-
 	bcmgenet_free_rx_buffers(priv);
 	kfree(priv->rx_cbs);
 	kfree(priv->tx_cbs);
@@ -3159,7 +3040,7 @@ static void bcmgenet_irq_task(struct work_struct *work)
 
 }
 
-/* bcmgenet_isr1: handle Rx and Tx priority queues */
+/* bcmgenet_isr1: handle Rx and Tx queues */
 static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
@@ -3178,7 +3059,7 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		  "%s: IRQ=0x%x\n", __func__, status);
 
 	/* Check Rx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->rx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->rx_queues; index++) {
 		if (!(status & BIT(UMAC_IRQ1_RX_INTR_SHIFT + index)))
 			continue;
 
@@ -3186,20 +3067,20 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 		rx_ring->dim.event_ctr++;
 
 		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
+			bcmgenet_rx_ring_int_disable(rx_ring);
 			__napi_schedule_irqoff(&rx_ring->napi);
 		}
 	}
 
 	/* Check Tx priority queue interrupts */
-	for (index = 0; index < priv->hw_params->tx_queues; index++) {
+	for (index = 0; index <= priv->hw_params->tx_queues; index++) {
 		if (!(status & BIT(index)))
 			continue;
 
 		tx_ring = &priv->tx_rings[index];
 
 		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
+			bcmgenet_tx_ring_int_disable(tx_ring);
 			__napi_schedule_irqoff(&tx_ring->napi);
 		}
 	}
@@ -3207,12 +3088,10 @@ static irqreturn_t bcmgenet_isr1(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
-/* bcmgenet_isr0: handle Rx and Tx default queues + other stuff */
+/* bcmgenet_isr0: handle other stuff */
 static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 {
 	struct bcmgenet_priv *priv = dev_id;
-	struct bcmgenet_rx_ring *rx_ring;
-	struct bcmgenet_tx_ring *tx_ring;
 	unsigned int status;
 	unsigned long flags;
 
@@ -3226,25 +3105,6 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	netif_dbg(priv, intr, priv->dev,
 		  "IRQ=0x%x\n", status);
 
-	if (status & UMAC_IRQ_RXDMA_DONE) {
-		rx_ring = &priv->rx_rings[DESC_INDEX];
-		rx_ring->dim.event_ctr++;
-
-		if (likely(napi_schedule_prep(&rx_ring->napi))) {
-			rx_ring->int_disable(rx_ring);
-			__napi_schedule_irqoff(&rx_ring->napi);
-		}
-	}
-
-	if (status & UMAC_IRQ_TXDMA_DONE) {
-		tx_ring = &priv->tx_rings[DESC_INDEX];
-
-		if (likely(napi_schedule_prep(&tx_ring->napi))) {
-			tx_ring->int_disable(tx_ring);
-			__napi_schedule_irqoff(&tx_ring->napi);
-		}
-	}
-
 	if (bcmgenet_has_mdio_intr(priv) &&
 		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
 		wake_up(&priv->wq);
@@ -3310,15 +3170,15 @@ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
 	u32 dma_ctrl;
 
 	/* disable DMA */
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
+	dma_ctrl = DMA_EN;
+	for (i = 0; i <= priv->hw_params->tx_queues; i++)
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
 	reg &= ~dma_ctrl;
 	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
 
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	dma_ctrl = DMA_EN;
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
 	reg &= ~dma_ctrl;
@@ -3401,6 +3261,9 @@ static int bcmgenet_open(struct net_device *dev)
 
 	bcmgenet_set_hw_addr(priv, dev->dev_addr);
 
+	/* HFB init */
+	bcmgenet_hfb_init(priv);
+
 	/* Disable RX/TX DMA and flush TX and RX queues */
 	dma_ctrl = bcmgenet_dma_disable(priv, true);
 
@@ -3411,12 +3274,8 @@ static int bcmgenet_open(struct net_device *dev)
 		goto err_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
 	bcmgenet_enable_dma(priv, dma_ctrl);
 
-	/* HFB init */
-	bcmgenet_hfb_init(priv);
-
 	ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
 			  dev->name, priv);
 	if (ret < 0) {
@@ -3523,16 +3382,11 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 	if (!netif_msg_tx_err(priv))
 		return;
 
-	txq = netdev_get_tx_queue(priv->dev, ring->queue);
+	txq = netdev_get_tx_queue(priv->dev, ring->index);
 
 	spin_lock(&ring->lock);
-	if (ring->index == DESC_INDEX) {
-		intsts = ~bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = UMAC_IRQ_TXDMA_DONE | UMAC_IRQ_TXDMA_MBDONE;
-	} else {
-		intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
-		intmsk = 1 << ring->index;
-	}
+	intsts = ~bcmgenet_intrl2_1_readl(priv, INTRL2_CPU_MASK_STATUS);
+	intmsk = 1 << ring->index;
 	c_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_CONS_INDEX);
 	p_index = bcmgenet_tdma_ring_readl(priv, ring->index, TDMA_PROD_INDEX);
 	txq_stopped = netif_tx_queue_stopped(txq);
@@ -3546,7 +3400,7 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 		  "(sw)c_index: %d (hw)c_index: %d\n"
 		  "(sw)clean_p: %d (sw)write_p: %d\n"
 		  "(sw)cb_ptr: %d (sw)end_ptr: %d\n",
-		  ring->index, ring->queue,
+		  ring->index, ring->index,
 		  txq_stopped ? "stopped" : "active",
 		  intsts & intmsk ? "enabled" : "disabled",
 		  free_bds, ring->size,
@@ -3559,25 +3413,20 @@ static void bcmgenet_dump_tx_queue(struct bcmgenet_tx_ring *ring)
 static void bcmgenet_timeout(struct net_device *dev, unsigned int txqueue)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	u32 int0_enable = 0;
 	u32 int1_enable = 0;
 	unsigned int q;
 
 	netif_dbg(priv, tx_err, dev, "bcmgenet_timeout\n");
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		bcmgenet_dump_tx_queue(&priv->tx_rings[q]);
-	bcmgenet_dump_tx_queue(&priv->tx_rings[DESC_INDEX]);
 
 	bcmgenet_tx_reclaim_all(dev);
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++)
+	for (q = 0; q <= priv->hw_params->tx_queues; q++)
 		int1_enable |= (1 << q);
 
-	int0_enable = UMAC_IRQ_TXDMA_DONE;
-
 	/* Re-enable TX interrupts if disabled */
-	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 	bcmgenet_intrl2_1_writel(priv, int1_enable, INTRL2_CPU_MASK_CLEAR);
 
 	netif_trans_update(dev);
@@ -3681,16 +3530,13 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 	struct bcmgenet_rx_ring *rx_ring;
 	unsigned int q;
 
-	for (q = 0; q < priv->hw_params->tx_queues; q++) {
+	for (q = 0; q <= priv->hw_params->tx_queues; q++) {
 		tx_ring = &priv->tx_rings[q];
 		tx_bytes += tx_ring->bytes;
 		tx_packets += tx_ring->packets;
 	}
-	tx_ring = &priv->tx_rings[DESC_INDEX];
-	tx_bytes += tx_ring->bytes;
-	tx_packets += tx_ring->packets;
 
-	for (q = 0; q < priv->hw_params->rx_queues; q++) {
+	for (q = 0; q <= priv->hw_params->rx_queues; q++) {
 		rx_ring = &priv->rx_rings[q];
 
 		rx_bytes += rx_ring->bytes;
@@ -3698,11 +3544,6 @@ static struct net_device_stats *bcmgenet_get_stats(struct net_device *dev)
 		rx_errors += rx_ring->errors;
 		rx_dropped += rx_ring->dropped;
 	}
-	rx_ring = &priv->rx_rings[DESC_INDEX];
-	rx_bytes += rx_ring->bytes;
-	rx_packets += rx_ring->packets;
-	rx_errors += rx_ring->errors;
-	rx_dropped += rx_ring->dropped;
 
 	dev->stats.tx_bytes = tx_bytes;
 	dev->stats.tx_packets = tx_packets;
@@ -4141,16 +3982,13 @@ static int bcmgenet_probe(struct platform_device *pdev)
 	if (err)
 		goto err_clk_disable;
 
-	/* setup number of real queues  + 1 (GENET_V1 has 0 hardware queues
-	 * just the ring 16 descriptor based TX
-	 */
+	/* setup number of real queues + 1 */
 	netif_set_real_num_tx_queues(priv->dev, priv->hw_params->tx_queues + 1);
 	netif_set_real_num_rx_queues(priv->dev, priv->hw_params->rx_queues + 1);
 
 	/* Set default coalescing parameters */
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
+	for (i = 0; i <= priv->hw_params->rx_queues; i++)
 		priv->rx_rings[i].rx_max_coalesced_frames = 1;
-	priv->rx_rings[DESC_INDEX].rx_max_coalesced_frames = 1;
 
 	/* libphy will determine the link state */
 	netif_carrier_off(dev);
@@ -4273,7 +4111,6 @@ static int bcmgenet_resume(struct device *d)
 		goto out_clk_disable;
 	}
 
-	/* Always enable ring 16 - descriptor ring */
 	bcmgenet_enable_dma(priv, dma_ctrl);
 
 	if (!device_may_wakeup(d))
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index a7f121503ffb0..926523d019dbf 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -18,6 +18,9 @@
 
 #include "../unimac.h"
 
+/* Maximum number of hardware queues, downsized if needed */
+#define GENET_MAX_MQ_CNT	4
+
 /* total number of Buffer Descriptors, same for Rx/Tx */
 #define TOTAL_DESC				256
 
@@ -513,7 +516,6 @@ struct bcmgenet_tx_ring {
 	unsigned long	packets;
 	unsigned long	bytes;
 	unsigned int	index;		/* ring index */
-	unsigned int	queue;		/* queue index */
 	struct enet_cb	*cbs;		/* tx ring buffer control block*/
 	unsigned int	size;		/* size of each tx ring */
 	unsigned int    clean_ptr;      /* Tx ring clean pointer */
@@ -523,8 +525,6 @@ struct bcmgenet_tx_ring {
 	unsigned int	prod_index;	/* Tx ring producer index SW copy */
 	unsigned int	cb_ptr;		/* Tx ring initial CB ptr */
 	unsigned int	end_ptr;	/* Tx ring end CB ptr */
-	void (*int_enable)(struct bcmgenet_tx_ring *);
-	void (*int_disable)(struct bcmgenet_tx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -553,8 +553,6 @@ struct bcmgenet_rx_ring {
 	struct bcmgenet_net_dim dim;
 	u32		rx_max_coalesced_frames;
 	u32		rx_coalesce_usecs;
-	void (*int_enable)(struct bcmgenet_rx_ring *);
-	void (*int_disable)(struct bcmgenet_rx_ring *);
 	struct bcmgenet_priv *priv;
 };
 
@@ -583,7 +581,7 @@ struct bcmgenet_priv {
 	struct enet_cb *tx_cbs;
 	unsigned int num_tx_bds;
 
-	struct bcmgenet_tx_ring tx_rings[DESC_INDEX + 1];
+	struct bcmgenet_tx_ring tx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* receive variables */
 	void __iomem *rx_bds;
@@ -593,7 +591,7 @@ struct bcmgenet_priv {
 	struct bcmgenet_rxnfc_rule rxnfc_rules[MAX_NUM_OF_FS_RULES];
 	struct list_head rxnfc_list;
 
-	struct bcmgenet_rx_ring rx_rings[DESC_INDEX + 1];
+	struct bcmgenet_rx_ring rx_rings[GENET_MAX_MQ_CNT + 1];
 
 	/* other misc variables */
 	const struct bcmgenet_hw_params *hw_params;
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 3b082114f2e53..f37665ce40cbc 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -2,7 +2,7 @@
 /*
  * Broadcom GENET (Gigabit Ethernet) Wake-on-LAN support
  *
- * Copyright (c) 2014-2024 Broadcom
+ * Copyright (c) 2014-2025 Broadcom
  */
 
 #define pr_fmt(fmt)				"bcmgenet_wol: " fmt
@@ -180,7 +180,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	if (priv->wolopts & WAKE_FILTER) {
 		list_for_each_entry(rule, &priv->rxnfc_list, list)
 			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE)
-				hfb_enable |= (1 << rule->fs.location);
+				hfb_enable |= (1 << (rule->fs.location + 1));
 		reg = (hfb_ctrl_reg & ~RBUF_HFB_EN) | RBUF_ACPI_EN;
 		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 	}

From 6d31f8fc6c2f1b74a0b94a92235ace9f43be5621 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:35 -0800
Subject: [PATCH 1812/2753] net: bcmgenet: add support for RX_CLS_FLOW_DISC

Now that the DESC_INDEX ring descriptor is no longer used we can
enable hardware discarding of flows by routing them to a queue
that is not enabled.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-8-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c | 13 ++++++++-----
 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 356d100b729d8..ea575e5ae4993 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -599,7 +599,7 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 					     struct bcmgenet_rxnfc_rule *rule)
 {
 	struct ethtool_rx_flow_spec *fs = &rule->fs;
-	u32 offset = 0, f_length = 0, f;
+	u32 offset = 0, f_length = 0, f, q;
 	u8 val_8, mask_8;
 	__be16 val_16;
 	u16 mask_16;
@@ -688,11 +688,13 @@ static void bcmgenet_hfb_create_rxnfc_filter(struct bcmgenet_priv *priv,
 
 	bcmgenet_hfb_set_filter_length(priv, f, 2 * f_length);
 	if (fs->ring_cookie == RX_CLS_FLOW_WAKE)
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, 0);
+		q = 0;
+	else if (fs->ring_cookie == RX_CLS_FLOW_DISC)
+		q = priv->hw_params->rx_queues + 1;
 	else
 		/* Other Rx rings are direct mapped here */
-		bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f,
-							 fs->ring_cookie);
+		q = fs->ring_cookie;
+	bcmgenet_hfb_set_filter_rx_queue_mapping(priv, f, q);
 	bcmgenet_hfb_enable_filter(priv, f);
 	rule->state = BCMGENET_RXNFC_STATE_ENABLED;
 }
@@ -1444,7 +1446,8 @@ static int bcmgenet_insert_flow(struct net_device *dev,
 	}
 
 	if (cmd->fs.ring_cookie > priv->hw_params->rx_queues &&
-	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE) {
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_WAKE &&
+	    cmd->fs.ring_cookie != RX_CLS_FLOW_DISC) {
 		netdev_err(dev, "rxnfc: Unsupported action (%llu)\n",
 			   cmd->fs.ring_cookie);
 		return -EINVAL;

From 8b031d4e9baaa33e1b0abd09b9a98a84576a21f0 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:36 -0800
Subject: [PATCH 1813/2753] net: bcmgenet: remove dma_ctrl argument

Since the individual queues manage their own DMA enables there
is no need to return dma_ctrl from bcmgenet_dma_disable() and
pass it back to bcmgenet_enable_dma().

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-9-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 21 +++++++------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ea575e5ae4993..56fe4526c4796 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3165,8 +3165,7 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
 	put_unaligned_be16(addr_tmp, &addr[4]);
 }
 
-/* Returns a reusable dma control register value */
-static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
+static void bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
 {
 	unsigned int i;
 	u32 reg;
@@ -3198,20 +3197,18 @@ static u32 bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
 		bcmgenet_rbuf_ctrl_set(priv, reg);
 		udelay(10);
 	}
-
-	return dma_ctrl;
 }
 
-static void bcmgenet_enable_dma(struct bcmgenet_priv *priv, u32 dma_ctrl)
+static void bcmgenet_enable_dma(struct bcmgenet_priv *priv)
 {
 	u32 reg;
 
 	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
+	reg |= DMA_EN;
 	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
 
 	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg |= dma_ctrl;
+	reg |= DMA_EN;
 	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
 }
 
@@ -3238,7 +3235,6 @@ static void bcmgenet_netif_start(struct net_device *dev)
 static int bcmgenet_open(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
-	unsigned long dma_ctrl;
 	int ret;
 
 	netif_dbg(priv, ifup, dev, "bcmgenet_open\n");
@@ -3268,7 +3264,7 @@ static int bcmgenet_open(struct net_device *dev)
 	bcmgenet_hfb_init(priv);
 
 	/* Disable RX/TX DMA and flush TX and RX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, true);
+	bcmgenet_dma_disable(priv, true);
 
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
 	ret = bcmgenet_init_dma(priv);
@@ -3277,7 +3273,7 @@ static int bcmgenet_open(struct net_device *dev)
 		goto err_clk_disable;
 	}
 
-	bcmgenet_enable_dma(priv, dma_ctrl);
+	bcmgenet_enable_dma(priv);
 
 	ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
 			  dev->name, priv);
@@ -4067,7 +4063,6 @@ static int bcmgenet_resume(struct device *d)
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct bcmgenet_rxnfc_rule *rule;
-	unsigned long dma_ctrl;
 	int ret;
 
 	if (!netif_running(dev))
@@ -4105,7 +4100,7 @@ static int bcmgenet_resume(struct device *d)
 			bcmgenet_hfb_create_rxnfc_filter(priv, rule);
 
 	/* Disable RX/TX DMA and flush TX queues */
-	dma_ctrl = bcmgenet_dma_disable(priv, false);
+	bcmgenet_dma_disable(priv, false);
 
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
 	ret = bcmgenet_init_dma(priv);
@@ -4114,7 +4109,7 @@ static int bcmgenet_resume(struct device *d)
 		goto out_clk_disable;
 	}
 
-	bcmgenet_enable_dma(priv, dma_ctrl);
+	bcmgenet_enable_dma(priv);
 
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);

From 58affb23b66793033f95cb4e9a57a388e0485edb Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:37 -0800
Subject: [PATCH 1814/2753] net: bcmgenet: consolidate dma initialization

The functions bcmgenet_dma_disable and bcmgenet_enable_dma are
only used as part of dma initialization. Their functionality is
moved inside bcmgenet_init_dma and the functions are removed.

Since the dma is always disabled inside of bcmgenet_init_dma,
the initialization functions bcmgenet_init_rx_queues and
bcmgenet_init_tx_queues no longer need to attempt to manage its
state.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-10-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 150 +++++++-----------
 1 file changed, 54 insertions(+), 96 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 56fe4526c4796..ca936a7e77531 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2746,17 +2746,7 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int start = 0, end = GENET_Q0_TX_BD_CNT;
-	u32 i, dma_enable;
-	u32 dma_ctrl, ring_cfg;
-	u32 dma_priority[3] = {0, 0, 0};
-
-	dma_ctrl = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
+	u32 i, ring_mask, dma_priority[3] = {0, 0, 0};
 
 	/* Enable strict priority arbiter mode */
 	bcmgenet_tdma_writel(priv, DMA_ARBITER_SP, DMA_ARB_CTRL);
@@ -2766,8 +2756,6 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 		bcmgenet_init_tx_ring(priv, i, end - start, start, end);
 		start = end;
 		end += priv->hw_params->tx_bds_per_q;
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 		dma_priority[DMA_PRIO_REG_INDEX(i)] |=
 			(i ? GENET_Q1_PRIORITY : GENET_Q0_PRIORITY)
 			<< DMA_PRIO_REG_SHIFT(i);
@@ -2778,13 +2766,13 @@ static void bcmgenet_init_tx_queues(struct net_device *dev)
 	bcmgenet_tdma_writel(priv, dma_priority[1], DMA_PRIORITY_1);
 	bcmgenet_tdma_writel(priv, dma_priority[2], DMA_PRIORITY_2);
 
-	/* Enable Tx queues */
-	bcmgenet_tdma_writel(priv, ring_cfg, DMA_RING_CFG);
+	/* Configure Tx queues as descriptor rings */
+	ring_mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_RING_CFG);
 
-	/* Enable Tx DMA */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_tdma_writel(priv, dma_ctrl, DMA_CTRL);
+	/* Enable Tx rings */
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_tdma_writel(priv, ring_mask, DMA_CTRL);
 }
 
 static void bcmgenet_enable_rx_napi(struct bcmgenet_priv *priv)
@@ -2833,17 +2821,9 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	unsigned int start = 0, end = GENET_Q0_RX_BD_CNT;
-	u32 i, dma_enable, dma_ctrl = 0, ring_cfg = 0;
+	u32 i, ring_mask;
 	int ret;
 
-	dma_ctrl = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	dma_enable = dma_ctrl & DMA_EN;
-	dma_ctrl &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
-
-	dma_ctrl = 0;
-	ring_cfg = 0;
-
 	/* Initialize Rx priority queues */
 	for (i = 0; i <= priv->hw_params->rx_queues; i++) {
 		ret = bcmgenet_init_rx_ring(priv, i, end - start, start, end);
@@ -2852,17 +2832,15 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 
 		start = end;
 		end += priv->hw_params->rx_bds_per_q;
-		ring_cfg |= (1 << i);
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
 	}
 
 	/* Configure Rx queues as descriptor rings */
-	bcmgenet_rdma_writel(priv, ring_cfg, DMA_RING_CFG);
+	ring_mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_RING_CFG);
 
 	/* Enable Rx rings */
-	if (dma_enable)
-		dma_ctrl |= DMA_EN;
-	bcmgenet_rdma_writel(priv, dma_ctrl, DMA_CTRL);
+	ring_mask <<= DMA_RING_BUF_EN_SHIFT;
+	bcmgenet_rdma_writel(priv, ring_mask, DMA_CTRL);
 
 	return 0;
 }
@@ -2957,14 +2935,42 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 }
 
 /* init_edma: Initialize DMA control register */
-static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
+static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 {
-	int ret;
-	unsigned int i;
 	struct enet_cb *cb;
+	u32 reg, dma_ctrl;
+	unsigned int i;
+	int ret;
 
 	netif_dbg(priv, hw, priv->dev, "%s\n", __func__);
 
+	/* Disable RX/TX DMA and flush TX queues */
+	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	for (i = 0; i < priv->hw_params->tx_queues; i++)
+		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	reg &= ~dma_ctrl;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	for (i = 0; i < priv->hw_params->rx_queues; i++)
+		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	reg &= ~dma_ctrl;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
+	udelay(10);
+	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
+
+	if (flush_rx) {
+		reg = bcmgenet_rbuf_ctrl_get(priv);
+		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
+		udelay(10);
+		bcmgenet_rbuf_ctrl_set(priv, reg);
+		udelay(10);
+	}
+
 	/* Initialize common Rx ring structures */
 	priv->rx_bds = priv->base + priv->hw_params->rdma_offset;
 	priv->num_rx_bds = TOTAL_DESC;
@@ -3014,6 +3020,15 @@ static int bcmgenet_init_dma(struct bcmgenet_priv *priv)
 	/* Initialize Tx queues */
 	bcmgenet_init_tx_queues(priv->dev);
 
+	/* Enable RX/TX DMA */
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	reg |= DMA_EN;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
 	return 0;
 }
 
@@ -3165,53 +3180,6 @@ static void bcmgenet_get_hw_addr(struct bcmgenet_priv *priv,
 	put_unaligned_be16(addr_tmp, &addr[4]);
 }
 
-static void bcmgenet_dma_disable(struct bcmgenet_priv *priv, bool flush_rx)
-{
-	unsigned int i;
-	u32 reg;
-	u32 dma_ctrl;
-
-	/* disable DMA */
-	dma_ctrl = DMA_EN;
-	for (i = 0; i <= priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = DMA_EN;
-	for (i = 0; i <= priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
-	udelay(10);
-	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);
-
-	if (flush_rx) {
-		reg = bcmgenet_rbuf_ctrl_get(priv);
-		bcmgenet_rbuf_ctrl_set(priv, reg | BIT(0));
-		udelay(10);
-		bcmgenet_rbuf_ctrl_set(priv, reg);
-		udelay(10);
-	}
-}
-
-static void bcmgenet_enable_dma(struct bcmgenet_priv *priv)
-{
-	u32 reg;
-
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg |= DMA_EN;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg |= DMA_EN;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-}
-
 static void bcmgenet_netif_start(struct net_device *dev)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
@@ -3263,18 +3231,13 @@ static int bcmgenet_open(struct net_device *dev)
 	/* HFB init */
 	bcmgenet_hfb_init(priv);
 
-	/* Disable RX/TX DMA and flush TX and RX queues */
-	bcmgenet_dma_disable(priv, true);
-
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, true);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto err_clk_disable;
 	}
 
-	bcmgenet_enable_dma(priv);
-
 	ret = request_irq(priv->irq0, bcmgenet_isr0, IRQF_SHARED,
 			  dev->name, priv);
 	if (ret < 0) {
@@ -4099,18 +4062,13 @@ static int bcmgenet_resume(struct device *d)
 		if (rule->state != BCMGENET_RXNFC_STATE_UNUSED)
 			bcmgenet_hfb_create_rxnfc_filter(priv, rule);
 
-	/* Disable RX/TX DMA and flush TX queues */
-	bcmgenet_dma_disable(priv, false);
-
 	/* Reinitialize TDMA and RDMA and SW housekeeping */
-	ret = bcmgenet_init_dma(priv);
+	ret = bcmgenet_init_dma(priv, false);
 	if (ret) {
 		netdev_err(dev, "failed to initialize DMA\n");
 		goto out_clk_disable;
 	}
 
-	bcmgenet_enable_dma(priv);
-
 	if (!device_may_wakeup(d))
 		phy_resume(dev->phydev);
 

From 791f349d02f73aa5c11e84994447adcaf76a92a4 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:38 -0800
Subject: [PATCH 1815/2753] net: bcmgenet: introduce bcmgenet_[r|t]dma_disable

The bcmgenet_rdma_disable and bcmgenet_tdma_disable functions
are introduced to provide a common method for disabling each
dma and the code is simplified.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-11-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 123 +++++++++---------
 1 file changed, 62 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index ca936a7e77531..38943bbc35b14 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2727,6 +2727,52 @@ static void bcmgenet_fini_tx_napi(struct bcmgenet_priv *priv)
 	}
 }
 
+static int bcmgenet_tdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->tx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int bcmgenet_rdma_disable(struct bcmgenet_priv *priv)
+{
+	int timeout = 0;
+	u32 reg, mask;
+
+	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
+	mask = (1 << (priv->hw_params->rx_queues + 1)) - 1;
+	mask = (mask << DMA_RING_BUF_EN_SHIFT) | DMA_EN;
+	reg &= ~mask;
+	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+
+	/* Check DMA status register to confirm DMA is disabled */
+	while (timeout++ < DMA_TIMEOUT_VAL) {
+		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
+		if ((reg & mask) == mask)
+			return 0;
+
+		udelay(1);
+	}
+
+	return -ETIMEDOUT;
+}
+
 /* Initialize Tx queues
  *
  * Queues 1-4 are priority-based, each one has 32 descriptors,
@@ -2848,26 +2894,9 @@ static int bcmgenet_init_rx_queues(struct net_device *dev)
 static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 {
 	int ret = 0;
-	int timeout = 0;
-	u32 reg;
-	u32 dma_ctrl;
-	int i;
 
 	/* Disable TDMA to stop add more frames in TX DMA */
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
-	/* Check TDMA status register to confirm TDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_tdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_tdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling TX DMA\n");
 		ret = -ETIMEDOUT;
 	}
@@ -2876,39 +2905,11 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv)
 	usleep_range(10000, 20000);
 
 	/* Disable RDMA */
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~DMA_EN;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	timeout = 0;
-	/* Check RDMA status register to confirm RDMA is disabled */
-	while (timeout++ < DMA_TIMEOUT_VAL) {
-		reg = bcmgenet_rdma_readl(priv, DMA_STATUS);
-		if (reg & DMA_DISABLED)
-			break;
-
-		udelay(1);
-	}
-
-	if (timeout == DMA_TIMEOUT_VAL) {
+	if (-ETIMEDOUT == bcmgenet_rdma_disable(priv)) {
 		netdev_warn(priv->dev, "Timed out while disabling RX DMA\n");
 		ret = -ETIMEDOUT;
 	}
 
-	dma_ctrl = 0;
-	for (i = 0; i <= priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
-
-	dma_ctrl = 0;
-	for (i = 0; i <= priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
-
 	return ret;
 }
 
@@ -2938,27 +2939,27 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 static int bcmgenet_init_dma(struct bcmgenet_priv *priv, bool flush_rx)
 {
 	struct enet_cb *cb;
-	u32 reg, dma_ctrl;
 	unsigned int i;
 	int ret;
+	u32 reg;
 
 	netif_dbg(priv, hw, priv->dev, "%s\n", __func__);
 
-	/* Disable RX/TX DMA and flush TX queues */
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->tx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+	/* Disable TX DMA */
+	ret = bcmgenet_tdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Tx DMA\n");
+		return ret;
+	}
 
-	dma_ctrl = 1 << (DESC_INDEX + DMA_RING_BUF_EN_SHIFT) | DMA_EN;
-	for (i = 0; i < priv->hw_params->rx_queues; i++)
-		dma_ctrl |= (1 << (i + DMA_RING_BUF_EN_SHIFT));
-	reg = bcmgenet_rdma_readl(priv, DMA_CTRL);
-	reg &= ~dma_ctrl;
-	bcmgenet_rdma_writel(priv, reg, DMA_CTRL);
+	/* Disable RX DMA */
+	ret = bcmgenet_rdma_disable(priv);
+	if (ret) {
+		netdev_err(priv->dev, "failed to halt Rx DMA\n");
+		return ret;
+	}
 
+	/* Flush TX queues */
 	bcmgenet_umac_writel(priv, 1, UMAC_TX_FLUSH);
 	udelay(10);
 	bcmgenet_umac_writel(priv, 0, UMAC_TX_FLUSH);

From f1bacae8b655163dcbc3c54b9e714ef1a8986d7b Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:39 -0800
Subject: [PATCH 1816/2753] net: bcmgenet: support reclaiming unsent Tx packets

When disabling the transmitter any outstanding packets can now
be reclaimed by bcmgenet_tx_reclaim_all() rather than by the
bcmgenet_fini_dma() function.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-12-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 37 +++++++++++++++----
 1 file changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 38943bbc35b14..0706c9635689f 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1903,12 +1903,39 @@ static unsigned int __bcmgenet_tx_reclaim(struct net_device *dev,
 }
 
 static unsigned int bcmgenet_tx_reclaim(struct net_device *dev,
-				struct bcmgenet_tx_ring *ring)
+				struct bcmgenet_tx_ring *ring,
+				bool all)
 {
-	unsigned int released;
+	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct device *kdev = &priv->pdev->dev;
+	unsigned int released, drop, wr_ptr;
+	struct enet_cb *cb_ptr;
+	struct sk_buff *skb;
 
 	spin_lock_bh(&ring->lock);
 	released = __bcmgenet_tx_reclaim(dev, ring);
+	if (all) {
+		skb = NULL;
+		drop = (ring->prod_index - ring->c_index) & DMA_C_INDEX_MASK;
+		released += drop;
+		ring->prod_index = ring->c_index & DMA_C_INDEX_MASK;
+		while (drop--) {
+			cb_ptr = bcmgenet_put_txcb(priv, ring);
+			skb = cb_ptr->skb;
+			bcmgenet_free_tx_cb(kdev, cb_ptr);
+			if (skb && cb_ptr == GENET_CB(skb)->first_cb) {
+				dev_consume_skb_any(skb);
+				skb = NULL;
+			}
+		}
+		if (skb)
+			dev_consume_skb_any(skb);
+		bcmgenet_tdma_ring_writel(priv, ring->index,
+					  ring->prod_index, TDMA_PROD_INDEX);
+		wr_ptr = ring->write_ptr * WORDS_PER_BD(priv);
+		bcmgenet_tdma_ring_writel(priv, ring->index, wr_ptr,
+					  TDMA_WRITE_PTR);
+	}
 	spin_unlock_bh(&ring->lock);
 
 	return released;
@@ -1945,7 +1972,7 @@ static void bcmgenet_tx_reclaim_all(struct net_device *dev)
 	int i = 0;
 
 	do {
-		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++]);
+		bcmgenet_tx_reclaim(dev, &priv->tx_rings[i++], true);
 	} while (i <= priv->hw_params->tx_queues && netif_is_multiqueue(dev));
 }
 
@@ -2921,10 +2948,6 @@ static void bcmgenet_fini_dma(struct bcmgenet_priv *priv)
 	bcmgenet_fini_rx_napi(priv);
 	bcmgenet_fini_tx_napi(priv);
 
-	for (i = 0; i < priv->num_tx_bds; i++)
-		dev_kfree_skb(bcmgenet_free_tx_cb(&priv->pdev->dev,
-						  priv->tx_cbs + i));
-
 	for (i = 0; i <= priv->hw_params->tx_queues; i++) {
 		txq = netdev_get_tx_queue(priv->dev, i);
 		netdev_tx_reset_queue(txq);

From ffce2bedd361177718dc0c3787f4adb4785a0151 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:40 -0800
Subject: [PATCH 1817/2753] net: bcmgenet: move bcmgenet_power_up into
 resume_noirq

The bcmgenet_power_up() function is moved from the resume method
to the resume_noirq method for symmetry with the suspend_noirq
method. This allows the wol_active flag to be removed.

The UMAC_IRQ_WAKE_EVENT interrupts that can be unmasked by the
bcmgenet_wol_power_down_cfg() function are now re-masked by the
bcmgenet_wol_power_up_cfg() function at the resume_noirq level
as well.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-13-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 24 +++++++++----------
 .../net/ethernet/broadcom/genet/bcmgenet.h    |  1 -
 .../ethernet/broadcom/genet/bcmgenet_wol.c    |  8 +++----
 3 files changed, 15 insertions(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 0706c9635689f..8aecf56578cbd 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -4038,8 +4038,20 @@ static int bcmgenet_resume_noirq(struct device *d)
 		reg = bcmgenet_intrl2_0_readl(priv, INTRL2_CPU_STAT);
 		if (reg & UMAC_IRQ_WAKE_EVENT)
 			pm_wakeup_event(&priv->pdev->dev, 0);
+
+		/* From WOL-enabled suspend, switch to regular clock */
+		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
 	}
 
+	/* If this is an internal GPHY, power it back on now, before UniMAC is
+	 * brought out of reset as absolutely no UniMAC activity is allowed
+	 */
+	if (priv->internal_phy)
+		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
+
+	/* take MAC out of reset */
+	bcmgenet_umac_reset(priv);
+
 	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT, INTRL2_CPU_CLEAR);
 
 	return 0;
@@ -4055,18 +4067,6 @@ static int bcmgenet_resume(struct device *d)
 	if (!netif_running(dev))
 		return 0;
 
-	/* From WOL-enabled suspend, switch to regular clock */
-	if (device_may_wakeup(d) && priv->wolopts)
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
-
-	/* If this is an internal GPHY, power it back on now, before UniMAC is
-	 * brought out of reset as absolutely no UniMAC activity is allowed
-	 */
-	if (priv->internal_phy)
-		bcmgenet_power_up(priv, GENET_POWER_PASSIVE);
-
-	bcmgenet_umac_reset(priv);
-
 	init_umac(priv);
 
 	phy_init_hw(dev->phydev);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 926523d019dbf..633fa9aa07262 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -641,7 +641,6 @@ struct bcmgenet_priv {
 	struct clk *clk_wol;
 	u32 wolopts;
 	u8 sopass[SOPASS_MAX];
-	bool wol_active;
 
 	struct bcmgenet_mib_counters mib;
 
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index f37665ce40cbc..5246214aebc92 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -199,7 +199,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		  retries);
 
 	clk_prepare_enable(priv->clk_wol);
-	priv->wol_active = 1;
 
 	if (hfb_enable) {
 		bcmgenet_hfb_reg_writel(priv, hfb_enable,
@@ -238,13 +237,12 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 		return;
 	}
 
-	if (!priv->wol_active)
-		return;	/* failed to suspend so skip the rest */
-
-	priv->wol_active = 0;
 	clk_disable_unprepare(priv->clk_wol);
 	priv->crc_fwd_en = 0;
 
+	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT,
+				 INTRL2_CPU_MASK_SET);
+
 	/* Disable Magic Packet Detection */
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);

From 2432b9817b7cb91aaae9e5032da0bb017cb3102d Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:41 -0800
Subject: [PATCH 1818/2753] net: bcmgenet: allow return of power up status

It is possible for a WoL power up to fail due to the GENET being
reset while in the suspend state. Allow these failures to be
returned as error codes to allow different recovery behavior
when necessary.

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-14-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/genet/bcmgenet.c     | 13 ++++++++-----
 drivers/net/ethernet/broadcom/genet/bcmgenet.h     |  4 ++--
 drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c | 12 +++++++-----
 3 files changed, 17 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 8aecf56578cbd..8aa575b93e564 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -1685,13 +1685,14 @@ static int bcmgenet_power_down(struct bcmgenet_priv *priv,
 	return ret;
 }
 
-static void bcmgenet_power_up(struct bcmgenet_priv *priv,
-			      enum bcmgenet_power_mode mode)
+static int bcmgenet_power_up(struct bcmgenet_priv *priv,
+			     enum bcmgenet_power_mode mode)
 {
+	int ret = 0;
 	u32 reg;
 
 	if (!bcmgenet_has_ext(priv))
-		return;
+		return ret;
 
 	reg = bcmgenet_ext_readl(priv, EXT_EXT_PWR_MGMT);
 
@@ -1727,11 +1728,13 @@ static void bcmgenet_power_up(struct bcmgenet_priv *priv,
 		}
 		break;
 	case GENET_POWER_WOL_MAGIC:
-		bcmgenet_wol_power_up_cfg(priv, mode);
-		return;
+		ret = bcmgenet_wol_power_up_cfg(priv, mode);
+		break;
 	default:
 		break;
 	}
+
+	return ret;
 }
 
 static struct enet_cb *bcmgenet_get_txcb(struct bcmgenet_priv *priv,
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index 633fa9aa07262..c95601898bd44 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -724,8 +724,8 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol);
 int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode);
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode);
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode);
 
 void bcmgenet_eee_enable_set(struct net_device *dev, bool enable,
 			     bool tx_lpi_enabled);
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index 5246214aebc92..d0f1fa7029176 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -227,14 +227,14 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	return 0;
 }
 
-void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
-			       enum bcmgenet_power_mode mode)
+int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
+			      enum bcmgenet_power_mode mode)
 {
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
 		netif_err(priv, wol, priv->dev, "invalid mode: %d\n", mode);
-		return;
+		return -EINVAL;
 	}
 
 	clk_disable_unprepare(priv->clk_wol);
@@ -247,7 +247,7 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		if (!(reg & MPD_EN))
-			return;	/* already reset so skip the rest */
+			return -EPERM;	/* already reset so skip the rest */
 		reg &= ~(MPD_EN | MPD_PW_EN);
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 	}
@@ -256,7 +256,7 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	if (priv->wolopts & WAKE_FILTER) {
 		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
 		if (!(reg & RBUF_ACPI_EN))
-			return;	/* already reset so skip the rest */
+			return -EPERM;	/* already reset so skip the rest */
 		reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
 		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 	}
@@ -267,4 +267,6 @@ void bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	reg &= ~CMD_CRC_FWD;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
+
+	return 0;
 }

From 254f3239dd070e469f45c3ca8b6ac38e47d6c730 Mon Sep 17 00:00:00 2001
From: Doug Berger <opendmb@gmail.com>
Date: Thu, 6 Mar 2025 11:26:42 -0800
Subject: [PATCH 1819/2753] net: bcmgenet: revise suspend/resume

If the network interface is configured for Wake-on-LAN we should
avoid bringing the interface down and up since it slows the time
to reestablish network traffic on resume.

Redundant calls to phy_suspend() and phy_resume() are removed
since they are already invoked from within phy_stop() and
phy_start() called from bcmgenet_netif_stop() and
bcmgenet_netif_start().

Signed-off-by: Doug Berger <opendmb@gmail.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://patch.msgid.link/20250306192643.2383632-15-opendmb@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/broadcom/genet/bcmgenet.c    | 100 +++++++++++++++---
 .../net/ethernet/broadcom/genet/bcmgenet.h    |   2 +
 .../ethernet/broadcom/genet/bcmgenet_wol.c    |  69 ++++++------
 3 files changed, 119 insertions(+), 52 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
index 8aa575b93e564..73d78dcb774d9 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -2584,7 +2584,7 @@ static void init_umac(struct bcmgenet_priv *priv)
 
 	/* Enable MDIO interrupts on GENET v3+ */
 	if (bcmgenet_has_mdio_intr(priv))
-		int0_enable |= (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR);
+		int0_enable |= UMAC_IRQ_MDIO_EVENT;
 
 	bcmgenet_intrl2_0_writel(priv, int0_enable, INTRL2_CPU_MASK_CLEAR);
 
@@ -3150,10 +3150,8 @@ static irqreturn_t bcmgenet_isr0(int irq, void *dev_id)
 	netif_dbg(priv, intr, priv->dev,
 		  "IRQ=0x%x\n", status);
 
-	if (bcmgenet_has_mdio_intr(priv) &&
-		status & (UMAC_IRQ_MDIO_DONE | UMAC_IRQ_MDIO_ERROR)) {
+	if (bcmgenet_has_mdio_intr(priv) && status & UMAC_IRQ_MDIO_EVENT)
 		wake_up(&priv->wq);
-	}
 
 	/* all other interested interrupts handled in bottom half */
 	status &= (UMAC_IRQ_LINK_EVENT | UMAC_IRQ_PHY_DET_R);
@@ -3311,19 +3309,21 @@ static void bcmgenet_netif_stop(struct net_device *dev, bool stop_phy)
 {
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 
-	bcmgenet_disable_tx_napi(priv);
 	netif_tx_disable(dev);
 
 	/* Disable MAC receive */
+	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
 	umac_enable_set(priv, CMD_RX_EN, false);
 
+	if (stop_phy)
+		phy_stop(dev->phydev);
+
 	bcmgenet_dma_teardown(priv);
 
 	/* Disable MAC transmit. TX DMA disabled must be done before this */
 	umac_enable_set(priv, CMD_TX_EN, false);
 
-	if (stop_phy)
-		phy_stop(dev->phydev);
+	bcmgenet_disable_tx_napi(priv);
 	bcmgenet_disable_rx_napi(priv);
 	bcmgenet_intr_disable(priv);
 
@@ -4043,7 +4043,10 @@ static int bcmgenet_resume_noirq(struct device *d)
 			pm_wakeup_event(&priv->pdev->dev, 0);
 
 		/* From WOL-enabled suspend, switch to regular clock */
-		bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC);
+		if (!bcmgenet_power_up(priv, GENET_POWER_WOL_MAGIC))
+			return 0;
+
+		/* Failed so fall through to reset MAC */
 	}
 
 	/* If this is an internal GPHY, power it back on now, before UniMAC is
@@ -4055,8 +4058,6 @@ static int bcmgenet_resume_noirq(struct device *d)
 	/* take MAC out of reset */
 	bcmgenet_umac_reset(priv);
 
-	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT, INTRL2_CPU_CLEAR);
-
 	return 0;
 }
 
@@ -4066,10 +4067,46 @@ static int bcmgenet_resume(struct device *d)
 	struct bcmgenet_priv *priv = netdev_priv(dev);
 	struct bcmgenet_rxnfc_rule *rule;
 	int ret;
+	u32 reg;
 
 	if (!netif_running(dev))
 		return 0;
 
+	if (device_may_wakeup(d) && priv->wolopts) {
+		reg = bcmgenet_umac_readl(priv, UMAC_CMD);
+		if (reg & CMD_RX_EN) {
+			/* Successfully exited WoL, just resume data flows */
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					bcmgenet_hfb_enable_filter(priv,
+							rule->fs.location + 1);
+			bcmgenet_hfb_enable_filter(priv, 0);
+			bcmgenet_set_rx_mode(dev);
+			bcmgenet_enable_rx_napi(priv);
+
+			/* Reinitialize Tx flows */
+			bcmgenet_tdma_disable(priv);
+			bcmgenet_init_tx_queues(priv->dev);
+			reg = bcmgenet_tdma_readl(priv, DMA_CTRL);
+			reg |= DMA_EN;
+			bcmgenet_tdma_writel(priv, reg, DMA_CTRL);
+			bcmgenet_enable_tx_napi(priv);
+
+			bcmgenet_link_intr_enable(priv);
+			phy_start_machine(dev->phydev);
+
+			netif_device_attach(dev);
+			enable_irq(priv->irq1);
+			return 0;
+		}
+		/* MAC was reset so complete bcmgenet_netif_stop() */
+		umac_enable_set(priv, CMD_RX_EN | CMD_TX_EN, false);
+		bcmgenet_rdma_disable(priv);
+		bcmgenet_intr_disable(priv);
+		bcmgenet_fini_dma(priv);
+		enable_irq(priv->irq1);
+	}
+
 	init_umac(priv);
 
 	phy_init_hw(dev->phydev);
@@ -4116,19 +4153,52 @@ static int bcmgenet_suspend(struct device *d)
 {
 	struct net_device *dev = dev_get_drvdata(d);
 	struct bcmgenet_priv *priv = netdev_priv(dev);
+	struct bcmgenet_rxnfc_rule *rule;
+	u32 reg, hfb_enable = 0;
 
 	if (!netif_running(dev))
 		return 0;
 
 	netif_device_detach(dev);
 
-	bcmgenet_netif_stop(dev, true);
+	if (device_may_wakeup(d) && priv->wolopts) {
+		netif_tx_disable(dev);
+
+		/* Suspend non-wake Rx data flows */
+		if (priv->wolopts & WAKE_FILTER)
+			list_for_each_entry(rule, &priv->rxnfc_list, list)
+				if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE &&
+				    rule->state == BCMGENET_RXNFC_STATE_ENABLED)
+					hfb_enable |= 1 << rule->fs.location;
+		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+		if (GENET_IS_V1(priv) || GENET_IS_V2(priv)) {
+			reg &= ~RBUF_HFB_FILTER_EN_MASK;
+			reg |= hfb_enable << (RBUF_HFB_FILTER_EN_SHIFT + 1);
+		} else {
+			bcmgenet_hfb_reg_writel(priv, hfb_enable << 1,
+						HFB_FLT_ENABLE_V3PLUS + 4);
+		}
+		if (!hfb_enable)
+			reg &= ~RBUF_HFB_EN;
+		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
-	if (!device_may_wakeup(d))
-		phy_suspend(dev->phydev);
+		/* Clear any old filter matches so only new matches wake */
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_MASK_SET);
+		bcmgenet_intrl2_0_writel(priv, 0xFFFFFFFF, INTRL2_CPU_CLEAR);
 
-	/* Disable filtering */
-	bcmgenet_hfb_reg_writel(priv, 0, HFB_CTRL);
+		if (-ETIMEDOUT == bcmgenet_tdma_disable(priv))
+			netdev_warn(priv->dev,
+				    "Timed out while disabling TX DMA\n");
+
+		bcmgenet_disable_tx_napi(priv);
+		bcmgenet_disable_rx_napi(priv);
+		disable_irq(priv->irq1);
+		bcmgenet_tx_reclaim_all(dev);
+		bcmgenet_fini_tx_napi(priv);
+	} else {
+		/* Teardown the interface */
+		bcmgenet_netif_stop(dev, true);
+	}
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.h b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
index c95601898bd44..10c631bbe9649 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.h
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.h
@@ -274,6 +274,8 @@ struct bcmgenet_mib_counters {
 /* Only valid for GENETv3+ */
 #define UMAC_IRQ_MDIO_DONE		(1 << 23)
 #define UMAC_IRQ_MDIO_ERROR		(1 << 24)
+#define UMAC_IRQ_MDIO_EVENT		(UMAC_IRQ_MDIO_DONE | \
+					 UMAC_IRQ_MDIO_ERROR)
 
 /* INTRL2 instance 1 definitions */
 #define UMAC_IRQ1_TX_INTR_MASK		0xFFFF
diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
index d0f1fa7029176..8fb5512882980 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
@@ -145,8 +145,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 				enum bcmgenet_power_mode mode)
 {
 	struct net_device *dev = priv->dev;
-	struct bcmgenet_rxnfc_rule *rule;
-	u32 reg, hfb_ctrl_reg, hfb_enable = 0;
+	u32 reg, hfb_ctrl_reg;
 	int retries = 0;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -154,18 +153,6 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 		return -EINVAL;
 	}
 
-	/* Can't suspend with WoL if MAC is still in reset */
-	spin_lock_bh(&priv->reg_lock);
-	reg = bcmgenet_umac_readl(priv, UMAC_CMD);
-	if (reg & CMD_SW_RESET)
-		reg &= ~CMD_SW_RESET;
-
-	/* disable RX */
-	reg &= ~CMD_RX_EN;
-	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
-	spin_unlock_bh(&priv->reg_lock);
-	mdelay(10);
-
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
 		reg = bcmgenet_umac_readl(priv, UMAC_MPD_CTRL);
 		reg |= MPD_EN;
@@ -177,13 +164,8 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	}
 
 	hfb_ctrl_reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-	if (priv->wolopts & WAKE_FILTER) {
-		list_for_each_entry(rule, &priv->rxnfc_list, list)
-			if (rule->fs.ring_cookie == RX_CLS_FLOW_WAKE)
-				hfb_enable |= (1 << (rule->fs.location + 1));
-		reg = (hfb_ctrl_reg & ~RBUF_HFB_EN) | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	reg = hfb_ctrl_reg | RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Do not leave UniMAC in MPD mode only */
 	retries = bcmgenet_poll_wol_status(priv);
@@ -198,14 +180,12 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	netif_dbg(priv, wol, dev, "MPD WOL-ready status set after %d msec\n",
 		  retries);
 
-	clk_prepare_enable(priv->clk_wol);
+	/* Disable phy status updates while suspending */
+	mutex_lock(&dev->phydev->lock);
+	dev->phydev->state = PHY_READY;
+	mutex_unlock(&dev->phydev->lock);
 
-	if (hfb_enable) {
-		bcmgenet_hfb_reg_writel(priv, hfb_enable,
-					HFB_FLT_ENABLE_V3PLUS + 4);
-		hfb_ctrl_reg = RBUF_HFB_EN | RBUF_ACPI_EN;
-		bcmgenet_hfb_reg_writel(priv, hfb_ctrl_reg, HFB_CTRL);
-	}
+	clk_prepare_enable(priv->clk_wol);
 
 	/* Enable CRC forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -213,13 +193,17 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 	priv->crc_fwd_en = 1;
 	reg |= CMD_CRC_FWD;
 
+	/* Can't suspend with WoL if MAC is still in reset */
+	if (reg & CMD_SW_RESET)
+		reg &= ~CMD_SW_RESET;
+
 	/* Receiver must be enabled for WOL MP detection */
 	reg |= CMD_RX_EN;
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
 	reg = UMAC_IRQ_MPD_R;
-	if (hfb_enable)
+	if (hfb_ctrl_reg & RBUF_HFB_EN)
 		reg |=  UMAC_IRQ_HFB_SM | UMAC_IRQ_HFB_MM;
 
 	bcmgenet_intrl2_0_writel(priv, reg, INTRL2_CPU_MASK_CLEAR);
@@ -230,6 +214,7 @@ int bcmgenet_wol_power_down_cfg(struct bcmgenet_priv *priv,
 int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 			      enum bcmgenet_power_mode mode)
 {
+	struct net_device *dev = priv->dev;
 	u32 reg;
 
 	if (mode != GENET_POWER_WOL_MAGIC) {
@@ -242,6 +227,10 @@ int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 
 	bcmgenet_intrl2_0_writel(priv, UMAC_IRQ_WAKE_EVENT,
 				 INTRL2_CPU_MASK_SET);
+	if (bcmgenet_has_mdio_intr(priv))
+		bcmgenet_intrl2_0_writel(priv,
+					 UMAC_IRQ_MDIO_EVENT,
+					 INTRL2_CPU_MASK_CLEAR);
 
 	/* Disable Magic Packet Detection */
 	if (priv->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) {
@@ -252,14 +241,12 @@ int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 		bcmgenet_umac_writel(priv, reg, UMAC_MPD_CTRL);
 	}
 
-	/* Disable WAKE_FILTER Detection */
-	if (priv->wolopts & WAKE_FILTER) {
-		reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
-		if (!(reg & RBUF_ACPI_EN))
-			return -EPERM;	/* already reset so skip the rest */
-		reg &= ~(RBUF_HFB_EN | RBUF_ACPI_EN);
-		bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
-	}
+	/* Disable ACPI mode */
+	reg = bcmgenet_hfb_reg_readl(priv, HFB_CTRL);
+	if (!(reg & RBUF_ACPI_EN))
+		return -EPERM;	/* already reset so skip the rest */
+	reg &= ~RBUF_ACPI_EN;
+	bcmgenet_hfb_reg_writel(priv, reg, HFB_CTRL);
 
 	/* Disable CRC Forward */
 	spin_lock_bh(&priv->reg_lock);
@@ -268,5 +255,13 @@ int bcmgenet_wol_power_up_cfg(struct bcmgenet_priv *priv,
 	bcmgenet_umac_writel(priv, reg, UMAC_CMD);
 	spin_unlock_bh(&priv->reg_lock);
 
+	/* Resume link status tracking */
+	mutex_lock(&dev->phydev->lock);
+	if (dev->phydev->link)
+		dev->phydev->state = PHY_RUNNING;
+	else
+		dev->phydev->state = PHY_NOLINK;
+	mutex_unlock(&dev->phydev->lock);
+
 	return 0;
 }

From dc5340c3133a3ebe54853fd299116149e528cfaa Mon Sep 17 00:00:00 2001
From: Joseph Huang <Joseph.Huang@garmin.com>
Date: Thu, 6 Mar 2025 12:23:05 -0500
Subject: [PATCH 1820/2753] net: dsa: mv88e6xxx: Verify after ATU Load ops

ATU Load operations could fail silently if there's not enough space
on the device to hold the new entry. When this happens, the symptom
depends on the unknown flood settings. If unknown multicast flood is
disabled, the multicast packets are dropped when the ATU table is
full. If unknown multicast flood is enabled, the multicast packets
will be flooded to all ports. Either way, IGMP snooping is broken
when the ATU Load operation fails silently.

Do a Read-After-Write verification after each fdb/mdb add operation
to make sure that the operation was really successful, and return
-ENOSPC otherwise.

Fixes: defb05b9b9b4 ("net: dsa: mv88e6xxx: Add support for fdb_add, fdb_del, and fdb_getnext")
Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250306172306.3859214-1-Joseph.Huang@garmin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 59 ++++++++++++++++++++++++++------
 1 file changed, 48 insertions(+), 11 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 68d1e891752b8..5db96ca52505a 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -2208,13 +2208,11 @@ mv88e6xxx_port_vlan_prepare(struct dsa_switch *ds, int port,
 	return err;
 }
 
-static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
-					const unsigned char *addr, u16 vid,
-					u8 state)
+static int mv88e6xxx_port_db_get(struct mv88e6xxx_chip *chip,
+				 const unsigned char *addr, u16 vid,
+				 u16 *fid, struct mv88e6xxx_atu_entry *entry)
 {
-	struct mv88e6xxx_atu_entry entry;
 	struct mv88e6xxx_vtu_entry vlan;
-	u16 fid;
 	int err;
 
 	/* Ports have two private address databases: one for when the port is
@@ -2225,7 +2223,7 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 	 * VLAN ID into the port's database used for VLAN-unaware bridging.
 	 */
 	if (vid == 0) {
-		fid = MV88E6XXX_FID_BRIDGED;
+		*fid = MV88E6XXX_FID_BRIDGED;
 	} else {
 		err = mv88e6xxx_vtu_get(chip, vid, &vlan);
 		if (err)
@@ -2235,14 +2233,39 @@ static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
 		if (!vlan.valid)
 			return -EOPNOTSUPP;
 
-		fid = vlan.fid;
+		*fid = vlan.fid;
 	}
 
-	entry.state = 0;
-	ether_addr_copy(entry.mac, addr);
-	eth_addr_dec(entry.mac);
+	entry->state = 0;
+	ether_addr_copy(entry->mac, addr);
+	eth_addr_dec(entry->mac);
+
+	return mv88e6xxx_g1_atu_getnext(chip, *fid, entry);
+}
+
+static bool mv88e6xxx_port_db_find(struct mv88e6xxx_chip *chip,
+				   const unsigned char *addr, u16 vid)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
 
-	err = mv88e6xxx_g1_atu_getnext(chip, fid, &entry);
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
+	if (err)
+		return false;
+
+	return entry.state && ether_addr_equal(entry.mac, addr);
+}
+
+static int mv88e6xxx_port_db_load_purge(struct mv88e6xxx_chip *chip, int port,
+					const unsigned char *addr, u16 vid,
+					u8 state)
+{
+	struct mv88e6xxx_atu_entry entry;
+	u16 fid;
+	int err;
+
+	err = mv88e6xxx_port_db_get(chip, addr, vid, &fid, &entry);
 	if (err)
 		return err;
 
@@ -2846,6 +2869,13 @@ static int mv88e6xxx_port_fdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, addr, vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;
@@ -6614,6 +6644,13 @@ static int mv88e6xxx_port_mdb_add(struct dsa_switch *ds, int port,
 	mv88e6xxx_reg_lock(chip);
 	err = mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid,
 					   MV88E6XXX_G1_ATU_DATA_STATE_MC_STATIC);
+	if (err)
+		goto out;
+
+	if (!mv88e6xxx_port_db_find(chip, mdb->addr, mdb->vid))
+		err = -ENOSPC;
+
+out:
 	mv88e6xxx_reg_unlock(chip);
 
 	return err;

From c1aacad30614dc1f8e7564c1350d4e7de4dd10b5 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Mar 2025 06:51:48 -0800
Subject: [PATCH 1821/2753] eth: fbnic: link NAPIs to page pools

The lifetime of page pools is tied to NAPI instances,
and they are destroyed before NAPI is deleted.
It's safe to link them up.

Acked-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250306145150.1757263-2-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index aba4c65974eea..2d2d41c6891b6 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -1316,7 +1316,9 @@ static int fbnic_alloc_nv_page_pool(struct fbnic_net *fbn,
 		.dev = nv->dev,
 		.dma_dir = DMA_BIDIRECTIONAL,
 		.offset = 0,
-		.max_len = PAGE_SIZE
+		.max_len = PAGE_SIZE,
+		.napi	= &nv->napi,
+		.netdev	= fbn->netdev,
 	};
 	struct page_pool *pp;
 

From bfb522f347df2d1fefc43f7b42e361321bc010d9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Mar 2025 06:51:49 -0800
Subject: [PATCH 1822/2753] eth: fbnic: fix typo in compile assert

We should be validating the Rx count on the Rx struct,
not the Tx struct. There is no real change here, rx_stats
and tx_stats are instances of the same struct.

Acked-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250306145150.1757263-3-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
index 2d2d41c6891b6..ac11389a764ce 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.c
@@ -1221,7 +1221,7 @@ void fbnic_aggregate_ring_rx_counters(struct fbnic_net *fbn,
 	fbn->rx_stats.rx.csum_complete += stats->rx.csum_complete;
 	fbn->rx_stats.rx.csum_none += stats->rx.csum_none;
 	/* Remember to add new stats here */
-	BUILD_BUG_ON(sizeof(fbn->tx_stats.rx) / 8 != 3);
+	BUILD_BUG_ON(sizeof(fbn->rx_stats.rx) / 8 != 3);
 }
 
 void fbnic_aggregate_ring_tx_counters(struct fbnic_net *fbn,

From 6cbf18a05c06090d867ef417a2a30b214d42d171 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Mar 2025 06:51:50 -0800
Subject: [PATCH 1823/2753] eth: fbnic: support ring size configuration

Support ethtool -g / -G. Leverage the code added for -l / -L
to alloc / stop / start / free.

Check parameters against HW min/max but also our own min/max.
Min HW queue is 16 entries, we can't deal with TWQs that small
because of the queue waking logic. Add similar contraint on RCQ
for symmetry.

We need 3 sizes on Rx, as the NIC does header-data split two separate
buffer pools:
  (1) head page ring    - how many empty pages we post for headers
  (2) payload page ring - how many empty pages we post for payloads
  (3) completion ring   - where NIC produces the Rx descriptors

Acked-by: Joe Damato <jdamato@fastly.com>
Link: https://patch.msgid.link/20250306145150.1757263-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../net/ethernet/meta/fbnic/fbnic_ethtool.c   | 109 ++++++++++++++++++
 drivers/net/ethernet/meta/fbnic/fbnic_txrx.h  |  13 +++
 2 files changed, 122 insertions(+)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
index c1477aad98a00..0a751a2aaf733 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_ethtool.c
@@ -191,6 +191,113 @@ static int fbnic_set_coalesce(struct net_device *netdev,
 	return 0;
 }
 
+static void
+fbnic_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+
+	ring->rx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_mini_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->rx_jumbo_max_pending = FBNIC_QUEUE_SIZE_MAX;
+	ring->tx_max_pending = FBNIC_QUEUE_SIZE_MAX;
+
+	ring->rx_pending = fbn->rcq_size;
+	ring->rx_mini_pending = fbn->hpq_size;
+	ring->rx_jumbo_pending = fbn->ppq_size;
+	ring->tx_pending = fbn->txq_size;
+}
+
+static void fbnic_set_rings(struct fbnic_net *fbn,
+			    struct ethtool_ringparam *ring)
+{
+	fbn->rcq_size = ring->rx_pending;
+	fbn->hpq_size = ring->rx_mini_pending;
+	fbn->ppq_size = ring->rx_jumbo_pending;
+	fbn->txq_size = ring->tx_pending;
+}
+
+static int
+fbnic_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring,
+		    struct kernel_ethtool_ringparam *kernel_ring,
+		    struct netlink_ext_ack *extack)
+
+{
+	struct fbnic_net *fbn = netdev_priv(netdev);
+	struct fbnic_net *clone;
+	int err;
+
+	ring->rx_pending	= roundup_pow_of_two(ring->rx_pending);
+	ring->rx_mini_pending	= roundup_pow_of_two(ring->rx_mini_pending);
+	ring->rx_jumbo_pending	= roundup_pow_of_two(ring->rx_jumbo_pending);
+	ring->tx_pending	= roundup_pow_of_two(ring->tx_pending);
+
+	/* These are absolute minimums allowing the device and driver to operate
+	 * but not necessarily guarantee reasonable performance. Settings below
+	 * Rx queue size of 128 and BDQs smaller than 64 are likely suboptimal
+	 * at best.
+	 */
+	if (ring->rx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_RX_DESC_MIN) ||
+	    ring->rx_mini_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->rx_jumbo_pending < FBNIC_QUEUE_SIZE_MIN ||
+	    ring->tx_pending < max(FBNIC_QUEUE_SIZE_MIN, FBNIC_TX_DESC_MIN)) {
+		NL_SET_ERR_MSG_MOD(extack, "requested ring size too small");
+		return -EINVAL;
+	}
+
+	if (!netif_running(netdev)) {
+		fbnic_set_rings(fbn, ring);
+		return 0;
+	}
+
+	clone = fbnic_clone_create(fbn);
+	if (!clone)
+		return -ENOMEM;
+
+	fbnic_set_rings(clone, ring);
+
+	err = fbnic_alloc_napi_vectors(clone);
+	if (err)
+		goto err_free_clone;
+
+	err = fbnic_alloc_resources(clone);
+	if (err)
+		goto err_free_napis;
+
+	fbnic_down_noidle(fbn);
+	err = fbnic_wait_all_queues_idle(fbn->fbd, true);
+	if (err)
+		goto err_start_stack;
+
+	err = fbnic_set_netif_queues(clone);
+	if (err)
+		goto err_start_stack;
+
+	/* Nothing can fail past this point */
+	fbnic_flush(fbn);
+
+	fbnic_clone_swap(fbn, clone);
+
+	fbnic_up(fbn);
+
+	fbnic_free_resources(clone);
+	fbnic_free_napi_vectors(clone);
+	fbnic_clone_free(clone);
+
+	return 0;
+
+err_start_stack:
+	fbnic_flush(fbn);
+	fbnic_up(fbn);
+	fbnic_free_resources(clone);
+err_free_napis:
+	fbnic_free_napi_vectors(clone);
+err_free_clone:
+	fbnic_clone_free(clone);
+	return err;
+}
+
 static void fbnic_get_strings(struct net_device *dev, u32 sset, u8 *data)
 {
 	int i;
@@ -1351,6 +1458,8 @@ static const struct ethtool_ops fbnic_ethtool_ops = {
 	.get_regs		= fbnic_get_regs,
 	.get_coalesce		= fbnic_get_coalesce,
 	.set_coalesce		= fbnic_set_coalesce,
+	.get_ringparam		= fbnic_get_ringparam,
+	.set_ringparam		= fbnic_set_ringparam,
 	.get_strings		= fbnic_get_strings,
 	.get_ethtool_stats	= fbnic_get_ethtool_stats,
 	.get_sset_count		= fbnic_get_sset_count,
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
index 54368dc22328d..f46616af41eac 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_txrx.h
@@ -24,9 +24,22 @@ struct fbnic_net;
 #define FBNIC_TX_DESC_WAKEUP	(FBNIC_MAX_SKB_DESC * 2)
 #define FBNIC_TX_DESC_MIN	roundup_pow_of_two(FBNIC_TX_DESC_WAKEUP)
 
+/* To receive the worst case packet we need:
+ *	1 descriptor for primary metadata
+ *	+ 1 descriptor for optional metadata
+ *	+ 1 descriptor for headers
+ *	+ 4 descriptors for payload
+ */
+#define FBNIC_MAX_RX_PKT_DESC	7
+#define FBNIC_RX_DESC_MIN	roundup_pow_of_two(FBNIC_MAX_RX_PKT_DESC * 2)
+
 #define FBNIC_MAX_TXQS			128u
 #define FBNIC_MAX_RXQS			128u
 
+/* These apply to TWQs, TCQ, RCQ */
+#define FBNIC_QUEUE_SIZE_MIN		16u
+#define FBNIC_QUEUE_SIZE_MAX		SZ_64K
+
 #define FBNIC_TXQ_SIZE_DEFAULT		1024
 #define FBNIC_HPQ_SIZE_DEFAULT		256
 #define FBNIC_PPQ_SIZE_DEFAULT		256

From f5afcb9fbb3984137feb12cb2d2fc6986a8347ac Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 6 Mar 2025 12:29:27 +0100
Subject: [PATCH 1824/2753] tcp: ulp: diag: always print the name if any

Since its introduction in commit 61723b393292 ("tcp: ulp: add functions
to dump ulp-specific information"), the ULP diag info have been exported
only if the requester had CAP_NET_ADMIN.

At least the ULP name can be exported without CAP_NET_ADMIN. This will
already help identifying which layer is being used, e.g. which TCP
connections are in fact MPTCP subflow.

Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250306-net-next-tcp-ulp-diag-net-admin-v1-1-06afdd860fc9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_diag.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index f428ecf9120f2..d8bba37dbffd8 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -83,7 +83,7 @@ static int tcp_diag_put_md5sig(struct sk_buff *skb,
 #endif
 
 static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk,
-			    const struct tcp_ulp_ops *ulp_ops)
+			    const struct tcp_ulp_ops *ulp_ops, bool net_admin)
 {
 	struct nlattr *nest;
 	int err;
@@ -96,7 +96,7 @@ static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk,
 	if (err)
 		goto nla_failure;
 
-	if (ulp_ops->get_info)
+	if (net_admin && ulp_ops->get_info)
 		err = ulp_ops->get_info(sk, skb);
 	if (err)
 		goto nla_failure;
@@ -113,6 +113,7 @@ static int tcp_diag_get_aux(struct sock *sk, bool net_admin,
 			    struct sk_buff *skb)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
+	const struct tcp_ulp_ops *ulp_ops;
 	int err = 0;
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -129,15 +130,13 @@ static int tcp_diag_get_aux(struct sock *sk, bool net_admin,
 	}
 #endif
 
-	if (net_admin) {
-		const struct tcp_ulp_ops *ulp_ops;
-
-		ulp_ops = icsk->icsk_ulp_ops;
-		if (ulp_ops)
-			err = tcp_diag_put_ulp(skb, sk, ulp_ops);
-		if (err)
+	ulp_ops = icsk->icsk_ulp_ops;
+	if (ulp_ops) {
+		err = tcp_diag_put_ulp(skb, sk, ulp_ops, net_admin);
+		if (err < 0)
 			return err;
 	}
+
 	return 0;
 }
 
@@ -164,14 +163,14 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
 	}
 #endif
 
-	if (net_admin && sk_fullsock(sk)) {
+	if (sk_fullsock(sk)) {
 		const struct tcp_ulp_ops *ulp_ops;
 
 		ulp_ops = icsk->icsk_ulp_ops;
 		if (ulp_ops) {
 			size += nla_total_size(0) +
 				nla_total_size(TCP_ULP_NAME_MAX);
-			if (ulp_ops->get_info_size)
+			if (net_admin && ulp_ops->get_info_size)
 				size += ulp_ops->get_info_size(sk);
 		}
 	}

From 0d7336f8f06d4a1a1e2c62624d086561e8490bb7 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 6 Mar 2025 12:29:28 +0100
Subject: [PATCH 1825/2753] tcp: ulp: diag: more info without CAP_NET_ADMIN

When introduced in commit 61723b393292 ("tcp: ulp: add functions to dump
ulp-specific information"), the whole ULP diag info has been exported
only if the requester had CAP_NET_ADMIN.

It looks like not everything is sensitive, and some info can be exported
to all users in order to ease the debugging from the userspace side
without requiring additional capabilities. Each layer should then decide
what can be exposed to everybody. The 'net_admin' boolean is then passed
to the different layers.

On kTLS side, it looks like there is nothing sensitive there: version,
cipher type, tx/rx user config type, plus some flags. So, only some
metadata about the configuration, no cryptographic info like keys, etc.
Then, everything can be exported to all users.

On MPTCP side, that's different. The MPTCP-related sequence numbers per
subflow should certainly not be exposed to everybody. For example, the
DSS mapping and ssn_offset would give all users on the system access to
narrow ranges of values for the subflow TCP sequence numbers and
MPTCP-level DSNs, and then ease packet injection. The TCP diag interface
doesn't expose the TCP sequence numbers for TCP sockets, so best to do
the same here. The rest -- token, IDs, flags -- can be exported to
everybody.

Acked-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250306-net-next-tcp-ulp-diag-net-admin-v1-2-06afdd860fc9@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/tcp.h   |  4 ++--
 net/ipv4/tcp_diag.c |  8 ++++----
 net/mptcp/diag.c    | 42 ++++++++++++++++++++++++++----------------
 net/tls/tls_main.c  |  4 ++--
 4 files changed, 34 insertions(+), 24 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index a9bc959fb102f..7207c52b1fc9c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2598,8 +2598,8 @@ struct tcp_ulp_ops {
 	/* cleanup ulp */
 	void (*release)(struct sock *sk);
 	/* diagnostic */
-	int (*get_info)(struct sock *sk, struct sk_buff *skb);
-	size_t (*get_info_size)(const struct sock *sk);
+	int (*get_info)(struct sock *sk, struct sk_buff *skb, bool net_admin);
+	size_t (*get_info_size)(const struct sock *sk, bool net_admin);
 	/* clone ulp */
 	void (*clone)(const struct request_sock *req, struct sock *newsk,
 		      const gfp_t priority);
diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c
index d8bba37dbffd8..45e174b8cd221 100644
--- a/net/ipv4/tcp_diag.c
+++ b/net/ipv4/tcp_diag.c
@@ -96,8 +96,8 @@ static int tcp_diag_put_ulp(struct sk_buff *skb, struct sock *sk,
 	if (err)
 		goto nla_failure;
 
-	if (net_admin && ulp_ops->get_info)
-		err = ulp_ops->get_info(sk, skb);
+	if (ulp_ops->get_info)
+		err = ulp_ops->get_info(sk, skb, net_admin);
 	if (err)
 		goto nla_failure;
 
@@ -170,8 +170,8 @@ static size_t tcp_diag_get_aux_size(struct sock *sk, bool net_admin)
 		if (ulp_ops) {
 			size += nla_total_size(0) +
 				nla_total_size(TCP_ULP_NAME_MAX);
-			if (net_admin && ulp_ops->get_info_size)
-				size += ulp_ops->get_info_size(sk);
+			if (ulp_ops->get_info_size)
+				size += ulp_ops->get_info_size(sk, net_admin);
 		}
 	}
 	return size;
diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
index 02205f7994d75..70cf9ebce8338 100644
--- a/net/mptcp/diag.c
+++ b/net/mptcp/diag.c
@@ -12,7 +12,7 @@
 #include <net/netlink.h>
 #include "protocol.h"
 
-static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
+static int subflow_get_info(struct sock *sk, struct sk_buff *skb, bool net_admin)
 {
 	struct mptcp_subflow_context *sf;
 	struct nlattr *start;
@@ -56,15 +56,6 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 
 	if (nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_TOKEN_REM, sf->remote_token) ||
 	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_TOKEN_LOC, sf->token) ||
-	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
-			sf->rel_write_seq) ||
-	    nla_put_u64_64bit(skb, MPTCP_SUBFLOW_ATTR_MAP_SEQ, sf->map_seq,
-			      MPTCP_SUBFLOW_ATTR_PAD) ||
-	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
-			sf->map_subflow_seq) ||
-	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_SSN_OFFSET, sf->ssn_offset) ||
-	    nla_put_u16(skb, MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
-			sf->map_data_len) ||
 	    nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) ||
 	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) ||
 	    nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) {
@@ -72,6 +63,21 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 		goto nla_failure;
 	}
 
+	/* Only export seq related counters to user with CAP_NET_ADMIN */
+	if (net_admin &&
+	    (nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ,
+			 sf->rel_write_seq) ||
+	     nla_put_u64_64bit(skb, MPTCP_SUBFLOW_ATTR_MAP_SEQ, sf->map_seq,
+			       MPTCP_SUBFLOW_ATTR_PAD) ||
+	     nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_MAP_SFSEQ,
+			 sf->map_subflow_seq) ||
+	     nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_SSN_OFFSET, sf->ssn_offset) ||
+	     nla_put_u16(skb, MPTCP_SUBFLOW_ATTR_MAP_DATALEN,
+			 sf->map_data_len))) {
+		err = -EMSGSIZE;
+		goto nla_failure;
+	}
+
 	rcu_read_unlock();
 	unlock_sock_fast(sk, slow);
 	nla_nest_end(skb, start);
@@ -84,22 +90,26 @@ static int subflow_get_info(struct sock *sk, struct sk_buff *skb)
 	return err;
 }
 
-static size_t subflow_get_info_size(const struct sock *sk)
+static size_t subflow_get_info_size(const struct sock *sk, bool net_admin)
 {
 	size_t size = 0;
 
 	size += nla_total_size(0) +	/* INET_ULP_INFO_MPTCP */
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_TOKEN_REM */
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_TOKEN_LOC */
-		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
-		nla_total_size_64bit(8) +	/* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
-		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
-		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
-		nla_total_size(2) +	/* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
 		nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_FLAGS */
 		nla_total_size(1) +	/* MPTCP_SUBFLOW_ATTR_ID_REM */
 		nla_total_size(1) +	/* MPTCP_SUBFLOW_ATTR_ID_LOC */
 		0;
+
+	if (net_admin)
+		size += nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
+			nla_total_size_64bit(8) +	/* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
+			nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
+			nla_total_size(4) +	/* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+			nla_total_size(2) +	/* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
+			0;
+
 	return size;
 }
 
diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c
index 99ca4465f7021..cb86b0bf9a53e 100644
--- a/net/tls/tls_main.c
+++ b/net/tls/tls_main.c
@@ -1057,7 +1057,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx)
 	return 0;
 }
 
-static int tls_get_info(struct sock *sk, struct sk_buff *skb)
+static int tls_get_info(struct sock *sk, struct sk_buff *skb, bool net_admin)
 {
 	u16 version, cipher_type;
 	struct tls_context *ctx;
@@ -1115,7 +1115,7 @@ static int tls_get_info(struct sock *sk, struct sk_buff *skb)
 	return err;
 }
 
-static size_t tls_get_info_size(const struct sock *sk)
+static size_t tls_get_info_size(const struct sock *sk, bool net_admin)
 {
 	size_t size = 0;
 

From e368d2a1e8b6f0926e4e76a56b484249905192f5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Thu, 6 Mar 2025 11:52:20 +0100
Subject: [PATCH 1826/2753] net: airoha: Fix dev->dsa_ptr check in
 airoha_get_dsa_tag()

Fix the following warning reported by Smatch static checker in
airoha_get_dsa_tag routine:

drivers/net/ethernet/airoha/airoha_eth.c:1722 airoha_get_dsa_tag()
warn: 'dp' isn't an ERR_PTR

dev->dsa_ptr can't be set to an error pointer, it can just be NULL.
Remove this check since it is already performed in netdev_uses_dsa().

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/netdev/Z8l3E0lGOcrel07C@lore-desk/T/#m54adc113fcdd8c5e6c5f65ffd60d8e8b1d483d90
Fixes: af3cf757d5c9 ("net: airoha: Move DSA tag in DMA descriptor")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306-airoha-flowtable-fixes-v1-1-68d3c1296cdd@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index e4130576ad10b..c0a642568ac11 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -1741,18 +1741,13 @@ static u32 airoha_get_dsa_tag(struct sk_buff *skb, struct net_device *dev)
 {
 #if IS_ENABLED(CONFIG_NET_DSA)
 	struct ethhdr *ehdr;
-	struct dsa_port *dp;
 	u8 xmit_tpid;
 	u16 tag;
 
 	if (!netdev_uses_dsa(dev))
 		return 0;
 
-	dp = dev->dsa_ptr;
-	if (IS_ERR(dp))
-		return 0;
-
-	if (dp->tag_ops->proto != DSA_TAG_PROTO_MTK)
+	if (dev->dsa_ptr->tag_ops->proto != DSA_TAG_PROTO_MTK)
 		return 0;
 
 	if (skb_cow_head(skb, 0))

From 26db9c9ee19c36a97dbb1cfef007a3c189c4c874 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Thu, 6 Mar 2025 18:24:18 +0800
Subject: [PATCH 1827/2753] net: mctp i3c: Copy headers if cloned

Use skb_cow_head() prior to modifying the tx skb. This is necessary
when the skb has been cloned, to avoid modifying other shared clones.

Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Fixes: c8755b29b58e ("mctp i3c: MCTP I3C driver")
Link: https://patch.msgid.link/20250306-matt-i3c-cow-head-v1-1-d5e6a5495227@codeconstruct.com.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mctp/mctp-i3c.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/mctp/mctp-i3c.c b/drivers/net/mctp/mctp-i3c.c
index c1e72253063b5..c678f79aa3561 100644
--- a/drivers/net/mctp/mctp-i3c.c
+++ b/drivers/net/mctp/mctp-i3c.c
@@ -506,10 +506,15 @@ static int mctp_i3c_header_create(struct sk_buff *skb, struct net_device *dev,
 	   const void *saddr, unsigned int len)
 {
 	struct mctp_i3c_internal_hdr *ihdr;
+	int rc;
 
 	if (!daddr || !saddr)
 		return -EINVAL;
 
+	rc = skb_cow_head(skb, sizeof(struct mctp_i3c_internal_hdr));
+	if (rc)
+		return rc;
+
 	skb_push(skb, sizeof(struct mctp_i3c_internal_hdr));
 	skb_reset_mac_header(skb);
 	ihdr = (void *)skb_mac_header(skb);

From 730f8d1c611cf925f1a4645afaa8b1386b05c82d Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Thu, 6 Mar 2025 10:46:36 +0100
Subject: [PATCH 1828/2753] MAINTAINERS: adjust entry in AIROHA ETHERNET DRIVER

Commit fb3dda82fd38 ("net: airoha: Move airoha_eth driver in a dedicated
folder") moves the driver to drivers/net/ethernet/airoha/, but misses to
adjust the AIROHA ETHERNET DRIVER section in MAINTAINERS. Hence,
./scripts/get_maintainer.pl --self-test=patterns complains about a broken
reference.

Adjust the file entry to the dedicated folder for this driver.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250306094636.63709-1-lukas.bulwahn@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index a55771d0c62e5..ffbcd072fb144 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -726,7 +726,7 @@ L:	linux-mediatek@lists.infradead.org (moderated for non-subscribers)
 L:	netdev@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/airoha,en7581-eth.yaml
-F:	drivers/net/ethernet/mediatek/airoha_eth.c
+F:	drivers/net/ethernet/airoha/
 
 AIROHA PCIE PHY DRIVER
 M:	Lorenzo Bianconi <lorenzo@kernel.org>

From e2537326e3b6b1bb18f834ebb80b8453c0018883 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Thu, 6 Mar 2025 10:47:53 +0100
Subject: [PATCH 1829/2753] net: ethernet: Remove accidental duplication in
 Kconfig file

Commit fb3dda82fd38 ("net: airoha: Move airoha_eth driver in a dedicated
folder") accidentally added the line:

  source "drivers/net/ethernet/mellanox/Kconfig"

in drivers/net/ethernet/Kconfig, so that this line is duplicated in that
file.

Remove this accidental duplication.

Fixes: fb3dda82fd38 ("net: airoha: Move airoha_eth driver in a dedicated folder")
Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250306094753.63806-1-lukas.bulwahn@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/Kconfig | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index 7941983d21e9e..f86d4557d8d77 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -21,7 +21,6 @@ source "drivers/net/ethernet/adaptec/Kconfig"
 source "drivers/net/ethernet/aeroflex/Kconfig"
 source "drivers/net/ethernet/agere/Kconfig"
 source "drivers/net/ethernet/airoha/Kconfig"
-source "drivers/net/ethernet/mellanox/Kconfig"
 source "drivers/net/ethernet/alacritech/Kconfig"
 source "drivers/net/ethernet/allwinner/Kconfig"
 source "drivers/net/ethernet/alteon/Kconfig"

From df8ce77ba8b7c012a3edd1ca7368b46831341466 Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Thu, 6 Mar 2025 10:33:20 +0800
Subject: [PATCH 1830/2753] net: mctp i2c: Copy headers if cloned

Use skb_cow_head() prior to modifying the TX SKB. This is necessary
when the SKB has been cloned, to avoid modifying other shared clones.

Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Fixes: f5b8abf9fc3d ("mctp i2c: MCTP I2C binding driver")
Link: https://patch.msgid.link/20250306-matt-mctp-i2c-cow-v1-1-293827212681@codeconstruct.com.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mctp/mctp-i2c.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/mctp/mctp-i2c.c b/drivers/net/mctp/mctp-i2c.c
index e3dcdeacc12c5..d74d47dd6e04d 100644
--- a/drivers/net/mctp/mctp-i2c.c
+++ b/drivers/net/mctp/mctp-i2c.c
@@ -583,6 +583,7 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	struct mctp_i2c_hdr *hdr;
 	struct mctp_hdr *mhdr;
 	u8 lldst, llsrc;
+	int rc;
 
 	if (len > MCTP_I2C_MAXMTU)
 		return -EMSGSIZE;
@@ -593,6 +594,10 @@ static int mctp_i2c_header_create(struct sk_buff *skb, struct net_device *dev,
 	lldst = *((u8 *)daddr);
 	llsrc = *((u8 *)saddr);
 
+	rc = skb_cow_head(skb, sizeof(struct mctp_i2c_hdr));
+	if (rc)
+		return rc;
+
 	skb_push(skb, sizeof(struct mctp_i2c_hdr));
 	skb_reset_mac_header(skb);
 	hdr = (void *)skb_mac_header(skb);

From 5d7610577fd9807c604cd43180a64037f35577df Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Tue, 4 Mar 2025 19:37:26 +0100
Subject: [PATCH 1831/2753] net: phy: tja11xx: add support for TJA1102S

NXPs TJA1102S is a single PHY version of the TJA1102 in which one of the
PHYs is disabled.

Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250304-tja1102s-support-v2-1-cd3e61ab920f@liebherr.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-tja11xx.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index ed7fa26bac8e8..9cf5e6d32fab8 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -21,6 +21,7 @@
 #define PHY_ID_TJA1100			0x0180dc40
 #define PHY_ID_TJA1101			0x0180dd00
 #define PHY_ID_TJA1102			0x0180dc80
+#define PHY_ID_TJA1102S			0x0180dc90
 
 #define MII_ECTRL			17
 #define MII_ECTRL_LINK_CONTROL		BIT(15)
@@ -316,6 +317,7 @@ static int tja11xx_config_init(struct phy_device *phydev)
 		if (ret)
 			return ret;
 		break;
+	case PHY_ID_TJA1102S:
 	case PHY_ID_TJA1101:
 		reg_mask = MII_CFG1_INTERFACE_MODE_MASK;
 		ret = tja11xx_get_interface_mode(phydev);
@@ -883,6 +885,29 @@ static struct phy_driver tja11xx_driver[] = {
 		.handle_interrupt = tja11xx_handle_interrupt,
 		.cable_test_start = tja11xx_cable_test_start,
 		.cable_test_get_status = tja11xx_cable_test_get_status,
+	}, {
+		PHY_ID_MATCH_MODEL(PHY_ID_TJA1102S),
+		.name		= "NXP TJA1102S",
+		.features       = PHY_BASIC_T1_FEATURES,
+		.flags          = PHY_POLL_CABLE_TEST,
+		.probe		= tja11xx_probe,
+		.soft_reset	= tja11xx_soft_reset,
+		.config_aneg	= tja11xx_config_aneg,
+		.config_init	= tja11xx_config_init,
+		.read_status	= tja11xx_read_status,
+		.get_sqi	= tja11xx_get_sqi,
+		.get_sqi_max	= tja11xx_get_sqi_max,
+		.suspend	= genphy_suspend,
+		.resume		= genphy_resume,
+		.set_loopback   = genphy_loopback,
+		/* Statistics */
+		.get_sset_count = tja11xx_get_sset_count,
+		.get_strings	= tja11xx_get_strings,
+		.get_stats	= tja11xx_get_stats,
+		.config_intr	= tja11xx_config_intr,
+		.handle_interrupt = tja11xx_handle_interrupt,
+		.cable_test_start = tja11xx_cable_test_start,
+		.cable_test_get_status = tja11xx_cable_test_get_status,
 	}
 };
 
@@ -892,6 +917,7 @@ static const struct mdio_device_id __maybe_unused tja11xx_tbl[] = {
 	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA1100) },
 	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA1101) },
 	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA1102) },
+	{ PHY_ID_MATCH_MODEL(PHY_ID_TJA1102S) },
 	{ }
 };
 

From 5b3178c452c337d24e2dd0e9bb014ed35489ac6c Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Tue, 4 Mar 2025 19:37:27 +0100
Subject: [PATCH 1832/2753] net: phy: tja11xx: enable PHY in sleep mode for
 TJA1102S

Due to pin strapping the PHY maybe disabled per default. TJA1102 devices
can be enabled by setting the PHY_EN bit. Support is provided for TJA1102S
devices but can be easily added for TJA1102 too.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Link: https://patch.msgid.link/20250304-tja1102s-support-v2-2-cd3e61ab920f@liebherr.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-tja11xx.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index 9cf5e6d32fab8..601094fe24ca8 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -28,6 +28,7 @@
 #define MII_ECTRL_POWER_MODE_MASK	GENMASK(14, 11)
 #define MII_ECTRL_POWER_MODE_NO_CHANGE	(0x0 << 11)
 #define MII_ECTRL_POWER_MODE_NORMAL	(0x3 << 11)
+#define MII_ECTRL_POWER_MODE_SLEEP	(0xa << 11)
 #define MII_ECTRL_POWER_MODE_STANDBY	(0xc << 11)
 #define MII_ECTRL_CABLE_TEST		BIT(5)
 #define MII_ECTRL_CONFIG_EN		BIT(2)
@@ -79,6 +80,9 @@
 #define MII_COMMCFG			27
 #define MII_COMMCFG_AUTO_OP		BIT(15)
 
+#define MII_CFG3			28
+#define MII_CFG3_PHY_EN			BIT(0)
+
 /* Configure REF_CLK as input in RMII mode */
 #define TJA110X_RMII_MODE_REFCLK_IN       BIT(0)
 
@@ -180,6 +184,14 @@ static int tja11xx_wakeup(struct phy_device *phydev)
 			return ret;
 
 		return tja11xx_enable_link_control(phydev);
+	case MII_ECTRL_POWER_MODE_SLEEP:
+		switch (phydev->phy_id & PHY_ID_MASK) {
+		case PHY_ID_TJA1102S:
+			/* Enable PHY, maybe it is disabled due to pin strapping */
+			return phy_set_bits(phydev, MII_CFG3, MII_CFG3_PHY_EN);
+		default:
+			return 0;
+		}
 	default:
 		break;
 	}

From a07364b394697d2e0baffeb517f41385259aa484 Mon Sep 17 00:00:00 2001
From: Andrei Botila <andrei.botila@oss.nxp.com>
Date: Tue, 4 Mar 2025 18:06:13 +0200
Subject: [PATCH 1833/2753] net: phy: nxp-c45-tja11xx: add TJA112X PHY
 configuration errata

The most recent sillicon versions of TJA1120 and TJA1121 can achieve
full silicon performance by putting the PHY in managed mode.

It is necessary to apply these PHY writes before link gets established.
Application of this fix is required after restart of device and wakeup
from sleep.

Cc: stable@vger.kernel.org
Fixes: f1fe5dff2b8a ("net: phy: nxp-c45-tja11xx: add TJA1120 support")
Signed-off-by: Andrei Botila <andrei.botila@oss.nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250304160619.181046-2-andrei.botila@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 52 +++++++++++++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 34231b5b91754..709d6c9f7cbae 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -22,6 +22,11 @@
 #define PHY_ID_TJA_1103			0x001BB010
 #define PHY_ID_TJA_1120			0x001BB031
 
+#define VEND1_DEVICE_ID3		0x0004
+#define TJA1120_DEV_ID3_SILICON_VERSION	GENMASK(15, 12)
+#define TJA1120_DEV_ID3_SAMPLE_TYPE	GENMASK(11, 8)
+#define DEVICE_ID3_SAMPLE_TYPE_R	0x9
+
 #define VEND1_DEVICE_CONTROL		0x0040
 #define DEVICE_CONTROL_RESET		BIT(15)
 #define DEVICE_CONTROL_CONFIG_GLOBAL_EN	BIT(14)
@@ -1593,6 +1598,50 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev)
 	return 0;
 }
 
+/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 */
+static void nxp_c45_tja1120_errata(struct phy_device *phydev)
+{
+	int silicon_version, sample_type;
+	bool macsec_ability;
+	int phy_abilities;
+	int ret = 0;
+
+	ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_DEVICE_ID3);
+	if (ret < 0)
+		return;
+
+	sample_type = FIELD_GET(TJA1120_DEV_ID3_SAMPLE_TYPE, ret);
+	if (sample_type != DEVICE_ID3_SAMPLE_TYPE_R)
+		return;
+
+	silicon_version = FIELD_GET(TJA1120_DEV_ID3_SILICON_VERSION, ret);
+
+	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
+				     VEND1_PORT_ABILITIES);
+	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+	if ((!macsec_ability && silicon_version == 2) ||
+	    (macsec_ability && silicon_version == 1)) {
+		/* TJA1120/TJA1121 PHY configuration errata workaround.
+		 * Apply PHY writes sequence before link up.
+		 */
+		if (!macsec_ability) {
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x4b95);
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0xf3cd);
+		} else {
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x89c7);
+			phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0893);
+		}
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x0476, 0x58a0);
+
+		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x8921, 0xa3a);
+		phy_write_mmd(phydev, MDIO_MMD_PMAPMD, 0x89F1, 0x16c1);
+
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0);
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0);
+	}
+}
+
 static int nxp_c45_config_init(struct phy_device *phydev)
 {
 	int ret;
@@ -1609,6 +1658,9 @@ static int nxp_c45_config_init(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 1);
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 2);
 
+	if (phy_id_compare(phydev->phy_id, PHY_ID_TJA_1120, GENMASK(31, 4)))
+		nxp_c45_tja1120_errata(phydev);
+
 	phy_set_bits_mmd(phydev, MDIO_MMD_VEND1, VEND1_PHY_CONFIG,
 			 PHY_CONFIG_AUTO);
 

From 48939523843e4813e78920f54937944a8787134b Mon Sep 17 00:00:00 2001
From: Andrei Botila <andrei.botila@oss.nxp.com>
Date: Tue, 4 Mar 2025 18:06:14 +0200
Subject: [PATCH 1834/2753] net: phy: nxp-c45-tja11xx: add TJA112XB SGMII PCS
 restart errata

TJA1120B/TJA1121B can achieve a stable operation of SGMII after
a startup event by putting the SGMII PCS into power down mode and
restart afterwards.

It is necessary to put the SGMII PCS into power down mode and back up.

Cc: stable@vger.kernel.org
Fixes: f1fe5dff2b8a ("net: phy: nxp-c45-tja11xx: add TJA1120 support")
Signed-off-by: Andrei Botila <andrei.botila@oss.nxp.com>
Link: https://patch.msgid.link/20250304160619.181046-3-andrei.botila@oss.nxp.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/nxp-c45-tja11xx.c | 20 ++++++++++++++++++--
 1 file changed, 18 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/nxp-c45-tja11xx.c b/drivers/net/phy/nxp-c45-tja11xx.c
index 709d6c9f7cbae..e9fc54517449c 100644
--- a/drivers/net/phy/nxp-c45-tja11xx.c
+++ b/drivers/net/phy/nxp-c45-tja11xx.c
@@ -114,6 +114,9 @@
 #define MII_BASIC_CONFIG_RMII		0x5
 #define MII_BASIC_CONFIG_MII		0x4
 
+#define VEND1_SGMII_BASIC_CONTROL	0xB000
+#define SGMII_LPM			BIT(11)
+
 #define VEND1_SYMBOL_ERROR_CNT_XTD	0x8351
 #define EXTENDED_CNT_EN			BIT(15)
 #define VEND1_MONITOR_STATUS		0xAC80
@@ -1598,11 +1601,11 @@ static int nxp_c45_set_phy_mode(struct phy_device *phydev)
 	return 0;
 }
 
-/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 */
+/* Errata: ES_TJA1120 and ES_TJA1121 Rev. 1.0 — 28 November 2024 Section 3.1 & 3.2 */
 static void nxp_c45_tja1120_errata(struct phy_device *phydev)
 {
+	bool macsec_ability, sgmii_ability;
 	int silicon_version, sample_type;
-	bool macsec_ability;
 	int phy_abilities;
 	int ret = 0;
 
@@ -1619,6 +1622,7 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev)
 	phy_abilities = phy_read_mmd(phydev, MDIO_MMD_VEND1,
 				     VEND1_PORT_ABILITIES);
 	macsec_ability = !!(phy_abilities & MACSEC_ABILITY);
+	sgmii_ability = !!(phy_abilities & SGMII_ABILITY);
 	if ((!macsec_ability && silicon_version == 2) ||
 	    (macsec_ability && silicon_version == 1)) {
 		/* TJA1120/TJA1121 PHY configuration errata workaround.
@@ -1639,6 +1643,18 @@ static void nxp_c45_tja1120_errata(struct phy_device *phydev)
 
 		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F8, 0x0);
 		phy_write_mmd(phydev, MDIO_MMD_VEND1, 0x01F9, 0x0);
+
+		if (sgmii_ability) {
+			/* TJA1120B/TJA1121B SGMII PCS restart errata workaround.
+			 * Put SGMII PCS into power down mode and back up.
+			 */
+			phy_set_bits_mmd(phydev, MDIO_MMD_VEND1,
+					 VEND1_SGMII_BASIC_CONTROL,
+					 SGMII_LPM);
+			phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1,
+					   VEND1_SGMII_BASIC_CONTROL,
+					   SGMII_LPM);
+		}
 	}
 }
 

From 248f6571fd4c51531f7f8f07f186f7ae98a50afc Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Tue, 4 Mar 2025 07:50:41 -0800
Subject: [PATCH 1835/2753] netpoll: Optimize skb refilling on critical path

netpoll tries to refill the skb queue on every packet send, independently
if packets are being consumed from the pool or not. This was
particularly problematic while being called from printk(), where the
operation would be done while holding the console lock.

Introduce a more intelligent approach to skb queue management. Instead
of constantly attempting to refill the queue, the system now defers
refilling to a work queue and only triggers the workqueue when a buffer
is actually dequeued. This change significantly reduces operations with
the lock held.

Add a work_struct to the netpoll structure for asynchronous refilling,
updating find_skb() to schedule refill work only when necessary (skb is
dequeued).

These changes have demonstrated a 15% reduction in time spent during
netpoll_send_msg operations, especially when no SKBs are not consumed
from consumed from pool.

When SKBs are being dequeued, the improvement is even better, around
70%, mainly because refilling the SKB pool is now happening outside of
the critical patch (with console_owner lock held).

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250304-netpoll_refill_v2-v1-1-06e2916a4642@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netpoll.h |  1 +
 net/core/netpoll.c      | 15 +++++++++++++--
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index f91e50a76efd4..f6e8abe0b1f19 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -33,6 +33,7 @@ struct netpoll {
 	u16 local_port, remote_port;
 	u8 remote_mac[ETH_ALEN];
 	struct sk_buff_head skb_pool;
+	struct work_struct refill_wq;
 };
 
 struct netpoll_info {
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 62b4041aae1ae..8a0df2b274a88 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -284,12 +284,13 @@ static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
 	struct sk_buff *skb;
 
 	zap_completion_queue();
-	refill_skbs(np);
 repeat:
 
 	skb = alloc_skb(len, GFP_ATOMIC);
-	if (!skb)
+	if (!skb) {
 		skb = skb_dequeue(&np->skb_pool);
+		schedule_work(&np->refill_wq);
+	}
 
 	if (!skb) {
 		if (++count < 10) {
@@ -535,6 +536,7 @@ static void skb_pool_flush(struct netpoll *np)
 {
 	struct sk_buff_head *skb_pool;
 
+	cancel_work_sync(&np->refill_wq);
 	skb_pool = &np->skb_pool;
 	skb_queue_purge_reason(skb_pool, SKB_CONSUMED);
 }
@@ -621,6 +623,14 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 }
 EXPORT_SYMBOL(netpoll_parse_options);
 
+static void refill_skbs_work_handler(struct work_struct *work)
+{
+	struct netpoll *np =
+		container_of(work, struct netpoll, refill_wq);
+
+	refill_skbs(np);
+}
+
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 {
 	struct netpoll_info *npinfo;
@@ -666,6 +676,7 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 
 	/* fill up the skb queue */
 	refill_skbs(np);
+	INIT_WORK(&np->refill_wq, refill_skbs_work_handler);
 
 	/* last thing to do is link it to the net device structure */
 	rcu_assign_pointer(ndev->npinfo, npinfo);

From 505ead7ab77f289f12d8a68ac83da068e4d4408b Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Thu, 6 Mar 2025 05:16:18 -0800
Subject: [PATCH 1836/2753] netpoll: hold rcu read lock in __netpoll_send_skb()

The function __netpoll_send_skb() is being invoked without holding the
RCU read lock. This oversight triggers a warning message when
CONFIG_PROVE_RCU_LIST is enabled:

	net/core/netpoll.c:330 suspicious rcu_dereference_check() usage!

	 netpoll_send_skb
	 netpoll_send_udp
	 write_ext_msg
	 console_flush_all
	 console_unlock
	 vprintk_emit

To prevent npinfo from disappearing unexpectedly, ensure that
__netpoll_send_skb() is protected with the RCU read lock.

Fixes: 2899656b494dcd1 ("netpoll: take rcu_read_lock_bh() in netpoll_send_skb_on_dev()")
Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306-netpoll_rcu_v2-v2-1-bc4f5c51742a@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netpoll.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 62b4041aae1ae..0ab722d95a2df 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -319,6 +319,7 @@ static int netpoll_owner_active(struct net_device *dev)
 static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 {
 	netdev_tx_t status = NETDEV_TX_BUSY;
+	netdev_tx_t ret = NET_XMIT_DROP;
 	struct net_device *dev;
 	unsigned long tries;
 	/* It is up to the caller to keep npinfo alive. */
@@ -327,11 +328,12 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 	lockdep_assert_irqs_disabled();
 
 	dev = np->dev;
+	rcu_read_lock();
 	npinfo = rcu_dereference_bh(dev->npinfo);
 
 	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
 		dev_kfree_skb_irq(skb);
-		return NET_XMIT_DROP;
+		goto out;
 	}
 
 	/* don't get messages out of order, and no recursion */
@@ -370,7 +372,10 @@ static netdev_tx_t __netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 		skb_queue_tail(&npinfo->txq, skb);
 		schedule_delayed_work(&npinfo->tx_work,0);
 	}
-	return NETDEV_TX_OK;
+	ret = NETDEV_TX_OK;
+out:
+	rcu_read_unlock();
+	return ret;
 }
 
 netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)

From da64a2359092ceec4f9dea5b329d0aef20104217 Mon Sep 17 00:00:00 2001
From: Tiezhu Yang <yangtiezhu@loongson.cn>
Date: Sat, 8 Mar 2025 13:50:45 +0800
Subject: [PATCH 1837/2753] LoongArch: Convert unreachable() to BUG()

When compiling on LoongArch, there exists the following objtool warning
in arch/loongarch/kernel/machine_kexec.o:

  kexec_reboot() falls through to next function crash_shutdown_secondary()

Avoid using unreachable() as it can (and will in the absence of UBSAN)
generate fall-through code. Use BUG() so we get a "break BRK_BUG" trap
(with unreachable annotation).

Cc: stable@vger.kernel.org  # 6.12+
Acked-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Tiezhu Yang <yangtiezhu@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/machine_kexec.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/loongarch/kernel/machine_kexec.c b/arch/loongarch/kernel/machine_kexec.c
index 8ae641dc53bb7..f9381800e291c 100644
--- a/arch/loongarch/kernel/machine_kexec.c
+++ b/arch/loongarch/kernel/machine_kexec.c
@@ -126,14 +126,14 @@ void kexec_reboot(void)
 	/* All secondary cpus go to kexec_smp_wait */
 	if (smp_processor_id() > 0) {
 		relocated_kexec_smp_wait(NULL);
-		unreachable();
+		BUG();
 	}
 #endif
 
 	do_kexec = (void *)reboot_code_buffer;
 	do_kexec(efi_boot, cmdline_ptr, systable_ptr, start_addr, first_ind_entry);
 
-	unreachable();
+	BUG();
 }
 
 

From a0d3c8bcb9206ac207c7ad3182027c6b0a1319bb Mon Sep 17 00:00:00 2001
From: Yuli Wang <wangyuli@uniontech.com>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1838/2753] LoongArch: Eliminate superfluous
 get_numa_distances_cnt()

In LoongArch, get_numa_distances_cnt() isn't in use, resulting in a
compiler warning.

Fix follow errors with clang-18 when W=1e:

arch/loongarch/kernel/acpi.c:259:28: error: unused function 'get_numa_distances_cnt' [-Werror,-Wunused-function]
  259 | static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
      |                            ^~~~~~~~~~~~~~~~~~~~~~
1 error generated.

Link: https://lore.kernel.org/all/Z7bHPVUH4lAezk0E@kernel.org/
Signed-off-by: Yuli Wang <wangyuli@uniontech.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/acpi.c | 12 ------------
 1 file changed, 12 deletions(-)

diff --git a/arch/loongarch/kernel/acpi.c b/arch/loongarch/kernel/acpi.c
index 382a09a7152c3..1120ac2824f6e 100644
--- a/arch/loongarch/kernel/acpi.c
+++ b/arch/loongarch/kernel/acpi.c
@@ -249,18 +249,6 @@ static __init int setup_node(int pxm)
 	return acpi_map_pxm_to_node(pxm);
 }
 
-/*
- * Callback for SLIT parsing.  pxm_to_node() returns NUMA_NO_NODE for
- * I/O localities since SRAT does not list them.  I/O localities are
- * not supported at this point.
- */
-unsigned int numa_distance_cnt;
-
-static inline unsigned int get_numa_distances_cnt(struct acpi_table_slit *slit)
-{
-	return slit->locality_count;
-}
-
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if ((u8)distance != distance || (from == to && distance != LOCAL_DISTANCE)) {

From c9117434c8f7523f0b77db4c5766f5011cc94677 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1839/2753] LoongArch: Use polling play_dead() when resuming
 from hibernation

When CONFIG_RANDOM_KMALLOC_CACHES or other randomization infrastructrue
enabled, the idle_task's stack may different between the booting kernel
and target kernel. So when resuming from hibernation, an ACTION_BOOT_CPU
IPI wakeup the idle instruction in arch_cpu_idle_dead() and jump to the
interrupt handler. But since the stack pointer is changed, the interrupt
handler cannot restore correct context.

So rename the current arch_cpu_idle_dead() to idle_play_dead(), make it
as the default version of play_dead(), and the new arch_cpu_idle_dead()
call play_dead() directly. For hibernation, implement an arch-specific
hibernate_resume_nonboot_cpu_disable() to use the polling version (idle
instruction is replace by nop, and irq is disabled) of play_dead(), i.e.
poll_play_dead(), to avoid IPI handler corrupting the idle_task's stack
when resuming from hibernation.

This solution is a little similar to commit 406f992e4a372dafbe3c ("x86 /
hibernate: Use hlt_play_dead() when resuming from hibernation").

Cc: stable@vger.kernel.org
Tested-by: Erpeng Xu <xuerpeng@uniontech.com>
Tested-by: Yuli Wang <wangyuli@uniontech.com>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/smp.c | 47 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 46 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kernel/smp.c b/arch/loongarch/kernel/smp.c
index fbf747447f13f..4b24589c0b565 100644
--- a/arch/loongarch/kernel/smp.c
+++ b/arch/loongarch/kernel/smp.c
@@ -19,6 +19,7 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/export.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/time.h>
 #include <linux/tracepoint.h>
@@ -423,7 +424,7 @@ void loongson_cpu_die(unsigned int cpu)
 	mb();
 }
 
-void __noreturn arch_cpu_idle_dead(void)
+static void __noreturn idle_play_dead(void)
 {
 	register uint64_t addr;
 	register void (*init_fn)(void);
@@ -447,6 +448,50 @@ void __noreturn arch_cpu_idle_dead(void)
 	BUG();
 }
 
+#ifdef CONFIG_HIBERNATION
+static void __noreturn poll_play_dead(void)
+{
+	register uint64_t addr;
+	register void (*init_fn)(void);
+
+	idle_task_exit();
+	__this_cpu_write(cpu_state, CPU_DEAD);
+
+	__smp_mb();
+	do {
+		__asm__ __volatile__("nop\n\t");
+		addr = iocsr_read64(LOONGARCH_IOCSR_MBUF0);
+	} while (addr == 0);
+
+	init_fn = (void *)TO_CACHE(addr);
+	iocsr_write32(0xffffffff, LOONGARCH_IOCSR_IPI_CLEAR);
+
+	init_fn();
+	BUG();
+}
+#endif
+
+static void (*play_dead)(void) = idle_play_dead;
+
+void __noreturn arch_cpu_idle_dead(void)
+{
+	play_dead();
+	BUG(); /* play_dead() doesn't return */
+}
+
+#ifdef CONFIG_HIBERNATION
+int hibernate_resume_nonboot_cpu_disable(void)
+{
+	int ret;
+
+	play_dead = poll_play_dead;
+	ret = suspend_disable_secondary_cpus();
+	play_dead = idle_play_dead;
+
+	return ret;
+}
+#endif
+
 #endif
 
 /*

From c8477bb0a8e7f6b2e47952b403c5cb67a6929e55 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1840/2753] LoongArch: Set max_pfn with the PFN of the last
 page

The current max_pfn equals to zero. In this case, it causes user cannot
get some page information through /proc filesystem such as kpagecount.
The following message is displayed by stress-ng test suite with command
"stress-ng --verbose --physpage 1 -t 1".

 # stress-ng --verbose --physpage 1 -t 1
 stress-ng: error: [1691] physpage: cannot read page count for address 0x134ac000 in /proc/kpagecount, errno=22 (Invalid argument)
 stress-ng: error: [1691] physpage: cannot read page count for address 0x7ffff207c3a8 in /proc/kpagecount, errno=22 (Invalid argument)
 stress-ng: error: [1691] physpage: cannot read page count for address 0x134b0000 in /proc/kpagecount, errno=22 (Invalid argument)
 ...

After applying this patch, the kernel can pass the test.

 # stress-ng --verbose --physpage 1 -t 1
 stress-ng: debug: [1701] physpage: [1701] started (instance 0 on CPU 3)
 stress-ng: debug: [1701] physpage: [1701] exited (instance 0 on CPU 3)
 stress-ng: debug: [1700] physpage: [1701] terminated (success)

Cc: stable@vger.kernel.org  # 6.8+
Fixes: ff6c3d81f2e8 ("NUMA: optimize detection of memory with no node id assigned by firmware")
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kernel/setup.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index edcfdfcad7d22..90cb3ca96f085 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -387,6 +387,9 @@ static void __init check_kernel_sections_mem(void)
  */
 static void __init arch_mem_init(char **cmdline_p)
 {
+	/* Recalculate max_low_pfn for "mem=xxx" */
+	max_pfn = max_low_pfn = PHYS_PFN(memblock_end_of_DRAM());
+
 	if (usermem)
 		pr_info("User-defined physical RAM map overwrite\n");
 

From 3109d5ff484b7bc7b955f166974c6776d91f247b Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:32 +0800
Subject: [PATCH 1841/2753] LoongArch: Set hugetlb mmap base address aligned
 with pmd size

With ltp test case "testcases/bin/hugefork02", there is a dmesg error
report message such as:

 kernel BUG at mm/hugetlb.c:5550!
 Oops - BUG[#1]:
 CPU: 0 UID: 0 PID: 1517 Comm: hugefork02 Not tainted 6.14.0-rc2+ #241
 Hardware name: QEMU QEMU Virtual Machine, BIOS unknown 2/2/2022
 pc 90000000004eaf1c ra 9000000000485538 tp 900000010edbc000 sp 900000010edbf940
 a0 900000010edbfb00 a1 9000000108d20280 a2 00007fffe9474000 a3 00007ffff3474000
 a4 0000000000000000 a5 0000000000000003 a6 00000000003cadd3 a7 0000000000000000
 t0 0000000001ffffff t1 0000000001474000 t2 900000010ecd7900 t3 00007fffe9474000
 t4 00007fffe9474000 t5 0000000000000040 t6 900000010edbfb00 t7 0000000000000001
 t8 0000000000000005 u0 90000000004849d0 s9 900000010edbfa00 s0 9000000108d20280
 s1 00007fffe9474000 s2 0000000002000000 s3 9000000108d20280 s4 9000000002b38b10
 s5 900000010edbfb00 s6 00007ffff3474000 s7 0000000000000406 s8 900000010edbfa08
    ra: 9000000000485538 unmap_vmas+0x130/0x218
   ERA: 90000000004eaf1c __unmap_hugepage_range+0x6f4/0x7d0
  PRMD: 00000004 (PPLV0 +PIE -PWE)
  EUEN: 00000007 (+FPE +SXE +ASXE -BTE)
  ECFG: 00071c1d (LIE=0,2-4,10-12 VS=7)
 ESTAT: 000c0000 [BRK] (IS= ECode=12 EsubCode=0)
 PRID: 0014c010 (Loongson-64bit, Loongson-3A5000)
 Process hugefork02 (pid: 1517, threadinfo=00000000a670eaf4, task=000000007a95fc64)
 Call Trace:
 [<90000000004eaf1c>] __unmap_hugepage_range+0x6f4/0x7d0
 [<9000000000485534>] unmap_vmas+0x12c/0x218
 [<9000000000494068>] exit_mmap+0xe0/0x308
 [<900000000025fdc4>] mmput+0x74/0x180
 [<900000000026a284>] do_exit+0x294/0x898
 [<900000000026aa30>] do_group_exit+0x30/0x98
 [<900000000027bed4>] get_signal+0x83c/0x868
 [<90000000002457b4>] arch_do_signal_or_restart+0x54/0xfa0
 [<90000000015795e8>] irqentry_exit_to_user_mode+0xb8/0x138
 [<90000000002572d0>] tlb_do_page_fault_1+0x114/0x1b4

The problem is that base address allocated from hugetlbfs is not aligned
with pmd size. Here add a checking for hugetlbfs and align base address
with pmd size. After this patch the test case "testcases/bin/hugefork02"
passes to run.

This is similar to the commit 7f24cbc9c4d42db8a3c8484d1 ("mm/mmap: teach
generic_get_unmapped_area{_topdown} to handle hugetlb mappings").

Cc: stable@vger.kernel.org  # 6.13+
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/mm/mmap.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/mm/mmap.c b/arch/loongarch/mm/mmap.c
index 914e82ff3f656..1df9e99582cc6 100644
--- a/arch/loongarch/mm/mmap.c
+++ b/arch/loongarch/mm/mmap.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
  */
 #include <linux/export.h>
+#include <linux/hugetlb.h>
 #include <linux/io.h>
 #include <linux/kfence.h>
 #include <linux/memblock.h>
@@ -63,8 +64,11 @@ static unsigned long arch_get_unmapped_area_common(struct file *filp,
 	}
 
 	info.length = len;
-	info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 	info.align_offset = pgoff << PAGE_SHIFT;
+	if (filp && is_file_hugepages(filp))
+		info.align_mask = huge_page_mask_align(filp);
+	else
+		info.align_mask = do_color_align ? (PAGE_MASK & SHM_ALIGN_MASK) : 0;
 
 	if (dir == DOWN) {
 		info.flags = VM_UNMAPPED_AREA_TOPDOWN;

From 6fb1867d5a44b0a061cf39d2492d23d314bcb8ce Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:51:59 +0800
Subject: [PATCH 1842/2753] LoongArch: KVM: Add interrupt checking for AVEC

There is a newly added macro INT_AVEC with CSR ESTAT register, which is
bit 14 used for LoongArch AVEC support. AVEC interrupt status bit 14 is
supported with macro CSR_ESTAT_IS, so here replace the hard-coded value
0x1fff with macro CSR_ESTAT_IS so that the AVEC interrupt status is also
supported by KVM.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/vcpu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 20f941af3e9ea..9e1a9b4aa4c6a 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -311,7 +311,7 @@ static int kvm_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int ret = RESUME_GUEST;
 	unsigned long estat = vcpu->arch.host_estat;
-	u32 intr = estat & 0x1fff; /* Ignore NMI */
+	u32 intr = estat & CSR_ESTAT_IS;
 	u32 ecode = (estat & CSR_ESTAT_EXC) >> CSR_ESTAT_EXC_SHIFT;
 
 	vcpu->mode = OUTSIDE_GUEST_MODE;

From 78d7bc5a02e1468df53896df354fa80727f35b7d Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:52:01 +0800
Subject: [PATCH 1843/2753] LoongArch: KVM: Reload guest CSR registers after
 sleep

On host, the HW guest CSR registers are lost after suspend and resume
operation. Since last_vcpu of boot CPU still records latest vCPU pointer
so that the guest CSR register skips to reload when boot CPU resumes and
vCPU is scheduled.

Here last_vcpu is cleared so that guest CSR registers will reload from
scheduled vCPU context after suspend and resume.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/main.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/arch/loongarch/kvm/main.c b/arch/loongarch/kvm/main.c
index f6d3242b9234a..b6864d6e5ec8d 100644
--- a/arch/loongarch/kvm/main.c
+++ b/arch/loongarch/kvm/main.c
@@ -317,6 +317,13 @@ int kvm_arch_enable_virtualization_cpu(void)
 	kvm_debug("GCFG:%lx GSTAT:%lx GINTC:%lx GTLBC:%lx",
 		  read_csr_gcfg(), read_csr_gstat(), read_csr_gintc(), read_csr_gtlbc());
 
+	/*
+	 * HW Guest CSR registers are lost after CPU suspend and resume.
+	 * Clear last_vcpu so that Guest CSR registers forced to reload
+	 * from vCPU SW state.
+	 */
+	this_cpu_ptr(vmcs)->last_vcpu = NULL;
+
 	return 0;
 }
 

From 6bdbb73dc8d99fbb77f5db79dbb6f108708090b4 Mon Sep 17 00:00:00 2001
From: Bibo Mao <maobibo@loongson.cn>
Date: Sat, 8 Mar 2025 13:52:04 +0800
Subject: [PATCH 1844/2753] LoongArch: KVM: Fix GPA size issue about VM

Physical address space is 48 bit on Loongson-3A5000 physical machine,
however it is 47 bit for VM on Loongson-3A5000 system. Size of physical
address space of VM is the same with the size of virtual user space (a
half) of physical machine.

Variable cpu_vabits represents user address space, kernel address space
is not included (user space and kernel space are both a half of total).
Here cpu_vabits, rather than cpu_vabits - 1, is to represent the size of
guest physical address space.

Also there is strict checking about page fault GPA address, inject error
if it is larger than maximum GPA address of VM.

Cc: stable@vger.kernel.org
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
---
 arch/loongarch/kvm/exit.c | 6 ++++++
 arch/loongarch/kvm/vm.c   | 6 +++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/arch/loongarch/kvm/exit.c b/arch/loongarch/kvm/exit.c
index c1e8ec5b941b2..ea321403644ad 100644
--- a/arch/loongarch/kvm/exit.c
+++ b/arch/loongarch/kvm/exit.c
@@ -669,6 +669,12 @@ static int kvm_handle_rdwr_fault(struct kvm_vcpu *vcpu, bool write)
 	struct kvm_run *run = vcpu->run;
 	unsigned long badv = vcpu->arch.badv;
 
+	/* Inject ADE exception if exceed max GPA size */
+	if (unlikely(badv >= vcpu->kvm->arch.gpa_size)) {
+		kvm_queue_exception(vcpu, EXCCODE_ADE, EXSUBCODE_ADEM);
+		return RESUME_GUEST;
+	}
+
 	ret = kvm_handle_mm_fault(vcpu, badv, write);
 	if (ret) {
 		/* Treat as MMIO */
diff --git a/arch/loongarch/kvm/vm.c b/arch/loongarch/kvm/vm.c
index b8b3e1972d6ea..edccfc8c9cd80 100644
--- a/arch/loongarch/kvm/vm.c
+++ b/arch/loongarch/kvm/vm.c
@@ -48,7 +48,11 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (kvm_pvtime_supported())
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
 
-	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
+	/*
+	 * cpu_vabits means user address space only (a half of total).
+	 * GPA size of VM is the same with the size of user address space.
+	 */
+	kvm->arch.gpa_size = BIT(cpu_vabits);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
 	kvm->arch.invalid_ptes[1] = (unsigned long)invalid_pte_table;

From c24f272ae751a9f54f8816430e7f2d56031892cc Mon Sep 17 00:00:00 2001
From: Phil Elwell <phil@raspberrypi.com>
Date: Sat, 22 Feb 2025 10:41:13 +0100
Subject: [PATCH 1845/2753] ARM: dts: bcm2711: Don't mark timer regs
 unconfigured

During upstream process of Raspberry Pi 4 back in 2019 the ARMv7 stubs
didn't configured the ARM architectural timer. This firmware issue has
been fixed in 2020, which gave users enough time to update their system.

So drop this property to allow the use of the vDSO version of
clock_gettime.

Link: https://github.com/raspberrypi/tools/pull/113
Fixes: 7dbe8c62ceeb ("ARM: dts: Add minimal Raspberry Pi 4 support")
Signed-off-by: Phil Elwell <phil@raspberrypi.com>
Signed-off-by: Stefan Wahren <wahrenst@gmx.net>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/r/20250222094113.48198-1-wahrenst@gmx.net
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm/boot/dts/broadcom/bcm2711.dtsi | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/arm/boot/dts/broadcom/bcm2711.dtsi b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
index e4e42af21ef3a..7cf93fdc676cb 100644
--- a/arch/arm/boot/dts/broadcom/bcm2711.dtsi
+++ b/arch/arm/boot/dts/broadcom/bcm2711.dtsi
@@ -451,8 +451,6 @@
 					  IRQ_TYPE_LEVEL_LOW)>,
 			     <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(4) |
 					  IRQ_TYPE_LEVEL_LOW)>;
-		/* This only applies to the ARMv7 stub */
-		arm,cpu-registers-not-fw-configured;
 	};
 
 	cpus: cpus {

From 56e12d0c8d395b6e48f128858d4f725c1ded6c95 Mon Sep 17 00:00:00 2001
From: "Chester A. Unal" <chester.a.unal@arinc9.com>
Date: Mon, 3 Mar 2025 13:06:50 +0000
Subject: [PATCH 1846/2753] ARM: dts: BCM5301X: Fix switch port labels of ASUS
 RT-AC5300

After using the device for a while, Tom reports that he initially described
the switch port labels incorrectly. Correct them.

Reported-by: Tom Brautaset <tbrautaset@gmail.com>
Fixes: 961dedc6b4e4 ("ARM: dts: BCM5301X: Add DT for ASUS RT-AC5300")
Signed-off-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://lore.kernel.org/r/20250303-for-broadcom-fix-rt-ac5300-switch-ports-v1-1-e058856ef4d3@arinc9.com
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts b/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
index 6c666dc7ad23e..01ec8c03686a6 100644
--- a/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
+++ b/arch/arm/boot/dts/broadcom/bcm47094-asus-rt-ac5300.dts
@@ -126,11 +126,11 @@
 
 	ports {
 		port@0 {
-			label = "lan4";
+			label = "wan";
 		};
 
 		port@1 {
-			label = "lan3";
+			label = "lan1";
 		};
 
 		port@2 {
@@ -138,11 +138,11 @@
 		};
 
 		port@3 {
-			label = "lan1";
+			label = "lan3";
 		};
 
 		port@4 {
-			label = "wan";
+			label = "lan4";
 		};
 	};
 };

From 24d4c56dd68906bf55ff8fc2e2d36760f97dce5f Mon Sep 17 00:00:00 2001
From: "Chester A. Unal" <chester.a.unal@arinc9.com>
Date: Tue, 4 Mar 2025 15:55:36 +0000
Subject: [PATCH 1847/2753] ARM: dts: BCM5301X: Fix switch port labels of ASUS
 RT-AC3200

After using the device for a while, Tom reports that he initially described
the switch port labels incorrectly. Apparently, ASUS's own firmware also
describes them incorrectly. Correct them to what is seen on the chassis.

Reported-by: Tom Brautaset <tbrautaset@gmail.com>
Fixes: b116239094d8 ("ARM: dts: BCM5301X: Add DT for ASUS RT-AC3200")
Signed-off-by: Chester A. Unal <chester.a.unal@arinc9.com>
Link: https://lore.kernel.org/r/20250304-for-broadcom-fix-rt-ac3200-switch-ports-v1-1-7e249a19a13e@arinc9.com
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts b/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
index 53cb0c58f6d05..3da2daee0c849 100644
--- a/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
+++ b/arch/arm/boot/dts/broadcom/bcm4709-asus-rt-ac3200.dts
@@ -124,19 +124,19 @@
 		};
 
 		port@1 {
-			label = "lan1";
+			label = "lan4";
 		};
 
 		port@2 {
-			label = "lan2";
+			label = "lan3";
 		};
 
 		port@3 {
-			label = "lan3";
+			label = "lan2";
 		};
 
 		port@4 {
-			label = "lan4";
+			label = "lan1";
 		};
 	};
 };

From 0704a15b930cf97073ce091a0cd7ad32f2304329 Mon Sep 17 00:00:00 2001
From: Thomas Mizrahi <thomasmizra@gmail.com>
Date: Sat, 8 Mar 2025 01:06:28 -0300
Subject: [PATCH 1848/2753] ASoC: amd: yc: Support mic on another Lenovo
 ThinkPad E16 Gen 2 model

The internal microphone on the Lenovo ThinkPad E16 model requires a
quirk entry to work properly. This was fixed in a previous patch (linked
below), but depending on the specific variant of the model, the product
name may be "21M5" or "21M6".

The following patch fixed this issue for the 21M5 variant:
  https://lore.kernel.org/all/20240725065442.9293-1-tiwai@suse.de/

This patch adds support for the microphone on the 21M6 variant.

Link: https://github.com/ramaureirac/thinkpad-e14-linux/issues/31
Cc: stable@vger.kernel.org
Signed-off-by: Thomas Mizrahi <thomasmizra@gmail.com>
Link: https://patch.msgid.link/20250308041303.198765-1-thomasmizra@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/amd/yc/acp6x-mach.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
index b16587d8f97a8..a7637056972aa 100644
--- a/sound/soc/amd/yc/acp6x-mach.c
+++ b/sound/soc/amd/yc/acp6x-mach.c
@@ -248,6 +248,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "21M5"),
 		}
 	},
+	{
+		.driver_data = &acp6x_card,
+		.matches = {
+			DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "21M6"),
+		}
+	},
 	{
 		.driver_data = &acp6x_card,
 		.matches = {

From b3aaf3c13baab4c6f024f0852ae970c75ca3b98f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Mar 2025 10:20:02 +0000
Subject: [PATCH 1849/2753] udp: expand SKB_DROP_REASON_UDP_CSUM use

SKB_DROP_REASON_UDP_CSUM can be used in four locations
when dropping a packet because of a wrong UDP checksum.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250307102002.2095238-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp.c | 6 +++---
 net/ipv6/udp.c | 2 +-
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 17c7736d83494..d0bffcfa56d8d 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1848,7 +1848,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk,
 			atomic_inc(&sk->sk_drops);
 			__skb_unlink(skb, rcvq);
 			*total += skb->truesize;
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
 		} else {
 			udp_skb_csum_unnecessary_set(skb);
 			break;
@@ -2002,7 +2002,7 @@ int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 		__UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite);
 		__UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite);
 		atomic_inc(&sk->sk_drops);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
 		goto try_again;
 	}
 
@@ -2117,7 +2117,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	}
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
 
 	/* starting over for a new packet, but check if we need to yield */
 	cond_resched();
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 3a0d6c5a8286b..024458ef163c9 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -586,7 +586,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
 		SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
 		SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
 	}
-	kfree_skb(skb);
+	kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);
 
 	/* starting over for a new packet, but check if we need to yield */
 	cond_resched();

From 9bfc9d65a1dc9ca2d45210ff4227517b460c19af Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 7 Mar 2025 16:03:58 +0000
Subject: [PATCH 1850/2753] hamradio: use netdev_lockdep_set_classes() helper

It is time to use netdev_lockdep_set_classes() in bpqether.c

List of related commits:

0bef512012b1 ("net: add netdev_lockdep_set_classes() to virtual drivers")
c74e1039912e ("net: bridge: use netdev_lockdep_set_classes()")
9a3c93af5491 ("vlan: use netdev_lockdep_set_classes()")
0d7dd798fd89 ("net: ipvlan: call netdev_lockdep_set_classes()")
24ffd752007f ("net: macvlan: call netdev_lockdep_set_classes()")
78e7a2ae8727 ("net: vrf: call netdev_lockdep_set_classes()")
d3fff6c443fe ("net: add netdev_lockdep_set_classes() helper")

syzbot reported:

WARNING: possible recursive locking detected
6.14.0-rc5-syzkaller-01064-g2525e16a2bae #0 Not tainted

dhcpcd/5501 is trying to acquire lock:
 ffff8880797e2d28 (&dev->lock){+.+.}-{4:4}, at: netdev_lock include/linux/netdevice.h:2765 [inline]
 ffff8880797e2d28 (&dev->lock){+.+.}-{4:4}, at: register_netdevice+0x12d8/0x1b70 net/core/dev.c:11008

but task is already holding lock:
 ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: netdev_lock include/linux/netdevice.h:2765 [inline]
 ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: netdev_lock_ops include/linux/netdevice.h:2804 [inline]
 ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: dev_change_flags+0x120/0x270 net/core/dev_api.c:65

other info that might help us debug this:
 Possible unsafe locking scenario:

       CPU0
       ----
  lock(&dev->lock);
  lock(&dev->lock);

 *** DEADLOCK ***

 May be due to missing lock nesting notation

2 locks held by dhcpcd/5501:
  #0: ffffffff8fed6848 (rtnl_mutex){+.+.}-{4:4}, at: rtnl_net_lock include/linux/rtnetlink.h:130 [inline]
  #0: ffffffff8fed6848 (rtnl_mutex){+.+.}-{4:4}, at: devinet_ioctl+0x34c/0x1d80 net/ipv4/devinet.c:1121
  #1: ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: netdev_lock include/linux/netdevice.h:2765 [inline]
  #1: ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: netdev_lock_ops include/linux/netdevice.h:2804 [inline]
  #1: ffff88802e530d28 (&dev->lock){+.+.}-{4:4}, at: dev_change_flags+0x120/0x270 net/core/dev_api.c:65

stack backtrace:
CPU: 1 UID: 0 PID: 5501 Comm: dhcpcd Not tainted 6.14.0-rc5-syzkaller-01064-g2525e16a2bae #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:94 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
  print_deadlock_bug+0x483/0x620 kernel/locking/lockdep.c:3039
  check_deadlock kernel/locking/lockdep.c:3091 [inline]
  validate_chain+0x15e2/0x5920 kernel/locking/lockdep.c:3893
  __lock_acquire+0x1397/0x2100 kernel/locking/lockdep.c:5228
  lock_acquire+0x1ed/0x550 kernel/locking/lockdep.c:5851
  __mutex_lock_common kernel/locking/mutex.c:585 [inline]
  __mutex_lock+0x19c/0x1010 kernel/locking/mutex.c:730
  netdev_lock include/linux/netdevice.h:2765 [inline]
  register_netdevice+0x12d8/0x1b70 net/core/dev.c:11008
  bpq_new_device drivers/net/hamradio/bpqether.c:499 [inline]
  bpq_device_event+0x4b1/0x8d0 drivers/net/hamradio/bpqether.c:542
  notifier_call_chain+0x1a5/0x3f0 kernel/notifier.c:85
 __dev_notify_flags+0x207/0x400
  netif_change_flags+0xf0/0x1a0 net/core/dev.c:9442
  dev_change_flags+0x146/0x270 net/core/dev_api.c:66
  devinet_ioctl+0xea2/0x1d80 net/ipv4/devinet.c:1200
  inet_ioctl+0x3d7/0x4f0 net/ipv4/af_inet.c:1001
  sock_do_ioctl+0x158/0x460 net/socket.c:1190
  sock_ioctl+0x626/0x8e0 net/socket.c:1309
  vfs_ioctl fs/ioctl.c:51 [inline]
  __do_sys_ioctl fs/ioctl.c:906 [inline]
  __se_sys_ioctl+0xf5/0x170 fs/ioctl.c:892
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 7e4d784f5810 ("net: hold netdev instance lock during rtnetlink operations")
Reported-by: syzbot <syzkaller@googlegroups.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250307160358.3153859-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/hamradio/bpqether.c | 24 ++----------------------
 1 file changed, 2 insertions(+), 22 deletions(-)

diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index bac1bb69d63a1..f6b0bfbbc753f 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -107,27 +107,6 @@ struct bpqdev {
 
 static LIST_HEAD(bpq_devices);
 
-/*
- * bpqether network devices are paired with ethernet devices below them, so
- * form a special "super class" of normal ethernet devices; split their locks
- * off into a separate class since they always nest.
- */
-static struct lock_class_key bpq_netdev_xmit_lock_key;
-static struct lock_class_key bpq_netdev_addr_lock_key;
-
-static void bpq_set_lockdep_class_one(struct net_device *dev,
-				      struct netdev_queue *txq,
-				      void *_unused)
-{
-	lockdep_set_class(&txq->_xmit_lock, &bpq_netdev_xmit_lock_key);
-}
-
-static void bpq_set_lockdep_class(struct net_device *dev)
-{
-	lockdep_set_class(&dev->addr_list_lock, &bpq_netdev_addr_lock_key);
-	netdev_for_each_tx_queue(dev, bpq_set_lockdep_class_one, NULL);
-}
-
 /* ------------------------------------------------------------------------ */
 
 
@@ -454,6 +433,8 @@ static const struct net_device_ops bpq_netdev_ops = {
 
 static void bpq_setup(struct net_device *dev)
 {
+	netdev_lockdep_set_classes(dev);
+
 	dev->netdev_ops	     = &bpq_netdev_ops;
 	dev->needs_free_netdev = true;
 
@@ -499,7 +480,6 @@ static int bpq_new_device(struct net_device *edev)
 	err = register_netdevice(ndev);
 	if (err)
 		goto error;
-	bpq_set_lockdep_class(ndev);
 
 	/* List protected by RTNL */
 	list_add_rcu(&bpq->bpq_list, &bpq_devices);

From 8ef890df4031121a94407c84659125cbccd3fdbe Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 7 Mar 2025 10:30:06 -0800
Subject: [PATCH 1851/2753] net: move misc netdev_lock flavors to a separate
 header

Move the more esoteric helpers for netdev instance lock to
a dedicated header. This avoids growing netdevice.h to infinity
and makes rebuilding the kernel much faster (after touching
the header with the helpers).

The main netdev_lock() / netdev_unlock() functions are used
in static inlines in netdevice.h and will probably be used
most commonly, so keep them in netdevice.h.

Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250307183006.2312761-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c               |  1 +
 drivers/net/dummy.c                           |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c |  1 +
 drivers/net/ethernet/intel/iavf/iavf_main.c   |  1 +
 drivers/net/ethernet/microsoft/mana/mana_en.c |  1 +
 drivers/net/geneve.c                          |  1 +
 drivers/net/hamradio/bpqether.c               |  1 +
 drivers/net/hyperv/netvsc_drv.c               |  1 +
 drivers/net/ipvlan/ipvlan_main.c              |  1 +
 drivers/net/loopback.c                        |  1 +
 drivers/net/macsec.c                          |  1 +
 drivers/net/macvlan.c                         |  1 +
 drivers/net/netdevsim/netdev.c                |  1 +
 drivers/net/ppp/ppp_generic.c                 |  1 +
 drivers/net/team/team_core.c                  |  1 +
 drivers/net/veth.c                            |  1 +
 drivers/net/vrf.c                             |  1 +
 drivers/net/vxlan/vxlan_core.c                |  1 +
 include/linux/netdevice.h                     | 81 +----------------
 include/net/netdev_lock.h                     | 89 +++++++++++++++++++
 kernel/bpf/offload.c                          |  1 +
 net/8021q/vlan_dev.c                          |  1 +
 net/bluetooth/6lowpan.c                       |  1 +
 net/bridge/br_device.c                        |  2 +
 net/core/dev.c                                |  1 +
 net/core/dev.h                                |  1 +
 net/core/dev_api.c                            |  2 +
 net/core/dev_ioctl.c                          |  1 +
 net/core/net-sysfs.c                          |  1 +
 net/core/rtnetlink.c                          |  1 +
 net/dsa/conduit.c                             |  1 +
 net/ethtool/cabletest.c                       |  1 +
 net/ethtool/cmis_fw_update.c                  |  1 +
 net/ethtool/features.c                        |  2 +
 net/ethtool/ioctl.c                           |  1 +
 net/ethtool/module.c                          |  1 +
 net/ethtool/netlink.c                         |  1 +
 net/ethtool/phy.c                             |  1 +
 net/ethtool/rss.c                             |  2 +
 net/ethtool/tsinfo.c                          |  1 +
 net/ieee802154/6lowpan/core.c                 |  1 +
 net/ipv4/ip_tunnel.c                          |  1 +
 net/ipv6/ip6_gre.c                            |  1 +
 net/ipv6/ip6_tunnel.c                         |  1 +
 net/ipv6/ip6_vti.c                            |  1 +
 net/ipv6/sit.c                                |  1 +
 net/l2tp/l2tp_eth.c                           |  1 +
 net/sched/sch_api.c                           |  1 +
 net/xdp/xsk.c                                 |  1 +
 net/xdp/xsk_buff_pool.c                       |  1 +
 51 files changed, 143 insertions(+), 80 deletions(-)
 create mode 100644 include/net/netdev_lock.h

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index cf0b02720dd82..6c95f478ab805 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -90,6 +90,7 @@
 #include <net/tls.h>
 #endif
 #include <net/ip6_route.h>
+#include <net/netdev_lock.h>
 #include <net/xdp.h>
 
 #include "bonding_priv.h"
diff --git a/drivers/net/dummy.c b/drivers/net/dummy.c
index 005d79975f3bd..a4938c6a5ebb5 100644
--- a/drivers/net/dummy.c
+++ b/drivers/net/dummy.c
@@ -38,6 +38,7 @@
 #include <linux/moduleparam.h>
 #include <linux/rtnetlink.h>
 #include <linux/net_tstamp.h>
+#include <net/netdev_lock.h>
 #include <net/rtnetlink.h>
 #include <linux/u64_stats_sync.h>
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 1a1e6da777775..b09171110ec49 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -54,6 +54,7 @@
 #include <net/pkt_cls.h>
 #include <net/page_pool/helpers.h>
 #include <linux/align.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <linux/pci-tph.h>
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 0caf6e9bccb8c..cf2b3ad75c9b9 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -15,6 +15,7 @@
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/filter.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 032e1a58af6f1..6d7ba4d67a193 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/net/intel/libie/rx.h>
+#include <net/netdev_lock.h>
 
 #include "iavf.h"
 #include "iavf_ptp.h"
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 0411a1897f573..2d826077d38cd 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -13,6 +13,7 @@
 
 #include <net/checksum.h>
 #include <net/ip6_checksum.h>
+#include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
 #include <net/xdp.h>
 
diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index 2c65f867fd31d..66e38ce9cd1d3 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -18,6 +18,7 @@
 #include <net/rtnetlink.h>
 #include <net/geneve.h>
 #include <net/gro.h>
+#include <net/netdev_lock.h>
 #include <net/protocol.h>
 
 #define GENEVE_NETDEV_VER	"0.6"
diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c
index f6b0bfbbc753f..0e0fe32d2da4e 100644
--- a/drivers/net/hamradio/bpqether.c
+++ b/drivers/net/hamradio/bpqether.c
@@ -77,6 +77,7 @@
 
 #include <net/ip.h>
 #include <net/arp.h>
+#include <net/netdev_lock.h>
 #include <net/net_namespace.h>
 
 #include <linux/bpqether.h>
diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c
index 9c6501bf27bde..c51b318b8a72e 100644
--- a/drivers/net/hyperv/netvsc_drv.c
+++ b/drivers/net/hyperv/netvsc_drv.c
@@ -29,6 +29,7 @@
 #include <linux/bpf.h>
 
 #include <net/arp.h>
+#include <net/netdev_lock.h>
 #include <net/route.h>
 #include <net/sock.h>
 #include <net/pkt_sched.h>
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index b56144ca2fded..0ed2fd833a5db 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -3,6 +3,7 @@
  */
 
 #include <linux/ethtool.h>
+#include <net/netdev_lock.h>
 
 #include "ipvlan.h"
 
diff --git a/drivers/net/loopback.c b/drivers/net/loopback.c
index 201fddcd3b1e8..1fb6ce6843ade 100644
--- a/drivers/net/loopback.c
+++ b/drivers/net/loopback.c
@@ -54,6 +54,7 @@
 #include <linux/percpu.h>
 #include <linux/net_tstamp.h>
 #include <net/net_namespace.h>
+#include <net/netdev_lock.h>
 #include <linux/u64_stats_sync.h>
 
 /* blackhole_netdev - a device used for dsts that are marked expired!
diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c
index 4de5d63fd577c..3d315e30ee472 100644
--- a/drivers/net/macsec.c
+++ b/drivers/net/macsec.c
@@ -19,6 +19,7 @@
 #include <net/gro_cells.h>
 #include <net/macsec.h>
 #include <net/dst_metadata.h>
+#include <net/netdev_lock.h>
 #include <linux/phy.h>
 #include <linux/byteorder/generic.h>
 #include <linux/if_arp.h>
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 4e9d54be887c1..d0dfa6bca6cc2 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -28,6 +28,7 @@
 #include <linux/if_macvlan.h>
 #include <linux/hash.h>
 #include <linux/workqueue.h>
+#include <net/netdev_lock.h>
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
 #include <linux/netpoll.h>
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index 54d03b0628d22..d71fd2907cc80 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -25,6 +25,7 @@
 #include <net/page_pool/helpers.h>
 #include <net/netlink.h>
 #include <net/net_shaper.h>
+#include <net/netdev_lock.h>
 #include <net/pkt_cls.h>
 #include <net/rtnetlink.h>
 #include <net/udp_tunnel.h>
diff --git a/drivers/net/ppp/ppp_generic.c b/drivers/net/ppp/ppp_generic.c
index ca77661688c0c..53463767cc43e 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -45,6 +45,7 @@
 #include <linux/slab.h>
 #include <linux/file.h>
 #include <linux/unaligned.h>
+#include <net/netdev_lock.h>
 #include <net/slhc_vj.h>
 #include <linux/atomic.h>
 #include <linux/refcount.h>
diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index fb917560d0a24..d8fc0c79745d3 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -23,6 +23,7 @@
 #include <linux/rtnetlink.h>
 #include <net/rtnetlink.h>
 #include <net/genetlink.h>
+#include <net/netdev_lock.h>
 #include <net/netlink.h>
 #include <net/sch_generic.h>
 #include <linux/if_team.h>
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 05f5eeef539f0..7bb53961c0eaf 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -17,6 +17,7 @@
 
 #include <net/rtnetlink.h>
 #include <net/dst.h>
+#include <net/netdev_lock.h>
 #include <net/xfrm.h>
 #include <net/xdp.h>
 #include <linux/veth.h>
diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index 36cf6191335ea..7168b33adadb0 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -34,6 +34,7 @@
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
 #include <net/fib_rules.h>
+#include <net/netdev_lock.h>
 #include <net/sch_generic.h>
 #include <net/netns/generic.h>
 #include <net/netfilter/nf_conntrack.h>
diff --git a/drivers/net/vxlan/vxlan_core.c b/drivers/net/vxlan/vxlan_core.c
index 227d7f5a302a9..8c49e903cb3a1 100644
--- a/drivers/net/vxlan/vxlan_core.c
+++ b/drivers/net/vxlan/vxlan_core.c
@@ -25,6 +25,7 @@
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <net/tun_proto.h>
 #include <net/vxlan.h>
 #include <net/nexthop.h>
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index d206c9592b60f..9a297757df7eb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2630,40 +2630,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
-static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
-				     const struct lockdep_map *b)
-{
-	/* Only lower devices currently grab the instance lock, so no
-	 * real ordering issues can occur. In the near future, only
-	 * hardware devices will grab instance lock which also does not
-	 * involve any ordering. Suppress lockdep ordering warnings
-	 * until (if) we start grabbing instance lock on pure SW
-	 * devices (bond/team/veth/etc).
-	 */
-	if (a == b)
-		return 0;
-	return -1;
-}
-
-#define netdev_lockdep_set_classes(dev)				\
-{								\
-	static struct lock_class_key qdisc_tx_busylock_key;	\
-	static struct lock_class_key qdisc_xmit_lock_key;	\
-	static struct lock_class_key dev_addr_list_lock_key;	\
-	static struct lock_class_key dev_instance_lock_key;	\
-	unsigned int i;						\
-								\
-	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
-	lockdep_set_class(&(dev)->addr_list_lock,		\
-			  &dev_addr_list_lock_key);		\
-	lockdep_set_class(&(dev)->lock,				\
-			  &dev_instance_lock_key);		\
-	lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL);	\
-	for (i = 0; i < (dev)->num_tx_queues; i++)		\
-		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
-				  &qdisc_xmit_lock_key);	\
-}
-
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
@@ -2765,56 +2731,11 @@ static inline void netdev_lock(struct net_device *dev)
 	mutex_lock(&dev->lock);
 }
 
-static inline bool netdev_trylock(struct net_device *dev)
-{
-	return mutex_trylock(&dev->lock);
-}
-
 static inline void netdev_unlock(struct net_device *dev)
 {
 	mutex_unlock(&dev->lock);
 }
-
-static inline void netdev_assert_locked(struct net_device *dev)
-{
-	lockdep_assert_held(&dev->lock);
-}
-
-static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
-{
-	if (dev->reg_state == NETREG_REGISTERED ||
-	    dev->reg_state == NETREG_UNREGISTERING)
-		netdev_assert_locked(dev);
-}
-
-static inline bool netdev_need_ops_lock(struct net_device *dev)
-{
-	bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
-
-#if IS_ENABLED(CONFIG_NET_SHAPER)
-	ret |= !!dev->netdev_ops->net_shaper_ops;
-#endif
-
-	return ret;
-}
-
-static inline void netdev_lock_ops(struct net_device *dev)
-{
-	if (netdev_need_ops_lock(dev))
-		netdev_lock(dev);
-}
-
-static inline void netdev_unlock_ops(struct net_device *dev)
-{
-	if (netdev_need_ops_lock(dev))
-		netdev_unlock(dev);
-}
-
-static inline void netdev_ops_assert_locked(struct net_device *dev)
-{
-	if (netdev_need_ops_lock(dev))
-		lockdep_assert_held(&dev->lock);
-}
+/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */
 
 void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
 
diff --git a/include/net/netdev_lock.h b/include/net/netdev_lock.h
new file mode 100644
index 0000000000000..99631fbd7f544
--- /dev/null
+++ b/include/net/netdev_lock.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _NET_NETDEV_LOCK_H
+#define _NET_NETDEV_LOCK_H
+
+#include <linux/lockdep.h>
+#include <linux/netdevice.h>
+
+static inline bool netdev_trylock(struct net_device *dev)
+{
+	return mutex_trylock(&dev->lock);
+}
+
+static inline void netdev_assert_locked(struct net_device *dev)
+{
+	lockdep_assert_held(&dev->lock);
+}
+
+static inline void netdev_assert_locked_or_invisible(struct net_device *dev)
+{
+	if (dev->reg_state == NETREG_REGISTERED ||
+	    dev->reg_state == NETREG_UNREGISTERING)
+		netdev_assert_locked(dev);
+}
+
+static inline bool netdev_need_ops_lock(struct net_device *dev)
+{
+	bool ret = dev->request_ops_lock || !!dev->queue_mgmt_ops;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	ret |= !!dev->netdev_ops->net_shaper_ops;
+#endif
+
+	return ret;
+}
+
+static inline void netdev_lock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_lock(dev);
+}
+
+static inline void netdev_unlock_ops(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		netdev_unlock(dev);
+}
+
+static inline void netdev_ops_assert_locked(struct net_device *dev)
+{
+	if (netdev_need_ops_lock(dev))
+		lockdep_assert_held(&dev->lock);
+}
+
+static inline int netdev_lock_cmp_fn(const struct lockdep_map *a,
+				     const struct lockdep_map *b)
+{
+	/* Only lower devices currently grab the instance lock, so no
+	 * real ordering issues can occur. In the near future, only
+	 * hardware devices will grab instance lock which also does not
+	 * involve any ordering. Suppress lockdep ordering warnings
+	 * until (if) we start grabbing instance lock on pure SW
+	 * devices (bond/team/veth/etc).
+	 */
+	if (a == b)
+		return 0;
+	return -1;
+}
+
+#define netdev_lockdep_set_classes(dev)				\
+{								\
+	static struct lock_class_key qdisc_tx_busylock_key;	\
+	static struct lock_class_key qdisc_xmit_lock_key;	\
+	static struct lock_class_key dev_addr_list_lock_key;	\
+	static struct lock_class_key dev_instance_lock_key;	\
+	unsigned int i;						\
+								\
+	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
+	lockdep_set_class(&(dev)->addr_list_lock,		\
+			  &dev_addr_list_lock_key);		\
+	lockdep_set_class(&(dev)->lock,				\
+			  &dev_instance_lock_key);		\
+	lock_set_cmp_fn(&dev->lock, netdev_lock_cmp_fn, NULL);	\
+	for (i = 0; i < (dev)->num_tx_queues; i++)		\
+		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
+				  &qdisc_xmit_lock_key);	\
+}
+
+#endif
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 4f707cfe7f103..42ae8d595c2c2 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -25,6 +25,7 @@
 #include <linux/rhashtable.h>
 #include <linux/rtnetlink.h>
 #include <linux/rwsem.h>
+#include <net/netdev_lock.h>
 #include <net/xdp.h>
 
 /* Protects offdevs, members of bpf_offload_netdev and offload members
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index ee32834007168..770a4dcf7f634 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -27,6 +27,7 @@
 #include <linux/phy.h>
 #include <net/arp.h>
 #include <net/macsec.h>
+#include <net/netdev_lock.h>
 
 #include "vlan.h"
 #include "vlanproc.h"
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 50cfec8ccac4f..1298c8685bad3 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -13,6 +13,7 @@
 #include <net/ipv6.h>
 #include <net/ip6_route.h>
 #include <net/addrconf.h>
+#include <net/netdev_lock.h>
 #include <net/pkt_sched.h>
 
 #include <net/bluetooth/bluetooth.h>
diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
index 9d8c72ed01aba..a818fdc22da9a 100644
--- a/net/bridge/br_device.c
+++ b/net/bridge/br_device.c
@@ -16,6 +16,8 @@
 #include <linux/netfilter_bridge.h>
 
 #include <linux/uaccess.h>
+#include <net/netdev_lock.h>
+
 #include "br_private.h"
 
 #define COMMON_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | \
diff --git a/net/core/dev.c b/net/core/dev.c
index a0f75a1d1f5a7..1cb134ff73270 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -156,6 +156,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/prandom.h>
 #include <linux/once_lite.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/types.h>
 #include <net/page_pool/helpers.h>
diff --git a/net/core/dev.h b/net/core/dev.h
index b50ca645c0863..0ddd3631acb01 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -6,6 +6,7 @@
 #include <linux/types.h>
 #include <linux/rwsem.h>
 #include <linux/netdevice.h>
+#include <net/netdev_lock.h>
 
 struct net;
 struct netlink_ext_ack;
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 655a95fb7baa6..1f0e24849bc65 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
+
 #include <linux/netdevice.h>
+#include <net/netdev_lock.h>
 
 #include "dev.h"
 
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 296e52d1395d6..5471cf4fc9849 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -10,6 +10,7 @@
 #include <linux/wireless.h>
 #include <linux/if_bridge.h>
 #include <net/dsa_stubs.h>
+#include <net/netdev_lock.h>
 #include <net/wext.h>
 
 #include "dev.h"
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 02d1d40b47ae3..529a0f7212682 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -23,6 +23,7 @@
 #include <linux/of.h>
 #include <linux/of_net.h>
 #include <linux/cpu.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_rx_queue.h>
 #include <net/rps.h>
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 88a352b02bcef..90597bf84e3d3 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -53,6 +53,7 @@
 #include <net/fib_rules.h>
 #include <net/rtnetlink.h>
 #include <net/net_namespace.h>
+#include <net/netdev_lock.h>
 #include <net/devlink.h>
 #if IS_ENABLED(CONFIG_IPV6)
 #include <net/addrconf.h>
diff --git a/net/dsa/conduit.c b/net/dsa/conduit.c
index f21bb2551bed2..4ae255cfb23f8 100644
--- a/net/dsa/conduit.c
+++ b/net/dsa/conduit.c
@@ -10,6 +10,7 @@
 #include <linux/netdevice.h>
 #include <linux/netlink.h>
 #include <net/dsa.h>
+#include <net/netdev_lock.h>
 
 #include "conduit.h"
 #include "dsa.h"
diff --git a/net/ethtool/cabletest.c b/net/ethtool/cabletest.c
index ddcba073321f0..0364b8fb577bc 100644
--- a/net/ethtool/cabletest.c
+++ b/net/ethtool/cabletest.c
@@ -2,6 +2,7 @@
 
 #include <linux/phy.h>
 #include <linux/ethtool_netlink.h>
+#include <net/netdev_lock.h>
 #include "netlink.h"
 #include "common.h"
 
diff --git a/net/ethtool/cmis_fw_update.c b/net/ethtool/cmis_fw_update.c
index 946830af3e7cc..df5f344209c47 100644
--- a/net/ethtool/cmis_fw_update.c
+++ b/net/ethtool/cmis_fw_update.c
@@ -2,6 +2,7 @@
 
 #include <linux/ethtool.h>
 #include <linux/firmware.h>
+#include <net/netdev_lock.h>
 
 #include "common.h"
 #include "module_fw.h"
diff --git a/net/ethtool/features.c b/net/ethtool/features.c
index ccffd64d5a879..f2217983be2bd 100644
--- a/net/ethtool/features.c
+++ b/net/ethtool/features.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <net/netdev_lock.h>
+
 #include "netlink.h"
 #include "common.h"
 #include "bitset.h"
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 496a2774100c6..221639407c724 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -31,6 +31,7 @@
 #include <net/ipv6.h>
 #include <net/xdp_sock_drv.h>
 #include <net/flow_offload.h>
+#include <net/netdev_lock.h>
 #include <linux/ethtool_netlink.h>
 #include "common.h"
 
diff --git a/net/ethtool/module.c b/net/ethtool/module.c
index d3d2e135e45eb..4d4e0a82579a2 100644
--- a/net/ethtool/module.c
+++ b/net/ethtool/module.c
@@ -4,6 +4,7 @@
 #include <linux/firmware.h>
 #include <linux/sfp.h>
 #include <net/devlink.h>
+#include <net/netdev_lock.h>
 
 #include "netlink.h"
 #include "common.h"
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 70834947f474c..a163d40c6431b 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
 #include <net/sock.h>
 #include <linux/ethtool_netlink.h>
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index 1a6b725d1f146..1f590e8d75ed6 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -9,6 +9,7 @@
 #include <linux/phy.h>
 #include <linux/phy_link_topology.h>
 #include <linux/sfp.h>
+#include <net/netdev_lock.h>
 
 struct phy_req_info {
 	struct ethnl_req_info		base;
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index ec41d1d7eefe4..6d9b1769896ba 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -1,5 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <net/netdev_lock.h>
+
 #include "netlink.h"
 #include "common.h"
 
diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 73b6a89b87316..32204cca24da3 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -4,6 +4,7 @@
 #include <linux/phy.h>
 #include <linux/phy_link_topology.h>
 #include <linux/ptp_clock_kernel.h>
+#include <net/netdev_lock.h>
 
 #include "netlink.h"
 #include "common.h"
diff --git a/net/ieee802154/6lowpan/core.c b/net/ieee802154/6lowpan/core.c
index 9a9da74b0a4fa..018929563c6bc 100644
--- a/net/ieee802154/6lowpan/core.c
+++ b/net/ieee802154/6lowpan/core.c
@@ -50,6 +50,7 @@
 #include <linux/if_arp.h>
 
 #include <net/ipv6.h>
+#include <net/netdev_lock.h>
 
 #include "6lowpan_i.h"
 
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 4b06dc7e04f2f..1024f961ec9ad 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -40,6 +40,7 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <net/rtnetlink.h>
 #include <net/udp.h>
 #include <net/dst_metadata.h>
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index c6ebb6a6d3908..957ca98fa70f9 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -43,6 +43,7 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <net/rtnetlink.h>
 
 #include <net/ipv6.h>
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 170a6ac30889a..a04dd1bb4b195 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -52,6 +52,7 @@
 #include <net/inet_ecn.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <net/dst_metadata.h>
 #include <net/inet_dscp.h>
 
diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 83c055996fbb0..09ec4b0ad7dc6 100644
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -45,6 +45,7 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <linux/etherdevice.h>
 
 #define IP6_VTI_HASH_SIZE_SHIFT  5
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 6f04703fe6386..9a0f32acb7500 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -51,6 +51,7 @@
 #include <net/dsfield.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <net/inet_dscp.h>
 
 /*
diff --git a/net/l2tp/l2tp_eth.c b/net/l2tp/l2tp_eth.c
index e836910734967..cf0b66f4fb29b 100644
--- a/net/l2tp/l2tp_eth.c
+++ b/net/l2tp/l2tp_eth.c
@@ -25,6 +25,7 @@
 #include <net/xfrm.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/netdev_lock.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/udp.h>
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index f5101c2ffc664..abace7665cfe6 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -26,6 +26,7 @@
 #include <linux/slab.h>
 #include <linux/hashtable.h>
 
+#include <net/netdev_lock.h>
 #include <net/net_namespace.h>
 #include <net/sock.h>
 #include <net/netlink.h>
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index f864e5d70b40a..e5d104ce7b82f 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -25,6 +25,7 @@
 #include <linux/vmalloc.h>
 #include <net/xdp_sock_drv.h>
 #include <net/busy_poll.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_rx_queue.h>
 #include <net/xdp.h>
 
diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 0e6ca568fdeeb..14716ad3d7bc4 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 
 #include <linux/netdevice.h>
+#include <net/netdev_lock.h>
 #include <net/xsk_buff_pool.h>
 #include <net/xdp_sock.h>
 #include <net/xdp_sock_drv.h>

From b36402e4a0772d1b3da06a4f5fbd1cfe4d6f1cc0 Mon Sep 17 00:00:00 2001
From: Jianfeng Liu <liujianfeng1994@gmail.com>
Date: Fri, 28 Feb 2025 22:33:08 +0800
Subject: [PATCH 1852/2753] arm64: dts: rockchip: slow down emmc freq for rock
 5 itx

The current max-frequency 200000000 of emmc is not stable. When doing
heavy write there will be I/O Error. After setting max-frequency to
150000000 the emmc is stable under write.

Also remove property mmc-hs200-1_8v because we are already running at
HS400 mode.

Tested with fio command:
fio -filename=./test_randread -direct=1 -iodepth 1 -thread \
-rw=randwrite -ioengine=psync -bs=16k -size=1G -numjobs=10 \
-runtime=600 -group_reporting -name=mytest

Signed-off-by: Jianfeng Liu <liujianfeng1994@gmail.com>
Link: https://lore.kernel.org/r/20250228143341.70244-1-liujianfeng1994@gmail.com
Signed-off-by: Heiko Stuebner <heiko@sntech.de>
---
 arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts b/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
index 6d68f70284e45..2a0590209462e 100644
--- a/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
+++ b/arch/arm64/boot/dts/rockchip/rk3588-rock-5-itx.dts
@@ -690,10 +690,9 @@
 
 &sdhci {
 	bus-width = <8>;
-	max-frequency = <200000000>;
+	max-frequency = <150000000>;
 	mmc-hs400-1_8v;
 	mmc-hs400-enhanced-strobe;
-	mmc-hs200-1_8v;
 	no-sdio;
 	no-sd;
 	non-removable;

From f6f425f3d251c059d1251edd4f37024290d3efca Mon Sep 17 00:00:00 2001
From: Chiara Meiohas <cmeiohas@nvidia.com>
Date: Wed, 26 Feb 2025 15:01:05 +0200
Subject: [PATCH 1853/2753] net/mlx5: Add RDMA_CTRL HW capabilities

Add RDMA_CTRL UCTX capabilities and add the RDMA_CTRL general object
type in hca_cap_2.

Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Chiara Meiohas <cmeiohas@nvidia.com>
Link: https://patch.msgid.link/ef7eb24be9a6f247ab52e8b4480350072e5182f5.1740574103.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index cc2875e843f7f..3b3d88ffcacc6 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1570,6 +1570,8 @@ enum {
 enum {
 	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
 	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
+	MLX5_UCTX_CAP_RDMA_CTRL = 1UL << 3,
+	MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA = 1UL << 4,
 };
 
 #define MLX5_FC_BULK_SIZE_FACTOR 128
@@ -2140,7 +2142,8 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   log_min_mkey_entity_size[0x5];
 	u8	   reserved_at_1b0[0x10];
 
-	u8	   reserved_at_1c0[0x60];
+	u8	   general_obj_types_127_64[0x40];
+	u8	   reserved_at_200[0x20];
 
 	u8	   reserved_at_220[0x1];
 	u8	   sw_vhca_id_valid[0x1];
@@ -12494,6 +12497,10 @@ enum {
 	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24),
 };
 
+enum {
+	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL = BIT_ULL(0x13),
+};
+
 enum {
 	MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
 	MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13,
@@ -12501,6 +12508,7 @@ enum {
 	MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24,
 	MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27,
 	MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47,
+	MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL = 0x53,
 	MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15,
 };
 

From 0a34fad1bed45ff2245ab8c315bc3d4c6471af46 Mon Sep 17 00:00:00 2001
From: Chiara Meiohas <cmeiohas@nvidia.com>
Date: Wed, 26 Feb 2025 15:01:06 +0200
Subject: [PATCH 1854/2753] net/mlx5: Allow the throttle mechanism to be more
 dynamic

Previously, throttle commands were identified and limited based on
opcode. These commands were limited to half the command slots using a
semaphore, and callback commands checked the opcode to determine
semaphore release.

To allow exceptions, we introduce a variable to indicate when the
throttle lock is held. This allows scenarios where throttle commands
are not limited. Callback functions use this variable to determine
if the throttle semaphore needs to be released.

This patch contains no functional changes. It's a preparation for the
next patch.

Signed-off-by: Chiara Meiohas <cmeiohas@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Link: https://patch.msgid.link/055d975edeb816ac4c0fd1e665c6157d11947d26.1740574103.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 43 +++++++++++++------
 include/linux/mlx5/driver.h                   |  1 +
 2 files changed, 32 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index e733b81e18a21..19c0c15c7e088 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -1881,7 +1881,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 {
 	struct mlx5_cmd_msg *inb, *outb;
 	u16 opcode = in_to_opcode(in);
-	bool throttle_op;
+	bool throttle_locked = false;
 	int pages_queue;
 	gfp_t gfp;
 	u8 token;
@@ -1890,12 +1890,12 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	if (mlx5_cmd_is_down(dev) || !opcode_allowed(&dev->cmd, opcode))
 		return -ENXIO;
 
-	throttle_op = mlx5_cmd_is_throttle_opcode(opcode);
-	if (throttle_op) {
-		if (callback) {
-			if (down_trylock(&dev->cmd.vars.throttle_sem))
-				return -EBUSY;
-		} else {
+	if (!callback) {
+		/* The semaphore is already held for callback commands. It was
+		 * acquired in mlx5_cmd_exec_cb()
+		 */
+		if (mlx5_cmd_is_throttle_opcode(opcode)) {
+			throttle_locked = true;
 			down(&dev->cmd.vars.throttle_sem);
 		}
 	}
@@ -1941,7 +1941,7 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 out_in:
 	free_msg(dev, inb);
 out_up:
-	if (throttle_op)
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
 	return err;
 }
@@ -2104,17 +2104,17 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	struct mlx5_async_work *work = _work;
 	struct mlx5_async_ctx *ctx;
 	struct mlx5_core_dev *dev;
-	u16 opcode;
+	bool throttle_locked;
 
 	ctx = work->ctx;
 	dev = ctx->dev;
-	opcode = work->opcode;
+	throttle_locked = work->throttle_locked;
 	status = cmd_status_err(dev, status, work->opcode, work->op_mod, work->out);
 	work->user_callback(status, work);
 	/* Can't access "work" from this point on. It could have been freed in
 	 * the callback.
 	 */
-	if (mlx5_cmd_is_throttle_opcode(opcode))
+	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
@@ -2131,11 +2131,30 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 	work->opcode = in_to_opcode(in);
 	work->op_mod = MLX5_GET(mbox_in, in, op_mod);
 	work->out = out;
+	work->throttle_locked = false;
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
+
+	if (mlx5_cmd_is_throttle_opcode(in_to_opcode(in))) {
+		if (down_trylock(&ctx->dev->cmd.vars.throttle_sem)) {
+			ret = -EBUSY;
+			goto dec_num_inflight;
+		}
+		work->throttle_locked = true;
+	}
+
 	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
 		       mlx5_cmd_exec_cb_handler, work, false);
-	if (ret && atomic_dec_and_test(&ctx->num_inflight))
+	if (ret)
+		goto sem_up;
+
+	return 0;
+
+sem_up:
+	if (work->throttle_locked)
+		up(&ctx->dev->cmd.vars.throttle_sem);
+dec_num_inflight:
+	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 
 	return ret;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index af86097641b0b..876d6b03a87a4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -989,6 +989,7 @@ struct mlx5_async_work {
 	mlx5_async_cbk_t user_callback;
 	u16 opcode; /* cmd opcode */
 	u16 op_mod; /* cmd op_mod */
+	u8 throttle_locked:1;
 	void *out; /* pointer to the cmd output buffer */
 };
 

From f9deed0980fe29c57488f395528fe3d923c91b1f Mon Sep 17 00:00:00 2001
From: Chiara Meiohas <cmeiohas@nvidia.com>
Date: Wed, 26 Feb 2025 15:01:07 +0200
Subject: [PATCH 1855/2753] net/mlx5: Limit non-privileged commands

Limit non-privileged UID commands to half of the available command slots
when privileged UIDs are present.
Privileged throttle commands will not be limited.

Use an xarray to store privileged UIDs. Add insert and remove functions
for privileged UIDs management.

Non-user commands (with uid 0) are not limited.

Signed-off-by: Chiara Meiohas <cmeiohas@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/d2f3dd9a0dbad3c9f2b4bb0723837995e4e06de2.1740574103.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/cmd.c | 85 +++++++++++++++++--
 include/linux/mlx5/driver.h                   |  5 ++
 2 files changed, 82 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
index 19c0c15c7e088..e53dbdc0a7a17 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c
@@ -94,6 +94,11 @@ static u16 in_to_opcode(void *in)
 	return MLX5_GET(mbox_in, in, opcode);
 }
 
+static u16 in_to_uid(void *in)
+{
+	return MLX5_GET(mbox_in, in, uid);
+}
+
 /* Returns true for opcodes that might be triggered very frequently and throttle
  * the command interface. Limit their command slots usage.
  */
@@ -823,7 +828,7 @@ static void cmd_status_print(struct mlx5_core_dev *dev, void *in, void *out)
 
 	opcode = in_to_opcode(in);
 	op_mod = MLX5_GET(mbox_in, in, op_mod);
-	uid    = MLX5_GET(mbox_in, in, uid);
+	uid    = in_to_uid(in);
 	status = MLX5_GET(mbox_out, out, status);
 
 	if (!uid && opcode != MLX5_CMD_OP_DESTROY_MKEY &&
@@ -1871,6 +1876,17 @@ static int is_manage_pages(void *in)
 	return in_to_opcode(in) == MLX5_CMD_OP_MANAGE_PAGES;
 }
 
+static bool mlx5_has_privileged_uid(struct mlx5_core_dev *dev)
+{
+	return !xa_empty(&dev->cmd.vars.privileged_uids);
+}
+
+static bool mlx5_cmd_is_privileged_uid(struct mlx5_core_dev *dev,
+				       u16 uid)
+{
+	return !!xa_load(&dev->cmd.vars.privileged_uids, uid);
+}
+
 /*  Notes:
  *    1. Callback functions may not sleep
  *    2. Page queue commands do not support asynchrous completion
@@ -1882,6 +1898,8 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 	struct mlx5_cmd_msg *inb, *outb;
 	u16 opcode = in_to_opcode(in);
 	bool throttle_locked = false;
+	bool unpriv_locked = false;
+	u16 uid = in_to_uid(in);
 	int pages_queue;
 	gfp_t gfp;
 	u8 token;
@@ -1894,7 +1912,12 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 		/* The semaphore is already held for callback commands. It was
 		 * acquired in mlx5_cmd_exec_cb()
 		 */
-		if (mlx5_cmd_is_throttle_opcode(opcode)) {
+		if (uid && mlx5_has_privileged_uid(dev)) {
+			if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+				unpriv_locked = true;
+				down(&dev->cmd.vars.unprivileged_sem);
+			}
+		} else if (mlx5_cmd_is_throttle_opcode(opcode)) {
 			throttle_locked = true;
 			down(&dev->cmd.vars.throttle_sem);
 		}
@@ -1943,6 +1966,9 @@ static int cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 out_up:
 	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
+
 	return err;
 }
 
@@ -2105,10 +2131,12 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	struct mlx5_async_ctx *ctx;
 	struct mlx5_core_dev *dev;
 	bool throttle_locked;
+	bool unpriv_locked;
 
 	ctx = work->ctx;
 	dev = ctx->dev;
 	throttle_locked = work->throttle_locked;
+	unpriv_locked = work->unpriv_locked;
 	status = cmd_status_err(dev, status, work->opcode, work->op_mod, work->out);
 	work->user_callback(status, work);
 	/* Can't access "work" from this point on. It could have been freed in
@@ -2116,6 +2144,8 @@ static void mlx5_cmd_exec_cb_handler(int status, void *_work)
 	 */
 	if (throttle_locked)
 		up(&dev->cmd.vars.throttle_sem);
+	if (unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
 }
@@ -2124,6 +2154,8 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 		     void *out, int out_size, mlx5_async_cbk_t callback,
 		     struct mlx5_async_work *work)
 {
+	struct mlx5_core_dev *dev = ctx->dev;
+	u16 uid;
 	int ret;
 
 	work->ctx = ctx;
@@ -2132,18 +2164,29 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 	work->op_mod = MLX5_GET(mbox_in, in, op_mod);
 	work->out = out;
 	work->throttle_locked = false;
+	work->unpriv_locked = false;
+	uid = in_to_uid(in);
+
 	if (WARN_ON(!atomic_inc_not_zero(&ctx->num_inflight)))
 		return -EIO;
 
-	if (mlx5_cmd_is_throttle_opcode(in_to_opcode(in))) {
-		if (down_trylock(&ctx->dev->cmd.vars.throttle_sem)) {
+	if (uid && mlx5_has_privileged_uid(dev)) {
+		if (!mlx5_cmd_is_privileged_uid(dev, uid)) {
+			if (down_trylock(&dev->cmd.vars.unprivileged_sem)) {
+				ret = -EBUSY;
+				goto dec_num_inflight;
+			}
+			work->unpriv_locked = true;
+		}
+	} else if (mlx5_cmd_is_throttle_opcode(in_to_opcode(in))) {
+		if (down_trylock(&dev->cmd.vars.throttle_sem)) {
 			ret = -EBUSY;
 			goto dec_num_inflight;
 		}
 		work->throttle_locked = true;
 	}
 
-	ret = cmd_exec(ctx->dev, in, in_size, out, out_size,
+	ret = cmd_exec(dev, in, in_size, out, out_size,
 		       mlx5_cmd_exec_cb_handler, work, false);
 	if (ret)
 		goto sem_up;
@@ -2152,7 +2195,9 @@ int mlx5_cmd_exec_cb(struct mlx5_async_ctx *ctx, void *in, int in_size,
 
 sem_up:
 	if (work->throttle_locked)
-		up(&ctx->dev->cmd.vars.throttle_sem);
+		up(&dev->cmd.vars.throttle_sem);
+	if (work->unpriv_locked)
+		up(&dev->cmd.vars.unprivileged_sem);
 dec_num_inflight:
 	if (atomic_dec_and_test(&ctx->num_inflight))
 		complete(&ctx->inflight_done);
@@ -2390,10 +2435,16 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	sema_init(&cmd->vars.sem, cmd->vars.max_reg_cmds);
 	sema_init(&cmd->vars.pages_sem, 1);
 	sema_init(&cmd->vars.throttle_sem, DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+	sema_init(&cmd->vars.unprivileged_sem,
+		  DIV_ROUND_UP(cmd->vars.max_reg_cmds, 2));
+
+	xa_init(&cmd->vars.privileged_uids);
 
 	cmd->pool = dma_pool_create("mlx5_cmd", mlx5_core_dma_dev(dev), size, align, 0);
-	if (!cmd->pool)
-		return -ENOMEM;
+	if (!cmd->pool) {
+		err = -ENOMEM;
+		goto err_destroy_xa;
+	}
 
 	err = alloc_cmd_page(dev, cmd);
 	if (err)
@@ -2427,6 +2478,8 @@ int mlx5_cmd_enable(struct mlx5_core_dev *dev)
 	free_cmd_page(dev, cmd);
 err_free_pool:
 	dma_pool_destroy(cmd->pool);
+err_destroy_xa:
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 	return err;
 }
 
@@ -2439,6 +2492,7 @@ void mlx5_cmd_disable(struct mlx5_core_dev *dev)
 	destroy_msg_cache(dev);
 	free_cmd_page(dev, cmd);
 	dma_pool_destroy(cmd->pool);
+	xa_destroy(&dev->cmd.vars.privileged_uids);
 }
 
 void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
@@ -2446,3 +2500,18 @@ void mlx5_cmd_set_state(struct mlx5_core_dev *dev,
 {
 	dev->cmd.state = cmdif_state;
 }
+
+int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	return xa_insert(&dev->cmd.vars.privileged_uids, uid,
+			 xa_mk_value(uid), GFP_KERNEL);
+}
+EXPORT_SYMBOL(mlx5_cmd_add_privileged_uid);
+
+void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid)
+{
+	void *data = xa_erase(&dev->cmd.vars.privileged_uids, uid);
+
+	WARN(!data, "Privileged UID %u does not exist\n", uid);
+}
+EXPORT_SYMBOL(mlx5_cmd_remove_privileged_uid);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 876d6b03a87a4..4f593a61220d2 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -305,6 +305,8 @@ struct mlx5_cmd {
 		struct semaphore sem;
 		struct semaphore pages_sem;
 		struct semaphore throttle_sem;
+		struct semaphore unprivileged_sem;
+		struct xarray	privileged_uids;
 	} vars;
 	enum mlx5_cmdif_state	state;
 	void	       *cmd_alloc_buf;
@@ -990,6 +992,7 @@ struct mlx5_async_work {
 	u16 opcode; /* cmd opcode */
 	u16 op_mod; /* cmd op_mod */
 	u8 throttle_locked:1;
+	u8 unpriv_locked:1;
 	void *out; /* pointer to the cmd output buffer */
 };
 
@@ -1020,6 +1023,8 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size);
 bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
+int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid);
+void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid);
 
 void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev);
 void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev);

From ab7d228c7e0d0efcac52b81f8514b43985747dc6 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Wed, 26 Feb 2025 15:01:08 +0200
Subject: [PATCH 1856/2753] net/mlx5: Query ADV_RDMA capabilities

Query ADV_RDMA capabilities which provide information for
advanced RDMA related features.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/e3e6ede03ea31cd201078dcdd4e407608e4a5a87.1740574103.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fw.c  |  7 ++++
 .../net/ethernet/mellanox/mlx5/core/main.c    |  1 +
 include/linux/mlx5/device.h                   |  5 +++
 include/linux/mlx5/mlx5_ifc.h                 | 42 ++++++++++++++++++-
 4 files changed, 54 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index b253d1673398d..57476487e31fe 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -287,6 +287,13 @@ int mlx5_query_hca_caps(struct mlx5_core_dev *dev)
 			return err;
 	}
 
+	if (MLX5_CAP_GEN(dev, adv_rdma)) {
+		err = mlx5_core_get_caps_mode(dev, MLX5_CAP_ADV_RDMA,
+					      HCA_CAP_OPMOD_GET_CUR);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index ec956c4bcebdb..af0b677393d08 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1795,6 +1795,7 @@ static const int types[] = {
 	MLX5_CAP_ADV_VIRTUALIZATION,
 	MLX5_CAP_CRYPTO,
 	MLX5_CAP_SHAMPO,
+	MLX5_CAP_ADV_RDMA,
 };
 
 static void mlx5_hca_caps_free(struct mlx5_core_dev *dev)
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index fd37f4e54d761..0ae6d69c5221d 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1251,6 +1251,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_GENERAL_2 = 0x20,
 	MLX5_CAP_PORT_SELECTION = 0x25,
 	MLX5_CAP_ADV_VIRTUALIZATION = 0x26,
+	MLX5_CAP_ADV_RDMA = 0x28,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1384,6 +1385,10 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(adv_virtualization_cap, \
 		 mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap)
 
+#define MLX5_CAP_ADV_RDMA(mdev, cap) \
+	MLX5_GET(adv_rdma_cap, \
+		 mdev->caps.hca[MLX5_CAP_ADV_RDMA]->cur, cap)
+
 #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \
 	MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap)
 
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 3b3d88ffcacc6..fea8af42f9548 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1993,7 +1993,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_geneve_tlv_options[0x8];
 	u8         reserved_at_568[0x3];
 	u8         max_geneve_tlv_option_data_len[0x5];
-	u8         reserved_at_570[0x9];
+	u8         reserved_at_570[0x1];
+	u8         adv_rdma[0x1];
+	u8         reserved_at_572[0x7];
 	u8         adv_virtualization[0x1];
 	u8         reserved_at_57a[0x6];
 
@@ -13076,6 +13078,44 @@ struct mlx5_ifc_load_vhca_state_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_adv_rdma_cap_bits {
+	u8         rdma_transport_manager[0x1];
+	u8         rdma_transport_manager_other_eswitch[0x1];
+	u8         reserved_at_2[0x1e];
+
+	u8         rcx_type[0x8];
+	u8         reserved_at_28[0x2];
+	u8         ps_entry_log_max_value[0x6];
+	u8         reserved_at_30[0x6];
+	u8         qp_max_ps_num_entry[0xa];
+
+	u8         mp_max_num_queues[0x8];
+	u8         ps_user_context_max_log_size[0x8];
+	u8         message_based_qp_and_striding_wq[0x8];
+	u8         reserved_at_58[0x8];
+
+	u8         max_receive_send_message_size_stride[0x10];
+	u8         reserved_at_70[0x10];
+
+	u8         max_receive_send_message_size_byte[0x20];
+
+	u8         reserved_at_a0[0x160];
+
+	struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_rx_flow_table_properties;
+
+	struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_tx_flow_table_properties;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_bitmask_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_bitmask_support_2;
+
+	u8         reserved_at_800[0x3800];
+};
+
 struct mlx5_ifc_adv_virtualization_cap_bits {
 	u8         reserved_at_0[0x3];
 	u8         pg_track_log_max_num[0x5];

From 15b103df80b25025040faa8f35164c2595977bdb Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Wed, 26 Feb 2025 15:01:09 +0200
Subject: [PATCH 1857/2753] net/mlx5: fs, add RDMA TRANSPORT steering domain
 support

Add RX and TX RDMA_TRANSPORT flow table namespace, and the ability
to create flow tables in those namespaces.

The RDMA_TRANSPORT RX and TX are per vport.

Packets will traverse through RDMA_TRANSPORT_RX after RDMA_RX and through
RDMA_TRANSPORT_TX before RDMA_TX, ensuring proper control and management.

RDMA_TRANSPORT domains are managed by the vport group manager.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/a6b550d9859a197eafa804b9a8d76916ca481da9.1740574103.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 .../mellanox/mlx5/core/esw/acl/helper.c       |   2 +-
 .../mellanox/mlx5/core/eswitch_offloads.c     |   6 +-
 .../net/ethernet/mellanox/mlx5/core/fs_cmd.c  |   2 +
 .../net/ethernet/mellanox/mlx5/core/fs_core.c | 178 ++++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/fs_core.h |  12 +-
 include/linux/mlx5/device.h                   |   6 +
 include/linux/mlx5/fs.h                       |  10 +-
 7 files changed, 195 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
index d599e50af346b..3ce455c2535c4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/acl/helper.c
@@ -27,7 +27,7 @@ esw_acl_table_create(struct mlx5_eswitch *esw, struct mlx5_vport *vport, int ns,
 	esw_debug(dev, "Create vport[%d] %s ACL table\n", vport_num,
 		  ns == MLX5_FLOW_NAMESPACE_ESW_INGRESS ? "ingress" : "egress");
 
-	root_ns = mlx5_get_flow_vport_acl_namespace(dev, ns, vport->index);
+	root_ns = mlx5_get_flow_vport_namespace(dev, ns, vport->index);
 	if (!root_ns) {
 		esw_warn(dev, "Failed to get E-Switch root namespace for vport (%d)\n",
 			 vport_num);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 20cc01ceee8a9..1ee5791573d84 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -2828,9 +2828,9 @@ static int esw_set_master_egress_rule(struct mlx5_core_dev *master,
 	if (IS_ERR(vport))
 		return PTR_ERR(vport);
 
-	egress_ns = mlx5_get_flow_vport_acl_namespace(master,
-						      MLX5_FLOW_NAMESPACE_ESW_EGRESS,
-						      vport->index);
+	egress_ns = mlx5_get_flow_vport_namespace(master,
+						  MLX5_FLOW_NAMESPACE_ESW_EGRESS,
+						  vport->index);
 	if (!egress_ns)
 		return -EINVAL;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
index ae20c061e0fb2..a47c29571f647 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c
@@ -1142,6 +1142,8 @@ const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type typ
 	case FS_FT_RDMA_RX:
 	case FS_FT_RDMA_TX:
 	case FS_FT_PORT_SEL:
+	case FS_FT_RDMA_TRANSPORT_RX:
+	case FS_FT_RDMA_TRANSPORT_TX:
 		return mlx5_fs_cmd_get_fw_cmds();
 	default:
 		return mlx5_fs_cmd_get_stub_cmds();
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index 22dc23d991d2e..6163bc98d94a9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -1456,7 +1456,7 @@ mlx5_create_auto_grouped_flow_table(struct mlx5_flow_namespace *ns,
 	struct mlx5_flow_table *ft;
 	int autogroups_max_fte;
 
-	ft = mlx5_create_flow_table(ns, ft_attr);
+	ft = mlx5_create_vport_flow_table(ns, ft_attr, ft_attr->vport);
 	if (IS_ERR(ft))
 		return ft;
 
@@ -2764,9 +2764,9 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 }
 EXPORT_SYMBOL(mlx5_get_flow_namespace);
 
-struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
-							      enum mlx5_flow_namespace_type type,
-							      int vport)
+struct mlx5_flow_namespace *
+mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,
+			      enum mlx5_flow_namespace_type type, int vport_idx)
 {
 	struct mlx5_flow_steering *steering = dev->priv.steering;
 
@@ -2775,25 +2775,43 @@ struct mlx5_flow_namespace *mlx5_get_flow_vport_acl_namespace(struct mlx5_core_d
 
 	switch (type) {
 	case MLX5_FLOW_NAMESPACE_ESW_EGRESS:
-		if (vport >= steering->esw_egress_acl_vports)
+		if (vport_idx >= steering->esw_egress_acl_vports)
 			return NULL;
 		if (steering->esw_egress_root_ns &&
-		    steering->esw_egress_root_ns[vport])
-			return &steering->esw_egress_root_ns[vport]->ns;
+		    steering->esw_egress_root_ns[vport_idx])
+			return &steering->esw_egress_root_ns[vport_idx]->ns;
 		else
 			return NULL;
 	case MLX5_FLOW_NAMESPACE_ESW_INGRESS:
-		if (vport >= steering->esw_ingress_acl_vports)
+		if (vport_idx >= steering->esw_ingress_acl_vports)
 			return NULL;
 		if (steering->esw_ingress_root_ns &&
-		    steering->esw_ingress_root_ns[vport])
-			return &steering->esw_ingress_root_ns[vport]->ns;
+		    steering->esw_ingress_root_ns[vport_idx])
+			return &steering->esw_ingress_root_ns[vport_idx]->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX:
+		if (vport_idx >= steering->rdma_transport_rx_vports)
+			return NULL;
+		if (steering->rdma_transport_rx_root_ns &&
+		    steering->rdma_transport_rx_root_ns[vport_idx])
+			return &steering->rdma_transport_rx_root_ns[vport_idx]->ns;
+		else
+			return NULL;
+	case MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX:
+		if (vport_idx >= steering->rdma_transport_tx_vports)
+			return NULL;
+
+		if (steering->rdma_transport_tx_root_ns &&
+		    steering->rdma_transport_tx_root_ns[vport_idx])
+			return &steering->rdma_transport_tx_root_ns[vport_idx]->ns;
 		else
 			return NULL;
 	default:
 		return NULL;
 	}
 }
+EXPORT_SYMBOL(mlx5_get_flow_vport_namespace);
 
 static struct fs_prio *_fs_create_prio(struct mlx5_flow_namespace *ns,
 				       unsigned int prio,
@@ -3199,6 +3217,127 @@ static int init_rdma_tx_root_ns(struct mlx5_flow_steering *steering)
 	return err;
 }
 
+static int
+init_rdma_transport_rx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_transport_rx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_RX);
+	if (!steering->rdma_transport_rx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&steering->rdma_transport_rx_root_ns[vport_idx]->ns,
+			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
+	return PTR_ERR_OR_ZERO(prio);
+}
+
+static int
+init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering,
+				   int vport_idx)
+{
+	struct fs_prio *prio;
+
+	steering->rdma_transport_tx_root_ns[vport_idx] =
+		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_TX);
+	if (!steering->rdma_transport_tx_root_ns[vport_idx])
+		return -ENOMEM;
+
+	/* create 1 prio*/
+	prio = fs_create_prio(&steering->rdma_transport_tx_root_ns[vport_idx]->ns,
+			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
+	return PTR_ERR_OR_ZERO(prio);
+}
+
+static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_rx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_rx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_rx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_rx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_rx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+	kfree(steering->rdma_transport_rx_root_ns);
+	steering->rdma_transport_rx_root_ns = NULL;
+	return err;
+}
+
+static int init_rdma_transport_tx_root_ns(struct mlx5_flow_steering *steering)
+{
+	struct mlx5_core_dev *dev = steering->dev;
+	int total_vports;
+	int err;
+	int i;
+
+	/* In case eswitch not supported and working in legacy mode */
+	total_vports = mlx5_eswitch_get_total_vports(dev) ?: 1;
+
+	steering->rdma_transport_tx_root_ns =
+			kcalloc(total_vports,
+				sizeof(*steering->rdma_transport_tx_root_ns),
+				GFP_KERNEL);
+	if (!steering->rdma_transport_tx_root_ns)
+		return -ENOMEM;
+
+	for (i = 0; i < total_vports; i++) {
+		err = init_rdma_transport_tx_root_ns_one(steering, i);
+		if (err)
+			goto cleanup_root_ns;
+	}
+	steering->rdma_transport_tx_vports = total_vports;
+	return 0;
+
+cleanup_root_ns:
+	while (i--)
+		cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+	kfree(steering->rdma_transport_tx_root_ns);
+	steering->rdma_transport_tx_root_ns = NULL;
+	return err;
+}
+
+static void cleanup_rdma_transport_roots_ns(struct mlx5_flow_steering *steering)
+{
+	int i;
+
+	if (steering->rdma_transport_rx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_rx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_rx_root_ns[i]);
+
+		kfree(steering->rdma_transport_rx_root_ns);
+		steering->rdma_transport_rx_root_ns = NULL;
+	}
+
+	if (steering->rdma_transport_tx_root_ns) {
+		for (i = 0; i < steering->rdma_transport_tx_vports; i++)
+			cleanup_root_ns(steering->rdma_transport_tx_root_ns[i]);
+
+		kfree(steering->rdma_transport_tx_root_ns);
+		steering->rdma_transport_tx_root_ns = NULL;
+	}
+}
+
 /* FT and tc chains are stored in the same array so we can re-use the
  * mlx5_get_fdb_sub_ns() and tc api for FT chains.
  * When creating a new ns for each chain store it in the first available slot.
@@ -3631,6 +3770,7 @@ void mlx5_fs_core_cleanup(struct mlx5_core_dev *dev)
 	cleanup_root_ns(steering->rdma_rx_root_ns);
 	cleanup_root_ns(steering->rdma_tx_root_ns);
 	cleanup_root_ns(steering->egress_root_ns);
+	cleanup_rdma_transport_roots_ns(steering);
 
 	devl_params_unregister(priv_to_devlink(dev), mlx5_fs_params,
 			       ARRAY_SIZE(mlx5_fs_params));
@@ -3700,6 +3840,18 @@ int mlx5_fs_core_init(struct mlx5_core_dev *dev)
 			goto err;
 	}
 
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(dev, ft_support)) {
+		err = init_rdma_transport_rx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
+	if (MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(dev, ft_support)) {
+		err = init_rdma_transport_tx_root_ns(steering);
+		if (err)
+			goto err;
+	}
+
 	return 0;
 
 err:
@@ -3850,8 +4002,10 @@ mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type
 	struct mlx5_flow_namespace *ns;
 
 	if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS ||
-	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS)
-		ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0);
+	    ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX ||
+	    ns_type == MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX)
+		ns = mlx5_get_flow_vport_namespace(dev, ns_type, 0);
 	else
 		ns = mlx5_get_flow_namespace(dev, ns_type);
 	if (!ns)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index 20837e526679d..dbe747e938415 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -115,7 +115,9 @@ enum fs_flow_table_type {
 	FS_FT_PORT_SEL		= 0X9,
 	FS_FT_FDB_RX		= 0xa,
 	FS_FT_FDB_TX		= 0xb,
-	FS_FT_MAX_TYPE = FS_FT_FDB_TX,
+	FS_FT_RDMA_TRANSPORT_RX	= 0xd,
+	FS_FT_RDMA_TRANSPORT_TX	= 0xe,
+	FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX,
 };
 
 enum fs_flow_table_op_mod {
@@ -158,6 +160,10 @@ struct mlx5_flow_steering {
 	struct mlx5_flow_root_namespace	*port_sel_root_ns;
 	int esw_egress_acl_vports;
 	int esw_ingress_acl_vports;
+	struct mlx5_flow_root_namespace **rdma_transport_rx_root_ns;
+	struct mlx5_flow_root_namespace **rdma_transport_tx_root_ns;
+	int rdma_transport_rx_vports;
+	int rdma_transport_tx_vports;
 };
 
 struct fs_node {
@@ -434,7 +440,9 @@ struct mlx5_flow_root_namespace *find_root(struct fs_node *node);
 	(type == FS_FT_PORT_SEL) ? MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) :      \
 	(type == FS_FT_FDB_RX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
 	(type == FS_FT_FDB_TX) ? MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) :      \
-	(BUILD_BUG_ON_ZERO(FS_FT_FDB_TX != FS_FT_MAX_TYPE))\
+	(type == FS_FT_RDMA_TRANSPORT_RX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) :      \
+	(type == FS_FT_RDMA_TRANSPORT_TX) ? MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) :      \
+	(BUILD_BUG_ON_ZERO(FS_FT_RDMA_TRANSPORT_TX != FS_FT_MAX_TYPE))\
 	)
 
 #endif
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 0ae6d69c5221d..8fe56d0362c62 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1346,6 +1346,12 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap)
 
+#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) \
+	MLX5_CAP_ADV_RDMA(mdev, rdma_transport_rx_flow_table_properties.cap)
+
+#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) \
+	MLX5_CAP_ADV_RDMA(mdev, rdma_transport_tx_flow_table_properties.cap)
+
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 01cb72d68c231..fd62b2b1611d6 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,7 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
+#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 0
 #define MLX5_FS_MAX_POOL_SIZE BIT(30)
 
 enum mlx5_flow_destination_type {
@@ -110,6 +111,8 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC,
 	MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX,
+	MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX,
 };
 
 enum {
@@ -194,9 +197,9 @@ struct mlx5_flow_namespace *
 mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 			enum mlx5_flow_namespace_type type);
 struct mlx5_flow_namespace *
-mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
-				  enum mlx5_flow_namespace_type type,
-				  int vport);
+mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,
+			      enum mlx5_flow_namespace_type type,
+			      int vport_idx);
 
 struct mlx5_flow_table_attr {
 	int prio;
@@ -204,6 +207,7 @@ struct mlx5_flow_table_attr {
 	u32 level;
 	u32 flags;
 	u16 uid;
+	u16 vport;
 	struct mlx5_flow_table *next_ft;
 
 	struct {

From 058a6bec37c6c3b826158f6d26b75de43816a880 Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Fri, 7 Mar 2025 23:02:56 +0100
Subject: [PATCH 1858/2753] x86/microcode/AMD: Add some forgotten models to the
 SHA check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add some more forgotten models to the SHA check.

Fixes: 50cef76d5cb0 ("x86/microcode/AMD: Load only SHA256-checksummed patches")
Reported-by: Toralf Förster <toralf.foerster@gmx.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Toralf Förster <toralf.foerster@gmx.de>
Link: https://lore.kernel.org/r/20250307220256.11816-1-bp@kernel.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 95ac1c6a84fbe..c69b1bc454834 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -175,23 +175,29 @@ static bool need_sha_check(u32 cur_rev)
 {
 	switch (cur_rev >> 8) {
 	case 0x80012: return cur_rev <= 0x800126f; break;
+	case 0x80082: return cur_rev <= 0x800820f; break;
 	case 0x83010: return cur_rev <= 0x830107c; break;
 	case 0x86001: return cur_rev <= 0x860010e; break;
 	case 0x86081: return cur_rev <= 0x8608108; break;
 	case 0x87010: return cur_rev <= 0x8701034; break;
 	case 0x8a000: return cur_rev <= 0x8a0000a; break;
+	case 0xa0010: return cur_rev <= 0xa00107a; break;
 	case 0xa0011: return cur_rev <= 0xa0011da; break;
 	case 0xa0012: return cur_rev <= 0xa001243; break;
+	case 0xa0082: return cur_rev <= 0xa00820e; break;
 	case 0xa1011: return cur_rev <= 0xa101153; break;
 	case 0xa1012: return cur_rev <= 0xa10124e; break;
 	case 0xa1081: return cur_rev <= 0xa108109; break;
 	case 0xa2010: return cur_rev <= 0xa20102f; break;
 	case 0xa2012: return cur_rev <= 0xa201212; break;
+	case 0xa4041: return cur_rev <= 0xa404109; break;
+	case 0xa5000: return cur_rev <= 0xa500013; break;
 	case 0xa6012: return cur_rev <= 0xa60120a; break;
 	case 0xa7041: return cur_rev <= 0xa704109; break;
 	case 0xa7052: return cur_rev <= 0xa705208; break;
 	case 0xa7080: return cur_rev <= 0xa708009; break;
 	case 0xa70c0: return cur_rev <= 0xa70C009; break;
+	case 0xaa001: return cur_rev <= 0xaa00116; break;
 	case 0xaa002: return cur_rev <= 0xaa00218; break;
 	default: break;
 	}

From 4fa911d2d4cf7e932461eab929c2799a434be2b0 Mon Sep 17 00:00:00 2001
From: Hector Martin <marcan@marcan.st>
Date: Wed, 6 Nov 2024 08:54:02 +0100
Subject: [PATCH 1859/2753] MAINTAINERS: Add apple-spi driver & binding files

This Apple SPI controller is present on Apple ARM SoCs (t8103/t6000).

Splitting this change from the binding/driver commits to avoid merge
conflicts with other things touching this section, as usual.

Signed-off-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Janne Grunau <j@jannau.net>
Link: https://lore.kernel.org/r/20241106-asahi-spi-v5-3-e81a4f3a8e19@jannau.net
Signed-off-by: Sven Peter <sven@svenpeter.dev>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 8e0736dc2ee0e..b124b897f6783 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2236,6 +2236,7 @@ F:	Documentation/devicetree/bindings/pci/apple,pcie.yaml
 F:	Documentation/devicetree/bindings/pinctrl/apple,pinctrl.yaml
 F:	Documentation/devicetree/bindings/power/apple*
 F:	Documentation/devicetree/bindings/pwm/apple,s5l-fpwm.yaml
+F:	Documentation/devicetree/bindings/spi/apple,spi.yaml
 F:	Documentation/devicetree/bindings/watchdog/apple,wdt.yaml
 F:	arch/arm64/boot/dts/apple/
 F:	drivers/bluetooth/hci_bcm4377.c
@@ -2253,6 +2254,7 @@ F:	drivers/nvmem/apple-efuses.c
 F:	drivers/pinctrl/pinctrl-apple-gpio.c
 F:	drivers/pwm/pwm-apple.c
 F:	drivers/soc/apple/*
+F:	drivers/spi/spi-apple.c
 F:	drivers/watchdog/apple_wdt.c
 F:	include/dt-bindings/interrupt-controller/apple-aic.h
 F:	include/dt-bindings/pinctrl/apple.h

From 3a0d2facfa645ce2fca794a1105d0634ab722008 Mon Sep 17 00:00:00 2001
From: Neal Gompa <neal@gompa.dev>
Date: Mon, 3 Mar 2025 10:40:10 -0500
Subject: [PATCH 1860/2753] MAINTAINERS: Add myself (Neal Gompa) as a reviewer
 for ARM Apple support

As a member of the Asahi Linux project, I (Neal) have been involved in
reviewing the patches downstream as part of enabling the Fedora Asahi Remix
distribution for years and have recently been reviewing patches for upstream
submission as well.

This formalizes my role as a reviewer for ARM Apple system support patches.

Signed-off-by: Neal Gompa <neal@gompa.dev>
Acked-by: Sven Peter <sven@svenpeter.dev>
Acked-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Link: https://lore.kernel.org/r/20250303154012.1417088-1-neal@gompa.dev
Signed-off-by: Sven Peter <sven@svenpeter.dev>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index b124b897f6783..226991726733a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2212,6 +2212,7 @@ ARM/APPLE MACHINE SUPPORT
 M:	Sven Peter <sven@svenpeter.dev>
 M:	Janne Grunau <j@jannau.net>
 R:	Alyssa Rosenzweig <alyssa@rosenzweig.io>
+R:	Neal Gompa <neal@gompa.dev>
 L:	asahi@lists.linux.dev
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained

From 80e54e84911a923c40d7bee33a34c1b4be148d7a Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 9 Mar 2025 13:45:25 -1000
Subject: [PATCH 1861/2753] Linux 6.14-rc6

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 6a8e5be6b0043..1d6a9ec8a2ace 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From aed709355fd05ef747e1af24a1d5d78cd7feb81e Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Mon, 10 Feb 2025 11:34:41 -0800
Subject: [PATCH 1862/2753] drm/hyperv: Fix address space leak when Hyper-V DRM
 device is removed

When a Hyper-V DRM device is probed, the driver allocates MMIO space for
the vram, and maps it cacheable. If the device removed, or in the error
path for device probing, the MMIO space is released but no unmap is done.
Consequently the kernel address space for the mapping is leaked.

Fix this by adding iounmap() calls in the device removal path, and in the
error path during device probing.

Fixes: f1f63cbb705d ("drm/hyperv: Fix an error handling path in hyperv_vmbus_probe()")
Fixes: a0ab5abced55 ("drm/hyperv : Removing the restruction of VRAM allocation with PCI bar size")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Tested-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250210193441.2414-1-mhklinux@outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250210193441.2414-1-mhklinux@outlook.com>
---
 drivers/gpu/drm/hyperv/hyperv_drm_drv.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
index f59abfa7622ac..0d49f168a919d 100644
--- a/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
+++ b/drivers/gpu/drm/hyperv/hyperv_drm_drv.c
@@ -154,6 +154,7 @@ static int hyperv_vmbus_probe(struct hv_device *hdev,
 	return 0;
 
 err_free_mmio:
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 err_vmbus_close:
 	vmbus_close(hdev->channel);
@@ -172,6 +173,7 @@ static void hyperv_vmbus_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
+	iounmap(hv->vram);
 	vmbus_free_mmio(hv->mem->start, hv->fb_size);
 }
 

From 304386373007aaca9236a3f36afac0bbedcd2bf0 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Tue, 18 Feb 2025 15:01:30 -0800
Subject: [PATCH 1863/2753] fbdev: hyperv_fb: Fix hang in kdump kernel when on
 Hyper-V Gen 2 VMs

Gen 2 Hyper-V VMs boot via EFI and have a standard EFI framebuffer
device. When the kdump kernel runs in such a VM, loading the efifb
driver may hang because of accessing the framebuffer at the wrong
memory address.

The scenario occurs when the hyperv_fb driver in the original kernel
moves the framebuffer to a different MMIO address because of conflicts
with an already-running efifb or simplefb driver. The hyperv_fb driver
then informs Hyper-V of the change, which is allowed by the Hyper-V FB
VMBus device protocol. However, when the kexec command loads the kdump
kernel into crash memory via the kexec_file_load() system call, the
system call doesn't know the framebuffer has moved, and it sets up the
kdump screen_info using the original framebuffer address. The transition
to the kdump kernel does not go through the Hyper-V host, so Hyper-V
does not reset the framebuffer address like it would do on a reboot.
When efifb tries to run, it accesses a non-existent framebuffer
address, which traps to the Hyper-V host. After many such accesses,
the Hyper-V host thinks the guest is being malicious, and throttles
the guest to the point that it runs very slowly or appears to have hung.

When the kdump kernel is loaded into crash memory via the kexec_load()
system call, the problem does not occur. In this case, the kexec command
builds the screen_info table itself in user space from data returned
by the FBIOGET_FSCREENINFO ioctl against /dev/fb0, which gives it the
new framebuffer location.

This problem was originally reported in 2020 [1], resulting in commit
3cb73bc3fa2a ("hyperv_fb: Update screen_info after removing old
framebuffer"). This commit solved the problem by setting orig_video_isVGA
to 0, so the kdump kernel was unaware of the EFI framebuffer. The efifb
driver did not try to load, and no hang occurred. But in 2024, commit
c25a19afb81c ("fbdev/hyperv_fb: Do not clear global screen_info")
effectively reverted 3cb73bc3fa2a. Commit c25a19afb81c has no reference
to 3cb73bc3fa2a, so perhaps it was done without knowing the implications
that were reported with 3cb73bc3fa2a. In any case, as of commit
c25a19afb81c, the original problem came back again.

Interestingly, the hyperv_drm driver does not have this problem because
it never moves the framebuffer. The difference is that the hyperv_drm
driver removes any conflicting framebuffers *before* allocating an MMIO
address, while the hyperv_fb drivers removes conflicting framebuffers
*after* allocating an MMIO address. With the "after" ordering, hyperv_fb
may encounter a conflict and move the framebuffer to a different MMIO
address. But the conflict is essentially bogus because it is removed
a few lines of code later.

Rather than fix the problem with the approach from 2020 in commit
3cb73bc3fa2a, instead slightly reorder the steps in hyperv_fb so
conflicting framebuffers are removed before allocating an MMIO address.
Then the default framebuffer MMIO address should always be available, and
there's never any confusion about which framebuffer address the kdump
kernel should use -- it's always the original address provided by
the Hyper-V host. This approach is already used by the hyperv_drm
driver, and is consistent with the usage guidelines at the head of
the module with the function aperture_remove_conflicting_devices().

This approach also solves a related minor problem when kexec_load()
is used to load the kdump kernel. With current code, unbinding and
rebinding the hyperv_fb driver could result in the framebuffer moving
back to the default framebuffer address, because on the rebind there
are no conflicts. If such a move is done after the kdump kernel is
loaded with the new framebuffer address, at kdump time it could again
have the wrong address.

This problem and fix are described in terms of the kdump kernel, but
it can also occur with any kernel started via kexec.

See extensive discussion of the problem and solution at [2].

[1] https://lore.kernel.org/linux-hyperv/20201014092429.1415040-1-kasong@redhat.com/
[2] https://lore.kernel.org/linux-hyperv/BLAPR10MB521793485093FDB448F7B2E5FDE92@BLAPR10MB5217.namprd10.prod.outlook.com/

Reported-by: Thomas Tai <thomas.tai@oracle.com>
Fixes: c25a19afb81c ("fbdev/hyperv_fb: Do not clear global screen_info")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/20250218230130.3207-1-mhklinux@outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250218230130.3207-1-mhklinux@outlook.com>
---
 drivers/video/fbdev/hyperv_fb.c | 20 +++++++++++++-------
 1 file changed, 13 insertions(+), 7 deletions(-)

diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 363e4ccfcdb77..ce23d0ef5702a 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -989,6 +989,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 
 		base = pci_resource_start(pdev, 0);
 		size = pci_resource_len(pdev, 0);
+		aperture_remove_conflicting_devices(base, size, KBUILD_MODNAME);
 
 		/*
 		 * For Gen 1 VM, we can directly use the contiguous memory
@@ -1010,11 +1011,21 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 			goto getmem_done;
 		}
 		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
+	} else {
+		aperture_remove_all_conflicting_devices(KBUILD_MODNAME);
 	}
 
 	/*
-	 * Cannot use the contiguous physical memory.
-	 * Allocate mmio space for framebuffer.
+	 * Cannot use contiguous physical memory, so allocate MMIO space for
+	 * the framebuffer. At this point in the function, conflicting devices
+	 * that might have claimed the framebuffer MMIO space based on
+	 * screen_info.lfb_base must have already been removed so that
+	 * vmbus_allocate_mmio() does not allocate different MMIO space. If the
+	 * kdump image were to be loaded using kexec_file_load(), the
+	 * framebuffer location in the kdump image would be set from
+	 * screen_info.lfb_base at the time that kdump is enabled. If the
+	 * framebuffer has moved elsewhere, this could be the wrong location,
+	 * causing kdump to hang when efifb (for example) loads.
 	 */
 	dio_fb_size =
 		screen_width * screen_height * screen_depth / 8;
@@ -1051,11 +1062,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	info->screen_size = dio_fb_size;
 
 getmem_done:
-	if (base && size)
-		aperture_remove_conflicting_devices(base, size, KBUILD_MODNAME);
-	else
-		aperture_remove_all_conflicting_devices(KBUILD_MODNAME);
-
 	if (!gen2vm)
 		pci_dev_put(pdev);
 

From f5e728a50bb17336a20803dde488515b833ecd1d Mon Sep 17 00:00:00 2001
From: Saurabh Sengar <ssengar@linux.microsoft.com>
Date: Sat, 1 Mar 2025 08:16:30 -0800
Subject: [PATCH 1864/2753] fbdev: hyperv_fb: Simplify hvfb_putmem

The device object required in 'hvfb_release_phymem' function
for 'dma_free_coherent' can also be obtained from the 'info'
pointer, making 'hdev' parameter in 'hvfb_putmem' redundant.
Remove the unnecessary 'hdev' argument from 'hvfb_putmem'.

Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/1740845791-19977-2-git-send-email-ssengar@linux.microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <1740845791-19977-2-git-send-email-ssengar@linux.microsoft.com>
---
 drivers/video/fbdev/hyperv_fb.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index ce23d0ef5702a..9798a34ac571f 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -952,7 +952,7 @@ static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
 }
 
 /* Release contiguous physical memory */
-static void hvfb_release_phymem(struct hv_device *hdev,
+static void hvfb_release_phymem(struct device *device,
 				phys_addr_t paddr, unsigned int size)
 {
 	unsigned int order = get_order(size);
@@ -960,7 +960,7 @@ static void hvfb_release_phymem(struct hv_device *hdev,
 	if (order <= MAX_PAGE_ORDER)
 		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
 	else
-		dma_free_coherent(&hdev->device,
+		dma_free_coherent(device,
 				  round_up(size, PAGE_SIZE),
 				  phys_to_virt(paddr),
 				  paddr);
@@ -1080,7 +1080,7 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 }
 
 /* Release the framebuffer */
-static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
+static void hvfb_putmem(struct fb_info *info)
 {
 	struct hvfb_par *par = info->par;
 
@@ -1089,7 +1089,7 @@ static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
 		iounmap(par->mmio_vp);
 		vmbus_free_mmio(par->mem->start, screen_fb_size);
 	} else {
-		hvfb_release_phymem(hdev, info->fix.smem_start,
+		hvfb_release_phymem(info->device, info->fix.smem_start,
 				    screen_fb_size);
 	}
 
@@ -1203,7 +1203,7 @@ static int hvfb_probe(struct hv_device *hdev,
 
 error:
 	fb_deferred_io_cleanup(info);
-	hvfb_putmem(hdev, info);
+	hvfb_putmem(info);
 error2:
 	vmbus_close(hdev->channel);
 error1:
@@ -1232,7 +1232,7 @@ static void hvfb_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
-	hvfb_putmem(hdev, info);
+	hvfb_putmem(info);
 	framebuffer_release(info);
 }
 

From ea2f45ab0e53b255f72c85ccd99e2b394fc5fceb Mon Sep 17 00:00:00 2001
From: Saurabh Sengar <ssengar@linux.microsoft.com>
Date: Sat, 1 Mar 2025 08:16:31 -0800
Subject: [PATCH 1865/2753] fbdev: hyperv_fb: Allow graceful removal of
 framebuffer

When a Hyper-V framebuffer device is unbind, hyperv_fb driver tries to
release the framebuffer forcefully. If this framebuffer is in use it
produce the following WARN and hence this framebuffer is never released.

[   44.111220] WARNING: CPU: 35 PID: 1882 at drivers/video/fbdev/core/fb_info.c:70 framebuffer_release+0x2c/0x40
< snip >
[   44.111289] Call Trace:
[   44.111290]  <TASK>
[   44.111291]  ? show_regs+0x6c/0x80
[   44.111295]  ? __warn+0x8d/0x150
[   44.111298]  ? framebuffer_release+0x2c/0x40
[   44.111300]  ? report_bug+0x182/0x1b0
[   44.111303]  ? handle_bug+0x6e/0xb0
[   44.111306]  ? exc_invalid_op+0x18/0x80
[   44.111308]  ? asm_exc_invalid_op+0x1b/0x20
[   44.111311]  ? framebuffer_release+0x2c/0x40
[   44.111313]  ? hvfb_remove+0x86/0xa0 [hyperv_fb]
[   44.111315]  vmbus_remove+0x24/0x40 [hv_vmbus]
[   44.111323]  device_remove+0x40/0x80
[   44.111325]  device_release_driver_internal+0x20b/0x270
[   44.111327]  ? bus_find_device+0xb3/0xf0

Fix this by moving the release of framebuffer and assosiated memory
to fb_ops.fb_destroy function, so that framebuffer framework handles
it gracefully.

While we fix this, also replace manual registrations/unregistration of
framebuffer with devm_register_framebuffer.

Fixes: 68a2d20b79b1 ("drivers/video: add Hyper-V Synthetic Video Frame Buffer Driver")

Signed-off-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Michael Kelley <mhklinux@outlook.com>
Link: https://lore.kernel.org/r/1740845791-19977-3-git-send-email-ssengar@linux.microsoft.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <1740845791-19977-3-git-send-email-ssengar@linux.microsoft.com>
---
 drivers/video/fbdev/hyperv_fb.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/video/fbdev/hyperv_fb.c b/drivers/video/fbdev/hyperv_fb.c
index 9798a34ac571f..75338ffc703fb 100644
--- a/drivers/video/fbdev/hyperv_fb.c
+++ b/drivers/video/fbdev/hyperv_fb.c
@@ -282,6 +282,8 @@ static uint screen_depth;
 static uint screen_fb_size;
 static uint dio_fb_size; /* FB size for deferred IO */
 
+static void hvfb_putmem(struct fb_info *info);
+
 /* Send message to Hyper-V host */
 static inline int synthvid_send(struct hv_device *hdev,
 				struct synthvid_msg *msg)
@@ -862,6 +864,17 @@ static void hvfb_ops_damage_area(struct fb_info *info, u32 x, u32 y, u32 width,
 		hvfb_ondemand_refresh_throttle(par, x, y, width, height);
 }
 
+/*
+ * fb_ops.fb_destroy is called by the last put_fb_info() call at the end
+ * of unregister_framebuffer() or fb_release(). Do any cleanup related to
+ * framebuffer here.
+ */
+static void hvfb_destroy(struct fb_info *info)
+{
+	hvfb_putmem(info);
+	framebuffer_release(info);
+}
+
 /*
  * TODO: GEN1 codepaths allocate from system or DMA-able memory. Fix the
  *       driver to use the _SYSMEM_ or _DMAMEM_ helpers in these cases.
@@ -877,6 +890,7 @@ static const struct fb_ops hvfb_ops = {
 	.fb_set_par = hvfb_set_par,
 	.fb_setcolreg = hvfb_setcolreg,
 	.fb_blank = hvfb_blank,
+	.fb_destroy	= hvfb_destroy,
 };
 
 /* Get options from kernel paramenter "video=" */
@@ -1178,7 +1192,7 @@ static int hvfb_probe(struct hv_device *hdev,
 	if (ret)
 		goto error;
 
-	ret = register_framebuffer(info);
+	ret = devm_register_framebuffer(&hdev->device, info);
 	if (ret) {
 		pr_err("Unable to register framebuffer\n");
 		goto error;
@@ -1226,14 +1240,10 @@ static void hvfb_remove(struct hv_device *hdev)
 
 	fb_deferred_io_cleanup(info);
 
-	unregister_framebuffer(info);
 	cancel_delayed_work_sync(&par->dwork);
 
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
-
-	hvfb_putmem(info);
-	framebuffer_release(info);
 }
 
 static int hvfb_suspend(struct hv_device *hdev)

From 09beefefb57bbc3a06d98f319d85db4d719d7bcb Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Wed, 26 Feb 2025 12:06:06 -0800
Subject: [PATCH 1866/2753] x86/hyperv: Fix output argument to hypercall that
 changes page visibility

The hypercall in hv_mark_gpa_visibility() is invoked with an input
argument and an output argument. The output argument ostensibly returns
the number of pages that were processed. But in fact, the hypercall does
not provide any output, so the output argument is spurious.

The spurious argument is harmless because Hyper-V ignores it, but in the
interest of correctness and to avoid the potential for future problems,
remove it.

Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Reviewed-by: Nuno Das Neves <nunodasneves@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250226200612.2062-2-mhklinux@outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250226200612.2062-2-mhklinux@outlook.com>
---
 arch/x86/hyperv/ivm.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index dd68d9ad9b22c..ec7880271cf98 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -464,7 +464,6 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 			   enum hv_mem_host_visibility visibility)
 {
 	struct hv_gpa_range_for_visibility *input;
-	u16 pages_processed;
 	u64 hv_status;
 	unsigned long flags;
 
@@ -493,7 +492,7 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 	memcpy((void *)input->gpa_page_list, pfn, count * sizeof(*pfn));
 	hv_status = hv_do_rep_hypercall(
 			HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY, count,
-			0, input, &pages_processed);
+			0, input, NULL);
 	local_irq_restore(flags);
 
 	if (hv_result_success(hv_status))

From a2add513311b48cc924a699a8174db2c61ed5e8a Mon Sep 17 00:00:00 2001
From: Jeff LaBundy <jeff@labundy.com>
Date: Sun, 9 Mar 2025 20:29:59 -0500
Subject: [PATCH 1867/2753] Input: iqs7222 - preserve system status register

Some register groups reserve a byte at the end of their continuous
address space. Depending on the variant of silicon, this field may
share the same memory space as the lower byte of the system status
register (0x10).

In these cases, caching the reserved byte and writing it later may
effectively reset the device depending on what happened in between
the read and write operations.

Solve this problem by avoiding any access to this last byte within
offending register groups. This method replaces a workaround which
attempted to write the reserved byte with up-to-date contents, but
left a small window in which updates by the device could have been
clobbered.

Now that the driver does not touch these reserved bytes, the order
in which the device's registers are written no longer matters, and
they can be written in their natural order. The new method is also
much more generic, and can be more easily extended to new variants
of silicon with different register maps.

As part of this change, the register read and write functions must
be gently updated to support byte access instead of word access.

Fixes: 2e70ef525b73 ("Input: iqs7222 - acknowledge reset before writing registers")
Signed-off-by: Jeff LaBundy <jeff@labundy.com>
Link: https://lore.kernel.org/r/Z85Alw+d9EHKXx2e@nixie71
Cc: stable@vger.kernel.org
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 drivers/input/misc/iqs7222.c | 50 ++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 28 deletions(-)

diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c
index 22022d11470db..80b917944b51e 100644
--- a/drivers/input/misc/iqs7222.c
+++ b/drivers/input/misc/iqs7222.c
@@ -100,11 +100,11 @@ enum iqs7222_reg_key_id {
 
 enum iqs7222_reg_grp_id {
 	IQS7222_REG_GRP_STAT,
-	IQS7222_REG_GRP_FILT,
 	IQS7222_REG_GRP_CYCLE,
 	IQS7222_REG_GRP_GLBL,
 	IQS7222_REG_GRP_BTN,
 	IQS7222_REG_GRP_CHAN,
+	IQS7222_REG_GRP_FILT,
 	IQS7222_REG_GRP_SLDR,
 	IQS7222_REG_GRP_TPAD,
 	IQS7222_REG_GRP_GPIO,
@@ -286,6 +286,7 @@ static const struct iqs7222_event_desc iqs7222_tp_events[] = {
 
 struct iqs7222_reg_grp_desc {
 	u16 base;
+	u16 val_len;
 	int num_row;
 	int num_col;
 };
@@ -342,6 +343,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAC00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -400,6 +402,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAC00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -454,6 +457,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xC400,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -496,6 +500,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xC400,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -543,6 +548,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAA00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -600,6 +606,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAA00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -656,6 +663,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -712,6 +720,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -768,6 +777,7 @@ static const struct iqs7222_dev_desc iqs7222_devs[] = {
 			},
 			[IQS7222_REG_GRP_FILT] = {
 				.base = 0xAE00,
+				.val_len = 3,
 				.num_row = 1,
 				.num_col = 2,
 			},
@@ -1604,7 +1614,7 @@ static int iqs7222_force_comms(struct iqs7222_private *iqs7222)
 }
 
 static int iqs7222_read_burst(struct iqs7222_private *iqs7222,
-			      u16 reg, void *val, u16 num_val)
+			      u16 reg, void *val, u16 val_len)
 {
 	u8 reg_buf[sizeof(__be16)];
 	int ret, i;
@@ -1619,7 +1629,7 @@ static int iqs7222_read_burst(struct iqs7222_private *iqs7222,
 		{
 			.addr = client->addr,
 			.flags = I2C_M_RD,
-			.len = num_val * sizeof(__le16),
+			.len = val_len,
 			.buf = (u8 *)val,
 		},
 	};
@@ -1675,7 +1685,7 @@ static int iqs7222_read_word(struct iqs7222_private *iqs7222, u16 reg, u16 *val)
 	__le16 val_buf;
 	int error;
 
-	error = iqs7222_read_burst(iqs7222, reg, &val_buf, 1);
+	error = iqs7222_read_burst(iqs7222, reg, &val_buf, sizeof(val_buf));
 	if (error)
 		return error;
 
@@ -1685,10 +1695,9 @@ static int iqs7222_read_word(struct iqs7222_private *iqs7222, u16 reg, u16 *val)
 }
 
 static int iqs7222_write_burst(struct iqs7222_private *iqs7222,
-			       u16 reg, const void *val, u16 num_val)
+			       u16 reg, const void *val, u16 val_len)
 {
 	int reg_len = reg > U8_MAX ? sizeof(reg) : sizeof(u8);
-	int val_len = num_val * sizeof(__le16);
 	int msg_len = reg_len + val_len;
 	int ret, i;
 	struct i2c_client *client = iqs7222->client;
@@ -1747,7 +1756,7 @@ static int iqs7222_write_word(struct iqs7222_private *iqs7222, u16 reg, u16 val)
 {
 	__le16 val_buf = cpu_to_le16(val);
 
-	return iqs7222_write_burst(iqs7222, reg, &val_buf, 1);
+	return iqs7222_write_burst(iqs7222, reg, &val_buf, sizeof(val_buf));
 }
 
 static int iqs7222_ati_trigger(struct iqs7222_private *iqs7222)
@@ -1831,30 +1840,14 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 
 	/*
 	 * Acknowledge reset before writing any registers in case the device
-	 * suffers a spurious reset during initialization. Because this step
-	 * may change the reserved fields of the second filter beta register,
-	 * its cache must be updated.
-	 *
-	 * Writing the second filter beta register, in turn, may clobber the
-	 * system status register. As such, the filter beta register pair is
-	 * written first to protect against this hazard.
+	 * suffers a spurious reset during initialization.
 	 */
 	if (dir == WRITE) {
-		u16 reg = dev_desc->reg_grps[IQS7222_REG_GRP_FILT].base + 1;
-		u16 filt_setup;
-
 		error = iqs7222_write_word(iqs7222, IQS7222_SYS_SETUP,
 					   iqs7222->sys_setup[0] |
 					   IQS7222_SYS_SETUP_ACK_RESET);
 		if (error)
 			return error;
-
-		error = iqs7222_read_word(iqs7222, reg, &filt_setup);
-		if (error)
-			return error;
-
-		iqs7222->filt_setup[1] &= GENMASK(7, 0);
-		iqs7222->filt_setup[1] |= (filt_setup & ~GENMASK(7, 0));
 	}
 
 	/*
@@ -1883,6 +1876,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 		int num_col = dev_desc->reg_grps[i].num_col;
 		u16 reg = dev_desc->reg_grps[i].base;
 		__le16 *val_buf;
+		u16 val_len = dev_desc->reg_grps[i].val_len ? : num_col * sizeof(*val_buf);
 		u16 *val;
 
 		if (!num_col)
@@ -1900,7 +1894,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 			switch (dir) {
 			case READ:
 				error = iqs7222_read_burst(iqs7222, reg,
-							   val_buf, num_col);
+							   val_buf, val_len);
 				for (k = 0; k < num_col; k++)
 					val[k] = le16_to_cpu(val_buf[k]);
 				break;
@@ -1909,7 +1903,7 @@ static int iqs7222_dev_init(struct iqs7222_private *iqs7222, int dir)
 				for (k = 0; k < num_col; k++)
 					val_buf[k] = cpu_to_le16(val[k]);
 				error = iqs7222_write_burst(iqs7222, reg,
-							    val_buf, num_col);
+							    val_buf, val_len);
 				break;
 
 			default:
@@ -1962,7 +1956,7 @@ static int iqs7222_dev_info(struct iqs7222_private *iqs7222)
 	int error, i;
 
 	error = iqs7222_read_burst(iqs7222, IQS7222_PROD_NUM, dev_id,
-				   ARRAY_SIZE(dev_id));
+				   sizeof(dev_id));
 	if (error)
 		return error;
 
@@ -2915,7 +2909,7 @@ static int iqs7222_report(struct iqs7222_private *iqs7222)
 	__le16 status[IQS7222_MAX_COLS_STAT];
 
 	error = iqs7222_read_burst(iqs7222, IQS7222_SYS_STATUS, status,
-				   num_stat);
+				   num_stat * sizeof(*status));
 	if (error)
 		return error;
 

From f550694e88b7b13b647777f889e03e544d9db60c Mon Sep 17 00:00:00 2001
From: Yael Chemla <ychemla@nvidia.com>
Date: Sun, 9 Mar 2025 20:41:37 +0200
Subject: [PATCH 1868/2753] net/mlx5: Add IFC bits for PPCNT recovery counters
 group

Add recovery counters group layout of PPCNT (Ports Performance Counters
Register). This group counts recovery events per link. Also add the
corresponding bit in PCAM to indicate this group is supported.

Signed-off-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741545697-23041-1-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/device.h   |  1 +
 include/linux/mlx5/mlx5_ifc.h | 11 ++++++++++-
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 8fe56d0362c62..904804e995aa8 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -1517,6 +1517,7 @@ enum {
 	MLX5_PHYSICAL_LAYER_COUNTERS_GROUP    = 0x12,
 	MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13,
 	MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16,
+	MLX5_PHYSICAL_LAYER_RECOVERY_GROUP    = 0x1a,
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
 	MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21,
 };
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index fea8af42f9548..2c09df4ee5742 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2645,6 +2645,12 @@ struct mlx5_ifc_field_select_802_1qau_rp_bits {
 	u8         field_select_8021qaurp[0x20];
 };
 
+struct mlx5_ifc_phys_layer_recovery_cntrs_bits {
+	u8         total_successful_recovery_events[0x20];
+
+	u8         reserved_at_20[0x7a0];
+};
+
 struct mlx5_ifc_phys_layer_cntrs_bits {
 	u8         time_since_last_clear_high[0x20];
 
@@ -4846,6 +4852,7 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout;
 	struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs;
 	struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs;
+	struct mlx5_ifc_phys_layer_recovery_cntrs_bits phys_layer_recovery_cntrs;
 	u8         reserved_at_0[0x7c0];
 };
 
@@ -10584,7 +10591,9 @@ struct mlx5_ifc_mtutc_reg_bits {
 };
 
 struct mlx5_ifc_pcam_enhanced_features_bits {
-	u8         reserved_at_0[0x1d];
+	u8         reserved_at_0[0x10];
+	u8         ppcnt_recovery_counters[0x1];
+	u8         reserved_at_11[0xc];
 	u8         fec_200G_per_lane_in_pplm[0x1];
 	u8         reserved_at_1e[0x2a];
 	u8         fec_100G_per_lane_in_pplm[0x1];

From 823869e1e61607ab0d433de3c8abed221dc80a5e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Thu, 6 Mar 2025 08:46:57 +0000
Subject: [PATCH 1869/2753] afs: Fix afs_atcell_get_link() to handle RCU
 pathwalk

The ->get_link() method may be entered under RCU pathwalk conditions (in
which case, the dentry pointer is NULL).  This is not taken account of by
afs_atcell_get_link() and lockdep will complain when it tries to lock an
rwsem.

Fix this by marking net->ws_cell as __rcu and using RCU access macros on it
and by making afs_atcell_get_link() just return a pointer to the name in
RCU pathwalk without taking net->cells_lock or a ref on the cell as RCU
will protect the name storage (the cell is already freed via call_rcu()).

Fixes: 30bca65bbbae ("afs: Make /afs/@cell and /afs/.@cell symlinks")
Reported-by: Alexander Viro <viro@zeniv.linux.org.uk>
Signed-off-by: David Howells <dhowells@redhat.com>
cc: Marc Dionne <marc.dionne@auristor.com>
cc: linux-afs@lists.infradead.org
cc: linux-fsdevel@vger.kernel.org
Link: https://lore.kernel.org/r/20250310094206.801057-2-dhowells@redhat.com/ # v4
---
 fs/afs/cell.c     | 11 ++++++-----
 fs/afs/dynroot.c  | 15 +++++++++++++--
 fs/afs/internal.h |  2 +-
 fs/afs/proc.c     |  4 ++--
 4 files changed, 22 insertions(+), 10 deletions(-)

diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index cee42646736c8..96a6781f36530 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -64,7 +64,8 @@ static struct afs_cell *afs_find_cell_locked(struct afs_net *net,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	if (!name) {
-		cell = net->ws_cell;
+		cell = rcu_dereference_protected(net->ws_cell,
+						 lockdep_is_held(&net->cells_lock));
 		if (!cell)
 			return ERR_PTR(-EDESTADDRREQ);
 		goto found;
@@ -388,8 +389,8 @@ int afs_cell_init(struct afs_net *net, const char *rootcell)
 	/* install the new cell */
 	down_write(&net->cells_lock);
 	afs_see_cell(new_root, afs_cell_trace_see_ws);
-	old_root = net->ws_cell;
-	net->ws_cell = new_root;
+	old_root = rcu_replace_pointer(net->ws_cell, new_root,
+				       lockdep_is_held(&net->cells_lock));
 	up_write(&net->cells_lock);
 
 	afs_unuse_cell(net, old_root, afs_cell_trace_unuse_ws);
@@ -945,8 +946,8 @@ void afs_cell_purge(struct afs_net *net)
 	_enter("");
 
 	down_write(&net->cells_lock);
-	ws = net->ws_cell;
-	net->ws_cell = NULL;
+	ws = rcu_replace_pointer(net->ws_cell, NULL,
+				 lockdep_is_held(&net->cells_lock));
 	up_write(&net->cells_lock);
 	afs_unuse_cell(net, ws, afs_cell_trace_unuse_ws);
 
diff --git a/fs/afs/dynroot.c b/fs/afs/dynroot.c
index d8bf52f77d930..008698d706caa 100644
--- a/fs/afs/dynroot.c
+++ b/fs/afs/dynroot.c
@@ -314,12 +314,23 @@ static const char *afs_atcell_get_link(struct dentry *dentry, struct inode *inod
 	const char *name;
 	bool dotted = vnode->fid.vnode == 3;
 
-	if (!net->ws_cell)
+	if (!dentry) {
+		/* We're in RCU-pathwalk. */
+		cell = rcu_dereference(net->ws_cell);
+		if (dotted)
+			name = cell->name - 1;
+		else
+			name = cell->name;
+		/* Shouldn't need to set a delayed call. */
+		return name;
+	}
+
+	if (!rcu_access_pointer(net->ws_cell))
 		return ERR_PTR(-ENOENT);
 
 	down_read(&net->cells_lock);
 
-	cell = net->ws_cell;
+	cell = rcu_dereference_protected(net->ws_cell, lockdep_is_held(&net->cells_lock));
 	if (dotted)
 		name = cell->name - 1;
 	else
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 90f407774a9a1..df30bd62da79e 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -287,7 +287,7 @@ struct afs_net {
 
 	/* Cell database */
 	struct rb_root		cells;
-	struct afs_cell		*ws_cell;
+	struct afs_cell __rcu	*ws_cell;
 	struct work_struct	cells_manager;
 	struct timer_list	cells_timer;
 	atomic_t		cells_outstanding;
diff --git a/fs/afs/proc.c b/fs/afs/proc.c
index e7614f4f30c21..12c88d8be3fe8 100644
--- a/fs/afs/proc.c
+++ b/fs/afs/proc.c
@@ -206,7 +206,7 @@ static int afs_proc_rootcell_show(struct seq_file *m, void *v)
 
 	net = afs_seq2net_single(m);
 	down_read(&net->cells_lock);
-	cell = net->ws_cell;
+	cell = rcu_dereference_protected(net->ws_cell, lockdep_is_held(&net->cells_lock));
 	if (cell)
 		seq_printf(m, "%s\n", cell->name);
 	up_read(&net->cells_lock);
@@ -242,7 +242,7 @@ static int afs_proc_rootcell_write(struct file *file, char *buf, size_t size)
 
 	ret = -EEXIST;
 	inode_lock(file_inode(file));
-	if (!net->ws_cell)
+	if (!rcu_access_pointer(net->ws_cell))
 		ret = afs_cell_init(net, buf);
 	else
 		printk("busy\n");

From 65be5c95d08eedda570a6c888a12384c77fe7614 Mon Sep 17 00:00:00 2001
From: Vladis Dronov <vdronov@redhat.com>
Date: Sun, 9 Mar 2025 18:22:16 +0100
Subject: [PATCH 1870/2753] x86/sgx: Warn explicitly if X86_FEATURE_SGX_LC is
 not enabled

The kernel requires X86_FEATURE_SGX_LC to be able to create SGX enclaves,
not just X86_FEATURE_SGX.

There is quite a number of hardware which has X86_FEATURE_SGX but not
X86_FEATURE_SGX_LC. A kernel running on such hardware does not create
the /dev/sgx_enclave file and does so silently.

Explicitly warn if X86_FEATURE_SGX_LC is not enabled to properly notify
users that the kernel disabled the SGX driver.

The X86_FEATURE_SGX_LC, a.k.a. SGX Launch Control, is a CPU feature
that enables LE (Launch Enclave) hash MSRs to be writable (with
additional opt-in required in the 'feature control' MSR) when running
enclaves, i.e. using a custom root key rather than the Intel proprietary
key for enclave signing.

I've hit this issue myself and have spent some time researching where
my /dev/sgx_enclave file went on SGX-enabled hardware.

Related links:

  https://github.com/intel/linux-sgx/issues/837
  https://patchwork.kernel.org/project/platform-driver-x86/patch/20180827185507.17087-3-jarkko.sakkinen@linux.intel.com/

[ mingo: Made the error message a bit more verbose, and added other cases
         where the kernel fails to create the /dev/sgx_enclave device node. ]

Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Kai Huang <kai.huang@intel.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Sean Christopherson <sean.j.christopherson@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250309172215.21777-2-vdronov@redhat.com
---
 arch/x86/kernel/cpu/sgx/driver.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/driver.c b/arch/x86/kernel/cpu/sgx/driver.c
index 22b65a5f5ec6c..7f8d1e11dbee2 100644
--- a/arch/x86/kernel/cpu/sgx/driver.c
+++ b/arch/x86/kernel/cpu/sgx/driver.c
@@ -150,13 +150,15 @@ int __init sgx_drv_init(void)
 	u64 xfrm_mask;
 	int ret;
 
-	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC))
+	if (!cpu_feature_enabled(X86_FEATURE_SGX_LC)) {
+		pr_info("SGX disabled: SGX launch control CPU feature is not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
+	}
 
 	cpuid_count(SGX_CPUID, 0, &eax, &ebx, &ecx, &edx);
 
 	if (!(eax & 1))  {
-		pr_err("SGX disabled: SGX1 instruction support not available.\n");
+		pr_info("SGX disabled: SGX1 instruction support not available, /dev/sgx_enclave disabled.\n");
 		return -ENODEV;
 	}
 
@@ -173,8 +175,10 @@ int __init sgx_drv_init(void)
 	}
 
 	ret = misc_register(&sgx_dev_enclave);
-	if (ret)
+	if (ret) {
+		pr_info("SGX disabled: Unable to register the /dev/sgx_enclave driver (%d).\n", ret);
 		return ret;
+	}
 
 	return 0;
 }

From 247fba13416af65b155949bae582d55c310f58b6 Mon Sep 17 00:00:00 2001
From: Bard Liao <yung-chuan.liao@linux.intel.com>
Date: Mon, 10 Mar 2025 16:04:40 +0800
Subject: [PATCH 1871/2753] ASoC: rt722-sdca: add missing readable registers

SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT_FU15,
RT722_SDCA_CTL_FU_CH_GAIN, CH_01) ... SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY,
RT722_SDCA_ENT_FU15, RT722_SDCA_CTL_FU_CH_GAIN, CH_04) are used by the
"FU15 Boost Volume" control, but not marked as readable.
And the mbq size are 2 for those registers.

Fixes: 7f5d6036ca005 ("ASoC: rt722-sdca: Add RT722 SDCA driver")
Signed-off-by: Bard Liao <yung-chuan.liao@linux.intel.com>
Reviewed-by: Ranjani Sridharan <ranjani.sridharan@linux.intel.com>
Reviewed-by: Shuming Fan <shumingf@realtek.com>
Link: https://patch.msgid.link/20250310080440.58797-1-yung-chuan.liao@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/rt722-sdca-sdw.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/sound/soc/codecs/rt722-sdca-sdw.c b/sound/soc/codecs/rt722-sdca-sdw.c
index 25fc13687bc83..4d3043627bd04 100644
--- a/sound/soc/codecs/rt722-sdca-sdw.c
+++ b/sound/soc/codecs/rt722-sdca-sdw.c
@@ -86,6 +86,10 @@ static bool rt722_sdca_mbq_readable_register(struct device *dev, unsigned int re
 	case 0x6100067:
 	case 0x6100070 ... 0x610007c:
 	case 0x6100080:
+	case SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT_FU15, RT722_SDCA_CTL_FU_CH_GAIN,
+			  CH_01) ...
+	     SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT_FU15, RT722_SDCA_CTL_FU_CH_GAIN,
+			  CH_04):
 	case SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT_USER_FU1E, RT722_SDCA_CTL_FU_VOLUME,
 			CH_01):
 	case SDW_SDCA_CTL(FUNC_NUM_MIC_ARRAY, RT722_SDCA_ENT_USER_FU1E, RT722_SDCA_CTL_FU_VOLUME,

From f3fa0e40df175acd60b71036b9a1fd62310aec03 Mon Sep 17 00:00:00 2001
From: Yafang Shao <laoar.shao@gmail.com>
Date: Wed, 5 Feb 2025 11:24:38 +0800
Subject: [PATCH 1872/2753] sched/clock: Don't define sched_clock_irqtime as
 static key
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The sched_clock_irqtime was defined as a static key in:

  8722903cbb8f ("sched: Define sched_clock_irqtime as static key")

However, this change introduces a 'sleeping in atomic context' warning:

	arch/x86/kernel/tsc.c:1214 mark_tsc_unstable()
	warn: sleeping in atomic context

As analyzed by Dan, the affected code path is as follows:

vcpu_load() <- disables preempt
-> kvm_arch_vcpu_load()
   -> mark_tsc_unstable() <- sleeps

virt/kvm/kvm_main.c
   166  void vcpu_load(struct kvm_vcpu *vcpu)
   167  {
   168          int cpu = get_cpu();
                          ^^^^^^^^^^
This get_cpu() disables preemption.

   169
   170          __this_cpu_write(kvm_running_vcpu, vcpu);
   171          preempt_notifier_register(&vcpu->preempt_notifier);
   172          kvm_arch_vcpu_load(vcpu, cpu);
   173          put_cpu();
   174  }

arch/x86/kvm/x86.c
  4979          if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
  4980                  s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
  4981                                  rdtsc() - vcpu->arch.last_host_tsc;
  4982                  if (tsc_delta < 0)
  4983                          mark_tsc_unstable("KVM discovered backwards TSC");

arch/x86/kernel/tsc.c
    1206 void mark_tsc_unstable(char *reason)
    1207 {
    1208         if (tsc_unstable)
    1209                 return;
    1210
    1211         tsc_unstable = 1;
    1212         if (using_native_sched_clock())
    1213                 clear_sched_clock_stable();
--> 1214         disable_sched_clock_irqtime();
                 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
kernel/jump_label.c
   245  void static_key_disable(struct static_key *key)
   246  {
   247          cpus_read_lock();
                ^^^^^^^^^^^^^^^^
This lock has a might_sleep() in it which triggers the static checker
warning.

   248          static_key_disable_cpuslocked(key);
   249          cpus_read_unlock();
   250  }

Let revert this change for now as {disable,enable}_sched_clock_irqtime
are used in many places, as pointed out by Sean, including the following:

The code path in clocksource_watchdog():

  clocksource_watchdog()
  |
  -> spin_lock(&watchdog_lock);
     |
     -> __clocksource_unstable()
        |
        -> clocksource.mark_unstable() == tsc_cs_mark_unstable()
           |
           -> disable_sched_clock_irqtime()

And the code path in sched_clock_register():

	/* Cannot register a sched_clock with interrupts on */
	local_irq_save(flags);

	...

	/* Enable IRQ time accounting if we have a fast enough sched_clock() */
	if (irqtime > 0 || (irqtime == -1 && rate >= 1000000))
		enable_sched_clock_irqtime();

	local_irq_restore(flags);

[ lkp@intel.com: reported a build error in the prev version ]
[ mingo: cherry-picked it over into sched/urgent ]

Closes: https://lore.kernel.org/kvm/37a79ba3-9ce0-479c-a5b0-2bd75d573ed3@stanley.mountain/
Fixes: 8722903cbb8f ("sched: Define sched_clock_irqtime as static key")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Dan Carpenter <dan.carpenter@linaro.org>
Debugged-by: Sean Christopherson <seanjc@google.com>
Debugged-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20250205032438.14668-1-laoar.shao@gmail.com
---
 kernel/sched/cputime.c | 8 ++++----
 kernel/sched/sched.h   | 4 ++--
 2 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5d9143dd08791..6dab4854c6c08 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -9,8 +9,6 @@
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 
-DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
-
 /*
  * There are no locks covering percpu hardirq/softirq time.
  * They are only modified in vtime_account, on corresponding CPU
@@ -24,14 +22,16 @@ DEFINE_STATIC_KEY_FALSE(sched_clock_irqtime);
  */
 DEFINE_PER_CPU(struct irqtime, cpu_irqtime);
 
+int sched_clock_irqtime;
+
 void enable_sched_clock_irqtime(void)
 {
-	static_branch_enable(&sched_clock_irqtime);
+	sched_clock_irqtime = 1;
 }
 
 void disable_sched_clock_irqtime(void)
 {
-	static_branch_disable(&sched_clock_irqtime);
+	sched_clock_irqtime = 0;
 }
 
 static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8512a9fb0229..023b844159c94 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3259,11 +3259,11 @@ struct irqtime {
 };
 
 DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-DECLARE_STATIC_KEY_FALSE(sched_clock_irqtime);
+extern int sched_clock_irqtime;
 
 static inline int irqtime_enabled(void)
 {
-	return static_branch_likely(&sched_clock_irqtime);
+	return sched_clock_irqtime;
 }
 
 /*

From e3e89178a9f4a80092578af3ff3c8478f9187d59 Mon Sep 17 00:00:00 2001
From: Florent Revest <revest@chromium.org>
Date: Mon, 10 Mar 2025 15:42:43 +0100
Subject: [PATCH 1873/2753] x86/microcode/AMD: Fix out-of-bounds on systems
 with CPU-less NUMA nodes

Currently, load_microcode_amd() iterates over all NUMA nodes, retrieves their
CPU masks and unconditionally accesses per-CPU data for the first CPU of each
mask.

According to Documentation/admin-guide/mm/numaperf.rst:

  "Some memory may share the same node as a CPU, and others are provided as
  memory only nodes."

Therefore, some node CPU masks may be empty and wouldn't have a "first CPU".

On a machine with far memory (and therefore CPU-less NUMA nodes):
- cpumask_of_node(nid) is 0
- cpumask_first(0) is CONFIG_NR_CPUS
- cpu_data(CONFIG_NR_CPUS) accesses the cpu_info per-CPU array at an
  index that is 1 out of bounds

This does not have any security implications since flashing microcode is
a privileged operation but I believe this has reliability implications by
potentially corrupting memory while flashing a microcode update.

When booting with CONFIG_UBSAN_BOUNDS=y on an AMD machine that flashes
a microcode update. I get the following splat:

  UBSAN: array-index-out-of-bounds in arch/x86/kernel/cpu/microcode/amd.c:X:Y
  index 512 is out of range for type 'unsigned long[512]'
  [...]
  Call Trace:
   dump_stack
   __ubsan_handle_out_of_bounds
   load_microcode_amd
   request_microcode_amd
   reload_store
   kernfs_fop_write_iter
   vfs_write
   ksys_write
   do_syscall_64
   entry_SYSCALL_64_after_hwframe

Change the loop to go over only NUMA nodes which have CPUs before determining
whether the first CPU on the respective node needs microcode update.

  [ bp: Massage commit message, fix typo. ]

Fixes: 7ff6edf4fef3 ("x86/microcode/AMD: Fix mixed steppings support")
Signed-off-by: Florent Revest <revest@chromium.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250310144243.861978-1-revest@chromium.org
---
 arch/x86/kernel/cpu/microcode/amd.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index c69b1bc454834..138689b8e1d83 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -1074,7 +1074,7 @@ static enum ucode_state load_microcode_amd(u8 family, const u8 *data, size_t siz
 	if (ret != UCODE_OK)
 		return ret;
 
-	for_each_node(nid) {
+	for_each_node_with_cpus(nid) {
 		cpu = cpumask_first(cpumask_of_node(nid));
 		c = &cpu_data(cpu);
 

From 10c7988418d8f759ba70c4a558961e0bfa74647f Mon Sep 17 00:00:00 2001
From: Tejas Upadhyay <tejas.upadhyay@intel.com>
Date: Thu, 6 Mar 2025 18:42:11 +0530
Subject: [PATCH 1874/2753] drm/xe: Release guc ids before cancelling work

A GT resets can be occurring in parallel while cancelling
work in async call  which can requeue these workers.
to avoid that, lets first release guc ids and then cancel
work so they don't requeued.

Fixes: 8ae8a2e8dd21 ("drm/xe: Long running job update")
Fixes: 12c2f962fe71 ("drm/xe: cancel pending job timer before freeing scheduler")
Signed-off-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Suggested-by: Matthew Brost <matthew.brost@intel.com>
Reviewed-by: Matthew Brost <matthew.brost@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306131211.975503-1-tejas.upadhyay@intel.com
Signed-off-by: Lucas De Marchi <lucas.demarchi@intel.com>
(cherry picked from commit 8e8d76f62329127b31c64a034b052fb9e30e92af)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_submit.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
index b6a2dd742ebdc..1a5fe4822a62e 100644
--- a/drivers/gpu/drm/xe/xe_guc_submit.c
+++ b/drivers/gpu/drm/xe/xe_guc_submit.c
@@ -1246,11 +1246,11 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
 	xe_pm_runtime_get(guc_to_xe(guc));
 	trace_xe_exec_queue_destroy(q);
 
+	release_guc_id(guc, q);
 	if (xe_exec_queue_is_lr(q))
 		cancel_work_sync(&ge->lr_tdr);
 	/* Confirm no work left behind accessing device structures */
 	cancel_delayed_work_sync(&ge->sched.base.work_tdr);
-	release_guc_id(guc, q);
 	xe_sched_entity_fini(&ge->entity);
 	xe_sched_fini(&ge->sched);
 

From 9106713bd2ab0cacd380cda0d3f0219f2e488086 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Thomas=20Hellstr=C3=B6m?= <thomas.hellstrom@linux.intel.com>
Date: Fri, 7 Mar 2025 11:01:09 +0100
Subject: [PATCH 1875/2753] drm/xe/userptr: Fix an incorrect assert
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The assert incorrectly checks the total length processed which
can in fact be greater than the number of pages. Fix.

Fixes: 0a98219bcc96 ("drm/xe/hmm: Don't dereference struct page pointers without notifier lock")
Cc: Matthew Auld <matthew.auld@intel.com>
Cc: Matthew Brost <matthew.brost@intel.com>
Signed-off-by: Thomas Hellström <thomas.hellstrom@linux.intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307100109.21397-1-thomas.hellstrom@linux.intel.com
(cherry picked from commit 70e5043ba85eae199b232e39921abd706b5c1fa4)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_hmm.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_hmm.c b/drivers/gpu/drm/xe/xe_hmm.c
index 392102515f3d8..c3cc0fa105e84 100644
--- a/drivers/gpu/drm/xe/xe_hmm.c
+++ b/drivers/gpu/drm/xe/xe_hmm.c
@@ -138,13 +138,17 @@ static int xe_build_sg(struct xe_device *xe, struct hmm_range *range,
 		i += size;
 
 		if (unlikely(j == st->nents - 1)) {
+			xe_assert(xe, i >= npages);
 			if (i > npages)
 				size -= (i - npages);
+
 			sg_mark_end(sgl);
+		} else {
+			xe_assert(xe, i < npages);
 		}
+
 		sg_set_page(sgl, page, size << PAGE_SHIFT, 0);
 	}
-	xe_assert(xe, i == npages);
 
 	return dma_map_sgtable(dev, st, write ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE,
 			       DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_NO_KERNEL_MAPPING);

From 6266f4a78131c795631440ea9c7b66cdfd399484 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Tue, 18 Feb 2025 23:18:55 +0200
Subject: [PATCH 1876/2753] drm/i915/cdclk: Do cdclk post plane programming
 later
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We currently call intel_set_cdclk_post_plane_update() far
too early. When pipes are active during the reprogramming
the current spot only works for the cd2x divider update
case, as that is synchronize to the pipe's vblank. Squashing
and crawling are not synchronized in any way, so doing the
programming while the pipes/planes are potentially still using
the old hardware state could lead to underruns.

Move the post plane reprgramming to a spot where we know
that the pipes/planes have switched over the new hardware
state.

Cc: stable@vger.kernel.org
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250218211913.27867-2-ville.syrjala@linux.intel.com
Reviewed-by: Vinod Govindapillai <vinod.govindapillai@intel.com>
(cherry picked from commit fb64f5568c0e0b5730733d70a012ae26b1a55815)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/display/intel_display.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
index 41128469f12a2..c9dcf2bbd4c73 100644
--- a/drivers/gpu/drm/i915/display/intel_display.c
+++ b/drivers/gpu/drm/i915/display/intel_display.c
@@ -7830,9 +7830,6 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 
 	intel_program_dpkgc_latency(state);
 
-	if (state->modeset)
-		intel_set_cdclk_post_plane_update(state);
-
 	intel_wait_for_vblank_workers(state);
 
 	/* FIXME: We should call drm_atomic_helper_commit_hw_done() here
@@ -7906,6 +7903,8 @@ static void intel_atomic_commit_tail(struct intel_atomic_state *state)
 		intel_verify_planes(state);
 
 	intel_sagv_post_plane_update(state);
+	if (state->modeset)
+		intel_set_cdclk_post_plane_update(state);
 	intel_pmdemand_post_plane_update(state);
 
 	drm_atomic_helper_commit_hw_done(&state->base);

From 3e331a6715ee26f2fabc59dad6bb36d810707028 Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Fri, 7 Mar 2025 19:56:35 -0500
Subject: [PATCH 1877/2753] drm/xe/pm: Temporarily disable D3Cold on BMG

Currently, many instability cases related to D3Cold -> D0 transition
on BMG are under investigation. Among them some bad cases where
the device is lost after 1 to 3 transitions from D3Cold to D0
on the runtime pm, with pcieport upstream bridge port link retrain
failure.

In other cases, it works fine, but with some sudden random memory
corruptions after D3cold, that could be 0xffff missed ack on GT
forcewake or GuC reload related failures.

In some other cases though, D3Cold -> D0 works pretty reliably.
It looks like it is a combination of GPU cards and Host boards at
this point. So, there is no possible/available quirk at this time.

This patch disables the D3Cold by default on BMG by reducing the
vram_d3cold_threshold to 0. Users and developers who wants to enable
it are still able to via
$ echo 300 > /sys/bus/pci/devices/<addr>/vram_d3cold_threshold

Fixes: 3adcf970dc7e ("drm/xe/bmg: Drop force_probe requirement")
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4037
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4395
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/4396
Cc: Karthik Poosa <karthik.poosa@intel.com>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250308005636.1475420-1-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit d945cc876277851053c0cf37927c8d7bd9d0e880)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_pm.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
index c9cc0c091dfdd..89fd2c043136e 100644
--- a/drivers/gpu/drm/xe/xe_pm.c
+++ b/drivers/gpu/drm/xe/xe_pm.c
@@ -267,6 +267,15 @@ int xe_pm_init_early(struct xe_device *xe)
 }
 ALLOW_ERROR_INJECTION(xe_pm_init_early, ERRNO); /* See xe_pci_probe() */
 
+static u32 vram_threshold_value(struct xe_device *xe)
+{
+	/* FIXME: D3Cold temporarily disabled by default on BMG */
+	if (xe->info.platform == XE_BATTLEMAGE)
+		return 0;
+
+	return DEFAULT_VRAM_THRESHOLD;
+}
+
 /**
  * xe_pm_init - Initialize Xe Power Management
  * @xe: xe device instance
@@ -277,6 +286,7 @@ ALLOW_ERROR_INJECTION(xe_pm_init_early, ERRNO); /* See xe_pci_probe() */
  */
 int xe_pm_init(struct xe_device *xe)
 {
+	u32 vram_threshold;
 	int err;
 
 	/* For now suspend/resume is only allowed with GuC */
@@ -290,7 +300,8 @@ int xe_pm_init(struct xe_device *xe)
 		if (err)
 			return err;
 
-		err = xe_pm_set_vram_threshold(xe, DEFAULT_VRAM_THRESHOLD);
+		vram_threshold = vram_threshold_value(xe);
+		err = xe_pm_set_vram_threshold(xe, vram_threshold);
 		if (err)
 			return err;
 	}

From c605acb53f449f6289f042790307d7dc9e62d03d Mon Sep 17 00:00:00 2001
From: Rodrigo Vivi <rodrigo.vivi@intel.com>
Date: Fri, 7 Mar 2025 11:03:07 -0500
Subject: [PATCH 1878/2753] drm/xe/guc_pc: Retry and wait longer for GuC PC
 start

In a rare situation of thermal limit during resume, GuC can
be slow and run into delays like this:

xe 0000:00:02.0: [drm] GT1: excessive init time: 667ms! \
   		 [status = 0x8002F034, timeouts = 0]
xe 0000:00:02.0: [drm] GT1: excessive init time: \
   		 [freq = 100MHz (req = 800MHz), before = 100MHz, \
   		 perf_limit_reasons = 0x1C001000]
xe 0000:00:02.0: [drm] *ERROR* GT1: GuC PC Start failed
------------[ cut here ]------------
xe 0000:00:02.0: [drm] GT1: Failed to start GuC PC: -EIO

When this happens, it will block entirely the GPU to be used.
So, let's try and with a huge timeout in the hope it comes back.

Also, let's collect some information on how long it is usually
taking on situations like this, so perhaps the time can be tuned
later.

Cc: Vinay Belgaumkar <vinay.belgaumkar@intel.com>
Cc: Jonathan Cavitt <jonathan.cavitt@intel.com>
Cc: John Harrison <John.C.Harrison@Intel.com>
Reviewed-by: Jonathan Cavitt <jonathan.cavitt@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307160307.1093391-1-rodrigo.vivi@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit b4b05e53b550a886b4754b87fd0dd2b304579e85)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_guc_pc.c | 53 +++++++++++++++++++++++++---------
 1 file changed, 40 insertions(+), 13 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_guc_pc.c b/drivers/gpu/drm/xe/xe_guc_pc.c
index df7f130fb663f..b995d1d51aed0 100644
--- a/drivers/gpu/drm/xe/xe_guc_pc.c
+++ b/drivers/gpu/drm/xe/xe_guc_pc.c
@@ -6,6 +6,7 @@
 #include "xe_guc_pc.h"
 
 #include <linux/delay.h>
+#include <linux/ktime.h>
 
 #include <drm/drm_managed.h>
 #include <generated/xe_wa_oob.h>
@@ -19,6 +20,7 @@
 #include "xe_gt.h"
 #include "xe_gt_idle.h"
 #include "xe_gt_printk.h"
+#include "xe_gt_throttle.h"
 #include "xe_gt_types.h"
 #include "xe_guc.h"
 #include "xe_guc_ct.h"
@@ -49,6 +51,9 @@
 #define LNL_MERT_FREQ_CAP	800
 #define BMG_MERT_FREQ_CAP	2133
 
+#define SLPC_RESET_TIMEOUT_MS 5 /* roughly 5ms, but no need for precision */
+#define SLPC_RESET_EXTENDED_TIMEOUT_MS 1000 /* To be used only at pc_start */
+
 /**
  * DOC: GuC Power Conservation (PC)
  *
@@ -113,9 +118,10 @@ static struct iosys_map *pc_to_maps(struct xe_guc_pc *pc)
 	 FIELD_PREP(HOST2GUC_PC_SLPC_REQUEST_MSG_1_EVENT_ARGC, count))
 
 static int wait_for_pc_state(struct xe_guc_pc *pc,
-			     enum slpc_global_state state)
+			     enum slpc_global_state state,
+			     int timeout_ms)
 {
-	int timeout_us = 5000; /* rought 5ms, but no need for precision */
+	int timeout_us = 1000 * timeout_ms;
 	int slept, wait = 10;
 
 	xe_device_assert_mem_access(pc_to_xe(pc));
@@ -164,7 +170,8 @@ static int pc_action_query_task_state(struct xe_guc_pc *pc)
 	};
 	int ret;
 
-	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
+	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
+			      SLPC_RESET_TIMEOUT_MS))
 		return -EAGAIN;
 
 	/* Blocking here to ensure the results are ready before reading them */
@@ -187,7 +194,8 @@ static int pc_action_set_param(struct xe_guc_pc *pc, u8 id, u32 value)
 	};
 	int ret;
 
-	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
+	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
+			      SLPC_RESET_TIMEOUT_MS))
 		return -EAGAIN;
 
 	ret = xe_guc_ct_send(ct, action, ARRAY_SIZE(action), 0, 0);
@@ -208,7 +216,8 @@ static int pc_action_unset_param(struct xe_guc_pc *pc, u8 id)
 	struct xe_guc_ct *ct = &pc_to_guc(pc)->ct;
 	int ret;
 
-	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING))
+	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
+			      SLPC_RESET_TIMEOUT_MS))
 		return -EAGAIN;
 
 	ret = xe_guc_ct_send(ct, action, ARRAY_SIZE(action), 0, 0);
@@ -440,6 +449,15 @@ u32 xe_guc_pc_get_act_freq(struct xe_guc_pc *pc)
 	return freq;
 }
 
+static u32 get_cur_freq(struct xe_gt *gt)
+{
+	u32 freq;
+
+	freq = xe_mmio_read32(&gt->mmio, RPNSWREQ);
+	freq = REG_FIELD_GET(REQ_RATIO_MASK, freq);
+	return decode_freq(freq);
+}
+
 /**
  * xe_guc_pc_get_cur_freq - Get Current requested frequency
  * @pc: The GuC PC
@@ -463,10 +481,7 @@ int xe_guc_pc_get_cur_freq(struct xe_guc_pc *pc, u32 *freq)
 		return -ETIMEDOUT;
 	}
 
-	*freq = xe_mmio_read32(&gt->mmio, RPNSWREQ);
-
-	*freq = REG_FIELD_GET(REQ_RATIO_MASK, *freq);
-	*freq = decode_freq(*freq);
+	*freq = get_cur_freq(gt);
 
 	xe_force_wake_put(gt_to_fw(gt), fw_ref);
 	return 0;
@@ -1002,6 +1017,7 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 	struct xe_gt *gt = pc_to_gt(pc);
 	u32 size = PAGE_ALIGN(sizeof(struct slpc_shared_data));
 	unsigned int fw_ref;
+	ktime_t earlier;
 	int ret;
 
 	xe_gt_assert(gt, xe_device_uc_enabled(xe));
@@ -1026,14 +1042,25 @@ int xe_guc_pc_start(struct xe_guc_pc *pc)
 	memset(pc->bo->vmap.vaddr, 0, size);
 	slpc_shared_data_write(pc, header.size, size);
 
+	earlier = ktime_get();
 	ret = pc_action_reset(pc);
 	if (ret)
 		goto out;
 
-	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING)) {
-		xe_gt_err(gt, "GuC PC Start failed\n");
-		ret = -EIO;
-		goto out;
+	if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
+			      SLPC_RESET_TIMEOUT_MS)) {
+		xe_gt_warn(gt, "GuC PC start taking longer than normal [freq = %dMHz (req = %dMHz), perf_limit_reasons = 0x%08X]\n",
+			   xe_guc_pc_get_act_freq(pc), get_cur_freq(gt),
+			   xe_gt_throttle_get_limit_reasons(gt));
+
+		if (wait_for_pc_state(pc, SLPC_GLOBAL_STATE_RUNNING,
+				      SLPC_RESET_EXTENDED_TIMEOUT_MS)) {
+			xe_gt_err(gt, "GuC PC Start failed: Dynamic GT frequency control and GT sleep states are now disabled.\n");
+			goto out;
+		}
+
+		xe_gt_warn(gt, "GuC PC excessive start time: %lldms",
+			   ktime_ms_delta(ktime_get(), earlier));
 	}
 
 	ret = pc_init_freqs(pc);

From 3f674e7b670b7b7d9261935820e4eba3c059f835 Mon Sep 17 00:00:00 2001
From: Keith Busch <kbusch@kernel.org>
Date: Thu, 6 Mar 2025 14:25:57 -0800
Subject: [PATCH 1879/2753] nvme-pci: fix stuck reset on concurrent DPC and HP

The PCIe error handling has the nvme driver quiesce the device, attempt
to restart it, then wait for that restart to complete.

A PCIe DPC event also toggles the PCIe link. If the slot doesn't have
out-of-band presence detection, this will trigger a pciehp
re-enumeration.

The error handling that calls nvme_error_resume is holding the device
lock while this happens. This lock blocks pciehp's request to disconnect
the driver from proceeding.

Meanwhile the nvme's reset can't make forward progress because its
device isn't there anymore with outstanding IO, and the timeout handler
won't do anything to fix it because the device is undergoing error
handling.

End result: deadlocked.

Fix this by having the timeout handler short cut the disabling for a
disconnected PCIe device. The downside is that we're relying on an IO
timeout to clean up this mess, which could be a minute by default.

Tested-by: Nilay Shroff <nilay@linux.ibm.com>
Reviewed-by: Nilay Shroff <nilay@linux.ibm.com>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/host/pci.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 640590b217282..e59aad269abf8 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1411,9 +1411,20 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	struct nvme_dev *dev = nvmeq->dev;
 	struct request *abort_req;
 	struct nvme_command cmd = { };
+	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	u32 csts = readl(dev->bar + NVME_REG_CSTS);
 	u8 opcode;
 
+	/*
+	 * Shutdown the device immediately if we see it is disconnected. This
+	 * unblocks PCIe error handling if the nvme driver is waiting in
+	 * error_resume for a device that has been removed. We can't unbind the
+	 * driver while the driver's error callback is waiting to complete, so
+	 * we're relying on a timeout to break that deadlock if a removal
+	 * occurs while reset work is running.
+	 */
+	if (pci_dev_is_disconnected(pdev))
+		nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_DELETING);
 	if (nvme_state_terminal(&dev->ctrl))
 		goto disable;
 
@@ -1421,7 +1432,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req)
 	 * the recovery mechanism will surely fail.
 	 */
 	mb();
-	if (pci_channel_offline(to_pci_dev(dev->dev)))
+	if (pci_channel_offline(pdev))
 		return BLK_EH_RESET_TIMER;
 
 	/*

From de93ddf88088f7624b589d0ff3af9effb87e8f3b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala@linux.intel.com>
Date: Wed, 19 Feb 2025 18:02:39 +0200
Subject: [PATCH 1880/2753] drm/atomic: Filter out redundant DPMS calls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Video players (eg. mpv) do periodic XResetScreenSaver() calls to
keep the screen on while the video playing. The modesetting ddx
plumbs these straight through into the kernel as DPMS setproperty
ioctls, without any filtering whatsoever. When implemented via
atomic these end up as empty commits on the crtc (which will
nonetheless take one full frame), which leads to a dropped
frame every time XResetScreenSaver() is called.

Let's just filter out redundant DPMS property changes in the
kernel to avoid this issue.

v2: Explain the resulting commits a bit better (Sima)
    Document the behaviour in uapi docs (Sima)

Cc: stable@vger.kernel.org
Testcase: igt/kms_flip/flip-vs-dpms-on-nop
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250219160239.17502-1-ville.syrjala@linux.intel.com
---
 drivers/gpu/drm/drm_atomic_uapi.c | 4 ++++
 drivers/gpu/drm/drm_connector.c   | 4 ++++
 2 files changed, 8 insertions(+)

diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
index 370dc676e3aa5..fd36b8fd54e9e 100644
--- a/drivers/gpu/drm/drm_atomic_uapi.c
+++ b/drivers/gpu/drm/drm_atomic_uapi.c
@@ -956,6 +956,10 @@ int drm_atomic_connector_commit_dpms(struct drm_atomic_state *state,
 
 	if (mode != DRM_MODE_DPMS_ON)
 		mode = DRM_MODE_DPMS_OFF;
+
+	if (connector->dpms == mode)
+		goto out;
+
 	connector->dpms = mode;
 
 	crtc = connector->state->crtc;
diff --git a/drivers/gpu/drm/drm_connector.c b/drivers/gpu/drm/drm_connector.c
index 5f24d6b41cc6d..48b08c9611a7b 100644
--- a/drivers/gpu/drm/drm_connector.c
+++ b/drivers/gpu/drm/drm_connector.c
@@ -1427,6 +1427,10 @@ EXPORT_SYMBOL(drm_hdmi_connector_get_output_format_name);
  * 	callback. For atomic drivers the remapping to the "ACTIVE" property is
  * 	implemented in the DRM core.
  *
+ * 	On atomic drivers any DPMS setproperty ioctl where the value does not
+ * 	change is completely skipped, otherwise a full atomic commit will occur.
+ * 	On legacy drivers the exact behavior is driver specific.
+ *
  * 	Note that this property cannot be set through the MODE_ATOMIC ioctl,
  * 	userspace must use "ACTIVE" on the CRTC instead.
  *

From 73fe9073c0cc28056cb9de0c8a516dac070f1d1f Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhklinux@outlook.com>
Date: Sun, 9 Mar 2025 20:52:08 -0700
Subject: [PATCH 1881/2753] Drivers: hv: vmbus: Don't release fb_mmio resource
 in vmbus_free_mmio()

The VMBus driver manages the MMIO space it owns via the hyperv_mmio
resource tree. Because the synthetic video framebuffer portion of the
MMIO space is initially setup by the Hyper-V host for each guest, the
VMBus driver does an early reserve of that portion of MMIO space in the
hyperv_mmio resource tree. It saves a pointer to that resource in
fb_mmio. When a VMBus driver requests MMIO space and passes "true"
for the "fb_overlap_ok" argument, the reserved framebuffer space is
used if possible. In that case it's not necessary to do another request
against the "shadow" hyperv_mmio resource tree because that resource
was already requested in the early reserve steps.

However, the vmbus_free_mmio() function currently does no special
handling for the fb_mmio resource. When a framebuffer device is
removed, or the driver is unbound, the current code for
vmbus_free_mmio() releases the reserved resource, leaving fb_mmio
pointing to memory that has been freed. If the same or another
driver is subsequently bound to the device, vmbus_allocate_mmio()
checks against fb_mmio, and potentially gets garbage. Furthermore
a second unbind operation produces this "nonexistent resource" error
because of the unbalanced behavior between vmbus_allocate_mmio() and
vmbus_free_mmio():

[   55.499643] resource: Trying to free nonexistent
			resource <0x00000000f0000000-0x00000000f07fffff>

Fix this by adding logic to vmbus_free_mmio() to recognize when
MMIO space in the fb_mmio reserved area would be released, and don't
release it. This filtering ensures the fb_mmio resource always exists,
and makes vmbus_free_mmio() more parallel with vmbus_allocate_mmio().

Fixes: be000f93e5d7 ("drivers:hv: Track allocations of children of hv_vmbus in private resource tree")
Signed-off-by: Michael Kelley <mhklinux@outlook.com>
Tested-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Link: https://lore.kernel.org/r/20250310035208.275764-1-mhklinux@outlook.com
Signed-off-by: Wei Liu <wei.liu@kernel.org>
Message-ID: <20250310035208.275764-1-mhklinux@outlook.com>
---
 drivers/hv/vmbus_drv.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 0f6cd44fff292..6e55a1a2613d3 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2262,12 +2262,25 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size)
 	struct resource *iter;
 
 	mutex_lock(&hyperv_mmio_lock);
+
+	/*
+	 * If all bytes of the MMIO range to be released are within the
+	 * special case fb_mmio shadow region, skip releasing the shadow
+	 * region since no corresponding __request_region() was done
+	 * in vmbus_allocate_mmio().
+	 */
+	if (fb_mmio && start >= fb_mmio->start &&
+	    (start + size - 1 <= fb_mmio->end))
+		goto skip_shadow_release;
+
 	for (iter = hyperv_mmio; iter; iter = iter->sibling) {
 		if ((iter->start >= start + size) || (iter->end <= start))
 			continue;
 
 		__release_region(iter, start, size);
 	}
+
+skip_shadow_release:
 	release_mem_region(start, size);
 	mutex_unlock(&hyperv_mmio_lock);
 

From 6fbafe1cbed10e53b3cf236a8a1987425206dd8e Mon Sep 17 00:00:00 2001
From: Panagiotis Foliadis <pfoliadis@posteo.net>
Date: Sat, 8 Mar 2025 16:49:05 +0000
Subject: [PATCH 1882/2753] rust: task: fix `SAFETY` comment in `Task::wake_up`

The `SAFETY` comment inside the `wake_up` method references
erroneously the `signal_pending` C function instead of the
`wake_up_process` which is actually called.

Fix the comment to reference the correct C function.

Fixes: fe95f58320e6 ("rust: task: adjust safety comments in Task methods")
Signed-off-by: Panagiotis Foliadis <pfoliadis@posteo.net>
Reviewed-by: Charalampos Mitrodimas <charmitro@posteo.net>
Reviewed-by: Alice Ryhl <aliceryhl@google.com>
Link: https://lore.kernel.org/r/20250308-comment-fix-v1-1-4bba709fd36d@posteo.net
[ Slightly reworded. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 rust/kernel/task.rs | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/rust/kernel/task.rs b/rust/kernel/task.rs
index 07bc22a7645c0..38da555a2bdbb 100644
--- a/rust/kernel/task.rs
+++ b/rust/kernel/task.rs
@@ -320,7 +320,7 @@ impl Task {
 
     /// Wakes up the task.
     pub fn wake_up(&self) {
-        // SAFETY: It's always safe to call `signal_pending` on a valid task, even if the task
+        // SAFETY: It's always safe to call `wake_up_process` on a valid task, even if the task
         // running.
         unsafe { bindings::wake_up_process(self.as_ptr()) };
     }

From bf9b8020a80d32f6aa80591297a087d0519dc931 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 6 Mar 2025 17:55:48 +0900
Subject: [PATCH 1883/2753] nvmet: pci-epf: Set NVMET_PCI_EPF_Q_LIVE when a
 queue is fully created

The function nvmet_pci_epf_create_sq() use test_and_set_bit() to check
that a submission queue is not already live and if not, set the
NVMET_PCI_EPF_Q_LIVE queue flag to declare the sq live (ready to use).
However, this is done on entry to the function, before the submission
queue is actually fully initialized and ready to use. This creates a
race situation with the function nvmet_pci_epf_poll_sqs_work() which
looks at the NVMET_PCI_EPF_Q_LIVE queue flag to poll the submission
queue when it is live. This race can lead to invalid DMA transfers if
nvmet_pci_epf_poll_sqs_work() runs after the NVMET_PCI_EPF_Q_LIVE flag
is set but before setting the sq pci address and doorbell ofset.

Avoid this race by only testing the NVMET_PCI_EPF_Q_LIVE flag on entry
to nvmet_pci_epf_create_sq() and setting it after the submission queue
is fully setup before nvmet_pci_epf_create_sq() returns success.
Since the function nvmet_pci_epf_create_cq() also has the same racy flag
setting pattern, also make a similar change in that function.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index 565d2bd36dcde..d55ad334670c5 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1265,7 +1265,7 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 	struct nvmet_pci_epf_queue *cq = &ctrl->cq[cqid];
 	u16 status;
 
-	if (test_and_set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
+	if (test_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags))
 		return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
 
 	if (!(flags & NVME_QUEUE_PHYS_CONTIG))
@@ -1300,6 +1300,8 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 	if (status != NVME_SC_SUCCESS)
 		goto err;
 
+	set_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
+
 	dev_dbg(ctrl->dev, "CQ[%u]: %u entries of %zu B, IRQ vector %u\n",
 		cqid, qsize, cq->qes, cq->vector);
 
@@ -1307,7 +1309,6 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 
 err:
 	clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags);
-	clear_bit(NVMET_PCI_EPF_Q_LIVE, &cq->flags);
 	return status;
 }
 
@@ -1333,7 +1334,7 @@ static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl,
 	struct nvmet_pci_epf_queue *sq = &ctrl->sq[sqid];
 	u16 status;
 
-	if (test_and_set_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags))
+	if (test_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags))
 		return NVME_SC_QID_INVALID | NVME_STATUS_DNR;
 
 	if (!(flags & NVME_QUEUE_PHYS_CONTIG))
@@ -1355,7 +1356,7 @@ static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl,
 
 	status = nvmet_sq_create(tctrl, &sq->nvme_sq, sqid, sq->depth);
 	if (status != NVME_SC_SUCCESS)
-		goto out_clear_bit;
+		return status;
 
 	sq->iod_wq = alloc_workqueue("sq%d_wq", WQ_UNBOUND,
 				min_t(int, sq->depth, WQ_MAX_ACTIVE), sqid);
@@ -1365,6 +1366,8 @@ static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl,
 		goto out_destroy_sq;
 	}
 
+	set_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags);
+
 	dev_dbg(ctrl->dev, "SQ[%u]: %u entries of %zu B\n",
 		sqid, qsize, sq->qes);
 
@@ -1372,8 +1375,6 @@ static u16 nvmet_pci_epf_create_sq(struct nvmet_ctrl *tctrl,
 
 out_destroy_sq:
 	nvmet_sq_destroy(&sq->nvme_sq);
-out_clear_bit:
-	clear_bit(NVMET_PCI_EPF_Q_LIVE, &sq->flags);
 	return status;
 }
 

From 39393f5c5c795992507aa5005a9d58396a5b07f1 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 6 Mar 2025 17:55:49 +0900
Subject: [PATCH 1884/2753] nvmet: pci-epf: Do not add an IRQ vector if not
 needed

The function nvmet_pci_epf_create_cq() always unconditionally calls
nvmet_pci_epf_add_irq_vector() to add an IRQ vector for a completion
queue. But this is not correct if the host requested the creation of a
completion queue for polling, without an IRQ vector specified (i.e. the
flag NVME_CQ_IRQ_ENABLED is not set).

Fix this by calling nvmet_pci_epf_add_irq_vector() and setting the queue
flag NVMET_PCI_EPF_Q_IRQ_ENABLED for the cq only if NVME_CQ_IRQ_ENABLED
is set. While at it, also fix the error path to add the missing removal
of the added IRQ vector if nvmet_cq_create() fails.

Fixes: 0faa0fe6f90e ("nvmet: New NVMe PCI endpoint function target driver")
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Keith Busch <kbusch@kernel.org>
---
 drivers/nvme/target/pci-epf.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/nvme/target/pci-epf.c b/drivers/nvme/target/pci-epf.c
index d55ad334670c5..b1e31483f1574 100644
--- a/drivers/nvme/target/pci-epf.c
+++ b/drivers/nvme/target/pci-epf.c
@@ -1271,9 +1271,6 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 	if (!(flags & NVME_QUEUE_PHYS_CONTIG))
 		return NVME_SC_INVALID_QUEUE | NVME_STATUS_DNR;
 
-	if (flags & NVME_CQ_IRQ_ENABLED)
-		set_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags);
-
 	cq->pci_addr = pci_addr;
 	cq->qid = cqid;
 	cq->depth = qsize + 1;
@@ -1290,10 +1287,11 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 		cq->qes = ctrl->io_cqes;
 	cq->pci_size = cq->qes * cq->depth;
 
-	cq->iv = nvmet_pci_epf_add_irq_vector(ctrl, vector);
-	if (!cq->iv) {
-		status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
-		goto err;
+	if (flags & NVME_CQ_IRQ_ENABLED) {
+		cq->iv = nvmet_pci_epf_add_irq_vector(ctrl, vector);
+		if (!cq->iv)
+			return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+		set_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags);
 	}
 
 	status = nvmet_cq_create(tctrl, &cq->nvme_cq, cqid, cq->depth);
@@ -1308,7 +1306,8 @@ static u16 nvmet_pci_epf_create_cq(struct nvmet_ctrl *tctrl,
 	return NVME_SC_SUCCESS;
 
 err:
-	clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags);
+	if (test_and_clear_bit(NVMET_PCI_EPF_Q_IRQ_ENABLED, &cq->flags))
+		nvmet_pci_epf_remove_irq_vector(ctrl, cq->vector);
 	return status;
 }
 

From bb39ed47065455604729404729d9116868638d31 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Wed, 5 Mar 2025 21:21:43 +0900
Subject: [PATCH 1885/2753] ksmbd: fix use-after-free in ksmbd_free_work_struct

->interim_entry of ksmbd_work could be deleted after oplock is freed.
We don't need to manage it with linked list. The interim request could be
immediately sent whenever a oplock break wait is needed.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/ksmbd_work.c |  3 ---
 fs/smb/server/ksmbd_work.h |  1 -
 fs/smb/server/oplock.c     | 37 +++++++++++++++----------------------
 fs/smb/server/oplock.h     |  1 -
 4 files changed, 15 insertions(+), 27 deletions(-)

diff --git a/fs/smb/server/ksmbd_work.c b/fs/smb/server/ksmbd_work.c
index 4af2e6007c29d..72b00ca6e4551 100644
--- a/fs/smb/server/ksmbd_work.c
+++ b/fs/smb/server/ksmbd_work.c
@@ -26,7 +26,6 @@ struct ksmbd_work *ksmbd_alloc_work_struct(void)
 		INIT_LIST_HEAD(&work->request_entry);
 		INIT_LIST_HEAD(&work->async_request_entry);
 		INIT_LIST_HEAD(&work->fp_entry);
-		INIT_LIST_HEAD(&work->interim_entry);
 		INIT_LIST_HEAD(&work->aux_read_list);
 		work->iov_alloc_cnt = 4;
 		work->iov = kcalloc(work->iov_alloc_cnt, sizeof(struct kvec),
@@ -56,8 +55,6 @@ void ksmbd_free_work_struct(struct ksmbd_work *work)
 	kfree(work->tr_buf);
 	kvfree(work->request_buf);
 	kfree(work->iov);
-	if (!list_empty(&work->interim_entry))
-		list_del(&work->interim_entry);
 
 	if (work->async_id)
 		ksmbd_release_id(&work->conn->async_ida, work->async_id);
diff --git a/fs/smb/server/ksmbd_work.h b/fs/smb/server/ksmbd_work.h
index 8ca2c813246e6..d36393ff8310c 100644
--- a/fs/smb/server/ksmbd_work.h
+++ b/fs/smb/server/ksmbd_work.h
@@ -89,7 +89,6 @@ struct ksmbd_work {
 	/* List head at conn->async_requests */
 	struct list_head                async_request_entry;
 	struct list_head                fp_entry;
-	struct list_head                interim_entry;
 };
 
 /**
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 3a3fe4afbdf0d..2febd1c8e278c 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -46,7 +46,6 @@ static struct oplock_info *alloc_opinfo(struct ksmbd_work *work,
 	opinfo->fid = id;
 	opinfo->Tid = Tid;
 	INIT_LIST_HEAD(&opinfo->op_entry);
-	INIT_LIST_HEAD(&opinfo->interim_list);
 	init_waitqueue_head(&opinfo->oplock_q);
 	init_waitqueue_head(&opinfo->oplock_brk);
 	atomic_set(&opinfo->refcount, 1);
@@ -803,7 +802,6 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 static int smb2_lease_break_noti(struct oplock_info *opinfo)
 {
 	struct ksmbd_conn *conn = opinfo->conn;
-	struct list_head *tmp, *t;
 	struct ksmbd_work *work;
 	struct lease_break_info *br_info;
 	struct lease *lease = opinfo->o_lease;
@@ -831,16 +829,6 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo)
 	work->sess = opinfo->sess;
 
 	if (opinfo->op_state == OPLOCK_ACK_WAIT) {
-		list_for_each_safe(tmp, t, &opinfo->interim_list) {
-			struct ksmbd_work *in_work;
-
-			in_work = list_entry(tmp, struct ksmbd_work,
-					     interim_entry);
-			setup_async_work(in_work, NULL, NULL);
-			smb2_send_interim_resp(in_work, STATUS_PENDING);
-			list_del_init(&in_work->interim_entry);
-			release_async_work(in_work);
-		}
 		INIT_WORK(&work->work, __smb2_lease_break_noti);
 		ksmbd_queue_work(work);
 		wait_for_break_ack(opinfo);
@@ -871,7 +859,8 @@ static void wait_lease_breaking(struct oplock_info *opinfo)
 	}
 }
 
-static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level)
+static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level,
+			struct ksmbd_work *in_work)
 {
 	int err = 0;
 
@@ -914,9 +903,15 @@ static int oplock_break(struct oplock_info *brk_opinfo, int req_op_level)
 		}
 
 		if (lease->state & (SMB2_LEASE_WRITE_CACHING_LE |
-				SMB2_LEASE_HANDLE_CACHING_LE))
+				SMB2_LEASE_HANDLE_CACHING_LE)) {
+			if (in_work) {
+				setup_async_work(in_work, NULL, NULL);
+				smb2_send_interim_resp(in_work, STATUS_PENDING);
+				release_async_work(in_work);
+			}
+
 			brk_opinfo->op_state = OPLOCK_ACK_WAIT;
-		else
+		} else
 			atomic_dec(&brk_opinfo->breaking_cnt);
 	} else {
 		err = oplock_break_pending(brk_opinfo, req_op_level);
@@ -1116,7 +1111,7 @@ void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
 			if (ksmbd_conn_releasing(opinfo->conn))
 				continue;
 
-			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL);
 			opinfo_put(opinfo);
 		}
 	}
@@ -1152,7 +1147,7 @@ void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp)
 
 			if (ksmbd_conn_releasing(opinfo->conn))
 				continue;
-			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE);
+			oplock_break(opinfo, SMB2_OPLOCK_LEVEL_NONE, NULL);
 			opinfo_put(opinfo);
 		}
 	}
@@ -1252,8 +1247,7 @@ int smb_grant_oplock(struct ksmbd_work *work, int req_op_level, u64 pid,
 		goto op_break_not_needed;
 	}
 
-	list_add(&work->interim_entry, &prev_opinfo->interim_list);
-	err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II);
+	err = oplock_break(prev_opinfo, SMB2_OPLOCK_LEVEL_II, work);
 	opinfo_put(prev_opinfo);
 	if (err == -ENOENT)
 		goto set_lev;
@@ -1322,8 +1316,7 @@ static void smb_break_all_write_oplock(struct ksmbd_work *work,
 	}
 
 	brk_opinfo->open_trunc = is_trunc;
-	list_add(&work->interim_entry, &brk_opinfo->interim_list);
-	oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II);
+	oplock_break(brk_opinfo, SMB2_OPLOCK_LEVEL_II, work);
 	opinfo_put(brk_opinfo);
 }
 
@@ -1386,7 +1379,7 @@ void smb_break_all_levII_oplock(struct ksmbd_work *work, struct ksmbd_file *fp,
 			    SMB2_LEASE_KEY_SIZE))
 			goto next;
 		brk_op->open_trunc = is_trunc;
-		oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE);
+		oplock_break(brk_op, SMB2_OPLOCK_LEVEL_NONE, NULL);
 next:
 		opinfo_put(brk_op);
 		rcu_read_lock();
diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
index 72bc88a63a408..3f64f07872638 100644
--- a/fs/smb/server/oplock.h
+++ b/fs/smb/server/oplock.h
@@ -67,7 +67,6 @@ struct oplock_info {
 	bool			is_lease;
 	bool			open_trunc;	/* truncate on open */
 	struct lease		*o_lease;
-	struct list_head        interim_list;
 	struct list_head        op_entry;
 	struct list_head        lease_entry;
 	wait_queue_head_t oplock_q; /* Other server threads */

From 3aa660c059240e0c795217182cf7df32909dd917 Mon Sep 17 00:00:00 2001
From: Namjae Jeon <linkinjeon@kernel.org>
Date: Thu, 6 Mar 2025 14:14:58 +0900
Subject: [PATCH 1886/2753] ksmbd: prevent connection release during oplock
 break notification

ksmbd_work could be freed when after connection release.
Increment r_count of ksmbd_conn to indicate that requests
are not finished yet and to not release the connection.

Cc: stable@vger.kernel.org
Reported-by: Norbert Szetei <norbert@doyensec.com>
Tested-by: Norbert Szetei <norbert@doyensec.com>
Signed-off-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/server/connection.c | 20 ++++++++++++++++++++
 fs/smb/server/connection.h |  2 ++
 fs/smb/server/oplock.c     |  6 ++++++
 fs/smb/server/server.c     | 14 ++------------
 4 files changed, 30 insertions(+), 12 deletions(-)

diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
index f8a40f65db6ae..c1f22c1291117 100644
--- a/fs/smb/server/connection.c
+++ b/fs/smb/server/connection.c
@@ -433,6 +433,26 @@ void ksmbd_conn_init_server_callbacks(struct ksmbd_conn_ops *ops)
 	default_conn_ops.terminate_fn = ops->terminate_fn;
 }
 
+void ksmbd_conn_r_count_inc(struct ksmbd_conn *conn)
+{
+	atomic_inc(&conn->r_count);
+}
+
+void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn)
+{
+	/*
+	 * Checking waitqueue to dropping pending requests on
+	 * disconnection. waitqueue_active is safe because it
+	 * uses atomic operation for condition.
+	 */
+	atomic_inc(&conn->refcnt);
+	if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q))
+		wake_up(&conn->r_count_q);
+
+	if (atomic_dec_and_test(&conn->refcnt))
+		kfree(conn);
+}
+
 int ksmbd_conn_transport_init(void)
 {
 	int ret;
diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
index b379ae4fdcdff..91c2318639e76 100644
--- a/fs/smb/server/connection.h
+++ b/fs/smb/server/connection.h
@@ -168,6 +168,8 @@ int ksmbd_conn_transport_init(void);
 void ksmbd_conn_transport_destroy(void);
 void ksmbd_conn_lock(struct ksmbd_conn *conn);
 void ksmbd_conn_unlock(struct ksmbd_conn *conn);
+void ksmbd_conn_r_count_inc(struct ksmbd_conn *conn);
+void ksmbd_conn_r_count_dec(struct ksmbd_conn *conn);
 
 /*
  * WARNING
diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
index 2febd1c8e278c..28886ff1ee577 100644
--- a/fs/smb/server/oplock.c
+++ b/fs/smb/server/oplock.c
@@ -634,6 +634,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk)
 {
 	struct smb2_oplock_break *rsp = NULL;
 	struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work);
+	struct ksmbd_conn *conn = work->conn;
 	struct oplock_break_info *br_info = work->request_buf;
 	struct smb2_hdr *rsp_hdr;
 	struct ksmbd_file *fp;
@@ -689,6 +690,7 @@ static void __smb2_oplock_break_noti(struct work_struct *wk)
 
 out:
 	ksmbd_free_work_struct(work);
+	ksmbd_conn_r_count_dec(conn);
 }
 
 /**
@@ -723,6 +725,7 @@ static int smb2_oplock_break_noti(struct oplock_info *opinfo)
 	work->sess = opinfo->sess;
 
 	if (opinfo->op_state == OPLOCK_ACK_WAIT) {
+		ksmbd_conn_r_count_inc(conn);
 		INIT_WORK(&work->work, __smb2_oplock_break_noti);
 		ksmbd_queue_work(work);
 
@@ -744,6 +747,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 {
 	struct smb2_lease_break *rsp = NULL;
 	struct ksmbd_work *work = container_of(wk, struct ksmbd_work, work);
+	struct ksmbd_conn *conn = work->conn;
 	struct lease_break_info *br_info = work->request_buf;
 	struct smb2_hdr *rsp_hdr;
 
@@ -790,6 +794,7 @@ static void __smb2_lease_break_noti(struct work_struct *wk)
 
 out:
 	ksmbd_free_work_struct(work);
+	ksmbd_conn_r_count_dec(conn);
 }
 
 /**
@@ -829,6 +834,7 @@ static int smb2_lease_break_noti(struct oplock_info *opinfo)
 	work->sess = opinfo->sess;
 
 	if (opinfo->op_state == OPLOCK_ACK_WAIT) {
+		ksmbd_conn_r_count_inc(conn);
 		INIT_WORK(&work->work, __smb2_lease_break_noti);
 		ksmbd_queue_work(work);
 		wait_for_break_ack(opinfo);
diff --git a/fs/smb/server/server.c b/fs/smb/server/server.c
index 601e7fcbcf1e6..ab533c6029879 100644
--- a/fs/smb/server/server.c
+++ b/fs/smb/server/server.c
@@ -270,17 +270,7 @@ static void handle_ksmbd_work(struct work_struct *wk)
 
 	ksmbd_conn_try_dequeue_request(work);
 	ksmbd_free_work_struct(work);
-	/*
-	 * Checking waitqueue to dropping pending requests on
-	 * disconnection. waitqueue_active is safe because it
-	 * uses atomic operation for condition.
-	 */
-	atomic_inc(&conn->refcnt);
-	if (!atomic_dec_return(&conn->r_count) && waitqueue_active(&conn->r_count_q))
-		wake_up(&conn->r_count_q);
-
-	if (atomic_dec_and_test(&conn->refcnt))
-		kfree(conn);
+	ksmbd_conn_r_count_dec(conn);
 }
 
 /**
@@ -310,7 +300,7 @@ static int queue_ksmbd_work(struct ksmbd_conn *conn)
 	conn->request_buf = NULL;
 
 	ksmbd_conn_enqueue_request(work);
-	atomic_inc(&conn->r_count);
+	ksmbd_conn_r_count_inc(conn);
 	/* update activity on connection */
 	conn->last_active = jiffies;
 	INIT_WORK(&work->work, handle_ksmbd_work);

From fd10709e28d2fa9015667aee56d92099fc97aa0d Mon Sep 17 00:00:00 2001
From: Bastien Nocera <hadess@hadess.net>
Date: Fri, 7 Mar 2025 15:37:32 +0100
Subject: [PATCH 1887/2753] MAINTAINERS: Remove myself from the goodix
 touchscreen maintainers

Haven't authored any commits to that driver in 10 years, and haven't
had supported hardware for nearly as long.

Signed-off-by: Bastien Nocera <hadess@hadess.net>
Link: https://lore.kernel.org/r/20250307143740.960328-1-hadess@hadess.net
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index baf0eeb9a3554..ca8945fd98bcd 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9729,7 +9729,6 @@ S:	Maintained
 F:	drivers/media/usb/go7007/
 
 GOODIX TOUCHSCREEN
-M:	Bastien Nocera <hadess@hadess.net>
 M:	Hans de Goede <hdegoede@redhat.com>
 L:	linux-input@vger.kernel.org
 S:	Maintained

From f5d4e81774c42d9c2ea3980e570f3330ff2ed5d2 Mon Sep 17 00:00:00 2001
From: Xin Wang <x.wang@intel.com>
Date: Mon, 3 Mar 2025 08:49:41 +0800
Subject: [PATCH 1888/2753] drm/xe: remove redundant check in
 xe_vm_create_ioctl()

The check for args->extensions is repeated twice in xe_vm_create_ioctl().
This commit removes the redundant check to streamline the code.

Fixes: 7224788f6756 ("drm/xe: Kill XE_VM_PROPERTY_BIND_OP_ERROR_CAPTURE_ADDRESS extension")
Cc: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Xin Wang <x.wang@intel.com>
Reviewed-by: Tejas Upadhyay <tejas.upadhyay@intel.com>
Reviewed-by: Matthew Auld <matthew.auld@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250303004942.951699-1-x.wang@intel.com
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
(cherry picked from commit 8da8aecf1f2d89c2b8188bcf7aa252ec146ddd12)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/xe/xe_vm.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
index ec6ec18ab3faa..5956631c0d40a 100644
--- a/drivers/gpu/drm/xe/xe_vm.c
+++ b/drivers/gpu/drm/xe/xe_vm.c
@@ -1809,9 +1809,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data,
 			 args->flags & DRM_XE_VM_CREATE_FLAG_FAULT_MODE))
 		return -EINVAL;
 
-	if (XE_IOCTL_DBG(xe, args->extensions))
-		return -EINVAL;
-
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_SCRATCH_PAGE)
 		flags |= XE_VM_FLAG_SCRATCH_PAGE;
 	if (args->flags & DRM_XE_VM_CREATE_FLAG_LR_MODE)

From df1e82e7acd3c50b65ca0e2e09089b78382d14ab Mon Sep 17 00:00:00 2001
From: David Rosca <david.rosca@amd.com>
Date: Thu, 13 Feb 2025 15:30:37 +0100
Subject: [PATCH 1889/2753] drm/amdgpu/display: Allow DCC for video formats on
 GFX12

We advertise DCC as supported for NV12/P010 formats on GFX12,
but it would fail on this check on atomic commit.

Signed-off-by: David Rosca <david.rosca@amd.com>
Reviewed-by: Ruijing Dong <ruijing.dong@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit ba795235a2b99ba9bbef647ab003b2f3145d9bbb)
Cc: stable@vger.kernel.org # 6.12.x
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
index 774cc3f4f3fd9..92472109f84a9 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
@@ -277,8 +277,11 @@ static int amdgpu_dm_plane_validate_dcc(struct amdgpu_device *adev,
 	if (!dcc->enable)
 		return 0;
 
-	if (format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN ||
-	    !dc->cap_funcs.get_dcc_compression_cap)
+	if (adev->family < AMDGPU_FAMILY_GC_12_0_0 &&
+	    format >= SURFACE_PIXEL_FORMAT_VIDEO_BEGIN)
+		return -EINVAL;
+
+	if (!dc->cap_funcs.get_dcc_compression_cap)
 		return -EINVAL;
 
 	input.format = format;

From e204aab79e01bc8ff750645666993ed8b719de57 Mon Sep 17 00:00:00 2001
From: Aliaksei Urbanski <aliaksei.urbanski@gmail.com>
Date: Thu, 6 Mar 2025 13:36:03 +0300
Subject: [PATCH 1890/2753] drm/amd/display: fix missing
 .is_two_pixels_per_container

Starting from 6.11, AMDGPU driver, while being loaded with amdgpu.dc=1,
due to lack of .is_two_pixels_per_container function in dce60_tg_funcs,
causes a NULL pointer dereference on PCs with old GPUs, such as R9 280X.

So this fix adds missing .is_two_pixels_per_container to dce60_tg_funcs.

Reported-by: Rosen Penev <rosenp@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3942
Fixes: e6a901a00822 ("drm/amd/display: use even ODM slice width for two pixels per container")
Signed-off-by: Aliaksei Urbanski <aliaksei.urbanski@gmail.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit bd4b125eb949785c6f8a53b0494e32795421209d)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
index e5fb0e8333e43..e691a1cf33567 100644
--- a/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
+++ b/drivers/gpu/drm/amd/display/dc/dce60/dce60_timing_generator.c
@@ -239,6 +239,7 @@ static const struct timing_generator_funcs dce60_tg_funcs = {
 				dce60_timing_generator_enable_advanced_request,
 		.configure_crc = dce60_configure_crc,
 		.get_crc = dce110_get_crc,
+		.is_two_pixels_per_container = dce110_is_two_pixels_per_container,
 };
 
 void dce60_timing_generator_construct(

From 4afacc9948e1f8fdbca401d259ae65ad93d298c0 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 6 Mar 2025 12:51:24 -0600
Subject: [PATCH 1891/2753] drm/amd: Keep display off while going into S4

When userspace invokes S4 the flow is:

1) amdgpu_pmops_prepare()
2) amdgpu_pmops_freeze()
3) Create hibernation image
4) amdgpu_pmops_thaw()
5) Write out image to disk
6) Turn off system

Then on resume amdgpu_pmops_restore() is called.

This flow has a problem that because amdgpu_pmops_thaw() is called
it will call amdgpu_device_resume() which will resume all of the GPU.

This includes turning the display hardware back on and discovering
connectors again.

This is an unexpected experience for the display to turn back on.
Adjust the flow so that during the S4 sequence display hardware is
not turned back on.

Reported-by: Xaver Hugl <xaver.hugl@gmail.com>
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2038
Cc: Muhammad Usama Anjum <usama.anjum@collabora.com>
Tested-by: Muhammad Usama Anjum <usama.anjum@collabora.com>
Acked-by: Alex Deucher <alexander.deucher@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Link: https://lore.kernel.org/r/20250306185124.44780-1-mario.limonciello@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 68bfdc8dc0a1a7fdd9ab61e69907ae71a6fd3d91)
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c           | 11 +++++++++--
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c |  5 +++++
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
index 95a05b03f799d..c0ddbe7d6f0bc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
@@ -2555,7 +2555,6 @@ static int amdgpu_pmops_freeze(struct device *dev)
 	int r;
 
 	r = amdgpu_device_suspend(drm_dev, true);
-	adev->in_s4 = false;
 	if (r)
 		return r;
 
@@ -2567,8 +2566,13 @@ static int amdgpu_pmops_freeze(struct device *dev)
 static int amdgpu_pmops_thaw(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+	int r;
 
-	return amdgpu_device_resume(drm_dev, true);
+	r = amdgpu_device_resume(drm_dev, true);
+	adev->in_s4 = false;
+
+	return r;
 }
 
 static int amdgpu_pmops_poweroff(struct device *dev)
@@ -2581,6 +2585,9 @@ static int amdgpu_pmops_poweroff(struct device *dev)
 static int amdgpu_pmops_restore(struct device *dev)
 {
 	struct drm_device *drm_dev = dev_get_drvdata(dev);
+	struct amdgpu_device *adev = drm_to_adev(drm_dev);
+
+	adev->in_s4 = false;
 
 	return amdgpu_device_resume(drm_dev, true);
 }
diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 9d9645a2d18ef..f4fed93f2915a 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -3373,6 +3373,11 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 
 		return 0;
 	}
+
+	/* leave display off for S4 sequence */
+	if (adev->in_s4)
+		return 0;
+
 	/* Recreate dc_state - DC invalidates it when setting power state to S3. */
 	dc_state_release(dm_state->context);
 	dm_state->context = dc_state_create(dm->dc, NULL);

From 40b8c14936bd2726354c856251f6baed9869e760 Mon Sep 17 00:00:00 2001
From: Leo Li <sunpeng.li@amd.com>
Date: Thu, 20 Feb 2025 16:20:26 -0500
Subject: [PATCH 1892/2753] drm/amd/display: Disable unneeded hpd interrupts
 during dm_init

[Why]

It seems HPD interrupts are enabled by default for all connectors, even
if the hpd source isn't valid. An eDP for example, does not have a valid
hpd source (but does have a valid hpdrx source; see construct_phy()).
Thus, eDPs should have their hpd interrupt disabled.

In the past, this wasn't really an issue. Although the driver gets
interrupted, then acks by writing to hw registers, there weren't any
subscribed handlers that did anything meaningful (see
register_hpd_handlers()).

But things changed with the introduction of IPS. s2idle requires that
the driver allows IPS for DMUB fw to put hw to sleep. Since register
access requires hw to be awake, the driver will block IPS entry to do
so. And no IPS means no hw sleep during s2idle.

This was the observation on DCN35 systems with an eDP. During suspend,
the eDP toggled its hpd pin as part of the panel power down sequence.
The driver was then interrupted, and acked by writing to registers,
blocking IPS entry.

[How]

Since DC marks eDP connections as having invalid hpd sources (see
construct_phy()), DM should disable them at the hw level. Do so in
amdgpu_dm_hpd_init() by disabling all hpd ints first, then selectively
enabling ones for connectors that have valid hpd sources.

Cc: Mario Limonciello <mario.limonciello@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Leo Li <sunpeng.li@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7b1ba19eb15f88e70782642ce2d934211269337b)
Cc: stable@vger.kernel.org
---
 .../drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c | 64 +++++++++++++------
 1 file changed, 45 insertions(+), 19 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
index c4a7fd453e5fc..a215234151ac3 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_irq.c
@@ -894,8 +894,16 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
+	int irq_type;
 	int i;
 
+	/* First, clear all hpd and hpdrx interrupts */
+	for (i = DC_IRQ_SOURCE_HPD1; i <= DC_IRQ_SOURCE_HPD6RX; i++) {
+		if (!dc_interrupt_set(adev->dm.dc, i, false))
+			drm_err(dev, "Failed to clear hpd(rx) source=%d on init\n",
+				i);
+	}
+
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
 		struct amdgpu_dm_connector *amdgpu_dm_connector;
@@ -908,10 +916,31 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 
 		dc_link = amdgpu_dm_connector->dc_link;
 
+		/*
+		 * Get a base driver irq reference for hpd ints for the lifetime
+		 * of dm. Note that only hpd interrupt types are registered with
+		 * base driver; hpd_rx types aren't. IOW, amdgpu_irq_get/put on
+		 * hpd_rx isn't available. DM currently controls hpd_rx
+		 * explicitly with dc_interrupt_set()
+		 */
 		if (dc_link->irq_source_hpd != DC_IRQ_SOURCE_INVALID) {
-			dc_interrupt_set(adev->dm.dc,
-					dc_link->irq_source_hpd,
-					true);
+			irq_type = dc_link->irq_source_hpd - DC_IRQ_SOURCE_HPD1;
+			/*
+			 * TODO: There's a mismatch between mode_info.num_hpd
+			 * and what bios reports as the # of connectors with hpd
+			 * sources. Since the # of hpd source types registered
+			 * with base driver == mode_info.num_hpd, we have to
+			 * fallback to dc_interrupt_set for the remaining types.
+			 */
+			if (irq_type < adev->mode_info.num_hpd) {
+				if (amdgpu_irq_get(adev, &adev->hpd_irq, irq_type))
+					drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n",
+						dc_link->irq_source_hpd);
+			} else {
+				dc_interrupt_set(adev->dm.dc,
+						 dc_link->irq_source_hpd,
+						 true);
+			}
 		}
 
 		if (dc_link->irq_source_hpd_rx != DC_IRQ_SOURCE_INVALID) {
@@ -921,12 +950,6 @@ void amdgpu_dm_hpd_init(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-
-	/* Update reference counts for HPDs */
-	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
-		if (amdgpu_irq_get(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
-			drm_err(dev, "DM_IRQ: Failed get HPD for source=%d)!\n", i);
-	}
 }
 
 /**
@@ -942,7 +965,7 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 	struct drm_device *dev = adev_to_drm(adev);
 	struct drm_connector *connector;
 	struct drm_connector_list_iter iter;
-	int i;
+	int irq_type;
 
 	drm_connector_list_iter_begin(dev, &iter);
 	drm_for_each_connector_iter(connector, &iter) {
@@ -956,9 +979,18 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 		dc_link = amdgpu_dm_connector->dc_link;
 
 		if (dc_link->irq_source_hpd != DC_IRQ_SOURCE_INVALID) {
-			dc_interrupt_set(adev->dm.dc,
-					dc_link->irq_source_hpd,
-					false);
+			irq_type = dc_link->irq_source_hpd - DC_IRQ_SOURCE_HPD1;
+
+			/* TODO: See same TODO in amdgpu_dm_hpd_init() */
+			if (irq_type < adev->mode_info.num_hpd) {
+				if (amdgpu_irq_put(adev, &adev->hpd_irq, irq_type))
+					drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n",
+						dc_link->irq_source_hpd);
+			} else {
+				dc_interrupt_set(adev->dm.dc,
+						 dc_link->irq_source_hpd,
+						 false);
+			}
 		}
 
 		if (dc_link->irq_source_hpd_rx != DC_IRQ_SOURCE_INVALID) {
@@ -968,10 +1000,4 @@ void amdgpu_dm_hpd_fini(struct amdgpu_device *adev)
 		}
 	}
 	drm_connector_list_iter_end(&iter);
-
-	/* Update reference counts for HPDs */
-	for (i = DC_IRQ_SOURCE_HPD1; i <= adev->mode_info.num_hpd; i++) {
-		if (amdgpu_irq_put(adev, &adev->hpd_irq, i - DC_IRQ_SOURCE_HPD1))
-			drm_err(dev, "DM_IRQ: Failed put HPD for source=%d!\n", i);
-	}
 }

From b5a981e1b34e44f94a5967f730fff4166f2101e8 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sat, 22 Feb 2025 23:37:32 -0600
Subject: [PATCH 1893/2753] drm/amd/display: fix default brightness

[Why]
To avoid flickering during boot default brightness level set by BIOS
should be maintained for as much of the boot as feasible.
commit 2fe87f54abdc ("drm/amd/display: Set default brightness according
to ACPI") attempted to set the right levels for AC vs DC, but brightness
still got reset to maximum level in initialization code for
setup_backlight_device().

[How]
Remove the hardcoded initialization in setup_backlight_device() and
instead program brightness value to match BIOS (AC or DC).  This avoids a
brightness flicker from kernel changing the value.  Userspace may however
still change it during boot.

Fixes: 2fe87f54abdc ("drm/amd/display: Set default brightness according to ACPI")
Acked-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 0747acf3311229e22009bec4a9e7fc30c879e842)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index f4fed93f2915a..4bd7f82c582dc 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -4911,6 +4911,7 @@ amdgpu_dm_register_backlight_device(struct amdgpu_dm_connector *aconnector)
 	dm->backlight_dev[aconnector->bl_idx] =
 		backlight_device_register(bl_name, aconnector->base.kdev, dm,
 					  &amdgpu_dm_backlight_ops, &props);
+	dm->brightness[aconnector->bl_idx] = props.brightness;
 
 	if (IS_ERR(dm->backlight_dev[aconnector->bl_idx])) {
 		DRM_ERROR("DM: Backlight registration failed!\n");
@@ -4978,7 +4979,6 @@ static void setup_backlight_device(struct amdgpu_display_manager *dm,
 	aconnector->bl_idx = bl_idx;
 
 	amdgpu_dm_update_backlight_caps(dm, bl_idx);
-	dm->brightness[bl_idx] = AMDGPU_MAX_BL_LEVEL;
 	dm->backlight_link[bl_idx] = link;
 	dm->num_of_edps++;
 

From 5760388d9681ac743038b846b9082b9023969551 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sun, 23 Feb 2025 00:04:35 -0600
Subject: [PATCH 1894/2753] drm/amd/display: Restore correct backlight
 brightness after a GPU reset

[Why]
GPU reset will attempt to restore cached state, but brightness doesn't
get restored. It will come back at 100% brightness, but userspace thinks
it's the previous value.

[How]
When running resume sequence if GPU is in reset restore brightness
to previous value.

Acked-by: Wayne Lin <Wayne.Lin@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 5e19e2b57b6bb640d68dfc7991e1e182922cf867)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
index 4bd7f82c582dc..74ad0d1240feb 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
@@ -245,6 +245,10 @@ static int amdgpu_dm_atomic_check(struct drm_device *dev,
 static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector);
 static void handle_hpd_rx_irq(void *param);
 
+static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+					 int bl_idx,
+					 u32 user_brightness);
+
 static bool
 is_timing_unchanged_for_freesync(struct drm_crtc_state *old_crtc_state,
 				 struct drm_crtc_state *new_crtc_state);
@@ -3371,6 +3375,12 @@ static int dm_resume(struct amdgpu_ip_block *ip_block)
 
 		mutex_unlock(&dm->dc_lock);
 
+		/* set the backlight after a reset */
+		for (i = 0; i < dm->num_of_edps; i++) {
+			if (dm->backlight_dev[i])
+				amdgpu_dm_backlight_set_level(dm, i, dm->brightness[i]);
+		}
+
 		return 0;
 	}
 

From 79e31396fdd7037c503e6add15af7cb00633ea92 Mon Sep 17 00:00:00 2001
From: Alex Hung <alex.hung@amd.com>
Date: Thu, 27 Feb 2025 16:36:25 -0700
Subject: [PATCH 1895/2753] drm/amd/display: Assign normalized_pix_clk when
 color depth = 14

[WHY & HOW]
A warning message "WARNING: CPU: 4 PID: 459 at ... /dc_resource.c:3397
calculate_phy_pix_clks+0xef/0x100 [amdgpu]" occurs because the
display_color_depth == COLOR_DEPTH_141414 is not handled. This is
observed in Radeon RX 6600 XT.

It is fixed by assigning pix_clk * (14 * 3) / 24 - same as the rests.

Also fixes the indentation in get_norm_pix_clk.

Reviewed-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 274a87eb389f58eddcbc5659ab0b180b37e92775)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/dc/core/dc_resource.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
index a45037cb4cc01..298668e9729c7 100644
--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
@@ -3389,10 +3389,13 @@ static int get_norm_pix_clk(const struct dc_crtc_timing *timing)
 			break;
 		case COLOR_DEPTH_121212:
 			normalized_pix_clk = (pix_clk * 36) / 24;
-		break;
+			break;
+		case COLOR_DEPTH_141414:
+			normalized_pix_clk = (pix_clk * 42) / 24;
+			break;
 		case COLOR_DEPTH_161616:
 			normalized_pix_clk = (pix_clk * 48) / 24;
-		break;
+			break;
 		default:
 			ASSERT(0);
 		break;

From e65e7bea220c3ce8c4c793b4ba35557f4994ab2b Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 28 Feb 2025 13:18:14 -0600
Subject: [PATCH 1896/2753] drm/amd/display: Fix slab-use-after-free on
 hdcp_work

[Why]
A slab-use-after-free is reported when HDCP is destroyed but the
property_validate_dwork queue is still running.

[How]
Cancel the delayed work when destroying workqueue.

Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/4006
Fixes: da3fd7ac0bcf ("drm/amd/display: Update CP property based on HW query")
Cc: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Alex Hung <alex.hung@amd.com>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Tom Chung <chiahsuan.chung@amd.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 725a04ba5a95e89c89633d4322430cfbca7ce128)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
index e339c7a8d541c..c0dc232440490 100644
--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
+++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_hdcp.c
@@ -455,6 +455,7 @@ void hdcp_destroy(struct kobject *kobj, struct hdcp_workqueue *hdcp_work)
 	for (i = 0; i < hdcp_work->max_link; i++) {
 		cancel_delayed_work_sync(&hdcp_work[i].callback_dwork);
 		cancel_delayed_work_sync(&hdcp_work[i].watchdog_timer_dwork);
+		cancel_delayed_work_sync(&hdcp_work[i].property_validate_dwork);
 	}
 
 	sysfs_remove_bin_file(kobj, &hdcp_work[0].attr);

From ded6ad4c6e2005e959ea09abba16c451433dd34b Mon Sep 17 00:00:00 2001
From: Alex Deucher <alexander.deucher@amd.com>
Date: Sun, 9 Mar 2025 12:26:50 -0400
Subject: [PATCH 1897/2753] drm/amdgpu/vce2: fix ip block reference

Need to use the correct IP block type.  VCE vs VCN.
Fixes mclk issues on Hawaii.

Suggested by selendym.

Fixes: 82ae6619a450 ("drm/amdgpu: update the handle ptr in wait_for_idle")
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/3997
Reviewed-by: Boyuan Zhang <Boyuan.Zhang@amd.com>
Cc: Sunil Khatri <sunil.khatri@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 02438acd252395628d74cfac692efbb676d21521)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdgpu/vce_v2_0.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
index c633b7ff29438..09fd6ef99b3d1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/vce_v2_0.c
@@ -284,7 +284,7 @@ static int vce_v2_0_stop(struct amdgpu_device *adev)
 		return 0;
 	}
 
-	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_VCN);
+	ip_block = amdgpu_device_ip_get_ip_block(adev, AMD_IP_BLOCK_TYPE_VCE);
 	if (!ip_block)
 		return -EINVAL;
 

From 366fef794bd2b7c2e9df933f6828dd9739bfba84 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ilpo.jarvinen@linux.intel.com>
Date: Mon, 10 Mar 2025 14:21:58 +0200
Subject: [PATCH 1898/2753] <linux/cleanup.h>: Allow the passing of both iomem
 and non-iomem pointers to no_free_ptr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Calling no_free_ptr() for an __iomem pointer results in Sparse
complaining about the types:

  warning: incorrect type in argument 1 (different address spaces)
     expected void const volatile *val
     got void [noderef] __iomem *__val

[ The example is from drivers/platform/x86/intel/pmc/core_ssram.c:283 ]

The problem is caused by the signature of __must_check_fn() added in:

  85be6d842447 ("cleanup: Make no_free_ptr() __must_check")

... to enforce that the return value is always used.

Use __force to allow both iomem and non-iomem pointers to be given for
no_free_ptr().

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/r/20250310122158.20966-1-ilpo.jarvinen@linux.intel.com
Closes: https://lore.kernel.org/oe-kbuild-all/202403050547.qnZtuNlN-lkp@intel.com/
---
 include/linux/cleanup.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index ec00e3f7af2b3..ee2614adb7858 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -212,7 +212,7 @@ const volatile void * __must_check_fn(const volatile void *val)
 { return val; }
 
 #define no_free_ptr(p) \
-	((typeof(p)) __must_check_fn(__get_and_null(p, NULL)))
+	((typeof(p)) __must_check_fn((__force const volatile void *)__get_and_null(p, NULL)))
 
 #define return_ptr(p)	return no_free_ptr(p)
 

From eab0396353be1c778eba1c0b5180176f04dd21ce Mon Sep 17 00:00:00 2001
From: Wentao Liang <vulab@iscas.ac.cn>
Date: Fri, 7 Mar 2025 10:18:20 +0800
Subject: [PATCH 1899/2753] net/mlx5: handle errors in
 mlx5_chains_create_table()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In mlx5_chains_create_table(), the return value of mlx5_get_fdb_sub_ns()
and mlx5_get_flow_namespace() must be checked to prevent NULL pointer
dereferences. If either function fails, the function should log error
message with mlx5_core_warn() and return error pointer.

Fixes: 39ac237ce009 ("net/mlx5: E-Switch, Refactor chains and priorities")
Signed-off-by: Wentao Liang <vulab@iscas.ac.cn>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250307021820.2646-1-vulab@iscas.ac.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index a80ecb672f33d..711d14dea2485 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -196,6 +196,11 @@ mlx5_chains_create_table(struct mlx5_fs_chains *chains,
 		ns = mlx5_get_flow_namespace(chains->dev, chains->ns);
 	}
 
+	if (!ns) {
+		mlx5_core_warn(chains->dev, "Failed to get flow namespace\n");
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	ft_attr.autogroup.num_reserved_entries = 2;
 	ft_attr.autogroup.max_num_groups = chains->group_num;
 	ft = mlx5_create_auto_grouped_flow_table(ns, &ft_attr);

From 2af5adf962d4611a576061501faa8fb39590407e Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 7 Mar 2025 01:12:09 +0000
Subject: [PATCH 1900/2753] virtio-net: Refactor napi_enable paths

Refactor virtnet_napi_enable and virtnet_napi_tx_enable to take a struct
receive_queue. Create a helper, virtnet_napi_do_enable, which contains
the logic to enable a NAPI.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20250307011215.266806-2-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 37 +++++++++++++++++++++----------------
 1 file changed, 21 insertions(+), 16 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index ac26a6201c444..133b004c7a9a9 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2807,7 +2807,8 @@ static void skb_recv_done(struct virtqueue *rvq)
 	virtqueue_napi_schedule(&rq->napi, rvq);
 }
 
-static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
+static void virtnet_napi_do_enable(struct virtqueue *vq,
+				   struct napi_struct *napi)
 {
 	napi_enable(napi);
 
@@ -2820,10 +2821,16 @@ static void virtnet_napi_enable(struct virtqueue *vq, struct napi_struct *napi)
 	local_bh_enable();
 }
 
-static void virtnet_napi_tx_enable(struct virtnet_info *vi,
-				   struct virtqueue *vq,
-				   struct napi_struct *napi)
+static void virtnet_napi_enable(struct receive_queue *rq)
 {
+	virtnet_napi_do_enable(rq->vq, &rq->napi);
+}
+
+static void virtnet_napi_tx_enable(struct send_queue *sq)
+{
+	struct virtnet_info *vi = sq->vq->vdev->priv;
+	struct napi_struct *napi = &sq->napi;
+
 	if (!napi->weight)
 		return;
 
@@ -2835,7 +2842,7 @@ static void virtnet_napi_tx_enable(struct virtnet_info *vi,
 		return;
 	}
 
-	return virtnet_napi_enable(vq, napi);
+	virtnet_napi_do_enable(sq->vq, napi);
 }
 
 static void virtnet_napi_tx_disable(struct napi_struct *napi)
@@ -2856,7 +2863,7 @@ static void refill_work(struct work_struct *work)
 
 		napi_disable(&rq->napi);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_enable(rq);
 
 		/* In theory, this can happen: if we don't get any buffers in
 		 * we will *never* try to fill again.
@@ -3073,8 +3080,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
-	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
-	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
+	virtnet_napi_enable(&vi->rq[qp_index]);
+	virtnet_napi_tx_enable(&vi->sq[qp_index]);
 
 	return 0;
 
@@ -3339,7 +3346,7 @@ static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
 		schedule_delayed_work(&vi->refill, 0);
 
 	if (running)
-		virtnet_napi_enable(rq->vq, &rq->napi);
+		virtnet_napi_enable(rq);
 }
 
 static int virtnet_rx_resize(struct virtnet_info *vi,
@@ -3402,7 +3409,7 @@ static void virtnet_tx_resume(struct virtnet_info *vi, struct send_queue *sq)
 	__netif_tx_unlock_bh(txq);
 
 	if (running)
-		virtnet_napi_tx_enable(vi, sq->vq, &sq->napi);
+		virtnet_napi_tx_enable(sq);
 }
 
 static int virtnet_tx_resize(struct virtnet_info *vi, struct send_queue *sq,
@@ -5983,9 +5990,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		if (old_prog)
 			bpf_prog_put(old_prog);
 		if (netif_running(dev)) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 
@@ -6000,9 +6006,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi);
-			virtnet_napi_tx_enable(vi, vi->sq[i].vq,
-					       &vi->sq[i].napi);
+			virtnet_napi_enable(&vi->rq[i]);
+			virtnet_napi_tx_enable(&vi->sq[i]);
 		}
 	}
 	if (prog)

From 986a93045183ae2f13e6d99d990ae8be36f6d6b0 Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 7 Mar 2025 01:12:10 +0000
Subject: [PATCH 1901/2753] virtio-net: Refactor napi_disable paths

Create virtnet_napi_disable helper and refactor virtnet_napi_tx_disable
to take a struct send_queue.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20250307011215.266806-3-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 25 +++++++++++++++++--------
 1 file changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 133b004c7a9a9..e578885c10938 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2845,12 +2845,21 @@ static void virtnet_napi_tx_enable(struct send_queue *sq)
 	virtnet_napi_do_enable(sq->vq, napi);
 }
 
-static void virtnet_napi_tx_disable(struct napi_struct *napi)
+static void virtnet_napi_tx_disable(struct send_queue *sq)
 {
+	struct napi_struct *napi = &sq->napi;
+
 	if (napi->weight)
 		napi_disable(napi);
 }
 
+static void virtnet_napi_disable(struct receive_queue *rq)
+{
+	struct napi_struct *napi = &rq->napi;
+
+	napi_disable(napi);
+}
+
 static void refill_work(struct work_struct *work)
 {
 	struct virtnet_info *vi =
@@ -2861,7 +2870,7 @@ static void refill_work(struct work_struct *work)
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
-		napi_disable(&rq->napi);
+		virtnet_napi_disable(rq);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
 		virtnet_napi_enable(rq);
 
@@ -3060,8 +3069,8 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
 
 static void virtnet_disable_queue_pair(struct virtnet_info *vi, int qp_index)
 {
-	virtnet_napi_tx_disable(&vi->sq[qp_index].napi);
-	napi_disable(&vi->rq[qp_index].napi);
+	virtnet_napi_tx_disable(&vi->sq[qp_index]);
+	virtnet_napi_disable(&vi->rq[qp_index]);
 	xdp_rxq_info_unreg(&vi->rq[qp_index].xdp_rxq);
 }
 
@@ -3333,7 +3342,7 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	bool running = netif_running(vi->dev);
 
 	if (running) {
-		napi_disable(&rq->napi);
+		virtnet_napi_disable(rq);
 		virtnet_cancel_dim(vi, &rq->dim);
 	}
 }
@@ -3375,7 +3384,7 @@ static void virtnet_tx_pause(struct virtnet_info *vi, struct send_queue *sq)
 	qindex = sq - vi->sq;
 
 	if (running)
-		virtnet_napi_tx_disable(&sq->napi);
+		virtnet_napi_tx_disable(sq);
 
 	txq = netdev_get_tx_queue(vi->dev, qindex);
 
@@ -5952,8 +5961,8 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
 		for (i = 0; i < vi->max_queue_pairs; i++) {
-			napi_disable(&vi->rq[i].napi);
-			virtnet_napi_tx_disable(&vi->sq[i].napi);
+			virtnet_napi_disable(&vi->rq[i]);
+			virtnet_napi_tx_disable(&vi->sq[i]);
 		}
 	}
 

From e7231f49d526823975bbfe0abde5c50b7e8dfe3a Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 7 Mar 2025 01:12:11 +0000
Subject: [PATCH 1902/2753] virtio-net: Map NAPIs to queues

Use netif_queue_set_napi to map NAPIs to queue IDs so that the mapping
can be accessed by user apps. Note that the netif_queue_set_napi
currently requires RTNL, so care must be taken to ensure RTNL is held on
paths where this API might be reached.

The paths in the driver where this API can be reached appear to be:

  - ndo_open, ndo_close, which hold RTNL so no driver change is needed.
  - rx_pause, rx_resume, tx_pause, tx_resume are reached either via
    an ethtool ioctl or via XSK - neither path requires a driver change.
  - power management paths (which call open and close), which have been
    updated to hold/release RTNL.

$ ethtool -i ens4 | grep driver
driver: virtio_net

$ sudo ethtool -L ens4 combined 4

$ ./tools/net/ynl/pyynl/cli.py \
       --spec Documentation/netlink/specs/netdev.yaml \
       --dump queue-get --json='{"ifindex": 2}'
[{'id': 0, 'ifindex': 2, 'napi-id': 8289, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8290, 'type': 'rx'},
 {'id': 2, 'ifindex': 2, 'napi-id': 8291, 'type': 'rx'},
 {'id': 3, 'ifindex': 2, 'napi-id': 8292, 'type': 'rx'},
 {'id': 0, 'ifindex': 2, 'type': 'tx'},
 {'id': 1, 'ifindex': 2, 'type': 'tx'},
 {'id': 2, 'ifindex': 2, 'type': 'tx'},
 {'id': 3, 'ifindex': 2, 'type': 'tx'}]

Note that virtio_net has TX-only NAPIs which do not have NAPI IDs, so
the lack of 'napi-id' in the above output is expected.

Signed-off-by: Joe Damato <jdamato@fastly.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20250307011215.266806-4-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 40 ++++++++++++++++++++++++++++++++++++----
 1 file changed, 36 insertions(+), 4 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e578885c10938..7bd63a677123a 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2823,13 +2823,18 @@ static void virtnet_napi_do_enable(struct virtqueue *vq,
 
 static void virtnet_napi_enable(struct receive_queue *rq)
 {
+	struct virtnet_info *vi = rq->vq->vdev->priv;
+	int qidx = vq2rxq(rq->vq);
+
 	virtnet_napi_do_enable(rq->vq, &rq->napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, &rq->napi);
 }
 
 static void virtnet_napi_tx_enable(struct send_queue *sq)
 {
 	struct virtnet_info *vi = sq->vq->vdev->priv;
 	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
 
 	if (!napi->weight)
 		return;
@@ -2843,20 +2848,28 @@ static void virtnet_napi_tx_enable(struct send_queue *sq)
 	}
 
 	virtnet_napi_do_enable(sq->vq, napi);
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, napi);
 }
 
 static void virtnet_napi_tx_disable(struct send_queue *sq)
 {
+	struct virtnet_info *vi = sq->vq->vdev->priv;
 	struct napi_struct *napi = &sq->napi;
+	int qidx = vq2txq(sq->vq);
 
-	if (napi->weight)
+	if (napi->weight) {
+		netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_TX, NULL);
 		napi_disable(napi);
+	}
 }
 
 static void virtnet_napi_disable(struct receive_queue *rq)
 {
+	struct virtnet_info *vi = rq->vq->vdev->priv;
 	struct napi_struct *napi = &rq->napi;
+	int qidx = vq2rxq(rq->vq);
 
+	netif_queue_set_napi(vi->dev, qidx, NETDEV_QUEUE_TYPE_RX, NULL);
 	napi_disable(napi);
 }
 
@@ -2870,9 +2883,23 @@ static void refill_work(struct work_struct *work)
 	for (i = 0; i < vi->curr_queue_pairs; i++) {
 		struct receive_queue *rq = &vi->rq[i];
 
-		virtnet_napi_disable(rq);
+		/*
+		 * When queue API support is added in the future and the call
+		 * below becomes napi_disable_locked, this driver will need to
+		 * be refactored.
+		 *
+		 * One possible solution would be to:
+		 *   - cancel refill_work with cancel_delayed_work (note:
+		 *     non-sync)
+		 *   - cancel refill_work with cancel_delayed_work_sync in
+		 *     virtnet_remove after the netdev is unregistered
+		 *   - wrap all of the work in a lock (perhaps the netdev
+		 *     instance lock)
+		 *   - check netif_running() and return early to avoid a race
+		 */
+		napi_disable(&rq->napi);
 		still_empty = !try_fill_recv(vi, rq, GFP_KERNEL);
-		virtnet_napi_enable(rq);
+		virtnet_napi_do_enable(rq->vq, &rq->napi);
 
 		/* In theory, this can happen: if we don't get any buffers in
 		 * we will *never* try to fill again.
@@ -5650,8 +5677,11 @@ static void virtnet_freeze_down(struct virtio_device *vdev)
 	netif_tx_lock_bh(vi->dev);
 	netif_device_detach(vi->dev);
 	netif_tx_unlock_bh(vi->dev);
-	if (netif_running(vi->dev))
+	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		virtnet_close(vi->dev);
+		rtnl_unlock();
+	}
 }
 
 static int init_vqs(struct virtnet_info *vi);
@@ -5671,7 +5701,9 @@ static int virtnet_restore_up(struct virtio_device *vdev)
 	enable_rx_mode_work(vi);
 
 	if (netif_running(vi->dev)) {
+		rtnl_lock();
 		err = virtnet_open(vi->dev);
+		rtnl_unlock();
 		if (err)
 			return err;
 	}

From d5d715207e2911b84b92f10420d4a8d7653aa98d Mon Sep 17 00:00:00 2001
From: Joe Damato <jdamato@fastly.com>
Date: Fri, 7 Mar 2025 01:12:12 +0000
Subject: [PATCH 1903/2753] virtio_net: Use persistent NAPI config

Use persistent NAPI config so that NAPI IDs are not renumbered as queue
counts change.

$ sudo ethtool -l ens4  | tail -5 | egrep -i '(current|combined)'
Current hardware settings:
Combined:       4

$ ./tools/net/ynl/pyynl/cli.py \
    --spec Documentation/netlink/specs/netdev.yaml \
    --dump queue-get --json='{"ifindex": 2}'
[{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'},
 {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'rx'},
 {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'rx'},
 {'id': 0, 'ifindex': 2, 'type': 'tx'},
 {'id': 1, 'ifindex': 2, 'type': 'tx'},
 {'id': 2, 'ifindex': 2, 'type': 'tx'},
 {'id': 3, 'ifindex': 2, 'type': 'tx'}]

Now adjust the queue count, note that the NAPI IDs are not renumbered:

$ sudo ethtool -L ens4 combined 1
$ ./tools/net/ynl/pyynl/cli.py \
    --spec Documentation/netlink/specs/netdev.yaml \
    --dump queue-get --json='{"ifindex": 2}'
[{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
 {'id': 0, 'ifindex': 2, 'type': 'tx'}]

$ sudo ethtool -L ens4 combined 8
$ ./tools/net/ynl/pyynl/cli.py \
    --spec Documentation/netlink/specs/netdev.yaml \
    --dump queue-get --json='{"ifindex": 2}'
[{'id': 0, 'ifindex': 2, 'napi-id': 8193, 'type': 'rx'},
 {'id': 1, 'ifindex': 2, 'napi-id': 8194, 'type': 'rx'},
 {'id': 2, 'ifindex': 2, 'napi-id': 8195, 'type': 'rx'},
 {'id': 3, 'ifindex': 2, 'napi-id': 8196, 'type': 'rx'},
 {'id': 4, 'ifindex': 2, 'napi-id': 8197, 'type': 'rx'},
 {'id': 5, 'ifindex': 2, 'napi-id': 8198, 'type': 'rx'},
 {'id': 6, 'ifindex': 2, 'napi-id': 8199, 'type': 'rx'},
 {'id': 7, 'ifindex': 2, 'napi-id': 8200, 'type': 'rx'},
 [...]

Signed-off-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Link: https://patch.msgid.link/20250307011215.266806-5-jdamato@fastly.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 7bd63a677123a..34cec2b11b74f 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -6455,8 +6455,9 @@ static int virtnet_alloc_queues(struct virtnet_info *vi)
 	INIT_DELAYED_WORK(&vi->refill, refill_work);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		vi->rq[i].pages = NULL;
-		netif_napi_add_weight(vi->dev, &vi->rq[i].napi, virtnet_poll,
-				      napi_weight);
+		netif_napi_add_config(vi->dev, &vi->rq[i].napi, virtnet_poll,
+				      i);
+		vi->rq[i].napi.weight = napi_weight;
 		netif_napi_add_tx_weight(vi->dev, &vi->sq[i].napi,
 					 virtnet_poll_tx,
 					 napi_tx ? napi_weight : 0);

From 54580ccdd8a9c6821fd6f72171d435480867e4c3 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 6 Mar 2025 22:34:08 -0500
Subject: [PATCH 1904/2753] ipv6: remove leftover ip6 cookie initializer

As of the blamed commit ipc6.dontfrag is always initialized at the
start of udpv6_sendmsg, by ipcm6_init_sk, to either 0 or 1.

Later checks against -1 are no longer needed and the branches are now
dead code.

The blamed commit had removed those branches. But I had overlooked
this one case.

UDP has both a lockless fast path and a slower path for corked
requests. This branch remained in the fast path.

Fixes: 096208592b09 ("ipv6: replace ipcm6_init calls with ipcm6_init_sk")
Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250307033620.411611-2-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_output.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d577bf2f30538..d91da522c34e7 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -2054,8 +2054,6 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 		ip6_cork_release(cork, &v6_cork);
 		return ERR_PTR(err);
 	}
-	if (ipc6->dontfrag < 0)
-		ipc6->dontfrag = inet6_test_bit(DONTFRAG, sk);
 
 	err = __ip6_append_data(sk, &queue, cork, &v6_cork,
 				&current->task_frag, getfrag, from,

From a18dfa9925b9ef6107ea3aa5814ca3c704d34a8a Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 6 Mar 2025 22:34:09 -0500
Subject: [PATCH 1905/2753] ipv6: save dontfrag in cork

When spanning datagram construction over multiple send calls using
MSG_MORE, per datagram settings are configured on the first send.

That is when ip(6)_setup_cork stores these settings for subsequent use
in __ip(6)_append_data and others.

The only flag that escaped this was dontfrag. As a result, a datagram
could be constructed with df=0 on the first sendmsg, but df=1 on a
next. Which is what cmsg_ip.sh does in an upcoming MSG_MORE test in
the "diff" scenario.

Changing datagram conditions in the middle of constructing an skb
makes this already complex code path even more convoluted. It is here
unintentional. Bring this flag in line with expected sockopt/cmsg
behavior.

And stop passing ipc6 to __ip6_append_data, to avoid such issues
in the future. This is already the case for __ip_append_data.

inet6_cork had a 6 byte hole, so the 1B flag has no impact.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250307033620.411611-3-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ipv6.h  | 1 +
 net/ipv6/ip6_output.c | 9 +++++----
 2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index a6e2aadbb91bd..5aeeed22f35bf 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -207,6 +207,7 @@ struct inet6_cork {
 	struct ipv6_txoptions *opt;
 	u8 hop_limit;
 	u8 tclass;
+	u8 dontfrag:1;
 };
 
 /* struct ipv6_pinfo - ipv6 private area */
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d91da522c34e7..581bc62890818 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1386,6 +1386,7 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork,
 	}
 	v6_cork->hop_limit = ipc6->hlimit;
 	v6_cork->tclass = ipc6->tclass;
+	v6_cork->dontfrag = ipc6->dontfrag;
 	if (rt->dst.flags & DST_XFRM_TUNNEL)
 		mtu = READ_ONCE(np->pmtudisc) >= IPV6_PMTUDISC_PROBE ?
 		      READ_ONCE(rt->dst.dev->mtu) : dst_mtu(&rt->dst);
@@ -1421,7 +1422,7 @@ static int __ip6_append_data(struct sock *sk,
 			     int getfrag(void *from, char *to, int offset,
 					 int len, int odd, struct sk_buff *skb),
 			     void *from, size_t length, int transhdrlen,
-			     unsigned int flags, struct ipcm6_cookie *ipc6)
+			     unsigned int flags)
 {
 	struct sk_buff *skb, *skb_prev = NULL;
 	struct inet_cork *cork = &cork_full->base;
@@ -1475,7 +1476,7 @@ static int __ip6_append_data(struct sock *sk,
 	if (headersize + transhdrlen > mtu)
 		goto emsgsize;
 
-	if (cork->length + length > mtu - headersize && ipc6->dontfrag &&
+	if (cork->length + length > mtu - headersize && v6_cork->dontfrag &&
 	    (sk->sk_protocol == IPPROTO_UDP ||
 	     sk->sk_protocol == IPPROTO_ICMPV6 ||
 	     sk->sk_protocol == IPPROTO_RAW)) {
@@ -1855,7 +1856,7 @@ int ip6_append_data(struct sock *sk,
 
 	return __ip6_append_data(sk, &sk->sk_write_queue, &inet->cork,
 				 &np->cork, sk_page_frag(sk), getfrag,
-				 from, length, transhdrlen, flags, ipc6);
+				 from, length, transhdrlen, flags);
 }
 EXPORT_SYMBOL_GPL(ip6_append_data);
 
@@ -2058,7 +2059,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk,
 	err = __ip6_append_data(sk, &queue, cork, &v6_cork,
 				&current->task_frag, getfrag, from,
 				length + exthdrlen, transhdrlen + exthdrlen,
-				flags, ipc6);
+				flags);
 	if (err) {
 		__ip6_flush_pending_frames(sk, &queue, cork, &v6_cork);
 		return ERR_PTR(err);

From 0922cb68edfde9e3920bb3aedea203d333af9f10 Mon Sep 17 00:00:00 2001
From: Willem de Bruijn <willemb@google.com>
Date: Thu, 6 Mar 2025 22:34:10 -0500
Subject: [PATCH 1906/2753] selftests/net: expand cmsg_ip with MSG_MORE

UDP send with MSG_MORE takes a slightly different path than the
lockless fast path.

For completeness, add coverage to this case too.

Pass MSG_MORE on the initial sendmsg, then follow up with a zero byte
write to unplug the cork.

Unrelated: also add two missing endlines in usage().

Signed-off-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250307033620.411611-4-willemdebruijn.kernel@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/cmsg_ip.sh    | 11 +++++++----
 tools/testing/selftests/net/cmsg_sender.c | 24 ++++++++++++++++++-----
 2 files changed, 26 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/net/cmsg_ip.sh b/tools/testing/selftests/net/cmsg_ip.sh
index 2a52520aca327..b55680e081ad7 100755
--- a/tools/testing/selftests/net/cmsg_ip.sh
+++ b/tools/testing/selftests/net/cmsg_ip.sh
@@ -50,8 +50,9 @@ check_result() {
 # IPV6_DONTFRAG
 for ovr in setsock cmsg both diff; do
     for df in 0 1; do
-	for p in u i r; do
+	for p in u U i r; do
 	    [ $p == "u" ] && prot=UDP
+	    [ $p == "U" ] && prot=UDP
 	    [ $p == "i" ] && prot=ICMP
 	    [ $p == "r" ] && prot=RAW
 
@@ -81,8 +82,9 @@ test_dscp() {
     ip $IPVER -netns $NS route add table 300 prohibit any
 
     for ovr in setsock cmsg both diff; do
-	for p in u i r; do
+	for p in u U i r; do
 	    [ $p == "u" ] && prot=UDP
+	    [ $p == "U" ] && prot=UDP
 	    [ $p == "i" ] && prot=ICMP
 	    [ $p == "r" ] && prot=RAW
 
@@ -134,8 +136,9 @@ test_ttl_hoplimit() {
     local -r LIM=4
 
     for ovr in setsock cmsg both diff; do
-	for p in u i r; do
+	for p in u U i r; do
 	    [ $p == "u" ] && prot=UDP
+	    [ $p == "U" ] && prot=UDP
 	    [ $p == "i" ] && prot=ICMP
 	    [ $p == "r" ] && prot=RAW
 
@@ -166,7 +169,7 @@ test_ttl_hoplimit -4 $TGT4 ttl
 test_ttl_hoplimit -6 $TGT6 hlim
 
 # IPV6 exthdr
-for p in u i r; do
+for p in u U i r; do
     # Very basic "does it crash" test
     for h in h d r; do
 	$NSEXE ./cmsg_sender -p $p -6 -H $h $TGT6 1234
diff --git a/tools/testing/selftests/net/cmsg_sender.c b/tools/testing/selftests/net/cmsg_sender.c
index 19bd8499031bf..a825e628aee73 100644
--- a/tools/testing/selftests/net/cmsg_sender.c
+++ b/tools/testing/selftests/net/cmsg_sender.c
@@ -33,6 +33,7 @@ enum {
 	ERN_RECVERR,
 	ERN_CMSG_RD,
 	ERN_CMSG_RCV,
+	ERN_SEND_MORE,
 };
 
 struct option_cmsg_u32 {
@@ -46,6 +47,7 @@ struct options {
 	const char *service;
 	unsigned int size;
 	unsigned int num_pkt;
+	bool msg_more;
 	struct {
 		unsigned int mark;
 		unsigned int dontfrag;
@@ -94,7 +96,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
 	       "\t\t-S      send() size\n"
 	       "\t\t-4/-6   Force IPv4 / IPv6 only\n"
 	       "\t\t-p prot Socket protocol\n"
-	       "\t\t        (u = UDP (default); i = ICMP; r = RAW)\n"
+	       "\t\t        (u = UDP (default); i = ICMP; r = RAW;\n"
+	       "\t\t         U = UDP with MSG_MORE)\n"
 	       "\n"
 	       "\t\t-m val  Set SO_MARK with given value\n"
 	       "\t\t-M val  Set SO_MARK via setsockopt\n"
@@ -109,8 +112,8 @@ static void __attribute__((noreturn)) cs_usage(const char *bin)
 	       "\t\t-l val  Set TTL/HOPLIMIT via cmsg\n"
 	       "\t\t-L val  Set TTL/HOPLIMIT via setsockopt\n"
 	       "\t\t-H type Add an IPv6 header option\n"
-	       "\t\t        (h = HOP; d = DST; r = RTDST)"
-	       "");
+	       "\t\t        (h = HOP; d = DST; r = RTDST)\n"
+	       "\n");
 	exit(ERN_HELP);
 }
 
@@ -133,8 +136,11 @@ static void cs_parse_args(int argc, char *argv[])
 			opt.sock.family = AF_INET6;
 			break;
 		case 'p':
-			if (*optarg == 'u' || *optarg == 'U') {
+			if (*optarg == 'u') {
 				opt.sock.proto = IPPROTO_UDP;
+			} else if (*optarg == 'U') {
+				opt.sock.proto = IPPROTO_UDP;
+				opt.msg_more = true;
 			} else if (*optarg == 'i' || *optarg == 'I') {
 				opt.sock.proto = IPPROTO_ICMP;
 			} else if (*optarg == 'r') {
@@ -531,7 +537,7 @@ int main(int argc, char *argv[])
 	cs_write_cmsg(fd, &msg, cbuf, sizeof(cbuf));
 
 	for (i = 0; i < opt.num_pkt; i++) {
-		err = sendmsg(fd, &msg, 0);
+		err = sendmsg(fd, &msg, opt.msg_more ? MSG_MORE : 0);
 		if (err < 0) {
 			if (!opt.silent_send)
 				fprintf(stderr, "send failed: %s\n", strerror(errno));
@@ -542,6 +548,14 @@ int main(int argc, char *argv[])
 			err = ERN_SEND_SHORT;
 			goto err_out;
 		}
+		if (opt.msg_more) {
+			err = write(fd, NULL, 0);
+			if (err < 0) {
+				fprintf(stderr, "send more: %s\n", strerror(errno));
+				err = ERN_SEND_MORE;
+				goto err_out;
+			}
+		}
 	}
 	err = ERN_SUCCESS;
 

From 473367a5ffe1607a61be481e2feda684eb5faea9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Fri, 7 Mar 2025 08:29:47 +0100
Subject: [PATCH 1907/2753] r8169: increase max jumbo packet size on
 RTL8125/RTL8126

Realtek confirmed that all RTL8125/RTL8126 chip versions support up to
16K jumbo packets. Reflect this in the driver.

Tested by Rui on RTL8125B with 12K jumbo packets.

Suggested-by: Rui Salvaterra <rsalvaterra@gmail.com>
Tested-by: Rui Salvaterra <rsalvaterra@gmail.com>
Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/396762ad-cc65-4e60-b01e-8847db89e98b@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index fa339bd8c775b..b18daeeda40d9 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -89,6 +89,7 @@
 #define JUMBO_6K	(6 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define JUMBO_7K	(7 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 #define JUMBO_9K	(9 * SZ_1K - VLAN_ETH_HLEN - ETH_FCS_LEN)
+#define JUMBO_16K	(SZ_16K - VLAN_ETH_HLEN - ETH_FCS_LEN)
 
 static const struct {
 	const char *name;
@@ -5360,6 +5361,9 @@ static int rtl_jumbo_max(struct rtl8169_private *tp)
 	/* RTL8168c */
 	case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24:
 		return JUMBO_6K;
+	/* RTL8125/8126 */
+	case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_71:
+		return JUMBO_16K;
 	default:
 		return JUMBO_9K;
 	}

From d0a4a1b36d7a71b45972ef33762c3fc082bec1db Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Fri, 7 Mar 2025 10:12:55 +0100
Subject: [PATCH 1908/2753] net: ethtool: tsinfo: Fix dump command

Fix missing initialization of ts_info->phc_index in the dump command,
which could cause a netdev interface to incorrectly display a PTP provider
at index 0 instead of "none".
Fix it by initializing the phc_index to -1.

In the same time, restore missing initialization of ts_info.cmd for the
IOCTL case, as it was before the transition from ethnl_default_dumpit to
custom ethnl_tsinfo_dumpit.

Also, remove unnecessary zeroing of ts_info, as it is embedded within
reply_data, which is fully zeroed two lines earlier.

Fixes: b9e3f7dc9ed95 ("net: ethtool: tsinfo: Enhance tsinfo to support several hwtstamp by net topology")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250307091255.463559-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ethtool/tsinfo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ethtool/tsinfo.c b/net/ethtool/tsinfo.c
index 691be6c445b38..ad3866c5a902b 100644
--- a/net/ethtool/tsinfo.c
+++ b/net/ethtool/tsinfo.c
@@ -290,7 +290,8 @@ static void *ethnl_tsinfo_prepare_dump(struct sk_buff *skb,
 	reply_data = ctx->reply_data;
 	memset(reply_data, 0, sizeof(*reply_data));
 	reply_data->base.dev = dev;
-	memset(&reply_data->ts_info, 0, sizeof(reply_data->ts_info));
+	reply_data->ts_info.cmd = ETHTOOL_GET_TS_INFO;
+	reply_data->ts_info.phc_index = -1;
 
 	return ehdr;
 }

From 991a1b09920bc15c66f64c1e7d15cdabd3816c46 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 7 Mar 2025 12:28:48 +0300
Subject: [PATCH 1909/2753] eth: fbnic: fix memory corruption in
 fbnic_tlv_attr_get_string()

This code is trying to ensure that the last byte of the buffer is a NUL
terminator.  However, the problem is that attr->value[] is an array of
__le32, not char, so it zeroes out 4 bytes way beyond the end of the
buffer.  Cast the buffer to char to address this.

Fixes: e5cf5107c9e4 ("eth: fbnic: Update fbnic_tlv_attr_get_string() to work like nla_strscpy()")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Lee Trager <lee@trager.us>
Link: https://patch.msgid.link/2791d4be-ade4-4e50-9b12-33307d8410f6@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/fbnic_tlv.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
index d558d176e0dfc..517ed8b2f1cb7 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_tlv.c
@@ -261,7 +261,7 @@ ssize_t fbnic_tlv_attr_get_string(struct fbnic_tlv_msg *attr, char *dst,
 		return -E2BIG;
 
 	srclen = le16_to_cpu(attr->hdr.len) - sizeof(*attr);
-	if (srclen > 0 && attr->value[srclen - 1] == '\0')
+	if (srclen > 0 && ((char *)attr->value)[srclen - 1] == '\0')
 		srclen--;
 
 	if (srclen >= dstsize) {

From cfa693bf9d5361608e2963f5dae053b3695af8eb Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 7 Mar 2025 11:12:23 +0100
Subject: [PATCH 1910/2753] net: usb: lan78xx: Sanitize return values of
 register read/write functions

usb_control_msg() returns the number of transferred bytes or a negative
error code. The current implementation propagates the transferred byte
count, which is unintended. This affects code paths that assume a
boolean success/failure check, such as the EEPROM detection logic.

Fix this by ensuring lan78xx_read_reg() and lan78xx_write_reg() return
only 0 on success and preserve negative error codes.

This approach is consistent with existing usage, as the transferred byte
count is not explicitly checked elsewhere.

Fixes: 8b1b2ca83b20 ("net: usb: lan78xx: Improve error handling in EEPROM and OTP operations")
Reported-by: Mark Brown <broonie@kernel.org>
Closes: https://lore.kernel.org/all/ac965de8-f320-430f-80f6-b16f4e1ba06d@sirena.org.uk
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Tested-by: Mark Brown <broonie@kernel.org>
Link: https://patch.msgid.link/20250307101223.3025632-1-o.rempel@pengutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/lan78xx.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index a91bf9c7e31d2..137adf6d5b08a 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -627,7 +627,7 @@ static int lan78xx_read_reg(struct lan78xx_net *dev, u32 index, u32 *data)
 
 	kfree(buf);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data)
@@ -658,7 +658,7 @@ static int lan78xx_write_reg(struct lan78xx_net *dev, u32 index, u32 data)
 
 	kfree(buf);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 
 static int lan78xx_update_reg(struct lan78xx_net *dev, u32 reg, u32 mask,

From 9f7b2aa5034e24d3c49db73d5f760c0435fe31c2 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:12 +0000
Subject: [PATCH 1911/2753] eth: bnxt: fix truesize for mb-xdp-pass case

When mb-xdp is set and return is XDP_PASS, packet is converted from
xdp_buff to sk_buff with xdp_update_skb_shared_info() in
bnxt_xdp_build_skb().
bnxt_xdp_build_skb() passes incorrect truesize argument to
xdp_update_skb_shared_info().
The truesize is calculated as BNXT_RX_PAGE_SIZE * sinfo->nr_frags but
the skb_shared_info was wiped by napi_build_skb() before.
So it stores sinfo->nr_frags before bnxt_xdp_build_skb() and use it
instead of getting skb_shared_info from xdp_get_shared_info_from_buff().

Splat looks like:
 ------------[ cut here ]------------
 WARNING: CPU: 2 PID: 0 at net/core/skbuff.c:6072 skb_try_coalesce+0x504/0x590
 Modules linked in: xt_nat xt_tcpudp veth af_packet xt_conntrack nft_chain_nat xt_MASQUERADE nf_conntrack_netlink xfrm_user xt_addrtype nft_coms
 CPU: 2 UID: 0 PID: 0 Comm: swapper/2 Not tainted 6.14.0-rc2+ #3
 RIP: 0010:skb_try_coalesce+0x504/0x590
 Code: 4b fd ff ff 49 8b 34 24 40 80 e6 40 0f 84 3d fd ff ff 49 8b 74 24 48 40 f6 c6 01 0f 84 2e fd ff ff 48 8d 4e ff e9 25 fd ff ff <0f> 0b e99
 RSP: 0018:ffffb62c4120caa8 EFLAGS: 00010287
 RAX: 0000000000000003 RBX: ffffb62c4120cb14 RCX: 0000000000000ec0
 RDX: 0000000000001000 RSI: ffffa06e5d7dc000 RDI: 0000000000000003
 RBP: ffffa06e5d7ddec0 R08: ffffa06e6120a800 R09: ffffa06e7a119900
 R10: 0000000000002310 R11: ffffa06e5d7dcec0 R12: ffffe4360575f740
 R13: ffffe43600000000 R14: 0000000000000002 R15: 0000000000000002
 FS:  0000000000000000(0000) GS:ffffa0755f700000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f147b76b0f8 CR3: 00000001615d4000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  <IRQ>
  ? __warn+0x84/0x130
  ? skb_try_coalesce+0x504/0x590
  ? report_bug+0x18a/0x1a0
  ? handle_bug+0x53/0x90
  ? exc_invalid_op+0x14/0x70
  ? asm_exc_invalid_op+0x16/0x20
  ? skb_try_coalesce+0x504/0x590
  inet_frag_reasm_finish+0x11f/0x2e0
  ip_defrag+0x37a/0x900
  ip_local_deliver+0x51/0x120
  ip_sublist_rcv_finish+0x64/0x70
  ip_sublist_rcv+0x179/0x210
  ip_list_rcv+0xf9/0x130

How to reproduce:
<Node A>
ip link set $interface1 xdp obj xdp_pass.o
ip link set $interface1 mtu 9000 up
ip a a 10.0.0.1/24 dev $interface1
<Node B>
ip link set $interfac2 mtu 9000 up
ip a a 10.0.0.2/24 dev $interface2
ping 10.0.0.1 -s 65000

Following ping.py patch adds xdp-mb-pass case. so ping.py is going to be
able to reproduce this issue.

Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250309134219.91670-2-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     | 8 ++++++++
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 7b8b5b39c7bbe..6b5fe4ee7a99b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2038,6 +2038,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 	struct rx_cmp_ext *rxcmp1;
 	u32 tmp_raw_cons = *raw_cons;
 	u16 cons, prod, cp_cons = RING_CMP(tmp_raw_cons);
+	struct skb_shared_info *sinfo;
 	struct bnxt_sw_rx_bd *rx_buf;
 	unsigned int len;
 	u8 *data_ptr, agg_bufs, cmp_type;
@@ -2164,6 +2165,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 							     false);
 			if (!frag_len)
 				goto oom_next_rx;
+
 		}
 		xdp_active = true;
 	}
@@ -2173,6 +2175,12 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			rc = 1;
 			goto next_rx;
 		}
+		if (xdp_buff_has_frags(&xdp)) {
+			sinfo = xdp_get_shared_info_from_buff(&xdp);
+			agg_bufs = sinfo->nr_frags;
+		} else {
+			agg_bufs = 0;
+		}
 	}
 
 	if (len <= bp->rx_copybreak) {
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index e6c64e4bd66c3..e9b49cb5b735b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -476,7 +476,7 @@ bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
 	}
 	xdp_update_skb_shared_info(skb, num_frags,
 				   sinfo->xdp_frags_size,
-				   BNXT_RX_PAGE_SIZE * sinfo->nr_frags,
+				   BNXT_RX_PAGE_SIZE * num_frags,
 				   xdp_buff_is_frag_pfmemalloc(xdp));
 	return skb;
 }

From ca2456e073957781e1184de68551c65161b2bd30 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:13 +0000
Subject: [PATCH 1912/2753] eth: bnxt: return fail if interface is down in
 bnxt_queue_mem_alloc()

The bnxt_queue_mem_alloc() is called to allocate new queue memory when
a queue is restarted.
It internally accesses rx buffer descriptor corresponding to the index.
The rx buffer descriptor is allocated and set when the interface is up
and it's freed when the interface is down.
So, if queue is restarted if interface is down, kernel panic occurs.

Splat looks like:
 BUG: unable to handle page fault for address: 000000000000b240
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 3 UID: 0 PID: 1563 Comm: ncdevmem2 Not tainted 6.14.0-rc2+ #9 844ddba6e7c459cafd0bf4db9a3198e
 Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
 RIP: 0010:bnxt_queue_mem_alloc+0x3f/0x4e0 [bnxt_en]
 Code: 41 54 4d 89 c4 4d 69 c0 c0 05 00 00 55 48 89 f5 53 48 89 fb 4c 8d b5 40 05 00 00 48 83 ec 15
 RSP: 0018:ffff9dcc83fef9e8 EFLAGS: 00010202
 RAX: ffffffffc0457720 RBX: ffff934ed8d40000 RCX: 0000000000000000
 RDX: 000000000000001f RSI: ffff934ea508f800 RDI: ffff934ea508f808
 RBP: ffff934ea508f800 R08: 000000000000b240 R09: ffff934e84f4b000
 R10: ffff9dcc83fefa30 R11: ffff934e84f4b000 R12: 000000000000001f
 R13: ffff934ed8d40ac0 R14: ffff934ea508fd40 R15: ffff934e84f4b000
 FS:  00007fa73888c740(0000) GS:ffff93559f780000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 000000000000b240 CR3: 0000000145a2e000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __die+0x20/0x70
  ? page_fault_oops+0x15a/0x460
  ? exc_page_fault+0x6e/0x180
  ? asm_exc_page_fault+0x22/0x30
  ? __pfx_bnxt_queue_mem_alloc+0x10/0x10 [bnxt_en 7f85e76f4d724ba07471d7e39d9e773aea6597b7]
  ? bnxt_queue_mem_alloc+0x3f/0x4e0 [bnxt_en 7f85e76f4d724ba07471d7e39d9e773aea6597b7]
  netdev_rx_queue_restart+0xc5/0x240
  net_devmem_bind_dmabuf_to_queue+0xf8/0x200
  netdev_nl_bind_rx_doit+0x3a7/0x450
  genl_family_rcv_msg_doit+0xd9/0x130
  genl_rcv_msg+0x184/0x2b0
  ? __pfx_netdev_nl_bind_rx_doit+0x10/0x10
  ? __pfx_genl_rcv_msg+0x10/0x10
  netlink_rcv_skb+0x54/0x100
  genl_rcv+0x24/0x40
...

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Fixes: 2d694c27d32e ("bnxt_en: implement netdev_queue_mgmt_ops")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250309134219.91670-3-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6b5fe4ee7a99b..acb9500ef9307 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15447,6 +15447,9 @@ static int bnxt_queue_mem_alloc(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_ring_struct *ring;
 	int rc;
 
+	if (!bp->rx_ring)
+		return -ENETDOWN;
+
 	rxr = &bp->rx_ring[idx];
 	clone = qmem;
 	memcpy(clone, rxr, sizeof(*rxr));

From 661958552eda5bf64bfafb4821cbdded935f1f68 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:14 +0000
Subject: [PATCH 1913/2753] eth: bnxt: do not use BNXT_VNIC_NTUPLE
 unconditionally in queue restart logic

When a queue is restarted, it sets MRU to 0 for stopping packet flow.
MRU variable is a member of vnic_info[], the first vnic_info is default
and the second is ntuple.
Only when ntuple is enabled(ethtool -K eth0 ntuple on), vnic_info for
ntuple is allocated in init logic.
The bp->nr_vnics indicates how many vnic_info are allocated.
However bnxt_queue_{start | stop}() accesses vnic_info[BNXT_VNIC_NTUPLE]
regardless of ntuple state.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Fixes: b9d2956e869c ("bnxt_en: stop packet flow during bnxt_queue_stop/start")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250309134219.91670-4-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index acb9500ef9307..218109ee1c234 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15643,7 +15643,7 @@ static int bnxt_queue_start(struct net_device *dev, void *qmem, int idx)
 	cpr = &rxr->bnapi->cp_ring;
 	cpr->sw_stats->rx.rx_resets++;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	for (i = 0; i <= bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 
 		rc = bnxt_hwrm_vnic_set_rss_p5(bp, vnic, true);
@@ -15671,7 +15671,7 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 	struct bnxt_vnic_info *vnic;
 	int i;
 
-	for (i = 0; i <= BNXT_VNIC_NTUPLE; i++) {
+	for (i = 0; i <= bp->nr_vnics; i++) {
 		vnic = &bp->vnic_info[i];
 		vnic->mru = 0;
 		bnxt_hwrm_vnic_update(bp, vnic,

From c03e7d05aa0e2f7e9a9ce5ad8a12471a53f941dc Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:15 +0000
Subject: [PATCH 1914/2753] eth: bnxt: do not update checksum in
 bnxt_xdp_build_skb()

The bnxt_rx_pkt() updates ip_summed value at the end if checksum offload
is enabled.
When the XDP-MB program is attached and it returns XDP_PASS, the
bnxt_xdp_build_skb() is called to update skb_shared_info.
The main purpose of bnxt_xdp_build_skb() is to update skb_shared_info,
but it updates ip_summed value too if checksum offload is enabled.
This is actually duplicate work.

When the bnxt_rx_pkt() updates ip_summed value, it checks if ip_summed
is CHECKSUM_NONE or not.
It means that ip_summed should be CHECKSUM_NONE at this moment.
But ip_summed may already be updated to CHECKSUM_UNNECESSARY in the
XDP-MB-PASS path.
So the by skb_checksum_none_assert() WARNS about it.

This is duplicate work and updating ip_summed in the
bnxt_xdp_build_skb() is not needed.

Splat looks like:
WARNING: CPU: 3 PID: 5782 at ./include/linux/skbuff.h:5155 bnxt_rx_pkt+0x479b/0x7610 [bnxt_en]
Modules linked in: bnxt_re bnxt_en rdma_ucm rdma_cm iw_cm ib_cm ib_uverbs veth xt_nat xt_tcpudp xt_conntrack nft_chain_nat xt_MASQUERADE nf_]
CPU: 3 UID: 0 PID: 5782 Comm: socat Tainted: G        W          6.14.0-rc4+ #27
Tainted: [W]=WARN
Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
RIP: 0010:bnxt_rx_pkt+0x479b/0x7610 [bnxt_en]
Code: 54 24 0c 4c 89 f1 4c 89 ff c1 ea 1f ff d3 0f 1f 00 49 89 c6 48 85 c0 0f 84 4c e5 ff ff 48 89 c7 e8 ca 3d a0 c8 e9 8f f4 ff ff <0f> 0b f
RSP: 0018:ffff88881ba09928 EFLAGS: 00010202
RAX: 0000000000000000 RBX: 00000000c7590303 RCX: 0000000000000000
RDX: 1ffff1104e7d1610 RSI: 0000000000000001 RDI: ffff8881c91300b8
RBP: ffff88881ba09b28 R08: ffff888273e8b0d0 R09: ffff888273e8b070
R10: ffff888273e8b010 R11: ffff888278b0f000 R12: ffff888273e8b080
R13: ffff8881c9130e00 R14: ffff8881505d3800 R15: ffff888273e8b000
FS:  00007f5a2e7be080(0000) GS:ffff88881ba00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fff2e708ff8 CR3: 000000013e3b0000 CR4: 00000000007506f0
PKRU: 55555554
Call Trace:
 <IRQ>
 ? __warn+0xcd/0x2f0
 ? bnxt_rx_pkt+0x479b/0x7610
 ? report_bug+0x326/0x3c0
 ? handle_bug+0x53/0xa0
 ? exc_invalid_op+0x14/0x50
 ? asm_exc_invalid_op+0x16/0x20
 ? bnxt_rx_pkt+0x479b/0x7610
 ? bnxt_rx_pkt+0x3e41/0x7610
 ? __pfx_bnxt_rx_pkt+0x10/0x10
 ? napi_complete_done+0x2cf/0x7d0
 __bnxt_poll_work+0x4e8/0x1220
 ? __pfx___bnxt_poll_work+0x10/0x10
 ? __pfx_mark_lock.part.0+0x10/0x10
 bnxt_poll_p5+0x36a/0xfa0
 ? __pfx_bnxt_poll_p5+0x10/0x10
 __napi_poll.constprop.0+0xa0/0x440
 net_rx_action+0x899/0xd00
...

Following ping.py patch adds xdp-mb-pass case. so ping.py is going
to be able to reproduce this issue.

Fixes: 1dc4c557bfed ("bnxt: adding bnxt_xdp_build_skb to build skb from multibuffer xdp_buff")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://patch.msgid.link/20250309134219.91670-5-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c     |  3 ++-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 11 ++---------
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h |  3 +--
 3 files changed, 5 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 218109ee1c234..9afb2c5072b13 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2218,7 +2218,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr,
 			if (!skb)
 				goto oom_next_rx;
 		} else {
-			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs, rxr->page_pool, &xdp, rxcmp1);
+			skb = bnxt_xdp_build_skb(bp, skb, agg_bufs,
+						 rxr->page_pool, &xdp);
 			if (!skb) {
 				/* we should be able to free the old skb here */
 				bnxt_xdp_buff_frags_free(rxr, &xdp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index e9b49cb5b735b..299822cacca48 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -460,20 +460,13 @@ int bnxt_xdp(struct net_device *dev, struct netdev_bpf *xdp)
 
 struct sk_buff *
 bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb, u8 num_frags,
-		   struct page_pool *pool, struct xdp_buff *xdp,
-		   struct rx_cmp_ext *rxcmp1)
+		   struct page_pool *pool, struct xdp_buff *xdp)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
 
 	if (!skb)
 		return NULL;
-	skb_checksum_none_assert(skb);
-	if (RX_CMP_L4_CS_OK(rxcmp1)) {
-		if (bp->dev->features & NETIF_F_RXCSUM) {
-			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			skb->csum_level = RX_CMP_ENCAP(rxcmp1);
-		}
-	}
+
 	xdp_update_skb_shared_info(skb, num_frags,
 				   sinfo->xdp_frags_size,
 				   BNXT_RX_PAGE_SIZE * num_frags,
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
index 0122782400b8a..220285e190fcd 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.h
@@ -33,6 +33,5 @@ void bnxt_xdp_buff_frags_free(struct bnxt_rx_ring_info *rxr,
 			      struct xdp_buff *xdp);
 struct sk_buff *bnxt_xdp_build_skb(struct bnxt *bp, struct sk_buff *skb,
 				   u8 num_frags, struct page_pool *pool,
-				   struct xdp_buff *xdp,
-				   struct rx_cmp_ext *rxcmp1);
+				   struct xdp_buff *xdp);
 #endif

From f09af5fdfbd9b0fcee73aab1116904c53b199e97 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:16 +0000
Subject: [PATCH 1915/2753] eth: bnxt: fix kernel panic in the
 bnxt_get_queue_stats{rx | tx}

When qstats-get operation is executed, callbacks of netdev_stats_ops
are called. The bnxt_get_queue_stats{rx | tx} collect per-queue stats
from sw_stats in the rings.
But {rx | tx | cp}_ring are allocated when the interface is up.
So, these rings are not allocated when the interface is down.

The qstats-get is allowed even if the interface is down. However,
the bnxt_get_queue_stats{rx | tx}() accesses cp_ring and tx_ring
without null check.
So, it needs to avoid accessing rings if the interface is down.

Reproducer:
 ip link set $interface down
 ./cli.py --spec netdev.yaml --dump qstats-get
OR
 ip link set $interface down
 python ./stats.py

Splat looks like:
 BUG: kernel NULL pointer dereference, address: 0000000000000000
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 1680fa067 P4D 1680fa067 PUD 16be3b067 PMD 0
 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 0 UID: 0 PID: 1495 Comm: python3 Not tainted 6.14.0-rc4+ #32 5cd0f999d5a15c574ac72b3e4b907341
 Hardware name: ASUS System Product Name/PRIME Z690-P D4, BIOS 0603 11/01/2021
 RIP: 0010:bnxt_get_queue_stats_rx+0xf/0x70 [bnxt_en]
 Code: c6 87 b5 18 00 00 02 eb a2 66 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 01
 RSP: 0018:ffffabef43cdb7e0 EFLAGS: 00010282
 RAX: 0000000000000000 RBX: ffffffffc04c8710 RCX: 0000000000000000
 RDX: ffffabef43cdb858 RSI: 0000000000000000 RDI: ffff8d504e850000
 RBP: ffff8d506c9f9c00 R08: 0000000000000004 R09: ffff8d506bcd901c
 R10: 0000000000000015 R11: ffff8d506bcd9000 R12: 0000000000000000
 R13: ffffabef43cdb8c0 R14: ffff8d504e850000 R15: 0000000000000000
 FS:  00007f2c5462b080(0000) GS:ffff8d575f600000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000000 CR3: 0000000167fd0000 CR4: 00000000007506f0
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __die+0x20/0x70
  ? page_fault_oops+0x15a/0x460
  ? sched_balance_find_src_group+0x58d/0xd10
  ? exc_page_fault+0x6e/0x180
  ? asm_exc_page_fault+0x22/0x30
  ? bnxt_get_queue_stats_rx+0xf/0x70 [bnxt_en cdd546fd48563c280cfd30e9647efa420db07bf1]
  netdev_nl_stats_by_netdev+0x2b1/0x4e0
  ? xas_load+0x9/0xb0
  ? xas_find+0x183/0x1d0
  ? xa_find+0x8b/0xe0
  netdev_nl_qstats_get_dumpit+0xbf/0x1e0
  genl_dumpit+0x31/0x90
  netlink_dump+0x1a8/0x360

Fixes: af7b3b4adda5 ("eth: bnxt: support per-queue statistics")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Link: https://patch.msgid.link/20250309134219.91670-6-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 9afb2c5072b13..bee12d9b57aba 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15384,6 +15384,9 @@ static void bnxt_get_queue_stats_rx(struct net_device *dev, int i,
 	struct bnxt_cp_ring_info *cpr;
 	u64 *sw;
 
+	if (!bp->bnapi)
+		return;
+
 	cpr = &bp->bnapi[i]->cp_ring;
 	sw = cpr->stats.sw_stats;
 
@@ -15407,6 +15410,9 @@ static void bnxt_get_queue_stats_tx(struct net_device *dev, int i,
 	struct bnxt_napi *bnapi;
 	u64 *sw;
 
+	if (!bp->tx_ring)
+		return;
+
 	bnapi = bp->tx_ring[bp->tx_ring_map[i]].bnapi;
 	sw = bnapi->cp_ring.stats.sw_stats;
 

From 87dd2850835dd7886726b428a8ef7d73a60520c7 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:17 +0000
Subject: [PATCH 1916/2753] eth: bnxt: fix memory leak in queue reset

When the queue is reset, the bnxt_alloc_one_tpa_info() is called to
allocate tpa_info for the new queue.
And then the old queue's tpa_info should be removed by the
bnxt_free_one_tpa_info(), but it is not called.
So memory leak occurs.
It adds the bnxt_free_one_tpa_info() in the bnxt_queue_mem_free().

unreferenced object 0xffff888293cc0000 (size 16384):
  comm "ncdevmem", pid 2076, jiffies 4296604081
  hex dump (first 32 bytes):
    00 00 00 00 00 00 00 00 40 75 78 93 82 88 ff ff  ........@ux.....
    40 75 78 93 02 00 00 00 00 00 00 00 00 00 00 00  @ux.............
  backtrace (crc 5d7d4798):
    ___kmalloc_large_node+0x10d/0x1b0
    __kmalloc_large_node_noprof+0x17/0x60
    __kmalloc_noprof+0x3f6/0x520
    bnxt_alloc_one_tpa_info+0x5f/0x300 [bnxt_en]
    bnxt_queue_mem_alloc+0x8e8/0x14f0 [bnxt_en]
    netdev_rx_queue_restart+0x233/0x620
    net_devmem_bind_dmabuf_to_queue+0x2a3/0x600
    netdev_nl_bind_rx_doit+0xc00/0x10a0
    genl_family_rcv_msg_doit+0x1d4/0x2b0
    genl_rcv_msg+0x3fb/0x6c0
    netlink_rcv_skb+0x12c/0x360
    genl_rcv+0x24/0x40
    netlink_unicast+0x447/0x710
    netlink_sendmsg+0x712/0xbc0
    __sys_sendto+0x3fd/0x4d0
    __x64_sys_sendto+0xdc/0x1b0

Fixes: 2d694c27d32e ("bnxt_en: implement netdev_queue_mgmt_ops")
Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250309134219.91670-7-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index bee12d9b57aba..55f553debd3b2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -15539,6 +15539,7 @@ static void bnxt_queue_mem_free(struct net_device *dev, void *qmem)
 	struct bnxt_ring_struct *ring;
 
 	bnxt_free_one_rx_ring_skbs(bp, rxr);
+	bnxt_free_one_tpa_info(bp, rxr);
 
 	xdp_rxq_info_unreg(&rxr->xdp_rxq);
 

From a70f891e0fa0435379ad4950e156a15a4ef88b4d Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:18 +0000
Subject: [PATCH 1917/2753] net: devmem: do not WARN conditionally after
 netdev_rx_queue_restart()

When devmem socket is closed, netdev_rx_queue_restart() is called to
reset queue by the net_devmem_unbind_dmabuf(). But callback may return
-ENETDOWN if the interface is down because queues are already freed
when the interface is down so queue reset is not needed.
So, it should not warn if the return value is -ENETDOWN.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250309134219.91670-8-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/devmem.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/devmem.c b/net/core/devmem.c
index 3bba3f018df03..0e5a2c672efd8 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -109,6 +109,7 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 	struct netdev_rx_queue *rxq;
 	unsigned long xa_idx;
 	unsigned int rxq_idx;
+	int err;
 
 	if (binding->list.next)
 		list_del(&binding->list);
@@ -120,7 +121,8 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 
 		rxq_idx = get_netdev_rx_queue_index(rxq);
 
-		WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
+		err = netdev_rx_queue_restart(binding->dev, rxq_idx);
+		WARN_ON(err && err != -ENETDOWN);
 	}
 
 	xa_erase(&net_devmem_dmabuf_bindings, binding->id);

From 75cc19c8ff8932d7da23480a49d1f9a050289c37 Mon Sep 17 00:00:00 2001
From: Taehee Yoo <ap420073@gmail.com>
Date: Sun, 9 Mar 2025 13:42:19 +0000
Subject: [PATCH 1918/2753] selftests: drv-net: add xdp cases for ping.py

ping.py has 3 cases, test_v4, test_v6 and test_tcp.
But these cases are not executed on the XDP environment.
So, it adds XDP environment, existing tests(test_v4, test_v6, and
test_tcp) are executed too on the below XDP environment.
So, it adds XDP cases.
1. xdp-generic + single-buffer
2. xdp-generic + multi-buffer
3. xdp-native + single-buffer
4. xdp-native + multi-buffer
5. xdp-offload

It also makes test_{v4 | v6 | tcp} sending large size packets. this may
help to check whether multi-buffer is working or not.

Note that the physical interface may be down and then up when xdp is
attached or detached.
This takes some period to activate traffic. So sleep(10) is
added if the test interface is the physical interface.
netdevsim and veth type interfaces skip sleep.

Signed-off-by: Taehee Yoo <ap420073@gmail.com>
Link: https://patch.msgid.link/20250309134219.91670-9-ap420073@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/ping.py   | 200 ++++++++++++++++--
 .../testing/selftests/net/lib/xdp_dummy.bpf.c |   6 +
 2 files changed, 191 insertions(+), 15 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index eb83e7b487978..93f4b411b378f 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -1,49 +1,219 @@
 #!/usr/bin/env python3
 # SPDX-License-Identifier: GPL-2.0
 
+import os
+import random, string, time
 from lib.py import ksft_run, ksft_exit
-from lib.py import ksft_eq
-from lib.py import NetDrvEpEnv
+from lib.py import ksft_eq, KsftSkipEx, KsftFailEx
+from lib.py import EthtoolFamily, NetDrvEpEnv
 from lib.py import bkg, cmd, wait_port_listen, rand_port
+from lib.py import ethtool, ip
 
+remote_ifname=""
+no_sleep=False
 
-def test_v4(cfg) -> None:
+def _test_v4(cfg) -> None:
     cfg.require_v4()
 
     cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}")
     cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote)
+    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v4}")
+    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v4}", host=cfg.remote)
 
-
-def test_v6(cfg) -> None:
+def _test_v6(cfg) -> None:
     cfg.require_v6()
 
-    cmd(f"ping -c 1 -W0.5 {cfg.remote_v6}")
-    cmd(f"ping -c 1 -W0.5 {cfg.v6}", host=cfg.remote)
-
+    cmd(f"ping -c 1 -W5 {cfg.remote_v6}")
+    cmd(f"ping -c 1 -W5 {cfg.v6}", host=cfg.remote)
+    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v6}")
+    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v6}", host=cfg.remote)
 
-def test_tcp(cfg) -> None:
+def _test_tcp(cfg) -> None:
     cfg.require_cmd("socat", remote=True)
 
     port = rand_port()
     listen_cmd = f"socat -{cfg.addr_ipver} -t 2 -u TCP-LISTEN:{port},reuseport STDOUT"
 
+    test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(65536))
     with bkg(listen_cmd, exit_wait=True) as nc:
         wait_port_listen(port)
 
-        cmd(f"echo ping | socat -t 2 -u STDIN TCP:{cfg.baddr}:{port}",
+        cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.baddr}:{port}",
             shell=True, host=cfg.remote)
-    ksft_eq(nc.stdout.strip(), "ping")
+    ksft_eq(nc.stdout.strip(), test_string)
 
+    test_string = ''.join(random.choice(string.ascii_lowercase) for _ in range(65536))
     with bkg(listen_cmd, host=cfg.remote, exit_wait=True) as nc:
         wait_port_listen(port, host=cfg.remote)
 
-        cmd(f"echo ping | socat -t 2 -u STDIN TCP:{cfg.remote_baddr}:{port}", shell=True)
-    ksft_eq(nc.stdout.strip(), "ping")
-
+        cmd(f"echo {test_string} | socat -t 2 -u STDIN TCP:{cfg.remote_baddr}:{port}", shell=True)
+    ksft_eq(nc.stdout.strip(), test_string)
+
+def _set_offload_checksum(cfg, netnl, on) -> None:
+    try:
+        ethtool(f" -K {cfg.ifname} rx {on} tx {on} ")
+    except:
+        return
+
+def _set_xdp_generic_sb_on(cfg) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_generic_mb_on(cfg) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_native_sb_on(cfg) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+    cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
+    xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
+    if xdp_info['xdp']['mode'] != 1:
+        """
+        If the interface doesn't support native-mode, it falls back to generic mode.
+        The mode value 1 is native and 2 is generic.
+        So it raises an exception if mode is not 1(native mode).
+        """
+        raise KsftSkipEx('device does not support native-XDP')
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_native_mb_on(cfg) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    try:
+        cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
+    except Exception as e:
+        cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+        raise KsftSkipEx('device does not support native-multi-buffer XDP')
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def _set_xdp_offload_on(cfg) -> None:
+    test_dir = os.path.dirname(os.path.realpath(__file__))
+    prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500", shell=True)
+    try:
+        cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True)
+    except Exception as e:
+        raise KsftSkipEx('device does not support offloaded XDP')
+    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+    if no_sleep != True:
+        time.sleep(10)
+
+def get_interface_info(cfg) -> None:
+    global remote_ifname
+    global no_sleep
+
+    remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_v4} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
+    remote_ifname = remote_info.rstrip('\n')
+    if remote_ifname == "":
+        raise KsftFailEx('Can not get remote interface')
+    local_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
+    if 'parentbus' in local_info and local_info['parentbus'] == "netdevsim":
+        no_sleep=True
+    if 'linkinfo' in local_info and local_info['linkinfo']['info_kind'] == "veth":
+        no_sleep=True
+
+def set_interface_init(cfg) -> None:
+    cmd(f"ip link set dev {cfg.ifname} mtu 1500", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdp off ", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdpgeneric off ", shell=True)
+    cmd(f"ip link set dev {cfg.ifname} xdpoffload off", shell=True)
+    cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
+
+def test_default(cfg, netnl) -> None:
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+
+def test_xdp_generic_sb(cfg, netnl) -> None:
+    _set_xdp_generic_sb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    ip("link set dev %s xdpgeneric off" % cfg.ifname)
+
+def test_xdp_generic_mb(cfg, netnl) -> None:
+    _set_xdp_generic_mb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    ip("link set dev %s xdpgeneric off" % cfg.ifname)
+
+def test_xdp_native_sb(cfg, netnl) -> None:
+    _set_xdp_native_sb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    ip("link set dev %s xdp off" % cfg.ifname)
+
+def test_xdp_native_mb(cfg, netnl) -> None:
+    _set_xdp_native_mb_on(cfg)
+    _set_offload_checksum(cfg, netnl, "off")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    _set_offload_checksum(cfg, netnl, "on")
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    ip("link set dev %s xdp off" % cfg.ifname)
+
+def test_xdp_offload(cfg, netnl) -> None:
+    _set_xdp_offload_on(cfg)
+    _test_v4(cfg)
+    _test_v6(cfg)
+    _test_tcp(cfg)
+    ip("link set dev %s xdpoffload off" % cfg.ifname)
 
 def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
-        ksft_run(globs=globals(), case_pfx={"test_"}, args=(cfg, ))
+        get_interface_info(cfg)
+        set_interface_init(cfg)
+        ksft_run([test_default,
+                  test_xdp_generic_sb,
+                  test_xdp_generic_mb,
+                  test_xdp_native_sb,
+                  test_xdp_native_mb,
+                  test_xdp_offload],
+                 args=(cfg, EthtoolFamily()))
+        set_interface_init(cfg)
     ksft_exit()
 
 
diff --git a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
index d988b2e0cee84..e73fab3edd9f7 100644
--- a/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
+++ b/tools/testing/selftests/net/lib/xdp_dummy.bpf.c
@@ -10,4 +10,10 @@ int xdp_dummy_prog(struct xdp_md *ctx)
 	return XDP_PASS;
 }
 
+SEC("xdp.frags")
+int xdp_dummy_prog_frags(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
 char _license[] SEC("license") = "GPL";

From 77b2ab31fc65c595ca0a339f6c5b8ef3adfae5c6 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Fri, 7 Mar 2025 15:47:31 +0000
Subject: [PATCH 1919/2753] MAINTAINERS: sfc: remove Martin Habets

Martin has left AMD and no longer works on the sfc driver.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20250307154731.211368-1-edward.cree@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 -
 1 file changed, 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ca11a553d4121..07b2d3c7ae5d7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21502,7 +21502,6 @@ F:	include/linux/slimbus.h
 
 SFC NETWORK DRIVER
 M:	Edward Cree <ecree.xilinx@gmail.com>
-M:	Martin Habets <habetsm.xilinx@gmail.com>
 L:	netdev@vger.kernel.org
 L:	linux-net-drivers@amd.com
 S:	Maintained

From 7462fe22cc74321eb663768848976d42eba3ddbb Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Fri, 7 Mar 2025 12:21:45 +0100
Subject: [PATCH 1920/2753] mptcp: pm: use addr entry for get_local_id

The following code in mptcp_userspace_pm_get_local_id() that assigns "skc"
to "new_entry" is not allowed in BPF if we use the same code to implement
the get_local_id() interface of a BFP path manager:

	memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
	new_entry.addr = *skc;
	new_entry.addr.id = 0;
	new_entry.flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;

To solve the issue, this patch moves this assignment to "new_entry" forward
to mptcp_pm_get_local_id(), and then passing "new_entry" as a parameter to
both mptcp_pm_nl_get_local_id() and mptcp_userspace_pm_get_local_id().

No behavioural changes intended.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-1-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c           |  9 ++++++---
 net/mptcp/pm_netlink.c   | 11 ++++-------
 net/mptcp/pm_userspace.c | 17 ++++++-----------
 net/mptcp/protocol.h     |  6 ++++--
 4 files changed, 20 insertions(+), 23 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 6c8cadf84f31f..f6030ce04efdf 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -406,7 +406,7 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 {
-	struct mptcp_addr_info skc_local;
+	struct mptcp_pm_addr_entry skc_local = { 0 };
 	struct mptcp_addr_info msk_local;
 
 	if (WARN_ON_ONCE(!msk))
@@ -416,10 +416,13 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
 	 * addr
 	 */
 	mptcp_local_address((struct sock_common *)msk, &msk_local);
-	mptcp_local_address((struct sock_common *)skc, &skc_local);
-	if (mptcp_addresses_equal(&msk_local, &skc_local, false))
+	mptcp_local_address((struct sock_common *)skc, &skc_local.addr);
+	if (mptcp_addresses_equal(&msk_local, &skc_local.addr, false))
 		return 0;
 
+	skc_local.addr.id = 0;
+	skc_local.flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
+
 	if (mptcp_pm_is_userspace(msk))
 		return mptcp_userspace_pm_get_local_id(msk, &skc_local);
 	return mptcp_pm_nl_get_local_id(msk, &skc_local);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index a6387bcf848b9..23c28e37ab8f1 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1150,7 +1150,8 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	return err;
 }
 
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
+			     struct mptcp_pm_addr_entry *skc)
 {
 	struct mptcp_pm_addr_entry *entry;
 	struct pm_nl_pernet *pernet;
@@ -1159,7 +1160,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	pernet = pm_nl_get_pernet_from_msk(msk);
 
 	rcu_read_lock();
-	entry = __lookup_addr(pernet, skc);
+	entry = __lookup_addr(pernet, &skc->addr);
 	ret = entry ? entry->addr.id : -1;
 	rcu_read_unlock();
 	if (ret >= 0)
@@ -1170,12 +1171,8 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
 	if (!entry)
 		return -ENOMEM;
 
-	entry->addr = *skc;
-	entry->addr.id = 0;
+	*entry = *skc;
 	entry->addr.port = 0;
-	entry->ifindex = 0;
-	entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
-	entry->lsk = NULL;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
 		kfree(entry);
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 7e7d01bef5d40..8c45eebe9bbc7 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -130,27 +130,22 @@ mptcp_userspace_pm_lookup_addr_by_id(struct mptcp_sock *msk, unsigned int id)
 }
 
 int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
-				    struct mptcp_addr_info *skc)
+				    struct mptcp_pm_addr_entry *skc)
 {
-	struct mptcp_pm_addr_entry *entry = NULL, new_entry;
 	__be16 msk_sport =  ((struct inet_sock *)
 			     inet_sk((struct sock *)msk))->inet_sport;
+	struct mptcp_pm_addr_entry *entry;
 
 	spin_lock_bh(&msk->pm.lock);
-	entry = mptcp_userspace_pm_lookup_addr(msk, skc);
+	entry = mptcp_userspace_pm_lookup_addr(msk, &skc->addr);
 	spin_unlock_bh(&msk->pm.lock);
 	if (entry)
 		return entry->addr.id;
 
-	memset(&new_entry, 0, sizeof(struct mptcp_pm_addr_entry));
-	new_entry.addr = *skc;
-	new_entry.addr.id = 0;
-	new_entry.flags = MPTCP_PM_ADDR_FLAG_IMPLICIT;
-
-	if (new_entry.addr.port == msk_sport)
-		new_entry.addr.port = 0;
+	if (skc->addr.port == msk_sport)
+		skc->addr.port = 0;
 
-	return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
+	return mptcp_userspace_pm_append_new_local_addr(msk, skc, true);
 }
 
 bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 7b74dedc79362..333d20a018b42 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1121,8 +1121,10 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
 			     struct mptcp_rm_list *rm_list);
 int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
-int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
+			     struct mptcp_pm_addr_entry *skc);
+int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
+				    struct mptcp_pm_addr_entry *skc);
 bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
 bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
 bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);

From fac7a6ddc75740ee3d24c7fa054921f9c495d8c2 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:46 +0100
Subject: [PATCH 1921/2753] mptcp: pm: remove '_nl' from
 mptcp_pm_nl_addr_send_ack

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_addr_send_ack()' is not specific
to this PM: it is used by both the in-kernel and userspace PMs.

To avoid confusions, the '_nl' bit has been removed from the name.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-2-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c           | 2 +-
 net/mptcp/pm_netlink.c   | 8 ++++----
 net/mptcp/pm_userspace.c | 2 +-
 net/mptcp/protocol.h     | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index f6030ce04efdf..ece706e8ed22b 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -57,7 +57,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	msk->pm.rm_list_tx = *rm_list;
 	rm_addr |= BIT(MPTCP_RM_ADDR_SIGNAL);
 	WRITE_ONCE(msk->pm.addr_signal, rm_addr);
-	mptcp_pm_nl_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack(msk);
 	return 0;
 }
 
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 23c28e37ab8f1..a70a688eae845 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -606,7 +606,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 			local.addr.id = 0;
 
 		mptcp_pm_announce_addr(msk, &local.addr, false);
-		mptcp_pm_nl_addr_send_ack(msk);
+		mptcp_pm_addr_send_ack(msk);
 
 		if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
 			signal_and_subflow = true;
@@ -740,7 +740,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 
 	remote = msk->pm.remote;
 	mptcp_pm_announce_addr(msk, &remote, true);
-	mptcp_pm_nl_addr_send_ack(msk);
+	mptcp_pm_addr_send_ack(msk);
 
 	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
 		return;
@@ -781,7 +781,7 @@ bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
 	return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
 }
 
-void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 {
 	struct mptcp_subflow_context *subflow, *alt = NULL;
 
@@ -942,7 +942,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk)
 	}
 	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
-		mptcp_pm_nl_addr_send_ack(msk);
+		mptcp_pm_addr_send_ack(msk);
 	}
 	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
 		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 8c45eebe9bbc7..b41e1aaa1d1cb 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -234,7 +234,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
 	if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) {
 		msk->pm.add_addr_signaled++;
 		mptcp_pm_announce_addr(msk, &addr_val.addr, false);
-		mptcp_pm_nl_addr_send_ack(msk);
+		mptcp_pm_addr_send_ack(msk);
 	}
 
 	spin_unlock_bh(&msk->pm.lock);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 333d20a018b42..2a3eb2392b3bb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1008,7 +1008,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
 void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
 bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
 				     const struct mptcp_addr_info *remote);
-void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);

From d1734987992c977f1515a5208688aced653c1869 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:47 +0100
Subject: [PATCH 1922/2753] mptcp: pm: remove '_nl' from
 mptcp_pm_nl_mp_prio_send_ack

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_mp_prio_send_ack()' is not
specific to this PM: it is used by both the in-kernel and userspace PMs.

To avoid confusions, the '_nl' bit has been removed from the name.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-3-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c   | 10 +++++-----
 net/mptcp/pm_userspace.c |  4 ++--
 net/mptcp/protocol.h     |  8 ++++----
 3 files changed, 11 insertions(+), 11 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index a70a688eae845..5494b5b409dc4 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -808,10 +808,10 @@ void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
 		mptcp_pm_send_ack(msk, alt, false, false);
 }
 
-int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-				 struct mptcp_addr_info *addr,
-				 struct mptcp_addr_info *rem,
-				 u8 bkup)
+int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
+			      struct mptcp_addr_info *addr,
+			      struct mptcp_addr_info *rem,
+			      u8 bkup)
 {
 	struct mptcp_subflow_context *subflow;
 
@@ -1936,7 +1936,7 @@ static void mptcp_nl_set_flags(struct net *net,
 
 		lock_sock(sk);
 		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			mptcp_pm_nl_mp_prio_send_ack(msk, &local->addr, NULL, bkup);
+			mptcp_pm_mp_prio_send_ack(msk, &local->addr, NULL, bkup);
 		/* Subflows will only be recreated if the SUBFLOW flag is set */
 		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
 			mptcp_pm_nl_fullmesh(msk, &local->addr);
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index b41e1aaa1d1cb..2626b2b092d4e 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -605,10 +605,10 @@ int mptcp_userspace_pm_set_flags(struct mptcp_pm_addr_entry *local,
 	spin_unlock_bh(&msk->pm.lock);
 
 	lock_sock(sk);
-	ret = mptcp_pm_nl_mp_prio_send_ack(msk, &local->addr, &rem, bkup);
+	ret = mptcp_pm_mp_prio_send_ack(msk, &local->addr, &rem, bkup);
 	release_sock(sk);
 
-	/* mptcp_pm_nl_mp_prio_send_ack() only fails in one case */
+	/* mptcp_pm_mp_prio_send_ack() only fails in one case */
 	if (ret < 0)
 		GENL_SET_ERR_MSG(info, "subflow not found");
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 2a3eb2392b3bb..5508343f2c698 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1013,10 +1013,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
 void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq);
-int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
-				 struct mptcp_addr_info *addr,
-				 struct mptcp_addr_info *rem,
-				 u8 bkup);
+int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
+			      struct mptcp_addr_info *addr,
+			      struct mptcp_addr_info *rem,
+			      u8 bkup);
 bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 			      const struct mptcp_addr_info *addr);
 void mptcp_pm_free_anno_list(struct mptcp_sock *msk);

From 551a9ad7879df1c7d604b27272fe84032a040074 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:48 +0100
Subject: [PATCH 1923/2753] mptcp: pm: remove '_nl' from mptcp_pm_nl_work

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_work' is not specific to this PM:
it is called from the core to call helpers, some of them needed by both
the in-kernel and userspace PMs.

To avoid confusions, the '_nl' bit has been removed from the name.

Also used 'worker' instead of 'work', similar to protocol.c's worker.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-4-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 2 +-
 net/mptcp/protocol.c   | 2 +-
 net/mptcp/protocol.h   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 5494b5b409dc4..f6f7ea25640b7 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -924,7 +924,7 @@ static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
 	mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
 }
 
-void mptcp_pm_nl_work(struct mptcp_sock *msk)
+void mptcp_pm_worker(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ec23e65ef0f11..ac946263ec64f 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -2681,7 +2681,7 @@ static void mptcp_worker(struct work_struct *work)
 
 	mptcp_check_fastclose(msk);
 
-	mptcp_pm_nl_work(msk);
+	mptcp_pm_worker(msk);
 
 	mptcp_check_send_data_fin(sk);
 	mptcp_check_data_fin_ack(sk);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 5508343f2c698..f29f4dd28fc56 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1147,7 +1147,7 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 }
 
 void __init mptcp_pm_nl_init(void);
-void mptcp_pm_nl_work(struct mptcp_sock *msk);
+void mptcp_pm_worker(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);

From 63611391850850bf27f81afb0d0b6d1237a34006 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:49 +0100
Subject: [PATCH 1924/2753] mptcp: pm: remove '_nl' from
 mptcp_pm_nl_rm_addr_received

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_rm_addr_received' is not specific
to this PM: it is called from the PM worker, and used by both the
in-kernel and userspace PMs. The helper has been renamed to
'mptcp_pm_rm_addr_recv' instead of '_received' to avoid confusions with
the one from pm.c.

mptcp_pm_nl_rm_addr_or_subflow', and 'mptcp_pm_nl_rm_subflow_received'
have been updated too for the same reason.

To avoid confusions, the '_nl' bit has been removed from the name.

While at it, the in-kernel PM specific code has been move from
mptcp_pm_rm_addr_or_subflow to a new dedicated helper, clearer.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-5-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 55 +++++++++++++++++++++---------------------
 1 file changed, 27 insertions(+), 28 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index f6f7ea25640b7..09ef3aa025e70 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -838,9 +838,20 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 	return -EINVAL;
 }
 
-static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
-					   const struct mptcp_rm_list *rm_list,
-					   enum linux_mptcp_mib_field rm_type)
+static void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
+{
+	if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+		/* Note: if the subflow has been closed before, this
+		 * add_addr_accepted counter will not be decremented.
+		 */
+		if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+			WRITE_ONCE(msk->pm.accept_addr, true);
+	}
+}
+
+static void mptcp_pm_rm_addr_or_subflow(struct mptcp_sock *msk,
+					const struct mptcp_rm_list *rm_list,
+					enum linux_mptcp_mib_field rm_type)
 {
 	struct mptcp_subflow_context *subflow, *tmp;
 	struct sock *sk = (struct sock *)msk;
@@ -893,35 +904,23 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 				__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
 
-		if (rm_type == MPTCP_MIB_RMADDR)
+		if (rm_type == MPTCP_MIB_RMADDR) {
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
-
-		if (!removed)
-			continue;
-
-		if (!mptcp_pm_is_kernel(msk))
-			continue;
-
-		if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
-		    !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
-			/* Note: if the subflow has been closed before, this
-			 * add_addr_accepted counter will not be decremented.
-			 */
-			if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
-				WRITE_ONCE(msk->pm.accept_addr, true);
+			if (removed && mptcp_pm_is_kernel(msk))
+				mptcp_pm_nl_rm_addr(msk, rm_id);
 		}
 	}
 }
 
-static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
+static void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk)
 {
-	mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
+	mptcp_pm_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
 }
 
-static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
-					    const struct mptcp_rm_list *rm_list)
+static void mptcp_pm_rm_subflow(struct mptcp_sock *msk,
+				const struct mptcp_rm_list *rm_list)
 {
-	mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
+	mptcp_pm_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
 }
 
 void mptcp_pm_worker(struct mptcp_sock *msk)
@@ -946,7 +945,7 @@ void mptcp_pm_worker(struct mptcp_sock *msk)
 	}
 	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
 		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
-		mptcp_pm_nl_rm_addr_received(msk);
+		mptcp_pm_rm_addr_recv(msk);
 	}
 	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
 		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
@@ -1538,7 +1537,7 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		list.ids[0] = mptcp_endp_get_local_id(msk, addr);
 		if (remove_subflow) {
 			spin_lock_bh(&msk->pm.lock);
-			mptcp_pm_nl_rm_subflow_received(msk, &list);
+			mptcp_pm_rm_subflow(msk, &list);
 			spin_unlock_bh(&msk->pm.lock);
 		}
 
@@ -1583,7 +1582,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
 		lock_sock(sk);
 		spin_lock_bh(&msk->pm.lock);
 		mptcp_pm_remove_addr(msk, &list);
-		mptcp_pm_nl_rm_subflow_received(msk, &list);
+		mptcp_pm_rm_subflow(msk, &list);
 		__mark_subflow_endp_available(msk, 0);
 		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
@@ -1670,7 +1669,7 @@ static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
 		mptcp_pm_remove_addr(msk, &alist);
 	}
 	if (slist.nr)
-		mptcp_pm_nl_rm_subflow_received(msk, &slist);
+		mptcp_pm_rm_subflow(msk, &slist);
 	/* Reset counters: maybe some subflows have been removed before */
 	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	msk->pm.local_addr_used = 0;
@@ -1910,7 +1909,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 	list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
 
 	spin_lock_bh(&msk->pm.lock);
-	mptcp_pm_nl_rm_subflow_received(msk, &list);
+	mptcp_pm_rm_subflow(msk, &list);
 	__mark_subflow_endp_available(msk, list.ids[0]);
 	mptcp_pm_create_subflow_or_signal_addr(msk);
 	spin_unlock_bh(&msk->pm.lock);

From 550c50bbc2b7950dd4ea1082c016f84469509eab Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:50 +0100
Subject: [PATCH 1925/2753] mptcp: pm: remove '_nl' from
 mptcp_pm_nl_subflow_chk_stale()

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_subflow_chk_stale' is not specific
to this PM: it is called from pm.c for both the in-kernel and userspace
PMs.

To avoid confusions, the '_nl' bit has been removed from the name.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-6-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 2 +-
 net/mptcp/pm_netlink.c | 2 +-
 net/mptcp/protocol.h   | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index ece706e8ed22b..14c7ff5c606c4 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -567,7 +567,7 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 	} else if (subflow->stale_rcv_tstamp == rcv_tstamp) {
 		if (subflow->stale_count < U8_MAX)
 			subflow->stale_count++;
-		mptcp_pm_nl_subflow_chk_stale(msk, ssk);
+		mptcp_pm_subflows_chk_stale(msk, ssk);
 	} else {
 		subflow->stale_count = 0;
 		mptcp_subflow_set_active(subflow);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 09ef3aa025e70..43667ad4c4aeb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1203,7 +1203,7 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
 					  },
 };
 
-void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
 	struct sock *sk = (struct sock *)msk;
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f29f4dd28fc56..a5db1a297fbca 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -992,7 +992,7 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 				  const struct mptcp_addr_info *loc,
 				  const struct mptcp_addr_info *rem);
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
-void mptcp_pm_nl_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
+void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);

From 498d7d8b75f16a5b6e4f6499f1e72e9296f2d0cd Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:51 +0100
Subject: [PATCH 1926/2753] mptcp: pm: remove '_nl' from
 mptcp_pm_nl_is_init_remote_addr

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. But here 'mptcp_pm_nl_is_init_remote_addr' is not
specific to this PM: it is called from pm.c for both the in-kernel and
userspace PMs.

To avoid confusions, the '_nl' bit has been removed from the name.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-7-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 2 +-
 net/mptcp/pm_netlink.c | 4 ++--
 net/mptcp/protocol.h   | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 14c7ff5c606c4..ab443b9f9c5f2 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -231,7 +231,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
 			__MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
 		}
 	/* id0 should not have a different address */
-	} else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) ||
+	} else if ((addr->id == 0 && !mptcp_pm_is_init_remote_addr(msk, addr)) ||
 		   (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
 		mptcp_pm_announce_addr(msk, addr, true);
 		mptcp_pm_add_addr_send_ack(msk);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 43667ad4c4aeb..029a74162b0bc 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -772,8 +772,8 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	}
 }
 
-bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
-				     const struct mptcp_addr_info *remote)
+bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
+				  const struct mptcp_addr_info *remote)
 {
 	struct mptcp_addr_info mpc_remote;
 
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index a5db1a297fbca..39bcad1def6bc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1006,8 +1006,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
 void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
 			      const struct mptcp_addr_info *addr);
 void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
-bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
-				     const struct mptcp_addr_info *remote);
+bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
+				  const struct mptcp_addr_info *remote);
 void mptcp_pm_addr_send_ack(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);

From 40aa7409d30df2b610f8e590cbb183faa2ac6f1f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:52 +0100
Subject: [PATCH 1927/2753] mptcp: pm: kernel: add '_pm' to mptcp_nl_set_flags

Currently, in-kernel PM specific helpers are prefixed with
'mptcp_pm_nl_'. Here, '_pm' was missing from 'mptcp_nl_set_flags'.

Add '_pm' to be similar to others, and add '_all' to avoid confusions
witih the global 'mptcp_pm_nl_set_flags'.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-8-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 029a74162b0bc..781831c506918 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1915,9 +1915,9 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 	spin_unlock_bh(&msk->pm.lock);
 }
 
-static void mptcp_nl_set_flags(struct net *net,
-			       struct mptcp_pm_addr_entry *local,
-			       u8 changed)
+static void mptcp_pm_nl_set_flags_all(struct net *net,
+				      struct mptcp_pm_addr_entry *local,
+				      u8 changed)
 {
 	u8 is_subflow = !!(local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
 	u8 bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
@@ -1992,7 +1992,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
 	*local = *entry;
 	spin_unlock_bh(&pernet->lock);
 
-	mptcp_nl_set_flags(net, local, changed);
+	mptcp_pm_nl_set_flags_all(net, local, changed);
 	return 0;
 }
 

From a17336b2b2e0339b8107b9d4d0fd6b7cf51172e4 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:53 +0100
Subject: [PATCH 1928/2753] mptcp: pm: avoid calling PM specific code from core

When destroying an MPTCP socket, some userspace PM specific code was
called from mptcp_destroy_common() in protocol.c. That feels wrong, and
it is the only case.

Instead, the core now calls mptcp_pm_destroy() from pm.c which is now in
charge of cleaning the announced addresses list, and ask the different
PMs to do extra cleaning if needed, e.g. the userspace PM, if used, will
clean the local addresses list.

While at it, the userspace PM specific helper has been prefixed with
'mptcp_userspace_pm_' like the other ones.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-9-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c           | 8 ++++++++
 net/mptcp/pm_userspace.c | 5 +----
 net/mptcp/protocol.c     | 3 +--
 net/mptcp/protocol.h     | 3 ++-
 4 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index ab443b9f9c5f2..17f99924dfa0e 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -599,6 +599,14 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 #endif
 }
 
+void mptcp_pm_destroy(struct mptcp_sock *msk)
+{
+	mptcp_pm_free_anno_list(msk);
+
+	if (mptcp_pm_is_userspace(msk))
+		mptcp_userspace_pm_free_local_addr_list(msk);
+}
+
 void mptcp_pm_data_reset(struct mptcp_sock *msk)
 {
 	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 2626b2b092d4e..13856df226736 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -12,15 +12,12 @@
 	list_for_each_entry(__entry,						\
 			    &((__msk)->pm.userspace_pm_local_addr_list), list)
 
-void mptcp_free_local_addr_list(struct mptcp_sock *msk)
+void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_addr_entry *entry, *tmp;
 	struct sock *sk = (struct sock *)msk;
 	LIST_HEAD(free_list);
 
-	if (!mptcp_pm_is_userspace(msk))
-		return;
-
 	spin_lock_bh(&msk->pm.lock);
 	list_splice_init(&msk->pm.userspace_pm_local_addr_list, &free_list);
 	spin_unlock_bh(&msk->pm.lock);
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ac946263ec64f..ad780ae1d30dc 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -3302,8 +3302,7 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags)
 	 * inet_sock_destruct() will dispose it
 	 */
 	mptcp_token_destroy(msk);
-	mptcp_pm_free_anno_list(msk);
-	mptcp_free_local_addr_list(msk);
+	mptcp_pm_destroy(msk);
 }
 
 static void mptcp_destroy(struct sock *sk)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 39bcad1def6bc..0013b68a2731e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -983,6 +983,7 @@ __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum su
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
 void mptcp_pm_data_reset(struct mptcp_sock *msk);
+void mptcp_pm_destroy(struct mptcp_sock *msk);
 int mptcp_pm_parse_addr(struct nlattr *attr, struct genl_info *info,
 			struct mptcp_addr_info *addr);
 int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
@@ -1042,7 +1043,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
 				struct mptcp_pm_addr_entry *entry);
 
-void mptcp_free_local_addr_list(struct mptcp_sock *msk);
+void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
 void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,
 		 const struct sock *ssk, gfp_t gfp);

From a49eb8ae95b8ce24f30a027f286baf8cac08a0ae Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:54 +0100
Subject: [PATCH 1929/2753] mptcp: pm: worker: split in-kernel and common tasks

To make it clear what actions are in-kernel PM specific and which ones
are not and done for all PMs, e.g. sending ADD_ADDR and close associated
subflows when a RM_ADDR is received.

The behavioural is changed a bit: MPTCP_PM_ADD_ADDR_RECEIVED is now
treated after MPTCP_PM_ADD_ADDR_SEND_ACK and MPTCP_PM_RM_ADDR_RECEIVED,
but that should not change anything in practice.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-10-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 25 +++++++++++++++++++++++++
 net/mptcp/pm_netlink.c | 23 +++--------------------
 net/mptcp/protocol.h   |  2 ++
 3 files changed, 30 insertions(+), 20 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 17f99924dfa0e..ddf9d0dc62745 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -599,6 +599,31 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 #endif
 }
 
+void mptcp_pm_worker(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	msk_owned_by_me(msk);
+
+	if (!(pm->status & MPTCP_PM_WORK_MASK))
+		return;
+
+	spin_lock_bh(&msk->pm.lock);
+
+	pr_debug("msk=%p status=%x\n", msk, pm->status);
+	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
+		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
+		mptcp_pm_addr_send_ack(msk);
+	}
+	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
+		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
+		mptcp_pm_rm_addr_recv(msk);
+	}
+	__mptcp_pm_kernel_worker(msk);
+
+	spin_unlock_bh(&msk->pm.lock);
+}
+
 void mptcp_pm_destroy(struct mptcp_sock *msk)
 {
 	mptcp_pm_free_anno_list(msk);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 781831c506918..37986208b9c0a 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -912,7 +912,7 @@ static void mptcp_pm_rm_addr_or_subflow(struct mptcp_sock *msk,
 	}
 }
 
-static void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk)
+void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk)
 {
 	mptcp_pm_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
 }
@@ -923,30 +923,15 @@ static void mptcp_pm_rm_subflow(struct mptcp_sock *msk,
 	mptcp_pm_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
 }
 
-void mptcp_pm_worker(struct mptcp_sock *msk)
+/* Called under PM lock */
+void __mptcp_pm_kernel_worker(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;
 
-	msk_owned_by_me(msk);
-
-	if (!(pm->status & MPTCP_PM_WORK_MASK))
-		return;
-
-	spin_lock_bh(&msk->pm.lock);
-
-	pr_debug("msk=%p status=%x\n", msk, pm->status);
 	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
 		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
 		mptcp_pm_nl_add_addr_received(msk);
 	}
-	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_SEND_ACK)) {
-		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_SEND_ACK);
-		mptcp_pm_addr_send_ack(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_RM_ADDR_RECEIVED)) {
-		pm->status &= ~BIT(MPTCP_PM_RM_ADDR_RECEIVED);
-		mptcp_pm_rm_addr_recv(msk);
-	}
 	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
 		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
 		mptcp_pm_nl_fully_established(msk);
@@ -955,8 +940,6 @@ void mptcp_pm_worker(struct mptcp_sock *msk)
 		pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
 		mptcp_pm_nl_subflow_established(msk);
 	}
-
-	spin_unlock_bh(&msk->pm.lock);
 }
 
 static bool address_use_port(struct mptcp_pm_addr_entry *entry)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 0013b68a2731e..d4725b32aa567 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1010,6 +1010,7 @@ void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
 bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
 				  const struct mptcp_addr_info *remote);
 void mptcp_pm_addr_send_ack(struct mptcp_sock *msk);
+void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
@@ -1149,6 +1150,7 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_worker(struct mptcp_sock *msk);
+void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);

From a14673127236c131cb3a5dbefe41d5c4171bd8a7 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:55 +0100
Subject: [PATCH 1930/2753] mptcp: pm: export mptcp_remote_address

In a following commit, the 'remote_address' helper will need to be used
from different files.

It is then exported, and prefixed with 'mptcp_', similar to
'mptcp_local_address'.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-11-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 14 +++++++-------
 net/mptcp/protocol.h   |  5 ++++-
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 37986208b9c0a..27b8daf3bc3ff 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -94,8 +94,8 @@ void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *
 #endif
 }
 
-static void remote_address(const struct sock_common *skc,
-			   struct mptcp_addr_info *addr)
+void mptcp_remote_address(const struct sock_common *skc,
+			  struct mptcp_addr_info *addr)
 {
 	addr->family = skc->skc_family;
 	addr->port = skc->skc_dport;
@@ -138,7 +138,7 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 		      (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
 			continue;
 
-		remote_address((struct sock_common *)ssk, &cur);
+		mptcp_remote_address((struct sock_common *)ssk, &cur);
 		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
 			return true;
 	}
@@ -428,7 +428,7 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 	int i = 0;
 
 	subflows_max = mptcp_pm_get_subflows_max(msk);
-	remote_address((struct sock_common *)sk, &remote);
+	mptcp_remote_address((struct sock_common *)sk, &remote);
 
 	/* Non-fullmesh endpoint, fill in the single entry
 	 * corresponding to the primary MPC subflow remote address
@@ -455,7 +455,7 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 
 		mptcp_for_each_subflow(msk, subflow) {
 			ssk = mptcp_subflow_tcp_sock(subflow);
-			remote_address((struct sock_common *)ssk, &addrs[i]);
+			mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
 			addrs[i].id = READ_ONCE(subflow->remote_id);
 			if (deny_id0 && !addrs[i].id)
 				continue;
@@ -777,7 +777,7 @@ bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
 {
 	struct mptcp_addr_info mpc_remote;
 
-	remote_address((struct sock_common *)msk, &mpc_remote);
+	mptcp_remote_address((struct sock_common *)msk, &mpc_remote);
 	return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
 }
 
@@ -826,7 +826,7 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 			continue;
 
 		if (rem && rem->family != AF_UNSPEC) {
-			remote_address((struct sock_common *)ssk, &remote);
+			mptcp_remote_address((struct sock_common *)ssk, &remote);
 			if (!mptcp_addresses_equal(&remote, rem, rem->port))
 				continue;
 		}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index d4725b32aa567..f66c3d28333fc 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -724,7 +724,10 @@ void mptcp_set_state(struct sock *sk, int state);
 
 bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
 			   const struct mptcp_addr_info *b, bool use_port);
-void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr);
+void mptcp_local_address(const struct sock_common *skc,
+			 struct mptcp_addr_info *addr);
+void mptcp_remote_address(const struct sock_common *skc,
+			  struct mptcp_addr_info *addr);
 
 /* called with sk socket lock held */
 int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_pm_local *local,

From bcc32640ada037f834e61f358e2ee384fdb4039a Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:56 +0100
Subject: [PATCH 1931/2753] mptcp: pm: move generic helper at the top

In prevision to another change importing all generic PM helpers from
pm_netlink.c to there.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-12-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c | 54 +++++++++++++++++++++++++-------------------------
 1 file changed, 27 insertions(+), 27 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index ddf9d0dc62745..cd50c5a0c78e8 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -12,6 +12,33 @@
 #include "mib.h"
 #include "mptcp_pm_gen.h"
 
+/* path manager helpers */
+
+/* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
+ * otherwise allow any matching local/remote pair
+ */
+bool mptcp_pm_addr_families_match(const struct sock *sk,
+				  const struct mptcp_addr_info *loc,
+				  const struct mptcp_addr_info *rem)
+{
+	bool mptcp_is_v4 = sk->sk_family == AF_INET;
+
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	bool loc_is_v4 = loc->family == AF_INET || ipv6_addr_v4mapped(&loc->addr6);
+	bool rem_is_v4 = rem->family == AF_INET || ipv6_addr_v4mapped(&rem->addr6);
+
+	if (mptcp_is_v4)
+		return loc_is_v4 && rem_is_v4;
+
+	if (ipv6_only_sock(sk))
+		return !loc_is_v4 && !rem_is_v4;
+
+	return loc_is_v4 == rem_is_v4;
+#else
+	return mptcp_is_v4 && loc->family == AF_INET && rem->family == AF_INET;
+#endif
+}
+
 /* path manager command handlers */
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
@@ -325,8 +352,6 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
 	}
 }
 
-/* path manager helpers */
-
 bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb,
 			      unsigned int opt_size, unsigned int remaining,
 			      struct mptcp_addr_info *addr, bool *echo,
@@ -574,31 +599,6 @@ void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 	}
 }
 
-/* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
- * otherwise allow any matching local/remote pair
- */
-bool mptcp_pm_addr_families_match(const struct sock *sk,
-				  const struct mptcp_addr_info *loc,
-				  const struct mptcp_addr_info *rem)
-{
-	bool mptcp_is_v4 = sk->sk_family == AF_INET;
-
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	bool loc_is_v4 = loc->family == AF_INET || ipv6_addr_v4mapped(&loc->addr6);
-	bool rem_is_v4 = rem->family == AF_INET || ipv6_addr_v4mapped(&rem->addr6);
-
-	if (mptcp_is_v4)
-		return loc_is_v4 && rem_is_v4;
-
-	if (ipv6_only_sock(sk))
-		return !loc_is_v4 && !rem_is_v4;
-
-	return loc_is_v4 == rem_is_v4;
-#else
-	return mptcp_is_v4 && loc->family == AF_INET && rem->family == AF_INET;
-#endif
-}
-
 void mptcp_pm_worker(struct mptcp_sock *msk)
 {
 	struct mptcp_pm_data *pm = &msk->pm;

From e4c28e3d5c09097b5ca7bc5690e01f48adb33811 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:57 +0100
Subject: [PATCH 1932/2753] mptcp: pm: move generic PM helpers to pm.c

Before this patch, the PM code was dispersed in different places:

- pm.c had common code for all PMs

- pm_netlink.c was supposed to be about the in-kernel PM, but also had
  exported common helpers, callbacks used by the different PMs, NL
  events for PM userspace daemon, etc. quite confusing.

- pm_userspace.c had userspace PM only code, but using specific
  in-kernel PM helpers

To clarify the code, a reorganisation is suggested here, only by moving
code around, and (un)exporting functions:

- helpers used from both PMs and not linked to Netlink
- callbacks used by different PMs, e.g. ADD_ADDR management
- some helpers have been marked as 'static'
- protocol.h has been updated accordingly
- (while at it, a needless if before a kfree(), spot by checkpatch in
   mptcp_remove_anno_list_by_saddr(), has been removed)

The code around the PM is now less confusing, which should help for the
maintenance in the long term.

This will certainly impact future backports, but because other cleanups
have already done recently, and more are coming to ease the addition of
a new path-manager controlled with BPF (struct_ops), doing that now
seems to be a good time. Also, many issues around the PM have been fixed
a few months ago while increasing the code coverage in the selftests, so
such big reorganisation can be done with more confidence now.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-13-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 460 ++++++++++++++++++++++++++++++++++++++++
 net/mptcp/pm_netlink.c | 461 +----------------------------------------
 net/mptcp/protocol.h   |  14 +-
 3 files changed, 467 insertions(+), 468 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index cd50c5a0c78e8..d02a0b3adfc43 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -12,6 +12,16 @@
 #include "mib.h"
 #include "mptcp_pm_gen.h"
 
+#define ADD_ADDR_RETRANS_MAX	3
+
+struct mptcp_pm_add_entry {
+	struct list_head	list;
+	struct mptcp_addr_info	addr;
+	u8			retrans_times;
+	struct timer_list	add_timer;
+	struct mptcp_sock	*sock;
+};
+
 /* path manager helpers */
 
 /* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
@@ -39,6 +49,345 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 #endif
 }
 
+bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
+			   const struct mptcp_addr_info *b, bool use_port)
+{
+	bool addr_equals = false;
+
+	if (a->family == b->family) {
+		if (a->family == AF_INET)
+			addr_equals = a->addr.s_addr == b->addr.s_addr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+		else
+			addr_equals = ipv6_addr_equal(&a->addr6, &b->addr6);
+	} else if (a->family == AF_INET) {
+		if (ipv6_addr_v4mapped(&b->addr6))
+			addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];
+	} else if (b->family == AF_INET) {
+		if (ipv6_addr_v4mapped(&a->addr6))
+			addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr;
+#endif
+	}
+
+	if (!addr_equals)
+		return false;
+	if (!use_port)
+		return true;
+
+	return a->port == b->port;
+}
+
+void mptcp_local_address(const struct sock_common *skc,
+			 struct mptcp_addr_info *addr)
+{
+	addr->family = skc->skc_family;
+	addr->port = htons(skc->skc_num);
+	if (addr->family == AF_INET)
+		addr->addr.s_addr = skc->skc_rcv_saddr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (addr->family == AF_INET6)
+		addr->addr6 = skc->skc_v6_rcv_saddr;
+#endif
+}
+
+void mptcp_remote_address(const struct sock_common *skc,
+			  struct mptcp_addr_info *addr)
+{
+	addr->family = skc->skc_family;
+	addr->port = skc->skc_dport;
+	if (addr->family == AF_INET)
+		addr->addr.s_addr = skc->skc_daddr;
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (addr->family == AF_INET6)
+		addr->addr6 = skc->skc_v6_daddr;
+#endif
+}
+
+static bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
+					 const struct mptcp_addr_info *remote)
+{
+	struct mptcp_addr_info mpc_remote;
+
+	mptcp_remote_address((struct sock_common *)msk, &mpc_remote);
+	return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
+}
+
+bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
+				   const struct mptcp_addr_info *saddr)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_addr_info cur;
+	struct sock_common *skc;
+
+	list_for_each_entry(subflow, list, node) {
+		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
+
+		mptcp_local_address(skc, &cur);
+		if (mptcp_addresses_equal(&cur, saddr, saddr->port))
+			return true;
+	}
+
+	return false;
+}
+
+static struct mptcp_pm_add_entry *
+mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
+				const struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	lockdep_assert_held(&msk->pm.lock);
+
+	list_for_each_entry(entry, &msk->pm.anno_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, addr, true))
+			return entry;
+	}
+
+	return NULL;
+}
+
+bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
+				     const struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *entry;
+
+	entry = mptcp_pm_del_add_timer(msk, addr, false);
+	kfree(entry);
+	return entry;
+}
+
+bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
+{
+	struct mptcp_pm_add_entry *entry;
+	struct mptcp_addr_info saddr;
+	bool ret = false;
+
+	mptcp_local_address((struct sock_common *)sk, &saddr);
+
+	spin_lock_bh(&msk->pm.lock);
+	list_for_each_entry(entry, &msk->pm.anno_list, list) {
+		if (mptcp_addresses_equal(&entry->addr, &saddr, true)) {
+			ret = true;
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock_bh(&msk->pm.lock);
+	return ret;
+}
+
+static void __mptcp_pm_send_ack(struct mptcp_sock *msk,
+				struct mptcp_subflow_context *subflow,
+				bool prio, bool backup)
+{
+	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+	bool slow;
+
+	pr_debug("send ack for %s\n",
+		 prio ? "mp_prio" :
+		 (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
+
+	slow = lock_sock_fast(ssk);
+	if (prio) {
+		subflow->send_mp_prio = 1;
+		subflow->request_bkup = backup;
+	}
+
+	__mptcp_subflow_send_ack(ssk);
+	unlock_sock_fast(ssk, slow);
+}
+
+void mptcp_pm_send_ack(struct mptcp_sock *msk,
+		       struct mptcp_subflow_context *subflow,
+		       bool prio, bool backup)
+{
+	spin_unlock_bh(&msk->pm.lock);
+	__mptcp_pm_send_ack(msk, subflow, prio, backup);
+	spin_lock_bh(&msk->pm.lock);
+}
+
+void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
+{
+	struct mptcp_subflow_context *subflow, *alt = NULL;
+
+	msk_owned_by_me(msk);
+	lockdep_assert_held(&msk->pm.lock);
+
+	if (!mptcp_pm_should_add_signal(msk) &&
+	    !mptcp_pm_should_rm_signal(msk))
+		return;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		if (__mptcp_subflow_active(subflow)) {
+			if (!subflow->stale) {
+				mptcp_pm_send_ack(msk, subflow, false, false);
+				return;
+			}
+
+			if (!alt)
+				alt = subflow;
+		}
+	}
+
+	if (alt)
+		mptcp_pm_send_ack(msk, alt, false, false);
+}
+
+int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
+			      struct mptcp_addr_info *addr,
+			      struct mptcp_addr_info *rem,
+			      u8 bkup)
+{
+	struct mptcp_subflow_context *subflow;
+
+	pr_debug("bkup=%d\n", bkup);
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		struct mptcp_addr_info local, remote;
+
+		mptcp_local_address((struct sock_common *)ssk, &local);
+		if (!mptcp_addresses_equal(&local, addr, addr->port))
+			continue;
+
+		if (rem && rem->family != AF_UNSPEC) {
+			mptcp_remote_address((struct sock_common *)ssk, &remote);
+			if (!mptcp_addresses_equal(&remote, rem, rem->port))
+				continue;
+		}
+
+		__mptcp_pm_send_ack(msk, subflow, true, bkup);
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void mptcp_pm_add_timer(struct timer_list *timer)
+{
+	struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
+	struct mptcp_sock *msk = entry->sock;
+	struct sock *sk = (struct sock *)msk;
+
+	pr_debug("msk=%p\n", msk);
+
+	if (!msk)
+		return;
+
+	if (inet_sk_state_load(sk) == TCP_CLOSE)
+		return;
+
+	if (!entry->addr.id)
+		return;
+
+	if (mptcp_pm_should_add_signal_addr(msk)) {
+		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
+		goto out;
+	}
+
+	spin_lock_bh(&msk->pm.lock);
+
+	if (!mptcp_pm_should_add_signal_addr(msk)) {
+		pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
+		mptcp_pm_announce_addr(msk, &entry->addr, false);
+		mptcp_pm_add_addr_send_ack(msk);
+		entry->retrans_times++;
+	}
+
+	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
+		sk_reset_timer(sk, timer,
+			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
+
+	spin_unlock_bh(&msk->pm.lock);
+
+	if (entry->retrans_times == ADD_ADDR_RETRANS_MAX)
+		mptcp_pm_subflow_established(msk);
+
+out:
+	__sock_put(sk);
+}
+
+struct mptcp_pm_add_entry *
+mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+		       const struct mptcp_addr_info *addr, bool check_id)
+{
+	struct mptcp_pm_add_entry *entry;
+	struct sock *sk = (struct sock *)msk;
+	struct timer_list *add_timer = NULL;
+
+	spin_lock_bh(&msk->pm.lock);
+	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
+	if (entry && (!check_id || entry->addr.id == addr->id)) {
+		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
+		add_timer = &entry->add_timer;
+	}
+	if (!check_id && entry)
+		list_del(&entry->list);
+	spin_unlock_bh(&msk->pm.lock);
+
+	/* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */
+	if (add_timer)
+		sk_stop_timer_sync(sk, add_timer);
+
+	return entry;
+}
+
+bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+			      const struct mptcp_addr_info *addr)
+{
+	struct mptcp_pm_add_entry *add_entry = NULL;
+	struct sock *sk = (struct sock *)msk;
+	struct net *net = sock_net(sk);
+
+	lockdep_assert_held(&msk->pm.lock);
+
+	add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
+
+	if (add_entry) {
+		if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
+			return false;
+
+		sk_reset_timer(sk, &add_entry->add_timer,
+			       jiffies + mptcp_get_add_addr_timeout(net));
+		return true;
+	}
+
+	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
+	if (!add_entry)
+		return false;
+
+	list_add(&add_entry->list, &msk->pm.anno_list);
+
+	add_entry->addr = *addr;
+	add_entry->sock = msk;
+	add_entry->retrans_times = 0;
+
+	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
+	sk_reset_timer(sk, &add_entry->add_timer,
+		       jiffies + mptcp_get_add_addr_timeout(net));
+
+	return true;
+}
+
+static void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_add_entry *entry, *tmp;
+	struct sock *sk = (struct sock *)msk;
+	LIST_HEAD(free_list);
+
+	pr_debug("msk=%p\n", msk);
+
+	spin_lock_bh(&msk->pm.lock);
+	list_splice_init(&msk->pm.anno_list, &free_list);
+	spin_unlock_bh(&msk->pm.lock);
+
+	list_for_each_entry_safe(entry, tmp, &free_list, list) {
+		sk_stop_timer_sync(sk, &entry->add_timer);
+		kfree(entry);
+	}
+}
+
 /* path manager command handlers */
 
 int mptcp_pm_announce_addr(struct mptcp_sock *msk,
@@ -297,6 +646,80 @@ void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk)
 	mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_SEND_ACK);
 }
 
+static void mptcp_pm_rm_addr_or_subflow(struct mptcp_sock *msk,
+					const struct mptcp_rm_list *rm_list,
+					enum linux_mptcp_mib_field rm_type)
+{
+	struct mptcp_subflow_context *subflow, *tmp;
+	struct sock *sk = (struct sock *)msk;
+	u8 i;
+
+	pr_debug("%s rm_list_nr %d\n",
+		 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
+
+	msk_owned_by_me(msk);
+
+	if (sk->sk_state == TCP_LISTEN)
+		return;
+
+	if (!rm_list->nr)
+		return;
+
+	if (list_empty(&msk->conn_list))
+		return;
+
+	for (i = 0; i < rm_list->nr; i++) {
+		u8 rm_id = rm_list->ids[i];
+		bool removed = false;
+
+		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
+			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+			u8 remote_id = READ_ONCE(subflow->remote_id);
+			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+			u8 id = subflow_get_local_id(subflow);
+
+			if ((1 << inet_sk_state_load(ssk)) &
+			    (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE))
+				continue;
+			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
+				continue;
+			if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id)
+				continue;
+
+			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n",
+				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
+				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
+			spin_unlock_bh(&msk->pm.lock);
+			mptcp_subflow_shutdown(sk, ssk, how);
+			removed |= subflow->request_join;
+
+			/* the following takes care of updating the subflows counter */
+			mptcp_close_ssk(sk, ssk, subflow);
+			spin_lock_bh(&msk->pm.lock);
+
+			if (rm_type == MPTCP_MIB_RMSUBFLOW)
+				__MPTCP_INC_STATS(sock_net(sk), rm_type);
+		}
+
+		if (rm_type == MPTCP_MIB_RMADDR) {
+			__MPTCP_INC_STATS(sock_net(sk), rm_type);
+			if (removed && mptcp_pm_is_kernel(msk))
+				mptcp_pm_nl_rm_addr(msk, rm_id);
+		}
+	}
+}
+
+static void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk)
+{
+	mptcp_pm_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
+}
+
+void mptcp_pm_rm_subflow(struct mptcp_sock *msk,
+			 const struct mptcp_rm_list *rm_list)
+{
+	mptcp_pm_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
+}
+
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list)
 {
@@ -580,6 +1003,43 @@ int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
 	return mptcp_pm_set_flags(info);
 }
 
+static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
+{
+	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
+	struct sock *sk = (struct sock *)msk;
+	unsigned int active_max_loss_cnt;
+	struct net *net = sock_net(sk);
+	unsigned int stale_loss_cnt;
+	bool slow;
+
+	stale_loss_cnt = mptcp_stale_loss_cnt(net);
+	if (subflow->stale || !stale_loss_cnt || subflow->stale_count <= stale_loss_cnt)
+		return;
+
+	/* look for another available subflow not in loss state */
+	active_max_loss_cnt = max_t(int, stale_loss_cnt - 1, 1);
+	mptcp_for_each_subflow(msk, iter) {
+		if (iter != subflow && mptcp_subflow_active(iter) &&
+		    iter->stale_count < active_max_loss_cnt) {
+			/* we have some alternatives, try to mark this subflow as idle ...*/
+			slow = lock_sock_fast(ssk);
+			if (!tcp_rtx_and_write_queues_empty(ssk)) {
+				subflow->stale = 1;
+				__mptcp_retransmit_pending_data(sk);
+				MPTCP_INC_STATS(net, MPTCP_MIB_SUBFLOWSTALE);
+			}
+			unlock_sock_fast(ssk, slow);
+
+			/* always try to push the pending data regardless of re-injections:
+			 * we can possibly use backup subflows now, and subflow selection
+			 * is cheap under the msk socket lock
+			 */
+			__mptcp_push_pending(sk, 0);
+			return;
+		}
+	}
+}
+
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 27b8daf3bc3ff..e4abb94e8c0bd 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -18,14 +18,6 @@
 
 static int pm_nl_pernet_id;
 
-struct mptcp_pm_add_entry {
-	struct list_head	list;
-	struct mptcp_addr_info	addr;
-	u8			retrans_times;
-	struct timer_list	add_timer;
-	struct mptcp_sock	*sock;
-};
-
 struct pm_nl_pernet {
 	/* protects pernet updates */
 	spinlock_t		lock;
@@ -41,7 +33,6 @@ struct pm_nl_pernet {
 };
 
 #define MPTCP_PM_ADDR_MAX	8
-#define ADD_ADDR_RETRANS_MAX	3
 
 static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
 {
@@ -54,77 +45,6 @@ pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
 	return pm_nl_get_pernet(sock_net((struct sock *)msk));
 }
 
-bool mptcp_addresses_equal(const struct mptcp_addr_info *a,
-			   const struct mptcp_addr_info *b, bool use_port)
-{
-	bool addr_equals = false;
-
-	if (a->family == b->family) {
-		if (a->family == AF_INET)
-			addr_equals = a->addr.s_addr == b->addr.s_addr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-		else
-			addr_equals = ipv6_addr_equal(&a->addr6, &b->addr6);
-	} else if (a->family == AF_INET) {
-		if (ipv6_addr_v4mapped(&b->addr6))
-			addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3];
-	} else if (b->family == AF_INET) {
-		if (ipv6_addr_v4mapped(&a->addr6))
-			addr_equals = a->addr6.s6_addr32[3] == b->addr.s_addr;
-#endif
-	}
-
-	if (!addr_equals)
-		return false;
-	if (!use_port)
-		return true;
-
-	return a->port == b->port;
-}
-
-void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr)
-{
-	addr->family = skc->skc_family;
-	addr->port = htons(skc->skc_num);
-	if (addr->family == AF_INET)
-		addr->addr.s_addr = skc->skc_rcv_saddr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	else if (addr->family == AF_INET6)
-		addr->addr6 = skc->skc_v6_rcv_saddr;
-#endif
-}
-
-void mptcp_remote_address(const struct sock_common *skc,
-			  struct mptcp_addr_info *addr)
-{
-	addr->family = skc->skc_family;
-	addr->port = skc->skc_dport;
-	if (addr->family == AF_INET)
-		addr->addr.s_addr = skc->skc_daddr;
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	else if (addr->family == AF_INET6)
-		addr->addr6 = skc->skc_v6_daddr;
-#endif
-}
-
-bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
-				   const struct mptcp_addr_info *saddr)
-{
-	struct mptcp_subflow_context *subflow;
-	struct mptcp_addr_info cur;
-	struct sock_common *skc;
-
-	list_for_each_entry(subflow, list, node) {
-		skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
-
-		mptcp_local_address(skc, &cur);
-		if (mptcp_addresses_equal(&cur, saddr, saddr->port))
-			return true;
-	}
-
-	return false;
-}
-
 static bool lookup_subflow_by_daddr(const struct list_head *list,
 				    const struct mptcp_addr_info *daddr)
 {
@@ -251,167 +171,6 @@ bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
 	return true;
 }
 
-struct mptcp_pm_add_entry *
-mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
-				const struct mptcp_addr_info *addr)
-{
-	struct mptcp_pm_add_entry *entry;
-
-	lockdep_assert_held(&msk->pm.lock);
-
-	list_for_each_entry(entry, &msk->pm.anno_list, list) {
-		if (mptcp_addresses_equal(&entry->addr, addr, true))
-			return entry;
-	}
-
-	return NULL;
-}
-
-bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk)
-{
-	struct mptcp_pm_add_entry *entry;
-	struct mptcp_addr_info saddr;
-	bool ret = false;
-
-	mptcp_local_address((struct sock_common *)sk, &saddr);
-
-	spin_lock_bh(&msk->pm.lock);
-	list_for_each_entry(entry, &msk->pm.anno_list, list) {
-		if (mptcp_addresses_equal(&entry->addr, &saddr, true)) {
-			ret = true;
-			goto out;
-		}
-	}
-
-out:
-	spin_unlock_bh(&msk->pm.lock);
-	return ret;
-}
-
-static void mptcp_pm_add_timer(struct timer_list *timer)
-{
-	struct mptcp_pm_add_entry *entry = from_timer(entry, timer, add_timer);
-	struct mptcp_sock *msk = entry->sock;
-	struct sock *sk = (struct sock *)msk;
-
-	pr_debug("msk=%p\n", msk);
-
-	if (!msk)
-		return;
-
-	if (inet_sk_state_load(sk) == TCP_CLOSE)
-		return;
-
-	if (!entry->addr.id)
-		return;
-
-	if (mptcp_pm_should_add_signal_addr(msk)) {
-		sk_reset_timer(sk, timer, jiffies + TCP_RTO_MAX / 8);
-		goto out;
-	}
-
-	spin_lock_bh(&msk->pm.lock);
-
-	if (!mptcp_pm_should_add_signal_addr(msk)) {
-		pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
-		mptcp_pm_announce_addr(msk, &entry->addr, false);
-		mptcp_pm_add_addr_send_ack(msk);
-		entry->retrans_times++;
-	}
-
-	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
-		sk_reset_timer(sk, timer,
-			       jiffies + mptcp_get_add_addr_timeout(sock_net(sk)));
-
-	spin_unlock_bh(&msk->pm.lock);
-
-	if (entry->retrans_times == ADD_ADDR_RETRANS_MAX)
-		mptcp_pm_subflow_established(msk);
-
-out:
-	__sock_put(sk);
-}
-
-struct mptcp_pm_add_entry *
-mptcp_pm_del_add_timer(struct mptcp_sock *msk,
-		       const struct mptcp_addr_info *addr, bool check_id)
-{
-	struct mptcp_pm_add_entry *entry;
-	struct sock *sk = (struct sock *)msk;
-	struct timer_list *add_timer = NULL;
-
-	spin_lock_bh(&msk->pm.lock);
-	entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-	if (entry && (!check_id || entry->addr.id == addr->id)) {
-		entry->retrans_times = ADD_ADDR_RETRANS_MAX;
-		add_timer = &entry->add_timer;
-	}
-	if (!check_id && entry)
-		list_del(&entry->list);
-	spin_unlock_bh(&msk->pm.lock);
-
-	/* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */
-	if (add_timer)
-		sk_stop_timer_sync(sk, add_timer);
-
-	return entry;
-}
-
-bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
-			      const struct mptcp_addr_info *addr)
-{
-	struct mptcp_pm_add_entry *add_entry = NULL;
-	struct sock *sk = (struct sock *)msk;
-	struct net *net = sock_net(sk);
-
-	lockdep_assert_held(&msk->pm.lock);
-
-	add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
-
-	if (add_entry) {
-		if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
-			return false;
-
-		sk_reset_timer(sk, &add_entry->add_timer,
-			       jiffies + mptcp_get_add_addr_timeout(net));
-		return true;
-	}
-
-	add_entry = kmalloc(sizeof(*add_entry), GFP_ATOMIC);
-	if (!add_entry)
-		return false;
-
-	list_add(&add_entry->list, &msk->pm.anno_list);
-
-	add_entry->addr = *addr;
-	add_entry->sock = msk;
-	add_entry->retrans_times = 0;
-
-	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
-	sk_reset_timer(sk, &add_entry->add_timer,
-		       jiffies + mptcp_get_add_addr_timeout(net));
-
-	return true;
-}
-
-void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
-{
-	struct mptcp_pm_add_entry *entry, *tmp;
-	struct sock *sk = (struct sock *)msk;
-	LIST_HEAD(free_list);
-
-	pr_debug("msk=%p\n", msk);
-
-	spin_lock_bh(&msk->pm.lock);
-	list_splice_init(&msk->pm.anno_list, &free_list);
-	spin_unlock_bh(&msk->pm.lock);
-
-	list_for_each_entry_safe(entry, tmp, &free_list, list) {
-		sk_stop_timer_sync(sk, &entry->add_timer);
-		kfree(entry);
-	}
-}
-
 /* Fill all the remote addresses into the array addrs[],
  * and return the array size.
  */
@@ -480,33 +239,6 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
 	return i;
 }
 
-static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-				bool prio, bool backup)
-{
-	struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-	bool slow;
-
-	pr_debug("send ack for %s\n",
-		 prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
-
-	slow = lock_sock_fast(ssk);
-	if (prio) {
-		subflow->send_mp_prio = 1;
-		subflow->request_bkup = backup;
-	}
-
-	__mptcp_subflow_send_ack(ssk);
-	unlock_sock_fast(ssk, slow);
-}
-
-static void mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow,
-			      bool prio, bool backup)
-{
-	spin_unlock_bh(&msk->pm.lock);
-	__mptcp_pm_send_ack(msk, subflow, prio, backup);
-	spin_lock_bh(&msk->pm.lock);
-}
-
 static struct mptcp_pm_addr_entry *
 __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
 {
@@ -772,73 +504,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
 	}
 }
 
-bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
-				  const struct mptcp_addr_info *remote)
-{
-	struct mptcp_addr_info mpc_remote;
-
-	mptcp_remote_address((struct sock_common *)msk, &mpc_remote);
-	return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
-}
-
-void mptcp_pm_addr_send_ack(struct mptcp_sock *msk)
-{
-	struct mptcp_subflow_context *subflow, *alt = NULL;
-
-	msk_owned_by_me(msk);
-	lockdep_assert_held(&msk->pm.lock);
-
-	if (!mptcp_pm_should_add_signal(msk) &&
-	    !mptcp_pm_should_rm_signal(msk))
-		return;
-
-	mptcp_for_each_subflow(msk, subflow) {
-		if (__mptcp_subflow_active(subflow)) {
-			if (!subflow->stale) {
-				mptcp_pm_send_ack(msk, subflow, false, false);
-				return;
-			}
-
-			if (!alt)
-				alt = subflow;
-		}
-	}
-
-	if (alt)
-		mptcp_pm_send_ack(msk, alt, false, false);
-}
-
-int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
-			      struct mptcp_addr_info *addr,
-			      struct mptcp_addr_info *rem,
-			      u8 bkup)
-{
-	struct mptcp_subflow_context *subflow;
-
-	pr_debug("bkup=%d\n", bkup);
-
-	mptcp_for_each_subflow(msk, subflow) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-		struct mptcp_addr_info local, remote;
-
-		mptcp_local_address((struct sock_common *)ssk, &local);
-		if (!mptcp_addresses_equal(&local, addr, addr->port))
-			continue;
-
-		if (rem && rem->family != AF_UNSPEC) {
-			mptcp_remote_address((struct sock_common *)ssk, &remote);
-			if (!mptcp_addresses_equal(&remote, rem, rem->port))
-				continue;
-		}
-
-		__mptcp_pm_send_ack(msk, subflow, true, bkup);
-		return 0;
-	}
-
-	return -EINVAL;
-}
-
-static void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
+void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
 {
 	if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
 		/* Note: if the subflow has been closed before, this
@@ -849,80 +515,6 @@ static void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
 	}
 }
 
-static void mptcp_pm_rm_addr_or_subflow(struct mptcp_sock *msk,
-					const struct mptcp_rm_list *rm_list,
-					enum linux_mptcp_mib_field rm_type)
-{
-	struct mptcp_subflow_context *subflow, *tmp;
-	struct sock *sk = (struct sock *)msk;
-	u8 i;
-
-	pr_debug("%s rm_list_nr %d\n",
-		 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
-
-	msk_owned_by_me(msk);
-
-	if (sk->sk_state == TCP_LISTEN)
-		return;
-
-	if (!rm_list->nr)
-		return;
-
-	if (list_empty(&msk->conn_list))
-		return;
-
-	for (i = 0; i < rm_list->nr; i++) {
-		u8 rm_id = rm_list->ids[i];
-		bool removed = false;
-
-		mptcp_for_each_subflow_safe(msk, subflow, tmp) {
-			struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-			u8 remote_id = READ_ONCE(subflow->remote_id);
-			int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
-			u8 id = subflow_get_local_id(subflow);
-
-			if ((1 << inet_sk_state_load(ssk)) &
-			    (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE))
-				continue;
-			if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
-				continue;
-			if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id)
-				continue;
-
-			pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n",
-				 rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
-				 i, rm_id, id, remote_id, msk->mpc_endpoint_id);
-			spin_unlock_bh(&msk->pm.lock);
-			mptcp_subflow_shutdown(sk, ssk, how);
-			removed |= subflow->request_join;
-
-			/* the following takes care of updating the subflows counter */
-			mptcp_close_ssk(sk, ssk, subflow);
-			spin_lock_bh(&msk->pm.lock);
-
-			if (rm_type == MPTCP_MIB_RMSUBFLOW)
-				__MPTCP_INC_STATS(sock_net(sk), rm_type);
-		}
-
-		if (rm_type == MPTCP_MIB_RMADDR) {
-			__MPTCP_INC_STATS(sock_net(sk), rm_type);
-			if (removed && mptcp_pm_is_kernel(msk))
-				mptcp_pm_nl_rm_addr(msk, rm_id);
-		}
-	}
-}
-
-void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk)
-{
-	mptcp_pm_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
-}
-
-static void mptcp_pm_rm_subflow(struct mptcp_sock *msk,
-				const struct mptcp_rm_list *rm_list)
-{
-	mptcp_pm_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
-}
-
 /* Called under PM lock */
 void __mptcp_pm_kernel_worker(struct mptcp_sock *msk)
 {
@@ -1186,43 +778,6 @@ static const struct genl_multicast_group mptcp_pm_mcgrps[] = {
 					  },
 };
 
-void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
-{
-	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
-	struct sock *sk = (struct sock *)msk;
-	unsigned int active_max_loss_cnt;
-	struct net *net = sock_net(sk);
-	unsigned int stale_loss_cnt;
-	bool slow;
-
-	stale_loss_cnt = mptcp_stale_loss_cnt(net);
-	if (subflow->stale || !stale_loss_cnt || subflow->stale_count <= stale_loss_cnt)
-		return;
-
-	/* look for another available subflow not in loss state */
-	active_max_loss_cnt = max_t(int, stale_loss_cnt - 1, 1);
-	mptcp_for_each_subflow(msk, iter) {
-		if (iter != subflow && mptcp_subflow_active(iter) &&
-		    iter->stale_count < active_max_loss_cnt) {
-			/* we have some alternatives, try to mark this subflow as idle ...*/
-			slow = lock_sock_fast(ssk);
-			if (!tcp_rtx_and_write_queues_empty(ssk)) {
-				subflow->stale = 1;
-				__mptcp_retransmit_pending_data(sk);
-				MPTCP_INC_STATS(net, MPTCP_MIB_SUBFLOWSTALE);
-			}
-			unlock_sock_fast(ssk, slow);
-
-			/* always try to push the pending data regardless of re-injections:
-			 * we can possibly use backup subflows now, and subflow selection
-			 * is cheap under the msk socket lock
-			 */
-			__mptcp_push_pending(sk, 0);
-			return;
-		}
-	}
-}
-
 static int mptcp_pm_family_to_addr(int family)
 {
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -1445,20 +1000,6 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
-bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,
-				     const struct mptcp_addr_info *addr)
-{
-	struct mptcp_pm_add_entry *entry;
-
-	entry = mptcp_pm_del_add_timer(msk, addr, false);
-	if (entry) {
-		kfree(entry);
-		return true;
-	}
-
-	return false;
-}
-
 static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
 				  const struct mptcp_addr_info *addr)
 {
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f66c3d28333fc..360d8cfa52797 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -996,7 +996,6 @@ bool mptcp_pm_addr_families_match(const struct sock *sk,
 				  const struct mptcp_addr_info *loc,
 				  const struct mptcp_addr_info *rem);
 void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
-void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk);
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side);
 void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk);
 bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk);
@@ -1010,10 +1009,13 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
 void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
 			      const struct mptcp_addr_info *addr);
 void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
-bool mptcp_pm_is_init_remote_addr(struct mptcp_sock *msk,
-				  const struct mptcp_addr_info *remote);
+void mptcp_pm_send_ack(struct mptcp_sock *msk,
+		       struct mptcp_subflow_context *subflow,
+		       bool prio, bool backup);
 void mptcp_pm_addr_send_ack(struct mptcp_sock *msk);
-void mptcp_pm_rm_addr_recv(struct mptcp_sock *msk);
+void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id);
+void mptcp_pm_rm_subflow(struct mptcp_sock *msk,
+			 const struct mptcp_rm_list *rm_list);
 void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
 			       const struct mptcp_rm_list *rm_list);
 void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup);
@@ -1024,14 +1026,10 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 			      u8 bkup);
 bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 			      const struct mptcp_addr_info *addr);
-void mptcp_pm_free_anno_list(struct mptcp_sock *msk);
 bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk);
 struct mptcp_pm_add_entry *
 mptcp_pm_del_add_timer(struct mptcp_sock *msk,
 		       const struct mptcp_addr_info *addr, bool check_id);
-struct mptcp_pm_add_entry *
-mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk,
-				const struct mptcp_addr_info *addr);
 bool mptcp_lookup_subflow_by_saddr(const struct list_head *list,
 				   const struct mptcp_addr_info *saddr);
 bool mptcp_remove_anno_list_by_saddr(struct mptcp_sock *msk,

From 8617e85e04bd08c6c6aa24c832f9bec10bf76648 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:58 +0100
Subject: [PATCH 1933/2753] mptcp: pm: split in-kernel PM specific code

Before this patch, the PM code was dispersed in different places:

- pm.c had common code for all PMs

- pm_netlink.c was supposed to be about the in-kernel PM, but also had
  exported common Netlink helpers, NL events for PM userspace daemons,
  etc. quite confusing.

To clarify the code, a reorganisation is suggested here, only by moving
code around to avoid confusions:

- pm_netlink.c now only contains common PM Netlink code:
  - PM events: this code was already there
  - shared helpers around Netlink code that were already there as well
  - more shared Netlink commands code from pm.c will come after

- pm_kernel.c now contains only code that is specific to the in-kernel
  PM. Now all functions are either called from:
  - pm.c: events coming from the core, when this PM is being used
  - pm_netlink.c: for shared Netlink commands
  - mptcp_pm_gen.c: for Netlink commands specific to the in-kernel PM
  - sockopt.c: for the exported counters per netns
  - (while at it, a useless 'return;' spot by checkpatch at the end of
     mptcp_pm_nl_set_flags_all, has been removed)

The code around the PM is now less confusing, which should help for the
maintenance in the long term.

This will certainly impact future backports, but because other cleanups
have already done recently, and more are coming to ease the addition of
a new path-manager controlled with BPF (struct_ops), doing that now
seems to be a good time. Also, many issues around the PM have been fixed
a few months ago while increasing the code coverage in the selftests, so
such big reorganisation can be done with more confidence now.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-14-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/Makefile     |    2 +-
 net/mptcp/pm_kernel.c  | 1410 ++++++++++++++++++++++++++++++++++++++++
 net/mptcp/pm_netlink.c | 1404 ---------------------------------------
 3 files changed, 1411 insertions(+), 1405 deletions(-)
 create mode 100644 net/mptcp/pm_kernel.c

diff --git a/net/mptcp/Makefile b/net/mptcp/Makefile
index bcf1dbf3a432f..89bf6c47c818d 100644
--- a/net/mptcp/Makefile
+++ b/net/mptcp/Makefile
@@ -3,7 +3,7 @@ obj-$(CONFIG_MPTCP) += mptcp.o
 
 mptcp-y := protocol.o subflow.o options.o token.o crypto.o ctrl.o pm.o diag.o \
 	   mib.o pm_netlink.o sockopt.o pm_userspace.o fastopen.o sched.o \
-	   mptcp_pm_gen.o
+	   mptcp_pm_gen.o pm_kernel.o
 
 obj-$(CONFIG_SYN_COOKIES) += syncookies.o
 obj-$(CONFIG_INET_MPTCP_DIAG) += mptcp_diag.o
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
new file mode 100644
index 0000000000000..daf8f98a31643
--- /dev/null
+++ b/net/mptcp/pm_kernel.c
@@ -0,0 +1,1410 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2025, Matthieu Baerts.
+ */
+
+#define pr_fmt(fmt) "MPTCP: " fmt
+
+#include <net/netns/generic.h>
+
+#include "protocol.h"
+#include "mib.h"
+#include "mptcp_pm_gen.h"
+
+static int pm_nl_pernet_id;
+
+struct pm_nl_pernet {
+	/* protects pernet updates */
+	spinlock_t		lock;
+	struct list_head	local_addr_list;
+	unsigned int		addrs;
+	unsigned int		stale_loss_cnt;
+	unsigned int		add_addr_signal_max;
+	unsigned int		add_addr_accept_max;
+	unsigned int		local_addr_max;
+	unsigned int		subflows_max;
+	unsigned int		next_id;
+	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+};
+
+#define MPTCP_PM_ADDR_MAX	8
+
+static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
+{
+	return net_generic(net, pm_nl_pernet_id);
+}
+
+static struct pm_nl_pernet *
+pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
+{
+	return pm_nl_get_pernet(sock_net((struct sock *)msk));
+}
+
+static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
+{
+	return pm_nl_get_pernet(genl_info_net(info));
+}
+
+unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
+{
+	const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	return READ_ONCE(pernet->add_addr_signal_max);
+}
+EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);
+
+unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	return READ_ONCE(pernet->add_addr_accept_max);
+}
+EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);
+
+unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	return READ_ONCE(pernet->subflows_max);
+}
+EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);
+
+unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	return READ_ONCE(pernet->local_addr_max);
+}
+EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);
+
+static bool lookup_subflow_by_daddr(const struct list_head *list,
+				    const struct mptcp_addr_info *daddr)
+{
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_addr_info cur;
+
+	list_for_each_entry(subflow, list, node) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+		if (!((1 << inet_sk_state_load(ssk)) &
+		      (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
+			continue;
+
+		mptcp_remote_address((struct sock_common *)ssk, &cur);
+		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
+			return true;
+	}
+
+	return false;
+}
+
+static bool
+select_local_address(const struct pm_nl_pernet *pernet,
+		     const struct mptcp_sock *msk,
+		     struct mptcp_pm_local *new_local)
+{
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
+
+	msk_owned_by_me(msk);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
+			continue;
+
+		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+			continue;
+
+		new_local->addr = entry->addr;
+		new_local->flags = entry->flags;
+		new_local->ifindex = entry->ifindex;
+		found = true;
+		break;
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
+static bool
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
+		      struct mptcp_pm_local *new_local)
+{
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
+
+	rcu_read_lock();
+	/* do not keep any additional per socket state, just signal
+	 * the address list in order.
+	 * Note: removal from the local address list during the msk life-cycle
+	 * can lead to additional addresses not being announced.
+	 */
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+			continue;
+
+		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
+			continue;
+
+		new_local->addr = entry->addr;
+		new_local->flags = entry->flags;
+		new_local->ifindex = entry->ifindex;
+		found = true;
+		break;
+	}
+	rcu_read_unlock();
+
+	return found;
+}
+
+/* Fill all the remote addresses into the array addrs[],
+ * and return the array size.
+ */
+static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
+					      struct mptcp_addr_info *local,
+					      bool fullmesh,
+					      struct mptcp_addr_info *addrs)
+{
+	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
+	struct sock *sk = (struct sock *)msk, *ssk;
+	struct mptcp_subflow_context *subflow;
+	struct mptcp_addr_info remote = { 0 };
+	unsigned int subflows_max;
+	int i = 0;
+
+	subflows_max = mptcp_pm_get_subflows_max(msk);
+	mptcp_remote_address((struct sock_common *)sk, &remote);
+
+	/* Non-fullmesh endpoint, fill in the single entry
+	 * corresponding to the primary MPC subflow remote address
+	 */
+	if (!fullmesh) {
+		if (deny_id0)
+			return 0;
+
+		if (!mptcp_pm_addr_families_match(sk, local, &remote))
+			return 0;
+
+		msk->pm.subflows++;
+		addrs[i++] = remote;
+	} else {
+		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+
+		/* Forbid creation of new subflows matching existing
+		 * ones, possibly already created by incoming ADD_ADDR
+		 */
+		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
+		mptcp_for_each_subflow(msk, subflow)
+			if (READ_ONCE(subflow->local_id) == local->id)
+				__set_bit(subflow->remote_id, unavail_id);
+
+		mptcp_for_each_subflow(msk, subflow) {
+			ssk = mptcp_subflow_tcp_sock(subflow);
+			mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
+			addrs[i].id = READ_ONCE(subflow->remote_id);
+			if (deny_id0 && !addrs[i].id)
+				continue;
+
+			if (test_bit(addrs[i].id, unavail_id))
+				continue;
+
+			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
+				continue;
+
+			if (msk->pm.subflows < subflows_max) {
+				/* forbid creating multiple address towards
+				 * this id
+				 */
+				__set_bit(addrs[i].id, unavail_id);
+				msk->pm.subflows++;
+				i++;
+			}
+		}
+	}
+
+	return i;
+}
+
+static struct mptcp_pm_addr_entry *
+__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
+{
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
+				lockdep_is_held(&pernet->lock)) {
+		if (entry->addr.id == id)
+			return entry;
+	}
+	return NULL;
+}
+
+static struct mptcp_pm_addr_entry *
+__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
+{
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
+				lockdep_is_held(&pernet->lock)) {
+		if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port))
+			return entry;
+	}
+	return NULL;
+}
+
+static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+{
+	struct sock *sk = (struct sock *)msk;
+	unsigned int add_addr_signal_max;
+	bool signal_and_subflow = false;
+	unsigned int local_addr_max;
+	struct pm_nl_pernet *pernet;
+	struct mptcp_pm_local local;
+	unsigned int subflows_max;
+
+	pernet = pm_nl_get_pernet(sock_net(sk));
+
+	add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
+	local_addr_max = mptcp_pm_get_local_addr_max(msk);
+	subflows_max = mptcp_pm_get_subflows_max(msk);
+
+	/* do lazy endpoint usage accounting for the MPC subflows */
+	if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
+		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
+		struct mptcp_pm_addr_entry *entry;
+		struct mptcp_addr_info mpc_addr;
+		bool backup = false;
+
+		mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
+		rcu_read_lock();
+		entry = __lookup_addr(pernet, &mpc_addr);
+		if (entry) {
+			__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
+			msk->mpc_endpoint_id = entry->addr.id;
+			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+		}
+		rcu_read_unlock();
+
+		if (backup)
+			mptcp_pm_send_ack(msk, subflow, true, backup);
+
+		msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
+	}
+
+	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
+		 msk->pm.local_addr_used, local_addr_max,
+		 msk->pm.add_addr_signaled, add_addr_signal_max,
+		 msk->pm.subflows, subflows_max);
+
+	/* check first for announce */
+	if (msk->pm.add_addr_signaled < add_addr_signal_max) {
+		/* due to racing events on both ends we can reach here while
+		 * previous add address is still running: if we invoke now
+		 * mptcp_pm_announce_addr(), that will fail and the
+		 * corresponding id will be marked as used.
+		 * Instead let the PM machinery reschedule us when the
+		 * current address announce will be completed.
+		 */
+		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
+			return;
+
+		if (!select_signal_address(pernet, msk, &local))
+			goto subflow;
+
+		/* If the alloc fails, we are on memory pressure, not worth
+		 * continuing, and trying to create subflows.
+		 */
+		if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
+			return;
+
+		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+		msk->pm.add_addr_signaled++;
+
+		/* Special case for ID0: set the correct ID */
+		if (local.addr.id == msk->mpc_endpoint_id)
+			local.addr.id = 0;
+
+		mptcp_pm_announce_addr(msk, &local.addr, false);
+		mptcp_pm_addr_send_ack(msk);
+
+		if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+			signal_and_subflow = true;
+	}
+
+subflow:
+	/* check if should create a new subflow */
+	while (msk->pm.local_addr_used < local_addr_max &&
+	       msk->pm.subflows < subflows_max) {
+		struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
+		bool fullmesh;
+		int i, nr;
+
+		if (signal_and_subflow)
+			signal_and_subflow = false;
+		else if (!select_local_address(pernet, msk, &local))
+			break;
+
+		fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+
+		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+
+		/* Special case for ID0: set the correct ID */
+		if (local.addr.id == msk->mpc_endpoint_id)
+			local.addr.id = 0;
+		else /* local_addr_used is not decr for ID 0 */
+			msk->pm.local_addr_used++;
+
+		nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
+		if (nr == 0)
+			continue;
+
+		spin_unlock_bh(&msk->pm.lock);
+		for (i = 0; i < nr; i++)
+			__mptcp_subflow_connect(sk, &local, &addrs[i]);
+		spin_lock_bh(&msk->pm.lock);
+	}
+	mptcp_pm_nl_check_work_pending(msk);
+}
+
+static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk)
+{
+	mptcp_pm_create_subflow_or_signal_addr(msk);
+}
+
+static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
+{
+	mptcp_pm_create_subflow_or_signal_addr(msk);
+}
+
+/* Fill all the local addresses into the array addrs[],
+ * and return the array size.
+ */
+static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
+					     struct mptcp_addr_info *remote,
+					     struct mptcp_pm_local *locals)
+{
+	struct sock *sk = (struct sock *)msk;
+	struct mptcp_pm_addr_entry *entry;
+	struct mptcp_addr_info mpc_addr;
+	struct pm_nl_pernet *pernet;
+	unsigned int subflows_max;
+	int i = 0;
+
+	pernet = pm_nl_get_pernet_from_msk(msk);
+	subflows_max = mptcp_pm_get_subflows_max(msk);
+
+	mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
+			continue;
+
+		if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote))
+			continue;
+
+		if (msk->pm.subflows < subflows_max) {
+			locals[i].addr = entry->addr;
+			locals[i].flags = entry->flags;
+			locals[i].ifindex = entry->ifindex;
+
+			/* Special case for ID0: set the correct ID */
+			if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port))
+				locals[i].addr.id = 0;
+
+			msk->pm.subflows++;
+			i++;
+		}
+	}
+	rcu_read_unlock();
+
+	/* If the array is empty, fill in the single
+	 * 'IPADDRANY' local address
+	 */
+	if (!i) {
+		memset(&locals[i], 0, sizeof(locals[i]));
+		locals[i].addr.family =
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+			       remote->family == AF_INET6 &&
+			       ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
+#endif
+			       remote->family;
+
+		if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote))
+			return 0;
+
+		msk->pm.subflows++;
+		i++;
+	}
+
+	return i;
+}
+
+static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX];
+	struct sock *sk = (struct sock *)msk;
+	unsigned int add_addr_accept_max;
+	struct mptcp_addr_info remote;
+	unsigned int subflows_max;
+	bool sf_created = false;
+	int i, nr;
+
+	add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
+	subflows_max = mptcp_pm_get_subflows_max(msk);
+
+	pr_debug("accepted %d:%d remote family %d\n",
+		 msk->pm.add_addr_accepted, add_addr_accept_max,
+		 msk->pm.remote.family);
+
+	remote = msk->pm.remote;
+	mptcp_pm_announce_addr(msk, &remote, true);
+	mptcp_pm_addr_send_ack(msk);
+
+	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
+		return;
+
+	/* pick id 0 port, if none is provided the remote address */
+	if (!remote.port)
+		remote.port = sk->sk_dport;
+
+	/* connect to the specified remote address, using whatever
+	 * local address the routing configuration will pick.
+	 */
+	nr = fill_local_addresses_vec(msk, &remote, locals);
+	if (nr == 0)
+		return;
+
+	spin_unlock_bh(&msk->pm.lock);
+	for (i = 0; i < nr; i++)
+		if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0)
+			sf_created = true;
+	spin_lock_bh(&msk->pm.lock);
+
+	if (sf_created) {
+		/* add_addr_accepted is not decr for ID 0 */
+		if (remote.id)
+			msk->pm.add_addr_accepted++;
+		if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
+		    msk->pm.subflows >= subflows_max)
+			WRITE_ONCE(msk->pm.accept_addr, false);
+	}
+}
+
+void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
+{
+	if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+		/* Note: if the subflow has been closed before, this
+		 * add_addr_accepted counter will not be decremented.
+		 */
+		if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+			WRITE_ONCE(msk->pm.accept_addr, true);
+	}
+}
+
+static bool address_use_port(struct mptcp_pm_addr_entry *entry)
+{
+	return (entry->flags &
+		(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
+		MPTCP_PM_ADDR_FLAG_SIGNAL;
+}
+
+/* caller must ensure the RCU grace period is already elapsed */
+static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
+{
+	if (entry->lsk)
+		sock_release(entry->lsk);
+	kfree(entry);
+}
+
+static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
+					     struct mptcp_pm_addr_entry *entry,
+					     bool needs_id, bool replace)
+{
+	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
+	unsigned int addr_max;
+	int ret = -EINVAL;
+
+	spin_lock_bh(&pernet->lock);
+	/* to keep the code simple, don't do IDR-like allocation for address ID,
+	 * just bail when we exceed limits
+	 */
+	if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
+		pernet->next_id = 1;
+	if (pernet->addrs >= MPTCP_PM_ADDR_MAX) {
+		ret = -ERANGE;
+		goto out;
+	}
+	if (test_bit(entry->addr.id, pernet->id_bitmap)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	/* do not insert duplicate address, differentiate on port only
+	 * singled addresses
+	 */
+	if (!address_use_port(entry))
+		entry->addr.port = 0;
+	list_for_each_entry(cur, &pernet->local_addr_list, list) {
+		if (mptcp_addresses_equal(&cur->addr, &entry->addr,
+					  cur->addr.port || entry->addr.port)) {
+			/* allow replacing the exiting endpoint only if such
+			 * endpoint is an implicit one and the user-space
+			 * did not provide an endpoint id
+			 */
+			if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) {
+				ret = -EEXIST;
+				goto out;
+			}
+			if (entry->addr.id)
+				goto out;
+
+			/* allow callers that only need to look up the local
+			 * addr's id to skip replacement. This allows them to
+			 * avoid calling synchronize_rcu in the packet recv
+			 * path.
+			 */
+			if (!replace) {
+				kfree(entry);
+				ret = cur->addr.id;
+				goto out;
+			}
+
+			pernet->addrs--;
+			entry->addr.id = cur->addr.id;
+			list_del_rcu(&cur->list);
+			del_entry = cur;
+			break;
+		}
+	}
+
+	if (!entry->addr.id && needs_id) {
+find_next:
+		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
+						    MPTCP_PM_MAX_ADDR_ID + 1,
+						    pernet->next_id);
+		if (!entry->addr.id && pernet->next_id != 1) {
+			pernet->next_id = 1;
+			goto find_next;
+		}
+	}
+
+	if (!entry->addr.id && needs_id)
+		goto out;
+
+	__set_bit(entry->addr.id, pernet->id_bitmap);
+	if (entry->addr.id > pernet->next_id)
+		pernet->next_id = entry->addr.id;
+
+	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+		addr_max = pernet->add_addr_signal_max;
+		WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1);
+	}
+	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+		addr_max = pernet->local_addr_max;
+		WRITE_ONCE(pernet->local_addr_max, addr_max + 1);
+	}
+
+	pernet->addrs++;
+	if (!entry->addr.port)
+		list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
+	else
+		list_add_rcu(&entry->list, &pernet->local_addr_list);
+	ret = entry->addr.id;
+
+out:
+	spin_unlock_bh(&pernet->lock);
+
+	/* just replaced an existing entry, free it */
+	if (del_entry) {
+		synchronize_rcu();
+		__mptcp_pm_release_addr_entry(del_entry);
+	}
+	return ret;
+}
+
+static struct lock_class_key mptcp_slock_keys[2];
+static struct lock_class_key mptcp_keys[2];
+
+static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
+					    struct mptcp_pm_addr_entry *entry)
+{
+	bool is_ipv6 = sk->sk_family == AF_INET6;
+	int addrlen = sizeof(struct sockaddr_in);
+	struct sockaddr_storage addr;
+	struct sock *newsk, *ssk;
+	int backlog = 1024;
+	int err;
+
+	err = sock_create_kern(sock_net(sk), entry->addr.family,
+			       SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk);
+	if (err)
+		return err;
+
+	newsk = entry->lsk->sk;
+	if (!newsk)
+		return -EINVAL;
+
+	/* The subflow socket lock is acquired in a nested to the msk one
+	 * in several places, even by the TCP stack, and this msk is a kernel
+	 * socket: lockdep complains. Instead of propagating the _nested
+	 * modifiers in several places, re-init the lock class for the msk
+	 * socket to an mptcp specific one.
+	 */
+	sock_lock_init_class_and_name(newsk,
+				      is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET",
+				      &mptcp_slock_keys[is_ipv6],
+				      is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET",
+				      &mptcp_keys[is_ipv6]);
+
+	lock_sock(newsk);
+	ssk = __mptcp_nmpc_sk(mptcp_sk(newsk));
+	release_sock(newsk);
+	if (IS_ERR(ssk))
+		return PTR_ERR(ssk);
+
+	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	if (entry->addr.family == AF_INET6)
+		addrlen = sizeof(struct sockaddr_in6);
+#endif
+	if (ssk->sk_family == AF_INET)
+		err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
+#if IS_ENABLED(CONFIG_MPTCP_IPV6)
+	else if (ssk->sk_family == AF_INET6)
+		err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
+#endif
+	if (err)
+		return err;
+
+	/* We don't use mptcp_set_state() here because it needs to be called
+	 * under the msk socket lock. For the moment, that will not bring
+	 * anything more than only calling inet_sk_state_store(), because the
+	 * old status is known (TCP_CLOSE).
+	 */
+	inet_sk_state_store(newsk, TCP_LISTEN);
+	lock_sock(ssk);
+	WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true);
+	err = __inet_listen_sk(ssk, backlog);
+	if (!err)
+		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);
+	release_sock(ssk);
+	return err;
+}
+
+int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
+			     struct mptcp_pm_addr_entry *skc)
+{
+	struct mptcp_pm_addr_entry *entry;
+	struct pm_nl_pernet *pernet;
+	int ret;
+
+	pernet = pm_nl_get_pernet_from_msk(msk);
+
+	rcu_read_lock();
+	entry = __lookup_addr(pernet, &skc->addr);
+	ret = entry ? entry->addr.id : -1;
+	rcu_read_unlock();
+	if (ret >= 0)
+		return ret;
+
+	/* address not found, add to local list */
+	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	if (!entry)
+		return -ENOMEM;
+
+	*entry = *skc;
+	entry->addr.port = 0;
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
+	if (ret < 0)
+		kfree(entry);
+
+	return ret;
+}
+
+bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+	struct mptcp_pm_addr_entry *entry;
+	bool backup;
+
+	rcu_read_lock();
+	entry = __lookup_addr(pernet, skc);
+	backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	rcu_read_unlock();
+
+	return backup;
+}
+
+static int mptcp_nl_add_subflow_or_signal_addr(struct net *net,
+					       struct mptcp_addr_info *addr)
+{
+	struct mptcp_sock *msk;
+	long s_slot = 0, s_num = 0;
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+		struct mptcp_addr_info mpc_addr;
+
+		if (!READ_ONCE(msk->fully_established) ||
+		    mptcp_pm_is_userspace(msk))
+			goto next;
+
+		/* if the endp linked to the init sf is re-added with a != ID */
+		mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
+		lock_sock(sk);
+		spin_lock_bh(&msk->pm.lock);
+		if (mptcp_addresses_equal(addr, &mpc_addr, addr->port))
+			msk->mpc_endpoint_id = addr->id;
+		mptcp_pm_create_subflow_or_signal_addr(msk);
+		spin_unlock_bh(&msk->pm.lock);
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
+				      struct genl_info *info)
+{
+	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
+
+	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
+					 mptcp_pm_address_nl_policy, info->extack) &&
+	    tb[MPTCP_PM_ADDR_ATTR_ID])
+		return true;
+	return false;
+}
+
+/* Add an MPTCP endpoint */
+int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	struct mptcp_pm_addr_entry addr, *entry;
+	struct nlattr *attr;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+	ret = mptcp_pm_parse_entry(attr, info, true, &addr);
+	if (ret < 0)
+		return ret;
+
+	if (addr.addr.port && !address_use_port(&addr)) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "flags must have signal and not subflow when using port");
+		return -EINVAL;
+	}
+
+	if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
+	    addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "flags mustn't have both signal and fullmesh");
+		return -EINVAL;
+	}
+
+	if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr,
+				    "can't create IMPLICIT endpoint");
+		return -EINVAL;
+	}
+
+	entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
+	if (!entry) {
+		GENL_SET_ERR_MSG(info, "can't allocate addr");
+		return -ENOMEM;
+	}
+
+	*entry = addr;
+	if (entry->addr.port) {
+		ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry);
+		if (ret) {
+			GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret);
+			goto out_free;
+		}
+	}
+	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
+						!mptcp_pm_has_addr_attr_id(attr, info),
+						true);
+	if (ret < 0) {
+		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
+		goto out_free;
+	}
+
+	mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr);
+	return 0;
+
+out_free:
+	__mptcp_pm_release_addr_entry(entry);
+	return ret;
+}
+
+static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
+				  const struct mptcp_addr_info *addr)
+{
+	return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
+}
+
+static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+				      const struct mptcp_addr_info *addr,
+				      bool force)
+{
+	struct mptcp_rm_list list = { .nr = 0 };
+	bool ret;
+
+	list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
+
+	ret = mptcp_remove_anno_list_by_saddr(msk, addr);
+	if (ret || force) {
+		spin_lock_bh(&msk->pm.lock);
+		if (ret) {
+			__set_bit(addr->id, msk->pm.id_avail_bitmap);
+			msk->pm.add_addr_signaled--;
+		}
+		mptcp_pm_remove_addr(msk, &list);
+		spin_unlock_bh(&msk->pm.lock);
+	}
+	return ret;
+}
+
+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
+{
+	/* If it was marked as used, and not ID 0, decrement local_addr_used */
+	if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
+	    id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
+		msk->pm.local_addr_used--;
+}
+
+static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+						   const struct mptcp_pm_addr_entry *entry)
+{
+	const struct mptcp_addr_info *addr = &entry->addr;
+	struct mptcp_rm_list list = { .nr = 1 };
+	long s_slot = 0, s_num = 0;
+	struct mptcp_sock *msk;
+
+	pr_debug("remove_id=%d\n", addr->id);
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+		bool remove_subflow;
+
+		if (mptcp_pm_is_userspace(msk))
+			goto next;
+
+		lock_sock(sk);
+		remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr);
+		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
+
+		list.ids[0] = mptcp_endp_get_local_id(msk, addr);
+		if (remove_subflow) {
+			spin_lock_bh(&msk->pm.lock);
+			mptcp_pm_rm_subflow(msk, &list);
+			spin_unlock_bh(&msk->pm.lock);
+		}
+
+		if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+			spin_lock_bh(&msk->pm.lock);
+			__mark_subflow_endp_available(msk, list.ids[0]);
+			spin_unlock_bh(&msk->pm.lock);
+		}
+
+		if (msk->mpc_endpoint_id == entry->addr.id)
+			msk->mpc_endpoint_id = 0;
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+static int mptcp_nl_remove_id_zero_address(struct net *net,
+					   struct mptcp_addr_info *addr)
+{
+	struct mptcp_rm_list list = { .nr = 0 };
+	long s_slot = 0, s_num = 0;
+	struct mptcp_sock *msk;
+
+	list.ids[list.nr++] = 0;
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+		struct mptcp_addr_info msk_local;
+
+		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
+			goto next;
+
+		mptcp_local_address((struct sock_common *)msk, &msk_local);
+		if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
+			goto next;
+
+		lock_sock(sk);
+		spin_lock_bh(&msk->pm.lock);
+		mptcp_pm_remove_addr(msk, &list);
+		mptcp_pm_rm_subflow(msk, &list);
+		__mark_subflow_endp_available(msk, 0);
+		spin_unlock_bh(&msk->pm.lock);
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+
+	return 0;
+}
+
+/* Remove an MPTCP endpoint */
+int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	struct mptcp_pm_addr_entry addr, *entry;
+	unsigned int addr_max;
+	struct nlattr *attr;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
+	if (ret < 0)
+		return ret;
+
+	/* the zero id address is special: the first address used by the msk
+	 * always gets such an id, so different subflows can have different zero
+	 * id addresses. Additionally zero id is not accounted for in id_bitmap.
+	 * Let's use an 'mptcp_rm_list' instead of the common remove code.
+	 */
+	if (addr.addr.id == 0)
+		return mptcp_nl_remove_id_zero_address(sock_net(skb->sk), &addr.addr);
+
+	spin_lock_bh(&pernet->lock);
+	entry = __lookup_addr_by_id(pernet, addr.addr.id);
+	if (!entry) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
+		spin_unlock_bh(&pernet->lock);
+		return -EINVAL;
+	}
+	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
+		addr_max = pernet->add_addr_signal_max;
+		WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1);
+	}
+	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+		addr_max = pernet->local_addr_max;
+		WRITE_ONCE(pernet->local_addr_max, addr_max - 1);
+	}
+
+	pernet->addrs--;
+	list_del_rcu(&entry->list);
+	__clear_bit(entry->addr.id, pernet->id_bitmap);
+	spin_unlock_bh(&pernet->lock);
+
+	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry);
+	synchronize_rcu();
+	__mptcp_pm_release_addr_entry(entry);
+
+	return ret;
+}
+
+static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
+					      struct list_head *rm_list)
+{
+	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
+	struct mptcp_pm_addr_entry *entry;
+
+	list_for_each_entry(entry, rm_list, list) {
+		if (slist.nr < MPTCP_RM_IDS_MAX &&
+		    mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+			slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+
+		if (alist.nr < MPTCP_RM_IDS_MAX &&
+		    mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
+			alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+	}
+
+	spin_lock_bh(&msk->pm.lock);
+	if (alist.nr) {
+		msk->pm.add_addr_signaled -= alist.nr;
+		mptcp_pm_remove_addr(msk, &alist);
+	}
+	if (slist.nr)
+		mptcp_pm_rm_subflow(msk, &slist);
+	/* Reset counters: maybe some subflows have been removed before */
+	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	msk->pm.local_addr_used = 0;
+	spin_unlock_bh(&msk->pm.lock);
+}
+
+static void mptcp_nl_flush_addrs_list(struct net *net,
+				      struct list_head *rm_list)
+{
+	long s_slot = 0, s_num = 0;
+	struct mptcp_sock *msk;
+
+	if (list_empty(rm_list))
+		return;
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+
+		if (!mptcp_pm_is_userspace(msk)) {
+			lock_sock(sk);
+			mptcp_pm_flush_addrs_and_subflows(msk, rm_list);
+			release_sock(sk);
+		}
+
+		sock_put(sk);
+		cond_resched();
+	}
+}
+
+/* caller must ensure the RCU grace period is already elapsed */
+static void __flush_addrs(struct list_head *list)
+{
+	while (!list_empty(list)) {
+		struct mptcp_pm_addr_entry *cur;
+
+		cur = list_entry(list->next,
+				 struct mptcp_pm_addr_entry, list);
+		list_del_rcu(&cur->list);
+		__mptcp_pm_release_addr_entry(cur);
+	}
+}
+
+static void __reset_counters(struct pm_nl_pernet *pernet)
+{
+	WRITE_ONCE(pernet->add_addr_signal_max, 0);
+	WRITE_ONCE(pernet->add_addr_accept_max, 0);
+	WRITE_ONCE(pernet->local_addr_max, 0);
+	pernet->addrs = 0;
+}
+
+int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	LIST_HEAD(free_list);
+
+	spin_lock_bh(&pernet->lock);
+	list_splice_init(&pernet->local_addr_list, &free_list);
+	__reset_counters(pernet);
+	pernet->next_id = 1;
+	bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	spin_unlock_bh(&pernet->lock);
+	mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list);
+	synchronize_rcu();
+	__flush_addrs(&free_list);
+	return 0;
+}
+
+int mptcp_pm_nl_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+			 struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	struct mptcp_pm_addr_entry *entry;
+	int ret = -EINVAL;
+
+	rcu_read_lock();
+	entry = __lookup_addr_by_id(pernet, id);
+	if (entry) {
+		*addr = *entry;
+		ret = 0;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
+			  struct netlink_callback *cb)
+{
+	struct net *net = sock_net(msg->sk);
+	struct mptcp_pm_addr_entry *entry;
+	struct pm_nl_pernet *pernet;
+	int id = cb->args[0];
+	int i;
+
+	pernet = pm_nl_get_pernet(net);
+
+	rcu_read_lock();
+	for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) {
+		if (test_bit(i, pernet->id_bitmap)) {
+			entry = __lookup_addr_by_id(pernet, i);
+			if (!entry)
+				break;
+
+			if (entry->addr.id <= id)
+				continue;
+
+			if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
+				break;
+
+			id = entry->addr.id;
+		}
+	}
+	rcu_read_unlock();
+
+	cb->args[0] = id;
+	return msg->len;
+}
+
+static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
+{
+	struct nlattr *attr = info->attrs[id];
+
+	if (!attr)
+		return 0;
+
+	*limit = nla_get_u32(attr);
+	if (*limit > MPTCP_PM_ADDR_MAX) {
+		NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr,
+					"limit greater than maximum (%u)",
+					MPTCP_PM_ADDR_MAX);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	unsigned int rcv_addrs, subflows;
+	int ret;
+
+	spin_lock_bh(&pernet->lock);
+	rcv_addrs = pernet->add_addr_accept_max;
+	ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs);
+	if (ret)
+		goto unlock;
+
+	subflows = pernet->subflows_max;
+	ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows);
+	if (ret)
+		goto unlock;
+
+	WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs);
+	WRITE_ONCE(pernet->subflows_max, subflows);
+
+unlock:
+	spin_unlock_bh(&pernet->lock);
+	return ret;
+}
+
+int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
+	struct sk_buff *msg;
+	void *reply;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
+				  MPTCP_PM_CMD_GET_LIMITS);
+	if (!reply)
+		goto fail;
+
+	if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS,
+			READ_ONCE(pernet->add_addr_accept_max)))
+		goto fail;
+
+	if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS,
+			READ_ONCE(pernet->subflows_max)))
+		goto fail;
+
+	genlmsg_end(msg, reply);
+	return genlmsg_reply(msg, info);
+
+fail:
+	GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
+	nlmsg_free(msg);
+	return -EMSGSIZE;
+}
+
+static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
+				 struct mptcp_addr_info *addr)
+{
+	struct mptcp_rm_list list = { .nr = 0 };
+
+	list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
+
+	spin_lock_bh(&msk->pm.lock);
+	mptcp_pm_rm_subflow(msk, &list);
+	__mark_subflow_endp_available(msk, list.ids[0]);
+	mptcp_pm_create_subflow_or_signal_addr(msk);
+	spin_unlock_bh(&msk->pm.lock);
+}
+
+static void mptcp_pm_nl_set_flags_all(struct net *net,
+				      struct mptcp_pm_addr_entry *local,
+				      u8 changed)
+{
+	u8 is_subflow = !!(local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
+	u8 bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
+	long s_slot = 0, s_num = 0;
+	struct mptcp_sock *msk;
+
+	if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow)
+		return;
+
+	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+		struct sock *sk = (struct sock *)msk;
+
+		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
+			goto next;
+
+		lock_sock(sk);
+		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
+			mptcp_pm_mp_prio_send_ack(msk, &local->addr, NULL, bkup);
+		/* Subflows will only be recreated if the SUBFLOW flag is set */
+		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
+			mptcp_pm_nl_fullmesh(msk, &local->addr);
+		release_sock(sk);
+
+next:
+		sock_put(sk);
+		cond_resched();
+	}
+}
+
+int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
+			  struct genl_info *info)
+{
+	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
+	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
+			   MPTCP_PM_ADDR_FLAG_FULLMESH;
+	struct net *net = genl_info_net(info);
+	struct mptcp_pm_addr_entry *entry;
+	struct pm_nl_pernet *pernet;
+	u8 lookup_by_id = 0;
+
+	pernet = pm_nl_get_pernet(net);
+
+	if (local->addr.family == AF_UNSPEC) {
+		lookup_by_id = 1;
+		if (!local->addr.id) {
+			NL_SET_ERR_MSG_ATTR(info->extack, attr,
+					    "missing address ID");
+			return -EOPNOTSUPP;
+		}
+	}
+
+	spin_lock_bh(&pernet->lock);
+	entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) :
+			       __lookup_addr(pernet, &local->addr);
+	if (!entry) {
+		spin_unlock_bh(&pernet->lock);
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
+		return -EINVAL;
+	}
+	if ((local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
+	    (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |
+			     MPTCP_PM_ADDR_FLAG_IMPLICIT))) {
+		spin_unlock_bh(&pernet->lock);
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "invalid addr flags");
+		return -EINVAL;
+	}
+
+	changed = (local->flags ^ entry->flags) & mask;
+	entry->flags = (entry->flags & ~mask) | (local->flags & mask);
+	*local = *entry;
+	spin_unlock_bh(&pernet->lock);
+
+	mptcp_pm_nl_set_flags_all(net, local, changed);
+	return 0;
+}
+
+bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
+
+	if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) ||
+	    (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap,
+			       MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) {
+		WRITE_ONCE(msk->pm.work_pending, false);
+		return false;
+	}
+	return true;
+}
+
+/* Called under PM lock */
+void __mptcp_pm_kernel_worker(struct mptcp_sock *msk)
+{
+	struct mptcp_pm_data *pm = &msk->pm;
+
+	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
+		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
+		mptcp_pm_nl_add_addr_received(msk);
+	}
+	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
+		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
+		mptcp_pm_nl_fully_established(msk);
+	}
+	if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) {
+		pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
+		mptcp_pm_nl_subflow_established(msk);
+	}
+}
+
+static int __net_init pm_nl_init_net(struct net *net)
+{
+	struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
+
+	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
+
+	/* Cit. 2 subflows ought to be enough for anybody. */
+	pernet->subflows_max = 2;
+	pernet->next_id = 1;
+	pernet->stale_loss_cnt = 4;
+	spin_lock_init(&pernet->lock);
+
+	/* No need to initialize other pernet fields, the struct is zeroed at
+	 * allocation time.
+	 */
+
+	return 0;
+}
+
+static void __net_exit pm_nl_exit_net(struct list_head *net_list)
+{
+	struct net *net;
+
+	list_for_each_entry(net, net_list, exit_list) {
+		struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
+
+		/* net is removed from namespace list, can't race with
+		 * other modifiers, also netns core already waited for a
+		 * RCU grace period.
+		 */
+		__flush_addrs(&pernet->local_addr_list);
+	}
+}
+
+static struct pernet_operations mptcp_pm_pernet_ops = {
+	.init = pm_nl_init_net,
+	.exit_batch = pm_nl_exit_net,
+	.id = &pm_nl_pernet_id,
+	.size = sizeof(struct pm_nl_pernet),
+};
+
+void __init mptcp_pm_nl_init(void)
+{
+	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
+		panic("Failed to register MPTCP PM pernet subsystem.\n");
+
+	if (genl_register_family(&mptcp_genl_family))
+		panic("Failed to register MPTCP PM netlink family\n");
+}
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index e4abb94e8c0bd..530b2362a5a35 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -6,768 +6,9 @@
 
 #define pr_fmt(fmt) "MPTCP: " fmt
 
-#include <linux/inet.h>
-#include <linux/kernel.h>
-#include <net/inet_common.h>
-#include <net/netns/generic.h>
-#include <net/mptcp.h>
-
 #include "protocol.h"
-#include "mib.h"
 #include "mptcp_pm_gen.h"
 
-static int pm_nl_pernet_id;
-
-struct pm_nl_pernet {
-	/* protects pernet updates */
-	spinlock_t		lock;
-	struct list_head	local_addr_list;
-	unsigned int		addrs;
-	unsigned int		stale_loss_cnt;
-	unsigned int		add_addr_signal_max;
-	unsigned int		add_addr_accept_max;
-	unsigned int		local_addr_max;
-	unsigned int		subflows_max;
-	unsigned int		next_id;
-	DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-};
-
-#define MPTCP_PM_ADDR_MAX	8
-
-static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net)
-{
-	return net_generic(net, pm_nl_pernet_id);
-}
-
-static struct pm_nl_pernet *
-pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk)
-{
-	return pm_nl_get_pernet(sock_net((struct sock *)msk));
-}
-
-static bool lookup_subflow_by_daddr(const struct list_head *list,
-				    const struct mptcp_addr_info *daddr)
-{
-	struct mptcp_subflow_context *subflow;
-	struct mptcp_addr_info cur;
-
-	list_for_each_entry(subflow, list, node) {
-		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
-
-		if (!((1 << inet_sk_state_load(ssk)) &
-		      (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
-			continue;
-
-		mptcp_remote_address((struct sock_common *)ssk, &cur);
-		if (mptcp_addresses_equal(&cur, daddr, daddr->port))
-			return true;
-	}
-
-	return false;
-}
-
-static bool
-select_local_address(const struct pm_nl_pernet *pernet,
-		     const struct mptcp_sock *msk,
-		     struct mptcp_pm_local *new_local)
-{
-	struct mptcp_pm_addr_entry *entry;
-	bool found = false;
-
-	msk_owned_by_me(msk);
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW))
-			continue;
-
-		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
-			continue;
-
-		new_local->addr = entry->addr;
-		new_local->flags = entry->flags;
-		new_local->ifindex = entry->ifindex;
-		found = true;
-		break;
-	}
-	rcu_read_unlock();
-
-	return found;
-}
-
-static bool
-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
-		     struct mptcp_pm_local *new_local)
-{
-	struct mptcp_pm_addr_entry *entry;
-	bool found = false;
-
-	rcu_read_lock();
-	/* do not keep any additional per socket state, just signal
-	 * the address list in order.
-	 * Note: removal from the local address list during the msk life-cycle
-	 * can lead to additional addresses not being announced.
-	 */
-	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
-			continue;
-
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
-			continue;
-
-		new_local->addr = entry->addr;
-		new_local->flags = entry->flags;
-		new_local->ifindex = entry->ifindex;
-		found = true;
-		break;
-	}
-	rcu_read_unlock();
-
-	return found;
-}
-
-unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
-{
-	const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-
-	return READ_ONCE(pernet->add_addr_signal_max);
-}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_signal_max);
-
-unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-
-	return READ_ONCE(pernet->add_addr_accept_max);
-}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_add_addr_accept_max);
-
-unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-
-	return READ_ONCE(pernet->subflows_max);
-}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_subflows_max);
-
-unsigned int mptcp_pm_get_local_addr_max(const struct mptcp_sock *msk)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-
-	return READ_ONCE(pernet->local_addr_max);
-}
-EXPORT_SYMBOL_GPL(mptcp_pm_get_local_addr_max);
-
-bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-
-	if (msk->pm.subflows == mptcp_pm_get_subflows_max(msk) ||
-	    (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap,
-			       MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) {
-		WRITE_ONCE(msk->pm.work_pending, false);
-		return false;
-	}
-	return true;
-}
-
-/* Fill all the remote addresses into the array addrs[],
- * and return the array size.
- */
-static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk,
-					      struct mptcp_addr_info *local,
-					      bool fullmesh,
-					      struct mptcp_addr_info *addrs)
-{
-	bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0);
-	struct sock *sk = (struct sock *)msk, *ssk;
-	struct mptcp_subflow_context *subflow;
-	struct mptcp_addr_info remote = { 0 };
-	unsigned int subflows_max;
-	int i = 0;
-
-	subflows_max = mptcp_pm_get_subflows_max(msk);
-	mptcp_remote_address((struct sock_common *)sk, &remote);
-
-	/* Non-fullmesh endpoint, fill in the single entry
-	 * corresponding to the primary MPC subflow remote address
-	 */
-	if (!fullmesh) {
-		if (deny_id0)
-			return 0;
-
-		if (!mptcp_pm_addr_families_match(sk, local, &remote))
-			return 0;
-
-		msk->pm.subflows++;
-		addrs[i++] = remote;
-	} else {
-		DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
-
-		/* Forbid creation of new subflows matching existing
-		 * ones, possibly already created by incoming ADD_ADDR
-		 */
-		bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1);
-		mptcp_for_each_subflow(msk, subflow)
-			if (READ_ONCE(subflow->local_id) == local->id)
-				__set_bit(subflow->remote_id, unavail_id);
-
-		mptcp_for_each_subflow(msk, subflow) {
-			ssk = mptcp_subflow_tcp_sock(subflow);
-			mptcp_remote_address((struct sock_common *)ssk, &addrs[i]);
-			addrs[i].id = READ_ONCE(subflow->remote_id);
-			if (deny_id0 && !addrs[i].id)
-				continue;
-
-			if (test_bit(addrs[i].id, unavail_id))
-				continue;
-
-			if (!mptcp_pm_addr_families_match(sk, local, &addrs[i]))
-				continue;
-
-			if (msk->pm.subflows < subflows_max) {
-				/* forbid creating multiple address towards
-				 * this id
-				 */
-				__set_bit(addrs[i].id, unavail_id);
-				msk->pm.subflows++;
-				i++;
-			}
-		}
-	}
-
-	return i;
-}
-
-static struct mptcp_pm_addr_entry *
-__lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id)
-{
-	struct mptcp_pm_addr_entry *entry;
-
-	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
-				lockdep_is_held(&pernet->lock)) {
-		if (entry->addr.id == id)
-			return entry;
-	}
-	return NULL;
-}
-
-static struct mptcp_pm_addr_entry *
-__lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
-{
-	struct mptcp_pm_addr_entry *entry;
-
-	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list,
-				lockdep_is_held(&pernet->lock)) {
-		if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port))
-			return entry;
-	}
-	return NULL;
-}
-
-static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
-{
-	struct sock *sk = (struct sock *)msk;
-	unsigned int add_addr_signal_max;
-	bool signal_and_subflow = false;
-	unsigned int local_addr_max;
-	struct pm_nl_pernet *pernet;
-	struct mptcp_pm_local local;
-	unsigned int subflows_max;
-
-	pernet = pm_nl_get_pernet(sock_net(sk));
-
-	add_addr_signal_max = mptcp_pm_get_add_addr_signal_max(msk);
-	local_addr_max = mptcp_pm_get_local_addr_max(msk);
-	subflows_max = mptcp_pm_get_subflows_max(msk);
-
-	/* do lazy endpoint usage accounting for the MPC subflows */
-	if (unlikely(!(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED))) && msk->first) {
-		struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(msk->first);
-		struct mptcp_pm_addr_entry *entry;
-		struct mptcp_addr_info mpc_addr;
-		bool backup = false;
-
-		mptcp_local_address((struct sock_common *)msk->first, &mpc_addr);
-		rcu_read_lock();
-		entry = __lookup_addr(pernet, &mpc_addr);
-		if (entry) {
-			__clear_bit(entry->addr.id, msk->pm.id_avail_bitmap);
-			msk->mpc_endpoint_id = entry->addr.id;
-			backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
-		}
-		rcu_read_unlock();
-
-		if (backup)
-			mptcp_pm_send_ack(msk, subflow, true, backup);
-
-		msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED);
-	}
-
-	pr_debug("local %d:%d signal %d:%d subflows %d:%d\n",
-		 msk->pm.local_addr_used, local_addr_max,
-		 msk->pm.add_addr_signaled, add_addr_signal_max,
-		 msk->pm.subflows, subflows_max);
-
-	/* check first for announce */
-	if (msk->pm.add_addr_signaled < add_addr_signal_max) {
-		/* due to racing events on both ends we can reach here while
-		 * previous add address is still running: if we invoke now
-		 * mptcp_pm_announce_addr(), that will fail and the
-		 * corresponding id will be marked as used.
-		 * Instead let the PM machinery reschedule us when the
-		 * current address announce will be completed.
-		 */
-		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
-			return;
-
-		if (!select_signal_address(pernet, msk, &local))
-			goto subflow;
-
-		/* If the alloc fails, we are on memory pressure, not worth
-		 * continuing, and trying to create subflows.
-		 */
-		if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
-			return;
-
-		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
-		msk->pm.add_addr_signaled++;
-
-		/* Special case for ID0: set the correct ID */
-		if (local.addr.id == msk->mpc_endpoint_id)
-			local.addr.id = 0;
-
-		mptcp_pm_announce_addr(msk, &local.addr, false);
-		mptcp_pm_addr_send_ack(msk);
-
-		if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
-			signal_and_subflow = true;
-	}
-
-subflow:
-	/* check if should create a new subflow */
-	while (msk->pm.local_addr_used < local_addr_max &&
-	       msk->pm.subflows < subflows_max) {
-		struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX];
-		bool fullmesh;
-		int i, nr;
-
-		if (signal_and_subflow)
-			signal_and_subflow = false;
-		else if (!select_local_address(pernet, msk, &local))
-			break;
-
-		fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
-
-		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
-
-		/* Special case for ID0: set the correct ID */
-		if (local.addr.id == msk->mpc_endpoint_id)
-			local.addr.id = 0;
-		else /* local_addr_used is not decr for ID 0 */
-			msk->pm.local_addr_used++;
-
-		nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
-		if (nr == 0)
-			continue;
-
-		spin_unlock_bh(&msk->pm.lock);
-		for (i = 0; i < nr; i++)
-			__mptcp_subflow_connect(sk, &local, &addrs[i]);
-		spin_lock_bh(&msk->pm.lock);
-	}
-	mptcp_pm_nl_check_work_pending(msk);
-}
-
-static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk)
-{
-	mptcp_pm_create_subflow_or_signal_addr(msk);
-}
-
-static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk)
-{
-	mptcp_pm_create_subflow_or_signal_addr(msk);
-}
-
-/* Fill all the local addresses into the array addrs[],
- * and return the array size.
- */
-static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
-					     struct mptcp_addr_info *remote,
-					     struct mptcp_pm_local *locals)
-{
-	struct sock *sk = (struct sock *)msk;
-	struct mptcp_pm_addr_entry *entry;
-	struct mptcp_addr_info mpc_addr;
-	struct pm_nl_pernet *pernet;
-	unsigned int subflows_max;
-	int i = 0;
-
-	pernet = pm_nl_get_pernet_from_msk(msk);
-	subflows_max = mptcp_pm_get_subflows_max(msk);
-
-	mptcp_local_address((struct sock_common *)msk, &mpc_addr);
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
-		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
-			continue;
-
-		if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote))
-			continue;
-
-		if (msk->pm.subflows < subflows_max) {
-			locals[i].addr = entry->addr;
-			locals[i].flags = entry->flags;
-			locals[i].ifindex = entry->ifindex;
-
-			/* Special case for ID0: set the correct ID */
-			if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port))
-				locals[i].addr.id = 0;
-
-			msk->pm.subflows++;
-			i++;
-		}
-	}
-	rcu_read_unlock();
-
-	/* If the array is empty, fill in the single
-	 * 'IPADDRANY' local address
-	 */
-	if (!i) {
-		memset(&locals[i], 0, sizeof(locals[i]));
-		locals[i].addr.family =
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-			       remote->family == AF_INET6 &&
-			       ipv6_addr_v4mapped(&remote->addr6) ? AF_INET :
-#endif
-			       remote->family;
-
-		if (!mptcp_pm_addr_families_match(sk, &locals[i].addr, remote))
-			return 0;
-
-		msk->pm.subflows++;
-		i++;
-	}
-
-	return i;
-}
-
-static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
-{
-	struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX];
-	struct sock *sk = (struct sock *)msk;
-	unsigned int add_addr_accept_max;
-	struct mptcp_addr_info remote;
-	unsigned int subflows_max;
-	bool sf_created = false;
-	int i, nr;
-
-	add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
-	subflows_max = mptcp_pm_get_subflows_max(msk);
-
-	pr_debug("accepted %d:%d remote family %d\n",
-		 msk->pm.add_addr_accepted, add_addr_accept_max,
-		 msk->pm.remote.family);
-
-	remote = msk->pm.remote;
-	mptcp_pm_announce_addr(msk, &remote, true);
-	mptcp_pm_addr_send_ack(msk);
-
-	if (lookup_subflow_by_daddr(&msk->conn_list, &remote))
-		return;
-
-	/* pick id 0 port, if none is provided the remote address */
-	if (!remote.port)
-		remote.port = sk->sk_dport;
-
-	/* connect to the specified remote address, using whatever
-	 * local address the routing configuration will pick.
-	 */
-	nr = fill_local_addresses_vec(msk, &remote, locals);
-	if (nr == 0)
-		return;
-
-	spin_unlock_bh(&msk->pm.lock);
-	for (i = 0; i < nr; i++)
-		if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0)
-			sf_created = true;
-	spin_lock_bh(&msk->pm.lock);
-
-	if (sf_created) {
-		/* add_addr_accepted is not decr for ID 0 */
-		if (remote.id)
-			msk->pm.add_addr_accepted++;
-		if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
-		    msk->pm.subflows >= subflows_max)
-			WRITE_ONCE(msk->pm.accept_addr, false);
-	}
-}
-
-void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id)
-{
-	if (rm_id && WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
-		/* Note: if the subflow has been closed before, this
-		 * add_addr_accepted counter will not be decremented.
-		 */
-		if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
-			WRITE_ONCE(msk->pm.accept_addr, true);
-	}
-}
-
-/* Called under PM lock */
-void __mptcp_pm_kernel_worker(struct mptcp_sock *msk)
-{
-	struct mptcp_pm_data *pm = &msk->pm;
-
-	if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
-		pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
-		mptcp_pm_nl_add_addr_received(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) {
-		pm->status &= ~BIT(MPTCP_PM_ESTABLISHED);
-		mptcp_pm_nl_fully_established(msk);
-	}
-	if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) {
-		pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED);
-		mptcp_pm_nl_subflow_established(msk);
-	}
-}
-
-static bool address_use_port(struct mptcp_pm_addr_entry *entry)
-{
-	return (entry->flags &
-		(MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) ==
-		MPTCP_PM_ADDR_FLAG_SIGNAL;
-}
-
-/* caller must ensure the RCU grace period is already elapsed */
-static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry)
-{
-	if (entry->lsk)
-		sock_release(entry->lsk);
-	kfree(entry);
-}
-
-static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet,
-					     struct mptcp_pm_addr_entry *entry,
-					     bool needs_id, bool replace)
-{
-	struct mptcp_pm_addr_entry *cur, *del_entry = NULL;
-	unsigned int addr_max;
-	int ret = -EINVAL;
-
-	spin_lock_bh(&pernet->lock);
-	/* to keep the code simple, don't do IDR-like allocation for address ID,
-	 * just bail when we exceed limits
-	 */
-	if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID)
-		pernet->next_id = 1;
-	if (pernet->addrs >= MPTCP_PM_ADDR_MAX) {
-		ret = -ERANGE;
-		goto out;
-	}
-	if (test_bit(entry->addr.id, pernet->id_bitmap)) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	/* do not insert duplicate address, differentiate on port only
-	 * singled addresses
-	 */
-	if (!address_use_port(entry))
-		entry->addr.port = 0;
-	list_for_each_entry(cur, &pernet->local_addr_list, list) {
-		if (mptcp_addresses_equal(&cur->addr, &entry->addr,
-					  cur->addr.port || entry->addr.port)) {
-			/* allow replacing the exiting endpoint only if such
-			 * endpoint is an implicit one and the user-space
-			 * did not provide an endpoint id
-			 */
-			if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) {
-				ret = -EEXIST;
-				goto out;
-			}
-			if (entry->addr.id)
-				goto out;
-
-			/* allow callers that only need to look up the local
-			 * addr's id to skip replacement. This allows them to
-			 * avoid calling synchronize_rcu in the packet recv
-			 * path.
-			 */
-			if (!replace) {
-				kfree(entry);
-				ret = cur->addr.id;
-				goto out;
-			}
-
-			pernet->addrs--;
-			entry->addr.id = cur->addr.id;
-			list_del_rcu(&cur->list);
-			del_entry = cur;
-			break;
-		}
-	}
-
-	if (!entry->addr.id && needs_id) {
-find_next:
-		entry->addr.id = find_next_zero_bit(pernet->id_bitmap,
-						    MPTCP_PM_MAX_ADDR_ID + 1,
-						    pernet->next_id);
-		if (!entry->addr.id && pernet->next_id != 1) {
-			pernet->next_id = 1;
-			goto find_next;
-		}
-	}
-
-	if (!entry->addr.id && needs_id)
-		goto out;
-
-	__set_bit(entry->addr.id, pernet->id_bitmap);
-	if (entry->addr.id > pernet->next_id)
-		pernet->next_id = entry->addr.id;
-
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
-		addr_max = pernet->add_addr_signal_max;
-		WRITE_ONCE(pernet->add_addr_signal_max, addr_max + 1);
-	}
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
-		addr_max = pernet->local_addr_max;
-		WRITE_ONCE(pernet->local_addr_max, addr_max + 1);
-	}
-
-	pernet->addrs++;
-	if (!entry->addr.port)
-		list_add_tail_rcu(&entry->list, &pernet->local_addr_list);
-	else
-		list_add_rcu(&entry->list, &pernet->local_addr_list);
-	ret = entry->addr.id;
-
-out:
-	spin_unlock_bh(&pernet->lock);
-
-	/* just replaced an existing entry, free it */
-	if (del_entry) {
-		synchronize_rcu();
-		__mptcp_pm_release_addr_entry(del_entry);
-	}
-	return ret;
-}
-
-static struct lock_class_key mptcp_slock_keys[2];
-static struct lock_class_key mptcp_keys[2];
-
-static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
-					    struct mptcp_pm_addr_entry *entry)
-{
-	bool is_ipv6 = sk->sk_family == AF_INET6;
-	int addrlen = sizeof(struct sockaddr_in);
-	struct sockaddr_storage addr;
-	struct sock *newsk, *ssk;
-	int backlog = 1024;
-	int err;
-
-	err = sock_create_kern(sock_net(sk), entry->addr.family,
-			       SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk);
-	if (err)
-		return err;
-
-	newsk = entry->lsk->sk;
-	if (!newsk)
-		return -EINVAL;
-
-	/* The subflow socket lock is acquired in a nested to the msk one
-	 * in several places, even by the TCP stack, and this msk is a kernel
-	 * socket: lockdep complains. Instead of propagating the _nested
-	 * modifiers in several places, re-init the lock class for the msk
-	 * socket to an mptcp specific one.
-	 */
-	sock_lock_init_class_and_name(newsk,
-				      is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET",
-				      &mptcp_slock_keys[is_ipv6],
-				      is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET",
-				      &mptcp_keys[is_ipv6]);
-
-	lock_sock(newsk);
-	ssk = __mptcp_nmpc_sk(mptcp_sk(newsk));
-	release_sock(newsk);
-	if (IS_ERR(ssk))
-		return PTR_ERR(ssk);
-
-	mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family);
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	if (entry->addr.family == AF_INET6)
-		addrlen = sizeof(struct sockaddr_in6);
-#endif
-	if (ssk->sk_family == AF_INET)
-		err = inet_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
-#if IS_ENABLED(CONFIG_MPTCP_IPV6)
-	else if (ssk->sk_family == AF_INET6)
-		err = inet6_bind_sk(ssk, (struct sockaddr *)&addr, addrlen);
-#endif
-	if (err)
-		return err;
-
-	/* We don't use mptcp_set_state() here because it needs to be called
-	 * under the msk socket lock. For the moment, that will not bring
-	 * anything more than only calling inet_sk_state_store(), because the
-	 * old status is known (TCP_CLOSE).
-	 */
-	inet_sk_state_store(newsk, TCP_LISTEN);
-	lock_sock(ssk);
-	WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true);
-	err = __inet_listen_sk(ssk, backlog);
-	if (!err)
-		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);
-	release_sock(ssk);
-	return err;
-}
-
-int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
-			     struct mptcp_pm_addr_entry *skc)
-{
-	struct mptcp_pm_addr_entry *entry;
-	struct pm_nl_pernet *pernet;
-	int ret;
-
-	pernet = pm_nl_get_pernet_from_msk(msk);
-
-	rcu_read_lock();
-	entry = __lookup_addr(pernet, &skc->addr);
-	ret = entry ? entry->addr.id : -1;
-	rcu_read_unlock();
-	if (ret >= 0)
-		return ret;
-
-	/* address not found, add to local list */
-	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
-	if (!entry)
-		return -ENOMEM;
-
-	*entry = *skc;
-	entry->addr.port = 0;
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
-	if (ret < 0)
-		kfree(entry);
-
-	return ret;
-}
-
-bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
-	struct mptcp_pm_addr_entry *entry;
-	bool backup;
-
-	rcu_read_lock();
-	entry = __lookup_addr(pernet, skc);
-	backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
-	rcu_read_unlock();
-
-	return backup;
-}
-
 #define MPTCP_PM_CMD_GRP_OFFSET       0
 #define MPTCP_PM_EV_GRP_OFFSET        1
 
@@ -886,381 +127,6 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
 	return 0;
 }
 
-static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
-{
-	return pm_nl_get_pernet(genl_info_net(info));
-}
-
-static int mptcp_nl_add_subflow_or_signal_addr(struct net *net,
-					       struct mptcp_addr_info *addr)
-{
-	struct mptcp_sock *msk;
-	long s_slot = 0, s_num = 0;
-
-	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
-		struct sock *sk = (struct sock *)msk;
-		struct mptcp_addr_info mpc_addr;
-
-		if (!READ_ONCE(msk->fully_established) ||
-		    mptcp_pm_is_userspace(msk))
-			goto next;
-
-		/* if the endp linked to the init sf is re-added with a != ID */
-		mptcp_local_address((struct sock_common *)msk, &mpc_addr);
-
-		lock_sock(sk);
-		spin_lock_bh(&msk->pm.lock);
-		if (mptcp_addresses_equal(addr, &mpc_addr, addr->port))
-			msk->mpc_endpoint_id = addr->id;
-		mptcp_pm_create_subflow_or_signal_addr(msk);
-		spin_unlock_bh(&msk->pm.lock);
-		release_sock(sk);
-
-next:
-		sock_put(sk);
-		cond_resched();
-	}
-
-	return 0;
-}
-
-static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr,
-				      struct genl_info *info)
-{
-	struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1];
-
-	if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr,
-					 mptcp_pm_address_nl_policy, info->extack) &&
-	    tb[MPTCP_PM_ADDR_ATTR_ID])
-		return true;
-	return false;
-}
-
-int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct mptcp_pm_addr_entry addr, *entry;
-	struct nlattr *attr;
-	int ret;
-
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
-		return -EINVAL;
-
-	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, true, &addr);
-	if (ret < 0)
-		return ret;
-
-	if (addr.addr.port && !address_use_port(&addr)) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr,
-				    "flags must have signal and not subflow when using port");
-		return -EINVAL;
-	}
-
-	if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL &&
-	    addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr,
-				    "flags mustn't have both signal and fullmesh");
-		return -EINVAL;
-	}
-
-	if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr,
-				    "can't create IMPLICIT endpoint");
-		return -EINVAL;
-	}
-
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
-	if (!entry) {
-		GENL_SET_ERR_MSG(info, "can't allocate addr");
-		return -ENOMEM;
-	}
-
-	*entry = addr;
-	if (entry->addr.port) {
-		ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry);
-		if (ret) {
-			GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret);
-			goto out_free;
-		}
-	}
-	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry,
-						!mptcp_pm_has_addr_attr_id(attr, info),
-						true);
-	if (ret < 0) {
-		GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret);
-		goto out_free;
-	}
-
-	mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr);
-	return 0;
-
-out_free:
-	__mptcp_pm_release_addr_entry(entry);
-	return ret;
-}
-
-static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
-				  const struct mptcp_addr_info *addr)
-{
-	return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
-}
-
-static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
-				      const struct mptcp_addr_info *addr,
-				      bool force)
-{
-	struct mptcp_rm_list list = { .nr = 0 };
-	bool ret;
-
-	list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
-
-	ret = mptcp_remove_anno_list_by_saddr(msk, addr);
-	if (ret || force) {
-		spin_lock_bh(&msk->pm.lock);
-		if (ret) {
-			__set_bit(addr->id, msk->pm.id_avail_bitmap);
-			msk->pm.add_addr_signaled--;
-		}
-		mptcp_pm_remove_addr(msk, &list);
-		spin_unlock_bh(&msk->pm.lock);
-	}
-	return ret;
-}
-
-static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
-{
-	/* If it was marked as used, and not ID 0, decrement local_addr_used */
-	if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
-	    id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
-		msk->pm.local_addr_used--;
-}
-
-static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
-						   const struct mptcp_pm_addr_entry *entry)
-{
-	const struct mptcp_addr_info *addr = &entry->addr;
-	struct mptcp_rm_list list = { .nr = 1 };
-	long s_slot = 0, s_num = 0;
-	struct mptcp_sock *msk;
-
-	pr_debug("remove_id=%d\n", addr->id);
-
-	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
-		struct sock *sk = (struct sock *)msk;
-		bool remove_subflow;
-
-		if (mptcp_pm_is_userspace(msk))
-			goto next;
-
-		lock_sock(sk);
-		remove_subflow = mptcp_lookup_subflow_by_saddr(&msk->conn_list, addr);
-		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
-					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
-
-		list.ids[0] = mptcp_endp_get_local_id(msk, addr);
-		if (remove_subflow) {
-			spin_lock_bh(&msk->pm.lock);
-			mptcp_pm_rm_subflow(msk, &list);
-			spin_unlock_bh(&msk->pm.lock);
-		}
-
-		if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
-			spin_lock_bh(&msk->pm.lock);
-			__mark_subflow_endp_available(msk, list.ids[0]);
-			spin_unlock_bh(&msk->pm.lock);
-		}
-
-		if (msk->mpc_endpoint_id == entry->addr.id)
-			msk->mpc_endpoint_id = 0;
-		release_sock(sk);
-
-next:
-		sock_put(sk);
-		cond_resched();
-	}
-
-	return 0;
-}
-
-static int mptcp_nl_remove_id_zero_address(struct net *net,
-					   struct mptcp_addr_info *addr)
-{
-	struct mptcp_rm_list list = { .nr = 0 };
-	long s_slot = 0, s_num = 0;
-	struct mptcp_sock *msk;
-
-	list.ids[list.nr++] = 0;
-
-	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
-		struct sock *sk = (struct sock *)msk;
-		struct mptcp_addr_info msk_local;
-
-		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
-			goto next;
-
-		mptcp_local_address((struct sock_common *)msk, &msk_local);
-		if (!mptcp_addresses_equal(&msk_local, addr, addr->port))
-			goto next;
-
-		lock_sock(sk);
-		spin_lock_bh(&msk->pm.lock);
-		mptcp_pm_remove_addr(msk, &list);
-		mptcp_pm_rm_subflow(msk, &list);
-		__mark_subflow_endp_available(msk, 0);
-		spin_unlock_bh(&msk->pm.lock);
-		release_sock(sk);
-
-next:
-		sock_put(sk);
-		cond_resched();
-	}
-
-	return 0;
-}
-
-int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct mptcp_pm_addr_entry addr, *entry;
-	unsigned int addr_max;
-	struct nlattr *attr;
-	int ret;
-
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
-		return -EINVAL;
-
-	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
-	if (ret < 0)
-		return ret;
-
-	/* the zero id address is special: the first address used by the msk
-	 * always gets such an id, so different subflows can have different zero
-	 * id addresses. Additionally zero id is not accounted for in id_bitmap.
-	 * Let's use an 'mptcp_rm_list' instead of the common remove code.
-	 */
-	if (addr.addr.id == 0)
-		return mptcp_nl_remove_id_zero_address(sock_net(skb->sk), &addr.addr);
-
-	spin_lock_bh(&pernet->lock);
-	entry = __lookup_addr_by_id(pernet, addr.addr.id);
-	if (!entry) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
-		spin_unlock_bh(&pernet->lock);
-		return -EINVAL;
-	}
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) {
-		addr_max = pernet->add_addr_signal_max;
-		WRITE_ONCE(pernet->add_addr_signal_max, addr_max - 1);
-	}
-	if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
-		addr_max = pernet->local_addr_max;
-		WRITE_ONCE(pernet->local_addr_max, addr_max - 1);
-	}
-
-	pernet->addrs--;
-	list_del_rcu(&entry->list);
-	__clear_bit(entry->addr.id, pernet->id_bitmap);
-	spin_unlock_bh(&pernet->lock);
-
-	mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry);
-	synchronize_rcu();
-	__mptcp_pm_release_addr_entry(entry);
-
-	return ret;
-}
-
-static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk,
-					      struct list_head *rm_list)
-{
-	struct mptcp_rm_list alist = { .nr = 0 }, slist = { .nr = 0 };
-	struct mptcp_pm_addr_entry *entry;
-
-	list_for_each_entry(entry, rm_list, list) {
-		if (slist.nr < MPTCP_RM_IDS_MAX &&
-		    mptcp_lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
-			slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
-
-		if (alist.nr < MPTCP_RM_IDS_MAX &&
-		    mptcp_remove_anno_list_by_saddr(msk, &entry->addr))
-			alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
-	}
-
-	spin_lock_bh(&msk->pm.lock);
-	if (alist.nr) {
-		msk->pm.add_addr_signaled -= alist.nr;
-		mptcp_pm_remove_addr(msk, &alist);
-	}
-	if (slist.nr)
-		mptcp_pm_rm_subflow(msk, &slist);
-	/* Reset counters: maybe some subflows have been removed before */
-	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	msk->pm.local_addr_used = 0;
-	spin_unlock_bh(&msk->pm.lock);
-}
-
-static void mptcp_nl_flush_addrs_list(struct net *net,
-				      struct list_head *rm_list)
-{
-	long s_slot = 0, s_num = 0;
-	struct mptcp_sock *msk;
-
-	if (list_empty(rm_list))
-		return;
-
-	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
-		struct sock *sk = (struct sock *)msk;
-
-		if (!mptcp_pm_is_userspace(msk)) {
-			lock_sock(sk);
-			mptcp_pm_flush_addrs_and_subflows(msk, rm_list);
-			release_sock(sk);
-		}
-
-		sock_put(sk);
-		cond_resched();
-	}
-}
-
-/* caller must ensure the RCU grace period is already elapsed */
-static void __flush_addrs(struct list_head *list)
-{
-	while (!list_empty(list)) {
-		struct mptcp_pm_addr_entry *cur;
-
-		cur = list_entry(list->next,
-				 struct mptcp_pm_addr_entry, list);
-		list_del_rcu(&cur->list);
-		__mptcp_pm_release_addr_entry(cur);
-	}
-}
-
-static void __reset_counters(struct pm_nl_pernet *pernet)
-{
-	WRITE_ONCE(pernet->add_addr_signal_max, 0);
-	WRITE_ONCE(pernet->add_addr_accept_max, 0);
-	WRITE_ONCE(pernet->local_addr_max, 0);
-	pernet->addrs = 0;
-}
-
-int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	LIST_HEAD(free_list);
-
-	spin_lock_bh(&pernet->lock);
-	list_splice_init(&pernet->local_addr_list, &free_list);
-	__reset_counters(pernet);
-	pernet->next_id = 1;
-	bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	spin_unlock_bh(&pernet->lock);
-	mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list);
-	synchronize_rcu();
-	__flush_addrs(&free_list);
-	return 0;
-}
-
 int mptcp_nl_fill_addr(struct sk_buff *skb,
 		       struct mptcp_pm_addr_entry *entry)
 {
@@ -1300,226 +166,6 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
-int mptcp_pm_nl_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
-			 struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct mptcp_pm_addr_entry *entry;
-	int ret = -EINVAL;
-
-	rcu_read_lock();
-	entry = __lookup_addr_by_id(pernet, id);
-	if (entry) {
-		*addr = *entry;
-		ret = 0;
-	}
-	rcu_read_unlock();
-
-	return ret;
-}
-
-int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
-			  struct netlink_callback *cb)
-{
-	struct net *net = sock_net(msg->sk);
-	struct mptcp_pm_addr_entry *entry;
-	struct pm_nl_pernet *pernet;
-	int id = cb->args[0];
-	int i;
-
-	pernet = pm_nl_get_pernet(net);
-
-	rcu_read_lock();
-	for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) {
-		if (test_bit(i, pernet->id_bitmap)) {
-			entry = __lookup_addr_by_id(pernet, i);
-			if (!entry)
-				break;
-
-			if (entry->addr.id <= id)
-				continue;
-
-			if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0)
-				break;
-
-			id = entry->addr.id;
-		}
-	}
-	rcu_read_unlock();
-
-	cb->args[0] = id;
-	return msg->len;
-}
-
-static int parse_limit(struct genl_info *info, int id, unsigned int *limit)
-{
-	struct nlattr *attr = info->attrs[id];
-
-	if (!attr)
-		return 0;
-
-	*limit = nla_get_u32(attr);
-	if (*limit > MPTCP_PM_ADDR_MAX) {
-		NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr,
-					"limit greater than maximum (%u)",
-					MPTCP_PM_ADDR_MAX);
-		return -EINVAL;
-	}
-	return 0;
-}
-
-int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	unsigned int rcv_addrs, subflows;
-	int ret;
-
-	spin_lock_bh(&pernet->lock);
-	rcv_addrs = pernet->add_addr_accept_max;
-	ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs);
-	if (ret)
-		goto unlock;
-
-	subflows = pernet->subflows_max;
-	ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows);
-	if (ret)
-		goto unlock;
-
-	WRITE_ONCE(pernet->add_addr_accept_max, rcv_addrs);
-	WRITE_ONCE(pernet->subflows_max, subflows);
-
-unlock:
-	spin_unlock_bh(&pernet->lock);
-	return ret;
-}
-
-int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct pm_nl_pernet *pernet = genl_info_pm_nl(info);
-	struct sk_buff *msg;
-	void *reply;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
-				  MPTCP_PM_CMD_GET_LIMITS);
-	if (!reply)
-		goto fail;
-
-	if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS,
-			READ_ONCE(pernet->add_addr_accept_max)))
-		goto fail;
-
-	if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS,
-			READ_ONCE(pernet->subflows_max)))
-		goto fail;
-
-	genlmsg_end(msg, reply);
-	return genlmsg_reply(msg, info);
-
-fail:
-	GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
-	nlmsg_free(msg);
-	return -EMSGSIZE;
-}
-
-static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
-				 struct mptcp_addr_info *addr)
-{
-	struct mptcp_rm_list list = { .nr = 0 };
-
-	list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
-
-	spin_lock_bh(&msk->pm.lock);
-	mptcp_pm_rm_subflow(msk, &list);
-	__mark_subflow_endp_available(msk, list.ids[0]);
-	mptcp_pm_create_subflow_or_signal_addr(msk);
-	spin_unlock_bh(&msk->pm.lock);
-}
-
-static void mptcp_pm_nl_set_flags_all(struct net *net,
-				      struct mptcp_pm_addr_entry *local,
-				      u8 changed)
-{
-	u8 is_subflow = !!(local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW);
-	u8 bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
-	long s_slot = 0, s_num = 0;
-	struct mptcp_sock *msk;
-
-	if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow)
-		return;
-
-	while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
-		struct sock *sk = (struct sock *)msk;
-
-		if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk))
-			goto next;
-
-		lock_sock(sk);
-		if (changed & MPTCP_PM_ADDR_FLAG_BACKUP)
-			mptcp_pm_mp_prio_send_ack(msk, &local->addr, NULL, bkup);
-		/* Subflows will only be recreated if the SUBFLOW flag is set */
-		if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH))
-			mptcp_pm_nl_fullmesh(msk, &local->addr);
-		release_sock(sk);
-
-next:
-		sock_put(sk);
-		cond_resched();
-	}
-
-	return;
-}
-
-int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local,
-			  struct genl_info *info)
-{
-	struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR];
-	u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP |
-			   MPTCP_PM_ADDR_FLAG_FULLMESH;
-	struct net *net = genl_info_net(info);
-	struct mptcp_pm_addr_entry *entry;
-	struct pm_nl_pernet *pernet;
-	u8 lookup_by_id = 0;
-
-	pernet = pm_nl_get_pernet(net);
-
-	if (local->addr.family == AF_UNSPEC) {
-		lookup_by_id = 1;
-		if (!local->addr.id) {
-			NL_SET_ERR_MSG_ATTR(info->extack, attr,
-					    "missing address ID");
-			return -EOPNOTSUPP;
-		}
-	}
-
-	spin_lock_bh(&pernet->lock);
-	entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) :
-			       __lookup_addr(pernet, &local->addr);
-	if (!entry) {
-		spin_unlock_bh(&pernet->lock);
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
-		return -EINVAL;
-	}
-	if ((local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) &&
-	    (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL |
-			     MPTCP_PM_ADDR_FLAG_IMPLICIT))) {
-		spin_unlock_bh(&pernet->lock);
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "invalid addr flags");
-		return -EINVAL;
-	}
-
-	changed = (local->flags ^ entry->flags) & mask;
-	entry->flags = (entry->flags & ~mask) | (local->flags & mask);
-	*local = *entry;
-	spin_unlock_bh(&pernet->lock);
-
-	mptcp_pm_nl_set_flags_all(net, local, changed);
-	return 0;
-}
-
 static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
 {
 	genlmsg_multicast_netns(&mptcp_genl_family, net,
@@ -1864,53 +510,3 @@ struct genl_family mptcp_genl_family __ro_after_init = {
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
-
-static int __net_init pm_nl_init_net(struct net *net)
-{
-	struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
-
-	INIT_LIST_HEAD_RCU(&pernet->local_addr_list);
-
-	/* Cit. 2 subflows ought to be enough for anybody. */
-	pernet->subflows_max = 2;
-	pernet->next_id = 1;
-	pernet->stale_loss_cnt = 4;
-	spin_lock_init(&pernet->lock);
-
-	/* No need to initialize other pernet fields, the struct is zeroed at
-	 * allocation time.
-	 */
-
-	return 0;
-}
-
-static void __net_exit pm_nl_exit_net(struct list_head *net_list)
-{
-	struct net *net;
-
-	list_for_each_entry(net, net_list, exit_list) {
-		struct pm_nl_pernet *pernet = pm_nl_get_pernet(net);
-
-		/* net is removed from namespace list, can't race with
-		 * other modifiers, also netns core already waited for a
-		 * RCU grace period.
-		 */
-		__flush_addrs(&pernet->local_addr_list);
-	}
-}
-
-static struct pernet_operations mptcp_pm_pernet_ops = {
-	.init = pm_nl_init_net,
-	.exit_batch = pm_nl_exit_net,
-	.id = &pm_nl_pernet_id,
-	.size = sizeof(struct pm_nl_pernet),
-};
-
-void __init mptcp_pm_nl_init(void)
-{
-	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
-		panic("Failed to register MPTCP PM pernet subsystem.\n");
-
-	if (genl_register_family(&mptcp_genl_family))
-		panic("Failed to register MPTCP PM netlink family\n");
-}

From 2e7e6e9cda1e330569bc0824e07abf53addc376f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 7 Mar 2025 12:21:59 +0100
Subject: [PATCH 1934/2753] mptcp: pm: move Netlink PM helpers to pm_netlink.c

Before this patch, the PM code was dispersed in different places:

- pm.c had common code for all PMs, but also Netlink specific code that
  will not be needed with the future BPF path-managers.

- pm_netlink.c had common Netlink code.

To clarify the code, a reorganisation is suggested here, only by moving
code around, and small helper renaming to avoid confusions:

- pm_netlink.c now only contains common PM Netlink code:
  - PM events: this code was already there
  - shared helpers around Netlink code that were already there as well
  - shared Netlink commands code from pm.c

- pm.c now no longer contain Netlink specific code.

- protocol.h has been updated accordingly:
  - mptcp_nl_fill_addr() no longer need to be exported.

The code around the PM is now less confusing, which should help for the
maintenance in the long term.

This will certainly impact future backports, but because other cleanups
have already done recently, and more are coming to ease the addition of
a new path-manager controlled with BPF (struct_ops), doing that now
seems to be a good time. Also, many issues around the PM have been fixed
a few months ago while increasing the code coverage in the selftests, so
such big reorganisation can be done with more confidence now.

No behavioural changes intended.

Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250307-net-next-mptcp-pm-reorg-v1-15-abef20ada03b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 119 -----------------------------------------
 net/mptcp/pm_netlink.c | 119 ++++++++++++++++++++++++++++++++++++++++-
 net/mptcp/protocol.h   |   2 -
 3 files changed, 117 insertions(+), 123 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index d02a0b3adfc43..833839d7286e7 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -5,12 +5,8 @@
  */
 #define pr_fmt(fmt) "MPTCP: " fmt
 
-#include <linux/kernel.h>
-#include <net/mptcp.h>
 #include "protocol.h"
-
 #include "mib.h"
-#include "mptcp_pm_gen.h"
 
 #define ADD_ADDR_RETRANS_MAX	3
 
@@ -888,121 +884,6 @@ bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
 	return mptcp_pm_nl_is_backup(msk, &skc_local);
 }
 
-static int mptcp_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
-			     struct genl_info *info)
-{
-	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_get_addr(id, addr, info);
-	return mptcp_pm_nl_get_addr(id, addr, info);
-}
-
-int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct mptcp_pm_addr_entry addr;
-	struct nlattr *attr;
-	struct sk_buff *msg;
-	void *reply;
-	int ret;
-
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
-		return -EINVAL;
-
-	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
-	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
-	if (ret < 0)
-		return ret;
-
-	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
-	if (!msg)
-		return -ENOMEM;
-
-	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
-				  info->genlhdr->cmd);
-	if (!reply) {
-		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
-		ret = -EMSGSIZE;
-		goto fail;
-	}
-
-	ret = mptcp_pm_get_addr(addr.addr.id, &addr, info);
-	if (ret) {
-		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
-		goto fail;
-	}
-
-	ret = mptcp_nl_fill_addr(msg, &addr);
-	if (ret)
-		goto fail;
-
-	genlmsg_end(msg, reply);
-	ret = genlmsg_reply(msg, info);
-	return ret;
-
-fail:
-	nlmsg_free(msg);
-	return ret;
-}
-
-int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
-			    struct netlink_callback *cb,
-			    struct mptcp_pm_addr_entry *entry)
-{
-	void *hdr;
-
-	hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
-			  cb->nlh->nlmsg_seq, &mptcp_genl_family,
-			  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
-	if (!hdr)
-		return -EINVAL;
-
-	if (mptcp_nl_fill_addr(msg, entry) < 0) {
-		genlmsg_cancel(msg, hdr);
-		return -EINVAL;
-	}
-
-	genlmsg_end(msg, hdr);
-	return 0;
-}
-
-static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
-{
-	const struct genl_info *info = genl_info_dump(cb);
-
-	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_dump_addr(msg, cb);
-	return mptcp_pm_nl_dump_addr(msg, cb);
-}
-
-int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
-				struct netlink_callback *cb)
-{
-	return mptcp_pm_dump_addr(msg, cb);
-}
-
-static int mptcp_pm_set_flags(struct genl_info *info)
-{
-	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
-	struct nlattr *attr_loc;
-	int ret = -EINVAL;
-
-	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
-		return ret;
-
-	attr_loc = info->attrs[MPTCP_PM_ATTR_ADDR];
-	ret = mptcp_pm_parse_entry(attr_loc, info, false, &loc);
-	if (ret < 0)
-		return ret;
-
-	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
-		return mptcp_userspace_pm_set_flags(&loc, info);
-	return mptcp_pm_nl_set_flags(&loc, info);
-}
-
-int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	return mptcp_pm_set_flags(info);
-}
-
 static void mptcp_pm_subflows_chk_stale(const struct mptcp_sock *msk, struct sock *ssk)
 {
 	struct mptcp_subflow_context *iter, *subflow = mptcp_subflow_ctx(ssk);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 530b2362a5a35..b2e5bbdcd5df9 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -127,8 +127,8 @@ int mptcp_pm_parse_entry(struct nlattr *attr, struct genl_info *info,
 	return 0;
 }
 
-int mptcp_nl_fill_addr(struct sk_buff *skb,
-		       struct mptcp_pm_addr_entry *entry)
+static int mptcp_nl_fill_addr(struct sk_buff *skb,
+			      struct mptcp_pm_addr_entry *entry)
 {
 	struct mptcp_addr_info *addr = &entry->addr;
 	struct nlattr *attr;
@@ -166,6 +166,121 @@ int mptcp_nl_fill_addr(struct sk_buff *skb,
 	return -EMSGSIZE;
 }
 
+static int mptcp_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
+			     struct genl_info *info)
+{
+	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+		return mptcp_userspace_pm_get_addr(id, addr, info);
+	return mptcp_pm_nl_get_addr(id, addr, info);
+}
+
+int mptcp_pm_nl_get_addr_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct mptcp_pm_addr_entry addr;
+	struct nlattr *attr;
+	struct sk_buff *msg;
+	void *reply;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR))
+		return -EINVAL;
+
+	attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR];
+	ret = mptcp_pm_parse_entry(attr, info, false, &addr);
+	if (ret < 0)
+		return ret;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0,
+				  info->genlhdr->cmd);
+	if (!reply) {
+		GENL_SET_ERR_MSG(info, "not enough space in Netlink message");
+		ret = -EMSGSIZE;
+		goto fail;
+	}
+
+	ret = mptcp_pm_get_addr(addr.addr.id, &addr, info);
+	if (ret) {
+		NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found");
+		goto fail;
+	}
+
+	ret = mptcp_nl_fill_addr(msg, &addr);
+	if (ret)
+		goto fail;
+
+	genlmsg_end(msg, reply);
+	ret = genlmsg_reply(msg, info);
+	return ret;
+
+fail:
+	nlmsg_free(msg);
+	return ret;
+}
+
+int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
+			    struct netlink_callback *cb,
+			    struct mptcp_pm_addr_entry *entry)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid,
+			  cb->nlh->nlmsg_seq, &mptcp_genl_family,
+			  NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR);
+	if (!hdr)
+		return -EINVAL;
+
+	if (mptcp_nl_fill_addr(msg, entry) < 0) {
+		genlmsg_cancel(msg, hdr);
+		return -EINVAL;
+	}
+
+	genlmsg_end(msg, hdr);
+	return 0;
+}
+
+static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb)
+{
+	const struct genl_info *info = genl_info_dump(cb);
+
+	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+		return mptcp_userspace_pm_dump_addr(msg, cb);
+	return mptcp_pm_nl_dump_addr(msg, cb);
+}
+
+int mptcp_pm_nl_get_addr_dumpit(struct sk_buff *msg,
+				struct netlink_callback *cb)
+{
+	return mptcp_pm_dump_addr(msg, cb);
+}
+
+static int mptcp_pm_set_flags(struct genl_info *info)
+{
+	struct mptcp_pm_addr_entry loc = { .addr = { .family = AF_UNSPEC }, };
+	struct nlattr *attr_loc;
+	int ret = -EINVAL;
+
+	if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ATTR_ADDR))
+		return ret;
+
+	attr_loc = info->attrs[MPTCP_PM_ATTR_ADDR];
+	ret = mptcp_pm_parse_entry(attr_loc, info, false, &loc);
+	if (ret < 0)
+		return ret;
+
+	if (info->attrs[MPTCP_PM_ATTR_TOKEN])
+		return mptcp_userspace_pm_set_flags(&loc, info);
+	return mptcp_pm_nl_set_flags(&loc, info);
+}
+
+int mptcp_pm_nl_set_flags_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return mptcp_pm_set_flags(info);
+}
+
 static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp)
 {
 	genlmsg_multicast_netns(&mptcp_genl_family, net,
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 360d8cfa52797..c51b6a22d5e09 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1057,8 +1057,6 @@ bool mptcp_userspace_pm_active(const struct mptcp_sock *msk);
 
 void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subflow,
 					      struct request_sock *req);
-int mptcp_nl_fill_addr(struct sk_buff *skb,
-		       struct mptcp_pm_addr_entry *entry);
 int mptcp_pm_genl_fill_addr(struct sk_buff *msg,
 			    struct netlink_callback *cb,
 			    struct mptcp_pm_addr_entry *entry);

From 025cf9318083d1d7c798846620be4559e03734f0 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:37 -0500
Subject: [PATCH 1935/2753] enic: Move function from header file to c file

Moves cq_enet_rq_desc_dec from cq_enet_desc.h to enic_rq.c.
This is in preparation for enic extended completion queue
enabling.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-1-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/cisco/enic/cq_enet_desc.h    | 81 ------------------
 drivers/net/ethernet/cisco/enic/enic_rq.c     | 84 +++++++++++++++++++
 2 files changed, 84 insertions(+), 81 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
index d25426470a293..6abc134d07032 100644
--- a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
@@ -88,85 +88,4 @@ struct cq_enet_rq_desc {
 #define CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT         (0x1 << 6)
 #define CQ_ENET_RQ_DESC_FLAGS_FCS_OK                (0x1 << 7)
 
-static inline void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index,
-	u8 *ingress_port, u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
-	u8 *csum_not_calc, u32 *rss_hash, u16 *bytes_written, u8 *packet_error,
-	u8 *vlan_stripped, u16 *vlan_tci, u16 *checksum, u8 *fcoe_sof,
-	u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error, u8 *fcoe_eof,
-	u8 *tcp_udp_csum_ok, u8 *udp, u8 *tcp, u8 *ipv4_csum_ok,
-	u8 *ipv6, u8 *ipv4, u8 *ipv4_fragment, u8 *fcs_ok)
-{
-	u16 completed_index_flags;
-	u16 q_number_rss_type_flags;
-	u16 bytes_written_flags;
-
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-
-	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
-	q_number_rss_type_flags =
-		le16_to_cpu(desc->q_number_rss_type_flags);
-	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
-
-	*ingress_port = (completed_index_flags &
-		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
-	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
-		1 : 0;
-	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
-		1 : 0;
-	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
-		1 : 0;
-
-	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
-		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
-	*csum_not_calc = (q_number_rss_type_flags &
-		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
-
-	*rss_hash = le32_to_cpu(desc->rss_hash);
-
-	*bytes_written = bytes_written_flags &
-		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
-	*packet_error = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
-	*vlan_stripped = (bytes_written_flags &
-		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
-
-	/*
-	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
-	 */
-	*vlan_tci = le16_to_cpu(desc->vlan);
-
-	if (*fcoe) {
-		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
-			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
-		*fcoe_fc_crc_ok = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
-		*fcoe_enc_error = (desc->flags &
-			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
-		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
-			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
-			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
-		*checksum = 0;
-	} else {
-		*fcoe_sof = 0;
-		*fcoe_fc_crc_ok = 0;
-		*fcoe_enc_error = 0;
-		*fcoe_eof = 0;
-		*checksum = le16_to_cpu(desc->checksum_fcoe);
-	}
-
-	*tcp_udp_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
-	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
-	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
-	*ipv4_csum_ok =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
-	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
-	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
-	*ipv4_fragment =
-		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
-	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
-}
-
 #endif /* _CQ_ENET_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
index e3228ef7988a1..7360799326e8b 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -101,6 +101,90 @@ static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
 	}
 }
 
+static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *type,
+				u8 *color, u16 *q_number, u16 *completed_index,
+				u8 *ingress_port, u8 *fcoe, u8 *eop, u8 *sop,
+				u8 *rss_type, u8 *csum_not_calc, u32 *rss_hash,
+				u16 *bytes_written, u8 *packet_error,
+				u8 *vlan_stripped, u16 *vlan_tci,
+				u16 *checksum, u8 *fcoe_sof,
+				u8 *fcoe_fc_crc_ok, u8 *fcoe_enc_error,
+				u8 *fcoe_eof, u8 *tcp_udp_csum_ok, u8 *udp,
+				u8 *tcp, u8 *ipv4_csum_ok, u8 *ipv6, u8 *ipv4,
+				u8 *ipv4_fragment, u8 *fcs_ok)
+{
+	u16 completed_index_flags;
+	u16 q_number_rss_type_flags;
+	u16 bytes_written_flags;
+
+	cq_desc_dec((struct cq_desc *)desc, type,
+		    color, q_number, completed_index);
+
+	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
+	q_number_rss_type_flags =
+		le16_to_cpu(desc->q_number_rss_type_flags);
+	bytes_written_flags = le16_to_cpu(desc->bytes_written_flags);
+
+	*ingress_port = (completed_index_flags &
+		CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT) ? 1 : 0;
+	*fcoe = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_FCOE) ?
+		1 : 0;
+	*eop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_EOP) ?
+		1 : 0;
+	*sop = (completed_index_flags & CQ_ENET_RQ_DESC_FLAGS_SOP) ?
+		1 : 0;
+
+	*rss_type = (u8)((q_number_rss_type_flags >> CQ_DESC_Q_NUM_BITS) &
+		CQ_ENET_RQ_DESC_RSS_TYPE_MASK);
+	*csum_not_calc = (q_number_rss_type_flags &
+		CQ_ENET_RQ_DESC_FLAGS_CSUM_NOT_CALC) ? 1 : 0;
+
+	*rss_hash = le32_to_cpu(desc->rss_hash);
+
+	*bytes_written = bytes_written_flags &
+		CQ_ENET_RQ_DESC_BYTES_WRITTEN_MASK;
+	*packet_error = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_TRUNCATED) ? 1 : 0;
+	*vlan_stripped = (bytes_written_flags &
+		CQ_ENET_RQ_DESC_FLAGS_VLAN_STRIPPED) ? 1 : 0;
+
+	/*
+	 * Tag Control Information(16) = user_priority(3) + cfi(1) + vlan(12)
+	 */
+	*vlan_tci = le16_to_cpu(desc->vlan);
+
+	if (*fcoe) {
+		*fcoe_sof = (u8)(le16_to_cpu(desc->checksum_fcoe) &
+			CQ_ENET_RQ_DESC_FCOE_SOF_MASK);
+		*fcoe_fc_crc_ok = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_FC_CRC_OK) ? 1 : 0;
+		*fcoe_enc_error = (desc->flags &
+			CQ_ENET_RQ_DESC_FCOE_ENC_ERROR) ? 1 : 0;
+		*fcoe_eof = (u8)((le16_to_cpu(desc->checksum_fcoe) >>
+			CQ_ENET_RQ_DESC_FCOE_EOF_SHIFT) &
+			CQ_ENET_RQ_DESC_FCOE_EOF_MASK);
+		*checksum = 0;
+	} else {
+		*fcoe_sof = 0;
+		*fcoe_fc_crc_ok = 0;
+		*fcoe_enc_error = 0;
+		*fcoe_eof = 0;
+		*checksum = le16_to_cpu(desc->checksum_fcoe);
+	}
+
+	*tcp_udp_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP_UDP_CSUM_OK) ? 1 : 0;
+	*udp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_UDP) ? 1 : 0;
+	*tcp = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_TCP) ? 1 : 0;
+	*ipv4_csum_ok =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_CSUM_OK) ? 1 : 0;
+	*ipv6 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV6) ? 1 : 0;
+	*ipv4 = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4) ? 1 : 0;
+	*ipv4_fragment =
+		(desc->flags & CQ_ENET_RQ_DESC_FLAGS_IPV4_FRAGMENT) ? 1 : 0;
+	*fcs_ok = (desc->flags & CQ_ENET_RQ_DESC_FLAGS_FCS_OK) ? 1 : 0;
+}
+
 static bool enic_rq_pkt_error(struct vnic_rq *vrq, u8 packet_error, u8 fcs_ok,
 			      u16 bytes_written)
 {

From eaa23db8686f119a5cadb0e47cfbdea347a6d239 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:38 -0500
Subject: [PATCH 1936/2753] enic: enic rq code reorg

Separates enic rx path from generic vnic api. Removes some
complexity of doign enic callbacks through vnic api in rx.
This is in preparation for enabling enic extended cq which
applies only to enic rx path.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-2-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/enic_main.c |   6 +-
 drivers/net/ethernet/cisco/enic/enic_rq.c   | 119 +++++++++++++++-----
 drivers/net/ethernet/cisco/enic/enic_rq.h   |   6 +-
 drivers/net/ethernet/cisco/enic/vnic_cq.h   |  14 +++
 4 files changed, 106 insertions(+), 39 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index f24fd29ea2071..080234ef4c2bb 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1386,8 +1386,7 @@ static int enic_poll(struct napi_struct *napi, int budget)
 				       enic_wq_service, NULL);
 
 	if (budget > 0)
-		rq_work_done = vnic_cq_service(&enic->cq[cq_rq],
-			rq_work_to_do, enic_rq_service, NULL);
+		rq_work_done = enic_rq_cq_service(enic, cq_rq, rq_work_to_do);
 
 	/* Accumulate intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
@@ -1516,8 +1515,7 @@ static int enic_poll_msix_rq(struct napi_struct *napi, int budget)
 	 */
 
 	if (budget > 0)
-		work_done = vnic_cq_service(&enic->cq[cq],
-			work_to_do, enic_rq_service, NULL);
+		work_done = enic_rq_cq_service(enic, cq, work_to_do);
 
 	/* Return intr event credits for this polling
 	 * cycle.  An intr event is the completion of a
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
index 7360799326e8b..842b273c2e2a5 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -21,14 +21,26 @@ static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
 		pkt_size->small_pkt_bytes_cnt += pkt_len;
 }
 
-int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
-		    u16 q_number, u16 completed_index, void *opaque)
+static void enic_rq_cq_desc_dec(struct cq_enet_rq_desc *desc, u8 *type,
+				u8 *color, u16 *q_number, u16 *completed_index)
 {
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	vnic_rq_service(&enic->rq[q_number].vrq, cq_desc, completed_index,
-			VNIC_RQ_RETURN_DESC, enic_rq_indicate_buf, opaque);
-	return 0;
+	/* type_color is the last field for all cq structs */
+	u8 type_color = desc->type_color;
+
+	/* Make sure color bit is read from desc *before* other fields
+	 * are read from desc.  Hardware guarantees color bit is last
+	 * bit (byte) written.  Adding the rmb() prevents the compiler
+	 * and/or CPU from reordering the reads which would potentially
+	 * result in reading stale values.
+	 */
+	rmb();
+
+	*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+		CQ_DESC_Q_NUM_MASK;
+	*completed_index = le16_to_cpu(desc->completed_index_flags) &
+	CQ_DESC_COMP_NDX_MASK;
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+	*type = type_color & CQ_DESC_TYPE_MASK;
 }
 
 static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
@@ -101,10 +113,9 @@ static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
 	}
 }
 
-static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *type,
-				u8 *color, u16 *q_number, u16 *completed_index,
-				u8 *ingress_port, u8 *fcoe, u8 *eop, u8 *sop,
-				u8 *rss_type, u8 *csum_not_calc, u32 *rss_hash,
+static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *ingress_port,
+				u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
+				u8 *csum_not_calc, u32 *rss_hash,
 				u16 *bytes_written, u8 *packet_error,
 				u8 *vlan_stripped, u16 *vlan_tci,
 				u16 *checksum, u8 *fcoe_sof,
@@ -117,9 +128,6 @@ static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *type,
 	u16 q_number_rss_type_flags;
 	u16 bytes_written_flags;
 
-	cq_desc_dec((struct cq_desc *)desc, type,
-		    color, q_number, completed_index);
-
 	completed_index_flags = le16_to_cpu(desc->completed_index_flags);
 	q_number_rss_type_flags =
 		le16_to_cpu(desc->q_number_rss_type_flags);
@@ -249,37 +257,33 @@ void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
 	buf->os_buf = NULL;
 }
 
-void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
-			  struct vnic_rq_buf *buf, int skipped, void *opaque)
+static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
+				 struct vnic_rq_buf *buf,
+				 struct cq_enet_rq_desc *cq_desc, u8 type,
+				 u16 q_number, u16 completed_index)
 {
-	struct enic *enic = vnic_dev_priv(rq->vdev);
 	struct sk_buff *skb;
 	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
 	struct enic_rq_stats *rqstats = &enic->rq[rq->index].stats;
 	struct napi_struct *napi;
 
-	u8 type, color, eop, sop, ingress_port, vlan_stripped;
+	u8 eop, sop, ingress_port, vlan_stripped;
 	u8 fcoe, fcoe_sof, fcoe_fc_crc_ok, fcoe_enc_error, fcoe_eof;
 	u8 tcp_udp_csum_ok, udp, tcp, ipv4_csum_ok;
 	u8 ipv6, ipv4, ipv4_fragment, fcs_ok, rss_type, csum_not_calc;
 	u8 packet_error;
-	u16 q_number, completed_index, bytes_written, vlan_tci, checksum;
+	u16 bytes_written, vlan_tci, checksum;
 	u32 rss_hash;
 
 	rqstats->packets++;
-	if (skipped) {
-		rqstats->desc_skip++;
-		return;
-	}
 
-	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &type, &color,
-			    &q_number, &completed_index, &ingress_port, &fcoe,
-			    &eop, &sop, &rss_type, &csum_not_calc, &rss_hash,
-			    &bytes_written, &packet_error, &vlan_stripped,
-			    &vlan_tci, &checksum, &fcoe_sof, &fcoe_fc_crc_ok,
-			    &fcoe_enc_error, &fcoe_eof, &tcp_udp_csum_ok, &udp,
-			    &tcp, &ipv4_csum_ok, &ipv6, &ipv4, &ipv4_fragment,
-			    &fcs_ok);
+	cq_enet_rq_desc_dec(cq_desc, &ingress_port,
+			    &fcoe, &eop, &sop, &rss_type, &csum_not_calc,
+			    &rss_hash, &bytes_written, &packet_error,
+			    &vlan_stripped, &vlan_tci, &checksum, &fcoe_sof,
+			    &fcoe_fc_crc_ok, &fcoe_enc_error, &fcoe_eof,
+			    &tcp_udp_csum_ok, &udp, &tcp, &ipv4_csum_ok, &ipv6,
+			    &ipv4, &ipv4_fragment, &fcs_ok);
 
 	if (enic_rq_pkt_error(rq, packet_error, fcs_ok, bytes_written))
 		return;
@@ -324,3 +328,56 @@ void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
 		rqstats->pkt_truncated++;
 	}
 }
+
+static void enic_rq_service(struct enic *enic, struct cq_enet_rq_desc *cq_desc,
+			    u8 type, u16 q_number, u16 completed_index)
+{
+	struct enic_rq_stats *rqstats = &enic->rq[q_number].stats;
+	struct vnic_rq *vrq = &enic->rq[q_number].vrq;
+	struct vnic_rq_buf *vrq_buf = vrq->to_clean;
+	int skipped;
+
+	while (1) {
+		skipped = (vrq_buf->index != completed_index);
+		if (!skipped)
+			enic_rq_indicate_buf(enic, vrq, vrq_buf, cq_desc, type,
+					     q_number, completed_index);
+		else
+			rqstats->desc_skip++;
+
+		vrq->ring.desc_avail++;
+		vrq->to_clean = vrq_buf->next;
+		vrq_buf = vrq_buf->next;
+		if (!skipped)
+			break;
+	}
+}
+
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	struct cq_enet_rq_desc *cq_desc;
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	u8 type, color;
+
+	cq_desc = (struct cq_enet_rq_desc *)vnic_cq_to_clean(cq);
+
+	enic_rq_cq_desc_dec(cq_desc,  &type, &color, &q_number,
+			    &completed_index);
+
+	while (color != cq->last_color) {
+		enic_rq_service(enic, cq_desc, type, q_number, completed_index);
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = (struct cq_enet_rq_desc *)vnic_cq_to_clean(cq);
+		enic_rq_cq_desc_dec(cq_desc, &type, &color, &q_number,
+				    &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.h b/drivers/net/ethernet/cisco/enic/enic_rq.h
index a75d07562686a..98476a7297afb 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.h
@@ -2,9 +2,7 @@
  * Copyright 2024 Cisco Systems, Inc.  All rights reserved.
  */
 
-int enic_rq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
-		    u16 q_number, u16 completed_index, void *opaque);
-void enic_rq_indicate_buf(struct vnic_rq *rq, struct cq_desc *cq_desc,
-			  struct vnic_rq_buf *buf, int skipped, void *opaque);
+unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);
 int enic_rq_alloc_buf(struct vnic_rq *rq);
 void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.h b/drivers/net/ethernet/cisco/enic/vnic_cq.h
index eed5bf59e5d2c..21d97c01f9424 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_cq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_cq.h
@@ -97,6 +97,20 @@ static inline unsigned int vnic_cq_service(struct vnic_cq *cq,
 	return work_done;
 }
 
+static inline void *vnic_cq_to_clean(struct vnic_cq *cq)
+{
+	return ((u8 *)cq->ring.descs + cq->ring.desc_size * cq->to_clean);
+}
+
+static inline void vnic_cq_inc_to_clean(struct vnic_cq *cq)
+{
+	cq->to_clean++;
+	if (cq->to_clean == cq->ring.desc_count) {
+		cq->to_clean = 0;
+		cq->last_color = cq->last_color ? 0 : 1;
+	}
+}
+
 void vnic_cq_free(struct vnic_cq *cq);
 int vnic_cq_alloc(struct vnic_dev *vdev, struct vnic_cq *cq, unsigned int index,
 	unsigned int desc_count, unsigned int desc_size);

From 2be2eb764343d5211b12b29fa45aaf518e8c3a7e Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:39 -0500
Subject: [PATCH 1937/2753] enic: enic rq extended cq defines

Adds the defines for 32 and 64 byte receive queue completion queue
descriptors.
Adds devcmd define to get rq cq descriptor size/s supported by hw.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-3-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/cisco/enic/cq_enet_desc.h    | 56 +++++++++++++++++++
 drivers/net/ethernet/cisco/enic/vnic_devcmd.h | 19 +++++++
 2 files changed, 75 insertions(+)

diff --git a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
index 6abc134d07032..809a3f30b87f7 100644
--- a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
@@ -24,6 +24,23 @@ static inline void cq_enet_wq_desc_dec(struct cq_enet_wq_desc *desc,
 		color, q_number, completed_index);
 }
 
+/*
+ * Defines and Capabilities for CMD_CQ_ENTRY_SIZE_SET
+ */
+#define VNIC_RQ_ALL (~0ULL)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16 0
+#define VNIC_RQ_CQ_ENTRY_SIZE_32 1
+#define VNIC_RQ_CQ_ENTRY_SIZE_64 2
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_16)
+#define VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_32)
+#define VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE BIT(VNIC_RQ_CQ_ENTRY_SIZE_64)
+
+#define VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT  (VNIC_RQ_CQ_ENTRY_SIZE_16_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_32_CAPABLE | \
+					VNIC_RQ_CQ_ENTRY_SIZE_64_CAPABLE)
+
 /* Completion queue descriptor: Ethernet receive queue, 16B */
 struct cq_enet_rq_desc {
 	__le16 completed_index_flags;
@@ -36,6 +53,45 @@ struct cq_enet_rq_desc {
 	u8 type_color;
 };
 
+/* Completion queue descriptor: Ethernet receive queue, 32B */
+struct cq_enet_rq_desc_32 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 type_color;
+};
+
+/* Completion queue descriptor: Ethernet receive queue, 64B */
+struct cq_enet_rq_desc_64 {
+	__le16 completed_index_flags;
+	__le16 q_number_rss_type_flags;
+	__le32 rss_hash;
+	__le16 bytes_written_flags;
+	__le16 vlan;
+	__le16 checksum_fcoe;
+	u8 flags;
+	u8 fetch_index_flags;
+	__le32 time_stamp;
+	__le16 time_stamp2;
+	__le16 pie_info;
+	__le32 pie_info2;
+	__le16 pie_info3;
+	u8 pie_info4;
+	u8 reserved[32];
+	u8 type_color;
+};
+
 #define CQ_ENET_RQ_DESC_FLAGS_INGRESS_PORT          (0x1 << 12)
 #define CQ_ENET_RQ_DESC_FLAGS_FCOE                  (0x1 << 13)
 #define CQ_ENET_RQ_DESC_FLAGS_EOP                   (0x1 << 14)
diff --git a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
index db56d778877a7..605ef17f967e4 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_devcmd.h
@@ -436,6 +436,25 @@ enum vnic_devcmd_cmd {
 	 * in: (u16) a2 = unsigned short int port information
 	 */
 	CMD_OVERLAY_OFFLOAD_CFG = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 73),
+
+	/*
+	 * Set extended CQ field in MREGS of RQ (or all RQs)
+	 * for given vNIC
+	 * in: (u64) a0 = RQ selection (VNIC_RQ_ALL for all RQs)
+	 *     (u32) a1 = CQ entry size
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_16 --> 16 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_32 --> 32 bytes
+	 *         VNIC_RQ_CQ_ENTRY_SIZE_64 --> 64 bytes
+	 *
+	 * Capability query:
+	 * out: (u32) a0 = errno, 0:valid cmd
+	 *      (u32) a1 = value consisting of supported entries
+	 *         bit 0: 16 bytes
+	 *         bit 1: 32 bytes
+	 *         bit 2: 64 bytes
+	 */
+	CMD_CQ_ENTRY_SIZE_SET = _CMDC(_CMD_DIR_WRITE, _CMD_VTYPE_ENET, 90),
+
 };
 
 /* CMD_ENABLE2 flags */

From bcb725c79cfa770aa1356eb2f26ffcfbae67fb13 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:40 -0500
Subject: [PATCH 1938/2753] enic: enable rq extended cq support

Enables getting from hw all the supported rq cq sizes and
uses the highest supported cq size.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-4-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/cq_desc.h   |   3 +
 drivers/net/ethernet/cisco/enic/enic.h      |   9 ++
 drivers/net/ethernet/cisco/enic/enic_main.c |   4 +
 drivers/net/ethernet/cisco/enic/enic_res.c  |  58 ++++++++++-
 drivers/net/ethernet/cisco/enic/enic_rq.c   | 105 +++++++++++++++-----
 5 files changed, 150 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/cq_desc.h b/drivers/net/ethernet/cisco/enic/cq_desc.h
index 462c5435a206b..8fc313b6ed043 100644
--- a/drivers/net/ethernet/cisco/enic/cq_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_desc.h
@@ -40,6 +40,9 @@ struct cq_desc {
 #define CQ_DESC_COMP_NDX_BITS    12
 #define CQ_DESC_COMP_NDX_MASK    ((1 << CQ_DESC_COMP_NDX_BITS) - 1)
 
+#define CQ_DESC_32_FI_MASK (BIT(0) | BIT(1))
+#define CQ_DESC_64_FI_MASK (BIT(0) | BIT(1))
+
 static inline void cq_desc_dec(const struct cq_desc *desc_arg,
 	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
 {
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 305ed12aa0311..d60e55accafd0 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -31,6 +31,13 @@
 
 #define ENIC_AIC_LARGE_PKT_DIFF	3
 
+enum ext_cq {
+	ENIC_RQ_CQ_ENTRY_SIZE_16,
+	ENIC_RQ_CQ_ENTRY_SIZE_32,
+	ENIC_RQ_CQ_ENTRY_SIZE_64,
+	ENIC_RQ_CQ_ENTRY_SIZE_MAX,
+};
+
 struct enic_msix_entry {
 	int requested;
 	char devname[IFNAMSIZ + 8];
@@ -228,6 +235,7 @@ struct enic {
 	struct enic_rfs_flw_tbl rfs_h;
 	u8 rss_key[ENIC_RSS_LEN];
 	struct vnic_gen_stats gen_stats;
+	enum ext_cq ext_cq;
 };
 
 static inline struct net_device *vnic_get_netdev(struct vnic_dev *vdev)
@@ -349,5 +357,6 @@ int enic_is_valid_vf(struct enic *enic, int vf);
 int enic_is_dynamic(struct enic *enic);
 void enic_set_ethtool_ops(struct net_device *netdev);
 int __enic_set_rsskey(struct enic *enic);
+void enic_ext_cq(struct enic *enic);
 
 #endif /* _ENIC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 080234ef4c2bb..d716514366dfc 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2192,6 +2192,7 @@ static void enic_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2218,6 +2219,7 @@ static void enic_tx_hang_reset(struct work_struct *work)
 	enic_init_vnic_resources(enic);
 	enic_set_rss_nic_cfg(enic);
 	enic_dev_set_ig_vlan_rewrite_mode(enic);
+	enic_ext_cq(enic);
 	enic_open(enic->netdev);
 
 	/* Allow infiniband to fiddle with the device again */
@@ -2592,6 +2594,8 @@ static int enic_dev_init(struct enic *enic)
 
 	enic_get_res_counts(enic);
 
+	enic_ext_cq(enic);
+
 	err = enic_alloc_enic_resources(enic);
 	if (err) {
 		dev_err(dev, "Failed to allocate enic resources\n");
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.c b/drivers/net/ethernet/cisco/enic/enic_res.c
index 1261251998330..a7179cc4b5296 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.c
+++ b/drivers/net/ethernet/cisco/enic/enic_res.c
@@ -312,6 +312,7 @@ void enic_init_vnic_resources(struct enic *enic)
 int enic_alloc_vnic_resources(struct enic *enic)
 {
 	enum vnic_dev_intr_mode intr_mode;
+	int rq_cq_desc_size;
 	unsigned int i;
 	int err;
 
@@ -326,6 +327,24 @@ int enic_alloc_vnic_resources(struct enic *enic)
 		intr_mode == VNIC_DEV_INTR_MODE_MSIX ? "MSI-X" :
 		"unknown");
 
+	switch (enic->ext_cq) {
+	case ENIC_RQ_CQ_ENTRY_SIZE_16:
+		rq_cq_desc_size = 16;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_32:
+		rq_cq_desc_size = 32;
+		break;
+	case ENIC_RQ_CQ_ENTRY_SIZE_64:
+		rq_cq_desc_size = 64;
+		break;
+	default:
+		dev_err(enic_get_dev(enic),
+			"Unable to determine rq cq desc size: %d",
+			enic->ext_cq);
+		err = -ENODEV;
+		goto err_out;
+	}
+
 	/* Allocate queue resources
 	 */
 
@@ -348,8 +367,8 @@ int enic_alloc_vnic_resources(struct enic *enic)
 	for (i = 0; i < enic->cq_count; i++) {
 		if (i < enic->rq_count)
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
-				enic->config.rq_desc_count,
-				sizeof(struct cq_enet_rq_desc));
+					enic->config.rq_desc_count,
+					rq_cq_desc_size);
 		else
 			err = vnic_cq_alloc(enic->vdev, &enic->cq[i], i,
 				enic->config.wq_desc_count,
@@ -380,6 +399,39 @@ int enic_alloc_vnic_resources(struct enic *enic)
 
 err_out_cleanup:
 	enic_free_vnic_resources(enic);
-
+err_out:
 	return err;
 }
+
+/*
+ * CMD_CQ_ENTRY_SIZE_SET can fail on older hw generations that don't support
+ * that command
+ */
+void enic_ext_cq(struct enic *enic)
+{
+	u64 a0 = CMD_CQ_ENTRY_SIZE_SET, a1 = 0;
+	int wait = 1000;
+	int ret;
+
+	spin_lock_bh(&enic->devcmd_lock);
+	ret = vnic_dev_cmd(enic->vdev, CMD_CAPABILITY, &a0, &a1, wait);
+	if (ret || a0) {
+		dev_info(&enic->pdev->dev,
+			 "CMD_CQ_ENTRY_SIZE_SET not supported.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+		goto out;
+	}
+	a1 &= VNIC_RQ_CQ_ENTRY_SIZE_ALL_BIT;
+	enic->ext_cq = fls(a1) - 1;
+	a0 = VNIC_RQ_ALL;
+	a1 = enic->ext_cq;
+	ret = vnic_dev_cmd(enic->vdev, CMD_CQ_ENTRY_SIZE_SET, &a0, &a1, wait);
+	if (ret) {
+		dev_info(&enic->pdev->dev, "CMD_CQ_ENTRY_SIZE_SET failed.");
+		enic->ext_cq = ENIC_RQ_CQ_ENTRY_SIZE_16;
+	}
+out:
+	spin_unlock_bh(&enic->devcmd_lock);
+	dev_info(&enic->pdev->dev, "CQ entry size set to %d bytes",
+		 16 << enic->ext_cq);
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_rq.c b/drivers/net/ethernet/cisco/enic/enic_rq.c
index 842b273c2e2a5..ccbf5c9a21d0f 100644
--- a/drivers/net/ethernet/cisco/enic/enic_rq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_rq.c
@@ -21,24 +21,76 @@ static void enic_intr_update_pkt_size(struct vnic_rx_bytes_counter *pkt_size,
 		pkt_size->small_pkt_bytes_cnt += pkt_len;
 }
 
-static void enic_rq_cq_desc_dec(struct cq_enet_rq_desc *desc, u8 *type,
+static void enic_rq_cq_desc_dec(void *cq_desc, u8 cq_desc_size, u8 *type,
 				u8 *color, u16 *q_number, u16 *completed_index)
 {
 	/* type_color is the last field for all cq structs */
-	u8 type_color = desc->type_color;
+	u8 type_color;
+
+	switch (cq_desc_size) {
+	case VNIC_RQ_CQ_ENTRY_SIZE_16: {
+		struct cq_enet_rq_desc *desc =
+			(struct cq_enet_rq_desc *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
 
-	/* Make sure color bit is read from desc *before* other fields
-	 * are read from desc.  Hardware guarantees color bit is last
-	 * bit (byte) written.  Adding the rmb() prevents the compiler
-	 * and/or CPU from reordering the reads which would potentially
-	 * result in reading stale values.
-	 */
-	rmb();
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_32: {
+		struct cq_enet_rq_desc_32 *desc =
+			(struct cq_enet_rq_desc_32 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_32_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	case VNIC_RQ_CQ_ENTRY_SIZE_64: {
+		struct cq_enet_rq_desc_64 *desc =
+			(struct cq_enet_rq_desc_64 *)cq_desc;
+		type_color = desc->type_color;
+
+		/* Make sure color bit is read from desc *before* other fields
+		 * are read from desc.  Hardware guarantees color bit is last
+		 * bit (byte) written.  Adding the rmb() prevents the compiler
+		 * and/or CPU from reordering the reads which would potentially
+		 * result in reading stale values.
+		 */
+		rmb();
+
+		*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
+			    CQ_DESC_Q_NUM_MASK;
+		*completed_index = le16_to_cpu(desc->completed_index_flags) &
+				   CQ_DESC_COMP_NDX_MASK;
+		*completed_index |= (desc->fetch_index_flags & CQ_DESC_64_FI_MASK) <<
+				CQ_DESC_COMP_NDX_BITS;
+		break;
+	}
+	}
 
-	*q_number = le16_to_cpu(desc->q_number_rss_type_flags) &
-		CQ_DESC_Q_NUM_MASK;
-	*completed_index = le16_to_cpu(desc->completed_index_flags) &
-	CQ_DESC_COMP_NDX_MASK;
 	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
 	*type = type_color & CQ_DESC_TYPE_MASK;
 }
@@ -113,6 +165,10 @@ static void enic_rq_set_skb_flags(struct vnic_rq *vrq, u8 type, u32 rss_hash,
 	}
 }
 
+/*
+ * cq_enet_rq_desc accesses section uses only the 1st 15 bytes of the cq which
+ * is identical for all type (16,32 and 64 byte) of cqs.
+ */
 static void cq_enet_rq_desc_dec(struct cq_enet_rq_desc *desc, u8 *ingress_port,
 				u8 *fcoe, u8 *eop, u8 *sop, u8 *rss_type,
 				u8 *csum_not_calc, u32 *rss_hash,
@@ -258,9 +314,8 @@ void enic_free_rq_buf(struct vnic_rq *rq, struct vnic_rq_buf *buf)
 }
 
 static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
-				 struct vnic_rq_buf *buf,
-				 struct cq_enet_rq_desc *cq_desc, u8 type,
-				 u16 q_number, u16 completed_index)
+				 struct vnic_rq_buf *buf, void *cq_desc,
+				 u8 type, u16 q_number, u16 completed_index)
 {
 	struct sk_buff *skb;
 	struct vnic_cq *cq = &enic->cq[enic_cq_rq(enic, rq->index)];
@@ -277,7 +332,7 @@ static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
 
 	rqstats->packets++;
 
-	cq_enet_rq_desc_dec(cq_desc, &ingress_port,
+	cq_enet_rq_desc_dec((struct cq_enet_rq_desc *)cq_desc, &ingress_port,
 			    &fcoe, &eop, &sop, &rss_type, &csum_not_calc,
 			    &rss_hash, &bytes_written, &packet_error,
 			    &vlan_stripped, &vlan_tci, &checksum, &fcoe_sof,
@@ -329,8 +384,8 @@ static void enic_rq_indicate_buf(struct enic *enic, struct vnic_rq *rq,
 	}
 }
 
-static void enic_rq_service(struct enic *enic, struct cq_enet_rq_desc *cq_desc,
-			    u8 type, u16 q_number, u16 completed_index)
+static void enic_rq_service(struct enic *enic, void *cq_desc, u8 type,
+			    u16 q_number, u16 completed_index)
 {
 	struct enic_rq_stats *rqstats = &enic->rq[q_number].stats;
 	struct vnic_rq *vrq = &enic->rq[q_number].vrq;
@@ -357,14 +412,12 @@ unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
 				unsigned int work_to_do)
 {
 	struct vnic_cq *cq = &enic->cq[cq_index];
-	struct cq_enet_rq_desc *cq_desc;
+	void *cq_desc = vnic_cq_to_clean(cq);
 	u16 q_number, completed_index;
 	unsigned int work_done = 0;
 	u8 type, color;
 
-	cq_desc = (struct cq_enet_rq_desc *)vnic_cq_to_clean(cq);
-
-	enic_rq_cq_desc_dec(cq_desc,  &type, &color, &q_number,
+	enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color, &q_number,
 			    &completed_index);
 
 	while (color != cq->last_color) {
@@ -374,9 +427,9 @@ unsigned int enic_rq_cq_service(struct enic *enic, unsigned int cq_index,
 		if (++work_done >= work_to_do)
 			break;
 
-		cq_desc = (struct cq_enet_rq_desc *)vnic_cq_to_clean(cq);
-		enic_rq_cq_desc_dec(cq_desc, &type, &color, &q_number,
-				    &completed_index);
+		cq_desc = vnic_cq_to_clean(cq);
+		enic_rq_cq_desc_dec(cq_desc, enic->ext_cq, &type, &color,
+				    &q_number, &completed_index);
 	}
 
 	return work_done;

From 6dca618c94676ed87ff29a8cb95431f4f2c189ee Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:41 -0500
Subject: [PATCH 1939/2753] enic: remove unused function cq_enet_wq_desc_dec

Removes cq_enet_wq_desc_dec, not needed anymore.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-5-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/cq_enet_desc.h | 7 -------
 1 file changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
index 809a3f30b87f7..50787cff29db0 100644
--- a/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_enet_desc.h
@@ -17,13 +17,6 @@ struct cq_enet_wq_desc {
 	u8 type_color;
 };
 
-static inline void cq_enet_wq_desc_dec(struct cq_enet_wq_desc *desc,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	cq_desc_dec((struct cq_desc *)desc, type,
-		color, q_number, completed_index);
-}
-
 /*
  * Defines and Capabilities for CMD_CQ_ENTRY_SIZE_SET
  */

From e5f1bcd93d96b338c486f2376f260f7fc98b3cd5 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:42 -0500
Subject: [PATCH 1940/2753] enic: added enic_wq.c and enic_wq.h

Moves wq related function to enic_wq.c. Prepares for
a cleaup of enic wq code path.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-6-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/Makefile    |   2 +-
 drivers/net/ethernet/cisco/enic/cq_desc.h   |  24 ----
 drivers/net/ethernet/cisco/enic/enic.h      |   4 +
 drivers/net/ethernet/cisco/enic/enic_main.c |  52 +--------
 drivers/net/ethernet/cisco/enic/enic_wq.c   | 118 ++++++++++++++++++++
 drivers/net/ethernet/cisco/enic/enic_wq.h   |  14 +++
 drivers/net/ethernet/cisco/enic/vnic_cq.h   |  41 -------
 7 files changed, 138 insertions(+), 117 deletions(-)
 create mode 100644 drivers/net/ethernet/cisco/enic/enic_wq.c
 create mode 100644 drivers/net/ethernet/cisco/enic/enic_wq.h

diff --git a/drivers/net/ethernet/cisco/enic/Makefile b/drivers/net/ethernet/cisco/enic/Makefile
index b3b5196b2dfcc..a96b8332e6e2a 100644
--- a/drivers/net/ethernet/cisco/enic/Makefile
+++ b/drivers/net/ethernet/cisco/enic/Makefile
@@ -3,5 +3,5 @@ obj-$(CONFIG_ENIC) := enic.o
 
 enic-y := enic_main.o vnic_cq.o vnic_intr.o vnic_wq.o \
 	enic_res.o enic_dev.o enic_pp.o vnic_dev.o vnic_rq.o vnic_vic.o \
-	enic_ethtool.o enic_api.o enic_clsf.o enic_rq.o
+	enic_ethtool.o enic_api.o enic_clsf.o enic_rq.o enic_wq.o
 
diff --git a/drivers/net/ethernet/cisco/enic/cq_desc.h b/drivers/net/ethernet/cisco/enic/cq_desc.h
index 8fc313b6ed043..bfb3f14e89f5d 100644
--- a/drivers/net/ethernet/cisco/enic/cq_desc.h
+++ b/drivers/net/ethernet/cisco/enic/cq_desc.h
@@ -43,28 +43,4 @@ struct cq_desc {
 #define CQ_DESC_32_FI_MASK (BIT(0) | BIT(1))
 #define CQ_DESC_64_FI_MASK (BIT(0) | BIT(1))
 
-static inline void cq_desc_dec(const struct cq_desc *desc_arg,
-	u8 *type, u8 *color, u16 *q_number, u16 *completed_index)
-{
-	const struct cq_desc *desc = desc_arg;
-	const u8 type_color = desc->type_color;
-
-	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
-
-	/*
-	 * Make sure color bit is read from desc *before* other fields
-	 * are read from desc.  Hardware guarantees color bit is last
-	 * bit (byte) written.  Adding the rmb() prevents the compiler
-	 * and/or CPU from reordering the reads which would potentially
-	 * result in reading stale values.
-	 */
-
-	rmb();
-
-	*type = type_color & CQ_DESC_TYPE_MASK;
-	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
-	*completed_index = le16_to_cpu(desc->completed_index) &
-		CQ_DESC_COMP_NDX_MASK;
-}
-
 #endif /* _CQ_DESC_H_ */
diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index d60e55accafd0..9c12e967e9f12 100644
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -83,6 +83,10 @@ struct enic_rx_coal {
 #define ENIC_SET_INSTANCE		(1 << 3)
 #define ENIC_SET_HOST			(1 << 4)
 
+#define MAX_TSO			BIT(16)
+#define WQ_ENET_MAX_DESC_LEN	BIT(WQ_ENET_LEN_BITS)
+#define ENIC_DESC_MAX_SPLITS	(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
+
 struct enic_port_profile {
 	u32 set;
 	u8 request;
diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index d716514366dfc..52174843f02f1 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -59,11 +59,9 @@
 #include "enic_pp.h"
 #include "enic_clsf.h"
 #include "enic_rq.h"
+#include "enic_wq.h"
 
 #define ENIC_NOTIFY_TIMER_PERIOD	(2 * HZ)
-#define WQ_ENET_MAX_DESC_LEN		(1 << WQ_ENET_LEN_BITS)
-#define MAX_TSO				(1 << 16)
-#define ENIC_DESC_MAX_SPLITS		(MAX_TSO / WQ_ENET_MAX_DESC_LEN + 1)
 
 #define PCI_DEVICE_ID_CISCO_VIC_ENET         0x0043  /* ethernet vnic */
 #define PCI_DEVICE_ID_CISCO_VIC_ENET_DYN     0x0044  /* enet dynamic vnic */
@@ -321,54 +319,6 @@ int enic_is_valid_vf(struct enic *enic, int vf)
 #endif
 }
 
-static void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	if (buf->sop)
-		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
-				 DMA_TO_DEVICE);
-	else
-		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
-			       DMA_TO_DEVICE);
-
-	if (buf->os_buf)
-		dev_kfree_skb_any(buf->os_buf);
-}
-
-static void enic_wq_free_buf(struct vnic_wq *wq,
-	struct cq_desc *cq_desc, struct vnic_wq_buf *buf, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(wq->vdev);
-
-	enic->wq[wq->index].stats.cq_work++;
-	enic->wq[wq->index].stats.cq_bytes += buf->len;
-	enic_free_wq_buf(wq, buf);
-}
-
-static int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque)
-{
-	struct enic *enic = vnic_dev_priv(vdev);
-
-	spin_lock(&enic->wq[q_number].lock);
-
-	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
-		completed_index, enic_wq_free_buf,
-		opaque);
-
-	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number)) &&
-	    vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
-	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
-		netif_wake_subqueue(enic->netdev, q_number);
-		enic->wq[q_number].stats.wake++;
-	}
-
-	spin_unlock(&enic->wq[q_number].lock);
-
-	return 0;
-}
-
 static bool enic_log_q_error(struct enic *enic)
 {
 	unsigned int i;
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.c b/drivers/net/ethernet/cisco/enic/enic_wq.c
new file mode 100644
index 0000000000000..59b02906a1f91
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.c
@@ -0,0 +1,118 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+
+#include <net/netdev_queues.h>
+#include "enic_res.h"
+#include "enic.h"
+#include "enic_wq.h"
+
+static void cq_desc_dec(const struct cq_desc *desc_arg, u8 *type, u8 *color,
+			u16 *q_number, u16 *completed_index)
+{
+	const struct cq_desc *desc = desc_arg;
+	const u8 type_color = desc->type_color;
+
+	*color = (type_color >> CQ_DESC_COLOR_SHIFT) & CQ_DESC_COLOR_MASK;
+
+	/*
+	 * Make sure color bit is read from desc *before* other fields
+	 * are read from desc.  Hardware guarantees color bit is last
+	 * bit (byte) written.  Adding the rmb() prevents the compiler
+	 * and/or CPU from reordering the reads which would potentially
+	 * result in reading stale values.
+	 */
+	rmb();
+
+	*type = type_color & CQ_DESC_TYPE_MASK;
+	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
+	*completed_index = le16_to_cpu(desc->completed_index) &
+		CQ_DESC_COMP_NDX_MASK;
+}
+
+unsigned int vnic_cq_service(struct vnic_cq *cq, unsigned int work_to_do,
+			     int (*q_service)(struct vnic_dev *vdev,
+					      struct cq_desc *cq_desc, u8 type,
+					      u16 q_number, u16 completed_index,
+					      void *opaque), void *opaque)
+{
+	struct cq_desc *cq_desc;
+	unsigned int work_done = 0;
+	u16 q_number, completed_index;
+	u8 type, color;
+
+	cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
+		   cq->ring.desc_size * cq->to_clean);
+	cq_desc_dec(cq_desc, &type, &color,
+		    &q_number, &completed_index);
+
+	while (color != cq->last_color) {
+		if ((*q_service)(cq->vdev, cq_desc, type, q_number,
+				 completed_index, opaque))
+			break;
+
+		cq->to_clean++;
+		if (cq->to_clean == cq->ring.desc_count) {
+			cq->to_clean = 0;
+			cq->last_color = cq->last_color ? 0 : 1;
+		}
+
+		cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
+			cq->ring.desc_size * cq->to_clean);
+		cq_desc_dec(cq_desc, &type, &color,
+			    &q_number, &completed_index);
+
+		work_done++;
+		if (work_done >= work_to_do)
+			break;
+	}
+
+	return work_done;
+}
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	if (buf->sop)
+		dma_unmap_single(&enic->pdev->dev, buf->dma_addr, buf->len,
+				 DMA_TO_DEVICE);
+	else
+		dma_unmap_page(&enic->pdev->dev, buf->dma_addr, buf->len,
+			       DMA_TO_DEVICE);
+
+	if (buf->os_buf)
+		dev_kfree_skb_any(buf->os_buf);
+}
+
+static void enic_wq_free_buf(struct vnic_wq *wq, struct cq_desc *cq_desc,
+			     struct vnic_wq_buf *buf, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(wq->vdev);
+
+	enic->wq[wq->index].stats.cq_work++;
+	enic->wq[wq->index].stats.cq_bytes += buf->len;
+	enic_free_wq_buf(wq, buf);
+}
+
+int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
+		    u16 q_number, u16 completed_index, void *opaque)
+{
+	struct enic *enic = vnic_dev_priv(vdev);
+
+	spin_lock(&enic->wq[q_number].lock);
+
+	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
+			completed_index, enic_wq_free_buf, opaque);
+
+	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number))
+	    && vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
+	    (MAX_SKB_FRAGS + ENIC_DESC_MAX_SPLITS)) {
+		netif_wake_subqueue(enic->netdev, q_number);
+		enic->wq[q_number].stats.wake++;
+	}
+
+	spin_unlock(&enic->wq[q_number].lock);
+
+	return 0;
+}
+
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.h b/drivers/net/ethernet/cisco/enic/enic_wq.h
new file mode 100644
index 0000000000000..cc4d6a969a9fb
--- /dev/null
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright 2025 Cisco Systems, Inc.  All rights reserved.
+ */
+
+unsigned int vnic_cq_service(struct vnic_cq *cq, unsigned int work_to_do,
+			     int (*q_service)(struct vnic_dev *vdev,
+					      struct cq_desc *cq_desc, u8 type,
+					      u16 q_number, u16 completed_index,
+					      void *opaque), void *opaque);
+
+void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf);
+
+int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
+		    u16 q_number, u16 completed_index, void *opaque);
diff --git a/drivers/net/ethernet/cisco/enic/vnic_cq.h b/drivers/net/ethernet/cisco/enic/vnic_cq.h
index 21d97c01f9424..0e37f5d5e5272 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_cq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_cq.h
@@ -56,47 +56,6 @@ struct vnic_cq {
 	ktime_t prev_ts;
 };
 
-static inline unsigned int vnic_cq_service(struct vnic_cq *cq,
-	unsigned int work_to_do,
-	int (*q_service)(struct vnic_dev *vdev, struct cq_desc *cq_desc,
-	u8 type, u16 q_number, u16 completed_index, void *opaque),
-	void *opaque)
-{
-	struct cq_desc *cq_desc;
-	unsigned int work_done = 0;
-	u16 q_number, completed_index;
-	u8 type, color;
-
-	cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-		cq->ring.desc_size * cq->to_clean);
-	cq_desc_dec(cq_desc, &type, &color,
-		&q_number, &completed_index);
-
-	while (color != cq->last_color) {
-
-		if ((*q_service)(cq->vdev, cq_desc, type,
-			q_number, completed_index, opaque))
-			break;
-
-		cq->to_clean++;
-		if (cq->to_clean == cq->ring.desc_count) {
-			cq->to_clean = 0;
-			cq->last_color = cq->last_color ? 0 : 1;
-		}
-
-		cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-			cq->ring.desc_size * cq->to_clean);
-		cq_desc_dec(cq_desc, &type, &color,
-			&q_number, &completed_index);
-
-		work_done++;
-		if (work_done >= work_to_do)
-			break;
-	}
-
-	return work_done;
-}
-
 static inline void *vnic_cq_to_clean(struct vnic_cq *cq)
 {
 	return ((u8 *)cq->ring.descs + cq->ring.desc_size * cq->to_clean);

From 26b2c5f6ff479825957975518df4cb8e96da0271 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:43 -0500
Subject: [PATCH 1941/2753] enic: cleanup of enic wq request completion path

Cleans up the enic wq request completion path needed for 16k wq size
support.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-7-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cisco/enic/enic_main.c |  7 +-
 drivers/net/ethernet/cisco/enic/enic_wq.c   | 95 ++++++++++-----------
 drivers/net/ethernet/cisco/enic/enic_wq.h   | 11 +--
 3 files changed, 52 insertions(+), 61 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 52174843f02f1..54aa3953bf7b6 100644
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -1332,8 +1332,7 @@ static int enic_poll(struct napi_struct *napi, int budget)
 	unsigned int  work_done, rq_work_done = 0, wq_work_done;
 	int err;
 
-	wq_work_done = vnic_cq_service(&enic->cq[cq_wq], wq_work_to_do,
-				       enic_wq_service, NULL);
+	wq_work_done = enic_wq_cq_service(enic, cq_wq, wq_work_to_do);
 
 	if (budget > 0)
 		rq_work_done = enic_rq_cq_service(enic, cq_rq, rq_work_to_do);
@@ -1435,8 +1434,8 @@ static int enic_poll_msix_wq(struct napi_struct *napi, int budget)
 	wq_irq = wq->index;
 	cq = enic_cq_wq(enic, wq_irq);
 	intr = enic_msix_wq_intr(enic, wq_irq);
-	wq_work_done = vnic_cq_service(&enic->cq[cq], wq_work_to_do,
-				       enic_wq_service, NULL);
+
+	wq_work_done = enic_wq_cq_service(enic, cq, wq_work_to_do);
 
 	vnic_intr_return_credits(&enic->intr[intr], wq_work_done,
 				 0 /* don't unmask intr */,
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.c b/drivers/net/ethernet/cisco/enic/enic_wq.c
index 59b02906a1f91..2a5ddad512e38 100644
--- a/drivers/net/ethernet/cisco/enic/enic_wq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.c
@@ -6,8 +6,12 @@
 #include "enic.h"
 #include "enic_wq.h"
 
-static void cq_desc_dec(const struct cq_desc *desc_arg, u8 *type, u8 *color,
-			u16 *q_number, u16 *completed_index)
+#define ENET_CQ_DESC_COMP_NDX_BITS 14
+#define ENET_CQ_DESC_COMP_NDX_MASK GENMASK(ENET_CQ_DESC_COMP_NDX_BITS - 1, 0)
+
+static void enic_wq_cq_desc_dec(const struct cq_desc *desc_arg, bool ext_wq,
+				u8 *type, u8 *color, u16 *q_number,
+				u16 *completed_index)
 {
 	const struct cq_desc *desc = desc_arg;
 	const u8 type_color = desc->type_color;
@@ -25,48 +29,13 @@ static void cq_desc_dec(const struct cq_desc *desc_arg, u8 *type, u8 *color,
 
 	*type = type_color & CQ_DESC_TYPE_MASK;
 	*q_number = le16_to_cpu(desc->q_number) & CQ_DESC_Q_NUM_MASK;
-	*completed_index = le16_to_cpu(desc->completed_index) &
-		CQ_DESC_COMP_NDX_MASK;
-}
-
-unsigned int vnic_cq_service(struct vnic_cq *cq, unsigned int work_to_do,
-			     int (*q_service)(struct vnic_dev *vdev,
-					      struct cq_desc *cq_desc, u8 type,
-					      u16 q_number, u16 completed_index,
-					      void *opaque), void *opaque)
-{
-	struct cq_desc *cq_desc;
-	unsigned int work_done = 0;
-	u16 q_number, completed_index;
-	u8 type, color;
-
-	cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-		   cq->ring.desc_size * cq->to_clean);
-	cq_desc_dec(cq_desc, &type, &color,
-		    &q_number, &completed_index);
-
-	while (color != cq->last_color) {
-		if ((*q_service)(cq->vdev, cq_desc, type, q_number,
-				 completed_index, opaque))
-			break;
-
-		cq->to_clean++;
-		if (cq->to_clean == cq->ring.desc_count) {
-			cq->to_clean = 0;
-			cq->last_color = cq->last_color ? 0 : 1;
-		}
-
-		cq_desc = (struct cq_desc *)((u8 *)cq->ring.descs +
-			cq->ring.desc_size * cq->to_clean);
-		cq_desc_dec(cq_desc, &type, &color,
-			    &q_number, &completed_index);
 
-		work_done++;
-		if (work_done >= work_to_do)
-			break;
-	}
-
-	return work_done;
+	if (ext_wq)
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			ENET_CQ_DESC_COMP_NDX_MASK;
+	else
+		*completed_index = le16_to_cpu(desc->completed_index) &
+			CQ_DESC_COMP_NDX_MASK;
 }
 
 void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf)
@@ -94,15 +63,15 @@ static void enic_wq_free_buf(struct vnic_wq *wq, struct cq_desc *cq_desc,
 	enic_free_wq_buf(wq, buf);
 }
 
-int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
-		    u16 q_number, u16 completed_index, void *opaque)
+static void enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc,
+			    u8 type, u16 q_number, u16 completed_index)
 {
 	struct enic *enic = vnic_dev_priv(vdev);
 
 	spin_lock(&enic->wq[q_number].lock);
 
 	vnic_wq_service(&enic->wq[q_number].vwq, cq_desc,
-			completed_index, enic_wq_free_buf, opaque);
+			completed_index, enic_wq_free_buf, NULL);
 
 	if (netif_tx_queue_stopped(netdev_get_tx_queue(enic->netdev, q_number))
 	    && vnic_wq_desc_avail(&enic->wq[q_number].vwq) >=
@@ -112,7 +81,37 @@ int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
 	}
 
 	spin_unlock(&enic->wq[q_number].lock);
-
-	return 0;
 }
 
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do)
+{
+	struct vnic_cq *cq = &enic->cq[cq_index];
+	u16 q_number, completed_index;
+	unsigned int work_done = 0;
+	struct cq_desc *cq_desc;
+	u8 type, color;
+	bool ext_wq;
+
+	ext_wq = cq->ring.size > ENIC_MAX_WQ_DESCS;
+
+	cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+	enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+			    &q_number, &completed_index);
+
+	while (color != cq->last_color) {
+		enic_wq_service(cq->vdev, cq_desc, type, q_number,
+				completed_index);
+
+		vnic_cq_inc_to_clean(cq);
+
+		if (++work_done >= work_to_do)
+			break;
+
+		cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
+		enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
+				    &q_number, &completed_index);
+	}
+
+	return work_done;
+}
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.h b/drivers/net/ethernet/cisco/enic/enic_wq.h
index cc4d6a969a9fb..12acb3f2fbc94 100644
--- a/drivers/net/ethernet/cisco/enic/enic_wq.h
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.h
@@ -2,13 +2,6 @@
  * Copyright 2025 Cisco Systems, Inc.  All rights reserved.
  */
 
-unsigned int vnic_cq_service(struct vnic_cq *cq, unsigned int work_to_do,
-			     int (*q_service)(struct vnic_dev *vdev,
-					      struct cq_desc *cq_desc, u8 type,
-					      u16 q_number, u16 completed_index,
-					      void *opaque), void *opaque);
-
 void enic_free_wq_buf(struct vnic_wq *wq, struct vnic_wq_buf *buf);
-
-int enic_wq_service(struct vnic_dev *vdev, struct cq_desc *cq_desc, u8 type,
-		    u16 q_number, u16 completed_index, void *opaque);
+unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
+				unsigned int work_to_do);

From df9fd2a3ce01ea08e4e14e3d9e9d3c113eaeba91 Mon Sep 17 00:00:00 2001
From: Satish Kharat <satishkh@cisco.com>
Date: Tue, 4 Mar 2025 19:56:44 -0500
Subject: [PATCH 1942/2753] enic: get max rq & wq entries supported by hw, 16K
 queues

Enables reading the max rq and wq entries supported from the hw.
Enables 16k rq and wq entries on hw that supports.

Co-developed-by: Nelson Escobar <neescoba@cisco.com>
Signed-off-by: Nelson Escobar <neescoba@cisco.com>
Co-developed-by: John Daley <johndale@cisco.com>
Signed-off-by: John Daley <johndale@cisco.com>
Signed-off-by: Satish Kharat <satishkh@cisco.com>
Link: https://patch.msgid.link/20250304-enic_cleanup_and_ext_cq-v2-8-85804263dad8@cisco.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/cisco/enic/enic_ethtool.c    | 12 ++++----
 drivers/net/ethernet/cisco/enic/enic_res.c    | 29 ++++++++++++-------
 drivers/net/ethernet/cisco/enic/enic_res.h    | 11 ++++---
 drivers/net/ethernet/cisco/enic/enic_wq.c     |  2 +-
 drivers/net/ethernet/cisco/enic/vnic_enet.h   |  5 ++++
 drivers/net/ethernet/cisco/enic/vnic_rq.h     |  2 +-
 drivers/net/ethernet/cisco/enic/vnic_wq.h     |  2 +-
 7 files changed, 39 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/cisco/enic/enic_ethtool.c b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
index 18b929fc28799..529160926a963 100644
--- a/drivers/net/ethernet/cisco/enic/enic_ethtool.c
+++ b/drivers/net/ethernet/cisco/enic/enic_ethtool.c
@@ -222,9 +222,9 @@ static void enic_get_ringparam(struct net_device *netdev,
 	struct enic *enic = netdev_priv(netdev);
 	struct vnic_enet_config *c = &enic->config;
 
-	ring->rx_max_pending = ENIC_MAX_RQ_DESCS;
+	ring->rx_max_pending = c->max_rq_ring;
 	ring->rx_pending = c->rq_desc_count;
-	ring->tx_max_pending = ENIC_MAX_WQ_DESCS;
+	ring->tx_max_pending = c->max_wq_ring;
 	ring->tx_pending = c->wq_desc_count;
 }
 
@@ -252,18 +252,18 @@ static int enic_set_ringparam(struct net_device *netdev,
 	}
 	rx_pending = c->rq_desc_count;
 	tx_pending = c->wq_desc_count;
-	if (ring->rx_pending > ENIC_MAX_RQ_DESCS ||
+	if (ring->rx_pending > c->max_rq_ring ||
 	    ring->rx_pending < ENIC_MIN_RQ_DESCS) {
 		netdev_info(netdev, "rx pending (%u) not in range [%u,%u]",
 			    ring->rx_pending, ENIC_MIN_RQ_DESCS,
-			    ENIC_MAX_RQ_DESCS);
+	      c->max_rq_ring);
 		return -EINVAL;
 	}
-	if (ring->tx_pending > ENIC_MAX_WQ_DESCS ||
+	if (ring->tx_pending > c->max_wq_ring ||
 	    ring->tx_pending < ENIC_MIN_WQ_DESCS) {
 		netdev_info(netdev, "tx pending (%u) not in range [%u,%u]",
 			    ring->tx_pending, ENIC_MIN_WQ_DESCS,
-			    ENIC_MAX_WQ_DESCS);
+			c->max_wq_ring);
 		return -EINVAL;
 	}
 	if (running)
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.c b/drivers/net/ethernet/cisco/enic/enic_res.c
index a7179cc4b5296..bbd3143ed73e7 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.c
+++ b/drivers/net/ethernet/cisco/enic/enic_res.c
@@ -59,31 +59,38 @@ int enic_get_vnic_config(struct enic *enic)
 	GET_CONFIG(intr_timer_usec);
 	GET_CONFIG(loop_tag);
 	GET_CONFIG(num_arfs);
+	GET_CONFIG(max_rq_ring);
+	GET_CONFIG(max_wq_ring);
+	GET_CONFIG(max_cq_ring);
+
+	if (!c->max_wq_ring)
+		c->max_wq_ring = ENIC_MAX_WQ_DESCS_DEFAULT;
+	if (!c->max_rq_ring)
+		c->max_rq_ring = ENIC_MAX_RQ_DESCS_DEFAULT;
+	if (!c->max_cq_ring)
+		c->max_cq_ring = ENIC_MAX_CQ_DESCS_DEFAULT;
 
 	c->wq_desc_count =
-		min_t(u32, ENIC_MAX_WQ_DESCS,
-		max_t(u32, ENIC_MIN_WQ_DESCS,
-		c->wq_desc_count));
+		min_t(u32, c->max_wq_ring,
+		      max_t(u32, ENIC_MIN_WQ_DESCS, c->wq_desc_count));
 	c->wq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	c->rq_desc_count =
-		min_t(u32, ENIC_MAX_RQ_DESCS,
-		max_t(u32, ENIC_MIN_RQ_DESCS,
-		c->rq_desc_count));
+		min_t(u32, c->max_rq_ring,
+		      max_t(u32, ENIC_MIN_RQ_DESCS, c->rq_desc_count));
 	c->rq_desc_count &= 0xffffffe0; /* must be aligned to groups of 32 */
 
 	if (c->mtu == 0)
 		c->mtu = 1500;
-	c->mtu = min_t(u16, ENIC_MAX_MTU,
-		max_t(u16, ENIC_MIN_MTU,
-		c->mtu));
+	c->mtu = min_t(u16, ENIC_MAX_MTU, max_t(u16, ENIC_MIN_MTU, c->mtu));
 
 	c->intr_timer_usec = min_t(u32, c->intr_timer_usec,
 		vnic_dev_get_intr_coal_timer_max(enic->vdev));
 
 	dev_info(enic_get_dev(enic),
-		"vNIC MAC addr %pM wq/rq %d/%d mtu %d\n",
-		enic->mac_addr, c->wq_desc_count, c->rq_desc_count, c->mtu);
+		 "vNIC MAC addr %pM wq/rq %d/%d max wq/rq/cq %d/%d/%d mtu %d\n",
+		 enic->mac_addr, c->wq_desc_count, c->rq_desc_count,
+		 c->max_wq_ring, c->max_rq_ring, c->max_cq_ring, c->mtu);
 
 	dev_info(enic_get_dev(enic), "vNIC csum tx/rx %s/%s "
 		"tso/lro %s/%s rss %s intr mode %s type %s timer %d usec "
diff --git a/drivers/net/ethernet/cisco/enic/enic_res.h b/drivers/net/ethernet/cisco/enic/enic_res.h
index b8ee42d297aaf..02dca1ae4a224 100644
--- a/drivers/net/ethernet/cisco/enic/enic_res.h
+++ b/drivers/net/ethernet/cisco/enic/enic_res.h
@@ -12,10 +12,13 @@
 #include "vnic_wq.h"
 #include "vnic_rq.h"
 
-#define ENIC_MIN_WQ_DESCS		64
-#define ENIC_MAX_WQ_DESCS		4096
-#define ENIC_MIN_RQ_DESCS		64
-#define ENIC_MAX_RQ_DESCS		4096
+#define ENIC_MIN_WQ_DESCS 64
+#define ENIC_MAX_WQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_WQ_DESCS 16384
+#define ENIC_MIN_RQ_DESCS 64
+#define ENIC_MAX_RQ_DESCS 16384
+#define ENIC_MAX_RQ_DESCS_DEFAULT 4096
+#define ENIC_MAX_CQ_DESCS_DEFAULT (64 * 1024)
 
 #define ENIC_MIN_MTU			ETH_MIN_MTU
 #define ENIC_MAX_MTU			9000
diff --git a/drivers/net/ethernet/cisco/enic/enic_wq.c b/drivers/net/ethernet/cisco/enic/enic_wq.c
index 2a5ddad512e38..07936f8b42317 100644
--- a/drivers/net/ethernet/cisco/enic/enic_wq.c
+++ b/drivers/net/ethernet/cisco/enic/enic_wq.c
@@ -93,7 +93,7 @@ unsigned int enic_wq_cq_service(struct enic *enic, unsigned int cq_index,
 	u8 type, color;
 	bool ext_wq;
 
-	ext_wq = cq->ring.size > ENIC_MAX_WQ_DESCS;
+	ext_wq = cq->ring.size > ENIC_MAX_WQ_DESCS_DEFAULT;
 
 	cq_desc = (struct cq_desc *)vnic_cq_to_clean(cq);
 	enic_wq_cq_desc_dec(cq_desc, ext_wq, &type, &color,
diff --git a/drivers/net/ethernet/cisco/enic/vnic_enet.h b/drivers/net/ethernet/cisco/enic/vnic_enet.h
index 5acc236069dea..9e8e86262a3fe 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_enet.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_enet.h
@@ -21,6 +21,11 @@ struct vnic_enet_config {
 	u16 loop_tag;
 	u16 vf_rq_count;
 	u16 num_arfs;
+	u8 reserved[66];
+	u32 max_rq_ring;	// MAX RQ ring size
+	u32 max_wq_ring;	// MAX WQ ring size
+	u32 max_cq_ring;	// MAX CQ ring size
+	u32 rdma_rsvd_lkey;	// Reserved (privileged) LKey
 };
 
 #define VENETF_TSO		0x1	/* TSO enabled */
diff --git a/drivers/net/ethernet/cisco/enic/vnic_rq.h b/drivers/net/ethernet/cisco/enic/vnic_rq.h
index 2ee4be2b9a343..a1cdd729caece 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_rq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_rq.h
@@ -50,7 +50,7 @@ struct vnic_rq_ctrl {
 	(VNIC_RQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_rq_buf))
 #define VNIC_RQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_RQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_RQ_BUF_BLKS_MAX VNIC_RQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_rq_buf {
 	struct vnic_rq_buf *next;
diff --git a/drivers/net/ethernet/cisco/enic/vnic_wq.h b/drivers/net/ethernet/cisco/enic/vnic_wq.h
index 75c5269110744..3bb4758100ba4 100644
--- a/drivers/net/ethernet/cisco/enic/vnic_wq.h
+++ b/drivers/net/ethernet/cisco/enic/vnic_wq.h
@@ -62,7 +62,7 @@ struct vnic_wq_buf {
 	(VNIC_WQ_BUF_BLK_ENTRIES(entries) * sizeof(struct vnic_wq_buf))
 #define VNIC_WQ_BUF_BLKS_NEEDED(entries) \
 	DIV_ROUND_UP(entries, VNIC_WQ_BUF_BLK_ENTRIES(entries))
-#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(4096)
+#define VNIC_WQ_BUF_BLKS_MAX VNIC_WQ_BUF_BLKS_NEEDED(16384)
 
 struct vnic_wq {
 	unsigned int index;

From 12d8f318347b1d4feac48e8ac351d3786af39599 Mon Sep 17 00:00:00 2001
From: Imre Deak <imre.deak@intel.com>
Date: Fri, 7 Mar 2025 20:31:52 +0200
Subject: [PATCH 1943/2753] drm/dp_mst: Fix locking when skipping CSN before
 topology probing

The handling of the MST Connection Status Notify message is skipped if
the probing of the topology is still pending. Acquiring the
drm_dp_mst_topology_mgr::probe_lock for this in
drm_dp_mst_handle_up_req() is problematic: the task/work this function
is called from is also responsible for handling MST down-request replies
(in drm_dp_mst_handle_down_rep()). Thus drm_dp_mst_link_probe_work() -
holding already probe_lock - could be blocked waiting for an MST
down-request reply while drm_dp_mst_handle_up_req() is waiting for
probe_lock while processing a CSN message. This leads to the probe
work's down-request message timing out.

A scenario similar to the above leading to a down-request timeout is
handling a CSN message in drm_dp_mst_handle_conn_stat(), holding the
probe_lock and sending down-request messages while a second CSN message
sent by the sink subsequently is handled by drm_dp_mst_handle_up_req().

Fix the above by moving the logic to skip the CSN handling to
drm_dp_mst_process_up_req(). This function is called from a work
(separate from the task/work handling new up/down messages), already
holding probe_lock. This solves the above timeout issue, since handling
of down-request replies won't be blocked by probe_lock.

Fixes: ddf983488c3e ("drm/dp_mst: Skip CSN if topology probing is not done yet")
Cc: Wayne Lin <Wayne.Lin@amd.com>
Cc: Lyude Paul <lyude@redhat.com>
Cc: stable@vger.kernel.org # v6.6+
Reviewed-by: Wayne Lin <Wayne.Lin@amd.com>
Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Imre Deak <imre.deak@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250307183152.3822170-1-imre.deak@intel.com
---
 drivers/gpu/drm/display/drm_dp_mst_topology.c | 40 +++++++++++--------
 1 file changed, 24 insertions(+), 16 deletions(-)

diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
index 06c91c5b7f7c8..6d09bef671da0 100644
--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
@@ -4025,6 +4025,22 @@ static int drm_dp_mst_handle_down_rep(struct drm_dp_mst_topology_mgr *mgr)
 	return 0;
 }
 
+static bool primary_mstb_probing_is_done(struct drm_dp_mst_topology_mgr *mgr)
+{
+	bool probing_done = false;
+
+	mutex_lock(&mgr->lock);
+
+	if (mgr->mst_primary && drm_dp_mst_topology_try_get_mstb(mgr->mst_primary)) {
+		probing_done = mgr->mst_primary->link_address_sent;
+		drm_dp_mst_topology_put_mstb(mgr->mst_primary);
+	}
+
+	mutex_unlock(&mgr->lock);
+
+	return probing_done;
+}
+
 static inline bool
 drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr,
 			  struct drm_dp_pending_up_req *up_req)
@@ -4055,8 +4071,12 @@ drm_dp_mst_process_up_req(struct drm_dp_mst_topology_mgr *mgr,
 
 	/* TODO: Add missing handler for DP_RESOURCE_STATUS_NOTIFY events */
 	if (msg->req_type == DP_CONNECTION_STATUS_NOTIFY) {
-		dowork = drm_dp_mst_handle_conn_stat(mstb, &msg->u.conn_stat);
-		hotplug = true;
+		if (!primary_mstb_probing_is_done(mgr)) {
+			drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it.\n");
+		} else {
+			dowork = drm_dp_mst_handle_conn_stat(mstb, &msg->u.conn_stat);
+			hotplug = true;
+		}
 	}
 
 	drm_dp_mst_topology_put_mstb(mstb);
@@ -4138,10 +4158,11 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 	drm_dp_send_up_ack_reply(mgr, mst_primary, up_req->msg.req_type,
 				 false);
 
+	drm_dp_mst_topology_put_mstb(mst_primary);
+
 	if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) {
 		const struct drm_dp_connection_status_notify *conn_stat =
 			&up_req->msg.u.conn_stat;
-		bool handle_csn;
 
 		drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n",
 			    conn_stat->port_number,
@@ -4150,16 +4171,6 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 			    conn_stat->message_capability_status,
 			    conn_stat->input_port,
 			    conn_stat->peer_device_type);
-
-		mutex_lock(&mgr->probe_lock);
-		handle_csn = mst_primary->link_address_sent;
-		mutex_unlock(&mgr->probe_lock);
-
-		if (!handle_csn) {
-			drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it.");
-			kfree(up_req);
-			goto out_put_primary;
-		}
 	} else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
 		const struct drm_dp_resource_status_notify *res_stat =
 			&up_req->msg.u.resource_stat;
@@ -4174,9 +4185,6 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
 	list_add_tail(&up_req->next, &mgr->up_req_list);
 	mutex_unlock(&mgr->up_req_lock);
 	queue_work(system_long_wq, &mgr->up_req_work);
-
-out_put_primary:
-	drm_dp_mst_topology_put_mstb(mst_primary);
 out_clear_reply:
 	reset_msg_rx_state(&mgr->up_req_recv);
 	return ret;

From a096a8602f4fee42a18b7537a7467a28c44728af Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:27 +0200
Subject: [PATCH 1944/2753] wifi: cfg80211: move link reconfig parameters into
 a struct

Add a new struct cfg80211_ml_reconf_req to collect the link
reconfiguration parameters.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.0cf299c1fdd0.Id1a3b1092dc52d0d3731a8798522fdf2e052bf0b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h     | 15 ++++++++++++---
 net/mac80211/cfg.c         |  7 +++----
 net/mac80211/ieee80211_i.h |  5 ++---
 net/mac80211/mlme.c        | 39 +++++++++++++++++++-------------------
 net/wireless/core.h        |  6 +++---
 net/wireless/mlme.c        | 13 ++++++-------
 net/wireless/nl80211.c     | 24 +++++++++++------------
 net/wireless/rdev-ops.h    | 10 ++++------
 net/wireless/trace.h       | 13 ++++++-------
 9 files changed, 67 insertions(+), 65 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 6b170a8d086c8..c7cfef104896f 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -7,7 +7,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014 Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #include <linux/ethtool.h>
@@ -3082,6 +3082,16 @@ struct cfg80211_assoc_link {
 	int error;
 };
 
+/**
+ * struct cfg80211_ml_reconf_req - MLO link reconfiguration request
+ * @add_links: data for links to add, see &struct cfg80211_assoc_link
+ * @rem_links: bitmap of links to remove
+ */
+struct cfg80211_ml_reconf_req {
+	struct cfg80211_assoc_link add_links[IEEE80211_MLD_MAX_NUM_LINKS];
+	u16 rem_links;
+};
+
 /**
  * enum cfg80211_assoc_req_flags - Over-ride default behaviour in association.
  *
@@ -4972,8 +4982,7 @@ struct cfg80211_ops {
 			    struct cfg80211_ttlm_params *params);
 	u32	(*get_radio_mask)(struct wiphy *wiphy, struct net_device *dev);
 	int     (*assoc_ml_reconf)(struct wiphy *wiphy, struct net_device *dev,
-				   struct cfg80211_assoc_link *add_links,
-				   u16 rem_links);
+				   struct cfg80211_ml_reconf_req *req);
 	int	(*set_epcs)(struct wiphy *wiphy, struct net_device *dev,
 			    bool val);
 };
diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 09708a060bb79..76453c0f82a52 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #include <linux/ieee80211.h>
@@ -5185,14 +5185,13 @@ ieee80211_set_ttlm(struct wiphy *wiphy, struct net_device *dev,
 
 static int
 ieee80211_assoc_ml_reconf(struct wiphy *wiphy, struct net_device *dev,
-			  struct cfg80211_assoc_link *add_links,
-			  u16 rem_links)
+			  struct cfg80211_ml_reconf_req *req)
 {
 	struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 
 	lockdep_assert_wiphy(sdata->local->hw.wiphy);
 
-	return ieee80211_mgd_assoc_ml_reconf(sdata, add_links, rem_links);
+	return ieee80211_mgd_assoc_ml_reconf(sdata, req);
 }
 
 static int
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 845888ac3d2cb..5f92619f8584a 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -5,7 +5,7 @@
  * Copyright 2006-2007	Jiri Benc <jbenc@suse.cz>
  * Copyright 2007-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2015  Intel Mobile Communications GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #ifndef IEEE80211_I_H
@@ -2789,8 +2789,7 @@ void ieee80211_process_epcs_teardown(struct ieee80211_sub_if_data *sdata,
 				     struct ieee80211_mgmt *mgmt, size_t len);
 
 int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
-				  struct cfg80211_assoc_link *add_links,
-				  u16 rem_links);
+				  struct cfg80211_ml_reconf_req *req);
 
 void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 				      struct ieee80211_mgmt *mgmt, size_t len);
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 23d85a1abbc59..613959f19713e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10362,8 +10362,7 @@ ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 }
 
 int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
-				  struct cfg80211_assoc_link *add_links,
-				  u16 rem_links)
+				  struct cfg80211_ml_reconf_req *req)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_mgd_assoc_data *data = NULL;
@@ -10383,9 +10382,8 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 		return -EBUSY;
 
 	added_links = 0;
-	for (link_id = 0; add_links && link_id < IEEE80211_MLD_MAX_NUM_LINKS;
-	     link_id++) {
-		if (!add_links[link_id].bss)
+	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
+		if (!req->add_links[link_id].bss)
 			continue;
 
 		added_links |= BIT(link_id);
@@ -10413,7 +10411,8 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
 			struct ieee80211_supported_band *sband;
-			struct cfg80211_bss *link_cbss = add_links[link_id].bss;
+			struct cfg80211_bss *link_cbss =
+				req->add_links[link_id].bss;
 			struct ieee80211_bss *bss;
 
 			if (!link_cbss)
@@ -10443,11 +10442,11 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 
 			data->link[link_id].bss = link_cbss;
 			data->link[link_id].disabled =
-				add_links[link_id].disabled;
+				req->add_links[link_id].disabled;
 			data->link[link_id].elems =
-				(u8 *)add_links[link_id].elems;
+				(u8 *)req->add_links[link_id].elems;
 			data->link[link_id].elems_len =
-				add_links[link_id].elems_len;
+				req->add_links[link_id].elems_len;
 
 			if (!bss->uapsd_supported)
 				uapsd_supported = false;
@@ -10497,10 +10496,11 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	 * Section 35.3.6.4 in Draft P802.11be_D7.0 the AP MLD should accept the
 	 * link removal request.
 	 */
-	if (rem_links) {
-		u16 new_active_links = sdata->vif.active_links & ~rem_links;
+	if (req->rem_links) {
+		u16 new_active_links =
+			sdata->vif.active_links & ~req->rem_links;
 
-		new_valid_links = sdata->vif.valid_links & ~rem_links;
+		new_valid_links = sdata->vif.valid_links & ~req->rem_links;
 
 		/* Should not be left with no valid links to perform the
 		 * ML reconfiguration
@@ -10535,14 +10535,15 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	 * is expected to send the ML reconfiguration response frame on the link
 	 * on which the request was received.
 	 */
-	skb = ieee80211_build_ml_reconf_req(sdata, data, rem_links);
+	skb = ieee80211_build_ml_reconf_req(sdata, data, req->rem_links);
 	if (!skb) {
 		err = -ENOMEM;
 		goto err_free;
 	}
 
-	if (rem_links) {
-		u16 new_dormant_links = sdata->vif.dormant_links & ~rem_links;
+	if (req->rem_links) {
+		u16 new_dormant_links =
+			sdata->vif.dormant_links & ~req->rem_links;
 
 		err = ieee80211_vif_set_links(sdata, new_valid_links,
 					      new_dormant_links);
@@ -10555,7 +10556,7 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
-			if (!(rem_links & BIT(link_id)))
+			if (!(req->rem_links & BIT(link_id)))
 				continue;
 
 			ieee80211_sta_remove_link(sta, link_id);
@@ -10564,17 +10565,17 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 		/* notify the driver and upper layers */
 		ieee80211_vif_cfg_change_notify(sdata,
 						BSS_CHANGED_MLD_VALID_LINKS);
-		cfg80211_links_removed(sdata->dev, rem_links);
+		cfg80211_links_removed(sdata->dev, req->rem_links);
 	}
 
 	sdata_info(sdata, "mlo: reconf: adding=0x%x, removed=0x%x\n",
-		   added_links, rem_links);
+		   added_links, req->rem_links);
 
 	ieee80211_tx_skb(sdata, skb);
 
 	sdata->u.mgd.reconf.added_links = added_links;
 	sdata->u.mgd.reconf.add_links_data = data;
-	sdata->u.mgd.reconf.removed_links = rem_links;
+	sdata->u.mgd.reconf.removed_links = req->rem_links;
 	wiphy_delayed_work_queue(sdata->local->hw.wiphy,
 				 &sdata->u.mgd.reconf.wk,
 				 IEEE80211_ASSOC_TIMEOUT_SHORT);
diff --git a/net/wireless/core.h b/net/wireless/core.h
index b094b526b05db..c56a35040caa1 100644
--- a/net/wireless/core.h
+++ b/net/wireless/core.h
@@ -3,7 +3,7 @@
  * Wireless configuration interface internals.
  *
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #ifndef __NET_WIRELESS_CORE_H
 #define __NET_WIRELESS_CORE_H
@@ -568,8 +568,8 @@ void cfg80211_wdev_release_link_bsses(struct wireless_dev *wdev, u16 link_mask);
 
 int cfg80211_assoc_ml_reconf(struct cfg80211_registered_device *rdev,
 			     struct net_device *dev,
-			     struct cfg80211_assoc_link *links,
-			     u16 rem_links);
+			     struct cfg80211_ml_reconf_req *req);
+
 /**
  * struct cfg80211_colocated_ap - colocated AP information
  *
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index e10f2b3b4b7f6..956d33b219df1 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -4,7 +4,7 @@
  *
  * Copyright (c) 2009, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2015		Intel Deutschland GmbH
- * Copyright (C) 2019-2020, 2022-2024 Intel Corporation
+ * Copyright (C) 2019-2020, 2022-2025 Intel Corporation
  */
 
 #include <linux/kernel.h>
@@ -1297,25 +1297,24 @@ void cfg80211_stop_background_radar_detection(struct wireless_dev *wdev)
 
 int cfg80211_assoc_ml_reconf(struct cfg80211_registered_device *rdev,
 			     struct net_device *dev,
-			     struct cfg80211_assoc_link *links,
-			     u16 rem_links)
+			     struct cfg80211_ml_reconf_req *req)
 {
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
 	int err;
 
 	lockdep_assert_wiphy(wdev->wiphy);
 
-	err = rdev_assoc_ml_reconf(rdev, dev, links, rem_links);
+	err = rdev_assoc_ml_reconf(rdev, dev, req);
 	if (!err) {
 		int link_id;
 
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
-			if (!links[link_id].bss)
+			if (!req->add_links[link_id].bss)
 				continue;
 
-			cfg80211_ref_bss(&rdev->wiphy, links[link_id].bss);
-			cfg80211_hold_bss(bss_from_pub(links[link_id].bss));
+			cfg80211_ref_bss(&rdev->wiphy, req->add_links[link_id].bss);
+			cfg80211_hold_bss(bss_from_pub(req->add_links[link_id].bss));
 		}
 	}
 
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 2c4e06610a791..fe706f70ac7ec 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #include <linux/if.h>
@@ -16488,9 +16488,9 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 	struct cfg80211_registered_device *rdev = info->user_ptr[0];
 	struct net_device *dev = info->user_ptr[1];
 	struct wireless_dev *wdev = dev->ieee80211_ptr;
-	struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS] = {};
+	struct cfg80211_ml_reconf_req req = {};
 	unsigned int link_id;
-	u16 add_links, rem_links;
+	u16 add_links;
 	int err;
 
 	if (!wdev->valid_links)
@@ -16506,39 +16506,37 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 
 	add_links = 0;
 	if (info->attrs[NL80211_ATTR_MLO_LINKS]) {
-		err = nl80211_process_links(rdev, links, NULL, 0, info);
+		err = nl80211_process_links(rdev, req.add_links, NULL, 0, info);
 		if (err)
 			return err;
 
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
-			if (!links[link_id].bss)
+			if (!req.add_links[link_id].bss)
 				continue;
 			add_links |= BIT(link_id);
 		}
 	}
 
 	if (info->attrs[NL80211_ATTR_MLO_RECONF_REM_LINKS])
-		rem_links =
+		req.rem_links =
 			nla_get_u16(info->attrs[NL80211_ATTR_MLO_RECONF_REM_LINKS]);
-	else
-		rem_links = 0;
 
 	/* Validate that existing links are not added, removed links are valid
 	 * and don't allow adding and removing the same links
 	 */
-	if ((add_links & rem_links) || !(add_links | rem_links) ||
+	if ((add_links & req.rem_links) || !(add_links | req.rem_links) ||
 	    (wdev->valid_links & add_links) ||
-	    ((wdev->valid_links & rem_links) != rem_links)) {
+	    ((wdev->valid_links & req.rem_links) != req.rem_links)) {
 		err = -EINVAL;
 		goto out;
 	}
 
-	err = cfg80211_assoc_ml_reconf(rdev, dev, links, rem_links);
+	err = cfg80211_assoc_ml_reconf(rdev, dev, &req);
 
 out:
-	for (link_id = 0; link_id < ARRAY_SIZE(links); link_id++)
-		cfg80211_put_bss(&rdev->wiphy, links[link_id].bss);
+	for (link_id = 0; link_id < ARRAY_SIZE(req.add_links); link_id++)
+		cfg80211_put_bss(&rdev->wiphy, req.add_links[link_id].bss);
 
 	return err;
 }
diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h
index 759da16233428..9f4783c2354c9 100644
--- a/net/wireless/rdev-ops.h
+++ b/net/wireless/rdev-ops.h
@@ -2,7 +2,7 @@
 /*
  * Portions of this file
  * Copyright(c) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018, 2021-2024 Intel Corporation
+ * Copyright (C) 2018, 2021-2025 Intel Corporation
  */
 #ifndef __CFG80211_RDEV_OPS
 #define __CFG80211_RDEV_OPS
@@ -1551,16 +1551,14 @@ rdev_get_radio_mask(struct cfg80211_registered_device *rdev,
 static inline int
 rdev_assoc_ml_reconf(struct cfg80211_registered_device *rdev,
 		     struct net_device *dev,
-		     struct cfg80211_assoc_link *add_links,
-		     u16 rem_links)
+		     struct cfg80211_ml_reconf_req *req)
 {
 	struct wiphy *wiphy = &rdev->wiphy;
 	int ret = -EOPNOTSUPP;
 
-	trace_rdev_assoc_ml_reconf(wiphy, dev, add_links, rem_links);
+	trace_rdev_assoc_ml_reconf(wiphy, dev, req);
 	if (rdev->ops->assoc_ml_reconf)
-		ret = rdev->ops->assoc_ml_reconf(wiphy, dev, add_links,
-						 rem_links);
+		ret = rdev->ops->assoc_ml_reconf(wiphy, dev, req);
 	trace_rdev_return_int(wiphy, ret);
 
 	return ret;
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index 9aa8081ca454f..b82dc7282c209 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -2,7 +2,7 @@
 /*
  * Portions of this file
  * Copyright(c) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2018, 2020-2024 Intel Corporation
+ * Copyright (C) 2018, 2020-2025 Intel Corporation
  */
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM cfg80211
@@ -4142,9 +4142,8 @@ TRACE_EVENT(cfg80211_mlo_reconf_add_done,
 
 TRACE_EVENT(rdev_assoc_ml_reconf,
 	TP_PROTO(struct wiphy *wiphy, struct net_device *netdev,
-		 struct cfg80211_assoc_link *add_links,
-		 u16 rem_links),
-	TP_ARGS(wiphy, netdev, add_links, rem_links),
+		 struct cfg80211_ml_reconf_req *req),
+	TP_ARGS(wiphy, netdev, req),
 	TP_STRUCT__entry(
 		WIPHY_ENTRY
 		NETDEV_ENTRY
@@ -4157,9 +4156,9 @@ TRACE_EVENT(rdev_assoc_ml_reconf,
 		u32 i;
 
 		__entry->add_links = 0;
-		__entry->rem_links = rem_links;
-		for (i = 0; add_links && i < IEEE80211_MLD_MAX_NUM_LINKS; i++)
-			if (add_links[i].bss)
+		__entry->rem_links = req->rem_links;
+		for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++)
+			if (req->add_links[i].bss)
 				__entry->add_links |= BIT(i);
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", add_links=0x%x, rem_links=0x%x",

From 969241371f06507f922633e42a4c1a8ce00f220e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:28 +0200
Subject: [PATCH 1945/2753] wifi: cfg80211: allow setting extended MLD capa/ops

Some extended MLD capabilities and operations bits (currently
the "BTM MLD Recommendataion For Multiple APs Support" bit)
may depend on userspace capabilities. Allow userspace to pass
the values for this field that it supports to the association
and link reconfiguration operations.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Link: https://patch.msgid.link/20250308225541.bd52078b5f65.I4dd8f53b0030db7ea87a2e0920989e7e2c7b5345@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  6 ++++++
 include/uapi/linux/nl80211.h | 10 +++++++++-
 net/wireless/nl80211.c       | 12 ++++++++++++
 net/wireless/trace.h         |  4 ++++
 4 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c7cfef104896f..29b9cf0fe6c81 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3086,10 +3086,13 @@ struct cfg80211_assoc_link {
  * struct cfg80211_ml_reconf_req - MLO link reconfiguration request
  * @add_links: data for links to add, see &struct cfg80211_assoc_link
  * @rem_links: bitmap of links to remove
+ * @ext_mld_capa_ops: extended MLD capabilities and operations set by
+ *	userspace for the ML reconfiguration action frame
  */
 struct cfg80211_ml_reconf_req {
 	struct cfg80211_assoc_link add_links[IEEE80211_MLD_MAX_NUM_LINKS];
 	u16 rem_links;
+	u16 ext_mld_capa_ops;
 };
 
 /**
@@ -3164,6 +3167,8 @@ enum cfg80211_assoc_req_flags {
  *	the link on which the association request should be sent
  * @ap_mld_addr: AP MLD address in case of MLO association request,
  *	valid iff @link_id >= 0
+ * @ext_mld_capa_ops: extended MLD capabilities and operations set by
+ *	userspace for the association
  */
 struct cfg80211_assoc_request {
 	struct cfg80211_bss *bss;
@@ -3184,6 +3189,7 @@ struct cfg80211_assoc_request {
 	struct cfg80211_assoc_link links[IEEE80211_MLD_MAX_NUM_LINKS];
 	const u8 *ap_mld_addr;
 	s8 link_id;
+	u16 ext_mld_capa_ops;
 };
 
 /**
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 9d8ecf20ef0d4..c59075acdb104 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -11,7 +11,7 @@
  * Copyright 2008 Jouni Malinen <jouni.malinen@atheros.com>
  * Copyright 2008 Colin McCabe <colin@cozybit.com>
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -2893,6 +2893,12 @@ enum nl80211_commands {
  * @NL80211_ATTR_EPCS: Flag attribute indicating that EPCS is enabled for a
  *	station interface.
  *
+ * @NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS: Extended MLD capabilities and
+ *	operations that userspace implements to use during association/ML
+ *	link reconfig, currently only "BTM MLD Recommendation For Multiple
+ *	APs Support". Drivers may set additional flags that they support
+ *	in the kernel or device.
+ *
  * @NUM_NL80211_ATTR: total number of nl80211_attrs available
  * @NL80211_ATTR_MAX: highest attribute number currently defined
  * @__NL80211_ATTR_AFTER_LAST: internal use
@@ -3448,6 +3454,8 @@ enum nl80211_attrs {
 	NL80211_ATTR_MLO_RECONF_REM_LINKS,
 	NL80211_ATTR_EPCS,
 
+	NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS,
+
 	/* add attributes here, update the policy in nl80211.c */
 
 	__NL80211_ATTR_AFTER_LAST,
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index fe706f70ac7ec..e2e8c368fbbf9 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -850,6 +850,7 @@ static const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = {
 				       NL80211_MAX_SUPP_SELECTORS),
 	[NL80211_ATTR_MLO_RECONF_REM_LINKS] = { .type = NLA_U16 },
 	[NL80211_ATTR_EPCS] = { .type = NLA_FLAG },
+	[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS] = { .type = NLA_U16 },
 };
 
 /* policy for the key attributes */
@@ -11373,6 +11374,10 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 			err = -EINVAL;
 			goto free;
 		}
+
+		if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS])
+			req.ext_mld_capa_ops =
+				nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]);
 	} else {
 		if (req.link_id >= 0)
 			return -EINVAL;
@@ -11382,6 +11387,9 @@ static int nl80211_associate(struct sk_buff *skb, struct genl_info *info)
 		if (IS_ERR(req.bss))
 			return PTR_ERR(req.bss);
 		ap_addr = req.bss->bssid;
+
+		if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS])
+			return -EINVAL;
 	}
 
 	err = nl80211_crypto_settings(rdev, info, &req.crypto, 1);
@@ -16532,6 +16540,10 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 		goto out;
 	}
 
+	if (info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS])
+		req.ext_mld_capa_ops =
+			nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]);
+
 	err = cfg80211_assoc_ml_reconf(rdev, dev, &req);
 
 out:
diff --git a/net/wireless/trace.h b/net/wireless/trace.h
index b82dc7282c209..4ed9fada4ec0e 100644
--- a/net/wireless/trace.h
+++ b/net/wireless/trace.h
@@ -1378,6 +1378,7 @@ TRACE_EVENT(rdev_assoc,
 		__dynamic_array(u8, fils_kek, req->fils_kek_len)
 		__dynamic_array(u8, fils_nonces,
 				req->fils_nonces ? 2 * FILS_NONCE_LEN : 0)
+		__field(u16, ext_mld_capa_ops)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
@@ -1404,6 +1405,7 @@ TRACE_EVENT(rdev_assoc,
 		if (req->fils_nonces)
 			memcpy(__get_dynamic_array(fils_nonces),
 			       req->fils_nonces, 2 * FILS_NONCE_LEN);
+		__entry->ext_mld_capa_ops = req->ext_mld_capa_ops;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", bssid: %pM"
 		  ", previous bssid: %pM, use mfp: %s, flags: 0x%x",
@@ -4149,6 +4151,7 @@ TRACE_EVENT(rdev_assoc_ml_reconf,
 		NETDEV_ENTRY
 		__field(u16, add_links)
 		__field(u16, rem_links)
+		__field(u16, ext_mld_capa_ops)
 	),
 	TP_fast_assign(
 		WIPHY_ASSIGN;
@@ -4160,6 +4163,7 @@ TRACE_EVENT(rdev_assoc_ml_reconf,
 		for (i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++)
 			if (req->add_links[i].bss)
 				__entry->add_links |= BIT(i);
+		__entry->ext_mld_capa_ops = req->ext_mld_capa_ops;
 	),
 	TP_printk(WIPHY_PR_FMT ", " NETDEV_PR_FMT ", add_links=0x%x, rem_links=0x%x",
 		  WIPHY_PR_ARG, NETDEV_PR_ARG,

From 96d4311c318474e2c77d9f5b6f32c3fce437aa09 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:29 +0200
Subject: [PATCH 1946/2753] wifi: mac80211: mlme: support extended MLD capa/ops
 in assoc

Support passing the value from userspace on to the AP in the
association and ML link reconfiguration requests. We may need
to also add a driver value to or in with the field, but for
now have no feature that is controlled by the driver.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.2e555beb0a76.I623f59023b47ec202fc0c7520f2b5f575b439927@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/mlme.c        | 32 ++++++++++++++++++++++++++++++--
 2 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 5f92619f8584a..a36563a07b3b0 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -462,6 +462,8 @@ struct ieee80211_mgd_assoc_data {
 
 	unsigned int assoc_link_id;
 
+	__le16 ext_mld_capa_ops;
+
 	u8 fils_nonces[2 * FILS_NONCE_LEN];
 	u8 fils_kek[FILS_MAX_KEK_LEN];
 	size_t fils_kek_len;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 613959f19713e..87ebeec2877df 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1943,6 +1943,21 @@ ieee80211_assoc_add_ml_elem(struct ieee80211_sub_if_data *sdata,
 	}
 	skb_put_data(skb, &mld_capa_ops, sizeof(mld_capa_ops));
 
+	/* Many APs have broken parsing of the extended MLD capa/ops field,
+	 * dropping (re-)association request frames or replying with association
+	 * response with a failure status if it's present. Without a clear
+	 * indication as to whether the AP supports parsing this field or not do
+	 * not include it in the common information unless strict mode is set.
+	 */
+	if (ieee80211_hw_check(&local->hw, STRICT) &&
+	    assoc_data->ext_mld_capa_ops) {
+		ml_elem->control |=
+			cpu_to_le16(IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP);
+		common->len += 2;
+		skb_put_data(skb, &assoc_data->ext_mld_capa_ops,
+			     sizeof(assoc_data->ext_mld_capa_ops));
+	}
+
 	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
 		u16 link_present_elems[PRESENT_ELEMS_MAX] = {};
 		const u8 *extra_elems;
@@ -2112,6 +2127,7 @@ static int ieee80211_send_assoc(struct ieee80211_sub_if_data *sdata)
 		/* max common info field in basic multi-link element */
 		size += sizeof(struct ieee80211_mle_basic_common_info) +
 			2 + /* capa & op */
+			2 + /* ext capa & op */
 			2; /* EML capa */
 
 		/*
@@ -9366,6 +9382,8 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 	else
 		memcpy(assoc_data->ap_addr, cbss->bssid, ETH_ALEN);
 
+	assoc_data->ext_mld_capa_ops = cpu_to_le16(req->ext_mld_capa_ops);
+
 	if (ifmgd->associated) {
 		u8 frame_buf[IEEE80211_DEAUTH_FRAME_LEN];
 
@@ -10136,7 +10154,7 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 static struct sk_buff *
 ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 			      struct ieee80211_mgd_assoc_data *add_links_data,
-			      u16 removed_links)
+			      u16 removed_links, __le16 ext_mld_capa_ops)
 {
 	struct ieee80211_local *local = sdata->local;
 	struct ieee80211_mgmt *mgmt;
@@ -10185,6 +10203,9 @@ ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 			var_common_size += 2;
 	}
 
+	if (ext_mld_capa_ops)
+		var_common_size += 2;
+
 	/* Add the common information length */
 	size += common_size + var_common_size;
 
@@ -10269,6 +10290,12 @@ ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 		skb_put_data(skb, &mld_capa_ops, sizeof(mld_capa_ops));
 	}
 
+	if (ext_mld_capa_ops) {
+		ml_elem->control |=
+			cpu_to_le16(IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP);
+		skb_put_data(skb, &ext_mld_capa_ops, sizeof(ext_mld_capa_ops));
+	}
+
 	if (sdata->u.mgd.flags & IEEE80211_STA_ENABLE_RRM)
 		capab |= WLAN_CAPABILITY_RADIO_MEASURE;
 
@@ -10535,7 +10562,8 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	 * is expected to send the ML reconfiguration response frame on the link
 	 * on which the request was received.
 	 */
-	skb = ieee80211_build_ml_reconf_req(sdata, data, req->rem_links);
+	skb = ieee80211_build_ml_reconf_req(sdata, data, req->rem_links,
+					    cpu_to_le16(req->ext_mld_capa_ops));
 	if (!skb) {
 		err = -ENOMEM;
 		goto err_free;

From cf4bd1608882792d4742e27a819493312904a680 Mon Sep 17 00:00:00 2001
From: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Sat, 8 Mar 2025 23:03:30 +0200
Subject: [PATCH 1947/2753] wifi: cfg80211: allow IR in 20 MHz configurations

Some regulatory bodies doesn't allow IR (initiate radioation) on a
specific subband, but allows it for channels with a bandwidth of 20 MHz.
Add a channel flag that indicates that, and consider it in
cfg80211_reg_check_beaconing.

While on it, fix the kernel doc of enum nl80211_reg_rule_flags and
change it to use BIT().

Signed-off-by: Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Co-developed-by: Somashekhar Puttagangaiah <somashekhar.puttagangaiah@intel.com>
Signed-off-by: Somashekhar Puttagangaiah <somashekhar.puttagangaiah@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.d3ab352a73ff.I8a8f79e1c9eb74936929463960ee2a324712fe51@changeid
[fix typo]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       |  3 +++
 include/uapi/linux/nl80211.h | 52 ++++++++++++++++++++----------------
 net/wireless/chan.c          |  8 +++++-
 net/wireless/nl80211.c       |  4 +++
 net/wireless/reg.c           |  4 ++-
 5 files changed, 46 insertions(+), 25 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 29b9cf0fe6c81..0d423830a8ed5 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -127,6 +127,8 @@ struct wiphy;
  *	even if it is otherwise disabled.
  * @IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP: Allow using this channel for AP operation
  *	with very low power (VLP), even if otherwise set to NO_IR.
+ * @IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY: Allow activity on a 20 MHz channel,
+ *	even if otherwise set to NO_IR.
  */
 enum ieee80211_channel_flags {
 	IEEE80211_CHAN_DISABLED			= BIT(0),
@@ -155,6 +157,7 @@ enum ieee80211_channel_flags {
 	IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT	= BIT(23),
 	IEEE80211_CHAN_CAN_MONITOR		= BIT(24),
 	IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP	= BIT(25),
+	IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY     = BIT(26),
 };
 
 #define IEEE80211_CHAN_NO_HT40 \
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index c59075acdb104..26cae1cc87273 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -4335,6 +4335,8 @@ enum nl80211_wmm_rule {
  *	otherwise completely disabled.
  * @NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP: This channel can be used for a
  *	very low power (VLP) AP, despite being NO_IR.
+ * @NL80211_FREQUENCY_ATTR_ALLOW_20MHZ_ACTIVITY: This channel can be active in
+ *	20 MHz bandwidth, despite being NO_IR.
  * @NL80211_FREQUENCY_ATTR_MAX: highest frequency attribute number
  *	currently defined
  * @__NL80211_FREQUENCY_ATTR_AFTER_LAST: internal use
@@ -4379,6 +4381,7 @@ enum nl80211_frequency_attr {
 	NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT,
 	NL80211_FREQUENCY_ATTR_CAN_MONITOR,
 	NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP,
+	NL80211_FREQUENCY_ATTR_ALLOW_20MHZ_ACTIVITY,
 
 	/* keep last */
 	__NL80211_FREQUENCY_ATTR_AFTER_LAST,
@@ -4590,31 +4593,34 @@ enum nl80211_sched_scan_match_attr {
  * @NL80211_RRF_NO_6GHZ_AFC_CLIENT: Client connection to AFC AP not allowed
  * @NL80211_RRF_ALLOW_6GHZ_VLP_AP: Very low power (VLP) AP can be permitted
  *	despite NO_IR configuration.
+ * @NL80211_RRF_ALLOW_20MHZ_ACTIVITY: Allow activity in 20 MHz bandwidth,
+ *	despite NO_IR configuration.
  */
 enum nl80211_reg_rule_flags {
-	NL80211_RRF_NO_OFDM		= 1<<0,
-	NL80211_RRF_NO_CCK		= 1<<1,
-	NL80211_RRF_NO_INDOOR		= 1<<2,
-	NL80211_RRF_NO_OUTDOOR		= 1<<3,
-	NL80211_RRF_DFS			= 1<<4,
-	NL80211_RRF_PTP_ONLY		= 1<<5,
-	NL80211_RRF_PTMP_ONLY		= 1<<6,
-	NL80211_RRF_NO_IR		= 1<<7,
-	__NL80211_RRF_NO_IBSS		= 1<<8,
-	NL80211_RRF_AUTO_BW		= 1<<11,
-	NL80211_RRF_IR_CONCURRENT	= 1<<12,
-	NL80211_RRF_NO_HT40MINUS	= 1<<13,
-	NL80211_RRF_NO_HT40PLUS		= 1<<14,
-	NL80211_RRF_NO_80MHZ		= 1<<15,
-	NL80211_RRF_NO_160MHZ		= 1<<16,
-	NL80211_RRF_NO_HE		= 1<<17,
-	NL80211_RRF_NO_320MHZ		= 1<<18,
-	NL80211_RRF_NO_EHT		= 1<<19,
-	NL80211_RRF_PSD			= 1<<20,
-	NL80211_RRF_DFS_CONCURRENT	= 1<<21,
-	NL80211_RRF_NO_6GHZ_VLP_CLIENT	= 1<<22,
-	NL80211_RRF_NO_6GHZ_AFC_CLIENT	= 1<<23,
-	NL80211_RRF_ALLOW_6GHZ_VLP_AP	= 1<<24,
+	NL80211_RRF_NO_OFDM                 = 1 << 0,
+	NL80211_RRF_NO_CCK                  = 1 << 1,
+	NL80211_RRF_NO_INDOOR               = 1 << 2,
+	NL80211_RRF_NO_OUTDOOR              = 1 << 3,
+	NL80211_RRF_DFS                     = 1 << 4,
+	NL80211_RRF_PTP_ONLY                = 1 << 5,
+	NL80211_RRF_PTMP_ONLY               = 1 << 6,
+	NL80211_RRF_NO_IR                   = 1 << 7,
+	__NL80211_RRF_NO_IBSS               = 1 << 8,
+	NL80211_RRF_AUTO_BW                 = 1 << 11,
+	NL80211_RRF_IR_CONCURRENT           = 1 << 12,
+	NL80211_RRF_NO_HT40MINUS            = 1 << 13,
+	NL80211_RRF_NO_HT40PLUS             = 1 << 14,
+	NL80211_RRF_NO_80MHZ                = 1 << 15,
+	NL80211_RRF_NO_160MHZ               = 1 << 16,
+	NL80211_RRF_NO_HE                   = 1 << 17,
+	NL80211_RRF_NO_320MHZ               = 1 << 18,
+	NL80211_RRF_NO_EHT                  = 1 << 19,
+	NL80211_RRF_PSD                     = 1 << 20,
+	NL80211_RRF_DFS_CONCURRENT          = 1 << 21,
+	NL80211_RRF_NO_6GHZ_VLP_CLIENT      = 1 << 22,
+	NL80211_RRF_NO_6GHZ_AFC_CLIENT      = 1 << 23,
+	NL80211_RRF_ALLOW_6GHZ_VLP_AP       = 1 << 24,
+	NL80211_RRF_ALLOW_20MHZ_ACTIVITY    = 1 << 25,
 };
 
 #define NL80211_RRF_PASSIVE_SCAN	NL80211_RRF_NO_IR
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 9f918b77b40e2..4cdb74a3f38c6 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -6,7 +6,7 @@
  *
  * Copyright 2009	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
- * Copyright 2018-2024	Intel Corporation
+ * Copyright 2018-2025	Intel Corporation
  */
 
 #include <linux/export.h>
@@ -1497,6 +1497,12 @@ bool cfg80211_reg_check_beaconing(struct wiphy *wiphy,
 	if (cfg->reg_power == IEEE80211_REG_VLP_AP)
 		permitting_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP;
 
+	if ((cfg->iftype == NL80211_IFTYPE_P2P_GO ||
+	     cfg->iftype == NL80211_IFTYPE_AP) &&
+	    (chandef->width == NL80211_CHAN_WIDTH_20_NOHT ||
+	     chandef->width == NL80211_CHAN_WIDTH_20))
+		permitting_flags |= IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY;
+
 	return _cfg80211_reg_can_beacon(wiphy, chandef, cfg->iftype,
 					check_no_ir ? IEEE80211_CHAN_NO_IR : 0,
 					permitting_flags);
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index e2e8c368fbbf9..aee49d43cf862 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -1235,6 +1235,10 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
 		if ((chan->flags & IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP) &&
 		    nla_put_flag(msg, NL80211_FREQUENCY_ATTR_ALLOW_6GHZ_VLP_AP))
 			goto nla_put_failure;
+		if ((chan->flags & IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY) &&
+		    nla_put_flag(msg,
+				 NL80211_FREQUENCY_ATTR_ALLOW_20MHZ_ACTIVITY))
+			goto nla_put_failure;
 	}
 
 	if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
diff --git a/net/wireless/reg.c b/net/wireless/reg.c
index 2dd0533e76605..9314f7fcd54bb 100644
--- a/net/wireless/reg.c
+++ b/net/wireless/reg.c
@@ -5,7 +5,7 @@
  * Copyright 2008-2011	Luis R. Rodriguez <mcgrof@qca.qualcomm.com>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright      2017  Intel Deutschland GmbH
- * Copyright (C) 2018 - 2024 Intel Corporation
+ * Copyright (C) 2018 - 2025 Intel Corporation
  *
  * Permission to use, copy, modify, and/or distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
@@ -1602,6 +1602,8 @@ static u32 map_regdom_flags(u32 rd_flags)
 		channel_flags |= IEEE80211_CHAN_PSD;
 	if (rd_flags & NL80211_RRF_ALLOW_6GHZ_VLP_AP)
 		channel_flags |= IEEE80211_CHAN_ALLOW_6GHZ_VLP_AP;
+	if (rd_flags & NL80211_RRF_ALLOW_20MHZ_ACTIVITY)
+		channel_flags |= IEEE80211_CHAN_ALLOW_20MHZ_ACTIVITY;
 	return channel_flags;
 }
 

From 7a6a740be17e049a2742c76bb1dadb3d78c930d9 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:31 +0200
Subject: [PATCH 1948/2753] wifi: mac80211: fix U-APSD check in ML
 reconfiguration

If U-APSD isn't enabled by us, then IEEE80211_STA_UAPSD_ENABLED
won't be set, but the AP can still support it in that case. Only
require U-APSD from the AP if we enabled it, don't require it to
be disabled on the AP if we didn't.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.b4674be12a38.I01959e448c6a2a3e8bc5d561bbae9e8d2cca616a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 87ebeec2877df..426c0246fe1fe 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10492,12 +10492,11 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 			}
 		}
 
-		/* Require U-APSD support to be similar to the current valid
-		 * links
-		 */
-		if (uapsd_supported !=
-		    !!(sdata->u.mgd.flags & IEEE80211_STA_UAPSD_ENABLED)) {
+		/* Require U-APSD support if we enabled it */
+		if (sdata->u.mgd.flags & IEEE80211_STA_UAPSD_ENABLED &&
+		    !uapsd_supported) {
 			err = -EINVAL;
+			sdata_info(sdata, "U-APSD on but not available on (all) new links\n");
 			goto err_free;
 		}
 

From cf12d3d71e72330b2c0bba467cc5bdea2232347e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:32 +0200
Subject: [PATCH 1949/2753] wifi: cfg80211: improve supported_selector
 documentation

Improve the documentation for supported BSS selectors to make it more
precise.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.ba402ff47314.I502b56111b62ea0be174ae76bd03684ae1d4aefb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h       | 4 ++--
 include/uapi/linux/nl80211.h | 6 +++---
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 0d423830a8ed5..c61894c1265a1 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -3148,10 +3148,10 @@ enum cfg80211_assoc_req_flags {
  *	included in the Current AP address field of the Reassociation Request
  *	frame.
  * @flags:  See &enum cfg80211_assoc_req_flags
- * @supported_selectors: supported selectors in IEEE 802.11 format
+ * @supported_selectors: supported BSS selectors in IEEE 802.11 format
  *	(or %NULL for no change).
  *	If %NULL, then support for SAE_H2E should be assumed.
- * @supported_selectors_len: Length of supported_selectors in octets.
+ * @supported_selectors_len: number of supported BSS selectors
  * @ht_capa:  HT Capabilities over-rides.  Values set in ht_capa_mask
  *	will be used in ht_capa.  Un-supported values will be ignored.
  * @ht_capa_mask:  The bits of ht_capa which are to be used.
diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h
index 26cae1cc87273..ddcc4cda74af5 100644
--- a/include/uapi/linux/nl80211.h
+++ b/include/uapi/linux/nl80211.h
@@ -2881,9 +2881,9 @@ enum nl80211_commands {
  * @NL80211_ATTR_VIF_RADIO_MASK: Bitmask of allowed radios (u32).
  *	A value of 0 means all radios.
  *
- * @NL80211_ATTR_SUPPORTED_SELECTORS: supported selectors, array of
- *	supported selectors as defined by IEEE 802.11 7.3.2.2 but without the
- *	length restriction (at most %NL80211_MAX_SUPP_SELECTORS).
+ * @NL80211_ATTR_SUPPORTED_SELECTORS: supported BSS Membership Selectors, array
+ *	of supported selectors as defined by IEEE Std 802.11-2020 9.4.2.3 but
+ *	without the length restriction (at most %NL80211_MAX_SUPP_SELECTORS).
  *	This can be used to provide a list of selectors that are implemented
  *	by the supplicant. If not given, support for SAE_H2E is assumed.
  *

From db97bb04c66d4d068be3fca5e28fb5de0301399d Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Sat, 8 Mar 2025 23:03:33 +0200
Subject: [PATCH 1950/2753] wifi: mac80211: allow 320 MHz FTM measurements

Add 320 MHz to the list of allowed bandwidths for FTM measurements.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.91f4cbe66817.I9205c585fca6a54a2c5a9e4db98c7781bd1fc4e1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 15bbc9d06c9e9..52728527c6f52 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -5,7 +5,7 @@
  * Copyright 2006-2010		Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2015-2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -793,6 +793,7 @@ int wiphy_register(struct wiphy *wiphy)
 				  BIT(NL80211_CHAN_WIDTH_80) |
 				  BIT(NL80211_CHAN_WIDTH_80P80) |
 				  BIT(NL80211_CHAN_WIDTH_160) |
+				  BIT(NL80211_CHAN_WIDTH_320) |
 				  BIT(NL80211_CHAN_WIDTH_5) |
 				  BIT(NL80211_CHAN_WIDTH_10))))
 			return -EINVAL;

From 65bff0be9b154621b617fc2e4bd89f1e18e97cdb Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sat, 8 Mar 2025 23:03:34 +0200
Subject: [PATCH 1951/2753] wifi: mac80211_hwsim: Fix MLD address translation

Do address translations only between shared links. It is
possible that while an non-AP MLD station and an AP MLD
station have shared links, the frame is intended to be sent
on a link which is not shared (for example when sending a
probe response).

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.1aa461270bb6.Ic21592e1b1634653f02b80628cb2152f6e9de367@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/mac80211_hwsim.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/virtual/mac80211_hwsim.c b/drivers/net/wireless/virtual/mac80211_hwsim.c
index d0d9dab7f11fa..b426f3bfab281 100644
--- a/drivers/net/wireless/virtual/mac80211_hwsim.c
+++ b/drivers/net/wireless/virtual/mac80211_hwsim.c
@@ -4,7 +4,7 @@
  * Copyright (c) 2008, Jouni Malinen <j@w1.fi>
  * Copyright (c) 2011, Javier Lopez <jlopex@gmail.com>
  * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (C) 2018 - 2024 Intel Corporation
+ * Copyright (C) 2018 - 2025 Intel Corporation
  */
 
 /*
@@ -1983,11 +1983,13 @@ static void mac80211_hwsim_tx(struct ieee80211_hw *hw,
 			return;
 		}
 
-		if (sta && sta->mlo) {
-			if (WARN_ON(!link_sta)) {
-				ieee80211_free_txskb(hw, skb);
-				return;
-			}
+		/* Do address translations only between shared links. It is
+		 * possible that while an non-AP MLD station and an AP MLD
+		 * station have shared links, the frame is intended to be sent
+		 * on a link which is not shared (for example when sending a
+		 * probe response).
+		 */
+		if (sta && sta->mlo && link_sta) {
 			/* address translation to link addresses on TX */
 			ether_addr_copy(hdr->addr1, link_sta->addr);
 			ether_addr_copy(hdr->addr2, bss_conf->addr);

From 700014d3ad1fd6e55c8f9ffa817514d3fbb5286e Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:35 +0200
Subject: [PATCH 1952/2753] wifi: mac80211: fix userspace_selectors corruption

Spotted during code review, the selectors need to be large
enough for a 128-bit bitmap, not a single unsigned long,
otherwise we have stack corruption.

We should also allow passing selectors from userspace, but
that should be a separate change.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.8f1bcf96a504.Ibeb8970c82a30c97279a4cc4e68faca5df1813a5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 14 ++++++--------
 1 file changed, 6 insertions(+), 8 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 426c0246fe1fe..85ae661976741 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -9914,8 +9914,6 @@ EXPORT_SYMBOL(ieee80211_disable_rssi_reports);
 
 static void ieee80211_ml_reconf_selectors(unsigned long *userspace_selectors)
 {
-	*userspace_selectors = 0;
-
 	/* these selectors are mandatory for ML reconfiguration */
 	set_bit(BSS_MEMBERSHIP_SELECTOR_SAE_H2E, userspace_selectors);
 	set_bit(BSS_MEMBERSHIP_SELECTOR_HE_PHY, userspace_selectors);
@@ -9935,7 +9933,7 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 		                sdata->u.mgd.reconf.removed_links;
 	u16 link_mask, valid_links;
 	unsigned int link_id;
-	unsigned long userspace_selectors;
+	unsigned long userspace_selectors[BITS_TO_LONGS(128)] = {};
 	size_t orig_len = len;
 	u8 i, group_key_data_len;
 	u8 *pos;
@@ -10043,7 +10041,7 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ieee80211_vif_set_links(sdata, valid_links, sdata->vif.dormant_links);
-	ieee80211_ml_reconf_selectors(&userspace_selectors);
+	ieee80211_ml_reconf_selectors(userspace_selectors);
 	link_mask = 0;
 	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
 		struct cfg80211_bss *cbss = add_links_data->link[link_id].bss;
@@ -10089,7 +10087,7 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 		link->u.mgd.conn = add_links_data->link[link_id].conn;
 		if (ieee80211_prep_channel(sdata, link, link_id, cbss,
 					   true, &link->u.mgd.conn,
-					   &userspace_selectors)) {
+					   userspace_selectors)) {
 			link_info(link, "mlo: reconf: prep_channel failed\n");
 			goto disconnect;
 		}
@@ -10427,14 +10425,14 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	 */
 	if (added_links) {
 		bool uapsd_supported;
-		unsigned long userspace_selectors;
+		unsigned long userspace_selectors[BITS_TO_LONGS(128)] = {};
 
 		data = kzalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
 			return -ENOMEM;
 
 		uapsd_supported = true;
-		ieee80211_ml_reconf_selectors(&userspace_selectors);
+		ieee80211_ml_reconf_selectors(userspace_selectors);
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
 			struct ieee80211_supported_band *sband;
@@ -10510,7 +10508,7 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 						     data->link[link_id].bss,
 						     true,
 						     &data->link[link_id].conn,
-						     &userspace_selectors);
+						     userspace_selectors);
 			if (err)
 				goto err_free;
 		}

From 0e104aa3676d020f6c442cd7fbaeb72adaaab6fc Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:36 +0200
Subject: [PATCH 1953/2753] wifi: mac80211: fix warning on disconnect during
 failed ML reconf

If multi-link reconfiguration fails, we can disconnect with a local link
already allocated but the BSS entry not assigned yet, which leads to a
warning in cfg80211. Add a check to avoid the warning.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.699bd9cbabe5.I599d5ff69092a65e916e2acd25137ae9df8debe8@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 85ae661976741..f3bf66d4ce6af 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4466,7 +4466,7 @@ static void __ieee80211_disconnect(struct ieee80211_sub_if_data *sdata)
 			struct ieee80211_link_data *link;
 
 			link = sdata_dereference(sdata->link[link_id], sdata);
-			if (!link)
+			if (!link || !link->conf->bss)
 				continue;
 			cfg80211_unlink_bss(local->hw.wiphy, link->conf->bss);
 			link->conf->bss = NULL;

From e16caea70610ed4226034dfcdaa5c43b36ff9e0a Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sat, 8 Mar 2025 23:03:37 +0200
Subject: [PATCH 1954/2753] wifi: cfg80211: Update the link address when a link
 is added

When links are added, update the wireless device link addresses based
on the information provided by the driver.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.d694a9125aba.I79b010ea9aab47893e4f22c266362fde30b7f9ac@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 1 +
 net/wireless/mlme.c    | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index c61894c1265a1..73f0e75cc8147 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -9770,6 +9770,7 @@ struct cfg80211_mlo_reconf_done_data {
 	u16 added_links;
 	struct {
 		struct cfg80211_bss *bss;
+		u8 *addr;
 	} links[IEEE80211_MLD_MAX_NUM_LINKS];
 };
 
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 956d33b219df1..05d44a4435189 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -1360,6 +1360,10 @@ void cfg80211_mlo_reconf_add_done(struct net_device *dev,
 		if (data->added_links & BIT(link_id)) {
 			wdev->links[link_id].client.current_bss =
 				bss_from_pub(bss);
+
+			memcpy(wdev->links[link_id].addr,
+			       data->links[link_id].addr,
+			       ETH_ALEN);
 		} else {
 			cfg80211_unhold_bss(bss_from_pub(bss));
 			cfg80211_put_bss(wiphy, bss);

From 2160998ded514404140617286dd53a35983e5090 Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sat, 8 Mar 2025 23:03:38 +0200
Subject: [PATCH 1955/2753] wifi: mac80211: Notify cfg80211 about added link
 addresses

When ML reconfiguration is done and new links are added, update
cfg80211 with the addresses of the newly added links.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.0c6bf8b1bef3.I2aa16801f07321a580dd7dce4a074a3486f627f1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index f3bf66d4ce6af..60a585caa96de 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10135,8 +10135,11 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 	done_data.len = orig_len;
 	done_data.added_links = link_mask;
 
-	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++)
+	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
 		done_data.links[link_id].bss = add_links_data->link[link_id].bss;
+		done_data.links[link_id].addr =
+			add_links_data->link[link_id].addr;
+	}
 
 	cfg80211_mlo_reconf_add_done(sdata->dev, &done_data);
 	kfree(sdata->u.mgd.reconf.add_links_data);

From 82306ea157ad5d1dc8126f81a989e61bf1001c0d Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:39 +0200
Subject: [PATCH 1956/2753] wifi: mac80211: fix ML reconf reset in disconnect

If disconnecting while ML reconfiguration is in progress,
the data isn't freed because the reset call is too late,
after the vif already switches to non-MLD. Move the call
to fix that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.abaea69cde42.I7e6b35731ded94fc2d68a2d4ecf81873712c268e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 60a585caa96de..9c4d4f04b23eb 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4152,16 +4152,16 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 	wiphy_work_cancel(sdata->local->hw.wiphy,
 			  &ifmgd->teardown_ttlm_work);
 
-	ieee80211_vif_set_links(sdata, 0, 0);
-
-	ifmgd->mcast_seq_last = IEEE80211_SN_MODULO;
-
 	/* if disconnection happens in the middle of the ML reconfiguration
 	 * flow, cfg80211 must called to release the BSS references obtained
 	 * when the flow started.
 	 */
 	ieee80211_ml_reconf_reset(sdata);
 
+	ieee80211_vif_set_links(sdata, 0, 0);
+
+	ifmgd->mcast_seq_last = IEEE80211_SN_MODULO;
+
 	ifmgd->epcs.enabled = false;
 	ifmgd->epcs.dialog_token = 0;
 }

From c3171bed65ec323803b6b73f74017f7d0fd7aa6c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:40 +0200
Subject: [PATCH 1957/2753] wifi: mac80211: don't include MLE in ML reconf
 per-STA profile

In the multi-link reconfiguration frame, the per-STA profile for
added links shouldn't include the multi-link element. Set the
association ID to an invalid value, so it doesn't erroneously
match the link ID if that happens to be zero.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.8e5be244c70f.I3472cd5c347814ee3600869a88488997bcd43224@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h | 2 +-
 net/mac80211/mlme.c        | 2 ++
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index a36563a07b3b0..217e949bb756c 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -460,7 +460,7 @@ struct ieee80211_mgd_assoc_data {
 	bool s1g;
 	bool spp_amsdu;
 
-	unsigned int assoc_link_id;
+	s8 assoc_link_id;
 
 	__le16 ext_mld_capa_ops;
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 9c4d4f04b23eb..94d9d9ca42fee 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10434,6 +10434,8 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 		if (!data)
 			return -ENOMEM;
 
+		data->assoc_link_id = -1;
+
 		uapsd_supported = true;
 		ieee80211_ml_reconf_selectors(userspace_selectors);
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;

From ff4d8998e84dcf52ba74716ab0512217eace6734 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:03:41 +0200
Subject: [PATCH 1958/2753] wifi: mac80211: set WMM in ML reconfiguration

In the per-STA profiles for added links in multi-link reconfiguration
the WMM element should be included. Fix that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308225541.59902f783420.I362c3101d3f523a8db37c16cd7b5f573d76a36e6@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 94d9d9ca42fee..bfd3653a5b847 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10435,6 +10435,7 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 			return -ENOMEM;
 
 		data->assoc_link_id = -1;
+		data->wmm = true;
 
 		uapsd_supported = true;
 		ieee80211_ml_reconf_selectors(userspace_selectors);

From 16a8d9a739430bec9c11eda69226c5a39f3478aa Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sat, 8 Mar 2025 23:19:12 +0200
Subject: [PATCH 1959/2753] wifi: iwlwifi: add support for BE213

Add the BE213 device. This is just like BE211 but with a limitation on
the bandwidth.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231426.f02f4d7fc73b.Idaf000dd311358e3b50a511f4efc1cc720abd58b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c   |  2 ++
 .../net/wireless/intel/iwlwifi/iwl-config.h   |  1 +
 .../wireless/intel/iwlwifi/iwl-nvm-parse.c    | 12 +++++++----
 drivers/net/wireless/intel/iwlwifi/pcie/drv.c | 21 ++++++++++++++++---
 4 files changed, 29 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index eb56af9a8411b..05cbb80ab575c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -142,6 +142,8 @@ const struct iwl_cfg_trans_params iwl_sc_trans_cfg = {
 	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
+const char iwl_sp_name[] = "Intel(R) Wi-Fi 7 BE213 160MHz";
+
 const struct iwl_cfg iwl_cfg_sc = {
 	.fw_name_mac = "sc",
 	IWL_DEVICE_SC,
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
index 7e4864c00780b..b9bd89bfdd748 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
@@ -550,6 +550,7 @@ extern const char iwl_ax231_name[];
 extern const char iwl_ax411_name[];
 extern const char iwl_fm_name[];
 extern const char iwl_wh_name[];
+extern const char iwl_sp_name[];
 extern const char iwl_gl_name[];
 extern const char iwl_mtp_name[];
 extern const char iwl_dr_name[];
diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
index 08269168b2fab..cd1b0048bb6da 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-nvm-parse.c
@@ -944,7 +944,8 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 				       IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK);
 		break;
 	case NL80211_BAND_6GHZ:
-		if (!trans->reduced_cap_sku) {
+		if (!trans->reduced_cap_sku &&
+		    trans->bw_limit >= 320) {
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[0] |=
 				IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
 			iftype_data->eht_cap.eht_cap_elem.phy_cap_info[1] |=
@@ -1098,15 +1099,18 @@ iwl_nvm_fixup_sband_iftd(struct iwl_trans *trans,
 		iftype_data->he_cap.he_cap_elem.phy_cap_info[0] &=
 			~IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G;
 
-	if (trans->reduced_cap_sku) {
+	if (trans->bw_limit < 320 || trans->reduced_cap_sku) {
 		memset(&iftype_data->eht_cap.eht_mcs_nss_supp.bw._320, 0,
 		       sizeof(iftype_data->eht_cap.eht_mcs_nss_supp.bw._320));
+		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
+			~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
+	}
+
+	if (trans->reduced_cap_sku) {
 		iftype_data->eht_cap.eht_mcs_nss_supp.bw._80.rx_tx_mcs13_max_nss = 0;
 		iftype_data->eht_cap.eht_mcs_nss_supp.bw._160.rx_tx_mcs13_max_nss = 0;
 		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[8] &=
 			~IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA;
-		iftype_data->eht_cap.eht_cap_elem.phy_cap_info[2] &=
-			~IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK;
 	}
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
index 03f7eb46bbc78..93446c3740081 100644
--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
@@ -1187,8 +1187,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc, iwl_wh_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
+		      160, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc, iwl_sp_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
@@ -1202,8 +1207,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc2, iwl_wh_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
+		      160, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2, iwl_sp_name),
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_GF, IWL_CFG_ANY, IWL_CFG_ANY,
@@ -1217,8 +1227,13 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct iwl_dev_info iwl_dev_info_table[] = {
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
 		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
 		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
-		      IWL_CFG_BW_ANY, IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_BW_NO_LIM, IWL_CFG_ANY, IWL_CFG_ANY,
 		      iwl_cfg_sc2f, iwl_wh_name),
+	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,
+		      IWL_CFG_MAC_TYPE_SC2F, IWL_CFG_ANY,
+		      IWL_CFG_RF_TYPE_WH, IWL_CFG_ANY, IWL_CFG_ANY,
+		      160, IWL_CFG_ANY, IWL_CFG_ANY,
+		      iwl_cfg_sc2f, iwl_sp_name),
 
 /* Dr */
 	_IWL_DEV_INFO(IWL_CFG_ANY, IWL_CFG_ANY,

From 3ea2970b0578011ab8402ad0cff39712255f63df Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sat, 8 Mar 2025 23:19:13 +0200
Subject: [PATCH 1960/2753] wifi: iwlwifi: fix the ECKV UEFI variable name

This UEFI variable name was badly named. Fix its name and also use the
right GUID to find it: we need to use the BT_WIFI (a.k.a. Common) GUID.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231426.78c998d0fa71.I2bc9d72c1dc2c4d7028f0265634a940c2fadbbb5@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c | 8 +++++---
 drivers/net/wireless/intel/iwlwifi/fw/uefi.h | 4 ++--
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index 78bd0eb7aa929..b4438b1f8dad8 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright(c) 2021-2024 Intel Corporation
+ * Copyright(c) 2021-2025 Intel Corporation
  */
 
 #include "iwl-drv.h"
@@ -681,8 +681,10 @@ int iwl_uefi_get_eckv(struct iwl_fw_runtime *fwrt, u32 *extl_clk)
 	struct uefi_cnv_var_eckv *data;
 	int ret = 0;
 
-	data = iwl_uefi_get_verified_variable(fwrt->trans, IWL_UEFI_ECKV_NAME,
-					      "ECKV", sizeof(*data), NULL);
+	data = iwl_uefi_get_verified_variable_guid(fwrt->trans,
+						   &IWL_EFI_WIFI_BT_GUID,
+						   IWL_UEFI_ECKV_NAME,
+						   "ECKV", sizeof(*data), NULL);
 	if (IS_ERR(data))
 		return -EINVAL;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
index 0c8943a8bd011..eb3c05417da37 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright(c) 2021-2024 Intel Corporation
+ * Copyright(c) 2021-2025 Intel Corporation
  */
 #ifndef __iwl_fw_uefi__
 #define __iwl_fw_uefi__
@@ -19,7 +19,7 @@
 #define IWL_UEFI_WTAS_NAME		L"UefiCnvWlanWTAS"
 #define IWL_UEFI_SPLC_NAME		L"UefiCnvWlanSPLC"
 #define IWL_UEFI_WRDD_NAME		L"UefiCnvWlanWRDD"
-#define IWL_UEFI_ECKV_NAME		L"UefiCnvWlanECKV"
+#define IWL_UEFI_ECKV_NAME		L"UefiCnvCommonECKV"
 #define IWL_UEFI_DSM_NAME		L"UefiCnvWlanGeneralCfg"
 #define IWL_UEFI_WBEM_NAME		L"UefiCnvWlanWBEM"
 #define IWL_UEFI_PUNCTURING_NAME	L"UefiCnvWlanPuncturing"

From 8d4aaec6608298451f55c65f532a8ec98436bec1 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Sat, 8 Mar 2025 23:19:14 +0200
Subject: [PATCH 1961/2753] wifi: iwlwifi: fix print for ECKV

The print was obviously wrong. We are handling ECKV and not WRDD in this
function.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231426.e006c6b21432.I318fed724709f9ee7a0c369e1cf5e1038ddd546a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/uefi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
index b4438b1f8dad8..386aadbce2a2d 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
+++ b/drivers/net/wireless/intel/iwlwifi/fw/uefi.c
@@ -690,7 +690,7 @@ int iwl_uefi_get_eckv(struct iwl_fw_runtime *fwrt, u32 *extl_clk)
 
 	if (data->revision != IWL_UEFI_ECKV_REVISION) {
 		ret = -EINVAL;
-		IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI WRDD revision:%d\n",
+		IWL_DEBUG_RADIO(fwrt, "Unsupported UEFI ECKV revision:%d\n",
 				data->revision);
 		goto out;
 	}

From abecf9ba94aa6784a33a5526bb83a43c977322e4 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Sat, 8 Mar 2025 23:19:15 +0200
Subject: [PATCH 1962/2753] wifi: iwlwifi: mvm: cleanup of TAS structure and
 enums

Removed mvm prefix from the following structures and enum names:
1. struct iwl_tas_status_per_mac
2. struct iwl_tas_status_resp
3. enum iwl_tas_dyna_status
4. enum iwl_tas_statically_disabled_reason
As these structures and enums are not specific to mvm.

Replaced TAS_LMAC_BAND_LB, TAS_LMAC_BAND_HB, and TAS_LMAC_BAND_UHB macros
with a generic BAND macro, as these macros are not specific to TAS.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.59144bee9987.Ic2678dcb5afdacc2ca234d4aa4901e7e1f6e8dbb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/debug.h | 39 ++++++++-----------
 .../net/wireless/intel/iwlwifi/mvm/debugfs.c  | 28 +++++--------
 2 files changed, 27 insertions(+), 40 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index aa88e91d117ee..e1b6795c1f646 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -51,7 +51,7 @@ enum iwl_debug_cmds {
 	/**
 	 * @GET_TAS_STATUS:
 	 * sends command to fw to get TAS status
-	 * the response is &struct iwl_mvm_tas_status_resp
+	 * the response is &struct iwl_tas_status_resp
 	 */
 	GET_TAS_STATUS = 0xA,
 	/**
@@ -439,25 +439,20 @@ struct iwl_dbg_dump_complete_cmd {
 	__le32 tp_data;
 } __packed; /* FW_DUMP_COMPLETE_CMD_API_S_VER_1 */
 
-#define TAS_LMAC_BAND_HB       0
-#define TAS_LMAC_BAND_LB       1
-#define TAS_LMAC_BAND_UHB      2
-#define TAS_LMAC_BAND_INVALID  3
-
 /**
- * struct iwl_mvm_tas_status_per_mac - tas status per lmac
+ * struct iwl_tas_status_per_mac - tas status per lmac
  * @static_status: tas statically enabled or disabled per lmac - TRUE/FALSE
  * @static_dis_reason: TAS static disable reason, uses
- *	&enum iwl_mvm_tas_statically_disabled_reason
+ *	&enum iwl_tas_statically_disabled_reason
  * @dynamic_status: Current TAS  status. uses
- *	&enum iwl_mvm_tas_dyna_status
+ *	&enum iwl_tas_dyna_status
  * @near_disconnection: is TAS currently near disconnection per lmac? - TRUE/FALSE
  * @max_reg_pwr_limit: Regulatory power limits in dBm
  * @sar_limit: SAR limits per lmac in dBm
  * @band: Band per lmac
  * @reserved: reserved
  */
-struct iwl_mvm_tas_status_per_mac {
+struct iwl_tas_status_per_mac {
 	u8 static_status;
 	u8 static_dis_reason;
 	u8 dynamic_status;
@@ -466,35 +461,35 @@ struct iwl_mvm_tas_status_per_mac {
 	__le16 sar_limit;
 	u8 band;
 	u8 reserved[3];
-} __packed; /*DEBUG_GET_TAS_STATUS_PER_MAC_S_VER_1*/
+} __packed; /* DEBUG_GET_TAS_STATUS_PER_MAC_S_VER_1 */
 
 /**
- * struct iwl_mvm_tas_status_resp - Response to GET_TAS_STATUS
+ * struct iwl_tas_status_resp - Response to GET_TAS_STATUS
  * @tas_fw_version: TAS FW version
  * @is_uhb_for_usa_enable: is UHB enabled in USA? - TRUE/FALSE
  * @curr_mcc: current mcc
  * @block_list: country block list
  * @tas_status_mac: TAS status per lmac, uses
- *	&struct iwl_mvm_tas_status_per_mac
+ *	&struct iwl_tas_status_per_mac
  * @in_dual_radio: is TAS in dual radio? - TRUE/FALSE
  * @uhb_allowed_flags: see &enum iwl_tas_uhb_allowed_flags.
  *	This member is valid only when fw has
  *	%IWL_UCODE_TLV_CAPA_UHB_CANADA_TAS_SUPPORT capability.
  * @reserved: reserved
  */
-struct iwl_mvm_tas_status_resp {
+struct iwl_tas_status_resp {
 	u8 tas_fw_version;
 	u8 is_uhb_for_usa_enable;
 	__le16 curr_mcc;
 	__le16 block_list[16];
-	struct iwl_mvm_tas_status_per_mac tas_status_mac[2];
+	struct iwl_tas_status_per_mac tas_status_mac[2];
 	u8 in_dual_radio;
 	u8 uhb_allowed_flags;
 	u8 reserved[2];
-} __packed; /*DEBUG_GET_TAS_STATUS_RSP_API_S_VER_3*/
+} __packed; /* DEBUG_GET_TAS_STATUS_RSP_API_S_VER_3 */
 
 /**
- * enum iwl_mvm_tas_dyna_status - TAS current running status
+ * enum iwl_tas_dyna_status - TAS current running status
  * @TAS_DYNA_INACTIVE: TAS status is inactive
  * @TAS_DYNA_INACTIVE_MVM_MODE: TAS is disabled due because FW is in MVM mode
  *	or is in softap mode.
@@ -507,7 +502,7 @@ struct iwl_mvm_tas_status_resp {
  * @TAS_DYNA_ACTIVE: TAS is currently active
  * @TAS_DYNA_STATUS_MAX: TAS status max value
  */
-enum iwl_mvm_tas_dyna_status {
+enum iwl_tas_dyna_status {
 	TAS_DYNA_INACTIVE,
 	TAS_DYNA_INACTIVE_MVM_MODE,
 	TAS_DYNA_INACTIVE_TRIGGER_MODE,
@@ -516,16 +511,16 @@ enum iwl_mvm_tas_dyna_status {
 	TAS_DYNA_ACTIVE,
 
 	TAS_DYNA_STATUS_MAX,
-}; /*_TAS_DYNA_STATUS_E*/
+};
 
 /**
- * enum iwl_mvm_tas_statically_disabled_reason - TAS statically disabled reason
+ * enum iwl_tas_statically_disabled_reason - TAS statically disabled reason
  * @TAS_DISABLED_DUE_TO_BIOS: TAS is disabled because TAS is disabled in BIOS
  * @TAS_DISABLED_DUE_TO_SAR_6DBM: TAS is disabled because SAR limit is less than 6 Dbm
  * @TAS_DISABLED_REASON_INVALID: TAS disable reason is invalid
  * @TAS_DISABLED_REASON_MAX: TAS disable reason max value
  */
-enum iwl_mvm_tas_statically_disabled_reason {
+enum iwl_tas_statically_disabled_reason {
 	TAS_DISABLED_DUE_TO_BIOS,
 	TAS_DISABLED_DUE_TO_SAR_6DBM,
 	TAS_DISABLED_REASON_INVALID,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 83e3c11603622..b453ad0000c82 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2012-2014, 2018-2023 Intel Corporation
+ * Copyright (C) 2012-2014, 2018-2023, 2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -542,7 +542,7 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file,
 					     size_t count, loff_t *ppos)
 {
 	struct iwl_mvm *mvm = file->private_data;
-	struct iwl_mvm_tas_status_resp *rsp = NULL;
+	struct iwl_tas_status_resp *rsp = NULL;
 	static const size_t bufsz = 1024;
 	char *buff, *pos, *endpos;
 	const char * const tas_dis_reason[TAS_DISABLED_REASON_MAX] = {
@@ -598,23 +598,19 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file,
 
 	pos += scnprintf(pos, endpos - pos, "TAS Conclusion:\n");
 	for (i = 0; i < rsp->in_dual_radio + 1; i++) {
-		if (rsp->tas_status_mac[i].band != TAS_LMAC_BAND_INVALID &&
-		    rsp->tas_status_mac[i].dynamic_status & BIT(TAS_DYNA_ACTIVE)) {
+		if (rsp->tas_status_mac[i].dynamic_status &
+		    BIT(TAS_DYNA_ACTIVE)) {
 			pos += scnprintf(pos, endpos - pos, "\tON for ");
 			switch (rsp->tas_status_mac[i].band) {
-			case TAS_LMAC_BAND_HB:
+			case PHY_BAND_5:
 				pos += scnprintf(pos, endpos - pos, "HB\n");
 				break;
-			case TAS_LMAC_BAND_LB:
+			case PHY_BAND_24:
 				pos += scnprintf(pos, endpos - pos, "LB\n");
 				break;
-			case TAS_LMAC_BAND_UHB:
+			case PHY_BAND_6:
 				pos += scnprintf(pos, endpos - pos, "UHB\n");
 				break;
-			case TAS_LMAC_BAND_INVALID:
-				pos += scnprintf(pos, endpos - pos,
-						 "INVALID BAND\n");
-				break;
 			default:
 				pos += scnprintf(pos, endpos - pos,
 						 "Unsupported band (%d)\n",
@@ -668,20 +664,16 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file,
 
 		pos += scnprintf(pos, endpos - pos, "TAS status for ");
 		switch (rsp->tas_status_mac[i].band) {
-		case TAS_LMAC_BAND_HB:
+		case PHY_BAND_5:
 			pos += scnprintf(pos, endpos - pos, "High band\n");
 			break;
-		case TAS_LMAC_BAND_LB:
+		case PHY_BAND_24:
 			pos += scnprintf(pos, endpos - pos, "Low band\n");
 			break;
-		case TAS_LMAC_BAND_UHB:
+		case PHY_BAND_6:
 			pos += scnprintf(pos, endpos - pos,
 					 "Ultra high band\n");
 			break;
-		case TAS_LMAC_BAND_INVALID:
-			pos += scnprintf(pos, endpos - pos,
-					 "INVALID band\n");
-			break;
 		default:
 			pos += scnprintf(pos, endpos - pos,
 					 "Unsupported band (%d)\n",

From 8e3c9e6a5200c01f79d95f442999719bbed0e196 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Sat, 8 Mar 2025 23:19:16 +0200
Subject: [PATCH 1963/2753] wifi: iwlwifi: Add new TAS disable reason for
 invalid table source

The new reason is added to the iwl_tas_statically_disabled_reason enum
and the corresponding message is updated in the
iwl_dbgfs_tas_get_status_read().

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.5e1272ef3508.I24f668ae716bee20cba15fdc73c3363693bbaf73@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/fw/api/debug.h | 3 +++
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c  | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
index e1b6795c1f646..0cf1e5124fba7 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/debug.h
@@ -518,12 +518,15 @@ enum iwl_tas_dyna_status {
  * @TAS_DISABLED_DUE_TO_BIOS: TAS is disabled because TAS is disabled in BIOS
  * @TAS_DISABLED_DUE_TO_SAR_6DBM: TAS is disabled because SAR limit is less than 6 Dbm
  * @TAS_DISABLED_REASON_INVALID: TAS disable reason is invalid
+ * @TAS_DISABLED_DUE_TO_TABLE_SOURCE_INVALID: TAS is disabled due to
+ *	table source invalid
  * @TAS_DISABLED_REASON_MAX: TAS disable reason max value
  */
 enum iwl_tas_statically_disabled_reason {
 	TAS_DISABLED_DUE_TO_BIOS,
 	TAS_DISABLED_DUE_TO_SAR_6DBM,
 	TAS_DISABLED_REASON_INVALID,
+	TAS_DISABLED_DUE_TO_TABLE_SOURCE_INVALID,
 
 	TAS_DISABLED_REASON_MAX,
 }; /*_TAS_STATICALLY_DISABLED_REASON_E*/
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index b453ad0000c82..6ffc04a23c6c1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -552,6 +552,8 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file,
 			"Due To SAR Limit Less Than 6 dBm",
 		[TAS_DISABLED_REASON_INVALID] =
 			"N/A",
+		[TAS_DISABLED_DUE_TO_TABLE_SOURCE_INVALID] =
+			"Due to table source invalid",
 	};
 	const char * const tas_current_status[TAS_DYNA_STATUS_MAX] = {
 		[TAS_DYNA_INACTIVE] = "INACTIVE",

From 5f0ab2f35a43773a0dfe1297129a8dbff906b932 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:19:17 +0200
Subject: [PATCH 1964/2753] wifi: iwlwifi: mark Br device not integrated

This is a discrete device, don't mark it as integrated.
This also means we cannot set the LTR delay.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.9bb69393fcc9.I197129383e5441c8139cbb0e810ae0b71198a37c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/dr.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
index 69176b59b4dee..48b487f6e366c 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
@@ -148,11 +148,9 @@ const struct iwl_cfg_trans_params iwl_br_trans_cfg = {
 	.mq_rx_supported = true,
 	.rf_id = true,
 	.gen2 = true,
-	.integrated = true,
 	.umac_prph_offset = 0x300000,
 	.xtal_latency = 12000,
 	.low_latency_xtal = true,
-	.ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
 };
 
 const char iwl_br_name[] = "Intel(R) TBD Br device";

From eb29b4ffafb20281624dcd2cbb768d6f30edf600 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 8 Mar 2025 23:19:18 +0200
Subject: [PATCH 1965/2753] wifi: iwlwifi: fix debug actions order

The order of actions taken for debug was implemented incorrectly.
Now we implemented the dump split and do the FW reset only in the
middle of the dump (rather than the FW killing itself on error.)
As a result, some of the actions taken when applying the config
will now crash the device, so we need to fix the order.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.6de7fa8e63ed.I40632c48e2a67a8aca05def572a934b88ce7934b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
index 08d990ba8a794..ce787326aa69d 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-dbg-tlv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/firmware.h>
 #include "iwl-drv.h"
@@ -1372,15 +1372,15 @@ void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	switch (tp_id) {
 	case IWL_FW_INI_TIME_POINT_EARLY:
 		iwl_dbg_tlv_init_cfg(fwrt);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_update_drams(fwrt);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	case IWL_FW_INI_TIME_POINT_AFTER_ALIVE:
 		iwl_dbg_tlv_apply_buffers(fwrt);
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	case IWL_FW_INI_TIME_POINT_PERIODIC:
 		iwl_dbg_tlv_set_periodic_trigs(fwrt);
@@ -1390,14 +1390,14 @@ void _iwl_dbg_tlv_time_point(struct iwl_fw_runtime *fwrt,
 	case IWL_FW_INI_TIME_POINT_MISSED_BEACONS:
 	case IWL_FW_INI_TIME_POINT_FW_DHC_NOTIFICATION:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data,
 				       iwl_dbg_tlv_check_fw_pkt);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	default:
 		iwl_dbg_tlv_send_hcmds(fwrt, hcmd_list);
-		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		iwl_dbg_tlv_tp_trigger(fwrt, sync, trig_list, tp_data, NULL);
+		iwl_dbg_tlv_apply_config(fwrt, conf_list);
 		break;
 	}
 }

From b2e709805ce955f80803b7cab3421813c79e1df4 Mon Sep 17 00:00:00 2001
From: Daniel Gabay <daniel.gabay@intel.com>
Date: Sat, 8 Mar 2025 23:19:19 +0200
Subject: [PATCH 1966/2753] wifi: iwlwifi: w/a FW SMPS mode selection

The FW is now responsible of determining the SMPS mode.
If the user disabled power save in a certain vif, we send the vif-level
power command to clear out the POWER_FLAGS_POWER_MANAGEMENT_ENA_MSK bit
for that vif.
But erroneously, the FW checks DEVICE_POWER_FLAGS_POWER_SAVE_ENA_MSK in
the device-level command to determine the SMPS mode.

To W/A this, send also the device-level command when the power save of a
vif changes, and disable power save if there is any vif that has power
save disabled.

Signed-off-by: Daniel Gabay <daniel.gabay@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.7bf205efa027.I2c793ff1fc2a6779a95faaee1ded348100fd97f1@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c | 15 +++++++++++++++
 .../net/wireless/intel/iwlwifi/mvm/mld-mac80211.c |  3 ++-
 drivers/net/wireless/intel/iwlwifi/mvm/mvm.h      |  3 +++
 3 files changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
index 20aaef913e3f1..1e916a0ce0824 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
@@ -4100,6 +4100,20 @@ iwl_mvm_sta_state_authorized_to_assoc(struct iwl_mvm *mvm,
 	return 0;
 }
 
+void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool update)
+{
+	struct iwl_mvm_vif *mvmvif = iwl_mvm_vif_from_mac80211(vif);
+
+	if (!iwl_mvm_has_rlc_offload(mvm))
+		return;
+
+	mvmvif->ps_disabled = !vif->cfg.ps;
+
+	if (update)
+		iwl_mvm_power_update_mac(mvm);
+}
+
 /* Common part for MLD and non-MLD modes */
 int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw,
 				 struct ieee80211_vif *vif,
@@ -4192,6 +4206,7 @@ int iwl_mvm_mac_sta_state_common(struct ieee80211_hw *hw,
 		   new_state == IEEE80211_STA_AUTHORIZED) {
 		ret = iwl_mvm_sta_state_assoc_to_authorized(mvm, vif, sta,
 							    callbacks);
+		iwl_mvm_smps_workaround(mvm, vif, true);
 	} else if (old_state == IEEE80211_STA_AUTHORIZED &&
 		   new_state == IEEE80211_STA_ASSOC) {
 		ret = iwl_mvm_sta_state_authorized_to_assoc(mvm, vif, sta,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
index 341a2a7a49ec9..78d7153a0cfca 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mld-mac80211.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2022-2024 Intel Corporation
+ * Copyright (C) 2022-2025 Intel Corporation
  */
 #include "mvm.h"
 
@@ -887,6 +887,7 @@ static void iwl_mvm_mld_vif_cfg_changed_station(struct iwl_mvm *mvm,
 	}
 
 	if (changes & BSS_CHANGED_PS) {
+		iwl_mvm_smps_workaround(mvm, vif, false);
 		ret = iwl_mvm_power_update_mac(mvm);
 		if (ret)
 			IWL_ERR(mvm, "failed to update power mode\n");
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index b6e0b63cbd3c1..f6391c7a3e296 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -3031,4 +3031,7 @@ iwl_mvm_send_ap_tx_power_constraint_cmd(struct iwl_mvm *mvm,
 					struct ieee80211_vif *vif,
 					struct ieee80211_bss_conf *bss_conf,
 					bool is_ap);
+
+void iwl_mvm_smps_workaround(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
+			     bool update);
 #endif /* __IWL_MVM_H__ */

From 9002ba67fb1e275f9cba38b4af42ebe43638fb5c Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Sat, 8 Mar 2025 23:19:20 +0200
Subject: [PATCH 1967/2753] wifi: iwlwifi: mvm: Fix bit size calculation in
 iwl_dbgfs_tas_get_status_read

Corrected the bit size calculation in the for_each_set_bit macro in
the iwl_dbgfs_tas_get_status_read(). The previous implementation used
sizeof(dyn_status), which only accounts for the number of bytes.
This has been updated to TAS_DYNA_STATUS_MAX to ensure the loop iterates
over the correct number of valid bits in dyn_status.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.65d373e4a10e.If2cea63035333b07849e5a2c2a4f5dc5c5239595@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
index 6ffc04a23c6c1..1289ff3ab162d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/debugfs.c
@@ -698,11 +698,9 @@ static ssize_t iwl_dbgfs_tas_get_status_read(struct file *file,
 
 		pos += scnprintf(pos, endpos - pos, "Dynamic status:\n");
 		dyn_status = (rsp->tas_status_mac[i].dynamic_status);
-		for_each_set_bit(tmp, &dyn_status, sizeof(dyn_status)) {
-			if (tmp >= 0 && tmp < TAS_DYNA_STATUS_MAX)
-				pos += scnprintf(pos, endpos - pos,
-						 "\t%s (%d)\n",
-						 tas_current_status[tmp], tmp);
+		for_each_set_bit(tmp, &dyn_status, TAS_DYNA_STATUS_MAX) {
+			pos += scnprintf(pos, endpos - pos, "\t%s (%d)\n",
+					 tas_current_status[tmp], tmp);
 		}
 
 		pos += scnprintf(pos, endpos - pos,

From d8bc6f24c65a1b8216717856cbc46ed904c2bb16 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sat, 8 Mar 2025 23:19:21 +0200
Subject: [PATCH 1968/2753] wifi: iwlwifi: bump FW API to 98 for BZ/SC/DR
 devices

Start supporting API versions 97 and 98 for those devices.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.55b5455795aa.I333f1e7fa31f9da1d40f668660c1e25b93ff469e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c | 4 ++--
 drivers/net/wireless/intel/iwlwifi/cfg/dr.c | 4 ++--
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c | 4 ++--
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index 36e8e3a991dcb..dbd3033851578 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_BZ_UCODE_API_MAX	96
+#define IWL_BZ_UCODE_API_MAX	98
 
 /* Lowest firmware API version supported */
 #define IWL_BZ_UCODE_API_MIN	92
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
index 48b487f6e366c..282b9b846c3ac 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/dr.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -9,7 +9,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_DR_UCODE_API_MAX	96
+#define IWL_DR_UCODE_API_MAX	98
 
 /* Lowest firmware API version supported */
 #define IWL_DR_UCODE_API_MIN	96
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index 05cbb80ab575c..a9fc9e8ec4312 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
  * Copyright (C) 2015-2017 Intel Deutschland GmbH
- * Copyright (C) 2018-2024 Intel Corporation
+ * Copyright (C) 2018-2025 Intel Corporation
  */
 #include <linux/module.h>
 #include <linux/stringify.h>
@@ -10,7 +10,7 @@
 #include "fw/api/txq.h"
 
 /* Highest firmware API version supported */
-#define IWL_SC_UCODE_API_MAX	96
+#define IWL_SC_UCODE_API_MAX	98
 
 /* Lowest firmware API version supported */
 #define IWL_SC_UCODE_API_MIN	92

From 96a3598ba82edb5d2498b9de298aed04caec4b6c Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sat, 8 Mar 2025 23:19:22 +0200
Subject: [PATCH 1969/2753] wifi: iwlwifi: bump minimum API version in BZ/SC to
 93

Stop supporting older FWs.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.73e962ca3e6c.I942fa8cafc1791b9330ad18e2599fae11d7b3336@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/cfg/bz.c | 2 +-
 drivers/net/wireless/intel/iwlwifi/cfg/sc.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
index dbd3033851578..f055255a7c937 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
@@ -13,7 +13,7 @@
 #define IWL_BZ_UCODE_API_MAX	98
 
 /* Lowest firmware API version supported */
-#define IWL_BZ_UCODE_API_MIN	92
+#define IWL_BZ_UCODE_API_MIN	93
 
 /* NVM versions */
 #define IWL_BZ_NVM_VERSION		0x0a1d
diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
index a9fc9e8ec4312..670031fd60dc9 100644
--- a/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
+++ b/drivers/net/wireless/intel/iwlwifi/cfg/sc.c
@@ -13,7 +13,7 @@
 #define IWL_SC_UCODE_API_MAX	98
 
 /* Lowest firmware API version supported */
-#define IWL_SC_UCODE_API_MIN	92
+#define IWL_SC_UCODE_API_MIN	93
 
 /* NVM versions */
 #define IWL_SC_NVM_VERSION		0x0a1d

From c7f50d0433a016d43681592836a3d484817bfb34 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sat, 8 Mar 2025 23:19:23 +0200
Subject: [PATCH 1970/2753] wifi: iwlwifi: don't warn when if there is a FW
 error

iwl_trans_reclaim is warning if it is called when the FW is not alive.
But if it is called when there is a pending restart, i.e. after a FW
error, there is no need to warn, instead - return silently.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.ba3d90b22c25.I9332506af1997faefcf0bdb51d98d5e874051722@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-trans.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
index 1632ab20a23f7..ea67df09fc014 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
- * Copyright (C) 2019-2021, 2023-2024 Intel Corporation
+ * Copyright (C) 2019-2021, 2023-2025 Intel Corporation
  */
 #include <linux/kernel.h>
 #include <linux/bsearch.h>
@@ -639,6 +639,9 @@ IWL_EXPORT_SYMBOL(iwl_trans_tx);
 void iwl_trans_reclaim(struct iwl_trans *trans, int queue, int ssn,
 		       struct sk_buff_head *skbs, bool is_flush)
 {
+	if (unlikely(test_bit(STATUS_FW_ERROR, &trans->status)))
+		return;
+
 	if (WARN_ONCE(trans->state != IWL_TRANS_FW_ALIVE,
 		      "bad state = %d\n", trans->state))
 		return;

From 46eeb90f03e03d5e8f7f9f1f0eb0792104fc5f86 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Wed, 5 Mar 2025 15:44:20 +0530
Subject: [PATCH 1971/2753] net: ti: icssg-prueth: Use page_pool API for RX
 buffer allocation

This is to prepare for native XDP support.

The page pool API is more faster in allocating pages than
__alloc_skb(). Drawback is that it works at PAGE_SIZE granularity
so we are not efficient in memory usage.
i.e. we are using PAGE_SIZE (4KB) memory for 1.5KB max packet size.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Link: https://patch.msgid.link/20250305101422.1908370-2-m-malladi@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/Kconfig               |   1 +
 drivers/net/ethernet/ti/icssg/icssg_common.c  | 174 ++++++++++++------
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |  14 +-
 .../net/ethernet/ti/icssg/icssg_prueth_sr1.c  |  51 +++--
 4 files changed, 150 insertions(+), 90 deletions(-)

diff --git a/drivers/net/ethernet/ti/Kconfig b/drivers/net/ethernet/ti/Kconfig
index 3a13d60a947a8..a07c910c497a9 100644
--- a/drivers/net/ethernet/ti/Kconfig
+++ b/drivers/net/ethernet/ti/Kconfig
@@ -205,6 +205,7 @@ config TI_ICSSG_PRUETH_SR1
 	select PHYLIB
 	select TI_ICSS_IEP
 	select TI_K3_CPPI_DESC_POOL
+	select PAGE_POOL
 	depends on PRU_REMOTEPROC
 	depends on NET_SWITCHDEV
 	depends on ARCH_K3 && OF && TI_K3_UDMA_GLUE_LAYER
diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index 74f0f200a89d4..acbb79ad8b0cd 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -45,6 +45,11 @@ void prueth_cleanup_rx_chns(struct prueth_emac *emac,
 			    struct prueth_rx_chn *rx_chn,
 			    int max_rflows)
 {
+	if (rx_chn->pg_pool) {
+		page_pool_destroy(rx_chn->pg_pool);
+		rx_chn->pg_pool = NULL;
+	}
+
 	if (rx_chn->desc_pool)
 		k3_cppi_desc_pool_destroy(rx_chn->desc_pool);
 
@@ -461,17 +466,17 @@ int prueth_init_rx_chns(struct prueth_emac *emac,
 }
 EXPORT_SYMBOL_GPL(prueth_init_rx_chns);
 
-int prueth_dma_rx_push(struct prueth_emac *emac,
-		       struct sk_buff *skb,
-		       struct prueth_rx_chn *rx_chn)
+int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
+			      struct prueth_rx_chn *rx_chn,
+			      struct page *page, u32 buf_len)
 {
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	u32 pkt_len = skb_tailroom(skb);
 	dma_addr_t desc_dma;
 	dma_addr_t buf_dma;
 	void **swdata;
 
+	buf_dma = page_pool_get_dma_addr(page) + PRUETH_HEADROOM;
 	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
 	if (!desc_rx) {
 		netdev_err(ndev, "rx push: failed to allocate descriptor\n");
@@ -479,25 +484,18 @@ int prueth_dma_rx_push(struct prueth_emac *emac,
 	}
 	desc_dma = k3_cppi_desc_pool_virt2dma(rx_chn->desc_pool, desc_rx);
 
-	buf_dma = dma_map_single(rx_chn->dma_dev, skb->data, pkt_len, DMA_FROM_DEVICE);
-	if (unlikely(dma_mapping_error(rx_chn->dma_dev, buf_dma))) {
-		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-		netdev_err(ndev, "rx push: failed to map rx pkt buffer\n");
-		return -EINVAL;
-	}
-
 	cppi5_hdesc_init(desc_rx, CPPI5_INFO0_HDESC_EPIB_PRESENT,
 			 PRUETH_NAV_PS_DATA_SIZE);
 	k3_udma_glue_rx_dma_to_cppi5_addr(rx_chn->rx_chn, &buf_dma);
-	cppi5_hdesc_attach_buf(desc_rx, buf_dma, skb_tailroom(skb), buf_dma, skb_tailroom(skb));
+	cppi5_hdesc_attach_buf(desc_rx, buf_dma, buf_len, buf_dma, buf_len);
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	*swdata = skb;
+	*swdata = page;
 
-	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, 0,
+	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, PRUETH_RX_FLOW_DATA,
 					desc_rx, desc_dma);
 }
-EXPORT_SYMBOL_GPL(prueth_dma_rx_push);
+EXPORT_SYMBOL_GPL(prueth_dma_rx_push_mapped);
 
 u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns)
 {
@@ -541,12 +539,16 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	u32 buf_dma_len, pkt_len, port_id = 0;
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb, *new_skb;
 	dma_addr_t desc_dma, buf_dma;
+	struct page *page, *new_page;
+	struct page_pool *pool;
+	struct sk_buff *skb;
 	void **swdata;
 	u32 *psdata;
+	void *pa;
 	int ret;
 
+	pool = rx_chn->pg_pool;
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
 	if (ret) {
 		if (ret != -ENODATA)
@@ -558,15 +560,9 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 		return 0;
 
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
-
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-
-	psdata = cppi5_hdesc_get_psdata(desc_rx);
-	/* RX HW timestamp */
-	if (emac->rx_ts_enabled)
-		emac_rx_timestamp(emac, skb, psdata);
-
+	page = *swdata;
+	page_pool_dma_sync_for_cpu(pool, page, 0, PAGE_SIZE);
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
 	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
@@ -574,32 +570,51 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	pkt_len -= 4;
 	cppi5_desc_get_tags_ids(&desc_rx->hdr, &port_id, NULL);
 
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	skb->dev = ndev;
-	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
 	/* if allocation fails we drop the packet but push the
-	 * descriptor back to the ring with old skb to prevent a stall
+	 * descriptor back to the ring with old page to prevent a stall
 	 */
-	if (!new_skb) {
+	new_page = page_pool_dev_alloc_pages(pool);
+	if (unlikely(!new_page)) {
+		new_page = page;
 		ndev->stats.rx_dropped++;
-		new_skb = skb;
-	} else {
-		/* send the filled skb up the n/w stack */
-		skb_put(skb, pkt_len);
-		if (emac->prueth->is_switch_mode)
-			skb->offload_fwd_mark = emac->offload_fwd_mark;
-		skb->protocol = eth_type_trans(skb, ndev);
-		napi_gro_receive(&emac->napi_rx, skb);
-		ndev->stats.rx_bytes += pkt_len;
-		ndev->stats.rx_packets++;
+		goto requeue;
+	}
+
+	/* prepare skb and send to n/w stack */
+	pa = page_address(page);
+	skb = napi_build_skb(pa, PAGE_SIZE);
+	if (!skb) {
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(pool, page);
+		goto requeue;
 	}
 
+	skb_reserve(skb, PRUETH_HEADROOM);
+	skb_put(skb, pkt_len);
+	skb->dev = ndev;
+
+	psdata = cppi5_hdesc_get_psdata(desc_rx);
+	/* RX HW timestamp */
+	if (emac->rx_ts_enabled)
+		emac_rx_timestamp(emac, skb, psdata);
+
+	if (emac->prueth->is_switch_mode)
+		skb->offload_fwd_mark = emac->offload_fwd_mark;
+	skb->protocol = eth_type_trans(skb, ndev);
+
+	skb_mark_for_recycle(skb);
+	napi_gro_receive(&emac->napi_rx, skb);
+	ndev->stats.rx_bytes += pkt_len;
+	ndev->stats.rx_packets++;
+
+requeue:
 	/* queue another RX DMA */
-	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_chns);
+	ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page,
+					PRUETH_MAX_PKT_SIZE);
 	if (WARN_ON(ret < 0)) {
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(pool, new_page);
 		ndev->stats.rx_errors++;
 		ndev->stats.rx_dropped++;
 	}
@@ -611,22 +626,16 @@ static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct prueth_rx_chn *rx_chn = data;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb;
-	dma_addr_t buf_dma;
-	u32 buf_dma_len;
+	struct page_pool *pool;
+	struct page *page;
 	void **swdata;
 
+	pool = rx_chn->pg_pool;
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
-	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
-
-	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len,
-			 DMA_FROM_DEVICE);
+	page = *swdata;
+	page_pool_recycle_direct(pool, page);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
-
-	dev_kfree_skb_any(skb);
 }
 
 static int prueth_tx_ts_cookie_get(struct prueth_emac *emac)
@@ -907,29 +916,71 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 }
 EXPORT_SYMBOL_GPL(icssg_napi_rx_poll);
 
+static struct page_pool *prueth_create_page_pool(struct prueth_emac *emac,
+						 struct device *dma_dev,
+						 int size)
+{
+	struct page_pool_params pp_params = { 0 };
+	struct page_pool *pool;
+
+	pp_params.order = 0;
+	pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
+	pp_params.pool_size = size;
+	pp_params.nid = dev_to_node(emac->prueth->dev);
+	pp_params.dma_dir = DMA_BIDIRECTIONAL;
+	pp_params.dev = dma_dev;
+	pp_params.napi = &emac->napi_rx;
+	pp_params.max_len = PAGE_SIZE;
+
+	pool = page_pool_create(&pp_params);
+	if (IS_ERR(pool))
+		netdev_err(emac->ndev, "cannot create rx page pool\n");
+
+	return pool;
+}
+
 int prueth_prepare_rx_chan(struct prueth_emac *emac,
 			   struct prueth_rx_chn *chn,
 			   int buf_size)
 {
-	struct sk_buff *skb;
+	struct page_pool *pool;
+	struct page *page;
 	int i, ret;
 
+	pool = prueth_create_page_pool(emac, chn->dma_dev, chn->descs_num);
+	if (IS_ERR(pool))
+		return PTR_ERR(pool);
+
+	chn->pg_pool = pool;
+
 	for (i = 0; i < chn->descs_num; i++) {
-		skb = __netdev_alloc_skb_ip_align(NULL, buf_size, GFP_KERNEL);
-		if (!skb)
-			return -ENOMEM;
+		/* NOTE: we're not using memory efficiently here.
+		 * 1 full page (4KB?) used here instead of
+		 * PRUETH_MAX_PKT_SIZE (~1.5KB?)
+		 */
+		page = page_pool_dev_alloc_pages(pool);
+		if (!page) {
+			netdev_err(emac->ndev, "couldn't allocate rx page\n");
+			ret = -ENOMEM;
+			goto recycle_alloc_pg;
+		}
 
-		ret = prueth_dma_rx_push(emac, skb, chn);
+		ret = prueth_dma_rx_push_mapped(emac, chn, page, buf_size);
 		if (ret < 0) {
 			netdev_err(emac->ndev,
-				   "cannot submit skb for rx chan %s ret %d\n",
+				   "cannot submit page for rx chan %s ret %d\n",
 				   chn->name, ret);
-			kfree_skb(skb);
-			return ret;
+			page_pool_recycle_direct(pool, page);
+			goto recycle_alloc_pg;
 		}
 	}
 
 	return 0;
+
+recycle_alloc_pg:
+	prueth_reset_rx_chan(&emac->rx_chns, PRUETH_MAX_RX_FLOWS, false);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(prueth_prepare_rx_chan);
 
@@ -958,6 +1009,9 @@ void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
 					  prueth_rx_cleanup, !!i);
 	if (disable)
 		k3_udma_glue_disable_rx_chn(chn->rx_chn);
+
+	page_pool_destroy(chn->pg_pool);
+	chn->pg_pool = NULL;
 }
 EXPORT_SYMBOL_GPL(prueth_reset_rx_chan);
 
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 329b46e9ee530..c7b906de18af6 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -33,6 +33,8 @@
 #include <linux/dma/k3-udma-glue.h>
 
 #include <net/devlink.h>
+#include <net/xdp.h>
+#include <net/page_pool/helpers.h>
 
 #include "icssg_config.h"
 #include "icss_iep.h"
@@ -131,6 +133,7 @@ struct prueth_rx_chn {
 	u32 descs_num;
 	unsigned int irq[ICSSG_MAX_RFLOWS];	/* separate irq per flow */
 	char name[32];
+	struct page_pool *pg_pool;
 };
 
 /* There are 4 Tx DMA channels, but the highest priority is CH3 (thread 3)
@@ -210,6 +213,10 @@ struct prueth_emac {
 	struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID];
 };
 
+/* The buf includes headroom compatible with both skb and xdpf */
+#define PRUETH_HEADROOM_NA (max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN)
+#define PRUETH_HEADROOM  ALIGN(PRUETH_HEADROOM_NA, sizeof(long))
+
 /**
  * struct prueth_pdata - PRUeth platform data
  * @fdqring_mode: Free desc queue mode
@@ -410,9 +417,10 @@ int prueth_init_rx_chns(struct prueth_emac *emac,
 			struct prueth_rx_chn *rx_chn,
 			char *name, u32 max_rflows,
 			u32 max_desc_num);
-int prueth_dma_rx_push(struct prueth_emac *emac,
-		       struct sk_buff *skb,
-		       struct prueth_rx_chn *rx_chn);
+int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
+			      struct prueth_rx_chn *rx_chn,
+			      struct page *page, u32 buf_len);
+unsigned int prueth_rxbuf_total_len(unsigned int len);
 void emac_rx_timestamp(struct prueth_emac *emac,
 		       struct sk_buff *skb, u32 *psdata);
 enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index 64a19ff39562f..8f5719a98614c 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -268,15 +268,15 @@ static int emac_phy_connect(struct prueth_emac *emac)
  * Returns skb pointer if packet found else NULL
  * Caller must free the returned skb.
  */
-static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac,
-					     u32 flow_id)
+static struct page *prueth_process_rx_mgm(struct prueth_emac *emac,
+					  u32 flow_id)
 {
 	struct prueth_rx_chn *rx_chn = &emac->rx_mgm_chn;
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
-	struct sk_buff *skb, *new_skb;
+	struct page *page, *new_page;
 	dma_addr_t desc_dma, buf_dma;
-	u32 buf_dma_len, pkt_len;
+	u32 buf_dma_len;
 	void **swdata;
 	int ret;
 
@@ -299,34 +299,31 @@ static struct sk_buff *prueth_process_rx_mgm(struct prueth_emac *emac,
 	}
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	skb = *swdata;
+	page = *swdata;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
-	pkt_len = cppi5_hdesc_get_pktlen(desc_rx);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 
-	new_skb = netdev_alloc_skb_ip_align(ndev, PRUETH_MAX_PKT_SIZE);
+	new_page = page_pool_dev_alloc_pages(rx_chn->pg_pool);
 	/* if allocation fails we drop the packet but push the
 	 * descriptor back to the ring with old skb to prevent a stall
 	 */
-	if (!new_skb) {
+	if (!new_page) {
 		netdev_err(ndev,
-			   "skb alloc failed, dropped mgm pkt from flow %d\n",
+			   "page alloc failed, dropped mgm pkt from flow %d\n",
 			   flow_id);
-		new_skb = skb;
-		skb = NULL;	/* return NULL */
-	} else {
-		/* return the filled skb */
-		skb_put(skb, pkt_len);
+		new_page = page;
+		page = NULL;	/* return NULL */
 	}
 
 	/* queue another DMA */
-	ret = prueth_dma_rx_push(emac, new_skb, &emac->rx_mgm_chn);
+	ret = prueth_dma_rx_push_mapped(emac, &emac->rx_chns, new_page,
+					PRUETH_MAX_PKT_SIZE);
 	if (WARN_ON(ret < 0))
-		dev_kfree_skb_any(new_skb);
+		page_pool_recycle_direct(rx_chn->pg_pool, new_page);
 
-	return skb;
+	return page;
 }
 
 static void prueth_tx_ts_sr1(struct prueth_emac *emac,
@@ -362,14 +359,14 @@ static void prueth_tx_ts_sr1(struct prueth_emac *emac,
 static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
-	struct sk_buff *skb;
+	struct page *page;
 
-	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1);
-	if (!skb)
+	page = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_TIMESTAMP_SR1);
+	if (!page)
 		return IRQ_NONE;
 
-	prueth_tx_ts_sr1(emac, (void *)skb->data);
-	dev_kfree_skb_any(skb);
+	prueth_tx_ts_sr1(emac, (void *)page_address(page));
+	page_pool_recycle_direct(page->pp, page);
 
 	return IRQ_HANDLED;
 }
@@ -377,15 +374,15 @@ static irqreturn_t prueth_rx_mgm_ts_thread_sr1(int irq, void *dev_id)
 static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id)
 {
 	struct prueth_emac *emac = dev_id;
-	struct sk_buff *skb;
+	struct page *page;
 	u32 rsp;
 
-	skb = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1);
-	if (!skb)
+	page = prueth_process_rx_mgm(emac, PRUETH_RX_MGM_FLOW_RESPONSE_SR1);
+	if (!page)
 		return IRQ_NONE;
 
 	/* Process command response */
-	rsp = le32_to_cpu(*(__le32 *)skb->data) & 0xffff0000;
+	rsp = le32_to_cpu(*(__le32 *)page_address(page)) & 0xffff0000;
 	if (rsp == ICSSG_SHUTDOWN_CMD_SR1) {
 		netdev_dbg(emac->ndev, "f/w Shutdown cmd resp %x\n", rsp);
 		complete(&emac->cmd_complete);
@@ -394,7 +391,7 @@ static irqreturn_t prueth_rx_mgm_rsp_thread(int irq, void *dev_id)
 		complete(&emac->cmd_complete);
 	}
 
-	dev_kfree_skb_any(skb);
+	page_pool_recycle_direct(page->pp, page);
 
 	return IRQ_HANDLED;
 }

From 73f7f1311866d9c6e4dbd1a330db86b20ea320ca Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Wed, 5 Mar 2025 15:44:21 +0530
Subject: [PATCH 1972/2753] net: ti: icssg-prueth: introduce and use
 prueth_swdata struct for SWDATA

We have different cases for SWDATA (skb, page, cmd, etc)
so it is better to have a dedicated data structure for that.
We can embed the type field inside the struct and use it
to interpret the data in completion handlers.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Link: https://patch.msgid.link/20250305101422.1908370-3-m-malladi@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c  | 52 +++++++++++--------
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  |  3 ++
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  | 16 ++++++
 .../net/ethernet/ti/icssg/icssg_prueth_sr1.c  |  9 ++--
 4 files changed, 54 insertions(+), 26 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index acbb79ad8b0cd..fee1204db3672 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -136,12 +136,12 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_tx;
 	struct netdev_queue *netif_txq;
+	struct prueth_swdata *swdata;
 	struct prueth_tx_chn *tx_chn;
 	unsigned int total_bytes = 0;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
-	void **swdata;
 
 	tx_chn = &emac->tx_chns[chn];
 
@@ -161,16 +161,11 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
 						     desc_dma);
 		swdata = cppi5_hdesc_get_swdata(desc_tx);
-
-		/* was this command's TX complete? */
-		if (emac->is_sr1 && *(swdata) == emac->cmd_data) {
-			prueth_xmit_free(tx_chn, desc_tx);
-			continue;
-		}
-
-		skb = *(swdata);
 		prueth_xmit_free(tx_chn, desc_tx);
+		if (swdata->type != PRUETH_SWDATA_SKB)
+			continue;
 
+		skb = swdata->data.skb;
 		ndev = skb->dev;
 		ndev->stats.tx_packets++;
 		ndev->stats.tx_bytes += skb->len;
@@ -472,9 +467,9 @@ int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
 {
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma;
 	dma_addr_t buf_dma;
-	void **swdata;
 
 	buf_dma = page_pool_get_dma_addr(page) + PRUETH_HEADROOM;
 	desc_rx = k3_cppi_desc_pool_alloc(rx_chn->desc_pool);
@@ -490,7 +485,8 @@ int prueth_dma_rx_push_mapped(struct prueth_emac *emac,
 	cppi5_hdesc_attach_buf(desc_rx, buf_dma, buf_len, buf_dma, buf_len);
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	*swdata = page;
+	swdata->type = PRUETH_SWDATA_PAGE;
+	swdata->data.page = page;
 
 	return k3_udma_glue_push_rx_chn(rx_chn->rx_chn, PRUETH_RX_FLOW_DATA,
 					desc_rx, desc_dma);
@@ -539,11 +535,11 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	u32 buf_dma_len, pkt_len, port_id = 0;
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma, buf_dma;
 	struct page *page, *new_page;
 	struct page_pool *pool;
 	struct sk_buff *skb;
-	void **swdata;
 	u32 *psdata;
 	void *pa;
 	int ret;
@@ -561,7 +557,13 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	page = *swdata;
+	if (swdata->type != PRUETH_SWDATA_PAGE) {
+		netdev_err(ndev, "rx_pkt: invalid swdata->type %d\n", swdata->type);
+		k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
+		return 0;
+	}
+
+	page = swdata->data.page;
 	page_pool_dma_sync_for_cpu(pool, page, 0, PAGE_SIZE);
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 	k3_udma_glue_rx_cppi5_to_dma_addr(rx_chn->rx_chn, &buf_dma);
@@ -626,15 +628,18 @@ static void prueth_rx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct prueth_rx_chn *rx_chn = data;
 	struct cppi5_host_desc_t *desc_rx;
+	struct prueth_swdata *swdata;
 	struct page_pool *pool;
 	struct page *page;
-	void **swdata;
 
 	pool = rx_chn->pg_pool;
 	desc_rx = k3_cppi_desc_pool_dma2virt(rx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	page = *swdata;
-	page_pool_recycle_direct(pool, page);
+	if (swdata->type == PRUETH_SWDATA_PAGE) {
+		page = swdata->data.page;
+		page_pool_recycle_direct(pool, page);
+	}
+
 	k3_cppi_desc_pool_free(rx_chn->desc_pool, desc_rx);
 }
 
@@ -671,13 +676,13 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
 	struct netdev_queue *netif_txq;
+	struct prueth_swdata *swdata;
 	struct prueth_tx_chn *tx_chn;
 	dma_addr_t desc_dma, buf_dma;
 	u32 pkt_len, dst_tag_id;
 	int i, ret = 0, q_idx;
 	bool in_tx_ts = 0;
 	int tx_ts_cookie;
-	void **swdata;
 	u32 *epib;
 
 	pkt_len = skb_headlen(skb);
@@ -739,7 +744,8 @@ enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev
 	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*swdata = skb;
+	swdata->type = PRUETH_SWDATA_SKB;
+	swdata->data.skb = skb;
 
 	/* Handle the case where skb is fragmented in pages */
 	cur_desc = first_desc;
@@ -842,15 +848,17 @@ static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
 {
 	struct prueth_tx_chn *tx_chn = data;
 	struct cppi5_host_desc_t *desc_tx;
+	struct prueth_swdata *swdata;
 	struct sk_buff *skb;
-	void **swdata;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	skb = *(swdata);
-	prueth_xmit_free(tx_chn, desc_tx);
+	if (swdata->type == PRUETH_SWDATA_SKB) {
+		skb = swdata->data.skb;
+		dev_kfree_skb_any(skb);
+	}
 
-	dev_kfree_skb_any(skb);
+	prueth_xmit_free(tx_chn, desc_tx);
 }
 
 irqreturn_t prueth_rx_irq(int irq, void *dev_id)
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 00ed978605478..3ff8c322f9d93 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1522,6 +1522,9 @@ static int prueth_probe(struct platform_device *pdev)
 
 	np = dev->of_node;
 
+	BUILD_BUG_ON_MSG((sizeof(struct prueth_swdata) > PRUETH_NAV_SW_DATA_SIZE),
+			 "insufficient SW_DATA size");
+
 	prueth = devm_kzalloc(dev, sizeof(*prueth), GFP_KERNEL);
 	if (!prueth)
 		return -ENOMEM;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index c7b906de18af6..3bbabd0071299 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -136,6 +136,22 @@ struct prueth_rx_chn {
 	struct page_pool *pg_pool;
 };
 
+enum prueth_swdata_type {
+	PRUETH_SWDATA_INVALID = 0,
+	PRUETH_SWDATA_SKB,
+	PRUETH_SWDATA_PAGE,
+	PRUETH_SWDATA_CMD,
+};
+
+struct prueth_swdata {
+	enum prueth_swdata_type type;
+	union prueth_data {
+		struct sk_buff *skb;
+		struct page *page;
+		u32 cmd;
+	} data;
+};
+
 /* There are 4 Tx DMA channels, but the highest priority is CH3 (thread 3)
  * and lower three are lower priority channels or threads.
  */
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index 8f5719a98614c..ff5f41bf499e3 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -84,7 +84,7 @@ static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd)
 	__le32 *data = emac->cmd_data;
 	dma_addr_t desc_dma, buf_dma;
 	struct prueth_tx_chn *tx_chn;
-	void **swdata;
+	struct prueth_swdata *swdata;
 	int ret = 0;
 	u32 *epib;
 
@@ -122,7 +122,8 @@ static int emac_send_command_sr1(struct prueth_emac *emac, u32 cmd)
 
 	cppi5_hdesc_attach_buf(first_desc, buf_dma, pkt_len, buf_dma, pkt_len);
 	swdata = cppi5_hdesc_get_swdata(first_desc);
-	*swdata = data;
+	swdata->type = PRUETH_SWDATA_CMD;
+	swdata->data.cmd = le32_to_cpu(data[0]);
 
 	cppi5_hdesc_set_pktlen(first_desc, pkt_len);
 	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
@@ -275,9 +276,9 @@ static struct page *prueth_process_rx_mgm(struct prueth_emac *emac,
 	struct net_device *ndev = emac->ndev;
 	struct cppi5_host_desc_t *desc_rx;
 	struct page *page, *new_page;
+	struct prueth_swdata *swdata;
 	dma_addr_t desc_dma, buf_dma;
 	u32 buf_dma_len;
-	void **swdata;
 	int ret;
 
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
@@ -299,7 +300,7 @@ static struct page *prueth_process_rx_mgm(struct prueth_emac *emac,
 	}
 
 	swdata = cppi5_hdesc_get_swdata(desc_rx);
-	page = *swdata;
+	page = swdata->data.page;
 	cppi5_hdesc_get_obuf(desc_rx, &buf_dma, &buf_dma_len);
 
 	dma_unmap_single(rx_chn->dma_dev, buf_dma, buf_dma_len, DMA_FROM_DEVICE);

From 62aa3246f46234c44a73aa2d37712dd2cb3cbb47 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Wed, 5 Mar 2025 15:44:22 +0530
Subject: [PATCH 1973/2753] net: ti: icssg-prueth: Add XDP support

Add native XDP support. We do not support zero copy yet.

Signed-off-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Link: https://patch.msgid.link/20250305101422.1908370-4-m-malladi@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 225 +++++++++++++++++--
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 128 ++++++++++-
 drivers/net/ethernet/ti/icssg/icssg_prueth.h |  17 ++
 3 files changed, 355 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index fee1204db3672..df5da7a98abf0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -98,11 +98,20 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
 {
 	struct cppi5_host_desc_t *first_desc, *next_desc;
 	dma_addr_t buf_dma, next_desc_dma;
+	struct prueth_swdata *swdata;
+	struct page *page;
 	u32 buf_dma_len;
 
 	first_desc = desc;
 	next_desc = first_desc;
 
+	swdata = cppi5_hdesc_get_swdata(desc);
+	if (swdata->type == PRUETH_SWDATA_PAGE) {
+		page = swdata->data.page;
+		page_pool_recycle_direct(page->pp, swdata->data.page);
+		goto free_desc;
+	}
+
 	cppi5_hdesc_get_obuf(first_desc, &buf_dma, &buf_dma_len);
 	k3_udma_glue_tx_cppi5_to_dma_addr(tx_chn->tx_chn, &buf_dma);
 
@@ -126,6 +135,7 @@ void prueth_xmit_free(struct prueth_tx_chn *tx_chn,
 		k3_cppi_desc_pool_free(tx_chn->desc_pool, next_desc);
 	}
 
+free_desc:
 	k3_cppi_desc_pool_free(tx_chn->desc_pool, first_desc);
 }
 EXPORT_SYMBOL_GPL(prueth_xmit_free);
@@ -139,6 +149,7 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 	struct prueth_swdata *swdata;
 	struct prueth_tx_chn *tx_chn;
 	unsigned int total_bytes = 0;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 	dma_addr_t desc_dma;
 	int res, num_tx = 0;
@@ -161,16 +172,28 @@ int emac_tx_complete_packets(struct prueth_emac *emac, int chn,
 		desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool,
 						     desc_dma);
 		swdata = cppi5_hdesc_get_swdata(desc_tx);
-		prueth_xmit_free(tx_chn, desc_tx);
-		if (swdata->type != PRUETH_SWDATA_SKB)
+
+		switch (swdata->type) {
+		case PRUETH_SWDATA_SKB:
+			skb = swdata->data.skb;
+			dev_sw_netstats_tx_add(skb->dev, 1, skb->len);
+			total_bytes += skb->len;
+			napi_consume_skb(skb, budget);
+			break;
+		case PRUETH_SWDATA_XDPF:
+			xdpf = swdata->data.xdpf;
+			dev_sw_netstats_tx_add(ndev, 1, xdpf->len);
+			total_bytes += xdpf->len;
+			xdp_return_frame(xdpf);
+			break;
+		default:
+			netdev_err(ndev, "tx_complete: invalid swdata type %d\n", swdata->type);
+			prueth_xmit_free(tx_chn, desc_tx);
+			ndev->stats.tx_dropped++;
 			continue;
+		}
 
-		skb = swdata->data.skb;
-		ndev = skb->dev;
-		ndev->stats.tx_packets++;
-		ndev->stats.tx_bytes += skb->len;
-		total_bytes += skb->len;
-		napi_consume_skb(skb, budget);
+		prueth_xmit_free(tx_chn, desc_tx);
 		num_tx++;
 	}
 
@@ -529,7 +552,153 @@ void emac_rx_timestamp(struct prueth_emac *emac,
 	ssh->hwtstamp = ns_to_ktime(ns);
 }
 
-static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
+/**
+ * emac_xmit_xdp_frame - transmits an XDP frame
+ * @emac: emac device
+ * @xdpf: data to transmit
+ * @page: page from page pool if already DMA mapped
+ * @q_idx: queue id
+ *
+ * Return: XDP state
+ */
+u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
+			struct xdp_frame *xdpf,
+			struct page *page,
+			unsigned int q_idx)
+{
+	struct cppi5_host_desc_t *first_desc;
+	struct net_device *ndev = emac->ndev;
+	struct prueth_tx_chn *tx_chn;
+	dma_addr_t desc_dma, buf_dma;
+	struct prueth_swdata *swdata;
+	u32 *epib;
+	int ret;
+
+	if (q_idx >= PRUETH_MAX_TX_QUEUES) {
+		netdev_err(ndev, "xdp tx: invalid q_id %d\n", q_idx);
+		return ICSSG_XDP_CONSUMED;	/* drop */
+	}
+
+	tx_chn = &emac->tx_chns[q_idx];
+
+	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+	if (!first_desc) {
+		netdev_dbg(ndev, "xdp tx: failed to allocate descriptor\n");
+		goto drop_free_descs;	/* drop */
+	}
+
+	if (page) { /* already DMA mapped by page_pool */
+		buf_dma = page_pool_get_dma_addr(page);
+		buf_dma += xdpf->headroom + sizeof(struct xdp_frame);
+	} else { /* Map the linear buffer */
+		buf_dma = dma_map_single(tx_chn->dma_dev, xdpf->data, xdpf->len, DMA_TO_DEVICE);
+		if (dma_mapping_error(tx_chn->dma_dev, buf_dma)) {
+			netdev_err(ndev, "xdp tx: failed to map data buffer\n");
+			goto drop_free_descs;	/* drop */
+		}
+	}
+
+	cppi5_hdesc_init(first_desc, CPPI5_INFO0_HDESC_EPIB_PRESENT,
+			 PRUETH_NAV_PS_DATA_SIZE);
+	cppi5_hdesc_set_pkttype(first_desc, 0);
+	epib = first_desc->epib;
+	epib[0] = 0;
+	epib[1] = 0;
+
+	/* set dst tag to indicate internal qid at the firmware which is at
+	 * bit8..bit15. bit0..bit7 indicates port num for directed
+	 * packets in case of switch mode operation
+	 */
+	cppi5_desc_set_tags_ids(&first_desc->hdr, 0, (emac->port_id | (q_idx << 8)));
+	k3_udma_glue_tx_dma_to_cppi5_addr(tx_chn->tx_chn, &buf_dma);
+	cppi5_hdesc_attach_buf(first_desc, buf_dma, xdpf->len, buf_dma, xdpf->len);
+	swdata = cppi5_hdesc_get_swdata(first_desc);
+	if (page) {
+		swdata->type = PRUETH_SWDATA_PAGE;
+		swdata->data.page = page;
+	} else {
+		swdata->type = PRUETH_SWDATA_XDPF;
+		swdata->data.xdpf = xdpf;
+	}
+
+	cppi5_hdesc_set_pktlen(first_desc, xdpf->len);
+	desc_dma = k3_cppi_desc_pool_virt2dma(tx_chn->desc_pool, first_desc);
+
+	ret = k3_udma_glue_push_tx_chn(tx_chn->tx_chn, first_desc, desc_dma);
+	if (ret) {
+		netdev_err(ndev, "xdp tx: push failed: %d\n", ret);
+		goto drop_free_descs;
+	}
+
+	return ICSSG_XDP_TX;
+
+drop_free_descs:
+	prueth_xmit_free(tx_chn, first_desc);
+	return ICSSG_XDP_CONSUMED;
+}
+EXPORT_SYMBOL_GPL(emac_xmit_xdp_frame);
+
+/**
+ * emac_run_xdp - run an XDP program
+ * @emac: emac device
+ * @xdp: XDP buffer containing the frame
+ * @page: page with RX data if already DMA mapped
+ * @len: Rx descriptor packet length
+ *
+ * Return: XDP state
+ */
+static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
+			struct page *page, u32 *len)
+{
+	struct net_device *ndev = emac->ndev;
+	struct bpf_prog *xdp_prog;
+	struct xdp_frame *xdpf;
+	u32 pkt_len = *len;
+	u32 act, result;
+	int q_idx, err;
+
+	xdp_prog = READ_ONCE(emac->xdp_prog);
+	act = bpf_prog_run_xdp(xdp_prog, xdp);
+	switch (act) {
+	case XDP_PASS:
+		return ICSSG_XDP_PASS;
+	case XDP_TX:
+		/* Send packet to TX ring for immediate transmission */
+		xdpf = xdp_convert_buff_to_frame(xdp);
+		if (unlikely(!xdpf)) {
+			ndev->stats.tx_dropped++;
+			goto drop;
+		}
+
+		q_idx = smp_processor_id() % emac->tx_ch_num;
+		result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
+		if (result == ICSSG_XDP_CONSUMED)
+			goto drop;
+
+		dev_sw_netstats_rx_add(ndev, xdpf->len);
+		return result;
+	case XDP_REDIRECT:
+		err = xdp_do_redirect(emac->ndev, xdp, xdp_prog);
+		if (err)
+			goto drop;
+
+		dev_sw_netstats_rx_add(ndev, pkt_len);
+		return ICSSG_XDP_REDIR;
+	default:
+		bpf_warn_invalid_xdp_action(emac->ndev, xdp_prog, act);
+		fallthrough;
+	case XDP_ABORTED:
+drop:
+		trace_xdp_exception(emac->ndev, xdp_prog, act);
+		fallthrough; /* handle aborts by dropping packet */
+	case XDP_DROP:
+		ndev->stats.rx_dropped++;
+		page_pool_recycle_direct(emac->rx_chns.pg_pool, page);
+		return ICSSG_XDP_CONSUMED;
+	}
+}
+
+static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id, u32 *xdp_state)
 {
 	struct prueth_rx_chn *rx_chn = &emac->rx_chns;
 	u32 buf_dma_len, pkt_len, port_id = 0;
@@ -540,10 +709,12 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 	struct page *page, *new_page;
 	struct page_pool *pool;
 	struct sk_buff *skb;
+	struct xdp_buff xdp;
 	u32 *psdata;
 	void *pa;
 	int ret;
 
+	*xdp_state = 0;
 	pool = rx_chn->pg_pool;
 	ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_id, &desc_dma);
 	if (ret) {
@@ -584,9 +755,21 @@ static int emac_rx_packet(struct prueth_emac *emac, u32 flow_id)
 		goto requeue;
 	}
 
-	/* prepare skb and send to n/w stack */
 	pa = page_address(page);
-	skb = napi_build_skb(pa, PAGE_SIZE);
+	if (emac->xdp_prog) {
+		xdp_init_buff(&xdp, PAGE_SIZE, &rx_chn->xdp_rxq);
+		xdp_prepare_buff(&xdp, pa, PRUETH_HEADROOM, pkt_len, false);
+
+		*xdp_state = emac_run_xdp(emac, &xdp, page, &pkt_len);
+		if (*xdp_state == ICSSG_XDP_PASS)
+			skb = xdp_build_skb_from_buff(&xdp);
+		else
+			goto requeue;
+	} else {
+		/* prepare skb and send to n/w stack */
+		skb = napi_build_skb(pa, PAGE_SIZE);
+	}
+
 	if (!skb) {
 		ndev->stats.rx_dropped++;
 		page_pool_recycle_direct(pool, page);
@@ -849,13 +1032,23 @@ static void prueth_tx_cleanup(void *data, dma_addr_t desc_dma)
 	struct prueth_tx_chn *tx_chn = data;
 	struct cppi5_host_desc_t *desc_tx;
 	struct prueth_swdata *swdata;
+	struct xdp_frame *xdpf;
 	struct sk_buff *skb;
 
 	desc_tx = k3_cppi_desc_pool_dma2virt(tx_chn->desc_pool, desc_dma);
 	swdata = cppi5_hdesc_get_swdata(desc_tx);
-	if (swdata->type == PRUETH_SWDATA_SKB) {
+
+	switch (swdata->type) {
+	case PRUETH_SWDATA_SKB:
 		skb = swdata->data.skb;
 		dev_kfree_skb_any(skb);
+		break;
+	case PRUETH_SWDATA_XDPF:
+		xdpf = swdata->data.xdpf;
+		xdp_return_frame(xdpf);
+		break;
+	default:
+		break;
 	}
 
 	prueth_xmit_free(tx_chn, desc_tx);
@@ -892,15 +1085,18 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 		PRUETH_RX_FLOW_DATA_SR1 : PRUETH_RX_FLOW_DATA;
 	int flow = emac->is_sr1 ?
 		PRUETH_MAX_RX_FLOWS_SR1 : PRUETH_MAX_RX_FLOWS;
+	int xdp_state_or = 0;
 	int num_rx = 0;
 	int cur_budget;
+	u32 xdp_state;
 	int ret;
 
 	while (flow--) {
 		cur_budget = budget - num_rx;
 
 		while (cur_budget--) {
-			ret = emac_rx_packet(emac, flow);
+			ret = emac_rx_packet(emac, flow, &xdp_state);
+			xdp_state_or |= xdp_state;
 			if (ret)
 				break;
 			num_rx++;
@@ -910,6 +1106,9 @@ int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget)
 			break;
 	}
 
+	if (xdp_state_or & ICSSG_XDP_REDIR)
+		xdp_do_flush();
+
 	if (num_rx < budget && napi_complete_done(napi_rx, num_rx)) {
 		if (unlikely(emac->rx_pace_timeout_ns)) {
 			hrtimer_start(&emac->rx_hrtimer,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 3ff8c322f9d93..c4a995630eca9 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -559,6 +559,33 @@ const struct icss_iep_clockops prueth_iep_clockops = {
 	.perout_enable = prueth_perout_enable,
 };
 
+static int prueth_create_xdp_rxqs(struct prueth_emac *emac)
+{
+	struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq;
+	struct page_pool *pool = emac->rx_chns.pg_pool;
+	int ret;
+
+	ret = xdp_rxq_info_reg(rxq, emac->ndev, 0, emac->napi_rx.napi_id);
+	if (ret)
+		return ret;
+
+	ret = xdp_rxq_info_reg_mem_model(rxq, MEM_TYPE_PAGE_POOL, pool);
+	if (ret)
+		xdp_rxq_info_unreg(rxq);
+
+	return ret;
+}
+
+static void prueth_destroy_xdp_rxqs(struct prueth_emac *emac)
+{
+	struct xdp_rxq_info *rxq = &emac->rx_chns.xdp_rxq;
+
+	if (!xdp_rxq_info_is_reg(rxq))
+		return;
+
+	xdp_rxq_info_unreg(rxq);
+}
+
 static int icssg_prueth_add_mcast(struct net_device *ndev, const u8 *addr)
 {
 	struct net_device *real_dev;
@@ -780,10 +807,14 @@ static int emac_ndo_open(struct net_device *ndev)
 	if (ret)
 		goto free_tx_ts_irq;
 
-	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	ret = prueth_create_xdp_rxqs(emac);
 	if (ret)
 		goto reset_rx_chn;
 
+	ret = k3_udma_glue_enable_rx_chn(emac->rx_chns.rx_chn);
+	if (ret)
+		goto destroy_xdp_rxqs;
+
 	for (i = 0; i < emac->tx_ch_num; i++) {
 		ret = k3_udma_glue_enable_tx_chn(emac->tx_chns[i].tx_chn);
 		if (ret)
@@ -809,6 +840,8 @@ static int emac_ndo_open(struct net_device *ndev)
 	 * any SKB for completion. So set false to free_skb
 	 */
 	prueth_reset_tx_chan(emac, i, false);
+destroy_xdp_rxqs:
+	prueth_destroy_xdp_rxqs(emac);
 reset_rx_chn:
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, false);
 free_tx_ts_irq:
@@ -879,7 +912,7 @@ static int emac_ndo_stop(struct net_device *ndev)
 	k3_udma_glue_tdown_rx_chn(emac->rx_chns.rx_chn, true);
 
 	prueth_reset_rx_chan(&emac->rx_chns, max_rx_flows, true);
-
+	prueth_destroy_xdp_rxqs(emac);
 	napi_disable(&emac->napi_rx);
 	hrtimer_cancel(&emac->rx_hrtimer);
 
@@ -1024,6 +1057,93 @@ static int emac_ndo_vlan_rx_del_vid(struct net_device *ndev,
 	return 0;
 }
 
+/**
+ * emac_xdp_xmit - Implements ndo_xdp_xmit
+ * @dev: netdev
+ * @n: number of frames
+ * @frames: array of XDP buffer pointers
+ * @flags: XDP extra info
+ *
+ * Return: number of frames successfully sent. Failed frames
+ * will be free'ed by XDP core.
+ *
+ * For error cases, a negative errno code is returned and no-frames
+ * are transmitted (caller must handle freeing frames).
+ **/
+static int emac_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
+			 u32 flags)
+{
+	struct prueth_emac *emac = netdev_priv(dev);
+	struct net_device *ndev = emac->ndev;
+	struct xdp_frame *xdpf;
+	unsigned int q_idx;
+	int nxmit = 0;
+	u32 err;
+	int i;
+
+	q_idx = smp_processor_id() % emac->tx_ch_num;
+
+	if (unlikely(flags & ~XDP_XMIT_FLAGS_MASK))
+		return -EINVAL;
+
+	for (i = 0; i < n; i++) {
+		xdpf = frames[i];
+		err = emac_xmit_xdp_frame(emac, xdpf, NULL, q_idx);
+		if (err != ICSSG_XDP_TX) {
+			ndev->stats.tx_dropped++;
+			break;
+		}
+		nxmit++;
+	}
+
+	return nxmit;
+}
+
+/**
+ * emac_xdp_setup - add/remove an XDP program
+ * @emac: emac device
+ * @bpf: XDP program
+ *
+ * Return: Always 0 (Success)
+ **/
+static int emac_xdp_setup(struct prueth_emac *emac, struct netdev_bpf *bpf)
+{
+	struct bpf_prog *prog = bpf->prog;
+	xdp_features_t val;
+
+	val = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
+	      NETDEV_XDP_ACT_NDO_XMIT;
+	xdp_set_features_flag(emac->ndev, val);
+
+	if (!emac->xdpi.prog && !prog)
+		return 0;
+
+	WRITE_ONCE(emac->xdp_prog, prog);
+
+	xdp_attachment_setup(&emac->xdpi, bpf);
+
+	return 0;
+}
+
+/**
+ * emac_ndo_bpf - implements ndo_bpf for icssg_prueth
+ * @ndev: network adapter device
+ * @bpf: XDP program
+ *
+ * Return: 0 on success, error code on failure.
+ **/
+static int emac_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+{
+	struct prueth_emac *emac = netdev_priv(ndev);
+
+	switch (bpf->command) {
+	case XDP_SETUP_PROG:
+		return emac_xdp_setup(emac, bpf);
+	default:
+		return -EINVAL;
+	}
+}
+
 static const struct net_device_ops emac_netdev_ops = {
 	.ndo_open = emac_ndo_open,
 	.ndo_stop = emac_ndo_stop,
@@ -1038,6 +1158,8 @@ static const struct net_device_ops emac_netdev_ops = {
 	.ndo_fix_features = emac_ndo_fix_features,
 	.ndo_vlan_rx_add_vid = emac_ndo_vlan_rx_add_vid,
 	.ndo_vlan_rx_kill_vid = emac_ndo_vlan_rx_del_vid,
+	.ndo_bpf = emac_ndo_bpf,
+	.ndo_xdp_xmit = emac_xdp_xmit,
 };
 
 static int prueth_netdev_init(struct prueth *prueth,
@@ -1066,6 +1188,8 @@ static int prueth_netdev_init(struct prueth *prueth,
 	emac->prueth = prueth;
 	emac->ndev = ndev;
 	emac->port_id = port;
+	emac->xdp_prog = NULL;
+	emac->ndev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 	emac->cmd_wq = create_singlethread_workqueue("icssg_cmd_wq");
 	if (!emac->cmd_wq) {
 		ret = -ENOMEM;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 3bbabd0071299..1dd76e2adfcd0 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -8,6 +8,8 @@
 #ifndef __NET_TI_ICSSG_PRUETH_H
 #define __NET_TI_ICSSG_PRUETH_H
 
+#include <linux/bpf.h>
+#include <linux/bpf_trace.h>
 #include <linux/etherdevice.h>
 #include <linux/genalloc.h>
 #include <linux/if_vlan.h>
@@ -134,6 +136,7 @@ struct prueth_rx_chn {
 	unsigned int irq[ICSSG_MAX_RFLOWS];	/* separate irq per flow */
 	char name[32];
 	struct page_pool *pg_pool;
+	struct xdp_rxq_info xdp_rxq;
 };
 
 enum prueth_swdata_type {
@@ -141,6 +144,7 @@ enum prueth_swdata_type {
 	PRUETH_SWDATA_SKB,
 	PRUETH_SWDATA_PAGE,
 	PRUETH_SWDATA_CMD,
+	PRUETH_SWDATA_XDPF,
 };
 
 struct prueth_swdata {
@@ -149,6 +153,7 @@ struct prueth_swdata {
 		struct sk_buff *skb;
 		struct page *page;
 		u32 cmd;
+		struct xdp_frame *xdpf;
 	} data;
 };
 
@@ -159,6 +164,12 @@ struct prueth_swdata {
 
 #define PRUETH_MAX_TX_TS_REQUESTS	50 /* Max simultaneous TX_TS requests */
 
+/* XDP BPF state */
+#define ICSSG_XDP_PASS           0
+#define ICSSG_XDP_CONSUMED       BIT(0)
+#define ICSSG_XDP_TX             BIT(1)
+#define ICSSG_XDP_REDIR          BIT(2)
+
 /* Minimum coalesce time in usecs for both Tx and Rx */
 #define ICSSG_MIN_COALESCE_USECS 20
 
@@ -227,6 +238,8 @@ struct prueth_emac {
 	unsigned long rx_pace_timeout_ns;
 
 	struct netdev_hw_addr_list vlan_mcast_list[MAX_VLAN_ID];
+	struct bpf_prog *xdp_prog;
+	struct xdp_attachment_info xdpi;
 };
 
 /* The buf includes headroom compatible with both skb and xdpf */
@@ -465,5 +478,9 @@ void prueth_put_cores(struct prueth *prueth, int slice);
 
 /* Revision specific helper */
 u64 icssg_ts_to_ns(u32 hi_sw, u32 hi, u32 lo, u32 cycle_time_ns);
+u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
+			struct xdp_frame *xdpf,
+			struct page *page,
+			unsigned int q_idx);
 
 #endif /* __NET_TI_ICSSG_PRUETH_H */

From 62531a1effa87bdab12d5104015af72e60d926ff Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Wed, 5 Mar 2025 14:15:09 +0200
Subject: [PATCH 1974/2753] net: switchdev: Convert blocking notification chain
 to a raw one

A blocking notification chain uses a read-write semaphore to protect the
integrity of the chain. The semaphore is acquired for writing when
adding / removing notifiers to / from the chain and acquired for reading
when traversing the chain and informing notifiers about an event.

In case of the blocking switchdev notification chain, recursive
notifications are possible which leads to the semaphore being acquired
twice for reading and to lockdep warnings being generated [1].

Specifically, this can happen when the bridge driver processes a
SWITCHDEV_BRPORT_UNOFFLOADED event which causes it to emit notifications
about deferred events when calling switchdev_deferred_process().

Fix this by converting the notification chain to a raw notification
chain in a similar fashion to the netdev notification chain. Protect
the chain using the RTNL mutex by acquiring it when modifying the chain.
Events are always informed under the RTNL mutex, but add an assertion in
call_switchdev_blocking_notifiers() to make sure this is not violated in
the future.

Maintain the "blocking" prefix as events are always emitted from process
context and listeners are allowed to block.

[1]:
WARNING: possible recursive locking detected
6.14.0-rc4-custom-g079270089484 #1 Not tainted
--------------------------------------------
ip/52731 is trying to acquire lock:
ffffffff850918d8 ((switchdev_blocking_notif_chain).rwsem){++++}-{4:4}, at: blocking_notifier_call_chain+0x58/0xa0

but task is already holding lock:
ffffffff850918d8 ((switchdev_blocking_notif_chain).rwsem){++++}-{4:4}, at: blocking_notifier_call_chain+0x58/0xa0

other info that might help us debug this:
Possible unsafe locking scenario:
CPU0
----
lock((switchdev_blocking_notif_chain).rwsem);
lock((switchdev_blocking_notif_chain).rwsem);

*** DEADLOCK ***
May be due to missing lock nesting notation
3 locks held by ip/52731:
 #0: ffffffff84f795b0 (rtnl_mutex){+.+.}-{4:4}, at: rtnl_newlink+0x727/0x1dc0
 #1: ffffffff8731f628 (&net->rtnl_mutex){+.+.}-{4:4}, at: rtnl_newlink+0x790/0x1dc0
 #2: ffffffff850918d8 ((switchdev_blocking_notif_chain).rwsem){++++}-{4:4}, at: blocking_notifier_call_chain+0x58/0xa0

stack backtrace:
...
? __pfx_down_read+0x10/0x10
? __pfx_mark_lock+0x10/0x10
? __pfx_switchdev_port_attr_set_deferred+0x10/0x10
blocking_notifier_call_chain+0x58/0xa0
switchdev_port_attr_notify.constprop.0+0xb3/0x1b0
? __pfx_switchdev_port_attr_notify.constprop.0+0x10/0x10
? mark_held_locks+0x94/0xe0
? switchdev_deferred_process+0x11a/0x340
switchdev_port_attr_set_deferred+0x27/0xd0
switchdev_deferred_process+0x164/0x340
br_switchdev_port_unoffload+0xc8/0x100 [bridge]
br_switchdev_blocking_event+0x29f/0x580 [bridge]
notifier_call_chain+0xa2/0x440
blocking_notifier_call_chain+0x6e/0xa0
switchdev_bridge_port_unoffload+0xde/0x1a0
...

Fixes: f7a70d650b0b6 ("net: bridge: switchdev: Ensure deferred event delivery on unoffload")
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Tested-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20250305121509.631207-1-amcohen@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/switchdev/switchdev.c | 25 ++++++++++++++++++-------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 6488ead9e4645..4d5fbacef496f 100644
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -472,7 +472,7 @@ bool switchdev_port_obj_act_is_deferred(struct net_device *dev,
 EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred);
 
 static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
-static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain);
+static RAW_NOTIFIER_HEAD(switchdev_blocking_notif_chain);
 
 /**
  *	register_switchdev_notifier - Register notifier
@@ -518,17 +518,27 @@ EXPORT_SYMBOL_GPL(call_switchdev_notifiers);
 
 int register_switchdev_blocking_notifier(struct notifier_block *nb)
 {
-	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;
+	struct raw_notifier_head *chain = &switchdev_blocking_notif_chain;
+	int err;
+
+	rtnl_lock();
+	err = raw_notifier_chain_register(chain, nb);
+	rtnl_unlock();
 
-	return blocking_notifier_chain_register(chain, nb);
+	return err;
 }
 EXPORT_SYMBOL_GPL(register_switchdev_blocking_notifier);
 
 int unregister_switchdev_blocking_notifier(struct notifier_block *nb)
 {
-	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;
+	struct raw_notifier_head *chain = &switchdev_blocking_notif_chain;
+	int err;
 
-	return blocking_notifier_chain_unregister(chain, nb);
+	rtnl_lock();
+	err = raw_notifier_chain_unregister(chain, nb);
+	rtnl_unlock();
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier);
 
@@ -536,10 +546,11 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
 				      struct switchdev_notifier_info *info,
 				      struct netlink_ext_ack *extack)
 {
+	ASSERT_RTNL();
 	info->dev = dev;
 	info->extack = extack;
-	return blocking_notifier_call_chain(&switchdev_blocking_notif_chain,
-					    val, info);
+	return raw_notifier_call_chain(&switchdev_blocking_notif_chain,
+				       val, info);
 }
 EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers);
 

From d4234d131b0a3f9e65973f1cdc71bb3560f5d14b Mon Sep 17 00:00:00 2001
From: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Date: Tue, 4 Mar 2025 15:27:00 +0800
Subject: [PATCH 1975/2753] arm64: mm: Populate vmemmap at the page level if
 not section aligned

On the arm64 platform with 4K base page config, SECTION_SIZE_BITS is set
to 27, making one section 128M. The related page struct which vmemmap
points to is 2M then.
Commit c1cc1552616d ("arm64: MMU initialisation") optimizes the
vmemmap to populate at the PMD section level which was suitable
initially since hot plug granule is always one section(128M). However,
commit ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug")
introduced a 2M(SUBSECTION_SIZE) hot plug granule, which disrupted the
existing arm64 assumptions.

The first problem is that if start or end is not aligned to a section
boundary, such as when a subsection is hot added, populating the entire
section is wasteful.

The next problem is if we hotplug something that spans part of 128 MiB
section (subsections, let's call it memblock1), and then hotplug something
that spans another part of a 128 MiB section(subsections, let's call it
memblock2), and subsequently unplug memblock1, vmemmap_free() will clear
the entire PMD entry which also supports memblock2 even though memblock2
is still active.

Assuming hotplug/unplug sizes are guaranteed to be symmetric. Do the
fix similar to x86-64: populate to pages levels if start/end is not aligned
with section boundary.

Cc: stable@vger.kernel.org # v5.4+
Fixes: ba72b4c8cf60 ("mm/sparsemem: support sub-section hotplug")
Acked-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250304072700.3405036-1-quic_zhenhuah@quicinc.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/mm/mmu.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index b4df5bc5b1b8b..1dfe1a8efdbe4 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1177,8 +1177,11 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+	/* [start, end] should be within one section */
+	WARN_ON_ONCE(end - start > PAGES_PER_SECTION * sizeof(struct page));
 
-	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES))
+	if (!IS_ENABLED(CONFIG_ARM64_4K_PAGES) ||
+	    (end - start < PAGES_PER_SECTION * sizeof(struct page)))
 		return vmemmap_populate_basepages(start, end, node, altmap);
 	else
 		return vmemmap_populate_hugepages(start, end, node, altmap);

From f7edb07ad7c66eab3dce57384f33b9799d579133 Mon Sep 17 00:00:00 2001
From: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Date: Tue, 4 Mar 2025 00:51:27 -0800
Subject: [PATCH 1976/2753] Fix mmu notifiers for range-based invalidates

Update the __flush_tlb_range_op macro not to modify its parameters as
these are unexepcted semantics. In practice, this fixes the call to
mmu_notifier_arch_invalidate_secondary_tlbs() in
__flush_tlb_range_nosync() to use the correct range instead of an empty
range with start=end. The empty range was (un)lucky as it results in
taking the invalidate-all path that doesn't cause correctness issues,
but can certainly result in suboptimal perf.

This has been broken since commit 6bbd42e2df8f ("mmu_notifiers: call
invalidate_range() when invalidating TLBs") when the call to the
notifiers was added to __flush_tlb_range(). It predates the addition of
the __flush_tlb_range_op() macro from commit 360839027a6e ("arm64: tlb:
Refactor the core flush algorithm of __flush_tlb_range") that made the
bug hard to spot.

Fixes: 6bbd42e2df8f ("mmu_notifiers: call invalidate_range() when invalidating TLBs")

Signed-off-by: Piotr Jaroszynski <pjaroszynski@nvidia.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Raghavendra Rao Ananta <rananta@google.com>
Cc: SeongJae Park <sj@kernel.org>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Nicolin Chen <nicolinc@nvidia.com>
Cc: linux-arm-kernel@lists.infradead.org
Cc: iommu@lists.linux.dev
Cc: linux-mm@kvack.org
Cc: linux-kernel@vger.kernel.org
Cc: stable@vger.kernel.org
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Alistair Popple <apopple@nvidia.com>
Link: https://lore.kernel.org/r/20250304085127.2238030-1-pjaroszynski@nvidia.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 arch/arm64/include/asm/tlbflush.h | 22 ++++++++++++----------
 1 file changed, 12 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index bc94e036a26b9..8104aee4f9a08 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -396,33 +396,35 @@ static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
 #define __flush_tlb_range_op(op, start, pages, stride,			\
 				asid, tlb_level, tlbi_user, lpa2)	\
 do {									\
+	typeof(start) __flush_start = start;				\
+	typeof(pages) __flush_pages = pages;				\
 	int num = 0;							\
 	int scale = 3;							\
 	int shift = lpa2 ? 16 : PAGE_SHIFT;				\
 	unsigned long addr;						\
 									\
-	while (pages > 0) {						\
+	while (__flush_pages > 0) {					\
 		if (!system_supports_tlb_range() ||			\
-		    pages == 1 ||					\
-		    (lpa2 && start != ALIGN(start, SZ_64K))) {		\
-			addr = __TLBI_VADDR(start, asid);		\
+		    __flush_pages == 1 ||				\
+		    (lpa2 && __flush_start != ALIGN(__flush_start, SZ_64K))) {	\
+			addr = __TLBI_VADDR(__flush_start, asid);	\
 			__tlbi_level(op, addr, tlb_level);		\
 			if (tlbi_user)					\
 				__tlbi_user_level(op, addr, tlb_level);	\
-			start += stride;				\
-			pages -= stride >> PAGE_SHIFT;			\
+			__flush_start += stride;			\
+			__flush_pages -= stride >> PAGE_SHIFT;		\
 			continue;					\
 		}							\
 									\
-		num = __TLBI_RANGE_NUM(pages, scale);			\
+		num = __TLBI_RANGE_NUM(__flush_pages, scale);		\
 		if (num >= 0) {						\
-			addr = __TLBI_VADDR_RANGE(start >> shift, asid, \
+			addr = __TLBI_VADDR_RANGE(__flush_start >> shift, asid, \
 						scale, num, tlb_level);	\
 			__tlbi(r##op, addr);				\
 			if (tlbi_user)					\
 				__tlbi_user(r##op, addr);		\
-			start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
-			pages -= __TLBI_RANGE_PAGES(num, scale);	\
+			__flush_start += __TLBI_RANGE_PAGES(num, scale) << PAGE_SHIFT; \
+			__flush_pages -= __TLBI_RANGE_PAGES(num, scale);\
 		}							\
 		scale--;						\
 	}								\

From 986a6f5eacb900ea0f6036ef724b26e76be40f65 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 10 Mar 2025 15:25:31 -0700
Subject: [PATCH 1977/2753] vboxsf: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to and correctly identify the char array as "not a C
string" and thereby eliminate the warning.

This effectively reverts the change in 4e7487245abc ("vboxsf: fix building
with GCC 15"), to add the annotation that has other uses (i.e. warning
if the string is ever used with C string APIs).

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Cc: Hans de Goede <hdegoede@redhat.com>
Cc: Brahmajit Das <brahmajit.xyz@gmail.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://lore.kernel.org/r/20250310222530.work.374-kees@kernel.org
Reviewed-by: Hans de Goede <hdegoede@redhat.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/vboxsf/super.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 1d94bb7841081..0bc96ab6580b3 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -21,8 +21,7 @@
 
 #define VBOXSF_SUPER_MAGIC 0x786f4256 /* 'VBox' little endian */
 
-static const unsigned char VBSF_MOUNT_SIGNATURE[4] = { '\000', '\377', '\376',
-						       '\375' };
+static const unsigned char VBSF_MOUNT_SIGNATURE[4] __nonstring = "\000\377\376\375";
 
 static int follow_symlinks;
 module_param(follow_symlinks, int, 0444);

From f5d83cf0eeb90fade4d5c4d17d24b8bee9ceeecc Mon Sep 17 00:00:00 2001
From: Matt Johnston <matt@codeconstruct.com.au>
Date: Thu, 6 Mar 2025 10:32:45 +0800
Subject: [PATCH 1978/2753] net: mctp: unshare packets when reassembling

Ensure that the frag_list used for reassembly isn't shared with other
packets. This avoids incorrect reassembly when packets are cloned, and
prevents a memory leak due to circular references between fragments and
their skb_shared_info.

The upcoming MCTP-over-USB driver uses skb_clone which can trigger the
problem - other MCTP drivers don't share SKBs.

A kunit test is added to reproduce the issue.

Signed-off-by: Matt Johnston <matt@codeconstruct.com.au>
Fixes: 4a992bbd3650 ("mctp: Implement message fragmentation & reassembly")
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306-matt-mctp-usb-v1-1-085502b3dd28@codeconstruct.com.au
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mctp/route.c           |  10 +++-
 net/mctp/test/route-test.c | 109 +++++++++++++++++++++++++++++++++++++
 2 files changed, 117 insertions(+), 2 deletions(-)

diff --git a/net/mctp/route.c b/net/mctp/route.c
index 3f2bd65ff5e3c..4c460160914f0 100644
--- a/net/mctp/route.c
+++ b/net/mctp/route.c
@@ -332,8 +332,14 @@ static int mctp_frag_queue(struct mctp_sk_key *key, struct sk_buff *skb)
 		& MCTP_HDR_SEQ_MASK;
 
 	if (!key->reasm_head) {
-		key->reasm_head = skb;
-		key->reasm_tailp = &(skb_shinfo(skb)->frag_list);
+		/* Since we're manipulating the shared frag_list, ensure it isn't
+		 * shared with any other SKBs.
+		 */
+		key->reasm_head = skb_unshare(skb, GFP_ATOMIC);
+		if (!key->reasm_head)
+			return -ENOMEM;
+
+		key->reasm_tailp = &(skb_shinfo(key->reasm_head)->frag_list);
 		key->last_seq = this_seq;
 		return 0;
 	}
diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 17165b86ce22d..06c1897b685a8 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -921,6 +921,114 @@ static void mctp_test_route_input_sk_fail_frag(struct kunit *test)
 	__mctp_route_test_fini(test, dev, rt, sock);
 }
 
+/* Input route to socket, using a fragmented message created from clones.
+ */
+static void mctp_test_route_input_cloned_frag(struct kunit *test)
+{
+	/* 5 packet fragments, forming 2 complete messages */
+	const struct mctp_hdr hdrs[5] = {
+		RX_FRAG(FL_S, 0),
+		RX_FRAG(0, 1),
+		RX_FRAG(FL_E, 2),
+		RX_FRAG(FL_S, 0),
+		RX_FRAG(FL_E, 1),
+	};
+	struct mctp_test_route *rt;
+	struct mctp_test_dev *dev;
+	struct sk_buff *skb[5];
+	struct sk_buff *rx_skb;
+	struct socket *sock;
+	size_t data_len;
+	u8 compare[100];
+	u8 flat[100];
+	size_t total;
+	void *p;
+	int rc;
+
+	/* Arbitrary length */
+	data_len = 3;
+	total = data_len + sizeof(struct mctp_hdr);
+
+	__mctp_route_test_init(test, &dev, &rt, &sock, MCTP_NET_ANY);
+
+	/* Create a single skb initially with concatenated packets */
+	skb[0] = mctp_test_create_skb(&hdrs[0], 5 * total);
+	mctp_test_skb_set_dev(skb[0], dev);
+	memset(skb[0]->data, 0 * 0x11, skb[0]->len);
+	memcpy(skb[0]->data, &hdrs[0], sizeof(struct mctp_hdr));
+
+	/* Extract and populate packets */
+	for (int i = 1; i < 5; i++) {
+		skb[i] = skb_clone(skb[i - 1], GFP_ATOMIC);
+		KUNIT_ASSERT_TRUE(test, skb[i]);
+		p = skb_pull(skb[i], total);
+		KUNIT_ASSERT_TRUE(test, p);
+		skb_reset_network_header(skb[i]);
+		memcpy(skb[i]->data, &hdrs[i], sizeof(struct mctp_hdr));
+		memset(&skb[i]->data[sizeof(struct mctp_hdr)], i * 0x11, data_len);
+	}
+	for (int i = 0; i < 5; i++)
+		skb_trim(skb[i], total);
+
+	/* SOM packets have a type byte to match the socket */
+	skb[0]->data[4] = 0;
+	skb[3]->data[4] = 0;
+
+	skb_dump("pkt1 ", skb[0], false);
+	skb_dump("pkt2 ", skb[1], false);
+	skb_dump("pkt3 ", skb[2], false);
+	skb_dump("pkt4 ", skb[3], false);
+	skb_dump("pkt5 ", skb[4], false);
+
+	for (int i = 0; i < 5; i++) {
+		KUNIT_EXPECT_EQ(test, refcount_read(&skb[i]->users), 1);
+		/* Take a reference so we can check refcounts at the end */
+		skb_get(skb[i]);
+	}
+
+	/* Feed the fragments into MCTP core */
+	for (int i = 0; i < 5; i++) {
+		rc = mctp_route_input(&rt->rt, skb[i]);
+		KUNIT_EXPECT_EQ(test, rc, 0);
+	}
+
+	/* Receive first reassembled message */
+	rx_skb = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+	KUNIT_EXPECT_EQ(test, rc, 0);
+	KUNIT_EXPECT_EQ(test, rx_skb->len, 3 * data_len);
+	rc = skb_copy_bits(rx_skb, 0, flat, rx_skb->len);
+	for (int i = 0; i < rx_skb->len; i++)
+		compare[i] = (i / data_len) * 0x11;
+	/* Set type byte */
+	compare[0] = 0;
+
+	KUNIT_EXPECT_MEMEQ(test, flat, compare, rx_skb->len);
+	KUNIT_EXPECT_EQ(test, refcount_read(&rx_skb->users), 1);
+	kfree_skb(rx_skb);
+
+	/* Receive second reassembled message */
+	rx_skb = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+	KUNIT_EXPECT_EQ(test, rc, 0);
+	KUNIT_EXPECT_EQ(test, rx_skb->len, 2 * data_len);
+	rc = skb_copy_bits(rx_skb, 0, flat, rx_skb->len);
+	for (int i = 0; i < rx_skb->len; i++)
+		compare[i] = (i / data_len + 3) * 0x11;
+	/* Set type byte */
+	compare[0] = 0;
+
+	KUNIT_EXPECT_MEMEQ(test, flat, compare, rx_skb->len);
+	KUNIT_EXPECT_EQ(test, refcount_read(&rx_skb->users), 1);
+	kfree_skb(rx_skb);
+
+	/* Check input skb refcounts */
+	for (int i = 0; i < 5; i++) {
+		KUNIT_EXPECT_EQ(test, refcount_read(&skb[i]->users), 1);
+		kfree_skb(skb[i]);
+	}
+
+	__mctp_route_test_fini(test, dev, rt, sock);
+}
+
 #if IS_ENABLED(CONFIG_MCTP_FLOWS)
 
 static void mctp_test_flow_init(struct kunit *test,
@@ -1144,6 +1252,7 @@ static struct kunit_case mctp_test_cases[] = {
 	KUNIT_CASE(mctp_test_packet_flow),
 	KUNIT_CASE(mctp_test_fragment_flow),
 	KUNIT_CASE(mctp_test_route_output_key_create),
+	KUNIT_CASE(mctp_test_route_input_cloned_frag),
 	{}
 };
 

From 0c5e145a350de3b38cd5ae77a401b12c46fb7c1d Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 6 Mar 2025 02:39:22 +0000
Subject: [PATCH 1979/2753] bonding: fix incorrect MAC address setting to
 receive NS messages

When validation on the backup slave is enabled, we need to validate the
Neighbor Solicitation (NS) messages received on the backup slave. To
receive these messages, the correct destination MAC address must be added
to the slave. However, the target in bonding is a unicast address, which
we cannot use directly. Instead, we should first convert it to a
Solicited-Node Multicast Address and then derive the corresponding MAC
address.

Fix the incorrect MAC address setting on both slave_set_ns_maddr() and
slave_set_ns_maddrs(). Since the two function names are similar. Add
some description for the functions. Also only use one mac_addr variable
in slave_set_ns_maddr() to save some code and logic.

Fixes: 8eb36164d1a6 ("bonding: add ns target multicast address to slave device")
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306023923.38777-2-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_options.c | 55 +++++++++++++++++++++++++-----
 1 file changed, 47 insertions(+), 8 deletions(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index 327b6ecdc77e0..d1b095af253bd 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -1242,10 +1242,28 @@ static bool slave_can_set_ns_maddr(const struct bonding *bond, struct slave *sla
 	       slave->dev->flags & IFF_MULTICAST;
 }
 
+/**
+ * slave_set_ns_maddrs - add/del all NS mac addresses for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @add: add or remove all the NS mac addresses
+ *
+ * This function tries to add or delete all the NS mac addresses on the slave
+ *
+ * Note, the IPv6 NS target address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * arp_validate changes
+ *   * enslaving, releasing new slaves
+ */
 static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool add)
 {
 	struct in6_addr *targets = bond->params.ns_targets;
 	char slot_maddr[MAX_ADDR_LEN];
+	struct in6_addr mcaddr;
 	int i;
 
 	if (!slave_can_set_ns_maddr(bond, slave))
@@ -1255,7 +1273,8 @@ static void slave_set_ns_maddrs(struct bonding *bond, struct slave *slave, bool
 		if (ipv6_addr_any(&targets[i]))
 			break;
 
-		if (!ndisc_mc_map(&targets[i], slot_maddr, slave->dev, 0)) {
+		addrconf_addr_solict_mult(&targets[i], &mcaddr);
+		if (!ndisc_mc_map(&mcaddr, slot_maddr, slave->dev, 0)) {
 			if (add)
 				dev_mc_add(slave->dev, slot_maddr);
 			else
@@ -1278,23 +1297,43 @@ void bond_slave_ns_maddrs_del(struct bonding *bond, struct slave *slave)
 	slave_set_ns_maddrs(bond, slave, false);
 }
 
+/**
+ * slave_set_ns_maddr - set new NS mac address for slave
+ * @bond: bond device
+ * @slave: slave device
+ * @target: the new IPv6 target
+ * @slot: the old IPv6 target in the slot
+ *
+ * This function tries to replace the old mac address to new one on the slave.
+ *
+ * Note, the target/slot IPv6 address is the unicast address in Neighbor
+ * Solicitation (NS) message. The dest address of NS message should be
+ * solicited-node multicast address of the target. The dest mac of NS message
+ * is converted from the solicited-node multicast address.
+ *
+ * This function is called when
+ *   * An IPv6 NS target is added or removed.
+ */
 static void slave_set_ns_maddr(struct bonding *bond, struct slave *slave,
 			       struct in6_addr *target, struct in6_addr *slot)
 {
-	char target_maddr[MAX_ADDR_LEN], slot_maddr[MAX_ADDR_LEN];
+	char mac_addr[MAX_ADDR_LEN];
+	struct in6_addr mcast_addr;
 
 	if (!bond->params.arp_validate || !slave_can_set_ns_maddr(bond, slave))
 		return;
 
-	/* remove the previous maddr from slave */
+	/* remove the previous mac addr from slave */
+	addrconf_addr_solict_mult(slot, &mcast_addr);
 	if (!ipv6_addr_any(slot) &&
-	    !ndisc_mc_map(slot, slot_maddr, slave->dev, 0))
-		dev_mc_del(slave->dev, slot_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_del(slave->dev, mac_addr);
 
-	/* add new maddr on slave if target is set */
+	/* add new mac addr on slave if target is set */
+	addrconf_addr_solict_mult(target, &mcast_addr);
 	if (!ipv6_addr_any(target) &&
-	    !ndisc_mc_map(target, target_maddr, slave->dev, 0))
-		dev_mc_add(slave->dev, target_maddr);
+	    !ndisc_mc_map(&mcast_addr, mac_addr, slave->dev, 0))
+		dev_mc_add(slave->dev, mac_addr);
 }
 
 static void _bond_options_ns_ip6_target_set(struct bonding *bond, int slot,

From 9318dc2357b6b8b2ea1200ab7f2d5877851b7382 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 6 Mar 2025 02:39:23 +0000
Subject: [PATCH 1980/2753] selftests: bonding: fix incorrect mac address

The correct mac address for NS target 2001:db8::254 is 33:33:ff:00:02:54,
not 33:33:00:00:02:54. The same with client maddress.

Fixes: 86fb6173d11e ("selftests: bonding: add ns multicast group testing")
Acked-by: Jay Vosburgh <jv@jvosburgh.net>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306023923.38777-3-liuhangbin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/bonding/bond_options.sh | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
index edc56e2cc6069..7bc148889ca72 100755
--- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh
+++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh
@@ -11,8 +11,8 @@ ALL_TESTS="
 
 lib_dir=$(dirname "$0")
 source ${lib_dir}/bond_topo_3d1c.sh
-c_maddr="33:33:00:00:00:10"
-g_maddr="33:33:00:00:02:54"
+c_maddr="33:33:ff:00:00:10"
+g_maddr="33:33:ff:00:02:54"
 
 skip_prio()
 {

From 415f135ace7fd824cde083184a922e39156055b5 Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Thu, 6 Mar 2025 15:05:10 +0800
Subject: [PATCH 1981/2753] rtase: Fix improper release of ring list entries in
 rtase_sw_reset

Since rtase_init_ring, which is called within rtase_sw_reset, adds ring
entries already present in the ring list back into the list, it causes
the ring list to form a cycle. This results in list_for_each_entry_safe
failing to find an endpoint during traversal, leading to an error.
Therefore, it is necessary to remove the previously added ring_list nodes
before calling rtase_init_ring.

Fixes: 079600489960 ("rtase: Implement net_device_ops")
Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306070510.18129-1-justinlai0215@realtek.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/realtek/rtase/rtase_main.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 3bd11cb56294c..2aacc1996796d 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1501,7 +1501,10 @@ static void rtase_wait_for_quiescence(const struct net_device *dev)
 static void rtase_sw_reset(struct net_device *dev)
 {
 	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_ring *ring, *tmp;
+	struct rtase_int_vector *ivec;
 	int ret;
+	u32 i;
 
 	netif_stop_queue(dev);
 	netif_carrier_off(dev);
@@ -1512,6 +1515,13 @@ static void rtase_sw_reset(struct net_device *dev)
 	rtase_tx_clear(tp);
 	rtase_rx_clear(tp);
 
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		list_for_each_entry_safe(ring, tmp, &ivec->ring_list,
+					 ring_entry)
+			list_del(&ring->ring_entry);
+	}
+
 	ret = rtase_init_ring(dev);
 	if (ret) {
 		netdev_err(dev, "unable to init ring\n");

From 0ea09cbf8350b70ad44d67a1dcb379008a356034 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 6 Mar 2025 10:05:33 -0800
Subject: [PATCH 1982/2753] docs: netdev: add a note on selftest posting

We haven't had much discussion on the list about this, but
a handful of people have been confused about rules on
posting selftests for fixes, lately. I tend to post fixes
with their respective selftests in the same series.
There are tradeoffs around size of the net tree and conflicts
but so far it hasn't been a major issue.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Link: https://patch.msgid.link/20250306180533.1864075-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/process/maintainer-netdev.rst | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst
index e497729525d5b..1ac62dc3a66f6 100644
--- a/Documentation/process/maintainer-netdev.rst
+++ b/Documentation/process/maintainer-netdev.rst
@@ -311,6 +311,14 @@ to the mailing list, e.g.::
 Posting as one thread is discouraged because it confuses patchwork
 (as of patchwork 2.2.2).
 
+Co-posting selftests
+--------------------
+
+Selftests should be part of the same series as the code changes.
+Specifically for fixes both code change and related test should go into
+the same tree (the tests may lack a Fixes tag, which is expected).
+Mixing code changes and test changes in a single commit is discouraged.
+
 Preparing changes
 -----------------
 

From 3a04334d6282d08fbdd6201e374db17d31927ba3 Mon Sep 17 00:00:00 2001
From: Alan Huang <mmpgouride@gmail.com>
Date: Sat, 8 Mar 2025 00:58:27 +0800
Subject: [PATCH 1983/2753] bcachefs: Fix b->written overflow

When bset past end of btree node, we should not add sectors to
b->written, which will overflow b->written.

Reported-by: syzbot+3cb3d9e8c3f197754825@syzkaller.appspotmail.com
Tested-by: syzbot+3cb3d9e8c3f197754825@syzkaller.appspotmail.com
Signed-off-by: Alan Huang <mmpgouride@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_io.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_io.c b/fs/bcachefs/btree_io.c
index dece27d9db04e..756736f9243d7 100644
--- a/fs/bcachefs/btree_io.c
+++ b/fs/bcachefs/btree_io.c
@@ -1186,7 +1186,7 @@ int bch2_btree_node_read_done(struct bch_fs *c, struct bch_dev *ca,
 			     le64_to_cpu(i->journal_seq),
 			     b->written, b->written + sectors, ptr_written);
 
-		b->written += sectors;
+		b->written = min(b->written + sectors, btree_sectors(c));
 
 		if (blacklisted && !first)
 			continue;

From e5c2bcc0cd47321d78bb4e865d7857304139f95d Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Tue, 11 Mar 2025 19:43:58 +0900
Subject: [PATCH 1984/2753] nvme: move error logging from nvme_end_req() to
 __nvme_end_req()

Before the Commit 1f47ed294a2b ("block: cleanup and fix batch completion
adding conditions"), blk_mq_add_to_batch() did not add failed
passthrough requests to batch, and returned false. After the commit,
blk_mq_add_to_batch() always adds passthrough requests to batch
regardless of whether the request failed or not, and returns true. This
affected error logging feature in the NVME driver.

Before the commit, the call chain of failed passthrough request was as
follows:

nvme_handle_cqe()
 blk_mq_add_to_batch() .. false is returned, then call nvme_pci_complete_rq()
 nvme_pci_complete_rq()
  nvme_complete_rq()
   nvme_end_req()
    nvme_log_err_passthru() .. error logging
    __nvme_end_req()        .. end of the rqeuest

After the commit, the call chain is as follows:

nvme_handle_cqe()
 blk_mq_add_to_batch() .. true is returned, then set nvme_pci_complete_batch()
 ..
 nvme_pci_complete_batch()
  nvme_complete_batch()
   nvme_complete_batch_req()
    __nvme_end_req() .. end of the request, without error logging

To make the error logging feature work again for passthrough requests, move the
nvme_log_err_passthru() call from nvme_end_req() to __nvme_end_req().

While at it, move nvme_log_error() call for non-passthrough requests together
with nvme_log_err_passthru(). Even though the trigger commit does not affect
non-passthrough requests, move it together for code simplicity.

Fixes: 1f47ed294a2b ("block: cleanup and fix batch completion adding conditions")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250311104359.1767728-2-shinichiro.kawasaki@wdc.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/nvme/host/core.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index f028913e2e622..8359d0aa0e44b 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -431,6 +431,12 @@ static inline void nvme_end_req_zoned(struct request *req)
 
 static inline void __nvme_end_req(struct request *req)
 {
+	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
+		if (blk_rq_is_passthrough(req))
+			nvme_log_err_passthru(req);
+		else
+			nvme_log_error(req);
+	}
 	nvme_end_req_zoned(req);
 	nvme_trace_bio_complete(req);
 	if (req->cmd_flags & REQ_NVME_MPATH)
@@ -441,12 +447,6 @@ void nvme_end_req(struct request *req)
 {
 	blk_status_t status = nvme_error_status(nvme_req(req)->status);
 
-	if (unlikely(nvme_req(req)->status && !(req->rq_flags & RQF_QUIET))) {
-		if (blk_rq_is_passthrough(req))
-			nvme_log_err_passthru(req);
-		else
-			nvme_log_error(req);
-	}
 	__nvme_end_req(req);
 	blk_mq_end_request(req, status);
 }

From ed92bc5264c4357d4fca292c769ea9967cd3d3b6 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 10 Mar 2025 18:45:36 +0100
Subject: [PATCH 1985/2753] ASoC: codecs: wm0010: Fix error handling path in
 wm0010_spi_probe()

Free some resources in the error handling path of the probe, as already
done in the remove function.

Fixes: e3523e01869d ("ASoC: wm0010: Add initial wm0010 DSP driver")
Fixes: fd8b96574456 ("ASoC: wm0010: Clear IRQ as wake source and include missing header")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/5139ba1ab8c4c157ce04e56096a0f54a1683195c.1741549792.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/wm0010.c | 13 +++++++++++--
 1 file changed, 11 insertions(+), 2 deletions(-)

diff --git a/sound/soc/codecs/wm0010.c b/sound/soc/codecs/wm0010.c
index edd2cb185c42c..9e67fbfc2ccaf 100644
--- a/sound/soc/codecs/wm0010.c
+++ b/sound/soc/codecs/wm0010.c
@@ -920,7 +920,7 @@ static int wm0010_spi_probe(struct spi_device *spi)
 	if (ret) {
 		dev_err(wm0010->dev, "Failed to set IRQ %d as wake source: %d\n",
 			irq, ret);
-		return ret;
+		goto free_irq;
 	}
 
 	if (spi->max_speed_hz)
@@ -932,9 +932,18 @@ static int wm0010_spi_probe(struct spi_device *spi)
 				     &soc_component_dev_wm0010, wm0010_dai,
 				     ARRAY_SIZE(wm0010_dai));
 	if (ret < 0)
-		return ret;
+		goto disable_irq_wake;
 
 	return 0;
+
+disable_irq_wake:
+	irq_set_irq_wake(wm0010->irq, 0);
+
+free_irq:
+	if (wm0010->irq)
+		free_irq(wm0010->irq, wm0010);
+
+	return ret;
 }
 
 static void wm0010_spi_remove(struct spi_device *spi)

From d2b9d97e89c79c95f8b517e4fa43fd100f936acc Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Fri, 7 Mar 2025 17:49:52 +0800
Subject: [PATCH 1986/2753] qlcnic: fix memory leak issues in
 qlcnic_sriov_common.c

Add qlcnic_sriov_free_vlans() in qlcnic_sriov_alloc_vlans() if
any sriov_vlans fails to be allocated.
Add qlcnic_sriov_free_vlans() to free the memory allocated by
qlcnic_sriov_alloc_vlans() if "sriov->allowed_vlans" fails to
be allocated.

Fixes: 91b7282b613d ("qlcnic: Support VLAN id config.")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Link: https://patch.msgid.link/20250307094952.14874-1-haoxiang_li2024@163.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
index f9dd50152b1e3..28d24d59efb84 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c
@@ -454,8 +454,10 @@ static int qlcnic_sriov_set_guest_vlan_mode(struct qlcnic_adapter *adapter,
 
 	num_vlans = sriov->num_allowed_vlans;
 	sriov->allowed_vlans = kcalloc(num_vlans, sizeof(u16), GFP_KERNEL);
-	if (!sriov->allowed_vlans)
+	if (!sriov->allowed_vlans) {
+		qlcnic_sriov_free_vlans(adapter);
 		return -ENOMEM;
+	}
 
 	vlans = (u16 *)&cmd->rsp.arg[3];
 	for (i = 0; i < num_vlans; i++)
@@ -2167,8 +2169,10 @@ int qlcnic_sriov_alloc_vlans(struct qlcnic_adapter *adapter)
 		vf = &sriov->vf_info[i];
 		vf->sriov_vlans = kcalloc(sriov->num_allowed_vlans,
 					  sizeof(*vf->sriov_vlans), GFP_KERNEL);
-		if (!vf->sriov_vlans)
+		if (!vf->sriov_vlans) {
+			qlcnic_sriov_free_vlans(adapter);
 			return -ENOMEM;
+		}
 	}
 
 	return 0;

From 58517f4df8424ec28dfe7290ccc61908eda57aae Mon Sep 17 00:00:00 2001
From: Roxana Nicolescu <nicolescu.roxana@protonmail.com>
Date: Tue, 11 Mar 2025 15:06:10 +0000
Subject: [PATCH 1987/2753] bcachefs: Initialize from_inode members for
 bch_io_opts

When there is no inode source, all "from_inode" members in the structure
bhc_io_opts should be set false.

Fixes: 7a7c43a0c1ecf ("bcachefs: Add bch_io_opts fields for indicating whether the opts came from the inode")
Reported-by: syzbot+c17ad4b4367b72a853cb@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=c17ad4b4367b72a853cb
Signed-off-by: Roxana Nicolescu <nicolescu.roxana@protonmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/inode.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/fs/bcachefs/inode.c b/fs/bcachefs/inode.c
index 04ec05206f8cf..339b80770f1dd 100644
--- a/fs/bcachefs/inode.c
+++ b/fs/bcachefs/inode.c
@@ -1198,6 +1198,7 @@ void bch2_inode_opts_get(struct bch_io_opts *opts, struct bch_fs *c,
 		opts->_name##_from_inode = true;			\
 	} else {							\
 		opts->_name = c->opts._name;				\
+		opts->_name##_from_inode = false;			\
 	}
 	BCH_INODE_OPTS()
 #undef x

From dbac8feb23382af1efa2e1a86049e079b6e42e12 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Tue, 11 Mar 2025 10:39:36 -0400
Subject: [PATCH 1988/2753] bcachefs: Make sure trans is unlocked when
 submitting read IO

We were still using the trans after the unlock, leading to this bug in
the retry path:

00255 ------------[ cut here ]------------
00255 kernel BUG at fs/bcachefs/btree_iter.c:3348!
00255 Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
00255 bcachefs (0ca38fe8-0a26-41f9-9b5d-6a27796c7803): /fiotest offset 86048768: no device to read from:
00255   u64s 8 type extent 4098:168192:U32_MAX len 128 ver 0: durability: 0 crc: c_size 128 size 128 offset 0 nonce 0 csum crc32c 0:8040a368  compress none ec: idx 83 block 1 ptr: 0:302:128 gen 0
00255 bcachefs (0ca38fe8-0a26-41f9-9b5d-6a27796c7803): /fiotest offset 85983232: no device to read from:
00255   u64s 8 type extent 4098:168064:U32_MAX len 128 ver 0: durability: 0 crc: c_size 128 size 128 offset 0 nonce 0 csum crc32c 0:43311336  compress none ec: idx 83 block 1 ptr: 0:302:0 gen 0
00255 Modules linked in:
00255 CPU: 5 UID: 0 PID: 304 Comm: kworker/u70:2 Not tainted 6.14.0-rc6-ktest-g526aae23d67d #16040
00255 Hardware name: linux,dummy-virt (DT)
00255 Workqueue: events_unbound bch2_rbio_retry
00255 pstate: 60001005 (nZCv daif -PAN -UAO -TCO -DIT +SSBS BTYPE=--)
00255 pc : __bch2_trans_get+0x100/0x378
00255 lr : __bch2_trans_get+0xa0/0x378
00255 sp : ffffff80c865b760
00255 x29: ffffff80c865b760 x28: 0000000000000000 x27: ffffff80d76ed880
00255 x26: 0000000000000018 x25: 0000000000000000 x24: ffffff80f4ec3760
00255 x23: ffffff80f4010140 x22: 0000000000000056 x21: ffffff80f4ec0000
00255 x20: ffffff80f4ec3788 x19: ffffff80d75f8000 x18: 00000000ffffffff
00255 x17: 2065707974203820 x16: 7334367520200a3a x15: 0000000000000008
00255 x14: 0000000000000001 x13: 0000000000000100 x12: 0000000000000006
00255 x11: ffffffc080b47a40 x10: 0000000000000000 x9 : ffffffc08038dea8
00255 x8 : ffffff80d75fc018 x7 : 0000000000000000 x6 : 0000000000003788
00255 x5 : 0000000000003760 x4 : ffffff80c922de80 x3 : ffffff80f18f0000
00255 x2 : ffffff80c922de80 x1 : 0000000000000130 x0 : 0000000000000006
00255 Call trace:
00255  __bch2_trans_get+0x100/0x378 (P)
00255  bch2_read_io_err+0x98/0x260
00255  bch2_read_endio+0xb8/0x2d0
00255  __bch2_read_extent+0xce8/0xfe0
00255  __bch2_read+0x2a8/0x978
00255  bch2_rbio_retry+0x188/0x318
00255  process_one_work+0x154/0x390
00255  worker_thread+0x20c/0x3b8
00255  kthread+0xf0/0x1b0
00255  ret_from_fork+0x10/0x20
00255 Code: 6b01001f 54ffff01 79408460 3617fec0 (d4210000)
00255 ---[ end trace 0000000000000000 ]---
00255 Kernel panic - not syncing: Oops - BUG: Fatal exception
00255 SMP: stopping secondary CPUs
00255 Kernel Offset: disabled
00255 CPU features: 0x000,00000070,00000010,8240500b
00255 Memory Limit: none
00255 ---[ end Kernel panic - not syncing: Oops - BUG: Fatal exception ]---

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/io_read.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index 8c7b2d3d779df..726da68073e2b 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -951,12 +951,6 @@ int __bch2_read_extent(struct btree_trans *trans, struct bch_read_bio *orig,
 		goto retry_pick;
 	}
 
-	/*
-	 * Unlock the iterator while the btree node's lock is still in
-	 * cache, before doing the IO:
-	 */
-	bch2_trans_unlock(trans);
-
 	if (flags & BCH_READ_NODECODE) {
 		/*
 		 * can happen if we retry, and the extent we were going to read
@@ -1113,6 +1107,15 @@ int __bch2_read_extent(struct btree_trans *trans, struct bch_read_bio *orig,
 		trace_and_count(c, read_split, &orig->bio);
 	}
 
+	/*
+	 * Unlock the iterator while the btree node's lock is still in
+	 * cache, before doing the IO:
+	 */
+	if (!(flags & BCH_READ_IN_RETRY))
+		bch2_trans_unlock(trans);
+	else
+		bch2_trans_unlock_long(trans);
+
 	if (!rbio->pick.idx) {
 		if (unlikely(!rbio->have_ioref)) {
 			struct printbuf buf = PRINTBUF;
@@ -1160,6 +1163,8 @@ int __bch2_read_extent(struct btree_trans *trans, struct bch_read_bio *orig,
 	if (likely(!(flags & BCH_READ_IN_RETRY))) {
 		return 0;
 	} else {
+		bch2_trans_unlock(trans);
+
 		int ret;
 
 		rbio->context = RBIO_CONTEXT_UNBOUND;

From 5b1122fc4995f308b21d7cfc64ef9880ac834d20 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 10 Mar 2025 22:48:29 +0300
Subject: [PATCH 1989/2753] platform/x86/amd/pmf: fix cleanup in
 amd_pmf_init_smart_pc()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are a few problems in this code:

First, if amd_pmf_tee_init() fails then the function returns directly
instead of cleaning up.  We cannot simply do a "goto error;" because
the amd_pmf_tee_init() cleanup calls tee_shm_free(dev->fw_shm_pool);
and amd_pmf_tee_deinit() calls it as well leading to a double free.
I have re-written this code to use an unwind ladder to free the
allocations.

Second, if amd_pmf_start_policy_engine() fails on every iteration though
the loop then the code calls amd_pmf_tee_deinit() twice which is also a
double free.  Call amd_pmf_tee_deinit() inside the loop for each failed
iteration.  Also on that path the error codes are not necessarily
negative kernel error codes.  Set the error code to -EINVAL.

There is a very subtle third bug which is that if the call to
input_register_device() in amd_pmf_register_input_device() fails then
we call input_unregister_device() on an input device that wasn't
registered.  This will lead to a reference counting underflow
because of the device_del(&dev->dev) in __input_unregister_device().
It's unlikely that anyone would ever hit this bug in real life.

Fixes: 376a8c2a1443 ("platform/x86/amd/pmf: Update PMF Driver for Compatibility with new PMF-TA")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Link: https://lore.kernel.org/r/232231fc-6a71-495e-971b-be2a76f6db4c@stanley.mountain
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/tee-if.c | 36 +++++++++++++++++++--------
 1 file changed, 25 insertions(+), 11 deletions(-)

diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c
index ceaff1ebb7b93..a1e43873a07b0 100644
--- a/drivers/platform/x86/amd/pmf/tee-if.c
+++ b/drivers/platform/x86/amd/pmf/tee-if.c
@@ -510,18 +510,18 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 
 	ret = amd_pmf_set_dram_addr(dev, true);
 	if (ret)
-		goto error;
+		goto err_cancel_work;
 
 	dev->policy_base = devm_ioremap_resource(dev->dev, dev->res);
 	if (IS_ERR(dev->policy_base)) {
 		ret = PTR_ERR(dev->policy_base);
-		goto error;
+		goto err_free_dram_buf;
 	}
 
 	dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL);
 	if (!dev->policy_buf) {
 		ret = -ENOMEM;
-		goto error;
+		goto err_free_dram_buf;
 	}
 
 	memcpy_fromio(dev->policy_buf, dev->policy_base, dev->policy_sz);
@@ -531,13 +531,13 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 	dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL);
 	if (!dev->prev_data) {
 		ret = -ENOMEM;
-		goto error;
+		goto err_free_policy;
 	}
 
 	for (i = 0; i < ARRAY_SIZE(amd_pmf_ta_uuid); i++) {
 		ret = amd_pmf_tee_init(dev, &amd_pmf_ta_uuid[i]);
 		if (ret)
-			return ret;
+			goto err_free_prev_data;
 
 		ret = amd_pmf_start_policy_engine(dev);
 		switch (ret) {
@@ -550,27 +550,41 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev)
 			status = false;
 			break;
 		default:
-			goto error;
+			ret = -EINVAL;
+			amd_pmf_tee_deinit(dev);
+			goto err_free_prev_data;
 		}
 
 		if (status)
 			break;
 	}
 
-	if (!status && !pb_side_load)
-		goto error;
+	if (!status && !pb_side_load) {
+		ret = -EINVAL;
+		goto err_free_prev_data;
+	}
 
 	if (pb_side_load)
 		amd_pmf_open_pb(dev, dev->dbgfs_dir);
 
 	ret = amd_pmf_register_input_device(dev);
 	if (ret)
-		goto error;
+		goto err_pmf_remove_pb;
 
 	return 0;
 
-error:
-	amd_pmf_deinit_smart_pc(dev);
+err_pmf_remove_pb:
+	if (pb_side_load && dev->esbin)
+		amd_pmf_remove_pb(dev);
+	amd_pmf_tee_deinit(dev);
+err_free_prev_data:
+	kfree(dev->prev_data);
+err_free_policy:
+	kfree(dev->policy_buf);
+err_free_dram_buf:
+	kfree(dev->buf);
+err_cancel_work:
+	cancel_delayed_work_sync(&dev->pb_work);
 
 	return ret;
 }

From a05507cef0ee6a0af402c0d7e994115033ff746b Mon Sep 17 00:00:00 2001
From: Lukas Hetzenecker <lukas@hetzenecker.me>
Date: Tue, 11 Mar 2025 00:28:03 +0100
Subject: [PATCH 1990/2753] platform/surface: aggregator_registry: Add Support
 for Surface Pro 11
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add SAM client device nodes for the Surface Pro 11 (Intel).
Like with the Surface Pro 10 already, the node group
is compatible, so it can be reused.

Signed-off-by: Lukas Hetzenecker <lukas@hetzenecker.me>
Link: https://lore.kernel.org/r/20250310232803.23691-1-lukas@hetzenecker.me
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/surface/surface_aggregator_registry.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c
index d4f32ad665305..a594d5fcfcfd1 100644
--- a/drivers/platform/surface/surface_aggregator_registry.c
+++ b/drivers/platform/surface/surface_aggregator_registry.c
@@ -371,7 +371,7 @@ static const struct software_node *ssam_node_group_sp8[] = {
 	NULL,
 };
 
-/* Devices for Surface Pro 9 (Intel/x86) and 10 */
+/* Devices for Surface Pro 9, 10 and 11 (Intel/x86) */
 static const struct software_node *ssam_node_group_sp9[] = {
 	&ssam_node_root,
 	&ssam_node_hub_kip,
@@ -430,6 +430,9 @@ static const struct acpi_device_id ssam_platform_hub_acpi_match[] = {
 	/* Surface Pro 10 */
 	{ "MSHW0510", (unsigned long)ssam_node_group_sp9 },
 
+	/* Surface Pro 11 */
+	{ "MSHW0583", (unsigned long)ssam_node_group_sp9 },
+
 	/* Surface Book 2 */
 	{ "MSHW0107", (unsigned long)ssam_node_group_gen5 },
 

From 3ad61970ac9e164be1b09b46c01aa942e8966132 Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Sat, 8 Mar 2025 23:19:25 +0200
Subject: [PATCH 1991/2753] wifi: iwlwifi: mvm: fix setting the TK when
 associated

When running secured ranging and the initiator is associated with
the responder, the TK was not set in the range request command.
Fix it.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250308231427.603dc31579d9.Icd19d797e56483c08dd22c55b96fee481c4d2f3d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
index dfb25b964f0eb..a493ef6bedc3e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/ftm-initiator.c
@@ -672,7 +672,11 @@ iwl_mvm_ftm_set_secured_ranging(struct iwl_mvm *mvm, struct ieee80211_vif *vif,
 
 			target.bssid = bssid;
 			target.cipher = cipher;
+			target.tk = NULL;
 			ieee80211_iter_keys(mvm->hw, vif, iter, &target);
+
+			if (!WARN_ON(!target.tk))
+				memcpy(tk, target.tk, TK_11AZ_LEN);
 		} else {
 			memcpy(tk, entry->tk, sizeof(entry->tk));
 		}

From 834bfc698bf7cee3bf61c0209b410c7f97a54108 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:39 +0200
Subject: [PATCH 1992/2753] wifi: iwlwifi: mld: fix build with CONFIG_PM_SLEEP
 undefined

fw_status.in_d3 is only defined under CONFIG_PM_SLEEP.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.6f7e44a27b87.I78b9311019b59477a1961cddc4640b255ceda651@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/hcmd.h | 4 +++-
 drivers/net/wireless/intel/iwlwifi/mld/mld.h  | 2 ++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h b/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
index 773bc1b093921..64a8d42483241 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/hcmd.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #ifndef __iwl_mld_hcmd_h__
 #define __iwl_mld_hcmd_h__
@@ -10,8 +10,10 @@ static inline int iwl_mld_send_cmd(struct iwl_mld *mld, struct iwl_host_cmd *cmd
 	/* No commands, including the d3 related commands, should be sent
 	 * after entering d3
 	 */
+#ifdef CONFIG_PM_SLEEP
 	if (WARN_ON(mld->fw_status.in_d3))
 		return -EIO;
+#endif
 
 	if (!(cmd->flags & CMD_ASYNC))
 		lockdep_assert_wiphy(mld->wiphy);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 6eda6081c8b41..1ab98ba42c760 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -296,7 +296,9 @@ iwl_cleanup_mld(struct iwl_mld *mld)
 	CLEANUP_STRUCT(mld);
 	CLEANUP_STRUCT(&mld->scan);
 
+#ifdef CONFIG_PM_SLEEP
 	mld->fw_status.in_d3 = false;
+#endif
 
 	iwl_mld_low_latency_restart_cleanup(mld);
 

From cb9716eae2dfac2f70fea19df928e61bed314ce9 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:40 +0200
Subject: [PATCH 1993/2753] wifi: iwlwifi: mld: fix SMPS W/A

If the user disables power save of a vif that didn't have it enabled
(for example before association), mac80211 will not notify the driver
with BSS_CHANGED_PS. This will cause the driver to not update the
device-level power save to disabled.
Fix this by checking the vif's power save status upon authorization, and
stop considering the vif's power save status on disassociation.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.1cdeb78b19ba.I58fe02c062524029071b04b093a1b09c5e46f4ef@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/iface.h    |  2 ++
 .../net/wireless/intel/iwlwifi/mld/mac80211.c | 25 +++++++++++++++----
 .../net/wireless/intel/iwlwifi/mld/power.c    |  3 ++-
 3 files changed, 24 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
index 2c928113f6802..57910660ed186 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -134,6 +134,7 @@ struct iwl_mld_emlsr {
  * @beacon_inject_active: indicates an active debugfs beacon ie injection
  * @low_latency_causes: bit flags, indicating the causes for low-latency,
  *	see @iwl_mld_low_latency_cause.
+ * @ps_disabled: indicates that PS is disabled for this interface
  * @mld: pointer to the mld structure.
  * @deflink: default link data, for use in non-MLO,
  * @link: reference to link data for each valid link, for use in MLO.
@@ -159,6 +160,7 @@ struct iwl_mld_vif {
 		bool beacon_inject_active;
 #endif
 		u8 low_latency_causes;
+		bool ps_disabled;
 	);
 	/* And here fields that survive a fw restart */
 	struct iwl_mld *mld;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index d73bd0179f7dc..ba149581e25d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -1262,6 +1262,23 @@ iwl_mld_mac80211_link_info_changed(struct ieee80211_hw *hw,
 		iwl_mld_set_tx_power(mld, link_conf, link_conf->txpower);
 }
 
+static void
+iwl_mld_smps_wa(struct iwl_mld *mld, struct ieee80211_vif *vif, bool enable)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+
+	/* Send the device-level power commands since the
+	 * firmware checks the POWER_TABLE_CMD's POWER_SAVE_EN bit to
+	 * determine SMPS mode.
+	 */
+	if (mld_vif->ps_disabled == !enable)
+		return;
+
+	mld_vif->ps_disabled = !enable;
+
+	iwl_mld_update_device_power(mld, false);
+}
+
 static
 void iwl_mld_mac80211_vif_cfg_changed(struct ieee80211_hw *hw,
 				      struct ieee80211_vif *vif,
@@ -1295,11 +1312,7 @@ void iwl_mld_mac80211_vif_cfg_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changes & BSS_CHANGED_PS) {
-		/* Send both device-level and MAC-level power commands since the
-		 * firmware checks the POWER_TABLE_CMD's POWER_SAVE_EN bit to
-		 * determine SMPS mode.
-		 */
-		iwl_mld_update_device_power(mld, false);
+		iwl_mld_smps_wa(mld, vif, vif->cfg.ps);
 		iwl_mld_update_mac_power(mld, vif, false);
 	}
 
@@ -1716,6 +1729,7 @@ static int iwl_mld_move_sta_state_up(struct iwl_mld *mld,
 						    FW_CTXT_ACTION_MODIFY);
 			if (ret)
 				return ret;
+			iwl_mld_smps_wa(mld, vif, vif->cfg.ps);
 		}
 
 		/* MFP is set by default before the station is authorized.
@@ -1758,6 +1772,7 @@ static int iwl_mld_move_sta_state_down(struct iwl_mld *mld,
 						  &mld_vif->emlsr.check_tpt_wk);
 
 			iwl_mld_reset_cca_40mhz_workaround(mld, vif);
+			iwl_mld_smps_wa(mld, vif, true);
 		}
 
 		/* once we move into assoc state, need to update the FW to
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/power.c b/drivers/net/wireless/intel/iwlwifi/mld/power.c
index ed7c0319f239b..2f16c174b57e5 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/power.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/power.c
@@ -15,11 +15,12 @@ static void iwl_mld_vif_ps_iterator(void *data, u8 *mac,
 				    struct ieee80211_vif *vif)
 {
 	bool *ps_enable = (bool *)data;
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
 
 	if (vif->type != NL80211_IFTYPE_STATION)
 		return;
 
-	*ps_enable &= vif->cfg.ps;
+	*ps_enable &= !mld_vif->ps_disabled;
 }
 
 int iwl_mld_update_device_power(struct iwl_mld *mld, bool d3)

From e8670620b07725d38f7c8a6f751a1173deeafb8a Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:41 +0200
Subject: [PATCH 1994/2753] wifi: iwlwifi: mld: track channel_load_not_by_us

For each channel context, track the avarage channel load by others in the
driver specific phy data, to be used by EMLSR.
Due to FW limitations, this value is incorrect in EMLSR, so it is
shouldn't be used in EMLSR.
On EMLSR exit, clear it so the wrong value won't be used.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.dd443fc5b178.I68b2fed197aae14888159b7a73bf40c2f346f41f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/mac80211.c |  1 +
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  | 21 +++++++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/phy.h  |  5 +++++
 .../net/wireless/intel/iwlwifi/mld/stats.c    | 10 ++++++++-
 .../wireless/intel/iwlwifi/mld/tests/utils.c  |  1 +
 5 files changed, 37 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index ba149581e25d4..b01a41f9b0133 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -847,6 +847,7 @@ int iwl_mld_add_chanctx(struct ieee80211_hw *hw,
 	if (fw_id < 0)
 		return fw_id;
 
+	phy->mld = mld;
 	phy->fw_id = fw_id;
 	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 99c8501129b8f..b68092be9aed7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -3,6 +3,7 @@
  * Copyright (C) 2024-2025 Intel Corporation
  */
 #include "mlo.h"
+#include "phy.h"
 
 /* Block reasons helper */
 #define HANDLE_EMLSR_BLOCKED_REASONS(HOW)	\
@@ -177,6 +178,19 @@ static void iwl_mld_check_emlsr_prevention(struct iwl_mld *mld,
 				 &mld_vif->emlsr.prevent_done_wk, delay);
 }
 
+static void iwl_mld_clear_avg_chan_load_iter(struct ieee80211_hw *hw,
+					     struct ieee80211_chanctx_conf *ctx,
+					     void *dat)
+{
+	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
+
+	/* It is ok to do it for all chanctx (and not only for the ones that
+	 * belong to the EMLSR vif) since EMLSR is not allowed if there is
+	 * another vif.
+	 */
+	phy->avg_channel_load_not_by_us = 0;
+}
+
 static int _iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
 			       enum iwl_mld_emlsr_exit exit, u8 link_to_keep,
 			       bool sync)
@@ -215,6 +229,13 @@ static int _iwl_mld_exit_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
 	/* Update latest exit reason and check EMLSR prevention */
 	iwl_mld_check_emlsr_prevention(mld, mld_vif, exit);
 
+	/* channel_load_not_by_us is invalid when in EMLSR.
+	 * Clear it so wrong values won't be used.
+	 */
+	ieee80211_iter_chan_contexts_atomic(mld->hw,
+					    iwl_mld_clear_avg_chan_load_iter,
+					    NULL);
+
 	return ret;
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.h b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
index 3dfb8ca994e2e..357bc9fe96249 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
@@ -15,6 +15,9 @@
  *	with. Used to detect a no-op when the chanctx changes.
  * @channel_load_by_us: channel load on this channel caused by
  *	the NIC itself, as indicated by firmware
+ * @avg_channel_load_not_by_us: averaged channel load on this channel caused by
+ *	others. This value is invalid when in EMLSR (due to FW limitations)
+ * @mld: pointer to the MLD context
  */
 struct iwl_mld_phy {
 	/* Add here fields that need clean up on hw restart */
@@ -24,6 +27,8 @@ struct iwl_mld_phy {
 	);
 	/* And here fields that survive a hw restart */
 	u32 channel_load_by_us;
+	u32 avg_channel_load_not_by_us;
+	struct iwl_mld *mld;
 };
 
 static inline struct iwl_mld_phy *
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
index 842b9b9fdd8c7..5633885c49ff2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/stats.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -461,6 +461,7 @@ static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
 {
 	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
 	const struct iwl_stats_ntfy_per_phy *per_phy = data;
+	u32 new_load;
 
 	if (WARN_ON(phy->fw_id >= IWL_STATS_MAX_PHY_OPERATIONAL))
 		return;
@@ -468,7 +469,14 @@ static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
 	phy->channel_load_by_us =
 		le32_to_cpu(per_phy[phy->fw_id].channel_load_by_us);
 
-	/* TODO: channel load not by us (task=statistics) */
+	new_load = le32_to_cpu(per_phy[phy->fw_id].channel_load_not_by_us);
+	if (IWL_FW_CHECK(phy->mld, new_load > 100, "Invalid channel load %u\n",
+			 new_load))
+		return;
+
+	/* give a weight of 0.5 for the old value */
+	phy->avg_channel_load_not_by_us =
+		(new_load >> 1) + (phy->avg_channel_load_not_by_us >> 1);
 }
 
 static void
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
index a8c1e6c721388..b6049918b5dba 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -168,6 +168,7 @@ iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def)
 	KUNIT_ASSERT_GE(test, fw_id, 0);
 
 	phy->fw_id = fw_id;
+	phy->mld = mld;
 	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
 
 	return ctx;

From 380038bb839de262f5ad84b41b16f3f69afd5a91 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:42 +0200
Subject: [PATCH 1995/2753] wifi: iwlwifi: mld: refactor
 iwl_mld_valid_emlsr_pair

- Change reasons enum to a bitmask and rename it
- Don't use 'else if' so all reasons will be set in the reasons bitmask

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.0a3b2f88fbbf.I0152bc39e828488451e85135feb044ce1f7a85d3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index b68092be9aed7..bbaf9ad0e9eb0 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -748,23 +748,23 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
 	struct iwl_mld *mld = mld_vif->mld;
-	enum iwl_mld_emlsr_exit ret = 0;
+	u32 reason_mask = 0;
 
 	/* Per-link considerations */
 	if (iwl_mld_emlsr_disallowed_with_link(mld, vif, a, true) ||
 	    iwl_mld_emlsr_disallowed_with_link(mld, vif, b, false))
 		return false;
 
-	if (a->chandef->chan->band == b->chandef->chan->band) {
-		ret |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
-	} else if (a->chandef->width != b->chandef->width) {
+	if (a->chandef->chan->band == b->chandef->chan->band)
+		reason_mask |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
+	if (a->chandef->width != b->chandef->width) {
 		/* TODO: task=EMLSR task=statistics
 		 * replace BANDWIDTH exit reason with channel load criteria
 		 */
-		ret |= IWL_MLD_EMLSR_EXIT_BANDWIDTH;
+		reason_mask |= IWL_MLD_EMLSR_EXIT_BANDWIDTH;
 	}
 
-	if (ret) {
+	if (reason_mask) {
 		IWL_DEBUG_INFO(mld,
 			       "Links %d and %d are not a valid pair for EMLSR\n",
 			       a->link_id, b->link_id);
@@ -772,7 +772,7 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 			       "Links bandwidth are: %d and %d\n",
 			       nl80211_chan_width_to_mhz(a->chandef->width),
 			       nl80211_chan_width_to_mhz(b->chandef->width));
-		iwl_mld_print_emlsr_exit(mld, ret);
+		iwl_mld_print_emlsr_exit(mld, reason_mask);
 		return false;
 	}
 

From 8d006c92132ed8bafc95feb314bcd3c5dd2e6bce Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Sun, 9 Mar 2025 07:36:43 +0200
Subject: [PATCH 1996/2753] wifi: iwlwifi: mld: assume wiphy is locked when
 getting BSS ifaces

The code was calling ieee80211_iterate_interfaces, however that
takes a lock of iflist_mtx, which must not be taken recursively. Fix
this by using the appropriate _mtx version that asserts that the wiphy
mutex is already held.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.6ce298d6a44f.Ibc862dfdd6cb2da63781c791b9dc601bd5ce4bdc@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/iface.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.c b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
index 691062b444619..e49e2260ac05e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.c
@@ -465,10 +465,10 @@ u8 iwl_mld_get_fw_bss_vifs_ids(struct iwl_mld *mld)
 {
 	u8 fw_id_bitmap = 0;
 
-	ieee80211_iterate_interfaces(mld->hw,
-				     IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER,
-				     iwl_mld_get_fw_id_bss_bitmap_iter,
-				     &fw_id_bitmap);
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_SKIP_SDATA_NOT_IN_DRIVER,
+						iwl_mld_get_fw_id_bss_bitmap_iter,
+						&fw_id_bitmap);
 
 	return fw_id_bitmap;
 }

From 6895d74c11d80c8c44cd14eade856c26a30902ad Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Mar 2025 07:36:44 +0200
Subject: [PATCH 1997/2753] wifi: iwlwifi: mld: initialize regulatory early

Since iwlmld claims wiphys to be self-managed, it needs to
have a regdomain registered before the wiphy is registered
to avoid issues when trying to get the regdomain, e.g. via
"iw phy phy0 reg get".

Move the initialization early, on every FW start not just
when starting to really operate it. This also requires the
self-managed flag to be set early.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.10ab8fed94e9.I7c8dee3d14c7427a56882739f82546c6492f3b10@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/fw.c     |  8 ++++----
 .../net/wireless/intel/iwlwifi/mld/mac80211.c   |  9 ---------
 drivers/net/wireless/intel/iwlwifi/mld/mld.c    | 17 +++++++++++++++--
 3 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index ec93af362cfc8..9c1dce0d59797 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -339,6 +339,10 @@ int iwl_mld_load_fw(struct iwl_mld *mld)
 	if (ret)
 		return ret;
 
+	ret = iwl_mld_init_mcc(mld);
+	if (ret)
+		return ret;
+
 	mld->fw_status.running = true;
 
 	return 0;
@@ -481,10 +485,6 @@ static int iwl_mld_config_fw(struct iwl_mld *mld)
 	if (ret)
 		return ret;
 
-	ret = iwl_mld_init_mcc(mld);
-	if (ret)
-		return ret;
-
 	if (mld->fw_status.in_hw_restart) {
 		iwl_mld_send_recovery_cmd(mld, ERROR_RECOVERY_UPDATE_DB);
 		iwl_mld_time_sync_fw_config(mld);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index b01a41f9b0133..27ef41d694796 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -164,14 +164,6 @@ static void iwl_mld_hw_set_security(struct iwl_mld *mld)
 			      NL80211_EXT_FEATURE_BEACON_PROTECTION);
 }
 
-static void iwl_mld_hw_set_regulatory(struct iwl_mld *mld)
-{
-	struct wiphy *wiphy = mld->wiphy;
-
-	wiphy->regulatory_flags |= REGULATORY_WIPHY_SELF_MANAGED;
-	wiphy->regulatory_flags |= REGULATORY_ENABLE_RELAX_NO_IR;
-}
-
 static void iwl_mld_hw_set_antennas(struct iwl_mld *mld)
 {
 	struct wiphy *wiphy = mld->wiphy;
@@ -415,7 +407,6 @@ int iwl_mld_register_hw(struct iwl_mld *mld)
 	iwl_mld_hw_set_addresses(mld);
 	iwl_mld_hw_set_channels(mld);
 	iwl_mld_hw_set_security(mld);
-	iwl_mld_hw_set_regulatory(mld);
 	iwl_mld_hw_set_pm(mld);
 	iwl_mld_hw_set_antennas(mld);
 	iwl_mac_hw_set_radiotap(mld);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.c b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
index adc3d23aa019f..d4a99ae64074f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.c
@@ -2,7 +2,7 @@
 /*
  * Copyright (C) 2024-2025 Intel Corporation
  */
-
+#include <linux/rtnetlink.h>
 #include <net/mac80211.h>
 
 #include "fw/api/rx.h"
@@ -50,6 +50,14 @@ static void __exit iwl_mld_exit(void)
 }
 module_exit(iwl_mld_exit);
 
+static void iwl_mld_hw_set_regulatory(struct iwl_mld *mld)
+{
+	struct wiphy *wiphy = mld->wiphy;
+
+	wiphy->regulatory_flags |= REGULATORY_WIPHY_SELF_MANAGED;
+	wiphy->regulatory_flags |= REGULATORY_ENABLE_RELAX_NO_IR;
+}
+
 VISIBLE_IF_IWLWIFI_KUNIT
 void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
 		       const struct iwl_cfg *cfg, const struct iwl_fw *fw,
@@ -67,7 +75,6 @@ void iwl_construct_mld(struct iwl_mld *mld, struct iwl_trans *trans,
 
 	/* Setup async RX handling */
 	spin_lock_init(&mld->async_handlers_lock);
-	INIT_LIST_HEAD(&mld->async_handlers_list);
 	wiphy_work_init(&mld->async_handlers_wk,
 			iwl_mld_async_handlers_wk);
 
@@ -387,9 +394,13 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	iwl_bios_setup_step(trans, &mld->fwrt);
 	mld->bios_enable_puncturing = iwl_uefi_get_puncturing(&mld->fwrt);
 
+	iwl_mld_hw_set_regulatory(mld);
+
 	/* Configure transport layer with the opmode specific params */
 	iwl_mld_configure_trans(op_mode);
 
+	/* needed for regulatory init */
+	rtnl_lock();
 	/* Needed for sending commands */
 	wiphy_lock(mld->wiphy);
 
@@ -401,6 +412,7 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 
 	if (ret) {
 		wiphy_unlock(mld->wiphy);
+		rtnl_unlock();
 		iwl_fw_flush_dumps(&mld->fwrt);
 		goto free_hw;
 	}
@@ -408,6 +420,7 @@ iwl_op_mode_mld_start(struct iwl_trans *trans, const struct iwl_cfg *cfg,
 	iwl_mld_stop_fw(mld);
 
 	wiphy_unlock(mld->wiphy);
+	rtnl_unlock();
 
 	ret = iwl_mld_leds_init(mld);
 	if (ret)

From 29b0ca82c1ee731691085ce8e8aac9e5bcd5d2b1 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:45 +0200
Subject: [PATCH 1998/2753] wifi: iwlwifi: mld: use the right iface iterator in
 low_latency

We used ieee80211_iterate_active_interfaces instead of
ieee80211_iterate_active_interfaces_mtx, which is the one to use when
the wiphy lock is held.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Daniel Gabay <daniel.gabay@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Link: https://patch.msgid.link/20250309073442.925cdca61ed0.I34f5c52d27414cb4c301bbd24df7c3530a43fa1d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/low_latency.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
index 439fc10a4a412..e74e66735f521 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
@@ -120,9 +120,9 @@ static void iwl_mld_low_latency_wk(struct wiphy *wiphy, struct wiphy_work *wk)
 		wiphy_delayed_work_queue(mld->wiphy, &mld->low_latency.work,
 					 MLD_LL_ACTIVE_WK_PERIOD);
 
-	ieee80211_iterate_active_interfaces(mld->hw,
-					    IEEE80211_IFACE_ITER_NORMAL,
-					    iwl_mld_low_latency_iter, mld);
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_low_latency_iter, mld);
 }
 
 int iwl_mld_low_latency_init(struct iwl_mld *mld)

From b807dec3e82ae623e0ec45a26e485548d91bbe9c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Mar 2025 07:36:46 +0200
Subject: [PATCH 1999/2753] wifi: iwlwifi: mld: fix OMI time protection logic

We're allowed to enter OMI only 5 seconds after the last
exit, so the logic needs to be inverted. Fix that.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.58efb4c91655.Id596fcda2fb28f5945548d780be9ff90aee76b7e@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/link.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
index 64ebafc35c9bf..f6d482817f1b7 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -760,8 +760,8 @@ void iwl_mld_check_omi_bw_reduction(struct iwl_mld *mld)
 		return;
 	}
 
-	if (time_is_before_jiffies(mld_link->rx_omi.exit_ts +
-				   msecs_to_jiffies(IWL_MLD_OMI_EXIT_PROTECTION)))
+	if (time_is_after_jiffies(mld_link->rx_omi.exit_ts +
+				  msecs_to_jiffies(IWL_MLD_OMI_EXIT_PROTECTION)))
 		return;
 
 	/* reduce bandwidth to 80 MHz to save power */

From fd04fbee7f0f8ec986772d41a1e1717f5bcf941c Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Mar 2025 07:36:47 +0200
Subject: [PATCH 2000/2753] wifi: iwlwifi: mld: enable OMI bandwidth reduction
 on 6 GHz

Due to the iwl_mld_get_chandef_from_chanctx() logic, even after
the OMI handshake to reduce bandwidth the driver wouldn't apply
that to the PHY context, since it always uses the normal, not
the reduced, configuration on 6 GHz (not strictly always, but
OMI will only apply if the original bandwidth is > 80 MHz.) Fix
this by making that selection contingent on AP mode. Refactor
the code a bit to also make it clearer why the min_def isn't
used in that case (for FILS.)

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.2706cbd0b100.Ic34636b1aee81a140eb690fca8139909a58f8e8b@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/link.c |  2 +-
 .../net/wireless/intel/iwlwifi/mld/mac80211.c |  4 +-
 drivers/net/wireless/intel/iwlwifi/mld/phy.c  | 49 +++++++++++++++++--
 drivers/net/wireless/intel/iwlwifi/mld/phy.h  |  3 +-
 .../wireless/intel/iwlwifi/mld/tests/utils.c  |  2 +-
 5 files changed, 50 insertions(+), 10 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
index f6d482817f1b7..1db69aee4e9fa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -67,7 +67,7 @@ static void iwl_mld_fill_rates(struct iwl_mld *mld,
 			       __le32 *cck_rates, __le32 *ofdm_rates)
 {
 	struct cfg80211_chan_def *chandef =
-		iwl_mld_get_chandef_from_chanctx(chan_ctx);
+		iwl_mld_get_chandef_from_chanctx(mld, chan_ctx);
 	struct ieee80211_supported_band *sband =
 		mld->hw->wiphy->bands[chandef->chan->band];
 	unsigned long basic = link->basic_rates;
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 27ef41d694796..91e201fde72aa 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -840,7 +840,7 @@ int iwl_mld_add_chanctx(struct ieee80211_hw *hw,
 
 	phy->mld = mld;
 	phy->fw_id = fw_id;
-	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
+	phy->chandef = *iwl_mld_get_chandef_from_chanctx(mld, ctx);
 
 	ret = iwl_mld_phy_fw_action(mld, ctx, FW_CTXT_ACTION_ADD);
 	if (ret) {
@@ -872,7 +872,7 @@ void iwl_mld_change_chanctx(struct ieee80211_hw *hw,
 	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);
 	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
 	struct cfg80211_chan_def *chandef =
-		iwl_mld_get_chandef_from_chanctx(ctx);
+		iwl_mld_get_chandef_from_chanctx(mld, ctx);
 
 	/* We don't care about these */
 	if (!(changed & ~(IEEE80211_CHANCTX_CHANGE_RX_CHAINS |
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.c b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
index c38f101628de3..2fbc8090088be 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/phy.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.c
@@ -22,16 +22,55 @@ int iwl_mld_allocate_fw_phy_id(struct iwl_mld *mld)
 }
 EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_allocate_fw_phy_id);
 
-struct cfg80211_chan_def *
-iwl_mld_get_chandef_from_chanctx(struct ieee80211_chanctx_conf *ctx)
+struct iwl_mld_chanctx_usage_data {
+	struct iwl_mld *mld;
+	struct ieee80211_chanctx_conf *ctx;
+	bool use_def;
+};
+
+static bool iwl_mld_chanctx_fils_enabled(struct ieee80211_vif *vif,
+					 struct ieee80211_chanctx_conf *ctx)
 {
-	bool use_def = cfg80211_channel_is_psc(ctx->def.chan) ||
+	if (vif->type != NL80211_IFTYPE_AP)
+		return false;
+
+	return cfg80211_channel_is_psc(ctx->def.chan) ||
 		(ctx->def.chan->band == NL80211_BAND_6GHZ &&
 		 ctx->def.width >= NL80211_CHAN_WIDTH_80);
+}
+
+static void iwl_mld_chanctx_usage_iter(void *_data, u8 *mac,
+				       struct ieee80211_vif *vif)
+{
+	struct iwl_mld_chanctx_usage_data *data = _data;
+	struct ieee80211_bss_conf *link_conf;
+	int link_id;
+
+	for_each_vif_active_link(vif, link_conf, link_id) {
+		if (rcu_access_pointer(link_conf->chanctx_conf) != data->ctx)
+			continue;
+
+		if (iwl_mld_chanctx_fils_enabled(vif, data->ctx))
+			data->use_def = true;
+	}
+}
+
+struct cfg80211_chan_def *
+iwl_mld_get_chandef_from_chanctx(struct iwl_mld *mld,
+				 struct ieee80211_chanctx_conf *ctx)
+{
+	struct iwl_mld_chanctx_usage_data data = {
+		.mld = mld,
+		.ctx = ctx,
+	};
+
+	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+						IEEE80211_IFACE_ITER_NORMAL,
+						iwl_mld_chanctx_usage_iter,
+						&data);
 
-	return use_def ? &ctx->def : &ctx->min_def;
+	return data.use_def ? &ctx->def : &ctx->min_def;
 }
-EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_get_chandef_from_chanctx);
 
 static u8
 iwl_mld_nl80211_width_to_fw(enum nl80211_chan_width width)
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/phy.h b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
index 357bc9fe96249..2212a89321b7e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/phy.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/phy.h
@@ -48,7 +48,8 @@ int iwl_mld_allocate_fw_phy_id(struct iwl_mld *mld);
 int iwl_mld_phy_fw_action(struct iwl_mld *mld,
 			  struct ieee80211_chanctx_conf *ctx, u32 action);
 struct cfg80211_chan_def *
-iwl_mld_get_chandef_from_chanctx(struct ieee80211_chanctx_conf *ctx);
+iwl_mld_get_chandef_from_chanctx(struct iwl_mld *mld,
+				 struct ieee80211_chanctx_conf *ctx);
 u8 iwl_mld_get_fw_ctrl_pos(const struct cfg80211_chan_def *chandef);
 
 #endif /* __iwl_mld_phy_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
index b6049918b5dba..6331cd91cdf6e 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -169,7 +169,7 @@ iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def)
 
 	phy->fw_id = fw_id;
 	phy->mld = mld;
-	phy->chandef = *iwl_mld_get_chandef_from_chanctx(ctx);
+	phy->chandef = *def;
 
 	return ctx;
 }

From 32c33a4dd2a9f80ded554551a172fcb351970b1c Mon Sep 17 00:00:00 2001
From: Avraham Stern <avraham.stern@intel.com>
Date: Sun, 9 Mar 2025 07:36:48 +0200
Subject: [PATCH 2001/2753] wifi: iwlwifi: mld: move the ftm initiator data to
 ftm-initiator.h

Move the FTM initiator data to the relevant header file and document
its fields.

Signed-off-by: Avraham Stern <avraham.stern@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.92830fd553ec.Icbbd0eba34c9ba318801074f7705f6d1e5af5482@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/ftm-initiator.h | 14 ++++++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/mld.h       |  7 ++-----
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
index e98fac34beba4..3fab25a52508a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/ftm-initiator.h
@@ -5,6 +5,20 @@
 #ifndef __iwl_mld_ftm_initiator_h__
 #define __iwl_mld_ftm_initiator_h__
 
+/**
+ * struct ftm_initiator_data - FTM initiator data
+ *
+ * @req: a pointer to cfg80211 FTM request
+ * @req_wdev: a pointer to the wdev that requested the current FTM request
+ * @responses: the number of responses received for the current FTM session.
+ *	Used for tracking the burst index in a periodic request.
+ */
+struct ftm_initiator_data {
+		struct cfg80211_pmsr_request *req;
+		struct wireless_dev *req_wdev;
+		int responses[IWL_TOF_MAX_APS];
+};
+
 int iwl_mld_ftm_start(struct iwl_mld *mld, struct ieee80211_vif *vif,
 		      struct cfg80211_pmsr_request *req);
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 1ab98ba42c760..38f1d1bc5a244 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -34,6 +34,7 @@
 #include "constants.h"
 #include "ptp.h"
 #include "time_sync.h"
+#include "ftm-initiator.h"
 
 /**
  * DOC: Introduction
@@ -277,11 +278,7 @@ struct iwl_mld {
 
 	struct iwl_mld_time_sync_data __rcu *time_sync;
 
-	struct {
-		struct cfg80211_pmsr_request *req;
-		struct wireless_dev *req_wdev;
-		int responses[IWL_TOF_MAX_APS];
-	} ftm_initiator;
+	struct ftm_initiator_data ftm_initiator;
 };
 
 /* memset the part of the struct that requires cleanup on restart */

From 67128af05c6419e1f56ea7f10a29fec8b8ec4add Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sun, 9 Mar 2025 07:36:49 +0200
Subject: [PATCH 2002/2753] wifi: iwlwifi: mld: remove AP keys only for AP STA

On station interfaces we don't only have the AP STA, but also
TDLS stations. Don't try to remove AP keys for them.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Tested-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.f06a4d6eed2b.Icd20af668a22bfae5328eb0ea00ce10a72ce3539@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/sta.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.c b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
index f266a81dd29b9..994d4561518bd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
@@ -793,7 +793,7 @@ void iwl_mld_remove_sta(struct iwl_mld *mld, struct ieee80211_sta *sta)
 		 * removed, but FW expects all the keys to be removed before
 		 * the STA is, so remove them all here.
 		 */
-		if (vif->type == NL80211_IFTYPE_STATION)
+		if (vif->type == NL80211_IFTYPE_STATION && !sta->tdls)
 			iwl_mld_remove_ap_keys(mld, vif, sta, link_id);
 
 		/* Remove the link_sta */

From 36b79cb091ad89f939d50a4f3af06534ae0fbdaa Mon Sep 17 00:00:00 2001
From: Ilan Peer <ilan.peer@intel.com>
Date: Sun, 9 Mar 2025 07:36:50 +0200
Subject: [PATCH 2003/2753] wifi: iwlwifi: mld: Correctly configure the A-MSDU
 max lengths

Refactor the setting of the A-MSDU maximal lengths as follows:

- Move the setting of the maximal A-MSDU length in case of HT from TLC
  logic to the station logic as it is not related to TLC.
- As long as the station is not associated, set RC A-MSDU maximal
  lengths to 1, to prevent iwlmld and mac80211 from building A-MSDUs.
- Update the RC and the TID specific A-MSDU maximal lengths based on
  the FW TLC notifications.

Signed-off-by: Ilan Peer <ilan.peer@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250309073442.afc842633002.I68153b6b0c5d976f2c7525009631f8fa28e9987c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/sta.c | 24 +++++++++++
 drivers/net/wireless/intel/iwlwifi/mld/tlc.c | 43 ++++++--------------
 2 files changed, 37 insertions(+), 30 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/sta.c b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
index 994d4561518bd..332a7aecec2d3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/sta.c
@@ -606,6 +606,25 @@ iwl_mld_remove_link_sta(struct iwl_mld *mld,
 		kfree_rcu(mld_link_sta, rcu_head);
 }
 
+static void iwl_mld_set_max_amsdu_len(struct iwl_mld *mld,
+				      struct ieee80211_link_sta *link_sta)
+{
+	const struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
+
+	/* For EHT, HE and VHT we can use the value as it was calculated by
+	 * mac80211. For HT, mac80211 doesn't enforce to 4095, so force it
+	 * here
+	 */
+	if (link_sta->eht_cap.has_eht || link_sta->he_cap.has_he ||
+	    link_sta->vht_cap.vht_supported ||
+	    !ht_cap->ht_supported ||
+	    !(ht_cap->cap & IEEE80211_HT_CAP_MAX_AMSDU))
+		return;
+
+	link_sta->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA;
+	ieee80211_sta_recalc_aggregates(link_sta->sta);
+}
+
 int iwl_mld_update_all_link_stations(struct iwl_mld *mld,
 				     struct ieee80211_sta *sta)
 {
@@ -618,6 +637,9 @@ int iwl_mld_update_all_link_stations(struct iwl_mld *mld,
 
 		if (ret)
 			return ret;
+
+		if (mld_sta->sta_state == IEEE80211_STA_ASSOC)
+			iwl_mld_set_max_amsdu_len(mld, link_sta);
 	}
 	return 0;
 }
@@ -1222,6 +1244,8 @@ int iwl_mld_update_link_stas(struct iwl_mld *mld,
 
 		link = link_conf_dereference_protected(mld_sta->vif,
 						       link_sta->link_id);
+
+		iwl_mld_set_max_amsdu_len(mld, link_sta);
 		iwl_mld_config_tlc_link(mld, vif, link, link_sta);
 
 		sta_mask_added |= BIT(mld_link_sta->fw_id);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tlc.c b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
index 85ec358f1417d..f054cc921d9d4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tlc.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 
 #include <net/mac80211.h>
@@ -467,7 +467,7 @@ static void iwl_mld_send_tlc_cmd(struct iwl_mld *mld,
 						   own_he_cap, own_eht_cap),
 		.chains = iwl_mld_get_fw_chains(mld),
 		.sgi_ch_width_supp = iwl_mld_get_fw_sgi(link_sta),
-		.max_mpdu_len = cpu_to_le16(link_sta->agg.max_rc_amsdu_len),
+		.max_mpdu_len = cpu_to_le16(link_sta->agg.max_amsdu_len),
 	};
 	int fw_sta_id = iwl_mld_fw_sta_id_from_link_sta(mld, link_sta);
 	int ret;
@@ -493,30 +493,6 @@ static void iwl_mld_send_tlc_cmd(struct iwl_mld *mld,
 		IWL_ERR(mld, "Failed to send TLC cmd (%d)\n", ret);
 }
 
-static void iwl_mld_recalc_amsdu_len(struct iwl_mld *mld,
-				     struct ieee80211_link_sta *link_sta)
-{
-	const struct ieee80211_sta_ht_cap *ht_cap = &link_sta->ht_cap;
-
-	/* For EHT, HE and VHT - we can use the value as it was calculated by
-	 * mac80211.
-	 */
-	if (link_sta->eht_cap.has_eht || link_sta->he_cap.has_he ||
-	    link_sta->vht_cap.vht_supported)
-		goto recalc;
-
-	/* But for HT, mac80211 doesn't enforce to 4095, so force it here */
-	if (ht_cap->ht_supported && ht_cap->cap & IEEE80211_HT_CAP_MAX_AMSDU)
-		/* Agg is offloaded, so we need to assume that agg are enabled
-		 * and max mpdu in ampdu is 4095 (spec 802.11-2016 9.3.2.1)
-		 */
-		link_sta->agg.max_amsdu_len = IEEE80211_MAX_MPDU_LEN_HT_BA;
-
-recalc:
-	link_sta->agg.max_rc_amsdu_len = link_sta->agg.max_amsdu_len;
-	ieee80211_sta_recalc_aggregates(link_sta->sta);
-}
-
 int iwl_mld_send_tlc_dhc(struct iwl_mld *mld, u8 sta_id, u32 type, u32 data)
 {
 	struct {
@@ -547,15 +523,22 @@ void iwl_mld_config_tlc_link(struct iwl_mld *mld,
 			     struct ieee80211_bss_conf *link_conf,
 			     struct ieee80211_link_sta *link_sta)
 {
+	struct iwl_mld_sta *mld_sta = iwl_mld_sta_from_mac80211(link_sta->sta);
 	enum nl80211_band band;
 
 	if (WARN_ON_ONCE(!link_conf->chanreq.oper.chan))
 		return;
 
-	band = link_conf->chanreq.oper.chan->band;
-
-	iwl_mld_recalc_amsdu_len(mld, link_sta);
+	/* Before we have information about a station, configure the A-MSDU RC
+	 * limit such that iwlmd and mac80211 would not be allowed to build
+	 * A-MSDUs.
+	 */
+	if (mld_sta->sta_state < IEEE80211_STA_ASSOC) {
+		link_sta->agg.max_rc_amsdu_len = 1;
+		ieee80211_sta_recalc_aggregates(link_sta->sta);
+	}
 
+	band = link_conf->chanreq.oper.chan->band;
 	iwl_mld_send_tlc_cmd(mld, vif, link_sta, band);
 }
 
@@ -706,7 +689,7 @@ void iwl_mld_handle_tlc_notif(struct iwl_mld *mld,
 			link_sta->agg.max_tid_amsdu_len[i] =
 				iwl_mld_get_amsdu_size_of_tid(mld, link_sta, i);
 		else
-			link_sta->agg.max_tid_amsdu_len[i] = 0;
+			link_sta->agg.max_tid_amsdu_len[i] = 1;
 	}
 
 	ieee80211_sta_recalc_aggregates(link_sta->sta);

From f31d666f0b710818603a8b6a03cff23ea4a2ad0e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:51 +0200
Subject: [PATCH 2004/2753] wifi: iwlwifi: mld: always do MLO scan before link
 selection

According to the requirements, if the last scan isn't older than 20
seconds, we can use its results and do the link selection without
scanning before.
But this applies only when trying to get back to EMLSR, not if the link
has bad RSSI/missed beacons.
Since an MLO scan is cheap anyway, and results from 20 seconds before
are really old, always scan before links switching.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.a4c96e5c49d4.Ie55697af49435c2c45dccf7c607de5857b370f7a@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/link.c |  2 +-
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  | 20 ++-----------------
 drivers/net/wireless/intel/iwlwifi/mld/mlo.h  |  3 ---
 .../net/wireless/intel/iwlwifi/mld/stats.c    |  2 +-
 4 files changed, 4 insertions(+), 23 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
index 1db69aee4e9fa..6db8b53053490 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -913,7 +913,7 @@ void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld,
 		ieee80211_cqm_beacon_loss_notify(vif, GFP_ATOMIC);
 
 		/* try to switch links, no-op if we don't have MLO */
-		iwl_mld_trigger_link_selection(mld, vif);
+		iwl_mld_int_mlo_scan(mld, vif);
 	}
 
 	/* no more logic if we're not in EMLSR */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index bbaf9ad0e9eb0..99ba4018fb247 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -289,22 +289,6 @@ int iwl_mld_block_emlsr_sync(struct iwl_mld *mld, struct ieee80211_vif *vif,
 static void _iwl_mld_select_links(struct iwl_mld *mld,
 				  struct ieee80211_vif *vif);
 
-void iwl_mld_trigger_link_selection(struct iwl_mld *mld,
-				    struct ieee80211_vif *vif)
-{
-	bool last_scan_was_recent =
-		time_before(jiffies, mld->scan.last_mlo_scan_jiffies +
-				     IWL_MLD_SCAN_EXPIRE_TIME);
-
-	if (last_scan_was_recent) {
-		IWL_DEBUG_EHT(mld, "MLO scan was recent, skip.\n");
-		_iwl_mld_select_links(mld, vif);
-	} else {
-		IWL_DEBUG_EHT(mld, "Doing link selection after MLO scan\n");
-		iwl_mld_int_mlo_scan(mld, vif);
-	}
-}
-
 void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
 			   enum iwl_mld_emlsr_blocked reason)
 {
@@ -334,7 +318,7 @@ void iwl_mld_unblock_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif,
 		return;
 
 	IWL_DEBUG_INFO(mld, "EMLSR is unblocked\n");
-	iwl_mld_trigger_link_selection(mld, vif);
+	iwl_mld_int_mlo_scan(mld, vif);
 }
 
 static void
@@ -1011,5 +995,5 @@ void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif)
 	    mld_vif->emlsr.blocked_reasons)
 		return;
 
-	iwl_mld_trigger_link_selection(mld, vif);
+	iwl_mld_int_mlo_scan(mld, vif);
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
index fd1abe8e6084a..0f1b18f61c759 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -141,9 +141,6 @@ void iwl_mld_emlsr_check_bt(struct iwl_mld *mld);
 
 void iwl_mld_emlsr_check_chan_load(struct iwl_mld *mld);
 
-void iwl_mld_trigger_link_selection(struct iwl_mld *mld,
-				    struct ieee80211_vif *vif);
-
 /**
  * iwl_mld_retry_emlsr - Retry entering EMLSR
  * @mld: MLD context
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
index 5633885c49ff2..a9d3860d8f9cb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/stats.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -384,7 +384,7 @@ static void iwl_mld_update_link_sig(struct ieee80211_vif *vif, int sig,
 	/* Handle inactive EMLSR, check whether to switch links */
 	if (!iwl_mld_emlsr_active(vif)) {
 		if (sig < IWL_MLD_LOW_RSSI_MLO_SCAN_THRESH)
-			iwl_mld_trigger_link_selection(mld, vif);
+			iwl_mld_int_mlo_scan(mld, vif);
 		return;
 	}
 

From d414ff7a733819f78a49b832fad6d4e7cb1f9150 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:52 +0200
Subject: [PATCH 2005/2753] wifi: iwlwifi: mld: fix bad RSSI handling

If the RSSI is dropping to below the threshold, we need to do a MLO
scan to try select a better link.
This is true also if the connection doesn't have EMLSR capability,
and also if we are in EMLSR.
Fix the logic to always check the RSSI (and do a MLO scan if needed).

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.a31b95888244.If6dca30d657658fa902b19e07b6fbc86c48d69cb@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/stats.c | 10 +++-------
 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
index a9d3860d8f9cb..75cb204c24194 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/stats.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -378,15 +378,11 @@ static void iwl_mld_update_link_sig(struct ieee80211_vif *vif, int sig,
 
 	/* TODO: task=statistics handle CQM notifications */
 
-	if (!iwl_mld_vif_has_emlsr_cap(vif))
-		return;
+	if (sig < IWL_MLD_LOW_RSSI_MLO_SCAN_THRESH)
+		iwl_mld_int_mlo_scan(mld, vif);
 
-	/* Handle inactive EMLSR, check whether to switch links */
-	if (!iwl_mld_emlsr_active(vif)) {
-		if (sig < IWL_MLD_LOW_RSSI_MLO_SCAN_THRESH)
-			iwl_mld_int_mlo_scan(mld, vif);
+	if (!iwl_mld_emlsr_active(vif))
 		return;
-	}
 
 	/* We are in EMLSR, check if we need to exit */
 	exit_emlsr_thresh =

From 9324731b9985478faf7f77713cc5e5fee811716e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Sun, 9 Mar 2025 07:36:53 +0200
Subject: [PATCH 2006/2753] wifi: iwlwifi: mld: avoid selecting bad links

Currently, we don't select a link that wasn't heared in the last 5
seconds.
But if the link started to suffer from missed beacons more recent than
that, we might select this link even we really shouldn't,
leading to a disconnection instead of a link switch.

Fix this by checking if a link was heared in the last MLO scan,
if not - don't include it in the link selection.
Since we do an MLO scan on missed beacons, we will not hear that link in
that scan, and won't select it.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250309073442.8f950497219e.I51306021fe9231a8184e89c23707be47d3c05241@changeid
[replace cast with ULL constant]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  | 10 +++++-----
 drivers/net/wireless/intel/iwlwifi/mld/scan.c |  4 +++-
 drivers/net/wireless/intel/iwlwifi/mld/scan.h |  5 +++--
 3 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 99ba4018fb247..a5b1d373922a8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -704,10 +704,9 @@ iwl_mld_set_link_sel_data(struct iwl_mld *mld,
 		if (WARN_ON_ONCE(!link_conf))
 			continue;
 
-		/* Ignore any BSS that was not seen in the last 5 seconds */
+		/* Ignore any BSS that was not seen in the last MLO scan */
 		if (ktime_before(link_conf->bss->ts_boottime,
-				 ktime_sub_ns(ktime_get_boottime_ns(),
-					      (u64)5 * NSEC_PER_SEC)))
+				 mld->scan.last_mlo_scan_time))
 			continue;
 
 		data[n_data].link_id = link_id;
@@ -819,8 +818,9 @@ static void _iwl_mld_select_links(struct iwl_mld *mld,
 	if (!mld_vif->authorized || hweight16(usable_links) <= 1)
 		return;
 
-	if (WARN(time_before(mld->scan.last_mlo_scan_jiffies,
-			     jiffies - IWL_MLD_SCAN_EXPIRE_TIME),
+	if (WARN(ktime_before(mld->scan.last_mlo_scan_time,
+			      ktime_sub_ns(ktime_get_boottime_ns(),
+					   5ULL * NSEC_PER_SEC)),
 		"Last MLO scan was too long ago, can't select links\n"))
 		return;
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.c b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
index 5f4ede92028b4..7ec04318ec2fc 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/scan.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.c
@@ -1794,6 +1794,9 @@ static void iwl_mld_int_mlo_scan_start(struct iwl_mld *mld,
 	ret = _iwl_mld_single_scan_start(mld, vif, req, &ies,
 					 IWL_MLD_SCAN_INT_MLO);
 
+	if (!ret)
+		mld->scan.last_mlo_scan_time = ktime_get_boottime_ns();
+
 	IWL_DEBUG_SCAN(mld, "Internal MLO scan: ret=%d\n", ret);
 }
 
@@ -1922,7 +1925,6 @@ void iwl_mld_handle_scan_complete_notif(struct iwl_mld *mld,
 		mld->scan.pass_all_sched_res = SCHED_SCAN_PASS_ALL_STATE_DISABLED;
 	} else if (mld->scan.uid_status[uid] == IWL_MLD_SCAN_INT_MLO) {
 		IWL_DEBUG_SCAN(mld, "Internal MLO scan completed\n");
-		mld->scan.last_mlo_scan_jiffies = jiffies;
 
 		/*
 		 * We limit link selection to internal MLO scans as otherwise
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/scan.h b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
index cb589e0023193..3ae940d55065c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/scan.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/scan.h
@@ -108,7 +108,8 @@ enum iwl_mld_traffic_load {
  *	in jiffies.
  * @last_start_time_jiffies: stores the last start time in jiffies
  *	(interface up/reset/resume).
- * @last_mlo_scan_jiffies: end time of the last MLO scan in jiffies.
+ * @last_mlo_scan_time: start time of the last MLO scan in nanoseconds since
+ *	boot.
  */
 struct iwl_mld_scan {
 	/* Add here fields that need clean up on restart */
@@ -129,7 +130,7 @@ struct iwl_mld_scan {
 	void *cmd;
 	unsigned long last_6ghz_passive_jiffies;
 	unsigned long last_start_time_jiffies;
-	unsigned long last_mlo_scan_jiffies;
+	unsigned long last_mlo_scan_time;
 };
 
 #endif /* __iwl_mld_scan_h__ */

From a8045e46c508b70fe4b30cc020fd0a2b0709b2e5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Jos=C3=A9=20Roberto=20de=20Souza?= <jose.souza@intel.com>
Date: Thu, 6 Mar 2025 13:08:27 -0800
Subject: [PATCH 2007/2753] drm/i915: Increase I915_PARAM_MMAP_GTT_VERSION
 version to indicate support for partial mmaps
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 255fc1703e42 ("drm/i915/gem: Calculate object page offset for partial memory mapping")
was the last patch of several patches fixing multiple partial mmaps.
But without a bump in I915_PARAM_MMAP_GTT_VERSION there is no clean
way for UMD to know if it can do multiple partial mmaps.

Fixes: 255fc1703e42 ("drm/i915/gem: Calculate object page offset for partial memory mapping")
Cc: Andi Shyti <andi.shyti@linux.intel.com>
Cc: Nirmoy Das <nirmoy.das@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Nirmoy Das <nirmoy.das@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20250306210827.171147-1-jose.souza@intel.com
(cherry picked from commit bfef148f3680e6b9d28e7fca46d9520f80c5e50e)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
---
 drivers/gpu/drm/i915/gem/i915_gem_mman.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index 21274aa9bdddc..c3dabb8579605 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -164,6 +164,9 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  * 4 - Support multiple fault handlers per object depending on object's
  *     backing storage (a.k.a. MMAP_OFFSET).
  *
+ * 5 - Support multiple partial mmaps(mmap part of BO + unmap a offset, multiple
+ *     times with different size and offset).
+ *
  * Restrictions:
  *
  *  * snoopable objects cannot be accessed via the GTT. It can cause machine
@@ -191,7 +194,7 @@ static unsigned int tile_row_pages(const struct drm_i915_gem_object *obj)
  */
 int i915_gem_mmap_gtt_version(void)
 {
-	return 4;
+	return 5;
 }
 
 static inline struct i915_gtt_view

From 5daa0c35a1f0e7a6c3b8ba9cb721e7d1ace6e619 Mon Sep 17 00:00:00 2001
From: Matthew Maurer <mmaurer@google.com>
Date: Wed, 8 Jan 2025 23:35:08 +0000
Subject: [PATCH 2008/2753] rust: Disallow BTF generation with Rust + LTO

The kernel cannot currently self-parse BTF containing Rust debug
information. pahole uses the language of the CU to determine whether to
filter out debug information when generating the BTF. When LTO is
enabled, Rust code can cross CU boundaries, resulting in Rust debug
information in CUs labeled as C. This results in a system which cannot
parse its own BTF.

Signed-off-by: Matthew Maurer <mmaurer@google.com>
Cc: stable@vger.kernel.org
Fixes: c1177979af9c ("btf, scripts: Exclude Rust CUs with pahole")
Link: https://lore.kernel.org/r/20250108-rust-btf-lto-incompat-v1-1-60243ff6d820@google.com
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 init/Kconfig | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/init/Kconfig b/init/Kconfig
index d0d021b3fa3b3..324c2886b2ea3 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1973,7 +1973,7 @@ config RUST
 	depends on !MODVERSIONS || GENDWARFKSYMS
 	depends on !GCC_PLUGIN_RANDSTRUCT
 	depends on !RANDSTRUCT
-	depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE
+	depends on !DEBUG_INFO_BTF || (PAHOLE_HAS_LANG_EXCLUDE && !LTO)
 	depends on !CFI_CLANG || HAVE_CFI_ICALL_NORMALIZE_INTEGERS_RUSTC
 	select CFI_ICALL_NORMALIZE_INTEGERS if CFI_CLANG
 	depends on !CALL_PADDING || RUSTC_VERSION >= 108100

From 2e0f91aba507a3cb59f7a12fc3ea2b7d4d6675b7 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Mon, 10 Feb 2025 12:03:24 -0500
Subject: [PATCH 2009/2753] scripts: generate_rust_analyzer: add missing macros
 deps

The macros crate has depended on std and proc_macro since its
introduction in commit 1fbde52bde73 ("rust: add `macros` crate"). These
dependencies were omitted from commit 8c4555ccc55c ("scripts: add
`generate_rust_analyzer.py`") resulting in missing go-to-definition and
autocomplete, and false-positive warnings emitted from rust-analyzer
such as:

  [{
  	"resource": "/Users/tamird/src/linux/rust/macros/module.rs",
  	"owner": "_generated_diagnostic_collection_name_#1",
  	"code": {
  		"value": "non_snake_case",
  		"target": {
  			"$mid": 1,
  			"path": "/rustc/",
  			"scheme": "https",
  			"authority": "doc.rust-lang.org",
  			"query": "search=non_snake_case"
  		}
  	},
  	"severity": 4,
  	"message": "Variable `None` should have snake_case name, e.g. `none`",
  	"source": "rust-analyzer",
  	"startLineNumber": 123,
  	"startColumn": 17,
  	"endLineNumber": 123,
  	"endColumn": 21
  }]

Add the missing dependencies to improve the developer experience.

  [ Fiona had a different approach (thanks!) at:

        https://lore.kernel.org/rust-for-linux/20241205115438.234221-1-me@kloenk.dev/

    But Tamir and Fiona agreed to this one. - Miguel ]

Fixes: 8c4555ccc55c ("scripts: add `generate_rust_analyzer.py`")
Reviewed-by: Fiona Behrens <me@kloenk.dev>
Diagnosed-by: Chayim Refael Friedman <chayimfr@gmail.com>
Link: https://github.com/rust-lang/rust-analyzer/issues/17759#issuecomment-2646328275
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Tested-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250210-rust-analyzer-macros-core-dep-v3-1-45eb4836f218@gmail.com
[ Removed `return`. Changed tag name. Added Link. Slightly
  reworded. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/generate_rust_analyzer.py | 30 +++++++++++++++++++++---------
 1 file changed, 21 insertions(+), 9 deletions(-)

diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index aa8ea1a4dbe5f..b40679a90843b 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -57,14 +57,26 @@ def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=Tr
         crates_indexes[display_name] = len(crates)
         crates.append(crate)
 
-    # First, the ones in `rust/` since they are a bit special.
-    append_crate(
-        "core",
-        sysroot_src / "core" / "src" / "lib.rs",
-        [],
-        cfg=crates_cfgs.get("core", []),
-        is_workspace_member=False,
-    )
+    def append_sysroot_crate(
+        display_name,
+        deps,
+        cfg=[],
+    ):
+        append_crate(
+            display_name,
+            sysroot_src / display_name / "src" / "lib.rs",
+            deps,
+            cfg,
+            is_workspace_member=False,
+        )
+
+    # NB: sysroot crates reexport items from one another so setting up our transitive dependencies
+    # here is important for ensuring that rust-analyzer can resolve symbols. The sources of truth
+    # for this dependency graph are `(sysroot_src / crate / "Cargo.toml" for crate in crates)`.
+    append_sysroot_crate("core", [], cfg=crates_cfgs.get("core", []))
+    append_sysroot_crate("alloc", ["core"])
+    append_sysroot_crate("std", ["alloc", "core"])
+    append_sysroot_crate("proc_macro", ["core", "std"])
 
     append_crate(
         "compiler_builtins",
@@ -75,7 +87,7 @@ def append_crate(display_name, root_module, deps, cfg=[], is_workspace_member=Tr
     append_crate(
         "macros",
         srctree / "rust" / "macros" / "lib.rs",
-        [],
+        ["std", "proc_macro"],
         is_proc_macro=True,
     )
 

From d1f928052439cad028438a8b8b34c1f01bc06068 Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Mon, 10 Feb 2025 13:04:16 -0500
Subject: [PATCH 2010/2753] scripts: generate_rust_analyzer: add missing
 include_dirs

Commit 8c4555ccc55c ("scripts: add `generate_rust_analyzer.py`")
specified OBJTREE for the bindings crate, and `source.include_dirs` for
the kernel crate, likely in an attempt to support out-of-source builds
for those crates where the generated files reside in `objtree` rather
than `srctree`. This was insufficient because both bits of configuration
are required for each crate; the result is that rust-analyzer is unable
to resolve generated files for either crate in an out-of-source build.

  [ Originally we were not using `OBJTREE` in the `kernel` crate, but
    we did pass the variable anyway, so conceptually it could have been
    there since then.

    Regarding `include_dirs`, it started in `kernel` before being in
    mainline because we included the bindings directly there (i.e.
    there was no `bindings` crate). However, when that crate got
    created, we moved the `OBJTREE` there but not the `include_dirs`.
    Nowadays, though, we happen to need the `include_dirs` also in
    the `kernel` crate for `generated_arch_static_branch_asm.rs` which
    was not there back then -- Tamir confirms it is indeed required
    for that reason. - Miguel ]

Add the missing bits to improve the developer experience.

Fixes: 8c4555ccc55c ("scripts: add `generate_rust_analyzer.py`")
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Tested-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250210-rust-analyzer-bindings-include-v2-1-23dff845edc3@gmail.com
[ Slightly reworded title. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/generate_rust_analyzer.py | 40 +++++++++++++++----------------
 1 file changed, 20 insertions(+), 20 deletions(-)

diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index b40679a90843b..f2d6787e9c0c5 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -97,27 +97,27 @@ def append_sysroot_crate(
         ["core", "compiler_builtins"],
     )
 
-    append_crate(
-        "bindings",
-        srctree / "rust"/ "bindings" / "lib.rs",
-        ["core"],
-        cfg=cfg,
-    )
-    crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True))
+    def append_crate_with_generated(
+        display_name,
+        deps,
+    ):
+        append_crate(
+            display_name,
+            srctree / "rust"/ display_name / "lib.rs",
+            deps,
+            cfg=cfg,
+        )
+        crates[-1]["env"]["OBJTREE"] = str(objtree.resolve(True))
+        crates[-1]["source"] = {
+            "include_dirs": [
+                str(srctree / "rust" / display_name),
+                str(objtree / "rust")
+            ],
+            "exclude_dirs": [],
+        }
 
-    append_crate(
-        "kernel",
-        srctree / "rust" / "kernel" / "lib.rs",
-        ["core", "macros", "build_error", "bindings"],
-        cfg=cfg,
-    )
-    crates[-1]["source"] = {
-        "include_dirs": [
-            str(srctree / "rust" / "kernel"),
-            str(objtree / "rust")
-        ],
-        "exclude_dirs": [],
-    }
+    append_crate_with_generated("bindings", ["core"])
+    append_crate_with_generated("kernel", ["core", "macros", "build_error", "bindings"])
 
     def is_root_crate(build_file, target):
         try:

From a1eb95d6b5f4cf5cc7b081e85e374d1dd98a213b Mon Sep 17 00:00:00 2001
From: Tamir Duberstein <tamird@gmail.com>
Date: Mon, 10 Feb 2025 13:04:17 -0500
Subject: [PATCH 2011/2753] scripts: generate_rust_analyzer: add uapi crate

Commit 4e1746656839 ("rust: uapi: Add UAPI crate") did not update
rust-analyzer to include the new crate.

Add the missing definition to improve the developer experience.

Fixes: 4e1746656839 ("rust: uapi: Add UAPI crate")
Signed-off-by: Tamir Duberstein <tamird@gmail.com>
Tested-by: Andreas Hindborg <a.hindborg@kernel.org>
Link: https://lore.kernel.org/r/20250210-rust-analyzer-bindings-include-v2-2-23dff845edc3@gmail.com
[ Slightly reworded title. - Miguel ]
Signed-off-by: Miguel Ojeda <ojeda@kernel.org>
---
 scripts/generate_rust_analyzer.py | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/scripts/generate_rust_analyzer.py b/scripts/generate_rust_analyzer.py
index f2d6787e9c0c5..adae71544cbd6 100755
--- a/scripts/generate_rust_analyzer.py
+++ b/scripts/generate_rust_analyzer.py
@@ -117,7 +117,8 @@ def append_crate_with_generated(
         }
 
     append_crate_with_generated("bindings", ["core"])
-    append_crate_with_generated("kernel", ["core", "macros", "build_error", "bindings"])
+    append_crate_with_generated("uapi", ["core"])
+    append_crate_with_generated("kernel", ["core", "macros", "build_error", "bindings", "uapi"])
 
     def is_root_crate(build_file, target):
         try:

From 379c590113ce46f605439d4887996c60ab8820cc Mon Sep 17 00:00:00 2001
From: Geert Uytterhoeven <geert+renesas@glider.be>
Date: Mon, 10 Mar 2025 14:12:20 +0100
Subject: [PATCH 2012/2753] ARM: shmobile: smp: Enforce shmobile_smp_*
 alignment

When the addresses of the shmobile_smp_mpidr, shmobile_smp_fn, and
shmobile_smp_arg variables are not multiples of 4 bytes, secondary CPU
bring-up fails:

    smp: Bringing up secondary CPUs ...
    CPU1: failed to come online
    CPU2: failed to come online
    CPU3: failed to come online
    smp: Brought up 1 node, 1 CPU

Fix this by adding the missing alignment directive.

Fixes: 4e960f52fce16a3b ("ARM: shmobile: Move shmobile_smp_{mpidr, fn, arg}[] from .text to .bss")
Closes: https://lore.kernel.org/r/CAMuHMdU=QR-JLgEHKWpsr6SbaZRc-Hz9r91JfpP8c3n2G-OjqA@mail.gmail.com
Signed-off-by: Geert Uytterhoeven <geert+renesas@glider.be>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://lore.kernel.org/c499234d559a0d95ad9472883e46077311051cd8.1741612208.git.geert+renesas@glider.be
Cc: stable@vger.kernel.org
---
 arch/arm/mach-shmobile/headsmp.S | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-shmobile/headsmp.S b/arch/arm/mach-shmobile/headsmp.S
index a956b489b6ea1..2bc7e73a8582d 100644
--- a/arch/arm/mach-shmobile/headsmp.S
+++ b/arch/arm/mach-shmobile/headsmp.S
@@ -136,6 +136,7 @@ ENDPROC(shmobile_smp_sleep)
 	.long	shmobile_smp_arg - 1b
 
 	.bss
+	.align	2
 	.globl	shmobile_smp_mpidr
 shmobile_smp_mpidr:
 	.space	NR_CPUS * 4

From 8ae227f8a7749eec92fc381dfbe213429c852278 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Tue, 11 Mar 2025 12:17:04 +0100
Subject: [PATCH 2013/2753] wifi: mac80211: fix MPDU length parsing for EHT 5/6
 GHz

The MPDU length is only configured using the EHT capabilities element on
2.4 GHz. On 5/6 GHz it is configured using the VHT or HE capabilities
respectively.

Fixes: cf0079279727 ("wifi: mac80211: parse A-MSDU len from EHT capabilities")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Link: https://patch.msgid.link/20250311121704.0634d31f0883.I28063e4d3ef7d296b7e8a1c303460346a30bf09c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/eht.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/mac80211/eht.c b/net/mac80211/eht.c
index 7a3116c36df9f..fd41046e3b681 100644
--- a/net/mac80211/eht.c
+++ b/net/mac80211/eht.c
@@ -2,7 +2,7 @@
 /*
  * EHT handling
  *
- * Copyright(c) 2021-2024 Intel Corporation
+ * Copyright(c) 2021-2025 Intel Corporation
  */
 
 #include "ieee80211_i.h"
@@ -76,6 +76,13 @@ ieee80211_eht_cap_ie_to_sta_eht_cap(struct ieee80211_sub_if_data *sdata,
 	link_sta->cur_max_bandwidth = ieee80211_sta_cap_rx_bw(link_sta);
 	link_sta->pub->bandwidth = ieee80211_sta_cur_vht_bw(link_sta);
 
+	/*
+	 * The MPDU length bits are reserved on all but 2.4 GHz and get set via
+	 * VHT (5 GHz) or HE (6 GHz) capabilities.
+	 */
+	if (sband->band != NL80211_BAND_2GHZ)
+		return;
+
 	switch (u8_get_bits(eht_cap->eht_cap_elem.mac_cap_info[0],
 			    IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK)) {
 	case IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454:

From c04d96913c88fdc11400ca6dd7f436bb6ecc764c Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 10 Mar 2025 15:23:32 -0700
Subject: [PATCH 2014/2753] wifi: mwifiex: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to and correctly identify the char array as "not a C
string" and thereby eliminate the warning.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Cc: Brian Norris <briannorris@chromium.org>
Cc: Francesco Dolcini <francesco@dolcini.it>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Allison Randal <allison@lohutok.net>
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250310222332.work.202-kees@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/cfp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/cfp.c b/drivers/net/wireless/marvell/mwifiex/cfp.c
index d39092b992129..d7fd79214bcfb 100644
--- a/drivers/net/wireless/marvell/mwifiex/cfp.c
+++ b/drivers/net/wireless/marvell/mwifiex/cfp.c
@@ -150,7 +150,7 @@ static const u16 ac_mcs_rate_nss2[8][10] = {
 
 struct region_code_mapping {
 	u8 code;
-	u8 region[IEEE80211_COUNTRY_STRING_LEN];
+	u8 region[IEEE80211_COUNTRY_STRING_LEN] __nonstring;
 };
 
 static struct region_code_mapping region_code_mapping_t[] = {

From 8300f2504afeceac234027d433a2f71d4a39c7fe Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 11 Mar 2025 15:55:20 -0700
Subject: [PATCH 2015/2753] wifi: zd1211rw: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to and correctly identify the char array as "not a C
string" and thereby eliminate the warning.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250311225513.it.620-kees@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/zydas/zd1211rw/zd_mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
index f90c33d19b399..9653dbaac3c05 100644
--- a/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
+++ b/drivers/net/wireless/zydas/zd1211rw/zd_mac.c
@@ -21,7 +21,7 @@
 
 struct zd_reg_alpha2_map {
 	u32 reg;
-	char alpha2[2];
+	char alpha2[2] __nonstring;
 };
 
 static struct zd_reg_alpha2_map reg_alpha2_map[] = {

From adb1ee4de04d496f3da409bb6791cfdd744ab2c3 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 11 Mar 2025 15:56:05 -0700
Subject: [PATCH 2016/2753] wifi: virt_wifi: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to and correctly identify the char array as "not a C
string" and thereby eliminate the warning.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250311225604.it.926-kees@kernel.org
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/virtual/virt_wifi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
index f9d11a0233136..1fffeff2190ca 100644
--- a/drivers/net/wireless/virtual/virt_wifi.c
+++ b/drivers/net/wireless/virtual/virt_wifi.c
@@ -146,7 +146,7 @@ static void virt_wifi_inform_bss(struct wiphy *wiphy)
 	static const struct {
 		u8 tag;
 		u8 len;
-		u8 ssid[8];
+		u8 ssid[8] __nonstring;
 	} __packed ssid = {
 		.tag = WLAN_EID_SSID,
 		.len = VIRT_WIFI_SSID_LEN,

From 899da1830db112e6bd54ed4573ace753eae6ef22 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 11 Mar 2025 12:10:03 +0100
Subject: [PATCH 2017/2753] wifi: mac80211: remove SSID from ML reconf

The ML reconfiguration frame shouldn't contain an SSID,
remove it.

Fixes: 36e05b0b8390 ("wifi: mac80211: Support dynamic link addition and removal")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Link: https://patch.msgid.link/20250311121004.fdf08f90bc30.I07f88d3a6f592a0df65d48f55d65c46a4d261007@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index bfd3653a5b847..3dae02345ab8e 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -10233,8 +10233,8 @@ ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 		size += 2 + sizeof(struct ieee80211_mle_per_sta_profile) +
 			ETH_ALEN;
 
-		/* SSID element + WMM */
-		size += 2 + sdata->vif.cfg.ssid_len + 9;
+		/* WMM */
+		size += 9;
 		size += ieee80211_link_common_elems_size(sdata, iftype, cbss,
 							 elems_len);
 	}
@@ -10346,11 +10346,6 @@ ieee80211_build_ml_reconf_req(struct ieee80211_sub_if_data *sdata,
 
 			capab_pos = skb_put(skb, 2);
 
-			skb_put_u8(skb, WLAN_EID_SSID);
-			skb_put_u8(skb, sdata->vif.cfg.ssid_len);
-			skb_put_data(skb, sdata->vif.cfg.ssid,
-				     sdata->vif.cfg.ssid_len);
-
 			extra_used =
 				ieee80211_add_link_elems(sdata, skb, &capab, NULL,
 							 add_links_data->link[link_id].elems,

From 80834e7d857932553dc22b0addbec744060aaf9f Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 11 Mar 2025 12:10:04 +0100
Subject: [PATCH 2018/2753] wifi: mac80211: use supported selectors from assoc
 in ML reconf

For multi-link reconfiguration, we shouldn't have any BSS
membership selectors that are different from the association.
Track the association selectors and use them to check the new
link(s) added during reconfiguration.

Fixes: 36e05b0b8390 ("wifi: mac80211: Support dynamic link addition and removal")
Reviewed-by: Ilan Peer <ilan.peer@intel.com>
Link: https://patch.msgid.link/20250311121004.771de0c36a75.I72f87d048c8693919b99dd9d4eee39833f06d15f@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/ieee80211_i.h |  4 ++--
 net/mac80211/mlme.c        | 29 +++++++++++------------------
 2 files changed, 13 insertions(+), 20 deletions(-)

diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 217e949bb756c..fb05f3cd37ec4 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -444,8 +444,6 @@ struct ieee80211_mgd_assoc_data {
 	const u8 *supp_rates;
 	u8 supp_rates_len;
 
-	unsigned long userspace_selectors[BITS_TO_LONGS(128)];
-
 	unsigned long timeout;
 	int tries;
 
@@ -524,6 +522,8 @@ struct ieee80211_if_managed {
 	struct ieee80211_mgd_auth_data *auth_data;
 	struct ieee80211_mgd_assoc_data *assoc_data;
 
+	unsigned long userspace_selectors[BITS_TO_LONGS(128)];
+
 	bool powersave; /* powersave requested for this iface */
 	bool broken_ap; /* AP is broken -- turn off powersave */
 
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 3dae02345ab8e..9bff639b52208 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -4164,6 +4164,9 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
 
 	ifmgd->epcs.enabled = false;
 	ifmgd->epcs.dialog_token = 0;
+
+	memset(ifmgd->userspace_selectors, 0,
+	       sizeof(ifmgd->userspace_selectors));
 }
 
 static void ieee80211_reset_ap_probe(struct ieee80211_sub_if_data *sdata)
@@ -6136,7 +6139,7 @@ static bool ieee80211_assoc_success(struct ieee80211_sub_if_data *sdata,
 
 			err = ieee80211_prep_channel(sdata, link, link_id, cbss,
 						     true, &link->u.mgd.conn,
-						     assoc_data->userspace_selectors);
+						     sdata->u.mgd.userspace_selectors);
 			if (err) {
 				link_info(link, "prep_channel failed\n");
 				goto out_err;
@@ -9400,7 +9403,9 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 					    false);
 	}
 
-	ieee80211_parse_cfg_selectors(assoc_data->userspace_selectors,
+	memset(sdata->u.mgd.userspace_selectors, 0,
+	       sizeof(sdata->u.mgd.userspace_selectors));
+	ieee80211_parse_cfg_selectors(sdata->u.mgd.userspace_selectors,
 				      req->supported_selectors,
 				      req->supported_selectors_len);
 
@@ -9651,7 +9656,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 		err = ieee80211_prep_channel(sdata, NULL, i,
 					     assoc_data->link[i].bss, true,
 					     &assoc_data->link[i].conn,
-					     assoc_data->userspace_selectors);
+					     sdata->u.mgd.userspace_selectors);
 		if (err) {
 			req->links[i].error = err;
 			goto err_clear;
@@ -9668,7 +9673,7 @@ int ieee80211_mgd_assoc(struct ieee80211_sub_if_data *sdata,
 					req->ap_mld_addr, true,
 					&assoc_data->link[assoc_link_id].conn,
 					override,
-					assoc_data->userspace_selectors);
+					sdata->u.mgd.userspace_selectors);
 	if (err)
 		goto err_clear;
 
@@ -9912,14 +9917,6 @@ void ieee80211_disable_rssi_reports(struct ieee80211_vif *vif)
 }
 EXPORT_SYMBOL(ieee80211_disable_rssi_reports);
 
-static void ieee80211_ml_reconf_selectors(unsigned long *userspace_selectors)
-{
-	/* these selectors are mandatory for ML reconfiguration */
-	set_bit(BSS_MEMBERSHIP_SELECTOR_SAE_H2E, userspace_selectors);
-	set_bit(BSS_MEMBERSHIP_SELECTOR_HE_PHY, userspace_selectors);
-	set_bit(BSS_MEMBERSHIP_SELECTOR_EHT_PHY, userspace_selectors);
-}
-
 void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 				      struct ieee80211_mgmt *mgmt, size_t len)
 {
@@ -9933,7 +9930,6 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 		                sdata->u.mgd.reconf.removed_links;
 	u16 link_mask, valid_links;
 	unsigned int link_id;
-	unsigned long userspace_selectors[BITS_TO_LONGS(128)] = {};
 	size_t orig_len = len;
 	u8 i, group_key_data_len;
 	u8 *pos;
@@ -10041,7 +10037,6 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 	}
 
 	ieee80211_vif_set_links(sdata, valid_links, sdata->vif.dormant_links);
-	ieee80211_ml_reconf_selectors(userspace_selectors);
 	link_mask = 0;
 	for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS; link_id++) {
 		struct cfg80211_bss *cbss = add_links_data->link[link_id].bss;
@@ -10087,7 +10082,7 @@ void ieee80211_process_ml_reconf_resp(struct ieee80211_sub_if_data *sdata,
 		link->u.mgd.conn = add_links_data->link[link_id].conn;
 		if (ieee80211_prep_channel(sdata, link, link_id, cbss,
 					   true, &link->u.mgd.conn,
-					   userspace_selectors)) {
+					   sdata->u.mgd.userspace_selectors)) {
 			link_info(link, "mlo: reconf: prep_channel failed\n");
 			goto disconnect;
 		}
@@ -10423,7 +10418,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 	 */
 	if (added_links) {
 		bool uapsd_supported;
-		unsigned long userspace_selectors[BITS_TO_LONGS(128)] = {};
 
 		data = kzalloc(sizeof(*data), GFP_KERNEL);
 		if (!data)
@@ -10433,7 +10427,6 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 		data->wmm = true;
 
 		uapsd_supported = true;
-		ieee80211_ml_reconf_selectors(userspace_selectors);
 		for (link_id = 0; link_id < IEEE80211_MLD_MAX_NUM_LINKS;
 		     link_id++) {
 			struct ieee80211_supported_band *sband;
@@ -10509,7 +10502,7 @@ int ieee80211_mgd_assoc_ml_reconf(struct ieee80211_sub_if_data *sdata,
 						     data->link[link_id].bss,
 						     true,
 						     &data->link[link_id].conn,
-						     userspace_selectors);
+						     sdata->u.mgd.userspace_selectors);
 			if (err)
 				goto err_free;
 		}

From b5c1622762f0937a66b69b7f15466c28fe85dcf1 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 11 Mar 2025 12:25:34 +0100
Subject: [PATCH 2019/2753] wifi: cfg80211: expose cfg80211_chandef_get_width()

This can be just a trivial inline, to simplify some code.
Expose it, and also use it in util.c where it wasn't
previously available.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250311122534.c5c3b4af9a74.Ib25cf60f634dc359961182113214e5cdc3504e9c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/net/cfg80211.h | 11 +++++++++++
 net/wireless/chan.c    |  5 -----
 net/wireless/util.c    |  4 ++--
 3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 73f0e75cc8147..efbd79c67be21 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -1008,6 +1008,17 @@ cfg80211_chandef_compatible(const struct cfg80211_chan_def *chandef1,
  */
 int nl80211_chan_width_to_mhz(enum nl80211_chan_width chan_width);
 
+/**
+ * cfg80211_chandef_get_width - return chandef width in MHz
+ * @c: chandef to return bandwidth for
+ * Return: channel width in MHz for the given chandef; note that it returns
+ *	80 for 80+80 configurations
+ */
+static inline int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
+{
+	return nl80211_chan_width_to_mhz(c->width);
+}
+
 /**
  * cfg80211_chandef_valid - check if a channel definition is valid
  * @chandef: the channel definition to check
diff --git a/net/wireless/chan.c b/net/wireless/chan.c
index 4cdb74a3f38c6..193734b7f9dc5 100644
--- a/net/wireless/chan.c
+++ b/net/wireless/chan.c
@@ -55,11 +55,6 @@ void cfg80211_chandef_create(struct cfg80211_chan_def *chandef,
 }
 EXPORT_SYMBOL(cfg80211_chandef_create);
 
-static int cfg80211_chandef_get_width(const struct cfg80211_chan_def *c)
-{
-	return nl80211_chan_width_to_mhz(c->width);
-}
-
 static u32 cfg80211_get_start_freq(const struct cfg80211_chan_def *chandef,
 				   u32 cf)
 {
diff --git a/net/wireless/util.c b/net/wireless/util.c
index 60157943d3519..ed868c0f7ca8e 100644
--- a/net/wireless/util.c
+++ b/net/wireless/util.c
@@ -5,7 +5,7 @@
  * Copyright 2007-2009	Johannes Berg <johannes@sipsolutions.net>
  * Copyright 2013-2014  Intel Mobile Communications GmbH
  * Copyright 2017	Intel Deutschland GmbH
- * Copyright (C) 2018-2023 Intel Corporation
+ * Copyright (C) 2018-2023, 2025 Intel Corporation
  */
 #include <linux/export.h>
 #include <linux/bitops.h>
@@ -2908,7 +2908,7 @@ bool cfg80211_radio_chandef_valid(const struct wiphy_radio *radio,
 	u32 freq, width;
 
 	freq = ieee80211_chandef_to_khz(chandef);
-	width = nl80211_chan_width_to_mhz(chandef->width);
+	width = cfg80211_chandef_get_width(chandef);
 	if (!ieee80211_radio_freq_range_valid(radio, freq, width))
 		return false;
 

From 34670beb481e5e1a40448fabd312d17a1fbf0a73 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 11 Mar 2025 12:25:35 +0100
Subject: [PATCH 2020/2753] wifi: mac80211: use cfg80211_chandef_get_width()

We can now use this helper here and simplify some code.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250311122534.0a1d24a1a763.I51a52a67587a7eee65c80b9c5cf132820ebb9dd9@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/mlme.c | 2 +-
 net/mac80211/wbrf.c | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 9bff639b52208..9c823c6d0c2fa 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -788,7 +788,7 @@ static int ieee80211_chandef_num_subchans(const struct cfg80211_chan_def *c)
 	if (c->width == NL80211_CHAN_WIDTH_80P80)
 		return 4 + 4;
 
-	return nl80211_chan_width_to_mhz(c->width) / 20;
+	return cfg80211_chandef_get_width(c) / 20;
 }
 
 static int ieee80211_chandef_num_widths(const struct cfg80211_chan_def *c)
diff --git a/net/mac80211/wbrf.c b/net/mac80211/wbrf.c
index 3a86123091373..478b34b81919b 100644
--- a/net/mac80211/wbrf.c
+++ b/net/mac80211/wbrf.c
@@ -2,6 +2,7 @@
 /*
  * Wifi Band Exclusion Interface for WLAN
  * Copyright (C) 2023 Advanced Micro Devices
+ * Copyright (C) 2025 Intel Corporation
  *
  */
 
@@ -45,7 +46,7 @@ static void get_ranges_from_chandef(struct cfg80211_chan_def *chandef,
 	u64 start_freq2, end_freq2;
 	int bandwidth;
 
-	bandwidth = nl80211_chan_width_to_mhz(chandef->width);
+	bandwidth = cfg80211_chandef_get_width(chandef);
 
 	get_chan_freq_boundary(chandef->center_freq1, bandwidth, &start_freq1, &end_freq1);
 

From 54be64fdf3ba6dbad2f5c48e466e1db43ad74bca Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Wed, 12 Mar 2025 11:31:40 +0300
Subject: [PATCH 2021/2753] wifi: iwlwifi: Fix uninitialized variable with
 __free()

Pointers declared with the __free(kfree) attribute need to be initialized
because they will be passed to kfree() on every return path.  There are
two return statement before the "cmd" pointer is initialized so this
leads to an uninitialized variable bug.

Fixes: d1e879ec600f ("wifi: iwlwifi: add iwlmld sub-driver")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/f7c17a7f-f173-43bf-bc39-316b8adde349@stanley.mountain
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/debugfs.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index c759c5c68dc04..1d4b2ad5d3889 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -556,8 +556,8 @@ iwl_dbgfs_vif_twt_setup_write(struct iwl_mld *mld, char *buf, size_t count,
 	};
 	struct ieee80211_vif *vif = data;
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_dhc_cmd *cmd __free(kfree) = NULL;
 	struct iwl_dhc_twt_operation *dhc_twt_cmd;
-	struct iwl_dhc_cmd *cmd __free(kfree);
 	u64 target_wake_time;
 	u32 twt_operation, interval_exp, interval_mantissa, min_wake_duration;
 	u8 trigger, flow_type, flow_id, protection, tenth_param;

From e51a349d2dcf1df8422dabb90b2f691dc7df6f92 Mon Sep 17 00:00:00 2001
From: Gu Bowen <gubowen5@huawei.com>
Date: Tue, 25 Feb 2025 10:28:56 +0800
Subject: [PATCH 2022/2753] mmc: atmel-mci: Add missing clk_disable_unprepare()

The error path when atmci_configure_dma() set dma fails in atmci driver
does not correctly disable the clock.
Add the missing clk_disable_unprepare() to the error path for pair with
clk_prepare_enable().

Fixes: 467e081d23e6 ("mmc: atmel-mci: use probe deferring if dma controller is not ready yet")
Signed-off-by: Gu Bowen <gubowen5@huawei.com>
Acked-by: Aubin Constans <aubin.constans@microchip.com>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/20250225022856.3452240-1-gubowen5@huawei.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/atmel-mci.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index fc360902729db..24fffc702a948 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -2499,8 +2499,10 @@ static int atmci_probe(struct platform_device *pdev)
 	/* Get MCI capabilities and set operations according to it */
 	atmci_get_cap(host);
 	ret = atmci_configure_dma(host);
-	if (ret == -EPROBE_DEFER)
+	if (ret == -EPROBE_DEFER) {
+		clk_disable_unprepare(host->mck);
 		goto err_dma_probe_defer;
+	}
 	if (ret == 0) {
 		host->prepare_data = &atmci_prepare_data_dma;
 		host->submit_data = &atmci_submit_data_dma;

From 285df995f90e3d61d97f327d34b9659d92313314 Mon Sep 17 00:00:00 2001
From: Andreas Kemnade <andreas@kemnade.info>
Date: Fri, 28 Feb 2025 15:04:20 +0100
Subject: [PATCH 2023/2753] i2c: omap: fix IRQ storms

On the GTA04A5 writing a reset command to the gyroscope causes IRQ
storms because NACK IRQs are enabled and therefore triggered but not
acked.

Sending a reset command to the gyroscope by
i2cset 1 0x69 0x14 0xb6
with an additional debug print in the ISR (not the thread) itself
causes

[ 363.353515] i2c i2c-1: ioctl, cmd=0x720, arg=0xbe801b00
[ 363.359039] omap_i2c 48072000.i2c: addr: 0x0069, len: 2, flags: 0x0, stop: 1
[ 363.366180] omap_i2c 48072000.i2c: IRQ LL (ISR = 0x1110)
[ 363.371673] omap_i2c 48072000.i2c: IRQ (ISR = 0x0010)
[ 363.376892] omap_i2c 48072000.i2c: IRQ LL (ISR = 0x0102)
[ 363.382263] omap_i2c 48072000.i2c: IRQ LL (ISR = 0x0102)
[ 363.387664] omap_i2c 48072000.i2c: IRQ LL (ISR = 0x0102)
repeating till infinity
[...]
(0x2 = NACK, 0x100 = Bus free, which is not enabled)
Apparently no other IRQ bit gets set, so this stalls.

Do not ignore enabled interrupts and make sure they are acked.
If the NACK IRQ is not needed, it should simply not enabled, but
according to the above log, caring about it is necessary unless
the Bus free IRQ is enabled and handled. The assumption that is
will always come with a ARDY IRQ, which was the idea behind
ignoring it, proves wrong.
It is true for simple reads from an unused address.

To still avoid the i2cdetect trouble which is the reason for
commit c770657bd261 ("i2c: omap: Fix standard mode false ACK readings"),
avoid doing much about NACK in omap_i2c_xfer_data() which is used
by both IRQ mode and polling mode, so also the false detection fix
is extended to polling usage and IRQ storms are avoided.

By changing this, the hardirq handler is not needed anymore to filter
stuff.

The mentioned gyro reset now just causes a -ETIMEDOUT instead of
hanging the system.

Fixes: c770657bd261 ("i2c: omap: Fix standard mode false ACK readings").
CC: stable@kernel.org
Signed-off-by: Andreas Kemnade <andreas@kemnade.info>
Tested-by: Nishanth Menon <nm@ti.com>
Reviewed-by: Aniket Limaye <a-limaye@ti.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250228140420.379498-1-andreas@kemnade.info
---
 drivers/i2c/busses/i2c-omap.c | 26 +++++++-------------------
 1 file changed, 7 insertions(+), 19 deletions(-)

diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index 92faf03d64cfb..f18c3e74b0762 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1048,23 +1048,6 @@ static int omap_i2c_transmit_data(struct omap_i2c_dev *omap, u8 num_bytes,
 	return 0;
 }
 
-static irqreturn_t
-omap_i2c_isr(int irq, void *dev_id)
-{
-	struct omap_i2c_dev *omap = dev_id;
-	irqreturn_t ret = IRQ_HANDLED;
-	u16 mask;
-	u16 stat;
-
-	stat = omap_i2c_read_reg(omap, OMAP_I2C_STAT_REG);
-	mask = omap_i2c_read_reg(omap, OMAP_I2C_IE_REG) & ~OMAP_I2C_STAT_NACK;
-
-	if (stat & mask)
-		ret = IRQ_WAKE_THREAD;
-
-	return ret;
-}
-
 static int omap_i2c_xfer_data(struct omap_i2c_dev *omap)
 {
 	u16 bits;
@@ -1095,8 +1078,13 @@ static int omap_i2c_xfer_data(struct omap_i2c_dev *omap)
 		}
 
 		if (stat & OMAP_I2C_STAT_NACK) {
-			err |= OMAP_I2C_STAT_NACK;
+			omap->cmd_err |= OMAP_I2C_STAT_NACK;
 			omap_i2c_ack_stat(omap, OMAP_I2C_STAT_NACK);
+
+			if (!(stat & ~OMAP_I2C_STAT_NACK)) {
+				err = -EAGAIN;
+				break;
+			}
 		}
 
 		if (stat & OMAP_I2C_STAT_AL) {
@@ -1472,7 +1460,7 @@ omap_i2c_probe(struct platform_device *pdev)
 				IRQF_NO_SUSPEND, pdev->name, omap);
 	else
 		r = devm_request_threaded_irq(&pdev->dev, omap->irq,
-				omap_i2c_isr, omap_i2c_isr_thread,
+				NULL, omap_i2c_isr_thread,
 				IRQF_NO_SUSPEND | IRQF_ONESHOT,
 				pdev->name, omap);
 

From 9b5463f349d019a261f1e80803447efca3126151 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 3 Mar 2025 20:53:08 +0100
Subject: [PATCH 2024/2753] i2c: ali1535: Fix an error handling path in
 ali1535_probe()

If i2c_add_adapter() fails, the request_region() call in ali1535_setup()
must be undone by a corresponding release_region() call, as done in the
remove function.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/0daf63d7a2ce74c02e2664ba805bbfadab7d25e5.1741031571.git.christophe.jaillet@wanadoo.fr
---
 drivers/i2c/busses/i2c-ali1535.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-ali1535.c b/drivers/i2c/busses/i2c-ali1535.c
index 544c94e86b896..1eac358380405 100644
--- a/drivers/i2c/busses/i2c-ali1535.c
+++ b/drivers/i2c/busses/i2c-ali1535.c
@@ -485,6 +485,8 @@ MODULE_DEVICE_TABLE(pci, ali1535_ids);
 
 static int ali1535_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (ali1535_setup(dev)) {
 		dev_warn(&dev->dev,
 			"ALI1535 not detected, module not inserted.\n");
@@ -496,7 +498,15 @@ static int ali1535_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	snprintf(ali1535_adapter.name, sizeof(ali1535_adapter.name),
 		"SMBus ALI1535 adapter at %04x", ali1535_offset);
-	return i2c_add_adapter(&ali1535_adapter);
+	ret = i2c_add_adapter(&ali1535_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(ali1535_smba, ALI1535_SMB_IOSIZE);
+	return ret;
 }
 
 static void ali1535_remove(struct pci_dev *dev)

From 6e55caaf30c88209d097e575a169b1dface1ab69 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 3 Mar 2025 20:58:06 +0100
Subject: [PATCH 2025/2753] i2c: ali15x3: Fix an error handling path in
 ali15x3_probe()

If i2c_add_adapter() fails, the request_region() call in ali15x3_setup()
must be undone by a corresponding release_region() call, as done in the
remove function.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/9b2090cbcc02659f425188ea05f2e02745c4e67b.1741031878.git.christophe.jaillet@wanadoo.fr
---
 drivers/i2c/busses/i2c-ali15x3.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-ali15x3.c b/drivers/i2c/busses/i2c-ali15x3.c
index 4761c72081022..418d11266671e 100644
--- a/drivers/i2c/busses/i2c-ali15x3.c
+++ b/drivers/i2c/busses/i2c-ali15x3.c
@@ -472,6 +472,8 @@ MODULE_DEVICE_TABLE (pci, ali15x3_ids);
 
 static int ali15x3_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (ali15x3_setup(dev)) {
 		dev_err(&dev->dev,
 			"ALI15X3 not detected, module not inserted.\n");
@@ -483,7 +485,15 @@ static int ali15x3_probe(struct pci_dev *dev, const struct pci_device_id *id)
 
 	snprintf(ali15x3_adapter.name, sizeof(ali15x3_adapter.name),
 		"SMBus ALI15X3 adapter at %04x", ali15x3_smba);
-	return i2c_add_adapter(&ali15x3_adapter);
+	ret = i2c_add_adapter(&ali15x3_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(ali15x3_smba, ALI15X3_SMB_IOSIZE);
+	return ret;
 }
 
 static void ali15x3_remove(struct pci_dev *dev)

From 2b22459792fcb4def9f0936d64575ac11a95a58d Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Mon, 3 Mar 2025 21:26:54 +0100
Subject: [PATCH 2026/2753] i2c: sis630: Fix an error handling path in
 sis630_probe()

If i2c_add_adapter() fails, the request_region() call in sis630_setup()
must be undone by a corresponding release_region() call, as done in the
remove function.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/3d607601f2c38e896b10207963c6ab499ca5c307.1741033587.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
---
 drivers/i2c/busses/i2c-sis630.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/i2c/busses/i2c-sis630.c b/drivers/i2c/busses/i2c-sis630.c
index 3505cf29cedda..a19c3d251804d 100644
--- a/drivers/i2c/busses/i2c-sis630.c
+++ b/drivers/i2c/busses/i2c-sis630.c
@@ -509,6 +509,8 @@ MODULE_DEVICE_TABLE(pci, sis630_ids);
 
 static int sis630_probe(struct pci_dev *dev, const struct pci_device_id *id)
 {
+	int ret;
+
 	if (sis630_setup(dev)) {
 		dev_err(&dev->dev,
 			"SIS630 compatible bus not detected, "
@@ -522,7 +524,15 @@ static int sis630_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	snprintf(sis630_adapter.name, sizeof(sis630_adapter.name),
 		 "SMBus SIS630 adapter at %04x", smbus_base + SMB_STS);
 
-	return i2c_add_adapter(&sis630_adapter);
+	ret = i2c_add_adapter(&sis630_adapter);
+	if (ret)
+		goto release_region;
+
+	return 0;
+
+release_region:
+	release_region(smbus_base + SMB_STS, SIS630_SMB_IOREGION);
+	return ret;
 }
 
 static void sis630_remove(struct pci_dev *dev)

From 81c0db302a674f8004ed805393d17fd76f552e83 Mon Sep 17 00:00:00 2001
From: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Date: Mon, 10 Mar 2025 22:16:36 -0700
Subject: [PATCH 2027/2753] RDMA/bnxt_re: Avoid clearing VLAN_ID mask in modify
 qp path

Driver is always clearing the mask that sets the VLAN ID/Service Level
in the adapter. Recent change for supporting multiple traffic class
exposed this issue.

Allow setting SL and VLAN_ID while QP is moved from INIT to RTR state.

Fixes: 1ac5a4047975 ("RDMA/bnxt_re: Add bnxt_re RoCE driver")
Fixes: c64b16a37b6d ("RDMA/bnxt_re: Support different traffic class")
Signed-off-by: Saravanan Vajravel <saravanan.vajravel@broadcom.com>
Signed-off-by: Selvin Xavier <selvin.xavier@broadcom.com>
Link: https://patch.msgid.link/1741670196-2919-1-git-send-email-selvin.xavier@broadcom.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/qplib_fp.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
index 5336f74297f81..457eecb99f969 100644
--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c
+++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c
@@ -1217,8 +1217,6 @@ static void __modify_flags_from_init_state(struct bnxt_qplib_qp *qp)
 			qp->path_mtu =
 				CMDQ_MODIFY_QP_PATH_MTU_MTU_2048;
 		}
-		qp->modify_flags &=
-			~CMDQ_MODIFY_QP_MODIFY_MASK_VLAN_ID;
 		/* Bono FW require the max_dest_rd_atomic to be >= 1 */
 		if (qp->max_dest_rd_atomic < 1)
 			qp->max_dest_rd_atomic = 1;

From 9bce6b5f8987678b9c6c1fe433af6b5fe41feadc Mon Sep 17 00:00:00 2001
From: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Date: Tue, 11 Mar 2025 19:43:59 +0900
Subject: [PATCH 2028/2753] block: change blk_mq_add_to_batch() third argument
 type to bool

Commit 1f47ed294a2b ("block: cleanup and fix batch completion adding
conditions") modified the evaluation criteria for the third argument,
'ioerror', in the blk_mq_add_to_batch() function. Initially, the
function had checked if 'ioerror' equals zero. Following the commit, it
started checking for negative error values, with the presumption that
such values, for instance -EIO, would be passed in.

However, blk_mq_add_to_batch() callers do not pass negative error
values. Instead, they pass status codes defined in various ways:

- NVMe PCI and Apple drivers pass NVMe status code
- virtio_blk driver passes the virtblk request header status byte
- null_blk driver passes blk_status_t

These codes are either zero or positive, therefore the revised check
fails to function as intended. Specifically, with the NVMe PCI driver,
this modification led to the failure of the blktests test case nvme/039.
In this test scenario, errors are artificially injected to the NVMe
driver, resulting in positive NVMe status codes passed to
blk_mq_add_to_batch(), which unexpectedly processes the failed I/O in a
batch. Hence the failure.

To correct the ioerror check within blk_mq_add_to_batch(), make all
callers to uniformly pass the argument as boolean. Modify the callers to
check their specific status codes and pass the boolean value 'is_error'.
Also describe the arguments of blK_mq_add_to_batch as kerneldoc.

Fixes: 1f47ed294a2b ("block: cleanup and fix batch completion adding conditions")
Signed-off-by: Shin'ichiro Kawasaki <shinichiro.kawasaki@wdc.com>
Link: https://lore.kernel.org/r/20250311104359.1767728-3-shinichiro.kawasaki@wdc.com
[axboe: fold in documentation update]
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 drivers/block/null_blk/main.c |  4 ++--
 drivers/block/virtio_blk.c    |  5 +++--
 drivers/nvme/host/apple.c     |  3 ++-
 drivers/nvme/host/pci.c       |  5 +++--
 include/linux/blk-mq.h        | 16 ++++++++++++----
 5 files changed, 22 insertions(+), 11 deletions(-)

diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
index d94ef37480bd4..fdc7a0b2af109 100644
--- a/drivers/block/null_blk/main.c
+++ b/drivers/block/null_blk/main.c
@@ -1549,8 +1549,8 @@ static int null_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 		cmd = blk_mq_rq_to_pdu(req);
 		cmd->error = null_process_cmd(cmd, req_op(req), blk_rq_pos(req),
 						blk_rq_sectors(req));
-		if (!blk_mq_add_to_batch(req, iob, (__force int) cmd->error,
-					blk_mq_end_request_batch))
+		if (!blk_mq_add_to_batch(req, iob, cmd->error != BLK_STS_OK,
+					 blk_mq_end_request_batch))
 			blk_mq_end_request(req, cmd->error);
 		nr++;
 	}
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index a4af39fc7ea28..286cab5e53684 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -1207,11 +1207,12 @@ static int virtblk_poll(struct blk_mq_hw_ctx *hctx, struct io_comp_batch *iob)
 
 	while ((vbr = virtqueue_get_buf(vq->vq, &len)) != NULL) {
 		struct request *req = blk_mq_rq_from_pdu(vbr);
+		u8 status = virtblk_vbr_status(vbr);
 
 		found++;
 		if (!blk_mq_complete_request_remote(req) &&
-		    !blk_mq_add_to_batch(req, iob, virtblk_vbr_status(vbr),
-						virtblk_complete_batch))
+		    !blk_mq_add_to_batch(req, iob, status != VIRTIO_BLK_S_OK,
+					 virtblk_complete_batch))
 			virtblk_request_done(req);
 	}
 
diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
index a060f69558e76..8971aca41e63d 100644
--- a/drivers/nvme/host/apple.c
+++ b/drivers/nvme/host/apple.c
@@ -599,7 +599,8 @@ static inline void apple_nvme_handle_cqe(struct apple_nvme_queue *q,
 	}
 
 	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
-	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
+	    !blk_mq_add_to_batch(req, iob,
+				 nvme_req(req)->status != NVME_SC_SUCCESS,
 				 apple_nvme_complete_batch))
 		apple_nvme_complete_rq(req);
 }
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 640590b217282..75de86e235ad7 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -1130,8 +1130,9 @@ static inline void nvme_handle_cqe(struct nvme_queue *nvmeq,
 
 	trace_nvme_sq(req, cqe->sq_head, nvmeq->sq_tail);
 	if (!nvme_try_complete_req(req, cqe->status, cqe->result) &&
-	    !blk_mq_add_to_batch(req, iob, nvme_req(req)->status,
-					nvme_pci_complete_batch))
+	    !blk_mq_add_to_batch(req, iob,
+				 nvme_req(req)->status != NVME_SC_SUCCESS,
+				 nvme_pci_complete_batch))
 		nvme_pci_complete_rq(req);
 }
 
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 71f4f0cc3dac6..aba9c24486aad 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -852,12 +852,20 @@ static inline bool blk_mq_is_reserved_rq(struct request *rq)
 	return rq->rq_flags & RQF_RESV;
 }
 
-/*
+/**
+ * blk_mq_add_to_batch() - add a request to the completion batch
+ * @req: The request to add to batch
+ * @iob: The batch to add the request
+ * @is_error: Specify true if the request failed with an error
+ * @complete: The completaion handler for the request
+ *
  * Batched completions only work when there is no I/O error and no special
  * ->end_io handler.
+ *
+ * Return: true when the request was added to the batch, otherwise false
  */
 static inline bool blk_mq_add_to_batch(struct request *req,
-				       struct io_comp_batch *iob, int ioerror,
+				       struct io_comp_batch *iob, bool is_error,
 				       void (*complete)(struct io_comp_batch *))
 {
 	/*
@@ -865,7 +873,7 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 	 * 1) No batch container
 	 * 2) Has scheduler data attached
 	 * 3) Not a passthrough request and end_io set
-	 * 4) Not a passthrough request and an ioerror
+	 * 4) Not a passthrough request and failed with an error
 	 */
 	if (!iob)
 		return false;
@@ -874,7 +882,7 @@ static inline bool blk_mq_add_to_batch(struct request *req,
 	if (!blk_rq_is_passthrough(req)) {
 		if (req->end_io)
 			return false;
-		if (ioerror < 0)
+		if (is_error)
 			return false;
 	}
 

From d653bfeb07ebb3499c403404c21ac58a16531607 Mon Sep 17 00:00:00 2001
From: Kohei Enju <enjuk@amazon.com>
Date: Sun, 9 Mar 2025 17:07:38 +0900
Subject: [PATCH 2029/2753] netfilter: nf_conncount: Fully initialize struct
 nf_conncount_tuple in insert_tree()

Since commit b36e4523d4d5 ("netfilter: nf_conncount: fix garbage
collection confirm race"), `cpu` and `jiffies32` were introduced to
the struct nf_conncount_tuple.

The commit made nf_conncount_add() initialize `conn->cpu` and
`conn->jiffies32` when allocating the struct.
In contrast, count_tree() was not changed to initialize them.

By commit 34848d5c896e ("netfilter: nf_conncount: Split insert and
traversal"), count_tree() was split and the relevant allocation
code now resides in insert_tree().
Initialize `conn->cpu` and `conn->jiffies32` in insert_tree().

BUG: KMSAN: uninit-value in find_or_evict net/netfilter/nf_conncount.c:117 [inline]
BUG: KMSAN: uninit-value in __nf_conncount_add+0xd9c/0x2850 net/netfilter/nf_conncount.c:143
 find_or_evict net/netfilter/nf_conncount.c:117 [inline]
 __nf_conncount_add+0xd9c/0x2850 net/netfilter/nf_conncount.c:143
 count_tree net/netfilter/nf_conncount.c:438 [inline]
 nf_conncount_count+0x82f/0x1e80 net/netfilter/nf_conncount.c:521
 connlimit_mt+0x7f6/0xbd0 net/netfilter/xt_connlimit.c:72
 __nft_match_eval net/netfilter/nft_compat.c:403 [inline]
 nft_match_eval+0x1a5/0x300 net/netfilter/nft_compat.c:433
 expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
 nft_do_chain+0x426/0x2290 net/netfilter/nf_tables_core.c:288
 nft_do_chain_ipv4+0x1a5/0x230 net/netfilter/nft_chain_filter.c:23
 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
 nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
 nf_hook_slow_list+0x24d/0x860 net/netfilter/core.c:663
 NF_HOOK_LIST include/linux/netfilter.h:350 [inline]
 ip_sublist_rcv+0x17b7/0x17f0 net/ipv4/ip_input.c:633
 ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:669
 __netif_receive_skb_list_ptype net/core/dev.c:5936 [inline]
 __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5983
 __netif_receive_skb_list net/core/dev.c:6035 [inline]
 netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:6126
 netif_receive_skb_list+0x5a/0x460 net/core/dev.c:6178
 xdp_recv_frames net/bpf/test_run.c:280 [inline]
 xdp_test_run_batch net/bpf/test_run.c:361 [inline]
 bpf_test_run_xdp_live+0x2e86/0x3480 net/bpf/test_run.c:390
 bpf_prog_test_run_xdp+0xf1d/0x1ae0 net/bpf/test_run.c:1316
 bpf_prog_test_run+0x5e5/0xa30 kernel/bpf/syscall.c:4407
 __sys_bpf+0x6aa/0xd90 kernel/bpf/syscall.c:5813
 __do_sys_bpf kernel/bpf/syscall.c:5902 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5900 [inline]
 __ia32_sys_bpf+0xa0/0xe0 kernel/bpf/syscall.c:5900
 ia32_sys_call+0x394d/0x4180 arch/x86/include/generated/asm/syscalls_32.h:358
 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline]
 __do_fast_syscall_32+0xb0/0x110 arch/x86/entry/common.c:387
 do_fast_syscall_32+0x38/0x80 arch/x86/entry/common.c:412
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:450
 entry_SYSENTER_compat_after_hwframe+0x84/0x8e

Uninit was created at:
 slab_post_alloc_hook mm/slub.c:4121 [inline]
 slab_alloc_node mm/slub.c:4164 [inline]
 kmem_cache_alloc_noprof+0x915/0xe10 mm/slub.c:4171
 insert_tree net/netfilter/nf_conncount.c:372 [inline]
 count_tree net/netfilter/nf_conncount.c:450 [inline]
 nf_conncount_count+0x1415/0x1e80 net/netfilter/nf_conncount.c:521
 connlimit_mt+0x7f6/0xbd0 net/netfilter/xt_connlimit.c:72
 __nft_match_eval net/netfilter/nft_compat.c:403 [inline]
 nft_match_eval+0x1a5/0x300 net/netfilter/nft_compat.c:433
 expr_call_ops_eval net/netfilter/nf_tables_core.c:240 [inline]
 nft_do_chain+0x426/0x2290 net/netfilter/nf_tables_core.c:288
 nft_do_chain_ipv4+0x1a5/0x230 net/netfilter/nft_chain_filter.c:23
 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
 nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
 nf_hook_slow_list+0x24d/0x860 net/netfilter/core.c:663
 NF_HOOK_LIST include/linux/netfilter.h:350 [inline]
 ip_sublist_rcv+0x17b7/0x17f0 net/ipv4/ip_input.c:633
 ip_list_rcv+0x9ef/0xa40 net/ipv4/ip_input.c:669
 __netif_receive_skb_list_ptype net/core/dev.c:5936 [inline]
 __netif_receive_skb_list_core+0x15c5/0x1670 net/core/dev.c:5983
 __netif_receive_skb_list net/core/dev.c:6035 [inline]
 netif_receive_skb_list_internal+0x1085/0x1700 net/core/dev.c:6126
 netif_receive_skb_list+0x5a/0x460 net/core/dev.c:6178
 xdp_recv_frames net/bpf/test_run.c:280 [inline]
 xdp_test_run_batch net/bpf/test_run.c:361 [inline]
 bpf_test_run_xdp_live+0x2e86/0x3480 net/bpf/test_run.c:390
 bpf_prog_test_run_xdp+0xf1d/0x1ae0 net/bpf/test_run.c:1316
 bpf_prog_test_run+0x5e5/0xa30 kernel/bpf/syscall.c:4407
 __sys_bpf+0x6aa/0xd90 kernel/bpf/syscall.c:5813
 __do_sys_bpf kernel/bpf/syscall.c:5902 [inline]
 __se_sys_bpf kernel/bpf/syscall.c:5900 [inline]
 __ia32_sys_bpf+0xa0/0xe0 kernel/bpf/syscall.c:5900
 ia32_sys_call+0x394d/0x4180 arch/x86/include/generated/asm/syscalls_32.h:358
 do_syscall_32_irqs_on arch/x86/entry/common.c:165 [inline]
 __do_fast_syscall_32+0xb0/0x110 arch/x86/entry/common.c:387
 do_fast_syscall_32+0x38/0x80 arch/x86/entry/common.c:412
 do_SYSENTER_32+0x1f/0x30 arch/x86/entry/common.c:450
 entry_SYSENTER_compat_after_hwframe+0x84/0x8e

Reported-by: syzbot+83fed965338b573115f7@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=83fed965338b573115f7
Fixes: b36e4523d4d5 ("netfilter: nf_conncount: fix garbage collection confirm race")
Signed-off-by: Kohei Enju <enjuk@amazon.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conncount.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
index ebe38ed2e6f4f..913ede2f57f9a 100644
--- a/net/netfilter/nf_conncount.c
+++ b/net/netfilter/nf_conncount.c
@@ -377,6 +377,8 @@ insert_tree(struct net *net,
 
 	conn->tuple = *tuple;
 	conn->zone = *zone;
+	conn->cpu = raw_smp_processor_id();
+	conn->jiffies32 = (u32)jiffies;
 	memcpy(rbconn->key, key, sizeof(u32) * data->keylen);
 
 	nf_conncount_list_init(&rbconn->list);

From c21b02fd9cbf15aed6e32c89e0fd70070281e3d1 Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 11 Mar 2025 12:52:45 +0100
Subject: [PATCH 2030/2753] selftests: netfilter: skip br_netfilter queue tests
 if kernel is tainted

These scripts fail if the kernel is tainted which leads to wrong test
failure reports in CI environments when an unrelated test triggers some
splat.

Check taint state at start of script and SKIP if its already dodgy.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 tools/testing/selftests/net/netfilter/br_netfilter.sh      | 7 +++++++
 .../testing/selftests/net/netfilter/br_netfilter_queue.sh  | 7 +++++++
 tools/testing/selftests/net/netfilter/nft_queue.sh         | 1 +
 3 files changed, 15 insertions(+)

diff --git a/tools/testing/selftests/net/netfilter/br_netfilter.sh b/tools/testing/selftests/net/netfilter/br_netfilter.sh
index c28379a965d83..1559ba275105e 100755
--- a/tools/testing/selftests/net/netfilter/br_netfilter.sh
+++ b/tools/testing/selftests/net/netfilter/br_netfilter.sh
@@ -13,6 +13,12 @@ source lib.sh
 
 checktool "nft --version" "run test without nft tool"
 
+read t < /proc/sys/kernel/tainted
+if [ "$t" -ne 0 ];then
+	echo SKIP: kernel is tainted
+	exit $ksft_skip
+fi
+
 cleanup() {
 	cleanup_all_ns
 }
@@ -165,6 +171,7 @@ if [ "$t" -eq 0 ];then
 	echo PASS: kernel not tainted
 else
 	echo ERROR: kernel is tainted
+	dmesg
 	ret=1
 fi
 
diff --git a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
index 6a764d70ab06f..4788641717d93 100755
--- a/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
+++ b/tools/testing/selftests/net/netfilter/br_netfilter_queue.sh
@@ -4,6 +4,12 @@ source lib.sh
 
 checktool "nft --version" "run test without nft tool"
 
+read t < /proc/sys/kernel/tainted
+if [ "$t" -ne 0 ];then
+	echo SKIP: kernel is tainted
+	exit $ksft_skip
+fi
+
 cleanup() {
 	cleanup_all_ns
 }
@@ -72,6 +78,7 @@ if [ "$t" -eq 0 ];then
 	echo PASS: kernel not tainted
 else
 	echo ERROR: kernel is tainted
+	dmesg
 	exit 1
 fi
 
diff --git a/tools/testing/selftests/net/netfilter/nft_queue.sh b/tools/testing/selftests/net/netfilter/nft_queue.sh
index 785e3875a6da4..784d1b46912b0 100755
--- a/tools/testing/selftests/net/netfilter/nft_queue.sh
+++ b/tools/testing/selftests/net/netfilter/nft_queue.sh
@@ -593,6 +593,7 @@ EOF
 		echo "PASS: queue program exiting while packets queued"
 	else
 		echo "TAINT: queue program exiting while packets queued"
+		dmesg
 		ret=1
 	fi
 }

From 80b78c39eb86e6b55f56363b709eb817527da5aa Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 10 Mar 2025 10:45:53 +0300
Subject: [PATCH 2031/2753] ipvs: prevent integer overflow in
 do_ip_vs_get_ctl()

The get->num_services variable is an unsigned int which is controlled by
the user.  The struct_size() function ensures that the size calculation
does not overflow an unsigned long, however, we are saving the result to
an int so the calculation can overflow.

Both "len" and "get->num_services" come from the user.  This check is
just a sanity check to help the user and ensure they are using the API
correctly.  An integer overflow here is not a big deal.  This has no
security impact.

Save the result from struct_size() type size_t to fix this integer
overflow bug.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Acked-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_ctl.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 7d13110ce1882..0633276d96bfb 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3091,12 +3091,12 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	case IP_VS_SO_GET_SERVICES:
 	{
 		struct ip_vs_get_services *get;
-		int size;
+		size_t size;
 
 		get = (struct ip_vs_get_services *)arg;
 		size = struct_size(get, entrytable, get->num_services);
 		if (*len != size) {
-			pr_err("length: %u != %u\n", *len, size);
+			pr_err("length: %u != %zu\n", *len, size);
 			ret = -EINVAL;
 			goto out;
 		}
@@ -3132,12 +3132,12 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
 	case IP_VS_SO_GET_DESTS:
 	{
 		struct ip_vs_get_dests *get;
-		int size;
+		size_t size;
 
 		get = (struct ip_vs_get_dests *)arg;
 		size = struct_size(get, entrytable, get->num_dests);
 		if (*len != size) {
-			pr_err("length: %u != %u\n", *len, size);
+			pr_err("length: %u != %zu\n", *len, size);
 			ret = -EINVAL;
 			goto out;
 		}

From b11a74ac4f545626d0dc95a8ca8c41df90532bf3 Mon Sep 17 00:00:00 2001
From: Navon John Lukose <navonjohnlukose@gmail.com>
Date: Sat, 8 Mar 2025 03:03:19 +0530
Subject: [PATCH 2032/2753] ALSA: hda/realtek: Add mute LED quirk for HP
 Pavilion x360 14-dy1xxx

Add a fixup to enable the mute LED on HP Pavilion x360 Convertible
14-dy1xxx with ALC295 codec. The appropriate coefficient index and bits
were identified through a brute-force method, as detailed in
https://bbs.archlinux.org/viewtopic.php?pid=2079504#p2079504.

Signed-off-by: Navon John Lukose <navonjohnlukose@gmail.com>
Link: https://patch.msgid.link/20250307213319.35507-1-navonjohnlukose@gmail.com
Signed-off-by: Takashi Iwai <tiwai@suse.de>
---
 sound/pci/hda/patch_realtek.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index d2a1f836dbbf7..a84857a3c2bfb 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4790,6 +4790,21 @@ static void alc236_fixup_hp_coef_micmute_led(struct hda_codec *codec,
 	}
 }
 
+static void alc295_fixup_hp_mute_led_coefbit11(struct hda_codec *codec,
+				const struct hda_fixup *fix, int action)
+{
+	struct alc_spec *spec = codec->spec;
+
+	if (action == HDA_FIXUP_ACT_PRE_PROBE) {
+		spec->mute_led_polarity = 0;
+		spec->mute_led_coef.idx = 0xb;
+		spec->mute_led_coef.mask = 3 << 3;
+		spec->mute_led_coef.on = 1 << 3;
+		spec->mute_led_coef.off = 1 << 4;
+		snd_hda_gen_add_mute_led_cdev(codec, coef_mute_led_set);
+	}
+}
+
 static void alc285_fixup_hp_mute_led(struct hda_codec *codec,
 				const struct hda_fixup *fix, int action)
 {
@@ -7656,6 +7671,7 @@ enum {
 	ALC290_FIXUP_MONO_SPEAKERS_HSJACK,
 	ALC290_FIXUP_SUBWOOFER,
 	ALC290_FIXUP_SUBWOOFER_HSJACK,
+	ALC295_FIXUP_HP_MUTE_LED_COEFBIT11,
 	ALC269_FIXUP_THINKPAD_ACPI,
 	ALC269_FIXUP_LENOVO_XPAD_ACPI,
 	ALC269_FIXUP_DMIC_THINKPAD_ACPI,
@@ -9401,6 +9417,10 @@ static const struct hda_fixup alc269_fixups[] = {
 		.chained = true,
 		.chain_id = ALC283_FIXUP_INT_MIC,
 	},
+	[ALC295_FIXUP_HP_MUTE_LED_COEFBIT11] = {
+		.type = HDA_FIXUP_FUNC,
+		.v.func = alc295_fixup_hp_mute_led_coefbit11,
+	},
 	[ALC298_FIXUP_SAMSUNG_AMP] = {
 		.type = HDA_FIXUP_FUNC,
 		.v.func = alc298_fixup_samsung_amp,
@@ -10451,6 +10471,7 @@ static const struct hda_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK(0x103c, 0x84e7, "HP Pavilion 15", ALC269_FIXUP_HP_MUTE_LED_MIC3),
 	SND_PCI_QUIRK(0x103c, 0x8519, "HP Spectre x360 15-df0xxx", ALC285_FIXUP_HP_SPECTRE_X360),
 	SND_PCI_QUIRK(0x103c, 0x8537, "HP ProBook 440 G6", ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF),
+	SND_PCI_QUIRK(0x103c, 0x85c6, "HP Pavilion x360 Convertible 14-dy1xxx", ALC295_FIXUP_HP_MUTE_LED_COEFBIT11),
 	SND_PCI_QUIRK(0x103c, 0x85de, "HP Envy x360 13-ar0xxx", ALC285_FIXUP_HP_ENVY_X360),
 	SND_PCI_QUIRK(0x103c, 0x860f, "HP ZBook 15 G6", ALC285_FIXUP_HP_GPIO_AMP_INIT),
 	SND_PCI_QUIRK(0x103c, 0x861f, "HP Elite Dragonfly G1", ALC285_FIXUP_HP_GPIO_AMP_INIT),

From d9e7c172a7f247f7ef0b151fa8c8f044b6a2a070 Mon Sep 17 00:00:00 2001
From: Hans Verkuil <hverkuil@xs4all.nl>
Date: Mon, 24 Feb 2025 15:40:58 +0100
Subject: [PATCH 2033/2753] media: rtl2832_sdr: assign vb2 lock before
 vb2_queue_init

Commit c780d01cf1a6 ("media: vb2: vb2_core_queue_init(): sanity check lock
and wait_prepare/finish") added a sanity check to ensure that if there are
no wait_prepare/finish callbacks set by the driver, then the vb2_queue lock
must be set, since otherwise the vb2 core cannot do correct locking.

The rtl2832_sdr.c triggered this warning: it turns out that while the
driver does set this lock, it sets it too late. So move it up to before
the vb2_queue_init() call.

Reported-by: Arthur Marsh <arthur.marsh@internode.on.net>
Closes: https://lore.kernel.org/linux-media/20241211042355.8479-1-user@am64/
Fixes: 8fcd2795d22a ("media: rtl2832_sdr: drop vb2_ops_wait_prepare/finish")
Cc: stable@vger.kernel.org
Reviewed-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
---
 drivers/media/dvb-frontends/rtl2832_sdr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/media/dvb-frontends/rtl2832_sdr.c b/drivers/media/dvb-frontends/rtl2832_sdr.c
index 05254d8717db8..0357624968f1b 100644
--- a/drivers/media/dvb-frontends/rtl2832_sdr.c
+++ b/drivers/media/dvb-frontends/rtl2832_sdr.c
@@ -1363,6 +1363,7 @@ static int rtl2832_sdr_probe(struct platform_device *pdev)
 	dev->vb_queue.ops = &rtl2832_sdr_vb2_ops;
 	dev->vb_queue.mem_ops = &vb2_vmalloc_memops;
 	dev->vb_queue.timestamp_flags = V4L2_BUF_FLAG_TIMESTAMP_MONOTONIC;
+	dev->vb_queue.lock = &dev->vb_queue_lock;
 	ret = vb2_queue_init(&dev->vb_queue);
 	if (ret) {
 		dev_err(&pdev->dev, "Could not initialize vb2 queue\n");
@@ -1421,7 +1422,6 @@ static int rtl2832_sdr_probe(struct platform_device *pdev)
 	/* Init video_device structure */
 	dev->vdev = rtl2832_sdr_template;
 	dev->vdev.queue = &dev->vb_queue;
-	dev->vdev.queue->lock = &dev->vb_queue_lock;
 	video_set_drvdata(&dev->vdev, dev);
 
 	/* Register the v4l2_device structure */

From 658fb7fe8e7f4014ea17a4da0e0c1d9bc319fa35 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Wed, 5 Mar 2025 18:27:32 +0100
Subject: [PATCH 2034/2753] ASoC: cs42l43: convert to SYSTEM_SLEEP_PM_OPS

The custom suspend function causes a build warning when CONFIG_PM_SLEEP
is disabled:

sound/soc/codecs/cs42l43.c:2405:12: error: unused function 'cs42l43_codec_runtime_force_suspend' [-Werror,-Wunused-function]

Change SET_SYSTEM_SLEEP_PM_OPS() to the newer SYSTEM_SLEEP_PM_OPS(),
to avoid this.

Fixes: 164b7dd4546b ("ASoC: cs42l43: Add jack delay debounce after suspend")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Maciej Strozek <mstrozek@opensource.cirrus.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://patch.msgid.link/20250305172738.3437513-1-arnd@kernel.org
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/cs42l43.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/cs42l43.c b/sound/soc/codecs/cs42l43.c
index d307b56a7f38e..ea84ac64c775e 100644
--- a/sound/soc/codecs/cs42l43.c
+++ b/sound/soc/codecs/cs42l43.c
@@ -2417,7 +2417,7 @@ static int cs42l43_codec_runtime_force_suspend(struct device *dev)
 
 static const struct dev_pm_ops cs42l43_codec_pm_ops = {
 	RUNTIME_PM_OPS(NULL, cs42l43_codec_runtime_resume, NULL)
-	SET_SYSTEM_SLEEP_PM_OPS(cs42l43_codec_runtime_force_suspend, pm_runtime_force_resume)
+	SYSTEM_SLEEP_PM_OPS(cs42l43_codec_runtime_force_suspend, pm_runtime_force_resume)
 };
 
 static const struct platform_device_id cs42l43_codec_id_table[] = {

From 18e0885bd2ca738407036434418a26a58394a60e Mon Sep 17 00:00:00 2001
From: Boon Khai Ng <boon.khai.ng@intel.com>
Date: Wed, 12 Mar 2025 11:05:44 +0800
Subject: [PATCH 2035/2753] USB: serial: ftdi_sio: add support for Altera USB
 Blaster 3

The Altera USB Blaster 3, available as both a cable and an on-board
solution, is primarily used for programming and debugging FPGAs.

It interfaces with host software such as Quartus Programmer,
System Console, SignalTap, and Nios Debugger. The device utilizes
either an FT2232 or FT4232 chip.

Enabling the support for various configurations of the on-board
USB Blaster 3 by including the appropriate VID/PID pairs,
allowing it to function as a serial device via ftdi_sio.

Note that this check-in does not include support for the
cable solution, as it does not support UART functionality.
The supported configurations are determined by the
hardware design and include:

1) PID 0x6022, FT2232, 1 JTAG port (Port A) + Port B as UART
2) PID 0x6025, FT4232, 1 JTAG port (Port A) + Port C as UART
3) PID 0x6026, FT4232, 1 JTAG port (Port A) + Port C, D as UART
4) PID 0x6029, FT4232, 1 JTAG port (Port B) + Port C as UART
5) PID 0x602a, FT4232, 1 JTAG port (Port B) + Port C, D as UART
6) PID 0x602c, FT4232, 1 JTAG port (Port A) + Port B as UART
7) PID 0x602d, FT4232, 1 JTAG port (Port A) + Port B, C as UART
8) PID 0x602e, FT4232, 1 JTAG port (Port A) + Port B, C, D as UART

These configurations allow for flexibility in how the USB Blaster 3 is
used, depending on the specific needs of the hardware design.

Signed-off-by: Boon Khai Ng <boon.khai.ng@intel.com>
Cc: stable@vger.kernel.org
Signed-off-by: Johan Hovold <johan@kernel.org>
---
 drivers/usb/serial/ftdi_sio.c     | 14 ++++++++++++++
 drivers/usb/serial/ftdi_sio_ids.h | 13 +++++++++++++
 2 files changed, 27 insertions(+)

diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index e07c5e3eb18c0..9b34e23b70919 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -1079,6 +1079,20 @@ static const struct usb_device_id id_table_combined[] = {
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	/* GMC devices */
 	{ USB_DEVICE(GMC_VID, GMC_Z216C_PID) },
+	/* Altera USB Blaster 3 */
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6022_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6025_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6026_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6026_PID, 3) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_6029_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602A_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602A_PID, 3) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602C_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602D_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602D_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 1) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 2) },
+	{ USB_DEVICE_INTERFACE_NUMBER(ALTERA_VID, ALTERA_UB3_602E_PID, 3) },
 	{ }					/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 5ee60ba2a73cd..52be47d684ea6 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1612,3 +1612,16 @@
  */
 #define GMC_VID				0x1cd7
 #define GMC_Z216C_PID			0x0217 /* GMC Z216C Adapter IR-USB */
+
+/*
+ *  Altera USB Blaster 3 (http://www.altera.com).
+ */
+#define ALTERA_VID			0x09fb
+#define ALTERA_UB3_6022_PID		0x6022
+#define ALTERA_UB3_6025_PID		0x6025
+#define ALTERA_UB3_6026_PID		0x6026
+#define ALTERA_UB3_6029_PID		0x6029
+#define ALTERA_UB3_602A_PID		0x602a
+#define ALTERA_UB3_602C_PID		0x602c
+#define ALTERA_UB3_602D_PID		0x602d
+#define ALTERA_UB3_602E_PID		0x602e

From 066e053fe208a3b83ee89dc5a192146add688861 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:47 +0100
Subject: [PATCH 2036/2753] fsnotify: add pre-content hooks on mmap()

Pre-content hooks in page faults introduces potential deadlock of HSM
handler in userspace with filesystem freezing.

The requirement with pre-content event is that for every accessed file
range an event covering at least this range will be generated at least
once before the file data is accesses.

In preparation to disabling pre-content event hooks on page faults,
add pre-content hooks at mmap() variants for the entire mmaped range,
so HSM can fill content when user requests to map a portion of the file.

Note that exec() variant also calls vm_mmap_pgoff() internally to map
code sections, so pre-content hooks are also generated in this case.

Link: https://lore.kernel.org/linux-fsdevel/7ehxrhbvehlrjwvrduoxsao5k3x4aw275patsb3krkwuq573yv@o2hskrfawbnc/
Suggested-by: Josef Bacik <josef@toxicpanda.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-2-amir73il@gmail.com
---
 include/linux/fsnotify.h | 21 +++++++++++++++++++++
 mm/util.c                |  3 +++
 2 files changed, 24 insertions(+)

diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 6a33288bd6a1f..83d3ac97f8262 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -170,6 +170,21 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 	return fsnotify_path(&file->f_path, FS_ACCESS_PERM);
 }
 
+/*
+ * fsnotify_mmap_perm - permission hook before mmap of file range
+ */
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
+{
+	/*
+	 * mmap() generates only pre-content events.
+	 */
+	if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode)))
+		return 0;
+
+	return fsnotify_pre_content(&file->f_path, &off, len);
+}
+
 /*
  * fsnotify_truncate_perm - permission hook before file truncate
  */
@@ -223,6 +238,12 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 	return 0;
 }
 
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
+{
+	return 0;
+}
+
 static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
 {
 	return 0;
diff --git a/mm/util.c b/mm/util.c
index b6b9684a14388..8c965474d329f 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -23,6 +23,7 @@
 #include <linux/processor.h>
 #include <linux/sizes.h>
 #include <linux/compat.h>
+#include <linux/fsnotify.h>
 
 #include <linux/uaccess.h>
 
@@ -569,6 +570,8 @@ unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
 	LIST_HEAD(uf);
 
 	ret = security_mmap_file(file, prot, flag);
+	if (!ret)
+		ret = fsnotify_mmap_perm(file, prot, pgoff >> PAGE_SHIFT, len);
 	if (!ret) {
 		if (mmap_write_lock_killable(mm))
 			return -EINTR;

From 25655580136de59ec89f09089dd28008ea440fc9 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:52 +0800
Subject: [PATCH 2037/2753] RDMA/hns: Fix soft lockup during bt pages loop

Driver runs a for-loop when allocating bt pages and mapping them with
buffer pages. When a large buffer (e.g. MR over 100GB) is being allocated,
it may require a considerable loop count. This will lead to soft lockup:

        watchdog: BUG: soft lockup - CPU#27 stuck for 22s!
        ...
        Call trace:
         hem_list_alloc_mid_bt+0x124/0x394 [hns_roce_hw_v2]
         hns_roce_hem_list_request+0xf8/0x160 [hns_roce_hw_v2]
         hns_roce_mtr_create+0x2e4/0x360 [hns_roce_hw_v2]
         alloc_mr_pbl+0xd4/0x17c [hns_roce_hw_v2]
         hns_roce_reg_user_mr+0xf8/0x190 [hns_roce_hw_v2]
         ib_uverbs_reg_mr+0x118/0x290

        watchdog: BUG: soft lockup - CPU#35 stuck for 23s!
        ...
        Call trace:
         hns_roce_hem_list_find_mtt+0x7c/0xb0 [hns_roce_hw_v2]
         mtr_map_bufs+0xc4/0x204 [hns_roce_hw_v2]
         hns_roce_mtr_create+0x31c/0x3c4 [hns_roce_hw_v2]
         alloc_mr_pbl+0xb0/0x160 [hns_roce_hw_v2]
         hns_roce_reg_user_mr+0x108/0x1c0 [hns_roce_hw_v2]
         ib_uverbs_reg_mr+0x120/0x2bc

Add a cond_resched() to fix soft lockup during these loops. In order not
to affect the allocation performance of normal-size buffer, set the loop
count of a 100GB MR as the threshold to call cond_resched().

Fixes: 38389eaa4db1 ("RDMA/hns: Add mtr support for mixed multihop addressing")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-3-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_hem.c | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
index 605562122ecce..ca0798224e565 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
@@ -1361,6 +1361,11 @@ static int hem_list_alloc_root_bt(struct hns_roce_dev *hr_dev,
 	return ret;
 }
 
+/* This is the bottom bt pages number of a 100G MR on 4K OS, assuming
+ * the bt page size is not expanded by cal_best_bt_pg_sz()
+ */
+#define RESCHED_LOOP_CNT_THRESHOLD_ON_4K 12800
+
 /* construct the base address table and link them by address hop config */
 int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 			      struct hns_roce_hem_list *hem_list,
@@ -1369,6 +1374,7 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 {
 	const struct hns_roce_buf_region *r;
 	int ofs, end;
+	int loop;
 	int unit;
 	int ret;
 	int i;
@@ -1386,7 +1392,10 @@ int hns_roce_hem_list_request(struct hns_roce_dev *hr_dev,
 			continue;
 
 		end = r->offset + r->count;
-		for (ofs = r->offset; ofs < end; ofs += unit) {
+		for (ofs = r->offset, loop = 1; ofs < end; ofs += unit, loop++) {
+			if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+				cond_resched();
+
 			ret = hem_list_alloc_mid_bt(hr_dev, r, unit, ofs,
 						    hem_list->mid_bt[i],
 						    &hem_list->btm_bt);
@@ -1443,9 +1452,14 @@ void *hns_roce_hem_list_find_mtt(struct hns_roce_dev *hr_dev,
 	struct list_head *head = &hem_list->btm_bt;
 	struct hns_roce_hem_item *hem, *temp_hem;
 	void *cpu_base = NULL;
+	int loop = 1;
 	int nr = 0;
 
 	list_for_each_entry_safe(hem, temp_hem, head, sibling) {
+		if (!(loop % RESCHED_LOOP_CNT_THRESHOLD_ON_4K))
+			cond_resched();
+		loop++;
+
 		if (hem_list_page_is_in_range(hem, offset)) {
 			nr = offset - hem->start;
 			cpu_base = hem->addr + nr * BA_BYTE_LEN;

From b9f59a24ba35a7d955a9f8e148dd9f85b7b40a01 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:53 +0800
Subject: [PATCH 2038/2753] RDMA/hns: Fix unmatched condition in error path of
 alloc_user_qp_db()

Currently the condition of unmapping sdb in error path is not exactly
the same as the condition of mapping in alloc_user_qp_db(). This may
cause a problem of unmapping an unmapped db in some case, such as
when the QP is XRC TGT. Unified the two conditions.

Fixes: 90ae0b57e4a5 ("RDMA/hns: Combine enable flags of qp")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-4-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_qp.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 9e2e76c594063..a97348a1c61f1 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -868,12 +868,14 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 			    struct hns_roce_ib_create_qp *ucmd,
 			    struct hns_roce_ib_create_qp_resp *resp)
 {
+	bool has_sdb = user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd);
 	struct hns_roce_ucontext *uctx = rdma_udata_to_drv_context(udata,
 		struct hns_roce_ucontext, ibucontext);
+	bool has_rdb = user_qp_has_rdb(hr_dev, init_attr, udata, resp);
 	struct ib_device *ibdev = &hr_dev->ib_dev;
 	int ret;
 
-	if (user_qp_has_sdb(hr_dev, init_attr, udata, resp, ucmd)) {
+	if (has_sdb) {
 		ret = hns_roce_db_map_user(uctx, ucmd->sdb_addr, &hr_qp->sdb);
 		if (ret) {
 			ibdev_err(ibdev,
@@ -884,7 +886,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 		hr_qp->en_flags |= HNS_ROCE_QP_CAP_SQ_RECORD_DB;
 	}
 
-	if (user_qp_has_rdb(hr_dev, init_attr, udata, resp)) {
+	if (has_rdb) {
 		ret = hns_roce_db_map_user(uctx, ucmd->db_addr, &hr_qp->rdb);
 		if (ret) {
 			ibdev_err(ibdev,
@@ -898,7 +900,7 @@ static int alloc_user_qp_db(struct hns_roce_dev *hr_dev,
 	return 0;
 
 err_sdb:
-	if (hr_qp->en_flags & HNS_ROCE_QP_CAP_SQ_RECORD_DB)
+	if (has_sdb)
 		hns_roce_db_unmap_user(uctx, &hr_qp->sdb);
 err_out:
 	return ret;

From 13c90c222049764bb7e6a1689bd785f424bd8bd5 Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:54 +0800
Subject: [PATCH 2039/2753] RDMA/hns: Fix invalid sq params not being blocked

SQ params from userspace are checked in by set_user_sq_size(). But
when the check fails, the function doesn't return but instead keep
running and overwrite 'ret'. As a result, the invalid params will
not get blocked actually.

Add a return right after the failed check. Besides, although the
check result of kernel sq params will not be overwritten, to keep
coding style unified, move default_congest_type() before
set_kernel_sq_size().

Fixes: 6ec429d5887a ("RDMA/hns: Support userspace configuring congestion control algorithm with QP granularity")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-5-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_qp.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index a97348a1c61f1..8408f9a5c309d 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -1121,24 +1121,23 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 						 ibucontext);
 		hr_qp->config = uctx->config;
 		ret = set_user_sq_size(hr_dev, &init_attr->cap, hr_qp, ucmd);
-		if (ret)
+		if (ret) {
 			ibdev_err(ibdev,
 				  "failed to set user SQ size, ret = %d.\n",
 				  ret);
+			return ret;
+		}
 
 		ret = set_congest_param(hr_dev, hr_qp, ucmd);
-		if (ret)
-			return ret;
 	} else {
 		if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
 			hr_qp->config = HNS_ROCE_EXSGE_FLAGS;
+		default_congest_type(hr_dev, hr_qp);
 		ret = set_kernel_sq_size(hr_dev, &init_attr->cap, hr_qp);
 		if (ret)
 			ibdev_err(ibdev,
 				  "failed to set kernel SQ size, ret = %d.\n",
 				  ret);
-
-		default_congest_type(hr_dev, hr_qp);
 	}
 
 	return ret;

From 444907dd45cbe62fd69398805b6e2c626fab5b3a Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:55 +0800
Subject: [PATCH 2040/2753] RDMA/hns: Fix a missing rollback in error path of
 hns_roce_create_qp_common()

When ib_copy_to_udata() fails in hns_roce_create_qp_common(),
hns_roce_qp_remove() should be called in the error path to
clean up resources in hns_roce_qp_store().

Fixes: 0f00571f9433 ("RDMA/hns: Use new SQ doorbell register for HIP09")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-6-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_qp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 8408f9a5c309d..52b671156246b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -1220,7 +1220,7 @@ static int hns_roce_create_qp_common(struct hns_roce_dev *hr_dev,
 				       min(udata->outlen, sizeof(resp)));
 		if (ret) {
 			ibdev_err(ibdev, "copy qp resp failed!\n");
-			goto err_store;
+			goto err_flow_ctrl;
 		}
 	}
 

From eda0a2fdbc24c35cd8d61d9c9111cafd5f89b2dc Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:56 +0800
Subject: [PATCH 2041/2753] RDMA/hns: Fix missing xa_destroy()

Add xa_destroy() for xarray in driver.

Fixes: 5c1f167af112 ("RDMA/hns: Init SRQ table for hip08")
Fixes: 27e19f451089 ("RDMA/hns: Convert cq_table to XArray")
Fixes: 736b5a70db98 ("RDMA/hns: Convert qp_table_tree to XArray")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-7-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_alloc.c | 4 +++-
 drivers/infiniband/hw/hns/hns_roce_cq.c    | 1 +
 drivers/infiniband/hw/hns/hns_roce_qp.c    | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_alloc.c b/drivers/infiniband/hw/hns/hns_roce_alloc.c
index 950c133d4220e..6ee911f6885b5 100644
--- a/drivers/infiniband/hw/hns/hns_roce_alloc.c
+++ b/drivers/infiniband/hw/hns/hns_roce_alloc.c
@@ -175,8 +175,10 @@ void hns_roce_cleanup_bitmap(struct hns_roce_dev *hr_dev)
 	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_XRC)
 		ida_destroy(&hr_dev->xrcd_ida.ida);
 
-	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ)
+	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_SRQ) {
 		ida_destroy(&hr_dev->srq_table.srq_ida.ida);
+		xa_destroy(&hr_dev->srq_table.xa);
+	}
 	hns_roce_cleanup_qp_table(hr_dev);
 	hns_roce_cleanup_cq_table(hr_dev);
 	ida_destroy(&hr_dev->mr_table.mtpt_ida.ida);
diff --git a/drivers/infiniband/hw/hns/hns_roce_cq.c b/drivers/infiniband/hw/hns/hns_roce_cq.c
index 4106423a1b399..3a5c93c9fb3e6 100644
--- a/drivers/infiniband/hw/hns/hns_roce_cq.c
+++ b/drivers/infiniband/hw/hns/hns_roce_cq.c
@@ -537,5 +537,6 @@ void hns_roce_cleanup_cq_table(struct hns_roce_dev *hr_dev)
 
 	for (i = 0; i < HNS_ROCE_CQ_BANK_NUM; i++)
 		ida_destroy(&hr_dev->cq_table.bank[i].ida);
+	xa_destroy(&hr_dev->cq_table.array);
 	mutex_destroy(&hr_dev->cq_table.bank_mutex);
 }
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index 52b671156246b..8901c142c1b65 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -1603,6 +1603,7 @@ void hns_roce_cleanup_qp_table(struct hns_roce_dev *hr_dev)
 	for (i = 0; i < HNS_ROCE_QP_BANK_NUM; i++)
 		ida_destroy(&hr_dev->qp_table.bank[i].ida);
 	xa_destroy(&hr_dev->qp_table.dip_xa);
+	xa_destroy(&hr_dev->qp_table_xa);
 	mutex_destroy(&hr_dev->qp_table.bank_mutex);
 	mutex_destroy(&hr_dev->qp_table.scc_mutex);
 }

From 6b5e41a8b51fce520bb09bd651a29ef495e990de Mon Sep 17 00:00:00 2001
From: Junxian Huang <huangjunxian6@hisilicon.com>
Date: Tue, 11 Mar 2025 16:48:57 +0800
Subject: [PATCH 2042/2753] RDMA/hns: Fix wrong value of max_sge_rd

There is no difference between the sge of READ and non-READ
operations in hns RoCE. Set max_sge_rd to the same value as
max_send_sge.

Fixes: 9a4435375cd1 ("IB/hns: Add driver files for hns RoCE driver")
Signed-off-by: Junxian Huang <huangjunxian6@hisilicon.com>
Link: https://patch.msgid.link/20250311084857.3803665-8-huangjunxian6@hisilicon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/hns/hns_roce_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index ae24c81c9812d..cf89a8db4f64c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -183,7 +183,7 @@ static int hns_roce_query_device(struct ib_device *ib_dev,
 				  IB_DEVICE_RC_RNR_NAK_GEN;
 	props->max_send_sge = hr_dev->caps.max_sq_sg;
 	props->max_recv_sge = hr_dev->caps.max_rq_sg;
-	props->max_sge_rd = 1;
+	props->max_sge_rd = hr_dev->caps.max_sq_sg;
 	props->max_cq = hr_dev->caps.num_cqs;
 	props->max_cqe = hr_dev->caps.max_cqes;
 	props->max_mr = hr_dev->caps.num_mtpts;

From 0882ca4eecfe8b0013f339144acf886a0a0de41f Mon Sep 17 00:00:00 2001
From: Yifan Zha <Yifan.Zha@amd.com>
Date: Wed, 5 Mar 2025 13:14:55 +0800
Subject: [PATCH 2043/2753] drm/amd/amdkfd: Evict all queues even HWS remove
 queue failed

[Why]
If reset is detected and kfd need to evict working queues, HWS moving queue will be failed.
Then remaining queues are not evicted and in active state.

After reset done, kfd uses HWS to termination remaining activated queues but HWS is resetted.
So remove queue will be failed again.

[How]
Keep removing all queues even if HWS returns failed.
It will not affect cpsch as it checks reset_domain->sem.

v2: If any queue failed, evict queue returns error.
v3: Declare err inside the if-block.

Reviewed-by: Felix Kuehling <felix.kuehling@amd.com>
Signed-off-by: Yifan Zha <Yifan.Zha@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 42c854b8fb0cce512534aa2b7141948e80c6ebb0)
Cc: stable@vger.kernel.org
---
 drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index d4593374e7a1e..34c2c42c0f95c 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -1230,11 +1230,13 @@ static int evict_process_queues_cpsch(struct device_queue_manager *dqm,
 		decrement_queue_count(dqm, qpd, q);
 
 		if (dqm->dev->kfd->shared_resources.enable_mes) {
-			retval = remove_queue_mes(dqm, q, qpd);
-			if (retval) {
+			int err;
+
+			err = remove_queue_mes(dqm, q, qpd);
+			if (err) {
 				dev_err(dev, "Failed to evict queue %d\n",
 					q->properties.queue_id);
-				goto out;
+				retval = err;
 			}
 		}
 	}

From 6cc30748e17ea2a64051ceaf83a8372484e597f1 Mon Sep 17 00:00:00 2001
From: Natalie Vock <natalie.vock@gmx.de>
Date: Mon, 10 Mar 2025 18:08:05 +0100
Subject: [PATCH 2044/2753] drm/amdgpu: NULL-check BO's backing store when
 determining GFX12 PTE flags
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

PRT BOs may not have any backing store, so bo->tbo.resource will be
NULL. Check for that before dereferencing.

Fixes: 0cce5f285d9a ("drm/amdkfd: Check correct memory types for is_system variable")
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Natalie Vock <natalie.vock@gmx.de>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 3e3fcd29b505cebed659311337ea03b7698767fc)
Cc: stable@vger.kernel.org # 6.12.x
---
 drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
index b749f1c3f6a9a..0fb88e6d5d54b 100644
--- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
@@ -528,8 +528,9 @@ static void gmc_v12_0_get_vm_pte(struct amdgpu_device *adev,
 
 	bo_adev = amdgpu_ttm_adev(bo->tbo.bdev);
 	coherent = bo->flags & AMDGPU_GEM_CREATE_COHERENT;
-	is_system = (bo->tbo.resource->mem_type == TTM_PL_TT) ||
-		(bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT);
+	is_system = bo->tbo.resource &&
+		(bo->tbo.resource->mem_type == TTM_PL_TT ||
+		 bo->tbo.resource->mem_type == AMDGPU_PL_PREEMPT);
 
 	if (bo && bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC)
 		*flags |= AMDGPU_PTE_DCC;

From 0c3057a5a04d07120b3d0ec9c79568fceb9c921e Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 6 Mar 2025 15:23:54 -0800
Subject: [PATCH 2045/2753] net_sched: Prevent creation of classes with
 TC_H_ROOT

The function qdisc_tree_reduce_backlog() uses TC_H_ROOT as a termination
condition when traversing up the qdisc tree to update parent backlog
counters. However, if a class is created with classid TC_H_ROOT, the
traversal terminates prematurely at this class instead of reaching the
actual root qdisc, causing parent statistics to be incorrectly maintained.
In case of DRR, this could lead to a crash as reported by Mingi Cho.

Prevent the creation of any Qdisc class with classid TC_H_ROOT
(0xFFFFFFFF) across all qdisc types, as suggested by Jamal.

Reported-by: Mingi Cho <mincho@theori.io>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Fixes: 066a3b5b2346 ("[NET_SCHED] sch_api: fix qdisc_tree_decrease_qlen() loop")
Link: https://patch.msgid.link/20250306232355.93864-2-xiyou.wangcong@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_api.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index e3e91cf867eb9..6c625dcd06519 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -2254,6 +2254,12 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n,
 		return -EOPNOTSUPP;
 	}
 
+	/* Prevent creation of traffic classes with classid TC_H_ROOT */
+	if (clid == TC_H_ROOT) {
+		NL_SET_ERR_MSG(extack, "Cannot create traffic class with classid TC_H_ROOT");
+		return -EINVAL;
+	}
+
 	new_cl = cl;
 	err = -EOPNOTSUPP;
 	if (cops->change)

From bb7737de5f593155aabbca283f4822176f4e7d6b Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 6 Mar 2025 15:23:55 -0800
Subject: [PATCH 2046/2753] selftests/tc-testing: Add a test case for DRR class
 with TC_H_ROOT

Integrate the reproduer from Mingi to TDC.

All test results:

1..4
ok 1 0385 - Create DRR with default setting
ok 2 2375 - Delete DRR with handle
ok 3 3092 - Show DRR class
ok 4 4009 - Reject creation of DRR class with classid TC_H_ROOT

Cc: Mingi Cho <mincho@theori.io>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250306232355.93864-3-xiyou.wangcong@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../tc-testing/tc-tests/qdiscs/drr.json       | 25 +++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
index 7126ec3485cbd..2b61d8d79bde8 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/drr.json
@@ -61,5 +61,30 @@
         "teardown": [
             "$TC qdisc del dev $DUMMY handle 1: root"
         ]
+    },
+    {
+        "id": "4009",
+        "name": "Reject creation of DRR class with classid TC_H_ROOT",
+        "category": [
+            "qdisc",
+            "drr"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$TC qdisc add dev $DUMMY root handle ffff: drr",
+            "$TC filter add dev $DUMMY parent ffff: basic classid ffff:1",
+            "$TC class add dev $DUMMY parent ffff: classid ffff:1 drr",
+            "$TC filter add dev $DUMMY parent ffff: prio 1 u32 match u16 0x0000 0xfe00 at 2 flowid ffff:ffff"
+        ],
+        "cmdUnderTest": "$TC class add dev $DUMMY parent ffff: classid ffff:ffff drr",
+        "expExitCode": "2",
+        "verifyCmd": "$TC class show dev $DUMMY",
+        "matchPattern": "class drr ffff:ffff",
+        "matchCount": "0",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY root"
+        ]
     }
 ]

From 0a13c1e0a449917b29c45d90701eededa69c99d3 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Fri, 7 Mar 2025 20:47:26 -0800
Subject: [PATCH 2047/2753] net: revert to lockless TC_SETUP_BLOCK and
 TC_SETUP_FT

There is a couple of places from which we can arrive to ndo_setup_tc
with TC_SETUP_BLOCK/TC_SETUP_FT:
- netlink
- netlink notifier
- netdev notifier

Locking netdev too deep in this call chain seems to be problematic
(especially assuming some/all of the call_netdevice_notifiers
NETDEV_UNREGISTER) might soon be running with the instance lock).
Revert to lockless ndo_setup_tc for TC_SETUP_BLOCK/TC_SETUP_FT. NFT
framework already takes care of most of the locking. Document
the assumptions.

ndo_setup_tc TC_SETUP_BLOCK
  nft_block_offload_cmd
    nft_chain_offload_cmd
      nft_flow_block_chain
        nft_flow_offload_chain
	  nft_flow_rule_offload_abort
	    nft_flow_rule_offload_commit
	  nft_flow_rule_offload_commit
	    nf_tables_commit
	      nfnetlink_rcv_batch
	        nfnetlink_rcv_skb_batch
		  nfnetlink_rcv
	nft_offload_netdev_event
	  NETDEV_UNREGISTER notifier

ndo_setup_tc TC_SETUP_FT
  nf_flow_table_offload_cmd
    nf_flow_table_offload_setup
      nft_unregister_flowtable_hook
        nft_register_flowtable_net_hooks
	  nft_flowtable_update
	  nf_tables_newflowtable
	    nfnetlink_rcv_batch (.call NFNL_CB_BATCH)
	nft_flowtable_update
	  nf_tables_newflowtable
	nft_flowtable_event
	  nf_tables_flowtable_event
	    NETDEV_UNREGISTER notifier
      __nft_unregister_flowtable_net_hooks
        nft_unregister_flowtable_net_hooks
	  nf_tables_commit
	    nfnetlink_rcv_batch (.call NFNL_CB_BATCH)
	  __nf_tables_abort
	    nf_tables_abort
	      nfnetlink_rcv_batch
	__nft_release_hook
	  __nft_release_hooks
	    nf_tables_pre_exit_net -> module unload
	  nft_rcv_nl_event
	    netlink_register_notifier (oh boy)
      nft_register_flowtable_net_hooks
      	nft_flowtable_update
	  nf_tables_newflowtable
        nf_tables_newflowtable

Fixes: c4f0f30b424e ("net: hold netdev instance lock during nft ndo_setup_tc")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reported-by: syzbot+0afb4bcf91e5a1afdcad@syzkaller.appspotmail.com
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250308044726.1193222-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/netdevices.rst |  6 ++++++
 include/linux/netdevice.h               |  2 --
 net/core/dev.c                          | 19 -------------------
 net/netfilter/nf_flow_table_offload.c   |  2 +-
 net/netfilter/nf_tables_offload.c       |  2 +-
 5 files changed, 8 insertions(+), 23 deletions(-)

diff --git a/Documentation/networking/netdevices.rst b/Documentation/networking/netdevices.rst
index d235a73648930..ebb868f50ac2b 100644
--- a/Documentation/networking/netdevices.rst
+++ b/Documentation/networking/netdevices.rst
@@ -290,6 +290,12 @@ ndo_set_rx_mode:
 	Synchronization: netif_addr_lock spinlock.
 	Context: BHs disabled
 
+ndo_setup_tc:
+	``TC_SETUP_BLOCK`` and ``TC_SETUP_FT`` are running under NFT locks
+	(i.e. no ``rtnl_lock`` and no device instance lock). The rest of
+	``tc_setup_type`` types run under netdev instance lock if the driver
+	implements queue management or shaper API.
+
 Most ndo callbacks not specified in the list above are running
 under ``rtnl_lock``. In addition, netdev instance lock is taken as well if
 the driver implements queue management or shaper API.
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9a297757df7eb..0dbfe069a6e38 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3316,8 +3316,6 @@ int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
 void netif_close(struct net_device *dev);
 void dev_close(struct net_device *dev);
 void dev_close_many(struct list_head *head, bool unlink);
-int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
-		 void *type_data);
 void netif_disable_lro(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1cb134ff73270..812134b71f050 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1761,25 +1761,6 @@ void netif_close(struct net_device *dev)
 	}
 }
 
-int dev_setup_tc(struct net_device *dev, enum tc_setup_type type,
-		 void *type_data)
-{
-	const struct net_device_ops *ops = dev->netdev_ops;
-	int ret;
-
-	ASSERT_RTNL();
-
-	if (!ops->ndo_setup_tc)
-		return -EOPNOTSUPP;
-
-	netdev_lock_ops(dev);
-	ret = ops->ndo_setup_tc(dev, type, type_data);
-	netdev_unlock_ops(dev);
-
-	return ret;
-}
-EXPORT_SYMBOL(dev_setup_tc);
-
 void netif_disable_lro(struct net_device *dev)
 {
 	struct net_device *lower_dev;
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index 0ec4abded10de..e06bc36f49fe7 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -1175,7 +1175,7 @@ static int nf_flow_table_offload_cmd(struct flow_block_offload *bo,
 	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
 					 extack);
 	down_write(&flowtable->flow_block_lock);
-	err = dev_setup_tc(dev, TC_SETUP_FT, bo);
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo);
 	up_write(&flowtable->flow_block_lock);
 	if (err < 0)
 		return err;
diff --git a/net/netfilter/nf_tables_offload.c b/net/netfilter/nf_tables_offload.c
index b761899c143cd..64675f1c7f295 100644
--- a/net/netfilter/nf_tables_offload.c
+++ b/net/netfilter/nf_tables_offload.c
@@ -390,7 +390,7 @@ static int nft_block_offload_cmd(struct nft_base_chain *chain,
 
 	nft_flow_block_offload_init(&bo, dev_net(dev), cmd, chain, &extack);
 
-	err = dev_setup_tc(dev, TC_SETUP_BLOCK, &bo);
+	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_BLOCK, &bo);
 	if (err < 0)
 		return err;
 

From 110eff172dfebcaa1402d25375add0a3581bb43b Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Sun, 9 Mar 2025 14:58:49 -0700
Subject: [PATCH 2048/2753] eth: bnxt: switch to netif_close

All (error) paths that call dev_close are already holding instance lock,
so switch to netif_close to avoid the deadlock.

v2:
- add missing EXPORT_MODULE for netif_close

Fixes: 004b5008016a ("eth: bnxt: remove most dependencies on RTNL")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250309215851.2003708-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 12 ++++++------
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c |  4 ++--
 net/core/dev.c                                    |  1 +
 3 files changed, 9 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b09171110ec49..66dfaf7e37766 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12802,7 +12802,7 @@ int bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init)
 		rc = __bnxt_open_nic(bp, irq_re_init, link_re_init);
 	if (rc) {
 		netdev_err(bp->dev, "nic open fail (rc: %x)\n", rc);
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 	}
 	return rc;
 }
@@ -12840,7 +12840,7 @@ int bnxt_half_open_nic(struct bnxt *bp)
 half_open_err:
 	bnxt_free_skbs(bp);
 	bnxt_free_mem(bp, true);
-	dev_close(bp->dev);
+	netif_close(bp->dev);
 	return rc;
 }
 
@@ -14195,7 +14195,7 @@ void bnxt_fw_reset(struct bnxt *bp)
 			netdev_err(bp->dev, "Firmware reset aborted, rc = %d\n",
 				   n);
 			clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state);
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 			goto fw_reset_exit;
 		} else if (n > 0) {
 			u16 vf_tmo_dsecs = n * 10;
@@ -14810,7 +14810,7 @@ static void bnxt_fw_reset_abort(struct bnxt *bp, int rc)
 	if (bp->fw_reset_state != BNXT_FW_RESET_STATE_POLL_VF)
 		bnxt_dl_health_fw_status_update(bp, false);
 	bp->fw_reset_state = 0;
-	dev_close(bp->dev);
+	netif_close(bp->dev);
 }
 
 static void bnxt_fw_reset_task(struct work_struct *work)
@@ -16276,7 +16276,7 @@ int bnxt_restore_pf_fw_resources(struct bnxt *bp)
 
 	if (netif_running(bp->dev)) {
 		if (rc)
-			dev_close(bp->dev);
+			netif_close(bp->dev);
 		else
 			rc = bnxt_open_nic(bp, true, false);
 	}
@@ -16669,7 +16669,7 @@ static void bnxt_shutdown(struct pci_dev *pdev)
 		goto shutdown_exit;
 
 	if (netif_running(dev))
-		dev_close(dev);
+		netif_close(dev);
 
 	bnxt_ptp_clear(bp);
 	bnxt_clear_int_mode(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index b06fcddfc81c8..b6d6fcd105d7b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -461,7 +461,7 @@ static int bnxt_dl_reload_down(struct devlink *dl, bool netns_change,
 		if (rc) {
 			NL_SET_ERR_MSG_MOD(extack, "Failed to deregister");
 			if (netif_running(bp->dev))
-				dev_close(bp->dev);
+				netif_close(bp->dev);
 			netdev_unlock(bp->dev);
 			rtnl_unlock();
 			break;
@@ -576,7 +576,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		*actions_performed |= BIT(action);
 	} else if (netif_running(bp->dev)) {
 		netdev_lock(bp->dev);
-		dev_close(bp->dev);
+		netif_close(bp->dev);
 		netdev_unlock(bp->dev);
 	}
 	rtnl_unlock();
diff --git a/net/core/dev.c b/net/core/dev.c
index 812134b71f050..0bf5af9706b12 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1760,6 +1760,7 @@ void netif_close(struct net_device *dev)
 		list_del(&single);
 	}
 }
+EXPORT_SYMBOL(netif_close);
 
 void netif_disable_lro(struct net_device *dev)
 {

From eaca6e5dc6ba19422989e73415a49042b2062ed0 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Sun, 9 Mar 2025 14:58:50 -0700
Subject: [PATCH 2049/2753] eth: bnxt: request unconditional ops lock

netdev_lock_ops conditionally grabs instance lock when queue_mgmt_ops
is defined. However queue_mgmt_ops support is signaled via FW
so we can sometimes boot without queue_mgmt_ops being set.
This will result in bnxt running without instance lock which
the driver now heavily depends on. Set request_ops_lock to true
unconditionally to always request netdev instance lock.

Fixes: 004b5008016a ("eth: bnxt: remove most dependencies on RTNL")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250309215851.2003708-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 66dfaf7e37766..08ac01d6a5097 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -16613,6 +16613,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		bp->rss_cap |= BNXT_RSS_CAP_MULTI_RSS_CTX;
 	if (BNXT_SUPPORTS_QUEUE_API(bp))
 		dev->queue_mgmt_ops = &bnxt_queue_mgmt_ops;
+	dev->request_ops_lock = true;
 
 	rc = register_netdev(dev);
 	if (rc)

From adbf627f170382684f095c261866510b2b70d841 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Sun, 9 Mar 2025 14:58:51 -0700
Subject: [PATCH 2050/2753] eth: bnxt: add missing netdev lock management to
 bnxt_dl_reload_up

bnxt_dl_reload_up is completely missing instance lock management
which can result in `devlink dev reload` leaving with instance
lock held. Add the missing calls.

Also add netdev_assert_locked to make it clear that the up() method
is running with the instance lock grabbed.

v2:
- add net/netdev_lock.h include to bnxt_devlink.c for netdev_assert_locked

Fixes: 004b5008016a ("eth: bnxt: remove most dependencies on RTNL")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250309215851.2003708-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index b6d6fcd105d7b..f8fcc8e0e8ded 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -11,6 +11,7 @@
 #include <linux/netdevice.h>
 #include <linux/vmalloc.h>
 #include <net/devlink.h>
+#include <net/netdev_lock.h>
 #include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
@@ -518,6 +519,8 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
 	int rc = 0;
 
+	netdev_assert_locked(bp->dev);
+
 	*actions_performed = 0;
 	switch (action) {
 	case DEVLINK_RELOAD_ACTION_DRIVER_REINIT: {
@@ -542,6 +545,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		if (!netif_running(bp->dev))
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Device is closed, not waiting for reset notice that will never come");
+		netdev_unlock(bp->dev);
 		rtnl_unlock();
 		while (test_bit(BNXT_STATE_FW_ACTIVATE, &bp->state)) {
 			if (time_after(jiffies, timeout)) {
@@ -557,6 +561,7 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 			msleep(50);
 		}
 		rtnl_lock();
+		netdev_lock(bp->dev);
 		if (!rc)
 			*actions_performed |= BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT);
 		clear_bit(BNXT_STATE_FW_ACTIVATE, &bp->state);
@@ -575,10 +580,9 @@ static int bnxt_dl_reload_up(struct devlink *dl, enum devlink_reload_action acti
 		}
 		*actions_performed |= BIT(action);
 	} else if (netif_running(bp->dev)) {
-		netdev_lock(bp->dev);
 		netif_close(bp->dev);
-		netdev_unlock(bp->dev);
 	}
+	netdev_unlock(bp->dev);
 	rtnl_unlock();
 	if (action == DEVLINK_RELOAD_ACTION_DRIVER_REINIT)
 		bnxt_ulp_start(bp, rc);

From 188107b2c403b593439ad5b74baed5fefa638df4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 10 Mar 2025 12:08:21 +0100
Subject: [PATCH 2051/2753] selftests: net: bump GRO timeout for gro/setup_veth

Commit 51bef03e1a71 ("selftests/net: deflake GRO tests") recently
switched to NAPI suspension, and lowered the timeout from 1ms to 100us.
This started causing flakes in netdev-run CI. Let's bump it to 200us.
In a quick test of a debug kernel I see failures with 100us, with 200us
in 5 runs I see 2 completely clean runs and 3 with a single retry
(GRO test will retry up to 5 times).

Reviewed-by: Kevin Krakauer <krakauer@google.com>
Link: https://patch.msgid.link/20250310110821.385621-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/setup_veth.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/setup_veth.sh b/tools/testing/selftests/net/setup_veth.sh
index eb3182066d126..152bf4c657478 100644
--- a/tools/testing/selftests/net/setup_veth.sh
+++ b/tools/testing/selftests/net/setup_veth.sh
@@ -11,7 +11,7 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 200000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
 	echo 1 > "/sys/class/net/${ns_dev}/napi_defer_hard_irqs"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up

From 17fef2042338e19ed7b57484da4db9e3a3b47c76 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Fri, 7 Mar 2025 12:39:33 +0000
Subject: [PATCH 2052/2753] net/mlx5: Avoid unnecessary use of comma operator

Although it does not seem to have any untoward side-effects,
the use of ';' to separate to assignments seems more appropriate than ','.

Flagged by clang-19 -Wcomma

No functional change intended.
Compile tested only.

Signed-off-by: Simon Horman <horms@kernel.org>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20250307-mlx5-comma-v1-1-934deb6927bb@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
index c862dd28c4661..e8cc91a9bd827 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/fs_chains.c
@@ -700,7 +700,7 @@ mlx5_chains_create_global_table(struct mlx5_fs_chains *chains)
 		goto err_ignore;
 	}
 
-	chain = mlx5_chains_get_chain_range(chains),
+	chain = mlx5_chains_get_chain_range(chains);
 	prio = mlx5_chains_get_prio_range(chains);
 	level = mlx5_chains_get_level_range(chains);
 

From b6b67141d6f1f736b17aca87e5ecb43b7c3a8205 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Tue, 11 Mar 2025 07:40:24 -0700
Subject: [PATCH 2053/2753] net: create netdev_nl_sock to wrap bindings list

No functional changes. Next patches will add more granular locking
to netdev_nl_sock.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250311144026.4154277-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml |  4 ++--
 include/net/netdev_netlink.h            | 11 +++++++++++
 net/core/netdev-genl-gen.c              |  4 ++--
 net/core/netdev-genl-gen.h              |  6 +++---
 net/core/netdev-genl.c                  | 19 +++++++++----------
 5 files changed, 27 insertions(+), 17 deletions(-)
 create mode 100644 include/net/netdev_netlink.h

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 36f1152bfac39..f5e0750ab71db 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -745,8 +745,8 @@ operations:
             - irq-suspend-timeout
 
 kernel-family:
-  headers: [ "linux/list.h"]
-  sock-priv: struct list_head
+  headers: [ "net/netdev_netlink.h"]
+  sock-priv: struct netdev_nl_sock
 
 mcast-groups:
   list:
diff --git a/include/net/netdev_netlink.h b/include/net/netdev_netlink.h
new file mode 100644
index 0000000000000..1599573d35c9a
--- /dev/null
+++ b/include/net/netdev_netlink.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_NETDEV_NETLINK_H
+#define __NET_NETDEV_NETLINK_H
+
+#include <linux/list.h>
+
+struct netdev_nl_sock {
+	struct list_head bindings;
+};
+
+#endif	/* __NET_NETDEV_NETLINK_H */
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 996ac6a449eba..739f7b6506a6a 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -9,7 +9,7 @@
 #include "netdev-genl-gen.h"
 
 #include <uapi/linux/netdev.h>
-#include <linux/list.h>
+#include <net/netdev_netlink.h>
 
 /* Integer value ranges */
 static const struct netlink_range_validation netdev_a_page_pool_id_range = {
@@ -217,7 +217,7 @@ struct genl_family netdev_nl_family __ro_after_init = {
 	.n_split_ops	= ARRAY_SIZE(netdev_nl_ops),
 	.mcgrps		= netdev_nl_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(netdev_nl_mcgrps),
-	.sock_priv_size	= sizeof(struct list_head),
+	.sock_priv_size	= sizeof(struct netdev_nl_sock),
 	.sock_priv_init	= __netdev_nl_sock_priv_init,
 	.sock_priv_destroy = __netdev_nl_sock_priv_destroy,
 };
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
index e09dd7539ff2b..17d39fd64c948 100644
--- a/net/core/netdev-genl-gen.h
+++ b/net/core/netdev-genl-gen.h
@@ -10,7 +10,7 @@
 #include <net/genetlink.h>
 
 #include <uapi/linux/netdev.h>
-#include <linux/list.h>
+#include <net/netdev_netlink.h>
 
 /* Common nested types */
 extern const struct nla_policy netdev_page_pool_info_nl_policy[NETDEV_A_PAGE_POOL_IFINDEX + 1];
@@ -42,7 +42,7 @@ enum {
 
 extern struct genl_family netdev_nl_family;
 
-void netdev_nl_sock_priv_init(struct list_head *priv);
-void netdev_nl_sock_priv_destroy(struct list_head *priv);
+void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv);
+void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv);
 
 #endif /* _LINUX_NETDEV_GEN_H */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 2b774183d31cd..a219be90c739e 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -829,8 +829,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 {
 	struct nlattr *tb[ARRAY_SIZE(netdev_queue_id_nl_policy)];
 	struct net_devmem_dmabuf_binding *binding;
-	struct list_head *sock_binding_list;
 	u32 ifindex, dmabuf_fd, rxq_idx;
+	struct netdev_nl_sock *priv;
 	struct net_device *netdev;
 	struct sk_buff *rsp;
 	struct nlattr *attr;
@@ -845,10 +845,9 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
 	dmabuf_fd = nla_get_u32(info->attrs[NETDEV_A_DMABUF_FD]);
 
-	sock_binding_list = genl_sk_priv_get(&netdev_nl_family,
-					     NETLINK_CB(skb).sk);
-	if (IS_ERR(sock_binding_list))
-		return PTR_ERR(sock_binding_list);
+	priv = genl_sk_priv_get(&netdev_nl_family, NETLINK_CB(skb).sk);
+	if (IS_ERR(priv))
+		return PTR_ERR(priv);
 
 	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
 	if (!rsp)
@@ -909,7 +908,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 			goto err_unbind;
 	}
 
-	list_add(&binding->list, sock_binding_list);
+	list_add(&binding->list, &priv->bindings);
 
 	nla_put_u32(rsp, NETDEV_A_DMABUF_ID, binding->id);
 	genlmsg_end(rsp, hdr);
@@ -931,17 +930,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	return err;
 }
 
-void netdev_nl_sock_priv_init(struct list_head *priv)
+void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv)
 {
-	INIT_LIST_HEAD(priv);
+	INIT_LIST_HEAD(&priv->bindings);
 }
 
-void netdev_nl_sock_priv_destroy(struct list_head *priv)
+void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
 {
 	struct net_devmem_dmabuf_binding *binding;
 	struct net_devmem_dmabuf_binding *temp;
 
-	list_for_each_entry_safe(binding, temp, priv, list) {
+	list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
 		rtnl_lock();
 		net_devmem_unbind_dmabuf(binding);
 		rtnl_unlock();

From 10eef096be25f3811ada2b43b108d1b8d8170001 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Tue, 11 Mar 2025 07:40:25 -0700
Subject: [PATCH 2054/2753] net: add granular lock for the netdev netlink
 socket

As we move away from rtnl_lock for queue ops, introduce
per-netdev_nl_sock lock.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Link: https://patch.msgid.link/20250311144026.4154277-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/netdev_netlink.h | 1 +
 net/core/netdev-genl.c       | 6 ++++++
 2 files changed, 7 insertions(+)

diff --git a/include/net/netdev_netlink.h b/include/net/netdev_netlink.h
index 1599573d35c9a..075962dbe743b 100644
--- a/include/net/netdev_netlink.h
+++ b/include/net/netdev_netlink.h
@@ -5,6 +5,7 @@
 #include <linux/list.h>
 
 struct netdev_nl_sock {
+	struct mutex lock;
 	struct list_head bindings;
 };
 
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a219be90c739e..63e10717efc5e 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -859,6 +859,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_genlmsg_free;
 	}
 
+	mutex_lock(&priv->lock);
 	rtnl_lock();
 
 	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
@@ -918,6 +919,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 		goto err_unbind;
 
 	rtnl_unlock();
+	mutex_unlock(&priv->lock);
 
 	return 0;
 
@@ -925,6 +927,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	net_devmem_unbind_dmabuf(binding);
 err_unlock:
 	rtnl_unlock();
+	mutex_unlock(&priv->lock);
 err_genlmsg_free:
 	nlmsg_free(rsp);
 	return err;
@@ -933,6 +936,7 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 void netdev_nl_sock_priv_init(struct netdev_nl_sock *priv)
 {
 	INIT_LIST_HEAD(&priv->bindings);
+	mutex_init(&priv->lock);
 }
 
 void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
@@ -940,11 +944,13 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
 	struct net_devmem_dmabuf_binding *binding;
 	struct net_devmem_dmabuf_binding *temp;
 
+	mutex_lock(&priv->lock);
 	list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
 		rtnl_lock();
 		net_devmem_unbind_dmabuf(binding);
 		rtnl_unlock();
 	}
+	mutex_unlock(&priv->lock);
 }
 
 static int netdev_genl_netdevice_event(struct notifier_block *nb,

From 1d22d3060b9b1f33da617045480c59c4c0511196 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Tue, 11 Mar 2025 07:40:26 -0700
Subject: [PATCH 2055/2753] net: drop rtnl_lock for queue_mgmt operations

All drivers that use queue API are already converted to use
netdev instance lock. Move netdev instance lock management to
the netlink layer and drop rtnl_lock.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Mina Almasry. <almasrymina@google.com>
Link: https://patch.msgid.link/20250311144026.4154277-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c |  4 ++--
 drivers/net/netdevsim/netdev.c            |  4 ++--
 net/core/devmem.c                         |  4 ++--
 net/core/netdev-genl.c                    | 13 ++++++-------
 net/core/netdev_rx_queue.c                | 16 ++++++----------
 5 files changed, 18 insertions(+), 23 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 08ac01d6a5097..d4dc812eb7e24 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -11381,14 +11381,14 @@ static void bnxt_irq_affinity_notify(struct irq_affinity_notify *notify,
 	if (pcie_tph_set_st_entry(irq->bp->pdev, irq->msix_nr, tag))
 		return;
 
-	rtnl_lock();
+	netdev_lock(irq->bp->dev);
 	if (netif_running(irq->bp->dev)) {
 		err = netdev_rx_queue_restart(irq->bp->dev, irq->ring_nr);
 		if (err)
 			netdev_err(irq->bp->dev,
 				   "RX queue restart failed: err=%d\n", err);
 	}
-	rtnl_unlock();
+	netdev_unlock(irq->bp->dev);
 }
 
 static void bnxt_irq_affinity_release(struct kref *ref)
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index d71fd2907cc80..e3152ebe98a23 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -787,7 +787,7 @@ nsim_qreset_write(struct file *file, const char __user *data,
 	if (ret != 2)
 		return -EINVAL;
 
-	rtnl_lock();
+	netdev_lock(ns->netdev);
 	if (queue >= ns->netdev->real_num_rx_queues) {
 		ret = -EINVAL;
 		goto exit_unlock;
@@ -801,7 +801,7 @@ nsim_qreset_write(struct file *file, const char __user *data,
 
 	ret = count;
 exit_unlock:
-	rtnl_unlock();
+	netdev_unlock(ns->netdev);
 	return ret;
 }
 
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 7c6e0b5b6acb5..5c4d79a1bcd82 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -25,7 +25,6 @@
 
 /* Device memory support */
 
-/* Protected by rtnl_lock() */
 static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
 
 static const struct memory_provider_ops dmabuf_devmem_ops;
@@ -128,9 +127,10 @@ void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding)
 		rxq->mp_params.mp_priv = NULL;
 		rxq->mp_params.mp_ops = NULL;
 
+		netdev_lock(binding->dev);
 		rxq_idx = get_netdev_rx_queue_index(rxq);
-
 		WARN_ON(netdev_rx_queue_restart(binding->dev, rxq_idx));
+		netdev_unlock(binding->dev);
 	}
 
 	xa_erase(&net_devmem_dmabuf_bindings, binding->id);
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 63e10717efc5e..a186fea63c09e 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -860,12 +860,11 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	}
 
 	mutex_lock(&priv->lock);
-	rtnl_lock();
 
-	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
 	if (!netdev || !netif_device_present(netdev)) {
 		err = -ENODEV;
-		goto err_unlock;
+		goto err_unlock_sock;
 	}
 
 	if (dev_xdp_prog_count(netdev)) {
@@ -918,7 +917,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 	if (err)
 		goto err_unbind;
 
-	rtnl_unlock();
+	netdev_unlock(netdev);
+
 	mutex_unlock(&priv->lock);
 
 	return 0;
@@ -926,7 +926,8 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)
 err_unbind:
 	net_devmem_unbind_dmabuf(binding);
 err_unlock:
-	rtnl_unlock();
+	netdev_unlock(netdev);
+err_unlock_sock:
 	mutex_unlock(&priv->lock);
 err_genlmsg_free:
 	nlmsg_free(rsp);
@@ -946,9 +947,7 @@ void netdev_nl_sock_priv_destroy(struct netdev_nl_sock *priv)
 
 	mutex_lock(&priv->lock);
 	list_for_each_entry_safe(binding, temp, &priv->bindings, list) {
-		rtnl_lock();
 		net_devmem_unbind_dmabuf(binding);
-		rtnl_unlock();
 	}
 	mutex_unlock(&priv->lock);
 }
diff --git a/net/core/netdev_rx_queue.c b/net/core/netdev_rx_queue.c
index 7419c41fd3cb9..a5b234b33cd5b 100644
--- a/net/core/netdev_rx_queue.c
+++ b/net/core/netdev_rx_queue.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 
 #include <linux/netdevice.h>
+#include <net/netdev_lock.h>
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <net/page_pool/memory_provider.h>
@@ -18,7 +19,7 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	    !qops->ndo_queue_mem_alloc || !qops->ndo_queue_start)
 		return -EOPNOTSUPP;
 
-	ASSERT_RTNL();
+	netdev_assert_locked(dev);
 
 	new_mem = kvzalloc(qops->ndo_queue_mem_size, GFP_KERNEL);
 	if (!new_mem)
@@ -30,8 +31,6 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 		goto err_free_new_mem;
 	}
 
-	netdev_lock(dev);
-
 	err = qops->ndo_queue_mem_alloc(dev, new_mem, rxq_idx);
 	if (err)
 		goto err_free_old_mem;
@@ -54,8 +53,6 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 
 	qops->ndo_queue_mem_free(dev, old_mem);
 
-	netdev_unlock(dev);
-
 	kvfree(old_mem);
 	kvfree(new_mem);
 
@@ -80,7 +77,6 @@ int netdev_rx_queue_restart(struct net_device *dev, unsigned int rxq_idx)
 	qops->ndo_queue_mem_free(dev, new_mem);
 
 err_free_old_mem:
-	netdev_unlock(dev);
 	kvfree(old_mem);
 
 err_free_new_mem:
@@ -118,9 +114,9 @@ int net_mp_open_rxq(struct net_device *dev, unsigned ifq_idx,
 {
 	int ret;
 
-	rtnl_lock();
+	netdev_lock(dev);
 	ret = __net_mp_open_rxq(dev, ifq_idx, p);
-	rtnl_unlock();
+	netdev_unlock(dev);
 	return ret;
 }
 
@@ -153,7 +149,7 @@ static void __net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
 void net_mp_close_rxq(struct net_device *dev, unsigned ifq_idx,
 		      struct pp_memory_provider_params *old_p)
 {
-	rtnl_lock();
+	netdev_lock(dev);
 	__net_mp_close_rxq(dev, ifq_idx, old_p);
-	rtnl_unlock();
+	netdev_unlock(dev);
 }

From e016cf5f39e9c53e274a7b7122a949d8839b8782 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Tue, 11 Mar 2025 10:28:20 +0100
Subject: [PATCH 2056/2753] netdevsim: 'support' multi-buf XDP

Don't error out on large MTU if XDP is multi-buf.
The ping test now tests ping with XDP and high MTU.
netdevsim doesn't actually run the prog (yet?) so
it doesn't matter if the prog was multi-buf..

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://patch.msgid.link/20250311092820.542148-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netdevsim/bpf.c    | 3 ++-
 drivers/net/netdevsim/netdev.c | 3 ++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c
index 608953d4f98da..49537d3c41205 100644
--- a/drivers/net/netdevsim/bpf.c
+++ b/drivers/net/netdevsim/bpf.c
@@ -296,7 +296,8 @@ static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf)
 		NSIM_EA(bpf->extack, "attempt to load offloaded prog to drv");
 		return -EINVAL;
 	}
-	if (ns->netdev->mtu > NSIM_XDP_MAX_MTU) {
+	if (bpf->prog && !bpf->prog->aux->xdp_has_frags &&
+	    ns->netdev->mtu > NSIM_XDP_MAX_MTU) {
 		NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled");
 		return -EINVAL;
 	}
diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c
index e3152ebe98a23..b67af4651185b 100644
--- a/drivers/net/netdevsim/netdev.c
+++ b/drivers/net/netdevsim/netdev.c
@@ -116,7 +116,8 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct netdevsim *ns = netdev_priv(dev);
 
-	if (ns->xdp.prog && new_mtu > NSIM_XDP_MAX_MTU)
+	if (ns->xdp.prog && !ns->xdp.prog->aux->xdp_has_frags &&
+	    new_mtu > NSIM_XDP_MAX_MTU)
 		return -EBUSY;
 
 	WRITE_ONCE(dev->mtu, new_mtu);

From 3df4583ae0cf3c93e4e3d6990566e1f7fe669bdf Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Thu, 6 Mar 2025 10:11:40 +0800
Subject: [PATCH 2057/2753] wifi: rtw89: add support for negative values of dBm
 to linear conversion

Enhanced the dBm to linear conversion function to accommodate negative
dBm values and improved the precision from 1 dBm to 0.25 dBm.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250306021144.12854-2-pkshih@realtek.com
---
 .../wireless/realtek/rtw89/rtw8852b_common.c  |   6 +-
 drivers/net/wireless/realtek/rtw89/util.c     | 215 +++++++++++-------
 drivers/net/wireless/realtek/rtw89/util.h     |   8 +-
 3 files changed, 137 insertions(+), 92 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
index 0e094ce9c9b08..99c9505b3cbd3 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_common.c
@@ -621,9 +621,9 @@ static void rtw8852bt_ext_loss_avg_update(struct rtw89_dev *rtwdev,
 	if (ext_loss_a == ext_loss_b) {
 		ext_loss_avg = ext_loss_a;
 	} else {
-		linear = rtw89_db_2_linear(abs(ext_loss_a - ext_loss_b)) + 1;
-		linear = DIV_ROUND_CLOSEST_ULL(linear / 2, 1 << RTW89_LINEAR_FRAC_BITS);
-		ext_loss_avg = rtw89_linear_2_db(linear);
+		linear = rtw89_db_to_linear(abs(ext_loss_a - ext_loss_b)) + 1;
+		linear /= 2;
+		ext_loss_avg = rtw89_linear_to_db(linear);
 		ext_loss_avg += min(ext_loss_a, ext_loss_b);
 	}
 
diff --git a/drivers/net/wireless/realtek/rtw89/util.c b/drivers/net/wireless/realtek/rtw89/util.c
index 33be268734735..073714db26f24 100644
--- a/drivers/net/wireless/realtek/rtw89/util.c
+++ b/drivers/net/wireless/realtek/rtw89/util.c
@@ -4,106 +4,151 @@
 
 #include "util.h"
 
-#define FRAC_ROWS 3
-#define FRAC_ROW_MAX (FRAC_ROWS - 1)
-#define NORM_ROW_MIN FRAC_ROWS
-
-static const u32 db_invert_table[12][8] = {
-	/* rows 0~2 in unit of U(32,3) */
-	{10, 13, 16, 20, 25, 32, 40, 50},
-	{64, 80, 101, 128, 160, 201, 256, 318},
-	{401, 505, 635, 800, 1007, 1268, 1596, 2010},
-	/* rows 3~11 in unit of U(32,0) */
-	{316, 398, 501, 631, 794, 1000, 1259, 1585},
-	{1995, 2512, 3162, 3981, 5012, 6310, 7943, 10000},
-	{12589, 15849, 19953, 25119, 31623, 39811, 50119, 63098},
-	{79433, 100000, 125893, 158489, 199526, 251189, 316228, 398107},
-	{501187, 630957, 794328, 1000000, 1258925, 1584893, 1995262, 2511886},
-	{3162278, 3981072, 5011872, 6309573, 7943282, 1000000, 12589254,
-	 15848932},
-	{19952623, 25118864, 31622777, 39810717, 50118723, 63095734, 79432823,
-	 100000000},
-	{125892541, 158489319, 199526232, 251188643, 316227766, 398107171,
-	 501187234, 630957345},
-	{794328235, 1000000000, 1258925412, 1584893192, 1995262315, 2511886432U,
-	 3162277660U, 3981071706U},
+#define RTW89_DBM_QUARTER_FACTOR 2
+#define RTW89_MIN_DBM (-41.25 * (1 << RTW89_DBM_QUARTER_FACTOR))
+#define RTW89_MAX_DBM (96 * (1 << RTW89_DBM_QUARTER_FACTOR))
+#define RTW89_DB_INVERT_TABLE_OFFSET (-RTW89_MIN_DBM)
+
+static const u64 db_invert_table[] = {
+	/* in unit of 0.000001 */
+	75, 79, 84, 89, 94, 100, 106, 112, 119, 126, 133, 141, 150, 158, 168, 178, 188,
+	200, 211, 224, 237, 251, 266, 282, 299, 316, 335, 355, 376, 398, 422, 447, 473,
+	501, 531, 562, 596, 631, 668, 708, 750, 794, 841, 891, 944, 1000, 1059, 1122, 1189,
+	1259, 1334, 1413, 1496, 1585, 1679, 1778, 1884, 1995, 2113, 2239, 2371, 2512, 2661,
+	2818, 2985, 3162, 3350, 3548, 3758, 3981, 4217, 4467, 4732, 5012, 5309, 5623, 5957,
+	6310, 6683, 7079, 7499, 7943, 8414, 8913, 9441, 10000, 10593, 11220, 11885, 12589,
+	13335, 14125, 14962, 15849, 16788, 17783, 18836, 19953, 21135, 22387, 23714, 25119,
+	26607, 28184, 29854, 31623, 33497, 35481, 37584, 39811, 42170, 44668, 47315, 50119,
+	53088, 56234, 59566, 63096, 66834, 70795, 74989, 79433, 84140, 89125, 94406, 100000,
+	105925, 112202, 118850, 125893, 133352, 141254, 149624, 158489, 167880, 177828,
+	188365, 199526, 211349, 223872, 237137, 251189, 266073, 281838, 298538, 316228,
+	334965, 354813, 375837, 398107, 421697, 446684, 473151, 501187, 530884, 562341,
+	595662, 630957, 668344, 707946, 749894, 794328, 841395, 891251, 944061, 1000000,
+	1059254, 1122018, 1188502, 1258925, 1333521, 1412538, 1496236, 1584893, 1678804,
+	1778279, 1883649, 1995262, 2113489, 2238721, 2371374, 2511886, 2660725, 2818383,
+	2985383, 3162278, 3349654, 3548134, 3758374, 3981072, 4216965, 4466836, 4731513,
+	5011872, 5308844, 5623413, 5956621, 6309573, 6683439, 7079458, 7498942, 7943282,
+	8413951, 8912509, 9440609, 10000000, 10592537, 11220185, 11885022, 12589254,
+	13335214, 14125375, 14962357, 15848932, 16788040, 17782794, 18836491, 19952623,
+	21134890, 22387211, 23713737, 25118864, 26607251, 28183829, 29853826, 31622777,
+	33496544, 35481339, 37583740, 39810717, 42169650, 44668359, 47315126, 50118723,
+	53088444, 56234133, 59566214, 63095734, 66834392, 70794578, 74989421, 79432823,
+	84139514, 89125094, 94406088, 100000000, 105925373, 112201845, 118850223, 125892541,
+	133352143, 141253754, 149623566, 158489319, 167880402, 177827941, 188364909, 199526231,
+	211348904, 223872114, 237137371, 251188643, 266072506, 281838293, 298538262, 316227766,
+	334965439, 354813389, 375837404, 398107171, 421696503, 446683592, 473151259, 501187234,
+	530884444, 562341325, 595662144, 630957344, 668343918, 707945784, 749894209, 794328235,
+	841395142, 891250938, 944060876, 1000000000, 1059253725, 1122018454, 1188502227,
+	1258925412, 1333521432, 1412537545, 1496235656, 1584893192, 1678804018, 1778279410,
+	1883649089, 1995262315, 2113489040, 2238721139, 2371373706, 2511886432, 2660725060,
+	2818382931, 2985382619, 3162277660, 3349654392, 3548133892, 3758374043, 3981071706,
+	4216965034, 4466835922ULL, 4731512590ULL, 5011872336ULL, 5308844442ULL, 5623413252ULL,
+	5956621435ULL, 6309573445ULL, 6683439176ULL, 7079457844ULL, 7498942093ULL,
+	7943282347ULL, 8413951416ULL, 8912509381ULL, 9440608763ULL, 10000000000ULL,
+	10592537252ULL, 11220184543ULL, 11885022274ULL, 12589254118ULL, 13335214322ULL,
+	14125375446ULL, 14962356561ULL, 15848931925ULL, 16788040181ULL, 17782794100ULL,
+	18836490895ULL, 19952623150ULL, 21134890398ULL, 22387211386ULL, 23713737057ULL,
+	25118864315ULL, 26607250598ULL, 28183829313ULL, 29853826189ULL, 31622776602ULL,
+	33496543916ULL, 35481338923ULL, 37583740429ULL, 39810717055ULL, 42169650343ULL,
+	44668359215ULL, 47315125896ULL, 50118723363ULL, 53088444423ULL, 56234132519ULL,
+	59566214353ULL, 63095734448ULL, 66834391757ULL, 70794578438ULL, 74989420933ULL,
+	79432823472ULL, 84139514165ULL, 89125093813ULL, 94406087629ULL, 100000000000ULL,
+	105925372518ULL, 112201845430ULL, 118850222744ULL, 125892541179ULL, 133352143216ULL,
+	141253754462ULL, 149623565609ULL, 158489319246ULL, 167880401812ULL, 177827941004ULL,
+	188364908949ULL, 199526231497ULL, 211348903984ULL, 223872113857ULL, 237137370566ULL,
+	251188643151ULL, 266072505980ULL, 281838293126ULL, 298538261892ULL, 316227766017ULL,
+	334965439158ULL, 354813389234ULL, 375837404288ULL, 398107170553ULL, 421696503429ULL,
+	446683592151ULL, 473151258961ULL, 501187233627ULL, 530884444231ULL, 562341325190ULL,
+	595662143529ULL, 630957344480ULL, 668343917569ULL, 707945784384ULL, 749894209332ULL,
+	794328234724ULL, 841395141645ULL, 891250938134ULL, 944060876286ULL, 1000000000000ULL,
+	1059253725177ULL, 1122018454302ULL, 1188502227437ULL, 1258925411794ULL,
+	1333521432163ULL, 1412537544623ULL, 1496235656094ULL, 1584893192461ULL,
+	1678804018123ULL, 1778279410039ULL, 1883649089490ULL, 1995262314969ULL,
+	2113489039837ULL, 2238721138568ULL, 2371373705662ULL, 2511886431510ULL,
+	2660725059799ULL, 2818382931264ULL, 2985382618918ULL, 3162277660168ULL,
+	3349654391578ULL, 3548133892336ULL, 3758374042884ULL, 3981071705535ULL,
+	4216965034286ULL, 4466835921510ULL, 4731512589615ULL, 5011872336273ULL,
+	5308844442310ULL, 5623413251904ULL, 5956621435290ULL, 6309573444802ULL,
+	6683439175686ULL, 7079457843841ULL, 7498942093325ULL, 7943282347243ULL,
+	8413951416452ULL, 8912509381337ULL, 9440608762859ULL, 10000000000000ULL,
+	10592537251773ULL, 11220184543020ULL, 11885022274370ULL, 12589254117942ULL,
+	13335214321633ULL, 14125375446228ULL, 14962356560944ULL, 15848931924611ULL,
+	16788040181226ULL, 17782794100389ULL, 18836490894898ULL, 19952623149689ULL,
+	21134890398367ULL, 22387211385683ULL, 23713737056617ULL, 25118864315096ULL,
+	26607250597988ULL, 28183829312645ULL, 29853826189180ULL, 31622776601684ULL,
+	33496543915783ULL, 35481338923358ULL, 37583740428845ULL, 39810717055350ULL,
+	42169650342858ULL, 44668359215096ULL, 47315125896148ULL, 50118723362727ULL,
+	53088444423099ULL, 56234132519035ULL, 59566214352901ULL, 63095734448019ULL,
+	66834391756862ULL, 70794578438414ULL, 74989420933246ULL, 79432823472428ULL,
+	84139514164520ULL, 89125093813375ULL, 94406087628593ULL, 100000000000000ULL,
+	105925372517729ULL, 112201845430197ULL, 118850222743702ULL, 125892541179417ULL,
+	133352143216332ULL, 141253754462276ULL, 149623565609444ULL, 158489319246111ULL,
+	167880401812256ULL, 177827941003893ULL, 188364908948981ULL, 199526231496888ULL,
+	211348903983664ULL, 223872113856834ULL, 237137370566166ULL, 251188643150958ULL,
+	266072505979882ULL, 281838293126446ULL, 298538261891796ULL, 316227766016838ULL,
+	334965439157829ULL, 354813389233577ULL, 375837404288444ULL, 398107170553497ULL,
+	421696503428583ULL, 446683592150964ULL, 473151258961482ULL, 501187233627272ULL,
+	530884444230989ULL, 562341325190350ULL, 595662143529011ULL, 630957344480196ULL,
+	668343917568615ULL, 707945784384138ULL, 749894209332456ULL, 794328234724284ULL,
+	841395141645198ULL, 891250938133745ULL, 944060876285923ULL, 1000000000000000ULL,
+	1059253725177290ULL, 1122018454301970ULL, 1188502227437020ULL, 1258925411794170ULL,
+	1333521432163330ULL, 1412537544622760ULL, 1496235656094440ULL, 1584893192461110ULL,
+	1678804018122560ULL, 1778279410038920ULL, 1883649089489810ULL, 1995262314968890ULL,
+	2113489039836650ULL, 2238721138568340ULL, 2371373705661660ULL, 2511886431509590ULL,
+	2660725059798820ULL, 2818382931264460ULL, 2985382618917960ULL, 3162277660168380ULL,
+	3349654391578280ULL, 3548133892335770ULL, 3758374042884440ULL, 3981071705534970ULL
 };
 
-u32 rtw89_linear_2_db(u64 val)
+s32 rtw89_linear_to_db_quarter(u64 val)
 {
-	u8 i, j;
-	u32 dB;
-
-	for (i = 0; i < 12; i++) {
-		for (j = 0; j < 8; j++) {
-			if (i <= FRAC_ROW_MAX &&
-			    (val << RTW89_LINEAR_FRAC_BITS) <= db_invert_table[i][j])
-				goto cnt;
-			else if (i > FRAC_ROW_MAX && val <= db_invert_table[i][j])
-				goto cnt;
-		}
-	}
+	int r = ARRAY_SIZE(db_invert_table) - 1;
+	int l = 0;
+	int m;
 
-	return 96; /* maximum 96 dB */
-
-cnt:
-	/* special cases */
-	if (j == 0 && i == 0)
-		goto end;
-
-	if (i == NORM_ROW_MIN && j == 0) {
-		if (db_invert_table[NORM_ROW_MIN][0] - val >
-		    val - (db_invert_table[FRAC_ROW_MAX][7] >> RTW89_LINEAR_FRAC_BITS)) {
-			i = FRAC_ROW_MAX;
-			j = 7;
-		}
-		goto end;
-	}
+	while (l <= r) {
+		m = l + (r - l) / 2;
 
-	if (i <= FRAC_ROW_MAX)
-		val <<= RTW89_LINEAR_FRAC_BITS;
+		if (db_invert_table[m] == val)
+			return m - (s32)RTW89_DB_INVERT_TABLE_OFFSET;
 
-	/* compare difference to get precise dB */
-	if (j == 0) {
-		if (db_invert_table[i][j] - val >
-		    val - db_invert_table[i - 1][7]) {
-			i--;
-			j = 7;
-		}
-	} else {
-		if (db_invert_table[i][j] - val >
-		    val - db_invert_table[i][j - 1]) {
-			j--;
-		}
+		if (db_invert_table[m] > val)
+			r = m - 1;
+		else
+			l = m + 1;
 	}
-end:
-	dB = (i << 3) + j + 1;
 
-	return dB;
+	if (l >= ARRAY_SIZE(db_invert_table))
+		return RTW89_MAX_DBM;
+	else if (r < 0)
+		return RTW89_MIN_DBM;
+	else if (val - db_invert_table[r] <= db_invert_table[l] - val)
+		return r - (s32)RTW89_DB_INVERT_TABLE_OFFSET;
+	else
+		return l - (s32)RTW89_DB_INVERT_TABLE_OFFSET;
 }
-EXPORT_SYMBOL(rtw89_linear_2_db);
+EXPORT_SYMBOL(rtw89_linear_to_db_quarter);
 
-u64 rtw89_db_2_linear(u32 db)
+s32 rtw89_linear_to_db(u64 val)
 {
-	u64 linear;
-	u8 i, j;
-
-	if (db > 96)
-		db = 96;
-	else if (db < 1)
-		return 1;
-
-	i = (db - 1) >> 3;
-	j = (db - 1) & 0x7;
+	return rtw89_linear_to_db_quarter(val) >> RTW89_DBM_QUARTER_FACTOR;
+}
+EXPORT_SYMBOL(rtw89_linear_to_db);
 
-	linear = db_invert_table[i][j];
+u64 rtw89_db_quarter_to_linear(s32 db)
+{
+	/* supported range -41.25 to 96 dBm, in unit of 0.25 dBm */
+	db = clamp_t(s32, db, RTW89_MIN_DBM, RTW89_MAX_DBM);
+	db += (s32)RTW89_DB_INVERT_TABLE_OFFSET;
 
-	if (i >= NORM_ROW_MIN)
-		linear = linear << RTW89_LINEAR_FRAC_BITS;
+	return db_invert_table[db];
+}
+EXPORT_SYMBOL(rtw89_db_quarter_to_linear);
 
-	return linear;
+u64 rtw89_db_to_linear(s32 db)
+{
+	return rtw89_db_quarter_to_linear(db << RTW89_DBM_QUARTER_FACTOR);
 }
-EXPORT_SYMBOL(rtw89_db_2_linear);
+EXPORT_SYMBOL(rtw89_db_to_linear);
 
 void rtw89_might_trailing_ellipsis(char *buf, size_t size, ssize_t used)
 {
diff --git a/drivers/net/wireless/realtek/rtw89/util.h b/drivers/net/wireless/realtek/rtw89/util.h
index 80441e8da60bb..bd08495301e45 100644
--- a/drivers/net/wireless/realtek/rtw89/util.h
+++ b/drivers/net/wireless/realtek/rtw89/util.h
@@ -6,8 +6,6 @@
 
 #include "core.h"
 
-#define RTW89_LINEAR_FRAC_BITS 3
-
 #define rtw89_iterate_vifs_bh(rtwdev, iterator, data)                          \
 	ieee80211_iterate_active_interfaces_atomic((rtwdev)->hw,               \
 			IEEE80211_IFACE_ITER_NORMAL, iterator, data)
@@ -75,8 +73,10 @@ static inline void ether_addr_copy_mask(u8 *dst, const u8 *src, u8 mask)
 	}
 }
 
-u32 rtw89_linear_2_db(u64 linear);
-u64 rtw89_db_2_linear(u32 db);
+s32 rtw89_linear_to_db_quarter(u64 val);
+s32 rtw89_linear_to_db(u64 val);
+u64 rtw89_db_quarter_to_linear(s32 db);
+u64 rtw89_db_to_linear(s32 db);
 void rtw89_might_trailing_ellipsis(char *buf, size_t size, ssize_t used);
 
 #endif

From 8ef675fc797b69aee6d729c6e191b7d3a6e2714e Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Thu, 6 Mar 2025 10:11:41 +0800
Subject: [PATCH 2058/2753] wifi: rtw89: refine mechanism of TAS

TAS state switching mechanism now incorporates the TX ratio as a
decision parameter. The average power calculation has been improved
by using a higher resolution conversion from dBm to linear. During
scan or MCC operations, TAS state is forced to static SAR and
suspend the average power calculation. Additionally, TAS window
size depends on the regulatory domain and band to ensure compliance.

TAS is enabled when permitted by the regulatory domain and is
currently supported on the 8852CE.

For debugging, add a flag to disable_dm that can stop TAS mechanism.

Co-developed-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Zong-Zhe Yang <kevin_yang@realtek.com>
Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250306021144.12854-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/chan.c     |  10 +-
 drivers/net/wireless/realtek/rtw89/core.c     |   4 +-
 drivers/net/wireless/realtek/rtw89/core.h     |  28 +-
 drivers/net/wireless/realtek/rtw89/debug.c    |   1 +
 drivers/net/wireless/realtek/rtw89/fw.h       |   6 +
 drivers/net/wireless/realtek/rtw89/phy.c      |  24 ++
 drivers/net/wireless/realtek/rtw89/regd.c     |  13 +
 drivers/net/wireless/realtek/rtw89/rtw8851b.c |   1 +
 drivers/net/wireless/realtek/rtw89/rtw8852a.c |   1 +
 drivers/net/wireless/realtek/rtw89/rtw8852b.c |   1 +
 .../net/wireless/realtek/rtw89/rtw8852bt.c    |   1 +
 drivers/net/wireless/realtek/rtw89/rtw8852c.c |   3 +
 drivers/net/wireless/realtek/rtw89/rtw8922a.c |   1 +
 drivers/net/wireless/realtek/rtw89/sar.c      | 369 ++++++++++++++----
 drivers/net/wireless/realtek/rtw89/sar.h      |   5 +-
 15 files changed, 377 insertions(+), 91 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/chan.c b/drivers/net/wireless/realtek/rtw89/chan.c
index be6d732739104..f60e93870b093 100644
--- a/drivers/net/wireless/realtek/rtw89/chan.c
+++ b/drivers/net/wireless/realtek/rtw89/chan.c
@@ -8,6 +8,7 @@
 #include "fw.h"
 #include "mac.h"
 #include "ps.h"
+#include "sar.h"
 #include "util.h"
 
 static void rtw89_swap_chanctx(struct rtw89_dev *rtwdev,
@@ -2673,6 +2674,7 @@ int rtw89_chanctx_ops_assign_vif(struct rtw89_dev *rtwdev,
 	struct rtw89_hal *hal = &rtwdev->hal;
 	struct rtw89_entity_mgnt *mgnt = &hal->entity_mgnt;
 	struct rtw89_entity_weight w = {};
+	int ret;
 
 	rtwvif_link->chanctx_idx = cfg->idx;
 	rtwvif_link->chanctx_assigned = true;
@@ -2692,7 +2694,13 @@ int rtw89_chanctx_ops_assign_vif(struct rtw89_dev *rtwdev,
 	rtw89_swap_chanctx(rtwdev, cfg->idx, RTW89_CHANCTX_0);
 
 out:
-	return rtw89_set_channel(rtwdev);
+	ret = rtw89_set_channel(rtwdev);
+	if (ret)
+		return ret;
+
+	rtw89_tas_reset(rtwdev, true);
+
+	return 0;
 }
 
 void rtw89_chanctx_ops_unassign_vif(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
index 4d286182e21d6..cc9b014457ace 100644
--- a/drivers/net/wireless/realtek/rtw89/core.c
+++ b/drivers/net/wireless/realtek/rtw89/core.c
@@ -4601,8 +4601,6 @@ int rtw89_core_start(struct rtw89_dev *rtwdev)
 	rtw89_mac_cfg_phy_rpt_bands(rtwdev, true);
 	rtw89_mac_update_rts_threshold(rtwdev);
 
-	rtw89_tas_reset(rtwdev);
-
 	ret = rtw89_hci_start(rtwdev);
 	if (ret) {
 		rtw89_err(rtwdev, "failed to start hci\n");
@@ -4956,6 +4954,7 @@ void rtw89_core_scan_start(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwv
 	rtw89_chip_rfk_scan(rtwdev, rtwvif_link, true);
 	rtw89_hci_recalc_int_mit(rtwdev);
 	rtw89_phy_config_edcca(rtwdev, bb, true);
+	rtw89_tas_scan(rtwdev, true);
 
 	rtw89_fw_h2c_cam(rtwdev, rtwvif_link, NULL, mac_addr);
 }
@@ -4982,6 +4981,7 @@ void rtw89_core_scan_complete(struct rtw89_dev *rtwdev,
 	rtw89_btc_ntfy_scan_finish(rtwdev, rtwvif_link->phy_idx);
 	bb = rtw89_get_bb_ctx(rtwdev, rtwvif_link->phy_idx);
 	rtw89_phy_config_edcca(rtwdev, bb, false);
+	rtw89_tas_scan(rtwdev, false);
 
 	rtwdev->scanning = false;
 	rtw89_for_each_active_bb(rtwdev, bb)
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 3f62df657e1fd..074c865e6d03f 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4240,6 +4240,7 @@ enum rtw89_chanctx_state {
 enum rtw89_chanctx_callbacks {
 	RTW89_CHANCTX_CALLBACK_PLACEHOLDER,
 	RTW89_CHANCTX_CALLBACK_RFK,
+	RTW89_CHANCTX_CALLBACK_TAS,
 
 	NUM_OF_RTW89_CHANCTX_CALLBACKS,
 };
@@ -4281,6 +4282,7 @@ struct rtw89_chip_info {
 	bool support_unii4;
 	bool support_rnr;
 	bool support_ant_gain;
+	bool support_tas;
 	bool ul_tb_waveform_ctrl;
 	bool ul_tb_pwr_diff;
 	bool rx_freq_frome_ie;
@@ -4679,18 +4681,29 @@ struct rtw89_6ghz_span {
 enum rtw89_tas_state {
 	RTW89_TAS_STATE_DPR_OFF,
 	RTW89_TAS_STATE_DPR_ON,
-	RTW89_TAS_STATE_DPR_FORBID,
+	RTW89_TAS_STATE_STATIC_SAR,
 };
 
-#define RTW89_TAS_MAX_WINDOW 50
+#define RTW89_TAS_TX_RATIO_WINDOW 6
+#define RTW89_TAS_TXPWR_WINDOW 180
 struct rtw89_tas_info {
-	s16 txpwr_history[RTW89_TAS_MAX_WINDOW];
-	s32 total_txpwr;
-	u8 cur_idx;
-	s8 dpr_gap;
-	s8 delta;
+	u16 tx_ratio_history[RTW89_TAS_TX_RATIO_WINDOW];
+	u64 txpwr_history[RTW89_TAS_TXPWR_WINDOW];
+	u8 txpwr_head_idx;
+	u8 txpwr_tail_idx;
+	u8 tx_ratio_idx;
+	u16 total_tx_ratio;
+	u64 total_txpwr;
+	u64 instant_txpwr;
+	u32 window_size;
+	s8 dpr_on_threshold;
+	s8 dpr_off_threshold;
+	enum rtw89_tas_state backup_state;
 	enum rtw89_tas_state state;
+	bool keep_history;
+	bool block_regd;
 	bool enable;
+	bool pause;
 };
 
 struct rtw89_chanctx_cfg {
@@ -4748,6 +4761,7 @@ struct rtw89_edcca_bak {
 enum rtw89_dm_type {
 	RTW89_DM_DYNAMIC_EDCCA,
 	RTW89_DM_THERMAL_PROTECT,
+	RTW89_DM_TAS,
 };
 
 #define RTW89_THERMAL_PROT_LV_MAX 5
diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
index 885a5ebeb6cd5..f2c5753fd3864 100644
--- a/drivers/net/wireless/realtek/rtw89/debug.c
+++ b/drivers/net/wireless/realtek/rtw89/debug.c
@@ -4154,6 +4154,7 @@ static const struct rtw89_disabled_dm_info {
 } rtw89_disabled_dm_infos[] = {
 	DM_INFO(DYNAMIC_EDCCA),
 	DM_INFO(THERMAL_PROTECT),
+	DM_INFO(TAS),
 };
 
 static ssize_t
diff --git a/drivers/net/wireless/realtek/rtw89/fw.h b/drivers/net/wireless/realtek/rtw89/fw.h
index e0faed0761509..55255b48bdb71 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.h
+++ b/drivers/net/wireless/realtek/rtw89/fw.h
@@ -4543,6 +4543,12 @@ struct rtw89_c2h_rfk_report {
 	u8 version;
 } __packed;
 
+struct rtw89_c2h_rf_tas_info {
+	struct rtw89_c2h_hdr hdr;
+	__le32 cur_idx;
+	__le16 txpwr_history[20];
+} __packed;
+
 #define RTW89_FW_RSVD_PLE_SIZE 0x800
 
 #define RTW89_FW_BACKTRACE_INFO_SIZE 8
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index e4b690a5febc9..abc2a7e989eb8 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -3459,6 +3459,30 @@ rtw89_phy_c2h_rfk_report_state(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u3
 static void
 rtw89_phy_c2h_rfk_log_tas_pwr(struct rtw89_dev *rtwdev, struct sk_buff *c2h, u32 len)
 {
+	const struct rtw89_c2h_rf_tas_info *rf_tas =
+		(const struct rtw89_c2h_rf_tas_info *)c2h->data;
+	const enum rtw89_sar_sources src = rtwdev->sar.src;
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	u64 linear = 0;
+	u32 i, cur_idx;
+	s16 txpwr;
+
+	if (!tas->enable || src == RTW89_SAR_SOURCE_NONE)
+		return;
+
+	cur_idx = le32_to_cpu(rf_tas->cur_idx);
+	for (i = 0; i < cur_idx; i++) {
+		txpwr = (s16)le16_to_cpu(rf_tas->txpwr_history[i]);
+		linear += rtw89_db_quarter_to_linear(txpwr);
+
+		rtw89_debug(rtwdev, RTW89_DBG_SAR,
+			    "tas: index: %u, txpwr: %d\n", i, txpwr);
+	}
+
+	if (cur_idx == 0)
+		tas->instant_txpwr = rtw89_db_to_linear(0);
+	else
+		tas->instant_txpwr = DIV_ROUND_DOWN_ULL(linear, cur_idx);
 }
 
 static
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index 0e67d0f128ddc..d31403f9009ee 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -721,6 +721,18 @@ static void rtw89_regd_apply_policy_6ghz(struct rtw89_dev *rtwdev,
 		sband->channels[i].flags |= IEEE80211_CHAN_DISABLED;
 }
 
+static void rtw89_regd_apply_policy_tas(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	const struct rtw89_regd *regd = regulatory->regd;
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+
+	if (!tas->enable)
+		return;
+
+	tas->block_regd = !test_bit(RTW89_REGD_FUNC_TAS, regd->func_bitmap);
+}
+
 static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 				      struct wiphy *wiphy,
 				      struct regulatory_request *request)
@@ -738,6 +750,7 @@ static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 
 	rtw89_regd_apply_policy_unii4(rtwdev, wiphy);
 	rtw89_regd_apply_policy_6ghz(rtwdev, wiphy);
+	rtw89_regd_apply_policy_tas(rtwdev);
 }
 
 static
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8851b.c b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
index b709dd71b06a2..0d482cd57f6eb 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8851b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8851b.c
@@ -2498,6 +2498,7 @@ const struct rtw89_chip_info rtw8851b_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_80),
 	.support_unii4		= true,
 	.support_ant_gain	= false,
+	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852a.c b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
index 638236bffebb5..286334e26c842 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852a.c
@@ -2216,6 +2216,7 @@ const struct rtw89_chip_info rtw8852a_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_80),
 	.support_unii4		= false,
 	.support_ant_gain	= false,
+	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
index 8bec74716f84a..eceb4fb9880d0 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
@@ -852,6 +852,7 @@ const struct rtw89_chip_info rtw8852b_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_80),
 	.support_unii4		= true,
 	.support_ant_gain	= true,
+	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
index e628106600054..bbf37442c4921 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852bt.c
@@ -785,6 +785,7 @@ const struct rtw89_chip_info rtw8852bt_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_80),
 	.support_unii4		= true,
 	.support_ant_gain	= true,
+	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= true,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= true,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852c.c b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
index 5d3e105dc87fc..08bcdf2463827 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8852c.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8852c.c
@@ -12,6 +12,7 @@
 #include "rtw8852c.h"
 #include "rtw8852c_rfk.h"
 #include "rtw8852c_table.h"
+#include "sar.h"
 #include "util.h"
 
 #define RTW8852C_FW_FORMAT_MAX 1
@@ -2880,6 +2881,7 @@ static int rtw8852c_mac_disable_bb_rf(struct rtw89_dev *rtwdev)
 
 static const struct rtw89_chanctx_listener rtw8852c_chanctx_listener = {
 	.callbacks[RTW89_CHANCTX_CALLBACK_RFK] = rtw8852c_rfk_chanctx_cb,
+	.callbacks[RTW89_CHANCTX_CALLBACK_TAS] = rtw89_tas_chanctx_cb,
 };
 
 #ifdef CONFIG_PM
@@ -3011,6 +3013,7 @@ const struct rtw89_chip_info rtw8852c_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_160),
 	.support_unii4		= true,
 	.support_ant_gain	= true,
+	.support_tas		= true,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= true,
 	.rx_freq_frome_ie	= false,
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index 210fa818ffe8f..d90af2daebcf7 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2770,6 +2770,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_160),
 	.support_unii4		= true,
 	.support_ant_gain	= false,
+	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,
 	.rx_freq_frome_ie	= false,
diff --git a/drivers/net/wireless/realtek/rtw89/sar.c b/drivers/net/wireless/realtek/rtw89/sar.c
index 24a32dc4e67d9..0b5af95287022 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.c
+++ b/drivers/net/wireless/realtek/rtw89/sar.c
@@ -7,10 +7,16 @@
 #include "phy.h"
 #include "reg.h"
 #include "sar.h"
+#include "util.h"
 
 #define RTW89_TAS_FACTOR 2 /* unit: 0.25 dBm */
+#define RTW89_TAS_SAR_GAP (1 << RTW89_TAS_FACTOR)
 #define RTW89_TAS_DPR_GAP (1 << RTW89_TAS_FACTOR)
 #define RTW89_TAS_DELTA (2 << RTW89_TAS_FACTOR)
+#define RTW89_TAS_TX_RATIO_THRESHOLD 70
+#define RTW89_TAS_DFLT_TX_RATIO 80
+#define RTW89_TAS_DPR_ON_OFFSET (RTW89_TAS_DELTA + RTW89_TAS_SAR_GAP)
+#define RTW89_TAS_DPR_OFF_OFFSET (4 << RTW89_TAS_FACTOR)
 
 static enum rtw89_sar_subband rtw89_sar_get_subband(struct rtw89_dev *rtwdev,
 						    u32 center_freq)
@@ -117,8 +123,8 @@ static s8 rtw89_txpwr_sar_to_mac(struct rtw89_dev *rtwdev, u8 fct, s32 cfg)
 			   RTW89_SAR_TXPWR_MAC_MAX);
 }
 
-static s8 rtw89_txpwr_tas_to_sar(const struct rtw89_sar_handler *sar_hdl,
-				 s8 cfg)
+static s32 rtw89_txpwr_tas_to_sar(const struct rtw89_sar_handler *sar_hdl,
+				  s32 cfg)
 {
 	const u8 fct = sar_hdl->txpwr_factor_sar;
 
@@ -128,8 +134,8 @@ static s8 rtw89_txpwr_tas_to_sar(const struct rtw89_sar_handler *sar_hdl,
 		return cfg >> (RTW89_TAS_FACTOR - fct);
 }
 
-static s8 rtw89_txpwr_sar_to_tas(const struct rtw89_sar_handler *sar_hdl,
-				 s8 cfg)
+static s32 rtw89_txpwr_sar_to_tas(const struct rtw89_sar_handler *sar_hdl,
+				  s32 cfg)
 {
 	const u8 fct = sar_hdl->txpwr_factor_sar;
 
@@ -139,13 +145,43 @@ static s8 rtw89_txpwr_sar_to_tas(const struct rtw89_sar_handler *sar_hdl,
 		return cfg << (RTW89_TAS_FACTOR - fct);
 }
 
+static bool rtw89_tas_is_active(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	struct rtw89_vif *rtwvif;
+
+	if (!tas->enable)
+		return false;
+
+	rtw89_for_each_rtwvif(rtwdev, rtwvif) {
+		if (ieee80211_vif_is_mld(rtwvif_to_vif(rtwvif)))
+			return false;
+	}
+
+	return true;
+}
+
+static const char *rtw89_tas_state_str(enum rtw89_tas_state state)
+{
+	switch (state) {
+	case RTW89_TAS_STATE_DPR_OFF:
+		return "DPR OFF";
+	case RTW89_TAS_STATE_DPR_ON:
+		return "DPR ON";
+	case RTW89_TAS_STATE_STATIC_SAR:
+		return "STATIC SAR";
+	default:
+		return NULL;
+	}
+}
+
 s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 {
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
 	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
 	struct rtw89_tas_info *tas = &rtwdev->tas;
-	s8 delta;
+	s32 offset;
 	int ret;
 	s32 cfg;
 	u8 fct;
@@ -159,15 +195,17 @@ s8 rtw89_query_sar(struct rtw89_dev *rtwdev, u32 center_freq)
 	if (ret)
 		return RTW89_SAR_TXPWR_MAC_MAX;
 
-	if (tas->enable) {
+	if (rtw89_tas_is_active(rtwdev)) {
 		switch (tas->state) {
 		case RTW89_TAS_STATE_DPR_OFF:
-			return RTW89_SAR_TXPWR_MAC_MAX;
+			offset = rtw89_txpwr_tas_to_sar(sar_hdl, RTW89_TAS_DPR_OFF_OFFSET);
+			cfg += offset;
+			break;
 		case RTW89_TAS_STATE_DPR_ON:
-			delta = rtw89_txpwr_tas_to_sar(sar_hdl, tas->delta);
-			cfg -= delta;
+			offset = rtw89_txpwr_tas_to_sar(sar_hdl, RTW89_TAS_DPR_ON_OFFSET);
+			cfg -= offset;
 			break;
-		case RTW89_TAS_STATE_DPR_FORBID:
+		case RTW89_TAS_STATE_STATIC_SAR:
 		default:
 			break;
 		}
@@ -223,13 +261,23 @@ int rtw89_print_tas(struct rtw89_dev *rtwdev, char *buf, size_t bufsz)
 	struct rtw89_tas_info *tas = &rtwdev->tas;
 	char *p = buf, *end = buf + bufsz;
 
-	if (!tas->enable) {
+	if (!rtw89_tas_is_active(rtwdev)) {
 		p += scnprintf(p, end - p, "no TAS is applied\n");
 		goto out;
 	}
 
-	p += scnprintf(p, end - p, "DPR gap: %d\n", tas->dpr_gap);
-	p += scnprintf(p, end - p, "TAS delta: %d\n", tas->delta);
+	p += scnprintf(p, end - p, "State: %s\n",
+		       rtw89_tas_state_str(tas->state));
+	p += scnprintf(p, end - p, "Average time: %d\n",
+		       tas->window_size * 2);
+	p += scnprintf(p, end - p, "SAR gap: %d dBm\n",
+		       RTW89_TAS_SAR_GAP >> RTW89_TAS_FACTOR);
+	p += scnprintf(p, end - p, "DPR gap: %d dBm\n",
+		       RTW89_TAS_DPR_GAP >> RTW89_TAS_FACTOR);
+	p += scnprintf(p, end - p, "DPR ON offset: %d dBm\n",
+		       RTW89_TAS_DPR_ON_OFFSET >> RTW89_TAS_FACTOR);
+	p += scnprintf(p, end - p, "DPR OFF offset: %d dBm\n",
+		       RTW89_TAS_DPR_OFF_OFFSET >> RTW89_TAS_FACTOR);
 
 out:
 	return p - buf;
@@ -250,6 +298,7 @@ static int rtw89_apply_sar_common(struct rtw89_dev *rtwdev,
 
 	rtw89_sar_set_src(rtwdev, RTW89_SAR_SOURCE_COMMON, cfg_common, sar);
 	rtw89_core_set_chip_txpwr(rtwdev);
+	rtw89_tas_reset(rtwdev, false);
 
 	return 0;
 }
@@ -314,65 +363,174 @@ int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 	return rtw89_apply_sar_common(rtwdev, &sar_common);
 }
 
-static void rtw89_tas_state_update(struct rtw89_dev *rtwdev)
+static bool rtw89_tas_query_sar_config(struct rtw89_dev *rtwdev, s32 *cfg)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	const enum rtw89_sar_sources src = rtwdev->sar.src;
 	/* its members are protected by rtw89_sar_set_src() */
 	const struct rtw89_sar_handler *sar_hdl = &rtw89_sar_handlers[src];
-	struct rtw89_tas_info *tas = &rtwdev->tas;
-	s32 txpwr_avg = tas->total_txpwr / RTW89_TAS_MAX_WINDOW / PERCENT;
-	s32 dpr_on_threshold, dpr_off_threshold, cfg;
-	enum rtw89_tas_state state = tas->state;
-	const struct rtw89_chan *chan;
 	int ret;
 
-	lockdep_assert_wiphy(rtwdev->hw->wiphy);
-
 	if (src == RTW89_SAR_SOURCE_NONE)
-		return;
+		return false;
 
-	chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
-	ret = sar_hdl->query_sar_config(rtwdev, chan->freq, &cfg);
+	ret = sar_hdl->query_sar_config(rtwdev, chan->freq, cfg);
 	if (ret)
+		return false;
+
+	*cfg = rtw89_txpwr_sar_to_tas(sar_hdl, *cfg);
+
+	return true;
+}
+
+static void rtw89_tas_state_update(struct rtw89_dev *rtwdev,
+				   enum rtw89_tas_state state)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+
+	if (tas->state == state)
 		return;
 
-	cfg = rtw89_txpwr_sar_to_tas(sar_hdl, cfg);
+	rtw89_debug(rtwdev, RTW89_DBG_SAR, "tas: switch state: %s -> %s\n",
+		    rtw89_tas_state_str(tas->state), rtw89_tas_state_str(state));
+
+	tas->state = state;
+	rtw89_core_set_chip_txpwr(rtwdev);
+}
 
-	if (tas->delta >= cfg) {
+static u32 rtw89_tas_get_window_size(struct rtw89_dev *rtwdev)
+{
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
+	u8 band = chan->band_type;
+	u8 regd = rtw89_regd_get(rtwdev, band);
+
+	switch (regd) {
+	default:
 		rtw89_debug(rtwdev, RTW89_DBG_SAR,
-			    "TAS delta exceed SAR limit\n");
-		state = RTW89_TAS_STATE_DPR_FORBID;
-		goto out;
+			    "tas: regd: %u is unhandled\n", regd);
+		fallthrough;
+	case RTW89_IC:
+	case RTW89_KCC:
+		return 180;
+	case RTW89_FCC:
+		switch (band) {
+		case RTW89_BAND_2G:
+			return 50;
+		case RTW89_BAND_5G:
+			return 30;
+		case RTW89_BAND_6G:
+		default:
+			return 15;
+		}
+		break;
 	}
+}
+
+static void rtw89_tas_window_update(struct rtw89_dev *rtwdev)
+{
+	u32 window_size = rtw89_tas_get_window_size(rtwdev);
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	u64 total_txpwr = 0;
+	u8 head_idx;
+	u32 i, j;
+
+	WARN_ON_ONCE(tas->window_size > RTW89_TAS_TXPWR_WINDOW);
+
+	if (tas->window_size == window_size)
+		return;
+
+	rtw89_debug(rtwdev, RTW89_DBG_SAR, "tas: window update: %u -> %u\n",
+		    tas->window_size, window_size);
+
+	head_idx = (tas->txpwr_tail_idx - window_size + 1 + RTW89_TAS_TXPWR_WINDOW) %
+		   RTW89_TAS_TXPWR_WINDOW;
+	for (i = 0; i < window_size; i++) {
+		j = (head_idx + i) % RTW89_TAS_TXPWR_WINDOW;
+		total_txpwr += tas->txpwr_history[j];
+	}
+
+	tas->window_size = window_size;
+	tas->total_txpwr = total_txpwr;
+	tas->txpwr_head_idx = head_idx;
+}
+
+static void rtw89_tas_history_update(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_bb_ctx *bb = rtw89_get_bb_ctx(rtwdev, RTW89_PHY_0);
+	struct rtw89_env_monitor_info *env = &bb->env_monitor;
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	u8 tx_ratio = env->ifs_clm_tx_ratio;
+	u64 instant_txpwr, txpwr;
+
+	/* txpwr in unit of linear(mW) multiply by percentage */
+	if (tx_ratio == 0) {
+		/* special case: idle tx power
+		 * use -40 dBm * 100 tx ratio
+		 */
+		instant_txpwr = rtw89_db_to_linear(-40);
+		txpwr = instant_txpwr * 100;
+	} else {
+		instant_txpwr = tas->instant_txpwr;
+		txpwr = instant_txpwr * tx_ratio;
+	}
+
+	tas->total_txpwr += txpwr - tas->txpwr_history[tas->txpwr_head_idx];
+	tas->total_tx_ratio += tx_ratio - tas->tx_ratio_history[tas->tx_ratio_idx];
+	tas->tx_ratio_history[tas->tx_ratio_idx] = tx_ratio;
+
+	tas->txpwr_head_idx = (tas->txpwr_head_idx + 1) % RTW89_TAS_TXPWR_WINDOW;
+	tas->txpwr_tail_idx = (tas->txpwr_tail_idx + 1) % RTW89_TAS_TXPWR_WINDOW;
+	tas->tx_ratio_idx = (tas->tx_ratio_idx + 1) % RTW89_TAS_TX_RATIO_WINDOW;
+	tas->txpwr_history[tas->txpwr_tail_idx] = txpwr;
 
-	dpr_on_threshold = cfg;
-	dpr_off_threshold = cfg - tas->dpr_gap;
 	rtw89_debug(rtwdev, RTW89_DBG_SAR,
-		    "DPR_ON thold: %d, DPR_OFF thold: %d, txpwr_avg: %d\n",
-		    dpr_on_threshold, dpr_off_threshold, txpwr_avg);
+		    "tas: instant_txpwr: %d, tx_ratio: %u, txpwr: %d\n",
+		    rtw89_linear_to_db_quarter(instant_txpwr), tx_ratio,
+		    rtw89_linear_to_db_quarter(div_u64(txpwr, PERCENT)));
+}
 
-	if (txpwr_avg >= dpr_on_threshold)
+static void rtw89_tas_rolling_average(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s32 dpr_on_threshold, dpr_off_threshold;
+	enum rtw89_tas_state state;
+	u16 tx_ratio_avg;
+	s32 txpwr_avg;
+	u64 linear;
+
+	linear = DIV_ROUND_DOWN_ULL(tas->total_txpwr, tas->window_size * PERCENT);
+	txpwr_avg = rtw89_linear_to_db_quarter(linear);
+	tx_ratio_avg = tas->total_tx_ratio / RTW89_TAS_TX_RATIO_WINDOW;
+	dpr_on_threshold = tas->dpr_on_threshold;
+	dpr_off_threshold = tas->dpr_off_threshold;
+
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "tas: DPR_ON: %d, DPR_OFF: %d, txpwr_avg: %d, tx_ratio_avg: %u\n",
+		    dpr_on_threshold, dpr_off_threshold, txpwr_avg, tx_ratio_avg);
+
+	if (tx_ratio_avg >= RTW89_TAS_TX_RATIO_THRESHOLD)
+		state = RTW89_TAS_STATE_STATIC_SAR;
+	else if (txpwr_avg >= dpr_on_threshold)
 		state = RTW89_TAS_STATE_DPR_ON;
 	else if (txpwr_avg < dpr_off_threshold)
 		state = RTW89_TAS_STATE_DPR_OFF;
-
-out:
-	if (tas->state == state)
+	else
 		return;
 
-	rtw89_debug(rtwdev, RTW89_DBG_SAR,
-		    "TAS old state: %d, new state: %d\n", tas->state, state);
-	tas->state = state;
-	rtw89_core_set_chip_txpwr(rtwdev);
+	rtw89_tas_state_update(rtwdev, state);
 }
 
 void rtw89_tas_init(struct rtw89_dev *rtwdev)
 {
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	struct rtw89_tas_info *tas = &rtwdev->tas;
 	struct rtw89_acpi_dsm_result res = {};
 	int ret;
 	u8 val;
 
+	if (!chip->support_tas)
+		return;
+
 	ret = rtw89_acpi_evaluate_dsm(rtwdev, RTW89_ACPI_DSM_FUNC_TAS_EN, &res);
 	if (ret) {
 		rtw89_debug(rtwdev, RTW89_DBG_SAR,
@@ -396,65 +554,116 @@ void rtw89_tas_init(struct rtw89_dev *rtwdev)
 		rtw89_debug(rtwdev, RTW89_DBG_SAR, "TAS not enable\n");
 		return;
 	}
-
-	tas->dpr_gap = RTW89_TAS_DPR_GAP;
-	tas->delta = RTW89_TAS_DELTA;
 }
 
-void rtw89_tas_reset(struct rtw89_dev *rtwdev)
+void rtw89_tas_reset(struct rtw89_dev *rtwdev, bool force)
 {
+	const struct rtw89_chan *chan = rtw89_chan_get(rtwdev, RTW89_CHANCTX_0);
 	struct rtw89_tas_info *tas = &rtwdev->tas;
+	u64 linear;
+	s32 cfg;
+	int i;
 
-	if (!tas->enable)
+	if (!rtw89_tas_is_active(rtwdev))
+		return;
+
+	if (!rtw89_tas_query_sar_config(rtwdev, &cfg))
+		return;
+
+	tas->dpr_on_threshold = cfg - RTW89_TAS_SAR_GAP;
+	tas->dpr_off_threshold = cfg - RTW89_TAS_SAR_GAP - RTW89_TAS_DPR_GAP;
+
+	/* avoid history reset after new SAR apply */
+	if (!force && tas->keep_history)
 		return;
 
-	memset(&tas->txpwr_history, 0, sizeof(tas->txpwr_history));
-	tas->total_txpwr = 0;
-	tas->cur_idx = 0;
+	linear = rtw89_db_quarter_to_linear(cfg) * RTW89_TAS_DFLT_TX_RATIO;
+	for (i = 0; i < RTW89_TAS_TXPWR_WINDOW; i++)
+		tas->txpwr_history[i] = linear;
+
+	for (i = 0; i < RTW89_TAS_TX_RATIO_WINDOW; i++)
+		tas->tx_ratio_history[i] = RTW89_TAS_DFLT_TX_RATIO;
+
+	tas->total_tx_ratio = RTW89_TAS_DFLT_TX_RATIO * RTW89_TAS_TX_RATIO_WINDOW;
+	tas->total_txpwr = linear * RTW89_TAS_TXPWR_WINDOW;
+	tas->window_size = RTW89_TAS_TXPWR_WINDOW;
+	tas->txpwr_head_idx = 0;
+	tas->txpwr_tail_idx = RTW89_TAS_TXPWR_WINDOW - 1;
+	tas->tx_ratio_idx = 0;
 	tas->state = RTW89_TAS_STATE_DPR_OFF;
-}
+	tas->backup_state = RTW89_TAS_STATE_DPR_OFF;
+	tas->keep_history = true;
 
-static const struct rtw89_reg_def txpwr_regs[] = {
-	{R_PATH0_TXPWR, B_PATH0_TXPWR},
-	{R_PATH1_TXPWR, B_PATH1_TXPWR},
-};
+	rtw89_debug(rtwdev, RTW89_DBG_SAR,
+		    "tas: band: %u, freq: %u\n", chan->band_type, chan->freq);
+}
 
 void rtw89_tas_track(struct rtw89_dev *rtwdev)
 {
-	struct rtw89_bb_ctx *bb = rtw89_get_bb_ctx(rtwdev, RTW89_PHY_0);
-	struct rtw89_env_monitor_info *env = &bb->env_monitor;
-	const enum rtw89_sar_sources src = rtwdev->sar.src;
-	u8 max_nss_num = rtwdev->chip->rf_path_num;
 	struct rtw89_tas_info *tas = &rtwdev->tas;
-	s16 tmp, txpwr, instant_txpwr = 0;
-	u32 val;
-	int i;
+	struct rtw89_hal *hal = &rtwdev->hal;
+	s32 cfg;
 
-	if (!tas->enable || src == RTW89_SAR_SOURCE_NONE)
+	if (hal->disabled_dm_bitmap & BIT(RTW89_DM_TAS))
 		return;
 
-	if (env->ccx_watchdog_result != RTW89_PHY_ENV_MON_IFS_CLM)
+	if (!rtw89_tas_is_active(rtwdev))
 		return;
 
-	for (i = 0; i < max_nss_num; i++) {
-		val = rtw89_phy_read32_mask(rtwdev, txpwr_regs[i].addr,
-					    txpwr_regs[i].mask);
-		tmp = sign_extend32(val, 8);
-		if (tmp <= 0)
-			return;
-		instant_txpwr += tmp;
+	if (!rtw89_tas_query_sar_config(rtwdev, &cfg) || tas->block_regd) {
+		rtw89_tas_state_update(rtwdev, RTW89_TAS_STATE_STATIC_SAR);
+		return;
 	}
 
-	instant_txpwr /= max_nss_num;
-	/* in unit of 0.25 dBm multiply by percentage */
-	txpwr = instant_txpwr * env->ifs_clm_tx_ratio;
-	tas->total_txpwr += txpwr - tas->txpwr_history[tas->cur_idx];
-	tas->txpwr_history[tas->cur_idx] = txpwr;
-	rtw89_debug(rtwdev, RTW89_DBG_SAR,
-		    "instant_txpwr: %d, tx_ratio: %d, txpwr: %d\n",
-		    instant_txpwr, env->ifs_clm_tx_ratio, txpwr);
+	if (tas->pause)
+		return;
+
+	rtw89_tas_window_update(rtwdev);
+	rtw89_tas_history_update(rtwdev);
+	rtw89_tas_rolling_average(rtwdev);
+}
+
+void rtw89_tas_scan(struct rtw89_dev *rtwdev, bool start)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s32 cfg;
+
+	if (!rtw89_tas_is_active(rtwdev))
+		return;
 
-	tas->cur_idx = (tas->cur_idx + 1) % RTW89_TAS_MAX_WINDOW;
+	if (!rtw89_tas_query_sar_config(rtwdev, &cfg))
+		return;
 
-	rtw89_tas_state_update(rtwdev);
+	if (start) {
+		tas->backup_state = tas->state;
+		rtw89_tas_state_update(rtwdev, RTW89_TAS_STATE_STATIC_SAR);
+	} else {
+		rtw89_tas_state_update(rtwdev, tas->backup_state);
+	}
+}
+
+void rtw89_tas_chanctx_cb(struct rtw89_dev *rtwdev,
+			  enum rtw89_chanctx_state state)
+{
+	struct rtw89_tas_info *tas = &rtwdev->tas;
+	s32 cfg;
+
+	if (!rtw89_tas_is_active(rtwdev))
+		return;
+
+	if (!rtw89_tas_query_sar_config(rtwdev, &cfg))
+		return;
+
+	switch (state) {
+	case RTW89_CHANCTX_STATE_MCC_START:
+		tas->pause = true;
+		rtw89_tas_state_update(rtwdev, RTW89_TAS_STATE_STATIC_SAR);
+		break;
+	case RTW89_CHANCTX_STATE_MCC_STOP:
+		tas->pause = false;
+		break;
+	default:
+		break;
+	}
 }
+EXPORT_SYMBOL(rtw89_tas_chanctx_cb);
diff --git a/drivers/net/wireless/realtek/rtw89/sar.h b/drivers/net/wireless/realtek/rtw89/sar.h
index 095277df5a710..0df1661db9a80 100644
--- a/drivers/net/wireless/realtek/rtw89/sar.h
+++ b/drivers/net/wireless/realtek/rtw89/sar.h
@@ -25,7 +25,10 @@ int rtw89_print_tas(struct rtw89_dev *rtwdev, char *buf, size_t bufsz);
 int rtw89_ops_set_sar_specs(struct ieee80211_hw *hw,
 			    const struct cfg80211_sar_specs *sar);
 void rtw89_tas_init(struct rtw89_dev *rtwdev);
-void rtw89_tas_reset(struct rtw89_dev *rtwdev);
+void rtw89_tas_reset(struct rtw89_dev *rtwdev, bool force);
 void rtw89_tas_track(struct rtw89_dev *rtwdev);
+void rtw89_tas_scan(struct rtw89_dev *rtwdev, bool start);
+void rtw89_tas_chanctx_cb(struct rtw89_dev *rtwdev,
+			  enum rtw89_chanctx_state state);
 
 #endif

From 9c225e119866a20eb76fd30ceed482cd363841ed Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Thu, 6 Mar 2025 10:11:42 +0800
Subject: [PATCH 2059/2753] wifi: rtw89: enable dynamic antenna gain based on
 country

The dynamic antenna gain (DAG) considers the country, meaning DAG can
be activated only when countries and regulatory domains allow it.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250306021144.12854-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h |  1 +
 drivers/net/wireless/realtek/rtw89/phy.c  | 11 ++++++++---
 drivers/net/wireless/realtek/rtw89/regd.c | 14 ++++++++++++++
 3 files changed, 23 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index 074c865e6d03f..b8f46207141e7 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4666,6 +4666,7 @@ enum rtw89_ant_gain_domain_type {
 struct rtw89_ant_gain_info {
 	s8 offset[RTW89_ANT_GAIN_CHAIN_NUM][RTW89_ANT_GAIN_SUBBAND_NR];
 	u32 regd_enabled;
+	bool block_country;
 };
 
 struct rtw89_6ghz_span {
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index abc2a7e989eb8..bd736417f4677 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2044,7 +2044,7 @@ static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u8 band, u32 cente
 	if (!chip->support_ant_gain)
 		return 0;
 
-	if (!(ant_gain->regd_enabled & BIT(regd)))
+	if (ant_gain->block_country || !(ant_gain->regd_enabled & BIT(regd)))
 		return 0;
 
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, center_freq);
@@ -2057,10 +2057,14 @@ s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
 				  const struct rtw89_chan *chan)
 {
 	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
 	u8 regd = rtw89_regd_get(rtwdev, chan->band_type);
 	s8 offset_patha, offset_pathb;
 
-	if (!(ant_gain->regd_enabled & BIT(regd)))
+	if (!chip->support_ant_gain)
+		return 0;
+
+	if (ant_gain->block_country || !(ant_gain->regd_enabled & BIT(regd)))
 		return 0;
 
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, chan->freq);
@@ -2079,7 +2083,8 @@ int rtw89_print_ant_gain(struct rtw89_dev *rtwdev, char *buf, size_t bufsz,
 	char *p = buf, *end = buf + bufsz;
 	s8 offset_patha, offset_pathb;
 
-	if (!chip->support_ant_gain || !(ant_gain->regd_enabled & BIT(regd))) {
+	if (!(chip->support_ant_gain && (ant_gain->regd_enabled & BIT(regd))) ||
+	    ant_gain->block_country) {
 		p += scnprintf(p, end - p, "no DAG is applied\n");
 		goto out;
 	}
diff --git a/drivers/net/wireless/realtek/rtw89/regd.c b/drivers/net/wireless/realtek/rtw89/regd.c
index d31403f9009ee..655323a796082 100644
--- a/drivers/net/wireless/realtek/rtw89/regd.c
+++ b/drivers/net/wireless/realtek/rtw89/regd.c
@@ -733,6 +733,19 @@ static void rtw89_regd_apply_policy_tas(struct rtw89_dev *rtwdev)
 	tas->block_regd = !test_bit(RTW89_REGD_FUNC_TAS, regd->func_bitmap);
 }
 
+static void rtw89_regd_apply_policy_ant_gain(struct rtw89_dev *rtwdev)
+{
+	struct rtw89_regulatory_info *regulatory = &rtwdev->regulatory;
+	struct rtw89_ant_gain_info *ant_gain = &rtwdev->ant_gain;
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	const struct rtw89_regd *regd = regulatory->regd;
+
+	if (!chip->support_ant_gain)
+		return;
+
+	ant_gain->block_country = !test_bit(RTW89_REGD_FUNC_DAG, regd->func_bitmap);
+}
+
 static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 				      struct wiphy *wiphy,
 				      struct regulatory_request *request)
@@ -751,6 +764,7 @@ static void rtw89_regd_notifier_apply(struct rtw89_dev *rtwdev,
 	rtw89_regd_apply_policy_unii4(rtwdev, wiphy);
 	rtw89_regd_apply_policy_6ghz(rtwdev, wiphy);
 	rtw89_regd_apply_policy_tas(rtwdev);
+	rtw89_regd_apply_policy_ant_gain(rtwdev);
 }
 
 static

From 6f039d9ba9cb1ebab9e790c1f4d3fa9e35d0b4fa Mon Sep 17 00:00:00 2001
From: Kuan-Chung Chen <damon.chen@realtek.com>
Date: Thu, 6 Mar 2025 10:11:43 +0800
Subject: [PATCH 2060/2753] wifi: rtw89: 8922a: enable dynamic antenna gain

The 8922A now supports dynamic antenna gain. However, in firmware
before v0.35.64.0, different transmit powers cannot be applied to
each RF path. To comply with regulatory limits in these older
firmware, the lower of the two requested transmit powers will
be used for both paths when they differ.

Signed-off-by: Kuan-Chung Chen <damon.chen@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250306021144.12854-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/core.h     |  1 +
 drivers/net/wireless/realtek/rtw89/fw.c       |  1 +
 drivers/net/wireless/realtek/rtw89/phy.c      |  6 +++
 drivers/net/wireless/realtek/rtw89/phy.h      |  7 +++
 drivers/net/wireless/realtek/rtw89/reg.h      | 28 +++++++---
 drivers/net/wireless/realtek/rtw89/rtw8922a.c | 54 ++++++++++++++++++-
 6 files changed, 88 insertions(+), 9 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index b8f46207141e7..c32b74df1443a 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -4492,6 +4492,7 @@ enum rtw89_fw_feature {
 	RTW89_FW_FEATURE_CH_INFO_BE_V0,
 	RTW89_FW_FEATURE_LPS_CH_INFO,
 	RTW89_FW_FEATURE_NO_PHYCAP_P1,
+	RTW89_FW_FEATURE_NO_POWER_DIFFERENCE,
 };
 
 struct rtw89_fw_suit {
diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
index d0a246f415ffc..8643b17866f89 100644
--- a/drivers/net/wireless/realtek/rtw89/fw.c
+++ b/drivers/net/wireless/realtek/rtw89/fw.c
@@ -849,6 +849,7 @@ static const struct __fw_feat_cfg fw_feat_tbl[] = {
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 47, 0, CH_INFO_BE_V0),
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 49, 0, RFK_PRE_NOTIFY_V1),
 	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 51, 0, NO_PHYCAP_P1),
+	__CFG_FW_FEAT(RTL8922A, lt, 0, 35, 64, 0, NO_POWER_DIFFERENCE),
 };
 
 static void rtw89_fw_iterate_feature_cfg(struct rtw89_fw_info *fw,
diff --git a/drivers/net/wireless/realtek/rtw89/phy.c b/drivers/net/wireless/realtek/rtw89/phy.c
index bd736417f4677..f4eee642e5ced 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.c
+++ b/drivers/net/wireless/realtek/rtw89/phy.c
@@ -2050,6 +2050,9 @@ static s8 rtw89_phy_ant_gain_offset(struct rtw89_dev *rtwdev, u8 band, u32 cente
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, center_freq);
 	offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, center_freq);
 
+	if (RTW89_CHK_FW_FEATURE(NO_POWER_DIFFERENCE, &rtwdev->fw))
+		return min(offset_patha, offset_pathb);
+
 	return max(offset_patha, offset_pathb);
 }
 
@@ -2067,6 +2070,9 @@ s16 rtw89_phy_ant_gain_pwr_offset(struct rtw89_dev *rtwdev,
 	if (ant_gain->block_country || !(ant_gain->regd_enabled & BIT(regd)))
 		return 0;
 
+	if (RTW89_CHK_FW_FEATURE(NO_POWER_DIFFERENCE, &rtwdev->fw))
+		return 0;
+
 	offset_patha = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_A, chan->freq);
 	offset_pathb = rtw89_phy_ant_gain_query(rtwdev, RF_PATH_B, chan->freq);
 
diff --git a/drivers/net/wireless/realtek/rtw89/phy.h b/drivers/net/wireless/realtek/rtw89/phy.h
index e20fff9bac3ee..518a100375fb3 100644
--- a/drivers/net/wireless/realtek/rtw89/phy.h
+++ b/drivers/net/wireless/realtek/rtw89/phy.h
@@ -914,6 +914,13 @@ static inline s8 rtw89_phy_txpwr_rf_to_bb(struct rtw89_dev *rtwdev, s8 txpwr_rf)
 	return txpwr_rf << (chip->txpwr_factor_bb - chip->txpwr_factor_rf);
 }
 
+static inline s8 rtw89_phy_txpwr_bb_to_rf(struct rtw89_dev *rtwdev, s8 txpwr_bb)
+{
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+
+	return txpwr_bb >> (chip->txpwr_factor_bb - chip->txpwr_factor_rf);
+}
+
 static inline s8 rtw89_phy_txpwr_rf_to_mac(struct rtw89_dev *rtwdev, s8 txpwr_rf)
 {
 	const struct rtw89_chip_info *chip = rtwdev->chip;
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index ec06f5bd0fab2..44201efee01ca 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -9181,6 +9181,16 @@
 #define B_IQKINF2_FCNT GENMASK(23, 16)
 #define B_IQKINF2_KCNT GENMASK(15, 8)
 #define B_IQKINF2_NCTLV GENMASK(7, 0)
+#define R_TXAGC_REF_DBM_RF1_P0 0xBC04
+#define B_TXAGC_OFDM_REF_DBM_RF1_P0 GENMASK(10, 2)
+#define B_TXAGC_CCK_REF_DBM_RF1_P0 GENMASK(19, 11)
+#define R_TSSI_K_RF1_P0 0xBC28
+#define B_TSSI_K_OFDM_RF1_P0 GENMASK(9, 0)
+#define R_TXAGC_REF_DBM_RF1_P1 0xBD04
+#define B_TXAGC_OFDM_REF_DBM_RF1_P1 GENMASK(10, 2)
+#define B_TXAGC_CCK_REF_DBM_RF1_P1 GENMASK(19, 11)
+#define R_TSSI_K_RF1_P1 0xBD28
+#define B_TSSI_K_OFDM_RF1_P1 GENMASK(9, 0)
 #define R_RFK_ST 0xBFF8
 #define R_DCOF0 0xC000
 #define B_DCOF0_RST BIT(17)
@@ -9350,16 +9360,18 @@
 #define R_TSSI_MAP_OFST_P1 0xE720
 #define B_TSSI_MAP_OFST_OFDM GENMASK(17, 9)
 #define B_TSSI_MAP_OFST_CCK GENMASK(26, 18)
-#define R_TXAGC_REF0_P0 0xE628
-#define R_TXAGC_REF0_P1 0xE728
-#define B_TXAGC_REF0_OFDM_DBM GENMASK(8, 0)
-#define B_TXAGC_REF0_CCK_DBM GENMASK(17, 9)
-#define B_TXAGC_REF0_OFDM_CW GENMASK(26, 18)
-#define R_TXAGC_REF1_P0 0xE62C
-#define R_TXAGC_REF1_P1 0xE72C
-#define B_TXAGC_REF1_CCK_CW GENMASK(8, 0)
+#define R_TXAGC_REF_DBM_P0 0xE628
+#define B_TXAGC_OFDM_REF_DBM_P0 GENMASK(8, 0)
+#define B_TXAGC_CCK_REF_DBM_P0 GENMASK(17, 9)
+#define R_TSSI_K_P0 0xE6A0
+#define B_TSSI_K_OFDM_P0 GENMASK(29, 20)
 #define R_TXPWR_RSTB 0xE70C
 #define B_TXPWR_RSTB BIT(16)
+#define R_TXAGC_REF_DBM_P1 0xE728
+#define B_TXAGC_OFDM_REF_DBM_P1 GENMASK(8, 0)
+#define B_TXAGC_CCK_REF_DBM_P1 GENMASK(17, 9)
+#define R_TSSI_K_P1 0xE7A0
+#define B_TSSI_K_OFDM_P1 GENMASK(29, 20)
 
 /* WiFi CPU local domain */
 #define R_AX_WDT_CTRL 0x0040
diff --git a/drivers/net/wireless/realtek/rtw89/rtw8922a.c b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
index d90af2daebcf7..8082592db84a1 100644
--- a/drivers/net/wireless/realtek/rtw89/rtw8922a.c
+++ b/drivers/net/wireless/realtek/rtw89/rtw8922a.c
@@ -2156,6 +2156,56 @@ static void rtw8922a_set_txpwr_ref(struct rtw89_dev *rtwdev,
 				     B_BE_PWR_REF_CTRL_CCK, ref_cck);
 }
 
+static const struct rtw89_reg_def rtw8922a_txpwr_ref[][3] = {
+	{{ .addr = R_TXAGC_REF_DBM_P0, .mask = B_TXAGC_OFDM_REF_DBM_P0},
+	 { .addr = R_TXAGC_REF_DBM_P0, .mask = B_TXAGC_CCK_REF_DBM_P0},
+	 { .addr = R_TSSI_K_P0, .mask = B_TSSI_K_OFDM_P0}
+	},
+	{{ .addr = R_TXAGC_REF_DBM_RF1_P0, .mask = B_TXAGC_OFDM_REF_DBM_RF1_P0},
+	 { .addr = R_TXAGC_REF_DBM_RF1_P0, .mask = B_TXAGC_CCK_REF_DBM_RF1_P0},
+	 { .addr = R_TSSI_K_RF1_P0, .mask = B_TSSI_K_OFDM_RF1_P0}
+	},
+};
+
+static void rtw8922a_set_txpwr_diff(struct rtw89_dev *rtwdev,
+				    const struct rtw89_chan *chan,
+				    enum rtw89_phy_idx phy_idx)
+{
+	s16 pwr_ofst = rtw89_phy_ant_gain_pwr_offset(rtwdev, chan);
+	const struct rtw89_chip_info *chip = rtwdev->chip;
+	static const u32 path_ofst[] = {0x0, 0x100};
+	const struct rtw89_reg_def *txpwr_ref;
+	static const s16 tssi_k_base = 0x12;
+	s16 tssi_k_ofst = abs(pwr_ofst) + tssi_k_base;
+	s16 ofst_dec[RF_PATH_NUM_8922A];
+	s16 tssi_k[RF_PATH_NUM_8922A];
+	s16 pwr_ref_ofst;
+	s16 pwr_ref = 0;
+	u8 i;
+
+	if (rtwdev->hal.cv == CHIP_CAV)
+		pwr_ref = 16;
+
+	pwr_ref <<= chip->txpwr_factor_rf;
+	pwr_ref_ofst = pwr_ref - rtw89_phy_txpwr_bb_to_rf(rtwdev, abs(pwr_ofst));
+
+	ofst_dec[RF_PATH_A] = pwr_ofst > 0 ? pwr_ref : pwr_ref_ofst;
+	ofst_dec[RF_PATH_B] = pwr_ofst > 0 ? pwr_ref_ofst : pwr_ref;
+	tssi_k[RF_PATH_A] = pwr_ofst > 0 ? tssi_k_base : tssi_k_ofst;
+	tssi_k[RF_PATH_B] = pwr_ofst > 0 ? tssi_k_ofst : tssi_k_base;
+
+	for (i = 0; i < RF_PATH_NUM_8922A; i++) {
+		txpwr_ref = rtw8922a_txpwr_ref[phy_idx];
+
+		rtw89_phy_write32_mask(rtwdev, txpwr_ref[0].addr + path_ofst[i],
+				       txpwr_ref[0].mask, ofst_dec[i]);
+		rtw89_phy_write32_mask(rtwdev, txpwr_ref[1].addr + path_ofst[i],
+				       txpwr_ref[1].mask, ofst_dec[i]);
+		rtw89_phy_write32_mask(rtwdev, txpwr_ref[2].addr + path_ofst[i],
+				       txpwr_ref[2].mask, tssi_k[i]);
+	}
+}
+
 static void rtw8922a_bb_tx_triangular(struct rtw89_dev *rtwdev, bool en,
 				      enum rtw89_phy_idx phy_idx)
 {
@@ -2192,6 +2242,8 @@ static void rtw8922a_set_txpwr(struct rtw89_dev *rtwdev,
 	rtw8922a_set_tx_shape(rtwdev, chan, phy_idx);
 	rtw89_phy_set_txpwr_limit(rtwdev, chan, phy_idx);
 	rtw89_phy_set_txpwr_limit_ru(rtwdev, chan, phy_idx);
+	rtw8922a_set_txpwr_diff(rtwdev, chan, phy_idx);
+	rtw8922a_set_txpwr_ref(rtwdev, phy_idx);
 }
 
 static void rtw8922a_set_txpwr_ctrl(struct rtw89_dev *rtwdev,
@@ -2769,7 +2821,7 @@ const struct rtw89_chip_info rtw8922a_chip_info = {
 				  BIT(NL80211_CHAN_WIDTH_80) |
 				  BIT(NL80211_CHAN_WIDTH_160),
 	.support_unii4		= true,
-	.support_ant_gain	= false,
+	.support_ant_gain	= true,
 	.support_tas		= false,
 	.ul_tb_waveform_ctrl	= false,
 	.ul_tb_pwr_diff		= false,

From a9b56f219a0fa550f92e65ac58443a7892380e09 Mon Sep 17 00:00:00 2001
From: Dian-Syuan Yang <dian_syuan0116@realtek.com>
Date: Thu, 6 Mar 2025 10:11:44 +0800
Subject: [PATCH 2061/2753] wifi: rtw89: set force HE TB mode when connecting
 to 11ax AP

Some of 11ax AP set the UL HE-SIG-A2 reserved subfield to all 0s, which
will cause the 11be chip to recognize trigger frame as EHT. We propose
a method to bypass the "UL HE-SIG-A2 reserved subfield" and always uses
HE TB in response to the AP's trigger frame.

Signed-off-by: Dian-Syuan Yang <dian_syuan0116@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250306021144.12854-6-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/mac.c      | 26 +++++++++++++++++++
 drivers/net/wireless/realtek/rtw89/mac.h      |  2 ++
 drivers/net/wireless/realtek/rtw89/mac80211.c |  1 +
 drivers/net/wireless/realtek/rtw89/reg.h      |  4 +++
 4 files changed, 33 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
index 513c317b286cc..b4841f948ec1c 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.c
+++ b/drivers/net/wireless/realtek/rtw89/mac.c
@@ -4837,6 +4837,32 @@ void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 		rtw89_write32_set(rtwdev, reg, mac->narrow_bw_ru_dis.mask);
 }
 
+void rtw89_mac_set_he_tb(struct rtw89_dev *rtwdev,
+			 struct rtw89_vif_link *rtwvif_link)
+{
+	struct ieee80211_bss_conf *bss_conf;
+	bool set;
+	u32 reg;
+
+	if (rtwdev->chip->chip_gen != RTW89_CHIP_BE)
+		return;
+
+	rcu_read_lock();
+
+	bss_conf = rtw89_vif_rcu_dereference_link(rtwvif_link, true);
+	set = bss_conf->he_support && !bss_conf->eht_support;
+
+	rcu_read_unlock();
+
+	reg = rtw89_mac_reg_by_idx(rtwdev, R_BE_CLIENT_OM_CTRL,
+				   rtwvif_link->mac_idx);
+
+	if (set)
+		rtw89_write32_set(rtwdev, reg, B_BE_TRIG_DIS_EHTTB);
+	else
+		rtw89_write32_clr(rtwdev, reg, B_BE_TRIG_DIS_EHTTB);
+}
+
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link)
 {
 	rtw89_mac_port_cfg_func_sw(rtwdev, rtwvif_link);
diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
index 4d5a06a2fe9b7..fd7935d245019 100644
--- a/drivers/net/wireless/realtek/rtw89/mac.h
+++ b/drivers/net/wireless/realtek/rtw89/mac.h
@@ -1188,6 +1188,8 @@ void rtw89_mac_port_cfg_rx_sync(struct rtw89_dev *rtwdev,
 				struct rtw89_vif_link *rtwvif_link, bool en);
 void rtw89_mac_set_he_obss_narrow_bw_ru(struct rtw89_dev *rtwdev,
 					struct rtw89_vif_link *rtwvif_link);
+void rtw89_mac_set_he_tb(struct rtw89_dev *rtwdev,
+			 struct rtw89_vif_link *rtwvif_link);
 void rtw89_mac_stop_ap(struct rtw89_dev *rtwdev, struct rtw89_vif_link *rtwvif_link);
 void rtw89_mac_enable_beacon_for_ap_vifs(struct rtw89_dev *rtwdev, bool en);
 int rtw89_mac_remove_vif(struct rtw89_dev *rtwdev, struct rtw89_vif_link *vif);
diff --git a/drivers/net/wireless/realtek/rtw89/mac80211.c b/drivers/net/wireless/realtek/rtw89/mac80211.c
index 778ca85892845..4fded07d0beeb 100644
--- a/drivers/net/wireless/realtek/rtw89/mac80211.c
+++ b/drivers/net/wireless/realtek/rtw89/mac80211.c
@@ -656,6 +656,7 @@ static void __rtw89_ops_bss_link_assoc(struct rtw89_dev *rtwdev,
 	rtw89_chip_cfg_txpwr_ul_tb_offset(rtwdev, rtwvif_link);
 	rtw89_mac_port_update(rtwdev, rtwvif_link);
 	rtw89_mac_set_he_obss_narrow_bw_ru(rtwdev, rtwvif_link);
+	rtw89_mac_set_he_tb(rtwdev, rtwvif_link);
 }
 
 static void __rtw89_ops_bss_assoc(struct rtw89_dev *rtwdev,
diff --git a/drivers/net/wireless/realtek/rtw89/reg.h b/drivers/net/wireless/realtek/rtw89/reg.h
index 44201efee01ca..c776954ad360d 100644
--- a/drivers/net/wireless/realtek/rtw89/reg.h
+++ b/drivers/net/wireless/realtek/rtw89/reg.h
@@ -7102,6 +7102,10 @@
 #define B_BE_MACLBK_RDY_NUM_MASK GENMASK(7, 3)
 #define B_BE_MACLBK_EN BIT(0)
 
+#define R_BE_CLIENT_OM_CTRL 0x11040
+#define R_BE_CLIENT_OM_CTRL_C1 0x15040
+#define B_BE_TRIG_DIS_EHTTB BIT(24)
+
 #define R_BE_WMAC_NAV_CTL 0x11080
 #define R_BE_WMAC_NAV_CTL_C1 0x15080
 #define B_BE_WMAC_NAV_UPPER_EN BIT(26)

From bb76dd94b7c7dd1a6fd04226af89f3130f506b84 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Sat, 8 Mar 2025 10:58:29 +0800
Subject: [PATCH 2062/2753] wifi: rtw89: coex: RTL8852BT coexistence Wi-Fi
 firmware support for 0.29.122.0

Add format version of Wi-Fi firmware commands/events for firmware
version 0.29.122.0.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250308025832.10400-2-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 858ff0cd1a239..f1a811c8713d4 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -132,6 +132,14 @@ static const u32 cxtbl[] = {
 
 static const struct rtw89_btc_ver rtw89_btc_ver_defs[] = {
 	/* firmware version must be in decreasing order for each chip */
+	{RTL8852BT, RTW89_FW_VER_CODE(0, 29, 122, 0),
+	 .fcxbtcrpt = 8, .fcxtdma = 7,    .fcxslots = 7, .fcxcysta = 7,
+	 .fcxstep = 7,   .fcxnullsta = 7, .fcxmreg = 7,  .fcxgpiodbg = 7,
+	 .fcxbtver = 7,  .fcxbtscan = 7,  .fcxbtafh = 7, .fcxbtdevinfo = 7,
+	 .fwlrole = 7,   .frptmap = 3,    .fcxctrl = 7,  .fcxinit = 7,
+	 .fwevntrptl = 1, .fwc2hfunc = 2, .drvinfo_type = 1, .info_buf = 1800,
+	 .max_role_num = 6,
+	},
 	{RTL8852BT, RTW89_FW_VER_CODE(0, 29, 90, 0),
 	 .fcxbtcrpt = 7, .fcxtdma = 7,    .fcxslots = 7, .fcxcysta = 7,
 	 .fcxstep = 7,   .fcxnullsta = 7, .fcxmreg = 7,  .fcxgpiodbg = 7,

From a36230aa5f5efceaf5f81682673732a921b91518 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Sat, 8 Mar 2025 10:58:30 +0800
Subject: [PATCH 2063/2753] wifi: rtw89: coex: Fix coexistence report not show
 as expected

This report will feedback some basic information from firmware(PTA counter,
report counter, mailbox counter etc). And the report version need to match
driver & firmware both side. The original logic break the switch case logic
before driver update the report version. It made the report can not be
parsed correctly. Delete the break at the version 7 and 8.
Add logic to count C2H event report.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250308025832.10400-3-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index f1a811c8713d4..94445c1d64d18 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -1380,11 +1380,9 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 		} else if (ver->fcxbtcrpt == 8) {
 			pfinfo = &pfwinfo->rpt_ctrl.finfo.v8;
 			pcinfo->req_len = sizeof(pfwinfo->rpt_ctrl.finfo.v8);
-			break;
 		} else if (ver->fcxbtcrpt == 7) {
 			pfinfo = &pfwinfo->rpt_ctrl.finfo.v7;
 			pcinfo->req_len = sizeof(pfwinfo->rpt_ctrl.finfo.v7);
-			break;
 		} else {
 			goto err;
 		}
@@ -8108,6 +8106,7 @@ void rtw89_btc_c2h_handle(struct rtw89_dev *rtwdev, struct sk_buff *skb,
 		return;
 
 	func = rtw89_btc_c2h_get_index_by_ver(rtwdev, func);
+	pfwinfo->cnt_c2h++;
 
 	switch (func) {
 	case BTF_EVNT_BUF_OVERFLOW:

From 6db476db57cac11d943dc3a60576d9ce0bdf8781 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Sat, 8 Mar 2025 10:58:31 +0800
Subject: [PATCH 2064/2753] wifi: rtw89: coex: Add parser for Bluetooth channel
 map report version 7

In order to rearrange the structure member, the format update to version 7.
And to parse the report correctly, add the related logic.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250308025832.10400-4-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 3 +++
 drivers/net/wireless/realtek/rtw89/core.h | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 94445c1d64d18..659b92b14d881 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -1540,6 +1540,9 @@ static u32 _chk_btc_report(struct rtw89_dev *rtwdev,
 		} else if (ver->fcxbtafh == 2) {
 			pfinfo = &pfwinfo->rpt_fbtc_btafh.finfo.v2;
 			pcinfo->req_len = sizeof(pfwinfo->rpt_fbtc_btafh.finfo.v2);
+		} else if (ver->fcxbtafh == 7) {
+			pfinfo = &pfwinfo->rpt_fbtc_btafh.finfo.v7;
+			pcinfo->req_len = sizeof(pfwinfo->rpt_fbtc_btafh.finfo.v7);
 		} else {
 			goto err;
 		}
diff --git a/drivers/net/wireless/realtek/rtw89/core.h b/drivers/net/wireless/realtek/rtw89/core.h
index c32b74df1443a..4be05d6cad187 100644
--- a/drivers/net/wireless/realtek/rtw89/core.h
+++ b/drivers/net/wireless/realtek/rtw89/core.h
@@ -3044,6 +3044,7 @@ struct rtw89_btc_rpt_cmn_info {
 union rtw89_btc_fbtc_btafh_info {
 	struct rtw89_btc_fbtc_btafh v1;
 	struct rtw89_btc_fbtc_btafh_v2 v2;
+	struct rtw89_btc_fbtc_btafh_v7 v7;
 };
 
 struct rtw89_btc_report_ctrl_state {

From e5c45671d996f36f6f3c33486662adba5d86f8b1 Mon Sep 17 00:00:00 2001
From: Ching-Te Ku <ku920601@realtek.com>
Date: Sat, 8 Mar 2025 10:58:32 +0800
Subject: [PATCH 2065/2753] wifi: rtw89: coex: Update Wi-Fi/Bluetooth
 coexistence version to 7.0.4

RTL8852BE-VT support for firmware 29.122. Add parser for Bluetooth channel
map report version 7.

Signed-off-by: Ching-Te Ku <ku920601@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250308025832.10400-5-pkshih@realtek.com
---
 drivers/net/wireless/realtek/rtw89/coex.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw89/coex.c b/drivers/net/wireless/realtek/rtw89/coex.c
index 659b92b14d881..5ccf0cbaed2fa 100644
--- a/drivers/net/wireless/realtek/rtw89/coex.c
+++ b/drivers/net/wireless/realtek/rtw89/coex.c
@@ -10,7 +10,7 @@
 #include "ps.h"
 #include "reg.h"
 
-#define RTW89_COEX_VERSION 0x07000313
+#define RTW89_COEX_VERSION 0x07000413
 #define FCXDEF_STEP 50 /* MUST <= FCXMAX_STEP and match with wl fw*/
 #define BTC_E2G_LIMIT_DEF 80
 

From 679ec431477cdb68d1cab068c008da0de7f842ef Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:22:17 +0200
Subject: [PATCH 2066/2753] wifi: rtw88: Add some definitions for RTL8814AU

Add various register definitions which will be used by the new driver.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/1dcb5abb-26f8-4db5-be36-057de56465e5@gmail.com
---
 drivers/net/wireless/realtek/rtw88/reg.h | 66 ++++++++++++++++++++++--
 1 file changed, 62 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
index 209b6fc08a73e..08e9494977e06 100644
--- a/drivers/net/wireless/realtek/rtw88/reg.h
+++ b/drivers/net/wireless/realtek/rtw88/reg.h
@@ -8,6 +8,7 @@
 #define REG_SYS_FUNC_EN		0x0002
 #define BIT_FEN_EN_25_1		BIT(13)
 #define BIT_FEN_ELDR		BIT(12)
+#define BIT_FEN_PCIEA		BIT(6)
 #define BIT_FEN_CPUEN		BIT(2)
 #define BIT_FEN_USBA		BIT(2)
 #define BIT_FEN_BB_GLB_RST	BIT(1)
@@ -39,6 +40,9 @@
 #define BIT_RF_RSTB		BIT(1)
 #define BIT_RF_EN		BIT(0)
 
+#define REG_RF_CTRL1		0x0020
+#define REG_RF_CTRL2		0x0021
+
 #define REG_AFE_CTRL1		0x0024
 #define BIT_MAC_CLK_SEL		(BIT(20) | BIT(21))
 #define REG_EFUSE_CTRL		0x0030
@@ -73,6 +77,8 @@
 #define BIT_BT_PTA_EN		BIT(5)
 #define BIT_WLRFE_4_5_EN	BIT(2)
 
+#define REG_GPIO_PIN_CTRL	0x0044
+
 #define REG_LED_CFG		0x004C
 #define BIT_LNAON_SEL_EN	BIT(26)
 #define BIT_PAPE_SEL_EN		BIT(25)
@@ -110,6 +116,7 @@
 #define BIT_SDIO_PAD_E5		BIT(18)
 
 #define REG_RF_B_CTRL		0x76
+#define REG_RF_CTRL3		0x0076
 
 #define REG_AFE_CTRL_4		0x0078
 #define BIT_CK320M_AFE_EN	BIT(4)
@@ -603,15 +610,25 @@
 #define REG_CCA2ND		0x0838
 #define REG_L1PKTH		0x0848
 #define REG_CLKTRK		0x0860
+#define REG_CSI_MASK_SETTING1	0x0874
+#define REG_NBI_SETTING		0x087c
+#define BIT_NBI_ENABLE		BIT(13)
+#define REG_CSI_FIX_MASK0	0x0880
+#define REG_CSI_FIX_MASK1	0x0884
+#define REG_CSI_FIX_MASK6	0x0898
+#define REG_CSI_FIX_MASK7	0x089c
 #define REG_ADCCLK		0x08AC
 #define REG_HSSI_READ		0x08B0
 #define REG_FPGA0_XCD_RF_PARA	0x08B4
 #define REG_RX_MCS_LIMIT	0x08BC
 #define REG_ADC160		0x08C4
+#define REG_DBGSEL		0x08fc
 #define REG_ANTSEL_SW		0x0900
 #define REG_DAC_RSTB		0x090c
+#define REG_PSD			0x0910
+#define BIT_PSD_INI		GENMASK(23, 22)
 #define REG_SINGLE_TONE_CONT_TX	0x0914
-
+#define REG_AGC_TABLE		0x0958
 #define REG_RFE_CTRL_E		0x0974
 #define REG_2ND_CCA_CTRL	0x0976
 #define REG_IQK_COM00		0x0978
@@ -621,10 +638,18 @@
 
 #define REG_FAS			0x09a4
 #define REG_RXSB		0x0a00
+#define BIT_RXSB_ANA_DIV	BIT(15)
 #define REG_CCK_RX		0x0a04
 #define REG_CCK_PD_TH		0x0a0a
-
-#define REG_CCK0_FAREPORT	0xa2c
+#define REG_PRECTRL		0x0a14
+#define BIT_DIS_CO_PATHSEL	BIT(7)
+#define BIT_IQ_WGT		GENMASK(9, 8)
+#define REG_CCA_MF		0x0a20
+#define BIT_MBC_WIN		GENMASK(5, 4)
+#define REG_CCK0_TX_FILTER1	0x0a20
+#define REG_CCK0_TX_FILTER2	0x0a24
+#define REG_CCK0_DEBUG_PORT	0x0a28
+#define REG_CCK0_FAREPORT	0x0a2c
 #define BIT_CCK0_2RX		BIT(18)
 #define BIT_CCK0_MRC		BIT(22)
 #define REG_FA_CCK		0x0a5c
@@ -643,10 +668,18 @@
 #define DIS_DPD_RATEVHT2SS_MCS1	BIT(9)
 #define DIS_DPD_RATEALL		GENMASK(9, 0)
 
+#define REG_CCA			0x0a70
+#define BIT_CCA_CO		BIT(7)
+#define REG_ANTSEL		0x0a74
+#define BIT_ANT_BYCO		BIT(8)
+#define REG_CCKTX		0x0a84
+#define BIT_CMB_CCA_2R		BIT(28)
+
 #define REG_CNTRST		0x0b58
 
 #define REG_3WIRE_SWA		0x0c00
 #define REG_RX_IQC_AB_A		0x0c10
+#define REG_RX_IQC_CD_A		0x0c14
 #define REG_TXSCALE_A		0x0c1c
 #define BB_SWING_MASK		GENMASK(31, 21)
 #define REG_TX_AGC_A_CCK_11_CCK_1		0xc20
@@ -674,7 +707,7 @@
 #define REG_LSSI_WRITE_A	0x0c90
 #define REG_PREDISTA		0x0c90
 #define REG_TXAGCIDX		0x0c94
-
+#define REG_TX_AGC_A		0x0c94
 #define REG_RFE_PINMUX_A	0x0cb0
 #define REG_RFE_INV_A		0x0cb4
 #define REG_RFE_CTRL8		0x0cb4
@@ -683,6 +716,7 @@
 #define DPDT_CTRL_PIN		0x77
 #define RFE_INV_MASK		0x3ff00000
 #define REG_RFECTL_A		0x0cb8
+#define REG_RFE_INV0		0x0cbc
 #define REG_RFE_INV8		0x0cbd
 #define BIT_MASK_RFE_INV89	GENMASK(1, 0)
 #define REG_RFE_INV16		0x0cbe
@@ -703,6 +737,7 @@
 
 #define REG_3WIRE_SWB		0x0e00
 #define REG_RX_IQC_AB_B		0x0e10
+#define REG_RX_IQC_CD_B		0x0e14
 #define REG_TXSCALE_B		0x0e1c
 #define REG_TX_AGC_B_CCK_11_CCK_1		0xe20
 #define REG_TX_AGC_B_OFDM18_OFDM6		0xe24
@@ -729,6 +764,7 @@
 #define REG_LSSI_WRITE_B	0x0e90
 #define REG_PREDISTB		0x0e90
 #define REG_INIDLYB		0x0e94
+#define REG_TX_AGC_B		0x0e94
 #define REG_RFE_PINMUX_B	0x0eb0
 #define REG_RFE_INV_B		0x0eb4
 #define REG_RFECTL_B		0x0eb8
@@ -744,8 +780,11 @@
 #define REG_CRC_HT		0x0f10
 #define REG_CRC_OFDM		0x0f14
 #define REG_FA_OFDM		0x0f48
+#define REG_DBGRPT		0x0fa0
 #define REG_CCA_CCK		0x0fcc
 
+#define REG_SYS_CFG3_8814A	0x1000
+
 #define REG_ANAPARSW_MAC_0	0x1010
 #define BIT_CF_L_V2		GENMASK(29, 28)
 
@@ -863,9 +902,27 @@
 #define LTECOEX_WRITE_DATA REG_WL2LTECOEX_INDIRECT_ACCESS_WRITE_DATA_V1
 #define LTECOEX_READ_DATA REG_WL2LTECOEX_INDIRECT_ACCESS_READ_DATA_V1
 
+#define REG_RX_IQC_AB_C		0x1810
+#define REG_RX_IQC_CD_C		0x1814
+#define REG_TXSCALE_C		0x181c
+#define REG_CK_MONHC		0x185c
+#define REG_AFE_PWR1_C		0x1860
 #define REG_IGN_GNT_BT1	0x1860
+#define REG_TX_AGC_C		0x1894
+#define REG_RFE_PINMUX_C	0x18b4
 
 #define REG_RFESEL_CTRL	0x1990
+#define REG_AGC_TBL		0x1998
+
+#define REG_RX_IQC_AB_D		0x1a10
+#define REG_RX_IQC_CD_D		0x1a14
+#define REG_TXSCALE_D		0x1a1c
+#define REG_CK_MONHD		0x1a5c
+#define REG_AFE_PWR1_D		0x1a60
+#define REG_TX_AGC_D		0x1a94
+#define REG_RFE_PINMUX_D	0x1ab4
+#define REG_RFE_INVSEL_D	0x1abc
+#define BIT_RFE_SELSW0_D	GENMASK(27, 20)
 
 #define REG_NOMASK_TXBT	0x1ca7
 #define REG_ANAPAR	0x1c30
@@ -906,6 +963,7 @@
 #define RF18_BAND_MASK	(BIT(16) | BIT(9) | BIT(8))
 #define RF18_CHANNEL_MASK	(MASKBYTE0)
 #define RF18_RFSI_MASK	(BIT(18) | BIT(17))
+#define RF_RCK1_V1	0x1c
 #define RF_RCK		0x1d
 #define RF_MODE_TABLE_ADDR	0x30
 #define RF_MODE_TABLE_DATA0	0x31

From f4debfcb1b3c14a28ec157a41e0b98be72e554a0 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:23:22 +0200
Subject: [PATCH 2067/2753] wifi: rtw88: Add rtw8814a_table.c (part 1/2)

This contains various tables for initialising the RTL8814A, plus TX
power limits.

Split into two patches because they are big.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/df0b8ceb-2c2f-4bda-906f-a05c7b4d424c@gmail.com
---
 .../wireless/realtek/rtw88/rtw8814a_table.c   | 12551 ++++++++++++++++
 1 file changed, 12551 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814a_table.c

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c
new file mode 100644
index 0000000000000..907cbd0321784
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c
@@ -0,0 +1,12551 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#include "main.h"
+#include "phy.h"
+#include "rtw8814a_table.h"
+
+static const u32 rtw8814a_mac[] = {
+	0x010, 0x0000007C,
+	0x014, 0x000000DB,
+	0x016, 0x00000002,
+	0x073, 0x00000010,
+	0x420, 0x00000080,
+	0x421, 0x0000000F,
+	0x428, 0x0000000A,
+	0x429, 0x00000010,
+	0x430, 0x00000000,
+	0x431, 0x00000000,
+	0x432, 0x00000000,
+	0x433, 0x00000001,
+	0x434, 0x00000004,
+	0x435, 0x00000005,
+	0x436, 0x00000007,
+	0x437, 0x00000008,
+	0x43C, 0x00000004,
+	0x43D, 0x00000005,
+	0x43E, 0x00000007,
+	0x43F, 0x00000008,
+	0x440, 0x0000005D,
+	0x441, 0x00000001,
+	0x442, 0x00000000,
+	0x444, 0x00000010,
+	0x445, 0x000000F0,
+	0x446, 0x00000001,
+	0x447, 0x000000FE,
+	0x448, 0x00000000,
+	0x449, 0x00000000,
+	0x44A, 0x00000000,
+	0x44B, 0x00000040,
+	0x44C, 0x00000010,
+	0x44D, 0x000000F0,
+	0x44E, 0x0000003F,
+	0x44F, 0x00000000,
+	0x450, 0x00000000,
+	0x451, 0x00000000,
+	0x452, 0x00000000,
+	0x453, 0x00000040,
+	0x45E, 0x00000004,
+	0x49C, 0x00000010,
+	0x49D, 0x000000F0,
+	0x49E, 0x00000000,
+	0x49F, 0x00000006,
+	0x4A0, 0x000000E0,
+	0x4A1, 0x00000003,
+	0x4A2, 0x00000000,
+	0x4A3, 0x00000040,
+	0x4A4, 0x00000015,
+	0x4A5, 0x000000F0,
+	0x4A6, 0x00000000,
+	0x4A7, 0x00000006,
+	0x4A8, 0x000000E0,
+	0x4A9, 0x00000000,
+	0x4AA, 0x00000000,
+	0x4AB, 0x00000000,
+	0x7DA, 0x00000008,
+	0x1448, 0x00000006,
+	0x144A, 0x00000006,
+	0x144C, 0x00000006,
+	0x144E, 0x00000006,
+	0x4C8, 0x000000FF,
+	0x4C9, 0x00000008,
+	0x4CA, 0x0000003C,
+	0x4CB, 0x0000003C,
+	0x4CC, 0x000000FF,
+	0x4CD, 0x000000FF,
+	0x4CE, 0x00000001,
+	0x4CF, 0x00000008,
+	0x500, 0x00000026,
+	0x501, 0x000000A2,
+	0x502, 0x0000002F,
+	0x503, 0x00000000,
+	0x504, 0x00000028,
+	0x505, 0x000000A3,
+	0x506, 0x0000005E,
+	0x507, 0x00000000,
+	0x508, 0x0000002B,
+	0x509, 0x000000A4,
+	0x50A, 0x0000005E,
+	0x50B, 0x00000000,
+	0x50C, 0x0000004F,
+	0x50D, 0x000000A4,
+	0x50E, 0x00000000,
+	0x50F, 0x00000000,
+	0x512, 0x0000001C,
+	0x514, 0x0000000A,
+	0x516, 0x0000000A,
+	0x521, 0x0000002F,
+	0x525, 0x00000047,
+	0x550, 0x00000010,
+	0x551, 0x00000010,
+	0x559, 0x00000002,
+	0x55C, 0x00000064,
+	0x55D, 0x000000FF,
+	0x577, 0x00000003,
+	0x5BE, 0x00000064,
+	0x604, 0x00000001,
+	0x605, 0x00000030,
+	0x607, 0x00000001,
+	0x608, 0x0000000E,
+	0x609, 0x0000002A,
+	0x60A, 0x00000000,
+	0x60C, 0x00000018,
+	0x60D, 0x00000050,
+	0x6A0, 0x000000FF,
+	0x6A1, 0x000000FF,
+	0x6A2, 0x000000FF,
+	0x6A3, 0x000000FF,
+	0x6A4, 0x000000FF,
+	0x6A5, 0x000000FF,
+	0x6DE, 0x00000084,
+	0x620, 0x000000FF,
+	0x621, 0x000000FF,
+	0x622, 0x000000FF,
+	0x623, 0x000000FF,
+	0x624, 0x000000FF,
+	0x625, 0x000000FF,
+	0x626, 0x000000FF,
+	0x627, 0x000000FF,
+	0x638, 0x00000064,
+	0x63C, 0x0000000A,
+	0x63D, 0x0000000A,
+	0x63E, 0x0000000E,
+	0x63F, 0x0000000E,
+	0x640, 0x00000040,
+	0x642, 0x00000040,
+	0x643, 0x00000000,
+	0x652, 0x000000C8,
+	0x66E, 0x00000005,
+	0x700, 0x00000021,
+	0x701, 0x00000043,
+	0x702, 0x00000065,
+	0x703, 0x00000087,
+	0x708, 0x00000021,
+	0x709, 0x00000043,
+	0x70A, 0x00000065,
+	0x70B, 0x00000087,
+	0x718, 0x00000040,
+	0x7D5, 0x000000BC,
+	0x7D8, 0x00000028,
+	0x7D9, 0x00000000,
+	0x7DA, 0x0000000B,
+};
+
+RTW_DECL_TABLE_PHY_COND(rtw8814a_mac, rtw_phy_cfg_mac);
+
+static const u32 rtw8814a_agc[] = {
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0xA0000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFD020003,
+	0x81C, 0xFC040003,
+	0x81C, 0xFB060003,
+	0x81C, 0xFA080003,
+	0x81C, 0xF90A0003,
+	0x81C, 0xF80C0003,
+	0x81C, 0xF70E0003,
+	0x81C, 0xF6100003,
+	0x81C, 0xF5120003,
+	0x81C, 0xF4140003,
+	0x81C, 0xF3160003,
+	0x81C, 0xF2180003,
+	0x81C, 0xF11A0003,
+	0x81C, 0xF01C0003,
+	0x81C, 0xEF1E0003,
+	0x81C, 0xEE200003,
+	0x81C, 0xED220003,
+	0x81C, 0xCF240003,
+	0x81C, 0xCE260003,
+	0x81C, 0xCD280003,
+	0x81C, 0xCC2A0003,
+	0x81C, 0xCB2C0003,
+	0x81C, 0xCA2E0003,
+	0x81C, 0xC9300003,
+	0x81C, 0xC8320003,
+	0x81C, 0xC7340003,
+	0x81C, 0xC6360003,
+	0x81C, 0xC5380003,
+	0x81C, 0xC43A0003,
+	0x81C, 0xA63C0003,
+	0x81C, 0xA53E0003,
+	0x81C, 0xA4400003,
+	0x81C, 0xA3420003,
+	0x81C, 0xA2440003,
+	0x81C, 0xA1460003,
+	0x81C, 0x86480003,
+	0x81C, 0x854A0003,
+	0x81C, 0x844C0003,
+	0x81C, 0x834E0003,
+	0x81C, 0x66500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x435C0003,
+	0x81C, 0x425E0003,
+	0x81C, 0x41600003,
+	0x81C, 0x27620003,
+	0x81C, 0x26640003,
+	0x81C, 0x25660003,
+	0x81C, 0x24680003,
+	0x81C, 0x236A0003,
+	0x81C, 0x226C0003,
+	0x81C, 0x216E0003,
+	0x81C, 0x21700003,
+	0x81C, 0x21720003,
+	0x81C, 0x21740003,
+	0x81C, 0x21760003,
+	0x81C, 0x21780003,
+	0x81C, 0x217A0003,
+	0x81C, 0x217C0003,
+	0x81C, 0x217E0003,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0x81C, 0xFE020003,
+	0x81C, 0xFD040003,
+	0x81C, 0xFC060003,
+	0x81C, 0xFB080003,
+	0x81C, 0xFA0A0003,
+	0x81C, 0xF90C0003,
+	0x81C, 0xF80E0003,
+	0x81C, 0xF7100003,
+	0x81C, 0xF6120003,
+	0x81C, 0xF5140003,
+	0x81C, 0xF4160003,
+	0x81C, 0xF3180003,
+	0x81C, 0xF21A0003,
+	0x81C, 0xF11C0003,
+	0x81C, 0xF01E0003,
+	0x81C, 0xEF200003,
+	0x81C, 0xEE220003,
+	0x81C, 0xED240003,
+	0x81C, 0xEC260003,
+	0x81C, 0xEB280003,
+	0x81C, 0xEA2A0003,
+	0x81C, 0xE92C0003,
+	0x81C, 0xE82E0003,
+	0x81C, 0xE7300003,
+	0x81C, 0xE6320003,
+	0x81C, 0xE5340003,
+	0x81C, 0xE4360003,
+	0x81C, 0xE3380003,
+	0x81C, 0xC53A0003,
+	0x81C, 0xC43C0003,
+	0x81C, 0xC33E0003,
+	0x81C, 0xC2400003,
+	0x81C, 0xC1420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0xA34E0003,
+	0x81C, 0xA2500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFD020003,
+	0x81C, 0xFC040003,
+	0x81C, 0xFB060003,
+	0x81C, 0xFA080003,
+	0x81C, 0xF90A0003,
+	0x81C, 0xF80C0003,
+	0x81C, 0xF70E0003,
+	0x81C, 0xF6100003,
+	0x81C, 0xF5120003,
+	0x81C, 0xF4140003,
+	0x81C, 0xF3160003,
+	0x81C, 0xF2180003,
+	0x81C, 0xF11A0003,
+	0x81C, 0xF01C0003,
+	0x81C, 0xEF1E0003,
+	0x81C, 0xEE200003,
+	0x81C, 0xED220003,
+	0x81C, 0xEC240003,
+	0x81C, 0xEB260003,
+	0x81C, 0xEA280003,
+	0x81C, 0xE92A0003,
+	0x81C, 0xE82C0003,
+	0x81C, 0xE72E0003,
+	0x81C, 0xE6300003,
+	0x81C, 0xE5320003,
+	0x81C, 0xE4340003,
+	0x81C, 0xE3360003,
+	0x81C, 0xC6380003,
+	0x81C, 0xC53A0003,
+	0x81C, 0xC43C0003,
+	0x81C, 0xC33E0003,
+	0x81C, 0xC2400003,
+	0x81C, 0xA9420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0xA34E0003,
+	0x81C, 0x66500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x49580003,
+	0x81C, 0x485A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0x81C, 0xFE020003,
+	0x81C, 0xFD040003,
+	0x81C, 0xFC060003,
+	0x81C, 0xFB080003,
+	0x81C, 0xFA0A0003,
+	0x81C, 0xF90C0003,
+	0x81C, 0xF80E0003,
+	0x81C, 0xF7100003,
+	0x81C, 0xF6120003,
+	0x81C, 0xF5140003,
+	0x81C, 0xF4160003,
+	0x81C, 0xF3180003,
+	0x81C, 0xF21A0003,
+	0x81C, 0xF11C0003,
+	0x81C, 0xF01E0003,
+	0x81C, 0xEF200003,
+	0x81C, 0xEE220003,
+	0x81C, 0xED240003,
+	0x81C, 0xEC260003,
+	0x81C, 0xEB280003,
+	0x81C, 0xEA2A0003,
+	0x81C, 0xE92C0003,
+	0x81C, 0xE82E0003,
+	0x81C, 0xE7300003,
+	0x81C, 0xE6320003,
+	0x81C, 0xE5340003,
+	0x81C, 0xE4360003,
+	0x81C, 0xE3380003,
+	0x81C, 0xC53A0003,
+	0x81C, 0xC43C0003,
+	0x81C, 0xC33E0003,
+	0x81C, 0xC2400003,
+	0x81C, 0xC1420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0xA34E0003,
+	0x81C, 0xA2500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFD020003,
+	0x81C, 0xFC040003,
+	0x81C, 0xFB060003,
+	0x81C, 0xFA080003,
+	0x81C, 0xF90A0003,
+	0x81C, 0xF80C0003,
+	0x81C, 0xF70E0003,
+	0x81C, 0xF6100003,
+	0x81C, 0xF5120003,
+	0x81C, 0xF4140003,
+	0x81C, 0xF3160003,
+	0x81C, 0xF2180003,
+	0x81C, 0xF11A0003,
+	0x81C, 0xF01C0003,
+	0x81C, 0xEF1E0003,
+	0x81C, 0xEE200003,
+	0x81C, 0xED220003,
+	0x81C, 0xEC240003,
+	0x81C, 0xEB260003,
+	0x81C, 0xEA280003,
+	0x81C, 0xE92A0003,
+	0x81C, 0xE82C0003,
+	0x81C, 0xE72E0003,
+	0x81C, 0xE6300003,
+	0x81C, 0xE5320003,
+	0x81C, 0xE4340003,
+	0x81C, 0xE3360003,
+	0x81C, 0xC6380003,
+	0x81C, 0xC53A0003,
+	0x81C, 0xC43C0003,
+	0x81C, 0xC33E0003,
+	0x81C, 0xC2400003,
+	0x81C, 0xA9420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0xA34E0003,
+	0x81C, 0x66500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x49580003,
+	0x81C, 0x485A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xDF000003,
+	0x81C, 0xDF020003,
+	0x81C, 0xDF040003,
+	0x81C, 0xDE060003,
+	0x81C, 0xDD080003,
+	0x81C, 0xDC0A0003,
+	0x81C, 0xDB0C0003,
+	0x81C, 0xDA0E0003,
+	0x81C, 0xD9100003,
+	0x81C, 0xD8120003,
+	0x81C, 0xD7140003,
+	0x81C, 0xD6160003,
+	0x81C, 0xD5180003,
+	0x81C, 0xD41A0003,
+	0x81C, 0xD31C0003,
+	0x81C, 0xD21E0003,
+	0x81C, 0xD1200003,
+	0x81C, 0xD0220003,
+	0x81C, 0xCF240003,
+	0x81C, 0xCE260003,
+	0x81C, 0xCD280003,
+	0x81C, 0xCC2A0003,
+	0x81C, 0xCB2C0003,
+	0x81C, 0xCA2E0003,
+	0x81C, 0xC9300003,
+	0x81C, 0xC8320003,
+	0x81C, 0xC7340003,
+	0x81C, 0xC6360003,
+	0x81C, 0xC5380003,
+	0x81C, 0xA73A0003,
+	0x81C, 0xA63C0003,
+	0x81C, 0xA53E0003,
+	0x81C, 0xA4400003,
+	0x81C, 0xA3420003,
+	0x81C, 0xA2440003,
+	0x81C, 0x87460003,
+	0x81C, 0x86480003,
+	0x81C, 0x854A0003,
+	0x81C, 0x844C0003,
+	0x81C, 0x834E0003,
+	0x81C, 0x82500003,
+	0x81C, 0x81520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x445C0003,
+	0x81C, 0x435E0003,
+	0x81C, 0x42600003,
+	0x81C, 0x41620003,
+	0x81C, 0x27640003,
+	0x81C, 0x26660003,
+	0x81C, 0x25680003,
+	0x81C, 0x246A0003,
+	0x81C, 0x236C0003,
+	0x81C, 0x226E0003,
+	0x81C, 0x21700003,
+	0x81C, 0x21720003,
+	0x81C, 0x21740003,
+	0x81C, 0x21760003,
+	0x81C, 0x21780003,
+	0x81C, 0x217A0003,
+	0x81C, 0x217C0003,
+	0x81C, 0x217E0003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000003,
+	0x81C, 0xFE020003,
+	0x81C, 0xFD040003,
+	0x81C, 0xFC060003,
+	0x81C, 0xFB080003,
+	0x81C, 0xFA0A0003,
+	0x81C, 0xF90C0003,
+	0x81C, 0xF80E0003,
+	0x81C, 0xF7100003,
+	0x81C, 0xF6120003,
+	0x81C, 0xF5140003,
+	0x81C, 0xF4160003,
+	0x81C, 0xF3180003,
+	0x81C, 0xF21A0003,
+	0x81C, 0xF11C0003,
+	0x81C, 0xF01E0003,
+	0x81C, 0xEF200003,
+	0x81C, 0xEE220003,
+	0x81C, 0xED240003,
+	0x81C, 0xEC260003,
+	0x81C, 0xEB280003,
+	0x81C, 0xEA2A0003,
+	0x81C, 0xE92C0003,
+	0x81C, 0xE82E0003,
+	0x81C, 0xE7300003,
+	0x81C, 0xE6320003,
+	0x81C, 0xE5340003,
+	0x81C, 0xE4360003,
+	0x81C, 0xE3380003,
+	0x81C, 0xC53A0003,
+	0x81C, 0xC43C0003,
+	0x81C, 0xC33E0003,
+	0x81C, 0xC2400003,
+	0x81C, 0xC1420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0xA34E0003,
+	0x81C, 0xA2500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xDF000003,
+	0x81C, 0xDF020003,
+	0x81C, 0xDF040003,
+	0x81C, 0xDE060003,
+	0x81C, 0xDD080003,
+	0x81C, 0xDC0A0003,
+	0x81C, 0xDB0C0003,
+	0x81C, 0xDA0E0003,
+	0x81C, 0xD9100003,
+	0x81C, 0xD8120003,
+	0x81C, 0xD7140003,
+	0x81C, 0xD6160003,
+	0x81C, 0xD5180003,
+	0x81C, 0xD41A0003,
+	0x81C, 0xD31C0003,
+	0x81C, 0xD21E0003,
+	0x81C, 0xD1200003,
+	0x81C, 0xD0220003,
+	0x81C, 0xCF240003,
+	0x81C, 0xCE260003,
+	0x81C, 0xCD280003,
+	0x81C, 0xCC2A0003,
+	0x81C, 0xCB2C0003,
+	0x81C, 0xCA2E0003,
+	0x81C, 0xC9300003,
+	0x81C, 0xC8320003,
+	0x81C, 0xC7340003,
+	0x81C, 0xC6360003,
+	0x81C, 0xC5380003,
+	0x81C, 0xA73A0003,
+	0x81C, 0xA63C0003,
+	0x81C, 0xA53E0003,
+	0x81C, 0xA4400003,
+	0x81C, 0xA3420003,
+	0x81C, 0xA2440003,
+	0x81C, 0x87460003,
+	0x81C, 0x86480003,
+	0x81C, 0x854A0003,
+	0x81C, 0x844C0003,
+	0x81C, 0x834E0003,
+	0x81C, 0x82500003,
+	0x81C, 0x81520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x445C0003,
+	0x81C, 0x435E0003,
+	0x81C, 0x42600003,
+	0x81C, 0x41620003,
+	0x81C, 0x27640003,
+	0x81C, 0x26660003,
+	0x81C, 0x25680003,
+	0x81C, 0x246A0003,
+	0x81C, 0x236C0003,
+	0x81C, 0x226E0003,
+	0x81C, 0x21700003,
+	0x81C, 0x21720003,
+	0x81C, 0x21740003,
+	0x81C, 0x21760003,
+	0x81C, 0x21780003,
+	0x81C, 0x217A0003,
+	0x81C, 0x217C0003,
+	0x81C, 0x217E0003,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFE020003,
+	0x81C, 0xFD040003,
+	0x81C, 0xFC060003,
+	0x81C, 0xFB080003,
+	0x81C, 0xFA0A0003,
+	0x81C, 0xF90C0003,
+	0x81C, 0xF80E0003,
+	0x81C, 0xF7100003,
+	0x81C, 0xF6120003,
+	0x81C, 0xF5140003,
+	0x81C, 0xF4160003,
+	0x81C, 0xF3180003,
+	0x81C, 0xF21A0003,
+	0x81C, 0xF11C0003,
+	0x81C, 0xF01E0003,
+	0x81C, 0xEF200003,
+	0x81C, 0xEE220003,
+	0x81C, 0xED240003,
+	0x81C, 0x0F260003,
+	0x81C, 0x0E280003,
+	0x81C, 0x0D2A0003,
+	0x81C, 0x0C2C0003,
+	0x81C, 0x0B2E0003,
+	0x81C, 0x0A300003,
+	0x81C, 0x09320003,
+	0x81C, 0x08340003,
+	0x81C, 0x07360003,
+	0x81C, 0x06380003,
+	0x81C, 0x053A0003,
+	0x81C, 0x043C0003,
+	0x81C, 0x033E0003,
+	0x81C, 0x23400003,
+	0x81C, 0x22420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0xA44C0003,
+	0x81C, 0x684E0003,
+	0x81C, 0x67500003,
+	0x81C, 0x66520003,
+	0x81C, 0x65540003,
+	0x81C, 0x64560003,
+	0x81C, 0x63580003,
+	0x81C, 0x625A0003,
+	0x81C, 0x615C0003,
+	0x81C, 0x475E0003,
+	0x81C, 0x46600003,
+	0x81C, 0x45620003,
+	0x81C, 0x44640003,
+	0x81C, 0x43660003,
+	0x81C, 0x42680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFE020003,
+	0x81C, 0xFD040003,
+	0x81C, 0xFC060003,
+	0x81C, 0xFB080003,
+	0x81C, 0xFA0A0003,
+	0x81C, 0xF90C0003,
+	0x81C, 0xF80E0003,
+	0x81C, 0xF7100003,
+	0x81C, 0xF6120003,
+	0x81C, 0xF5140003,
+	0x81C, 0xF4160003,
+	0x81C, 0xF3180003,
+	0x81C, 0xF21A0003,
+	0x81C, 0xF11C0003,
+	0x81C, 0xF01E0003,
+	0x81C, 0xEF200003,
+	0x81C, 0xEE220003,
+	0x81C, 0xED240003,
+	0x81C, 0xEC260003,
+	0x81C, 0xEB280003,
+	0x81C, 0xEA2A0003,
+	0x81C, 0xE92C0003,
+	0x81C, 0xE72E0003,
+	0x81C, 0xE6300003,
+	0x81C, 0xE5320003,
+	0x81C, 0x08340003,
+	0x81C, 0x07360003,
+	0x81C, 0x06380003,
+	0x81C, 0x053A0003,
+	0x81C, 0x043C0003,
+	0x81C, 0x033E0003,
+	0x81C, 0x02400003,
+	0x81C, 0xA9420003,
+	0x81C, 0xA8440003,
+	0x81C, 0xA7460003,
+	0x81C, 0xA6480003,
+	0x81C, 0xA54A0003,
+	0x81C, 0x684C0003,
+	0x81C, 0x674E0003,
+	0x81C, 0x66500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x475C0003,
+	0x81C, 0x465E0003,
+	0x81C, 0x45600003,
+	0x81C, 0x44620003,
+	0x81C, 0x43640003,
+	0x81C, 0x42660003,
+	0x81C, 0x41680003,
+	0x81C, 0x416A0003,
+	0x81C, 0x416C0003,
+	0x81C, 0x416E0003,
+	0x81C, 0x41700003,
+	0x81C, 0x41720003,
+	0x81C, 0x41740003,
+	0x81C, 0x41760003,
+	0x81C, 0x41780003,
+	0x81C, 0x417A0003,
+	0x81C, 0x417C0003,
+	0x81C, 0x417E0003,
+	0xA0000000,	0x00000000,
+	0x81C, 0xFE000003,
+	0x81C, 0xFD020003,
+	0x81C, 0xFC040003,
+	0x81C, 0xFB060003,
+	0x81C, 0xFA080003,
+	0x81C, 0xF90A0003,
+	0x81C, 0xF80C0003,
+	0x81C, 0xF70E0003,
+	0x81C, 0xF6100003,
+	0x81C, 0xF5120003,
+	0x81C, 0xF4140003,
+	0x81C, 0xF3160003,
+	0x81C, 0xF2180003,
+	0x81C, 0xF11A0003,
+	0x81C, 0xF01C0003,
+	0x81C, 0xEF1E0003,
+	0x81C, 0xEE200003,
+	0x81C, 0xED220003,
+	0x81C, 0xCF240003,
+	0x81C, 0xCE260003,
+	0x81C, 0xCD280003,
+	0x81C, 0xCC2A0003,
+	0x81C, 0xCB2C0003,
+	0x81C, 0xCA2E0003,
+	0x81C, 0xC9300003,
+	0x81C, 0xC8320003,
+	0x81C, 0xC7340003,
+	0x81C, 0xC6360003,
+	0x81C, 0xC5380003,
+	0x81C, 0xC43A0003,
+	0x81C, 0xA63C0003,
+	0x81C, 0xA53E0003,
+	0x81C, 0xA4400003,
+	0x81C, 0xA3420003,
+	0x81C, 0xA2440003,
+	0x81C, 0xA1460003,
+	0x81C, 0x86480003,
+	0x81C, 0x854A0003,
+	0x81C, 0x844C0003,
+	0x81C, 0x834E0003,
+	0x81C, 0x66500003,
+	0x81C, 0x65520003,
+	0x81C, 0x64540003,
+	0x81C, 0x63560003,
+	0x81C, 0x62580003,
+	0x81C, 0x615A0003,
+	0x81C, 0x435C0003,
+	0x81C, 0x425E0003,
+	0x81C, 0x41600003,
+	0x81C, 0x27620003,
+	0x81C, 0x26640003,
+	0x81C, 0x25660003,
+	0x81C, 0x24680003,
+	0x81C, 0x236A0003,
+	0x81C, 0x226C0003,
+	0x81C, 0x216E0003,
+	0x81C, 0x21700003,
+	0x81C, 0x21720003,
+	0x81C, 0x21740003,
+	0x81C, 0x21760003,
+	0x81C, 0x21780003,
+	0x81C, 0x217A0003,
+	0x81C, 0x217C0003,
+	0x81C, 0x217E0003,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000103,
+	0x81C, 0xF8020103,
+	0x81C, 0xF7040103,
+	0x81C, 0xF6060103,
+	0x81C, 0xF5080103,
+	0x81C, 0xF40A0103,
+	0x81C, 0xF30C0103,
+	0x81C, 0xF20E0103,
+	0x81C, 0xF1100103,
+	0x81C, 0xF0120103,
+	0x81C, 0xEF140103,
+	0x81C, 0xEE160103,
+	0x81C, 0xED180103,
+	0x81C, 0xEC1A0103,
+	0x81C, 0xEB1C0103,
+	0x81C, 0xEA1E0103,
+	0x81C, 0xE9200103,
+	0x81C, 0xE8220103,
+	0x81C, 0xE7240103,
+	0x81C, 0xE6260103,
+	0x81C, 0xE5280103,
+	0x81C, 0xE42A0103,
+	0x81C, 0xE32C0103,
+	0x81C, 0xC32E0103,
+	0x81C, 0xC2300103,
+	0x81C, 0xC1320103,
+	0x81C, 0xA5340103,
+	0x81C, 0xA4360103,
+	0x81C, 0xA3380103,
+	0x81C, 0xA23A0103,
+	0x81C, 0xA13C0103,
+	0x81C, 0x843E0103,
+	0x81C, 0x83400103,
+	0x81C, 0x82420103,
+	0x81C, 0x81440103,
+	0x81C, 0x64460103,
+	0x81C, 0x63480103,
+	0x81C, 0x624A0103,
+	0x81C, 0x614C0103,
+	0x81C, 0x444E0103,
+	0x81C, 0x43500103,
+	0x81C, 0x42520103,
+	0x81C, 0x41540103,
+	0x81C, 0x25560103,
+	0x81C, 0x24580103,
+	0x81C, 0x235A0103,
+	0x81C, 0x065C0103,
+	0x81C, 0x055E0103,
+	0x81C, 0x04600103,
+	0x81C, 0x03620103,
+	0x81C, 0x02640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000103,
+	0x81C, 0xF7020103,
+	0x81C, 0xF6040103,
+	0x81C, 0xF5060103,
+	0x81C, 0xF4080103,
+	0x81C, 0xF30A0103,
+	0x81C, 0xF20C0103,
+	0x81C, 0xF10E0103,
+	0x81C, 0xF0100103,
+	0x81C, 0xEF120103,
+	0x81C, 0xEE140103,
+	0x81C, 0xED160103,
+	0x81C, 0xEC180103,
+	0x81C, 0xEB1A0103,
+	0x81C, 0xEA1C0103,
+	0x81C, 0xE91E0103,
+	0x81C, 0xE8200103,
+	0x81C, 0xE7220103,
+	0x81C, 0xE6240103,
+	0x81C, 0xE5260103,
+	0x81C, 0xE4280103,
+	0x81C, 0xE32A0103,
+	0x81C, 0xE22C0103,
+	0x81C, 0xE12E0103,
+	0x81C, 0xA5300103,
+	0x81C, 0xA4320103,
+	0x81C, 0xA3340103,
+	0x81C, 0xA2360103,
+	0x81C, 0xA1380103,
+	0x81C, 0x843A0103,
+	0x81C, 0x833C0103,
+	0x81C, 0x823E0103,
+	0x81C, 0x81400103,
+	0x81C, 0x64420103,
+	0x81C, 0x63440103,
+	0x81C, 0x62460103,
+	0x81C, 0x61480103,
+	0x81C, 0x454A0103,
+	0x81C, 0x444C0103,
+	0x81C, 0x434E0103,
+	0x81C, 0x42500103,
+	0x81C, 0x25520103,
+	0x81C, 0x24540103,
+	0x81C, 0x23560103,
+	0x81C, 0x06580103,
+	0x81C, 0x055A0103,
+	0x81C, 0x045C0103,
+	0x81C, 0x035E0103,
+	0x81C, 0x02600103,
+	0x81C, 0x01620103,
+	0x81C, 0x01640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFC000103,
+	0x81C, 0xFB020103,
+	0x81C, 0xFA040103,
+	0x81C, 0xF9060103,
+	0x81C, 0xF8080103,
+	0x81C, 0xF70A0103,
+	0x81C, 0xF60C0103,
+	0x81C, 0xF50E0103,
+	0x81C, 0xF4100103,
+	0x81C, 0xF3120103,
+	0x81C, 0xF2140103,
+	0x81C, 0xF1160103,
+	0x81C, 0xF0180103,
+	0x81C, 0xEF1A0103,
+	0x81C, 0xEE1C0103,
+	0x81C, 0xED1E0103,
+	0x81C, 0xEC200103,
+	0x81C, 0xEB220103,
+	0x81C, 0xEA240103,
+	0x81C, 0xE9260103,
+	0x81C, 0xE8280103,
+	0x81C, 0xE72A0103,
+	0x81C, 0xE62C0103,
+	0x81C, 0xE52E0103,
+	0x81C, 0xE4300103,
+	0x81C, 0xE3320103,
+	0x81C, 0xE2340103,
+	0x81C, 0xE1360103,
+	0x81C, 0x87380103,
+	0x81C, 0x863A0103,
+	0x81C, 0x853C0103,
+	0x81C, 0x843E0103,
+	0x81C, 0x83400103,
+	0x81C, 0x82420103,
+	0x81C, 0x81440103,
+	0x81C, 0x64460103,
+	0x81C, 0x63480103,
+	0x81C, 0x624A0103,
+	0x81C, 0x464C0103,
+	0x81C, 0x454E0103,
+	0x81C, 0x44500103,
+	0x81C, 0x43520103,
+	0x81C, 0x26540103,
+	0x81C, 0x25560103,
+	0x81C, 0x24580103,
+	0x81C, 0x075A0103,
+	0x81C, 0x065C0103,
+	0x81C, 0x055E0103,
+	0x81C, 0x04600103,
+	0x81C, 0x03620103,
+	0x81C, 0x02640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000103,
+	0x81C, 0xF8020103,
+	0x81C, 0xF7040103,
+	0x81C, 0xF6060103,
+	0x81C, 0xF5080103,
+	0x81C, 0xF40A0103,
+	0x81C, 0xF30C0103,
+	0x81C, 0xF20E0103,
+	0x81C, 0xF1100103,
+	0x81C, 0xF0120103,
+	0x81C, 0xEF140103,
+	0x81C, 0xEE160103,
+	0x81C, 0xED180103,
+	0x81C, 0xEC1A0103,
+	0x81C, 0xEB1C0103,
+	0x81C, 0xEA1E0103,
+	0x81C, 0xE9200103,
+	0x81C, 0xE8220103,
+	0x81C, 0xE7240103,
+	0x81C, 0xE6260103,
+	0x81C, 0xE5280103,
+	0x81C, 0xE42A0103,
+	0x81C, 0xE32C0103,
+	0x81C, 0xE22E0103,
+	0x81C, 0xA6300103,
+	0x81C, 0xA5320103,
+	0x81C, 0xA4340103,
+	0x81C, 0xA3360103,
+	0x81C, 0xA2380103,
+	0x81C, 0xA13A0103,
+	0x81C, 0x843C0103,
+	0x81C, 0x833E0103,
+	0x81C, 0x82400103,
+	0x81C, 0x81420103,
+	0x81C, 0x64440103,
+	0x81C, 0x63460103,
+	0x81C, 0x62480103,
+	0x81C, 0x614A0103,
+	0x81C, 0x444C0103,
+	0x81C, 0x434E0103,
+	0x81C, 0x42500103,
+	0x81C, 0x41520103,
+	0x81C, 0x25540103,
+	0x81C, 0x24560103,
+	0x81C, 0x23580103,
+	0x81C, 0x225A0103,
+	0x81C, 0x055C0103,
+	0x81C, 0x045E0103,
+	0x81C, 0x03600103,
+	0x81C, 0x02620103,
+	0x81C, 0x01640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFD000103,
+	0x81C, 0xFC020103,
+	0x81C, 0xFB040103,
+	0x81C, 0xFA060103,
+	0x81C, 0xF9080103,
+	0x81C, 0xF80A0103,
+	0x81C, 0xF70C0103,
+	0x81C, 0xF60E0103,
+	0x81C, 0xF5100103,
+	0x81C, 0xF4120103,
+	0x81C, 0xF3140103,
+	0x81C, 0xF2160103,
+	0x81C, 0xF1180103,
+	0x81C, 0xF01A0103,
+	0x81C, 0xEF1C0103,
+	0x81C, 0xEE1E0103,
+	0x81C, 0xED200103,
+	0x81C, 0xEC220103,
+	0x81C, 0xEB240103,
+	0x81C, 0xEA260103,
+	0x81C, 0xE9280103,
+	0x81C, 0xE82A0103,
+	0x81C, 0xE72C0103,
+	0x81C, 0xE62E0103,
+	0x81C, 0xE5300103,
+	0x81C, 0xE4320103,
+	0x81C, 0xE3340103,
+	0x81C, 0xE2360103,
+	0x81C, 0xE1380103,
+	0x81C, 0xA33A0103,
+	0x81C, 0xA23C0103,
+	0x81C, 0xA13E0103,
+	0x81C, 0x84400103,
+	0x81C, 0x83420103,
+	0x81C, 0x82440103,
+	0x81C, 0x81460103,
+	0x81C, 0x64480103,
+	0x81C, 0x634A0103,
+	0x81C, 0x624C0103,
+	0x81C, 0x614E0103,
+	0x81C, 0x45500103,
+	0x81C, 0x44520103,
+	0x81C, 0x43540103,
+	0x81C, 0x42560103,
+	0x81C, 0x25580103,
+	0x81C, 0x245A0103,
+	0x81C, 0x235C0103,
+	0x81C, 0x065E0103,
+	0x81C, 0x05600103,
+	0x81C, 0x04620103,
+	0x81C, 0x03640103,
+	0x81C, 0x02660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFA000103,
+	0x81C, 0xF9020103,
+	0x81C, 0xF8040103,
+	0x81C, 0xF7060103,
+	0x81C, 0xF6080103,
+	0x81C, 0xF50A0103,
+	0x81C, 0xF40C0103,
+	0x81C, 0xF30E0103,
+	0x81C, 0xF2100103,
+	0x81C, 0xF1120103,
+	0x81C, 0xF0140103,
+	0x81C, 0xEF160103,
+	0x81C, 0xEE180103,
+	0x81C, 0xED1A0103,
+	0x81C, 0xEC1C0103,
+	0x81C, 0xEB1E0103,
+	0x81C, 0xEA200103,
+	0x81C, 0xE9220103,
+	0x81C, 0xE8240103,
+	0x81C, 0xE7260103,
+	0x81C, 0xE6280103,
+	0x81C, 0xE52A0103,
+	0x81C, 0xE42C0103,
+	0x81C, 0xE32E0103,
+	0x81C, 0xE2300103,
+	0x81C, 0xE1320103,
+	0x81C, 0xA5340103,
+	0x81C, 0xA4360103,
+	0x81C, 0xA3380103,
+	0x81C, 0xA23A0103,
+	0x81C, 0xA13C0103,
+	0x81C, 0x843E0103,
+	0x81C, 0x83400103,
+	0x81C, 0x82420103,
+	0x81C, 0x81440103,
+	0x81C, 0x64460103,
+	0x81C, 0x63480103,
+	0x81C, 0x624A0103,
+	0x81C, 0x614C0103,
+	0x81C, 0x454E0103,
+	0x81C, 0x44500103,
+	0x81C, 0x43520103,
+	0x81C, 0x42540103,
+	0x81C, 0x41560103,
+	0x81C, 0x24580103,
+	0x81C, 0x235A0103,
+	0x81C, 0x225C0103,
+	0x81C, 0x055E0103,
+	0x81C, 0x04600103,
+	0x81C, 0x03620103,
+	0x81C, 0x02640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000103,
+	0x81C, 0xFF020103,
+	0x81C, 0xFE040103,
+	0x81C, 0xFD060103,
+	0x81C, 0xFC080103,
+	0x81C, 0xFB0A0103,
+	0x81C, 0xFA0C0103,
+	0x81C, 0xF90E0103,
+	0x81C, 0xF8100103,
+	0x81C, 0xF7120103,
+	0x81C, 0xF6140103,
+	0x81C, 0xF5160103,
+	0x81C, 0xF4180103,
+	0x81C, 0xF31A0103,
+	0x81C, 0xF21C0103,
+	0x81C, 0xF11E0103,
+	0x81C, 0xF0200103,
+	0x81C, 0xEF220103,
+	0x81C, 0xEE240103,
+	0x81C, 0xED260103,
+	0x81C, 0xEC280103,
+	0x81C, 0xEB2A0103,
+	0x81C, 0xEA2C0103,
+	0x81C, 0xE92E0103,
+	0x81C, 0xE8300103,
+	0x81C, 0xE7320103,
+	0x81C, 0xE6340103,
+	0x81C, 0xE5360103,
+	0x81C, 0xE4380103,
+	0x81C, 0xE33A0103,
+	0x81C, 0xA53C0103,
+	0x81C, 0xA43E0103,
+	0x81C, 0xA3400103,
+	0x81C, 0xA2420103,
+	0x81C, 0xA1440103,
+	0x81C, 0x85460103,
+	0x81C, 0x84480103,
+	0x81C, 0x834A0103,
+	0x81C, 0x824C0103,
+	0x81C, 0x814E0103,
+	0x81C, 0x64500103,
+	0x81C, 0x63520103,
+	0x81C, 0x62540103,
+	0x81C, 0x44560103,
+	0x81C, 0x43580103,
+	0x81C, 0x425A0103,
+	0x81C, 0x265C0103,
+	0x81C, 0x255E0103,
+	0x81C, 0x24600103,
+	0x81C, 0x07620103,
+	0x81C, 0x06640103,
+	0x81C, 0x05660103,
+	0x81C, 0x04680103,
+	0x81C, 0x036A0103,
+	0x81C, 0x026C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000103,
+	0x81C, 0xF7020103,
+	0x81C, 0xF6040103,
+	0x81C, 0xF5060103,
+	0x81C, 0xF4080103,
+	0x81C, 0xF30A0103,
+	0x81C, 0xF20C0103,
+	0x81C, 0xF10E0103,
+	0x81C, 0xF0100103,
+	0x81C, 0xEF120103,
+	0x81C, 0xEE140103,
+	0x81C, 0xED160103,
+	0x81C, 0xEC180103,
+	0x81C, 0xEB1A0103,
+	0x81C, 0xEA1C0103,
+	0x81C, 0xE91E0103,
+	0x81C, 0xE8200103,
+	0x81C, 0xE7220103,
+	0x81C, 0xE6240103,
+	0x81C, 0xE5260103,
+	0x81C, 0xE4280103,
+	0x81C, 0xE32A0103,
+	0x81C, 0xE22C0103,
+	0x81C, 0xE12E0103,
+	0x81C, 0xA4300103,
+	0x81C, 0xA3320103,
+	0x81C, 0xA2340103,
+	0x81C, 0xA1360103,
+	0x81C, 0x85380103,
+	0x81C, 0x843A0103,
+	0x81C, 0x833C0103,
+	0x81C, 0x823E0103,
+	0x81C, 0x65400103,
+	0x81C, 0x64420103,
+	0x81C, 0x63440103,
+	0x81C, 0x62460103,
+	0x81C, 0x45480103,
+	0x81C, 0x444A0103,
+	0x81C, 0x434C0103,
+	0x81C, 0x264E0103,
+	0x81C, 0x25500103,
+	0x81C, 0x24520103,
+	0x81C, 0x08540103,
+	0x81C, 0x07560103,
+	0x81C, 0x06580103,
+	0x81C, 0x055A0103,
+	0x81C, 0x045C0103,
+	0x81C, 0x035E0103,
+	0x81C, 0x02600103,
+	0x81C, 0x01620103,
+	0x81C, 0x01640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000103,
+	0x81C, 0xFF020103,
+	0x81C, 0xFE040103,
+	0x81C, 0xFD060103,
+	0x81C, 0xFC080103,
+	0x81C, 0xFB0A0103,
+	0x81C, 0xFA0C0103,
+	0x81C, 0xF90E0103,
+	0x81C, 0xF8100103,
+	0x81C, 0xF7120103,
+	0x81C, 0xF6140103,
+	0x81C, 0xF5160103,
+	0x81C, 0xF4180103,
+	0x81C, 0xF31A0103,
+	0x81C, 0xF21C0103,
+	0x81C, 0xF11E0103,
+	0x81C, 0xF0200103,
+	0x81C, 0xEF220103,
+	0x81C, 0xEE240103,
+	0x81C, 0xED260103,
+	0x81C, 0xEC280103,
+	0x81C, 0xEB2A0103,
+	0x81C, 0xEA2C0103,
+	0x81C, 0xE92E0103,
+	0x81C, 0xE8300103,
+	0x81C, 0xE7320103,
+	0x81C, 0xE6340103,
+	0x81C, 0xE5360103,
+	0x81C, 0xE4380103,
+	0x81C, 0xE33A0103,
+	0x81C, 0xA53C0103,
+	0x81C, 0xA43E0103,
+	0x81C, 0xA3400103,
+	0x81C, 0xA2420103,
+	0x81C, 0xA1440103,
+	0x81C, 0x85460103,
+	0x81C, 0x84480103,
+	0x81C, 0x834A0103,
+	0x81C, 0x824C0103,
+	0x81C, 0x814E0103,
+	0x81C, 0x64500103,
+	0x81C, 0x63520103,
+	0x81C, 0x62540103,
+	0x81C, 0x44560103,
+	0x81C, 0x43580103,
+	0x81C, 0x425A0103,
+	0x81C, 0x265C0103,
+	0x81C, 0x255E0103,
+	0x81C, 0x24600103,
+	0x81C, 0x07620103,
+	0x81C, 0x06640103,
+	0x81C, 0x05660103,
+	0x81C, 0x04680103,
+	0x81C, 0x036A0103,
+	0x81C, 0x026C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000103,
+	0x81C, 0xF8020103,
+	0x81C, 0xF7040103,
+	0x81C, 0xF6060103,
+	0x81C, 0xF5080103,
+	0x81C, 0xF40A0103,
+	0x81C, 0xF30C0103,
+	0x81C, 0xF20E0103,
+	0x81C, 0xF1100103,
+	0x81C, 0xF0120103,
+	0x81C, 0xEF140103,
+	0x81C, 0xEE160103,
+	0x81C, 0xED180103,
+	0x81C, 0xEC1A0103,
+	0x81C, 0xEB1C0103,
+	0x81C, 0xEA1E0103,
+	0x81C, 0xE9200103,
+	0x81C, 0xE8220103,
+	0x81C, 0xE7240103,
+	0x81C, 0xE6260103,
+	0x81C, 0xE5280103,
+	0x81C, 0xE42A0103,
+	0x81C, 0xE32C0103,
+	0x81C, 0xE22E0103,
+	0x81C, 0xA6300103,
+	0x81C, 0xA5320103,
+	0x81C, 0xA4340103,
+	0x81C, 0xA3360103,
+	0x81C, 0xA2380103,
+	0x81C, 0xA13A0103,
+	0x81C, 0x843C0103,
+	0x81C, 0x833E0103,
+	0x81C, 0x82400103,
+	0x81C, 0x81420103,
+	0x81C, 0x64440103,
+	0x81C, 0x63460103,
+	0x81C, 0x62480103,
+	0x81C, 0x614A0103,
+	0x81C, 0x444C0103,
+	0x81C, 0x434E0103,
+	0x81C, 0x42500103,
+	0x81C, 0x41520103,
+	0x81C, 0x25540103,
+	0x81C, 0x24560103,
+	0x81C, 0x23580103,
+	0x81C, 0x225A0103,
+	0x81C, 0x055C0103,
+	0x81C, 0x045E0103,
+	0x81C, 0x03600103,
+	0x81C, 0x02620103,
+	0x81C, 0x01640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFA000103,
+	0x81C, 0xF9020103,
+	0x81C, 0xF8040103,
+	0x81C, 0xF7060103,
+	0x81C, 0xF6080103,
+	0x81C, 0xF50A0103,
+	0x81C, 0xF40C0103,
+	0x81C, 0xF30E0103,
+	0x81C, 0xF2100103,
+	0x81C, 0xF1120103,
+	0x81C, 0xF0140103,
+	0x81C, 0xEF160103,
+	0x81C, 0xEE180103,
+	0x81C, 0xED1A0103,
+	0x81C, 0xCC1C0103,
+	0x81C, 0xCB1E0103,
+	0x81C, 0xCA200103,
+	0x81C, 0xE9220103,
+	0x81C, 0xE8240103,
+	0x81C, 0xE7260103,
+	0x81C, 0xE6280103,
+	0x81C, 0xE42A0103,
+	0x81C, 0xE32C0103,
+	0x81C, 0xE22E0103,
+	0x81C, 0xA7300103,
+	0x81C, 0xA6320103,
+	0x81C, 0xA5340103,
+	0x81C, 0xA4360103,
+	0x81C, 0xA3380103,
+	0x81C, 0xA23A0103,
+	0x81C, 0xA13C0103,
+	0x81C, 0x843E0103,
+	0x81C, 0x83400103,
+	0x81C, 0x82420103,
+	0x81C, 0x65440103,
+	0x81C, 0x64460103,
+	0x81C, 0x63480103,
+	0x81C, 0x624A0103,
+	0x81C, 0x614C0103,
+	0x81C, 0x444E0103,
+	0x81C, 0x43500103,
+	0x81C, 0x42520103,
+	0x81C, 0x41540103,
+	0x81C, 0x24560103,
+	0x81C, 0x23580103,
+	0x81C, 0x055A0103,
+	0x81C, 0x045C0103,
+	0x81C, 0x035E0103,
+	0x81C, 0x02600103,
+	0x81C, 0x01620103,
+	0x81C, 0x01640103,
+	0x81C, 0x01660103,
+	0x81C, 0x01680103,
+	0x81C, 0x016A0103,
+	0x81C, 0x016C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0xA0000000,	0x00000000,
+	0x81C, 0xFF000103,
+	0x81C, 0xFE020103,
+	0x81C, 0xFD040103,
+	0x81C, 0xFC060103,
+	0x81C, 0xFB080103,
+	0x81C, 0xFA0A0103,
+	0x81C, 0xF90C0103,
+	0x81C, 0xF80E0103,
+	0x81C, 0xF7100103,
+	0x81C, 0xF6120103,
+	0x81C, 0xF5140103,
+	0x81C, 0xF4160103,
+	0x81C, 0xF3180103,
+	0x81C, 0xF21A0103,
+	0x81C, 0xF11C0103,
+	0x81C, 0xF01E0103,
+	0x81C, 0xEF200103,
+	0x81C, 0xEE220103,
+	0x81C, 0xED240103,
+	0x81C, 0xEC260103,
+	0x81C, 0xEB280103,
+	0x81C, 0xEA2A0103,
+	0x81C, 0xE92C0103,
+	0x81C, 0xE82E0103,
+	0x81C, 0xE7300103,
+	0x81C, 0xE6320103,
+	0x81C, 0xE5340103,
+	0x81C, 0xE4360103,
+	0x81C, 0xE3380103,
+	0x81C, 0xE23A0103,
+	0x81C, 0xE13C0103,
+	0x81C, 0xA43E0103,
+	0x81C, 0xA3400103,
+	0x81C, 0xA2420103,
+	0x81C, 0xA1440103,
+	0x81C, 0x86460103,
+	0x81C, 0x85480103,
+	0x81C, 0x844A0103,
+	0x81C, 0x834C0103,
+	0x81C, 0x824E0103,
+	0x81C, 0x81500103,
+	0x81C, 0x64520103,
+	0x81C, 0x63540103,
+	0x81C, 0x62560103,
+	0x81C, 0x61580103,
+	0x81C, 0x435A0103,
+	0x81C, 0x425C0103,
+	0x81C, 0x415E0103,
+	0x81C, 0x25600103,
+	0x81C, 0x24620103,
+	0x81C, 0x06640103,
+	0x81C, 0x05660103,
+	0x81C, 0x04680103,
+	0x81C, 0x036A0103,
+	0x81C, 0x026C0103,
+	0x81C, 0x016E0103,
+	0x81C, 0x01700103,
+	0x81C, 0x01720103,
+	0x81C, 0x01740103,
+	0x81C, 0x01760103,
+	0x81C, 0x01780103,
+	0x81C, 0x017A0103,
+	0x81C, 0x017C0103,
+	0x81C, 0x017E0103,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFA000203,
+	0x81C, 0xF9020203,
+	0x81C, 0xF8040203,
+	0x81C, 0xF7060203,
+	0x81C, 0xF6080203,
+	0x81C, 0xF50A0203,
+	0x81C, 0xF40C0203,
+	0x81C, 0xF30E0203,
+	0x81C, 0xF2100203,
+	0x81C, 0xF1120203,
+	0x81C, 0xF0140203,
+	0x81C, 0xEF160203,
+	0x81C, 0xEE180203,
+	0x81C, 0xED1A0203,
+	0x81C, 0xEC1C0203,
+	0x81C, 0xEB1E0203,
+	0x81C, 0xEA200203,
+	0x81C, 0xE9220203,
+	0x81C, 0xE8240203,
+	0x81C, 0xE7260203,
+	0x81C, 0xE6280203,
+	0x81C, 0xE52A0203,
+	0x81C, 0xE42C0203,
+	0x81C, 0xE32E0203,
+	0x81C, 0xE2300203,
+	0x81C, 0xE1320203,
+	0x81C, 0xA5340203,
+	0x81C, 0xA4360203,
+	0x81C, 0xA3380203,
+	0x81C, 0xA23A0203,
+	0x81C, 0xA13C0203,
+	0x81C, 0x843E0203,
+	0x81C, 0x83400203,
+	0x81C, 0x82420203,
+	0x81C, 0x81440203,
+	0x81C, 0x63460203,
+	0x81C, 0x62480203,
+	0x81C, 0x614A0203,
+	0x81C, 0x464C0203,
+	0x81C, 0x454E0203,
+	0x81C, 0x44500203,
+	0x81C, 0x43520203,
+	0x81C, 0x42540203,
+	0x81C, 0x41560203,
+	0x81C, 0x24580203,
+	0x81C, 0x235A0203,
+	0x81C, 0x065C0203,
+	0x81C, 0x055E0203,
+	0x81C, 0x04600203,
+	0x81C, 0x03620203,
+	0x81C, 0x02640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000203,
+	0x81C, 0xF7020203,
+	0x81C, 0xF6040203,
+	0x81C, 0xF5060203,
+	0x81C, 0xF4080203,
+	0x81C, 0xF30A0203,
+	0x81C, 0xF20C0203,
+	0x81C, 0xF10E0203,
+	0x81C, 0xF0100203,
+	0x81C, 0xEF120203,
+	0x81C, 0xEE140203,
+	0x81C, 0xED160203,
+	0x81C, 0xEC180203,
+	0x81C, 0xEB1A0203,
+	0x81C, 0xEA1C0203,
+	0x81C, 0xE91E0203,
+	0x81C, 0xE8200203,
+	0x81C, 0xE7220203,
+	0x81C, 0xE6240203,
+	0x81C, 0xE5260203,
+	0x81C, 0xE4280203,
+	0x81C, 0xE32A0203,
+	0x81C, 0xE22C0203,
+	0x81C, 0xE12E0203,
+	0x81C, 0xA6300203,
+	0x81C, 0xA5320203,
+	0x81C, 0xA4340203,
+	0x81C, 0xA3360203,
+	0x81C, 0xA2380203,
+	0x81C, 0x853A0203,
+	0x81C, 0x843C0203,
+	0x81C, 0x833E0203,
+	0x81C, 0x82400203,
+	0x81C, 0x81420203,
+	0x81C, 0x64440203,
+	0x81C, 0x63460203,
+	0x81C, 0x62480203,
+	0x81C, 0x614A0203,
+	0x81C, 0x444C0203,
+	0x81C, 0x434E0203,
+	0x81C, 0x42500203,
+	0x81C, 0x25520203,
+	0x81C, 0x24540203,
+	0x81C, 0x23560203,
+	0x81C, 0x06580203,
+	0x81C, 0x055A0203,
+	0x81C, 0x045C0203,
+	0x81C, 0x035E0203,
+	0x81C, 0x02600203,
+	0x81C, 0x01620203,
+	0x81C, 0x01640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFC000203,
+	0x81C, 0xFB020203,
+	0x81C, 0xFA040203,
+	0x81C, 0xF9060203,
+	0x81C, 0xF8080203,
+	0x81C, 0xF70A0203,
+	0x81C, 0xF60C0203,
+	0x81C, 0xF50E0203,
+	0x81C, 0xF4100203,
+	0x81C, 0xF3120203,
+	0x81C, 0xF2140203,
+	0x81C, 0xF1160203,
+	0x81C, 0xF0180203,
+	0x81C, 0xEF1A0203,
+	0x81C, 0xEE1C0203,
+	0x81C, 0xED1E0203,
+	0x81C, 0xEC200203,
+	0x81C, 0xEB220203,
+	0x81C, 0xEA240203,
+	0x81C, 0xE9260203,
+	0x81C, 0xE8280203,
+	0x81C, 0xE72A0203,
+	0x81C, 0xE62C0203,
+	0x81C, 0xE52E0203,
+	0x81C, 0xE4300203,
+	0x81C, 0xE3320203,
+	0x81C, 0xE2340203,
+	0x81C, 0xE1360203,
+	0x81C, 0x87380203,
+	0x81C, 0x863A0203,
+	0x81C, 0x853C0203,
+	0x81C, 0x843E0203,
+	0x81C, 0x83400203,
+	0x81C, 0x82420203,
+	0x81C, 0x81440203,
+	0x81C, 0x64460203,
+	0x81C, 0x63480203,
+	0x81C, 0x624A0203,
+	0x81C, 0x474C0203,
+	0x81C, 0x464E0203,
+	0x81C, 0x45500203,
+	0x81C, 0x44520203,
+	0x81C, 0x43540203,
+	0x81C, 0x42560203,
+	0x81C, 0x24580203,
+	0x81C, 0x235A0203,
+	0x81C, 0x075C0203,
+	0x81C, 0x065E0203,
+	0x81C, 0x05600203,
+	0x81C, 0x04620203,
+	0x81C, 0x03640203,
+	0x81C, 0x02660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000203,
+	0x81C, 0xF7020203,
+	0x81C, 0xF6040203,
+	0x81C, 0xF5060203,
+	0x81C, 0xF4080203,
+	0x81C, 0xF30A0203,
+	0x81C, 0xF20C0203,
+	0x81C, 0xF10E0203,
+	0x81C, 0xF0100203,
+	0x81C, 0xEF120203,
+	0x81C, 0xEE140203,
+	0x81C, 0xED160203,
+	0x81C, 0xEC180203,
+	0x81C, 0xEB1A0203,
+	0x81C, 0xEA1C0203,
+	0x81C, 0xE91E0203,
+	0x81C, 0xE8200203,
+	0x81C, 0xE7220203,
+	0x81C, 0xE6240203,
+	0x81C, 0xE5260203,
+	0x81C, 0xE4280203,
+	0x81C, 0xE32A0203,
+	0x81C, 0xE22C0203,
+	0x81C, 0xE12E0203,
+	0x81C, 0xA6300203,
+	0x81C, 0xA5320203,
+	0x81C, 0xA4340203,
+	0x81C, 0xA3360203,
+	0x81C, 0xA2380203,
+	0x81C, 0xA13A0203,
+	0x81C, 0x843C0203,
+	0x81C, 0x833E0203,
+	0x81C, 0x82400203,
+	0x81C, 0x81420203,
+	0x81C, 0x64440203,
+	0x81C, 0x63460203,
+	0x81C, 0x62480203,
+	0x81C, 0x614A0203,
+	0x81C, 0x444C0203,
+	0x81C, 0x434E0203,
+	0x81C, 0x42500203,
+	0x81C, 0x41520203,
+	0x81C, 0x25540203,
+	0x81C, 0x24560203,
+	0x81C, 0x23580203,
+	0x81C, 0x065A0203,
+	0x81C, 0x055C0203,
+	0x81C, 0x045E0203,
+	0x81C, 0x03600203,
+	0x81C, 0x02620203,
+	0x81C, 0x01640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFB000203,
+	0x81C, 0xFA020203,
+	0x81C, 0xF9040203,
+	0x81C, 0xF8060203,
+	0x81C, 0xF7080203,
+	0x81C, 0xF60A0203,
+	0x81C, 0xF50C0203,
+	0x81C, 0xF40E0203,
+	0x81C, 0xF3100203,
+	0x81C, 0xF2120203,
+	0x81C, 0xF1140203,
+	0x81C, 0xF0160203,
+	0x81C, 0xEF180203,
+	0x81C, 0xEE1A0203,
+	0x81C, 0xED1C0203,
+	0x81C, 0xEC1E0203,
+	0x81C, 0xEB200203,
+	0x81C, 0xEA220203,
+	0x81C, 0xE9240203,
+	0x81C, 0xE8260203,
+	0x81C, 0xE7280203,
+	0x81C, 0xE62A0203,
+	0x81C, 0xE52C0203,
+	0x81C, 0xE42E0203,
+	0x81C, 0xE3300203,
+	0x81C, 0xE2320203,
+	0x81C, 0xE1340203,
+	0x81C, 0xA5360203,
+	0x81C, 0xA4380203,
+	0x81C, 0xA33A0203,
+	0x81C, 0xA23C0203,
+	0x81C, 0x843E0203,
+	0x81C, 0x83400203,
+	0x81C, 0x82420203,
+	0x81C, 0x81440203,
+	0x81C, 0x64460203,
+	0x81C, 0x63480203,
+	0x81C, 0x624A0203,
+	0x81C, 0x614C0203,
+	0x81C, 0x474E0203,
+	0x81C, 0x46500203,
+	0x81C, 0x45520203,
+	0x81C, 0x44540203,
+	0x81C, 0x43560203,
+	0x81C, 0x25580203,
+	0x81C, 0x245A0203,
+	0x81C, 0x235C0203,
+	0x81C, 0x075E0203,
+	0x81C, 0x06600203,
+	0x81C, 0x05620203,
+	0x81C, 0x04640203,
+	0x81C, 0x03660203,
+	0x81C, 0x02680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFC000203,
+	0x81C, 0xFB020203,
+	0x81C, 0xFA040203,
+	0x81C, 0xF9060203,
+	0x81C, 0xF8080203,
+	0x81C, 0xF70A0203,
+	0x81C, 0xF60C0203,
+	0x81C, 0xF50E0203,
+	0x81C, 0xF4100203,
+	0x81C, 0xF3120203,
+	0x81C, 0xF2140203,
+	0x81C, 0xF1160203,
+	0x81C, 0xF0180203,
+	0x81C, 0xEF1A0203,
+	0x81C, 0xEE1C0203,
+	0x81C, 0xED1E0203,
+	0x81C, 0xEC200203,
+	0x81C, 0xEB220203,
+	0x81C, 0xEA240203,
+	0x81C, 0xE9260203,
+	0x81C, 0xE8280203,
+	0x81C, 0xE72A0203,
+	0x81C, 0xE62C0203,
+	0x81C, 0xE52E0203,
+	0x81C, 0xE4300203,
+	0x81C, 0xE3320203,
+	0x81C, 0xE2340203,
+	0x81C, 0xE1360203,
+	0x81C, 0xA5380203,
+	0x81C, 0xA43A0203,
+	0x81C, 0xA33C0203,
+	0x81C, 0x853E0203,
+	0x81C, 0x84400203,
+	0x81C, 0x83420203,
+	0x81C, 0x82440203,
+	0x81C, 0x81460203,
+	0x81C, 0x64480203,
+	0x81C, 0x634A0203,
+	0x81C, 0x624C0203,
+	0x81C, 0x614E0203,
+	0x81C, 0x46500203,
+	0x81C, 0x45520203,
+	0x81C, 0x44540203,
+	0x81C, 0x43560203,
+	0x81C, 0x25580203,
+	0x81C, 0x245A0203,
+	0x81C, 0x235C0203,
+	0x81C, 0x075E0203,
+	0x81C, 0x06600203,
+	0x81C, 0x05620203,
+	0x81C, 0x04640203,
+	0x81C, 0x03660203,
+	0x81C, 0x02680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000203,
+	0x81C, 0xFF020203,
+	0x81C, 0xFE040203,
+	0x81C, 0xFD060203,
+	0x81C, 0xFC080203,
+	0x81C, 0xFB0A0203,
+	0x81C, 0xFA0C0203,
+	0x81C, 0xF90E0203,
+	0x81C, 0xF8100203,
+	0x81C, 0xF7120203,
+	0x81C, 0xF6140203,
+	0x81C, 0xF5160203,
+	0x81C, 0xF4180203,
+	0x81C, 0xF31A0203,
+	0x81C, 0xF21C0203,
+	0x81C, 0xF11E0203,
+	0x81C, 0xF0200203,
+	0x81C, 0xEF220203,
+	0x81C, 0xEE240203,
+	0x81C, 0xED260203,
+	0x81C, 0xEC280203,
+	0x81C, 0xEB2A0203,
+	0x81C, 0xEA2C0203,
+	0x81C, 0xE92E0203,
+	0x81C, 0xE8300203,
+	0x81C, 0xE7320203,
+	0x81C, 0xE6340203,
+	0x81C, 0xE5360203,
+	0x81C, 0xE4380203,
+	0x81C, 0xE33A0203,
+	0x81C, 0xE23C0203,
+	0x81C, 0xE13E0203,
+	0x81C, 0xA4400203,
+	0x81C, 0xA3420203,
+	0x81C, 0xA2440203,
+	0x81C, 0xA1460203,
+	0x81C, 0x84480203,
+	0x81C, 0x834A0203,
+	0x81C, 0x824C0203,
+	0x81C, 0x814E0203,
+	0x81C, 0x64500203,
+	0x81C, 0x63520203,
+	0x81C, 0x62540203,
+	0x81C, 0x61560203,
+	0x81C, 0x45580203,
+	0x81C, 0x445A0203,
+	0x81C, 0x435C0203,
+	0x81C, 0x425E0203,
+	0x81C, 0x24600203,
+	0x81C, 0x23620203,
+	0x81C, 0x07640203,
+	0x81C, 0x06660203,
+	0x81C, 0x05680203,
+	0x81C, 0x046A0203,
+	0x81C, 0x036C0203,
+	0x81C, 0x026E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000203,
+	0x81C, 0xF6020203,
+	0x81C, 0xF5040203,
+	0x81C, 0xF4060203,
+	0x81C, 0xF3080203,
+	0x81C, 0xF20A0203,
+	0x81C, 0xF10C0203,
+	0x81C, 0xF00E0203,
+	0x81C, 0xEF100203,
+	0x81C, 0xEE120203,
+	0x81C, 0xED140203,
+	0x81C, 0xEC160203,
+	0x81C, 0xEB180203,
+	0x81C, 0xEA1A0203,
+	0x81C, 0xE91C0203,
+	0x81C, 0xE81E0203,
+	0x81C, 0xE7200203,
+	0x81C, 0xE6220203,
+	0x81C, 0xE5240203,
+	0x81C, 0xE4260203,
+	0x81C, 0xE3280203,
+	0x81C, 0xE22A0203,
+	0x81C, 0xA62C0203,
+	0x81C, 0xA52E0203,
+	0x81C, 0xA4300203,
+	0x81C, 0xA3320203,
+	0x81C, 0xA2340203,
+	0x81C, 0xA1360203,
+	0x81C, 0x86380203,
+	0x81C, 0x853A0203,
+	0x81C, 0x843C0203,
+	0x81C, 0x833E0203,
+	0x81C, 0x65400203,
+	0x81C, 0x64420203,
+	0x81C, 0x63440203,
+	0x81C, 0x46460203,
+	0x81C, 0x45480203,
+	0x81C, 0x444A0203,
+	0x81C, 0x434C0203,
+	0x81C, 0x264E0203,
+	0x81C, 0x25500203,
+	0x81C, 0x24520203,
+	0x81C, 0x08540203,
+	0x81C, 0x07560203,
+	0x81C, 0x06580203,
+	0x81C, 0x055A0203,
+	0x81C, 0x045C0203,
+	0x81C, 0x035E0203,
+	0x81C, 0x02600203,
+	0x81C, 0x01620203,
+	0x81C, 0x01640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFF000203,
+	0x81C, 0xFF020203,
+	0x81C, 0xFE040203,
+	0x81C, 0xFD060203,
+	0x81C, 0xFC080203,
+	0x81C, 0xFB0A0203,
+	0x81C, 0xFA0C0203,
+	0x81C, 0xF90E0203,
+	0x81C, 0xF8100203,
+	0x81C, 0xF7120203,
+	0x81C, 0xF6140203,
+	0x81C, 0xF5160203,
+	0x81C, 0xF4180203,
+	0x81C, 0xF31A0203,
+	0x81C, 0xF21C0203,
+	0x81C, 0xF11E0203,
+	0x81C, 0xF0200203,
+	0x81C, 0xEF220203,
+	0x81C, 0xEE240203,
+	0x81C, 0xED260203,
+	0x81C, 0xEC280203,
+	0x81C, 0xEB2A0203,
+	0x81C, 0xEA2C0203,
+	0x81C, 0xE92E0203,
+	0x81C, 0xE8300203,
+	0x81C, 0xE7320203,
+	0x81C, 0xE6340203,
+	0x81C, 0xE5360203,
+	0x81C, 0xE4380203,
+	0x81C, 0xE33A0203,
+	0x81C, 0xE23C0203,
+	0x81C, 0xE13E0203,
+	0x81C, 0xA4400203,
+	0x81C, 0xA3420203,
+	0x81C, 0xA2440203,
+	0x81C, 0xA1460203,
+	0x81C, 0x84480203,
+	0x81C, 0x834A0203,
+	0x81C, 0x824C0203,
+	0x81C, 0x814E0203,
+	0x81C, 0x64500203,
+	0x81C, 0x63520203,
+	0x81C, 0x62540203,
+	0x81C, 0x61560203,
+	0x81C, 0x45580203,
+	0x81C, 0x445A0203,
+	0x81C, 0x435C0203,
+	0x81C, 0x425E0203,
+	0x81C, 0x24600203,
+	0x81C, 0x23620203,
+	0x81C, 0x07640203,
+	0x81C, 0x06660203,
+	0x81C, 0x05680203,
+	0x81C, 0x046A0203,
+	0x81C, 0x036C0203,
+	0x81C, 0x026E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000203,
+	0x81C, 0xF7020203,
+	0x81C, 0xF6040203,
+	0x81C, 0xF5060203,
+	0x81C, 0xF4080203,
+	0x81C, 0xF30A0203,
+	0x81C, 0xF20C0203,
+	0x81C, 0xF10E0203,
+	0x81C, 0xF0100203,
+	0x81C, 0xEF120203,
+	0x81C, 0xEE140203,
+	0x81C, 0xED160203,
+	0x81C, 0xEC180203,
+	0x81C, 0xEB1A0203,
+	0x81C, 0xEA1C0203,
+	0x81C, 0xE91E0203,
+	0x81C, 0xE8200203,
+	0x81C, 0xE7220203,
+	0x81C, 0xE6240203,
+	0x81C, 0xE5260203,
+	0x81C, 0xE4280203,
+	0x81C, 0xE32A0203,
+	0x81C, 0xE22C0203,
+	0x81C, 0xE12E0203,
+	0x81C, 0xA6300203,
+	0x81C, 0xA5320203,
+	0x81C, 0xA4340203,
+	0x81C, 0xA3360203,
+	0x81C, 0xA2380203,
+	0x81C, 0xA13A0203,
+	0x81C, 0x843C0203,
+	0x81C, 0x833E0203,
+	0x81C, 0x82400203,
+	0x81C, 0x81420203,
+	0x81C, 0x64440203,
+	0x81C, 0x63460203,
+	0x81C, 0x62480203,
+	0x81C, 0x614A0203,
+	0x81C, 0x444C0203,
+	0x81C, 0x434E0203,
+	0x81C, 0x42500203,
+	0x81C, 0x41520203,
+	0x81C, 0x25540203,
+	0x81C, 0x24560203,
+	0x81C, 0x23580203,
+	0x81C, 0x065A0203,
+	0x81C, 0x055C0203,
+	0x81C, 0x045E0203,
+	0x81C, 0x03600203,
+	0x81C, 0x02620203,
+	0x81C, 0x01640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000203,
+	0x81C, 0xF8020203,
+	0x81C, 0xF7040203,
+	0x81C, 0xF6060203,
+	0x81C, 0xF5080203,
+	0x81C, 0xF40A0203,
+	0x81C, 0xF30C0203,
+	0x81C, 0xF20E0203,
+	0x81C, 0xF1100203,
+	0x81C, 0xF0120203,
+	0x81C, 0xEF140203,
+	0x81C, 0xCE160203,
+	0x81C, 0xCD180203,
+	0x81C, 0xCC1A0203,
+	0x81C, 0xCB1C0203,
+	0x81C, 0xCA1E0203,
+	0x81C, 0xC9200203,
+	0x81C, 0xC8220203,
+	0x81C, 0xC7240203,
+	0x81C, 0xC6260203,
+	0x81C, 0xC5280203,
+	0x81C, 0xC42A0203,
+	0x81C, 0xC32C0203,
+	0x81C, 0xC22E0203,
+	0x81C, 0xC1300203,
+	0x81C, 0xA5320203,
+	0x81C, 0xA4340203,
+	0x81C, 0xA3360203,
+	0x81C, 0xA2380203,
+	0x81C, 0xA13A0203,
+	0x81C, 0x853C0203,
+	0x81C, 0x843E0203,
+	0x81C, 0x83400203,
+	0x81C, 0x82420203,
+	0x81C, 0x81440203,
+	0x81C, 0x64460203,
+	0x81C, 0x63480203,
+	0x81C, 0x624A0203,
+	0x81C, 0x614C0203,
+	0x81C, 0x444E0203,
+	0x81C, 0x43500203,
+	0x81C, 0x42520203,
+	0x81C, 0x41540203,
+	0x81C, 0x24560203,
+	0x81C, 0x23580203,
+	0x81C, 0x075A0203,
+	0x81C, 0x065C0203,
+	0x81C, 0x055E0203,
+	0x81C, 0x04600203,
+	0x81C, 0x03620203,
+	0x81C, 0x02640203,
+	0x81C, 0x01660203,
+	0x81C, 0x01680203,
+	0x81C, 0x016A0203,
+	0x81C, 0x016C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0xA0000000,	0x00000000,
+	0x81C, 0xFF000203,
+	0x81C, 0xFF020203,
+	0x81C, 0xFE040203,
+	0x81C, 0xFD060203,
+	0x81C, 0xFC080203,
+	0x81C, 0xFB0A0203,
+	0x81C, 0xFA0C0203,
+	0x81C, 0xF90E0203,
+	0x81C, 0xF8100203,
+	0x81C, 0xF7120203,
+	0x81C, 0xF6140203,
+	0x81C, 0xF5160203,
+	0x81C, 0xF4180203,
+	0x81C, 0xF31A0203,
+	0x81C, 0xF21C0203,
+	0x81C, 0xF11E0203,
+	0x81C, 0xF0200203,
+	0x81C, 0xEF220203,
+	0x81C, 0xEE240203,
+	0x81C, 0xED260203,
+	0x81C, 0xEC280203,
+	0x81C, 0xEB2A0203,
+	0x81C, 0xEA2C0203,
+	0x81C, 0xE92E0203,
+	0x81C, 0xE8300203,
+	0x81C, 0xE7320203,
+	0x81C, 0xE6340203,
+	0x81C, 0xE5360203,
+	0x81C, 0xE4380203,
+	0x81C, 0xE33A0203,
+	0x81C, 0xE23C0203,
+	0x81C, 0xE13E0203,
+	0x81C, 0xA4400203,
+	0x81C, 0xA3420203,
+	0x81C, 0xA2440203,
+	0x81C, 0xA1460203,
+	0x81C, 0x85480203,
+	0x81C, 0x844A0203,
+	0x81C, 0x834C0203,
+	0x81C, 0x824E0203,
+	0x81C, 0x81500203,
+	0x81C, 0x64520203,
+	0x81C, 0x63540203,
+	0x81C, 0x62560203,
+	0x81C, 0x61580203,
+	0x81C, 0x445A0203,
+	0x81C, 0x435C0203,
+	0x81C, 0x425E0203,
+	0x81C, 0x25600203,
+	0x81C, 0x24620203,
+	0x81C, 0x06640203,
+	0x81C, 0x05660203,
+	0x81C, 0x04680203,
+	0x81C, 0x036A0203,
+	0x81C, 0x026C0203,
+	0x81C, 0x016E0203,
+	0x81C, 0x01700203,
+	0x81C, 0x01720203,
+	0x81C, 0x01740203,
+	0x81C, 0x01760203,
+	0x81C, 0x01780203,
+	0x81C, 0x017A0203,
+	0x81C, 0x017C0203,
+	0x81C, 0x017E0203,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF8000303,
+	0x81C, 0xF7020303,
+	0x81C, 0xF6040303,
+	0x81C, 0xF5060303,
+	0x81C, 0xF4080303,
+	0x81C, 0xF30A0303,
+	0x81C, 0xF20C0303,
+	0x81C, 0xF10E0303,
+	0x81C, 0xF0100303,
+	0x81C, 0xEF120303,
+	0x81C, 0xEE140303,
+	0x81C, 0xED160303,
+	0x81C, 0xEC180303,
+	0x81C, 0xEB1A0303,
+	0x81C, 0xEA1C0303,
+	0x81C, 0xE91E0303,
+	0x81C, 0xE8200303,
+	0x81C, 0xE7220303,
+	0x81C, 0xE6240303,
+	0x81C, 0xE5260303,
+	0x81C, 0xE4280303,
+	0x81C, 0xE32A0303,
+	0x81C, 0xE22C0303,
+	0x81C, 0xE12E0303,
+	0x81C, 0xA6300303,
+	0x81C, 0xA5320303,
+	0x81C, 0xA4340303,
+	0x81C, 0xA3360303,
+	0x81C, 0xA2380303,
+	0x81C, 0xA13A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x454C0303,
+	0x81C, 0x444E0303,
+	0x81C, 0x43500303,
+	0x81C, 0x42520303,
+	0x81C, 0x41540303,
+	0x81C, 0x24560303,
+	0x81C, 0x23580303,
+	0x81C, 0x065A0303,
+	0x81C, 0x055C0303,
+	0x81C, 0x045E0303,
+	0x81C, 0x03600303,
+	0x81C, 0x02620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000303,
+	0x81C, 0xF6020303,
+	0x81C, 0xF5040303,
+	0x81C, 0xF4060303,
+	0x81C, 0xF3080303,
+	0x81C, 0xF20A0303,
+	0x81C, 0xF10C0303,
+	0x81C, 0xF00E0303,
+	0x81C, 0xEF100303,
+	0x81C, 0xEE120303,
+	0x81C, 0xED140303,
+	0x81C, 0xEC160303,
+	0x81C, 0xEB180303,
+	0x81C, 0xEA1A0303,
+	0x81C, 0xE91C0303,
+	0x81C, 0xE81E0303,
+	0x81C, 0xE7200303,
+	0x81C, 0xE6220303,
+	0x81C, 0xE5240303,
+	0x81C, 0xE4260303,
+	0x81C, 0xE3280303,
+	0x81C, 0xC32A0303,
+	0x81C, 0xC22C0303,
+	0x81C, 0xC12E0303,
+	0x81C, 0xA5300303,
+	0x81C, 0xA4320303,
+	0x81C, 0xA3340303,
+	0x81C, 0xA2360303,
+	0x81C, 0xA1380303,
+	0x81C, 0x853A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x454C0303,
+	0x81C, 0x444E0303,
+	0x81C, 0x43500303,
+	0x81C, 0x25520303,
+	0x81C, 0x24540303,
+	0x81C, 0x23560303,
+	0x81C, 0x06580303,
+	0x81C, 0x055A0303,
+	0x81C, 0x045C0303,
+	0x81C, 0x035E0303,
+	0x81C, 0x02600303,
+	0x81C, 0x01620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000303,
+	0x81C, 0xF8020303,
+	0x81C, 0xF7040303,
+	0x81C, 0xF6060303,
+	0x81C, 0xF5080303,
+	0x81C, 0xF40A0303,
+	0x81C, 0xF30C0303,
+	0x81C, 0xF20E0303,
+	0x81C, 0xF1100303,
+	0x81C, 0xF0120303,
+	0x81C, 0xEF140303,
+	0x81C, 0xEE160303,
+	0x81C, 0xED180303,
+	0x81C, 0xEC1A0303,
+	0x81C, 0xEB1C0303,
+	0x81C, 0xEA1E0303,
+	0x81C, 0xE9200303,
+	0x81C, 0xE8220303,
+	0x81C, 0xE7240303,
+	0x81C, 0xE6260303,
+	0x81C, 0xE5280303,
+	0x81C, 0xE42A0303,
+	0x81C, 0xE32C0303,
+	0x81C, 0xE22E0303,
+	0x81C, 0xE1300303,
+	0x81C, 0xA4320303,
+	0x81C, 0xA3340303,
+	0x81C, 0xA2360303,
+	0x81C, 0xA1380303,
+	0x81C, 0x853A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x444C0303,
+	0x81C, 0x434E0303,
+	0x81C, 0x42500303,
+	0x81C, 0x25520303,
+	0x81C, 0x24540303,
+	0x81C, 0x23560303,
+	0x81C, 0x07580303,
+	0x81C, 0x065A0303,
+	0x81C, 0x055C0303,
+	0x81C, 0x045E0303,
+	0x81C, 0x03600303,
+	0x81C, 0x02620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000303,
+	0x81C, 0xF6020303,
+	0x81C, 0xF5040303,
+	0x81C, 0xF4060303,
+	0x81C, 0xF3080303,
+	0x81C, 0xF20A0303,
+	0x81C, 0xF10C0303,
+	0x81C, 0xF00E0303,
+	0x81C, 0xEF100303,
+	0x81C, 0xEE120303,
+	0x81C, 0xED140303,
+	0x81C, 0xEC160303,
+	0x81C, 0xEB180303,
+	0x81C, 0xEA1A0303,
+	0x81C, 0xE91C0303,
+	0x81C, 0xE81E0303,
+	0x81C, 0xE7200303,
+	0x81C, 0xE6220303,
+	0x81C, 0xE5240303,
+	0x81C, 0xE4260303,
+	0x81C, 0xE3280303,
+	0x81C, 0xE22A0303,
+	0x81C, 0xE12C0303,
+	0x81C, 0xA72E0303,
+	0x81C, 0xA6300303,
+	0x81C, 0xA5320303,
+	0x81C, 0xA4340303,
+	0x81C, 0xA3360303,
+	0x81C, 0xA2380303,
+	0x81C, 0xA13A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x454C0303,
+	0x81C, 0x444E0303,
+	0x81C, 0x43500303,
+	0x81C, 0x42520303,
+	0x81C, 0x41540303,
+	0x81C, 0x24560303,
+	0x81C, 0x23580303,
+	0x81C, 0x065A0303,
+	0x81C, 0x055C0303,
+	0x81C, 0x045E0303,
+	0x81C, 0x03600303,
+	0x81C, 0x02620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFB000303,
+	0x81C, 0xFA020303,
+	0x81C, 0xF9040303,
+	0x81C, 0xF8060303,
+	0x81C, 0xF7080303,
+	0x81C, 0xF60A0303,
+	0x81C, 0xF50C0303,
+	0x81C, 0xF40E0303,
+	0x81C, 0xF3100303,
+	0x81C, 0xF2120303,
+	0x81C, 0xF1140303,
+	0x81C, 0xF0160303,
+	0x81C, 0xEF180303,
+	0x81C, 0xEE1A0303,
+	0x81C, 0xED1C0303,
+	0x81C, 0xEC1E0303,
+	0x81C, 0xEB200303,
+	0x81C, 0xEA220303,
+	0x81C, 0xE9240303,
+	0x81C, 0xE8260303,
+	0x81C, 0xE7280303,
+	0x81C, 0xE62A0303,
+	0x81C, 0xE52C0303,
+	0x81C, 0xE42E0303,
+	0x81C, 0xE3300303,
+	0x81C, 0xE2320303,
+	0x81C, 0xE1340303,
+	0x81C, 0xC2360303,
+	0x81C, 0xC1380303,
+	0x81C, 0xA33A0303,
+	0x81C, 0xA23C0303,
+	0x81C, 0x853E0303,
+	0x81C, 0x84400303,
+	0x81C, 0x83420303,
+	0x81C, 0x66440303,
+	0x81C, 0x65460303,
+	0x81C, 0x64480303,
+	0x81C, 0x634A0303,
+	0x81C, 0x624C0303,
+	0x81C, 0x614E0303,
+	0x81C, 0x45500303,
+	0x81C, 0x44520303,
+	0x81C, 0x43540303,
+	0x81C, 0x42560303,
+	0x81C, 0x25580303,
+	0x81C, 0x245A0303,
+	0x81C, 0x235C0303,
+	0x81C, 0x065E0303,
+	0x81C, 0x05600303,
+	0x81C, 0x04620303,
+	0x81C, 0x03640303,
+	0x81C, 0x02660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF9000303,
+	0x81C, 0xF8020303,
+	0x81C, 0xF7040303,
+	0x81C, 0xF6060303,
+	0x81C, 0xF5080303,
+	0x81C, 0xF40A0303,
+	0x81C, 0xF30C0303,
+	0x81C, 0xF20E0303,
+	0x81C, 0xF1100303,
+	0x81C, 0xF0120303,
+	0x81C, 0xEF140303,
+	0x81C, 0xEE160303,
+	0x81C, 0xED180303,
+	0x81C, 0xEC1A0303,
+	0x81C, 0xEB1C0303,
+	0x81C, 0xEA1E0303,
+	0x81C, 0xE9200303,
+	0x81C, 0xE8220303,
+	0x81C, 0xE7240303,
+	0x81C, 0xE6260303,
+	0x81C, 0xE5280303,
+	0x81C, 0xE42A0303,
+	0x81C, 0xE32C0303,
+	0x81C, 0xE22E0303,
+	0x81C, 0xE1300303,
+	0x81C, 0xA6320303,
+	0x81C, 0xA5340303,
+	0x81C, 0xA4360303,
+	0x81C, 0xA3380303,
+	0x81C, 0xA23A0303,
+	0x81C, 0xA13C0303,
+	0x81C, 0x853E0303,
+	0x81C, 0x84400303,
+	0x81C, 0x83420303,
+	0x81C, 0x82440303,
+	0x81C, 0x81460303,
+	0x81C, 0x64480303,
+	0x81C, 0x634A0303,
+	0x81C, 0x624C0303,
+	0x81C, 0x614E0303,
+	0x81C, 0x44500303,
+	0x81C, 0x43520303,
+	0x81C, 0x42540303,
+	0x81C, 0x41560303,
+	0x81C, 0x25580303,
+	0x81C, 0x245A0303,
+	0x81C, 0x235C0303,
+	0x81C, 0x055E0303,
+	0x81C, 0x04600303,
+	0x81C, 0x03620303,
+	0x81C, 0x02640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000303,
+	0x81C, 0xFD020303,
+	0x81C, 0xFC040303,
+	0x81C, 0xFB060303,
+	0x81C, 0xFA080303,
+	0x81C, 0xF90A0303,
+	0x81C, 0xF80C0303,
+	0x81C, 0xF70E0303,
+	0x81C, 0xF6100303,
+	0x81C, 0xF5120303,
+	0x81C, 0xF4140303,
+	0x81C, 0xF3160303,
+	0x81C, 0xF2180303,
+	0x81C, 0xF11A0303,
+	0x81C, 0xF01C0303,
+	0x81C, 0xEF1E0303,
+	0x81C, 0xEE200303,
+	0x81C, 0xED220303,
+	0x81C, 0xEC240303,
+	0x81C, 0xEB260303,
+	0x81C, 0xEA280303,
+	0x81C, 0xE92A0303,
+	0x81C, 0xE82C0303,
+	0x81C, 0xE72E0303,
+	0x81C, 0xE6300303,
+	0x81C, 0xE5320303,
+	0x81C, 0xE4340303,
+	0x81C, 0xE3360303,
+	0x81C, 0xC3380303,
+	0x81C, 0xC23A0303,
+	0x81C, 0xC13C0303,
+	0x81C, 0xA43E0303,
+	0x81C, 0xA3400303,
+	0x81C, 0xA2420303,
+	0x81C, 0xA1440303,
+	0x81C, 0x85460303,
+	0x81C, 0x84480303,
+	0x81C, 0x834A0303,
+	0x81C, 0x824C0303,
+	0x81C, 0x814E0303,
+	0x81C, 0x64500303,
+	0x81C, 0x63520303,
+	0x81C, 0x62540303,
+	0x81C, 0x61560303,
+	0x81C, 0x44580303,
+	0x81C, 0x435A0303,
+	0x81C, 0x425C0303,
+	0x81C, 0x265E0303,
+	0x81C, 0x25600303,
+	0x81C, 0x24620303,
+	0x81C, 0x06640303,
+	0x81C, 0x05660303,
+	0x81C, 0x04680303,
+	0x81C, 0x036A0303,
+	0x81C, 0x026C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000303,
+	0x81C, 0xF6020303,
+	0x81C, 0xF5040303,
+	0x81C, 0xF4060303,
+	0x81C, 0xF3080303,
+	0x81C, 0xF20A0303,
+	0x81C, 0xF10C0303,
+	0x81C, 0xF00E0303,
+	0x81C, 0xEF100303,
+	0x81C, 0xEE120303,
+	0x81C, 0xED140303,
+	0x81C, 0xEC160303,
+	0x81C, 0xEB180303,
+	0x81C, 0xEA1A0303,
+	0x81C, 0xE91C0303,
+	0x81C, 0xE81E0303,
+	0x81C, 0xE7200303,
+	0x81C, 0xE6220303,
+	0x81C, 0xE5240303,
+	0x81C, 0xE4260303,
+	0x81C, 0xE3280303,
+	0x81C, 0xE22A0303,
+	0x81C, 0xA62C0303,
+	0x81C, 0xA52E0303,
+	0x81C, 0xA4300303,
+	0x81C, 0xA3320303,
+	0x81C, 0xA2340303,
+	0x81C, 0x87360303,
+	0x81C, 0x86380303,
+	0x81C, 0x853A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x66400303,
+	0x81C, 0x65420303,
+	0x81C, 0x64440303,
+	0x81C, 0x45460303,
+	0x81C, 0x44480303,
+	0x81C, 0x434A0303,
+	0x81C, 0x274C0303,
+	0x81C, 0x264E0303,
+	0x81C, 0x25500303,
+	0x81C, 0x24520303,
+	0x81C, 0x23540303,
+	0x81C, 0x08560303,
+	0x81C, 0x07580303,
+	0x81C, 0x065A0303,
+	0x81C, 0x055C0303,
+	0x81C, 0x045E0303,
+	0x81C, 0x03600303,
+	0x81C, 0x02620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xFE000303,
+	0x81C, 0xFD020303,
+	0x81C, 0xFC040303,
+	0x81C, 0xFB060303,
+	0x81C, 0xFA080303,
+	0x81C, 0xF90A0303,
+	0x81C, 0xF80C0303,
+	0x81C, 0xF70E0303,
+	0x81C, 0xF6100303,
+	0x81C, 0xF5120303,
+	0x81C, 0xF4140303,
+	0x81C, 0xF3160303,
+	0x81C, 0xF2180303,
+	0x81C, 0xF11A0303,
+	0x81C, 0xF01C0303,
+	0x81C, 0xEF1E0303,
+	0x81C, 0xEE200303,
+	0x81C, 0xED220303,
+	0x81C, 0xEC240303,
+	0x81C, 0xEB260303,
+	0x81C, 0xEA280303,
+	0x81C, 0xE92A0303,
+	0x81C, 0xE82C0303,
+	0x81C, 0xE72E0303,
+	0x81C, 0xE6300303,
+	0x81C, 0xE5320303,
+	0x81C, 0xE4340303,
+	0x81C, 0xE3360303,
+	0x81C, 0xC3380303,
+	0x81C, 0xC23A0303,
+	0x81C, 0xC13C0303,
+	0x81C, 0xA43E0303,
+	0x81C, 0xA3400303,
+	0x81C, 0xA2420303,
+	0x81C, 0xA1440303,
+	0x81C, 0x85460303,
+	0x81C, 0x84480303,
+	0x81C, 0x834A0303,
+	0x81C, 0x824C0303,
+	0x81C, 0x814E0303,
+	0x81C, 0x64500303,
+	0x81C, 0x63520303,
+	0x81C, 0x62540303,
+	0x81C, 0x61560303,
+	0x81C, 0x44580303,
+	0x81C, 0x435A0303,
+	0x81C, 0x425C0303,
+	0x81C, 0x265E0303,
+	0x81C, 0x25600303,
+	0x81C, 0x24620303,
+	0x81C, 0x06640303,
+	0x81C, 0x05660303,
+	0x81C, 0x04680303,
+	0x81C, 0x036A0303,
+	0x81C, 0x026C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000303,
+	0x81C, 0xF6020303,
+	0x81C, 0xF5040303,
+	0x81C, 0xF4060303,
+	0x81C, 0xF3080303,
+	0x81C, 0xF20A0303,
+	0x81C, 0xF10C0303,
+	0x81C, 0xF00E0303,
+	0x81C, 0xEF100303,
+	0x81C, 0xEE120303,
+	0x81C, 0xED140303,
+	0x81C, 0xEC160303,
+	0x81C, 0xEB180303,
+	0x81C, 0xEA1A0303,
+	0x81C, 0xE91C0303,
+	0x81C, 0xE81E0303,
+	0x81C, 0xE7200303,
+	0x81C, 0xE6220303,
+	0x81C, 0xE5240303,
+	0x81C, 0xE4260303,
+	0x81C, 0xE3280303,
+	0x81C, 0xE22A0303,
+	0x81C, 0xE12C0303,
+	0x81C, 0xA72E0303,
+	0x81C, 0xA6300303,
+	0x81C, 0xA5320303,
+	0x81C, 0xA4340303,
+	0x81C, 0xA3360303,
+	0x81C, 0xA2380303,
+	0x81C, 0xA13A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x454C0303,
+	0x81C, 0x444E0303,
+	0x81C, 0x43500303,
+	0x81C, 0x42520303,
+	0x81C, 0x41540303,
+	0x81C, 0x24560303,
+	0x81C, 0x23580303,
+	0x81C, 0x065A0303,
+	0x81C, 0x055C0303,
+	0x81C, 0x045E0303,
+	0x81C, 0x03600303,
+	0x81C, 0x02620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x81C, 0xF7000303,
+	0x81C, 0xF6020303,
+	0x81C, 0xF5040303,
+	0x81C, 0xF4060303,
+	0x81C, 0xF3080303,
+	0x81C, 0xF20A0303,
+	0x81C, 0xF10C0303,
+	0x81C, 0xF00E0303,
+	0x81C, 0xEF100303,
+	0x81C, 0xEE120303,
+	0x81C, 0xED140303,
+	0x81C, 0xEC160303,
+	0x81C, 0xEB180303,
+	0x81C, 0xEA1A0303,
+	0x81C, 0xAF1C0303,
+	0x81C, 0xAE1E0303,
+	0x81C, 0xAD200303,
+	0x81C, 0xAC220303,
+	0x81C, 0xAB240303,
+	0x81C, 0xAA260303,
+	0x81C, 0xC5280303,
+	0x81C, 0xC42A0303,
+	0x81C, 0xC32C0303,
+	0x81C, 0xC22E0303,
+	0x81C, 0xA5300303,
+	0x81C, 0xA4320303,
+	0x81C, 0xA3340303,
+	0x81C, 0xA2360303,
+	0x81C, 0xA1380303,
+	0x81C, 0x853A0303,
+	0x81C, 0x843C0303,
+	0x81C, 0x833E0303,
+	0x81C, 0x82400303,
+	0x81C, 0x81420303,
+	0x81C, 0x64440303,
+	0x81C, 0x63460303,
+	0x81C, 0x62480303,
+	0x81C, 0x614A0303,
+	0x81C, 0x444C0303,
+	0x81C, 0x434E0303,
+	0x81C, 0x42500303,
+	0x81C, 0x41520303,
+	0x81C, 0x25540303,
+	0x81C, 0x24560303,
+	0x81C, 0x06580303,
+	0x81C, 0x055A0303,
+	0x81C, 0x045C0303,
+	0x81C, 0x035E0303,
+	0x81C, 0x02600303,
+	0x81C, 0x01620303,
+	0x81C, 0x01640303,
+	0x81C, 0x01660303,
+	0x81C, 0x01680303,
+	0x81C, 0x016A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0xA0000000,	0x00000000,
+	0x81C, 0xFD000303,
+	0x81C, 0xFC020303,
+	0x81C, 0xFB040303,
+	0x81C, 0xFA060303,
+	0x81C, 0xF9080303,
+	0x81C, 0xF80A0303,
+	0x81C, 0xF70C0303,
+	0x81C, 0xF60E0303,
+	0x81C, 0xF5100303,
+	0x81C, 0xF4120303,
+	0x81C, 0xF3140303,
+	0x81C, 0xF2160303,
+	0x81C, 0xF1180303,
+	0x81C, 0xF01A0303,
+	0x81C, 0xEF1C0303,
+	0x81C, 0xEE1E0303,
+	0x81C, 0xED200303,
+	0x81C, 0xEC220303,
+	0x81C, 0xEB240303,
+	0x81C, 0xEA260303,
+	0x81C, 0xE9280303,
+	0x81C, 0xE82A0303,
+	0x81C, 0xE72C0303,
+	0x81C, 0xE62E0303,
+	0x81C, 0xE5300303,
+	0x81C, 0xE4320303,
+	0x81C, 0xE3340303,
+	0x81C, 0xE2360303,
+	0x81C, 0xE1380303,
+	0x81C, 0xA53A0303,
+	0x81C, 0xA43C0303,
+	0x81C, 0xA33E0303,
+	0x81C, 0xA2400303,
+	0x81C, 0xA1420303,
+	0x81C, 0x87440303,
+	0x81C, 0x86460303,
+	0x81C, 0x85480303,
+	0x81C, 0x844A0303,
+	0x81C, 0x834C0303,
+	0x81C, 0x824E0303,
+	0x81C, 0x81500303,
+	0x81C, 0x64520303,
+	0x81C, 0x63540303,
+	0x81C, 0x62560303,
+	0x81C, 0x61580303,
+	0x81C, 0x435A0303,
+	0x81C, 0x425C0303,
+	0x81C, 0x415E0303,
+	0x81C, 0x07600303,
+	0x81C, 0x06620303,
+	0x81C, 0x05640303,
+	0x81C, 0x04660303,
+	0x81C, 0x03680303,
+	0x81C, 0x026A0303,
+	0x81C, 0x016C0303,
+	0x81C, 0x016E0303,
+	0x81C, 0x01700303,
+	0x81C, 0x01720303,
+	0x81C, 0x01740303,
+	0x81C, 0x01760303,
+	0x81C, 0x01780303,
+	0x81C, 0x017A0303,
+	0x81C, 0x017C0303,
+	0x81C, 0x017E0303,
+	0xB0000000,	0x00000000,
+	0xC50, 0x00000022,
+	0xC50, 0x00000020,
+	0xE50, 0x00000022,
+	0xE50, 0x00000020,
+	0x1850, 0x00000022,
+	0x1850, 0x00000020,
+	0x1A50, 0x00000022,
+	0x1A50, 0x00000020,
+};
+
+RTW_DECL_TABLE_PHY_COND(rtw8814a_agc, rtw_phy_cfg_agc);
+
+static const u32 rtw8814a_bb[] = {
+	0x800, 0x9020D010,
+	0x804, 0x08011280,
+	0x808, 0x0E0282FF,
+	0x80C, 0x1000002F,
+	0x80000003,	0x00000000,	0x40000000,	0x00000000,
+	0x810, 0x33303265,
+	0xA0000000,	0x00000000,
+	0x810, 0x33303265,
+	0xB0000000,	0x00000000,
+	0x814, 0x020C3D10,
+	0x818, 0x04A10385,
+	0x820, 0x00000000,
+	0x824, 0x00033E40,
+	0x828, 0x00000000,
+	0x82C, 0x73985170,
+	0x830, 0x79A0EA08,
+	0x834, 0x042E708A,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x838, 0x86667640,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x838, 0x86667641,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x838, 0x86667641,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x838, 0x86667641,
+	0xA0000000,	0x00000000,
+	0x838, 0x86667640,
+	0xB0000000,	0x00000000,
+	0x83C, 0x9798B9B9,
+	0x840, 0x17578F60,
+	0x844, 0x4BBDFCDE,
+	0x848, 0x5CD07F8B,
+	0x84C, 0x6CFBF7B5,
+	0x850, 0x28834706,
+	0x854, 0x0001520C,
+	0x858, 0x4060C000,
+	0x85C, 0x74210368,
+	0x860, 0x6929C321,
+	0x864, 0x79727432,
+	0x868, 0x8CA7A314,
+	0x86C, 0x438C2878,
+	0x870, 0x44444444,
+	0x874, 0x21612C2E,
+	0x878, 0x00003152,
+	0x87C, 0x000FC000,
+	0x8A0, 0x00000013,
+	0x8A4, 0x7F7F7F7F,
+	0x8A8, 0xA202033E,
+	0x8AC, 0xF40F550A,
+	0x8B0, 0x00000600,
+	0x8B4, 0x000FC080,
+	0x8B8, 0xEC0057FF,
+	0x8BC, 0x8CA520C3,
+	0x8C0, 0x3FF00020,
+	0x8C4, 0x44C00000,
+	0x80000009,	0x00000000,	0x40000000,	0x00000000,
+	0x8C8, 0x80025969,
+	0xA0000000,	0x00000000,
+	0x8C8, 0x80025167,
+	0xB0000000,	0x00000000,
+	0x8CC, 0x08250492,
+	0x8D0, 0x0000B800,
+	0x8D4, 0x940008A0,
+	0x8D8, 0x290B5612,
+	0x8DC, 0x00000000,
+	0x8E0, 0x32316407,
+	0x8E4, 0x4A092925,
+	0x8E8, 0xFFFFC42C,
+	0x8EC, 0x99999999,
+	0x8F0, 0x00009999,
+	0x8F4, 0x00F80FA1,
+	0x8F8, 0x400082C0,
+	0x8FC, 0x00000000,
+	0x900, 0x00400700,
+	0x90C, 0x09004000,
+	0x910, 0x0000FC00,
+	0x914, 0xD6400404,
+	0x918, 0x1C1028C0,
+	0x91C, 0x64B11A1C,
+	0x920, 0xE0767233,
+	0x924, 0x055AA500,
+	0x928, 0x4AB0E4E4,
+	0x92C, 0xFFFE0000,
+	0x930, 0xFFFFFFFE,
+	0x934, 0x001FFFFF,
+	0x938, 0x00008400,
+	0x93C, 0x932C0642,
+	0x940, 0x093E9360,
+	0x944, 0x08000000,
+	0x948, 0x04000000,
+	0x950, 0x02010080,
+	0x954, 0x86510080,
+	0x960, 0x00000000,
+	0x964, 0x00000000,
+	0x968, 0x00000000,
+	0x96C, 0x00000000,
+	0x970, 0x801FFFFF,
+	0x978, 0x00000000,
+	0x97C, 0x00000000,
+	0x980, 0x00000000,
+	0x984, 0x00000000,
+	0x988, 0x00000000,
+	0x98C, 0x03440000,
+	0x990, 0x27100000,
+	0x994, 0xFFFF0100,
+	0x998, 0xFFFFFF5C,
+	0x99C, 0xFFFFFFFF,
+	0x9A0, 0x000000FF,
+	0x9A4, 0x00080080,
+	0x9A8, 0x0C2F0000,
+	0x9AC, 0x00560000,
+	0x9B0, 0x81081008,
+	0x9B4, 0x00000000,
+	0x9B8, 0x01081008,
+	0x9BC, 0x01081008,
+	0x9D0, 0x00000000,
+	0x9D4, 0x00000000,
+	0x9D8, 0x00000000,
+	0x9DC, 0x00000000,
+	0x9E4, 0x00000002,
+	0x9E8, 0x000022D5,
+	0x9FC, 0xEFFFF7FF,
+	0xB00, 0xE3100000,
+	0xB04, 0x0000B000,
+	0xB0C, 0x31EAA006,
+	0xB5C, 0x41CFFFFF,
+	0xC00, 0x00000007,
+	0xC04, 0x00042020,
+	0xC08, 0x80410231,
+	0xC0C, 0x00000000,
+	0xC10, 0x00000100,
+	0xC14, 0x01000000,
+	0xC1C, 0x40000053,
+	0xC50, 0x00000020,
+	0xC54, 0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0xC58, 0x3C0A0C14,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0xC58, 0x3C0A0C14,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0xC58, 0x3C0A0C14,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xC58, 0x3C0A0C14,
+	0xA0000000,	0x00000000,
+	0xC58, 0x3C020C14,
+	0xB0000000,	0x00000000,
+	0xC5C, 0x0D000058,
+	0xC60, 0x1B800000,
+	0xC60, 0x0B800001,
+	0xC60, 0x05800002,
+	0xC60, 0x07800003,
+	0xC60, 0x1A800004,
+	0xC60, 0x0B800005,
+	0xC60, 0x05800006,
+	0xC60, 0x0E800007,
+	0xC60, 0x1A800008,
+	0xC60, 0x0B800009,
+	0xC60, 0x1580000A,
+	0xC60, 0x0880000B,
+	0xC60, 0x1A80000C,
+	0xC60, 0x0B80000D,
+	0xC60, 0x0580000E,
+	0xC60, 0x0E80000F,
+	0xC60, 0x1A800010,
+	0xC60, 0x0B800011,
+	0xC60, 0x15800012,
+	0xC60, 0x08800013,
+	0xC60, 0x1A800014,
+	0xC60, 0x0B800015,
+	0xC60, 0x05800016,
+	0xC60, 0x07800017,
+	0xC60, 0x1A800018,
+	0xC60, 0x0B800019,
+	0xC60, 0x1580001A,
+	0xC60, 0x0880001B,
+	0xC60, 0x1B80001C,
+	0xC60, 0x0B80001D,
+	0xC60, 0x0580001E,
+	0xC60, 0x0780001F,
+	0xC60, 0x1B800020,
+	0xC60, 0x0B800021,
+	0xC60, 0x05800022,
+	0xC60, 0x07800023,
+	0xC60, 0x1B800024,
+	0xC60, 0x0B800025,
+	0xC60, 0x05800026,
+	0xC60, 0x07800027,
+	0xC60, 0x1B800028,
+	0xC60, 0x0B800029,
+	0xC60, 0x0580002A,
+	0xC60, 0x0780002B,
+	0xC60, 0x1B800030,
+	0xC60, 0x0B800031,
+	0xC60, 0x05800032,
+	0xC60, 0x00800033,
+	0xC60, 0x1B800034,
+	0xC60, 0x0B800035,
+	0xC60, 0x05800036,
+	0xC60, 0x00800037,
+	0xC60, 0x1B800038,
+	0xC60, 0x0B800039,
+	0xC60, 0x0580003A,
+	0xC60, 0x0E80803B,
+	0xC94, 0x01000401,
+	0xC98, 0x00188000,
+	0xCA0, 0x00002929,
+	0xCA4, 0x08040201,
+	0xCA8, 0x80402010,
+	0xCAC, 0x77777000,
+	0xCB0, 0x54775477,
+	0xCB4, 0x54775477,
+	0xCB8, 0x00500000,
+	0xCBC, 0x77700000,
+	0xCC0, 0x00000010,
+	0xCC8, 0x00000010,
+	0xE00, 0x00000007,
+	0xE04, 0x00042020,
+	0xE08, 0x80410231,
+	0xE0C, 0x00000000,
+	0xE10, 0x00000100,
+	0xE14, 0x01000000,
+	0xE1C, 0x40000053,
+	0xE50, 0x00000020,
+	0xE54, 0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0xE58, 0x3C0A0C14,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0xE58, 0x3C0A0C14,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0xE58, 0x3C0A0C14,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xE58, 0x3C0A0C14,
+	0xA0000000,	0x00000000,
+	0xE58, 0x3C020C14,
+	0xB0000000,	0x00000000,
+	0xE5C, 0x0D000058,
+	0xE60, 0x1B800000,
+	0xE60, 0x0B800001,
+	0xE60, 0x05800002,
+	0xE60, 0x07800003,
+	0xE60, 0x1A800004,
+	0xE60, 0x0B800005,
+	0xE60, 0x05800006,
+	0xE60, 0x0E800007,
+	0xE60, 0x1A800008,
+	0xE60, 0x0B800009,
+	0xE60, 0x1580000A,
+	0xE60, 0x0880000B,
+	0xE60, 0x1A80000C,
+	0xE60, 0x0B80000D,
+	0xE60, 0x0580000E,
+	0xE60, 0x0E80000F,
+	0xE60, 0x1A800010,
+	0xE60, 0x0B800011,
+	0xE60, 0x15800012,
+	0xE60, 0x08800013,
+	0xE60, 0x1A800014,
+	0xE60, 0x0B800015,
+	0xE60, 0x05800016,
+	0xE60, 0x07800017,
+	0xE60, 0x1A800018,
+	0xE60, 0x0B800019,
+	0xE60, 0x1580001A,
+	0xE60, 0x0880001B,
+	0xE60, 0x1B80001C,
+	0xE60, 0x0B80001D,
+	0xE60, 0x0580001E,
+	0xE60, 0x0780001F,
+	0xE60, 0x1B800020,
+	0xE60, 0x0B800021,
+	0xE60, 0x05800022,
+	0xE60, 0x07800023,
+	0xE60, 0x1B800024,
+	0xE60, 0x0B800025,
+	0xE60, 0x05800026,
+	0xE60, 0x07800027,
+	0xE60, 0x1B800028,
+	0xE60, 0x0B800029,
+	0xE60, 0x0580002A,
+	0xE60, 0x0780002B,
+	0xE60, 0x1B800030,
+	0xE60, 0x0B800031,
+	0xE60, 0x05800032,
+	0xE60, 0x00800033,
+	0xE60, 0x1B800034,
+	0xE60, 0x0B800035,
+	0xE60, 0x05800036,
+	0xE60, 0x00800037,
+	0xE60, 0x1B800038,
+	0xE60, 0x0B800039,
+	0xE60, 0x0580003A,
+	0xE60, 0x0E80803B,
+	0xE94, 0x01000401,
+	0xE98, 0x00188000,
+	0xEA0, 0x00002929,
+	0xEA4, 0x08040201,
+	0xEA8, 0x80402010,
+	0xEAC, 0x77777000,
+	0xEB0, 0x54775477,
+	0xEB4, 0x54775477,
+	0xEB8, 0x00500000,
+	0xEBC, 0x77700000,
+	0x1800, 0x00000007,
+	0x1804, 0x00042020,
+	0x1808, 0x80410231,
+	0x180C, 0x00000000,
+	0x1810, 0x00000100,
+	0x1814, 0x01000000,
+	0x181C, 0x40000053,
+	0x1850, 0x00000020,
+	0x1854, 0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1858, 0x3C0A0C14,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1858, 0x3C0A0C14,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1858, 0x3C0A0C14,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1858, 0x3C0A0C14,
+	0xA0000000,	0x00000000,
+	0x1858, 0x3C020C14,
+	0xB0000000,	0x00000000,
+	0x185C, 0x0D000058,
+	0x1860, 0x1B800000,
+	0x1860, 0x0B800001,
+	0x1860, 0x05800002,
+	0x1860, 0x07800003,
+	0x1860, 0x1A800004,
+	0x1860, 0x0B800005,
+	0x1860, 0x05800006,
+	0x1860, 0x0E800007,
+	0x1860, 0x1A800008,
+	0x1860, 0x0B800009,
+	0x1860, 0x1580000A,
+	0x1860, 0x0880000B,
+	0x1860, 0x1A80000C,
+	0x1860, 0x0B80000D,
+	0x1860, 0x0580000E,
+	0x1860, 0x0E80000F,
+	0x1860, 0x1A800010,
+	0x1860, 0x0B800011,
+	0x1860, 0x15800012,
+	0x1860, 0x08800013,
+	0x1860, 0x1A800014,
+	0x1860, 0x0B800015,
+	0x1860, 0x05800016,
+	0x1860, 0x07800017,
+	0x1860, 0x1A800018,
+	0x1860, 0x0B800019,
+	0x1860, 0x1580001A,
+	0x1860, 0x0880001B,
+	0x1860, 0x1B80001C,
+	0x1860, 0x0B80001D,
+	0x1860, 0x0580001E,
+	0x1860, 0x0780001F,
+	0x1860, 0x1B800020,
+	0x1860, 0x0B800021,
+	0x1860, 0x05800022,
+	0x1860, 0x07800023,
+	0x1860, 0x1B800024,
+	0x1860, 0x0B800025,
+	0x1860, 0x05800026,
+	0x1860, 0x07800027,
+	0x1860, 0x1B800028,
+	0x1860, 0x0B800029,
+	0x1860, 0x0580002A,
+	0x1860, 0x0780002B,
+	0x1860, 0x1B800030,
+	0x1860, 0x0B800031,
+	0x1860, 0x05800032,
+	0x1860, 0x00800033,
+	0x1860, 0x1B800034,
+	0x1860, 0x0B800035,
+	0x1860, 0x05800036,
+	0x1860, 0x00800037,
+	0x1860, 0x1B800038,
+	0x1860, 0x0B800039,
+	0x1860, 0x0580003A,
+	0x1860, 0x0E80803B,
+	0x1894, 0x01000401,
+	0x1898, 0x00188000,
+	0x18A0, 0x00002929,
+	0x18A4, 0x08040201,
+	0x18A8, 0x80402010,
+	0x18AC, 0x77777000,
+	0x18B0, 0x54775477,
+	0x18B4, 0x54775477,
+	0x18B8, 0x00500000,
+	0x18BC, 0x77700000,
+	0x1A00, 0x00000007,
+	0x1A04, 0x00042020,
+	0x1A08, 0x80410231,
+	0x1A0C, 0x00000000,
+	0x1A10, 0x00000100,
+	0x1A14, 0x01000000,
+	0x1A1C, 0x40000053,
+	0x1A50, 0x00000020,
+	0x1A54, 0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1A58, 0x3C0A0C14,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1A58, 0x3C0A0C14,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1A58, 0x3C0A0C14,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1A58, 0x3C0A0C14,
+	0xA0000000,	0x00000000,
+	0x1A58, 0x3C020C14,
+	0xB0000000,	0x00000000,
+	0x1A5C, 0x0D000058,
+	0x1A60, 0x1B800000,
+	0x1A60, 0x0B800001,
+	0x1A60, 0x05800002,
+	0x1A60, 0x07800003,
+	0x1A60, 0x1A800004,
+	0x1A60, 0x0B800005,
+	0x1A60, 0x05800006,
+	0x1A60, 0x0E800007,
+	0x1A60, 0x1A800008,
+	0x1A60, 0x0B800009,
+	0x1A60, 0x1580000A,
+	0x1A60, 0x0880000B,
+	0x1A60, 0x1A80000C,
+	0x1A60, 0x0B80000D,
+	0x1A60, 0x0580000E,
+	0x1A60, 0x0E80000F,
+	0x1A60, 0x1A800010,
+	0x1A60, 0x0B800011,
+	0x1A60, 0x15800012,
+	0x1A60, 0x08800013,
+	0x1A60, 0x1A800014,
+	0x1A60, 0x0B800015,
+	0x1A60, 0x05800016,
+	0x1A60, 0x07800017,
+	0x1A60, 0x1A800018,
+	0x1A60, 0x0B800019,
+	0x1A60, 0x1580001A,
+	0x1A60, 0x0880001B,
+	0x1A60, 0x1B80001C,
+	0x1A60, 0x0B80001D,
+	0x1A60, 0x0580001E,
+	0x1A60, 0x0780001F,
+	0x1A60, 0x1B800020,
+	0x1A60, 0x0B800021,
+	0x1A60, 0x05800022,
+	0x1A60, 0x07800023,
+	0x1A60, 0x1B800024,
+	0x1A60, 0x0B800025,
+	0x1A60, 0x05800026,
+	0x1A60, 0x07800027,
+	0x1A60, 0x1B800028,
+	0x1A60, 0x0B800029,
+	0x1A60, 0x0580002A,
+	0x1A60, 0x0780002B,
+	0x1A60, 0x1B800030,
+	0x1A60, 0x0B800031,
+	0x1A60, 0x05800032,
+	0x1A60, 0x00800033,
+	0x1A60, 0x1B800034,
+	0x1A60, 0x0B800035,
+	0x1A60, 0x05800036,
+	0x1A60, 0x00800037,
+	0x1A60, 0x1B800038,
+	0x1A60, 0x0B800039,
+	0x1A60, 0x0580003A,
+	0x1A60, 0x0E80803B,
+	0x1A94, 0x01000401,
+	0x1A98, 0x00188000,
+	0x1AA0, 0x00002929,
+	0x1AA4, 0x08040201,
+	0x1AA8, 0x80402010,
+	0x1AAC, 0x77777000,
+	0x1AB0, 0x54775477,
+	0x1AB4, 0x54775477,
+	0x1AB8, 0x00500000,
+	0x1ABC, 0x77700000,
+	0x1904, 0x00030000,
+	0x1914, 0x00030000,
+	0x1984, 0x03000000,
+	0x1988, 0x00000087,
+	0x198C, 0x00000007,
+	0x1990, 0xFFAA5500,
+	0x1994, 0x00000077,
+	0x1998, 0x12801000,
+	0x1998, 0x12801000,
+	0x1998, 0x12801001,
+	0x1998, 0x12801002,
+	0x1998, 0x12801003,
+	0x1998, 0x12801004,
+	0x1998, 0x12801005,
+	0x1998, 0x12801006,
+	0x1998, 0x12801007,
+	0x1998, 0x12801008,
+	0x1998, 0x12801009,
+	0x1998, 0x1280100A,
+	0x1998, 0x1280100B,
+	0x1998, 0x1280100C,
+	0x1998, 0x1280100D,
+	0x1998, 0x1280100E,
+	0x1998, 0x1280100F,
+	0x1998, 0x12801010,
+	0x1998, 0x12801011,
+	0x1998, 0x12801012,
+	0x1998, 0x12801013,
+	0x1998, 0x12801014,
+	0x1998, 0x12801015,
+	0x1998, 0x12801016,
+	0x1998, 0x12801017,
+	0x1998, 0x12801018,
+	0x1998, 0x12801019,
+	0x1998, 0x1280101A,
+	0x1998, 0x1280101B,
+	0x1998, 0x1280101C,
+	0x1998, 0x1280101D,
+	0x1998, 0x1280101E,
+	0x1998, 0x1280101F,
+	0x1998, 0x12801020,
+	0x1998, 0x12801021,
+	0x1998, 0x12801022,
+	0x1998, 0x12801023,
+	0x1998, 0x1280102C,
+	0x1998, 0x1280102D,
+	0x1998, 0x1280102E,
+	0x1998, 0x1280102F,
+	0x1998, 0x12801030,
+	0x1998, 0x12801031,
+	0x1998, 0x12801032,
+	0x1998, 0x12801033,
+	0x1998, 0x12801034,
+	0x1998, 0x12801035,
+	0x1998, 0x12801036,
+	0x1998, 0x12801037,
+	0x1998, 0x12801038,
+	0x1998, 0x12801039,
+	0x1998, 0x1280103A,
+	0x1998, 0x1280103B,
+	0x1998, 0x1280103C,
+	0x1998, 0x1280103D,
+	0x1998, 0x1280103E,
+	0x1998, 0x1280103F,
+	0x1998, 0x12801040,
+	0x1998, 0x12801041,
+	0x1998, 0x12801042,
+	0x1998, 0x12801043,
+	0x1998, 0x12801044,
+	0x1998, 0x12801045,
+	0x1998, 0x12801046,
+	0x1998, 0x12801047,
+	0x1998, 0x12801048,
+	0x1998, 0x12801049,
+	0x1998, 0x12801100,
+	0x1998, 0x12801101,
+	0x1998, 0x12801102,
+	0x1998, 0x12801103,
+	0x1998, 0x12801104,
+	0x1998, 0x12801105,
+	0x1998, 0x12801106,
+	0x1998, 0x12801107,
+	0x1998, 0x12801108,
+	0x1998, 0x12801109,
+	0x1998, 0x1280110A,
+	0x1998, 0x1280110B,
+	0x1998, 0x1280110C,
+	0x1998, 0x1280110D,
+	0x1998, 0x1280110E,
+	0x1998, 0x1280110F,
+	0x1998, 0x12801110,
+	0x1998, 0x12801111,
+	0x1998, 0x12801112,
+	0x1998, 0x12801113,
+	0x1998, 0x12801114,
+	0x1998, 0x12801115,
+	0x1998, 0x12801116,
+	0x1998, 0x12801117,
+	0x1998, 0x12801118,
+	0x1998, 0x12801119,
+	0x1998, 0x1280111A,
+	0x1998, 0x1280111B,
+	0x1998, 0x1280111C,
+	0x1998, 0x1280111D,
+	0x1998, 0x1280111E,
+	0x1998, 0x1280111F,
+	0x1998, 0x12801120,
+	0x1998, 0x12801121,
+	0x1998, 0x12801122,
+	0x1998, 0x12801123,
+	0x1998, 0x1280112C,
+	0x1998, 0x1280112D,
+	0x1998, 0x1280112E,
+	0x1998, 0x1280112F,
+	0x1998, 0x12801130,
+	0x1998, 0x12801131,
+	0x1998, 0x12801132,
+	0x1998, 0x12801133,
+	0x1998, 0x12801134,
+	0x1998, 0x12801135,
+	0x1998, 0x12801136,
+	0x1998, 0x12801137,
+	0x1998, 0x12801138,
+	0x1998, 0x12801139,
+	0x1998, 0x1280113A,
+	0x1998, 0x1280113B,
+	0x1998, 0x1280113C,
+	0x1998, 0x1280113D,
+	0x1998, 0x1280113E,
+	0x1998, 0x1280113F,
+	0x1998, 0x12801140,
+	0x1998, 0x12801141,
+	0x1998, 0x12801142,
+	0x1998, 0x12801143,
+	0x1998, 0x12801144,
+	0x1998, 0x12801145,
+	0x1998, 0x12801146,
+	0x1998, 0x12801147,
+	0x1998, 0x12801148,
+	0x1998, 0x12801149,
+	0x1998, 0x12801200,
+	0x1998, 0x12801201,
+	0x1998, 0x12801202,
+	0x1998, 0x12801203,
+	0x1998, 0x12801204,
+	0x1998, 0x12801205,
+	0x1998, 0x12801206,
+	0x1998, 0x12801207,
+	0x1998, 0x12801208,
+	0x1998, 0x12801209,
+	0x1998, 0x1280120A,
+	0x1998, 0x1280120B,
+	0x1998, 0x1280120C,
+	0x1998, 0x1280120D,
+	0x1998, 0x1280120E,
+	0x1998, 0x1280120F,
+	0x1998, 0x12801210,
+	0x1998, 0x12801211,
+	0x1998, 0x12801212,
+	0x1998, 0x12801213,
+	0x1998, 0x12801214,
+	0x1998, 0x12801215,
+	0x1998, 0x12801216,
+	0x1998, 0x12801217,
+	0x1998, 0x12801218,
+	0x1998, 0x12801219,
+	0x1998, 0x1280121A,
+	0x1998, 0x1280121B,
+	0x1998, 0x1280121C,
+	0x1998, 0x1280121D,
+	0x1998, 0x1280121E,
+	0x1998, 0x1280121F,
+	0x1998, 0x12801220,
+	0x1998, 0x12801221,
+	0x1998, 0x12801222,
+	0x1998, 0x12801223,
+	0x1998, 0x1280122C,
+	0x1998, 0x1280122D,
+	0x1998, 0x1280122E,
+	0x1998, 0x1280122F,
+	0x1998, 0x12801230,
+	0x1998, 0x12801231,
+	0x1998, 0x12801232,
+	0x1998, 0x12801233,
+	0x1998, 0x12801234,
+	0x1998, 0x12801235,
+	0x1998, 0x12801236,
+	0x1998, 0x12801237,
+	0x1998, 0x12801238,
+	0x1998, 0x12801239,
+	0x1998, 0x1280123A,
+	0x1998, 0x1280123B,
+	0x1998, 0x1280123C,
+	0x1998, 0x1280123D,
+	0x1998, 0x1280123E,
+	0x1998, 0x1280123F,
+	0x1998, 0x12801240,
+	0x1998, 0x12801241,
+	0x1998, 0x12801242,
+	0x1998, 0x12801243,
+	0x1998, 0x12801244,
+	0x1998, 0x12801245,
+	0x1998, 0x12801246,
+	0x1998, 0x12801247,
+	0x1998, 0x12801248,
+	0x1998, 0x12801249,
+	0x1998, 0x12801300,
+	0x1998, 0x12801301,
+	0x1998, 0x12801302,
+	0x1998, 0x12801303,
+	0x1998, 0x12801304,
+	0x1998, 0x12801305,
+	0x1998, 0x12801306,
+	0x1998, 0x12801307,
+	0x1998, 0x12801308,
+	0x1998, 0x12801309,
+	0x1998, 0x1280130A,
+	0x1998, 0x1280130B,
+	0x1998, 0x1280130C,
+	0x1998, 0x1280130D,
+	0x1998, 0x1280130E,
+	0x1998, 0x1280130F,
+	0x1998, 0x12801310,
+	0x1998, 0x12801311,
+	0x1998, 0x12801312,
+	0x1998, 0x12801313,
+	0x1998, 0x12801314,
+	0x1998, 0x12801315,
+	0x1998, 0x12801316,
+	0x1998, 0x12801317,
+	0x1998, 0x12801318,
+	0x1998, 0x12801319,
+	0x1998, 0x1280131A,
+	0x1998, 0x1280131B,
+	0x1998, 0x1280131C,
+	0x1998, 0x1280131D,
+	0x1998, 0x1280131E,
+	0x1998, 0x1280131F,
+	0x1998, 0x12801320,
+	0x1998, 0x12801321,
+	0x1998, 0x12801322,
+	0x1998, 0x12801323,
+	0x1998, 0x1280132C,
+	0x1998, 0x1280132D,
+	0x1998, 0x1280132E,
+	0x1998, 0x1280132F,
+	0x1998, 0x12801330,
+	0x1998, 0x12801331,
+	0x1998, 0x12801332,
+	0x1998, 0x12801333,
+	0x1998, 0x12801334,
+	0x1998, 0x12801335,
+	0x1998, 0x12801336,
+	0x1998, 0x12801337,
+	0x1998, 0x12801338,
+	0x1998, 0x12801339,
+	0x1998, 0x1280133A,
+	0x1998, 0x1280133B,
+	0x1998, 0x1280133C,
+	0x1998, 0x1280133D,
+	0x1998, 0x1280133E,
+	0x1998, 0x1280133F,
+	0x1998, 0x12801340,
+	0x1998, 0x12801341,
+	0x1998, 0x12801342,
+	0x1998, 0x12801343,
+	0x1998, 0x12801344,
+	0x1998, 0x12801345,
+	0x1998, 0x12801346,
+	0x1998, 0x12801347,
+	0x1998, 0x12801348,
+	0x1998, 0x12801349,
+	0x19D4, 0x88888888,
+	0x19D8, 0x00000888,
+	0xB00, 0xE3100100,
+	0xB00, 0xE7100100,
+	0xC60, 0x15808002,
+	0xC60, 0x01808003,
+	0xE60, 0x15808002,
+	0xE60, 0x01808003,
+	0x1860, 0x15808002,
+	0x1860, 0x01808003,
+	0x1A60, 0x15808002,
+	0x1A60, 0x01808003,
+	0xB00, 0xE3100100,
+	0xC5C, 0x0D080058,
+	0xE5C, 0x0D080058,
+	0x185C, 0x0D080058,
+	0x1A5C, 0x0D080058,
+	0xC5C, 0x0D000058,
+	0xE5C, 0x0D000058,
+	0x185C, 0x0D000058,
+	0x1A5C, 0x0D000058,
+	0xC60, 0x05808002,
+	0xC60, 0x0E808003,
+	0xE60, 0x05808002,
+	0xE60, 0x0E808003,
+	0x1860, 0x05808002,
+	0x1860, 0x0E808003,
+	0x1A60, 0x05808002,
+	0x1A60, 0x0E808003,
+	0xB00, 0xE7100100,
+	0xB00, 0xE3100100,
+	0xB00, 0xE3100000,
+	0x1C38, 0x00000002,
+	0xA00, 0x00D047C8,
+	0xA04, 0x46FF800C,
+	0xA08, 0x8C838300,
+	0xA0C, 0x2E7E000F,
+	0xA10, 0x9500BB78,
+	0xA14, 0x11144028,
+	0xA18, 0x00881117,
+	0xA1C, 0x89140F00,
+	0xA20, 0x1A1B0030,
+	0xA24, 0x090E1317,
+	0xA28, 0x00000204,
+	0xA2C, 0x00900000,
+	0xA70, 0x101FFF00,
+	0xA74, 0x00000128,
+	0xA78, 0x00000900,
+	0xA7C, 0x225B0606,
+	0xA80, 0x218075B2,
+	0xA84, 0x9C1F8C00,
+	0x1B04, 0xE24628D2,
+	0x1B10, 0x88010D46,
+	0x1B14, 0x00000000,
+	0x1B18, 0x00292903,
+	0x1B00, 0xF8000000,
+	0x1B00, 0xF800D000,
+	0x1B00, 0xF801F000,
+	0x1B1C, 0xA2123DB2,
+	0x1B20, 0x07040001,
+	0x1B24, 0x07060807,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0xA0000000,	0x00000000,
+	0x1B28, 0xC0060348,
+	0xB0000000,	0x00000000,
+	0x1B2C, 0x20000003,
+	0x1B30, 0x20000000,
+	0x1B38, 0x20000000,
+	0x1B3C, 0x20000000,
+	0x1BD4, 0x00000001,
+	0x1B94, 0x80000000,
+	0x1B34, 0x00000000,
+	0x1B34, 0x00000002,
+	0x1B34, 0x00000000,
+	0x1B00, 0xF8000002,
+	0x1B00, 0xF800D002,
+	0x1B00, 0xF801F002,
+	0x1B1C, 0xA2123DB2,
+	0x1B20, 0x07040001,
+	0x1B24, 0x07060807,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0xA0000000,	0x00000000,
+	0x1B28, 0xC0060348,
+	0xB0000000,	0x00000000,
+	0x1B2C, 0x20000003,
+	0x1B30, 0x20000000,
+	0x1B38, 0x20000000,
+	0x1B3C, 0x20000000,
+	0x1BD4, 0x00000001,
+	0x1B94, 0x80000000,
+	0x1B34, 0x00000000,
+	0x1B34, 0x00000002,
+	0x1B34, 0x00000000,
+	0x1B00, 0xF8000004,
+	0x1B00, 0xF800D004,
+	0x1B00, 0xF801F004,
+	0x1B1C, 0xA2123DB2,
+	0x1B20, 0x07040001,
+	0x1B24, 0x07060807,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0xA0000000,	0x00000000,
+	0x1B28, 0xC0060348,
+	0xB0000000,	0x00000000,
+	0x1B2C, 0x20000003,
+	0x1B30, 0x20000000,
+	0x1B38, 0x20000000,
+	0x1B3C, 0x20000000,
+	0x1BD4, 0x00000001,
+	0x1B94, 0x80000000,
+	0x1B34, 0x00000000,
+	0x1B34, 0x00000002,
+	0x1B34, 0x00000000,
+	0x1B00, 0xF8000006,
+	0x1B00, 0xF800D006,
+	0x1B00, 0xF801F006,
+	0x1B1C, 0xA2123DB2,
+	0x1B20, 0x07040001,
+	0x1B24, 0x07060807,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B28, 0xC0060324,
+	0xA0000000,	0x00000000,
+	0x1B28, 0xC0060348,
+	0xB0000000,	0x00000000,
+	0x1B2C, 0x20000003,
+	0x1B30, 0x20000000,
+	0x1B38, 0x20000000,
+	0x1B3C, 0x20000000,
+	0x1BD4, 0x00000001,
+	0x1B94, 0x80000000,
+	0x1B34, 0x00000000,
+	0x1B34, 0x00000002,
+	0x1B34, 0x00000000,
+	0x1B00, 0xF8000000,
+	0x1B80, 0x00000007,
+	0x1B80, 0x09060005,
+	0x1B80, 0x09060007,
+	0x1B80, 0x0FFE0015,
+	0x1B80, 0x0FFE0017,
+	0x1B80, 0x00240025,
+	0x1B80, 0x00240027,
+	0x1B80, 0x00040035,
+	0x1B80, 0x00040037,
+	0x1B80, 0x05C00045,
+	0x1B80, 0x05C00047,
+	0x1B80, 0x00070055,
+	0x1B80, 0x00070057,
+	0x1B80, 0x64000065,
+	0x1B80, 0x64000067,
+	0x1B80, 0x00020075,
+	0x1B80, 0x00020077,
+	0x1B80, 0x00080085,
+	0x1B80, 0x00080087,
+	0x1B80, 0x80000095,
+	0x1B80, 0x80000097,
+	0x1B80, 0x090100A5,
+	0x1B80, 0x090100A7,
+	0x1B80, 0x0F0200B5,
+	0x1B80, 0x0F0200B7,
+	0x1B80, 0x002400C5,
+	0x1B80, 0x002400C7,
+	0x1B80, 0x000400D5,
+	0x1B80, 0x000400D7,
+	0x1B80, 0x05C000E5,
+	0x1B80, 0x05C000E7,
+	0x1B80, 0x000700F5,
+	0x1B80, 0x000700F7,
+	0x1B80, 0x64020105,
+	0x1B80, 0x64020107,
+	0x1B80, 0x00020115,
+	0x1B80, 0x00020117,
+	0x1B80, 0x00040125,
+	0x1B80, 0x00040127,
+	0x1B80, 0x4A000135,
+	0x1B80, 0x4A000137,
+	0x1B80, 0x4B040145,
+	0x1B80, 0x4B040147,
+	0x1B80, 0x85030155,
+	0x1B80, 0x85030157,
+	0x1B80, 0x40010165,
+	0x1B80, 0x40010167,
+	0x1B80, 0xE0290175,
+	0x1B80, 0xE0290177,
+	0x1B80, 0x00040185,
+	0x1B80, 0x00040187,
+	0x1B80, 0x4B050195,
+	0x1B80, 0x4B050197,
+	0x1B80, 0x860301A5,
+	0x1B80, 0x860301A7,
+	0x1B80, 0x400301B5,
+	0x1B80, 0x400301B7,
+	0x1B80, 0xE02901C5,
+	0x1B80, 0xE02901C7,
+	0x1B80, 0x000401D5,
+	0x1B80, 0x000401D7,
+	0x1B80, 0x4B0601E5,
+	0x1B80, 0x4B0601E7,
+	0x1B80, 0x870301F5,
+	0x1B80, 0x870301F7,
+	0x1B80, 0x40050205,
+	0x1B80, 0x40050207,
+	0x1B80, 0xE0290215,
+	0x1B80, 0xE0290217,
+	0x1B80, 0x00040225,
+	0x1B80, 0x00040227,
+	0x1B80, 0x4B070235,
+	0x1B80, 0x4B070237,
+	0x1B80, 0x88030245,
+	0x1B80, 0x88030247,
+	0x1B80, 0x40070255,
+	0x1B80, 0x40070257,
+	0x1B80, 0xE0290265,
+	0x1B80, 0xE0290267,
+	0x1B80, 0x4B000275,
+	0x1B80, 0x4B000277,
+	0x1B80, 0x30000285,
+	0x1B80, 0x30000287,
+	0x1B80, 0xFE100295,
+	0x1B80, 0xFE100297,
+	0x1B80, 0xFF1002A5,
+	0x1B80, 0xFF1002A7,
+	0x1B80, 0xE18602B5,
+	0x1B80, 0xE18602B7,
+	0x1B80, 0xF00A02C5,
+	0x1B80, 0xF00A02C7,
+	0x1B80, 0xF10A02D5,
+	0x1B80, 0xF10A02D7,
+	0x1B80, 0xF20A02E5,
+	0x1B80, 0xF20A02E7,
+	0x1B80, 0xF30802F5,
+	0x1B80, 0xF30802F7,
+	0x1B80, 0xF4070305,
+	0x1B80, 0xF4070307,
+	0x1B80, 0xF5060315,
+	0x1B80, 0xF5060317,
+	0x1B80, 0xF7060325,
+	0x1B80, 0xF7060327,
+	0x1B80, 0xF8050335,
+	0x1B80, 0xF8050337,
+	0x1B80, 0xF9040345,
+	0x1B80, 0xF9040347,
+	0x1B80, 0x00010355,
+	0x1B80, 0x00010357,
+	0x1B80, 0x303B0365,
+	0x1B80, 0x303B0367,
+	0x1B80, 0x30500375,
+	0x1B80, 0x30500377,
+	0x1B80, 0x305C0385,
+	0x1B80, 0x305C0387,
+	0x1B80, 0x31D50395,
+	0x1B80, 0x31D50397,
+	0x1B80, 0x31C503A5,
+	0x1B80, 0x31C503A7,
+	0x1B80, 0x4D0403B5,
+	0x1B80, 0x4D0403B7,
+	0x1B80, 0x2EF003C5,
+	0x1B80, 0x2EF003C7,
+	0x1B80, 0x000203D5,
+	0x1B80, 0x000203D7,
+	0x1B80, 0x208003E5,
+	0x1B80, 0x208003E7,
+	0x1B80, 0x000003F5,
+	0x1B80, 0x000003F7,
+	0x1B80, 0x4D000405,
+	0x1B80, 0x4D000407,
+	0x1B80, 0x55070415,
+	0x1B80, 0x55070417,
+	0x1B80, 0xE1230425,
+	0x1B80, 0xE1230427,
+	0x1B80, 0xE1230435,
+	0x1B80, 0xE1230437,
+	0x1B80, 0x4D040445,
+	0x1B80, 0x4D040447,
+	0x1B80, 0x20800455,
+	0x1B80, 0x20800457,
+	0x1B80, 0x84000465,
+	0x1B80, 0x84000467,
+	0x1B80, 0x4D000475,
+	0x1B80, 0x4D000477,
+	0x1B80, 0x550F0485,
+	0x1B80, 0x550F0487,
+	0x1B80, 0xE1230495,
+	0x1B80, 0xE1230497,
+	0x1B80, 0x4F0204A5,
+	0x1B80, 0x4F0204A7,
+	0x1B80, 0x4E0004B5,
+	0x1B80, 0x4E0004B7,
+	0x1B80, 0x530204C5,
+	0x1B80, 0x530204C7,
+	0x1B80, 0x520104D5,
+	0x1B80, 0x520104D7,
+	0x1B80, 0xE12704E5,
+	0x1B80, 0xE12704E7,
+	0x1B80, 0x000104F5,
+	0x1B80, 0x000104F7,
+	0x1B80, 0x5C720505,
+	0x1B80, 0x5C720507,
+	0x1B80, 0xE1320515,
+	0x1B80, 0xE1320517,
+	0x1B80, 0x54E50525,
+	0x1B80, 0x54E50527,
+	0x1B80, 0x54BF0535,
+	0x1B80, 0x54BF0537,
+	0x1B80, 0x54C50545,
+	0x1B80, 0x54C50547,
+	0x1B80, 0x54BE0555,
+	0x1B80, 0x54BE0557,
+	0x1B80, 0x54DF0565,
+	0x1B80, 0x54DF0567,
+	0x1B80, 0x0BA60575,
+	0x1B80, 0x0BA60577,
+	0x1B80, 0xF3130585,
+	0x1B80, 0xF3130587,
+	0x1B80, 0xF41E0595,
+	0x1B80, 0xF41E0597,
+	0x1B80, 0xF53C05A5,
+	0x1B80, 0xF53C05A7,
+	0x1B80, 0x000105B5,
+	0x1B80, 0x000105B7,
+	0x1B80, 0x620605C5,
+	0x1B80, 0x620605C7,
+	0x1B80, 0x600605D5,
+	0x1B80, 0x600605D7,
+	0x1B80, 0xE1A905E5,
+	0x1B80, 0xE1A905E7,
+	0x1B80, 0x0C0005F5,
+	0x1B80, 0x0C0005F7,
+	0x1B80, 0x5C720605,
+	0x1B80, 0x5C720607,
+	0x1B80, 0xE1320615,
+	0x1B80, 0xE1320617,
+	0x1B80, 0x5CF10625,
+	0x1B80, 0x5CF10627,
+	0x1B80, 0x0C010635,
+	0x1B80, 0x0C010637,
+	0x1B80, 0xF2020645,
+	0x1B80, 0xF2020647,
+	0x1B80, 0x30D60655,
+	0x1B80, 0x30D60657,
+	0x1B80, 0x0AC60665,
+	0x1B80, 0x0AC60667,
+	0x1B80, 0xE1B60675,
+	0x1B80, 0xE1B60677,
+	0x1B80, 0xE1580685,
+	0x1B80, 0xE1580687,
+	0x1B80, 0x54E50695,
+	0x1B80, 0x54E50697,
+	0x1B80, 0x000106A5,
+	0x1B80, 0x000106A7,
+	0x1B80, 0x560106B5,
+	0x1B80, 0x560106B7,
+	0x1B80, 0x5CE206C5,
+	0x1B80, 0x5CE206C7,
+	0x1B80, 0x0AE106D5,
+	0x1B80, 0x0AE106D7,
+	0x1B80, 0x630C06E5,
+	0x1B80, 0x630C06E7,
+	0x1B80, 0xE13F06F5,
+	0x1B80, 0xE13F06F7,
+	0x1B80, 0x00270705,
+	0x1B80, 0x00270707,
+	0x1B80, 0xE16C0715,
+	0x1B80, 0xE16C0717,
+	0x1B80, 0x00020725,
+	0x1B80, 0x00020727,
+	0x1B80, 0x002A0735,
+	0x1B80, 0x002A0737,
+	0x1B80, 0x07140745,
+	0x1B80, 0x07140747,
+	0x1B80, 0x00020755,
+	0x1B80, 0x00020757,
+	0x1B80, 0x30C30765,
+	0x1B80, 0x30C30767,
+	0x1B80, 0x56010775,
+	0x1B80, 0x56010777,
+	0x1B80, 0x5CE20785,
+	0x1B80, 0x5CE20787,
+	0x1B80, 0x0AE10795,
+	0x1B80, 0x0AE10797,
+	0x1B80, 0x631707A5,
+	0x1B80, 0x631707A7,
+	0x1B80, 0xE13F07B5,
+	0x1B80, 0xE13F07B7,
+	0x1B80, 0x002507C5,
+	0x1B80, 0x002507C7,
+	0x1B80, 0xE16C07D5,
+	0x1B80, 0xE16C07D7,
+	0x1B80, 0x000207E5,
+	0x1B80, 0x000207E7,
+	0x1B80, 0x630F07F5,
+	0x1B80, 0x630F07F7,
+	0x1B80, 0xE13F0805,
+	0x1B80, 0xE13F0807,
+	0x1B80, 0x63070815,
+	0x1B80, 0x63070817,
+	0x1B80, 0xE13F0825,
+	0x1B80, 0xE13F0827,
+	0x1B80, 0x07140835,
+	0x1B80, 0x07140837,
+	0x1B80, 0x56000845,
+	0x1B80, 0x56000847,
+	0x1B80, 0x5CF20855,
+	0x1B80, 0x5CF20857,
+	0x1B80, 0x0AF10865,
+	0x1B80, 0x0AF10867,
+	0x1B80, 0x07140875,
+	0x1B80, 0x07140877,
+	0x1B80, 0x07140885,
+	0x1B80, 0x07140887,
+	0x1B80, 0x630F0895,
+	0x1B80, 0x630F0897,
+	0x1B80, 0xE13F08A5,
+	0x1B80, 0xE13F08A7,
+	0x1B80, 0x631708B5,
+	0x1B80, 0x631708B7,
+	0x1B80, 0xE13F08C5,
+	0x1B80, 0xE13F08C7,
+	0x1B80, 0x002508D5,
+	0x1B80, 0x002508D7,
+	0x1B80, 0xE16C08E5,
+	0x1B80, 0xE16C08E7,
+	0x1B80, 0x000208F5,
+	0x1B80, 0x000208F7,
+	0x1B80, 0x30C30905,
+	0x1B80, 0x30C30907,
+	0x1B80, 0xE1A90915,
+	0x1B80, 0xE1A90917,
+	0x1B80, 0x62060925,
+	0x1B80, 0x62060927,
+	0x1B80, 0x60060935,
+	0x1B80, 0x60060937,
+	0x1B80, 0xE1160945,
+	0x1B80, 0xE1160947,
+	0x1B80, 0x54BE0955,
+	0x1B80, 0x54BE0957,
+	0x1B80, 0x56010965,
+	0x1B80, 0x56010967,
+	0x1B80, 0x5CE20975,
+	0x1B80, 0x5CE20977,
+	0x1B80, 0x0AE10985,
+	0x1B80, 0x0AE10987,
+	0x1B80, 0x633A0995,
+	0x1B80, 0x633A0997,
+	0x1B80, 0xE13F09A5,
+	0x1B80, 0xE13F09A7,
+	0x1B80, 0x633709B5,
+	0x1B80, 0x633709B7,
+	0x1B80, 0xE13F09C5,
+	0x1B80, 0xE13F09C7,
+	0x1B80, 0x632F09D5,
+	0x1B80, 0x632F09D7,
+	0x1B80, 0xE13F09E5,
+	0x1B80, 0xE13F09E7,
+	0x1B80, 0x632709F5,
+	0x1B80, 0x632709F7,
+	0x1B80, 0xE13F0A05,
+	0x1B80, 0xE13F0A07,
+	0x1B80, 0x631F0A15,
+	0x1B80, 0x631F0A17,
+	0x1B80, 0xE13F0A25,
+	0x1B80, 0xE13F0A27,
+	0x1B80, 0x63170A35,
+	0x1B80, 0x63170A37,
+	0x1B80, 0xE13F0A45,
+	0x1B80, 0xE13F0A47,
+	0x1B80, 0x630F0A55,
+	0x1B80, 0x630F0A57,
+	0x1B80, 0xE13F0A65,
+	0x1B80, 0xE13F0A67,
+	0x1B80, 0x63070A75,
+	0x1B80, 0x63070A77,
+	0x1B80, 0xE13F0A85,
+	0x1B80, 0xE13F0A87,
+	0x1B80, 0xE16C0A95,
+	0x1B80, 0xE16C0A97,
+	0x1B80, 0x56000AA5,
+	0x1B80, 0x56000AA7,
+	0x1B80, 0x5CF20AB5,
+	0x1B80, 0x5CF20AB7,
+	0x1B80, 0x0AF10AC5,
+	0x1B80, 0x0AF10AC7,
+	0x1B80, 0xF5040AD5,
+	0x1B80, 0xF5040AD7,
+	0x1B80, 0xE13F0AE5,
+	0x1B80, 0xE13F0AE7,
+	0x1B80, 0xE16C0AF5,
+	0x1B80, 0xE16C0AF7,
+	0x1B80, 0x30B30B05,
+	0x1B80, 0x30B30B07,
+	0x1B80, 0x07140B15,
+	0x1B80, 0x07140B17,
+	0x1B80, 0x07140B25,
+	0x1B80, 0x07140B27,
+	0x1B80, 0x630F0B35,
+	0x1B80, 0x630F0B37,
+	0x1B80, 0xE13F0B45,
+	0x1B80, 0xE13F0B47,
+	0x1B80, 0x63170B55,
+	0x1B80, 0x63170B57,
+	0x1B80, 0xE13F0B65,
+	0x1B80, 0xE13F0B67,
+	0x1B80, 0x631F0B75,
+	0x1B80, 0x631F0B77,
+	0x1B80, 0xE13F0B85,
+	0x1B80, 0xE13F0B87,
+	0x1B80, 0x63270B95,
+	0x1B80, 0x63270B97,
+	0x1B80, 0xE13F0BA5,
+	0x1B80, 0xE13F0BA7,
+	0x1B80, 0x632F0BB5,
+	0x1B80, 0x632F0BB7,
+	0x1B80, 0xE13F0BC5,
+	0x1B80, 0xE13F0BC7,
+	0x1B80, 0x63370BD5,
+	0x1B80, 0x63370BD7,
+	0x1B80, 0xE13F0BE5,
+	0x1B80, 0xE13F0BE7,
+	0x1B80, 0x633A0BF5,
+	0x1B80, 0x633A0BF7,
+	0x1B80, 0xE13F0C05,
+	0x1B80, 0xE13F0C07,
+	0x1B80, 0xF60B0C15,
+	0x1B80, 0xF60B0C17,
+	0x1B80, 0xF7170C25,
+	0x1B80, 0xF7170C27,
+	0x1B80, 0x4D300C35,
+	0x1B80, 0x4D300C37,
+	0x1B80, 0x57040C45,
+	0x1B80, 0x57040C47,
+	0x1B80, 0x57000C55,
+	0x1B80, 0x57000C57,
+	0x1B80, 0x96000C65,
+	0x1B80, 0x96000C67,
+	0x1B80, 0x57080C75,
+	0x1B80, 0x57080C77,
+	0x1B80, 0x57000C85,
+	0x1B80, 0x57000C87,
+	0x1B80, 0x95000C95,
+	0x1B80, 0x95000C97,
+	0x1B80, 0x4D000CA5,
+	0x1B80, 0x4D000CA7,
+	0x1B80, 0x6C070CB5,
+	0x1B80, 0x6C070CB7,
+	0x1B80, 0x00010CC5,
+	0x1B80, 0x00010CC7,
+	0x1B80, 0x00220CD5,
+	0x1B80, 0x00220CD7,
+	0x1B80, 0x06140CE5,
+	0x1B80, 0x06140CE7,
+	0x1B80, 0xE16C0CF5,
+	0x1B80, 0xE16C0CF7,
+	0x1B80, 0x00020D05,
+	0x1B80, 0x00020D07,
+	0x1B80, 0x00250D15,
+	0x1B80, 0x00250D17,
+	0x1B80, 0x06140D25,
+	0x1B80, 0x06140D27,
+	0x1B80, 0xE16C0D35,
+	0x1B80, 0xE16C0D37,
+	0x1B80, 0x00020D45,
+	0x1B80, 0x00020D47,
+	0x1B80, 0x00010D55,
+	0x1B80, 0x00010D57,
+	0x1B80, 0x00320D65,
+	0x1B80, 0x00320D67,
+	0x1B80, 0xE16C0D75,
+	0x1B80, 0xE16C0D77,
+	0x1B80, 0x00020D85,
+	0x1B80, 0x00020D87,
+	0x1B80, 0xE1860D95,
+	0x1B80, 0xE1860D97,
+	0x1B80, 0xE1B60DA5,
+	0x1B80, 0xE1B60DA7,
+	0x1B80, 0x5CD10DB5,
+	0x1B80, 0x5CD10DB7,
+	0x1B80, 0x673A0DC5,
+	0x1B80, 0x673A0DC7,
+	0x1B80, 0xE1230DD5,
+	0x1B80, 0xE1230DD7,
+	0x1B80, 0xF80B0DE5,
+	0x1B80, 0xF80B0DE7,
+	0x1B80, 0xF9110DF5,
+	0x1B80, 0xF9110DF7,
+	0x1B80, 0xE1580E05,
+	0x1B80, 0xE1580E07,
+	0x1B80, 0x67370E15,
+	0x1B80, 0x67370E17,
+	0x1B80, 0xE1580E25,
+	0x1B80, 0xE1580E27,
+	0x1B80, 0x672F0E35,
+	0x1B80, 0x672F0E37,
+	0x1B80, 0xE1580E45,
+	0x1B80, 0xE1580E47,
+	0x1B80, 0x67270E55,
+	0x1B80, 0x67270E57,
+	0x1B80, 0xE1580E65,
+	0x1B80, 0xE1580E67,
+	0x1B80, 0x671F0E75,
+	0x1B80, 0x671F0E77,
+	0x1B80, 0xE1580E85,
+	0x1B80, 0xE1580E87,
+	0x1B80, 0x67170E95,
+	0x1B80, 0x67170E97,
+	0x1B80, 0xE1580EA5,
+	0x1B80, 0xE1580EA7,
+	0x1B80, 0xF8020EB5,
+	0x1B80, 0xF8020EB7,
+	0x1B80, 0x30EE0EC5,
+	0x1B80, 0x30EE0EC7,
+	0x1B80, 0xE0D10ED5,
+	0x1B80, 0xE0D10ED7,
+	0x1B80, 0x670F0EE5,
+	0x1B80, 0x670F0EE7,
+	0x1B80, 0xE1580EF5,
+	0x1B80, 0xE1580EF7,
+	0x1B80, 0x67070F05,
+	0x1B80, 0x67070F07,
+	0x1B80, 0xE1580F15,
+	0x1B80, 0xE1580F17,
+	0x1B80, 0xF9020F25,
+	0x1B80, 0xF9020F27,
+	0x1B80, 0x30F50F35,
+	0x1B80, 0x30F50F37,
+	0x1B80, 0xE0CD0F45,
+	0x1B80, 0xE0CD0F47,
+	0x1B80, 0x06140F55,
+	0x1B80, 0x06140F57,
+	0x1B80, 0xE16C0F65,
+	0x1B80, 0xE16C0F67,
+	0x1B80, 0x5CF10F75,
+	0x1B80, 0x5CF10F77,
+	0x1B80, 0xE1580F85,
+	0x1B80, 0xE1580F87,
+	0x1B80, 0x06140F95,
+	0x1B80, 0x06140F97,
+	0x1B80, 0xE16C0FA5,
+	0x1B80, 0xE16C0FA7,
+	0x1B80, 0xF9020FB5,
+	0x1B80, 0xF9020FB7,
+	0x1B80, 0x30FF0FC5,
+	0x1B80, 0x30FF0FC7,
+	0x1B80, 0xE0CD0FD5,
+	0x1B80, 0xE0CD0FD7,
+	0x1B80, 0x31130FE5,
+	0x1B80, 0x31130FE7,
+	0x1B80, 0x670F0FF5,
+	0x1B80, 0x670F0FF7,
+	0x1B80, 0xE1581005,
+	0x1B80, 0xE1581007,
+	0x1B80, 0x67171015,
+	0x1B80, 0x67171017,
+	0x1B80, 0xE1581025,
+	0x1B80, 0xE1581027,
+	0x1B80, 0xF8021035,
+	0x1B80, 0xF8021037,
+	0x1B80, 0x31071045,
+	0x1B80, 0x31071047,
+	0x1B80, 0xE0D11055,
+	0x1B80, 0xE0D11057,
+	0x1B80, 0x31131065,
+	0x1B80, 0x31131067,
+	0x1B80, 0x670F1075,
+	0x1B80, 0x670F1077,
+	0x1B80, 0xE1581085,
+	0x1B80, 0xE1581087,
+	0x1B80, 0x671F1095,
+	0x1B80, 0x671F1097,
+	0x1B80, 0xE15810A5,
+	0x1B80, 0xE15810A7,
+	0x1B80, 0x672710B5,
+	0x1B80, 0x672710B7,
+	0x1B80, 0xE15810C5,
+	0x1B80, 0xE15810C7,
+	0x1B80, 0x672F10D5,
+	0x1B80, 0x672F10D7,
+	0x1B80, 0xE15810E5,
+	0x1B80, 0xE15810E7,
+	0x1B80, 0x673710F5,
+	0x1B80, 0x673710F7,
+	0x1B80, 0xE1581105,
+	0x1B80, 0xE1581107,
+	0x1B80, 0x673A1115,
+	0x1B80, 0x673A1117,
+	0x1B80, 0xE1581125,
+	0x1B80, 0xE1581127,
+	0x1B80, 0x4D101135,
+	0x1B80, 0x4D101137,
+	0x1B80, 0x30C41145,
+	0x1B80, 0x30C41147,
+	0x1B80, 0x00011155,
+	0x1B80, 0x00011157,
+	0x1B80, 0x6F241165,
+	0x1B80, 0x6F241167,
+	0x1B80, 0x6E401175,
+	0x1B80, 0x6E401177,
+	0x1B80, 0x6D001185,
+	0x1B80, 0x6D001187,
+	0x1B80, 0x55031195,
+	0x1B80, 0x55031197,
+	0x1B80, 0x312311A5,
+	0x1B80, 0x312311A7,
+	0x1B80, 0x6F1C11B5,
+	0x1B80, 0x6F1C11B7,
+	0x1B80, 0x6E4011C5,
+	0x1B80, 0x6E4011C7,
+	0x1B80, 0x550B11D5,
+	0x1B80, 0x550B11D7,
+	0x1B80, 0x312311E5,
+	0x1B80, 0x312311E7,
+	0x1B80, 0x061C11F5,
+	0x1B80, 0x061C11F7,
+	0x1B80, 0x54DE1205,
+	0x1B80, 0x54DE1207,
+	0x1B80, 0x06DC1215,
+	0x1B80, 0x06DC1217,
+	0x1B80, 0x55131225,
+	0x1B80, 0x55131227,
+	0x1B80, 0x74011235,
+	0x1B80, 0x74011237,
+	0x1B80, 0x74001245,
+	0x1B80, 0x74001247,
+	0x1B80, 0x8E001255,
+	0x1B80, 0x8E001257,
+	0x1B80, 0x00011265,
+	0x1B80, 0x00011267,
+	0x1B80, 0x57021275,
+	0x1B80, 0x57021277,
+	0x1B80, 0x57001285,
+	0x1B80, 0x57001287,
+	0x1B80, 0x97001295,
+	0x1B80, 0x97001297,
+	0x1B80, 0x000112A5,
+	0x1B80, 0x000112A7,
+	0x1B80, 0x54BF12B5,
+	0x1B80, 0x54BF12B7,
+	0x1B80, 0x54C112C5,
+	0x1B80, 0x54C112C7,
+	0x1B80, 0x54A212D5,
+	0x1B80, 0x54A212D7,
+	0x1B80, 0x54C012E5,
+	0x1B80, 0x54C012E7,
+	0x1B80, 0x54A112F5,
+	0x1B80, 0x54A112F7,
+	0x1B80, 0x54DF1305,
+	0x1B80, 0x54DF1307,
+	0x1B80, 0x00011315,
+	0x1B80, 0x00011317,
+	0x1B80, 0x55001325,
+	0x1B80, 0x55001327,
+	0x1B80, 0xE1231335,
+	0x1B80, 0xE1231337,
+	0x1B80, 0x54811345,
+	0x1B80, 0x54811347,
+	0x1B80, 0xE1231355,
+	0x1B80, 0xE1231357,
+	0x1B80, 0x54801365,
+	0x1B80, 0x54801367,
+	0x1B80, 0x002A1375,
+	0x1B80, 0x002A1377,
+	0x1B80, 0xE12B1385,
+	0x1B80, 0xE12B1387,
+	0x1B80, 0xE1231395,
+	0x1B80, 0xE1231397,
+	0x1B80, 0x548013A5,
+	0x1B80, 0x548013A7,
+	0x1B80, 0xE17213B5,
+	0x1B80, 0xE17213B7,
+	0x1B80, 0xBF3013C5,
+	0x1B80, 0xBF3013C7,
+	0x1B80, 0x000213D5,
+	0x1B80, 0x000213D7,
+	0x1B80, 0x302813E5,
+	0x1B80, 0x302813E7,
+	0x1B80, 0x4F7813F5,
+	0x1B80, 0x4F7813F7,
+	0x1B80, 0x4E001405,
+	0x1B80, 0x4E001407,
+	0x1B80, 0x53871415,
+	0x1B80, 0x53871417,
+	0x1B80, 0x52F11425,
+	0x1B80, 0x52F11427,
+	0x1B80, 0xE1161435,
+	0x1B80, 0xE1161437,
+	0x1B80, 0xE11B1445,
+	0x1B80, 0xE11B1447,
+	0x1B80, 0xE11F1455,
+	0x1B80, 0xE11F1457,
+	0x1B80, 0xE1271465,
+	0x1B80, 0xE1271467,
+	0x1B80, 0x54811475,
+	0x1B80, 0x54811477,
+	0x1B80, 0xE1161485,
+	0x1B80, 0xE1161487,
+	0x1B80, 0xE11B1495,
+	0x1B80, 0xE11B1497,
+	0x1B80, 0xE11F14A5,
+	0x1B80, 0xE11F14A7,
+	0x1B80, 0xE12714B5,
+	0x1B80, 0xE12714B7,
+	0x1B80, 0x548014C5,
+	0x1B80, 0x548014C7,
+	0x1B80, 0x002A14D5,
+	0x1B80, 0x002A14D7,
+	0x1B80, 0xE12B14E5,
+	0x1B80, 0xE12B14E7,
+	0x1B80, 0xE11614F5,
+	0x1B80, 0xE11614F7,
+	0x1B80, 0xE11B1505,
+	0x1B80, 0xE11B1507,
+	0x1B80, 0xE11F1515,
+	0x1B80, 0xE11F1517,
+	0x1B80, 0xE1271525,
+	0x1B80, 0xE1271527,
+	0x1B80, 0x54801535,
+	0x1B80, 0x54801537,
+	0x1B80, 0xE1721545,
+	0x1B80, 0xE1721547,
+	0x1B80, 0xBF171555,
+	0x1B80, 0xBF171557,
+	0x1B80, 0x00021565,
+	0x1B80, 0x00021567,
+	0x1B80, 0x30281575,
+	0x1B80, 0x30281577,
+	0x1B80, 0x06141585,
+	0x1B80, 0x06141587,
+	0x1B80, 0x73201595,
+	0x1B80, 0x73201597,
+	0x1B80, 0x720015A5,
+	0x1B80, 0x720015A7,
+	0x1B80, 0x710015B5,
+	0x1B80, 0x710015B7,
+	0x1B80, 0x550115C5,
+	0x1B80, 0x550115C7,
+	0x1B80, 0xE12315D5,
+	0x1B80, 0xE12315D7,
+	0x1B80, 0xE12715E5,
+	0x1B80, 0xE12715E7,
+	0x1B80, 0x548115F5,
+	0x1B80, 0x548115F7,
+	0x1B80, 0xE1231605,
+	0x1B80, 0xE1231607,
+	0x1B80, 0xE1271615,
+	0x1B80, 0xE1271617,
+	0x1B80, 0x54801625,
+	0x1B80, 0x54801627,
+	0x1B80, 0x002A1635,
+	0x1B80, 0x002A1637,
+	0x1B80, 0xE12B1645,
+	0x1B80, 0xE12B1647,
+	0x1B80, 0xE1231655,
+	0x1B80, 0xE1231657,
+	0x1B80, 0xE1271665,
+	0x1B80, 0xE1271667,
+	0x1B80, 0x54801675,
+	0x1B80, 0x54801677,
+	0x1B80, 0xE1721685,
+	0x1B80, 0xE1721687,
+	0x1B80, 0xBF031695,
+	0x1B80, 0xBF031697,
+	0x1B80, 0x000216A5,
+	0x1B80, 0x000216A7,
+	0x1B80, 0x302816B5,
+	0x1B80, 0x302816B7,
+	0x1B80, 0x54BF16C5,
+	0x1B80, 0x54BF16C7,
+	0x1B80, 0x54C516D5,
+	0x1B80, 0x54C516D7,
+	0x1B80, 0x050A16E5,
+	0x1B80, 0x050A16E7,
+	0x1B80, 0x071416F5,
+	0x1B80, 0x071416F7,
+	0x1B80, 0x54DF1705,
+	0x1B80, 0x54DF1707,
+	0x1B80, 0x00011715,
+	0x1B80, 0x00011717,
+	0x1B80, 0x54BF1725,
+	0x1B80, 0x54BF1727,
+	0x1B80, 0x54C01735,
+	0x1B80, 0x54C01737,
+	0x1B80, 0x54A31745,
+	0x1B80, 0x54A31747,
+	0x1B80, 0x54C11755,
+	0x1B80, 0x54C11757,
+	0x1B80, 0x54A41765,
+	0x1B80, 0x54A41767,
+	0x1B80, 0x4C831775,
+	0x1B80, 0x4C831777,
+	0x1B80, 0x4C031785,
+	0x1B80, 0x4C031787,
+	0x1B80, 0xBF0B1795,
+	0x1B80, 0xBF0B1797,
+	0x1B80, 0x54C217A5,
+	0x1B80, 0x54C217A7,
+	0x1B80, 0x54A417B5,
+	0x1B80, 0x54A417B7,
+	0x1B80, 0x4C8517C5,
+	0x1B80, 0x4C8517C7,
+	0x1B80, 0x4C0517D5,
+	0x1B80, 0x4C0517D7,
+	0x1B80, 0xBF0617E5,
+	0x1B80, 0xBF0617E7,
+	0x1B80, 0x54C117F5,
+	0x1B80, 0x54C117F7,
+	0x1B80, 0x54A31805,
+	0x1B80, 0x54A31807,
+	0x1B80, 0x4C861815,
+	0x1B80, 0x4C861817,
+	0x1B80, 0x4C061825,
+	0x1B80, 0x4C061827,
+	0x1B80, 0xBF011835,
+	0x1B80, 0xBF011837,
+	0x1B80, 0x54DF1845,
+	0x1B80, 0x54DF1847,
+	0x1B80, 0x00011855,
+	0x1B80, 0x00011857,
+	0x1B80, 0x00071865,
+	0x1B80, 0x00071867,
+	0x1B80, 0x54011875,
+	0x1B80, 0x54011877,
+	0x1B80, 0x00041885,
+	0x1B80, 0x00041887,
+	0x1B80, 0x56001895,
+	0x1B80, 0x56001897,
+	0x1B80, 0x5CF218A5,
+	0x1B80, 0x5CF218A7,
+	0x1B80, 0x630718B5,
+	0x1B80, 0x630718B7,
+	0x1B80, 0x620418C5,
+	0x1B80, 0x620418C7,
+	0x1B80, 0x610018D5,
+	0x1B80, 0x610018D7,
+	0x1B80, 0x670718E5,
+	0x1B80, 0x670718E7,
+	0x1B80, 0x660618F5,
+	0x1B80, 0x660618F7,
+	0x1B80, 0x6F201905,
+	0x1B80, 0x6F201907,
+	0x1B80, 0x6E001915,
+	0x1B80, 0x6E001917,
+	0x1B80, 0x6D001925,
+	0x1B80, 0x6D001927,
+	0x1B80, 0x6C031935,
+	0x1B80, 0x6C031937,
+	0x1B80, 0x73201945,
+	0x1B80, 0x73201947,
+	0x1B80, 0x72001955,
+	0x1B80, 0x72001957,
+	0x1B80, 0x71001965,
+	0x1B80, 0x71001967,
+	0x1B80, 0x7B201975,
+	0x1B80, 0x7B201977,
+	0x1B80, 0x7A001985,
+	0x1B80, 0x7A001987,
+	0x1B80, 0x79001995,
+	0x1B80, 0x79001997,
+	0x1B80, 0x7F2019A5,
+	0x1B80, 0x7F2019A7,
+	0x1B80, 0x7E0019B5,
+	0x1B80, 0x7E0019B7,
+	0x1B80, 0x7D0019C5,
+	0x1B80, 0x7D0019C7,
+	0x1B80, 0x090119D5,
+	0x1B80, 0x090119D7,
+	0x1B80, 0x0AC619E5,
+	0x1B80, 0x0AC619E7,
+	0x1B80, 0x0BA619F5,
+	0x1B80, 0x0BA619F7,
+	0x1B80, 0x0C011A05,
+	0x1B80, 0x0C011A07,
+	0x1B80, 0x0D021A15,
+	0x1B80, 0x0D021A17,
+	0x1B80, 0x0E041A25,
+	0x1B80, 0x0E041A27,
+	0x1B80, 0x0FFF1A35,
+	0x1B80, 0x0FFF1A37,
+	0x1B80, 0x4D041A45,
+	0x1B80, 0x4D041A47,
+	0x1B80, 0x28F81A55,
+	0x1B80, 0x28F81A57,
+	0x1B80, 0xE0001A65,
+	0x1B80, 0xE0001A67,
+	0x1B80, 0x4D001A75,
+	0x1B80, 0x4D001A77,
+	0x1B80, 0x00011A85,
+	0x1B80, 0x00011A87,
+	0x1B80, 0x4D041A95,
+	0x1B80, 0x4D041A97,
+	0x1B80, 0x2EF81AA5,
+	0x1B80, 0x2EF81AA7,
+	0x1B80, 0x00021AB5,
+	0x1B80, 0x00021AB7,
+	0x1B80, 0x23031AC5,
+	0x1B80, 0x23031AC7,
+	0x1B80, 0x00001AD5,
+	0x1B80, 0x00001AD7,
+	0x1B80, 0x23131AE5,
+	0x1B80, 0x23131AE7,
+	0x1B80, 0xE77F1AF5,
+	0x1B80, 0xE77F1AF7,
+	0x1B80, 0x232F1B05,
+	0x1B80, 0x232F1B07,
+	0x1B80, 0xEFBF1B15,
+	0x1B80, 0xEFBF1B17,
+	0x1B80, 0x2EF01B25,
+	0x1B80, 0x2EF01B27,
+	0x1B80, 0x00021B35,
+	0x1B80, 0x00021B37,
+	0x1B80, 0x4D001B45,
+	0x1B80, 0x4D001B47,
+	0x1B80, 0x00011B55,
+	0x1B80, 0x00011B57,
+	0x1B80, 0x4D041B65,
+	0x1B80, 0x4D041B67,
+	0x1B80, 0x2EF81B75,
+	0x1B80, 0x2EF81B77,
+	0x1B80, 0x00021B85,
+	0x1B80, 0x00021B87,
+	0x1B80, 0x23031B95,
+	0x1B80, 0x23031B97,
+	0x1B80, 0x00001BA5,
+	0x1B80, 0x00001BA7,
+	0x1B80, 0x23131BB5,
+	0x1B80, 0x23131BB7,
+	0x1B80, 0xE77F1BC5,
+	0x1B80, 0xE77F1BC7,
+	0x1B80, 0x232F1BD5,
+	0x1B80, 0x232F1BD7,
+	0x1B80, 0xE79F1BE5,
+	0x1B80, 0xE79F1BE7,
+	0x1B80, 0x2EF01BF5,
+	0x1B80, 0x2EF01BF7,
+	0x1B80, 0x00021C05,
+	0x1B80, 0x00021C07,
+	0x1B80, 0x28F81C15,
+	0x1B80, 0x28F81C17,
+	0x1B80, 0x80001C25,
+	0x1B80, 0x80001C27,
+	0x1B80, 0x4D001C35,
+	0x1B80, 0x4D001C37,
+	0x1B80, 0x00011C45,
+	0x1B80, 0x00011C47,
+	0x1B80, 0x00041C55,
+	0x1B80, 0x00041C57,
+	0x1B80, 0x6BC01C65,
+	0x1B80, 0x6BC01C67,
+	0x1B80, 0x4D041C75,
+	0x1B80, 0x4D041C77,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241C85,
+	0x1B80, 0x68241C87,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x68481C85,
+	0x1B80, 0x68481C87,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x66061C95,
+	0x1B80, 0x66061C97,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x650C1CA5,
+	0x1B80, 0x650C1CA7,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x65041CA5,
+	0x1B80, 0x65041CA7,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x64471CB5,
+	0x1B80, 0x64471CB7,
+	0x1B80, 0x23411CC5,
+	0x1B80, 0x23411CC7,
+	0x1B80, 0x100E1CD5,
+	0x1B80, 0x100E1CD7,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60101CE5,
+	0x1B80, 0x60101CE7,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x60011CE5,
+	0x1B80, 0x60011CE7,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x23411CF5,
+	0x1B80, 0x23411CF7,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60811D05,
+	0x1B80, 0x60811D07,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x60611D05,
+	0x1B80, 0x60611D07,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x23411D15,
+	0x1B80, 0x23411D17,
+	0x1B80, 0x70E11D25,
+	0x1B80, 0x70E11D27,
+	0x1B80, 0x4D001D35,
+	0x1B80, 0x4D001D37,
+	0x1B80, 0x00011D45,
+	0x1B80, 0x00011D47,
+	0x1B80, 0x00041D55,
+	0x1B80, 0x00041D57,
+	0x1B80, 0x6B401D65,
+	0x1B80, 0x6B401D67,
+	0x1B80, 0x4D041D75,
+	0x1B80, 0x4D041D77,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x68241D85,
+	0x1B80, 0x68241D87,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x68481D85,
+	0x1B80, 0x68481D87,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x66061D95,
+	0x1B80, 0x66061D97,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65081DA5,
+	0x1B80, 0x65081DA7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65081DA5,
+	0x1B80, 0x65081DA7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x65181DA5,
+	0x1B80, 0x65181DA7,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x65081DA5,
+	0x1B80, 0x65081DA7,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x64481DB5,
+	0x1B80, 0x64481DB7,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x64471DB5,
+	0x1B80, 0x64471DB7,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x23411DC5,
+	0x1B80, 0x23411DC7,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E41DD5,
+	0x1B80, 0x11E41DD7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E41DD5,
+	0x1B80, 0x11E41DD7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x11E81DD5,
+	0x1B80, 0x11E81DD7,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x11E41DD5,
+	0x1B80, 0x11E41DD7,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x60011DE5,
+	0x1B80, 0x60011DE7,
+	0x1B80, 0x23411DF5,
+	0x1B80, 0x23411DF7,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60E11E05,
+	0x1B80, 0x60E11E07,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x60E11E05,
+	0x1B80, 0x60E11E07,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0x1B80, 0x61E11E05,
+	0x1B80, 0x61E11E07,
+	0xA0000000,	0x00000000,
+	0x1B80, 0x60E11E05,
+	0x1B80, 0x60E11E07,
+	0xB0000000,	0x00000000,
+	0x1B80, 0x23411E15,
+	0x1B80, 0x23411E17,
+	0x1B80, 0x70611E25,
+	0x1B80, 0x70611E27,
+	0x1B80, 0x4D001E35,
+	0x1B80, 0x4D001E37,
+	0x1B80, 0x00011E45,
+	0x1B80, 0x00011E47,
+	0x1B80, 0x00001E55,
+	0x1B80, 0x00001E57,
+	0x1B80, 0x00001E65,
+	0x1B80, 0x00001E67,
+	0x1B80, 0x00001E75,
+	0x1B80, 0x00001E77,
+	0x1B80, 0x00001E85,
+	0x1B80, 0x00001E87,
+	0x1B80, 0x00001E95,
+	0x1B80, 0x00001E97,
+	0x1B80, 0x00001EA5,
+	0x1B80, 0x00001EA7,
+	0x1B80, 0x00001EB5,
+	0x1B80, 0x00001EB7,
+	0x1B80, 0x00001EC5,
+	0x1B80, 0x00001EC7,
+	0x1B80, 0x00001ED5,
+	0x1B80, 0x00001ED7,
+	0x1B80, 0x00001EE5,
+	0x1B80, 0x00001EE7,
+	0x1B80, 0x00001EF5,
+	0x1B80, 0x00001EF7,
+	0x1B80, 0x00001F05,
+	0x1B80, 0x00001F07,
+	0x1B80, 0x00001F15,
+	0x1B80, 0x00001F17,
+	0x1B80, 0x00001F25,
+	0x1B80, 0x00001F27,
+	0x1B80, 0x00001F35,
+	0x1B80, 0x00001F37,
+	0x1B80, 0x00001F45,
+	0x1B80, 0x00001F47,
+	0x1B80, 0x00001F55,
+	0x1B80, 0x00001F57,
+	0x1B80, 0x00001F65,
+	0x1B80, 0x00001F67,
+	0x1B80, 0x00001F75,
+	0x1B80, 0x00001F77,
+	0x1B80, 0x00001F85,
+	0x1B80, 0x00001F87,
+	0x1B80, 0x00001F95,
+	0x1B80, 0x00001F97,
+	0x1B80, 0x00001FA5,
+	0x1B80, 0x00001FA7,
+	0x1B80, 0x00001FB5,
+	0x1B80, 0x00001FB7,
+	0x1B80, 0x00001FC5,
+	0x1B80, 0x00001FC7,
+	0x1B80, 0x00001FD5,
+	0x1B80, 0x00001FD7,
+	0x1B80, 0x00001FE5,
+	0x1B80, 0x00001FE7,
+	0x1B80, 0x00001FF5,
+	0x1B80, 0x00001FF7,
+	0x1B80, 0x00000006,
+	0x1B80, 0x00000002,
+};
+
+RTW_DECL_TABLE_PHY_COND(rtw8814a_bb, rtw_phy_cfg_bb);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x32323232, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x26283032, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x30303030, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x24262830, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x32322426, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x30323232, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x22242628, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x30303030, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x24262830, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x20222222, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x32323232, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x26283032, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x30303030, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x24262830, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x32322426, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x30323232, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x30303030, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x24262830, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x20222222, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x32323232, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x26283032, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x30303030, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x24262830, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x32322426, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x30323232, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x22242628, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x30303030, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x24262830, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x20222222, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x32323232, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x26283032, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x30303030, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x24262830, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x32322426, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x30323232, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x22242628, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x30303030, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x24262830, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x20222222, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x32323232, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x26283032, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x30303030, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x24262830, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x32322426, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x30323232, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x22242628, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x30303030, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x24262830, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x20222222, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x32323232, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x26283032, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x30303030, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x24262830, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x32322426, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x30323232, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x30303030, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x24262830, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x20222222, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x32323232, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x26283032, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x30303030, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x24262830, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x32322426, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x30323232, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x22242628, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x30303030, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x24262830, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x20222222, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x32323232, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x26283032, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x30303030, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x24262830, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x32322426, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x30323232, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x22242628, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x30303030, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x24262830, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x20222222, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type0[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x32323232, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x32323232, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x28303232, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x32323232, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x26283032, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x30303030, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x24262830, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x28282828, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x22242628, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x32323232, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x26283032, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x30302224, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x28303030, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x20222426, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x28282828, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x22242628, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x18202020, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x32323232, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x32323232, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x28303232, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x32323232, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x26283032, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x30303030, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x24262830, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x28282828, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x22242628, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x32323232, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x26283032, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x30302224, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x28303030, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x20222426, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x28282828, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x22242628, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x18202020, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x32323232, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x32323232, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x28303232, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x32323232, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x26283032, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x30303030, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x24262830, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x28282828, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x22242628, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x32323232, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x26283032, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x30302224, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x28303030, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x20222426, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x28282828, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x22242628, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x18202020, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x32323232, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x32323232, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x28303232, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x32323232, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x26283032, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x30303030, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x24262830, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x28282828, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x22242628, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x32323232, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x26283032, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x30302224, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x28303030, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x20222426, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x28282828, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x22242628, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x18202020, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x32323232, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x28303232, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x32323232, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x26283032, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x30303030, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x24262830, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x28282828, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x22242628, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x32323232, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x26283032, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x30302224, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x28303030, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x20222426, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x28282828, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x22242628, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x18202020, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x32323232, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x28303232, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x32323232, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x26283032, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x30303030, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x24262830, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x28282828, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x22242628, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x32323232, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x26283032, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x30302224, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x28303030, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x20222426, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x28282828, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x22242628, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x18202020, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x32323232, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x28303232, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x32323232, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x26283032, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x30303030, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x24262830, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x28282828, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x22242628, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x32323232, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x26283032, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x30302224, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x28303030, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x20222426, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x28282828, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x22242628, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x18202020, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x32323232, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x28303232, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x32323232, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x26283032, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x30303030, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x24262830, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x28282828, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x22242628, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x32323232, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x26283032, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x30302224, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x28303030, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x20222426, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x28282828, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x22242628, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x18202020, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type0);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type2[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x32323232, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x26283032, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x30303030, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x24262830, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x32322426, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x30323232, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x22242628, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x30303030, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x24262830, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x20222222, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x32323232, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x26283032, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x30303030, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x24262830, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x32322426, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x30323232, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x30303030, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x24262830, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x20222222, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x32323232, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x26283032, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x30303030, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x24262830, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x32322426, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x30323232, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x22242628, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x30303030, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x24262830, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x20222222, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x32323232, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x26283032, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x30303030, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x24262830, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x32322426, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x30323232, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x22242628, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x30303030, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x24262830, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x20222222, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x32323232, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x26283032, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x30303030, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x24262830, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x32322426, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x30323232, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x22242628, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x30303030, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x24262830, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x20222222, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x32323232, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x26283032, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x30303030, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x24262830, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x32322426, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x30323232, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x30303030, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x24262830, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x20222222, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x32323232, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x26283032, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x30303030, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x24262830, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x32322426, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x30323232, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x22242628, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x30303030, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x24262830, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x20222222, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x32323232, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x26283032, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x30303030, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x24262830, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x32322426, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x30323232, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x22242628, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x30303030, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x24262830, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x20222222, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type2);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type3[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x48484848, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x44464646, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x42444646, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x46464646, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x42444646, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x46464646, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x42444646, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x42444646, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x46463840, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x46464646, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x38404244, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x46464646, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x42444646, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x38383840, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x48484848, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x44464646, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x42444646, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x46464646, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x42444646, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x46464646, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x42444646, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x42444646, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x46463840, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x46464646, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x38404244, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x46464646, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x42444646, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x38383840, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x48484848, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x44464646, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x42444646, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x46464646, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x42444646, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x46464646, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x42444646, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x42444646, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x46463840, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x46464646, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x38404244, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x46464646, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x42444646, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x38383840, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x48484848, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x44464646, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x42444646, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x46464646, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x42444646, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x46464646, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x42444646, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x42444646, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x46463840, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x46464646, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x38404244, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x46464646, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x42444646, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x38383840, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x44464646, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x42444646, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x46464646, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x42444646, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x46464646, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x42444646, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x42444646, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x46463840, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x46464646, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x38404244, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x46464646, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x42444646, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x38383840, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x44464646, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x42444646, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x46464646, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x42444646, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x46464646, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x42444646, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x42444646, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x46463840, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x46464646, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x38404244, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x46464646, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x42444646, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x38383840, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x44464646, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x42444646, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x46464646, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x42444646, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x46464646, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x42444646, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x42444646, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x46463840, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x46464646, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x38404244, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x46464646, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x42444646, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x38383840, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x44464646, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x42444646, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x46464646, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x42444646, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x46464646, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x42444646, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x42444646, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x46463840, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x46464646, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x38404244, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x46464646, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x42444646, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x38383840, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type3);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type4[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x42424242, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x42424242, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x36384042, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x42424242, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x34363840, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x42424242, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x34363840, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x42424242, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x34363840, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x42424242, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x34363840, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x42423032, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x38404242, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x30323436, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x42424242, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x34363840, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x30303032, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x42424242, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x42424242, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x36384042, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x42424242, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x34363840, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x42424242, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x34363840, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x42424242, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x34363840, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x42424242, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x34363840, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x42423032, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x38404242, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x30323436, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x42424242, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x34363840, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x30303032, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x42424242, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x42424242, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x36384042, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x42424242, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x34363840, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x42424242, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x34363840, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x42424242, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x34363840, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x42424242, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x34363840, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x42423032, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x38404242, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x30323436, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x42424242, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x34363840, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x30303032, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x42424242, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x42424242, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x36384042, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x42424242, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x34363840, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x42424242, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x34363840, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x42424242, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x34363840, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x42424242, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x34363840, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x42423032, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x38404242, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x30323436, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x42424242, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x34363840, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x30303032, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x42424242, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x36384042, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x42424242, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x34363840, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x42424242, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x34363840, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x42424242, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x34363840, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x42424242, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x34363840, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x42423032, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x38404242, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x30323436, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x42424242, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x34363840, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x30303032, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x42424242, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x36384042, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x42424242, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x34363840, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x42424242, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x34363840, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x42424242, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x34363840, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x42424242, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x34363840, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x42423032, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x38404242, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x30323436, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x42424242, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x34363840, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x30303032, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x42424242, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x36384042, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x42424242, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x34363840, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x42424242, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x34363840, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x42424242, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x34363840, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x42424242, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x34363840, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x42423032, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x38404242, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x30323436, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x42424242, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x34363840, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x30303032, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x42424242, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x36384042, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x42424242, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x34363840, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x42424242, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x34363840, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x42424242, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x34363840, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x42424242, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x34363840, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x42423032, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x38404242, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x30323436, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x42424242, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x34363840, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x30303032, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type4);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type5[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x48484848, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x44464646, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x42444646, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x44444444, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x40424444, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x42424242, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x38404242, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x46464646, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x42444646, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x44444040, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x44444444, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x38384042, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x42424242, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x38404242, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x20203636, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x48484848, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x44464646, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x42444646, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x44444444, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x40424444, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x42424242, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x38404242, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x46464646, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x42444646, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x44444040, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x44444444, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x38384042, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x42424242, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x38404242, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x20203636, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x48484848, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x44464646, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x42444646, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x44444444, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x40424444, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x42424242, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x38404242, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x46464646, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x42444646, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x44444040, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x44444444, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x38384042, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x42424242, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x38404242, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x20203636, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x48484848, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x44464646, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x42444646, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x44444444, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x40424444, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x42424242, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x38404242, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x46464646, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x42444646, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x44444040, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x44444444, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x38384042, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x42424242, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x38404242, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x20203636, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x44464646, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x42444646, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x44444444, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x40424444, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x42424242, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x38404242, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x42444646, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x44443840, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x44444444, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x36384042, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x42424242, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x38404242, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x20203436, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x44464646, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x42444646, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x44444444, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x40424444, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x42424242, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x38404242, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x42444646, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x44443840, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x44444444, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x36384042, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x42424242, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x38404242, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x20203436, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x44464646, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x42444646, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x44444444, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x40424444, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x42424242, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x38404242, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x42444646, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x44443840, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x44444444, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x36384042, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x42424242, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x38404242, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x20203436, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x44464646, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x42444646, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x44444444, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x40424444, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x42424242, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x38404242, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x42444646, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x44443840, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x44444444, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x36384042, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x42424242, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x38404242, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x20203436, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type5);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type7[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x34343434, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x28303234, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x34343434, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x28303234, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x34342426, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x32343434, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x24262830, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x34343434, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x28303234, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x24263434, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x34343434, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x28303234, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x34343434, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x28303234, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x34342426, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x32343434, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x24262830, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x34343434, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x28303234, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x24263434, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x34343434, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x28303234, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x34343434, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x28303234, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x34342426, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x32343434, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x24262830, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x34343434, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x28303234, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x24263434, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x34343434, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x28303234, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x34343434, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x28303234, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x34342426, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x32343434, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x24262830, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x34343434, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x28303234, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x24263434, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x30323434, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x28303234, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x34343434, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x28303234, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x34343434, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x28303234, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x34342426, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x32343434, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x24262830, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x34343434, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x28303234, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x24263434, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x30323434, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x28303234, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x34343434, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x28303234, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x34343434, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x28303234, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x34342426, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x32343434, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x24262830, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x34343434, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x28303234, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x24263434, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x30323434, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x28303234, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x34343434, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x28303234, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x34343434, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x28303234, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x34342426, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x32343434, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x24262830, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x34343434, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x28303234, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x24263434, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x30323434, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x28303234, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x34343434, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x28303234, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x34343434, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x28303234, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x34342426, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x32343434, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x24262830, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x34343434, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x28303234, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x24263434, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type7);
+
+static const struct rtw_phy_pg_cfg_pair rtw8814a_bb_pg_type8[] = {
+	{ 0, 0, 0, 0x00000c20, 0xffffffff, 0x43434343, },
+	{ 0, 0, 0, 0x00000c24, 0xffffffff, 0x43434343, },
+	{ 0, 0, 0, 0x00000c28, 0xffffffff, 0x35373941, },
+	{ 0, 0, 0, 0x00000c2c, 0xffffffff, 0x43434343, },
+	{ 0, 0, 0, 0x00000c30, 0xffffffff, 0x33353739, },
+	{ 0, 0, 1, 0x00000c34, 0xffffffff, 0x43434343, },
+	{ 0, 0, 1, 0x00000c38, 0xffffffff, 0x31333537, },
+	{ 0, 0, 2, 0x00000cd8, 0xffffffff, 0x43434343, },
+	{ 0, 0, 2, 0x00000cdc, 0xffffffff, 0x29313335, },
+	{ 0, 0, 0, 0x00000c3c, 0xffffffff, 0x34343434, },
+	{ 0, 0, 0, 0x00000c40, 0xffffffff, 0x28303234, },
+	{ 0, 0, 0, 0x00000c44, 0xffffffff, 0x32322426, },
+	{ 0, 0, 1, 0x00000c48, 0xffffffff, 0x30323232, },
+	{ 0, 0, 1, 0x00000c4c, 0xffffffff, 0x22242628, },
+	{ 0, 0, 2, 0x00000ce0, 0xffffffff, 0x30303030, },
+	{ 0, 0, 2, 0x00000ce4, 0xffffffff, 0x24262830, },
+	{ 0, 0, 2, 0x00000ce8, 0x0000ffff, 0x20222222, },
+	{ 0, 1, 0, 0x00000e20, 0xffffffff, 0x43434343, },
+	{ 0, 1, 0, 0x00000e24, 0xffffffff, 0x43434343, },
+	{ 0, 1, 0, 0x00000e28, 0xffffffff, 0x35373941, },
+	{ 0, 1, 0, 0x00000e2c, 0xffffffff, 0x41434343, },
+	{ 0, 1, 0, 0x00000e30, 0xffffffff, 0x33353739, },
+	{ 0, 1, 1, 0x00000e34, 0xffffffff, 0x39414141, },
+	{ 0, 1, 1, 0x00000e38, 0xffffffff, 0x31333537, },
+	{ 0, 1, 2, 0x00000ed8, 0xffffffff, 0x37393939, },
+	{ 0, 1, 2, 0x00000edc, 0xffffffff, 0x29313335, },
+	{ 0, 1, 0, 0x00000e3c, 0xffffffff, 0x34343434, },
+	{ 0, 1, 0, 0x00000e40, 0xffffffff, 0x28303234, },
+	{ 0, 1, 0, 0x00000e44, 0xffffffff, 0x32322426, },
+	{ 0, 1, 1, 0x00000e48, 0xffffffff, 0x30323232, },
+	{ 0, 1, 1, 0x00000e4c, 0xffffffff, 0x22242628, },
+	{ 0, 1, 2, 0x00000ee0, 0xffffffff, 0x30303030, },
+	{ 0, 1, 2, 0x00000ee4, 0xffffffff, 0x24262830, },
+	{ 0, 1, 2, 0x00000ee8, 0x0000ffff, 0x20222222, },
+	{ 0, 2, 0, 0x00001820, 0xffffffff, 0x43434343, },
+	{ 0, 2, 0, 0x00001824, 0xffffffff, 0x43434343, },
+	{ 0, 2, 0, 0x00001828, 0xffffffff, 0x35373941, },
+	{ 0, 2, 0, 0x0000182c, 0xffffffff, 0x41434343, },
+	{ 0, 2, 0, 0x00001830, 0xffffffff, 0x33353739, },
+	{ 0, 2, 1, 0x00001834, 0xffffffff, 0x39414141, },
+	{ 0, 2, 1, 0x00001838, 0xffffffff, 0x31333537, },
+	{ 0, 2, 2, 0x000018d8, 0xffffffff, 0x37393939, },
+	{ 0, 2, 2, 0x000018dc, 0xffffffff, 0x29313335, },
+	{ 0, 2, 0, 0x0000183c, 0xffffffff, 0x34343434, },
+	{ 0, 2, 0, 0x00001840, 0xffffffff, 0x28303234, },
+	{ 0, 2, 0, 0x00001844, 0xffffffff, 0x32322426, },
+	{ 0, 2, 1, 0x00001848, 0xffffffff, 0x30323232, },
+	{ 0, 2, 1, 0x0000184c, 0xffffffff, 0x22242628, },
+	{ 0, 2, 2, 0x000018e0, 0xffffffff, 0x30303030, },
+	{ 0, 2, 2, 0x000018e4, 0xffffffff, 0x24262830, },
+	{ 0, 2, 2, 0x000018e8, 0x0000ffff, 0x20222222, },
+	{ 0, 3, 0, 0x00001a20, 0xffffffff, 0x43434343, },
+	{ 0, 3, 0, 0x00001a24, 0xffffffff, 0x43434343, },
+	{ 0, 3, 0, 0x00001a28, 0xffffffff, 0x35373941, },
+	{ 0, 3, 0, 0x00001a2c, 0xffffffff, 0x41434343, },
+	{ 0, 3, 0, 0x00001a30, 0xffffffff, 0x33353739, },
+	{ 0, 3, 1, 0x00001a34, 0xffffffff, 0x39414141, },
+	{ 0, 3, 1, 0x00001a38, 0xffffffff, 0x31333537, },
+	{ 0, 3, 2, 0x00001ad8, 0xffffffff, 0x37393939, },
+	{ 0, 3, 2, 0x00001adc, 0xffffffff, 0x29313335, },
+	{ 0, 3, 0, 0x00001a3c, 0xffffffff, 0x34343434, },
+	{ 0, 3, 0, 0x00001a40, 0xffffffff, 0x28303234, },
+	{ 0, 3, 0, 0x00001a44, 0xffffffff, 0x32322426, },
+	{ 0, 3, 1, 0x00001a48, 0xffffffff, 0x30323232, },
+	{ 0, 3, 1, 0x00001a4c, 0xffffffff, 0x22242628, },
+	{ 0, 3, 2, 0x00001ae0, 0xffffffff, 0x30303030, },
+	{ 0, 3, 2, 0x00001ae4, 0xffffffff, 0x24262830, },
+	{ 0, 3, 2, 0x00001ae8, 0x0000ffff, 0x20222222, },
+	{ 1, 0, 0, 0x00000c24, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c28, 0xffffffff, 0x39414345, },
+	{ 1, 0, 0, 0x00000c2c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c30, 0xffffffff, 0x38404244, },
+	{ 1, 0, 1, 0x00000c34, 0xffffffff, 0x46464646, },
+	{ 1, 0, 1, 0x00000c38, 0xffffffff, 0x36384042, },
+	{ 1, 0, 2, 0x00000cd8, 0xffffffff, 0x46464646, },
+	{ 1, 0, 2, 0x00000cdc, 0xffffffff, 0x34363840, },
+	{ 1, 0, 0, 0x00000c3c, 0xffffffff, 0x46464646, },
+	{ 1, 0, 0, 0x00000c40, 0xffffffff, 0x38404244, },
+	{ 1, 0, 0, 0x00000c44, 0xffffffff, 0x46463738, },
+	{ 1, 0, 1, 0x00000c48, 0xffffffff, 0x42444646, },
+	{ 1, 0, 1, 0x00000c4c, 0xffffffff, 0x35373840, },
+	{ 1, 0, 2, 0x00000ce0, 0xffffffff, 0x46464646, },
+	{ 1, 0, 2, 0x00000ce4, 0xffffffff, 0x37394143, },
+	{ 1, 0, 2, 0x00000ce8, 0x0000ffff, 0x33333335, },
+	{ 1, 1, 0, 0x00000e24, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e28, 0xffffffff, 0x39414345, },
+	{ 1, 1, 0, 0x00000e2c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e30, 0xffffffff, 0x38404244, },
+	{ 1, 1, 1, 0x00000e34, 0xffffffff, 0x46464646, },
+	{ 1, 1, 1, 0x00000e38, 0xffffffff, 0x36384042, },
+	{ 1, 1, 2, 0x00000ed8, 0xffffffff, 0x46464646, },
+	{ 1, 1, 2, 0x00000edc, 0xffffffff, 0x34363840, },
+	{ 1, 1, 0, 0x00000e3c, 0xffffffff, 0x46464646, },
+	{ 1, 1, 0, 0x00000e40, 0xffffffff, 0x38404244, },
+	{ 1, 1, 0, 0x00000e44, 0xffffffff, 0x46463738, },
+	{ 1, 1, 1, 0x00000e48, 0xffffffff, 0x42444646, },
+	{ 1, 1, 1, 0x00000e4c, 0xffffffff, 0x35373840, },
+	{ 1, 1, 2, 0x00000ee0, 0xffffffff, 0x46464646, },
+	{ 1, 1, 2, 0x00000ee4, 0xffffffff, 0x37394143, },
+	{ 1, 1, 2, 0x00000ee8, 0x0000ffff, 0x33333335, },
+	{ 1, 2, 0, 0x00001824, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001828, 0xffffffff, 0x39414345, },
+	{ 1, 2, 0, 0x0000182c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001830, 0xffffffff, 0x38404244, },
+	{ 1, 2, 1, 0x00001834, 0xffffffff, 0x46464646, },
+	{ 1, 2, 1, 0x00001838, 0xffffffff, 0x36384042, },
+	{ 1, 2, 2, 0x000018d8, 0xffffffff, 0x46464646, },
+	{ 1, 2, 2, 0x000018dc, 0xffffffff, 0x34363840, },
+	{ 1, 2, 0, 0x0000183c, 0xffffffff, 0x46464646, },
+	{ 1, 2, 0, 0x00001840, 0xffffffff, 0x38404244, },
+	{ 1, 2, 0, 0x00001844, 0xffffffff, 0x46463738, },
+	{ 1, 2, 1, 0x00001848, 0xffffffff, 0x42444646, },
+	{ 1, 2, 1, 0x0000184c, 0xffffffff, 0x35373840, },
+	{ 1, 2, 2, 0x000018e0, 0xffffffff, 0x46464646, },
+	{ 1, 2, 2, 0x000018e4, 0xffffffff, 0x37394143, },
+	{ 1, 2, 2, 0x000018e8, 0x0000ffff, 0x33333335, },
+	{ 1, 3, 0, 0x00001a24, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a28, 0xffffffff, 0x39414345, },
+	{ 1, 3, 0, 0x00001a2c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a30, 0xffffffff, 0x38404244, },
+	{ 1, 3, 1, 0x00001a34, 0xffffffff, 0x46464646, },
+	{ 1, 3, 1, 0x00001a38, 0xffffffff, 0x36384042, },
+	{ 1, 3, 2, 0x00001ad8, 0xffffffff, 0x46464646, },
+	{ 1, 3, 2, 0x00001adc, 0xffffffff, 0x34363840, },
+	{ 1, 3, 0, 0x00001a3c, 0xffffffff, 0x46464646, },
+	{ 1, 3, 0, 0x00001a40, 0xffffffff, 0x38404244, },
+	{ 1, 3, 0, 0x00001a44, 0xffffffff, 0x46463738, },
+	{ 1, 3, 1, 0x00001a48, 0xffffffff, 0x42444646, },
+	{ 1, 3, 1, 0x00001a4c, 0xffffffff, 0x35373840, },
+	{ 1, 3, 2, 0x00001ae0, 0xffffffff, 0x46464646, },
+	{ 1, 3, 2, 0x00001ae4, 0xffffffff, 0x37394143, },
+	{ 1, 3, 2, 0x00001ae8, 0x0000ffff, 0x33333335, },
+};
+
+RTW_DECL_TABLE_BB_PG(rtw8814a_bb_pg_type8);
+
+static const u32 rtw8814a_rf_a[] = {
+		0x018, 0x00013124,
+		0x040, 0x00000C00,
+		0x058, 0x00000F98,
+		0x07F, 0x00068004,
+		0x0B0, 0x000FFFFE,
+		0x0B1, 0x0003FF48,
+		0x0B2, 0x0006AA3F,
+		0x0B3, 0x000FFC9A,
+		0x0B4, 0x0000A78F,
+		0x0B5, 0x00000A3F,
+		0x0B6, 0x0000C09C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0B7, 0x00030008,
+	0xA0000000,	0x00000000,
+		0x0B7, 0x0003000C,
+	0xB0000000,	0x00000000,
+		0x0B8, 0x0007400E,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0xA0000000,	0x00000000,
+		0x0B9, 0x000FBF50,
+	0xB0000000,	0x00000000,
+		0x0BA, 0x00050780,
+		0x0BB, 0x00000000,
+		0x0BC, 0x00040009,
+		0x0BD, 0x00000000,
+		0x0BE, 0x00000000,
+		0x0BF, 0x00000000,
+		0x0EF, 0x00020000,
+		0x03E, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xA0000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xB0000000,	0x00000000,
+		0x03E, 0x00020000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00040000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00040000,
+	0xA0000000,	0x00000000,
+		0x03F, 0x00040000,
+	0xB0000000,	0x00000000,
+		0x03E, 0x00040000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xA0000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xB0000000,	0x00000000,
+		0x03E, 0x00060000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xA0000000,	0x00000000,
+		0x03F, 0x00030000,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00010000,
+		0x03E, 0x00000000,
+		0x03F, 0x00006800,
+		0x03E, 0x00000080,
+		0x03F, 0x00006000,
+		0x03E, 0x00000100,
+		0x03F, 0x00004800,
+		0x03E, 0x00000180,
+		0x03F, 0x00004000,
+		0x03E, 0x00000200,
+		0x03F, 0x00004000,
+		0x03E, 0x00000280,
+		0x03F, 0x00002800,
+		0x03E, 0x00000300,
+		0x03F, 0x00002800,
+		0x03E, 0x00000380,
+		0x03F, 0x00002000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00040000,
+		0x03E, 0x00000000,
+		0x03F, 0x000000BC,
+		0x03E, 0x00000040,
+		0x03F, 0x00000053,
+		0x03E, 0x00000050,
+		0x03F, 0x00000050,
+		0x03E, 0x00000060,
+		0x03F, 0x00000050,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00000400,
+		0x03E, 0x00000006,
+		0x041, 0x000EE080,
+		0x03E, 0x00000008,
+		0x041, 0x000EE0C0,
+		0x03E, 0x0000000A,
+		0x041, 0x000EE100,
+		0x03E, 0x0000000C,
+		0x041, 0x000EE100,
+		0x0EF, 0x00000000,
+		0x018, 0x00000006,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0xA0000000,	0x00000000,
+		0x086, 0x000E4B58,
+		0x087, 0x00049F80,
+	0xB0000000,	0x00000000,
+		0x0DF, 0x00000008,
+		0x0EF, 0x00002000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x000179C3,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0003F258,
+		0x03B, 0x00030A58,
+		0x03B, 0x0002FA58,
+		0x03B, 0x00022590,
+		0x03B, 0x0001FA50,
+		0x03B, 0x00010248,
+		0x03B, 0x00008240,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000100,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000ADF6,
+		0x034, 0x00009DF3,
+		0x034, 0x00008DF0,
+		0x034, 0x00007DED,
+		0x034, 0x00006DEA,
+		0x034, 0x00005CED,
+		0x034, 0x00004CEA,
+		0x034, 0x000034EA,
+		0x034, 0x000024E7,
+		0x034, 0x0000146A,
+		0x034, 0x0000006B,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008ADF6,
+		0x034, 0x00089DF3,
+		0x034, 0x00088DF0,
+		0x034, 0x00087DED,
+		0x034, 0x00086DEA,
+		0x034, 0x00085CED,
+		0x034, 0x00084CEA,
+		0x034, 0x000834EA,
+		0x034, 0x000824E7,
+		0x034, 0x0008146A,
+		0x034, 0x0008006B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x000020A2,
+		0x0DF, 0x00000080,
+		0x035, 0x00000192,
+		0x035, 0x00008192,
+		0x035, 0x00010192,
+		0x036, 0x00000024,
+		0x036, 0x00008024,
+		0x036, 0x00010024,
+		0x036, 0x00018024,
+		0x0EF, 0x00000000,
+		0x051, 0x00000C21,
+		0x052, 0x000006D9,
+		0x053, 0x000FC649,
+		0x054, 0x0000017E,
+		0x018, 0x0001012A,
+		0x081, 0x0007FC00,
+		0x089, 0x00050110,
+		0x08A, 0x00043E50,
+		0x08B, 0x0002E180,
+		0x08C, 0x00093C3C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xA0000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xA0000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00001000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00028000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00030023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00028623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00021633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0001C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00010293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00009593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0000118B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0000078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x000AC000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00040000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0004C000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00070023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00068623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00061633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0005C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00050293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00049593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0004138B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0004078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0008C000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00004000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B0023,
+	0x80000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A8623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A1633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0009C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00090293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00089593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0008118B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0008078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00000800,
+		0x03B, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000801,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00000803,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00040000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001801,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000003,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000003,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001001,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001000,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00080000,
+	0x80000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000800,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001002,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x00013124,
+		0x0EF, 0x00000100,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A1AD,
+		0x034, 0x000491AA,
+		0x034, 0x000481A7,
+		0x034, 0x000470AA,
+		0x034, 0x000460A7,
+		0x034, 0x00045049,
+		0x034, 0x00044046,
+		0x034, 0x00043026,
+		0x034, 0x00042009,
+		0x034, 0x00041006,
+		0x034, 0x00040003,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3F5,
+		0x034, 0x000493F2,
+		0x034, 0x000483B0,
+		0x034, 0x00047370,
+		0x034, 0x0004636D,
+		0x034, 0x0004536A,
+		0x034, 0x00044349,
+		0x034, 0x0004316A,
+		0x034, 0x00042167,
+		0x034, 0x00041129,
+		0x034, 0x00040049,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AF,
+		0x034, 0x000483AB,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004406A,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0004AFF1,
+		0x034, 0x00049FEE,
+		0x034, 0x00048FEB,
+		0x034, 0x00047FE8,
+		0x034, 0x00046DEA,
+		0x034, 0x00045DE7,
+		0x034, 0x00044CEA,
+		0x034, 0x00043CE7,
+		0x034, 0x00042C69,
+		0x034, 0x00041C66,
+		0x034, 0x00040C28,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A1AD,
+		0x034, 0x000291AA,
+		0x034, 0x000281A7,
+		0x034, 0x000270AA,
+		0x034, 0x000260A7,
+		0x034, 0x00025049,
+		0x034, 0x00024046,
+		0x034, 0x00023026,
+		0x034, 0x00022009,
+		0x034, 0x00021006,
+		0x034, 0x00020003,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3F5,
+		0x034, 0x000293F2,
+		0x034, 0x000282F1,
+		0x034, 0x000272B0,
+		0x034, 0x000262AD,
+		0x034, 0x000252AA,
+		0x034, 0x000242A7,
+		0x034, 0x000230EC,
+		0x034, 0x000220E9,
+		0x034, 0x0002106A,
+		0x034, 0x00020067,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0002AFF1,
+		0x034, 0x00029FEE,
+		0x034, 0x00028FEB,
+		0x034, 0x00027FE8,
+		0x034, 0x00026DEA,
+		0x034, 0x00025DE7,
+		0x034, 0x00024CEA,
+		0x034, 0x00023CE7,
+		0x034, 0x00022C69,
+		0x034, 0x00021C66,
+		0x034, 0x00020C28,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EC,
+		0x034, 0x0000938C,
+		0x034, 0x000081AD,
+		0x034, 0x000071AA,
+		0x034, 0x000061A7,
+		0x034, 0x000050AA,
+		0x034, 0x000040A7,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x0000100C,
+		0x034, 0x00000009,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3F4,
+		0x034, 0x000093F1,
+		0x034, 0x000082B1,
+		0x034, 0x000071D1,
+		0x034, 0x000061CE,
+		0x034, 0x000051CB,
+		0x034, 0x000041C8,
+		0x034, 0x000030CB,
+		0x034, 0x000020C8,
+		0x034, 0x00001087,
+		0x034, 0x00000084,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000AFF1,
+		0x034, 0x00009FEE,
+		0x034, 0x00008FEB,
+		0x034, 0x00007FE8,
+		0x034, 0x00006DEA,
+		0x034, 0x00005DE7,
+		0x034, 0x00004CEA,
+		0x034, 0x00003CE7,
+		0x034, 0x00002C69,
+		0x034, 0x00001C66,
+		0x034, 0x00000C28,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA1AD,
+		0x034, 0x000C91AA,
+		0x034, 0x000C81A7,
+		0x034, 0x000C70AA,
+		0x034, 0x000C60A7,
+		0x034, 0x000C5049,
+		0x034, 0x000C4046,
+		0x034, 0x000C3026,
+		0x034, 0x000C2009,
+		0x034, 0x000C1006,
+		0x034, 0x000C0003,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3F5,
+		0x034, 0x000C93F2,
+		0x034, 0x000C83B0,
+		0x034, 0x000C7370,
+		0x034, 0x000C636D,
+		0x034, 0x000C536A,
+		0x034, 0x000C4349,
+		0x034, 0x000C316A,
+		0x034, 0x000C2167,
+		0x034, 0x000C1129,
+		0x034, 0x000C0049,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AF,
+		0x034, 0x000C83AB,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C406A,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0xA0000000,	0x00000000,
+		0x034, 0x000CA794,
+		0x034, 0x000C9791,
+		0x034, 0x000C878E,
+		0x034, 0x000C778B,
+		0x034, 0x000C658D,
+		0x034, 0x000C558A,
+		0x034, 0x000C448D,
+		0x034, 0x000C348A,
+		0x034, 0x000C244C,
+		0x034, 0x000C1449,
+		0x034, 0x000C042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA1AD,
+		0x034, 0x000A91AA,
+		0x034, 0x000A81A7,
+		0x034, 0x000A70AA,
+		0x034, 0x000A60A7,
+		0x034, 0x000A5049,
+		0x034, 0x000A4046,
+		0x034, 0x000A3026,
+		0x034, 0x000A2009,
+		0x034, 0x000A1006,
+		0x034, 0x000A0003,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3F5,
+		0x034, 0x000A93F2,
+		0x034, 0x000A82F1,
+		0x034, 0x000A72B0,
+		0x034, 0x000A62AD,
+		0x034, 0x000A52AA,
+		0x034, 0x000A42A7,
+		0x034, 0x000A30EC,
+		0x034, 0x000A20E9,
+		0x034, 0x000A106A,
+		0x034, 0x000A0067,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0xA0000000,	0x00000000,
+		0x034, 0x000AA794,
+		0x034, 0x000A9791,
+		0x034, 0x000A878E,
+		0x034, 0x000A778B,
+		0x034, 0x000A658D,
+		0x034, 0x000A558A,
+		0x034, 0x000A448D,
+		0x034, 0x000A348A,
+		0x034, 0x000A244C,
+		0x034, 0x000A1449,
+		0x034, 0x000A042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EC,
+		0x034, 0x0008938C,
+		0x034, 0x000881AD,
+		0x034, 0x000871AA,
+		0x034, 0x000861A7,
+		0x034, 0x000850AA,
+		0x034, 0x000840A7,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x0008100C,
+		0x034, 0x00080009,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3F4,
+		0x034, 0x000893F1,
+		0x034, 0x000882B1,
+		0x034, 0x000871D1,
+		0x034, 0x000861CE,
+		0x034, 0x000851CB,
+		0x034, 0x000841C8,
+		0x034, 0x000830CB,
+		0x034, 0x000820C8,
+		0x034, 0x00081087,
+		0x034, 0x00080084,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008A794,
+		0x034, 0x00089791,
+		0x034, 0x0008878E,
+		0x034, 0x0008778B,
+		0x034, 0x0008658D,
+		0x034, 0x0008558A,
+		0x034, 0x0008448D,
+		0x034, 0x0008348A,
+		0x034, 0x0008244C,
+		0x034, 0x00081449,
+		0x034, 0x0008042B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0DF, 0x00000001,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000040,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0xA0000000,	0x00000000,
+		0x035, 0x00000747,
+		0x035, 0x00008747,
+		0x035, 0x00010747,
+		0x035, 0x00020747,
+		0x035, 0x00028747,
+		0x035, 0x00030747,
+		0x035, 0x00040747,
+		0x035, 0x00048747,
+		0x035, 0x00050747,
+		0x035, 0x000805FB,
+		0x035, 0x000885FB,
+		0x035, 0x000905FB,
+		0x035, 0x000A05FB,
+		0x035, 0x000A85FB,
+		0x035, 0x000B05FB,
+		0x035, 0x000C05FB,
+		0x035, 0x000C85FB,
+		0x035, 0x000D05FB,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0DF, 0x00000001,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000010,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000473,
+		0x036, 0x00008473,
+		0x036, 0x00010473,
+		0x036, 0x00020473,
+		0x036, 0x00028473,
+		0x036, 0x00030473,
+		0x036, 0x00040473,
+		0x036, 0x00048473,
+		0x036, 0x00050473,
+		0x036, 0x00080473,
+		0x036, 0x00088473,
+		0x036, 0x00090473,
+		0x036, 0x000A0473,
+		0x036, 0x000A8473,
+		0x036, 0x000B0473,
+		0x036, 0x000C0473,
+		0x036, 0x000C8473,
+		0x036, 0x000D0473,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0xA0000000,	0x00000000,
+		0x036, 0x00000473,
+		0x036, 0x00008473,
+		0x036, 0x00010473,
+		0x036, 0x00020473,
+		0x036, 0x00028473,
+		0x036, 0x00030473,
+		0x036, 0x00040473,
+		0x036, 0x00048473,
+		0x036, 0x00050473,
+		0x036, 0x00080473,
+		0x036, 0x00088473,
+		0x036, 0x00090473,
+		0x036, 0x000A0473,
+		0x036, 0x000A8473,
+		0x036, 0x000B0473,
+		0x036, 0x000C0473,
+		0x036, 0x000C8473,
+		0x036, 0x000D0473,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x0EF, 0x00000004,
+		0x037, 0x00000000,
+		0x038, 0x00005146,
+		0x037, 0x00004000,
+		0x038, 0x00005146,
+		0x037, 0x00008000,
+		0x038, 0x00005146,
+		0x037, 0x00010000,
+		0x038, 0x00005146,
+		0x037, 0x00014000,
+		0x038, 0x00005146,
+		0x037, 0x00018000,
+		0x038, 0x00004D4E,
+		0x037, 0x0001C000,
+		0x038, 0x00004D4E,
+		0x037, 0x00020000,
+		0x038, 0x00004D4E,
+		0x037, 0x00024000,
+		0x038, 0x000071C6,
+		0x037, 0x00028000,
+		0x038, 0x000071C6,
+		0x037, 0x0002C000,
+		0x038, 0x000071C6,
+		0x037, 0x00030000,
+		0x038, 0x000071CE,
+		0x037, 0x00034000,
+		0x038, 0x000071CE,
+		0x037, 0x00038000,
+		0x038, 0x00005126,
+		0x037, 0x0003C000,
+		0x038, 0x00005126,
+		0x037, 0x00040000,
+		0x038, 0x00005126,
+		0x037, 0x00044000,
+		0x038, 0x00005126,
+		0x037, 0x00048000,
+		0x038, 0x00005126,
+		0x037, 0x00080000,
+		0x038, 0x00005ECE,
+		0x037, 0x00084000,
+		0x038, 0x00005ECE,
+		0x037, 0x00088000,
+		0x038, 0x00005ECE,
+		0x037, 0x00090000,
+		0x038, 0x00005ECE,
+		0x037, 0x00094000,
+		0x038, 0x00005ECE,
+		0x037, 0x00098000,
+		0x038, 0x00005ECE,
+		0x037, 0x0009C000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000AC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000BC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C8000,
+		0x038, 0x00005ECE,
+		0x0EF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000008,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000007D,
+		0x03C, 0x0000047D,
+		0x03C, 0x0000087D,
+		0x03C, 0x0000107D,
+		0x03C, 0x0000147D,
+		0x03C, 0x0000187D,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x0000054A,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x0000154A,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x0000254A,
+		0x03C, 0x00002821,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000037E,
+		0x03C, 0x00000575,
+		0x03C, 0x00000971,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001575,
+		0x03C, 0x00001871,
+		0x03C, 0x0000217E,
+		0x03C, 0x00002575,
+		0x03C, 0x00002871,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x061, 0x000C0D47,
+		0x062, 0x0000133C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0xA0000000,	0x00000000,
+		0x063, 0x0007D0E7,
+	0xB0000000,	0x00000000,
+		0x064, 0x00014FEC,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0xA0000000,	0x00000000,
+		0x065, 0x000933FF,
+	0xB0000000,	0x00000000,
+		0x066, 0x00000040,
+		0x057, 0x00050000,
+		0x056, 0x00051DF0,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x055, 0x00082061,
+	0xA0000000,	0x00000000,
+		0x055, 0x00082060,
+	0xB0000000,	0x00000000,
+		0x01C, 0x000739D2,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x01F, 0x0002255C,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x01F, 0x0002255C,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x01F, 0x0002255C,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x01F, 0x0002255C,
+	0xA0000000,	0x00000000,
+		0x01F, 0x0002255C,
+	0xB0000000,	0x00000000,
+		0x0B1, 0x0007FF48,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0C4, 0x00081700,
+	0xA0000000,	0x00000000,
+		0x0C4, 0x00083F00,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001B126,
+		0xFFE, 0x00000000,
+		0xFFE, 0x00000000,
+		0xFFE, 0x00000000,
+		0x018, 0x00013126,
+		0x018, 0x00013124,
+};
+
+RTW_DECL_TABLE_RF_RADIO(rtw8814a_rf_a, A);
+
+static const u32 rtw8814a_rf_b[] = {
+		0x018, 0x00013124,
+		0x040, 0x00000C00,
+		0x058, 0x00000F98,
+		0x07F, 0x00068004,
+		0x018, 0x00000006,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0xA0000000,	0x00000000,
+		0x086, 0x000E4B58,
+		0x087, 0x00049F80,
+	0xB0000000,	0x00000000,
+		0x0DF, 0x00000008,
+		0x0EF, 0x00002000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F39B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F39B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017BC3,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0003F258,
+		0x03B, 0x00030A58,
+		0x03B, 0x0002FA58,
+		0x03B, 0x00022590,
+		0x03B, 0x0001FA50,
+		0x03B, 0x00010248,
+		0x03B, 0x00008240,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000100,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000ADF6,
+		0x034, 0x00009DF3,
+		0x034, 0x00008DF0,
+		0x034, 0x00007DED,
+		0x034, 0x00006DEA,
+		0x034, 0x00005CED,
+		0x034, 0x00004CEA,
+		0x034, 0x000034EA,
+		0x034, 0x000024E7,
+		0x034, 0x0000146A,
+		0x034, 0x0000006B,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008ADF6,
+		0x034, 0x00089DF3,
+		0x034, 0x00088DF0,
+		0x034, 0x00087DED,
+		0x034, 0x00086DEA,
+		0x034, 0x00085CED,
+		0x034, 0x00084CEA,
+		0x034, 0x000834EA,
+		0x034, 0x000824E7,
+		0x034, 0x0008146A,
+		0x034, 0x0008006B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x000020A2,
+		0x0DF, 0x00000080,
+		0x035, 0x00000192,
+		0x035, 0x00008192,
+		0x035, 0x00010192,
+		0x036, 0x00000024,
+		0x036, 0x00008024,
+		0x036, 0x00010024,
+		0x036, 0x00018024,
+		0x0EF, 0x00000000,
+		0x051, 0x00000C21,
+		0x052, 0x000006D9,
+		0x053, 0x000FC649,
+		0x054, 0x0000017E,
+		0x018, 0x0001012A,
+		0x081, 0x0007FC00,
+		0x089, 0x00050110,
+		0x08A, 0x00043E50,
+		0x08B, 0x0002E180,
+		0x08C, 0x00093C3C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xA0000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xB0000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+		0x0EF, 0x00001000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00040000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00030023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00028623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00021633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0001C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00010293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00009593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x00000F8B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0000078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00070023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00068623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00061633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0005C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00050293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00049593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+		0x03B, 0x0004078B,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0004C000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0004C000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00004000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B0023,
+	0x80000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A8623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A1633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0009C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00090293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00089593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0008138B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0008078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00000800,
+		0x03B, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00000803,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00040000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000800,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000800,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001000,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00080000,
+	0x80000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001002,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x00013124,
+		0x0EF, 0x00000100,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x000491AD,
+		0x034, 0x000481AA,
+		0x034, 0x000471A7,
+		0x034, 0x000460AA,
+		0x034, 0x000450A7,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x0004200C,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x00049389,
+		0x034, 0x0004816D,
+		0x034, 0x0004716A,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38B,
+		0x034, 0x00049388,
+		0x034, 0x0004818B,
+		0x034, 0x00047188,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x00049389,
+		0x034, 0x0004816D,
+		0x034, 0x0004716A,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38B,
+		0x034, 0x00049388,
+		0x034, 0x0004818B,
+		0x034, 0x00047188,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3F5,
+		0x034, 0x000493F3,
+		0x034, 0x000483B2,
+		0x034, 0x00047390,
+		0x034, 0x0004638D,
+		0x034, 0x0004538A,
+		0x034, 0x00044387,
+		0x034, 0x0004324A,
+		0x034, 0x00042247,
+		0x034, 0x0004104D,
+		0x034, 0x0004004A,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004AFF7,
+		0x034, 0x00049FF6,
+		0x034, 0x00048FF3,
+		0x034, 0x00047FF0,
+		0x034, 0x00046FED,
+		0x034, 0x00045FEA,
+		0x034, 0x00044FE7,
+		0x034, 0x00043DEA,
+		0x034, 0x00042DE7,
+		0x034, 0x00041DE4,
+		0x034, 0x00040CE7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x00049389,
+		0x034, 0x0004816D,
+		0x034, 0x0004716A,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x00049389,
+		0x034, 0x0004816D,
+		0x034, 0x0004716A,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0xA0000000,	0x00000000,
+		0x034, 0x0004AFF4,
+		0x034, 0x00049FF1,
+		0x034, 0x00048FEE,
+		0x034, 0x00047FEB,
+		0x034, 0x00046FE8,
+		0x034, 0x00045DEA,
+		0x034, 0x00044CED,
+		0x034, 0x00043CEA,
+		0x034, 0x00042C6C,
+		0x034, 0x00041C69,
+		0x034, 0x00040C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A38C,
+		0x034, 0x000291AD,
+		0x034, 0x000281AA,
+		0x034, 0x000271A7,
+		0x034, 0x000260AA,
+		0x034, 0x000250A7,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x0002200C,
+		0x034, 0x00021009,
+		0x034, 0x00020006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EE,
+		0x034, 0x000293AC,
+		0x034, 0x00028389,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AD,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EE,
+		0x034, 0x000293AC,
+		0x034, 0x00028389,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EF,
+		0x034, 0x000293AD,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3F5,
+		0x034, 0x000293F3,
+		0x034, 0x000283D0,
+		0x034, 0x00027371,
+		0x034, 0x0002636E,
+		0x034, 0x0002536B,
+		0x034, 0x00024368,
+		0x034, 0x0002332A,
+		0x034, 0x00022327,
+		0x034, 0x0002104C,
+		0x034, 0x00020049,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002AFF7,
+		0x034, 0x00029FF6,
+		0x034, 0x00028FF3,
+		0x034, 0x00027FF0,
+		0x034, 0x00026FED,
+		0x034, 0x00025FEA,
+		0x034, 0x00024FE7,
+		0x034, 0x00023DEA,
+		0x034, 0x00022DE7,
+		0x034, 0x00021DE4,
+		0x034, 0x00020F25,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EE,
+		0x034, 0x000293AC,
+		0x034, 0x00028389,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EE,
+		0x034, 0x000293AC,
+		0x034, 0x00028389,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0002AFF4,
+		0x034, 0x00029FF1,
+		0x034, 0x00028FEE,
+		0x034, 0x00027FEB,
+		0x034, 0x00026FE8,
+		0x034, 0x00025DEA,
+		0x034, 0x00024CED,
+		0x034, 0x00023CEA,
+		0x034, 0x00022C6C,
+		0x034, 0x00021C69,
+		0x034, 0x00020C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A38C,
+		0x034, 0x000091AD,
+		0x034, 0x000081AA,
+		0x034, 0x000071A7,
+		0x034, 0x000060AA,
+		0x034, 0x000050A7,
+		0x034, 0x0000402C,
+		0x034, 0x00003029,
+		0x034, 0x00002026,
+		0x034, 0x00001009,
+		0x034, 0x00000006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EC,
+		0x034, 0x000093AC,
+		0x034, 0x000081EC,
+		0x034, 0x0000716D,
+		0x034, 0x0000616A,
+		0x034, 0x0000506D,
+		0x034, 0x0000404C,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EF,
+		0x034, 0x000093AD,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EC,
+		0x034, 0x000093AC,
+		0x034, 0x000081EC,
+		0x034, 0x0000716D,
+		0x034, 0x0000616A,
+		0x034, 0x0000506D,
+		0x034, 0x0000404C,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EF,
+		0x034, 0x000093AD,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3F4,
+		0x034, 0x000093F0,
+		0x034, 0x000083AE,
+		0x034, 0x00007350,
+		0x034, 0x0000634D,
+		0x034, 0x0000534A,
+		0x034, 0x00004347,
+		0x034, 0x0000312D,
+		0x034, 0x0000212A,
+		0x034, 0x00001127,
+		0x034, 0x0000002A,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000AFF7,
+		0x034, 0x00009FF4,
+		0x034, 0x00008FF1,
+		0x034, 0x00007FEE,
+		0x034, 0x00006FEB,
+		0x034, 0x00005FE8,
+		0x034, 0x00004DEB,
+		0x034, 0x00003DE8,
+		0x034, 0x00002DE5,
+		0x034, 0x00001C8B,
+		0x034, 0x00000C88,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EC,
+		0x034, 0x000093AC,
+		0x034, 0x000081EC,
+		0x034, 0x0000716D,
+		0x034, 0x0000616A,
+		0x034, 0x0000506D,
+		0x034, 0x0000404C,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EC,
+		0x034, 0x000093AC,
+		0x034, 0x000081EC,
+		0x034, 0x0000716D,
+		0x034, 0x0000616A,
+		0x034, 0x0000506D,
+		0x034, 0x0000404C,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000AFF4,
+		0x034, 0x00009FF1,
+		0x034, 0x00008FEE,
+		0x034, 0x00007FEB,
+		0x034, 0x00006FE8,
+		0x034, 0x00005DEA,
+		0x034, 0x00004CED,
+		0x034, 0x00003CEA,
+		0x034, 0x00002C6C,
+		0x034, 0x00001C69,
+		0x034, 0x00000C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C91AD,
+		0x034, 0x000C81AA,
+		0x034, 0x000C71A7,
+		0x034, 0x000C60AA,
+		0x034, 0x000C50A7,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C200C,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C9389,
+		0x034, 0x000C816D,
+		0x034, 0x000C716A,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38B,
+		0x034, 0x000C9388,
+		0x034, 0x000C818B,
+		0x034, 0x000C7188,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C9389,
+		0x034, 0x000C816D,
+		0x034, 0x000C716A,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38B,
+		0x034, 0x000C9388,
+		0x034, 0x000C818B,
+		0x034, 0x000C7188,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3F5,
+		0x034, 0x000C93F3,
+		0x034, 0x000C83B2,
+		0x034, 0x000C7390,
+		0x034, 0x000C638D,
+		0x034, 0x000C538A,
+		0x034, 0x000C4387,
+		0x034, 0x000C324A,
+		0x034, 0x000C2247,
+		0x034, 0x000C104D,
+		0x034, 0x000C004A,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CAFF7,
+		0x034, 0x000C9FF6,
+		0x034, 0x000C8FF3,
+		0x034, 0x000C7FF0,
+		0x034, 0x000C6FED,
+		0x034, 0x000C5FEA,
+		0x034, 0x000C4FE7,
+		0x034, 0x000C3DEA,
+		0x034, 0x000C2DE7,
+		0x034, 0x000C1DE4,
+		0x034, 0x000C0CE7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C9389,
+		0x034, 0x000C816D,
+		0x034, 0x000C716A,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C9389,
+		0x034, 0x000C816D,
+		0x034, 0x000C716A,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0xA0000000,	0x00000000,
+		0x034, 0x000CA794,
+		0x034, 0x000C9791,
+		0x034, 0x000C878E,
+		0x034, 0x000C778B,
+		0x034, 0x000C658D,
+		0x034, 0x000C558A,
+		0x034, 0x000C448D,
+		0x034, 0x000C348A,
+		0x034, 0x000C244C,
+		0x034, 0x000C1449,
+		0x034, 0x000C042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA38C,
+		0x034, 0x000A91AD,
+		0x034, 0x000A81AA,
+		0x034, 0x000A71A7,
+		0x034, 0x000A60AA,
+		0x034, 0x000A50A7,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A200C,
+		0x034, 0x000A1009,
+		0x034, 0x000A0006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EE,
+		0x034, 0x000A93AC,
+		0x034, 0x000A8389,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AD,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EE,
+		0x034, 0x000A93AC,
+		0x034, 0x000A8389,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EF,
+		0x034, 0x000A93AD,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3F5,
+		0x034, 0x000A93F3,
+		0x034, 0x000A83D0,
+		0x034, 0x000A7371,
+		0x034, 0x000A636E,
+		0x034, 0x000A536B,
+		0x034, 0x000A4368,
+		0x034, 0x000A332A,
+		0x034, 0x000A2327,
+		0x034, 0x000A104C,
+		0x034, 0x000A0049,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AAFF7,
+		0x034, 0x000A9FF6,
+		0x034, 0x000A8FF3,
+		0x034, 0x000A7FF0,
+		0x034, 0x000A6FED,
+		0x034, 0x000A5FEA,
+		0x034, 0x000A4FE7,
+		0x034, 0x000A3DEA,
+		0x034, 0x000A2DE7,
+		0x034, 0x000A1DE4,
+		0x034, 0x000A0F25,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EE,
+		0x034, 0x000A93AC,
+		0x034, 0x000A8389,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EE,
+		0x034, 0x000A93AC,
+		0x034, 0x000A8389,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0xA0000000,	0x00000000,
+		0x034, 0x000AA794,
+		0x034, 0x000A9791,
+		0x034, 0x000A878E,
+		0x034, 0x000A778B,
+		0x034, 0x000A658D,
+		0x034, 0x000A558A,
+		0x034, 0x000A448D,
+		0x034, 0x000A348A,
+		0x034, 0x000A244C,
+		0x034, 0x000A1449,
+		0x034, 0x000A042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A38C,
+		0x034, 0x000891AD,
+		0x034, 0x000881AA,
+		0x034, 0x000871A7,
+		0x034, 0x000860AA,
+		0x034, 0x000850A7,
+		0x034, 0x0008402C,
+		0x034, 0x00083029,
+		0x034, 0x00082026,
+		0x034, 0x00081009,
+		0x034, 0x00080006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EC,
+		0x034, 0x000893AC,
+		0x034, 0x000881EC,
+		0x034, 0x0008716D,
+		0x034, 0x0008616A,
+		0x034, 0x0008506D,
+		0x034, 0x0008404C,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EF,
+		0x034, 0x000893AD,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EC,
+		0x034, 0x000893AC,
+		0x034, 0x000881EC,
+		0x034, 0x0008716D,
+		0x034, 0x0008616A,
+		0x034, 0x0008506D,
+		0x034, 0x0008404C,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EF,
+		0x034, 0x000893AD,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3F4,
+		0x034, 0x000893F0,
+		0x034, 0x000883AE,
+		0x034, 0x00087350,
+		0x034, 0x0008634D,
+		0x034, 0x0008534A,
+		0x034, 0x00084347,
+		0x034, 0x0008312D,
+		0x034, 0x0008212A,
+		0x034, 0x00081127,
+		0x034, 0x0008002A,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008AFF7,
+		0x034, 0x00089FF4,
+		0x034, 0x00088FF1,
+		0x034, 0x00087FEE,
+		0x034, 0x00086FEB,
+		0x034, 0x00085FE8,
+		0x034, 0x00084DEB,
+		0x034, 0x00083DE8,
+		0x034, 0x00082DE5,
+		0x034, 0x00081C8B,
+		0x034, 0x00080C88,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EC,
+		0x034, 0x000893AC,
+		0x034, 0x000881EC,
+		0x034, 0x0008716D,
+		0x034, 0x0008616A,
+		0x034, 0x0008506D,
+		0x034, 0x0008404C,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EC,
+		0x034, 0x000893AC,
+		0x034, 0x000881EC,
+		0x034, 0x0008716D,
+		0x034, 0x0008616A,
+		0x034, 0x0008506D,
+		0x034, 0x0008404C,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008A794,
+		0x034, 0x00089791,
+		0x034, 0x0008878E,
+		0x034, 0x0008778B,
+		0x034, 0x0008658D,
+		0x034, 0x0008558A,
+		0x034, 0x0008448D,
+		0x034, 0x0008348A,
+		0x034, 0x0008244C,
+		0x034, 0x00081449,
+		0x034, 0x0008042B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000040,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0xA0000000,	0x00000000,
+		0x035, 0x00000484,
+		0x035, 0x00008484,
+		0x035, 0x00010484,
+		0x035, 0x00020584,
+		0x035, 0x00028584,
+		0x035, 0x00030584,
+		0x035, 0x00040584,
+		0x035, 0x00048584,
+		0x035, 0x00050584,
+		0x035, 0x000805FB,
+		0x035, 0x000885FB,
+		0x035, 0x000905FB,
+		0x035, 0x000A05FB,
+		0x035, 0x000A85FB,
+		0x035, 0x000B05FB,
+		0x035, 0x000C05FB,
+		0x035, 0x000C85FB,
+		0x035, 0x000D05FB,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000010,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000473,
+		0x036, 0x00008473,
+		0x036, 0x00010473,
+		0x036, 0x00020473,
+		0x036, 0x00028473,
+		0x036, 0x00030473,
+		0x036, 0x00040473,
+		0x036, 0x00048473,
+		0x036, 0x00050473,
+		0x036, 0x00080473,
+		0x036, 0x00088473,
+		0x036, 0x00090473,
+		0x036, 0x000A0473,
+		0x036, 0x000A8473,
+		0x036, 0x000B0473,
+		0x036, 0x000C0473,
+		0x036, 0x000C8473,
+		0x036, 0x000D0473,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0xA0000000,	0x00000000,
+		0x036, 0x00000474,
+		0x036, 0x00008474,
+		0x036, 0x00010474,
+		0x036, 0x00020474,
+		0x036, 0x00028474,
+		0x036, 0x00030474,
+		0x036, 0x00040474,
+		0x036, 0x00048474,
+		0x036, 0x00050474,
+		0x036, 0x00080474,
+		0x036, 0x00088474,
+		0x036, 0x00090474,
+		0x036, 0x000A0474,
+		0x036, 0x000A8474,
+		0x036, 0x000B0474,
+		0x036, 0x000C0474,
+		0x036, 0x000C8474,
+		0x036, 0x000D0474,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x0EF, 0x00000004,
+		0x037, 0x00000000,
+		0x038, 0x0000514E,
+		0x037, 0x00004000,
+		0x038, 0x0000514E,
+		0x037, 0x00008000,
+		0x038, 0x0000514E,
+		0x037, 0x00010000,
+		0x038, 0x0000514E,
+		0x037, 0x00014000,
+		0x038, 0x0000514E,
+		0x037, 0x00018000,
+		0x038, 0x0000514E,
+		0x037, 0x0001C000,
+		0x038, 0x0000514E,
+		0x037, 0x00020000,
+		0x038, 0x0000514E,
+		0x037, 0x00024000,
+		0x038, 0x0000514E,
+		0x037, 0x00028000,
+		0x038, 0x0000514E,
+		0x037, 0x0002C000,
+		0x038, 0x0000714E,
+		0x037, 0x00030000,
+		0x038, 0x0000514E,
+		0x037, 0x00034000,
+		0x038, 0x0000514E,
+		0x037, 0x00038000,
+		0x038, 0x0000514E,
+		0x037, 0x0003C000,
+		0x038, 0x0000514E,
+		0x037, 0x00040000,
+		0x038, 0x0000514E,
+		0x037, 0x00044000,
+		0x038, 0x0000514E,
+		0x037, 0x00048000,
+		0x038, 0x0000514E,
+		0x037, 0x00080000,
+		0x038, 0x00005ECE,
+		0x037, 0x00084000,
+		0x038, 0x00005ECE,
+		0x037, 0x00088000,
+		0x038, 0x00005ECE,
+		0x037, 0x00090000,
+		0x038, 0x00005ECE,
+		0x037, 0x00094000,
+		0x038, 0x00005ECE,
+		0x037, 0x00098000,
+		0x038, 0x00005ECE,
+		0x037, 0x0009C000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000AC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000BC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C8000,
+		0x038, 0x00005ECE,
+		0x0EF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000008,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000007D,
+		0x03C, 0x0000047D,
+		0x03C, 0x0000087D,
+		0x03C, 0x0000107D,
+		0x03C, 0x0000147D,
+		0x03C, 0x0000187D,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027E,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227E,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000037E,
+		0x03C, 0x00000575,
+		0x03C, 0x00000971,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001575,
+		0x03C, 0x00001871,
+		0x03C, 0x0000217E,
+		0x03C, 0x00002575,
+		0x03C, 0x00002871,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x061, 0x000C0D47,
+		0x062, 0x0000133C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0xA0000000,	0x00000000,
+		0x063, 0x0007D0E7,
+	0xB0000000,	0x00000000,
+		0x064, 0x00014FEC,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0xA0000000,	0x00000000,
+		0x065, 0x000923FF,
+	0xB0000000,	0x00000000,
+		0x066, 0x00000040,
+		0x057, 0x00050000,
+		0x056, 0x00051DF0,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x055, 0x00082060,
+	0xB0000000,	0x00000000,
+};
+
+RTW_DECL_TABLE_RF_RADIO(rtw8814a_rf_b, B);
+
+static const u32 rtw8814a_rf_c[] = {
+		0x018, 0x00013124,
+		0x040, 0x00000C00,
+		0x058, 0x00000F98,
+		0x07F, 0x00068004,
+		0x018, 0x00000006,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0xA0000000,	0x00000000,
+		0x086, 0x000E4B58,
+		0x087, 0x00049F80,
+	0xB0000000,	0x00000000,
+		0x0DF, 0x00000008,
+		0x0EF, 0x00002000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017823,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0003F258,
+		0x03B, 0x00030A58,
+		0x03B, 0x0002FA58,
+		0x03B, 0x00022590,
+		0x03B, 0x0001FA50,
+		0x03B, 0x00010248,
+		0x03B, 0x00008240,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000100,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000ADF6,
+		0x034, 0x00009DF3,
+		0x034, 0x00008DF0,
+		0x034, 0x00007DED,
+		0x034, 0x00006DEA,
+		0x034, 0x00005CED,
+		0x034, 0x00004CEA,
+		0x034, 0x000034EA,
+		0x034, 0x000024E7,
+		0x034, 0x0000146A,
+		0x034, 0x0000006B,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008ADF6,
+		0x034, 0x00089DF3,
+		0x034, 0x00088DF0,
+		0x034, 0x00087DED,
+		0x034, 0x00086DEA,
+		0x034, 0x00085CED,
+		0x034, 0x00084CEA,
+		0x034, 0x000834EA,
+		0x034, 0x000824E7,
+		0x034, 0x0008146A,
+		0x034, 0x0008006B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x000020A2,
+		0x0DF, 0x00000080,
+		0x035, 0x00000192,
+		0x035, 0x00008192,
+		0x035, 0x00010192,
+		0x036, 0x00000024,
+		0x036, 0x00008024,
+		0x036, 0x00010024,
+		0x036, 0x00018024,
+		0x0EF, 0x00000000,
+		0x051, 0x00000C21,
+		0x052, 0x000006D9,
+		0x053, 0x000FC649,
+		0x054, 0x0000017E,
+		0x018, 0x0001012A,
+		0x081, 0x0007FC00,
+		0x089, 0x00050110,
+		0x08A, 0x00043E50,
+		0x08B, 0x0002E180,
+		0x08C, 0x00093C3C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xA0000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xA0000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00001000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0006C000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x000D4000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00080000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0006C000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0008C000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00004000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x000A0000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00030023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00028623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00021633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0001C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00010293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00009593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0000118B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0000078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0004C000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00084000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00080000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0004C000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x000D0000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00080000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00080000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00028000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00070023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00068623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00061633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0005C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00050293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00049593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+		0x03B, 0x0004078B,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00080000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B0023,
+	0x80000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A8623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A1633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0009C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00090293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00089593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0008128B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0008078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00000800,
+		0x03B, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001803,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001803,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00000803,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00040000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000800,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001000,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00080000,
+	0x80000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001002,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x018, 0x00013124,
+	0xA0000000,	0x00000000,
+		0x018, 0x00013124,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000100,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A38C,
+		0x034, 0x000491AD,
+		0x034, 0x000481AA,
+		0x034, 0x000471A7,
+		0x034, 0x000460AA,
+		0x034, 0x000450A7,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x0004200C,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3F5,
+		0x034, 0x000493F3,
+		0x034, 0x00048393,
+		0x034, 0x00047390,
+		0x034, 0x0004638D,
+		0x034, 0x0004538A,
+		0x034, 0x00044387,
+		0x034, 0x000430ED,
+		0x034, 0x000420EA,
+		0x034, 0x000410E7,
+		0x034, 0x0004002D,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004AFF7,
+		0x034, 0x00049FF6,
+		0x034, 0x00048FF3,
+		0x034, 0x00047FF0,
+		0x034, 0x00046FED,
+		0x034, 0x00045FEA,
+		0x034, 0x00044FE7,
+		0x034, 0x00043CD0,
+		0x034, 0x00042CCD,
+		0x034, 0x00041CCA,
+		0x034, 0x00040CC7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EF,
+		0x034, 0x000493AD,
+		0x034, 0x0004838A,
+		0x034, 0x0004718C,
+		0x034, 0x00046189,
+		0x034, 0x0004506D,
+		0x034, 0x0004404C,
+		0x034, 0x0004302C,
+		0x034, 0x00042029,
+		0x034, 0x00041026,
+		0x034, 0x00040023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0004AFF4,
+		0x034, 0x00049FF1,
+		0x034, 0x00048FEE,
+		0x034, 0x00047FEB,
+		0x034, 0x00046FE8,
+		0x034, 0x00045DEA,
+		0x034, 0x00044CED,
+		0x034, 0x00043CEA,
+		0x034, 0x00042C6C,
+		0x034, 0x00041C69,
+		0x034, 0x00040C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x0002938C,
+		0x034, 0x000281AD,
+		0x034, 0x000271AA,
+		0x034, 0x000261A7,
+		0x034, 0x000250AA,
+		0x034, 0x000240A7,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x0002100C,
+		0x034, 0x00020009,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x0002936D,
+		0x034, 0x0002836A,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x0002936D,
+		0x034, 0x0002836A,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x000293AC,
+		0x034, 0x0002838A,
+		0x034, 0x0002718C,
+		0x034, 0x00026189,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3F5,
+		0x034, 0x000293F3,
+		0x034, 0x000282F2,
+		0x034, 0x000272D0,
+		0x034, 0x000262CD,
+		0x034, 0x000252CA,
+		0x034, 0x000242C7,
+		0x034, 0x000230CD,
+		0x034, 0x000220CA,
+		0x034, 0x000210C7,
+		0x034, 0x00020086,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002AFF7,
+		0x034, 0x00029FF6,
+		0x034, 0x00028FF3,
+		0x034, 0x00027FF0,
+		0x034, 0x00026FED,
+		0x034, 0x00025FEA,
+		0x034, 0x00024FE7,
+		0x034, 0x00023DEA,
+		0x034, 0x00022DE7,
+		0x034, 0x00021DE4,
+		0x034, 0x00020E44,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x0002936D,
+		0x034, 0x0002836A,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EC,
+		0x034, 0x0002936D,
+		0x034, 0x0002836A,
+		0x034, 0x0002716D,
+		0x034, 0x0002616A,
+		0x034, 0x0002506D,
+		0x034, 0x0002406A,
+		0x034, 0x0002302C,
+		0x034, 0x00022029,
+		0x034, 0x00021026,
+		0x034, 0x00020023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0002AFF4,
+		0x034, 0x00029FF1,
+		0x034, 0x00028FEE,
+		0x034, 0x00027FEB,
+		0x034, 0x00026FE8,
+		0x034, 0x00025DEA,
+		0x034, 0x00024CED,
+		0x034, 0x00023CEA,
+		0x034, 0x00022C6C,
+		0x034, 0x00021C69,
+		0x034, 0x00020C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A38C,
+		0x034, 0x000091AD,
+		0x034, 0x000081AA,
+		0x034, 0x000071A7,
+		0x034, 0x000060AA,
+		0x034, 0x000050A7,
+		0x034, 0x0000402C,
+		0x034, 0x00003029,
+		0x034, 0x0000200C,
+		0x034, 0x00001009,
+		0x034, 0x00000006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3F5,
+		0x034, 0x000093F1,
+		0x034, 0x000083B0,
+		0x034, 0x00007370,
+		0x034, 0x0000636D,
+		0x034, 0x0000536A,
+		0x034, 0x00004367,
+		0x034, 0x0000308E,
+		0x034, 0x0000208B,
+		0x034, 0x00001088,
+		0x034, 0x00000085,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000AFF7,
+		0x034, 0x00009FF5,
+		0x034, 0x00008FF2,
+		0x034, 0x00007FEF,
+		0x034, 0x00006FEC,
+		0x034, 0x00005FE9,
+		0x034, 0x00004EAA,
+		0x034, 0x00003EA7,
+		0x034, 0x00002C70,
+		0x034, 0x00001C6D,
+		0x034, 0x00000C6A,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AB,
+		0x034, 0x00008389,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000AFF4,
+		0x034, 0x00009FF1,
+		0x034, 0x00008FEE,
+		0x034, 0x00007FEB,
+		0x034, 0x00006FE8,
+		0x034, 0x00005DEA,
+		0x034, 0x00004CED,
+		0x034, 0x00003CEA,
+		0x034, 0x00002C6C,
+		0x034, 0x00001C69,
+		0x034, 0x00000C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA38C,
+		0x034, 0x000C91AD,
+		0x034, 0x000C81AA,
+		0x034, 0x000C71A7,
+		0x034, 0x000C60AA,
+		0x034, 0x000C50A7,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C200C,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3F5,
+		0x034, 0x000C93F3,
+		0x034, 0x000C8393,
+		0x034, 0x000C7390,
+		0x034, 0x000C638D,
+		0x034, 0x000C538A,
+		0x034, 0x000C4387,
+		0x034, 0x000C30ED,
+		0x034, 0x000C20EA,
+		0x034, 0x000C10E7,
+		0x034, 0x000C002D,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CAFF7,
+		0x034, 0x000C9FF6,
+		0x034, 0x000C8FF3,
+		0x034, 0x000C7FF0,
+		0x034, 0x000C6FED,
+		0x034, 0x000C5FEA,
+		0x034, 0x000C4FE7,
+		0x034, 0x000C3CD0,
+		0x034, 0x000C2CCD,
+		0x034, 0x000C1CCA,
+		0x034, 0x000C0CC7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EF,
+		0x034, 0x000C93AD,
+		0x034, 0x000C838A,
+		0x034, 0x000C718C,
+		0x034, 0x000C6189,
+		0x034, 0x000C506D,
+		0x034, 0x000C404C,
+		0x034, 0x000C302C,
+		0x034, 0x000C2029,
+		0x034, 0x000C1026,
+		0x034, 0x000C0023,
+	0xA0000000,	0x00000000,
+		0x034, 0x000CA794,
+		0x034, 0x000C9791,
+		0x034, 0x000C878E,
+		0x034, 0x000C778B,
+		0x034, 0x000C658D,
+		0x034, 0x000C558A,
+		0x034, 0x000C448D,
+		0x034, 0x000C348A,
+		0x034, 0x000C244C,
+		0x034, 0x000C1449,
+		0x034, 0x000C042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A938C,
+		0x034, 0x000A81AD,
+		0x034, 0x000A71AA,
+		0x034, 0x000A61A7,
+		0x034, 0x000A50AA,
+		0x034, 0x000A40A7,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A100C,
+		0x034, 0x000A0009,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A936D,
+		0x034, 0x000A836A,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A936D,
+		0x034, 0x000A836A,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A93AC,
+		0x034, 0x000A838A,
+		0x034, 0x000A718C,
+		0x034, 0x000A6189,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3F5,
+		0x034, 0x000A93F3,
+		0x034, 0x000A82F2,
+		0x034, 0x000A72D0,
+		0x034, 0x000A62CD,
+		0x034, 0x000A52CA,
+		0x034, 0x000A42C7,
+		0x034, 0x000A30CD,
+		0x034, 0x000A20CA,
+		0x034, 0x000A10C7,
+		0x034, 0x000A0086,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AAFF7,
+		0x034, 0x000A9FF6,
+		0x034, 0x000A8FF3,
+		0x034, 0x000A7FF0,
+		0x034, 0x000A6FED,
+		0x034, 0x000A5FEA,
+		0x034, 0x000A4FE7,
+		0x034, 0x000A3DEA,
+		0x034, 0x000A2DE7,
+		0x034, 0x000A1DE4,
+		0x034, 0x000A0E44,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A936D,
+		0x034, 0x000A836A,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EC,
+		0x034, 0x000A936D,
+		0x034, 0x000A836A,
+		0x034, 0x000A716D,
+		0x034, 0x000A616A,
+		0x034, 0x000A506D,
+		0x034, 0x000A406A,
+		0x034, 0x000A302C,
+		0x034, 0x000A2029,
+		0x034, 0x000A1026,
+		0x034, 0x000A0023,
+	0xA0000000,	0x00000000,
+		0x034, 0x000AA794,
+		0x034, 0x000A9791,
+		0x034, 0x000A878E,
+		0x034, 0x000A778B,
+		0x034, 0x000A658D,
+		0x034, 0x000A558A,
+		0x034, 0x000A448D,
+		0x034, 0x000A348A,
+		0x034, 0x000A244C,
+		0x034, 0x000A1449,
+		0x034, 0x000A042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A38C,
+		0x034, 0x000891AD,
+		0x034, 0x000881AA,
+		0x034, 0x000871A7,
+		0x034, 0x000860AA,
+		0x034, 0x000850A7,
+		0x034, 0x0008402C,
+		0x034, 0x00083029,
+		0x034, 0x0008200C,
+		0x034, 0x00081009,
+		0x034, 0x00000006,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3F5,
+		0x034, 0x000893F1,
+		0x034, 0x000883B0,
+		0x034, 0x00087370,
+		0x034, 0x0008636D,
+		0x034, 0x0008536A,
+		0x034, 0x00084367,
+		0x034, 0x0008308E,
+		0x034, 0x0008208B,
+		0x034, 0x00081088,
+		0x034, 0x00080085,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008AFF7,
+		0x034, 0x00089FF5,
+		0x034, 0x00088FF2,
+		0x034, 0x00087FEF,
+		0x034, 0x00086FEC,
+		0x034, 0x00085FE9,
+		0x034, 0x00084EAA,
+		0x034, 0x00083EA7,
+		0x034, 0x00082C70,
+		0x034, 0x00081C6D,
+		0x034, 0x00080C6A,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AB,
+		0x034, 0x00088389,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008A794,
+		0x034, 0x00089791,
+		0x034, 0x0008878E,
+		0x034, 0x0008778B,
+		0x034, 0x0008658D,
+		0x034, 0x0008558A,
+		0x034, 0x0008448D,
+		0x034, 0x0008348A,
+		0x034, 0x0008244C,
+		0x034, 0x00081449,
+		0x034, 0x0008042B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000040,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0xA0000000,	0x00000000,
+		0x035, 0x00000484,
+		0x035, 0x00008484,
+		0x035, 0x00010484,
+		0x035, 0x00020584,
+		0x035, 0x00028584,
+		0x035, 0x00030584,
+		0x035, 0x00040584,
+		0x035, 0x00048584,
+		0x035, 0x00050584,
+		0x035, 0x000805FB,
+		0x035, 0x000885FB,
+		0x035, 0x000905FB,
+		0x035, 0x000A05FB,
+		0x035, 0x000A85FB,
+		0x035, 0x000B05FB,
+		0x035, 0x000C05FB,
+		0x035, 0x000C85FB,
+		0x035, 0x000D05FB,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000010,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000473,
+		0x036, 0x00008473,
+		0x036, 0x00010473,
+		0x036, 0x00020473,
+		0x036, 0x00028473,
+		0x036, 0x00030473,
+		0x036, 0x00040473,
+		0x036, 0x00048473,
+		0x036, 0x00050473,
+		0x036, 0x00080473,
+		0x036, 0x00088473,
+		0x036, 0x00090473,
+		0x036, 0x000A0473,
+		0x036, 0x000A8473,
+		0x036, 0x000B0473,
+		0x036, 0x000C0473,
+		0x036, 0x000C8473,
+		0x036, 0x000D0473,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0xA0000000,	0x00000000,
+		0x036, 0x00000474,
+		0x036, 0x00008474,
+		0x036, 0x00010474,
+		0x036, 0x00020474,
+		0x036, 0x00028474,
+		0x036, 0x00030474,
+		0x036, 0x00040474,
+		0x036, 0x00048474,
+		0x036, 0x00050474,
+		0x036, 0x00080474,
+		0x036, 0x00088474,
+		0x036, 0x00090474,
+		0x036, 0x000A0474,
+		0x036, 0x000A8474,
+		0x036, 0x000B0474,
+		0x036, 0x000C0474,
+		0x036, 0x000C8474,
+		0x036, 0x000D0474,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x0EF, 0x00000004,
+		0x037, 0x00000000,
+		0x038, 0x0000514E,
+		0x037, 0x00004000,
+		0x038, 0x0000514E,
+		0x037, 0x00008000,
+		0x038, 0x0000514E,
+		0x037, 0x00010000,
+		0x038, 0x0000514E,
+		0x037, 0x00014000,
+		0x038, 0x0000514E,
+		0x037, 0x00018000,
+		0x038, 0x0000514E,
+		0x037, 0x0001C000,
+		0x038, 0x0000514E,
+		0x037, 0x00020000,
+		0x038, 0x0000514E,
+		0x037, 0x00024000,
+		0x038, 0x0000514E,
+		0x037, 0x00028000,
+		0x038, 0x0000514E,
+		0x037, 0x0002C000,
+		0x038, 0x0000714E,
+		0x037, 0x00030000,
+		0x038, 0x0000514E,
+		0x037, 0x00034000,
+		0x038, 0x0000514E,
+		0x037, 0x00038000,
+		0x038, 0x0000514E,
+		0x037, 0x0003C000,
+		0x038, 0x0000514E,
+		0x037, 0x00040000,
+		0x038, 0x0000514E,
+		0x037, 0x00044000,
+		0x038, 0x0000514E,
+		0x037, 0x00048000,
+		0x038, 0x0000514E,
+		0x037, 0x00080000,
+		0x038, 0x00005ECE,
+		0x037, 0x00084000,
+		0x038, 0x00005ECE,
+		0x037, 0x00088000,
+		0x038, 0x00005ECE,
+		0x037, 0x00090000,
+		0x038, 0x00005ECE,
+		0x037, 0x00094000,
+		0x038, 0x00005ECE,
+		0x037, 0x00098000,
+		0x038, 0x00005ECE,
+		0x037, 0x0009C000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000AC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000BC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C8000,
+		0x038, 0x00005ECE,
+		0x0EF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000008,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000007D,
+		0x03C, 0x0000047D,
+		0x03C, 0x0000087D,
+		0x03C, 0x0000107D,
+		0x03C, 0x0000147D,
+		0x03C, 0x0000187D,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000541,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001541,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002541,
+		0x03C, 0x00002821,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027D,
+		0x03C, 0x00000546,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127D,
+		0x03C, 0x00001546,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227D,
+		0x03C, 0x00002546,
+		0x03C, 0x00002821,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000037E,
+		0x03C, 0x00000575,
+		0x03C, 0x00000971,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001575,
+		0x03C, 0x00001871,
+		0x03C, 0x0000217E,
+		0x03C, 0x00002575,
+		0x03C, 0x00002871,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x061, 0x000C0D47,
+		0x062, 0x0000133C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0xA0000000,	0x00000000,
+		0x063, 0x0007D0E7,
+	0xB0000000,	0x00000000,
+		0x064, 0x00014FEC,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0xA0000000,	0x00000000,
+		0x065, 0x000923FF,
+	0xB0000000,	0x00000000,
+		0x066, 0x00000040,
+		0x057, 0x00050000,
+		0x056, 0x00051DF0,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x055, 0x00082060,
+	0xB0000000,	0x00000000,
+};
+
+RTW_DECL_TABLE_RF_RADIO(rtw8814a_rf_c, C);

From e38246889cc9f8497c8d7413b73856ae1634322d Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:24:02 +0200
Subject: [PATCH 2068/2753] wifi: rtw88: Add rtw8814a_table.c (part 2/2)

This contains various tables for initialising the RTL8814A, plus TX
power limits.

Also add rtw8814a_table.h.

Split into two patches because they are big.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/4c48e35e-1b04-42ed-940e-0e931693def6@gmail.com
---
 .../wireless/realtek/rtw88/rtw8814a_table.c   | 11379 ++++++++++++++++
 .../wireless/realtek/rtw88/rtw8814a_table.h   |    40 +
 2 files changed, 11419 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814a_table.h

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c
index 907cbd0321784..b9ce51a09fc85 100644
--- a/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.c
@@ -12549,3 +12549,11382 @@ static const u32 rtw8814a_rf_c[] = {
 };
 
 RTW_DECL_TABLE_RF_RADIO(rtw8814a_rf_c, C);
+
+static const u32 rtw8814a_rf_d[] = {
+		0x018, 0x00013124,
+		0x040, 0x00000C00,
+		0x058, 0x00000F98,
+		0x07F, 0x00068004,
+		0x018, 0x00000006,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x086, 0x000E335A,
+		0x087, 0x00079F80,
+	0xA0000000,	0x00000000,
+		0x086, 0x000E4B58,
+		0x087, 0x00049F80,
+	0xB0000000,	0x00000000,
+		0x0DF, 0x00000008,
+		0x0EF, 0x00002000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F09B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F09B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0003F19B,
+		0x03B, 0x00037A5B,
+		0x03B, 0x0002A433,
+		0x03B, 0x00027BD3,
+		0x03B, 0x0001F80B,
+		0x03B, 0x00017803,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0003F258,
+		0x03B, 0x00030A58,
+		0x03B, 0x0002FA58,
+		0x03B, 0x00022590,
+		0x03B, 0x0001FA50,
+		0x03B, 0x00010248,
+		0x03B, 0x00008240,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000100,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000ADF6,
+		0x034, 0x00009DF3,
+		0x034, 0x00008DF0,
+		0x034, 0x00007DED,
+		0x034, 0x00006DEA,
+		0x034, 0x00005CED,
+		0x034, 0x00004CEA,
+		0x034, 0x000034EA,
+		0x034, 0x000024E7,
+		0x034, 0x0000146A,
+		0x034, 0x0000006B,
+	0xB0000000,	0x00000000,
+	0x80000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A0D0,
+		0x034, 0x000090CD,
+		0x034, 0x000080CA,
+		0x034, 0x0000704D,
+		0x034, 0x0000604A,
+		0x034, 0x00005047,
+		0x034, 0x0000400A,
+		0x034, 0x00003007,
+		0x034, 0x00002004,
+		0x034, 0x00001001,
+		0x034, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008ADF6,
+		0x034, 0x00089DF3,
+		0x034, 0x00088DF0,
+		0x034, 0x00087DED,
+		0x034, 0x00086DEA,
+		0x034, 0x00085CED,
+		0x034, 0x00084CEA,
+		0x034, 0x000834EA,
+		0x034, 0x000824E7,
+		0x034, 0x0008146A,
+		0x034, 0x0008006B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x000020A2,
+		0x0DF, 0x00000080,
+		0x035, 0x00000192,
+		0x035, 0x00008192,
+		0x035, 0x00010192,
+		0x036, 0x00000024,
+		0x036, 0x00008024,
+		0x036, 0x00010024,
+		0x036, 0x00018024,
+		0x0EF, 0x00000000,
+		0x051, 0x00000C21,
+		0x052, 0x000006D9,
+		0x053, 0x000FC649,
+		0x054, 0x0000017E,
+		0x018, 0x0001012A,
+		0x081, 0x0007FC00,
+		0x089, 0x00050110,
+		0x08A, 0x00043E50,
+		0x08B, 0x0002E180,
+		0x08C, 0x00093C3C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xA0000000,	0x00000000,
+		0x085, 0x000F8000,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xA0000000,	0x00000000,
+		0x08D, 0x000FFFF0,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00001000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00038023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00048000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00040000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00088000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00048000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00030023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00028623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00021633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0001C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00010293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00009593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x00000F8B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0000078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00078023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00044000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00024000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00070023,
+		0x03C, 0x00048000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00068623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00061633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0005C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00050293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00049593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x00040F8B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0004078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xA0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B8023,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00004000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00004000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00060000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00024000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00004000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000B0023,
+	0x80000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x00020000,
+	0xB0000000,	0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A8623,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x000A1633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x0009C633,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00090293,
+		0x03C, 0x00000000,
+		0x03A, 0x0000013C,
+		0x03B, 0x00089593,
+		0x03C, 0x00000000,
+		0x03A, 0x00000148,
+	0x80000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03B, 0x0008138B,
+	0xA0000000,	0x00000000,
+		0x03B, 0x0008078B,
+	0xB0000000,	0x00000000,
+		0x03C, 0x00000000,
+		0x0EF, 0x00000000,
+		0x0EF, 0x00000800,
+		0x03B, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001003,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001803,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000803,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00000803,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00040000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001002,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000001,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000802,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001803,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001000,
+	0xB0000000,	0x00000000,
+		0x03B, 0x00080000,
+	0x80000007,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001802,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00001000,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x03A, 0x00000802,
+	0xA0000000,	0x00000000,
+		0x03A, 0x00001002,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000006,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x00013124,
+		0x0EF, 0x00000100,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3EB,
+		0x034, 0x0004938B,
+		0x034, 0x000481AC,
+		0x034, 0x000471A9,
+		0x034, 0x000460AC,
+		0x034, 0x000450A9,
+		0x034, 0x0004402E,
+		0x034, 0x0004302B,
+		0x034, 0x00042028,
+		0x034, 0x0004100B,
+		0x034, 0x00040008,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3F4,
+		0x034, 0x000493D2,
+		0x034, 0x000482D1,
+		0x034, 0x000471F1,
+		0x034, 0x000461EE,
+		0x034, 0x000451EB,
+		0x034, 0x000441E8,
+		0x034, 0x0004314B,
+		0x034, 0x00042148,
+		0x034, 0x0004104B,
+		0x034, 0x00040048,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004AFF7,
+		0x034, 0x00049FF6,
+		0x034, 0x00048FF3,
+		0x034, 0x00047FF0,
+		0x034, 0x00046FED,
+		0x034, 0x00045FEA,
+		0x034, 0x00044FE7,
+		0x034, 0x00043CB1,
+		0x034, 0x00042CAE,
+		0x034, 0x00041CAB,
+		0x034, 0x00040CA8,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0004A3AD,
+		0x034, 0x0004938A,
+		0x034, 0x0004818C,
+		0x034, 0x00047189,
+		0x034, 0x0004606D,
+		0x034, 0x0004506A,
+		0x034, 0x0004402C,
+		0x034, 0x00043029,
+		0x034, 0x00042026,
+		0x034, 0x00041009,
+		0x034, 0x00040006,
+	0xA0000000,	0x00000000,
+		0x034, 0x0004AFF4,
+		0x034, 0x00049FF1,
+		0x034, 0x00048FEE,
+		0x034, 0x00047FEB,
+		0x034, 0x00046FE8,
+		0x034, 0x00045DEA,
+		0x034, 0x00044CED,
+		0x034, 0x00043CEA,
+		0x034, 0x00042C6C,
+		0x034, 0x00041C69,
+		0x034, 0x00040C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3EE,
+		0x034, 0x000293EB,
+		0x034, 0x0002838B,
+		0x034, 0x000271AC,
+		0x034, 0x000261A9,
+		0x034, 0x000250AC,
+		0x034, 0x000240A9,
+		0x034, 0x000230A6,
+		0x034, 0x0002202C,
+		0x034, 0x00021029,
+		0x034, 0x00020026,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3F5,
+		0x034, 0x000293D2,
+		0x034, 0x000283CE,
+		0x034, 0x00027290,
+		0x034, 0x0002628D,
+		0x034, 0x0002528A,
+		0x034, 0x00024287,
+		0x034, 0x0002308D,
+		0x034, 0x0002208A,
+		0x034, 0x00021087,
+		0x034, 0x00020048,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002AFF7,
+		0x034, 0x00029FF6,
+		0x034, 0x00028FF3,
+		0x034, 0x00027FF0,
+		0x034, 0x00026FED,
+		0x034, 0x00025FEA,
+		0x034, 0x00024FE7,
+		0x034, 0x00023DEA,
+		0x034, 0x00022DE7,
+		0x034, 0x00021DE4,
+		0x034, 0x00020D48,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0002A3AD,
+		0x034, 0x0002938A,
+		0x034, 0x0002818C,
+		0x034, 0x00027189,
+		0x034, 0x0002606D,
+		0x034, 0x0002504C,
+		0x034, 0x0002402C,
+		0x034, 0x00023029,
+		0x034, 0x00022026,
+		0x034, 0x00021023,
+		0x034, 0x00020006,
+	0xA0000000,	0x00000000,
+		0x034, 0x0002AFF4,
+		0x034, 0x00029FF1,
+		0x034, 0x00028FEE,
+		0x034, 0x00027FEB,
+		0x034, 0x00026FE8,
+		0x034, 0x00025DEA,
+		0x034, 0x00024CED,
+		0x034, 0x00023CEA,
+		0x034, 0x00022C6C,
+		0x034, 0x00021C69,
+		0x034, 0x00020C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EF,
+		0x034, 0x000093EC,
+		0x034, 0x0000838C,
+		0x034, 0x000071AD,
+		0x034, 0x000061AA,
+		0x034, 0x000050AD,
+		0x034, 0x000040AA,
+		0x034, 0x0000306A,
+		0x034, 0x0000202D,
+		0x034, 0x0000102A,
+		0x034, 0x00000027,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3F1,
+		0x034, 0x000092B1,
+		0x034, 0x000081CF,
+		0x034, 0x00007170,
+		0x034, 0x0000616D,
+		0x034, 0x0000516A,
+		0x034, 0x00004167,
+		0x034, 0x0000302F,
+		0x034, 0x0000202C,
+		0x034, 0x00001029,
+		0x034, 0x00000026,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000AFF7,
+		0x034, 0x00009FF6,
+		0x034, 0x00008FF3,
+		0x034, 0x00007FF0,
+		0x034, 0x00006FED,
+		0x034, 0x00005FEA,
+		0x034, 0x00004FE7,
+		0x034, 0x00003EC7,
+		0x034, 0x00002EC4,
+		0x034, 0x00001D4B,
+		0x034, 0x00000D48,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0000A3EE,
+		0x034, 0x000093AC,
+		0x034, 0x0000838A,
+		0x034, 0x0000718C,
+		0x034, 0x00006189,
+		0x034, 0x0000506D,
+		0x034, 0x0000406A,
+		0x034, 0x0000302C,
+		0x034, 0x00002029,
+		0x034, 0x00001026,
+		0x034, 0x00000023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0000AFF4,
+		0x034, 0x00009FF1,
+		0x034, 0x00008FEE,
+		0x034, 0x00007FEB,
+		0x034, 0x00006FE8,
+		0x034, 0x00005DEA,
+		0x034, 0x00004CED,
+		0x034, 0x00003CEA,
+		0x034, 0x00002C6C,
+		0x034, 0x00001C69,
+		0x034, 0x00000C2B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3EB,
+		0x034, 0x000C938B,
+		0x034, 0x000C81AC,
+		0x034, 0x000C71A9,
+		0x034, 0x000C60AC,
+		0x034, 0x000C50A9,
+		0x034, 0x000C402E,
+		0x034, 0x000C302B,
+		0x034, 0x000C2028,
+		0x034, 0x000C100B,
+		0x034, 0x000C0008,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3F4,
+		0x034, 0x000C93D2,
+		0x034, 0x000C82D1,
+		0x034, 0x000C71F1,
+		0x034, 0x000C61EE,
+		0x034, 0x000C51EB,
+		0x034, 0x000C41E8,
+		0x034, 0x000C314B,
+		0x034, 0x000C2148,
+		0x034, 0x000C104B,
+		0x034, 0x000C0048,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CAFF7,
+		0x034, 0x000C9FF6,
+		0x034, 0x000C8FF3,
+		0x034, 0x000C7FF0,
+		0x034, 0x000C6FED,
+		0x034, 0x000C5FEA,
+		0x034, 0x000C4FE7,
+		0x034, 0x000C3CB1,
+		0x034, 0x000C2CAE,
+		0x034, 0x000C1CAB,
+		0x034, 0x000C0CA8,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000CA3AD,
+		0x034, 0x000C938A,
+		0x034, 0x000C818C,
+		0x034, 0x000C7189,
+		0x034, 0x000C606D,
+		0x034, 0x000C506A,
+		0x034, 0x000C402C,
+		0x034, 0x000C3029,
+		0x034, 0x000C2026,
+		0x034, 0x000C1009,
+		0x034, 0x000C0006,
+	0xA0000000,	0x00000000,
+		0x034, 0x000CA794,
+		0x034, 0x000C9791,
+		0x034, 0x000C878E,
+		0x034, 0x000C778B,
+		0x034, 0x000C658D,
+		0x034, 0x000C558A,
+		0x034, 0x000C448D,
+		0x034, 0x000C348A,
+		0x034, 0x000C244C,
+		0x034, 0x000C1449,
+		0x034, 0x000C042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3EE,
+		0x034, 0x000A93EB,
+		0x034, 0x000A838B,
+		0x034, 0x000A71AC,
+		0x034, 0x000A61A9,
+		0x034, 0x000A50AC,
+		0x034, 0x000A40A9,
+		0x034, 0x000A30A6,
+		0x034, 0x000A202C,
+		0x034, 0x000A1029,
+		0x034, 0x000A0026,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3F5,
+		0x034, 0x000A93D2,
+		0x034, 0x000A83CE,
+		0x034, 0x000A7290,
+		0x034, 0x000A628D,
+		0x034, 0x000A528A,
+		0x034, 0x000A4287,
+		0x034, 0x000A308D,
+		0x034, 0x000A208A,
+		0x034, 0x000A1087,
+		0x034, 0x000A0048,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AAFF7,
+		0x034, 0x000A9FF6,
+		0x034, 0x000A8FF3,
+		0x034, 0x000A7FF0,
+		0x034, 0x000A6FED,
+		0x034, 0x000A5FEA,
+		0x034, 0x000A4FE7,
+		0x034, 0x000A3DEA,
+		0x034, 0x000A2DE7,
+		0x034, 0x000A1DE4,
+		0x034, 0x000A0D48,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x000AA3AD,
+		0x034, 0x000A938A,
+		0x034, 0x000A818C,
+		0x034, 0x000A7189,
+		0x034, 0x000A606D,
+		0x034, 0x000A504C,
+		0x034, 0x000A402C,
+		0x034, 0x000A3029,
+		0x034, 0x000A2026,
+		0x034, 0x000A1023,
+		0x034, 0x000A0006,
+	0xA0000000,	0x00000000,
+		0x034, 0x000AA794,
+		0x034, 0x000A9791,
+		0x034, 0x000A878E,
+		0x034, 0x000A778B,
+		0x034, 0x000A658D,
+		0x034, 0x000A558A,
+		0x034, 0x000A448D,
+		0x034, 0x000A348A,
+		0x034, 0x000A244C,
+		0x034, 0x000A1449,
+		0x034, 0x000A042B,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EF,
+		0x034, 0x000893EC,
+		0x034, 0x0008838C,
+		0x034, 0x000871AD,
+		0x034, 0x000861AA,
+		0x034, 0x000850AD,
+		0x034, 0x000840AA,
+		0x034, 0x0008306A,
+		0x034, 0x0008202D,
+		0x034, 0x0008102A,
+		0x034, 0x00080027,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3F1,
+		0x034, 0x000892B1,
+		0x034, 0x000881CF,
+		0x034, 0x00087170,
+		0x034, 0x0008616D,
+		0x034, 0x0008516A,
+		0x034, 0x00084167,
+		0x034, 0x0008302F,
+		0x034, 0x0008202C,
+		0x034, 0x00081029,
+		0x034, 0x00080026,
+	0x90000009,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008AFF7,
+		0x034, 0x00089FF6,
+		0x034, 0x00088FF3,
+		0x034, 0x00087FF0,
+		0x034, 0x00086FED,
+		0x034, 0x00085FEA,
+		0x034, 0x00084FE7,
+		0x034, 0x00083EC7,
+		0x034, 0x00082EC4,
+		0x034, 0x00081D4B,
+		0x034, 0x00080D48,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x034, 0x0008A3EE,
+		0x034, 0x000893AC,
+		0x034, 0x0008838A,
+		0x034, 0x0008718C,
+		0x034, 0x00086189,
+		0x034, 0x0008506D,
+		0x034, 0x0008406A,
+		0x034, 0x0008302C,
+		0x034, 0x00082029,
+		0x034, 0x00081026,
+		0x034, 0x00080023,
+	0xA0000000,	0x00000000,
+		0x034, 0x0008A794,
+		0x034, 0x00089791,
+		0x034, 0x0008878E,
+		0x034, 0x0008778B,
+		0x034, 0x0008658D,
+		0x034, 0x0008558A,
+		0x034, 0x0008448D,
+		0x034, 0x0008348A,
+		0x034, 0x0008244C,
+		0x034, 0x00081449,
+		0x034, 0x0008042B,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000040,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x035, 0x000006CC,
+		0x035, 0x000086CC,
+		0x035, 0x000106CC,
+		0x035, 0x000206CC,
+		0x035, 0x000286CC,
+		0x035, 0x000306CC,
+		0x035, 0x000406CC,
+		0x035, 0x000486CC,
+		0x035, 0x000506CC,
+		0x035, 0x000806CC,
+		0x035, 0x000886CC,
+		0x035, 0x000906CC,
+		0x035, 0x000A06CC,
+		0x035, 0x000A86CC,
+		0x035, 0x000B06CC,
+		0x035, 0x000C06CC,
+		0x035, 0x000C86CC,
+		0x035, 0x000D06CC,
+	0xA0000000,	0x00000000,
+		0x035, 0x00000484,
+		0x035, 0x00008484,
+		0x035, 0x00010484,
+		0x035, 0x00020584,
+		0x035, 0x00028584,
+		0x035, 0x00030584,
+		0x035, 0x00040584,
+		0x035, 0x00048584,
+		0x035, 0x00050584,
+		0x035, 0x000805FB,
+		0x035, 0x000885FB,
+		0x035, 0x000905FB,
+		0x035, 0x000A05FB,
+		0x035, 0x000A85FB,
+		0x035, 0x000B05FB,
+		0x035, 0x000C05FB,
+		0x035, 0x000C85FB,
+		0x035, 0x000D05FB,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x0DF, 0x00000001,
+	0xA0000000,	0x00000000,
+		0x0DF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x018, 0x0001712A,
+		0x0EF, 0x00000010,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000473,
+		0x036, 0x00008473,
+		0x036, 0x00010473,
+		0x036, 0x00020473,
+		0x036, 0x00028473,
+		0x036, 0x00030473,
+		0x036, 0x00040473,
+		0x036, 0x00048473,
+		0x036, 0x00050473,
+		0x036, 0x00080473,
+		0x036, 0x00088473,
+		0x036, 0x00090473,
+		0x036, 0x000A0473,
+		0x036, 0x000A8473,
+		0x036, 0x000B0473,
+		0x036, 0x000C0473,
+		0x036, 0x000C8473,
+		0x036, 0x000D0473,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x036, 0x00000475,
+		0x036, 0x00008475,
+		0x036, 0x00010475,
+		0x036, 0x00020475,
+		0x036, 0x00028475,
+		0x036, 0x00030475,
+		0x036, 0x00040475,
+		0x036, 0x00048475,
+		0x036, 0x00050475,
+		0x036, 0x00080475,
+		0x036, 0x00088475,
+		0x036, 0x00090475,
+		0x036, 0x000A0475,
+		0x036, 0x000A8475,
+		0x036, 0x000B0475,
+		0x036, 0x000C0475,
+		0x036, 0x000C8475,
+		0x036, 0x000D0475,
+	0xA0000000,	0x00000000,
+		0x036, 0x00000474,
+		0x036, 0x00008474,
+		0x036, 0x00010474,
+		0x036, 0x00020474,
+		0x036, 0x00028474,
+		0x036, 0x00030474,
+		0x036, 0x00040474,
+		0x036, 0x00048474,
+		0x036, 0x00050474,
+		0x036, 0x00080474,
+		0x036, 0x00088474,
+		0x036, 0x00090474,
+		0x036, 0x000A0474,
+		0x036, 0x000A8474,
+		0x036, 0x000B0474,
+		0x036, 0x000C0474,
+		0x036, 0x000C8474,
+		0x036, 0x000D0474,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x0EF, 0x00000004,
+		0x037, 0x00000000,
+		0x038, 0x0000514E,
+		0x037, 0x00004000,
+		0x038, 0x0000514E,
+		0x037, 0x00008000,
+		0x038, 0x0000514E,
+		0x037, 0x00010000,
+		0x038, 0x0000514E,
+		0x037, 0x00014000,
+		0x038, 0x0000514E,
+		0x037, 0x00018000,
+		0x038, 0x0000514E,
+		0x037, 0x0001C000,
+		0x038, 0x0000514E,
+		0x037, 0x00020000,
+		0x038, 0x0000514E,
+		0x037, 0x00024000,
+		0x038, 0x0000514E,
+		0x037, 0x00028000,
+		0x038, 0x0000514E,
+		0x037, 0x0002C000,
+		0x038, 0x0000714E,
+		0x037, 0x00030000,
+		0x038, 0x0000514E,
+		0x037, 0x00034000,
+		0x038, 0x0000514E,
+		0x037, 0x00038000,
+		0x038, 0x0000514E,
+		0x037, 0x0003C000,
+		0x038, 0x0000514E,
+		0x037, 0x00040000,
+		0x038, 0x0000514E,
+		0x037, 0x00044000,
+		0x038, 0x0000514E,
+		0x037, 0x00048000,
+		0x038, 0x0000514E,
+		0x037, 0x00080000,
+		0x038, 0x00005ECE,
+		0x037, 0x00084000,
+		0x038, 0x00005ECE,
+		0x037, 0x00088000,
+		0x038, 0x00005ECE,
+		0x037, 0x00090000,
+		0x038, 0x00005ECE,
+		0x037, 0x00094000,
+		0x038, 0x00005ECE,
+		0x037, 0x00098000,
+		0x038, 0x00005ECE,
+		0x037, 0x0009C000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000A8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000AC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000B8000,
+		0x038, 0x00005ECE,
+		0x037, 0x000BC000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C0000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C4000,
+		0x038, 0x00005ECE,
+		0x037, 0x000C8000,
+		0x038, 0x00005ECE,
+		0x0EF, 0x00000000,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000008,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000007D,
+		0x03C, 0x0000047D,
+		0x03C, 0x0000087D,
+		0x03C, 0x0000107D,
+		0x03C, 0x0000147D,
+		0x03C, 0x0000187D,
+	0xB0000000,	0x00000000,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x00000275,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x00001275,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x00002275,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x03C, 0x0000027F,
+		0x03C, 0x00000542,
+		0x03C, 0x00000821,
+		0x03C, 0x0000127F,
+		0x03C, 0x00001542,
+		0x03C, 0x00001821,
+		0x03C, 0x0000227F,
+		0x03C, 0x00002542,
+		0x03C, 0x00002821,
+	0xA0000000,	0x00000000,
+		0x03C, 0x0000037E,
+		0x03C, 0x00000575,
+		0x03C, 0x00000971,
+		0x03C, 0x0000127E,
+		0x03C, 0x00001575,
+		0x03C, 0x00001871,
+		0x03C, 0x0000217E,
+		0x03C, 0x00002575,
+		0x03C, 0x00002871,
+	0xB0000000,	0x00000000,
+		0x0EF, 0x00000000,
+		0x061, 0x000C0D47,
+		0x062, 0x0000133C,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x063, 0x000750E7,
+	0xA0000000,	0x00000000,
+		0x063, 0x0007D0E7,
+	0xB0000000,	0x00000000,
+		0x064, 0x00014FEC,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+		0x065, 0x000920D0,
+	0xA0000000,	0x00000000,
+		0x065, 0x000923FF,
+	0xB0000000,	0x00000000,
+		0x066, 0x00000040,
+		0x057, 0x00050000,
+		0x056, 0x00051DF0,
+	0x80000001,	0x00000000,	0x40000000,	0x00000000,
+	0x90000002,	0x00000000,	0x40000000,	0x00000000,
+	0x90000003,	0x00000000,	0x40000000,	0x00000000,
+	0x90000004,	0x00000000,	0x40000000,	0x00000000,
+	0x90000005,	0x00000000,	0x40000000,	0x00000000,
+	0x90000008,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000a,	0x00000000,	0x40000000,	0x00000000,
+	0x9000000b,	0x00000000,	0x40000000,	0x00000000,
+	0xA0000000,	0x00000000,
+		0x055, 0x00082060,
+	0xB0000000,	0x00000000,
+};
+
+RTW_DECL_TABLE_RF_RADIO(rtw8814a_rf_d, D);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt[] = {
+	{ 0, 0, 0, 0, 1, 36, },
+	{ 2, 0, 0, 0, 1, 32, },
+	{ 1, 0, 0, 0, 1, 32, },
+	{ 0, 0, 0, 0, 2, 36, },
+	{ 2, 0, 0, 0, 2, 32, },
+	{ 1, 0, 0, 0, 2, 32, },
+	{ 0, 0, 0, 0, 3, 36, },
+	{ 2, 0, 0, 0, 3, 32, },
+	{ 1, 0, 0, 0, 3, 32, },
+	{ 0, 0, 0, 0, 4, 36, },
+	{ 2, 0, 0, 0, 4, 32, },
+	{ 1, 0, 0, 0, 4, 32, },
+	{ 0, 0, 0, 0, 5, 36, },
+	{ 2, 0, 0, 0, 5, 32, },
+	{ 1, 0, 0, 0, 5, 32, },
+	{ 0, 0, 0, 0, 6, 36, },
+	{ 2, 0, 0, 0, 6, 32, },
+	{ 1, 0, 0, 0, 6, 32, },
+	{ 0, 0, 0, 0, 7, 36, },
+	{ 2, 0, 0, 0, 7, 32, },
+	{ 1, 0, 0, 0, 7, 32, },
+	{ 0, 0, 0, 0, 8, 36, },
+	{ 2, 0, 0, 0, 8, 32, },
+	{ 1, 0, 0, 0, 8, 32, },
+	{ 0, 0, 0, 0, 9, 36, },
+	{ 2, 0, 0, 0, 9, 32, },
+	{ 1, 0, 0, 0, 9, 32, },
+	{ 0, 0, 0, 0, 10, 36, },
+	{ 2, 0, 0, 0, 10, 32, },
+	{ 1, 0, 0, 0, 10, 32, },
+	{ 0, 0, 0, 0, 11, 36, },
+	{ 2, 0, 0, 0, 11, 32, },
+	{ 1, 0, 0, 0, 11, 32, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 32, },
+	{ 1, 0, 0, 0, 12, 32, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 32, },
+	{ 1, 0, 0, 0, 13, 32, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 32, },
+	{ 0, 0, 0, 1, 1, 34, },
+	{ 2, 0, 0, 1, 1, 32, },
+	{ 1, 0, 0, 1, 1, 32, },
+	{ 0, 0, 0, 1, 2, 36, },
+	{ 2, 0, 0, 1, 2, 32, },
+	{ 1, 0, 0, 1, 2, 32, },
+	{ 0, 0, 0, 1, 3, 36, },
+	{ 2, 0, 0, 1, 3, 32, },
+	{ 1, 0, 0, 1, 3, 32, },
+	{ 0, 0, 0, 1, 4, 36, },
+	{ 2, 0, 0, 1, 4, 32, },
+	{ 1, 0, 0, 1, 4, 32, },
+	{ 0, 0, 0, 1, 5, 36, },
+	{ 2, 0, 0, 1, 5, 32, },
+	{ 1, 0, 0, 1, 5, 32, },
+	{ 0, 0, 0, 1, 6, 36, },
+	{ 2, 0, 0, 1, 6, 32, },
+	{ 1, 0, 0, 1, 6, 32, },
+	{ 0, 0, 0, 1, 7, 36, },
+	{ 2, 0, 0, 1, 7, 32, },
+	{ 1, 0, 0, 1, 7, 32, },
+	{ 0, 0, 0, 1, 8, 36, },
+	{ 2, 0, 0, 1, 8, 32, },
+	{ 1, 0, 0, 1, 8, 32, },
+	{ 0, 0, 0, 1, 9, 36, },
+	{ 2, 0, 0, 1, 9, 32, },
+	{ 1, 0, 0, 1, 9, 32, },
+	{ 0, 0, 0, 1, 10, 36, },
+	{ 2, 0, 0, 1, 10, 32, },
+	{ 1, 0, 0, 1, 10, 32, },
+	{ 0, 0, 0, 1, 11, 32, },
+	{ 2, 0, 0, 1, 11, 32, },
+	{ 1, 0, 0, 1, 11, 32, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 32, },
+	{ 1, 0, 0, 1, 12, 32, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 32, },
+	{ 1, 0, 0, 1, 13, 32, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 34, },
+	{ 2, 0, 0, 2, 1, 32, },
+	{ 1, 0, 0, 2, 1, 32, },
+	{ 0, 0, 0, 2, 2, 36, },
+	{ 2, 0, 0, 2, 2, 32, },
+	{ 1, 0, 0, 2, 2, 32, },
+	{ 0, 0, 0, 2, 3, 36, },
+	{ 2, 0, 0, 2, 3, 32, },
+	{ 1, 0, 0, 2, 3, 32, },
+	{ 0, 0, 0, 2, 4, 36, },
+	{ 2, 0, 0, 2, 4, 32, },
+	{ 1, 0, 0, 2, 4, 32, },
+	{ 0, 0, 0, 2, 5, 36, },
+	{ 2, 0, 0, 2, 5, 32, },
+	{ 1, 0, 0, 2, 5, 32, },
+	{ 0, 0, 0, 2, 6, 36, },
+	{ 2, 0, 0, 2, 6, 32, },
+	{ 1, 0, 0, 2, 6, 32, },
+	{ 0, 0, 0, 2, 7, 36, },
+	{ 2, 0, 0, 2, 7, 32, },
+	{ 1, 0, 0, 2, 7, 32, },
+	{ 0, 0, 0, 2, 8, 36, },
+	{ 2, 0, 0, 2, 8, 32, },
+	{ 1, 0, 0, 2, 8, 32, },
+	{ 0, 0, 0, 2, 9, 36, },
+	{ 2, 0, 0, 2, 9, 32, },
+	{ 1, 0, 0, 2, 9, 32, },
+	{ 0, 0, 0, 2, 10, 36, },
+	{ 2, 0, 0, 2, 10, 32, },
+	{ 1, 0, 0, 2, 10, 32, },
+	{ 0, 0, 0, 2, 11, 32, },
+	{ 2, 0, 0, 2, 11, 32, },
+	{ 1, 0, 0, 2, 11, 32, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 32, },
+	{ 1, 0, 0, 2, 12, 32, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 32, },
+	{ 1, 0, 0, 2, 13, 32, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 32, },
+	{ 2, 0, 0, 3, 1, 30, },
+	{ 1, 0, 0, 3, 1, 30, },
+	{ 0, 0, 0, 3, 2, 34, },
+	{ 2, 0, 0, 3, 2, 30, },
+	{ 1, 0, 0, 3, 2, 30, },
+	{ 0, 0, 0, 3, 3, 34, },
+	{ 2, 0, 0, 3, 3, 30, },
+	{ 1, 0, 0, 3, 3, 30, },
+	{ 0, 0, 0, 3, 4, 34, },
+	{ 2, 0, 0, 3, 4, 30, },
+	{ 1, 0, 0, 3, 4, 30, },
+	{ 0, 0, 0, 3, 5, 34, },
+	{ 2, 0, 0, 3, 5, 30, },
+	{ 1, 0, 0, 3, 5, 30, },
+	{ 0, 0, 0, 3, 6, 34, },
+	{ 2, 0, 0, 3, 6, 30, },
+	{ 1, 0, 0, 3, 6, 30, },
+	{ 0, 0, 0, 3, 7, 34, },
+	{ 2, 0, 0, 3, 7, 30, },
+	{ 1, 0, 0, 3, 7, 30, },
+	{ 0, 0, 0, 3, 8, 34, },
+	{ 2, 0, 0, 3, 8, 30, },
+	{ 1, 0, 0, 3, 8, 30, },
+	{ 0, 0, 0, 3, 9, 34, },
+	{ 2, 0, 0, 3, 9, 30, },
+	{ 1, 0, 0, 3, 9, 30, },
+	{ 0, 0, 0, 3, 10, 34, },
+	{ 2, 0, 0, 3, 10, 30, },
+	{ 1, 0, 0, 3, 10, 30, },
+	{ 0, 0, 0, 3, 11, 30, },
+	{ 2, 0, 0, 3, 11, 30, },
+	{ 1, 0, 0, 3, 11, 30, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 30, },
+	{ 1, 0, 0, 3, 12, 30, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 30, },
+	{ 1, 0, 0, 3, 13, 30, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 30, },
+	{ 2, 0, 0, 6, 1, 28, },
+	{ 1, 0, 0, 6, 1, 28, },
+	{ 0, 0, 0, 6, 2, 32, },
+	{ 2, 0, 0, 6, 2, 28, },
+	{ 1, 0, 0, 6, 2, 28, },
+	{ 0, 0, 0, 6, 3, 32, },
+	{ 2, 0, 0, 6, 3, 28, },
+	{ 1, 0, 0, 6, 3, 28, },
+	{ 0, 0, 0, 6, 4, 32, },
+	{ 2, 0, 0, 6, 4, 28, },
+	{ 1, 0, 0, 6, 4, 28, },
+	{ 0, 0, 0, 6, 5, 32, },
+	{ 2, 0, 0, 6, 5, 28, },
+	{ 1, 0, 0, 6, 5, 28, },
+	{ 0, 0, 0, 6, 6, 32, },
+	{ 2, 0, 0, 6, 6, 28, },
+	{ 1, 0, 0, 6, 6, 28, },
+	{ 0, 0, 0, 6, 7, 32, },
+	{ 2, 0, 0, 6, 7, 28, },
+	{ 1, 0, 0, 6, 7, 28, },
+	{ 0, 0, 0, 6, 8, 32, },
+	{ 2, 0, 0, 6, 8, 28, },
+	{ 1, 0, 0, 6, 8, 28, },
+	{ 0, 0, 0, 6, 9, 32, },
+	{ 2, 0, 0, 6, 9, 28, },
+	{ 1, 0, 0, 6, 9, 28, },
+	{ 0, 0, 0, 6, 10, 32, },
+	{ 2, 0, 0, 6, 10, 28, },
+	{ 1, 0, 0, 6, 10, 28, },
+	{ 0, 0, 0, 6, 11, 28, },
+	{ 2, 0, 0, 6, 11, 28, },
+	{ 1, 0, 0, 6, 11, 28, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 28, },
+	{ 1, 0, 0, 6, 12, 28, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 28, },
+	{ 1, 0, 0, 6, 13, 28, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 28, },
+	{ 2, 0, 0, 7, 1, 26, },
+	{ 1, 0, 0, 7, 1, 26, },
+	{ 0, 0, 0, 7, 2, 30, },
+	{ 2, 0, 0, 7, 2, 26, },
+	{ 1, 0, 0, 7, 2, 26, },
+	{ 0, 0, 0, 7, 3, 30, },
+	{ 2, 0, 0, 7, 3, 26, },
+	{ 1, 0, 0, 7, 3, 26, },
+	{ 0, 0, 0, 7, 4, 30, },
+	{ 2, 0, 0, 7, 4, 26, },
+	{ 1, 0, 0, 7, 4, 26, },
+	{ 0, 0, 0, 7, 5, 30, },
+	{ 2, 0, 0, 7, 5, 26, },
+	{ 1, 0, 0, 7, 5, 26, },
+	{ 0, 0, 0, 7, 6, 30, },
+	{ 2, 0, 0, 7, 6, 26, },
+	{ 1, 0, 0, 7, 6, 26, },
+	{ 0, 0, 0, 7, 7, 30, },
+	{ 2, 0, 0, 7, 7, 26, },
+	{ 1, 0, 0, 7, 7, 26, },
+	{ 0, 0, 0, 7, 8, 30, },
+	{ 2, 0, 0, 7, 8, 26, },
+	{ 1, 0, 0, 7, 8, 26, },
+	{ 0, 0, 0, 7, 9, 30, },
+	{ 2, 0, 0, 7, 9, 26, },
+	{ 1, 0, 0, 7, 9, 26, },
+	{ 0, 0, 0, 7, 10, 30, },
+	{ 2, 0, 0, 7, 10, 26, },
+	{ 1, 0, 0, 7, 10, 26, },
+	{ 0, 0, 0, 7, 11, 26, },
+	{ 2, 0, 0, 7, 11, 26, },
+	{ 1, 0, 0, 7, 11, 26, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 26, },
+	{ 1, 0, 0, 7, 12, 26, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 26, },
+	{ 1, 0, 0, 7, 13, 26, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 32, },
+	{ 2, 0, 1, 2, 3, 32, },
+	{ 1, 0, 1, 2, 3, 32, },
+	{ 0, 0, 1, 2, 4, 36, },
+	{ 2, 0, 1, 2, 4, 32, },
+	{ 1, 0, 1, 2, 4, 32, },
+	{ 0, 0, 1, 2, 5, 36, },
+	{ 2, 0, 1, 2, 5, 32, },
+	{ 1, 0, 1, 2, 5, 32, },
+	{ 0, 0, 1, 2, 6, 36, },
+	{ 2, 0, 1, 2, 6, 32, },
+	{ 1, 0, 1, 2, 6, 32, },
+	{ 0, 0, 1, 2, 7, 36, },
+	{ 2, 0, 1, 2, 7, 32, },
+	{ 1, 0, 1, 2, 7, 32, },
+	{ 0, 0, 1, 2, 8, 36, },
+	{ 2, 0, 1, 2, 8, 32, },
+	{ 1, 0, 1, 2, 8, 32, },
+	{ 0, 0, 1, 2, 9, 36, },
+	{ 2, 0, 1, 2, 9, 32, },
+	{ 1, 0, 1, 2, 9, 32, },
+	{ 0, 0, 1, 2, 10, 36, },
+	{ 2, 0, 1, 2, 10, 32, },
+	{ 1, 0, 1, 2, 10, 32, },
+	{ 0, 0, 1, 2, 11, 32, },
+	{ 2, 0, 1, 2, 11, 32, },
+	{ 1, 0, 1, 2, 11, 32, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 32, },
+	{ 1, 0, 1, 2, 12, 32, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 32, },
+	{ 1, 0, 1, 2, 13, 32, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 30, },
+	{ 2, 0, 1, 3, 3, 30, },
+	{ 1, 0, 1, 3, 3, 30, },
+	{ 0, 0, 1, 3, 4, 34, },
+	{ 2, 0, 1, 3, 4, 30, },
+	{ 1, 0, 1, 3, 4, 30, },
+	{ 0, 0, 1, 3, 5, 34, },
+	{ 2, 0, 1, 3, 5, 30, },
+	{ 1, 0, 1, 3, 5, 30, },
+	{ 0, 0, 1, 3, 6, 34, },
+	{ 2, 0, 1, 3, 6, 30, },
+	{ 1, 0, 1, 3, 6, 30, },
+	{ 0, 0, 1, 3, 7, 34, },
+	{ 2, 0, 1, 3, 7, 30, },
+	{ 1, 0, 1, 3, 7, 30, },
+	{ 0, 0, 1, 3, 8, 34, },
+	{ 2, 0, 1, 3, 8, 30, },
+	{ 1, 0, 1, 3, 8, 30, },
+	{ 0, 0, 1, 3, 9, 34, },
+	{ 2, 0, 1, 3, 9, 30, },
+	{ 1, 0, 1, 3, 9, 30, },
+	{ 0, 0, 1, 3, 10, 34, },
+	{ 2, 0, 1, 3, 10, 30, },
+	{ 1, 0, 1, 3, 10, 30, },
+	{ 0, 0, 1, 3, 11, 30, },
+	{ 2, 0, 1, 3, 11, 30, },
+	{ 1, 0, 1, 3, 11, 30, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 30, },
+	{ 1, 0, 1, 3, 12, 30, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 30, },
+	{ 1, 0, 1, 3, 13, 30, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 28, },
+	{ 2, 0, 1, 6, 3, 28, },
+	{ 1, 0, 1, 6, 3, 28, },
+	{ 0, 0, 1, 6, 4, 32, },
+	{ 2, 0, 1, 6, 4, 28, },
+	{ 1, 0, 1, 6, 4, 28, },
+	{ 0, 0, 1, 6, 5, 32, },
+	{ 2, 0, 1, 6, 5, 28, },
+	{ 1, 0, 1, 6, 5, 28, },
+	{ 0, 0, 1, 6, 6, 32, },
+	{ 2, 0, 1, 6, 6, 28, },
+	{ 1, 0, 1, 6, 6, 28, },
+	{ 0, 0, 1, 6, 7, 32, },
+	{ 2, 0, 1, 6, 7, 28, },
+	{ 1, 0, 1, 6, 7, 28, },
+	{ 0, 0, 1, 6, 8, 32, },
+	{ 2, 0, 1, 6, 8, 28, },
+	{ 1, 0, 1, 6, 8, 28, },
+	{ 0, 0, 1, 6, 9, 32, },
+	{ 2, 0, 1, 6, 9, 28, },
+	{ 1, 0, 1, 6, 9, 28, },
+	{ 0, 0, 1, 6, 10, 32, },
+	{ 2, 0, 1, 6, 10, 28, },
+	{ 1, 0, 1, 6, 10, 28, },
+	{ 0, 0, 1, 6, 11, 28, },
+	{ 2, 0, 1, 6, 11, 28, },
+	{ 1, 0, 1, 6, 11, 28, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 28, },
+	{ 1, 0, 1, 6, 12, 28, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 28, },
+	{ 1, 0, 1, 6, 13, 28, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 26, },
+	{ 2, 0, 1, 7, 3, 26, },
+	{ 1, 0, 1, 7, 3, 26, },
+	{ 0, 0, 1, 7, 4, 30, },
+	{ 2, 0, 1, 7, 4, 26, },
+	{ 1, 0, 1, 7, 4, 26, },
+	{ 0, 0, 1, 7, 5, 30, },
+	{ 2, 0, 1, 7, 5, 26, },
+	{ 1, 0, 1, 7, 5, 26, },
+	{ 0, 0, 1, 7, 6, 30, },
+	{ 2, 0, 1, 7, 6, 26, },
+	{ 1, 0, 1, 7, 6, 26, },
+	{ 0, 0, 1, 7, 7, 30, },
+	{ 2, 0, 1, 7, 7, 26, },
+	{ 1, 0, 1, 7, 7, 26, },
+	{ 0, 0, 1, 7, 8, 30, },
+	{ 2, 0, 1, 7, 8, 26, },
+	{ 1, 0, 1, 7, 8, 26, },
+	{ 0, 0, 1, 7, 9, 30, },
+	{ 2, 0, 1, 7, 9, 26, },
+	{ 1, 0, 1, 7, 9, 26, },
+	{ 0, 0, 1, 7, 10, 30, },
+	{ 2, 0, 1, 7, 10, 26, },
+	{ 1, 0, 1, 7, 10, 26, },
+	{ 0, 0, 1, 7, 11, 26, },
+	{ 2, 0, 1, 7, 11, 26, },
+	{ 1, 0, 1, 7, 11, 26, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 26, },
+	{ 1, 0, 1, 7, 12, 26, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 26, },
+	{ 1, 0, 1, 7, 13, 26, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 30, },
+	{ 2, 1, 0, 1, 36, 32, },
+	{ 1, 1, 0, 1, 36, 32, },
+	{ 0, 1, 0, 1, 40, 30, },
+	{ 2, 1, 0, 1, 40, 32, },
+	{ 1, 1, 0, 1, 40, 32, },
+	{ 0, 1, 0, 1, 44, 30, },
+	{ 2, 1, 0, 1, 44, 32, },
+	{ 1, 1, 0, 1, 44, 32, },
+	{ 0, 1, 0, 1, 48, 30, },
+	{ 2, 1, 0, 1, 48, 32, },
+	{ 1, 1, 0, 1, 48, 32, },
+	{ 0, 1, 0, 1, 52, 36, },
+	{ 2, 1, 0, 1, 52, 32, },
+	{ 1, 1, 0, 1, 52, 32, },
+	{ 0, 1, 0, 1, 56, 34, },
+	{ 2, 1, 0, 1, 56, 32, },
+	{ 1, 1, 0, 1, 56, 32, },
+	{ 0, 1, 0, 1, 60, 32, },
+	{ 2, 1, 0, 1, 60, 32, },
+	{ 1, 1, 0, 1, 60, 32, },
+	{ 0, 1, 0, 1, 64, 28, },
+	{ 2, 1, 0, 1, 64, 32, },
+	{ 1, 1, 0, 1, 64, 32, },
+	{ 0, 1, 0, 1, 100, 30, },
+	{ 2, 1, 0, 1, 100, 32, },
+	{ 1, 1, 0, 1, 100, 32, },
+	{ 0, 1, 0, 1, 104, 30, },
+	{ 2, 1, 0, 1, 104, 32, },
+	{ 1, 1, 0, 1, 104, 32, },
+	{ 0, 1, 0, 1, 108, 32, },
+	{ 2, 1, 0, 1, 108, 32, },
+	{ 1, 1, 0, 1, 108, 32, },
+	{ 0, 1, 0, 1, 112, 34, },
+	{ 2, 1, 0, 1, 112, 32, },
+	{ 1, 1, 0, 1, 112, 32, },
+	{ 0, 1, 0, 1, 116, 34, },
+	{ 2, 1, 0, 1, 116, 32, },
+	{ 1, 1, 0, 1, 116, 32, },
+	{ 0, 1, 0, 1, 120, 36, },
+	{ 2, 1, 0, 1, 120, 32, },
+	{ 1, 1, 0, 1, 120, 32, },
+	{ 0, 1, 0, 1, 124, 34, },
+	{ 2, 1, 0, 1, 124, 32, },
+	{ 1, 1, 0, 1, 124, 32, },
+	{ 0, 1, 0, 1, 128, 32, },
+	{ 2, 1, 0, 1, 128, 32, },
+	{ 1, 1, 0, 1, 128, 32, },
+	{ 0, 1, 0, 1, 132, 30, },
+	{ 2, 1, 0, 1, 132, 32, },
+	{ 1, 1, 0, 1, 132, 32, },
+	{ 0, 1, 0, 1, 136, 30, },
+	{ 2, 1, 0, 1, 136, 32, },
+	{ 1, 1, 0, 1, 136, 32, },
+	{ 0, 1, 0, 1, 140, 28, },
+	{ 2, 1, 0, 1, 140, 32, },
+	{ 1, 1, 0, 1, 140, 32, },
+	{ 0, 1, 0, 1, 149, 36, },
+	{ 2, 1, 0, 1, 149, 32, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 36, },
+	{ 2, 1, 0, 1, 153, 32, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 36, },
+	{ 2, 1, 0, 1, 157, 32, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 36, },
+	{ 2, 1, 0, 1, 161, 32, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 36, },
+	{ 2, 1, 0, 1, 165, 32, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 30, },
+	{ 2, 1, 0, 2, 36, 32, },
+	{ 1, 1, 0, 2, 36, 32, },
+	{ 0, 1, 0, 2, 40, 30, },
+	{ 2, 1, 0, 2, 40, 32, },
+	{ 1, 1, 0, 2, 40, 32, },
+	{ 0, 1, 0, 2, 44, 30, },
+	{ 2, 1, 0, 2, 44, 32, },
+	{ 1, 1, 0, 2, 44, 32, },
+	{ 0, 1, 0, 2, 48, 30, },
+	{ 2, 1, 0, 2, 48, 32, },
+	{ 1, 1, 0, 2, 48, 32, },
+	{ 0, 1, 0, 2, 52, 36, },
+	{ 2, 1, 0, 2, 52, 32, },
+	{ 1, 1, 0, 2, 52, 32, },
+	{ 0, 1, 0, 2, 56, 34, },
+	{ 2, 1, 0, 2, 56, 32, },
+	{ 1, 1, 0, 2, 56, 32, },
+	{ 0, 1, 0, 2, 60, 32, },
+	{ 2, 1, 0, 2, 60, 32, },
+	{ 1, 1, 0, 2, 60, 32, },
+	{ 0, 1, 0, 2, 64, 28, },
+	{ 2, 1, 0, 2, 64, 32, },
+	{ 1, 1, 0, 2, 64, 32, },
+	{ 0, 1, 0, 2, 100, 30, },
+	{ 2, 1, 0, 2, 100, 32, },
+	{ 1, 1, 0, 2, 100, 32, },
+	{ 0, 1, 0, 2, 104, 30, },
+	{ 2, 1, 0, 2, 104, 32, },
+	{ 1, 1, 0, 2, 104, 32, },
+	{ 0, 1, 0, 2, 108, 32, },
+	{ 2, 1, 0, 2, 108, 32, },
+	{ 1, 1, 0, 2, 108, 32, },
+	{ 0, 1, 0, 2, 112, 34, },
+	{ 2, 1, 0, 2, 112, 32, },
+	{ 1, 1, 0, 2, 112, 32, },
+	{ 0, 1, 0, 2, 116, 34, },
+	{ 2, 1, 0, 2, 116, 32, },
+	{ 1, 1, 0, 2, 116, 32, },
+	{ 0, 1, 0, 2, 120, 36, },
+	{ 2, 1, 0, 2, 120, 32, },
+	{ 1, 1, 0, 2, 120, 32, },
+	{ 0, 1, 0, 2, 124, 34, },
+	{ 2, 1, 0, 2, 124, 32, },
+	{ 1, 1, 0, 2, 124, 32, },
+	{ 0, 1, 0, 2, 128, 32, },
+	{ 2, 1, 0, 2, 128, 32, },
+	{ 1, 1, 0, 2, 128, 32, },
+	{ 0, 1, 0, 2, 132, 30, },
+	{ 2, 1, 0, 2, 132, 32, },
+	{ 1, 1, 0, 2, 132, 32, },
+	{ 0, 1, 0, 2, 136, 30, },
+	{ 2, 1, 0, 2, 136, 32, },
+	{ 1, 1, 0, 2, 136, 32, },
+	{ 0, 1, 0, 2, 140, 28, },
+	{ 2, 1, 0, 2, 140, 32, },
+	{ 1, 1, 0, 2, 140, 32, },
+	{ 0, 1, 0, 2, 149, 36, },
+	{ 2, 1, 0, 2, 149, 32, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 36, },
+	{ 2, 1, 0, 2, 153, 32, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 36, },
+	{ 2, 1, 0, 2, 157, 32, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 36, },
+	{ 2, 1, 0, 2, 161, 32, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 36, },
+	{ 2, 1, 0, 2, 165, 32, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 28, },
+	{ 2, 1, 0, 3, 36, 30, },
+	{ 1, 1, 0, 3, 36, 30, },
+	{ 0, 1, 0, 3, 40, 28, },
+	{ 2, 1, 0, 3, 40, 30, },
+	{ 1, 1, 0, 3, 40, 30, },
+	{ 0, 1, 0, 3, 44, 28, },
+	{ 2, 1, 0, 3, 44, 30, },
+	{ 1, 1, 0, 3, 44, 30, },
+	{ 0, 1, 0, 3, 48, 28, },
+	{ 2, 1, 0, 3, 48, 30, },
+	{ 1, 1, 0, 3, 48, 30, },
+	{ 0, 1, 0, 3, 52, 34, },
+	{ 2, 1, 0, 3, 52, 30, },
+	{ 1, 1, 0, 3, 52, 30, },
+	{ 0, 1, 0, 3, 56, 32, },
+	{ 2, 1, 0, 3, 56, 30, },
+	{ 1, 1, 0, 3, 56, 30, },
+	{ 0, 1, 0, 3, 60, 30, },
+	{ 2, 1, 0, 3, 60, 30, },
+	{ 1, 1, 0, 3, 60, 30, },
+	{ 0, 1, 0, 3, 64, 26, },
+	{ 2, 1, 0, 3, 64, 30, },
+	{ 1, 1, 0, 3, 64, 30, },
+	{ 0, 1, 0, 3, 100, 28, },
+	{ 2, 1, 0, 3, 100, 30, },
+	{ 1, 1, 0, 3, 100, 30, },
+	{ 0, 1, 0, 3, 104, 28, },
+	{ 2, 1, 0, 3, 104, 30, },
+	{ 1, 1, 0, 3, 104, 30, },
+	{ 0, 1, 0, 3, 108, 30, },
+	{ 2, 1, 0, 3, 108, 30, },
+	{ 1, 1, 0, 3, 108, 30, },
+	{ 0, 1, 0, 3, 112, 32, },
+	{ 2, 1, 0, 3, 112, 30, },
+	{ 1, 1, 0, 3, 112, 30, },
+	{ 0, 1, 0, 3, 116, 32, },
+	{ 2, 1, 0, 3, 116, 30, },
+	{ 1, 1, 0, 3, 116, 30, },
+	{ 0, 1, 0, 3, 120, 34, },
+	{ 2, 1, 0, 3, 120, 30, },
+	{ 1, 1, 0, 3, 120, 30, },
+	{ 0, 1, 0, 3, 124, 32, },
+	{ 2, 1, 0, 3, 124, 30, },
+	{ 1, 1, 0, 3, 124, 30, },
+	{ 0, 1, 0, 3, 128, 30, },
+	{ 2, 1, 0, 3, 128, 30, },
+	{ 1, 1, 0, 3, 128, 30, },
+	{ 0, 1, 0, 3, 132, 28, },
+	{ 2, 1, 0, 3, 132, 30, },
+	{ 1, 1, 0, 3, 132, 30, },
+	{ 0, 1, 0, 3, 136, 28, },
+	{ 2, 1, 0, 3, 136, 30, },
+	{ 1, 1, 0, 3, 136, 30, },
+	{ 0, 1, 0, 3, 140, 26, },
+	{ 2, 1, 0, 3, 140, 30, },
+	{ 1, 1, 0, 3, 140, 30, },
+	{ 0, 1, 0, 3, 149, 34, },
+	{ 2, 1, 0, 3, 149, 30, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 34, },
+	{ 2, 1, 0, 3, 153, 30, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 34, },
+	{ 2, 1, 0, 3, 157, 30, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 34, },
+	{ 2, 1, 0, 3, 161, 30, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 34, },
+	{ 2, 1, 0, 3, 165, 30, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 26, },
+	{ 2, 1, 0, 6, 36, 28, },
+	{ 1, 1, 0, 6, 36, 28, },
+	{ 0, 1, 0, 6, 40, 26, },
+	{ 2, 1, 0, 6, 40, 28, },
+	{ 1, 1, 0, 6, 40, 28, },
+	{ 0, 1, 0, 6, 44, 26, },
+	{ 2, 1, 0, 6, 44, 28, },
+	{ 1, 1, 0, 6, 44, 28, },
+	{ 0, 1, 0, 6, 48, 26, },
+	{ 2, 1, 0, 6, 48, 28, },
+	{ 1, 1, 0, 6, 48, 28, },
+	{ 0, 1, 0, 6, 52, 32, },
+	{ 2, 1, 0, 6, 52, 28, },
+	{ 1, 1, 0, 6, 52, 28, },
+	{ 0, 1, 0, 6, 56, 30, },
+	{ 2, 1, 0, 6, 56, 28, },
+	{ 1, 1, 0, 6, 56, 28, },
+	{ 0, 1, 0, 6, 60, 28, },
+	{ 2, 1, 0, 6, 60, 28, },
+	{ 1, 1, 0, 6, 60, 28, },
+	{ 0, 1, 0, 6, 64, 24, },
+	{ 2, 1, 0, 6, 64, 28, },
+	{ 1, 1, 0, 6, 64, 28, },
+	{ 0, 1, 0, 6, 100, 26, },
+	{ 2, 1, 0, 6, 100, 28, },
+	{ 1, 1, 0, 6, 100, 28, },
+	{ 0, 1, 0, 6, 104, 26, },
+	{ 2, 1, 0, 6, 104, 28, },
+	{ 1, 1, 0, 6, 104, 28, },
+	{ 0, 1, 0, 6, 108, 28, },
+	{ 2, 1, 0, 6, 108, 28, },
+	{ 1, 1, 0, 6, 108, 28, },
+	{ 0, 1, 0, 6, 112, 30, },
+	{ 2, 1, 0, 6, 112, 28, },
+	{ 1, 1, 0, 6, 112, 28, },
+	{ 0, 1, 0, 6, 116, 30, },
+	{ 2, 1, 0, 6, 116, 28, },
+	{ 1, 1, 0, 6, 116, 28, },
+	{ 0, 1, 0, 6, 120, 32, },
+	{ 2, 1, 0, 6, 120, 28, },
+	{ 1, 1, 0, 6, 120, 28, },
+	{ 0, 1, 0, 6, 124, 30, },
+	{ 2, 1, 0, 6, 124, 28, },
+	{ 1, 1, 0, 6, 124, 28, },
+	{ 0, 1, 0, 6, 128, 28, },
+	{ 2, 1, 0, 6, 128, 28, },
+	{ 1, 1, 0, 6, 128, 28, },
+	{ 0, 1, 0, 6, 132, 26, },
+	{ 2, 1, 0, 6, 132, 28, },
+	{ 1, 1, 0, 6, 132, 28, },
+	{ 0, 1, 0, 6, 136, 26, },
+	{ 2, 1, 0, 6, 136, 28, },
+	{ 1, 1, 0, 6, 136, 28, },
+	{ 0, 1, 0, 6, 140, 24, },
+	{ 2, 1, 0, 6, 140, 28, },
+	{ 1, 1, 0, 6, 140, 28, },
+	{ 0, 1, 0, 6, 149, 32, },
+	{ 2, 1, 0, 6, 149, 28, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 32, },
+	{ 2, 1, 0, 6, 153, 28, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 32, },
+	{ 2, 1, 0, 6, 157, 28, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 32, },
+	{ 2, 1, 0, 6, 161, 28, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 32, },
+	{ 2, 1, 0, 6, 165, 28, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 24, },
+	{ 2, 1, 0, 7, 36, 26, },
+	{ 1, 1, 0, 7, 36, 26, },
+	{ 0, 1, 0, 7, 40, 24, },
+	{ 2, 1, 0, 7, 40, 26, },
+	{ 1, 1, 0, 7, 40, 26, },
+	{ 0, 1, 0, 7, 44, 24, },
+	{ 2, 1, 0, 7, 44, 26, },
+	{ 1, 1, 0, 7, 44, 26, },
+	{ 0, 1, 0, 7, 48, 24, },
+	{ 2, 1, 0, 7, 48, 26, },
+	{ 1, 1, 0, 7, 48, 26, },
+	{ 0, 1, 0, 7, 52, 30, },
+	{ 2, 1, 0, 7, 52, 26, },
+	{ 1, 1, 0, 7, 52, 26, },
+	{ 0, 1, 0, 7, 56, 28, },
+	{ 2, 1, 0, 7, 56, 26, },
+	{ 1, 1, 0, 7, 56, 26, },
+	{ 0, 1, 0, 7, 60, 26, },
+	{ 2, 1, 0, 7, 60, 26, },
+	{ 1, 1, 0, 7, 60, 26, },
+	{ 0, 1, 0, 7, 64, 22, },
+	{ 2, 1, 0, 7, 64, 26, },
+	{ 1, 1, 0, 7, 64, 26, },
+	{ 0, 1, 0, 7, 100, 24, },
+	{ 2, 1, 0, 7, 100, 26, },
+	{ 1, 1, 0, 7, 100, 26, },
+	{ 0, 1, 0, 7, 104, 24, },
+	{ 2, 1, 0, 7, 104, 26, },
+	{ 1, 1, 0, 7, 104, 26, },
+	{ 0, 1, 0, 7, 108, 26, },
+	{ 2, 1, 0, 7, 108, 26, },
+	{ 1, 1, 0, 7, 108, 26, },
+	{ 0, 1, 0, 7, 112, 28, },
+	{ 2, 1, 0, 7, 112, 26, },
+	{ 1, 1, 0, 7, 112, 26, },
+	{ 0, 1, 0, 7, 116, 28, },
+	{ 2, 1, 0, 7, 116, 26, },
+	{ 1, 1, 0, 7, 116, 26, },
+	{ 0, 1, 0, 7, 120, 30, },
+	{ 2, 1, 0, 7, 120, 26, },
+	{ 1, 1, 0, 7, 120, 26, },
+	{ 0, 1, 0, 7, 124, 28, },
+	{ 2, 1, 0, 7, 124, 26, },
+	{ 1, 1, 0, 7, 124, 26, },
+	{ 0, 1, 0, 7, 128, 26, },
+	{ 2, 1, 0, 7, 128, 26, },
+	{ 1, 1, 0, 7, 128, 26, },
+	{ 0, 1, 0, 7, 132, 24, },
+	{ 2, 1, 0, 7, 132, 26, },
+	{ 1, 1, 0, 7, 132, 26, },
+	{ 0, 1, 0, 7, 136, 24, },
+	{ 2, 1, 0, 7, 136, 26, },
+	{ 1, 1, 0, 7, 136, 26, },
+	{ 0, 1, 0, 7, 140, 22, },
+	{ 2, 1, 0, 7, 140, 26, },
+	{ 1, 1, 0, 7, 140, 26, },
+	{ 0, 1, 0, 7, 149, 30, },
+	{ 2, 1, 0, 7, 149, 26, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 30, },
+	{ 2, 1, 0, 7, 153, 26, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 30, },
+	{ 2, 1, 0, 7, 157, 26, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 30, },
+	{ 2, 1, 0, 7, 161, 26, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 30, },
+	{ 2, 1, 0, 7, 165, 26, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 30, },
+	{ 2, 1, 1, 2, 38, 32, },
+	{ 1, 1, 1, 2, 38, 32, },
+	{ 0, 1, 1, 2, 46, 30, },
+	{ 2, 1, 1, 2, 46, 32, },
+	{ 1, 1, 1, 2, 46, 32, },
+	{ 0, 1, 1, 2, 54, 32, },
+	{ 2, 1, 1, 2, 54, 32, },
+	{ 1, 1, 1, 2, 54, 32, },
+	{ 0, 1, 1, 2, 62, 32, },
+	{ 2, 1, 1, 2, 62, 32, },
+	{ 1, 1, 1, 2, 62, 32, },
+	{ 0, 1, 1, 2, 102, 28, },
+	{ 2, 1, 1, 2, 102, 32, },
+	{ 1, 1, 1, 2, 102, 32, },
+	{ 0, 1, 1, 2, 110, 32, },
+	{ 2, 1, 1, 2, 110, 32, },
+	{ 1, 1, 1, 2, 110, 32, },
+	{ 0, 1, 1, 2, 118, 36, },
+	{ 2, 1, 1, 2, 118, 32, },
+	{ 1, 1, 1, 2, 118, 32, },
+	{ 0, 1, 1, 2, 126, 34, },
+	{ 2, 1, 1, 2, 126, 32, },
+	{ 1, 1, 1, 2, 126, 32, },
+	{ 0, 1, 1, 2, 134, 32, },
+	{ 2, 1, 1, 2, 134, 32, },
+	{ 1, 1, 1, 2, 134, 32, },
+	{ 0, 1, 1, 2, 151, 36, },
+	{ 2, 1, 1, 2, 151, 32, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 36, },
+	{ 2, 1, 1, 2, 159, 32, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 28, },
+	{ 2, 1, 1, 3, 38, 30, },
+	{ 1, 1, 1, 3, 38, 30, },
+	{ 0, 1, 1, 3, 46, 28, },
+	{ 2, 1, 1, 3, 46, 30, },
+	{ 1, 1, 1, 3, 46, 30, },
+	{ 0, 1, 1, 3, 54, 30, },
+	{ 2, 1, 1, 3, 54, 30, },
+	{ 1, 1, 1, 3, 54, 30, },
+	{ 0, 1, 1, 3, 62, 30, },
+	{ 2, 1, 1, 3, 62, 30, },
+	{ 1, 1, 1, 3, 62, 30, },
+	{ 0, 1, 1, 3, 102, 26, },
+	{ 2, 1, 1, 3, 102, 30, },
+	{ 1, 1, 1, 3, 102, 30, },
+	{ 0, 1, 1, 3, 110, 30, },
+	{ 2, 1, 1, 3, 110, 30, },
+	{ 1, 1, 1, 3, 110, 30, },
+	{ 0, 1, 1, 3, 118, 34, },
+	{ 2, 1, 1, 3, 118, 30, },
+	{ 1, 1, 1, 3, 118, 30, },
+	{ 0, 1, 1, 3, 126, 32, },
+	{ 2, 1, 1, 3, 126, 30, },
+	{ 1, 1, 1, 3, 126, 30, },
+	{ 0, 1, 1, 3, 134, 30, },
+	{ 2, 1, 1, 3, 134, 30, },
+	{ 1, 1, 1, 3, 134, 30, },
+	{ 0, 1, 1, 3, 151, 34, },
+	{ 2, 1, 1, 3, 151, 30, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 34, },
+	{ 2, 1, 1, 3, 159, 30, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 26, },
+	{ 2, 1, 1, 6, 38, 28, },
+	{ 1, 1, 1, 6, 38, 28, },
+	{ 0, 1, 1, 6, 46, 26, },
+	{ 2, 1, 1, 6, 46, 28, },
+	{ 1, 1, 1, 6, 46, 28, },
+	{ 0, 1, 1, 6, 54, 28, },
+	{ 2, 1, 1, 6, 54, 28, },
+	{ 1, 1, 1, 6, 54, 28, },
+	{ 0, 1, 1, 6, 62, 28, },
+	{ 2, 1, 1, 6, 62, 28, },
+	{ 1, 1, 1, 6, 62, 28, },
+	{ 0, 1, 1, 6, 102, 24, },
+	{ 2, 1, 1, 6, 102, 28, },
+	{ 1, 1, 1, 6, 102, 28, },
+	{ 0, 1, 1, 6, 110, 28, },
+	{ 2, 1, 1, 6, 110, 28, },
+	{ 1, 1, 1, 6, 110, 28, },
+	{ 0, 1, 1, 6, 118, 32, },
+	{ 2, 1, 1, 6, 118, 28, },
+	{ 1, 1, 1, 6, 118, 28, },
+	{ 0, 1, 1, 6, 126, 30, },
+	{ 2, 1, 1, 6, 126, 28, },
+	{ 1, 1, 1, 6, 126, 28, },
+	{ 0, 1, 1, 6, 134, 28, },
+	{ 2, 1, 1, 6, 134, 28, },
+	{ 1, 1, 1, 6, 134, 28, },
+	{ 0, 1, 1, 6, 151, 32, },
+	{ 2, 1, 1, 6, 151, 28, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 32, },
+	{ 2, 1, 1, 6, 159, 28, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 24, },
+	{ 2, 1, 1, 7, 38, 26, },
+	{ 1, 1, 1, 7, 38, 26, },
+	{ 0, 1, 1, 7, 46, 24, },
+	{ 2, 1, 1, 7, 46, 26, },
+	{ 1, 1, 1, 7, 46, 26, },
+	{ 0, 1, 1, 7, 54, 26, },
+	{ 2, 1, 1, 7, 54, 26, },
+	{ 1, 1, 1, 7, 54, 26, },
+	{ 0, 1, 1, 7, 62, 26, },
+	{ 2, 1, 1, 7, 62, 26, },
+	{ 1, 1, 1, 7, 62, 26, },
+	{ 0, 1, 1, 7, 102, 22, },
+	{ 2, 1, 1, 7, 102, 26, },
+	{ 1, 1, 1, 7, 102, 26, },
+	{ 0, 1, 1, 7, 110, 26, },
+	{ 2, 1, 1, 7, 110, 26, },
+	{ 1, 1, 1, 7, 110, 26, },
+	{ 0, 1, 1, 7, 118, 30, },
+	{ 2, 1, 1, 7, 118, 26, },
+	{ 1, 1, 1, 7, 118, 26, },
+	{ 0, 1, 1, 7, 126, 28, },
+	{ 2, 1, 1, 7, 126, 26, },
+	{ 1, 1, 1, 7, 126, 26, },
+	{ 0, 1, 1, 7, 134, 26, },
+	{ 2, 1, 1, 7, 134, 26, },
+	{ 1, 1, 1, 7, 134, 26, },
+	{ 0, 1, 1, 7, 151, 30, },
+	{ 2, 1, 1, 7, 151, 26, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 30, },
+	{ 2, 1, 1, 7, 159, 26, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 30, },
+	{ 2, 1, 2, 4, 42, 32, },
+	{ 1, 1, 2, 4, 42, 32, },
+	{ 0, 1, 2, 4, 58, 28, },
+	{ 2, 1, 2, 4, 58, 32, },
+	{ 1, 1, 2, 4, 58, 32, },
+	{ 0, 1, 2, 4, 106, 30, },
+	{ 2, 1, 2, 4, 106, 32, },
+	{ 1, 1, 2, 4, 106, 32, },
+	{ 0, 1, 2, 4, 122, 34, },
+	{ 2, 1, 2, 4, 122, 32, },
+	{ 1, 1, 2, 4, 122, 32, },
+	{ 0, 1, 2, 4, 155, 36, },
+	{ 2, 1, 2, 4, 155, 32, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 28, },
+	{ 2, 1, 2, 5, 42, 30, },
+	{ 1, 1, 2, 5, 42, 30, },
+	{ 0, 1, 2, 5, 58, 26, },
+	{ 2, 1, 2, 5, 58, 30, },
+	{ 1, 1, 2, 5, 58, 30, },
+	{ 0, 1, 2, 5, 106, 28, },
+	{ 2, 1, 2, 5, 106, 30, },
+	{ 1, 1, 2, 5, 106, 30, },
+	{ 0, 1, 2, 5, 122, 32, },
+	{ 2, 1, 2, 5, 122, 30, },
+	{ 1, 1, 2, 5, 122, 30, },
+	{ 0, 1, 2, 5, 155, 34, },
+	{ 2, 1, 2, 5, 155, 30, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 26, },
+	{ 2, 1, 2, 8, 42, 28, },
+	{ 1, 1, 2, 8, 42, 28, },
+	{ 0, 1, 2, 8, 58, 24, },
+	{ 2, 1, 2, 8, 58, 28, },
+	{ 1, 1, 2, 8, 58, 28, },
+	{ 0, 1, 2, 8, 106, 26, },
+	{ 2, 1, 2, 8, 106, 28, },
+	{ 1, 1, 2, 8, 106, 28, },
+	{ 0, 1, 2, 8, 122, 30, },
+	{ 2, 1, 2, 8, 122, 28, },
+	{ 1, 1, 2, 8, 122, 28, },
+	{ 0, 1, 2, 8, 155, 32, },
+	{ 2, 1, 2, 8, 155, 28, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 24, },
+	{ 2, 1, 2, 9, 42, 26, },
+	{ 1, 1, 2, 9, 42, 26, },
+	{ 0, 1, 2, 9, 58, 22, },
+	{ 2, 1, 2, 9, 58, 26, },
+	{ 1, 1, 2, 9, 58, 26, },
+	{ 0, 1, 2, 9, 106, 24, },
+	{ 2, 1, 2, 9, 106, 26, },
+	{ 1, 1, 2, 9, 106, 26, },
+	{ 0, 1, 2, 9, 122, 28, },
+	{ 2, 1, 2, 9, 122, 26, },
+	{ 1, 1, 2, 9, 122, 26, },
+	{ 0, 1, 2, 9, 155, 30, },
+	{ 2, 1, 2, 9, 155, 26, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type0[] = {
+	{ 0, 0, 0, 0, 1, 32, },
+	{ 2, 0, 0, 0, 1, 32, },
+	{ 1, 0, 0, 0, 1, 32, },
+	{ 0, 0, 0, 0, 2, 32, },
+	{ 2, 0, 0, 0, 2, 32, },
+	{ 1, 0, 0, 0, 2, 32, },
+	{ 0, 0, 0, 0, 3, 32, },
+	{ 2, 0, 0, 0, 3, 32, },
+	{ 1, 0, 0, 0, 3, 32, },
+	{ 0, 0, 0, 0, 4, 32, },
+	{ 2, 0, 0, 0, 4, 32, },
+	{ 1, 0, 0, 0, 4, 32, },
+	{ 0, 0, 0, 0, 5, 32, },
+	{ 2, 0, 0, 0, 5, 32, },
+	{ 1, 0, 0, 0, 5, 32, },
+	{ 0, 0, 0, 0, 6, 32, },
+	{ 2, 0, 0, 0, 6, 32, },
+	{ 1, 0, 0, 0, 6, 32, },
+	{ 0, 0, 0, 0, 7, 32, },
+	{ 2, 0, 0, 0, 7, 32, },
+	{ 1, 0, 0, 0, 7, 32, },
+	{ 0, 0, 0, 0, 8, 32, },
+	{ 2, 0, 0, 0, 8, 32, },
+	{ 1, 0, 0, 0, 8, 32, },
+	{ 0, 0, 0, 0, 9, 32, },
+	{ 2, 0, 0, 0, 9, 32, },
+	{ 1, 0, 0, 0, 9, 32, },
+	{ 0, 0, 0, 0, 10, 32, },
+	{ 2, 0, 0, 0, 10, 32, },
+	{ 1, 0, 0, 0, 10, 32, },
+	{ 0, 0, 0, 0, 11, 32, },
+	{ 2, 0, 0, 0, 11, 32, },
+	{ 1, 0, 0, 0, 11, 32, },
+	{ 0, 0, 0, 0, 12, 24, },
+	{ 2, 0, 0, 0, 12, 32, },
+	{ 1, 0, 0, 0, 12, 32, },
+	{ 0, 0, 0, 0, 13, 16, },
+	{ 2, 0, 0, 0, 13, 32, },
+	{ 1, 0, 0, 0, 13, 32, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 32, },
+	{ 0, 0, 0, 1, 1, 28, },
+	{ 2, 0, 0, 1, 1, 32, },
+	{ 1, 0, 0, 1, 1, 32, },
+	{ 0, 0, 0, 1, 2, 32, },
+	{ 2, 0, 0, 1, 2, 32, },
+	{ 1, 0, 0, 1, 2, 32, },
+	{ 0, 0, 0, 1, 3, 32, },
+	{ 2, 0, 0, 1, 3, 32, },
+	{ 1, 0, 0, 1, 3, 32, },
+	{ 0, 0, 0, 1, 4, 32, },
+	{ 2, 0, 0, 1, 4, 32, },
+	{ 1, 0, 0, 1, 4, 32, },
+	{ 0, 0, 0, 1, 5, 32, },
+	{ 2, 0, 0, 1, 5, 32, },
+	{ 1, 0, 0, 1, 5, 32, },
+	{ 0, 0, 0, 1, 6, 32, },
+	{ 2, 0, 0, 1, 6, 32, },
+	{ 1, 0, 0, 1, 6, 32, },
+	{ 0, 0, 0, 1, 7, 32, },
+	{ 2, 0, 0, 1, 7, 32, },
+	{ 1, 0, 0, 1, 7, 32, },
+	{ 0, 0, 0, 1, 8, 32, },
+	{ 2, 0, 0, 1, 8, 32, },
+	{ 1, 0, 0, 1, 8, 32, },
+	{ 0, 0, 0, 1, 9, 32, },
+	{ 2, 0, 0, 1, 9, 32, },
+	{ 1, 0, 0, 1, 9, 32, },
+	{ 0, 0, 0, 1, 10, 32, },
+	{ 2, 0, 0, 1, 10, 32, },
+	{ 1, 0, 0, 1, 10, 32, },
+	{ 0, 0, 0, 1, 11, 28, },
+	{ 2, 0, 0, 1, 11, 32, },
+	{ 1, 0, 0, 1, 11, 32, },
+	{ 0, 0, 0, 1, 12, 18, },
+	{ 2, 0, 0, 1, 12, 32, },
+	{ 1, 0, 0, 1, 12, 32, },
+	{ 0, 0, 0, 1, 13, 8, },
+	{ 2, 0, 0, 1, 13, 32, },
+	{ 1, 0, 0, 1, 13, 32, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 26, },
+	{ 2, 0, 0, 2, 1, 32, },
+	{ 1, 0, 0, 2, 1, 32, },
+	{ 0, 0, 0, 2, 2, 32, },
+	{ 2, 0, 0, 2, 2, 32, },
+	{ 1, 0, 0, 2, 2, 32, },
+	{ 0, 0, 0, 2, 3, 32, },
+	{ 2, 0, 0, 2, 3, 32, },
+	{ 1, 0, 0, 2, 3, 32, },
+	{ 0, 0, 0, 2, 4, 32, },
+	{ 2, 0, 0, 2, 4, 32, },
+	{ 1, 0, 0, 2, 4, 32, },
+	{ 0, 0, 0, 2, 5, 32, },
+	{ 2, 0, 0, 2, 5, 32, },
+	{ 1, 0, 0, 2, 5, 32, },
+	{ 0, 0, 0, 2, 6, 32, },
+	{ 2, 0, 0, 2, 6, 32, },
+	{ 1, 0, 0, 2, 6, 32, },
+	{ 0, 0, 0, 2, 7, 32, },
+	{ 2, 0, 0, 2, 7, 32, },
+	{ 1, 0, 0, 2, 7, 32, },
+	{ 0, 0, 0, 2, 8, 32, },
+	{ 2, 0, 0, 2, 8, 32, },
+	{ 1, 0, 0, 2, 8, 32, },
+	{ 0, 0, 0, 2, 9, 32, },
+	{ 2, 0, 0, 2, 9, 32, },
+	{ 1, 0, 0, 2, 9, 32, },
+	{ 0, 0, 0, 2, 10, 32, },
+	{ 2, 0, 0, 2, 10, 32, },
+	{ 1, 0, 0, 2, 10, 32, },
+	{ 0, 0, 0, 2, 11, 26, },
+	{ 2, 0, 0, 2, 11, 32, },
+	{ 1, 0, 0, 2, 11, 32, },
+	{ 0, 0, 0, 2, 12, 16, },
+	{ 2, 0, 0, 2, 12, 32, },
+	{ 1, 0, 0, 2, 12, 32, },
+	{ 0, 0, 0, 2, 13, 6, },
+	{ 2, 0, 0, 2, 13, 32, },
+	{ 1, 0, 0, 2, 13, 32, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 24, },
+	{ 2, 0, 0, 3, 1, 30, },
+	{ 1, 0, 0, 3, 1, 30, },
+	{ 0, 0, 0, 3, 2, 30, },
+	{ 2, 0, 0, 3, 2, 30, },
+	{ 1, 0, 0, 3, 2, 30, },
+	{ 0, 0, 0, 3, 3, 30, },
+	{ 2, 0, 0, 3, 3, 30, },
+	{ 1, 0, 0, 3, 3, 30, },
+	{ 0, 0, 0, 3, 4, 30, },
+	{ 2, 0, 0, 3, 4, 30, },
+	{ 1, 0, 0, 3, 4, 30, },
+	{ 0, 0, 0, 3, 5, 30, },
+	{ 2, 0, 0, 3, 5, 30, },
+	{ 1, 0, 0, 3, 5, 30, },
+	{ 0, 0, 0, 3, 6, 30, },
+	{ 2, 0, 0, 3, 6, 30, },
+	{ 1, 0, 0, 3, 6, 30, },
+	{ 0, 0, 0, 3, 7, 30, },
+	{ 2, 0, 0, 3, 7, 30, },
+	{ 1, 0, 0, 3, 7, 30, },
+	{ 0, 0, 0, 3, 8, 30, },
+	{ 2, 0, 0, 3, 8, 30, },
+	{ 1, 0, 0, 3, 8, 30, },
+	{ 0, 0, 0, 3, 9, 30, },
+	{ 2, 0, 0, 3, 9, 30, },
+	{ 1, 0, 0, 3, 9, 30, },
+	{ 0, 0, 0, 3, 10, 30, },
+	{ 2, 0, 0, 3, 10, 30, },
+	{ 1, 0, 0, 3, 10, 30, },
+	{ 0, 0, 0, 3, 11, 24, },
+	{ 2, 0, 0, 3, 11, 30, },
+	{ 1, 0, 0, 3, 11, 30, },
+	{ 0, 0, 0, 3, 12, 14, },
+	{ 2, 0, 0, 3, 12, 30, },
+	{ 1, 0, 0, 3, 12, 30, },
+	{ 0, 0, 0, 3, 13, 4, },
+	{ 2, 0, 0, 3, 13, 30, },
+	{ 1, 0, 0, 3, 13, 30, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 22, },
+	{ 2, 0, 0, 6, 1, 28, },
+	{ 1, 0, 0, 6, 1, 28, },
+	{ 0, 0, 0, 6, 2, 28, },
+	{ 2, 0, 0, 6, 2, 28, },
+	{ 1, 0, 0, 6, 2, 28, },
+	{ 0, 0, 0, 6, 3, 28, },
+	{ 2, 0, 0, 6, 3, 28, },
+	{ 1, 0, 0, 6, 3, 28, },
+	{ 0, 0, 0, 6, 4, 28, },
+	{ 2, 0, 0, 6, 4, 28, },
+	{ 1, 0, 0, 6, 4, 28, },
+	{ 0, 0, 0, 6, 5, 28, },
+	{ 2, 0, 0, 6, 5, 28, },
+	{ 1, 0, 0, 6, 5, 28, },
+	{ 0, 0, 0, 6, 6, 28, },
+	{ 2, 0, 0, 6, 6, 28, },
+	{ 1, 0, 0, 6, 6, 28, },
+	{ 0, 0, 0, 6, 7, 28, },
+	{ 2, 0, 0, 6, 7, 28, },
+	{ 1, 0, 0, 6, 7, 28, },
+	{ 0, 0, 0, 6, 8, 28, },
+	{ 2, 0, 0, 6, 8, 28, },
+	{ 1, 0, 0, 6, 8, 28, },
+	{ 0, 0, 0, 6, 9, 28, },
+	{ 2, 0, 0, 6, 9, 28, },
+	{ 1, 0, 0, 6, 9, 28, },
+	{ 0, 0, 0, 6, 10, 28, },
+	{ 2, 0, 0, 6, 10, 28, },
+	{ 1, 0, 0, 6, 10, 28, },
+	{ 0, 0, 0, 6, 11, 22, },
+	{ 2, 0, 0, 6, 11, 28, },
+	{ 1, 0, 0, 6, 11, 28, },
+	{ 0, 0, 0, 6, 12, 14, },
+	{ 2, 0, 0, 6, 12, 28, },
+	{ 1, 0, 0, 6, 12, 28, },
+	{ 0, 0, 0, 6, 13, 4, },
+	{ 2, 0, 0, 6, 13, 28, },
+	{ 1, 0, 0, 6, 13, 28, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 20, },
+	{ 2, 0, 0, 7, 1, 26, },
+	{ 1, 0, 0, 7, 1, 26, },
+	{ 0, 0, 0, 7, 2, 26, },
+	{ 2, 0, 0, 7, 2, 26, },
+	{ 1, 0, 0, 7, 2, 26, },
+	{ 0, 0, 0, 7, 3, 26, },
+	{ 2, 0, 0, 7, 3, 26, },
+	{ 1, 0, 0, 7, 3, 26, },
+	{ 0, 0, 0, 7, 4, 26, },
+	{ 2, 0, 0, 7, 4, 26, },
+	{ 1, 0, 0, 7, 4, 26, },
+	{ 0, 0, 0, 7, 5, 26, },
+	{ 2, 0, 0, 7, 5, 26, },
+	{ 1, 0, 0, 7, 5, 26, },
+	{ 0, 0, 0, 7, 6, 26, },
+	{ 2, 0, 0, 7, 6, 26, },
+	{ 1, 0, 0, 7, 6, 26, },
+	{ 0, 0, 0, 7, 7, 26, },
+	{ 2, 0, 0, 7, 7, 26, },
+	{ 1, 0, 0, 7, 7, 26, },
+	{ 0, 0, 0, 7, 8, 26, },
+	{ 2, 0, 0, 7, 8, 26, },
+	{ 1, 0, 0, 7, 8, 26, },
+	{ 0, 0, 0, 7, 9, 26, },
+	{ 2, 0, 0, 7, 9, 26, },
+	{ 1, 0, 0, 7, 9, 26, },
+	{ 0, 0, 0, 7, 10, 26, },
+	{ 2, 0, 0, 7, 10, 26, },
+	{ 1, 0, 0, 7, 10, 26, },
+	{ 0, 0, 0, 7, 11, 20, },
+	{ 2, 0, 0, 7, 11, 26, },
+	{ 1, 0, 0, 7, 11, 26, },
+	{ 0, 0, 0, 7, 12, 14, },
+	{ 2, 0, 0, 7, 12, 26, },
+	{ 1, 0, 0, 7, 12, 26, },
+	{ 0, 0, 0, 7, 13, 4, },
+	{ 2, 0, 0, 7, 13, 26, },
+	{ 1, 0, 0, 7, 13, 26, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 26, },
+	{ 2, 0, 1, 2, 3, 32, },
+	{ 1, 0, 1, 2, 3, 32, },
+	{ 0, 0, 1, 2, 4, 32, },
+	{ 2, 0, 1, 2, 4, 32, },
+	{ 1, 0, 1, 2, 4, 32, },
+	{ 0, 0, 1, 2, 5, 32, },
+	{ 2, 0, 1, 2, 5, 32, },
+	{ 1, 0, 1, 2, 5, 32, },
+	{ 0, 0, 1, 2, 6, 32, },
+	{ 2, 0, 1, 2, 6, 32, },
+	{ 1, 0, 1, 2, 6, 32, },
+	{ 0, 0, 1, 2, 7, 32, },
+	{ 2, 0, 1, 2, 7, 32, },
+	{ 1, 0, 1, 2, 7, 32, },
+	{ 0, 0, 1, 2, 8, 32, },
+	{ 2, 0, 1, 2, 8, 32, },
+	{ 1, 0, 1, 2, 8, 32, },
+	{ 0, 0, 1, 2, 9, 32, },
+	{ 2, 0, 1, 2, 9, 32, },
+	{ 1, 0, 1, 2, 9, 32, },
+	{ 0, 0, 1, 2, 10, 32, },
+	{ 2, 0, 1, 2, 10, 32, },
+	{ 1, 0, 1, 2, 10, 32, },
+	{ 0, 0, 1, 2, 11, 26, },
+	{ 2, 0, 1, 2, 11, 32, },
+	{ 1, 0, 1, 2, 11, 32, },
+	{ 0, 0, 1, 2, 12, 16, },
+	{ 2, 0, 1, 2, 12, 32, },
+	{ 1, 0, 1, 2, 12, 32, },
+	{ 0, 0, 1, 2, 13, 10, },
+	{ 2, 0, 1, 2, 13, 32, },
+	{ 1, 0, 1, 2, 13, 32, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 24, },
+	{ 2, 0, 1, 3, 3, 30, },
+	{ 1, 0, 1, 3, 3, 30, },
+	{ 0, 0, 1, 3, 4, 30, },
+	{ 2, 0, 1, 3, 4, 30, },
+	{ 1, 0, 1, 3, 4, 30, },
+	{ 0, 0, 1, 3, 5, 30, },
+	{ 2, 0, 1, 3, 5, 30, },
+	{ 1, 0, 1, 3, 5, 30, },
+	{ 0, 0, 1, 3, 6, 30, },
+	{ 2, 0, 1, 3, 6, 30, },
+	{ 1, 0, 1, 3, 6, 30, },
+	{ 0, 0, 1, 3, 7, 30, },
+	{ 2, 0, 1, 3, 7, 30, },
+	{ 1, 0, 1, 3, 7, 30, },
+	{ 0, 0, 1, 3, 8, 30, },
+	{ 2, 0, 1, 3, 8, 30, },
+	{ 1, 0, 1, 3, 8, 30, },
+	{ 0, 0, 1, 3, 9, 30, },
+	{ 2, 0, 1, 3, 9, 30, },
+	{ 1, 0, 1, 3, 9, 30, },
+	{ 0, 0, 1, 3, 10, 30, },
+	{ 2, 0, 1, 3, 10, 30, },
+	{ 1, 0, 1, 3, 10, 30, },
+	{ 0, 0, 1, 3, 11, 24, },
+	{ 2, 0, 1, 3, 11, 30, },
+	{ 1, 0, 1, 3, 11, 30, },
+	{ 0, 0, 1, 3, 12, 14, },
+	{ 2, 0, 1, 3, 12, 30, },
+	{ 1, 0, 1, 3, 12, 30, },
+	{ 0, 0, 1, 3, 13, 8, },
+	{ 2, 0, 1, 3, 13, 30, },
+	{ 1, 0, 1, 3, 13, 30, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 22, },
+	{ 2, 0, 1, 6, 3, 28, },
+	{ 1, 0, 1, 6, 3, 28, },
+	{ 0, 0, 1, 6, 4, 28, },
+	{ 2, 0, 1, 6, 4, 28, },
+	{ 1, 0, 1, 6, 4, 28, },
+	{ 0, 0, 1, 6, 5, 28, },
+	{ 2, 0, 1, 6, 5, 28, },
+	{ 1, 0, 1, 6, 5, 28, },
+	{ 0, 0, 1, 6, 6, 28, },
+	{ 2, 0, 1, 6, 6, 28, },
+	{ 1, 0, 1, 6, 6, 28, },
+	{ 0, 0, 1, 6, 7, 28, },
+	{ 2, 0, 1, 6, 7, 28, },
+	{ 1, 0, 1, 6, 7, 28, },
+	{ 0, 0, 1, 6, 8, 28, },
+	{ 2, 0, 1, 6, 8, 28, },
+	{ 1, 0, 1, 6, 8, 28, },
+	{ 0, 0, 1, 6, 9, 28, },
+	{ 2, 0, 1, 6, 9, 28, },
+	{ 1, 0, 1, 6, 9, 28, },
+	{ 0, 0, 1, 6, 10, 28, },
+	{ 2, 0, 1, 6, 10, 28, },
+	{ 1, 0, 1, 6, 10, 28, },
+	{ 0, 0, 1, 6, 11, 22, },
+	{ 2, 0, 1, 6, 11, 28, },
+	{ 1, 0, 1, 6, 11, 28, },
+	{ 0, 0, 1, 6, 12, 14, },
+	{ 2, 0, 1, 6, 12, 28, },
+	{ 1, 0, 1, 6, 12, 28, },
+	{ 0, 0, 1, 6, 13, 8, },
+	{ 2, 0, 1, 6, 13, 28, },
+	{ 1, 0, 1, 6, 13, 28, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 20, },
+	{ 2, 0, 1, 7, 3, 26, },
+	{ 1, 0, 1, 7, 3, 26, },
+	{ 0, 0, 1, 7, 4, 26, },
+	{ 2, 0, 1, 7, 4, 26, },
+	{ 1, 0, 1, 7, 4, 26, },
+	{ 0, 0, 1, 7, 5, 26, },
+	{ 2, 0, 1, 7, 5, 26, },
+	{ 1, 0, 1, 7, 5, 26, },
+	{ 0, 0, 1, 7, 6, 26, },
+	{ 2, 0, 1, 7, 6, 26, },
+	{ 1, 0, 1, 7, 6, 26, },
+	{ 0, 0, 1, 7, 7, 26, },
+	{ 2, 0, 1, 7, 7, 26, },
+	{ 1, 0, 1, 7, 7, 26, },
+	{ 0, 0, 1, 7, 8, 26, },
+	{ 2, 0, 1, 7, 8, 26, },
+	{ 1, 0, 1, 7, 8, 26, },
+	{ 0, 0, 1, 7, 9, 26, },
+	{ 2, 0, 1, 7, 9, 26, },
+	{ 1, 0, 1, 7, 9, 26, },
+	{ 0, 0, 1, 7, 10, 26, },
+	{ 2, 0, 1, 7, 10, 26, },
+	{ 1, 0, 1, 7, 10, 26, },
+	{ 0, 0, 1, 7, 11, 20, },
+	{ 2, 0, 1, 7, 11, 26, },
+	{ 1, 0, 1, 7, 11, 26, },
+	{ 0, 0, 1, 7, 12, 14, },
+	{ 2, 0, 1, 7, 12, 26, },
+	{ 1, 0, 1, 7, 12, 26, },
+	{ 0, 0, 1, 7, 13, 8, },
+	{ 2, 0, 1, 7, 13, 26, },
+	{ 1, 0, 1, 7, 13, 26, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 28, },
+	{ 2, 1, 0, 1, 36, 32, },
+	{ 1, 1, 0, 1, 36, 32, },
+	{ 0, 1, 0, 1, 40, 32, },
+	{ 2, 1, 0, 1, 40, 32, },
+	{ 1, 1, 0, 1, 40, 32, },
+	{ 0, 1, 0, 1, 44, 32, },
+	{ 2, 1, 0, 1, 44, 32, },
+	{ 1, 1, 0, 1, 44, 32, },
+	{ 0, 1, 0, 1, 48, 32, },
+	{ 2, 1, 0, 1, 48, 32, },
+	{ 1, 1, 0, 1, 48, 32, },
+	{ 0, 1, 0, 1, 52, 32, },
+	{ 2, 1, 0, 1, 52, 32, },
+	{ 1, 1, 0, 1, 52, 32, },
+	{ 0, 1, 0, 1, 56, 32, },
+	{ 2, 1, 0, 1, 56, 32, },
+	{ 1, 1, 0, 1, 56, 32, },
+	{ 0, 1, 0, 1, 60, 32, },
+	{ 2, 1, 0, 1, 60, 32, },
+	{ 1, 1, 0, 1, 60, 32, },
+	{ 0, 1, 0, 1, 64, 28, },
+	{ 2, 1, 0, 1, 64, 32, },
+	{ 1, 1, 0, 1, 64, 32, },
+	{ 0, 1, 0, 1, 100, 28, },
+	{ 2, 1, 0, 1, 100, 32, },
+	{ 1, 1, 0, 1, 100, 32, },
+	{ 0, 1, 0, 1, 104, 32, },
+	{ 2, 1, 0, 1, 104, 32, },
+	{ 1, 1, 0, 1, 104, 32, },
+	{ 0, 1, 0, 1, 108, 32, },
+	{ 2, 1, 0, 1, 108, 32, },
+	{ 1, 1, 0, 1, 108, 32, },
+	{ 0, 1, 0, 1, 112, 32, },
+	{ 2, 1, 0, 1, 112, 32, },
+	{ 1, 1, 0, 1, 112, 32, },
+	{ 0, 1, 0, 1, 116, 32, },
+	{ 2, 1, 0, 1, 116, 32, },
+	{ 1, 1, 0, 1, 116, 32, },
+	{ 0, 1, 0, 1, 120, 32, },
+	{ 2, 1, 0, 1, 120, 32, },
+	{ 1, 1, 0, 1, 120, 32, },
+	{ 0, 1, 0, 1, 124, 32, },
+	{ 2, 1, 0, 1, 124, 32, },
+	{ 1, 1, 0, 1, 124, 32, },
+	{ 0, 1, 0, 1, 128, 32, },
+	{ 2, 1, 0, 1, 128, 32, },
+	{ 1, 1, 0, 1, 128, 32, },
+	{ 0, 1, 0, 1, 132, 32, },
+	{ 2, 1, 0, 1, 132, 32, },
+	{ 1, 1, 0, 1, 132, 32, },
+	{ 0, 1, 0, 1, 136, 32, },
+	{ 2, 1, 0, 1, 136, 32, },
+	{ 1, 1, 0, 1, 136, 32, },
+	{ 0, 1, 0, 1, 140, 28, },
+	{ 2, 1, 0, 1, 140, 32, },
+	{ 1, 1, 0, 1, 140, 32, },
+	{ 0, 1, 0, 1, 149, 28, },
+	{ 2, 1, 0, 1, 149, 32, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 32, },
+	{ 2, 1, 0, 1, 153, 32, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 32, },
+	{ 2, 1, 0, 1, 157, 32, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 32, },
+	{ 2, 1, 0, 1, 161, 32, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 32, },
+	{ 2, 1, 0, 1, 165, 32, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 26, },
+	{ 2, 1, 0, 2, 36, 32, },
+	{ 1, 1, 0, 2, 36, 32, },
+	{ 0, 1, 0, 2, 40, 32, },
+	{ 2, 1, 0, 2, 40, 32, },
+	{ 1, 1, 0, 2, 40, 32, },
+	{ 0, 1, 0, 2, 44, 32, },
+	{ 2, 1, 0, 2, 44, 32, },
+	{ 1, 1, 0, 2, 44, 32, },
+	{ 0, 1, 0, 2, 48, 32, },
+	{ 2, 1, 0, 2, 48, 32, },
+	{ 1, 1, 0, 2, 48, 32, },
+	{ 0, 1, 0, 2, 52, 32, },
+	{ 2, 1, 0, 2, 52, 32, },
+	{ 1, 1, 0, 2, 52, 32, },
+	{ 0, 1, 0, 2, 56, 32, },
+	{ 2, 1, 0, 2, 56, 32, },
+	{ 1, 1, 0, 2, 56, 32, },
+	{ 0, 1, 0, 2, 60, 32, },
+	{ 2, 1, 0, 2, 60, 32, },
+	{ 1, 1, 0, 2, 60, 32, },
+	{ 0, 1, 0, 2, 64, 26, },
+	{ 2, 1, 0, 2, 64, 32, },
+	{ 1, 1, 0, 2, 64, 32, },
+	{ 0, 1, 0, 2, 100, 26, },
+	{ 2, 1, 0, 2, 100, 32, },
+	{ 1, 1, 0, 2, 100, 32, },
+	{ 0, 1, 0, 2, 104, 32, },
+	{ 2, 1, 0, 2, 104, 32, },
+	{ 1, 1, 0, 2, 104, 32, },
+	{ 0, 1, 0, 2, 108, 32, },
+	{ 2, 1, 0, 2, 108, 32, },
+	{ 1, 1, 0, 2, 108, 32, },
+	{ 0, 1, 0, 2, 112, 32, },
+	{ 2, 1, 0, 2, 112, 32, },
+	{ 1, 1, 0, 2, 112, 32, },
+	{ 0, 1, 0, 2, 116, 32, },
+	{ 2, 1, 0, 2, 116, 32, },
+	{ 1, 1, 0, 2, 116, 32, },
+	{ 0, 1, 0, 2, 120, 32, },
+	{ 2, 1, 0, 2, 120, 32, },
+	{ 1, 1, 0, 2, 120, 32, },
+	{ 0, 1, 0, 2, 124, 32, },
+	{ 2, 1, 0, 2, 124, 32, },
+	{ 1, 1, 0, 2, 124, 32, },
+	{ 0, 1, 0, 2, 128, 32, },
+	{ 2, 1, 0, 2, 128, 32, },
+	{ 1, 1, 0, 2, 128, 32, },
+	{ 0, 1, 0, 2, 132, 32, },
+	{ 2, 1, 0, 2, 132, 32, },
+	{ 1, 1, 0, 2, 132, 32, },
+	{ 0, 1, 0, 2, 136, 32, },
+	{ 2, 1, 0, 2, 136, 32, },
+	{ 1, 1, 0, 2, 136, 32, },
+	{ 0, 1, 0, 2, 140, 26, },
+	{ 2, 1, 0, 2, 140, 32, },
+	{ 1, 1, 0, 2, 140, 32, },
+	{ 0, 1, 0, 2, 149, 26, },
+	{ 2, 1, 0, 2, 149, 32, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 32, },
+	{ 2, 1, 0, 2, 153, 32, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 32, },
+	{ 2, 1, 0, 2, 157, 32, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 32, },
+	{ 2, 1, 0, 2, 161, 32, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 32, },
+	{ 2, 1, 0, 2, 165, 32, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 24, },
+	{ 2, 1, 0, 3, 36, 28, },
+	{ 1, 1, 0, 3, 36, 28, },
+	{ 0, 1, 0, 3, 40, 28, },
+	{ 2, 1, 0, 3, 40, 28, },
+	{ 1, 1, 0, 3, 40, 28, },
+	{ 0, 1, 0, 3, 44, 28, },
+	{ 2, 1, 0, 3, 44, 28, },
+	{ 1, 1, 0, 3, 44, 28, },
+	{ 0, 1, 0, 3, 48, 28, },
+	{ 2, 1, 0, 3, 48, 28, },
+	{ 1, 1, 0, 3, 48, 28, },
+	{ 0, 1, 0, 3, 52, 28, },
+	{ 2, 1, 0, 3, 52, 28, },
+	{ 1, 1, 0, 3, 52, 28, },
+	{ 0, 1, 0, 3, 56, 28, },
+	{ 2, 1, 0, 3, 56, 28, },
+	{ 1, 1, 0, 3, 56, 28, },
+	{ 0, 1, 0, 3, 60, 28, },
+	{ 2, 1, 0, 3, 60, 28, },
+	{ 1, 1, 0, 3, 60, 28, },
+	{ 0, 1, 0, 3, 64, 24, },
+	{ 2, 1, 0, 3, 64, 28, },
+	{ 1, 1, 0, 3, 64, 28, },
+	{ 0, 1, 0, 3, 100, 24, },
+	{ 2, 1, 0, 3, 100, 28, },
+	{ 1, 1, 0, 3, 100, 28, },
+	{ 0, 1, 0, 3, 104, 28, },
+	{ 2, 1, 0, 3, 104, 28, },
+	{ 1, 1, 0, 3, 104, 28, },
+	{ 0, 1, 0, 3, 108, 28, },
+	{ 2, 1, 0, 3, 108, 28, },
+	{ 1, 1, 0, 3, 108, 28, },
+	{ 0, 1, 0, 3, 112, 28, },
+	{ 2, 1, 0, 3, 112, 28, },
+	{ 1, 1, 0, 3, 112, 28, },
+	{ 0, 1, 0, 3, 116, 28, },
+	{ 2, 1, 0, 3, 116, 28, },
+	{ 1, 1, 0, 3, 116, 28, },
+	{ 0, 1, 0, 3, 120, 28, },
+	{ 2, 1, 0, 3, 120, 28, },
+	{ 1, 1, 0, 3, 120, 28, },
+	{ 0, 1, 0, 3, 124, 28, },
+	{ 2, 1, 0, 3, 124, 28, },
+	{ 1, 1, 0, 3, 124, 28, },
+	{ 0, 1, 0, 3, 128, 28, },
+	{ 2, 1, 0, 3, 128, 28, },
+	{ 1, 1, 0, 3, 128, 28, },
+	{ 0, 1, 0, 3, 132, 28, },
+	{ 2, 1, 0, 3, 132, 28, },
+	{ 1, 1, 0, 3, 132, 28, },
+	{ 0, 1, 0, 3, 136, 28, },
+	{ 2, 1, 0, 3, 136, 28, },
+	{ 1, 1, 0, 3, 136, 28, },
+	{ 0, 1, 0, 3, 140, 24, },
+	{ 2, 1, 0, 3, 140, 28, },
+	{ 1, 1, 0, 3, 140, 28, },
+	{ 0, 1, 0, 3, 149, 24, },
+	{ 2, 1, 0, 3, 149, 28, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 28, },
+	{ 2, 1, 0, 3, 153, 28, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 28, },
+	{ 2, 1, 0, 3, 157, 28, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 28, },
+	{ 2, 1, 0, 3, 161, 28, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 28, },
+	{ 2, 1, 0, 3, 165, 28, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 22, },
+	{ 2, 1, 0, 6, 36, 26, },
+	{ 1, 1, 0, 6, 36, 26, },
+	{ 0, 1, 0, 6, 40, 26, },
+	{ 2, 1, 0, 6, 40, 26, },
+	{ 1, 1, 0, 6, 40, 26, },
+	{ 0, 1, 0, 6, 44, 26, },
+	{ 2, 1, 0, 6, 44, 26, },
+	{ 1, 1, 0, 6, 44, 26, },
+	{ 0, 1, 0, 6, 48, 26, },
+	{ 2, 1, 0, 6, 48, 26, },
+	{ 1, 1, 0, 6, 48, 26, },
+	{ 0, 1, 0, 6, 52, 26, },
+	{ 2, 1, 0, 6, 52, 26, },
+	{ 1, 1, 0, 6, 52, 26, },
+	{ 0, 1, 0, 6, 56, 26, },
+	{ 2, 1, 0, 6, 56, 26, },
+	{ 1, 1, 0, 6, 56, 26, },
+	{ 0, 1, 0, 6, 60, 26, },
+	{ 2, 1, 0, 6, 60, 26, },
+	{ 1, 1, 0, 6, 60, 26, },
+	{ 0, 1, 0, 6, 64, 22, },
+	{ 2, 1, 0, 6, 64, 26, },
+	{ 1, 1, 0, 6, 64, 26, },
+	{ 0, 1, 0, 6, 100, 22, },
+	{ 2, 1, 0, 6, 100, 26, },
+	{ 1, 1, 0, 6, 100, 26, },
+	{ 0, 1, 0, 6, 104, 26, },
+	{ 2, 1, 0, 6, 104, 26, },
+	{ 1, 1, 0, 6, 104, 26, },
+	{ 0, 1, 0, 6, 108, 26, },
+	{ 2, 1, 0, 6, 108, 26, },
+	{ 1, 1, 0, 6, 108, 26, },
+	{ 0, 1, 0, 6, 112, 26, },
+	{ 2, 1, 0, 6, 112, 26, },
+	{ 1, 1, 0, 6, 112, 26, },
+	{ 0, 1, 0, 6, 116, 26, },
+	{ 2, 1, 0, 6, 116, 26, },
+	{ 1, 1, 0, 6, 116, 26, },
+	{ 0, 1, 0, 6, 120, 26, },
+	{ 2, 1, 0, 6, 120, 26, },
+	{ 1, 1, 0, 6, 120, 26, },
+	{ 0, 1, 0, 6, 124, 26, },
+	{ 2, 1, 0, 6, 124, 26, },
+	{ 1, 1, 0, 6, 124, 26, },
+	{ 0, 1, 0, 6, 128, 26, },
+	{ 2, 1, 0, 6, 128, 26, },
+	{ 1, 1, 0, 6, 128, 26, },
+	{ 0, 1, 0, 6, 132, 26, },
+	{ 2, 1, 0, 6, 132, 26, },
+	{ 1, 1, 0, 6, 132, 26, },
+	{ 0, 1, 0, 6, 136, 26, },
+	{ 2, 1, 0, 6, 136, 26, },
+	{ 1, 1, 0, 6, 136, 26, },
+	{ 0, 1, 0, 6, 140, 22, },
+	{ 2, 1, 0, 6, 140, 26, },
+	{ 1, 1, 0, 6, 140, 26, },
+	{ 0, 1, 0, 6, 149, 22, },
+	{ 2, 1, 0, 6, 149, 26, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 26, },
+	{ 2, 1, 0, 6, 153, 26, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 26, },
+	{ 2, 1, 0, 6, 157, 26, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 26, },
+	{ 2, 1, 0, 6, 161, 26, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 26, },
+	{ 2, 1, 0, 6, 165, 26, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 20, },
+	{ 2, 1, 0, 7, 36, 24, },
+	{ 1, 1, 0, 7, 36, 24, },
+	{ 0, 1, 0, 7, 40, 24, },
+	{ 2, 1, 0, 7, 40, 24, },
+	{ 1, 1, 0, 7, 40, 24, },
+	{ 0, 1, 0, 7, 44, 24, },
+	{ 2, 1, 0, 7, 44, 24, },
+	{ 1, 1, 0, 7, 44, 24, },
+	{ 0, 1, 0, 7, 48, 24, },
+	{ 2, 1, 0, 7, 48, 24, },
+	{ 1, 1, 0, 7, 48, 24, },
+	{ 0, 1, 0, 7, 52, 24, },
+	{ 2, 1, 0, 7, 52, 24, },
+	{ 1, 1, 0, 7, 52, 24, },
+	{ 0, 1, 0, 7, 56, 24, },
+	{ 2, 1, 0, 7, 56, 24, },
+	{ 1, 1, 0, 7, 56, 24, },
+	{ 0, 1, 0, 7, 60, 24, },
+	{ 2, 1, 0, 7, 60, 24, },
+	{ 1, 1, 0, 7, 60, 24, },
+	{ 0, 1, 0, 7, 64, 20, },
+	{ 2, 1, 0, 7, 64, 24, },
+	{ 1, 1, 0, 7, 64, 24, },
+	{ 0, 1, 0, 7, 100, 20, },
+	{ 2, 1, 0, 7, 100, 24, },
+	{ 1, 1, 0, 7, 100, 24, },
+	{ 0, 1, 0, 7, 104, 24, },
+	{ 2, 1, 0, 7, 104, 24, },
+	{ 1, 1, 0, 7, 104, 24, },
+	{ 0, 1, 0, 7, 108, 24, },
+	{ 2, 1, 0, 7, 108, 24, },
+	{ 1, 1, 0, 7, 108, 24, },
+	{ 0, 1, 0, 7, 112, 24, },
+	{ 2, 1, 0, 7, 112, 24, },
+	{ 1, 1, 0, 7, 112, 24, },
+	{ 0, 1, 0, 7, 116, 24, },
+	{ 2, 1, 0, 7, 116, 24, },
+	{ 1, 1, 0, 7, 116, 24, },
+	{ 0, 1, 0, 7, 120, 24, },
+	{ 2, 1, 0, 7, 120, 24, },
+	{ 1, 1, 0, 7, 120, 24, },
+	{ 0, 1, 0, 7, 124, 24, },
+	{ 2, 1, 0, 7, 124, 24, },
+	{ 1, 1, 0, 7, 124, 24, },
+	{ 0, 1, 0, 7, 128, 24, },
+	{ 2, 1, 0, 7, 128, 24, },
+	{ 1, 1, 0, 7, 128, 24, },
+	{ 0, 1, 0, 7, 132, 24, },
+	{ 2, 1, 0, 7, 132, 24, },
+	{ 1, 1, 0, 7, 132, 24, },
+	{ 0, 1, 0, 7, 136, 24, },
+	{ 2, 1, 0, 7, 136, 24, },
+	{ 1, 1, 0, 7, 136, 24, },
+	{ 0, 1, 0, 7, 140, 20, },
+	{ 2, 1, 0, 7, 140, 24, },
+	{ 1, 1, 0, 7, 140, 24, },
+	{ 0, 1, 0, 7, 149, 20, },
+	{ 2, 1, 0, 7, 149, 24, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 24, },
+	{ 2, 1, 0, 7, 153, 24, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 24, },
+	{ 2, 1, 0, 7, 157, 24, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 24, },
+	{ 2, 1, 0, 7, 161, 24, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 24, },
+	{ 2, 1, 0, 7, 165, 24, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 26, },
+	{ 2, 1, 1, 2, 38, 32, },
+	{ 1, 1, 1, 2, 38, 32, },
+	{ 0, 1, 1, 2, 46, 32, },
+	{ 2, 1, 1, 2, 46, 32, },
+	{ 1, 1, 1, 2, 46, 32, },
+	{ 0, 1, 1, 2, 54, 32, },
+	{ 2, 1, 1, 2, 54, 32, },
+	{ 1, 1, 1, 2, 54, 32, },
+	{ 0, 1, 1, 2, 62, 26, },
+	{ 2, 1, 1, 2, 62, 32, },
+	{ 1, 1, 1, 2, 62, 32, },
+	{ 0, 1, 1, 2, 102, 26, },
+	{ 2, 1, 1, 2, 102, 32, },
+	{ 1, 1, 1, 2, 102, 32, },
+	{ 0, 1, 1, 2, 110, 32, },
+	{ 2, 1, 1, 2, 110, 32, },
+	{ 1, 1, 1, 2, 110, 32, },
+	{ 0, 1, 1, 2, 118, 32, },
+	{ 2, 1, 1, 2, 118, 32, },
+	{ 1, 1, 1, 2, 118, 32, },
+	{ 0, 1, 1, 2, 126, 32, },
+	{ 2, 1, 1, 2, 126, 32, },
+	{ 1, 1, 1, 2, 126, 32, },
+	{ 0, 1, 1, 2, 134, 32, },
+	{ 2, 1, 1, 2, 134, 32, },
+	{ 1, 1, 1, 2, 134, 32, },
+	{ 0, 1, 1, 2, 151, 26, },
+	{ 2, 1, 1, 2, 151, 32, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 32, },
+	{ 2, 1, 1, 2, 159, 32, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 24, },
+	{ 2, 1, 1, 3, 38, 28, },
+	{ 1, 1, 1, 3, 38, 28, },
+	{ 0, 1, 1, 3, 46, 28, },
+	{ 2, 1, 1, 3, 46, 28, },
+	{ 1, 1, 1, 3, 46, 28, },
+	{ 0, 1, 1, 3, 54, 28, },
+	{ 2, 1, 1, 3, 54, 28, },
+	{ 1, 1, 1, 3, 54, 28, },
+	{ 0, 1, 1, 3, 62, 24, },
+	{ 2, 1, 1, 3, 62, 28, },
+	{ 1, 1, 1, 3, 62, 28, },
+	{ 0, 1, 1, 3, 102, 24, },
+	{ 2, 1, 1, 3, 102, 28, },
+	{ 1, 1, 1, 3, 102, 28, },
+	{ 0, 1, 1, 3, 110, 28, },
+	{ 2, 1, 1, 3, 110, 28, },
+	{ 1, 1, 1, 3, 110, 28, },
+	{ 0, 1, 1, 3, 118, 28, },
+	{ 2, 1, 1, 3, 118, 28, },
+	{ 1, 1, 1, 3, 118, 28, },
+	{ 0, 1, 1, 3, 126, 28, },
+	{ 2, 1, 1, 3, 126, 28, },
+	{ 1, 1, 1, 3, 126, 28, },
+	{ 0, 1, 1, 3, 134, 28, },
+	{ 2, 1, 1, 3, 134, 28, },
+	{ 1, 1, 1, 3, 134, 28, },
+	{ 0, 1, 1, 3, 151, 24, },
+	{ 2, 1, 1, 3, 151, 28, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 28, },
+	{ 2, 1, 1, 3, 159, 28, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 20, },
+	{ 2, 1, 1, 6, 38, 26, },
+	{ 1, 1, 1, 6, 38, 26, },
+	{ 0, 1, 1, 6, 46, 26, },
+	{ 2, 1, 1, 6, 46, 26, },
+	{ 1, 1, 1, 6, 46, 26, },
+	{ 0, 1, 1, 6, 54, 26, },
+	{ 2, 1, 1, 6, 54, 26, },
+	{ 1, 1, 1, 6, 54, 26, },
+	{ 0, 1, 1, 6, 62, 20, },
+	{ 2, 1, 1, 6, 62, 26, },
+	{ 1, 1, 1, 6, 62, 26, },
+	{ 0, 1, 1, 6, 102, 20, },
+	{ 2, 1, 1, 6, 102, 26, },
+	{ 1, 1, 1, 6, 102, 26, },
+	{ 0, 1, 1, 6, 110, 26, },
+	{ 2, 1, 1, 6, 110, 26, },
+	{ 1, 1, 1, 6, 110, 26, },
+	{ 0, 1, 1, 6, 118, 26, },
+	{ 2, 1, 1, 6, 118, 26, },
+	{ 1, 1, 1, 6, 118, 26, },
+	{ 0, 1, 1, 6, 126, 26, },
+	{ 2, 1, 1, 6, 126, 26, },
+	{ 1, 1, 1, 6, 126, 26, },
+	{ 0, 1, 1, 6, 134, 26, },
+	{ 2, 1, 1, 6, 134, 26, },
+	{ 1, 1, 1, 6, 134, 26, },
+	{ 0, 1, 1, 6, 151, 20, },
+	{ 2, 1, 1, 6, 151, 26, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 26, },
+	{ 2, 1, 1, 6, 159, 26, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 18, },
+	{ 2, 1, 1, 7, 38, 24, },
+	{ 1, 1, 1, 7, 38, 24, },
+	{ 0, 1, 1, 7, 46, 24, },
+	{ 2, 1, 1, 7, 46, 24, },
+	{ 1, 1, 1, 7, 46, 24, },
+	{ 0, 1, 1, 7, 54, 24, },
+	{ 2, 1, 1, 7, 54, 24, },
+	{ 1, 1, 1, 7, 54, 24, },
+	{ 0, 1, 1, 7, 62, 18, },
+	{ 2, 1, 1, 7, 62, 24, },
+	{ 1, 1, 1, 7, 62, 24, },
+	{ 0, 1, 1, 7, 102, 18, },
+	{ 2, 1, 1, 7, 102, 24, },
+	{ 1, 1, 1, 7, 102, 24, },
+	{ 0, 1, 1, 7, 110, 24, },
+	{ 2, 1, 1, 7, 110, 24, },
+	{ 1, 1, 1, 7, 110, 24, },
+	{ 0, 1, 1, 7, 118, 24, },
+	{ 2, 1, 1, 7, 118, 24, },
+	{ 1, 1, 1, 7, 118, 24, },
+	{ 0, 1, 1, 7, 126, 24, },
+	{ 2, 1, 1, 7, 126, 24, },
+	{ 1, 1, 1, 7, 126, 24, },
+	{ 0, 1, 1, 7, 134, 24, },
+	{ 2, 1, 1, 7, 134, 24, },
+	{ 1, 1, 1, 7, 134, 24, },
+	{ 0, 1, 1, 7, 151, 18, },
+	{ 2, 1, 1, 7, 151, 24, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 24, },
+	{ 2, 1, 1, 7, 159, 24, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 22, },
+	{ 2, 1, 2, 4, 42, 30, },
+	{ 1, 1, 2, 4, 42, 30, },
+	{ 0, 1, 2, 4, 58, 22, },
+	{ 2, 1, 2, 4, 58, 30, },
+	{ 1, 1, 2, 4, 58, 30, },
+	{ 0, 1, 2, 4, 106, 22, },
+	{ 2, 1, 2, 4, 106, 30, },
+	{ 1, 1, 2, 4, 106, 30, },
+	{ 0, 1, 2, 4, 122, 30, },
+	{ 2, 1, 2, 4, 122, 30, },
+	{ 1, 1, 2, 4, 122, 30, },
+	{ 0, 1, 2, 4, 155, 22, },
+	{ 2, 1, 2, 4, 155, 30, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 20, },
+	{ 2, 1, 2, 5, 42, 28, },
+	{ 1, 1, 2, 5, 42, 28, },
+	{ 0, 1, 2, 5, 58, 20, },
+	{ 2, 1, 2, 5, 58, 28, },
+	{ 1, 1, 2, 5, 58, 28, },
+	{ 0, 1, 2, 5, 106, 20, },
+	{ 2, 1, 2, 5, 106, 28, },
+	{ 1, 1, 2, 5, 106, 28, },
+	{ 0, 1, 2, 5, 122, 28, },
+	{ 2, 1, 2, 5, 122, 28, },
+	{ 1, 1, 2, 5, 122, 28, },
+	{ 0, 1, 2, 5, 155, 20, },
+	{ 2, 1, 2, 5, 155, 28, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 18, },
+	{ 2, 1, 2, 8, 42, 26, },
+	{ 1, 1, 2, 8, 42, 26, },
+	{ 0, 1, 2, 8, 58, 18, },
+	{ 2, 1, 2, 8, 58, 26, },
+	{ 1, 1, 2, 8, 58, 26, },
+	{ 0, 1, 2, 8, 106, 18, },
+	{ 2, 1, 2, 8, 106, 26, },
+	{ 1, 1, 2, 8, 106, 26, },
+	{ 0, 1, 2, 8, 122, 26, },
+	{ 2, 1, 2, 8, 122, 26, },
+	{ 1, 1, 2, 8, 122, 26, },
+	{ 0, 1, 2, 8, 155, 18, },
+	{ 2, 1, 2, 8, 155, 26, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 16, },
+	{ 2, 1, 2, 9, 42, 24, },
+	{ 1, 1, 2, 9, 42, 24, },
+	{ 0, 1, 2, 9, 58, 16, },
+	{ 2, 1, 2, 9, 58, 24, },
+	{ 1, 1, 2, 9, 58, 24, },
+	{ 0, 1, 2, 9, 106, 16, },
+	{ 2, 1, 2, 9, 106, 24, },
+	{ 1, 1, 2, 9, 106, 24, },
+	{ 0, 1, 2, 9, 122, 24, },
+	{ 2, 1, 2, 9, 122, 24, },
+	{ 1, 1, 2, 9, 122, 24, },
+	{ 0, 1, 2, 9, 155, 16, },
+	{ 2, 1, 2, 9, 155, 24, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type0);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type1[] = {
+		{ 0, 0, 0, 0, 1, 34, },
+	{ 2, 0, 0, 0, 1, 32, },
+	{ 1, 0, 0, 0, 1, 32, },
+	{ 0, 0, 0, 0, 2, 34, },
+	{ 2, 0, 0, 0, 2, 32, },
+	{ 1, 0, 0, 0, 2, 32, },
+	{ 0, 0, 0, 0, 3, 34, },
+	{ 2, 0, 0, 0, 3, 32, },
+	{ 1, 0, 0, 0, 3, 32, },
+	{ 0, 0, 0, 0, 4, 34, },
+	{ 2, 0, 0, 0, 4, 32, },
+	{ 1, 0, 0, 0, 4, 32, },
+	{ 0, 0, 0, 0, 5, 34, },
+	{ 2, 0, 0, 0, 5, 32, },
+	{ 1, 0, 0, 0, 5, 32, },
+	{ 0, 0, 0, 0, 6, 34, },
+	{ 2, 0, 0, 0, 6, 32, },
+	{ 1, 0, 0, 0, 6, 32, },
+	{ 0, 0, 0, 0, 7, 34, },
+	{ 2, 0, 0, 0, 7, 32, },
+	{ 1, 0, 0, 0, 7, 32, },
+	{ 0, 0, 0, 0, 8, 34, },
+	{ 2, 0, 0, 0, 8, 32, },
+	{ 1, 0, 0, 0, 8, 32, },
+	{ 0, 0, 0, 0, 9, 34, },
+	{ 2, 0, 0, 0, 9, 32, },
+	{ 1, 0, 0, 0, 9, 32, },
+	{ 0, 0, 0, 0, 10, 34, },
+	{ 2, 0, 0, 0, 10, 32, },
+	{ 1, 0, 0, 0, 10, 32, },
+	{ 0, 0, 0, 0, 11, 34, },
+	{ 2, 0, 0, 0, 11, 32, },
+	{ 1, 0, 0, 0, 11, 32, },
+	{ 0, 0, 0, 0, 12, 24, },
+	{ 2, 0, 0, 0, 12, 32, },
+	{ 1, 0, 0, 0, 12, 32, },
+	{ 0, 0, 0, 0, 13, 16, },
+	{ 2, 0, 0, 0, 13, 32, },
+	{ 1, 0, 0, 0, 13, 32, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 32, },
+	{ 0, 0, 0, 1, 1, 30, },
+	{ 2, 0, 0, 1, 1, 32, },
+	{ 1, 0, 0, 1, 1, 32, },
+	{ 0, 0, 0, 1, 2, 32, },
+	{ 2, 0, 0, 1, 2, 32, },
+	{ 1, 0, 0, 1, 2, 32, },
+	{ 0, 0, 0, 1, 3, 32, },
+	{ 2, 0, 0, 1, 3, 32, },
+	{ 1, 0, 0, 1, 3, 32, },
+	{ 0, 0, 0, 1, 4, 32, },
+	{ 2, 0, 0, 1, 4, 32, },
+	{ 1, 0, 0, 1, 4, 32, },
+	{ 0, 0, 0, 1, 5, 32, },
+	{ 2, 0, 0, 1, 5, 32, },
+	{ 1, 0, 0, 1, 5, 32, },
+	{ 0, 0, 0, 1, 6, 32, },
+	{ 2, 0, 0, 1, 6, 32, },
+	{ 1, 0, 0, 1, 6, 32, },
+	{ 0, 0, 0, 1, 7, 32, },
+	{ 2, 0, 0, 1, 7, 32, },
+	{ 1, 0, 0, 1, 7, 32, },
+	{ 0, 0, 0, 1, 8, 32, },
+	{ 2, 0, 0, 1, 8, 32, },
+	{ 1, 0, 0, 1, 8, 32, },
+	{ 0, 0, 0, 1, 9, 32, },
+	{ 2, 0, 0, 1, 9, 32, },
+	{ 1, 0, 0, 1, 9, 32, },
+	{ 0, 0, 0, 1, 10, 32, },
+	{ 2, 0, 0, 1, 10, 32, },
+	{ 1, 0, 0, 1, 10, 32, },
+	{ 0, 0, 0, 1, 11, 30, },
+	{ 2, 0, 0, 1, 11, 32, },
+	{ 1, 0, 0, 1, 11, 32, },
+	{ 0, 0, 0, 1, 12, 18, },
+	{ 2, 0, 0, 1, 12, 32, },
+	{ 1, 0, 0, 1, 12, 32, },
+	{ 0, 0, 0, 1, 13, 8, },
+	{ 2, 0, 0, 1, 13, 32, },
+	{ 1, 0, 0, 1, 13, 32, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 28, },
+	{ 2, 0, 0, 2, 1, 32, },
+	{ 1, 0, 0, 2, 1, 32, },
+	{ 0, 0, 0, 2, 2, 32, },
+	{ 2, 0, 0, 2, 2, 32, },
+	{ 1, 0, 0, 2, 2, 32, },
+	{ 0, 0, 0, 2, 3, 32, },
+	{ 2, 0, 0, 2, 3, 32, },
+	{ 1, 0, 0, 2, 3, 32, },
+	{ 0, 0, 0, 2, 4, 32, },
+	{ 2, 0, 0, 2, 4, 32, },
+	{ 1, 0, 0, 2, 4, 32, },
+	{ 0, 0, 0, 2, 5, 32, },
+	{ 2, 0, 0, 2, 5, 32, },
+	{ 1, 0, 0, 2, 5, 32, },
+	{ 0, 0, 0, 2, 6, 32, },
+	{ 2, 0, 0, 2, 6, 32, },
+	{ 1, 0, 0, 2, 6, 32, },
+	{ 0, 0, 0, 2, 7, 32, },
+	{ 2, 0, 0, 2, 7, 32, },
+	{ 1, 0, 0, 2, 7, 32, },
+	{ 0, 0, 0, 2, 8, 32, },
+	{ 2, 0, 0, 2, 8, 32, },
+	{ 1, 0, 0, 2, 8, 32, },
+	{ 0, 0, 0, 2, 9, 32, },
+	{ 2, 0, 0, 2, 9, 32, },
+	{ 1, 0, 0, 2, 9, 32, },
+	{ 0, 0, 0, 2, 10, 32, },
+	{ 2, 0, 0, 2, 10, 32, },
+	{ 1, 0, 0, 2, 10, 32, },
+	{ 0, 0, 0, 2, 11, 28, },
+	{ 2, 0, 0, 2, 11, 32, },
+	{ 1, 0, 0, 2, 11, 32, },
+	{ 0, 0, 0, 2, 12, 16, },
+	{ 2, 0, 0, 2, 12, 32, },
+	{ 1, 0, 0, 2, 12, 32, },
+	{ 0, 0, 0, 2, 13, 6, },
+	{ 2, 0, 0, 2, 13, 32, },
+	{ 1, 0, 0, 2, 13, 32, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 26, },
+	{ 2, 0, 0, 3, 1, 30, },
+	{ 1, 0, 0, 3, 1, 30, },
+	{ 0, 0, 0, 3, 2, 30, },
+	{ 2, 0, 0, 3, 2, 30, },
+	{ 1, 0, 0, 3, 2, 30, },
+	{ 0, 0, 0, 3, 3, 30, },
+	{ 2, 0, 0, 3, 3, 30, },
+	{ 1, 0, 0, 3, 3, 30, },
+	{ 0, 0, 0, 3, 4, 30, },
+	{ 2, 0, 0, 3, 4, 30, },
+	{ 1, 0, 0, 3, 4, 30, },
+	{ 0, 0, 0, 3, 5, 30, },
+	{ 2, 0, 0, 3, 5, 30, },
+	{ 1, 0, 0, 3, 5, 30, },
+	{ 0, 0, 0, 3, 6, 30, },
+	{ 2, 0, 0, 3, 6, 30, },
+	{ 1, 0, 0, 3, 6, 30, },
+	{ 0, 0, 0, 3, 7, 30, },
+	{ 2, 0, 0, 3, 7, 30, },
+	{ 1, 0, 0, 3, 7, 30, },
+	{ 0, 0, 0, 3, 8, 30, },
+	{ 2, 0, 0, 3, 8, 30, },
+	{ 1, 0, 0, 3, 8, 30, },
+	{ 0, 0, 0, 3, 9, 30, },
+	{ 2, 0, 0, 3, 9, 30, },
+	{ 1, 0, 0, 3, 9, 30, },
+	{ 0, 0, 0, 3, 10, 30, },
+	{ 2, 0, 0, 3, 10, 30, },
+	{ 1, 0, 0, 3, 10, 30, },
+	{ 0, 0, 0, 3, 11, 26, },
+	{ 2, 0, 0, 3, 11, 30, },
+	{ 1, 0, 0, 3, 11, 30, },
+	{ 0, 0, 0, 3, 12, 14, },
+	{ 2, 0, 0, 3, 12, 30, },
+	{ 1, 0, 0, 3, 12, 30, },
+	{ 0, 0, 0, 3, 13, 4, },
+	{ 2, 0, 0, 3, 13, 30, },
+	{ 1, 0, 0, 3, 13, 30, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 24, },
+	{ 2, 0, 0, 6, 1, 28, },
+	{ 1, 0, 0, 6, 1, 28, },
+	{ 0, 0, 0, 6, 2, 28, },
+	{ 2, 0, 0, 6, 2, 28, },
+	{ 1, 0, 0, 6, 2, 28, },
+	{ 0, 0, 0, 6, 3, 28, },
+	{ 2, 0, 0, 6, 3, 28, },
+	{ 1, 0, 0, 6, 3, 28, },
+	{ 0, 0, 0, 6, 4, 28, },
+	{ 2, 0, 0, 6, 4, 28, },
+	{ 1, 0, 0, 6, 4, 28, },
+	{ 0, 0, 0, 6, 5, 28, },
+	{ 2, 0, 0, 6, 5, 28, },
+	{ 1, 0, 0, 6, 5, 28, },
+	{ 0, 0, 0, 6, 6, 28, },
+	{ 2, 0, 0, 6, 6, 28, },
+	{ 1, 0, 0, 6, 6, 28, },
+	{ 0, 0, 0, 6, 7, 28, },
+	{ 2, 0, 0, 6, 7, 28, },
+	{ 1, 0, 0, 6, 7, 28, },
+	{ 0, 0, 0, 6, 8, 28, },
+	{ 2, 0, 0, 6, 8, 28, },
+	{ 1, 0, 0, 6, 8, 28, },
+	{ 0, 0, 0, 6, 9, 28, },
+	{ 2, 0, 0, 6, 9, 28, },
+	{ 1, 0, 0, 6, 9, 28, },
+	{ 0, 0, 0, 6, 10, 28, },
+	{ 2, 0, 0, 6, 10, 28, },
+	{ 1, 0, 0, 6, 10, 28, },
+	{ 0, 0, 0, 6, 11, 24, },
+	{ 2, 0, 0, 6, 11, 28, },
+	{ 1, 0, 0, 6, 11, 28, },
+	{ 0, 0, 0, 6, 12, 14, },
+	{ 2, 0, 0, 6, 12, 28, },
+	{ 1, 0, 0, 6, 12, 28, },
+	{ 0, 0, 0, 6, 13, 4, },
+	{ 2, 0, 0, 6, 13, 28, },
+	{ 1, 0, 0, 6, 13, 28, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 22, },
+	{ 2, 0, 0, 7, 1, 26, },
+	{ 1, 0, 0, 7, 1, 26, },
+	{ 0, 0, 0, 7, 2, 26, },
+	{ 2, 0, 0, 7, 2, 26, },
+	{ 1, 0, 0, 7, 2, 26, },
+	{ 0, 0, 0, 7, 3, 26, },
+	{ 2, 0, 0, 7, 3, 26, },
+	{ 1, 0, 0, 7, 3, 26, },
+	{ 0, 0, 0, 7, 4, 26, },
+	{ 2, 0, 0, 7, 4, 26, },
+	{ 1, 0, 0, 7, 4, 26, },
+	{ 0, 0, 0, 7, 5, 26, },
+	{ 2, 0, 0, 7, 5, 26, },
+	{ 1, 0, 0, 7, 5, 26, },
+	{ 0, 0, 0, 7, 6, 26, },
+	{ 2, 0, 0, 7, 6, 26, },
+	{ 1, 0, 0, 7, 6, 26, },
+	{ 0, 0, 0, 7, 7, 26, },
+	{ 2, 0, 0, 7, 7, 26, },
+	{ 1, 0, 0, 7, 7, 26, },
+	{ 0, 0, 0, 7, 8, 26, },
+	{ 2, 0, 0, 7, 8, 26, },
+	{ 1, 0, 0, 7, 8, 26, },
+	{ 0, 0, 0, 7, 9, 26, },
+	{ 2, 0, 0, 7, 9, 26, },
+	{ 1, 0, 0, 7, 9, 26, },
+	{ 0, 0, 0, 7, 10, 26, },
+	{ 2, 0, 0, 7, 10, 26, },
+	{ 1, 0, 0, 7, 10, 26, },
+	{ 0, 0, 0, 7, 11, 22, },
+	{ 2, 0, 0, 7, 11, 26, },
+	{ 1, 0, 0, 7, 11, 26, },
+	{ 0, 0, 0, 7, 12, 14, },
+	{ 2, 0, 0, 7, 12, 26, },
+	{ 1, 0, 0, 7, 12, 26, },
+	{ 0, 0, 0, 7, 13, 4, },
+	{ 2, 0, 0, 7, 13, 26, },
+	{ 1, 0, 0, 7, 13, 26, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 28, },
+	{ 2, 0, 1, 2, 3, 32, },
+	{ 1, 0, 1, 2, 3, 32, },
+	{ 0, 0, 1, 2, 4, 32, },
+	{ 2, 0, 1, 2, 4, 32, },
+	{ 1, 0, 1, 2, 4, 32, },
+	{ 0, 0, 1, 2, 5, 32, },
+	{ 2, 0, 1, 2, 5, 32, },
+	{ 1, 0, 1, 2, 5, 32, },
+	{ 0, 0, 1, 2, 6, 32, },
+	{ 2, 0, 1, 2, 6, 32, },
+	{ 1, 0, 1, 2, 6, 32, },
+	{ 0, 0, 1, 2, 7, 32, },
+	{ 2, 0, 1, 2, 7, 32, },
+	{ 1, 0, 1, 2, 7, 32, },
+	{ 0, 0, 1, 2, 8, 32, },
+	{ 2, 0, 1, 2, 8, 32, },
+	{ 1, 0, 1, 2, 8, 32, },
+	{ 0, 0, 1, 2, 9, 32, },
+	{ 2, 0, 1, 2, 9, 32, },
+	{ 1, 0, 1, 2, 9, 32, },
+	{ 0, 0, 1, 2, 10, 32, },
+	{ 2, 0, 1, 2, 10, 32, },
+	{ 1, 0, 1, 2, 10, 32, },
+	{ 0, 0, 1, 2, 11, 28, },
+	{ 2, 0, 1, 2, 11, 32, },
+	{ 1, 0, 1, 2, 11, 32, },
+	{ 0, 0, 1, 2, 12, 16, },
+	{ 2, 0, 1, 2, 12, 32, },
+	{ 1, 0, 1, 2, 12, 32, },
+	{ 0, 0, 1, 2, 13, 10, },
+	{ 2, 0, 1, 2, 13, 32, },
+	{ 1, 0, 1, 2, 13, 32, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 26, },
+	{ 2, 0, 1, 3, 3, 30, },
+	{ 1, 0, 1, 3, 3, 30, },
+	{ 0, 0, 1, 3, 4, 30, },
+	{ 2, 0, 1, 3, 4, 30, },
+	{ 1, 0, 1, 3, 4, 30, },
+	{ 0, 0, 1, 3, 5, 30, },
+	{ 2, 0, 1, 3, 5, 30, },
+	{ 1, 0, 1, 3, 5, 30, },
+	{ 0, 0, 1, 3, 6, 30, },
+	{ 2, 0, 1, 3, 6, 30, },
+	{ 1, 0, 1, 3, 6, 30, },
+	{ 0, 0, 1, 3, 7, 30, },
+	{ 2, 0, 1, 3, 7, 30, },
+	{ 1, 0, 1, 3, 7, 30, },
+	{ 0, 0, 1, 3, 8, 30, },
+	{ 2, 0, 1, 3, 8, 30, },
+	{ 1, 0, 1, 3, 8, 30, },
+	{ 0, 0, 1, 3, 9, 30, },
+	{ 2, 0, 1, 3, 9, 30, },
+	{ 1, 0, 1, 3, 9, 30, },
+	{ 0, 0, 1, 3, 10, 30, },
+	{ 2, 0, 1, 3, 10, 30, },
+	{ 1, 0, 1, 3, 10, 30, },
+	{ 0, 0, 1, 3, 11, 26, },
+	{ 2, 0, 1, 3, 11, 30, },
+	{ 1, 0, 1, 3, 11, 30, },
+	{ 0, 0, 1, 3, 12, 14, },
+	{ 2, 0, 1, 3, 12, 30, },
+	{ 1, 0, 1, 3, 12, 30, },
+	{ 0, 0, 1, 3, 13, 8, },
+	{ 2, 0, 1, 3, 13, 30, },
+	{ 1, 0, 1, 3, 13, 30, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 24, },
+	{ 2, 0, 1, 6, 3, 28, },
+	{ 1, 0, 1, 6, 3, 28, },
+	{ 0, 0, 1, 6, 4, 28, },
+	{ 2, 0, 1, 6, 4, 28, },
+	{ 1, 0, 1, 6, 4, 28, },
+	{ 0, 0, 1, 6, 5, 28, },
+	{ 2, 0, 1, 6, 5, 28, },
+	{ 1, 0, 1, 6, 5, 28, },
+	{ 0, 0, 1, 6, 6, 28, },
+	{ 2, 0, 1, 6, 6, 28, },
+	{ 1, 0, 1, 6, 6, 28, },
+	{ 0, 0, 1, 6, 7, 28, },
+	{ 2, 0, 1, 6, 7, 28, },
+	{ 1, 0, 1, 6, 7, 28, },
+	{ 0, 0, 1, 6, 8, 28, },
+	{ 2, 0, 1, 6, 8, 28, },
+	{ 1, 0, 1, 6, 8, 28, },
+	{ 0, 0, 1, 6, 9, 28, },
+	{ 2, 0, 1, 6, 9, 28, },
+	{ 1, 0, 1, 6, 9, 28, },
+	{ 0, 0, 1, 6, 10, 28, },
+	{ 2, 0, 1, 6, 10, 28, },
+	{ 1, 0, 1, 6, 10, 28, },
+	{ 0, 0, 1, 6, 11, 24, },
+	{ 2, 0, 1, 6, 11, 28, },
+	{ 1, 0, 1, 6, 11, 28, },
+	{ 0, 0, 1, 6, 12, 14, },
+	{ 2, 0, 1, 6, 12, 28, },
+	{ 1, 0, 1, 6, 12, 28, },
+	{ 0, 0, 1, 6, 13, 8, },
+	{ 2, 0, 1, 6, 13, 28, },
+	{ 1, 0, 1, 6, 13, 28, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 22, },
+	{ 2, 0, 1, 7, 3, 26, },
+	{ 1, 0, 1, 7, 3, 26, },
+	{ 0, 0, 1, 7, 4, 26, },
+	{ 2, 0, 1, 7, 4, 26, },
+	{ 1, 0, 1, 7, 4, 26, },
+	{ 0, 0, 1, 7, 5, 26, },
+	{ 2, 0, 1, 7, 5, 26, },
+	{ 1, 0, 1, 7, 5, 26, },
+	{ 0, 0, 1, 7, 6, 26, },
+	{ 2, 0, 1, 7, 6, 26, },
+	{ 1, 0, 1, 7, 6, 26, },
+	{ 0, 0, 1, 7, 7, 26, },
+	{ 2, 0, 1, 7, 7, 26, },
+	{ 1, 0, 1, 7, 7, 26, },
+	{ 0, 0, 1, 7, 8, 26, },
+	{ 2, 0, 1, 7, 8, 26, },
+	{ 1, 0, 1, 7, 8, 26, },
+	{ 0, 0, 1, 7, 9, 26, },
+	{ 2, 0, 1, 7, 9, 26, },
+	{ 1, 0, 1, 7, 9, 26, },
+	{ 0, 0, 1, 7, 10, 26, },
+	{ 2, 0, 1, 7, 10, 26, },
+	{ 1, 0, 1, 7, 10, 26, },
+	{ 0, 0, 1, 7, 11, 22, },
+	{ 2, 0, 1, 7, 11, 26, },
+	{ 1, 0, 1, 7, 11, 26, },
+	{ 0, 0, 1, 7, 12, 14, },
+	{ 2, 0, 1, 7, 12, 26, },
+	{ 1, 0, 1, 7, 12, 26, },
+	{ 0, 0, 1, 7, 13, 8, },
+	{ 2, 0, 1, 7, 13, 26, },
+	{ 1, 0, 1, 7, 13, 26, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 28, },
+	{ 2, 1, 0, 1, 36, 32, },
+	{ 1, 1, 0, 1, 36, 32, },
+	{ 0, 1, 0, 1, 40, 32, },
+	{ 2, 1, 0, 1, 40, 32, },
+	{ 1, 1, 0, 1, 40, 32, },
+	{ 0, 1, 0, 1, 44, 32, },
+	{ 2, 1, 0, 1, 44, 32, },
+	{ 1, 1, 0, 1, 44, 32, },
+	{ 0, 1, 0, 1, 48, 32, },
+	{ 2, 1, 0, 1, 48, 32, },
+	{ 1, 1, 0, 1, 48, 32, },
+	{ 0, 1, 0, 1, 52, 32, },
+	{ 2, 1, 0, 1, 52, 32, },
+	{ 1, 1, 0, 1, 52, 32, },
+	{ 0, 1, 0, 1, 56, 32, },
+	{ 2, 1, 0, 1, 56, 32, },
+	{ 1, 1, 0, 1, 56, 32, },
+	{ 0, 1, 0, 1, 60, 32, },
+	{ 2, 1, 0, 1, 60, 32, },
+	{ 1, 1, 0, 1, 60, 32, },
+	{ 0, 1, 0, 1, 64, 30, },
+	{ 2, 1, 0, 1, 64, 32, },
+	{ 1, 1, 0, 1, 64, 32, },
+	{ 0, 1, 0, 1, 100, 28, },
+	{ 2, 1, 0, 1, 100, 32, },
+	{ 1, 1, 0, 1, 100, 32, },
+	{ 0, 1, 0, 1, 104, 32, },
+	{ 2, 1, 0, 1, 104, 32, },
+	{ 1, 1, 0, 1, 104, 32, },
+	{ 0, 1, 0, 1, 108, 32, },
+	{ 2, 1, 0, 1, 108, 32, },
+	{ 1, 1, 0, 1, 108, 32, },
+	{ 0, 1, 0, 1, 112, 32, },
+	{ 2, 1, 0, 1, 112, 32, },
+	{ 1, 1, 0, 1, 112, 32, },
+	{ 0, 1, 0, 1, 116, 32, },
+	{ 2, 1, 0, 1, 116, 32, },
+	{ 1, 1, 0, 1, 116, 32, },
+	{ 0, 1, 0, 1, 120, 32, },
+	{ 2, 1, 0, 1, 120, 32, },
+	{ 1, 1, 0, 1, 120, 32, },
+	{ 0, 1, 0, 1, 124, 32, },
+	{ 2, 1, 0, 1, 124, 32, },
+	{ 1, 1, 0, 1, 124, 32, },
+	{ 0, 1, 0, 1, 128, 32, },
+	{ 2, 1, 0, 1, 128, 32, },
+	{ 1, 1, 0, 1, 128, 32, },
+	{ 0, 1, 0, 1, 132, 32, },
+	{ 2, 1, 0, 1, 132, 32, },
+	{ 1, 1, 0, 1, 132, 32, },
+	{ 0, 1, 0, 1, 136, 32, },
+	{ 2, 1, 0, 1, 136, 32, },
+	{ 1, 1, 0, 1, 136, 32, },
+	{ 0, 1, 0, 1, 140, 28, },
+	{ 2, 1, 0, 1, 140, 32, },
+	{ 1, 1, 0, 1, 140, 32, },
+	{ 0, 1, 0, 1, 149, 28, },
+	{ 2, 1, 0, 1, 149, 32, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 32, },
+	{ 2, 1, 0, 1, 153, 32, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 32, },
+	{ 2, 1, 0, 1, 157, 32, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 32, },
+	{ 2, 1, 0, 1, 161, 32, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 32, },
+	{ 2, 1, 0, 1, 165, 32, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 28, },
+	{ 2, 1, 0, 2, 36, 32, },
+	{ 1, 1, 0, 2, 36, 32, },
+	{ 0, 1, 0, 2, 40, 32, },
+	{ 2, 1, 0, 2, 40, 32, },
+	{ 1, 1, 0, 2, 40, 32, },
+	{ 0, 1, 0, 2, 44, 32, },
+	{ 2, 1, 0, 2, 44, 32, },
+	{ 1, 1, 0, 2, 44, 32, },
+	{ 0, 1, 0, 2, 48, 32, },
+	{ 2, 1, 0, 2, 48, 32, },
+	{ 1, 1, 0, 2, 48, 32, },
+	{ 0, 1, 0, 2, 52, 32, },
+	{ 2, 1, 0, 2, 52, 32, },
+	{ 1, 1, 0, 2, 52, 32, },
+	{ 0, 1, 0, 2, 56, 32, },
+	{ 2, 1, 0, 2, 56, 32, },
+	{ 1, 1, 0, 2, 56, 32, },
+	{ 0, 1, 0, 2, 60, 32, },
+	{ 2, 1, 0, 2, 60, 32, },
+	{ 1, 1, 0, 2, 60, 32, },
+	{ 0, 1, 0, 2, 64, 30, },
+	{ 2, 1, 0, 2, 64, 32, },
+	{ 1, 1, 0, 2, 64, 32, },
+	{ 0, 1, 0, 2, 100, 28, },
+	{ 2, 1, 0, 2, 100, 32, },
+	{ 1, 1, 0, 2, 100, 32, },
+	{ 0, 1, 0, 2, 104, 32, },
+	{ 2, 1, 0, 2, 104, 32, },
+	{ 1, 1, 0, 2, 104, 32, },
+	{ 0, 1, 0, 2, 108, 32, },
+	{ 2, 1, 0, 2, 108, 32, },
+	{ 1, 1, 0, 2, 108, 32, },
+	{ 0, 1, 0, 2, 112, 32, },
+	{ 2, 1, 0, 2, 112, 32, },
+	{ 1, 1, 0, 2, 112, 32, },
+	{ 0, 1, 0, 2, 116, 32, },
+	{ 2, 1, 0, 2, 116, 32, },
+	{ 1, 1, 0, 2, 116, 32, },
+	{ 0, 1, 0, 2, 120, 32, },
+	{ 2, 1, 0, 2, 120, 32, },
+	{ 1, 1, 0, 2, 120, 32, },
+	{ 0, 1, 0, 2, 124, 32, },
+	{ 2, 1, 0, 2, 124, 32, },
+	{ 1, 1, 0, 2, 124, 32, },
+	{ 0, 1, 0, 2, 128, 32, },
+	{ 2, 1, 0, 2, 128, 32, },
+	{ 1, 1, 0, 2, 128, 32, },
+	{ 0, 1, 0, 2, 132, 32, },
+	{ 2, 1, 0, 2, 132, 32, },
+	{ 1, 1, 0, 2, 132, 32, },
+	{ 0, 1, 0, 2, 136, 32, },
+	{ 2, 1, 0, 2, 136, 32, },
+	{ 1, 1, 0, 2, 136, 32, },
+	{ 0, 1, 0, 2, 140, 28, },
+	{ 2, 1, 0, 2, 140, 32, },
+	{ 1, 1, 0, 2, 140, 32, },
+	{ 0, 1, 0, 2, 149, 28, },
+	{ 2, 1, 0, 2, 149, 32, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 32, },
+	{ 2, 1, 0, 2, 153, 32, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 32, },
+	{ 2, 1, 0, 2, 157, 32, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 32, },
+	{ 2, 1, 0, 2, 161, 32, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 32, },
+	{ 2, 1, 0, 2, 165, 32, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 26, },
+	{ 2, 1, 0, 3, 36, 30, },
+	{ 1, 1, 0, 3, 36, 30, },
+	{ 0, 1, 0, 3, 40, 30, },
+	{ 2, 1, 0, 3, 40, 30, },
+	{ 1, 1, 0, 3, 40, 30, },
+	{ 0, 1, 0, 3, 44, 30, },
+	{ 2, 1, 0, 3, 44, 30, },
+	{ 1, 1, 0, 3, 44, 30, },
+	{ 0, 1, 0, 3, 48, 30, },
+	{ 2, 1, 0, 3, 48, 30, },
+	{ 1, 1, 0, 3, 48, 30, },
+	{ 0, 1, 0, 3, 52, 30, },
+	{ 2, 1, 0, 3, 52, 30, },
+	{ 1, 1, 0, 3, 52, 30, },
+	{ 0, 1, 0, 3, 56, 30, },
+	{ 2, 1, 0, 3, 56, 30, },
+	{ 1, 1, 0, 3, 56, 30, },
+	{ 0, 1, 0, 3, 60, 30, },
+	{ 2, 1, 0, 3, 60, 30, },
+	{ 1, 1, 0, 3, 60, 30, },
+	{ 0, 1, 0, 3, 64, 28, },
+	{ 2, 1, 0, 3, 64, 30, },
+	{ 1, 1, 0, 3, 64, 30, },
+	{ 0, 1, 0, 3, 100, 28, },
+	{ 2, 1, 0, 3, 100, 30, },
+	{ 1, 1, 0, 3, 100, 30, },
+	{ 0, 1, 0, 3, 104, 30, },
+	{ 2, 1, 0, 3, 104, 30, },
+	{ 1, 1, 0, 3, 104, 30, },
+	{ 0, 1, 0, 3, 108, 30, },
+	{ 2, 1, 0, 3, 108, 30, },
+	{ 1, 1, 0, 3, 108, 30, },
+	{ 0, 1, 0, 3, 112, 30, },
+	{ 2, 1, 0, 3, 112, 30, },
+	{ 1, 1, 0, 3, 112, 30, },
+	{ 0, 1, 0, 3, 116, 30, },
+	{ 2, 1, 0, 3, 116, 30, },
+	{ 1, 1, 0, 3, 116, 30, },
+	{ 0, 1, 0, 3, 120, 30, },
+	{ 2, 1, 0, 3, 120, 30, },
+	{ 1, 1, 0, 3, 120, 30, },
+	{ 0, 1, 0, 3, 124, 30, },
+	{ 2, 1, 0, 3, 124, 30, },
+	{ 1, 1, 0, 3, 124, 30, },
+	{ 0, 1, 0, 3, 128, 30, },
+	{ 2, 1, 0, 3, 128, 30, },
+	{ 1, 1, 0, 3, 128, 30, },
+	{ 0, 1, 0, 3, 132, 30, },
+	{ 2, 1, 0, 3, 132, 30, },
+	{ 1, 1, 0, 3, 132, 30, },
+	{ 0, 1, 0, 3, 136, 30, },
+	{ 2, 1, 0, 3, 136, 30, },
+	{ 1, 1, 0, 3, 136, 30, },
+	{ 0, 1, 0, 3, 140, 26, },
+	{ 2, 1, 0, 3, 140, 30, },
+	{ 1, 1, 0, 3, 140, 30, },
+	{ 0, 1, 0, 3, 149, 26, },
+	{ 2, 1, 0, 3, 149, 30, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 30, },
+	{ 2, 1, 0, 3, 153, 30, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 30, },
+	{ 2, 1, 0, 3, 157, 30, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 30, },
+	{ 2, 1, 0, 3, 161, 30, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 30, },
+	{ 2, 1, 0, 3, 165, 30, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 24, },
+	{ 2, 1, 0, 6, 36, 28, },
+	{ 1, 1, 0, 6, 36, 28, },
+	{ 0, 1, 0, 6, 40, 28, },
+	{ 2, 1, 0, 6, 40, 28, },
+	{ 1, 1, 0, 6, 40, 28, },
+	{ 0, 1, 0, 6, 44, 28, },
+	{ 2, 1, 0, 6, 44, 28, },
+	{ 1, 1, 0, 6, 44, 28, },
+	{ 0, 1, 0, 6, 48, 28, },
+	{ 2, 1, 0, 6, 48, 28, },
+	{ 1, 1, 0, 6, 48, 28, },
+	{ 0, 1, 0, 6, 52, 28, },
+	{ 2, 1, 0, 6, 52, 28, },
+	{ 1, 1, 0, 6, 52, 28, },
+	{ 0, 1, 0, 6, 56, 28, },
+	{ 2, 1, 0, 6, 56, 28, },
+	{ 1, 1, 0, 6, 56, 28, },
+	{ 0, 1, 0, 6, 60, 28, },
+	{ 2, 1, 0, 6, 60, 28, },
+	{ 1, 1, 0, 6, 60, 28, },
+	{ 0, 1, 0, 6, 64, 26, },
+	{ 2, 1, 0, 6, 64, 28, },
+	{ 1, 1, 0, 6, 64, 28, },
+	{ 0, 1, 0, 6, 100, 24, },
+	{ 2, 1, 0, 6, 100, 28, },
+	{ 1, 1, 0, 6, 100, 28, },
+	{ 0, 1, 0, 6, 104, 28, },
+	{ 2, 1, 0, 6, 104, 28, },
+	{ 1, 1, 0, 6, 104, 28, },
+	{ 0, 1, 0, 6, 108, 28, },
+	{ 2, 1, 0, 6, 108, 28, },
+	{ 1, 1, 0, 6, 108, 28, },
+	{ 0, 1, 0, 6, 112, 28, },
+	{ 2, 1, 0, 6, 112, 28, },
+	{ 1, 1, 0, 6, 112, 28, },
+	{ 0, 1, 0, 6, 116, 28, },
+	{ 2, 1, 0, 6, 116, 28, },
+	{ 1, 1, 0, 6, 116, 28, },
+	{ 0, 1, 0, 6, 120, 28, },
+	{ 2, 1, 0, 6, 120, 28, },
+	{ 1, 1, 0, 6, 120, 28, },
+	{ 0, 1, 0, 6, 124, 28, },
+	{ 2, 1, 0, 6, 124, 28, },
+	{ 1, 1, 0, 6, 124, 28, },
+	{ 0, 1, 0, 6, 128, 28, },
+	{ 2, 1, 0, 6, 128, 28, },
+	{ 1, 1, 0, 6, 128, 28, },
+	{ 0, 1, 0, 6, 132, 28, },
+	{ 2, 1, 0, 6, 132, 28, },
+	{ 1, 1, 0, 6, 132, 28, },
+	{ 0, 1, 0, 6, 136, 28, },
+	{ 2, 1, 0, 6, 136, 28, },
+	{ 1, 1, 0, 6, 136, 28, },
+	{ 0, 1, 0, 6, 140, 24, },
+	{ 2, 1, 0, 6, 140, 28, },
+	{ 1, 1, 0, 6, 140, 28, },
+	{ 0, 1, 0, 6, 149, 24, },
+	{ 2, 1, 0, 6, 149, 28, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 28, },
+	{ 2, 1, 0, 6, 153, 28, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 28, },
+	{ 2, 1, 0, 6, 157, 28, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 28, },
+	{ 2, 1, 0, 6, 161, 28, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 28, },
+	{ 2, 1, 0, 6, 165, 28, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 22, },
+	{ 2, 1, 0, 7, 36, 26, },
+	{ 1, 1, 0, 7, 36, 26, },
+	{ 0, 1, 0, 7, 40, 26, },
+	{ 2, 1, 0, 7, 40, 26, },
+	{ 1, 1, 0, 7, 40, 26, },
+	{ 0, 1, 0, 7, 44, 26, },
+	{ 2, 1, 0, 7, 44, 26, },
+	{ 1, 1, 0, 7, 44, 26, },
+	{ 0, 1, 0, 7, 48, 26, },
+	{ 2, 1, 0, 7, 48, 26, },
+	{ 1, 1, 0, 7, 48, 26, },
+	{ 0, 1, 0, 7, 52, 26, },
+	{ 2, 1, 0, 7, 52, 26, },
+	{ 1, 1, 0, 7, 52, 26, },
+	{ 0, 1, 0, 7, 56, 26, },
+	{ 2, 1, 0, 7, 56, 26, },
+	{ 1, 1, 0, 7, 56, 26, },
+	{ 0, 1, 0, 7, 60, 26, },
+	{ 2, 1, 0, 7, 60, 26, },
+	{ 1, 1, 0, 7, 60, 26, },
+	{ 0, 1, 0, 7, 64, 24, },
+	{ 2, 1, 0, 7, 64, 26, },
+	{ 1, 1, 0, 7, 64, 26, },
+	{ 0, 1, 0, 7, 100, 22, },
+	{ 2, 1, 0, 7, 100, 26, },
+	{ 1, 1, 0, 7, 100, 26, },
+	{ 0, 1, 0, 7, 104, 26, },
+	{ 2, 1, 0, 7, 104, 26, },
+	{ 1, 1, 0, 7, 104, 26, },
+	{ 0, 1, 0, 7, 108, 26, },
+	{ 2, 1, 0, 7, 108, 26, },
+	{ 1, 1, 0, 7, 108, 26, },
+	{ 0, 1, 0, 7, 112, 26, },
+	{ 2, 1, 0, 7, 112, 26, },
+	{ 1, 1, 0, 7, 112, 26, },
+	{ 0, 1, 0, 7, 116, 26, },
+	{ 2, 1, 0, 7, 116, 26, },
+	{ 1, 1, 0, 7, 116, 26, },
+	{ 0, 1, 0, 7, 120, 26, },
+	{ 2, 1, 0, 7, 120, 26, },
+	{ 1, 1, 0, 7, 120, 26, },
+	{ 0, 1, 0, 7, 124, 26, },
+	{ 2, 1, 0, 7, 124, 26, },
+	{ 1, 1, 0, 7, 124, 26, },
+	{ 0, 1, 0, 7, 128, 26, },
+	{ 2, 1, 0, 7, 128, 26, },
+	{ 1, 1, 0, 7, 128, 26, },
+	{ 0, 1, 0, 7, 132, 26, },
+	{ 2, 1, 0, 7, 132, 26, },
+	{ 1, 1, 0, 7, 132, 26, },
+	{ 0, 1, 0, 7, 136, 26, },
+	{ 2, 1, 0, 7, 136, 26, },
+	{ 1, 1, 0, 7, 136, 26, },
+	{ 0, 1, 0, 7, 140, 22, },
+	{ 2, 1, 0, 7, 140, 26, },
+	{ 1, 1, 0, 7, 140, 26, },
+	{ 0, 1, 0, 7, 149, 22, },
+	{ 2, 1, 0, 7, 149, 26, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 26, },
+	{ 2, 1, 0, 7, 153, 26, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 26, },
+	{ 2, 1, 0, 7, 157, 26, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 26, },
+	{ 2, 1, 0, 7, 161, 26, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 26, },
+	{ 2, 1, 0, 7, 165, 26, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 28, },
+	{ 2, 1, 1, 2, 38, 32, },
+	{ 1, 1, 1, 2, 38, 32, },
+	{ 0, 1, 1, 2, 46, 32, },
+	{ 2, 1, 1, 2, 46, 32, },
+	{ 1, 1, 1, 2, 46, 32, },
+	{ 0, 1, 1, 2, 54, 32, },
+	{ 2, 1, 1, 2, 54, 32, },
+	{ 1, 1, 1, 2, 54, 32, },
+	{ 0, 1, 1, 2, 62, 28, },
+	{ 2, 1, 1, 2, 62, 32, },
+	{ 1, 1, 1, 2, 62, 32, },
+	{ 0, 1, 1, 2, 102, 28, },
+	{ 2, 1, 1, 2, 102, 32, },
+	{ 1, 1, 1, 2, 102, 32, },
+	{ 0, 1, 1, 2, 110, 32, },
+	{ 2, 1, 1, 2, 110, 32, },
+	{ 1, 1, 1, 2, 110, 32, },
+	{ 0, 1, 1, 2, 118, 32, },
+	{ 2, 1, 1, 2, 118, 32, },
+	{ 1, 1, 1, 2, 118, 32, },
+	{ 0, 1, 1, 2, 126, 32, },
+	{ 2, 1, 1, 2, 126, 32, },
+	{ 1, 1, 1, 2, 126, 32, },
+	{ 0, 1, 1, 2, 134, 30, },
+	{ 2, 1, 1, 2, 134, 32, },
+	{ 1, 1, 1, 2, 134, 32, },
+	{ 0, 1, 1, 2, 151, 28, },
+	{ 2, 1, 1, 2, 151, 32, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 32, },
+	{ 2, 1, 1, 2, 159, 32, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 26, },
+	{ 2, 1, 1, 3, 38, 30, },
+	{ 1, 1, 1, 3, 38, 30, },
+	{ 0, 1, 1, 3, 46, 30, },
+	{ 2, 1, 1, 3, 46, 30, },
+	{ 1, 1, 1, 3, 46, 30, },
+	{ 0, 1, 1, 3, 54, 30, },
+	{ 2, 1, 1, 3, 54, 30, },
+	{ 1, 1, 1, 3, 54, 30, },
+	{ 0, 1, 1, 3, 62, 26, },
+	{ 2, 1, 1, 3, 62, 30, },
+	{ 1, 1, 1, 3, 62, 30, },
+	{ 0, 1, 1, 3, 102, 26, },
+	{ 2, 1, 1, 3, 102, 30, },
+	{ 1, 1, 1, 3, 102, 30, },
+	{ 0, 1, 1, 3, 110, 30, },
+	{ 2, 1, 1, 3, 110, 30, },
+	{ 1, 1, 1, 3, 110, 30, },
+	{ 0, 1, 1, 3, 118, 30, },
+	{ 2, 1, 1, 3, 118, 30, },
+	{ 1, 1, 1, 3, 118, 30, },
+	{ 0, 1, 1, 3, 126, 30, },
+	{ 2, 1, 1, 3, 126, 30, },
+	{ 1, 1, 1, 3, 126, 30, },
+	{ 0, 1, 1, 3, 134, 28, },
+	{ 2, 1, 1, 3, 134, 30, },
+	{ 1, 1, 1, 3, 134, 30, },
+	{ 0, 1, 1, 3, 151, 26, },
+	{ 2, 1, 1, 3, 151, 30, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 30, },
+	{ 2, 1, 1, 3, 159, 30, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 20, },
+	{ 2, 1, 1, 6, 38, 28, },
+	{ 1, 1, 1, 6, 38, 28, },
+	{ 0, 1, 1, 6, 46, 28, },
+	{ 2, 1, 1, 6, 46, 28, },
+	{ 1, 1, 1, 6, 46, 28, },
+	{ 0, 1, 1, 6, 54, 28, },
+	{ 2, 1, 1, 6, 54, 28, },
+	{ 1, 1, 1, 6, 54, 28, },
+	{ 0, 1, 1, 6, 62, 20, },
+	{ 2, 1, 1, 6, 62, 28, },
+	{ 1, 1, 1, 6, 62, 28, },
+	{ 0, 1, 1, 6, 102, 22, },
+	{ 2, 1, 1, 6, 102, 28, },
+	{ 1, 1, 1, 6, 102, 28, },
+	{ 0, 1, 1, 6, 110, 28, },
+	{ 2, 1, 1, 6, 110, 28, },
+	{ 1, 1, 1, 6, 110, 28, },
+	{ 0, 1, 1, 6, 118, 28, },
+	{ 2, 1, 1, 6, 118, 28, },
+	{ 1, 1, 1, 6, 118, 28, },
+	{ 0, 1, 1, 6, 126, 28, },
+	{ 2, 1, 1, 6, 126, 28, },
+	{ 1, 1, 1, 6, 126, 28, },
+	{ 0, 1, 1, 6, 134, 26, },
+	{ 2, 1, 1, 6, 134, 28, },
+	{ 1, 1, 1, 6, 134, 28, },
+	{ 0, 1, 1, 6, 151, 22, },
+	{ 2, 1, 1, 6, 151, 28, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 28, },
+	{ 2, 1, 1, 6, 159, 28, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 18, },
+	{ 2, 1, 1, 7, 38, 26, },
+	{ 1, 1, 1, 7, 38, 26, },
+	{ 0, 1, 1, 7, 46, 26, },
+	{ 2, 1, 1, 7, 46, 26, },
+	{ 1, 1, 1, 7, 46, 26, },
+	{ 0, 1, 1, 7, 54, 26, },
+	{ 2, 1, 1, 7, 54, 26, },
+	{ 1, 1, 1, 7, 54, 26, },
+	{ 0, 1, 1, 7, 62, 18, },
+	{ 2, 1, 1, 7, 62, 26, },
+	{ 1, 1, 1, 7, 62, 26, },
+	{ 0, 1, 1, 7, 102, 20, },
+	{ 2, 1, 1, 7, 102, 26, },
+	{ 1, 1, 1, 7, 102, 26, },
+	{ 0, 1, 1, 7, 110, 26, },
+	{ 2, 1, 1, 7, 110, 26, },
+	{ 1, 1, 1, 7, 110, 26, },
+	{ 0, 1, 1, 7, 118, 26, },
+	{ 2, 1, 1, 7, 118, 26, },
+	{ 1, 1, 1, 7, 118, 26, },
+	{ 0, 1, 1, 7, 126, 26, },
+	{ 2, 1, 1, 7, 126, 26, },
+	{ 1, 1, 1, 7, 126, 26, },
+	{ 0, 1, 1, 7, 134, 24, },
+	{ 2, 1, 1, 7, 134, 26, },
+	{ 1, 1, 1, 7, 134, 26, },
+	{ 0, 1, 1, 7, 151, 20, },
+	{ 2, 1, 1, 7, 151, 26, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 26, },
+	{ 2, 1, 1, 7, 159, 26, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 24, },
+	{ 2, 1, 2, 4, 42, 32, },
+	{ 1, 1, 2, 4, 42, 32, },
+	{ 0, 1, 2, 4, 58, 24, },
+	{ 2, 1, 2, 4, 58, 32, },
+	{ 1, 1, 2, 4, 58, 32, },
+	{ 0, 1, 2, 4, 106, 24, },
+	{ 2, 1, 2, 4, 106, 32, },
+	{ 1, 1, 2, 4, 106, 32, },
+	{ 0, 1, 2, 4, 122, 32, },
+	{ 2, 1, 2, 4, 122, 32, },
+	{ 1, 1, 2, 4, 122, 32, },
+	{ 0, 1, 2, 4, 155, 26, },
+	{ 2, 1, 2, 4, 155, 32, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 22, },
+	{ 2, 1, 2, 5, 42, 30, },
+	{ 1, 1, 2, 5, 42, 30, },
+	{ 0, 1, 2, 5, 58, 22, },
+	{ 2, 1, 2, 5, 58, 30, },
+	{ 1, 1, 2, 5, 58, 30, },
+	{ 0, 1, 2, 5, 106, 22, },
+	{ 2, 1, 2, 5, 106, 30, },
+	{ 1, 1, 2, 5, 106, 30, },
+	{ 0, 1, 2, 5, 122, 30, },
+	{ 2, 1, 2, 5, 122, 30, },
+	{ 1, 1, 2, 5, 122, 30, },
+	{ 0, 1, 2, 5, 155, 24, },
+	{ 2, 1, 2, 5, 155, 30, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 20, },
+	{ 2, 1, 2, 8, 42, 28, },
+	{ 1, 1, 2, 8, 42, 28, },
+	{ 0, 1, 2, 8, 58, 20, },
+	{ 2, 1, 2, 8, 58, 28, },
+	{ 1, 1, 2, 8, 58, 28, },
+	{ 0, 1, 2, 8, 106, 20, },
+	{ 2, 1, 2, 8, 106, 28, },
+	{ 1, 1, 2, 8, 106, 28, },
+	{ 0, 1, 2, 8, 122, 28, },
+	{ 2, 1, 2, 8, 122, 28, },
+	{ 1, 1, 2, 8, 122, 28, },
+	{ 0, 1, 2, 8, 155, 20, },
+	{ 2, 1, 2, 8, 155, 28, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 18, },
+	{ 2, 1, 2, 9, 42, 26, },
+	{ 1, 1, 2, 9, 42, 26, },
+	{ 0, 1, 2, 9, 58, 18, },
+	{ 2, 1, 2, 9, 58, 26, },
+	{ 1, 1, 2, 9, 58, 26, },
+	{ 0, 1, 2, 9, 106, 18, },
+	{ 2, 1, 2, 9, 106, 26, },
+	{ 1, 1, 2, 9, 106, 26, },
+	{ 0, 1, 2, 9, 122, 26, },
+	{ 2, 1, 2, 9, 122, 26, },
+	{ 1, 1, 2, 9, 122, 26, },
+	{ 0, 1, 2, 9, 155, 18, },
+	{ 2, 1, 2, 9, 155, 26, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type1);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type2[] = {
+	{ 0, 0, 0, 0, 1, 42, },
+	{ 2, 0, 0, 0, 1, 42, },
+	{ 1, 0, 0, 0, 1, 42, },
+	{ 0, 0, 0, 0, 2, 50, },
+	{ 2, 0, 0, 0, 2, 42, },
+	{ 1, 0, 0, 0, 2, 42, },
+	{ 0, 0, 0, 0, 3, 50, },
+	{ 2, 0, 0, 0, 3, 42, },
+	{ 1, 0, 0, 0, 3, 42, },
+	{ 0, 0, 0, 0, 4, 50, },
+	{ 2, 0, 0, 0, 4, 42, },
+	{ 1, 0, 0, 0, 4, 42, },
+	{ 0, 0, 0, 0, 5, 50, },
+	{ 2, 0, 0, 0, 5, 42, },
+	{ 1, 0, 0, 0, 5, 42, },
+	{ 0, 0, 0, 0, 6, 50, },
+	{ 2, 0, 0, 0, 6, 42, },
+	{ 1, 0, 0, 0, 6, 42, },
+	{ 0, 0, 0, 0, 7, 50, },
+	{ 2, 0, 0, 0, 7, 42, },
+	{ 1, 0, 0, 0, 7, 42, },
+	{ 0, 0, 0, 0, 8, 50, },
+	{ 2, 0, 0, 0, 8, 42, },
+	{ 1, 0, 0, 0, 8, 42, },
+	{ 0, 0, 0, 0, 9, 50, },
+	{ 2, 0, 0, 0, 9, 42, },
+	{ 1, 0, 0, 0, 9, 42, },
+	{ 0, 0, 0, 0, 10, 50, },
+	{ 2, 0, 0, 0, 10, 42, },
+	{ 1, 0, 0, 0, 10, 42, },
+	{ 0, 0, 0, 0, 11, 44, },
+	{ 2, 0, 0, 0, 11, 42, },
+	{ 1, 0, 0, 0, 11, 42, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 42, },
+	{ 1, 0, 0, 0, 12, 42, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 42, },
+	{ 1, 0, 0, 0, 13, 42, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 42, },
+	{ 0, 0, 0, 1, 1, 32, },
+	{ 2, 0, 0, 1, 1, 42, },
+	{ 1, 0, 0, 1, 1, 42, },
+	{ 0, 0, 0, 1, 2, 42, },
+	{ 2, 0, 0, 1, 2, 42, },
+	{ 1, 0, 0, 1, 2, 42, },
+	{ 0, 0, 0, 1, 3, 42, },
+	{ 2, 0, 0, 1, 3, 42, },
+	{ 1, 0, 0, 1, 3, 42, },
+	{ 0, 0, 0, 1, 4, 42, },
+	{ 2, 0, 0, 1, 4, 42, },
+	{ 1, 0, 0, 1, 4, 42, },
+	{ 0, 0, 0, 1, 5, 42, },
+	{ 2, 0, 0, 1, 5, 42, },
+	{ 1, 0, 0, 1, 5, 42, },
+	{ 0, 0, 0, 1, 6, 42, },
+	{ 2, 0, 0, 1, 6, 42, },
+	{ 1, 0, 0, 1, 6, 42, },
+	{ 0, 0, 0, 1, 7, 42, },
+	{ 2, 0, 0, 1, 7, 42, },
+	{ 1, 0, 0, 1, 7, 42, },
+	{ 0, 0, 0, 1, 8, 42, },
+	{ 2, 0, 0, 1, 8, 42, },
+	{ 1, 0, 0, 1, 8, 42, },
+	{ 0, 0, 0, 1, 9, 42, },
+	{ 2, 0, 0, 1, 9, 42, },
+	{ 1, 0, 0, 1, 9, 42, },
+	{ 0, 0, 0, 1, 10, 42, },
+	{ 2, 0, 0, 1, 10, 42, },
+	{ 1, 0, 0, 1, 10, 42, },
+	{ 0, 0, 0, 1, 11, 32, },
+	{ 2, 0, 0, 1, 11, 42, },
+	{ 1, 0, 0, 1, 11, 42, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 42, },
+	{ 1, 0, 0, 1, 12, 42, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 42, },
+	{ 1, 0, 0, 1, 13, 42, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 32, },
+	{ 2, 0, 0, 2, 1, 42, },
+	{ 1, 0, 0, 2, 1, 42, },
+	{ 0, 0, 0, 2, 2, 40, },
+	{ 2, 0, 0, 2, 2, 42, },
+	{ 1, 0, 0, 2, 2, 42, },
+	{ 0, 0, 0, 2, 3, 40, },
+	{ 2, 0, 0, 2, 3, 42, },
+	{ 1, 0, 0, 2, 3, 42, },
+	{ 0, 0, 0, 2, 4, 40, },
+	{ 2, 0, 0, 2, 4, 42, },
+	{ 1, 0, 0, 2, 4, 42, },
+	{ 0, 0, 0, 2, 5, 40, },
+	{ 2, 0, 0, 2, 5, 42, },
+	{ 1, 0, 0, 2, 5, 42, },
+	{ 0, 0, 0, 2, 6, 40, },
+	{ 2, 0, 0, 2, 6, 42, },
+	{ 1, 0, 0, 2, 6, 42, },
+	{ 0, 0, 0, 2, 7, 40, },
+	{ 2, 0, 0, 2, 7, 42, },
+	{ 1, 0, 0, 2, 7, 42, },
+	{ 0, 0, 0, 2, 8, 40, },
+	{ 2, 0, 0, 2, 8, 42, },
+	{ 1, 0, 0, 2, 8, 42, },
+	{ 0, 0, 0, 2, 9, 40, },
+	{ 2, 0, 0, 2, 9, 42, },
+	{ 1, 0, 0, 2, 9, 42, },
+	{ 0, 0, 0, 2, 10, 40, },
+	{ 2, 0, 0, 2, 10, 42, },
+	{ 1, 0, 0, 2, 10, 42, },
+	{ 0, 0, 0, 2, 11, 28, },
+	{ 2, 0, 0, 2, 11, 42, },
+	{ 1, 0, 0, 2, 11, 42, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 42, },
+	{ 1, 0, 0, 2, 12, 42, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 42, },
+	{ 1, 0, 0, 2, 13, 42, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 32, },
+	{ 2, 0, 0, 3, 1, 40, },
+	{ 1, 0, 0, 3, 1, 40, },
+	{ 0, 0, 0, 3, 2, 40, },
+	{ 2, 0, 0, 3, 2, 40, },
+	{ 1, 0, 0, 3, 2, 40, },
+	{ 0, 0, 0, 3, 3, 40, },
+	{ 2, 0, 0, 3, 3, 40, },
+	{ 1, 0, 0, 3, 3, 40, },
+	{ 0, 0, 0, 3, 4, 40, },
+	{ 2, 0, 0, 3, 4, 40, },
+	{ 1, 0, 0, 3, 4, 40, },
+	{ 0, 0, 0, 3, 5, 40, },
+	{ 2, 0, 0, 3, 5, 40, },
+	{ 1, 0, 0, 3, 5, 40, },
+	{ 0, 0, 0, 3, 6, 40, },
+	{ 2, 0, 0, 3, 6, 40, },
+	{ 1, 0, 0, 3, 6, 40, },
+	{ 0, 0, 0, 3, 7, 40, },
+	{ 2, 0, 0, 3, 7, 40, },
+	{ 1, 0, 0, 3, 7, 40, },
+	{ 0, 0, 0, 3, 8, 40, },
+	{ 2, 0, 0, 3, 8, 40, },
+	{ 1, 0, 0, 3, 8, 40, },
+	{ 0, 0, 0, 3, 9, 40, },
+	{ 2, 0, 0, 3, 9, 40, },
+	{ 1, 0, 0, 3, 9, 40, },
+	{ 0, 0, 0, 3, 10, 40, },
+	{ 2, 0, 0, 3, 10, 40, },
+	{ 1, 0, 0, 3, 10, 40, },
+	{ 0, 0, 0, 3, 11, 28, },
+	{ 2, 0, 0, 3, 11, 40, },
+	{ 1, 0, 0, 3, 11, 40, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 40, },
+	{ 1, 0, 0, 3, 12, 40, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 40, },
+	{ 1, 0, 0, 3, 13, 40, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 32, },
+	{ 2, 0, 0, 6, 1, 40, },
+	{ 1, 0, 0, 6, 1, 40, },
+	{ 0, 0, 0, 6, 2, 40, },
+	{ 2, 0, 0, 6, 2, 40, },
+	{ 1, 0, 0, 6, 2, 40, },
+	{ 0, 0, 0, 6, 3, 40, },
+	{ 2, 0, 0, 6, 3, 40, },
+	{ 1, 0, 0, 6, 3, 40, },
+	{ 0, 0, 0, 6, 4, 40, },
+	{ 2, 0, 0, 6, 4, 40, },
+	{ 1, 0, 0, 6, 4, 40, },
+	{ 0, 0, 0, 6, 5, 40, },
+	{ 2, 0, 0, 6, 5, 40, },
+	{ 1, 0, 0, 6, 5, 40, },
+	{ 0, 0, 0, 6, 6, 40, },
+	{ 2, 0, 0, 6, 6, 40, },
+	{ 1, 0, 0, 6, 6, 40, },
+	{ 0, 0, 0, 6, 7, 40, },
+	{ 2, 0, 0, 6, 7, 40, },
+	{ 1, 0, 0, 6, 7, 40, },
+	{ 0, 0, 0, 6, 8, 40, },
+	{ 2, 0, 0, 6, 8, 40, },
+	{ 1, 0, 0, 6, 8, 40, },
+	{ 0, 0, 0, 6, 9, 40, },
+	{ 2, 0, 0, 6, 9, 40, },
+	{ 1, 0, 0, 6, 9, 40, },
+	{ 0, 0, 0, 6, 10, 40, },
+	{ 2, 0, 0, 6, 10, 40, },
+	{ 1, 0, 0, 6, 10, 40, },
+	{ 0, 0, 0, 6, 11, 28, },
+	{ 2, 0, 0, 6, 11, 40, },
+	{ 1, 0, 0, 6, 11, 40, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 40, },
+	{ 1, 0, 0, 6, 12, 40, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 40, },
+	{ 1, 0, 0, 6, 13, 40, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 32, },
+	{ 2, 0, 0, 7, 1, 40, },
+	{ 1, 0, 0, 7, 1, 40, },
+	{ 0, 0, 0, 7, 2, 40, },
+	{ 2, 0, 0, 7, 2, 40, },
+	{ 1, 0, 0, 7, 2, 40, },
+	{ 0, 0, 0, 7, 3, 40, },
+	{ 2, 0, 0, 7, 3, 40, },
+	{ 1, 0, 0, 7, 3, 40, },
+	{ 0, 0, 0, 7, 4, 40, },
+	{ 2, 0, 0, 7, 4, 40, },
+	{ 1, 0, 0, 7, 4, 40, },
+	{ 0, 0, 0, 7, 5, 40, },
+	{ 2, 0, 0, 7, 5, 40, },
+	{ 1, 0, 0, 7, 5, 40, },
+	{ 0, 0, 0, 7, 6, 40, },
+	{ 2, 0, 0, 7, 6, 40, },
+	{ 1, 0, 0, 7, 6, 40, },
+	{ 0, 0, 0, 7, 7, 40, },
+	{ 2, 0, 0, 7, 7, 40, },
+	{ 1, 0, 0, 7, 7, 40, },
+	{ 0, 0, 0, 7, 8, 40, },
+	{ 2, 0, 0, 7, 8, 40, },
+	{ 1, 0, 0, 7, 8, 40, },
+	{ 0, 0, 0, 7, 9, 40, },
+	{ 2, 0, 0, 7, 9, 40, },
+	{ 1, 0, 0, 7, 9, 40, },
+	{ 0, 0, 0, 7, 10, 40, },
+	{ 2, 0, 0, 7, 10, 40, },
+	{ 1, 0, 0, 7, 10, 40, },
+	{ 0, 0, 0, 7, 11, 28, },
+	{ 2, 0, 0, 7, 11, 40, },
+	{ 1, 0, 0, 7, 11, 40, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 40, },
+	{ 1, 0, 0, 7, 12, 40, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 40, },
+	{ 1, 0, 0, 7, 13, 40, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 30, },
+	{ 2, 0, 1, 2, 3, 34, },
+	{ 1, 0, 1, 2, 3, 34, },
+	{ 0, 0, 1, 2, 4, 34, },
+	{ 2, 0, 1, 2, 4, 34, },
+	{ 1, 0, 1, 2, 4, 34, },
+	{ 0, 0, 1, 2, 5, 34, },
+	{ 2, 0, 1, 2, 5, 34, },
+	{ 1, 0, 1, 2, 5, 34, },
+	{ 0, 0, 1, 2, 6, 34, },
+	{ 2, 0, 1, 2, 6, 34, },
+	{ 1, 0, 1, 2, 6, 34, },
+	{ 0, 0, 1, 2, 7, 34, },
+	{ 2, 0, 1, 2, 7, 34, },
+	{ 1, 0, 1, 2, 7, 34, },
+	{ 0, 0, 1, 2, 8, 34, },
+	{ 2, 0, 1, 2, 8, 34, },
+	{ 1, 0, 1, 2, 8, 34, },
+	{ 0, 0, 1, 2, 9, 34, },
+	{ 2, 0, 1, 2, 9, 34, },
+	{ 1, 0, 1, 2, 9, 34, },
+	{ 0, 0, 1, 2, 10, 34, },
+	{ 2, 0, 1, 2, 10, 34, },
+	{ 1, 0, 1, 2, 10, 34, },
+	{ 0, 0, 1, 2, 11, 28, },
+	{ 2, 0, 1, 2, 11, 34, },
+	{ 1, 0, 1, 2, 11, 34, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 34, },
+	{ 1, 0, 1, 2, 12, 34, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 34, },
+	{ 1, 0, 1, 2, 13, 34, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 30, },
+	{ 2, 0, 1, 3, 3, 34, },
+	{ 1, 0, 1, 3, 3, 34, },
+	{ 0, 0, 1, 3, 4, 34, },
+	{ 2, 0, 1, 3, 4, 34, },
+	{ 1, 0, 1, 3, 4, 34, },
+	{ 0, 0, 1, 3, 5, 34, },
+	{ 2, 0, 1, 3, 5, 34, },
+	{ 1, 0, 1, 3, 5, 34, },
+	{ 0, 0, 1, 3, 6, 34, },
+	{ 2, 0, 1, 3, 6, 34, },
+	{ 1, 0, 1, 3, 6, 34, },
+	{ 0, 0, 1, 3, 7, 34, },
+	{ 2, 0, 1, 3, 7, 34, },
+	{ 1, 0, 1, 3, 7, 34, },
+	{ 0, 0, 1, 3, 8, 34, },
+	{ 2, 0, 1, 3, 8, 34, },
+	{ 1, 0, 1, 3, 8, 34, },
+	{ 0, 0, 1, 3, 9, 34, },
+	{ 2, 0, 1, 3, 9, 34, },
+	{ 1, 0, 1, 3, 9, 34, },
+	{ 0, 0, 1, 3, 10, 34, },
+	{ 2, 0, 1, 3, 10, 34, },
+	{ 1, 0, 1, 3, 10, 34, },
+	{ 0, 0, 1, 3, 11, 28, },
+	{ 2, 0, 1, 3, 11, 34, },
+	{ 1, 0, 1, 3, 11, 34, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 34, },
+	{ 1, 0, 1, 3, 12, 34, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 34, },
+	{ 1, 0, 1, 3, 13, 34, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 30, },
+	{ 2, 0, 1, 6, 3, 34, },
+	{ 1, 0, 1, 6, 3, 34, },
+	{ 0, 0, 1, 6, 4, 34, },
+	{ 2, 0, 1, 6, 4, 34, },
+	{ 1, 0, 1, 6, 4, 34, },
+	{ 0, 0, 1, 6, 5, 34, },
+	{ 2, 0, 1, 6, 5, 34, },
+	{ 1, 0, 1, 6, 5, 34, },
+	{ 0, 0, 1, 6, 6, 34, },
+	{ 2, 0, 1, 6, 6, 34, },
+	{ 1, 0, 1, 6, 6, 34, },
+	{ 0, 0, 1, 6, 7, 34, },
+	{ 2, 0, 1, 6, 7, 34, },
+	{ 1, 0, 1, 6, 7, 34, },
+	{ 0, 0, 1, 6, 8, 34, },
+	{ 2, 0, 1, 6, 8, 34, },
+	{ 1, 0, 1, 6, 8, 34, },
+	{ 0, 0, 1, 6, 9, 34, },
+	{ 2, 0, 1, 6, 9, 34, },
+	{ 1, 0, 1, 6, 9, 34, },
+	{ 0, 0, 1, 6, 10, 34, },
+	{ 2, 0, 1, 6, 10, 34, },
+	{ 1, 0, 1, 6, 10, 34, },
+	{ 0, 0, 1, 6, 11, 28, },
+	{ 2, 0, 1, 6, 11, 34, },
+	{ 1, 0, 1, 6, 11, 34, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 34, },
+	{ 1, 0, 1, 6, 12, 34, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 34, },
+	{ 1, 0, 1, 6, 13, 34, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 30, },
+	{ 2, 0, 1, 7, 3, 34, },
+	{ 1, 0, 1, 7, 3, 34, },
+	{ 0, 0, 1, 7, 4, 34, },
+	{ 2, 0, 1, 7, 4, 34, },
+	{ 1, 0, 1, 7, 4, 34, },
+	{ 0, 0, 1, 7, 5, 34, },
+	{ 2, 0, 1, 7, 5, 34, },
+	{ 1, 0, 1, 7, 5, 34, },
+	{ 0, 0, 1, 7, 6, 34, },
+	{ 2, 0, 1, 7, 6, 34, },
+	{ 1, 0, 1, 7, 6, 34, },
+	{ 0, 0, 1, 7, 7, 34, },
+	{ 2, 0, 1, 7, 7, 34, },
+	{ 1, 0, 1, 7, 7, 34, },
+	{ 0, 0, 1, 7, 8, 34, },
+	{ 2, 0, 1, 7, 8, 34, },
+	{ 1, 0, 1, 7, 8, 34, },
+	{ 0, 0, 1, 7, 9, 34, },
+	{ 2, 0, 1, 7, 9, 34, },
+	{ 1, 0, 1, 7, 9, 34, },
+	{ 0, 0, 1, 7, 10, 34, },
+	{ 2, 0, 1, 7, 10, 34, },
+	{ 1, 0, 1, 7, 10, 34, },
+	{ 0, 0, 1, 7, 11, 28, },
+	{ 2, 0, 1, 7, 11, 34, },
+	{ 1, 0, 1, 7, 11, 34, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 34, },
+	{ 1, 0, 1, 7, 12, 34, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 34, },
+	{ 1, 0, 1, 7, 13, 34, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 42, },
+	{ 2, 1, 0, 1, 36, 42, },
+	{ 1, 1, 0, 1, 36, 42, },
+	{ 0, 1, 0, 1, 40, 42, },
+	{ 2, 1, 0, 1, 40, 42, },
+	{ 1, 1, 0, 1, 40, 42, },
+	{ 0, 1, 0, 1, 44, 42, },
+	{ 2, 1, 0, 1, 44, 42, },
+	{ 1, 1, 0, 1, 44, 42, },
+	{ 0, 1, 0, 1, 48, 42, },
+	{ 2, 1, 0, 1, 48, 42, },
+	{ 1, 1, 0, 1, 48, 42, },
+	{ 0, 1, 0, 1, 52, 42, },
+	{ 2, 1, 0, 1, 52, 42, },
+	{ 1, 1, 0, 1, 52, 42, },
+	{ 0, 1, 0, 1, 56, 42, },
+	{ 2, 1, 0, 1, 56, 42, },
+	{ 1, 1, 0, 1, 56, 42, },
+	{ 0, 1, 0, 1, 60, 42, },
+	{ 2, 1, 0, 1, 60, 42, },
+	{ 1, 1, 0, 1, 60, 42, },
+	{ 0, 1, 0, 1, 64, 42, },
+	{ 2, 1, 0, 1, 64, 42, },
+	{ 1, 1, 0, 1, 64, 42, },
+	{ 0, 1, 0, 1, 100, 42, },
+	{ 2, 1, 0, 1, 100, 42, },
+	{ 1, 1, 0, 1, 100, 42, },
+	{ 0, 1, 0, 1, 104, 42, },
+	{ 2, 1, 0, 1, 104, 42, },
+	{ 1, 1, 0, 1, 104, 42, },
+	{ 0, 1, 0, 1, 108, 42, },
+	{ 2, 1, 0, 1, 108, 42, },
+	{ 1, 1, 0, 1, 108, 42, },
+	{ 0, 1, 0, 1, 112, 42, },
+	{ 2, 1, 0, 1, 112, 42, },
+	{ 1, 1, 0, 1, 112, 42, },
+	{ 0, 1, 0, 1, 116, 42, },
+	{ 2, 1, 0, 1, 116, 42, },
+	{ 1, 1, 0, 1, 116, 42, },
+	{ 0, 1, 0, 1, 120, 42, },
+	{ 2, 1, 0, 1, 120, 42, },
+	{ 1, 1, 0, 1, 120, 42, },
+	{ 0, 1, 0, 1, 124, 42, },
+	{ 2, 1, 0, 1, 124, 42, },
+	{ 1, 1, 0, 1, 124, 42, },
+	{ 0, 1, 0, 1, 128, 42, },
+	{ 2, 1, 0, 1, 128, 42, },
+	{ 1, 1, 0, 1, 128, 42, },
+	{ 0, 1, 0, 1, 132, 42, },
+	{ 2, 1, 0, 1, 132, 42, },
+	{ 1, 1, 0, 1, 132, 42, },
+	{ 0, 1, 0, 1, 136, 42, },
+	{ 2, 1, 0, 1, 136, 42, },
+	{ 1, 1, 0, 1, 136, 42, },
+	{ 0, 1, 0, 1, 140, 40, },
+	{ 2, 1, 0, 1, 140, 40, },
+	{ 1, 1, 0, 1, 140, 40, },
+	{ 0, 1, 0, 1, 149, 44, },
+	{ 2, 1, 0, 1, 149, 44, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 44, },
+	{ 2, 1, 0, 1, 153, 44, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 44, },
+	{ 2, 1, 0, 1, 157, 44, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 44, },
+	{ 2, 1, 0, 1, 161, 44, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 44, },
+	{ 2, 1, 0, 1, 165, 44, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 32, },
+	{ 2, 1, 0, 2, 36, 32, },
+	{ 1, 1, 0, 2, 36, 32, },
+	{ 0, 1, 0, 2, 40, 32, },
+	{ 2, 1, 0, 2, 40, 32, },
+	{ 1, 1, 0, 2, 40, 32, },
+	{ 0, 1, 0, 2, 44, 32, },
+	{ 2, 1, 0, 2, 44, 32, },
+	{ 1, 1, 0, 2, 44, 32, },
+	{ 0, 1, 0, 2, 48, 36, },
+	{ 2, 1, 0, 2, 48, 36, },
+	{ 1, 1, 0, 2, 48, 36, },
+	{ 0, 1, 0, 2, 52, 36, },
+	{ 2, 1, 0, 2, 52, 36, },
+	{ 1, 1, 0, 2, 52, 36, },
+	{ 0, 1, 0, 2, 56, 32, },
+	{ 2, 1, 0, 2, 56, 32, },
+	{ 1, 1, 0, 2, 56, 32, },
+	{ 0, 1, 0, 2, 60, 32, },
+	{ 2, 1, 0, 2, 60, 32, },
+	{ 1, 1, 0, 2, 60, 32, },
+	{ 0, 1, 0, 2, 64, 32, },
+	{ 2, 1, 0, 2, 64, 32, },
+	{ 1, 1, 0, 2, 64, 32, },
+	{ 0, 1, 0, 2, 100, 32, },
+	{ 2, 1, 0, 2, 100, 32, },
+	{ 1, 1, 0, 2, 100, 32, },
+	{ 0, 1, 0, 2, 104, 32, },
+	{ 2, 1, 0, 2, 104, 32, },
+	{ 1, 1, 0, 2, 104, 32, },
+	{ 0, 1, 0, 2, 108, 32, },
+	{ 2, 1, 0, 2, 108, 32, },
+	{ 1, 1, 0, 2, 108, 32, },
+	{ 0, 1, 0, 2, 112, 32, },
+	{ 2, 1, 0, 2, 112, 32, },
+	{ 1, 1, 0, 2, 112, 32, },
+	{ 0, 1, 0, 2, 116, 32, },
+	{ 2, 1, 0, 2, 116, 32, },
+	{ 1, 1, 0, 2, 116, 32, },
+	{ 0, 1, 0, 2, 120, 32, },
+	{ 2, 1, 0, 2, 120, 32, },
+	{ 1, 1, 0, 2, 120, 32, },
+	{ 0, 1, 0, 2, 124, 32, },
+	{ 2, 1, 0, 2, 124, 32, },
+	{ 1, 1, 0, 2, 124, 32, },
+	{ 0, 1, 0, 2, 128, 32, },
+	{ 2, 1, 0, 2, 128, 32, },
+	{ 1, 1, 0, 2, 128, 32, },
+	{ 0, 1, 0, 2, 132, 32, },
+	{ 2, 1, 0, 2, 132, 32, },
+	{ 1, 1, 0, 2, 132, 32, },
+	{ 0, 1, 0, 2, 136, 32, },
+	{ 2, 1, 0, 2, 136, 32, },
+	{ 1, 1, 0, 2, 136, 32, },
+	{ 0, 1, 0, 2, 140, 30, },
+	{ 2, 1, 0, 2, 140, 30, },
+	{ 1, 1, 0, 2, 140, 30, },
+	{ 0, 1, 0, 2, 149, 40, },
+	{ 2, 1, 0, 2, 149, 40, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 40, },
+	{ 2, 1, 0, 2, 153, 40, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 40, },
+	{ 2, 1, 0, 2, 157, 40, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 40, },
+	{ 2, 1, 0, 2, 161, 40, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 42, },
+	{ 2, 1, 0, 2, 165, 42, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 32, },
+	{ 2, 1, 0, 3, 36, 32, },
+	{ 1, 1, 0, 3, 36, 32, },
+	{ 0, 1, 0, 3, 40, 32, },
+	{ 2, 1, 0, 3, 40, 32, },
+	{ 1, 1, 0, 3, 40, 32, },
+	{ 0, 1, 0, 3, 44, 32, },
+	{ 2, 1, 0, 3, 44, 32, },
+	{ 1, 1, 0, 3, 44, 32, },
+	{ 0, 1, 0, 3, 48, 36, },
+	{ 2, 1, 0, 3, 48, 36, },
+	{ 1, 1, 0, 3, 48, 36, },
+	{ 0, 1, 0, 3, 52, 36, },
+	{ 2, 1, 0, 3, 52, 36, },
+	{ 1, 1, 0, 3, 52, 36, },
+	{ 0, 1, 0, 3, 56, 32, },
+	{ 2, 1, 0, 3, 56, 32, },
+	{ 1, 1, 0, 3, 56, 32, },
+	{ 0, 1, 0, 3, 60, 32, },
+	{ 2, 1, 0, 3, 60, 32, },
+	{ 1, 1, 0, 3, 60, 32, },
+	{ 0, 1, 0, 3, 64, 32, },
+	{ 2, 1, 0, 3, 64, 32, },
+	{ 1, 1, 0, 3, 64, 32, },
+	{ 0, 1, 0, 3, 100, 32, },
+	{ 2, 1, 0, 3, 100, 32, },
+	{ 1, 1, 0, 3, 100, 32, },
+	{ 0, 1, 0, 3, 104, 32, },
+	{ 2, 1, 0, 3, 104, 32, },
+	{ 1, 1, 0, 3, 104, 32, },
+	{ 0, 1, 0, 3, 108, 32, },
+	{ 2, 1, 0, 3, 108, 32, },
+	{ 1, 1, 0, 3, 108, 32, },
+	{ 0, 1, 0, 3, 112, 32, },
+	{ 2, 1, 0, 3, 112, 32, },
+	{ 1, 1, 0, 3, 112, 32, },
+	{ 0, 1, 0, 3, 116, 32, },
+	{ 2, 1, 0, 3, 116, 32, },
+	{ 1, 1, 0, 3, 116, 32, },
+	{ 0, 1, 0, 3, 120, 32, },
+	{ 2, 1, 0, 3, 120, 32, },
+	{ 1, 1, 0, 3, 120, 32, },
+	{ 0, 1, 0, 3, 124, 32, },
+	{ 2, 1, 0, 3, 124, 32, },
+	{ 1, 1, 0, 3, 124, 32, },
+	{ 0, 1, 0, 3, 128, 32, },
+	{ 2, 1, 0, 3, 128, 32, },
+	{ 1, 1, 0, 3, 128, 32, },
+	{ 0, 1, 0, 3, 132, 32, },
+	{ 2, 1, 0, 3, 132, 32, },
+	{ 1, 1, 0, 3, 132, 32, },
+	{ 0, 1, 0, 3, 136, 32, },
+	{ 2, 1, 0, 3, 136, 32, },
+	{ 1, 1, 0, 3, 136, 32, },
+	{ 0, 1, 0, 3, 140, 30, },
+	{ 2, 1, 0, 3, 140, 30, },
+	{ 1, 1, 0, 3, 140, 30, },
+	{ 0, 1, 0, 3, 149, 40, },
+	{ 2, 1, 0, 3, 149, 40, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 40, },
+	{ 2, 1, 0, 3, 153, 40, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 40, },
+	{ 2, 1, 0, 3, 157, 40, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 40, },
+	{ 2, 1, 0, 3, 161, 40, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 42, },
+	{ 2, 1, 0, 3, 165, 42, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 32, },
+	{ 2, 1, 0, 6, 36, 32, },
+	{ 1, 1, 0, 6, 36, 32, },
+	{ 0, 1, 0, 6, 40, 32, },
+	{ 2, 1, 0, 6, 40, 32, },
+	{ 1, 1, 0, 6, 40, 32, },
+	{ 0, 1, 0, 6, 44, 32, },
+	{ 2, 1, 0, 6, 44, 32, },
+	{ 1, 1, 0, 6, 44, 32, },
+	{ 0, 1, 0, 6, 48, 36, },
+	{ 2, 1, 0, 6, 48, 36, },
+	{ 1, 1, 0, 6, 48, 36, },
+	{ 0, 1, 0, 6, 52, 36, },
+	{ 2, 1, 0, 6, 52, 36, },
+	{ 1, 1, 0, 6, 52, 36, },
+	{ 0, 1, 0, 6, 56, 32, },
+	{ 2, 1, 0, 6, 56, 32, },
+	{ 1, 1, 0, 6, 56, 32, },
+	{ 0, 1, 0, 6, 60, 32, },
+	{ 2, 1, 0, 6, 60, 32, },
+	{ 1, 1, 0, 6, 60, 32, },
+	{ 0, 1, 0, 6, 64, 32, },
+	{ 2, 1, 0, 6, 64, 32, },
+	{ 1, 1, 0, 6, 64, 32, },
+	{ 0, 1, 0, 6, 100, 32, },
+	{ 2, 1, 0, 6, 100, 32, },
+	{ 1, 1, 0, 6, 100, 32, },
+	{ 0, 1, 0, 6, 104, 32, },
+	{ 2, 1, 0, 6, 104, 32, },
+	{ 1, 1, 0, 6, 104, 32, },
+	{ 0, 1, 0, 6, 108, 32, },
+	{ 2, 1, 0, 6, 108, 32, },
+	{ 1, 1, 0, 6, 108, 32, },
+	{ 0, 1, 0, 6, 112, 32, },
+	{ 2, 1, 0, 6, 112, 32, },
+	{ 1, 1, 0, 6, 112, 32, },
+	{ 0, 1, 0, 6, 116, 32, },
+	{ 2, 1, 0, 6, 116, 32, },
+	{ 1, 1, 0, 6, 116, 32, },
+	{ 0, 1, 0, 6, 120, 32, },
+	{ 2, 1, 0, 6, 120, 32, },
+	{ 1, 1, 0, 6, 120, 32, },
+	{ 0, 1, 0, 6, 124, 32, },
+	{ 2, 1, 0, 6, 124, 32, },
+	{ 1, 1, 0, 6, 124, 32, },
+	{ 0, 1, 0, 6, 128, 32, },
+	{ 2, 1, 0, 6, 128, 32, },
+	{ 1, 1, 0, 6, 128, 32, },
+	{ 0, 1, 0, 6, 132, 32, },
+	{ 2, 1, 0, 6, 132, 32, },
+	{ 1, 1, 0, 6, 132, 32, },
+	{ 0, 1, 0, 6, 136, 32, },
+	{ 2, 1, 0, 6, 136, 32, },
+	{ 1, 1, 0, 6, 136, 32, },
+	{ 0, 1, 0, 6, 140, 30, },
+	{ 2, 1, 0, 6, 140, 30, },
+	{ 1, 1, 0, 6, 140, 30, },
+	{ 0, 1, 0, 6, 149, 40, },
+	{ 2, 1, 0, 6, 149, 40, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 40, },
+	{ 2, 1, 0, 6, 153, 40, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 40, },
+	{ 2, 1, 0, 6, 157, 40, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 40, },
+	{ 2, 1, 0, 6, 161, 40, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 42, },
+	{ 2, 1, 0, 6, 165, 42, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 32, },
+	{ 2, 1, 0, 7, 36, 32, },
+	{ 1, 1, 0, 7, 36, 32, },
+	{ 0, 1, 0, 7, 40, 32, },
+	{ 2, 1, 0, 7, 40, 32, },
+	{ 1, 1, 0, 7, 40, 32, },
+	{ 0, 1, 0, 7, 44, 32, },
+	{ 2, 1, 0, 7, 44, 32, },
+	{ 1, 1, 0, 7, 44, 32, },
+	{ 0, 1, 0, 7, 48, 36, },
+	{ 2, 1, 0, 7, 48, 36, },
+	{ 1, 1, 0, 7, 48, 36, },
+	{ 0, 1, 0, 7, 52, 36, },
+	{ 2, 1, 0, 7, 52, 36, },
+	{ 1, 1, 0, 7, 52, 36, },
+	{ 0, 1, 0, 7, 56, 32, },
+	{ 2, 1, 0, 7, 56, 32, },
+	{ 1, 1, 0, 7, 56, 32, },
+	{ 0, 1, 0, 7, 60, 32, },
+	{ 2, 1, 0, 7, 60, 32, },
+	{ 1, 1, 0, 7, 60, 32, },
+	{ 0, 1, 0, 7, 64, 32, },
+	{ 2, 1, 0, 7, 64, 32, },
+	{ 1, 1, 0, 7, 64, 32, },
+	{ 0, 1, 0, 7, 100, 32, },
+	{ 2, 1, 0, 7, 100, 32, },
+	{ 1, 1, 0, 7, 100, 32, },
+	{ 0, 1, 0, 7, 104, 32, },
+	{ 2, 1, 0, 7, 104, 32, },
+	{ 1, 1, 0, 7, 104, 32, },
+	{ 0, 1, 0, 7, 108, 32, },
+	{ 2, 1, 0, 7, 108, 32, },
+	{ 1, 1, 0, 7, 108, 32, },
+	{ 0, 1, 0, 7, 112, 32, },
+	{ 2, 1, 0, 7, 112, 32, },
+	{ 1, 1, 0, 7, 112, 32, },
+	{ 0, 1, 0, 7, 116, 32, },
+	{ 2, 1, 0, 7, 116, 32, },
+	{ 1, 1, 0, 7, 116, 32, },
+	{ 0, 1, 0, 7, 120, 32, },
+	{ 2, 1, 0, 7, 120, 32, },
+	{ 1, 1, 0, 7, 120, 32, },
+	{ 0, 1, 0, 7, 124, 32, },
+	{ 2, 1, 0, 7, 124, 32, },
+	{ 1, 1, 0, 7, 124, 32, },
+	{ 0, 1, 0, 7, 128, 32, },
+	{ 2, 1, 0, 7, 128, 32, },
+	{ 1, 1, 0, 7, 128, 32, },
+	{ 0, 1, 0, 7, 132, 32, },
+	{ 2, 1, 0, 7, 132, 32, },
+	{ 1, 1, 0, 7, 132, 32, },
+	{ 0, 1, 0, 7, 136, 32, },
+	{ 2, 1, 0, 7, 136, 32, },
+	{ 1, 1, 0, 7, 136, 32, },
+	{ 0, 1, 0, 7, 140, 30, },
+	{ 2, 1, 0, 7, 140, 30, },
+	{ 1, 1, 0, 7, 140, 30, },
+	{ 0, 1, 0, 7, 149, 40, },
+	{ 2, 1, 0, 7, 149, 40, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 40, },
+	{ 2, 1, 0, 7, 153, 40, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 40, },
+	{ 2, 1, 0, 7, 157, 40, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 40, },
+	{ 2, 1, 0, 7, 161, 40, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 42, },
+	{ 2, 1, 0, 7, 165, 42, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 32, },
+	{ 2, 1, 1, 2, 38, 32, },
+	{ 1, 1, 1, 2, 38, 32, },
+	{ 0, 1, 1, 2, 46, 36, },
+	{ 2, 1, 1, 2, 46, 36, },
+	{ 1, 1, 1, 2, 46, 36, },
+	{ 0, 1, 1, 2, 54, 36, },
+	{ 2, 1, 1, 2, 54, 36, },
+	{ 1, 1, 1, 2, 54, 36, },
+	{ 0, 1, 1, 2, 62, 32, },
+	{ 2, 1, 1, 2, 62, 32, },
+	{ 1, 1, 1, 2, 62, 32, },
+	{ 0, 1, 1, 2, 102, 30, },
+	{ 2, 1, 1, 2, 102, 30, },
+	{ 1, 1, 1, 2, 102, 30, },
+	{ 0, 1, 1, 2, 110, 32, },
+	{ 2, 1, 1, 2, 110, 32, },
+	{ 1, 1, 1, 2, 110, 32, },
+	{ 0, 1, 1, 2, 118, 32, },
+	{ 2, 1, 1, 2, 118, 32, },
+	{ 1, 1, 1, 2, 118, 32, },
+	{ 0, 1, 1, 2, 126, 32, },
+	{ 2, 1, 1, 2, 126, 32, },
+	{ 1, 1, 1, 2, 126, 32, },
+	{ 0, 1, 1, 2, 134, 36, },
+	{ 2, 1, 1, 2, 134, 36, },
+	{ 1, 1, 1, 2, 134, 36, },
+	{ 0, 1, 1, 2, 151, 36, },
+	{ 2, 1, 1, 2, 151, 36, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 40, },
+	{ 2, 1, 1, 2, 159, 40, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 32, },
+	{ 2, 1, 1, 3, 38, 32, },
+	{ 1, 1, 1, 3, 38, 32, },
+	{ 0, 1, 1, 3, 46, 36, },
+	{ 2, 1, 1, 3, 46, 36, },
+	{ 1, 1, 1, 3, 46, 36, },
+	{ 0, 1, 1, 3, 54, 36, },
+	{ 2, 1, 1, 3, 54, 36, },
+	{ 1, 1, 1, 3, 54, 36, },
+	{ 0, 1, 1, 3, 62, 32, },
+	{ 2, 1, 1, 3, 62, 32, },
+	{ 1, 1, 1, 3, 62, 32, },
+	{ 0, 1, 1, 3, 102, 30, },
+	{ 2, 1, 1, 3, 102, 30, },
+	{ 1, 1, 1, 3, 102, 30, },
+	{ 0, 1, 1, 3, 110, 32, },
+	{ 2, 1, 1, 3, 110, 32, },
+	{ 1, 1, 1, 3, 110, 32, },
+	{ 0, 1, 1, 3, 118, 32, },
+	{ 2, 1, 1, 3, 118, 32, },
+	{ 1, 1, 1, 3, 118, 32, },
+	{ 0, 1, 1, 3, 126, 32, },
+	{ 2, 1, 1, 3, 126, 32, },
+	{ 1, 1, 1, 3, 126, 32, },
+	{ 0, 1, 1, 3, 134, 36, },
+	{ 2, 1, 1, 3, 134, 36, },
+	{ 1, 1, 1, 3, 134, 36, },
+	{ 0, 1, 1, 3, 151, 36, },
+	{ 2, 1, 1, 3, 151, 36, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 40, },
+	{ 2, 1, 1, 3, 159, 40, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 32, },
+	{ 2, 1, 1, 6, 38, 32, },
+	{ 1, 1, 1, 6, 38, 32, },
+	{ 0, 1, 1, 6, 46, 36, },
+	{ 2, 1, 1, 6, 46, 36, },
+	{ 1, 1, 1, 6, 46, 36, },
+	{ 0, 1, 1, 6, 54, 36, },
+	{ 2, 1, 1, 6, 54, 36, },
+	{ 1, 1, 1, 6, 54, 36, },
+	{ 0, 1, 1, 6, 62, 32, },
+	{ 2, 1, 1, 6, 62, 32, },
+	{ 1, 1, 1, 6, 62, 32, },
+	{ 0, 1, 1, 6, 102, 30, },
+	{ 2, 1, 1, 6, 102, 30, },
+	{ 1, 1, 1, 6, 102, 30, },
+	{ 0, 1, 1, 6, 110, 32, },
+	{ 2, 1, 1, 6, 110, 32, },
+	{ 1, 1, 1, 6, 110, 32, },
+	{ 0, 1, 1, 6, 118, 32, },
+	{ 2, 1, 1, 6, 118, 32, },
+	{ 1, 1, 1, 6, 118, 32, },
+	{ 0, 1, 1, 6, 126, 32, },
+	{ 2, 1, 1, 6, 126, 32, },
+	{ 1, 1, 1, 6, 126, 32, },
+	{ 0, 1, 1, 6, 134, 36, },
+	{ 2, 1, 1, 6, 134, 36, },
+	{ 1, 1, 1, 6, 134, 36, },
+	{ 0, 1, 1, 6, 151, 36, },
+	{ 2, 1, 1, 6, 151, 36, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 40, },
+	{ 2, 1, 1, 6, 159, 40, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 32, },
+	{ 2, 1, 1, 7, 38, 32, },
+	{ 1, 1, 1, 7, 38, 32, },
+	{ 0, 1, 1, 7, 46, 36, },
+	{ 2, 1, 1, 7, 46, 36, },
+	{ 1, 1, 1, 7, 46, 36, },
+	{ 0, 1, 1, 7, 54, 36, },
+	{ 2, 1, 1, 7, 54, 36, },
+	{ 1, 1, 1, 7, 54, 36, },
+	{ 0, 1, 1, 7, 62, 32, },
+	{ 2, 1, 1, 7, 62, 32, },
+	{ 1, 1, 1, 7, 62, 32, },
+	{ 0, 1, 1, 7, 102, 30, },
+	{ 2, 1, 1, 7, 102, 30, },
+	{ 1, 1, 1, 7, 102, 30, },
+	{ 0, 1, 1, 7, 110, 32, },
+	{ 2, 1, 1, 7, 110, 32, },
+	{ 1, 1, 1, 7, 110, 32, },
+	{ 0, 1, 1, 7, 118, 32, },
+	{ 2, 1, 1, 7, 118, 32, },
+	{ 1, 1, 1, 7, 118, 32, },
+	{ 0, 1, 1, 7, 126, 32, },
+	{ 2, 1, 1, 7, 126, 32, },
+	{ 1, 1, 1, 7, 126, 32, },
+	{ 0, 1, 1, 7, 134, 36, },
+	{ 2, 1, 1, 7, 134, 36, },
+	{ 1, 1, 1, 7, 134, 36, },
+	{ 0, 1, 1, 7, 151, 36, },
+	{ 2, 1, 1, 7, 151, 36, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 40, },
+	{ 2, 1, 1, 7, 159, 40, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 34, },
+	{ 2, 1, 2, 4, 42, 34, },
+	{ 1, 1, 2, 4, 42, 34, },
+	{ 0, 1, 2, 4, 58, 34, },
+	{ 2, 1, 2, 4, 58, 34, },
+	{ 1, 1, 2, 4, 58, 34, },
+	{ 0, 1, 2, 4, 106, 32, },
+	{ 2, 1, 2, 4, 106, 32, },
+	{ 1, 1, 2, 4, 106, 32, },
+	{ 0, 1, 2, 4, 122, 34, },
+	{ 2, 1, 2, 4, 122, 34, },
+	{ 1, 1, 2, 4, 122, 34, },
+	{ 0, 1, 2, 4, 155, 34, },
+	{ 2, 1, 2, 4, 155, 34, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 34, },
+	{ 2, 1, 2, 5, 42, 34, },
+	{ 1, 1, 2, 5, 42, 34, },
+	{ 0, 1, 2, 5, 58, 34, },
+	{ 2, 1, 2, 5, 58, 34, },
+	{ 1, 1, 2, 5, 58, 34, },
+	{ 0, 1, 2, 5, 106, 32, },
+	{ 2, 1, 2, 5, 106, 32, },
+	{ 1, 1, 2, 5, 106, 32, },
+	{ 0, 1, 2, 5, 122, 34, },
+	{ 2, 1, 2, 5, 122, 34, },
+	{ 1, 1, 2, 5, 122, 34, },
+	{ 0, 1, 2, 5, 155, 34, },
+	{ 2, 1, 2, 5, 155, 34, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 34, },
+	{ 2, 1, 2, 8, 42, 34, },
+	{ 1, 1, 2, 8, 42, 34, },
+	{ 0, 1, 2, 8, 58, 34, },
+	{ 2, 1, 2, 8, 58, 34, },
+	{ 1, 1, 2, 8, 58, 34, },
+	{ 0, 1, 2, 8, 106, 32, },
+	{ 2, 1, 2, 8, 106, 32, },
+	{ 1, 1, 2, 8, 106, 32, },
+	{ 0, 1, 2, 8, 122, 34, },
+	{ 2, 1, 2, 8, 122, 34, },
+	{ 1, 1, 2, 8, 122, 34, },
+	{ 0, 1, 2, 8, 155, 34, },
+	{ 2, 1, 2, 8, 155, 34, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 34, },
+	{ 2, 1, 2, 9, 42, 34, },
+	{ 1, 1, 2, 9, 42, 34, },
+	{ 0, 1, 2, 9, 58, 34, },
+	{ 2, 1, 2, 9, 58, 34, },
+	{ 1, 1, 2, 9, 58, 34, },
+	{ 0, 1, 2, 9, 106, 32, },
+	{ 2, 1, 2, 9, 106, 32, },
+	{ 1, 1, 2, 9, 106, 32, },
+	{ 0, 1, 2, 9, 122, 34, },
+	{ 2, 1, 2, 9, 122, 34, },
+	{ 1, 1, 2, 9, 122, 34, },
+	{ 0, 1, 2, 9, 155, 34, },
+	{ 2, 1, 2, 9, 155, 34, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type2);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type3[] = {
+	{ 0, 0, 0, 0, 1, 46, },
+	{ 2, 0, 0, 0, 1, 40, },
+	{ 1, 0, 0, 0, 1, 40, },
+	{ 0, 0, 0, 0, 2, 46, },
+	{ 2, 0, 0, 0, 2, 40, },
+	{ 1, 0, 0, 0, 2, 40, },
+	{ 0, 0, 0, 0, 3, 46, },
+	{ 2, 0, 0, 0, 3, 40, },
+	{ 1, 0, 0, 0, 3, 40, },
+	{ 0, 0, 0, 0, 4, 46, },
+	{ 2, 0, 0, 0, 4, 40, },
+	{ 1, 0, 0, 0, 4, 40, },
+	{ 0, 0, 0, 0, 5, 46, },
+	{ 2, 0, 0, 0, 5, 40, },
+	{ 1, 0, 0, 0, 5, 40, },
+	{ 0, 0, 0, 0, 6, 46, },
+	{ 2, 0, 0, 0, 6, 40, },
+	{ 1, 0, 0, 0, 6, 40, },
+	{ 0, 0, 0, 0, 7, 46, },
+	{ 2, 0, 0, 0, 7, 40, },
+	{ 1, 0, 0, 0, 7, 40, },
+	{ 0, 0, 0, 0, 8, 46, },
+	{ 2, 0, 0, 0, 8, 40, },
+	{ 1, 0, 0, 0, 8, 40, },
+	{ 0, 0, 0, 0, 9, 46, },
+	{ 2, 0, 0, 0, 9, 40, },
+	{ 1, 0, 0, 0, 9, 40, },
+	{ 0, 0, 0, 0, 10, 46, },
+	{ 2, 0, 0, 0, 10, 40, },
+	{ 1, 0, 0, 0, 10, 40, },
+	{ 0, 0, 0, 0, 11, 46, },
+	{ 2, 0, 0, 0, 11, 40, },
+	{ 1, 0, 0, 0, 11, 40, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 40, },
+	{ 1, 0, 0, 0, 12, 40, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 40, },
+	{ 1, 0, 0, 0, 13, 40, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 40, },
+	{ 0, 0, 0, 1, 1, 46, },
+	{ 2, 0, 0, 1, 1, 40, },
+	{ 1, 0, 0, 1, 1, 40, },
+	{ 0, 0, 0, 1, 2, 46, },
+	{ 2, 0, 0, 1, 2, 40, },
+	{ 1, 0, 0, 1, 2, 40, },
+	{ 0, 0, 0, 1, 3, 46, },
+	{ 2, 0, 0, 1, 3, 40, },
+	{ 1, 0, 0, 1, 3, 40, },
+	{ 0, 0, 0, 1, 4, 46, },
+	{ 2, 0, 0, 1, 4, 40, },
+	{ 1, 0, 0, 1, 4, 40, },
+	{ 0, 0, 0, 1, 5, 46, },
+	{ 2, 0, 0, 1, 5, 40, },
+	{ 1, 0, 0, 1, 5, 40, },
+	{ 0, 0, 0, 1, 6, 46, },
+	{ 2, 0, 0, 1, 6, 40, },
+	{ 1, 0, 0, 1, 6, 40, },
+	{ 0, 0, 0, 1, 7, 46, },
+	{ 2, 0, 0, 1, 7, 40, },
+	{ 1, 0, 0, 1, 7, 40, },
+	{ 0, 0, 0, 1, 8, 46, },
+	{ 2, 0, 0, 1, 8, 40, },
+	{ 1, 0, 0, 1, 8, 40, },
+	{ 0, 0, 0, 1, 9, 46, },
+	{ 2, 0, 0, 1, 9, 40, },
+	{ 1, 0, 0, 1, 9, 40, },
+	{ 0, 0, 0, 1, 10, 46, },
+	{ 2, 0, 0, 1, 10, 40, },
+	{ 1, 0, 0, 1, 10, 40, },
+	{ 0, 0, 0, 1, 11, 46, },
+	{ 2, 0, 0, 1, 11, 40, },
+	{ 1, 0, 0, 1, 11, 40, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 40, },
+	{ 1, 0, 0, 1, 12, 40, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 40, },
+	{ 1, 0, 0, 1, 13, 40, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 46, },
+	{ 2, 0, 0, 2, 1, 40, },
+	{ 1, 0, 0, 2, 1, 40, },
+	{ 0, 0, 0, 2, 2, 46, },
+	{ 2, 0, 0, 2, 2, 40, },
+	{ 1, 0, 0, 2, 2, 40, },
+	{ 0, 0, 0, 2, 3, 46, },
+	{ 2, 0, 0, 2, 3, 40, },
+	{ 1, 0, 0, 2, 3, 40, },
+	{ 0, 0, 0, 2, 4, 46, },
+	{ 2, 0, 0, 2, 4, 40, },
+	{ 1, 0, 0, 2, 4, 40, },
+	{ 0, 0, 0, 2, 5, 46, },
+	{ 2, 0, 0, 2, 5, 40, },
+	{ 1, 0, 0, 2, 5, 40, },
+	{ 0, 0, 0, 2, 6, 46, },
+	{ 2, 0, 0, 2, 6, 40, },
+	{ 1, 0, 0, 2, 6, 40, },
+	{ 0, 0, 0, 2, 7, 46, },
+	{ 2, 0, 0, 2, 7, 40, },
+	{ 1, 0, 0, 2, 7, 40, },
+	{ 0, 0, 0, 2, 8, 46, },
+	{ 2, 0, 0, 2, 8, 40, },
+	{ 1, 0, 0, 2, 8, 40, },
+	{ 0, 0, 0, 2, 9, 46, },
+	{ 2, 0, 0, 2, 9, 40, },
+	{ 1, 0, 0, 2, 9, 40, },
+	{ 0, 0, 0, 2, 10, 46, },
+	{ 2, 0, 0, 2, 10, 40, },
+	{ 1, 0, 0, 2, 10, 40, },
+	{ 0, 0, 0, 2, 11, 46, },
+	{ 2, 0, 0, 2, 11, 40, },
+	{ 1, 0, 0, 2, 11, 40, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 40, },
+	{ 1, 0, 0, 2, 12, 40, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 40, },
+	{ 1, 0, 0, 2, 13, 40, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 46, },
+	{ 2, 0, 0, 3, 1, 40, },
+	{ 1, 0, 0, 3, 1, 40, },
+	{ 0, 0, 0, 3, 2, 46, },
+	{ 2, 0, 0, 3, 2, 40, },
+	{ 1, 0, 0, 3, 2, 40, },
+	{ 0, 0, 0, 3, 3, 46, },
+	{ 2, 0, 0, 3, 3, 40, },
+	{ 1, 0, 0, 3, 3, 40, },
+	{ 0, 0, 0, 3, 4, 46, },
+	{ 2, 0, 0, 3, 4, 40, },
+	{ 1, 0, 0, 3, 4, 40, },
+	{ 0, 0, 0, 3, 5, 46, },
+	{ 2, 0, 0, 3, 5, 40, },
+	{ 1, 0, 0, 3, 5, 40, },
+	{ 0, 0, 0, 3, 6, 46, },
+	{ 2, 0, 0, 3, 6, 40, },
+	{ 1, 0, 0, 3, 6, 40, },
+	{ 0, 0, 0, 3, 7, 46, },
+	{ 2, 0, 0, 3, 7, 40, },
+	{ 1, 0, 0, 3, 7, 40, },
+	{ 0, 0, 0, 3, 8, 46, },
+	{ 2, 0, 0, 3, 8, 40, },
+	{ 1, 0, 0, 3, 8, 40, },
+	{ 0, 0, 0, 3, 9, 46, },
+	{ 2, 0, 0, 3, 9, 40, },
+	{ 1, 0, 0, 3, 9, 40, },
+	{ 0, 0, 0, 3, 10, 46, },
+	{ 2, 0, 0, 3, 10, 40, },
+	{ 1, 0, 0, 3, 10, 40, },
+	{ 0, 0, 0, 3, 11, 46, },
+	{ 2, 0, 0, 3, 11, 40, },
+	{ 1, 0, 0, 3, 11, 40, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 40, },
+	{ 1, 0, 0, 3, 12, 40, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 40, },
+	{ 1, 0, 0, 3, 13, 40, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 46, },
+	{ 2, 0, 0, 6, 1, 40, },
+	{ 1, 0, 0, 6, 1, 40, },
+	{ 0, 0, 0, 6, 2, 46, },
+	{ 2, 0, 0, 6, 2, 40, },
+	{ 1, 0, 0, 6, 2, 40, },
+	{ 0, 0, 0, 6, 3, 46, },
+	{ 2, 0, 0, 6, 3, 40, },
+	{ 1, 0, 0, 6, 3, 40, },
+	{ 0, 0, 0, 6, 4, 46, },
+	{ 2, 0, 0, 6, 4, 40, },
+	{ 1, 0, 0, 6, 4, 40, },
+	{ 0, 0, 0, 6, 5, 46, },
+	{ 2, 0, 0, 6, 5, 40, },
+	{ 1, 0, 0, 6, 5, 40, },
+	{ 0, 0, 0, 6, 6, 46, },
+	{ 2, 0, 0, 6, 6, 40, },
+	{ 1, 0, 0, 6, 6, 40, },
+	{ 0, 0, 0, 6, 7, 46, },
+	{ 2, 0, 0, 6, 7, 40, },
+	{ 1, 0, 0, 6, 7, 40, },
+	{ 0, 0, 0, 6, 8, 46, },
+	{ 2, 0, 0, 6, 8, 40, },
+	{ 1, 0, 0, 6, 8, 40, },
+	{ 0, 0, 0, 6, 9, 46, },
+	{ 2, 0, 0, 6, 9, 40, },
+	{ 1, 0, 0, 6, 9, 40, },
+	{ 0, 0, 0, 6, 10, 46, },
+	{ 2, 0, 0, 6, 10, 40, },
+	{ 1, 0, 0, 6, 10, 40, },
+	{ 0, 0, 0, 6, 11, 46, },
+	{ 2, 0, 0, 6, 11, 40, },
+	{ 1, 0, 0, 6, 11, 40, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 40, },
+	{ 1, 0, 0, 6, 12, 40, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 40, },
+	{ 1, 0, 0, 6, 13, 40, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 46, },
+	{ 2, 0, 0, 7, 1, 40, },
+	{ 1, 0, 0, 7, 1, 40, },
+	{ 0, 0, 0, 7, 2, 46, },
+	{ 2, 0, 0, 7, 2, 40, },
+	{ 1, 0, 0, 7, 2, 40, },
+	{ 0, 0, 0, 7, 3, 46, },
+	{ 2, 0, 0, 7, 3, 40, },
+	{ 1, 0, 0, 7, 3, 40, },
+	{ 0, 0, 0, 7, 4, 46, },
+	{ 2, 0, 0, 7, 4, 40, },
+	{ 1, 0, 0, 7, 4, 40, },
+	{ 0, 0, 0, 7, 5, 46, },
+	{ 2, 0, 0, 7, 5, 40, },
+	{ 1, 0, 0, 7, 5, 40, },
+	{ 0, 0, 0, 7, 6, 46, },
+	{ 2, 0, 0, 7, 6, 40, },
+	{ 1, 0, 0, 7, 6, 40, },
+	{ 0, 0, 0, 7, 7, 46, },
+	{ 2, 0, 0, 7, 7, 40, },
+	{ 1, 0, 0, 7, 7, 40, },
+	{ 0, 0, 0, 7, 8, 46, },
+	{ 2, 0, 0, 7, 8, 40, },
+	{ 1, 0, 0, 7, 8, 40, },
+	{ 0, 0, 0, 7, 9, 46, },
+	{ 2, 0, 0, 7, 9, 40, },
+	{ 1, 0, 0, 7, 9, 40, },
+	{ 0, 0, 0, 7, 10, 46, },
+	{ 2, 0, 0, 7, 10, 40, },
+	{ 1, 0, 0, 7, 10, 40, },
+	{ 0, 0, 0, 7, 11, 46, },
+	{ 2, 0, 0, 7, 11, 40, },
+	{ 1, 0, 0, 7, 11, 40, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 40, },
+	{ 1, 0, 0, 7, 12, 40, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 40, },
+	{ 1, 0, 0, 7, 13, 40, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 46, },
+	{ 2, 0, 1, 2, 3, 40, },
+	{ 1, 0, 1, 2, 3, 40, },
+	{ 0, 0, 1, 2, 4, 46, },
+	{ 2, 0, 1, 2, 4, 40, },
+	{ 1, 0, 1, 2, 4, 40, },
+	{ 0, 0, 1, 2, 5, 46, },
+	{ 2, 0, 1, 2, 5, 40, },
+	{ 1, 0, 1, 2, 5, 40, },
+	{ 0, 0, 1, 2, 6, 46, },
+	{ 2, 0, 1, 2, 6, 40, },
+	{ 1, 0, 1, 2, 6, 40, },
+	{ 0, 0, 1, 2, 7, 46, },
+	{ 2, 0, 1, 2, 7, 40, },
+	{ 1, 0, 1, 2, 7, 40, },
+	{ 0, 0, 1, 2, 8, 46, },
+	{ 2, 0, 1, 2, 8, 40, },
+	{ 1, 0, 1, 2, 8, 40, },
+	{ 0, 0, 1, 2, 9, 46, },
+	{ 2, 0, 1, 2, 9, 40, },
+	{ 1, 0, 1, 2, 9, 40, },
+	{ 0, 0, 1, 2, 10, 46, },
+	{ 2, 0, 1, 2, 10, 40, },
+	{ 1, 0, 1, 2, 10, 40, },
+	{ 0, 0, 1, 2, 11, 46, },
+	{ 2, 0, 1, 2, 11, 40, },
+	{ 1, 0, 1, 2, 11, 40, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 40, },
+	{ 1, 0, 1, 2, 12, 40, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 40, },
+	{ 1, 0, 1, 2, 13, 40, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 46, },
+	{ 2, 0, 1, 3, 3, 40, },
+	{ 1, 0, 1, 3, 3, 40, },
+	{ 0, 0, 1, 3, 4, 46, },
+	{ 2, 0, 1, 3, 4, 40, },
+	{ 1, 0, 1, 3, 4, 40, },
+	{ 0, 0, 1, 3, 5, 46, },
+	{ 2, 0, 1, 3, 5, 40, },
+	{ 1, 0, 1, 3, 5, 40, },
+	{ 0, 0, 1, 3, 6, 46, },
+	{ 2, 0, 1, 3, 6, 40, },
+	{ 1, 0, 1, 3, 6, 40, },
+	{ 0, 0, 1, 3, 7, 46, },
+	{ 2, 0, 1, 3, 7, 40, },
+	{ 1, 0, 1, 3, 7, 40, },
+	{ 0, 0, 1, 3, 8, 46, },
+	{ 2, 0, 1, 3, 8, 40, },
+	{ 1, 0, 1, 3, 8, 40, },
+	{ 0, 0, 1, 3, 9, 46, },
+	{ 2, 0, 1, 3, 9, 40, },
+	{ 1, 0, 1, 3, 9, 40, },
+	{ 0, 0, 1, 3, 10, 46, },
+	{ 2, 0, 1, 3, 10, 40, },
+	{ 1, 0, 1, 3, 10, 40, },
+	{ 0, 0, 1, 3, 11, 46, },
+	{ 2, 0, 1, 3, 11, 40, },
+	{ 1, 0, 1, 3, 11, 40, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 40, },
+	{ 1, 0, 1, 3, 12, 40, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 40, },
+	{ 1, 0, 1, 3, 13, 40, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 46, },
+	{ 2, 0, 1, 6, 3, 40, },
+	{ 1, 0, 1, 6, 3, 40, },
+	{ 0, 0, 1, 6, 4, 46, },
+	{ 2, 0, 1, 6, 4, 40, },
+	{ 1, 0, 1, 6, 4, 40, },
+	{ 0, 0, 1, 6, 5, 46, },
+	{ 2, 0, 1, 6, 5, 40, },
+	{ 1, 0, 1, 6, 5, 40, },
+	{ 0, 0, 1, 6, 6, 46, },
+	{ 2, 0, 1, 6, 6, 40, },
+	{ 1, 0, 1, 6, 6, 40, },
+	{ 0, 0, 1, 6, 7, 46, },
+	{ 2, 0, 1, 6, 7, 40, },
+	{ 1, 0, 1, 6, 7, 40, },
+	{ 0, 0, 1, 6, 8, 46, },
+	{ 2, 0, 1, 6, 8, 40, },
+	{ 1, 0, 1, 6, 8, 40, },
+	{ 0, 0, 1, 6, 9, 46, },
+	{ 2, 0, 1, 6, 9, 40, },
+	{ 1, 0, 1, 6, 9, 40, },
+	{ 0, 0, 1, 6, 10, 46, },
+	{ 2, 0, 1, 6, 10, 40, },
+	{ 1, 0, 1, 6, 10, 40, },
+	{ 0, 0, 1, 6, 11, 46, },
+	{ 2, 0, 1, 6, 11, 40, },
+	{ 1, 0, 1, 6, 11, 40, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 40, },
+	{ 1, 0, 1, 6, 12, 40, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 40, },
+	{ 1, 0, 1, 6, 13, 40, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 46, },
+	{ 2, 0, 1, 7, 3, 40, },
+	{ 1, 0, 1, 7, 3, 40, },
+	{ 0, 0, 1, 7, 4, 46, },
+	{ 2, 0, 1, 7, 4, 40, },
+	{ 1, 0, 1, 7, 4, 40, },
+	{ 0, 0, 1, 7, 5, 46, },
+	{ 2, 0, 1, 7, 5, 40, },
+	{ 1, 0, 1, 7, 5, 40, },
+	{ 0, 0, 1, 7, 6, 46, },
+	{ 2, 0, 1, 7, 6, 40, },
+	{ 1, 0, 1, 7, 6, 40, },
+	{ 0, 0, 1, 7, 7, 46, },
+	{ 2, 0, 1, 7, 7, 40, },
+	{ 1, 0, 1, 7, 7, 40, },
+	{ 0, 0, 1, 7, 8, 46, },
+	{ 2, 0, 1, 7, 8, 40, },
+	{ 1, 0, 1, 7, 8, 40, },
+	{ 0, 0, 1, 7, 9, 46, },
+	{ 2, 0, 1, 7, 9, 40, },
+	{ 1, 0, 1, 7, 9, 40, },
+	{ 0, 0, 1, 7, 10, 46, },
+	{ 2, 0, 1, 7, 10, 40, },
+	{ 1, 0, 1, 7, 10, 40, },
+	{ 0, 0, 1, 7, 11, 46, },
+	{ 2, 0, 1, 7, 11, 40, },
+	{ 1, 0, 1, 7, 11, 40, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 40, },
+	{ 1, 0, 1, 7, 12, 40, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 40, },
+	{ 1, 0, 1, 7, 13, 40, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 46, },
+	{ 2, 1, 0, 1, 36, 40, },
+	{ 1, 1, 0, 1, 36, 40, },
+	{ 0, 1, 0, 1, 40, 46, },
+	{ 2, 1, 0, 1, 40, 40, },
+	{ 1, 1, 0, 1, 40, 40, },
+	{ 0, 1, 0, 1, 44, 46, },
+	{ 2, 1, 0, 1, 44, 40, },
+	{ 1, 1, 0, 1, 44, 40, },
+	{ 0, 1, 0, 1, 48, 46, },
+	{ 2, 1, 0, 1, 48, 40, },
+	{ 1, 1, 0, 1, 48, 40, },
+	{ 0, 1, 0, 1, 52, 46, },
+	{ 2, 1, 0, 1, 52, 40, },
+	{ 1, 1, 0, 1, 52, 40, },
+	{ 0, 1, 0, 1, 56, 46, },
+	{ 2, 1, 0, 1, 56, 40, },
+	{ 1, 1, 0, 1, 56, 40, },
+	{ 0, 1, 0, 1, 60, 46, },
+	{ 2, 1, 0, 1, 60, 40, },
+	{ 1, 1, 0, 1, 60, 40, },
+	{ 0, 1, 0, 1, 64, 46, },
+	{ 2, 1, 0, 1, 64, 40, },
+	{ 1, 1, 0, 1, 64, 40, },
+	{ 0, 1, 0, 1, 100, 46, },
+	{ 2, 1, 0, 1, 100, 40, },
+	{ 1, 1, 0, 1, 100, 40, },
+	{ 0, 1, 0, 1, 104, 46, },
+	{ 2, 1, 0, 1, 104, 40, },
+	{ 1, 1, 0, 1, 104, 40, },
+	{ 0, 1, 0, 1, 108, 46, },
+	{ 2, 1, 0, 1, 108, 40, },
+	{ 1, 1, 0, 1, 108, 40, },
+	{ 0, 1, 0, 1, 112, 46, },
+	{ 2, 1, 0, 1, 112, 40, },
+	{ 1, 1, 0, 1, 112, 40, },
+	{ 0, 1, 0, 1, 116, 46, },
+	{ 2, 1, 0, 1, 116, 40, },
+	{ 1, 1, 0, 1, 116, 40, },
+	{ 0, 1, 0, 1, 120, 46, },
+	{ 2, 1, 0, 1, 120, 40, },
+	{ 1, 1, 0, 1, 120, 40, },
+	{ 0, 1, 0, 1, 124, 46, },
+	{ 2, 1, 0, 1, 124, 40, },
+	{ 1, 1, 0, 1, 124, 40, },
+	{ 0, 1, 0, 1, 128, 46, },
+	{ 2, 1, 0, 1, 128, 40, },
+	{ 1, 1, 0, 1, 128, 40, },
+	{ 0, 1, 0, 1, 132, 46, },
+	{ 2, 1, 0, 1, 132, 40, },
+	{ 1, 1, 0, 1, 132, 40, },
+	{ 0, 1, 0, 1, 136, 46, },
+	{ 2, 1, 0, 1, 136, 40, },
+	{ 1, 1, 0, 1, 136, 40, },
+	{ 0, 1, 0, 1, 140, 46, },
+	{ 2, 1, 0, 1, 140, 40, },
+	{ 1, 1, 0, 1, 140, 40, },
+	{ 0, 1, 0, 1, 149, 46, },
+	{ 2, 1, 0, 1, 149, 40, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 46, },
+	{ 2, 1, 0, 1, 153, 40, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 46, },
+	{ 2, 1, 0, 1, 157, 40, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 46, },
+	{ 2, 1, 0, 1, 161, 40, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 46, },
+	{ 2, 1, 0, 1, 165, 40, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 46, },
+	{ 2, 1, 0, 2, 36, 40, },
+	{ 1, 1, 0, 2, 36, 40, },
+	{ 0, 1, 0, 2, 40, 46, },
+	{ 2, 1, 0, 2, 40, 40, },
+	{ 1, 1, 0, 2, 40, 40, },
+	{ 0, 1, 0, 2, 44, 46, },
+	{ 2, 1, 0, 2, 44, 40, },
+	{ 1, 1, 0, 2, 44, 40, },
+	{ 0, 1, 0, 2, 48, 46, },
+	{ 2, 1, 0, 2, 48, 40, },
+	{ 1, 1, 0, 2, 48, 40, },
+	{ 0, 1, 0, 2, 52, 46, },
+	{ 2, 1, 0, 2, 52, 40, },
+	{ 1, 1, 0, 2, 52, 40, },
+	{ 0, 1, 0, 2, 56, 46, },
+	{ 2, 1, 0, 2, 56, 40, },
+	{ 1, 1, 0, 2, 56, 40, },
+	{ 0, 1, 0, 2, 60, 46, },
+	{ 2, 1, 0, 2, 60, 40, },
+	{ 1, 1, 0, 2, 60, 40, },
+	{ 0, 1, 0, 2, 64, 46, },
+	{ 2, 1, 0, 2, 64, 40, },
+	{ 1, 1, 0, 2, 64, 40, },
+	{ 0, 1, 0, 2, 100, 46, },
+	{ 2, 1, 0, 2, 100, 40, },
+	{ 1, 1, 0, 2, 100, 40, },
+	{ 0, 1, 0, 2, 104, 46, },
+	{ 2, 1, 0, 2, 104, 40, },
+	{ 1, 1, 0, 2, 104, 40, },
+	{ 0, 1, 0, 2, 108, 46, },
+	{ 2, 1, 0, 2, 108, 40, },
+	{ 1, 1, 0, 2, 108, 40, },
+	{ 0, 1, 0, 2, 112, 46, },
+	{ 2, 1, 0, 2, 112, 40, },
+	{ 1, 1, 0, 2, 112, 40, },
+	{ 0, 1, 0, 2, 116, 46, },
+	{ 2, 1, 0, 2, 116, 40, },
+	{ 1, 1, 0, 2, 116, 40, },
+	{ 0, 1, 0, 2, 120, 46, },
+	{ 2, 1, 0, 2, 120, 40, },
+	{ 1, 1, 0, 2, 120, 40, },
+	{ 0, 1, 0, 2, 124, 46, },
+	{ 2, 1, 0, 2, 124, 40, },
+	{ 1, 1, 0, 2, 124, 40, },
+	{ 0, 1, 0, 2, 128, 46, },
+	{ 2, 1, 0, 2, 128, 40, },
+	{ 1, 1, 0, 2, 128, 40, },
+	{ 0, 1, 0, 2, 132, 46, },
+	{ 2, 1, 0, 2, 132, 40, },
+	{ 1, 1, 0, 2, 132, 40, },
+	{ 0, 1, 0, 2, 136, 46, },
+	{ 2, 1, 0, 2, 136, 40, },
+	{ 1, 1, 0, 2, 136, 40, },
+	{ 0, 1, 0, 2, 140, 46, },
+	{ 2, 1, 0, 2, 140, 40, },
+	{ 1, 1, 0, 2, 140, 40, },
+	{ 0, 1, 0, 2, 149, 46, },
+	{ 2, 1, 0, 2, 149, 40, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 46, },
+	{ 2, 1, 0, 2, 153, 40, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 46, },
+	{ 2, 1, 0, 2, 157, 40, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 46, },
+	{ 2, 1, 0, 2, 161, 40, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 46, },
+	{ 2, 1, 0, 2, 165, 40, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 46, },
+	{ 2, 1, 0, 3, 36, 40, },
+	{ 1, 1, 0, 3, 36, 40, },
+	{ 0, 1, 0, 3, 40, 46, },
+	{ 2, 1, 0, 3, 40, 40, },
+	{ 1, 1, 0, 3, 40, 40, },
+	{ 0, 1, 0, 3, 44, 46, },
+	{ 2, 1, 0, 3, 44, 40, },
+	{ 1, 1, 0, 3, 44, 40, },
+	{ 0, 1, 0, 3, 48, 46, },
+	{ 2, 1, 0, 3, 48, 40, },
+	{ 1, 1, 0, 3, 48, 40, },
+	{ 0, 1, 0, 3, 52, 46, },
+	{ 2, 1, 0, 3, 52, 40, },
+	{ 1, 1, 0, 3, 52, 40, },
+	{ 0, 1, 0, 3, 56, 46, },
+	{ 2, 1, 0, 3, 56, 40, },
+	{ 1, 1, 0, 3, 56, 40, },
+	{ 0, 1, 0, 3, 60, 46, },
+	{ 2, 1, 0, 3, 60, 40, },
+	{ 1, 1, 0, 3, 60, 40, },
+	{ 0, 1, 0, 3, 64, 46, },
+	{ 2, 1, 0, 3, 64, 40, },
+	{ 1, 1, 0, 3, 64, 40, },
+	{ 0, 1, 0, 3, 100, 46, },
+	{ 2, 1, 0, 3, 100, 40, },
+	{ 1, 1, 0, 3, 100, 40, },
+	{ 0, 1, 0, 3, 104, 46, },
+	{ 2, 1, 0, 3, 104, 40, },
+	{ 1, 1, 0, 3, 104, 40, },
+	{ 0, 1, 0, 3, 108, 46, },
+	{ 2, 1, 0, 3, 108, 40, },
+	{ 1, 1, 0, 3, 108, 40, },
+	{ 0, 1, 0, 3, 112, 46, },
+	{ 2, 1, 0, 3, 112, 40, },
+	{ 1, 1, 0, 3, 112, 40, },
+	{ 0, 1, 0, 3, 116, 46, },
+	{ 2, 1, 0, 3, 116, 40, },
+	{ 1, 1, 0, 3, 116, 40, },
+	{ 0, 1, 0, 3, 120, 46, },
+	{ 2, 1, 0, 3, 120, 40, },
+	{ 1, 1, 0, 3, 120, 40, },
+	{ 0, 1, 0, 3, 124, 46, },
+	{ 2, 1, 0, 3, 124, 40, },
+	{ 1, 1, 0, 3, 124, 40, },
+	{ 0, 1, 0, 3, 128, 46, },
+	{ 2, 1, 0, 3, 128, 40, },
+	{ 1, 1, 0, 3, 128, 40, },
+	{ 0, 1, 0, 3, 132, 46, },
+	{ 2, 1, 0, 3, 132, 40, },
+	{ 1, 1, 0, 3, 132, 40, },
+	{ 0, 1, 0, 3, 136, 46, },
+	{ 2, 1, 0, 3, 136, 40, },
+	{ 1, 1, 0, 3, 136, 40, },
+	{ 0, 1, 0, 3, 140, 46, },
+	{ 2, 1, 0, 3, 140, 40, },
+	{ 1, 1, 0, 3, 140, 40, },
+	{ 0, 1, 0, 3, 149, 46, },
+	{ 2, 1, 0, 3, 149, 40, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 46, },
+	{ 2, 1, 0, 3, 153, 40, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 46, },
+	{ 2, 1, 0, 3, 157, 40, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 46, },
+	{ 2, 1, 0, 3, 161, 40, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 46, },
+	{ 2, 1, 0, 3, 165, 40, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 46, },
+	{ 2, 1, 0, 6, 36, 40, },
+	{ 1, 1, 0, 6, 36, 40, },
+	{ 0, 1, 0, 6, 40, 46, },
+	{ 2, 1, 0, 6, 40, 40, },
+	{ 1, 1, 0, 6, 40, 40, },
+	{ 0, 1, 0, 6, 44, 46, },
+	{ 2, 1, 0, 6, 44, 40, },
+	{ 1, 1, 0, 6, 44, 40, },
+	{ 0, 1, 0, 6, 48, 46, },
+	{ 2, 1, 0, 6, 48, 40, },
+	{ 1, 1, 0, 6, 48, 40, },
+	{ 0, 1, 0, 6, 52, 46, },
+	{ 2, 1, 0, 6, 52, 40, },
+	{ 1, 1, 0, 6, 52, 40, },
+	{ 0, 1, 0, 6, 56, 46, },
+	{ 2, 1, 0, 6, 56, 40, },
+	{ 1, 1, 0, 6, 56, 40, },
+	{ 0, 1, 0, 6, 60, 46, },
+	{ 2, 1, 0, 6, 60, 40, },
+	{ 1, 1, 0, 6, 60, 40, },
+	{ 0, 1, 0, 6, 64, 46, },
+	{ 2, 1, 0, 6, 64, 40, },
+	{ 1, 1, 0, 6, 64, 40, },
+	{ 0, 1, 0, 6, 100, 46, },
+	{ 2, 1, 0, 6, 100, 40, },
+	{ 1, 1, 0, 6, 100, 40, },
+	{ 0, 1, 0, 6, 104, 46, },
+	{ 2, 1, 0, 6, 104, 40, },
+	{ 1, 1, 0, 6, 104, 40, },
+	{ 0, 1, 0, 6, 108, 46, },
+	{ 2, 1, 0, 6, 108, 40, },
+	{ 1, 1, 0, 6, 108, 40, },
+	{ 0, 1, 0, 6, 112, 46, },
+	{ 2, 1, 0, 6, 112, 40, },
+	{ 1, 1, 0, 6, 112, 40, },
+	{ 0, 1, 0, 6, 116, 46, },
+	{ 2, 1, 0, 6, 116, 40, },
+	{ 1, 1, 0, 6, 116, 40, },
+	{ 0, 1, 0, 6, 120, 46, },
+	{ 2, 1, 0, 6, 120, 40, },
+	{ 1, 1, 0, 6, 120, 40, },
+	{ 0, 1, 0, 6, 124, 46, },
+	{ 2, 1, 0, 6, 124, 40, },
+	{ 1, 1, 0, 6, 124, 40, },
+	{ 0, 1, 0, 6, 128, 46, },
+	{ 2, 1, 0, 6, 128, 40, },
+	{ 1, 1, 0, 6, 128, 40, },
+	{ 0, 1, 0, 6, 132, 46, },
+	{ 2, 1, 0, 6, 132, 40, },
+	{ 1, 1, 0, 6, 132, 40, },
+	{ 0, 1, 0, 6, 136, 46, },
+	{ 2, 1, 0, 6, 136, 40, },
+	{ 1, 1, 0, 6, 136, 40, },
+	{ 0, 1, 0, 6, 140, 46, },
+	{ 2, 1, 0, 6, 140, 40, },
+	{ 1, 1, 0, 6, 140, 40, },
+	{ 0, 1, 0, 6, 149, 46, },
+	{ 2, 1, 0, 6, 149, 40, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 46, },
+	{ 2, 1, 0, 6, 153, 40, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 46, },
+	{ 2, 1, 0, 6, 157, 40, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 46, },
+	{ 2, 1, 0, 6, 161, 40, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 46, },
+	{ 2, 1, 0, 6, 165, 40, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 46, },
+	{ 2, 1, 0, 7, 36, 40, },
+	{ 1, 1, 0, 7, 36, 40, },
+	{ 0, 1, 0, 7, 40, 46, },
+	{ 2, 1, 0, 7, 40, 40, },
+	{ 1, 1, 0, 7, 40, 40, },
+	{ 0, 1, 0, 7, 44, 46, },
+	{ 2, 1, 0, 7, 44, 40, },
+	{ 1, 1, 0, 7, 44, 40, },
+	{ 0, 1, 0, 7, 48, 46, },
+	{ 2, 1, 0, 7, 48, 40, },
+	{ 1, 1, 0, 7, 48, 40, },
+	{ 0, 1, 0, 7, 52, 46, },
+	{ 2, 1, 0, 7, 52, 40, },
+	{ 1, 1, 0, 7, 52, 40, },
+	{ 0, 1, 0, 7, 56, 46, },
+	{ 2, 1, 0, 7, 56, 40, },
+	{ 1, 1, 0, 7, 56, 40, },
+	{ 0, 1, 0, 7, 60, 46, },
+	{ 2, 1, 0, 7, 60, 40, },
+	{ 1, 1, 0, 7, 60, 40, },
+	{ 0, 1, 0, 7, 64, 46, },
+	{ 2, 1, 0, 7, 64, 40, },
+	{ 1, 1, 0, 7, 64, 40, },
+	{ 0, 1, 0, 7, 100, 46, },
+	{ 2, 1, 0, 7, 100, 40, },
+	{ 1, 1, 0, 7, 100, 40, },
+	{ 0, 1, 0, 7, 104, 46, },
+	{ 2, 1, 0, 7, 104, 40, },
+	{ 1, 1, 0, 7, 104, 40, },
+	{ 0, 1, 0, 7, 108, 46, },
+	{ 2, 1, 0, 7, 108, 40, },
+	{ 1, 1, 0, 7, 108, 40, },
+	{ 0, 1, 0, 7, 112, 46, },
+	{ 2, 1, 0, 7, 112, 40, },
+	{ 1, 1, 0, 7, 112, 40, },
+	{ 0, 1, 0, 7, 116, 46, },
+	{ 2, 1, 0, 7, 116, 40, },
+	{ 1, 1, 0, 7, 116, 40, },
+	{ 0, 1, 0, 7, 120, 46, },
+	{ 2, 1, 0, 7, 120, 40, },
+	{ 1, 1, 0, 7, 120, 40, },
+	{ 0, 1, 0, 7, 124, 46, },
+	{ 2, 1, 0, 7, 124, 40, },
+	{ 1, 1, 0, 7, 124, 40, },
+	{ 0, 1, 0, 7, 128, 46, },
+	{ 2, 1, 0, 7, 128, 40, },
+	{ 1, 1, 0, 7, 128, 40, },
+	{ 0, 1, 0, 7, 132, 46, },
+	{ 2, 1, 0, 7, 132, 40, },
+	{ 1, 1, 0, 7, 132, 40, },
+	{ 0, 1, 0, 7, 136, 46, },
+	{ 2, 1, 0, 7, 136, 40, },
+	{ 1, 1, 0, 7, 136, 40, },
+	{ 0, 1, 0, 7, 140, 46, },
+	{ 2, 1, 0, 7, 140, 40, },
+	{ 1, 1, 0, 7, 140, 40, },
+	{ 0, 1, 0, 7, 149, 46, },
+	{ 2, 1, 0, 7, 149, 40, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 46, },
+	{ 2, 1, 0, 7, 153, 40, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 46, },
+	{ 2, 1, 0, 7, 157, 40, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 46, },
+	{ 2, 1, 0, 7, 161, 40, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 46, },
+	{ 2, 1, 0, 7, 165, 40, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 46, },
+	{ 2, 1, 1, 2, 38, 40, },
+	{ 1, 1, 1, 2, 38, 40, },
+	{ 0, 1, 1, 2, 46, 46, },
+	{ 2, 1, 1, 2, 46, 40, },
+	{ 1, 1, 1, 2, 46, 40, },
+	{ 0, 1, 1, 2, 54, 46, },
+	{ 2, 1, 1, 2, 54, 40, },
+	{ 1, 1, 1, 2, 54, 40, },
+	{ 0, 1, 1, 2, 62, 46, },
+	{ 2, 1, 1, 2, 62, 40, },
+	{ 1, 1, 1, 2, 62, 40, },
+	{ 0, 1, 1, 2, 102, 46, },
+	{ 2, 1, 1, 2, 102, 40, },
+	{ 1, 1, 1, 2, 102, 40, },
+	{ 0, 1, 1, 2, 110, 46, },
+	{ 2, 1, 1, 2, 110, 40, },
+	{ 1, 1, 1, 2, 110, 40, },
+	{ 0, 1, 1, 2, 118, 46, },
+	{ 2, 1, 1, 2, 118, 40, },
+	{ 1, 1, 1, 2, 118, 40, },
+	{ 0, 1, 1, 2, 126, 46, },
+	{ 2, 1, 1, 2, 126, 40, },
+	{ 1, 1, 1, 2, 126, 40, },
+	{ 0, 1, 1, 2, 134, 46, },
+	{ 2, 1, 1, 2, 134, 40, },
+	{ 1, 1, 1, 2, 134, 40, },
+	{ 0, 1, 1, 2, 151, 46, },
+	{ 2, 1, 1, 2, 151, 40, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 46, },
+	{ 2, 1, 1, 2, 159, 40, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 46, },
+	{ 2, 1, 1, 3, 38, 40, },
+	{ 1, 1, 1, 3, 38, 40, },
+	{ 0, 1, 1, 3, 46, 46, },
+	{ 2, 1, 1, 3, 46, 40, },
+	{ 1, 1, 1, 3, 46, 40, },
+	{ 0, 1, 1, 3, 54, 46, },
+	{ 2, 1, 1, 3, 54, 40, },
+	{ 1, 1, 1, 3, 54, 40, },
+	{ 0, 1, 1, 3, 62, 46, },
+	{ 2, 1, 1, 3, 62, 40, },
+	{ 1, 1, 1, 3, 62, 40, },
+	{ 0, 1, 1, 3, 102, 46, },
+	{ 2, 1, 1, 3, 102, 40, },
+	{ 1, 1, 1, 3, 102, 40, },
+	{ 0, 1, 1, 3, 110, 46, },
+	{ 2, 1, 1, 3, 110, 40, },
+	{ 1, 1, 1, 3, 110, 40, },
+	{ 0, 1, 1, 3, 118, 46, },
+	{ 2, 1, 1, 3, 118, 40, },
+	{ 1, 1, 1, 3, 118, 40, },
+	{ 0, 1, 1, 3, 126, 46, },
+	{ 2, 1, 1, 3, 126, 40, },
+	{ 1, 1, 1, 3, 126, 40, },
+	{ 0, 1, 1, 3, 134, 46, },
+	{ 2, 1, 1, 3, 134, 40, },
+	{ 1, 1, 1, 3, 134, 40, },
+	{ 0, 1, 1, 3, 151, 46, },
+	{ 2, 1, 1, 3, 151, 40, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 46, },
+	{ 2, 1, 1, 3, 159, 40, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 46, },
+	{ 2, 1, 1, 6, 38, 40, },
+	{ 1, 1, 1, 6, 38, 40, },
+	{ 0, 1, 1, 6, 46, 46, },
+	{ 2, 1, 1, 6, 46, 40, },
+	{ 1, 1, 1, 6, 46, 40, },
+	{ 0, 1, 1, 6, 54, 46, },
+	{ 2, 1, 1, 6, 54, 40, },
+	{ 1, 1, 1, 6, 54, 40, },
+	{ 0, 1, 1, 6, 62, 46, },
+	{ 2, 1, 1, 6, 62, 40, },
+	{ 1, 1, 1, 6, 62, 40, },
+	{ 0, 1, 1, 6, 102, 46, },
+	{ 2, 1, 1, 6, 102, 40, },
+	{ 1, 1, 1, 6, 102, 40, },
+	{ 0, 1, 1, 6, 110, 46, },
+	{ 2, 1, 1, 6, 110, 40, },
+	{ 1, 1, 1, 6, 110, 40, },
+	{ 0, 1, 1, 6, 118, 46, },
+	{ 2, 1, 1, 6, 118, 40, },
+	{ 1, 1, 1, 6, 118, 40, },
+	{ 0, 1, 1, 6, 126, 46, },
+	{ 2, 1, 1, 6, 126, 40, },
+	{ 1, 1, 1, 6, 126, 40, },
+	{ 0, 1, 1, 6, 134, 46, },
+	{ 2, 1, 1, 6, 134, 40, },
+	{ 1, 1, 1, 6, 134, 40, },
+	{ 0, 1, 1, 6, 151, 46, },
+	{ 2, 1, 1, 6, 151, 40, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 46, },
+	{ 2, 1, 1, 6, 159, 40, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 46, },
+	{ 2, 1, 1, 7, 38, 40, },
+	{ 1, 1, 1, 7, 38, 40, },
+	{ 0, 1, 1, 7, 46, 46, },
+	{ 2, 1, 1, 7, 46, 40, },
+	{ 1, 1, 1, 7, 46, 40, },
+	{ 0, 1, 1, 7, 54, 46, },
+	{ 2, 1, 1, 7, 54, 40, },
+	{ 1, 1, 1, 7, 54, 40, },
+	{ 0, 1, 1, 7, 62, 46, },
+	{ 2, 1, 1, 7, 62, 40, },
+	{ 1, 1, 1, 7, 62, 40, },
+	{ 0, 1, 1, 7, 102, 46, },
+	{ 2, 1, 1, 7, 102, 40, },
+	{ 1, 1, 1, 7, 102, 40, },
+	{ 0, 1, 1, 7, 110, 46, },
+	{ 2, 1, 1, 7, 110, 40, },
+	{ 1, 1, 1, 7, 110, 40, },
+	{ 0, 1, 1, 7, 118, 46, },
+	{ 2, 1, 1, 7, 118, 40, },
+	{ 1, 1, 1, 7, 118, 40, },
+	{ 0, 1, 1, 7, 126, 46, },
+	{ 2, 1, 1, 7, 126, 40, },
+	{ 1, 1, 1, 7, 126, 40, },
+	{ 0, 1, 1, 7, 134, 46, },
+	{ 2, 1, 1, 7, 134, 40, },
+	{ 1, 1, 1, 7, 134, 40, },
+	{ 0, 1, 1, 7, 151, 46, },
+	{ 2, 1, 1, 7, 151, 40, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 46, },
+	{ 2, 1, 1, 7, 159, 40, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 46, },
+	{ 2, 1, 2, 4, 42, 40, },
+	{ 1, 1, 2, 4, 42, 40, },
+	{ 0, 1, 2, 4, 58, 46, },
+	{ 2, 1, 2, 4, 58, 40, },
+	{ 1, 1, 2, 4, 58, 40, },
+	{ 0, 1, 2, 4, 106, 46, },
+	{ 2, 1, 2, 4, 106, 40, },
+	{ 1, 1, 2, 4, 106, 40, },
+	{ 0, 1, 2, 4, 122, 46, },
+	{ 2, 1, 2, 4, 122, 40, },
+	{ 1, 1, 2, 4, 122, 40, },
+	{ 0, 1, 2, 4, 155, 46, },
+	{ 2, 1, 2, 4, 155, 40, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 46, },
+	{ 2, 1, 2, 5, 42, 40, },
+	{ 1, 1, 2, 5, 42, 40, },
+	{ 0, 1, 2, 5, 58, 46, },
+	{ 2, 1, 2, 5, 58, 40, },
+	{ 1, 1, 2, 5, 58, 40, },
+	{ 0, 1, 2, 5, 106, 46, },
+	{ 2, 1, 2, 5, 106, 40, },
+	{ 1, 1, 2, 5, 106, 40, },
+	{ 0, 1, 2, 5, 122, 46, },
+	{ 2, 1, 2, 5, 122, 40, },
+	{ 1, 1, 2, 5, 122, 40, },
+	{ 0, 1, 2, 5, 155, 46, },
+	{ 2, 1, 2, 5, 155, 40, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 46, },
+	{ 2, 1, 2, 8, 42, 40, },
+	{ 1, 1, 2, 8, 42, 40, },
+	{ 0, 1, 2, 8, 58, 46, },
+	{ 2, 1, 2, 8, 58, 40, },
+	{ 1, 1, 2, 8, 58, 40, },
+	{ 0, 1, 2, 8, 106, 46, },
+	{ 2, 1, 2, 8, 106, 40, },
+	{ 1, 1, 2, 8, 106, 40, },
+	{ 0, 1, 2, 8, 122, 46, },
+	{ 2, 1, 2, 8, 122, 40, },
+	{ 1, 1, 2, 8, 122, 40, },
+	{ 0, 1, 2, 8, 155, 46, },
+	{ 2, 1, 2, 8, 155, 40, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 46, },
+	{ 2, 1, 2, 9, 42, 40, },
+	{ 1, 1, 2, 9, 42, 40, },
+	{ 0, 1, 2, 9, 58, 46, },
+	{ 2, 1, 2, 9, 58, 40, },
+	{ 1, 1, 2, 9, 58, 40, },
+	{ 0, 1, 2, 9, 106, 46, },
+	{ 2, 1, 2, 9, 106, 40, },
+	{ 1, 1, 2, 9, 106, 40, },
+	{ 0, 1, 2, 9, 122, 46, },
+	{ 2, 1, 2, 9, 122, 40, },
+	{ 1, 1, 2, 9, 122, 40, },
+	{ 0, 1, 2, 9, 155, 46, },
+	{ 2, 1, 2, 9, 155, 40, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type3);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type5[] = {
+	{ 0, 0, 0, 0, 1, 46, },
+	{ 2, 0, 0, 0, 1, 40, },
+	{ 1, 0, 0, 0, 1, 40, },
+	{ 0, 0, 0, 0, 2, 46, },
+	{ 2, 0, 0, 0, 2, 40, },
+	{ 1, 0, 0, 0, 2, 40, },
+	{ 0, 0, 0, 0, 3, 46, },
+	{ 2, 0, 0, 0, 3, 40, },
+	{ 1, 0, 0, 0, 3, 40, },
+	{ 0, 0, 0, 0, 4, 46, },
+	{ 2, 0, 0, 0, 4, 40, },
+	{ 1, 0, 0, 0, 4, 40, },
+	{ 0, 0, 0, 0, 5, 46, },
+	{ 2, 0, 0, 0, 5, 40, },
+	{ 1, 0, 0, 0, 5, 40, },
+	{ 0, 0, 0, 0, 6, 46, },
+	{ 2, 0, 0, 0, 6, 40, },
+	{ 1, 0, 0, 0, 6, 40, },
+	{ 0, 0, 0, 0, 7, 46, },
+	{ 2, 0, 0, 0, 7, 40, },
+	{ 1, 0, 0, 0, 7, 40, },
+	{ 0, 0, 0, 0, 8, 46, },
+	{ 2, 0, 0, 0, 8, 40, },
+	{ 1, 0, 0, 0, 8, 40, },
+	{ 0, 0, 0, 0, 9, 46, },
+	{ 2, 0, 0, 0, 9, 40, },
+	{ 1, 0, 0, 0, 9, 40, },
+	{ 0, 0, 0, 0, 10, 46, },
+	{ 2, 0, 0, 0, 10, 40, },
+	{ 1, 0, 0, 0, 10, 40, },
+	{ 0, 0, 0, 0, 11, 46, },
+	{ 2, 0, 0, 0, 11, 40, },
+	{ 1, 0, 0, 0, 11, 40, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 40, },
+	{ 1, 0, 0, 0, 12, 40, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 40, },
+	{ 1, 0, 0, 0, 13, 40, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 40, },
+	{ 0, 0, 0, 1, 1, 46, },
+	{ 2, 0, 0, 1, 1, 40, },
+	{ 1, 0, 0, 1, 1, 40, },
+	{ 0, 0, 0, 1, 2, 46, },
+	{ 2, 0, 0, 1, 2, 40, },
+	{ 1, 0, 0, 1, 2, 40, },
+	{ 0, 0, 0, 1, 3, 46, },
+	{ 2, 0, 0, 1, 3, 40, },
+	{ 1, 0, 0, 1, 3, 40, },
+	{ 0, 0, 0, 1, 4, 46, },
+	{ 2, 0, 0, 1, 4, 40, },
+	{ 1, 0, 0, 1, 4, 40, },
+	{ 0, 0, 0, 1, 5, 46, },
+	{ 2, 0, 0, 1, 5, 40, },
+	{ 1, 0, 0, 1, 5, 40, },
+	{ 0, 0, 0, 1, 6, 46, },
+	{ 2, 0, 0, 1, 6, 40, },
+	{ 1, 0, 0, 1, 6, 40, },
+	{ 0, 0, 0, 1, 7, 46, },
+	{ 2, 0, 0, 1, 7, 40, },
+	{ 1, 0, 0, 1, 7, 40, },
+	{ 0, 0, 0, 1, 8, 46, },
+	{ 2, 0, 0, 1, 8, 40, },
+	{ 1, 0, 0, 1, 8, 40, },
+	{ 0, 0, 0, 1, 9, 46, },
+	{ 2, 0, 0, 1, 9, 40, },
+	{ 1, 0, 0, 1, 9, 40, },
+	{ 0, 0, 0, 1, 10, 46, },
+	{ 2, 0, 0, 1, 10, 40, },
+	{ 1, 0, 0, 1, 10, 40, },
+	{ 0, 0, 0, 1, 11, 46, },
+	{ 2, 0, 0, 1, 11, 40, },
+	{ 1, 0, 0, 1, 11, 40, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 40, },
+	{ 1, 0, 0, 1, 12, 40, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 40, },
+	{ 1, 0, 0, 1, 13, 40, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 46, },
+	{ 2, 0, 0, 2, 1, 40, },
+	{ 1, 0, 0, 2, 1, 40, },
+	{ 0, 0, 0, 2, 2, 46, },
+	{ 2, 0, 0, 2, 2, 40, },
+	{ 1, 0, 0, 2, 2, 40, },
+	{ 0, 0, 0, 2, 3, 46, },
+	{ 2, 0, 0, 2, 3, 40, },
+	{ 1, 0, 0, 2, 3, 40, },
+	{ 0, 0, 0, 2, 4, 46, },
+	{ 2, 0, 0, 2, 4, 40, },
+	{ 1, 0, 0, 2, 4, 40, },
+	{ 0, 0, 0, 2, 5, 46, },
+	{ 2, 0, 0, 2, 5, 40, },
+	{ 1, 0, 0, 2, 5, 40, },
+	{ 0, 0, 0, 2, 6, 46, },
+	{ 2, 0, 0, 2, 6, 40, },
+	{ 1, 0, 0, 2, 6, 40, },
+	{ 0, 0, 0, 2, 7, 46, },
+	{ 2, 0, 0, 2, 7, 40, },
+	{ 1, 0, 0, 2, 7, 40, },
+	{ 0, 0, 0, 2, 8, 46, },
+	{ 2, 0, 0, 2, 8, 40, },
+	{ 1, 0, 0, 2, 8, 40, },
+	{ 0, 0, 0, 2, 9, 46, },
+	{ 2, 0, 0, 2, 9, 40, },
+	{ 1, 0, 0, 2, 9, 40, },
+	{ 0, 0, 0, 2, 10, 46, },
+	{ 2, 0, 0, 2, 10, 40, },
+	{ 1, 0, 0, 2, 10, 40, },
+	{ 0, 0, 0, 2, 11, 46, },
+	{ 2, 0, 0, 2, 11, 40, },
+	{ 1, 0, 0, 2, 11, 40, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 40, },
+	{ 1, 0, 0, 2, 12, 40, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 40, },
+	{ 1, 0, 0, 2, 13, 40, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 46, },
+	{ 2, 0, 0, 3, 1, 40, },
+	{ 1, 0, 0, 3, 1, 40, },
+	{ 0, 0, 0, 3, 2, 46, },
+	{ 2, 0, 0, 3, 2, 40, },
+	{ 1, 0, 0, 3, 2, 40, },
+	{ 0, 0, 0, 3, 3, 46, },
+	{ 2, 0, 0, 3, 3, 40, },
+	{ 1, 0, 0, 3, 3, 40, },
+	{ 0, 0, 0, 3, 4, 46, },
+	{ 2, 0, 0, 3, 4, 40, },
+	{ 1, 0, 0, 3, 4, 40, },
+	{ 0, 0, 0, 3, 5, 46, },
+	{ 2, 0, 0, 3, 5, 40, },
+	{ 1, 0, 0, 3, 5, 40, },
+	{ 0, 0, 0, 3, 6, 46, },
+	{ 2, 0, 0, 3, 6, 40, },
+	{ 1, 0, 0, 3, 6, 40, },
+	{ 0, 0, 0, 3, 7, 46, },
+	{ 2, 0, 0, 3, 7, 40, },
+	{ 1, 0, 0, 3, 7, 40, },
+	{ 0, 0, 0, 3, 8, 46, },
+	{ 2, 0, 0, 3, 8, 40, },
+	{ 1, 0, 0, 3, 8, 40, },
+	{ 0, 0, 0, 3, 9, 46, },
+	{ 2, 0, 0, 3, 9, 40, },
+	{ 1, 0, 0, 3, 9, 40, },
+	{ 0, 0, 0, 3, 10, 46, },
+	{ 2, 0, 0, 3, 10, 40, },
+	{ 1, 0, 0, 3, 10, 40, },
+	{ 0, 0, 0, 3, 11, 46, },
+	{ 2, 0, 0, 3, 11, 40, },
+	{ 1, 0, 0, 3, 11, 40, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 40, },
+	{ 1, 0, 0, 3, 12, 40, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 40, },
+	{ 1, 0, 0, 3, 13, 40, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 46, },
+	{ 2, 0, 0, 6, 1, 40, },
+	{ 1, 0, 0, 6, 1, 40, },
+	{ 0, 0, 0, 6, 2, 46, },
+	{ 2, 0, 0, 6, 2, 40, },
+	{ 1, 0, 0, 6, 2, 40, },
+	{ 0, 0, 0, 6, 3, 46, },
+	{ 2, 0, 0, 6, 3, 40, },
+	{ 1, 0, 0, 6, 3, 40, },
+	{ 0, 0, 0, 6, 4, 46, },
+	{ 2, 0, 0, 6, 4, 40, },
+	{ 1, 0, 0, 6, 4, 40, },
+	{ 0, 0, 0, 6, 5, 46, },
+	{ 2, 0, 0, 6, 5, 40, },
+	{ 1, 0, 0, 6, 5, 40, },
+	{ 0, 0, 0, 6, 6, 46, },
+	{ 2, 0, 0, 6, 6, 40, },
+	{ 1, 0, 0, 6, 6, 40, },
+	{ 0, 0, 0, 6, 7, 46, },
+	{ 2, 0, 0, 6, 7, 40, },
+	{ 1, 0, 0, 6, 7, 40, },
+	{ 0, 0, 0, 6, 8, 46, },
+	{ 2, 0, 0, 6, 8, 40, },
+	{ 1, 0, 0, 6, 8, 40, },
+	{ 0, 0, 0, 6, 9, 46, },
+	{ 2, 0, 0, 6, 9, 40, },
+	{ 1, 0, 0, 6, 9, 40, },
+	{ 0, 0, 0, 6, 10, 46, },
+	{ 2, 0, 0, 6, 10, 40, },
+	{ 1, 0, 0, 6, 10, 40, },
+	{ 0, 0, 0, 6, 11, 46, },
+	{ 2, 0, 0, 6, 11, 40, },
+	{ 1, 0, 0, 6, 11, 40, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 40, },
+	{ 1, 0, 0, 6, 12, 40, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 40, },
+	{ 1, 0, 0, 6, 13, 40, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 46, },
+	{ 2, 0, 0, 7, 1, 40, },
+	{ 1, 0, 0, 7, 1, 40, },
+	{ 0, 0, 0, 7, 2, 46, },
+	{ 2, 0, 0, 7, 2, 40, },
+	{ 1, 0, 0, 7, 2, 40, },
+	{ 0, 0, 0, 7, 3, 46, },
+	{ 2, 0, 0, 7, 3, 40, },
+	{ 1, 0, 0, 7, 3, 40, },
+	{ 0, 0, 0, 7, 4, 46, },
+	{ 2, 0, 0, 7, 4, 40, },
+	{ 1, 0, 0, 7, 4, 40, },
+	{ 0, 0, 0, 7, 5, 46, },
+	{ 2, 0, 0, 7, 5, 40, },
+	{ 1, 0, 0, 7, 5, 40, },
+	{ 0, 0, 0, 7, 6, 46, },
+	{ 2, 0, 0, 7, 6, 40, },
+	{ 1, 0, 0, 7, 6, 40, },
+	{ 0, 0, 0, 7, 7, 46, },
+	{ 2, 0, 0, 7, 7, 40, },
+	{ 1, 0, 0, 7, 7, 40, },
+	{ 0, 0, 0, 7, 8, 46, },
+	{ 2, 0, 0, 7, 8, 40, },
+	{ 1, 0, 0, 7, 8, 40, },
+	{ 0, 0, 0, 7, 9, 46, },
+	{ 2, 0, 0, 7, 9, 40, },
+	{ 1, 0, 0, 7, 9, 40, },
+	{ 0, 0, 0, 7, 10, 46, },
+	{ 2, 0, 0, 7, 10, 40, },
+	{ 1, 0, 0, 7, 10, 40, },
+	{ 0, 0, 0, 7, 11, 46, },
+	{ 2, 0, 0, 7, 11, 40, },
+	{ 1, 0, 0, 7, 11, 40, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 40, },
+	{ 1, 0, 0, 7, 12, 40, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 40, },
+	{ 1, 0, 0, 7, 13, 40, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 46, },
+	{ 2, 0, 1, 2, 3, 40, },
+	{ 1, 0, 1, 2, 3, 40, },
+	{ 0, 0, 1, 2, 4, 46, },
+	{ 2, 0, 1, 2, 4, 40, },
+	{ 1, 0, 1, 2, 4, 40, },
+	{ 0, 0, 1, 2, 5, 46, },
+	{ 2, 0, 1, 2, 5, 40, },
+	{ 1, 0, 1, 2, 5, 40, },
+	{ 0, 0, 1, 2, 6, 46, },
+	{ 2, 0, 1, 2, 6, 40, },
+	{ 1, 0, 1, 2, 6, 40, },
+	{ 0, 0, 1, 2, 7, 46, },
+	{ 2, 0, 1, 2, 7, 40, },
+	{ 1, 0, 1, 2, 7, 40, },
+	{ 0, 0, 1, 2, 8, 46, },
+	{ 2, 0, 1, 2, 8, 40, },
+	{ 1, 0, 1, 2, 8, 40, },
+	{ 0, 0, 1, 2, 9, 46, },
+	{ 2, 0, 1, 2, 9, 40, },
+	{ 1, 0, 1, 2, 9, 40, },
+	{ 0, 0, 1, 2, 10, 46, },
+	{ 2, 0, 1, 2, 10, 40, },
+	{ 1, 0, 1, 2, 10, 40, },
+	{ 0, 0, 1, 2, 11, 46, },
+	{ 2, 0, 1, 2, 11, 40, },
+	{ 1, 0, 1, 2, 11, 40, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 40, },
+	{ 1, 0, 1, 2, 12, 40, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 40, },
+	{ 1, 0, 1, 2, 13, 40, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 46, },
+	{ 2, 0, 1, 3, 3, 40, },
+	{ 1, 0, 1, 3, 3, 40, },
+	{ 0, 0, 1, 3, 4, 46, },
+	{ 2, 0, 1, 3, 4, 40, },
+	{ 1, 0, 1, 3, 4, 40, },
+	{ 0, 0, 1, 3, 5, 46, },
+	{ 2, 0, 1, 3, 5, 40, },
+	{ 1, 0, 1, 3, 5, 40, },
+	{ 0, 0, 1, 3, 6, 46, },
+	{ 2, 0, 1, 3, 6, 40, },
+	{ 1, 0, 1, 3, 6, 40, },
+	{ 0, 0, 1, 3, 7, 46, },
+	{ 2, 0, 1, 3, 7, 40, },
+	{ 1, 0, 1, 3, 7, 40, },
+	{ 0, 0, 1, 3, 8, 46, },
+	{ 2, 0, 1, 3, 8, 40, },
+	{ 1, 0, 1, 3, 8, 40, },
+	{ 0, 0, 1, 3, 9, 46, },
+	{ 2, 0, 1, 3, 9, 40, },
+	{ 1, 0, 1, 3, 9, 40, },
+	{ 0, 0, 1, 3, 10, 46, },
+	{ 2, 0, 1, 3, 10, 40, },
+	{ 1, 0, 1, 3, 10, 40, },
+	{ 0, 0, 1, 3, 11, 46, },
+	{ 2, 0, 1, 3, 11, 40, },
+	{ 1, 0, 1, 3, 11, 40, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 40, },
+	{ 1, 0, 1, 3, 12, 40, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 40, },
+	{ 1, 0, 1, 3, 13, 40, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 46, },
+	{ 2, 0, 1, 6, 3, 40, },
+	{ 1, 0, 1, 6, 3, 40, },
+	{ 0, 0, 1, 6, 4, 46, },
+	{ 2, 0, 1, 6, 4, 40, },
+	{ 1, 0, 1, 6, 4, 40, },
+	{ 0, 0, 1, 6, 5, 46, },
+	{ 2, 0, 1, 6, 5, 40, },
+	{ 1, 0, 1, 6, 5, 40, },
+	{ 0, 0, 1, 6, 6, 46, },
+	{ 2, 0, 1, 6, 6, 40, },
+	{ 1, 0, 1, 6, 6, 40, },
+	{ 0, 0, 1, 6, 7, 46, },
+	{ 2, 0, 1, 6, 7, 40, },
+	{ 1, 0, 1, 6, 7, 40, },
+	{ 0, 0, 1, 6, 8, 46, },
+	{ 2, 0, 1, 6, 8, 40, },
+	{ 1, 0, 1, 6, 8, 40, },
+	{ 0, 0, 1, 6, 9, 46, },
+	{ 2, 0, 1, 6, 9, 40, },
+	{ 1, 0, 1, 6, 9, 40, },
+	{ 0, 0, 1, 6, 10, 46, },
+	{ 2, 0, 1, 6, 10, 40, },
+	{ 1, 0, 1, 6, 10, 40, },
+	{ 0, 0, 1, 6, 11, 46, },
+	{ 2, 0, 1, 6, 11, 40, },
+	{ 1, 0, 1, 6, 11, 40, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 40, },
+	{ 1, 0, 1, 6, 12, 40, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 40, },
+	{ 1, 0, 1, 6, 13, 40, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 46, },
+	{ 2, 0, 1, 7, 3, 40, },
+	{ 1, 0, 1, 7, 3, 40, },
+	{ 0, 0, 1, 7, 4, 46, },
+	{ 2, 0, 1, 7, 4, 40, },
+	{ 1, 0, 1, 7, 4, 40, },
+	{ 0, 0, 1, 7, 5, 46, },
+	{ 2, 0, 1, 7, 5, 40, },
+	{ 1, 0, 1, 7, 5, 40, },
+	{ 0, 0, 1, 7, 6, 46, },
+	{ 2, 0, 1, 7, 6, 40, },
+	{ 1, 0, 1, 7, 6, 40, },
+	{ 0, 0, 1, 7, 7, 46, },
+	{ 2, 0, 1, 7, 7, 40, },
+	{ 1, 0, 1, 7, 7, 40, },
+	{ 0, 0, 1, 7, 8, 46, },
+	{ 2, 0, 1, 7, 8, 40, },
+	{ 1, 0, 1, 7, 8, 40, },
+	{ 0, 0, 1, 7, 9, 46, },
+	{ 2, 0, 1, 7, 9, 40, },
+	{ 1, 0, 1, 7, 9, 40, },
+	{ 0, 0, 1, 7, 10, 46, },
+	{ 2, 0, 1, 7, 10, 40, },
+	{ 1, 0, 1, 7, 10, 40, },
+	{ 0, 0, 1, 7, 11, 46, },
+	{ 2, 0, 1, 7, 11, 40, },
+	{ 1, 0, 1, 7, 11, 40, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 40, },
+	{ 1, 0, 1, 7, 12, 40, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 40, },
+	{ 1, 0, 1, 7, 13, 40, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 46, },
+	{ 2, 1, 0, 1, 36, 40, },
+	{ 1, 1, 0, 1, 36, 40, },
+	{ 0, 1, 0, 1, 40, 46, },
+	{ 2, 1, 0, 1, 40, 40, },
+	{ 1, 1, 0, 1, 40, 40, },
+	{ 0, 1, 0, 1, 44, 46, },
+	{ 2, 1, 0, 1, 44, 40, },
+	{ 1, 1, 0, 1, 44, 40, },
+	{ 0, 1, 0, 1, 48, 46, },
+	{ 2, 1, 0, 1, 48, 40, },
+	{ 1, 1, 0, 1, 48, 40, },
+	{ 0, 1, 0, 1, 52, 46, },
+	{ 2, 1, 0, 1, 52, 40, },
+	{ 1, 1, 0, 1, 52, 40, },
+	{ 0, 1, 0, 1, 56, 46, },
+	{ 2, 1, 0, 1, 56, 40, },
+	{ 1, 1, 0, 1, 56, 40, },
+	{ 0, 1, 0, 1, 60, 46, },
+	{ 2, 1, 0, 1, 60, 40, },
+	{ 1, 1, 0, 1, 60, 40, },
+	{ 0, 1, 0, 1, 64, 46, },
+	{ 2, 1, 0, 1, 64, 40, },
+	{ 1, 1, 0, 1, 64, 40, },
+	{ 0, 1, 0, 1, 100, 46, },
+	{ 2, 1, 0, 1, 100, 40, },
+	{ 1, 1, 0, 1, 100, 40, },
+	{ 0, 1, 0, 1, 104, 46, },
+	{ 2, 1, 0, 1, 104, 40, },
+	{ 1, 1, 0, 1, 104, 40, },
+	{ 0, 1, 0, 1, 108, 46, },
+	{ 2, 1, 0, 1, 108, 40, },
+	{ 1, 1, 0, 1, 108, 40, },
+	{ 0, 1, 0, 1, 112, 46, },
+	{ 2, 1, 0, 1, 112, 40, },
+	{ 1, 1, 0, 1, 112, 40, },
+	{ 0, 1, 0, 1, 116, 46, },
+	{ 2, 1, 0, 1, 116, 40, },
+	{ 1, 1, 0, 1, 116, 40, },
+	{ 0, 1, 0, 1, 120, 46, },
+	{ 2, 1, 0, 1, 120, 40, },
+	{ 1, 1, 0, 1, 120, 40, },
+	{ 0, 1, 0, 1, 124, 46, },
+	{ 2, 1, 0, 1, 124, 40, },
+	{ 1, 1, 0, 1, 124, 40, },
+	{ 0, 1, 0, 1, 128, 46, },
+	{ 2, 1, 0, 1, 128, 40, },
+	{ 1, 1, 0, 1, 128, 40, },
+	{ 0, 1, 0, 1, 132, 46, },
+	{ 2, 1, 0, 1, 132, 40, },
+	{ 1, 1, 0, 1, 132, 40, },
+	{ 0, 1, 0, 1, 136, 46, },
+	{ 2, 1, 0, 1, 136, 40, },
+	{ 1, 1, 0, 1, 136, 40, },
+	{ 0, 1, 0, 1, 140, 46, },
+	{ 2, 1, 0, 1, 140, 40, },
+	{ 1, 1, 0, 1, 140, 40, },
+	{ 0, 1, 0, 1, 149, 46, },
+	{ 2, 1, 0, 1, 149, 40, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 46, },
+	{ 2, 1, 0, 1, 153, 40, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 46, },
+	{ 2, 1, 0, 1, 157, 40, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 46, },
+	{ 2, 1, 0, 1, 161, 40, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 46, },
+	{ 2, 1, 0, 1, 165, 40, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 46, },
+	{ 2, 1, 0, 2, 36, 40, },
+	{ 1, 1, 0, 2, 36, 40, },
+	{ 0, 1, 0, 2, 40, 46, },
+	{ 2, 1, 0, 2, 40, 40, },
+	{ 1, 1, 0, 2, 40, 40, },
+	{ 0, 1, 0, 2, 44, 46, },
+	{ 2, 1, 0, 2, 44, 40, },
+	{ 1, 1, 0, 2, 44, 40, },
+	{ 0, 1, 0, 2, 48, 46, },
+	{ 2, 1, 0, 2, 48, 40, },
+	{ 1, 1, 0, 2, 48, 40, },
+	{ 0, 1, 0, 2, 52, 46, },
+	{ 2, 1, 0, 2, 52, 40, },
+	{ 1, 1, 0, 2, 52, 40, },
+	{ 0, 1, 0, 2, 56, 46, },
+	{ 2, 1, 0, 2, 56, 40, },
+	{ 1, 1, 0, 2, 56, 40, },
+	{ 0, 1, 0, 2, 60, 46, },
+	{ 2, 1, 0, 2, 60, 40, },
+	{ 1, 1, 0, 2, 60, 40, },
+	{ 0, 1, 0, 2, 64, 46, },
+	{ 2, 1, 0, 2, 64, 40, },
+	{ 1, 1, 0, 2, 64, 40, },
+	{ 0, 1, 0, 2, 100, 46, },
+	{ 2, 1, 0, 2, 100, 40, },
+	{ 1, 1, 0, 2, 100, 40, },
+	{ 0, 1, 0, 2, 104, 46, },
+	{ 2, 1, 0, 2, 104, 40, },
+	{ 1, 1, 0, 2, 104, 40, },
+	{ 0, 1, 0, 2, 108, 46, },
+	{ 2, 1, 0, 2, 108, 40, },
+	{ 1, 1, 0, 2, 108, 40, },
+	{ 0, 1, 0, 2, 112, 46, },
+	{ 2, 1, 0, 2, 112, 40, },
+	{ 1, 1, 0, 2, 112, 40, },
+	{ 0, 1, 0, 2, 116, 46, },
+	{ 2, 1, 0, 2, 116, 40, },
+	{ 1, 1, 0, 2, 116, 40, },
+	{ 0, 1, 0, 2, 120, 46, },
+	{ 2, 1, 0, 2, 120, 40, },
+	{ 1, 1, 0, 2, 120, 40, },
+	{ 0, 1, 0, 2, 124, 46, },
+	{ 2, 1, 0, 2, 124, 40, },
+	{ 1, 1, 0, 2, 124, 40, },
+	{ 0, 1, 0, 2, 128, 46, },
+	{ 2, 1, 0, 2, 128, 40, },
+	{ 1, 1, 0, 2, 128, 40, },
+	{ 0, 1, 0, 2, 132, 46, },
+	{ 2, 1, 0, 2, 132, 40, },
+	{ 1, 1, 0, 2, 132, 40, },
+	{ 0, 1, 0, 2, 136, 46, },
+	{ 2, 1, 0, 2, 136, 40, },
+	{ 1, 1, 0, 2, 136, 40, },
+	{ 0, 1, 0, 2, 140, 46, },
+	{ 2, 1, 0, 2, 140, 40, },
+	{ 1, 1, 0, 2, 140, 40, },
+	{ 0, 1, 0, 2, 149, 46, },
+	{ 2, 1, 0, 2, 149, 40, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 46, },
+	{ 2, 1, 0, 2, 153, 40, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 46, },
+	{ 2, 1, 0, 2, 157, 40, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 46, },
+	{ 2, 1, 0, 2, 161, 40, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 46, },
+	{ 2, 1, 0, 2, 165, 40, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 46, },
+	{ 2, 1, 0, 3, 36, 40, },
+	{ 1, 1, 0, 3, 36, 40, },
+	{ 0, 1, 0, 3, 40, 46, },
+	{ 2, 1, 0, 3, 40, 40, },
+	{ 1, 1, 0, 3, 40, 40, },
+	{ 0, 1, 0, 3, 44, 46, },
+	{ 2, 1, 0, 3, 44, 40, },
+	{ 1, 1, 0, 3, 44, 40, },
+	{ 0, 1, 0, 3, 48, 46, },
+	{ 2, 1, 0, 3, 48, 40, },
+	{ 1, 1, 0, 3, 48, 40, },
+	{ 0, 1, 0, 3, 52, 46, },
+	{ 2, 1, 0, 3, 52, 40, },
+	{ 1, 1, 0, 3, 52, 40, },
+	{ 0, 1, 0, 3, 56, 46, },
+	{ 2, 1, 0, 3, 56, 40, },
+	{ 1, 1, 0, 3, 56, 40, },
+	{ 0, 1, 0, 3, 60, 46, },
+	{ 2, 1, 0, 3, 60, 40, },
+	{ 1, 1, 0, 3, 60, 40, },
+	{ 0, 1, 0, 3, 64, 46, },
+	{ 2, 1, 0, 3, 64, 40, },
+	{ 1, 1, 0, 3, 64, 40, },
+	{ 0, 1, 0, 3, 100, 46, },
+	{ 2, 1, 0, 3, 100, 40, },
+	{ 1, 1, 0, 3, 100, 40, },
+	{ 0, 1, 0, 3, 104, 46, },
+	{ 2, 1, 0, 3, 104, 40, },
+	{ 1, 1, 0, 3, 104, 40, },
+	{ 0, 1, 0, 3, 108, 46, },
+	{ 2, 1, 0, 3, 108, 40, },
+	{ 1, 1, 0, 3, 108, 40, },
+	{ 0, 1, 0, 3, 112, 46, },
+	{ 2, 1, 0, 3, 112, 40, },
+	{ 1, 1, 0, 3, 112, 40, },
+	{ 0, 1, 0, 3, 116, 46, },
+	{ 2, 1, 0, 3, 116, 40, },
+	{ 1, 1, 0, 3, 116, 40, },
+	{ 0, 1, 0, 3, 120, 46, },
+	{ 2, 1, 0, 3, 120, 40, },
+	{ 1, 1, 0, 3, 120, 40, },
+	{ 0, 1, 0, 3, 124, 46, },
+	{ 2, 1, 0, 3, 124, 40, },
+	{ 1, 1, 0, 3, 124, 40, },
+	{ 0, 1, 0, 3, 128, 46, },
+	{ 2, 1, 0, 3, 128, 40, },
+	{ 1, 1, 0, 3, 128, 40, },
+	{ 0, 1, 0, 3, 132, 46, },
+	{ 2, 1, 0, 3, 132, 40, },
+	{ 1, 1, 0, 3, 132, 40, },
+	{ 0, 1, 0, 3, 136, 46, },
+	{ 2, 1, 0, 3, 136, 40, },
+	{ 1, 1, 0, 3, 136, 40, },
+	{ 0, 1, 0, 3, 140, 46, },
+	{ 2, 1, 0, 3, 140, 40, },
+	{ 1, 1, 0, 3, 140, 40, },
+	{ 0, 1, 0, 3, 149, 46, },
+	{ 2, 1, 0, 3, 149, 40, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 46, },
+	{ 2, 1, 0, 3, 153, 40, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 46, },
+	{ 2, 1, 0, 3, 157, 40, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 46, },
+	{ 2, 1, 0, 3, 161, 40, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 46, },
+	{ 2, 1, 0, 3, 165, 40, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 46, },
+	{ 2, 1, 0, 6, 36, 40, },
+	{ 1, 1, 0, 6, 36, 40, },
+	{ 0, 1, 0, 6, 40, 46, },
+	{ 2, 1, 0, 6, 40, 40, },
+	{ 1, 1, 0, 6, 40, 40, },
+	{ 0, 1, 0, 6, 44, 46, },
+	{ 2, 1, 0, 6, 44, 40, },
+	{ 1, 1, 0, 6, 44, 40, },
+	{ 0, 1, 0, 6, 48, 46, },
+	{ 2, 1, 0, 6, 48, 40, },
+	{ 1, 1, 0, 6, 48, 40, },
+	{ 0, 1, 0, 6, 52, 46, },
+	{ 2, 1, 0, 6, 52, 40, },
+	{ 1, 1, 0, 6, 52, 40, },
+	{ 0, 1, 0, 6, 56, 46, },
+	{ 2, 1, 0, 6, 56, 40, },
+	{ 1, 1, 0, 6, 56, 40, },
+	{ 0, 1, 0, 6, 60, 46, },
+	{ 2, 1, 0, 6, 60, 40, },
+	{ 1, 1, 0, 6, 60, 40, },
+	{ 0, 1, 0, 6, 64, 46, },
+	{ 2, 1, 0, 6, 64, 40, },
+	{ 1, 1, 0, 6, 64, 40, },
+	{ 0, 1, 0, 6, 100, 46, },
+	{ 2, 1, 0, 6, 100, 40, },
+	{ 1, 1, 0, 6, 100, 40, },
+	{ 0, 1, 0, 6, 104, 46, },
+	{ 2, 1, 0, 6, 104, 40, },
+	{ 1, 1, 0, 6, 104, 40, },
+	{ 0, 1, 0, 6, 108, 46, },
+	{ 2, 1, 0, 6, 108, 40, },
+	{ 1, 1, 0, 6, 108, 40, },
+	{ 0, 1, 0, 6, 112, 46, },
+	{ 2, 1, 0, 6, 112, 40, },
+	{ 1, 1, 0, 6, 112, 40, },
+	{ 0, 1, 0, 6, 116, 46, },
+	{ 2, 1, 0, 6, 116, 40, },
+	{ 1, 1, 0, 6, 116, 40, },
+	{ 0, 1, 0, 6, 120, 46, },
+	{ 2, 1, 0, 6, 120, 40, },
+	{ 1, 1, 0, 6, 120, 40, },
+	{ 0, 1, 0, 6, 124, 46, },
+	{ 2, 1, 0, 6, 124, 40, },
+	{ 1, 1, 0, 6, 124, 40, },
+	{ 0, 1, 0, 6, 128, 46, },
+	{ 2, 1, 0, 6, 128, 40, },
+	{ 1, 1, 0, 6, 128, 40, },
+	{ 0, 1, 0, 6, 132, 46, },
+	{ 2, 1, 0, 6, 132, 40, },
+	{ 1, 1, 0, 6, 132, 40, },
+	{ 0, 1, 0, 6, 136, 46, },
+	{ 2, 1, 0, 6, 136, 40, },
+	{ 1, 1, 0, 6, 136, 40, },
+	{ 0, 1, 0, 6, 140, 46, },
+	{ 2, 1, 0, 6, 140, 40, },
+	{ 1, 1, 0, 6, 140, 40, },
+	{ 0, 1, 0, 6, 149, 46, },
+	{ 2, 1, 0, 6, 149, 40, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 46, },
+	{ 2, 1, 0, 6, 153, 40, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 46, },
+	{ 2, 1, 0, 6, 157, 40, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 46, },
+	{ 2, 1, 0, 6, 161, 40, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 46, },
+	{ 2, 1, 0, 6, 165, 40, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 46, },
+	{ 2, 1, 0, 7, 36, 40, },
+	{ 1, 1, 0, 7, 36, 40, },
+	{ 0, 1, 0, 7, 40, 46, },
+	{ 2, 1, 0, 7, 40, 40, },
+	{ 1, 1, 0, 7, 40, 40, },
+	{ 0, 1, 0, 7, 44, 46, },
+	{ 2, 1, 0, 7, 44, 40, },
+	{ 1, 1, 0, 7, 44, 40, },
+	{ 0, 1, 0, 7, 48, 46, },
+	{ 2, 1, 0, 7, 48, 40, },
+	{ 1, 1, 0, 7, 48, 40, },
+	{ 0, 1, 0, 7, 52, 46, },
+	{ 2, 1, 0, 7, 52, 40, },
+	{ 1, 1, 0, 7, 52, 40, },
+	{ 0, 1, 0, 7, 56, 46, },
+	{ 2, 1, 0, 7, 56, 40, },
+	{ 1, 1, 0, 7, 56, 40, },
+	{ 0, 1, 0, 7, 60, 46, },
+	{ 2, 1, 0, 7, 60, 40, },
+	{ 1, 1, 0, 7, 60, 40, },
+	{ 0, 1, 0, 7, 64, 46, },
+	{ 2, 1, 0, 7, 64, 40, },
+	{ 1, 1, 0, 7, 64, 40, },
+	{ 0, 1, 0, 7, 100, 46, },
+	{ 2, 1, 0, 7, 100, 40, },
+	{ 1, 1, 0, 7, 100, 40, },
+	{ 0, 1, 0, 7, 104, 46, },
+	{ 2, 1, 0, 7, 104, 40, },
+	{ 1, 1, 0, 7, 104, 40, },
+	{ 0, 1, 0, 7, 108, 46, },
+	{ 2, 1, 0, 7, 108, 40, },
+	{ 1, 1, 0, 7, 108, 40, },
+	{ 0, 1, 0, 7, 112, 46, },
+	{ 2, 1, 0, 7, 112, 40, },
+	{ 1, 1, 0, 7, 112, 40, },
+	{ 0, 1, 0, 7, 116, 46, },
+	{ 2, 1, 0, 7, 116, 40, },
+	{ 1, 1, 0, 7, 116, 40, },
+	{ 0, 1, 0, 7, 120, 46, },
+	{ 2, 1, 0, 7, 120, 40, },
+	{ 1, 1, 0, 7, 120, 40, },
+	{ 0, 1, 0, 7, 124, 46, },
+	{ 2, 1, 0, 7, 124, 40, },
+	{ 1, 1, 0, 7, 124, 40, },
+	{ 0, 1, 0, 7, 128, 46, },
+	{ 2, 1, 0, 7, 128, 40, },
+	{ 1, 1, 0, 7, 128, 40, },
+	{ 0, 1, 0, 7, 132, 46, },
+	{ 2, 1, 0, 7, 132, 40, },
+	{ 1, 1, 0, 7, 132, 40, },
+	{ 0, 1, 0, 7, 136, 46, },
+	{ 2, 1, 0, 7, 136, 40, },
+	{ 1, 1, 0, 7, 136, 40, },
+	{ 0, 1, 0, 7, 140, 46, },
+	{ 2, 1, 0, 7, 140, 40, },
+	{ 1, 1, 0, 7, 140, 40, },
+	{ 0, 1, 0, 7, 149, 46, },
+	{ 2, 1, 0, 7, 149, 40, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 46, },
+	{ 2, 1, 0, 7, 153, 40, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 46, },
+	{ 2, 1, 0, 7, 157, 40, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 46, },
+	{ 2, 1, 0, 7, 161, 40, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 46, },
+	{ 2, 1, 0, 7, 165, 40, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 46, },
+	{ 2, 1, 1, 2, 38, 40, },
+	{ 1, 1, 1, 2, 38, 40, },
+	{ 0, 1, 1, 2, 46, 46, },
+	{ 2, 1, 1, 2, 46, 40, },
+	{ 1, 1, 1, 2, 46, 40, },
+	{ 0, 1, 1, 2, 54, 46, },
+	{ 2, 1, 1, 2, 54, 40, },
+	{ 1, 1, 1, 2, 54, 40, },
+	{ 0, 1, 1, 2, 62, 46, },
+	{ 2, 1, 1, 2, 62, 40, },
+	{ 1, 1, 1, 2, 62, 40, },
+	{ 0, 1, 1, 2, 102, 46, },
+	{ 2, 1, 1, 2, 102, 40, },
+	{ 1, 1, 1, 2, 102, 40, },
+	{ 0, 1, 1, 2, 110, 46, },
+	{ 2, 1, 1, 2, 110, 40, },
+	{ 1, 1, 1, 2, 110, 40, },
+	{ 0, 1, 1, 2, 118, 46, },
+	{ 2, 1, 1, 2, 118, 40, },
+	{ 1, 1, 1, 2, 118, 40, },
+	{ 0, 1, 1, 2, 126, 46, },
+	{ 2, 1, 1, 2, 126, 40, },
+	{ 1, 1, 1, 2, 126, 40, },
+	{ 0, 1, 1, 2, 134, 46, },
+	{ 2, 1, 1, 2, 134, 40, },
+	{ 1, 1, 1, 2, 134, 40, },
+	{ 0, 1, 1, 2, 151, 46, },
+	{ 2, 1, 1, 2, 151, 40, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 46, },
+	{ 2, 1, 1, 2, 159, 40, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 46, },
+	{ 2, 1, 1, 3, 38, 40, },
+	{ 1, 1, 1, 3, 38, 40, },
+	{ 0, 1, 1, 3, 46, 46, },
+	{ 2, 1, 1, 3, 46, 40, },
+	{ 1, 1, 1, 3, 46, 40, },
+	{ 0, 1, 1, 3, 54, 46, },
+	{ 2, 1, 1, 3, 54, 40, },
+	{ 1, 1, 1, 3, 54, 40, },
+	{ 0, 1, 1, 3, 62, 46, },
+	{ 2, 1, 1, 3, 62, 40, },
+	{ 1, 1, 1, 3, 62, 40, },
+	{ 0, 1, 1, 3, 102, 46, },
+	{ 2, 1, 1, 3, 102, 40, },
+	{ 1, 1, 1, 3, 102, 40, },
+	{ 0, 1, 1, 3, 110, 46, },
+	{ 2, 1, 1, 3, 110, 40, },
+	{ 1, 1, 1, 3, 110, 40, },
+	{ 0, 1, 1, 3, 118, 46, },
+	{ 2, 1, 1, 3, 118, 40, },
+	{ 1, 1, 1, 3, 118, 40, },
+	{ 0, 1, 1, 3, 126, 46, },
+	{ 2, 1, 1, 3, 126, 40, },
+	{ 1, 1, 1, 3, 126, 40, },
+	{ 0, 1, 1, 3, 134, 46, },
+	{ 2, 1, 1, 3, 134, 40, },
+	{ 1, 1, 1, 3, 134, 40, },
+	{ 0, 1, 1, 3, 151, 46, },
+	{ 2, 1, 1, 3, 151, 40, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 46, },
+	{ 2, 1, 1, 3, 159, 40, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 46, },
+	{ 2, 1, 1, 6, 38, 40, },
+	{ 1, 1, 1, 6, 38, 40, },
+	{ 0, 1, 1, 6, 46, 46, },
+	{ 2, 1, 1, 6, 46, 40, },
+	{ 1, 1, 1, 6, 46, 40, },
+	{ 0, 1, 1, 6, 54, 46, },
+	{ 2, 1, 1, 6, 54, 40, },
+	{ 1, 1, 1, 6, 54, 40, },
+	{ 0, 1, 1, 6, 62, 46, },
+	{ 2, 1, 1, 6, 62, 40, },
+	{ 1, 1, 1, 6, 62, 40, },
+	{ 0, 1, 1, 6, 102, 46, },
+	{ 2, 1, 1, 6, 102, 40, },
+	{ 1, 1, 1, 6, 102, 40, },
+	{ 0, 1, 1, 6, 110, 46, },
+	{ 2, 1, 1, 6, 110, 40, },
+	{ 1, 1, 1, 6, 110, 40, },
+	{ 0, 1, 1, 6, 118, 46, },
+	{ 2, 1, 1, 6, 118, 40, },
+	{ 1, 1, 1, 6, 118, 40, },
+	{ 0, 1, 1, 6, 126, 46, },
+	{ 2, 1, 1, 6, 126, 40, },
+	{ 1, 1, 1, 6, 126, 40, },
+	{ 0, 1, 1, 6, 134, 46, },
+	{ 2, 1, 1, 6, 134, 40, },
+	{ 1, 1, 1, 6, 134, 40, },
+	{ 0, 1, 1, 6, 151, 46, },
+	{ 2, 1, 1, 6, 151, 40, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 46, },
+	{ 2, 1, 1, 6, 159, 40, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 46, },
+	{ 2, 1, 1, 7, 38, 40, },
+	{ 1, 1, 1, 7, 38, 40, },
+	{ 0, 1, 1, 7, 46, 46, },
+	{ 2, 1, 1, 7, 46, 40, },
+	{ 1, 1, 1, 7, 46, 40, },
+	{ 0, 1, 1, 7, 54, 46, },
+	{ 2, 1, 1, 7, 54, 40, },
+	{ 1, 1, 1, 7, 54, 40, },
+	{ 0, 1, 1, 7, 62, 46, },
+	{ 2, 1, 1, 7, 62, 40, },
+	{ 1, 1, 1, 7, 62, 40, },
+	{ 0, 1, 1, 7, 102, 46, },
+	{ 2, 1, 1, 7, 102, 40, },
+	{ 1, 1, 1, 7, 102, 40, },
+	{ 0, 1, 1, 7, 110, 46, },
+	{ 2, 1, 1, 7, 110, 40, },
+	{ 1, 1, 1, 7, 110, 40, },
+	{ 0, 1, 1, 7, 118, 46, },
+	{ 2, 1, 1, 7, 118, 40, },
+	{ 1, 1, 1, 7, 118, 40, },
+	{ 0, 1, 1, 7, 126, 46, },
+	{ 2, 1, 1, 7, 126, 40, },
+	{ 1, 1, 1, 7, 126, 40, },
+	{ 0, 1, 1, 7, 134, 46, },
+	{ 2, 1, 1, 7, 134, 40, },
+	{ 1, 1, 1, 7, 134, 40, },
+	{ 0, 1, 1, 7, 151, 46, },
+	{ 2, 1, 1, 7, 151, 40, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 46, },
+	{ 2, 1, 1, 7, 159, 40, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 46, },
+	{ 2, 1, 2, 4, 42, 40, },
+	{ 1, 1, 2, 4, 42, 40, },
+	{ 0, 1, 2, 4, 58, 46, },
+	{ 2, 1, 2, 4, 58, 40, },
+	{ 1, 1, 2, 4, 58, 40, },
+	{ 0, 1, 2, 4, 106, 46, },
+	{ 2, 1, 2, 4, 106, 40, },
+	{ 1, 1, 2, 4, 106, 40, },
+	{ 0, 1, 2, 4, 122, 46, },
+	{ 2, 1, 2, 4, 122, 40, },
+	{ 1, 1, 2, 4, 122, 40, },
+	{ 0, 1, 2, 4, 155, 46, },
+	{ 2, 1, 2, 4, 155, 40, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 46, },
+	{ 2, 1, 2, 5, 42, 40, },
+	{ 1, 1, 2, 5, 42, 40, },
+	{ 0, 1, 2, 5, 58, 46, },
+	{ 2, 1, 2, 5, 58, 40, },
+	{ 1, 1, 2, 5, 58, 40, },
+	{ 0, 1, 2, 5, 106, 46, },
+	{ 2, 1, 2, 5, 106, 40, },
+	{ 1, 1, 2, 5, 106, 40, },
+	{ 0, 1, 2, 5, 122, 46, },
+	{ 2, 1, 2, 5, 122, 40, },
+	{ 1, 1, 2, 5, 122, 40, },
+	{ 0, 1, 2, 5, 155, 46, },
+	{ 2, 1, 2, 5, 155, 40, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 46, },
+	{ 2, 1, 2, 8, 42, 40, },
+	{ 1, 1, 2, 8, 42, 40, },
+	{ 0, 1, 2, 8, 58, 46, },
+	{ 2, 1, 2, 8, 58, 40, },
+	{ 1, 1, 2, 8, 58, 40, },
+	{ 0, 1, 2, 8, 106, 46, },
+	{ 2, 1, 2, 8, 106, 40, },
+	{ 1, 1, 2, 8, 106, 40, },
+	{ 0, 1, 2, 8, 122, 46, },
+	{ 2, 1, 2, 8, 122, 40, },
+	{ 1, 1, 2, 8, 122, 40, },
+	{ 0, 1, 2, 8, 155, 46, },
+	{ 2, 1, 2, 8, 155, 40, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 46, },
+	{ 2, 1, 2, 9, 42, 40, },
+	{ 1, 1, 2, 9, 42, 40, },
+	{ 0, 1, 2, 9, 58, 46, },
+	{ 2, 1, 2, 9, 58, 40, },
+	{ 1, 1, 2, 9, 58, 40, },
+	{ 0, 1, 2, 9, 106, 46, },
+	{ 2, 1, 2, 9, 106, 40, },
+	{ 1, 1, 2, 9, 106, 40, },
+	{ 0, 1, 2, 9, 122, 46, },
+	{ 2, 1, 2, 9, 122, 40, },
+	{ 1, 1, 2, 9, 122, 40, },
+	{ 0, 1, 2, 9, 155, 46, },
+	{ 2, 1, 2, 9, 155, 40, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type5);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type7[] = {
+	{ 0, 0, 0, 0, 1, 44, },
+	{ 2, 0, 0, 0, 1, 32, },
+	{ 1, 0, 0, 0, 1, 32, },
+	{ 0, 0, 0, 0, 2, 52, },
+	{ 2, 0, 0, 0, 2, 32, },
+	{ 1, 0, 0, 0, 2, 32, },
+	{ 0, 0, 0, 0, 3, 52, },
+	{ 2, 0, 0, 0, 3, 32, },
+	{ 1, 0, 0, 0, 3, 32, },
+	{ 0, 0, 0, 0, 4, 52, },
+	{ 2, 0, 0, 0, 4, 32, },
+	{ 1, 0, 0, 0, 4, 32, },
+	{ 0, 0, 0, 0, 5, 52, },
+	{ 2, 0, 0, 0, 5, 32, },
+	{ 1, 0, 0, 0, 5, 32, },
+	{ 0, 0, 0, 0, 6, 52, },
+	{ 2, 0, 0, 0, 6, 32, },
+	{ 1, 0, 0, 0, 6, 32, },
+	{ 0, 0, 0, 0, 7, 52, },
+	{ 2, 0, 0, 0, 7, 32, },
+	{ 1, 0, 0, 0, 7, 32, },
+	{ 0, 0, 0, 0, 8, 52, },
+	{ 2, 0, 0, 0, 8, 32, },
+	{ 1, 0, 0, 0, 8, 32, },
+	{ 0, 0, 0, 0, 9, 52, },
+	{ 2, 0, 0, 0, 9, 32, },
+	{ 1, 0, 0, 0, 9, 32, },
+	{ 0, 0, 0, 0, 10, 52, },
+	{ 2, 0, 0, 0, 10, 32, },
+	{ 1, 0, 0, 0, 10, 32, },
+	{ 0, 0, 0, 0, 11, 44, },
+	{ 2, 0, 0, 0, 11, 32, },
+	{ 1, 0, 0, 0, 11, 32, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 32, },
+	{ 1, 0, 0, 0, 12, 32, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 32, },
+	{ 1, 0, 0, 0, 13, 32, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 32, },
+	{ 0, 0, 0, 1, 1, 38, },
+	{ 2, 0, 0, 1, 1, 32, },
+	{ 1, 0, 0, 1, 1, 32, },
+	{ 0, 0, 0, 1, 2, 46, },
+	{ 2, 0, 0, 1, 2, 32, },
+	{ 1, 0, 0, 1, 2, 32, },
+	{ 0, 0, 0, 1, 3, 46, },
+	{ 2, 0, 0, 1, 3, 32, },
+	{ 1, 0, 0, 1, 3, 32, },
+	{ 0, 0, 0, 1, 4, 46, },
+	{ 2, 0, 0, 1, 4, 32, },
+	{ 1, 0, 0, 1, 4, 32, },
+	{ 0, 0, 0, 1, 5, 46, },
+	{ 2, 0, 0, 1, 5, 32, },
+	{ 1, 0, 0, 1, 5, 32, },
+	{ 0, 0, 0, 1, 6, 46, },
+	{ 2, 0, 0, 1, 6, 32, },
+	{ 1, 0, 0, 1, 6, 32, },
+	{ 0, 0, 0, 1, 7, 46, },
+	{ 2, 0, 0, 1, 7, 32, },
+	{ 1, 0, 0, 1, 7, 32, },
+	{ 0, 0, 0, 1, 8, 46, },
+	{ 2, 0, 0, 1, 8, 32, },
+	{ 1, 0, 0, 1, 8, 32, },
+	{ 0, 0, 0, 1, 9, 46, },
+	{ 2, 0, 0, 1, 9, 32, },
+	{ 1, 0, 0, 1, 9, 32, },
+	{ 0, 0, 0, 1, 10, 46, },
+	{ 2, 0, 0, 1, 10, 32, },
+	{ 1, 0, 0, 1, 10, 32, },
+	{ 0, 0, 0, 1, 11, 38, },
+	{ 2, 0, 0, 1, 11, 32, },
+	{ 1, 0, 0, 1, 11, 32, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 32, },
+	{ 1, 0, 0, 1, 12, 32, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 32, },
+	{ 1, 0, 0, 1, 13, 32, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 63, },
+	{ 0, 0, 0, 2, 1, 34, },
+	{ 2, 0, 0, 2, 1, 32, },
+	{ 1, 0, 0, 2, 1, 32, },
+	{ 0, 0, 0, 2, 2, 46, },
+	{ 2, 0, 0, 2, 2, 32, },
+	{ 1, 0, 0, 2, 2, 32, },
+	{ 0, 0, 0, 2, 3, 46, },
+	{ 2, 0, 0, 2, 3, 32, },
+	{ 1, 0, 0, 2, 3, 32, },
+	{ 0, 0, 0, 2, 4, 46, },
+	{ 2, 0, 0, 2, 4, 32, },
+	{ 1, 0, 0, 2, 4, 32, },
+	{ 0, 0, 0, 2, 5, 46, },
+	{ 2, 0, 0, 2, 5, 32, },
+	{ 1, 0, 0, 2, 5, 32, },
+	{ 0, 0, 0, 2, 6, 46, },
+	{ 2, 0, 0, 2, 6, 32, },
+	{ 1, 0, 0, 2, 6, 32, },
+	{ 0, 0, 0, 2, 7, 46, },
+	{ 2, 0, 0, 2, 7, 32, },
+	{ 1, 0, 0, 2, 7, 32, },
+	{ 0, 0, 0, 2, 8, 46, },
+	{ 2, 0, 0, 2, 8, 32, },
+	{ 1, 0, 0, 2, 8, 32, },
+	{ 0, 0, 0, 2, 9, 46, },
+	{ 2, 0, 0, 2, 9, 32, },
+	{ 1, 0, 0, 2, 9, 32, },
+	{ 0, 0, 0, 2, 10, 46, },
+	{ 2, 0, 0, 2, 10, 32, },
+	{ 1, 0, 0, 2, 10, 32, },
+	{ 0, 0, 0, 2, 11, 34, },
+	{ 2, 0, 0, 2, 11, 32, },
+	{ 1, 0, 0, 2, 11, 32, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 32, },
+	{ 1, 0, 0, 2, 12, 32, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 32, },
+	{ 1, 0, 0, 2, 13, 32, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 63, },
+	{ 0, 0, 0, 3, 1, 32, },
+	{ 2, 0, 0, 3, 1, 30, },
+	{ 1, 0, 0, 3, 1, 30, },
+	{ 0, 0, 0, 3, 2, 44, },
+	{ 2, 0, 0, 3, 2, 30, },
+	{ 1, 0, 0, 3, 2, 30, },
+	{ 0, 0, 0, 3, 3, 44, },
+	{ 2, 0, 0, 3, 3, 30, },
+	{ 1, 0, 0, 3, 3, 30, },
+	{ 0, 0, 0, 3, 4, 44, },
+	{ 2, 0, 0, 3, 4, 30, },
+	{ 1, 0, 0, 3, 4, 30, },
+	{ 0, 0, 0, 3, 5, 44, },
+	{ 2, 0, 0, 3, 5, 30, },
+	{ 1, 0, 0, 3, 5, 30, },
+	{ 0, 0, 0, 3, 6, 44, },
+	{ 2, 0, 0, 3, 6, 30, },
+	{ 1, 0, 0, 3, 6, 30, },
+	{ 0, 0, 0, 3, 7, 44, },
+	{ 2, 0, 0, 3, 7, 30, },
+	{ 1, 0, 0, 3, 7, 30, },
+	{ 0, 0, 0, 3, 8, 44, },
+	{ 2, 0, 0, 3, 8, 30, },
+	{ 1, 0, 0, 3, 8, 30, },
+	{ 0, 0, 0, 3, 9, 44, },
+	{ 2, 0, 0, 3, 9, 30, },
+	{ 1, 0, 0, 3, 9, 30, },
+	{ 0, 0, 0, 3, 10, 44, },
+	{ 2, 0, 0, 3, 10, 30, },
+	{ 1, 0, 0, 3, 10, 30, },
+	{ 0, 0, 0, 3, 11, 32, },
+	{ 2, 0, 0, 3, 11, 30, },
+	{ 1, 0, 0, 3, 11, 30, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 30, },
+	{ 1, 0, 0, 3, 12, 30, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 30, },
+	{ 1, 0, 0, 3, 13, 30, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 63, },
+	{ 0, 0, 0, 6, 1, 30, },
+	{ 2, 0, 0, 6, 1, 28, },
+	{ 1, 0, 0, 6, 1, 28, },
+	{ 0, 0, 0, 6, 2, 42, },
+	{ 2, 0, 0, 6, 2, 28, },
+	{ 1, 0, 0, 6, 2, 28, },
+	{ 0, 0, 0, 6, 3, 42, },
+	{ 2, 0, 0, 6, 3, 28, },
+	{ 1, 0, 0, 6, 3, 28, },
+	{ 0, 0, 0, 6, 4, 42, },
+	{ 2, 0, 0, 6, 4, 28, },
+	{ 1, 0, 0, 6, 4, 28, },
+	{ 0, 0, 0, 6, 5, 42, },
+	{ 2, 0, 0, 6, 5, 28, },
+	{ 1, 0, 0, 6, 5, 28, },
+	{ 0, 0, 0, 6, 6, 42, },
+	{ 2, 0, 0, 6, 6, 28, },
+	{ 1, 0, 0, 6, 6, 28, },
+	{ 0, 0, 0, 6, 7, 42, },
+	{ 2, 0, 0, 6, 7, 28, },
+	{ 1, 0, 0, 6, 7, 28, },
+	{ 0, 0, 0, 6, 8, 42, },
+	{ 2, 0, 0, 6, 8, 28, },
+	{ 1, 0, 0, 6, 8, 28, },
+	{ 0, 0, 0, 6, 9, 42, },
+	{ 2, 0, 0, 6, 9, 28, },
+	{ 1, 0, 0, 6, 9, 28, },
+	{ 0, 0, 0, 6, 10, 42, },
+	{ 2, 0, 0, 6, 10, 28, },
+	{ 1, 0, 0, 6, 10, 28, },
+	{ 0, 0, 0, 6, 11, 30, },
+	{ 2, 0, 0, 6, 11, 28, },
+	{ 1, 0, 0, 6, 11, 28, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 28, },
+	{ 1, 0, 0, 6, 12, 28, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 28, },
+	{ 1, 0, 0, 6, 13, 28, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 63, },
+	{ 0, 0, 0, 7, 1, 28, },
+	{ 2, 0, 0, 7, 1, 26, },
+	{ 1, 0, 0, 7, 1, 26, },
+	{ 0, 0, 0, 7, 2, 40, },
+	{ 2, 0, 0, 7, 2, 26, },
+	{ 1, 0, 0, 7, 2, 26, },
+	{ 0, 0, 0, 7, 3, 40, },
+	{ 2, 0, 0, 7, 3, 26, },
+	{ 1, 0, 0, 7, 3, 26, },
+	{ 0, 0, 0, 7, 4, 40, },
+	{ 2, 0, 0, 7, 4, 26, },
+	{ 1, 0, 0, 7, 4, 26, },
+	{ 0, 0, 0, 7, 5, 40, },
+	{ 2, 0, 0, 7, 5, 26, },
+	{ 1, 0, 0, 7, 5, 26, },
+	{ 0, 0, 0, 7, 6, 40, },
+	{ 2, 0, 0, 7, 6, 26, },
+	{ 1, 0, 0, 7, 6, 26, },
+	{ 0, 0, 0, 7, 7, 40, },
+	{ 2, 0, 0, 7, 7, 26, },
+	{ 1, 0, 0, 7, 7, 26, },
+	{ 0, 0, 0, 7, 8, 40, },
+	{ 2, 0, 0, 7, 8, 26, },
+	{ 1, 0, 0, 7, 8, 26, },
+	{ 0, 0, 0, 7, 9, 40, },
+	{ 2, 0, 0, 7, 9, 26, },
+	{ 1, 0, 0, 7, 9, 26, },
+	{ 0, 0, 0, 7, 10, 40, },
+	{ 2, 0, 0, 7, 10, 26, },
+	{ 1, 0, 0, 7, 10, 26, },
+	{ 0, 0, 0, 7, 11, 28, },
+	{ 2, 0, 0, 7, 11, 26, },
+	{ 1, 0, 0, 7, 11, 26, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 26, },
+	{ 1, 0, 0, 7, 12, 26, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 26, },
+	{ 1, 0, 0, 7, 13, 26, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 63, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 36, },
+	{ 2, 0, 1, 2, 3, 32, },
+	{ 1, 0, 1, 2, 3, 32, },
+	{ 0, 0, 1, 2, 4, 40, },
+	{ 2, 0, 1, 2, 4, 32, },
+	{ 1, 0, 1, 2, 4, 32, },
+	{ 0, 0, 1, 2, 5, 40, },
+	{ 2, 0, 1, 2, 5, 32, },
+	{ 1, 0, 1, 2, 5, 32, },
+	{ 0, 0, 1, 2, 6, 40, },
+	{ 2, 0, 1, 2, 6, 32, },
+	{ 1, 0, 1, 2, 6, 32, },
+	{ 0, 0, 1, 2, 7, 40, },
+	{ 2, 0, 1, 2, 7, 32, },
+	{ 1, 0, 1, 2, 7, 32, },
+	{ 0, 0, 1, 2, 8, 40, },
+	{ 2, 0, 1, 2, 8, 32, },
+	{ 1, 0, 1, 2, 8, 32, },
+	{ 0, 0, 1, 2, 9, 40, },
+	{ 2, 0, 1, 2, 9, 32, },
+	{ 1, 0, 1, 2, 9, 32, },
+	{ 0, 0, 1, 2, 10, 40, },
+	{ 2, 0, 1, 2, 10, 32, },
+	{ 1, 0, 1, 2, 10, 32, },
+	{ 0, 0, 1, 2, 11, 34, },
+	{ 2, 0, 1, 2, 11, 32, },
+	{ 1, 0, 1, 2, 11, 32, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 32, },
+	{ 1, 0, 1, 2, 12, 32, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 32, },
+	{ 1, 0, 1, 2, 13, 32, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 34, },
+	{ 2, 0, 1, 3, 3, 30, },
+	{ 1, 0, 1, 3, 3, 30, },
+	{ 0, 0, 1, 3, 4, 38, },
+	{ 2, 0, 1, 3, 4, 30, },
+	{ 1, 0, 1, 3, 4, 30, },
+	{ 0, 0, 1, 3, 5, 38, },
+	{ 2, 0, 1, 3, 5, 30, },
+	{ 1, 0, 1, 3, 5, 30, },
+	{ 0, 0, 1, 3, 6, 38, },
+	{ 2, 0, 1, 3, 6, 30, },
+	{ 1, 0, 1, 3, 6, 30, },
+	{ 0, 0, 1, 3, 7, 38, },
+	{ 2, 0, 1, 3, 7, 30, },
+	{ 1, 0, 1, 3, 7, 30, },
+	{ 0, 0, 1, 3, 8, 38, },
+	{ 2, 0, 1, 3, 8, 30, },
+	{ 1, 0, 1, 3, 8, 30, },
+	{ 0, 0, 1, 3, 9, 38, },
+	{ 2, 0, 1, 3, 9, 30, },
+	{ 1, 0, 1, 3, 9, 30, },
+	{ 0, 0, 1, 3, 10, 38, },
+	{ 2, 0, 1, 3, 10, 30, },
+	{ 1, 0, 1, 3, 10, 30, },
+	{ 0, 0, 1, 3, 11, 32, },
+	{ 2, 0, 1, 3, 11, 30, },
+	{ 1, 0, 1, 3, 11, 30, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 30, },
+	{ 1, 0, 1, 3, 12, 30, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 30, },
+	{ 1, 0, 1, 3, 13, 30, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 32, },
+	{ 2, 0, 1, 6, 3, 28, },
+	{ 1, 0, 1, 6, 3, 28, },
+	{ 0, 0, 1, 6, 4, 36, },
+	{ 2, 0, 1, 6, 4, 28, },
+	{ 1, 0, 1, 6, 4, 28, },
+	{ 0, 0, 1, 6, 5, 36, },
+	{ 2, 0, 1, 6, 5, 28, },
+	{ 1, 0, 1, 6, 5, 28, },
+	{ 0, 0, 1, 6, 6, 36, },
+	{ 2, 0, 1, 6, 6, 28, },
+	{ 1, 0, 1, 6, 6, 28, },
+	{ 0, 0, 1, 6, 7, 36, },
+	{ 2, 0, 1, 6, 7, 28, },
+	{ 1, 0, 1, 6, 7, 28, },
+	{ 0, 0, 1, 6, 8, 36, },
+	{ 2, 0, 1, 6, 8, 28, },
+	{ 1, 0, 1, 6, 8, 28, },
+	{ 0, 0, 1, 6, 9, 36, },
+	{ 2, 0, 1, 6, 9, 28, },
+	{ 1, 0, 1, 6, 9, 28, },
+	{ 0, 0, 1, 6, 10, 36, },
+	{ 2, 0, 1, 6, 10, 28, },
+	{ 1, 0, 1, 6, 10, 28, },
+	{ 0, 0, 1, 6, 11, 30, },
+	{ 2, 0, 1, 6, 11, 28, },
+	{ 1, 0, 1, 6, 11, 28, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 28, },
+	{ 1, 0, 1, 6, 12, 28, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 28, },
+	{ 1, 0, 1, 6, 13, 28, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 32, },
+	{ 2, 0, 1, 7, 3, 26, },
+	{ 1, 0, 1, 7, 3, 26, },
+	{ 0, 0, 1, 7, 4, 36, },
+	{ 2, 0, 1, 7, 4, 26, },
+	{ 1, 0, 1, 7, 4, 26, },
+	{ 0, 0, 1, 7, 5, 36, },
+	{ 2, 0, 1, 7, 5, 26, },
+	{ 1, 0, 1, 7, 5, 26, },
+	{ 0, 0, 1, 7, 6, 36, },
+	{ 2, 0, 1, 7, 6, 26, },
+	{ 1, 0, 1, 7, 6, 26, },
+	{ 0, 0, 1, 7, 7, 36, },
+	{ 2, 0, 1, 7, 7, 26, },
+	{ 1, 0, 1, 7, 7, 26, },
+	{ 0, 0, 1, 7, 8, 36, },
+	{ 2, 0, 1, 7, 8, 26, },
+	{ 1, 0, 1, 7, 8, 26, },
+	{ 0, 0, 1, 7, 9, 36, },
+	{ 2, 0, 1, 7, 9, 26, },
+	{ 1, 0, 1, 7, 9, 26, },
+	{ 0, 0, 1, 7, 10, 36, },
+	{ 2, 0, 1, 7, 10, 26, },
+	{ 1, 0, 1, 7, 10, 26, },
+	{ 0, 0, 1, 7, 11, 30, },
+	{ 2, 0, 1, 7, 11, 26, },
+	{ 1, 0, 1, 7, 11, 26, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 26, },
+	{ 1, 0, 1, 7, 12, 26, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 26, },
+	{ 1, 0, 1, 7, 13, 26, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 38, },
+	{ 2, 1, 0, 1, 36, 32, },
+	{ 1, 1, 0, 1, 36, 32, },
+	{ 0, 1, 0, 1, 40, 38, },
+	{ 2, 1, 0, 1, 40, 32, },
+	{ 1, 1, 0, 1, 40, 32, },
+	{ 0, 1, 0, 1, 44, 38, },
+	{ 2, 1, 0, 1, 44, 32, },
+	{ 1, 1, 0, 1, 44, 32, },
+	{ 0, 1, 0, 1, 48, 38, },
+	{ 2, 1, 0, 1, 48, 32, },
+	{ 1, 1, 0, 1, 48, 32, },
+	{ 0, 1, 0, 1, 52, 38, },
+	{ 2, 1, 0, 1, 52, 32, },
+	{ 1, 1, 0, 1, 52, 32, },
+	{ 0, 1, 0, 1, 56, 38, },
+	{ 2, 1, 0, 1, 56, 32, },
+	{ 1, 1, 0, 1, 56, 32, },
+	{ 0, 1, 0, 1, 60, 38, },
+	{ 2, 1, 0, 1, 60, 32, },
+	{ 1, 1, 0, 1, 60, 32, },
+	{ 0, 1, 0, 1, 64, 38, },
+	{ 2, 1, 0, 1, 64, 32, },
+	{ 1, 1, 0, 1, 64, 32, },
+	{ 0, 1, 0, 1, 100, 36, },
+	{ 2, 1, 0, 1, 100, 32, },
+	{ 1, 1, 0, 1, 100, 32, },
+	{ 0, 1, 0, 1, 104, 36, },
+	{ 2, 1, 0, 1, 104, 32, },
+	{ 1, 1, 0, 1, 104, 32, },
+	{ 0, 1, 0, 1, 108, 36, },
+	{ 2, 1, 0, 1, 108, 32, },
+	{ 1, 1, 0, 1, 108, 32, },
+	{ 0, 1, 0, 1, 112, 36, },
+	{ 2, 1, 0, 1, 112, 32, },
+	{ 1, 1, 0, 1, 112, 32, },
+	{ 0, 1, 0, 1, 116, 36, },
+	{ 2, 1, 0, 1, 116, 32, },
+	{ 1, 1, 0, 1, 116, 32, },
+	{ 0, 1, 0, 1, 120, 36, },
+	{ 2, 1, 0, 1, 120, 32, },
+	{ 1, 1, 0, 1, 120, 32, },
+	{ 0, 1, 0, 1, 124, 36, },
+	{ 2, 1, 0, 1, 124, 32, },
+	{ 1, 1, 0, 1, 124, 32, },
+	{ 0, 1, 0, 1, 128, 36, },
+	{ 2, 1, 0, 1, 128, 32, },
+	{ 1, 1, 0, 1, 128, 32, },
+	{ 0, 1, 0, 1, 132, 36, },
+	{ 2, 1, 0, 1, 132, 32, },
+	{ 1, 1, 0, 1, 132, 32, },
+	{ 0, 1, 0, 1, 136, 36, },
+	{ 2, 1, 0, 1, 136, 32, },
+	{ 1, 1, 0, 1, 136, 32, },
+	{ 0, 1, 0, 1, 140, 36, },
+	{ 2, 1, 0, 1, 140, 32, },
+	{ 1, 1, 0, 1, 140, 32, },
+	{ 0, 1, 0, 1, 149, 36, },
+	{ 2, 1, 0, 1, 149, 32, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 36, },
+	{ 2, 1, 0, 1, 153, 32, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 36, },
+	{ 2, 1, 0, 1, 157, 32, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 36, },
+	{ 2, 1, 0, 1, 161, 32, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 36, },
+	{ 2, 1, 0, 1, 165, 32, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 36, },
+	{ 2, 1, 0, 2, 36, 32, },
+	{ 1, 1, 0, 2, 36, 32, },
+	{ 0, 1, 0, 2, 40, 36, },
+	{ 2, 1, 0, 2, 40, 32, },
+	{ 1, 1, 0, 2, 40, 32, },
+	{ 0, 1, 0, 2, 44, 36, },
+	{ 2, 1, 0, 2, 44, 32, },
+	{ 1, 1, 0, 2, 44, 32, },
+	{ 0, 1, 0, 2, 48, 36, },
+	{ 2, 1, 0, 2, 48, 32, },
+	{ 1, 1, 0, 2, 48, 32, },
+	{ 0, 1, 0, 2, 52, 36, },
+	{ 2, 1, 0, 2, 52, 32, },
+	{ 1, 1, 0, 2, 52, 32, },
+	{ 0, 1, 0, 2, 56, 36, },
+	{ 2, 1, 0, 2, 56, 32, },
+	{ 1, 1, 0, 2, 56, 32, },
+	{ 0, 1, 0, 2, 60, 36, },
+	{ 2, 1, 0, 2, 60, 32, },
+	{ 1, 1, 0, 2, 60, 32, },
+	{ 0, 1, 0, 2, 64, 36, },
+	{ 2, 1, 0, 2, 64, 32, },
+	{ 1, 1, 0, 2, 64, 32, },
+	{ 0, 1, 0, 2, 100, 36, },
+	{ 2, 1, 0, 2, 100, 32, },
+	{ 1, 1, 0, 2, 100, 32, },
+	{ 0, 1, 0, 2, 104, 36, },
+	{ 2, 1, 0, 2, 104, 32, },
+	{ 1, 1, 0, 2, 104, 32, },
+	{ 0, 1, 0, 2, 108, 36, },
+	{ 2, 1, 0, 2, 108, 32, },
+	{ 1, 1, 0, 2, 108, 32, },
+	{ 0, 1, 0, 2, 112, 36, },
+	{ 2, 1, 0, 2, 112, 32, },
+	{ 1, 1, 0, 2, 112, 32, },
+	{ 0, 1, 0, 2, 116, 36, },
+	{ 2, 1, 0, 2, 116, 32, },
+	{ 1, 1, 0, 2, 116, 32, },
+	{ 0, 1, 0, 2, 120, 36, },
+	{ 2, 1, 0, 2, 120, 32, },
+	{ 1, 1, 0, 2, 120, 32, },
+	{ 0, 1, 0, 2, 124, 36, },
+	{ 2, 1, 0, 2, 124, 32, },
+	{ 1, 1, 0, 2, 124, 32, },
+	{ 0, 1, 0, 2, 128, 36, },
+	{ 2, 1, 0, 2, 128, 32, },
+	{ 1, 1, 0, 2, 128, 32, },
+	{ 0, 1, 0, 2, 132, 36, },
+	{ 2, 1, 0, 2, 132, 32, },
+	{ 1, 1, 0, 2, 132, 32, },
+	{ 0, 1, 0, 2, 136, 36, },
+	{ 2, 1, 0, 2, 136, 32, },
+	{ 1, 1, 0, 2, 136, 32, },
+	{ 0, 1, 0, 2, 140, 34, },
+	{ 2, 1, 0, 2, 140, 32, },
+	{ 1, 1, 0, 2, 140, 32, },
+	{ 0, 1, 0, 2, 149, 32, },
+	{ 2, 1, 0, 2, 149, 32, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 38, },
+	{ 2, 1, 0, 2, 153, 32, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 38, },
+	{ 2, 1, 0, 2, 157, 32, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 38, },
+	{ 2, 1, 0, 2, 161, 32, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 38, },
+	{ 2, 1, 0, 2, 165, 32, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 34, },
+	{ 2, 1, 0, 3, 36, 30, },
+	{ 1, 1, 0, 3, 36, 30, },
+	{ 0, 1, 0, 3, 40, 34, },
+	{ 2, 1, 0, 3, 40, 30, },
+	{ 1, 1, 0, 3, 40, 30, },
+	{ 0, 1, 0, 3, 44, 34, },
+	{ 2, 1, 0, 3, 44, 30, },
+	{ 1, 1, 0, 3, 44, 30, },
+	{ 0, 1, 0, 3, 48, 34, },
+	{ 2, 1, 0, 3, 48, 30, },
+	{ 1, 1, 0, 3, 48, 30, },
+	{ 0, 1, 0, 3, 52, 34, },
+	{ 2, 1, 0, 3, 52, 30, },
+	{ 1, 1, 0, 3, 52, 30, },
+	{ 0, 1, 0, 3, 56, 34, },
+	{ 2, 1, 0, 3, 56, 30, },
+	{ 1, 1, 0, 3, 56, 30, },
+	{ 0, 1, 0, 3, 60, 34, },
+	{ 2, 1, 0, 3, 60, 30, },
+	{ 1, 1, 0, 3, 60, 30, },
+	{ 0, 1, 0, 3, 64, 34, },
+	{ 2, 1, 0, 3, 64, 30, },
+	{ 1, 1, 0, 3, 64, 30, },
+	{ 0, 1, 0, 3, 100, 34, },
+	{ 2, 1, 0, 3, 100, 30, },
+	{ 1, 1, 0, 3, 100, 30, },
+	{ 0, 1, 0, 3, 104, 34, },
+	{ 2, 1, 0, 3, 104, 30, },
+	{ 1, 1, 0, 3, 104, 30, },
+	{ 0, 1, 0, 3, 108, 34, },
+	{ 2, 1, 0, 3, 108, 30, },
+	{ 1, 1, 0, 3, 108, 30, },
+	{ 0, 1, 0, 3, 112, 34, },
+	{ 2, 1, 0, 3, 112, 30, },
+	{ 1, 1, 0, 3, 112, 30, },
+	{ 0, 1, 0, 3, 116, 34, },
+	{ 2, 1, 0, 3, 116, 30, },
+	{ 1, 1, 0, 3, 116, 30, },
+	{ 0, 1, 0, 3, 120, 34, },
+	{ 2, 1, 0, 3, 120, 30, },
+	{ 1, 1, 0, 3, 120, 30, },
+	{ 0, 1, 0, 3, 124, 34, },
+	{ 2, 1, 0, 3, 124, 30, },
+	{ 1, 1, 0, 3, 124, 30, },
+	{ 0, 1, 0, 3, 128, 34, },
+	{ 2, 1, 0, 3, 128, 30, },
+	{ 1, 1, 0, 3, 128, 30, },
+	{ 0, 1, 0, 3, 132, 34, },
+	{ 2, 1, 0, 3, 132, 30, },
+	{ 1, 1, 0, 3, 132, 30, },
+	{ 0, 1, 0, 3, 136, 34, },
+	{ 2, 1, 0, 3, 136, 30, },
+	{ 1, 1, 0, 3, 136, 30, },
+	{ 0, 1, 0, 3, 140, 32, },
+	{ 2, 1, 0, 3, 140, 30, },
+	{ 1, 1, 0, 3, 140, 30, },
+	{ 0, 1, 0, 3, 149, 30, },
+	{ 2, 1, 0, 3, 149, 30, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 36, },
+	{ 2, 1, 0, 3, 153, 30, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 36, },
+	{ 2, 1, 0, 3, 157, 30, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 36, },
+	{ 2, 1, 0, 3, 161, 30, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 36, },
+	{ 2, 1, 0, 3, 165, 30, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 32, },
+	{ 2, 1, 0, 6, 36, 28, },
+	{ 1, 1, 0, 6, 36, 28, },
+	{ 0, 1, 0, 6, 40, 32, },
+	{ 2, 1, 0, 6, 40, 28, },
+	{ 1, 1, 0, 6, 40, 28, },
+	{ 0, 1, 0, 6, 44, 32, },
+	{ 2, 1, 0, 6, 44, 28, },
+	{ 1, 1, 0, 6, 44, 28, },
+	{ 0, 1, 0, 6, 48, 32, },
+	{ 2, 1, 0, 6, 48, 28, },
+	{ 1, 1, 0, 6, 48, 28, },
+	{ 0, 1, 0, 6, 52, 32, },
+	{ 2, 1, 0, 6, 52, 28, },
+	{ 1, 1, 0, 6, 52, 28, },
+	{ 0, 1, 0, 6, 56, 32, },
+	{ 2, 1, 0, 6, 56, 28, },
+	{ 1, 1, 0, 6, 56, 28, },
+	{ 0, 1, 0, 6, 60, 32, },
+	{ 2, 1, 0, 6, 60, 28, },
+	{ 1, 1, 0, 6, 60, 28, },
+	{ 0, 1, 0, 6, 64, 32, },
+	{ 2, 1, 0, 6, 64, 28, },
+	{ 1, 1, 0, 6, 64, 28, },
+	{ 0, 1, 0, 6, 100, 32, },
+	{ 2, 1, 0, 6, 100, 28, },
+	{ 1, 1, 0, 6, 100, 28, },
+	{ 0, 1, 0, 6, 104, 32, },
+	{ 2, 1, 0, 6, 104, 28, },
+	{ 1, 1, 0, 6, 104, 28, },
+	{ 0, 1, 0, 6, 108, 32, },
+	{ 2, 1, 0, 6, 108, 28, },
+	{ 1, 1, 0, 6, 108, 28, },
+	{ 0, 1, 0, 6, 112, 32, },
+	{ 2, 1, 0, 6, 112, 28, },
+	{ 1, 1, 0, 6, 112, 28, },
+	{ 0, 1, 0, 6, 116, 32, },
+	{ 2, 1, 0, 6, 116, 28, },
+	{ 1, 1, 0, 6, 116, 28, },
+	{ 0, 1, 0, 6, 120, 32, },
+	{ 2, 1, 0, 6, 120, 28, },
+	{ 1, 1, 0, 6, 120, 28, },
+	{ 0, 1, 0, 6, 124, 32, },
+	{ 2, 1, 0, 6, 124, 28, },
+	{ 1, 1, 0, 6, 124, 28, },
+	{ 0, 1, 0, 6, 128, 32, },
+	{ 2, 1, 0, 6, 128, 28, },
+	{ 1, 1, 0, 6, 128, 28, },
+	{ 0, 1, 0, 6, 132, 32, },
+	{ 2, 1, 0, 6, 132, 28, },
+	{ 1, 1, 0, 6, 132, 28, },
+	{ 0, 1, 0, 6, 136, 32, },
+	{ 2, 1, 0, 6, 136, 28, },
+	{ 1, 1, 0, 6, 136, 28, },
+	{ 0, 1, 0, 6, 140, 30, },
+	{ 2, 1, 0, 6, 140, 28, },
+	{ 1, 1, 0, 6, 140, 28, },
+	{ 0, 1, 0, 6, 149, 28, },
+	{ 2, 1, 0, 6, 149, 28, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 34, },
+	{ 2, 1, 0, 6, 153, 28, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 34, },
+	{ 2, 1, 0, 6, 157, 28, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 34, },
+	{ 2, 1, 0, 6, 161, 28, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 34, },
+	{ 2, 1, 0, 6, 165, 28, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 30, },
+	{ 2, 1, 0, 7, 36, 26, },
+	{ 1, 1, 0, 7, 36, 26, },
+	{ 0, 1, 0, 7, 40, 30, },
+	{ 2, 1, 0, 7, 40, 26, },
+	{ 1, 1, 0, 7, 40, 26, },
+	{ 0, 1, 0, 7, 44, 30, },
+	{ 2, 1, 0, 7, 44, 26, },
+	{ 1, 1, 0, 7, 44, 26, },
+	{ 0, 1, 0, 7, 48, 30, },
+	{ 2, 1, 0, 7, 48, 26, },
+	{ 1, 1, 0, 7, 48, 26, },
+	{ 0, 1, 0, 7, 52, 30, },
+	{ 2, 1, 0, 7, 52, 26, },
+	{ 1, 1, 0, 7, 52, 26, },
+	{ 0, 1, 0, 7, 56, 30, },
+	{ 2, 1, 0, 7, 56, 26, },
+	{ 1, 1, 0, 7, 56, 26, },
+	{ 0, 1, 0, 7, 60, 30, },
+	{ 2, 1, 0, 7, 60, 26, },
+	{ 1, 1, 0, 7, 60, 26, },
+	{ 0, 1, 0, 7, 64, 30, },
+	{ 2, 1, 0, 7, 64, 26, },
+	{ 1, 1, 0, 7, 64, 26, },
+	{ 0, 1, 0, 7, 100, 30, },
+	{ 2, 1, 0, 7, 100, 26, },
+	{ 1, 1, 0, 7, 100, 26, },
+	{ 0, 1, 0, 7, 104, 30, },
+	{ 2, 1, 0, 7, 104, 26, },
+	{ 1, 1, 0, 7, 104, 26, },
+	{ 0, 1, 0, 7, 108, 30, },
+	{ 2, 1, 0, 7, 108, 26, },
+	{ 1, 1, 0, 7, 108, 26, },
+	{ 0, 1, 0, 7, 112, 30, },
+	{ 2, 1, 0, 7, 112, 26, },
+	{ 1, 1, 0, 7, 112, 26, },
+	{ 0, 1, 0, 7, 116, 30, },
+	{ 2, 1, 0, 7, 116, 26, },
+	{ 1, 1, 0, 7, 116, 26, },
+	{ 0, 1, 0, 7, 120, 30, },
+	{ 2, 1, 0, 7, 120, 26, },
+	{ 1, 1, 0, 7, 120, 26, },
+	{ 0, 1, 0, 7, 124, 30, },
+	{ 2, 1, 0, 7, 124, 26, },
+	{ 1, 1, 0, 7, 124, 26, },
+	{ 0, 1, 0, 7, 128, 30, },
+	{ 2, 1, 0, 7, 128, 26, },
+	{ 1, 1, 0, 7, 128, 26, },
+	{ 0, 1, 0, 7, 132, 30, },
+	{ 2, 1, 0, 7, 132, 26, },
+	{ 1, 1, 0, 7, 132, 26, },
+	{ 0, 1, 0, 7, 136, 30, },
+	{ 2, 1, 0, 7, 136, 26, },
+	{ 1, 1, 0, 7, 136, 26, },
+	{ 0, 1, 0, 7, 140, 28, },
+	{ 2, 1, 0, 7, 140, 26, },
+	{ 1, 1, 0, 7, 140, 26, },
+	{ 0, 1, 0, 7, 149, 26, },
+	{ 2, 1, 0, 7, 149, 26, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 32, },
+	{ 2, 1, 0, 7, 153, 26, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 32, },
+	{ 2, 1, 0, 7, 157, 26, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 32, },
+	{ 2, 1, 0, 7, 161, 26, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 32, },
+	{ 2, 1, 0, 7, 165, 26, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 32, },
+	{ 2, 1, 1, 2, 38, 32, },
+	{ 1, 1, 1, 2, 38, 32, },
+	{ 0, 1, 1, 2, 46, 32, },
+	{ 2, 1, 1, 2, 46, 32, },
+	{ 1, 1, 1, 2, 46, 32, },
+	{ 0, 1, 1, 2, 54, 32, },
+	{ 2, 1, 1, 2, 54, 32, },
+	{ 1, 1, 1, 2, 54, 32, },
+	{ 0, 1, 1, 2, 62, 30, },
+	{ 2, 1, 1, 2, 62, 32, },
+	{ 1, 1, 1, 2, 62, 32, },
+	{ 0, 1, 1, 2, 102, 30, },
+	{ 2, 1, 1, 2, 102, 32, },
+	{ 1, 1, 1, 2, 102, 32, },
+	{ 0, 1, 1, 2, 110, 38, },
+	{ 2, 1, 1, 2, 110, 32, },
+	{ 1, 1, 1, 2, 110, 32, },
+	{ 0, 1, 1, 2, 118, 38, },
+	{ 2, 1, 1, 2, 118, 32, },
+	{ 1, 1, 1, 2, 118, 32, },
+	{ 0, 1, 1, 2, 126, 38, },
+	{ 2, 1, 1, 2, 126, 32, },
+	{ 1, 1, 1, 2, 126, 32, },
+	{ 0, 1, 1, 2, 134, 38, },
+	{ 2, 1, 1, 2, 134, 32, },
+	{ 1, 1, 1, 2, 134, 32, },
+	{ 0, 1, 1, 2, 151, 32, },
+	{ 2, 1, 1, 2, 151, 32, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 32, },
+	{ 2, 1, 1, 2, 159, 32, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 30, },
+	{ 2, 1, 1, 3, 38, 30, },
+	{ 1, 1, 1, 3, 38, 30, },
+	{ 0, 1, 1, 3, 46, 30, },
+	{ 2, 1, 1, 3, 46, 30, },
+	{ 1, 1, 1, 3, 46, 30, },
+	{ 0, 1, 1, 3, 54, 30, },
+	{ 2, 1, 1, 3, 54, 30, },
+	{ 1, 1, 1, 3, 54, 30, },
+	{ 0, 1, 1, 3, 62, 28, },
+	{ 2, 1, 1, 3, 62, 30, },
+	{ 1, 1, 1, 3, 62, 30, },
+	{ 0, 1, 1, 3, 102, 28, },
+	{ 2, 1, 1, 3, 102, 30, },
+	{ 1, 1, 1, 3, 102, 30, },
+	{ 0, 1, 1, 3, 110, 36, },
+	{ 2, 1, 1, 3, 110, 30, },
+	{ 1, 1, 1, 3, 110, 30, },
+	{ 0, 1, 1, 3, 118, 36, },
+	{ 2, 1, 1, 3, 118, 30, },
+	{ 1, 1, 1, 3, 118, 30, },
+	{ 0, 1, 1, 3, 126, 36, },
+	{ 2, 1, 1, 3, 126, 30, },
+	{ 1, 1, 1, 3, 126, 30, },
+	{ 0, 1, 1, 3, 134, 36, },
+	{ 2, 1, 1, 3, 134, 30, },
+	{ 1, 1, 1, 3, 134, 30, },
+	{ 0, 1, 1, 3, 151, 30, },
+	{ 2, 1, 1, 3, 151, 30, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 30, },
+	{ 2, 1, 1, 3, 159, 30, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 28, },
+	{ 2, 1, 1, 6, 38, 28, },
+	{ 1, 1, 1, 6, 38, 28, },
+	{ 0, 1, 1, 6, 46, 28, },
+	{ 2, 1, 1, 6, 46, 28, },
+	{ 1, 1, 1, 6, 46, 28, },
+	{ 0, 1, 1, 6, 54, 28, },
+	{ 2, 1, 1, 6, 54, 28, },
+	{ 1, 1, 1, 6, 54, 28, },
+	{ 0, 1, 1, 6, 62, 26, },
+	{ 2, 1, 1, 6, 62, 28, },
+	{ 1, 1, 1, 6, 62, 28, },
+	{ 0, 1, 1, 6, 102, 26, },
+	{ 2, 1, 1, 6, 102, 28, },
+	{ 1, 1, 1, 6, 102, 28, },
+	{ 0, 1, 1, 6, 110, 34, },
+	{ 2, 1, 1, 6, 110, 28, },
+	{ 1, 1, 1, 6, 110, 28, },
+	{ 0, 1, 1, 6, 118, 34, },
+	{ 2, 1, 1, 6, 118, 28, },
+	{ 1, 1, 1, 6, 118, 28, },
+	{ 0, 1, 1, 6, 126, 34, },
+	{ 2, 1, 1, 6, 126, 28, },
+	{ 1, 1, 1, 6, 126, 28, },
+	{ 0, 1, 1, 6, 134, 34, },
+	{ 2, 1, 1, 6, 134, 28, },
+	{ 1, 1, 1, 6, 134, 28, },
+	{ 0, 1, 1, 6, 151, 28, },
+	{ 2, 1, 1, 6, 151, 28, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 28, },
+	{ 2, 1, 1, 6, 159, 28, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 26, },
+	{ 2, 1, 1, 7, 38, 26, },
+	{ 1, 1, 1, 7, 38, 26, },
+	{ 0, 1, 1, 7, 46, 26, },
+	{ 2, 1, 1, 7, 46, 26, },
+	{ 1, 1, 1, 7, 46, 26, },
+	{ 0, 1, 1, 7, 54, 26, },
+	{ 2, 1, 1, 7, 54, 26, },
+	{ 1, 1, 1, 7, 54, 26, },
+	{ 0, 1, 1, 7, 62, 24, },
+	{ 2, 1, 1, 7, 62, 26, },
+	{ 1, 1, 1, 7, 62, 26, },
+	{ 0, 1, 1, 7, 102, 24, },
+	{ 2, 1, 1, 7, 102, 26, },
+	{ 1, 1, 1, 7, 102, 26, },
+	{ 0, 1, 1, 7, 110, 32, },
+	{ 2, 1, 1, 7, 110, 26, },
+	{ 1, 1, 1, 7, 110, 26, },
+	{ 0, 1, 1, 7, 118, 32, },
+	{ 2, 1, 1, 7, 118, 26, },
+	{ 1, 1, 1, 7, 118, 26, },
+	{ 0, 1, 1, 7, 126, 32, },
+	{ 2, 1, 1, 7, 126, 26, },
+	{ 1, 1, 1, 7, 126, 26, },
+	{ 0, 1, 1, 7, 134, 32, },
+	{ 2, 1, 1, 7, 134, 26, },
+	{ 1, 1, 1, 7, 134, 26, },
+	{ 0, 1, 1, 7, 151, 26, },
+	{ 2, 1, 1, 7, 151, 26, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 26, },
+	{ 2, 1, 1, 7, 159, 26, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 26, },
+	{ 2, 1, 2, 4, 42, 32, },
+	{ 1, 1, 2, 4, 42, 32, },
+	{ 0, 1, 2, 4, 58, 26, },
+	{ 2, 1, 2, 4, 58, 32, },
+	{ 1, 1, 2, 4, 58, 32, },
+	{ 0, 1, 2, 4, 106, 28, },
+	{ 2, 1, 2, 4, 106, 32, },
+	{ 1, 1, 2, 4, 106, 32, },
+	{ 0, 1, 2, 4, 122, 28, },
+	{ 2, 1, 2, 4, 122, 32, },
+	{ 1, 1, 2, 4, 122, 32, },
+	{ 0, 1, 2, 4, 155, 28, },
+	{ 2, 1, 2, 4, 155, 32, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 24, },
+	{ 2, 1, 2, 5, 42, 30, },
+	{ 1, 1, 2, 5, 42, 30, },
+	{ 0, 1, 2, 5, 58, 24, },
+	{ 2, 1, 2, 5, 58, 30, },
+	{ 1, 1, 2, 5, 58, 30, },
+	{ 0, 1, 2, 5, 106, 26, },
+	{ 2, 1, 2, 5, 106, 30, },
+	{ 1, 1, 2, 5, 106, 30, },
+	{ 0, 1, 2, 5, 122, 26, },
+	{ 2, 1, 2, 5, 122, 30, },
+	{ 1, 1, 2, 5, 122, 30, },
+	{ 0, 1, 2, 5, 155, 26, },
+	{ 2, 1, 2, 5, 155, 30, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 22, },
+	{ 2, 1, 2, 8, 42, 28, },
+	{ 1, 1, 2, 8, 42, 28, },
+	{ 0, 1, 2, 8, 58, 22, },
+	{ 2, 1, 2, 8, 58, 28, },
+	{ 1, 1, 2, 8, 58, 28, },
+	{ 0, 1, 2, 8, 106, 24, },
+	{ 2, 1, 2, 8, 106, 28, },
+	{ 1, 1, 2, 8, 106, 28, },
+	{ 0, 1, 2, 8, 122, 24, },
+	{ 2, 1, 2, 8, 122, 28, },
+	{ 1, 1, 2, 8, 122, 28, },
+	{ 0, 1, 2, 8, 155, 24, },
+	{ 2, 1, 2, 8, 155, 28, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 20, },
+	{ 2, 1, 2, 9, 42, 26, },
+	{ 1, 1, 2, 9, 42, 26, },
+	{ 0, 1, 2, 9, 58, 20, },
+	{ 2, 1, 2, 9, 58, 26, },
+	{ 1, 1, 2, 9, 58, 26, },
+	{ 0, 1, 2, 9, 106, 22, },
+	{ 2, 1, 2, 9, 106, 26, },
+	{ 1, 1, 2, 9, 106, 26, },
+	{ 0, 1, 2, 9, 122, 22, },
+	{ 2, 1, 2, 9, 122, 26, },
+	{ 1, 1, 2, 9, 122, 26, },
+	{ 0, 1, 2, 9, 155, 22, },
+	{ 2, 1, 2, 9, 155, 26, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type7);
+
+static const struct rtw_txpwr_lmt_cfg_pair rtw8814a_txpwr_lmt_type8[] = {
+	{ 0, 0, 0, 0, 1, 46, },
+	{ 2, 0, 0, 0, 1, 46, },
+	{ 1, 0, 0, 0, 1, 46, },
+	{ 0, 0, 0, 0, 2, 46, },
+	{ 2, 0, 0, 0, 2, 46, },
+	{ 1, 0, 0, 0, 2, 46, },
+	{ 0, 0, 0, 0, 3, 46, },
+	{ 2, 0, 0, 0, 3, 46, },
+	{ 1, 0, 0, 0, 3, 46, },
+	{ 0, 0, 0, 0, 4, 46, },
+	{ 2, 0, 0, 0, 4, 46, },
+	{ 1, 0, 0, 0, 4, 46, },
+	{ 0, 0, 0, 0, 5, 46, },
+	{ 2, 0, 0, 0, 5, 46, },
+	{ 1, 0, 0, 0, 5, 46, },
+	{ 0, 0, 0, 0, 6, 46, },
+	{ 2, 0, 0, 0, 6, 46, },
+	{ 1, 0, 0, 0, 6, 46, },
+	{ 0, 0, 0, 0, 7, 46, },
+	{ 2, 0, 0, 0, 7, 46, },
+	{ 1, 0, 0, 0, 7, 46, },
+	{ 0, 0, 0, 0, 8, 46, },
+	{ 2, 0, 0, 0, 8, 46, },
+	{ 1, 0, 0, 0, 8, 46, },
+	{ 0, 0, 0, 0, 9, 46, },
+	{ 2, 0, 0, 0, 9, 46, },
+	{ 1, 0, 0, 0, 9, 46, },
+	{ 0, 0, 0, 0, 10, 46, },
+	{ 2, 0, 0, 0, 10, 46, },
+	{ 1, 0, 0, 0, 10, 46, },
+	{ 0, 0, 0, 0, 11, 46, },
+	{ 2, 0, 0, 0, 11, 46, },
+	{ 1, 0, 0, 0, 11, 46, },
+	{ 0, 0, 0, 0, 12, 63, },
+	{ 2, 0, 0, 0, 12, 46, },
+	{ 1, 0, 0, 0, 12, 46, },
+	{ 0, 0, 0, 0, 13, 63, },
+	{ 2, 0, 0, 0, 13, 46, },
+	{ 1, 0, 0, 0, 13, 46, },
+	{ 0, 0, 0, 0, 14, 63, },
+	{ 2, 0, 0, 0, 14, 63, },
+	{ 1, 0, 0, 0, 14, 46, },
+	{ 0, 0, 0, 1, 1, 46, },
+	{ 2, 0, 0, 1, 1, 46, },
+	{ 1, 0, 0, 1, 1, 46, },
+	{ 0, 0, 0, 1, 2, 46, },
+	{ 2, 0, 0, 1, 2, 46, },
+	{ 1, 0, 0, 1, 2, 46, },
+	{ 0, 0, 0, 1, 3, 46, },
+	{ 2, 0, 0, 1, 3, 46, },
+	{ 1, 0, 0, 1, 3, 46, },
+	{ 0, 0, 0, 1, 4, 46, },
+	{ 2, 0, 0, 1, 4, 46, },
+	{ 1, 0, 0, 1, 4, 46, },
+	{ 0, 0, 0, 1, 5, 46, },
+	{ 2, 0, 0, 1, 5, 46, },
+	{ 1, 0, 0, 1, 5, 46, },
+	{ 0, 0, 0, 1, 6, 46, },
+	{ 2, 0, 0, 1, 6, 46, },
+	{ 1, 0, 0, 1, 6, 46, },
+	{ 0, 0, 0, 1, 7, 46, },
+	{ 2, 0, 0, 1, 7, 46, },
+	{ 1, 0, 0, 1, 7, 46, },
+	{ 0, 0, 0, 1, 8, 46, },
+	{ 2, 0, 0, 1, 8, 46, },
+	{ 1, 0, 0, 1, 8, 46, },
+	{ 0, 0, 0, 1, 9, 46, },
+	{ 2, 0, 0, 1, 9, 46, },
+	{ 1, 0, 0, 1, 9, 46, },
+	{ 0, 0, 0, 1, 10, 46, },
+	{ 2, 0, 0, 1, 10, 46, },
+	{ 1, 0, 0, 1, 10, 46, },
+	{ 0, 0, 0, 1, 11, 46, },
+	{ 2, 0, 0, 1, 11, 46, },
+	{ 1, 0, 0, 1, 11, 46, },
+	{ 0, 0, 0, 1, 12, 63, },
+	{ 2, 0, 0, 1, 12, 46, },
+	{ 1, 0, 0, 1, 12, 46, },
+	{ 0, 0, 0, 1, 13, 63, },
+	{ 2, 0, 0, 1, 13, 46, },
+	{ 1, 0, 0, 1, 13, 46, },
+	{ 0, 0, 0, 1, 14, 63, },
+	{ 2, 0, 0, 1, 14, 63, },
+	{ 1, 0, 0, 1, 14, 46, },
+	{ 0, 0, 0, 2, 1, 46, },
+	{ 2, 0, 0, 2, 1, 46, },
+	{ 1, 0, 0, 2, 1, 46, },
+	{ 0, 0, 0, 2, 2, 46, },
+	{ 2, 0, 0, 2, 2, 46, },
+	{ 1, 0, 0, 2, 2, 46, },
+	{ 0, 0, 0, 2, 3, 46, },
+	{ 2, 0, 0, 2, 3, 46, },
+	{ 1, 0, 0, 2, 3, 46, },
+	{ 0, 0, 0, 2, 4, 46, },
+	{ 2, 0, 0, 2, 4, 46, },
+	{ 1, 0, 0, 2, 4, 46, },
+	{ 0, 0, 0, 2, 5, 46, },
+	{ 2, 0, 0, 2, 5, 46, },
+	{ 1, 0, 0, 2, 5, 46, },
+	{ 0, 0, 0, 2, 6, 46, },
+	{ 2, 0, 0, 2, 6, 46, },
+	{ 1, 0, 0, 2, 6, 46, },
+	{ 0, 0, 0, 2, 7, 46, },
+	{ 2, 0, 0, 2, 7, 46, },
+	{ 1, 0, 0, 2, 7, 46, },
+	{ 0, 0, 0, 2, 8, 46, },
+	{ 2, 0, 0, 2, 8, 46, },
+	{ 1, 0, 0, 2, 8, 46, },
+	{ 0, 0, 0, 2, 9, 46, },
+	{ 2, 0, 0, 2, 9, 46, },
+	{ 1, 0, 0, 2, 9, 46, },
+	{ 0, 0, 0, 2, 10, 46, },
+	{ 2, 0, 0, 2, 10, 46, },
+	{ 1, 0, 0, 2, 10, 46, },
+	{ 0, 0, 0, 2, 11, 46, },
+	{ 2, 0, 0, 2, 11, 46, },
+	{ 1, 0, 0, 2, 11, 46, },
+	{ 0, 0, 0, 2, 12, 63, },
+	{ 2, 0, 0, 2, 12, 46, },
+	{ 1, 0, 0, 2, 12, 46, },
+	{ 0, 0, 0, 2, 13, 63, },
+	{ 2, 0, 0, 2, 13, 46, },
+	{ 1, 0, 0, 2, 13, 46, },
+	{ 0, 0, 0, 2, 14, 63, },
+	{ 2, 0, 0, 2, 14, 63, },
+	{ 1, 0, 0, 2, 14, 46, },
+	{ 0, 0, 0, 3, 1, 46, },
+	{ 2, 0, 0, 3, 1, 46, },
+	{ 1, 0, 0, 3, 1, 46, },
+	{ 0, 0, 0, 3, 2, 46, },
+	{ 2, 0, 0, 3, 2, 46, },
+	{ 1, 0, 0, 3, 2, 46, },
+	{ 0, 0, 0, 3, 3, 46, },
+	{ 2, 0, 0, 3, 3, 46, },
+	{ 1, 0, 0, 3, 3, 46, },
+	{ 0, 0, 0, 3, 4, 46, },
+	{ 2, 0, 0, 3, 4, 46, },
+	{ 1, 0, 0, 3, 4, 46, },
+	{ 0, 0, 0, 3, 5, 46, },
+	{ 2, 0, 0, 3, 5, 46, },
+	{ 1, 0, 0, 3, 5, 46, },
+	{ 0, 0, 0, 3, 6, 46, },
+	{ 2, 0, 0, 3, 6, 46, },
+	{ 1, 0, 0, 3, 6, 46, },
+	{ 0, 0, 0, 3, 7, 46, },
+	{ 2, 0, 0, 3, 7, 46, },
+	{ 1, 0, 0, 3, 7, 46, },
+	{ 0, 0, 0, 3, 8, 46, },
+	{ 2, 0, 0, 3, 8, 46, },
+	{ 1, 0, 0, 3, 8, 46, },
+	{ 0, 0, 0, 3, 9, 46, },
+	{ 2, 0, 0, 3, 9, 46, },
+	{ 1, 0, 0, 3, 9, 46, },
+	{ 0, 0, 0, 3, 10, 46, },
+	{ 2, 0, 0, 3, 10, 46, },
+	{ 1, 0, 0, 3, 10, 46, },
+	{ 0, 0, 0, 3, 11, 46, },
+	{ 2, 0, 0, 3, 11, 46, },
+	{ 1, 0, 0, 3, 11, 46, },
+	{ 0, 0, 0, 3, 12, 63, },
+	{ 2, 0, 0, 3, 12, 46, },
+	{ 1, 0, 0, 3, 12, 46, },
+	{ 0, 0, 0, 3, 13, 63, },
+	{ 2, 0, 0, 3, 13, 46, },
+	{ 1, 0, 0, 3, 13, 46, },
+	{ 0, 0, 0, 3, 14, 63, },
+	{ 2, 0, 0, 3, 14, 63, },
+	{ 1, 0, 0, 3, 14, 46, },
+	{ 0, 0, 0, 6, 1, 46, },
+	{ 2, 0, 0, 6, 1, 46, },
+	{ 1, 0, 0, 6, 1, 46, },
+	{ 0, 0, 0, 6, 2, 46, },
+	{ 2, 0, 0, 6, 2, 46, },
+	{ 1, 0, 0, 6, 2, 46, },
+	{ 0, 0, 0, 6, 3, 46, },
+	{ 2, 0, 0, 6, 3, 46, },
+	{ 1, 0, 0, 6, 3, 46, },
+	{ 0, 0, 0, 6, 4, 46, },
+	{ 2, 0, 0, 6, 4, 46, },
+	{ 1, 0, 0, 6, 4, 46, },
+	{ 0, 0, 0, 6, 5, 46, },
+	{ 2, 0, 0, 6, 5, 46, },
+	{ 1, 0, 0, 6, 5, 46, },
+	{ 0, 0, 0, 6, 6, 46, },
+	{ 2, 0, 0, 6, 6, 46, },
+	{ 1, 0, 0, 6, 6, 46, },
+	{ 0, 0, 0, 6, 7, 46, },
+	{ 2, 0, 0, 6, 7, 46, },
+	{ 1, 0, 0, 6, 7, 46, },
+	{ 0, 0, 0, 6, 8, 46, },
+	{ 2, 0, 0, 6, 8, 46, },
+	{ 1, 0, 0, 6, 8, 46, },
+	{ 0, 0, 0, 6, 9, 46, },
+	{ 2, 0, 0, 6, 9, 46, },
+	{ 1, 0, 0, 6, 9, 46, },
+	{ 0, 0, 0, 6, 10, 46, },
+	{ 2, 0, 0, 6, 10, 46, },
+	{ 1, 0, 0, 6, 10, 46, },
+	{ 0, 0, 0, 6, 11, 46, },
+	{ 2, 0, 0, 6, 11, 46, },
+	{ 1, 0, 0, 6, 11, 46, },
+	{ 0, 0, 0, 6, 12, 63, },
+	{ 2, 0, 0, 6, 12, 46, },
+	{ 1, 0, 0, 6, 12, 46, },
+	{ 0, 0, 0, 6, 13, 63, },
+	{ 2, 0, 0, 6, 13, 46, },
+	{ 1, 0, 0, 6, 13, 46, },
+	{ 0, 0, 0, 6, 14, 63, },
+	{ 2, 0, 0, 6, 14, 63, },
+	{ 1, 0, 0, 6, 14, 46, },
+	{ 0, 0, 0, 7, 1, 46, },
+	{ 2, 0, 0, 7, 1, 46, },
+	{ 1, 0, 0, 7, 1, 46, },
+	{ 0, 0, 0, 7, 2, 46, },
+	{ 2, 0, 0, 7, 2, 46, },
+	{ 1, 0, 0, 7, 2, 46, },
+	{ 0, 0, 0, 7, 3, 46, },
+	{ 2, 0, 0, 7, 3, 46, },
+	{ 1, 0, 0, 7, 3, 46, },
+	{ 0, 0, 0, 7, 4, 46, },
+	{ 2, 0, 0, 7, 4, 46, },
+	{ 1, 0, 0, 7, 4, 46, },
+	{ 0, 0, 0, 7, 5, 46, },
+	{ 2, 0, 0, 7, 5, 46, },
+	{ 1, 0, 0, 7, 5, 46, },
+	{ 0, 0, 0, 7, 6, 46, },
+	{ 2, 0, 0, 7, 6, 46, },
+	{ 1, 0, 0, 7, 6, 46, },
+	{ 0, 0, 0, 7, 7, 46, },
+	{ 2, 0, 0, 7, 7, 46, },
+	{ 1, 0, 0, 7, 7, 46, },
+	{ 0, 0, 0, 7, 8, 46, },
+	{ 2, 0, 0, 7, 8, 46, },
+	{ 1, 0, 0, 7, 8, 46, },
+	{ 0, 0, 0, 7, 9, 46, },
+	{ 2, 0, 0, 7, 9, 46, },
+	{ 1, 0, 0, 7, 9, 46, },
+	{ 0, 0, 0, 7, 10, 46, },
+	{ 2, 0, 0, 7, 10, 46, },
+	{ 1, 0, 0, 7, 10, 46, },
+	{ 0, 0, 0, 7, 11, 46, },
+	{ 2, 0, 0, 7, 11, 46, },
+	{ 1, 0, 0, 7, 11, 46, },
+	{ 0, 0, 0, 7, 12, 63, },
+	{ 2, 0, 0, 7, 12, 46, },
+	{ 1, 0, 0, 7, 12, 46, },
+	{ 0, 0, 0, 7, 13, 63, },
+	{ 2, 0, 0, 7, 13, 46, },
+	{ 1, 0, 0, 7, 13, 46, },
+	{ 0, 0, 0, 7, 14, 63, },
+	{ 2, 0, 0, 7, 14, 63, },
+	{ 1, 0, 0, 7, 14, 46, },
+	{ 0, 0, 1, 2, 1, 63, },
+	{ 2, 0, 1, 2, 1, 63, },
+	{ 1, 0, 1, 2, 1, 63, },
+	{ 0, 0, 1, 2, 2, 63, },
+	{ 2, 0, 1, 2, 2, 63, },
+	{ 1, 0, 1, 2, 2, 63, },
+	{ 0, 0, 1, 2, 3, 30, },
+	{ 2, 0, 1, 2, 3, 34, },
+	{ 1, 0, 1, 2, 3, 34, },
+	{ 0, 0, 1, 2, 4, 34, },
+	{ 2, 0, 1, 2, 4, 34, },
+	{ 1, 0, 1, 2, 4, 34, },
+	{ 0, 0, 1, 2, 5, 34, },
+	{ 2, 0, 1, 2, 5, 34, },
+	{ 1, 0, 1, 2, 5, 34, },
+	{ 0, 0, 1, 2, 6, 34, },
+	{ 2, 0, 1, 2, 6, 34, },
+	{ 1, 0, 1, 2, 6, 34, },
+	{ 0, 0, 1, 2, 7, 34, },
+	{ 2, 0, 1, 2, 7, 34, },
+	{ 1, 0, 1, 2, 7, 34, },
+	{ 0, 0, 1, 2, 8, 34, },
+	{ 2, 0, 1, 2, 8, 34, },
+	{ 1, 0, 1, 2, 8, 34, },
+	{ 0, 0, 1, 2, 9, 34, },
+	{ 2, 0, 1, 2, 9, 34, },
+	{ 1, 0, 1, 2, 9, 34, },
+	{ 0, 0, 1, 2, 10, 34, },
+	{ 2, 0, 1, 2, 10, 34, },
+	{ 1, 0, 1, 2, 10, 34, },
+	{ 0, 0, 1, 2, 11, 28, },
+	{ 2, 0, 1, 2, 11, 34, },
+	{ 1, 0, 1, 2, 11, 34, },
+	{ 0, 0, 1, 2, 12, 63, },
+	{ 2, 0, 1, 2, 12, 34, },
+	{ 1, 0, 1, 2, 12, 34, },
+	{ 0, 0, 1, 2, 13, 63, },
+	{ 2, 0, 1, 2, 13, 34, },
+	{ 1, 0, 1, 2, 13, 34, },
+	{ 0, 0, 1, 2, 14, 63, },
+	{ 2, 0, 1, 2, 14, 63, },
+	{ 1, 0, 1, 2, 14, 63, },
+	{ 0, 0, 1, 3, 1, 63, },
+	{ 2, 0, 1, 3, 1, 63, },
+	{ 1, 0, 1, 3, 1, 63, },
+	{ 0, 0, 1, 3, 2, 63, },
+	{ 2, 0, 1, 3, 2, 63, },
+	{ 1, 0, 1, 3, 2, 63, },
+	{ 0, 0, 1, 3, 3, 30, },
+	{ 2, 0, 1, 3, 3, 34, },
+	{ 1, 0, 1, 3, 3, 34, },
+	{ 0, 0, 1, 3, 4, 34, },
+	{ 2, 0, 1, 3, 4, 34, },
+	{ 1, 0, 1, 3, 4, 34, },
+	{ 0, 0, 1, 3, 5, 34, },
+	{ 2, 0, 1, 3, 5, 34, },
+	{ 1, 0, 1, 3, 5, 34, },
+	{ 0, 0, 1, 3, 6, 34, },
+	{ 2, 0, 1, 3, 6, 34, },
+	{ 1, 0, 1, 3, 6, 34, },
+	{ 0, 0, 1, 3, 7, 34, },
+	{ 2, 0, 1, 3, 7, 34, },
+	{ 1, 0, 1, 3, 7, 34, },
+	{ 0, 0, 1, 3, 8, 34, },
+	{ 2, 0, 1, 3, 8, 34, },
+	{ 1, 0, 1, 3, 8, 34, },
+	{ 0, 0, 1, 3, 9, 34, },
+	{ 2, 0, 1, 3, 9, 34, },
+	{ 1, 0, 1, 3, 9, 34, },
+	{ 0, 0, 1, 3, 10, 34, },
+	{ 2, 0, 1, 3, 10, 34, },
+	{ 1, 0, 1, 3, 10, 34, },
+	{ 0, 0, 1, 3, 11, 28, },
+	{ 2, 0, 1, 3, 11, 34, },
+	{ 1, 0, 1, 3, 11, 34, },
+	{ 0, 0, 1, 3, 12, 63, },
+	{ 2, 0, 1, 3, 12, 34, },
+	{ 1, 0, 1, 3, 12, 34, },
+	{ 0, 0, 1, 3, 13, 63, },
+	{ 2, 0, 1, 3, 13, 34, },
+	{ 1, 0, 1, 3, 13, 34, },
+	{ 0, 0, 1, 3, 14, 63, },
+	{ 2, 0, 1, 3, 14, 63, },
+	{ 1, 0, 1, 3, 14, 63, },
+	{ 0, 0, 1, 6, 1, 63, },
+	{ 2, 0, 1, 6, 1, 63, },
+	{ 1, 0, 1, 6, 1, 63, },
+	{ 0, 0, 1, 6, 2, 63, },
+	{ 2, 0, 1, 6, 2, 63, },
+	{ 1, 0, 1, 6, 2, 63, },
+	{ 0, 0, 1, 6, 3, 30, },
+	{ 2, 0, 1, 6, 3, 34, },
+	{ 1, 0, 1, 6, 3, 34, },
+	{ 0, 0, 1, 6, 4, 34, },
+	{ 2, 0, 1, 6, 4, 34, },
+	{ 1, 0, 1, 6, 4, 34, },
+	{ 0, 0, 1, 6, 5, 34, },
+	{ 2, 0, 1, 6, 5, 34, },
+	{ 1, 0, 1, 6, 5, 34, },
+	{ 0, 0, 1, 6, 6, 34, },
+	{ 2, 0, 1, 6, 6, 34, },
+	{ 1, 0, 1, 6, 6, 34, },
+	{ 0, 0, 1, 6, 7, 34, },
+	{ 2, 0, 1, 6, 7, 34, },
+	{ 1, 0, 1, 6, 7, 34, },
+	{ 0, 0, 1, 6, 8, 34, },
+	{ 2, 0, 1, 6, 8, 34, },
+	{ 1, 0, 1, 6, 8, 34, },
+	{ 0, 0, 1, 6, 9, 34, },
+	{ 2, 0, 1, 6, 9, 34, },
+	{ 1, 0, 1, 6, 9, 34, },
+	{ 0, 0, 1, 6, 10, 34, },
+	{ 2, 0, 1, 6, 10, 34, },
+	{ 1, 0, 1, 6, 10, 34, },
+	{ 0, 0, 1, 6, 11, 28, },
+	{ 2, 0, 1, 6, 11, 34, },
+	{ 1, 0, 1, 6, 11, 34, },
+	{ 0, 0, 1, 6, 12, 63, },
+	{ 2, 0, 1, 6, 12, 34, },
+	{ 1, 0, 1, 6, 12, 34, },
+	{ 0, 0, 1, 6, 13, 63, },
+	{ 2, 0, 1, 6, 13, 34, },
+	{ 1, 0, 1, 6, 13, 34, },
+	{ 0, 0, 1, 6, 14, 63, },
+	{ 2, 0, 1, 6, 14, 63, },
+	{ 1, 0, 1, 6, 14, 63, },
+	{ 0, 0, 1, 7, 1, 63, },
+	{ 2, 0, 1, 7, 1, 63, },
+	{ 1, 0, 1, 7, 1, 63, },
+	{ 0, 0, 1, 7, 2, 63, },
+	{ 2, 0, 1, 7, 2, 63, },
+	{ 1, 0, 1, 7, 2, 63, },
+	{ 0, 0, 1, 7, 3, 30, },
+	{ 2, 0, 1, 7, 3, 34, },
+	{ 1, 0, 1, 7, 3, 34, },
+	{ 0, 0, 1, 7, 4, 34, },
+	{ 2, 0, 1, 7, 4, 34, },
+	{ 1, 0, 1, 7, 4, 34, },
+	{ 0, 0, 1, 7, 5, 34, },
+	{ 2, 0, 1, 7, 5, 34, },
+	{ 1, 0, 1, 7, 5, 34, },
+	{ 0, 0, 1, 7, 6, 34, },
+	{ 2, 0, 1, 7, 6, 34, },
+	{ 1, 0, 1, 7, 6, 34, },
+	{ 0, 0, 1, 7, 7, 34, },
+	{ 2, 0, 1, 7, 7, 34, },
+	{ 1, 0, 1, 7, 7, 34, },
+	{ 0, 0, 1, 7, 8, 34, },
+	{ 2, 0, 1, 7, 8, 34, },
+	{ 1, 0, 1, 7, 8, 34, },
+	{ 0, 0, 1, 7, 9, 34, },
+	{ 2, 0, 1, 7, 9, 34, },
+	{ 1, 0, 1, 7, 9, 34, },
+	{ 0, 0, 1, 7, 10, 34, },
+	{ 2, 0, 1, 7, 10, 34, },
+	{ 1, 0, 1, 7, 10, 34, },
+	{ 0, 0, 1, 7, 11, 28, },
+	{ 2, 0, 1, 7, 11, 34, },
+	{ 1, 0, 1, 7, 11, 34, },
+	{ 0, 0, 1, 7, 12, 63, },
+	{ 2, 0, 1, 7, 12, 34, },
+	{ 1, 0, 1, 7, 12, 34, },
+	{ 0, 0, 1, 7, 13, 63, },
+	{ 2, 0, 1, 7, 13, 34, },
+	{ 1, 0, 1, 7, 13, 34, },
+	{ 0, 0, 1, 7, 14, 63, },
+	{ 2, 0, 1, 7, 14, 63, },
+	{ 1, 0, 1, 7, 14, 63, },
+	{ 0, 1, 0, 1, 36, 46, },
+	{ 2, 1, 0, 1, 36, 46, },
+	{ 1, 1, 0, 1, 36, 46, },
+	{ 0, 1, 0, 1, 40, 46, },
+	{ 2, 1, 0, 1, 40, 46, },
+	{ 1, 1, 0, 1, 40, 46, },
+	{ 0, 1, 0, 1, 44, 46, },
+	{ 2, 1, 0, 1, 44, 46, },
+	{ 1, 1, 0, 1, 44, 46, },
+	{ 0, 1, 0, 1, 48, 46, },
+	{ 2, 1, 0, 1, 48, 46, },
+	{ 1, 1, 0, 1, 48, 46, },
+	{ 0, 1, 0, 1, 52, 46, },
+	{ 2, 1, 0, 1, 52, 46, },
+	{ 1, 1, 0, 1, 52, 46, },
+	{ 0, 1, 0, 1, 56, 46, },
+	{ 2, 1, 0, 1, 56, 46, },
+	{ 1, 1, 0, 1, 56, 46, },
+	{ 0, 1, 0, 1, 60, 46, },
+	{ 2, 1, 0, 1, 60, 46, },
+	{ 1, 1, 0, 1, 60, 46, },
+	{ 0, 1, 0, 1, 64, 46, },
+	{ 2, 1, 0, 1, 64, 46, },
+	{ 1, 1, 0, 1, 64, 46, },
+	{ 0, 1, 0, 1, 100, 46, },
+	{ 2, 1, 0, 1, 100, 46, },
+	{ 1, 1, 0, 1, 100, 46, },
+	{ 0, 1, 0, 1, 104, 46, },
+	{ 2, 1, 0, 1, 104, 46, },
+	{ 1, 1, 0, 1, 104, 46, },
+	{ 0, 1, 0, 1, 108, 46, },
+	{ 2, 1, 0, 1, 108, 46, },
+	{ 1, 1, 0, 1, 108, 46, },
+	{ 0, 1, 0, 1, 112, 46, },
+	{ 2, 1, 0, 1, 112, 46, },
+	{ 1, 1, 0, 1, 112, 46, },
+	{ 0, 1, 0, 1, 116, 46, },
+	{ 2, 1, 0, 1, 116, 46, },
+	{ 1, 1, 0, 1, 116, 46, },
+	{ 0, 1, 0, 1, 120, 46, },
+	{ 2, 1, 0, 1, 120, 46, },
+	{ 1, 1, 0, 1, 120, 46, },
+	{ 0, 1, 0, 1, 124, 46, },
+	{ 2, 1, 0, 1, 124, 46, },
+	{ 1, 1, 0, 1, 124, 46, },
+	{ 0, 1, 0, 1, 128, 46, },
+	{ 2, 1, 0, 1, 128, 46, },
+	{ 1, 1, 0, 1, 128, 46, },
+	{ 0, 1, 0, 1, 132, 46, },
+	{ 2, 1, 0, 1, 132, 46, },
+	{ 1, 1, 0, 1, 132, 46, },
+	{ 0, 1, 0, 1, 136, 46, },
+	{ 2, 1, 0, 1, 136, 46, },
+	{ 1, 1, 0, 1, 136, 46, },
+	{ 0, 1, 0, 1, 140, 46, },
+	{ 2, 1, 0, 1, 140, 46, },
+	{ 1, 1, 0, 1, 140, 46, },
+	{ 0, 1, 0, 1, 149, 46, },
+	{ 2, 1, 0, 1, 149, 46, },
+	{ 1, 1, 0, 1, 149, 63, },
+	{ 0, 1, 0, 1, 153, 46, },
+	{ 2, 1, 0, 1, 153, 46, },
+	{ 1, 1, 0, 1, 153, 63, },
+	{ 0, 1, 0, 1, 157, 46, },
+	{ 2, 1, 0, 1, 157, 46, },
+	{ 1, 1, 0, 1, 157, 63, },
+	{ 0, 1, 0, 1, 161, 46, },
+	{ 2, 1, 0, 1, 161, 46, },
+	{ 1, 1, 0, 1, 161, 63, },
+	{ 0, 1, 0, 1, 165, 46, },
+	{ 2, 1, 0, 1, 165, 46, },
+	{ 1, 1, 0, 1, 165, 63, },
+	{ 0, 1, 0, 2, 36, 46, },
+	{ 2, 1, 0, 2, 36, 46, },
+	{ 1, 1, 0, 2, 36, 46, },
+	{ 0, 1, 0, 2, 40, 46, },
+	{ 2, 1, 0, 2, 40, 46, },
+	{ 1, 1, 0, 2, 40, 46, },
+	{ 0, 1, 0, 2, 44, 46, },
+	{ 2, 1, 0, 2, 44, 46, },
+	{ 1, 1, 0, 2, 44, 46, },
+	{ 0, 1, 0, 2, 48, 46, },
+	{ 2, 1, 0, 2, 48, 46, },
+	{ 1, 1, 0, 2, 48, 46, },
+	{ 0, 1, 0, 2, 52, 46, },
+	{ 2, 1, 0, 2, 52, 46, },
+	{ 1, 1, 0, 2, 52, 46, },
+	{ 0, 1, 0, 2, 56, 46, },
+	{ 2, 1, 0, 2, 56, 46, },
+	{ 1, 1, 0, 2, 56, 46, },
+	{ 0, 1, 0, 2, 60, 46, },
+	{ 2, 1, 0, 2, 60, 46, },
+	{ 1, 1, 0, 2, 60, 46, },
+	{ 0, 1, 0, 2, 64, 46, },
+	{ 2, 1, 0, 2, 64, 46, },
+	{ 1, 1, 0, 2, 64, 46, },
+	{ 0, 1, 0, 2, 100, 46, },
+	{ 2, 1, 0, 2, 100, 46, },
+	{ 1, 1, 0, 2, 100, 46, },
+	{ 0, 1, 0, 2, 104, 46, },
+	{ 2, 1, 0, 2, 104, 46, },
+	{ 1, 1, 0, 2, 104, 46, },
+	{ 0, 1, 0, 2, 108, 46, },
+	{ 2, 1, 0, 2, 108, 46, },
+	{ 1, 1, 0, 2, 108, 46, },
+	{ 0, 1, 0, 2, 112, 46, },
+	{ 2, 1, 0, 2, 112, 46, },
+	{ 1, 1, 0, 2, 112, 46, },
+	{ 0, 1, 0, 2, 116, 46, },
+	{ 2, 1, 0, 2, 116, 46, },
+	{ 1, 1, 0, 2, 116, 46, },
+	{ 0, 1, 0, 2, 120, 46, },
+	{ 2, 1, 0, 2, 120, 46, },
+	{ 1, 1, 0, 2, 120, 46, },
+	{ 0, 1, 0, 2, 124, 46, },
+	{ 2, 1, 0, 2, 124, 46, },
+	{ 1, 1, 0, 2, 124, 46, },
+	{ 0, 1, 0, 2, 128, 46, },
+	{ 2, 1, 0, 2, 128, 46, },
+	{ 1, 1, 0, 2, 128, 46, },
+	{ 0, 1, 0, 2, 132, 46, },
+	{ 2, 1, 0, 2, 132, 46, },
+	{ 1, 1, 0, 2, 132, 46, },
+	{ 0, 1, 0, 2, 136, 46, },
+	{ 2, 1, 0, 2, 136, 46, },
+	{ 1, 1, 0, 2, 136, 46, },
+	{ 0, 1, 0, 2, 140, 46, },
+	{ 2, 1, 0, 2, 140, 46, },
+	{ 1, 1, 0, 2, 140, 46, },
+	{ 0, 1, 0, 2, 149, 46, },
+	{ 2, 1, 0, 2, 149, 46, },
+	{ 1, 1, 0, 2, 149, 63, },
+	{ 0, 1, 0, 2, 153, 46, },
+	{ 2, 1, 0, 2, 153, 46, },
+	{ 1, 1, 0, 2, 153, 63, },
+	{ 0, 1, 0, 2, 157, 46, },
+	{ 2, 1, 0, 2, 157, 46, },
+	{ 1, 1, 0, 2, 157, 63, },
+	{ 0, 1, 0, 2, 161, 46, },
+	{ 2, 1, 0, 2, 161, 46, },
+	{ 1, 1, 0, 2, 161, 63, },
+	{ 0, 1, 0, 2, 165, 46, },
+	{ 2, 1, 0, 2, 165, 46, },
+	{ 1, 1, 0, 2, 165, 63, },
+	{ 0, 1, 0, 3, 36, 46, },
+	{ 2, 1, 0, 3, 36, 46, },
+	{ 1, 1, 0, 3, 36, 46, },
+	{ 0, 1, 0, 3, 40, 46, },
+	{ 2, 1, 0, 3, 40, 46, },
+	{ 1, 1, 0, 3, 40, 46, },
+	{ 0, 1, 0, 3, 44, 46, },
+	{ 2, 1, 0, 3, 44, 46, },
+	{ 1, 1, 0, 3, 44, 46, },
+	{ 0, 1, 0, 3, 48, 46, },
+	{ 2, 1, 0, 3, 48, 46, },
+	{ 1, 1, 0, 3, 48, 46, },
+	{ 0, 1, 0, 3, 52, 46, },
+	{ 2, 1, 0, 3, 52, 46, },
+	{ 1, 1, 0, 3, 52, 46, },
+	{ 0, 1, 0, 3, 56, 46, },
+	{ 2, 1, 0, 3, 56, 46, },
+	{ 1, 1, 0, 3, 56, 46, },
+	{ 0, 1, 0, 3, 60, 46, },
+	{ 2, 1, 0, 3, 60, 46, },
+	{ 1, 1, 0, 3, 60, 46, },
+	{ 0, 1, 0, 3, 64, 46, },
+	{ 2, 1, 0, 3, 64, 46, },
+	{ 1, 1, 0, 3, 64, 46, },
+	{ 0, 1, 0, 3, 100, 46, },
+	{ 2, 1, 0, 3, 100, 46, },
+	{ 1, 1, 0, 3, 100, 46, },
+	{ 0, 1, 0, 3, 104, 46, },
+	{ 2, 1, 0, 3, 104, 46, },
+	{ 1, 1, 0, 3, 104, 46, },
+	{ 0, 1, 0, 3, 108, 46, },
+	{ 2, 1, 0, 3, 108, 46, },
+	{ 1, 1, 0, 3, 108, 46, },
+	{ 0, 1, 0, 3, 112, 46, },
+	{ 2, 1, 0, 3, 112, 46, },
+	{ 1, 1, 0, 3, 112, 46, },
+	{ 0, 1, 0, 3, 116, 46, },
+	{ 2, 1, 0, 3, 116, 46, },
+	{ 1, 1, 0, 3, 116, 46, },
+	{ 0, 1, 0, 3, 120, 46, },
+	{ 2, 1, 0, 3, 120, 46, },
+	{ 1, 1, 0, 3, 120, 46, },
+	{ 0, 1, 0, 3, 124, 46, },
+	{ 2, 1, 0, 3, 124, 46, },
+	{ 1, 1, 0, 3, 124, 46, },
+	{ 0, 1, 0, 3, 128, 46, },
+	{ 2, 1, 0, 3, 128, 46, },
+	{ 1, 1, 0, 3, 128, 46, },
+	{ 0, 1, 0, 3, 132, 46, },
+	{ 2, 1, 0, 3, 132, 46, },
+	{ 1, 1, 0, 3, 132, 46, },
+	{ 0, 1, 0, 3, 136, 46, },
+	{ 2, 1, 0, 3, 136, 46, },
+	{ 1, 1, 0, 3, 136, 46, },
+	{ 0, 1, 0, 3, 140, 46, },
+	{ 2, 1, 0, 3, 140, 46, },
+	{ 1, 1, 0, 3, 140, 46, },
+	{ 0, 1, 0, 3, 149, 46, },
+	{ 2, 1, 0, 3, 149, 46, },
+	{ 1, 1, 0, 3, 149, 63, },
+	{ 0, 1, 0, 3, 153, 46, },
+	{ 2, 1, 0, 3, 153, 46, },
+	{ 1, 1, 0, 3, 153, 63, },
+	{ 0, 1, 0, 3, 157, 46, },
+	{ 2, 1, 0, 3, 157, 46, },
+	{ 1, 1, 0, 3, 157, 63, },
+	{ 0, 1, 0, 3, 161, 46, },
+	{ 2, 1, 0, 3, 161, 46, },
+	{ 1, 1, 0, 3, 161, 63, },
+	{ 0, 1, 0, 3, 165, 46, },
+	{ 2, 1, 0, 3, 165, 46, },
+	{ 1, 1, 0, 3, 165, 63, },
+	{ 0, 1, 0, 6, 36, 46, },
+	{ 2, 1, 0, 6, 36, 46, },
+	{ 1, 1, 0, 6, 36, 46, },
+	{ 0, 1, 0, 6, 40, 46, },
+	{ 2, 1, 0, 6, 40, 46, },
+	{ 1, 1, 0, 6, 40, 46, },
+	{ 0, 1, 0, 6, 44, 46, },
+	{ 2, 1, 0, 6, 44, 46, },
+	{ 1, 1, 0, 6, 44, 46, },
+	{ 0, 1, 0, 6, 48, 46, },
+	{ 2, 1, 0, 6, 48, 46, },
+	{ 1, 1, 0, 6, 48, 46, },
+	{ 0, 1, 0, 6, 52, 46, },
+	{ 2, 1, 0, 6, 52, 46, },
+	{ 1, 1, 0, 6, 52, 46, },
+	{ 0, 1, 0, 6, 56, 46, },
+	{ 2, 1, 0, 6, 56, 46, },
+	{ 1, 1, 0, 6, 56, 46, },
+	{ 0, 1, 0, 6, 60, 46, },
+	{ 2, 1, 0, 6, 60, 46, },
+	{ 1, 1, 0, 6, 60, 46, },
+	{ 0, 1, 0, 6, 64, 46, },
+	{ 2, 1, 0, 6, 64, 46, },
+	{ 1, 1, 0, 6, 64, 46, },
+	{ 0, 1, 0, 6, 100, 46, },
+	{ 2, 1, 0, 6, 100, 46, },
+	{ 1, 1, 0, 6, 100, 46, },
+	{ 0, 1, 0, 6, 104, 46, },
+	{ 2, 1, 0, 6, 104, 46, },
+	{ 1, 1, 0, 6, 104, 46, },
+	{ 0, 1, 0, 6, 108, 46, },
+	{ 2, 1, 0, 6, 108, 46, },
+	{ 1, 1, 0, 6, 108, 46, },
+	{ 0, 1, 0, 6, 112, 46, },
+	{ 2, 1, 0, 6, 112, 46, },
+	{ 1, 1, 0, 6, 112, 46, },
+	{ 0, 1, 0, 6, 116, 46, },
+	{ 2, 1, 0, 6, 116, 46, },
+	{ 1, 1, 0, 6, 116, 46, },
+	{ 0, 1, 0, 6, 120, 46, },
+	{ 2, 1, 0, 6, 120, 46, },
+	{ 1, 1, 0, 6, 120, 46, },
+	{ 0, 1, 0, 6, 124, 46, },
+	{ 2, 1, 0, 6, 124, 46, },
+	{ 1, 1, 0, 6, 124, 46, },
+	{ 0, 1, 0, 6, 128, 46, },
+	{ 2, 1, 0, 6, 128, 46, },
+	{ 1, 1, 0, 6, 128, 46, },
+	{ 0, 1, 0, 6, 132, 46, },
+	{ 2, 1, 0, 6, 132, 46, },
+	{ 1, 1, 0, 6, 132, 46, },
+	{ 0, 1, 0, 6, 136, 46, },
+	{ 2, 1, 0, 6, 136, 46, },
+	{ 1, 1, 0, 6, 136, 46, },
+	{ 0, 1, 0, 6, 140, 46, },
+	{ 2, 1, 0, 6, 140, 46, },
+	{ 1, 1, 0, 6, 140, 46, },
+	{ 0, 1, 0, 6, 149, 46, },
+	{ 2, 1, 0, 6, 149, 46, },
+	{ 1, 1, 0, 6, 149, 63, },
+	{ 0, 1, 0, 6, 153, 46, },
+	{ 2, 1, 0, 6, 153, 46, },
+	{ 1, 1, 0, 6, 153, 63, },
+	{ 0, 1, 0, 6, 157, 46, },
+	{ 2, 1, 0, 6, 157, 46, },
+	{ 1, 1, 0, 6, 157, 63, },
+	{ 0, 1, 0, 6, 161, 46, },
+	{ 2, 1, 0, 6, 161, 46, },
+	{ 1, 1, 0, 6, 161, 63, },
+	{ 0, 1, 0, 6, 165, 46, },
+	{ 2, 1, 0, 6, 165, 46, },
+	{ 1, 1, 0, 6, 165, 63, },
+	{ 0, 1, 0, 7, 36, 46, },
+	{ 2, 1, 0, 7, 36, 46, },
+	{ 1, 1, 0, 7, 36, 46, },
+	{ 0, 1, 0, 7, 40, 46, },
+	{ 2, 1, 0, 7, 40, 46, },
+	{ 1, 1, 0, 7, 40, 46, },
+	{ 0, 1, 0, 7, 44, 46, },
+	{ 2, 1, 0, 7, 44, 46, },
+	{ 1, 1, 0, 7, 44, 46, },
+	{ 0, 1, 0, 7, 48, 46, },
+	{ 2, 1, 0, 7, 48, 46, },
+	{ 1, 1, 0, 7, 48, 46, },
+	{ 0, 1, 0, 7, 52, 46, },
+	{ 2, 1, 0, 7, 52, 46, },
+	{ 1, 1, 0, 7, 52, 46, },
+	{ 0, 1, 0, 7, 56, 46, },
+	{ 2, 1, 0, 7, 56, 46, },
+	{ 1, 1, 0, 7, 56, 46, },
+	{ 0, 1, 0, 7, 60, 46, },
+	{ 2, 1, 0, 7, 60, 46, },
+	{ 1, 1, 0, 7, 60, 46, },
+	{ 0, 1, 0, 7, 64, 46, },
+	{ 2, 1, 0, 7, 64, 46, },
+	{ 1, 1, 0, 7, 64, 46, },
+	{ 0, 1, 0, 7, 100, 46, },
+	{ 2, 1, 0, 7, 100, 46, },
+	{ 1, 1, 0, 7, 100, 46, },
+	{ 0, 1, 0, 7, 104, 46, },
+	{ 2, 1, 0, 7, 104, 46, },
+	{ 1, 1, 0, 7, 104, 46, },
+	{ 0, 1, 0, 7, 108, 46, },
+	{ 2, 1, 0, 7, 108, 46, },
+	{ 1, 1, 0, 7, 108, 46, },
+	{ 0, 1, 0, 7, 112, 46, },
+	{ 2, 1, 0, 7, 112, 46, },
+	{ 1, 1, 0, 7, 112, 46, },
+	{ 0, 1, 0, 7, 116, 46, },
+	{ 2, 1, 0, 7, 116, 46, },
+	{ 1, 1, 0, 7, 116, 46, },
+	{ 0, 1, 0, 7, 120, 46, },
+	{ 2, 1, 0, 7, 120, 46, },
+	{ 1, 1, 0, 7, 120, 46, },
+	{ 0, 1, 0, 7, 124, 46, },
+	{ 2, 1, 0, 7, 124, 46, },
+	{ 1, 1, 0, 7, 124, 46, },
+	{ 0, 1, 0, 7, 128, 46, },
+	{ 2, 1, 0, 7, 128, 46, },
+	{ 1, 1, 0, 7, 128, 46, },
+	{ 0, 1, 0, 7, 132, 46, },
+	{ 2, 1, 0, 7, 132, 46, },
+	{ 1, 1, 0, 7, 132, 46, },
+	{ 0, 1, 0, 7, 136, 46, },
+	{ 2, 1, 0, 7, 136, 46, },
+	{ 1, 1, 0, 7, 136, 46, },
+	{ 0, 1, 0, 7, 140, 46, },
+	{ 2, 1, 0, 7, 140, 46, },
+	{ 1, 1, 0, 7, 140, 46, },
+	{ 0, 1, 0, 7, 149, 46, },
+	{ 2, 1, 0, 7, 149, 46, },
+	{ 1, 1, 0, 7, 149, 63, },
+	{ 0, 1, 0, 7, 153, 46, },
+	{ 2, 1, 0, 7, 153, 46, },
+	{ 1, 1, 0, 7, 153, 63, },
+	{ 0, 1, 0, 7, 157, 46, },
+	{ 2, 1, 0, 7, 157, 46, },
+	{ 1, 1, 0, 7, 157, 63, },
+	{ 0, 1, 0, 7, 161, 46, },
+	{ 2, 1, 0, 7, 161, 46, },
+	{ 1, 1, 0, 7, 161, 63, },
+	{ 0, 1, 0, 7, 165, 46, },
+	{ 2, 1, 0, 7, 165, 46, },
+	{ 1, 1, 0, 7, 165, 63, },
+	{ 0, 1, 1, 2, 38, 46, },
+	{ 2, 1, 1, 2, 38, 46, },
+	{ 1, 1, 1, 2, 38, 46, },
+	{ 0, 1, 1, 2, 46, 46, },
+	{ 2, 1, 1, 2, 46, 46, },
+	{ 1, 1, 1, 2, 46, 46, },
+	{ 0, 1, 1, 2, 54, 46, },
+	{ 2, 1, 1, 2, 54, 46, },
+	{ 1, 1, 1, 2, 54, 46, },
+	{ 0, 1, 1, 2, 62, 46, },
+	{ 2, 1, 1, 2, 62, 46, },
+	{ 1, 1, 1, 2, 62, 46, },
+	{ 0, 1, 1, 2, 102, 46, },
+	{ 2, 1, 1, 2, 102, 46, },
+	{ 1, 1, 1, 2, 102, 46, },
+	{ 0, 1, 1, 2, 110, 46, },
+	{ 2, 1, 1, 2, 110, 46, },
+	{ 1, 1, 1, 2, 110, 46, },
+	{ 0, 1, 1, 2, 118, 46, },
+	{ 2, 1, 1, 2, 118, 46, },
+	{ 1, 1, 1, 2, 118, 46, },
+	{ 0, 1, 1, 2, 126, 46, },
+	{ 2, 1, 1, 2, 126, 46, },
+	{ 1, 1, 1, 2, 126, 46, },
+	{ 0, 1, 1, 2, 134, 46, },
+	{ 2, 1, 1, 2, 134, 46, },
+	{ 1, 1, 1, 2, 134, 46, },
+	{ 0, 1, 1, 2, 151, 46, },
+	{ 2, 1, 1, 2, 151, 46, },
+	{ 1, 1, 1, 2, 151, 63, },
+	{ 0, 1, 1, 2, 159, 46, },
+	{ 2, 1, 1, 2, 159, 46, },
+	{ 1, 1, 1, 2, 159, 63, },
+	{ 0, 1, 1, 3, 38, 46, },
+	{ 2, 1, 1, 3, 38, 46, },
+	{ 1, 1, 1, 3, 38, 46, },
+	{ 0, 1, 1, 3, 46, 46, },
+	{ 2, 1, 1, 3, 46, 46, },
+	{ 1, 1, 1, 3, 46, 46, },
+	{ 0, 1, 1, 3, 54, 46, },
+	{ 2, 1, 1, 3, 54, 46, },
+	{ 1, 1, 1, 3, 54, 46, },
+	{ 0, 1, 1, 3, 62, 46, },
+	{ 2, 1, 1, 3, 62, 46, },
+	{ 1, 1, 1, 3, 62, 46, },
+	{ 0, 1, 1, 3, 102, 46, },
+	{ 2, 1, 1, 3, 102, 46, },
+	{ 1, 1, 1, 3, 102, 46, },
+	{ 0, 1, 1, 3, 110, 46, },
+	{ 2, 1, 1, 3, 110, 46, },
+	{ 1, 1, 1, 3, 110, 46, },
+	{ 0, 1, 1, 3, 118, 46, },
+	{ 2, 1, 1, 3, 118, 46, },
+	{ 1, 1, 1, 3, 118, 46, },
+	{ 0, 1, 1, 3, 126, 46, },
+	{ 2, 1, 1, 3, 126, 46, },
+	{ 1, 1, 1, 3, 126, 46, },
+	{ 0, 1, 1, 3, 134, 46, },
+	{ 2, 1, 1, 3, 134, 46, },
+	{ 1, 1, 1, 3, 134, 46, },
+	{ 0, 1, 1, 3, 151, 46, },
+	{ 2, 1, 1, 3, 151, 46, },
+	{ 1, 1, 1, 3, 151, 63, },
+	{ 0, 1, 1, 3, 159, 46, },
+	{ 2, 1, 1, 3, 159, 46, },
+	{ 1, 1, 1, 3, 159, 63, },
+	{ 0, 1, 1, 6, 38, 46, },
+	{ 2, 1, 1, 6, 38, 46, },
+	{ 1, 1, 1, 6, 38, 46, },
+	{ 0, 1, 1, 6, 46, 46, },
+	{ 2, 1, 1, 6, 46, 46, },
+	{ 1, 1, 1, 6, 46, 46, },
+	{ 0, 1, 1, 6, 54, 46, },
+	{ 2, 1, 1, 6, 54, 46, },
+	{ 1, 1, 1, 6, 54, 46, },
+	{ 0, 1, 1, 6, 62, 46, },
+	{ 2, 1, 1, 6, 62, 46, },
+	{ 1, 1, 1, 6, 62, 46, },
+	{ 0, 1, 1, 6, 102, 46, },
+	{ 2, 1, 1, 6, 102, 46, },
+	{ 1, 1, 1, 6, 102, 46, },
+	{ 0, 1, 1, 6, 110, 46, },
+	{ 2, 1, 1, 6, 110, 46, },
+	{ 1, 1, 1, 6, 110, 46, },
+	{ 0, 1, 1, 6, 118, 46, },
+	{ 2, 1, 1, 6, 118, 46, },
+	{ 1, 1, 1, 6, 118, 46, },
+	{ 0, 1, 1, 6, 126, 46, },
+	{ 2, 1, 1, 6, 126, 46, },
+	{ 1, 1, 1, 6, 126, 46, },
+	{ 0, 1, 1, 6, 134, 46, },
+	{ 2, 1, 1, 6, 134, 46, },
+	{ 1, 1, 1, 6, 134, 46, },
+	{ 0, 1, 1, 6, 151, 46, },
+	{ 2, 1, 1, 6, 151, 46, },
+	{ 1, 1, 1, 6, 151, 63, },
+	{ 0, 1, 1, 6, 159, 46, },
+	{ 2, 1, 1, 6, 159, 46, },
+	{ 1, 1, 1, 6, 159, 63, },
+	{ 0, 1, 1, 7, 38, 46, },
+	{ 2, 1, 1, 7, 38, 46, },
+	{ 1, 1, 1, 7, 38, 46, },
+	{ 0, 1, 1, 7, 46, 46, },
+	{ 2, 1, 1, 7, 46, 46, },
+	{ 1, 1, 1, 7, 46, 46, },
+	{ 0, 1, 1, 7, 54, 46, },
+	{ 2, 1, 1, 7, 54, 46, },
+	{ 1, 1, 1, 7, 54, 46, },
+	{ 0, 1, 1, 7, 62, 46, },
+	{ 2, 1, 1, 7, 62, 46, },
+	{ 1, 1, 1, 7, 62, 46, },
+	{ 0, 1, 1, 7, 102, 46, },
+	{ 2, 1, 1, 7, 102, 46, },
+	{ 1, 1, 1, 7, 102, 46, },
+	{ 0, 1, 1, 7, 110, 46, },
+	{ 2, 1, 1, 7, 110, 46, },
+	{ 1, 1, 1, 7, 110, 46, },
+	{ 0, 1, 1, 7, 118, 46, },
+	{ 2, 1, 1, 7, 118, 46, },
+	{ 1, 1, 1, 7, 118, 46, },
+	{ 0, 1, 1, 7, 126, 46, },
+	{ 2, 1, 1, 7, 126, 46, },
+	{ 1, 1, 1, 7, 126, 46, },
+	{ 0, 1, 1, 7, 134, 46, },
+	{ 2, 1, 1, 7, 134, 46, },
+	{ 1, 1, 1, 7, 134, 46, },
+	{ 0, 1, 1, 7, 151, 46, },
+	{ 2, 1, 1, 7, 151, 46, },
+	{ 1, 1, 1, 7, 151, 63, },
+	{ 0, 1, 1, 7, 159, 46, },
+	{ 2, 1, 1, 7, 159, 46, },
+	{ 1, 1, 1, 7, 159, 63, },
+	{ 0, 1, 2, 4, 42, 46, },
+	{ 2, 1, 2, 4, 42, 46, },
+	{ 1, 1, 2, 4, 42, 46, },
+	{ 0, 1, 2, 4, 58, 46, },
+	{ 2, 1, 2, 4, 58, 46, },
+	{ 1, 1, 2, 4, 58, 46, },
+	{ 0, 1, 2, 4, 106, 46, },
+	{ 2, 1, 2, 4, 106, 46, },
+	{ 1, 1, 2, 4, 106, 46, },
+	{ 0, 1, 2, 4, 122, 46, },
+	{ 2, 1, 2, 4, 122, 46, },
+	{ 1, 1, 2, 4, 122, 46, },
+	{ 0, 1, 2, 4, 155, 46, },
+	{ 2, 1, 2, 4, 155, 46, },
+	{ 1, 1, 2, 4, 155, 63, },
+	{ 0, 1, 2, 5, 42, 46, },
+	{ 2, 1, 2, 5, 42, 46, },
+	{ 1, 1, 2, 5, 42, 46, },
+	{ 0, 1, 2, 5, 58, 46, },
+	{ 2, 1, 2, 5, 58, 46, },
+	{ 1, 1, 2, 5, 58, 46, },
+	{ 0, 1, 2, 5, 106, 46, },
+	{ 2, 1, 2, 5, 106, 46, },
+	{ 1, 1, 2, 5, 106, 46, },
+	{ 0, 1, 2, 5, 122, 46, },
+	{ 2, 1, 2, 5, 122, 46, },
+	{ 1, 1, 2, 5, 122, 46, },
+	{ 0, 1, 2, 5, 155, 46, },
+	{ 2, 1, 2, 5, 155, 46, },
+	{ 1, 1, 2, 5, 155, 63, },
+	{ 0, 1, 2, 8, 42, 46, },
+	{ 2, 1, 2, 8, 42, 46, },
+	{ 1, 1, 2, 8, 42, 46, },
+	{ 0, 1, 2, 8, 58, 46, },
+	{ 2, 1, 2, 8, 58, 46, },
+	{ 1, 1, 2, 8, 58, 46, },
+	{ 0, 1, 2, 8, 106, 46, },
+	{ 2, 1, 2, 8, 106, 46, },
+	{ 1, 1, 2, 8, 106, 46, },
+	{ 0, 1, 2, 8, 122, 46, },
+	{ 2, 1, 2, 8, 122, 46, },
+	{ 1, 1, 2, 8, 122, 46, },
+	{ 0, 1, 2, 8, 155, 46, },
+	{ 2, 1, 2, 8, 155, 46, },
+	{ 1, 1, 2, 8, 155, 63, },
+	{ 0, 1, 2, 9, 42, 46, },
+	{ 2, 1, 2, 9, 42, 46, },
+	{ 1, 1, 2, 9, 42, 46, },
+	{ 0, 1, 2, 9, 58, 46, },
+	{ 2, 1, 2, 9, 58, 46, },
+	{ 1, 1, 2, 9, 58, 46, },
+	{ 0, 1, 2, 9, 106, 46, },
+	{ 2, 1, 2, 9, 106, 46, },
+	{ 1, 1, 2, 9, 106, 46, },
+	{ 0, 1, 2, 9, 122, 46, },
+	{ 2, 1, 2, 9, 122, 46, },
+	{ 1, 1, 2, 9, 122, 46, },
+	{ 0, 1, 2, 9, 155, 46, },
+	{ 2, 1, 2, 9, 155, 46, },
+	{ 1, 1, 2, 9, 155, 63, },
+};
+
+RTW_DECL_TABLE_TXPWR_LMT(rtw8814a_txpwr_lmt_type8);
+
+static const u8
+rtw8814a_pwrtrk_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 9, 9, 10, 11,
+	 11, 12, 13, 13, 14, 15, 15, 16, 17, 17, 18, 19, 19},
+	{0, 1, 1, 2, 2, 3, 4, 4, 5, 6, 6, 7, 7, 8, 9, 9, 10, 10,
+	 11, 12, 12, 13, 13, 14, 15, 15, 16, 17, 17, 18},
+	{0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 12, 12, 13, 14, 14, 15, 16, 16, 17, 17, 18, 19},
+};
+
+static const u8
+rtw8814a_pwrtrk_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 25, 25, 25},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 25, 25},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 25, 25},
+};
+
+static const u8
+rtw8814a_pwrtrk_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 2, 2, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 9, 10, 10,
+	 11, 12, 13, 14, 15, 15, 15, 15, 16, 16, 17, 18},
+	{0, 1, 1, 2, 3, 3, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10, 11,
+	 12, 12, 13, 14, 15, 15, 16, 17, 17, 18, 19, 19, 20},
+	{0, 1, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 10, 11, 11,
+	 12, 13, 13, 14, 14, 15, 16, 17, 18, 18, 19, 20, 20},
+};
+
+static const u8
+rtw8814a_pwrtrk_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+	 16, 16, 17, 18, 19, 20, 21, 21, 22, 23, 24, 25, 25},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 17, 18, 19, 20, 21, 22, 23, 24, 24, 25, 25, 25},
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+	 16, 16, 17, 18, 19, 20, 21, 22, 23, 23, 24, 25, 25},
+};
+
+static const u8
+rtw8814a_pwrtrk_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 2, 2, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 13, 13, 14, 14, 15, 15, 16, 17, 17},
+	{0, 1, 1, 2, 3, 3, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10, 11,
+	 12, 12, 13, 14, 15, 15, 16, 17, 17, 18, 19, 19, 20},
+	{0, 1, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 10, 11, 11,
+	 12, 13, 13, 14, 14, 15, 16, 17, 18, 18, 19, 20, 20},
+};
+
+static const u8
+rtw8814a_pwrtrk_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 3, 4, 5, 6, 7, 8, 8, 9, 10, 11, 12, 13, 14,
+	 15, 15, 16, 17, 18, 18, 19, 20, 21, 22, 23, 23, 24},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 18, 18, 19, 20, 21, 22, 23, 24, 25, 25, 25, 25},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
+	 16, 16, 17, 18, 19, 20, 20, 21, 22, 23, 24, 25, 25},
+};
+
+static const u8
+rtw8814a_pwrtrk_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8,
+	 8, 9, 9, 10, 11, 11, 11, 11, 12, 12, 13, 13, 14},
+	{0, 1, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 9, 9, 10, 11, 11,
+	 12, 13, 14, 14, 15, 16, 16, 17, 18, 19, 19, 20, 21},
+	{0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 12, 12, 13, 14, 14, 15, 16, 16, 17, 17, 18, 19},
+};
+
+static const u8
+rtw8814a_pwrtrk_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 2, 3, 4, 5, 6, 7, 7, 8, 9, 10, 11, 12, 12, 13,
+	 14, 15, 16, 16, 17, 18, 19, 20, 21, 21, 22, 23, 24},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 18, 19, 20, 21, 22, 23, 23, 24, 25, 25, 25, 25},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 17, 18, 19, 20, 21, 22, 23, 24, 25, 25, 25, 25},
+};
+
+static const u8 rtw8814a_pwrtrk_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 3, 4, 4, 5, 5, 6, 6, 6, 7,
+	 7, 8, 8, 9, 9, 9, 10, 10, 11, 11, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 9, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7,
+	 7, 7, 8, 8, 9, 9, 10, 10, 10, 11, 11, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 12, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7,
+	 7, 8, 8, 8, 9, 9, 10, 10, 11, 11, 11, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 9, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 7, 8, 8, 9, 9, 10, 10, 11, 11, 11, 12, 12, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8,
+	 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7,
+	 7, 8, 8, 8, 9, 9, 10, 10, 10, 11, 11, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 9, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 6,
+	 7, 7, 8, 8, 8, 9, 9, 10, 10, 10, 11, 11, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 4, 5, 5, 6, 6, 7, 7,
+	 7, 8, 8, 9, 9, 10, 10, 11, 11, 11, 12, 12, 13
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 5, 5, 5, 6,
+	 6, 6, 7, 7, 8, 8, 8, 9, 9, 10, 10, 10, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 3, 4, 4, 5, 5, 6, 6, 6, 7,
+	 7, 8, 8, 9, 9, 9, 10, 10, 11, 11, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 3, 4, 4, 5, 5, 5, 6, 6, 7,
+	 7, 8, 8, 8, 9, 9, 10, 10, 11, 11, 11, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 7,
+	 8, 8, 9, 9, 10, 10, 11, 11, 12, 12, 13, 13, 14
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_2g_cck_a_p,
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type0_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type0_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type0_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type0_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type0_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type0_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_type0_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_type0_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_type0_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_type0_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_type0_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_type0_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_type0_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_type0_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_type0_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_type0_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_type0_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_type0_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_type0_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_type0_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_type0_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_type0_2g_cck_a_p,
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 6, 7, 7, 8, 9, 10, 10, 11, 11, 12, 12,
+	 12, 13, 14, 15, 15, 16, 16, 16, 16, 16, 16, 16, 16},
+	{0, 1, 2, 3, 4, 5, 5, 6, 6, 7, 8, 9, 9, 10, 10, 10, 10,
+	 11, 11, 12, 12, 13, 14, 15, 16, 16, 16, 16, 16, 16},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 9, 10, 10, 11, 11, 11, 12,
+	 12, 13, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 3, 4, 5, 6, 7, 8, 8, 9, 10, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 21, 22, 22, 22, 22, 22, 22},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 9, 10, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 21, 22, 22, 22, 22, 22, 22},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16,
+	 17, 18, 19, 20, 21, 22, 23, 23, 23, 23, 23, 23, 23},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 3, 4, 5, 6, 7, 7, 8, 9, 10, 10, 11, 11, 12,
+	 12, 13, 14, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 9, 10, 10, 11, 11, 12,
+	 13, 13, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 9, 10, 11, 11,
+	 12, 12, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 6, 6, 7, 8, 9, 10, 11, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 21, 21, 21, 21, 21, 21, 21},
+	{0, 1, 2, 3, 4, 5, 6, 6, 7, 8, 8, 9, 10, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 20, 20, 21, 21, 21, 21, 21},
+	{0, 1, 2, 3, 3, 4, 5, 6, 7, 7, 8, 9, 10, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 21, 21, 21, 21, 21, 21, 21},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 2, 3, 4, 5, 6, 7, 8, 9, 10, 10, 10, 11, 12, 13,
+	 13, 13, 14, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 9, 10, 10, 11, 11, 12,
+	 13, 13, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 9, 10, 11, 11,
+	 12, 12, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 11, 12, 13, 14, 15,
+	 16, 17, 18, 19, 20, 21, 21, 21, 21, 21, 21, 21, 21},
+	{0, 0, 1, 2, 3, 4, 5, 6, 6, 7, 8, 9, 10, 10, 11, 12, 13,
+	 14, 15, 16, 17, 18, 19, 20, 20, 20, 20, 20, 20, 20},
+	{0, 1, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 11, 12, 13, 14,
+	 15, 16, 17, 18, 19, 20, 21, 21, 21, 21, 21, 21, 21},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 7, 8, 9, 10, 10, 11, 11, 11,
+	 12, 13, 13, 13, 13, 14, 15, 15, 15, 15, 15, 15, 15},
+	{0, 1, 2, 3, 3, 4, 5, 6, 7, 8, 8, 9, 10, 10, 11, 12, 12,
+	 12, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 9, 10, 11, 11, 11, 12,
+	 12, 12, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+};
+
+static const u8
+rtw8814a_pwrtrk_type2_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 10, 10, 11, 12, 13, 14,
+	 15, 15, 16, 17, 18, 18, 19, 19, 20, 20, 20, 20, 20},
+	{0, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 10, 11, 12, 13, 14,
+	 15, 16, 16, 17, 18, 19, 20, 20, 20, 20, 20, 20, 20},
+	{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 11, 12, 13, 14, 15,
+	 15, 16, 17, 18, 19, 19, 20, 20, 20, 20, 20, 20, 20},
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5,
+	 6, 6, 7, 8, 9, 10, 11, 11, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 6, 7, 7, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 5, 6, 6, 6, 7, 7, 8, 8, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 4, 4, 4, 5, 5, 6, 7, 8, 8, 9, 10, 10,
+	 11, 12, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 5, 5, 6, 6, 7, 7, 8, 8, 8,
+	 9, 9, 10, 10, 11, 11, 12, 12, 12, 13, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 2, 2, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 9, 9, 9,
+	 10, 11, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7, 7, 8, 8, 9, 10,
+	 11, 12, 12, 13, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 7, 8,
+	 9, 9, 9, 9, 9, 9, 10, 10, 11, 11, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 1, 2, 3, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 10, 11, 12, 12, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 2, 2, 3, 4, 5, 5, 6, 6, 6, 6, 7, 8, 9, 9, 10,
+	 10, 11, 11, 11, 12, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 2, 3, 3, 4, 5, 6, 6, 7, 7, 8, 8, 9, 10,
+	 10, 10, 11, 11, 12, 12, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 1, 2, 3, 3, 4, 4, 5, 5, 6, 7, 8, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 4, 4, 5, 5, 6, 6, 7, 8, 9, 9, 9, 9,
+	 10, 10, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type2_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 0, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 8, 9, 9, 10, 10,
+	 11, 11, 12, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type2_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type2_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type2_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type2_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_type2_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_type2_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_type2_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_type2_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_type2_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_type2_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_type2_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_type2_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_type2_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_type2_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_type2_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_type2_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_type2_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_type2_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_type2_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_type2_2g_cck_a_p,
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 3, 3, 3, 4, 6, 6, 7, 7, 8, 9, 10, 11, 12, 13, 13, 14,
+	 14, 14, 14, 14, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 4, 5, 6, 7, 7, 8, 7, 8, 10, 11, 12, 12, 13, 13, 14, 14,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 5, 5, 6, 7, 8, 9, 9, 10, 11, 12, 13, 13, 14, 15, 15, 16,
+	 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16, 16},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 0, 1, 2, 2, 3, 4, 5, 5, 6, 7, 9, 10, 10, 11, 12,
+	 12, 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 0, 0, 1, 1, 1, 2, 3, 4, 5, 6, 7, 8, 8, 9, 11, 12,
+	 12, 13, 13, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 0, 1, 1, 2, 2, 3, 5, 7, 8, 9, 10, 11, 12, 13, 13,
+	 13, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 2, 3, 3, 4, 6, 7, 7, 8, 9, 9, 9, 10, 10, 10,
+	 10, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12},
+	{0, 1, 2, 3, 3, 7, 7, 8, 8, 9, 11, 12, 12, 13, 14, 14, 15,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 0, 1, 2, 3, 4, 5, 7, 8, 8, 10, 11, 12, 12, 13, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 0, 1, 1, 2, 2, 3, 4, 5, 6, 6, 7, 8, 9, 11, 11,
+	 11, 11, 11, 11, 12, 12, 12, 12, 12, 13, 13, 13, 13},
+	{0, 0, 1, 2, 3, 3, 5, 5, 6, 8, 8, 9, 10, 11, 13, 13, 13,
+	 13, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 4, 4, 5, 7, 8, 9, 9, 10, 11, 12, 12, 12,
+	 12, 13, 13, 13, 13, 13, 13, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 2, 2, 2, 3, 4, 5, 6, 7, 9, 10, 10, 10, 10, 10,
+	 10, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12},
+	{0, 1, 2, 3, 3, 7, 7, 8, 8, 9, 11, 12, 12, 13, 14, 14, 15,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 0, 1, 2, 3, 4, 5, 7, 8, 8, 10, 11, 12, 12, 13, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 1, 2, 2, 4, 5, 6, 6, 7, 8, 9, 10, 11, 11, 11,
+	 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 0, 2, 3, 4, 5, 6, 8, 8, 9, 9, 11, 12, 13, 13, 13,
+	 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 0, 1, 2, 3, 3, 4, 6, 7, 8, 9, 10, 11, 12, 12, 12,
+	 12, 13, 13, 13, 13, 13, 13, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 0, 1, 2, 3, 3, 3, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 10, 11, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12},
+	{0, 2, 3, 4, 5, 7, 7, 8, 9, 10, 12, 13, 14, 15, 16, 17, 17,
+	 17, 17, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18, 18},
+	{0, 1, 2, 3, 3, 4, 6, 7, 8, 8, 10, 11, 11, 12, 13, 13, 13,
+	 13, 13, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type5_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 1, 3, 3, 3, 5, 5, 6, 6, 8, 8, 9, 10, 11, 11, 11,
+	 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 8, 8, 9, 11, 12, 13, 14, 15,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 0, 1, 3, 3, 4, 5, 5, 6, 7, 7, 8, 10, 10, 11, 11, 11,
+	 11, 12, 12, 12, 12, 12, 13, 13, 13, 13, 13, 13, 13},
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 4, 5, 6, 6, 7, 7, 7, 8, 9, 9, 9,
+	 9, 9, 10, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 2, 3, 4, 4, 5, 6, 6, 7, 7, 8, 8,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 10, 10, 10, 10, 10
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10, 10,
+	 10, 10, 10, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 8, 8, 9, 9, 9,
+	 9, 9, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 4, 5, 6, 6, 7, 7, 8, 9, 10, 10, 10,
+	 10, 10, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 8, 9, 9, 9, 9,
+	 9, 9, 10, 10, 10, 10, 10, 11, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 5, 5, 6, 7, 7, 8, 8, 9, 10, 10, 10,
+	 10, 11, 11, 11, 11, 111, 12, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 7, 8, 8, 9, 9, 9,
+	 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 5, 5, 6, 7, 7, 8, 8, 8, 9, 9, 9, 9,
+	 10, 10, 10, 10, 10, 11, 11, 10, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 8,
+	 9, 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 8, 8, 9, 10, 10, 10,
+	 10, 11, 11, 11, 11, 11, 11, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 8,
+	 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 2, 3, 4, 4, 5, 6, 6, 6, 7, 7, 8, 8, 9, 10, 10, 10,
+	 10, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 7, 7, 8, 8, 8,
+	 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 5, 5, 6, 7, 7, 8, 8, 9, 9, 9, 9, 10,
+	 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10
+};
+
+static const u8 rtw8814a_pwrtrk_type5_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 1, 1, 2, 2, 2, 3, 4, 4, 5, 6, 7, 8, 8, 9, 9, 9,
+	 9, 9, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type5_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type5_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type5_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type5_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_type5_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_type5_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_type5_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_type5_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_type5_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_type5_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_type5_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_type5_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_type5_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_type5_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_type5_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_type5_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_type5_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_type5_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_type5_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_type5_2g_cck_a_p,
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+	{0, 0, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 8,
+	 8, 9, 9, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10},
+};
+
+static const u8
+rtw8814a_pwrtrk_type7_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 0, 1, 1, 2, 3, 3, 4, 5, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 11, 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 5, 6, 7, 7,
+	 7, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+static const u8 rtw8814a_pwrtrk_type7_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5, 6, 6, 7, 7,
+	 8, 8, 8, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9, 9
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type7_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type7_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type7_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type7_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_type7_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_type7_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_type7_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_type7_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_type7_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_type7_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_type7_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_type7_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_type7_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_type7_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_type7_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_type7_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_type7_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_type7_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_type7_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_type7_2g_cck_a_p,
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gd_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 4, 6, 7, 7, 8, 8, 9, 10, 10, 11, 11, 12,
+	 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 4, 6, 7, 7, 8, 9, 9, 10, 10, 11, 11, 12,
+	 12, 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 4, 5, 6, 6, 7, 7, 8, 8, 8, 9, 10, 10,
+	 10, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gd_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 4, 4, 5, 6, 7, 8, 9, 10, 11, 12, 14, 14,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 0, 1, 2, 3, 5, 5, 6, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 4, 5, 6, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gc_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 4, 4, 5, 6, 7, 7, 8, 8, 9, 9, 10, 11, 11, 12,
+	 12, 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 5, 6, 7, 7, 8, 9, 9, 10, 10, 10, 11, 11,
+	 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 8, 9, 10, 10, 11, 11,
+	 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gc_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 4, 4, 5, 6, 7, 7, 8, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 3, 4, 4, 5, 6, 7, 7, 8, 10, 11, 12, 13, 14,
+	 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15, 15},
+	{0, 0, 1, 2, 4, 5, 5, 6, 6, 7, 7, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gb_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 8, 9, 9, 10, 11, 11,
+	 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 1, 2, 3, 4, 5, 6, 7, 7, 8, 9, 9, 10, 10, 10, 11, 11,
+	 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 8, 9, 10, 10, 11, 11,
+	 11, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5gb_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 3, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 10, 11, 11, 13, 13,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 4, 4, 5, 6, 7, 8, 10, 10, 11, 13, 13,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5ga_n[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 1, 2, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 9, 10, 11, 11,
+	 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12, 12},
+	{0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 9, 10, 10, 10, 11, 11,
+	 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+	{0, 1, 2, 3, 4, 4, 5, 6, 7, 7, 8, 9, 10, 10, 10, 11, 12,
+	 12, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13, 13},
+};
+
+static const u8
+rtw8814a_pwrtrk_type8_5ga_p[RTW_PWR_TRK_5G_NUM][RTW_PWR_TRK_TBL_SZ] = {
+	{0, 0, 1, 2, 3, 3, 4, 5, 6, 7, 7, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 4, 5, 5, 6, 7, 8, 9, 10, 11, 12, 13, 13,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+	{0, 0, 1, 2, 3, 3, 4, 4, 6, 7, 7, 9, 10, 11, 12, 13, 14,
+	 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14, 14},
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gd_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 1, 2, 2, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5,
+	 6, 6, 7, 8, 9, 10, 11, 11, 11, 11, 11, 11, 11
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gd_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 6, 7, 7, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gc_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 5, 6, 6, 6, 7, 7, 8, 8, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gc_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 4, 4, 4, 5, 5, 6, 7, 8, 8, 9, 10, 10,
+	 11, 12, 13, 13, 14, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gb_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 5, 5, 6, 6, 7, 7, 8, 8, 8,
+	 9, 9, 10, 10, 11, 11, 12, 12, 12, 13, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2gb_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2ga_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 2, 2, 3, 4, 4, 5, 5, 6, 6, 7, 7, 8, 9, 9, 9,
+	 10, 11, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2ga_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 4, 4, 4, 5, 6, 6, 7, 7, 8, 8, 9, 10,
+	 11, 12, 12, 13, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_d_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 3, 3, 3, 4, 4, 4, 5, 5, 5, 6, 6, 7, 8,
+	 9, 9, 9, 9, 9, 9, 10, 10, 11, 11, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_d_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 1, 2, 3, 3, 4, 4, 5, 6, 6, 7, 8, 8, 9, 10, 10,
+	 10, 11, 12, 12, 13, 14, 14, 14, 14, 14, 14, 14
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_c_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 2, 2, 3, 4, 5, 5, 6, 6, 6, 6, 7, 8, 9, 9, 10,
+	 10, 11, 11, 11, 12, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_c_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 0, 1, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 7, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_b_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 2, 2, 2, 3, 3, 4, 5, 6, 6, 7, 7, 8, 8, 9, 10,
+	 10, 10, 11, 11, 12, 12, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_b_p[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 1, 1, 2, 3, 3, 4, 4, 5, 5, 6, 7, 8, 8, 9, 9, 10,
+	 10, 11, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_a_n[RTW_PWR_TRK_TBL_SZ] = {
+	0, 1, 2, 2, 3, 4, 4, 4, 5, 5, 6, 6, 7, 8, 9, 9, 9, 9,
+	 10, 10, 11, 11, 11, 12, 12, 12, 12, 12, 12, 12
+};
+
+static const u8 rtw8814a_pwrtrk_type8_2g_cck_a_p[RTW_PWR_TRK_TBL_SZ] = {
+	 0, 0, 1, 2, 2, 3, 3, 4, 5, 5, 6, 7, 8, 9, 9, 10, 10,
+	 11, 11, 12, 12, 12, 13, 13, 13, 13, 13, 13, 13, 13
+};
+
+const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type8_tbl = {
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gd_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gd_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gd_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gd_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gd_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gd_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gd_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gc_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gc_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gc_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gc_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gc_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gc_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gc_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gb_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gb_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gb_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5gb_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5gb_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5gb_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5gb_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5ga_n[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5ga_n[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_n[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5ga_n[RTW_PWR_TRK_5G_3],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_1] = rtw8814a_pwrtrk_type8_5ga_p[RTW_PWR_TRK_5G_1],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_2] = rtw8814a_pwrtrk_type8_5ga_p[RTW_PWR_TRK_5G_2],
+	.pwrtrk_5ga_p[RTW_PWR_TRK_5G_3] = rtw8814a_pwrtrk_type8_5ga_p[RTW_PWR_TRK_5G_3],
+	.pwrtrk_2gd_n = rtw8814a_pwrtrk_type8_2gd_n,
+	.pwrtrk_2gd_p = rtw8814a_pwrtrk_type8_2gd_p,
+	.pwrtrk_2gc_n = rtw8814a_pwrtrk_type8_2gc_n,
+	.pwrtrk_2gc_p = rtw8814a_pwrtrk_type8_2gc_p,
+	.pwrtrk_2gb_n = rtw8814a_pwrtrk_type8_2gb_n,
+	.pwrtrk_2gb_p = rtw8814a_pwrtrk_type8_2gb_p,
+	.pwrtrk_2ga_n = rtw8814a_pwrtrk_type8_2ga_n,
+	.pwrtrk_2ga_p = rtw8814a_pwrtrk_type8_2ga_p,
+	.pwrtrk_2g_cckd_n = rtw8814a_pwrtrk_type8_2g_cck_d_n,
+	.pwrtrk_2g_cckd_p = rtw8814a_pwrtrk_type8_2g_cck_d_p,
+	.pwrtrk_2g_cckc_n = rtw8814a_pwrtrk_type8_2g_cck_c_n,
+	.pwrtrk_2g_cckc_p = rtw8814a_pwrtrk_type8_2g_cck_c_p,
+	.pwrtrk_2g_cckb_n = rtw8814a_pwrtrk_type8_2g_cck_b_n,
+	.pwrtrk_2g_cckb_p = rtw8814a_pwrtrk_type8_2g_cck_b_p,
+	.pwrtrk_2g_ccka_n = rtw8814a_pwrtrk_type8_2g_cck_a_n,
+	.pwrtrk_2g_ccka_p = rtw8814a_pwrtrk_type8_2g_cck_a_p,
+};
+
+static const struct rtw_pwr_seq_cmd init_power_on_8814a[] = {
+	{0x10c2,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), BIT(1)},
+	{0xFFFF,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 0,
+	 RTW_PWR_CMD_END, 0, 0},
+};
+
+static const struct rtw_pwr_seq_cmd trans_carddis_to_cardemu_8814a[] = {
+	{0x0012,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(6), BIT(6)},
+	{0x0015,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(5), 0},
+	{0x0015,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(6), 0},
+	{0x0023,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(4), 0},
+	{0x0046,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x00},
+	{0x0062,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x00},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_PCI_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(2), 0},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(3), 0},
+	{0x0301,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_PCI_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0},
+	{0x0071,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_PCI_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(2), 0},
+	{0xFFFF,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 0,
+	 RTW_PWR_CMD_END, 0, 0},
+};
+
+static const struct rtw_pwr_seq_cmd trans_cardemu_to_act_8814a[] = {
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(2), 0},
+	{0x0006,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_POLLING, BIT(1), BIT(1)},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(3), 0},
+	{0x00F0,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(7), 0},
+	{0x0081,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0x30, 0x20},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(0), BIT(0)},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_POLLING, BIT(0), 0},
+	{0xFFFF,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 0,
+	 RTW_PWR_CMD_END, 0, 0},
+};
+
+static const struct rtw_pwr_seq_cmd trans_act_to_cardemu_8814a[] = {
+	{0x0c00,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x04},
+	{0x0e00,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x04},
+	{0x1002,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(0), 0},
+	{0x0002,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_DELAY, 1, RTW_PWR_DELAY_US},
+	{0x1002,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_PCI_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x001F,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0},
+	{0x0007,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x28},
+	{0x0008,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0x02, 0},
+	{0x0066,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(7), 0},
+	{0x0041,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(4), 0},
+	{0x0042,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x004e,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(5), BIT(5)},
+	{0x0041,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_USB_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(0), 0},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), BIT(1)},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_POLLING, BIT(1), 0},
+	{0xFFFF,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 0,
+	 RTW_PWR_CMD_END, 0, 0},
+};
+
+static const struct rtw_pwr_seq_cmd trans_cardemu_to_carddis_8814a[] = {
+	{0x0003,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(2), 0},
+	{0x0080,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x01},
+	{0x0081,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x30},
+	{0x0045,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x00},
+	{0x0046,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0xff},
+	{0x0047,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0},
+	{0x0015,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(6), BIT(6)},
+	{0x0015,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(5), BIT(5)},
+	{0x0012,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(6), 0},
+	{0x0023,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(4), BIT(4)},
+	{0x0008,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x0007,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xFF, 0x20},
+	{0x001f,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x0020,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x0021,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x0076,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(1), 0},
+	{0x0091,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, 0xA0, 0xA0},
+	{0x0070,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(3), BIT(3)},
+	{0x0005,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 RTW_PWR_ADDR_MAC,
+	 RTW_PWR_CMD_WRITE, BIT(3), BIT(3)},
+	{0xFFFF,
+	 RTW_PWR_CUT_ALL_MSK,
+	 RTW_PWR_INTF_ALL_MSK,
+	 0,
+	 RTW_PWR_CMD_END, 0, 0},
+};
+
+const struct rtw_pwr_seq_cmd * const card_enable_flow_8814a[] = {
+	init_power_on_8814a,
+	trans_carddis_to_cardemu_8814a,
+	trans_cardemu_to_act_8814a,
+	NULL
+};
+
+const struct rtw_pwr_seq_cmd * const card_disable_flow_8814a[] = {
+	trans_act_to_cardemu_8814a,
+	trans_cardemu_to_carddis_8814a,
+	NULL
+};
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a_table.h b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.h
new file mode 100644
index 0000000000000..69fb87e36c481
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a_table.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#ifndef __RTW8814A_TABLE_H__
+#define __RTW8814A_TABLE_H__
+
+extern const struct rtw_table rtw8814a_mac_tbl;
+extern const struct rtw_table rtw8814a_agc_tbl;
+extern const struct rtw_table rtw8814a_bb_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type0_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type2_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type3_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type4_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type5_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type7_tbl;
+extern const struct rtw_table rtw8814a_bb_pg_type8_tbl;
+extern const struct rtw_table rtw8814a_rf_a_tbl;
+extern const struct rtw_table rtw8814a_rf_b_tbl;
+extern const struct rtw_table rtw8814a_rf_c_tbl;
+extern const struct rtw_table rtw8814a_rf_d_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type0_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type1_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type2_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type3_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type5_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type7_tbl;
+extern const struct rtw_table rtw8814a_txpwr_lmt_type8_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type0_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type2_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type5_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type7_tbl;
+extern const struct rtw_pwr_track_tbl rtw8814a_rtw_pwrtrk_type8_tbl;
+extern const struct rtw_pwr_seq_cmd * const card_disable_flow_8814a[];
+extern const struct rtw_pwr_seq_cmd * const card_enable_flow_8814a[];
+
+#endif

From 1a75457846424b77978d0ba1feb836913ed60637 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:24:40 +0200
Subject: [PATCH 2069/2753] wifi: rtw88: Add rtw8814a.{c,h}

These contain all the logic for the RTL8814A chip.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/5d3b8c03-63c1-4f20-860a-89d424badad8@gmail.com
---
 drivers/net/wireless/realtek/rtw88/rtw8814a.c | 2257 +++++++++++++++++
 drivers/net/wireless/realtek/rtw88/rtw8814a.h |   62 +
 2 files changed, 2319 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814a.c
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814a.h

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a.c b/drivers/net/wireless/realtek/rtw88/rtw8814a.c
new file mode 100644
index 0000000000000..cfd35d40d46e2
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a.c
@@ -0,0 +1,2257 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#include <linux/usb.h>
+#include "main.h"
+#include "coex.h"
+#include "tx.h"
+#include "phy.h"
+#include "rtw8814a.h"
+#include "rtw8814a_table.h"
+#include "rtw88xxa.h"
+#include "reg.h"
+#include "debug.h"
+#include "efuse.h"
+#include "regd.h"
+#include "usb.h"
+
+static void rtw8814a_efuse_grant(struct rtw_dev *rtwdev, bool on)
+{
+	if (on) {
+		rtw_write8(rtwdev, REG_EFUSE_ACCESS, EFUSE_ACCESS_ON);
+
+		rtw_write16_set(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_ELDR);
+		rtw_write16_set(rtwdev, REG_SYS_CLKR,
+				BIT_LOADER_CLK_EN | BIT_ANA8M);
+	} else {
+		rtw_write8(rtwdev, REG_EFUSE_ACCESS, EFUSE_ACCESS_OFF);
+	}
+}
+
+static void rtw8814a_read_rfe_type(struct rtw_dev *rtwdev)
+{
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+
+	if (!(efuse->rfe_option & BIT(7)))
+		return;
+
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE)
+		efuse->rfe_option = 0;
+	else if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB)
+		efuse->rfe_option = 1;
+}
+
+static void rtw8814a_read_amplifier_type(struct rtw_dev *rtwdev)
+{
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+
+	switch (efuse->rfe_option) {
+	case 1:
+		/* Internal 2G */
+		efuse->pa_type_2g = 0;
+		efuse->lna_type_2g = 0;
+		/* External 5G */
+		efuse->pa_type_5g = BIT(0);
+		efuse->lna_type_5g = BIT(3);
+		break;
+	case 2 ... 5:
+		/* External everything */
+		efuse->pa_type_2g = BIT(4);
+		efuse->lna_type_2g = BIT(3);
+		efuse->pa_type_5g = BIT(0);
+		efuse->lna_type_5g = BIT(3);
+		break;
+	case 6:
+		efuse->lna_type_5g = BIT(3);
+		break;
+	default:
+		break;
+	}
+}
+
+static void rtw8814a_read_rf_type(struct rtw_dev *rtwdev,
+				  struct rtw8814a_efuse *map)
+{
+	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+	struct rtw_hal *hal = &rtwdev->hal;
+
+	switch (map->trx_antenna_option) {
+	case 0xff: /* 4T4R */
+	case 0xee: /* 3T3R */
+		if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB &&
+		    rtwusb->udev->speed != USB_SPEED_SUPER)
+			hal->rf_type = RF_2T2R;
+		else
+			hal->rf_type = RF_3T3R;
+
+		break;
+	case 0x66: /* 2T2R */
+	case 0x6f: /* 2T4R */
+	default:
+		hal->rf_type = RF_2T2R;
+		break;
+	}
+
+	hal->rf_path_num = 4;
+	hal->rf_phy_num = 4;
+
+	if (hal->rf_type == RF_3T3R) {
+		hal->antenna_rx = BB_PATH_ABC;
+		hal->antenna_tx = BB_PATH_ABC;
+	} else {
+		hal->antenna_rx = BB_PATH_AB;
+		hal->antenna_tx = BB_PATH_AB;
+	}
+}
+
+static void rtw8814a_init_hwcap(struct rtw_dev *rtwdev)
+{
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+	struct rtw_hal *hal = &rtwdev->hal;
+
+	efuse->hw_cap.bw = BIT(RTW_CHANNEL_WIDTH_20) |
+			   BIT(RTW_CHANNEL_WIDTH_40) |
+			   BIT(RTW_CHANNEL_WIDTH_80);
+	efuse->hw_cap.ptcl = EFUSE_HW_CAP_PTCL_VHT;
+
+	if (hal->rf_type == RF_3T3R)
+		efuse->hw_cap.nss = 3;
+	else
+		efuse->hw_cap.nss = 2;
+
+	rtw_dbg(rtwdev, RTW_DBG_EFUSE,
+		"hw cap: hci=0x%02x, bw=0x%02x, ptcl=0x%02x, ant_num=%d, nss=%d\n",
+		efuse->hw_cap.hci, efuse->hw_cap.bw, efuse->hw_cap.ptcl,
+		efuse->hw_cap.ant_num, efuse->hw_cap.nss);
+}
+
+static int rtw8814a_read_efuse(struct rtw_dev *rtwdev, u8 *log_map)
+{
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+	struct rtw8814a_efuse *map;
+	int i;
+
+	if (rtw_dbg_is_enabled(rtwdev, RTW_DBG_EFUSE))
+		print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1,
+			       log_map, rtwdev->chip->log_efuse_size, true);
+
+	map = (struct rtw8814a_efuse *)log_map;
+
+	efuse->usb_mode_switch = u8_get_bits(map->usb_mode, BIT(4));
+	efuse->rfe_option = map->rfe_option;
+	efuse->rf_board_option = map->rf_board_option;
+	efuse->crystal_cap = map->xtal_k;
+	efuse->channel_plan = map->channel_plan;
+	efuse->country_code[0] = map->country_code[0];
+	efuse->country_code[1] = map->country_code[1];
+	efuse->bt_setting = map->rf_bt_setting;
+	efuse->regd = map->rf_board_option & 0x7;
+	efuse->thermal_meter[RF_PATH_A] = map->thermal_meter;
+	efuse->thermal_meter_k = map->thermal_meter;
+	efuse->tx_bb_swing_setting_2g = map->tx_bb_swing_setting_2g;
+	efuse->tx_bb_swing_setting_5g = map->tx_bb_swing_setting_5g;
+
+	rtw8814a_read_rfe_type(rtwdev);
+	rtw8814a_read_amplifier_type(rtwdev);
+
+	/* Override rtw_chip_parameter_setup() */
+	rtw8814a_read_rf_type(rtwdev, map);
+
+	rtw8814a_init_hwcap(rtwdev);
+
+	for (i = 0; i < 4; i++)
+		efuse->txpwr_idx_table[i] = map->txpwr_idx_table[i];
+
+	switch (rtw_hci_type(rtwdev)) {
+	case RTW_HCI_TYPE_USB:
+		ether_addr_copy(efuse->addr, map->u.mac_addr);
+		break;
+	case RTW_HCI_TYPE_PCIE:
+		ether_addr_copy(efuse->addr, map->e.mac_addr);
+		break;
+	case RTW_HCI_TYPE_SDIO:
+	default:
+		/* unsupported now */
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static void rtw8814a_init_rfe_reg(struct rtw_dev *rtwdev)
+{
+	u8 rfe_option = rtwdev->efuse.rfe_option;
+
+	if (rfe_option == 2 || rfe_option == 1) {
+		rtw_write32_mask(rtwdev, 0x1994, 0xf, 0xf);
+		rtw_write8_set(rtwdev, REG_GPIO_MUXCFG + 2, 0xf0);
+	} else if (rfe_option == 0) {
+		rtw_write32_mask(rtwdev, 0x1994, 0xf, 0xf);
+		rtw_write8_set(rtwdev, REG_GPIO_MUXCFG + 2, 0xc0);
+	}
+}
+
+#define RTW_TXSCALE_SIZE 37
+static const u32 rtw8814a_txscale_tbl[RTW_TXSCALE_SIZE] = {
+	0x081, 0x088, 0x090, 0x099, 0x0a2, 0x0ac, 0x0b6, 0x0c0, 0x0cc, 0x0d8,
+	0x0e5, 0x0f2, 0x101, 0x110, 0x120, 0x131, 0x143, 0x156, 0x16a, 0x180,
+	0x197, 0x1af, 0x1c8, 0x1e3, 0x200, 0x21e, 0x23e, 0x261, 0x285, 0x2ab,
+	0x2d3, 0x2fe, 0x32b, 0x35c, 0x38e, 0x3c4, 0x3fe
+};
+
+static u32 rtw8814a_get_bb_swing(struct rtw_dev *rtwdev, u8 band, u8 rf_path)
+{
+	static const u32 swing2setting[4] = {0x200, 0x16a, 0x101, 0x0b6};
+	struct rtw_efuse *efuse = &rtwdev->efuse;
+	u8 tx_bb_swing;
+
+	if (band == RTW_BAND_2G)
+		tx_bb_swing = efuse->tx_bb_swing_setting_2g;
+	else
+		tx_bb_swing = efuse->tx_bb_swing_setting_5g;
+
+	tx_bb_swing >>= 2 * rf_path;
+	tx_bb_swing &= 0x3;
+
+	return swing2setting[tx_bb_swing];
+}
+
+static u8 rtw8814a_get_swing_index(struct rtw_dev *rtwdev)
+{
+	u32 swing, table_value;
+	u8 i;
+
+	swing = rtw8814a_get_bb_swing(rtwdev, rtwdev->hal.current_band_type,
+				      RF_PATH_A);
+
+	for (i = 0; i < ARRAY_SIZE(rtw8814a_txscale_tbl); i++) {
+		table_value = rtw8814a_txscale_tbl[i];
+		if (swing == table_value)
+			return i;
+	}
+
+	return 24;
+}
+
+static void rtw8814a_pwrtrack_init(struct rtw_dev *rtwdev)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	u8 path;
+
+	dm_info->default_ofdm_index = rtw8814a_get_swing_index(rtwdev);
+
+	for (path = RF_PATH_A; path < rtwdev->hal.rf_path_num; path++) {
+		ewma_thermal_init(&dm_info->avg_thermal[path]);
+		dm_info->delta_power_index[path] = 0;
+		dm_info->delta_power_index_last[path] = 0;
+	}
+	dm_info->pwr_trk_triggered = false;
+	dm_info->pwr_trk_init_trigger = true;
+	dm_info->thermal_meter_k = rtwdev->efuse.thermal_meter_k;
+}
+
+static void rtw8814a_config_trx_path(struct rtw_dev *rtwdev)
+{
+	/* RX CCK disable 2R CCA */
+	rtw_write32_clr(rtwdev, REG_CCK0_FAREPORT,
+			BIT_CCK0_2RX | BIT_CCK0_MRC);
+	/* pathB tx on, path A/C/D tx off */
+	rtw_write32_mask(rtwdev, REG_CCK_RX, 0xf0000000, 0x4);
+	/* pathB rx */
+	rtw_write32_mask(rtwdev, REG_CCK_RX, 0x0f000000, 0x5);
+}
+
+static void rtw8814a_config_cck_rx_antenna_init(struct rtw_dev *rtwdev)
+{
+	/* CCK 2R CCA parameters */
+
+	/* Disable Ant diversity */
+	rtw_write32_mask(rtwdev, REG_RXSB, BIT_RXSB_ANA_DIV, 0x0);
+	/* Concurrent CCA at LSB & USB */
+	rtw_write32_mask(rtwdev, REG_CCA, BIT_CCA_CO, 0);
+	/* RX path diversity enable */
+	rtw_write32_mask(rtwdev, REG_ANTSEL, BIT_ANT_BYCO, 0);
+	/* r_en_mrc_antsel */
+	rtw_write32_mask(rtwdev, REG_PRECTRL, BIT_DIS_CO_PATHSEL, 0);
+	/* MBC weighting */
+	rtw_write32_mask(rtwdev, REG_CCA_MF, BIT_MBC_WIN, 1);
+	/* 2R CCA only */
+	rtw_write32_mask(rtwdev, REG_CCKTX, BIT_CMB_CCA_2R, 1);
+}
+
+static void rtw8814a_phy_set_param(struct rtw_dev *rtwdev)
+{
+	u32 crystal_cap, val32;
+	u8 val8, rf_path;
+
+	/* power on BB/RF domain */
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB)
+		rtw_write8_set(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_USBA);
+	else if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE)
+		rtw_write8_set(rtwdev, REG_SYS_FUNC_EN, BIT_FEN_PCIEA);
+
+	rtw_write8_set(rtwdev, REG_SYS_CFG3_8814A + 2,
+		       BIT_FEN_BB_GLB_RST | BIT_FEN_BB_RSTB);
+
+	/* Power on RF paths A..D */
+	val8 = BIT_RF_EN | BIT_RF_RSTB | BIT_RF_SDM_RSTB;
+	rtw_write8(rtwdev, REG_RF_CTRL, val8);
+	rtw_write8(rtwdev, REG_RF_CTRL1, val8);
+	rtw_write8(rtwdev, REG_RF_CTRL2, val8);
+	rtw_write8(rtwdev, REG_RF_CTRL3, val8);
+
+	rtw_load_table(rtwdev, rtwdev->chip->bb_tbl);
+	rtw_load_table(rtwdev, rtwdev->chip->agc_tbl);
+
+	crystal_cap = rtwdev->efuse.crystal_cap & 0x3F;
+	crystal_cap |= crystal_cap << 6;
+	rtw_write32_mask(rtwdev, REG_AFE_CTRL3, 0x07ff8000, crystal_cap);
+
+	rtw8814a_config_trx_path(rtwdev);
+
+	for (rf_path = 0; rf_path < rtwdev->hal.rf_path_num; rf_path++)
+		rtw_load_table(rtwdev, rtwdev->chip->rf_tbl[rf_path]);
+
+	val32 = rtw_read_rf(rtwdev, RF_PATH_A, RF_RCK1_V1, RFREG_MASK);
+	rtw_write_rf(rtwdev, RF_PATH_B, RF_RCK1_V1, RFREG_MASK, val32);
+	rtw_write_rf(rtwdev, RF_PATH_C, RF_RCK1_V1, RFREG_MASK, val32);
+	rtw_write_rf(rtwdev, RF_PATH_D, RF_RCK1_V1, RFREG_MASK, val32);
+
+	rtw_write32_set(rtwdev, REG_RXPSEL, BIT_RX_PSEL_RST);
+
+	rtw_write8(rtwdev, REG_HWSEQ_CTRL, 0xFF);
+
+	rtw_write32(rtwdev, REG_BAR_MODE_CTRL, 0x0201ffff);
+
+	rtw_write8(rtwdev, REG_MISC_CTRL, BIT_DIS_SECOND_CCA);
+
+	rtw_write8(rtwdev, REG_NAV_CTRL + 2, 0);
+
+	rtw_write8_clr(rtwdev, REG_GPIO_MUXCFG, BIT(5));
+
+	rtw8814a_config_cck_rx_antenna_init(rtwdev);
+
+	rtw_phy_init(rtwdev);
+	rtw8814a_pwrtrack_init(rtwdev);
+
+	rtw8814a_init_rfe_reg(rtwdev);
+
+	rtw_write8_clr(rtwdev, REG_QUEUE_CTRL, BIT(3));
+
+	rtw_write8(rtwdev, REG_NAV_CTRL + 2, 235);
+
+	/* enable Tx report. */
+	rtw_write8(rtwdev,  REG_FWHW_TXQ_CTRL + 1, 0x1F);
+
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB) {
+		/* Reset USB mode switch setting */
+		rtw_write8(rtwdev, REG_SYS_SDIO_CTRL, 0x0);
+		rtw_write8(rtwdev, REG_ACLK_MON, 0x0);
+	}
+}
+
+static void rtw8814ae_enable_rf_1_2v(struct rtw_dev *rtwdev)
+{
+	/* This is for fullsize card, because GPIO7 there is floating.
+	 * We should pull GPIO7 high to enable RF 1.2V Switch Power Supply
+	 */
+
+	/* 1. set 0x40[1:0] to 0, BIT_GPIOSEL=0, select pin as GPIO */
+	rtw_write8_clr(rtwdev, REG_GPIO_MUXCFG, BIT(1) | BIT(0));
+
+	/* 2. set 0x44[31] to 0
+	 * mode=0: data port;
+	 * mode=1 and BIT_GPIO_IO_SEL=0: interrupt mode;
+	 */
+	rtw_write8_clr(rtwdev, REG_GPIO_PIN_CTRL + 3, BIT(7));
+
+	/* 3. data mode
+	 * 3.1 set 0x44[23] to 1
+	 * sel=0: input;
+	 * sel=1: output;
+	 */
+	rtw_write8_set(rtwdev, REG_GPIO_PIN_CTRL + 2, BIT(7));
+
+	/* 3.2 set 0x44[15] to 1
+	 * output high value;
+	 */
+	rtw_write8_set(rtwdev, REG_GPIO_PIN_CTRL + 1, BIT(7));
+}
+
+static int rtw8814a_mac_init(struct rtw_dev *rtwdev)
+{
+	struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+
+	rtw_write16(rtwdev, REG_CR,
+		    MAC_TRX_ENABLE | BIT_MAC_SEC_EN | BIT_32K_CAL_TMR_EN);
+
+	rtw_load_table(rtwdev, rtwdev->chip->mac_tbl);
+
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB)
+		rtw_write8(rtwdev, REG_AUTO_LLT_V1 + 3,
+			   rtwdev->chip->usb_tx_agg_desc_num << 1);
+
+	rtw_write32(rtwdev, REG_HIMR0, 0);
+	rtw_write32(rtwdev, REG_HIMR1, 0);
+
+	rtw_write32_mask(rtwdev, REG_RRSR, 0xfffff, 0xfffff);
+
+	rtw_write16(rtwdev, REG_RETRY_LIMIT, 0x3030);
+
+	rtw_write16(rtwdev, REG_RXFLTMAP0, 0xffff);
+	rtw_write16(rtwdev, REG_RXFLTMAP1, 0x0400);
+	rtw_write16(rtwdev, REG_RXFLTMAP2, 0xffff);
+
+	rtw_write8(rtwdev, REG_MAX_AGGR_NUM, 0x36);
+	rtw_write8(rtwdev, REG_MAX_AGGR_NUM + 1, 0x36);
+
+	/* Set Spec SIFS (used in NAV) */
+	rtw_write16(rtwdev, REG_SPEC_SIFS, 0x100a);
+	rtw_write16(rtwdev, REG_MAC_SPEC_SIFS, 0x100a);
+
+	/* Set SIFS for CCK */
+	rtw_write16(rtwdev, REG_SIFS, 0x100a);
+
+	/* Set SIFS for OFDM */
+	rtw_write16(rtwdev, REG_SIFS + 2, 0x100a);
+
+	/* TXOP */
+	rtw_write32(rtwdev, REG_EDCA_BE_PARAM, 0x005EA42B);
+	rtw_write32(rtwdev, REG_EDCA_BK_PARAM, 0x0000A44F);
+	rtw_write32(rtwdev, REG_EDCA_VI_PARAM, 0x005EA324);
+	rtw_write32(rtwdev, REG_EDCA_VO_PARAM, 0x002FA226);
+
+	rtw_write8_set(rtwdev, REG_FWHW_TXQ_CTRL, BIT(7));
+
+	rtw_write8(rtwdev, REG_ACKTO, 0x80);
+
+	rtw_write16(rtwdev, REG_BCN_CTRL,
+		    BIT_DIS_TSF_UDT | (BIT_DIS_TSF_UDT << 8));
+	rtw_write32_mask(rtwdev, REG_TBTT_PROHIBIT, 0xfffff, WLAN_TBTT_TIME);
+	rtw_write8(rtwdev, REG_DRVERLYINT, 0x05);
+	rtw_write8(rtwdev, REG_BCNDMATIM, WLAN_BCN_DMA_TIME);
+	rtw_write16(rtwdev, REG_BCNTCFG, 0x4413);
+	rtw_write8(rtwdev, REG_BCN_MAX_ERR, 0xFF);
+
+	rtw_write32(rtwdev, REG_FAST_EDCA_VOVI_SETTING, 0x08070807);
+	rtw_write32(rtwdev, REG_FAST_EDCA_BEBK_SETTING, 0x08070807);
+
+	if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_USB &&
+	    rtwusb->udev->speed == USB_SPEED_SUPER) {
+		/* Disable U1/U2 Mode to avoid 2.5G spur in USB3.0. */
+		rtw_write8_clr(rtwdev, REG_USB_MOD, BIT(4) | BIT(3));
+		/* To avoid usb 3.0 H2C fail. */
+		rtw_write16(rtwdev, 0xf002, 0);
+
+		rtw_write8_clr(rtwdev, REG_SW_AMPDU_BURST_MODE_CTRL,
+			       BIT_PRE_TX_CMD);
+	} else if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE) {
+		rtw8814ae_enable_rf_1_2v(rtwdev);
+
+		/* Force the antenna b to wifi. */
+		rtw_write8_set(rtwdev, REG_PAD_CTRL1, BIT(2));
+		rtw_write8_set(rtwdev, REG_PAD_CTRL1 + 1, BIT(0));
+		rtw_write8_set(rtwdev, REG_LED_CFG + 3,
+			       (BIT(27) | BIT_DPDT_WL_SEL) >> 24);
+	}
+
+	return 0;
+}
+
+static void rtw8814a_set_rfe_reg_24g(struct rtw_dev *rtwdev)
+{
+	switch (rtwdev->efuse.rfe_option) {
+	case 2:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x72707270);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x72707270);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x72707270);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x77707770);
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x72);
+
+		break;
+	case 1:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x77777777);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x77777777);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x77777777);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x77777777);
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x77);
+
+		break;
+	case 0:
+	default:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x77777777);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x77777777);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x77777777);
+		/* Is it not necessary to set REG_RFE_PINMUX_D ? */
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x77);
+
+		break;
+	}
+}
+
+static void rtw8814a_set_rfe_reg_5g(struct rtw_dev *rtwdev)
+{
+	switch (rtwdev->efuse.rfe_option) {
+	case 2:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x37173717);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x37173717);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x37173717);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x77177717);
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x37);
+
+		break;
+	case 1:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x33173317);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x33173317);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x33173317);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x77177717);
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x33);
+
+		break;
+	case 0:
+	default:
+		rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x54775477);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x54775477);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x54775477);
+		rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x54775477);
+
+		rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D,
+				 BIT_RFE_SELSW0_D, 0x54);
+
+		break;
+	}
+}
+
+static void rtw8814a_set_channel_bb_swing(struct rtw_dev *rtwdev, u8 band)
+{
+	rtw_write32_mask(rtwdev, REG_TXSCALE_A, BB_SWING_MASK,
+			 rtw8814a_get_bb_swing(rtwdev, band, RF_PATH_A));
+	rtw_write32_mask(rtwdev, REG_TXSCALE_B, BB_SWING_MASK,
+			 rtw8814a_get_bb_swing(rtwdev, band, RF_PATH_B));
+	rtw_write32_mask(rtwdev, REG_TXSCALE_C, BB_SWING_MASK,
+			 rtw8814a_get_bb_swing(rtwdev, band, RF_PATH_C));
+	rtw_write32_mask(rtwdev, REG_TXSCALE_D, BB_SWING_MASK,
+			 rtw8814a_get_bb_swing(rtwdev, band, RF_PATH_D));
+	rtw8814a_pwrtrack_init(rtwdev);
+}
+
+static void rtw8814a_set_bw_reg_adc(struct rtw_dev *rtwdev, u8 bw)
+{
+	u32 adc = 0;
+
+	if (bw == RTW_CHANNEL_WIDTH_20)
+		adc = 0;
+	else if (bw == RTW_CHANNEL_WIDTH_40)
+		adc = 1;
+	else if (bw == RTW_CHANNEL_WIDTH_80)
+		adc = 2;
+
+	rtw_write32_mask(rtwdev, REG_ADCCLK, BIT(1) | BIT(0), adc);
+}
+
+static void rtw8814a_set_bw_reg_agc(struct rtw_dev *rtwdev, u8 new_band, u8 bw)
+{
+	u32 agc = 7;
+
+	if (bw == RTW_CHANNEL_WIDTH_20) {
+		agc = 6;
+	} else if (bw == RTW_CHANNEL_WIDTH_40) {
+		if (new_band == RTW_BAND_5G)
+			agc = 8;
+		else
+			agc = 7;
+	} else if (bw == RTW_CHANNEL_WIDTH_80) {
+		agc = 3;
+	}
+
+	rtw_write32_mask(rtwdev, REG_CCASEL, 0xf000, agc);
+}
+
+static void rtw8814a_switch_band(struct rtw_dev *rtwdev, u8 new_band, u8 bw)
+{
+	/* Clear 0x1000[16], When this bit is set to 0, CCK and OFDM
+	 * are disabled, and clock are gated. Otherwise, CCK and OFDM
+	 * are enabled.
+	 */
+	rtw_write8_clr(rtwdev, REG_SYS_CFG3_8814A + 2, BIT_FEN_BB_RSTB);
+
+	if (new_band == RTW_BAND_2G) {
+		rtw_write32_mask(rtwdev, REG_AGC_TABLE, 0x1f, 0);
+
+		rtw8814a_set_rfe_reg_24g(rtwdev);
+
+		rtw_write32_mask(rtwdev, REG_TXPSEL, 0xf0, 0x2);
+		rtw_write32_mask(rtwdev, REG_CCK_RX, 0x0f000000, 0x5);
+
+		rtw_write32_mask(rtwdev, REG_RXPSEL, BIT_RX_PSEL_RST, 0x3);
+
+		rtw_write8(rtwdev, REG_CCK_CHECK, 0);
+
+		rtw_write32_mask(rtwdev, 0xa80, BIT(18), 0);
+	} else {
+		rtw_write8(rtwdev, REG_CCK_CHECK, BIT_CHECK_CCK_EN);
+
+		/* Enable CCK Tx function, even when CCK is off */
+		rtw_write32_mask(rtwdev, 0xa80, BIT(18), 1);
+
+		rtw8814a_set_rfe_reg_5g(rtwdev);
+
+		rtw_write32_mask(rtwdev, REG_TXPSEL, 0xf0, 0x0);
+		rtw_write32_mask(rtwdev, REG_CCK_RX, 0x0f000000, 0xf);
+
+		rtw_write32_mask(rtwdev, REG_RXPSEL, BIT_RX_PSEL_RST, 0x2);
+	}
+
+	rtw8814a_set_channel_bb_swing(rtwdev, new_band);
+
+	rtw8814a_set_bw_reg_adc(rtwdev, bw);
+	rtw8814a_set_bw_reg_agc(rtwdev, new_band, bw);
+
+	rtw_write8_set(rtwdev, REG_SYS_CFG3_8814A + 2, BIT_FEN_BB_RSTB);
+}
+
+static void rtw8814a_switch_channel(struct rtw_dev *rtwdev, u8 channel)
+{
+	struct rtw_hal *hal = &rtwdev->hal;
+	u32 fc_area, rf_mod_ag, cfgch;
+	u8 path;
+
+	switch (channel) {
+	case 36 ... 48:
+		fc_area = 0x494;
+		break;
+	case 50 ... 64:
+		fc_area = 0x453;
+		break;
+	case 100 ... 116:
+		fc_area = 0x452;
+		break;
+	default:
+		if (channel >= 118)
+			fc_area = 0x412;
+		else
+			fc_area = 0x96a;
+		break;
+	}
+
+	rtw_write32_mask(rtwdev, REG_CLKTRK, 0x1ffe0000, fc_area);
+
+	for (path = 0; path < hal->rf_path_num; path++) {
+		switch (channel) {
+		case 36 ... 64:
+			rf_mod_ag = 0x101;
+			break;
+		case 100 ... 140:
+			rf_mod_ag = 0x301;
+			break;
+		default:
+			if (channel > 140)
+				rf_mod_ag = 0x501;
+			else
+				rf_mod_ag = 0x000;
+			break;
+		}
+
+		cfgch = (rf_mod_ag << 8) | channel;
+
+		rtw_write_rf(rtwdev, path, RF_CFGCH,
+			     RF18_RFSI_MASK | RF18_BAND_MASK | RF18_CHANNEL_MASK, cfgch);
+	}
+
+	switch (channel) {
+	case 36 ... 64:
+		rtw_write32_mask(rtwdev, REG_AGC_TABLE, 0x1f, 1);
+		break;
+	case 100 ... 144:
+		rtw_write32_mask(rtwdev, REG_AGC_TABLE, 0x1f, 2);
+		break;
+	default:
+		if (channel >= 149)
+			rtw_write32_mask(rtwdev, REG_AGC_TABLE, 0x1f, 3);
+
+		break;
+	}
+}
+
+static void rtw8814a_24g_cck_tx_dfir(struct rtw_dev *rtwdev, u8 channel)
+{
+	if (channel >= 1 && channel <= 11) {
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER1, 0x1a1b0030);
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER2, 0x090e1317);
+		rtw_write32(rtwdev, REG_CCK0_DEBUG_PORT, 0x00000204);
+	} else if (channel >= 12 && channel <= 13) {
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER1, 0x1a1b0030);
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER2, 0x090e1217);
+		rtw_write32(rtwdev, REG_CCK0_DEBUG_PORT, 0x00000305);
+	} else if (channel == 14) {
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER1, 0x1a1b0030);
+		rtw_write32(rtwdev, REG_CCK0_TX_FILTER2, 0x00000E17);
+		rtw_write32(rtwdev, REG_CCK0_DEBUG_PORT, 0x00000000);
+	}
+}
+
+static void rtw8814a_set_bw_reg_mac(struct rtw_dev *rtwdev, u8 bw)
+{
+	u16 val16 = rtw_read16(rtwdev, REG_WMAC_TRXPTCL_CTL);
+
+	val16 &= ~BIT_RFMOD;
+	if (bw == RTW_CHANNEL_WIDTH_80)
+		val16 |= BIT_RFMOD_80M;
+	else if (bw == RTW_CHANNEL_WIDTH_40)
+		val16 |= BIT_RFMOD_40M;
+
+	rtw_write16(rtwdev, REG_WMAC_TRXPTCL_CTL, val16);
+}
+
+static void rtw8814a_set_bw_rf(struct rtw_dev *rtwdev, u8 bw)
+{
+	u8 path;
+
+	for (path = RF_PATH_A; path < rtwdev->hal.rf_path_num; path++) {
+		switch (bw) {
+		case RTW_CHANNEL_WIDTH_5:
+		case RTW_CHANNEL_WIDTH_10:
+		case RTW_CHANNEL_WIDTH_20:
+		default:
+			rtw_write_rf(rtwdev, path, RF_CFGCH, RF18_BW_MASK, 3);
+			break;
+		case RTW_CHANNEL_WIDTH_40:
+			rtw_write_rf(rtwdev, path, RF_CFGCH, RF18_BW_MASK, 1);
+			break;
+		case RTW_CHANNEL_WIDTH_80:
+			rtw_write_rf(rtwdev, path, RF_CFGCH, RF18_BW_MASK, 0);
+			break;
+		}
+	}
+}
+
+static void rtw8814a_adc_clk(struct rtw_dev *rtwdev)
+{
+	static const u32 rxiqc_reg[2][4] = {
+		{ REG_RX_IQC_AB_A, REG_RX_IQC_AB_B,
+		  REG_RX_IQC_AB_C, REG_RX_IQC_AB_D },
+		{ REG_RX_IQC_CD_A, REG_RX_IQC_CD_B,
+		  REG_RX_IQC_CD_C, REG_RX_IQC_CD_D }
+	};
+	u32 bb_reg_8fc, bb_reg_808, rxiqc[4];
+	u32 i = 0, mac_active = 1;
+	u8 mac_reg_522;
+
+	if (rtwdev->hal.cut_version != RTW_CHIP_VER_CUT_A)
+		return;
+
+	/* 1 Step1. MAC TX pause */
+	mac_reg_522 = rtw_read8(rtwdev, REG_TXPAUSE);
+	bb_reg_8fc = rtw_read32(rtwdev, REG_DBGSEL);
+	bb_reg_808 = rtw_read32(rtwdev, REG_RXPSEL);
+	rtw_write8(rtwdev, REG_TXPAUSE, 0x3f);
+
+	/* 1 Step 2. Backup rxiqc & rxiqc = 0 */
+	for (i = 0; i < 4; i++) {
+		rxiqc[i] = rtw_read32(rtwdev, rxiqc_reg[0][i]);
+		rtw_write32(rtwdev, rxiqc_reg[0][i], 0x0);
+		rtw_write32(rtwdev, rxiqc_reg[1][i], 0x0);
+	}
+	rtw_write32_mask(rtwdev, REG_PRECTRL, BIT_IQ_WGT, 0x3);
+	i = 0;
+
+	/* 1 Step 3. Monitor MAC IDLE */
+	rtw_write32(rtwdev, REG_DBGSEL, 0x0);
+	while (mac_active) {
+		mac_active = rtw_read32(rtwdev, REG_DBGRPT) & 0x803e0008;
+		i++;
+		if (i > 1000)
+			break;
+	}
+
+	/* 1 Step 4. ADC clk flow */
+	rtw_write8(rtwdev, REG_RXPSEL, 0x11);
+	rtw_write32_mask(rtwdev, REG_DAC_RSTB, BIT(13), 0x1);
+	rtw_write8_mask(rtwdev, REG_GNT_BT, BIT(2) | BIT(1), 0x3);
+	rtw_write32_mask(rtwdev, REG_CCK_RPT_FORMAT, BIT(2), 0x1);
+
+	/* 0xc1c/0xe1c/0x181c/0x1a1c[4] must=1 to ensure table can be
+	 * written when bbrstb=0
+	 * 0xc60/0xe60/0x1860/0x1a60[15] always = 1 after this line
+	 * 0xc60/0xe60/0x1860/0x1a60[14] always = 0 bcz its error in A-cut
+	 */
+
+	/* power_off/clk_off @ anapar_state=idle mode */
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x15800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x01808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x15800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x01808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x15800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x01808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x15800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x01808003);
+
+	rtw_write8_mask(rtwdev, REG_GNT_BT, BIT(2), 0x0);
+	rtw_write32_mask(rtwdev, REG_CCK_RPT_FORMAT, BIT(2), 0x0);
+	/* [19] = 1 to turn off ADC */
+	rtw_write32(rtwdev, REG_CK_MONHA, 0x0D080058);
+	rtw_write32(rtwdev, REG_CK_MONHB, 0x0D080058);
+	rtw_write32(rtwdev, REG_CK_MONHC, 0x0D080058);
+	rtw_write32(rtwdev, REG_CK_MONHD, 0x0D080058);
+
+	/* power_on/clk_off */
+	/* [19] = 0 to turn on ADC */
+	rtw_write32(rtwdev, REG_CK_MONHA, 0x0D000058);
+	rtw_write32(rtwdev, REG_CK_MONHB, 0x0D000058);
+	rtw_write32(rtwdev, REG_CK_MONHC, 0x0D000058);
+	rtw_write32(rtwdev, REG_CK_MONHD, 0x0D000058);
+
+	/* power_on/clk_on @ anapar_state=BT mode */
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x05808032);
+	rtw_write8_mask(rtwdev, REG_GNT_BT, BIT(2), 0x1);
+	rtw_write32_mask(rtwdev, REG_CCK_RPT_FORMAT, BIT(2), 0x1);
+
+	/* recover original setting @ anapar_state=BT mode */
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x05808032);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x05808032);
+
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x05800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x07808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x05800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x07808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x05800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x07808003);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x05800002);
+	rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x07808003);
+
+	rtw_write8_mask(rtwdev, REG_GNT_BT, BIT(2) | BIT(1), 0x0);
+	rtw_write32_mask(rtwdev, REG_CCK_RPT_FORMAT, BIT(2), 0x0);
+	rtw_write32_mask(rtwdev, REG_DAC_RSTB, BIT(13), 0x0);
+
+	/* 1 Step 5. Recover MAC TX & IQC */
+	rtw_write8(rtwdev, REG_TXPAUSE, mac_reg_522);
+	rtw_write32(rtwdev, REG_DBGSEL, bb_reg_8fc);
+	rtw_write32(rtwdev, REG_RXPSEL, bb_reg_808);
+	for (i = 0; i < 4; i++) {
+		rtw_write32(rtwdev, rxiqc_reg[0][i], rxiqc[i]);
+		rtw_write32(rtwdev, rxiqc_reg[1][i], 0x01000000);
+	}
+	rtw_write32_mask(rtwdev, REG_PRECTRL, BIT_IQ_WGT, 0x0);
+}
+
+static void rtw8814a_spur_calibration_ch140(struct rtw_dev *rtwdev, u8 channel)
+{
+	struct rtw_hal *hal = &rtwdev->hal;
+
+	/* Add for 8814AE module ch140 MP Rx */
+	if (channel == 140) {
+		if (hal->ch_param[0] == 0)
+			hal->ch_param[0] = rtw_read32(rtwdev, REG_CCASEL);
+		if (hal->ch_param[1] == 0)
+			hal->ch_param[1] = rtw_read32(rtwdev, REG_PDMFTH);
+
+		rtw_write32(rtwdev, REG_CCASEL, 0x75438170);
+		rtw_write32(rtwdev, REG_PDMFTH, 0x79a18a0a);
+	} else {
+		if (rtw_read32(rtwdev, REG_CCASEL) == 0x75438170 &&
+		    hal->ch_param[0] != 0)
+			rtw_write32(rtwdev, REG_CCASEL, hal->ch_param[0]);
+
+		if (rtw_read32(rtwdev, REG_PDMFTH) == 0x79a18a0a &&
+		    hal->ch_param[1] != 0)
+			rtw_write32(rtwdev, REG_PDMFTH, hal->ch_param[1]);
+
+		hal->ch_param[0] = rtw_read32(rtwdev, REG_CCASEL);
+		hal->ch_param[1] = rtw_read32(rtwdev, REG_PDMFTH);
+	}
+}
+
+static void rtw8814a_set_nbi_reg(struct rtw_dev *rtwdev, u32 tone_idx)
+{
+	/* tone_idx X 10 */
+	static const u32 nbi_128[] = {
+		25, 55, 85, 115, 135,
+		155, 185, 205, 225, 245,
+		265, 285, 305, 335, 355,
+		375, 395, 415, 435, 455,
+		485, 505, 525, 555, 585, 615, 635
+	};
+	u32 reg_idx = 0;
+	u32 i;
+
+	for (i = 0; i < ARRAY_SIZE(nbi_128); i++) {
+		if (tone_idx < nbi_128[i]) {
+			reg_idx = i + 1;
+			break;
+		}
+	}
+
+	rtw_write32_mask(rtwdev, REG_NBI_SETTING, 0xfc000, reg_idx);
+}
+
+static void rtw8814a_nbi_setting(struct rtw_dev *rtwdev, u32 ch, u32 f_intf)
+{
+	u32 fc, int_distance, tone_idx;
+
+	fc = 2412 + (ch - 1) * 5;
+	int_distance = abs_diff(fc, f_intf);
+
+	/* 10 * (int_distance / 0.3125) */
+	tone_idx = int_distance << 5;
+
+	rtw8814a_set_nbi_reg(rtwdev, tone_idx);
+
+	rtw_write32_mask(rtwdev, REG_NBI_SETTING, BIT_NBI_ENABLE, 1);
+}
+
+static void rtw8814a_spur_nbi_setting(struct rtw_dev *rtwdev)
+{
+	u8 primary_channel = rtwdev->hal.primary_channel;
+	u8 rfe_type = rtwdev->efuse.rfe_option;
+
+	if (rfe_type != 0 && rfe_type != 1 && rfe_type != 6 && rfe_type != 7)
+		return;
+
+	if (primary_channel == 14)
+		rtw8814a_nbi_setting(rtwdev, primary_channel, 2480);
+	else if (primary_channel >= 4 && primary_channel <= 8)
+		rtw8814a_nbi_setting(rtwdev, primary_channel, 2440);
+	else
+		rtw_write32_mask(rtwdev, REG_NBI_SETTING, BIT_NBI_ENABLE, 0);
+}
+
+/* A workaround to eliminate the 5280 MHz & 5600 MHz & 5760 MHz spur of 8814A */
+static void rtw8814a_spur_calibration(struct rtw_dev *rtwdev, u8 channel, u8 bw)
+{
+	u8 rfe_type = rtwdev->efuse.rfe_option;
+	bool reset_nbi_csi = true;
+
+	if (rfe_type == 0) {
+		switch (bw) {
+		case RTW_CHANNEL_WIDTH_40:
+			if (channel == 54 || channel == 118) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x3e >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+
+				reset_nbi_csi = false;
+			} else if (channel == 151) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x1e >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK0,
+						 BIT(16), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+
+				reset_nbi_csi = false;
+			}
+			break;
+		case RTW_CHANNEL_WIDTH_80:
+			if (channel == 58 || channel == 122) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x3a >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK7,
+						 BIT(0), 1);
+
+				reset_nbi_csi = false;
+			} else if (channel == 155) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x5a >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK6,
+						 BIT(16), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+
+				reset_nbi_csi = false;
+			}
+			break;
+		case RTW_CHANNEL_WIDTH_20:
+			if (channel == 153) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x1e >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK7,
+						 BIT(16), 1);
+
+				reset_nbi_csi = false;
+			}
+
+			rtw8814a_spur_calibration_ch140(rtwdev, channel);
+			break;
+		default:
+			break;
+		}
+	} else if (rfe_type == 1 || rfe_type == 2) {
+		switch (bw) {
+		case RTW_CHANNEL_WIDTH_20:
+			if (channel == 153) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x1E >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK7,
+						 BIT(16), 1);
+
+				reset_nbi_csi = false;
+			}
+			break;
+		case RTW_CHANNEL_WIDTH_40:
+			if (channel == 151) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x1e >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK0,
+						 BIT(16), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+
+				reset_nbi_csi = false;
+			}
+			break;
+		case RTW_CHANNEL_WIDTH_80:
+			if (channel == 155) {
+				rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+						 0x000fe000, 0x5a >> 1);
+				rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1,
+						 BIT(0), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+				rtw_write32_mask(rtwdev, REG_CSI_FIX_MASK6,
+						 BIT(16), 1);
+				rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+
+				reset_nbi_csi = false;
+			}
+			break;
+		default:
+			break;
+		}
+	}
+
+	if (reset_nbi_csi) {
+		rtw_write32_mask(rtwdev, REG_NBI_SETTING,
+				 0x000fe000, 0xfc >> 1);
+		rtw_write32_mask(rtwdev, REG_CSI_MASK_SETTING1, BIT(0), 0);
+		rtw_write32(rtwdev, REG_CSI_FIX_MASK0, 0);
+		rtw_write32(rtwdev, REG_CSI_FIX_MASK1, 0);
+		rtw_write32(rtwdev, REG_CSI_FIX_MASK6, 0);
+		rtw_write32(rtwdev, REG_CSI_FIX_MASK7, 0);
+	}
+
+	rtw8814a_spur_nbi_setting(rtwdev);
+}
+
+static void rtw8814a_set_bw_mode(struct rtw_dev *rtwdev, u8 new_band,
+				 u8 channel, u8 bw, u8 primary_chan_idx)
+{
+	u8 txsc40 = 0, txsc20, txsc;
+
+	rtw8814a_set_bw_reg_mac(rtwdev, bw);
+
+	txsc20 = primary_chan_idx;
+	if (bw == RTW_CHANNEL_WIDTH_80) {
+		if (txsc20 == RTW_SC_20_UPPER || txsc20 == RTW_SC_20_UPMOST)
+			txsc40 = RTW_SC_40_UPPER;
+		else
+			txsc40 = RTW_SC_40_LOWER;
+	}
+
+	txsc = BIT_TXSC_20M(txsc20) | BIT_TXSC_40M(txsc40);
+	rtw_write8(rtwdev, REG_DATA_SC, txsc);
+
+	rtw8814a_set_bw_reg_adc(rtwdev, bw);
+	rtw8814a_set_bw_reg_agc(rtwdev, new_band, bw);
+
+	if (bw == RTW_CHANNEL_WIDTH_80) {
+		rtw_write32_mask(rtwdev, REG_ADCCLK, 0x3c, txsc);
+	} else if (bw == RTW_CHANNEL_WIDTH_40) {
+		rtw_write32_mask(rtwdev, REG_ADCCLK, 0x3c, txsc);
+
+		if (txsc == RTW_SC_20_UPPER)
+			rtw_write32_set(rtwdev, REG_RXSB, BIT(4));
+		else
+			rtw_write32_clr(rtwdev, REG_RXSB, BIT(4));
+	}
+
+	rtw8814a_set_bw_rf(rtwdev, bw);
+
+	rtw8814a_adc_clk(rtwdev);
+
+	rtw8814a_spur_calibration(rtwdev, channel, bw);
+}
+
+static void rtw8814a_set_channel(struct rtw_dev *rtwdev, u8 channel, u8 bw,
+				 u8 primary_chan_idx)
+{
+	u8 old_band, new_band;
+
+	if (rtw_read8(rtwdev, REG_CCK_CHECK) & BIT_CHECK_CCK_EN)
+		old_band = RTW_BAND_5G;
+	else
+		old_band = RTW_BAND_2G;
+
+	if (channel > 14)
+		new_band = RTW_BAND_5G;
+	else
+		new_band = RTW_BAND_2G;
+
+	if (new_band != old_band)
+		rtw8814a_switch_band(rtwdev, new_band, bw);
+
+	rtw8814a_switch_channel(rtwdev, channel);
+
+	rtw8814a_24g_cck_tx_dfir(rtwdev, channel);
+
+	rtw8814a_set_bw_mode(rtwdev, new_band, channel, bw, primary_chan_idx);
+}
+
+static s8 rtw8814a_cck_rx_pwr(u8 lna_idx, u8 vga_idx)
+{
+	s8 rx_pwr_all = 0;
+
+	switch (lna_idx) {
+	case 7:
+		rx_pwr_all = -38 - 2 * vga_idx;
+		break;
+	case 5:
+		rx_pwr_all = -28 - 2 * vga_idx;
+		break;
+	case 3:
+		rx_pwr_all = -8 - 2 * vga_idx;
+		break;
+	case 2:
+		rx_pwr_all = -1 - 2 * vga_idx;
+		break;
+	default:
+		break;
+	}
+
+	return rx_pwr_all;
+}
+
+static void rtw8814a_query_phy_status(struct rtw_dev *rtwdev, u8 *phy_status,
+				      struct rtw_rx_pkt_stat *pkt_stat)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	struct rtw_jaguar_phy_status_rpt *rpt;
+	u8 gain[RTW_RF_PATH_MAX], rssi, i;
+	s8 rx_pwr_db, middle1, middle2;
+	s8 snr[RTW_RF_PATH_MAX];
+	s8 evm[RTW_RF_PATH_MAX];
+	u8 rfmode, subchannel;
+	u8 lna, vga;
+	s8 cfo[2];
+
+	rpt = (struct rtw_jaguar_phy_status_rpt *)phy_status;
+
+	pkt_stat->bw = RTW_CHANNEL_WIDTH_20;
+
+	if (pkt_stat->rate <= DESC_RATE11M) {
+		lna = le32_get_bits(rpt->w1, RTW_JGRPHY_W1_AGC_RPT_LNA_IDX);
+		vga = le32_get_bits(rpt->w1, RTW_JGRPHY_W1_AGC_RPT_VGA_IDX);
+
+		rx_pwr_db = rtw8814a_cck_rx_pwr(lna, vga);
+
+		pkt_stat->rx_power[RF_PATH_A] = rx_pwr_db;
+		pkt_stat->rssi = rtw_phy_rf_power_2_rssi(pkt_stat->rx_power, 1);
+		dm_info->rssi[RF_PATH_A] = pkt_stat->rssi;
+		pkt_stat->signal_power = rx_pwr_db;
+	} else { /* OFDM rate */
+		gain[RF_PATH_A] = le32_get_bits(rpt->w0, RTW_JGRPHY_W0_GAIN_A);
+		gain[RF_PATH_B] = le32_get_bits(rpt->w0, RTW_JGRPHY_W0_GAIN_B);
+		gain[RF_PATH_C] = le32_get_bits(rpt->w5, RTW_JGRPHY_W5_GAIN_C);
+		gain[RF_PATH_D] = le32_get_bits(rpt->w6, RTW_JGRPHY_W6_GAIN_D);
+
+		snr[RF_PATH_A] = le32_get_bits(rpt->w3, RTW_JGRPHY_W3_RXSNR_A);
+		snr[RF_PATH_B] = le32_get_bits(rpt->w4, RTW_JGRPHY_W4_RXSNR_B);
+		snr[RF_PATH_C] = le32_get_bits(rpt->w5, RTW_JGRPHY_W5_RXSNR_C);
+		snr[RF_PATH_D] = le32_get_bits(rpt->w5, RTW_JGRPHY_W5_RXSNR_D);
+
+		evm[RF_PATH_A] = le32_get_bits(rpt->w3, RTW_JGRPHY_W3_RXEVM_1);
+		evm[RF_PATH_B] = le32_get_bits(rpt->w3, RTW_JGRPHY_W3_RXEVM_2);
+		evm[RF_PATH_C] = le32_get_bits(rpt->w4, RTW_JGRPHY_W4_RXEVM_3);
+		evm[RF_PATH_D] = le32_get_bits(rpt->w5, RTW_JGRPHY_W5_RXEVM_4);
+
+		if (pkt_stat->rate <= DESC_RATE54M)
+			evm[RF_PATH_A] = le32_get_bits(rpt->w6,
+						       RTW_JGRPHY_W6_SIGEVM);
+
+		for (i = RF_PATH_A; i < RTW_RF_PATH_MAX; i++) {
+			pkt_stat->rx_power[i] = gain[i] - 110;
+
+			rssi = rtw_phy_rf_power_2_rssi(&pkt_stat->rx_power[i], 1);
+			dm_info->rssi[i] = rssi;
+
+			pkt_stat->rx_snr[i] = snr[i];
+			dm_info->rx_snr[i] = snr[i] >> 1;
+
+			pkt_stat->rx_evm[i] = evm[i];
+			evm[i] = max_t(s8, -127, evm[i]);
+			dm_info->rx_evm_dbm[i] = abs(evm[i]) >> 1;
+		}
+
+		rssi = rtw_phy_rf_power_2_rssi(pkt_stat->rx_power,
+					       RTW_RF_PATH_MAX);
+		pkt_stat->rssi = rssi;
+
+		/* When power saving is enabled the hardware sometimes
+		 * reports unbelievably high gain for paths A and C
+		 * (e.g. one frame 64 68 68 72, the next frame 106 66 88 72,
+		 * the next 66 66 68 72), so use the second lowest gain
+		 * instead of the highest.
+		 */
+		middle1 = max(min(gain[RF_PATH_A], gain[RF_PATH_B]),
+			      min(gain[RF_PATH_C], gain[RF_PATH_D]));
+		middle2 = min(max(gain[RF_PATH_A], gain[RF_PATH_B]),
+			      max(gain[RF_PATH_C], gain[RF_PATH_D]));
+		rx_pwr_db = min(middle1, middle2);
+		rx_pwr_db -= 110;
+		pkt_stat->signal_power = rx_pwr_db;
+
+		rfmode = le32_get_bits(rpt->w0, RTW_JGRPHY_W0_R_RFMOD);
+		subchannel = le32_get_bits(rpt->w0, RTW_JGRPHY_W0_SUB_CHNL);
+
+		if (rfmode == 1 && subchannel == 0) {
+			pkt_stat->bw = RTW_CHANNEL_WIDTH_40;
+		} else if (rfmode == 2) {
+			if (subchannel == 0)
+				pkt_stat->bw = RTW_CHANNEL_WIDTH_80;
+			else if (subchannel == 9 || subchannel == 10)
+				pkt_stat->bw = RTW_CHANNEL_WIDTH_40;
+		}
+
+		cfo[RF_PATH_A] = le32_get_bits(rpt->w2, RTW_JGRPHY_W2_CFO_TAIL_A);
+		cfo[RF_PATH_B] = le32_get_bits(rpt->w2, RTW_JGRPHY_W2_CFO_TAIL_B);
+
+		for (i = RF_PATH_A; i < 2; i++) {
+			pkt_stat->cfo_tail[i] = cfo[i];
+			dm_info->cfo_tail[i] = (cfo[i] * 5) >> 1;
+		}
+	}
+}
+
+static void
+rtw8814a_set_tx_power_index_by_rate(struct rtw_dev *rtwdev, u8 path, u8 rs)
+{
+	struct rtw_hal *hal = &rtwdev->hal;
+	u32 txagc_table_wd;
+	u8 rate, pwr_index;
+	int j;
+
+	for (j = 0; j < rtw_rate_size[rs]; j++) {
+		rate = rtw_rate_section[rs][j];
+
+		pwr_index = hal->tx_pwr_tbl[path][rate] + 2;
+		if (pwr_index > rtwdev->chip->max_power_index)
+			pwr_index = rtwdev->chip->max_power_index;
+
+		txagc_table_wd = 0x00801000;
+		txagc_table_wd |= (pwr_index << 24) | (path << 8) | rate;
+
+		rtw_write32(rtwdev, REG_AGC_TBL, txagc_table_wd);
+
+		/* first time to turn on the txagc table
+		 * second to write the addr0
+		 */
+		if (rate == DESC_RATE1M)
+			rtw_write32(rtwdev, REG_AGC_TBL, txagc_table_wd);
+	}
+}
+
+static void rtw8814a_set_tx_power_index(struct rtw_dev *rtwdev)
+{
+	struct rtw_hal *hal = &rtwdev->hal;
+	int path;
+
+	for (path = 0; path < hal->rf_path_num; path++) {
+		if (hal->current_band_type == RTW_BAND_2G)
+			rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+							    RTW_RATE_SECTION_CCK);
+
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_OFDM);
+
+		if (test_bit(RTW_FLAG_SCANNING, rtwdev->flags))
+			continue;
+
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_HT_1S);
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_VHT_1S);
+
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_HT_2S);
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_VHT_2S);
+
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_HT_3S);
+		rtw8814a_set_tx_power_index_by_rate(rtwdev, path,
+						    RTW_RATE_SECTION_VHT_3S);
+	}
+}
+
+static void rtw8814a_cfg_ldo25(struct rtw_dev *rtwdev, bool enable)
+{
+}
+
+static void rtw8814a_false_alarm_statistics(struct rtw_dev *rtwdev)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	u32 cck_fa_cnt, ofdm_fa_cnt;
+	u32 crc32_cnt, cca32_cnt;
+	u32 cck_enable;
+
+	cck_enable = rtw_read32(rtwdev, REG_RXPSEL) & BIT(28);
+	cck_fa_cnt = rtw_read16(rtwdev, REG_FA_CCK);
+	ofdm_fa_cnt = rtw_read16(rtwdev, REG_FA_OFDM);
+
+	dm_info->cck_fa_cnt = cck_fa_cnt;
+	dm_info->ofdm_fa_cnt = ofdm_fa_cnt;
+	dm_info->total_fa_cnt = ofdm_fa_cnt;
+	if (cck_enable)
+		dm_info->total_fa_cnt += cck_fa_cnt;
+
+	crc32_cnt = rtw_read32(rtwdev, REG_CRC_CCK);
+	dm_info->cck_ok_cnt = u32_get_bits(crc32_cnt, MASKLWORD);
+	dm_info->cck_err_cnt = u32_get_bits(crc32_cnt, MASKHWORD);
+
+	crc32_cnt = rtw_read32(rtwdev, REG_CRC_OFDM);
+	dm_info->ofdm_ok_cnt = u32_get_bits(crc32_cnt, MASKLWORD);
+	dm_info->ofdm_err_cnt = u32_get_bits(crc32_cnt, MASKHWORD);
+
+	crc32_cnt = rtw_read32(rtwdev, REG_CRC_HT);
+	dm_info->ht_ok_cnt = u32_get_bits(crc32_cnt, MASKLWORD);
+	dm_info->ht_err_cnt = u32_get_bits(crc32_cnt, MASKHWORD);
+
+	crc32_cnt = rtw_read32(rtwdev, REG_CRC_VHT);
+	dm_info->vht_ok_cnt = u32_get_bits(crc32_cnt, MASKLWORD);
+	dm_info->vht_err_cnt = u32_get_bits(crc32_cnt, MASKHWORD);
+
+	cca32_cnt = rtw_read32(rtwdev, REG_CCA_OFDM);
+	dm_info->ofdm_cca_cnt = u32_get_bits(cca32_cnt, MASKHWORD);
+	dm_info->total_cca_cnt = dm_info->ofdm_cca_cnt;
+	if (cck_enable) {
+		cca32_cnt = rtw_read32(rtwdev, REG_CCA_CCK);
+		dm_info->cck_cca_cnt = u32_get_bits(cca32_cnt, MASKLWORD);
+		dm_info->total_cca_cnt += dm_info->cck_cca_cnt;
+	}
+
+	rtw_write32_set(rtwdev, REG_FAS, BIT(17));
+	rtw_write32_clr(rtwdev, REG_FAS, BIT(17));
+	rtw_write32_clr(rtwdev, REG_CCK0_FAREPORT, BIT(15));
+	rtw_write32_set(rtwdev, REG_CCK0_FAREPORT, BIT(15));
+	rtw_write32_set(rtwdev, REG_CNTRST, BIT(0));
+	rtw_write32_clr(rtwdev, REG_CNTRST, BIT(0));
+}
+
+#define MAC_REG_NUM_8814 2
+#define BB_REG_NUM_8814 14
+#define RF_REG_NUM_8814 1
+
+static void rtw8814a_iqk_backup_mac_bb(struct rtw_dev *rtwdev,
+				       u32 *mac_backup, u32 *bb_backup,
+				       const u32 *mac_regs,
+				       const u32 *bb_regs)
+{
+	u32 i;
+
+	/* save MACBB default value */
+	for (i = 0; i < MAC_REG_NUM_8814; i++)
+		mac_backup[i] = rtw_read32(rtwdev, mac_regs[i]);
+
+	for (i = 0; i < BB_REG_NUM_8814; i++)
+		bb_backup[i] = rtw_read32(rtwdev, bb_regs[i]);
+}
+
+static void rtw8814a_iqk_backup_rf(struct rtw_dev *rtwdev,
+				   u32 rf_backup[][4], const u32 *rf_regs)
+{
+	u32 i;
+
+	/* Save RF Parameters */
+	for (i = 0; i < RF_REG_NUM_8814; i++) {
+		rf_backup[i][RF_PATH_A] = rtw_read_rf(rtwdev, RF_PATH_A,
+						      rf_regs[i], RFREG_MASK);
+		rf_backup[i][RF_PATH_B] = rtw_read_rf(rtwdev, RF_PATH_B,
+						      rf_regs[i], RFREG_MASK);
+		rf_backup[i][RF_PATH_C] = rtw_read_rf(rtwdev, RF_PATH_C,
+						      rf_regs[i], RFREG_MASK);
+		rf_backup[i][RF_PATH_D] = rtw_read_rf(rtwdev, RF_PATH_D,
+						      rf_regs[i], RFREG_MASK);
+	}
+}
+
+static void rtw8814a_iqk_afe_setting(struct rtw_dev *rtwdev, bool do_iqk)
+{
+	if (do_iqk) {
+		/* IQK AFE setting RX_WAIT_CCA mode */
+		rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x0e808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x0e808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x0e808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x0e808003);
+	} else {
+		rtw_write32(rtwdev, REG_AFE_PWR1_A, 0x07808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_B, 0x07808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_C, 0x07808003);
+		rtw_write32(rtwdev, REG_AFE_PWR1_D, 0x07808003);
+	}
+
+	rtw_write32_mask(rtwdev, REG_DAC_RSTB, BIT(13), 0x1);
+
+	rtw_write8_set(rtwdev, REG_GNT_BT, BIT(2) | BIT(1));
+	rtw_write8_clr(rtwdev, REG_GNT_BT, BIT(2) | BIT(1));
+
+	rtw_write32_set(rtwdev, REG_CCK_RPT_FORMAT, BIT(2));
+	rtw_write32_clr(rtwdev, REG_CCK_RPT_FORMAT, BIT(2));
+}
+
+static void rtw8814a_iqk_restore_mac_bb(struct rtw_dev *rtwdev,
+					u32 *mac_backup, u32 *bb_backup,
+					const u32 *mac_regs,
+					const u32 *bb_regs)
+{
+	u32 i;
+
+	/* Reload MacBB Parameters */
+	for (i = 0; i < MAC_REG_NUM_8814; i++)
+		rtw_write32(rtwdev, mac_regs[i], mac_backup[i]);
+
+	for (i = 0; i < BB_REG_NUM_8814; i++)
+		rtw_write32(rtwdev, bb_regs[i], bb_backup[i]);
+}
+
+static void rtw8814a_iqk_restore_rf(struct rtw_dev *rtwdev,
+				    const u32 rf_backup[][4],
+				    const u32 *rf_regs)
+{
+	u32 i;
+
+	rtw_write_rf(rtwdev, RF_PATH_A, RF_LUTWE, RFREG_MASK, 0x0);
+	rtw_write_rf(rtwdev, RF_PATH_B, RF_LUTWE, RFREG_MASK, 0x0);
+	rtw_write_rf(rtwdev, RF_PATH_C, RF_LUTWE, RFREG_MASK, 0x0);
+	rtw_write_rf(rtwdev, RF_PATH_D, RF_LUTWE, RFREG_MASK, 0x0);
+
+	rtw_write_rf(rtwdev, RF_PATH_A, RF_RXBB2, RFREG_MASK, 0x88001);
+	rtw_write_rf(rtwdev, RF_PATH_B, RF_RXBB2, RFREG_MASK, 0x88001);
+	rtw_write_rf(rtwdev, RF_PATH_C, RF_RXBB2, RFREG_MASK, 0x88001);
+	rtw_write_rf(rtwdev, RF_PATH_D, RF_RXBB2, RFREG_MASK, 0x88001);
+
+	for (i = 0; i < RF_REG_NUM_8814; i++) {
+		rtw_write_rf(rtwdev, RF_PATH_A, rf_regs[i],
+			     RFREG_MASK, rf_backup[i][RF_PATH_A]);
+		rtw_write_rf(rtwdev, RF_PATH_B, rf_regs[i],
+			     RFREG_MASK, rf_backup[i][RF_PATH_B]);
+		rtw_write_rf(rtwdev, RF_PATH_C, rf_regs[i],
+			     RFREG_MASK, rf_backup[i][RF_PATH_C]);
+		rtw_write_rf(rtwdev, RF_PATH_D, rf_regs[i],
+			     RFREG_MASK, rf_backup[i][RF_PATH_D]);
+	}
+}
+
+static void rtw8814a_iqk_reset_nctl(struct rtw_dev *rtwdev)
+{
+	rtw_write32(rtwdev, 0x1b00, 0xf8000000);
+	rtw_write32(rtwdev, 0x1b80, 0x00000006);
+
+	rtw_write32(rtwdev, 0x1b00, 0xf8000000);
+	rtw_write32(rtwdev, 0x1b80, 0x00000002);
+}
+
+static void rtw8814a_iqk_configure_mac(struct rtw_dev *rtwdev)
+{
+	rtw_write8(rtwdev, REG_TXPAUSE, 0x3f);
+	rtw_write32_clr(rtwdev, REG_BCN_CTRL,
+			(BIT_EN_BCN_FUNCTION << 8) | BIT_EN_BCN_FUNCTION);
+
+	/* RX ante off */
+	rtw_write8(rtwdev, REG_RXPSEL, 0x00);
+	/* CCA off */
+	rtw_write32_mask(rtwdev, REG_CCA2ND, 0xf, 0xe);
+	/* CCK RX path off */
+	rtw_write32_set(rtwdev, REG_PRECTRL, BIT_IQ_WGT);
+	rtw_write32(rtwdev, REG_RFE_PINMUX_A, 0x77777777);
+	rtw_write32(rtwdev, REG_RFE_PINMUX_B, 0x77777777);
+	rtw_write32(rtwdev, REG_RFE_PINMUX_C, 0x77777777);
+	rtw_write32(rtwdev, REG_RFE_PINMUX_D, 0x77777777);
+	rtw_write32_mask(rtwdev, REG_RFE_INVSEL_D, BIT_RFE_SELSW0_D, 0x77);
+	rtw_write32_mask(rtwdev, REG_PSD, BIT_PSD_INI, 0x0);
+
+	rtw_write32_mask(rtwdev, REG_RFE_INV0, 0xf, 0x0);
+}
+
+static void rtw8814a_lok_one_shot(struct rtw_dev *rtwdev, u8 path)
+{
+	u32 lok_temp1, lok_temp2;
+	bool lok_ready;
+	u8 ii;
+
+	/* ADC Clock source */
+	rtw_write32_mask(rtwdev, REG_FAS, BIT(21) | BIT(20), path);
+	/* LOK: CMD ID = 0
+	 * {0xf8000011, 0xf8000021, 0xf8000041, 0xf8000081}
+	 */
+	rtw_write32(rtwdev, 0x1b00, 0xf8000001 | (BIT(path) << 4));
+
+	usleep_range(1000, 1100);
+
+	if (read_poll_timeout(!rtw_read32_mask, lok_ready, lok_ready,
+			      1000, 10000, false,
+			      rtwdev, 0x1b00, BIT(0))) {
+		rtw_dbg(rtwdev, RTW_DBG_RFK, "==>S%d LOK timed out\n", path);
+
+		rtw8814a_iqk_reset_nctl(rtwdev);
+
+		rtw_write_rf(rtwdev, path, RF_DTXLOK, RFREG_MASK, 0x08400);
+
+		return;
+	}
+
+	rtw_write32(rtwdev, 0x1b00, 0xf8000000 | (path << 1));
+	rtw_write32(rtwdev, 0x1bd4, 0x003f0001);
+
+	lok_temp2 = rtw_read32_mask(rtwdev, 0x1bfc, 0x003e0000);
+	lok_temp2 = (lok_temp2 + 0x10) & 0x1f;
+
+	lok_temp1 = rtw_read32_mask(rtwdev, 0x1bfc, 0x0000003e);
+	lok_temp1 = (lok_temp1 + 0x10) & 0x1f;
+
+	for (ii = 1; ii < 5; ii++) {
+		lok_temp1 += (lok_temp1 & BIT(4 - ii)) << (ii * 2);
+		lok_temp2 += (lok_temp2 & BIT(4 - ii)) << (ii * 2);
+	}
+
+	rtw_dbg(rtwdev, RTW_DBG_RFK,
+		"path %d lok_temp1 = %#x, lok_temp2 = %#x\n",
+		path, lok_temp1 >> 4, lok_temp2 >> 4);
+
+	rtw_write_rf(rtwdev, path, RF_DTXLOK, 0x07c00, lok_temp1 >> 4);
+	rtw_write_rf(rtwdev, path, RF_DTXLOK, 0xf8000, lok_temp2 >> 4);
+}
+
+static void rtw8814a_iqk_tx_one_shot(struct rtw_dev *rtwdev, u8 path,
+				     u32 *tx_matrix, bool *tx_ok)
+{
+	u8 bw = rtwdev->hal.current_band_width;
+	u8 cal_retry;
+	u32 iqk_cmd;
+
+	for (cal_retry = 0; cal_retry < 4; cal_retry++) {
+		rtw_write32_mask(rtwdev, REG_FAS, BIT(21) | BIT(20), path);
+
+		iqk_cmd = 0xf8000001 | ((bw + 3) << 8) | (BIT(path) << 4);
+
+		rtw_dbg(rtwdev, RTW_DBG_RFK, "TXK_Trigger = %#x\n", iqk_cmd);
+
+		rtw_write32(rtwdev, 0x1b00, iqk_cmd);
+
+		usleep_range(10000, 11000);
+
+		if (read_poll_timeout(!rtw_read32_mask, *tx_ok, *tx_ok,
+				      1000, 20000, false,
+				      rtwdev, 0x1b00, BIT(0))) {
+			rtw_dbg(rtwdev, RTW_DBG_RFK,
+				"tx iqk S%d timed out\n", path);
+
+			rtw8814a_iqk_reset_nctl(rtwdev);
+		} else {
+			*tx_ok = !rtw_read32_mask(rtwdev, 0x1b08, BIT(26));
+
+			if (*tx_ok)
+				break;
+		}
+	}
+
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d tx ==> 0x1b00 = 0x%x\n",
+		path, rtw_read32(rtwdev, 0x1b00));
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d tx ==> 0x1b08 = 0x%x\n",
+		path, rtw_read32(rtwdev, 0x1b08));
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d tx ==> cal_retry = %x\n",
+		path, cal_retry);
+
+	rtw_write32(rtwdev, 0x1b00, 0xf8000000 | (path << 1));
+
+	if (*tx_ok) {
+		*tx_matrix = rtw_read32(rtwdev, 0x1b38);
+
+		rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d_IQC = 0x%x\n",
+			path, *tx_matrix);
+	}
+}
+
+static void rtw8814a_iqk_rx_one_shot(struct rtw_dev *rtwdev, u8 path,
+				     u32 *tx_matrix, bool *tx_ok)
+{
+	static const u16 iqk_apply[RTW_RF_PATH_MAX] = {
+		REG_TXAGCIDX, REG_TX_AGC_B, REG_TX_AGC_C, REG_TX_AGC_D
+	};
+	u8 band = rtwdev->hal.current_band_type;
+	u8 bw = rtwdev->hal.current_band_width;
+	u32 rx_matrix;
+	u8 cal_retry;
+	u32 iqk_cmd;
+	bool rx_ok;
+
+	for (cal_retry = 0; cal_retry < 4; cal_retry++) {
+		rtw_write32_mask(rtwdev, REG_FAS, BIT(21) | BIT(20), path);
+
+		if (band == RTW_BAND_2G) {
+			rtw_write_rf(rtwdev, path, RF_LUTDBG, BIT(11), 0x1);
+			rtw_write_rf(rtwdev, path, RF_GAINTX, 0xfffff, 0x51ce1);
+
+			switch (path) {
+			case 0:
+			case 1:
+				rtw_write32(rtwdev, REG_RFE_PINMUX_B,
+					    0x54775477);
+				break;
+			case 2:
+				rtw_write32(rtwdev, REG_RFE_PINMUX_C,
+					    0x54775477);
+				break;
+			case 3:
+				rtw_write32(rtwdev, REG_RFE_INVSEL_D, 0x75400000);
+				rtw_write32(rtwdev, REG_RFE_PINMUX_D,
+					    0x77777777);
+				break;
+			}
+		}
+
+		iqk_cmd = 0xf8000001 | ((9 - bw) << 8) | (BIT(path) << 4);
+
+		rtw_dbg(rtwdev, RTW_DBG_RFK, "RXK_Trigger = 0x%x\n", iqk_cmd);
+
+		rtw_write32(rtwdev, 0x1b00, iqk_cmd);
+
+		usleep_range(10000, 11000);
+
+		if (read_poll_timeout(!rtw_read32_mask, rx_ok, rx_ok,
+				      1000, 20000, false,
+				      rtwdev, 0x1b00, BIT(0))) {
+			rtw_dbg(rtwdev, RTW_DBG_RFK,
+				"rx iqk S%d timed out\n", path);
+
+			rtw8814a_iqk_reset_nctl(rtwdev);
+		} else {
+			rx_ok = !rtw_read32_mask(rtwdev, 0x1b08, BIT(26));
+
+			if (rx_ok)
+				break;
+		}
+	}
+
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d rx ==> 0x1b00 = 0x%x\n",
+		path, rtw_read32(rtwdev, 0x1b00));
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d rx ==> 0x1b08 = 0x%x\n",
+		path, rtw_read32(rtwdev, 0x1b08));
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d rx ==> cal_retry = %x\n",
+		path, cal_retry);
+
+	rtw_write32(rtwdev, 0x1b00, 0xf8000000 | (path << 1));
+
+	if (rx_ok) {
+		rtw_write32(rtwdev, 0x1b3c, 0x20000000);
+		rx_matrix = rtw_read32(rtwdev, 0x1b3c);
+
+		rtw_dbg(rtwdev, RTW_DBG_RFK, "S%d_IQC = 0x%x\n",
+			path, rx_matrix);
+	}
+
+	if (*tx_ok)
+		rtw_write32(rtwdev, 0x1b38, *tx_matrix);
+	else
+		rtw_write32_mask(rtwdev, iqk_apply[path], BIT(0), 0x0);
+
+	if (!rx_ok)
+		rtw_write32_mask(rtwdev, iqk_apply[path],
+				 BIT(11) | BIT(10), 0x0);
+
+	if (band == RTW_BAND_2G)
+		rtw_write_rf(rtwdev, path, RF_LUTDBG, BIT(11), 0x0);
+}
+
+static void rtw8814a_iqk(struct rtw_dev *rtwdev)
+{
+	u8 band = rtwdev->hal.current_band_type;
+	u8 bw = rtwdev->hal.current_band_width;
+	u32 tx_matrix[RTW_RF_PATH_MAX];
+	bool tx_ok[RTW_RF_PATH_MAX];
+	u8 path;
+
+	rtw_dbg(rtwdev, RTW_DBG_RFK, "IQK band = %d GHz bw = %d MHz\n",
+		band == RTW_BAND_2G ? 2 : 5, (1 << (bw + 1)) * 10);
+
+	rtw_write_rf(rtwdev, RF_PATH_A, RF_TXMOD, BIT(19), 0x1);
+	rtw_write_rf(rtwdev, RF_PATH_B, RF_TXMOD, BIT(19), 0x1);
+	rtw_write_rf(rtwdev, RF_PATH_C, RF_TXMOD, BIT(19), 0x1);
+	rtw_write_rf(rtwdev, RF_PATH_D, RF_TXMOD, BIT(19), 0x1);
+
+	rtw_write32_mask(rtwdev, REG_TXAGCIDX,
+			 (BIT(11) | BIT(10) | BIT(0)), 0x401);
+	rtw_write32_mask(rtwdev, REG_TX_AGC_B,
+			 (BIT(11) | BIT(10) | BIT(0)), 0x401);
+	rtw_write32_mask(rtwdev, REG_TX_AGC_C,
+			 (BIT(11) | BIT(10) | BIT(0)), 0x401);
+	rtw_write32_mask(rtwdev, REG_TX_AGC_D,
+			 (BIT(11) | BIT(10) | BIT(0)), 0x401);
+
+	if (band == RTW_BAND_5G)
+		rtw_write32(rtwdev, 0x1b00, 0xf8000ff1);
+	else
+		rtw_write32(rtwdev, 0x1b00, 0xf8000ef1);
+
+	usleep_range(1000, 1100);
+
+	rtw_write32(rtwdev, 0x810, 0x20101063);
+	rtw_write32(rtwdev, REG_DAC_RSTB, 0x0B00C000);
+
+	for (path = RF_PATH_A; path < RTW_RF_PATH_MAX; path++)
+		rtw8814a_lok_one_shot(rtwdev, path);
+
+	for (path = RF_PATH_A; path < RTW_RF_PATH_MAX; path++)
+		rtw8814a_iqk_tx_one_shot(rtwdev, path,
+					 &tx_matrix[path], &tx_ok[path]);
+
+	for (path = RF_PATH_A; path < RTW_RF_PATH_MAX; path++)
+		rtw8814a_iqk_rx_one_shot(rtwdev, path,
+					 &tx_matrix[path], &tx_ok[path]);
+}
+
+static void rtw8814a_do_iqk(struct rtw_dev *rtwdev)
+{
+	static const u32 backup_mac_reg[MAC_REG_NUM_8814] = {0x520, 0x550};
+	static const u32 backup_bb_reg[BB_REG_NUM_8814] = {
+		0xa14, 0x808, 0x838, 0x90c, 0x810, 0xcb0, 0xeb0,
+		0x18b4, 0x1ab4, 0x1abc, 0x9a4, 0x764, 0xcbc, 0x910
+	};
+	static const u32 backup_rf_reg[RF_REG_NUM_8814] = {0x0};
+	u32 rf_backup[RF_REG_NUM_8814][RTW_RF_PATH_MAX];
+	u32 mac_backup[MAC_REG_NUM_8814];
+	u32 bb_backup[BB_REG_NUM_8814];
+
+	rtw8814a_iqk_backup_mac_bb(rtwdev, mac_backup, bb_backup,
+				   backup_mac_reg, backup_bb_reg);
+	rtw8814a_iqk_afe_setting(rtwdev, true);
+	rtw8814a_iqk_backup_rf(rtwdev, rf_backup, backup_rf_reg);
+	rtw8814a_iqk_configure_mac(rtwdev);
+	rtw8814a_iqk(rtwdev);
+	rtw8814a_iqk_reset_nctl(rtwdev); /* for 3-wire to BB use */
+	rtw8814a_iqk_afe_setting(rtwdev, false);
+	rtw8814a_iqk_restore_mac_bb(rtwdev, mac_backup, bb_backup,
+				    backup_mac_reg, backup_bb_reg);
+	rtw8814a_iqk_restore_rf(rtwdev, rf_backup, backup_rf_reg);
+}
+
+static void rtw8814a_phy_calibration(struct rtw_dev *rtwdev)
+{
+	rtw8814a_do_iqk(rtwdev);
+}
+
+static void rtw8814a_coex_cfg_init(struct rtw_dev *rtwdev)
+{
+}
+
+static void rtw8814a_coex_cfg_ant_switch(struct rtw_dev *rtwdev, u8 ctrl_type,
+					 u8 pos_type)
+{
+	/* Override rtw_coex_coex_ctrl_owner(). RF path C does not
+	 * function when BIT_LTE_MUX_CTRL_PATH is set.
+	 */
+	rtw_write8_clr(rtwdev, REG_SYS_SDIO_CTRL + 3,
+		       BIT_LTE_MUX_CTRL_PATH >> 24);
+}
+
+static void rtw8814a_coex_cfg_gnt_fix(struct rtw_dev *rtwdev)
+{
+}
+
+static void rtw8814a_coex_cfg_gnt_debug(struct rtw_dev *rtwdev)
+{
+}
+
+static void rtw8814a_coex_cfg_rfe_type(struct rtw_dev *rtwdev)
+{
+	struct rtw_coex *coex = &rtwdev->coex;
+	struct rtw_coex_rfe *coex_rfe = &coex->rfe;
+
+	/* Only needed to make rtw8814a_coex_cfg_ant_switch() run. */
+	coex_rfe->ant_switch_exist = true;
+}
+
+static void rtw8814a_coex_cfg_wl_tx_power(struct rtw_dev *rtwdev, u8 wl_pwr)
+{
+}
+
+static void rtw8814a_coex_cfg_wl_rx_gain(struct rtw_dev *rtwdev, bool low_gain)
+{
+}
+
+static void rtw8814a_txagc_swing_offset(struct rtw_dev *rtwdev, u8 path,
+					u8 tx_pwr_idx_offset,
+					s8 *txagc_idx, u8 *swing_idx)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	u8 swing_upper_bound = dm_info->default_ofdm_index + 10;
+	s8 delta_pwr_idx = dm_info->delta_power_index[path];
+	u8 swing_index = dm_info->default_ofdm_index;
+	u8 max_tx_pwr_idx_offset = 0xf;
+	u8 swing_lower_bound = 0;
+	s8 agc_index = 0;
+
+	tx_pwr_idx_offset = min_t(u8, tx_pwr_idx_offset, max_tx_pwr_idx_offset);
+
+	if (delta_pwr_idx >= 0) {
+		if (delta_pwr_idx <= tx_pwr_idx_offset) {
+			agc_index = delta_pwr_idx;
+			swing_index = dm_info->default_ofdm_index;
+		} else if (delta_pwr_idx > tx_pwr_idx_offset) {
+			agc_index = tx_pwr_idx_offset;
+			swing_index = dm_info->default_ofdm_index +
+					delta_pwr_idx - tx_pwr_idx_offset;
+			swing_index = min_t(u8, swing_index, swing_upper_bound);
+		}
+	} else {
+		if (dm_info->default_ofdm_index > abs(delta_pwr_idx))
+			swing_index =
+				dm_info->default_ofdm_index + delta_pwr_idx;
+		else
+			swing_index = swing_lower_bound;
+		swing_index = max_t(u8, swing_index, swing_lower_bound);
+
+		agc_index = 0;
+	}
+
+	if (swing_index >= RTW_TXSCALE_SIZE) {
+		rtw_warn(rtwdev, "swing index overflow\n");
+		swing_index = RTW_TXSCALE_SIZE - 1;
+	}
+	*txagc_idx = agc_index;
+	*swing_idx = swing_index;
+}
+
+static void rtw8814a_pwrtrack_set_pwr(struct rtw_dev *rtwdev, u8 path,
+				      u8 pwr_idx_offset)
+{
+	static const u32 txagc_reg[RTW_RF_PATH_MAX] = {
+		REG_TX_AGC_A, REG_TX_AGC_B, REG_TX_AGC_C, REG_TX_AGC_D
+	};
+	static const u32 txscale_reg[RTW_RF_PATH_MAX] = {
+		REG_TXSCALE_A, REG_TXSCALE_B, REG_TXSCALE_C, REG_TXSCALE_D
+	};
+	s8 txagc_idx;
+	u8 swing_idx;
+
+	rtw8814a_txagc_swing_offset(rtwdev, path, pwr_idx_offset,
+				    &txagc_idx, &swing_idx);
+	rtw_write32_mask(rtwdev, txagc_reg[path], GENMASK(29, 25),
+			 txagc_idx);
+	rtw_write32_mask(rtwdev, txscale_reg[path], BB_SWING_MASK,
+			 rtw8814a_txscale_tbl[swing_idx]);
+}
+
+static void rtw8814a_pwrtrack_set(struct rtw_dev *rtwdev, u8 path)
+{
+	u8 max_pwr_idx = rtwdev->chip->max_power_index;
+	u8 band_width = rtwdev->hal.current_band_width;
+	u8 channel = rtwdev->hal.current_channel;
+	u8 tx_rate = rtwdev->dm_info.tx_rate;
+	u8 regd = rtw_regd_get(rtwdev);
+	u8 pwr_idx_offset, tx_pwr_idx;
+
+	tx_pwr_idx = rtw_phy_get_tx_power_index(rtwdev, path, tx_rate,
+						band_width, channel, regd);
+
+	tx_pwr_idx = min_t(u8, tx_pwr_idx, max_pwr_idx);
+
+	pwr_idx_offset = max_pwr_idx - tx_pwr_idx;
+
+	rtw8814a_pwrtrack_set_pwr(rtwdev, path, pwr_idx_offset);
+}
+
+static void rtw8814a_phy_pwrtrack_path(struct rtw_dev *rtwdev,
+				       struct rtw_swing_table *swing_table,
+				       u8 path)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	u8 power_idx_cur, power_idx_last;
+	u8 delta;
+
+	/* 8814A only has one thermal meter at PATH A */
+	delta = rtw_phy_pwrtrack_get_delta(rtwdev, RF_PATH_A);
+
+	power_idx_last = dm_info->delta_power_index[path];
+	power_idx_cur = rtw_phy_pwrtrack_get_pwridx(rtwdev, swing_table,
+						    path, RF_PATH_A, delta);
+
+	/* if delta of power indexes are the same, just skip */
+	if (power_idx_cur == power_idx_last)
+		return;
+
+	dm_info->delta_power_index[path] = power_idx_cur;
+	rtw8814a_pwrtrack_set(rtwdev, path);
+}
+
+static void rtw8814a_phy_pwrtrack(struct rtw_dev *rtwdev)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+	struct rtw_swing_table swing_table;
+	u8 thermal_value, path;
+
+	rtw_phy_config_swing_table(rtwdev, &swing_table);
+
+	if (rtwdev->efuse.thermal_meter[RF_PATH_A] == 0xff)
+		return;
+
+	thermal_value = rtw_read_rf(rtwdev, RF_PATH_A, RF_T_METER, 0xfc00);
+
+	rtw_phy_pwrtrack_avg(rtwdev, thermal_value, RF_PATH_A);
+
+	if (dm_info->pwr_trk_init_trigger)
+		dm_info->pwr_trk_init_trigger = false;
+	else if (!rtw_phy_pwrtrack_thermal_changed(rtwdev, thermal_value,
+						   RF_PATH_A))
+		goto iqk;
+
+	for (path = RF_PATH_A; path < rtwdev->hal.rf_path_num; path++)
+		rtw8814a_phy_pwrtrack_path(rtwdev, &swing_table, path);
+
+iqk:
+	if (rtw_phy_pwrtrack_need_iqk(rtwdev))
+		rtw8814a_do_iqk(rtwdev);
+}
+
+static void rtw8814a_pwr_track(struct rtw_dev *rtwdev)
+{
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+
+	if (!dm_info->pwr_trk_triggered) {
+		rtw_write_rf(rtwdev, RF_PATH_A, RF_T_METER,
+			     GENMASK(17, 16), 0x03);
+		dm_info->pwr_trk_triggered = true;
+		return;
+	}
+
+	rtw8814a_phy_pwrtrack(rtwdev);
+	dm_info->pwr_trk_triggered = false;
+}
+
+static void rtw8814a_phy_cck_pd_set(struct rtw_dev *rtwdev, u8 new_lvl)
+{
+	static const u8 pd[CCK_PD_LV_MAX] = {0x40, 0x83, 0xcd, 0xdd, 0xed};
+	struct rtw_dm_info *dm_info = &rtwdev->dm_info;
+
+	/* Override rtw_phy_cck_pd_lv_link(). It implements something
+	 * like type 2/3/4. We need type 1 here.
+	 */
+	if (rtw_is_assoc(rtwdev)) {
+		if (dm_info->min_rssi > 60) {
+			new_lvl = CCK_PD_LV3;
+		} else if (dm_info->min_rssi > 35) {
+			new_lvl = CCK_PD_LV2;
+		} else if (dm_info->min_rssi > 20) {
+			if (dm_info->cck_fa_avg > 500)
+				new_lvl = CCK_PD_LV2;
+			else if (dm_info->cck_fa_avg < 250)
+				new_lvl = CCK_PD_LV1;
+			else
+				return;
+		} else {
+			new_lvl = CCK_PD_LV1;
+		}
+	}
+
+	rtw_dbg(rtwdev, RTW_DBG_PHY, "lv: (%d) -> (%d)\n",
+		dm_info->cck_pd_lv[RTW_CHANNEL_WIDTH_20][RF_PATH_A], new_lvl);
+
+	if (dm_info->cck_pd_lv[RTW_CHANNEL_WIDTH_20][RF_PATH_A] == new_lvl)
+		return;
+
+	dm_info->cck_fa_avg = CCK_FA_AVG_RESET;
+	dm_info->cck_pd_lv[RTW_CHANNEL_WIDTH_20][RF_PATH_A] = new_lvl;
+
+	rtw_write8(rtwdev, REG_CCK_PD_TH, pd[new_lvl]);
+}
+
+static void rtw8814a_led_set(struct led_classdev *led,
+			     enum led_brightness brightness)
+{
+	struct rtw_dev *rtwdev = container_of(led, struct rtw_dev, led_cdev);
+	u32 led_gpio_cfg;
+
+	led_gpio_cfg = rtw_read32(rtwdev, REG_GPIO_PIN_CTRL_2);
+	led_gpio_cfg |= BIT(16) | BIT(17) | BIT(21) | BIT(22);
+
+	if (brightness == LED_OFF) {
+		led_gpio_cfg |= BIT(8) | BIT(9) | BIT(13) | BIT(14);
+	} else {
+		led_gpio_cfg &= ~(BIT(8) | BIT(9) | BIT(13) | BIT(14));
+		led_gpio_cfg &= ~(BIT(0) | BIT(1) | BIT(5) | BIT(6));
+	}
+
+	rtw_write32(rtwdev, REG_GPIO_PIN_CTRL_2, led_gpio_cfg);
+}
+
+static void rtw8814a_fill_txdesc_checksum(struct rtw_dev *rtwdev,
+					  struct rtw_tx_pkt_info *pkt_info,
+					  u8 *txdesc)
+{
+	size_t words = 32 / 2; /* calculate the first 32 bytes (16 words) */
+
+	fill_txdesc_checksum_common(txdesc, words);
+}
+
+static const struct rtw_chip_ops rtw8814a_ops = {
+	.power_on		= rtw_power_on,
+	.power_off		= rtw_power_off,
+	.phy_set_param		= rtw8814a_phy_set_param,
+	.read_efuse		= rtw8814a_read_efuse,
+	.query_phy_status	= rtw8814a_query_phy_status,
+	.set_channel		= rtw8814a_set_channel,
+	.mac_init		= rtw8814a_mac_init,
+	.read_rf		= rtw_phy_read_rf,
+	.write_rf		= rtw_phy_write_rf_reg_sipi,
+	.set_tx_power_index	= rtw8814a_set_tx_power_index,
+	.set_antenna		= NULL,
+	.cfg_ldo25		= rtw8814a_cfg_ldo25,
+	.efuse_grant		= rtw8814a_efuse_grant,
+	.false_alarm_statistics	= rtw8814a_false_alarm_statistics,
+	.phy_calibration	= rtw8814a_phy_calibration,
+	.cck_pd_set		= rtw8814a_phy_cck_pd_set,
+	.pwr_track		= rtw8814a_pwr_track,
+	.config_bfee		= NULL,
+	.set_gid_table		= NULL,
+	.cfg_csi_rate		= NULL,
+	.led_set		= rtw8814a_led_set,
+	.fill_txdesc_checksum	= rtw8814a_fill_txdesc_checksum,
+
+	.coex_set_init		= rtw8814a_coex_cfg_init,
+	.coex_set_ant_switch	= rtw8814a_coex_cfg_ant_switch,
+	.coex_set_gnt_fix	= rtw8814a_coex_cfg_gnt_fix,
+	.coex_set_gnt_debug	= rtw8814a_coex_cfg_gnt_debug,
+	.coex_set_rfe_type	= rtw8814a_coex_cfg_rfe_type,
+	.coex_set_wl_tx_power	= rtw8814a_coex_cfg_wl_tx_power,
+	.coex_set_wl_rx_gain	= rtw8814a_coex_cfg_wl_rx_gain,
+};
+
+static const struct rtw_rqpn rqpn_table_8814a[] = {
+	/* SDIO */
+	{RTW_DMA_MAPPING_NORMAL, RTW_DMA_MAPPING_NORMAL, /* vo vi */
+	 RTW_DMA_MAPPING_LOW, RTW_DMA_MAPPING_LOW,	 /* be bk */
+	 RTW_DMA_MAPPING_EXTRA, RTW_DMA_MAPPING_HIGH},	 /* mg hi */
+	/* PCIE */
+	{RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_NORMAL,
+	 RTW_DMA_MAPPING_LOW, RTW_DMA_MAPPING_LOW,
+	 RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_HIGH},
+	/* USB, 2 bulk out */
+	{RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_HIGH,
+	 RTW_DMA_MAPPING_NORMAL, RTW_DMA_MAPPING_NORMAL,
+	 RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_HIGH},
+	/* USB, 3 bulk out */
+	{RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_NORMAL,
+	 RTW_DMA_MAPPING_LOW, RTW_DMA_MAPPING_LOW,
+	 RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_HIGH},
+	/* USB, 4 bulk out */
+	{RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_NORMAL,
+	 RTW_DMA_MAPPING_LOW, RTW_DMA_MAPPING_LOW,
+	 RTW_DMA_MAPPING_HIGH, RTW_DMA_MAPPING_HIGH},
+};
+
+static const struct rtw_prioq_addrs prioq_addrs_8814a = {
+	.prio[RTW_DMA_MAPPING_EXTRA] = {
+		.rsvd = REG_FIFOPAGE_INFO_4, .avail = REG_FIFOPAGE_INFO_4 + 2,
+	},
+	.prio[RTW_DMA_MAPPING_LOW] = {
+		.rsvd = REG_FIFOPAGE_INFO_2, .avail = REG_FIFOPAGE_INFO_2 + 2,
+	},
+	.prio[RTW_DMA_MAPPING_NORMAL] = {
+		.rsvd = REG_FIFOPAGE_INFO_3, .avail = REG_FIFOPAGE_INFO_3 + 2,
+	},
+	.prio[RTW_DMA_MAPPING_HIGH] = {
+		.rsvd = REG_FIFOPAGE_INFO_1, .avail = REG_FIFOPAGE_INFO_1 + 2,
+	},
+	.wsize = true,
+};
+
+static const struct rtw_page_table page_table_8814a[] = {
+	/* SDIO */
+	{0, 0, 0, 0, 0},	/* hq nq lq exq gapq */
+	/* PCIE */
+	{32, 32, 32, 32, 0},
+	/* USB, 2 bulk out */
+	{32, 32, 32, 32, 0},
+	/* USB, 3 bulk out */
+	{32, 32, 32, 32, 0},
+	/* USB, 4 bulk out */
+	{32, 32, 32, 32, 0},
+};
+
+static const struct rtw_intf_phy_para_table phy_para_table_8814a = {};
+
+static const struct rtw_hw_reg rtw8814a_dig[] = {
+	[0] = { .addr = 0xc50, .mask = 0x7f },
+	[1] = { .addr = 0xe50, .mask = 0x7f },
+	[2] = { .addr = 0x1850, .mask = 0x7f },
+	[3] = { .addr = 0x1a50, .mask = 0x7f },
+};
+
+static const struct rtw_rfe_def rtw8814a_rfe_defs[] = {
+	[0] = { .phy_pg_tbl	= &rtw8814a_bb_pg_type0_tbl,
+		.txpwr_lmt_tbl	= &rtw8814a_txpwr_lmt_type0_tbl,
+		.pwr_track_tbl	= &rtw8814a_rtw_pwrtrk_type0_tbl },
+	[1] = { .phy_pg_tbl	= &rtw8814a_bb_pg_tbl,
+		.txpwr_lmt_tbl	= &rtw8814a_txpwr_lmt_type1_tbl,
+		.pwr_track_tbl	= &rtw8814a_rtw_pwrtrk_tbl },
+};
+
+/* rssi in percentage % (dbm = % - 100) */
+static const u8 wl_rssi_step_8814a[] = {60, 50, 44, 30};
+static const u8 bt_rssi_step_8814a[] = {30, 30, 30, 30};
+
+/* wl_tx_dec_power, bt_tx_dec_power, wl_rx_gain, bt_rx_lna_constrain */
+static const struct coex_rf_para rf_para_tx_8814a[] = {
+	{0, 0, false, 7},  /* for normal */
+	{0, 16, false, 7}, /* for WL-CPT */
+	{4, 0, true, 1},
+	{3, 6, true, 1},
+	{2, 9, true, 1},
+	{1, 13, true, 1}
+};
+
+static const struct coex_rf_para rf_para_rx_8814a[] = {
+	{0, 0, false, 7},  /* for normal */
+	{0, 16, false, 7}, /* for WL-CPT */
+	{4, 0, true, 1},
+	{3, 6, true, 1},
+	{2, 9, true, 1},
+	{1, 13, true, 1}
+};
+
+static_assert(ARRAY_SIZE(rf_para_tx_8814a) == ARRAY_SIZE(rf_para_rx_8814a));
+
+const struct rtw_chip_info rtw8814a_hw_spec = {
+	.ops = &rtw8814a_ops,
+	.id = RTW_CHIP_TYPE_8814A,
+	.fw_name = "rtw88/rtw8814a_fw.bin",
+	.wlan_cpu = RTW_WCPU_11AC,
+	.tx_pkt_desc_sz = 40,
+	.tx_buf_desc_sz = 16,
+	.rx_pkt_desc_sz = 24,
+	.rx_buf_desc_sz = 8,
+	.phy_efuse_size = 1024,
+	.log_efuse_size = 512,
+	.ptct_efuse_size = 0,
+	.txff_size = (2048 - 10) * TX_PAGE_SIZE,
+	.rxff_size = 23552,
+	.rsvd_drv_pg_num = 8,
+	.band = RTW_BAND_2G | RTW_BAND_5G,
+	.page_size = TX_PAGE_SIZE,
+	.csi_buf_pg_num = 0,
+	.dig_min = 0x1c,
+	.txgi_factor = 1,
+	.is_pwr_by_rate_dec = true,
+	.rx_ldpc = true,
+	.max_power_index = 0x3f,
+	.ampdu_density = IEEE80211_HT_MPDU_DENSITY_2,
+	.usb_tx_agg_desc_num = 3,
+	.hw_feature_report = false,
+	.c2h_ra_report_size = 6,
+	.old_datarate_fb_limit = false,
+	.ht_supported = true,
+	.vht_supported = true,
+	.lps_deep_mode_supported = BIT(LPS_DEEP_MODE_LCLK),
+	.sys_func_en = 0xDC,
+	.pwr_on_seq = card_enable_flow_8814a,
+	.pwr_off_seq = card_disable_flow_8814a,
+	.rqpn_table = rqpn_table_8814a,
+	.prioq_addrs = &prioq_addrs_8814a,
+	.page_table = page_table_8814a,
+	.intf_table = &phy_para_table_8814a,
+	.dig = rtw8814a_dig,
+	.dig_cck = NULL,
+	.rf_base_addr = {0x2800, 0x2c00, 0x3800, 0x3c00},
+	.rf_sipi_addr = {0xc90, 0xe90, 0x1890, 0x1a90},
+	.ltecoex_addr = NULL,
+	.mac_tbl = &rtw8814a_mac_tbl,
+	.agc_tbl = &rtw8814a_agc_tbl,
+	.bb_tbl = &rtw8814a_bb_tbl,
+	.rf_tbl = {&rtw8814a_rf_a_tbl, &rtw8814a_rf_b_tbl,
+		   &rtw8814a_rf_c_tbl, &rtw8814a_rf_d_tbl},
+	.rfe_defs = rtw8814a_rfe_defs,
+	.rfe_defs_size = ARRAY_SIZE(rtw8814a_rfe_defs),
+	.iqk_threshold = 8,
+	.max_scan_ie_len = IEEE80211_MAX_DATA_LEN,
+
+	.coex_para_ver = 0,
+	.bt_desired_ver = 0,
+	.scbd_support = false,
+	.new_scbd10_def = false,
+	.ble_hid_profile_support = false,
+	.wl_mimo_ps_support = false,
+	.pstdma_type = COEX_PSTDMA_FORCE_LPSOFF,
+	.bt_rssi_type = COEX_BTRSSI_RATIO,
+	.ant_isolation = 15,
+	.rssi_tolerance = 2,
+	.wl_rssi_step = wl_rssi_step_8814a,
+	.bt_rssi_step = bt_rssi_step_8814a,
+	.table_sant_num = 0,
+	.table_sant = NULL,
+	.table_nsant_num = 0,
+	.table_nsant = NULL,
+	.tdma_sant_num = 0,
+	.tdma_sant = NULL,
+	.tdma_nsant_num = 0,
+	.tdma_nsant = NULL,
+	.wl_rf_para_num = ARRAY_SIZE(rf_para_tx_8814a),
+	.wl_rf_para_tx = rf_para_tx_8814a,
+	.wl_rf_para_rx = rf_para_rx_8814a,
+	.bt_afh_span_bw20 = 0x24,
+	.bt_afh_span_bw40 = 0x36,
+	.afh_5g_num = 0,
+	.afh_5g = NULL,
+	.coex_info_hw_regs_num = 0,
+	.coex_info_hw_regs = NULL,
+};
+EXPORT_SYMBOL(rtw8814a_hw_spec);
+
+MODULE_FIRMWARE("rtw88/rtw8814a_fw.bin");
+
+MODULE_AUTHOR("Bitterblue Smith <rtl8821cerfe2@gmail.com>");
+MODULE_DESCRIPTION("Realtek 802.11ac wireless 8814a driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814a.h b/drivers/net/wireless/realtek/rtw88/rtw8814a.h
new file mode 100644
index 0000000000000..c57c7c8f915e2
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814a.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#ifndef __RTW8814A_H__
+#define __RTW8814A_H__
+
+struct rtw8814au_efuse {
+	u8 vid[2];			/* 0xd0 */
+	u8 pid[2];			/* 0xd2 */
+	u8 res[4];			/* 0xd4 */
+	u8 mac_addr[ETH_ALEN];		/* 0xd8 */
+} __packed;
+
+struct rtw8814ae_efuse {
+	u8 mac_addr[ETH_ALEN];		/* 0xd0 */
+	u8 vid[2];			/* 0xd6 */
+	u8 did[2];			/* 0xd8 */
+	u8 svid[2];			/* 0xda */
+	u8 smid[2];			/* 0xdc */
+} __packed;
+
+struct rtw8814a_efuse {
+	__le16 rtl_id;
+	u8 res0[0x0c];
+	u8 usb_mode;			/* 0x0e */
+	u8 res1;
+
+	/* power index for four RF paths */
+	struct rtw_txpwr_idx txpwr_idx_table[4];
+
+	u8 channel_plan;		/* 0xb8 */
+	u8 xtal_k;			/* 0xb9 */
+	u8 thermal_meter;		/* 0xba */
+	u8 iqk_lck;			/* 0xbb */
+	u8 pa_type;			/* 0xbc */
+	u8 lna_type_2g[2];		/* 0xbd */
+	u8 lna_type_5g[2];		/* 0xbf */
+	u8 rf_board_option;		/* 0xc1 */
+	u8 res2;
+	u8 rf_bt_setting;		/* 0xc3 */
+	u8 eeprom_version;		/* 0xc4 */
+	u8 eeprom_customer_id;		/* 0xc5 */
+	u8 tx_bb_swing_setting_2g;	/* 0xc6 */
+	u8 tx_bb_swing_setting_5g;	/* 0xc7 */
+	u8 res3;
+	u8 trx_antenna_option;		/* 0xc9 */
+	u8 rfe_option;			/* 0xca */
+	u8 country_code[2];		/* 0xcb */
+	u8 res4[3];
+	union {
+		struct rtw8814au_efuse u;
+		struct rtw8814ae_efuse e;
+	};
+	u8 res5[0x122];			/* 0xde */
+} __packed;
+
+static_assert(sizeof(struct rtw8814a_efuse) == 512);
+
+extern const struct rtw_chip_info rtw8814a_hw_spec;
+
+#endif

From dad8e879310211c1e02f09c35f169388bccbfa42 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:25:09 +0200
Subject: [PATCH 2070/2753] wifi: rtw88: Add rtw8814ae.c

This is the entry point for the new module rtw88_8814ae.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/74ebab2f-a23e-4d87-935f-0af2b5cba672@gmail.com
---
 .../net/wireless/realtek/rtw88/rtw8814ae.c    | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814ae.c

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814ae.c b/drivers/net/wireless/realtek/rtw88/rtw8814ae.c
new file mode 100644
index 0000000000000..54d2e20a7764e
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814ae.c
@@ -0,0 +1,31 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#include <linux/module.h>
+#include <linux/pci.h>
+#include "pci.h"
+#include "rtw8814a.h"
+
+static const struct pci_device_id rtw_8814ae_id_table[] = {
+	{
+		PCI_DEVICE(PCI_VENDOR_ID_REALTEK, 0x8813),
+		.driver_data = (kernel_ulong_t)&rtw8814a_hw_spec
+	},
+	{}
+};
+MODULE_DEVICE_TABLE(pci, rtw_8814ae_id_table);
+
+static struct pci_driver rtw_8814ae_driver = {
+	.name = "rtw_8814ae",
+	.id_table = rtw_8814ae_id_table,
+	.probe = rtw_pci_probe,
+	.remove = rtw_pci_remove,
+	.driver.pm = &rtw_pm_ops,
+	.shutdown = rtw_pci_shutdown,
+};
+module_pci_driver(rtw_8814ae_driver);
+
+MODULE_AUTHOR("Bitterblue Smith <rtl8821cerfe2@gmail.com>");
+MODULE_DESCRIPTION("Realtek 802.11ac wireless 8814ae driver");
+MODULE_LICENSE("Dual BSD/GPL");

From bad060e8a425182809bfc2586a2e7f5ccd1a994d Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:25:37 +0200
Subject: [PATCH 2071/2753] wifi: rtw88: Add rtw8814au.c

This is the entry point for the new module rtw88_8814au.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/71457787-5a9e-4ead-a62c-22ca44e00b89@gmail.com
---
 .../net/wireless/realtek/rtw88/rtw8814au.c    | 54 +++++++++++++++++++
 1 file changed, 54 insertions(+)
 create mode 100644 drivers/net/wireless/realtek/rtw88/rtw8814au.c

diff --git a/drivers/net/wireless/realtek/rtw88/rtw8814au.c b/drivers/net/wireless/realtek/rtw88/rtw8814au.c
new file mode 100644
index 0000000000000..afe045fb84de1
--- /dev/null
+++ b/drivers/net/wireless/realtek/rtw88/rtw8814au.c
@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
+/* Copyright(c) 2025  Realtek Corporation
+ */
+
+#include <linux/module.h>
+#include <linux/usb.h>
+#include "main.h"
+#include "rtw8814a.h"
+#include "usb.h"
+
+static const struct usb_device_id rtw_8814au_id_table[] = {
+	{ USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0x8813, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x400b, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x056e, 0x400d, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0846, 0x9054, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x1817, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x1852, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0b05, 0x1853, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x0e66, 0x0026, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331a, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x809a, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x20f4, 0x809b, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x2357, 0x0106, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa834, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{ USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xa833, 0xff, 0xff, 0xff),
+	  .driver_info = (kernel_ulong_t)&(rtw8814a_hw_spec) },
+	{},
+};
+MODULE_DEVICE_TABLE(usb, rtw_8814au_id_table);
+
+static struct usb_driver rtw_8814au_driver = {
+	.name = "rtw_8814au",
+	.id_table = rtw_8814au_id_table,
+	.probe = rtw_usb_probe,
+	.disconnect = rtw_usb_disconnect,
+};
+module_usb_driver(rtw_8814au_driver);
+
+MODULE_AUTHOR("Bitterblue Smith <rtl8821cerfe2@gmail.com>");
+MODULE_DESCRIPTION("Realtek 802.11ac wireless 8814au driver");
+MODULE_LICENSE("Dual BSD/GPL");

From deb3ddeb18652118956fb581a39ac299e1ee5623 Mon Sep 17 00:00:00 2001
From: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Date: Fri, 7 Mar 2025 02:26:25 +0200
Subject: [PATCH 2072/2753] wifi: rtw88: Enable the new RTL8814AE/RTL8814AU
 drivers

RTL8814A is a wifi 5 chip with 4 RF paths (chains), 3 spatial streams,
and probably no Bluetooth.

The USB-based RTL8814AU can reach 800 Mbps in the 5 GHz band in USB 3
mode. In USB 2 mode it only uses 2 spatial streams.

The PCI-based RTL8814AE is not as popular and didn't get as much
testing so it's unclear how fast it goes. It's more like a bonus on top
of the RTL8814AU support.

Signed-off-by: Bitterblue Smith <rtl8821cerfe2@gmail.com>
Acked-by: Ping-Ke Shih <pkshih@realtek.com>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/5795b0a7-511e-40b5-ac36-476b63f174c7@gmail.com
---
 drivers/net/wireless/realtek/rtw88/Kconfig  | 25 +++++++++++++++++++++
 drivers/net/wireless/realtek/rtw88/Makefile |  9 ++++++++
 2 files changed, 34 insertions(+)

diff --git a/drivers/net/wireless/realtek/rtw88/Kconfig b/drivers/net/wireless/realtek/rtw88/Kconfig
index ab21b8059e0bf..3736f290bd426 100644
--- a/drivers/net/wireless/realtek/rtw88/Kconfig
+++ b/drivers/net/wireless/realtek/rtw88/Kconfig
@@ -54,6 +54,9 @@ config RTW88_8812A
 	tristate
 	select RTW88_88XXA
 
+config RTW88_8814A
+	tristate
+
 config RTW88_8822BE
 	tristate "Realtek 8822BE PCI wireless network adapter"
 	depends on PCI
@@ -222,6 +225,28 @@ config RTW88_8812AU
 
 	  802.11ac USB wireless network adapter
 
+config RTW88_8814AE
+	tristate "Realtek 8814AE PCI wireless network adapter"
+	depends on PCI
+	select RTW88_CORE
+	select RTW88_PCI
+	select RTW88_8814A
+	help
+	  Select this option will enable support for 8814AE chipset
+
+	  802.11ac PCIe wireless network adapter
+
+config RTW88_8814AU
+	tristate "Realtek 8814AU USB wireless network adapter"
+	depends on USB
+	select RTW88_CORE
+	select RTW88_USB
+	select RTW88_8814A
+	help
+	  Select this option will enable support for 8814AU chipset
+
+	  802.11ac USB wireless network adapter
+
 config RTW88_DEBUG
 	bool "Realtek rtw88 debug support"
 	depends on RTW88_CORE
diff --git a/drivers/net/wireless/realtek/rtw88/Makefile b/drivers/net/wireless/realtek/rtw88/Makefile
index 0cbbb366e3930..0b3da05a29380 100644
--- a/drivers/net/wireless/realtek/rtw88/Makefile
+++ b/drivers/net/wireless/realtek/rtw88/Makefile
@@ -94,6 +94,15 @@ rtw88_8821au-objs		:= rtw8821au.o
 obj-$(CONFIG_RTW88_8812AU)	+= rtw88_8812au.o
 rtw88_8812au-objs		:= rtw8812au.o
 
+obj-$(CONFIG_RTW88_8814A)	+= rtw88_8814a.o
+rtw88_8814a-objs		:= rtw8814a.o rtw8814a_table.o
+
+obj-$(CONFIG_RTW88_8814AE)	+= rtw88_8814ae.o
+rtw88_8814ae-objs		:= rtw8814ae.o
+
+obj-$(CONFIG_RTW88_8814AU)	+= rtw88_8814au.o
+rtw88_8814au-objs		:= rtw8814au.o
+
 obj-$(CONFIG_RTW88_PCI)		+= rtw88_pci.o
 rtw88_pci-objs			:= pci.o
 

From d58ad77d5cc2a6d04db622a898e54d93fc7002a2 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Mon, 10 Mar 2025 15:22:58 -0700
Subject: [PATCH 2073/2753] wifi: rtw88: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to and correctly identify the char array as "not a C
string" and thereby eliminate the warning.

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Cc: Ping-Ke Shih <pkshih@realtek.com>
Cc: Johannes Berg <johannes@sipsolutions.net>
Cc: linux-wireless@vger.kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
Signed-off-by: Ping-Ke Shih <pkshih@realtek.com>
Link: https://patch.msgid.link/20250310222257.work.866-kees@kernel.org
---
 drivers/net/wireless/realtek/rtw88/main.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
index c15e0f55d09a7..02343e059fd97 100644
--- a/drivers/net/wireless/realtek/rtw88/main.h
+++ b/drivers/net/wireless/realtek/rtw88/main.h
@@ -835,7 +835,7 @@ struct rtw_vif {
 };
 
 struct rtw_regulatory {
-	char alpha2[2];
+	char alpha2[2] __nonstring;
 	u8 txpwr_regd_2g;
 	u8 txpwr_regd_5g;
 };

From 3bcde88d381a336ff252d67867c186ee602e6656 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Wed, 12 Mar 2025 17:21:31 -0400
Subject: [PATCH 2074/2753] bcachefs: fix tiny leak in bch2_dev_add()

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/super.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/fs/bcachefs/super.c b/fs/bcachefs/super.c
index 6d97d412fed98..0459c875e189b 100644
--- a/fs/bcachefs/super.c
+++ b/fs/bcachefs/super.c
@@ -1811,7 +1811,11 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 		goto err_late;
 
 	up_write(&c->state_lock);
-	return 0;
+out:
+	printbuf_exit(&label);
+	printbuf_exit(&errbuf);
+	bch_err_fn(c, ret);
+	return ret;
 
 err_unlock:
 	mutex_unlock(&c->sb_lock);
@@ -1820,10 +1824,7 @@ int bch2_dev_add(struct bch_fs *c, const char *path)
 	if (ca)
 		bch2_dev_free(ca);
 	bch2_free_super(&sb);
-	printbuf_exit(&label);
-	printbuf_exit(&errbuf);
-	bch_err_fn(c, ret);
-	return ret;
+	goto out;
 err_late:
 	up_write(&c->state_lock);
 	ca = NULL;

From 0102fbf52b93e609fec0dab53b1fb4fe69113f5e Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 11 Mar 2025 18:56:31 +0100
Subject: [PATCH 2075/2753] gpiolib: don't check the retval of get_direction()
 when registering a chip

During chip registration we should neither check the return value of
gc->get_direction() nor hold the SRCU lock when calling it. The former
is because pin controllers may have pins set to alternate functions and
return errors from their get_direction() callbacks. That's alright - we
should default to the safe INPUT state and not bail-out. The latter is
not needed because we haven't registered the chip yet so there's nothing
to protect against dynamic removal. In fact: we currently hit a lockdep
splat. Revert to calling the gc->get_direction() callback directly and
*not* checking its value.

Fixes: 9d846b1aebbe ("gpiolib: check the return value of gpio_chip::get_direction()")
Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/all/81f890fc-6688-42f0-9756-567efc8bb97a@samsung.com/
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Link: https://lore.kernel.org/r/20250226-retval-fixes-v2-1-c8dc57182441@linaro.org
Tested-by: Gene C <arch@sapience.com>
Link: https://lore.kernel.org/r/20250311175631.83779-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 27 +++++++++++----------------
 1 file changed, 11 insertions(+), 16 deletions(-)

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 8741600af7efb..de708d0818581 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1056,24 +1056,19 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 
 		desc->gdev = gdev;
 
-		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index)) {
-			ret = gc->get_direction(gc, desc_index);
-			if (ret < 0)
-				/*
-				 * FIXME: Bail-out here once all GPIO drivers
-				 * are updated to not return errors in
-				 * situations that can be considered normal
-				 * operation.
-				 */
-				dev_warn(&gdev->dev,
-					 "%s: get_direction failed: %d\n",
-					 __func__, ret);
-
-			assign_bit(FLAG_IS_OUT, &desc->flags, !ret);
-		} else {
+		/*
+		 * We would typically want to check the return value of
+		 * get_direction() here but we must not check the return value
+		 * and bail-out as pin controllers can have pins configured to
+		 * alternate functions and return -EINVAL. Also: there's no
+		 * need to take the SRCU lock here.
+		 */
+		if (gc->get_direction && gpiochip_line_is_valid(gc, desc_index))
+			assign_bit(FLAG_IS_OUT, &desc->flags,
+				   !gc->get_direction(gc, desc_index));
+		else
 			assign_bit(FLAG_IS_OUT,
 				   &desc->flags, !gc->direction_input);
-		}
 	}
 
 	ret = of_gpiochip_add(gc);

From dcb73cbaaeb39c9fd00bf2e019f911725945e2fe Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 11 Mar 2025 15:31:43 +0100
Subject: [PATCH 2076/2753] gpio: cdev: use raw notifier for line state events

We use a notifier to implement the mechanism of informing the user-space
about changes in GPIO line status. We register with the notifier when
the GPIO character device file is opened and unregister when the last
reference to the associated file descriptor is dropped.

Since commit fcc8b637c542 ("gpiolib: switch the line state notifier to
atomic") we use the atomic notifier variant. Atomic notifiers call
rcu_synchronize in atomic_notifier_chain_unregister() which caused a
significant performance regression in some circumstances, observed by
user-space when calling close() on the GPIO device file descriptor.

Replace the atomic notifier with the raw variant and provide
synchronization with a read-write spinlock.

Fixes: fcc8b637c542 ("gpiolib: switch the line state notifier to atomic")
Reported-by: David Jander <david@protonic.nl>
Closes: https://lore.kernel.org/all/20250311110034.53959031@erd003.prtnl/
Tested-by: David Jander <david@protonic.nl>
Tested-by: Kent Gibson <warthog618@gmail.com>
Link: https://lore.kernel.org/r/20250311-gpiolib-line-state-raw-notifier-v2-1-138374581e1e@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib-cdev.c | 15 +++++++++------
 drivers/gpio/gpiolib.c      |  8 +++++---
 drivers/gpio/gpiolib.h      |  5 ++++-
 3 files changed, 18 insertions(+), 10 deletions(-)

diff --git a/drivers/gpio/gpiolib-cdev.c b/drivers/gpio/gpiolib-cdev.c
index 40f76a90fd7db..107d75558b5a8 100644
--- a/drivers/gpio/gpiolib-cdev.c
+++ b/drivers/gpio/gpiolib-cdev.c
@@ -2729,8 +2729,9 @@ static int gpio_chrdev_open(struct inode *inode, struct file *file)
 	cdev->gdev = gpio_device_get(gdev);
 
 	cdev->lineinfo_changed_nb.notifier_call = lineinfo_changed_notify;
-	ret = atomic_notifier_chain_register(&gdev->line_state_notifier,
-					     &cdev->lineinfo_changed_nb);
+	scoped_guard(write_lock_irqsave, &gdev->line_state_lock)
+		ret = raw_notifier_chain_register(&gdev->line_state_notifier,
+						  &cdev->lineinfo_changed_nb);
 	if (ret)
 		goto out_free_bitmap;
 
@@ -2754,8 +2755,9 @@ static int gpio_chrdev_open(struct inode *inode, struct file *file)
 	blocking_notifier_chain_unregister(&gdev->device_notifier,
 					   &cdev->device_unregistered_nb);
 out_unregister_line_notifier:
-	atomic_notifier_chain_unregister(&gdev->line_state_notifier,
-					 &cdev->lineinfo_changed_nb);
+	scoped_guard(write_lock_irqsave, &gdev->line_state_lock)
+		raw_notifier_chain_unregister(&gdev->line_state_notifier,
+					      &cdev->lineinfo_changed_nb);
 out_free_bitmap:
 	gpio_device_put(gdev);
 	bitmap_free(cdev->watched_lines);
@@ -2779,8 +2781,9 @@ static int gpio_chrdev_release(struct inode *inode, struct file *file)
 
 	blocking_notifier_chain_unregister(&gdev->device_notifier,
 					   &cdev->device_unregistered_nb);
-	atomic_notifier_chain_unregister(&gdev->line_state_notifier,
-					 &cdev->lineinfo_changed_nb);
+	scoped_guard(write_lock_irqsave, &gdev->line_state_lock)
+		raw_notifier_chain_unregister(&gdev->line_state_notifier,
+					      &cdev->lineinfo_changed_nb);
 	bitmap_free(cdev->watched_lines);
 	gpio_device_put(gdev);
 	kfree(cdev);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index de708d0818581..0c00ed2ab4315 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1025,7 +1025,8 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 		}
 	}
 
-	ATOMIC_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier);
+	rwlock_init(&gdev->line_state_lock);
+	RAW_INIT_NOTIFIER_HEAD(&gdev->line_state_notifier);
 	BLOCKING_INIT_NOTIFIER_HEAD(&gdev->device_notifier);
 
 	ret = init_srcu_struct(&gdev->srcu);
@@ -4188,8 +4189,9 @@ EXPORT_SYMBOL_GPL(gpiod_set_array_value_cansleep);
 
 void gpiod_line_state_notify(struct gpio_desc *desc, unsigned long action)
 {
-	atomic_notifier_call_chain(&desc->gdev->line_state_notifier,
-				   action, desc);
+	guard(read_lock_irqsave)(&desc->gdev->line_state_lock);
+
+	raw_notifier_call_chain(&desc->gdev->line_state_notifier, action, desc);
 }
 
 /**
diff --git a/drivers/gpio/gpiolib.h b/drivers/gpio/gpiolib.h
index 147156ec502b2..c129a03e20408 100644
--- a/drivers/gpio/gpiolib.h
+++ b/drivers/gpio/gpiolib.h
@@ -16,6 +16,7 @@
 #include <linux/gpio/driver.h>
 #include <linux/module.h>
 #include <linux/notifier.h>
+#include <linux/spinlock.h>
 #include <linux/srcu.h>
 #include <linux/workqueue.h>
 
@@ -45,6 +46,7 @@
  * @list: links gpio_device:s together for traversal
  * @line_state_notifier: used to notify subscribers about lines being
  *                       requested, released or reconfigured
+ * @line_state_lock: RW-spinlock protecting the line state notifier
  * @line_state_wq: used to emit line state events from a separate thread in
  *                 process context
  * @device_notifier: used to notify character device wait queues about the GPIO
@@ -72,7 +74,8 @@ struct gpio_device {
 	const char		*label;
 	void			*data;
 	struct list_head        list;
-	struct atomic_notifier_head line_state_notifier;
+	struct raw_notifier_head line_state_notifier;
+	rwlock_t		line_state_lock;
 	struct workqueue_struct	*line_state_wq;
 	struct blocking_notifier_head device_notifier;
 	struct srcu_struct	srcu;

From 0e2268f88bb27ef14ac3de1bc4df29ff12bb28cb Mon Sep 17 00:00:00 2001
From: Horatiu Vultur <horatiu.vultur@microchip.com>
Date: Thu, 27 Feb 2025 11:55:02 +0100
Subject: [PATCH 2077/2753] reset: mchp: sparx5: Fix for lan966x

With the blamed commit it seems that lan966x doesn't seem to boot
anymore when the internal CPU is used.
The reason seems to be the usage of the devm_of_iomap, if we replace
this with devm_ioremap, this seems to fix the issue as we use the same
region also for other devices.

Fixes: 0426a920d6269c ("reset: mchp: sparx5: Map cpu-syscon locally in case of LAN966x")
Reviewed-by: Herve Codina <herve.codina@bootlin.com>
Tested-by: Herve Codina <herve.codina@bootlin.com>
Signed-off-by: Horatiu Vultur <horatiu.vultur@microchip.com>
Reviewed-by: Philipp Zabel <p.zabel@pengutronix.de>
Link: https://lore.kernel.org/r/20250227105502.25125-1-horatiu.vultur@microchip.com
Signed-off-by: Philipp Zabel <p.zabel@pengutronix.de>
---
 drivers/reset/reset-microchip-sparx5.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/reset/reset-microchip-sparx5.c b/drivers/reset/reset-microchip-sparx5.c
index aa5464be7053b..6d3e75b33260e 100644
--- a/drivers/reset/reset-microchip-sparx5.c
+++ b/drivers/reset/reset-microchip-sparx5.c
@@ -8,6 +8,7 @@
  */
 #include <linux/mfd/syscon.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/property.h>
@@ -72,14 +73,22 @@ static struct regmap *mchp_lan966x_syscon_to_regmap(struct device *dev,
 						    struct device_node *syscon_np)
 {
 	struct regmap_config regmap_config = mchp_lan966x_syscon_regmap_config;
-	resource_size_t size;
+	struct resource res;
 	void __iomem *base;
+	int err;
+
+	err = of_address_to_resource(syscon_np, 0, &res);
+	if (err)
+		return ERR_PTR(err);
 
-	base = devm_of_iomap(dev, syscon_np, 0, &size);
-	if (IS_ERR(base))
-		return ERR_CAST(base);
+	/* It is not possible to use devm_of_iomap because this resource is
+	 * shared with other drivers.
+	 */
+	base = devm_ioremap(dev, res.start, resource_size(&res));
+	if (!base)
+		return ERR_PTR(-ENOMEM);
 
-	regmap_config.max_register = size - 4;
+	regmap_config.max_register =  resource_size(&res) - 4;
 
 	return devm_regmap_init_mmio(dev, base, &regmap_config);
 }

From 9e3285040514cafee035e1be24502097d3d0b75f Mon Sep 17 00:00:00 2001
From: Jian Shen <shenjian15@huawei.com>
Date: Fri, 7 Mar 2025 19:37:33 +0800
Subject: [PATCH 2078/2753] net: hns3: use string choices helper

Use string choices helper for better readability.

Signed-off-by: Jian Shen <shenjian15@huawei.com>
Signed-off-by: Jijie Shao <shaojijie@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250307113733.819448-1-shaojijie@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/hisilicon/hns3/hns3_debugfs.c    | 24 ++++---
 .../ethernet/hisilicon/hns3/hns3_ethtool.c    |  3 +-
 .../hisilicon/hns3/hns3pf/hclge_debugfs.c     | 63 +++++++++----------
 .../hisilicon/hns3/hns3pf/hclge_main.c        | 10 +--
 .../hisilicon/hns3/hns3pf/hclge_ptp.c         |  3 +-
 5 files changed, 54 insertions(+), 49 deletions(-)

diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
index 9bbece25552b1..09749e9f73986 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/debugfs.h>
 #include <linux/device.h>
+#include <linux/string_choices.h>
 
 #include "hnae3.h"
 #include "hns3_debugfs.h"
@@ -661,12 +662,14 @@ static void hns3_dump_rx_queue_info(struct hns3_enet_ring *ring,
 		HNS3_RING_RX_RING_PKTNUM_RECORD_REG));
 	sprintf(result[j++], "%u", ring->rx_copybreak);
 
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	sprintf(result[j++], "%s",
+		str_on_off(readl_relaxed(ring->tqp->io_base +
+					 HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_RX_EN_REG) ? "on" : "off");
+		sprintf(result[j++], "%s",
+			str_on_off(readl_relaxed(ring->tqp->io_base +
+						 HNS3_RING_RX_EN_REG)));
 	else
 		sprintf(result[j++], "%s", "NA");
 
@@ -764,12 +767,14 @@ static void hns3_dump_tx_queue_info(struct hns3_enet_ring *ring,
 	sprintf(result[j++], "%u", readl_relaxed(ring->tqp->io_base +
 		HNS3_RING_TX_RING_PKTNUM_RECORD_REG));
 
-	sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-		HNS3_RING_EN_REG) ? "on" : "off");
+	sprintf(result[j++], "%s",
+		str_on_off(readl_relaxed(ring->tqp->io_base +
+					 HNS3_RING_EN_REG)));
 
 	if (hnae3_ae_dev_tqp_txrx_indep_supported(ae_dev))
-		sprintf(result[j++], "%s", readl_relaxed(ring->tqp->io_base +
-			HNS3_RING_TX_EN_REG) ? "on" : "off");
+		sprintf(result[j++], "%s",
+			str_on_off(readl_relaxed(ring->tqp->io_base +
+						 HNS3_RING_TX_EN_REG)));
 	else
 		sprintf(result[j++], "%s", "NA");
 
@@ -1030,7 +1035,6 @@ static void
 hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
 {
 	struct hnae3_ae_dev *ae_dev = pci_get_drvdata(h->pdev);
-	const char * const str[] = {"no", "yes"};
 	unsigned long *caps = ae_dev->caps;
 	u32 i, state;
 
@@ -1039,7 +1043,7 @@ hns3_dbg_dev_caps(struct hnae3_handle *h, char *buf, int len, int *pos)
 	for (i = 0; i < ARRAY_SIZE(hns3_dbg_cap); i++) {
 		state = test_bit(hns3_dbg_cap[i].cap_bit, caps);
 		*pos += scnprintf(buf + *pos, len - *pos, "%s: %s\n",
-				  hns3_dbg_cap[i].name, str[state]);
+				  hns3_dbg_cap[i].name, str_yes_no(state));
 	}
 
 	*pos += scnprintf(buf + *pos, len - *pos, "\n");
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
index b771a2daba436..6715222aeb661 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c
@@ -3,6 +3,7 @@
 
 #include <linux/etherdevice.h>
 #include <linux/string.h>
+#include <linux/string_choices.h>
 #include <linux/phy.h>
 #include <linux/sfp.h>
 
@@ -1198,7 +1199,7 @@ static int hns3_set_tx_push(struct net_device *netdev, u32 tx_push)
 		return 0;
 
 	netdev_dbg(netdev, "Changing tx push from %s to %s\n",
-		   old_state ? "on" : "off", tx_push ? "on" : "off");
+		   str_on_off(old_state), str_on_off(tx_push));
 
 	if (tx_push)
 		set_bit(HNS3_NIC_STATE_TX_PUSH_ENABLE, &priv->state);
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
index debf143e99401..c464906935946 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c
@@ -3,6 +3,7 @@
 
 #include <linux/device.h>
 #include <linux/sched/clock.h>
+#include <linux/string_choices.h>
 
 #include "hclge_debugfs.h"
 #include "hclge_err.h"
@@ -11,7 +12,6 @@
 #include "hclge_tm.h"
 #include "hnae3.h"
 
-static const char * const state_str[] = { "off", "on" };
 static const char * const hclge_mac_state_str[] = {
 	"TO_ADD", "TO_DEL", "ACTIVE"
 };
@@ -2573,7 +2573,7 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 	loopback_en = hnae3_get_bit(le32_to_cpu(req_app->txrx_pad_fcs_loop_en),
 				    HCLGE_MAC_APP_LP_B);
 	pos += scnprintf(buf + pos, len - pos, "app loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_COMMON_LOOPBACK, true);
 	ret = hclge_cmd_send(&hdev->hw, &desc, 1);
@@ -2586,22 +2586,22 @@ static int hclge_dbg_dump_loopback(struct hclge_dev *hdev, char *buf, int len)
 
 	loopback_en = req_common->enable & HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B;
 	pos += scnprintf(buf + pos, len - pos, "serdes serial loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	loopback_en = req_common->enable &
 			HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B ? 1 : 0;
 	pos += scnprintf(buf + pos, len - pos, "serdes parallel loopback: %s\n",
-			 state_str[loopback_en]);
+			 str_on_off(loopback_en));
 
 	if (phydev) {
 		loopback_en = phydev->loopback_enabled;
 		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+				 str_on_off(loopback_en));
 	} else if (hnae3_dev_phy_imp_supported(hdev)) {
 		loopback_en = req_common->enable &
 			      HCLGE_CMD_GE_PHY_INNER_LOOP_B;
 		pos += scnprintf(buf + pos, len - pos, "phy loopback: %s\n",
-				 state_str[loopback_en]);
+				 str_on_off(loopback_en));
 	}
 
 	return 0;
@@ -2894,9 +2894,9 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 	egress = vlan_fe & HCLGE_FILTER_FE_NIC_EGRESS_B ? 1 : 0;
 
 	*pos += scnprintf(buf, len, "I_PORT_VLAN_FILTER: %s\n",
-			  state_str[ingress]);
+			  str_on_off(ingress));
 	*pos += scnprintf(buf + *pos, len - *pos, "E_PORT_VLAN_FILTER: %s\n",
-			  state_str[egress]);
+			  str_on_off(egress));
 
 	hclge_dbg_fill_content(content, sizeof(content), vlan_filter_items,
 			       NULL, ARRAY_SIZE(vlan_filter_items));
@@ -2915,11 +2915,11 @@ static int hclge_dbg_dump_vlan_filter_config(struct hclge_dev *hdev, char *buf,
 			return ret;
 		j = 0;
 		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
-		result[j++] = state_str[ingress];
-		result[j++] = state_str[egress];
-		result[j++] =
-			test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
-				 hdev->ae_dev->caps) ? state_str[bypass] : "NA";
+		result[j++] = str_on_off(ingress);
+		result[j++] = str_on_off(egress);
+		result[j++] = test_bit(HNAE3_DEV_SUPPORT_PORT_VLAN_BYPASS_B,
+				       hdev->ae_dev->caps) ?
+			      str_on_off(bypass) : "NA";
 		hclge_dbg_fill_content(content, sizeof(content),
 				       vlan_filter_items, result,
 				       ARRAY_SIZE(vlan_filter_items));
@@ -2958,19 +2958,19 @@ static int hclge_dbg_dump_vlan_offload_config(struct hclge_dev *hdev, char *buf,
 		j = 0;
 		result[j++] = hclge_dbg_get_func_id_str(str_id, i);
 		result[j++] = str_pvid;
-		result[j++] = state_str[vlan_cfg.accept_tag1];
-		result[j++] = state_str[vlan_cfg.accept_tag2];
-		result[j++] = state_str[vlan_cfg.accept_untag1];
-		result[j++] = state_str[vlan_cfg.accept_untag2];
-		result[j++] = state_str[vlan_cfg.insert_tag1];
-		result[j++] = state_str[vlan_cfg.insert_tag2];
-		result[j++] = state_str[vlan_cfg.shift_tag];
-		result[j++] = state_str[vlan_cfg.strip_tag1];
-		result[j++] = state_str[vlan_cfg.strip_tag2];
-		result[j++] = state_str[vlan_cfg.drop_tag1];
-		result[j++] = state_str[vlan_cfg.drop_tag2];
-		result[j++] = state_str[vlan_cfg.pri_only1];
-		result[j++] = state_str[vlan_cfg.pri_only2];
+		result[j++] = str_on_off(vlan_cfg.accept_tag1);
+		result[j++] = str_on_off(vlan_cfg.accept_tag2);
+		result[j++] = str_on_off(vlan_cfg.accept_untag1);
+		result[j++] = str_on_off(vlan_cfg.accept_untag2);
+		result[j++] = str_on_off(vlan_cfg.insert_tag1);
+		result[j++] = str_on_off(vlan_cfg.insert_tag2);
+		result[j++] = str_on_off(vlan_cfg.shift_tag);
+		result[j++] = str_on_off(vlan_cfg.strip_tag1);
+		result[j++] = str_on_off(vlan_cfg.strip_tag2);
+		result[j++] = str_on_off(vlan_cfg.drop_tag1);
+		result[j++] = str_on_off(vlan_cfg.drop_tag2);
+		result[j++] = str_on_off(vlan_cfg.pri_only1);
+		result[j++] = str_on_off(vlan_cfg.pri_only2);
 
 		hclge_dbg_fill_content(content, sizeof(content),
 				       vlan_offload_items, result,
@@ -3007,14 +3007,13 @@ static int hclge_dbg_dump_ptp_info(struct hclge_dev *hdev, char *buf, int len)
 	pos += scnprintf(buf + pos, len - pos, "phc %s's debug info:\n",
 			 ptp->info.name);
 	pos += scnprintf(buf + pos, len - pos, "ptp enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_EN, &ptp->flags)));
 	pos += scnprintf(buf + pos, len - pos, "ptp tx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_TX_EN,
+					     &ptp->flags)));
 	pos += scnprintf(buf + pos, len - pos, "ptp rx enable: %s\n",
-			 test_bit(HCLGE_PTP_FLAG_RX_EN, &ptp->flags) ?
-			 "yes" : "no");
+			 str_yes_no(test_bit(HCLGE_PTP_FLAG_RX_EN,
+					     &ptp->flags)));
 
 	last_rx = jiffies_to_msecs(ptp->last_rx);
 	pos += scnprintf(buf + pos, len - pos, "last rx time: %lu.%lu\n",
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 3f17b3073e50f..8c736a069eeb4 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -8000,7 +8000,7 @@ static int hclge_set_loopback(struct hnae3_handle *handle,
 	ret = hclge_tqp_enable(handle, en);
 	if (ret)
 		dev_err(&hdev->pdev->dev, "failed to %s tqp in loopback, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }
@@ -11200,9 +11200,9 @@ static void hclge_info_show(struct hclge_dev *hdev)
 	dev_info(dev, "This is %s PF\n",
 		 hdev->flag & HCLGE_FLAG_MAIN ? "main" : "not main");
 	dev_info(dev, "DCB %s\n",
-		 handle->kinfo.tc_info.dcb_ets_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.dcb_ets_active));
 	dev_info(dev, "MQPRIO %s\n",
-		 handle->kinfo.tc_info.mqprio_active ? "enable" : "disable");
+		 str_enable_disable(handle->kinfo.tc_info.mqprio_active));
 	dev_info(dev, "Default tx spare buffer size: %u\n",
 		 hdev->tx_spare_buf_size);
 
@@ -11976,7 +11976,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret) {
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d mac spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 		return ret;
 	}
 
@@ -11984,7 +11984,7 @@ static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"Set vf %d vlan spoof check %s failed, ret=%d\n",
-			vf, enable ? "on" : "off", ret);
+			vf, str_on_off(enable), ret);
 
 	return ret;
 }
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
index 181af419b878d..59cc9221185f2 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_ptp.c
@@ -2,6 +2,7 @@
 // Copyright (c) 2021 Hisilicon Limited.
 
 #include <linux/skbuff.h>
+#include <linux/string_choices.h>
 #include "hclge_main.h"
 #include "hnae3.h"
 
@@ -226,7 +227,7 @@ static int hclge_ptp_int_en(struct hclge_dev *hdev, bool en)
 	if (ret)
 		dev_err(&hdev->pdev->dev,
 			"failed to %s ptp interrupt, ret = %d\n",
-			en ? "enable" : "disable", ret);
+			str_enable_disable(en), ret);
 
 	return ret;
 }

From 676cc91e1f2a3f70f26dffa57b7e54bec9ab9d54 Mon Sep 17 00:00:00 2001
From: Janik Haag <janik@aq0.de>
Date: Fri, 7 Mar 2025 15:56:49 +0100
Subject: [PATCH 2079/2753] net: cn23xx: fix typos

This patch fixes a few typos, spelling mistakes, and a bit of grammar,
increasing the comments readability.

Signed-off-by: Janik Haag <janik@aq0.de>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250307145648.1679912-2-janik@aq0.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../cavium/liquidio/cn23xx_pf_device.c        | 76 +++++++++----------
 1 file changed, 38 insertions(+), 38 deletions(-)

diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
index 9ad49aea2673b..ff8f2f9f9cae1 100644
--- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
+++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c
@@ -49,7 +49,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	lio_pci_readq(oct, CN23XX_RST_SOFT_RST);
 	lio_pci_writeq(oct, 1, CN23XX_RST_SOFT_RST);
 
-	/* Wait for 100ms as Octeon resets. */
+	/* Wait for 100ms as Octeon resets */
 	mdelay(100);
 
 	if (octeon_read_csr64(oct, CN23XX_SLI_SCRATCH1)) {
@@ -61,7 +61,7 @@ static int cn23xx_pf_soft_reset(struct octeon_device *oct)
 	dev_dbg(&oct->pci_dev->dev, "OCTEON[%d]: Reset completed\n",
 		oct->octeon_id);
 
-	/* restore the  reset value*/
+	/* Restore the reset value */
 	octeon_write_csr64(oct, CN23XX_WIN_WR_MASK_REG, 0xFF);
 
 	return 0;
@@ -121,7 +121,7 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us)
 	oqticks_per_us /= 1024;
 
 	/* time_intr is in microseconds. The next 2 steps gives the oq ticks
-	 *  corressponding to time_intr.
+	 * corresponding to time_intr.
 	 */
 	oqticks_per_us *= time_intr_in_us;
 	oqticks_per_us /= 1000;
@@ -136,11 +136,11 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	u64 reg_val;
 	u64 temp;
 
-	/* programming SRN and TRS for each MAC(0..3)  */
+	/* Programming SRN and TRS for each MAC(0..3) */
 
 	dev_dbg(&oct->pci_dev->dev, "%s:Using pcie port %d\n",
 		__func__, mac_no);
-	/* By default, mapping all 64 IOQs to  a single MACs */
+	/* By default, map all 64 IOQs to a single MAC */
 
 	reg_val =
 	    octeon_read_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num));
@@ -164,7 +164,7 @@ static void cn23xx_setup_global_mac_regs(struct octeon_device *oct)
 	temp = oct->sriov_info.max_vfs & 0xff;
 	reg_val |= (temp << CN23XX_PKT_MAC_CTL_RINFO_NVFS_BIT_POS);
 
-	/* write these settings to MAC register */
+	/* Write these settings to MAC register */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_MAC_RINFO64(mac_no, pf_num),
 			   reg_val);
 
@@ -183,10 +183,10 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 	srn = oct->sriov_info.pf_srn;
 	ern = srn + oct->sriov_info.num_pf_rings;
 
-	/*As per HRM reg description, s/w cant write 0 to ENB. */
-	/*to make the queue off, need to set the RST bit. */
+	/* As per HRM reg description, s/w can't write 0 to ENB. */
+	/* We need to set the RST bit, to turn the queue off. */
 
-	/* Reset the Enable bit for all the 64 IQs.  */
+	/* Reset the enable bit for all the 64 IQs. */
 	for (q_no = srn; q_no < ern; q_no++) {
 		/* set RST bit to 1. This bit applies to both IQ and OQ */
 		d64 = octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -194,7 +194,7 @@ static int cn23xx_reset_io_queues(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), d64);
 	}
 
-	/*wait until the RST bit is clear or the RST and quite bits are set*/
+	/* Wait until the RST bit is clear or the RST and quiet bits are set */
 	for (q_no = srn; q_no < ern; q_no++) {
 		u64 reg_val = octeon_read_csr64(oct,
 					CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -245,15 +245,15 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 	if (cn23xx_reset_io_queues(oct))
 		return -1;
 
-	/** Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
-	 * for all queues.Only PF can set these bits.
+	/* Set the MAC_NUM and PVF_NUM in IQ_PKT_CONTROL reg
+	 * for all queues. Only PF can set these bits.
 	 * bits 29:30 indicate the MAC num.
 	 * bits 32:47 indicate the PVF num.
 	 */
 	for (q_no = 0; q_no < ern; q_no++) {
 		reg_val = (u64)oct->pcie_port << CN23XX_PKT_INPUT_CTL_MAC_NUM_POS;
 
-		/* for VF assigned queues. */
+		/* For VF assigned queues. */
 		if (q_no < oct->sriov_info.pf_srn) {
 			vf_num = q_no / oct->sriov_info.rings_per_vf;
 			vf_num += 1; /* VF1, VF2,........ */
@@ -268,7 +268,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 				   reg_val);
 	}
 
-	/* Select ES, RO, NS, RDSIZE,DPTR Fomat#0 for
+	/* Select ES, RO, NS, RDSIZE,DPTR Format#0 for
 	 * pf queues
 	 */
 	for (q_no = srn; q_no < ern; q_no++) {
@@ -289,7 +289,7 @@ static int cn23xx_pf_setup_global_input_regs(struct octeon_device *oct)
 		octeon_write_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no),
 				   reg_val);
 
-		/* Set WMARK level for triggering PI_INT */
+		/* Set WMARK level to trigger PI_INT */
 		/* intr_threshold = CN23XX_DEF_IQ_INTR_THRESHOLD & */
 		intr_threshold = CFG_GET_IQ_INTR_PKT(cn23xx->conf) &
 				 CN23XX_PKT_IN_DONE_WMARK_MASK;
@@ -354,7 +354,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 		/* set the ES bit */
 		reg_val |= (CN23XX_PKT_OUTPUT_CTL_ES);
 
-		/* write all the selected settings */
+		/* Write all the selected settings */
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no), reg_val);
 
 		/* Enabling these interrupt in oct->fn_list.enable_interrupt()
@@ -373,7 +373,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 	/** Setting the water mark level for pko back pressure **/
 	writeq(0x40, (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OQ_WMARK);
 
-	/** Disabling setting OQs in reset when ring has no dorebells
+	/* Disabling setting OQs in reset when ring has no doorbells
 	 * enabling this will cause of head of line blocking
 	 */
 	/* Do it only for pass1.1. and pass1.2 */
@@ -383,7 +383,7 @@ static void cn23xx_pf_setup_global_output_regs(struct octeon_device *oct)
 				     CN23XX_SLI_GBL_CONTROL) | 0x2,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_GBL_CONTROL);
 
-	/** Enable channel-level backpressure */
+	/** Enable channel-level backpressure **/
 	if (oct->pf_num)
 		writeq(0xffffffffffffffffULL,
 		       (u8 *)oct->mmio[0].hw_addr + CN23XX_SLI_OUT_BP_EN2_W1S);
@@ -396,7 +396,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 {
 	cn23xx_enable_error_reporting(oct);
 
-	/* program the MAC(0..3)_RINFO before setting up input/output regs */
+	/* Program the MAC(0..3)_RINFO before setting up input/output regs */
 	cn23xx_setup_global_mac_regs(oct);
 
 	if (cn23xx_pf_setup_global_input_regs(oct))
@@ -410,7 +410,7 @@ static int cn23xx_setup_pf_device_regs(struct octeon_device *oct)
 	octeon_write_csr64(oct, CN23XX_SLI_WINDOW_CTL,
 			   CN23XX_SLI_WINDOW_CTL_DEFAULT);
 
-	/* set SLI_PKT_IN_JABBER to handle large VXLAN packets */
+	/* Set SLI_PKT_IN_JABBER to handle large VXLAN packets */
 	octeon_write_csr64(oct, CN23XX_SLI_PKT_IN_JABBER, CN23XX_INPUT_JABBER);
 	return 0;
 }
@@ -574,7 +574,7 @@ static int cn23xx_setup_pf_mbox(struct octeon_device *oct)
 		mbox->mbox_read_reg = (u8 *)oct->mmio[0].hw_addr +
 				      CN23XX_SLI_PKT_PF_VF_MBOX_SIG(q_no, 1);
 
-		/*Mail Box Thread creation*/
+		/* Mail Box Thread creation */
 		INIT_DELAYED_WORK(&mbox->mbox_poll_wk.work,
 				  cn23xx_pf_mbox_thread);
 		mbox->mbox_poll_wk.ctxptr = (void *)mbox;
@@ -626,7 +626,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	ern = srn + oct->num_iqs;
 
 	for (q_no = srn; q_no < ern; q_no++) {
-		/* set the corresponding IQ IS_64B bit */
+		/* Set the corresponding IQ IS_64B bit */
 		if (oct->io_qmask.iq64B & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr64(
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no));
@@ -635,7 +635,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 			    oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no), reg_val);
 		}
 
-		/* set the corresponding IQ ENB bit */
+		/* Set the corresponding IQ ENB bit */
 		if (oct->io_qmask.iq & BIT_ULL(q_no - srn)) {
 			/* IOQs are in reset by default in PEM2 mode,
 			 * clearing reset bit
@@ -681,7 +681,7 @@ static int cn23xx_enable_io_queues(struct octeon_device *oct)
 	}
 	for (q_no = srn; q_no < ern; q_no++) {
 		u32 reg_val;
-		/* set the corresponding OQ ENB bit */
+		/* Set the corresponding OQ ENB bit */
 		if (oct->io_qmask.oq & BIT_ULL(q_no - srn)) {
 			reg_val = octeon_read_csr(
 			    oct, CN23XX_SLI_OQ_PKT_CONTROL(q_no));
@@ -707,7 +707,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 	for (q_no = srn; q_no < ern; q_no++) {
 		loop = HZ;
 
-		/* start the Reset for a particular ring */
+		/* Start the Reset for a particular ring */
 		WRITE_ONCE(d64, octeon_read_csr64(
 			   oct, CN23XX_SLI_IQ_PKT_CONTROL64(q_no)));
 		WRITE_ONCE(d64, READ_ONCE(d64) &
@@ -740,7 +740,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 		loop = HZ;
 
 		/* Wait until hardware indicates that the particular IQ
-		 * is out of reset.It given that SLI_PKT_RING_RST is
+		 * is out of reset. Given that SLI_PKT_RING_RST is
 		 * common for both IQs and OQs
 		 */
 		WRITE_ONCE(d64, octeon_read_csr64(
@@ -760,7 +760,7 @@ static void cn23xx_disable_io_queues(struct octeon_device *oct)
 			schedule_timeout_uninterruptible(1);
 		}
 
-		/* clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
+		/* Clear the SLI_PKT(0..63)_CNTS[CNT] reg value */
 		WRITE_ONCE(d32, octeon_read_csr(
 					oct, CN23XX_SLI_OQ_PKTS_SENT(q_no)));
 		octeon_write_csr(oct, CN23XX_SLI_OQ_PKTS_SENT(q_no),
@@ -793,7 +793,7 @@ static u64 cn23xx_pf_msix_interrupt_handler(void *dev)
 	if (!pkts_sent || (pkts_sent == 0xFFFFFFFFFFFFFFFFULL))
 		return ret;
 
-	/* Write count reg in sli_pkt_cnts to clear these int.*/
+	/* Write count reg in sli_pkt_cnts to clear these int. */
 	if ((pkts_sent & CN23XX_INTR_PO_INT) ||
 	    (pkts_sent & CN23XX_INTR_PI_INT)) {
 		if (pkts_sent & CN23XX_INTR_PO_INT)
@@ -908,7 +908,7 @@ static u32 cn23xx_bar1_idx_read(struct octeon_device *oct, u32 idx)
 	    oct, CN23XX_PEM_BAR1_INDEX_REG(oct->pcie_port, idx));
 }
 
-/* always call with lock held */
+/* Always call with lock held */
 static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 {
 	u32 new_idx;
@@ -919,7 +919,7 @@ static u32 cn23xx_update_read_index(struct octeon_instr_queue *iq)
 	iq->pkt_in_done = pkt_in_done;
 
 	/* Modulo of the new index with the IQ size will give us
-	 * the new index.  The iq->reset_instr_cnt is always zero for
+	 * the new index. The iq->reset_instr_cnt is always zero for
 	 * cn23xx, so no extra adjustments are needed.
 	 */
 	new_idx = (iq->octeon_read_index +
@@ -934,8 +934,8 @@ static void cn23xx_enable_pf_interrupt(struct octeon_device *oct, u8 intr_flag)
 	struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip;
 	u64 intr_val = 0;
 
-	/*  Divide the single write to multiple writes based on the flag. */
-	/* Enable Interrupt */
+	/* Divide the single write to multiple writes based on the flag. */
+	/* Enable Interrupts */
 	if (intr_flag == OCTEON_ALL_INTR) {
 		writeq(cn23xx->intr_mask64, cn23xx->intr_enb_reg64);
 	} else if (intr_flag & OCTEON_OUTPUT_INTR) {
@@ -990,7 +990,7 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 
 	ret = 0;
 
-	/** Read Function Dependency Link reg to get the function number */
+	/* Read Function Dependency Link reg to get the function number */
 	if (pci_read_config_dword(oct->pci_dev, CN23XX_PCIE_SRIOV_FDL,
 				  &fdl_bit) == 0) {
 		oct->pf_num = ((fdl_bit >> CN23XX_PCIE_SRIOV_FDL_BIT_POS) &
@@ -1003,13 +1003,13 @@ static int cn23xx_get_pf_num(struct octeon_device *oct)
 		 * In this case, read the PF number from the
 		 * SLI_PKT0_INPUT_CONTROL reg (written by f/w)
 		 */
-		pkt0_in_ctl = octeon_read_csr64(oct,
-						CN23XX_SLI_IQ_PKT_CONTROL64(0));
+		pkt0_in_ctl =
+			octeon_read_csr64(oct, CN23XX_SLI_IQ_PKT_CONTROL64(0));
 		pfnum = (pkt0_in_ctl >> CN23XX_PKT_INPUT_CTL_PF_NUM_POS) &
 			CN23XX_PKT_INPUT_CTL_PF_NUM_MASK;
 		mac = (octeon_read_csr(oct, CN23XX_SLI_MAC_NUMBER)) & 0xff;
 
-		/* validate PF num by reading RINFO; f/w writes RINFO.trs == 1*/
+		/* Validate PF num by reading RINFO; f/w writes RINFO.trs == 1 */
 		d64 = octeon_read_csr64(oct,
 					CN23XX_SLI_PKT_MAC_RINFO64(mac, pfnum));
 		trs = (int)(d64 >> CN23XX_PKT_MAC_CTL_RINFO_TRS_BIT_POS) & 0xff;
@@ -1252,9 +1252,9 @@ int cn23xx_fw_loaded(struct octeon_device *oct)
 	u64 val;
 
 	/* If there's more than one active PF on this NIC, then that
-	 * implies that the NIC firmware is loaded and running.  This check
+	 * implies that the NIC firmware is loaded and running. This check
 	 * prevents a rare false negative that might occur if we only relied
-	 * on checking the SCR2_BIT_FW_LOADED flag.  The false negative would
+	 * on checking the SCR2_BIT_FW_LOADED flag. The false negative would
 	 * happen if the PF driver sees SCR2_BIT_FW_LOADED as cleared even
 	 * though the firmware was already loaded but still booting and has yet
 	 * to set SCR2_BIT_FW_LOADED.

From 6edd78af9506bb182518da7f6feebd75655d9a0e Mon Sep 17 00:00:00 2001
From: Alexey Kashavkin <akashavkin@gmail.com>
Date: Sun, 2 Mar 2025 00:14:36 +0300
Subject: [PATCH 2080/2753] netfilter: nft_exthdr: fix offset with
 ipv4_find_option()

There is an incorrect calculation in the offset variable which causes
the nft_skb_copy_to_reg() function to always return -EFAULT. Adding the
start variable is redundant. In the __ip_options_compile() function the
correct offset is specified when finding the function. There is no need
to add the size of the iphdr structure to the offset.

Fixes: dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options")
Signed-off-by: Alexey Kashavkin <akashavkin@gmail.com>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_exthdr.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index b8d03364566c1..c74012c991255 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -85,7 +85,6 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb,
 	unsigned char optbuf[sizeof(struct ip_options) + 40];
 	struct ip_options *opt = (struct ip_options *)optbuf;
 	struct iphdr *iph, _iph;
-	unsigned int start;
 	bool found = false;
 	__be32 info;
 	int optlen;
@@ -93,7 +92,6 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb,
 	iph = skb_header_pointer(skb, 0, sizeof(_iph), &_iph);
 	if (!iph)
 		return -EBADMSG;
-	start = sizeof(struct iphdr);
 
 	optlen = iph->ihl * 4 - (int)sizeof(struct iphdr);
 	if (optlen <= 0)
@@ -103,7 +101,7 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb,
 	/* Copy the options since __ip_options_compile() modifies
 	 * the options.
 	 */
-	if (skb_copy_bits(skb, start, opt->__data, optlen))
+	if (skb_copy_bits(skb, sizeof(struct iphdr), opt->__data, optlen))
 		return -EBADMSG;
 	opt->optlen = optlen;
 
@@ -118,18 +116,18 @@ static int ipv4_find_option(struct net *net, struct sk_buff *skb,
 		found = target == IPOPT_SSRR ? opt->is_strictroute :
 					       !opt->is_strictroute;
 		if (found)
-			*offset = opt->srr + start;
+			*offset = opt->srr;
 		break;
 	case IPOPT_RR:
 		if (!opt->rr)
 			break;
-		*offset = opt->rr + start;
+		*offset = opt->rr;
 		found = true;
 		break;
 	case IPOPT_RA:
 		if (!opt->router_alert)
 			break;
-		*offset = opt->router_alert + start;
+		*offset = opt->router_alert;
 		found = true;
 		break;
 	default:

From 05fd00e5e7b1ac60d264f72423fba38cc382b447 Mon Sep 17 00:00:00 2001
From: Jaakko Karrenpalo <jkarrenpalo@gmail.com>
Date: Fri, 7 Mar 2025 18:16:59 +0200
Subject: [PATCH 2081/2753] net: hsr: Fix PRP duplicate detection

Add PRP specific function for handling duplicate
packets. This is needed because of potential
L2 802.1p prioritization done by network switches.

The L2 prioritization can re-order the PRP packets
from a node causing the existing implementation to
discard the frame(s) that have been received 'late'
because the sequence number is before the previous
received packet. This can happen if the node is
sending multiple frames back-to-back with different
priority.

Signed-off-by: Jaakko Karrenpalo <jkarrenpalo@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250307161700.1045-1-jkarrenpalo@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/hsr/hsr_device.c   |  2 +
 net/hsr/hsr_forward.c  |  4 +-
 net/hsr/hsr_framereg.c | 95 ++++++++++++++++++++++++++++++++++++++++--
 net/hsr/hsr_framereg.h |  8 +++-
 net/hsr/hsr_main.h     |  2 +
 5 files changed, 104 insertions(+), 7 deletions(-)

diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
index c6f8614e9ed1f..439cfb7ad5d14 100644
--- a/net/hsr/hsr_device.c
+++ b/net/hsr/hsr_device.c
@@ -616,6 +616,7 @@ static struct hsr_proto_ops hsr_ops = {
 	.drop_frame = hsr_drop_frame,
 	.fill_frame_info = hsr_fill_frame_info,
 	.invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame,
+	.register_frame_out = hsr_register_frame_out,
 };
 
 static struct hsr_proto_ops prp_ops = {
@@ -626,6 +627,7 @@ static struct hsr_proto_ops prp_ops = {
 	.fill_frame_info = prp_fill_frame_info,
 	.handle_san_frame = prp_handle_san_frame,
 	.update_san_info = prp_update_san_info,
+	.register_frame_out = prp_register_frame_out,
 };
 
 void hsr_dev_setup(struct net_device *dev)
diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
index a4bacf1985558..c67c0d35921de 100644
--- a/net/hsr/hsr_forward.c
+++ b/net/hsr/hsr_forward.c
@@ -536,8 +536,8 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
 		 * Also for SAN, this shouldn't be done.
 		 */
 		if (!frame->is_from_san &&
-		    hsr_register_frame_out(port, frame->node_src,
-					   frame->sequence_nr))
+		    hsr->proto_ops->register_frame_out &&
+		    hsr->proto_ops->register_frame_out(port, frame))
 			continue;
 
 		if (frame->is_supervision && port->type == HSR_PT_MASTER &&
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 73bc6f659812f..85991fab7db58 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -35,6 +35,7 @@ static bool seq_nr_after(u16 a, u16 b)
 
 #define seq_nr_before(a, b)		seq_nr_after((b), (a))
 #define seq_nr_before_or_eq(a, b)	(!seq_nr_after((a), (b)))
+#define PRP_DROP_WINDOW_LEN 32768
 
 bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr)
 {
@@ -176,8 +177,11 @@ static struct hsr_node *hsr_add_node(struct hsr_priv *hsr,
 		new_node->time_in[i] = now;
 		new_node->time_out[i] = now;
 	}
-	for (i = 0; i < HSR_PT_PORTS; i++)
+	for (i = 0; i < HSR_PT_PORTS; i++) {
 		new_node->seq_out[i] = seq_out;
+		new_node->seq_expected[i] = seq_out + 1;
+		new_node->seq_start[i] = seq_out + 1;
+	}
 
 	if (san && hsr->proto_ops->handle_san_frame)
 		hsr->proto_ops->handle_san_frame(san, rx_port, new_node);
@@ -482,9 +486,11 @@ void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
  *	 0 otherwise, or
  *	 negative error code on error
  */
-int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
-			   u16 sequence_nr)
+int hsr_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame)
 {
+	struct hsr_node *node = frame->node_src;
+	u16 sequence_nr = frame->sequence_nr;
+
 	spin_lock_bh(&node->seq_out_lock);
 	if (seq_nr_before_or_eq(sequence_nr, node->seq_out[port->type]) &&
 	    time_is_after_jiffies(node->time_out[port->type] +
@@ -499,6 +505,89 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
 	return 0;
 }
 
+/* Adaptation of the PRP duplicate discard algorithm described in wireshark
+ * wiki (https://wiki.wireshark.org/PRP)
+ *
+ * A drop window is maintained for both LANs with start sequence set to the
+ * first sequence accepted on the LAN that has not been seen on the other LAN,
+ * and expected sequence set to the latest received sequence number plus one.
+ *
+ * When a frame is received on either LAN it is compared against the received
+ * frames on the other LAN. If it is outside the drop window of the other LAN
+ * the frame is accepted and the drop window is updated.
+ * The drop window for the other LAN is reset.
+ *
+ * 'port' is the outgoing interface
+ * 'frame' is the frame to be sent
+ *
+ * Return:
+ *	 1 if frame can be shown to have been sent recently on this interface,
+ *	 0 otherwise
+ */
+int prp_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame)
+{
+	enum hsr_port_type other_port;
+	enum hsr_port_type rcv_port;
+	struct hsr_node *node;
+	u16 sequence_diff;
+	u16 sequence_exp;
+	u16 sequence_nr;
+
+	/* out-going frames are always in order
+	 * and can be checked the same way as for HSR
+	 */
+	if (frame->port_rcv->type == HSR_PT_MASTER)
+		return hsr_register_frame_out(port, frame);
+
+	/* for PRP we should only forward frames from the slave ports
+	 * to the master port
+	 */
+	if (port->type != HSR_PT_MASTER)
+		return 1;
+
+	node = frame->node_src;
+	sequence_nr = frame->sequence_nr;
+	sequence_exp = sequence_nr + 1;
+	rcv_port = frame->port_rcv->type;
+	other_port = rcv_port == HSR_PT_SLAVE_A ? HSR_PT_SLAVE_B :
+				 HSR_PT_SLAVE_A;
+
+	spin_lock_bh(&node->seq_out_lock);
+	if (time_is_before_jiffies(node->time_out[port->type] +
+	    msecs_to_jiffies(HSR_ENTRY_FORGET_TIME)) ||
+	    (node->seq_start[rcv_port] == node->seq_expected[rcv_port] &&
+	     node->seq_start[other_port] == node->seq_expected[other_port])) {
+		/* the node hasn't been sending for a while
+		 * or both drop windows are empty, forward the frame
+		 */
+		node->seq_start[rcv_port] = sequence_nr;
+	} else if (seq_nr_before(sequence_nr, node->seq_expected[other_port]) &&
+		   seq_nr_before_or_eq(node->seq_start[other_port], sequence_nr)) {
+		/* drop the frame, update the drop window for the other port
+		 * and reset our drop window
+		 */
+		node->seq_start[other_port] = sequence_exp;
+		node->seq_expected[rcv_port] = sequence_exp;
+		node->seq_start[rcv_port] = node->seq_expected[rcv_port];
+		spin_unlock_bh(&node->seq_out_lock);
+		return 1;
+	}
+
+	/* update the drop window for the port where this frame was received
+	 * and clear the drop window for the other port
+	 */
+	node->seq_start[other_port] = node->seq_expected[other_port];
+	node->seq_expected[rcv_port] = sequence_exp;
+	sequence_diff = sequence_exp - node->seq_start[rcv_port];
+	if (sequence_diff > PRP_DROP_WINDOW_LEN)
+		node->seq_start[rcv_port] = sequence_exp - PRP_DROP_WINDOW_LEN;
+
+	node->time_out[port->type] = jiffies;
+	node->seq_out[port->type] = sequence_nr;
+	spin_unlock_bh(&node->seq_out_lock);
+	return 0;
+}
+
 static struct hsr_port *get_late_port(struct hsr_priv *hsr,
 				      struct hsr_node *node)
 {
diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
index 993fa950d8144..b04948659d84d 100644
--- a/net/hsr/hsr_framereg.h
+++ b/net/hsr/hsr_framereg.h
@@ -44,8 +44,7 @@ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb,
 
 void hsr_register_frame_in(struct hsr_node *node, struct hsr_port *port,
 			   u16 sequence_nr);
-int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node,
-			   u16 sequence_nr);
+int hsr_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame);
 
 void hsr_prune_nodes(struct timer_list *t);
 void hsr_prune_proxy_nodes(struct timer_list *t);
@@ -73,6 +72,8 @@ void prp_update_san_info(struct hsr_node *node, bool is_sup);
 bool hsr_is_node_in_db(struct list_head *node_db,
 		       const unsigned char addr[ETH_ALEN]);
 
+int prp_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame);
+
 struct hsr_node {
 	struct list_head	mac_list;
 	/* Protect R/W access to seq_out */
@@ -89,6 +90,9 @@ struct hsr_node {
 	bool			san_b;
 	u16			seq_out[HSR_PT_PORTS];
 	bool			removed;
+	/* PRP specific duplicate handling */
+	u16			seq_expected[HSR_PT_PORTS];
+	u16			seq_start[HSR_PT_PORTS];
 	struct rcu_head		rcu_head;
 };
 
diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
index 7561845b8bf6f..1bc47b17a2968 100644
--- a/net/hsr/hsr_main.h
+++ b/net/hsr/hsr_main.h
@@ -175,6 +175,8 @@ struct hsr_proto_ops {
 			       struct hsr_frame_info *frame);
 	bool (*invalid_dan_ingress_frame)(__be16 protocol);
 	void (*update_san_info)(struct hsr_node *node, bool is_sup);
+	int (*register_frame_out)(struct hsr_port *port,
+				  struct hsr_frame_info *frame);
 };
 
 struct hsr_self_node {

From 814dbf4b6c955cad72e787a44f6e0cf90afc8fda Mon Sep 17 00:00:00 2001
From: Jaakko Karrenpalo <jkarrenpalo@gmail.com>
Date: Fri, 7 Mar 2025 18:17:00 +0200
Subject: [PATCH 2082/2753] net: hsr: Add KUnit test for PRP

Add unit tests for the PRP duplicate detection

Signed-off-by: Jaakko Karrenpalo <jkarrenpalo@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250307161700.1045-2-jkarrenpalo@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/hsr/Kconfig                |  18 +++
 net/hsr/Makefile               |   2 +
 net/hsr/hsr_framereg.c         |   4 +
 net/hsr/prp_dup_discard_test.c | 212 +++++++++++++++++++++++++++++++++
 4 files changed, 236 insertions(+)
 create mode 100644 net/hsr/prp_dup_discard_test.c

diff --git a/net/hsr/Kconfig b/net/hsr/Kconfig
index 1b048c17b6c83..fcacdf4f0ffc3 100644
--- a/net/hsr/Kconfig
+++ b/net/hsr/Kconfig
@@ -38,3 +38,21 @@ config HSR
 	  relying on this code in a safety critical system!
 
 	  If unsure, say N.
+
+if HSR
+
+config PRP_DUP_DISCARD_KUNIT_TEST
+	tristate "PRP duplicate discard KUnit tests" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	help
+	  Covers the PRP duplicate discard algorithm.
+	  Only useful for kernel devs running KUnit test harness and are not
+	  for inclusion into a production build.
+
+	  For more information on KUnit and unit tests in general please refer
+	  to the KUnit documentation in Documentation/dev-tools/kunit/.
+
+	  If unsure, say N.
+
+endif
diff --git a/net/hsr/Makefile b/net/hsr/Makefile
index 75df90d3b4162..34e581db5c413 100644
--- a/net/hsr/Makefile
+++ b/net/hsr/Makefile
@@ -8,3 +8,5 @@ obj-$(CONFIG_HSR)	+= hsr.o
 hsr-y			:= hsr_main.o hsr_framereg.o hsr_device.o \
 			   hsr_netlink.o hsr_slave.o hsr_forward.o
 hsr-$(CONFIG_DEBUG_FS) += hsr_debugfs.o
+
+obj-$(CONFIG_PRP_DUP_DISCARD_KUNIT_TEST) += prp_dup_discard_test.o
diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
index 85991fab7db58..4ce471a2f3870 100644
--- a/net/hsr/hsr_framereg.c
+++ b/net/hsr/hsr_framereg.c
@@ -588,6 +588,10 @@ int prp_register_frame_out(struct hsr_port *port, struct hsr_frame_info *frame)
 	return 0;
 }
 
+#if IS_MODULE(CONFIG_PRP_DUP_DISCARD_KUNIT_TEST)
+EXPORT_SYMBOL(prp_register_frame_out);
+#endif
+
 static struct hsr_port *get_late_port(struct hsr_priv *hsr,
 				      struct hsr_node *node)
 {
diff --git a/net/hsr/prp_dup_discard_test.c b/net/hsr/prp_dup_discard_test.c
new file mode 100644
index 0000000000000..e86b7b633ae89
--- /dev/null
+++ b/net/hsr/prp_dup_discard_test.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <kunit/test.h>
+
+#include "hsr_main.h"
+#include "hsr_framereg.h"
+
+struct prp_test_data {
+	struct hsr_port port;
+	struct hsr_port port_rcv;
+	struct hsr_frame_info frame;
+	struct hsr_node node;
+};
+
+static struct prp_test_data *build_prp_test_data(struct kunit *test)
+{
+	struct prp_test_data *data = kunit_kzalloc(test,
+		sizeof(struct prp_test_data), GFP_USER);
+	KUNIT_EXPECT_NOT_ERR_OR_NULL(test, data);
+
+	data->frame.node_src = &data->node;
+	data->frame.port_rcv = &data->port_rcv;
+	data->port_rcv.type = HSR_PT_SLAVE_A;
+	data->node.seq_start[HSR_PT_SLAVE_A] = 1;
+	data->node.seq_expected[HSR_PT_SLAVE_A] = 1;
+	data->node.seq_start[HSR_PT_SLAVE_B] = 1;
+	data->node.seq_expected[HSR_PT_SLAVE_B] = 1;
+	data->node.seq_out[HSR_PT_MASTER] = 0;
+	data->node.time_out[HSR_PT_MASTER] = jiffies;
+	data->port.type = HSR_PT_MASTER;
+
+	return data;
+}
+
+static void check_prp_counters(struct kunit *test,
+			       struct prp_test_data *data,
+			       u16 seq_start_a, u16 seq_expected_a,
+			       u16 seq_start_b, u16 seq_expected_b)
+{
+	KUNIT_EXPECT_EQ(test, data->node.seq_start[HSR_PT_SLAVE_A],
+			seq_start_a);
+	KUNIT_EXPECT_EQ(test, data->node.seq_start[HSR_PT_SLAVE_B],
+			seq_start_b);
+	KUNIT_EXPECT_EQ(test, data->node.seq_expected[HSR_PT_SLAVE_A],
+			seq_expected_a);
+	KUNIT_EXPECT_EQ(test, data->node.seq_expected[HSR_PT_SLAVE_B],
+			seq_expected_b);
+}
+
+static void prp_dup_discard_forward(struct kunit *test)
+{
+	/* Normal situation, both LANs in sync. Next frame is forwarded */
+	struct prp_test_data *data = build_prp_test_data(test);
+
+	data->frame.sequence_nr = 2;
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	KUNIT_EXPECT_EQ(test, jiffies, data->node.time_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, data->frame.sequence_nr,
+			   data->frame.sequence_nr + 1, 1, 1);
+}
+
+static void prp_dup_discard_inside_dropwindow(struct kunit *test)
+{
+	/* Normal situation, other LAN ahead by one. Frame is dropped */
+	struct prp_test_data *data = build_prp_test_data(test);
+	unsigned long time = jiffies - 10;
+
+	data->frame.sequence_nr = 1;
+	data->node.seq_expected[HSR_PT_SLAVE_B] = 3;
+	data->node.seq_out[HSR_PT_MASTER] = 2;
+	data->node.time_out[HSR_PT_MASTER] = time;
+
+	KUNIT_EXPECT_EQ(test, 1,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, 2, data->node.seq_out[HSR_PT_MASTER]);
+	KUNIT_EXPECT_EQ(test, time, data->node.time_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, 2, 2, 2, 3);
+}
+
+static void prp_dup_discard_node_timeout(struct kunit *test)
+{
+	/* Timeout situation, node hasn't sent anything for a while */
+	struct prp_test_data *data = build_prp_test_data(test);
+
+	data->frame.sequence_nr = 7;
+	data->node.seq_start[HSR_PT_SLAVE_A] = 1234;
+	data->node.seq_expected[HSR_PT_SLAVE_A] = 1235;
+	data->node.seq_start[HSR_PT_SLAVE_B] = 1234;
+	data->node.seq_expected[HSR_PT_SLAVE_B] = 1234;
+	data->node.seq_out[HSR_PT_MASTER] = 1234;
+	data->node.time_out[HSR_PT_MASTER] =
+		jiffies - msecs_to_jiffies(HSR_ENTRY_FORGET_TIME) - 1;
+
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	KUNIT_EXPECT_EQ(test, jiffies, data->node.time_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, data->frame.sequence_nr,
+			   data->frame.sequence_nr + 1, 1234, 1234);
+}
+
+static void prp_dup_discard_out_of_sequence(struct kunit *test)
+{
+	/* One frame is received out of sequence on both LANs */
+	struct prp_test_data *data = build_prp_test_data(test);
+
+	data->node.seq_start[HSR_PT_SLAVE_A] = 10;
+	data->node.seq_expected[HSR_PT_SLAVE_A] = 10;
+	data->node.seq_start[HSR_PT_SLAVE_B] = 10;
+	data->node.seq_expected[HSR_PT_SLAVE_B] = 10;
+	data->node.seq_out[HSR_PT_MASTER] = 9;
+
+	/* 1st old frame, should be accepted */
+	data->frame.sequence_nr = 8;
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, data->frame.sequence_nr,
+			   data->frame.sequence_nr + 1, 10, 10);
+
+	/* 2nd frame should be dropped */
+	data->frame.sequence_nr = 8;
+	data->port_rcv.type = HSR_PT_SLAVE_B;
+	KUNIT_EXPECT_EQ(test, 1,
+			prp_register_frame_out(&data->port, &data->frame));
+	check_prp_counters(test, data, data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1);
+
+	/* Next frame, this is forwarded */
+	data->frame.sequence_nr = 10;
+	data->port_rcv.type = HSR_PT_SLAVE_A;
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, data->frame.sequence_nr,
+			   data->frame.sequence_nr + 1, 9, 9);
+
+	/* and next one is dropped */
+	data->frame.sequence_nr = 10;
+	data->port_rcv.type = HSR_PT_SLAVE_B;
+	KUNIT_EXPECT_EQ(test, 1,
+			prp_register_frame_out(&data->port, &data->frame));
+	check_prp_counters(test, data, data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1,
+			   data->frame.sequence_nr + 1);
+}
+
+static void prp_dup_discard_lan_b_late(struct kunit *test)
+{
+	/* LAN B is behind */
+	struct prp_test_data *data = build_prp_test_data(test);
+
+	data->node.seq_start[HSR_PT_SLAVE_A] = 9;
+	data->node.seq_expected[HSR_PT_SLAVE_A] = 9;
+	data->node.seq_start[HSR_PT_SLAVE_B] = 9;
+	data->node.seq_expected[HSR_PT_SLAVE_B] = 9;
+	data->node.seq_out[HSR_PT_MASTER] = 8;
+
+	data->frame.sequence_nr = 9;
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, 9, 10, 9, 9);
+
+	data->frame.sequence_nr = 10;
+	KUNIT_EXPECT_EQ(test, 0,
+			prp_register_frame_out(&data->port, &data->frame));
+	KUNIT_EXPECT_EQ(test, data->frame.sequence_nr,
+			data->node.seq_out[HSR_PT_MASTER]);
+	check_prp_counters(test, data, 9, 11, 9, 9);
+
+	data->frame.sequence_nr = 9;
+	data->port_rcv.type = HSR_PT_SLAVE_B;
+	KUNIT_EXPECT_EQ(test, 1,
+			prp_register_frame_out(&data->port, &data->frame));
+	check_prp_counters(test, data, 10, 11, 10, 10);
+
+	data->frame.sequence_nr = 10;
+	data->port_rcv.type = HSR_PT_SLAVE_B;
+	KUNIT_EXPECT_EQ(test, 1,
+			prp_register_frame_out(&data->port, &data->frame));
+	check_prp_counters(test, data,  11, 11, 11, 11);
+}
+
+static struct kunit_case prp_dup_discard_test_cases[] = {
+	KUNIT_CASE(prp_dup_discard_forward),
+	KUNIT_CASE(prp_dup_discard_inside_dropwindow),
+	KUNIT_CASE(prp_dup_discard_node_timeout),
+	KUNIT_CASE(prp_dup_discard_out_of_sequence),
+	KUNIT_CASE(prp_dup_discard_lan_b_late),
+	{}
+};
+
+static struct kunit_suite prp_dup_discard_suite = {
+	.name = "prp_duplicate_discard",
+	.test_cases = prp_dup_discard_test_cases,
+};
+
+kunit_test_suite(prp_dup_discard_suite);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("KUnit tests for PRP duplicate discard");
+MODULE_AUTHOR("Jaakko Karrenpalo <jkarrenpalo@gmail.com>");

From 183185a18ff96751db52a46ccf93fff3a1f42815 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 7 Mar 2025 20:28:53 +0100
Subject: [PATCH 2083/2753] gre: Fix IPv6 link-local address generation.

Use addrconf_addr_gen() to generate IPv6 link-local addresses on GRE
devices in most cases and fall back to using add_v4_addrs() only in
case the GRE configuration is incompatible with addrconf_addr_gen().

GRE used to use addrconf_addr_gen() until commit e5dd729460ca
("ip/ip6_gre: use the same logic as SIT interfaces when computing v6LL
address") restricted this use to gretap and ip6gretap devices, and
created add_v4_addrs() (borrowed from SIT) for non-Ethernet GRE ones.

The original problem came when commit 9af28511be10 ("addrconf: refuse
isatap eui64 for INADDR_ANY") made __ipv6_isatap_ifid() fail when its
addr parameter was 0. The commit says that this would create an invalid
address, however, I couldn't find any RFC saying that the generated
interface identifier would be wrong. Anyway, since gre over IPv4
devices pass their local tunnel address to __ipv6_isatap_ifid(), that
commit broke their IPv6 link-local address generation when the local
address was unspecified.

Then commit e5dd729460ca ("ip/ip6_gre: use the same logic as SIT
interfaces when computing v6LL address") tried to fix that case by
defining add_v4_addrs() and calling it to generate the IPv6 link-local
address instead of using addrconf_addr_gen() (apart for gretap and
ip6gretap devices, which would still use the regular
addrconf_addr_gen(), since they have a MAC address).

That broke several use cases because add_v4_addrs() isn't properly
integrated into the rest of IPv6 Neighbor Discovery code. Several of
these shortcomings have been fixed over time, but add_v4_addrs()
remains broken on several aspects. In particular, it doesn't send any
Router Sollicitations, so the SLAAC process doesn't start until the
interface receives a Router Advertisement. Also, add_v4_addrs() mostly
ignores the address generation mode of the interface
(/proc/sys/net/ipv6/conf/*/addr_gen_mode), thus breaking the
IN6_ADDR_GEN_MODE_RANDOM and IN6_ADDR_GEN_MODE_STABLE_PRIVACY cases.

Fix the situation by using add_v4_addrs() only in the specific scenario
where the normal method would fail. That is, for interfaces that have
all of the following characteristics:

  * run over IPv4,
  * transport IP packets directly, not Ethernet (that is, not gretap
    interfaces),
  * tunnel endpoint is INADDR_ANY (that is, 0),
  * device address generation mode is EUI64.

In all other cases, revert back to the regular addrconf_addr_gen().

Also, remove the special case for ip6gre interfaces in add_v4_addrs(),
since ip6gre devices now always use addrconf_addr_gen() instead.

Fixes: e5dd729460ca ("ip/ip6_gre: use the same logic as SIT interfaces when computing v6LL address")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Link: https://patch.msgid.link/559c32ce5c9976b269e6337ac9abb6a96abe5096.1741375285.git.gnault@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/addrconf.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ac8cc10765360..8b6258819dade 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3209,16 +3209,13 @@ static void add_v4_addrs(struct inet6_dev *idev)
 	struct in6_addr addr;
 	struct net_device *dev;
 	struct net *net = dev_net(idev->dev);
-	int scope, plen, offset = 0;
+	int scope, plen;
 	u32 pflags = 0;
 
 	ASSERT_RTNL();
 
 	memset(&addr, 0, sizeof(struct in6_addr));
-	/* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
-	if (idev->dev->addr_len == sizeof(struct in6_addr))
-		offset = sizeof(struct in6_addr) - 4;
-	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
+	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
 
 	if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
 		scope = IPV6_ADDR_COMPATv4;
@@ -3529,7 +3526,13 @@ static void addrconf_gre_config(struct net_device *dev)
 		return;
 	}
 
-	if (dev->type == ARPHRD_ETHER) {
+	/* Generate the IPv6 link-local address using addrconf_addr_gen(),
+	 * unless we have an IPv4 GRE device not bound to an IP address and
+	 * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
+	 * case). Such devices fall back to add_v4_addrs() instead.
+	 */
+	if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
+	      idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
 		addrconf_addr_gen(idev, true);
 		return;
 	}

From 6f50175ccad4278ed3a9394c00b797b75441bd6e Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Fri, 7 Mar 2025 20:28:58 +0100
Subject: [PATCH 2084/2753] selftests: Add IPv6 link-local address generation
 tests for GRE devices.

GRE devices have their special code for IPv6 link-local address
generation that has been the source of several regressions in the past.

Add selftest to check that all gre, ip6gre, gretap and ip6gretap get an
IPv6 link-link local address in accordance with the
net.ipv6.conf.<dev>.addr_gen_mode sysctl.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/2d6772af8e1da9016b2180ec3f8d9ee99f470c77.1741375285.git.gnault@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 +
 .../testing/selftests/net/gre_ipv6_lladdr.sh  | 177 ++++++++++++++++++
 2 files changed, 178 insertions(+)
 create mode 100755 tools/testing/selftests/net/gre_ipv6_lladdr.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 73ee88d6b0430..5916f3b81c39f 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,6 +31,7 @@ TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
+TEST_PROGS += gre_ipv6_lladdr.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
new file mode 100755
index 0000000000000..5b34f6e1f8314
--- /dev/null
+++ b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
@@ -0,0 +1,177 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+
+source ./lib.sh
+
+PAUSE_ON_FAIL="no"
+
+# The trap function handler
+#
+exit_cleanup_all()
+{
+	cleanup_all_ns
+
+	exit "${EXIT_STATUS}"
+}
+
+# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
+# underlay by future GRE devices.
+#
+setup_basenet()
+{
+	ip -netns "${NS0}" link set dev lo up
+	ip -netns "${NS0}" address add dev lo 192.0.2.10/24
+	ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
+}
+
+# Check if network device has an IPv6 link-local address assigned.
+#
+# Parameters:
+#
+#   * $1: The network device to test
+#   * $2: An extra regular expression that should be matched (to verify the
+#         presence of extra attributes)
+#   * $3: The expected return code from grep (to allow checking the absence of
+#         a link-local address)
+#   * $4: The user visible name for the scenario being tested
+#
+check_ipv6_ll_addr()
+{
+	local DEV="$1"
+	local EXTRA_MATCH="$2"
+	local XRET="$3"
+	local MSG="$4"
+
+	RET=0
+	set +e
+	ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
+	check_err_fail "${XRET}" $? ""
+	log_test "${MSG}"
+	set -e
+}
+
+# Create a GRE device and verify that it gets an IPv6 link-local address as
+# expected.
+#
+# Parameters:
+#
+#   * $1: The device type (gre, ip6gre, gretap or ip6gretap)
+#   * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
+#   * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
+#   * $4: The IPv6 interface identifier generation mode to use for the GRE
+#         device (eui64, none, stable-privacy or random).
+#
+test_gre_device()
+{
+	local GRE_TYPE="$1"
+	local LOCAL_IP="$2"
+	local REMOTE_IP="$3"
+	local MODE="$4"
+	local ADDR_GEN_MODE
+	local MATCH_REGEXP
+	local MSG
+
+	ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
+
+	case "${MODE}" in
+	    "eui64")
+		ADDR_GEN_MODE=0
+		MATCH_REGEXP=""
+		MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		;;
+	    "none")
+		ADDR_GEN_MODE=1
+		MATCH_REGEXP=""
+		MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=1 # No link-local address should be generated
+		;;
+	    "stable-privacy")
+		ADDR_GEN_MODE=2
+		MATCH_REGEXP="stable-privacy"
+		MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		# Initialise stable_secret (required for stable-privacy mode)
+		ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
+		;;
+	    "random")
+		ADDR_GEN_MODE=3
+		MATCH_REGEXP="stable-privacy"
+		MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
+		XRET=0
+		;;
+	esac
+
+	# Check that IPv6 link-local address is generated when device goes up
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+	ip -netns "${NS0}" link set dev gretest up
+	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
+
+	# Now disable link-local address generation
+	ip -netns "${NS0}" link set dev gretest down
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
+	ip -netns "${NS0}" link set dev gretest up
+
+	# Check that link-local address generation works when re-enabled while
+	# the device is already up
+	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
+	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
+
+	ip -netns "${NS0}" link del dev gretest
+}
+
+test_gre4()
+{
+	local GRE_TYPE
+	local MODE
+
+	for GRE_TYPE in "gre" "gretap"; do
+		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+		for MODE in "eui64" "none" "stable-privacy" "random"; do
+			test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
+		done
+	done
+}
+
+test_gre6()
+{
+	local GRE_TYPE
+	local MODE
+
+	for GRE_TYPE in "ip6gre" "ip6gretap"; do
+		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
+
+		for MODE in "eui64" "none" "stable-privacy" "random"; do
+			test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
+			test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
+		done
+	done
+}
+
+usage()
+{
+	echo "Usage: $0 [-p]"
+	exit 1
+}
+
+while getopts :p o
+do
+	case $o in
+		p) PAUSE_ON_FAIL="yes";;
+		*) usage;;
+	esac
+done
+
+setup_ns NS0
+
+set -e
+trap exit_cleanup_all EXIT
+
+setup_basenet
+
+test_gre4
+test_gre6

From a1e64addf3ff9257b45b78bc7d743781c3f41340 Mon Sep 17 00:00:00 2001
From: Ilya Maximets <i.maximets@ovn.org>
Date: Sat, 8 Mar 2025 01:45:59 +0100
Subject: [PATCH 2085/2753] net: openvswitch: remove misbehaving actions length
 check

The actions length check is unreliable and produces different results
depending on the initial length of the provided netlink attribute and
the composition of the actual actions inside of it.  For example, a
user can add 4088 empty clone() actions without triggering -EMSGSIZE,
on attempt to add 4089 such actions the operation will fail with the
-EMSGSIZE verdict.  However, if another 16 KB of other actions will
be *appended* to the previous 4089 clone() actions, the check passes
and the flow is successfully installed into the openvswitch datapath.

The reason for a such a weird behavior is the way memory is allocated.
When ovs_flow_cmd_new() is invoked, it calls ovs_nla_copy_actions(),
that in turn calls nla_alloc_flow_actions() with either the actual
length of the user-provided actions or the MAX_ACTIONS_BUFSIZE.  The
function adds the size of the sw_flow_actions structure and then the
actually allocated memory is rounded up to the closest power of two.

So, if the user-provided actions are larger than MAX_ACTIONS_BUFSIZE,
then MAX_ACTIONS_BUFSIZE + sizeof(*sfa) rounded up is 32K + 24 -> 64K.
Later, while copying individual actions, we look at ksize(), which is
64K, so this way the MAX_ACTIONS_BUFSIZE check is not actually
triggered and the user can easily allocate almost 64 KB of actions.

However, when the initial size is less than MAX_ACTIONS_BUFSIZE, but
the actions contain ones that require size increase while copying
(such as clone() or sample()), then the limit check will be performed
during the reserve_sfa_size() and the user will not be allowed to
create actions that yield more than 32 KB internally.

This is one part of the problem.  The other part is that it's not
actually possible for the userspace application to know beforehand
if the particular set of actions will be rejected or not.

Certain actions require more space in the internal representation,
e.g. an empty clone() takes 4 bytes in the action list passed in by
the user, but it takes 12 bytes in the internal representation due
to an extra nested attribute, and some actions require less space in
the internal representations, e.g. set(tunnel(..)) normally takes
64+ bytes in the action list provided by the user, but only needs to
store a single pointer in the internal implementation, since all the
data is stored in the tunnel_info structure instead.

And the action size limit is applied to the internal representation,
not to the action list passed by the user.  So, it's not possible for
the userpsace application to predict if the certain combination of
actions will be rejected or not, because it is not possible for it to
calculate how much space these actions will take in the internal
representation without knowing kernel internals.

All that is causing random failures in ovs-vswitchd in userspace and
inability to handle certain traffic patterns as a result.  For example,
it is reported that adding a bit more than a 1100 VMs in an OpenStack
setup breaks the network due to OVS not being able to handle ARP
traffic anymore in some cases (it tries to install a proper datapath
flow, but the kernel rejects it with -EMSGSIZE, even though the action
list isn't actually that large.)

Kernel behavior must be consistent and predictable in order for the
userspace application to use it in a reasonable way.  ovs-vswitchd has
a mechanism to re-direct parts of the traffic and partially handle it
in userspace if the required action list is oversized, but that doesn't
work properly if we can't actually tell if the action list is oversized
or not.

Solution for this is to check the size of the user-provided actions
instead of the internal representation.  This commit just removes the
check from the internal part because there is already an implicit size
check imposed by the netlink protocol.  The attribute can't be larger
than 64 KB.  Realistically, we could reduce the limit to 32 KB, but
we'll be risking to break some existing setups that rely on the fact
that it's possible to create nearly 64 KB action lists today.

Vast majority of flows in real setups are below 100-ish bytes.  So
removal of the limit will not change real memory consumption on the
system.  The absolutely worst case scenario is if someone adds a flow
with 64 KB of empty clone() actions.  That will yield a 192 KB in the
internal representation consuming 256 KB block of memory.  However,
that list of actions is not meaningful and also a no-op.  Real world
very large action lists (that can occur for a rare cases of BUM
traffic handling) are unlikely to contain a large number of clones and
will likely have a lot of tunnel attributes making the internal
representation comparable in size to the original action list.
So, it should be fine to just remove the limit.

Commit in the 'Fixes' tag is the first one that introduced the
difference between internal representation and the user-provided action
lists, but there were many more afterwards that lead to the situation
we have today.

Fixes: 7d5437c709de ("openvswitch: Add tunneling interface.")
Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Link: https://patch.msgid.link/20250308004609.2881861-1-i.maximets@ovn.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/flow_netlink.c | 15 +--------------
 1 file changed, 1 insertion(+), 14 deletions(-)

diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c
index 881ddd3696d54..95e0dd14dc1a3 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -2317,14 +2317,10 @@ int ovs_nla_put_mask(const struct sw_flow *flow, struct sk_buff *skb)
 				OVS_FLOW_ATTR_MASK, true, skb);
 }
 
-#define MAX_ACTIONS_BUFSIZE	(32 * 1024)
-
 static struct sw_flow_actions *nla_alloc_flow_actions(int size)
 {
 	struct sw_flow_actions *sfa;
 
-	WARN_ON_ONCE(size > MAX_ACTIONS_BUFSIZE);
-
 	sfa = kmalloc(kmalloc_size_roundup(sizeof(*sfa) + size), GFP_KERNEL);
 	if (!sfa)
 		return ERR_PTR(-ENOMEM);
@@ -2480,15 +2476,6 @@ static struct nlattr *reserve_sfa_size(struct sw_flow_actions **sfa,
 
 	new_acts_size = max(next_offset + req_size, ksize(*sfa) * 2);
 
-	if (new_acts_size > MAX_ACTIONS_BUFSIZE) {
-		if ((next_offset + req_size) > MAX_ACTIONS_BUFSIZE) {
-			OVS_NLERR(log, "Flow action size exceeds max %u",
-				  MAX_ACTIONS_BUFSIZE);
-			return ERR_PTR(-EMSGSIZE);
-		}
-		new_acts_size = MAX_ACTIONS_BUFSIZE;
-	}
-
 	acts = nla_alloc_flow_actions(new_acts_size);
 	if (IS_ERR(acts))
 		return ERR_CAST(acts);
@@ -3545,7 +3532,7 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr,
 	int err;
 	u32 mpls_label_count = 0;
 
-	*sfa = nla_alloc_flow_actions(min(nla_len(attr), MAX_ACTIONS_BUFSIZE));
+	*sfa = nla_alloc_flow_actions(nla_len(attr));
 	if (IS_ERR(*sfa))
 		return PTR_ERR(*sfa);
 

From 1063ae07383c0ddc5bcce170260c143825846b03 Mon Sep 17 00:00:00 2001
From: Xin Long <lucien.xin@gmail.com>
Date: Sat, 8 Mar 2025 13:05:43 -0500
Subject: [PATCH 2086/2753] Revert "openvswitch: switch to per-action label
 counting in conntrack"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Currently, ovs_ct_set_labels() is only called for confirmed conntrack
entries (ct) within ovs_ct_commit(). However, if the conntrack entry
does not have the labels_ext extension, attempting to allocate it in
ovs_ct_get_conn_labels() for a confirmed entry triggers a warning in
nf_ct_ext_add():

  WARN_ON(nf_ct_is_confirmed(ct));

This happens when the conntrack entry is created externally before OVS
increments net->ct.labels_used. The issue has become more likely since
commit fcb1aa5163b1 ("openvswitch: switch to per-action label counting
in conntrack"), which changed to use per-action label counting and
increment net->ct.labels_used when a flow with ct action is added.

Since there’s no straightforward way to fully resolve this issue at the
moment, this reverts the commit to avoid breaking existing use cases.

Fixes: fcb1aa5163b1 ("openvswitch: switch to per-action label counting in conntrack")
Reported-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Xin Long <lucien.xin@gmail.com>
Acked-by: Aaron Conole <aconole@redhat.com>
Link: https://patch.msgid.link/1bdeb2f3a812bca016a225d3de714427b2cd4772.1741457143.git.lucien.xin@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/openvswitch/conntrack.c | 30 ++++++++++++++++++------------
 net/openvswitch/datapath.h  |  3 +++
 2 files changed, 21 insertions(+), 12 deletions(-)

diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index 3bb4810234aac..e573e92213029 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -1368,8 +1368,11 @@ bool ovs_ct_verify(struct net *net, enum ovs_key_attr attr)
 	    attr == OVS_KEY_ATTR_CT_MARK)
 		return true;
 	if (IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) &&
-	    attr == OVS_KEY_ATTR_CT_LABELS)
-		return true;
+	    attr == OVS_KEY_ATTR_CT_LABELS) {
+		struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
+
+		return ovs_net->xt_label;
+	}
 
 	return false;
 }
@@ -1378,7 +1381,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		       const struct sw_flow_key *key,
 		       struct sw_flow_actions **sfa,  bool log)
 {
-	unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
 	struct ovs_conntrack_info ct_info;
 	const char *helper = NULL;
 	u16 family;
@@ -1407,12 +1409,6 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr,
 		return -ENOMEM;
 	}
 
-	if (nf_connlabels_get(net, n_bits - 1)) {
-		nf_ct_tmpl_free(ct_info.ct);
-		OVS_NLERR(log, "Failed to set connlabel length");
-		return -EOPNOTSUPP;
-	}
-
 	if (ct_info.timeout[0]) {
 		if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto,
 				      ct_info.timeout))
@@ -1581,7 +1577,6 @@ static void __ovs_ct_free_action(struct ovs_conntrack_info *ct_info)
 	if (ct_info->ct) {
 		if (ct_info->timeout[0])
 			nf_ct_destroy_timeout(ct_info->ct);
-		nf_connlabels_put(nf_ct_net(ct_info->ct));
 		nf_ct_tmpl_free(ct_info->ct);
 	}
 }
@@ -2006,9 +2001,17 @@ struct genl_family dp_ct_limit_genl_family __ro_after_init = {
 
 int ovs_ct_init(struct net *net)
 {
-#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+	unsigned int n_bits = sizeof(struct ovs_key_ct_labels) * BITS_PER_BYTE;
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
 
+	if (nf_connlabels_get(net, n_bits - 1)) {
+		ovs_net->xt_label = false;
+		OVS_NLERR(true, "Failed to set connlabel length");
+	} else {
+		ovs_net->xt_label = true;
+	}
+
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	return ovs_ct_limit_init(net, ovs_net);
 #else
 	return 0;
@@ -2017,9 +2020,12 @@ int ovs_ct_init(struct net *net)
 
 void ovs_ct_exit(struct net *net)
 {
-#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_net *ovs_net = net_generic(net, ovs_net_id);
 
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	ovs_ct_limit_exit(net, ovs_net);
 #endif
+
+	if (ovs_net->xt_label)
+		nf_connlabels_put(net);
 }
diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 365b9bb7f546e..9ca6231ea6470 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -160,6 +160,9 @@ struct ovs_net {
 #if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_ct_limit_info *ct_limit_info;
 #endif
+
+	/* Module reference for configuring conntrack. */
+	bool xt_label;
 };
 
 /**

From 313cf06ef4de23873a35237cdb2bfedeeba8fb02 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Sat, 8 Mar 2025 21:37:13 +0000
Subject: [PATCH 2087/2753] dt-bindings: net: rockchip-dwmac: Require
 rockchip,grf and rockchip,php-grf

All Rockchip GMAC variants typically write to GRF regs to control e.g.
interface mode, speed and MAC rx/tx delay. Newer SoCs such as RK3562,
RK3576 and RK3588 use a mix of GRF and peripheral GRF regs.

Prior to the commit b331b8ef86f0 ("dt-bindings: net: convert
rockchip-dwmac to json-schema") the property rockchip,grf was listed
under "Required properties". During the conversion this was lost and
rockchip,grf has since then incorrectly been treated as optional and
not as required.

Similarly, when rockchip,php-grf was added to the schema in the
commit a2b77831427c ("dt-bindings: net: rockchip-dwmac: add rk3588 gmac
compatible") it also incorrectly has been treated as optional for all
GMAC variants, when it should have been required for RK3588, and later
also for RK3576.

Update this binding to require rockchip,grf and rockchip,php-grf to
properly reflect that GRF (and peripheral GRF for RK3576/RK3588) is
required to control part of GMAC.

This should not introduce any breakage as all Rockchip GMAC nodes have
been added together with a rockchip,grf phandle (and rockchip,php-grf
where required) in their initial commit.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://patch.msgid.link/20250308213720.2517944-2-jonas@kwiboo.se
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../bindings/net/rockchip-dwmac.yaml          | 21 ++++++++++++++++---
 1 file changed, 18 insertions(+), 3 deletions(-)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index f8a576611d6c1..8dd870f0214db 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -32,9 +32,6 @@ select:
   required:
     - compatible
 
-allOf:
-  - $ref: snps,dwmac.yaml#
-
 properties:
   compatible:
     oneOf:
@@ -114,6 +111,24 @@ required:
   - compatible
   - clocks
   - clock-names
+  - rockchip,grf
+
+allOf:
+  - $ref: snps,dwmac.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - rockchip,rk3576-gmac
+              - rockchip,rk3588-gmac
+    then:
+      required:
+        - rockchip,php-grf
+    else:
+      properties:
+        rockchip,php-grf: false
 
 unevaluatedProperties: false
 

From 247e84f66a3d1946193d739fec5dc3d69833fd00 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Sat, 8 Mar 2025 21:37:14 +0000
Subject: [PATCH 2088/2753] net: stmmac: dwmac-rk: Validate GRF and peripheral
 GRF during probe

All Rockchip GMAC variants typically write to GRF regs to control e.g.
interface mode, speed and MAC rx/tx delay. Newer SoCs such as RK3576 and
RK3588 use a mix of GRF and peripheral GRF regs. These syscon regmaps is
located with help of a rockchip,grf and rockchip,php-grf phandle.

However, validating the rockchip,grf and rockchip,php-grf syscon regmap
is deferred until e.g. interface mode or speed is configured, inside the
individual SoC specific operations.

Change to validate the rockchip,grf and rockchip,php-grf syscon regmap
at probe time to simplify all SoC specific operations.

This should not introduce any backward compatibility issues as all
GMAC nodes have been added together with a rockchip,grf phandle (and
rockchip,php-grf where required) in their initial commit.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250308213720.2517944-3-jonas@kwiboo.se
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 21 +++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 003fa5cf42c33..5615f015c5fe4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,7 @@ struct rk_gmac_ops {
 	void (*set_clock_selection)(struct rk_priv_data *bsp_priv, bool input,
 				    bool enable);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	bool php_grf_required;
 	bool regs_valid;
 	u32 regs[];
 };
@@ -1254,6 +1255,7 @@ static const struct rk_gmac_ops rk3576_ops = {
 	.set_rgmii_speed = rk3576_set_gmac_speed,
 	.set_rmii_speed = rk3576_set_gmac_speed,
 	.set_clock_selection = rk3576_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0x2a220000, /* gmac0 */
@@ -1401,6 +1403,7 @@ static const struct rk_gmac_ops rk3588_ops = {
 	.set_rgmii_speed = rk3588_set_gmac_speed,
 	.set_rmii_speed = rk3588_set_gmac_speed,
 	.set_clock_selection = rk3588_set_clock_selection,
+	.php_grf_required = true,
 	.regs_valid = true,
 	.regs = {
 		0xfe1b0000, /* gmac0 */
@@ -1812,8 +1815,22 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 
 	bsp_priv->grf = syscon_regmap_lookup_by_phandle(dev->of_node,
 							"rockchip,grf");
-	bsp_priv->php_grf = syscon_regmap_lookup_by_phandle(dev->of_node,
-							    "rockchip,php-grf");
+	if (IS_ERR(bsp_priv->grf)) {
+		dev_err_probe(dev, PTR_ERR(bsp_priv->grf),
+			      "failed to lookup rockchip,grf\n");
+		return ERR_CAST(bsp_priv->grf);
+	}
+
+	if (ops->php_grf_required) {
+		bsp_priv->php_grf =
+			syscon_regmap_lookup_by_phandle(dev->of_node,
+							"rockchip,php-grf");
+		if (IS_ERR(bsp_priv->php_grf)) {
+			dev_err_probe(dev, PTR_ERR(bsp_priv->php_grf),
+				      "failed to lookup rockchip,php-grf\n");
+			return ERR_CAST(bsp_priv->php_grf);
+		}
+	}
 
 	if (plat->phy_node) {
 		bsp_priv->integrated_phy = of_property_read_bool(plat->phy_node,

From 41f35564cb71e7043e0afcf30078b4a6145cab64 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Sat, 8 Mar 2025 21:37:15 +0000
Subject: [PATCH 2089/2753] net: stmmac: dwmac-rk: Remove unneeded GRF and
 peripheral GRF checks

Now that GRF, and peripheral GRF where needed, is validated at probe
time there is no longer any need to check and log an error in each SoC
specific operation.

Remove unneeded IS_ERR() checks and early bail out from each SoC
specific operation.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250308213720.2517944-4-jonas@kwiboo.se
Reviewed-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 249 ------------------
 1 file changed, 249 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 5615f015c5fe4..342463587d06f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -102,13 +102,6 @@ struct rk_priv_data {
 
 static void px30_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, PX30_GRF_GMAC_CON1,
 		     PX30_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -182,13 +175,6 @@ static const struct rk_gmac_ops px30_ops = {
 static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 		     RK3128_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3128_GMAC_RMII_MODE_CLR);
@@ -200,13 +186,6 @@ static void rk3128_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3128_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 		     RK3128_GMAC_PHY_INTF_SEL_RMII | RK3128_GMAC_RMII_MODE);
 }
@@ -215,11 +194,6 @@ static void rk3128_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 			     RK3128_GMAC_CLK_2_5M);
@@ -237,11 +211,6 @@ static void rk3128_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3128_GRF_MAC_CON1,
 			     RK3128_GMAC_RMII_CLK_2_5M |
@@ -298,13 +267,6 @@ static const struct rk_gmac_ops rk3128_ops = {
 static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3228_GMAC_RMII_MODE_CLR |
@@ -317,13 +279,6 @@ static void rk3228_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3228_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 		     RK3228_GMAC_PHY_INTF_SEL_RMII |
 		     RK3228_GMAC_RMII_MODE);
@@ -336,11 +291,6 @@ static void rk3228_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 			     RK3228_GMAC_CLK_2_5M);
@@ -358,11 +308,6 @@ static void rk3228_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3228_GRF_MAC_CON1,
 			     RK3228_GMAC_RMII_CLK_2_5M |
@@ -420,13 +365,6 @@ static const struct rk_gmac_ops rk3228_ops = {
 static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 		     RK3288_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3288_GMAC_RMII_MODE_CLR);
@@ -438,13 +376,6 @@ static void rk3288_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3288_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 		     RK3288_GMAC_PHY_INTF_SEL_RMII | RK3288_GMAC_RMII_MODE);
 }
@@ -453,11 +384,6 @@ static void rk3288_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 			     RK3288_GMAC_CLK_2_5M);
@@ -475,11 +401,6 @@ static void rk3288_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3288_GRF_SOC_CON1,
 			     RK3288_GMAC_RMII_CLK_2_5M |
@@ -512,13 +433,6 @@ static const struct rk_gmac_ops rk3288_ops = {
 
 static void rk3308_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
 		     RK3308_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -527,11 +441,6 @@ static void rk3308_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3308_GRF_MAC_CON0,
 			     RK3308_GMAC_SPEED_10M);
@@ -584,13 +493,6 @@ static const struct rk_gmac_ops rk3308_ops = {
 static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1,
 		     RK3328_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3328_GMAC_RMII_MODE_CLR |
@@ -604,14 +506,8 @@ static void rk3328_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3328_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int reg;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 :
 		  RK3328_GRF_MAC_CON1;
 
@@ -624,11 +520,6 @@ static void rk3328_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3328_GRF_MAC_CON1,
 			     RK3328_GMAC_CLK_2_5M);
@@ -647,11 +538,6 @@ static void rk3328_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int reg;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	reg = bsp_priv->integrated_phy ? RK3328_GRF_MAC_CON2 :
 		  RK3328_GRF_MAC_CON1;
 
@@ -712,13 +598,6 @@ static const struct rk_gmac_ops rk3328_ops = {
 static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 		     RK3366_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3366_GMAC_RMII_MODE_CLR);
@@ -730,13 +609,6 @@ static void rk3366_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3366_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 		     RK3366_GMAC_PHY_INTF_SEL_RMII | RK3366_GMAC_RMII_MODE);
 }
@@ -745,11 +617,6 @@ static void rk3366_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 			     RK3366_GMAC_CLK_2_5M);
@@ -767,11 +634,6 @@ static void rk3366_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3366_GRF_SOC_CON6,
 			     RK3366_GMAC_RMII_CLK_2_5M |
@@ -823,13 +685,6 @@ static const struct rk_gmac_ops rk3366_ops = {
 static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 		     RK3368_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3368_GMAC_RMII_MODE_CLR);
@@ -841,13 +696,6 @@ static void rk3368_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3368_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 		     RK3368_GMAC_PHY_INTF_SEL_RMII | RK3368_GMAC_RMII_MODE);
 }
@@ -856,11 +704,6 @@ static void rk3368_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 			     RK3368_GMAC_CLK_2_5M);
@@ -878,11 +721,6 @@ static void rk3368_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3368_GRF_SOC_CON15,
 			     RK3368_GMAC_RMII_CLK_2_5M |
@@ -934,13 +772,6 @@ static const struct rk_gmac_ops rk3368_ops = {
 static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 		     RK3399_GMAC_PHY_INTF_SEL_RGMII |
 		     RK3399_GMAC_RMII_MODE_CLR);
@@ -952,13 +783,6 @@ static void rk3399_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3399_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 		     RK3399_GMAC_PHY_INTF_SEL_RMII | RK3399_GMAC_RMII_MODE);
 }
@@ -967,11 +791,6 @@ static void rk3399_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10)
 		regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 			     RK3399_GMAC_CLK_2_5M);
@@ -989,11 +808,6 @@ static void rk3399_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RK3399_GRF_SOC_CON5,
 			     RK3399_GMAC_RMII_CLK_2_5M |
@@ -1038,14 +852,8 @@ static const struct rk_gmac_ops rk3399_ops = {
 static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 con0, con1;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	con0 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON0 :
 				     RK3568_GRF_GMAC0_CON0;
 	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
@@ -1063,14 +871,8 @@ static void rk3568_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3568_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 con1;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	con1 = (bsp_priv->id == 1) ? RK3568_GRF_GMAC1_CON1 :
 				     RK3568_GRF_GMAC0_CON1;
 	regmap_write(bsp_priv->grf, con1, RK3568_GMAC_PHY_INTF_SEL_RMII);
@@ -1148,14 +950,8 @@ static const struct rk_gmac_ops rk3568_ops = {
 static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int offset_con;
 
-	if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "Missing rockchip,grf or rockchip,php-grf property\n");
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
 					 RK3576_GRF_GMAC_CON0;
 
@@ -1181,14 +977,8 @@ static void rk3576_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3576_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	unsigned int offset_con;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3576_GRF_GMAC_CON1 :
 					 RK3576_GRF_GMAC_CON0;
 
@@ -1308,14 +1098,8 @@ static const struct rk_gmac_ops rk3576_ops = {
 static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
 	u32 offset_con, id = bsp_priv->id;
 
-	if (IS_ERR(bsp_priv->grf) || IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "Missing rockchip,grf or rockchip,php_grf property\n");
-		return;
-	}
-
 	offset_con = bsp_priv->id == 1 ? RK3588_GRF_GMAC_CON9 :
 					 RK3588_GRF_GMAC_CON8;
 
@@ -1336,13 +1120,6 @@ static void rk3588_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rk3588_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->php_grf)) {
-		dev_err(dev, "%s: Missing rockchip,php_grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->php_grf, RK3588_GRF_GMAC_CON0,
 		     RK3588_GMAC_PHY_INTF_SEL_RMII(bsp_priv->id));
 
@@ -1426,13 +1203,6 @@ static const struct rk_gmac_ops rk3588_ops = {
 
 static void rv1108_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0,
 		     RV1108_GMAC_PHY_INTF_SEL_RMII);
 }
@@ -1441,11 +1211,6 @@ static void rv1108_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
 {
 	struct device *dev = &bsp_priv->pdev->dev;
 
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	if (speed == 10) {
 		regmap_write(bsp_priv->grf, RV1108_GRF_GMAC_CON0,
 			     RV1108_GMAC_RMII_CLK_2_5M |
@@ -1494,13 +1259,6 @@ static const struct rk_gmac_ops rv1108_ops = {
 static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv,
 				int tx_delay, int rx_delay)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "Missing rockchip,grf property\n");
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0,
 		     RV1126_GMAC_PHY_INTF_SEL_RGMII |
 		     RV1126_GMAC_M0_RXCLK_DLY_ENABLE |
@@ -1519,13 +1277,6 @@ static void rv1126_set_to_rgmii(struct rk_priv_data *bsp_priv,
 
 static void rv1126_set_to_rmii(struct rk_priv_data *bsp_priv)
 {
-	struct device *dev = &bsp_priv->pdev->dev;
-
-	if (IS_ERR(bsp_priv->grf)) {
-		dev_err(dev, "%s: Missing rockchip,grf property\n", __func__);
-		return;
-	}
-
 	regmap_write(bsp_priv->grf, RV1126_GRF_GMAC_CON0,
 		     RV1126_GMAC_PHY_INTF_SEL_RMII);
 }

From 5a1dddd2944492edb1e61c5db1cc386e5419fcf4 Mon Sep 17 00:00:00 2001
From: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Date: Sun, 9 Mar 2025 00:33:01 +0000
Subject: [PATCH 2090/2753] dt-bindings: net: Define interrupt constraints for
 DWMAC vendor bindings

The `snps,dwmac.yaml` binding currently sets `maxItems: 3` for the
`interrupts` and `interrupt-names` properties, but vendor bindings
selecting `snps,dwmac.yaml` do not impose these limits.

Define constraints for `interrupts` and `interrupt-names` properties in
various DWMAC vendor bindings to ensure proper validation and consistency.

Signed-off-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Acked-by: Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp>
Link: https://patch.msgid.link/20250309003301.1152228-1-prabhakar.mahadev-lad.rj@bp.renesas.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../devicetree/bindings/net/amlogic,meson-dwmac.yaml   |  6 ++++++
 .../devicetree/bindings/net/intel,dwmac-plat.yaml      |  6 ++++++
 .../devicetree/bindings/net/mediatek-dwmac.yaml        |  6 ++++++
 .../devicetree/bindings/net/nxp,dwmac-imx.yaml         |  8 ++++++++
 .../devicetree/bindings/net/rockchip-dwmac.yaml        | 10 ++++++++++
 Documentation/devicetree/bindings/net/stm32-dwmac.yaml | 10 ++++++++++
 .../bindings/net/toshiba,visconti-dwmac.yaml           |  6 ++++++
 7 files changed, 52 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
index 798a4c19f18cf..0cd78d71768c1 100644
--- a/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/amlogic,meson-dwmac.yaml
@@ -152,6 +152,12 @@ properties:
           The second range is is for the Amlogic specific configuration
           (for example the PRG_ETHERNET register range on Meson8b and newer)
 
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    const: macirq
+
 required:
   - compatible
   - reg
diff --git a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
index 42a0bc94312c3..62c1da36a2b5a 100644
--- a/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
+++ b/Documentation/devicetree/bindings/net/intel,dwmac-plat.yaml
@@ -41,6 +41,12 @@ properties:
       - const: ptp_ref
       - const: tx_clk
 
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    const: macirq
+
 required:
   - compatible
   - clocks
diff --git a/Documentation/devicetree/bindings/net/mediatek-dwmac.yaml b/Documentation/devicetree/bindings/net/mediatek-dwmac.yaml
index ed9d845f60080..3aab21b8e8de5 100644
--- a/Documentation/devicetree/bindings/net/mediatek-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/mediatek-dwmac.yaml
@@ -64,6 +64,12 @@ properties:
       - const: rmii_internal
       - const: mac_cg
 
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    const: macirq
+
   power-domains:
     maxItems: 1
 
diff --git a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
index 87bc4416eadf2..e5db346beca96 100644
--- a/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
+++ b/Documentation/devicetree/bindings/net/nxp,dwmac-imx.yaml
@@ -56,6 +56,14 @@ properties:
         - tx
         - mem
 
+  interrupts:
+    maxItems: 2
+
+  interrupt-names:
+    items:
+      - const: macirq
+      - const: eth_wake_irq
+
   intf_mode:
     $ref: /schemas/types.yaml#/definitions/phandle-array
     items:
diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index 8dd870f0214db..63ee0cc7a8f89 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -55,6 +55,16 @@ properties:
               - rockchip,rv1126-gmac
           - const: snps,dwmac-4.20a
 
+  interrupts:
+    minItems: 1
+    maxItems: 2
+
+  interrupt-names:
+    minItems: 1
+    items:
+      - const: macirq
+      - const: eth_wake_irq
+
   clocks:
     minItems: 5
     maxItems: 8
diff --git a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
index 85cea9966a27e..987254900d0da 100644
--- a/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/stm32-dwmac.yaml
@@ -54,6 +54,16 @@ properties:
     items:
       - const: stmmaceth
 
+  interrupts:
+    minItems: 1
+    maxItems: 2
+
+  interrupt-names:
+    minItems: 1
+    items:
+      - const: macirq
+      - const: eth_wake_irq
+
   clocks:
     minItems: 3
     items:
diff --git a/Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml b/Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml
index 052f636158b3f..f0f32e18fc855 100644
--- a/Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/toshiba,visconti-dwmac.yaml
@@ -42,6 +42,12 @@ properties:
       - const: stmmaceth
       - const: phy_ref_clk
 
+  interrupts:
+    maxItems: 1
+
+  interrupt-names:
+    const: macirq
+
 required:
   - compatible
   - reg

From 03ebae19925519cca5b314443c6082e0aeaa6321 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:39 +0200
Subject: [PATCH 2091/2753] net/mlx5: DR, use the right action structs for
 STEv3

Some actions in ConnectX-8 (STEv3) have different structure,
and they are handled separately in ste_ctx_v3.
This separate handling was missing two actions: INSERT_HDR
and REMOVE_HDR, which broke SWS for Linux Bridge.
This patch resolves the issue by introducing dedicated
callbacks for the insert and remove header functions,
with version-specific implementations for each STE variant.

Fixes: 4d617b57574f ("net/mlx5: DR, add support for ConnectX-8 steering")
Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Itamar Gozlan <igozlan@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741644104-97767-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../mellanox/mlx5/core/steering/sws/dr_ste.h  |  4 ++
 .../mlx5/core/steering/sws/dr_ste_v1.c        | 52 ++++++++++---------
 .../mlx5/core/steering/sws/dr_ste_v1.h        |  4 ++
 .../mlx5/core/steering/sws/dr_ste_v2.c        |  2 +
 .../mlx5/core/steering/sws/dr_ste_v3.c        | 42 +++++++++++++++
 5 files changed, 79 insertions(+), 25 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
index 5f409dc30aca8..3d5afc832fa56 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste.h
@@ -210,6 +210,10 @@ struct mlx5dr_ste_ctx {
 	void (*set_encap_l3)(u8 *hw_ste_p, u8 *frst_s_action,
 			     u8 *scnd_d_action, u32 reformat_id,
 			     int size);
+	void (*set_insert_hdr)(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			       u8 anchor, u8 offset, int size);
+	void (*set_remove_hdr)(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			       u8 offset, int size);
 	/* Send */
 	void (*prepare_for_postsend)(u8 *hw_ste_p, u32 ste_size);
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
index 7f83d77c43ef0..6447efbae00dc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.c
@@ -266,10 +266,10 @@ void dr_ste_v1_set_encap(u8 *hw_ste_p, u8 *d_action, u32 reformat_id, int size)
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
-				     u32 reformat_id,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+			      u32 reformat_id,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_double_action_insert_with_ptr_v1, d_action,
 		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
@@ -286,9 +286,9 @@ static void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
-static void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
-				     u8 anchor, u8 offset,
-				     int size)
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+			      u8 anchor, u8 offset,
+			      int size)
 {
 	MLX5_SET(ste_single_action_remove_header_size_v1, s_action,
 		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
@@ -584,11 +584,11 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 	} else if (action_type_set[DR_ACTION_TYP_REMOVE_HDR]) {
@@ -597,10 +597,10 @@ void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -792,11 +792,11 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
 			action = MLX5_ADDR_OF(ste_mask_and_match_v1, last_ste, action);
 			action_sz = DR_STE_ACTION_TRIPLE_SZ;
 		}
-		dr_ste_v1_set_insert_hdr(last_ste, action,
-					 attr->reformat.id,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_insert_hdr(last_ste, action,
+					attr->reformat.id,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_DOUBLE_SZ;
 		action += DR_STE_ACTION_DOUBLE_SZ;
 		allow_modify_hdr = false;
@@ -808,10 +808,10 @@ void dr_ste_v1_set_actions_rx(struct mlx5dr_ste_ctx *ste_ctx,
 			allow_modify_hdr = true;
 			allow_ctr = true;
 		}
-		dr_ste_v1_set_remove_hdr(last_ste, action,
-					 attr->reformat.param_0,
-					 attr->reformat.param_1,
-					 attr->reformat.size);
+		ste_ctx->set_remove_hdr(last_ste, action,
+					attr->reformat.param_0,
+					attr->reformat.param_1,
+					attr->reformat.size);
 		action_sz -= DR_STE_ACTION_SINGLE_SZ;
 		action += DR_STE_ACTION_SINGLE_SZ;
 	}
@@ -2200,6 +2200,8 @@ static struct mlx5dr_ste_ctx ste_ctx_v1 = {
 	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
 	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
 	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
index a8d9e308d3392..591c20c95a6ac 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v1.h
@@ -156,6 +156,10 @@ void dr_ste_v1_set_pop_vlan(u8 *hw_ste_p, u8 *s_action, u8 vlans_num);
 void dr_ste_v1_set_encap_l3(u8 *hw_ste_p, u8 *frst_s_action, u8 *scnd_d_action,
 			    u32 reformat_id, int size);
 void dr_ste_v1_set_rx_decap(u8 *hw_ste_p, u8 *s_action);
+void dr_ste_v1_set_insert_hdr(u8 *hw_ste_p, u8 *d_action, u32 reformat_id,
+			      u8 anchor, u8 offset, int size);
+void dr_ste_v1_set_remove_hdr(u8 *hw_ste_p, u8 *s_action, u8 anchor,
+			      u8 offset, int size);
 void dr_ste_v1_set_actions_tx(struct mlx5dr_ste_ctx *ste_ctx, struct mlx5dr_domain *dmn,
 			      u8 *action_type_set, u32 actions_caps, u8 *last_ste,
 			      struct mlx5dr_ste_actions_attr *attr, u32 *added_stes);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
index 0882dba0f64b9..d0ebaf820d42b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v2.c
@@ -69,6 +69,8 @@ static struct mlx5dr_ste_ctx ste_ctx_v2 = {
 	.set_pop_vlan			= &dr_ste_v1_set_pop_vlan,
 	.set_rx_decap			= &dr_ste_v1_set_rx_decap,
 	.set_encap_l3			= &dr_ste_v1_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v1_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v1_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
index cc60ce1d274ef..e468a9ae44e8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/sws/dr_ste_v3.c
@@ -79,6 +79,46 @@ static void dr_ste_v3_set_rx_decap(u8 *hw_ste_p, u8 *s_action)
 	dr_ste_v1_set_reparse(hw_ste_p);
 }
 
+static void dr_ste_v3_set_insert_hdr(u8 *hw_ste_p, u8 *d_action,
+				     u32 reformat_id, u8 anchor,
+				     u8 offset, int size)
+{
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 action_id, DR_STE_V1_ACTION_ID_INSERT_POINTER);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 size, size / 2);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 start_offset, offset / 2);
+
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 pointer, reformat_id);
+	MLX5_SET(ste_double_action_insert_with_ptr_v3, d_action,
+		 attributes, DR_STE_V1_ACTION_INSERT_PTR_ATTR_NONE);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
+static void dr_ste_v3_set_remove_hdr(u8 *hw_ste_p, u8 *s_action,
+				     u8 anchor, u8 offset, int size)
+{
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 action_id, DR_STE_V1_ACTION_ID_REMOVE_BY_SIZE);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_anchor, anchor);
+
+	/* The hardware expects here size and offset in words (2 byte) */
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 remove_size, size / 2);
+	MLX5_SET(ste_single_action_remove_header_size_v3, s_action,
+		 start_offset, offset / 2);
+
+	dr_ste_v1_set_reparse(hw_ste_p);
+}
+
 static int
 dr_ste_v3_set_action_decap_l3_list(void *data, u32 data_sz,
 				   u8 *hw_action, u32 hw_action_sz,
@@ -211,6 +251,8 @@ static struct mlx5dr_ste_ctx ste_ctx_v3 = {
 	.set_pop_vlan			= &dr_ste_v3_set_pop_vlan,
 	.set_rx_decap			= &dr_ste_v3_set_rx_decap,
 	.set_encap_l3			= &dr_ste_v3_set_encap_l3,
+	.set_insert_hdr			= &dr_ste_v3_set_insert_hdr,
+	.set_remove_hdr			= &dr_ste_v3_set_remove_hdr,
 	/* Send */
 	.prepare_for_postsend		= &dr_ste_v1_prepare_for_postsend,
 };

From 521992337f67f71ce4436b98bc32563ddb1a5ce3 Mon Sep 17 00:00:00 2001
From: Vlad Dogaru <vdogaru@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:40 +0200
Subject: [PATCH 2092/2753] net/mlx5: HWS, Rightsize bwc matcher priority

The bwc layer was clamping the matcher priority from 32 bits to 16 bits.
This didn't show up until a matcher was resized, since the initial
native matcher was created using the correct 32 bit value.

The fix also reorders fields to avoid some padding.

Fixes: 2111bb970c78 ("net/mlx5: HWS, added backward-compatible API handling")
Signed-off-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741644104-97767-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
index f9f569131ddeb..47f7ed1415535 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/bwc.h
@@ -24,8 +24,8 @@ struct mlx5hws_bwc_matcher {
 	struct mlx5hws_matcher *matcher;
 	struct mlx5hws_match_template *mt;
 	struct mlx5hws_action_template *at[MLX5HWS_BWC_MATCHER_ATTACH_AT_NUM];
+	u32 priority;
 	u8 num_of_at;
-	u16 priority;
 	u8 size_log;
 	atomic_t num_of_rules;
 	struct list_head *rules;

From 32d2724db5b2361ab293427ccd5c24f4f2bcca14 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:41 +0200
Subject: [PATCH 2093/2753] net/mlx5: Fix incorrect IRQ pool usage when
 releasing IRQs

mlx5_irq_pool_get() is a getter for completion IRQ pool only.
However, after the cited commit, mlx5_irq_pool_get() is called during
ctrl IRQ release flow to retrieve the pool, resulting in the use of an
incorrect IRQ pool.

Hence, use the newly introduced mlx5_irq_get_pool() getter to retrieve
the correct IRQ pool based on the IRQ itself. While at it, rename
mlx5_irq_pool_get() to mlx5_irq_table_get_comp_irq_pool() which
accurately reflects its purpose and improves code readability.

Fixes: 0477d5168bbb ("net/mlx5: Expose SFs IRQs")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/1741644104-97767-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/eq.c        |  2 +-
 .../net/ethernet/mellanox/mlx5/core/irq_affinity.c  |  2 +-
 drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h  |  4 +++-
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c   | 13 ++++++++++---
 drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h   |  2 +-
 5 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 2b229b6226c6a..dfb079e59d858 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -871,8 +871,8 @@ static void comp_irq_release_sf(struct mlx5_core_dev *dev, u16 vecidx)
 
 static int comp_irq_request_sf(struct mlx5_core_dev *dev, u16 vecidx)
 {
+	struct mlx5_irq_pool *pool = mlx5_irq_table_get_comp_irq_pool(dev);
 	struct mlx5_eq_table *table = dev->priv.eq_table;
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
 	struct irq_affinity_desc af_desc = {};
 	struct mlx5_irq *irq;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
index 1477db7f5307e..2691d88cdee1f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
@@ -175,7 +175,7 @@ mlx5_irq_affinity_request(struct mlx5_core_dev *dev, struct mlx5_irq_pool *pool,
 
 void mlx5_irq_affinity_irq_release(struct mlx5_core_dev *dev, struct mlx5_irq *irq)
 {
-	struct mlx5_irq_pool *pool = mlx5_irq_pool_get(dev);
+	struct mlx5_irq_pool *pool = mlx5_irq_get_pool(irq);
 	int cpu;
 
 	cpu = cpumask_first(mlx5_irq_get_affinity_mask(irq));
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
index 0881e961d8b17..586688da9940e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_irq.h
@@ -10,12 +10,15 @@
 
 struct mlx5_irq;
 struct cpu_rmap;
+struct mlx5_irq_pool;
 
 int mlx5_irq_table_init(struct mlx5_core_dev *dev);
 void mlx5_irq_table_cleanup(struct mlx5_core_dev *dev);
 int mlx5_irq_table_create(struct mlx5_core_dev *dev);
 void mlx5_irq_table_destroy(struct mlx5_core_dev *dev);
 void mlx5_irq_table_free_irqs(struct mlx5_core_dev *dev);
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev);
 int mlx5_irq_table_get_num_comp(struct mlx5_irq_table *table);
 int mlx5_irq_table_get_sfs_vec(struct mlx5_irq_table *table);
 struct mlx5_irq_table *mlx5_irq_table_get(struct mlx5_core_dev *dev);
@@ -38,7 +41,6 @@ struct cpumask *mlx5_irq_get_affinity_mask(struct mlx5_irq *irq);
 int mlx5_irq_get_index(struct mlx5_irq *irq);
 int mlx5_irq_get_irq(const struct mlx5_irq *irq);
 
-struct mlx5_irq_pool;
 #ifdef CONFIG_MLX5_SF
 struct mlx5_irq *mlx5_irq_affinity_irq_request_auto(struct mlx5_core_dev *dev,
 						    struct cpumask *used_cpus, u16 vecidx);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
index d9362eabc6a1c..2c5f850c31f68 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.c
@@ -378,6 +378,11 @@ int mlx5_irq_get_index(struct mlx5_irq *irq)
 	return irq->map.index;
 }
 
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq)
+{
+	return irq->pool;
+}
+
 /* irq_pool API */
 
 /* requesting an irq from a given pool according to given index */
@@ -405,18 +410,20 @@ static struct mlx5_irq_pool *sf_ctrl_irq_pool_get(struct mlx5_irq_table *irq_tab
 	return irq_table->sf_ctrl_pool;
 }
 
-static struct mlx5_irq_pool *sf_irq_pool_get(struct mlx5_irq_table *irq_table)
+static struct mlx5_irq_pool *
+sf_comp_irq_pool_get(struct mlx5_irq_table *irq_table)
 {
 	return irq_table->sf_comp_pool;
 }
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev)
+struct mlx5_irq_pool *
+mlx5_irq_table_get_comp_irq_pool(struct mlx5_core_dev *dev)
 {
 	struct mlx5_irq_table *irq_table = mlx5_irq_table_get(dev);
 	struct mlx5_irq_pool *pool = NULL;
 
 	if (mlx5_core_is_sf(dev))
-		pool = sf_irq_pool_get(irq_table);
+		pool = sf_comp_irq_pool_get(irq_table);
 
 	/* In some configs, there won't be a pool of SFs IRQs. Hence, returning
 	 * the PF IRQs pool in case the SF pool doesn't exist.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
index c4d377f8df308..cc064425fe160 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/pci_irq.h
@@ -28,7 +28,6 @@ struct mlx5_irq_pool {
 	struct mlx5_core_dev *dev;
 };
 
-struct mlx5_irq_pool *mlx5_irq_pool_get(struct mlx5_core_dev *dev);
 static inline bool mlx5_irq_pool_is_sf_pool(struct mlx5_irq_pool *pool)
 {
 	return !strncmp("mlx5_sf", pool->name, strlen("mlx5_sf"));
@@ -40,5 +39,6 @@ struct mlx5_irq *mlx5_irq_alloc(struct mlx5_irq_pool *pool, int i,
 int mlx5_irq_get_locked(struct mlx5_irq *irq);
 int mlx5_irq_read_locked(struct mlx5_irq *irq);
 int mlx5_irq_put(struct mlx5_irq *irq);
+struct mlx5_irq_pool *mlx5_irq_get_pool(struct mlx5_irq *irq);
 
 #endif /* __PCI_IRQ_H__ */

From 32966984bee1defd9f5a8f9be274d7c32f911ba1 Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:42 +0200
Subject: [PATCH 2094/2753] net/mlx5: Lag, Check shared fdb before creating
 MultiPort E-Switch

Currently, MultiPort E-Switch is requesting to create a LAG with shared
FDB without checking the LAG is supporting shared FDB.
Add the check.

Fixes: a32327a3a02c ("net/mlx5: Lag, Control MultiPort E-Switch single FDB mode")
Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/1741644104-97767-5-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c   | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h   | 1 +
 drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c | 3 ++-
 3 files changed, 5 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index cea5aa314f6c5..ed2ba272946b9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -951,7 +951,7 @@ void mlx5_disable_lag(struct mlx5_lag *ldev)
 				mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
 }
 
-static bool mlx5_shared_fdb_supported(struct mlx5_lag *ldev)
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev)
 {
 	int idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev;
@@ -1038,7 +1038,7 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 	}
 
 	if (do_bond && !__mlx5_lag_is_active(ldev)) {
-		bool shared_fdb = mlx5_shared_fdb_supported(ldev);
+		bool shared_fdb = mlx5_lag_shared_fdb_supported(ldev);
 
 		roce_lag = mlx5_lag_is_roce_lag(ldev);
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
index 01cf723669471..c2f256bb2bc20 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.h
@@ -92,6 +92,7 @@ mlx5_lag_is_ready(struct mlx5_lag *ldev)
 	return test_bit(MLX5_LAG_FLAG_NDEVS_READY, &ldev->state_flags);
 }
 
+bool mlx5_lag_shared_fdb_supported(struct mlx5_lag *ldev);
 bool mlx5_lag_check_prereq(struct mlx5_lag *ldev);
 void mlx5_modify_lag(struct mlx5_lag *ldev,
 		     struct lag_tracker *tracker);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
index ffac0bd6c8952..1770297a112e2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/mpesw.c
@@ -83,7 +83,8 @@ static int enable_mpesw(struct mlx5_lag *ldev)
 	if (mlx5_eswitch_mode(dev0) != MLX5_ESWITCH_OFFLOADS ||
 	    !MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table) ||
 	    !MLX5_CAP_GEN(dev0, create_lag_when_not_master_up) ||
-	    !mlx5_lag_check_prereq(ldev))
+	    !mlx5_lag_check_prereq(ldev) ||
+	    !mlx5_lag_shared_fdb_supported(ldev))
 		return -EOPNOTSUPP;
 
 	err = mlx5_mpesw_metadata_set(ldev);

From 4b8eeed4fb105770ce6dc84a2c6ef953c7b71cbb Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:43 +0200
Subject: [PATCH 2095/2753] net/mlx5: Bridge, fix the crash caused by LAG state
 check

When removing LAG device from bridge, NETDEV_CHANGEUPPER event is
triggered. Driver finds the lower devices (PFs) to flush all the
offloaded entries. And mlx5_lag_is_shared_fdb is checked, it returns
false if one of PF is unloaded. In such case,
mlx5_esw_bridge_lag_rep_get() and its caller return NULL, instead of
the alive PF, and the flush is skipped.

Besides, the bridge fdb entry's lastuse is updated in mlx5 bridge
event handler. But this SWITCHDEV_FDB_ADD_TO_BRIDGE event can be
ignored in this case because the upper interface for bond is deleted,
and the entry will never be aged because lastuse is never updated.

To make things worse, as the entry is alive, mlx5 bridge workqueue
keeps sending that event, which is then handled by kernel bridge
notifier. It causes the following crash when accessing the passed bond
netdev which is already destroyed.

To fix this issue, remove such checks. LAG state is already checked in
commit 15f8f168952f ("net/mlx5: Bridge, verify LAG state when adding
bond to bridge"), driver still need to skip offload if LAG becomes
invalid state after initialization.

 Oops: stack segment: 0000 [#1] SMP
 CPU: 3 UID: 0 PID: 23695 Comm: kworker/u40:3 Tainted: G           OE      6.11.0_mlnx #1
 Tainted: [O]=OOT_MODULE, [E]=UNSIGNED_MODULE
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 Workqueue: mlx5_bridge_wq mlx5_esw_bridge_update_work [mlx5_core]
 RIP: 0010:br_switchdev_event+0x2c/0x110 [bridge]
 Code: 44 00 00 48 8b 02 48 f7 00 00 02 00 00 74 69 41 54 55 53 48 83 ec 08 48 8b a8 08 01 00 00 48 85 ed 74 4a 48 83 fe 02 48 89 d3 <4c> 8b 65 00 74 23 76 49 48 83 fe 05 74 7e 48 83 fe 06 75 2f 0f b7
 RSP: 0018:ffffc900092cfda0 EFLAGS: 00010297
 RAX: ffff888123bfe000 RBX: ffffc900092cfe08 RCX: 00000000ffffffff
 RDX: ffffc900092cfe08 RSI: 0000000000000001 RDI: ffffffffa0c585f0
 RBP: 6669746f6e690a30 R08: 0000000000000000 R09: ffff888123ae92c8
 R10: 0000000000000000 R11: fefefefefefefeff R12: ffff888123ae9c60
 R13: 0000000000000001 R14: ffffc900092cfe08 R15: 0000000000000000
 FS:  0000000000000000(0000) GS:ffff88852c980000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f15914c8734 CR3: 0000000002830005 CR4: 0000000000770ef0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __die_body+0x1a/0x60
  ? die+0x38/0x60
  ? do_trap+0x10b/0x120
  ? do_error_trap+0x64/0xa0
  ? exc_stack_segment+0x33/0x50
  ? asm_exc_stack_segment+0x22/0x30
  ? br_switchdev_event+0x2c/0x110 [bridge]
  ? sched_balance_newidle.isra.149+0x248/0x390
  notifier_call_chain+0x4b/0xa0
  atomic_notifier_call_chain+0x16/0x20
  mlx5_esw_bridge_update+0xec/0x170 [mlx5_core]
  mlx5_esw_bridge_update_work+0x19/0x40 [mlx5_core]
  process_scheduled_works+0x81/0x390
  worker_thread+0x106/0x250
  ? bh_worker+0x110/0x110
  kthread+0xb7/0xe0
  ? kthread_park+0x80/0x80
  ret_from_fork+0x2d/0x50
  ? kthread_park+0x80/0x80
  ret_from_fork_asm+0x11/0x20
  </TASK>

Fixes: ff9b7521468b ("net/mlx5: Bridge, support LAG")
Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Vlad Buslov <vladbu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/1741644104-97767-6-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/en/rep/bridge.c  | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
index 5d128c5b4529a..0f5d7ea8956f7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/rep/bridge.c
@@ -48,15 +48,10 @@ mlx5_esw_bridge_lag_rep_get(struct net_device *dev, struct mlx5_eswitch *esw)
 	struct list_head *iter;
 
 	netdev_for_each_lower_dev(dev, lower, iter) {
-		struct mlx5_core_dev *mdev;
-		struct mlx5e_priv *priv;
-
 		if (!mlx5e_eswitch_rep(lower))
 			continue;
 
-		priv = netdev_priv(lower);
-		mdev = priv->mdev;
-		if (mlx5_lag_is_shared_fdb(mdev) && mlx5_esw_bridge_dev_same_esw(lower, esw))
+		if (mlx5_esw_bridge_dev_same_esw(lower, esw))
 			return lower;
 	}
 
@@ -125,7 +120,7 @@ static bool mlx5_esw_bridge_is_local(struct net_device *dev, struct net_device *
 	priv = netdev_priv(rep);
 	mdev = priv->mdev;
 	if (netif_is_lag_master(dev))
-		return mlx5_lag_is_shared_fdb(mdev) && mlx5_lag_is_master(mdev);
+		return mlx5_lag_is_master(mdev);
 	return true;
 }
 
@@ -455,6 +450,9 @@ static int mlx5_esw_bridge_switchdev_event(struct notifier_block *nb,
 	if (!rep)
 		return NOTIFY_DONE;
 
+	if (netif_is_lag_master(dev) && !mlx5_lag_is_shared_fdb(esw->dev))
+		return NOTIFY_DONE;
+
 	switch (event) {
 	case SWITCHDEV_FDB_ADD_TO_BRIDGE:
 		fdb_info = container_of(info,

From e92df790d07a8eea873efcb84776e7b71f81c7d5 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Tue, 11 Mar 2025 00:01:44 +0200
Subject: [PATCH 2096/2753] net/mlx5e: Prevent bridge link show failure for
 non-eswitch-allowed devices

mlx5_eswitch_get_vepa returns -EPERM if the device lacks
eswitch_manager capability, blocking mlx5e_bridge_getlink from
retrieving VEPA mode. Since mlx5e_bridge_getlink implements
ndo_bridge_getlink, returning -EPERM causes bridge link show to fail
instead of skipping devices without this capability.

To avoid this, return -EOPNOTSUPP from mlx5e_bridge_getlink when
mlx5_eswitch_get_vepa fails, ensuring the command continues processing
other devices while ignoring those without the necessary capability.

Fixes: 4b89251de024 ("net/mlx5: Support ndo bridge_setlink and getlink")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/1741644104-97767-7-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index a814b63ed97e5..8fcaee381b0e0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -5132,11 +5132,9 @@ static int mlx5e_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	struct mlx5e_priv *priv = netdev_priv(dev);
 	struct mlx5_core_dev *mdev = priv->mdev;
 	u8 mode, setting;
-	int err;
 
-	err = mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting);
-	if (err)
-		return err;
+	if (mlx5_eswitch_get_vepa(mdev->priv.eswitch, &setting))
+		return -EOPNOTSUPP;
 	mode = setting ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB;
 	return ndo_dflt_bridge_getlink(skb, pid, seq, dev,
 				       mode,

From 3e64bb2ae7d9f2b3a8259d4d6b86ed1984d5460a Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Tue, 11 Mar 2025 03:17:40 -0700
Subject: [PATCH 2097/2753] net: mana: cleanup mana struct after
 debugfs_remove()

When on a MANA VM hibernation is triggered, as part of hibernate_snapshot(),
mana_gd_suspend() and mana_gd_resume() are called. If during this
mana_gd_resume(), a failure occurs with HWC creation, mana_port_debugfs
pointer does not get reinitialized and ends up pointing to older,
cleaned-up dentry.
Further in the hibernation path, as part of power_down(), mana_gd_shutdown()
is triggered. This call, unaware of the failures in resume, tries to cleanup
the already cleaned up  mana_port_debugfs value and hits the following bug:

[  191.359296] mana 7870:00:00.0: Shutdown was called
[  191.359918] BUG: kernel NULL pointer dereference, address: 0000000000000098
[  191.360584] #PF: supervisor write access in kernel mode
[  191.361125] #PF: error_code(0x0002) - not-present page
[  191.361727] PGD 1080ea067 P4D 0
[  191.362172] Oops: Oops: 0002 [#1] SMP NOPTI
[  191.362606] CPU: 11 UID: 0 PID: 1674 Comm: bash Not tainted 6.14.0-rc5+ #2
[  191.363292] Hardware name: Microsoft Corporation Virtual Machine/Virtual Machine, BIOS Hyper-V UEFI Release v4.1 11/21/2024
[  191.364124] RIP: 0010:down_write+0x19/0x50
[  191.364537] Code: 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 0f 1f 44 00 00 55 48 89 e5 53 48 89 fb e8 de cd ff ff 31 c0 ba 01 00 00 00 <f0> 48 0f b1 13 75 16 65 48 8b 05 88 24 4c 6a 48 89 43 08 48 8b 5d
[  191.365867] RSP: 0000:ff45fbe0c1c037b8 EFLAGS: 00010246
[  191.366350] RAX: 0000000000000000 RBX: 0000000000000098 RCX: ffffff8100000000
[  191.366951] RDX: 0000000000000001 RSI: 0000000000000064 RDI: 0000000000000098
[  191.367600] RBP: ff45fbe0c1c037c0 R08: 0000000000000000 R09: 0000000000000001
[  191.368225] R10: ff45fbe0d2b01000 R11: 0000000000000008 R12: 0000000000000000
[  191.368874] R13: 000000000000000b R14: ff43dc27509d67c0 R15: 0000000000000020
[  191.369549] FS:  00007dbc5001e740(0000) GS:ff43dc663f380000(0000) knlGS:0000000000000000
[  191.370213] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[  191.370830] CR2: 0000000000000098 CR3: 0000000168e8e002 CR4: 0000000000b73ef0
[  191.371557] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[  191.372192] DR3: 0000000000000000 DR6: 00000000fffe07f0 DR7: 0000000000000400
[  191.372906] Call Trace:
[  191.373262]  <TASK>
[  191.373621]  ? show_regs+0x64/0x70
[  191.374040]  ? __die+0x24/0x70
[  191.374468]  ? page_fault_oops+0x290/0x5b0
[  191.374875]  ? do_user_addr_fault+0x448/0x800
[  191.375357]  ? exc_page_fault+0x7a/0x160
[  191.375971]  ? asm_exc_page_fault+0x27/0x30
[  191.376416]  ? down_write+0x19/0x50
[  191.376832]  ? down_write+0x12/0x50
[  191.377232]  simple_recursive_removal+0x4a/0x2a0
[  191.377679]  ? __pfx_remove_one+0x10/0x10
[  191.378088]  debugfs_remove+0x44/0x70
[  191.378530]  mana_detach+0x17c/0x4f0
[  191.378950]  ? __flush_work+0x1e2/0x3b0
[  191.379362]  ? __cond_resched+0x1a/0x50
[  191.379787]  mana_remove+0xf2/0x1a0
[  191.380193]  mana_gd_shutdown+0x3b/0x70
[  191.380642]  pci_device_shutdown+0x3a/0x80
[  191.381063]  device_shutdown+0x13e/0x230
[  191.381480]  kernel_power_off+0x35/0x80
[  191.381890]  hibernate+0x3c6/0x470
[  191.382312]  state_store+0xcb/0xd0
[  191.382734]  kobj_attr_store+0x12/0x30
[  191.383211]  sysfs_kf_write+0x3e/0x50
[  191.383640]  kernfs_fop_write_iter+0x140/0x1d0
[  191.384106]  vfs_write+0x271/0x440
[  191.384521]  ksys_write+0x72/0xf0
[  191.384924]  __x64_sys_write+0x19/0x20
[  191.385313]  x64_sys_call+0x2b0/0x20b0
[  191.385736]  do_syscall_64+0x79/0x150
[  191.386146]  ? __mod_memcg_lruvec_state+0xe7/0x240
[  191.386676]  ? __lruvec_stat_mod_folio+0x79/0xb0
[  191.387124]  ? __pfx_lru_add+0x10/0x10
[  191.387515]  ? queued_spin_unlock+0x9/0x10
[  191.387937]  ? do_anonymous_page+0x33c/0xa00
[  191.388374]  ? __handle_mm_fault+0xcf3/0x1210
[  191.388805]  ? __count_memcg_events+0xbe/0x180
[  191.389235]  ? handle_mm_fault+0xae/0x300
[  191.389588]  ? do_user_addr_fault+0x559/0x800
[  191.390027]  ? irqentry_exit_to_user_mode+0x43/0x230
[  191.390525]  ? irqentry_exit+0x1d/0x30
[  191.390879]  ? exc_page_fault+0x86/0x160
[  191.391235]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[  191.391745] RIP: 0033:0x7dbc4ff1c574
[  191.392111] Code: c7 00 16 00 00 00 b8 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 f3 0f 1e fa 80 3d d5 ea 0e 00 00 74 13 b8 01 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 54 c3 0f 1f 00 55 48 89 e5 48 83 ec 20 48 89
[  191.393412] RSP: 002b:00007ffd95a23ab8 EFLAGS: 00000202 ORIG_RAX: 0000000000000001
[  191.393990] RAX: ffffffffffffffda RBX: 0000000000000005 RCX: 00007dbc4ff1c574
[  191.394594] RDX: 0000000000000005 RSI: 00005a6eeadb0ce0 RDI: 0000000000000001
[  191.395215] RBP: 00007ffd95a23ae0 R08: 00007dbc50003b20 R09: 0000000000000000
[  191.395805] R10: 0000000000000001 R11: 0000000000000202 R12: 0000000000000005
[  191.396404] R13: 00005a6eeadb0ce0 R14: 00007dbc500045c0 R15: 00007dbc50001ee0
[  191.396987]  </TASK>

To fix this, we explicitly set such mana debugfs variables to NULL after
debugfs_remove() is called.

Fixes: 6607c17c6c5e ("net: mana: Enable debugfs files for MANA device")
Cc: stable@vger.kernel.org
Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://patch.msgid.link/1741688260-28922-1-git-send-email-shradhagupta@linux.microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 11 ++++++++++-
 drivers/net/ethernet/microsoft/mana/mana_en.c   | 10 ++++++----
 2 files changed, 16 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index be95336ce089a..11457b6296cc0 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -1547,6 +1547,7 @@ static int mana_gd_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 * adapter-MTU file and apc->mana_pci_debugfs folder.
 	 */
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
+	gc->mana_pci_debugfs = NULL;
 	pci_iounmap(pdev, bar0_va);
 free_gc:
 	pci_set_drvdata(pdev, NULL);
@@ -1569,6 +1570,8 @@ static void mana_gd_remove(struct pci_dev *pdev)
 
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
 
+	gc->mana_pci_debugfs = NULL;
+
 	pci_iounmap(pdev, gc->bar0_va);
 
 	vfree(gc);
@@ -1622,6 +1625,8 @@ static void mana_gd_shutdown(struct pci_dev *pdev)
 
 	debugfs_remove_recursive(gc->mana_pci_debugfs);
 
+	gc->mana_pci_debugfs = NULL;
+
 	pci_disable_device(pdev);
 }
 
@@ -1648,8 +1653,10 @@ static int __init mana_driver_init(void)
 	mana_debugfs_root = debugfs_create_dir("mana", NULL);
 
 	err = pci_register_driver(&mana_driver);
-	if (err)
+	if (err) {
 		debugfs_remove(mana_debugfs_root);
+		mana_debugfs_root = NULL;
+	}
 
 	return err;
 }
@@ -1659,6 +1666,8 @@ static void __exit mana_driver_exit(void)
 	pci_unregister_driver(&mana_driver);
 
 	debugfs_remove(mana_debugfs_root);
+
+	mana_debugfs_root = NULL;
 }
 
 module_init(mana_driver_init);
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index aa1e47233fe50..ae76ecc7a5d36 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -738,12 +738,11 @@ static const struct net_device_ops mana_devops = {
 static void mana_cleanup_port_context(struct mana_port_context *apc)
 {
 	/*
-	 * at this point all dir/files under the vport directory
-	 * are already cleaned up.
-	 * We are sure the apc->mana_port_debugfs remove will not
-	 * cause any freed memory access issues
+	 * make sure subsequent cleanup attempts don't end up removing already
+	 * cleaned dentry pointer
 	 */
 	debugfs_remove(apc->mana_port_debugfs);
+	apc->mana_port_debugfs = NULL;
 	kfree(apc->rxqs);
 	apc->rxqs = NULL;
 }
@@ -1254,6 +1253,7 @@ static void mana_destroy_eq(struct mana_context *ac)
 		return;
 
 	debugfs_remove_recursive(ac->mana_eqs_debugfs);
+	ac->mana_eqs_debugfs = NULL;
 
 	for (i = 0; i < gc->max_num_queues; i++) {
 		eq = ac->eqs[i].eq;
@@ -1914,6 +1914,7 @@ static void mana_destroy_txq(struct mana_port_context *apc)
 
 	for (i = 0; i < apc->num_queues; i++) {
 		debugfs_remove_recursive(apc->tx_qp[i].mana_tx_debugfs);
+		apc->tx_qp[i].mana_tx_debugfs = NULL;
 
 		napi = &apc->tx_qp[i].tx_cq.napi;
 		if (apc->tx_qp[i].txq.napi_initialized) {
@@ -2099,6 +2100,7 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
 		return;
 
 	debugfs_remove_recursive(rxq->mana_rx_debugfs);
+	rxq->mana_rx_debugfs = NULL;
 
 	napi = &rxq->rx_cq.napi;
 

From 4490fe973669360efaef7350aeb9706f70164176 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Wed, 5 Mar 2025 21:44:02 -0600
Subject: [PATCH 2098/2753] platform/x86/amd: pmf: Fix missing hidden options
 for Smart PC
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

amd_pmf_get_slider_info() checks the current profile to report correct
value to the TA inputs.  If hidden options are in use then the wrong
values will be reported to TA.

Add the two compat options PLATFORM_PROFILE_BALANCED_PERFORMANCE and
PLATFORM_PROFILE_QUIET for this use.

Reported-by: Yijun Shen <Yijun.Shen@dell.com>
Fixes: 9a43102daf64d ("platform/x86/amd: pmf: Add balanced-performance to hidden choices")
Fixes: 44e94fece5170 ("platform/x86/amd: pmf: Add 'quiet' to hidden choices")
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Acked-by: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
Link: https://lore.kernel.org/r/20250306034402.50478-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/amd/pmf/spc.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
index f34f3130c3307..1d90f9382024b 100644
--- a/drivers/platform/x86/amd/pmf/spc.c
+++ b/drivers/platform/x86/amd/pmf/spc.c
@@ -219,12 +219,14 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
 
 	switch (dev->current_profile) {
 	case PLATFORM_PROFILE_PERFORMANCE:
+	case PLATFORM_PROFILE_BALANCED_PERFORMANCE:
 		val = TA_BEST_PERFORMANCE;
 		break;
 	case PLATFORM_PROFILE_BALANCED:
 		val = TA_BETTER_PERFORMANCE;
 		break;
 	case PLATFORM_PROFILE_LOW_POWER:
+	case PLATFORM_PROFILE_QUIET:
 		val = TA_BEST_BATTERY;
 		break;
 	default:

From fc99045effa81fdf509c2a97cbb7e6e8f2fd4443 Mon Sep 17 00:00:00 2001
From: Paulo Alcantara <pc@manguebit.com>
Date: Wed, 12 Mar 2025 10:51:31 -0300
Subject: [PATCH 2099/2753] smb: client: fix regression with guest option

When mounting a CIFS share with 'guest' mount option, mount.cifs(8)
will set empty password= and password2= options.  Currently we only
handle empty strings from user= and password= options, so the mount
will fail with

	cifs: Bad value for 'password2'

Fix this by handling empty string from password2= option as well.

Link: https://bbs.archlinux.org/viewtopic.php?id=303927
Reported-by: Adam Williamson <awilliam@redhat.com>
Closes: https://lore.kernel.org/r/83c00b5fea81c07f6897a5dd3ef50fd3b290f56c.camel@redhat.com
Fixes: 35f834265e0d ("smb3: fix broken reconnect when password changing on the server by allowing password rotation")
Cc: stable@vger.kernel.org
Signed-off-by: Paulo Alcantara (Red Hat) <pc@manguebit.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index e9b286d9a7ba3..457452b4d42da 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -171,6 +171,7 @@ const struct fs_parameter_spec smb3_fs_parameters[] = {
 	fsparam_string("username", Opt_user),
 	fsparam_string("pass", Opt_pass),
 	fsparam_string("password", Opt_pass),
+	fsparam_string("pass2", Opt_pass2),
 	fsparam_string("password2", Opt_pass2),
 	fsparam_string("ip", Opt_ip),
 	fsparam_string("addr", Opt_ip),
@@ -1131,6 +1132,9 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		} else if (!strcmp("user", param->key) || !strcmp("username", param->key)) {
 			skip_parsing = true;
 			opt = Opt_user;
+		} else if (!strcmp("pass2", param->key) || !strcmp("password2", param->key)) {
+			skip_parsing = true;
+			opt = Opt_pass2;
 		}
 	}
 

From 7489161b1852390b4413d57f2457cd40b34da6cc Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Tue, 11 Mar 2025 17:22:03 +0300
Subject: [PATCH 2100/2753] cifs: Fix integer overflow while processing
 acregmax mount option

User-provided mount parameter acregmax of type u32 is intended to have
an upper limit, but before it is validated, the value is converted from
seconds to jiffies which can lead to an integer overflow.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 5780464614f6 ("cifs: Add new parameter "acregmax" for distinct file and directory metadata timeout")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 457452b4d42da..5f3c5967a0f5a 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1344,11 +1344,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		}
 		break;
 	case Opt_acregmax:
-		ctx->acregmax = HZ * result.uint_32;
-		if (ctx->acregmax > CIFS_MAX_ACTIMEO) {
+		if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) {
 			cifs_errorf(fc, "acregmax too large\n");
 			goto cifs_parse_mount_err;
 		}
+		ctx->acregmax = HZ * result.uint_32;
 		break;
 	case Opt_acdirmax:
 		ctx->acdirmax = HZ * result.uint_32;

From 5b29891f91dfb8758baf1e2217bef4b16b2b165b Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Tue, 11 Mar 2025 17:22:04 +0300
Subject: [PATCH 2101/2753] cifs: Fix integer overflow while processing
 acdirmax mount option

User-provided mount parameter acdirmax of type u32 is intended to have
an upper limit, but before it is validated, the value is converted from
seconds to jiffies which can lead to an integer overflow.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 4c9f948142a5 ("cifs: Add new mount parameter "acdirmax" to allow caching directory metadata")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 5f3c5967a0f5a..c983021c406bb 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1351,11 +1351,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		ctx->acregmax = HZ * result.uint_32;
 		break;
 	case Opt_acdirmax:
-		ctx->acdirmax = HZ * result.uint_32;
-		if (ctx->acdirmax > CIFS_MAX_ACTIMEO) {
+		if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) {
 			cifs_errorf(fc, "acdirmax too large\n");
 			goto cifs_parse_mount_err;
 		}
+		ctx->acdirmax = HZ * result.uint_32;
 		break;
 	case Opt_actimeo:
 		if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) {

From 64f690ee22c99e16084e0e45181b2a1eed2fa149 Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Tue, 11 Mar 2025 17:22:05 +0300
Subject: [PATCH 2102/2753] cifs: Fix integer overflow while processing actimeo
 mount option

User-provided mount parameter actimeo of type u32 is intended to have
an upper limit, but before it is validated, the value is converted from
seconds to jiffies which can lead to an integer overflow.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 6d20e8406f09 ("cifs: add attribute cache timeout (actimeo) tunable")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index c983021c406bb..85b062e7f48db 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1358,7 +1358,7 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		ctx->acdirmax = HZ * result.uint_32;
 		break;
 	case Opt_actimeo:
-		if (HZ * result.uint_32 > CIFS_MAX_ACTIMEO) {
+		if (result.uint_32 > CIFS_MAX_ACTIMEO / HZ) {
 			cifs_errorf(fc, "timeout too large\n");
 			goto cifs_parse_mount_err;
 		}

From d5a30fddfe2f2e540f6c43b59cf701809995faef Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Tue, 11 Mar 2025 17:22:06 +0300
Subject: [PATCH 2103/2753] cifs: Fix integer overflow while processing
 closetimeo mount option

User-provided mount parameter closetimeo of type u32 is intended to have
an upper limit, but before it is validated, the value is converted from
seconds to jiffies which can lead to an integer overflow.

Found by Linux Verification Center (linuxtesting.org) with SVACE.

Fixes: 5efdd9122eff ("smb3: allow deferred close timeout to be configurable")
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/fs_context.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/fs/smb/client/fs_context.c b/fs/smb/client/fs_context.c
index 85b062e7f48db..8c73d4d60d1a7 100644
--- a/fs/smb/client/fs_context.c
+++ b/fs/smb/client/fs_context.c
@@ -1370,11 +1370,11 @@ static int smb3_fs_context_parse_param(struct fs_context *fc,
 		ctx->acdirmax = ctx->acregmax = HZ * result.uint_32;
 		break;
 	case Opt_closetimeo:
-		ctx->closetimeo = HZ * result.uint_32;
-		if (ctx->closetimeo > SMB3_MAX_DCLOSETIMEO) {
+		if (result.uint_32 > SMB3_MAX_DCLOSETIMEO / HZ) {
 			cifs_errorf(fc, "closetimeo too large\n");
 			goto cifs_parse_mount_err;
 		}
+		ctx->closetimeo = HZ * result.uint_32;
 		break;
 	case Opt_echo_interval:
 		ctx->echo_interval = result.uint_32;

From 605b249ea96770ac4fac4b8510a99e0f8442be5e Mon Sep 17 00:00:00 2001
From: Henrique Carvalho <henrique.carvalho@suse.com>
Date: Tue, 11 Mar 2025 15:23:59 -0300
Subject: [PATCH 2104/2753] smb: client: Fix match_session bug preventing
 session reuse

Fix a bug in match_session() that can causes the session to not be
reused in some cases.

Reproduction steps:

mount.cifs //server/share /mnt/a -o credentials=creds
mount.cifs //server/share /mnt/b -o credentials=creds,sec=ntlmssp
cat /proc/fs/cifs/DebugData | grep SessionId | wc -l

mount.cifs //server/share /mnt/b -o credentials=creds,sec=ntlmssp
mount.cifs //server/share /mnt/a -o credentials=creds
cat /proc/fs/cifs/DebugData | grep SessionId | wc -l

Cc: stable@vger.kernel.org
Reviewed-by: Enzo Matsumiya <ematsumiya@suse.de>
Signed-off-by: Henrique Carvalho <henrique.carvalho@suse.com>
Signed-off-by: Steve French <stfrench@microsoft.com>
---
 fs/smb/client/connect.c | 16 ++++++++++++----
 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
index f917de020dd5d..73f93a35eeddb 100644
--- a/fs/smb/client/connect.c
+++ b/fs/smb/client/connect.c
@@ -1825,9 +1825,8 @@ static int match_session(struct cifs_ses *ses,
 			 struct smb3_fs_context *ctx,
 			 bool match_super)
 {
-	if (ctx->sectype != Unspecified &&
-	    ctx->sectype != ses->sectype)
-		return 0;
+	struct TCP_Server_Info *server = ses->server;
+	enum securityEnum ctx_sec, ses_sec;
 
 	if (!match_super && ctx->dfs_root_ses != ses->dfs_root_ses)
 		return 0;
@@ -1839,11 +1838,20 @@ static int match_session(struct cifs_ses *ses,
 	if (ses->chan_max < ctx->max_channels)
 		return 0;
 
-	switch (ses->sectype) {
+	ctx_sec = server->ops->select_sectype(server, ctx->sectype);
+	ses_sec = server->ops->select_sectype(server, ses->sectype);
+
+	if (ctx_sec != ses_sec)
+		return 0;
+
+	switch (ctx_sec) {
+	case IAKerb:
 	case Kerberos:
 		if (!uid_eq(ctx->cred_uid, ses->cred_uid))
 			return 0;
 		break;
+	case NTLMv2:
+	case RawNTLMSSP:
 	default:
 		/* NULL username means anonymous session */
 		if (ses->user_name == NULL) {

From bc71aab4513f7fecd23c051703ef5adea2230a54 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:48 +0100
Subject: [PATCH 2105/2753] Revert "ext4: add pre-content fsnotify hook for DAX
 faults"

This reverts commit bb480760ffc7018e21ee6f60241c2b99ff26ee0e.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-3-amir73il@gmail.com
---
 fs/ext4/file.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index a5205149adba3..3bd96c3d4cd0c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -756,9 +756,6 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
 			return VM_FAULT_SIGBUS;
 		}
 	} else {
-		result = filemap_fsnotify_fault(vmf);
-		if (unlikely(result))
-			return result;
 		filemap_invalidate_lock_shared(mapping);
 	}
 	result = dax_iomap_fault(vmf, order, &pfn, &error, &ext4_iomap_ops);

From 27773ce1776279ed3220a34d2e6bfcecaee7fc66 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:49 +0100
Subject: [PATCH 2106/2753] Revert "xfs: add pre-content fsnotify hook for DAX
 faults"

This reverts commit 7f4796a46571ced5d3d5b0942e1bfea1eedaaecd.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-4-amir73il@gmail.com
---
 fs/xfs/xfs_file.c | 13 -------------
 1 file changed, 13 deletions(-)

diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f7a7d89c345ec..9a435b1ff2647 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1451,9 +1451,6 @@ xfs_dax_read_fault(
 
 	trace_xfs_read_fault(ip, order);
 
-	ret = filemap_fsnotify_fault(vmf);
-	if (unlikely(ret))
-		return ret;
 	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
 	ret = xfs_dax_fault_locked(vmf, order, false);
 	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
@@ -1482,16 +1479,6 @@ xfs_write_fault(
 	vm_fault_t		ret;
 
 	trace_xfs_write_fault(ip, order);
-	/*
-	 * Usually we get here from ->page_mkwrite callback but in case of DAX
-	 * we will get here also for ordinary write fault. Handle HSM
-	 * notifications for that case.
-	 */
-	if (IS_DAX(inode)) {
-		ret = filemap_fsnotify_fault(vmf);
-		if (unlikely(ret))
-			return ret;
-	}
 
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vmf->vma->vm_file);

From 955fbe0ef19df4197595a98d0906c94025c4beef Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:50 +0100
Subject: [PATCH 2107/2753] Revert "fsnotify: generate pre-content permission
 event on page fault"

This reverts commit 8392bc2ff8c8bf7c4c5e6dfa71ccd893a3c046f6.

In the use case of buffered write whose input buffer is mmapped file on a
filesystem with a pre-content mark, the prefaulting of the buffer can
happen under the filesystem freeze protection (obtained in vfs_write())
which breaks assumptions of pre-content hook and introduces potential
deadlock of HSM handler in userspace with filesystem freezing.

Now that we have pre-content hooks at file mmap() time, disable the
pre-content event hooks on page fault to avoid the potential deadlock.

Reported-by: syzbot+7229071b47908b19d5b7@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-fsdevel/7ehxrhbvehlrjwvrduoxsao5k3x4aw275patsb3krkwuq573yv@o2hskrfawbnc/
Fixes: 8392bc2ff8c8 ("fsnotify: generate pre-content permission event on page fault")
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-5-amir73il@gmail.com
---
 include/linux/mm.h |  1 -
 mm/filemap.c       | 74 ----------------------------------------------
 mm/nommu.c         |  7 -----
 3 files changed, 82 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7b1068ddcbb70..8483e09aeb2cd 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3420,7 +3420,6 @@ extern vm_fault_t filemap_fault(struct vm_fault *vmf);
 extern vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 		pgoff_t start_pgoff, pgoff_t end_pgoff);
 extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
-extern vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf);
 
 extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
diff --git a/mm/filemap.c b/mm/filemap.c
index 2974691fdfad2..ff5fcdd961364 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -47,7 +47,6 @@
 #include <linux/splice.h>
 #include <linux/rcupdate_wait.h>
 #include <linux/sched/mm.h>
-#include <linux/fsnotify.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include "internal.h"
@@ -3336,48 +3335,6 @@ static vm_fault_t filemap_fault_recheck_pte_none(struct vm_fault *vmf)
 	return ret;
 }
 
-/**
- * filemap_fsnotify_fault - maybe emit a pre-content event.
- * @vmf:	struct vm_fault containing details of the fault.
- *
- * If we have a pre-content watch on this file we will emit an event for this
- * range.  If we return anything the fault caller should return immediately, we
- * will return VM_FAULT_RETRY if we had to emit an event, which will trigger the
- * fault again and then the fault handler will run the second time through.
- *
- * Return: a bitwise-OR of %VM_FAULT_ codes, 0 if nothing happened.
- */
-vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf)
-{
-	struct file *fpin = NULL;
-	int mask = (vmf->flags & FAULT_FLAG_WRITE) ? MAY_WRITE : MAY_ACCESS;
-	loff_t pos = vmf->pgoff >> PAGE_SHIFT;
-	size_t count = PAGE_SIZE;
-	int err;
-
-	/*
-	 * We already did this and now we're retrying with everything locked,
-	 * don't emit the event and continue.
-	 */
-	if (vmf->flags & FAULT_FLAG_TRIED)
-		return 0;
-
-	/* No watches, we're done. */
-	if (likely(!FMODE_FSNOTIFY_HSM(vmf->vma->vm_file->f_mode)))
-		return 0;
-
-	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-	if (!fpin)
-		return VM_FAULT_SIGBUS;
-
-	err = fsnotify_file_area_perm(fpin, mask, &pos, count);
-	fput(fpin);
-	if (err)
-		return VM_FAULT_SIGBUS;
-	return VM_FAULT_RETRY;
-}
-EXPORT_SYMBOL_GPL(filemap_fsnotify_fault);
-
 /**
  * filemap_fault - read in file data for page fault handling
  * @vmf:	struct vm_fault containing details of the fault
@@ -3481,37 +3438,6 @@ vm_fault_t filemap_fault(struct vm_fault *vmf)
 	 * or because readahead was otherwise unable to retrieve it.
 	 */
 	if (unlikely(!folio_test_uptodate(folio))) {
-		/*
-		 * If this is a precontent file we have can now emit an event to
-		 * try and populate the folio.
-		 */
-		if (!(vmf->flags & FAULT_FLAG_TRIED) &&
-		    unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) {
-			loff_t pos = folio_pos(folio);
-			size_t count = folio_size(folio);
-
-			/* We're NOWAIT, we have to retry. */
-			if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT) {
-				folio_unlock(folio);
-				goto out_retry;
-			}
-
-			if (mapping_locked)
-				filemap_invalidate_unlock_shared(mapping);
-			mapping_locked = false;
-
-			folio_unlock(folio);
-			fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-			if (!fpin)
-				goto out_retry;
-
-			error = fsnotify_file_area_perm(fpin, MAY_ACCESS, &pos,
-							count);
-			if (error)
-				ret = VM_FAULT_SIGBUS;
-			goto out_retry;
-		}
-
 		/*
 		 * If the invalidate lock is not held, the folio was in cache
 		 * and uptodate and now it is not. Strange but possible since we
diff --git a/mm/nommu.c b/mm/nommu.c
index baa79abdaf037..9cb6e99215e2b 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1613,13 +1613,6 @@ int remap_vmalloc_range(struct vm_area_struct *vma, void *addr,
 }
 EXPORT_SYMBOL(remap_vmalloc_range);
 
-vm_fault_t filemap_fsnotify_fault(struct vm_fault *vmf)
-{
-	BUG();
-	return 0;
-}
-EXPORT_SYMBOL_GPL(filemap_fsnotify_fault);
-
 vm_fault_t filemap_fault(struct vm_fault *vmf)
 {
 	BUG();

From 4f4dc3a9378bc2e6bcf331ee9e65a21abf67e7e0 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:51 +0100
Subject: [PATCH 2108/2753] Revert "mm: don't allow huge faults for files with
 pre content watches"

This reverts commit 20bf82a898b65c129af76deb96a1b415d3098a28.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-6-amir73il@gmail.com
---
 mm/memory.c | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c
index b9661ccfa64fd..fb7b8dc751679 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -76,7 +76,6 @@
 #include <linux/ptrace.h>
 #include <linux/vmalloc.h>
 #include <linux/sched/sysctl.h>
-#include <linux/fsnotify.h>
 
 #include <trace/events/kmem.h>
 
@@ -5750,17 +5749,8 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
 static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
 {
 	struct vm_area_struct *vma = vmf->vma;
-
 	if (vma_is_anonymous(vma))
 		return do_huge_pmd_anonymous_page(vmf);
-	/*
-	 * Currently we just emit PAGE_SIZE for our fault events, so don't allow
-	 * a huge fault if we have a pre content watch on this file.  This would
-	 * be trivial to support, but there would need to be tests to ensure
-	 * this works properly and those don't exist currently.
-	 */
-	if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
-		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 	return VM_FAULT_FALLBACK;
@@ -5784,9 +5774,6 @@ static inline vm_fault_t wp_huge_pmd(struct vm_fault *vmf)
 	}
 
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
-		/* See comment in create_huge_pmd. */
-		if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
-			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PMD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))
@@ -5809,9 +5796,6 @@ static vm_fault_t create_huge_pud(struct vm_fault *vmf)
 	/* No support for anonymous transparent PUD pages yet */
 	if (vma_is_anonymous(vma))
 		return VM_FAULT_FALLBACK;
-	/* See comment in create_huge_pmd. */
-	if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
-		return VM_FAULT_FALLBACK;
 	if (vma->vm_ops->huge_fault)
 		return vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -5829,9 +5813,6 @@ static vm_fault_t wp_huge_pud(struct vm_fault *vmf, pud_t orig_pud)
 	if (vma_is_anonymous(vma))
 		goto split;
 	if (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) {
-		/* See comment in create_huge_pmd. */
-		if (unlikely(FMODE_FSNOTIFY_HSM(vma->vm_file->f_mode)))
-			goto split;
 		if (vma->vm_ops->huge_fault) {
 			ret = vma->vm_ops->huge_fault(vmf, PUD_ORDER);
 			if (!(ret & VM_FAULT_FALLBACK))

From 252256e416deb255607f0c4a69e7cfec079e5d61 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Wed, 12 Mar 2025 08:38:52 +0100
Subject: [PATCH 2109/2753] Revert "fanotify: disable readahead if we have
 pre-content watches"

This reverts commit fac84846a28c0950d4433118b3dffd44306df62d.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250312073852.2123409-7-amir73il@gmail.com
---
 mm/filemap.c   | 12 ------------
 mm/readahead.c | 14 --------------
 2 files changed, 26 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index ff5fcdd961364..6d616bb9001eb 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3197,14 +3197,6 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	unsigned long vm_flags = vmf->vma->vm_flags;
 	unsigned int mmap_miss;
 
-	/*
-	 * If we have pre-content watches we need to disable readahead to make
-	 * sure that we don't populate our mapping with 0 filled pages that we
-	 * never emitted an event for.
-	 */
-	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
-		return fpin;
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
 	if ((vm_flags & VM_HUGEPAGE) && HPAGE_PMD_ORDER <= MAX_PAGECACHE_ORDER) {
@@ -3273,10 +3265,6 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
 	struct file *fpin = NULL;
 	unsigned int mmap_miss;
 
-	/* See comment in do_sync_mmap_readahead. */
-	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode)))
-		return fpin;
-
 	/* If we don't want any read-ahead, don't bother */
 	if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
 		return fpin;
diff --git a/mm/readahead.c b/mm/readahead.c
index 220155a5c9646..6a4e96b69702b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -128,7 +128,6 @@
 #include <linux/blk-cgroup.h>
 #include <linux/fadvise.h>
 #include <linux/sched/mm.h>
-#include <linux/fsnotify.h>
 
 #include "internal.h"
 
@@ -558,15 +557,6 @@ void page_cache_sync_ra(struct readahead_control *ractl,
 	unsigned long max_pages, contig_count;
 	pgoff_t prev_index, miss;
 
-	/*
-	 * If we have pre-content watches we need to disable readahead to make
-	 * sure that we don't find 0 filled pages in cache that we never emitted
-	 * events for. Filesystems supporting HSM must make sure to not call
-	 * this function with ractl->file unset for files handled by HSM.
-	 */
-	if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode)))
-		return;
-
 	/*
 	 * Even if readahead is disabled, issue this request as readahead
 	 * as we'll need it to satisfy the requested range. The forced
@@ -645,10 +635,6 @@ void page_cache_async_ra(struct readahead_control *ractl,
 	if (!ra->ra_pages)
 		return;
 
-	/* See the comment in page_cache_sync_ra. */
-	if (ractl->file && unlikely(FMODE_FSNOTIFY_HSM(ractl->file->f_mode)))
-		return;
-
 	/*
 	 * Same bit is used for PG_readahead and PG_reclaim.
 	 */

From 69a5a13a22b1def29dce62b5b7c86e6098c20c68 Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 13 Mar 2025 09:56:07 -0400
Subject: [PATCH 2110/2753] bcachefs: target_congested ->
 get_random_u32_below()

get_random_u32_below() has a better algorithm than bch2_rand_range(),
it just didn't exist at the time.

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/io_read.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/bcachefs/io_read.c b/fs/bcachefs/io_read.c
index 726da68073e2b..aa91fcf51eecc 100644
--- a/fs/bcachefs/io_read.c
+++ b/fs/bcachefs/io_read.c
@@ -59,7 +59,7 @@ static bool bch2_target_congested(struct bch_fs *c, u16 target)
 	}
 	rcu_read_unlock();
 
-	return bch2_rand_range(nr * CONGESTED_MAX) < total;
+	return get_random_u32_below(nr * CONGESTED_MAX) < total;
 }
 
 #else

From 9c18ea7ffee090b47afaa7dc41903fb1b436d7bd Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Thu, 13 Mar 2025 11:16:28 -0400
Subject: [PATCH 2111/2753] bcachefs: bch2_get_random_u64_below()

steal the (clever) algorithm from get_random_u32_below()

this fixes a bug where we were passing roundup_pow_of_two() a 64 bit
number - we're squaring device latencies now:

[  +1.681698] ------------[ cut here ]------------
[  +0.000010] UBSAN: shift-out-of-bounds in ./include/linux/log2.h:57:13
[  +0.000011] shift exponent 64 is too large for 64-bit type 'long unsigned int'
[  +0.000011] CPU: 1 UID: 0 PID: 196 Comm: kworker/u32:13 Not tainted 6.14.0-rc6-dave+ #10
[  +0.000012] Hardware name: ASUS System Product Name/PRIME B460I-PLUS, BIOS 1301 07/13/2021
[  +0.000005] Workqueue: events_unbound __bch2_read_endio [bcachefs]
[  +0.000354] Call Trace:
[  +0.000005]  <TASK>
[  +0.000007]  dump_stack_lvl+0x5d/0x80
[  +0.000018]  ubsan_epilogue+0x5/0x30
[  +0.000008]  __ubsan_handle_shift_out_of_bounds.cold+0x61/0xe6
[  +0.000011]  bch2_rand_range.cold+0x17/0x20 [bcachefs]
[  +0.000231]  bch2_bkey_pick_read_device+0x547/0x920 [bcachefs]
[  +0.000229]  __bch2_read_extent+0x1e4/0x18e0 [bcachefs]
[  +0.000241]  ? bch2_btree_iter_peek_slot+0x3df/0x800 [bcachefs]
[  +0.000180]  ? bch2_read_retry_nodecode+0x270/0x330 [bcachefs]
[  +0.000230]  bch2_read_retry_nodecode+0x270/0x330 [bcachefs]
[  +0.000230]  bch2_rbio_retry+0x1fa/0x600 [bcachefs]
[  +0.000224]  ? bch2_printbuf_make_room+0x71/0xb0 [bcachefs]
[  +0.000243]  ? bch2_read_csum_err+0x4a4/0x610 [bcachefs]
[  +0.000278]  bch2_read_csum_err+0x4a4/0x610 [bcachefs]
[  +0.000227]  ? __bch2_read_endio+0x58b/0x870 [bcachefs]
[  +0.000220]  __bch2_read_endio+0x58b/0x870 [bcachefs]
[  +0.000268]  ? try_to_wake_up+0x31c/0x7f0
[  +0.000011]  ? process_one_work+0x176/0x330
[  +0.000008]  process_one_work+0x176/0x330
[  +0.000008]  worker_thread+0x252/0x390
[  +0.000008]  ? __pfx_worker_thread+0x10/0x10
[  +0.000006]  kthread+0xec/0x230
[  +0.000011]  ? __pfx_kthread+0x10/0x10
[  +0.000009]  ret_from_fork+0x31/0x50
[  +0.000009]  ? __pfx_kthread+0x10/0x10
[  +0.000008]  ret_from_fork_asm+0x1a/0x30
[  +0.000012]  </TASK>
[  +0.000046] ---[ end trace ]---

Reported-by: Roland Vet <vet.roland@protonmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/extents.c |  2 +-
 fs/bcachefs/util.c    | 23 ++++++++++++++---------
 fs/bcachefs/util.h    |  2 +-
 3 files changed, 16 insertions(+), 11 deletions(-)

diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
index 05d5f71a7ca9f..2d8042f853dcd 100644
--- a/fs/bcachefs/extents.c
+++ b/fs/bcachefs/extents.c
@@ -99,7 +99,7 @@ static inline bool ptr_better(struct bch_fs *c,
 
 		/* Pick at random, biased in favor of the faster device: */
 
-		return bch2_rand_range(l1 + l2) > l1;
+		return bch2_get_random_u64_below(l1 + l2) > l1;
 	}
 
 	if (bch2_force_reconstruct_read)
diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index e0a876cbaa6b7..8e3ab4bf79a90 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -653,19 +653,24 @@ int bch2_bio_alloc_pages(struct bio *bio, size_t size, gfp_t gfp_mask)
 	return 0;
 }
 
-size_t bch2_rand_range(size_t max)
+u64 bch2_get_random_u64_below(u64 ceil)
 {
-	size_t rand;
+	if (ceil <= U32_MAX)
+		return __get_random_u32_below(ceil);
 
-	if (!max)
-		return 0;
+	/* this is the same (clever) algorithm as in __get_random_u32_below() */
+	u64 rand = get_random_u64();
+	u64 mult = ceil * rand;
 
-	do {
-		rand = get_random_long();
-		rand &= roundup_pow_of_two(max) - 1;
-	} while (rand >= max);
+	if (unlikely(mult < ceil)) {
+		u64 bound = -ceil % ceil;
+		while (unlikely(mult < bound)) {
+			rand = get_random_u64();
+			mult = ceil * rand;
+		}
+	}
 
-	return rand;
+	return mul_u64_u64_shr(ceil, rand, 64);
 }
 
 void memcpy_to_bio(struct bio *dst, struct bvec_iter dst_iter, const void *src)
diff --git a/fs/bcachefs/util.h b/fs/bcachefs/util.h
index e7c3541b38f3f..f4a4783219d9d 100644
--- a/fs/bcachefs/util.h
+++ b/fs/bcachefs/util.h
@@ -401,7 +401,7 @@ do {									\
 	_ret;								\
 })
 
-size_t bch2_rand_range(size_t);
+u64 bch2_get_random_u64_below(u64);
 
 void memcpy_to_bio(struct bio *, struct bvec_iter, const void *);
 void memcpy_from_bio(void *, struct bio *, struct bvec_iter);

From 57e9417f69839cb10f7ffca684c38acd28ceb57b Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Sat, 8 Mar 2025 10:50:08 -0500
Subject: [PATCH 2112/2753] dm-flakey: Fix memory corruption in optional
 corrupt_bio_byte feature

Fix memory corruption due to incorrect parameter being passed to bio_init

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org	# v6.5+
Fixes: 1d9a94389853 ("dm flakey: clone pages on write bio before corrupting them")
---
 drivers/md/dm-flakey.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/md/dm-flakey.c b/drivers/md/dm-flakey.c
index 731467d4ed101..b690905ab89ff 100644
--- a/drivers/md/dm-flakey.c
+++ b/drivers/md/dm-flakey.c
@@ -426,7 +426,7 @@ static struct bio *clone_bio(struct dm_target *ti, struct flakey_c *fc, struct b
 	if (!clone)
 		return NULL;
 
-	bio_init(clone, fc->dev->bdev, bio->bi_inline_vecs, nr_iovecs, bio->bi_opf);
+	bio_init(clone, fc->dev->bdev, clone->bi_inline_vecs, nr_iovecs, bio->bi_opf);
 
 	clone->bi_iter.bi_sector = flakey_map_sector(ti, bio->bi_iter.bi_sector);
 	clone->bi_private = bio;

From a2ab25529bbcea51b5e01dded79f45aeb94f644a Mon Sep 17 00:00:00 2001
From: Ajay Kaher <ajay.kaher@broadcom.com>
Date: Thu, 13 Mar 2025 17:31:11 +0000
Subject: [PATCH 2113/2753] x86/vmware: Parse MP tables for SEV-SNP enabled
 guests under VMware hypervisors

Under VMware hypervisors, SEV-SNP enabled VMs are fundamentally able to boot
without UEFI, but this regressed a year ago due to:

  0f4a1e80989a ("x86/sev: Skip ROM range scans and validation for SEV-SNP guests")

In this case, mpparse_find_mptable() has to be called to parse MP
tables which contains the necessary boot information.

[ mingo: Updated the changelog. ]

Fixes: 0f4a1e80989a ("x86/sev: Skip ROM range scans and validation for SEV-SNP guests")
Co-developed-by: Ye Li <ye.li@broadcom.com>
Signed-off-by: Ye Li <ye.li@broadcom.com>
Signed-off-by: Ajay Kaher <ajay.kaher@broadcom.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Ye Li <ye.li@broadcom.com>
Reviewed-by: Kevin Loughlin <kevinloughlin@google.com>
Acked-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20250313173111.10918-1-ajay.kaher@broadcom.com
---
 arch/x86/kernel/cpu/vmware.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 00189cdeb775f..cb3f900c46fcc 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -26,6 +26,7 @@
 #include <linux/export.h>
 #include <linux/clocksource.h>
 #include <linux/cpu.h>
+#include <linux/efi.h>
 #include <linux/reboot.h>
 #include <linux/static_call.h>
 #include <asm/div64.h>
@@ -429,6 +430,9 @@ static void __init vmware_platform_setup(void)
 		pr_warn("Failed to get TSC freq from the hypervisor\n");
 	}
 
+	if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !efi_enabled(EFI_BOOT))
+		x86_init.mpparse.find_mptable = mpparse_find_mptable;
+
 	vmware_paravirt_ops_setup();
 
 #ifdef CONFIG_X86_IO_APIC

From 72d061ee630d0dbb45c2920d8d19b3861c413e54 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 10 Mar 2025 22:46:56 +0300
Subject: [PATCH 2114/2753] Bluetooth: Fix error code in chan_alloc_skb_cb()

The chan_alloc_skb_cb() function is supposed to return error pointers on
error.  Returning NULL will lead to a NULL dereference.

Fixes: 6b8d4a6a0314 ("Bluetooth: 6LoWPAN: Use connected oriented channel instead of fixed one")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/6lowpan.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 50cfec8ccac4f..3c29778171c58 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -825,11 +825,16 @@ static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan,
 					 unsigned long hdr_len,
 					 unsigned long len, int nb)
 {
+	struct sk_buff *skb;
+
 	/* Note that we must allocate using GFP_ATOMIC here as
 	 * this function is called originally from netdev hard xmit
 	 * function in atomic context.
 	 */
-	return bt_skb_alloc(hdr_len + len, GFP_ATOMIC);
+	skb = bt_skb_alloc(hdr_len + len, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+	return skb;
 }
 
 static void chan_suspend_cb(struct l2cap_chan *chan)

From f6685a96c8c8a07e260e39bac86d4163cfb38a4d Mon Sep 17 00:00:00 2001
From: Arkadiusz Bokowy <arkadiusz.bokowy@gmail.com>
Date: Wed, 12 Mar 2025 20:09:43 +0100
Subject: [PATCH 2115/2753] Bluetooth: hci_event: Fix connection regression
 between LE and non-LE adapters

Due to a typo during defining HCI errors it is not possible to connect
LE-capable device with BR/EDR only adapter. The connection is terminated
by the LE adapter because the invalid LL params error code is treated
as unsupported remote feature.

Fixes: 79c0868ad65a ("Bluetooth: hci_event: Use HCI error defines instead of magic values")
Signed-off-by: Arkadiusz Bokowy <arkadiusz.bokowy@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 0d51970d809fd..3ec915738112b 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -683,7 +683,7 @@ enum {
 #define HCI_ERROR_REMOTE_POWER_OFF	0x15
 #define HCI_ERROR_LOCAL_HOST_TERM	0x16
 #define HCI_ERROR_PAIRING_NOT_ALLOWED	0x18
-#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE	0x1e
+#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE	0x1a
 #define HCI_ERROR_INVALID_LL_PARAMS	0x1e
 #define HCI_ERROR_UNSPECIFIED		0x1f
 #define HCI_ERROR_ADVERTISING_TIMEOUT	0x3c

From 49f6713cb6913e1e62d98a36548c592b3d5d32df Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 12 Mar 2025 16:35:20 +0100
Subject: [PATCH 2116/2753] tcp: bpf: Introduce bpf_sol_tcp_getsockopt to
 support TCP_BPF flags

The patch refactors a bit on supporting getsockopt for TCP BPF flags.
For now, only TCP_BPF_SOCK_OPS_CB_FLAGS. Later, more flags will be added
into this function.

No functional changes here.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250312153523.9860-2-kerneljasonxing@gmail.com
---
 net/core/filter.c | 33 +++++++++++++++++++++------------
 1 file changed, 21 insertions(+), 12 deletions(-)

diff --git a/net/core/filter.c b/net/core/filter.c
index a0867c5b32b37..2932de5cc57ce 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5282,6 +5282,26 @@ static int sol_socket_sockopt(struct sock *sk, int optname,
 			     KERNEL_SOCKPTR(optval), *optlen);
 }
 
+static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname,
+				  char *optval, int optlen)
+{
+	if (optlen != sizeof(int))
+		return -EINVAL;
+
+	switch (optname) {
+	case TCP_BPF_SOCK_OPS_CB_FLAGS: {
+		int cb_flags = tcp_sk(sk)->bpf_sock_ops_cb_flags;
+
+		memcpy(optval, &cb_flags, optlen);
+		break;
+	}
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int bpf_sol_tcp_setsockopt(struct sock *sk, int optname,
 				  char *optval, int optlen)
 {
@@ -5415,20 +5435,9 @@ static int sol_tcp_sockopt(struct sock *sk, int optname,
 		if (*optlen < 1)
 			return -EINVAL;
 		break;
-	case TCP_BPF_SOCK_OPS_CB_FLAGS:
-		if (*optlen != sizeof(int))
-			return -EINVAL;
-		if (getopt) {
-			struct tcp_sock *tp = tcp_sk(sk);
-			int cb_flags = tp->bpf_sock_ops_cb_flags;
-
-			memcpy(optval, &cb_flags, *optlen);
-			return 0;
-		}
-		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
 	default:
 		if (getopt)
-			return -EINVAL;
+			return bpf_sol_tcp_getsockopt(sk, optname, optval, *optlen);
 		return bpf_sol_tcp_setsockopt(sk, optname, optval, *optlen);
 	}
 

From 5584cd7e0ddd0d4e6e91498864c4cd025445dafe Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 12 Mar 2025 16:35:21 +0100
Subject: [PATCH 2117/2753] tcp: bpf: Support bpf_getsockopt for
 TCP_BPF_RTO_MIN

Support bpf_getsockopt if application tries to know what the RTO MIN
of this socket is.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250312153523.9860-3-kerneljasonxing@gmail.com
---
 net/core/filter.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 2932de5cc57ce..4d34d35af5c78 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5295,6 +5295,12 @@ static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname,
 		memcpy(optval, &cb_flags, optlen);
 		break;
 	}
+	case TCP_BPF_RTO_MIN: {
+		int rto_min_us = jiffies_to_usecs(inet_csk(sk)->icsk_rto_min);
+
+		memcpy(optval, &rto_min_us, optlen);
+		break;
+	}
 	default:
 		return -EINVAL;
 	}

From d22b8b04b88e39d0ed1177fb31fd3e880ac0ee2d Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 12 Mar 2025 16:35:22 +0100
Subject: [PATCH 2118/2753] tcp: bpf: Support bpf_getsockopt for
 TCP_BPF_DELACK_MAX

Support bpf_getsockopt if application tries to know what the delayed ack
max time is.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250312153523.9860-4-kerneljasonxing@gmail.com
---
 net/core/filter.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/core/filter.c b/net/core/filter.c
index 4d34d35af5c78..46ae8eb7a03cb 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -5301,6 +5301,12 @@ static int bpf_sol_tcp_getsockopt(struct sock *sk, int optname,
 		memcpy(optval, &rto_min_us, optlen);
 		break;
 	}
+	case TCP_BPF_DELACK_MAX: {
+		int delack_max_us = jiffies_to_usecs(inet_csk(sk)->icsk_delack_max);
+
+		memcpy(optval, &delack_max_us, optlen);
+		break;
+	}
 	default:
 		return -EINVAL;
 	}

From a1e0783e1036ac33a08bdb6b88e671e267c332aa Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Wed, 12 Mar 2025 16:35:23 +0100
Subject: [PATCH 2119/2753] selftests/bpf: Add bpf_getsockopt() for
 TCP_BPF_DELACK_MAX and TCP_BPF_RTO_MIN

Add selftests for TCP_BPF_DELACK_MAX and TCP_BPF_RTO_MIN BPF socket
cases.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Link: https://patch.msgid.link/20250312153523.9860-5-kerneljasonxing@gmail.com
---
 tools/testing/selftests/bpf/progs/setget_sockopt.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/progs/setget_sockopt.c b/tools/testing/selftests/bpf/progs/setget_sockopt.c
index 106fe430f41b9..0107a24b7522b 100644
--- a/tools/testing/selftests/bpf/progs/setget_sockopt.c
+++ b/tools/testing/selftests/bpf/progs/setget_sockopt.c
@@ -61,6 +61,8 @@ static const struct sockopt_test sol_tcp_tests[] = {
 	{ .opt = TCP_NOTSENT_LOWAT, .new = 1314, .expected = 1314, },
 	{ .opt = TCP_BPF_SOCK_OPS_CB_FLAGS, .new = BPF_SOCK_OPS_ALL_CB_FLAGS,
 	  .expected = BPF_SOCK_OPS_ALL_CB_FLAGS, },
+	{ .opt = TCP_BPF_DELACK_MAX, .new = 30000, .expected = 30000, },
+	{ .opt = TCP_BPF_RTO_MIN, .new = 30000, .expected = 30000, },
 	{ .opt = TCP_RTO_MAX_MS, .new = 2000, .expected = 2000, },
 	{ .opt = 0, },
 };

From f2865c6300d75a9f187dd7918d248e010970fd44 Mon Sep 17 00:00:00 2001
From: Amit Sunil Dhamne <amitsd@google.com>
Date: Mon, 10 Mar 2025 19:19:07 -0700
Subject: [PATCH 2120/2753] usb: typec: tcpm: fix state transition for
 SNK_WAIT_CAPABILITIES state in run_state_machine()

A subtle error got introduced while manually fixing merge conflict in
tcpm.c for commit 85c4efbe6088 ("Merge v6.12-rc6 into usb-next"). As a
result of this error, the next state is unconditionally set to
SNK_WAIT_CAPABILITIES_TIMEOUT while handling SNK_WAIT_CAPABILITIES state
in run_state_machine(...).

Fix this by setting new state of TCPM state machine to `upcoming_state`
(that is set to different values based on conditions).

Cc: stable@vger.kernel.org
Fixes: 85c4efbe60888 ("Merge v6.12-rc6 into usb-next")
Signed-off-by: Amit Sunil Dhamne <amitsd@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250310-fix-snk-wait-timeout-v6-14-rc6-v1-1-5db14475798f@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/tcpm/tcpm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
index 6bf1a22c785af..62ca4a0ec55bb 100644
--- a/drivers/usb/typec/tcpm/tcpm.c
+++ b/drivers/usb/typec/tcpm/tcpm.c
@@ -5117,16 +5117,16 @@ static void run_state_machine(struct tcpm_port *port)
 		 */
 		if (port->vbus_never_low) {
 			port->vbus_never_low = false;
-			tcpm_set_state(port, SNK_SOFT_RESET,
-				       port->timings.sink_wait_cap_time);
+			upcoming_state = SNK_SOFT_RESET;
 		} else {
 			if (!port->self_powered)
 				upcoming_state = SNK_WAIT_CAPABILITIES_TIMEOUT;
 			else
 				upcoming_state = hard_reset_state(port);
-			tcpm_set_state(port, SNK_WAIT_CAPABILITIES_TIMEOUT,
-				       port->timings.sink_wait_cap_time);
 		}
+
+		tcpm_set_state(port, upcoming_state,
+			       port->timings.sink_wait_cap_time);
 		break;
 	case SNK_WAIT_CAPABILITIES_TIMEOUT:
 		/*

From 6263bad801ec08dadfd6fa3ac7673f556ef1795b Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Wed, 12 Mar 2025 18:45:22 +0100
Subject: [PATCH 2121/2753] dt-bindings: can: fsl,flexcan: add transceiver
 capabilities

Currently the flexcan driver does only support adding PHYs by using the
"old" regulator bindings. Add support for CAN transceivers as a PHY.

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Link: https://patch.msgid.link/20250312-flexcan-add-transceiver-caps-v4-1-29e89ae0225a@liebherr.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../devicetree/bindings/net/can/fsl,flexcan.yaml         | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
index 73252fe56fe6c..37e3e4f487629 100644
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -77,6 +77,9 @@ properties:
   xceiver-supply:
     description: Regulator that powers the CAN transceiver.
 
+  phys:
+    maxItems: 1
+
   big-endian:
     $ref: /schemas/types.yaml#/definitions/flag
     description: |
@@ -171,6 +174,12 @@ allOf:
         interrupts:
           maxItems: 1
         interrupt-names: false
+  - if:
+      required:
+        - xceiver-supply
+    then:
+      properties:
+        phys: false
 
 additionalProperties: false
 

From d80bfde3c57a02e67e7d3354d977b6376cc275ba Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Wed, 12 Mar 2025 18:45:23 +0100
Subject: [PATCH 2122/2753] can: flexcan: add transceiver capabilities

Currently the flexcan driver does only support adding PHYs by using the
"old" regulator bindings. Add support for CAN transceivers as a PHY. Add
the capability to ensure that the PHY is in operational state when the link
is set to an "up" state.

Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Link: https://patch.msgid.link/20250312-flexcan-add-transceiver-caps-v4-2-29e89ae0225a@liebherr.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 27 ++++++++++++++++++++------
 drivers/net/can/flexcan/flexcan.h      |  1 +
 2 files changed, 22 insertions(+), 6 deletions(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index b347a1c93536d..7588cb54a909a 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -26,6 +26,7 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/can/platform/flexcan.h>
+#include <linux/phy/phy.h>
 #include <linux/pm_runtime.h>
 #include <linux/property.h>
 #include <linux/regmap.h>
@@ -644,18 +645,22 @@ static void flexcan_clks_disable(const struct flexcan_priv *priv)
 
 static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv)
 {
-	if (!priv->reg_xceiver)
-		return 0;
+	if (priv->reg_xceiver)
+		return regulator_enable(priv->reg_xceiver);
+	else if (priv->transceiver)
+		return phy_power_on(priv->transceiver);
 
-	return regulator_enable(priv->reg_xceiver);
+	return 0;
 }
 
 static inline int flexcan_transceiver_disable(const struct flexcan_priv *priv)
 {
-	if (!priv->reg_xceiver)
-		return 0;
+	if (priv->reg_xceiver)
+		return regulator_disable(priv->reg_xceiver);
+	else if (priv->transceiver)
+		return phy_power_off(priv->transceiver);
 
-	return regulator_disable(priv->reg_xceiver);
+	return 0;
 }
 
 static int flexcan_chip_enable(struct flexcan_priv *priv)
@@ -2086,6 +2091,7 @@ static int flexcan_probe(struct platform_device *pdev)
 	struct net_device *dev;
 	struct flexcan_priv *priv;
 	struct regulator *reg_xceiver;
+	struct phy *transceiver;
 	struct clk *clk_ipg = NULL, *clk_per = NULL;
 	struct flexcan_regs __iomem *regs;
 	struct flexcan_platform_data *pdata;
@@ -2101,6 +2107,11 @@ static int flexcan_probe(struct platform_device *pdev)
 	else if (IS_ERR(reg_xceiver))
 		return PTR_ERR(reg_xceiver);
 
+	transceiver = devm_phy_optional_get(&pdev->dev, NULL);
+	if (IS_ERR(transceiver))
+		return dev_err_probe(&pdev->dev, PTR_ERR(transceiver),
+				     "failed to get phy\n");
+
 	if (pdev->dev.of_node) {
 		of_property_read_u32(pdev->dev.of_node,
 				     "clock-frequency", &clock_freq);
@@ -2198,6 +2209,10 @@ static int flexcan_probe(struct platform_device *pdev)
 	priv->clk_per = clk_per;
 	priv->clk_src = clk_src;
 	priv->reg_xceiver = reg_xceiver;
+	priv->transceiver = transceiver;
+
+	if (transceiver)
+		priv->can.bitrate_max = transceiver->attrs.max_link_rate;
 
 	if (priv->devtype_data.quirks & FLEXCAN_QUIRK_NR_IRQ_3) {
 		priv->irq_boff = platform_get_irq(pdev, 1);
diff --git a/drivers/net/can/flexcan/flexcan.h b/drivers/net/can/flexcan/flexcan.h
index 2cf886618c962..16692a2502eba 100644
--- a/drivers/net/can/flexcan/flexcan.h
+++ b/drivers/net/can/flexcan/flexcan.h
@@ -107,6 +107,7 @@ struct flexcan_priv {
 	struct clk *clk_per;
 	struct flexcan_devtype_data devtype_data;
 	struct regulator *reg_xceiver;
+	struct phy *transceiver;
 	struct flexcan_stop_mode stm;
 
 	int irq_boff;

From 1d22a122ffb116c3cf78053e812b8b21f8852ee9 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Tue, 18 Feb 2025 23:32:28 +0900
Subject: [PATCH 2123/2753] can: ucan: fix out of bound read in strscpy()
 source

Commit 7fdaf8966aae ("can: ucan: use strscpy() to instead of strncpy()")
unintentionally introduced a one byte out of bound read on strscpy()'s
source argument (which is kind of ironic knowing that strscpy() is meant
to be a more secure alternative :)).

Let's consider below buffers:

  dest[len + 1]; /* will be NUL terminated */
  src[len]; /* may not be NUL terminated */

When doing:

  strncpy(dest, src, len);
  dest[len] = '\0';

strncpy() will read up to len bytes from src.

On the other hand:

  strscpy(dest, src, len + 1);

will read up to len + 1 bytes from src, that is to say, an out of bound
read of one byte will occur on src if it is not NUL terminated. Note
that the src[len] byte is never copied, but strscpy() still needs to
read it to check whether a truncation occurred or not.

This exact pattern happened in ucan.

The root cause is that the source is not NUL terminated. Instead of
doing a copy in a local buffer, directly NUL terminate it as soon as
usb_control_msg() returns. With this, the local firmware_str[] variable
can be removed.

On top of this do a couple refactors:

  - ucan_ctl_payload->raw is only used for the firmware string, so
    rename it to ucan_ctl_payload->fw_str and change its type from u8 to
    char.

  - ucan_device_request_in() is only used to retrieve the firmware
    string, so rename it to ucan_get_fw_str() and refactor it to make it
    directly handle all the string termination logic.

Reported-by: syzbot+d7d8c418e8317899e88c@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-can/67b323a4.050a0220.173698.002b.GAE@google.com/
Fixes: 7fdaf8966aae ("can: ucan: use strscpy() to instead of strncpy()")
Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250218143515.627682-2-mailhol.vincent@wanadoo.fr
Cc: stable@vger.kernel.org
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/usb/ucan.c | 43 ++++++++++++++++----------------------
 1 file changed, 18 insertions(+), 25 deletions(-)

diff --git a/drivers/net/can/usb/ucan.c b/drivers/net/can/usb/ucan.c
index 39a63b7313a46..07406daf7c88e 100644
--- a/drivers/net/can/usb/ucan.c
+++ b/drivers/net/can/usb/ucan.c
@@ -186,7 +186,7 @@ union ucan_ctl_payload {
 	 */
 	struct ucan_ctl_cmd_get_protocol_version cmd_get_protocol_version;
 
-	u8 raw[128];
+	u8 fw_str[128];
 } __packed;
 
 enum {
@@ -424,18 +424,20 @@ static int ucan_ctrl_command_out(struct ucan_priv *up,
 			       UCAN_USB_CTL_PIPE_TIMEOUT);
 }
 
-static int ucan_device_request_in(struct ucan_priv *up,
-				  u8 cmd, u16 subcmd, u16 datalen)
+static void ucan_get_fw_str(struct ucan_priv *up, char *fw_str, size_t size)
 {
-	return usb_control_msg(up->udev,
-			       usb_rcvctrlpipe(up->udev, 0),
-			       cmd,
-			       USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE,
-			       subcmd,
-			       0,
-			       up->ctl_msg_buffer,
-			       datalen,
-			       UCAN_USB_CTL_PIPE_TIMEOUT);
+	int ret;
+
+	ret = usb_control_msg(up->udev, usb_rcvctrlpipe(up->udev, 0),
+			      UCAN_DEVICE_GET_FW_STRING,
+			      USB_DIR_IN | USB_TYPE_VENDOR |
+			      USB_RECIP_DEVICE,
+			      0, 0, fw_str, size - 1,
+			      UCAN_USB_CTL_PIPE_TIMEOUT);
+	if (ret > 0)
+		fw_str[ret] = '\0';
+	else
+		strscpy(fw_str, "unknown", size);
 }
 
 /* Parse the device information structure reported by the device and
@@ -1314,7 +1316,6 @@ static int ucan_probe(struct usb_interface *intf,
 	u8 in_ep_addr;
 	u8 out_ep_addr;
 	union ucan_ctl_payload *ctl_msg_buffer;
-	char firmware_str[sizeof(union ucan_ctl_payload) + 1];
 
 	udev = interface_to_usbdev(intf);
 
@@ -1527,17 +1528,6 @@ static int ucan_probe(struct usb_interface *intf,
 	 */
 	ucan_parse_device_info(up, &ctl_msg_buffer->cmd_get_device_info);
 
-	/* just print some device information - if available */
-	ret = ucan_device_request_in(up, UCAN_DEVICE_GET_FW_STRING, 0,
-				     sizeof(union ucan_ctl_payload));
-	if (ret > 0) {
-		/* copy string while ensuring zero termination */
-		strscpy(firmware_str, up->ctl_msg_buffer->raw,
-			sizeof(union ucan_ctl_payload) + 1);
-	} else {
-		strcpy(firmware_str, "unknown");
-	}
-
 	/* device is compatible, reset it */
 	ret = ucan_ctrl_command_out(up, UCAN_COMMAND_RESET, 0, 0);
 	if (ret < 0)
@@ -1555,7 +1545,10 @@ static int ucan_probe(struct usb_interface *intf,
 
 	/* initialisation complete, log device info */
 	netdev_info(up->netdev, "registered device\n");
-	netdev_info(up->netdev, "firmware string: %s\n", firmware_str);
+	ucan_get_fw_str(up, up->ctl_msg_buffer->fw_str,
+			sizeof(up->ctl_msg_buffer->fw_str));
+	netdev_info(up->netdev, "firmware string: %s\n",
+		    up->ctl_msg_buffer->fw_str);
 
 	/* success */
 	return 0;

From 80b5f90158d1364cbd80ad82852a757fc0692bf2 Mon Sep 17 00:00:00 2001
From: Oliver Hartkopp <socketcan@hartkopp.net>
Date: Mon, 10 Mar 2025 15:33:53 +0100
Subject: [PATCH 2124/2753] can: statistics: use atomic access in hot path

In can_send() and can_receive() CAN messages and CAN filter matches are
counted to be visible in the CAN procfs files.

KCSAN detected a data race within can_send() when two CAN frames have
been generated by a timer event writing to the same CAN netdevice at the
same time. Use atomic operations to access the statistics in the hot path
to fix the KCSAN complaint.

Reported-by: syzbot+78ce4489b812515d5e4d@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/67cd717d.050a0220.e1a89.0006.GAE@google.com
Signed-off-by: Oliver Hartkopp <socketcan@hartkopp.net>
Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20250310143353.3242-1-socketcan@hartkopp.net
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/af_can.c | 12 ++++++------
 net/can/af_can.h | 12 ++++++------
 net/can/proc.c   | 46 +++++++++++++++++++++++++++-------------------
 3 files changed, 39 insertions(+), 31 deletions(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 01f3fbb3b67dc..65230e81fa08c 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -287,8 +287,8 @@ int can_send(struct sk_buff *skb, int loop)
 		netif_rx(newskb);
 
 	/* update statistics */
-	pkg_stats->tx_frames++;
-	pkg_stats->tx_frames_delta++;
+	atomic_long_inc(&pkg_stats->tx_frames);
+	atomic_long_inc(&pkg_stats->tx_frames_delta);
 
 	return 0;
 
@@ -647,8 +647,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	int matches;
 
 	/* update statistics */
-	pkg_stats->rx_frames++;
-	pkg_stats->rx_frames_delta++;
+	atomic_long_inc(&pkg_stats->rx_frames);
+	atomic_long_inc(&pkg_stats->rx_frames_delta);
 
 	/* create non-zero unique skb identifier together with *skb */
 	while (!(can_skb_prv(skb)->skbcnt))
@@ -669,8 +669,8 @@ static void can_receive(struct sk_buff *skb, struct net_device *dev)
 	consume_skb(skb);
 
 	if (matches > 0) {
-		pkg_stats->matches++;
-		pkg_stats->matches_delta++;
+		atomic_long_inc(&pkg_stats->matches);
+		atomic_long_inc(&pkg_stats->matches_delta);
 	}
 }
 
diff --git a/net/can/af_can.h b/net/can/af_can.h
index 7c2d9161e2245..22f3352c77fec 100644
--- a/net/can/af_can.h
+++ b/net/can/af_can.h
@@ -66,9 +66,9 @@ struct receiver {
 struct can_pkg_stats {
 	unsigned long jiffies_init;
 
-	unsigned long rx_frames;
-	unsigned long tx_frames;
-	unsigned long matches;
+	atomic_long_t rx_frames;
+	atomic_long_t tx_frames;
+	atomic_long_t matches;
 
 	unsigned long total_rx_rate;
 	unsigned long total_tx_rate;
@@ -82,9 +82,9 @@ struct can_pkg_stats {
 	unsigned long max_tx_rate;
 	unsigned long max_rx_match_ratio;
 
-	unsigned long rx_frames_delta;
-	unsigned long tx_frames_delta;
-	unsigned long matches_delta;
+	atomic_long_t rx_frames_delta;
+	atomic_long_t tx_frames_delta;
+	atomic_long_t matches_delta;
 };
 
 /* persistent statistics */
diff --git a/net/can/proc.c b/net/can/proc.c
index bbce97825f13f..25fdf060e30d0 100644
--- a/net/can/proc.c
+++ b/net/can/proc.c
@@ -118,6 +118,13 @@ void can_stat_update(struct timer_list *t)
 	struct can_pkg_stats *pkg_stats = net->can.pkg_stats;
 	unsigned long j = jiffies; /* snapshot */
 
+	long rx_frames = atomic_long_read(&pkg_stats->rx_frames);
+	long tx_frames = atomic_long_read(&pkg_stats->tx_frames);
+	long matches = atomic_long_read(&pkg_stats->matches);
+	long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta);
+	long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta);
+	long matches_delta = atomic_long_read(&pkg_stats->matches_delta);
+
 	/* restart counting in timer context on user request */
 	if (user_reset)
 		can_init_stats(net);
@@ -127,35 +134,33 @@ void can_stat_update(struct timer_list *t)
 		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (pkg_stats->rx_frames > (ULONG_MAX / HZ))
+	if (rx_frames > (LONG_MAX / HZ))
 		can_init_stats(net);
 
 	/* prevent overflow in calc_rate() */
-	if (pkg_stats->tx_frames > (ULONG_MAX / HZ))
+	if (tx_frames > (LONG_MAX / HZ))
 		can_init_stats(net);
 
 	/* matches overflow - very improbable */
-	if (pkg_stats->matches > (ULONG_MAX / 100))
+	if (matches > (LONG_MAX / 100))
 		can_init_stats(net);
 
 	/* calc total values */
-	if (pkg_stats->rx_frames)
-		pkg_stats->total_rx_match_ratio = (pkg_stats->matches * 100) /
-			pkg_stats->rx_frames;
+	if (rx_frames)
+		pkg_stats->total_rx_match_ratio = (matches * 100) / rx_frames;
 
 	pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j,
-					    pkg_stats->tx_frames);
+					    tx_frames);
 	pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j,
-					    pkg_stats->rx_frames);
+					    rx_frames);
 
 	/* calc current values */
-	if (pkg_stats->rx_frames_delta)
+	if (rx_frames_delta)
 		pkg_stats->current_rx_match_ratio =
-			(pkg_stats->matches_delta * 100) /
-			pkg_stats->rx_frames_delta;
+			(matches_delta * 100) /	rx_frames_delta;
 
-	pkg_stats->current_tx_rate = calc_rate(0, HZ, pkg_stats->tx_frames_delta);
-	pkg_stats->current_rx_rate = calc_rate(0, HZ, pkg_stats->rx_frames_delta);
+	pkg_stats->current_tx_rate = calc_rate(0, HZ, tx_frames_delta);
+	pkg_stats->current_rx_rate = calc_rate(0, HZ, rx_frames_delta);
 
 	/* check / update maximum values */
 	if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate)
@@ -168,9 +173,9 @@ void can_stat_update(struct timer_list *t)
 		pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio;
 
 	/* clear values for 'current rate' calculation */
-	pkg_stats->tx_frames_delta = 0;
-	pkg_stats->rx_frames_delta = 0;
-	pkg_stats->matches_delta   = 0;
+	atomic_long_set(&pkg_stats->tx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->rx_frames_delta, 0);
+	atomic_long_set(&pkg_stats->matches_delta, 0);
 
 	/* restart timer (one second) */
 	mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ));
@@ -214,9 +219,12 @@ static int can_stats_proc_show(struct seq_file *m, void *v)
 	struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats;
 
 	seq_putc(m, '\n');
-	seq_printf(m, " %8ld transmitted frames (TXF)\n", pkg_stats->tx_frames);
-	seq_printf(m, " %8ld received frames (RXF)\n", pkg_stats->rx_frames);
-	seq_printf(m, " %8ld matched frames (RXMF)\n", pkg_stats->matches);
+	seq_printf(m, " %8ld transmitted frames (TXF)\n",
+		   atomic_long_read(&pkg_stats->tx_frames));
+	seq_printf(m, " %8ld received frames (RXF)\n",
+		   atomic_long_read(&pkg_stats->rx_frames));
+	seq_printf(m, " %8ld matched frames (RXMF)\n",
+		   atomic_long_read(&pkg_stats->matches));
 
 	seq_putc(m, '\n');
 

From 51f6fc9eb1d77ae5cacc796fc043dedc1f0f0073 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Fri, 7 Mar 2025 17:03:26 +0000
Subject: [PATCH 2125/2753] dt-bindings: can: renesas,rcar-canfd: Fix typo in
 pattern properties for R-Car V4M

The Renesas R-Car V4M(R8A779H0) SoC, supports up to four channels.
Fix the typo 5->4 in pattern properties.

Fixes: ced52c6ed257 ("dt-bindings: can: renesas,rcar-canfd: Document R-Car V4M support")
Cc: stable@vger.kernel.org
Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Acked-by: "Rob Herring (Arm)" <robh@kernel.org>
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Link: https://patch.msgid.link/20250307170330.173425-2-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 .../devicetree/bindings/net/can/renesas,rcar-canfd.yaml         | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
index 7c5ac5d2e880b..f6884f6e59e74 100644
--- a/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
+++ b/Documentation/devicetree/bindings/net/can/renesas,rcar-canfd.yaml
@@ -170,7 +170,7 @@ allOf:
             const: renesas,r8a779h0-canfd
     then:
       patternProperties:
-        "^channel[5-7]$": false
+        "^channel[4-7]$": false
     else:
       if:
         not:

From 1dba0a37644ed3022558165bbb5cb9bda540eaf7 Mon Sep 17 00:00:00 2001
From: Biju Das <biju.das.jz@bp.renesas.com>
Date: Fri, 7 Mar 2025 17:03:27 +0000
Subject: [PATCH 2126/2753] can: rcar_canfd: Fix page entries in the AFL list

There are a total of 96 AFL pages and each page has 16 entries with
registers CFDGAFLIDr, CFDGAFLMr, CFDGAFLP0r, CFDGAFLP1r holding
the rule entries (r = 0..15).

Currently, RCANFD_GAFL* macros use a start variable to find AFL entries,
which is incorrect as the testing on RZ/G3E shows ch1 and ch4
gets a start value of 0 and the register contents are overwritten.

Fix this issue by using rule_entry corresponding to the channel
to find the page entries in the AFL list.

Fixes: dd3bd23eb438 ("can: rcar_canfd: Add Renesas R-Car CAN FD driver")
Cc: stable@vger.kernel.org
Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com>
Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>
Link: https://patch.msgid.link/20250307170330.173425-3-biju.das.jz@bp.renesas.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/rcar/rcar_canfd.c | 28 +++++++++++-----------------
 1 file changed, 11 insertions(+), 17 deletions(-)

diff --git a/drivers/net/can/rcar/rcar_canfd.c b/drivers/net/can/rcar/rcar_canfd.c
index df1a5d0b37b22..aa3df0d05b853 100644
--- a/drivers/net/can/rcar/rcar_canfd.c
+++ b/drivers/net/can/rcar/rcar_canfd.c
@@ -787,22 +787,14 @@ static void rcar_canfd_configure_controller(struct rcar_canfd_global *gpriv)
 }
 
 static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
-					   u32 ch)
+					   u32 ch, u32 rule_entry)
 {
-	u32 cfg;
-	int offset, start, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	int offset, page, num_rules = RCANFD_CHANNEL_NUMRULES;
+	u32 rule_entry_index = rule_entry % 16;
 	u32 ridx = ch + RCANFD_RFFIFO_IDX;
 
-	if (ch == 0) {
-		start = 0; /* Channel 0 always starts from 0th rule */
-	} else {
-		/* Get number of Channel 0 rules and adjust */
-		cfg = rcar_canfd_read(gpriv->base, RCANFD_GAFLCFG(ch));
-		start = RCANFD_GAFLCFG_GETRNC(gpriv, 0, cfg);
-	}
-
 	/* Enable write access to entry */
-	page = RCANFD_GAFL_PAGENUM(start);
+	page = RCANFD_GAFL_PAGENUM(rule_entry);
 	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLECTR,
 			   (RCANFD_GAFLECTR_AFLPN(gpriv, page) |
 			    RCANFD_GAFLECTR_AFLDAE));
@@ -818,13 +810,13 @@ static void rcar_canfd_configure_afl_rules(struct rcar_canfd_global *gpriv,
 		offset = RCANFD_C_GAFL_OFFSET;
 
 	/* Accept all IDs */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLID(offset, rule_entry_index), 0);
 	/* IDE or RTR is not considered for matching */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLM(offset, rule_entry_index), 0);
 	/* Any data length accepted */
-	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, start), 0);
+	rcar_canfd_write(gpriv->base, RCANFD_GAFLP0(offset, rule_entry_index), 0);
 	/* Place the msg in corresponding Rx FIFO entry */
-	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, start),
+	rcar_canfd_set_bit(gpriv->base, RCANFD_GAFLP1(offset, rule_entry_index),
 			   RCANFD_GAFLP1_GAFLFDP(ridx));
 
 	/* Disable write access to page */
@@ -1851,6 +1843,7 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 	unsigned long channels_mask = 0;
 	int err, ch_irq, g_irq;
 	int g_err_irq, g_recc_irq;
+	u32 rule_entry = 0;
 	bool fdmode = true;			/* CAN FD only mode - default */
 	char name[9] = "channelX";
 	int i;
@@ -2023,7 +2016,8 @@ static int rcar_canfd_probe(struct platform_device *pdev)
 		rcar_canfd_configure_tx(gpriv, ch);
 
 		/* Configure receive rules */
-		rcar_canfd_configure_afl_rules(gpriv, ch);
+		rcar_canfd_configure_afl_rules(gpriv, ch, rule_entry);
+		rule_entry += RCANFD_CHANNEL_NUMRULES;
 	}
 
 	/* Configure common interrupts */

From 958ee3d715773d88e5d85c36311ef458d6b352a2 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Fri, 7 Mar 2025 14:08:15 -0500
Subject: [PATCH 2127/2753] dt-bindings: can: fsl,flexcan: add i.MX94 support

Add compatible string "fsl,imx94-flexcan" for the i.MX94 chip, which
is backward compatible with i.MX95. Set it to fall back to
"fsl,imx95-flexcan".

Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Frank Li <Frank.Li@nxp.com>
Link: https://patch.msgid.link/20250307190816.2971810-1-Frank.Li@nxp.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
index 37e3e4f487629..f81d56f7c12a5 100644
--- a/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
+++ b/Documentation/devicetree/bindings/net/can/fsl,flexcan.yaml
@@ -45,6 +45,10 @@ properties:
           - enum:
               - nxp,s32g3-flexcan
           - const: nxp,s32g2-flexcan
+      - items:
+          - enum:
+              - fsl,imx94-flexcan
+          - const: fsl,imx95-flexcan
 
   reg:
     maxItems: 1

From a1e36ec36356e33fd089761021e0de031ae3a06a Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Fri, 14 Mar 2025 09:35:51 +0100
Subject: [PATCH 2128/2753] selftests: drv-net: fix merge conflicts resolution

After the recent merge between net-next and net, I got some conflicts on
my side because the merge resolution was different from Stephen's one
[1] I applied on my side in the MPTCP tree.

It looks like the code that is now in net-next is using the old way to
retrieve the local and remote addresses. This patch is now using the new
way, like what was in Stephen's email [1].

Also, in get_interface_info(), there were no conflicts in this area,
because that was new code from 'net', but a small adaptation was needed
there as well to get the remote address.

Fixes: 941defcea7e1 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net")
Link: https://lore.kernel.org/20250311115758.17a1d414@canb.auug.org.au [1]
Suggested-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250314-net-next-drv-net-ping-fix-merge-v1-1-0d5c19daf707@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/ping.py | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 7a1026a073681..79f07e0510ecc 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -15,18 +15,18 @@
 def _test_v4(cfg) -> None:
     cfg.require_ipver("4")
 
-    cmd(f"ping -c 1 -W0.5 {cfg.remote_v4}")
-    cmd(f"ping -c 1 -W0.5 {cfg.v4}", host=cfg.remote)
-    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v4}")
-    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v4}", host=cfg.remote)
+    cmd("ping -c 1 -W0.5 " + cfg.remote_addr_v["4"])
+    cmd("ping -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["4"])
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["4"], host=cfg.remote)
 
 def _test_v6(cfg) -> None:
     cfg.require_ipver("6")
 
-    cmd(f"ping -c 1 -W5 {cfg.remote_v6}")
-    cmd(f"ping -c 1 -W5 {cfg.v6}", host=cfg.remote)
-    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.remote_v6}")
-    cmd(f"ping -s 65000 -c 1 -W0.5 {cfg.v6}", host=cfg.remote)
+    cmd("ping -c 1 -W5 " + cfg.remote_addr_v["6"])
+    cmd("ping -c 1 -W5 " + cfg.addr_v["6"], host=cfg.remote)
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.remote_addr_v["6"])
+    cmd("ping -s 65000 -c 1 -W0.5 " + cfg.addr_v["6"], host=cfg.remote)
 
 def _test_tcp(cfg) -> None:
     cfg.require_cmd("socat", remote=True)
@@ -120,7 +120,7 @@ def get_interface_info(cfg) -> None:
     global remote_ifname
     global no_sleep
 
-    remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_v4} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
+    remote_info = cmd(f"ip -4 -o addr show to {cfg.remote_addr_v['4']} | awk '{{print $2}}'", shell=True, host=cfg.remote).stdout
     remote_ifname = remote_info.rstrip('\n')
     if remote_ifname == "":
         raise KsftFailEx('Can not get remote interface')

From cb16dfed0093217a68c0faa9394fa5823927e04c Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Fri, 14 Mar 2025 12:03:33 +0100
Subject: [PATCH 2129/2753] efi/libstub: Avoid physical address 0x0 when doing
 random allocation

Ben reports spurious EFI zboot failures on a system where physical RAM
starts at 0x0. When doing random memory allocation from the EFI stub on
such a platform, a random seed of 0x0 (which means no entropy source is
available) will result in the allocation to be placed at address 0x0 if
sufficient space is available.

When this allocation is subsequently passed on to the decompression
code, the 0x0 address is mistaken for NULL and the code complains and
gives up.

So avoid address 0x0 when doing random allocation, and set the minimum
address to the minimum alignment.

Cc: <stable@vger.kernel.org>
Reported-by: Ben Schneider <ben@bens.haus>
Tested-by: Ben Schneider <ben@bens.haus>
Reviewed-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/libstub/randomalloc.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/firmware/efi/libstub/randomalloc.c b/drivers/firmware/efi/libstub/randomalloc.c
index 5a732018be36d..fd80b2f3233aa 100644
--- a/drivers/firmware/efi/libstub/randomalloc.c
+++ b/drivers/firmware/efi/libstub/randomalloc.c
@@ -75,6 +75,10 @@ efi_status_t efi_random_alloc(unsigned long size,
 	if (align < EFI_ALLOC_ALIGN)
 		align = EFI_ALLOC_ALIGN;
 
+	/* Avoid address 0x0, as it can be mistaken for NULL */
+	if (alloc_min == 0)
+		alloc_min = align;
+
 	size = round_up(size, EFI_ALLOC_ALIGN);
 
 	/* count the suitable slots in each memory map entry */

From fd99d6ed20234b83d65b9c5417794343577cf3e5 Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Fri, 14 Mar 2025 19:01:44 +0800
Subject: [PATCH 2130/2753] can: flexcan: only change CAN state when link up in
 system PM

After a suspend/resume cycle on a down interface, it will come up as
ERROR-ACTIVE.

$ ip -details -s -s a s dev flexcan0
3: flexcan0: <NOARP,ECHO> mtu 16 qdisc pfifo_fast state DOWN group default qlen 10
    link/can  promiscuity 0 allmulti 0 minmtu 0 maxmtu 0
    can state STOPPED (berr-counter tx 0 rx 0) restart-ms 1000

$ sudo systemctl suspend

$ ip -details -s -s a s dev flexcan0
3: flexcan0: <NOARP,ECHO> mtu 16 qdisc pfifo_fast state DOWN group default qlen 10
    link/can  promiscuity 0 allmulti 0 minmtu 0 maxmtu 0
    can state ERROR-ACTIVE (berr-counter tx 0 rx 0) restart-ms 1000

And only set CAN state to CAN_STATE_ERROR_ACTIVE when resume process
has no issue, otherwise keep in CAN_STATE_SLEEPING as suspend did.

Fixes: 4de349e786a3 ("can: flexcan: fix resume function")
Cc: stable@vger.kernel.org
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Link: https://patch.msgid.link/20250314110145.899179-1-haibo.chen@nxp.com
Reported-by: Marc Kleine-Budde <mkl@pengutronix.de>
Closes: https://lore.kernel.org/all/20250314-married-polar-elephant-b15594-mkl@pengutronix.de
[mkl: add newlines]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index ac1a860986df6..3a71fd2357222 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -2266,8 +2266,9 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 		}
 		netif_stop_queue(dev);
 		netif_device_detach(dev);
+
+		priv->can.state = CAN_STATE_SLEEPING;
 	}
-	priv->can.state = CAN_STATE_SLEEPING;
 
 	return 0;
 }
@@ -2278,7 +2279,6 @@ static int __maybe_unused flexcan_resume(struct device *device)
 	struct flexcan_priv *priv = netdev_priv(dev);
 	int err;
 
-	priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	if (netif_running(dev)) {
 		netif_device_attach(dev);
 		netif_start_queue(dev);
@@ -2298,6 +2298,8 @@ static int __maybe_unused flexcan_resume(struct device *device)
 
 			flexcan_chip_interrupts_enable(dev);
 		}
+
+		priv->can.state = CAN_STATE_ERROR_ACTIVE;
 	}
 
 	return 0;

From 5a19143124be42900b3fbc9ada3c919632eb45eb Mon Sep 17 00:00:00 2001
From: Haibo Chen <haibo.chen@nxp.com>
Date: Fri, 14 Mar 2025 19:01:45 +0800
Subject: [PATCH 2131/2753] can: flexcan: disable transceiver during system PM

During system PM, if no wakeup requirement, disable transceiver to
save power.

Fixes: 4de349e786a3 ("can: flexcan: fix resume function")
Cc: stable@vger.kernel.org
Reviewed-by: Frank Li <frank.li@nxp.com>
Signed-off-by: Haibo Chen <haibo.chen@nxp.com>
Link: https://patch.msgid.link/20250314110145.899179-2-haibo.chen@nxp.com
[mkl: add newlines]
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/flexcan/flexcan-core.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/drivers/net/can/flexcan/flexcan-core.c b/drivers/net/can/flexcan/flexcan-core.c
index 3a71fd2357222..b080740bcb104 100644
--- a/drivers/net/can/flexcan/flexcan-core.c
+++ b/drivers/net/can/flexcan/flexcan-core.c
@@ -2260,6 +2260,10 @@ static int __maybe_unused flexcan_suspend(struct device *device)
 
 			flexcan_chip_interrupts_disable(dev);
 
+			err = flexcan_transceiver_disable(priv);
+			if (err)
+				return err;
+
 			err = pinctrl_pm_select_sleep_state(device);
 			if (err)
 				return err;
@@ -2292,10 +2296,16 @@ static int __maybe_unused flexcan_resume(struct device *device)
 			if (err)
 				return err;
 
-			err = flexcan_chip_start(dev);
+			err = flexcan_transceiver_enable(priv);
 			if (err)
 				return err;
 
+			err = flexcan_chip_start(dev);
+			if (err) {
+				flexcan_transceiver_disable(priv);
+				return err;
+			}
+
 			flexcan_chip_interrupts_enable(dev);
 		}
 

From 6bffe88452dbe284747442f10a7ac8249d6495d7 Mon Sep 17 00:00:00 2001
From: Davide Caratti <dcaratti@redhat.com>
Date: Fri, 14 Mar 2025 12:39:49 +0100
Subject: [PATCH 2132/2753] can: add protocol counter for AF_CAN sockets

The third column in the output of the following command:

| # grep CAN /proc/net/protocols

is systematically '0': use sock_prot_inuse_add() to account for the number
of sockets for each protocol on top of AF_CAN family.

Signed-off-by: Davide Caratti <dcaratti@redhat.com>
Link: https://patch.msgid.link/9db5d0e6c11b232ad895885616f1258882a32f61.1741952160.git.dcaratti@redhat.com
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 net/can/af_can.c | 2 ++
 net/can/bcm.c    | 1 +
 net/can/isotp.c  | 1 +
 net/can/raw.c    | 5 ++++-
 4 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/can/af_can.c b/net/can/af_can.c
index 01f3fbb3b67dc..7b191dbe36930 100644
--- a/net/can/af_can.c
+++ b/net/can/af_can.c
@@ -172,6 +172,8 @@ static int can_create(struct net *net, struct socket *sock, int protocol,
 		sock_orphan(sk);
 		sock_put(sk);
 		sock->sk = NULL;
+	} else {
+		sock_prot_inuse_add(net, sk->sk_prot, 1);
 	}
 
  errout:
diff --git a/net/can/bcm.c b/net/can/bcm.c
index 217049fa496e9..6dc041e054ba1 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1625,6 +1625,7 @@ static int bcm_release(struct socket *sock)
 	sock->sk = NULL;
 
 	release_sock(sk);
+	sock_prot_inuse_add(net, sk->sk_prot, -1);
 	sock_put(sk);
 
 	return 0;
diff --git a/net/can/isotp.c b/net/can/isotp.c
index 16046931542a5..789583c62f980 100644
--- a/net/can/isotp.c
+++ b/net/can/isotp.c
@@ -1239,6 +1239,7 @@ static int isotp_release(struct socket *sock)
 	sock->sk = NULL;
 
 	release_sock(sk);
+	sock_prot_inuse_add(net, sk->sk_prot, -1);
 	sock_put(sk);
 
 	return 0;
diff --git a/net/can/raw.c b/net/can/raw.c
index 9b1d5f036f579..020f21430b1d8 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -397,11 +397,13 @@ static int raw_release(struct socket *sock)
 {
 	struct sock *sk = sock->sk;
 	struct raw_sock *ro;
+	struct net *net;
 
 	if (!sk)
 		return 0;
 
 	ro = raw_sk(sk);
+	net = sock_net(sk);
 
 	spin_lock(&raw_notifier_lock);
 	while (raw_busy_notifier == ro) {
@@ -421,7 +423,7 @@ static int raw_release(struct socket *sock)
 			raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk);
 			netdev_put(ro->dev, &ro->dev_tracker);
 		} else {
-			raw_disable_allfilters(sock_net(sk), NULL, sk);
+			raw_disable_allfilters(net, NULL, sk);
 		}
 	}
 
@@ -440,6 +442,7 @@ static int raw_release(struct socket *sock)
 	release_sock(sk);
 	rtnl_unlock();
 
+	sock_prot_inuse_add(net, sk->sk_prot, -1);
 	sock_put(sk);
 
 	return 0;

From 0b4ffbe4888a2c71185eaf5c1a02dd3586a9bc04 Mon Sep 17 00:00:00 2001
From: Tengda Wu <wutengda@huaweicloud.com>
Date: Fri, 14 Mar 2025 06:53:35 +0000
Subject: [PATCH 2133/2753] tracing: Correct the refcount if the
 hist/hist_debug file fails to open

The function event_{hist,hist_debug}_open() maintains the refcount of
'file->tr' and 'file' through tracing_open_file_tr(). However, it does
not roll back these counts on subsequent failure paths, resulting in a
refcount leak.

A very obvious case is that if the hist/hist_debug file belongs to a
specific instance, the refcount leak will prevent the deletion of that
instance, as it relies on the condition 'tr->ref == 1' within
__remove_instance().

Fix this by calling tracing_release_file_tr() on all failure paths in
event_{hist,hist_debug}_open() to correct the refcount.

Cc: stable@vger.kernel.org
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Zheng Yejian <zhengyejian1@huawei.com>
Link: https://lore.kernel.org/20250314065335.1202817-1-wutengda@huaweicloud.com
Fixes: 1cc111b9cddc ("tracing: Fix uaf issue when open the hist or hist_debug file")
Signed-off-by: Tengda Wu <wutengda@huaweicloud.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 kernel/trace/trace_events_hist.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index ad7419e240556..53dc6719181e5 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -5689,12 +5689,16 @@ static int event_hist_open(struct inode *inode, struct file *file)
 	guard(mutex)(&event_mutex);
 
 	event_file = event_file_data(file);
-	if (!event_file)
-		return -ENODEV;
+	if (!event_file) {
+		ret = -ENODEV;
+		goto err;
+	}
 
 	hist_file = kzalloc(sizeof(*hist_file), GFP_KERNEL);
-	if (!hist_file)
-		return -ENOMEM;
+	if (!hist_file) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
 	hist_file->file = file;
 	hist_file->last_act = get_hist_hit_count(event_file);
@@ -5702,9 +5706,14 @@ static int event_hist_open(struct inode *inode, struct file *file)
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
 	ret = single_open(file, hist_show, hist_file);
-	if (ret)
+	if (ret) {
 		kfree(hist_file);
+		goto err;
+	}
 
+	return 0;
+err:
+	tracing_release_file_tr(inode, file);
 	return ret;
 }
 
@@ -5979,7 +5988,10 @@ static int event_hist_debug_open(struct inode *inode, struct file *file)
 
 	/* Clear private_data to avoid warning in single_open() */
 	file->private_data = NULL;
-	return single_open(file, hist_debug_show, file);
+	ret = single_open(file, hist_debug_show, file);
+	if (ret)
+		tracing_release_file_tr(inode, file);
+	return ret;
 }
 
 const struct file_operations event_hist_debug_fops = {

From ca3ac4bf4dc307cea5781dccccf41c1d14c2f82f Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 3 Mar 2025 18:02:32 +0000
Subject: [PATCH 2134/2753] xfs: Use abs_diff instead of XFS_ABSDIFF

We have a central definition for this function since 2023, used by
a number of different parts of the kernel.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Carlos Maiolino <cmaiolino@redhat.com>
Reviewed-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: Carlos Maiolino <cem@kernel.org>
---
 fs/xfs/libxfs/xfs_alloc.c | 8 +++-----
 1 file changed, 3 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 3d33e17f2e5ce..7839efe050bfa 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -33,8 +33,6 @@ struct kmem_cache	*xfs_extfree_item_cache;
 
 struct workqueue_struct *xfs_alloc_wq;
 
-#define XFS_ABSDIFF(a,b)	(((a) <= (b)) ? ((b) - (a)) : ((a) - (b)))
-
 #define	XFSA_FIXUP_BNO_OK	1
 #define	XFSA_FIXUP_CNT_OK	2
 
@@ -410,8 +408,8 @@ xfs_alloc_compute_diff(
 		if (newbno1 != NULLAGBLOCK && newbno2 != NULLAGBLOCK) {
 			if (newlen1 < newlen2 ||
 			    (newlen1 == newlen2 &&
-			     XFS_ABSDIFF(newbno1, wantbno) >
-			     XFS_ABSDIFF(newbno2, wantbno)))
+			     abs_diff(newbno1, wantbno) >
+			     abs_diff(newbno2, wantbno)))
 				newbno1 = newbno2;
 		} else if (newbno2 != NULLAGBLOCK)
 			newbno1 = newbno2;
@@ -427,7 +425,7 @@ xfs_alloc_compute_diff(
 	} else
 		newbno1 = freeend - wantlen;
 	*newbnop = newbno1;
-	return newbno1 == NULLAGBLOCK ? 0 : XFS_ABSDIFF(newbno1, wantbno);
+	return newbno1 == NULLAGBLOCK ? 0 : abs_diff(newbno1, wantbno);
 }
 
 /*

From bfc6c67ec2d64d0ca4e5cc3e1ac84298a10b8d62 Mon Sep 17 00:00:00 2001
From: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Date: Tue, 4 Mar 2025 20:43:04 +0800
Subject: [PATCH 2135/2753] net/smc: use the correct ndev to find pnetid by
 pnetid table

When using smc_pnet in SMC, it will only search the pnetid in the
base_ndev of the netdev hierarchy(both HW PNETID and User-defined
sw pnetid). This may not work for some scenarios when using SMC in
container on cloud environment.
In container, there have choices of different container network,
such as directly using host network, virtual network IPVLAN, veth,
etc. Different choices of container network have different netdev
hierarchy. Examples of netdev hierarchy show below. (eth0 and eth1
in host below is the netdev directly related to the physical device).
            _______________________________
           |   _________________           |
           |  |POD              |          |
           |  |                 |          |
           |  | eth0_________   |          |
           |  |____|         |__|          |
           |       |         |             |
           |       |         |             |
           |   eth1|base_ndev| eth0_______ |
           |       |         |    | RDMA  ||
           | host  |_________|    |_______||
           ---------------------------------
     netdev hierarchy if directly using host network
           ________________________________
           |   _________________           |
           |  |POD  __________  |          |
           |  |    |upper_ndev| |          |
           |  |eth0|__________| |          |
           |  |_______|_________|          |
           |          |lower netdev        |
           |        __|______              |
           |   eth1|         | eth0_______ |
           |       |base_ndev|    | RDMA  ||
           | host  |_________|    |_______||
           ---------------------------------
            netdev hierarchy if using IPVLAN
            _______________________________
           |   _____________________       |
           |  |POD        _________ |      |
           |  |          |base_ndev||      |
           |  |eth0(veth)|_________||      |
           |  |____________|________|      |
           |               |pairs          |
           |        _______|_              |
           |       |         | eth0_______ |
           |   veth|base_ndev|    | RDMA  ||
           |       |_________|    |_______||
           |        _________              |
           |   eth1|base_ndev|             |
           | host  |_________|             |
           ---------------------------------
             netdev hierarchy if using veth
Due to some reasons, the eth1 in host is not RDMA attached netdevice,
pnetid is needed to map the eth1(in host) with RDMA device so that POD
can do SMC-R. Because the eth1(in host) is managed by CNI plugin(such
as Terway, network management plugin in container environment), and in
cloud environment the eth(in host) can dynamically be inserted by CNI
when POD create and dynamically be removed by CNI when POD destroy and
no POD related to the eth(in host) anymore. It is hard to config the
pnetid to the eth1(in host). But it is easy to config the pnetid to the
netdevice which can be seen in POD. When do SMC-R, both the container
directly using host network and the container using veth network can
successfully match the RDMA device, because the configured pnetid netdev
is a base_ndev. But the container using IPVLAN can not successfully
match the RDMA device and 0x03030000 fallback happens, because the
configured pnetid netdev is not a base_ndev. Additionally, if config
pnetid to the eth1(in host) also can not work for matching RDMA device
when using veth network and doing SMC-R in POD.

To resolve the problems list above, this patch extends to search user
-defined sw pnetid in the clc handshake ndev when no pnetid can be found
in the base_ndev, and the base_ndev take precedence over ndev for backward
compatibility. This patch also can unify the pnetid setup of different
network choices list above in container(Config user-defined sw pnetid in
the netdevice can be seen in POD).

Signed-off-by: Guangguan Wang <guangguan.wang@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-by: Halil Pasic <pasic@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/smc/smc_pnet.c | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c
index 716808f374a8d..b391c2ef463f2 100644
--- a/net/smc/smc_pnet.c
+++ b/net/smc/smc_pnet.c
@@ -1079,14 +1079,16 @@ static void smc_pnet_find_roce_by_pnetid(struct net_device *ndev,
 					 struct smc_init_info *ini)
 {
 	u8 ndev_pnetid[SMC_MAX_PNETID_LEN];
+	struct net_device *base_ndev;
 	struct net *net;
 
-	ndev = pnet_find_base_ndev(ndev);
+	base_ndev = pnet_find_base_ndev(ndev);
 	net = dev_net(ndev);
-	if (smc_pnetid_by_dev_port(ndev->dev.parent, ndev->dev_port,
+	if (smc_pnetid_by_dev_port(base_ndev->dev.parent, base_ndev->dev_port,
 				   ndev_pnetid) &&
+	    smc_pnet_find_ndev_pnetid_by_table(base_ndev, ndev_pnetid) &&
 	    smc_pnet_find_ndev_pnetid_by_table(ndev, ndev_pnetid)) {
-		smc_pnet_find_rdma_dev(ndev, ini);
+		smc_pnet_find_rdma_dev(base_ndev, ini);
 		return; /* pnetid could not be determined */
 	}
 	_smc_pnet_find_roce_by_pnetid(ndev_pnetid, ini, NULL, net);

From 03fc0a2dc9f8c292fad8a1bcfb6d1f0dec1824be Mon Sep 17 00:00:00 2001
From: Ike Panhc <ike.pan@canonical.com>
Date: Fri, 14 Mar 2025 12:57:32 +0800
Subject: [PATCH 2136/2753] MAINTAINERS: Update Ike Panhc's email address
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

I am no longer at Canonical and update with my personal email address.

Signed-off-by: Ike Panhc <ike.pan@canonical.com>
Link: https://lore.kernel.org/r/20250314045732.389973-1-ike.pan@canonical.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 .mailmap    | 1 +
 MAINTAINERS | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

diff --git a/.mailmap b/.mailmap
index ae0adc499f4ac..449c5e3a5d26b 100644
--- a/.mailmap
+++ b/.mailmap
@@ -281,6 +281,7 @@ Henrik Rydberg <rydberg@bitmath.org>
 Herbert Xu <herbert@gondor.apana.org.au>
 Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com>
 Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn>
+Ike Panhc <ikepanhc@gmail.com> <ike.pan@canonical.com>
 J. Bruce Fields <bfields@fieldses.org> <bfields@redhat.com>
 J. Bruce Fields <bfields@fieldses.org> <bfields@citi.umich.edu>
 Jacob Shin <Jacob.Shin@amd.com>
diff --git a/MAINTAINERS b/MAINTAINERS
index 896a307fa0654..bb4c069cc1e92 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11140,7 +11140,7 @@ S:	Maintained
 F:	drivers/i2c/busses/i2c-icy.c
 
 IDEAPAD LAPTOP EXTRAS DRIVER
-M:	Ike Panhc <ike.pan@canonical.com>
+M:	Ike Panhc <ikepanhc@gmail.com>
 L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 W:	http://launchpad.net/ideapad-laptop

From 90fd9ad5b0c981693c8512d9da01f14fb6596e9d Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 14 Mar 2025 09:54:43 -0400
Subject: [PATCH 2137/2753] bcachefs: Change btree wb assert to runtime error

We just had a report of the assert for "btree in write buffer for
non-write buffer btree" popping during the 6.14 upgrade.

- 150TB filesystem, after a reboot the upgrade was able to continue from
  where it left off, so no major damage.

But with 6.14 about to come out we want to get this tracked down asap,
and need more data if other users hit this.

Convert the BUG_ON() to an emergency read-only, and print out btree, the
key itself, and stack trace from the original write buffer update (which
did not have this check before).

Reported-by: Stijn Tintel <stijn@linux-ipv6.be>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/btree_update.h       |  8 ++++++++
 fs/bcachefs/btree_write_buffer.c | 21 ++++++++++++++++++++-
 2 files changed, 28 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/btree_update.h b/fs/bcachefs/btree_update.h
index 8f22ef9a7651a..47d8690f01bfc 100644
--- a/fs/bcachefs/btree_update.h
+++ b/fs/bcachefs/btree_update.h
@@ -126,10 +126,18 @@ bch2_trans_jset_entry_alloc(struct btree_trans *trans, unsigned u64s)
 
 int bch2_btree_insert_clone_trans(struct btree_trans *, enum btree_id, struct bkey_i *);
 
+int bch2_btree_write_buffer_insert_err(struct btree_trans *,
+				       enum btree_id, struct bkey_i *);
+
 static inline int __must_check bch2_trans_update_buffered(struct btree_trans *trans,
 					    enum btree_id btree,
 					    struct bkey_i *k)
 {
+	if (unlikely(!btree_type_uses_write_buffer(btree))) {
+		int ret = bch2_btree_write_buffer_insert_err(trans, btree, k);
+		dump_stack();
+		return ret;
+	}
 	/*
 	 * Most updates skip the btree write buffer until journal replay is
 	 * finished because synchronization with journal replay relies on having
diff --git a/fs/bcachefs/btree_write_buffer.c b/fs/bcachefs/btree_write_buffer.c
index b56c4987b8c97..2c09d19dd6210 100644
--- a/fs/bcachefs/btree_write_buffer.c
+++ b/fs/bcachefs/btree_write_buffer.c
@@ -264,6 +264,22 @@ static void move_keys_from_inc_to_flushing(struct btree_write_buffer *wb)
 	BUG_ON(wb->sorted.size < wb->flushing.keys.nr);
 }
 
+int bch2_btree_write_buffer_insert_err(struct btree_trans *trans,
+				       enum btree_id btree, struct bkey_i *k)
+{
+	struct bch_fs *c = trans->c;
+	struct printbuf buf = PRINTBUF;
+
+	prt_printf(&buf, "attempting to do write buffer update on non wb btree=");
+	bch2_btree_id_to_text(&buf, btree);
+	prt_str(&buf, "\n");
+	bch2_bkey_val_to_text(&buf, c, bkey_i_to_s_c(k));
+
+	bch2_fs_inconsistent(c, "%s", buf.buf);
+	printbuf_exit(&buf);
+	return -EROFS;
+}
+
 static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 {
 	struct bch_fs *c = trans->c;
@@ -312,7 +328,10 @@ static int bch2_btree_write_buffer_flush_locked(struct btree_trans *trans)
 	darray_for_each(wb->sorted, i) {
 		struct btree_write_buffered_key *k = &wb->flushing.keys.data[i->idx];
 
-		BUG_ON(!btree_type_uses_write_buffer(k->btree));
+		if (unlikely(!btree_type_uses_write_buffer(k->btree))) {
+			ret = bch2_btree_write_buffer_insert_err(trans, k->btree, &k->k);
+			goto err;
+		}
 
 		for (struct wb_key_ref *n = i + 1; n < min(i + 4, &darray_top(wb->sorted)); n++)
 			prefetch(&wb->flushing.keys.data[n->idx]);

From edcccc6892f65eff5fd3027a13976131dc7fd733 Mon Sep 17 00:00:00 2001
From: Roger Quadros <rogerq@kernel.org>
Date: Mon, 10 Mar 2025 15:15:14 +0100
Subject: [PATCH 2138/2753] memory: omap-gpmc: drop no compatible check

We are no longer depending on legacy device trees so
drop the no compatible check for NAND and OneNAND
nodes.

Suggested-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Roger Quadros <rogerq@kernel.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250114-omap-gpmc-drop-no-compatible-check-v1-1-262c8d549732@kernel.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/memory/omap-gpmc.c | 20 --------------------
 1 file changed, 20 deletions(-)

diff --git a/drivers/memory/omap-gpmc.c b/drivers/memory/omap-gpmc.c
index e2a75a52563f5..53f1888cc84f6 100644
--- a/drivers/memory/omap-gpmc.c
+++ b/drivers/memory/omap-gpmc.c
@@ -2226,26 +2226,6 @@ static int gpmc_probe_generic_child(struct platform_device *pdev,
 		goto err;
 	}
 
-	if (of_node_name_eq(child, "nand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible NAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
-	if (of_node_name_eq(child, "onenand")) {
-		/* Warn about older DT blobs with no compatible property */
-		if (!of_property_read_bool(child, "compatible")) {
-			dev_warn(&pdev->dev,
-				 "Incompatible OneNAND node: missing compatible");
-			ret = -EINVAL;
-			goto err;
-		}
-	}
-
 	if (of_match_node(omap_nand_ids, child)) {
 		/* NAND specific setup */
 		val = 8;

From 262666c04be6afa8f15b6c318596b54c37499cda Mon Sep 17 00:00:00 2001
From: Huisong Li <lihuisong@huawei.com>
Date: Fri, 14 Mar 2025 18:01:43 +0800
Subject: [PATCH 2139/2753] soc: hisilicon: kunpeng_hccs: Fix incorrect string
 assembly

String assembly should use sysfs_emit_at() instead of sysfs_emit().

Fixes: 23fe8112a231 ("soc: hisilicon: kunpeng_hccs: Add used HCCS types sysfs")
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Huisong Li <lihuisong@huawei.com>
Link: https://lore.kernel.org/r/20250314100143.3377268-1-lihuisong@huawei.com
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/soc/hisilicon/kunpeng_hccs.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/soc/hisilicon/kunpeng_hccs.c b/drivers/soc/hisilicon/kunpeng_hccs.c
index 8aa8dec14911c..444a8f59b7da7 100644
--- a/drivers/soc/hisilicon/kunpeng_hccs.c
+++ b/drivers/soc/hisilicon/kunpeng_hccs.c
@@ -1539,8 +1539,8 @@ static ssize_t used_types_show(struct kobject *kobj,
 	u16 i;
 
 	for (i = 0; i < hdev->used_type_num - 1; i++)
-		len += sysfs_emit(&buf[len], "%s ", hdev->type_name_maps[i].name);
-	len += sysfs_emit(&buf[len], "%s\n", hdev->type_name_maps[i].name);
+		len += sysfs_emit_at(buf, len, "%s ", hdev->type_name_maps[i].name);
+	len += sysfs_emit_at(buf, len, "%s\n", hdev->type_name_maps[i].name);
 
 	return len;
 }

From 45d5fe1c53baaed1fb3043f45d1e15ebb4bbe86a Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Mon, 1 Apr 2024 10:09:46 -0500
Subject: [PATCH 2140/2753] ARM: davinci: da850: fix selecting
 ARCH_DAVINCI_DA8XX

Chips in the DA850 family need to have ARCH_DAVINCI_DA8XX to be selected
in order to enable some peripheral drivers.

This was accidentally removed in a previous commit.

Fixes: dec85a95167a ("ARM: davinci: clean up platform support")
Signed-off-by: David Lechner <dlechner@baylibre.com>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mach-davinci/Kconfig | 1 +
 1 file changed, 1 insertion(+)

diff --git a/arch/arm/mach-davinci/Kconfig b/arch/arm/mach-davinci/Kconfig
index 2a8a9fe46586d..3fa15f3422409 100644
--- a/arch/arm/mach-davinci/Kconfig
+++ b/arch/arm/mach-davinci/Kconfig
@@ -27,6 +27,7 @@ config ARCH_DAVINCI_DA830
 
 config ARCH_DAVINCI_DA850
 	bool "DA850/OMAP-L138/AM18x based system"
+	select ARCH_DAVINCI_DA8XX
 	select DAVINCI_CP_INTC
 
 config ARCH_DAVINCI_DA8XX

From 0a8bb688aa824863716fc570d818b8659a79309d Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Mon, 10 Mar 2025 15:14:09 +0900
Subject: [PATCH 2141/2753] tracing: tprobe-events: Fix to clean up tprobe
 correctly when module unload

When unloading module, the tprobe events are not correctly cleaned
up. Thus it becomes `fprobe-event` and never be enabled again even
if loading the same module again.

For example;

 # cd /sys/kernel/tracing
 # modprobe trace_events_sample
 # echo 't:my_tprobe foo_bar' >> dynamic_events
 # cat dynamic_events
t:tracepoints/my_tprobe foo_bar
 # rmmod trace_events_sample
 # cat dynamic_events
f:tracepoints/my_tprobe foo_bar

As you can see, the second time my_tprobe starts with 'f' instead
of 't'.

This unregisters the fprobe and tracepoint callback when module is
unloaded but marks the fprobe-event is tprobe-event.

Link: https://lore.kernel.org/all/174158724946.189309.15826571379395619524.stgit@mhiramat.tok.corp.google.com/

Fixes: 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on future loaded modules")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 kernel/trace/trace_fprobe.c | 9 ++++++---
 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index e27305d31fc57..88a80953ae5ea 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -1008,10 +1008,13 @@ static int __tracepoint_probe_module_cb(struct notifier_block *self,
 					reenable_trace_fprobe(tf);
 			}
 		} else if (val == MODULE_STATE_GOING && tp_mod->mod == tf->mod) {
-			tracepoint_probe_unregister(tf->tpoint,
+			unregister_fprobe(&tf->fp);
+			if (trace_fprobe_is_tracepoint(tf)) {
+				tracepoint_probe_unregister(tf->tpoint,
 					tf->tpoint->probestub, NULL);
-			tf->tpoint = NULL;
-			tf->mod = NULL;
+				tf->tpoint = TRACEPOINT_STUB;
+				tf->mod = NULL;
+			}
 		}
 	}
 	mutex_unlock(&event_mutex);

From ac91052f0ae5be9e46211ba92cc31c0e3b0a933a Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Thu, 13 Mar 2025 10:00:10 +0900
Subject: [PATCH 2142/2753] tracing: tprobe-events: Fix leakage of module
 refcount

When enabling the tracepoint at loading module, the target module
refcount is incremented by find_tracepoint_in_module(). But it is
unnecessary because the module is not unloaded while processing
module loading callbacks.
Moreover, the refcount is not decremented in that function.
To be clear the module refcount handling, move the try_module_get()
callsite to trace_fprobe_create_internal(), where it is actually
required.

Link: https://lore.kernel.org/all/174182761071.83274.18334217580449925882.stgit@devnote2/

Fixes: 57a7e6de9e30 ("tracing/fprobe: Support raw tracepoints on future loaded modules")
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: stable@vger.kernel.org
---
 kernel/trace/trace_fprobe.c | 21 ++++++++-------------
 1 file changed, 8 insertions(+), 13 deletions(-)

diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 88a80953ae5ea..985ff98272da8 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -920,13 +920,8 @@ static void __find_tracepoint_module_cb(struct tracepoint *tp, struct module *mo
 
 	if (!data->tpoint && !strcmp(data->tp_name, tp->name)) {
 		data->tpoint = tp;
-		if (!data->mod) {
+		if (!data->mod)
 			data->mod = mod;
-			if (!try_module_get(data->mod)) {
-				data->tpoint = NULL;
-				data->mod = NULL;
-			}
-		}
 	}
 }
 
@@ -938,13 +933,7 @@ static void __find_tracepoint_cb(struct tracepoint *tp, void *priv)
 		data->tpoint = tp;
 }
 
-/*
- * Find a tracepoint from kernel and module. If the tracepoint is in a module,
- * this increments the module refcount to prevent unloading until the
- * trace_fprobe is registered to the list. After registering the trace_fprobe
- * on the trace_fprobe list, the module refcount is decremented because
- * tracepoint_probe_module_cb will handle it.
- */
+/* Find a tracepoint from kernel and module. */
 static struct tracepoint *find_tracepoint(const char *tp_name,
 					  struct module **tp_mod)
 {
@@ -973,6 +962,7 @@ static void reenable_trace_fprobe(struct trace_fprobe *tf)
 	}
 }
 
+/* Find a tracepoint from specified module. */
 static struct tracepoint *find_tracepoint_in_module(struct module *mod,
 						    const char *tp_name)
 {
@@ -1179,6 +1169,11 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	if (is_tracepoint) {
 		ctx->flags |= TPARG_FL_TPOINT;
 		tpoint = find_tracepoint(symbol, &tp_mod);
+		/* lock module until register this tprobe. */
+		if (tp_mod && !try_module_get(tp_mod)) {
+			tpoint = NULL;
+			tp_mod = NULL;
+		}
 		if (tpoint) {
 			ctx->funcname = kallsyms_lookup(
 				(unsigned long)tpoint->probestub,

From 1a2b74d0a2a46c219b25fdb0efcf9cd7f55cfe5e Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Fri, 14 Mar 2025 18:20:20 -0400
Subject: [PATCH 2143/2753] bcachefs: fix build on 32 bit in
 get_random_u64_below()

bare 64 bit divides not allowed, whoops

arm-linux-gnueabi-ld: drivers/char/random.o: in function `__get_random_u64_below':
drivers/char/random.c:602:(.text+0xc70): undefined reference to `__aeabi_uldivmod'

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
---
 fs/bcachefs/util.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/fs/bcachefs/util.c b/fs/bcachefs/util.c
index 8e3ab4bf79a90..da2cd11b3025d 100644
--- a/fs/bcachefs/util.c
+++ b/fs/bcachefs/util.c
@@ -663,7 +663,8 @@ u64 bch2_get_random_u64_below(u64 ceil)
 	u64 mult = ceil * rand;
 
 	if (unlikely(mult < ceil)) {
-		u64 bound = -ceil % ceil;
+		u64 bound;
+		div64_u64_rem(-ceil, ceil, &bound);
 		while (unlikely(mult < bound)) {
 			rand = get_random_u64();
 			mult = ceil * rand;

From 4701f33a10702d5fc577c32434eb62adde0a1ae1 Mon Sep 17 00:00:00 2001
From: Linus Torvalds <torvalds@linux-foundation.org>
Date: Sun, 16 Mar 2025 12:55:17 -1000
Subject: [PATCH 2144/2753] Linux 6.14-rc7

---
 Makefile | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Makefile b/Makefile
index 1d6a9ec8a2ace..50694bbbf828e 100644
--- a/Makefile
+++ b/Makefile
@@ -2,7 +2,7 @@
 VERSION = 6
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Baby Opossum Posse
 
 # *DOCUMENTATION*

From 654b33ada4ab5e926cd9c570196fefa7bec7c1df Mon Sep 17 00:00:00 2001
From: Ye Bin <yebin10@huawei.com>
Date: Sat, 1 Mar 2025 15:06:24 +0300
Subject: [PATCH 2145/2753] proc: fix UAF in proc_get_inode()

Fix race between rmmod and /proc/XXX's inode instantiation.

The bug is that pde->proc_ops don't belong to /proc, it belongs to a
module, therefore dereferencing it after /proc entry has been registered
is a bug unless use_pde/unuse_pde() pair has been used.

use_pde/unuse_pde can be avoided (2 atomic ops!) because pde->proc_ops
never changes so information necessary for inode instantiation can be
saved _before_ proc_register() in PDE itself and used later, avoiding
pde->proc_ops->...  dereference.

      rmmod                         lookup
sys_delete_module
                         proc_lookup_de
			   pde_get(de);
			   proc_get_inode(dir->i_sb, de);
  mod->exit()
    proc_remove
      remove_proc_subtree
       proc_entry_rundown(de);
  free_module(mod);

                               if (S_ISREG(inode->i_mode))
	                         if (de->proc_ops->proc_read_iter)
                           --> As module is already freed, will trigger UAF

BUG: unable to handle page fault for address: fffffbfff80a702b
PGD 817fc4067 P4D 817fc4067 PUD 817fc0067 PMD 102ef4067 PTE 0
Oops: Oops: 0000 [#1] PREEMPT SMP KASAN PTI
CPU: 26 UID: 0 PID: 2667 Comm: ls Tainted: G
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996)
RIP: 0010:proc_get_inode+0x302/0x6e0
RSP: 0018:ffff88811c837998 EFLAGS: 00010a06
RAX: dffffc0000000000 RBX: ffffffffc0538140 RCX: 0000000000000007
RDX: 1ffffffff80a702b RSI: 0000000000000001 RDI: ffffffffc0538158
RBP: ffff8881299a6000 R08: 0000000067bbe1e5 R09: 1ffff11023906f20
R10: ffffffffb560ca07 R11: ffffffffb2b43a58 R12: ffff888105bb78f0
R13: ffff888100518048 R14: ffff8881299a6004 R15: 0000000000000001
FS:  00007f95b9686840(0000) GS:ffff8883af100000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: fffffbfff80a702b CR3: 0000000117dd2000 CR4: 00000000000006f0
DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
Call Trace:
 <TASK>
 proc_lookup_de+0x11f/0x2e0
 __lookup_slow+0x188/0x350
 walk_component+0x2ab/0x4f0
 path_lookupat+0x120/0x660
 filename_lookup+0x1ce/0x560
 vfs_statx+0xac/0x150
 __do_sys_newstat+0x96/0x110
 do_syscall_64+0x5f/0x170
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

[adobriyan@gmail.com: don't do 2 atomic ops on the common path]
Link: https://lkml.kernel.org/r/3d25ded0-1739-447e-812b-e34da7990dcf@p183
Fixes: 778f3dd5a13c ("Fix procfs compat_ioctl regression")
Signed-off-by: Ye Bin <yebin10@huawei.com>
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: David S. Miller <davem@davemloft.net>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/generic.c       | 10 +++++++++-
 fs/proc/inode.c         |  6 +++---
 fs/proc/internal.h      | 14 ++++++++++++++
 include/linux/proc_fs.h |  7 +++++--
 4 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 8ec90826a49e9..a3e22803cddf2 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -559,10 +559,16 @@ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode,
 	return p;
 }
 
-static inline void pde_set_flags(struct proc_dir_entry *pde)
+static void pde_set_flags(struct proc_dir_entry *pde)
 {
 	if (pde->proc_ops->proc_flags & PROC_ENTRY_PERMANENT)
 		pde->flags |= PROC_ENTRY_PERMANENT;
+	if (pde->proc_ops->proc_read_iter)
+		pde->flags |= PROC_ENTRY_proc_read_iter;
+#ifdef CONFIG_COMPAT
+	if (pde->proc_ops->proc_compat_ioctl)
+		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
+#endif
 }
 
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
@@ -626,6 +632,7 @@ struct proc_dir_entry *proc_create_seq_private(const char *name, umode_t mode,
 	p->proc_ops = &proc_seq_ops;
 	p->seq_ops = ops;
 	p->state_size = state_size;
+	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_seq_private);
@@ -656,6 +663,7 @@ struct proc_dir_entry *proc_create_single_data(const char *name, umode_t mode,
 		return NULL;
 	p->proc_ops = &proc_single_ops;
 	p->single_show = show;
+	pde_set_flags(p);
 	return proc_register(parent, p);
 }
 EXPORT_SYMBOL(proc_create_single_data);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 626ad7bd94f24..a3eb3b740f766 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -656,13 +656,13 @@ struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 
 	if (S_ISREG(inode->i_mode)) {
 		inode->i_op = de->proc_iops;
-		if (de->proc_ops->proc_read_iter)
+		if (pde_has_proc_read_iter(de))
 			inode->i_fop = &proc_iter_file_ops;
 		else
 			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-		if (de->proc_ops->proc_compat_ioctl) {
-			if (de->proc_ops->proc_read_iter)
+		if (pde_has_proc_compat_ioctl(de)) {
+			if (pde_has_proc_read_iter(de))
 				inode->i_fop = &proc_iter_file_ops_compat;
 			else
 				inode->i_fop = &proc_reg_file_ops_compat;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 1695509370b88..77a517f91821a 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -85,6 +85,20 @@ static inline void pde_make_permanent(struct proc_dir_entry *pde)
 	pde->flags |= PROC_ENTRY_PERMANENT;
 }
 
+static inline bool pde_has_proc_read_iter(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_read_iter;
+}
+
+static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
+{
+#ifdef CONFIG_COMPAT
+	return pde->flags & PROC_ENTRY_proc_compat_ioctl;
+#else
+	return false;
+#endif
+}
+
 extern struct kmem_cache *proc_dir_entry_cache;
 void pde_free(struct proc_dir_entry *pde);
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index 0b2a898544409..ea62201c74c40 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -20,10 +20,13 @@ enum {
 	 * If in doubt, ignore this flag.
 	 */
 #ifdef MODULE
-	PROC_ENTRY_PERMANENT = 0U,
+	PROC_ENTRY_PERMANENT		= 0U,
 #else
-	PROC_ENTRY_PERMANENT = 1U << 0,
+	PROC_ENTRY_PERMANENT		= 1U << 0,
 #endif
+
+	PROC_ENTRY_proc_read_iter	= 1U << 1,
+	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
 };
 
 struct proc_ops {

From 665575cff098b696995ddaddf4646a4099941f5e Mon Sep 17 00:00:00 2001
From: Dave Hansen <dave.hansen@linux.intel.com>
Date: Fri, 28 Feb 2025 12:37:22 -0800
Subject: [PATCH 2146/2753] filemap: move prefaulting out of hot write path

There is a generic anti-pattern that shows up in the VFS and several
filesystems where the hot write paths touch userspace twice when they
could get away with doing it once.

Dave Chinner suggested that they should all be fixed up[1].  I agree[2].
But, the series to do that fixup spans a bunch of filesystems and a lot of
people.  This patch fixes common code that absolutely everyone uses.  It
has measurable performance benefits[3].

I think this patch can go in and not be held up by the others.

I will post them separately to their separate maintainers for
consideration. But, honestly, I'm not going to lose any sleep if
the maintainers don't pick those up.

1. https://lore.kernel.org/all/Z5f-x278Z3wTIugL@dread.disaster.area/
2. https://lore.kernel.org/all/20250129181749.C229F6F3@davehans-spike.ostc.intel.com/
3. https://lore.kernel.org/all/202502121529.d62a409e-lkp@intel.com/


This patch:

There is a bit of a sordid history here. I originally wrote
998ef75ddb57 ("fs: do not prefault sys_write() user buffer pages")
to fix a performance issue that showed up on early SMAP hardware.
But that was reverted with 00a3d660cbac because it exposed an
underlying filesystem bug.

This is a reimplementation of the original commit along with some
simplification and comment improvements.

The basic problem is that the generic write path has two userspace
accesses: one to prefault the write source buffer and then another to
perform the actual write. On x86, this means an extra STAC/CLAC pair.
These are relatively expensive instructions because they function as
barriers.

Keep the prefaulting behavior but move it into the slow path that gets
run when the write did not make any progress. This avoids livelocks
that can happen when the write's source and destination target the
same folio. Contrary to the existing comments, the fault-in does not
prevent deadlocks. That's accomplished by using an "atomic" usercopy
that disables page faults.

The end result is that the generic write fast path now touches
userspace once instead of twice.

0day has shown some improvements on a couple of microbenchmarks:

	https://lore.kernel.org/all/202502121529.d62a409e-lkp@intel.com/

Link: https://lkml.kernel.org/r/20250228203722.CAEB63AC@davehans-spike.ostc.intel.com
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Link: https://lore.kernel.org/all/yxyuijjfd6yknryji2q64j3keq2ygw6ca6fs5jwyolklzvo45s@4u63qqqyosy2/
Cc: Ted Ts'o <tytso@mit.edu>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mateusz Guzik <mjguzik@gmail.com>
Cc: Dave Chinner <david@fromorbit.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/filemap.c | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index 2974691fdfad2..fbaf0e4fc8e1c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -4169,17 +4169,6 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 		bytes = min(chunk - offset, bytes);
 		balance_dirty_pages_ratelimited(mapping);
 
-		/*
-		 * Bring in the user page that we will copy from _first_.
-		 * Otherwise there's a nasty deadlock on copying from the
-		 * same page as we're writing to, without it being marked
-		 * up-to-date.
-		 */
-		if (unlikely(fault_in_iov_iter_readable(i, bytes) == bytes)) {
-			status = -EFAULT;
-			break;
-		}
-
 		if (fatal_signal_pending(current)) {
 			status = -EINTR;
 			break;
@@ -4197,6 +4186,12 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 		if (mapping_writably_mapped(mapping))
 			flush_dcache_folio(folio);
 
+		/*
+		 * Faults here on mmap()s can recurse into arbitrary
+		 * filesystem code. Lots of locks are held that can
+		 * deadlock. Use an atomic copy to avoid deadlocking
+		 * in page fault handling.
+		 */
 		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
 		flush_dcache_folio(folio);
 
@@ -4222,6 +4217,16 @@ ssize_t generic_perform_write(struct kiocb *iocb, struct iov_iter *i)
 				bytes = copied;
 				goto retry;
 			}
+
+			/*
+			 * 'folio' is now unlocked and faults on it can be
+			 * handled. Ensure forward progress by trying to
+			 * fault it in now.
+			 */
+			if (fault_in_iov_iter_readable(i, bytes) == bytes) {
+				status = -EFAULT;
+				break;
+			}
 		} else {
 			pos += status;
 			written += status;

From 39a326e6daba5703a8e4de17cacc7ddb0dc5b07f Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 28 Feb 2025 09:53:36 -0800
Subject: [PATCH 2147/2753] mm/damon: respect core layer filters' allowance
 decision on ops layer

Filtering decisions are made in filters evaluation order.  Once a decision
is made by a filter, filters that scheduled to be evaluated after the
decision-made filter should just respect it.  This is the intended and
documented behavior.  Since core layer-handled filters are evaluated
before operations layer-handled filters, decisions made on core layer
should respected by ops layer.

In case of reject filters, the decision is respected, since core
layer-rejected regions are not passed to ops layer.  But in case of allow
filters, ops layer filters don't know if the region has passed to them
because it was allowed by core filters or just because it didn't match to
any core layer.  The current wrong implementation assumes it was due to
not matched by any core filters.  As a reuslt, the decision is not
respected.  Pass the missing information to ops layer using a new filed in
'struct damos', and make the ops layer filters respect it.

Link: https://lkml.kernel.org/r/20250228175336.42781-1-sj@kernel.org
Fixes: 491fee286e56 ("mm/damon/core: support damos_filter->allow")
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 5 +++++
 mm/damon/core.c       | 6 +++++-
 mm/damon/paddr.c      | 3 +++
 3 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/include/linux/damon.h b/include/linux/damon.h
index af525252b853a..c9074d569596a 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -470,6 +470,11 @@ struct damos {
 	unsigned long next_apply_sis;
 	/* informs if ongoing DAMOS walk for this scheme is finished */
 	bool walk_completed;
+	/*
+	 * If the current region in the filtering stage is allowed by core
+	 * layer-handled filters.  If true, operations layer allows it, too.
+	 */
+	bool core_filters_allowed;
 /* public: */
 	struct damos_quota quota;
 	struct damos_watermarks wmarks;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index c7b9813088626..de4396519b83b 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1429,9 +1429,13 @@ static bool damos_filter_out(struct damon_ctx *ctx, struct damon_target *t,
 {
 	struct damos_filter *filter;
 
+	s->core_filters_allowed = false;
 	damos_for_each_filter(filter, s) {
-		if (damos_filter_match(ctx, t, r, filter))
+		if (damos_filter_match(ctx, t, r, filter)) {
+			if (filter->allow)
+				s->core_filters_allowed = true;
 			return !filter->allow;
+		}
 	}
 	return false;
 }
diff --git a/mm/damon/paddr.c b/mm/damon/paddr.c
index 0f9ae14f884dd..c834aa2178352 100644
--- a/mm/damon/paddr.c
+++ b/mm/damon/paddr.c
@@ -236,6 +236,9 @@ static bool damos_pa_filter_out(struct damos *scheme, struct folio *folio)
 {
 	struct damos_filter *filter;
 
+	if (scheme->core_filters_allowed)
+		return false;
+
 	damos_for_each_filter(filter, scheme) {
 		if (damos_pa_filter_match(filter, folio))
 			return !filter->allow;

From 73d7a69de212aebb59f4ff23aae0422e86c488fe Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Fri, 28 Feb 2025 09:44:50 -0800
Subject: [PATCH 2148/2753] mm/damon/core: initialize damos->walk_completed in
 damon_new_scheme()

The function for allocating and initialize a 'struct damos' object,
damon_new_scheme(), is not initializing damos->walk_completed field.  Only
damos_walk_complete() is setting the field.  Hence the field will be
eventually set and used correctly from second damos_walk() call for the
scheme.  But the first damos_walk() could mistakenly not walk on the
regions.  Actually, a common usage of DAMOS for taking an access pattern
snapshot is installing a monitoring-purpose DAMOS scheme, doing
damos_walk() to retrieve the snapshot, and then removing the scheme.
DAMON user-space tool (damo) also gets runtime snapshot in the way.  Hence
the problem can continuously happen in such use cases.  Initialize it
properly in the allocation function.

Link: https://lkml.kernel.org/r/20250228174450.41472-1-sj@kernel.org
Fixes: bf0eaba0ff9c ("mm/damon/core: implement damos_walk()")
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/damon/core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/mm/damon/core.c b/mm/damon/core.c
index de4396519b83b..384935ef4e65e 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -373,6 +373,7 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern,
 	 * or damon_attrs are updated.
 	 */
 	scheme->next_apply_sis = 0;
+	scheme->walk_completed = false;
 	INIT_LIST_HEAD(&scheme->filters);
 	scheme->stat = (struct damos_stat){};
 	INIT_LIST_HEAD(&scheme->list);

From cb402bbdabcaa5a765068c5b8673bbfc1c264242 Mon Sep 17 00:00:00 2001
From: Jinjiang Tu <tujinjiang@huawei.com>
Date: Tue, 4 Mar 2025 21:21:06 +0800
Subject: [PATCH 2149/2753] mm/hugetlb: fix surplus pages in
 dissolve_free_huge_page()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

In dissolve_free_huge_page(), free huge pages are dissolved without
adjusting surplus count. However, free huge pages may be accounted as
surplus pages, and will lead to wrong surplus count.

I reproduce this issue on qemu. The steps are:
1) Node1 is memory-less at first. Hot-add memory to node1 by executing
the two commands in qemu monitor:
  object_add memory-backend-ram,id=mem1,size=1G
  device_add pc-dimm,id=dimm1,memdev=mem1,node=1
2) online one memory block of Node1 with：
  echo online_movable > /sys/devices/system/node/node1/memoryX/state
3) create 64 huge pages for node1
4) run a program to reserve (don't consume) all the huge pages
5) echo 0 > nr_huge_pages for node1. After this step, free huge pages in
Node1 are surplus.
6) create 80 huge pages for node0
7) offline memory of node1, The memory range to offline contains the free
surplus huge pages created in step3) ~ step5)
  echo offline > /sys/devices/system/node/node1/memoryX/state
8) kill the program in step 4)

The result:
           Node0     Node1
total       80        0
free        80        0
surplus     0         61

To fix it, adjust surplus when destroying huge pages if the node has
surplus pages in dissolve_free_hugetlb_folio().

The result with this patch:
           Node0     Node1
total       80        0
free        80        0
surplus     0         0

Link: https://lkml.kernel.org/r/20250304132106.2872754-1-tujinjiang@huawei.com
Fixes: c8721bbbdd36 ("mm: memory-hotplug: enable memory hotplug to handle hugepage")
Signed-off-by: Jinjiang Tu <tujinjiang@huawei.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: Jinjiang Tu <tujinjiang@huawei.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Nanyong Sun <sunnanyong@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/hugetlb.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 97930d44d460e..318624c965844 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2135,6 +2135,8 @@ int dissolve_free_hugetlb_folio(struct folio *folio)
 
 	if (!folio_ref_count(folio)) {
 		struct hstate *h = folio_hstate(folio);
+		bool adjust_surplus = false;
+
 		if (!available_huge_pages(h))
 			goto out;
 
@@ -2157,7 +2159,9 @@ int dissolve_free_hugetlb_folio(struct folio *folio)
 			goto retry;
 		}
 
-		remove_hugetlb_folio(h, folio, false);
+		if (h->surplus_huge_pages_node[folio_nid(folio)])
+			adjust_surplus = true;
+		remove_hugetlb_folio(h, folio, adjust_surplus);
 		h->max_huge_pages--;
 		spin_unlock_irq(&hugetlb_lock);
 
@@ -2177,7 +2181,7 @@ int dissolve_free_hugetlb_folio(struct folio *folio)
 			rc = hugetlb_vmemmap_restore_folio(h, folio);
 			if (rc) {
 				spin_lock_irq(&hugetlb_lock);
-				add_hugetlb_folio(h, folio, false);
+				add_hugetlb_folio(h, folio, adjust_surplus);
 				h->max_huge_pages++;
 				goto out;
 			}

From 60cf233b585cdf1f3c5e52d1225606b86acd08b0 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Wed, 5 Mar 2025 15:04:03 -0500
Subject: [PATCH 2150/2753] mm/migrate: fix shmem xarray update during
 migration

A shmem folio can be either in page cache or in swap cache, but not at the
same time.  Namely, once it is in swap cache, folio->mapping should be
NULL, and the folio is no longer in a shmem mapping.

In __folio_migrate_mapping(), to determine the number of xarray entries to
update, folio_test_swapbacked() is used, but that conflates shmem in page
cache case and shmem in swap cache case.  It leads to xarray multi-index
entry corruption, since it turns a sibling entry to a normal entry during
xas_store() (see [1] for a userspace reproduction).  Fix it by only using
folio_test_swapcache() to determine whether xarray is storing swap cache
entries or not to choose the right number of xarray entries to update.

[1] https://lore.kernel.org/linux-mm/Z8idPCkaJW1IChjT@casper.infradead.org/

Note:
In __split_huge_page(), folio_test_anon() && folio_test_swapcache() is
used to get swap_cache address space, but that ignores the shmem folio in
swap cache case.  It could lead to NULL pointer dereferencing when a
in-swap-cache shmem folio is split at __xa_store(), since
!folio_test_anon() is true and folio->mapping is NULL.  But fortunately,
its caller split_huge_page_to_list_to_order() bails out early with EBUSY
when folio->mapping is NULL.  So no need to take care of it here.

Link: https://lkml.kernel.org/r/20250305200403.2822855-1-ziy@nvidia.com
Fixes: fc346d0a70a1 ("mm: migrate high-order folios in swap cache correctly")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Liu Shixin <liushixin2@huawei.com>
Closes: https://lore.kernel.org/all/28546fb4-5210-bf75-16d6-43e1f8646080@huawei.com/
Suggested-by: Hugh Dickins <hughd@google.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: Charan Teja Kalla <quic_charante@quicinc.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/migrate.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/mm/migrate.c b/mm/migrate.c
index fb19a18892c89..97f0edf0c0325 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -518,15 +518,13 @@ static int __folio_migrate_mapping(struct address_space *mapping,
 	if (folio_test_anon(folio) && folio_test_large(folio))
 		mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON, 1);
 	folio_ref_add(newfolio, nr); /* add cache reference */
-	if (folio_test_swapbacked(folio)) {
+	if (folio_test_swapbacked(folio))
 		__folio_set_swapbacked(newfolio);
-		if (folio_test_swapcache(folio)) {
-			folio_set_swapcache(newfolio);
-			newfolio->private = folio_get_private(folio);
-		}
+	if (folio_test_swapcache(folio)) {
+		folio_set_swapcache(newfolio);
+		newfolio->private = folio_get_private(folio);
 		entries = nr;
 	} else {
-		VM_BUG_ON_FOLIO(folio_test_swapcache(folio), folio);
 		entries = 1;
 	}
 

From d7147a33570ce07965d76e4491c7c9d8d38006f4 Mon Sep 17 00:00:00 2001
From: Zhiyu Zhang <zhiyuzhang999@gmail.com>
Date: Thu, 6 Mar 2025 21:28:55 +0800
Subject: [PATCH 2151/2753] squashfs: fix invalid pointer dereference in
 squashfs_cache_delete

When mounting a squashfs fails, squashfs_cache_init() may return an error
pointer (e.g., -ENOMEM) instead of NULL.  However, squashfs_cache_delete()
only checks for a NULL cache, and attempts to dereference the invalid
pointer.  This leads to a kernel crash (BUG: unable to handle kernel
paging request in squashfs_cache_delete).

This patch fixes the issue by checking IS_ERR(cache) before accessing it.

Link: https://lkml.kernel.org/r/20250306132855.2030-1-zhiyuzhang999@gmail.com
Fixes: 49ff29240ebb ("squashfs: make squashfs_cache_init() return ERR_PTR(-ENOMEM)")
Signed-off-by: Zhiyu Zhang <zhiyuzhang999@gmail.com>
Reported-by: Zhiyu Zhang <zhiyuzhang999@gmail.com>
Closes: https://lore.kernel.org/linux-fsdevel/CALf2hKvaq8B4u5yfrE+BYt7aNguao99mfWxHngA+=o5hwzjdOg@mail.gmail.com/
Tested-by: Zhiyu Zhang <zhiyuzhang999@gmail.com>
Reviewed-by: Phillip Lougher <phillip@squashfs.org.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/squashfs/cache.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/squashfs/cache.c b/fs/squashfs/cache.c
index 4db0d2b0aab8f..181260e72680c 100644
--- a/fs/squashfs/cache.c
+++ b/fs/squashfs/cache.c
@@ -198,7 +198,7 @@ void squashfs_cache_delete(struct squashfs_cache *cache)
 {
 	int i, j;
 
-	if (cache == NULL)
+	if (IS_ERR(cache) || cache == NULL)
 		return;
 
 	for (i = 0; i < cache->entries; i++) {

From 8c6ff7f181786d0b296bb0f1bf269ca8770632c9 Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Thu, 6 Mar 2025 12:00:37 +0530
Subject: [PATCH 2152/2753] mm/vma: do not register private-anon mappings with
 khugepaged during mmap

We already are registering private-anon VMAs with khugepaged during fault
time, in do_huge_pmd_anonymous_page().  Commit "register suitable readonly
file vmas for khugepaged" moved the khugepaged registration logic from
shmem_mmap to the generic mmap path.

The userspace-visible effect should be this: khugepaged will unnecessarily
scan mm's which haven't yet faulted in.  Note that it won't actually
collapse because all PTEs are none.

Now that I think about it, the mm is going to have a file VMA anyways
during fork+exec, so the mm already gets registered during mmap due to the
non-anon case (I *think*), so at least one of either the mmap registration
or fault-time registration is redundant.

Make this logic specific for non-anon mappings.

Link: https://lkml.kernel.org/r/20250306063037.16299-1-dev.jain@arm.com
Fixes: 613bec092fe7 ("mm: mmap: register suitable readonly file vmas for khugepaged")
Signed-off-by: Dev Jain <dev.jain@arm.com>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@kernel.org>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/vma.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/mm/vma.c b/mm/vma.c
index 96bcb372c90e4..71ca012c616c9 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2381,7 +2381,8 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 	 * vma_merge_new_range() calls khugepaged_enter_vma() too, the below
 	 * call covers the non-merge case.
 	 */
-	khugepaged_enter_vma(vma, map->flags);
+	if (!vma_is_anonymous(vma))
+		khugepaged_enter_vma(vma, map->flags);
 	ksm_add_vma(vma);
 	*vmap = vma;
 	return 0;

From 73f839b6d2ed75f281bd75aeb68e81bce373bdee Mon Sep 17 00:00:00 2001
From: Muchun Song <songmuchun@bytedance.com>
Date: Thu, 6 Mar 2025 10:31:33 +0800
Subject: [PATCH 2153/2753] mm: memcontrol: fix swap counter leak from offline
 cgroup

Commit 6769183166b3 removed the parameter of id from swap_cgroup_record()
and get the memcg id from mem_cgroup_id(folio_memcg(folio)).  However, the
caller of it may update a different memcg's counter instead of
folio_memcg(folio).

E.g.  in the caller of mem_cgroup_swapout(), @swap_memcg could be
different with @memcg and update the counter of @swap_memcg, but
swap_cgroup_record() records the wrong memcg's ID.  When it is uncharged
from __mem_cgroup_uncharge_swap(), the swap counter will leak since the
wrong recorded ID.

Fix it by bringing the parameter of id back.

Link: https://lkml.kernel.org/r/20250306023133.44838-1-songmuchun@bytedance.com
Fixes: 6769183166b3 ("mm/swap_cgroup: decouple swap cgroup recording and clearing")
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Kairui Song <kasong@tencent.com>
Cc: Chris Li <chrisl@kernel.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap_cgroup.h | 4 ++--
 mm/memcontrol.c             | 4 ++--
 mm/swap_cgroup.c            | 7 ++++---
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/include/linux/swap_cgroup.h b/include/linux/swap_cgroup.h
index b5ec038069dab..91cdf12190a03 100644
--- a/include/linux/swap_cgroup.h
+++ b/include/linux/swap_cgroup.h
@@ -6,7 +6,7 @@
 
 #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP)
 
-extern void swap_cgroup_record(struct folio *folio, swp_entry_t ent);
+extern void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent);
 extern unsigned short swap_cgroup_clear(swp_entry_t ent, unsigned int nr_ents);
 extern unsigned short lookup_swap_cgroup_id(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
@@ -15,7 +15,7 @@ extern void swap_cgroup_swapoff(int type);
 #else
 
 static inline
-void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+void swap_cgroup_record(struct folio *folio, unsigned short id, swp_entry_t ent)
 {
 }
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 4de6acb9b8ecb..8f9b35f80e24e 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4993,7 +4993,7 @@ void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(swap_memcg, nr_entries - 1);
 	mod_memcg_state(swap_memcg, MEMCG_SWAP, nr_entries);
 
-	swap_cgroup_record(folio, entry);
+	swap_cgroup_record(folio, mem_cgroup_id(swap_memcg), entry);
 
 	folio_unqueue_deferred_split(folio);
 	folio->memcg_data = 0;
@@ -5055,7 +5055,7 @@ int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry)
 		mem_cgroup_id_get_many(memcg, nr_pages - 1);
 	mod_memcg_state(memcg, MEMCG_SWAP, nr_pages);
 
-	swap_cgroup_record(folio, entry);
+	swap_cgroup_record(folio, mem_cgroup_id(memcg), entry);
 
 	return 0;
 }
diff --git a/mm/swap_cgroup.c b/mm/swap_cgroup.c
index be39078f255be..1007c30f12e2c 100644
--- a/mm/swap_cgroup.c
+++ b/mm/swap_cgroup.c
@@ -58,9 +58,11 @@ static unsigned short __swap_cgroup_id_xchg(struct swap_cgroup *map,
  * entries must not have been charged
  *
  * @folio: the folio that the swap entry belongs to
+ * @id: mem_cgroup ID to be recorded
  * @ent: the first swap entry to be recorded
  */
-void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
+void swap_cgroup_record(struct folio *folio, unsigned short id,
+			swp_entry_t ent)
 {
 	unsigned int nr_ents = folio_nr_pages(folio);
 	struct swap_cgroup *map;
@@ -72,8 +74,7 @@ void swap_cgroup_record(struct folio *folio, swp_entry_t ent)
 	map = swap_cgroup_ctrl[swp_type(ent)].map;
 
 	do {
-		old = __swap_cgroup_id_xchg(map, offset,
-					    mem_cgroup_id(folio_memcg(folio)));
+		old = __swap_cgroup_id_xchg(map, offset, id);
 		VM_BUG_ON(old);
 	} while (++offset != end);
 }

From 182db972c9568dc530b2f586a2f82dfd039d9f2a Mon Sep 17 00:00:00 2001
From: "Raphael S. Carvalho" <raphaelsc@scylladb.com>
Date: Mon, 24 Feb 2025 11:37:00 -0300
Subject: [PATCH 2154/2753] mm: fix error handling in __filemap_get_folio()
 with FGP_NOWAIT
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

original report:
https://lore.kernel.org/all/CAKhLTr1UL3ePTpYjXOx2AJfNk8Ku2EdcEfu+CH1sf3Asr=B-Dw@mail.gmail.com/T/

When doing buffered writes with FGP_NOWAIT, under memory pressure, the
system returned ENOMEM despite there being plenty of available memory, to
be reclaimed from page cache.  The user space used io_uring interface,
which in turn submits I/O with FGP_NOWAIT (the fast path).

retsnoop pointed to iomap_get_folio:

00:34:16.180612 -> 00:34:16.180651 TID/PID 253786/253721
(reactor-1/combined_tests):

                    entry_SYSCALL_64_after_hwframe+0x76
                    do_syscall_64+0x82
                    __do_sys_io_uring_enter+0x265
                    io_submit_sqes+0x209
                    io_issue_sqe+0x5b
                    io_write+0xdd
                    xfs_file_buffered_write+0x84
                    iomap_file_buffered_write+0x1a6
    32us [-ENOMEM]  iomap_write_begin+0x408
iter=&{.inode=0xffff8c67aa031138,.len=4096,.flags=33,.iomap={.addr=0xffffffffffffffff,.length=4096,.type=1,.flags=3,.bdev=0x…
pos=0 len=4096 foliop=0xffffb32c296b7b80
!    4us [-ENOMEM]  iomap_get_folio
iter=&{.inode=0xffff8c67aa031138,.len=4096,.flags=33,.iomap={.addr=0xffffffffffffffff,.length=4096,.type=1,.flags=3,.bdev=0x…
pos=0 len=4096

This is likely a regression caused by 66dabbb65d67 ("mm: return an ERR_PTR
from __filemap_get_folio"), which moved error handling from
io_map_get_folio() to __filemap_get_folio(), but broke FGP_NOWAIT
handling, so ENOMEM is being escaped to user space.  Had it correctly
returned -EAGAIN with NOWAIT, either io_uring or user space itself would
be able to retry the request.

It's not enough to patch io_uring since the iomap interface is the one
responsible for it, and pwritev2(RWF_NOWAIT) and AIO interfaces must
return the proper error too.

The patch was tested with scylladb test suite (its original reproducer),
and the tests all pass now when memory is pressured.

Link: https://lkml.kernel.org/r/20250224143700.23035-1-raphaelsc@scylladb.com
Fixes: 66dabbb65d67 ("mm: return an ERR_PTR from __filemap_get_folio")
Signed-off-by: Raphael S. Carvalho <raphaelsc@scylladb.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Cc: "Darrick J. Wong" <djwong@kernel.org>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/filemap.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/mm/filemap.c b/mm/filemap.c
index fbaf0e4fc8e1c..6e3d27993b676 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1986,8 +1986,19 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 
 		if (err == -EEXIST)
 			goto repeat;
-		if (err)
+		if (err) {
+			/*
+			 * When NOWAIT I/O fails to allocate folios this could
+			 * be due to a nonblocking memory allocation and not
+			 * because the system actually is out of memory.
+			 * Return -EAGAIN so that there caller retries in a
+			 * blocking fashion instead of propagating -ENOMEM
+			 * to the application.
+			 */
+			if ((fgp_flags & FGP_NOWAIT) && err == -ENOMEM)
+				err = -EAGAIN;
 			return ERR_PTR(err);
+		}
 		/*
 		 * filemap_add_folio locks the page, and for mmap
 		 * we expect an unlocked page.

From 67a2f86846f244d81601cf2e1552c4656b8556d6 Mon Sep 17 00:00:00 2001
From: Rafael Aquini <raquini@redhat.com>
Date: Tue, 18 Feb 2025 14:22:51 -0500
Subject: [PATCH 2155/2753] selftests/mm: run_vmtests.sh: fix half_ufd_size_MB
 calculation

We noticed that uffd-stress test was always failing to run when invoked
for the hugetlb profiles on x86_64 systems with a processor count of 64 or
bigger:

  ...
  # ------------------------------------
  # running ./uffd-stress hugetlb 128 32
  # ------------------------------------
  # ERROR: invalid MiB (errno=9, @uffd-stress.c:459)
  ...
  # [FAIL]
  not ok 3 uffd-stress hugetlb 128 32 # exit=1
  ...

The problem boils down to how run_vmtests.sh (mis)calculates the size of
the region it feeds to uffd-stress.  The latter expects to see an amount
of MiB while the former is just giving out the number of free hugepages
halved down.  This measurement discrepancy ends up violating uffd-stress'
assertion on number of hugetlb pages allocated per CPU, causing it to bail
out with the error above.

This commit fixes that issue by adjusting run_vmtests.sh's
half_ufd_size_MB calculation so it properly renders the region size in
MiB, as expected, while maintaining all of its original constraints in
place.

Link: https://lkml.kernel.org/r/20250218192251.53243-1-aquini@redhat.com
Fixes: 2e47a445d7b3 ("selftests/mm: run_vmtests.sh: fix hugetlb mem size calculation")
Signed-off-by: Rafael Aquini <raquini@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 tools/testing/selftests/mm/run_vmtests.sh | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index da7e266681031..7cc71d942f83b 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -304,7 +304,9 @@ uffd_stress_bin=./uffd-stress
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} anon 20 16
 # Hugetlb tests require source and destination huge pages. Pass in half
 # the size of the free pages we have, which is used for *each*.
-half_ufd_size_MB=$((freepgs / 2))
+# uffd-stress expects a region expressed in MiB, so we adjust
+# half_ufd_size_MB accordingly.
+half_ufd_size_MB=$(((freepgs * hpgsize_KB) / 1024 / 2))
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb "$half_ufd_size_MB" 32
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} hugetlb-private "$half_ufd_size_MB" 32
 CATEGORY="userfaultfd" run_test ${uffd_stress_bin} shmem 20 16

From 14efb4793519d73fb2902bb0ece319b886e4b4b9 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 10 Mar 2025 11:57:27 -0400
Subject: [PATCH 2156/2753] mm/huge_memory: drop beyond-EOF folios with the
 right number of refs

When an after-split folio is large and needs to be dropped due to EOF,
folio_put_refs(folio, folio_nr_pages(folio)) should be used to drop all
page cache refs.  Otherwise, the folio will not be freed, causing memory
leak.

This leak would happen on a filesystem with blocksize > page_size and a
truncate is performed, where the blocksize makes folios split to >0 order
ones, causing truncated folios not being freed.

Link: https://lkml.kernel.org/r/20250310155727.472846-1-ziy@nvidia.com
Fixes: c010d47f107f ("mm: thp: split huge page to any lower order pages")
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reported-by: Hugh Dickins <hughd@google.com>
Closes: https://lore.kernel.org/all/fcbadb7f-dd3e-21df-f9a7-2853b53183c4@google.com/
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Luis Chamberalin <mcgrof@kernel.org>
Cc: Matthew Wilcow (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Pankaj Raghav <p.raghav@samsung.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Yu Zhao <yuzhao@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/huge_memory.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 3d3ebdc002d59..373781b21e5ca 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3304,7 +3304,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
 				folio_account_cleaned(tail,
 					inode_to_wb(folio->mapping->host));
 			__filemap_remove_folio(tail, NULL);
-			folio_put(tail);
+			folio_put_refs(tail, folio_nr_pages(tail));
 		} else if (!folio_test_anon(folio)) {
 			__xa_store(&folio->mapping->i_pages, tail->index,
 					tail, 0);

From 9f01b4954490d4ccdbcc2b9be34a9921ceee9cbb Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Mon, 10 Mar 2025 16:09:34 -0700
Subject: [PATCH 2157/2753] memcg: drain obj stock on cpu hotplug teardown

Currently on cpu hotplug teardown, only memcg stock is drained but we
need to drain the obj stock as well otherwise we will miss the stats
accumulated on the target cpu as well as the nr_bytes cached. The stats
include MEMCG_KMEM, NR_SLAB_RECLAIMABLE_B & NR_SLAB_UNRECLAIMABLE_B. In
addition we are leaking reference to struct obj_cgroup object.

Link: https://lkml.kernel.org/r/20250310230934.2913113-1-shakeel.butt@linux.dev
Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API")
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/memcontrol.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8f9b35f80e24e..a037ec92881d5 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1921,9 +1921,18 @@ void drain_all_stock(struct mem_cgroup *root_memcg)
 static int memcg_hotplug_cpu_dead(unsigned int cpu)
 {
 	struct memcg_stock_pcp *stock;
+	struct obj_cgroup *old;
+	unsigned long flags;
 
 	stock = &per_cpu(memcg_stock, cpu);
+
+	/* drain_obj_stock requires stock_lock */
+	local_lock_irqsave(&memcg_stock.stock_lock, flags);
+	old = drain_obj_stock(stock);
+	local_unlock_irqrestore(&memcg_stock.stock_lock, flags);
+
 	drain_stock(stock);
+	obj_cgroup_put(old);
 
 	return 0;
 }

From b9c0e49abfca06f1a109acea834bcfc934f33f76 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 10 Mar 2025 14:35:24 +0000
Subject: [PATCH 2158/2753] mm: decline to manipulate the refcount on a slab
 page

Slab pages now have a refcount of 0, so nobody should be trying to
manipulate the refcount on them.  Doing so has little effect; the object
could be freed and reallocated to a different purpose, although the slab
itself would not be until the refcount was put making it behave rather
like TYPESAFE_BY_RCU.

Unfortunately, __iov_iter_get_pages_alloc() does take a refcount.  Fix
that to not change the refcount, and make put_page() silently not change
the refcount.  get_page() warns so that we can fix any other callers that
need to be changed.

Long-term, networking needs to stop taking a refcount on the pages that it
uses and rely on the caller to hold whatever references are necessary to
make the memory stable.  In the medium term, more page types are going to
hav a zero refcount, so we'll want to move get_page() and put_page() out
of line.

Link: https://lkml.kernel.org/r/20250310143544.1216127-1-willy@infradead.org
Fixes: 9aec2fb0fd5e (slab: allocate frozen pages)
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reported-by: Hannes Reinecke <hare@suse.de>
Closes: https://lore.kernel.org/all/08c29e4b-2f71-4b6d-8046-27e407214d8c@suse.com/
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 8 +++++++-
 lib/iov_iter.c     | 8 ++++++--
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7b1068ddcbb70..fd1e85b4b48a2 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1458,7 +1458,10 @@ static inline void folio_get(struct folio *folio)
 
 static inline void get_page(struct page *page)
 {
-	folio_get(page_folio(page));
+	struct folio *folio = page_folio(page);
+	if (WARN_ON_ONCE(folio_test_slab(folio)))
+		return;
+	folio_get(folio);
 }
 
 static inline __must_check bool try_get_page(struct page *page)
@@ -1552,6 +1555,9 @@ static inline void put_page(struct page *page)
 {
 	struct folio *folio = page_folio(page);
 
+	if (folio_test_slab(folio))
+		return;
+
 	/*
 	 * For some devmap managed pages we need to catch refcount transition
 	 * from 2 to 1:
diff --git a/lib/iov_iter.c b/lib/iov_iter.c
index 65f550cb5081b..8c7fdb7d8c8fa 100644
--- a/lib/iov_iter.c
+++ b/lib/iov_iter.c
@@ -1190,8 +1190,12 @@ static ssize_t __iov_iter_get_pages_alloc(struct iov_iter *i,
 		if (!n)
 			return -ENOMEM;
 		p = *pages;
-		for (int k = 0; k < n; k++)
-			get_page(p[k] = page + k);
+		for (int k = 0; k < n; k++) {
+			struct folio *folio = page_folio(page);
+			p[k] = page + k;
+			if (!folio_test_slab(folio))
+				folio_get(folio);
+		}
 		maxsize = min_t(size_t, maxsize, n * PAGE_SIZE - *start);
 		i->count -= maxsize;
 		i->iov_offset += maxsize;

From 800f1059c99e2b39899bdc67a7593a7bea6375d8 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Mon, 10 Mar 2025 10:28:55 +0200
Subject: [PATCH 2159/2753] mm/page_alloc: fix memory accept before watermarks
 gets initialized

Watermarks are initialized during the postcore initcall.  Until then, all
watermarks are set to zero.  This causes cond_accept_memory() to
incorrectly skip memory acceptance because a watermark of 0 is always met.

This can lead to a premature OOM on boot.

To ensure progress, accept one MAX_ORDER page if the watermark is zero.

Link: https://lkml.kernel.org/r/20250310082855.2587122-1-kirill.shutemov@linux.intel.com
Fixes: dcdfdd40fa82 ("mm: Add support for unaccepted memory")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Tested-by: Farrah Chen <farrah.chen@intel.com>
Reported-by: Farrah Chen <farrah.chen@intel.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Pankaj Gupta <pankaj.gupta@amd.com>
Cc: Ashish Kalra <ashish.kalra@amd.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
Cc: Thomas Lendacky <thomas.lendacky@amd.com>
Cc: <stable@vger.kernel.org>	[6.5+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 mm/page_alloc.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 94917c729120f..542d25f77be80 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7004,7 +7004,7 @@ static inline bool has_unaccepted_memory(void)
 
 static bool cond_accept_memory(struct zone *zone, unsigned int order)
 {
-	long to_accept;
+	long to_accept, wmark;
 	bool ret = false;
 
 	if (!has_unaccepted_memory())
@@ -7013,8 +7013,18 @@ static bool cond_accept_memory(struct zone *zone, unsigned int order)
 	if (list_empty(&zone->unaccepted_pages))
 		return false;
 
+	wmark = promo_wmark_pages(zone);
+
+	/*
+	 * Watermarks have not been initialized yet.
+	 *
+	 * Accepting one MAX_ORDER page to ensure progress.
+	 */
+	if (!wmark)
+		return try_to_accept_memory_one(zone);
+
 	/* How much to accept to get to promo watermark? */
-	to_accept = promo_wmark_pages(zone) -
+	to_accept = wmark -
 		    (zone_page_state(zone, NR_FREE_PAGES) -
 		    __zone_watermark_unusable_free(zone, order, 0) -
 		    zone_page_state(zone, NR_UNACCEPTED));

From 723ef0e20dbb2aa1b5406d2bb75374fc48187daa Mon Sep 17 00:00:00 2001
From: Kamal Dasu <kamal.dasu@broadcom.com>
Date: Tue, 11 Mar 2025 12:59:35 -0400
Subject: [PATCH 2160/2753] mmc: sdhci-brcmstb: add cqhci suspend/resume to PM
 ops

cqhci timeouts observed on brcmstb platforms during suspend:
  ...
  [  164.832853] mmc0: cqhci: timeout for tag 18
  ...

Adding cqhci_suspend()/resume() calls to disable cqe
in sdhci_brcmstb_suspend()/resume() respectively to fix
CQE timeouts seen on PM suspend.

Fixes: d46ba2d17f90 ("mmc: sdhci-brcmstb: Add support for Command Queuing (CQE)")
Cc: stable@vger.kernel.org
Signed-off-by: Kamal Dasu <kamal.dasu@broadcom.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Link: https://lore.kernel.org/r/20250311165946.28190-1-kamal.dasu@broadcom.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/mmc/host/sdhci-brcmstb.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/mmc/host/sdhci-brcmstb.c b/drivers/mmc/host/sdhci-brcmstb.c
index 0ef4d578ade84..48cdcba0f39cc 100644
--- a/drivers/mmc/host/sdhci-brcmstb.c
+++ b/drivers/mmc/host/sdhci-brcmstb.c
@@ -503,8 +503,15 @@ static int sdhci_brcmstb_suspend(struct device *dev)
 	struct sdhci_host *host = dev_get_drvdata(dev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
 	struct sdhci_brcmstb_priv *priv = sdhci_pltfm_priv(pltfm_host);
+	int ret;
 
 	clk_disable_unprepare(priv->base_clk);
+	if (host->mmc->caps2 & MMC_CAP2_CQE) {
+		ret = cqhci_suspend(host->mmc);
+		if (ret)
+			return ret;
+	}
+
 	return sdhci_pltfm_suspend(dev);
 }
 
@@ -529,6 +536,9 @@ static int sdhci_brcmstb_resume(struct device *dev)
 			ret = clk_set_rate(priv->base_clk, priv->base_freq_hz);
 	}
 
+	if (host->mmc->caps2 & MMC_CAP2_CQE)
+		ret = cqhci_resume(host->mmc);
+
 	return ret;
 }
 #endif

From 53df59ddaadfa88afd0b1a097777a36eec09603b Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Mon, 17 Mar 2025 10:14:49 +0100
Subject: [PATCH 2161/2753] MAINTAINERS: correct list and scope of LTC4286
 HARDWARE MONITOR

This entry has a wrong list, i2c instead of hwmon. Also, it states to
maintain Kconfig and Makefile which is not suitable for a single driver.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Fixes: 7707cf82e138 ("dt-bindings: hwmon: Add lltc ltc4286 driver bindings")
Link: https://lore.kernel.org/r/20250317091459.41462-2-wsa+renesas@sang-engineering.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 MAINTAINERS | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index ed7aa6867674e..babef8001ed22 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -13752,12 +13752,10 @@ F:	drivers/hwmon/ltc4282.c
 
 LTC4286 HARDWARE MONITOR DRIVER
 M:	Delphine CC Chiu <Delphine_CC_Chiu@Wiwynn.com>
-L:	linux-i2c@vger.kernel.org
+L:	linux-hwmon@vger.kernel.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/hwmon/lltc,ltc4286.yaml
 F:	Documentation/hwmon/ltc4286.rst
-F:	drivers/hwmon/pmbus/Kconfig
-F:	drivers/hwmon/pmbus/Makefile
 F:	drivers/hwmon/pmbus/ltc4286.c
 
 LTC4306 I2C MULTIPLEXER DRIVER

From 815f80ad20b63830949a77c816e35395d5d55144 Mon Sep 17 00:00:00 2001
From: Tasos Sahanidis <tasos@tasossah.com>
Date: Wed, 12 Mar 2025 05:08:32 +0200
Subject: [PATCH 2162/2753] hwmon: (nct6775-core) Fix out of bounds access for
 NCT679{8,9}

pwm_num is set to 7 for these chips, but NCT6776_REG_PWM_MODE and
NCT6776_PWM_MODE_MASK only contain 6 values.

Fix this by adding another 0 to the end of each array.

Signed-off-by: Tasos Sahanidis <tasos@tasossah.com>
Link: https://lore.kernel.org/r/20250312030832.106475-1-tasos@tasossah.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/nct6775-core.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
index fa3351351825b..79bc67ffb9986 100644
--- a/drivers/hwmon/nct6775-core.c
+++ b/drivers/hwmon/nct6775-core.c
@@ -273,8 +273,8 @@ static const s8 NCT6776_BEEP_BITS[NUM_BEEP_BITS] = {
 static const u16 NCT6776_REG_TOLERANCE_H[] = {
 	0x10c, 0x20c, 0x30c, 0x80c, 0x90c, 0xa0c, 0xb0c };
 
-static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0 };
-static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_REG_PWM_MODE[] = { 0x04, 0, 0, 0, 0, 0, 0 };
+static const u8 NCT6776_PWM_MODE_MASK[] = { 0x01, 0, 0, 0, 0, 0, 0 };
 
 static const u16 NCT6776_REG_FAN_MIN[] = {
 	0x63a, 0x63c, 0x63e, 0x640, 0x642, 0x64a, 0x64c };

From 149dfb31615e22271d2525f078c95ea49bc4db24 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:41 +0100
Subject: [PATCH 2163/2753] tcp: reorganize tcp_in_ack_event() and
 tcp_count_delivered()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- Move tcp_count_delivered() earlier and split tcp_count_delivered_ce()
  out of it
- Move tcp_in_ack_event() later
- While at it, remove the inline from tcp_in_ack_event() and let
  the compiler to decide

Accurate ECN's heuristics does not know if there is going
to be ACE field based CE counter increase or not until after
rtx queue has been processed. Only then the number of ACKed
bytes/pkts is available. As CE or not affects presence of
FLAG_ECE, that information for tcp_in_ack_event is not yet
available in the old location of the call to tcp_in_ack_event().

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 56 +++++++++++++++++++++++++-------------------
 1 file changed, 32 insertions(+), 24 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4e22123480889..6a8eca916580e 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -421,6 +421,20 @@ static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr
 	return false;
 }
 
+static void tcp_count_delivered_ce(struct tcp_sock *tp, u32 ecn_count)
+{
+	tp->delivered_ce += ecn_count;
+}
+
+/* Updates the delivered and delivered_ce counts */
+static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
+				bool ece_ack)
+{
+	tp->delivered += delivered;
+	if (ece_ack)
+		tcp_count_delivered_ce(tp, delivered);
+}
+
 /* Buffer size and advertised window tuning.
  *
  * 1. Tuning sk->sk_sndbuf, when connection enters established state.
@@ -1156,15 +1170,6 @@ void tcp_mark_skb_lost(struct sock *sk, struct sk_buff *skb)
 	}
 }
 
-/* Updates the delivered and delivered_ce counts */
-static void tcp_count_delivered(struct tcp_sock *tp, u32 delivered,
-				bool ece_ack)
-{
-	tp->delivered += delivered;
-	if (ece_ack)
-		tp->delivered_ce += delivered;
-}
-
 /* This procedure tags the retransmission queue when SACKs arrive.
  *
  * We have three tag bits: SACKED(S), RETRANS(R) and LOST(L).
@@ -3864,12 +3869,23 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
 	}
 }
 
-static inline void tcp_in_ack_event(struct sock *sk, u32 flags)
+static void tcp_in_ack_event(struct sock *sk, int flag)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 
-	if (icsk->icsk_ca_ops->in_ack_event)
-		icsk->icsk_ca_ops->in_ack_event(sk, flags);
+	if (icsk->icsk_ca_ops->in_ack_event) {
+		u32 ack_ev_flags = 0;
+
+		if (flag & FLAG_WIN_UPDATE)
+			ack_ev_flags |= CA_ACK_WIN_UPDATE;
+		if (flag & FLAG_SLOWPATH) {
+			ack_ev_flags |= CA_ACK_SLOWPATH;
+			if (flag & FLAG_ECE)
+				ack_ev_flags |= CA_ACK_ECE;
+		}
+
+		icsk->icsk_ca_ops->in_ack_event(sk, ack_ev_flags);
+	}
 }
 
 /* Congestion control has updated the cwnd already. So if we're in
@@ -3986,12 +4002,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 		tcp_snd_una_update(tp, ack);
 		flag |= FLAG_WIN_UPDATE;
 
-		tcp_in_ack_event(sk, CA_ACK_WIN_UPDATE);
-
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHPACKS);
 	} else {
-		u32 ack_ev_flags = CA_ACK_SLOWPATH;
-
 		if (ack_seq != TCP_SKB_CB(skb)->end_seq)
 			flag |= FLAG_DATA;
 		else
@@ -4003,19 +4015,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 			flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una,
 							&sack_state);
 
-		if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb))) {
+		if (tcp_ecn_rcv_ecn_echo(tp, tcp_hdr(skb)))
 			flag |= FLAG_ECE;
-			ack_ev_flags |= CA_ACK_ECE;
-		}
 
 		if (sack_state.sack_delivered)
 			tcp_count_delivered(tp, sack_state.sack_delivered,
 					    flag & FLAG_ECE);
-
-		if (flag & FLAG_WIN_UPDATE)
-			ack_ev_flags |= CA_ACK_WIN_UPDATE;
-
-		tcp_in_ack_event(sk, ack_ev_flags);
 	}
 
 	/* This is a deviation from RFC3168 since it states that:
@@ -4042,6 +4047,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 	tcp_rack_update_reo_wnd(sk, &rs);
 
+	tcp_in_ack_event(sk, flag);
+
 	if (tp->tlp_high_seq)
 		tcp_process_tlp_ack(sk, ack, flag);
 
@@ -4073,6 +4080,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	return 1;
 
 no_queue:
+	tcp_in_ack_event(sk, flag);
 	/* If data was DSACKed, see if we can undo a cwnd reduction. */
 	if (flag & FLAG_DSACKING_ACK) {
 		tcp_fastretrans_alert(sk, prior_snd_una, num_dupack, &flag,

From da610e18313be854977347450c86997548406813 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:42 +0100
Subject: [PATCH 2164/2753] tcp: create FLAG_TS_PROGRESS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Whenever timestamp advances, it declares progress which
can be used by the other parts of the stack to decide that
the ACK is the most recent one seen so far.

AccECN will use this flag when deciding whether to use the
ACK to update AccECN state or not.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 37 ++++++++++++++++++++++++++++---------
 1 file changed, 28 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6a8eca916580e..771e075d457d9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -102,6 +102,7 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #define FLAG_NO_CHALLENGE_ACK	0x8000 /* do not call tcp_send_challenge_ack()	*/
 #define FLAG_ACK_MAYBE_DELAYED	0x10000 /* Likely a delayed ACK */
 #define FLAG_DSACK_TLP		0x20000 /* DSACK for tail loss probe */
+#define FLAG_TS_PROGRESS	0x40000 /* Positive timestamp delta */
 
 #define FLAG_ACKED		(FLAG_DATA_ACKED|FLAG_SYN_ACKED)
 #define FLAG_NOT_DUP		(FLAG_DATA|FLAG_WIN_UPDATE|FLAG_ACKED)
@@ -3821,8 +3822,16 @@ static void tcp_store_ts_recent(struct tcp_sock *tp)
 	tp->rx_opt.ts_recent_stamp = ktime_get_seconds();
 }
 
-static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+static int __tcp_replace_ts_recent(struct tcp_sock *tp, s32 tstamp_delta)
 {
+	tcp_store_ts_recent(tp);
+	return tstamp_delta > 0 ? FLAG_TS_PROGRESS : 0;
+}
+
+static int tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
+{
+	s32 delta;
+
 	if (tp->rx_opt.saw_tstamp && !after(seq, tp->rcv_wup)) {
 		/* PAWS bug workaround wrt. ACK frames, the PAWS discard
 		 * extra check below makes sure this can only happen
@@ -3831,9 +3840,13 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq)
 		 * Not only, also it occurs for expired timestamps.
 		 */
 
-		if (tcp_paws_check(&tp->rx_opt, 0))
-			tcp_store_ts_recent(tp);
+		if (tcp_paws_check(&tp->rx_opt, 0)) {
+			delta = tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent;
+			return __tcp_replace_ts_recent(tp, delta);
+		}
 	}
+
+	return 0;
 }
 
 /* This routine deals with acks during a TLP episode and ends an episode by
@@ -3990,7 +4003,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 	 * is in window.
 	 */
 	if (flag & FLAG_UPDATE_TS_RECENT)
-		tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+		flag |= tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
 
 	if ((flag & (FLAG_SLOWPATH | FLAG_SND_UNA_ADVANCED)) ==
 	    FLAG_SND_UNA_ADVANCED) {
@@ -6165,6 +6178,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 	    TCP_SKB_CB(skb)->seq == tp->rcv_nxt &&
 	    !after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt)) {
 		int tcp_header_len = tp->tcp_header_len;
+		s32 delta = 0;
+		int flag = 0;
 
 		/* Timestamp header prediction: tcp_header_len
 		 * is automatically equal to th->doff*4 due to pred_flags
@@ -6177,8 +6192,10 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			if (!tcp_parse_aligned_timestamp(tp, th))
 				goto slow_path;
 
+			delta = tp->rx_opt.rcv_tsval -
+				tp->rx_opt.ts_recent;
 			/* If PAWS failed, check it more carefully in slow path */
-			if ((s32)(tp->rx_opt.rcv_tsval - tp->rx_opt.ts_recent) < 0)
+			if (delta < 0)
 				goto slow_path;
 
 			/* DO NOT update ts_recent here, if checksum fails
@@ -6198,12 +6215,13 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 				if (tcp_header_len ==
 				    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
 				    tp->rcv_nxt == tp->rcv_wup)
-					tcp_store_ts_recent(tp);
+					flag |= __tcp_replace_ts_recent(tp,
+									delta);
 
 				/* We know that such packets are checksummed
 				 * on entry.
 				 */
-				tcp_ack(sk, skb, 0);
+				tcp_ack(sk, skb, flag);
 				__kfree_skb(skb);
 				tcp_data_snd_check(sk);
 				/* When receiving pure ack in fast path, update
@@ -6234,7 +6252,8 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 			if (tcp_header_len ==
 			    (sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED) &&
 			    tp->rcv_nxt == tp->rcv_wup)
-				tcp_store_ts_recent(tp);
+				flag |= __tcp_replace_ts_recent(tp,
+								delta);
 
 			tcp_rcv_rtt_measure_ts(sk, skb);
 
@@ -6249,7 +6268,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb)
 
 			if (TCP_SKB_CB(skb)->ack_seq != tp->snd_una) {
 				/* Well, only one small jumplet in fast path... */
-				tcp_ack(sk, skb, FLAG_DATA);
+				tcp_ack(sk, skb, flag | FLAG_DATA);
 				tcp_data_snd_check(sk);
 				if (!inet_csk_ack_scheduled(sk))
 					goto no_ack;

From 0114a91da67263c56612ff19a6aa0992466e7756 Mon Sep 17 00:00:00 2001
From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Date: Wed, 5 Mar 2025 23:38:43 +0100
Subject: [PATCH 2165/2753] tcp: use BIT() macro in include/net/tcp.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use BIT() macro for TCP flags field and TCP congestion control
flags that will be used by the congestion control algorithm.

No functional changes.

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Ilpo Järvinen <ij@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h | 21 +++++++++++----------
 1 file changed, 11 insertions(+), 10 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 7207c52b1fc9c..d2315d69e0195 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -26,6 +26,7 @@
 #include <linux/kref.h>
 #include <linux/ktime.h>
 #include <linux/indirect_call_wrapper.h>
+#include <linux/bits.h>
 
 #include <net/inet_connection_sock.h>
 #include <net/inet_timewait_sock.h>
@@ -934,14 +935,14 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
 
 #define tcp_flag_byte(th) (((u_int8_t *)th)[13])
 
-#define TCPHDR_FIN 0x01
-#define TCPHDR_SYN 0x02
-#define TCPHDR_RST 0x04
-#define TCPHDR_PSH 0x08
-#define TCPHDR_ACK 0x10
-#define TCPHDR_URG 0x20
-#define TCPHDR_ECE 0x40
-#define TCPHDR_CWR 0x80
+#define TCPHDR_FIN	BIT(0)
+#define TCPHDR_SYN	BIT(1)
+#define TCPHDR_RST	BIT(2)
+#define TCPHDR_PSH	BIT(3)
+#define TCPHDR_ACK	BIT(4)
+#define TCPHDR_URG	BIT(5)
+#define TCPHDR_ECE	BIT(6)
+#define TCPHDR_CWR	BIT(7)
 
 #define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
 
@@ -1132,9 +1133,9 @@ enum tcp_ca_ack_event_flags {
 #define TCP_CA_UNSPEC	0
 
 /* Algorithm can be set on socket without CAP_NET_ADMIN privileges */
-#define TCP_CONG_NON_RESTRICTED 0x1
+#define TCP_CONG_NON_RESTRICTED		BIT(0)
 /* Requires ECN/ECT set on all packets */
-#define TCP_CONG_NEEDS_ECN	0x2
+#define TCP_CONG_NEEDS_ECN		BIT(1)
 #define TCP_CONG_MASK	(TCP_CONG_NON_RESTRICTED | TCP_CONG_NEEDS_ECN)
 
 union tcp_cc_info;

From 2c2f08d31d2f6cd5621b121d596986bd54da679a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:44 +0100
Subject: [PATCH 2166/2753] tcp: extend TCP flags to allow AE bit/ACE field
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With AccECN, there's one additional TCP flag to be used (AE)
and ACE field that overloads the definition of AE, CWR, and
ECE flags. As tcp_flags was previously only 1 byte, the
byte-order stuff needs to be added to it's handling.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h             | 11 +++++++++--
 include/uapi/linux/tcp.h      |  9 ++++++---
 net/ipv4/tcp_ipv4.c           |  2 +-
 net/ipv4/tcp_output.c         |  8 ++++----
 net/ipv6/tcp_ipv6.c           |  2 +-
 net/netfilter/nf_log_syslog.c |  8 +++++---
 6 files changed, 26 insertions(+), 14 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index d2315d69e0195..4e11bdc864709 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -943,7 +943,14 @@ static inline u32 tcp_rsk_tsval(const struct tcp_request_sock *treq)
 #define TCPHDR_URG	BIT(5)
 #define TCPHDR_ECE	BIT(6)
 #define TCPHDR_CWR	BIT(7)
-
+#define TCPHDR_AE	BIT(8)
+#define TCPHDR_FLAGS_MASK (TCPHDR_FIN | TCPHDR_SYN | TCPHDR_RST | \
+			   TCPHDR_PSH | TCPHDR_ACK | TCPHDR_URG | \
+			   TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
+#define tcp_flags_ntohs(th) (ntohs(*(__be16 *)&tcp_flag_word(th)) & \
+			    TCPHDR_FLAGS_MASK)
+
+#define TCPHDR_ACE (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)
 #define TCPHDR_SYN_ECN	(TCPHDR_SYN | TCPHDR_ECE | TCPHDR_CWR)
 
 /* State flags for sacked in struct tcp_skb_cb */
@@ -978,7 +985,7 @@ struct tcp_skb_cb {
 			u16	tcp_gso_size;
 		};
 	};
-	__u8		tcp_flags;	/* TCP header flags. (tcp[13])	*/
+	__u16		tcp_flags;	/* TCP header flags (tcp[12-13])*/
 
 	__u8		sacked;		/* State flags for SACK.	*/
 	__u8		ip_dsfield;	/* IPv4 tos or IPv6 dsfield	*/
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 32a27b4a5020a..92a2e79222ea5 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -28,7 +28,8 @@ struct tcphdr {
 	__be32	seq;
 	__be32	ack_seq;
 #if defined(__LITTLE_ENDIAN_BITFIELD)
-	__u16	res1:4,
+	__u16	ae:1,
+		res1:3,
 		doff:4,
 		fin:1,
 		syn:1,
@@ -40,7 +41,8 @@ struct tcphdr {
 		cwr:1;
 #elif defined(__BIG_ENDIAN_BITFIELD)
 	__u16	doff:4,
-		res1:4,
+		res1:3,
+		ae:1,
 		cwr:1,
 		ece:1,
 		urg:1,
@@ -70,6 +72,7 @@ union tcp_word_hdr {
 #define tcp_flag_word(tp) (((union tcp_word_hdr *)(tp))->words[3])
 
 enum {
+	TCP_FLAG_AE  = __constant_cpu_to_be32(0x01000000),
 	TCP_FLAG_CWR = __constant_cpu_to_be32(0x00800000),
 	TCP_FLAG_ECE = __constant_cpu_to_be32(0x00400000),
 	TCP_FLAG_URG = __constant_cpu_to_be32(0x00200000),
@@ -78,7 +81,7 @@ enum {
 	TCP_FLAG_RST = __constant_cpu_to_be32(0x00040000),
 	TCP_FLAG_SYN = __constant_cpu_to_be32(0x00020000),
 	TCP_FLAG_FIN = __constant_cpu_to_be32(0x00010000),
-	TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0F000000),
+	TCP_RESERVED_BITS = __constant_cpu_to_be32(0x0E000000),
 	TCP_DATA_OFFSET = __constant_cpu_to_be32(0xF0000000)
 };
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index d9405b012dff0..fab684221bf72 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2159,7 +2159,7 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff * 4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th);
 	TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph);
 	TCP_SKB_CB(skb)->sacked	 = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 24e56bf967472..efd3cb5e1ded0 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -403,7 +403,7 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 /* Constructs common control bits of non-data skb. If SYN/FIN is present,
  * auto increment end seqno.
  */
-static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u8 flags)
+static void tcp_init_nondata_skb(struct sk_buff *skb, u32 seq, u16 flags)
 {
 	skb->ip_summed = CHECKSUM_PARTIAL;
 
@@ -1395,7 +1395,7 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb,
 	th->seq			= htonl(tcb->seq);
 	th->ack_seq		= htonl(rcv_nxt);
 	*(((__be16 *)th) + 6)	= htons(((tcp_header_size >> 2) << 12) |
-					tcb->tcp_flags);
+					(tcb->tcp_flags & TCPHDR_FLAGS_MASK));
 
 	th->check		= 0;
 	th->urg_ptr		= 0;
@@ -1616,8 +1616,8 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue,
 	struct sk_buff *buff;
 	int old_factor;
 	long limit;
+	u16 flags;
 	int nlen;
-	u8 flags;
 
 	if (WARN_ON(len > skb->len))
 		return -EINVAL;
@@ -2171,7 +2171,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len,
 {
 	int nlen = skb->len - len;
 	struct sk_buff *buff;
-	u8 flags;
+	u16 flags;
 
 	/* All of a TSO frame must be composed of paged data.  */
 	DEBUG_NET_WARN_ON_ONCE(skb->len != skb->data_len);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 85c4820bfe158..a2fcc317a88e7 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1731,7 +1731,7 @@ static void tcp_v6_fill_cb(struct sk_buff *skb, const struct ipv6hdr *hdr,
 	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
 				    skb->len - th->doff*4);
 	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
-	TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th);
+	TCP_SKB_CB(skb)->tcp_flags = tcp_flags_ntohs(th);
 	TCP_SKB_CB(skb)->ip_dsfield = ipv6_get_dsfield(hdr);
 	TCP_SKB_CB(skb)->sacked = 0;
 	TCP_SKB_CB(skb)->has_rxtstamp =
diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c
index 58402226045e8..86d5fc5d28e3b 100644
--- a/net/netfilter/nf_log_syslog.c
+++ b/net/netfilter/nf_log_syslog.c
@@ -216,7 +216,9 @@ nf_log_dump_tcp_header(struct nf_log_buf *m,
 	/* Max length: 9 "RES=0x3C " */
 	nf_log_buf_add(m, "RES=0x%02x ", (u_int8_t)(ntohl(tcp_flag_word(th) &
 					    TCP_RESERVED_BITS) >> 22));
-	/* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */
+	/* Max length: 35 "AE CWR ECE URG ACK PSH RST SYN FIN " */
+	if (th->ae)
+		nf_log_buf_add(m, "AE ");
 	if (th->cwr)
 		nf_log_buf_add(m, "CWR ");
 	if (th->ece)
@@ -516,7 +518,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
 
 	/* Proto    Max log string length */
 	/* IP:	    40+46+6+11+127 = 230 */
-	/* TCP:     10+max(25,20+30+13+9+32+11+127) = 252 */
+	/* TCP:     10+max(25,20+30+13+9+35+11+127) = 255 */
 	/* UDP:     10+max(25,20) = 35 */
 	/* UDPLITE: 14+max(25,20) = 39 */
 	/* ICMP:    11+max(25, 18+25+max(19,14,24+3+n+10,3+n+10)) = 91+n */
@@ -526,7 +528,7 @@ dump_ipv4_packet(struct net *net, struct nf_log_buf *m,
 
 	/* (ICMP allows recursion one level deep) */
 	/* maxlen =  IP + ICMP +  IP + max(TCP,UDP,ICMP,unknown) */
-	/* maxlen = 230+   91  + 230 + 252 = 803 */
+	/* maxlen = 230+   91  + 230 + 255 = 806 */
 }
 
 static noinline_for_stack void

From f0db2bca0cf9d35a348f8fa726c1f61879a5cd02 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:46 +0100
Subject: [PATCH 2167/2753] tcp: rework {__,}tcp_ecn_check_ce() ->
 tcp_data_ecn_check()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Rename tcp_ecn_check_ce to tcp_data_ecn_check as it is
called only for data segments, not for ACKs (with AccECN,
also ACKs may get ECN bits).

The extra "layer" in tcp_ecn_check_ce() function just
checks for ECN being enabled, that can be moved into
tcp_ecn_field_check rather than having the __ variant.

No functional changes.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_input.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 771e075d457d9..769048b559e59 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -365,10 +365,13 @@ static void tcp_ecn_withdraw_cwr(struct tcp_sock *tp)
 	tp->ecn_flags &= ~TCP_ECN_QUEUE_CWR;
 }
 
-static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
+static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
+	if (!(tcp_sk(sk)->ecn_flags & TCP_ECN_OK))
+		return;
+
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
 	case INET_ECN_NOT_ECT:
 		/* Funny extension: if ECT is not set on a segment,
@@ -397,12 +400,6 @@ static void __tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
 	}
 }
 
-static void tcp_ecn_check_ce(struct sock *sk, const struct sk_buff *skb)
-{
-	if (tcp_sk(sk)->ecn_flags & TCP_ECN_OK)
-		__tcp_ecn_check_ce(sk, skb);
-}
-
 static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
 {
 	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr))
@@ -874,7 +871,7 @@ static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
 	icsk->icsk_ack.lrcvtime = now;
 	tcp_save_lrcv_flowlabel(sk, skb);
 
-	tcp_ecn_check_ce(sk, skb);
+	tcp_data_ecn_check(sk, skb);
 
 	if (skb->len >= 128)
 		tcp_grow_window(sk, skb, true);
@@ -5041,7 +5038,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 	bool fragstolen;
 
 	tcp_save_lrcv_flowlabel(sk, skb);
-	tcp_ecn_check_ce(sk, skb);
+	tcp_data_ecn_check(sk, skb);
 
 	if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP);

From 041fb11d518f5d25d323766bc0f59b09bba314bc Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:47 +0100
Subject: [PATCH 2168/2753] tcp: helpers for ECN mode handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Create helpers for TCP ECN modes. No functional changes.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        | 44 ++++++++++++++++++++++++++++++++++++----
 net/ipv4/tcp.c           |  2 +-
 net/ipv4/tcp_dctcp.c     |  2 +-
 net/ipv4/tcp_input.c     | 14 ++++++-------
 net/ipv4/tcp_minisocks.c |  4 +++-
 net/ipv4/tcp_output.c    |  6 +++---
 6 files changed, 55 insertions(+), 17 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4e11bdc864709..5520f2d62dc0d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -374,10 +374,46 @@ static inline void tcp_dec_quickack_mode(struct sock *sk)
 	}
 }
 
-#define	TCP_ECN_OK		1
-#define	TCP_ECN_QUEUE_CWR	2
-#define	TCP_ECN_DEMAND_CWR	4
-#define	TCP_ECN_SEEN		8
+#define	TCP_ECN_MODE_RFC3168	BIT(0)
+#define	TCP_ECN_QUEUE_CWR	BIT(1)
+#define	TCP_ECN_DEMAND_CWR	BIT(2)
+#define	TCP_ECN_SEEN		BIT(3)
+#define	TCP_ECN_MODE_ACCECN	BIT(4)
+
+#define	TCP_ECN_DISABLED	0
+#define	TCP_ECN_MODE_PENDING	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)
+#define	TCP_ECN_MODE_ANY	(TCP_ECN_MODE_RFC3168 | TCP_ECN_MODE_ACCECN)
+
+static inline bool tcp_ecn_mode_any(const struct tcp_sock *tp)
+{
+	return tp->ecn_flags & TCP_ECN_MODE_ANY;
+}
+
+static inline bool tcp_ecn_mode_rfc3168(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_RFC3168;
+}
+
+static inline bool tcp_ecn_mode_accecn(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_ANY) == TCP_ECN_MODE_ACCECN;
+}
+
+static inline bool tcp_ecn_disabled(const struct tcp_sock *tp)
+{
+	return !tcp_ecn_mode_any(tp);
+}
+
+static inline bool tcp_ecn_mode_pending(const struct tcp_sock *tp)
+{
+	return (tp->ecn_flags & TCP_ECN_MODE_PENDING) == TCP_ECN_MODE_PENDING;
+}
+
+static inline void tcp_ecn_mode_set(struct tcp_sock *tp, u8 mode)
+{
+	tp->ecn_flags &= ~TCP_ECN_MODE_ANY;
+	tp->ecn_flags |= mode;
+}
 
 enum tcp_tw_status {
 	TCP_TW_SUCCESS = 0,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 46951e7493084..989c3c3d8e757 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -4138,7 +4138,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 		info->tcpi_rcv_wscale = tp->rx_opt.rcv_wscale;
 	}
 
-	if (tp->ecn_flags & TCP_ECN_OK)
+	if (tcp_ecn_mode_any(tp))
 		info->tcpi_options |= TCPI_OPT_ECN;
 	if (tp->ecn_flags & TCP_ECN_SEEN)
 		info->tcpi_options |= TCPI_OPT_ECN_SEEN;
diff --git a/net/ipv4/tcp_dctcp.c b/net/ipv4/tcp_dctcp.c
index 8a45a4aea9335..03abe0848420d 100644
--- a/net/ipv4/tcp_dctcp.c
+++ b/net/ipv4/tcp_dctcp.c
@@ -90,7 +90,7 @@ __bpf_kfunc static void dctcp_init(struct sock *sk)
 {
 	const struct tcp_sock *tp = tcp_sk(sk);
 
-	if ((tp->ecn_flags & TCP_ECN_OK) ||
+	if (tcp_ecn_mode_any(tp) ||
 	    (sk->sk_state == TCP_LISTEN ||
 	     sk->sk_state == TCP_CLOSE)) {
 		struct dctcp *ca = inet_csk_ca(sk);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 769048b559e59..5c270cf966784 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -342,7 +342,7 @@ static bool tcp_in_quickack_mode(struct sock *sk)
 
 static void tcp_ecn_queue_cwr(struct tcp_sock *tp)
 {
-	if (tp->ecn_flags & TCP_ECN_OK)
+	if (tcp_ecn_mode_rfc3168(tp))
 		tp->ecn_flags |= TCP_ECN_QUEUE_CWR;
 }
 
@@ -369,7 +369,7 @@ static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (!(tcp_sk(sk)->ecn_flags & TCP_ECN_OK))
+	if (tcp_ecn_disabled(tp))
 		return;
 
 	switch (TCP_SKB_CB(skb)->ip_dsfield & INET_ECN_MASK) {
@@ -402,19 +402,19 @@ static void tcp_data_ecn_check(struct sock *sk, const struct sk_buff *skb)
 
 static void tcp_ecn_rcv_synack(struct tcp_sock *tp, const struct tcphdr *th)
 {
-	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || th->cwr))
-		tp->ecn_flags &= ~TCP_ECN_OK;
+	if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || th->cwr))
+		tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 }
 
 static void tcp_ecn_rcv_syn(struct tcp_sock *tp, const struct tcphdr *th)
 {
-	if ((tp->ecn_flags & TCP_ECN_OK) && (!th->ece || !th->cwr))
-		tp->ecn_flags &= ~TCP_ECN_OK;
+	if (tcp_ecn_mode_rfc3168(tp) && (!th->ece || !th->cwr))
+		tcp_ecn_mode_set(tp, TCP_ECN_DISABLED);
 }
 
 static bool tcp_ecn_rcv_ecn_echo(const struct tcp_sock *tp, const struct tcphdr *th)
 {
-	if (th->ece && !th->syn && (tp->ecn_flags & TCP_ECN_OK))
+	if (th->ece && !th->syn && tcp_ecn_mode_rfc3168(tp))
 		return true;
 	return false;
 }
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 3cb8f281186b2..0ae24add155b1 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -461,7 +461,9 @@ void tcp_openreq_init_rwin(struct request_sock *req,
 static void tcp_ecn_openreq_child(struct tcp_sock *tp,
 				  const struct request_sock *req)
 {
-	tp->ecn_flags = inet_rsk(req)->ecn_ok ? TCP_ECN_OK : 0;
+	tcp_ecn_mode_set(tp, inet_rsk(req)->ecn_ok ?
+			     TCP_ECN_MODE_RFC3168 :
+			     TCP_ECN_DISABLED);
 }
 
 void tcp_ca_openreq_child(struct sock *sk, const struct dst_entry *dst)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index efd3cb5e1ded0..fffbd3ee44edc 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -325,7 +325,7 @@ static void tcp_ecn_send_synack(struct sock *sk, struct sk_buff *skb)
 	const struct tcp_sock *tp = tcp_sk(sk);
 
 	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_CWR;
-	if (!(tp->ecn_flags & TCP_ECN_OK))
+	if (tcp_ecn_disabled(tp))
 		TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_ECE;
 	else if (tcp_ca_needs_ecn(sk) ||
 		 tcp_bpf_ca_needs_ecn(sk))
@@ -351,7 +351,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 
 	if (use_ecn) {
 		TCP_SKB_CB(skb)->tcp_flags |= TCPHDR_ECE | TCPHDR_CWR;
-		tp->ecn_flags = TCP_ECN_OK;
+		tcp_ecn_mode_set(tp, TCP_ECN_MODE_RFC3168);
 		if (tcp_ca_needs_ecn(sk) || bpf_needs_ecn)
 			INET_ECN_xmit(sk);
 	}
@@ -381,7 +381,7 @@ static void tcp_ecn_send(struct sock *sk, struct sk_buff *skb,
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tp->ecn_flags & TCP_ECN_OK) {
+	if (tcp_ecn_mode_rfc3168(tp)) {
 		/* Not-retransmitted data segment: set ECT and inject CWR. */
 		if (skb->len != tcp_header_len &&
 		    !before(TCP_SKB_CB(skb)->seq, tp->snd_nxt)) {

From 023af5a72ab161f2e661afb53e3b6a6901f6ba00 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:48 +0100
Subject: [PATCH 2169/2753] gso: AccECN support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Handling the CWR flag differs between RFC 3168 ECN and AccECN.
With RFC 3168 ECN aware TSO (NETIF_F_TSO_ECN) CWR flag is cleared
starting from 2nd segment which is incompatible how AccECN handles
the CWR flag. Such super-segments are indicated by SKB_GSO_TCP_ECN.
With AccECN, CWR flag (or more accurately, the ACE field that also
includes ECE & AE flags) changes only when new packet(s) with CE
mark arrives so the flag should not be changed within a super-skb.
The new skb/feature flags are necessary to prevent such TSO engines
corrupting AccECN ACE counters by clearing the CWR flag (if the
CWR handling feature cannot be turned off).

If NIC is completely unaware of RFC3168 ECN (doesn't support
NETIF_F_TSO_ECN) or its TSO engine can be set to not touch CWR flag
despite supporting also NETIF_F_TSO_ECN, TSO could be safely used
with AccECN on such NIC. This should be evaluated per NIC basis
(not done in this patch series for any NICs).

For the cases, where TSO cannot keep its hands off the CWR flag,
a GSO fallback is provided by this patch.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/linux/netdev_features.h | 8 +++++---
 include/linux/netdevice.h       | 2 ++
 include/linux/skbuff.h          | 2 ++
 net/ethtool/common.c            | 1 +
 net/ipv4/tcp_offload.c          | 6 +++++-
 5 files changed, 15 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 11be70a7929f2..7a01c518e5730 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -53,12 +53,12 @@ enum {
 	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	NETIF_F_GSO_UDP_L4_BIT,		/* ... UDP payload GSO (not UFO) */
 	NETIF_F_GSO_FRAGLIST_BIT,		/* ... Fraglist GSO */
+	NETIF_F_GSO_ACCECN_BIT,		/* TCP AccECN w/ TSO (no clear CWR) */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_FRAGLIST_BIT,
+		NETIF_F_GSO_ACCECN_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
-	__UNUSED_NETIF_F_37,
 	NETIF_F_NTUPLE_BIT,		/* N-tuple filters supported */
 	NETIF_F_RXHASH_BIT,		/* Receive hashing offload */
 	NETIF_F_RXCSUM_BIT,		/* Receive checksumming offload */
@@ -128,6 +128,7 @@ enum {
 #define NETIF_F_SG		__NETIF_F(SG)
 #define NETIF_F_TSO6		__NETIF_F(TSO6)
 #define NETIF_F_TSO_ECN		__NETIF_F(TSO_ECN)
+#define NETIF_F_GSO_ACCECN	__NETIF_F(GSO_ACCECN)
 #define NETIF_F_TSO		__NETIF_F(TSO)
 #define NETIF_F_VLAN_CHALLENGED	__NETIF_F(VLAN_CHALLENGED)
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
@@ -210,7 +211,8 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | \
+				 NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \
 				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
 
 /*
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0dbfe069a6e38..67527243459b3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5269,6 +5269,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_ACCECN !=
+		     (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 14517e95a46c4..b8a1343d6785c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -708,6 +708,8 @@ enum {
 	SKB_GSO_UDP_L4 = 1 << 17,
 
 	SKB_GSO_FRAGLIST = 1 << 18,
+
+	SKB_GSO_TCP_ACCECN = 1 << 19,
 };
 
 #if BITS_PER_LONG > 32
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index ac8b6107863e5..1c6f2a2f18714 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -36,6 +36,7 @@ const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = {
 	[NETIF_F_TSO_BIT] =              "tx-tcp-segmentation",
 	[NETIF_F_GSO_ROBUST_BIT] =       "tx-gso-robust",
 	[NETIF_F_TSO_ECN_BIT] =          "tx-tcp-ecn-segmentation",
+	[NETIF_F_GSO_ACCECN_BIT] =	 "tx-tcp-accecn-segmentation",
 	[NETIF_F_TSO_MANGLEID_BIT] =	 "tx-tcp-mangleid-segmentation",
 	[NETIF_F_TSO6_BIT] =             "tx-tcp6-segmentation",
 	[NETIF_F_FSO_BIT] =              "tx-fcoe-segmentation",
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index e27f4ee2a0de3..8c74fd69db2a8 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -142,6 +142,7 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 	struct sk_buff *gso_skb = skb;
 	__sum16 newcheck;
 	bool ooo_okay, copy_destructor;
+	bool ecn_cwr_mask;
 	__wsum delta;
 
 	th = tcp_hdr(skb);
@@ -201,6 +202,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 
 	newcheck = ~csum_fold(csum_add(csum_unfold(th->check), delta));
 
+	ecn_cwr_mask = !!(skb_shinfo(gso_skb)->gso_type & SKB_GSO_TCP_ACCECN);
+
 	while (skb->next) {
 		th->fin = th->psh = 0;
 		th->check = newcheck;
@@ -220,7 +223,8 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
 		th = tcp_hdr(skb);
 
 		th->seq = htonl(seq);
-		th->cwr = 0;
+
+		th->cwr &= ecn_cwr_mask;
 	}
 
 	/* Following permits TCP Small Queues to work well with GSO :

From 4e4f7cefb130af6aba6a393b2d13930b49390df9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:49 +0100
Subject: [PATCH 2170/2753] gro: prevent ACE field corruption & better AccECN
 handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are important differences in how the CWR field behaves
in RFC3168 and AccECN. With AccECN, CWR flag is part of the
ACE counter and its changes are important so adjust the flags
changed mask accordingly.

Also, if CWR is there, set the Accurate ECN GSO flag to avoid
corrupting CWR flag somewhere.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_offload.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index 8c74fd69db2a8..934f777f29d36 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -332,7 +332,7 @@ struct sk_buff *tcp_gro_receive(struct list_head *head, struct sk_buff *skb,
 	th2 = tcp_hdr(p);
 	flush = (__force int)(flags & TCP_FLAG_CWR);
 	flush |= (__force int)((flags ^ tcp_flag_word(th2)) &
-		  ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH));
+		  ~(TCP_FLAG_FIN | TCP_FLAG_PSH));
 	flush |= (__force int)(th->ack_seq ^ th2->ack_seq);
 	for (i = sizeof(*th); i < thlen; i += 4)
 		flush |= *(u32 *)((u8 *)th + i) ^
@@ -408,7 +408,7 @@ void tcp_gro_complete(struct sk_buff *skb)
 	shinfo->gso_segs = NAPI_GRO_CB(skb)->count;
 
 	if (th->cwr)
-		shinfo->gso_type |= SKB_GSO_TCP_ECN;
+		shinfo->gso_type |= SKB_GSO_TCP_ACCECN;
 }
 EXPORT_SYMBOL(tcp_gro_complete);
 

From d722762c4eaa918d3d2f78b41cca3f480a616d65 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:50 +0100
Subject: [PATCH 2171/2753] tcp: AccECN support to tcp_add_backlog
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

AE flag needs to be preserved for AccECN.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/ipv4/tcp_ipv4.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fab684221bf72..87f270ebc635f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2051,7 +2051,8 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	    !((TCP_SKB_CB(tail)->tcp_flags &
 	      TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) ||
 	    ((TCP_SKB_CB(tail)->tcp_flags ^
-	      TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) ||
+	      TCP_SKB_CB(skb)->tcp_flags) &
+	     (TCPHDR_ECE | TCPHDR_CWR | TCPHDR_AE)) ||
 	    !tcp_skb_can_collapse_rx(tail, skb) ||
 	    thtail->doff != th->doff ||
 	    memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th)))

From 4618e195f9251947a5f15f7e5533bcc3a19b93ef Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:51 +0100
Subject: [PATCH 2172/2753] tcp: add new TCP_TW_ACK_OOW state and allow ECN
 bits in TOS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ECN bits in TOS are always cleared when sending in ACKs in TW. Clearing
them is problematic for TCP flows that used Accurate ECN because ECN bits
decide which service queue the packet is placed into (L4S vs Classic).
Effectively, TW ACKs are always downgraded from L4S to Classic queue
which might impact, e.g., delay the ACK will experience on the path
compared with the other packets of the flow.

Change the TW ACK sending code to differentiate:
- In tcp_v4_send_reset(), commit ba9e04a7ddf4f ("ip: fix tos reflection
  in ack and reset packets") cleans ECN bits for TW reset and this is
  not affected.
- In tcp_v4_timewait_ack(), ECN bits for all TW ACKs are cleaned. But now
  only ECN bits of ACKs for oow data or paws_reject are cleaned, and ECN
  bits of other ACKs will not be cleaned.
- In tcp_v4_reqsk_send_ack(), commit 66b13d99d96a1 ("ipv4: tcp: fix TOS
  value in ACK messages sent from TIME_WAIT") did not clean ECN bits of
  ACKs for oow data or paws_reject. But now the ECN bits rae cleaned for
  these ACKs.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h        |  3 ++-
 net/ipv4/ip_output.c     |  3 +--
 net/ipv4/tcp_ipv4.c      | 29 +++++++++++++++++++++++------
 net/ipv4/tcp_minisocks.c |  2 +-
 net/ipv6/tcp_ipv6.c      | 24 +++++++++++++++++-------
 5 files changed, 44 insertions(+), 17 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5520f2d62dc0d..c6bdd3d631598 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -419,7 +419,8 @@ enum tcp_tw_status {
 	TCP_TW_SUCCESS = 0,
 	TCP_TW_RST = 1,
 	TCP_TW_ACK = 2,
-	TCP_TW_SYN = 3
+	TCP_TW_SYN = 3,
+	TCP_TW_ACK_OOW = 4
 };
 
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ea7a260bec8aa..6e18d7ec50624 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -75,7 +75,6 @@
 #include <net/checksum.h>
 #include <net/gso.h>
 #include <net/inetpeer.h>
-#include <net/inet_ecn.h>
 #include <net/lwtunnel.h>
 #include <net/inet_dscp.h>
 #include <linux/bpf-cgroup.h>
@@ -1640,7 +1639,7 @@ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
 	if (IS_ERR(rt))
 		return;
 
-	inet_sk(sk)->tos = arg->tos & ~INET_ECN_MASK;
+	inet_sk(sk)->tos = arg->tos;
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 87f270ebc635f..4fa4fbb0ad12d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -66,6 +66,7 @@
 #include <net/transp_v6.h>
 #include <net/ipv6.h>
 #include <net/inet_common.h>
+#include <net/inet_ecn.h>
 #include <net/timewait_sock.h>
 #include <net/xfrm.h>
 #include <net/secure_seq.h>
@@ -887,7 +888,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) !=
 		     offsetof(struct inet_timewait_sock, tw_bound_dev_if));
 
-	arg.tos = ip_hdr(skb)->tos;
+	/* ECN bits of TW reset are cleared */
+	arg.tos = ip_hdr(skb)->tos & ~INET_ECN_MASK;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
 	local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
@@ -1033,11 +1035,21 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	local_bh_enable();
 }
 
-static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
+static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb,
+				enum tcp_tw_status tw_status)
 {
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 	struct tcp_key key = {};
+	u8 tos = tw->tw_tos;
+
+	/* Cleaning only ECN bits of TW ACKs of oow data or is paws_reject,
+	 * while not cleaning ECN bits of other TW ACKs to avoid these ACKs
+	 * being placed in a different service queues (Classic rather than L4S)
+	 */
+	if (tw_status == TCP_TW_ACK_OOW)
+		tos &= ~INET_ECN_MASK;
+
 #ifdef CONFIG_TCP_AO
 	struct tcp_ao_info *ao_info;
 
@@ -1081,7 +1093,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			READ_ONCE(tcptw->tw_ts_recent),
 			tw->tw_bound_dev_if, &key,
 			tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
-			tw->tw_tos,
+			tos,
 			tw->tw_txhash);
 
 	inet_twsk_put(tw);
@@ -1151,6 +1163,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			key.type = TCP_KEY_MD5;
 	}
 
+	/* Cleaning ECN bits of TW ACKs of oow data or is paws_reject */
 	tcp_v4_send_ack(sk, skb, seq,
 			tcp_rsk(req)->rcv_nxt,
 			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
@@ -1158,7 +1171,7 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			req->ts_recent,
 			0, &key,
 			inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0,
-			ip_hdr(skb)->tos,
+			ip_hdr(skb)->tos & ~INET_ECN_MASK,
 			READ_ONCE(tcp_rsk(req)->txhash));
 	if (tcp_key_is_ao(&key))
 		kfree(key.traffic_key);
@@ -2175,6 +2188,7 @@ int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net_rcu(skb->dev);
 	enum skb_drop_reason drop_reason;
+	enum tcp_tw_status tw_status;
 	int sdif = inet_sdif(skb);
 	int dif = inet_iif(skb);
 	const struct iphdr *iph;
@@ -2402,7 +2416,9 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		inet_twsk_put(inet_twsk(sk));
 		goto csum_error;
 	}
-	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) {
+
+	tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn);
+	switch (tw_status) {
 	case TCP_TW_SYN: {
 		struct sock *sk2 = inet_lookup_listener(net,
 							net->ipv4.tcp_death_row.hashinfo,
@@ -2423,7 +2439,8 @@ int tcp_v4_rcv(struct sk_buff *skb)
 		/* to ACK */
 		fallthrough;
 	case TCP_TW_ACK:
-		tcp_v4_timewait_ack(sk, skb);
+	case TCP_TW_ACK_OOW:
+		tcp_v4_timewait_ack(sk, skb, tw_status);
 		break;
 	case TCP_TW_RST:
 		tcp_v4_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0ae24add155b1..fb9349be36b80 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -44,7 +44,7 @@ tcp_timewait_check_oow_rate_limit(struct inet_timewait_sock *tw,
 		/* Send ACK. Note, we do not put the bucket,
 		 * it will be released by caller.
 		 */
-		return TCP_TW_ACK;
+		return TCP_TW_ACK_OOW;
 	}
 
 	/* We are rate-limiting, so just release the tw sock and drop skb. */
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index a2fcc317a88e7..e182ee0a23304 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -999,7 +999,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 	if (!IS_ERR(dst)) {
 		skb_dst_set(buff, dst);
 		ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL,
-			 tclass & ~INET_ECN_MASK, priority);
+			 tclass, priority);
 		TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 		if (rst)
 			TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
@@ -1135,7 +1135,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
 	trace_tcp_send_reset(sk, skb, reason);
 
 	tcp_v6_send_response(sk, skb, seq, ack_seq, 0, 0, 0, oif, 1,
-			     ipv6_get_dsfield(ipv6h), label, priority, txhash,
+			     ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK,
+			     label, priority, txhash,
 			     &key);
 
 #if defined(CONFIG_TCP_MD5SIG) || defined(CONFIG_TCP_AO)
@@ -1155,11 +1156,16 @@ static void tcp_v6_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq,
 			     tclass, label, priority, txhash, key);
 }
 
-static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
+static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb,
+				enum tcp_tw_status tw_status)
 {
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
+	u8 tclass = tw->tw_tclass;
 	struct tcp_key key = {};
+
+	if (tw_status == TCP_TW_ACK_OOW)
+		tclass &= ~INET_ECN_MASK;
 #ifdef CONFIG_TCP_AO
 	struct tcp_ao_info *ao_info;
 
@@ -1203,7 +1209,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_tw_tsval(tcptw),
 			READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
-			&key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel),
+			&key, tclass, cpu_to_be32(tw->tw_flowlabel),
 			tw->tw_priority, tw->tw_txhash);
 
 #ifdef CONFIG_TCP_AO
@@ -1280,7 +1286,8 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 			tcp_synack_window(req) >> inet_rsk(req)->rcv_wscale,
 			tcp_rsk_tsval(tcp_rsk(req)),
 			req->ts_recent, sk->sk_bound_dev_if,
-			&key, ipv6_get_dsfield(ipv6_hdr(skb)), 0,
+			&key, ipv6_get_dsfield(ipv6_hdr(skb)) & ~INET_ECN_MASK,
+			0,
 			READ_ONCE(sk->sk_priority),
 			READ_ONCE(tcp_rsk(req)->txhash));
 	if (tcp_key_is_ao(&key))
@@ -1742,6 +1749,7 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net_rcu(skb->dev);
 	enum skb_drop_reason drop_reason;
+	enum tcp_tw_status tw_status;
 	int sdif = inet6_sdif(skb);
 	int dif = inet6_iif(skb);
 	const struct tcphdr *th;
@@ -1962,7 +1970,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 		goto csum_error;
 	}
 
-	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn)) {
+	tw_status = tcp_timewait_state_process(inet_twsk(sk), skb, th, &isn);
+	switch (tw_status) {
 	case TCP_TW_SYN:
 	{
 		struct sock *sk2;
@@ -1987,7 +1996,8 @@ INDIRECT_CALLABLE_SCOPE int tcp_v6_rcv(struct sk_buff *skb)
 		/* to ACK */
 		fallthrough;
 	case TCP_TW_ACK:
-		tcp_v6_timewait_ack(sk, skb);
+	case TCP_TW_ACK_OOW:
+		tcp_v6_timewait_ack(sk, skb, tw_status);
 		break;
 	case TCP_TW_RST:
 		tcp_v6_send_reset(sk, skb, SK_RST_REASON_TCP_TIMEWAIT_SOCKET);

From 9866884ce8ef25338c5b33cbb97c2b5d92088528 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= <ij@kernel.org>
Date: Wed, 5 Mar 2025 23:38:52 +0100
Subject: [PATCH 2173/2753] tcp: Pass flags to __tcp_send_ack
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Accurate ECN needs to send custom flags to handle IP-ECN
field reflection during handshake.

Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/tcp.h     | 2 +-
 net/ipv4/bpf_tcp_ca.c | 2 +-
 net/ipv4/tcp_dctcp.h  | 2 +-
 net/ipv4/tcp_output.c | 6 +++---
 4 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index c6bdd3d631598..d08fbf90495de 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -707,7 +707,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority,
 			   enum sk_rst_reason reason);
 int tcp_send_synack(struct sock *);
 void tcp_push_one(struct sock *, unsigned int mss_now);
-void __tcp_send_ack(struct sock *sk, u32 rcv_nxt);
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags);
 void tcp_send_ack(struct sock *sk);
 void tcp_send_delayed_ack(struct sock *sk);
 void tcp_send_loss_probe(struct sock *sk);
diff --git a/net/ipv4/bpf_tcp_ca.c b/net/ipv4/bpf_tcp_ca.c
index 554804774628e..e01492234b0b3 100644
--- a/net/ipv4/bpf_tcp_ca.c
+++ b/net/ipv4/bpf_tcp_ca.c
@@ -121,7 +121,7 @@ static int bpf_tcp_ca_btf_struct_access(struct bpf_verifier_log *log,
 BPF_CALL_2(bpf_tcp_send_ack, struct tcp_sock *, tp, u32, rcv_nxt)
 {
 	/* bpf_tcp_ca prog cannot have NULL tp */
-	__tcp_send_ack((struct sock *)tp, rcv_nxt);
+	__tcp_send_ack((struct sock *)tp, rcv_nxt, 0);
 	return 0;
 }
 
diff --git a/net/ipv4/tcp_dctcp.h b/net/ipv4/tcp_dctcp.h
index d69a77cbd0c75..4b0259111d816 100644
--- a/net/ipv4/tcp_dctcp.h
+++ b/net/ipv4/tcp_dctcp.h
@@ -28,7 +28,7 @@ static inline void dctcp_ece_ack_update(struct sock *sk, enum tcp_ca_event evt,
 		 */
 		if (inet_csk(sk)->icsk_ack.pending & ICSK_ACK_TIMER) {
 			dctcp_ece_ack_cwr(sk, *ce_state);
-			__tcp_send_ack(sk, *prior_rcv_nxt);
+			__tcp_send_ack(sk, *prior_rcv_nxt, 0);
 		}
 		inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index fffbd3ee44edc..e0a4e5432399a 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4240,7 +4240,7 @@ void tcp_send_delayed_ack(struct sock *sk)
 }
 
 /* This routine sends an ack and also updates the window. */
-void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
+void __tcp_send_ack(struct sock *sk, u32 rcv_nxt, u16 flags)
 {
 	struct sk_buff *buff;
 
@@ -4269,7 +4269,7 @@ void __tcp_send_ack(struct sock *sk, u32 rcv_nxt)
 
 	/* Reserve space for headers and prepare control bits. */
 	skb_reserve(buff, MAX_TCP_HEADER);
-	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK);
+	tcp_init_nondata_skb(buff, tcp_acceptable_seq(sk), TCPHDR_ACK | flags);
 
 	/* We do not want pure acks influencing TCP Small Queues or fq/pacing
 	 * too much.
@@ -4284,7 +4284,7 @@ EXPORT_SYMBOL_GPL(__tcp_send_ack);
 
 void tcp_send_ack(struct sock *sk)
 {
-	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt);
+	__tcp_send_ack(sk, tcp_sk(sk)->rcv_nxt, 0);
 }
 
 /* This routine sends a packet with an out of date sequence

From dec1277875a5974413068bfb67df7e87e51a189b Mon Sep 17 00:00:00 2001
From: Ard Biesheuvel <ardb@kernel.org>
Date: Mon, 17 Mar 2025 08:23:11 +0100
Subject: [PATCH 2174/2753] efivarfs: use I_MUTEX_CHILD nested lock to traverse
 variables on resume

syzbot warns about a potential deadlock, but this is a false positive
resulting from a missing lockdep annotation: iterate_dir() locks the
parent whereas the inode_lock() it warns about locks the child, which is
guaranteed to be a different lock.

So use inode_lock_nested() instead with the appropriate lock class.

Reported-by: syzbot+019072ad24ab1d948228@syzkaller.appspotmail.com
Suggested-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/super.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 6eae8cf655c12..42295d04f08de 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -421,7 +421,7 @@ static bool efivarfs_actor(struct dir_context *ctx, const char *name, int len,
 	if (err)
 		size = 0;
 
-	inode_lock(inode);
+	inode_lock_nested(inode, I_MUTEX_CHILD);
 	i_size_write(inode, size);
 	inode_unlock(inode);
 

From cc2cc56fc6e6349ba69e37d5706ddada8936c8ff Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Sun, 9 Mar 2025 20:07:41 +0200
Subject: [PATCH 2175/2753] net/mlx5: fs, add API for sharing HWS action by
 refcount

Counters HWS actions are shared using refcount, to create action on
demand by flow steering rule and destroy only when no rules are using
the action. The method is extensible to other HWS action types, such as
flow meter and sampler actions, in the downstream patches.

Add an API to facilitate the reuse of get/put logic for HWS actions
shared by refcount.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1741543663-22123-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/fs_core.h |  8 +--
 .../mellanox/mlx5/core/steering/hws/fs_hws.c  | 57 +++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/fs_hws.h  | 17 ++++++
 .../mlx5/core/steering/hws/fs_hws_pools.c     | 41 ++-----------
 4 files changed, 81 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
index dbe747e938415..0767239f651ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h
@@ -347,16 +347,10 @@ struct mlx5_fc {
 	u64 lastbytes;
 };
 
-struct mlx5_fc_bulk_hws_data {
-	struct mlx5hws_action *hws_action;
-	struct mutex lock; /* protects hws_action */
-	refcount_t hws_action_refcount;
-};
-
 struct mlx5_fc_bulk {
 	struct mlx5_fs_bulk fs_bulk;
 	u32 base_id;
-	struct mlx5_fc_bulk_hws_data hws_data;
+	struct mlx5_fs_hws_data hws_data;
 	struct mlx5_fc fcs[];
 };
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index f34bbbbba1c2a..50e43d574e0aa 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -519,6 +519,63 @@ mlx5_fs_create_action_last(struct mlx5hws_context *ctx)
 	return mlx5hws_action_create_last(ctx, flags);
 }
 
+static struct mlx5hws_action *
+mlx5_fs_create_hws_action(struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+
+	switch (create_ctx->actions_type) {
+	case MLX5HWS_ACTION_TYP_CTR:
+		return mlx5hws_action_create_counter(create_ctx->hws_ctx,
+						     create_ctx->id, flags);
+	default:
+		return NULL;
+	}
+}
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx)
+{
+	/* try avoid locking if not necessary */
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount))
+		return fs_hws_data->hws_action;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (refcount_inc_not_zero(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return fs_hws_data->hws_action;
+	}
+	fs_hws_data->hws_action = mlx5_fs_create_hws_action(create_ctx);
+	if (!fs_hws_data->hws_action) {
+		mutex_unlock(&fs_hws_data->lock);
+		return NULL;
+	}
+	refcount_set(&fs_hws_data->hws_action_refcount, 1);
+	mutex_unlock(&fs_hws_data->lock);
+
+	return fs_hws_data->hws_action;
+}
+
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data)
+{
+	if (!fs_hws_data)
+		return;
+
+	/* try avoid locking if not necessary */
+	if (refcount_dec_not_one(&fs_hws_data->hws_action_refcount))
+		return;
+
+	mutex_lock(&fs_hws_data->lock);
+	if (!refcount_dec_and_test(&fs_hws_data->hws_action_refcount)) {
+		mutex_unlock(&fs_hws_data->lock);
+		return;
+	}
+	mlx5hws_action_destroy(fs_hws_data->hws_action);
+	fs_hws_data->hws_action = NULL;
+	mutex_unlock(&fs_hws_data->lock);
+}
+
 static void mlx5_fs_destroy_fs_action(struct mlx5_fs_hws_rule_action *fs_action)
 {
 	switch (mlx5hws_action_get_type(fs_action->action)) {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
index cbddb72d43624..1c4b853cf88d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -58,6 +58,23 @@ struct mlx5_fs_hws_rule {
 	int num_fs_actions;
 };
 
+struct mlx5_fs_hws_data {
+	struct mlx5hws_action *hws_action;
+	struct mutex lock; /* protects hws_action */
+	refcount_t hws_action_refcount;
+};
+
+struct mlx5_fs_hws_create_action_ctx {
+	enum mlx5hws_action_type actions_type;
+	struct mlx5hws_context *hws_ctx;
+	u32 id;
+};
+
+struct mlx5hws_action *
+mlx5_fs_get_hws_action(struct mlx5_fs_hws_data *fs_hws_data,
+		       struct mlx5_fs_hws_create_action_ctx *create_ctx);
+void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data);
+
 #ifdef CONFIG_MLX5_HW_STEERING
 
 bool mlx5_fs_hws_is_supported(struct mlx5_core_dev *dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
index 2ae4ac62b0e26..f1ecdba74e1f4 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws_pools.c
@@ -405,46 +405,17 @@ bool mlx5_fs_hws_mh_pool_match(struct mlx5_fs_pool *mh_pool,
 struct mlx5hws_action *mlx5_fc_get_hws_action(struct mlx5hws_context *ctx,
 					      struct mlx5_fc *counter)
 {
-	u32 flags = MLX5HWS_ACTION_FLAG_HWS_FDB | MLX5HWS_ACTION_FLAG_SHARED;
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
 	struct mlx5_fc_bulk *fc_bulk = counter->bulk;
-	struct mlx5_fc_bulk_hws_data *fc_bulk_hws;
 
-	fc_bulk_hws = &fc_bulk->hws_data;
-	/* try avoid locking if not necessary */
-	if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount))
-		return fc_bulk_hws->hws_action;
+	create_ctx.hws_ctx = ctx;
+	create_ctx.id = fc_bulk->base_id;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_CTR;
 
-	mutex_lock(&fc_bulk_hws->lock);
-	if (refcount_inc_not_zero(&fc_bulk_hws->hws_action_refcount)) {
-		mutex_unlock(&fc_bulk_hws->lock);
-		return fc_bulk_hws->hws_action;
-	}
-	fc_bulk_hws->hws_action =
-		mlx5hws_action_create_counter(ctx, fc_bulk->base_id, flags);
-	if (!fc_bulk_hws->hws_action) {
-		mutex_unlock(&fc_bulk_hws->lock);
-		return NULL;
-	}
-	refcount_set(&fc_bulk_hws->hws_action_refcount, 1);
-	mutex_unlock(&fc_bulk_hws->lock);
-
-	return fc_bulk_hws->hws_action;
+	return mlx5_fs_get_hws_action(&fc_bulk->hws_data, &create_ctx);
 }
 
 void mlx5_fc_put_hws_action(struct mlx5_fc *counter)
 {
-	struct mlx5_fc_bulk_hws_data *fc_bulk_hws = &counter->bulk->hws_data;
-
-	/* try avoid locking if not necessary */
-	if (refcount_dec_not_one(&fc_bulk_hws->hws_action_refcount))
-		return;
-
-	mutex_lock(&fc_bulk_hws->lock);
-	if (!refcount_dec_and_test(&fc_bulk_hws->hws_action_refcount)) {
-		mutex_unlock(&fc_bulk_hws->lock);
-		return;
-	}
-	mlx5hws_action_destroy(fc_bulk_hws->hws_action);
-	fc_bulk_hws->hws_action = NULL;
-	mutex_unlock(&fc_bulk_hws->lock);
+	mlx5_fs_put_hws_action(&counter->bulk->hws_data);
 }

From 82d3639ef7dc54d5b5cb454d9a13005202d7a701 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Sun, 9 Mar 2025 20:07:42 +0200
Subject: [PATCH 2176/2753] net/mlx5: fs, add support for flow meters HWS
 action

Add support for HW Steering action of flow meter range. Flow meters
range can use one HWS action for the whole range. Thus, share a cached
HWS action among rules that use same flow meter object range. Hold
refcount for each rule using the cached action.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1741543663-22123-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/mellanox/mlx5/core/en/tc/meter.c |   5 +
 .../ethernet/mellanox/mlx5/core/en/tc/meter.h |  13 ++
 .../mellanox/mlx5/core/eswitch_offloads.c     |   1 +
 .../mellanox/mlx5/core/steering/hws/fs_hws.c  | 120 ++++++++++++++++--
 .../mellanox/mlx5/core/steering/hws/fs_hws.h  |   5 +
 include/linux/mlx5/fs.h                       |   1 +
 6 files changed, 135 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
index 8218c892b1617..7819fb2972802 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.c
@@ -593,3 +593,8 @@ mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 	*drops = packets2;
 	*lastuse = max_t(u64, lastuse1, lastuse2);
 }
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return meter->meters_obj->base_id;
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
index 9b795cd106bbe..d6afb6556875c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/meter.h
@@ -72,4 +72,17 @@ void
 mlx5e_tc_meter_get_stats(struct mlx5e_flow_meter_handle *meter,
 			 u64 *bytes, u64 *packets, u64 *drops, u64 *lastuse);
 
+#if IS_ENABLED(CONFIG_MLX5_CLS_ACT)
+
+int mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter);
+
+#else /* CONFIG_MLX5_CLS_ACT */
+
+static inline int
+mlx5e_flow_meter_get_base_id(struct mlx5e_flow_meter_handle *meter)
+{
+	return 0;
+}
+#endif /* CONFIG_MLX5_CLS_ACT */
+
 #endif /* __MLX5_EN_FLOW_METER_H__ */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
index 8987f17e485c9..a6a8eea5980ca 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c
@@ -648,6 +648,7 @@ esw_setup_meter(struct mlx5_flow_attr *attr, struct mlx5_flow_act *flow_act)
 	meter = attr->meter_attr.meter;
 	flow_act->exe_aso.type = attr->exe_aso_type;
 	flow_act->exe_aso.object_id = meter->obj_id;
+	flow_act->exe_aso.base_id = mlx5e_flow_meter_get_base_id(meter);
 	flow_act->exe_aso.flow_meter.meter_idx = meter->idx;
 	flow_act->exe_aso.flow_meter.init_color = MLX5_FLOW_METER_COLOR_GREEN;
 	/* use metadata reg 5 for packet color */
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index 50e43d574e0aa..edf7db1e6e9c8 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -66,6 +66,7 @@ static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev,
 	xa_init(&hws_pool->table_dests);
 	xa_init(&hws_pool->vport_dests);
 	xa_init(&hws_pool->vport_vhca_dests);
+	xa_init(&hws_pool->aso_meters);
 	return 0;
 
 cleanup_insert_hdr:
@@ -88,10 +89,14 @@ static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev,
 static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx)
 {
 	struct mlx5_fs_hws_actions_pool *hws_pool = &fs_ctx->hws_pool;
+	struct mlx5_fs_hws_data *fs_hws_data;
 	struct mlx5hws_action *action;
 	struct mlx5_fs_pool *pool;
 	unsigned long i;
 
+	xa_for_each(&hws_pool->aso_meters, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->aso_meters);
 	xa_for_each(&hws_pool->vport_vhca_dests, i, action)
 		mlx5hws_action_destroy(action);
 	xa_destroy(&hws_pool->vport_vhca_dests);
@@ -459,6 +464,70 @@ mlx5_fs_create_dest_action_range(struct mlx5hws_context *ctx,
 						      flags);
 }
 
+static struct mlx5_fs_hws_data *
+mlx5_fs_get_cached_hws_data(struct xarray *cache_xa, unsigned long index)
+{
+	struct mlx5_fs_hws_data *fs_hws_data;
+	int err;
+
+	xa_lock(cache_xa);
+	fs_hws_data = xa_load(cache_xa, index);
+	if (!fs_hws_data) {
+		fs_hws_data = kzalloc(sizeof(*fs_hws_data), GFP_ATOMIC);
+		if (!fs_hws_data) {
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+		refcount_set(&fs_hws_data->hws_action_refcount, 0);
+		mutex_init(&fs_hws_data->lock);
+		err = __xa_insert(cache_xa, index, fs_hws_data, GFP_ATOMIC);
+		if (err) {
+			kfree(fs_hws_data);
+			xa_unlock(cache_xa);
+			return NULL;
+		}
+	}
+	xa_unlock(cache_xa);
+
+	return fs_hws_data;
+}
+
+static struct mlx5hws_action *
+mlx5_fs_get_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+			     struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *meter_hws_data;
+	u32 id = exe_aso->base_id;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = mlx5_fs_get_cached_hws_data(meters_xa, id);
+	if (!meter_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_ASO_METER;
+	create_ctx.id = id;
+	create_ctx.return_reg_id = exe_aso->return_reg_id;
+
+	return mlx5_fs_get_hws_action(meter_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
+					 struct mlx5_exe_aso *exe_aso)
+{
+	struct mlx5_fs_hws_data *meter_hws_data;
+	struct xarray *meters_xa;
+
+	meters_xa = &fs_ctx->hws_pool.aso_meters;
+	meter_hws_data = xa_load(meters_xa, exe_aso->base_id);
+	if (!meter_hws_data)
+		return;
+	return mlx5_fs_put_hws_action(meter_hws_data);
+}
+
 static struct mlx5hws_action *
 mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx,
 				 struct mlx5hws_action_dest_attr *dests,
@@ -528,6 +597,11 @@ mlx5_fs_create_hws_action(struct mlx5_fs_hws_create_action_ctx *create_ctx)
 	case MLX5HWS_ACTION_TYP_CTR:
 		return mlx5hws_action_create_counter(create_ctx->hws_ctx,
 						     create_ctx->id, flags);
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		return mlx5hws_action_create_aso_meter(create_ctx->hws_ctx,
+						       create_ctx->id,
+						       create_ctx->return_reg_id,
+						       flags);
 	default:
 		return NULL;
 	}
@@ -576,26 +650,33 @@ void mlx5_fs_put_hws_action(struct mlx5_fs_hws_data *fs_hws_data)
 	mutex_unlock(&fs_hws_data->lock);
 }
 
-static void mlx5_fs_destroy_fs_action(struct mlx5_fs_hws_rule_action *fs_action)
+static void mlx5_fs_destroy_fs_action(struct mlx5_flow_root_namespace *ns,
+				      struct mlx5_fs_hws_rule_action *fs_action)
 {
+	struct mlx5_fs_hws_context *fs_ctx = &ns->fs_hws_context;
+
 	switch (mlx5hws_action_get_type(fs_action->action)) {
 	case MLX5HWS_ACTION_TYP_CTR:
 		mlx5_fc_put_hws_action(fs_action->counter);
 		break;
+	case MLX5HWS_ACTION_TYP_ASO_METER:
+		mlx5_fs_put_action_aso_meter(fs_ctx, fs_action->exe_aso);
+		break;
 	default:
 		mlx5hws_action_destroy(fs_action->action);
 	}
 }
 
 static void
-mlx5_fs_destroy_fs_actions(struct mlx5_fs_hws_rule_action **fs_actions,
+mlx5_fs_destroy_fs_actions(struct mlx5_flow_root_namespace *ns,
+			   struct mlx5_fs_hws_rule_action **fs_actions,
 			   int *num_fs_actions)
 {
 	int i;
 
 	/* Free in reverse order to handle action dependencies */
 	for (i = *num_fs_actions - 1; i >= 0; i--)
-		mlx5_fs_destroy_fs_action(*fs_actions + i);
+		mlx5_fs_destroy_fs_action(ns, *fs_actions + i);
 	*num_fs_actions = 0;
 	kfree(*fs_actions);
 	*fs_actions = NULL;
@@ -792,8 +873,25 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 	}
 
 	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_EXECUTE_ASO) {
-		err = -EOPNOTSUPP;
-		goto free_actions;
+		if (fte_action->exe_aso.type != MLX5_EXE_ASO_FLOW_METER ||
+		    num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) {
+			err = -EOPNOTSUPP;
+			goto free_actions;
+		}
+
+		tmp_action = mlx5_fs_get_action_aso_meter(fs_ctx,
+							  &fte_action->exe_aso);
+		if (!tmp_action) {
+			err = -ENOMEM;
+			goto free_actions;
+		}
+		(*ractions)[num_actions].aso_meter.offset =
+			fte_action->exe_aso.flow_meter.meter_idx;
+		(*ractions)[num_actions].aso_meter.init_color =
+			fte_action->exe_aso.flow_meter.init_color;
+		(*ractions)[num_actions++].action = tmp_action;
+		fs_actions[num_fs_actions].action = tmp_action;
+		fs_actions[num_fs_actions++].exe_aso = &fte_action->exe_aso;
 	}
 
 	if (fte_action->action & MLX5_FLOW_CONTEXT_ACTION_DROP) {
@@ -907,7 +1005,7 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 	return 0;
 
 free_actions:
-	mlx5_fs_destroy_fs_actions(&fs_actions, &num_fs_actions);
+	mlx5_fs_destroy_fs_actions(ns, &fs_actions, &num_fs_actions);
 free_dest_actions_alloc:
 	kfree(dest_actions);
 free_fs_actions_alloc:
@@ -957,7 +1055,7 @@ static int mlx5_cmd_hws_create_fte(struct mlx5_flow_root_namespace *ns,
 	return 0;
 
 free_actions:
-	mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions,
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
 				   &fte->fs_hws_rule.num_fs_actions);
 out_err:
 	mlx5_core_err(ns->dev, "Failed to create hws rule err(%d)\n", err);
@@ -977,7 +1075,8 @@ static int mlx5_cmd_hws_delete_fte(struct mlx5_flow_root_namespace *ns,
 	err = mlx5hws_bwc_rule_destroy(rule->bwc_rule);
 	rule->bwc_rule = NULL;
 
-	mlx5_fs_destroy_fs_actions(&rule->hws_fs_actions, &rule->num_fs_actions);
+	mlx5_fs_destroy_fs_actions(ns, &rule->hws_fs_actions,
+				   &rule->num_fs_actions);
 
 	return err;
 }
@@ -1015,11 +1114,12 @@ static int mlx5_cmd_hws_update_fte(struct mlx5_flow_root_namespace *ns,
 	if (ret)
 		goto restore_actions;
 
-	mlx5_fs_destroy_fs_actions(&saved_hws_fs_actions, &saved_num_fs_actions);
+	mlx5_fs_destroy_fs_actions(ns, &saved_hws_fs_actions,
+				   &saved_num_fs_actions);
 	return ret;
 
 restore_actions:
-	mlx5_fs_destroy_fs_actions(&fte->fs_hws_rule.hws_fs_actions,
+	mlx5_fs_destroy_fs_actions(ns, &fte->fs_hws_rule.hws_fs_actions,
 				   &fte->fs_hws_rule.num_fs_actions);
 	fte->fs_hws_rule.hws_fs_actions = saved_hws_fs_actions;
 	fte->fs_hws_rule.num_fs_actions = saved_num_fs_actions;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
index 1c4b853cf88d3..6970b1aa9540b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -22,6 +22,7 @@ struct mlx5_fs_hws_actions_pool {
 	struct xarray table_dests;
 	struct xarray vport_vhca_dests;
 	struct xarray vport_dests;
+	struct xarray aso_meters;
 };
 
 struct mlx5_fs_hws_context {
@@ -49,6 +50,7 @@ struct mlx5_fs_hws_rule_action {
 	struct mlx5hws_action *action;
 	union {
 		struct mlx5_fc *counter;
+		struct mlx5_exe_aso *exe_aso;
 	};
 };
 
@@ -68,6 +70,9 @@ struct mlx5_fs_hws_create_action_ctx {
 	enum mlx5hws_action_type actions_type;
 	struct mlx5hws_context *hws_ctx;
 	u32 id;
+	union {
+		u8 return_reg_id;
+	};
 };
 
 struct mlx5hws_action *
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index fd62b2b1611d6..939e58c2f3865 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -244,6 +244,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
 
 struct mlx5_exe_aso {
 	u32 object_id;
+	int base_id;
 	u8 type;
 	u8 return_reg_id;
 	union {

From 32e658c84b6d63003167db2dd6863e945cadb723 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Sun, 9 Mar 2025 20:07:43 +0200
Subject: [PATCH 2177/2753] net/mlx5: fs, add support for dest flow sampler HWS
 action

Add support for HW Steering action of flow sampler destination. For each
flow sampler created cache the hws action by sampler id as a key. Hold
refcount for each rule using the cached action.

Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/1741543663-22123-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../mellanox/mlx5/core/steering/hws/fs_hws.c  | 54 +++++++++++++++++++
 .../mellanox/mlx5/core/steering/hws/fs_hws.h  |  2 +
 2 files changed, 56 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
index edf7db1e6e9c8..1b787cd66e6fd 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.c
@@ -67,6 +67,7 @@ static int mlx5_fs_init_hws_actions_pool(struct mlx5_core_dev *dev,
 	xa_init(&hws_pool->vport_dests);
 	xa_init(&hws_pool->vport_vhca_dests);
 	xa_init(&hws_pool->aso_meters);
+	xa_init(&hws_pool->sample_dests);
 	return 0;
 
 cleanup_insert_hdr:
@@ -94,6 +95,9 @@ static void mlx5_fs_cleanup_hws_actions_pool(struct mlx5_fs_hws_context *fs_ctx)
 	struct mlx5_fs_pool *pool;
 	unsigned long i;
 
+	xa_for_each(&hws_pool->sample_dests, i, fs_hws_data)
+		kfree(fs_hws_data);
+	xa_destroy(&hws_pool->sample_dests);
 	xa_for_each(&hws_pool->aso_meters, i, fs_hws_data)
 		kfree(fs_hws_data);
 	xa_destroy(&hws_pool->aso_meters);
@@ -528,6 +532,42 @@ static void mlx5_fs_put_action_aso_meter(struct mlx5_fs_hws_context *fs_ctx,
 	return mlx5_fs_put_hws_action(meter_hws_data);
 }
 
+static struct mlx5hws_action *
+mlx5_fs_get_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+				struct mlx5_flow_rule *dst)
+{
+	struct mlx5_fs_hws_create_action_ctx create_ctx;
+	struct mlx5hws_context *ctx = fs_ctx->hws_ctx;
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	u32 id = dst->dest_attr.sampler_id;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = mlx5_fs_get_cached_hws_data(sampler_xa, id);
+	if (!sampler_hws_data)
+		return NULL;
+
+	create_ctx.hws_ctx = ctx;
+	create_ctx.actions_type = MLX5HWS_ACTION_TYP_SAMPLER;
+	create_ctx.id = id;
+
+	return mlx5_fs_get_hws_action(sampler_hws_data, &create_ctx);
+}
+
+static void mlx5_fs_put_dest_action_sampler(struct mlx5_fs_hws_context *fs_ctx,
+					    u32 sampler_id)
+{
+	struct mlx5_fs_hws_data *sampler_hws_data;
+	struct xarray *sampler_xa;
+
+	sampler_xa = &fs_ctx->hws_pool.sample_dests;
+	sampler_hws_data = xa_load(sampler_xa, sampler_id);
+	if (!sampler_hws_data)
+		return;
+
+	mlx5_fs_put_hws_action(sampler_hws_data);
+}
+
 static struct mlx5hws_action *
 mlx5_fs_create_action_dest_array(struct mlx5hws_context *ctx,
 				 struct mlx5hws_action_dest_attr *dests,
@@ -602,6 +642,9 @@ mlx5_fs_create_hws_action(struct mlx5_fs_hws_create_action_ctx *create_ctx)
 						       create_ctx->id,
 						       create_ctx->return_reg_id,
 						       flags);
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		return mlx5hws_action_create_flow_sampler(create_ctx->hws_ctx,
+							  create_ctx->id, flags);
 	default:
 		return NULL;
 	}
@@ -662,6 +705,9 @@ static void mlx5_fs_destroy_fs_action(struct mlx5_flow_root_namespace *ns,
 	case MLX5HWS_ACTION_TYP_ASO_METER:
 		mlx5_fs_put_action_aso_meter(fs_ctx, fs_action->exe_aso);
 		break;
+	case MLX5HWS_ACTION_TYP_SAMPLER:
+		mlx5_fs_put_dest_action_sampler(fs_ctx, fs_action->sampler_id);
+		break;
 	default:
 		mlx5hws_action_destroy(fs_action->action);
 	}
@@ -939,6 +985,14 @@ static int mlx5_fs_fte_get_hws_actions(struct mlx5_flow_root_namespace *ns,
 				dest_action = mlx5_fs_get_dest_action_vport(fs_ctx, dst,
 									    type_uplink);
 				break;
+			case MLX5_FLOW_DESTINATION_TYPE_FLOW_SAMPLER:
+				dest_action =
+					mlx5_fs_get_dest_action_sampler(fs_ctx,
+									dst);
+				fs_actions[num_fs_actions].action = dest_action;
+				fs_actions[num_fs_actions++].sampler_id =
+							dst->dest_attr.sampler_id;
+				break;
 			default:
 				err = -EOPNOTSUPP;
 				goto free_actions;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
index 6970b1aa9540b..8b56298288da2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/fs_hws.h
@@ -23,6 +23,7 @@ struct mlx5_fs_hws_actions_pool {
 	struct xarray vport_vhca_dests;
 	struct xarray vport_dests;
 	struct xarray aso_meters;
+	struct xarray sample_dests;
 };
 
 struct mlx5_fs_hws_context {
@@ -51,6 +52,7 @@ struct mlx5_fs_hws_rule_action {
 	union {
 		struct mlx5_fc *counter;
 		struct mlx5_exe_aso *exe_aso;
+		u32 sampler_id;
 	};
 };
 

From 43e2aa56aea2e292c209cfd77c3f2d8553fb66e9 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 9 Mar 2025 21:04:14 +0100
Subject: [PATCH 2178/2753] net: phy: move PHY package MMD access function
 declarations from phy.h to phylib.h

These functions are used by PHY drivers only, therefore move their
declaration to phylib.h.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/406c8a20-b62e-4ee3-b174-b566724a0876@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylib.h | 6 ++++++
 include/linux/phy.h      | 8 --------
 2 files changed, 6 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/phylib.h b/drivers/net/phy/phylib.h
index f0e499fed1f71..c15484a805b39 100644
--- a/drivers/net/phy/phylib.h
+++ b/drivers/net/phy/phylib.h
@@ -15,6 +15,12 @@ int __phy_package_read(struct phy_device *phydev, unsigned int addr_offset,
 		       u32 regnum);
 int __phy_package_write(struct phy_device *phydev, unsigned int addr_offset,
 			u32 regnum, u16 val);
+int __phy_package_read_mmd(struct phy_device *phydev,
+			   unsigned int addr_offset, int devad,
+			   u32 regnum);
+int __phy_package_write_mmd(struct phy_device *phydev,
+			    unsigned int addr_offset, int devad,
+			    u32 regnum, u16 val);
 bool phy_package_init_once(struct phy_device *phydev);
 bool phy_package_probe_once(struct phy_device *phydev);
 int phy_package_join(struct phy_device *phydev, int base_addr, size_t priv_size);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index c4a6385faf41c..fc028bab10b7d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2107,18 +2107,10 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct kernel_hwtstamp_config *config,
 		       struct netlink_ext_ack *extack);
 
-int __phy_package_read_mmd(struct phy_device *phydev,
-			   unsigned int addr_offset, int devad,
-			   u32 regnum);
-
 int phy_package_read_mmd(struct phy_device *phydev,
 			 unsigned int addr_offset, int devad,
 			 u32 regnum);
 
-int __phy_package_write_mmd(struct phy_device *phydev,
-			    unsigned int addr_offset, int devad,
-			    u32 regnum, u16 val);
-
 int phy_package_write_mmd(struct phy_device *phydev,
 			  unsigned int addr_offset, int devad,
 			  u32 regnum, u16 val);

From 8ea221b22172a2cc5d0edbfec4b34ef3fe8de167 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sun, 9 Mar 2025 21:05:08 +0100
Subject: [PATCH 2179/2753] net: phy: remove unused functions
 phy_package_[read|write]_mmd

These functions have never had a user, so remove them.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/5792e2cd-6f0a-4f7d-a5ef-b932f94d82f3@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-core.c | 75 --------------------------------------
 include/linux/phy.h        |  8 ----
 2 files changed, 83 deletions(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 154d29be6293a..31ed1ce3b62f1 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -734,43 +734,6 @@ int __phy_package_read_mmd(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(__phy_package_read_mmd);
 
-/**
- * phy_package_read_mmd - read MMD reg relative to PHY package base addr
- * @phydev: The phy_device struct
- * @addr_offset: The offset to be added to PHY package base_addr
- * @devad: The MMD to read from
- * @regnum: The register on the MMD to read
- *
- * Convenience helper for reading a register of an MMD on a given PHY
- * using the PHY package base address. The base address is added to
- * the addr_offset value.
- *
- * Same calling rules as for phy_read();
- *
- * NOTE: It's assumed that the entire PHY package is either C22 or C45.
- */
-int phy_package_read_mmd(struct phy_device *phydev,
-			 unsigned int addr_offset, int devad,
-			 u32 regnum)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-	int val;
-
-	if (addr < 0)
-		return addr;
-
-	if (regnum > (u16)~0 || devad > 32)
-		return -EINVAL;
-
-	phy_lock_mdio_bus(phydev);
-	val = mmd_phy_read(phydev->mdio.bus, addr, phydev->is_c45, devad,
-			   regnum);
-	phy_unlock_mdio_bus(phydev);
-
-	return val;
-}
-EXPORT_SYMBOL(phy_package_read_mmd);
-
 /**
  * __phy_package_write_mmd - write MMD reg relative to PHY package base addr
  * @phydev: The phy_device struct
@@ -804,44 +767,6 @@ int __phy_package_write_mmd(struct phy_device *phydev,
 }
 EXPORT_SYMBOL(__phy_package_write_mmd);
 
-/**
- * phy_package_write_mmd - write MMD reg relative to PHY package base addr
- * @phydev: The phy_device struct
- * @addr_offset: The offset to be added to PHY package base_addr
- * @devad: The MMD to write to
- * @regnum: The register on the MMD to write
- * @val: value to write to @regnum
- *
- * Convenience helper for writing a register of an MMD on a given PHY
- * using the PHY package base address. The base address is added to
- * the addr_offset value.
- *
- * Same calling rules as for phy_write();
- *
- * NOTE: It's assumed that the entire PHY package is either C22 or C45.
- */
-int phy_package_write_mmd(struct phy_device *phydev,
-			  unsigned int addr_offset, int devad,
-			  u32 regnum, u16 val)
-{
-	int addr = phy_package_address(phydev, addr_offset);
-	int ret;
-
-	if (addr < 0)
-		return addr;
-
-	if (regnum > (u16)~0 || devad > 32)
-		return -EINVAL;
-
-	phy_lock_mdio_bus(phydev);
-	ret = mmd_phy_write(phydev->mdio.bus, addr, phydev->is_c45, devad,
-			    regnum, val);
-	phy_unlock_mdio_bus(phydev);
-
-	return ret;
-}
-EXPORT_SYMBOL(phy_package_write_mmd);
-
 /**
  * phy_modify_changed - Function for modifying a PHY register
  * @phydev: the phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index fc028bab10b7d..61a8cb9d12477 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2107,14 +2107,6 @@ int __phy_hwtstamp_set(struct phy_device *phydev,
 		       struct kernel_hwtstamp_config *config,
 		       struct netlink_ext_ack *extack);
 
-int phy_package_read_mmd(struct phy_device *phydev,
-			 unsigned int addr_offset, int devad,
-			 u32 regnum);
-
-int phy_package_write_mmd(struct phy_device *phydev,
-			  unsigned int addr_offset, int devad,
-			  u32 regnum, u16 val);
-
 extern const struct bus_type mdio_bus_type;
 
 struct mdio_board_info {

From 38f13bf801303a38316a12e06dbfc6fdc410f8ed Mon Sep 17 00:00:00 2001
From: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Date: Mon, 10 Mar 2025 13:08:35 +0800
Subject: [PATCH 2180/2753] stmmac: intel: Fix warning message for return value
 in intel_tsn_lane_is_available()

Fix the warning "warn: missing error code? 'ret'" in the
intel_tsn_lane_is_available() function.

The function now returns 0 to indicate that a TSN lane was found and
returns -EINVAL when it is not found.

Fixes: a42f6b3f1cc1 ("net: stmmac: configure SerDes according to the interface mode")
Signed-off-by: Choong Yong Liang <yong.liang.choong@linux.intel.com>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250310050835.808870-1-yong.liang.choong@linux.intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
index 9c8de47ee149f..5910571a954f9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-intel.c
@@ -494,10 +494,10 @@ static int intel_tsn_lane_is_available(struct net_device *ndev,
 			if ((rbuf.buf[0] >>
 				(4 * (intel_priv->tsn_lane_regs[j] % 8)) &
 					B_PCH_FIA_PCR_L0O) == 0xB)
-				return ret;
+				return 0;
 	}
 
-	return ret;
+	return -EINVAL;
 }
 
 static int intel_set_reg_access(const struct pmc_serdes_regs *regs, int max_regs)

From a07f23ad9baf716cbf7746e452c92960536ceae6 Mon Sep 17 00:00:00 2001
From: Philipp Hahn <phahn-oss@avm.de>
Date: Mon, 10 Mar 2025 11:17:35 +0100
Subject: [PATCH 2181/2753] cdc_ether|r8152: ThinkPad Hybrid USB-C/A Dock quirk

Lenovo ThinkPad Hybrid USB-C with USB-A Dock (17ef:a359) is affected by
the same problem as the Lenovo Powered USB-C Travel Hub (17ef:721e):
Both are based on the Realtek RTL8153B chip used to use the cdc_ether
driver. However, using this driver, with the system suspended the device
constantly sends pause-frames as soon as the receive buffer fills up.
This causes issues with other devices, where some Ethernet switches stop
forwarding packets altogether.

Using the Realtek driver (r8152) fixes this issue. Pause frames are no
longer sent while the host system is suspended.

Cc: Leon Schuermann <leon@is.currently.online>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Oliver Neukum <oliver@neukum.org> (maintainer:USB CDC ETHERNET DRIVER)
Cc: netdev@vger.kernel.org (open list:NETWORKING DRIVERS)
Link: https://git.kernel.org/netdev/net/c/cb82a54904a9
Link: https://git.kernel.org/netdev/net/c/2284bbd0cf39
Link: https://www.lenovo.com/de/de/p/accessories-and-software/docking/docking-usb-docks/40af0135eu
Signed-off-by: Philipp Hahn <phahn-oss@avm.de>
Reviewed-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/484336aad52d14ccf061b535bc19ef6396ef5120.1741601523.git.p.hahn@avm.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/usb/cdc_ether.c | 7 +++++++
 drivers/net/usb/r8152.c     | 6 ++++++
 drivers/net/usb/r8153_ecm.c | 6 ++++++
 3 files changed, 19 insertions(+)

diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c
index a6469235d904e..a032c1ded4063 100644
--- a/drivers/net/usb/cdc_ether.c
+++ b/drivers/net/usb/cdc_ether.c
@@ -783,6 +783,13 @@ static const struct usb_device_id	products[] = {
 	.driver_info = 0,
 },
 
+/* Lenovo ThinkPad Hybrid USB-C with USB-A Dock (40af0135eu, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(LENOVO_VENDOR_ID, 0xa359, USB_CLASS_COMM,
+			USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = 0,
+},
+
 /* Aquantia AQtion USB to 5GbE Controller (based on AQC111U) */
 {
 	USB_DEVICE_AND_INTERFACE_INFO(AQUANTIA_VENDOR_ID, 0xc101,
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index e1021148d3a69..2cab046749a92 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -785,6 +785,7 @@ enum rtl8152_flags {
 #define DEVICE_ID_THINKPAD_USB_C_DONGLE			0x720c
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2		0xa387
 #define DEVICE_ID_THINKPAD_USB_C_DOCK_GEN3		0x3062
+#define DEVICE_ID_THINKPAD_HYBRID_USB_C_DOCK		0xa359
 
 struct tally_counter {
 	__le64	tx_packets;
@@ -9787,6 +9788,7 @@ static bool rtl8152_supports_lenovo_macpassthru(struct usb_device *udev)
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN2:
 		case DEVICE_ID_THINKPAD_USB_C_DOCK_GEN3:
 		case DEVICE_ID_THINKPAD_USB_C_DONGLE:
+		case DEVICE_ID_THINKPAD_HYBRID_USB_C_DOCK:
 			return 1;
 		}
 	} else if (vendor_id == VENDOR_ID_REALTEK && parent_vendor_id == VENDOR_ID_LENOVO) {
@@ -10064,6 +10066,8 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0927) },
 	{ USB_DEVICE(VENDOR_ID_MICROSOFT, 0x0c5e) },
 	{ USB_DEVICE(VENDOR_ID_SAMSUNG, 0xa101) },
+
+	/* Lenovo */
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x304f) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x3054) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x3062) },
@@ -10074,7 +10078,9 @@ static const struct usb_device_id rtl8152_table[] = {
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x720c) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x7214) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0x721e) },
+	{ USB_DEVICE(VENDOR_ID_LENOVO,  0xa359) },
 	{ USB_DEVICE(VENDOR_ID_LENOVO,  0xa387) },
+
 	{ USB_DEVICE(VENDOR_ID_LINKSYS, 0x0041) },
 	{ USB_DEVICE(VENDOR_ID_NVIDIA,  0x09ff) },
 	{ USB_DEVICE(VENDOR_ID_TPLINK,  0x0601) },
diff --git a/drivers/net/usb/r8153_ecm.c b/drivers/net/usb/r8153_ecm.c
index 20b2df8d74ae1..8d860dacdf49b 100644
--- a/drivers/net/usb/r8153_ecm.c
+++ b/drivers/net/usb/r8153_ecm.c
@@ -135,6 +135,12 @@ static const struct usb_device_id products[] = {
 				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
 	.driver_info = (unsigned long)&r8153_info,
 },
+/* Lenovo ThinkPad Hybrid USB-C with USB-A Dock (40af0135eu, based on Realtek RTL8153) */
+{
+	USB_DEVICE_AND_INTERFACE_INFO(VENDOR_ID_LENOVO, 0xa359, USB_CLASS_COMM,
+				      USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE),
+	.driver_info = (unsigned long)&r8153_info,
+},
 
 	{ },		/* END */
 };

From 35b862eac9099bb492229627c44e541633fb5938 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Mar 2025 11:10:52 +0000
Subject: [PATCH 2182/2753] net: phylink: expand on .pcs_config() method
 documentation

Expand on the requirements of the .pcs_config() method documentation,
specifically mentioning that it should cause minimal disruption to
an established link, and that it should return a positive non-zero
value when requiring the .pcs_an_restart() method to be called.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1trb24-005oVq-Is@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/phylink.h | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index c187267a15b6c..79876c84ae814 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -595,6 +595,14 @@ void pcs_get_state(struct phylink_pcs *pcs, unsigned int neg_mode,
  * The %neg_mode argument should be tested via the phylink_mode_*() family of
  * functions, or for PCS that set pcs->neg_mode true, should be tested
  * against the PHYLINK_PCS_NEG_* definitions.
+ *
+ * pcs_config() will be called when configuration of the PCS is required
+ * or when the advertisement is possibly updated. It must not unnecessarily
+ * disrupt an established link.
+ *
+ * When an autonegotiation restart is required for 802.3z modes, .pcs_config()
+ * should return a positive non-zero integer (e.g. 1) to indicate to phylink
+ * to call the pcs_an_restart() method.
  */
 int pcs_config(struct phylink_pcs *pcs, unsigned int neg_mode,
 	       phy_interface_t interface, const unsigned long *advertising,

From 180fa8d0a2cb4c1b0f60cc28ce481407c3c44ffb Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Mar 2025 12:31:25 +0000
Subject: [PATCH 2183/2753] net: stmmac: remove redundant racy tear-down in
 stmmac_dvr_remove()

While the network device is registered, it is published to userspace,
and thus userspace can change its state. This means calling
functions such as stmmac_stop_all_dma() and stmmac_mac_set() are
racy.

Moreover, unregister_netdev() will unpublish the network device, and
then if appropriate call the .ndo_stop() method, which is
stmmac_release(). This will first call phylink_stop() which will
synchronously take the link down, resulting in stmmac_mac_link_down()
and stmmac_mac_set(, false) being called.

stmmac_release() will also call stmmac_stop_all_dma().

Consequently, neither of these two functions need to called prior
to unregister_netdev() as that will safely call paths that will
result in this work being done if necessary.

Remove these redundant racy calls.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Furong Xu <0x1207@gmail.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1trcI1-005rn2-CZ@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index fa1d7d3a2f438..c2ee6c0af3fd8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7768,8 +7768,6 @@ void stmmac_dvr_remove(struct device *dev)
 
 	pm_runtime_get_sync(dev);
 
-	stmmac_stop_all_dma(priv);
-	stmmac_mac_set(priv, priv->ioaddr, false);
 	unregister_netdev(ndev);
 
 #ifdef CONFIG_DEBUG_FS

From 39b0a10d80d6c7573fe94d09635c3931a91065d9 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Mon, 10 Mar 2025 12:31:30 +0000
Subject: [PATCH 2184/2753] net: stmmac: remove unnecessary stmmac_mac_set() in
 stmmac_release()

stmmac_release() calls phylink_stop() and then goes on to call
stmmac_mac_set(, false). However, phylink_stop() will call
stmmac_mac_link_down() before returning, which will do this work.
Remove this unnecessary call.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Tested-by: Furong Xu <0x1207@gmail.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1trcI6-005rn8-GV@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index c2ee6c0af3fd8..839ecebf5f5f3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -4129,9 +4129,6 @@ static int stmmac_release(struct net_device *dev)
 	/* Release and free the Rx/Tx resources */
 	free_dma_desc_resources(priv, &priv->dma_conf);
 
-	/* Disable the MAC Rx/Tx */
-	stmmac_mac_set(priv, priv->ioaddr, false);
-
 	/* Powerdown Serdes if there is */
 	if (priv->plat->serdes_powerdown)
 		priv->plat->serdes_powerdown(dev, priv->plat->bsp_priv);

From 9130945f81613bf1b7103e27accbbea924d97c18 Mon Sep 17 00:00:00 2001
From: "Eric W. Biederman" <ebiederm@xmission.com>
Date: Mon, 17 Mar 2025 08:47:30 -0500
Subject: [PATCH 2185/2753] MAINTAINERS: Remove myself

Unfortunately I no longer have time to meaningfully take part in the
linux kernel development.

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 MAINTAINERS | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 2892988675b8b..16f51eb6ebe82 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8647,7 +8647,6 @@ F:	rust/kernel/net/phy/reg.rs
 
 EXEC & BINFMT API, ELF
 M:	Kees Cook <kees@kernel.org>
-R:	Eric Biederman <ebiederm@xmission.com>
 L:	linux-mm@kvack.org
 S:	Supported
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/execve
@@ -12827,9 +12826,7 @@ F:	fs/kernfs/
 F:	include/linux/kernfs.h
 
 KEXEC
-M:	Eric Biederman <ebiederm@xmission.com>
 L:	kexec@lists.infradead.org
-S:	Maintained
 W:	http://kernel.org/pub/linux/utils/kernel/kexec/
 F:	include/linux/kexec.h
 F:	include/uapi/linux/kexec.h

From 11092db5b57377ac99e6339cfd16ca35ef011f3c Mon Sep 17 00:00:00 2001
From: James Bottomley <James.Bottomley@HansenPartnership.com>
Date: Mon, 17 Mar 2025 23:06:01 -0400
Subject: [PATCH 2186/2753] efivarfs: fix NULL dereference on resume

LSMs often inspect the path.mnt of files in the security hooks, and this
causes a NULL deref in efivarfs_pm_notify() because the path is
constructed with a NULL path.mnt.

Fix by obtaining from vfs_kern_mount() instead, and being very careful
to ensure that deactivate_super() (potentially triggered by a racing
userspace umount) is not called directly from the notifier, because it
would deadlock when efivarfs_kill_sb() tried to unregister the notifier
chain.

[ Al notes:
	Umm...  That's probably safe, but not as a long-term solution -
	it's too intimately dependent upon fs/super.c internals. The
	reasons why you can't run into ->s_umount deadlock here are
	non-trivial... ]

Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>
Link: https://lore.kernel.org/r/e54e6a2f-1178-4980-b771-4d9bafc2aa47@tnxip.de
Link: https://lore.kernel.org/r/3e998bf87638a442cbc6864cdcd3d8d9e08ce3e3.camel@HansenPartnership.com
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 fs/efivarfs/super.c | 50 +++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 48 insertions(+), 2 deletions(-)

diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index 42295d04f08de..0486e9b68bc6e 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -474,12 +474,25 @@ static int efivarfs_check_missing(efi_char16_t *name16, efi_guid_t vendor,
 	return err;
 }
 
+static void efivarfs_deactivate_super_work(struct work_struct *work)
+{
+	struct super_block *s = container_of(work, struct super_block,
+					     destroy_work);
+	/*
+	 * note: here s->destroy_work is free for reuse (which
+	 * will happen in deactivate_super)
+	 */
+	deactivate_super(s);
+}
+
+static struct file_system_type efivarfs_type;
+
 static int efivarfs_pm_notify(struct notifier_block *nb, unsigned long action,
 			      void *ptr)
 {
 	struct efivarfs_fs_info *sfi = container_of(nb, struct efivarfs_fs_info,
 						    pm_nb);
-	struct path path = { .mnt = NULL, .dentry = sfi->sb->s_root, };
+	struct path path;
 	struct efivarfs_ctx ectx = {
 		.ctx = {
 			.actor	= efivarfs_actor,
@@ -487,6 +500,7 @@ static int efivarfs_pm_notify(struct notifier_block *nb, unsigned long action,
 		.sb = sfi->sb,
 	};
 	struct file *file;
+	struct super_block *s = sfi->sb;
 	static bool rescan_done = true;
 
 	if (action == PM_HIBERNATION_PREPARE) {
@@ -499,11 +513,43 @@ static int efivarfs_pm_notify(struct notifier_block *nb, unsigned long action,
 	if (rescan_done)
 		return NOTIFY_DONE;
 
+	/* ensure single superblock is alive and pin it */
+	if (!atomic_inc_not_zero(&s->s_active))
+		return NOTIFY_DONE;
+
 	pr_info("efivarfs: resyncing variable state\n");
 
-	/* O_NOATIME is required to prevent oops on NULL mnt */
+	path.dentry = sfi->sb->s_root;
+
+	/*
+	 * do not add SB_KERNMOUNT which a single superblock could
+	 * expose to userspace and which also causes MNT_INTERNAL, see
+	 * below
+	 */
+	path.mnt = vfs_kern_mount(&efivarfs_type, 0,
+				  efivarfs_type.name, NULL);
+	if (IS_ERR(path.mnt)) {
+		pr_err("efivarfs: internal mount failed\n");
+		/*
+		 * We may be the last pinner of the superblock but
+		 * calling efivarfs_kill_sb from within the notifier
+		 * here would deadlock trying to unregister it
+		 */
+		INIT_WORK(&s->destroy_work, efivarfs_deactivate_super_work);
+		schedule_work(&s->destroy_work);
+		return PTR_ERR(path.mnt);
+	}
+
+	/* path.mnt now has pin on superblock, so this must be above one */
+	atomic_dec(&s->s_active);
+
 	file = kernel_file_open(&path, O_RDONLY | O_DIRECTORY | O_NOATIME,
 				current_cred());
+	/*
+	 * safe even if last put because no MNT_INTERNAL means this
+	 * will do delayed deactivate_super and not deadlock
+	 */
+	mntput(path.mnt);
 	if (IS_ERR(file))
 		return NOTIFY_DONE;
 

From 79f88a584e35133359c394506b351a60230cf37b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:35:58 +0100
Subject: [PATCH 2187/2753] net: ethtool: Export the link_mode_params
 definitions

link_mode_params contains a lookup table of all 802.3 link modes that
are currently supported with structured data about each mode's speed,
duplex, number of lanes and mediums.

As a preparation for a port representation, export that table for the
rest of the net stack to use.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-2-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/ethtool.h | 8 ++++++++
 net/ethtool/common.c    | 1 +
 net/ethtool/common.h    | 7 -------
 3 files changed, 9 insertions(+), 7 deletions(-)

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 7f222dccc7d1d..8210ece94fa6b 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -210,6 +210,14 @@ static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx)
 
 void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id);
 
+struct link_mode_info {
+	int                             speed;
+	u8                              lanes;
+	u8                              duplex;
+};
+
+extern const struct link_mode_info link_mode_params[];
+
 /* declare a link mode bitmap */
 #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name)		\
 	DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS)
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 1c6f2a2f18714..7e3c16856c1a8 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -424,6 +424,7 @@ const struct link_mode_info link_mode_params[] = {
 	__DEFINE_LINK_MODE_PARAMS(800000, VR4, Full),
 };
 static_assert(ARRAY_SIZE(link_mode_params) == __ETHTOOL_LINK_MODE_MASK_NBITS);
+EXPORT_SYMBOL_GPL(link_mode_params);
 
 const char netif_msg_class_names[][ETH_GSTRING_LEN] = {
 	[NETIF_MSG_DRV_BIT]		= "drv",
diff --git a/net/ethtool/common.h b/net/ethtool/common.h
index a1088c2441d0a..b4683d286a5a5 100644
--- a/net/ethtool/common.h
+++ b/net/ethtool/common.h
@@ -15,12 +15,6 @@
 #define __SOF_TIMESTAMPING_CNT (const_ilog2(SOF_TIMESTAMPING_LAST) + 1)
 #define __HWTSTAMP_FLAG_CNT (const_ilog2(HWTSTAMP_FLAG_LAST) + 1)
 
-struct link_mode_info {
-	int				speed;
-	u8				lanes;
-	u8				duplex;
-};
-
 struct genl_info;
 struct hwtstamp_provider_desc;
 
@@ -33,7 +27,6 @@ tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN];
 extern const char
 phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN];
 extern const char link_mode_names[][ETH_GSTRING_LEN];
-extern const struct link_mode_info link_mode_params[];
 extern const char netif_msg_class_names[][ETH_GSTRING_LEN];
 extern const char wol_mode_names[][ETH_GSTRING_LEN];
 extern const char sof_timestamping_names[][ETH_GSTRING_LEN];

From d8c838a57ce25c746c9882ffa427d8bb3f22b526 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:35:59 +0100
Subject: [PATCH 2188/2753] net: phy: Use an internal, searchable storage for
 the linkmodes

The canonical definition for all the link modes is in linux/ethtool.h,
which is complemented by the link_mode_params array stored in
net/ethtool/common.h . That array contains all the metadata about each
of these modes, including the Speed and Duplex information.

Phylib and phylink needs that information as well for internal
management of the link, which was done by duplicating that information
in locally-stored arrays and lookup functions. This makes it easy for
developpers adding new modes to forget modifying phylib and phylink
accordingly.

However, the link_mode_params array in net/ethtool/common.c is fairly
inefficient to search through, as it isn't sorted in any manner. Phylib
and phylink perform a lot of lookup operations, mostly to filter modes
by speed and/or duplex.

We therefore introduce the link_caps private array in phy_caps.c, that
indexes linkmodes in a more efficient manner. Each element associated a
tuple <speed, duplex> to a bitfield of all the linkmodes runs at these
speed/duplex.

We end-up with an array that's fairly short, easily addressable and that
it optimised for the typical use-cases of phylib/phylink.

That array is initialized at the same time as phylib. As the
link_mode_params array is part of the net stack, which phylink depends
on, it should always be accessible from phylib.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-3-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/Makefile     |  2 +-
 drivers/net/phy/phy-caps.h   | 43 +++++++++++++++++
 drivers/net/phy/phy_caps.c   | 90 ++++++++++++++++++++++++++++++++++++
 drivers/net/phy/phy_device.c |  5 ++
 4 files changed, 139 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/phy/phy-caps.h
 create mode 100644 drivers/net/phy/phy_caps.c

diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile
index 8f9ba5e8290de..23ce205ae91d8 100644
--- a/drivers/net/phy/Makefile
+++ b/drivers/net/phy/Makefile
@@ -3,7 +3,7 @@
 
 libphy-y			:= phy.o phy-c45.o phy-core.o phy_device.o \
 				   linkmode.o phy_link_topology.o \
-				   phy_package.o
+				   phy_package.o phy_caps.o
 mdio-bus-y			+= mdio_bus.o mdio_device.o
 
 ifdef CONFIG_MDIO_DEVICE
diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
new file mode 100644
index 0000000000000..6024f1d11a93c
--- /dev/null
+++ b/drivers/net/phy/phy-caps.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * link caps internal header, for link modes <-> capabilities <-> interfaces
+ * conversions.
+ */
+
+#ifndef __PHY_CAPS_H
+#define __PHY_CAPS_H
+
+#include <linux/ethtool.h>
+
+enum {
+	LINK_CAPA_10HD = 0,
+	LINK_CAPA_10FD,
+	LINK_CAPA_100HD,
+	LINK_CAPA_100FD,
+	LINK_CAPA_1000HD,
+	LINK_CAPA_1000FD,
+	LINK_CAPA_2500FD,
+	LINK_CAPA_5000FD,
+	LINK_CAPA_10000FD,
+	LINK_CAPA_20000FD,
+	LINK_CAPA_25000FD,
+	LINK_CAPA_40000FD,
+	LINK_CAPA_50000FD,
+	LINK_CAPA_56000FD,
+	LINK_CAPA_100000FD,
+	LINK_CAPA_200000FD,
+	LINK_CAPA_400000FD,
+	LINK_CAPA_800000FD,
+
+	__LINK_CAPA_MAX,
+};
+
+struct link_capabilities {
+	int speed;
+	unsigned int duplex;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(linkmodes);
+};
+
+int phy_caps_init(void);
+
+#endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
new file mode 100644
index 0000000000000..6cb18e216d97a
--- /dev/null
+++ b/drivers/net/phy/phy_caps.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+
+#include <linux/ethtool.h>
+#include <linux/linkmode.h>
+#include <linux/phy.h>
+
+#include "phy-caps.h"
+
+static struct link_capabilities link_caps[__LINK_CAPA_MAX] __ro_after_init = {
+	{ SPEED_10, DUPLEX_HALF, {0} }, /* LINK_CAPA_10HD */
+	{ SPEED_10, DUPLEX_FULL, {0} }, /* LINK_CAPA_10FD */
+	{ SPEED_100, DUPLEX_HALF, {0} }, /* LINK_CAPA_100HD */
+	{ SPEED_100, DUPLEX_FULL, {0} }, /* LINK_CAPA_100FD */
+	{ SPEED_1000, DUPLEX_HALF, {0} }, /* LINK_CAPA_1000HD */
+	{ SPEED_1000, DUPLEX_FULL, {0} }, /* LINK_CAPA_1000FD */
+	{ SPEED_2500, DUPLEX_FULL, {0} }, /* LINK_CAPA_2500FD */
+	{ SPEED_5000, DUPLEX_FULL, {0} }, /* LINK_CAPA_5000FD */
+	{ SPEED_10000, DUPLEX_FULL, {0} }, /* LINK_CAPA_10000FD */
+	{ SPEED_20000, DUPLEX_FULL, {0} }, /* LINK_CAPA_20000FD */
+	{ SPEED_25000, DUPLEX_FULL, {0} }, /* LINK_CAPA_25000FD */
+	{ SPEED_40000, DUPLEX_FULL, {0} }, /* LINK_CAPA_40000FD */
+	{ SPEED_50000, DUPLEX_FULL, {0} }, /* LINK_CAPA_50000FD */
+	{ SPEED_56000, DUPLEX_FULL, {0} }, /* LINK_CAPA_56000FD */
+	{ SPEED_100000, DUPLEX_FULL, {0} }, /* LINK_CAPA_100000FD */
+	{ SPEED_200000, DUPLEX_FULL, {0} }, /* LINK_CAPA_200000FD */
+	{ SPEED_400000, DUPLEX_FULL, {0} }, /* LINK_CAPA_400000FD */
+	{ SPEED_800000, DUPLEX_FULL, {0} }, /* LINK_CAPA_800000FD */
+};
+
+static int speed_duplex_to_capa(int speed, unsigned int duplex)
+{
+	if (duplex == DUPLEX_UNKNOWN ||
+	    (speed > SPEED_1000 && duplex != DUPLEX_FULL))
+		return -EINVAL;
+
+	switch (speed) {
+	case SPEED_10: return duplex == DUPLEX_FULL ?
+			      LINK_CAPA_10FD : LINK_CAPA_10HD;
+	case SPEED_100: return duplex == DUPLEX_FULL ?
+			       LINK_CAPA_100FD : LINK_CAPA_100HD;
+	case SPEED_1000: return duplex == DUPLEX_FULL ?
+				LINK_CAPA_1000FD : LINK_CAPA_1000HD;
+	case SPEED_2500: return LINK_CAPA_2500FD;
+	case SPEED_5000: return LINK_CAPA_5000FD;
+	case SPEED_10000: return LINK_CAPA_10000FD;
+	case SPEED_20000: return LINK_CAPA_20000FD;
+	case SPEED_25000: return LINK_CAPA_25000FD;
+	case SPEED_40000: return LINK_CAPA_40000FD;
+	case SPEED_50000: return LINK_CAPA_50000FD;
+	case SPEED_56000: return LINK_CAPA_56000FD;
+	case SPEED_100000: return LINK_CAPA_100000FD;
+	case SPEED_200000: return LINK_CAPA_200000FD;
+	case SPEED_400000: return LINK_CAPA_400000FD;
+	case SPEED_800000: return LINK_CAPA_800000FD;
+	}
+
+	return -EINVAL;
+}
+
+/**
+ * phy_caps_init() - Initializes the link_caps array from the link_mode_params.
+ *
+ * Returns: 0 if phy caps init was successful, -EINVAL if we found an
+ *	    unexpected linkmode setting that requires LINK_CAPS update.
+ *
+ */
+int phy_caps_init(void)
+{
+	const struct link_mode_info *linkmode;
+	int i, capa;
+
+	/* Fill the caps array from net/ethtool/common.c */
+	for (i = 0; i < __ETHTOOL_LINK_MODE_MASK_NBITS; i++) {
+		linkmode = &link_mode_params[i];
+		capa = speed_duplex_to_capa(linkmode->speed, linkmode->duplex);
+
+		if (capa < 0) {
+			if (linkmode->speed != SPEED_UNKNOWN) {
+				pr_err("Unknown speed %d, please update LINK_CAPS\n",
+				       linkmode->speed);
+				return -EINVAL;
+			}
+			continue;
+		}
+
+		__set_bit(i, link_caps[capa].linkmodes);
+	}
+
+	return 0;
+}
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index b2d32fbc8c850..4980862398d04 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -42,6 +42,7 @@
 #include <linux/unistd.h>
 
 #include "phylib-internal.h"
+#include "phy-caps.h"
 
 MODULE_DESCRIPTION("PHY library");
 MODULE_AUTHOR("Andy Fleming");
@@ -3558,6 +3559,10 @@ static int __init phy_init(void)
 	if (rc)
 		goto err_ethtool_phy_ops;
 
+	rc = phy_caps_init();
+	if (rc)
+		goto err_mdio_bus;
+
 	features_init();
 
 	rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE);

From 8c8c4a87933dd924f9fb56dfd35bae7e8f30a4b5 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:00 +0100
Subject: [PATCH 2189/2753] net: phy: phy_caps: Move phy_speeds to phy_caps

Use the newly introduced link_capabilities array to derive the list of
possible speeds when given a combination of linkmodes. As
link_capabilities is indexed by speed, we don't have to iterate the
whole phy_settings array.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-4-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  3 +++
 drivers/net/phy/phy-core.c | 15 ---------------
 drivers/net/phy/phy.c      |  3 ++-
 drivers/net/phy/phy_caps.c | 33 +++++++++++++++++++++++++++++++++
 include/linux/phy.h        |  2 --
 5 files changed, 38 insertions(+), 18 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 6024f1d11a93c..5a5f4ee3006b8 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -40,4 +40,7 @@ struct link_capabilities {
 
 int phy_caps_init(void);
 
+size_t phy_caps_speeds(unsigned int *speeds, size_t size,
+		       unsigned long *linkmodes);
+
 #endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 31ed1ce3b62f1..102834b11de0e 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -340,21 +340,6 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact)
 }
 EXPORT_SYMBOL_GPL(phy_lookup_setting);
 
-size_t phy_speeds(unsigned int *speeds, size_t size,
-		  unsigned long *mask)
-{
-	size_t count;
-	int i;
-
-	for (i = 0, count = 0; i < ARRAY_SIZE(settings) && count < size; i++)
-		if (settings[i].bit < __ETHTOOL_LINK_MODE_MASK_NBITS &&
-		    test_bit(settings[i].bit, mask) &&
-		    (count == 0 || speeds[count - 1] != settings[i].speed))
-			speeds[count++] = settings[i].speed;
-
-	return count;
-}
-
 static void __set_linkmode_max_speed(u32 max_speed, unsigned long *addr)
 {
 	const struct phy_setting *p;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 16ffc00b419ca..3128df03feda3 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -37,6 +37,7 @@
 #include <net/sock.h>
 
 #include "phylib-internal.h"
+#include "phy-caps.h"
 
 #define PHY_STATE_TIME	HZ
 
@@ -245,7 +246,7 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
 				  unsigned int *speeds,
 				  unsigned int size)
 {
-	return phy_speeds(speeds, size, phy->supported);
+	return phy_caps_speeds(speeds, size, phy->supported);
 }
 
 /**
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 6cb18e216d97a..8ce91257160fc 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -57,6 +57,9 @@ static int speed_duplex_to_capa(int speed, unsigned int duplex)
 	return -EINVAL;
 }
 
+#define for_each_link_caps_asc_speed(cap) \
+	for (cap = link_caps; cap < &link_caps[__LINK_CAPA_MAX]; cap++)
+
 /**
  * phy_caps_init() - Initializes the link_caps array from the link_mode_params.
  *
@@ -88,3 +91,33 @@ int phy_caps_init(void)
 
 	return 0;
 }
+
+/**
+ * phy_caps_speeds() - Fill an array of supported SPEED_* values for given modes
+ * @speeds: Output array to store the speeds list into
+ * @size: Size of the output array
+ * @linkmodes: Linkmodes to get the speeds from
+ *
+ * Fills the speeds array with all possible speeds that can be achieved with
+ * the specified linkmodes.
+ *
+ * Returns: The number of speeds filled into the array. If the input array isn't
+ *	    big enough to store all speeds, fill it as much as possible.
+ */
+size_t phy_caps_speeds(unsigned int *speeds, size_t size,
+		       unsigned long *linkmodes)
+{
+	struct link_capabilities *lcap;
+	size_t count = 0;
+
+	for_each_link_caps_asc_speed(lcap) {
+		if (linkmode_intersects(lcap->linkmodes, linkmodes) &&
+		    (count == 0 || speeds[count - 1] != lcap->speed)) {
+			speeds[count++] = lcap->speed;
+			if (count >= size)
+				break;
+		}
+	}
+
+	return count;
+}
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 61a8cb9d12477..83c50bb219391 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1287,8 +1287,6 @@ struct phy_setting {
 const struct phy_setting *
 phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
 		   bool exact);
-size_t phy_speeds(unsigned int *speeds, size_t size,
-		  unsigned long *mask);
 
 /**
  * phy_is_started - Convenience function to check whether PHY is started

From 4823ed0609194e164bcacac04a610dd86717689f Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:01 +0100
Subject: [PATCH 2190/2753] net: phy: phy_caps: Move __set_linkmode_max_speed
 to phy_caps

Convert the __set_linkmode_max_speed to use the link_capabilities array.
This makes it easy to clamp the linkmodes to a given max speed.
Introduce a new helper phy_caps_linkmode_max_speed to replace the
previous one that used phy_settings.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-5-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  2 ++
 drivers/net/phy/phy-core.c | 18 +++---------------
 drivers/net/phy/phy_caps.c | 19 +++++++++++++++++++
 3 files changed, 24 insertions(+), 15 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 5a5f4ee3006b8..1bef9cca62c56 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -42,5 +42,7 @@ int phy_caps_init(void);
 
 size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 		       unsigned long *linkmodes);
+void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
+
 
 #endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 102834b11de0e..741350d7d29cf 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -8,6 +8,7 @@
 
 #include "phylib.h"
 #include "phylib-internal.h"
+#include "phy-caps.h"
 
 /**
  * phy_speed_to_str - Return a string representing the PHY link speed
@@ -340,22 +341,9 @@ phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact)
 }
 EXPORT_SYMBOL_GPL(phy_lookup_setting);
 
-static void __set_linkmode_max_speed(u32 max_speed, unsigned long *addr)
-{
-	const struct phy_setting *p;
-	int i;
-
-	for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) {
-		if (p->speed > max_speed)
-			linkmode_clear_bit(p->bit, addr);
-		else
-			break;
-	}
-}
-
 static void __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
-	__set_linkmode_max_speed(max_speed, phydev->supported);
+	phy_caps_linkmode_max_speed(max_speed, phydev->supported);
 }
 
 /**
@@ -558,7 +546,7 @@ int phy_speed_down_core(struct phy_device *phydev)
 	if (min_common_speed == SPEED_UNKNOWN)
 		return -EINVAL;
 
-	__set_linkmode_max_speed(min_common_speed, phydev->advertising);
+	phy_caps_linkmode_max_speed(min_common_speed, phydev->advertising);
 
 	return 0;
 }
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 8ce91257160fc..d43493884ff79 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -60,6 +60,9 @@ static int speed_duplex_to_capa(int speed, unsigned int duplex)
 #define for_each_link_caps_asc_speed(cap) \
 	for (cap = link_caps; cap < &link_caps[__LINK_CAPA_MAX]; cap++)
 
+#define for_each_link_caps_desc_speed(cap) \
+	for (cap = &link_caps[__LINK_CAPA_MAX - 1]; cap >= link_caps; cap--)
+
 /**
  * phy_caps_init() - Initializes the link_caps array from the link_mode_params.
  *
@@ -121,3 +124,19 @@ size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 
 	return count;
 }
+
+/**
+ * phy_caps_linkmode_max_speed() - Clamp a linkmodes set to a max speed
+ * @max_speed: Speed limit for the linkmode set
+ * @linkmodes: Linkmodes to limit
+ */
+void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes)
+{
+	struct link_capabilities *lcap;
+
+	for_each_link_caps_desc_speed(lcap)
+		if (lcap->speed > max_speed)
+			linkmode_andnot(linkmodes, linkmodes, lcap->linkmodes);
+		else
+			break;
+}

From 87b22ce312350170af5e970c5abfb2bb87e39964 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:02 +0100
Subject: [PATCH 2191/2753] net: phy: phy_caps: Introduce phy_caps_valid

With the link_capabilities array, it's trivial to validate a given mask
againts a <speed, duplex> tuple. Create a helper for that purpose, and
use it to replace a phy_settings lookup in phy_check_valid();

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-6-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  1 +
 drivers/net/phy/phy.c      |  2 +-
 drivers/net/phy/phy_caps.c | 19 +++++++++++++++++++
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 1bef9cca62c56..1217686f1f917 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -43,6 +43,7 @@ int phy_caps_init(void);
 size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 		       unsigned long *linkmodes);
 void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
+bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes);
 
 
 #endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 3128df03feda3..8df37d221fba6 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -260,7 +260,7 @@ unsigned int phy_supported_speeds(struct phy_device *phy,
  */
 bool phy_check_valid(int speed, int duplex, unsigned long *features)
 {
-	return !!phy_lookup_setting(speed, duplex, features, true);
+	return phy_caps_valid(speed, duplex, features);
 }
 EXPORT_SYMBOL(phy_check_valid);
 
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index d43493884ff79..4ee8c25c8521c 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -140,3 +140,22 @@ void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes)
 		else
 			break;
 }
+
+/**
+ * phy_caps_valid() - Validate a linkmodes set agains given speed and duplex
+ * @speed: input speed to validate
+ * @duplex: input duplex to validate. Passing DUPLEX_UNKNOWN is always not valid
+ * @linkmodes: The linkmodes to validate
+ *
+ * Returns: True if at least one of the linkmodes in @linkmodes can function at
+ *          the given speed and duplex, false otherwise.
+ */
+bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes)
+{
+	int capa = speed_duplex_to_capa(speed, duplex);
+
+	if (capa < 0)
+		return false;
+
+	return linkmode_intersects(link_caps[capa].linkmodes, linkmodes);
+}

From dbcd85b05c5ba520b75dbf51d0b48b5a366b6c68 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:03 +0100
Subject: [PATCH 2192/2753] net: phy: phy_caps: Implement link_capabilities
 lookup by linkmode

In several occasions, phylib needs to lookup a set of matching speed and
duplex against a given linkmode set. Instead of relying on the
phy_settings array and thus iterate over the whole linkmodes list, use
the link_capabilities array to lookup these matches, as we aren't
interested in the actual link setting that matches but rather the speed
and duplex for that setting.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-7-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  5 +++++
 drivers/net/phy/phy-core.c | 36 +++++++++++++-----------------
 drivers/net/phy/phy_caps.c | 45 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 65 insertions(+), 21 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 1217686f1f917..8833798f141f3 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -45,5 +45,10 @@ size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
 bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes);
 
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode(const unsigned long *linkmodes);
+
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only);
 
 #endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 741350d7d29cf..a1caa0f313ecd 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -469,16 +469,15 @@ EXPORT_SYMBOL_GPL(phy_resolve_aneg_pause);
 void phy_resolve_aneg_linkmode(struct phy_device *phydev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
-	int i;
+	const struct link_capabilities *c;
 
 	linkmode_and(common, phydev->lp_advertising, phydev->advertising);
 
-	for (i = 0; i < ARRAY_SIZE(settings); i++)
-		if (test_bit(settings[i].bit, common)) {
-			phydev->speed = settings[i].speed;
-			phydev->duplex = settings[i].duplex;
-			break;
-		}
+	c = phy_caps_lookup_by_linkmode(common);
+	if (c) {
+		phydev->speed = c->speed;
+		phydev->duplex = c->duplex;
+	}
 
 	phy_resolve_aneg_pause(phydev);
 }
@@ -496,7 +495,8 @@ EXPORT_SYMBOL_GPL(phy_resolve_aneg_linkmode);
 void phy_check_downshift(struct phy_device *phydev)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
-	int i, speed = SPEED_UNKNOWN;
+	const struct link_capabilities *c;
+	int speed = SPEED_UNKNOWN;
 
 	phydev->downshifted_rate = 0;
 
@@ -506,11 +506,9 @@ void phy_check_downshift(struct phy_device *phydev)
 
 	linkmode_and(common, phydev->lp_advertising, phydev->advertising);
 
-	for (i = 0; i < ARRAY_SIZE(settings); i++)
-		if (test_bit(settings[i].bit, common)) {
-			speed = settings[i].speed;
-			break;
-		}
+	c = phy_caps_lookup_by_linkmode(common);
+	if (c)
+		speed = c->speed;
 
 	if (speed == SPEED_UNKNOWN || phydev->speed >= speed)
 		return;
@@ -524,17 +522,13 @@ void phy_check_downshift(struct phy_device *phydev)
 static int phy_resolve_min_speed(struct phy_device *phydev, bool fdx_only)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
-	int i = ARRAY_SIZE(settings);
+	const struct link_capabilities *c;
 
 	linkmode_and(common, phydev->lp_advertising, phydev->advertising);
 
-	while (--i >= 0) {
-		if (test_bit(settings[i].bit, common)) {
-			if (fdx_only && settings[i].duplex != DUPLEX_FULL)
-				continue;
-			return settings[i].speed;
-		}
-	}
+	c = phy_caps_lookup_by_linkmode_rev(common, fdx_only);
+	if (c)
+		return c->speed;
 
 	return SPEED_UNKNOWN;
 }
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 4ee8c25c8521c..c39f38c12ef2a 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -125,6 +125,51 @@ size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 	return count;
 }
 
+/**
+ * phy_caps_lookup_by_linkmode() - Lookup the fastest matching link_capabilities
+ * @linkmodes: Linkmodes to match against
+ *
+ * Returns: The highest-speed link_capabilities that intersects the given
+ *	    linkmodes. In case several DUPLEX_ options exist at that speed,
+ *	    DUPLEX_FULL is matched first. NULL is returned if no match.
+ */
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode(const unsigned long *linkmodes)
+{
+	struct link_capabilities *lcap;
+
+	for_each_link_caps_desc_speed(lcap)
+		if (linkmode_intersects(lcap->linkmodes, linkmodes))
+			return lcap;
+
+	return NULL;
+}
+
+/**
+ * phy_caps_lookup_by_linkmode_rev() - Lookup the slowest matching link_capabilities
+ * @linkmodes: Linkmodes to match against
+ * @fdx_only: Full duplex match only when set
+ *
+ * Returns: The lowest-speed link_capabilities that intersects the given
+ *	    linkmodes. When set, fdx_only will ignore half-duplex matches.
+ *	    NULL is returned if no match.
+ */
+const struct link_capabilities *
+phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only)
+{
+	struct link_capabilities *lcap;
+
+	for_each_link_caps_asc_speed(lcap) {
+		if (fdx_only && lcap->duplex != DUPLEX_FULL)
+			continue;
+
+		if (linkmode_intersects(lcap->linkmodes, linkmodes))
+			return lcap;
+	}
+
+	return NULL;
+}
+
 /**
  * phy_caps_linkmode_max_speed() - Clamp a linkmodes set to a max speed
  * @max_speed: Speed limit for the linkmode set

From fc81e257d19f5733c22732eef29fa15ee8bef221 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:04 +0100
Subject: [PATCH 2193/2753] net: phy: phy_caps: Allow looking-up link caps
 based on speed and duplex

As the link_caps array is efficient for <speed,duplex> lookups,
implement a function for speed/duplex lookups that matches a given
mask. This replicates to some extent the phy_lookup_settings()
behaviour, matching full link_capabilities instead of a single linkmode.

phy.c's phy_santize_settings() and phylink's
phylink_ethtool_ksettings_set() performs such lookup using the
phy_settings table, but are only interested in the actual speed/duplex
that were matched, rathet than the individual linkmode.

Similar to phy_lookup_settings(), the newly introduced phy_caps_lookup()
will run through the link_caps[] array by descending speed/duplex order.

If the link_capabilities for a given <speed/duplex> tuple intersects the
passed linkmodes, we consider that a match.

Similar to phy_lookup_settings(), we also allow passing an 'exact'
boolean, allowing non-exact match. Here, we MUST always match the
linkmodes mask, but we allow matching on lower speed settings.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-8-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  4 ++++
 drivers/net/phy/phy.c      | 32 ++++++--------------------
 drivers/net/phy/phy_caps.c | 47 ++++++++++++++++++++++++++++++++++++++
 drivers/net/phy/phylink.c  | 17 +++++++-------
 4 files changed, 67 insertions(+), 33 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 8833798f141f3..aef4b54a8429d 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -51,4 +51,8 @@ phy_caps_lookup_by_linkmode(const unsigned long *linkmodes);
 const struct link_capabilities *
 phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only);
 
+const struct link_capabilities *
+phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
+		bool exact);
+
 #endif /* __PHY_CAPS_H */
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 8df37d221fba6..562acde892249 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -213,25 +213,6 @@ int phy_aneg_done(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_aneg_done);
 
-/**
- * phy_find_valid - find a PHY setting that matches the requested parameters
- * @speed: desired speed
- * @duplex: desired duplex
- * @supported: mask of supported link modes
- *
- * Locate a supported phy setting that is, in priority order:
- * - an exact match for the specified speed and duplex mode
- * - a match for the specified speed, or slower speed
- * - the slowest supported speed
- * Returns the matched phy_setting entry, or %NULL if no supported phy
- * settings were found.
- */
-static const struct phy_setting *
-phy_find_valid(int speed, int duplex, unsigned long *supported)
-{
-	return phy_lookup_setting(speed, duplex, supported, false);
-}
-
 /**
  * phy_supported_speeds - return all speeds currently supported by a phy device
  * @phy: The phy device to return supported speeds of.
@@ -274,13 +255,14 @@ EXPORT_SYMBOL(phy_check_valid);
  */
 static void phy_sanitize_settings(struct phy_device *phydev)
 {
-	const struct phy_setting *setting;
+	const struct link_capabilities *c;
+
+	c = phy_caps_lookup(phydev->speed, phydev->duplex, phydev->supported,
+			    false);
 
-	setting = phy_find_valid(phydev->speed, phydev->duplex,
-				 phydev->supported);
-	if (setting) {
-		phydev->speed = setting->speed;
-		phydev->duplex = setting->duplex;
+	if (c) {
+		phydev->speed = c->speed;
+		phydev->duplex = c->duplex;
 	} else {
 		/* We failed to find anything (no supported speeds?) */
 		phydev->speed = SPEED_UNKNOWN;
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index c39f38c12ef2a..0366feee2912a 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -170,6 +170,53 @@ phy_caps_lookup_by_linkmode_rev(const unsigned long *linkmodes, bool fdx_only)
 	return NULL;
 }
 
+/**
+ * phy_caps_lookup() - Lookup capabilities by speed/duplex that matches a mask
+ * @speed: Speed to match
+ * @duplex: Duplex to match
+ * @supported: Mask of linkmodes to match
+ * @exact: Perform an exact match or not.
+ *
+ * Lookup a link_capabilities entry that intersect the supported linkmodes mask,
+ * and that matches the passed speed and duplex.
+ *
+ * When @exact is set, an exact match is performed on speed and duplex, meaning
+ * that if the linkmodes for the given speed and duplex intersect the supported
+ * mask, this capability is returned, otherwise we don't have a match and return
+ * NULL.
+ *
+ * When @exact is not set, we return either an exact match, or matching capabilities
+ * at lower speed, or the lowest matching speed, or NULL.
+ *
+ * Returns: a matched link_capabilities according to the above process, NULL
+ *	    otherwise.
+ */
+const struct link_capabilities *
+phy_caps_lookup(int speed, unsigned int duplex, const unsigned long *supported,
+		bool exact)
+{
+	const struct link_capabilities *lcap, *last = NULL;
+
+	for_each_link_caps_desc_speed(lcap) {
+		if (linkmode_intersects(lcap->linkmodes, supported)) {
+			last = lcap;
+			/* exact match on speed and duplex*/
+			if (lcap->speed == speed && lcap->duplex == duplex) {
+				return lcap;
+			} else if (!exact) {
+				if (lcap->speed <= speed)
+					return lcap;
+			}
+		}
+	}
+
+	if (!exact)
+		return last;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(phy_caps_lookup);
+
 /**
  * phy_caps_linkmode_max_speed() - Clamp a linkmodes set to a max speed
  * @max_speed: Speed limit for the linkmode set
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 76b1a329607bb..ad611dda19335 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -20,6 +20,7 @@
 #include <linux/timer.h>
 #include <linux/workqueue.h>
 
+#include "phy-caps.h"
 #include "sfp.h"
 #include "swphy.h"
 
@@ -2852,8 +2853,8 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 				  const struct ethtool_link_ksettings *kset)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(support);
+	const struct link_capabilities *c;
 	struct phylink_link_state config;
-	const struct phy_setting *s;
 
 	ASSERT_RTNL();
 
@@ -2896,23 +2897,23 @@ int phylink_ethtool_ksettings_set(struct phylink *pl,
 		/* Autonegotiation disabled, select a suitable speed and
 		 * duplex.
 		 */
-		s = phy_lookup_setting(kset->base.speed, kset->base.duplex,
-				       pl->supported, false);
-		if (!s)
+		c = phy_caps_lookup(kset->base.speed, kset->base.duplex,
+				    pl->supported, false);
+		if (!c)
 			return -EINVAL;
 
 		/* If we have a fixed link, refuse to change link parameters.
 		 * If the link parameters match, accept them but do nothing.
 		 */
 		if (pl->req_link_an_mode == MLO_AN_FIXED) {
-			if (s->speed != pl->link_config.speed ||
-			    s->duplex != pl->link_config.duplex)
+			if (c->speed != pl->link_config.speed ||
+			    c->duplex != pl->link_config.duplex)
 				return -EINVAL;
 			return 0;
 		}
 
-		config.speed = s->speed;
-		config.duplex = s->duplex;
+		config.speed = c->speed;
+		config.duplex = c->duplex;
 		break;
 
 	case AUTONEG_ENABLE:

From c7ae89c6b4d55de583eb08da8100dc20a2828d9e Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:05 +0100
Subject: [PATCH 2194/2753] net: phy: phy_device: Use link_capabilities lookup
 for PHY aneg config

When configuring PHY advertising with autoneg disabled, we lookd for an
exact linkmode to advertise and configure for the requested Speed and
Duplex, specially at or over 1G.

Using phy_caps_lookup allows us to build a list of the supported
linkmodes at that speed that we can advertise instead of the first mode
that matches.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-9-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy_device.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 4980862398d04..3f734e847e8e2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2120,7 +2120,7 @@ EXPORT_SYMBOL(genphy_check_and_restart_aneg);
 int __genphy_config_aneg(struct phy_device *phydev, bool changed)
 {
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(fixed_advert);
-	const struct phy_setting *set;
+	const struct link_capabilities *c;
 	unsigned long *advert;
 	int err;
 
@@ -2146,10 +2146,11 @@ int __genphy_config_aneg(struct phy_device *phydev, bool changed)
 	} else {
 		linkmode_zero(fixed_advert);
 
-		set = phy_lookup_setting(phydev->speed, phydev->duplex,
-					 phydev->supported, true);
-		if (set)
-			linkmode_set_bit(set->bit, fixed_advert);
+		c = phy_caps_lookup(phydev->speed, phydev->duplex,
+				    phydev->supported, true);
+		if (c)
+			linkmode_and(fixed_advert, phydev->supported,
+				     c->linkmodes);
 
 		advert = fixed_advert;
 	}

From de7d3f87be3cba8ad06978271a3135bd08810c97 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:06 +0100
Subject: [PATCH 2195/2753] net: phylink: Use phy_caps_lookup for fixed-link
 configuration

When phylink creates a fixed-link configuration, it finds a matching
linkmode to set as the advertised, lp_advertising and supported modes
based on the speed and duplex of the fixed link.

Use the newly introduced phy_caps_lookup to get these modes instead of
phy_lookup_settings(). This has the side effect that the matched
settings and configured linkmodes may now contain several linkmodes (the
intersection of supported linkmodes from the phylink settings and the
linkmodes that match speed/duplex) instead of the one from
phy_lookup_settings().

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-10-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylink.c | 44 +++++++++++++++++++++++++++------------
 1 file changed, 31 insertions(+), 13 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index ad611dda19335..694b836d8ff73 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -802,12 +802,26 @@ static int phylink_validate(struct phylink *pl, unsigned long *supported,
 	return phylink_validate_mac_and_pcs(pl, supported, state);
 }
 
+static void phylink_fill_fixedlink_supported(unsigned long *supported)
+{
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, supported);
+	linkmode_set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, supported);
+}
+
 static int phylink_parse_fixedlink(struct phylink *pl,
 				   const struct fwnode_handle *fwnode)
 {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(match) = { 0, };
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, };
+	const struct link_capabilities *c;
 	struct fwnode_handle *fixed_node;
-	const struct phy_setting *s;
 	struct gpio_desc *desc;
 	u32 speed;
 	int ret;
@@ -875,12 +889,16 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 		phylink_warn(pl, "fixed link specifies half duplex for %dMbps link?\n",
 			     pl->link_config.speed);
 
-	linkmode_fill(pl->supported);
+	linkmode_zero(pl->supported);
+	phylink_fill_fixedlink_supported(pl->supported);
+
 	linkmode_copy(pl->link_config.advertising, pl->supported);
 	phylink_validate(pl, pl->supported, &pl->link_config);
 
-	s = phy_lookup_setting(pl->link_config.speed, pl->link_config.duplex,
-			       pl->supported, true);
+	c = phy_caps_lookup(pl->link_config.speed, pl->link_config.duplex,
+			    pl->supported, true);
+	if (c)
+		linkmode_and(match, pl->supported, c->linkmodes);
 
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, mask);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, mask);
@@ -889,9 +907,10 @@ static int phylink_parse_fixedlink(struct phylink *pl,
 
 	phylink_set(pl->supported, MII);
 
-	if (s) {
-		__set_bit(s->bit, pl->supported);
-		__set_bit(s->bit, pl->link_config.lp_advertising);
+	if (c) {
+		linkmode_or(pl->supported, pl->supported, match);
+		linkmode_or(pl->link_config.lp_advertising,
+			    pl->link_config.lp_advertising, match);
 	} else {
 		phylink_warn(pl, "fixed link %s duplex %dMbps not recognised\n",
 			     pl->link_config.duplex == DUPLEX_FULL ? "full" : "half",
@@ -1879,21 +1898,20 @@ static int phylink_register_sfp(struct phylink *pl,
 int phylink_set_fixed_link(struct phylink *pl,
 			   const struct phylink_link_state *state)
 {
-	const struct phy_setting *s;
+	const struct link_capabilities *c;
 	unsigned long *adv;
 
 	if (pl->cfg_link_an_mode != MLO_AN_PHY || !state ||
 	    !test_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state))
 		return -EINVAL;
 
-	s = phy_lookup_setting(state->speed, state->duplex,
-			       pl->supported, true);
-	if (!s)
+	c = phy_caps_lookup(state->speed, state->duplex,
+			    pl->supported, true);
+	if (!c)
 		return -EINVAL;
 
 	adv = pl->link_config.advertising;
-	linkmode_zero(adv);
-	linkmode_set_bit(s->bit, adv);
+	linkmode_and(adv, pl->supported, c->linkmodes);
 	linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, adv);
 
 	pl->link_config.speed = state->speed;

From ce60fef7feccb5c71d5b49e489d24db7d79c2ac7 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:07 +0100
Subject: [PATCH 2196/2753] net: phy: drop phy_settings and the associated
 lookup helpers

The phy_settings array is no longer relevant as it has now been replaced
by the link_caps array and associated phy_caps helpers.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-11-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-core.c | 184 -------------------------------------
 include/linux/phy.h        |  13 ---
 2 files changed, 197 deletions(-)

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index a1caa0f313ecd..e177037f9110b 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -157,190 +157,6 @@ int phy_interface_num_ports(phy_interface_t interface)
 }
 EXPORT_SYMBOL_GPL(phy_interface_num_ports);
 
-/* A mapping of all SUPPORTED settings to speed/duplex.  This table
- * must be grouped by speed and sorted in descending match priority
- * - iow, descending speed.
- */
-
-#define PHY_SETTING(s, d, b) { .speed = SPEED_ ## s, .duplex = DUPLEX_ ## d, \
-			       .bit = ETHTOOL_LINK_MODE_ ## b ## _BIT}
-
-static const struct phy_setting settings[] = {
-	/* 800G */
-	PHY_SETTING( 800000, FULL, 800000baseCR8_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseKR8_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseDR8_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseDR8_2_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseSR8_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseVR8_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseCR4_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseKR4_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseDR4_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseDR4_2_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseSR4_Full		),
-	PHY_SETTING( 800000, FULL, 800000baseVR4_Full		),
-	/* 400G */
-	PHY_SETTING( 400000, FULL, 400000baseCR8_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseKR8_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseLR8_ER8_FR8_Full	),
-	PHY_SETTING( 400000, FULL, 400000baseDR8_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseSR8_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseCR4_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseKR4_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseLR4_ER4_FR4_Full	),
-	PHY_SETTING( 400000, FULL, 400000baseDR4_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseSR4_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseCR2_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseKR2_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseDR2_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseDR2_2_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseSR2_Full		),
-	PHY_SETTING( 400000, FULL, 400000baseVR2_Full		),
-	/* 200G */
-	PHY_SETTING( 200000, FULL, 200000baseCR4_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseKR4_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseLR4_ER4_FR4_Full	),
-	PHY_SETTING( 200000, FULL, 200000baseDR4_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseSR4_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseCR2_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseKR2_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseLR2_ER2_FR2_Full	),
-	PHY_SETTING( 200000, FULL, 200000baseDR2_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseSR2_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseCR_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseKR_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseDR_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseDR_2_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseSR_Full		),
-	PHY_SETTING( 200000, FULL, 200000baseVR_Full		),
-	/* 100G */
-	PHY_SETTING( 100000, FULL, 100000baseCR4_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseKR4_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseLR4_ER4_Full	),
-	PHY_SETTING( 100000, FULL, 100000baseSR4_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseCR2_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseKR2_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseLR2_ER2_FR2_Full	),
-	PHY_SETTING( 100000, FULL, 100000baseDR2_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseSR2_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseCR_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseKR_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseLR_ER_FR_Full	),
-	PHY_SETTING( 100000, FULL, 100000baseDR_Full		),
-	PHY_SETTING( 100000, FULL, 100000baseSR_Full		),
-	/* 56G */
-	PHY_SETTING(  56000, FULL,  56000baseCR4_Full	  	),
-	PHY_SETTING(  56000, FULL,  56000baseKR4_Full	  	),
-	PHY_SETTING(  56000, FULL,  56000baseLR4_Full	  	),
-	PHY_SETTING(  56000, FULL,  56000baseSR4_Full	  	),
-	/* 50G */
-	PHY_SETTING(  50000, FULL,  50000baseCR2_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseKR2_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseSR2_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseCR_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseKR_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseLR_ER_FR_Full	),
-	PHY_SETTING(  50000, FULL,  50000baseDR_Full		),
-	PHY_SETTING(  50000, FULL,  50000baseSR_Full		),
-	/* 40G */
-	PHY_SETTING(  40000, FULL,  40000baseCR4_Full		),
-	PHY_SETTING(  40000, FULL,  40000baseKR4_Full		),
-	PHY_SETTING(  40000, FULL,  40000baseLR4_Full		),
-	PHY_SETTING(  40000, FULL,  40000baseSR4_Full		),
-	/* 25G */
-	PHY_SETTING(  25000, FULL,  25000baseCR_Full		),
-	PHY_SETTING(  25000, FULL,  25000baseKR_Full		),
-	PHY_SETTING(  25000, FULL,  25000baseSR_Full		),
-	/* 20G */
-	PHY_SETTING(  20000, FULL,  20000baseKR2_Full		),
-	PHY_SETTING(  20000, FULL,  20000baseMLD2_Full		),
-	/* 10G */
-	PHY_SETTING(  10000, FULL,  10000baseCR_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseER_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseKR_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseKX4_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseLR_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseLRM_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseR_FEC		),
-	PHY_SETTING(  10000, FULL,  10000baseSR_Full		),
-	PHY_SETTING(  10000, FULL,  10000baseT_Full		),
-	/* 5G */
-	PHY_SETTING(   5000, FULL,   5000baseT_Full		),
-	/* 2.5G */
-	PHY_SETTING(   2500, FULL,   2500baseT_Full		),
-	PHY_SETTING(   2500, FULL,   2500baseX_Full		),
-	/* 1G */
-	PHY_SETTING(   1000, FULL,   1000baseT_Full		),
-	PHY_SETTING(   1000, HALF,   1000baseT_Half		),
-	PHY_SETTING(   1000, FULL,   1000baseT1_Full		),
-	PHY_SETTING(   1000, FULL,   1000baseX_Full		),
-	PHY_SETTING(   1000, FULL,   1000baseKX_Full		),
-	/* 100M */
-	PHY_SETTING(    100, FULL,    100baseT_Full		),
-	PHY_SETTING(    100, FULL,    100baseT1_Full		),
-	PHY_SETTING(    100, HALF,    100baseT_Half		),
-	PHY_SETTING(    100, HALF,    100baseFX_Half		),
-	PHY_SETTING(    100, FULL,    100baseFX_Full		),
-	/* 10M */
-	PHY_SETTING(     10, FULL,     10baseT_Full		),
-	PHY_SETTING(     10, HALF,     10baseT_Half		),
-	PHY_SETTING(     10, FULL,     10baseT1L_Full		),
-	PHY_SETTING(     10, FULL,     10baseT1S_Full		),
-	PHY_SETTING(     10, HALF,     10baseT1S_Half		),
-	PHY_SETTING(     10, HALF,     10baseT1S_P2MP_Half	),
-	PHY_SETTING(     10, FULL,     10baseT1BRR_Full		),
-};
-#undef PHY_SETTING
-
-/**
- * phy_lookup_setting - lookup a PHY setting
- * @speed: speed to match
- * @duplex: duplex to match
- * @mask: allowed link modes
- * @exact: an exact match is required
- *
- * Search the settings array for a setting that matches the speed and
- * duplex, and which is supported.
- *
- * If @exact is unset, either an exact match or %NULL for no match will
- * be returned.
- *
- * If @exact is set, an exact match, the fastest supported setting at
- * or below the specified speed, the slowest supported setting, or if
- * they all fail, %NULL will be returned.
- */
-const struct phy_setting *
-phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact)
-{
-	const struct phy_setting *p, *match = NULL, *last = NULL;
-	int i;
-
-	for (i = 0, p = settings; i < ARRAY_SIZE(settings); i++, p++) {
-		if (p->bit < __ETHTOOL_LINK_MODE_MASK_NBITS &&
-		    test_bit(p->bit, mask)) {
-			last = p;
-			if (p->speed == speed && p->duplex == duplex) {
-				/* Exact match for speed and duplex */
-				match = p;
-				break;
-			} else if (!exact) {
-				if (!match && p->speed <= speed)
-					/* Candidate */
-					match = p;
-
-				if (p->speed < speed)
-					break;
-			}
-		}
-	}
-
-	if (!match && !exact)
-		match = last;
-
-	return match;
-}
-EXPORT_SYMBOL_GPL(phy_lookup_setting);
-
 static void __set_phy_supported(struct phy_device *phydev, u32 max_speed)
 {
 	phy_caps_linkmode_max_speed(max_speed, phydev->supported);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 83c50bb219391..c24e1a5658196 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1275,19 +1275,6 @@ const char *phy_rate_matching_to_str(int rate_matching);
 
 int phy_interface_num_ports(phy_interface_t interface);
 
-/* A structure for mapping a particular speed and duplex
- * combination to a particular SUPPORTED and ADVERTISED value
- */
-struct phy_setting {
-	u32 speed;
-	u8 duplex;
-	u8 bit;
-};
-
-const struct phy_setting *
-phy_lookup_setting(int speed, int duplex, const unsigned long *mask,
-		   bool exact);
-
 /**
  * phy_is_started - Convenience function to check whether PHY is started
  * @phydev: The phy_device struct

From 3bea75002a05b86bf4d87773c456f39f7693f5c4 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:08 +0100
Subject: [PATCH 2197/2753] net: phylink: Add a mapping between MAC_CAPS and
 LINK_CAPS

phylink allows MAC drivers to report the capabilities in terms of speed,
duplex and pause support. This is done through a dedicated set of enum
values in the form of the MAC_ capabilities. They are very close to what
the LINK_CAPA_xxx can express, with the difference that LINK_CAPA don't
have any information about Pause/Asym Pause support.

To prepare converting phylink to using the phy_caps, add the mapping
between MAC capabilities and phy_caps. While doing so, we move the
phylink_caps_params array up a bit to simplify future commits.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-12-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phylink.c | 49 ++++++++++++++++++++-------------------
 1 file changed, 25 insertions(+), 24 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 694b836d8ff73..f9007bc14d54c 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -292,6 +292,31 @@ static int phylink_interface_max_speed(phy_interface_t interface)
 	return SPEED_UNKNOWN;
 }
 
+static struct {
+	unsigned long mask;
+	int speed;
+	unsigned int duplex;
+	unsigned int caps_bit;
+} phylink_caps_params[] = {
+	{ MAC_400000FD, SPEED_400000, DUPLEX_FULL, BIT(LINK_CAPA_400000FD) },
+	{ MAC_200000FD, SPEED_200000, DUPLEX_FULL, BIT(LINK_CAPA_200000FD) },
+	{ MAC_100000FD, SPEED_100000, DUPLEX_FULL, BIT(LINK_CAPA_100000FD) },
+	{ MAC_56000FD,  SPEED_56000,  DUPLEX_FULL, BIT(LINK_CAPA_56000FD) },
+	{ MAC_50000FD,  SPEED_50000,  DUPLEX_FULL, BIT(LINK_CAPA_50000FD) },
+	{ MAC_40000FD,  SPEED_40000,  DUPLEX_FULL, BIT(LINK_CAPA_40000FD) },
+	{ MAC_25000FD,  SPEED_25000,  DUPLEX_FULL, BIT(LINK_CAPA_25000FD) },
+	{ MAC_20000FD,  SPEED_20000,  DUPLEX_FULL, BIT(LINK_CAPA_20000FD) },
+	{ MAC_10000FD,  SPEED_10000,  DUPLEX_FULL, BIT(LINK_CAPA_10000FD) },
+	{ MAC_5000FD,   SPEED_5000,   DUPLEX_FULL, BIT(LINK_CAPA_5000FD) },
+	{ MAC_2500FD,   SPEED_2500,   DUPLEX_FULL, BIT(LINK_CAPA_2500FD) },
+	{ MAC_1000FD,   SPEED_1000,   DUPLEX_FULL, BIT(LINK_CAPA_1000FD) },
+	{ MAC_1000HD,   SPEED_1000,   DUPLEX_HALF, BIT(LINK_CAPA_1000HD) },
+	{ MAC_100FD,    SPEED_100,    DUPLEX_FULL, BIT(LINK_CAPA_100FD) },
+	{ MAC_100HD,    SPEED_100,    DUPLEX_HALF, BIT(LINK_CAPA_100HD) },
+	{ MAC_10FD,     SPEED_10,     DUPLEX_FULL, BIT(LINK_CAPA_10FD) },
+	{ MAC_10HD,     SPEED_10,     DUPLEX_HALF, BIT(LINK_CAPA_10HD) },
+};
+
 /**
  * phylink_caps_to_linkmodes() - Convert capabilities to ethtool link modes
  * @linkmodes: ethtool linkmode mask (must be already initialised)
@@ -445,30 +470,6 @@ static void phylink_caps_to_linkmodes(unsigned long *linkmodes,
 	}
 }
 
-static struct {
-	unsigned long mask;
-	int speed;
-	unsigned int duplex;
-} phylink_caps_params[] = {
-	{ MAC_400000FD, SPEED_400000, DUPLEX_FULL },
-	{ MAC_200000FD, SPEED_200000, DUPLEX_FULL },
-	{ MAC_100000FD, SPEED_100000, DUPLEX_FULL },
-	{ MAC_56000FD,  SPEED_56000,  DUPLEX_FULL },
-	{ MAC_50000FD,  SPEED_50000,  DUPLEX_FULL },
-	{ MAC_40000FD,  SPEED_40000,  DUPLEX_FULL },
-	{ MAC_25000FD,  SPEED_25000,  DUPLEX_FULL },
-	{ MAC_20000FD,  SPEED_20000,  DUPLEX_FULL },
-	{ MAC_10000FD,  SPEED_10000,  DUPLEX_FULL },
-	{ MAC_5000FD,   SPEED_5000,   DUPLEX_FULL },
-	{ MAC_2500FD,   SPEED_2500,   DUPLEX_FULL },
-	{ MAC_1000FD,   SPEED_1000,   DUPLEX_FULL },
-	{ MAC_1000HD,   SPEED_1000,   DUPLEX_HALF },
-	{ MAC_100FD,    SPEED_100,    DUPLEX_FULL },
-	{ MAC_100HD,    SPEED_100,    DUPLEX_HALF },
-	{ MAC_10FD,     SPEED_10,     DUPLEX_FULL },
-	{ MAC_10HD,     SPEED_10,     DUPLEX_HALF },
-};
-
 /**
  * phylink_limit_mac_speed - limit the phylink_config to a maximum speed
  * @config: pointer to a &struct phylink_config

From 4ca5b8a258b67aa5e06af56e53708cc23ea05e79 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:09 +0100
Subject: [PATCH 2198/2753] net: phylink: Convert capabilities to linkmodes
 using phy_caps

phylink_caps_to_linkmodes() is used to derive a list of linkmodes that
can be conceivably exposed using a given set of speeds and duplex
through phylink's MAC capabilities.

This list can be derived from the link_caps array in phy_caps, provided
we convert the MAC capabilities into a LINK_CAPA bitmask first.

Introduce an internal phylink helper phylink_caps_to_link_caps() to
convert from MAC capabilities into phy_caps, then  phy_caps_linkmodes()
to do the link_caps -> linkmodes conversion.

This avoids having to update phylink for every new linkmode.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-13-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |   1 +
 drivers/net/phy/phy_caps.c |  14 ++++
 drivers/net/phy/phylink.c  | 155 +++++--------------------------------
 3 files changed, 36 insertions(+), 134 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index aef4b54a8429d..7fc930876e332 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -44,6 +44,7 @@ size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 		       unsigned long *linkmodes);
 void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
 bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes);
+void phy_caps_linkmodes(unsigned long caps, unsigned long *linkmodes);
 
 const struct link_capabilities *
 phy_caps_lookup_by_linkmode(const unsigned long *linkmodes);
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 0366feee2912a..fc1568f83c1aa 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -251,3 +251,17 @@ bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes)
 
 	return linkmode_intersects(link_caps[capa].linkmodes, linkmodes);
 }
+
+/**
+ * phy_caps_linkmodes() - Convert a bitfield of capabilities into linkmodes
+ * @caps: The list of caps, each bit corresponding to a LINK_CAPA value
+ * @linkmodes: The set of linkmodes to fill. Must be previously initialized.
+ */
+void phy_caps_linkmodes(unsigned long caps, unsigned long *linkmodes)
+{
+	unsigned long capa;
+
+	for_each_set_bit(capa, &caps, __LINK_CAPA_MAX)
+		linkmode_or(linkmodes, linkmodes, link_caps[capa].linkmodes);
+}
+EXPORT_SYMBOL_GPL(phy_caps_linkmodes);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index f9007bc14d54c..947e6468776c0 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -317,6 +317,24 @@ static struct {
 	{ MAC_10HD,     SPEED_10,     DUPLEX_HALF, BIT(LINK_CAPA_10HD) },
 };
 
+/**
+ * phylink_caps_to_link_caps() - Convert a set of MAC capabilities LINK caps
+ * @caps: A set of MAC capabilities
+ *
+ * Returns: The corresponding set of LINK_CAPA as defined in phy-caps.h
+ */
+static unsigned long phylink_caps_to_link_caps(unsigned long caps)
+{
+	unsigned long link_caps = 0;
+	int i;
+
+	for (i = 0; i <  ARRAY_SIZE(phylink_caps_params); i++)
+		if (caps & phylink_caps_params[i].mask)
+			link_caps |= phylink_caps_params[i].caps_bit;
+
+	return link_caps;
+}
+
 /**
  * phylink_caps_to_linkmodes() - Convert capabilities to ethtool link modes
  * @linkmodes: ethtool linkmode mask (must be already initialised)
@@ -328,146 +346,15 @@ static struct {
 static void phylink_caps_to_linkmodes(unsigned long *linkmodes,
 				      unsigned long caps)
 {
+	unsigned long link_caps = phylink_caps_to_link_caps(caps);
+
 	if (caps & MAC_SYM_PAUSE)
 		__set_bit(ETHTOOL_LINK_MODE_Pause_BIT, linkmodes);
 
 	if (caps & MAC_ASYM_PAUSE)
 		__set_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, linkmodes);
 
-	if (caps & MAC_10HD) {
-		__set_bit(ETHTOOL_LINK_MODE_10baseT_Half_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10baseT1S_Half_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10baseT1S_P2MP_Half_BIT, linkmodes);
-	}
-
-	if (caps & MAC_10FD) {
-		__set_bit(ETHTOOL_LINK_MODE_10baseT_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10baseT1S_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_100HD) {
-		__set_bit(ETHTOOL_LINK_MODE_100baseT_Half_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100baseFX_Half_BIT, linkmodes);
-	}
-
-	if (caps & MAC_100FD) {
-		__set_bit(ETHTOOL_LINK_MODE_100baseT_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100baseFX_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_1000HD)
-		__set_bit(ETHTOOL_LINK_MODE_1000baseT_Half_BIT, linkmodes);
-
-	if (caps & MAC_1000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_1000baseX_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_2500FD) {
-		__set_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_5000FD)
-		__set_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, linkmodes);
-
-	if (caps & MAC_10000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_10000baseT_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseR_FEC_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseCR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseSR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseLR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseLRM_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_10000baseER_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_25000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_25000baseSR_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_40000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_40000baseSR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_40000baseLR4_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_50000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_50000baseCR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseKR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseSR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseKR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseSR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseCR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseLR_ER_FR_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_50000baseDR_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_56000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_100000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseSR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseKR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseSR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseCR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseLR2_ER2_FR2_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseDR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseKR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseSR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseLR_ER_FR_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseCR_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_100000baseDR_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_200000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_200000baseKR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseSR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseKR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseSR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseLR2_ER2_FR2_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseDR2_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_200000baseCR2_Full_BIT, linkmodes);
-	}
-
-	if (caps & MAC_400000FD) {
-		__set_bit(ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseKR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseSR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseLR4_ER4_FR4_Full_BIT,
-			  linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseDR4_Full_BIT, linkmodes);
-		__set_bit(ETHTOOL_LINK_MODE_400000baseCR4_Full_BIT, linkmodes);
-	}
+	phy_caps_linkmodes(link_caps, linkmodes);
 }
 
 /**

From 3bd87f3b4405cefa12b6be7ebf75a021cac4738a Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 7 Mar 2025 18:36:10 +0100
Subject: [PATCH 2199/2753] net: phylink: Use phy_caps to get an interface's
 capabilities and modes

Phylink has internal code to get the MAC capabilities of a given PHY
interface (what are the supported speed and duplex).

Extract that into phy_caps, but use the link_capa for conversion. Add an
internal phylink helper for the link caps -> mac caps conversion, and
use this in phylink_caps_to_linkmodes().

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250307173611.129125-14-maxime.chevallier@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-caps.h |  4 ++
 drivers/net/phy/phy_caps.c | 92 ++++++++++++++++++++++++++++++++++++++
 drivers/net/phy/phylink.c  | 90 ++++++-------------------------------
 3 files changed, 110 insertions(+), 76 deletions(-)

diff --git a/drivers/net/phy/phy-caps.h b/drivers/net/phy/phy-caps.h
index 7fc930876e332..157759966650e 100644
--- a/drivers/net/phy/phy-caps.h
+++ b/drivers/net/phy/phy-caps.h
@@ -8,6 +8,7 @@
 #define __PHY_CAPS_H
 
 #include <linux/ethtool.h>
+#include <linux/phy.h>
 
 enum {
 	LINK_CAPA_10HD = 0,
@@ -32,6 +33,8 @@ enum {
 	__LINK_CAPA_MAX,
 };
 
+#define LINK_CAPA_ALL	GENMASK((__LINK_CAPA_MAX - 1), 0)
+
 struct link_capabilities {
 	int speed;
 	unsigned int duplex;
@@ -45,6 +48,7 @@ size_t phy_caps_speeds(unsigned int *speeds, size_t size,
 void phy_caps_linkmode_max_speed(u32 max_speed, unsigned long *linkmodes);
 bool phy_caps_valid(int speed, int duplex, const unsigned long *linkmodes);
 void phy_caps_linkmodes(unsigned long caps, unsigned long *linkmodes);
+unsigned long phy_caps_from_interface(phy_interface_t interface);
 
 const struct link_capabilities *
 phy_caps_lookup_by_linkmode(const unsigned long *linkmodes);
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index fc1568f83c1aa..7033216897264 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -265,3 +265,95 @@ void phy_caps_linkmodes(unsigned long caps, unsigned long *linkmodes)
 		linkmode_or(linkmodes, linkmodes, link_caps[capa].linkmodes);
 }
 EXPORT_SYMBOL_GPL(phy_caps_linkmodes);
+
+/**
+ * phy_caps_from_interface() - Get the link capa from a given PHY interface
+ * @interface: The PHY interface we want to get the possible Speed/Duplex from
+ *
+ * Returns: A bitmask of LINK_CAPA_xxx values that can be achieved with the
+ *          provided interface.
+ */
+unsigned long phy_caps_from_interface(phy_interface_t interface)
+{
+	unsigned long link_caps = 0;
+
+	switch (interface) {
+	case PHY_INTERFACE_MODE_USXGMII:
+		link_caps |= BIT(LINK_CAPA_10000FD) | BIT(LINK_CAPA_5000FD);
+		fallthrough;
+
+	case PHY_INTERFACE_MODE_10G_QXGMII:
+		link_caps |= BIT(LINK_CAPA_2500FD);
+		fallthrough;
+
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_PSGMII:
+	case PHY_INTERFACE_MODE_QSGMII:
+	case PHY_INTERFACE_MODE_QUSGMII:
+	case PHY_INTERFACE_MODE_SGMII:
+	case PHY_INTERFACE_MODE_GMII:
+		link_caps |= BIT(LINK_CAPA_1000HD) | BIT(LINK_CAPA_1000FD);
+		fallthrough;
+
+	case PHY_INTERFACE_MODE_REVRMII:
+	case PHY_INTERFACE_MODE_RMII:
+	case PHY_INTERFACE_MODE_SMII:
+	case PHY_INTERFACE_MODE_REVMII:
+	case PHY_INTERFACE_MODE_MII:
+		link_caps |= BIT(LINK_CAPA_10HD) | BIT(LINK_CAPA_10FD);
+		fallthrough;
+
+	case PHY_INTERFACE_MODE_100BASEX:
+		link_caps |= BIT(LINK_CAPA_100HD) | BIT(LINK_CAPA_100FD);
+		break;
+
+	case PHY_INTERFACE_MODE_TBI:
+	case PHY_INTERFACE_MODE_MOCA:
+	case PHY_INTERFACE_MODE_RTBI:
+	case PHY_INTERFACE_MODE_1000BASEX:
+		link_caps |= BIT(LINK_CAPA_1000HD);
+		fallthrough;
+	case PHY_INTERFACE_MODE_1000BASEKX:
+	case PHY_INTERFACE_MODE_TRGMII:
+		link_caps |= BIT(LINK_CAPA_1000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_2500BASEX:
+		link_caps |= BIT(LINK_CAPA_2500FD);
+		break;
+
+	case PHY_INTERFACE_MODE_5GBASER:
+		link_caps |= BIT(LINK_CAPA_5000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_XGMII:
+	case PHY_INTERFACE_MODE_RXAUI:
+	case PHY_INTERFACE_MODE_XAUI:
+	case PHY_INTERFACE_MODE_10GBASER:
+	case PHY_INTERFACE_MODE_10GKR:
+		link_caps |= BIT(LINK_CAPA_10000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_25GBASER:
+		link_caps |= BIT(LINK_CAPA_25000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_XLGMII:
+		link_caps |= BIT(LINK_CAPA_40000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_INTERNAL:
+		link_caps |= LINK_CAPA_ALL;
+		break;
+
+	case PHY_INTERFACE_MODE_NA:
+	case PHY_INTERFACE_MODE_MAX:
+		break;
+	}
+
+	return link_caps;
+}
+EXPORT_SYMBOL_GPL(phy_caps_from_interface);
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 947e6468776c0..0f70a7f3dfccd 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -335,6 +335,18 @@ static unsigned long phylink_caps_to_link_caps(unsigned long caps)
 	return link_caps;
 }
 
+static unsigned long phylink_link_caps_to_mac_caps(unsigned long link_caps)
+{
+	unsigned long caps = 0;
+	int i;
+
+	for (i = 0; i <  ARRAY_SIZE(phylink_caps_params); i++)
+		if (link_caps & phylink_caps_params[i].caps_bit)
+			caps |= phylink_caps_params[i].mask;
+
+	return caps;
+}
+
 /**
  * phylink_caps_to_linkmodes() - Convert capabilities to ethtool link modes
  * @linkmodes: ethtool linkmode mask (must be already initialised)
@@ -412,86 +424,12 @@ static unsigned long phylink_get_capabilities(phy_interface_t interface,
 					      unsigned long mac_capabilities,
 					      int rate_matching)
 {
+	unsigned long link_caps = phy_caps_from_interface(interface);
 	int max_speed = phylink_interface_max_speed(interface);
 	unsigned long caps = MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
 	unsigned long matched_caps = 0;
 
-	switch (interface) {
-	case PHY_INTERFACE_MODE_USXGMII:
-		caps |= MAC_10000FD | MAC_5000FD;
-		fallthrough;
-
-	case PHY_INTERFACE_MODE_10G_QXGMII:
-		caps |= MAC_2500FD;
-		fallthrough;
-
-	case PHY_INTERFACE_MODE_RGMII_TXID:
-	case PHY_INTERFACE_MODE_RGMII_RXID:
-	case PHY_INTERFACE_MODE_RGMII_ID:
-	case PHY_INTERFACE_MODE_RGMII:
-	case PHY_INTERFACE_MODE_PSGMII:
-	case PHY_INTERFACE_MODE_QSGMII:
-	case PHY_INTERFACE_MODE_QUSGMII:
-	case PHY_INTERFACE_MODE_SGMII:
-	case PHY_INTERFACE_MODE_GMII:
-		caps |= MAC_1000HD | MAC_1000FD;
-		fallthrough;
-
-	case PHY_INTERFACE_MODE_REVRMII:
-	case PHY_INTERFACE_MODE_RMII:
-	case PHY_INTERFACE_MODE_SMII:
-	case PHY_INTERFACE_MODE_REVMII:
-	case PHY_INTERFACE_MODE_MII:
-		caps |= MAC_10HD | MAC_10FD;
-		fallthrough;
-
-	case PHY_INTERFACE_MODE_100BASEX:
-		caps |= MAC_100HD | MAC_100FD;
-		break;
-
-	case PHY_INTERFACE_MODE_TBI:
-	case PHY_INTERFACE_MODE_MOCA:
-	case PHY_INTERFACE_MODE_RTBI:
-	case PHY_INTERFACE_MODE_1000BASEX:
-		caps |= MAC_1000HD;
-		fallthrough;
-	case PHY_INTERFACE_MODE_1000BASEKX:
-	case PHY_INTERFACE_MODE_TRGMII:
-		caps |= MAC_1000FD;
-		break;
-
-	case PHY_INTERFACE_MODE_2500BASEX:
-		caps |= MAC_2500FD;
-		break;
-
-	case PHY_INTERFACE_MODE_5GBASER:
-		caps |= MAC_5000FD;
-		break;
-
-	case PHY_INTERFACE_MODE_XGMII:
-	case PHY_INTERFACE_MODE_RXAUI:
-	case PHY_INTERFACE_MODE_XAUI:
-	case PHY_INTERFACE_MODE_10GBASER:
-	case PHY_INTERFACE_MODE_10GKR:
-		caps |= MAC_10000FD;
-		break;
-
-	case PHY_INTERFACE_MODE_25GBASER:
-		caps |= MAC_25000FD;
-		break;
-
-	case PHY_INTERFACE_MODE_XLGMII:
-		caps |= MAC_40000FD;
-		break;
-
-	case PHY_INTERFACE_MODE_INTERNAL:
-		caps |= ~0;
-		break;
-
-	case PHY_INTERFACE_MODE_NA:
-	case PHY_INTERFACE_MODE_MAX:
-		break;
-	}
+	caps |= phylink_link_caps_to_mac_caps(link_caps);
 
 	switch (rate_matching) {
 	case RATE_MATCH_OPEN_LOOP:

From ea841520c50f5f7c72c8070e3b79e1927b94fabf Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Fri, 14 Mar 2025 09:38:53 +0530
Subject: [PATCH 2200/2753] wifi: nl80211: store chandef on the correct link
 when starting CAC

Link ID to store chandef is still being used as 0 even in case of MLO which
is incorrect. This leads to issue during CAC completion where link 0 as well
gets stopped.

Fixes: 0b7798232eee ("wifi: cfg80211/mac80211: use proper link ID for DFS")
Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250314-fix_starting_cac_during_mlo-v1-1-3b51617d7ea5@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 299d575cf60ee..1a9fc403d50d8 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -10182,7 +10182,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
 	switch (wdev->iftype) {
 	case NL80211_IFTYPE_AP:
 	case NL80211_IFTYPE_P2P_GO:
-		wdev->links[0].ap.chandef = chandef;
+		wdev->links[link_id].ap.chandef = chandef;
 		break;
 	case NL80211_IFTYPE_ADHOC:
 		wdev->u.ibss.chandef = chandef;

From d4c6ca39d6661c7877c3012db7ac1e4714732a71 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Thu, 13 Mar 2025 00:22:24 +0200
Subject: [PATCH 2201/2753] wifi: iwlwifi: mld: Rename
 WIPHY_DEBUGFS_HANDLER_WRAPPER to WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER

Renamed the macro WIPHY_DEBUGFS_HANDLER_WRAPPER to
WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER to better reflect its purpose as a
write handler.

Additionally, updated the corresponding macro
WIPHY_DEBUGFS_HANDLER_WRAPPER_MLD to
WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER_MLD for consistency.

This change does not alter the functionality but enhances the
maintainability of the code.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.bb8a1d7907c8.I53325f2f37ccaad2b212d35d10616e06c1555e48@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/debugfs.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
index 04c536db8b166..13d97184a31fb 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
 /*
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include "iface.h"
 #include "sta.h"
@@ -67,7 +67,7 @@ static const struct file_operations iwl_dbgfs_##name##_ops = {		\
 	.release = _iwl_dbgfs_release,					\
 }
 
-#define WIPHY_DEBUGFS_HANDLER_WRAPPER(name)				\
+#define WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER(name)			\
 static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
 				       struct file *file, char *buf,	\
 				       size_t count, void *data)	\
@@ -97,7 +97,7 @@ static inline struct iwl_mld *iwl_mld_from_vif(struct ieee80211_vif *vif)
 }
 
 #define WIPHY_DEBUGFS_WRITE_WRAPPER(name, bufsz, objtype)		\
-WIPHY_DEBUGFS_HANDLER_WRAPPER(name)					\
+WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER(name)				\
 static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 					  const char __user *user_buf,	\
 					  size_t count, loff_t *ppos)	\
@@ -121,7 +121,7 @@ static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 		.llseek = generic_file_llseek,				\
 	}
 
-#define WIPHY_DEBUGFS_HANDLER_WRAPPER_MLD(name)				\
+#define WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER_MLD(name)			\
 static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
 				       struct file *file, char *buf,	\
 				       size_t count, void *data)	\
@@ -132,7 +132,7 @@ static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
 }
 
 #define WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\
-WIPHY_DEBUGFS_HANDLER_WRAPPER_MLD(name)					\
+WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER_MLD(name)				\
 static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 					  const char __user *user_buf,	\
 					  size_t count, loff_t *ppos)	\
@@ -170,7 +170,7 @@ static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 	}
 
 #define WIPHY_DEBUGFS_WRITE_WRAPPER_IEEE80211(name, bufsz, objtype)	\
-WIPHY_DEBUGFS_HANDLER_WRAPPER(name)					\
+WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER(name)				\
 static ssize_t _iwl_dbgfs_##name##_write(struct file *file,		\
 					  const char __user *user_buf,	\
 					  size_t count, loff_t *ppos)	\

From 4b8130a722eb3634a8cde1e8cb1b113e488df5ac Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Thu, 13 Mar 2025 00:22:25 +0200
Subject: [PATCH 2202/2753] wifi: iwlwifi: mld: Add support for
 WIPHY_DEBUGFS_READ_FILE_OPS_MLD macro

Introduced the WIPHY_DEBUGFS_READ_FILE_OPS_MLD macro to enable reading
data from the driver while holding the wiphy lock.
This will enable read operations with wiphy locked.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.b0ddb6b0a144.I1fab63f2c6f52fea61cc5d7b27775aed58adfd8d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/debugfs.h  | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
index 13d97184a31fb..900aaed907756 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
@@ -121,6 +121,16 @@ static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 		.llseek = generic_file_llseek,				\
 	}
 
+#define WIPHY_DEBUGFS_READ_HANDLER_WRAPPER_MLD(name)			\
+static ssize_t iwl_dbgfs_##name##_read_handler(struct wiphy *wiphy,	\
+				       struct file *file, char *buf,	\
+				       size_t count, void *data)	\
+{									\
+	struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);		\
+	struct iwl_mld *mld = IWL_MAC80211_GET_MLD(hw);			\
+	return iwl_dbgfs_##name##_read(mld, buf, count);		\
+}
+
 #define WIPHY_DEBUGFS_WRITE_HANDLER_WRAPPER_MLD(name)			\
 static ssize_t iwl_dbgfs_##name##_write_handler(struct wiphy *wiphy,	\
 				       struct file *file, char *buf,	\
@@ -147,6 +157,40 @@ static ssize_t __iwl_dbgfs_##name##_write(struct file *file,		\
 				NULL);					\
 }
 
+#define WIPHY_DEBUGFS_READ_WRAPPER_MLD(name)				\
+WIPHY_DEBUGFS_READ_HANDLER_WRAPPER_MLD(name)				\
+static ssize_t __iwl_dbgfs_##name##_read(struct file *file,		\
+					char __user *user_buf,		\
+					size_t count, loff_t *ppos)	\
+{									\
+	struct dbgfs_##name##_data *data = file->private_data;		\
+	struct iwl_mld *mld = data->arg;				\
+									\
+	if (!data->read_done) {						\
+		data->read_done = true;					\
+		data->rlen = wiphy_locked_debugfs_read(mld->wiphy,	\
+				file, data->buf, sizeof(data->buf),	\
+				user_buf, count, ppos,			\
+				iwl_dbgfs_##name##_read_handler, NULL);	\
+		return data->rlen;					\
+	}								\
+									\
+	if (data->rlen < 0)						\
+		return data->rlen;					\
+	return simple_read_from_buffer(user_buf, count, ppos,		\
+				       data->buf, data->rlen);		\
+}
+
+#define WIPHY_DEBUGFS_READ_FILE_OPS_MLD(name, bufsz)			\
+	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct iwl_mld)		\
+	WIPHY_DEBUGFS_READ_WRAPPER_MLD(name)				\
+	static const struct file_operations iwl_dbgfs_##name##_ops = {	\
+		.read = __iwl_dbgfs_##name##_read,			\
+		.open = _iwl_dbgfs_##name##_open,			\
+		.llseek = generic_file_llseek,				\
+		.release = _iwl_dbgfs_release,				\
+	}
+
 #define WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(name, bufsz)			\
 	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct iwl_mld)		\
 	WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\

From 8301e2636c106f28f0deca5d73fe72015db6acb2 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Thu, 13 Mar 2025 00:22:26 +0200
Subject: [PATCH 2203/2753] wifi: iwlwifi: mld: Ensure wiphy lock is held
 during debugfs read operations

The WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD macro is intended to call
read/write handlers with the wiphy lock held. However, the current
implementation uses the MLD_DEBUGFS_READ_WRAPPER macro, which does
not hold the wiphy lock during read operations. This fix updates
the WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD macro to use the
WIPHY_DEBUGFS_READ_WRAPPER_MLD macro instead, ensuring that the
wiphy lock is held during both read and write operations.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.2001d2335e9d.I607a8bd12efc6d1190cef1fca44279dbdd2756ea@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/debugfs.c | 3 +--
 drivers/net/wireless/intel/iwlwifi/mld/debugfs.h | 4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index 1d4b2ad5d3889..c67dbbf575d73 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -178,8 +178,7 @@ iwl_dbgfs_he_sniffer_params_write(struct iwl_mld *mld, char *buf,
 }
 
 static ssize_t
-iwl_dbgfs_he_sniffer_params_read(struct iwl_mld *mld, size_t count,
-				 char *buf)
+iwl_dbgfs_he_sniffer_params_read(struct iwl_mld *mld, char *buf, size_t count)
 {
 	return scnprintf(buf, count,
 			 "%d %02hhx:%02hhx:%02hhx:%02hhx:%02hhx:%02hhx\n",
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
index 900aaed907756..eeba35342ba1b 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.h
@@ -204,10 +204,10 @@ static ssize_t __iwl_dbgfs_##name##_read(struct file *file,		\
 #define WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD(name, bufsz)		\
 	MLD_DEBUGFS_OPEN_WRAPPER(name, bufsz, struct iwl_mld)		\
 	WIPHY_DEBUGFS_WRITE_WRAPPER_MLD(name)				\
-	MLD_DEBUGFS_READ_WRAPPER(name)					\
+	WIPHY_DEBUGFS_READ_WRAPPER_MLD(name)				\
 	static const struct file_operations iwl_dbgfs_##name##_ops = {	\
 		.write = __iwl_dbgfs_##name##_write,			\
-		.read = _iwl_dbgfs_##name##_read,			\
+		.read = __iwl_dbgfs_##name##_read,			\
 		.open = _iwl_dbgfs_##name##_open,			\
 		.llseek = generic_file_llseek,				\
 		.release = _iwl_dbgfs_release,				\

From b611cf6b57a8091a2ebbe415f421865407968ef2 Mon Sep 17 00:00:00 2001
From: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Date: Thu, 13 Mar 2025 00:22:27 +0200
Subject: [PATCH 2204/2753] wifi: iwlwifi: mld: add support for
 DHC_TOOLS_UMAC_GET_TAS_STATUS command

Add debugfs file in mld to retrieve TAS status per radio, TAS block list,
current mcc, OEM name and OEM allowed list. This will add ability to get
TAS status to user application via debugfs and required for debugging.

Add the required API definitions and some debug host command utils.

Signed-off-by: Pagadala Yesu Anjaneyulu <pagadala.yesu.anjaneyulu@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.66524c6ea198.I1625135284fc075148a55dd9ac629e94ca881fe4@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/fw/api/dhc.h   |  97 ++++++++
 .../net/wireless/intel/iwlwifi/fw/dhc-utils.h |  75 ++++++
 .../net/wireless/intel/iwlwifi/mld/debugfs.c  | 232 ++++++++++++++++++
 3 files changed, 404 insertions(+)
 create mode 100644 drivers/net/wireless/intel/iwlwifi/fw/dhc-utils.h

diff --git a/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h b/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h
index dbe06f3fc6626..b6d79c678cd89 100644
--- a/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h
+++ b/drivers/net/wireless/intel/iwlwifi/fw/api/dhc.h
@@ -15,6 +15,19 @@ enum iwl_dhc_table_id {
 	 * @DHC_TABLE_INTEGRATION: select the integration table
 	 */
 	DHC_TABLE_INTEGRATION	= 2 << DHC_TABLE_MASK_POS,
+	/**
+	 * @DHC_TABLE_TOOLS: select the tools table
+	 */
+	DHC_TABLE_TOOLS		= 0,
+};
+
+/**
+ * enum iwl_dhc_umac_tools_table - tools operations
+ * @DHC_TOOLS_UMAC_GET_TAS_STATUS: Get TAS status.
+ *	See @struct iwl_dhc_tas_status_resp
+ */
+enum iwl_dhc_umac_tools_table {
+	DHC_TOOLS_UMAC_GET_TAS_STATUS = 0,
 };
 
 /**
@@ -58,6 +71,90 @@ struct iwl_dhc_cmd {
 	__le32 data[];
 } __packed; /* DHC_CMD_API_S */
 
+/**
+ * struct iwl_dhc_payload_hdr - DHC payload header
+ * @version: a version of a payload
+ * @reserved: reserved for alignment
+ */
+struct iwl_dhc_payload_hdr {
+	u8 version;
+	u8 reserved[3];
+} __packed; /* DHC_PAYLOAD_HDR_API_S_VER_1 */
+
+/**
+ * struct iwl_dhc_tas_status_per_radio - TAS status per radio
+ * @band: &PHY_BAND_5 for high band, PHY_BAND_24 for low band and
+ *	&PHY_BAND_6 for ultra high band.
+ * @static_status: TAS statically enabled or disabled
+ * @static_disable_reason: TAS static disable reason, uses
+ *	&enum iwl_tas_statically_disabled_reason
+ * @near_disconnection: is TAS currently near disconnection per radio
+ * @dynamic_status_ant_a: Antenna A current TAS status.
+ *	uses &enum iwl_tas_dyna_status
+ * @dynamic_status_ant_b: Antenna B current TAS status.
+ *	uses &enum iwl_tas_dyna_status
+ * @max_reg_pwr_limit_ant_a: Antenna A regulatory power limits in dBm
+ * @max_reg_pwr_limit_ant_b: Antenna B regulatory power limits in dBm
+ * @sar_limit_ant_a: Antenna A SAR limit per radio in dBm
+ * @sar_limit_ant_b: Antenna B SAR limit per radio in dBm
+ * @reserved: reserved for alignment
+ */
+struct iwl_dhc_tas_status_per_radio {
+	u8 band;
+	u8 static_status;
+	u8 static_disable_reason;
+	u8 near_disconnection;
+	u8 dynamic_status_ant_a;
+	u8 dynamic_status_ant_b;
+	__le16 max_reg_pwr_limit_ant_a;
+	__le16 max_reg_pwr_limit_ant_b;
+	__le16 sar_limit_ant_a;
+	__le16 sar_limit_ant_b;
+	u8 reserved[2];
+} __packed; /* DHC_TAS_STATUS_PER_RADIO_S_VER_1 */
+
+/**
+ * struct iwl_dhc_tas_status_resp - Response to DHC_TOOLS_UMAC_GET_TAS_STATUS
+ * @header: DHC payload header, uses &struct iwl_dhc_payload_hdr
+ * @tas_config_info: see @struct bios_value_u32
+ * @mcc_block_list: block listed country codes
+ * @tas_status_radio: TAS status, uses &struct iwl_dhc_tas_status_per_radio
+ * @curr_mcc: current mcc
+ * @valid_radio_mask: represent entry in tas_status_per_radio is valid.
+ * @reserved: reserved for alignment
+ */
+struct iwl_dhc_tas_status_resp {
+	struct iwl_dhc_payload_hdr header;
+	struct bios_value_u32 tas_config_info;
+	__le16 mcc_block_list[IWL_WTAS_BLACK_LIST_MAX];
+	struct iwl_dhc_tas_status_per_radio tas_status_radio[2];
+	__le16 curr_mcc;
+	u8 valid_radio_mask;
+	u8 reserved;
+} __packed; /* DHC_TAS_STATUS_RSP_API_S_VER_1 */
+
+/**
+ * struct iwl_dhc_cmd_resp_v1 - debug host command response
+ * @status: status of the command
+ * @data: the response data
+ */
+struct iwl_dhc_cmd_resp_v1 {
+	__le32 status;
+	__le32 data[];
+} __packed; /* DHC_RESP_API_S_VER_1 */
+
+/**
+ * struct iwl_dhc_cmd_resp - debug host command response
+ * @status: status of the command
+ * @descriptor: command descriptor (index_and_mask) returned
+ * @data: the response data
+ */
+struct iwl_dhc_cmd_resp {
+	__le32 status;
+	__le32 descriptor;
+	__le32 data[];
+} __packed; /* DHC_RESP_API_S_VER_2 and DHC_RESP_API_S_VER_3 */
+
 /**
  * enum iwl_dhc_twt_operation_type - describes the TWT operation type
  *
diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dhc-utils.h b/drivers/net/wireless/intel/iwlwifi/fw/dhc-utils.h
new file mode 100644
index 0000000000000..983acee5cd7d8
--- /dev/null
+++ b/drivers/net/wireless/intel/iwlwifi/fw/dhc-utils.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause */
+/*
+ * Copyright (C) 2021, 2025 Intel Corporation
+ */
+#ifndef __iwl_fw_dhc_utils_h__
+#define __iwl_fw_dhc_utils_h__
+
+#include <linux/types.h>
+#include "fw/img.h"
+#include "api/commands.h"
+#include "api/dhc.h"
+
+/**
+ * iwl_dhc_resp_status - return status of DHC response
+ * @fw: firwmware image information
+ * @pkt: response packet, must not be %NULL
+ *
+ * Returns: the status value of the DHC command or (u32)-1 if the
+ *	    response was too short.
+ */
+static inline u32 iwl_dhc_resp_status(const struct iwl_fw *fw,
+				      struct iwl_rx_packet *pkt)
+{
+	if (iwl_fw_lookup_notif_ver(fw, IWL_ALWAYS_LONG_GROUP,
+				    DEBUG_HOST_COMMAND, 1) >= 2) {
+		struct iwl_dhc_cmd_resp *resp = (void *)pkt->data;
+
+		if (iwl_rx_packet_payload_len(pkt) < sizeof(*resp))
+			return (u32)-1;
+
+		return le32_to_cpu(resp->status);
+	} else {
+		struct iwl_dhc_cmd_resp_v1 *resp = (void *)pkt->data;
+
+		if (iwl_rx_packet_payload_len(pkt) < sizeof(*resp))
+			return (u32)-1;
+
+		return le32_to_cpu(resp->status);
+	}
+}
+
+/**
+ * iwl_dhc_resp_data - return data pointer of DHC response
+ * @fw: firwmware image information
+ * @pkt: response packet, must not be %NULL
+ * @len: where to store the length
+ *
+ * Returns: The data pointer, or an ERR_PTR() if the data was
+ *	    not valid (too short).
+ */
+static inline void *iwl_dhc_resp_data(const struct iwl_fw *fw,
+				      struct iwl_rx_packet *pkt,
+				      unsigned int *len)
+{
+	if (iwl_fw_lookup_notif_ver(fw, IWL_ALWAYS_LONG_GROUP,
+				    DEBUG_HOST_COMMAND, 1) >= 2) {
+		struct iwl_dhc_cmd_resp *resp = (void *)pkt->data;
+
+		if (iwl_rx_packet_payload_len(pkt) < sizeof(*resp))
+			return ERR_PTR(-EINVAL);
+
+		*len = iwl_rx_packet_payload_len(pkt) - sizeof(*resp);
+		return (void *)&resp->data;
+	} else {
+		struct iwl_dhc_cmd_resp_v1 *resp = (void *)pkt->data;
+
+		if (iwl_rx_packet_payload_len(pkt) < sizeof(*resp))
+			return ERR_PTR(-EINVAL);
+
+		*len = iwl_rx_packet_payload_len(pkt) - sizeof(*resp);
+		return (void *)&resp->data;
+	}
+}
+
+#endif  /* __iwl_fw_dhc_utils_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index c67dbbf575d73..14330daa6d138 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -21,6 +21,8 @@
 #include "fw/api/rs.h"
 #include "fw/api/dhc.h"
 #include "fw/api/rfi.h"
+#include "fw/dhc-utils.h"
+#include <linux/dmi.h>
 
 #define MLD_DEBUGFS_READ_FILE_OPS(name, bufsz)				\
 	_MLD_DEBUGFS_READ_FILE_OPS(name, bufsz, struct iwl_mld)
@@ -206,11 +208,240 @@ iwl_dbgfs_he_sniffer_params_read(struct iwl_mld *mld, char *buf, size_t count)
 #define IWL_RFI_BUF_SIZE (IWL_RFI_DDR_BUF_SIZE + IWL_RFI_DLVR_BUF_SIZE +\
 				IWL_RFI_DESENSE_BUF_SIZE + 32)
 
+static size_t iwl_mld_dump_tas_resp(struct iwl_dhc_tas_status_resp *resp,
+				    size_t count, u8 *buf)
+{
+	const char * const tas_dis_reason[TAS_DISABLED_REASON_MAX] = {
+		[TAS_DISABLED_DUE_TO_BIOS] =
+			"Due To BIOS",
+		[TAS_DISABLED_DUE_TO_SAR_6DBM] =
+			"Due To SAR Limit Less Than 6 dBm",
+		[TAS_DISABLED_REASON_INVALID] =
+			"N/A",
+		[TAS_DISABLED_DUE_TO_TABLE_SOURCE_INVALID] =
+			"Due to table source invalid"
+	};
+	const char * const tas_current_status[TAS_DYNA_STATUS_MAX] = {
+		[TAS_DYNA_INACTIVE] = "INACTIVE",
+		[TAS_DYNA_INACTIVE_MVM_MODE] =
+			"inactive due to mvm mode",
+		[TAS_DYNA_INACTIVE_TRIGGER_MODE] =
+			"inactive due to trigger mode",
+		[TAS_DYNA_INACTIVE_BLOCK_LISTED] =
+			"inactive due to block listed",
+		[TAS_DYNA_INACTIVE_UHB_NON_US] =
+			"inactive due to uhb non US",
+		[TAS_DYNA_ACTIVE] = "ACTIVE",
+	};
+	ssize_t pos = 0;
+
+	if (resp->header.version != 1) {
+		pos += scnprintf(buf + pos, count - pos,
+				 "Unsupported TAS response version:%d",
+				 resp->header.version);
+		return pos;
+	}
+
+	pos += scnprintf(buf + pos, count - pos, "TAS Report\n");
+	switch (resp->tas_config_info.table_source) {
+	case BIOS_SOURCE_NONE:
+		pos += scnprintf(buf + pos, count - pos,
+				 "BIOS SOURCE NONE ");
+		break;
+	case BIOS_SOURCE_ACPI:
+		pos += scnprintf(buf + pos, count - pos,
+				 "BIOS SOURCE ACPI ");
+		break;
+	case BIOS_SOURCE_UEFI:
+		pos += scnprintf(buf + pos, count - pos,
+				 "BIOS SOURCE UEFI ");
+		break;
+	default:
+		pos += scnprintf(buf + pos, count - pos,
+				 "BIOS SOURCE UNKNOWN (%d) ",
+				 resp->tas_config_info.table_source);
+		break;
+	}
+
+	pos += scnprintf(buf + pos, count - pos,
+			 "revision is: %d data is: 0x%08x\n",
+			 resp->tas_config_info.table_revision,
+			 resp->tas_config_info.value);
+	pos += scnprintf(buf + pos, count - pos, "Current MCC: 0x%x\n",
+			 le16_to_cpu(resp->curr_mcc));
+
+	pos += scnprintf(buf + pos, count - pos, "Block list entries:");
+	for (int i = 0; i < ARRAY_SIZE(resp->mcc_block_list); i++)
+		pos += scnprintf(buf + pos, count - pos, " 0x%x",
+				 le16_to_cpu(resp->mcc_block_list[i]));
+
+	pos += scnprintf(buf + pos, count - pos,
+			 "\nDo TAS Support Dual Radio?: %s\n",
+			 hweight8(resp->valid_radio_mask) > 1 ?
+			 "TRUE" : "FALSE");
+
+	for (int i = 0; i < ARRAY_SIZE(resp->tas_status_radio); i++) {
+		int tmp;
+		unsigned long dynamic_status;
+
+		if (!(resp->valid_radio_mask & BIT(i)))
+			continue;
+
+		pos += scnprintf(buf + pos, count - pos,
+				 "TAS report for radio:%d\n", i + 1);
+		pos += scnprintf(buf + pos, count - pos,
+				 "Static status: %sabled\n",
+				 resp->tas_status_radio[i].static_status ?
+				 "En" : "Dis");
+		if (!resp->tas_status_radio[i].static_status) {
+			u8 static_disable_reason =
+				resp->tas_status_radio[i].static_disable_reason;
+
+			pos += scnprintf(buf + pos, count - pos,
+					 "\tStatic Disabled Reason: ");
+			if (static_disable_reason >= TAS_DISABLED_REASON_MAX) {
+				pos += scnprintf(buf + pos, count - pos,
+						 "unsupported value (%d)\n",
+						 static_disable_reason);
+				continue;
+			}
+
+			pos += scnprintf(buf + pos, count - pos,
+					 "%s (%d)\n",
+					 tas_dis_reason[static_disable_reason],
+					 static_disable_reason);
+			continue;
+		}
+
+		pos += scnprintf(buf + pos, count - pos, "\tANT A %s and ",
+				 (resp->tas_status_radio[i].dynamic_status_ant_a
+				  & BIT(TAS_DYNA_ACTIVE)) ? "ON" : "OFF");
+
+		pos += scnprintf(buf + pos, count - pos, "ANT B %s for ",
+				 (resp->tas_status_radio[i].dynamic_status_ant_b
+				  & BIT(TAS_DYNA_ACTIVE)) ? "ON" : "OFF");
+
+		switch (resp->tas_status_radio[i].band) {
+		case PHY_BAND_5:
+			pos += scnprintf(buf + pos, count - pos, "HB\n");
+			break;
+		case PHY_BAND_24:
+			pos += scnprintf(buf + pos, count - pos, "LB\n");
+			break;
+		case PHY_BAND_6:
+			pos += scnprintf(buf + pos, count - pos, "UHB\n");
+			break;
+		default:
+			pos += scnprintf(buf + pos, count - pos,
+					 "Unsupported band (%d)\n",
+					 resp->tas_status_radio[i].band);
+			break;
+		}
+
+		pos += scnprintf(buf + pos, count - pos,
+				 "Is near disconnection?: %s\n",
+				 resp->tas_status_radio[i].near_disconnection ?
+				 "True" : "False");
+
+		pos += scnprintf(buf + pos, count - pos,
+				 "Dynamic status antenna A:\n");
+		dynamic_status = resp->tas_status_radio[i].dynamic_status_ant_a;
+		for_each_set_bit(tmp, &dynamic_status, TAS_DYNA_STATUS_MAX) {
+			pos += scnprintf(buf + pos, count - pos, "\t%s (%d)\n",
+					 tas_current_status[tmp], tmp);
+		}
+		pos += scnprintf(buf + pos, count - pos,
+				 "\nDynamic status antenna B:\n");
+		dynamic_status = resp->tas_status_radio[i].dynamic_status_ant_b;
+		for_each_set_bit(tmp, &dynamic_status, TAS_DYNA_STATUS_MAX) {
+			pos += scnprintf(buf + pos, count - pos, "\t%s (%d)\n",
+					 tas_current_status[tmp], tmp);
+		}
+
+		tmp = le16_to_cpu(resp->tas_status_radio[i].max_reg_pwr_limit_ant_a);
+		pos += scnprintf(buf + pos, count - pos,
+				 "Max antenna A regulatory pwr limit (dBm): %d.%03d\n",
+				 tmp / 8, 125 * (tmp % 8));
+		tmp = le16_to_cpu(resp->tas_status_radio[i].max_reg_pwr_limit_ant_b);
+		pos += scnprintf(buf + pos, count - pos,
+				 "Max antenna B regulatory pwr limit (dBm): %d.%03d\n",
+				 tmp / 8, 125 * (tmp % 8));
+
+		tmp = le16_to_cpu(resp->tas_status_radio[i].sar_limit_ant_a);
+		pos += scnprintf(buf + pos, count - pos,
+				 "Antenna A SAR limit (dBm): %d.%03d\n",
+				 tmp / 8, 125 * (tmp % 8));
+		tmp = le16_to_cpu(resp->tas_status_radio[i].sar_limit_ant_b);
+		pos += scnprintf(buf + pos, count - pos,
+				 "Antenna B SAR limit (dBm): %d.%03d\n",
+				 tmp / 8, 125 * (tmp % 8));
+	}
+
+	return pos;
+}
+
+static ssize_t iwl_dbgfs_tas_get_status_read(struct iwl_mld *mld, char *buf,
+					     size_t count)
+{
+	struct iwl_dhc_cmd cmd = {
+		.index_and_mask = cpu_to_le32(DHC_TABLE_TOOLS |
+					      DHC_TARGET_UMAC |
+					      DHC_TOOLS_UMAC_GET_TAS_STATUS),
+	};
+	struct iwl_host_cmd hcmd = {
+		.id = WIDE_ID(LEGACY_GROUP, DEBUG_HOST_COMMAND),
+		.flags = CMD_WANT_SKB,
+		.len[0] = sizeof(cmd),
+		.data[0] = &cmd,
+	};
+	struct iwl_dhc_tas_status_resp *resp = NULL;
+	ssize_t pos = 0;
+	u32 resp_len;
+	u32 status;
+	int ret;
+
+	if (iwl_mld_dbgfs_fw_cmd_disabled(mld))
+		return -EIO;
+
+	ret = iwl_mld_send_cmd(mld, &hcmd);
+	if (ret)
+		return ret;
+
+	pos += scnprintf(buf + pos, count - pos, "\nOEM name: %s\n",
+			 dmi_get_system_info(DMI_SYS_VENDOR) ?: "<unknown>");
+	pos += scnprintf(buf + pos, count - pos,
+			 "\tVendor In Approved List: %s\n",
+			 iwl_is_tas_approved() ? "YES" : "NO");
+
+	status = iwl_dhc_resp_status(mld->fwrt.fw, hcmd.resp_pkt);
+	if (status != 1) {
+		pos += scnprintf(buf + pos, count - pos,
+				 "response status is not success: %d\n",
+				 status);
+		goto out;
+	}
+
+	resp = iwl_dhc_resp_data(mld->fwrt.fw, hcmd.resp_pkt, &resp_len);
+	if (IS_ERR(resp) || resp_len != sizeof(*resp)) {
+		pos += scnprintf(buf + pos, count - pos,
+			"Invalid size for TAS response (%u instead of %zd)\n",
+			resp_len, sizeof(*resp));
+		goto out;
+	}
+
+	pos += iwl_mld_dump_tas_resp(resp, count - pos, buf + pos);
+
+out:
+	iwl_free_resp(&hcmd);
+	return pos;
+}
+
 WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_nmi, 10);
 WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_restart, 10);
 WIPHY_DEBUGFS_READ_WRITE_FILE_OPS_MLD(he_sniffer_params, 32);
 WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(fw_dbg_clear, 10);
 WIPHY_DEBUGFS_WRITE_FILE_OPS_MLD(send_echo_cmd, 8);
+WIPHY_DEBUGFS_READ_FILE_OPS_MLD(tas_get_status, 2048);
 
 static ssize_t iwl_dbgfs_wifi_6e_enable_read(struct iwl_mld *mld,
 					     size_t count, u8 *buf)
@@ -307,6 +538,7 @@ iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir)
 	MLD_DEBUGFS_ADD_FILE(he_sniffer_params, debugfs_dir, 0600);
 	MLD_DEBUGFS_ADD_FILE(fw_dbg_clear, debugfs_dir, 0200);
 	MLD_DEBUGFS_ADD_FILE(send_echo_cmd, debugfs_dir, 0200);
+	MLD_DEBUGFS_ADD_FILE(tas_get_status, debugfs_dir, 0400);
 #ifdef CONFIG_THERMAL
 	MLD_DEBUGFS_ADD_FILE(start_ctdp, debugfs_dir, 0200);
 	MLD_DEBUGFS_ADD_FILE(stop_ctdp, debugfs_dir, 0200);

From 4d7236f968f27af942347fe1c8363764cdee63f5 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:28 +0200
Subject: [PATCH 2205/2753] wifi: iwlwifi: mld: remove IWL_MLD_EMLSR_BLOCKED_FW

The channel load logic moves from the FW to the driver.
- Implement the logic: allow EMLSR only if the candidate primary link is
  active and if its average channel load exceeds the threshold.
- Remove IWL_MLD_EMLSR_BLOCKED_FW. Instead, treat ESR_RECOMMEND_LEAVE in
  the EMLSR_RECOMMENDATION notif as an EXIT reason.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.6729a8d67815.Iab39bf0982d8cdbb0db701d31854101c2fcf3b64@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../wireless/intel/iwlwifi/mld/constants.h    |   2 +-
 .../net/wireless/intel/iwlwifi/mld/iface.h    |  12 +-
 .../net/wireless/intel/iwlwifi/mld/mac80211.c |  13 +-
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  | 130 ++++++++++++++----
 drivers/net/wireless/intel/iwlwifi/mld/mlo.h  |   5 +-
 .../net/wireless/intel/iwlwifi/mld/stats.c    |  10 +-
 6 files changed, 124 insertions(+), 48 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/constants.h b/drivers/net/wireless/intel/iwlwifi/mld/constants.h
index 9a24996014b8d..2a59b29b75cb2 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/constants.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/constants.h
@@ -68,7 +68,7 @@
 #define IWL_MLD_LOW_RSSI_THRESH_160MHZ		-72
 
 #define IWL_MLD_ENTER_EMLSR_TPT_THRESH		400
-#define IWL_MLD_CHAN_LOAD_THRESH		2 /* in percentage */
+#define IWL_MLD_EXIT_EMLSR_CHAN_LOAD		2 /* in percentage */
 
 #define IWL_MLD_FTM_INITIATOR_ALGO		IWL_TOF_ALGO_TYPE_MAX_LIKE
 #define IWL_MLD_FTM_INITIATOR_DYNACK		true
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
index 57910660ed186..550ae3c9d766a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -24,7 +24,6 @@ enum iwl_mld_cca_40mhz_wa_status {
  *
  * @IWL_MLD_EMLSR_BLOCKED_PREVENTION: Prevent repeated EMLSR enter/exit
  * @IWL_MLD_EMLSR_BLOCKED_WOWLAN: WOWLAN is preventing EMLSR
- * @IWL_MLD_EMLSR_BLOCKED_FW: FW did not recommend MLO
  * @IWL_MLD_EMLSR_BLOCKED_ROC: remain-on-channel is preventing EMLSR
  * @IWL_MLD_EMLSR_BLOCKED_NON_BSS: An active non-BSS interface's link is
  *      preventing EMLSR
@@ -36,11 +35,10 @@ enum iwl_mld_cca_40mhz_wa_status {
 enum iwl_mld_emlsr_blocked {
 	IWL_MLD_EMLSR_BLOCKED_PREVENTION	= 0x1,
 	IWL_MLD_EMLSR_BLOCKED_WOWLAN		= 0x2,
-	IWL_MLD_EMLSR_BLOCKED_FW		= 0x4,
-	IWL_MLD_EMLSR_BLOCKED_ROC		= 0x8,
-	IWL_MLD_EMLSR_BLOCKED_NON_BSS		= 0x10,
-	IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS	= 0x20,
-	IWL_MLD_EMLSR_BLOCKED_TPT		= 0x40,
+	IWL_MLD_EMLSR_BLOCKED_ROC		= 0x4,
+	IWL_MLD_EMLSR_BLOCKED_NON_BSS		= 0x8,
+	IWL_MLD_EMLSR_BLOCKED_TMP_NON_BSS	= 0x10,
+	IWL_MLD_EMLSR_BLOCKED_TPT		= 0x20,
 };
 
 /**
@@ -62,6 +60,7 @@ enum iwl_mld_emlsr_blocked {
  * @IWL_MLD_EMLSR_EXIT_CHAN_LOAD: Exit EMLSR because the primary channel is not
  *	loaded enough to justify EMLSR.
  * @IWL_MLD_EMLSR_EXIT_RFI: Exit EMLSR due to RFI
+ * @IWL_MLD_EMLSR_EXIT_FW_REQUEST: Exit EMLSR because the FW requested it
  */
 enum iwl_mld_emlsr_exit {
 	IWL_MLD_EMLSR_EXIT_BLOCK		= 0x1,
@@ -75,6 +74,7 @@ enum iwl_mld_emlsr_exit {
 	IWL_MLD_EMLSR_EXIT_BT_COEX		= 0x100,
 	IWL_MLD_EMLSR_EXIT_CHAN_LOAD		= 0x200,
 	IWL_MLD_EMLSR_EXIT_RFI			= 0x400,
+	IWL_MLD_EMLSR_EXIT_FW_REQUEST		= 0x800,
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 91e201fde72aa..f6623988fff6a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -1189,8 +1189,13 @@ iwl_mld_mac80211_link_info_changed_sta(struct iwl_mld *mld,
 		iwl_mld_omi_ap_changed_bw(mld, link_conf, bw);
 	}
 
-	if (changes & BSS_CHANGED_BANDWIDTH)
-		iwl_mld_emlsr_check_equal_bw(mld, vif, link_conf);
+	if (changes & BSS_CHANGED_BANDWIDTH) {
+		if (iwl_mld_emlsr_active(vif))
+			iwl_mld_emlsr_check_equal_bw(mld, vif, link_conf);
+		else
+			/* Channel load threshold may have changed */
+			iwl_mld_retry_emlsr(mld, vif);
+	}
 }
 
 static int iwl_mld_update_mu_groups(struct iwl_mld *mld,
@@ -1712,10 +1717,6 @@ static int iwl_mld_move_sta_state_up(struct iwl_mld *mld,
 						    IWL_MLD_EMLSR_BLOCKED_TPT,
 						    0);
 
-			/* Wait for the FW to send a recommendation */
-			iwl_mld_block_emlsr(mld, vif,
-					    IWL_MLD_EMLSR_BLOCKED_FW, 0);
-
 			/* clear COEX_HIGH_PRIORITY_ENABLE */
 			ret = iwl_mld_mac_fw_action(mld, vif,
 						    FW_CTXT_ACTION_MODIFY);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index a5b1d373922a8..9556ff3a75a16 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -9,7 +9,6 @@
 #define HANDLE_EMLSR_BLOCKED_REASONS(HOW)	\
 	HOW(PREVENTION)			\
 	HOW(WOWLAN)			\
-	HOW(FW)				\
 	HOW(ROC)			\
 	HOW(NON_BSS)			\
 	HOW(TMP_NON_BSS)		\
@@ -53,7 +52,8 @@ static void iwl_mld_print_emlsr_blocked(struct iwl_mld *mld, u32 mask)
 	HOW(LINK_USAGE)			\
 	HOW(BT_COEX)			\
 	HOW(CHAN_LOAD)			\
-	HOW(RFI)
+	HOW(RFI)			\
+	HOW(FW_REQUEST)
 
 static const char *
 iwl_mld_get_emlsr_exit_string(enum iwl_mld_emlsr_exit exit)
@@ -332,18 +332,14 @@ iwl_mld_vif_iter_emlsr_mode_notif(void *data, u8 *mac,
 		return;
 
 	switch (le32_to_cpu(notif->action)) {
-	case ESR_RECOMMEND_ENTER:
-		iwl_mld_unblock_emlsr(mld_vif->mld, vif,
-				      IWL_MLD_EMLSR_BLOCKED_FW);
-		break;
 	case ESR_RECOMMEND_LEAVE:
-		iwl_mld_block_emlsr(mld_vif->mld, vif,
-				    IWL_MLD_EMLSR_BLOCKED_FW,
-				    iwl_mld_get_primary_link(vif));
+		iwl_mld_exit_emlsr(mld_vif->mld, vif,
+				   IWL_MLD_EMLSR_EXIT_FW_REQUEST,
+				   iwl_mld_get_primary_link(vif));
 		break;
+	case ESR_RECOMMEND_ENTER:
 	case ESR_FORCE_LEAVE:
 	default:
-		/* ESR_FORCE_LEAVE should not happen at this point */
 		IWL_WARN(mld_vif->mld, "Unexpected EMLSR notification: %d\n",
 			 le32_to_cpu(notif->action));
 	}
@@ -724,6 +720,53 @@ iwl_mld_set_link_sel_data(struct iwl_mld *mld,
 	return n_data;
 }
 
+static u32
+iwl_mld_get_min_chan_load_thresh(struct ieee80211_chanctx_conf *chanctx)
+{
+	const struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(chanctx);
+
+	switch (phy->chandef.width) {
+	case NL80211_CHAN_WIDTH_320:
+	case NL80211_CHAN_WIDTH_160:
+		return 5;
+	case NL80211_CHAN_WIDTH_80:
+		return 7;
+	default:
+		break;
+	}
+	return 10;
+}
+
+static bool
+iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
+				  struct ieee80211_vif *vif,
+				  const struct iwl_mld_link_sel_data *a,
+				  const struct iwl_mld_link_sel_data *b)
+{
+	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(vif);
+	struct iwl_mld_link *link_a =
+		iwl_mld_link_dereference_check(mld_vif, a->link_id);
+	struct ieee80211_chanctx_conf *chanctx_a = NULL;
+	u32 primary_load_perc;
+
+	if (!link_a || !link_a->active) {
+		IWL_DEBUG_EHT(mld, "Primary link is not active. Can't enter EMLSR\n");
+		return false;
+	}
+
+	chanctx_a = wiphy_dereference(mld->wiphy, link_a->chan_ctx);
+
+	if (WARN_ON(!chanctx_a))
+		return false;
+
+	primary_load_perc =
+		iwl_mld_phy_from_mac80211(chanctx_a)->avg_channel_load_not_by_us;
+
+	IWL_DEBUG_EHT(mld, "Average channel load not by us: %u\n", primary_load_perc);
+
+	return primary_load_perc > iwl_mld_get_min_chan_load_thresh(chanctx_a);
+}
+
 static bool
 iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 			 struct iwl_mld_link_sel_data *a,
@@ -746,6 +789,8 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 		 */
 		reason_mask |= IWL_MLD_EMLSR_EXIT_BANDWIDTH;
 	}
+	if (!iwl_mld_channel_load_allows_emlsr(mld, vif, a, b))
+		reason_mask |= IWL_MLD_EMLSR_EXIT_CHAN_LOAD;
 
 	if (reason_mask) {
 		IWL_DEBUG_INFO(mld,
@@ -904,7 +949,6 @@ void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
 		link_conf_dereference_check(vif, other_link_id);
 
 	if (!ieee80211_vif_link_active(vif, link->link_id) ||
-	    !iwl_mld_emlsr_active(vif) ||
 	    WARN_ON(link->link_id == other_link_id || !other_link))
 		return;
 
@@ -952,39 +996,67 @@ void iwl_mld_emlsr_check_bt(struct iwl_mld *mld)
 						NULL);
 }
 
-static void iwl_mld_emlsr_check_chan_load_iter(void *_data, u8 *mac,
-					       struct ieee80211_vif *vif)
+struct iwl_mld_chan_load_data {
+	struct iwl_mld_phy *phy;
+	u32 prev_chan_load_not_by_us;
+};
+
+static void iwl_mld_chan_load_update_iter(void *_data, u8 *mac,
+					  struct ieee80211_vif *vif)
 {
-	struct iwl_mld *mld = (struct iwl_mld *)_data;
+	struct iwl_mld_chan_load_data *data = _data;
+	const struct iwl_mld_phy *phy = data->phy;
+	struct ieee80211_chanctx_conf *chanctx =
+		container_of((const void *)phy, struct ieee80211_chanctx_conf,
+			     drv_priv);
+	struct iwl_mld *mld = iwl_mld_vif_from_mac80211(vif)->mld;
 	struct ieee80211_bss_conf *prim_link;
 	unsigned int prim_link_id;
-	int chan_load;
-
-	if (!iwl_mld_emlsr_active(vif))
-		return;
 
 	prim_link_id = iwl_mld_get_primary_link(vif);
 	prim_link = link_conf_dereference_protected(vif, prim_link_id);
+
 	if (WARN_ON(!prim_link))
 		return;
 
-	chan_load = iwl_mld_get_chan_load_by_others(mld, prim_link, true);
-
-	if (chan_load < 0)
+	if (chanctx != rcu_access_pointer(prim_link->chanctx_conf))
 		return;
 
-	/* chan_load is in range [0,255] */
-	if (chan_load < NORMALIZE_PERCENT_TO_255(IWL_MLD_CHAN_LOAD_THRESH))
-		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
-				   prim_link_id);
+	if (iwl_mld_emlsr_active(vif)) {
+		int chan_load = iwl_mld_get_chan_load_by_others(mld, prim_link,
+								true);
+
+		if (chan_load < 0)
+			return;
+
+		/* chan_load is in range [0,255] */
+		if (chan_load < NORMALIZE_PERCENT_TO_255(IWL_MLD_EXIT_EMLSR_CHAN_LOAD))
+			iwl_mld_exit_emlsr(mld, vif,
+					   IWL_MLD_EMLSR_EXIT_CHAN_LOAD,
+					   prim_link_id);
+	} else {
+		u32 old_chan_load = data->prev_chan_load_not_by_us;
+		u32 new_chan_load = phy->avg_channel_load_not_by_us;
+		u32 thresh = iwl_mld_get_min_chan_load_thresh(chanctx);
+
+		if (old_chan_load <= thresh && new_chan_load > thresh)
+			iwl_mld_retry_emlsr(mld, vif);
+	}
 }
 
-void iwl_mld_emlsr_check_chan_load(struct iwl_mld *mld)
+void iwl_mld_emlsr_check_chan_load(struct ieee80211_hw *hw,
+				   struct iwl_mld_phy *phy,
+				   u32 prev_chan_load_not_by_us)
 {
-	ieee80211_iterate_active_interfaces_mtx(mld->hw,
+	struct iwl_mld_chan_load_data data = {
+		.phy = phy,
+		.prev_chan_load_not_by_us = prev_chan_load_not_by_us,
+	};
+
+	ieee80211_iterate_active_interfaces_mtx(hw,
 						IEEE80211_IFACE_ITER_NORMAL,
-						iwl_mld_emlsr_check_chan_load_iter,
-						(void *)(uintptr_t)mld);
+						iwl_mld_chan_load_update_iter,
+						&data);
 }
 
 void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif)
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
index 0f1b18f61c759..a5fbe1919c6da 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -11,6 +11,7 @@
 #include "iwl-config.h"
 #include "iwl-trans.h"
 #include "iface.h"
+#include "phy.h"
 
 struct iwl_mld;
 
@@ -139,7 +140,9 @@ void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
 
 void iwl_mld_emlsr_check_bt(struct iwl_mld *mld);
 
-void iwl_mld_emlsr_check_chan_load(struct iwl_mld *mld);
+void iwl_mld_emlsr_check_chan_load(struct ieee80211_hw *hw,
+				   struct iwl_mld_phy *phy,
+				   u32 prev_chan_load_not_by_us);
 
 /**
  * iwl_mld_retry_emlsr - Retry entering EMLSR
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/stats.c b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
index 75cb204c24194..0715bbc310319 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/stats.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/stats.c
@@ -457,7 +457,7 @@ static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
 {
 	struct iwl_mld_phy *phy = iwl_mld_phy_from_mac80211(ctx);
 	const struct iwl_stats_ntfy_per_phy *per_phy = data;
-	u32 new_load;
+	u32 new_load, old_load;
 
 	if (WARN_ON(phy->fw_id >= IWL_STATS_MAX_PHY_OPERATIONAL))
 		return;
@@ -465,14 +465,16 @@ static void iwl_mld_fill_chanctx_stats(struct ieee80211_hw *hw,
 	phy->channel_load_by_us =
 		le32_to_cpu(per_phy[phy->fw_id].channel_load_by_us);
 
+	old_load = phy->avg_channel_load_not_by_us;
 	new_load = le32_to_cpu(per_phy[phy->fw_id].channel_load_not_by_us);
 	if (IWL_FW_CHECK(phy->mld, new_load > 100, "Invalid channel load %u\n",
 			 new_load))
 		return;
 
 	/* give a weight of 0.5 for the old value */
-	phy->avg_channel_load_not_by_us =
-		(new_load >> 1) + (phy->avg_channel_load_not_by_us >> 1);
+	phy->avg_channel_load_not_by_us = (new_load >> 1) + (old_load >> 1);
+
+	iwl_mld_emlsr_check_chan_load(hw, phy, old_load);
 }
 
 static void
@@ -483,8 +485,6 @@ iwl_mld_process_per_phy_stats(struct iwl_mld *mld,
 					 iwl_mld_fill_chanctx_stats,
 					 (void *)(uintptr_t)per_phy);
 
-	/* channel_load_by_us may have been updated, so recheck */
-	iwl_mld_emlsr_check_chan_load(mld);
 }
 
 void iwl_mld_handle_stats_oper_notif(struct iwl_mld *mld,

From 008c04d53ef5af32b99dfcd502174ed05aaf80c9 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:29 +0200
Subject: [PATCH 2206/2753] wifi: iwlwifi: mld: prevent toggling EMLSR due to
 FW requests

We exit EMLSR mode if the FW requested to do so.
To prevent repeated toggling of the EMLSR mode (frequent entry and
exit), add this exit reason to the EMLSR prevention mechanism.
This mechanism avoids re-entering EMLSR for a certain period of time
after multiple exits caused by the same reason.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.f0e74a7f99af.I447c8788afba85a2a5040ae2c1213b6e05ec14f3@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 9556ff3a75a16..8f6da90bf82cd 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -116,8 +116,9 @@ void iwl_mld_emlsr_tmp_non_bss_done_wk(struct wiphy *wiphy,
 #define IWL_MLD_SCAN_EXPIRE_TIME	(HZ * IWL_MLD_SCAN_EXPIRE_TIME_SEC)
 
 /* Exit reasons that can cause longer EMLSR prevention */
-#define IWL_MLD_PREVENT_EMLSR_REASONS	(IWL_MLD_EMLSR_EXIT_MISSED_BEACON | \
-					 IWL_MLD_EMLSR_EXIT_LINK_USAGE)
+#define IWL_MLD_PREVENT_EMLSR_REASONS	(IWL_MLD_EMLSR_EXIT_MISSED_BEACON	| \
+					 IWL_MLD_EMLSR_EXIT_LINK_USAGE		| \
+					 IWL_MLD_EMLSR_EXIT_FW_REQUEST)
 #define IWL_MLD_PREVENT_EMLSR_TIMEOUT	(HZ * 400)
 
 #define IWL_MLD_EMLSR_PREVENT_SHORT	(HZ * 300)

From c008fadb90b13c9f2a9759a448bc7d823f897a9b Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:30 +0200
Subject: [PATCH 2207/2753] wifi: iwlwifi: mld: allow EMLSR for unequal
 bandwidth

Allow EMLSR if the bandwidths of the links are unequal if one of the
following conditions is true:
1. in low latency mode
2. bandwidth of the secondary link is greater than the bandwidth of the
   primary
3. the primary link is active and is loaded enough to justify EMLSR

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.150c330711c4.Ifd72d2e076783991852a7f1756948b4f0efb9fea@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/iface.h    | 15 ++---
 .../wireless/intel/iwlwifi/mld/low_latency.c  |  4 ++
 .../net/wireless/intel/iwlwifi/mld/mac80211.c | 10 +--
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  | 63 +++++++++++--------
 drivers/net/wireless/intel/iwlwifi/mld/mlo.h  |  4 --
 5 files changed, 49 insertions(+), 47 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/iface.h b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
index 550ae3c9d766a..d1d56b081bf63 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/iface.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/iface.h
@@ -52,8 +52,6 @@ enum iwl_mld_emlsr_blocked {
  * @IWL_MLD_EMLSR_EXIT_FAIL_ENTRY: FW failed to enter EMLSR
  * @IWL_MLD_EMLSR_EXIT_CSA: EMLSR prevented due to channel switch on link
  * @IWL_MLD_EMLSR_EXIT_EQUAL_BAND: EMLSR prevented as both links share the band
- * @IWL_MLD_EMLSR_EXIT_BANDWIDTH: Bandwidths of primary and secondary links are
- *      not equal
  * @IWL_MLD_EMLSR_EXIT_LOW_RSSI: Link RSSI is unsuitable for EMLSR
  * @IWL_MLD_EMLSR_EXIT_LINK_USAGE: Exit EMLSR due to low TPT on secondary link
  * @IWL_MLD_EMLSR_EXIT_BT_COEX: Exit EMLSR due to BT coexistence
@@ -68,13 +66,12 @@ enum iwl_mld_emlsr_exit {
 	IWL_MLD_EMLSR_EXIT_FAIL_ENTRY		= 0x4,
 	IWL_MLD_EMLSR_EXIT_CSA			= 0x8,
 	IWL_MLD_EMLSR_EXIT_EQUAL_BAND		= 0x10,
-	IWL_MLD_EMLSR_EXIT_BANDWIDTH		= 0x20,
-	IWL_MLD_EMLSR_EXIT_LOW_RSSI		= 0x40,
-	IWL_MLD_EMLSR_EXIT_LINK_USAGE		= 0x80,
-	IWL_MLD_EMLSR_EXIT_BT_COEX		= 0x100,
-	IWL_MLD_EMLSR_EXIT_CHAN_LOAD		= 0x200,
-	IWL_MLD_EMLSR_EXIT_RFI			= 0x400,
-	IWL_MLD_EMLSR_EXIT_FW_REQUEST		= 0x800,
+	IWL_MLD_EMLSR_EXIT_LOW_RSSI		= 0x20,
+	IWL_MLD_EMLSR_EXIT_LINK_USAGE		= 0x40,
+	IWL_MLD_EMLSR_EXIT_BT_COEX		= 0x80,
+	IWL_MLD_EMLSR_EXIT_CHAN_LOAD		= 0x100,
+	IWL_MLD_EMLSR_EXIT_RFI			= 0x200,
+	IWL_MLD_EMLSR_EXIT_FW_REQUEST		= 0x400,
 };
 
 /**
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
index e74e66735f521..a4a612afb3b30 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/low_latency.c
@@ -7,6 +7,7 @@
 #include "low_latency.h"
 #include "hcmd.h"
 #include "power.h"
+#include "mlo.h"
 
 #define MLD_LL_WK_INTERVAL_MSEC 500
 #define MLD_LL_PERIOD (HZ * MLD_LL_WK_INTERVAL_MSEC / 1000)
@@ -230,6 +231,9 @@ void iwl_mld_vif_update_low_latency(struct iwl_mld *mld,
 		return;
 
 	iwl_mld_update_mac_power(mld, vif, false);
+
+	if (low_latency)
+		iwl_mld_retry_emlsr(mld, vif);
 }
 
 static bool iwl_mld_is_vo_vi_pkt(struct ieee80211_hdr *hdr)
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index f6623988fff6a..938cf5900a295 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -1187,15 +1187,11 @@ iwl_mld_mac80211_link_info_changed_sta(struct iwl_mld *mld,
 		bw = ieee80211_chan_width_to_rx_bw(link_conf->chanreq.oper.width);
 
 		iwl_mld_omi_ap_changed_bw(mld, link_conf, bw);
-	}
 
-	if (changes & BSS_CHANGED_BANDWIDTH) {
-		if (iwl_mld_emlsr_active(vif))
-			iwl_mld_emlsr_check_equal_bw(mld, vif, link_conf);
-		else
-			/* Channel load threshold may have changed */
-			iwl_mld_retry_emlsr(mld, vif);
 	}
+
+	if (changes & BSS_CHANGED_BANDWIDTH)
+		iwl_mld_retry_emlsr(mld, vif);
 }
 
 static int iwl_mld_update_mu_groups(struct iwl_mld *mld,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 8f6da90bf82cd..9342f03c0908a 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -47,7 +47,6 @@ static void iwl_mld_print_emlsr_blocked(struct iwl_mld *mld, u32 mask)
 	HOW(FAIL_ENTRY)			\
 	HOW(CSA)			\
 	HOW(EQUAL_BAND)			\
-	HOW(BANDWIDTH)			\
 	HOW(LOW_RSSI)			\
 	HOW(LINK_USAGE)			\
 	HOW(BT_COEX)			\
@@ -748,6 +747,7 @@ iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 	struct iwl_mld_link *link_a =
 		iwl_mld_link_dereference_check(mld_vif, a->link_id);
 	struct ieee80211_chanctx_conf *chanctx_a = NULL;
+	u32 bw_a, bw_b, ratio;
 	u32 primary_load_perc;
 
 	if (!link_a || !link_a->active) {
@@ -765,7 +765,34 @@ iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 
 	IWL_DEBUG_EHT(mld, "Average channel load not by us: %u\n", primary_load_perc);
 
-	return primary_load_perc > iwl_mld_get_min_chan_load_thresh(chanctx_a);
+	if (primary_load_perc < iwl_mld_get_min_chan_load_thresh(chanctx_a)) {
+		IWL_DEBUG_EHT(mld, "Channel load is below the minimum threshold\n");
+		return false;
+	}
+
+	if (iwl_mld_vif_low_latency(mld_vif)) {
+		IWL_DEBUG_EHT(mld, "Low latency vif, EMLSR is allowed\n");
+		return true;
+	}
+
+	if (a->chandef->width <= b->chandef->width)
+		return true;
+
+	bw_a = nl80211_chan_width_to_mhz(a->chandef->width);
+	bw_b = nl80211_chan_width_to_mhz(b->chandef->width);
+	ratio = bw_a / bw_b;
+
+	switch (ratio) {
+	case 2:
+		return primary_load_perc > 25;
+	case 4:
+		return primary_load_perc > 40;
+	case 8:
+	case 16:
+		return primary_load_perc > 50;
+	}
+
+	return false;
 }
 
 static bool
@@ -784,12 +811,6 @@ iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
 
 	if (a->chandef->chan->band == b->chandef->chan->band)
 		reason_mask |= IWL_MLD_EMLSR_EXIT_EQUAL_BAND;
-	if (a->chandef->width != b->chandef->width) {
-		/* TODO: task=EMLSR task=statistics
-		 * replace BANDWIDTH exit reason with channel load criteria
-		 */
-		reason_mask |= IWL_MLD_EMLSR_EXIT_BANDWIDTH;
-	}
 	if (!iwl_mld_channel_load_allows_emlsr(mld, vif, a, b))
 		reason_mask |= IWL_MLD_EMLSR_EXIT_CHAN_LOAD;
 
@@ -941,23 +962,6 @@ void iwl_mld_select_links(struct iwl_mld *mld)
 						NULL);
 }
 
-void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
-				  struct ieee80211_vif *vif,
-				  struct ieee80211_bss_conf *link)
-{
-	u8 other_link_id = iwl_mld_get_other_link(vif, link->link_id);
-	struct ieee80211_bss_conf *other_link =
-		link_conf_dereference_check(vif, other_link_id);
-
-	if (!ieee80211_vif_link_active(vif, link->link_id) ||
-	    WARN_ON(link->link_id == other_link_id || !other_link))
-		return;
-
-	if (link->chanreq.oper.width != other_link->chanreq.oper.width)
-		iwl_mld_exit_emlsr(mld, vif, IWL_MLD_EMLSR_EXIT_BANDWIDTH,
-				   iwl_mld_get_primary_link(vif));
-}
-
 static void iwl_mld_emlsr_check_bt_iter(void *_data, u8 *mac,
 					struct ieee80211_vif *vif)
 {
@@ -1038,10 +1042,15 @@ static void iwl_mld_chan_load_update_iter(void *_data, u8 *mac,
 	} else {
 		u32 old_chan_load = data->prev_chan_load_not_by_us;
 		u32 new_chan_load = phy->avg_channel_load_not_by_us;
-		u32 thresh = iwl_mld_get_min_chan_load_thresh(chanctx);
+		u32 min_thresh = iwl_mld_get_min_chan_load_thresh(chanctx);
+
+#define THRESHOLD_CROSSED(threshold) \
+	(old_chan_load <= (threshold) && new_chan_load > (threshold))
 
-		if (old_chan_load <= thresh && new_chan_load > thresh)
+		if (THRESHOLD_CROSSED(min_thresh) || THRESHOLD_CROSSED(25) ||
+		    THRESHOLD_CROSSED(40) || THRESHOLD_CROSSED(50))
 			iwl_mld_retry_emlsr(mld, vif);
+#undef THRESHOLD_CROSSED
 	}
 }
 
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
index a5fbe1919c6da..6c652c17069f8 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -134,10 +134,6 @@ void iwl_mld_emlsr_unblock_tpt_wk(struct wiphy *wiphy, struct wiphy_work *wk);
 
 void iwl_mld_select_links(struct iwl_mld *mld);
 
-void iwl_mld_emlsr_check_equal_bw(struct iwl_mld *mld,
-				  struct ieee80211_vif *vif,
-				  struct ieee80211_bss_conf *link);
-
 void iwl_mld_emlsr_check_bt(struct iwl_mld *mld);
 
 void iwl_mld_emlsr_check_chan_load(struct ieee80211_hw *hw,

From de5ca699bc3f7fe9f90ba927d8a6e7783cd7311d Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:31 +0200
Subject: [PATCH 2208/2753] wifi: iwlwifi: mld: KUnit: introduce
 iwl_mld_kunit_link

To allow setting up association/EMLSR states with more flexibility,
change the relevant functions to receive a new struct, iwl_mld_kunit_link,
which will contain all the link parameters (for now just link id, band
and bandwidth).

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.f336491ccc4e.I6b727765eb394a3dbb78cea71e356be1bdc4a17c@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../intel/iwlwifi/mld/tests/link-selection.c  | 13 +++---
 .../wireless/intel/iwlwifi/mld/tests/link.c   | 15 +++++--
 .../wireless/intel/iwlwifi/mld/tests/utils.c  | 45 +++++++++----------
 .../wireless/intel/iwlwifi/mld/tests/utils.h  | 22 ++++++---
 4 files changed, 54 insertions(+), 41 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
index d835550c1a6bd..34782569d67e4 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
@@ -126,23 +126,24 @@ static void test_link_grading(struct kunit *test)
 	struct ieee80211_vif *vif;
 	struct ieee80211_bss_conf *link;
 	unsigned int actual_grade;
-	u8 assoc_link_id;
 	/* Extract test case parameters */
 	u8 link_id = test_param->input.link.link_id;
-	enum nl80211_band band = test_param->input.link.chandef->chan->band;
 	bool active = test_param->input.link.active;
 	u16 valid_links;
+	struct iwl_mld_kunit_link assoc_link = {
+		.band = test_param->input.link.chandef->chan->band,
+	};
 
 	/* If the link is not active, use a different link as the assoc link */
 	if (active) {
-		assoc_link_id = link_id;
+		assoc_link.id = link_id;
 		valid_links = BIT(link_id);
 	} else {
-		assoc_link_id = BIT(ffz(BIT(link_id)));
-		valid_links = BIT(assoc_link_id) | BIT(link_id);
+		assoc_link.id = BIT(ffz(BIT(link_id)));
+		valid_links = BIT(assoc_link.id) | BIT(link_id);
 	}
 
-	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, assoc_link_id, band);
+	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, &assoc_link);
 
 	wiphy_lock(mld->wiphy);
 	link = wiphy_dereference(mld->wiphy, vif->link_conf[link_id]);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
index 6e251dbc1dfe1..4a4eaa134bd3c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link.c
@@ -2,7 +2,7 @@
 /*
  * KUnit tests for channel helper functions
  *
- * Copyright (C) 2024 Intel Corporation
+ * Copyright (C) 2024-2025 Intel Corporation
  */
 #include <kunit/static_stub.h>
 
@@ -61,6 +61,14 @@ static void test_missed_beacon(struct kunit *test)
 		(const void *)(test->param_value);
 	struct ieee80211_vif *vif;
 	struct iwl_rx_packet *pkt;
+	struct iwl_mld_kunit_link link1 = {
+		.id = 0,
+		.band = NL80211_BAND_6GHZ,
+	};
+	struct iwl_mld_kunit_link link2 = {
+		.id = 1,
+		.band = NL80211_BAND_5GHZ,
+	};
 
 	kunit_activate_static_stub(test, ieee80211_connection_loss,
 				   fake_ieee80211_connection_loss);
@@ -68,12 +76,11 @@ static void test_missed_beacon(struct kunit *test)
 	notif = (void *)pkt->data;
 
 	if (test_param->input.emlsr) {
-		vif = iwlmld_kunit_assoc_emlsr(0x3, NL80211_BAND_5GHZ,
-					       NL80211_BAND_6GHZ);
+		vif = iwlmld_kunit_assoc_emlsr(&link1, &link2);
 	} else {
 		struct iwl_mld_vif *mld_vif;
 
-		vif = iwlmld_kunit_setup_non_mlo_assoc(NL80211_BAND_6GHZ);
+		vif = iwlmld_kunit_setup_non_mlo_assoc(&link1);
 		mld_vif = iwl_mld_vif_from_mac80211(vif);
 		notif->link_id = cpu_to_le32(mld_vif->deflink.fw_id);
 	}
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
index 6331cd91cdf6e..fa2710661bd5c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -329,7 +329,7 @@ static void iwlmld_kunit_set_vif_associated(struct ieee80211_vif *vif)
 }
 
 static struct ieee80211_vif *
-iwlmld_kunit_setup_assoc(bool mlo, u8 link_id, enum nl80211_band band)
+iwlmld_kunit_setup_assoc(bool mlo, struct iwl_mld_kunit_link *assoc_link)
 {
 	struct kunit *test = kunit_get_current_test();
 	struct iwl_mld *mld = test->priv;
@@ -337,32 +337,32 @@ iwlmld_kunit_setup_assoc(bool mlo, u8 link_id, enum nl80211_band band)
 	struct ieee80211_bss_conf *link;
 	struct ieee80211_chanctx_conf *chan_ctx;
 
-	KUNIT_ASSERT_TRUE(test, mlo || link_id == 0);
+	KUNIT_ASSERT_TRUE(test, mlo || assoc_link->id == 0);
 
 	vif = iwlmld_kunit_add_vif(mlo, NL80211_IFTYPE_STATION);
 
 	if (mlo)
-		link = iwlmld_kunit_add_link(vif, link_id);
+		link = iwlmld_kunit_add_link(vif, assoc_link->id);
 	else
 		link = &vif->bss_conf;
 
-	chan_ctx = iwlmld_kunit_add_chanctx(band);
+	chan_ctx = iwlmld_kunit_add_chanctx(assoc_link->band);
 
 	wiphy_lock(mld->wiphy);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
 	wiphy_unlock(mld->wiphy);
 
 	/* The AP sta will now be pointer to by mld_vif->ap_sta */
-	iwlmld_kunit_setup_sta(vif, IEEE80211_STA_AUTHORIZED, link_id);
+	iwlmld_kunit_setup_sta(vif, IEEE80211_STA_AUTHORIZED, assoc_link->id);
 
 	iwlmld_kunit_set_vif_associated(vif);
 
 	return vif;
 }
 
-struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
-						   u8 assoc_link_id,
-						   enum nl80211_band band)
+struct ieee80211_vif *
+iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
+			     struct iwl_mld_kunit_link *assoc_link)
 {
 	struct kunit *test = kunit_get_current_test();
 	struct ieee80211_vif *vif;
@@ -370,13 +370,13 @@ struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
 	KUNIT_ASSERT_TRUE(test,
 			  hweight16(valid_links) == 1 ||
 			  hweight16(valid_links) == 2);
-	KUNIT_ASSERT_TRUE(test, valid_links & BIT(assoc_link_id));
+	KUNIT_ASSERT_TRUE(test, valid_links & BIT(assoc_link->id));
 
-	vif = iwlmld_kunit_setup_assoc(true, assoc_link_id, band);
+	vif = iwlmld_kunit_setup_assoc(true, assoc_link);
 
 	/* Add the other link, if applicable */
 	if (hweight16(valid_links) > 1) {
-		u8 other_link_id = ffs(valid_links & ~BIT(assoc_link_id)) - 1;
+		u8 other_link_id = ffs(valid_links & ~BIT(assoc_link->id)) - 1;
 
 		iwlmld_kunit_add_link(vif, other_link_id);
 	}
@@ -384,9 +384,10 @@ struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
 	return vif;
 }
 
-struct ieee80211_vif *iwlmld_kunit_setup_non_mlo_assoc(enum nl80211_band band)
+struct ieee80211_vif *
+iwlmld_kunit_setup_non_mlo_assoc(struct iwl_mld_kunit_link *assoc_link)
 {
-	return iwlmld_kunit_setup_assoc(false, 0, band);
+	return iwlmld_kunit_setup_assoc(false, assoc_link);
 }
 
 struct iwl_rx_packet *
@@ -403,9 +404,8 @@ _iwl_mld_kunit_create_pkt(const void *notif, size_t notif_sz)
 	return pkt;
 }
 
-struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
-					       enum nl80211_band band1,
-					       enum nl80211_band band2)
+struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(struct iwl_mld_kunit_link *link1,
+					       struct iwl_mld_kunit_link *link2)
 {
 	struct kunit *test = kunit_get_current_test();
 	struct iwl_mld *mld = test->priv;
@@ -414,23 +414,20 @@ struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
 	struct ieee80211_chanctx_conf *chan_ctx;
 	struct ieee80211_sta *sta;
 	struct iwl_mld_vif *mld_vif;
-	u8 assoc_link_id, other_link_id;
+	u16 valid_links = BIT(link1->id) | BIT(link2->id);
 
 	KUNIT_ASSERT_TRUE(test, hweight16(valid_links) == 2);
 
-	assoc_link_id = ffs(valid_links) - 1;
-	other_link_id = ffs(valid_links & ~BIT(assoc_link_id)) - 1;
-
-	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, assoc_link_id, band1);
+	vif = iwlmld_kunit_setup_mlo_assoc(valid_links, link1);
 	mld_vif = iwl_mld_vif_from_mac80211(vif);
 
 	/* Activate second link */
 	wiphy_lock(mld->wiphy);
 
-	link = wiphy_dereference(mld->wiphy, vif->link_conf[other_link_id]);
+	link = wiphy_dereference(mld->wiphy, vif->link_conf[link2->id]);
 	KUNIT_EXPECT_NOT_NULL(test, link);
 
-	chan_ctx = iwlmld_kunit_add_chanctx(band2);
+	chan_ctx = iwlmld_kunit_add_chanctx(link2->band);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
 
 	wiphy_unlock(mld->wiphy);
@@ -439,7 +436,7 @@ struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
 	sta = mld_vif->ap_sta;
 	KUNIT_EXPECT_NOT_NULL(test, sta);
 
-	iwlmld_kunit_alloc_link_sta(sta, other_link_id);
+	iwlmld_kunit_alloc_link_sta(sta, link2->id);
 
 	return vif;
 }
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
index 9b1f2ada997f3..bb757a7dd8e74 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
@@ -13,6 +13,12 @@ struct iwl_mld;
 
 int iwlmld_kunit_test_init(struct kunit *test);
 
+struct iwl_mld_kunit_link {
+	u8 id;
+	enum nl80211_band band;
+	enum nl80211_chan_width bandwidth;
+};
+
 enum nl80211_iftype;
 
 struct ieee80211_vif *iwlmld_kunit_add_vif(bool mlo, enum nl80211_iftype type);
@@ -88,10 +94,12 @@ struct ieee80211_sta *iwlmld_kunit_setup_sta(struct ieee80211_vif *vif,
 					     enum ieee80211_sta_state state,
 					     int link_id);
 
-struct ieee80211_vif *iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
-						   u8 assoc_link_id,
-						   enum nl80211_band band);
-struct ieee80211_vif *iwlmld_kunit_setup_non_mlo_assoc(enum nl80211_band band);
+struct ieee80211_vif *
+iwlmld_kunit_setup_mlo_assoc(u16 valid_links,
+			     struct iwl_mld_kunit_link *assoc_link);
+
+struct ieee80211_vif *
+iwlmld_kunit_setup_non_mlo_assoc(struct iwl_mld_kunit_link *assoc_link);
 
 struct iwl_rx_packet *
 _iwl_mld_kunit_create_pkt(const void *notif, size_t notif_sz);
@@ -99,9 +107,9 @@ _iwl_mld_kunit_create_pkt(const void *notif, size_t notif_sz);
 #define iwl_mld_kunit_create_pkt(_notif)	\
 	_iwl_mld_kunit_create_pkt(&(_notif), sizeof(_notif))
 
-struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(u16 valid_links,
-					       enum nl80211_band band1,
-					       enum nl80211_band band2);
+struct ieee80211_vif *
+iwlmld_kunit_assoc_emlsr(struct iwl_mld_kunit_link *link1,
+			 struct iwl_mld_kunit_link *link2);
 
 struct element *iwlmld_kunit_gen_element(u8 id, const void *data, size_t len);
 

From 2907c039ff396d43d13ef19b0dbd9b86791f2520 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:32 +0200
Subject: [PATCH 2209/2753] wifi: iwlwifi: mld: KUnit: create chanctx with a
 custom width

Currently iwlmld_kunit_add_chanctx receives a band, picks a predefined
static chandef, and creates the chanctx from it.
Change it to receive a bandwidth as well. Otherwise, the bandwidth in
the chanctx/phy will be different than what test specified in the
iwl_mld_kunit_link.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.85a1285d34cd.Ia71cdcd4241fe73501bc93e3cb2c6bb3f631b9ec@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/tests/utils.c   |  5 +++--
 .../net/wireless/intel/iwlwifi/mld/tests/utils.h   | 14 ++++++++------
 2 files changed, 11 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
index fa2710661bd5c..9712ee6965093 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.c
@@ -346,7 +346,8 @@ iwlmld_kunit_setup_assoc(bool mlo, struct iwl_mld_kunit_link *assoc_link)
 	else
 		link = &vif->bss_conf;
 
-	chan_ctx = iwlmld_kunit_add_chanctx(assoc_link->band);
+	chan_ctx = iwlmld_kunit_add_chanctx(assoc_link->band,
+					    assoc_link->bandwidth);
 
 	wiphy_lock(mld->wiphy);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
@@ -427,7 +428,7 @@ struct ieee80211_vif *iwlmld_kunit_assoc_emlsr(struct iwl_mld_kunit_link *link1,
 	link = wiphy_dereference(mld->wiphy, vif->link_conf[link2->id]);
 	KUNIT_EXPECT_NOT_NULL(test, link);
 
-	chan_ctx = iwlmld_kunit_add_chanctx(link2->band);
+	chan_ctx = iwlmld_kunit_add_chanctx(link2->band, link2->bandwidth);
 	iwlmld_kunit_assign_chanctx_to_link(vif, link, chan_ctx);
 
 	wiphy_unlock(mld->wiphy);
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
index bb757a7dd8e74..d3723653cf1b3 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/utils.h
@@ -65,24 +65,26 @@ struct ieee80211_chanctx_conf *
 iwlmld_kunit_add_chanctx_from_def(struct cfg80211_chan_def *def);
 
 static inline struct ieee80211_chanctx_conf *
-iwlmld_kunit_add_chanctx(enum nl80211_band band)
+iwlmld_kunit_add_chanctx(enum nl80211_band band, enum nl80211_chan_width width)
 {
-	struct cfg80211_chan_def *chandef;
+	struct cfg80211_chan_def chandef;
 
 	switch (band) {
 	case NL80211_BAND_2GHZ:
-		chandef = &chandef_2ghz;
+		chandef = chandef_2ghz;
 		break;
 	case NL80211_BAND_5GHZ:
-		chandef = &chandef_5ghz;
+		chandef = chandef_5ghz;
 		break;
 	default:
 	case NL80211_BAND_6GHZ:
-		chandef = &chandef_6ghz;
+		chandef = chandef_6ghz;
 		break;
 	}
 
-	return iwlmld_kunit_add_chanctx_from_def(chandef);
+	chandef.width = width;
+
+	return iwlmld_kunit_add_chanctx_from_def(&chandef);
 }
 
 void iwlmld_kunit_assign_chanctx_to_link(struct ieee80211_vif *vif,

From f2aac4c73c9945cce156fd58a9a2f31f2c8a90c7 Mon Sep 17 00:00:00 2001
From: Niklas Cassel <cassel@kernel.org>
Date: Mon, 17 Mar 2025 18:03:49 +0100
Subject: [PATCH 2210/2753] ata: libata-core: Add ATA_QUIRK_NO_LPM_ON_ATI for
 certain Samsung SSDs

Before commit 7627a0edef54 ("ata: ahci: Drop low power policy board type")
the ATI AHCI controllers specified board type 'board_ahci' rather than
board type 'board_ahci'. This means that LPM was historically not enabled
for the ATI AHCI controllers.

By looking at commit 7a8526a5cd51 ("libata: Add ATA_HORKAGE_NO_NCQ_ON_ATI
for Samsung 860 and 870 SSD."), it is clear that, for some unknown reason,
that Samsung SSDs do not play nice with ATI AHCI controllers. (When using
other AHCI controllers, NCQ can be enabled on these Samsung SSDs without
issues.)

In a similar way, from user reports, it is clear the ATI AHCI controllers
can enable LPM on e.g. Maxtor HDDs perfectly fine, but when enabling LPM
on certain Samsung SSDs, things break. (E.g. the SSDs will not get detected
by the ATI AHCI controller even after a COMRESET.)

Yet, when using LPM on these Samsung SSDs with other AHCI controllers, e.g.
Intel AHCI controllers, these Samsung drives appear to work perfectly fine.

Considering that the combination of ATI + Samsung, for some unknown reason,
does not seem to work well, disable LPM when detecting an ATI AHCI
controller with a problematic Samsung SSD.

Apply this new ATA_QUIRK_NO_LPM_ON_ATI quirk for all Samsung SSDs that have
already been reported to not play nice with ATI (ATA_QUIRK_NO_NCQ_ON_ATI).

Fixes: 7627a0edef54 ("ata: ahci: Drop low power policy board type")
Suggested-by: Hans de Goede <hdegoede@redhat.com>
Reported-by: Eric <eric.4.debian@grabatoulnz.fr>
Closes: https://lore.kernel.org/linux-ide/Z8SBZMBjvVXA7OAK@eldamar.lan/
Tested-by: Eric <eric.4.debian@grabatoulnz.fr>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250317170348.1748671-2-cassel@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 14 +++++++++++---
 include/linux/libata.h    |  2 ++
 2 files changed, 13 insertions(+), 3 deletions(-)

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index c085dd81ebe7f..d956735e2a764 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2845,6 +2845,10 @@ int ata_dev_configure(struct ata_device *dev)
 	    (id[ATA_ID_SATA_CAPABILITY] & 0xe) == 0x2)
 		dev->quirks |= ATA_QUIRK_NOLPM;
 
+	if (dev->quirks & ATA_QUIRK_NO_LPM_ON_ATI &&
+	    ata_dev_check_adapter(dev, PCI_VENDOR_ID_ATI))
+		dev->quirks |= ATA_QUIRK_NOLPM;
+
 	if (ap->flags & ATA_FLAG_NO_LPM)
 		dev->quirks |= ATA_QUIRK_NOLPM;
 
@@ -3897,6 +3901,7 @@ static const char * const ata_quirk_names[] = {
 	[__ATA_QUIRK_MAX_SEC_1024]	= "maxsec1024",
 	[__ATA_QUIRK_MAX_TRIM_128M]	= "maxtrim128m",
 	[__ATA_QUIRK_NO_NCQ_ON_ATI]	= "noncqonati",
+	[__ATA_QUIRK_NO_LPM_ON_ATI]	= "nolpmonati",
 	[__ATA_QUIRK_NO_ID_DEV_LOG]	= "noiddevlog",
 	[__ATA_QUIRK_NO_LOG_DIR]	= "nologdir",
 	[__ATA_QUIRK_NO_FUA]		= "nofua",
@@ -4142,13 +4147,16 @@ static const struct ata_dev_quirks_entry __ata_dev_quirks[] = {
 						ATA_QUIRK_ZERO_AFTER_TRIM },
 	{ "Samsung SSD 860*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "Samsung SSD 870*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "SAMSUNG*MZ7LH*",		NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM |
-						ATA_QUIRK_NO_NCQ_ON_ATI, },
+						ATA_QUIRK_NO_NCQ_ON_ATI |
+						ATA_QUIRK_NO_LPM_ON_ATI },
 	{ "FCCT*M500*",			NULL,	ATA_QUIRK_NO_NCQ_TRIM |
 						ATA_QUIRK_ZERO_AFTER_TRIM },
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index c1a85d46eba6d..4f62c43059c21 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -88,6 +88,7 @@ enum ata_quirks {
 	__ATA_QUIRK_MAX_SEC_1024,	/* Limit max sects to 1024 */
 	__ATA_QUIRK_MAX_TRIM_128M,	/* Limit max trim size to 128M */
 	__ATA_QUIRK_NO_NCQ_ON_ATI,	/* Disable NCQ on ATI chipset */
+	__ATA_QUIRK_NO_LPM_ON_ATI,	/* Disable LPM on ATI chipset */
 	__ATA_QUIRK_NO_ID_DEV_LOG,	/* Identify device log missing */
 	__ATA_QUIRK_NO_LOG_DIR,		/* Do not read log directory */
 	__ATA_QUIRK_NO_FUA,		/* Do not use FUA */
@@ -432,6 +433,7 @@ enum {
 	ATA_QUIRK_MAX_SEC_1024		= (1U << __ATA_QUIRK_MAX_SEC_1024),
 	ATA_QUIRK_MAX_TRIM_128M		= (1U << __ATA_QUIRK_MAX_TRIM_128M),
 	ATA_QUIRK_NO_NCQ_ON_ATI		= (1U << __ATA_QUIRK_NO_NCQ_ON_ATI),
+	ATA_QUIRK_NO_LPM_ON_ATI		= (1U << __ATA_QUIRK_NO_LPM_ON_ATI),
 	ATA_QUIRK_NO_ID_DEV_LOG		= (1U << __ATA_QUIRK_NO_ID_DEV_LOG),
 	ATA_QUIRK_NO_LOG_DIR		= (1U << __ATA_QUIRK_NO_LOG_DIR),
 	ATA_QUIRK_NO_FUA		= (1U << __ATA_QUIRK_NO_FUA),

From 905d1a220e8db4aaf0ccc5cb9f733ac2e5989386 Mon Sep 17 00:00:00 2001
From: Paul Greenwalt <paul.greenwalt@intel.com>
Date: Mon, 10 Mar 2025 10:44:54 -0700
Subject: [PATCH 2211/2753] ice: Add E830 checksum offload support

E830 supports raw receive and generic transmit checksum offloads.

Raw receive checksum support is provided by hardware calculating the
checksum over the whole packet, regardless of type. The calculated
checksum is provided to driver in the Rx flex descriptor. Then the driver
assigns the checksum to skb->csum and sets skb->ip_summed to
CHECKSUM_COMPLETE.

Generic transmit checksum support is provided by hardware calculating the
checksum given two offsets: the start offset to begin checksum calculation,
and the offset to insert the calculated checksum in the packet. Support is
advertised to the stack using NETIF_F_HW_CSUM feature.

E830 has the following limitations when both generic transmit checksum
offload and TCP Segmentation Offload (TSO) are enabled:

1. Inner packet header modification is not supported. This restriction
   includes the inability to alter TCP flags, such as the push flag. As a
   result, this limitation can impact the receiver's ability to coalesce
   packets, potentially degrading network throughput.
2. The Maximum Segment Size (MSS) is limited to 1023 bytes, which prevents
   support of Maximum Transmission Unit (MTU) greater than 1063 bytes.

Therefore NETIF_F_HW_CSUM and NETIF_F_ALL_TSO features are mutually
exclusive. NETIF_F_HW_CSUM hardware feature support is indicated but is not
enabled by default. Instead, IP checksums and NETIF_F_ALL_TSO are the
defaults. Enforcement of mutual exclusivity of NETIF_F_HW_CSUM and
NETIF_F_ALL_TSO is done in ice_set_features(). Mutual exclusivity
of IP checksums and NETIF_F_HW_CSUM is handled by netdev_fix_features().

When NETIF_F_HW_CSUM is requested the provided skb->csum_start and
skb->csum_offset are passed to hardware in the Tx context descriptor
generic checksum (GCS) parameters. Hardware calculates the 1's complement
from skb->csum_start to the end of the packet, and inserts the result in
the packet at skb->csum_offset.

Co-developed-by: Alice Michael <alice.michael@intel.com>
Signed-off-by: Alice Michael <alice.michael@intel.com>
Co-developed-by: Eric Joyner <eric.joyner@intel.com>
Signed-off-by: Eric Joyner <eric.joyner@intel.com>
Signed-off-by: Paul Greenwalt <paul.greenwalt@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-2-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/ice/ice.h          |  1 +
 .../net/ethernet/intel/ice/ice_lan_tx_rx.h    |  9 +++++--
 drivers/net/ethernet/intel/ice/ice_lib.c      |  8 +++++-
 drivers/net/ethernet/intel/ice/ice_main.c     | 18 +++++++++++++
 drivers/net/ethernet/intel/ice/ice_txrx.c     | 27 ++++++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_txrx.h     |  2 ++
 drivers/net/ethernet/intel/ice/ice_txrx_lib.c | 26 ++++++++++++++++++
 7 files changed, 87 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 5ceeae664598c..fd083647c14ac 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -201,6 +201,7 @@ enum ice_feature {
 	ICE_F_SMA_CTRL,
 	ICE_F_CGU,
 	ICE_F_GNSS,
+	ICE_F_GCS,
 	ICE_F_ROCE_LAG,
 	ICE_F_SRIOV_LAG,
 	ICE_F_MBX_LIMIT,
diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
index 1479b45738af1..77ba26538b07b 100644
--- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
+++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h
@@ -229,7 +229,7 @@ struct ice_32b_rx_flex_desc_nic {
 	__le16 status_error1;
 	u8 flexi_flags2;
 	u8 ts_low;
-	__le16 l2tag2_1st;
+	__le16 raw_csum;
 	__le16 l2tag2_2nd;
 
 	/* Qword 3 */
@@ -478,10 +478,15 @@ enum ice_tx_desc_len_fields {
 struct ice_tx_ctx_desc {
 	__le32 tunneling_params;
 	__le16 l2tag2;
-	__le16 rsvd;
+	__le16 gcs;
 	__le64 qw1;
 };
 
+#define ICE_TX_GCS_DESC_START_M		GENMASK(7, 0)
+#define ICE_TX_GCS_DESC_OFFSET_M	GENMASK(11, 8)
+#define ICE_TX_GCS_DESC_TYPE_M		GENMASK(14, 12)
+#define ICE_TX_GCS_DESC_CSUM_PSH	1
+
 #define ICE_TXD_CTX_QW1_CMD_S	4
 #define ICE_TXD_CTX_QW1_CMD_M	(0x7FUL << ICE_TXD_CTX_QW1_CMD_S)
 
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index d7aa8487943a6..0bcf9d127ac9e 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1431,6 +1431,10 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi)
 		ring->dev = dev;
 		ring->count = vsi->num_rx_desc;
 		ring->cached_phctime = pf->ptp.cached_phc_time;
+
+		if (ice_is_feature_supported(pf, ICE_F_GCS))
+			ring->flags |= ICE_RX_FLAGS_RING_GCS;
+
 		WRITE_ONCE(vsi->rx_rings[i], ring);
 	}
 
@@ -3899,8 +3903,10 @@ void ice_init_feature_support(struct ice_pf *pf)
 		break;
 	}
 
-	if (pf->hw.mac_type == ICE_MAC_E830)
+	if (pf->hw.mac_type == ICE_MAC_E830) {
 		ice_set_feature_support(pf, ICE_F_MBX_LIMIT);
+		ice_set_feature_support(pf, ICE_F_GCS);
+	}
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 6470bbb680cb1..049edeb601043 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -3634,6 +3634,12 @@ void ice_set_netdev_features(struct net_device *netdev)
 	/* Allow core to manage IRQs affinity */
 	netif_set_affinity_auto(netdev);
 
+	/* Mutual exclusivity for TSO and GCS is enforced by the set features
+	 * ndo callback.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS))
+		netdev->hw_features |= NETIF_F_HW_CSUM;
+
 	netif_set_tso_max_size(netdev, ICE_MAX_TSO_SIZE);
 }
 
@@ -6549,6 +6555,18 @@ ice_set_features(struct net_device *netdev, netdev_features_t features)
 	if (changed & NETIF_F_LOOPBACK)
 		ret = ice_set_loopback(vsi, !!(features & NETIF_F_LOOPBACK));
 
+	/* Due to E830 hardware limitations, TSO (NETIF_F_ALL_TSO) with GCS
+	 * (NETIF_F_HW_CSUM) is not supported.
+	 */
+	if (ice_is_feature_supported(pf, ICE_F_GCS) &&
+	    ((features & NETIF_F_HW_CSUM) && (features & NETIF_F_ALL_TSO))) {
+		if (netdev->features & NETIF_F_HW_CSUM)
+			dev_err(ice_pf_to_dev(pf), "To enable TSO, you must first disable HW checksum.\n");
+		else
+			dev_err(ice_pf_to_dev(pf), "To enable HW checksum, you must first disable TSO.\n");
+		return -EIO;
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 380ba1e8b3b2c..1e4f6f6ee449c 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -1809,6 +1809,7 @@ ice_tx_map(struct ice_tx_ring *tx_ring, struct ice_tx_buf *first,
 static
 int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 {
+	const struct ice_tx_ring *tx_ring = off->tx_ring;
 	u32 l4_len = 0, l3_len = 0, l2_len = 0;
 	struct sk_buff *skb = first->skb;
 	union {
@@ -1958,6 +1959,30 @@ int ice_tx_csum(struct ice_tx_buf *first, struct ice_tx_offload_params *off)
 	l3_len = l4.hdr - ip.hdr;
 	offset |= (l3_len / 4) << ICE_TX_DESC_LEN_IPLEN_S;
 
+	if ((tx_ring->netdev->features & NETIF_F_HW_CSUM) &&
+	    !(first->tx_flags & ICE_TX_FLAGS_TSO) &&
+	    !skb_csum_is_sctp(skb)) {
+		/* Set GCS */
+		u16 csum_start = (skb->csum_start - skb->mac_header) / 2;
+		u16 csum_offset = skb->csum_offset / 2;
+		u16 gcs_params;
+
+		gcs_params = FIELD_PREP(ICE_TX_GCS_DESC_START_M, csum_start) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_OFFSET_M, csum_offset) |
+			     FIELD_PREP(ICE_TX_GCS_DESC_TYPE_M,
+					ICE_TX_GCS_DESC_CSUM_PSH);
+
+		/* Unlike legacy HW checksums, GCS requires a context
+		 * descriptor.
+		 */
+		off->cd_qw1 |= ICE_TX_DESC_DTYPE_CTX;
+		off->cd_gcs_params = gcs_params;
+		/* Fill out CSO info in data descriptors */
+		off->td_offset |= offset;
+		off->td_cmd |= cmd;
+		return 1;
+	}
+
 	/* Enable L4 checksum offloads */
 	switch (l4_proto) {
 	case IPPROTO_TCP:
@@ -2441,7 +2466,7 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_tx_ring *tx_ring)
 		/* setup context descriptor */
 		cdesc->tunneling_params = cpu_to_le32(offload.cd_tunnel_params);
 		cdesc->l2tag2 = cpu_to_le16(offload.cd_l2tag2);
-		cdesc->rsvd = cpu_to_le16(0);
+		cdesc->gcs = cpu_to_le16(offload.cd_gcs_params);
 		cdesc->qw1 = cpu_to_le64(offload.cd_qw1);
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h
index 806bce701df34..a4b1e95146327 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.h
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.h
@@ -193,6 +193,7 @@ struct ice_tx_offload_params {
 	u32 td_l2tag1;
 	u32 cd_tunnel_params;
 	u16 cd_l2tag2;
+	u16 cd_gcs_params;
 	u8 header_len;
 };
 
@@ -366,6 +367,7 @@ struct ice_rx_ring {
 #define ICE_RX_FLAGS_RING_BUILD_SKB	BIT(1)
 #define ICE_RX_FLAGS_CRC_STRIP_DIS	BIT(2)
 #define ICE_RX_FLAGS_MULTIDEV		BIT(3)
+#define ICE_RX_FLAGS_RING_GCS		BIT(4)
 	u8 flags;
 	/* CL5 - 5th cacheline starts here */
 	struct xdp_rxq_info xdp_rxq;
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
index 2719f0e20933f..45cfaabc41cbe 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx_lib.c
@@ -80,6 +80,23 @@ ice_rx_hash_to_skb(const struct ice_rx_ring *rx_ring,
 		libeth_rx_pt_set_hash(skb, hash, decoded);
 }
 
+/**
+ * ice_rx_gcs - Set generic checksum in skb
+ * @skb: skb currently being received and modified
+ * @rx_desc: receive descriptor
+ */
+static void ice_rx_gcs(struct sk_buff *skb,
+		       const union ice_32b_rx_flex_desc *rx_desc)
+{
+	const struct ice_32b_rx_flex_desc_nic *desc;
+	u16 csum;
+
+	desc = (struct ice_32b_rx_flex_desc_nic *)rx_desc;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	csum = (__force u16)desc->raw_csum;
+	skb->csum = csum_unfold((__force __sum16)swab16(csum));
+}
+
 /**
  * ice_rx_csum - Indicate in skb if checksum is good
  * @ring: the ring we care about
@@ -107,6 +124,15 @@ ice_rx_csum(struct ice_rx_ring *ring, struct sk_buff *skb,
 	rx_status0 = le16_to_cpu(rx_desc->wb.status_error0);
 	rx_status1 = le16_to_cpu(rx_desc->wb.status_error1);
 
+	if ((ring->flags & ICE_RX_FLAGS_RING_GCS) &&
+	    rx_desc->wb.rxdid == ICE_RXDID_FLEX_NIC &&
+	    (decoded.inner_prot == LIBETH_RX_PT_INNER_TCP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_UDP ||
+	     decoded.inner_prot == LIBETH_RX_PT_INNER_ICMP)) {
+		ice_rx_gcs(skb, rx_desc);
+		return;
+	}
+
 	/* check if HW has decoded the packet and checksum */
 	if (!(rx_status0 & BIT(ICE_RX_FLEX_DESC_STATUS0_L3L4P_S)))
 		return;

From 178edd2633869d523f93881d4ff357916dfb953e Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 10 Mar 2025 10:44:55 -0700
Subject: [PATCH 2212/2753] ice: rename ice_ptp_init_phc_eth56g function

Refactor the code by changing ice_ptp_init_phc_eth56g function
name to ice_ptp_init_phc_e825, to be consistent with the naming pattern
for other devices.

Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-3-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index 3e824f7b30c00..fbaf2819e40e9 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -2650,18 +2650,17 @@ static void ice_sb_access_ena_eth56g(struct ice_hw *hw, bool enable)
 }
 
 /**
- * ice_ptp_init_phc_eth56g - Perform E82X specific PHC initialization
+ * ice_ptp_init_phc_e825 - Perform E825 specific PHC initialization
  * @hw: pointer to HW struct
  *
- * Perform PHC initialization steps specific to E82X devices.
+ * Perform E825-specific PTP hardware clock initialization steps.
  *
- * Return:
- * * %0     - success
- * * %other - failed to initialize CGU
+ * Return: 0 on success, negative error code otherwise.
  */
-static int ice_ptp_init_phc_eth56g(struct ice_hw *hw)
+static int ice_ptp_init_phc_e825(struct ice_hw *hw)
 {
 	ice_sb_access_ena_eth56g(hw, true);
+
 	/* Initialize the Clock Generation Unit */
 	return ice_init_cgu_e82x(hw);
 }
@@ -6123,7 +6122,7 @@ int ice_ptp_init_phc(struct ice_hw *hw)
 	case ICE_MAC_GENERIC:
 		return ice_ptp_init_phc_e82x(hw);
 	case ICE_MAC_GENERIC_3K_E825:
-		return ice_ptp_init_phc_eth56g(hw);
+		return ice_ptp_init_phc_e825(hw);
 	default:
 		return -EOPNOTSUPP;
 	}

From 66a1b7e09fb0daa8052067d99a6ae330e9098389 Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 10 Mar 2025 10:44:56 -0700
Subject: [PATCH 2213/2753] ice: Refactor E825C PHY registers info struct

Simplify ice_phy_reg_info_eth56g struct definition to include base
address for the very first quad. Use base address info and 'step'
value to determine address for specific PHY quad.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-4-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/intel/ice/ice_ptp_consts.h   | 75 ++++---------------
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c   |  6 +-
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h   |  4 +-
 3 files changed, 20 insertions(+), 65 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
index ac46d11833007..003cdfada3ca8 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_consts.h
@@ -10,70 +10,25 @@
 /* Constants defined for the PTP 1588 clock hardware. */
 
 const struct ice_phy_reg_info_eth56g eth56g_phy_res[NUM_ETH56G_PHY_RES] = {
-	/* ETH56G_PHY_REG_PTP */
-	{
-		/* base_addr */
-		{
-			0x092000,
-			0x126000,
-			0x1BA000,
-			0x24E000,
-			0x2E2000,
-		},
-		/* step */
-		0x98,
+	[ETH56G_PHY_REG_PTP] = {
+		.base_addr = 0x092000,
+		.step = 0x98,
 	},
-	/* ETH56G_PHY_MEM_PTP */
-	{
-		/* base_addr */
-		{
-			0x093000,
-			0x127000,
-			0x1BB000,
-			0x24F000,
-			0x2E3000,
-		},
-		/* step */
-		0x200,
+	[ETH56G_PHY_MEM_PTP] = {
+		.base_addr = 0x093000,
+		.step = 0x200,
 	},
-	/* ETH56G_PHY_REG_XPCS */
-	{
-		/* base_addr */
-		{
-			0x000000,
-			0x009400,
-			0x128000,
-			0x1BC000,
-			0x250000,
-		},
-		/* step */
-		0x21000,
+	[ETH56G_PHY_REG_XPCS] = {
+		.base_addr = 0x000000,
+		.step = 0x21000,
 	},
-	/* ETH56G_PHY_REG_MAC */
-	{
-		/* base_addr */
-		{
-			0x085000,
-			0x119000,
-			0x1AD000,
-			0x241000,
-			0x2D5000,
-		},
-		/* step */
-		0x1000,
+	[ETH56G_PHY_REG_MAC] = {
+		.base_addr = 0x085000,
+		.step = 0x1000,
 	},
-	/* ETH56G_PHY_REG_GPCS */
-	{
-		/* base_addr */
-		{
-			0x084000,
-			0x118000,
-			0x1AC000,
-			0x240000,
-			0x2D4000,
-		},
-		/* step */
-		0x400,
+	[ETH56G_PHY_REG_GPCS] = {
+		.base_addr = 0x084000,
+		.step = 0x400,
 	},
 };
 
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index fbaf2819e40e9..89bb8461284ad 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -1010,7 +1010,7 @@ static int ice_phy_res_address_eth56g(struct ice_hw *hw, u8 lane,
 
 	/* Lanes 4..7 are in fact 0..3 on a second PHY */
 	lane %= hw->ptp.ports_per_phy;
-	*addr = eth56g_phy_res[res_type].base[0] +
+	*addr = eth56g_phy_res[res_type].base_addr +
 		lane * eth56g_phy_res[res_type].step + offset;
 
 	return 0;
@@ -1240,7 +1240,7 @@ static int ice_write_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
 	if (port >= hw->ptp.num_lports)
 		return -EIO;
 
-	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset;
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
 
 	return ice_write_phy_eth56g(hw, port, addr, val);
 }
@@ -1265,7 +1265,7 @@ static int ice_read_quad_ptp_reg_eth56g(struct ice_hw *hw, u8 port,
 	if (port >= hw->ptp.num_lports)
 		return -EIO;
 
-	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base[0] + offset;
+	addr = eth56g_phy_res[ETH56G_PHY_REG_PTP].base_addr + offset;
 
 	return ice_read_phy_eth56g(hw, port, addr, val);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index 8442d1d603517..cca81391b6ad0 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -65,14 +65,14 @@ enum ice_eth56g_link_spd {
 
 /**
  * struct ice_phy_reg_info_eth56g - ETH56G PHY register parameters
- * @base: base address for each PHY block
+ * @base_addr: base address for each PHY block
  * @step: step between PHY lanes
  *
  * Characteristic information for the various PHY register parameters in the
  * ETH56G devices
  */
 struct ice_phy_reg_info_eth56g {
-	u32 base[NUM_ETH56G_PHY_RES];
+	u32 base_addr;
 	u32 step;
 };
 

From 50f4ffac918e6e77a501ac743f43204b0b15714e Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Mon, 10 Mar 2025 10:44:57 -0700
Subject: [PATCH 2214/2753] ice: E825C PHY register cleanup

Minor PTP register refactor, including logical grouping E825C 1-step
timestamping registers. Remove unused register definitions
(PHY_REG_GPCS_BITSLIP, PHY_REG_REVISION).
Also, apply preferred GENMASK macro (instead of ICE_M) for register
fields definition affected by this patch.

Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Grzegorz Nitka <grzegorz.nitka@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-5-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/ice/ice_ptp_hw.h | 31 ++++++++++-----------
 1 file changed, 14 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
index cca81391b6ad0..e5925ccc26132 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.h
@@ -780,36 +780,19 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_XIF_TS_SFD_ENA_M	ICE_M(0x1, 20)
 #define PHY_MAC_XIF_GMII_TS_SEL_M	ICE_M(0x1, 21)
 
-/* GPCS config register */
-#define PHY_GPCS_CONFIG_REG0		0x268
-#define PHY_GPCS_CONFIG_REG0_TX_THR_M	ICE_M(0xF, 24)
-#define PHY_GPCS_BITSLIP		0x5C
-
 #define PHY_TS_INT_CONFIG_THRESHOLD_M	ICE_M(0x3F, 0)
 #define PHY_TS_INT_CONFIG_ENA_M		BIT(6)
 
-/* 1-step PTP config */
-#define PHY_PTP_1STEP_CONFIG		0x270
-#define PHY_PTP_1STEP_T1S_UP64_M	ICE_M(0xF, 4)
-#define PHY_PTP_1STEP_T1S_DELTA_M	ICE_M(0xF, 8)
-#define PHY_PTP_1STEP_PEER_DELAY(_port)	(0x274 + 4 * (_port))
-#define PHY_PTP_1STEP_PD_ADD_PD_M	ICE_M(0x1, 0)
-#define PHY_PTP_1STEP_PD_DELAY_M	ICE_M(0x3fffffff, 1)
-#define PHY_PTP_1STEP_PD_DLY_V_M	ICE_M(0x1, 31)
-
 /* Macros to derive offsets for TimeStampLow and TimeStampHigh */
 #define PHY_TSTAMP_L(x) (((x) * 8) + 0)
 #define PHY_TSTAMP_U(x) (((x) * 8) + 4)
 
-#define PHY_REG_REVISION		0x85000
-
 #define PHY_REG_DESKEW_0		0x94
 #define PHY_REG_DESKEW_0_RLEVEL		GENMASK(6, 0)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC	GENMASK(9, 7)
 #define PHY_REG_DESKEW_0_RLEVEL_FRAC_W	3
 #define PHY_REG_DESKEW_0_VALID		GENMASK(10, 10)
 
-#define PHY_REG_GPCS_BITSLIP		0x5C
 #define PHY_REG_SD_BIT_SLIP(_port_offset)	(0x29C + 4 * (_port_offset))
 #define PHY_REVISION_ETH56G		0x10200
 #define PHY_VENDOR_TXLANE_THRESH	0x2000C
@@ -829,7 +812,21 @@ static inline bool ice_is_dual(struct ice_hw *hw)
 #define PHY_MAC_BLOCKTIME		0x50
 #define PHY_MAC_MARKERTIME		0x54
 #define PHY_MAC_TX_OFFSET		0x58
+#define PHY_GPCS_BITSLIP		0x5C
 
 #define PHY_PTP_INT_STATUS		0x7FD140
 
+/* ETH56G registers shared per quad */
+/* GPCS config register */
+#define PHY_GPCS_CONFIG_REG0		0x268
+#define PHY_GPCS_CONFIG_REG0_TX_THR_M	GENMASK(27, 24)
+/* 1-step PTP config */
+#define PHY_PTP_1STEP_CONFIG		0x270
+#define PHY_PTP_1STEP_T1S_UP64_M	GENMASK(7, 4)
+#define PHY_PTP_1STEP_T1S_DELTA_M	GENMASK(11, 8)
+#define PHY_PTP_1STEP_PEER_DELAY(_quad_lane)	(0x274 + 4 * (_quad_lane))
+#define PHY_PTP_1STEP_PD_ADD_PD_M	BIT(0)
+#define PHY_PTP_1STEP_PD_DELAY_M	GENMASK(30, 1)
+#define PHY_PTP_1STEP_PD_DLY_V_M	BIT(31)
+
 #endif /* _ICE_PTP_HW_H_ */

From 18a9b8e358c2f970804c77806228bc7a45769224 Mon Sep 17 00:00:00 2001
From: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Date: Mon, 10 Mar 2025 10:44:58 -0700
Subject: [PATCH 2215/2753] ixgbe: add PTP support for E610 device

Add PTP support for E610 adapter. The E610 is based on X550 and adds
firmware managed link, enhanced security capabilities and support for
updated server manageability. It does not introduce any new PTP features
compared to X550.

Reviewed-by: Milena Olech <milena.olech@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Piotr Kwapulinski <piotr.kwapulinski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Tested-by: Bharath R <bharath.r@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-6-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c |  1 +
 drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c     | 13 +++++++++++--
 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
index da91c582d439b..f03925c1f521a 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c
@@ -3185,6 +3185,7 @@ static int ixgbe_get_ts_info(struct net_device *dev,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		info->rx_filters |= BIT(HWTSTAMP_FILTER_ALL);
 		break;
 	case ixgbe_mac_X540:
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index 9339edbd90821..eef25e11d9381 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -140,6 +140,7 @@
  * proper mult and shift to convert the cycles into nanoseconds of time.
  */
 #define IXGBE_X550_BASE_PERIOD 0xC80000000ULL
+#define IXGBE_E610_BASE_PERIOD 0x333333333ULL
 #define INCVALUE_MASK	0x7FFFFFFF
 #define ISGN		0x80000000
 
@@ -415,6 +416,7 @@ static void ixgbe_ptp_convert_to_hwtstamp(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -492,11 +494,13 @@ static int ixgbe_ptp_adjfine_X550(struct ptp_clock_info *ptp, long scaled_ppm)
 	struct ixgbe_adapter *adapter =
 			container_of(ptp, struct ixgbe_adapter, ptp_caps);
 	struct ixgbe_hw *hw = &adapter->hw;
+	u64 rate, base;
 	bool neg_adj;
-	u64 rate;
 	u32 inca;
 
-	neg_adj = diff_by_scaled_ppm(IXGBE_X550_BASE_PERIOD, scaled_ppm, &rate);
+	base = hw->mac.type == ixgbe_mac_e610 ? IXGBE_E610_BASE_PERIOD :
+						IXGBE_X550_BASE_PERIOD;
+	neg_adj = diff_by_scaled_ppm(base, scaled_ppm, &rate);
 
 	/* warn if rate is too large */
 	if (rate >= INCVALUE_MASK)
@@ -559,6 +563,7 @@ static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* Upper 32 bits represent billions of cycles, lower 32 bits
 		 * represent cycles. However, we use timespec64_to_ns for the
 		 * correct math even though the units haven't been corrected
@@ -1067,6 +1072,7 @@ static int ixgbe_ptp_set_timestamp_mode(struct ixgbe_adapter *adapter,
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		/* enable timestamping all packets only if at least some
 		 * packets were requested. Otherwise, play nice and disable
 		 * timestamping
@@ -1233,6 +1239,7 @@ void ixgbe_ptp_start_cyclecounter(struct ixgbe_adapter *adapter)
 		fallthrough;
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		cc.read = ixgbe_ptp_read_X550;
 		break;
 	case ixgbe_mac_X540:
@@ -1280,6 +1287,7 @@ static void ixgbe_ptp_init_systime(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
 	case ixgbe_mac_X550:
+	case ixgbe_mac_e610:
 		tsauxc = IXGBE_READ_REG(hw, IXGBE_TSAUXC);
 
 		/* Reset SYSTIME registers to 0 */
@@ -1407,6 +1415,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter)
 	case ixgbe_mac_X550:
 	case ixgbe_mac_X550EM_x:
 	case ixgbe_mac_x550em_a:
+	case ixgbe_mac_e610:
 		snprintf(adapter->ptp_caps.name, 16, "%s", netdev->name);
 		adapter->ptp_caps.owner = THIS_MODULE;
 		adapter->ptp_caps.max_adj = 30000000;

From affead2d904e8f82c0b89e23b3835242eb8c3e1a Mon Sep 17 00:00:00 2001
From: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Date: Mon, 10 Mar 2025 10:44:59 -0700
Subject: [PATCH 2216/2753] ixgbe: add support for thermal sensor event
 reception

E610 NICs unlike the previous devices utilising ixgbe driver
are notified in the case of overheating by the FW ACI event.

In event of overheat when threshold is exceeded, FW suspends all
traffic and sends overtemp event to the driver. Then driver
logs appropriate message and disables the adapter instance.
The card remains in that state until the platform is rebooted.

This approach is a solution to the fact current version of the
E610 FW doesn't support reading thermal sensor data by the
SW. So give to user at least any info that overtemp event
has occurred, without interface disappearing from the OS
without any note.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Tested-by: Jeremiah Lokan <jeremiahx.j.lokan@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://patch.msgid.link/20250310174502.3708121-7-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c      | 4 ++++
 drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h | 3 +++
 2 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 467f81239e12f..481f917f7ed28 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -3185,6 +3185,10 @@ static void ixgbe_handle_fw_event(struct ixgbe_adapter *adapter)
 		case ixgbe_aci_opc_get_link_status:
 			ixgbe_handle_link_status_event(adapter, &event);
 			break;
+		case ixgbe_aci_opc_temp_tca_event:
+			e_crit(drv, "%s\n", ixgbe_overheat_msg);
+			ixgbe_down(adapter);
+			break;
 		default:
 			e_warn(hw, "unknown FW async event captured\n");
 			break;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index 8d06ade3c7cd9..617e07878e4f7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -171,6 +171,9 @@ enum ixgbe_aci_opc {
 	ixgbe_aci_opc_done_alt_write			= 0x0904,
 	ixgbe_aci_opc_clear_port_alt_write		= 0x0906,
 
+	/* TCA Events */
+	ixgbe_aci_opc_temp_tca_event                    = 0x0C94,
+
 	/* debug commands */
 	ixgbe_aci_opc_debug_dump_internals		= 0xFF08,
 

From b54b249084648c86fcb351a186210d144c20f544 Mon Sep 17 00:00:00 2001
From: Vasuthevan Maheswaran <vasuthevan.maheswaran@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:23 -0700
Subject: [PATCH 2217/2753] bnxt_en: Add support for a new ethtool dump flag 3

When doing a live coredump with ethtool -w, the context data cached
in the NIC is not dumped by the FW by default.  The reason is that
retrieving this cached context data with traffic running may cause
problems.  Add a new dump flag 3 to allow the option to include this
cached context data which may be useful in some debug scenarios.

Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
Reviewed-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Signed-off-by: Vasuthevan Maheswaran <vasuthevan.maheswaran@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-2-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.h          | 1 +
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c | 9 ++++++---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  | 5 +++--
 3 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index e85b5ce94f587..e93ba0e4f0878 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2697,6 +2697,7 @@ struct bnxt {
 #define BNXT_DUMP_LIVE		0
 #define BNXT_DUMP_CRASH		1
 #define BNXT_DUMP_DRIVER	2
+#define BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE	3
 
 	struct bpf_prog		*xdp_prog;
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 7236d8e548ab5..5576e7cf84631 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -159,8 +159,8 @@ static int bnxt_hwrm_dbg_coredump_list(struct bnxt *bp,
 	return rc;
 }
 
-static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
-					   u16 segment_id)
+static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 dump_type,
+					   u16 component_id, u16 segment_id)
 {
 	struct hwrm_dbg_coredump_initiate_input *req;
 	int rc;
@@ -172,6 +172,8 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id,
 	hwrm_req_timeout(bp, req, bp->hwrm_cmd_max_timeout);
 	req->component_id = cpu_to_le16(component_id);
 	req->segment_id = cpu_to_le16(segment_id);
+	if (dump_type == BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE)
+		req->seg_flags = DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE;
 
 	return hwrm_req_send(bp, req);
 }
@@ -450,7 +452,8 @@ static int __bnxt_get_coredump(struct bnxt *bp, u16 dump_type, void *buf,
 
 		start = jiffies;
 
-		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);
+		rc = bnxt_hwrm_dbg_coredump_initiate(bp, dump_type, comp_id,
+						     seg_id);
 		if (rc) {
 			netdev_err(bp->dev,
 				   "Failed to initiate coredump for seg = %d\n",
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9c58208395144..e031340bdce27 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -5077,8 +5077,9 @@ static int bnxt_set_dump(struct net_device *dev, struct ethtool_dump *dump)
 {
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (dump->flag > BNXT_DUMP_DRIVER) {
-		netdev_info(dev, "Supports only Live(0), Crash(1), Driver(2) dumps.\n");
+	if (dump->flag > BNXT_DUMP_LIVE_WITH_CTX_L1_CACHE) {
+		netdev_info(dev,
+			    "Supports only Live(0), Crash(1), Driver(2), Live with cached context(3) dumps.\n");
 		return -EINVAL;
 	}
 

From ed827402d4f0bb936d3a64ea6915c2fbb6eed30c Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:24 -0700
Subject: [PATCH 2218/2753] bnxt_en: Refactor bnxt_hwrm_nvm_req()

bnxt_hwrm_nvm_req() first searches the nvm_params[] array for the
NVM parameter to set or get.  The array entry contains all the
NVM information about that parameter.  The information is then used
to send the FW message to set or get the parameter.

Refactor it to only do the array search in bnxt_hwrm_nvm_req() and
pass the array entry to the new function __bnxt_hwrm_nvm_req() to
send the FW message.  The next patch will be able to use the new
function.

Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-3-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.c | 63 ++++++++++---------
 1 file changed, 33 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index f8fcc8e0e8ded..e61523854dd8b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -1023,37 +1023,19 @@ static int bnxt_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 }
 
-static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
-			     union devlink_param_value *val)
+static int __bnxt_hwrm_nvm_req(struct bnxt *bp,
+			       const struct bnxt_dl_nvm_param *nvm, void *msg,
+			       union devlink_param_value *val)
 {
 	struct hwrm_nvm_get_variable_input *req = msg;
-	struct bnxt_dl_nvm_param nvm_param;
 	struct hwrm_err_output *resp;
 	union bnxt_nvm_data *data;
 	dma_addr_t data_dma_addr;
-	int idx = 0, rc, i;
-
-	/* Get/Set NVM CFG parameter is supported only on PFs */
-	if (BNXT_VF(bp)) {
-		hwrm_req_drop(bp, req);
-		return -EPERM;
-	}
-
-	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
-		if (nvm_params[i].id == param_id) {
-			nvm_param = nvm_params[i];
-			break;
-		}
-	}
-
-	if (i == ARRAY_SIZE(nvm_params)) {
-		hwrm_req_drop(bp, req);
-		return -EOPNOTSUPP;
-	}
+	int idx = 0, rc;
 
-	if (nvm_param.dir_type == BNXT_NVM_PORT_CFG)
+	if (nvm->dir_type == BNXT_NVM_PORT_CFG)
 		idx = bp->pf.port_id;
-	else if (nvm_param.dir_type == BNXT_NVM_FUNC_CFG)
+	else if (nvm->dir_type == BNXT_NVM_FUNC_CFG)
 		idx = bp->pf.fw_fid - BNXT_FIRST_PF_FID;
 
 	data = hwrm_req_dma_slice(bp, req, sizeof(*data), &data_dma_addr);
@@ -1064,23 +1046,23 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	}
 
 	req->dest_data_addr = cpu_to_le64(data_dma_addr);
-	req->data_len = cpu_to_le16(nvm_param.nvm_num_bits);
-	req->option_num = cpu_to_le16(nvm_param.offset);
+	req->data_len = cpu_to_le16(nvm->nvm_num_bits);
+	req->option_num = cpu_to_le16(nvm->offset);
 	req->index_0 = cpu_to_le16(idx);
 	if (idx)
 		req->dimensions = cpu_to_le16(1);
 
 	resp = hwrm_req_hold(bp, req);
 	if (req->req_type == cpu_to_le16(HWRM_NVM_SET_VARIABLE)) {
-		bnxt_copy_to_nvm_data(data, val, nvm_param.nvm_num_bits,
-				      nvm_param.dl_num_bytes);
+		bnxt_copy_to_nvm_data(data, val, nvm->nvm_num_bits,
+				      nvm->dl_num_bytes);
 		rc = hwrm_req_send(bp, msg);
 	} else {
 		rc = hwrm_req_send_silent(bp, msg);
 		if (!rc) {
 			bnxt_copy_from_nvm_data(val, data,
-						nvm_param.nvm_num_bits,
-						nvm_param.dl_num_bytes);
+						nvm->nvm_num_bits,
+						nvm->dl_num_bytes);
 		} else {
 			if (resp->cmd_err ==
 				NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST)
@@ -1093,6 +1075,27 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
 	return rc;
 }
 
+static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg,
+			     union devlink_param_value *val)
+{
+	struct hwrm_nvm_get_variable_input *req = msg;
+	const struct bnxt_dl_nvm_param *nvm_param;
+	int i;
+
+	/* Get/Set NVM CFG parameter is supported only on PFs */
+	if (BNXT_VF(bp)) {
+		hwrm_req_drop(bp, req);
+		return -EPERM;
+	}
+
+	for (i = 0; i < ARRAY_SIZE(nvm_params); i++) {
+		nvm_param = &nvm_params[i];
+		if (nvm_param->id == param_id)
+			return __bnxt_hwrm_nvm_req(bp, nvm_param, msg, val);
+	}
+	return -EOPNOTSUPP;
+}
+
 static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id,
 				 struct devlink_param_gset_ctx *ctx)
 {

From 2c4d376c3a489e4cb60ae6458b62a4c1d8124895 Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:25 -0700
Subject: [PATCH 2219/2753] bnxt_en: Add devlink support for ENABLE_ROCE nvm
 parameter

Add set/show support for the ENABLE_ROCE NVM parameter to
enable/disable RoCE for a PF.

Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Co-developed-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-4-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/devlink/bnxt.rst     |  2 ++
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.c | 32 +++++++++++++++++++
 .../net/ethernet/broadcom/bnxt/bnxt_devlink.h |  2 ++
 3 files changed, 36 insertions(+)

diff --git a/Documentation/networking/devlink/bnxt.rst b/Documentation/networking/devlink/bnxt.rst
index a4fb27663cd6b..9a8b3d76d11f4 100644
--- a/Documentation/networking/devlink/bnxt.rst
+++ b/Documentation/networking/devlink/bnxt.rst
@@ -24,6 +24,8 @@ Parameters
      - Permanent
    * - ``enable_remote_dev_reset``
      - Runtime
+   * - ``enable_roce``
+     - Permanent
 
 The ``bnxt`` driver also implements the following driver-specific
 parameters.
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index e61523854dd8b..777880594a04c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -679,6 +679,8 @@ static const struct bnxt_dl_nvm_param nvm_params[] = {
 	 NVM_OFF_MSIX_VEC_PER_PF_MAX, BNXT_NVM_SHARED_CFG, 10, 4},
 	{DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN,
 	 NVM_OFF_MSIX_VEC_PER_PF_MIN, BNXT_NVM_SHARED_CFG, 7, 4},
+	{DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, NVM_OFF_SUPPORT_RDMA,
+	 BNXT_NVM_FUNC_CFG, 1, 1},
 	{BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK, NVM_OFF_DIS_GRE_VER_CHECK,
 	 BNXT_NVM_SHARED_CFG, 1, 1},
 };
@@ -1132,6 +1134,32 @@ static int bnxt_dl_nvm_param_set(struct devlink *dl, u32 id,
 	return bnxt_hwrm_nvm_req(bp, id, req, &ctx->val);
 }
 
+static int bnxt_dl_roce_validate(struct devlink *dl, u32 id,
+				 union devlink_param_value val,
+				 struct netlink_ext_ack *extack)
+{
+	const struct bnxt_dl_nvm_param nvm_roce_cap = {0, NVM_OFF_RDMA_CAPABLE,
+		BNXT_NVM_SHARED_CFG, 1, 1};
+	struct bnxt *bp = bnxt_get_bp_from_dl(dl);
+	struct hwrm_nvm_get_variable_input *req;
+	union devlink_param_value roce_cap;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_NVM_GET_VARIABLE);
+	if (rc)
+		return rc;
+
+	if (__bnxt_hwrm_nvm_req(bp, &nvm_roce_cap, req, &roce_cap)) {
+		NL_SET_ERR_MSG_MOD(extack, "Unable to verify if device is RDMA Capable");
+		return -EINVAL;
+	}
+	if (!roce_cap.vbool) {
+		NL_SET_ERR_MSG_MOD(extack, "Device does not support RDMA");
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int bnxt_dl_msix_validate(struct devlink *dl, u32 id,
 				 union devlink_param_value val,
 				 struct netlink_ext_ack *extack)
@@ -1196,6 +1224,10 @@ static const struct devlink_param bnxt_dl_params[] = {
 			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
 			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
 			      bnxt_dl_msix_validate),
+	DEVLINK_PARAM_GENERIC(ENABLE_ROCE,
+			      BIT(DEVLINK_PARAM_CMODE_PERMANENT),
+			      bnxt_dl_nvm_param_get, bnxt_dl_nvm_param_set,
+			      bnxt_dl_roce_validate),
 	DEVLINK_PARAM_DRIVER(BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,
 			     "gre_ver_check", DEVLINK_PARAM_TYPE_BOOL,
 			     BIT(DEVLINK_PARAM_CMODE_PERMANENT),
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
index b8105065367b6..7f45dcd7b2879 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h
@@ -41,8 +41,10 @@ static inline void bnxt_dl_set_remote_reset(struct devlink *dl, bool value)
 #define NVM_OFF_MSIX_VEC_PER_PF_MAX	108
 #define NVM_OFF_MSIX_VEC_PER_PF_MIN	114
 #define NVM_OFF_IGNORE_ARI		164
+#define NVM_OFF_RDMA_CAPABLE		161
 #define NVM_OFF_DIS_GRE_VER_CHECK	171
 #define NVM_OFF_ENABLE_SRIOV		401
+#define NVM_OFF_SUPPORT_RDMA		506
 #define NVM_OFF_NVM_CFG_VER		602
 
 #define BNXT_NVM_CFG_VER_BITS		8

From a6c81e32aeacbfd530d576fa401edd506ec966ef Mon Sep 17 00:00:00 2001
From: shantiprasad shettar <shantiprasad.shettar@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:26 -0700
Subject: [PATCH 2220/2753] bnxt_en: Query FW parameters when the CAPS_CHANGE
 bit is set

Newer FW can set the CAPS_CHANGE flag during ifup if some capabilities
or configurations have changed.  For example, the CoS queue
configurations may have changed.  Support this new flag by treating it
almost like FW reset.  The driver will essentially rediscover all
features and capabilities, reconfigure all backing store context memory,
reset everything to default, and reserve all resources.

Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: shantiprasad shettar <shantiprasad.shettar@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-5-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 869bdde09c730..08a41e9c25ff1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -12309,6 +12309,7 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 	struct hwrm_func_drv_if_change_input *req;
 	bool fw_reset = !bp->irq_tbl;
 	bool resc_reinit = false;
+	bool caps_change = false;
 	int rc, retry = 0;
 	u32 flags = 0;
 
@@ -12364,8 +12365,11 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up)
 		set_bit(BNXT_STATE_ABORT_ERR, &bp->state);
 		return -ENODEV;
 	}
-	if (resc_reinit || fw_reset) {
-		if (fw_reset) {
+	if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE)
+		caps_change = true;
+
+	if (resc_reinit || fw_reset || caps_change) {
+		if (fw_reset || caps_change) {
 			set_bit(BNXT_STATE_FW_RESET_DET, &bp->state);
 			if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 				bnxt_ulp_irq_stop(bp);

From 17596d239f341b3ae4f32781c5d56bf28494709d Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:27 -0700
Subject: [PATCH 2221/2753] bnxt_en: Update firmware interface to 1.10.3.97

The main changes are adding i2c write for module eeprom and a new v2
PCIe statistics structure.

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-6-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h | 143 +++++++++++++++---
 1 file changed, 119 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
index 5f8de16343788..549231703bce7 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
@@ -2,7 +2,7 @@
  *
  * Copyright (c) 2014-2016 Broadcom Corporation
  * Copyright (c) 2014-2018 Broadcom Limited
- * Copyright (c) 2018-2024 Broadcom Inc.
+ * Copyright (c) 2018-2025 Broadcom Inc.
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -438,6 +438,7 @@ struct cmd_nums {
 	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
 	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
 	#define HWRM_MFG_TESTS                            0x21bUL
+	#define HWRM_MFG_WRITE_CERT_NVM                   0x21cUL
 	#define HWRM_PORT_POE_CFG                         0x230UL
 	#define HWRM_PORT_POE_QCFG                        0x231UL
 	#define HWRM_UDCC_QCAPS                           0x258UL
@@ -514,6 +515,8 @@ struct cmd_nums {
 	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
 	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
 	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
+	#define HWRM_TFC_TCAM_PRI_UPDATE                  0x39dUL
+	#define HWRM_TFC_HOT_UPGRADE_PROCESS              0x3a0UL
 	#define HWRM_SV                                   0x400UL
 	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
 	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
@@ -629,8 +632,8 @@ struct hwrm_err_output {
 #define HWRM_VERSION_MAJOR 1
 #define HWRM_VERSION_MINOR 10
 #define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 85
-#define HWRM_VERSION_STR "1.10.3.85"
+#define HWRM_VERSION_RSVD 97
+#define HWRM_VERSION_STR "1.10.3.97"
 
 /* hwrm_ver_get_input (size:192b/24B) */
 struct hwrm_ver_get_input {
@@ -1905,11 +1908,15 @@ struct hwrm_func_qcaps_output {
 	__le32	roce_vf_max_srq;
 	__le32	roce_vf_max_gid;
 	__le32	flags_ext3;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP     0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER          0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED     0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP            0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER                 0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED            0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED                0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED          0x20UL
 	__le16	max_roce_vfs;
-	u8	unused_3[5];
+	__le16	max_crypto_rx_flow_filters;
+	u8	unused_3[3];
 	u8	valid;
 };
 
@@ -1924,7 +1931,7 @@ struct hwrm_func_qcfg_input {
 	u8	unused_0[6];
 };
 
-/* hwrm_func_qcfg_output (size:1280b/160B) */
+/* hwrm_func_qcfg_output (size:1344b/168B) */
 struct hwrm_func_qcfg_output {
 	__le16	error_code;
 	__le16	req_type;
@@ -2087,14 +2094,18 @@ struct hwrm_func_qcfg_output {
 	__le16	host_mtu;
 	__le16	flags2;
 	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
-	u8	unused_4[2];
+	__le16	stag_vid;
 	u8	port_kdnet_mode;
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
 	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
 	u8	kdnet_pcie_function;
 	__le16	port_kdnet_fid;
-	u8	unused_5[2];
+	u8	unused_5;
+	u8	roce_bidi_opt_mode;
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DISABLED      0x1UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED     0x2UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_SHARED        0x4UL
 	__le32	num_ktls_tx_key_ctxs;
 	__le32	num_ktls_rx_key_ctxs;
 	u8	lag_id;
@@ -2112,7 +2123,8 @@ struct hwrm_func_qcfg_output {
 	__le16	xid_partition_cfg;
 	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
 	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
-	u8	unused_7;
+	__le16	mirror_vnic_id;
+	u8	unused_7[7];
 	u8	valid;
 };
 
@@ -3965,7 +3977,7 @@ struct ts_split_entries {
 	__le32	region_num_entries;
 	u8	tsid;
 	u8	lkup_static_bkt_cnt_exp[2];
-	u8	rsvd;
+	u8	locked;
 	__le32	rsvd2[2];
 };
 
@@ -5483,6 +5495,37 @@ struct hwrm_port_phy_qcaps_output {
 	u8	valid;
 };
 
+/* hwrm_port_phy_i2c_write_input (size:832b/104B) */
+struct hwrm_port_phy_i2c_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+	__le32	data[16];
+};
+
+/* hwrm_port_phy_i2c_write_output (size:128b/16B) */
+struct hwrm_port_phy_i2c_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
 /* hwrm_port_phy_i2c_read_input (size:320b/40B) */
 struct hwrm_port_phy_i2c_read_input {
 	__le16	req_type;
@@ -6610,8 +6653,9 @@ struct hwrm_vnic_alloc_input {
 	__le32	flags;
 	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
 	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
+	#define VNIC_ALLOC_REQ_FLAGS_VNIC_ID_VALID            0x4UL
 	__le16	virtio_net_fid;
-	u8	unused_0[2];
+	__le16	vnic_id;
 };
 
 /* hwrm_vnic_alloc_output (size:128b/16B) */
@@ -6710,6 +6754,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
 	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
 	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
+	#define VNIC_CFG_REQ_ENABLES_RAW_QP_ID                0x400UL
 	__le16	vnic_id;
 	__le16	dflt_ring_grp;
 	__le16	rss_rule;
@@ -6729,7 +6774,7 @@ struct hwrm_vnic_cfg_input {
 	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
 	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
 	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
-	u8	unused0[4];
+	__le32	raw_qp_id;
 };
 
 /* hwrm_vnic_cfg_output (size:128b/16B) */
@@ -7082,6 +7127,15 @@ struct hwrm_vnic_plcmodes_cfg_output {
 	u8	valid;
 };
 
+/* hwrm_vnic_plcmodes_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_plcmodes_cfg_cmd_err {
+	u8	code;
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_UNKNOWN               0x0UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD 0x1UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_LAST                 VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD
+	u8	unused_0[7];
+};
+
 /* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
 struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
 	__le16	req_type;
@@ -7131,15 +7185,16 @@ struct hwrm_ring_alloc_input {
 	__le16	target_id;
 	__le64	resp_addr;
 	__le32	enables;
-	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG           0x2UL
-	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID      0x8UL
-	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID           0x20UL
-	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID       0x40UL
-	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID       0x80UL
-	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID      0x100UL
-	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                0x200UL
-	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE         0x400UL
-	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID     0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG              0x2UL
+	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID         0x8UL
+	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID              0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID          0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID          0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID         0x100UL
+	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                   0x200UL
+	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE            0x400UL
+	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID        0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID     0x1000UL
 	u8	ring_type;
 	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
 	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
@@ -7226,7 +7281,11 @@ struct hwrm_ring_alloc_input {
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
 	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
-	u8	unused_4[2];
+	u8	rx_rate_profile_sel;
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_DEFAULT   0x0UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE 0x1UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST     RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE
+	u8	unused_4;
 	__le64	cq_handle;
 };
 
@@ -9122,6 +9181,39 @@ struct pcie_ctx_hw_stats {
 	__le64	pcie_recovery_histogram;
 };
 
+/* pcie_ctx_hw_stats_v2 (size:4096b/512B) */
+struct pcie_ctx_hw_stats_v2 {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+	__le32	pcie_tl_credit_nph_histogram[8];
+	__le32	pcie_tl_credit_ph_histogram[8];
+	__le32	pcie_tl_credit_pd_histogram[8];
+	__le32	pcie_cmpl_latest_times[4];
+	__le32	pcie_cmpl_longest_time;
+	__le32	pcie_cmpl_shortest_time;
+	__le32	unused_0[2];
+	__le32	pcie_cmpl_latest_headers[4][4];
+	__le32	pcie_cmpl_longest_headers[4][4];
+	__le32	pcie_cmpl_shortest_headers[4][4];
+	__le32	pcie_wr_latency_histogram[12];
+	__le32	pcie_wr_latency_all_normal_count;
+	__le32	unused_1;
+	__le64	pcie_posted_packet_count;
+	__le64	pcie_non_posted_packet_count;
+	__le64	pcie_other_packet_count;
+	__le64	pcie_blocked_packet_count;
+	__le64	pcie_cmpl_packet_count;
+};
+
 /* hwrm_stat_generic_qstats_input (size:256b/32B) */
 struct hwrm_stat_generic_qstats_input {
 	__le16	req_type;
@@ -9317,6 +9409,9 @@ struct hwrm_struct_hdr {
 	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND
 	__le16	len;
 	u8	version;
+	#define STRUCT_HDR_VERSION_0 0x0UL
+	#define STRUCT_HDR_VERSION_1 0x1UL
+	#define STRUCT_HDR_VERSION_LAST STRUCT_HDR_VERSION_1
 	u8	count;
 	__le16	subtype;
 	__le16	next_offset;

From 1b64544d634c33605dd112fb7349188b4c305f61 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:28 -0700
Subject: [PATCH 2222/2753] bnxt_en: Refactor bnxt_get_module_eeprom_by_page()

In preparation for adding .set_module_eeprom_by_page(), extract the
common error checking done in bnxt_get_module_eeprom_by_page() into
a new common function that can be re-used for
.set_module_eeprom_by_page().

Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-7-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 21 +++++++++++++++----
 1 file changed, 17 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index e031340bdce27..c0de8f0e722d3 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -4541,11 +4541,11 @@ static int bnxt_get_module_status(struct bnxt *bp, struct netlink_ext_ack *extac
 	return -EINVAL;
 }
 
-static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
-					  const struct ethtool_module_eeprom *page_data,
-					  struct netlink_ext_ack *extack)
+static int
+bnxt_mod_eeprom_by_page_precheck(struct bnxt *bp,
+				 const struct ethtool_module_eeprom *page_data,
+				 struct netlink_ext_ack *extack)
 {
-	struct bnxt *bp = netdev_priv(dev);
 	int rc;
 
 	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) {
@@ -4567,6 +4567,19 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 		NL_SET_ERR_MSG_MOD(extack, "Firmware not capable for bank selection");
 		return -EINVAL;
 	}
+	return 0;
+}
+
+static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
 
 	rc = bnxt_read_sfp_module_eeprom_info(bp, page_data->i2c_address << 1,
 					      page_data->page, page_data->bank,

From c3be245dfc8a5506e0936e9a1224813edc506a0c Mon Sep 17 00:00:00 2001
From: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Date: Mon, 10 Mar 2025 11:31:29 -0700
Subject: [PATCH 2223/2753] bnxt_en: add .set_module_eeprom_by_page() support

Add support for .set_module_eeprom_by_page() callback
which implements generic solution for modules eeprom access.
This implementation also supports CMIS 5.0.3 compliant
eeprom FW download.

Sample Usage:
ethtool --flash-module-firmware enp177s0np0 file dummy.bin

Signed-off-by: Damodharam Ammepalli <damodharam.ammepalli@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250310183129.3154117-8-michael.chan@broadcom.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 59 ++++++++++++++++++-
 1 file changed, 58 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index c0de8f0e722d3..48dd5922e4dd8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -4550,7 +4550,7 @@ bnxt_mod_eeprom_by_page_precheck(struct bnxt *bp,
 
 	if (BNXT_VF(bp) && !BNXT_VF_IS_TRUSTED(bp)) {
 		NL_SET_ERR_MSG_MOD(extack,
-				   "Module read not permitted on untrusted VF");
+				   "Module read/write not permitted on untrusted VF");
 		return -EPERM;
 	}
 
@@ -4593,6 +4593,62 @@ static int bnxt_get_module_eeprom_by_page(struct net_device *dev,
 	return page_data->length;
 }
 
+static int bnxt_write_sfp_module_eeprom_info(struct bnxt *bp,
+					     const struct ethtool_module_eeprom *page)
+{
+	struct hwrm_port_phy_i2c_write_input *req;
+	int bytes_written = 0;
+	int rc;
+
+	rc = hwrm_req_init(bp, req, HWRM_PORT_PHY_I2C_WRITE);
+	if (rc)
+		return rc;
+
+	hwrm_req_hold(bp, req);
+	req->i2c_slave_addr = page->i2c_address << 1;
+	req->page_number = cpu_to_le16(page->page);
+	req->bank_number = page->bank;
+	req->port_id = cpu_to_le16(bp->pf.port_id);
+	req->enables = cpu_to_le32(PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET |
+				   PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER);
+
+	while (bytes_written < page->length) {
+		u16 xfer_size;
+
+		xfer_size = min_t(u16, page->length - bytes_written,
+				  BNXT_MAX_PHY_I2C_RESP_SIZE);
+		req->page_offset = cpu_to_le16(page->offset + bytes_written);
+		req->data_length = xfer_size;
+		memcpy(req->data, page->data + bytes_written, xfer_size);
+		rc = hwrm_req_send(bp, req);
+		if (rc)
+			break;
+		bytes_written += xfer_size;
+	}
+
+	hwrm_req_drop(bp, req);
+	return rc;
+}
+
+static int bnxt_set_module_eeprom_by_page(struct net_device *dev,
+					  const struct ethtool_module_eeprom *page_data,
+					  struct netlink_ext_ack *extack)
+{
+	struct bnxt *bp = netdev_priv(dev);
+	int rc;
+
+	rc = bnxt_mod_eeprom_by_page_precheck(bp, page_data, extack);
+	if (rc)
+		return rc;
+
+	rc = bnxt_write_sfp_module_eeprom_info(bp, page_data);
+	if (rc) {
+		NL_SET_ERR_MSG_MOD(extack, "Module`s eeprom write failed");
+		return rc;
+	}
+	return page_data->length;
+}
+
 static int bnxt_nway_reset(struct net_device *dev)
 {
 	int rc = 0;
@@ -5455,6 +5511,7 @@ const struct ethtool_ops bnxt_ethtool_ops = {
 	.get_module_info	= bnxt_get_module_info,
 	.get_module_eeprom	= bnxt_get_module_eeprom,
 	.get_module_eeprom_by_page = bnxt_get_module_eeprom_by_page,
+	.set_module_eeprom_by_page = bnxt_set_module_eeprom_by_page,
 	.nway_reset		= bnxt_nway_reset,
 	.set_phys_id		= bnxt_set_phys_id,
 	.self_test		= bnxt_self_test,

From cf6efe8902350d2bdd968784a2522b672d77bb81 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:33 +0200
Subject: [PATCH 2224/2753] wifi: iwlwifi: mld: KUnit: test
 iwl_mld_channel_load_allows_emlsr

Add tests to check that iwl_mld_channel_load_allows_emlsr decides
correctly whether EMLSR is allowed or not.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Link: https://patch.msgid.link/20250313002008.06fdf416c62f.If6e8f0e017287e79364eac9366f93c9ab964a673@changeid
[fix kunit visibility macro]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c  |   9 +-
 drivers/net/wireless/intel/iwlwifi/mld/mlo.h  |  14 ++
 .../intel/iwlwifi/mld/tests/link-selection.c  | 131 ++++++++++++++++++
 3 files changed, 147 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 9342f03c0908a..4bd3b2b637691 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -602,12 +602,6 @@ void iwl_mld_emlsr_unblock_tpt_wk(struct wiphy *wiphy, struct wiphy_work *wk)
 /*
  * Link selection
  */
-struct iwl_mld_link_sel_data {
-	u8 link_id;
-	const struct cfg80211_chan_def *chandef;
-	s32 signal;
-	u16 grade;
-};
 
 s8 iwl_mld_get_emlsr_rssi_thresh(struct iwl_mld *mld,
 				 const struct cfg80211_chan_def *chandef,
@@ -737,7 +731,7 @@ iwl_mld_get_min_chan_load_thresh(struct ieee80211_chanctx_conf *chanctx)
 	return 10;
 }
 
-static bool
+VISIBLE_IF_IWLWIFI_KUNIT bool
 iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 				  struct ieee80211_vif *vif,
 				  const struct iwl_mld_link_sel_data *a,
@@ -794,6 +788,7 @@ iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
 
 	return false;
 }
+EXPORT_SYMBOL_IF_IWLWIFI_KUNIT(iwl_mld_channel_load_allows_emlsr);
 
 static bool
 iwl_mld_valid_emlsr_pair(struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
index 6c652c17069f8..4fb1fdbe3df9c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.h
@@ -150,4 +150,18 @@ void iwl_mld_emlsr_check_chan_load(struct ieee80211_hw *hw,
  */
 void iwl_mld_retry_emlsr(struct iwl_mld *mld, struct ieee80211_vif *vif);
 
+struct iwl_mld_link_sel_data {
+	u8 link_id;
+	const struct cfg80211_chan_def *chandef;
+	s32 signal;
+	u16 grade;
+};
+
+#if IS_ENABLED(CONFIG_IWLWIFI_KUNIT_TESTS)
+bool iwl_mld_channel_load_allows_emlsr(struct iwl_mld *mld,
+				       struct ieee80211_vif *vif,
+				       const struct iwl_mld_link_sel_data *a,
+				       const struct iwl_mld_link_sel_data *b);
+#endif
+
 #endif /* __iwl_mld_mlo_h__ */
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
index 34782569d67e4..295dcfd3f85d1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/tests/link-selection.c
@@ -11,6 +11,7 @@
 #include "link.h"
 #include "iface.h"
 #include "phy.h"
+#include "mlo.h"
 
 static const struct link_grading_test_case {
 	const char *desc;
@@ -170,3 +171,133 @@ static struct kunit_suite link_selection = {
 };
 
 kunit_test_suite(link_selection);
+
+static const struct channel_load_case {
+	const char *desc;
+	bool low_latency_vif;
+	u32 chan_load_not_by_us;
+	enum nl80211_chan_width bw_a;
+	enum nl80211_chan_width bw_b;
+	bool primary_link_active;
+	bool expected_result;
+} channel_load_cases[] = {
+	{
+		.desc = "Unequal bandwidth, primary link inactive, EMLSR not allowed",
+		.low_latency_vif = false,
+		.primary_link_active = false,
+		.bw_a = NL80211_CHAN_WIDTH_40,
+		.bw_b = NL80211_CHAN_WIDTH_20,
+		.expected_result = false,
+	},
+	{
+		.desc = "Equal bandwidths, sufficient channel load, EMLSR allowed",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 11,
+		.bw_a = NL80211_CHAN_WIDTH_40,
+		.bw_b = NL80211_CHAN_WIDTH_40,
+		.expected_result = true,
+	},
+	{
+		.desc = "Equal bandwidths, insufficient channel load, EMLSR not allowed",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 6,
+		.bw_a = NL80211_CHAN_WIDTH_80,
+		.bw_b = NL80211_CHAN_WIDTH_80,
+		.expected_result = false,
+	},
+	{
+		.desc = "Low latency VIF, sufficient channel load, EMLSR allowed",
+		.low_latency_vif = true,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 6,
+		.bw_a = NL80211_CHAN_WIDTH_160,
+		.bw_b = NL80211_CHAN_WIDTH_160,
+		.expected_result = true,
+	},
+	{
+		.desc = "Different bandwidths (2x ratio), primary link load permits EMLSR",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 30,
+		.bw_a = NL80211_CHAN_WIDTH_40,
+		.bw_b = NL80211_CHAN_WIDTH_20,
+		.expected_result = true,
+	},
+	{
+		.desc = "Different bandwidths (4x ratio), primary link load permits EMLSR",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 45,
+		.bw_a = NL80211_CHAN_WIDTH_80,
+		.bw_b = NL80211_CHAN_WIDTH_20,
+		.expected_result = true,
+	},
+	{
+		.desc = "Different bandwidths (16x ratio), primary link load insufficient",
+		.low_latency_vif = false,
+		.primary_link_active = true,
+		.chan_load_not_by_us = 45,
+		.bw_a = NL80211_CHAN_WIDTH_320,
+		.bw_b = NL80211_CHAN_WIDTH_20,
+		.expected_result = false,
+	},
+};
+
+KUNIT_ARRAY_PARAM_DESC(channel_load, channel_load_cases, desc);
+
+static void test_iwl_mld_channel_load_allows_emlsr(struct kunit *test)
+{
+	const struct channel_load_case *params = test->param_value;
+	struct iwl_mld *mld = test->priv;
+	struct ieee80211_vif *vif;
+	struct cfg80211_chan_def chandef_a, chandef_b;
+	struct iwl_mld_link_sel_data a = {.chandef = &chandef_a,
+					  .link_id = 4};
+	struct iwl_mld_link_sel_data b = {.chandef = &chandef_b,
+					  .link_id = 5};
+	struct iwl_mld_kunit_link assoc_link = {
+		.id = params->primary_link_active ? a.link_id : b.link_id,
+		.bandwidth = params->primary_link_active ? params->bw_a : params->bw_b,
+	};
+	bool result;
+
+	vif = iwlmld_kunit_setup_mlo_assoc(BIT(a.link_id) | BIT(b.link_id),
+					   &assoc_link);
+
+	chandef_a.width = params->bw_a;
+	chandef_b.width = params->bw_b;
+
+	if (params->low_latency_vif)
+		iwl_mld_vif_from_mac80211(vif)->low_latency_causes = 1;
+
+	wiphy_lock(mld->wiphy);
+
+	/* Simulate channel load */
+	if (params->primary_link_active) {
+		struct iwl_mld_phy *phy =
+			iwlmld_kunit_get_phy_of_link(vif, a.link_id);
+
+		phy->avg_channel_load_not_by_us = params->chan_load_not_by_us;
+	}
+
+	result = iwl_mld_channel_load_allows_emlsr(mld, vif, &a, &b);
+
+	wiphy_unlock(mld->wiphy);
+
+	KUNIT_EXPECT_EQ(test, result, params->expected_result);
+}
+
+static struct kunit_case channel_load_criteria_test_cases[] = {
+	KUNIT_CASE_PARAM(test_iwl_mld_channel_load_allows_emlsr, channel_load_gen_params),
+	{}
+};
+
+static struct kunit_suite channel_load_criteria_tests = {
+	.name = "iwlmld_channel_load_allows_emlsr",
+	.test_cases = channel_load_criteria_test_cases,
+	.init = iwlmld_kunit_test_init,
+};
+
+kunit_test_suite(channel_load_criteria_tests);

From 892998c759065c9abb93ff6acbee0fae0c9cce13 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:34 +0200
Subject: [PATCH 2225/2753] wifi: iwlwifi: mld: make
 iwl_mld_run_fw_init_sequence static

It is not used outside of fw.c.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.2d30c0b66734.I98cd21aeaf6e787af3ee3ed60d0ad8656ed8ec52@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/fw.c  | 2 +-
 drivers/net/wireless/intel/iwlwifi/mld/mld.h | 1 -
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/fw.c b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
index 9c1dce0d59797..62da137e10247 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/fw.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/fw.c
@@ -257,7 +257,7 @@ static int iwl_mld_load_fw_wait_alive(struct iwl_mld *mld)
 	return ret;
 }
 
-int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
+static int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld)
 {
 	struct iwl_notification_wait init_wait;
 	struct iwl_init_extended_cfg_cmd init_cfg = {};
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mld.h b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
index 38f1d1bc5a244..5eceaaf7696db 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mld.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mld.h
@@ -336,7 +336,6 @@ iwl_mld_add_debugfs_files(struct iwl_mld *mld, struct dentry *debugfs_dir)
 {}
 #endif
 
-int iwl_mld_run_fw_init_sequence(struct iwl_mld *mld);
 int iwl_mld_load_fw(struct iwl_mld *mld);
 void iwl_mld_stop_fw(struct iwl_mld *mld);
 int iwl_mld_start_fw(struct iwl_mld *mld);

From bb307028a0c8a39b1b2bc4960794ea00f774637e Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:35 +0200
Subject: [PATCH 2226/2753] wifi: iwlwifi: mld: fix copy/paste error

iwl_mld_emlsr_tmp_non_bss_done_wk used the wrong work name
(prevent_done_wk) to extract the mld_vif pointer,
so the pointer was a wrong one, leading to a page fault.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.aabb2232f9dd.I7cb24458a747e8363df2bf1ff848db6a9d472f60@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/mlo.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
index 4bd3b2b637691..a870e169e2655 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mlo.c
@@ -99,7 +99,7 @@ void iwl_mld_emlsr_tmp_non_bss_done_wk(struct wiphy *wiphy,
 				       struct wiphy_work *wk)
 {
 	struct iwl_mld_vif *mld_vif = container_of(wk, struct iwl_mld_vif,
-						   emlsr.prevent_done_wk.work);
+						   emlsr.tmp_non_bss_done_wk.work);
 	struct ieee80211_vif *vif =
 		container_of((void *)mld_vif, struct ieee80211_vif, drv_priv);
 

From 5789f7913ee37e0f54c073287ab4b5942feb4d12 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:36 +0200
Subject: [PATCH 2227/2753] wifi: iwlwifi: mld: iwl_mld_remove_link can't fail

iwl_mld_remove_link removes the link from both the FW and from the
driver.
If removing it from the FW failed, we assume that the FW is
dead anyway and remove it from the driver as well.
On the other hand, we still return an error value, indicating the caller
(i.e. mac80211) that the link couldn't be removed - while it was
actually removed.
Later, mac80211 might tell the driver again to remove that link,
and then the driver will warn that it doesn't exist.

Fix this by making iwl_mld_remove_link a void function.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250313002008.16fe6ebae412.If5371ff7e096b7078ff9e98ff0e72010cd1f076d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/link.c | 19 ++++++++-----------
 drivers/net/wireless/intel/iwlwifi/mld/link.h |  4 ++--
 .../net/wireless/intel/iwlwifi/mld/mac80211.c |  9 ++-------
 3 files changed, 12 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.c b/drivers/net/wireless/intel/iwlwifi/mld/link.c
index 6db8b53053490..82a4979a3af3c 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.c
@@ -455,7 +455,7 @@ void iwl_mld_deactivate_link(struct iwl_mld *mld,
 					       mld_link->fw_id);
 }
 
-static int
+static void
 iwl_mld_rm_link_from_fw(struct iwl_mld *mld, struct ieee80211_bss_conf *link)
 {
 	struct iwl_mld_link *mld_link = iwl_mld_link_from_mac80211(link);
@@ -464,13 +464,13 @@ iwl_mld_rm_link_from_fw(struct iwl_mld *mld, struct ieee80211_bss_conf *link)
 	lockdep_assert_wiphy(mld->wiphy);
 
 	if (WARN_ON(!mld_link))
-		return -EINVAL;
+		return;
 
 	cmd.link_id = cpu_to_le32(mld_link->fw_id);
 	cmd.spec_link_id = link->link_id;
 	cmd.phy_id = cpu_to_le32(FW_CTXT_ID_INVALID);
 
-	return iwl_mld_send_link_cmd(mld, &cmd, FW_CTXT_ACTION_REMOVE);
+	iwl_mld_send_link_cmd(mld, &cmd, FW_CTXT_ACTION_REMOVE);
 }
 
 static void iwl_mld_omi_bw_update(struct iwl_mld *mld,
@@ -832,18 +832,17 @@ int iwl_mld_add_link(struct iwl_mld *mld,
 }
 
 /* Remove link from fw, unmap the bss_conf, and destroy the link structure */
-int iwl_mld_remove_link(struct iwl_mld *mld,
-			struct ieee80211_bss_conf *bss_conf)
+void iwl_mld_remove_link(struct iwl_mld *mld,
+			 struct ieee80211_bss_conf *bss_conf)
 {
 	struct iwl_mld_vif *mld_vif = iwl_mld_vif_from_mac80211(bss_conf->vif);
 	struct iwl_mld_link *link = iwl_mld_link_from_mac80211(bss_conf);
 	bool is_deflink = link == &mld_vif->deflink;
-	int ret;
 
 	if (WARN_ON(!link || link->active))
-		return -EINVAL;
+		return;
 
-	ret = iwl_mld_rm_link_from_fw(mld, bss_conf);
+	iwl_mld_rm_link_from_fw(mld, bss_conf);
 	/* Continue cleanup on failure */
 
 	if (!is_deflink)
@@ -854,11 +853,9 @@ int iwl_mld_remove_link(struct iwl_mld *mld,
 	wiphy_delayed_work_cancel(mld->wiphy, &link->rx_omi.finished_work);
 
 	if (WARN_ON(link->fw_id >= mld->fw->ucode_capa.num_links))
-		return -EINVAL;
+		return;
 
 	RCU_INIT_POINTER(mld->fw_id_to_bss_conf[link->fw_id], NULL);
-
-	return ret;
 }
 
 void iwl_mld_handle_missed_beacon_notif(struct iwl_mld *mld,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/link.h b/drivers/net/wireless/intel/iwlwifi/mld/link.h
index 3a4f3ac990d7e..42b7bdcbd7412 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/link.h
+++ b/drivers/net/wireless/intel/iwlwifi/mld/link.h
@@ -114,8 +114,8 @@ iwl_mld_cleanup_link(struct iwl_mld *mld, struct iwl_mld_link *link)
 
 int iwl_mld_add_link(struct iwl_mld *mld,
 		     struct ieee80211_bss_conf *bss_conf);
-int iwl_mld_remove_link(struct iwl_mld *mld,
-			struct ieee80211_bss_conf *bss_conf);
+void iwl_mld_remove_link(struct iwl_mld *mld,
+			 struct ieee80211_bss_conf *bss_conf);
 int iwl_mld_activate_link(struct iwl_mld *mld,
 			  struct ieee80211_bss_conf *link);
 void iwl_mld_deactivate_link(struct iwl_mld *mld,
diff --git a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
index 938cf5900a295..6851064b82da1 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/mac80211.c
@@ -2456,13 +2456,8 @@ iwl_mld_change_vif_links(struct ieee80211_hw *hw,
 		added |= BIT(0);
 
 	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {
-		if (removed & BIT(i)) {
-			link_conf = old[i];
-
-			err = iwl_mld_remove_link(mld, link_conf);
-			if (err)
-				return err;
-		}
+		if (removed & BIT(i))
+			iwl_mld_remove_link(mld, old[i]);
 	}
 
 	for (int i = 0; i < IEEE80211_MLD_MAX_NUM_LINKS; i++) {

From 630b6c095e1910a295d8f4494684ef3502c00cf3 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Thu, 13 Mar 2025 00:22:37 +0200
Subject: [PATCH 2228/2753] wifi: iwlwifi: mld: we support v6 of
 compressed_ba_notif

It just added a field that we don't use. Claim support for this new
version.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250313002008.f3b668f41de7.Ib8d984c7158bf286adfb6d343955ff5f95b51d52@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/mld/notif.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/notif.c b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
index 06caedf9b0ba1..fc18cba8aaa8d 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/notif.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/notif.c
@@ -347,7 +347,8 @@ CMD_VERSIONS(missed_beacon_notif,
 CMD_VERSIONS(tx_resp_notif,
 	     CMD_VER_ENTRY(8, iwl_tx_resp))
 CMD_VERSIONS(compressed_ba_notif,
-	     CMD_VER_ENTRY(5, iwl_compressed_ba_notif))
+	     CMD_VER_ENTRY(5, iwl_compressed_ba_notif)
+	     CMD_VER_ENTRY(6, iwl_compressed_ba_notif))
 CMD_VERSIONS(tlc_notif,
 	     CMD_VER_ENTRY(3, iwl_tlc_update_notif))
 CMD_VERSIONS(mu_mimo_grp_notif,

From e4f4a4accf27185ed68493d1aeac1b79096e5a44 Mon Sep 17 00:00:00 2001
From: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Date: Thu, 13 Mar 2025 00:22:38 +0200
Subject: [PATCH 2229/2753] wifi: iwlwifi: mld: add debugfs to control MLO scan

Add a debugfs entry to start/stop an MLO scan. This is required for
testing.

Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Reviewed-by: Benjamin Berg <benjamin.berg@intel.com>
Link: https://patch.msgid.link/20250313002008.1a1c2d285336.I5163ceb97ac797e3cf00badf79b9aa9355d7327d@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/mld/debugfs.c  | 30 ++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
index 14330daa6d138..453ce2ba39d1f 100644
--- a/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
+++ b/drivers/net/wireless/intel/iwlwifi/mld/debugfs.c
@@ -14,6 +14,7 @@
 #include "notif.h"
 #include "ap.h"
 #include "iwl-utils.h"
+#include "scan.h"
 #ifdef CONFIG_THERMAL
 #include "thermal.h"
 #endif
@@ -901,6 +902,33 @@ iwl_dbgfs_vif_twt_operation_write(struct iwl_mld *mld, char *buf, size_t count,
 
 VIF_DEBUGFS_WRITE_FILE_OPS(twt_operation, 256);
 
+static ssize_t iwl_dbgfs_vif_int_mlo_scan_write(struct iwl_mld *mld, char *buf,
+						size_t count, void *data)
+{
+	struct ieee80211_vif *vif = data;
+	u32 action;
+	int ret;
+
+	if (!vif->cfg.assoc || !ieee80211_vif_is_mld(vif))
+		return -EINVAL;
+
+	if (kstrtou32(buf, 0, &action))
+		return -EINVAL;
+
+	if (action == 0) {
+		ret = iwl_mld_scan_stop(mld, IWL_MLD_SCAN_INT_MLO, false);
+	} else if (action == 1) {
+		iwl_mld_int_mlo_scan(mld, vif);
+		ret = 0;
+	} else {
+		ret = -EINVAL;
+	}
+
+	return ret ?: count;
+}
+
+VIF_DEBUGFS_WRITE_FILE_OPS(int_mlo_scan, 32);
+
 void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
 			     struct ieee80211_vif *vif)
 {
@@ -939,8 +967,8 @@ void iwl_mld_add_vif_debugfs(struct ieee80211_hw *hw,
 	VIF_DEBUGFS_ADD_FILE(low_latency, mld_vif_dbgfs, 0600);
 	VIF_DEBUGFS_ADD_FILE(twt_setup, mld_vif_dbgfs, 0200);
 	VIF_DEBUGFS_ADD_FILE(twt_operation, mld_vif_dbgfs, 0200);
+	VIF_DEBUGFS_ADD_FILE(int_mlo_scan, mld_vif_dbgfs, 0200);
 }
-
 #define LINK_DEBUGFS_WRITE_FILE_OPS(name, bufsz)			\
 	WIPHY_DEBUGFS_WRITE_FILE_OPS(link_##name, bufsz, bss_conf)
 

From 4fcfcbe457349267fe048524078e8970807c1a5b Mon Sep 17 00:00:00 2001
From: Jeff Chen <jeff.chen_1@nxp.com>
Date: Fri, 14 Mar 2025 17:42:38 +0800
Subject: [PATCH 2230/2753] wifi: mwifiex: Fix HT40 bandwidth issue.

This patch addresses an issue where, despite the AP supporting 40MHz
bandwidth, the connection was limited to 20MHz. Without this fix,
even if the access point supports 40MHz, the bandwidth after
connection remains at 20MHz. This issue is not a regression.

Signed-off-by: Jeff Chen <jeff.chen_1@nxp.com>
Reviewed-by: Francesco Dolcini <francesco.dolcini@toradex.com>
Link: https://patch.msgid.link/20250314094238.2097341-1-jeff.chen_1@nxp.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/11n.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/11n.c b/drivers/net/wireless/marvell/mwifiex/11n.c
index 66f0f5377ac18..738bafc3749b0 100644
--- a/drivers/net/wireless/marvell/mwifiex/11n.c
+++ b/drivers/net/wireless/marvell/mwifiex/11n.c
@@ -403,12 +403,14 @@ mwifiex_cmd_append_11n_tlv(struct mwifiex_private *priv,
 
 		if (sband->ht_cap.cap & IEEE80211_HT_CAP_SUP_WIDTH_20_40 &&
 		    bss_desc->bcn_ht_oper->ht_param &
-		    IEEE80211_HT_PARAM_CHAN_WIDTH_ANY)
+		    IEEE80211_HT_PARAM_CHAN_WIDTH_ANY) {
+			chan_list->chan_scan_param[0].radio_type |=
+				CHAN_BW_40MHZ << 2;
 			SET_SECONDARYCHAN(chan_list->chan_scan_param[0].
 					  radio_type,
 					  (bss_desc->bcn_ht_oper->ht_param &
 					  IEEE80211_HT_PARAM_CHA_SEC_OFFSET));
-
+		}
 		*buffer += struct_size(chan_list, chan_scan_param, 1);
 		ret_len += struct_size(chan_list, chan_scan_param, 1);
 	}

From 892726f0099efdbec0be8275b58af0dc70e02ff2 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 18 Mar 2025 09:54:46 +0100
Subject: [PATCH 2231/2753] wifi: mac80211: fix indentation in
 ieee80211_set_monitor_channel()

There's some confusing indentation, I thought even that braces
were missing. Fix indentation here.

Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 76453c0f82a52..211ad64cfcdfb 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -919,7 +919,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 	sdata = IEEE80211_DEV_TO_SUB_IF(dev);
 	if (!ieee80211_hw_check(&local->hw, NO_VIRTUAL_MONITOR)) {
 		if (cfg80211_chandef_identical(&local->monitor_chanreq.oper,
-						   &chanreq.oper))
+					       &chanreq.oper))
 			return 0;
 
 		sdata = wiphy_dereference(wiphy, local->monitor_sdata);
@@ -928,7 +928,7 @@ static int ieee80211_set_monitor_channel(struct wiphy *wiphy,
 	}
 
 	if (rcu_access_pointer(sdata->deflink.conf->chanctx_conf) &&
-		cfg80211_chandef_identical(&sdata->vif.bss_conf.chanreq.oper,
+	    cfg80211_chandef_identical(&sdata->vif.bss_conf.chanreq.oper,
 				       &chanreq.oper))
 		return 0;
 

From 16ee3ea8faef8ff042acc15867a6c458c573de61 Mon Sep 17 00:00:00 2001
From: Mikhail Lobanov <m.lobanov@rosa.ru>
Date: Mon, 17 Mar 2025 13:31:37 +0300
Subject: [PATCH 2232/2753] wifi: mac80211: check basic rates validity in
 sta_link_apply_parameters

When userspace sets supported rates for a new station via
NL80211_CMD_NEW_STATION, it might send a list that's empty
or contains only invalid values. Currently, we process these
values in sta_link_apply_parameters() without checking the result of
ieee80211_parse_bitrates(), which can lead to an empty rates bitmap.

A similar issue was addressed for NL80211_CMD_SET_BSS in commit
ce04abc3fcc6 ("wifi: mac80211: check basic rates validity").
This patch applies the same approach in sta_link_apply_parameters()
for NL80211_CMD_NEW_STATION, ensuring there is at least one valid
rate by inspecting the result of ieee80211_parse_bitrates().

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: b95eb7f0eee4 ("wifi: cfg80211/mac80211: separate link params from station params")
Signed-off-by: Mikhail Lobanov <m.lobanov@rosa.ru>
Link: https://patch.msgid.link/20250317103139.17625-1-m.lobanov@rosa.ru
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/mac80211/cfg.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
index 211ad64cfcdfb..9f683f838431d 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -1907,12 +1907,12 @@ static int sta_link_apply_parameters(struct ieee80211_local *local,
 	}
 
 	if (params->supported_rates &&
-	    params->supported_rates_len) {
-		ieee80211_parse_bitrates(link->conf->chanreq.oper.width,
-					 sband, params->supported_rates,
-					 params->supported_rates_len,
-					 &link_sta->pub->supp_rates[sband->band]);
-	}
+	    params->supported_rates_len &&
+	    !ieee80211_parse_bitrates(link->conf->chanreq.oper.width,
+				      sband, params->supported_rates,
+				      params->supported_rates_len,
+				      &link_sta->pub->supp_rates[sband->band]))
+		return -EINVAL;
 
 	if (params->ht_capa)
 		ieee80211_ht_cap_ie_to_sta_ht_cap(sdata, sband,

From fc88dee89d7b63eeb17699393eb659aadf9d9b7c Mon Sep 17 00:00:00 2001
From: Edward Adam Davis <eadavis@qq.com>
Date: Tue, 18 Mar 2025 11:13:45 +0800
Subject: [PATCH 2233/2753] wifi: cfg80211: init wiphy_work before allocating
 rfkill fails

syzbort reported a uninitialize wiphy_work_lock in cfg80211_dev_free. [1]

After rfkill allocation fails, the wiphy release process will be performed,
which will cause cfg80211_dev_free to access the uninitialized wiphy_work
related data.

Move the initialization of wiphy_work to before rfkill initialization to
avoid this issue.

[1]
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe
you didn't initialize this object before use?
turning off the locking correctness validator.
CPU: 0 UID: 0 PID: 5935 Comm: syz-executor550 Not tainted 6.14.0-rc6-syzkaller-00103-g4003c9e78778 #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x116/0x1f0 lib/dump_stack.c:120
 assign_lock_key kernel/locking/lockdep.c:983 [inline]
 register_lock_class+0xc39/0x1240 kernel/locking/lockdep.c:1297
 __lock_acquire+0x135/0x3c40 kernel/locking/lockdep.c:5103
 lock_acquire.part.0+0x11b/0x380 kernel/locking/lockdep.c:5851
 __raw_spin_lock_irqsave include/linux/spinlock_api_smp.h:110 [inline]
 _raw_spin_lock_irqsave+0x3a/0x60 kernel/locking/spinlock.c:162
 cfg80211_dev_free+0x30/0x3d0 net/wireless/core.c:1196
 device_release+0xa1/0x240 drivers/base/core.c:2568
 kobject_cleanup lib/kobject.c:689 [inline]
 kobject_release lib/kobject.c:720 [inline]
 kref_put include/linux/kref.h:65 [inline]
 kobject_put+0x1e4/0x5a0 lib/kobject.c:737
 put_device+0x1f/0x30 drivers/base/core.c:3774
 wiphy_free net/wireless/core.c:1224 [inline]
 wiphy_new_nm+0x1c1f/0x2160 net/wireless/core.c:562
 ieee80211_alloc_hw_nm+0x1b7a/0x2260 net/mac80211/main.c:835
 mac80211_hwsim_new_radio+0x1d6/0x54e0 drivers/net/wireless/virtual/mac80211_hwsim.c:5185
 hwsim_new_radio_nl+0xb42/0x12b0 drivers/net/wireless/virtual/mac80211_hwsim.c:6242
 genl_family_rcv_msg_doit+0x202/0x2f0 net/netlink/genetlink.c:1115
 genl_family_rcv_msg net/netlink/genetlink.c:1195 [inline]
 genl_rcv_msg+0x565/0x800 net/netlink/genetlink.c:1210
 netlink_rcv_skb+0x16b/0x440 net/netlink/af_netlink.c:2533
 genl_rcv+0x28/0x40 net/netlink/genetlink.c:1219
 netlink_unicast_kernel net/netlink/af_netlink.c:1312 [inline]
 netlink_unicast+0x53c/0x7f0 net/netlink/af_netlink.c:1338
 netlink_sendmsg+0x8b8/0xd70 net/netlink/af_netlink.c:1882
 sock_sendmsg_nosec net/socket.c:718 [inline]
 __sock_sendmsg net/socket.c:733 [inline]
 ____sys_sendmsg+0xaaf/0xc90 net/socket.c:2573
 ___sys_sendmsg+0x135/0x1e0 net/socket.c:2627
 __sys_sendmsg+0x16e/0x220 net/socket.c:2659
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xcd/0x250 arch/x86/entry/common.c:83

Fixes: 72d520476a2f ("wifi: cfg80211: cancel wiphy_work before freeing wiphy")
Reported-by: syzbot+aaf0488c83d1d5f4f029@syzkaller.appspotmail.com
Close: https://syzkaller.appspot.com/bug?extid=aaf0488c83d1d5f4f029
Tested-by: syzbot+aaf0488c83d1d5f4f029@syzkaller.appspotmail.com
Signed-off-by: Edward Adam Davis <eadavis@qq.com>
Link: https://patch.msgid.link/tencent_258DD9121DDDB9DD9A1939CFAA0D8625B107@qq.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/wireless/core.c b/net/wireless/core.c
index 983c4d3c95528..9e6b319031210 100644
--- a/net/wireless/core.c
+++ b/net/wireless/core.c
@@ -546,6 +546,9 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
 	INIT_WORK(&rdev->mgmt_registrations_update_wk,
 		  cfg80211_mgmt_registrations_update_wk);
 	spin_lock_init(&rdev->mgmt_registrations_lock);
+	INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work);
+	INIT_LIST_HEAD(&rdev->wiphy_work_list);
+	spin_lock_init(&rdev->wiphy_work_lock);
 
 #ifdef CONFIG_CFG80211_DEFAULT_PS
 	rdev->wiphy.flags |= WIPHY_FLAG_PS_ON_BY_DEFAULT;
@@ -563,9 +566,6 @@ struct wiphy *wiphy_new_nm(const struct cfg80211_ops *ops, int sizeof_priv,
 		return NULL;
 	}
 
-	INIT_WORK(&rdev->wiphy_work, cfg80211_wiphy_work);
-	INIT_LIST_HEAD(&rdev->wiphy_work_list);
-	spin_lock_init(&rdev->wiphy_work_lock);
 	INIT_WORK(&rdev->rfkill_block, cfg80211_rfkill_block_work);
 	INIT_WORK(&rdev->conn_work, cfg80211_conn_work);
 	INIT_WORK(&rdev->event_work, cfg80211_event_work);

From 69ae7e1f73abae20f26e3536ca4a980b90eafeb7 Mon Sep 17 00:00:00 2001
From: Jeff Chen <jeff.chen_1@nxp.com>
Date: Tue, 18 Mar 2025 13:07:38 +0800
Subject: [PATCH 2234/2753] wifi: mwifiex: Fix premature release of RF
 calibration data.

This patch resolves an issue where RF calibration data was being
released before the download process. Without this fix, the
external calibration data file would not be downloaded
at all.

Fixes: d39fbc88956e ("mwifiex: remove cfg_data construction")
Signed-off-by: Jeff Chen <jeff.chen_1@nxp.com>
Link: https://patch.msgid.link/20250318050739.2239376-2-jeff.chen_1@nxp.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/main.c    | 4 ----
 drivers/net/wireless/marvell/mwifiex/sta_cmd.c | 6 +++++-
 2 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/main.c b/drivers/net/wireless/marvell/mwifiex/main.c
index 45eecb5f643b7..b07cb302a00c6 100644
--- a/drivers/net/wireless/marvell/mwifiex/main.c
+++ b/drivers/net/wireless/marvell/mwifiex/main.c
@@ -691,10 +691,6 @@ static int _mwifiex_fw_dpc(const struct firmware *firmware, void *context)
 
 	init_failed = true;
 done:
-	if (adapter->cal_data) {
-		release_firmware(adapter->cal_data);
-		adapter->cal_data = NULL;
-	}
 	if (adapter->firmware) {
 		release_firmware(adapter->firmware);
 		adapter->firmware = NULL;
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
index e2800a831c8ed..c0e6ce1a82fed 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
@@ -2293,9 +2293,13 @@ int mwifiex_sta_init_cmd(struct mwifiex_private *priv, u8 first_sta, bool init)
 						"marvell,caldata");
 		}
 
-		if (adapter->cal_data)
+		if (adapter->cal_data) {
 			mwifiex_send_cmd(priv, HostCmd_CMD_CFG_DATA,
 					 HostCmd_ACT_GEN_SET, 0, NULL, true);
+			release_firmware(adapter->cal_data);
+			adapter->cal_data = NULL;
+		}
+
 
 		/* Read MAC address from HW */
 		ret = mwifiex_send_cmd(priv, HostCmd_CMD_GET_HW_SPEC,

From 9868c4ce9481043d6c11f7421fe2b9637aa0feee Mon Sep 17 00:00:00 2001
From: Jeff Chen <jeff.chen_1@nxp.com>
Date: Tue, 18 Mar 2025 13:07:39 +0800
Subject: [PATCH 2235/2753] wifi: mwifiex: Fix RF calibration data download
 from file

This patch resolves an issue where RF calibration data from a
file could not be downloaded to the firmware. The feature to
download calibration data from a file was broken by the commit:
d39fbc88956e.

The issue arose because the function `mwifiex_cmd_cfg_data()`
was modified in a way that prevented proper handling of
file-based calibration data. While this patch restores the ability
to download RF calibration data from a file, it may inadvertently
break the feature to download calibration data from the device
tree. This is because the function `mwifiex_dnld_dt_cfgdata()`,
which also relies on `mwifiex_cmd_cfg_data()`, is still used for
device tree-based calibration data downloads.

Fixes: d39fbc88956e ("mwifiex: remove cfg_data construction")
Signed-off-by: Jeff Chen <jeff.chen_1@nxp.com>
Link: https://patch.msgid.link/20250318050739.2239376-3-jeff.chen_1@nxp.com
[add newline for shorter lines]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/marvell/mwifiex/fw.h      | 14 ++++++++++++++
 drivers/net/wireless/marvell/mwifiex/sta_cmd.c | 12 ++++++++++--
 2 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/marvell/mwifiex/fw.h b/drivers/net/wireless/marvell/mwifiex/fw.h
index 4a96281792cc1..91458f3bd14a5 100644
--- a/drivers/net/wireless/marvell/mwifiex/fw.h
+++ b/drivers/net/wireless/marvell/mwifiex/fw.h
@@ -454,6 +454,11 @@ enum mwifiex_channel_flags {
 #define HostCmd_RET_BIT                       0x8000
 #define HostCmd_ACT_GEN_GET                   0x0000
 #define HostCmd_ACT_GEN_SET                   0x0001
+#define HOST_CMD_ACT_GEN_SET                  0x0001
+/* Add this non-CamelCase-style macro to comply with checkpatch requirements.
+ *  This macro will eventually replace all existing CamelCase-style macros in
+ *  the future for consistency.
+ */
 #define HostCmd_ACT_GEN_REMOVE                0x0004
 #define HostCmd_ACT_BITWISE_SET               0x0002
 #define HostCmd_ACT_BITWISE_CLR               0x0003
@@ -2352,6 +2357,14 @@ struct host_cmd_ds_add_station {
 	u8 tlv[];
 } __packed;
 
+#define MWIFIEX_CFG_TYPE_CAL 0x2
+
+struct host_cmd_ds_802_11_cfg_data {
+	__le16 action;
+	__le16 type;
+	__le16 data_len;
+} __packed;
+
 struct host_cmd_ds_command {
 	__le16 command;
 	__le16 size;
@@ -2431,6 +2444,7 @@ struct host_cmd_ds_command {
 		struct host_cmd_ds_pkt_aggr_ctrl pkt_aggr_ctrl;
 		struct host_cmd_ds_sta_configure sta_cfg;
 		struct host_cmd_ds_add_station sta_info;
+		struct host_cmd_ds_802_11_cfg_data cfg_data;
 	} params;
 } __packed;
 
diff --git a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
index c0e6ce1a82fed..c4689f5a1acc8 100644
--- a/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
+++ b/drivers/net/wireless/marvell/mwifiex/sta_cmd.c
@@ -1507,6 +1507,7 @@ static int mwifiex_cmd_cfg_data(struct mwifiex_private *priv,
 	u32 len;
 	u8 *data = (u8 *)cmd + S_DS_GEN;
 	int ret;
+	struct host_cmd_ds_802_11_cfg_data *pcfg_data;
 
 	if (prop) {
 		len = prop->length;
@@ -1514,12 +1515,20 @@ static int mwifiex_cmd_cfg_data(struct mwifiex_private *priv,
 						data, len);
 		if (ret)
 			return ret;
+
+		cmd->size = cpu_to_le16(S_DS_GEN + len);
 		mwifiex_dbg(adapter, INFO,
 			    "download cfg_data from device tree: %s\n",
 			    prop->name);
 	} else if (adapter->cal_data->data && adapter->cal_data->size > 0) {
 		len = mwifiex_parse_cal_cfg((u8 *)adapter->cal_data->data,
-					    adapter->cal_data->size, data);
+					    adapter->cal_data->size,
+					    data + sizeof(*pcfg_data));
+		pcfg_data = &cmd->params.cfg_data;
+		pcfg_data->action = cpu_to_le16(HOST_CMD_ACT_GEN_SET);
+		pcfg_data->type = cpu_to_le16(MWIFIEX_CFG_TYPE_CAL);
+		pcfg_data->data_len = cpu_to_le16(len);
+		cmd->size = cpu_to_le16(S_DS_GEN + sizeof(*pcfg_data) + len);
 		mwifiex_dbg(adapter, INFO,
 			    "download cfg_data from config file\n");
 	} else {
@@ -1527,7 +1536,6 @@ static int mwifiex_cmd_cfg_data(struct mwifiex_private *priv,
 	}
 
 	cmd->command = cpu_to_le16(HostCmd_CMD_CFG_DATA);
-	cmd->size = cpu_to_le16(S_DS_GEN + len);
 
 	return 0;
 }

From b407b4b804cd6193f45599aff82307c9e2a81225 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Mon, 10 Mar 2025 23:26:53 +0200
Subject: [PATCH 2236/2753] net/mlx5: Rename devlink rate parent set function
 for leaf nodes

Rename `mlx5_esw_devlink_rate_parent_set()` to
`mlx5_esw_devlink_rate_leaf_parent_set()` to distinguish setting a
parent for leafs from nodes, which is not yet supported.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741642016-44918-2-git-send-email-tariqt@nvidia.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 8 ++++----
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h | 8 ++++----
 3 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index a2cf3e79693dd..2a9e3a43c1c8c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -327,7 +327,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_node_tx_max_set = mlx5_esw_devlink_rate_node_tx_max_set,
 	.rate_node_new = mlx5_esw_devlink_rate_node_new,
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
-	.rate_leaf_parent_set = mlx5_esw_devlink_rate_parent_set,
+	.rate_leaf_parent_set = mlx5_esw_devlink_rate_leaf_parent_set,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 823c1ba456cd1..c56027838a572 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -986,10 +986,10 @@ int mlx5_esw_qos_vport_update_parent(struct mlx5_vport *vport, struct mlx5_esw_s
 	return err;
 }
 
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack)
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
 {
 	struct mlx5_esw_sched_node *node;
 	struct mlx5_vport *vport = priv;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
index 6eb8f6a648c83..43a40bda7d19e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -29,10 +29,10 @@ int mlx5_esw_devlink_rate_node_new(struct devlink_rate *rate_node, void **priv,
 				   struct netlink_ext_ack *extack);
 int mlx5_esw_devlink_rate_node_del(struct devlink_rate *rate_node, void *priv,
 				   struct netlink_ext_ack *extack);
-int mlx5_esw_devlink_rate_parent_set(struct devlink_rate *devlink_rate,
-				     struct devlink_rate *parent,
-				     void *priv, void *parent_priv,
-				     struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
 #endif
 
 #endif

From 498bd79cb92be572258a587a4abee67d464ba1de Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Mon, 10 Mar 2025 23:26:54 +0200
Subject: [PATCH 2237/2753] net/mlx5: Introduce hierarchy level tracking on
 scheduling nodes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add a `level` field to `mlx5_esw_sched_node` to track the hierarchy
depth of each scheduling node. This allows enforcement of the
scheduling depth constraints based on `log_esw_max_sched_depth`.

Modify `esw_qos_node_set_parent()` and `__esw_qos_alloc_node()` to
correctly assign hierarchy levels. Ensure that nodes inherit their
parent’s level incrementally.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741642016-44918-3-git-send-email-tariqt@nvidia.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 19 ++++++++++++++++---
 1 file changed, 16 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index c56027838a572..959e4446327de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -90,8 +90,22 @@ struct mlx5_esw_sched_node {
 	struct list_head children;
 	/* Valid only if this node is associated with a vport. */
 	struct mlx5_vport *vport;
+	/* Level in the hierarchy. The root node level is 1. */
+	u8 level;
 };
 
+static void esw_qos_node_attach_to_parent(struct mlx5_esw_sched_node *node)
+{
+	if (!node->parent) {
+		/* Root children are assigned a depth level of 2. */
+		node->level = 2;
+		list_add_tail(&node->entry, &node->esw->qos.domain->nodes);
+	} else {
+		node->level = node->parent->level + 1;
+		list_add_tail(&node->entry, &node->parent->children);
+	}
+}
+
 static void
 esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_node *parent)
 {
@@ -99,6 +113,7 @@ esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_
 	node->parent = parent;
 	list_add_tail(&node->entry, &parent->children);
 	node->esw = parent->esw;
+	node->level = parent->level + 1;
 }
 
 void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport)
@@ -358,7 +373,6 @@ static struct mlx5_esw_sched_node *
 __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type type,
 		     struct mlx5_esw_sched_node *parent)
 {
-	struct list_head *parent_children;
 	struct mlx5_esw_sched_node *node;
 
 	node = kzalloc(sizeof(*node), GFP_KERNEL);
@@ -370,8 +384,7 @@ __esw_qos_alloc_node(struct mlx5_eswitch *esw, u32 tsar_ix, enum sched_node_type
 	node->type = type;
 	node->parent = parent;
 	INIT_LIST_HEAD(&node->children);
-	parent_children = parent ? &parent->children : &esw->qos.domain->nodes;
-	list_add_tail(&node->entry, parent_children);
+	esw_qos_node_attach_to_parent(node);
 
 	return node;
 }

From f88c349c75e3784a3f5463f5b403ff28dd823782 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Mon, 10 Mar 2025 23:26:55 +0200
Subject: [PATCH 2238/2753] net/mlx5: Preserve rate settings when creating a
 rate node

Modify `esw_qos_create_node_sched_elem()` to receive max_rate and
bw_share values while maintaining the previous configuration.

This change is essential for the upcoming patch that will modify rate
nodes and requires the existing settings to be preserved unless
explicitly changed.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741642016-44918-4-git-send-email-tariqt@nvidia.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 959e4446327de..3c850efb4ca35 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -320,8 +320,9 @@ static int esw_qos_set_node_min_rate(struct mlx5_esw_sched_node *node,
 	return 0;
 }
 
-static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
-					  u32 *tsar_ix)
+static int
+esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_element_id,
+			       u32 max_rate, u32 bw_share, u32 *tsar_ix)
 {
 	u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
 	void *attr;
@@ -338,6 +339,8 @@ static int esw_qos_create_node_sched_elem(struct mlx5_core_dev *dev, u32 parent_
 		 SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
 	MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
 		 parent_element_id);
+	MLX5_SET(scheduling_context, tsar_ctx, max_average_bw, max_rate);
+	MLX5_SET(scheduling_context, tsar_ctx, bw_share, bw_share);
 	attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
 	MLX5_SET(tsar_element, attr, tsar_type, TSAR_ELEMENT_TSAR_TYPE_DWRR);
 
@@ -409,7 +412,8 @@ __esw_qos_create_vports_sched_node(struct mlx5_eswitch *esw, struct mlx5_esw_sch
 	u32 tsar_ix;
 	int err;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, &tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, esw->qos.root_tsar_ix, 0,
+					     0, &tsar_ix);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "E-Switch create TSAR for node failed");
 		return ERR_PTR(err);
@@ -476,7 +480,8 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
 	if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
 		return -EOPNOTSUPP;
 
-	err = esw_qos_create_node_sched_elem(esw->dev, 0, &esw->qos.root_tsar_ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, 0, 0, 0,
+					     &esw->qos.root_tsar_ix);
 	if (err) {
 		esw_warn(dev, "E-Switch create root TSAR failed (%d)\n", err);
 		return err;

From 9c7bbf4c3304f139faad4b753241963f875b4195 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Mon, 10 Mar 2025 23:26:56 +0200
Subject: [PATCH 2239/2753] net/mlx5: Add support for setting parent of nodes

Introduce `mlx5_esw_devlink_rate_node_parent_set()` to allow assigning
a parent to scheduling nodes.
Implement `mlx5_esw_qos_node_update_parent()` and
`mlx5_esw_qos_node_validate_set_parent()` to enforce constraints on
node reassignment.

Don't allow reassignment of nodes with active rate objects.

Update `esw_qos_node_set_parent()` to handle cases where
the parent is NULL. A NULL parent indicates that the scheduling element
is attached to the root scheduling element, and since only rate nodes
can be connected to the root, this update is now necessary.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741642016-44918-5-git-send-email-tariqt@nvidia.com
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c |   1 +
 .../net/ethernet/mellanox/mlx5/core/esw/qos.c | 108 +++++++++++++++++-
 .../net/ethernet/mellanox/mlx5/core/esw/qos.h |   4 +
 3 files changed, 110 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 2a9e3a43c1c8c..73cd746443788 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -328,6 +328,7 @@ static const struct devlink_ops mlx5_devlink_ops = {
 	.rate_node_new = mlx5_esw_devlink_rate_node_new,
 	.rate_node_del = mlx5_esw_devlink_rate_node_del,
 	.rate_leaf_parent_set = mlx5_esw_devlink_rate_leaf_parent_set,
+	.rate_node_parent_set = mlx5_esw_devlink_rate_node_parent_set,
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
 	.port_new = mlx5_devlink_sf_port_new,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
index 3c850efb4ca35..b6ae384396b33 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
@@ -111,9 +111,9 @@ esw_qos_node_set_parent(struct mlx5_esw_sched_node *node, struct mlx5_esw_sched_
 {
 	list_del_init(&node->entry);
 	node->parent = parent;
-	list_add_tail(&node->entry, &parent->children);
-	node->esw = parent->esw;
-	node->level = parent->level + 1;
+	if (parent)
+		node->esw = parent->esw;
+	esw_qos_node_attach_to_parent(node);
 }
 
 void mlx5_esw_qos_vport_qos_free(struct mlx5_vport *vport)
@@ -1018,3 +1018,105 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
 	node = parent_priv;
 	return mlx5_esw_qos_vport_update_parent(vport, node, extack);
 }
+
+static int
+mlx5_esw_qos_node_validate_set_parent(struct mlx5_esw_sched_node *node,
+				      struct mlx5_esw_sched_node *parent,
+				      struct netlink_ext_ack *extack)
+{
+	u8 new_level, max_level;
+
+	if (parent && parent->esw != node->esw) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot assign node to another E-Switch");
+		return -EOPNOTSUPP;
+	}
+
+	if (!list_empty(&node->children)) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Cannot reassign a node that contains rate objects");
+		return -EOPNOTSUPP;
+	}
+
+	new_level = parent ? parent->level + 1 : 2;
+	max_level = 1 << MLX5_CAP_QOS(node->esw->dev, log_esw_max_sched_depth);
+	if (new_level > max_level) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Node hierarchy depth exceeds the maximum supported level");
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+static int esw_qos_vports_node_update_parent(struct mlx5_esw_sched_node *node,
+					     struct mlx5_esw_sched_node *parent,
+					     struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent = node->parent;
+	struct mlx5_eswitch *esw = node->esw;
+	u32 parent_ix;
+	int err;
+
+	parent_ix = parent ? parent->ix : node->esw->qos.root_tsar_ix;
+	mlx5_destroy_scheduling_element_cmd(esw->dev,
+					    SCHEDULING_HIERARCHY_E_SWITCH,
+					    node->ix);
+	err = esw_qos_create_node_sched_elem(esw->dev, parent_ix,
+					     node->max_rate, 0, &node->ix);
+	if (err) {
+		NL_SET_ERR_MSG_MOD(extack,
+				   "Failed to create a node under the new hierarchy.");
+		if (esw_qos_create_node_sched_elem(esw->dev, curr_parent->ix,
+						   node->max_rate,
+						   node->bw_share,
+						   &node->ix))
+			esw_warn(esw->dev, "Node restore QoS failed\n");
+
+		return err;
+	}
+	esw_qos_node_set_parent(node, parent);
+
+	return 0;
+}
+
+static int mlx5_esw_qos_node_update_parent(struct mlx5_esw_sched_node *node,
+					   struct mlx5_esw_sched_node *parent,
+					   struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *curr_parent;
+	struct mlx5_eswitch *esw = node->esw;
+	int err;
+
+	err = mlx5_esw_qos_node_validate_set_parent(node, parent, extack);
+	if (err)
+		return err;
+
+	esw_qos_lock(esw);
+	curr_parent = node->parent;
+	err = esw_qos_vports_node_update_parent(node, parent, extack);
+	if (err)
+		goto out;
+
+	esw_qos_normalize_min_rate(esw, curr_parent, extack);
+	esw_qos_normalize_min_rate(esw, parent, extack);
+
+out:
+	esw_qos_unlock(esw);
+
+	return err;
+}
+
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack)
+{
+	struct mlx5_esw_sched_node *node = priv, *parent_node;
+
+	if (!parent)
+		return mlx5_esw_qos_node_update_parent(node, NULL, extack);
+
+	parent_node = parent_priv;
+	return mlx5_esw_qos_node_update_parent(node, parent_node, extack);
+}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
index 43a40bda7d19e..ed40ec8f027e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.h
@@ -33,6 +33,10 @@ int mlx5_esw_devlink_rate_leaf_parent_set(struct devlink_rate *devlink_rate,
 					  struct devlink_rate *parent,
 					  void *priv, void *parent_priv,
 					  struct netlink_ext_ack *extack);
+int mlx5_esw_devlink_rate_node_parent_set(struct devlink_rate *devlink_rate,
+					  struct devlink_rate *parent,
+					  void *priv, void *parent_priv,
+					  struct netlink_ext_ack *extack);
 #endif
 
 #endif

From f5825e79b2b7b1b0912c219d24cd7aa3eb3e300d Mon Sep 17 00:00:00 2001
From: Chen Ni <nichen@iscas.ac.cn>
Date: Tue, 11 Mar 2025 15:06:24 +0800
Subject: [PATCH 2240/2753] qed: remove cast to pointers passed to kfree

Remove unnecessary casts to pointer types passed to kfree.
Issue detected by coccinelle:
@@
type t1;
expression *e;
@@

-kfree((t1 *)e);
+kfree(e);

Signed-off-by: Chen Ni <nichen@iscas.ac.cn>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Link: https://patch.msgid.link/20250311070624.1037787-1-nichen@iscas.ac.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/qlogic/qed/qed_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c
index f915c423fe70b..886061d7351a1 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_main.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_main.c
@@ -454,7 +454,7 @@ int qed_fill_dev_info(struct qed_dev *cdev,
 
 static void qed_free_cdev(struct qed_dev *cdev)
 {
-	kfree((void *)cdev);
+	kfree(cdev);
 }
 
 static struct qed_dev *qed_alloc_cdev(struct pci_dev *pdev)

From 5f079290e5913a0060e059500b7d440990ac1066 Mon Sep 17 00:00:00 2001
From: Vignesh Raghavendra <vigneshr@ti.com>
Date: Tue, 11 Mar 2025 21:12:59 +0530
Subject: [PATCH 2241/2753] net: ethernet: ti: am65-cpsw: Fix NAPI registration
 sequence

Registering the interrupts for TX or RX DMA Channels prior to registering
their respective NAPI callbacks can result in a NULL pointer dereference.
This is seen in practice as a random occurrence since it depends on the
randomness associated with the generation of traffic by Linux and the
reception of traffic from the wire.

Fixes: 681eb2beb3ef ("net: ethernet: ti: am65-cpsw: ensure proper channel cleanup in error path")
Signed-off-by: Vignesh Raghavendra <vigneshr@ti.com>
Co-developed-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Signed-off-by: Siddharth Vadapalli <s-vadapalli@ti.com>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@siemens.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Link: https://patch.msgid.link/20250311154259.102865-1-s-vadapalli@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/am65-cpsw-nuss.c | 32 +++++++++++++-----------
 1 file changed, 18 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
index 2806238629f82..bef734c6e5c2b 100644
--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
@@ -2306,14 +2306,18 @@ static void am65_cpsw_nuss_remove_tx_chns(struct am65_cpsw_common *common)
 static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 {
 	struct device *dev = common->dev;
+	struct am65_cpsw_tx_chn *tx_chn;
 	int i, ret = 0;
 
 	for (i = 0; i < common->tx_ch_num; i++) {
-		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
+		tx_chn = &common->tx_chns[i];
 
 		hrtimer_init(&tx_chn->tx_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED);
 		tx_chn->tx_hrtimer.function = &am65_cpsw_nuss_tx_timer_callback;
 
+		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
+				  am65_cpsw_nuss_tx_poll);
+
 		ret = devm_request_irq(dev, tx_chn->irq,
 				       am65_cpsw_nuss_tx_irq,
 				       IRQF_TRIGGER_HIGH,
@@ -2323,19 +2327,16 @@ static int am65_cpsw_nuss_ndev_add_tx_napi(struct am65_cpsw_common *common)
 				tx_chn->id, tx_chn->irq, ret);
 			goto err;
 		}
-
-		netif_napi_add_tx(common->dma_ndev, &tx_chn->napi_tx,
-				  am65_cpsw_nuss_tx_poll);
 	}
 
 	return 0;
 
 err:
-	for (--i ; i >= 0 ; i--) {
-		struct am65_cpsw_tx_chn *tx_chn = &common->tx_chns[i];
-
-		netif_napi_del(&tx_chn->napi_tx);
+	netif_napi_del(&tx_chn->napi_tx);
+	for (--i; i >= 0; i--) {
+		tx_chn = &common->tx_chns[i];
 		devm_free_irq(dev, tx_chn->irq, tx_chn);
+		netif_napi_del(&tx_chn->napi_tx);
 	}
 
 	return ret;
@@ -2569,6 +2570,9 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			     HRTIMER_MODE_REL_PINNED);
 		flow->rx_hrtimer.function = &am65_cpsw_nuss_rx_timer_callback;
 
+		netif_napi_add(common->dma_ndev, &flow->napi_rx,
+			       am65_cpsw_nuss_rx_poll);
+
 		ret = devm_request_irq(dev, flow->irq,
 				       am65_cpsw_nuss_rx_irq,
 				       IRQF_TRIGGER_HIGH,
@@ -2577,11 +2581,8 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 			dev_err(dev, "failure requesting rx %d irq %u, %d\n",
 				i, flow->irq, ret);
 			flow->irq = -EINVAL;
-			goto err_flow;
+			goto err_request_irq;
 		}
-
-		netif_napi_add(common->dma_ndev, &flow->napi_rx,
-			       am65_cpsw_nuss_rx_poll);
 	}
 
 	/* setup classifier to route priorities to flows */
@@ -2589,11 +2590,14 @@ static int am65_cpsw_nuss_init_rx_chns(struct am65_cpsw_common *common)
 
 	return 0;
 
+err_request_irq:
+	netif_napi_del(&flow->napi_rx);
+
 err_flow:
-	for (--i; i >= 0 ; i--) {
+	for (--i; i >= 0; i--) {
 		flow = &rx_chn->flows[i];
-		netif_napi_del(&flow->napi_rx);
 		devm_free_irq(dev, flow->irq, flow);
+		netif_napi_del(&flow->napi_rx);
 	}
 
 err:

From 2fc8a346625eb1abfe202062c7e6a13d76cde5ea Mon Sep 17 00:00:00 2001
From: Haiyang Zhang <haiyangz@microsoft.com>
Date: Tue, 11 Mar 2025 13:12:54 -0700
Subject: [PATCH 2242/2753] net: mana: Support holes in device list reply msg

According to GDMA protocol, holes (zeros) are allowed at the beginning
or middle of the gdma_list_devices_resp message. The existing code
cannot properly handle this, and may miss some devices in the list.

To fix, scan the entire list until the num_of_devs are found, or until
the end of the list.

Cc: stable@vger.kernel.org
Fixes: ca9c54d2d6a5 ("net: mana: Add a driver for Microsoft Azure Network Adapter (MANA)")
Signed-off-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Long Li <longli@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@microsoft.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/1741723974-1534-1-git-send-email-haiyangz@microsoft.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microsoft/mana/gdma_main.c | 14 ++++++++++----
 include/net/mana/gdma.h                         | 11 +++++++----
 2 files changed, 17 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/microsoft/mana/gdma_main.c b/drivers/net/ethernet/microsoft/mana/gdma_main.c
index 11457b6296cc0..638ef64d639f3 100644
--- a/drivers/net/ethernet/microsoft/mana/gdma_main.c
+++ b/drivers/net/ethernet/microsoft/mana/gdma_main.c
@@ -134,9 +134,10 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 	struct gdma_list_devices_resp resp = {};
 	struct gdma_general_req req = {};
 	struct gdma_dev_id dev;
-	u32 i, max_num_devs;
+	int found_dev = 0;
 	u16 dev_type;
 	int err;
+	u32 i;
 
 	mana_gd_init_req_hdr(&req.hdr, GDMA_LIST_DEVICES, sizeof(req),
 			     sizeof(resp));
@@ -148,12 +149,17 @@ static int mana_gd_detect_devices(struct pci_dev *pdev)
 		return err ? err : -EPROTO;
 	}
 
-	max_num_devs = min_t(u32, MAX_NUM_GDMA_DEVICES, resp.num_of_devs);
-
-	for (i = 0; i < max_num_devs; i++) {
+	for (i = 0; i < GDMA_DEV_LIST_SIZE &&
+	     found_dev < resp.num_of_devs; i++) {
 		dev = resp.devs[i];
 		dev_type = dev.type;
 
+		/* Skip empty devices */
+		if (dev.as_uint32 == 0)
+			continue;
+
+		found_dev++;
+
 		/* HWC is already detected in mana_hwc_create_channel(). */
 		if (dev_type == GDMA_DEVICE_HWC)
 			continue;
diff --git a/include/net/mana/gdma.h b/include/net/mana/gdma.h
index 90f56656b5724..62e9d76738628 100644
--- a/include/net/mana/gdma.h
+++ b/include/net/mana/gdma.h
@@ -408,8 +408,6 @@ struct gdma_context {
 	struct gdma_dev		mana_ib;
 };
 
-#define MAX_NUM_GDMA_DEVICES	4
-
 static inline bool mana_gd_is_mana(struct gdma_dev *gd)
 {
 	return gd->dev_id.type == GDMA_DEVICE_MANA;
@@ -556,11 +554,15 @@ enum {
 #define GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG BIT(3)
 #define GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT BIT(5)
 
+/* Driver can handle holes (zeros) in the device list */
+#define GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP BIT(11)
+
 #define GDMA_DRV_CAP_FLAGS1 \
 	(GDMA_DRV_CAP_FLAG_1_EQ_SHARING_MULTI_VPORT | \
 	 GDMA_DRV_CAP_FLAG_1_NAPI_WKDONE_FIX | \
 	 GDMA_DRV_CAP_FLAG_1_HWC_TIMEOUT_RECONFIG | \
-	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT)
+	 GDMA_DRV_CAP_FLAG_1_VARIABLE_INDIRECTION_TABLE_SUPPORT | \
+	 GDMA_DRV_CAP_FLAG_1_DEV_LIST_HOLES_SUP)
 
 #define GDMA_DRV_CAP_FLAGS2 0
 
@@ -621,11 +623,12 @@ struct gdma_query_max_resources_resp {
 }; /* HW DATA */
 
 /* GDMA_LIST_DEVICES */
+#define GDMA_DEV_LIST_SIZE 64
 struct gdma_list_devices_resp {
 	struct gdma_resp_hdr hdr;
 	u32 num_of_devs;
 	u32 reserved;
-	struct gdma_dev_id devs[64];
+	struct gdma_dev_id devs[GDMA_DEV_LIST_SIZE];
 }; /* HW DATA */
 
 /* GDMA_REGISTER_DEVICE */

From 8d4880db378350f8ed8969feea13bdc164564fc1 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 11 Mar 2025 21:42:28 +0100
Subject: [PATCH 2243/2753] udp_tunnel: create a fastpath GRO lookup.

Most UDP tunnels bind a socket to a local port, with ANY address, no
peer and no interface index specified.
Additionally it's quite common to have a single tunnel device per
namespace.

Track in each namespace the UDP tunnel socket respecting the above.
When only a single one is present, store a reference in the netns.

When such reference is not NULL, UDP tunnel GRO lookup just need to
match the incoming packet destination port vs the socket local port.

The tunnel socket never sets the reuse[port] flag[s]. When bound to no
address and interface, no other socket can exist in the same netns
matching the specified local port.

Matching packets with non-local destination addresses will be
aggregated, and eventually segmented as needed - no behavior changes
intended.

Note that the UDP tunnel socket reference is stored into struct
netns_ipv4 for both IPv4 and IPv6 tunnels. That is intentional to keep
all the fastpath-related netns fields in the same struct and allow
cacheline-based optimization. Currently both the IPv4 and IPv6 socket
pointer share the same cacheline as the `udp_table` field.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/4d5c319c4471161829f50cb8436841de81a5edae.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/udp.h        | 16 ++++++++++++++++
 include/net/netns/ipv4.h   | 11 +++++++++++
 include/net/udp.h          |  1 +
 include/net/udp_tunnel.h   | 18 ++++++++++++++++++
 net/ipv4/udp.c             | 13 ++++++++++++-
 net/ipv4/udp_offload.c     | 37 +++++++++++++++++++++++++++++++++++++
 net/ipv4/udp_tunnel_core.c | 12 ++++++++++++
 net/ipv6/udp.c             |  2 ++
 net/ipv6/udp_offload.c     |  5 +++++
 9 files changed, 114 insertions(+), 1 deletion(-)

diff --git a/include/linux/udp.h b/include/linux/udp.h
index 0807e21cfec95..895240177f4f4 100644
--- a/include/linux/udp.h
+++ b/include/linux/udp.h
@@ -101,6 +101,13 @@ struct udp_sock {
 
 	/* Cache friendly copy of sk->sk_peek_off >= 0 */
 	bool		peeking_with_offset;
+
+	/*
+	 * Accounting for the tunnel GRO fastpath.
+	 * Unprotected by compilers guard, as it uses space available in
+	 * the last UDP socket cacheline.
+	 */
+	struct hlist_node	tunnel_list;
 };
 
 #define udp_test_bit(nr, sk)			\
@@ -219,4 +226,13 @@ static inline void udp_allow_gso(struct sock *sk)
 
 #define IS_UDPLITE(__sk) (__sk->sk_protocol == IPPROTO_UDPLITE)
 
+static inline struct sock *udp_tunnel_sk(const struct net *net, bool is_ipv6)
+{
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	return rcu_dereference(net->ipv4.udp_tunnel_gro[is_ipv6].sk);
+#else
+	return NULL;
+#endif
+}
+
 #endif	/* _LINUX_UDP_H */
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 650b2dc9199f4..6373e3f17da84 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -47,6 +47,11 @@ struct sysctl_fib_multipath_hash_seed {
 };
 #endif
 
+struct udp_tunnel_gro {
+	struct sock __rcu *sk;
+	struct hlist_head list;
+};
+
 struct netns_ipv4 {
 	/* Cacheline organization can be found documented in
 	 * Documentation/networking/net_cachelines/netns_ipv4_sysctl.rst.
@@ -85,6 +90,11 @@ struct netns_ipv4 {
 	struct inet_timewait_death_row tcp_death_row;
 	struct udp_table *udp_table;
 
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	/* Not in a pernet subsys because need to be available at GRO stage */
+	struct udp_tunnel_gro udp_tunnel_gro[2];
+#endif
+
 #ifdef CONFIG_SYSCTL
 	struct ctl_table_header	*forw_hdr;
 	struct ctl_table_header	*frags_hdr;
@@ -277,4 +287,5 @@ struct netns_ipv4 {
 	struct hlist_head	*inet_addr_lst;
 	struct delayed_work	addr_chk_work;
 };
+
 #endif
diff --git a/include/net/udp.h b/include/net/udp.h
index 6e89520e100dc..a772510b2aa58 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -290,6 +290,7 @@ static inline void udp_lib_init_sock(struct sock *sk)
 	struct udp_sock *up = udp_sk(sk);
 
 	skb_queue_head_init(&up->reader_queue);
+	INIT_HLIST_NODE(&up->tunnel_list);
 	up->forward_threshold = sk->sk_rcvbuf >> 2;
 	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 }
diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index a93dc51f6323e..eda0f3e2f65fa 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -203,6 +203,24 @@ static inline void udp_tunnel_encap_enable(struct sock *sk)
 	udp_encap_enable();
 }
 
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add);
+#else
+static inline void udp_tunnel_update_gro_lookup(struct net *net,
+						struct sock *sk, bool add) {}
+#endif
+
+static inline void udp_tunnel_cleanup_gro(struct sock *sk)
+{
+	struct udp_sock *up = udp_sk(sk);
+	struct net *net = sock_net(sk);
+
+	if (!up->tunnel_list.pprev)
+		return;
+
+	udp_tunnel_update_gro_lookup(net, sk, false);
+}
+
 #define UDP_TUNNEL_NIC_MAX_TABLES	4
 
 enum udp_tunnel_nic_info_flags {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index d0bffcfa56d8d..db606f7e41638 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2891,8 +2891,10 @@ void udp_destroy_sock(struct sock *sk)
 			if (encap_destroy)
 				encap_destroy(sk);
 		}
-		if (udp_test_bit(ENCAP_ENABLED, sk))
+		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udp_encap_needed_key);
+			udp_tunnel_cleanup_gro(sk);
+		}
 	}
 }
 
@@ -3804,6 +3806,15 @@ static void __net_init udp_set_table(struct net *net)
 
 static int __net_init udp_pernet_init(struct net *net)
 {
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+	int i;
+
+	/* No tunnel is configured */
+	for (i = 0; i < ARRAY_SIZE(net->ipv4.udp_tunnel_gro); ++i) {
+		INIT_HLIST_HEAD(&net->ipv4.udp_tunnel_gro[i].list);
+		RCU_INIT_POINTER(net->ipv4.udp_tunnel_gro[i].sk, NULL);
+	}
+#endif
 	udp_sysctl_init(net);
 	udp_set_table(net);
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 2c0725583be39..e36d8a234848f 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -12,6 +12,38 @@
 #include <net/udp.h>
 #include <net/protocol.h>
 #include <net/inet_common.h>
+#include <net/udp_tunnel.h>
+
+#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+static DEFINE_SPINLOCK(udp_tunnel_gro_lock);
+
+void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add)
+{
+	bool is_ipv6 = sk->sk_family == AF_INET6;
+	struct udp_sock *tup, *up = udp_sk(sk);
+	struct udp_tunnel_gro *udp_tunnel_gro;
+
+	spin_lock(&udp_tunnel_gro_lock);
+	udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6];
+	if (add)
+		hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list);
+	else
+		hlist_del_init(&up->tunnel_list);
+
+	if (udp_tunnel_gro->list.first &&
+	    !udp_tunnel_gro->list.first->next) {
+		tup = hlist_entry(udp_tunnel_gro->list.first, struct udp_sock,
+				  tunnel_list);
+
+		rcu_assign_pointer(udp_tunnel_gro->sk, (struct sock *)tup);
+	} else {
+		RCU_INIT_POINTER(udp_tunnel_gro->sk, NULL);
+	}
+
+	spin_unlock(&udp_tunnel_gro_lock);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup);
+#endif
 
 static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
 	netdev_features_t features,
@@ -635,8 +667,13 @@ static struct sock *udp4_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct iphdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net_rcu(skb->dev);
+	struct sock *sk;
 	int iif, sdif;
 
+	sk = udp_tunnel_sk(net, false);
+	if (sk && dport == htons(sk->sk_num))
+		return sk;
+
 	inet_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp4_lib_lookup(net, iph->saddr, sport,
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index 619a53eb672da..b5695826e57ad 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -58,6 +58,15 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg,
 }
 EXPORT_SYMBOL(udp_sock_create4);
 
+static bool sk_saddr_any(struct sock *sk)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
+#else
+	return !sk->sk_rcv_saddr;
+#endif
+}
+
 void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 			   struct udp_tunnel_sock_cfg *cfg)
 {
@@ -80,6 +89,9 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 	udp_sk(sk)->gro_complete = cfg->gro_complete;
 
 	udp_tunnel_encap_enable(sk);
+
+	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sock->sk))
+		udp_tunnel_update_gro_lookup(net, sock->sk, true);
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 024458ef163c9..7317f8e053f1c 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -46,6 +46,7 @@
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
 #include <net/ip6_tunnel.h>
+#include <net/udp_tunnel.h>
 #include <net/xfrm.h>
 #include <net/inet_hashtables.h>
 #include <net/inet6_hashtables.h>
@@ -1825,6 +1826,7 @@ void udpv6_destroy_sock(struct sock *sk)
 		if (udp_test_bit(ENCAP_ENABLED, sk)) {
 			static_branch_dec(&udpv6_encap_needed_key);
 			udp_encap_disable();
+			udp_tunnel_cleanup_gro(sk);
 		}
 	}
 }
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index 404212dfc99ab..d8445ac1b2e43 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -118,8 +118,13 @@ static struct sock *udp6_gro_lookup_skb(struct sk_buff *skb, __be16 sport,
 {
 	const struct ipv6hdr *iph = skb_gro_network_header(skb);
 	struct net *net = dev_net_rcu(skb->dev);
+	struct sock *sk;
 	int iif, sdif;
 
+	sk = udp_tunnel_sk(net, true);
+	if (sk && dport == htons(sk->sk_num))
+		return sk;
+
 	inet6_get_iif_sdif(skb, &iif, &sdif);
 
 	return __udp6_lib_lookup(net, &iph->saddr, sport,

From 311b36574ceaccfa3f91b74054a09cd4bb877702 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 11 Mar 2025 21:42:29 +0100
Subject: [PATCH 2244/2753] udp_tunnel: use static call for GRO hooks when
 possible

It's quite common to have a single UDP tunnel type active in the
whole system. In such a case we can replace the indirect call for
the UDP tunnel GRO callback with a static call.

Add the related accounting in the control path and switch to static
call when possible. To keep the code simple use a static array for
the registered tunnel types, and size such array based on the kernel
config.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/6fd1f9c7651151493ecab174e7b8386a1534170d.1741718157.git.pabeni@redhat.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/udp_tunnel.h   |   4 ++
 net/ipv4/udp_offload.c     | 130 ++++++++++++++++++++++++++++++++++++-
 net/ipv4/udp_tunnel_core.c |   2 +
 3 files changed, 135 insertions(+), 1 deletion(-)

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index eda0f3e2f65fa..a7b230867eb14 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -205,9 +205,11 @@ static inline void udp_tunnel_encap_enable(struct sock *sk)
 
 #if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
 void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add);
+void udp_tunnel_update_gro_rcv(struct sock *sk, bool add);
 #else
 static inline void udp_tunnel_update_gro_lookup(struct net *net,
 						struct sock *sk, bool add) {}
+static inline void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) {}
 #endif
 
 static inline void udp_tunnel_cleanup_gro(struct sock *sk)
@@ -215,6 +217,8 @@ static inline void udp_tunnel_cleanup_gro(struct sock *sk)
 	struct udp_sock *up = udp_sk(sk);
 	struct net *net = sock_net(sk);
 
+	udp_tunnel_update_gro_rcv(sk, false);
+
 	if (!up->tunnel_list.pprev)
 		return;
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index e36d8a234848f..088aa8cb8ac0c 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -15,6 +15,37 @@
 #include <net/udp_tunnel.h>
 
 #if IS_ENABLED(CONFIG_NET_UDP_TUNNEL)
+
+/*
+ * Dummy GRO tunnel callback, exists mainly to avoid dangling/NULL
+ * values for the udp tunnel static call.
+ */
+static struct sk_buff *dummy_gro_rcv(struct sock *sk,
+				     struct list_head *head,
+				     struct sk_buff *skb)
+{
+	NAPI_GRO_CB(skb)->flush = 1;
+	return NULL;
+}
+
+typedef struct sk_buff *(*udp_tunnel_gro_rcv_t)(struct sock *sk,
+						struct list_head *head,
+						struct sk_buff *skb);
+
+struct udp_tunnel_type_entry {
+	udp_tunnel_gro_rcv_t gro_receive;
+	refcount_t count;
+};
+
+#define UDP_MAX_TUNNEL_TYPES (IS_ENABLED(CONFIG_GENEVE) + \
+			      IS_ENABLED(CONFIG_VXLAN) * 2 + \
+			      IS_ENABLED(CONFIG_NET_FOU) * 2)
+
+DEFINE_STATIC_CALL(udp_tunnel_gro_rcv, dummy_gro_rcv);
+static DEFINE_STATIC_KEY_FALSE(udp_tunnel_static_call);
+static struct mutex udp_tunnel_gro_type_lock;
+static struct udp_tunnel_type_entry udp_tunnel_gro_types[UDP_MAX_TUNNEL_TYPES];
+static unsigned int udp_tunnel_gro_type_nr;
 static DEFINE_SPINLOCK(udp_tunnel_gro_lock);
 
 void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add)
@@ -43,6 +74,101 @@ void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add)
 	spin_unlock(&udp_tunnel_gro_lock);
 }
 EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_lookup);
+
+void udp_tunnel_update_gro_rcv(struct sock *sk, bool add)
+{
+	struct udp_tunnel_type_entry *cur = NULL;
+	struct udp_sock *up = udp_sk(sk);
+	int i, old_gro_type_nr;
+
+	if (!up->gro_receive)
+		return;
+
+	mutex_lock(&udp_tunnel_gro_type_lock);
+	for (i = 0; i < udp_tunnel_gro_type_nr; i++)
+		if (udp_tunnel_gro_types[i].gro_receive == up->gro_receive)
+			cur = &udp_tunnel_gro_types[i];
+
+	old_gro_type_nr = udp_tunnel_gro_type_nr;
+	if (add) {
+		/*
+		 * Update the matching entry, if found, or add a new one
+		 * if needed
+		 */
+		if (cur) {
+			refcount_inc(&cur->count);
+			goto out;
+		}
+
+		if (unlikely(udp_tunnel_gro_type_nr == UDP_MAX_TUNNEL_TYPES)) {
+			pr_err_once("Too many UDP tunnel types, please increase UDP_MAX_TUNNEL_TYPES\n");
+			/* Ensure static call will never be enabled */
+			udp_tunnel_gro_type_nr = UDP_MAX_TUNNEL_TYPES + 2;
+			goto out;
+		}
+
+		cur = &udp_tunnel_gro_types[udp_tunnel_gro_type_nr++];
+		refcount_set(&cur->count, 1);
+		cur->gro_receive = up->gro_receive;
+	} else {
+		/*
+		 * The stack cleanups only successfully added tunnel, the
+		 * lookup on removal should never fail.
+		 */
+		if (WARN_ON_ONCE(!cur))
+			goto out;
+
+		if (!refcount_dec_and_test(&cur->count))
+			goto out;
+
+		/* avoid gaps, so that the enable tunnel has always id 0 */
+		*cur = udp_tunnel_gro_types[--udp_tunnel_gro_type_nr];
+	}
+
+	if (udp_tunnel_gro_type_nr == 1) {
+		static_call_update(udp_tunnel_gro_rcv,
+				   udp_tunnel_gro_types[0].gro_receive);
+		static_branch_enable(&udp_tunnel_static_call);
+	} else if (old_gro_type_nr == 1) {
+		static_branch_disable(&udp_tunnel_static_call);
+		static_call_update(udp_tunnel_gro_rcv, dummy_gro_rcv);
+	}
+
+out:
+	mutex_unlock(&udp_tunnel_gro_type_lock);
+}
+EXPORT_SYMBOL_GPL(udp_tunnel_update_gro_rcv);
+
+static void udp_tunnel_gro_init(void)
+{
+	mutex_init(&udp_tunnel_gro_type_lock);
+}
+
+static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk,
+					  struct list_head *head,
+					  struct sk_buff *skb)
+{
+	if (static_branch_likely(&udp_tunnel_static_call)) {
+		if (unlikely(gro_recursion_inc_test(skb))) {
+			NAPI_GRO_CB(skb)->flush |= 1;
+			return NULL;
+		}
+		return static_call(udp_tunnel_gro_rcv)(sk, head, skb);
+	}
+	return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
+}
+
+#else
+
+static void udp_tunnel_gro_init(void) {}
+
+static struct sk_buff *udp_tunnel_gro_rcv(struct sock *sk,
+					  struct list_head *head,
+					  struct sk_buff *skb)
+{
+	return call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
+}
+
 #endif
 
 static struct sk_buff *__skb_udp_tunnel_segment(struct sk_buff *skb,
@@ -654,7 +780,7 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
 
 	skb_gro_pull(skb, sizeof(struct udphdr)); /* pull encapsulating udp header */
 	skb_gro_postpull_rcsum(skb, uh, sizeof(struct udphdr));
-	pp = call_gro_receive_sk(udp_sk(sk)->gro_receive, sk, head, skb);
+	pp = udp_tunnel_gro_rcv(sk, head, skb);
 
 out:
 	skb_gro_flush_final(skb, pp, flush);
@@ -804,5 +930,7 @@ int __init udpv4_offload_init(void)
 			.gro_complete =	udp4_gro_complete,
 		},
 	};
+
+	udp_tunnel_gro_init();
 	return inet_add_offload(&net_hotdata.udpv4_offload, IPPROTO_UDP);
 }
diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index b5695826e57ad..c49fceea83139 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -90,6 +90,8 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_tunnel_encap_enable(sk);
 
+	udp_tunnel_update_gro_rcv(sock->sk, true);
+
 	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sock->sk))
 		udp_tunnel_update_gro_lookup(net, sock->sk, true);
 }

From daa624d3c2ddffdcbad140a9625a4064371db44f Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 22:25:30 +0100
Subject: [PATCH 2245/2753] net: ipv6: fix TCP GSO segmentation with NAT

When updating the source/destination address, the TCP/UDP checksum needs to
be updated as well.

Fixes: bee88cd5bd83 ("net: add support for segmenting TCP fraglist GSO packets")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Link: https://patch.msgid.link/20250311212530.91519-1-nbd@nbd.name
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/tcpv6_offload.c | 21 +++++++++++++++------
 1 file changed, 15 insertions(+), 6 deletions(-)

diff --git a/net/ipv6/tcpv6_offload.c b/net/ipv6/tcpv6_offload.c
index a45bf17cb2a17..ae2da28f9dfb1 100644
--- a/net/ipv6/tcpv6_offload.c
+++ b/net/ipv6/tcpv6_offload.c
@@ -94,14 +94,23 @@ INDIRECT_CALLABLE_SCOPE int tcp6_gro_complete(struct sk_buff *skb, int thoff)
 }
 
 static void __tcpv6_gso_segment_csum(struct sk_buff *seg,
+				     struct in6_addr *oldip,
+				     const struct in6_addr *newip,
 				     __be16 *oldport, __be16 newport)
 {
-	struct tcphdr *th;
+	struct tcphdr *th = tcp_hdr(seg);
+
+	if (!ipv6_addr_equal(oldip, newip)) {
+		inet_proto_csum_replace16(&th->check, seg,
+					  oldip->s6_addr32,
+					  newip->s6_addr32,
+					  true);
+		*oldip = *newip;
+	}
 
 	if (*oldport == newport)
 		return;
 
-	th = tcp_hdr(seg);
 	inet_proto_csum_replace2(&th->check, seg, *oldport, newport, false);
 	*oldport = newport;
 }
@@ -129,10 +138,10 @@ static struct sk_buff *__tcpv6_gso_segment_list_csum(struct sk_buff *segs)
 		th2 = tcp_hdr(seg);
 		iph2 = ipv6_hdr(seg);
 
-		iph2->saddr = iph->saddr;
-		iph2->daddr = iph->daddr;
-		__tcpv6_gso_segment_csum(seg, &th2->source, th->source);
-		__tcpv6_gso_segment_csum(seg, &th2->dest, th->dest);
+		__tcpv6_gso_segment_csum(seg, &iph2->saddr, &iph->saddr,
+					 &th2->source, th->source);
+		__tcpv6_gso_segment_csum(seg, &iph2->daddr, &iph->daddr,
+					 &th2->dest, th->dest);
 	}
 
 	return segs;

From 9740890ee20e01f99ff1dde84c63dcf089fabb98 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 11 Mar 2025 18:03:25 -0700
Subject: [PATCH 2246/2753] ipv6: Fix memleak of nhc_pcpu_rth_output in
 fib_check_nh_v6_gw().

fib_check_nh_v6_gw() expects that fib6_nh_init() cleans up everything
when it fails.

Commit 7dd73168e273 ("ipv6: Always allocate pcpu memory in a fib6_nh")
moved fib_nh_common_init() before alloc_percpu_gfp() within fib6_nh_init()
but forgot to add cleanup for fib6_nh->nh_common.nhc_pcpu_rth_output in
case it fails to allocate fib6_nh->rt6i_pcpu, resulting in memleak.

Let's call fib_nh_common_release() and clear nhc_pcpu_rth_output in the
error path.

Note that we can remove the fib6_nh_release() call in nh_create_ipv6()
later in net-next.git.

Fixes: 7dd73168e273 ("ipv6: Always allocate pcpu memory in a fib6_nh")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250312010333.56001-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/route.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index ef2d23a1e3d53..bc6bcf5d7133e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3644,7 +3644,8 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh,
 		in6_dev_put(idev);
 
 	if (err) {
-		lwtstate_put(fib6_nh->fib_nh_lws);
+		fib_nh_common_release(&fib6_nh->nh_common);
+		fib6_nh->nh_common.nhc_pcpu_rth_output = NULL;
 		fib6_nh->fib_nh_lws = NULL;
 		netdev_put(dev, dev_tracker);
 	}

From 9a81fc3480bf5dbe2bf80e278c440770f6ba2692 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Tue, 11 Mar 2025 18:38:48 -0700
Subject: [PATCH 2247/2753] ipv6: Set errno after ip_fib_metrics_init() in
 ip6_route_info_create().

While creating a new IPv6, we could get a weird -ENOMEM when
RTA_NH_ID is set and either of the conditions below is true:

  1) CONFIG_IPV6_SUBTREES is enabled and rtm_src_len is specified
  2) nexthop_get() fails

e.g.)

  # strace ip -6 route add fe80::dead:beef:dead:beef nhid 1 from ::
  recvmsg(3, {msg_iov=[{iov_base=[...[
    {error=-ENOMEM, msg=[... [...]]},
    [{nla_len=49, nla_type=NLMSGERR_ATTR_MSG}, "Nexthops can not be used with so"...]
  ]], iov_len=32768}], msg_iovlen=1, msg_controllen=0, msg_flags=0}, 0) = 148

Let's set err explicitly after ip_fib_metrics_init() in
ip6_route_info_create().

Fixes: f88d8ea67fbd ("ipv6: Plumb support for nexthop object in a fib6_info")
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20250312013854.61125-1-kuniyu@amazon.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/route.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bc6bcf5d7133e..15ce21afc8c62 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -3803,10 +3803,12 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
 	if (nh) {
 		if (rt->fib6_src.plen) {
 			NL_SET_ERR_MSG(extack, "Nexthops can not be used with source routing");
+			err = -EINVAL;
 			goto out_free;
 		}
 		if (!nexthop_get(nh)) {
 			NL_SET_ERR_MSG(extack, "Nexthop has been deleted");
+			err = -ENOENT;
 			goto out_free;
 		}
 		rt->nh = nh;

From 24faa63bcea88b6f24b0a3a710708505a876f9ba Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 12 Mar 2025 14:34:50 +0800
Subject: [PATCH 2248/2753] net: skbuff: Remove unused skb_add_data()

Since commit a4ea4c477619 ("rxrpc: Don't use a ring buffer for call Tx
queue") this function is not used anymore.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312063450.183652-1-yuehaibing@huawei.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/skbuff.h | 19 -------------------
 1 file changed, 19 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b8a1343d6785c..cd8294cdc2496 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3867,25 +3867,6 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i)
 	__must_check;
 
-static inline int skb_add_data(struct sk_buff *skb,
-			       struct iov_iter *from, int copy)
-{
-	const int off = skb->len;
-
-	if (skb->ip_summed == CHECKSUM_NONE) {
-		__wsum csum = 0;
-		if (csum_and_copy_from_iter_full(skb_put(skb, copy), copy,
-					         &csum, from)) {
-			skb->csum = csum_block_add(skb->csum, csum, off);
-			return 0;
-		}
-	} else if (copy_from_iter_full(skb_put(skb, copy), copy, from))
-		return 0;
-
-	__skb_trim(skb, off);
-	return -EFAULT;
-}
-
 static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
 				    const struct page *page, int off)
 {

From ae2d90355aa5592b0e99c8bbb4c3fa1d8e205f1b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Mar 2025 08:22:47 +0000
Subject: [PATCH 2249/2753] inet: frags: add inet_frag_putn() helper

inet_frag_putn() can release multiple references
in one step.

Use it in inet_frags_free_cb().

Replace inet_frag_put(X) with inet_frag_putn(X, 1)

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250312082250.1803501-2-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/inet_frag.h                 | 4 ++--
 include/net/ipv6_frag.h                 | 3 ++-
 net/ieee802154/6lowpan/reassembly.c     | 7 ++++---
 net/ipv4/inet_fragment.c                | 3 +--
 net/ipv4/ip_fragment.c                  | 2 +-
 net/ipv6/netfilter/nf_conntrack_reasm.c | 3 ++-
 net/ipv6/reassembly.c                   | 4 ++--
 7 files changed, 14 insertions(+), 12 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 5af6eb14c5db1..26687ad0b1414 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -145,9 +145,9 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
 unsigned int inet_frag_rbtree_purge(struct rb_root *root,
 				    enum skb_drop_reason reason);
 
-static inline void inet_frag_put(struct inet_frag_queue *q)
+static inline void inet_frag_putn(struct inet_frag_queue *q, int refs)
 {
-	if (refcount_dec_and_test(&q->refcnt))
+	if (refs && refcount_sub_and_test(refs, &q->refcnt))
 		inet_frag_destroy(q);
 }
 
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 7321ffe3a108c..9d968d7d9fa40 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -66,6 +66,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 {
 	struct net_device *dev = NULL;
 	struct sk_buff *head;
+	int refs = 1;
 
 	rcu_read_lock();
 	/* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */
@@ -109,7 +110,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 	spin_unlock(&fq->q.lock);
 out_rcu_unlock:
 	rcu_read_unlock();
-	inet_frag_put(&fq->q);
+	inet_frag_putn(&fq->q, refs);
 }
 
 /* Check if the upper layer header is truncated in the first fragment. */
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 867d637d86f08..2df1a027e68a1 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -45,6 +45,7 @@ static void lowpan_frag_expire(struct timer_list *t)
 {
 	struct inet_frag_queue *frag = from_timer(frag, t, timer);
 	struct frag_queue *fq;
+	int refs = 1;
 
 	fq = container_of(frag, struct frag_queue, q);
 
@@ -56,7 +57,7 @@ static void lowpan_frag_expire(struct timer_list *t)
 	inet_frag_kill(&fq->q);
 out:
 	spin_unlock(&fq->q.lock);
-	inet_frag_put(&fq->q);
+	inet_frag_putn(&fq->q, refs);
 }
 
 static inline struct lowpan_frag_queue *
@@ -302,13 +303,13 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 
 	fq = fq_find(net, cb, &hdr.source, &hdr.dest);
 	if (fq != NULL) {
-		int ret;
+		int ret, refs = 1;
 
 		spin_lock(&fq->q.lock);
 		ret = lowpan_frag_queue(fq, skb, frag_type);
 		spin_unlock(&fq->q.lock);
 
-		inet_frag_put(&fq->q);
+		inet_frag_putn(&fq->q, refs);
 		return ret;
 	}
 
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index d179a2c842227..efc4cbee04c27 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -145,8 +145,7 @@ static void inet_frags_free_cb(void *ptr, void *arg)
 	}
 	spin_unlock_bh(&fq->lock);
 
-	if (refcount_sub_and_test(count, &fq->refcnt))
-		inet_frag_destroy(fq);
+	inet_frag_putn(fq, count);
 }
 
 static LLIST_HEAD(fqdir_free_list);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 7a435746a22de..474a26191c898 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -112,7 +112,7 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 
 static void ipq_put(struct ipq *ipq)
 {
-	inet_frag_put(&ipq->q);
+	inet_frag_putn(&ipq->q, 1);
 }
 
 /* Kill ipq entry. It is not destroyed immediately,
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 4120e67a8ce6b..fcf969f9fe2ab 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -447,6 +447,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
 	struct ipv6hdr *hdr;
+	int refs = 1;
 	u8 prevhdr;
 
 	/* Jumbo payload inhibits frag. header */
@@ -489,7 +490,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	}
 
 	spin_unlock_bh(&fq->q.lock);
-	inet_frag_put(&fq->q);
+	inet_frag_putn(&fq->q, refs);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_ct_frag6_gather);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index a48be617a8ab5..5d56a8e5166bc 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -380,7 +380,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		u32 prob_offset = 0;
-		int ret;
+		int ret, refs = 1;
 
 		spin_lock(&fq->q.lock);
 
@@ -389,7 +389,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 				     &prob_offset);
 
 		spin_unlock(&fq->q.lock);
-		inet_frag_put(&fq->q);
+		inet_frag_putn(&fq->q, refs);
 		if (prob_offset) {
 			__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
 					IPSTATS_MIB_INHDRERRORS);

From a2fb987c0ecf0498cc17056339cb11d128c46ab7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Mar 2025 08:22:48 +0000
Subject: [PATCH 2250/2753] ipv4: frags: remove ipq_put()

Replace ipq_put() with inet_frag_putn()

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250312082250.1803501-3-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv4/ip_fragment.c | 15 ++++-----------
 1 file changed, 4 insertions(+), 11 deletions(-)

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 474a26191c898..ee953be49b34d 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -107,14 +107,6 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 		inet_putpeer(qp->peer);
 }
 
-
-/* Destruction primitives. */
-
-static void ipq_put(struct ipq *ipq)
-{
-	inet_frag_putn(&ipq->q, 1);
-}
-
 /* Kill ipq entry. It is not destroyed immediately,
  * because caller (and someone more) holds reference count.
  */
@@ -143,6 +135,7 @@ static void ip_expire(struct timer_list *t)
 	struct sk_buff *head = NULL;
 	struct net *net;
 	struct ipq *qp;
+	int refs = 1;
 
 	qp = container_of(frag, struct ipq, q);
 	net = qp->q.fqdir->net;
@@ -202,7 +195,7 @@ static void ip_expire(struct timer_list *t)
 out_rcu_unlock:
 	rcu_read_unlock();
 	kfree_skb_reason(head, reason);
-	ipq_put(qp);
+	inet_frag_putn(&qp->q, refs);
 }
 
 /* Find the correct entry in the "incomplete datagrams" queue for
@@ -498,14 +491,14 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	/* Lookup (or create) queue header */
 	qp = ip_find(net, ip_hdr(skb), user, vif);
 	if (qp) {
-		int ret;
+		int ret, refs = 1;
 
 		spin_lock(&qp->q.lock);
 
 		ret = ip_frag_queue(qp, skb);
 
 		spin_unlock(&qp->q.lock);
-		ipq_put(qp);
+		inet_frag_putn(&qp->q, refs);
 		return ret;
 	}
 

From eb0dfc0ef195a04e519b15d73cf25d8c25ee8df7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Mar 2025 08:22:49 +0000
Subject: [PATCH 2251/2753] inet: frags: change inet_frag_kill() to defer
 refcount updates

In the following patch, we no longer assume inet_frag_kill()
callers own a reference.

Consuming two refcounts from inet_frag_kill() would lead in UAF.

Propagate the pointer to the refs that will be consumed later
by the final inet_frag_putn() call.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250312082250.1803501-4-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/inet_frag.h                 |  2 +-
 include/net/ipv6_frag.h                 |  2 +-
 net/ieee802154/6lowpan/reassembly.c     | 17 ++++++++------
 net/ipv4/inet_fragment.c                | 12 +++++-----
 net/ipv4/ip_fragment.c                  | 30 ++++++++++---------------
 net/ipv6/netfilter/nf_conntrack_reasm.c | 21 +++++++++--------
 net/ipv6/reassembly.c                   | 18 ++++++++-------
 7 files changed, 53 insertions(+), 49 deletions(-)

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 26687ad0b1414..0eccd9c3a883f 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -137,7 +137,7 @@ static inline void fqdir_pre_exit(struct fqdir *fqdir)
 }
 void fqdir_exit(struct fqdir *fqdir);
 
-void inet_frag_kill(struct inet_frag_queue *q);
+void inet_frag_kill(struct inet_frag_queue *q, int *refs);
 void inet_frag_destroy(struct inet_frag_queue *q);
 struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key);
 
diff --git a/include/net/ipv6_frag.h b/include/net/ipv6_frag.h
index 9d968d7d9fa40..38ef66826939e 100644
--- a/include/net/ipv6_frag.h
+++ b/include/net/ipv6_frag.h
@@ -78,7 +78,7 @@ ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq)
 		goto out;
 
 	fq->q.flags |= INET_FRAG_DROP;
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, &refs);
 
 	dev = dev_get_by_index_rcu(net, fq->iif);
 	if (!dev)
diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index 2df1a027e68a1..c5f86cff06ee7 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -31,7 +31,8 @@ static const char lowpan_frags_cache_name[] = "lowpan-frags";
 static struct inet_frags lowpan_frags;
 
 static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb,
-			     struct sk_buff *prev,  struct net_device *ldev);
+			     struct sk_buff *prev, struct net_device *ldev,
+			     int *refs);
 
 static void lowpan_frag_init(struct inet_frag_queue *q, const void *a)
 {
@@ -54,7 +55,7 @@ static void lowpan_frag_expire(struct timer_list *t)
 	if (fq->q.flags & INET_FRAG_COMPLETE)
 		goto out;
 
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, &refs);
 out:
 	spin_unlock(&fq->q.lock);
 	inet_frag_putn(&fq->q, refs);
@@ -83,7 +84,8 @@ fq_find(struct net *net, const struct lowpan_802154_cb *cb,
 }
 
 static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
-			     struct sk_buff *skb, u8 frag_type)
+			     struct sk_buff *skb, u8 frag_type,
+			     int *refs)
 {
 	struct sk_buff *prev_tail;
 	struct net_device *ldev;
@@ -144,7 +146,7 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		res = lowpan_frag_reasm(fq, skb, prev_tail, ldev);
+		res = lowpan_frag_reasm(fq, skb, prev_tail, ldev, refs);
 		skb->_skb_refdst = orefdst;
 		return res;
 	}
@@ -163,11 +165,12 @@ static int lowpan_frag_queue(struct lowpan_frag_queue *fq,
  *	the last and the first frames arrived and all the bits are here.
  */
 static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *skb,
-			     struct sk_buff *prev_tail, struct net_device *ldev)
+			     struct sk_buff *prev_tail, struct net_device *ldev,
+			     int *refs)
 {
 	void *reasm_data;
 
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 
 	reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail);
 	if (!reasm_data)
@@ -306,7 +309,7 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 		int ret, refs = 1;
 
 		spin_lock(&fq->q.lock);
-		ret = lowpan_frag_queue(fq, skb, frag_type);
+		ret = lowpan_frag_queue(fq, skb, frag_type, &refs);
 		spin_unlock(&fq->q.lock);
 
 		inet_frag_putn(&fq->q, refs);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index efc4cbee04c27..5eb1860500138 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -225,10 +225,10 @@ void fqdir_exit(struct fqdir *fqdir)
 }
 EXPORT_SYMBOL(fqdir_exit);
 
-void inet_frag_kill(struct inet_frag_queue *fq)
+void inet_frag_kill(struct inet_frag_queue *fq, int *refs)
 {
 	if (del_timer(&fq->timer))
-		refcount_dec(&fq->refcnt);
+		(*refs)++;
 
 	if (!(fq->flags & INET_FRAG_COMPLETE)) {
 		struct fqdir *fqdir = fq->fqdir;
@@ -243,7 +243,7 @@ void inet_frag_kill(struct inet_frag_queue *fq)
 		if (!READ_ONCE(fqdir->dead)) {
 			rhashtable_remove_fast(&fqdir->rhashtable, &fq->node,
 					       fqdir->f->rhash_params);
-			refcount_dec(&fq->refcnt);
+			(*refs)++;
 		} else {
 			fq->flags |= INET_FRAG_HASH_DEAD;
 		}
@@ -349,9 +349,11 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
 	*prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key,
 						 &q->node, f->rhash_params);
 	if (*prev) {
+		int refs = 2;
+
 		q->flags |= INET_FRAG_COMPLETE;
-		inet_frag_kill(q);
-		inet_frag_destroy(q);
+		inet_frag_kill(q, &refs);
+		inet_frag_putn(q, refs);
 		return NULL;
 	}
 	return q;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index ee953be49b34d..c5f3c810706fb 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -76,7 +76,8 @@ static u8 ip4_frag_ecn(u8 tos)
 static struct inet_frags ip4_frags;
 
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
-			 struct sk_buff *prev_tail, struct net_device *dev);
+			 struct sk_buff *prev_tail, struct net_device *dev,
+			 int *refs);
 
 
 static void ip4_frag_init(struct inet_frag_queue *q, const void *a)
@@ -107,14 +108,6 @@ static void ip4_frag_free(struct inet_frag_queue *q)
 		inet_putpeer(qp->peer);
 }
 
-/* Kill ipq entry. It is not destroyed immediately,
- * because caller (and someone more) holds reference count.
- */
-static void ipq_kill(struct ipq *ipq)
-{
-	inet_frag_kill(&ipq->q);
-}
-
 static bool frag_expire_skip_icmp(u32 user)
 {
 	return user == IP_DEFRAG_AF_PACKET ||
@@ -152,7 +145,7 @@ static void ip_expire(struct timer_list *t)
 		goto out;
 
 	qp->q.flags |= INET_FRAG_DROP;
-	ipq_kill(qp);
+	inet_frag_kill(&qp->q, &refs);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMTIMEOUT);
 
@@ -271,7 +264,7 @@ static int ip_frag_reinit(struct ipq *qp)
 }
 
 /* Add new segment to existing queue. */
-static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
+static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb, int *refs)
 {
 	struct net *net = qp->q.fqdir->net;
 	int ihl, end, flags, offset;
@@ -291,7 +284,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	if (!(IPCB(skb)->flags & IPSKB_FRAG_COMPLETE) &&
 	    unlikely(ip_frag_too_far(qp)) &&
 	    unlikely(err = ip_frag_reinit(qp))) {
-		ipq_kill(qp);
+		inet_frag_kill(&qp->q, refs);
 		goto err;
 	}
 
@@ -375,10 +368,10 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip_frag_reasm(qp, skb, prev_tail, dev);
+		err = ip_frag_reasm(qp, skb, prev_tail, dev, refs);
 		skb->_skb_refdst = orefdst;
 		if (err)
-			inet_frag_kill(&qp->q);
+			inet_frag_kill(&qp->q, refs);
 		return err;
 	}
 
@@ -395,7 +388,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
 	err = -EINVAL;
 	__IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS);
 discard_qp:
-	inet_frag_kill(&qp->q);
+	inet_frag_kill(&qp->q, refs);
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 err:
 	kfree_skb_reason(skb, reason);
@@ -409,7 +402,8 @@ static bool ip_frag_coalesce_ok(const struct ipq *qp)
 
 /* Build a new IP datagram from all its fragments. */
 static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
-			 struct sk_buff *prev_tail, struct net_device *dev)
+			 struct sk_buff *prev_tail, struct net_device *dev,
+			 int *refs)
 {
 	struct net *net = qp->q.fqdir->net;
 	struct iphdr *iph;
@@ -417,7 +411,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb,
 	int len, err;
 	u8 ecn;
 
-	ipq_kill(qp);
+	inet_frag_kill(&qp->q, refs);
 
 	ecn = ip_frag_ecn_table[qp->ecn];
 	if (unlikely(ecn == 0xff)) {
@@ -495,7 +489,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 
 		spin_lock(&qp->q.lock);
 
-		ret = ip_frag_queue(qp, skb);
+		ret = ip_frag_queue(qp, skb, &refs);
 
 		spin_unlock(&qp->q.lock);
 		inet_frag_putn(&qp->q, refs);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index fcf969f9fe2ab..f33acb730dc58 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -123,7 +123,8 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
 #endif
 
 static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			     struct sk_buff *prev_tail, struct net_device *dev);
+			     struct sk_buff *prev_tail, struct net_device *dev,
+			     int *refs);
 
 static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 {
@@ -167,7 +168,8 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
 
 
 static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
-			     const struct frag_hdr *fhdr, int nhoff)
+			     const struct frag_hdr *fhdr, int nhoff,
+			     int *refs)
 {
 	unsigned int payload_len;
 	struct net_device *dev;
@@ -221,7 +223,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 			 * this case. -DaveM
 			 */
 			pr_debug("end of fragment not rounded to 8 bytes.\n");
-			inet_frag_kill(&fq->q);
+			inet_frag_kill(&fq->q, refs);
 			return -EPROTO;
 		}
 		if (end > fq->q.len) {
@@ -287,7 +289,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = nf_ct_frag6_reasm(fq, skb, prev, dev);
+		err = nf_ct_frag6_reasm(fq, skb, prev, dev, refs);
 		skb->_skb_refdst = orefdst;
 
 		/* After queue has assumed skb ownership, only 0 or
@@ -301,7 +303,7 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
 	return -EINPROGRESS;
 
 insert_error:
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 err:
 	skb_dst_drop(skb);
 	return -EINVAL;
@@ -315,13 +317,14 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
  *	the last and the first frames arrived and all the bits are here.
  */
 static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			     struct sk_buff *prev_tail, struct net_device *dev)
+			     struct sk_buff *prev_tail, struct net_device *dev,
+			     int *refs)
 {
 	void *reasm_data;
 	int payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -372,7 +375,7 @@ static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	return 0;
 
 err:
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 	return -EINVAL;
 }
 
@@ -483,7 +486,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 
 	spin_lock_bh(&fq->q.lock);
 
-	ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff);
+	ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff, &refs);
 	if (ret == -EPROTO) {
 		skb->transport_header = savethdr;
 		ret = 0;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 5d56a8e5166bc..7560380bd5871 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -68,7 +68,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
 static struct inet_frags ip6_frags;
 
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			  struct sk_buff *prev_tail, struct net_device *dev);
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs);
 
 static void ip6_frag_expire(struct timer_list *t)
 {
@@ -105,7 +106,7 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif)
 
 static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 			  struct frag_hdr *fhdr, int nhoff,
-			  u32 *prob_offset)
+			  u32 *prob_offset, int *refs)
 {
 	struct net *net = dev_net(skb_dst(skb)->dev);
 	int offset, end, fragsize;
@@ -220,7 +221,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 		unsigned long orefdst = skb->_skb_refdst;
 
 		skb->_skb_refdst = 0UL;
-		err = ip6_frag_reasm(fq, skb, prev_tail, dev);
+		err = ip6_frag_reasm(fq, skb, prev_tail, dev, refs);
 		skb->_skb_refdst = orefdst;
 		return err;
 	}
@@ -238,7 +239,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASM_OVERLAPS);
 discard_fq:
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
 			IPSTATS_MIB_REASMFAILS);
 err:
@@ -254,7 +255,8 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
  *	the last and the first frames arrived and all the bits are here.
  */
 static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
-			  struct sk_buff *prev_tail, struct net_device *dev)
+			  struct sk_buff *prev_tail, struct net_device *dev,
+			  int *refs)
 {
 	struct net *net = fq->q.fqdir->net;
 	unsigned int nhoff;
@@ -262,7 +264,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	int payload_len;
 	u8 ecn;
 
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 
 	ecn = ip_frag_ecn_table[fq->ecn];
 	if (unlikely(ecn == 0xff))
@@ -320,7 +322,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	rcu_read_lock();
 	__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
 	rcu_read_unlock();
-	inet_frag_kill(&fq->q);
+	inet_frag_kill(&fq->q, refs);
 	return -1;
 }
 
@@ -386,7 +388,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 
 		fq->iif = iif;
 		ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff,
-				     &prob_offset);
+				     &prob_offset, &refs);
 
 		spin_unlock(&fq->q.lock);
 		inet_frag_putn(&fq->q, refs);

From ca0359df45a55a9eb4d6dc09a481064abf78320f Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Mar 2025 08:22:50 +0000
Subject: [PATCH 2252/2753] inet: frags: save a pair of atomic operations in
 reassembly

As mentioned in commit 648700f76b03 ("inet: frags:
use rhashtables for reassembly units"):

  A followup patch will even remove the refcount hold/release
  left from prior implementation and save a couple of atomic
  operations.

This patch implements this idea, seven years later.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250312082250.1803501-5-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ieee802154/6lowpan/reassembly.c     |  5 ++++-
 net/ipv4/inet_fragment.c                | 18 ++++++++----------
 net/ipv4/ip_fragment.c                  |  5 ++++-
 net/ipv6/netfilter/nf_conntrack_reasm.c |  5 ++++-
 net/ipv6/reassembly.c                   |  9 ++++-----
 5 files changed, 24 insertions(+), 18 deletions(-)

diff --git a/net/ieee802154/6lowpan/reassembly.c b/net/ieee802154/6lowpan/reassembly.c
index c5f86cff06ee7..d4b983d170382 100644
--- a/net/ieee802154/6lowpan/reassembly.c
+++ b/net/ieee802154/6lowpan/reassembly.c
@@ -304,17 +304,20 @@ int lowpan_frag_rcv(struct sk_buff *skb, u8 frag_type)
 		goto err;
 	}
 
+	rcu_read_lock();
 	fq = fq_find(net, cb, &hdr.source, &hdr.dest);
 	if (fq != NULL) {
-		int ret, refs = 1;
+		int ret, refs = 0;
 
 		spin_lock(&fq->q.lock);
 		ret = lowpan_frag_queue(fq, skb, frag_type, &refs);
 		spin_unlock(&fq->q.lock);
 
+		rcu_read_unlock();
 		inet_frag_putn(&fq->q, refs);
 		return ret;
 	}
+	rcu_read_unlock();
 
 err:
 	kfree_skb(skb);
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5eb1860500138..19fae4811ab28 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -327,7 +327,8 @@ static struct inet_frag_queue *inet_frag_alloc(struct fqdir *fqdir,
 
 	timer_setup(&q->timer, f->frag_expire, 0);
 	spin_lock_init(&q->lock);
-	refcount_set(&q->refcnt, 3);
+	/* One reference for the timer, one for the hash table. */
+	refcount_set(&q->refcnt, 2);
 
 	return q;
 }
@@ -349,7 +350,11 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
 	*prev = rhashtable_lookup_get_insert_key(&fqdir->rhashtable, &q->key,
 						 &q->node, f->rhash_params);
 	if (*prev) {
-		int refs = 2;
+		/* We could not insert in the hash table,
+		 * we need to cancel what inet_frag_alloc()
+		 * anticipated.
+		 */
+		int refs = 1;
 
 		q->flags |= INET_FRAG_COMPLETE;
 		inet_frag_kill(q, &refs);
@@ -359,7 +364,6 @@ static struct inet_frag_queue *inet_frag_create(struct fqdir *fqdir,
 	return q;
 }
 
-/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */
 struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
 {
 	/* This pairs with WRITE_ONCE() in fqdir_pre_exit(). */
@@ -369,17 +373,11 @@ struct inet_frag_queue *inet_frag_find(struct fqdir *fqdir, void *key)
 	if (!high_thresh || frag_mem_limit(fqdir) > high_thresh)
 		return NULL;
 
-	rcu_read_lock();
-
 	prev = rhashtable_lookup(&fqdir->rhashtable, key, fqdir->f->rhash_params);
 	if (!prev)
 		fq = inet_frag_create(fqdir, key, &prev);
-	if (!IS_ERR_OR_NULL(prev)) {
+	if (!IS_ERR_OR_NULL(prev))
 		fq = prev;
-		if (!refcount_inc_not_zero(&fq->refcnt))
-			fq = NULL;
-	}
-	rcu_read_unlock();
 	return fq;
 }
 EXPORT_SYMBOL(inet_frag_find);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index c5f3c810706fb..77f395b28ec74 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -483,18 +483,21 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMREQDS);
 
 	/* Lookup (or create) queue header */
+	rcu_read_lock();
 	qp = ip_find(net, ip_hdr(skb), user, vif);
 	if (qp) {
-		int ret, refs = 1;
+		int ret, refs = 0;
 
 		spin_lock(&qp->q.lock);
 
 		ret = ip_frag_queue(qp, skb, &refs);
 
 		spin_unlock(&qp->q.lock);
+		rcu_read_unlock();
 		inet_frag_putn(&qp->q, refs);
 		return ret;
 	}
+	rcu_read_unlock();
 
 	__IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index f33acb730dc58..d6bd8f7079bb7 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -450,7 +450,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	struct frag_hdr *fhdr;
 	struct frag_queue *fq;
 	struct ipv6hdr *hdr;
-	int refs = 1;
+	int refs = 0;
 	u8 prevhdr;
 
 	/* Jumbo payload inhibits frag. header */
@@ -477,9 +477,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	hdr = ipv6_hdr(skb);
 	fhdr = (struct frag_hdr *)skb_transport_header(skb);
 
+	rcu_read_lock();
 	fq = fq_find(net, fhdr->identification, user, hdr,
 		     skb->dev ? skb->dev->ifindex : 0);
 	if (fq == NULL) {
+		rcu_read_unlock();
 		pr_debug("Can't find and can't create new queue\n");
 		return -ENOMEM;
 	}
@@ -493,6 +495,7 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user)
 	}
 
 	spin_unlock_bh(&fq->q.lock);
+	rcu_read_unlock();
 	inet_frag_putn(&fq->q, refs);
 	return ret;
 }
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 7560380bd5871..49740898bc137 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -305,9 +305,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 	skb_postpush_rcsum(skb, skb_network_header(skb),
 			   skb_network_header_len(skb));
 
-	rcu_read_lock();
 	__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMOKS);
-	rcu_read_unlock();
 	fq->q.rb_fragments = RB_ROOT;
 	fq->q.fragments_tail = NULL;
 	fq->q.last_run_head = NULL;
@@ -319,9 +317,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb,
 out_oom:
 	net_dbg_ratelimited("ip6_frag_reasm: no memory for reassembly\n");
 out_fail:
-	rcu_read_lock();
 	__IP6_INC_STATS(net, __in6_dev_stats_get(dev, skb), IPSTATS_MIB_REASMFAILS);
-	rcu_read_unlock();
 	inet_frag_kill(&fq->q, refs);
 	return -1;
 }
@@ -379,10 +375,11 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 	}
 
 	iif = skb->dev ? skb->dev->ifindex : 0;
+	rcu_read_lock();
 	fq = fq_find(net, fhdr->identification, hdr, iif);
 	if (fq) {
 		u32 prob_offset = 0;
-		int ret, refs = 1;
+		int ret, refs = 0;
 
 		spin_lock(&fq->q.lock);
 
@@ -391,6 +388,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 				     &prob_offset, &refs);
 
 		spin_unlock(&fq->q.lock);
+		rcu_read_unlock();
 		inet_frag_putn(&fq->q, refs);
 		if (prob_offset) {
 			__IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev),
@@ -400,6 +398,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb)
 		}
 		return ret;
 	}
+	rcu_read_unlock();
 
 	__IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS);
 	kfree_skb(skb);

From 15492700ac41459b54a6683490adcee350ab11e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 12 Mar 2025 08:39:07 +0000
Subject: [PATCH 2253/2753] tcp: cache RTAX_QUICKACK metric in a hot cache line

tcp_in_quickack_mode() is called from input path for small packets.

It calls __sk_dst_get() which reads sk->sk_dst_cache which has been
put in sock_read_tx group (for good reasons).

Then dst_metric(dst, RTAX_QUICKACK) also needs extra cache line misses.

Cache RTAX_QUICKACK in icsk->icsk_ack.dst_quick_ack to no longer pull
these cache lines for the cases a delayed ACK is scheduled.

After this patch TCP receive path does not longer access sock_read_tx
group.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250312083907.1931644-1-edumazet@google.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/inet_connection_sock.h | 3 ++-
 net/core/sock.c                    | 6 +++++-
 net/ipv4/tcp_input.c               | 3 +--
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index d9978ffacc970..f736d3097e43d 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -117,7 +117,8 @@ struct inet_connection_sock {
 		#define ATO_BITS 8
 		__u32		  ato:ATO_BITS,	 /* Predicted tick of soft clock	   */
 				  lrcv_flowlabel:20, /* last received ipv6 flowlabel	   */
-				  unused:4;
+				  dst_quick_ack:1, /* cache dst RTAX_QUICKACK		   */
+				  unused:3;
 		unsigned long	  timeout;	 /* Currently scheduled timeout		   */
 		__u32		  lrcvtime;	 /* timestamp of last received data packet */
 		__u16		  last_seg_size; /* Size of last incoming segment	   */
diff --git a/net/core/sock.c b/net/core/sock.c
index a0598518ce898..323892066def8 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2565,8 +2565,12 @@ void sk_setup_caps(struct sock *sk, struct dst_entry *dst)
 	u32 max_segs = 1;
 
 	sk->sk_route_caps = dst->dev->features;
-	if (sk_is_tcp(sk))
+	if (sk_is_tcp(sk)) {
+		struct inet_connection_sock *icsk = inet_csk(sk);
+
 		sk->sk_route_caps |= NETIF_F_GSO;
+		icsk->icsk_ack.dst_quick_ack = dst_metric(dst, RTAX_QUICKACK);
+	}
 	if (sk->sk_route_caps & NETIF_F_GSO)
 		sk->sk_route_caps |= NETIF_F_GSO_SOFTWARE;
 	if (unlikely(sk->sk_gso_disabled))
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5c270cf966784..72382ee4456db 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -334,9 +334,8 @@ static void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks)
 static bool tcp_in_quickack_mode(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
-	const struct dst_entry *dst = __sk_dst_get(sk);
 
-	return (dst && dst_metric(dst, RTAX_QUICKACK)) ||
+	return icsk->icsk_ack.dst_quick_ack ||
 		(icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk));
 }
 

From e6f98260d76c9204cf799b281211f4a62f932678 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 18 Mar 2025 10:29:43 +0100
Subject: [PATCH 2254/2753] wifi: iwlwifi: remove a buggy else statement in
 op_mode selection

This led to weird behavior. The next debug print was not printed.

Fixes: d1e879ec600f9 ("wifi: iwlwifi: add iwlmld sub-driver")
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250318103019.bf54d0474909.Icfb129d4cf13b42b13e2ac4aa1bd171ef46bf561@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index dcf07ac042f74..15d2211e565c3 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
 /*
- * Copyright (C) 2005-2014, 2018-2024 Intel Corporation
+ * Copyright (C) 2005-2014, 2018-2025 Intel Corporation
  * Copyright (C) 2013-2015 Intel Mobile Communications GmbH
  * Copyright (C) 2016-2017 Intel Deutschland GmbH
  */
@@ -1732,7 +1732,6 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 #if IS_ENABLED(CONFIG_IWLMLD)
 	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION)
 		op = &iwlwifi_opmode_table[MLD_OP_MODE];
-	else
 #else
 	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION) {
 		IWL_ERR(drv,

From db9b4b8311c19410ea7b064902b16c371f0fff83 Mon Sep 17 00:00:00 2001
From: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Date: Tue, 18 Mar 2025 10:29:44 +0100
Subject: [PATCH 2255/2753] wifi: iwlwifi: do not use iwlmld for non-wifi7
 devices

Roll-back to use iwlmvm for those devices. iwlmld will support wifi7
capable devices only. The firmware for the non-wifi7 capable will soon
be frozen and we don't want iwlmld to have to support devices that will
require the old APIs.

Fixes: d1e879ec600f9 ("wifi: iwlwifi: add iwlmld sub-driver")
Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Link: https://patch.msgid.link/20250318103019.df6df96df826.I0020ca9f6c6c928caa78721666df131a692c6186@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/intel/iwlwifi/iwl-drv.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
index 15d2211e565c3..d36837501e08a 100644
--- a/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
+++ b/drivers/net/wireless/intel/iwlwifi/iwl-drv.c
@@ -174,6 +174,11 @@ static inline char iwl_drv_get_step(int step)
 	return 'a' + step;
 }
 
+static bool iwl_drv_is_wifi7_supported(struct iwl_trans *trans)
+{
+	return CSR_HW_RFID_TYPE(trans->hw_rf_id) >= IWL_CFG_RF_TYPE_FM;
+}
+
 const char *iwl_drv_get_fwname_pre(struct iwl_trans *trans, char *buf)
 {
 	char mac_step, rf_step;
@@ -1730,10 +1735,12 @@ static void iwl_req_fw_callback(const struct firmware *ucode_raw, void *context)
 	}
 
 #if IS_ENABLED(CONFIG_IWLMLD)
-	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION)
+	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION &&
+	    iwl_drv_is_wifi7_supported(drv->trans))
 		op = &iwlwifi_opmode_table[MLD_OP_MODE];
 #else
-	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION) {
+	if (pieces->major >= IWL_MLD_SUPPORTED_FW_VERSION &&
+	    iwl_drv_is_wifi7_supported(drv->trans)) {
 		IWL_ERR(drv,
 			"IWLMLD needs to be compiled to support this firmware\n");
 		mutex_unlock(&iwlwifi_opmode_table_mtx);

From e74c0a7875cfec27c25f582f001cc4625a0f8c07 Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Thu, 15 Aug 2024 13:00:23 -0600
Subject: [PATCH 2256/2753] wifi: iwlwifi: dvm: Avoid
 -Wflex-array-member-not-at-end warnings

-Wflex-array-member-not-at-end was introduced in GCC-14, and we are
getting ready to enable it, globally.

So, in order to avoid ending up with a flexible-array member in the
middle of multiple other structs, we use the `__struct_group()`
helper to create a new tagged `struct iwl_tx_cmd_hdr`. This structure
groups together all the members of the flexible `struct iwl_tx_cmd`
except the flexible array.

As a result, the array is effectively separated from the rest of the
members without modifying the memory layout of the flexible structure.
We then change the type of the middle struct members currently causing
trouble from `struct iwl_tx_cmd` to `struct iwl_tx_cmd_hdr`.

We also want to ensure that when new members need to be added to the
flexible structure, they are always included within the newly created
tagged struct. For this, we use `static_assert()`. This ensures that the
memory layout for both the flexible structure and the new tagged struct
is the same after any changes.

This approach avoids having to implement `struct iwl_tx_cmd_hdr`
as a completely separate structure, thus preventing having to maintain
two independent but basically identical structures, closing the door
to potential bugs in the future.

So, with these changes, fix the following warnings:

drivers/net/wireless/intel/iwlwifi/dvm/commands.h:2315:27: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]
drivers/net/wireless/intel/iwlwifi/dvm/commands.h:2426:27: warning: structure containing a flexible array member is not at the end of another structure [-Wflex-array-member-not-at-end]

Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Acked-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/Zr5QR03+wyw571zd@elsanto
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 .../net/wireless/intel/iwlwifi/dvm/commands.h | 154 +++++++++---------
 1 file changed, 78 insertions(+), 76 deletions(-)

diff --git a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h
index 3f49c0bccb286..96ea6c8dfc890 100644
--- a/drivers/net/wireless/intel/iwlwifi/dvm/commands.h
+++ b/drivers/net/wireless/intel/iwlwifi/dvm/commands.h
@@ -1180,85 +1180,87 @@ struct iwl_dram_scratch {
 } __packed;
 
 struct iwl_tx_cmd {
-	/*
-	 * MPDU byte count:
-	 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
-	 * + 8 byte IV for CCM or TKIP (not used for WEP)
-	 * + Data payload
-	 * + 8-byte MIC (not used for CCM/WEP)
-	 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
-	 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
-	 * Range: 14-2342 bytes.
-	 */
-	__le16 len;
-
-	/*
-	 * MPDU or MSDU byte count for next frame.
-	 * Used for fragmentation and bursting, but not 11n aggregation.
-	 * Same as "len", but for next frame.  Set to 0 if not applicable.
-	 */
-	__le16 next_frame_len;
-
-	__le32 tx_flags;	/* TX_CMD_FLG_* */
-
-	/* uCode may modify this field of the Tx command (in host DRAM!).
-	 * Driver must also set dram_lsb_ptr and dram_msb_ptr in this cmd. */
-	struct iwl_dram_scratch scratch;
-
-	/* Rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is cleared. */
-	__le32 rate_n_flags;	/* RATE_MCS_* */
-
-	/* Index of destination station in uCode's station table */
-	u8 sta_id;
-
-	/* Type of security encryption:  CCM or TKIP */
-	u8 sec_ctl;		/* TX_CMD_SEC_* */
-
-	/*
-	 * Index into rate table (see REPLY_TX_LINK_QUALITY_CMD) for initial
-	 * Tx attempt, if TX_CMD_FLG_STA_RATE_MSK is set.  Normally "0" for
-	 * data frames, this field may be used to selectively reduce initial
-	 * rate (via non-0 value) for special frames (e.g. management), while
-	 * still supporting rate scaling for all frames.
-	 */
-	u8 initial_rate_index;
-	u8 reserved;
-	u8 key[16];
-	__le16 next_frame_flags;
-	__le16 reserved2;
-	union {
-		__le32 life_time;
-		__le32 attempt;
-	} stop_time;
-
-	/* Host DRAM physical address pointer to "scratch" in this command.
-	 * Must be dword aligned.  "0" in dram_lsb_ptr disables usage. */
-	__le32 dram_lsb_ptr;
-	u8 dram_msb_ptr;
-
-	u8 rts_retry_limit;	/*byte 50 */
-	u8 data_retry_limit;	/*byte 51 */
-	u8 tid_tspec;
-	union {
-		__le16 pm_frame_timeout;
-		__le16 attempt_duration;
-	} timeout;
-
-	/*
-	 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
-	 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
-	 */
-	__le16 driver_txop;
-
+	/* New members MUST be added within the __struct_group() macro below. */
+	__struct_group(iwl_tx_cmd_hdr, __hdr, __packed,
+		/*
+		 * MPDU byte count:
+		 * MAC header (24/26/30/32 bytes) + 2 bytes pad if 26/30 header size,
+		 * + 8 byte IV for CCM or TKIP (not used for WEP)
+		 * + Data payload
+		 * + 8-byte MIC (not used for CCM/WEP)
+		 * NOTE:  Does not include Tx command bytes, post-MAC pad bytes,
+		 *        MIC (CCM) 8 bytes, ICV (WEP/TKIP/CKIP) 4 bytes, CRC 4 bytes.i
+		 * Range: 14-2342 bytes.
+		 */
+		__le16 len;
+
+		/*
+		 * MPDU or MSDU byte count for next frame.
+		 * Used for fragmentation and bursting, but not 11n aggregation.
+		 * Same as "len", but for next frame.  Set to 0 if not applicable.
+		 */
+		__le16 next_frame_len;
+
+		__le32 tx_flags;	/* TX_CMD_FLG_* */
+
+		/* uCode may modify this field of the Tx command (in host DRAM!).
+		 * Driver must also set dram_lsb_ptr and dram_msb_ptr in this cmd. */
+		struct iwl_dram_scratch scratch;
+
+		/* Rate for *all* Tx attempts, if TX_CMD_FLG_STA_RATE_MSK is cleared. */
+		__le32 rate_n_flags;	/* RATE_MCS_* */
+
+		/* Index of destination station in uCode's station table */
+		u8 sta_id;
+
+		/* Type of security encryption:  CCM or TKIP */
+		u8 sec_ctl;		/* TX_CMD_SEC_* */
+
+		/*
+		 * Index into rate table (see REPLY_TX_LINK_QUALITY_CMD) for initial
+		 * Tx attempt, if TX_CMD_FLG_STA_RATE_MSK is set.  Normally "0" for
+		 * data frames, this field may be used to selectively reduce initial
+		 * rate (via non-0 value) for special frames (e.g. management), while
+		 * still supporting rate scaling for all frames.
+		 */
+		u8 initial_rate_index;
+		u8 reserved;
+		u8 key[16];
+		__le16 next_frame_flags;
+		__le16 reserved2;
+		union {
+			__le32 life_time;
+			__le32 attempt;
+		} stop_time;
+
+		/* Host DRAM physical address pointer to "scratch" in this command.
+		 * Must be dword aligned.  "0" in dram_lsb_ptr disables usage. */
+		__le32 dram_lsb_ptr;
+		u8 dram_msb_ptr;
+
+		u8 rts_retry_limit;	/*byte 50 */
+		u8 data_retry_limit;	/*byte 51 */
+		u8 tid_tspec;
+		union {
+			__le16 pm_frame_timeout;
+			__le16 attempt_duration;
+		} timeout;
+
+		/*
+		 * Duration of EDCA burst Tx Opportunity, in 32-usec units.
+		 * Set this if txop time is not specified by HCCA protocol (e.g. by AP).
+		 */
+		__le16 driver_txop;
+
+	);
 	/*
 	 * MAC header goes here, followed by 2 bytes padding if MAC header
 	 * length is 26 or 30 bytes, followed by payload data
 	 */
-	union {
-		DECLARE_FLEX_ARRAY(u8, payload);
-		DECLARE_FLEX_ARRAY(struct ieee80211_hdr, hdr);
-	};
+	struct ieee80211_hdr hdr[];
 } __packed;
+static_assert(offsetof(struct iwl_tx_cmd, hdr) == sizeof(struct iwl_tx_cmd_hdr),
+	      "struct member likely outside of __struct_group()");
 
 /*
  * TX command response is sent after *agn* transmission attempts.
@@ -2312,7 +2314,7 @@ struct iwl_scan_cmd {
 
 	/* For active scans (set to all-0s for passive scans).
 	 * Does not include payload.  Must specify Tx rate; no rate scaling. */
-	struct iwl_tx_cmd tx_cmd;
+	struct iwl_tx_cmd_hdr tx_cmd;
 
 	/* For directed active scans (set to all-0s otherwise) */
 	struct iwl_ssid_ie direct_scan[PROBE_OPTION_MAX];
@@ -2423,7 +2425,7 @@ struct iwlagn_beacon_notif {
  */
 
 struct iwl_tx_beacon_cmd {
-	struct iwl_tx_cmd tx;
+	struct iwl_tx_cmd_hdr tx;
 	__le16 tim_idx;
 	u8 tim_size;
 	u8 reserved1;

From cd0b9da682cfe3b595b1d8195e6bfe8acc76e2c3 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Tue, 18 Mar 2025 13:50:08 +0100
Subject: [PATCH 2257/2753] wifi: nl80211: re-enable multi-link reconfiguration

With the recent fixes, we can re-enable multi-link
reconfiguration. Also add a CMD() entry to allow
userspace discovery for it.

Link: https://patch.msgid.link/20250318135009.a95c43837a0f.Ic6ed3d184e5be8ba47c6affa7271daaf824fd823@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 net/wireless/nl80211.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 1a9fc403d50d8..f039a7d0d6f73 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -2773,6 +2773,7 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev,
 			CMD(update_ft_ies, UPDATE_FT_IES);
 			if (rdev->wiphy.sar_capa)
 				CMD(set_sar_specs, SET_SAR_SPECS);
+			CMD(assoc_ml_reconf, ASSOC_MLO_RECONF);
 		}
 #undef CMD
 
@@ -16557,7 +16558,7 @@ static int nl80211_assoc_ml_reconf(struct sk_buff *skb, struct genl_info *info)
 		req.ext_mld_capa_ops =
 			nla_get_u16(info->attrs[NL80211_ATTR_ASSOC_MLD_EXT_CAPA_OPS]);
 
-	err = -EOPNOTSUPP;
+	err = cfg80211_assoc_ml_reconf(rdev, dev, &req);
 
 out:
 	for (link_id = 0; link_id < ARRAY_SIZE(req.add_links); link_id++)

From 8ee1c926f31e9b13a67a235ba8cf7c05f37f4296 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:26 +0000
Subject: [PATCH 2258/2753] net: stmmac: qcom-ethqos: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it a second time in qcom_ethqos_probe(). Use
plat_dat->phy_interface to initialise ethqos->phy_mode.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGI-005uzT-KB@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c | 4 +---
 1 file changed, 1 insertion(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index eafe637540b60..0e4da216f942c 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -794,9 +794,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	if (!ethqos)
 		return -ENOMEM;
 
-	ret = of_get_phy_mode(np, &ethqos->phy_mode);
-	if (ret)
-		return dev_err_probe(dev, ret, "Failed to get phy mode\n");
+	ethqos->phy_mode = plat_dat->phy_interface;
 	switch (ethqos->phy_mode) {
 	case PHY_INTERFACE_MODE_RGMII:
 	case PHY_INTERFACE_MODE_RGMII_ID:

From 46f84d700cb88f934ea1e4fc7d9d814e9bcf06f1 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:31 +0000
Subject: [PATCH 2259/2753] net: stmmac: mediatek: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Initialise priv_plat->phy_mode from plat->phy_interface
inmediatek_dwmac_common_data().

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGN-005uzZ-NG@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
index c9636832a570a..d178d5ddc7c7a 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-mediatek.c
@@ -456,7 +456,6 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
 {
 	struct mac_delay_struct *mac_delay = &plat->mac_delay;
 	u32 tx_delay_ps, rx_delay_ps;
-	int err;
 
 	plat->peri_regmap = syscon_regmap_lookup_by_phandle(plat->np, "mediatek,pericfg");
 	if (IS_ERR(plat->peri_regmap)) {
@@ -464,12 +463,6 @@ static int mediatek_dwmac_config_dt(struct mediatek_dwmac_plat_data *plat)
 		return PTR_ERR(plat->peri_regmap);
 	}
 
-	err = of_get_phy_mode(plat->np, &plat->phy_mode);
-	if (err) {
-		dev_err(plat->dev, "not find phy-mode\n");
-		return err;
-	}
-
 	if (!of_property_read_u32(plat->np, "mediatek,tx-delay-ps", &tx_delay_ps)) {
 		if (tx_delay_ps < plat->variant->tx_delay_max) {
 			mac_delay->tx_delay = tx_delay_ps;
@@ -587,6 +580,7 @@ static int mediatek_dwmac_common_data(struct platform_device *pdev,
 {
 	int i;
 
+	priv_plat->phy_mode = plat->phy_interface;
 	plat->mac_interface = priv_plat->phy_mode;
 	if (priv_plat->mac_wol)
 		plat->flags &= ~STMMAC_FLAG_USE_PHY_WOL;

From e3ef12172a839d517cae11e635cd734db2d67449 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:36 +0000
Subject: [PATCH 2260/2753] net: stmmac: anarion: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Rearrange the initialisation order so we can pass plat_dat into
anarion_config_dt(), thereby providing plat_dat->phy_interface as
necessary there.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGS-005uzf-QE@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/stmicro/stmmac/dwmac-anarion.c   | 21 ++++++++-----------
 1 file changed, 9 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
index ef99ef3f1ab47..37fe7c2888784 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c
@@ -59,10 +59,11 @@ static void anarion_gmac_exit(struct platform_device *pdev, void *priv)
 	gmac_write_reg(gmac, GMAC_RESET_CONTROL_REG, 1);
 }
 
-static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
+static struct anarion_gmac *
+anarion_config_dt(struct platform_device *pdev,
+		  struct plat_stmmacenet_data *plat_dat)
 {
 	struct anarion_gmac *gmac;
-	phy_interface_t phy_mode;
 	void __iomem *ctl_block;
 	int err;
 
@@ -79,11 +80,7 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
 
 	gmac->ctl_block = ctl_block;
 
-	err = of_get_phy_mode(pdev->dev.of_node, &phy_mode);
-	if (err)
-		return ERR_PTR(err);
-
-	switch (phy_mode) {
+	switch (plat_dat->phy_interface) {
 	case PHY_INTERFACE_MODE_RGMII:
 		fallthrough;
 	case PHY_INTERFACE_MODE_RGMII_ID:
@@ -93,7 +90,7 @@ static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev)
 		break;
 	default:
 		dev_err(&pdev->dev, "Unsupported phy-mode (%d)\n",
-			phy_mode);
+			plat_dat->phy_interface);
 		return ERR_PTR(-ENOTSUPP);
 	}
 
@@ -111,14 +108,14 @@ static int anarion_dwmac_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	gmac = anarion_config_dt(pdev);
-	if (IS_ERR(gmac))
-		return PTR_ERR(gmac);
-
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
 
+	gmac = anarion_config_dt(pdev, plat_dat);
+	if (IS_ERR(gmac))
+		return PTR_ERR(gmac);
+
 	plat_dat->init = anarion_gmac_init;
 	plat_dat->exit = anarion_gmac_exit;
 	anarion_gmac_init(pdev, gmac);

From f07cb4b4b4816169cd4b051286d1bccff3fef666 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:41 +0000
Subject: [PATCH 2261/2753] net: stmmac: ipq806x: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Pass plat_dat into ipq806x_gmac_of_parse(), and set gmac->phy_mode from
plat_dat->phy_interface.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGX-005uzl-TQ@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
index 0a9c137cc4e63..ca4035cbb55b6 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-ipq806x.c
@@ -211,16 +211,12 @@ static int ipq806x_gmac_set_speed(struct ipq806x_gmac *gmac, int speed)
 	return 0;
 }
 
-static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac)
+static int ipq806x_gmac_of_parse(struct ipq806x_gmac *gmac,
+				 struct plat_stmmacenet_data *plat_dat)
 {
 	struct device *dev = &gmac->pdev->dev;
-	int ret;
 
-	ret = of_get_phy_mode(dev->of_node, &gmac->phy_mode);
-	if (ret) {
-		dev_err(dev, "missing phy mode property\n");
-		return -EINVAL;
-	}
+	gmac->phy_mode = plat_dat->phy_interface;
 
 	if (of_property_read_u32(dev->of_node, "qcom,id", &gmac->id) < 0) {
 		dev_err(dev, "missing qcom id property\n");
@@ -398,7 +394,7 @@ static int ipq806x_gmac_probe(struct platform_device *pdev)
 
 	gmac->pdev = pdev;
 
-	err = ipq806x_gmac_of_parse(gmac);
+	err = ipq806x_gmac_of_parse(gmac, plat_dat);
 	if (err) {
 		dev_err(dev, "device tree parsing error\n");
 		return err;

From 3e5833060efb6478757dc34284d76ee196157833 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:47 +0000
Subject: [PATCH 2262/2753] net: stmmac: meson8b: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Set dwmac->phy_mode from plat_dat->phy_interface.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGd-005uzr-0C@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
index 9c2d62d133ade..a50782994b979 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c
@@ -417,11 +417,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev)
 		return PTR_ERR(dwmac->regs);
 
 	dwmac->dev = &pdev->dev;
-	ret = of_get_phy_mode(pdev->dev.of_node, &dwmac->phy_mode);
-	if (ret) {
-		dev_err(&pdev->dev, "missing phy-mode property\n");
-		return ret;
-	}
+	dwmac->phy_mode = plat_dat->phy_interface;
 
 	/* use 2ns as fallback since this value was previously hardcoded */
 	if (of_property_read_u32(pdev->dev.of_node, "amlogic,tx-delay-ns",

From 9886718ad1c5dc26c6b57f5c3eb66f1bf2ba0d06 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:52 +0000
Subject: [PATCH 2263/2753] net: stmmac: rk: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Set bsp_priv->phy_iface from plat->phy_interface.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGi-005uzx-3p@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 342463587d06f..2d4fee8b9ab14 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1503,7 +1503,7 @@ static struct rk_priv_data *rk_gmac_setup(struct platform_device *pdev,
 	if (!bsp_priv)
 		return ERR_PTR(-ENOMEM);
 
-	of_get_phy_mode(dev->of_node, &bsp_priv->phy_iface);
+	bsp_priv->phy_iface = plat->phy_interface;
 	bsp_priv->ops = ops;
 
 	/* Some SoCs have multiple MAC controllers, which need

From 3e2858bb3f59e9158f76746fc4b7d7faaa1cb20e Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:20:57 +0000
Subject: [PATCH 2264/2753] net: stmmac: sti: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Pass plat_dat into sti_dwmac_parse_data(), and set dwmac->interface
from plat_dat->phy_interface.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGn-005v02-7G@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
index 13b9c2a51fce4..be57c6c12c1c2 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sti.c
@@ -185,7 +185,8 @@ static int sti_dwmac_set_mode(struct sti_dwmac *dwmac)
 }
 
 static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
-				struct platform_device *pdev)
+				struct platform_device *pdev,
+				struct plat_stmmacenet_data *plat_dat)
 {
 	struct resource *res;
 	struct device *dev = &pdev->dev;
@@ -204,12 +205,7 @@ static int sti_dwmac_parse_data(struct sti_dwmac *dwmac,
 	if (IS_ERR(regmap))
 		return PTR_ERR(regmap);
 
-	err = of_get_phy_mode(np, &dwmac->interface);
-	if (err && err != -ENODEV) {
-		dev_err(dev, "Can't get phy-mode\n");
-		return err;
-	}
-
+	dwmac->interface = plat_dat->phy_interface;
 	dwmac->regmap = regmap;
 	dwmac->gmac_en = of_property_read_bool(np, "st,gmac_en");
 	dwmac->ext_phyclk = of_property_read_bool(np, "st,ext-phyclk");
@@ -268,7 +264,7 @@ static int sti_dwmac_probe(struct platform_device *pdev)
 	if (!dwmac)
 		return -ENOMEM;
 
-	ret = sti_dwmac_parse_data(dwmac, pdev);
+	ret = sti_dwmac_parse_data(dwmac, pdev, plat_dat);
 	if (ret) {
 		dev_err(&pdev->dev, "Unable to parse OF data\n");
 		return ret;

From 3d9e9dfce04c77f2e232a50834f4666e1994cbb0 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:21:02 +0000
Subject: [PATCH 2265/2753] net: stmmac: sun8i: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

sun8i was using of_get_phy_mode() to set plat_dat->mac_interface, which
defaults to plat_dat->phy_interface when the mac-mode DT property is
not present. As nothing in arch/*/boot/dts sets the mac-mode property,
it is highly likely that these two will be identical, and thus there
is no need for this glue driver to set plat_dat->mac_interface.

Reviewed-by: Andre Przywara <andre.przywara@arm.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGs-005v09-CD@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
index 4b7b2582a1201..85723a78793ab 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sun8i.c
@@ -1155,11 +1155,10 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	struct stmmac_resources stmmac_res;
 	struct sunxi_priv_data *gmac;
 	struct device *dev = &pdev->dev;
-	phy_interface_t interface;
-	int ret;
 	struct stmmac_priv *priv;
 	struct net_device *ndev;
 	struct regmap *regmap;
+	int ret;
 
 	ret = stmmac_get_platform_resources(pdev, &stmmac_res);
 	if (ret)
@@ -1219,10 +1218,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	ret = of_get_phy_mode(dev->of_node, &interface);
-	if (ret)
-		return -EINVAL;
-
 	plat_dat = devm_stmmac_probe_config_dt(pdev, stmmac_res.mac);
 	if (IS_ERR(plat_dat))
 		return PTR_ERR(plat_dat);
@@ -1230,7 +1225,6 @@ static int sun8i_dwmac_probe(struct platform_device *pdev)
 	/* platform data specifying hardware features and callbacks.
 	 * hardware features were copied from Allwinner drivers.
 	 */
-	plat_dat->mac_interface = interface;
 	plat_dat->rx_coe = STMMAC_RX_COE_TYPE2;
 	plat_dat->tx_coe = 1;
 	plat_dat->flags |= STMMAC_FLAG_HAS_SUN8I;

From 00d2c3c071245712a7fb3882f9074ecc594eaa68 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:21:07 +0000
Subject: [PATCH 2266/2753] net: stmmac: sunxi: remove of_get_phy_mode()

devm_stmmac_probe_config_dt() already gets the PHY mode from firmware,
which is stored in plat_dat->phy_interface. Therefore, we don't need to
get it in platform code.

Set gmac->interface from plat_dat->phy_interface.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Acked-by: Jernej Skrabec <jernej.skrabec@gmail.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIGx-005v0F-Ev@rmk-PC.armlinux.org.uk
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
index 1b1ce2888b2eb..9f098ff0ff058 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-sunxi.c
@@ -116,11 +116,7 @@ static int sun7i_gmac_probe(struct platform_device *pdev)
 	if (!gmac)
 		return -ENOMEM;
 
-	ret = of_get_phy_mode(dev->of_node, &gmac->interface);
-	if (ret && ret != -ENODEV) {
-		dev_err(dev, "Can't get phy-mode\n");
-		return ret;
-	}
+	gmac->interface = plat_dat->phy_interface;
 
 	gmac->tx_clk = devm_clk_get(dev, "allwinner_gmac_tx");
 	if (IS_ERR(gmac->tx_clk)) {

From f3b97b7d4bf316c3991e5634c9f4847c2df35478 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 12 Mar 2025 10:52:49 +0100
Subject: [PATCH 2267/2753] devlink: fix xa_alloc_cyclic() error handling

In case of returning 1 from xa_alloc_cyclic() (wrapping) ERR_PTR(1) will
be returned, which will cause IS_ERR() to be false. Which can lead to
dereference not allocated pointer (rel).

Fix it by checking if err is lower than zero.

This wasn't found in real usecase, only noticed. Credit to Pierre.

Fixes: c137743bce02 ("devlink: introduce object and nested devlink relationship infra")
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 net/devlink/core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/devlink/core.c b/net/devlink/core.c
index f49cd83f1955f..7203c39532fcc 100644
--- a/net/devlink/core.c
+++ b/net/devlink/core.c
@@ -117,7 +117,7 @@ static struct devlink_rel *devlink_rel_alloc(void)
 
 	err = xa_alloc_cyclic(&devlink_rels, &rel->index, rel,
 			      xa_limit_32b, &next, GFP_KERNEL);
-	if (err) {
+	if (err < 0) {
 		kfree(rel);
 		return ERR_PTR(err);
 	}

From 3614bf90130d60f191a5fe218d04f6251c678e13 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 12 Mar 2025 10:52:50 +0100
Subject: [PATCH 2268/2753] dpll: fix xa_alloc_cyclic() error handling

In case of returning 1 from xa_alloc_cyclic() (wrapping) ERR_PTR(1) will
be returned, which will cause IS_ERR() to be false. Which can lead to
dereference not allocated pointer (pin).

Fix it by checking if err is lower than zero.

This wasn't found in real usecase, only noticed. Credit to Pierre.

Fixes: 97f265ef7f5b ("dpll: allocate pin ids in cycle")
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/dpll/dpll_core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 32019dc33cca7..1877201d1aa9f 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -505,7 +505,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
-	if (ret)
+	if (ret < 0)
 		goto err_xa_alloc;
 	return pin;
 err_xa_alloc:

From 3178d2b048365fe2c078cd53f85f2abf1487733b Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Wed, 12 Mar 2025 10:52:51 +0100
Subject: [PATCH 2269/2753] phy: fix xa_alloc_cyclic() error handling

xa_alloc_cyclic() can return 1, which isn't an error. To prevent
situation when the caller of this function will treat it as no error do
a check only for negative here.

Fixes: 384968786909 ("net: phy: Introduce ethernet link topology representation")
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/phy/phy_link_topology.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/phy_link_topology.c b/drivers/net/phy/phy_link_topology.c
index 4a5d73002a1a8..0e9e987f37dd8 100644
--- a/drivers/net/phy/phy_link_topology.c
+++ b/drivers/net/phy/phy_link_topology.c
@@ -73,7 +73,7 @@ int phy_link_topo_add_phy(struct net_device *dev,
 				      xa_limit_32b, &topo->next_phy_index,
 				      GFP_KERNEL);
 
-	if (ret)
+	if (ret < 0)
 		goto err;
 
 	return 0;

From 5fd0ff3b96494e6a2eaf876ace3152a01dca9c1f Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Mon, 17 Feb 2025 16:17:29 +0800
Subject: [PATCH 2270/2753] wifi: mt76: mt7925: introduce MLO capability
 control

This patch introduces MLO capability control for the MT792x Wi-Fi driver.
It removes the unused `MT792x_CHIP_CAP_MLO_EVT_EN` flag and introduces new
capability flags `MT792x_CHIP_CAP_MLO_EN` and `MT792x_CHIP_CAP_MLO_EML_EN`
to enable MLO and EML features based on firmware capabilities.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Reviewed-by: Sabeeh Khan <sabeeh-khan@ti.com>
Link: https://patch.msgid.link/20250217081729.1840930-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c  | 10 ++++++++--
 drivers/net/wireless/mediatek/mt76/mt792x.h      |  3 ++-
 3 files changed, 11 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 98daf80ac1313..ad47a4b153da5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -251,7 +251,7 @@ int mt7925_init_mlo_caps(struct mt792x_phy *phy)
 		},
 	};
 
-	if (!(phy->chip_cap & MT792x_CHIP_CAP_MLO_EVT_EN))
+	if (!(phy->chip_cap & MT792x_CHIP_CAP_MLO_EN))
 		return 0;
 
 	ext_capab[0].eml_capabilities = phy->eml_cap;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 15815ad84713a..5f40c3c1ffa10 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -2559,6 +2559,7 @@ mt7925_mcu_bss_mld_tlv(struct sk_buff *skb,
 	struct ieee80211_vif *vif = link_conf->vif;
 	struct mt792x_bss_conf *mconf = mt792x_link_conf_to_mconf(link_conf);
 	struct mt792x_vif *mvif = (struct mt792x_vif *)link_conf->vif->drv_priv;
+	struct mt792x_phy *phy = mvif->phy;
 	struct bss_mld_tlv *mld;
 	struct tlv *tlv;
 	bool is_mld;
@@ -2574,8 +2575,13 @@ mt7925_mcu_bss_mld_tlv(struct sk_buff *skb,
 	mld->group_mld_id = is_mld ? mvif->bss_conf.mt76.idx : 0xff;
 	mld->own_mld_id = mconf->mt76.idx + 32;
 	mld->remap_idx = 0xff;
-	mld->eml_enable = !!(link_conf->vif->cfg.eml_cap &
-			     IEEE80211_EML_CAP_EMLSR_SUPP);
+
+	if (phy->chip_cap & MT792x_CHIP_CAP_MLO_EML_EN) {
+		mld->eml_enable = !!(link_conf->vif->cfg.eml_cap &
+				     IEEE80211_EML_CAP_EMLSR_SUPP);
+	} else {
+		mld->eml_enable = 0;
+	}
 
 	memcpy(mld->mac_addr, vif->addr, ETH_ALEN);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 32ed01a96bf7c..454c6f523cc22 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -27,8 +27,9 @@
 
 #define MT792x_CHIP_CAP_CLC_EVT_EN BIT(0)
 #define MT792x_CHIP_CAP_RSSI_NOTIFY_EVT_EN BIT(1)
-#define MT792x_CHIP_CAP_MLO_EVT_EN BIT(2)
 #define MT792x_CHIP_CAP_WF_RF_PIN_CTRL_EVT_EN BIT(3)
+#define MT792x_CHIP_CAP_MLO_EN BIT(8)
+#define MT792x_CHIP_CAP_MLO_EML_EN BIT(9)
 
 /* NOTE: used to map mt76_rates. idx may change if firmware expands table */
 #define MT792x_BASIC_RATES_TBL	11

From 2d5630b0c9466ac6549495828aa7dce7424a272a Mon Sep 17 00:00:00 2001
From: Quan Zhou <quan.zhou@mediatek.com>
Date: Tue, 14 Jan 2025 13:06:22 +0800
Subject: [PATCH 2271/2753] wifi: mt76: mt7925: fix fails to enter low power
 mode in suspend state

The mt7925 sometimes fails to enter low power mode during suspend.
This is caused by the chip firmware sending an additional ACK event
to the host after processing the suspend command. Due to timing issues,
this event may not reach the host, causing the chip to get stuck.
To resolve this, the ACK flag in the suspend command is removed,
as it is not needed in the MT7925 architecture. This prevents the
firmware from sending the additional ACK event, ensuring the device
can reliably enter low power mode during suspend.

Signed-off-by: Quan Zhou <quan.zhou@mediatek.com>
Link: https://patch.msgid.link/d056938144a3a0336c3a4e3cec6f271899f32bf7.1736775666.git.quan.zhou@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 5f40c3c1ffa10..4bbbcfd5cdd4f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -3272,6 +3272,9 @@ int mt7925_mcu_fill_message(struct mt76_dev *mdev, struct sk_buff *skb,
 		else
 			uni_txd->option = MCU_CMD_UNI_EXT_ACK;
 
+		if (cmd == MCU_UNI_CMD(HIF_CTRL))
+			uni_txd->option &= ~MCU_CMD_ACK;
+
 		goto exit;
 	}
 

From 77b749520cac06d000d9923f79ffa632cdea6113 Mon Sep 17 00:00:00 2001
From: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Date: Tue, 14 Jan 2025 07:44:41 -0800
Subject: [PATCH 2272/2753] wifi: mt76: mt7915: fix possible integer overflows
 in mt7915_muru_stats_show()

Assuming sums of values stored in variables such as sub_total_cnt
and total_ppdu_cnt are big enough to warrant their u64 type, it
makes sense to ensure that their calculation takes into account
possible integer overflow issues.

Play it safe and fix the problem by casting right hand expressions
to u64 as well. Also, slightly adjust tabulation.

Found by Linux Verification Center (linuxtesting.org) with static
analysis tool SVACE.

Fixes: 1966a5078f2d ("mt76: mt7915: add mu-mimo and ofdma debugfs knobs")
Signed-off-by: Nikita Zhandarovich <n.zhandarovich@fintech.ru>
Link: https://patch.msgid.link/20250114154441.16920-1-n.zhandarovich@fintech.ru
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7915/debugfs.c   | 45 ++++++++++---------
 1 file changed, 23 insertions(+), 22 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index 578013884e438..4fec7d000a631 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -303,9 +303,9 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 		   phy->mib.dl_vht_3mu_cnt,
 		   phy->mib.dl_vht_4mu_cnt);
 
-	sub_total_cnt = phy->mib.dl_vht_2mu_cnt +
-			phy->mib.dl_vht_3mu_cnt +
-			phy->mib.dl_vht_4mu_cnt;
+	sub_total_cnt = (u64)phy->mib.dl_vht_2mu_cnt +
+			     phy->mib.dl_vht_3mu_cnt +
+			     phy->mib.dl_vht_4mu_cnt;
 
 	seq_printf(file, "\nTotal non-HE MU-MIMO DL PPDU count: %lld",
 		   sub_total_cnt);
@@ -353,26 +353,27 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 		   phy->mib.dl_he_9to16ru_cnt,
 		   phy->mib.dl_he_gtr16ru_cnt);
 
-	sub_total_cnt = phy->mib.dl_he_2mu_cnt +
-			phy->mib.dl_he_3mu_cnt +
-			phy->mib.dl_he_4mu_cnt;
+	sub_total_cnt = (u64)phy->mib.dl_he_2mu_cnt +
+			     phy->mib.dl_he_3mu_cnt +
+			     phy->mib.dl_he_4mu_cnt;
 	total_ppdu_cnt = sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE MU-MIMO DL PPDU count: %lld",
 		   sub_total_cnt);
 
-	sub_total_cnt = phy->mib.dl_he_2ru_cnt +
-			phy->mib.dl_he_3ru_cnt +
-			phy->mib.dl_he_4ru_cnt +
-			phy->mib.dl_he_5to8ru_cnt +
-			phy->mib.dl_he_9to16ru_cnt +
-			phy->mib.dl_he_gtr16ru_cnt;
+	sub_total_cnt = (u64)phy->mib.dl_he_2ru_cnt +
+			     phy->mib.dl_he_3ru_cnt +
+			     phy->mib.dl_he_4ru_cnt +
+			     phy->mib.dl_he_5to8ru_cnt +
+			     phy->mib.dl_he_9to16ru_cnt +
+			     phy->mib.dl_he_gtr16ru_cnt;
 	total_ppdu_cnt += sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE OFDMA DL PPDU count: %lld",
 		   sub_total_cnt);
 
-	total_ppdu_cnt += phy->mib.dl_he_su_cnt + phy->mib.dl_he_ext_su_cnt;
+	total_ppdu_cnt += (u64)phy->mib.dl_he_su_cnt +
+			       phy->mib.dl_he_ext_su_cnt;
 
 	seq_printf(file, "\nAll HE DL PPDU count: %lld", total_ppdu_cnt);
 
@@ -404,20 +405,20 @@ static int mt7915_muru_stats_show(struct seq_file *file, void *data)
 		   phy->mib.ul_hetrig_9to16ru_cnt,
 		   phy->mib.ul_hetrig_gtr16ru_cnt);
 
-	sub_total_cnt = phy->mib.ul_hetrig_2mu_cnt +
-			phy->mib.ul_hetrig_3mu_cnt +
-			phy->mib.ul_hetrig_4mu_cnt;
+	sub_total_cnt = (u64)phy->mib.ul_hetrig_2mu_cnt +
+			     phy->mib.ul_hetrig_3mu_cnt +
+			     phy->mib.ul_hetrig_4mu_cnt;
 	total_ppdu_cnt = sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE MU-MIMO UL TB PPDU count: %lld",
 		   sub_total_cnt);
 
-	sub_total_cnt = phy->mib.ul_hetrig_2ru_cnt +
-			phy->mib.ul_hetrig_3ru_cnt +
-			phy->mib.ul_hetrig_4ru_cnt +
-			phy->mib.ul_hetrig_5to8ru_cnt +
-			phy->mib.ul_hetrig_9to16ru_cnt +
-			phy->mib.ul_hetrig_gtr16ru_cnt;
+	sub_total_cnt = (u64)phy->mib.ul_hetrig_2ru_cnt +
+			     phy->mib.ul_hetrig_3ru_cnt +
+			     phy->mib.ul_hetrig_4ru_cnt +
+			     phy->mib.ul_hetrig_5to8ru_cnt +
+			     phy->mib.ul_hetrig_9to16ru_cnt +
+			     phy->mib.ul_hetrig_gtr16ru_cnt;
 	total_ppdu_cnt += sub_total_cnt;
 
 	seq_printf(file, "\nTotal HE OFDMA UL TB PPDU count: %lld",

From 8ae45b1f699bbc27ea8647093f794f671e77410b Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Thu, 16 Jan 2025 13:59:25 +0800
Subject: [PATCH 2273/2753] wifi: mt76: mt7925: ensure wow pattern command
 align fw format

Align the format of "struct mt7925_wow_pattern_tlv" with
firmware to ensure proper functionality.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250116055925.3856856-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
index 1e47d2c61b545..6bf1623e542eb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
@@ -566,8 +566,8 @@ struct mt7925_wow_pattern_tlv {
 	u8 offset;
 	u8 mask[MT76_CONNAC_WOW_MASK_MAX_LEN];
 	u8 pattern[MT76_CONNAC_WOW_PATTEN_MAX_LEN];
-	u8 rsv[7];
-} __packed;
+	u8 rsv[4];
+};
 
 struct roc_acquire_tlv {
 	__le16 tag;

From 6458d760a0c0afd2fda11e83ed3e1125a252432f Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Thu, 16 Jan 2025 14:21:31 +0800
Subject: [PATCH 2274/2753] wifi: mt76: mt7925: fix country count limitation
 for CLC

Due to the increase in the number of power tables for 6Ghz on CLC,
the variable nr_country is no longer sufficient to represent the
total quantity. Therefore, we have switched to calculating the
length of clc buf to obtain the correct power table.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250116062131.3860198-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 4bbbcfd5cdd4f..10272af24dd1d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -3164,13 +3164,14 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		.acpi_conf = mt792x_acpi_get_flags(&dev->phy),
 	};
 	int ret, valid_cnt = 0;
-	u8 i, *pos;
+	u8 *pos, *last_pos;
 
 	if (!clc)
 		return 0;
 
 	pos = clc->data + sizeof(*seg) * clc->nr_seg;
-	for (i = 0; i < clc->nr_country; i++) {
+	last_pos = clc->data + le32_to_cpu(*(__le32 *)(clc->data + 4));
+	while (pos < last_pos) {
 		struct mt7925_clc_rule *rule = (struct mt7925_clc_rule *)pos;
 
 		pos += sizeof(*rule);

From 4bc1da524b502999da28d287de4286c986a1af57 Mon Sep 17 00:00:00 2001
From: Haoxiang Li <haoxiang_li2024@163.com>
Date: Wed, 19 Feb 2025 11:36:45 +0800
Subject: [PATCH 2275/2753] wifi: mt76: Add check for devm_kstrdup()

Add check for the return value of devm_kstrdup() in
mt76_get_of_data_from_mtd() to catch potential exception.

Fixes: e7a6a044f9b9 ("mt76: testmode: move mtd part to mt76_dev")
Cc: stable@vger.kernel.org
Signed-off-by: Haoxiang Li <haoxiang_li2024@163.com>
Link: https://patch.msgid.link/20250219033645.2594753-1-haoxiang_li2024@163.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/eeprom.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/eeprom.c b/drivers/net/wireless/mediatek/mt76/eeprom.c
index 0bc66cc19acd1..443517d06c9fa 100644
--- a/drivers/net/wireless/mediatek/mt76/eeprom.c
+++ b/drivers/net/wireless/mediatek/mt76/eeprom.c
@@ -95,6 +95,10 @@ int mt76_get_of_data_from_mtd(struct mt76_dev *dev, void *eep, int offset, int l
 
 #ifdef CONFIG_NL80211_TESTMODE
 	dev->test_mtd.name = devm_kstrdup(dev->dev, part, GFP_KERNEL);
+	if (!dev->test_mtd.name) {
+		ret = -ENOMEM;
+		goto out_put_node;
+	}
 	dev->test_mtd.offset = offset;
 #endif
 

From ffb9d7bcd3e3e2d937bcfd7fc064b15f3b7ca3e3 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Mon, 24 Feb 2025 00:21:24 +0100
Subject: [PATCH 2276/2753] wifi: mt76: mt7925: Remove unnecessary if-check

The if and else branches implement the same logic. Remove the
unnecessary if-check and simplify the code.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://patch.msgid.link/20250223232127.99357-2-thorsten.blum@linux.dev
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 6 +-----
 1 file changed, 1 insertion(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 10272af24dd1d..eee65cf482034 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -1983,11 +1983,7 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev,
 		mlink = mt792x_sta_to_link(msta, link_sta->link_id);
 	}
 	info.wcid = link_sta ? &mlink->wcid : &mvif->sta.deflink.wcid;
-
-	if (link_sta)
-		info.newly = state != MT76_STA_INFO_STATE_ASSOC;
-	else
-		info.newly = state == MT76_STA_INFO_STATE_ASSOC ? false : true;
+	info.newly = state != MT76_STA_INFO_STATE_ASSOC;
 
 	if (ieee80211_vif_is_mld(vif))
 		err = mt7925_mcu_mlo_sta_cmd(&dev->mphy, &info);

From bf39813599b0375a3eebbbc6837f728554b3883a Mon Sep 17 00:00:00 2001
From: Quan Zhou <quan.zhou@mediatek.com>
Date: Mon, 24 Feb 2025 21:05:14 +0800
Subject: [PATCH 2277/2753] wifi: mt76: mt7925: Simplify HIF suspend handling
 to avoid suspend fail

System suspend failures may occur due to inappropriate
handling of traffic not idle event by the WiFi driver.
The WiFi firmware's traffic not idle indication does
not need to be tied to suspend. Fix the flow to ensuring
the system can suspend properly.

Signed-off-by: Quan Zhou <quan.zhou@mediatek.com>
Link: https://patch.msgid.link/34208c7280325f57a651363d339399eb1744d3b7.1740400998.git.quan.zhou@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 12 ++++--------
 1 file changed, 4 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index eee65cf482034..7885d71b7a77d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -348,14 +348,10 @@ mt7925_mcu_handle_hif_ctrl_basic(struct mt792x_dev *dev, struct tlv *tlv)
 	basic = (struct mt7925_mcu_hif_ctrl_basic_tlv *)tlv;
 
 	if (basic->hifsuspend) {
-		if (basic->hif_tx_traffic_status == HIF_TRAFFIC_IDLE &&
-		    basic->hif_rx_traffic_status == HIF_TRAFFIC_IDLE)
-			/* success */
-			dev->hif_idle = true;
-		else
-			/* busy */
-			/* invalid */
-			dev->hif_idle = false;
+		dev->hif_idle = true;
+		if (!(basic->hif_tx_traffic_status == HIF_TRAFFIC_IDLE &&
+		      basic->hif_rx_traffic_status == HIF_TRAFFIC_IDLE))
+			dev_info(dev->mt76.dev, "Hif traffic not idle.\n");
 	} else {
 		dev->hif_resumed = true;
 	}

From adc3fd2a2277b7cc0b61692463771bf9bd298036 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 18 Feb 2025 11:33:42 +0800
Subject: [PATCH 2278/2753] wifi: mt76: mt7921: fix kernel panic due to null
 pointer dereference

Address a kernel panic caused by a null pointer dereference in the
`mt792x_rx_get_wcid` function. The issue arises because the `deflink` structure
is not properly initialized with the `sta` context. This patch ensures that the
`deflink` structure is correctly linked to the `sta` context, preventing the
null pointer dereference.

 BUG: kernel NULL pointer dereference, address: 0000000000000400
 #PF: supervisor read access in kernel mode
 #PF: error_code(0x0000) - not-present page
 PGD 0 P4D 0
 Oops: Oops: 0000 [#1] PREEMPT SMP NOPTI
 CPU: 0 UID: 0 PID: 470 Comm: mt76-usb-rx phy Not tainted 6.12.13-gentoo-dist #1
 Hardware name:  /AMD HUDSON-M1, BIOS 4.6.4 11/15/2011
 RIP: 0010:mt792x_rx_get_wcid+0x48/0x140 [mt792x_lib]
 RSP: 0018:ffffa147c055fd98 EFLAGS: 00010202
 RAX: 0000000000000000 RBX: ffff8e9ecb652000 RCX: 0000000000000000
 RDX: 0000000000000000 RSI: 0000000000000001 RDI: ffff8e9ecb652000
 RBP: 0000000000000685 R08: ffff8e9ec6570000 R09: 0000000000000000
 R10: ffff8e9ecd2ca000 R11: ffff8e9f22a217c0 R12: 0000000038010119
 R13: 0000000080843801 R14: ffff8e9ec6570000 R15: ffff8e9ecb652000
 FS:  0000000000000000(0000) GS:ffff8e9f22a00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 0000000000000400 CR3: 000000000d2ea000 CR4: 00000000000006f0
 Call Trace:
  <TASK>
  ? __die_body.cold+0x19/0x27
  ? page_fault_oops+0x15a/0x2f0
  ? search_module_extables+0x19/0x60
  ? search_bpf_extables+0x5f/0x80
  ? exc_page_fault+0x7e/0x180
  ? asm_exc_page_fault+0x26/0x30
  ? mt792x_rx_get_wcid+0x48/0x140 [mt792x_lib]
  mt7921_queue_rx_skb+0x1c6/0xaa0 [mt7921_common]
  mt76u_alloc_queues+0x784/0x810 [mt76_usb]
  ? __pfx___mt76_worker_fn+0x10/0x10 [mt76]
  __mt76_worker_fn+0x4f/0x80 [mt76]
  kthread+0xd2/0x100
  ? __pfx_kthread+0x10/0x10
  ret_from_fork+0x34/0x50
  ? __pfx_kthread+0x10/0x10
  ret_from_fork_asm+0x1a/0x30
  </TASK>
 ---[ end trace 0000000000000000 ]---

Reported-by: Nick Morrow <usbwifi2024@gmail.com>
Closes: https://github.com/morrownr/USB-WiFi/issues/577
Cc: stable@vger.kernel.org
Fixes: 90c10286b176 ("wifi: mt76: mt7925: Update mt792x_rx_get_wcid for per-link STA")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Tested-by: Salah Coronya <salah.coronya@gmail.com>
Link: https://patch.msgid.link/20250218033343.1999648-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7921/main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
index 13e58c328aff4..78b77a54d1957 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
@@ -811,6 +811,7 @@ int mt7921_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	msta->deflink.wcid.phy_idx = mvif->bss_conf.mt76.band_idx;
 	msta->deflink.wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	msta->deflink.last_txs = jiffies;
+	msta->deflink.sta = msta;
 
 	ret = mt76_connac_pm_wake(&dev->mphy, &dev->pm);
 	if (ret)

From 766ea2cf5a398c7eed519b12c6c6cf1631143ea2 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:46 -0800
Subject: [PATCH 2279/2753] Revert "wifi: mt76: mt7925: Update
 mt7925_mcu_uni_[tx,rx]_ba for MLO"

For MLO, mac80211 will send the BA action for each link to
the driver, so the driver does not need to handle it itself.
Therefore, revert this patch.

Fixes: eb2a9a12c609 ("wifi: mt76: mt7925: Update mt7925_mcu_uni_[tx,rx]_ba for MLO")
Cc: stable@vger.kernel.org
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-1-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/main.c  | 10 ++--
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 50 ++++---------------
 .../wireless/mediatek/mt76/mt7925/mt7925.h    |  2 -
 3 files changed, 14 insertions(+), 48 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index ad47a4b153da5..47a6040381a0e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1289,22 +1289,22 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta->deflink.wcid, tid, ssn,
 				   params->buf_size);
-		mt7925_mcu_uni_rx_ba(dev, vif, params, true);
+		mt7925_mcu_uni_rx_ba(dev, params, true);
 		break;
 	case IEEE80211_AMPDU_RX_STOP:
 		mt76_rx_aggr_stop(&dev->mt76, &msta->deflink.wcid, tid);
-		mt7925_mcu_uni_rx_ba(dev, vif, params, false);
+		mt7925_mcu_uni_rx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
 		mtxq->aggr = true;
 		mtxq->send_bar = false;
-		mt7925_mcu_uni_tx_ba(dev, vif, params, true);
+		mt7925_mcu_uni_tx_ba(dev, params, true);
 		break;
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
 		clear_bit(tid, &msta->deflink.wcid.ampdu_state);
-		mt7925_mcu_uni_tx_ba(dev, vif, params, false);
+		mt7925_mcu_uni_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
 		set_bit(tid, &msta->deflink.wcid.ampdu_state);
@@ -1313,7 +1313,7 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
 		clear_bit(tid, &msta->deflink.wcid.ampdu_state);
-		mt7925_mcu_uni_tx_ba(dev, vif, params, false);
+		mt7925_mcu_uni_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 7885d71b7a77d..ebe7cc30aaf95 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -572,10 +572,10 @@ void mt7925_mcu_rx_event(struct mt792x_dev *dev, struct sk_buff *skb)
 
 static int
 mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif,
-		  struct mt76_wcid *wcid,
 		  struct ieee80211_ampdu_params *params,
 		  bool enable, bool tx)
 {
+	struct mt76_wcid *wcid = (struct mt76_wcid *)params->sta->drv_priv;
 	struct sta_rec_ba_uni *ba;
 	struct sk_buff *skb;
 	struct tlv *tlv;
@@ -603,60 +603,28 @@ mt7925_mcu_sta_ba(struct mt76_dev *dev, struct mt76_vif_link *mvif,
 
 /** starec & wtbl **/
 int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev,
-			 struct ieee80211_vif *vif,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
 	struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv;
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_link_sta *mlink;
-	struct mt792x_bss_conf *mconf;
-	unsigned long usable_links = ieee80211_vif_usable_links(vif);
-	struct mt76_wcid *wcid;
-	u8 link_id, ret;
-
-	for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) {
-		mconf = mt792x_vif_to_link(mvif, link_id);
-		mlink = mt792x_sta_to_link(msta, link_id);
-		wcid = &mlink->wcid;
-
-		if (enable && !params->amsdu)
-			mlink->wcid.amsdu = false;
+	struct mt792x_vif *mvif = msta->vif;
 
-		ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params,
-					enable, true);
-		if (ret < 0)
-			break;
-	}
+	if (enable && !params->amsdu)
+		msta->deflink.wcid.amsdu = false;
 
-	return ret;
+	return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, params,
+				 enable, true);
 }
 
 int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev,
-			 struct ieee80211_vif *vif,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable)
 {
 	struct mt792x_sta *msta = (struct mt792x_sta *)params->sta->drv_priv;
-	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-	struct mt792x_link_sta *mlink;
-	struct mt792x_bss_conf *mconf;
-	unsigned long usable_links = ieee80211_vif_usable_links(vif);
-	struct mt76_wcid *wcid;
-	u8 link_id, ret;
-
-	for_each_set_bit(link_id, &usable_links, IEEE80211_MLD_MAX_NUM_LINKS) {
-		mconf = mt792x_vif_to_link(mvif, link_id);
-		mlink = mt792x_sta_to_link(msta, link_id);
-		wcid = &mlink->wcid;
-
-		ret = mt7925_mcu_sta_ba(&dev->mt76, &mconf->mt76, wcid, params,
-					enable, false);
-		if (ret < 0)
-			break;
-	}
+	struct mt792x_vif *mvif = msta->vif;
 
-	return ret;
+	return mt7925_mcu_sta_ba(&dev->mt76, &mvif->bss_conf.mt76, params,
+				 enable, false);
 }
 
 static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index 8707b5d04743b..fd5f9d4ea4a7a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -263,11 +263,9 @@ int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev,
 				 struct ieee80211_vif *vif,
 				 bool enable);
 int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev,
-			 struct ieee80211_vif *vif,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
 int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev,
-			 struct ieee80211_vif *vif,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
 void mt7925_scan_work(struct work_struct *work);

From 4bada9b0a29c185d45cc9512509edd6069fbfa79 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:47 -0800
Subject: [PATCH 2280/2753] wifi: mt76: mt7925: fix the wrong link_idx when a
 p2p_device is present

When the p2p device and MLO station are running concurrently, the p2p device
will occupy the wrong link_idx when the MLO secondary link is added.

Fixes: 9e4c3a007f01 ("wifi: mt76: connac: Extend mt76_connac_mcu_uni_add_dev for MLO")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-2-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h          |  1 +
 .../net/wireless/mediatek/mt76/mt76_connac_mcu.c   |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt7925/main.c   | 14 ++++++++++----
 3 files changed, 13 insertions(+), 6 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 132148f7b1070..05651efb549ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -769,6 +769,7 @@ struct mt76_testmode_data {
 
 struct mt76_vif_link {
 	u8 idx;
+	u8 link_idx;
 	u8 omac_idx;
 	u8 band_idx;
 	u8 wmm_idx;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index f30cf9e716105..d0e49d68c5dbf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -1168,7 +1168,7 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 			.tag = cpu_to_le16(DEV_INFO_ACTIVE),
 			.len = cpu_to_le16(sizeof(struct req_tlv)),
 			.active = enable,
-			.link_idx = mvif->idx,
+			.link_idx = mvif->link_idx,
 		},
 	};
 	struct {
@@ -1191,7 +1191,7 @@ int mt76_connac_mcu_uni_add_dev(struct mt76_phy *phy,
 			.bmc_tx_wlan_idx = cpu_to_le16(wcid->idx),
 			.sta_idx = cpu_to_le16(wcid->idx),
 			.conn_state = 1,
-			.link_idx = mvif->idx,
+			.link_idx = mvif->link_idx,
 		},
 	};
 	int err, idx, cmd, len;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 47a6040381a0e..676882f3928ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -360,10 +360,15 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev,
 	struct mt76_txq *mtxq;
 	int idx, ret = 0;
 
-	mconf->mt76.idx = __ffs64(~dev->mt76.vif_mask);
-	if (mconf->mt76.idx >= MT792x_MAX_INTERFACES) {
-		ret = -ENOSPC;
-		goto out;
+	if (vif->type == NL80211_IFTYPE_P2P_DEVICE) {
+		mconf->mt76.idx = MT792x_MAX_INTERFACES;
+	} else {
+		mconf->mt76.idx = __ffs64(~dev->mt76.vif_mask);
+
+		if (mconf->mt76.idx >= MT792x_MAX_INTERFACES) {
+			ret = -ENOSPC;
+			goto out;
+		}
 	}
 
 	mconf->mt76.omac_idx = ieee80211_vif_is_mld(vif) ?
@@ -371,6 +376,7 @@ static int mt7925_mac_link_bss_add(struct mt792x_dev *dev,
 	mconf->mt76.band_idx = 0xff;
 	mconf->mt76.wmm_idx = ieee80211_vif_is_mld(vif) ?
 			      0 : mconf->mt76.idx % MT76_CONNAC_MAX_WMM_SETS;
+	mconf->mt76.link_idx = hweight16(mvif->valid_links);
 
 	if (mvif->phy->mt76->chandef.chan->band != NL80211_BAND_2GHZ)
 		mconf->mt76.basic_rates_idx = MT792x_BASIC_RATES_TBL + 4;

From 7dcea6fe33ee3d7cbb65baee0dd7adc76d1c9ddc Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:48 -0800
Subject: [PATCH 2281/2753] wifi: mt76: mt7925: fix the wrong simultaneous cap
 for MLO

The mt7925 chip is only support a single radio, so the maximum
number of simultaneous should be 0.

Fixes: 86c051f2c418 ("wifi: mt76: mt7925: enabling MLO when the firmware supports it")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-3-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 676882f3928ea..dd886b39f5500 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -256,7 +256,7 @@ int mt7925_init_mlo_caps(struct mt792x_phy *phy)
 
 	ext_capab[0].eml_capabilities = phy->eml_cap;
 	ext_capab[0].mld_capa_and_ops =
-		u16_encode_bits(1, IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS);
+		u16_encode_bits(0, IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS);
 
 	wiphy->flags |= WIPHY_FLAG_SUPPORTS_MLO;
 	wiphy->iftype_ext_capab = ext_capab;

From 0ebb60da8416c1d8e84c7e511a5687ce76a9467a Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:49 -0800
Subject: [PATCH 2282/2753] wifi: mt76: mt7925: adjust rm BSS flow to prevent
 next connection failure

Removing BSS without removing STAREC first will cause firmware
abnormal and next connection fail.

Fixes: 816161051a03 ("wifi: mt76: mt7925: Cleanup MLO settings post-disconnection")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-4-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/main.c  | 66 +++++++++----------
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 56 ++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7925/mcu.h   |  2 +
 3 files changed, 91 insertions(+), 33 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index dd886b39f5500..2f6c687d0a056 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1155,7 +1155,12 @@ static void mt7925_mac_link_sta_remove(struct mt76_dev *mdev,
 		struct mt792x_bss_conf *mconf;
 
 		mconf = mt792x_link_conf_to_mconf(link_conf);
-		mt792x_mac_link_bss_remove(dev, mconf, mlink);
+
+		if (ieee80211_vif_is_mld(vif))
+			mt792x_mac_link_bss_remove(dev, mconf, mlink);
+		else
+			mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf,
+						link_sta, false);
 	}
 
 	spin_lock_bh(&mdev->sta_poll_lock);
@@ -1175,6 +1180,31 @@ mt7925_mac_sta_remove_links(struct mt792x_dev *dev, struct ieee80211_vif *vif,
 	struct mt76_wcid *wcid;
 	unsigned int link_id;
 
+	/* clean up bss before starec */
+	for_each_set_bit(link_id, &old_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_link_sta *link_sta;
+		struct ieee80211_bss_conf *link_conf;
+		struct mt792x_bss_conf *mconf;
+		struct mt792x_link_sta *mlink;
+
+		link_sta = mt792x_sta_to_link_sta(vif, sta, link_id);
+		if (!link_sta)
+			continue;
+
+		mlink = mt792x_sta_to_link(msta, link_id);
+		if (!mlink)
+			continue;
+
+		link_conf = mt792x_vif_to_bss_conf(vif, link_id);
+		if (!link_conf)
+			continue;
+
+		mconf = mt792x_link_conf_to_mconf(link_conf);
+
+		mt7925_mcu_add_bss_info(&dev->phy, mconf->mt76.ctx, link_conf,
+					link_sta, false);
+	}
+
 	for_each_set_bit(link_id, &old_links, IEEE80211_MLD_MAX_NUM_LINKS) {
 		struct ieee80211_link_sta *link_sta;
 		struct mt792x_link_sta *mlink;
@@ -1212,44 +1242,14 @@ void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
-	struct {
-		struct {
-			u8 omac_idx;
-			u8 band_idx;
-			__le16 pad;
-		} __packed hdr;
-		struct req_tlv {
-			__le16 tag;
-			__le16 len;
-			u8 active;
-			u8 link_idx; /* hw link idx */
-			u8 omac_addr[ETH_ALEN];
-		} __packed tlv;
-	} dev_req = {
-		.hdr = {
-			.omac_idx = 0,
-			.band_idx = 0,
-		},
-		.tlv = {
-			.tag = cpu_to_le16(DEV_INFO_ACTIVE),
-			.len = cpu_to_le16(sizeof(struct req_tlv)),
-			.active = true,
-		},
-	};
 	unsigned long rem;
 
 	rem = ieee80211_vif_is_mld(vif) ? msta->valid_links : BIT(0);
 
 	mt7925_mac_sta_remove_links(dev, vif, sta, rem);
 
-	if (ieee80211_vif_is_mld(vif)) {
-		mt7925_mcu_set_dbdc(&dev->mphy, false);
-
-		/* recovery omac address for the legacy interface */
-		memcpy(dev_req.tlv.omac_addr, vif->addr, ETH_ALEN);
-		mt76_mcu_send_msg(mdev, MCU_UNI_CMD(DEV_INFO_UPDATE),
-				  &dev_req, sizeof(dev_req), true);
-	}
+	if (ieee80211_vif_is_mld(vif))
+		mt7925_mcu_del_dev(mdev, vif);
 
 	if (vif->type == NL80211_IFTYPE_STATION) {
 		struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index ebe7cc30aaf95..d970243d64ff3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -2634,6 +2634,62 @@ int mt7925_mcu_set_timing(struct mt792x_phy *phy,
 				     MCU_UNI_CMD(BSS_INFO_UPDATE), true);
 }
 
+void mt7925_mcu_del_dev(struct mt76_dev *mdev,
+			struct ieee80211_vif *vif)
+{
+	struct mt76_vif_link *mvif = (struct mt76_vif_link *)vif->drv_priv;
+	struct {
+		struct {
+			u8 omac_idx;
+			u8 band_idx;
+			__le16 pad;
+		} __packed hdr;
+		struct req_tlv {
+			__le16 tag;
+			__le16 len;
+			u8 active;
+			u8 link_idx; /* hw link idx */
+			u8 omac_addr[ETH_ALEN];
+		} __packed tlv;
+	} dev_req = {
+		.tlv = {
+			.tag = cpu_to_le16(DEV_INFO_ACTIVE),
+			.len = cpu_to_le16(sizeof(struct req_tlv)),
+			.active = true,
+		},
+	};
+	struct {
+		struct {
+			u8 bss_idx;
+			u8 pad[3];
+		} __packed hdr;
+		struct mt76_connac_bss_basic_tlv basic;
+	} basic_req = {
+		.basic = {
+			.tag = cpu_to_le16(UNI_BSS_INFO_BASIC),
+			.len = cpu_to_le16(sizeof(struct mt76_connac_bss_basic_tlv)),
+			.active = true,
+			.conn_state = 1,
+		},
+	};
+
+	dev_req.hdr.omac_idx = mvif->omac_idx;
+	dev_req.hdr.band_idx = mvif->band_idx;
+
+	basic_req.hdr.bss_idx = mvif->idx;
+	basic_req.basic.omac_idx = mvif->omac_idx;
+	basic_req.basic.band_idx = mvif->band_idx;
+	basic_req.basic.link_idx = mvif->link_idx;
+
+	mt76_mcu_send_msg(mdev, MCU_UNI_CMD(BSS_INFO_UPDATE),
+			  &basic_req, sizeof(basic_req), true);
+
+	/* recovery omac address for the legacy interface */
+	memcpy(dev_req.tlv.omac_addr, vif->addr, ETH_ALEN);
+	mt76_mcu_send_msg(mdev, MCU_UNI_CMD(DEV_INFO_UPDATE),
+			  &dev_req, sizeof(dev_req), true);
+}
+
 int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 			    struct ieee80211_chanctx_conf *ctx,
 			    struct ieee80211_bss_conf *link_conf,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
index 6bf1623e542eb..8ac43feb26d64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.h
@@ -627,6 +627,8 @@ int mt7925_mcu_sched_scan_req(struct mt76_phy *phy,
 int mt7925_mcu_sched_scan_enable(struct mt76_phy *phy,
 				 struct ieee80211_vif *vif,
 				 bool enable);
+void mt7925_mcu_del_dev(struct mt76_dev *mdev,
+			struct ieee80211_vif *vif);
 int mt7925_mcu_add_bss_info(struct mt792x_phy *phy,
 			    struct ieee80211_chanctx_conf *ctx,
 			    struct ieee80211_bss_conf *link_conf,

From cb1353ef34735ec1e5d9efa1fe966f05ff1dc1e1 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:50 -0800
Subject: [PATCH 2283/2753] wifi: mt76: mt7925: integrate *mlo_sta_cmd and
 *sta_cmd

Integrate *mlo_sta_cmd and *sta_cmd for the MLO firmware.

Fixes: 86c051f2c418 ("wifi: mt76: mt7925: enabling MLO when the firmware supports it")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-5-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 59 ++-----------------
 1 file changed, 4 insertions(+), 55 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index d970243d64ff3..17baa653dab15 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -1814,49 +1814,6 @@ mt7925_mcu_sta_mld_tlv(struct sk_buff *skb,
 	}
 }
 
-static int
-mt7925_mcu_sta_cmd(struct mt76_phy *phy,
-		   struct mt76_sta_cmd_info *info)
-{
-	struct mt76_vif_link *mvif = (struct mt76_vif_link *)info->vif->drv_priv;
-	struct mt76_dev *dev = phy->dev;
-	struct sk_buff *skb;
-	int conn_state;
-
-	skb = __mt76_connac_mcu_alloc_sta_req(dev, mvif, info->wcid,
-					      MT7925_STA_UPDATE_MAX_SIZE);
-	if (IS_ERR(skb))
-		return PTR_ERR(skb);
-
-	conn_state = info->enable ? CONN_STATE_PORT_SECURE :
-				    CONN_STATE_DISCONNECT;
-	if (info->link_sta)
-		mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf,
-					      info->link_sta,
-					      conn_state, info->newly);
-	if (info->link_sta && info->enable) {
-		mt7925_mcu_sta_phy_tlv(skb, info->vif, info->link_sta);
-		mt7925_mcu_sta_ht_tlv(skb, info->link_sta);
-		mt7925_mcu_sta_vht_tlv(skb, info->link_sta);
-		mt76_connac_mcu_sta_uapsd(skb, info->vif, info->link_sta->sta);
-		mt7925_mcu_sta_amsdu_tlv(skb, info->vif, info->link_sta);
-		mt7925_mcu_sta_he_tlv(skb, info->link_sta);
-		mt7925_mcu_sta_he_6g_tlv(skb, info->link_sta);
-		mt7925_mcu_sta_eht_tlv(skb, info->link_sta);
-		mt7925_mcu_sta_rate_ctrl_tlv(skb, info->vif,
-					     info->link_sta);
-		mt7925_mcu_sta_state_v2_tlv(phy, skb, info->link_sta,
-					    info->vif, info->rcpi,
-					    info->state);
-		mt7925_mcu_sta_mld_tlv(skb, info->vif, info->link_sta->sta);
-	}
-
-	if (info->enable)
-		mt7925_mcu_sta_hdr_trans_tlv(skb, info->vif, info->link_sta);
-
-	return mt76_mcu_skb_send_msg(dev, skb, info->cmd, true);
-}
-
 static void
 mt7925_mcu_sta_remove_tlv(struct sk_buff *skb)
 {
@@ -1869,8 +1826,8 @@ mt7925_mcu_sta_remove_tlv(struct sk_buff *skb)
 }
 
 static int
-mt7925_mcu_mlo_sta_cmd(struct mt76_phy *phy,
-		       struct mt76_sta_cmd_info *info)
+mt7925_mcu_sta_cmd(struct mt76_phy *phy,
+		   struct mt76_sta_cmd_info *info)
 {
 	struct mt792x_vif *mvif = (struct mt792x_vif *)info->vif->drv_priv;
 	struct mt76_dev *dev = phy->dev;
@@ -1884,12 +1841,10 @@ mt7925_mcu_mlo_sta_cmd(struct mt76_phy *phy,
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
-	if (info->enable)
+	if (info->enable && info->link_sta) {
 		mt76_connac_mcu_sta_basic_tlv(dev, skb, info->link_conf,
 					      info->link_sta,
 					      info->enable, info->newly);
-
-	if (info->enable && info->link_sta) {
 		mt7925_mcu_sta_phy_tlv(skb, info->vif, info->link_sta);
 		mt7925_mcu_sta_ht_tlv(skb, info->link_sta);
 		mt7925_mcu_sta_vht_tlv(skb, info->link_sta);
@@ -1940,7 +1895,6 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev,
 	};
 	struct mt792x_sta *msta;
 	struct mt792x_link_sta *mlink;
-	int err;
 
 	if (link_sta) {
 		msta = (struct mt792x_sta *)link_sta->sta->drv_priv;
@@ -1949,12 +1903,7 @@ int mt7925_mcu_sta_update(struct mt792x_dev *dev,
 	info.wcid = link_sta ? &mlink->wcid : &mvif->sta.deflink.wcid;
 	info.newly = state != MT76_STA_INFO_STATE_ASSOC;
 
-	if (ieee80211_vif_is_mld(vif))
-		err = mt7925_mcu_mlo_sta_cmd(&dev->mphy, &info);
-	else
-		err = mt7925_mcu_sta_cmd(&dev->mphy, &info);
-
-	return err;
+	return mt7925_mcu_sta_cmd(&dev->mphy, &info);
 }
 
 int mt7925_mcu_set_beacon_filter(struct mt792x_dev *dev,

From 276a568832577c81ec90b62dc506bbdc3781ca46 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 16:08:51 -0800
Subject: [PATCH 2284/2753] wifi: mt76: mt7925: update the power-saving flow

After joining MLO, ensure that all links are setup before
enabling power-saving.

Fixes: 86c051f2c418 ("wifi: mt76: mt7925: enabling MLO when the firmware supports it")
Cc: stable@vger.kernel.org
Co-developed-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Tested-by: Caleb Jorden <cjorden@gmail.com>
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250305000851.493671-6-sean.wang@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/init.c  |  1 +
 .../net/wireless/mediatek/mt76/mt7925/main.c  | 68 ++++++++++++++++---
 .../wireless/mediatek/mt76/mt7925/mt7925.h    |  1 +
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  9 +++
 4 files changed, 68 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index f41ca42484978..a2bb36dab2310 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -244,6 +244,7 @@ int mt7925_register_device(struct mt792x_dev *dev)
 	dev->mt76.tx_worker.fn = mt792x_tx_worker;
 
 	INIT_DELAYED_WORK(&dev->pm.ps_work, mt792x_pm_power_save_work);
+	INIT_DELAYED_WORK(&dev->mlo_pm_work, mt7925_mlo_pm_work);
 	INIT_WORK(&dev->pm.wake_work, mt792x_pm_wake_work);
 	spin_lock_init(&dev->pm.wake.lock);
 	mutex_init(&dev->pm.mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 2f6c687d0a056..0b390b2691e3f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -427,6 +427,7 @@ mt7925_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	mvif->bss_conf.vif = mvif;
 	mvif->sta.vif = mvif;
 	mvif->deflink_id = IEEE80211_LINK_UNSPECIFIED;
+	mvif->mlo_pm_state = MT792x_MLO_LINK_DISASSOC;
 
 	ret = mt7925_mac_link_bss_add(dev, &vif->bss_conf, &mvif->sta.deflink);
 	if (ret < 0)
@@ -1242,6 +1243,7 @@ void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt792x_dev *dev = container_of(mdev, struct mt792x_dev, mt76);
 	struct mt792x_sta *msta = (struct mt792x_sta *)sta->drv_priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
 	unsigned long rem;
 
 	rem = ieee80211_vif_is_mld(vif) ? msta->valid_links : BIT(0);
@@ -1252,11 +1254,11 @@ void mt7925_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		mt7925_mcu_del_dev(mdev, vif);
 
 	if (vif->type == NL80211_IFTYPE_STATION) {
-		struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
-
 		mvif->wep_sta = NULL;
 		ewma_rssi_init(&mvif->bss_conf.rssi);
 	}
+
+	mvif->mlo_pm_state = MT792x_MLO_LINK_DISASSOC;
 }
 EXPORT_SYMBOL_GPL(mt7925_mac_sta_remove);
 
@@ -1328,6 +1330,38 @@ mt7925_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	return ret;
 }
 
+static void
+mt7925_mlo_pm_iter(void *priv, u8 *mac, struct ieee80211_vif *vif)
+{
+	struct mt792x_dev *dev = priv;
+	struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+	unsigned long valid = ieee80211_vif_is_mld(vif) ?
+				    mvif->valid_links : BIT(0);
+	struct ieee80211_bss_conf *bss_conf;
+	int i;
+
+	if (mvif->mlo_pm_state != MT792x_MLO_CHANGED_PS)
+		return;
+
+	mt792x_mutex_acquire(dev);
+	for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
+		bss_conf = mt792x_vif_to_bss_conf(vif, i);
+		mt7925_mcu_uni_bss_ps(dev, bss_conf);
+	}
+	mt792x_mutex_release(dev);
+}
+
+void mt7925_mlo_pm_work(struct work_struct *work)
+{
+	struct mt792x_dev *dev = container_of(work, struct mt792x_dev,
+					      mlo_pm_work.work);
+	struct ieee80211_hw *hw = mt76_hw(dev);
+
+	ieee80211_iterate_active_interfaces(hw,
+					    IEEE80211_IFACE_ITER_RESUME_ALL,
+					    mt7925_mlo_pm_iter, dev);
+}
+
 static bool is_valid_alpha2(const char *alpha2)
 {
 	if (!alpha2)
@@ -1877,6 +1911,9 @@ static void mt7925_vif_cfg_changed(struct ieee80211_hw *hw,
 		mt7925_mcu_sta_update(dev, NULL, vif, true,
 				      MT76_STA_INFO_STATE_ASSOC);
 		mt7925_mcu_set_beacon_filter(dev, vif, vif->cfg.assoc);
+
+		if (ieee80211_vif_is_mld(vif))
+			mvif->mlo_pm_state = MT792x_MLO_LINK_ASSOC;
 	}
 
 	if (changed & BSS_CHANGED_ARP_FILTER) {
@@ -1887,9 +1924,19 @@ static void mt7925_vif_cfg_changed(struct ieee80211_hw *hw,
 	}
 
 	if (changed & BSS_CHANGED_PS) {
-		for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
-			bss_conf = mt792x_vif_to_bss_conf(vif, i);
+		if (hweight16(mvif->valid_links) < 2) {
+			/* legacy */
+			bss_conf = &vif->bss_conf;
 			mt7925_mcu_uni_bss_ps(dev, bss_conf);
+		} else {
+			if (mvif->mlo_pm_state == MT792x_MLO_LINK_ASSOC) {
+				mvif->mlo_pm_state = MT792x_MLO_CHANGED_PS_PENDING;
+			} else if (mvif->mlo_pm_state == MT792x_MLO_CHANGED_PS) {
+				for_each_set_bit(i, &valid, IEEE80211_MLD_MAX_NUM_LINKS) {
+					bss_conf = mt792x_vif_to_bss_conf(vif, i);
+					mt7925_mcu_uni_bss_ps(dev, bss_conf);
+				}
+			}
 		}
 	}
 
@@ -1940,11 +1987,12 @@ static void mt7925_link_info_changed(struct ieee80211_hw *hw,
 	if (changed & (BSS_CHANGED_QOS | BSS_CHANGED_BEACON_ENABLED))
 		mt7925_mcu_set_tx(dev, info);
 
-	if (changed & BSS_CHANGED_BSSID) {
-		if (ieee80211_vif_is_mld(vif) &&
-		    hweight16(mvif->valid_links) == 2)
-			/* Indicate the secondary setup done */
-			mt7925_mcu_uni_bss_bcnft(dev, info, true);
+	if (mvif->mlo_pm_state == MT792x_MLO_CHANGED_PS_PENDING) {
+		/* Indicate the secondary setup done */
+		mt7925_mcu_uni_bss_bcnft(dev, info, true);
+
+		ieee80211_queue_delayed_work(hw, &dev->mlo_pm_work, 5 * HZ);
+		mvif->mlo_pm_state = MT792x_MLO_CHANGED_PS;
 	}
 
 	mt792x_mutex_release(dev);
@@ -2028,8 +2076,6 @@ mt7925_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			goto free;
 
 		if (mconf != &mvif->bss_conf) {
-			mt7925_mcu_set_bss_pm(dev, link_conf, true);
-
 			err = mt7925_set_mlo_roc(phy, &mvif->bss_conf,
 						 vif->active_links);
 			if (err < 0)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index fd5f9d4ea4a7a..cb7b1a49fbd14 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -268,6 +268,7 @@ int mt7925_mcu_uni_tx_ba(struct mt792x_dev *dev,
 int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool enable);
+void mt7925_mlo_pm_work(struct work_struct *work);
 void mt7925_scan_work(struct work_struct *work);
 void mt7925_roc_work(struct work_struct *work);
 int mt7925_mcu_uni_bss_ps(struct mt792x_dev *dev,
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 454c6f523cc22..048f9ab161263 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -82,6 +82,13 @@ enum mt792x_reg_power_type {
 	MT_AP_VLP,
 };
 
+enum mt792x_mlo_pm_state {
+	MT792x_MLO_LINK_DISASSOC,
+	MT792x_MLO_LINK_ASSOC,
+	MT792x_MLO_CHANGED_PS_PENDING,
+	MT792x_MLO_CHANGED_PS,
+};
+
 DECLARE_EWMA(avg_signal, 10, 8)
 
 struct mt792x_link_sta {
@@ -135,6 +142,7 @@ struct mt792x_vif {
 	struct mt792x_phy *phy;
 	u16 valid_links;
 	u8 deflink_id;
+	enum mt792x_mlo_pm_state mlo_pm_state;
 
 	struct work_struct csa_work;
 	struct timer_list csa_timer;
@@ -240,6 +248,7 @@ struct mt792x_dev {
 	const struct mt792x_irq_map *irq_map;
 
 	struct work_struct ipv6_ns_work;
+	struct delayed_work mlo_pm_work;
 	/* IPv6 addresses for WoWLAN */
 	struct sk_buff_head ipv6_ns_list;
 

From f2027ef3f733d3f0bb7f27fa3343784058f946ab Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:44 +0800
Subject: [PATCH 2285/2753] wifi: mt76: mt7925: load the appropriate CLC data
 based on hardware type

Read the EEPROM to determine the hardware type and uses this to load the
correct CLC data.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 61 ++++++++++++++++++-
 .../wireless/mediatek/mt76/mt7925/mt7925.h    |  3 +
 2 files changed, 63 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 17baa653dab15..0f58a5afb77a5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -627,6 +627,54 @@ int mt7925_mcu_uni_rx_ba(struct mt792x_dev *dev,
 				 enable, false);
 }
 
+static int mt7925_mcu_read_eeprom(struct mt792x_dev *dev, u32 offset, u8 *val)
+{
+	struct {
+		u8 rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		__le32 addr;
+		__le32 valid;
+		u8 data[MT7925_EEPROM_BLOCK_SIZE];
+	} __packed req = {
+		.tag = cpu_to_le16(1),
+		.len = cpu_to_le16(sizeof(req) - 4),
+		.addr = cpu_to_le32(round_down(offset,
+				    MT7925_EEPROM_BLOCK_SIZE)),
+	};
+	struct evt {
+		u8 rsv[4];
+
+		__le16 tag;
+		__le16 len;
+
+		__le32 ver;
+		__le32 addr;
+		__le32 valid;
+		__le32 size;
+		__le32 magic_num;
+		__le32 type;
+		__le32 rsv1[4];
+		u8 data[32];
+	} __packed *res;
+	struct sk_buff *skb;
+	int ret;
+
+	ret = mt76_mcu_send_and_get_msg(&dev->mt76, MCU_WM_UNI_CMD_QUERY(EFUSE_CTRL),
+					&req, sizeof(req), true, &skb);
+	if (ret)
+		return ret;
+
+	res = (struct evt *)skb->data;
+	*val = res->data[offset % MT7925_EEPROM_BLOCK_SIZE];
+
+	dev_kfree_skb(skb);
+
+	return 0;
+}
+
 static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 {
 	const struct mt76_connac2_fw_trailer *hdr;
@@ -635,13 +683,20 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	struct mt76_dev *mdev = &dev->mt76;
 	struct mt792x_phy *phy = &dev->phy;
 	const struct firmware *fw;
+	u8 *clc_base = NULL, hw_encap = 0;
 	int ret, i, len, offset = 0;
-	u8 *clc_base = NULL;
 
 	if (mt7925_disable_clc ||
 	    mt76_is_usb(&dev->mt76))
 		return 0;
 
+	if (mt76_is_mmio(&dev->mt76)) {
+		ret = mt7925_mcu_read_eeprom(dev, MT_EE_HW_TYPE, &hw_encap);
+		if (ret)
+			return ret;
+		hw_encap = u8_get_bits(hw_encap, MT_EE_HW_TYPE_ENCAP);
+	}
+
 	ret = request_firmware(&fw, fw_name, mdev->dev);
 	if (ret)
 		return ret;
@@ -686,6 +741,10 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 		if (phy->clc[clc->idx])
 			continue;
 
+		/* header content sanity */
+		if (u8_get_bits(clc->type, MT_EE_HW_TYPE_ENCAP) != hw_encap)
+			continue;
+
 		phy->clc[clc->idx] = devm_kmemdup(mdev->dev, clc,
 						  le32_to_cpu(clc->len),
 						  GFP_KERNEL);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index cb7b1a49fbd14..073e433069e0e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -167,9 +167,12 @@ enum mt7925_eeprom_field {
 	MT_EE_CHIP_ID =		0x000,
 	MT_EE_VERSION =		0x002,
 	MT_EE_MAC_ADDR =	0x004,
+	MT_EE_HW_TYPE =		0xa71,
 	__MT_EE_MAX =		0x9ff
 };
 
+#define MT_EE_HW_TYPE_ENCAP     GENMASK(1, 0)
+
 enum {
 	TXPWR_USER,
 	TXPWR_EEPROM,

From f0317215b367e22e1cde5dcdb4c0687f0a85b913 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:45 +0800
Subject: [PATCH 2286/2753] wifi: mt76: mt7925: add EHT control support based
 on the CLC data

Some countries do not support EHT modulation for now. To prevent violating
regulations, the MT7925 chipset should control the EHT capabilities.
Therefore, when a regulatory domain change is detected during scanning,
the `mt7925_regd_be_ctrl` will process the CLC data to update the EHT
capabilities.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-2-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/init.c  | 38 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7925/main.c  |  2 +
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   | 10 +++--
 .../wireless/mediatek/mt76/mt7925/mt7925.h    | 27 +++++++++++--
 drivers/net/wireless/mediatek/mt76/mt792x.h   |  1 +
 5 files changed, 71 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index a2bb36dab2310..46b12a2e81ee2 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -58,6 +58,44 @@ static int mt7925_thermal_init(struct mt792x_phy *phy)
 	return PTR_ERR_OR_ZERO(hwmon);
 }
 
+void mt7925_regd_be_ctrl(struct mt792x_dev *dev, u8 *alpha2)
+{
+	struct mt792x_phy *phy = &dev->phy;
+	struct mt7925_clc_rule_v2 *rule;
+	struct mt7925_clc *clc;
+	bool old = dev->has_eht, new = true;
+	u8 *pos;
+
+	if (!phy->clc[MT792x_CLC_BE_CTRL])
+		goto out;
+
+	clc = (struct mt7925_clc *)phy->clc[MT792x_CLC_BE_CTRL];
+	pos = clc->data;
+
+	while (1) {
+		rule = (struct mt7925_clc_rule_v2 *)pos;
+
+		if (rule->alpha2[0] == alpha2[0] &&
+		    rule->alpha2[1] == alpha2[1]) {
+			new = false;
+			break;
+		}
+
+		/* Check the last one */
+		if (rule->flag && BIT(0))
+			break;
+
+		pos += sizeof(*rule);
+	}
+
+out:
+	if (old == new)
+		return;
+
+	dev->has_eht = new;
+	mt7925_set_stream_he_eht_caps(phy);
+}
+
 void mt7925_regd_update(struct mt792x_dev *dev)
 {
 	struct mt76_dev *mdev = &dev->mt76;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/main.c b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
index 0b390b2691e3f..e79364ac129ee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/main.c
@@ -1418,6 +1418,8 @@ void mt7925_scan_work(struct work_struct *work)
 				if (!is_valid_alpha2(evt->alpha2))
 					break;
 
+				mt7925_regd_be_ctrl(phy->dev, evt->alpha2);
+
 				if (mdev->alpha2[0] != '0' && mdev->alpha2[1] != '0')
 					break;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 0f58a5afb77a5..575b51931d7d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -742,7 +742,9 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 			continue;
 
 		/* header content sanity */
-		if (u8_get_bits(clc->type, MT_EE_HW_TYPE_ENCAP) != hw_encap)
+		if ((clc->idx == MT792x_CLC_BE_CTRL &&
+		     u8_get_bits(clc->t2.type, MT_EE_HW_TYPE_ENCAP) != hw_encap) ||
+		    u8_get_bits(clc->t0.type, MT_EE_HW_TYPE_ENCAP) != hw_encap)
 			continue;
 
 		phy->clc[clc->idx] = devm_kmemdup(mdev->dev, clc,
@@ -851,7 +853,6 @@ mt7925_mcu_parse_phy_cap(struct mt792x_dev *dev, char *data)
 	mdev->phy.chainmask = mdev->phy.antenna_mask;
 	mdev->phy.cap.has_2ghz = cap->hw_path & BIT(WF0_24G);
 	mdev->phy.cap.has_5ghz = cap->hw_path & BIT(WF0_5G);
-	dev->has_eht = cap->eht;
 }
 
 static void
@@ -3193,7 +3194,7 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 	if (!clc)
 		return 0;
 
-	pos = clc->data + sizeof(*seg) * clc->nr_seg;
+	pos = clc->data + sizeof(*seg) * clc->t0.nr_seg;
 	last_pos = clc->data + le32_to_cpu(*(__le32 *)(clc->data + 4));
 	while (pos < last_pos) {
 		struct mt7925_clc_rule *rule = (struct mt7925_clc_rule *)pos;
@@ -3239,6 +3240,9 @@ int mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 
 	/* submit all clc config */
 	for (i = 0; i < ARRAY_SIZE(phy->clc); i++) {
+		if (i == MT792x_CLC_BE_CTRL)
+			continue;
+
 		ret = __mt7925_mcu_set_clc(dev, alpha2, env_cap,
 					   phy->clc[i], i);
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index 073e433069e0e..5cd3073dfc504 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -137,6 +137,12 @@ enum {
 	MT7925_CLC_MAX_NUM,
 };
 
+struct mt7925_clc_rule_v2 {
+	u32 flag;
+	u8 alpha2[2];
+	u8 rsv[10];
+} __packed;
+
 struct mt7925_clc_rule {
 	u8 alpha2[2];
 	u8 type[2];
@@ -152,14 +158,26 @@ struct mt7925_clc_segment {
 	u8 rsv2[4];
 } __packed;
 
-struct mt7925_clc {
-	__le32 len;
-	u8 idx;
-	u8 ver;
+struct mt7925_clc_type0 {
 	u8 nr_country;
 	u8 type;
 	u8 nr_seg;
 	u8 rsv[7];
+} __packed;
+
+struct mt7925_clc_type2 {
+	u8 type;
+	u8 rsv[9];
+} __packed;
+
+struct mt7925_clc {
+	__le32 len;
+	u8 idx;
+	u8 ver;
+	union {
+		struct mt7925_clc_type0 t0;
+		struct mt7925_clc_type2 t2;
+	};
 	u8 data[];
 } __packed;
 
@@ -238,6 +256,7 @@ int mt7925_mcu_chip_config(struct mt792x_dev *dev, const char *cmd);
 int mt7925_mcu_set_rxfilter(struct mt792x_dev *dev, u32 fif,
 			    u8 bit_op, u32 bit_map);
 
+void mt7925_regd_be_ctrl(struct mt792x_dev *dev, u8 *alpha2);
 void mt7925_regd_update(struct mt792x_dev *dev);
 int mt7925_mac_init(struct mt792x_dev *dev);
 int mt7925_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 048f9ab161263..97e9de88a63d8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -71,6 +71,7 @@ struct mt792x_fw_features {
 enum {
 	MT792x_CLC_POWER,
 	MT792x_CLC_POWER_EXT,
+	MT792x_CLC_BE_CTRL,
 	MT792x_CLC_MAX_NUM,
 };
 

From 91b3790240b5114a07a5d14a33e48d6c99350496 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:46 +0800
Subject: [PATCH 2287/2753] wifi: mt76: mt7925: update the channel usage when
 the regd domain changed

The 5.9/6GHz channel license of a certain platform device has been
regulated in various countries. That may be difference with standard Liunx
regulatory domain settings. In this case, when .reg_notifier() called for
regulatory change, mt7925 chipset should update the channel usage based on
CLC data.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-3-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/init.c  | 40 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7925/mcu.c   |  7 +++-
 .../wireless/mediatek/mt76/mt7925/mt7925.h    |  3 +-
 3 files changed, 48 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 46b12a2e81ee2..8732b05355dbc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -96,15 +96,55 @@ void mt7925_regd_be_ctrl(struct mt792x_dev *dev, u8 *alpha2)
 	mt7925_set_stream_he_eht_caps(phy);
 }
 
+static void
+mt7925_regd_channel_update(struct wiphy *wiphy, struct mt792x_dev *dev)
+{
+#define IS_UNII_INVALID(idx, sfreq, efreq, cfreq) \
+	(!(dev->phy.clc_chan_conf & BIT(idx)) && (cfreq) >= (sfreq) && (cfreq) <= (efreq))
+	struct ieee80211_supported_band *sband;
+	struct mt76_dev *mdev = &dev->mt76;
+	struct ieee80211_channel *ch;
+	int i;
+
+	sband = wiphy->bands[NL80211_BAND_5GHZ];
+	if (!sband)
+		return;
+
+	for (i = 0; i < sband->n_channels; i++) {
+		ch = &sband->channels[i];
+
+		/* UNII-4 */
+		if (IS_UNII_INVALID(0, 5845, 5925, ch->center_freq))
+			ch->flags |= IEEE80211_CHAN_DISABLED;
+	}
+
+	sband = wiphy->bands[NL80211_BAND_6GHZ];
+	if (!sband)
+		return;
+
+	for (i = 0; i < sband->n_channels; i++) {
+		ch = &sband->channels[i];
+
+		/* UNII-5/6/7/8 */
+		if (IS_UNII_INVALID(1, 5925, 6425, ch->center_freq) ||
+		    IS_UNII_INVALID(2, 6425, 6525, ch->center_freq) ||
+		    IS_UNII_INVALID(3, 6525, 6875, ch->center_freq) ||
+		    IS_UNII_INVALID(4, 6875, 7125, ch->center_freq))
+			ch->flags |= IEEE80211_CHAN_DISABLED;
+	}
+}
+
 void mt7925_regd_update(struct mt792x_dev *dev)
 {
 	struct mt76_dev *mdev = &dev->mt76;
 	struct ieee80211_hw *hw = mdev->hw;
+	struct wiphy *wiphy = hw->wiphy;
 
 	if (!dev->regd_change)
 		return;
 
 	mt7925_mcu_set_clc(dev, mdev->alpha2, dev->country_ie_env);
+	mt7925_regd_channel_update(wiphy, dev);
 	mt7925_mcu_set_channel_domain(hw->priv);
 	mt7925_set_tx_sar_pwr(hw, NULL);
 	dev->regd_change = false;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 575b51931d7d4..30f88a9dcded3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -686,6 +686,7 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
 	u8 *clc_base = NULL, hw_encap = 0;
 	int ret, i, len, offset = 0;
 
+	dev->phy.clc_chan_conf = 0xff;
 	if (mt7925_disable_clc ||
 	    mt76_is_usb(&dev->mt76))
 		return 0;
@@ -3194,6 +3195,7 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 	if (!clc)
 		return 0;
 
+	req.ver = clc->ver;
 	pos = clc->data + sizeof(*seg) * clc->t0.nr_seg;
 	last_pos = clc->data + le32_to_cpu(*(__le32 *)(clc->data + 4));
 	while (pos < last_pos) {
@@ -3211,6 +3213,7 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		memcpy(req.type, rule->type, 2);
 
 		req.size = cpu_to_le16(seg->len);
+		dev->phy.clc_chan_conf = clc->ver == 1 ? 0xff : rule->flag;
 		skb = __mt76_mcu_msg_alloc(&dev->mt76, &req,
 					   le16_to_cpu(req.size) + sizeof(req),
 					   sizeof(req), GFP_KERNEL);
@@ -3226,8 +3229,10 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 		valid_cnt++;
 	}
 
-	if (!valid_cnt)
+	if (!valid_cnt) {
+		dev->phy.clc_chan_conf = 0xff;
 		return -ENOENT;
+	}
 
 	return 0;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
index 5cd3073dfc504..4e50f2597ccd4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mt7925.h
@@ -147,7 +147,8 @@ struct mt7925_clc_rule {
 	u8 alpha2[2];
 	u8 type[2];
 	u8 seg_idx;
-	u8 rsv[3];
+	u8 flag; /* UNII4~8 ctrl flag */
+	u8 rsv[2];
 } __packed;
 
 struct mt7925_clc_segment {

From b4ea6fdfc08375aae59c7e7059653b9877171fe4 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:47 +0800
Subject: [PATCH 2288/2753] wifi: mt76: mt7925: remove unused acpi function for
 clc

The code for handling ACPI configuration in CLC was copied from the mt7921
driver but is not utilized in the mt7925 implementation. So removes the
unused functionality to clean up the codebase.

Cc: stable@vger.kernel.org
Fixes: c948b5da6bbe ("wifi: mt76: mt7925: add Mediatek Wi-Fi7 driver for mt7925 chips")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-4-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7925/mcu.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
index 30f88a9dcded3..e61da76b2097b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
@@ -3187,7 +3187,6 @@ __mt7925_mcu_set_clc(struct mt792x_dev *dev, u8 *alpha2,
 
 		.idx = idx,
 		.env = env_cap,
-		.acpi_conf = mt792x_acpi_get_flags(&dev->phy),
 	};
 	int ret, valid_cnt = 0;
 	u8 *pos, *last_pos;

From 7cebc2300de2c6948792c5b9bee8937f219b58f7 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:48 +0800
Subject: [PATCH 2289/2753] wifi: mt76: mt792x: extend MTCL of APCI to version3
 for EHT control

This patch introduces version 3 of the MTCL table, which provides
regulatory information for WiFi 7. It also configured by the platform
vender like the version 1 and 2.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-5-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt792x.h   |   6 +-
 .../wireless/mediatek/mt76/mt792x_acpi_sar.c  | 123 ++++++++++++++----
 .../wireless/mediatek/mt76/mt792x_acpi_sar.h  |  18 ++-
 3 files changed, 120 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt792x.h b/drivers/net/wireless/mediatek/mt76/mt792x.h
index 97e9de88a63d8..e0359d431eca9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x.h
@@ -508,7 +508,7 @@ int mt792xe_mcu_fw_pmctrl(struct mt792x_dev *dev);
 int mt792x_init_acpi_sar(struct mt792x_dev *dev);
 int mt792x_init_acpi_sar_power(struct mt792x_phy *phy, bool set_default);
 u8 mt792x_acpi_get_flags(struct mt792x_phy *phy);
-u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2);
+u32 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2);
 #else
 static inline int mt792x_init_acpi_sar(struct mt792x_dev *dev)
 {
@@ -526,9 +526,9 @@ static inline u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
 	return 0;
 }
 
-static inline u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
+static inline u32 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
 {
-	return 0xf;
+	return MT792X_ACPI_MTCL_INVALID;
 }
 #endif
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
index 9317f8ff2070f..d1aebadd50aac 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.c
@@ -4,6 +4,28 @@
 #include <linux/acpi.h>
 #include "mt792x.h"
 
+static const char * const cc_list_all[] = {
+	"00", "EU", "AR", "AU", "AZ", "BY", "BO", "BR",
+	"CA", "CL", "CN", "ID", "JP", "MY", "MX", "ME",
+	"MA", "NZ", "NG", "PH", "RU", "RS", "SG", "KR",
+	"TW", "TH", "UA", "GB", "US", "VN", "KH", "PY",
+};
+
+static const char * const cc_list_eu[] = {
+	"AD", "AT", "BE", "BG", "CY", "CZ", "HR", "DK",
+	"EE", "FI", "FR", "DE", "GR", "HU", "IS", "IE",
+	"IT", "LV", "LI", "LT", "LU", "MC", "MT", "NL",
+	"NO", "PL", "PT", "RO", "SK", "SI", "ES", "SE",
+	"CH",
+};
+
+static const char * const cc_list_be[] = {
+	"AR", "BR", "BY", "CL", "IQ", "MX", "OM", "RU",
+	"RW", "VN", "KR", "UA", "", "", "", "",
+	"EU", "AT", "CN", "CA", "TW", "NZ", "PH", "UK",
+	"US",
+};
+
 static int
 mt792x_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
 {
@@ -66,13 +88,22 @@ mt792x_acpi_read(struct mt792x_dev *dev, u8 *method, u8 **tbl, u32 *len)
 }
 
 /* MTCL : Country List Table for 6G band */
+/* MTCL : Country List Table for 6G band and 11BE */
 static int
 mt792x_asar_acpi_read_mtcl(struct mt792x_dev *dev, u8 **table, u8 *version)
 {
-	int ret;
+	int len, ret;
 
-	*version = ((ret = mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, NULL)) < 0)
-		   ? 1 : 2;
+	ret = mt792x_acpi_read(dev, MT792x_ACPI_MTCL, table, &len);
+	if (ret)
+		return ret;
+
+	if (len == sizeof(struct mt792x_asar_cl))
+		*version = ((struct mt792x_asar_cl *)*table)->version;
+	else if (len == sizeof(struct mt792x_asar_cl_v3))
+		*version = ((struct mt792x_asar_cl_v3 *)*table)->version;
+	else
+		return -EINVAL;
 
 	return ret;
 }
@@ -351,10 +382,24 @@ u8 mt792x_acpi_get_flags(struct mt792x_phy *phy)
 }
 EXPORT_SYMBOL_GPL(mt792x_acpi_get_flags);
 
-static u8
+static u32
+mt792x_acpi_get_mtcl_map_v3(int row, int column, struct mt792x_asar_cl_v3 *cl)
+{
+	u32 config = 0;
+	u8 mode_be = 0;
+
+	mode_be = (cl->mode_be > 0x02) ? 0 : cl->mode_be;
+
+	if (cl->version > 2 && cl->clbe[row] & BIT(column))
+		config |= (mode_be & 0x3) << 4;
+
+	return config;
+}
+
+static u32
 mt792x_acpi_get_mtcl_map(int row, int column, struct mt792x_asar_cl *cl)
 {
-	u8 config = 0;
+	u32 config = 0;
 	u8 mode_6g, mode_5g9;
 
 	mode_6g = (cl->mode_6g > 0x02) ? 0 : cl->mode_6g;
@@ -368,30 +413,44 @@ mt792x_acpi_get_mtcl_map(int row, int column, struct mt792x_asar_cl *cl)
 	return config;
 }
 
-u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
+static u32
+mt792x_acpi_parse_mtcl_tbl_v3(struct mt792x_phy *phy, char *alpha2)
 {
-	static const char * const cc_list_all[] = {
-		"00", "EU", "AR", "AU", "AZ", "BY", "BO", "BR",
-		"CA", "CL", "CN", "ID", "JP", "MY", "MX", "ME",
-		"MA", "NZ", "NG", "PH", "RU", "RS", "SG", "KR",
-		"TW", "TH", "UA", "GB", "US", "VN", "KH", "PY",
-	};
-	static const char * const cc_list_eu[] = {
-		"AT", "BE", "BG", "CY", "CZ", "HR", "DK", "EE",
-		"FI", "FR", "DE", "GR", "HU", "IS", "IE", "IT",
-		"LV", "LI", "LT", "LU", "MT", "NL", "NO", "PL",
-		"PT", "RO", "SK", "SI", "ES", "SE", "CH",
-	};
 	struct mt792x_acpi_sar *sar = phy->acpisar;
-	struct mt792x_asar_cl *cl;
+	struct mt792x_asar_cl_v3 *cl = sar->countrylist_v3;
 	int col, row, i;
 
-	if (!sar)
-		return 0xf;
+	if (sar->ver != 3)
+		goto out;
 
-	cl = sar->countrylist;
 	if (!cl)
-		return 0xc;
+		return MT792X_ACPI_MTCL_INVALID;
+
+	for (i = 0; i < ARRAY_SIZE(cc_list_be); i++) {
+		col = 7 - i % 8;
+		row = i / 8;
+		if (!memcmp(cc_list_be[i], alpha2, 2))
+			return mt792x_acpi_get_mtcl_map_v3(row, col, cl);
+	}
+	for (i = 0; i < ARRAY_SIZE(cc_list_eu); i++) {
+		if (!memcmp(cc_list_eu[i], alpha2, 2))
+			return mt792x_acpi_get_mtcl_map_v3(3, 7, cl);
+	}
+
+out:
+	/* Depends on driver */
+	return 0x20;
+}
+
+static u32
+mt792x_acpi_parse_mtcl_tbl(struct mt792x_phy *phy, char *alpha2)
+{
+	struct mt792x_acpi_sar *sar = phy->acpisar;
+	struct mt792x_asar_cl *cl = sar->countrylist;
+	int col, row, i;
+
+	if (!cl)
+		return MT792X_ACPI_MTCL_INVALID;
 
 	for (i = 0; i < ARRAY_SIZE(cc_list_all); i++) {
 		col = 7 - i % 8;
@@ -406,4 +465,22 @@ u8 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
 
 	return mt792x_acpi_get_mtcl_map(0, 7, cl);
 }
+
+u32 mt792x_acpi_get_mtcl_conf(struct mt792x_phy *phy, char *alpha2)
+{
+	struct mt792x_acpi_sar *sar = phy->acpisar;
+	u32 config = 0;
+
+	if (!sar)
+		return MT792X_ACPI_MTCL_INVALID;
+
+	config = mt792x_acpi_parse_mtcl_tbl_v3(phy, alpha2);
+
+	if (config == MT792X_ACPI_MTCL_INVALID)
+		return MT792X_ACPI_MTCL_INVALID;
+
+	config |= mt792x_acpi_parse_mtcl_tbl(phy, alpha2);
+
+	return config;
+}
 EXPORT_SYMBOL_GPL(mt792x_acpi_get_mtcl_conf);
diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
index 2298983b6342f..e45dcd7fbdb18 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_acpi_sar.h
@@ -15,6 +15,8 @@
 #define MT792x_ACPI_MTGS		"MTGS"
 #define MT792x_ACPI_MTFG		"MTFG"
 
+#define MT792X_ACPI_MTCL_INVALID	0xffffffff
+
 struct mt792x_asar_dyn_limit {
 	u8 idx;
 	u8 frp[5];
@@ -72,6 +74,17 @@ struct mt792x_asar_geo_v2 {
 	DECLARE_FLEX_ARRAY(struct mt792x_asar_geo_limit_v2, tbl);
 } __packed;
 
+struct mt792x_asar_cl_v3 {
+	u8 names[4];
+	u8 version;
+	u8 mode_6g;
+	u8 cl6g[6];
+	u8 mode_5g9;
+	u8 cl5g9[6];
+	u8 mode_be;
+	u8 clbe[6];
+} __packed;
+
 struct mt792x_asar_cl {
 	u8 names[4];
 	u8 version;
@@ -100,7 +113,10 @@ struct mt792x_acpi_sar {
 		struct mt792x_asar_geo *geo;
 		struct mt792x_asar_geo_v2 *geo_v2;
 	};
-	struct mt792x_asar_cl *countrylist;
+	union {
+		struct mt792x_asar_cl *countrylist;
+		struct mt792x_asar_cl_v3 *countrylist_v3;
+	};
 	struct mt792x_asar_fg *fg;
 };
 

From 51ac8dbb706a6a88dbe289205aeb22e4013e5885 Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Tue, 4 Mar 2025 19:36:49 +0800
Subject: [PATCH 2290/2753] wifi: mt76: mt7925: add MTCL support to enhance the
 regulatory compliance

Apply the MTCL configuration to improving channel availability and
regulatory compliance if MTCL table is supported.

Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250304113649.867387-6-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7925/init.c    | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/init.c b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
index 8732b05355dbc..63cb08f4d87cc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7925/init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7925/init.c
@@ -64,8 +64,15 @@ void mt7925_regd_be_ctrl(struct mt792x_dev *dev, u8 *alpha2)
 	struct mt7925_clc_rule_v2 *rule;
 	struct mt7925_clc *clc;
 	bool old = dev->has_eht, new = true;
+	u32 mtcl_conf = mt792x_acpi_get_mtcl_conf(&dev->phy, alpha2);
 	u8 *pos;
 
+	if (mtcl_conf != MT792X_ACPI_MTCL_INVALID &&
+	    (((mtcl_conf >> 4) & 0x3) == 0)) {
+		new = false;
+		goto out;
+	}
+
 	if (!phy->clc[MT792x_CLC_BE_CTRL])
 		goto out;
 
@@ -101,11 +108,21 @@ mt7925_regd_channel_update(struct wiphy *wiphy, struct mt792x_dev *dev)
 {
 #define IS_UNII_INVALID(idx, sfreq, efreq, cfreq) \
 	(!(dev->phy.clc_chan_conf & BIT(idx)) && (cfreq) >= (sfreq) && (cfreq) <= (efreq))
+#define MT7925_UNII_59G_IS_VALID	0x1
+#define MT7925_UNII_6G_IS_VALID	0x1e
 	struct ieee80211_supported_band *sband;
 	struct mt76_dev *mdev = &dev->mt76;
 	struct ieee80211_channel *ch;
+	u32 mtcl_conf = mt792x_acpi_get_mtcl_conf(&dev->phy, mdev->alpha2);
 	int i;
 
+	if (mtcl_conf != MT792X_ACPI_MTCL_INVALID) {
+		if ((mtcl_conf & 0x3) == 0)
+			dev->phy.clc_chan_conf &= ~MT7925_UNII_59G_IS_VALID;
+		if (((mtcl_conf >> 2) & 0x3) == 0)
+			dev->phy.clc_chan_conf &= ~MT7925_UNII_6G_IS_VALID;
+	}
+
 	sband = wiphy->bands[NL80211_BAND_5GHZ];
 	if (!sband)
 		return;

From 764bf16699ac9ed3fa1aa02db99a3a40a0078322 Mon Sep 17 00:00:00 2001
From: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Date: Tue, 11 Feb 2025 08:12:43 +0000
Subject: [PATCH 2291/2753] wifi: mt76: add mt76_get_power_bound helper
 function

This will replace mt7915_get_power_bound function from b/mt7915/mcu.h,
since we will need it also for mt7921 and mt7925

Signed-off-by: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Link: https://patch.msgid.link/20250211081247.5892-2-razvan.grigore@vampirebyte.ro
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c | 11 +++++++++++
 drivers/net/wireless/mediatek/mt76/mt76.h     |  2 ++
 2 files changed, 13 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 508b472408c20..2c98cc42cd7e6 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -1697,6 +1697,17 @@ void mt76_wcid_add_poll(struct mt76_dev *dev, struct mt76_wcid *wcid)
 }
 EXPORT_SYMBOL_GPL(mt76_wcid_add_poll);
 
+s8 mt76_get_power_bound(struct mt76_phy *phy, s8 txpower)
+{
+	int n_chains = hweight16(phy->chainmask);
+
+	txpower = mt76_get_sar_power(phy, phy->chandef.chan, txpower * 2);
+	txpower -= mt76_tx_power_nss_delta(n_chains);
+
+	return txpower;
+}
+EXPORT_SYMBOL_GPL(mt76_get_power_bound);
+
 int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		     unsigned int link_id, int *dbm)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 05651efb549ec..7596191252dc3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -1483,6 +1483,8 @@ void mt76_sta_pre_rcu_remove(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 int mt76_get_min_avg_rssi(struct mt76_dev *dev, u8 phy_idx);
 
+s8 mt76_get_power_bound(struct mt76_phy *phy, s8 txpower);
+
 int mt76_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		     unsigned int link_id, int *dbm);
 int mt76_init_sar_power(struct ieee80211_hw *hw,

From b4446a000bee8a73d027cd0e882015030d84166f Mon Sep 17 00:00:00 2001
From: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Date: Tue, 11 Feb 2025 08:12:46 +0000
Subject: [PATCH 2292/2753] wifi: mt76: mt7915: cleanup mt7915_get_power_bound

Refactor for making use of mt76_get_power_bound instead of the specific
mt7915_get_power_bound, since we need this for other chipsets as well
when calculating txpower

Signed-off-by: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Link: https://patch.msgid.link/20250211081247.5892-5-razvan.grigore@vampirebyte.ro
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c |  8 ++++----
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.c     |  4 ++--
 drivers/net/wireless/mediatek/mt76/mt7915/mcu.h     | 12 ------------
 3 files changed, 6 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
index 4fec7d000a631..192e8eff970b9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/debugfs.c
@@ -1085,13 +1085,13 @@ mt7915_rate_txpower_set(struct file *file, const char __user *user_buf,
 		return -EINVAL;
 
 	if (pwr160)
-		pwr160 = mt7915_get_power_bound(phy, pwr160);
+		pwr160 = mt76_get_power_bound(mphy, pwr160);
 	if (pwr80)
-		pwr80 = mt7915_get_power_bound(phy, pwr80);
+		pwr80 = mt76_get_power_bound(mphy, pwr80);
 	if (pwr40)
-		pwr40 = mt7915_get_power_bound(phy, pwr40);
+		pwr40 = mt76_get_power_bound(mphy, pwr40);
 	if (pwr20)
-		pwr20 = mt7915_get_power_bound(phy, pwr20);
+		pwr20 = mt76_get_power_bound(mphy, pwr20);
 
 	if (pwr160 < 0 || pwr80 < 0 || pwr40 < 0 || pwr20 < 0)
 		return -EINVAL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
index 9d790f234e82c..3643c72bb68d4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.c
@@ -3323,7 +3323,7 @@ int mt7915_mcu_set_txpower_frame(struct mt7915_phy *phy,
 	if (ret)
 		return ret;
 
-	txpower = mt7915_get_power_bound(phy, txpower);
+	txpower = mt76_get_power_bound(mphy, txpower);
 	if (txpower > mphy->txpower_cur || txpower < 0)
 		return -EINVAL;
 
@@ -3373,7 +3373,7 @@ int mt7915_mcu_set_txpower_sku(struct mt7915_phy *phy)
 	int i, idx;
 	int tx_power;
 
-	tx_power = mt7915_get_power_bound(phy, hw->conf.power_level);
+	tx_power = mt76_get_power_bound(mphy, hw->conf.power_level);
 	tx_power = mt76_get_rate_power_limits(mphy, mphy->chandef.chan,
 					      &limits_array, tx_power);
 	mphy->txpower_cur = tx_power;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
index 49476a4182fd1..092ed504a8f26 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7915/mcu.h
@@ -515,16 +515,4 @@ enum {
 					 sizeof(struct bss_info_bmc_rate) +\
 					 sizeof(struct bss_info_ext_bss))
 
-static inline s8
-mt7915_get_power_bound(struct mt7915_phy *phy, s8 txpower)
-{
-	struct mt76_phy *mphy = phy->mt76;
-	int n_chains = hweight16(mphy->chainmask);
-
-	txpower = mt76_get_sar_power(mphy, mphy->chandef.chan, txpower * 2);
-	txpower -= mt76_tx_power_nss_delta(n_chains);
-
-	return txpower;
-}
-
 #endif

From 6fc82f65870daa4bb351abb91411e139c4cdeb6b Mon Sep 17 00:00:00 2001
From: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Date: Tue, 11 Feb 2025 08:12:47 +0000
Subject: [PATCH 2293/2753] wifi: mt76: mt7996: cleanup mt7996_get_power_bound

Refactor for making use of mt76_get_power_bound instead of the specific
mt7996_get_power_bound, since we need this for other chipsets as well
when calculating txpower

Signed-off-by: Razvan Grigore <razvan.grigore@vampirebyte.ro>
Link: https://patch.msgid.link/20250211081247.5892-6-razvan.grigore@vampirebyte.ro
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c |  2 +-
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.h | 12 ------------
 2 files changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index e4569d0322214..76f489e2f6021 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4579,7 +4579,7 @@ int mt7996_mcu_set_txpower_sku(struct mt7996_phy *phy)
 	struct sk_buff *skb;
 	int i, tx_power;
 
-	tx_power = mt7996_get_power_bound(phy, phy->txpower);
+	tx_power = mt76_get_power_bound(mphy, phy->txpower);
 	tx_power = mt76_get_rate_power_limits(mphy, mphy->chandef.chan,
 					      &la, tx_power);
 	mphy->txpower_cur = tx_power;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index 43468bcaffc6d..bd1ba00e1bc64 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -809,18 +809,6 @@ enum {
 #define MT7996_MAX_BSS_OFFLOAD_SIZE	(MT7996_MAX_BEACON_SIZE +		\
 					 MT7996_BEACON_UPDATE_SIZE)
 
-static inline s8
-mt7996_get_power_bound(struct mt7996_phy *phy, s8 txpower)
-{
-	struct mt76_phy *mphy = phy->mt76;
-	int n_chains = hweight16(mphy->chainmask);
-
-	txpower = mt76_get_sar_power(mphy, mphy->chandef.chan, txpower * 2);
-	txpower -= mt76_tx_power_nss_delta(n_chains);
-
-	return txpower;
-}
-
 enum {
 	UNI_BAND_CONFIG_RADIO_ENABLE,
 	UNI_BAND_CONFIG_RTS_THRESHOLD = 0x08,

From 593c829b4326f7b3b15a69e97c9044ecbad3c319 Mon Sep 17 00:00:00 2001
From: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Date: Tue, 11 Mar 2025 11:36:38 +0100
Subject: [PATCH 2294/2753] wifi: mt76: mt7996: revise TXS size

Size of MPDU/PPDU TXS is 12 DWs.
In mt7996/mt7992, last 4 DWs are reserved, so TXS size was mistakenly
considered to be 8 DWs. However, in mt7990, 9th DW of TXS starts to be used.

Signed-off-by: Benjamin Lin <benjamin-jw.lin@mediatek.com>
Link: https://patch.msgid.link/20250311103646.43346-1-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h | 3 +++
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c       | 4 ++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
index db0c29e65185c..487ad716f872a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
@@ -314,6 +314,9 @@ enum tx_frag_idx {
 #define MT_TXFREE_INFO_COUNT		GENMASK(27, 24)
 #define MT_TXFREE_INFO_STAT		GENMASK(29, 28)
 
+#define MT_TXS_HDR_SIZE			4 /* Unit: DW */
+#define MT_TXS_SIZE			12 /* Unit: DW */
+
 #define MT_TXS0_BW			GENMASK(31, 29)
 #define MT_TXS0_TID			GENMASK(28, 26)
 #define MT_TXS0_AMPDU			BIT(25)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 019c925ae600e..33a8049d3356f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1399,7 +1399,7 @@ bool mt7996_rx_check(struct mt76_dev *mdev, void *data, int len)
 		mt7996_mac_tx_free(dev, data, len);
 		return false;
 	case PKT_TYPE_TXS:
-		for (rxd += 4; rxd + 8 <= end; rxd += 8)
+		for (rxd += MT_TXS_HDR_SIZE; rxd + MT_TXS_SIZE <= end; rxd += MT_TXS_SIZE)
 			mt7996_mac_add_txs(dev, rxd);
 		return false;
 	case PKT_TYPE_RX_FW_MONITOR:
@@ -1442,7 +1442,7 @@ void mt7996_queue_rx_skb(struct mt76_dev *mdev, enum mt76_rxq_id q,
 		mt7996_mcu_rx_event(dev, skb);
 		break;
 	case PKT_TYPE_TXS:
-		for (rxd += 4; rxd + 8 <= end; rxd += 8)
+		for (rxd += MT_TXS_HDR_SIZE; rxd + MT_TXS_SIZE <= end; rxd += MT_TXS_SIZE)
 			mt7996_mac_add_txs(dev, rxd);
 		dev_kfree_skb(skb);
 		break;

From 8d38abdf6c182225c5c0a81451fa51b7b36a635d Mon Sep 17 00:00:00 2001
From: Rex Lu <rex.lu@mediatek.com>
Date: Tue, 11 Mar 2025 11:36:39 +0100
Subject: [PATCH 2295/2753] wifi: mt76: mt7996: fix SER reset trigger on WED
 reset

The firmware needs a specific trigger when WED is being reset due to an
ethernet reset condition. This helps prevent further L1 SER failure.

Signed-off-by: Rex Lu <rex.lu@mediatek.com>
Link: https://patch.msgid.link/20250311103646.43346-2-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.h  | 3 ++-
 drivers/net/wireless/mediatek/mt76/mt7996/mmio.c | 2 +-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index bd1ba00e1bc64..5fdc47dad28c6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -896,7 +896,8 @@ enum {
 	UNI_CMD_SER_SET_RECOVER_L3_TX_DISABLE,
 	UNI_CMD_SER_SET_RECOVER_L3_BF,
 	UNI_CMD_SER_SET_RECOVER_L4_MDP,
-	UNI_CMD_SER_SET_RECOVER_FULL,
+	UNI_CMD_SER_SET_RECOVER_FROM_ETH,
+	UNI_CMD_SER_SET_RECOVER_FULL = 8,
 	UNI_CMD_SER_SET_SYSTEM_ASSERT,
 	/* action */
 	UNI_CMD_SER_ENABLE = 1,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 7a8ee6c75cf2b..9d37f82387464 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -281,7 +281,7 @@ static int mt7996_mmio_wed_reset(struct mtk_wed_device *wed)
 	if (test_and_set_bit(MT76_STATE_WED_RESET, &mphy->state))
 		return -EBUSY;
 
-	ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_TRIGGER, UNI_CMD_SER_SET_RECOVER_L1,
+	ret = mt7996_mcu_set_ser(dev, UNI_CMD_SER_TRIGGER, UNI_CMD_SER_SET_RECOVER_FROM_ETH,
 				 mphy->band_idx);
 	if (ret)
 		goto out;

From 0337355cc217215ba7c4e5a858c8f73c1a78bab4 Mon Sep 17 00:00:00 2001
From: Michael-CY Lee <michael-cy.lee@mediatek.com>
Date: Tue, 11 Mar 2025 11:36:40 +0100
Subject: [PATCH 2296/2753] wifi: mt76: mt7996: remove unnecessary key->cipher
 check for BIP frames

The cipher type check is redundant, and there is no need to dereference the
key struct here.

Signed-off-by: Michael-CY Lee <michael-cy.lee@mediatek.com>
Link: https://patch.msgid.link/20250311103646.43346-3-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 33a8049d3356f..162d1552602ea 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -773,8 +773,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	    info->flags & IEEE80211_TX_CTL_USE_MINRATE)
 		val |= MT_TXD1_FIXED_RATE;
 
-	if (key && multicast && ieee80211_is_robust_mgmt_frame(skb) &&
-	    key->cipher == WLAN_CIPHER_SUITE_AES_CMAC) {
+	if (key && multicast && ieee80211_is_robust_mgmt_frame(skb)) {
 		val |= MT_TXD1_BIP;
 		txwi[3] &= ~cpu_to_le32(MT_TXD3_PROTECT_FRAME);
 	}

From 3ba20af886d1f604dceeb4d4c8ff872e2c4e885e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 11:36:41 +0100
Subject: [PATCH 2297/2753] wifi: mt76: scan: set vif offchannel link for
 scanning/roc

The driver needs to know what vif link to use

Link: https://patch.msgid.link/20250311103646.43346-4-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/channel.c | 3 +++
 drivers/net/wireless/mediatek/mt76/mt76.h    | 2 ++
 2 files changed, 5 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/channel.c b/drivers/net/wireless/mediatek/mt76/channel.c
index 6a35c6ebd823e..e7b839e742903 100644
--- a/drivers/net/wireless/mediatek/mt76/channel.c
+++ b/drivers/net/wireless/mediatek/mt76/channel.c
@@ -293,6 +293,7 @@ struct mt76_vif_link *mt76_get_vif_phy_link(struct mt76_phy *phy,
 		kfree(mlink);
 		return ERR_PTR(ret);
 	}
+	rcu_assign_pointer(mvif->offchannel_link, mlink);
 
 	return mlink;
 }
@@ -301,10 +302,12 @@ void mt76_put_vif_phy_link(struct mt76_phy *phy, struct ieee80211_vif *vif,
 			   struct mt76_vif_link *mlink)
 {
 	struct mt76_dev *dev = phy->dev;
+	struct mt76_vif_data *mvif = mlink->mvif;
 
 	if (IS_ERR_OR_NULL(mlink) || !mlink->offchannel)
 		return;
 
+	rcu_assign_pointer(mvif->offchannel_link, NULL);
 	dev->drv->vif_link_remove(phy, vif, &vif->bss_conf, mlink);
 	kfree(mlink);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 7596191252dc3..c16a6743ad64c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -351,6 +351,7 @@ struct mt76_wcid {
 	u8 hw_key_idx;
 	u8 hw_key_idx2;
 
+	u8 offchannel:1;
 	u8 sta:1;
 	u8 sta_disabled:1;
 	u8 amsdu:1;
@@ -787,6 +788,7 @@ struct mt76_vif_link {
 
 struct mt76_vif_data {
 	struct mt76_vif_link __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
+	struct mt76_vif_link __rcu *offchannel_link;
 
 	struct mt76_phy *roc_phy;
 	u16 valid_links;

From 13b4c81083cc4b59fb639a511c0a9a7c38efde7e Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 11:36:42 +0100
Subject: [PATCH 2298/2753] wifi: mt76: mt7996: use the correct vif link for
 scanning/roc

Use the newly added offchannel_link pointer in vif data

Link: https://patch.msgid.link/20250311103646.43346-5-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 40 +++++++++++++------
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  1 +
 2 files changed, 28 insertions(+), 13 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 162d1552602ea..9dfc8106ebec9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -831,7 +831,8 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	u8 band_idx = (info->hw_queue & MT_TX_HW_QUEUE_PHY) >> 2;
 	u8 p_fmt, q_idx, omac_idx = 0, wmm_idx = 0;
 	bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP;
-	struct mt76_vif_link *mvif;
+	struct mt76_vif_link *mlink = NULL;
+	struct mt7996_vif *mvif;
 	u16 tx_count = 15;
 	u32 val;
 	bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
@@ -839,11 +840,18 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	bool beacon = !!(changed & (BSS_CHANGED_BEACON |
 				    BSS_CHANGED_BEACON_ENABLED)) && (!inband_disc);
 
-	mvif = vif ? (struct mt76_vif_link *)vif->drv_priv : NULL;
-	if (mvif) {
-		omac_idx = mvif->omac_idx;
-		wmm_idx = mvif->wmm_idx;
-		band_idx = mvif->band_idx;
+	if (vif) {
+		mvif = (struct mt7996_vif *)vif->drv_priv;
+		if (wcid->offchannel)
+			mlink = rcu_dereference(mvif->mt76.offchannel_link);
+		if (!mlink)
+			mlink = &mvif->deflink.mt76;
+	}
+
+	if (mlink) {
+		omac_idx = mlink->omac_idx;
+		wmm_idx = mlink->wmm_idx;
+		band_idx = mlink->band_idx;
 	}
 
 	if (inband_disc) {
@@ -909,13 +917,13 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			     is_multicast_ether_addr(hdr->addr1);
 		u8 idx = MT7996_BASIC_RATES_TBL;
 
-		if (mvif) {
-			if (mcast && mvif->mcast_rates_idx)
-				idx = mvif->mcast_rates_idx;
-			else if (beacon && mvif->beacon_rates_idx)
-				idx = mvif->beacon_rates_idx;
+		if (mlink) {
+			if (mcast && mlink->mcast_rates_idx)
+				idx = mlink->mcast_rates_idx;
+			else if (beacon && mlink->beacon_rates_idx)
+				idx = mlink->beacon_rates_idx;
 			else
-				idx = mvif->basic_rates_idx;
+				idx = mlink->basic_rates_idx;
 		}
 
 		val = FIELD_PREP(MT_TXD6_TX_RATE, idx) | MT_TXD6_FIXED_BW;
@@ -983,8 +991,14 @@ int mt7996_tx_prepare_skb(struct mt76_dev *mdev, void *txwi_ptr,
 
 	if (vif) {
 		struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+		struct mt76_vif_link *mlink = NULL;
+
+		if (wcid->offchannel)
+			mlink = rcu_dereference(mvif->mt76.offchannel_link);
+		if (!mlink)
+			mlink = &mvif->deflink.mt76;
 
-		txp->fw.bss_idx = mvif->deflink.mt76.idx;
+		txp->fw.bss_idx = mlink->idx;
 	}
 
 	txp->fw.token = cpu_to_le16(id);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 69dd565d83190..886b6ef3462b6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -249,6 +249,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	mlink->band_idx = band_idx;
 	mlink->wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3;
 	mlink->wcid = &link->sta.wcid;
+	mlink->wcid->offchannel = mlink->offchannel;
 
 	ret = mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, true);
 	if (ret)

From 0c5a89ceddc1728a40cb3313948401dd70e3c649 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 11:36:43 +0100
Subject: [PATCH 2299/2753] wifi: mt76: only mark tx-status-failed frames as
 ACKed on mt76x0/2

The interrupt status polling is unreliable, which can cause status events
to get lost. On all newer chips, txs-timeout is an indication that the
packet was either never sent, or never acked.
Fixes issues with inactivity polling.

Link: https://patch.msgid.link/20250311103646.43346-6-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76.h       | 1 +
 drivers/net/wireless/mediatek/mt76/mt76x0/pci.c | 3 ++-
 drivers/net/wireless/mediatek/mt76/mt76x0/usb.c | 3 ++-
 drivers/net/wireless/mediatek/mt76/mt76x2/pci.c | 3 ++-
 drivers/net/wireless/mediatek/mt76/mt76x2/usb.c | 3 ++-
 drivers/net/wireless/mediatek/mt76/tx.c         | 3 ++-
 6 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index c16a6743ad64c..b461273c33064 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -492,6 +492,7 @@ struct mt76_hw_cap {
 #define MT_DRV_RX_DMA_HDR		BIT(3)
 #define MT_DRV_HW_MGMT_TXQ		BIT(4)
 #define MT_DRV_AMSDU_OFFLOAD		BIT(5)
+#define MT_DRV_IGNORE_TXS_FAILED	BIT(6)
 
 struct mt76_driver_ops {
 	u32 drv_flags;
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
index b456ccd00d581..11c16d1fc70fc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/pci.c
@@ -156,7 +156,8 @@ mt76x0e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
 		.drv_flags = MT_DRV_TX_ALIGNED4_SKBS |
-			     MT_DRV_SW_RX_AIRTIME,
+			     MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x0_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index b031c500b7415..90e5666c0857d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -214,7 +214,8 @@ static int mt76x0u_probe(struct usb_interface *usb_intf,
 			 const struct usb_device_id *id)
 {
 	static const struct mt76_driver_ops drv_ops = {
-		.drv_flags = MT_DRV_SW_RX_AIRTIME,
+		.drv_flags = MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x0_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
index 727bfdd00b400..2303019670e2c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/pci.c
@@ -22,7 +22,8 @@ mt76x2e_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 	static const struct mt76_driver_ops drv_ops = {
 		.txwi_size = sizeof(struct mt76x02_txwi),
 		.drv_flags = MT_DRV_TX_ALIGNED4_SKBS |
-			     MT_DRV_SW_RX_AIRTIME,
+			     MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x2e_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index e832ad53e2393..3747f9ed31e6f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -29,7 +29,8 @@ static int mt76x2u_probe(struct usb_interface *intf,
 			 const struct usb_device_id *id)
 {
 	static const struct mt76_driver_ops drv_ops = {
-		.drv_flags = MT_DRV_SW_RX_AIRTIME,
+		.drv_flags = MT_DRV_SW_RX_AIRTIME |
+			     MT_DRV_IGNORE_TXS_FAILED,
 		.survey_flags = SURVEY_INFO_TIME_TX,
 		.update_survey = mt76x02_update_channel,
 		.set_channel = mt76x2u_set_channel,
diff --git a/drivers/net/wireless/mediatek/mt76/tx.c b/drivers/net/wireless/mediatek/mt76/tx.c
index af0c50c983ec1..513916469ca2f 100644
--- a/drivers/net/wireless/mediatek/mt76/tx.c
+++ b/drivers/net/wireless/mediatek/mt76/tx.c
@@ -100,7 +100,8 @@ __mt76_tx_status_skb_done(struct mt76_dev *dev, struct sk_buff *skb, u8 flags,
 		return;
 
 	/* Tx status can be unreliable. if it fails, mark the frame as ACKed */
-	if (flags & MT_TX_CB_TXS_FAILED) {
+	if (flags & MT_TX_CB_TXS_FAILED &&
+	    (dev->drv->drv_flags & MT_DRV_IGNORE_TXS_FAILED)) {
 		info->status.rates[0].count = 0;
 		info->status.rates[0].idx = -1;
 		info->flags |= IEEE80211_TX_STAT_ACK;

From 86db2c5d4ed390b97a5b455a97e2cd9c4f3eff2b Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 11:36:44 +0100
Subject: [PATCH 2300/2753] wifi: mt76: mt7996: implement driver specific
 get_txpower function

Fixes reporting tx power for vifs that don't have a channel context
assigned. Report the tx power of a phy that is covered by the vif's
radio mask.

Link: https://patch.msgid.link/20250311103646.43346-7-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 29 ++++++++++++++++++-
 1 file changed, 28 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 886b6ef3462b6..b01cc7ef47999 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -602,6 +602,33 @@ static void mt7996_configure_filter(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
+static int
+mt7996_get_txpower(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		   unsigned int link_id, int *dbm)
+{
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink);
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	struct wireless_dev *wdev;
+	int n_chains, delta, i;
+
+	if (!phy) {
+		wdev = ieee80211_vif_to_wdev(vif);
+		for (i = 0; i < hw->wiphy->n_radio; i++)
+			if (wdev->radio_mask & BIT(i))
+				phy = dev->radio_phy[i];
+
+		if (!phy)
+			return -EINVAL;
+	}
+
+	n_chains = hweight16(phy->mt76->chainmask);
+	delta = mt76_tx_power_nss_delta(n_chains);
+	*dbm = DIV_ROUND_UP(phy->mt76->txpower_cur + delta, 2);
+
+	return 0;
+}
+
 static u8
 mt7996_get_rates_table(struct mt7996_phy *phy, struct ieee80211_bss_conf *conf,
 		       bool beacon, bool mcast)
@@ -1651,7 +1678,7 @@ const struct ieee80211_ops mt7996_ops = {
 	.remain_on_channel = mt76_remain_on_channel,
 	.cancel_remain_on_channel = mt76_cancel_remain_on_channel,
 	.release_buffered_frames = mt76_release_buffered_frames,
-	.get_txpower = mt76_get_txpower,
+	.get_txpower = mt7996_get_txpower,
 	.channel_switch_beacon = mt7996_channel_switch_beacon,
 	.get_stats = mt7996_get_stats,
 	.get_et_sset_count = mt7996_get_et_sset_count,

From 5b5f1ca9ce73ab6c35e5cd3348f8432ba190d7f4 Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Tue, 11 Mar 2025 11:36:45 +0100
Subject: [PATCH 2301/2753] wifi: mt76: scan: fix setting tx_info fields

ieee80211_tx_prepare_skb initializes the skb cb, so fields need to be set
afterwards.

Link: https://patch.msgid.link/20250311103646.43346-8-nbd@nbd.name
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/scan.c | 21 +++++++++++++--------
 1 file changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/scan.c b/drivers/net/wireless/mediatek/mt76/scan.c
index 1c4f9deaaada5..9b20ccbeb8cf1 100644
--- a/drivers/net/wireless/mediatek/mt76/scan.c
+++ b/drivers/net/wireless/mediatek/mt76/scan.c
@@ -52,11 +52,6 @@ mt76_scan_send_probe(struct mt76_dev *dev, struct cfg80211_ssid *ssid)
 		ether_addr_copy(hdr->addr3, req->bssid);
 	}
 
-	info = IEEE80211_SKB_CB(skb);
-	if (req->no_cck)
-		info->flags |= IEEE80211_TX_CTL_NO_CCK_RATE;
-	info->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
-
 	if (req->ie_len)
 		skb_put_data(skb, req->ie, req->ie_len);
 
@@ -64,10 +59,20 @@ mt76_scan_send_probe(struct mt76_dev *dev, struct cfg80211_ssid *ssid)
 	skb_set_queue_mapping(skb, IEEE80211_AC_VO);
 
 	rcu_read_lock();
-	if (ieee80211_tx_prepare_skb(phy->hw, vif, skb, band, NULL))
-		mt76_tx(phy, NULL, mvif->wcid, skb);
-	else
+
+	if (!ieee80211_tx_prepare_skb(phy->hw, vif, skb, band, NULL)) {
 		ieee80211_free_txskb(phy->hw, skb);
+		goto out;
+	}
+
+	info = IEEE80211_SKB_CB(skb);
+	if (req->no_cck)
+		info->flags |= IEEE80211_TX_CTL_NO_CCK_RATE;
+	info->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
+
+	mt76_tx(phy, NULL, mvif->wcid, skb);
+
+out:
 	rcu_read_unlock();
 }
 

From 142f82d45ed4fbe2d08cf6f19a6fa90970de044b Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:00 +0100
Subject: [PATCH 2302/2753] wifi: mt76: mt7996: Add change_vif_links stub

change_vif_links callback is required by mac80211.
This is a preliminary patch to introduce MLO support for MT7996 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-1-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index b01cc7ef47999..c0e7ab9bcae5f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1650,6 +1650,14 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 
 #endif
 
+static int
+mt7996_change_vif_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			u16 old_links, u16 new_links,
+			struct ieee80211_bss_conf *old[IEEE80211_MLD_MAX_NUM_LINKS])
+{
+	return 0;
+}
+
 const struct ieee80211_ops mt7996_ops = {
 	.add_chanctx = mt76_add_chanctx,
 	.remove_chanctx = mt76_remove_chanctx,
@@ -1705,4 +1713,5 @@ const struct ieee80211_ops mt7996_ops = {
 	.net_fill_forward_path = mt7996_net_fill_forward_path,
 	.net_setup_tc = mt76_wed_net_setup_tc,
 #endif
+	.change_vif_links = mt7996_change_vif_links,
 };

From f32915eb6dd4b66c0b434afc7c30c2ff55a4e6e8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:01 +0100
Subject: [PATCH 2303/2753] wifi: mt76: mt7996: Introduce mt7996_sta_link
 container

Similar to mt7996_vif_link, add mt7996_sta_link structure as driver
representation for sta links. This is a preliminary patch to introduce
MLO support for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-2-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7996/debugfs.c   |  12 +-
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 117 +++++++++------
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 136 ++++++++++--------
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   |  33 +++--
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  10 +-
 5 files changed, 181 insertions(+), 127 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
index 7b2bb72b407da..d453c2fc97e4f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
@@ -617,13 +617,14 @@ mt7996_sta_hw_queue_read(void *data, struct ieee80211_sta *sta)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_dev *dev = msta->vif->deflink.phy->dev;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct seq_file *s = data;
 	u8 ac;
 
 	for (ac = 0; ac < 4; ac++) {
 		u32 qlen, ctrl, val;
-		u32 idx = msta->wcid.idx >> 5;
-		u8 offs = msta->wcid.idx & GENMASK(4, 0);
+		u32 idx = msta_link->wcid.idx >> 5;
+		u8 offs = msta_link->wcid.idx & GENMASK(4, 0);
 
 		ctrl = BIT(31) | BIT(11) | (ac << 24);
 		val = mt76_rr(dev, MT_PLE_AC_QEMPTY(ac, idx));
@@ -631,11 +632,11 @@ mt7996_sta_hw_queue_read(void *data, struct ieee80211_sta *sta)
 		if (val & BIT(offs))
 			continue;
 
-		mt76_wr(dev, MT_FL_Q0_CTRL, ctrl | msta->wcid.idx);
+		mt76_wr(dev, MT_FL_Q0_CTRL, ctrl | msta_link->wcid.idx);
 		qlen = mt76_get_field(dev, MT_FL_Q3_CTRL,
 				      GENMASK(11, 0));
 		seq_printf(s, "\tSTA %pM wcid %d: AC%d%d queued:%d\n",
-			   sta->addr, msta->wcid.idx,
+			   sta->addr, msta_link->wcid.idx,
 			   msta->vif->deflink.mt76.wmm_idx, ac, qlen);
 	}
 }
@@ -930,6 +931,7 @@ static ssize_t mt7996_sta_fixed_rate_set(struct file *file,
 	struct ieee80211_sta *sta = file->private_data;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_dev *dev = msta->vif->deflink.phy->dev;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct ra_rate phy = {};
 	char buf[100];
 	int ret;
@@ -964,7 +966,7 @@ static ssize_t mt7996_sta_fixed_rate_set(struct file *file,
 		goto out;
 	}
 
-	phy.wlan_idx = cpu_to_le16(msta->wcid.idx);
+	phy.wlan_idx = cpu_to_le16(msta_link->wcid.idx);
 	phy.gi = cpu_to_le16(gi);
 	phy.ltf = cpu_to_le16(ltf);
 	phy.ldpc = phy.ldpc ? 7 : 0;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 9dfc8106ebec9..754f8e520f52f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -55,7 +55,8 @@ static const struct mt7996_dfs_radar_spec jp_radar_specs = {
 static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
 					    u16 idx, bool unicast)
 {
-	struct mt7996_sta *sta;
+	struct mt7996_sta_link *msta_link;
+	struct mt7996_sta *msta;
 	struct mt76_wcid *wcid;
 
 	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
@@ -68,11 +69,13 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
 	if (!wcid->sta)
 		return NULL;
 
-	sta = container_of(wcid, struct mt7996_sta, wcid);
-	if (!sta->vif)
+	msta_link = container_of(wcid, struct mt7996_sta_link, wcid);
+	msta = msta_link->sta;
+
+	if (!msta->vif)
 		return NULL;
 
-	return &sta->vif->deflink.sta.wcid;
+	return &msta->vif->deflink.sta.deflink.wcid;
 }
 
 bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask)
@@ -100,6 +103,7 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		[IEEE80211_AC_VI] = 4,
 		[IEEE80211_AC_VO] = 6
 	};
+	struct mt7996_sta_link *msta_link;
 	struct ieee80211_sta *sta;
 	struct mt7996_sta *msta;
 	u32 tx_time[IEEE80211_NUM_ACS], rx_time[IEEE80211_NUM_ACS];
@@ -123,25 +127,27 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 			spin_unlock_bh(&dev->mt76.sta_poll_lock);
 			break;
 		}
-		msta = list_first_entry(&sta_poll_list,
-					struct mt7996_sta, wcid.poll_list);
-		list_del_init(&msta->wcid.poll_list);
+		msta_link = list_first_entry(&sta_poll_list,
+					     struct mt7996_sta_link,
+					     wcid.poll_list);
+		msta = msta_link->sta;
+		list_del_init(&msta_link->wcid.poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
-		idx = msta->wcid.idx;
+		idx = msta_link->wcid.idx;
 
 		/* refresh peer's airtime reporting */
 		addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 20);
 
 		for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-			u32 tx_last = msta->airtime_ac[i];
-			u32 rx_last = msta->airtime_ac[i + 4];
+			u32 tx_last = msta_link->airtime_ac[i];
+			u32 rx_last = msta_link->airtime_ac[i + 4];
 
-			msta->airtime_ac[i] = mt76_rr(dev, addr);
-			msta->airtime_ac[i + 4] = mt76_rr(dev, addr + 4);
+			msta_link->airtime_ac[i] = mt76_rr(dev, addr);
+			msta_link->airtime_ac[i + 4] = mt76_rr(dev, addr + 4);
 
-			tx_time[i] = msta->airtime_ac[i] - tx_last;
-			rx_time[i] = msta->airtime_ac[i + 4] - rx_last;
+			tx_time[i] = msta_link->airtime_ac[i] - tx_last;
+			rx_time[i] = msta_link->airtime_ac[i + 4] - rx_last;
 
 			if ((tx_last | rx_last) & BIT(30))
 				clear = true;
@@ -152,10 +158,11 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		if (clear) {
 			mt7996_mac_wtbl_update(dev, idx,
 					       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
-			memset(msta->airtime_ac, 0, sizeof(msta->airtime_ac));
+			memset(msta_link->airtime_ac, 0,
+			       sizeof(msta_link->airtime_ac));
 		}
 
-		if (!msta->wcid.sta)
+		if (!msta_link->wcid.sta)
 			continue;
 
 		sta = container_of((void *)msta, struct ieee80211_sta,
@@ -181,10 +188,11 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		rssi[2] = to_rssi(GENMASK(23, 16), val);
 		rssi[3] = to_rssi(GENMASK(31, 14), val);
 
-		msta->ack_signal =
+		msta_link->ack_signal =
 			mt76_rx_signal(msta->vif->deflink.phy->mt76->antenna_mask, rssi);
 
-		ewma_avg_signal_add(&msta->avg_ack_signal, -msta->ack_signal);
+		ewma_avg_signal_add(&msta_link->avg_ack_signal,
+				    -msta_link->ack_signal);
 	}
 
 	rcu_read_unlock();
@@ -194,9 +202,10 @@ void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
 			      struct ieee80211_vif *vif, bool enable)
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta_link *msta_link = &mvif->deflink.sta.deflink;
 	u32 addr;
 
-	addr = mt7996_mac_wtbl_lmac_addr(dev, mvif->deflink.sta.wcid.idx, 5);
+	addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 5);
 	if (enable)
 		mt76_set(dev, addr, BIT(5));
 	else
@@ -477,8 +486,12 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 	status->wcid = mt7996_rx_get_wcid(dev, idx, unicast);
 
 	if (status->wcid) {
-		msta = container_of(status->wcid, struct mt7996_sta, wcid);
-		mt76_wcid_add_poll(&dev->mt76, &msta->wcid);
+		struct mt7996_sta_link *msta_link;
+
+		msta_link = container_of(status->wcid, struct mt7996_sta_link,
+					 wcid);
+		msta = msta_link->sta;
+		mt76_wcid_add_poll(&dev->mt76, &msta_link->wcid);
 	}
 
 	status->freq = mphy->chandef.chan->center_freq;
@@ -1040,9 +1053,10 @@ u32 mt7996_wed_init_buf(void *ptr, dma_addr_t phys, int token_id)
 static void
 mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb)
 {
-	struct mt7996_sta *msta;
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP;
+	struct mt7996_sta_link *msta_link;
+	struct mt7996_sta *msta;
 	u16 fc, tid;
 
 	if (!sta || !(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he))
@@ -1071,7 +1085,9 @@ mt7996_tx_check_aggr(struct ieee80211_sta *sta, struct sk_buff *skb)
 		return;
 
 	msta = (struct mt7996_sta *)sta->drv_priv;
-	if (!test_and_set_bit(tid, &msta->wcid.ampdu_state))
+	msta_link = &msta->deflink;
+
+	if (!test_and_set_bit(tid, &msta_link->wcid.ampdu_state))
 		ieee80211_start_tx_ba_session(sta, tid, 0);
 }
 
@@ -1149,7 +1165,7 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 		 */
 		info = le32_to_cpu(*cur_info);
 		if (info & MT_TXFREE_INFO_PAIR) {
-			struct mt7996_sta *msta;
+			struct mt7996_sta_link *msta_link;
 			u16 idx;
 
 			idx = FIELD_GET(MT_TXFREE_INFO_WLAN_ID, info);
@@ -1158,8 +1174,9 @@ mt7996_mac_tx_free(struct mt7996_dev *dev, void *data, int len)
 			if (!sta)
 				continue;
 
-			msta = container_of(wcid, struct mt7996_sta, wcid);
-			mt76_wcid_add_poll(&dev->mt76, &msta->wcid);
+			msta_link = container_of(wcid, struct mt7996_sta_link,
+						 wcid);
+			mt76_wcid_add_poll(&dev->mt76, &msta_link->wcid);
 			continue;
 		} else if (info & MT_TXFREE_INFO_HEADER) {
 			u32 tx_retries = 0, tx_failed = 0;
@@ -1357,7 +1374,7 @@ mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid,
 
 static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 {
-	struct mt7996_sta *msta = NULL;
+	struct mt7996_sta_link *msta_link;
 	struct mt76_wcid *wcid;
 	__le32 *txs_data = data;
 	u16 wcidx;
@@ -1378,14 +1395,13 @@ static void mt7996_mac_add_txs(struct mt7996_dev *dev, void *data)
 	if (!wcid)
 		goto out;
 
-	msta = container_of(wcid, struct mt7996_sta, wcid);
-
 	mt7996_mac_add_txs_skb(dev, wcid, pid, txs_data);
 
 	if (!wcid->sta)
 		goto out;
 
-	mt76_wcid_add_poll(&dev->mt76, &msta->wcid);
+	msta_link = container_of(wcid, struct mt7996_sta_link, wcid);
+	mt76_wcid_add_poll(&dev->mt76, &msta_link->wcid);
 
 out:
 	rcu_read_unlock();
@@ -2252,6 +2268,7 @@ void mt7996_mac_update_stats(struct mt7996_phy *phy)
 void mt7996_mac_sta_rc_work(struct work_struct *work)
 {
 	struct mt7996_dev *dev = container_of(work, struct mt7996_dev, rc_work);
+	struct mt7996_sta_link *msta_link;
 	struct ieee80211_sta *sta;
 	struct ieee80211_vif *vif;
 	struct mt7996_sta *msta;
@@ -2262,12 +2279,15 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 	list_splice_init(&dev->sta_rc_list, &list);
 
 	while (!list_empty(&list)) {
-		msta = list_first_entry(&list, struct mt7996_sta, rc_list);
-		list_del_init(&msta->rc_list);
-		changed = msta->changed;
-		msta->changed = 0;
+		msta_link = list_first_entry(&list, struct mt7996_sta_link,
+					     rc_list);
+		list_del_init(&msta_link->rc_list);
+
+		changed = msta_link->changed;
+		msta_link->changed = 0;
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
+		msta = msta_link->sta;
 		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
 		vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
 
@@ -2551,7 +2571,7 @@ static int mt7996_mac_check_twt_req(struct ieee80211_twt_setup *twt)
 }
 
 static bool
-mt7996_mac_twt_param_equal(struct mt7996_sta *msta,
+mt7996_mac_twt_param_equal(struct mt7996_sta_link *msta_link,
 			   struct ieee80211_twt_params *twt_agrt)
 {
 	u16 type = le16_to_cpu(twt_agrt->req_type);
@@ -2562,10 +2582,10 @@ mt7996_mac_twt_param_equal(struct mt7996_sta *msta,
 	for (i = 0; i < MT7996_MAX_STA_TWT_AGRT; i++) {
 		struct mt7996_twt_flow *f;
 
-		if (!(msta->twt.flowid_mask & BIT(i)))
+		if (!(msta_link->twt.flowid_mask & BIT(i)))
 			continue;
 
-		f = &msta->twt.flow[i];
+		f = &msta_link->twt.flow[i];
 		if (f->duration == twt_agrt->min_twt_dur &&
 		    f->mantissa == twt_agrt->mantissa &&
 		    f->exp == exp &&
@@ -2585,6 +2605,7 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 	enum ieee80211_twt_setup_cmd setup_cmd = TWT_SETUP_CMD_REJECT;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct ieee80211_twt_params *twt_agrt = (void *)twt->params;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	u16 req_type = le16_to_cpu(twt_agrt->req_type);
 	enum ieee80211_twt_setup_cmd sta_setup_cmd;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
@@ -2599,7 +2620,8 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 	if (dev->twt.n_agrt == MT7996_MAX_TWT_AGRT)
 		goto unlock;
 
-	if (hweight8(msta->twt.flowid_mask) == ARRAY_SIZE(msta->twt.flow))
+	if (hweight8(msta_link->twt.flowid_mask) ==
+	    ARRAY_SIZE(msta_link->twt.flow))
 		goto unlock;
 
 	if (twt_agrt->min_twt_dur < MT7996_MIN_TWT_DUR) {
@@ -2608,10 +2630,10 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 		goto unlock;
 	}
 
-	if (mt7996_mac_twt_param_equal(msta, twt_agrt))
+	if (mt7996_mac_twt_param_equal(msta_link, twt_agrt))
 		goto unlock;
 
-	flowid = ffs(~msta->twt.flowid_mask) - 1;
+	flowid = ffs(~msta_link->twt.flowid_mask) - 1;
 	twt_agrt->req_type &= ~cpu_to_le16(IEEE80211_TWT_REQTYPE_FLOWID);
 	twt_agrt->req_type |= le16_encode_bits(flowid,
 					       IEEE80211_TWT_REQTYPE_FLOWID);
@@ -2620,10 +2642,10 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 	exp = FIELD_GET(IEEE80211_TWT_REQTYPE_WAKE_INT_EXP, req_type);
 	sta_setup_cmd = FIELD_GET(IEEE80211_TWT_REQTYPE_SETUP_CMD, req_type);
 
-	flow = &msta->twt.flow[flowid];
+	flow = &msta_link->twt.flow[flowid];
 	memset(flow, 0, sizeof(*flow));
 	INIT_LIST_HEAD(&flow->list);
-	flow->wcid = msta->wcid.idx;
+	flow->wcid = msta_link->wcid.idx;
 	flow->table_id = table_id;
 	flow->id = flowid;
 	flow->duration = twt_agrt->min_twt_dur;
@@ -2655,7 +2677,7 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 
 	setup_cmd = TWT_SETUP_CMD_ACCEPT;
 	dev->twt.table_mask |= BIT(table_id);
-	msta->twt.flowid_mask |= BIT(flowid);
+	msta_link->twt.flowid_mask |= BIT(flowid);
 	dev->twt.n_agrt++;
 
 unlock:
@@ -2671,23 +2693,24 @@ void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev,
 				  struct mt7996_sta *msta,
 				  u8 flowid)
 {
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_twt_flow *flow;
 
 	lockdep_assert_held(&dev->mt76.mutex);
 
-	if (flowid >= ARRAY_SIZE(msta->twt.flow))
+	if (flowid >= ARRAY_SIZE(msta_link->twt.flow))
 		return;
 
-	if (!(msta->twt.flowid_mask & BIT(flowid)))
+	if (!(msta_link->twt.flowid_mask & BIT(flowid)))
 		return;
 
-	flow = &msta->twt.flow[flowid];
+	flow = &msta_link->twt.flow[flowid];
 	if (mt7996_mcu_twt_agrt_update(dev, msta->vif, flow,
 				       MCU_TWT_AGRT_DELETE))
 		return;
 
 	list_del_init(&flow->list);
-	msta->twt.flowid_mask &= ~BIT(flowid);
+	msta_link->twt.flowid_mask &= ~BIT(flowid);
 	dev->twt.table_mask &= ~BIT(flow->table_id);
 	dev->twt.n_agrt--;
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index c0e7ab9bcae5f..0cd011619fd3f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -163,7 +163,7 @@ mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = sta ? (struct mt7996_sta *)sta->drv_priv :
 				  &mlink->sta;
-	struct mt76_wcid *wcid = &msta->wcid;
+	struct mt76_wcid *wcid = &msta->deflink.wcid;
 	u8 *wcid_keyidx = &wcid->hw_key_idx;
 	struct mt7996_phy *phy;
 	int idx = key->keyidx;
@@ -208,8 +208,7 @@ mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		return mt7996_mcu_bcn_prot_enable(dev, vif, key);
 
 	return mt7996_mcu_add_key(&dev->mt76, vif, key,
-				  MCU_WMWA_UNI_CMD(STA_REC_UPDATE),
-				  &msta->wcid, cmd);
+				  MCU_WMWA_UNI_CMD(STA_REC_UPDATE), wcid, cmd);
 }
 
 static void
@@ -230,6 +229,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 			struct mt76_vif_link *mlink)
 {
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
+	struct mt7996_sta_link *msta_link = &link->sta.deflink;
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
 	u8 band_idx = phy->mt76->band_idx;
@@ -248,7 +248,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	mlink->omac_idx = idx;
 	mlink->band_idx = band_idx;
 	mlink->wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3;
-	mlink->wcid = &link->sta.wcid;
+	mlink->wcid = &msta_link->wcid;
 	mlink->wcid->offchannel = mlink->offchannel;
 
 	ret = mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, true);
@@ -260,10 +260,11 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	idx = MT7996_WTBL_RESERVED - mlink->idx;
 
-	INIT_LIST_HEAD(&link->sta.rc_list);
-	link->sta.wcid.idx = idx;
-	link->sta.wcid.tx_info |= MT_WCID_TX_INFO_SET;
-	mt76_wcid_init(&link->sta.wcid, band_idx);
+	INIT_LIST_HEAD(&msta_link->rc_list);
+	msta_link->sta = &link->sta;
+	msta_link->wcid.idx = idx;
+	msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
+	mt76_wcid_init(&msta_link->wcid, band_idx);
 
 	mt7996_mac_wtbl_update(dev, idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
@@ -290,7 +291,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	 */
 	if (vif->type != NL80211_IFTYPE_STATION)
 		mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_PORT_SECURE, true);
-	rcu_assign_pointer(dev->mt76.wcid[idx], &link->sta.wcid);
+	rcu_assign_pointer(dev->mt76.wcid[idx], &msta_link->wcid);
 
 	ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, link);
 
@@ -304,11 +305,10 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
-	struct mt7996_sta *msta;
-	int idx;
+	struct mt7996_sta *msta = &link->sta;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
+	int idx = msta_link->wcid.idx;
 
-	msta = &link->sta;
-	idx = msta->wcid.idx;
 	mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_DISCONNECT, false);
 	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, false);
 
@@ -320,11 +320,11 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	phy->omac_mask &= ~BIT_ULL(mlink->omac_idx);
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	if (!list_empty(&msta->wcid.poll_list))
-		list_del_init(&msta->wcid.poll_list);
+	if (!list_empty(&msta_link->wcid.poll_list))
+		list_del_init(&msta_link->wcid.poll_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
-	mt76_wcid_cleanup(&dev->mt76, &msta->wcid);
+	mt76_wcid_cleanup(&dev->mt76, &msta_link->wcid);
 }
 
 static void mt7996_phy_set_rxfilter(struct mt7996_phy *phy)
@@ -788,6 +788,7 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif_link *link = &mvif->deflink;
 	u8 band_idx = link->phy->mt76->band_idx;
 	int idx;
@@ -796,14 +797,15 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (idx < 0)
 		return -ENOSPC;
 
-	INIT_LIST_HEAD(&msta->rc_list);
-	INIT_LIST_HEAD(&msta->wcid.poll_list);
 	msta->vif = mvif;
-	msta->wcid.sta = 1;
-	msta->wcid.idx = idx;
-	msta->wcid.phy_idx = band_idx;
+	INIT_LIST_HEAD(&msta_link->rc_list);
+	INIT_LIST_HEAD(&msta_link->wcid.poll_list);
+	msta_link->sta = msta;
+	msta_link->wcid.sta = 1;
+	msta_link->wcid.idx = idx;
+	msta_link->wcid.phy_idx = band_idx;
 
-	ewma_avg_signal_init(&msta->avg_ack_signal);
+	ewma_avg_signal_init(&msta_link->avg_ack_signal);
 
 	mt7996_mac_wtbl_update(dev, idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
@@ -818,6 +820,7 @@ int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_vif_link *link = &mvif->deflink;
 	int i, ret;
@@ -833,8 +836,8 @@ int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 		if (ret)
 			return ret;
 
-		msta->wcid.tx_info |= MT_WCID_TX_INFO_SET;
-		msta->wcid.sta = 1;
+		msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
+		msta_link->wcid.sta = 1;
 
 		return 0;
 
@@ -843,13 +846,13 @@ int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 					  CONN_STATE_PORT_SECURE, false);
 
 	case MT76_STA_EVENT_DISASSOC:
-		for (i = 0; i < ARRAY_SIZE(msta->twt.flow); i++)
+		for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++)
 			mt7996_mac_twt_teardown_flow(dev, msta, i);
 
 		mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
 				   CONN_STATE_DISCONNECT, false);
-		msta->wcid.sta_disabled = 1;
-		msta->wcid.sta = 0;
+		msta_link->wcid.sta_disabled = 1;
+		msta_link->wcid.sta = 0;
 
 		return 0;
 	}
@@ -862,15 +865,16 @@ void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 {
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 
-	mt7996_mac_wtbl_update(dev, msta->wcid.idx,
+	mt7996_mac_wtbl_update(dev, msta_link->wcid.idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 
 	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta->wcid.poll_list))
-		list_del_init(&msta->wcid.poll_list);
-	if (!list_empty(&msta->rc_list))
-		list_del_init(&msta->rc_list);
+	if (!list_empty(&msta_link->wcid.poll_list))
+		list_del_init(&msta_link->wcid.poll_list);
+	if (!list_empty(&msta_link->rc_list))
+		list_del_init(&msta_link->rc_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
 }
 
@@ -888,7 +892,7 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 		struct mt7996_vif *mvif;
 
 		mvif = (struct mt7996_vif *)vif->drv_priv;
-		wcid = &mvif->deflink.sta.wcid;
+		wcid = &mvif->deflink.sta.deflink.wcid;
 
 		if (mvif->mt76.roc_phy &&
 		    (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)) {
@@ -901,10 +905,10 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 	}
 
 	if (control->sta) {
-		struct mt7996_sta *sta;
+		struct mt7996_sta_link *msta_link;
 
-		sta = (struct mt7996_sta *)control->sta->drv_priv;
-		wcid = &sta->wcid;
+		msta_link = (struct mt7996_sta_link *)control->sta->drv_priv;
+		wcid = &msta_link->wcid;
 	}
 
 	if (!mphy) {
@@ -944,6 +948,7 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	struct ieee80211_sta *sta = params->sta;
 	struct ieee80211_txq *txq = sta->txq[params->tid];
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	u16 tid = params->tid;
 	u16 ssn = params->ssn;
 	struct mt76_txq *mtxq;
@@ -957,12 +962,12 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_lock(&dev->mt76.mutex);
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
-		mt76_rx_aggr_start(&dev->mt76, &msta->wcid, tid, ssn,
+		mt76_rx_aggr_start(&dev->mt76, &msta_link->wcid, tid, ssn,
 				   params->buf_size);
 		ret = mt7996_mcu_add_rx_ba(dev, params, true);
 		break;
 	case IEEE80211_AMPDU_RX_STOP:
-		mt76_rx_aggr_stop(&dev->mt76, &msta->wcid, tid);
+		mt76_rx_aggr_stop(&dev->mt76, &msta_link->wcid, tid);
 		ret = mt7996_mcu_add_rx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_OPERATIONAL:
@@ -973,16 +978,16 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	case IEEE80211_AMPDU_TX_STOP_FLUSH:
 	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->wcid.ampdu_state);
+		clear_bit(tid, &msta_link->wcid.ampdu_state);
 		ret = mt7996_mcu_add_tx_ba(dev, params, false);
 		break;
 	case IEEE80211_AMPDU_TX_START:
-		set_bit(tid, &msta->wcid.ampdu_state);
+		set_bit(tid, &msta_link->wcid.ampdu_state);
 		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
 		break;
 	case IEEE80211_AMPDU_TX_STOP_CONT:
 		mtxq->aggr = false;
-		clear_bit(tid, &msta->wcid.ampdu_state);
+		clear_bit(tid, &msta_link->wcid.ampdu_state);
 		ret = mt7996_mcu_add_tx_ba(dev, params, false);
 		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
 		break;
@@ -1173,7 +1178,8 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw,
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct rate_info *txrate = &msta->wcid.rate;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct rate_info *txrate = &msta_link->wcid.rate;
 
 	if (txrate->legacy || txrate->flags) {
 		if (txrate->legacy) {
@@ -1193,29 +1199,30 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw,
 	sinfo->txrate.flags = txrate->flags;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BITRATE);
 
-	sinfo->tx_failed = msta->wcid.stats.tx_failed;
+	sinfo->tx_failed = msta_link->wcid.stats.tx_failed;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED);
 
-	sinfo->tx_retries = msta->wcid.stats.tx_retries;
+	sinfo->tx_retries = msta_link->wcid.stats.tx_retries;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_RETRIES);
 
-	sinfo->ack_signal = (s8)msta->ack_signal;
+	sinfo->ack_signal = (s8)msta_link->ack_signal;
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL);
 
-	sinfo->avg_ack_signal = -(s8)ewma_avg_signal_read(&msta->avg_ack_signal);
+	sinfo->avg_ack_signal =
+		-(s8)ewma_avg_signal_read(&msta_link->avg_ack_signal);
 	sinfo->filled |= BIT_ULL(NL80211_STA_INFO_ACK_SIGNAL_AVG);
 
 	if (mtk_wed_device_active(&dev->mt76.mmio.wed)) {
-		sinfo->tx_bytes = msta->wcid.stats.tx_bytes;
+		sinfo->tx_bytes = msta_link->wcid.stats.tx_bytes;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_BYTES64);
 
-		sinfo->rx_bytes = msta->wcid.stats.rx_bytes;
+		sinfo->rx_bytes = msta_link->wcid.stats.rx_bytes;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_BYTES64);
 
-		sinfo->tx_packets = msta->wcid.stats.tx_packets;
+		sinfo->tx_packets = msta_link->wcid.stats.tx_packets;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_PACKETS);
 
-		sinfo->rx_packets = msta->wcid.stats.rx_packets;
+		sinfo->rx_packets = msta_link->wcid.stats.rx_packets;
 		sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_PACKETS);
 	}
 }
@@ -1224,12 +1231,13 @@ static void mt7996_sta_rc_work(void *data, struct ieee80211_sta *sta)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_dev *dev = msta->vif->deflink.phy->dev;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	u32 *changed = data;
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
-	msta->changed |= *changed;
-	if (list_empty(&msta->rc_list))
-		list_add_tail(&msta->rc_list, &dev->sta_rc_list);
+	msta_link->changed |= *changed;
+	if (list_empty(&msta_link->rc_list))
+		list_add_tail(&msta_link->rc_list, &dev->sta_rc_list);
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
 }
 
@@ -1276,13 +1284,14 @@ static void mt7996_sta_set_4addr(struct ieee80211_hw *hw,
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 
 	if (enabled)
-		set_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags);
+		set_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
 	else
-		clear_bit(MT_WCID_FLAG_4ADDR, &msta->wcid.flags);
+		clear_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
 
-	if (!msta->wcid.sta)
+	if (!msta_link->wcid.sta)
 		return;
 
 	mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta);
@@ -1295,13 +1304,14 @@ static void mt7996_sta_set_decap_offload(struct ieee80211_hw *hw,
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 
 	if (enabled)
-		set_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags);
+		set_bit(MT_WCID_FLAG_HDR_TRANS, &msta_link->wcid.flags);
 	else
-		clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta->wcid.flags);
+		clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta_link->wcid.flags);
 
-	if (!msta->wcid.sta)
+	if (!msta_link->wcid.sta)
 		return;
 
 	mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta);
@@ -1436,11 +1446,12 @@ static void mt7996_ethtool_worker(void *wi_data, struct ieee80211_sta *sta)
 {
 	struct mt76_ethtool_worker_info *wi = wi_data;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 
 	if (msta->vif->deflink.mt76.idx != wi->idx)
 		return;
 
-	mt76_ethtool_worker(wi, &msta->wcid.stats, true);
+	mt76_ethtool_worker(wi, &msta_link->wcid.stats, true);
 }
 
 static
@@ -1617,6 +1628,7 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif_link *mlink = &mvif->deflink;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
@@ -1632,7 +1644,7 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 	if (!mtk_wed_device_active(wed))
 		return -ENODEV;
 
-	if (!msta->wcid.sta || msta->wcid.idx > MT7996_WTBL_STA)
+	if (!msta_link->wcid.sta || msta_link->wcid.idx > MT7996_WTBL_STA)
 		return -EIO;
 
 	path->type = DEV_PATH_MTK_WDMA;
@@ -1640,7 +1652,7 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 	path->mtk_wdma.wdma_idx = wed->wdma_idx;
 	path->mtk_wdma.bss = mvif->deflink.mt76.idx;
 	path->mtk_wdma.queue = 0;
-	path->mtk_wdma.wcid = msta->wcid.idx;
+	path->mtk_wdma.wcid = msta_link->wcid.idx;
 
 	path->mtk_wdma.amsdu = mtk_wed_is_amsdu_supported(wed);
 	ctx->dev = NULL;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 76f489e2f6021..b0ddc2af15169 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1162,10 +1162,11 @@ int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 			 bool enable)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)params->sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif *mvif = msta->vif;
 
 	if (enable && !params->amsdu)
-		msta->wcid.amsdu = false;
+		msta_link->wcid.amsdu = false;
 
 	return mt7996_mcu_sta_ba(dev, &mvif->deflink.mt76, params, enable, true);
 }
@@ -1322,6 +1323,7 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 			 struct ieee80211_vif *vif, struct ieee80211_sta *sta)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sta_rec_amsdu *amsdu;
 	struct tlv *tlv;
 
@@ -1337,7 +1339,7 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	amsdu = (struct sta_rec_amsdu *)tlv;
 	amsdu->max_amsdu_num = 8;
 	amsdu->amsdu_en = true;
-	msta->wcid.amsdu = true;
+	msta_link->wcid.amsdu = true;
 
 	switch (sta->deflink.agg.max_amsdu_len) {
 	case IEEE80211_MAX_MPDU_LEN_VHT_11454:
@@ -1879,13 +1881,14 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sta_phy_uni *phy = data;
 	struct sta_rec_ra_fixed_uni *ra;
 	struct sk_buff *skb;
 	struct tlv *tlv;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
-					      &msta->wcid,
+					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -1972,14 +1975,14 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 	/* fixed GI */
 	if (mask->control[band].gi != NL80211_TXRATE_DEFAULT_GI ||
 	    mask->control[band].he_gi != GENMASK(7, 0)) {
-		struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+		struct mt7996_sta_link *msta_link = (void *)sta->drv_priv;
 		u32 addr;
 
 		/* firmware updates only TXCMD but doesn't take WTBL into
 		 * account, so driver should update here to reflect the
 		 * actual txrate hardware sends out.
 		 */
-		addr = mt7996_mac_wtbl_lmac_addr(dev, msta->wcid.idx, 7);
+		addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 7);
 		if (sta->deflink.he_cap.has_he)
 			mt76_rmw_field(dev, addr, GENMASK(31, 24), phy.sgi);
 		else
@@ -2113,11 +2116,12 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sk_buff *skb;
 	int ret;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
-					      &msta->wcid,
+					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -2148,6 +2152,7 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 {
 #define MT_STA_BSS_GROUP		1
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta_link *msta_link;
 	struct mt7996_sta *msta;
 	struct {
 		u8 __rsv1[4];
@@ -2167,7 +2172,8 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	};
 
 	msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta;
-	req.wlan_idx = cpu_to_le16(msta->wcid.idx);
+	msta_link = &msta->deflink;
+	req.wlan_idx = cpu_to_le16(msta_link->wcid.idx);
 
 	return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(VOW), &req,
 				 sizeof(req), true);
@@ -2184,8 +2190,9 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 
 	if (sta) {
 		struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+		struct mt7996_sta_link *msta_link = &msta->deflink;
 
-		wcid = &msta->wcid;
+		wcid = &msta_link->wcid;
 		link_sta = &sta->deflink;
 	}
 
@@ -2312,12 +2319,14 @@ static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 {
 #define TSC_TYPE_BIGTK_PN 2
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta_link *msta_link = &mvif->deflink.sta.deflink;
 	struct sta_rec_pn_info *pn_info;
 	struct sk_buff *skb, *rskb;
 	struct tlv *tlv;
 	int ret;
 
-	skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76, &mvif->deflink.sta.wcid);
+	skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
+					    &msta_link->wcid);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -4344,19 +4353,21 @@ int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     struct ieee80211_sta *sta)
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	struct mt7996_sta_link *msta_link;
 	struct mt7996_sta *msta;
 	struct sk_buff *skb;
 
 	msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta;
+	msta_link = &msta->deflink;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
-					      &msta->wcid,
+					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
 	/* starec hdr trans */
-	mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, &msta->wcid);
+	mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, &msta_link->wcid);
 	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 }
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 29fabb9b04ae3..d0a4240f12a48 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -185,10 +185,10 @@ struct mt7996_twt_flow {
 
 DECLARE_EWMA(avg_signal, 10, 8)
 
-struct mt7996_sta {
+struct mt7996_sta_link {
 	struct mt76_wcid wcid; /* must be first */
 
-	struct mt7996_vif *vif;
+	struct mt7996_sta *sta;
 
 	struct list_head rc_list;
 	u32 airtime_ac[8];
@@ -206,6 +206,12 @@ struct mt7996_sta {
 	} twt;
 };
 
+struct mt7996_sta {
+	struct mt7996_sta_link deflink; /* must be first */
+
+	struct mt7996_vif *vif;
+};
+
 struct mt7996_vif_link {
 	struct mt76_vif_link mt76; /* must be first */
 

From 35997d7d39cce52c8ffa1e06acac6240e67bca33 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:02 +0100
Subject: [PATCH 2304/2753] wifi: mt76: mt7996: Add mt7996_sta_link struct in
 mt7996_vif_link

Introduce mt7996_sta_link field in mt7996_vif_link structure instead of
mt7996_sta. This is a preliminary patch to support MLO in MT7996 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-3-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  6 ++---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 24 ++++++++++---------
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 10 ++++----
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  2 +-
 4 files changed, 22 insertions(+), 20 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 754f8e520f52f..456666eb7080c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -72,10 +72,10 @@ static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
 	msta_link = container_of(wcid, struct mt7996_sta_link, wcid);
 	msta = msta_link->sta;
 
-	if (!msta->vif)
+	if (!msta || !msta->vif)
 		return NULL;
 
-	return &msta->vif->deflink.sta.deflink.wcid;
+	return &msta->vif->deflink.msta_link.wcid;
 }
 
 bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask)
@@ -202,7 +202,7 @@ void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
 			      struct ieee80211_vif *vif, bool enable)
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link = &mvif->deflink.sta.deflink;
+	struct mt7996_sta_link *msta_link = &mvif->deflink.msta_link;
 	u32 addr;
 
 	addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 5);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 0cd011619fd3f..34f984387c007 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -161,19 +161,23 @@ mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		  struct mt7996_vif_link *mlink, struct ieee80211_key_conf *key)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt7996_sta *msta = sta ? (struct mt7996_sta *)sta->drv_priv :
-				  &mlink->sta;
-	struct mt76_wcid *wcid = &msta->deflink.wcid;
-	u8 *wcid_keyidx = &wcid->hw_key_idx;
+	struct mt76_wcid *wcid = &mlink->msta_link.wcid;
 	struct mt7996_phy *phy;
 	int idx = key->keyidx;
+	u8 *wcid_keyidx;
 
 	phy = mt7996_vif_link_phy(mlink);
 	if (!phy)
 		return -EINVAL;
 
-	if (sta && !wcid->sta)
-		return -EOPNOTSUPP;
+	if (sta) {
+		struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+
+		wcid = &msta->deflink.wcid;
+		if (!wcid->sta)
+			return -EOPNOTSUPP;
+	}
+	wcid_keyidx = &wcid->hw_key_idx;
 
 	switch (key->cipher) {
 	case WLAN_CIPHER_SUITE_AES_CMAC:
@@ -229,7 +233,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 			struct mt76_vif_link *mlink)
 {
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
-	struct mt7996_sta_link *msta_link = &link->sta.deflink;
+	struct mt7996_sta_link *msta_link = &link->msta_link;
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
 	u8 band_idx = phy->mt76->band_idx;
@@ -261,7 +265,6 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	idx = MT7996_WTBL_RESERVED - mlink->idx;
 
 	INIT_LIST_HEAD(&msta_link->rc_list);
-	msta_link->sta = &link->sta;
 	msta_link->wcid.idx = idx;
 	msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	mt76_wcid_init(&msta_link->wcid, band_idx);
@@ -303,10 +306,9 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 			    struct mt76_vif_link *mlink)
 {
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
+	struct mt7996_sta_link *msta_link = &link->msta_link;
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
-	struct mt7996_sta *msta = &link->sta;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
 	int idx = msta_link->wcid.idx;
 
 	mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_DISCONNECT, false);
@@ -892,7 +894,7 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 		struct mt7996_vif *mvif;
 
 		mvif = (struct mt7996_vif *)vif->drv_priv;
-		wcid = &mvif->deflink.sta.deflink.wcid;
+		wcid = &mvif->deflink.msta_link.wcid;
 
 		if (mvif->mt76.roc_phy &&
 		    (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)) {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index b0ddc2af15169..9018ede6efed4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2171,8 +2171,8 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		.val = cpu_to_le32(mvif->deflink.mt76.idx % 16),
 	};
 
-	msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta;
-	msta_link = &msta->deflink;
+	msta = sta ? (struct mt7996_sta *)sta->drv_priv : NULL;
+	msta_link = msta ? &msta->deflink : &mvif->deflink.msta_link;
 	req.wlan_idx = cpu_to_le16(msta_link->wcid.idx);
 
 	return mt76_mcu_send_msg(&dev->mt76, MCU_WM_UNI_CMD(VOW), &req,
@@ -2319,7 +2319,7 @@ static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 {
 #define TSC_TYPE_BIGTK_PN 2
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link = &mvif->deflink.sta.deflink;
+	struct mt7996_sta_link *msta_link = &mvif->deflink.msta_link;
 	struct sta_rec_pn_info *pn_info;
 	struct sk_buff *skb, *rskb;
 	struct tlv *tlv;
@@ -4357,8 +4357,8 @@ int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 	struct mt7996_sta *msta;
 	struct sk_buff *skb;
 
-	msta = sta ? (struct mt7996_sta *)sta->drv_priv : &mvif->deflink.sta;
-	msta_link = &msta->deflink;
+	msta = sta ? (struct mt7996_sta *)sta->drv_priv : NULL;
+	msta_link = msta ? &msta->deflink : &mvif->deflink.msta_link;
 
 	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
 					      &msta_link->wcid,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index d0a4240f12a48..ac5b94e1315ec 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -215,7 +215,7 @@ struct mt7996_sta {
 struct mt7996_vif_link {
 	struct mt76_vif_link mt76; /* must be first */
 
-	struct mt7996_sta sta;
+	struct mt7996_sta_link msta_link;
 	struct mt7996_phy *phy;
 
 	struct ieee80211_tx_queue_params queue_params[IEEE80211_NUM_ACS];

From 2b967a3ad1b054b8a2e0eaa503009029f0e4ffe5 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:03 +0100
Subject: [PATCH 2305/2753] wifi: mt76: mt7996: Add vif_cfg_changed callback

Introduce vif_cfg_changed mac80211 callback as preliminary patch to
enable MLO support in MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-4-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 35 ++++++++++++++++++-
 1 file changed, 34 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 34f984387c007..59a1e5e52450a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -679,6 +679,39 @@ mt7996_update_mu_group(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mt76_wr(dev, MT_WF_PHYRX_BAND_GID_TAB_POS3(band), mu[3]);
 }
 
+static void
+mt7996_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		       u64 changed)
+{
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+
+	mutex_lock(&dev->mt76.mutex);
+
+	if ((changed & BSS_CHANGED_ASSOC) && vif->cfg.assoc) {
+		struct ieee80211_bss_conf *link_conf;
+		unsigned long link_id;
+
+		for_each_vif_active_link(vif, link_conf, link_id) {
+			struct mt7996_vif_link *link;
+
+			link = mt7996_vif_link(dev, vif, link_id);
+			if (!link)
+				continue;
+
+			if (!link->phy)
+				continue;
+
+			mt7996_mcu_add_bss_info(link->phy, vif, link_conf,
+						&link->mt76, true);
+			mt7996_mcu_add_sta(dev, vif, &link->mt76, NULL,
+					   CONN_STATE_PORT_SECURE,
+					   !!(changed & BSS_CHANGED_BSSID));
+		}
+	}
+
+	mutex_unlock(&dev->mt76.mutex);
+}
+
 static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 				    struct ieee80211_vif *vif,
 				    struct ieee80211_bss_conf *info,
@@ -705,7 +738,6 @@ static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
 	 * and then peer references bss_info_rfch to set bandwidth cap.
 	 */
 	if ((changed & BSS_CHANGED_BSSID && !is_zero_ether_addr(info->bssid)) ||
-	    (changed & BSS_CHANGED_ASSOC && vif->cfg.assoc) ||
 	    (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon)) {
 		mt7996_mcu_add_bss_info(phy, vif, info, mvif, true);
 		mt7996_mcu_add_sta(dev, vif, mvif, NULL, CONN_STATE_PORT_SECURE,
@@ -1688,6 +1720,7 @@ const struct ieee80211_ops mt7996_ops = {
 	.conf_tx = mt7996_conf_tx,
 	.configure_filter = mt7996_configure_filter,
 	.bss_info_changed = mt7996_bss_info_changed,
+	.vif_cfg_changed = mt7996_vif_cfg_changed,
 	.sta_state = mt76_sta_state,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
 	.link_sta_rc_update = mt7996_sta_rc_update,

From 0a04597cd37bd258f3d361556999944aef1eba91 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:04 +0100
Subject: [PATCH 2306/2753] wifi: mt76: mt7996: Add link_info_changed callback

Convert bss_info_changed mac80211 callback in link_info_changed one.
This is a preliminary patch to enable MLO support in MT7996 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-5-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 59a1e5e52450a..81a13662db24e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -712,10 +712,9 @@ mt7996_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
-static void mt7996_bss_info_changed(struct ieee80211_hw *hw,
-				    struct ieee80211_vif *vif,
-				    struct ieee80211_bss_conf *info,
-				    u64 changed)
+static void
+mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			 struct ieee80211_bss_conf *info, u64 changed)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt76_vif_link *mvif;
@@ -1719,8 +1718,8 @@ const struct ieee80211_ops mt7996_ops = {
 	.config = mt7996_config,
 	.conf_tx = mt7996_conf_tx,
 	.configure_filter = mt7996_configure_filter,
-	.bss_info_changed = mt7996_bss_info_changed,
 	.vif_cfg_changed = mt7996_vif_cfg_changed,
+	.link_info_changed = mt7996_link_info_changed,
 	.sta_state = mt76_sta_state,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
 	.link_sta_rc_update = mt7996_sta_rc_update,

From e5d944b4af63285cc5133d9619cc2a4722cb588d Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:05 +0100
Subject: [PATCH 2307/2753] wifi: mt76: mt7996: Add mt7996_sta_state routine

Introduce mt7996_sta_state routine in order to initialize wcid structure
in mt7996 codebase. This is a preliminary patch to enable MLO support in
MT7996 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-6-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mac80211.c |   5 +-
 drivers/net/wireless/mediatek/mt76/mt76.h     |   2 +
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 100 +++++++++++++++---
 .../net/wireless/mediatek/mt76/mt7996/mmio.c  |   3 -
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |   6 --
 5 files changed, 91 insertions(+), 25 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 2c98cc42cd7e6..b88d7e10742ee 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -816,8 +816,8 @@ void mt76_free_device(struct mt76_dev *dev)
 }
 EXPORT_SYMBOL_GPL(mt76_free_device);
 
-static struct mt76_phy *
-mt76_vif_phy(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
+struct mt76_phy *mt76_vif_phy(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif)
 {
 	struct mt76_vif_link *mlink = (struct mt76_vif_link *)vif->drv_priv;
 	struct mt76_chanctx *ctx;
@@ -831,6 +831,7 @@ mt76_vif_phy(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	ctx = (struct mt76_chanctx *)mlink->ctx->drv_priv;
 	return ctx->phy;
 }
+EXPORT_SYMBOL_GPL(mt76_vif_phy);
 
 static void mt76_rx_release_amsdu(struct mt76_phy *phy, enum mt76_rxq_id q)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index b461273c33064..d7cd467b812fc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -1228,6 +1228,8 @@ struct mt76_phy *mt76_alloc_phy(struct mt76_dev *dev, unsigned int size,
 				u8 band_idx);
 int mt76_register_phy(struct mt76_phy *phy, bool vht,
 		      struct ieee80211_rate *rates, int n_rates);
+struct mt76_phy *mt76_vif_phy(struct ieee80211_hw *hw,
+			      struct ieee80211_vif *vif);
 
 struct dentry *mt76_register_debugfs_fops(struct mt76_phy *phy,
 					  const struct file_operations *ops);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 81a13662db24e..d99a98d57142f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -815,20 +815,26 @@ mt7996_channel_switch_beacon(struct ieee80211_hw *hw,
 	mutex_unlock(&dev->mt76.mutex);
 }
 
-int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-		       struct ieee80211_sta *sta)
+static int
+mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
 {
+	struct mt76_dev *mdev = mphy->dev;
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif_link *link = &mvif->deflink;
-	u8 band_idx = link->phy->mt76->band_idx;
-	int idx;
+	u8 band_idx = mphy->band_idx;
+	int i, idx, ret = 0;
 
-	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7996_WTBL_STA);
-	if (idx < 0)
-		return -ENOSPC;
+	mutex_lock(&mdev->mutex);
+
+	idx = mt76_wcid_alloc(mdev->wcid_mask, MT7996_WTBL_STA);
+	if (idx < 0) {
+		ret = -ENOSPC;
+		goto unlock;
+	}
 
 	msta->vif = mvif;
 	INIT_LIST_HEAD(&msta_link->rc_list);
@@ -838,20 +844,37 @@ int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	msta_link->wcid.idx = idx;
 	msta_link->wcid.phy_idx = band_idx;
 
+	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
+		struct mt76_txq *mtxq;
+
+		if (!sta->txq[i])
+			continue;
+
+		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
+		mtxq->wcid = idx;
+	}
+
 	ewma_avg_signal_init(&msta_link->avg_ack_signal);
+	ewma_signal_init(&msta_link->wcid.rssi);
 
 	mt7996_mac_wtbl_update(dev, idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
 	mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, CONN_STATE_DISCONNECT,
 			   true);
 
-	return 0;
+	rcu_assign_pointer(mdev->wcid[idx], &msta_link->wcid);
+	mt76_wcid_init(&msta_link->wcid, band_idx);
+	mphy->num_sta++;
+unlock:
+	mutex_unlock(&mdev->mutex);
+
+	return ret;
 }
 
-int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			 struct ieee80211_sta *sta, enum mt76_sta_event ev)
+static int
+mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+		     struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
-	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
@@ -893,12 +916,20 @@ int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	return 0;
 }
 
-void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta)
+static void
+mt7996_mac_sta_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
+		      struct ieee80211_sta *sta)
 {
+	struct mt76_dev *mdev = mphy->dev;
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_sta_link *msta_link = &msta->deflink;
+	int i, idx = msta_link->wcid.idx;
+
+	mutex_lock(&mdev->mutex);
+
+	for (i = 0; i < ARRAY_SIZE(msta_link->wcid.aggr); i++)
+		mt76_rx_aggr_stop(mdev, &msta_link->wcid, i);
 
 	mt7996_mac_wtbl_update(dev, msta_link->wcid.idx,
 			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
@@ -909,6 +940,47 @@ void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
 	if (!list_empty(&msta_link->rc_list))
 		list_del_init(&msta_link->rc_list);
 	spin_unlock_bh(&mdev->sta_poll_lock);
+
+	mt76_wcid_cleanup(mdev, &msta_link->wcid);
+	mt76_wcid_mask_clear(mdev->wcid_mask, idx);
+	mphy->num_sta--;
+
+	mutex_unlock(&mdev->mutex);
+}
+
+static int
+mt7996_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+		 struct ieee80211_sta *sta, enum ieee80211_sta_state old_state,
+		 enum ieee80211_sta_state new_state)
+{
+	struct mt76_phy *mphy = mt76_vif_phy(hw, vif);
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	enum mt76_sta_event ev;
+
+	if (!mphy)
+		return -EINVAL;
+
+	if (old_state == IEEE80211_STA_NOTEXIST &&
+	    new_state == IEEE80211_STA_NONE)
+		return mt7996_mac_sta_add(mphy, vif, sta);
+
+	if (old_state == IEEE80211_STA_NONE &&
+	    new_state == IEEE80211_STA_NOTEXIST)
+		mt7996_mac_sta_remove(mphy, vif, sta);
+
+	if (old_state == IEEE80211_STA_AUTH &&
+	    new_state == IEEE80211_STA_ASSOC)
+		ev = MT76_STA_EVENT_ASSOC;
+	else if (old_state == IEEE80211_STA_ASSOC &&
+		 new_state == IEEE80211_STA_AUTHORIZED)
+		ev = MT76_STA_EVENT_AUTHORIZE;
+	else if (old_state == IEEE80211_STA_ASSOC &&
+		 new_state == IEEE80211_STA_AUTH)
+		ev = MT76_STA_EVENT_DISASSOC;
+	else
+		return 0;
+
+	return mt7996_mac_sta_event(dev, vif, sta, ev);
 }
 
 static void mt7996_tx(struct ieee80211_hw *hw,
@@ -1720,7 +1792,7 @@ const struct ieee80211_ops mt7996_ops = {
 	.configure_filter = mt7996_configure_filter,
 	.vif_cfg_changed = mt7996_vif_cfg_changed,
 	.link_info_changed = mt7996_link_info_changed,
-	.sta_state = mt76_sta_state,
+	.sta_state = mt7996_sta_state,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
 	.link_sta_rc_update = mt7996_sta_rc_update,
 	.set_key = mt7996_set_key,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
index 9d37f82387464..13b188e281bdb 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mmio.c
@@ -618,9 +618,6 @@ struct mt7996_dev *mt7996_mmio_probe(struct device *pdev,
 		.rx_skb = mt7996_queue_rx_skb,
 		.rx_check = mt7996_rx_check,
 		.rx_poll_complete = mt7996_rx_poll_complete,
-		.sta_add = mt7996_mac_sta_add,
-		.sta_event = mt7996_mac_sta_event,
-		.sta_remove = mt7996_mac_sta_remove,
 		.update_survey = mt7996_update_channel,
 		.set_channel = mt7996_set_channel,
 		.vif_link_add = mt7996_vif_link_add,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index ac5b94e1315ec..117a9e6c49645 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -696,12 +696,6 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct ieee80211_key_conf *key, int pid,
 			   enum mt76_txq_id qid, u32 changed);
 void mt7996_mac_set_coverage_class(struct mt7996_phy *phy);
-int mt7996_mac_sta_add(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-		       struct ieee80211_sta *sta);
-int mt7996_mac_sta_event(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			 struct ieee80211_sta *sta, enum mt76_sta_event ev);
-void mt7996_mac_sta_remove(struct mt76_dev *mdev, struct ieee80211_vif *vif,
-			   struct ieee80211_sta *sta);
 void mt7996_mac_work(struct work_struct *work);
 void mt7996_mac_reset_work(struct work_struct *work);
 void mt7996_mac_dump_work(struct work_struct *work);

From dd82a9e02c054052b5899872c1f32805428f6131 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:06 +0100
Subject: [PATCH 2308/2753] wifi: mt76: mt7996: Rely on mt7996_sta_link in
 sta_add/sta_remove callbacks

Generalize mt7996_mac_sta_add() and mt7996_mac_sta_remove() routines to
deal with mt7996_sta_link structure.
This is a preliminary patch to introduce MLO support for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-7-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 189 +++++++++++++-----
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |   4 +
 2 files changed, 143 insertions(+), 50 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index d99a98d57142f..1bca444d2d023 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -816,59 +816,164 @@ mt7996_channel_switch_beacon(struct ieee80211_hw *hw,
 }
 
 static int
-mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
-		   struct ieee80211_sta *sta)
+mt7996_mac_sta_init_link(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			 struct mt7996_vif_link *link,
+			 struct ieee80211_sta *sta, unsigned int link_id)
 {
-	struct mt76_dev *mdev = mphy->dev;
-	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
-	struct mt7996_vif_link *link = &mvif->deflink;
-	u8 band_idx = mphy->band_idx;
-	int i, idx, ret = 0;
+	struct mt7996_phy *phy = link->phy;
+	struct mt7996_sta_link *msta_link;
+	int idx;
 
-	mutex_lock(&mdev->mutex);
+	idx = mt76_wcid_alloc(dev->mt76.wcid_mask, MT7996_WTBL_STA);
+	if (idx < 0)
+		return -ENOSPC;
+
+	if (msta->deflink_id == IEEE80211_LINK_UNSPECIFIED) {
+		int i;
+
+		msta_link = &msta->deflink;
+		msta->deflink_id = link_id;
+
+		for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
+			struct mt76_txq *mtxq;
+
+			if (!sta->txq[i])
+				continue;
 
-	idx = mt76_wcid_alloc(mdev->wcid_mask, MT7996_WTBL_STA);
-	if (idx < 0) {
-		ret = -ENOSPC;
-		goto unlock;
+			mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
+			mtxq->wcid = idx;
+		}
+	} else {
+		msta_link = kzalloc(sizeof(*msta_link), GFP_KERNEL);
+		if (!msta_link)
+			return -ENOMEM;
 	}
 
-	msta->vif = mvif;
 	INIT_LIST_HEAD(&msta_link->rc_list);
 	INIT_LIST_HEAD(&msta_link->wcid.poll_list);
 	msta_link->sta = msta;
 	msta_link->wcid.sta = 1;
 	msta_link->wcid.idx = idx;
-	msta_link->wcid.phy_idx = band_idx;
+	msta_link->wcid.link_id = link_id;
+
+	ewma_avg_signal_init(&msta_link->avg_ack_signal);
+	ewma_signal_init(&msta_link->wcid.rssi);
 
-	for (i = 0; i < ARRAY_SIZE(sta->txq); i++) {
-		struct mt76_txq *mtxq;
+	rcu_assign_pointer(msta->link[link_id], msta_link);
 
-		if (!sta->txq[i])
+	mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
+	mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, CONN_STATE_DISCONNECT,
+			   true);
+
+	rcu_assign_pointer(dev->mt76.wcid[idx], &msta_link->wcid);
+	mt76_wcid_init(&msta_link->wcid, phy->mt76->band_idx);
+
+	return 0;
+}
+
+static void
+mt7996_mac_sta_deinit_link(struct mt7996_dev *dev,
+			   struct mt7996_sta_link *msta_link)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(msta_link->wcid.aggr); i++)
+		mt76_rx_aggr_stop(&dev->mt76, &msta_link->wcid, i);
+
+	mt7996_mac_wtbl_update(dev, msta_link->wcid.idx,
+			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
+
+	spin_lock_bh(&dev->mt76.sta_poll_lock);
+	if (!list_empty(&msta_link->wcid.poll_list))
+		list_del_init(&msta_link->wcid.poll_list);
+	if (!list_empty(&msta_link->rc_list))
+		list_del_init(&msta_link->rc_list);
+	spin_unlock_bh(&dev->mt76.sta_poll_lock);
+
+	mt76_wcid_cleanup(&dev->mt76, &msta_link->wcid);
+	mt76_wcid_mask_clear(dev->mt76.wcid_mask, msta_link->wcid.idx);
+}
+
+static void
+mt7996_mac_sta_remove_links(struct mt7996_dev *dev, struct ieee80211_sta *sta,
+			    unsigned long links)
+{
+	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt76_dev *mdev = &dev->mt76;
+	unsigned int link_id;
+
+	for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct mt7996_sta_link *msta_link = NULL;
+
+		msta_link = rcu_replace_pointer(msta->link[link_id], msta_link,
+						lockdep_is_held(&mdev->mutex));
+		if (!msta_link)
 			continue;
 
-		mtxq = (struct mt76_txq *)sta->txq[i]->drv_priv;
-		mtxq->wcid = idx;
+		mt7996_mac_sta_deinit_link(dev, msta_link);
+		if (msta->deflink_id == link_id) {
+			msta->deflink_id = IEEE80211_LINK_UNSPECIFIED;
+			continue;
+		}
+
+		kfree_rcu(msta_link, rcu_head);
 	}
+}
 
-	ewma_avg_signal_init(&msta_link->avg_ack_signal);
-	ewma_signal_init(&msta_link->wcid.rssi);
+static int
+mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+			 struct ieee80211_sta *sta, unsigned long new_links)
+{
+	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	unsigned int link_id;
+	int err;
 
-	mt7996_mac_wtbl_update(dev, idx,
-			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
-	mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, CONN_STATE_DISCONNECT,
-			   true);
+	for_each_set_bit(link_id, &new_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct mt7996_vif_link *link;
+
+		if (rcu_access_pointer(msta->link[link_id]))
+			continue;
+
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			goto error_unlink;
+
+		err = mt7996_mac_sta_init_link(dev, vif, link, sta, link_id);
+		if (err)
+			goto error_unlink;
+	}
+
+	return 0;
+
+error_unlink:
+	mt7996_mac_sta_remove_links(dev, sta, new_links);
+
+	return err;
+}
+
+static int
+mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
+		   struct ieee80211_sta *sta)
+{
+	struct mt76_dev *mdev = mphy->dev;
+	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
+	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+	unsigned long links = sta->mlo ? sta->valid_links : BIT(0);
+	int err;
+
+	mutex_lock(&mdev->mutex);
+
+	msta->deflink_id = IEEE80211_LINK_UNSPECIFIED;
+	msta->vif = mvif;
+	err = mt7996_mac_sta_add_links(dev, vif, sta, links);
+	if (!err)
+		mphy->num_sta++;
 
-	rcu_assign_pointer(mdev->wcid[idx], &msta_link->wcid);
-	mt76_wcid_init(&msta_link->wcid, band_idx);
-	mphy->num_sta++;
-unlock:
 	mutex_unlock(&mdev->mutex);
 
-	return ret;
+	return err;
 }
 
 static int
@@ -922,27 +1027,11 @@ mt7996_mac_sta_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 {
 	struct mt76_dev *mdev = mphy->dev;
 	struct mt7996_dev *dev = container_of(mdev, struct mt7996_dev, mt76);
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
-	int i, idx = msta_link->wcid.idx;
+	unsigned long links = sta->mlo ? sta->valid_links : BIT(0);
 
 	mutex_lock(&mdev->mutex);
 
-	for (i = 0; i < ARRAY_SIZE(msta_link->wcid.aggr); i++)
-		mt76_rx_aggr_stop(mdev, &msta_link->wcid, i);
-
-	mt7996_mac_wtbl_update(dev, msta_link->wcid.idx,
-			       MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
-
-	spin_lock_bh(&mdev->sta_poll_lock);
-	if (!list_empty(&msta_link->wcid.poll_list))
-		list_del_init(&msta_link->wcid.poll_list);
-	if (!list_empty(&msta_link->rc_list))
-		list_del_init(&msta_link->rc_list);
-	spin_unlock_bh(&mdev->sta_poll_lock);
-
-	mt76_wcid_cleanup(mdev, &msta_link->wcid);
-	mt76_wcid_mask_clear(mdev->wcid_mask, idx);
+	mt7996_mac_sta_remove_links(dev, sta, links);
 	mphy->num_sta--;
 
 	mutex_unlock(&mdev->mutex);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 117a9e6c49645..cf37baa91a8ba 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -204,10 +204,14 @@ struct mt7996_sta_link {
 		u8 flowid_mask;
 		struct mt7996_twt_flow flow[MT7996_MAX_STA_TWT_AGRT];
 	} twt;
+
+	struct rcu_head rcu_head;
 };
 
 struct mt7996_sta {
 	struct mt7996_sta_link deflink; /* must be first */
+	struct mt7996_sta_link __rcu *link[IEEE80211_MLD_MAX_NUM_LINKS];
+	u8 deflink_id;
 
 	struct mt7996_vif *vif;
 };

From f520eceacd24ce8f70e222d31c3e694b21568bd7 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Tue, 11 Mar 2025 18:45:07 +0100
Subject: [PATCH 2309/2753] wifi: mt76: mt7996: Add mt7996_mac_sta_change_links
 callback

Intrdouce mt7996_mac_sta_change_links routine to set change_sta_links
required by mac80211. This is a preliminary patch to introduce MLO
support for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-8-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 21 +++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 1bca444d2d023..307c68c6b0cd7 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -952,6 +952,26 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	return err;
 }
 
+static int
+mt7996_mac_sta_change_links(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+			    struct ieee80211_sta *sta, u16 old_links,
+			    u16 new_links)
+{
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	unsigned long add = new_links & ~old_links;
+	unsigned long rem = old_links & ~new_links;
+	int ret;
+
+	mutex_lock(&dev->mt76.mutex);
+
+	mt7996_mac_sta_remove_links(dev, sta, rem);
+	ret = mt7996_mac_sta_add_links(dev, vif, sta, add);
+
+	mutex_unlock(&dev->mt76.mutex);
+
+	return ret;
+}
+
 static int
 mt7996_mac_sta_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 		   struct ieee80211_sta *sta)
@@ -1921,4 +1941,5 @@ const struct ieee80211_ops mt7996_ops = {
 	.net_setup_tc = mt76_wed_net_setup_tc,
 #endif
 	.change_vif_links = mt7996_change_vif_links,
+	.change_sta_links = mt7996_mac_sta_change_links,
 };

From ecd72f9695e7e250af4d555de22ba302e37c805a Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:08 +0100
Subject: [PATCH 2310/2753] wifi: mt76: mt7996: Support MLO in
 mt7996_mac_sta_event()

Similar to mt7996_mac_sta_add() adn mt7996_mac_sta_remove(), update
mt7996_mac_sta_event routine to take into account MLO support.
Please note mcu routines does not support MLO yet.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-9-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 69 +++++++++++--------
 1 file changed, 40 insertions(+), 29 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 307c68c6b0cd7..6d323b5e4e807 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1001,41 +1001,52 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		     struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_vif_link *link = &mvif->deflink;
-	int i, ret;
-
-	switch (ev) {
-	case MT76_STA_EVENT_ASSOC:
-		ret = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
-					 CONN_STATE_CONNECT, true);
-		if (ret)
-			return ret;
-
-		ret = mt7996_mcu_add_rate_ctrl(dev, vif, sta, false);
-		if (ret)
-			return ret;
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
 
-		msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
-		msta_link->wcid.sta = 1;
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct mt7996_sta_link *msta_link;
+		struct mt7996_vif_link *link;
+		int i, err;
 
-		return 0;
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
 
-	case MT76_STA_EVENT_AUTHORIZE:
-		return mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
-					  CONN_STATE_PORT_SECURE, false);
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
+		if (!msta_link)
+			continue;
 
-	case MT76_STA_EVENT_DISASSOC:
-		for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++)
-			mt7996_mac_twt_teardown_flow(dev, msta, i);
+		switch (ev) {
+		case MT76_STA_EVENT_ASSOC:
+			err = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
+						 CONN_STATE_CONNECT, true);
+			if (err)
+				return err;
 
-		mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
-				   CONN_STATE_DISCONNECT, false);
-		msta_link->wcid.sta_disabled = 1;
-		msta_link->wcid.sta = 0;
+			err = mt7996_mcu_add_rate_ctrl(dev, vif, sta, false);
+			if (err)
+				return err;
 
-		return 0;
+			msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
+			msta_link->wcid.sta = 1;
+			break;
+		case MT76_STA_EVENT_AUTHORIZE:
+			err = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
+						 CONN_STATE_PORT_SECURE, false);
+			if (err)
+				return err;
+			break;
+		case MT76_STA_EVENT_DISASSOC:
+			for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++)
+				mt7996_mac_twt_teardown_flow(dev, msta, i);
+
+			mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
+					   CONN_STATE_DISCONNECT, false);
+			msta_link->wcid.sta_disabled = 1;
+			msta_link->wcid.sta = 0;
+			break;
+		}
 	}
 
 	return 0;

From 9890624c1b3948c1c7f1d0e19ef0bb7680b8c80d Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Tue, 11 Mar 2025 18:45:09 +0100
Subject: [PATCH 2311/2753] wifi: mt76: Check link_conf pointer in
 mt76_connac_mcu_sta_basic_tlv()

This is a preliminary patch to introduce MLO support for MT7996 driver.

Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-10-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
index d0e49d68c5dbf..bafcf5a279e23 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76_connac_mcu.c
@@ -391,7 +391,7 @@ void mt76_connac_mcu_sta_basic_tlv(struct mt76_dev *dev, struct sk_buff *skb,
 		basic->conn_type = cpu_to_le32(CONNECTION_INFRA_BC);
 
 		if (vif->type == NL80211_IFTYPE_STATION &&
-		    !is_zero_ether_addr(link_conf->bssid)) {
+		    link_conf && !is_zero_ether_addr(link_conf->bssid)) {
 			memcpy(basic->peer_addr, link_conf->bssid, ETH_ALEN);
 			basic->aid = cpu_to_le16(vif->cfg.aid);
 		} else {

From c7e4fc362443ecbdae2f0adef16eda955f433473 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Tue, 11 Mar 2025 18:45:10 +0100
Subject: [PATCH 2312/2753] wifi: mt76: mt7996: Update mt7996_mcu_add_sta to
 MLO support

Update mt7996_mcu_add_sta routine and all the called subroutines to
support MLO. This is a preliminary patch to enable MLO for MT7996
driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-11-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  72 +++--
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 296 +++++++++---------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |   9 +-
 3 files changed, 208 insertions(+), 169 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 6d323b5e4e807..5ab4f08dba06f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -293,7 +293,8 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	 * interface, since firmware only records BSSID when the entry is new
 	 */
 	if (vif->type != NL80211_IFTYPE_STATION)
-		mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_PORT_SECURE, true);
+		mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL,
+				   CONN_STATE_PORT_SECURE, true);
 	rcu_assign_pointer(dev->mt76.wcid[idx], &msta_link->wcid);
 
 	ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, link);
@@ -311,7 +312,8 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 	struct mt7996_dev *dev = phy->dev;
 	int idx = msta_link->wcid.idx;
 
-	mt7996_mcu_add_sta(dev, vif, mlink, NULL, CONN_STATE_DISCONNECT, false);
+	mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL,
+			   CONN_STATE_DISCONNECT, false);
 	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, false);
 
 	mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, false);
@@ -703,7 +705,7 @@ mt7996_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 			mt7996_mcu_add_bss_info(link->phy, vif, link_conf,
 						&link->mt76, true);
-			mt7996_mcu_add_sta(dev, vif, &link->mt76, NULL,
+			mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL,
 					   CONN_STATE_PORT_SECURE,
 					   !!(changed & BSS_CHANGED_BSSID));
 		}
@@ -717,17 +719,17 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			 struct ieee80211_bss_conf *info, u64 changed)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt76_vif_link *mvif;
+	struct mt7996_vif_link *link;
 	struct mt7996_phy *phy;
 	struct mt76_phy *mphy;
 
 	mutex_lock(&dev->mt76.mutex);
 
-	mvif = mt76_vif_conf_link(&dev->mt76, vif, info);
-	if (!mvif)
+	link = mt7996_vif_conf_link(dev, vif, info);
+	if (!link)
 		goto out;
 
-	mphy = mt76_vif_link_phy(mvif);
+	mphy = mt76_vif_link_phy(&link->mt76);
 	if (!mphy)
 		goto out;
 
@@ -738,8 +740,9 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	 */
 	if ((changed & BSS_CHANGED_BSSID && !is_zero_ether_addr(info->bssid)) ||
 	    (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon)) {
-		mt7996_mcu_add_bss_info(phy, vif, info, mvif, true);
-		mt7996_mcu_add_sta(dev, vif, mvif, NULL, CONN_STATE_PORT_SECURE,
+		mt7996_mcu_add_bss_info(phy, vif, info, &link->mt76, true);
+		mt7996_mcu_add_sta(dev, info, NULL, link, NULL,
+				   CONN_STATE_PORT_SECURE,
 				   !!(changed & BSS_CHANGED_BSSID));
 	}
 
@@ -756,11 +759,11 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	}
 
 	if (changed & BSS_CHANGED_MCAST_RATE)
-		mvif->mcast_rates_idx =
+		link->mt76.mcast_rates_idx =
 			mt7996_get_rates_table(phy, info, false, true);
 
 	if (changed & BSS_CHANGED_BASIC_RATES)
-		mvif->basic_rates_idx =
+		link->mt76.basic_rates_idx =
 			mt7996_get_rates_table(phy, info, false, false);
 
 	/* ensure that enable txcmd_mode after bss_info */
@@ -772,15 +775,15 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	if (changed & BSS_CHANGED_HE_BSS_COLOR) {
 		if ((vif->type == NL80211_IFTYPE_AP &&
-		    mvif->omac_idx <= HW_BSSID_MAX) ||
+		    link->mt76.omac_idx <= HW_BSSID_MAX) ||
 		   vif->type == NL80211_IFTYPE_STATION)
-			mt7996_mcu_update_bss_color(dev, mvif,
+			mt7996_mcu_update_bss_color(dev, &link->mt76,
 						    &info->he_bss_color);
 	}
 
 	if (changed & (BSS_CHANGED_BEACON |
 		       BSS_CHANGED_BEACON_ENABLED)) {
-		mvif->beacon_rates_idx =
+		link->mt76.beacon_rates_idx =
 			mt7996_get_rates_table(phy, info, true, false);
 
 		mt7996_mcu_add_beacon(hw, vif, info);
@@ -816,10 +819,12 @@ mt7996_channel_switch_beacon(struct ieee80211_hw *hw,
 }
 
 static int
-mt7996_mac_sta_init_link(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			 struct mt7996_vif_link *link,
-			 struct ieee80211_sta *sta, unsigned int link_id)
+mt7996_mac_sta_init_link(struct mt7996_dev *dev,
+			 struct ieee80211_bss_conf *link_conf,
+			 struct ieee80211_link_sta *link_sta,
+			 struct mt7996_vif_link *link, unsigned int link_id)
 {
+	struct ieee80211_sta *sta = link_sta->sta;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_phy *phy = link->phy;
 	struct mt7996_sta_link *msta_link;
@@ -863,8 +868,8 @@ mt7996_mac_sta_init_link(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	rcu_assign_pointer(msta->link[link_id], msta_link);
 
 	mt7996_mac_wtbl_update(dev, idx, MT_WTBL_UPDATE_ADM_COUNT_CLEAR);
-	mt7996_mcu_add_sta(dev, vif, &link->mt76, sta, CONN_STATE_DISCONNECT,
-			   true);
+	mt7996_mcu_add_sta(dev, link_conf, link_sta, link, msta_link,
+			   CONN_STATE_DISCONNECT, true);
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], &msta_link->wcid);
 	mt76_wcid_init(&msta_link->wcid, phy->mt76->band_idx);
@@ -930,16 +935,27 @@ mt7996_mac_sta_add_links(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	int err;
 
 	for_each_set_bit(link_id, &new_links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct ieee80211_bss_conf *link_conf;
+		struct ieee80211_link_sta *link_sta;
 		struct mt7996_vif_link *link;
 
 		if (rcu_access_pointer(msta->link[link_id]))
 			continue;
 
+		link_conf = link_conf_dereference_protected(vif, link_id);
+		if (!link_conf)
+			goto error_unlink;
+
 		link = mt7996_vif_link(dev, vif, link_id);
 		if (!link)
 			goto error_unlink;
 
-		err = mt7996_mac_sta_init_link(dev, vif, link, sta, link_id);
+		link_sta = link_sta_dereference_protected(sta, link_id);
+		if (!link_sta)
+			goto error_unlink;
+
+		err = mt7996_mac_sta_init_link(dev, link_conf, link_sta, link,
+					       link_id);
 		if (err)
 			goto error_unlink;
 	}
@@ -1005,10 +1021,15 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	unsigned int link_id;
 
 	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct ieee80211_bss_conf *link_conf;
 		struct mt7996_sta_link *msta_link;
 		struct mt7996_vif_link *link;
 		int i, err;
 
+		link_conf = link_conf_dereference_protected(vif, link_id);
+		if (!link_conf)
+			continue;
+
 		link = mt7996_vif_link(dev, vif, link_id);
 		if (!link)
 			continue;
@@ -1019,7 +1040,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 
 		switch (ev) {
 		case MT76_STA_EVENT_ASSOC:
-			err = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
+			err = mt7996_mcu_add_sta(dev, link_conf, link_sta,
+						 link, msta_link,
 						 CONN_STATE_CONNECT, true);
 			if (err)
 				return err;
@@ -1032,7 +1054,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			msta_link->wcid.sta = 1;
 			break;
 		case MT76_STA_EVENT_AUTHORIZE:
-			err = mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
+			err = mt7996_mcu_add_sta(dev, link_conf, link_sta,
+						 link, msta_link,
 						 CONN_STATE_PORT_SECURE, false);
 			if (err)
 				return err;
@@ -1041,8 +1064,9 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++)
 				mt7996_mac_twt_teardown_flow(dev, msta, i);
 
-			mt7996_mcu_add_sta(dev, vif, &link->mt76, sta,
-					   CONN_STATE_DISCONNECT, false);
+			mt7996_mcu_add_sta(dev, link_conf, link_sta, link,
+					   msta_link, CONN_STATE_DISCONNECT,
+					   false);
 			msta_link->wcid.sta_disabled = 1;
 			msta_link->wcid.sta = 0;
 			break;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 9018ede6efed4..43e85308132e5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -118,13 +118,13 @@ mt7996_mcu_get_sta_nss(u16 mcs_map)
 }
 
 static void
-mt7996_mcu_set_sta_he_mcs(struct ieee80211_sta *sta, __le16 *he_mcs,
-			  u16 mcs_map)
+mt7996_mcu_set_sta_he_mcs(struct ieee80211_link_sta *link_sta,
+			  struct mt7996_vif_link *link,
+			  __le16 *he_mcs, u16 mcs_map)
 {
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	enum nl80211_band band = msta->vif->deflink.phy->mt76->chandef.chan->band;
-	const u16 *mask = msta->vif->deflink.bitrate_mask.control[band].he_mcs;
-	int nss, max_nss = sta->deflink.rx_nss > 3 ? 4 : sta->deflink.rx_nss;
+	int nss, max_nss = link_sta->rx_nss > 3 ? 4 : link_sta->rx_nss;
+	enum nl80211_band band = link->phy->mt76->chandef.chan->band;
+	const u16 *mask = link->bitrate_mask.control[band].he_mcs;
 
 	for (nss = 0; nss < max_nss; nss++) {
 		int mcs;
@@ -1182,15 +1182,17 @@ int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev,
 }
 
 static void
-mt7996_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+mt7996_mcu_sta_he_tlv(struct sk_buff *skb,
+		      struct ieee80211_link_sta *link_sta,
+		      struct mt7996_vif_link *link)
 {
-	struct ieee80211_he_cap_elem *elem = &sta->deflink.he_cap.he_cap_elem;
+	struct ieee80211_he_cap_elem *elem = &link_sta->he_cap.he_cap_elem;
 	struct ieee80211_he_mcs_nss_supp mcs_map;
 	struct sta_rec_he_v2 *he;
 	struct tlv *tlv;
 	int i = 0;
 
-	if (!sta->deflink.he_cap.has_he)
+	if (!link_sta->he_cap.has_he)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HE_V2, sizeof(*he));
@@ -1202,21 +1204,21 @@ mt7996_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 		he->he_phy_cap[i] = elem->phy_cap_info[i];
 	}
 
-	mcs_map = sta->deflink.he_cap.he_mcs_nss_supp;
-	switch (sta->deflink.bandwidth) {
+	mcs_map = link_sta->he_cap.he_mcs_nss_supp;
+	switch (link_sta->bandwidth) {
 	case IEEE80211_STA_RX_BW_160:
 		if (elem->phy_cap_info[0] &
 		    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
-			mt7996_mcu_set_sta_he_mcs(sta,
+			mt7996_mcu_set_sta_he_mcs(link_sta, link,
 						  &he->max_nss_mcs[CMD_HE_MCS_BW8080],
 						  le16_to_cpu(mcs_map.rx_mcs_80p80));
 
-		mt7996_mcu_set_sta_he_mcs(sta,
+		mt7996_mcu_set_sta_he_mcs(link_sta, link,
 					  &he->max_nss_mcs[CMD_HE_MCS_BW160],
 					  le16_to_cpu(mcs_map.rx_mcs_160));
 		fallthrough;
 	default:
-		mt7996_mcu_set_sta_he_mcs(sta,
+		mt7996_mcu_set_sta_he_mcs(link_sta, link,
 					  &he->max_nss_mcs[CMD_HE_MCS_BW80],
 					  le16_to_cpu(mcs_map.rx_mcs_80));
 		break;
@@ -1226,24 +1228,26 @@ mt7996_mcu_sta_he_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 }
 
 static void
-mt7996_mcu_sta_he_6g_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+mt7996_mcu_sta_he_6g_tlv(struct sk_buff *skb,
+			 struct ieee80211_link_sta *link_sta)
 {
 	struct sta_rec_he_6g_capa *he_6g;
 	struct tlv *tlv;
 
-	if (!sta->deflink.he_6ghz_capa.capa)
+	if (!link_sta->he_6ghz_capa.capa)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HE_6G, sizeof(*he_6g));
 
 	he_6g = (struct sta_rec_he_6g_capa *)tlv;
-	he_6g->capa = sta->deflink.he_6ghz_capa.capa;
+	he_6g->capa = link_sta->he_6ghz_capa.capa;
 }
 
 static void
-mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+mt7996_mcu_sta_eht_tlv(struct sk_buff *skb,
+		       struct ieee80211_link_sta *link_sta)
 {
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta *msta = (struct mt7996_sta *)link_sta->sta->drv_priv;
 	struct ieee80211_vif *vif = container_of((void *)msta->vif,
 						 struct ieee80211_vif, drv_priv);
 	struct ieee80211_eht_mcs_nss_supp *mcs_map;
@@ -1251,11 +1255,11 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 	struct sta_rec_eht *eht;
 	struct tlv *tlv;
 
-	if (!sta->deflink.eht_cap.has_eht)
+	if (!link_sta->eht_cap.has_eht)
 		return;
 
-	mcs_map = &sta->deflink.eht_cap.eht_mcs_nss_supp;
-	elem = &sta->deflink.eht_cap.eht_cap_elem;
+	mcs_map = &link_sta->eht_cap.eht_mcs_nss_supp;
+	elem = &link_sta->eht_cap.eht_cap_elem;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_EHT, sizeof(*eht));
 
@@ -1266,7 +1270,7 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 	eht->phy_cap_ext = cpu_to_le64(elem->phy_cap_info[8]);
 
 	if (vif->type != NL80211_IFTYPE_STATION &&
-	    (sta->deflink.he_cap.he_cap_elem.phy_cap_info[0] &
+	    (link_sta->he_cap.he_cap_elem.phy_cap_info[0] &
 	     (IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G |
 	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G |
 	      IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G |
@@ -1282,48 +1286,48 @@ mt7996_mcu_sta_eht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
 }
 
 static void
-mt7996_mcu_sta_ht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+mt7996_mcu_sta_ht_tlv(struct sk_buff *skb, struct ieee80211_link_sta *link_sta)
 {
 	struct sta_rec_ht_uni *ht;
 	struct tlv *tlv;
 
-	if (!sta->deflink.ht_cap.ht_supported)
+	if (!link_sta->ht_cap.ht_supported)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HT, sizeof(*ht));
 
 	ht = (struct sta_rec_ht_uni *)tlv;
-	ht->ht_cap = cpu_to_le16(sta->deflink.ht_cap.cap);
-	ht->ampdu_param = u8_encode_bits(sta->deflink.ht_cap.ampdu_factor,
+	ht->ht_cap = cpu_to_le16(link_sta->ht_cap.cap);
+	ht->ampdu_param = u8_encode_bits(link_sta->ht_cap.ampdu_factor,
 					 IEEE80211_HT_AMPDU_PARM_FACTOR) |
-			  u8_encode_bits(sta->deflink.ht_cap.ampdu_density,
+			  u8_encode_bits(link_sta->ht_cap.ampdu_density,
 					 IEEE80211_HT_AMPDU_PARM_DENSITY);
 }
 
 static void
-mt7996_mcu_sta_vht_tlv(struct sk_buff *skb, struct ieee80211_sta *sta)
+mt7996_mcu_sta_vht_tlv(struct sk_buff *skb, struct ieee80211_link_sta *link_sta)
 {
 	struct sta_rec_vht *vht;
 	struct tlv *tlv;
 
 	/* For 6G band, this tlv is necessary to let hw work normally */
-	if (!sta->deflink.he_6ghz_capa.capa && !sta->deflink.vht_cap.vht_supported)
+	if (!link_sta->he_6ghz_capa.capa && !link_sta->vht_cap.vht_supported)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_VHT, sizeof(*vht));
 
 	vht = (struct sta_rec_vht *)tlv;
-	vht->vht_cap = cpu_to_le32(sta->deflink.vht_cap.cap);
-	vht->vht_rx_mcs_map = sta->deflink.vht_cap.vht_mcs.rx_mcs_map;
-	vht->vht_tx_mcs_map = sta->deflink.vht_cap.vht_mcs.tx_mcs_map;
+	vht->vht_cap = cpu_to_le32(link_sta->vht_cap.cap);
+	vht->vht_rx_mcs_map = link_sta->vht_cap.vht_mcs.rx_mcs_map;
+	vht->vht_tx_mcs_map = link_sta->vht_cap.vht_mcs.tx_mcs_map;
 }
 
 static void
 mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
-			 struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+			 struct ieee80211_vif *vif,
+			 struct ieee80211_link_sta *link_sta,
+			 struct mt7996_sta_link *msta_link)
 {
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sta_rec_amsdu *amsdu;
 	struct tlv *tlv;
 
@@ -1332,7 +1336,7 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	    vif->type != NL80211_IFTYPE_AP)
 		return;
 
-	if (!sta->deflink.agg.max_amsdu_len)
+	if (!link_sta->agg.max_amsdu_len)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_HW_AMSDU, sizeof(*amsdu));
@@ -1341,7 +1345,7 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	amsdu->amsdu_en = true;
 	msta_link->wcid.amsdu = true;
 
-	switch (sta->deflink.agg.max_amsdu_len) {
+	switch (link_sta->agg.max_amsdu_len) {
 	case IEEE80211_MAX_MPDU_LEN_VHT_11454:
 		amsdu->max_mpdu_size =
 			IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454;
@@ -1358,30 +1362,31 @@ mt7996_mcu_sta_amsdu_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 
 static void
 mt7996_mcu_sta_muru_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
-			struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+			struct ieee80211_bss_conf *link_conf,
+			struct ieee80211_link_sta *link_sta)
 {
-	struct ieee80211_he_cap_elem *elem = &sta->deflink.he_cap.he_cap_elem;
+	struct ieee80211_he_cap_elem *elem = &link_sta->he_cap.he_cap_elem;
 	struct sta_rec_muru *muru;
 	struct tlv *tlv;
 
-	if (vif->type != NL80211_IFTYPE_STATION &&
-	    vif->type != NL80211_IFTYPE_AP)
+	if (link_conf->vif->type != NL80211_IFTYPE_STATION &&
+	    link_conf->vif->type != NL80211_IFTYPE_AP)
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_MURU, sizeof(*muru));
 
 	muru = (struct sta_rec_muru *)tlv;
-	muru->cfg.mimo_dl_en = vif->bss_conf.eht_mu_beamformer ||
-			       vif->bss_conf.he_mu_beamformer ||
-			       vif->bss_conf.vht_mu_beamformer ||
-			       vif->bss_conf.vht_mu_beamformee;
+	muru->cfg.mimo_dl_en = link_conf->eht_mu_beamformer ||
+			       link_conf->he_mu_beamformer ||
+			       link_conf->vht_mu_beamformer ||
+			       link_conf->vht_mu_beamformee;
 	muru->cfg.ofdma_dl_en = true;
 
-	if (sta->deflink.vht_cap.vht_supported)
+	if (link_sta->vht_cap.vht_supported)
 		muru->mimo_dl.vht_mu_bfee =
-			!!(sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE);
+			!!(link_sta->vht_cap.cap & IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE);
 
-	if (!sta->deflink.he_cap.has_he)
+	if (!link_sta->he_cap.has_he)
 		return;
 
 	muru->mimo_dl.partial_bw_dl_mimo =
@@ -1412,49 +1417,50 @@ mt7996_mcu_sta_muru_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 }
 
 static inline bool
-mt7996_is_ebf_supported(struct mt7996_phy *phy, struct ieee80211_vif *vif,
-			struct ieee80211_sta *sta, bool bfee)
+mt7996_is_ebf_supported(struct mt7996_phy *phy,
+			struct ieee80211_bss_conf *link_conf,
+			struct ieee80211_link_sta *link_sta, bool bfee)
 {
 	int sts = hweight16(phy->mt76->chainmask);
 
-	if (vif->type != NL80211_IFTYPE_STATION &&
-	    vif->type != NL80211_IFTYPE_AP)
+	if (link_conf->vif->type != NL80211_IFTYPE_STATION &&
+	    link_conf->vif->type != NL80211_IFTYPE_AP)
 		return false;
 
 	if (!bfee && sts < 2)
 		return false;
 
-	if (sta->deflink.eht_cap.has_eht) {
-		struct ieee80211_sta_eht_cap *pc = &sta->deflink.eht_cap;
+	if (link_sta->eht_cap.has_eht) {
+		struct ieee80211_sta_eht_cap *pc = &link_sta->eht_cap;
 		struct ieee80211_eht_cap_elem_fixed *pe = &pc->eht_cap_elem;
 
 		if (bfee)
-			return vif->bss_conf.eht_su_beamformee &&
+			return link_conf->eht_su_beamformee &&
 			       EHT_PHY(CAP0_SU_BEAMFORMER, pe->phy_cap_info[0]);
 		else
-			return vif->bss_conf.eht_su_beamformer &&
+			return link_conf->eht_su_beamformer &&
 			       EHT_PHY(CAP0_SU_BEAMFORMEE, pe->phy_cap_info[0]);
 	}
 
-	if (sta->deflink.he_cap.has_he) {
-		struct ieee80211_he_cap_elem *pe = &sta->deflink.he_cap.he_cap_elem;
+	if (link_sta->he_cap.has_he) {
+		struct ieee80211_he_cap_elem *pe = &link_sta->he_cap.he_cap_elem;
 
 		if (bfee)
-			return vif->bss_conf.he_su_beamformee &&
+			return link_conf->he_su_beamformee &&
 			       HE_PHY(CAP3_SU_BEAMFORMER, pe->phy_cap_info[3]);
 		else
-			return vif->bss_conf.he_su_beamformer &&
+			return link_conf->he_su_beamformer &&
 			       HE_PHY(CAP4_SU_BEAMFORMEE, pe->phy_cap_info[4]);
 	}
 
-	if (sta->deflink.vht_cap.vht_supported) {
-		u32 cap = sta->deflink.vht_cap.cap;
+	if (link_sta->vht_cap.vht_supported) {
+		u32 cap = link_sta->vht_cap.cap;
 
 		if (bfee)
-			return vif->bss_conf.vht_su_beamformee &&
+			return link_conf->vht_su_beamformee &&
 			       (cap & IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE);
 		else
-			return vif->bss_conf.vht_su_beamformer &&
+			return link_conf->vht_su_beamformer &&
 			       (cap & IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE);
 	}
 
@@ -1475,10 +1481,11 @@ mt7996_mcu_sta_sounding_rate(struct sta_rec_bf *bf, struct mt7996_phy *phy)
 }
 
 static void
-mt7996_mcu_sta_bfer_ht(struct ieee80211_sta *sta, struct mt7996_phy *phy,
-		       struct sta_rec_bf *bf, bool explicit)
+mt7996_mcu_sta_bfer_ht(struct ieee80211_link_sta *link_sta,
+		       struct mt7996_phy *phy, struct sta_rec_bf *bf,
+		       bool explicit)
 {
-	struct ieee80211_mcs_info *mcs = &sta->deflink.ht_cap.mcs;
+	struct ieee80211_mcs_info *mcs = &link_sta->ht_cap.mcs;
 	u8 n = 0;
 
 	bf->tx_mode = MT_PHY_TYPE_HT;
@@ -1501,10 +1508,11 @@ mt7996_mcu_sta_bfer_ht(struct ieee80211_sta *sta, struct mt7996_phy *phy,
 }
 
 static void
-mt7996_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7996_phy *phy,
-			struct sta_rec_bf *bf, bool explicit)
+mt7996_mcu_sta_bfer_vht(struct ieee80211_link_sta *link_sta,
+			struct mt7996_phy *phy, struct sta_rec_bf *bf,
+			bool explicit)
 {
-	struct ieee80211_sta_vht_cap *pc = &sta->deflink.vht_cap;
+	struct ieee80211_sta_vht_cap *pc = &link_sta->vht_cap;
 	struct ieee80211_sta_vht_cap *vc = &phy->mt76->sband_5g.sband.vht_cap;
 	u16 mcs_map = le16_to_cpu(pc->vht_mcs.rx_mcs_map);
 	u8 nss_mcs = mt7996_mcu_get_sta_nss(mcs_map);
@@ -1525,24 +1533,24 @@ mt7996_mcu_sta_bfer_vht(struct ieee80211_sta *sta, struct mt7996_phy *phy,
 		bf->ncol = min_t(u8, nss_mcs, bf->nrow);
 		bf->ibf_ncol = min_t(u8, MT7996_IBF_MAX_NC, bf->ncol);
 
-		if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160)
+		if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160)
 			bf->nrow = 1;
 	} else {
 		bf->nrow = tx_ant;
 		bf->ncol = min_t(u8, nss_mcs, bf->nrow);
 		bf->ibf_ncol = min_t(u8, MT7996_IBF_MAX_NC, nss_mcs);
 
-		if (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_160)
+		if (link_sta->bandwidth == IEEE80211_STA_RX_BW_160)
 			bf->ibf_nrow = 1;
 	}
 }
 
 static void
-mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
-		       struct mt7996_phy *phy, struct sta_rec_bf *bf,
-		       bool explicit)
+mt7996_mcu_sta_bfer_he(struct ieee80211_link_sta *link_sta,
+		       struct ieee80211_vif *vif, struct mt7996_phy *phy,
+		       struct sta_rec_bf *bf, bool explicit)
 {
-	struct ieee80211_sta_he_cap *pc = &sta->deflink.he_cap;
+	struct ieee80211_sta_he_cap *pc = &link_sta->he_cap;
 	struct ieee80211_he_cap_elem *pe = &pc->he_cap_elem;
 	const struct ieee80211_sta_he_cap *vc =
 		mt76_connac_get_he_phy_cap(phy->mt76, vif);
@@ -1571,7 +1579,7 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 	bf->ibf_ncol = explicit ? min_t(u8, MT7996_IBF_MAX_NC, bf->ncol) :
 				  min_t(u8, MT7996_IBF_MAX_NC, nss_mcs);
 
-	if (sta->deflink.bandwidth != IEEE80211_STA_RX_BW_160)
+	if (link_sta->bandwidth != IEEE80211_STA_RX_BW_160)
 		return;
 
 	/* go over for 160MHz and 80p80 */
@@ -1603,11 +1611,11 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 }
 
 static void
-mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
-			struct mt7996_phy *phy, struct sta_rec_bf *bf,
-			bool explicit)
+mt7996_mcu_sta_bfer_eht(struct ieee80211_link_sta *link_sta,
+			struct ieee80211_vif *vif, struct mt7996_phy *phy,
+			struct sta_rec_bf *bf, bool explicit)
 {
-	struct ieee80211_sta_eht_cap *pc = &sta->deflink.eht_cap;
+	struct ieee80211_sta_eht_cap *pc = &link_sta->eht_cap;
 	struct ieee80211_eht_cap_elem_fixed *pe = &pc->eht_cap_elem;
 	struct ieee80211_eht_mcs_nss_supp *eht_nss = &pc->eht_mcs_nss_supp;
 	const struct ieee80211_sta_eht_cap *vc =
@@ -1631,10 +1639,10 @@ mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 	bf->ibf_ncol = explicit ? min_t(u8, MT7996_IBF_MAX_NC, bf->ncol) :
 				  min_t(u8, MT7996_IBF_MAX_NC, nss_mcs);
 
-	if (sta->deflink.bandwidth < IEEE80211_STA_RX_BW_160)
+	if (link_sta->bandwidth < IEEE80211_STA_RX_BW_160)
 		return;
 
-	switch (sta->deflink.bandwidth) {
+	switch (link_sta->bandwidth) {
 	case IEEE80211_STA_RX_BW_160:
 		snd_dim = EHT_PHY(CAP2_SOUNDING_DIM_160MHZ_MASK, ve->phy_cap_info[2]);
 		sts = EHT_PHY(CAP1_BEAMFORMEE_SS_160MHZ_MASK, pe->phy_cap_info[1]);
@@ -1662,13 +1670,15 @@ mt7996_mcu_sta_bfer_eht(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
 
 static void
 mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
-			struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+			struct ieee80211_bss_conf *link_conf,
+			struct ieee80211_link_sta *link_sta,
+			struct mt7996_vif_link *link)
 {
 #define EBF_MODE	BIT(0)
 #define IBF_MODE	BIT(1)
 #define BF_MAT_ORDER	4
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_phy *phy = mvif->deflink.phy;
+	struct ieee80211_vif *vif = link_conf->vif;
+	struct mt7996_phy *phy = link->phy;
 	int tx_ant = hweight16(phy->mt76->chainmask) - 1;
 	struct sta_rec_bf *bf;
 	struct tlv *tlv;
@@ -1680,10 +1690,10 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	};
 	bool ebf;
 
-	if (!(sta->deflink.ht_cap.ht_supported || sta->deflink.he_cap.has_he))
+	if (!(link_sta->ht_cap.ht_supported || link_sta->he_cap.has_he))
 		return;
 
-	ebf = mt7996_is_ebf_supported(phy, vif, sta, false);
+	ebf = mt7996_is_ebf_supported(phy, link_conf, link_sta, false);
 	if (!ebf && !dev->ibf)
 		return;
 
@@ -1694,28 +1704,29 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 	 * vht: support eBF and iBF
 	 * ht: iBF only, since mac80211 lacks of eBF support
 	 */
-	if (sta->deflink.eht_cap.has_eht)
-		mt7996_mcu_sta_bfer_eht(sta, vif, phy, bf, ebf);
-	else if (sta->deflink.he_cap.has_he)
-		mt7996_mcu_sta_bfer_he(sta, vif, phy, bf, ebf);
-	else if (sta->deflink.vht_cap.vht_supported)
-		mt7996_mcu_sta_bfer_vht(sta, phy, bf, ebf);
-	else if (sta->deflink.ht_cap.ht_supported)
-		mt7996_mcu_sta_bfer_ht(sta, phy, bf, ebf);
+	if (link_sta->eht_cap.has_eht)
+		mt7996_mcu_sta_bfer_eht(link_sta, vif, link->phy, bf, ebf);
+	else if (link_sta->he_cap.has_he)
+		mt7996_mcu_sta_bfer_he(link_sta, vif, link->phy, bf, ebf);
+	else if (link_sta->vht_cap.vht_supported)
+		mt7996_mcu_sta_bfer_vht(link_sta, link->phy, bf, ebf);
+	else if (link_sta->ht_cap.ht_supported)
+		mt7996_mcu_sta_bfer_ht(link_sta, link->phy, bf, ebf);
 	else
 		return;
 
 	bf->bf_cap = ebf ? EBF_MODE : (dev->ibf ? IBF_MODE : 0);
 	if (is_mt7992(&dev->mt76) && tx_ant == 4)
 		bf->bf_cap |= IBF_MODE;
-	bf->bw = sta->deflink.bandwidth;
-	bf->ibf_dbw = sta->deflink.bandwidth;
+
+	bf->bw = link_sta->bandwidth;
+	bf->ibf_dbw = link_sta->bandwidth;
 	bf->ibf_nrow = tx_ant;
 
-	if (sta->deflink.eht_cap.has_eht || sta->deflink.he_cap.has_he)
+	if (link_sta->eht_cap.has_eht || link_sta->he_cap.has_he)
 		bf->ibf_timeout = is_mt7996(&dev->mt76) ? MT7996_IBF_TIMEOUT :
 							  MT7992_IBF_TIMEOUT;
-	else if (!ebf && sta->deflink.bandwidth <= IEEE80211_STA_RX_BW_40 && !bf->ncol)
+	else if (!ebf && link_sta->bandwidth <= IEEE80211_STA_RX_BW_40 && !bf->ncol)
 		bf->ibf_timeout = MT7996_IBF_TIMEOUT_LEGACY;
 	else
 		bf->ibf_timeout = MT7996_IBF_TIMEOUT;
@@ -1729,7 +1740,7 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 				      matrix[bf->nrow][bf->ncol] : 0;
 	}
 
-	switch (sta->deflink.bandwidth) {
+	switch (link_sta->bandwidth) {
 	case IEEE80211_STA_RX_BW_160:
 	case IEEE80211_STA_RX_BW_80:
 		bf->mem_total = bf->mem_20m * 2;
@@ -1745,31 +1756,32 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
 
 static void
 mt7996_mcu_sta_bfee_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
-			struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+			struct ieee80211_bss_conf *link_conf,
+			struct ieee80211_link_sta *link_sta,
+			struct mt7996_vif_link *link)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_phy *phy = mvif->deflink.phy;
+	struct mt7996_phy *phy = link->phy;
 	int tx_ant = hweight8(phy->mt76->antenna_mask) - 1;
 	struct sta_rec_bfee *bfee;
 	struct tlv *tlv;
 	u8 nrow = 0;
 
-	if (!(sta->deflink.vht_cap.vht_supported || sta->deflink.he_cap.has_he))
+	if (!(link_sta->vht_cap.vht_supported || link_sta->he_cap.has_he))
 		return;
 
-	if (!mt7996_is_ebf_supported(phy, vif, sta, true))
+	if (!mt7996_is_ebf_supported(phy, link_conf, link_sta, true))
 		return;
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_BFEE, sizeof(*bfee));
 	bfee = (struct sta_rec_bfee *)tlv;
 
-	if (sta->deflink.he_cap.has_he) {
-		struct ieee80211_he_cap_elem *pe = &sta->deflink.he_cap.he_cap_elem;
+	if (link_sta->he_cap.has_he) {
+		struct ieee80211_he_cap_elem *pe = &link_sta->he_cap.he_cap_elem;
 
 		nrow = HE_PHY(CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK,
 			      pe->phy_cap_info[5]);
-	} else if (sta->deflink.vht_cap.vht_supported) {
-		struct ieee80211_sta_vht_cap *pc = &sta->deflink.vht_cap;
+	} else if (link_sta->vht_cap.vht_supported) {
+		struct ieee80211_sta_vht_cap *pc = &link_sta->vht_cap;
 
 		nrow = FIELD_GET(IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK,
 				 pc->cap);
@@ -2131,7 +2143,7 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	 * update sta_rec_he here.
 	 */
 	if (changed)
-		mt7996_mcu_sta_he_tlv(skb, sta);
+		mt7996_mcu_sta_he_tlv(skb, &sta->deflink, &mvif->deflink);
 
 	/* sta_rec_ra accommodates BW, NSS and only MCS range format
 	 * i.e 0-{7,8,9} for VHT.
@@ -2179,67 +2191,67 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 				 sizeof(req), true);
 }
 
-int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-		       struct mt76_vif_link *mlink,
-		       struct ieee80211_sta *sta, int conn_state, bool newly)
+int mt7996_mcu_add_sta(struct mt7996_dev *dev,
+		       struct ieee80211_bss_conf *link_conf,
+		       struct ieee80211_link_sta *link_sta,
+		       struct mt7996_vif_link *link,
+		       struct mt7996_sta_link *msta_link,
+		       int conn_state, bool newly)
 {
-	struct ieee80211_link_sta *link_sta = NULL;
-	struct mt76_wcid *wcid = mlink->wcid;
+	struct mt76_wcid *wcid = msta_link ? &msta_link->wcid : link->mt76.wcid;
+	struct ieee80211_sta *sta = link_sta ? link_sta->sta : NULL;
 	struct sk_buff *skb;
 	int ret;
 
-	if (sta) {
-		struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-		struct mt7996_sta_link *msta_link = &msta->deflink;
-
-		wcid = &msta_link->wcid;
-		link_sta = &sta->deflink;
-	}
-
-	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, mlink, wcid,
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76, wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
 	/* starec basic */
-	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, &vif->bss_conf, link_sta,
+	mt76_connac_mcu_sta_basic_tlv(&dev->mt76, skb, link_conf, link_sta,
 				      conn_state, newly);
 
 	if (conn_state == CONN_STATE_DISCONNECT)
 		goto out;
 
 	/* starec hdr trans */
-	mt7996_mcu_sta_hdr_trans_tlv(dev, skb, vif, wcid);
+	mt7996_mcu_sta_hdr_trans_tlv(dev, skb, link_conf->vif, wcid);
 	/* starec tx proc */
 	mt7996_mcu_sta_tx_proc_tlv(skb);
 
 	/* tag order is in accordance with firmware dependency. */
-	if (sta) {
+	if (link_sta) {
 		/* starec hdrt mode */
 		mt7996_mcu_sta_hdrt_tlv(dev, skb);
-		/* starec bfer */
-		mt7996_mcu_sta_bfer_tlv(dev, skb, vif, sta);
+		if (conn_state == CONN_STATE_CONNECT) {
+			/* starec bfer */
+			mt7996_mcu_sta_bfer_tlv(dev, skb, link_conf, link_sta,
+						link);
+			/* starec bfee */
+			mt7996_mcu_sta_bfee_tlv(dev, skb, link_conf, link_sta,
+						link);
+		}
 		/* starec ht */
-		mt7996_mcu_sta_ht_tlv(skb, sta);
+		mt7996_mcu_sta_ht_tlv(skb, link_sta);
 		/* starec vht */
-		mt7996_mcu_sta_vht_tlv(skb, sta);
+		mt7996_mcu_sta_vht_tlv(skb, link_sta);
 		/* starec uapsd */
-		mt76_connac_mcu_sta_uapsd(skb, vif, sta);
+		mt76_connac_mcu_sta_uapsd(skb, link_conf->vif, sta);
 		/* starec amsdu */
-		mt7996_mcu_sta_amsdu_tlv(dev, skb, vif, sta);
+		mt7996_mcu_sta_amsdu_tlv(dev, skb, link_conf->vif, link_sta,
+					 msta_link);
 		/* starec he */
-		mt7996_mcu_sta_he_tlv(skb, sta);
+		mt7996_mcu_sta_he_tlv(skb, link_sta, link);
 		/* starec he 6g*/
-		mt7996_mcu_sta_he_6g_tlv(skb, sta);
+		mt7996_mcu_sta_he_6g_tlv(skb, link_sta);
 		/* starec eht */
-		mt7996_mcu_sta_eht_tlv(skb, sta);
+		mt7996_mcu_sta_eht_tlv(skb, link_sta);
 		/* starec muru */
-		mt7996_mcu_sta_muru_tlv(dev, skb, vif, sta);
-		/* starec bfee */
-		mt7996_mcu_sta_bfee_tlv(dev, skb, vif, sta);
+		mt7996_mcu_sta_muru_tlv(dev, skb, link_conf, link_sta);
 	}
 
-	ret = mt7996_mcu_add_group(dev, vif, sta);
+	ret = mt7996_mcu_add_group(dev, link_conf->vif, sta);
 	if (ret) {
 		dev_kfree_skb(skb);
 		return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index cf37baa91a8ba..0dd9d798541f9 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -572,9 +572,12 @@ int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_bss_conf *link_conf,
 			    struct mt76_vif_link *mlink, int enable);
-int mt7996_mcu_add_sta(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-		       struct mt76_vif_link *mlink,
-		       struct ieee80211_sta *sta, int conn_state, bool newly);
+int mt7996_mcu_add_sta(struct mt7996_dev *dev,
+		       struct ieee80211_bss_conf *link_conf,
+		       struct ieee80211_link_sta *link_sta,
+		       struct mt7996_vif_link *link,
+		       struct mt7996_sta_link *msta_link,
+		       int conn_state, bool newly);
 int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool add);

From 7854cc94ec353ee501074637a7caf87a49cff35b Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Tue, 11 Mar 2025 18:45:11 +0100
Subject: [PATCH 2313/2753] wifi: mt76: mt7996: Rely on mt7996_vif_link in
 mt7996_mcu_twt_agrt_update signature

This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-12-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 5 +++--
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c    | 8 ++++----
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 2 +-
 3 files changed, 8 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 456666eb7080c..4a7f6fd902529 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2672,7 +2672,8 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 	}
 	flow->tsf = le64_to_cpu(twt_agrt->twt);
 
-	if (mt7996_mcu_twt_agrt_update(dev, msta->vif, flow, MCU_TWT_AGRT_ADD))
+	if (mt7996_mcu_twt_agrt_update(dev, &msta->vif->deflink, flow,
+				       MCU_TWT_AGRT_ADD))
 		goto unlock;
 
 	setup_cmd = TWT_SETUP_CMD_ACCEPT;
@@ -2705,7 +2706,7 @@ void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev,
 		return;
 
 	flow = &msta_link->twt.flow[flowid];
-	if (mt7996_mcu_twt_agrt_update(dev, msta->vif, flow,
+	if (mt7996_mcu_twt_agrt_update(dev, &msta->vif->deflink, flow,
 				       MCU_TWT_AGRT_DELETE))
 		return;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 43e85308132e5..e6ebb309a8257 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4236,7 +4236,7 @@ int mt7996_mcu_update_bss_color(struct mt7996_dev *dev,
 #define TWT_AGRT_PROTECT	BIT(2)
 
 int mt7996_mcu_twt_agrt_update(struct mt7996_dev *dev,
-			       struct mt7996_vif *mvif,
+			       struct mt7996_vif_link *link,
 			       struct mt7996_twt_flow *flow,
 			       int cmd)
 {
@@ -4267,12 +4267,12 @@ int mt7996_mcu_twt_agrt_update(struct mt7996_dev *dev,
 		.len = cpu_to_le16(sizeof(req) - 4),
 		.tbl_idx = flow->table_id,
 		.cmd = cmd,
-		.own_mac_idx = mvif->deflink.mt76.omac_idx,
+		.own_mac_idx = link->mt76.omac_idx,
 		.flowid = flow->id,
 		.peer_id = cpu_to_le16(flow->wcid),
 		.duration = flow->duration,
-		.bss = mvif->deflink.mt76.idx,
-		.bss_idx = mvif->deflink.mt76.idx,
+		.bss = link->mt76.idx,
+		.bss_idx = link->mt76.idx,
 		.start_tsf = cpu_to_le64(flow->tsf),
 		.mantissa = flow->mantissa,
 		.exponent = flow->exp,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 0dd9d798541f9..962022c7eec9f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -563,7 +563,7 @@ int mt7996_run(struct mt7996_phy *phy);
 int mt7996_mcu_init(struct mt7996_dev *dev);
 int mt7996_mcu_init_firmware(struct mt7996_dev *dev);
 int mt7996_mcu_twt_agrt_update(struct mt7996_dev *dev,
-			       struct mt7996_vif *mvif,
+			       struct mt7996_vif_link *link,
 			       struct mt7996_twt_flow *flow,
 			       int cmd);
 int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,

From 3c477b7fca1ddfe01ae9029b7c264fd099b05af6 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 11 Mar 2025 18:45:12 +0100
Subject: [PATCH 2314/2753] wifi: mt76: mt7996: Rely on mt7996_vif/sta_link in
 twt teardown

This is a preliminary patch to enable MLO for MT7996 driver

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250311-mt7996-mlo-v2-13-31df6972519b@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 7 +++----
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 7 +++++--
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h | 3 ++-
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 4a7f6fd902529..7ddd4b0cadf5d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2691,10 +2691,10 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 }
 
 void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev,
-				  struct mt7996_sta *msta,
+				  struct mt7996_vif_link *link,
+				  struct mt7996_sta_link *msta_link,
 				  u8 flowid)
 {
-	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct mt7996_twt_flow *flow;
 
 	lockdep_assert_held(&dev->mt76.mutex);
@@ -2706,8 +2706,7 @@ void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev,
 		return;
 
 	flow = &msta_link->twt.flow[flowid];
-	if (mt7996_mcu_twt_agrt_update(dev, &msta->vif->deflink, flow,
-				       MCU_TWT_AGRT_DELETE))
+	if (mt7996_mcu_twt_agrt_update(dev, link, flow, MCU_TWT_AGRT_DELETE))
 		return;
 
 	list_del_init(&flow->list);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 5ab4f08dba06f..11ad95e05b948 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1062,7 +1062,8 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			break;
 		case MT76_STA_EVENT_DISASSOC:
 			for (i = 0; i < ARRAY_SIZE(msta_link->twt.flow); i++)
-				mt7996_mac_twt_teardown_flow(dev, msta, i);
+				mt7996_mac_twt_teardown_flow(dev, link,
+							     msta_link, i);
 
 			mt7996_mcu_add_sta(dev, link_conf, link_sta, link,
 					   msta_link, CONN_STATE_DISCONNECT,
@@ -1804,10 +1805,12 @@ mt7996_twt_teardown_request(struct ieee80211_hw *hw,
 			    u8 flowid)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct mt7996_vif_link *link = &msta->vif->deflink;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 
 	mutex_lock(&dev->mt76.mutex);
-	mt7996_mac_twt_teardown_flow(dev, msta, flowid);
+	mt7996_mac_twt_teardown_flow(dev, link, msta_link, flowid);
 	mutex_unlock(&dev->mt76.mutex);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 962022c7eec9f..84b9ff707d565 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -709,7 +709,8 @@ void mt7996_mac_dump_work(struct work_struct *work);
 void mt7996_mac_sta_rc_work(struct work_struct *work);
 void mt7996_mac_update_stats(struct mt7996_phy *phy);
 void mt7996_mac_twt_teardown_flow(struct mt7996_dev *dev,
-				  struct mt7996_sta *msta,
+				  struct mt7996_vif_link *link,
+				  struct mt7996_sta_link *msta_link,
 				  u8 flowid);
 void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 			      struct ieee80211_sta *sta,

From 2660fde82f65caefadb5bb53bc5f1cf43fe224ff Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:45 +0100
Subject: [PATCH 2315/2753] wifi: mt76: mt7996: Update mt7996_mcu_add_rate_ctrl
 to MLO

Update mt7996_mcu_add_rate_ctrl routine and all the called subroutines
to support MLO.
This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-1-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |   9 +-
 .../net/wireless/mediatek/mt76/mt7996/main.c  |   4 +-
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 144 +++++++++---------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  15 +-
 4 files changed, 96 insertions(+), 76 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 7ddd4b0cadf5d..48ba975f069c5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2294,10 +2294,15 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 		if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED |
 			       IEEE80211_RC_NSS_CHANGED |
 			       IEEE80211_RC_BW_CHANGED))
-			mt7996_mcu_add_rate_ctrl(dev, vif, sta, true);
+			mt7996_mcu_add_rate_ctrl(dev, vif, &vif->bss_conf,
+						 &sta->deflink,
+						 &msta->vif->deflink,
+						 msta_link, true);
 
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
-			mt7996_mcu_set_fixed_field(dev, vif, sta, NULL,
+			mt7996_mcu_set_fixed_field(dev, &sta->deflink,
+						   &msta->vif->deflink,
+						   msta_link, NULL,
 						   RATE_PARAM_MMPS_UPDATE);
 
 		spin_lock_bh(&dev->mt76.sta_poll_lock);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 11ad95e05b948..25dbf086c8ef0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1046,7 +1046,9 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 			if (err)
 				return err;
 
-			err = mt7996_mcu_add_rate_ctrl(dev, vif, sta, false);
+			err = mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
+						       link_sta, link,
+						       msta_link, false);
 			if (err)
 				return err;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index e6ebb309a8257..0cc822a8a6799 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -167,11 +167,11 @@ mt7996_mcu_set_sta_he_mcs(struct ieee80211_link_sta *link_sta,
 }
 
 static void
-mt7996_mcu_set_sta_vht_mcs(struct ieee80211_sta *sta, __le16 *vht_mcs,
-			   const u16 *mask)
+mt7996_mcu_set_sta_vht_mcs(struct ieee80211_link_sta *link_sta,
+			   __le16 *vht_mcs, const u16 *mask)
 {
-	u16 mcs, mcs_map = le16_to_cpu(sta->deflink.vht_cap.vht_mcs.rx_mcs_map);
-	int nss, max_nss = sta->deflink.rx_nss > 3 ? 4 : sta->deflink.rx_nss;
+	u16 mcs, mcs_map = le16_to_cpu(link_sta->vht_cap.vht_mcs.rx_mcs_map);
+	int nss, max_nss = link_sta->rx_nss > 3 ? 4 : link_sta->rx_nss;
 
 	for (nss = 0; nss < max_nss; nss++, mcs_map >>= 2) {
 		switch (mcs_map & 0x3) {
@@ -193,13 +193,13 @@ mt7996_mcu_set_sta_vht_mcs(struct ieee80211_sta *sta, __le16 *vht_mcs,
 }
 
 static void
-mt7996_mcu_set_sta_ht_mcs(struct ieee80211_sta *sta, u8 *ht_mcs,
-			  const u8 *mask)
+mt7996_mcu_set_sta_ht_mcs(struct ieee80211_link_sta *link_sta,
+			  u8 *ht_mcs, const u8 *mask)
 {
-	int nss, max_nss = sta->deflink.rx_nss > 3 ? 4 : sta->deflink.rx_nss;
+	int nss, max_nss = link_sta->rx_nss > 3 ? 4 : link_sta->rx_nss;
 
 	for (nss = 0; nss < max_nss; nss++)
-		ht_mcs[nss] = sta->deflink.ht_cap.mcs.rx_mask[nss] & mask[nss];
+		ht_mcs[nss] = link_sta->ht_cap.mcs.rx_mask[nss] & mask[nss];
 }
 
 static int
@@ -1888,18 +1888,18 @@ int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				     MCU_WM_UNI_CMD(RA), true);
 }
 
-int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			       struct ieee80211_sta *sta, void *data, u32 field)
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev,
+			       struct ieee80211_link_sta *link_sta,
+			       struct mt7996_vif_link *link,
+			       struct mt7996_sta_link *msta_link,
+			       void *data, u32 field)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sta_phy_uni *phy = data;
 	struct sta_rec_ra_fixed_uni *ra;
 	struct sk_buff *skb;
 	struct tlv *tlv;
 
-	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
 					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
@@ -1919,7 +1919,7 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif
 			ra->phy = *phy;
 		break;
 	case RATE_PARAM_MMPS_UPDATE:
-		ra->mmps_mode = mt7996_mcu_get_mmps_mode(sta->deflink.smps_mode);
+		ra->mmps_mode = mt7996_mcu_get_mmps_mode(link_sta->smps_mode);
 		break;
 	default:
 		break;
@@ -1931,12 +1931,13 @@ int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif
 }
 
 static int
-mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			       struct ieee80211_sta *sta)
+mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev,
+			       struct ieee80211_link_sta *link_sta,
+			       struct mt7996_vif_link *link,
+			       struct mt7996_sta_link *msta_link)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct cfg80211_chan_def *chandef = &mvif->deflink.phy->mt76->chandef;
-	struct cfg80211_bitrate_mask *mask = &mvif->deflink.bitrate_mask;
+	struct cfg80211_chan_def *chandef = &link->phy->mt76->chandef;
+	struct cfg80211_bitrate_mask *mask = &link->bitrate_mask;
 	enum nl80211_band band = chandef->chan->band;
 	struct sta_phy_uni phy = {};
 	int ret, nrates = 0;
@@ -1957,11 +1958,11 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 		}								\
 	} while (0)
 
-	if (sta->deflink.he_cap.has_he) {
+	if (link_sta->he_cap.has_he) {
 		__sta_phy_bitrate_mask_check(he_mcs, he_gi, 0, 1);
-	} else if (sta->deflink.vht_cap.vht_supported) {
+	} else if (link_sta->vht_cap.vht_supported) {
 		__sta_phy_bitrate_mask_check(vht_mcs, gi, 0, 0);
-	} else if (sta->deflink.ht_cap.ht_supported) {
+	} else if (link_sta->ht_cap.ht_supported) {
 		__sta_phy_bitrate_mask_check(ht_mcs, gi, 1, 0);
 	} else {
 		nrates = hweight32(mask->control[band].legacy);
@@ -1978,7 +1979,8 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 
 	/* fixed single rate */
 	if (nrates == 1) {
-		ret = mt7996_mcu_set_fixed_field(dev, vif, sta, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
+						 msta_link, &phy,
 						 RATE_PARAM_FIXED_MCS);
 		if (ret)
 			return ret;
@@ -1987,7 +1989,6 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 	/* fixed GI */
 	if (mask->control[band].gi != NL80211_TXRATE_DEFAULT_GI ||
 	    mask->control[band].he_gi != GENMASK(7, 0)) {
-		struct mt7996_sta_link *msta_link = (void *)sta->drv_priv;
 		u32 addr;
 
 		/* firmware updates only TXCMD but doesn't take WTBL into
@@ -1995,12 +1996,13 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 		 * actual txrate hardware sends out.
 		 */
 		addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 7);
-		if (sta->deflink.he_cap.has_he)
+		if (link_sta->he_cap.has_he)
 			mt76_rmw_field(dev, addr, GENMASK(31, 24), phy.sgi);
 		else
 			mt76_rmw_field(dev, addr, GENMASK(15, 12), phy.sgi);
 
-		ret = mt7996_mcu_set_fixed_field(dev, vif, sta, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
+						 msta_link, &phy,
 						 RATE_PARAM_FIXED_GI);
 		if (ret)
 			return ret;
@@ -2008,7 +2010,8 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 
 	/* fixed HE_LTF */
 	if (mask->control[band].he_ltf != GENMASK(7, 0)) {
-		ret = mt7996_mcu_set_fixed_field(dev, vif, sta, &phy,
+		ret = mt7996_mcu_set_fixed_field(dev, link_sta, link,
+						 msta_link, &phy,
 						 RATE_PARAM_FIXED_HE_LTF);
 		if (ret)
 			return ret;
@@ -2019,30 +2022,32 @@ mt7996_mcu_add_rate_ctrl_fixed(struct mt7996_dev *dev, struct ieee80211_vif *vif
 
 static void
 mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
-			     struct ieee80211_vif *vif, struct ieee80211_sta *sta)
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf,
+			     struct ieee80211_link_sta *link_sta,
+			     struct mt7996_vif_link *link)
 {
 #define INIT_RCPI 180
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt76_phy *mphy = mvif->deflink.phy->mt76;
+	struct mt76_phy *mphy = link->phy->mt76;
 	struct cfg80211_chan_def *chandef = &mphy->chandef;
-	struct cfg80211_bitrate_mask *mask = &mvif->deflink.bitrate_mask;
+	struct cfg80211_bitrate_mask *mask = &link->bitrate_mask;
+	u32 cap = link_sta->sta->wme ? STA_CAP_WMM : 0;
 	enum nl80211_band band = chandef->chan->band;
 	struct sta_rec_ra_uni *ra;
 	struct tlv *tlv;
-	u32 supp_rate = sta->deflink.supp_rates[band];
-	u32 cap = sta->wme ? STA_CAP_WMM : 0;
+	u32 supp_rate = link_sta->supp_rates[band];
 
 	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_RA, sizeof(*ra));
 	ra = (struct sta_rec_ra_uni *)tlv;
 
 	ra->valid = true;
 	ra->auto_rate = true;
-	ra->phy_mode = mt76_connac_get_phy_mode(mphy, vif, band, &sta->deflink);
+	ra->phy_mode = mt76_connac_get_phy_mode(mphy, vif, band, link_sta);
 	ra->channel = chandef->chan->hw_value;
-	ra->bw = (sta->deflink.bandwidth == IEEE80211_STA_RX_BW_320) ?
-		 CMD_CBW_320MHZ : sta->deflink.bandwidth;
+	ra->bw = (link_sta->bandwidth == IEEE80211_STA_RX_BW_320) ?
+		 CMD_CBW_320MHZ : link_sta->bandwidth;
 	ra->phy.bw = ra->bw;
-	ra->mmps_mode = mt7996_mcu_get_mmps_mode(sta->deflink.smps_mode);
+	ra->mmps_mode = mt7996_mcu_get_mmps_mode(link_sta->smps_mode);
 
 	if (supp_rate) {
 		supp_rate &= mask->control[band].legacy;
@@ -2062,60 +2067,60 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
 		}
 	}
 
-	if (sta->deflink.ht_cap.ht_supported) {
+	if (link_sta->ht_cap.ht_supported) {
 		ra->supp_mode |= MODE_HT;
-		ra->af = sta->deflink.ht_cap.ampdu_factor;
-		ra->ht_gf = !!(sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_GRN_FLD);
+		ra->af = link_sta->ht_cap.ampdu_factor;
+		ra->ht_gf = !!(link_sta->ht_cap.cap & IEEE80211_HT_CAP_GRN_FLD);
 
 		cap |= STA_CAP_HT;
-		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_SGI_20)
+		if (link_sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_20)
 			cap |= STA_CAP_SGI_20;
-		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_SGI_40)
+		if (link_sta->ht_cap.cap & IEEE80211_HT_CAP_SGI_40)
 			cap |= STA_CAP_SGI_40;
-		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_TX_STBC)
+		if (link_sta->ht_cap.cap & IEEE80211_HT_CAP_TX_STBC)
 			cap |= STA_CAP_TX_STBC;
-		if (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
+		if (link_sta->ht_cap.cap & IEEE80211_HT_CAP_RX_STBC)
 			cap |= STA_CAP_RX_STBC;
-		if (vif->bss_conf.ht_ldpc &&
-		    (sta->deflink.ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING))
+		if (link_conf->ht_ldpc &&
+		    (link_sta->ht_cap.cap & IEEE80211_HT_CAP_LDPC_CODING))
 			cap |= STA_CAP_LDPC;
 
-		mt7996_mcu_set_sta_ht_mcs(sta, ra->ht_mcs,
+		mt7996_mcu_set_sta_ht_mcs(link_sta, ra->ht_mcs,
 					  mask->control[band].ht_mcs);
 		ra->supp_ht_mcs = *(__le32 *)ra->ht_mcs;
 	}
 
-	if (sta->deflink.vht_cap.vht_supported) {
+	if (link_sta->vht_cap.vht_supported) {
 		u8 af;
 
 		ra->supp_mode |= MODE_VHT;
 		af = FIELD_GET(IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK,
-			       sta->deflink.vht_cap.cap);
+			       link_sta->vht_cap.cap);
 		ra->af = max_t(u8, ra->af, af);
 
 		cap |= STA_CAP_VHT;
-		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80)
+		if (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_80)
 			cap |= STA_CAP_VHT_SGI_80;
-		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_160)
+		if (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_SHORT_GI_160)
 			cap |= STA_CAP_VHT_SGI_160;
-		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_TXSTBC)
+		if (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_TXSTBC)
 			cap |= STA_CAP_VHT_TX_STBC;
-		if (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_1)
+		if (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_RXSTBC_1)
 			cap |= STA_CAP_VHT_RX_STBC;
-		if ((vif->type != NL80211_IFTYPE_AP || vif->bss_conf.vht_ldpc) &&
-		    (sta->deflink.vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC))
+		if ((vif->type != NL80211_IFTYPE_AP || link_conf->vht_ldpc) &&
+		    (link_sta->vht_cap.cap & IEEE80211_VHT_CAP_RXLDPC))
 			cap |= STA_CAP_VHT_LDPC;
 
-		mt7996_mcu_set_sta_vht_mcs(sta, ra->supp_vht_mcs,
+		mt7996_mcu_set_sta_vht_mcs(link_sta, ra->supp_vht_mcs,
 					   mask->control[band].vht_mcs);
 	}
 
-	if (sta->deflink.he_cap.has_he) {
+	if (link_sta->he_cap.has_he) {
 		ra->supp_mode |= MODE_HE;
 		cap |= STA_CAP_HE;
 
-		if (sta->deflink.he_6ghz_capa.capa)
-			ra->af = le16_get_bits(sta->deflink.he_6ghz_capa.capa,
+		if (link_sta->he_6ghz_capa.capa)
+			ra->af = le16_get_bits(link_sta->he_6ghz_capa.capa,
 					       IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP);
 	}
 	ra->sta_cap = cpu_to_le32(cap);
@@ -2123,16 +2128,17 @@ mt7996_mcu_sta_rate_ctrl_tlv(struct sk_buff *skb, struct mt7996_dev *dev,
 	memset(ra->rx_rcpi, INIT_RCPI, sizeof(ra->rx_rcpi));
 }
 
-int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			     struct ieee80211_sta *sta, bool changed)
+int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf,
+			     struct ieee80211_link_sta *link_sta,
+			     struct mt7996_vif_link *link,
+			     struct mt7996_sta_link *msta_link, bool changed)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
 	struct sk_buff *skb;
 	int ret;
 
-	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
 					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
@@ -2143,19 +2149,19 @@ int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	 * update sta_rec_he here.
 	 */
 	if (changed)
-		mt7996_mcu_sta_he_tlv(skb, &sta->deflink, &mvif->deflink);
+		mt7996_mcu_sta_he_tlv(skb, link_sta, link);
 
 	/* sta_rec_ra accommodates BW, NSS and only MCS range format
 	 * i.e 0-{7,8,9} for VHT.
 	 */
-	mt7996_mcu_sta_rate_ctrl_tlv(skb, dev, vif, sta);
+	mt7996_mcu_sta_rate_ctrl_tlv(skb, dev, vif, link_conf, link_sta, link);
 
 	ret = mt76_mcu_skb_send_msg(&dev->mt76, skb,
 				    MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 	if (ret)
 		return ret;
 
-	return mt7996_mcu_add_rate_ctrl_fixed(dev, vif, sta);
+	return mt7996_mcu_add_rate_ctrl_fixed(dev, link_sta, link, msta_link);
 }
 
 static int
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 84b9ff707d565..a91a50b72218c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -593,16 +593,23 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
 				    struct ieee80211_vif *vif, u32 changed);
 int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_he_obss_pd *he_obss_pd);
-int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			     struct ieee80211_sta *sta, bool changed);
+int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
+			     struct ieee80211_vif *vif,
+			     struct ieee80211_bss_conf *link_conf,
+			     struct ieee80211_link_sta *link_sta,
+			     struct mt7996_vif_link *link,
+			     struct mt7996_sta_link *msta_link, bool changed);
 int mt7996_set_channel(struct mt76_phy *mphy);
 int mt7996_mcu_set_chan_info(struct mt7996_phy *phy, u16 tag);
 int mt7996_mcu_set_tx(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		      struct ieee80211_bss_conf *link_conf);
 int mt7996_mcu_set_fixed_rate_ctrl(struct mt7996_dev *dev,
 				   void *data, u16 version);
-int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			       struct ieee80211_sta *sta, void *data, u32 field);
+int mt7996_mcu_set_fixed_field(struct mt7996_dev *dev,
+			       struct ieee80211_link_sta *link_sta,
+			       struct mt7996_vif_link *link,
+			       struct mt7996_sta_link *msta_link,
+			       void *data, u32 field);
 int mt7996_mcu_set_eeprom(struct mt7996_dev *dev);
 int mt7996_mcu_get_eeprom(struct mt7996_dev *dev, u32 offset, u8 *buf, u32 buf_len);
 int mt7996_mcu_get_eeprom_free_block(struct mt7996_dev *dev, u8 *block_num);

From 00cef41d9d8f5552c1bf14b507ac8bd6eab0aa8c Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:46 +0100
Subject: [PATCH 2316/2753] wifi: mt76: mt7996: Add
 mt7996_mcu_sta_mld_setup_tlv() and mt7996_mcu_sta_eht_mld_tlv()

mt7996_mcu_sta_mld_setup_tlv is needed to push MLO configuration to the
MCU. This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-2-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 79 +++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/mcu.h   | 32 ++++++++
 2 files changed, 111 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 0cc822a8a6799..0c1e47f0c73a8 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2197,6 +2197,80 @@ mt7996_mcu_add_group(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 				 sizeof(req), true);
 }
 
+static void
+mt7996_mcu_sta_mld_setup_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
+			     struct ieee80211_sta *sta)
+{
+	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	unsigned long links = sta->valid_links;
+	unsigned int nlinks = hweight16(links);
+	struct mld_setup_link *mld_setup_link;
+	struct sta_rec_mld_setup *mld_setup;
+	struct mt7996_sta_link *msta_link;
+	struct ieee80211_vif *vif;
+	unsigned int link_id;
+	struct tlv *tlv;
+
+	msta_link = mt76_dereference(msta->link[msta->deflink_id], &dev->mt76);
+	if (!msta_link)
+		return;
+
+	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_MLD,
+				      sizeof(struct sta_rec_mld_setup) +
+				      sizeof(struct mld_setup_link) * nlinks);
+
+	mld_setup = (struct sta_rec_mld_setup *)tlv;
+	memcpy(mld_setup->mld_addr, sta->addr, ETH_ALEN);
+	mld_setup->setup_wcid = cpu_to_le16(msta_link->wcid.idx);
+	mld_setup->primary_id = cpu_to_le16(msta_link->wcid.idx);
+
+	if (nlinks > 1) {
+		link_id = __ffs(links & ~BIT(msta->deflink_id));
+		msta_link = mt76_dereference(msta->link[msta->deflink_id],
+					     &dev->mt76);
+		if (!msta_link)
+			return;
+	}
+	mld_setup->seconed_id = cpu_to_le16(msta_link->wcid.idx);
+	mld_setup->link_num = nlinks;
+
+	vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
+	mld_setup_link = (struct mld_setup_link *)mld_setup->link_info;
+	for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct mt7996_vif_link *link;
+
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
+		if (!msta_link)
+			continue;
+
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
+
+		if (!msta_link)
+			continue;
+
+		mld_setup_link->wcid = cpu_to_le16(msta_link->wcid.idx);
+		mld_setup_link->bss_idx = link->mt76.idx;
+		mld_setup_link++;
+	}
+}
+
+static void
+mt7996_mcu_sta_eht_mld_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
+			   struct ieee80211_sta *sta)
+{
+	struct sta_rec_eht_mld *eht_mld;
+	struct tlv *tlv;
+	int i;
+
+	tlv = mt76_connac_mcu_add_tlv(skb, STA_REC_EHT_MLD, sizeof(*eht_mld));
+	eht_mld = (struct sta_rec_eht_mld *)tlv;
+
+	for (i = 0; i < ARRAY_SIZE(eht_mld->str_cap); i++)
+		eht_mld->str_cap[i] = 0x7;
+}
+
 int mt7996_mcu_add_sta(struct mt7996_dev *dev,
 		       struct ieee80211_bss_conf *link_conf,
 		       struct ieee80211_link_sta *link_sta,
@@ -2255,6 +2329,11 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev,
 		mt7996_mcu_sta_eht_tlv(skb, link_sta);
 		/* starec muru */
 		mt7996_mcu_sta_muru_tlv(dev, skb, link_conf, link_sta);
+
+		if (sta->mlo) {
+			mt7996_mcu_sta_mld_setup_tlv(dev, skb, sta);
+			mt7996_mcu_sta_eht_mld_tlv(dev, skb, sta);
+		}
 	}
 
 	ret = mt7996_mcu_add_group(dev, link_conf->vif, sta);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
index 5fdc47dad28c6..2ab6a53bee869 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.h
@@ -625,6 +625,35 @@ struct sta_rec_hdr_trans {
 	u8 mesh;
 } __packed;
 
+struct sta_rec_mld_setup {
+	__le16 tag;
+	__le16 len;
+	u8 mld_addr[ETH_ALEN];
+	__le16 primary_id;
+	__le16 seconed_id;
+	__le16 setup_wcid;
+	u8 link_num;
+	u8 info;
+	u8 __rsv[2];
+	u8 link_info[];
+} __packed;
+
+struct sta_rec_eht_mld {
+	__le16 tag;
+	__le16 len;
+	u8 nsep;
+	u8 __rsv1[2];
+	u8 str_cap[__MT_MAX_BAND];
+	__le16 eml_cap;
+	u8 __rsv2[4];
+} __packed;
+
+struct mld_setup_link {
+	__le16 wcid;
+	u8 bss_idx;
+	u8 __rsv;
+} __packed;
+
 struct hdr_trans_en {
 	__le16 tag;
 	__le16 len;
@@ -798,6 +827,9 @@ enum {
 					 sizeof(struct sta_rec_eht) +		\
 					 sizeof(struct sta_rec_hdrt) +		\
 					 sizeof(struct sta_rec_hdr_trans) +	\
+					 sizeof(struct sta_rec_mld_setup) +	\
+					 sizeof(struct mld_setup_link) * 3 +	\
+					 sizeof(struct sta_rec_eht_mld) +	\
 					 sizeof(struct tlv))
 
 #define MT7996_MAX_BEACON_SIZE		1338

From c1d6dd5d03eb504c06bda7ce983d223fc56d774a Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:47 +0100
Subject: [PATCH 2317/2753] wifi: mt76: mt7996: Add mt7996_mcu_teardown_mld_sta
 rouine

mt7996_mcu_teardown_mld_sta is used to remove MLO configuration from the
MCU. This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-3-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c   | 12 +++++++++---
 .../net/wireless/mediatek/mt76/mt7996/mcu.c    | 18 ++++++++++++++++++
 .../net/wireless/mediatek/mt76/mt7996/mt7996.h |  3 +++
 3 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 25dbf086c8ef0..642d633b5126c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1017,6 +1017,7 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 		     struct ieee80211_sta *sta, enum mt76_sta_event ev)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+	unsigned long links = sta->valid_links;
 	struct ieee80211_link_sta *link_sta;
 	unsigned int link_id;
 
@@ -1067,11 +1068,16 @@ mt7996_mac_sta_event(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 				mt7996_mac_twt_teardown_flow(dev, link,
 							     msta_link, i);
 
-			mt7996_mcu_add_sta(dev, link_conf, link_sta, link,
-					   msta_link, CONN_STATE_DISCONNECT,
-					   false);
+			if (sta->mlo && links == BIT(link_id)) /* last link */
+				mt7996_mcu_teardown_mld_sta(dev, link,
+							    msta_link);
+			else
+				mt7996_mcu_add_sta(dev, link_conf, link_sta,
+						   link, msta_link,
+						   CONN_STATE_DISCONNECT, false);
 			msta_link->wcid.sta_disabled = 1;
 			msta_link->wcid.sta = 0;
+			links = links & ~BIT(link_id);
 			break;
 		}
 	}
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 0c1e47f0c73a8..a5522f31c343b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2346,6 +2346,24 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev,
 				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
 }
 
+int mt7996_mcu_teardown_mld_sta(struct mt7996_dev *dev,
+				struct mt7996_vif_link *link,
+				struct mt7996_sta_link *msta_link)
+{
+	struct sk_buff *skb;
+
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
+					      &msta_link->wcid,
+					      MT7996_STA_UPDATE_MAX_SIZE);
+	if (IS_ERR(skb))
+		return PTR_ERR(skb);
+
+	mt76_connac_mcu_add_tlv(skb, STA_REC_MLD_OFF, sizeof(struct tlv));
+
+	return mt76_mcu_skb_send_msg(&dev->mt76, skb,
+				     MCU_WMWA_UNI_CMD(STA_REC_UPDATE), true);
+}
+
 static int
 mt7996_mcu_sta_key_tlv(struct mt76_wcid *wcid,
 		       struct sk_buff *skb,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index a91a50b72218c..c2a2916e0647c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -578,6 +578,9 @@ int mt7996_mcu_add_sta(struct mt7996_dev *dev,
 		       struct mt7996_vif_link *link,
 		       struct mt7996_sta_link *msta_link,
 		       int conn_state, bool newly);
+int mt7996_mcu_teardown_mld_sta(struct mt7996_dev *dev,
+				struct mt7996_vif_link *link,
+				struct mt7996_sta_link *msta_link);
 int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
 			 bool add);

From f0b0b239b8f36cdc55cf0bc1bac75ec07fc9fef1 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:48 +0100
Subject: [PATCH 2318/2753] wifi: mt76: mt7996: rework mt7996_mac_write_txwi()
 for MLO support

Update mt7996_mac_write_txwi routine and all the called subroutines to
support MLO.
This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-4-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 55 ++++++++++++++-----
 1 file changed, 41 insertions(+), 14 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 48ba975f069c5..eed692cd64a6a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -730,9 +730,8 @@ mt7996_mac_write_txwi_8023(struct mt7996_dev *dev, __le32 *txwi,
 	u32 val;
 
 	if (wcid->sta) {
-		struct ieee80211_sta *sta;
+		struct ieee80211_sta *sta = wcid_to_sta(wcid);
 
-		sta = container_of((void *)wcid, struct ieee80211_sta, drv_priv);
 		wmm = sta->wme;
 	}
 
@@ -759,7 +758,9 @@ mt7996_mac_write_txwi_8023(struct mt7996_dev *dev, __le32 *txwi,
 
 static void
 mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
-			    struct sk_buff *skb, struct ieee80211_key_conf *key)
+			    struct sk_buff *skb,
+			    struct ieee80211_key_conf *key,
+			    struct mt76_wcid *wcid)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
 	struct ieee80211_mgmt *mgmt = (struct ieee80211_mgmt *)skb->data;
@@ -767,6 +768,7 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 	bool multicast = is_multicast_ether_addr(hdr->addr1);
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
 	__le16 fc = hdr->frame_control, sc = hdr->seq_ctrl;
+	u16 seqno = le16_to_cpu(sc);
 	u8 fc_type, fc_stype;
 	u32 val;
 
@@ -816,9 +818,13 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 		txwi[3] |= cpu_to_le32(MT_TXD3_REM_TX_COUNT);
 	}
 
-	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
-		u16 seqno = le16_to_cpu(sc);
+	if (multicast && ieee80211_vif_is_mld(info->control.vif)) {
+		val = MT_TXD3_SN_VALID |
+		      FIELD_PREP(MT_TXD3_SEQ, IEEE80211_SEQ_TO_SN(seqno));
+		txwi[3] |= cpu_to_le32(val);
+	}
 
+	if (info->flags & IEEE80211_TX_CTL_INJECTED) {
 		if (ieee80211_is_back_req(hdr->frame_control)) {
 			struct ieee80211_bar *bar;
 
@@ -831,6 +837,19 @@ mt7996_mac_write_txwi_80211(struct mt7996_dev *dev, __le32 *txwi,
 		txwi[3] |= cpu_to_le32(val);
 		txwi[3] &= ~cpu_to_le32(MT_TXD3_HW_AMSDU);
 	}
+
+	if (ieee80211_vif_is_mld(info->control.vif) &&
+	    (multicast || unlikely(skb->protocol == cpu_to_be16(ETH_P_PAE))))
+		txwi[5] |= cpu_to_le32(MT_TXD5_FL);
+
+	if (ieee80211_is_nullfunc(fc) && ieee80211_has_a4(fc) &&
+	    ieee80211_vif_is_mld(info->control.vif)) {
+		txwi[5] |= cpu_to_le32(MT_TXD5_FL);
+		txwi[6] |= cpu_to_le32(MT_TXD6_DIS_MAT);
+	}
+
+	if (!wcid->sta && ieee80211_is_mgmt(fc))
+		txwi[6] |= cpu_to_le32(MT_TXD6_DIS_MAT);
 }
 
 void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
@@ -846,6 +865,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	bool is_8023 = info->flags & IEEE80211_TX_CTL_HW_80211_ENCAP;
 	struct mt76_vif_link *mlink = NULL;
 	struct mt7996_vif *mvif;
+	unsigned int link_id;
 	u16 tx_count = 15;
 	u32 val;
 	bool inband_disc = !!(changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
@@ -853,13 +873,15 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	bool beacon = !!(changed & (BSS_CHANGED_BEACON |
 				    BSS_CHANGED_BEACON_ENABLED)) && (!inband_disc);
 
-	if (vif) {
-		mvif = (struct mt7996_vif *)vif->drv_priv;
-		if (wcid->offchannel)
-			mlink = rcu_dereference(mvif->mt76.offchannel_link);
-		if (!mlink)
-			mlink = &mvif->deflink.mt76;
-	}
+	if (wcid != &dev->mt76.global_wcid)
+		link_id = wcid->link_id;
+	else
+		link_id = u32_get_bits(info->control.flags,
+				       IEEE80211_TX_CTRL_MLO_LINK);
+
+	mvif = vif ? (struct mt7996_vif *)vif->drv_priv : NULL;
+	if (mvif)
+		mlink = rcu_dereference(mvif->mt76.link[link_id]);
 
 	if (mlink) {
 		omac_idx = mlink->omac_idx;
@@ -911,7 +933,10 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 		val |= MT_TXD5_TX_STATUS_HOST;
 	txwi[5] = cpu_to_le32(val);
 
-	val = MT_TXD6_DIS_MAT | MT_TXD6_DAS;
+	val = MT_TXD6_DAS;
+	if (q_idx >= MT_LMAC_ALTX0 && q_idx <= MT_LMAC_BCN0)
+		val |= MT_TXD6_DIS_MAT;
+
 	if (is_mt7996(&dev->mt76))
 		val |= FIELD_PREP(MT_TXD6_MSDU_CNT, 1);
 	else if (is_8023 || !ieee80211_is_mgmt(hdr->frame_control))
@@ -923,7 +948,7 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 	if (is_8023)
 		mt7996_mac_write_txwi_8023(dev, txwi, skb, wcid);
 	else
-		mt7996_mac_write_txwi_80211(dev, txwi, skb, key);
+		mt7996_mac_write_txwi_80211(dev, txwi, skb, key, wcid);
 
 	if (txwi[1] & cpu_to_le32(MT_TXD1_FIXED_RATE)) {
 		bool mcast = ieee80211_is_data(hdr->frame_control) &&
@@ -940,6 +965,8 @@ void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 		}
 
 		val = FIELD_PREP(MT_TXD6_TX_RATE, idx) | MT_TXD6_FIXED_BW;
+		if (mcast)
+			val |= MT_TXD6_DIS_MAT;
 		txwi[6] |= cpu_to_le32(val);
 		txwi[3] |= cpu_to_le32(MT_TXD3_BA_DISABLE);
 	}

From 19db942418f53959f6d9b6fb60fe43268552fe01 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:49 +0100
Subject: [PATCH 2319/2753] wifi: mt76: mt7996: Rely on wcid_to_sta in
 mt7996_mac_add_txs_skb()

This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-5-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index eed692cd64a6a..9f8436edc8137 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -1287,7 +1287,7 @@ mt7996_mac_add_txs_skb(struct mt7996_dev *dev, struct mt76_wcid *wcid,
 		struct ieee80211_sta *sta;
 		u8 tid;
 
-		sta = container_of((void *)wcid, struct ieee80211_sta, drv_priv);
+		sta = wcid_to_sta(wcid);
 		tid = FIELD_GET(MT_TXS0_TID, txs);
 		ieee80211_refresh_tx_agg_session_timer(sta, tid);
 	}

From 7464b12b7d92b9641d4664735b9f3c3f0b6173d9 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:50 +0100
Subject: [PATCH 2320/2753] wifi: mt76: mt7996: rework mt7996_rx_get_wcid to
 support MLO

The wcid idx and band idx in the TXS are sometimes mismatched since the
FW will select a transmission link according to a private algorithm.
That is, the wcid idx in the TXS would be the one registered by the
driver rather than the actual wcid idx used during transmission.
However, the band idx in the TXS is the band select for transmission.
Therefore, we should get the driver-registered wcid in order
to notify the driver the packet has been acked; otherwise,
the driver will be unable to match the transmitted packet and its TXS.
This is a preliminary patch to enable MLO for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-6-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 33 +++++++++++++++----
 1 file changed, 26 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 9f8436edc8137..b8d88fdee97a3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -53,29 +53,48 @@ static const struct mt7996_dfs_radar_spec jp_radar_specs = {
 };
 
 static struct mt76_wcid *mt7996_rx_get_wcid(struct mt7996_dev *dev,
-					    u16 idx, bool unicast)
+					    u16 idx, u8 band_idx)
 {
 	struct mt7996_sta_link *msta_link;
 	struct mt7996_sta *msta;
+	struct mt7996_vif *mvif;
 	struct mt76_wcid *wcid;
+	int i;
 
 	if (idx >= ARRAY_SIZE(dev->mt76.wcid))
 		return NULL;
 
 	wcid = rcu_dereference(dev->mt76.wcid[idx]);
-	if (unicast || !wcid)
-		return wcid;
+	if (!wcid)
+		return NULL;
 
-	if (!wcid->sta)
+	if (!mt7996_band_valid(dev, band_idx))
 		return NULL;
 
+	if (wcid->phy_idx == band_idx)
+		return wcid;
+
 	msta_link = container_of(wcid, struct mt7996_sta_link, wcid);
 	msta = msta_link->sta;
-
 	if (!msta || !msta->vif)
 		return NULL;
 
-	return &msta->vif->deflink.msta_link.wcid;
+	mvif = msta->vif;
+	for (i = 0; i < ARRAY_SIZE(mvif->mt76.link); i++) {
+		struct mt76_vif_link *mlink;
+
+		mlink = rcu_dereference(mvif->mt76.link[i]);
+		if (!mlink)
+			continue;
+
+		if (mlink->band_idx != band_idx)
+			continue;
+
+		msta_link = rcu_dereference(msta->link[i]);
+		break;
+	}
+
+	return &msta_link->wcid;
 }
 
 bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask)
@@ -483,7 +502,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
 
 	unicast = FIELD_GET(MT_RXD3_NORMAL_ADDR_TYPE, rxd3) == MT_RXD3_NORMAL_U2M;
 	idx = FIELD_GET(MT_RXD1_NORMAL_WLAN_IDX, rxd1);
-	status->wcid = mt7996_rx_get_wcid(dev, idx, unicast);
+	status->wcid = mt7996_rx_get_wcid(dev, idx, band_idx);
 
 	if (status->wcid) {
 		struct mt7996_sta_link *msta_link;

From aa99241833bffd44e604f92b97d7652f300cdce6 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:51 +0100
Subject: [PATCH 2321/2753] wifi: mt76: mt7996: rework mt7996_sta_set_4addr and
 mt7996_sta_set_decap_offload to support MLO

Rework mt7996_sta_set_4addr and mt7996_sta_set_decap_offload routines in
order to properly support multi-link. This is a preliminary patch to enable
MLO for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-7-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 74 ++++++++++++++-----
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 11 +--
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  3 +-
 3 files changed, 61 insertions(+), 27 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 642d633b5126c..f7703e00712cd 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1540,19 +1540,37 @@ static void mt7996_sta_set_4addr(struct ieee80211_hw *hw,
 				 struct ieee80211_sta *sta,
 				 bool enabled)
 {
-	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
 
-	if (enabled)
-		set_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
-	else
-		clear_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
+	mutex_lock(&dev->mt76.mutex);
 
-	if (!msta_link->wcid.sta)
-		return;
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct mt7996_sta_link *msta_link;
+		struct mt7996_vif_link *link;
 
-	mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta);
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
+
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
+		if (!msta_link)
+			continue;
+
+		if (enabled)
+			set_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
+		else
+			clear_bit(MT_WCID_FLAG_4ADDR, &msta_link->wcid.flags);
+
+		if (!msta_link->wcid.sta)
+			continue;
+
+		mt7996_mcu_wtbl_update_hdr_trans(dev, vif, link, msta_link);
+	}
+
+	mutex_unlock(&dev->mt76.mutex);
 }
 
 static void mt7996_sta_set_decap_offload(struct ieee80211_hw *hw,
@@ -1560,19 +1578,39 @@ static void mt7996_sta_set_decap_offload(struct ieee80211_hw *hw,
 					 struct ieee80211_sta *sta,
 					 bool enabled)
 {
-	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct mt7996_dev *dev = mt7996_hw_dev(hw);
+	struct ieee80211_link_sta *link_sta;
+	unsigned int link_id;
 
-	if (enabled)
-		set_bit(MT_WCID_FLAG_HDR_TRANS, &msta_link->wcid.flags);
-	else
-		clear_bit(MT_WCID_FLAG_HDR_TRANS, &msta_link->wcid.flags);
+	mutex_lock(&dev->mt76.mutex);
 
-	if (!msta_link->wcid.sta)
-		return;
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct mt7996_sta_link *msta_link;
+		struct mt7996_vif_link *link;
 
-	mt7996_mcu_wtbl_update_hdr_trans(dev, vif, sta);
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
+
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
+		if (!msta_link)
+			continue;
+
+		if (enabled)
+			set_bit(MT_WCID_FLAG_HDR_TRANS,
+				&msta_link->wcid.flags);
+		else
+			clear_bit(MT_WCID_FLAG_HDR_TRANS,
+				  &msta_link->wcid.flags);
+
+		if (!msta_link->wcid.sta)
+			continue;
+
+		mt7996_mcu_wtbl_update_hdr_trans(dev, vif, link, msta_link);
+	}
+
+	mutex_unlock(&dev->mt76.mutex);
 }
 
 static const char mt7996_gstrings_stats[][ETH_GSTRING_LEN] = {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index a5522f31c343b..263eb1f552f00 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4465,17 +4465,12 @@ int mt7996_mcu_rdd_cmd(struct mt7996_dev *dev, int cmd, u8 index,
 
 int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     struct ieee80211_vif *vif,
-				     struct ieee80211_sta *sta)
+				     struct mt7996_vif_link *link,
+				     struct mt7996_sta_link *msta_link)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link;
-	struct mt7996_sta *msta;
 	struct sk_buff *skb;
 
-	msta = sta ? (struct mt7996_sta *)sta->drv_priv : NULL;
-	msta_link = msta ? &msta->deflink : &mvif->deflink.msta_link;
-
-	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
+	skb = __mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
 					      &msta_link->wcid,
 					      MT7996_STA_UPDATE_MAX_SIZE);
 	if (IS_ERR(skb))
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index c2a2916e0647c..f226090bcd02e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -749,7 +749,8 @@ int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif
 			       struct ieee80211_key_conf *key);
 int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     struct ieee80211_vif *vif,
-				     struct ieee80211_sta *sta);
+				     struct mt7996_vif_link *link,
+				     struct mt7996_sta_link *msta_link);
 int mt7996_mcu_cp_support(struct mt7996_dev *dev, u8 mode);
 #ifdef CONFIG_MAC80211_DEBUGFS
 void mt7996_sta_add_debugfs(struct ieee80211_hw *hw, struct ieee80211_vif *vif,

From c9710b54763b2907740898f2b6032af2bb8369fd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:52 +0100
Subject: [PATCH 2322/2753] wifi: mt76: mt7996: Add mt7996_sta_link to
 mt7996_mcu_add_bss_info signature

This is a preliminary patch to introduce MLO support for MT996 driver.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-8-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   | 13 ++++++++-----
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c    |  5 +++--
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h |  3 ++-
 3 files changed, 13 insertions(+), 8 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index f7703e00712cd..4abbe761b732f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -195,7 +195,8 @@ mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 
 	if (cmd == SET_KEY && !sta && !mlink->mt76.cipher) {
 		mlink->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher);
-		mt7996_mcu_add_bss_info(phy, vif, &vif->bss_conf, &mlink->mt76, true);
+		mt7996_mcu_add_bss_info(phy, vif, &vif->bss_conf, &mlink->mt76,
+					&mlink->msta_link, true);
 	}
 
 	if (cmd == SET_KEY) {
@@ -288,7 +289,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	mt7996_init_bitrate_mask(vif, link);
 
-	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, true);
+	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, msta_link, true);
 	/* defer the first STA_REC of BMC entry to BSS_CHANGED_BSSID for STA
 	 * interface, since firmware only records BSSID when the entry is new
 	 */
@@ -314,7 +315,7 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL,
 			   CONN_STATE_DISCONNECT, false);
-	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, false);
+	mt7996_mcu_add_bss_info(phy, vif, link_conf, mlink, msta_link, false);
 
 	mt7996_mcu_add_dev_info(phy, vif, link_conf, mlink, false);
 
@@ -704,7 +705,8 @@ mt7996_vif_cfg_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 				continue;
 
 			mt7996_mcu_add_bss_info(link->phy, vif, link_conf,
-						&link->mt76, true);
+						&link->mt76, &link->msta_link,
+						true);
 			mt7996_mcu_add_sta(dev, link_conf, NULL, link, NULL,
 					   CONN_STATE_PORT_SECURE,
 					   !!(changed & BSS_CHANGED_BSSID));
@@ -740,7 +742,8 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	 */
 	if ((changed & BSS_CHANGED_BSSID && !is_zero_ether_addr(info->bssid)) ||
 	    (changed & BSS_CHANGED_BEACON_ENABLED && info->enable_beacon)) {
-		mt7996_mcu_add_bss_info(phy, vif, info, &link->mt76, true);
+		mt7996_mcu_add_bss_info(phy, vif, info, &link->mt76,
+					&link->msta_link, true);
 		mt7996_mcu_add_sta(dev, info, NULL, link, NULL,
 				   CONN_STATE_PORT_SECURE,
 				   !!(changed & BSS_CHANGED_BSSID));
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 263eb1f552f00..2520feba1607d 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1064,7 +1064,8 @@ __mt7996_mcu_alloc_bss_req(struct mt76_dev *dev, struct mt76_vif_link *mvif, int
 
 int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_bss_conf *link_conf,
-			    struct mt76_vif_link *mlink, int enable)
+			    struct mt76_vif_link *mlink,
+			    struct mt7996_sta_link *msta_link, int enable)
 {
 	struct mt7996_dev *dev = phy->dev;
 	struct sk_buff *skb;
@@ -1081,7 +1082,7 @@ int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 
 	/* bss_basic must be first */
 	mt7996_mcu_bss_basic_tlv(skb, vif, link_conf, mlink, phy->mt76,
-				 mlink->wcid->idx, enable);
+				 msta_link->wcid.idx, enable);
 	mt7996_mcu_bss_sec_tlv(skb, mlink);
 
 	if (vif->type == NL80211_IFTYPE_MONITOR)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index f226090bcd02e..4d5ab3f4b78ee 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -571,7 +571,8 @@ int mt7996_mcu_add_dev_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct mt76_vif_link *mlink, bool enable);
 int mt7996_mcu_add_bss_info(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 			    struct ieee80211_bss_conf *link_conf,
-			    struct mt76_vif_link *mlink, int enable);
+			    struct mt76_vif_link *mlink,
+			    struct mt7996_sta_link *msta_link, int enable);
 int mt7996_mcu_add_sta(struct mt7996_dev *dev,
 		       struct ieee80211_bss_conf *link_conf,
 		       struct ieee80211_link_sta *link_sta,

From 01690494f6540702fdb9e83c7f9ad4946aabd963 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:53 +0100
Subject: [PATCH 2323/2753] wifi: mt76: mt7996: rework mt7996_set_hw_key to
 support MLO

Modify mt7996_set_hw_key routine to work in a multi-link setup.
This is a preliminary patch to enable MLO for MT7996 driver

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-9-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 138 +++++++++++-------
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   |  18 +--
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |   4 +-
 3 files changed, 99 insertions(+), 61 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 4abbe761b732f..a845c3e758adc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -158,62 +158,101 @@ mt7996_init_bitrate_mask(struct ieee80211_vif *vif, struct mt7996_vif_link *mlin
 static int
 mt7996_set_hw_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		  struct ieee80211_vif *vif, struct ieee80211_sta *sta,
-		  struct mt7996_vif_link *mlink, struct ieee80211_key_conf *key)
+		  struct ieee80211_key_conf *key)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt76_wcid *wcid = &mlink->msta_link.wcid;
-	struct mt7996_phy *phy;
 	int idx = key->keyidx;
-	u8 *wcid_keyidx;
+	unsigned int link_id;
+	unsigned long links;
+
+	if (key->link_id >= 0)
+		links = BIT(key->link_id);
+	else if (sta && sta->valid_links)
+		links = sta->valid_links;
+	else if (vif->valid_links)
+		links = vif->valid_links;
+	else
+		links = BIT(0);
 
-	phy = mt7996_vif_link_phy(mlink);
-	if (!phy)
-		return -EINVAL;
+	for_each_set_bit(link_id, &links, IEEE80211_MLD_MAX_NUM_LINKS) {
+		struct mt7996_sta_link *msta_link;
+		struct mt7996_vif_link *link;
+		u8 *wcid_keyidx;
+		int err;
 
-	if (sta) {
-		struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
 
-		wcid = &msta->deflink.wcid;
-		if (!wcid->sta)
-			return -EOPNOTSUPP;
-	}
-	wcid_keyidx = &wcid->hw_key_idx;
+		if (sta) {
+			struct mt7996_sta *msta;
 
-	switch (key->cipher) {
-	case WLAN_CIPHER_SUITE_AES_CMAC:
-	case WLAN_CIPHER_SUITE_BIP_CMAC_256:
-	case WLAN_CIPHER_SUITE_BIP_GMAC_128:
-	case WLAN_CIPHER_SUITE_BIP_GMAC_256:
-		if (key->keyidx == 6 || key->keyidx == 7) {
-			wcid_keyidx = &wcid->hw_key_idx2;
-			key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE;
+			msta = (struct mt7996_sta *)sta->drv_priv;
+			msta_link = mt76_dereference(msta->link[link_id],
+						     &dev->mt76);
+			if (!msta_link)
+				continue;
+
+			if (!msta_link->wcid.sta)
+				return -EOPNOTSUPP;
+		} else {
+			msta_link = &link->msta_link;
+		}
+		wcid_keyidx = &msta_link->wcid.hw_key_idx;
+
+		switch (key->cipher) {
+		case WLAN_CIPHER_SUITE_AES_CMAC:
+		case WLAN_CIPHER_SUITE_BIP_CMAC_256:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_128:
+		case WLAN_CIPHER_SUITE_BIP_GMAC_256:
+			if (key->keyidx == 6 || key->keyidx == 7) {
+				wcid_keyidx = &msta_link->wcid.hw_key_idx2;
+				key->flags |= IEEE80211_KEY_FLAG_GENERATE_MMIE;
+			}
+			break;
+		default:
+			break;
 		}
-		break;
-	default:
-		break;
-	}
 
-	if (cmd == SET_KEY && !sta && !mlink->mt76.cipher) {
-		mlink->mt76.cipher = mt76_connac_mcu_get_cipher(key->cipher);
-		mt7996_mcu_add_bss_info(phy, vif, &vif->bss_conf, &mlink->mt76,
-					&mlink->msta_link, true);
-	}
+		if (cmd == SET_KEY && !sta && !link->mt76.cipher) {
+			struct ieee80211_bss_conf *link_conf;
 
-	if (cmd == SET_KEY) {
-		*wcid_keyidx = idx;
-	} else {
-		if (idx == *wcid_keyidx)
-			*wcid_keyidx = -1;
-		return 0;
-	}
+			link_conf = link_conf_dereference_protected(vif,
+								    link_id);
+			if (!link_conf)
+				link_conf = &vif->bss_conf;
 
-	mt76_wcid_key_setup(&dev->mt76, wcid, key);
+			link->mt76.cipher =
+				mt76_connac_mcu_get_cipher(key->cipher);
+			mt7996_mcu_add_bss_info(link->phy, vif, link_conf,
+						&link->mt76, msta_link, true);
+		}
 
-	if (key->keyidx == 6 || key->keyidx == 7)
-		return mt7996_mcu_bcn_prot_enable(dev, vif, key);
+		if (cmd == SET_KEY) {
+			*wcid_keyidx = idx;
+		} else {
+			if (idx == *wcid_keyidx)
+				*wcid_keyidx = -1;
+			continue;
+		}
 
-	return mt7996_mcu_add_key(&dev->mt76, vif, key,
-				  MCU_WMWA_UNI_CMD(STA_REC_UPDATE), wcid, cmd);
+		mt76_wcid_key_setup(&dev->mt76, &msta_link->wcid, key);
+
+		if (key->keyidx == 6 || key->keyidx == 7) {
+			err = mt7996_mcu_bcn_prot_enable(dev, link,
+							 msta_link, key);
+			if (err)
+				return err;
+		}
+
+		err = mt7996_mcu_add_key(&dev->mt76, vif, key,
+					 MCU_WMWA_UNI_CMD(STA_REC_UPDATE),
+					 &msta_link->wcid, cmd);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static void
@@ -221,12 +260,10 @@ mt7996_key_iter(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		struct ieee80211_sta *sta, struct ieee80211_key_conf *key,
 		void *data)
 {
-	struct mt7996_vif_link *mlink = data;
-
 	if (sta)
 		return;
 
-	WARN_ON(mt7996_set_hw_key(hw, SET_KEY, vif, NULL, mlink, key));
+	WARN_ON(mt7996_set_hw_key(hw, SET_KEY, vif, NULL, key));
 }
 
 int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
@@ -298,7 +335,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 				   CONN_STATE_PORT_SECURE, true);
 	rcu_assign_pointer(dev->mt76.wcid[idx], &msta_link->wcid);
 
-	ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, link);
+	ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, NULL);
 
 	return 0;
 }
@@ -486,7 +523,6 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_vif_link *mlink = &mvif->deflink;
 	int err;
 
 	/* The hardware does not support per-STA RX GTK, fallback
@@ -521,11 +557,11 @@ static int mt7996_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd,
 		return -EOPNOTSUPP;
 	}
 
-	if (!mt7996_vif_link_phy(mlink))
-	    return 0; /* defer until after link add */
+	if (!mt7996_vif_link_phy(&mvif->deflink))
+		return 0; /* defer until after link add */
 
 	mutex_lock(&dev->mt76.mutex);
-	err = mt7996_set_hw_key(hw, cmd, vif, sta, mlink, key);
+	err = mt7996_set_hw_key(hw, cmd, vif, sta, key);
 	mutex_unlock(&dev->mt76.mutex);
 
 	return err;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 2520feba1607d..2404569018a03 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2430,18 +2430,17 @@ int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
 	return mt76_mcu_skb_send_msg(dev, skb, mcu_cmd, true);
 }
 
-static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif,
-			     u8 *pn)
+static int mt7996_mcu_get_pn(struct mt7996_dev *dev,
+			     struct mt7996_vif_link *link,
+			     struct mt7996_sta_link *msta_link, u8 *pn)
 {
 #define TSC_TYPE_BIGTK_PN 2
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link = &mvif->deflink.msta_link;
 	struct sta_rec_pn_info *pn_info;
 	struct sk_buff *skb, *rskb;
 	struct tlv *tlv;
 	int ret;
 
-	skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &mvif->deflink.mt76,
+	skb = mt76_connac_mcu_alloc_sta_req(&dev->mt76, &link->mt76,
 					    &msta_link->wcid);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -2466,10 +2465,11 @@ static int mt7996_mcu_get_pn(struct mt7996_dev *dev, struct ieee80211_vif *vif,
 	return 0;
 }
 
-int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev,
+			       struct mt7996_vif_link *link,
+			       struct mt7996_sta_link *msta_link,
 			       struct ieee80211_key_conf *key)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_mcu_bcn_prot_tlv *bcn_prot;
 	struct sk_buff *skb;
 	struct tlv *tlv;
@@ -2478,7 +2478,7 @@ int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif
 		  sizeof(struct mt7996_mcu_bcn_prot_tlv);
 	int ret;
 
-	skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->deflink.mt76, len);
+	skb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &link->mt76, len);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
 
@@ -2486,7 +2486,7 @@ int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif
 
 	bcn_prot = (struct mt7996_mcu_bcn_prot_tlv *)tlv;
 
-	ret = mt7996_mcu_get_pn(dev, vif, pn);
+	ret = mt7996_mcu_get_pn(dev, link, msta_link, pn);
 	if (ret) {
 		dev_kfree_skb(skb);
 		return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 4d5ab3f4b78ee..1e79757b7a519 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -746,7 +746,9 @@ bool mt7996_debugfs_rx_log(struct mt7996_dev *dev, const void *data, int len);
 int mt7996_mcu_add_key(struct mt76_dev *dev, struct ieee80211_vif *vif,
 		       struct ieee80211_key_conf *key, int mcu_cmd,
 		       struct mt76_wcid *wcid, enum set_key_cmd cmd);
-int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev, struct ieee80211_vif *vif,
+int mt7996_mcu_bcn_prot_enable(struct mt7996_dev *dev,
+			       struct mt7996_vif_link *link,
+			       struct mt7996_sta_link *msta_link,
 			       struct ieee80211_key_conf *key);
 int mt7996_mcu_wtbl_update_hdr_trans(struct mt7996_dev *dev,
 				     struct ieee80211_vif *vif,

From cf88e159de3d32aeca223cb6fc953c951479eaf8 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:54 +0100
Subject: [PATCH 2324/2753] wifi: mt76: mt7996: rework mt7996_sta_hw_queue_read
 to support MLO

Extend mt7996_sta_hw_queue_read to support multi-link setup.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-10-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../wireless/mediatek/mt76/mt7996/debugfs.c   | 54 +++++++++++++------
 1 file changed, 38 insertions(+), 16 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
index d453c2fc97e4f..4a28db17a2874 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/debugfs.c
@@ -616,29 +616,51 @@ static void
 mt7996_sta_hw_queue_read(void *data, struct ieee80211_sta *sta)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_dev *dev = msta->vif->deflink.phy->dev;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct mt7996_vif *mvif = msta->vif;
+	struct mt7996_dev *dev = mvif->deflink.phy->dev;
+	struct ieee80211_link_sta *link_sta;
 	struct seq_file *s = data;
-	u8 ac;
+	struct ieee80211_vif *vif;
+	unsigned int link_id;
 
-	for (ac = 0; ac < 4; ac++) {
-		u32 qlen, ctrl, val;
-		u32 idx = msta_link->wcid.idx >> 5;
-		u8 offs = msta_link->wcid.idx & GENMASK(4, 0);
+	vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv);
+
+	rcu_read_lock();
 
-		ctrl = BIT(31) | BIT(11) | (ac << 24);
-		val = mt76_rr(dev, MT_PLE_AC_QEMPTY(ac, idx));
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct mt7996_sta_link *msta_link;
+		struct mt76_vif_link *mlink;
+		u8 ac;
 
-		if (val & BIT(offs))
+		mlink = rcu_dereference(mvif->mt76.link[link_id]);
+		if (!mlink)
 			continue;
 
-		mt76_wr(dev, MT_FL_Q0_CTRL, ctrl | msta_link->wcid.idx);
-		qlen = mt76_get_field(dev, MT_FL_Q3_CTRL,
-				      GENMASK(11, 0));
-		seq_printf(s, "\tSTA %pM wcid %d: AC%d%d queued:%d\n",
-			   sta->addr, msta_link->wcid.idx,
-			   msta->vif->deflink.mt76.wmm_idx, ac, qlen);
+		msta_link = rcu_dereference(msta->link[link_id]);
+		if (!msta_link)
+			continue;
+
+		for (ac = 0; ac < 4; ac++) {
+			u32 idx = msta_link->wcid.idx >> 5, qlen, ctrl, val;
+			u8 offs = msta_link->wcid.idx & GENMASK(4, 0);
+
+			ctrl = BIT(31) | BIT(11) | (ac << 24);
+			val = mt76_rr(dev, MT_PLE_AC_QEMPTY(ac, idx));
+
+			if (val & BIT(offs))
+				continue;
+
+			mt76_wr(dev,
+				MT_FL_Q0_CTRL, ctrl | msta_link->wcid.idx);
+			qlen = mt76_get_field(dev, MT_FL_Q3_CTRL,
+					      GENMASK(11, 0));
+			seq_printf(s, "\tSTA %pM wcid %d: AC%d%d queued:%d\n",
+				   sta->addr, msta_link->wcid.idx,
+				   mlink->wmm_idx, ac, qlen);
+		}
 	}
+
+	rcu_read_unlock();
 }
 
 static int

From 601e4adc6520bfd1e3a8ad26139f22cc0ccb2e58 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:13:55 +0100
Subject: [PATCH 2325/2753] wifi: mt76: mt7996: remove
 mt7996_mac_enable_rtscts()

It is controlled by FW, also, driver should not directly write WTBL to
prevent WTBL overwritten issues.

Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-11-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c    | 14 --------------
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   |  3 ---
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h |  2 --
 3 files changed, 19 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index b8d88fdee97a3..c1c7638e29a12 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -217,20 +217,6 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 	rcu_read_unlock();
 }
 
-void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
-			      struct ieee80211_vif *vif, bool enable)
-{
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_sta_link *msta_link = &mvif->deflink.msta_link;
-	u32 addr;
-
-	addr = mt7996_mac_wtbl_lmac_addr(dev, msta_link->wcid.idx, 5);
-	if (enable)
-		mt76_set(dev, addr, BIT(5));
-	else
-		mt76_clear(dev, addr, BIT(5));
-}
-
 /* The HW does not translate the mac header to 802.3 for mesh point */
 static int mt7996_reverse_frag0_hdr_trans(struct sk_buff *skb, u16 hdr_gap)
 {
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index a845c3e758adc..8d7ad2dc2d7bc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -785,9 +785,6 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 				   !!(changed & BSS_CHANGED_BSSID));
 	}
 
-	if (changed & BSS_CHANGED_ERP_CTS_PROT)
-		mt7996_mac_enable_rtscts(dev, vif, info->use_cts_prot);
-
 	if (changed & BSS_CHANGED_ERP_SLOT) {
 		int slottime = info->use_short_slot ? 9 : 20;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 1e79757b7a519..8a347dd8e648a 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -707,8 +707,6 @@ bool mt7996_mac_wtbl_update(struct mt7996_dev *dev, int idx, u32 mask);
 void mt7996_mac_reset_counters(struct mt7996_phy *phy);
 void mt7996_mac_cca_stats_reset(struct mt7996_phy *phy);
 void mt7996_mac_enable_nf(struct mt7996_dev *dev, u8 band);
-void mt7996_mac_enable_rtscts(struct mt7996_dev *dev,
-			      struct ieee80211_vif *vif, bool enable);
 void mt7996_mac_write_txwi(struct mt7996_dev *dev, __le32 *txwi,
 			   struct sk_buff *skb, struct mt76_wcid *wcid,
 			   struct ieee80211_key_conf *key, int pid,

From 0762bdd30279facd1ccf681d38b27ffe9dd2fa17 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:56 +0100
Subject: [PATCH 2326/2753] wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work
 to support MLO

Rework mt7996_mac_sta_rc_work routine in order to support multi-link
setup.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Co-developed-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-12-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 40 ++++++++++++++-----
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 30 +++++++++-----
 2 files changed, 52 insertions(+), 18 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index c1c7638e29a12..c56b1126abd59 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2300,13 +2300,20 @@ void mt7996_mac_update_stats(struct mt7996_phy *phy)
 void mt7996_mac_sta_rc_work(struct work_struct *work)
 {
 	struct mt7996_dev *dev = container_of(work, struct mt7996_dev, rc_work);
+	struct ieee80211_bss_conf *link_conf;
+	struct ieee80211_link_sta *link_sta;
 	struct mt7996_sta_link *msta_link;
+	struct mt7996_vif_link *link;
+	struct mt76_vif_link *mlink;
 	struct ieee80211_sta *sta;
 	struct ieee80211_vif *vif;
 	struct mt7996_sta *msta;
-	u32 changed;
+	struct mt7996_vif *mvif;
 	LIST_HEAD(list);
+	u32 changed;
+	u8 link_id;
 
+	rcu_read_lock();
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
 	list_splice_init(&dev->sta_rc_list, &list);
 
@@ -2319,21 +2326,35 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 		msta_link->changed = 0;
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
+		sta = wcid_to_sta(&msta_link->wcid);
+		link_id = msta_link->wcid.link_id;
 		msta = msta_link->sta;
-		sta = container_of((void *)msta, struct ieee80211_sta, drv_priv);
-		vif = container_of((void *)msta->vif, struct ieee80211_vif, drv_priv);
+		mvif = msta->vif;
+		vif = container_of((void *)mvif, struct ieee80211_vif, drv_priv);
+
+		mlink = rcu_dereference(mvif->mt76.link[link_id]);
+		if (!mlink)
+			continue;
+
+		link_sta = rcu_dereference(sta->link[link_id]);
+		if (!link_sta)
+			continue;
+
+		link_conf = rcu_dereference(vif->link_conf[link_id]);
+		if (!link_conf)
+			continue;
+
+		link = (struct mt7996_vif_link *)mlink;
 
 		if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED |
 			       IEEE80211_RC_NSS_CHANGED |
 			       IEEE80211_RC_BW_CHANGED))
-			mt7996_mcu_add_rate_ctrl(dev, vif, &vif->bss_conf,
-						 &sta->deflink,
-						 &msta->vif->deflink,
-						 msta_link, true);
+			mt7996_mcu_add_rate_ctrl(dev, vif, link_conf,
+						 link_sta, link, msta_link,
+						 true);
 
 		if (changed & IEEE80211_RC_SMPS_CHANGED)
-			mt7996_mcu_set_fixed_field(dev, &sta->deflink,
-						   &msta->vif->deflink,
+			mt7996_mcu_set_fixed_field(dev, link_sta, link,
 						   msta_link, NULL,
 						   RATE_PARAM_MMPS_UPDATE);
 
@@ -2341,6 +2362,7 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 	}
 
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
+	rcu_read_unlock();
 }
 
 void mt7996_mac_work(struct work_struct *work)
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 8d7ad2dc2d7bc..4d3098e47dbbc 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -304,6 +304,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	INIT_LIST_HEAD(&msta_link->rc_list);
 	msta_link->wcid.idx = idx;
+	msta_link->wcid.link_id = link_conf->link_id;
 	msta_link->wcid.tx_info |= MT_WCID_TX_INFO_SET;
 	mt76_wcid_init(&msta_link->wcid, band_idx);
 
@@ -1521,29 +1522,39 @@ static void mt7996_sta_statistics(struct ieee80211_hw *hw,
 	}
 }
 
-static void mt7996_sta_rc_work(void *data, struct ieee80211_sta *sta)
+static void mt7996_link_rate_ctrl_update(void *data, struct ieee80211_sta *sta)
 {
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
 	struct mt7996_dev *dev = msta->vif->deflink.phy->dev;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct mt7996_sta_link *msta_link;
 	u32 *changed = data;
 
+	rcu_read_lock();
+
+	msta_link = rcu_dereference(msta->link[msta->deflink_id]);
+	if (!msta_link)
+		goto out;
+
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
+
 	msta_link->changed |= *changed;
 	if (list_empty(&msta_link->rc_list))
 		list_add_tail(&msta_link->rc_list, &dev->sta_rc_list);
+
 	spin_unlock_bh(&dev->mt76.sta_poll_lock);
+out:
+	rcu_read_unlock();
 }
 
-static void mt7996_sta_rc_update(struct ieee80211_hw *hw,
-				 struct ieee80211_vif *vif,
-				 struct ieee80211_link_sta *link_sta,
-				 u32 changed)
+static void mt7996_link_sta_rc_update(struct ieee80211_hw *hw,
+				      struct ieee80211_vif *vif,
+				      struct ieee80211_link_sta *link_sta,
+				      u32 changed)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct ieee80211_sta *sta = link_sta->sta;
 
-	mt7996_sta_rc_work(&changed, sta);
+	mt7996_link_rate_ctrl_update(&changed, sta);
 	ieee80211_queue_work(hw, &dev->rc_work);
 }
 
@@ -1565,7 +1576,8 @@ mt7996_set_bitrate_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	 * - multiple rates: if it's not in range format i.e 0-{7,8,9} for VHT
 	 * then multiple MCS setting (MCS 4,5,6) is not supported.
 	 */
-	ieee80211_iterate_stations_atomic(hw, mt7996_sta_rc_work, &changed);
+	ieee80211_iterate_stations_atomic(hw, mt7996_link_rate_ctrl_update,
+					  &changed);
 	ieee80211_queue_work(hw, &dev->rc_work);
 
 	return 0;
@@ -2023,7 +2035,7 @@ const struct ieee80211_ops mt7996_ops = {
 	.link_info_changed = mt7996_link_info_changed,
 	.sta_state = mt7996_sta_state,
 	.sta_pre_rcu_remove = mt76_sta_pre_rcu_remove,
-	.link_sta_rc_update = mt7996_sta_rc_update,
+	.link_sta_rc_update = mt7996_link_sta_rc_update,
 	.set_key = mt7996_set_key,
 	.ampdu_action = mt7996_ampdu_action,
 	.set_rts_threshold = mt7996_set_rts_threshold,

From 19a2239529c177a717146203ebc29db32221a214 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:57 +0100
Subject: [PATCH 2327/2753] wifi: mt76: mt7996: rework mt7996_mac_sta_poll to
 support MLO

Rework mt7996_mac_sta_poll routine in order to support multi-link
setup.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-13-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   | 20 ++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index c56b1126abd59..6870ee189dca6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -123,10 +123,12 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		[IEEE80211_AC_VO] = 6
 	};
 	struct mt7996_sta_link *msta_link;
+	struct mt76_vif_link *mlink;
 	struct ieee80211_sta *sta;
 	struct mt7996_sta *msta;
 	u32 tx_time[IEEE80211_NUM_ACS], rx_time[IEEE80211_NUM_ACS];
 	LIST_HEAD(sta_poll_list);
+	struct mt76_wcid *wcid;
 	int i;
 
 	spin_lock_bh(&dev->mt76.sta_poll_lock);
@@ -150,10 +152,11 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 					     struct mt7996_sta_link,
 					     wcid.poll_list);
 		msta = msta_link->sta;
-		list_del_init(&msta_link->wcid.poll_list);
+		wcid = &msta_link->wcid;
+		list_del_init(&wcid->poll_list);
 		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
-		idx = msta_link->wcid.idx;
+		idx = wcid->idx;
 
 		/* refresh peer's airtime reporting */
 		addr = mt7996_mac_wtbl_lmac_addr(dev, idx, 20);
@@ -181,7 +184,7 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 			       sizeof(msta_link->airtime_ac));
 		}
 
-		if (!msta_link->wcid.sta)
+		if (!wcid->sta)
 			continue;
 
 		sta = container_of((void *)msta, struct ieee80211_sta,
@@ -207,8 +210,15 @@ static void mt7996_mac_sta_poll(struct mt7996_dev *dev)
 		rssi[2] = to_rssi(GENMASK(23, 16), val);
 		rssi[3] = to_rssi(GENMASK(31, 14), val);
 
-		msta_link->ack_signal =
-			mt76_rx_signal(msta->vif->deflink.phy->mt76->antenna_mask, rssi);
+		mlink = rcu_dereference(msta->vif->mt76.link[wcid->link_id]);
+		if (mlink) {
+			struct mt76_phy *mphy = mt76_vif_link_phy(mlink);
+
+			if (mphy)
+				msta_link->ack_signal =
+					mt76_rx_signal(mphy->antenna_mask,
+						       rssi);
+		}
 
 		ewma_avg_signal_add(&msta_link->avg_ack_signal,
 				    -msta_link->ack_signal);

From 5c1fa8b219c8dac5e4a0b0ade771bb9c285f00bd Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:58 +0100
Subject: [PATCH 2328/2753] wifi: mt76: mt7996: rework mt7996_update_mu_group
 to support MLO

Rework mt7996_update_mu_group routine in order to support multi-link
setup.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-14-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c | 7 +++----
 1 file changed, 3 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 4d3098e47dbbc..2bf6453975ae5 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -700,12 +700,11 @@ mt7996_get_rates_table(struct mt7996_phy *phy, struct ieee80211_bss_conf *conf,
 }
 
 static void
-mt7996_update_mu_group(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+mt7996_update_mu_group(struct ieee80211_hw *hw, struct mt7996_vif_link *link,
 		       struct ieee80211_bss_conf *info)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	u8 band = mvif->deflink.mt76.band_idx;
+	u8 band = link->mt76.band_idx;
 	u32 *mu;
 
 	mu = (u32 *)info->mu_group.membership;
@@ -831,7 +830,7 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		mt7996_mcu_beacon_inband_discov(dev, vif, changed);
 
 	if (changed & BSS_CHANGED_MU_GROUPS)
-		mt7996_update_mu_group(hw, vif, info);
+		mt7996_update_mu_group(hw, link, info);
 
 	if (changed & BSS_CHANGED_TXPOWER &&
 	    info->txpower != phy->txpower) {

From 856825941dcc912f1b67f2f45d3ccfd3d861ab89 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:13:59 +0100
Subject: [PATCH 2329/2753] wifi: mt76: mt7996: rework
 mt7996_net_fill_forward_path to support MLO

Rework mt7996_net_fill_forward_path routine in order to support multi-link
setup.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-15-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 24 +++++++++++++------
 1 file changed, 17 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 2bf6453975ae5..4a33979ee8535 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1973,13 +1973,26 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
-	struct mt7996_vif_link *mlink = &mvif->deflink;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct mtk_wed_device *wed = &dev->mt76.mmio.wed;
+	struct mt7996_sta_link *msta_link;
+	struct mt7996_vif_link *link;
+	struct mt76_vif_link *mlink;
 	struct mt7996_phy *phy;
 
-	phy = mt7996_vif_link_phy(mlink);
+	mlink = rcu_dereference(mvif->mt76.link[msta->deflink_id]);
+	if (!mlink)
+		return -EIO;
+
+	msta_link = rcu_dereference(msta->link[msta->deflink_id]);
+	if (!msta_link)
+		return -EIO;
+
+	if (!msta_link->wcid.sta || msta_link->wcid.idx > MT7996_WTBL_STA)
+		return -EIO;
+
+	link = (struct mt7996_vif_link *)mlink;
+	phy = mt7996_vif_link_phy(link);
 	if (!phy)
 		return -ENODEV;
 
@@ -1989,13 +2002,10 @@ mt7996_net_fill_forward_path(struct ieee80211_hw *hw,
 	if (!mtk_wed_device_active(wed))
 		return -ENODEV;
 
-	if (!msta_link->wcid.sta || msta_link->wcid.idx > MT7996_WTBL_STA)
-		return -EIO;
-
 	path->type = DEV_PATH_MTK_WDMA;
 	path->dev = ctx->dev;
 	path->mtk_wdma.wdma_idx = wed->wdma_idx;
-	path->mtk_wdma.bss = mvif->deflink.mt76.idx;
+	path->mtk_wdma.bss = mlink->idx;
 	path->mtk_wdma.queue = 0;
 	path->mtk_wdma.wcid = msta_link->wcid.idx;
 

From 2bd378d6b5da8c3c2b03f9942df03fa26e177c18 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:14:00 +0100
Subject: [PATCH 2330/2753] wifi: mt76: mt7996: rework mt7996_mcu_add_obss_spr
 to support MLO

Rework mt7996_mcu_add_obss_spr routine in order to support multi-link
setup.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-16-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt7996/main.c   |  3 ++-
 drivers/net/wireless/mediatek/mt76/mt7996/mcu.c    | 11 ++++++-----
 drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h |  3 ++-
 3 files changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 4a33979ee8535..eeb856984298c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -807,7 +807,7 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 		mt7996_mcu_set_tx(dev, vif, info);
 
 	if (changed & BSS_CHANGED_HE_OBSS_PD)
-		mt7996_mcu_add_obss_spr(phy, vif, &info->he_obss_pd);
+		mt7996_mcu_add_obss_spr(phy, link, &info->he_obss_pd);
 
 	if (changed & BSS_CHANGED_HE_BSS_COLOR) {
 		if ((vif->type == NL80211_IFTYPE_AP &&
@@ -1254,6 +1254,7 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	mtxq = (struct mt76_txq *)txq->drv_priv;
 
 	mutex_lock(&dev->mt76.mutex);
+
 	switch (action) {
 	case IEEE80211_AMPDU_RX_START:
 		mt76_rx_aggr_start(&dev->mt76, &msta_link->wcid, tid, ssn,
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 2404569018a03..dd8cabe6552ae 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -4193,12 +4193,12 @@ mt7996_mcu_set_obss_spr_pd(struct mt7996_phy *phy,
 }
 
 static int
-mt7996_mcu_set_obss_spr_siga(struct mt7996_phy *phy, struct ieee80211_vif *vif,
+mt7996_mcu_set_obss_spr_siga(struct mt7996_phy *phy,
+			     struct mt7996_vif_link *link,
 			     struct ieee80211_he_obss_pd *he_obss_pd)
 {
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_dev *dev = phy->dev;
-	u8 omac = mvif->deflink.mt76.omac_idx;
+	u8 omac = link->mt76.omac_idx;
 	struct {
 		u8 band_idx;
 		u8 __rsv[3];
@@ -4270,7 +4270,8 @@ mt7996_mcu_set_obss_spr_bitmap(struct mt7996_phy *phy,
 				 sizeof(req), true);
 }
 
-int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif,
+int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy,
+			    struct mt7996_vif_link *link,
 			    struct ieee80211_he_obss_pd *he_obss_pd)
 {
 	int ret;
@@ -4304,7 +4305,7 @@ int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif,
 		return ret;
 
 	/* Set SR prohibit */
-	ret = mt7996_mcu_set_obss_spr_siga(phy, vif, he_obss_pd);
+	ret = mt7996_mcu_set_obss_spr_siga(phy, link, he_obss_pd);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 8a347dd8e648a..45280f8f34fc4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -595,7 +595,8 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			  struct ieee80211_bss_conf *link_conf);
 int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
 				    struct ieee80211_vif *vif, u32 changed);
-int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy, struct ieee80211_vif *vif,
+int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy,
+			    struct mt7996_vif_link *link,
 			    struct ieee80211_he_obss_pd *he_obss_pd);
 int mt7996_mcu_add_rate_ctrl(struct mt7996_dev *dev,
 			     struct ieee80211_vif *vif,

From c92fc81ba9e76973f4e5345183771af4d87addd8 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:14:01 +0100
Subject: [PATCH 2331/2753] wifi: mt76: mt7996: rework
 mt7996_mcu_beacon_inband_discov to support MLO

Rework mt7996_mcu_beacon_inband_discov routine in order to support
multi-link setup.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-17-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  |  2 +-
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 19 ++++++++++---------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  3 ++-
 3 files changed, 13 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index eeb856984298c..bcca1850d471b 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -827,7 +827,7 @@ mt7996_link_info_changed(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	if (changed & (BSS_CHANGED_UNSOL_BCAST_PROBE_RESP |
 		       BSS_CHANGED_FILS_DISCOVERY))
-		mt7996_mcu_beacon_inband_discov(dev, vif, changed);
+		mt7996_mcu_beacon_inband_discov(dev, info, link, changed);
 
 	if (changed & BSS_CHANGED_MU_GROUPS)
 		mt7996_update_mu_group(hw, link, info);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index dd8cabe6552ae..4bd0c16500ab6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -2717,13 +2717,14 @@ int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 }
 
 int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
-				    struct ieee80211_vif *vif, u32 changed)
+				    struct ieee80211_bss_conf *link_conf,
+				    struct mt7996_vif_link *link, u32 changed)
 {
 #define OFFLOAD_TX_MODE_SU	BIT(0)
 #define OFFLOAD_TX_MODE_MU	BIT(1)
+	struct ieee80211_vif *vif = link_conf->vif;
 	struct ieee80211_hw *hw = mt76_hw(dev);
-	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
-	struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink);
+	struct mt7996_phy *phy = link->phy;
 	struct mt76_wcid *wcid = &dev->mt76.global_wcid;
 	struct bss_inband_discovery_tlv *discov;
 	struct ieee80211_tx_info *info;
@@ -2740,21 +2741,21 @@ int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
 	chandef = &phy->mt76->chandef;
 	band = chandef->chan->band;
 
-	if (vif->bss_conf.nontransmitted)
+	if (link_conf->nontransmitted)
 		return 0;
 
-	rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &mvif->deflink.mt76,
+	rskb = __mt7996_mcu_alloc_bss_req(&dev->mt76, &link->mt76,
 					  MT7996_MAX_BSS_OFFLOAD_SIZE);
 	if (IS_ERR(rskb))
 		return PTR_ERR(rskb);
 
 	if (changed & BSS_CHANGED_FILS_DISCOVERY &&
-	    vif->bss_conf.fils_discovery.max_interval) {
-		interval = vif->bss_conf.fils_discovery.max_interval;
+	    link_conf->fils_discovery.max_interval) {
+		interval = link_conf->fils_discovery.max_interval;
 		skb = ieee80211_get_fils_discovery_tmpl(hw, vif);
 	} else if (changed & BSS_CHANGED_UNSOL_BCAST_PROBE_RESP &&
-		   vif->bss_conf.unsol_bcast_probe_resp_interval) {
-		interval = vif->bss_conf.unsol_bcast_probe_resp_interval;
+		   link_conf->unsol_bcast_probe_resp_interval) {
+		interval = link_conf->unsol_bcast_probe_resp_interval;
 		skb = ieee80211_get_unsol_bcast_probe_resp_tmpl(hw, vif);
 	}
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 45280f8f34fc4..124a48e2706e4 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -594,7 +594,8 @@ int mt7996_mcu_update_bss_color(struct mt7996_dev *dev,
 int mt7996_mcu_add_beacon(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 			  struct ieee80211_bss_conf *link_conf);
 int mt7996_mcu_beacon_inband_discov(struct mt7996_dev *dev,
-				    struct ieee80211_vif *vif, u32 changed);
+				    struct ieee80211_bss_conf *link_conf,
+				    struct mt7996_vif_link *link, u32 changed);
 int mt7996_mcu_add_obss_spr(struct mt7996_phy *phy,
 			    struct mt7996_vif_link *link,
 			    struct ieee80211_he_obss_pd *he_obss_pd);

From a3316d2fc669f585428a3c0086efe01a9547a171 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:14:02 +0100
Subject: [PATCH 2332/2753] wifi: mt76: mt7996: set vif default link_id
 adding/removing vif links

This info will be consumed by subsequent patches (e.g. in set/get tsf
routines).

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-18-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index bcca1850d471b..40efba5bcaac3 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -271,6 +271,7 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 			struct mt76_vif_link *mlink)
 {
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta_link *msta_link = &link->msta_link;
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
@@ -338,6 +339,9 @@ int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	ieee80211_iter_keys(mphy->hw, vif, mt7996_key_iter, NULL);
 
+	if (mvif->mt76.deflink_id == IEEE80211_LINK_UNSPECIFIED)
+		mvif->mt76.deflink_id = link_conf->link_id;
+
 	return 0;
 }
 
@@ -346,6 +350,7 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 			    struct mt76_vif_link *mlink)
 {
 	struct mt7996_vif_link *link = container_of(mlink, struct mt7996_vif_link, mt76);
+	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_sta_link *msta_link = &link->msta_link;
 	struct mt7996_phy *phy = mphy->priv;
 	struct mt7996_dev *dev = phy->dev;
@@ -359,6 +364,19 @@ void mt7996_vif_link_remove(struct mt76_phy *mphy, struct ieee80211_vif *vif,
 
 	rcu_assign_pointer(dev->mt76.wcid[idx], NULL);
 
+	if (mvif->mt76.deflink_id == link_conf->link_id) {
+		struct ieee80211_bss_conf *iter;
+		unsigned int link_id;
+
+		mvif->mt76.deflink_id = IEEE80211_LINK_UNSPECIFIED;
+		for_each_vif_active_link(vif, iter, link_id) {
+			if (link_id != IEEE80211_LINK_UNSPECIFIED) {
+				mvif->mt76.deflink_id = link_id;
+				break;
+			}
+		}
+	}
+
 	dev->mt76.vif_mask &= ~BIT_ULL(mlink->idx);
 	phy->omac_mask &= ~BIT_ULL(mlink->omac_idx);
 
@@ -443,6 +461,7 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
 	mt76_vif_init(vif, &mvif->mt76);
 
 	vif->offload_flags |= IEEE80211_OFFLOAD_ENCAP_4ADDR;
+	mvif->mt76.deflink_id = IEEE80211_LINK_UNSPECIFIED;
 
 out:
 	mutex_unlock(&dev->mt76.mutex);

From a9384b36a42afc2d715eb74c19a7ee558f09ef82 Mon Sep 17 00:00:00 2001
From: Shayne Chen <shayne.chen@mediatek.com>
Date: Wed, 12 Mar 2025 12:14:03 +0100
Subject: [PATCH 2333/2753] wifi: mt76: mt7996: rework set/get_tsf callabcks to
 support MLO

This is a preliminary patch in order to enable MLO for MT7996 driver.

Co-developed-by: Bo Jiao <Bo.Jiao@mediatek.com>
Signed-off-by: Bo Jiao <Bo.Jiao@mediatek.com>
Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com>
Signed-off-by: Shayne Chen <shayne.chen@mediatek.com>
Co-developed-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-19-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/mac.c   |  2 +-
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 48 ++++++++++++-------
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  2 +-
 3 files changed, 33 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index 6870ee189dca6..a52b4e71b267e 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2732,7 +2732,7 @@ void mt7996_mac_add_twt_setup(struct ieee80211_hw *hw,
 
 		flow->sched = true;
 		flow->start_tsf = mt7996_mac_twt_sched_list_add(dev, flow);
-		curr_tsf = __mt7996_get_tsf(hw, msta->vif);
+		curr_tsf = __mt7996_get_tsf(hw, &msta->vif->deflink);
 		div_u64_rem(curr_tsf - flow->start_tsf, interval, &rem);
 		flow_tsf = curr_tsf + interval - rem;
 		twt_agrt->twt = cpu_to_le64(flow_tsf);
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 40efba5bcaac3..8bcb4b8e3ef58 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1336,10 +1336,10 @@ mt7996_get_stats(struct ieee80211_hw *hw,
 	return 0;
 }
 
-u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif *mvif)
+u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif_link *link)
 {
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink);
+	struct mt7996_phy *phy = link->phy;
 	union {
 		u64 t64;
 		u32 t32[2];
@@ -1351,8 +1351,8 @@ u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif *mvif)
 
 	lockdep_assert_held(&dev->mt76.mutex);
 
-	n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
-					       : mvif->deflink.mt76.omac_idx;
+	n = link->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
+					       : link->mt76.omac_idx;
 	/* TSF software read */
 	mt76_rmw(dev, MT_LPON_TCR(phy->mt76->band_idx, n), MT_LPON_TCR_SW_MODE,
 		 MT_LPON_TCR_SW_READ);
@@ -1370,7 +1370,7 @@ mt7996_get_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif)
 	u64 ret;
 
 	mutex_lock(&dev->mt76.mutex);
-	ret = __mt7996_get_tsf(hw, mvif);
+	ret = __mt7996_get_tsf(hw, &mvif->deflink);
 	mutex_unlock(&dev->mt76.mutex);
 
 	return ret;
@@ -1382,26 +1382,33 @@ mt7996_set_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink);
+	struct mt7996_vif_link *link;
+	struct mt7996_phy *phy;
 	union {
 		u64 t64;
 		u32 t32[2];
 	} tsf = { .t64 = timestamp, };
 	u16 n;
 
-	if (!phy)
-		return;
-
 	mutex_lock(&dev->mt76.mutex);
 
-	n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
-					       : mvif->deflink.mt76.omac_idx;
+	link = mt7996_vif_link(dev, vif, mvif->mt76.deflink_id);
+	if (!link)
+		goto unlock;
+
+	n = link->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
+					       : link->mt76.omac_idx;
+	phy = link->phy;
+	if (!phy)
+		goto unlock;
+
 	mt76_wr(dev, MT_LPON_UTTR0(phy->mt76->band_idx), tsf.t32[0]);
 	mt76_wr(dev, MT_LPON_UTTR1(phy->mt76->band_idx), tsf.t32[1]);
 	/* TSF software overwrite */
 	mt76_rmw(dev, MT_LPON_TCR(phy->mt76->band_idx, n), MT_LPON_TCR_SW_MODE,
 		 MT_LPON_TCR_SW_WRITE);
 
+unlock:
 	mutex_unlock(&dev->mt76.mutex);
 }
 
@@ -1411,26 +1418,33 @@ mt7996_offset_tsf(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 {
 	struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
-	struct mt7996_phy *phy = mt7996_vif_link_phy(&mvif->deflink);
+	struct mt7996_vif_link *link;
+	struct mt7996_phy *phy;
 	union {
 		u64 t64;
 		u32 t32[2];
 	} tsf = { .t64 = timestamp, };
 	u16 n;
 
-	if (!phy)
-		return;
-
 	mutex_lock(&dev->mt76.mutex);
 
-	n = mvif->deflink.mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
-					       : mvif->deflink.mt76.omac_idx;
+	link = mt7996_vif_link(dev, vif, mvif->mt76.deflink_id);
+	if (!link)
+		goto unlock;
+
+	phy = link->phy;
+	if (!phy)
+		goto unlock;
+
+	n = link->mt76.omac_idx > HW_BSSID_MAX ? HW_BSSID_0
+					       : link->mt76.omac_idx;
 	mt76_wr(dev, MT_LPON_UTTR0(phy->mt76->band_idx), tsf.t32[0]);
 	mt76_wr(dev, MT_LPON_UTTR1(phy->mt76->band_idx), tsf.t32[1]);
 	/* TSF software adjust*/
 	mt76_rmw(dev, MT_LPON_TCR(phy->mt76->band_idx, n), MT_LPON_TCR_SW_MODE,
 		 MT_LPON_TCR_SW_ADJUST);
 
+unlock:
 	mutex_unlock(&dev->mt76.mutex);
 }
 
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 124a48e2706e4..815a3c68b8723 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -535,7 +535,7 @@ struct mt7996_dev *mt7996_mmio_probe(struct device *pdev,
 				     void __iomem *mem_base, u32 device_id);
 void mt7996_wfsys_reset(struct mt7996_dev *dev);
 irqreturn_t mt7996_irq_handler(int irq, void *dev_instance);
-u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif *mvif);
+u64 __mt7996_get_tsf(struct ieee80211_hw *hw, struct mt7996_vif_link *link);
 int mt7996_register_device(struct mt7996_dev *dev);
 void mt7996_unregister_device(struct mt7996_dev *dev);
 int mt7996_vif_link_add(struct mt76_phy *mphy, struct ieee80211_vif *vif,

From ef3f5941e560320a430c00d359c12a206a36f2c1 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:14:04 +0100
Subject: [PATCH 2334/2753] wifi: mt76: mt7996: rework mt7996_ampdu_action to
 support MLO

Active/de-active TX/RX BA sessssion for each active links running
mt7996_ampdu_action routine.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-20-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 89 ++++++++++++-------
 .../net/wireless/mediatek/mt76/mt7996/mcu.c   | 16 ++--
 .../wireless/mediatek/mt76/mt7996/mt7996.h    |  5 +-
 3 files changed, 64 insertions(+), 46 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index 8bcb4b8e3ef58..adeb267b28018 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1259,12 +1259,13 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 	enum ieee80211_ampdu_mlme_action action = params->action;
 	struct mt7996_dev *dev = mt7996_hw_dev(hw);
 	struct ieee80211_sta *sta = params->sta;
-	struct ieee80211_txq *txq = sta->txq[params->tid];
 	struct mt7996_sta *msta = (struct mt7996_sta *)sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
+	struct ieee80211_txq *txq = sta->txq[params->tid];
+	struct ieee80211_link_sta *link_sta;
 	u16 tid = params->tid;
 	u16 ssn = params->ssn;
 	struct mt76_txq *mtxq;
+	unsigned int link_id;
 	int ret = 0;
 
 	if (!txq)
@@ -1274,38 +1275,60 @@ mt7996_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
 
 	mutex_lock(&dev->mt76.mutex);
 
-	switch (action) {
-	case IEEE80211_AMPDU_RX_START:
-		mt76_rx_aggr_start(&dev->mt76, &msta_link->wcid, tid, ssn,
-				   params->buf_size);
-		ret = mt7996_mcu_add_rx_ba(dev, params, true);
-		break;
-	case IEEE80211_AMPDU_RX_STOP:
-		mt76_rx_aggr_stop(&dev->mt76, &msta_link->wcid, tid);
-		ret = mt7996_mcu_add_rx_ba(dev, params, false);
-		break;
-	case IEEE80211_AMPDU_TX_OPERATIONAL:
-		mtxq->aggr = true;
-		mtxq->send_bar = false;
-		ret = mt7996_mcu_add_tx_ba(dev, params, true);
-		break;
-	case IEEE80211_AMPDU_TX_STOP_FLUSH:
-	case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
-		mtxq->aggr = false;
-		clear_bit(tid, &msta_link->wcid.ampdu_state);
-		ret = mt7996_mcu_add_tx_ba(dev, params, false);
-		break;
-	case IEEE80211_AMPDU_TX_START:
-		set_bit(tid, &msta_link->wcid.ampdu_state);
-		ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
-		break;
-	case IEEE80211_AMPDU_TX_STOP_CONT:
-		mtxq->aggr = false;
-		clear_bit(tid, &msta_link->wcid.ampdu_state);
-		ret = mt7996_mcu_add_tx_ba(dev, params, false);
-		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
-		break;
+	for_each_sta_active_link(vif, sta, link_sta, link_id) {
+		struct mt7996_sta_link *msta_link;
+		struct mt7996_vif_link *link;
+
+		msta_link = mt76_dereference(msta->link[link_id], &dev->mt76);
+		if (!msta_link)
+			continue;
+
+		link = mt7996_vif_link(dev, vif, link_id);
+		if (!link)
+			continue;
+
+		switch (action) {
+		case IEEE80211_AMPDU_RX_START:
+			mt76_rx_aggr_start(&dev->mt76, &msta_link->wcid, tid,
+					   ssn, params->buf_size);
+			ret = mt7996_mcu_add_rx_ba(dev, params, link, true);
+			break;
+		case IEEE80211_AMPDU_RX_STOP:
+			mt76_rx_aggr_stop(&dev->mt76, &msta_link->wcid, tid);
+			ret = mt7996_mcu_add_rx_ba(dev, params, link, false);
+			break;
+		case IEEE80211_AMPDU_TX_OPERATIONAL:
+			mtxq->aggr = true;
+			mtxq->send_bar = false;
+			ret = mt7996_mcu_add_tx_ba(dev, params, link,
+						   msta_link, true);
+			break;
+		case IEEE80211_AMPDU_TX_STOP_FLUSH:
+		case IEEE80211_AMPDU_TX_STOP_FLUSH_CONT:
+			mtxq->aggr = false;
+			clear_bit(tid, &msta_link->wcid.ampdu_state);
+			ret = mt7996_mcu_add_tx_ba(dev, params, link,
+						   msta_link, false);
+			break;
+		case IEEE80211_AMPDU_TX_START:
+			set_bit(tid, &msta_link->wcid.ampdu_state);
+			ret = IEEE80211_AMPDU_TX_START_IMMEDIATE;
+			break;
+		case IEEE80211_AMPDU_TX_STOP_CONT:
+			mtxq->aggr = false;
+			clear_bit(tid, &msta_link->wcid.ampdu_state);
+			ret = mt7996_mcu_add_tx_ba(dev, params, link,
+						   msta_link, false);
+			break;
+		}
+
+		if (ret)
+			break;
 	}
+
+	if (action == IEEE80211_AMPDU_TX_STOP_CONT)
+		ieee80211_stop_tx_ba_cb_irqsafe(vif, sta->addr, tid);
+
 	mutex_unlock(&dev->mt76.mutex);
 
 	return ret;
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
index 4bd0c16500ab6..ddd555942c738 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
@@ -1160,26 +1160,20 @@ mt7996_mcu_sta_ba(struct mt7996_dev *dev, struct mt76_vif_link *mvif,
 /** starec & wtbl **/
 int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
-			 bool enable)
+			 struct mt7996_vif_link *link,
+			 struct mt7996_sta_link *msta_link, bool enable)
 {
-	struct mt7996_sta *msta = (struct mt7996_sta *)params->sta->drv_priv;
-	struct mt7996_sta_link *msta_link = &msta->deflink;
-	struct mt7996_vif *mvif = msta->vif;
-
 	if (enable && !params->amsdu)
 		msta_link->wcid.amsdu = false;
 
-	return mt7996_mcu_sta_ba(dev, &mvif->deflink.mt76, params, enable, true);
+	return mt7996_mcu_sta_ba(dev, &link->mt76, params, enable, true);
 }
 
 int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
-			 bool enable)
+			 struct mt7996_vif_link *link, bool enable)
 {
-	struct mt7996_sta *msta = (struct mt7996_sta *)params->sta->drv_priv;
-	struct mt7996_vif *mvif = msta->vif;
-
-	return mt7996_mcu_sta_ba(dev, &mvif->deflink.mt76, params, enable, false);
+	return mt7996_mcu_sta_ba(dev, &link->mt76, params, enable, false);
 }
 
 static void
diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
index 815a3c68b8723..43e646ed6094c 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mt7996.h
@@ -584,10 +584,11 @@ int mt7996_mcu_teardown_mld_sta(struct mt7996_dev *dev,
 				struct mt7996_sta_link *msta_link);
 int mt7996_mcu_add_tx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
-			 bool add);
+			 struct mt7996_vif_link *link,
+			 struct mt7996_sta_link *msta_link, bool enable);
 int mt7996_mcu_add_rx_ba(struct mt7996_dev *dev,
 			 struct ieee80211_ampdu_params *params,
-			 bool add);
+			 struct mt7996_vif_link *link, bool enable);
 int mt7996_mcu_update_bss_color(struct mt7996_dev *dev,
 				struct mt76_vif_link *mlink,
 				struct cfg80211_he_bss_color *he_bss_color);

From 3ce8acb86b6614b9f7af794f119f9627efe6b302 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Wed, 12 Mar 2025 12:14:05 +0100
Subject: [PATCH 2335/2753] wifi: mt76: mt7996: Update mt7996_tx to MLO support

Rework mt7996_tx routine in order to support multi-link
setup.

Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Link: https://patch.msgid.link/20250312-b4-mt7996-mlo-p2-v1-21-015b3d6fd928@kernel.org
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 .../net/wireless/mediatek/mt76/mt7996/main.c  | 31 ++++++++++++-------
 1 file changed, 20 insertions(+), 11 deletions(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
index adeb267b28018..91c64e3a0860f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
@@ -1200,12 +1200,18 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
 	struct ieee80211_vif *vif = info->control.vif;
 	struct mt76_wcid *wcid = &dev->mt76.global_wcid;
+	u8 link_id = u32_get_bits(info->control.flags,
+				  IEEE80211_TX_CTRL_MLO_LINK);
+
+	rcu_read_lock();
 
 	if (vif) {
-		struct mt7996_vif *mvif;
+		struct mt7996_vif *mvif = (void *)vif->drv_priv;
+		struct mt76_vif_link *mlink;
 
-		mvif = (struct mt7996_vif *)vif->drv_priv;
-		wcid = &mvif->deflink.msta_link.wcid;
+		mlink = rcu_dereference(mvif->mt76.link[link_id]);
+		if (mlink && mlink->wcid)
+			wcid = mlink->wcid;
 
 		if (mvif->mt76.roc_phy &&
 		    (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN)) {
@@ -1217,19 +1223,22 @@ static void mt7996_tx(struct ieee80211_hw *hw,
 		}
 	}
 
-	if (control->sta) {
-		struct mt7996_sta_link *msta_link;
-
-		msta_link = (struct mt7996_sta_link *)control->sta->drv_priv;
-		wcid = &msta_link->wcid;
-	}
-
 	if (!mphy) {
 		ieee80211_free_txskb(hw, skb);
-		return;
+		goto unlock;
 	}
 
+	if (control->sta) {
+		struct mt7996_sta *msta = (void *)control->sta->drv_priv;
+		struct mt7996_sta_link *msta_link;
+
+		msta_link = rcu_dereference(msta->link[link_id]);
+		if (msta_link)
+			wcid = &msta_link->wcid;
+	}
 	mt76_tx(mphy, control->sta, wcid, skb);
+unlock:
+	rcu_read_unlock();
 }
 
 static int mt7996_set_rts_threshold(struct ieee80211_hw *hw, u32 val)

From 06e70003d88218675c566584dd76867fcb39706d Mon Sep 17 00:00:00 2001
From: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Date: Thu, 13 Mar 2025 13:40:44 +0800
Subject: [PATCH 2336/2753] wifi: mt76: mt792x: re-register CHANCTX_STA_CSA
 only for the mt7921 series

CSA is currently not supported on mt7925, so CSA is only registered for
the mt7921 series

Cc: stable@vger.kernel.org
Fixes: 8aa2f59260eb ("wifi: mt76: mt7921: introduce CSA support")
Signed-off-by: Ming Yen Hsieh <mingyen.hsieh@mediatek.com>
Link: https://patch.msgid.link/20250313054044.2638837-1-mingyen.hsieh@mediatek.com
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt792x_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt792x_core.c b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
index 8799627f62926..0f7806f6338d0 100644
--- a/drivers/net/wireless/mediatek/mt76/mt792x_core.c
+++ b/drivers/net/wireless/mediatek/mt76/mt792x_core.c
@@ -665,7 +665,8 @@ int mt792x_init_wiphy(struct ieee80211_hw *hw)
 	ieee80211_hw_set(hw, SUPPORTS_DYNAMIC_PS);
 	ieee80211_hw_set(hw, SUPPORTS_VHT_EXT_NSS_BW);
 	ieee80211_hw_set(hw, CONNECTION_MONITOR);
-	ieee80211_hw_set(hw, CHANCTX_STA_CSA);
+	if (is_mt7921(&dev->mt76))
+		ieee80211_hw_set(hw, CHANCTX_STA_CSA);
 
 	if (dev->pm.enable)
 		ieee80211_hw_set(hw, CONNECTION_MONITOR);

From 06cccc2ebbe6c8a20f714f3a0ff3ff489d3004bb Mon Sep 17 00:00:00 2001
From: Icenowy Zheng <uwu@icenowy.me>
Date: Mon, 17 Mar 2025 18:22:35 +0800
Subject: [PATCH 2337/2753] wifi: mt76: mt76x2u: add TP-Link TL-WDN6200 ID to
 device table

The TP-Link TL-WDN6200 "Driverless" version cards use a MT7612U chipset.

Add the USB ID to mt76x2u driver.

Signed-off-by: Icenowy Zheng <uwu@icenowy.me>
Link: https://patch.msgid.link/20250317102235.1421726-1-uwu@icenowy.me
Signed-off-by: Felix Fietkau <nbd@nbd.name>
---
 drivers/net/wireless/mediatek/mt76/mt76x2/usb.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index 3747f9ed31e6f..84ef80ab4afbf 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -22,6 +22,7 @@ static const struct usb_device_id mt76x2u_device_table[] = {
 	{ USB_DEVICE(0x0846, 0x9053) },	/* Netgear A6210 */
 	{ USB_DEVICE(0x045e, 0x02e6) },	/* XBox One Wireless Adapter */
 	{ USB_DEVICE(0x045e, 0x02fe) },	/* XBox One Wireless Adapter */
+	{ USB_DEVICE(0x2357, 0x0137) },	/* TP-Link TL-WDN6200 */
 	{ },
 };
 

From 0c1f1eb65425451b8bcde52c055803cddecd1151 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:25 +0000
Subject: [PATCH 2338/2753] net: stmmac: allow platforms to use PHY tx clock
 stop capability

Allow platform glue to instruct stmmac to make use of the PHY transmit
clock stop capability when deciding whether to allow the transmit clock
from the DWMAC core to be stopped.

Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsITp-005vG9-Px@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac.h     |  1 +
 .../net/ethernet/stmicro/stmmac/stmmac_main.c    | 16 ++++++++++++----
 include/linux/stmmac.h                           |  3 ++-
 3 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
index d87275c1cf23b..bddfa0f4aa217 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h
@@ -306,6 +306,7 @@ struct stmmac_priv {
 	struct timer_list eee_ctrl_timer;
 	int lpi_irq;
 	u32 tx_lpi_timer;
+	bool tx_lpi_clk_stop;
 	bool eee_enabled;
 	bool eee_active;
 	bool eee_sw_timer_en;
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index 839ecebf5f5f3..a6a533d8a45be 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -457,8 +457,7 @@ static void stmmac_try_to_start_sw_lpi(struct stmmac_priv *priv)
 	/* Check and enter in LPI mode */
 	if (!priv->tx_path_in_lpi_mode)
 		stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_FORCED,
-			priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING,
-			0);
+				    priv->tx_lpi_clk_stop, 0);
 }
 
 /**
@@ -1104,13 +1103,18 @@ static int stmmac_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
 
 	priv->eee_enabled = true;
 
+	/* Update the transmit clock stop according to PHY capability if
+	 * the platform allows
+	 */
+	if (priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP)
+		priv->tx_lpi_clk_stop = tx_clk_stop;
+
 	stmmac_set_eee_timer(priv, priv->hw, STMMAC_DEFAULT_LIT_LS,
 			     STMMAC_DEFAULT_TWT_LS);
 
 	/* Try to cnfigure the hardware timer. */
 	ret = stmmac_set_lpi_mode(priv, priv->hw, STMMAC_LPI_TIMER,
-				  priv->plat->flags & STMMAC_FLAG_EN_TX_LPI_CLOCKGATING,
-				  priv->tx_lpi_timer);
+				  priv->tx_lpi_clk_stop, priv->tx_lpi_timer);
 
 	if (ret) {
 		/* Hardware timer mode not supported, or value out of range.
@@ -1269,6 +1273,10 @@ static int stmmac_phy_setup(struct stmmac_priv *priv)
 	if (!(priv->plat->flags & STMMAC_FLAG_RX_CLK_RUNS_IN_LPI))
 		priv->phylink_config.eee_rx_clk_stop_enable = true;
 
+	/* Set the default transmit clock stop bit based on the platform glue */
+	priv->tx_lpi_clk_stop = priv->plat->flags &
+				STMMAC_FLAG_EN_TX_LPI_CLOCKGATING;
+
 	mdio_bus_data = priv->plat->mdio_bus_data;
 	if (mdio_bus_data)
 		priv->phylink_config.default_an_inband =
diff --git a/include/linux/stmmac.h b/include/linux/stmmac.h
index b6f03ab125957..c4ec8bb8144e7 100644
--- a/include/linux/stmmac.h
+++ b/include/linux/stmmac.h
@@ -183,7 +183,8 @@ struct dwmac4_addrs {
 #define STMMAC_FLAG_INT_SNAPSHOT_EN		BIT(9)
 #define STMMAC_FLAG_RX_CLK_RUNS_IN_LPI		BIT(10)
 #define STMMAC_FLAG_EN_TX_LPI_CLOCKGATING	BIT(11)
-#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY	BIT(12)
+#define STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP	BIT(12)
+#define STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY	BIT(13)
 
 struct plat_stmmacenet_data {
 	int bus_id;

From 5f250bd72a01fe6bd89b71393a09c0ab1d408645 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:30 +0000
Subject: [PATCH 2339/2753] net: stmmac: starfive: use PHY capability for TX
 clock stop

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

Add the flag to allow the stmmac core to use the PHY capability.

Cc: Samin Guo <samin.guo@starfivetech.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsITu-005vGF-TM@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
index 5e31cb3bb4b83..2013d7477eb76 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c
@@ -124,6 +124,7 @@ static int starfive_dwmac_probe(struct platform_device *pdev)
 		plat_dat->set_clk_tx_rate = stmmac_set_clk_tx_rate;
 
 	dwmac->dev = &pdev->dev;
+	plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 	plat_dat->bsp_priv = dwmac;
 	plat_dat->dma_cfg->dche = true;
 

From a5bc19e2abeb570ff60f973dec84807ec8d3d695 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:36 +0000
Subject: [PATCH 2340/2753] net: stmmac: stm32: use PHY capability for TX clock
 stop

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

Add the flag to allow the stmmac core to use the PHY capability.

Cc: Christophe Roullier <christophe.roullier@st.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIU0-005vGL-17@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
index 1fcb74e9e3ffa..c3d321192581f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-stm32.c
@@ -538,6 +538,7 @@ static int stm32_dwmac_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	plat_dat->flags |= STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP;
 	plat_dat->bsp_priv = dwmac;
 
 	ret = stm32_dwmac_init(plat_dat, false);

From 637af286f9fcacd351f02dd9eb581b3c939639e9 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:41 +0000
Subject: [PATCH 2341/2753] riscv: dts: starfive: remove
 "snps,en-tx-lpi-clockgating" property

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

As commit "net: stmmac: starfive: use PHY capability for TX clock stop"
adds the flag to use the PHY capability, remove the DT property that is
now unecessary.

Cc: Samin Guo <samin.guo@starfivetech.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIU5-005vGR-4c@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 arch/riscv/boot/dts/starfive/jh7110.dtsi | 2 --
 1 file changed, 2 deletions(-)

diff --git a/arch/riscv/boot/dts/starfive/jh7110.dtsi b/arch/riscv/boot/dts/starfive/jh7110.dtsi
index 0d8339357bad3..a7aed4a21b655 100644
--- a/arch/riscv/boot/dts/starfive/jh7110.dtsi
+++ b/arch/riscv/boot/dts/starfive/jh7110.dtsi
@@ -1022,7 +1022,6 @@
 			snps,force_thresh_dma_mode;
 			snps,axi-config = <&stmmac_axi_setup>;
 			snps,tso;
-			snps,en-tx-lpi-clockgating;
 			snps,txpbl = <16>;
 			snps,rxpbl = <16>;
 			starfive,syscon = <&aon_syscon 0xc 0x12>;
@@ -1053,7 +1052,6 @@
 			snps,force_thresh_dma_mode;
 			snps,axi-config = <&stmmac_axi_setup>;
 			snps,tso;
-			snps,en-tx-lpi-clockgating;
 			snps,txpbl = <16>;
 			snps,rxpbl = <16>;
 			starfive,syscon = <&sys_syscon 0x90 0x2>;

From 50a84bbc7ec10a48348afbf68682fd14dce5321b Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:46 +0000
Subject: [PATCH 2342/2753] ARM: dts: stm32: remove
 "snps,en-tx-lpi-clockgating" property

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

As commit "net: stmmac: stm32: use PHY capability for TX clock stop"
adds the flag to use the PHY capability, remove the DT property that is
now unecessary.

Cc: Samin Guo <samin.guo@starfivetech.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIUA-005vGX-8A@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 arch/arm/boot/dts/st/stm32mp151.dtsi | 1 -
 1 file changed, 1 deletion(-)

diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi
index b9a87fbe971d6..0daa8ffe2ff5d 100644
--- a/arch/arm/boot/dts/st/stm32mp151.dtsi
+++ b/arch/arm/boot/dts/st/stm32mp151.dtsi
@@ -1781,7 +1781,6 @@
 				st,syscon = <&syscfg 0x4>;
 				snps,mixed-burst;
 				snps,pbl = <2>;
-				snps,en-tx-lpi-clockgating;
 				snps,axi-config = <&stmmac_axi_config_0>;
 				snps,tso;
 				access-controllers = <&etzpc 94>;

From a62b7901d3a917964098c9b9215ff580bbaa85f5 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:51 +0000
Subject: [PATCH 2343/2753] dt-bindings: deprecate "snps,en-tx-lpi-clockgating"
 property

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

Therefore, snps,en-tx-lpi-clockgating is technically incorrect, so this
commit deprecates the property in the binding.

Acked-by: Rob Herring (Arm) <robh@kernel.org>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/E1tsIUF-005vGd-C5@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/devicetree/bindings/net/snps,dwmac.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/net/snps,dwmac.yaml b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
index 3f0aa46d798ef..78b3030dc56d2 100644
--- a/Documentation/devicetree/bindings/net/snps,dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/snps,dwmac.yaml
@@ -494,6 +494,7 @@ properties:
 
   snps,en-tx-lpi-clockgating:
     $ref: /schemas/types.yaml#/definitions/flag
+    deprecated: true
     description:
       Enable gating of the MAC TX clock during TX low-power mode
 

From cf0a96de397e06e6cf3e0f4c10d6cb60e6166d2d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 09:34:56 +0000
Subject: [PATCH 2344/2753] net: stmmac: deprecate "snps,en-tx-lpi-clockgating"
 property

Whether the MII transmit clock can be stopped is primarily a property
of the PHY (there is a capability bit that should be checked first.)
Whether the MAC is capable of stopping the transmit clock is a separate
issue, but this is already handled by the core DesignWare MAC code.

Therefore, snps,en-tx-lpi-clockgating is technically incorrect, and
this commit adds a warning should a DT be encountered with the property
present.

However, we keep backwards compatibility.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com>
Link: https://patch.msgid.link/E1tsIUK-005vGk-H7@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index 8dc3bd6946c67..c73eff6a56b87 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -497,8 +497,11 @@ stmmac_probe_config_dt(struct platform_device *pdev, u8 *mac)
 	plat->force_sf_dma_mode =
 		of_property_read_bool(np, "snps,force_sf_dma_mode");
 
-	if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating"))
+	if (of_property_read_bool(np, "snps,en-tx-lpi-clockgating")) {
+		dev_warn(&pdev->dev,
+			 "OF property snps,en-tx-lpi-clockgating is deprecated, please convert driver to use STMMAC_FLAG_EN_TX_LPI_CLK_PHY_CAP\n");
 		plat->flags |= STMMAC_FLAG_EN_TX_LPI_CLOCKGATING;
+	}
 
 	/* Set the maxmtu to a default of JUMBO_LEN in case the
 	 * parameter is not present in the device tree.

From eae1389ab2f52bae4011514bbd0173b5b56affff Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 12 Mar 2025 13:49:52 +0200
Subject: [PATCH 2345/2753] net/mlx5: HWS, remove unused code for alias flow
 tables

Alias flow tables are not in use by HWS - remove the unused code.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741780194-137519-2-git-send-email-tariqt@nvidia.com
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c | 6 ------
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h | 3 ---
 2 files changed, 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
index 487e75476b0ab..e8f98c109b999 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.c
@@ -130,12 +130,6 @@ int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 	return mlx5_cmd_exec_in(mdev, destroy_flow_table, in);
 }
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id)
-{
-	hws_cmd_general_obj_destroy(mdev, MLX5_OBJ_TYPE_FT_ALIAS, table_id);
-}
-
 static int hws_cmd_flow_group_create(struct mlx5_core_dev *mdev,
 				     struct mlx5hws_cmd_fg_attr *fg_attr,
 				     u32 *group_id)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
index 610c63d81ad95..51d9e0291ac16 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/cmd.h
@@ -258,9 +258,6 @@ int mlx5hws_cmd_flow_table_query(struct mlx5_core_dev *mdev,
 int mlx5hws_cmd_flow_table_destroy(struct mlx5_core_dev *mdev,
 				   u8 fw_ft_type, u32 table_id);
 
-void mlx5hws_cmd_alias_flow_table_destroy(struct mlx5_core_dev *mdev,
-					  u32 table_id);
-
 int mlx5hws_cmd_rtc_create(struct mlx5_core_dev *mdev,
 			   struct mlx5hws_cmd_rtc_create_attr *rtc_attr,
 			   u32 *rtc_id);

From 1a403ad383ab0b4718b8502fcb6fb4900501c453 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 12 Mar 2025 13:49:53 +0200
Subject: [PATCH 2346/2753] net/mlx5: HWS, use list_move() instead of del/add

Wherever applicable, use list_move function instead of list_del + list_add.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741780194-137519-3-git-send-email-tariqt@nvidia.com
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c | 3 +--
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c | 3 +--
 2 files changed, 2 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index 10ece7df1cfaf..c4851d5584b75 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -1985,8 +1985,7 @@ int mlx5hws_definer_get_obj(struct mlx5hws_context *ctx,
 			continue;
 
 		/* Reuse definer and set LRU (move to be first in the list) */
-		list_del_init(&cached_definer->list_node);
-		list_add(&cached_definer->list_node, &cache->list_head);
+		list_move(&cached_definer->list_node, &cache->list_head);
 		cached_definer->refcount++;
 		return cached_definer->definer.obj_id;
 	}
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
index d9dc4f2d0dc68..f51ed24526b91 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/pat_arg.c
@@ -153,8 +153,7 @@ mlx5hws_pat_get_existing_cached_pattern(struct mlx5hws_pattern_cache *cache,
 	cached_pattern = mlx5hws_pat_find_cached_pattern(cache, num_of_actions, actions);
 	if (cached_pattern) {
 		/* LRU: move it to be first in the list */
-		list_del_init(&cached_pattern->ptrn_list_node);
-		list_add(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
+		list_move(&cached_pattern->ptrn_list_node, &cache->ptrn_list);
 		cached_pattern->refcount++;
 	}
 

From 8389f2de903cf02525017f4d5a883f6dc6b59df8 Mon Sep 17 00:00:00 2001
From: Yevgeny Kliteynik <kliteyn@nvidia.com>
Date: Wed, 12 Mar 2025 13:49:54 +0200
Subject: [PATCH 2347/2753] net/mlx5: HWS, log the unsupported mask in definer

If a user requested to match on an unsupported combination of fields,
print the unsupported combination in the error message.

Signed-off-by: Yevgeny Kliteynik <kliteyn@nvidia.com>
Reviewed-by: Vlad Dogaru <vdogaru@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1741780194-137519-4-git-send-email-tariqt@nvidia.com
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index c4851d5584b75..c8cc0c8115f53 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -500,7 +500,8 @@ hws_definer_check_match_flags(struct mlx5hws_definer_conv_data *cd)
 	return 0;
 
 err_conflict:
-	mlx5hws_err(cd->ctx, "Invalid definer fields combination\n");
+	mlx5hws_err(cd->ctx, "Invalid definer fields combination: match_flags = 0x%08x\n",
+		    cd->match_flags);
 	return -EINVAL;
 }
 

From acf10a8c0b3a36d5ff35f91585e9755ea0b62ac3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 12 Mar 2025 14:10:40 +0100
Subject: [PATCH 2348/2753] selftests: drv-net: use defer in the ping test

Make sure the test cleans up after itself. The XDP off statements
at the end of the test may not be reached.

Fixes: 75cc19c8ff89 ("selftests: drv-net: add xdp cases for ping.py")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312131040.660386-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/drivers/net/ping.py | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/ping.py b/tools/testing/selftests/drivers/net/ping.py
index 93f4b411b378f..fc69bfcc37c46 100755
--- a/tools/testing/selftests/drivers/net/ping.py
+++ b/tools/testing/selftests/drivers/net/ping.py
@@ -7,7 +7,7 @@
 from lib.py import ksft_eq, KsftSkipEx, KsftFailEx
 from lib.py import EthtoolFamily, NetDrvEpEnv
 from lib.py import bkg, cmd, wait_port_listen, rand_port
-from lib.py import ethtool, ip
+from lib.py import defer, ethtool, ip
 
 remote_ifname=""
 no_sleep=False
@@ -60,6 +60,7 @@ def _set_xdp_generic_sb_on(cfg) -> None:
     prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
     cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
     cmd(f"ip link set dev {cfg.ifname} mtu 1500 xdpgeneric obj {prog} sec xdp", shell=True)
+    defer(cmd, f"ip link set dev {cfg.ifname} xdpgeneric off")
 
     if no_sleep != True:
         time.sleep(10)
@@ -68,7 +69,9 @@ def _set_xdp_generic_mb_on(cfg) -> None:
     test_dir = os.path.dirname(os.path.realpath(__file__))
     prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
     cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
     ip("link set dev %s mtu 9000 xdpgeneric obj %s sec xdp.frags" % (cfg.ifname, prog))
+    defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdpgeneric off")
 
     if no_sleep != True:
         time.sleep(10)
@@ -78,6 +81,7 @@ def _set_xdp_native_sb_on(cfg) -> None:
     prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
     cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
     cmd(f"ip -j link set dev {cfg.ifname} mtu 1500 xdp obj {prog} sec xdp", shell=True)
+    defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
     xdp_info = ip("-d link show %s" % (cfg.ifname), json=True)[0]
     if xdp_info['xdp']['mode'] != 1:
         """
@@ -94,10 +98,11 @@ def _set_xdp_native_mb_on(cfg) -> None:
     test_dir = os.path.dirname(os.path.realpath(__file__))
     prog = test_dir + "/../../net/lib/xdp_dummy.bpf.o"
     cmd(f"ip link set dev {remote_ifname} mtu 9000", shell=True, host=cfg.remote)
+    defer(ip, f"link set dev {remote_ifname} mtu 1500", host=cfg.remote)
     try:
         cmd(f"ip link set dev {cfg.ifname} mtu 9000 xdp obj {prog} sec xdp.frags", shell=True)
+        defer(ip, f"link set dev {cfg.ifname} mtu 1500 xdp off")
     except Exception as e:
-        cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
         raise KsftSkipEx('device does not support native-multi-buffer XDP')
 
     if no_sleep != True:
@@ -111,6 +116,7 @@ def _set_xdp_offload_on(cfg) -> None:
         cmd(f"ip link set dev {cfg.ifname} xdpoffload obj {prog} sec xdp", shell=True)
     except Exception as e:
         raise KsftSkipEx('device does not support offloaded XDP')
+    defer(ip, f"link set dev {cfg.ifname} xdpoffload off")
     cmd(f"ip link set dev {remote_ifname} mtu 1500", shell=True, host=cfg.remote)
 
     if no_sleep != True:
@@ -157,7 +163,6 @@ def test_xdp_generic_sb(cfg, netnl) -> None:
     _test_v4(cfg)
     _test_v6(cfg)
     _test_tcp(cfg)
-    ip("link set dev %s xdpgeneric off" % cfg.ifname)
 
 def test_xdp_generic_mb(cfg, netnl) -> None:
     _set_xdp_generic_mb_on(cfg)
@@ -169,7 +174,6 @@ def test_xdp_generic_mb(cfg, netnl) -> None:
     _test_v4(cfg)
     _test_v6(cfg)
     _test_tcp(cfg)
-    ip("link set dev %s xdpgeneric off" % cfg.ifname)
 
 def test_xdp_native_sb(cfg, netnl) -> None:
     _set_xdp_native_sb_on(cfg)
@@ -181,7 +185,6 @@ def test_xdp_native_sb(cfg, netnl) -> None:
     _test_v4(cfg)
     _test_v6(cfg)
     _test_tcp(cfg)
-    ip("link set dev %s xdp off" % cfg.ifname)
 
 def test_xdp_native_mb(cfg, netnl) -> None:
     _set_xdp_native_mb_on(cfg)
@@ -193,14 +196,12 @@ def test_xdp_native_mb(cfg, netnl) -> None:
     _test_v4(cfg)
     _test_v6(cfg)
     _test_tcp(cfg)
-    ip("link set dev %s xdp off" % cfg.ifname)
 
 def test_xdp_offload(cfg, netnl) -> None:
     _set_xdp_offload_on(cfg)
     _test_v4(cfg)
     _test_v6(cfg)
     _test_tcp(cfg)
-    ip("link set dev %s xdpoffload off" % cfg.ifname)
 
 def main() -> None:
     with NetDrvEpEnv(__file__) as cfg:
@@ -213,7 +214,6 @@ def main() -> None:
                   test_xdp_native_mb,
                   test_xdp_offload],
                  args=(cfg, EthtoolFamily()))
-        set_interface_init(cfg)
     ksft_exit()
 
 

From d3c58b656c97de195df3889c55ee9e91a8d65b6c Mon Sep 17 00:00:00 2001
From: Chen-Yu Tsai <wens@csie.org>
Date: Thu, 13 Mar 2025 00:34:26 +0800
Subject: [PATCH 2349/2753] net: stmmac: dwmac-rk: Provide FIFO sizes for DWMAC
 1000

The DWMAC 1000 DMA capabilities register does not provide actual
FIFO sizes, nor does the driver really care. If they are not
provided via some other means, the driver will work fine, only
disallowing changing the MTU setting.

Provide the FIFO sizes through the driver's platform data to enable
MTU changes. The FIFO sizes are confirmed to be the same across RK3288,
RK3328, RK3399 and PX30, based on their respective manuals. It is
likely that Rockchip synthesized their DWMAC 1000 with the same
parameters on all their chips that have it.

Signed-off-by: Chen-Yu Tsai <wens@csie.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250312163426.2178314-1-wens@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 2d4fee8b9ab14..c404017bc1da9 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -1737,8 +1737,11 @@ static int rk_gmac_probe(struct platform_device *pdev)
 	/* If the stmmac is not already selected as gmac4,
 	 * then make sure we fallback to gmac.
 	 */
-	if (!plat_dat->has_gmac4)
+	if (!plat_dat->has_gmac4) {
 		plat_dat->has_gmac = true;
+		plat_dat->rx_fifo_size = 4096;
+		plat_dat->tx_fifo_size = 2048;
+	}
 
 	plat_dat->set_clk_tx_rate = rk_set_clk_tx_rate;
 

From 756f88ff9c6ae3d059180813102610c39ea99c27 Mon Sep 17 00:00:00 2001
From: Jonathan Lennox <jonathan.lennox42@gmail.com>
Date: Wed, 12 Mar 2025 17:48:04 +0000
Subject: [PATCH 2350/2753] tc-tests: Update tc police action tests for tc
 buffer size rounding fixes.

Before tc's recent change to fix rounding errors, several tests which
specified a burst size of "1m" would translate back to being 1048574
bytes (2b less than 1Mb).  sprint_size prints this as "1024Kb".

With the tc fix, the burst size is instead correctly reported as
1048576 bytes (precisely 1Mb), which sprint_size prints as "1Mb".

This updates the expected output in the tests' matchPattern values
to accept either the old or the new output.

Signed-off-by: Jonathan Lennox <jonathan.lennox@8x8.com>
Link: https://patch.msgid.link/20250312174804.313107-1-jonathan.lennox@8x8.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/tc-testing/tc-tests/actions/police.json  | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
index dd8109768f8f9..5596f4df0e9f6 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/police.json
@@ -689,7 +689,7 @@
         "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m continue index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action police index 1",
-        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action continue",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action continue",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action police"
@@ -716,7 +716,7 @@
         "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m drop index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions ls action police",
-        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action drop",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action drop",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action police"
@@ -743,7 +743,7 @@
         "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m ok index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions ls action police",
-        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pass",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action pass",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action police"
@@ -770,7 +770,7 @@
         "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m reclassify index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action police index 1",
-        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action reclassify",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action reclassify",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action police"
@@ -797,7 +797,7 @@
         "cmdUnderTest": "$TC actions add action police rate 7mbit burst 1m pipe index 1",
         "expExitCode": "0",
         "verifyCmd": "$TC actions ls action police",
-        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst 1024Kb mtu 2Kb action pipe",
+        "matchPattern": "action order [0-9]*:  police 0x1 rate 7Mbit burst (1024Kb|1Mb) mtu 2Kb action pipe",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action police"

From 8033d2aef51722fe74068b52553625ed91ea256c Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 12 Mar 2025 12:05:12 -0700
Subject: [PATCH 2351/2753] Revert "net: replace dev_addr_sem with netdev
 instance lock"

This reverts commit df43d8bf10316a7c3b1e47e3cc0057a54df4a5b8.

Cc: Kohei Enju <enjuk@amazon.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Fixes: df43d8bf1031 ("net: replace dev_addr_sem with netdev instance lock")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250312190513.1252045-2-sdf@fomichev.me
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/tap.c         |  2 +-
 drivers/net/tun.c         |  2 +-
 include/linux/netdevice.h |  6 ++++-
 net/core/dev.c            | 52 +++++++++++++++++++--------------------
 net/core/dev.h            |  3 ++-
 net/core/dev_api.c        | 17 +++++++++++--
 net/core/dev_ioctl.c      |  2 +-
 net/core/net-sysfs.c      |  7 ++++--
 net/core/rtnetlink.c      |  6 +----
 9 files changed, 56 insertions(+), 41 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 4382f5e323b06..d4ece538f1b23 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1017,7 +1017,7 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 			rtnl_unlock();
 			return -ENOLINK;
 		}
-		ret = dev_set_mac_address(tap->dev, &sa, NULL);
+		ret = dev_set_mac_address_user(tap->dev, &sa, NULL);
 		tap_put_tap_dev(tap);
 		rtnl_unlock();
 		return ret;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 55b60cb68d00f..f75f912a0225f 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3193,7 +3193,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	case SIOCSIFHWADDR:
 		/* Set hw address */
-		ret = dev_set_mac_address(tun->dev, &ifr.ifr_hwaddr, NULL);
+		ret = dev_set_mac_address_user(tun->dev, &ifr.ifr_hwaddr, NULL);
 		break;
 
 	case TUNGETSNDBUF:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 67527243459b3..0db9fc0afe360 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2498,7 +2498,7 @@ struct net_device {
 	 *
 	 * Protects:
 	 *	@gro_flush_timeout, @napi_defer_hard_irqs, @napi_list,
-	 *	@net_shaper_hierarchy, @reg_state, @threaded, @dev_addr
+	 *	@net_shaper_hierarchy, @reg_state, @threaded
 	 *
 	 * Partially protects (writers must hold both @lock and rtnl_lock):
 	 *	@up
@@ -4196,6 +4196,10 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			  struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
+int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			       struct netlink_ext_ack *extack);
+int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int dev_get_port_parent_id(struct net_device *dev,
 			   struct netdev_phys_item_id *ppid, bool recurse);
diff --git a/net/core/dev.c b/net/core/dev.c
index 6fa6ed5b57987..977a9946d39c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1059,28 +1059,6 @@ struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex)
 	return __netdev_put_lock(dev);
 }
 
-/**
- * netdev_get_by_name_lock() - find a device by its name
- * @net: the applicable net namespace
- * @name: name of device
- *
- * Search for an interface by name. If a valid device
- * with @name is found it will be returned with netdev->lock held.
- * netdev_unlock() must be called to release it.
- *
- * Return: pointer to a device with lock held, NULL if not found.
- */
-struct net_device *netdev_get_by_name_lock(struct net *net, const char *name)
-{
-	struct net_device *dev;
-
-	dev = dev_get_by_name(net, name);
-	if (!dev)
-		return NULL;
-
-	return __netdev_put_lock(dev);
-}
-
 struct net_device *
 netdev_xa_find_lock(struct net *net, struct net_device *dev,
 		    unsigned long *index)
@@ -9597,24 +9575,44 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 	return 0;
 }
 
+DECLARE_RWSEM(dev_addr_sem);
+
+int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			       struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	down_write(&dev_addr_sem);
+	ret = netif_set_mac_address(dev, sa, extack);
+	up_write(&dev_addr_sem);
+	return ret;
+}
+
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
 	size_t size = sizeof(sa->sa_data_min);
 	struct net_device *dev;
+	int ret = 0;
 
-	dev = netdev_get_by_name_lock(net, dev_name);
-	if (!dev)
-		return -ENODEV;
+	down_read(&dev_addr_sem);
+	rcu_read_lock();
 
+	dev = dev_get_by_name_rcu(net, dev_name);
+	if (!dev) {
+		ret = -ENODEV;
+		goto unlock;
+	}
 	if (!dev->addr_len)
 		memset(sa->sa_data, 0, size);
 	else
 		memcpy(sa->sa_data, dev->dev_addr,
 		       min_t(size_t, size, dev->addr_len));
 	sa->sa_family = dev->type;
-	netdev_unlock(dev);
 
-	return 0;
+unlock:
+	rcu_read_unlock();
+	up_read(&dev_addr_sem);
+	return ret;
 }
 EXPORT_SYMBOL(dev_get_mac_address);
 
diff --git a/net/core/dev.h b/net/core/dev.h
index 0ddd3631acb01..7ee203395d8e2 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -29,7 +29,6 @@ netdev_napi_by_id_lock(struct net *net, unsigned int napi_id);
 struct net_device *dev_get_by_napi_id(unsigned int napi_id);
 
 struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex);
-struct net_device *netdev_get_by_name_lock(struct net *net, const char *name);
 struct net_device *__netdev_put_lock(struct net_device *dev);
 struct net_device *
 netdev_xa_find_lock(struct net *net, struct net_device *dev,
@@ -71,6 +70,8 @@ extern int		weight_p;
 extern int		dev_weight_rx_bias;
 extern int		dev_weight_tx_bias;
 
+extern struct rw_semaphore dev_addr_sem;
+
 /* rtnl helpers */
 extern struct list_head net_todo_list;
 void netdev_run_todo(void);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 1f0e24849bc65..2e17548af685a 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -84,6 +84,19 @@ void dev_set_group(struct net_device *dev, int new_group)
 	netdev_unlock_ops(dev);
 }
 
+int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+			     struct netlink_ext_ack *extack)
+{
+	int ret;
+
+	netdev_lock_ops(dev);
+	ret = netif_set_mac_address_user(dev, sa, extack);
+	netdev_unlock_ops(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_mac_address_user);
+
 /**
  * dev_change_net_namespace() - move device to different nethost namespace
  * @dev: device
@@ -299,9 +312,9 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 {
 	int ret;
 
-	netdev_lock(dev);
+	netdev_lock_ops(dev);
 	ret = netif_set_mac_address(dev, sa, extack);
-	netdev_unlock(dev);
+	netdev_unlock_ops(dev);
 
 	return ret;
 }
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 5471cf4fc9849..eb8b41ec5523c 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -575,7 +575,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	case SIOCSIFHWADDR:
 		if (dev->addr_len > sizeof(struct sockaddr))
 			return -EINVAL;
-		return dev_set_mac_address(dev, &ifr->ifr_hwaddr, NULL);
+		return dev_set_mac_address_user(dev, &ifr->ifr_hwaddr, NULL);
 
 	case SIOCSIFHWBROADCAST:
 		if (ifr->ifr_hwaddr.sa_family != dev->type)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 529a0f7212682..abaa1c919b984 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -263,11 +263,14 @@ static ssize_t address_show(struct device *dev, struct device_attribute *attr,
 	struct net_device *ndev = to_net_dev(dev);
 	ssize_t ret = -EINVAL;
 
-	netdev_lock(ndev);
+	down_read(&dev_addr_sem);
+
+	rcu_read_lock();
 	if (dev_isalive(ndev))
 		ret = sysfs_format_mac(buf, ndev->dev_addr, ndev->addr_len);
-	netdev_unlock(ndev);
+	rcu_read_unlock();
 
+	up_read(&dev_addr_sem);
 	return ret;
 }
 static DEVICE_ATTR_RO(address);
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 90597bf84e3d3..9355058bf9969 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3090,11 +3090,7 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 		sa->sa_family = dev->type;
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		if (!netdev_need_ops_lock(dev))
-			netdev_lock(dev);
-		err = netif_set_mac_address(dev, sa, extack);
-		if (!netdev_need_ops_lock(dev))
-			netdev_unlock(dev);
+		err = netif_set_mac_address_user(dev, sa, extack);
 		kfree(sa);
 		if (err)
 			goto errout;

From 6dd132516f8e467f144f7871ff2708ce827417a1 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Wed, 12 Mar 2025 12:05:13 -0700
Subject: [PATCH 2352/2753] net: reorder dev_addr_sem lock

Lockdep complains about circular lock in 1 -> 2 -> 3 (see below).

Change the lock ordering to be:
- rtnl_lock
- dev_addr_sem
- netdev_ops (only for lower devices!)
- team_lock (or other per-upper device lock)

1. rtnl_lock -> netdev_ops -> dev_addr_sem

rtnl_setlink
  rtnl_lock
    do_setlink IFLA_ADDRESS on lower
      netdev_ops
        dev_addr_sem

2. rtnl_lock -> team_lock -> netdev_ops

rtnl_newlink
  rtnl_lock
    do_setlink IFLA_MASTER on lower
      do_set_master
        team_add_slave
          team_lock
            team_port_add
	      dev_set_mtu
	        netdev_ops

3. rtnl_lock -> dev_addr_sem -> team_lock

rtnl_newlink
  rtnl_lock
    do_setlink IFLA_ADDRESS on upper
      dev_addr_sem
        netif_set_mac_address
          team_set_mac_address
            team_lock

4. rtnl_lock -> netdev_ops -> dev_addr_sem

rtnl_lock
  dev_ifsioc
    dev_set_mac_address_user

__tun_chr_ioctl
  rtnl_lock
    dev_set_mac_address_user

tap_ioctl
  rtnl_lock
    dev_set_mac_address_user

dev_set_mac_address_user
  netdev_lock_ops
    netif_set_mac_address_user
      dev_addr_sem

v2:
- move lock reorder to happen after kmalloc (Kuniyuki)

Cc: Kohei Enju <enjuk@amazon.com>
Fixes: df43d8bf1031 ("net: replace dev_addr_sem with netdev instance lock")
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250312190513.1252045-3-sdf@fomichev.me
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/netdevice.h |  2 --
 net/core/dev.c            | 11 -----------
 net/core/dev_api.c        |  4 +++-
 net/core/rtnetlink.c      | 15 +++++++++++++--
 4 files changed, 16 insertions(+), 16 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0db9fc0afe360..0c5b1f7f8f3af 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4196,8 +4196,6 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			  struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 			struct netlink_ext_ack *extack);
-int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			       struct netlink_ext_ack *extack);
 int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 977a9946d39c5..2355603417650 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9577,17 +9577,6 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr *sa,
 
 DECLARE_RWSEM(dev_addr_sem);
 
-int netif_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
-			       struct netlink_ext_ack *extack)
-{
-	int ret;
-
-	down_write(&dev_addr_sem);
-	ret = netif_set_mac_address(dev, sa, extack);
-	up_write(&dev_addr_sem);
-	return ret;
-}
-
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
 	size_t size = sizeof(sa->sa_data_min);
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 2e17548af685a..8dbc606121007 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -89,9 +89,11 @@ int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
 {
 	int ret;
 
+	down_write(&dev_addr_sem);
 	netdev_lock_ops(dev);
-	ret = netif_set_mac_address_user(dev, sa, extack);
+	ret = netif_set_mac_address(dev, sa, extack);
 	netdev_unlock_ops(dev);
+	up_write(&dev_addr_sem);
 
 	return ret;
 }
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9355058bf9969..5a24a30dfc2d1 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3088,13 +3088,24 @@ static int do_setlink(const struct sk_buff *skb, struct net_device *dev,
 			goto errout;
 		}
 		sa->sa_family = dev->type;
+
+		netdev_unlock_ops(dev);
+
+		/* dev_addr_sem is an outer lock, enforce proper ordering */
+		down_write(&dev_addr_sem);
+		netdev_lock_ops(dev);
+
 		memcpy(sa->sa_data, nla_data(tb[IFLA_ADDRESS]),
 		       dev->addr_len);
-		err = netif_set_mac_address_user(dev, sa, extack);
+		err = netif_set_mac_address(dev, sa, extack);
 		kfree(sa);
-		if (err)
+		if (err) {
+			up_write(&dev_addr_sem);
 			goto errout;
+		}
 		status |= DO_SETLINK_MODIFIED;
+
+		up_write(&dev_addr_sem);
 	}
 
 	if (tb[IFLA_MTU]) {

From 34e5ededf4b8ad4c9e58f0cab8596e26c8fa59a2 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Wed, 12 Mar 2025 20:21:42 +0100
Subject: [PATCH 2353/2753] r8169: switch away from deprecated pcim_iomap_table

Avoid using deprecated pcim_iomap_table by switching to
pcim_iomap_region.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/a36b4cf3-c792-40fa-8164-5dc9d5f14dd0@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/realtek/r8169_main.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index b18daeeda40d9..53e541ddb439f 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5447,11 +5447,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (region < 0)
 		return dev_err_probe(&pdev->dev, -ENODEV, "no MMIO resource found\n");
 
-	rc = pcim_iomap_regions(pdev, BIT(region), KBUILD_MODNAME);
-	if (rc < 0)
-		return dev_err_probe(&pdev->dev, rc, "cannot remap MMIO, aborting\n");
-
-	tp->mmio_addr = pcim_iomap_table(pdev)[region];
+	tp->mmio_addr = pcim_iomap_region(pdev, region, KBUILD_MODNAME);
+	if (IS_ERR(tp->mmio_addr))
+		return dev_err_probe(&pdev->dev, PTR_ERR(tp->mmio_addr),
+				     "cannot remap MMIO, aborting\n");
 
 	txconfig = RTL_R32(tp, TxConfig);
 	if (txconfig == ~0U)

From c9cb135bc604ad6e457e06c19e0857c9cd0eef7f Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 12 Mar 2025 19:43:09 +0000
Subject: [PATCH 2354/2753] net: stmmac: dwc-qos-eth: use devm_kzalloc() for
 AXI data

Everywhere else in the driver uses devm_kzalloc() when allocating the
AXI data, so there is no kfree() of this structure. However,
dwc-qos-eth uses kzalloc(), which leads to this memory being leaked.
Switch to use devm_kzalloc().

Fixes: d8256121a91a ("stmmac: adding new glue driver dwmac-dwc-qos-eth")
Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1tsRyv-0064nU-O9@rmk-PC.armlinux.org.uk
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
index bd4eb187f8c64..b5a7e05ab7a7e 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c
@@ -46,7 +46,9 @@ static int dwc_eth_dwmac_config_dt(struct platform_device *pdev,
 	u32 a_index = 0;
 
 	if (!plat_dat->axi) {
-		plat_dat->axi = kzalloc(sizeof(struct stmmac_axi), GFP_KERNEL);
+		plat_dat->axi = devm_kzalloc(&pdev->dev,
+					     sizeof(struct stmmac_axi),
+					     GFP_KERNEL);
 
 		if (!plat_dat->axi)
 			return -ENOMEM;

From 6d6c1ba7824022528dbe3e283fafbd0775424128 Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Wed, 12 Mar 2025 13:51:46 -0600
Subject: [PATCH 2355/2753] net, treewide: define and use MAC_ADDR_STR_LEN

There are a few places in the tree which compute the length of the
string representation of a MAC address as 3 * ETH_ALEN - 1. Define a
constant for this and use it where relevant. No functionality changes
are expected.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Acked-by: Johannes Berg <johannes@sipsolutions.net>
Reviewed-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@verge.net.au>
Link: https://patch.msgid.link/20250312-netconsole-v6-1-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/netconsole.c           | 2 +-
 drivers/nvmem/brcm_nvram.c         | 2 +-
 drivers/nvmem/layouts/u-boot-env.c | 2 +-
 include/linux/if_ether.h           | 3 +++
 lib/net_utils.c                    | 4 +---
 net/mac80211/debugfs_sta.c         | 7 ++++---
 6 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 098ea9eb02373..43757b5c02169 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -739,7 +739,7 @@ static ssize_t remote_mac_store(struct config_item *item, const char *buf,
 
 	if (!mac_pton(buf, remote_mac))
 		goto out_unlock;
-	if (buf[3 * ETH_ALEN - 1] && buf[3 * ETH_ALEN - 1] != '\n')
+	if (buf[MAC_ADDR_STR_LEN] && buf[MAC_ADDR_STR_LEN] != '\n')
 		goto out_unlock;
 	memcpy(nt->np.remote_mac, remote_mac, ETH_ALEN);
 
diff --git a/drivers/nvmem/brcm_nvram.c b/drivers/nvmem/brcm_nvram.c
index b810df727b446..b4cf245fb2467 100644
--- a/drivers/nvmem/brcm_nvram.c
+++ b/drivers/nvmem/brcm_nvram.c
@@ -100,7 +100,7 @@ static int brcm_nvram_read_post_process_macaddr(void *context, const char *id, i
 {
 	u8 mac[ETH_ALEN];
 
-	if (bytes != 3 * ETH_ALEN - 1)
+	if (bytes != MAC_ADDR_STR_LEN)
 		return -EINVAL;
 
 	if (!mac_pton(buf, mac))
diff --git a/drivers/nvmem/layouts/u-boot-env.c b/drivers/nvmem/layouts/u-boot-env.c
index 731e6f4f12b2b..436426d4e8f91 100644
--- a/drivers/nvmem/layouts/u-boot-env.c
+++ b/drivers/nvmem/layouts/u-boot-env.c
@@ -37,7 +37,7 @@ static int u_boot_env_read_post_process_ethaddr(void *context, const char *id, i
 {
 	u8 mac[ETH_ALEN];
 
-	if (bytes != 3 * ETH_ALEN - 1)
+	if (bytes != MAC_ADDR_STR_LEN)
 		return -EINVAL;
 
 	if (!mac_pton(buf, mac))
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 8a9792a6427ad..61b7335aa037c 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -19,6 +19,9 @@
 #include <linux/skbuff.h>
 #include <uapi/linux/if_ether.h>
 
+/* XX:XX:XX:XX:XX:XX */
+#define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1)
+
 static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 {
 	return (struct ethhdr *)skb_mac_header(skb);
diff --git a/lib/net_utils.c b/lib/net_utils.c
index 42bb0473fb22f..215cda672fee1 100644
--- a/lib/net_utils.c
+++ b/lib/net_utils.c
@@ -7,11 +7,9 @@
 
 bool mac_pton(const char *s, u8 *mac)
 {
-	size_t maxlen = 3 * ETH_ALEN - 1;
 	int i;
 
-	/* XX:XX:XX:XX:XX:XX */
-	if (strnlen(s, maxlen) < maxlen)
+	if (strnlen(s, MAC_ADDR_STR_LEN) < MAC_ADDR_STR_LEN)
 		return false;
 
 	/* Don't dirty result unless string is valid MAC. */
diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c
index a67a9d3160086..a8948f4d983e5 100644
--- a/net/mac80211/debugfs_sta.c
+++ b/net/mac80211/debugfs_sta.c
@@ -457,11 +457,12 @@ static ssize_t link_sta_addr_read(struct file *file, char __user *userbuf,
 				  size_t count, loff_t *ppos)
 {
 	struct link_sta_info *link_sta = file->private_data;
-	u8 mac[3 * ETH_ALEN + 1];
+	u8 mac[MAC_ADDR_STR_LEN + 2];
 
 	snprintf(mac, sizeof(mac), "%pM\n", link_sta->pub->addr);
 
-	return simple_read_from_buffer(userbuf, count, ppos, mac, 3 * ETH_ALEN);
+	return simple_read_from_buffer(userbuf, count, ppos, mac,
+				       MAC_ADDR_STR_LEN + 1);
 }
 
 LINK_STA_OPS(addr);
@@ -1240,7 +1241,7 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta)
 	struct ieee80211_local *local = sta->local;
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct dentry *stations_dir = sta->sdata->debugfs.subdir_stations;
-	u8 mac[3*ETH_ALEN];
+	u8 mac[MAC_ADDR_STR_LEN + 1];
 
 	if (!stations_dir)
 		return;

From f8a10bed32f5fbede13a5f22fdc4ab8740ea213a Mon Sep 17 00:00:00 2001
From: Uday Shankar <ushankar@purestorage.com>
Date: Wed, 12 Mar 2025 13:51:47 -0600
Subject: [PATCH 2356/2753] netconsole: allow selection of egress interface via
 MAC address

Currently, netconsole has two methods of configuration - module
parameter and configfs. The former interface allows for netconsole
activation earlier during boot (by specifying the module parameter on
the kernel command line), so it is preferred for debugging issues which
arise before userspace is up/the configfs interface can be used. The
module parameter syntax requires specifying the egress interface name.
This requirement makes it hard to use for a couple reasons:
- The egress interface name can be hard or impossible to predict. For
  example, installing a new network card in a system can change the
  interface names assigned by the kernel.
- When constructing the module parameter, one may have trouble
  determining the original (kernel-assigned) name of the interface
  (which is the name that should be given to netconsole) if some stable
  interface naming scheme is in effect. A human can usually look at
  kernel logs to determine the original name, but this is very painful
  if automation is constructing the parameter.

For these reasons, allow selection of the egress interface via MAC
address when configuring netconsole using the module parameter. Update
the netconsole documentation with an example of the new syntax.
Selection of egress interface by MAC address via configfs is far less
interesting (since when this interface can be used, one should be able
to easily convert between MAC address and interface name), so it is left
unimplemented.

Signed-off-by: Uday Shankar <ushankar@purestorage.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Tested-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-netconsole-v6-2-3437933e79b8@purestorage.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/netconsole.rst |  6 ++-
 include/linux/netpoll.h                 |  6 +++
 net/core/netpoll.c                      | 51 +++++++++++++++++++------
 3 files changed, 50 insertions(+), 13 deletions(-)

diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
index ae82a6337a8d8..ec740ba127976 100644
--- a/Documentation/networking/netconsole.rst
+++ b/Documentation/networking/netconsole.rst
@@ -47,7 +47,7 @@ following format::
 	r             if present, prepend kernel version (release) to the message
 	src-port      source for UDP packets (defaults to 6665)
 	src-ip        source IP to use (interface address)
-	dev           network interface (eth0)
+	dev           network interface name (eth0) or MAC address
 	tgt-port      port for logging agent (6666)
 	tgt-ip        IP address for logging agent
 	tgt-macaddr   ethernet MAC address for logging agent (broadcast)
@@ -64,6 +64,10 @@ or using IPv6::
 
  insmod netconsole netconsole=@/,@fd00:1:2:3::1/
 
+or using a MAC address to select the egress interface::
+
+   linux netconsole=4444@10.0.0.1/22:33:44:55:66:77,9353@10.0.0.2/12:34:56:78:9a:bc
+
 It also supports logging to multiple remote agents by specifying
 parameters for the multiple agents separated by semicolons and the
 complete string enclosed in "quotes", thusly::
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index f6e8abe0b1f19..0477208ed9ffa 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -25,7 +25,13 @@ union inet_addr {
 struct netpoll {
 	struct net_device *dev;
 	netdevice_tracker dev_tracker;
+	/*
+	 * Either dev_name or dev_mac can be used to specify the local
+	 * interface - dev_name is used if it is a nonempty string, else
+	 * dev_mac is used.
+	 */
 	char dev_name[IFNAMSIZ];
+	u8 dev_mac[ETH_ALEN];
 	const char *name;
 
 	union inet_addr local_ip, remote_ip;
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 3cc3eae9def30..7bc75a4ef5d2a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -507,7 +507,8 @@ void netpoll_print_options(struct netpoll *np)
 		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
 	else
 		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
-	np_info(np, "interface '%s'\n", np->dev_name);
+	np_info(np, "interface name '%s'\n", np->dev_name);
+	np_info(np, "local ethernet address '%pM'\n", np->dev_mac);
 	np_info(np, "remote port %d\n", np->remote_port);
 	if (np->ipv6)
 		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
@@ -577,11 +578,18 @@ int netpoll_parse_options(struct netpoll *np, char *opt)
 	cur++;
 
 	if (*cur != ',') {
-		/* parse out dev name */
+		/* parse out dev_name or dev_mac */
 		if ((delim = strchr(cur, ',')) == NULL)
 			goto parse_failed;
 		*delim = 0;
-		strscpy(np->dev_name, cur, sizeof(np->dev_name));
+
+		np->dev_name[0] = '\0';
+		eth_broadcast_addr(np->dev_mac);
+		if (!strchr(cur, ':'))
+			strscpy(np->dev_name, cur, sizeof(np->dev_name));
+		else if (!mac_pton(cur, np->dev_mac))
+			goto parse_failed;
+
 		cur = delim;
 	}
 	cur++;
@@ -695,27 +703,45 @@ int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
 }
 EXPORT_SYMBOL_GPL(__netpoll_setup);
 
+/*
+ * Returns a pointer to a string representation of the identifier used
+ * to select the egress interface for the given netpoll instance. buf
+ * must be a buffer of length at least MAC_ADDR_STR_LEN + 1.
+ */
+static char *egress_dev(struct netpoll *np, char *buf)
+{
+	if (np->dev_name[0])
+		return np->dev_name;
+
+	snprintf(buf, MAC_ADDR_STR_LEN, "%pM", np->dev_mac);
+	return buf;
+}
+
 int netpoll_setup(struct netpoll *np)
 {
+	struct net *net = current->nsproxy->net_ns;
+	char buf[MAC_ADDR_STR_LEN + 1];
 	struct net_device *ndev = NULL;
 	bool ip_overwritten = false;
 	struct in_device *in_dev;
 	int err;
 
 	rtnl_lock();
-	if (np->dev_name[0]) {
-		struct net *net = current->nsproxy->net_ns;
+	if (np->dev_name[0])
 		ndev = __dev_get_by_name(net, np->dev_name);
-	}
+	else if (is_valid_ether_addr(np->dev_mac))
+		ndev = dev_getbyhwaddr(net, ARPHRD_ETHER, np->dev_mac);
+
 	if (!ndev) {
-		np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
+		np_err(np, "%s doesn't exist, aborting\n", egress_dev(np, buf));
 		err = -ENODEV;
 		goto unlock;
 	}
 	netdev_hold(ndev, &np->dev_tracker, GFP_KERNEL);
 
 	if (netdev_master_upper_dev_get(ndev)) {
-		np_err(np, "%s is a slave device, aborting\n", np->dev_name);
+		np_err(np, "%s is a slave device, aborting\n",
+		       egress_dev(np, buf));
 		err = -EBUSY;
 		goto put;
 	}
@@ -723,7 +749,8 @@ int netpoll_setup(struct netpoll *np)
 	if (!netif_running(ndev)) {
 		unsigned long atmost;
 
-		np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
+		np_info(np, "device %s not up yet, forcing it\n",
+			egress_dev(np, buf));
 
 		err = dev_open(ndev, NULL);
 
@@ -757,7 +784,7 @@ int netpoll_setup(struct netpoll *np)
 			if (!ifa) {
 put_noaddr:
 				np_err(np, "no IP address for %s, aborting\n",
-				       np->dev_name);
+				       egress_dev(np, buf));
 				err = -EDESTADDRREQ;
 				goto put;
 			}
@@ -788,13 +815,13 @@ int netpoll_setup(struct netpoll *np)
 			}
 			if (err) {
 				np_err(np, "no IPv6 address for %s, aborting\n",
-				       np->dev_name);
+				       egress_dev(np, buf));
 				goto put;
 			} else
 				np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6);
 #else
 			np_err(np, "IPv6 is not supported %s, aborting\n",
-			       np->dev_name);
+			       egress_dev(np, buf));
 			err = -EINVAL;
 			goto put;
 #endif

From 3d97da0ee6253d79add79254015623a2cdff9634 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 12 Mar 2025 13:07:01 -0700
Subject: [PATCH 2357/2753] net: macb: Add __nonstring annotations for
 unterminated strings

When a character array without a terminating NUL character has a static
initializer, GCC 15's -Wunterminated-string-initialization will only
warn if the array lacks the "nonstring" attribute[1]. Mark the arrays
with __nonstring to correctly identify the char array as "not a C string"
and thereby eliminate the warning:

In file included from ../drivers/net/ethernet/cadence/macb_main.c:42:
../drivers/net/ethernet/cadence/macb.h:1070:35: warning: initializer-string for array of 'char' truncates NUL terminator but destination lacks 'nonstring' attribute (33 chars into 32 available) [-Wunterminated-string-initialization]
 1070 |         GEM_STAT_TITLE(TX1519CNT, "tx_greater_than_1518_byte_frames"),
      |                                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1050:24: note: in definition of macro 'GEM_STAT_TITLE_BITS'
 1050 |         .stat_string = title,                           \
      |                        ^~~~~
../drivers/net/ethernet/cadence/macb.h:1070:9: note: in expansion of macro 'GEM_STAT_TITLE'
 1070 |         GEM_STAT_TITLE(TX1519CNT, "tx_greater_than_1518_byte_frames"),
      |         ^~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1097:35: warning: initializer-string for array of 'char' truncates NUL terminator but destination lacks 'nonstring' attribute (33 chars into 32 available) [-Wunterminated-string-initialization]
 1097 |         GEM_STAT_TITLE(RX1519CNT, "rx_greater_than_1518_byte_frames"),
      |                                   ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../drivers/net/ethernet/cadence/macb.h:1050:24: note: in definition of macro 'GEM_STAT_TITLE_BITS'
 1050 |         .stat_string = title,                           \
      |                        ^~~~~
../drivers/net/ethernet/cadence/macb.h:1097:9: note: in expansion of macro 'GEM_STAT_TITLE'
 1097 |         GEM_STAT_TITLE(RX1519CNT, "rx_greater_than_1518_byte_frames"),
      |         ^~~~~~~~~~~~~~

Since these strings are copied with memcpy() they do not need to be
NUL terminated, and can use __nonstring:

                        memcpy(p, gem_statistics[i].stat_string,
                               ETH_GSTRING_LEN);

Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178 [1]
Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312200700.make.521-kees@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/cadence/macb.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index 2a3924f01bf44..c9a5c8beb2fa8 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -1025,7 +1025,7 @@ struct gem_stats {
  * this register should contribute to.
  */
 struct gem_statistic {
-	char stat_string[ETH_GSTRING_LEN];
+	char stat_string[ETH_GSTRING_LEN] __nonstring;
 	int offset;
 	u32 stat_bits;
 };

From 1794d7ab34d2221ac7eb921b171e75b856e10561 Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Wed, 19 Mar 2025 19:44:25 +0100
Subject: [PATCH 2358/2753] wifi: mt76: mt7996: fix locking in
 mt7996_mac_sta_rc_work()

The 'continue' statements need to be under spinlock, since
the spinlock needs to be held as a loop invariant.

Fixes: 0762bdd30279 ("wifi: mt76: mt7996: rework mt7996_mac_sta_rc_work to support MLO")
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/mediatek/mt76/mt7996/mac.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
index a52b4e71b267e..d89c06f47997f 100644
--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
@@ -2334,7 +2334,6 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 
 		changed = msta_link->changed;
 		msta_link->changed = 0;
-		spin_unlock_bh(&dev->mt76.sta_poll_lock);
 
 		sta = wcid_to_sta(&msta_link->wcid);
 		link_id = msta_link->wcid.link_id;
@@ -2354,6 +2353,8 @@ void mt7996_mac_sta_rc_work(struct work_struct *work)
 		if (!link_conf)
 			continue;
 
+		spin_unlock_bh(&dev->mt76.sta_poll_lock);
+
 		link = (struct mt7996_vif_link *)mlink;
 
 		if (changed & (IEEE80211_RC_SUPP_RATES_CHANGED |

From 559847f56769037e5b2e0474d3dbff985b98083d Mon Sep 17 00:00:00 2001
From: Gavrilov Ilia <Ilia.Gavrilov@infotecs.ru>
Date: Thu, 13 Mar 2025 08:50:08 +0000
Subject: [PATCH 2359/2753] xsk: fix an integer overflow in
 xp_create_and_assign_umem()

Since the i and pool->chunk_size variables are of type 'u32',
their product can wrap around and then be cast to 'u64'.
This can lead to two different XDP buffers pointing to the same
memory area.

Found by InfoTeCS on behalf of Linux Verification Center
(linuxtesting.org) with SVACE.

Fixes: 94033cd8e73b ("xsk: Optimize for aligned case")
Cc: stable@vger.kernel.org
Signed-off-by: Ilia Gavrilov <Ilia.Gavrilov@infotecs.ru>
Link: https://patch.msgid.link/20250313085007.3116044-1-Ilia.Gavrilov@infotecs.ru
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/xdp/xsk_buff_pool.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
index 1f7975b496579..d158cb6dd3919 100644
--- a/net/xdp/xsk_buff_pool.c
+++ b/net/xdp/xsk_buff_pool.c
@@ -105,7 +105,7 @@ struct xsk_buff_pool *xp_create_and_assign_umem(struct xdp_sock *xs,
 		if (pool->unaligned)
 			pool->free_heads[i] = xskb;
 		else
-			xp_init_xskb_addr(xskb, pool, i * pool->chunk_size);
+			xp_init_xskb_addr(xskb, pool, (u64)i * pool->chunk_size);
 	}
 
 	return pool;

From 45456e38c44eda2f1285601398fd289b3cec7002 Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 12 Mar 2025 21:30:06 +0100
Subject: [PATCH 2360/2753] net: phy: Allow loopback speed selection for PHY
 drivers

PHY drivers support loopback mode, but it is not possible to select the
speed of the loopback mode. The speed is chosen by the set_loopback()
operation of the PHY driver. Same is valid for genphy_loopback().

There are PHYs that support loopback with different speeds. Extend
set_loopback() to make loopback speed selection possible.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312203010.47429-2-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/adin1100.c          |  5 ++++-
 drivers/net/phy/dp83867.c           |  5 ++++-
 drivers/net/phy/marvell.c           |  8 +++++++-
 drivers/net/phy/mxl-gpy.c           | 11 +++++++----
 drivers/net/phy/phy-c45.c           |  5 ++++-
 drivers/net/phy/phy_device.c        | 12 +++++++++---
 drivers/net/phy/xilinx_gmii2rgmii.c |  7 ++++---
 include/linux/phy.h                 | 16 ++++++++++++----
 8 files changed, 51 insertions(+), 18 deletions(-)

diff --git a/drivers/net/phy/adin1100.c b/drivers/net/phy/adin1100.c
index 6bb469429b9d0..bd7a47a903aca 100644
--- a/drivers/net/phy/adin1100.c
+++ b/drivers/net/phy/adin1100.c
@@ -215,8 +215,11 @@ static int adin_resume(struct phy_device *phydev)
 	return adin_set_powerdown_mode(phydev, false);
 }
 
-static int adin_set_loopback(struct phy_device *phydev, bool enable)
+static int adin_set_loopback(struct phy_device *phydev, bool enable, int speed)
 {
+	if (enable && speed)
+		return -EOPNOTSUPP;
+
 	if (enable)
 		return phy_set_bits_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_10T1L_CTRL,
 					BMCR_LOOPBACK);
diff --git a/drivers/net/phy/dp83867.c b/drivers/net/phy/dp83867.c
index c1451df430ace..063266cafe9c7 100644
--- a/drivers/net/phy/dp83867.c
+++ b/drivers/net/phy/dp83867.c
@@ -1009,8 +1009,11 @@ static void dp83867_link_change_notify(struct phy_device *phydev)
 	}
 }
 
-static int dp83867_loopback(struct phy_device *phydev, bool enable)
+static int dp83867_loopback(struct phy_device *phydev, bool enable, int speed)
 {
+	if (enable && speed)
+		return -EOPNOTSUPP;
+
 	return phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK,
 			  enable ? BMCR_LOOPBACK : 0);
 }
diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index dd254e36ca8ae..f2ad675537d1e 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2131,13 +2131,19 @@ static void marvell_get_stats_simple(struct phy_device *phydev,
 		data[i] = marvell_get_stat_simple(phydev, i);
 }
 
-static int m88e1510_loopback(struct phy_device *phydev, bool enable)
+static int m88e1510_loopback(struct phy_device *phydev, bool enable, int speed)
 {
 	int err;
 
 	if (enable) {
 		u16 bmcr_ctl, mscr2_ctl = 0;
 
+		if (speed == SPEED_10 || speed == SPEED_100 ||
+		    speed == SPEED_1000)
+			phydev->speed = speed;
+		else if (speed)
+			return -EINVAL;
+
 		bmcr_ctl = mii_bmcr_encode_fixed(phydev->speed, phydev->duplex);
 
 		err = phy_write(phydev, MII_BMCR, bmcr_ctl);
diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c
index 94d9cb727121a..a6cca8d432536 100644
--- a/drivers/net/phy/mxl-gpy.c
+++ b/drivers/net/phy/mxl-gpy.c
@@ -813,7 +813,7 @@ static void gpy_get_wol(struct phy_device *phydev,
 	wol->wolopts = priv->wolopts;
 }
 
-static int gpy_loopback(struct phy_device *phydev, bool enable)
+static int gpy_loopback(struct phy_device *phydev, bool enable, int speed)
 {
 	struct gpy_priv *priv = phydev->priv;
 	u16 set = 0;
@@ -822,6 +822,9 @@ static int gpy_loopback(struct phy_device *phydev, bool enable)
 	if (enable) {
 		u64 now = get_jiffies_64();
 
+		if (speed)
+			return -EOPNOTSUPP;
+
 		/* wait until 3 seconds from last disable */
 		if (time_before64(now, priv->lb_dis_to))
 			msleep(jiffies64_to_msecs(priv->lb_dis_to - now));
@@ -845,15 +848,15 @@ static int gpy_loopback(struct phy_device *phydev, bool enable)
 	return 0;
 }
 
-static int gpy115_loopback(struct phy_device *phydev, bool enable)
+static int gpy115_loopback(struct phy_device *phydev, bool enable, int speed)
 {
 	struct gpy_priv *priv = phydev->priv;
 
 	if (enable)
-		return gpy_loopback(phydev, enable);
+		return gpy_loopback(phydev, enable, speed);
 
 	if (priv->fw_minor > 0x76)
-		return gpy_loopback(phydev, 0);
+		return gpy_loopback(phydev, 0, 0);
 
 	return genphy_soft_reset(phydev);
 }
diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 0bcbdce381071..8a0ffc3174ecf 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1228,8 +1228,11 @@ int gen10g_config_aneg(struct phy_device *phydev)
 }
 EXPORT_SYMBOL_GPL(gen10g_config_aneg);
 
-int genphy_c45_loopback(struct phy_device *phydev, bool enable)
+int genphy_c45_loopback(struct phy_device *phydev, bool enable, int speed)
 {
+	if (enable && speed)
+		return -EOPNOTSUPP;
+
 	return phy_modify_mmd(phydev, MDIO_MMD_PCS, MDIO_CTRL1,
 			      MDIO_PCS_CTRL1_LOOPBACK,
 			      enable ? MDIO_PCS_CTRL1_LOOPBACK : 0);
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 3f734e847e8e2..09864c9635ace 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1838,9 +1838,9 @@ int phy_loopback(struct phy_device *phydev, bool enable)
 	}
 
 	if (phydev->drv->set_loopback)
-		ret = phydev->drv->set_loopback(phydev, enable);
+		ret = phydev->drv->set_loopback(phydev, enable, 0);
 	else
-		ret = genphy_loopback(phydev, enable);
+		ret = genphy_loopback(phydev, enable, 0);
 
 	if (ret)
 		goto out;
@@ -2610,12 +2610,18 @@ int genphy_resume(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(genphy_resume);
 
-int genphy_loopback(struct phy_device *phydev, bool enable)
+int genphy_loopback(struct phy_device *phydev, bool enable, int speed)
 {
 	if (enable) {
 		u16 ctl = BMCR_LOOPBACK;
 		int ret, val;
 
+		if (speed == SPEED_10 || speed == SPEED_100 ||
+		    speed == SPEED_1000)
+			phydev->speed = speed;
+		else if (speed)
+			return -EINVAL;
+
 		ctl |= mii_bmcr_encode_fixed(phydev->speed, phydev->duplex);
 
 		phy_modify(phydev, MII_BMCR, ~0, ctl);
diff --git a/drivers/net/phy/xilinx_gmii2rgmii.c b/drivers/net/phy/xilinx_gmii2rgmii.c
index 7c51daecf18ee..2024d8ef36d98 100644
--- a/drivers/net/phy/xilinx_gmii2rgmii.c
+++ b/drivers/net/phy/xilinx_gmii2rgmii.c
@@ -64,15 +64,16 @@ static int xgmiitorgmii_read_status(struct phy_device *phydev)
 	return 0;
 }
 
-static int xgmiitorgmii_set_loopback(struct phy_device *phydev, bool enable)
+static int xgmiitorgmii_set_loopback(struct phy_device *phydev, bool enable,
+				     int speed)
 {
 	struct gmii2rgmii *priv = mdiodev_get_drvdata(&phydev->mdio);
 	int err;
 
 	if (priv->phy_drv->set_loopback)
-		err = priv->phy_drv->set_loopback(phydev, enable);
+		err = priv->phy_drv->set_loopback(phydev, enable, speed);
 	else
-		err = genphy_loopback(phydev, enable);
+		err = genphy_loopback(phydev, enable, speed);
 	if (err < 0)
 		return err;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index c24e1a5658196..1c05158e94388 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1136,8 +1136,16 @@ struct phy_driver {
 	int (*set_tunable)(struct phy_device *dev,
 			    struct ethtool_tunable *tuna,
 			    const void *data);
-	/** @set_loopback: Set the loopback mood of the PHY */
-	int (*set_loopback)(struct phy_device *dev, bool enable);
+	/**
+	 * @set_loopback: Set the loopback mode of the PHY
+	 * enable selects if the loopback mode is enabled or disabled. If the
+	 * loopback mode is enabled, then the speed of the loopback mode can be
+	 * requested with the speed argument. If the speed argument is zero,
+	 * then any speed can be selected. If the speed argument is > 0, then
+	 * this speed shall be selected for the loopback mode or EOPNOTSUPP
+	 * shall be returned if speed selection is not supported.
+	 */
+	int (*set_loopback)(struct phy_device *dev, bool enable, int speed);
 	/** @get_sqi: Get the signal quality indication */
 	int (*get_sqi)(struct phy_device *dev);
 	/** @get_sqi_max: Get the maximum signal quality indication */
@@ -1915,7 +1923,7 @@ int genphy_read_status(struct phy_device *phydev);
 int genphy_read_master_slave(struct phy_device *phydev);
 int genphy_suspend(struct phy_device *phydev);
 int genphy_resume(struct phy_device *phydev);
-int genphy_loopback(struct phy_device *phydev, bool enable);
+int genphy_loopback(struct phy_device *phydev, bool enable, int speed);
 int genphy_soft_reset(struct phy_device *phydev);
 irqreturn_t genphy_handle_interrupt_no_ack(struct phy_device *phydev);
 
@@ -1957,7 +1965,7 @@ int genphy_c45_pma_baset1_read_master_slave(struct phy_device *phydev);
 int genphy_c45_read_status(struct phy_device *phydev);
 int genphy_c45_baset1_read_status(struct phy_device *phydev);
 int genphy_c45_config_aneg(struct phy_device *phydev);
-int genphy_c45_loopback(struct phy_device *phydev, bool enable);
+int genphy_c45_loopback(struct phy_device *phydev, bool enable, int speed);
 int genphy_c45_pma_resume(struct phy_device *phydev);
 int genphy_c45_pma_suspend(struct phy_device *phydev);
 int genphy_c45_fast_retrain(struct phy_device *phydev, bool enable);

From 0d60fd50328a96a901b09ed653704ce7f41d15ce Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 12 Mar 2025 21:30:07 +0100
Subject: [PATCH 2361/2753] net: phy: Support speed selection for PHY loopback

phy_loopback() leaves it to the PHY driver to select the speed of the
loopback mode. Thus, the speed of the loopback mode depends on the PHY
driver in use.

Add support for speed selection to phy_loopback() to enable loopback
with defined speeds. Ensure that link up is signaled if speed changes
as speed is not allowed to change during link up. Link down and up is
necessary for a new speed.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Link: https://patch.msgid.link/20250312203010.47429-3-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/engleder/tsnep_main.c    |  2 +-
 .../net/ethernet/hisilicon/hns/hns_ethtool.c  |  4 +-
 .../hisilicon/hns3/hns3pf/hclge_main.c        |  4 +-
 .../hisilicon/hns3/hns3pf/hclge_mdio.c        |  2 +-
 .../stmicro/stmmac/stmmac_selftests.c         |  8 +-
 drivers/net/phy/phy.c                         | 87 +++++++++++++++++++
 drivers/net/phy/phy_device.c                  | 35 --------
 include/linux/phy.h                           |  2 +-
 net/core/selftests.c                          |  4 +-
 9 files changed, 100 insertions(+), 48 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 3de4cb06e2668..7a9fe0719f8cc 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -223,7 +223,7 @@ static int tsnep_phy_loopback(struct tsnep_adapter *adapter, bool enable)
 {
 	int retval;
 
-	retval = phy_loopback(adapter->phydev, enable);
+	retval = phy_loopback(adapter->phydev, enable, 0);
 
 	/* PHY link state change is not signaled if loopback is enabled, it
 	 * would delay a working loopback anyway, let's ensure that loopback
diff --git a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
index 6c458f037262f..60a586a951a02 100644
--- a/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
+++ b/drivers/net/ethernet/hisilicon/hns/hns_ethtool.c
@@ -266,9 +266,9 @@ static int hns_nic_config_phy_loopback(struct phy_device *phy_dev, u8 en)
 		if (err)
 			goto out;
 
-		err = phy_loopback(phy_dev, true);
+		err = phy_loopback(phy_dev, true, 0);
 	} else {
-		err = phy_loopback(phy_dev, false);
+		err = phy_loopback(phy_dev, false, 0);
 		if (err)
 			goto out;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
index 8c736a069eeb4..92f9b8ec76d9f 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
@@ -7875,7 +7875,7 @@ static int hclge_enable_phy_loopback(struct hclge_dev *hdev,
 	if (ret)
 		return ret;
 
-	return phy_loopback(phydev, true);
+	return phy_loopback(phydev, true, 0);
 }
 
 static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
@@ -7883,7 +7883,7 @@ static int hclge_disable_phy_loopback(struct hclge_dev *hdev,
 {
 	int ret;
 
-	ret = phy_loopback(phydev, false);
+	ret = phy_loopback(phydev, false, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
index 80079657afebe..9a456ebf9b7cd 100644
--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
@@ -258,7 +258,7 @@ void hclge_mac_start_phy(struct hclge_dev *hdev)
 	if (!phydev)
 		return;
 
-	phy_loopback(phydev, false);
+	phy_loopback(phydev, false, 0);
 
 	phy_start(phydev);
 }
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
index 3ca1c2a816ff1..a01bc394d1ac4 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c
@@ -382,14 +382,14 @@ static int stmmac_test_phy_loopback(struct stmmac_priv *priv)
 	if (!priv->dev->phydev)
 		return -EOPNOTSUPP;
 
-	ret = phy_loopback(priv->dev->phydev, true);
+	ret = phy_loopback(priv->dev->phydev, true, 0);
 	if (ret)
 		return ret;
 
 	attr.dst = priv->dev->dev_addr;
 	ret = __stmmac_test_loopback(priv, &attr);
 
-	phy_loopback(priv->dev->phydev, false);
+	phy_loopback(priv->dev->phydev, false, 0);
 	return ret;
 }
 
@@ -1985,7 +1985,7 @@ void stmmac_selftest_run(struct net_device *dev,
 		case STMMAC_LOOPBACK_PHY:
 			ret = -EOPNOTSUPP;
 			if (dev->phydev)
-				ret = phy_loopback(dev->phydev, true);
+				ret = phy_loopback(dev->phydev, true, 0);
 			if (!ret)
 				break;
 			fallthrough;
@@ -2018,7 +2018,7 @@ void stmmac_selftest_run(struct net_device *dev,
 		case STMMAC_LOOPBACK_PHY:
 			ret = -EOPNOTSUPP;
 			if (dev->phydev)
-				ret = phy_loopback(dev->phydev, false);
+				ret = phy_loopback(dev->phydev, false, 0);
 			if (!ret)
 				break;
 			fallthrough;
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 562acde892249..13df28445f020 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -1707,6 +1707,93 @@ void phy_mac_interrupt(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_mac_interrupt);
 
+/**
+ * phy_loopback - Configure loopback mode of PHY
+ * @phydev: target phy_device struct
+ * @enable: enable or disable loopback mode
+ * @speed: enable loopback mode with speed
+ *
+ * Configure loopback mode of PHY and signal link down and link up if speed is
+ * changing.
+ *
+ * Return: 0 on success, negative error code on failure.
+ */
+int phy_loopback(struct phy_device *phydev, bool enable, int speed)
+{
+	bool link_up = false;
+	int ret = 0;
+
+	if (!phydev->drv)
+		return -EIO;
+
+	mutex_lock(&phydev->lock);
+
+	if (enable && phydev->loopback_enabled) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	if (!enable && !phydev->loopback_enabled) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	if (enable) {
+		/*
+		 * Link up is signaled with a defined speed. If speed changes,
+		 * then first link down and after that link up needs to be
+		 * signaled.
+		 */
+		if (phydev->link && phydev->state == PHY_RUNNING) {
+			/* link is up and signaled */
+			if (speed && phydev->speed != speed) {
+				/* signal link down and up for new speed */
+				phydev->link = false;
+				phydev->state = PHY_NOLINK;
+				phy_link_down(phydev);
+
+				link_up = true;
+			}
+		} else {
+			/* link is not signaled */
+			if (speed) {
+				/* signal link up for new speed */
+				link_up = true;
+			}
+		}
+	}
+
+	if (phydev->drv->set_loopback)
+		ret = phydev->drv->set_loopback(phydev, enable, speed);
+	else
+		ret = genphy_loopback(phydev, enable, speed);
+
+	if (ret) {
+		if (enable) {
+			/* try to restore link if enabling loopback fails */
+			if (phydev->drv->set_loopback)
+				phydev->drv->set_loopback(phydev, false, 0);
+			else
+				genphy_loopback(phydev, false, 0);
+		}
+
+		goto out;
+	}
+
+	if (link_up) {
+		phydev->link = true;
+		phydev->state = PHY_RUNNING;
+		phy_link_up(phydev);
+	}
+
+	phydev->loopback_enabled = enable;
+
+out:
+	mutex_unlock(&phydev->lock);
+	return ret;
+}
+EXPORT_SYMBOL(phy_loopback);
+
 /**
  * phy_eee_tx_clock_stop_capable() - indicate whether the MAC can stop tx clock
  * @phydev: target phy_device struct
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 09864c9635ace..675fbd2253787 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1818,41 +1818,6 @@ int phy_resume(struct phy_device *phydev)
 }
 EXPORT_SYMBOL(phy_resume);
 
-int phy_loopback(struct phy_device *phydev, bool enable)
-{
-	int ret = 0;
-
-	if (!phydev->drv)
-		return -EIO;
-
-	mutex_lock(&phydev->lock);
-
-	if (enable && phydev->loopback_enabled) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	if (!enable && !phydev->loopback_enabled) {
-		ret = -EINVAL;
-		goto out;
-	}
-
-	if (phydev->drv->set_loopback)
-		ret = phydev->drv->set_loopback(phydev, enable, 0);
-	else
-		ret = genphy_loopback(phydev, enable, 0);
-
-	if (ret)
-		goto out;
-
-	phydev->loopback_enabled = enable;
-
-out:
-	mutex_unlock(&phydev->lock);
-	return ret;
-}
-EXPORT_SYMBOL(phy_loopback);
-
 /**
  * phy_reset_after_clk_enable - perform a PHY reset if needed
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 1c05158e94388..60d3b8860ea26 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1808,7 +1808,7 @@ int phy_init_hw(struct phy_device *phydev);
 int phy_suspend(struct phy_device *phydev);
 int phy_resume(struct phy_device *phydev);
 int __phy_resume(struct phy_device *phydev);
-int phy_loopback(struct phy_device *phydev, bool enable);
+int phy_loopback(struct phy_device *phydev, bool enable, int speed);
 int phy_sfp_connect_phy(void *upstream, struct phy_device *phy);
 void phy_sfp_disconnect_phy(void *upstream, struct phy_device *phy);
 void phy_sfp_attach(void *upstream, struct sfp_bus *bus);
diff --git a/net/core/selftests.c b/net/core/selftests.c
index 8f801e6e3b91b..e99ae983fca9b 100644
--- a/net/core/selftests.c
+++ b/net/core/selftests.c
@@ -299,7 +299,7 @@ static int net_test_phy_loopback_enable(struct net_device *ndev)
 	if (!ndev->phydev)
 		return -EOPNOTSUPP;
 
-	return phy_loopback(ndev->phydev, true);
+	return phy_loopback(ndev->phydev, true, 0);
 }
 
 static int net_test_phy_loopback_disable(struct net_device *ndev)
@@ -307,7 +307,7 @@ static int net_test_phy_loopback_disable(struct net_device *ndev)
 	if (!ndev->phydev)
 		return -EOPNOTSUPP;
 
-	return phy_loopback(ndev->phydev, false);
+	return phy_loopback(ndev->phydev, false, 0);
 }
 
 static int net_test_phy_loopback_udp(struct net_device *ndev)

From fe4bf60ffdff689d825a0f613636946124c9b5fe Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 12 Mar 2025 21:30:08 +0100
Subject: [PATCH 2362/2753] net: phy: micrel: Add loopback support

The KSZ9031 PHYs requires full duplex for loopback mode. Add PHY
specific set_loopback() to ensure this.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250312203010.47429-4-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/micrel.c | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
index 289e1d56aa655..24882d30f6858 100644
--- a/drivers/net/phy/micrel.c
+++ b/drivers/net/phy/micrel.c
@@ -1032,6 +1032,29 @@ static int ksz9021_config_init(struct phy_device *phydev)
 #define MII_KSZ9031RN_EDPD		0x23
 #define MII_KSZ9031RN_EDPD_ENABLE	BIT(0)
 
+static int ksz9031_set_loopback(struct phy_device *phydev, bool enable,
+				int speed)
+{
+	u16 ctl = BMCR_LOOPBACK;
+	int val;
+
+	if (!enable)
+		return genphy_loopback(phydev, enable, 0);
+
+	if (speed == SPEED_10 || speed == SPEED_100 || speed == SPEED_1000)
+		phydev->speed = speed;
+	else if (speed)
+		return -EINVAL;
+	phydev->duplex = DUPLEX_FULL;
+
+	ctl |= mii_bmcr_encode_fixed(phydev->speed, phydev->duplex);
+
+	phy_write(phydev, MII_BMCR, ctl);
+
+	return phy_read_poll_timeout(phydev, MII_BMSR, val, val & BMSR_LSTATUS,
+				     5000, 500000, true);
+}
+
 static int ksz9031_of_load_skew_values(struct phy_device *phydev,
 				       const struct device_node *of_node,
 				       u16 reg, size_t field_sz,
@@ -5565,6 +5588,7 @@ static struct phy_driver ksphy_driver[] = {
 	.resume		= kszphy_resume,
 	.cable_test_start	= ksz9x31_cable_test_start,
 	.cable_test_get_status	= ksz9x31_cable_test_get_status,
+	.set_loopback	= ksz9031_set_loopback,
 }, {
 	.phy_id		= PHY_ID_LAN8814,
 	.phy_id_mask	= MICREL_PHY_ID_MASK,

From 1a0df6c96ce52b3c9fa01b312be3f5ac5162c48b Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 12 Mar 2025 21:30:09 +0100
Subject: [PATCH 2363/2753] net: phy: marvell: Align set_loopback()
 implementation

Use genphy_loopback() to disable loopback like ksz9031_set_loopback().
This way disable loopback is implemented only once within
genphy_loopback() and the set_loopback() implementations look similar.

Also fix comment about msleep() in the out-of loopback case which is not
executed in the out-of loopback case.

Suggested-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312203010.47429-5-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/marvell.c | 72 ++++++++++++++++++---------------------
 1 file changed, 33 insertions(+), 39 deletions(-)

diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c
index f2ad675537d1e..623292948fa70 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -2133,56 +2133,50 @@ static void marvell_get_stats_simple(struct phy_device *phydev,
 
 static int m88e1510_loopback(struct phy_device *phydev, bool enable, int speed)
 {
+	u16 bmcr_ctl, mscr2_ctl = 0;
 	int err;
 
-	if (enable) {
-		u16 bmcr_ctl, mscr2_ctl = 0;
+	if (!enable)
+		return genphy_loopback(phydev, enable, 0);
 
-		if (speed == SPEED_10 || speed == SPEED_100 ||
-		    speed == SPEED_1000)
-			phydev->speed = speed;
-		else if (speed)
-			return -EINVAL;
-
-		bmcr_ctl = mii_bmcr_encode_fixed(phydev->speed, phydev->duplex);
-
-		err = phy_write(phydev, MII_BMCR, bmcr_ctl);
-		if (err < 0)
-			return err;
+	if (speed == SPEED_10 || speed == SPEED_100 || speed == SPEED_1000)
+		phydev->speed = speed;
+	else if (speed)
+		return -EINVAL;
 
-		if (phydev->speed == SPEED_1000)
-			mscr2_ctl = BMCR_SPEED1000;
-		else if (phydev->speed == SPEED_100)
-			mscr2_ctl = BMCR_SPEED100;
+	bmcr_ctl = mii_bmcr_encode_fixed(phydev->speed, phydev->duplex);
 
-		err = phy_modify_paged(phydev, MII_MARVELL_MSCR_PAGE,
-				       MII_88E1510_MSCR_2, BMCR_SPEED1000 |
-				       BMCR_SPEED100, mscr2_ctl);
-		if (err < 0)
-			return err;
+	err = phy_write(phydev, MII_BMCR, bmcr_ctl);
+	if (err < 0)
+		return err;
 
-		/* Need soft reset to have speed configuration takes effect */
-		err = genphy_soft_reset(phydev);
-		if (err < 0)
-			return err;
+	if (phydev->speed == SPEED_1000)
+		mscr2_ctl = BMCR_SPEED1000;
+	else if (phydev->speed == SPEED_100)
+		mscr2_ctl = BMCR_SPEED100;
 
-		err = phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK,
-				 BMCR_LOOPBACK);
+	err = phy_modify_paged(phydev, MII_MARVELL_MSCR_PAGE,
+			       MII_88E1510_MSCR_2, BMCR_SPEED1000 |
+			       BMCR_SPEED100, mscr2_ctl);
+	if (err < 0)
+		return err;
 
-		if (!err) {
-			/* It takes some time for PHY device to switch
-			 * into/out-of loopback mode.
-			 */
-			msleep(1000);
-		}
+	/* Need soft reset to have speed configuration takes effect */
+	err = genphy_soft_reset(phydev);
+	if (err < 0)
 		return err;
-	} else {
-		err = phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK, 0);
-		if (err < 0)
-			return err;
 
-		return phy_config_aneg(phydev);
+	err = phy_modify(phydev, MII_BMCR, BMCR_LOOPBACK,
+			 BMCR_LOOPBACK);
+
+	if (!err) {
+		/*
+		 * It takes some time for PHY device to switch into loopback
+		 * mode.
+		 */
+		msleep(1000);
 	}
+	return err;
 }
 
 static int marvell_vct5_wait_complete(struct phy_device *phydev)

From 163d744d020e0d2106b5560f67557ffbbacd86ef Mon Sep 17 00:00:00 2001
From: Gerhard Engleder <gerhard@engleder-embedded.com>
Date: Wed, 12 Mar 2025 21:30:10 +0100
Subject: [PATCH 2364/2753] tsnep: Select speed for loopback

Use 100 Mbps only if the PHY is configured to this speed. Otherwise use
always the maximum speed of 1000 Mbps.

Also remove explicit setting of carrier on and link mode after loopback.
This is not needed anymore, because phy_loopback() with selected speed
signals the link and the speed to the MAC.

Signed-off-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250312203010.47429-6-gerhard@engleder-embedded.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/engleder/tsnep_main.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/engleder/tsnep_main.c b/drivers/net/ethernet/engleder/tsnep_main.c
index 7a9fe0719f8cc..625245b0845c7 100644
--- a/drivers/net/ethernet/engleder/tsnep_main.c
+++ b/drivers/net/ethernet/engleder/tsnep_main.c
@@ -221,20 +221,19 @@ static void tsnep_phy_link_status_change(struct net_device *netdev)
 
 static int tsnep_phy_loopback(struct tsnep_adapter *adapter, bool enable)
 {
-	int retval;
-
-	retval = phy_loopback(adapter->phydev, enable, 0);
+	int speed;
 
-	/* PHY link state change is not signaled if loopback is enabled, it
-	 * would delay a working loopback anyway, let's ensure that loopback
-	 * is working immediately by setting link mode directly
-	 */
-	if (!retval && enable) {
-		netif_carrier_on(adapter->netdev);
-		tsnep_set_link_mode(adapter);
+	if (enable) {
+		if (adapter->phydev->autoneg == AUTONEG_DISABLE &&
+		    adapter->phydev->speed == SPEED_100)
+			speed = SPEED_100;
+		else
+			speed = SPEED_1000;
+	} else {
+		speed = 0;
 	}
 
-	return retval;
+	return phy_loopback(adapter->phydev, enable, speed);
 }
 
 static int tsnep_phy_open(struct tsnep_adapter *adapter)

From 5eada2aabf13dcc4574b0a281b963b8cc55a52cc Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 12 Mar 2025 15:15:50 -0700
Subject: [PATCH 2365/2753] igb: reject invalid external timestamp requests for
 82580-based HW

The igb_ptp_feature_enable_82580 function correctly checks that unknown
flags are not passed to the function. However, it does not actually check
PTP_RISING_EDGE or PTP_FALLING_EDGE when configuring the external timestamp
function.

The data sheet for the 82580 product says:

  Upon a change in the input level of one of the SDP pins that was
  configured to detect Time stamp events using the TSSDP register, a time
  stamp of the system time is captured into one of the two auxiliary time
  stamp registers (AUXSTMPL/H0 or AUXSTMPL/H1).

  For example to define timestamping of events in the AUXSTMPL0 and
  AUXSTMPH0 registers, Software should:

  1. Set the TSSDP.AUX0_SDP_SEL field to select the SDP pin that detects
     the level change and set the TSSDP.AUX0_TS_SDP_EN bit to 1.

  2. Set the TSAUXC.EN_TS0 bit to 1 to enable timestamping

The same paragraph is in the i350 and i354 data sheets.

The wording implies that the time stamps are captured at any level change.
There does not appear to be any way to only timestamp one edge of the
signal.

Reject requests which do not set both PTP_RISING_EDGE and PTP_FALLING_EDGE
when operating under PTP_STRICT_FLAGS mode via PTP_EXTTS_REQUEST2.

Fixes: 38970eac41db ("igb: support EXTTS on 82580/i354/i350")
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-jk-net-fixes-supported-extts-flags-v2-1-ea930ba82459@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/intel/igb/igb_ptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index f945705561200..f323e1c1989f1 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -509,6 +509,12 @@ static int igb_ptp_feature_enable_82580(struct ptp_clock_info *ptp,
 					PTP_STRICT_FLAGS))
 			return -EOPNOTSUPP;
 
+		/* Both the rising and falling edge are timestamped */
+		if (rq->extts.flags & PTP_STRICT_FLAGS &&
+		    (rq->extts.flags & PTP_ENABLE_FEATURE) &&
+		    (rq->extts.flags & PTP_EXTTS_EDGES) != PTP_EXTTS_EDGES)
+			return -EOPNOTSUPP;
+
 		if (on) {
 			pin = ptp_find_pin(igb->ptp_clock, PTP_PF_EXTTS,
 					   rq->extts.index);

From 51d58c0c7921d3c93c44099b90dc46720d095bde Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 12 Mar 2025 15:15:51 -0700
Subject: [PATCH 2366/2753] renesas: reject PTP_STRICT_FLAGS as unsupported
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ravb_ptp_extts() function checks the flags coming from the
PTP_EXTTS_REQUEST ioctl, to ensure that future flags are not accepted on
accident.

This was updated to 'honor' the PTP_STRICT_FLAGS in commit 6138e687c7b6
("ptp: Introduce strict checking of external time stamp options.").
However, the driver does not *actually* validate the flags.

I originally fixed this driver to reject future flags in commit
592025a03b34 ("renesas: reject unsupported external timestamp flags"). It
is still unclear whether this hardware timestamps the rising, falling, or
both edges of the input signal.

Accepting requests with PTP_STRICT_FLAGS is a bug, as this could lead to
users mistakenly assuming a request with PTP_RISING_EDGE actually
timestamps the rising edge only.

Reject requests with PTP_STRICT_FLAGS (and hence all PTP_EXTTS_REQUEST2
requests) until someone with access to the datasheet or hardware knowledge
can confirm the timestamping behavior and update this driver.

Fixes: 6138e687c7b6 ("ptp: Introduce strict checking of external time stamp options.")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-jk-net-fixes-supported-extts-flags-v2-2-ea930ba82459@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/renesas/ravb_ptp.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/renesas/ravb_ptp.c b/drivers/net/ethernet/renesas/ravb_ptp.c
index 6e4ef7af27bf3..b4365906669f3 100644
--- a/drivers/net/ethernet/renesas/ravb_ptp.c
+++ b/drivers/net/ethernet/renesas/ravb_ptp.c
@@ -179,8 +179,7 @@ static int ravb_ptp_extts(struct ptp_clock_info *ptp,
 	/* Reject requests with unsupported flags */
 	if (req->flags & ~(PTP_ENABLE_FEATURE |
 			   PTP_RISING_EDGE |
-			   PTP_FALLING_EDGE |
-			   PTP_STRICT_FLAGS))
+			   PTP_FALLING_EDGE))
 		return -EOPNOTSUPP;
 
 	if (req->index)

From c0b4ddd30871c59043ed3592e6abeee55c3bf045 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 12 Mar 2025 15:15:52 -0700
Subject: [PATCH 2367/2753] net: lan743x: reject unsupported external timestamp
 requests

The lan743x_ptp_io_event_cap_en() function checks that the given request
sets only one of PTP_RISING_EDGE or PTP_FALLING_EDGE, but not both.

However, this driver does not check whether other flags (such as
PTP_EXT_OFF) are set, nor whether any future unrecognized flags are set.

Fix this by adding the appropriate check to the lan743x_ptp_io_extts()
function.

Fixes: 60942c397af6 ("net: lan743x: Add support for PTP-IO Event Input External Timestamp (extts)")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-jk-net-fixes-supported-extts-flags-v2-3-ea930ba82459@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/microchip/lan743x_ptp.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c
index 4a777b449ecd0..0be44dcb33938 100644
--- a/drivers/net/ethernet/microchip/lan743x_ptp.c
+++ b/drivers/net/ethernet/microchip/lan743x_ptp.c
@@ -942,6 +942,12 @@ static int lan743x_ptp_io_extts(struct lan743x_adapter *adapter, int on,
 
 	extts = &ptp->extts[index];
 
+	if (extts_request->flags & ~(PTP_ENABLE_FEATURE |
+				     PTP_RISING_EDGE |
+				     PTP_FALLING_EDGE |
+				     PTP_STRICT_FLAGS))
+		return -EOPNOTSUPP;
+
 	if (on) {
 		extts_pin = ptp_find_pin(ptp->ptp_clock, PTP_PF_EXTTS, index);
 		if (extts_pin < 0)

From af2b428f7992c07b0767c9a3c341b54d9069542e Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 12 Mar 2025 15:15:53 -0700
Subject: [PATCH 2368/2753] broadcom: fix supported flag check in periodic
 output function

In bcm_ptp_perout_locked, the driver rejects requests which have
PTP_PEROUT_PHASE set. This appears to be an attempt to reject any
unsupported flags. Unfortunately, this only checks one flag, but does not
protect against PTP_PEROUT_ONE_SHOT, or any future flags which may be
added.

Fix the check to ensure that no flag other than the supported
PTP_PEROUT_DUTY_CYCLE is set.

Fixes: 7bfe91efd525 ("net: phy: Add support for 1PPS out and external timestamps")
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-jk-net-fixes-supported-extts-flags-v2-4-ea930ba82459@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/bcm-phy-ptp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/bcm-phy-ptp.c b/drivers/net/phy/bcm-phy-ptp.c
index 208e8f561e069..eba8b5fb1365f 100644
--- a/drivers/net/phy/bcm-phy-ptp.c
+++ b/drivers/net/phy/bcm-phy-ptp.c
@@ -597,7 +597,8 @@ static int bcm_ptp_perout_locked(struct bcm_ptp_private *priv,
 
 	period = BCM_MAX_PERIOD_8NS;	/* write nonzero value */
 
-	if (req->flags & PTP_PEROUT_PHASE)
+	/* Reject unsupported flags */
+	if (req->flags & ~PTP_PEROUT_DUTY_CYCLE)
 		return -EOPNOTSUPP;
 
 	if (req->flags & PTP_PEROUT_DUTY_CYCLE)

From 8dcfc910a81d8b53f59f8b23211e81f2a91f84f9 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Wed, 12 Mar 2025 15:15:54 -0700
Subject: [PATCH 2369/2753] ptp: ocp: reject unsupported periodic output flags

The ptp_ocp_signal_from_perout() function supports PTP_PEROUT_DUTY_CYCLE
and PTP_PEROUT_PHASE. It does not support PTP_PEROUT_ONE_SHOT, but does not
reject a request with such an unsupported flag.

Add the appropriate check to ensure that unsupported requests are rejected
both for PTP_PEROUT_ONE_SHOT as well as any future flags.

Fixes: 1aa66a3a135a ("ptp: ocp: Program the signal generators via PTP_CLK_REQ_PEROUT")
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250312-jk-net-fixes-supported-extts-flags-v2-5-ea930ba82459@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/ptp/ptp_ocp.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
index 34c616bd0a02f..b25635c5c7453 100644
--- a/drivers/ptp/ptp_ocp.c
+++ b/drivers/ptp/ptp_ocp.c
@@ -2090,6 +2090,10 @@ ptp_ocp_signal_from_perout(struct ptp_ocp *bp, int gen,
 {
 	struct ptp_ocp_signal s = { };
 
+	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
+			   PTP_PEROUT_PHASE))
+		return -EOPNOTSUPP;
+
 	s.polarity = bp->signal[gen].polarity;
 	s.period = ktime_set(req->period.sec, req->period.nsec);
 	if (!s.period)

From 27b918007d96402aba10ed52a6af8015230f1793 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 13 Mar 2025 03:06:57 -0700
Subject: [PATCH 2370/2753] net: vlan: don't propagate flags on open

With the device instance lock, there is now a possibility of a deadlock:

[    1.211455] ============================================
[    1.211571] WARNING: possible recursive locking detected
[    1.211687] 6.14.0-rc5-01215-g032756b4ca7a-dirty #5 Not tainted
[    1.211823] --------------------------------------------
[    1.211936] ip/184 is trying to acquire lock:
[    1.212032] ffff8881024a4c30 (&dev->lock){+.+.}-{4:4}, at: dev_set_allmulti+0x4e/0xb0
[    1.212207]
[    1.212207] but task is already holding lock:
[    1.212332] ffff8881024a4c30 (&dev->lock){+.+.}-{4:4}, at: dev_open+0x50/0xb0
[    1.212487]
[    1.212487] other info that might help us debug this:
[    1.212626]  Possible unsafe locking scenario:
[    1.212626]
[    1.212751]        CPU0
[    1.212815]        ----
[    1.212871]   lock(&dev->lock);
[    1.212944]   lock(&dev->lock);
[    1.213016]
[    1.213016]  *** DEADLOCK ***
[    1.213016]
[    1.213143]  May be due to missing lock nesting notation
[    1.213143]
[    1.213294] 3 locks held by ip/184:
[    1.213371]  #0: ffffffff838b53e0 (rtnl_mutex){+.+.}-{4:4}, at: rtnl_nets_lock+0x1b/0xa0
[    1.213543]  #1: ffffffff84e5fc70 (&net->rtnl_mutex){+.+.}-{4:4}, at: rtnl_nets_lock+0x37/0xa0
[    1.213727]  #2: ffff8881024a4c30 (&dev->lock){+.+.}-{4:4}, at: dev_open+0x50/0xb0
[    1.213895]
[    1.213895] stack backtrace:
[    1.213991] CPU: 0 UID: 0 PID: 184 Comm: ip Not tainted 6.14.0-rc5-01215-g032756b4ca7a-dirty #5
[    1.213993] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Arch Linux 1.16.3-1-1 04/01/2014
[    1.213994] Call Trace:
[    1.213995]  <TASK>
[    1.213996]  dump_stack_lvl+0x8e/0xd0
[    1.214000]  print_deadlock_bug+0x28b/0x2a0
[    1.214020]  lock_acquire+0xea/0x2a0
[    1.214027]  __mutex_lock+0xbf/0xd40
[    1.214038]  dev_set_allmulti+0x4e/0xb0 # real_dev->flags & IFF_ALLMULTI
[    1.214040]  vlan_dev_open+0xa5/0x170 # ndo_open on vlandev
[    1.214042]  __dev_open+0x145/0x270
[    1.214046]  __dev_change_flags+0xb0/0x1e0
[    1.214051]  netif_change_flags+0x22/0x60 # IFF_UP vlandev
[    1.214053]  dev_change_flags+0x61/0xb0 # for each device in group from dev->vlan_info
[    1.214055]  vlan_device_event+0x766/0x7c0 # on netdevsim0
[    1.214058]  notifier_call_chain+0x78/0x120
[    1.214062]  netif_open+0x6d/0x90
[    1.214064]  dev_open+0x5b/0xb0 # locks netdevsim0
[    1.214066]  bond_enslave+0x64c/0x1230
[    1.214075]  do_set_master+0x175/0x1e0 # on netdevsim0
[    1.214077]  do_setlink+0x516/0x13b0
[    1.214094]  rtnl_newlink+0xaba/0xb80
[    1.214132]  rtnetlink_rcv_msg+0x440/0x490
[    1.214144]  netlink_rcv_skb+0xeb/0x120
[    1.214150]  netlink_unicast+0x1f9/0x320
[    1.214153]  netlink_sendmsg+0x346/0x3f0
[    1.214157]  __sock_sendmsg+0x86/0xb0
[    1.214160]  ____sys_sendmsg+0x1c8/0x220
[    1.214164]  ___sys_sendmsg+0x28f/0x2d0
[    1.214179]  __x64_sys_sendmsg+0xef/0x140
[    1.214184]  do_syscall_64+0xec/0x1d0
[    1.214190]  entry_SYSCALL_64_after_hwframe+0x77/0x7f
[    1.214191] RIP: 0033:0x7f2d1b4a7e56

Device setup:

     netdevsim0 (down)
     ^        ^
  bond        netdevsim1.100@netdevsim1 allmulticast=on (down)

When we enslave the lower device (netdevsim0) which has a vlan, we
propagate vlan's allmuti/promisc flags during ndo_open. This causes
(re)locking on of the real_dev.

Propagate allmulti/promisc on flags change, not on the open. There
is a slight semantics change that vlans that are down now propagate
the flags, but this seems unlikely to result in the real issues.

Reproducer:

  echo 0 1 > /sys/bus/netdevsim/new_device

  dev_path=$(ls -d /sys/bus/netdevsim/devices/netdevsim0/net/*)
  dev=$(echo $dev_path | rev | cut -d/ -f1 | rev)

  ip link set dev $dev name netdevsim0
  ip link set dev netdevsim0 up

  ip link add link netdevsim0 name netdevsim0.100 type vlan id 100
  ip link set dev netdevsim0.100 allmulticast on down
  ip link add name bond1 type bond mode 802.3ad
  ip link set dev netdevsim0 down
  ip link set dev netdevsim0 master bond1
  ip link set dev bond1 up
  ip link show

Reported-by: syzbot+b0c03d76056ef6cd12a6@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/Z9CfXjLMKn6VLG5d@mini-arch/T/#m15ba130f53227c883e79fb969687d69d670337a0
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313100657.2287455-1-sdf@fomichev.me
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/8021q/vlan_dev.c | 31 ++++---------------------------
 1 file changed, 4 insertions(+), 27 deletions(-)

diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index 770a4dcf7f634..fbf296137b094 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -274,17 +274,6 @@ static int vlan_dev_open(struct net_device *dev)
 			goto out;
 	}
 
-	if (dev->flags & IFF_ALLMULTI) {
-		err = dev_set_allmulti(real_dev, 1);
-		if (err < 0)
-			goto del_unicast;
-	}
-	if (dev->flags & IFF_PROMISC) {
-		err = dev_set_promiscuity(real_dev, 1);
-		if (err < 0)
-			goto clear_allmulti;
-	}
-
 	ether_addr_copy(vlan->real_dev_addr, real_dev->dev_addr);
 
 	if (vlan->flags & VLAN_FLAG_GVRP)
@@ -298,12 +287,6 @@ static int vlan_dev_open(struct net_device *dev)
 		netif_carrier_on(dev);
 	return 0;
 
-clear_allmulti:
-	if (dev->flags & IFF_ALLMULTI)
-		dev_set_allmulti(real_dev, -1);
-del_unicast:
-	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
-		dev_uc_del(real_dev, dev->dev_addr);
 out:
 	netif_carrier_off(dev);
 	return err;
@@ -316,10 +299,6 @@ static int vlan_dev_stop(struct net_device *dev)
 
 	dev_mc_unsync(real_dev, dev);
 	dev_uc_unsync(real_dev, dev);
-	if (dev->flags & IFF_ALLMULTI)
-		dev_set_allmulti(real_dev, -1);
-	if (dev->flags & IFF_PROMISC)
-		dev_set_promiscuity(real_dev, -1);
 
 	if (!ether_addr_equal(dev->dev_addr, real_dev->dev_addr))
 		dev_uc_del(real_dev, dev->dev_addr);
@@ -489,12 +468,10 @@ static void vlan_dev_change_rx_flags(struct net_device *dev, int change)
 {
 	struct net_device *real_dev = vlan_dev_priv(dev)->real_dev;
 
-	if (dev->flags & IFF_UP) {
-		if (change & IFF_ALLMULTI)
-			dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
-		if (change & IFF_PROMISC)
-			dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
-	}
+	if (change & IFF_ALLMULTI)
+		dev_set_allmulti(real_dev, dev->flags & IFF_ALLMULTI ? 1 : -1);
+	if (change & IFF_PROMISC)
+		dev_set_promiscuity(real_dev, dev->flags & IFF_PROMISC ? 1 : -1);
 }
 
 static void vlan_dev_set_rx_mode(struct net_device *vlan_dev)

From b97d6b6820279c84d67d5e870d87ce45e8e348a5 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Thu, 13 Mar 2025 11:20:50 +0100
Subject: [PATCH 2371/2753] mptcp: pm: split netlink and in-kernel init

The registration of mptcp_genl_family is useful for both the in-kernel
and the userspace PM. It should then be done in pm_netlink.c.

On the other hand, the registration of the in-kernel pernet subsystem is
specific to the in-kernel PM, and should stay there in pm_kernel.c.

Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-1-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c         | 1 +
 net/mptcp/pm_kernel.c  | 5 +----
 net/mptcp/pm_netlink.c | 6 ++++++
 net/mptcp/protocol.h   | 1 +
 4 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 833839d7286e7..8e6a325a38980 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1022,5 +1022,6 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 
 void __init mptcp_pm_init(void)
 {
+	mptcp_pm_kernel_register();
 	mptcp_pm_nl_init();
 }
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index daf8f98a31643..62ae68abb2cb0 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -1400,11 +1400,8 @@ static struct pernet_operations mptcp_pm_pernet_ops = {
 	.size = sizeof(struct pm_nl_pernet),
 };
 
-void __init mptcp_pm_nl_init(void)
+void __init mptcp_pm_kernel_register(void)
 {
 	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
 		panic("Failed to register MPTCP PM pernet subsystem.\n");
-
-	if (genl_register_family(&mptcp_genl_family))
-		panic("Failed to register MPTCP PM netlink family\n");
 }
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index b2e5bbdcd5df9..50aaf259959ae 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -625,3 +625,9 @@ struct genl_family mptcp_genl_family __ro_after_init = {
 	.mcgrps		= mptcp_pm_mcgrps,
 	.n_mcgrps	= ARRAY_SIZE(mptcp_pm_mcgrps),
 };
+
+void __init mptcp_pm_nl_init(void)
+{
+	if (genl_register_family(&mptcp_genl_family))
+		panic("Failed to register MPTCP PM netlink family\n");
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c51b6a22d5e09..ffb70fe081818 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1147,6 +1147,7 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 	return local_id;
 }
 
+void __init mptcp_pm_kernel_register(void);
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_worker(struct mptcp_sock *msk);
 void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);

From fa123489e7ef5c5c26d530bc4d7411bca7253c69 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:51 +0100
Subject: [PATCH 2372/2753] mptcp: pm: in-kernel: use kmemdup helper

Instead of using kmalloc() or kzalloc() to allocate an entry and
then immediately duplicate another entry to the newly allocated
one, kmemdup() helper can be used to simplify the code.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-2-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm_kernel.c | 6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 62ae68abb2cb0..806a9b5b3c07a 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -710,11 +710,10 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk,
 		return ret;
 
 	/* address not found, add to local list */
-	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
+	entry = kmemdup(skc, sizeof(*skc), GFP_ATOMIC);
 	if (!entry)
 		return -ENOMEM;
 
-	*entry = *skc;
 	entry->addr.port = 0;
 	ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true, false);
 	if (ret < 0)
@@ -817,13 +816,12 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
 		return -EINVAL;
 	}
 
-	entry = kzalloc(sizeof(*entry), GFP_KERNEL_ACCOUNT);
+	entry = kmemdup(&addr, sizeof(addr), GFP_KERNEL_ACCOUNT);
 	if (!entry) {
 		GENL_SET_ERR_MSG(info, "can't allocate addr");
 		return -ENOMEM;
 	}
 
-	*entry = addr;
 	if (entry->addr.port) {
 		ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry);
 		if (ret) {

From 5fff36b69cd4031ddb97325d1bfbff1c20e7657c Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:52 +0100
Subject: [PATCH 2373/2753] mptcp: pm: use pm variable instead of msk->pm

The variable "pm" has been defined in mptcp_pm_fully_established()
and mptcp_pm_data_reset() as "msk->pm", so use "pm" directly instead
of using "msk->pm".

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-3-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 8e6a325a38980..04a156395aadd 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -511,13 +511,13 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
 	 * be sure to serve this event only once.
 	 */
 	if (READ_ONCE(pm->work_pending) &&
-	    !(msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
+	    !(pm->status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)))
 		mptcp_pm_schedule_work(msk, MPTCP_PM_ESTABLISHED);
 
-	if ((msk->pm.status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0)
+	if ((pm->status & BIT(MPTCP_PM_ALREADY_ESTABLISHED)) == 0)
 		announce = true;
 
-	msk->pm.status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
+	pm->status |= BIT(MPTCP_PM_ALREADY_ESTABLISHED);
 	spin_unlock_bh(&pm->lock);
 
 	if (announce)
@@ -1009,7 +1009,7 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	WRITE_ONCE(pm->addr_signal, 0);
 	WRITE_ONCE(pm->remote_deny_join_id0, false);
 	pm->status = 0;
-	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	bitmap_fill(pm->id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 }
 
 void mptcp_pm_data_init(struct mptcp_sock *msk)

From 98a0a99e81b685b94042cdfcd3fe9d7cca225617 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:53 +0100
Subject: [PATCH 2374/2753] mptcp: pm: only fill id_avail_bitmap for in-kernel
 pm

id_avail_bitmap of struct mptcp_pm_data is currently only used by the
in-kernel PM, so this patch moves its initialization operation under
the "if (pm_type == MPTCP_PM_TYPE_KERNEL)" condition.

Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-4-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 04a156395aadd..af009661477b1 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1000,6 +1000,8 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 			   !!mptcp_pm_get_add_addr_accept_max(msk) &&
 			   subflows_allowed);
 		WRITE_ONCE(pm->accept_subflow, subflows_allowed);
+
+		bitmap_fill(pm->id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	} else {
 		WRITE_ONCE(pm->work_pending, 0);
 		WRITE_ONCE(pm->accept_addr, 0);
@@ -1009,7 +1011,6 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	WRITE_ONCE(pm->addr_signal, 0);
 	WRITE_ONCE(pm->remote_deny_join_id0, false);
 	pm->status = 0;
-	bitmap_fill(pm->id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 }
 
 void mptcp_pm_data_init(struct mptcp_sock *msk)

From eff5b1578e99c031f8d33e3f2a972504a3933831 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:54 +0100
Subject: [PATCH 2375/2753] mptcp: pm: add struct_group in mptcp_pm_data

This patch adds a "struct_group(reset, ...)" in struct mptcp_pm_data to
simplify the reset, and make sure we don't miss any.

Suggested-by: Matthieu Baerts <matttbe@kernel.org>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-5-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c       | 13 +------------
 net/mptcp/protocol.h |  5 +++++
 2 files changed, 6 insertions(+), 12 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index af009661477b1..85ee999729a1c 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -978,10 +978,7 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 	u8 pm_type = mptcp_get_pm_type(sock_net((struct sock *)msk));
 	struct mptcp_pm_data *pm = &msk->pm;
 
-	pm->add_addr_signaled = 0;
-	pm->add_addr_accepted = 0;
-	pm->local_addr_used = 0;
-	pm->subflows = 0;
+	memset(&pm->reset, 0, sizeof(pm->reset));
 	pm->rm_list_tx.nr = 0;
 	pm->rm_list_rx.nr = 0;
 	WRITE_ONCE(pm->pm_type, pm_type);
@@ -1002,15 +999,7 @@ void mptcp_pm_data_reset(struct mptcp_sock *msk)
 		WRITE_ONCE(pm->accept_subflow, subflows_allowed);
 
 		bitmap_fill(pm->id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
-	} else {
-		WRITE_ONCE(pm->work_pending, 0);
-		WRITE_ONCE(pm->accept_addr, 0);
-		WRITE_ONCE(pm->accept_subflow, 0);
 	}
-
-	WRITE_ONCE(pm->addr_signal, 0);
-	WRITE_ONCE(pm->remote_deny_join_id0, false);
-	pm->status = 0;
 }
 
 void mptcp_pm_data_init(struct mptcp_sock *msk)
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ffb70fe081818..15e2a03025ecb 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -223,6 +223,8 @@ struct mptcp_pm_data {
 
 	spinlock_t	lock;		/*protects the whole PM data */
 
+	struct_group(reset,
+
 	u8		addr_signal;
 	bool		server_side;
 	bool		work_pending;
@@ -235,6 +237,9 @@ struct mptcp_pm_data {
 	u8		pm_type;
 	u8		subflows;
 	u8		status;
+
+	);
+
 	DECLARE_BITMAP(id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	struct mptcp_rm_list rm_list_tx;
 	struct mptcp_rm_list rm_list_rx;

From 1305b0c22eca7373910f30ec31912796617b7121 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:55 +0100
Subject: [PATCH 2376/2753] mptcp: pm: define struct mptcp_pm_ops

In order to allow users to develop their own BPF-based path manager,
this patch defines a struct ops "mptcp_pm_ops" for an MPTCP path
manager, which contains a set of interfaces. Currently only init()
and release() interfaces are included, subsequent patches will add
others step by step.

Add a set of functions to register, unregister, find and validate a
given path manager struct ops.

"list" is used to add this path manager to mptcp_pm_list list when
it is registered. "name" is used to identify this path manager.
mptcp_pm_find() uses "name" to find a path manager on the list.

mptcp_pm_unregister is not used in this set, but will be invoked in
.unreg of struct bpf_struct_ops. mptcp_pm_validate() will be invoked
in .validate of struct bpf_struct_ops. That's why they are exported.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-6-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/net/mptcp.h  | 12 +++++++++++
 net/mptcp/pm.c       | 50 ++++++++++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.h |  5 +++++
 3 files changed, 67 insertions(+)

diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 2c85ca92bb1c3..645d15695e3f5 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -14,6 +14,7 @@
 
 struct mptcp_info;
 struct mptcp_sock;
+struct mptcp_pm_addr_entry;
 struct seq_file;
 
 /* MPTCP sk_buff extension data */
@@ -121,6 +122,17 @@ struct mptcp_sched_ops {
 	void (*release)(struct mptcp_sock *msk);
 } ____cacheline_aligned_in_smp;
 
+#define MPTCP_PM_NAME_MAX	16
+
+struct mptcp_pm_ops {
+	char			name[MPTCP_PM_NAME_MAX];
+	struct module		*owner;
+	struct list_head	list;
+
+	void (*init)(struct mptcp_sock *msk);
+	void (*release)(struct mptcp_sock *msk);
+} ____cacheline_aligned_in_smp;
+
 #ifdef CONFIG_MPTCP
 void mptcp_init(void);
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 85ee999729a1c..f4948a2cf9be0 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -5,6 +5,8 @@
  */
 #define pr_fmt(fmt) "MPTCP: " fmt
 
+#include <linux/rculist.h>
+#include <linux/spinlock.h>
 #include "protocol.h"
 #include "mib.h"
 
@@ -18,6 +20,9 @@ struct mptcp_pm_add_entry {
 	struct mptcp_sock	*sock;
 };
 
+static DEFINE_SPINLOCK(mptcp_pm_list_lock);
+static LIST_HEAD(mptcp_pm_list);
+
 /* path manager helpers */
 
 /* if sk is ipv4 or ipv6_only allows only same-family local and remote addresses,
@@ -1015,3 +1020,48 @@ void __init mptcp_pm_init(void)
 	mptcp_pm_kernel_register();
 	mptcp_pm_nl_init();
 }
+
+/* Must be called with rcu read lock held */
+struct mptcp_pm_ops *mptcp_pm_find(const char *name)
+{
+	struct mptcp_pm_ops *pm_ops;
+
+	list_for_each_entry_rcu(pm_ops, &mptcp_pm_list, list) {
+		if (!strcmp(pm_ops->name, name))
+			return pm_ops;
+	}
+
+	return NULL;
+}
+
+int mptcp_pm_validate(struct mptcp_pm_ops *pm_ops)
+{
+	return 0;
+}
+
+int mptcp_pm_register(struct mptcp_pm_ops *pm_ops)
+{
+	int ret;
+
+	ret = mptcp_pm_validate(pm_ops);
+	if (ret)
+		return ret;
+
+	spin_lock(&mptcp_pm_list_lock);
+	if (mptcp_pm_find(pm_ops->name)) {
+		spin_unlock(&mptcp_pm_list_lock);
+		return -EEXIST;
+	}
+	list_add_tail_rcu(&pm_ops->list, &mptcp_pm_list);
+	spin_unlock(&mptcp_pm_list_lock);
+
+	pr_debug("%s registered\n", pm_ops->name);
+	return 0;
+}
+
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops)
+{
+	spin_lock(&mptcp_pm_list_lock);
+	list_del_rcu(&pm_ops->list);
+	spin_unlock(&mptcp_pm_list_lock);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 15e2a03025ecb..ac8a178426e4e 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1050,6 +1050,11 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
 				struct mptcp_pm_addr_entry *entry);
 
+struct mptcp_pm_ops *mptcp_pm_find(const char *name);
+int mptcp_pm_register(struct mptcp_pm_ops *pm_ops);
+void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops);
+int mptcp_pm_validate(struct mptcp_pm_ops *pm_ops);
+
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 
 void mptcp_event(enum mptcp_event_type type, const struct mptcp_sock *msk,

From 770170b418106fe152160510715fe5f8e601509c Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:56 +0100
Subject: [PATCH 2377/2753] mptcp: pm: register in-kernel and userspace PM

This patch defines the original in-kernel netlink path manager as a
new struct mptcp_pm_ops named "mptcp_pm_kernel", and register it in
mptcp_pm_kernel_register(). And define the userspace path manager as
a new struct mptcp_pm_ops named "mptcp_pm_userspace", and register it
in mptcp_pm_init().

To ensure that there's always a valid path manager available, the default
path manager "mptcp_pm_kernel" will be skipped in mptcp_pm_unregister().

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-7-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/pm.c           |  5 +++++
 net/mptcp/pm_kernel.c    |  7 +++++++
 net/mptcp/pm_userspace.c | 10 ++++++++++
 net/mptcp/protocol.h     |  4 ++++
 4 files changed, 26 insertions(+)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index f4948a2cf9be0..3896f21a46bd7 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1018,6 +1018,7 @@ void mptcp_pm_data_init(struct mptcp_sock *msk)
 void __init mptcp_pm_init(void)
 {
 	mptcp_pm_kernel_register();
+	mptcp_pm_userspace_register();
 	mptcp_pm_nl_init();
 }
 
@@ -1061,6 +1062,10 @@ int mptcp_pm_register(struct mptcp_pm_ops *pm_ops)
 
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops)
 {
+	/* skip unregistering the default path manager */
+	if (WARN_ON_ONCE(pm_ops == &mptcp_pm_kernel))
+		return;
+
 	spin_lock(&mptcp_pm_list_lock);
 	list_del_rcu(&pm_ops->list);
 	spin_unlock(&mptcp_pm_list_lock);
diff --git a/net/mptcp/pm_kernel.c b/net/mptcp/pm_kernel.c
index 806a9b5b3c07a..d39e7c1784608 100644
--- a/net/mptcp/pm_kernel.c
+++ b/net/mptcp/pm_kernel.c
@@ -1398,8 +1398,15 @@ static struct pernet_operations mptcp_pm_pernet_ops = {
 	.size = sizeof(struct pm_nl_pernet),
 };
 
+struct mptcp_pm_ops mptcp_pm_kernel = {
+	.name			= "kernel",
+	.owner			= THIS_MODULE,
+};
+
 void __init mptcp_pm_kernel_register(void)
 {
 	if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0)
 		panic("Failed to register MPTCP PM pernet subsystem.\n");
+
+	mptcp_pm_register(&mptcp_pm_kernel);
 }
diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
index 13856df226736..2cb62f026b1f4 100644
--- a/net/mptcp/pm_userspace.c
+++ b/net/mptcp/pm_userspace.c
@@ -682,3 +682,13 @@ int mptcp_userspace_pm_get_addr(u8 id, struct mptcp_pm_addr_entry *addr,
 	sock_put(sk);
 	return ret;
 }
+
+static struct mptcp_pm_ops mptcp_pm_userspace = {
+	.name			= "userspace",
+	.owner			= THIS_MODULE,
+};
+
+void __init mptcp_pm_userspace_register(void)
+{
+	mptcp_pm_register(&mptcp_pm_userspace);
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index ac8a178426e4e..c9e435a1fd7c7 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1050,6 +1050,9 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 void mptcp_pm_remove_addr_entry(struct mptcp_sock *msk,
 				struct mptcp_pm_addr_entry *entry);
 
+/* the default path manager, used in mptcp_pm_unregister */
+extern struct mptcp_pm_ops mptcp_pm_kernel;
+
 struct mptcp_pm_ops *mptcp_pm_find(const char *name);
 int mptcp_pm_register(struct mptcp_pm_ops *pm_ops);
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops);
@@ -1158,6 +1161,7 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 }
 
 void __init mptcp_pm_kernel_register(void);
+void __init mptcp_pm_userspace_register(void);
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_worker(struct mptcp_sock *msk);
 void __mptcp_pm_kernel_worker(struct mptcp_sock *msk);

From 595c26d122d120b6b2f65495e31c857d0c8c6374 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:57 +0100
Subject: [PATCH 2378/2753] mptcp: sysctl: set path manager by name

Similar to net.mptcp.scheduler, a new net.mptcp.path_manager sysctl knob
is added to determine which path manager will be used by each newly
created MPTCP socket by setting the name of it.

Dealing with an explicit name is easier than with a number, especially
when more PMs will be introduced.

This sysctl knob makes the old one "pm_type" deprecated.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-8-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/mptcp-sysctl.rst | 19 +++++++++
 net/mptcp/ctrl.c                          | 50 +++++++++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 3 files changed, 70 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 03e1d3610333e..b78a2254d4523 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -72,6 +72,23 @@ enabled - BOOLEAN
 
 	Default: 1 (enabled)
 
+path_manager - STRING
+	Set the default path manager name to use for each new MPTCP
+	socket. In-kernel path management will control subflow
+	connections and address advertisements according to
+	per-namespace values configured over the MPTCP netlink
+	API. Userspace path management puts per-MPTCP-connection subflow
+	connection decisions and address advertisements under control of
+	a privileged userspace program, at the cost of more netlink
+	traffic to propagate all of the related events and commands.
+
+	This is a per-namespace sysctl.
+
+	* "kernel"          - In-kernel path manager
+	* "userspace"       - Userspace path manager
+
+	Default: "kernel"
+
 pm_type - INTEGER
 	Set the default path manager type to use for each new MPTCP
 	socket. In-kernel path management will control subflow
@@ -84,6 +101,8 @@ pm_type - INTEGER
 
 	This is a per-namespace sysctl.
 
+	Deprecated since v6.15, use path_manager instead.
+
 	* 0 - In-kernel path manager
 	* 1 - Userspace path manager
 
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index be6c0237e10bf..4209dc7f97048 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -39,6 +39,7 @@ struct mptcp_pernet {
 	u8 allow_join_initial_addr_port;
 	u8 pm_type;
 	char scheduler[MPTCP_SCHED_NAME_MAX];
+	char path_manager[MPTCP_PM_NAME_MAX];
 };
 
 static struct mptcp_pernet *mptcp_get_pernet(const struct net *net)
@@ -83,6 +84,11 @@ int mptcp_get_pm_type(const struct net *net)
 	return mptcp_get_pernet(net)->pm_type;
 }
 
+const char *mptcp_get_path_manager(const struct net *net)
+{
+	return mptcp_get_pernet(net)->path_manager;
+}
+
 const char *mptcp_get_scheduler(const struct net *net)
 {
 	return mptcp_get_pernet(net)->scheduler;
@@ -101,6 +107,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->stale_loss_cnt = 4;
 	pernet->pm_type = MPTCP_PM_TYPE_KERNEL;
 	strscpy(pernet->scheduler, "default", sizeof(pernet->scheduler));
+	strscpy(pernet->path_manager, "kernel", sizeof(pernet->path_manager));
 }
 
 #ifdef CONFIG_SYSCTL
@@ -174,6 +181,42 @@ static int proc_blackhole_detect_timeout(const struct ctl_table *table,
 	return ret;
 }
 
+static int mptcp_set_path_manager(char *path_manager, const char *name)
+{
+	struct mptcp_pm_ops *pm_ops;
+	int ret = 0;
+
+	rcu_read_lock();
+	pm_ops = mptcp_pm_find(name);
+	if (pm_ops)
+		strscpy(path_manager, name, MPTCP_PM_NAME_MAX);
+	else
+		ret = -ENOENT;
+	rcu_read_unlock();
+
+	return ret;
+}
+
+static int proc_path_manager(const struct ctl_table *ctl, int write,
+			     void *buffer, size_t *lenp, loff_t *ppos)
+{
+	char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data;
+	char pm_name[MPTCP_PM_NAME_MAX];
+	const struct ctl_table tbl = {
+		.data = pm_name,
+		.maxlen = MPTCP_PM_NAME_MAX,
+	};
+	int ret;
+
+	strscpy(pm_name, *path_manager, MPTCP_PM_NAME_MAX);
+
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		ret = mptcp_set_path_manager(*path_manager, pm_name);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -253,6 +296,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_dou8vec_minmax,
 	},
+	{
+		.procname = "path_manager",
+		.maxlen	= MPTCP_PM_NAME_MAX,
+		.mode = 0644,
+		.proc_handler = proc_path_manager,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -278,6 +327,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[8].data = &pernet->close_timeout;
 	table[9].data = &pernet->blackhole_timeout;
 	table[10].data = &pernet->syn_retrans_before_tcp_fallback;
+	table[11].data = &pernet->path_manager;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index c9e435a1fd7c7..818c2c648677c 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -699,6 +699,7 @@ int mptcp_allow_join_id0(const struct net *net);
 unsigned int mptcp_stale_loss_cnt(const struct net *net);
 unsigned int mptcp_close_timeout(const struct sock *sk);
 int mptcp_get_pm_type(const struct net *net);
+const char *mptcp_get_path_manager(const struct net *net);
 const char *mptcp_get_scheduler(const struct net *net);
 
 void mptcp_active_disable(struct sock *sk);

From 573b653401a8fa9bf61c281fa922e42f1e5c51e6 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:58 +0100
Subject: [PATCH 2379/2753] mptcp: sysctl: map path_manager to pm_type

This patch maps the newly added path manager sysctl "path_manager"
to the old one "pm_type".

	path_manager   pm_type

	"kernel"    -> MPTCP_PM_TYPE_KERNEL
	"userspace" -> MPTCP_PM_TYPE_USERSPACE
	others      -> __MPTCP_PM_TYPE_NR

It is important to add this to keep a compatibility with the now
deprecated pm_type sysctl knob.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-9-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/ctrl.c | 15 ++++++++++++++-
 1 file changed, 14 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 4209dc7f97048..cb0811e636ff2 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -200,6 +200,9 @@ static int mptcp_set_path_manager(char *path_manager, const char *name)
 static int proc_path_manager(const struct ctl_table *ctl, int write,
 			     void *buffer, size_t *lenp, loff_t *ppos)
 {
+	struct mptcp_pernet *pernet = container_of(ctl->data,
+						   struct mptcp_pernet,
+						   path_manager);
 	char (*path_manager)[MPTCP_PM_NAME_MAX] = ctl->data;
 	char pm_name[MPTCP_PM_NAME_MAX];
 	const struct ctl_table tbl = {
@@ -211,8 +214,18 @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
 	strscpy(pm_name, *path_manager, MPTCP_PM_NAME_MAX);
 
 	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
-	if (write && ret == 0)
+	if (write && ret == 0) {
 		ret = mptcp_set_path_manager(*path_manager, pm_name);
+		if (ret == 0) {
+			u8 pm_type = __MPTCP_PM_TYPE_NR;
+
+			if (strncmp(pm_name, "kernel", MPTCP_PM_NAME_MAX) == 0)
+				pm_type = MPTCP_PM_TYPE_KERNEL;
+			else if (strncmp(pm_name, "userspace", MPTCP_PM_NAME_MAX) == 0)
+				pm_type = MPTCP_PM_TYPE_USERSPACE;
+			pernet->pm_type = pm_type;
+		}
+	}
 
 	return ret;
 }

From 7982ed0edda3379e17c9cfe64e761af34ef63546 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:20:59 +0100
Subject: [PATCH 2380/2753] mptcp: sysctl: map pm_type to path_manager

This patch adds a new proc_handler "proc_pm_type" for "pm_type" to
map old path manager sysctl "pm_type" to the newly added "path_manager".

	path_manager		   pm_type

	MPTCP_PM_TYPE_KERNEL    -> "kernel"
	MPTCP_PM_TYPE_USERSPACE -> "userspace"

It is important to add this to keep a compatibility with the now
deprecated pm_type sysctl knob.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-10-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/ctrl.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index cb0811e636ff2..4d8b31f32eb50 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -230,6 +230,29 @@ static int proc_path_manager(const struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_pm_type(const struct ctl_table *ctl, int write,
+			void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct mptcp_pernet *pernet = container_of(ctl->data,
+						   struct mptcp_pernet,
+						   pm_type);
+	int ret;
+
+	ret = proc_dou8vec_minmax(ctl, write, buffer, lenp, ppos);
+	if (write && ret == 0) {
+		u8 pm_type = READ_ONCE(*(u8 *)ctl->data);
+		char *pm_name = "";
+
+		if (pm_type == MPTCP_PM_TYPE_KERNEL)
+			pm_name = "kernel";
+		else if (pm_type == MPTCP_PM_TYPE_USERSPACE)
+			pm_name = "userspace";
+		mptcp_set_path_manager(pernet->path_manager, pm_name);
+	}
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -274,7 +297,7 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.procname = "pm_type",
 		.maxlen = sizeof(u8),
 		.mode = 0644,
-		.proc_handler = proc_dou8vec_minmax,
+		.proc_handler = proc_pm_type,
 		.extra1       = SYSCTL_ZERO,
 		.extra2       = &mptcp_pm_type_max
 	},

From fa3ee9dd8067e178b459f1df3081fd25fc03c4b5 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:21:00 +0100
Subject: [PATCH 2381/2753] mptcp: sysctl: add available_path_managers

Similarly to net.mptcp.available_schedulers, this patch adds a new one
net.mptcp.available_path_managers to list the available path managers.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-11-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 Documentation/networking/mptcp-sysctl.rst |  4 ++++
 include/net/mptcp.h                       |  2 ++
 net/mptcp/ctrl.c                          | 25 +++++++++++++++++++++++
 net/mptcp/pm.c                            | 19 +++++++++++++++++
 net/mptcp/protocol.h                      |  1 +
 5 files changed, 51 insertions(+)

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index b78a2254d4523..5bfab01eff5a9 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -30,6 +30,10 @@ allow_join_initial_addr_port - BOOLEAN
 
 	Default: 1
 
+available_path_managers - STRING
+	Shows the available path managers choices that are registered. More
+	path managers may be available, but not loaded.
+
 available_schedulers - STRING
 	Shows the available schedulers choices that are registered. More packet
 	schedulers may be available, but not loaded.
diff --git a/include/net/mptcp.h b/include/net/mptcp.h
index 645d15695e3f5..bfbad695951cf 100644
--- a/include/net/mptcp.h
+++ b/include/net/mptcp.h
@@ -123,6 +123,8 @@ struct mptcp_sched_ops {
 } ____cacheline_aligned_in_smp;
 
 #define MPTCP_PM_NAME_MAX	16
+#define MPTCP_PM_MAX		128
+#define MPTCP_PM_BUF_MAX	(MPTCP_PM_NAME_MAX * MPTCP_PM_MAX)
 
 struct mptcp_pm_ops {
 	char			name[MPTCP_PM_NAME_MAX];
diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c
index 4d8b31f32eb50..d9290c5bb6c79 100644
--- a/net/mptcp/ctrl.c
+++ b/net/mptcp/ctrl.c
@@ -253,6 +253,24 @@ static int proc_pm_type(const struct ctl_table *ctl, int write,
 	return ret;
 }
 
+static int proc_available_path_managers(const struct ctl_table *ctl,
+					int write, void *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	struct ctl_table tbl = { .maxlen = MPTCP_PM_BUF_MAX, };
+	int ret;
+
+	tbl.data = kmalloc(tbl.maxlen, GFP_USER);
+	if (!tbl.data)
+		return -ENOMEM;
+
+	mptcp_pm_get_available(tbl.data, MPTCP_PM_BUF_MAX);
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	kfree(tbl.data);
+
+	return ret;
+}
+
 static struct ctl_table mptcp_sysctl_table[] = {
 	{
 		.procname = "enabled",
@@ -338,6 +356,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.mode = 0644,
 		.proc_handler = proc_path_manager,
 	},
+	{
+		.procname = "available_path_managers",
+		.maxlen	= MPTCP_PM_BUF_MAX,
+		.mode = 0444,
+		.proc_handler = proc_available_path_managers,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -364,6 +388,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	table[9].data = &pernet->blackhole_timeout;
 	table[10].data = &pernet->syn_retrans_before_tcp_fallback;
 	table[11].data = &pernet->path_manager;
+	/* table[12] is for available_path_managers which is read-only info */
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 3896f21a46bd7..18b19dbccbba7 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -1070,3 +1070,22 @@ void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops)
 	list_del_rcu(&pm_ops->list);
 	spin_unlock(&mptcp_pm_list_lock);
 }
+
+/* Build string with list of available path manager values.
+ * Similar to tcp_get_available_congestion_control()
+ */
+void mptcp_pm_get_available(char *buf, size_t maxlen)
+{
+	struct mptcp_pm_ops *pm_ops;
+	size_t offs = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(pm_ops, &mptcp_pm_list, list) {
+		offs += snprintf(buf + offs, maxlen - offs, "%s%s",
+				 offs == 0 ? "" : " ", pm_ops->name);
+
+		if (WARN_ON_ONCE(offs >= maxlen))
+			break;
+	}
+	rcu_read_unlock();
+}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 818c2c648677c..d409586b5977f 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1058,6 +1058,7 @@ struct mptcp_pm_ops *mptcp_pm_find(const char *name);
 int mptcp_pm_register(struct mptcp_pm_ops *pm_ops);
 void mptcp_pm_unregister(struct mptcp_pm_ops *pm_ops);
 int mptcp_pm_validate(struct mptcp_pm_ops *pm_ops);
+void mptcp_pm_get_available(char *buf, size_t maxlen);
 
 void mptcp_userspace_pm_free_local_addr_list(struct mptcp_sock *msk);
 

From 9cf0128e64ab4ecd46f734d5c9870549cd29053f Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Thu, 13 Mar 2025 11:21:01 +0100
Subject: [PATCH 2382/2753] selftests: mptcp: add pm sysctl mapping tests

This patch checks if the newly added net.mptcp.path_manager is mapped
successfully from or to the old net.mptcp.pm_type in userspace_pm.sh.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250313-net-next-mptcp-pm-ops-intro-v1-12-f4e4a88efc50@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../selftests/net/mptcp/userspace_pm.sh       | 30 ++++++++++++++++++-
 1 file changed, 29 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh
index 3651f73451cf8..333064b0b5ac0 100755
--- a/tools/testing/selftests/net/mptcp/userspace_pm.sh
+++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh
@@ -117,7 +117,36 @@ cleanup()
 trap cleanup EXIT
 
 # Create and configure network namespaces for testing
+print_title "Init"
 mptcp_lib_ns_init ns1 ns2
+
+# check path_manager and pm_type sysctl mapping
+if [ -f /proc/sys/net/mptcp/path_manager ]; then
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=userspace
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.path_manager=error 2>/dev/null
+	pm_type="$(ip netns exec "$ns1" sysctl -n net.mptcp.pm_type)"
+	if [ "${pm_type}" != "1" ]; then
+		test_fail "unexpected pm_type after error: ${pm_type}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+
+	ip netns exec "$ns1" sysctl -q net.mptcp.pm_type=0
+	pm_name="$(ip netns exec "$ns1" sysctl -n net.mptcp.path_manager)"
+	if [ "${pm_name}" != "kernel" ]; then
+		test_fail "unexpected path-manager: ${pm_name}"
+		mptcp_lib_result_print_all_tap
+		exit ${KSFT_FAIL}
+	fi
+fi
+
 for i in "$ns1" "$ns2" ;do
 	ip netns exec "$i" sysctl -q net.mptcp.pm_type=1
 done
@@ -152,7 +181,6 @@ mptcp_lib_events "${ns1}" "${server_evts}" server_evts_pid
 sleep 0.5
 mptcp_lib_subtests_last_ts_reset
 
-print_title "Init"
 print_test "Created network namespaces ns1, ns2"
 test_pass
 

From f3009d0d6ab78053117f8857b921a8237f4d17b3 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Fri, 14 Mar 2025 13:10:57 +0300
Subject: [PATCH 2383/2753] net: atm: fix use after free in lec_send()

The ->send() operation frees skb so save the length before calling
->send() to avoid a use after free.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/c751531d-4af4-42fe-affe-6104b34b791d@stanley.mountain
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/atm/lec.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/atm/lec.c b/net/atm/lec.c
index ffef658862db1..a948dd47c3f34 100644
--- a/net/atm/lec.c
+++ b/net/atm/lec.c
@@ -181,6 +181,7 @@ static void
 lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 {
 	struct net_device *dev = skb->dev;
+	unsigned int len = skb->len;
 
 	ATM_SKB(skb)->vcc = vcc;
 	atm_account_tx(vcc, skb);
@@ -191,7 +192,7 @@ lec_send(struct atm_vcc *vcc, struct sk_buff *skb)
 	}
 
 	dev->stats.tx_packets++;
-	dev->stats.tx_bytes += skb->len;
+	dev->stats.tx_bytes += len;
 }
 
 static void lec_tx_timeout(struct net_device *dev, unsigned int txqueue)

From 47a9b5e52abd2b717dfc8b9460589f89936d93cf Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Fri, 14 Mar 2025 15:57:21 +0530
Subject: [PATCH 2384/2753] net: ti: icssg-prueth: Add lock to stats

Currently the API emac_update_hardware_stats() reads different ICSSG
stats without any lock protection.

This API gets called by .ndo_get_stats64() which is only under RCU
protection and nothing else. Add lock to this API so that the reading of
statistics happens during lock.

Fixes: c1e10d5dc7a1 ("net: ti: icssg-prueth: Add ICSSG Stats")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250314102721.1394366-1-danishanwar@ti.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/ti/icssg/icssg_prueth.c | 1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.h | 2 ++
 drivers/net/ethernet/ti/icssg/icssg_stats.c  | 4 ++++
 3 files changed, 7 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index 00ed978605478..9a75733e3f8fb 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -1679,6 +1679,7 @@ static int prueth_probe(struct platform_device *pdev)
 	}
 
 	spin_lock_init(&prueth->vtbl_lock);
+	spin_lock_init(&prueth->stats_lock);
 	/* setup netdev interfaces */
 	if (eth0_node) {
 		ret = prueth_netdev_init(prueth, eth0_node);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index 329b46e9ee530..f41786b05741f 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -305,6 +305,8 @@ struct prueth {
 	int default_vlan;
 	/** @vtbl_lock: Lock for vtbl in shared memory */
 	spinlock_t vtbl_lock;
+	/** @stats_lock: Lock for reading icssg stats */
+	spinlock_t stats_lock;
 };
 
 struct emac_tx_ts_response {
diff --git a/drivers/net/ethernet/ti/icssg/icssg_stats.c b/drivers/net/ethernet/ti/icssg/icssg_stats.c
index 8800bd3a8d074..6f0edae38ea24 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_stats.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_stats.c
@@ -26,6 +26,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 	u32 val, reg;
 	int i;
 
+	spin_lock(&prueth->stats_lock);
+
 	for (i = 0; i < ARRAY_SIZE(icssg_all_miig_stats); i++) {
 		regmap_read(prueth->miig_rt,
 			    base + icssg_all_miig_stats[i].offset,
@@ -51,6 +53,8 @@ void emac_update_hardware_stats(struct prueth_emac *emac)
 			emac->pa_stats[i] += val;
 		}
 	}
+
+	spin_unlock(&prueth->stats_lock);
 }
 
 void icssg_stats_work_handler(struct work_struct *work)

From 986ffb3a57c5650fb8bf6d59a8f0f07046abfeb6 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:46 +0100
Subject: [PATCH 2385/2753] net: lwtunnel: fix recursion loops

This patch acts as a parachute, catch all solution, by detecting
recursion loops in lwtunnel users and taking care of them (e.g., a loop
between routes, a loop within the same route, etc). In general, such
loops are the consequence of pathological configurations. Each lwtunnel
user is still free to catch such loops early and do whatever they want
with them. It will be the case in a separate patch for, e.g., seg6 and
seg6_local, in order to provide drop reasons and update statistics.
Another example of a lwtunnel user taking care of loops is ioam6, which
has valid use cases that include loops (e.g., inline mode), and which is
addressed by the next patch in this series. Overall, this patch acts as
a last resort to catch loops and drop packets, since we don't want to
leak something unintentionally because of a pathological configuration
in lwtunnels.

The solution in this patch reuses dev_xmit_recursion(),
dev_xmit_recursion_inc(), and dev_xmit_recursion_dec(), which seems fine
considering the context.

Closes: https://lore.kernel.org/netdev/2bc9e2079e864a9290561894d2a602d6@akamai.com/
Closes: https://lore.kernel.org/netdev/Z7NKYMY7fJT5cYWu@shredder/
Fixes: ffce41962ef6 ("lwtunnel: support dst output redirect function")
Fixes: 2536862311d2 ("lwt: Add support to redirect dst.input")
Fixes: 14972cbd34ff ("net: lwtunnel: Handle fragmentation")
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-2-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/lwtunnel.c | 65 ++++++++++++++++++++++++++++++++++++---------
 1 file changed, 53 insertions(+), 12 deletions(-)

diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index 711cd3b4347a7..4417a18b3e951 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -23,6 +23,8 @@
 #include <net/ip6_fib.h>
 #include <net/rtnh.h>
 
+#include "dev.h"
+
 DEFINE_STATIC_KEY_FALSE(nf_hooks_lwtunnel_enabled);
 EXPORT_SYMBOL_GPL(nf_hooks_lwtunnel_enabled);
 
@@ -325,13 +327,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_cmp_encap);
 
 int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
+		goto drop;
+	}
 
-	if (!dst)
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
 		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -341,8 +353,11 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->output))
+	if (likely(ops && ops->output)) {
+		dev_xmit_recursion_inc();
 		ret = ops->output(net, sk, skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
@@ -359,13 +374,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_output);
 
 int lwtunnel_xmit(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
+
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
+		goto drop;
+	}
 
-	if (!dst)
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
 		goto drop;
+	}
 
 	lwtstate = dst->lwtstate;
 
@@ -376,8 +401,11 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->xmit))
+	if (likely(ops && ops->xmit)) {
+		dev_xmit_recursion_inc();
 		ret = ops->xmit(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)
@@ -394,13 +422,23 @@ EXPORT_SYMBOL_GPL(lwtunnel_xmit);
 
 int lwtunnel_input(struct sk_buff *skb)
 {
-	struct dst_entry *dst = skb_dst(skb);
 	const struct lwtunnel_encap_ops *ops;
 	struct lwtunnel_state *lwtstate;
-	int ret = -EINVAL;
+	struct dst_entry *dst;
+	int ret;
 
-	if (!dst)
+	if (dev_xmit_recursion()) {
+		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
+				     __func__);
+		ret = -ENETDOWN;
 		goto drop;
+	}
+
+	dst = skb_dst(skb);
+	if (!dst) {
+		ret = -EINVAL;
+		goto drop;
+	}
 	lwtstate = dst->lwtstate;
 
 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
@@ -410,8 +448,11 @@ int lwtunnel_input(struct sk_buff *skb)
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[lwtstate->type]);
-	if (likely(ops && ops->input))
+	if (likely(ops && ops->input)) {
+		dev_xmit_recursion_inc();
 		ret = ops->input(skb);
+		dev_xmit_recursion_dec();
+	}
 	rcu_read_unlock();
 
 	if (ret == -EOPNOTSUPP)

From 3e7a60b368eadf6c30a4a79dea1eb8f88b6d620d Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:47 +0100
Subject: [PATCH 2386/2753] net: ipv6: ioam6: fix lwtunnel_output() loop

Fix the lwtunnel_output() reentry loop in ioam6_iptunnel when the
destination is the same after transformation. Note that a check on the
destination address was already performed, but it was not enough. This
is the example of a lwtunnel user taking care of loops without relying
only on the last resort detection offered by lwtunnel.

Fixes: 8cb3bf8bff3c ("ipv6: ioam: Add support for the ip6ip6 encapsulation")
Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-3-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ioam6_iptunnel.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ioam6_iptunnel.c b/net/ipv6/ioam6_iptunnel.c
index 2c383c12a4315..09065187378e6 100644
--- a/net/ipv6/ioam6_iptunnel.c
+++ b/net/ipv6/ioam6_iptunnel.c
@@ -337,7 +337,6 @@ static int ioam6_do_encap(struct net *net, struct sk_buff *skb,
 static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 {
 	struct dst_entry *dst = skb_dst(skb), *cache_dst = NULL;
-	struct in6_addr orig_daddr;
 	struct ioam6_lwt *ilwt;
 	int err = -EINVAL;
 	u32 pkt_cnt;
@@ -352,8 +351,6 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (pkt_cnt % ilwt->freq.n >= ilwt->freq.k)
 		goto out;
 
-	orig_daddr = ipv6_hdr(skb)->daddr;
-
 	local_bh_disable();
 	cache_dst = dst_cache_get(&ilwt->cache);
 	local_bh_enable();
@@ -422,7 +419,10 @@ static int ioam6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 			goto drop;
 	}
 
-	if (!ipv6_addr_equal(&orig_daddr, &ipv6_hdr(skb)->daddr)) {
+	/* avoid lwtunnel_output() reentry loop when destination is the same
+	 * after transformation (e.g., with the inline mode)
+	 */
+	if (dst->lwtstate != cache_dst->lwtstate) {
 		skb_dst_drop(skb);
 		skb_dst_set(skb, cache_dst);
 		return dst_output(net, sk, skb);

From 3ed61b8938c66680e13a1d1929afb9b145c26a86 Mon Sep 17 00:00:00 2001
From: Justin Iurman <justin.iurman@uliege.be>
Date: Fri, 14 Mar 2025 13:00:48 +0100
Subject: [PATCH 2387/2753] selftests: net: test for lwtunnel dst ref loops

As recently specified by commit 0ea09cbf8350 ("docs: netdev: add a note
on selftest posting") in net-next, the selftest is therefore shipped in
this series. However, this selftest does not really test this series. It
needs this series to avoid crashing the kernel. What it really tests,
thanks to kmemleak, is what was fixed by the following commits:
- commit c71a192976de ("net: ipv6: fix dst refleaks in rpl, seg6 and
ioam6 lwtunnels")
- commit 92191dd10730 ("net: ipv6: fix dst ref loops in rpl, seg6 and
ioam6 lwtunnels")
- commit c64a0727f9b1 ("net: ipv6: fix dst ref loop on input in seg6
lwt")
- commit 13e55fbaec17 ("net: ipv6: fix dst ref loop on input in rpl
lwt")
- commit 0e7633d7b95b ("net: ipv6: fix dst ref loop in ila lwtunnel")
- commit 5da15a9c11c1 ("net: ipv6: fix missing dst ref drop in ila
lwtunnel")

Signed-off-by: Justin Iurman <justin.iurman@uliege.be>
Link: https://patch.msgid.link/20250314120048.12569-4-justin.iurman@uliege.be
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 +
 tools/testing/selftests/net/config            |   2 +
 .../selftests/net/lwt_dst_cache_ref_loop.sh   | 246 ++++++++++++++++++
 3 files changed, 249 insertions(+)
 create mode 100755 tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 5916f3b81c39f..843ab747645d0 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -101,6 +101,7 @@ TEST_PROGS += vlan_bridge_binding.sh
 TEST_PROGS += bpf_offload.py
 TEST_PROGS += ipv6_route_update_soft_lockup.sh
 TEST_PROGS += busy_poll_test.sh
+TEST_PROGS += lwt_dst_cache_ref_loop.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/config b/tools/testing/selftests/net/config
index 5b9baf7089506..61e5116987f3e 100644
--- a/tools/testing/selftests/net/config
+++ b/tools/testing/selftests/net/config
@@ -107,3 +107,5 @@ CONFIG_XFRM_INTERFACE=m
 CONFIG_XFRM_USER=m
 CONFIG_IP_NF_MATCH_RPFILTER=m
 CONFIG_IP6_NF_MATCH_RPFILTER=m
+CONFIG_IPV6_ILA=m
+CONFIG_IPV6_RPL_LWTUNNEL=y
diff --git a/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh
new file mode 100755
index 0000000000000..881eb399798f7
--- /dev/null
+++ b/tools/testing/selftests/net/lwt_dst_cache_ref_loop.sh
@@ -0,0 +1,246 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0+
+#
+# Author: Justin Iurman <justin.iurman@uliege.be>
+#
+# WARNING
+# -------
+# This is just a dummy script that triggers encap cases with possible dst cache
+# reference loops in affected lwt users (see list below). Some cases are
+# pathological configurations for simplicity, others are valid. Overall, we
+# don't want this issue to happen, no matter what. In order to catch any
+# reference loops, kmemleak MUST be used. The results alone are always blindly
+# successful, don't rely on them. Note that the following tests may crash the
+# kernel if the fix to prevent lwtunnel_{input|output|xmit}() reentry loops is
+# not present.
+#
+# Affected lwt users so far (please update accordingly if needed):
+#  - ila_lwt (output only)
+#  - ioam6_iptunnel (output only)
+#  - rpl_iptunnel (both input and output)
+#  - seg6_iptunnel (both input and output)
+
+source lib.sh
+
+check_compatibility()
+{
+	setup_ns tmp_node &>/dev/null
+	if [ $? != 0 ]; then
+		echo "SKIP: Cannot create netns."
+		exit $ksft_skip
+	fi
+
+	ip link add name veth0 netns $tmp_node type veth \
+		peer name veth1 netns $tmp_node &>/dev/null
+	local ret=$?
+
+	ip -netns $tmp_node link set veth0 up &>/dev/null
+	ret=$((ret + $?))
+
+	ip -netns $tmp_node link set veth1 up &>/dev/null
+	ret=$((ret + $?))
+
+	if [ $ret != 0 ]; then
+		echo "SKIP: Cannot configure links."
+		cleanup_ns $tmp_node
+		exit $ksft_skip
+	fi
+
+	lsmod 2>/dev/null | grep -q "ila"
+	ila_lsmod=$?
+	[ $ila_lsmod != 0 ] && modprobe ila &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:1::/64 \
+		encap ila 1:2:3:4 csum-mode no-action ident-type luid \
+			hook-type output \
+		dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:2::/64 \
+		encap ioam6 trace prealloc type 0x800000 ns 0 size 4 \
+		dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:3::/64 \
+		encap rpl segs 2001:db8:3::1 dev veth0 &>/dev/null
+
+	ip -netns $tmp_node route add 2001:db8:4::/64 \
+		encap seg6 mode inline segs 2001:db8:4::1 dev veth0 &>/dev/null
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ila"
+	skip_ila=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap ioam6"
+	skip_ioam6=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap rpl"
+	skip_rpl=$?
+
+	ip -netns $tmp_node -6 route 2>/dev/null | grep -q "encap seg6"
+	skip_seg6=$?
+
+	cleanup_ns $tmp_node
+}
+
+setup()
+{
+	setup_ns alpha beta gamma &>/dev/null
+
+	ip link add name veth-alpha netns $alpha type veth \
+		peer name veth-betaL netns $beta &>/dev/null
+
+	ip link add name veth-betaR netns $beta type veth \
+		peer name veth-gamma netns $gamma &>/dev/null
+
+	ip -netns $alpha link set veth-alpha name veth0 &>/dev/null
+	ip -netns $beta link set veth-betaL name veth0 &>/dev/null
+	ip -netns $beta link set veth-betaR name veth1 &>/dev/null
+	ip -netns $gamma link set veth-gamma name veth0 &>/dev/null
+
+	ip -netns $alpha addr add 2001:db8:1::2/64 dev veth0 &>/dev/null
+	ip -netns $alpha link set veth0 up &>/dev/null
+	ip -netns $alpha link set lo up &>/dev/null
+	ip -netns $alpha route add 2001:db8:2::/64 \
+		via 2001:db8:1::1 dev veth0 &>/dev/null
+
+	ip -netns $beta addr add 2001:db8:1::1/64 dev veth0 &>/dev/null
+	ip -netns $beta addr add 2001:db8:2::1/64 dev veth1 &>/dev/null
+	ip -netns $beta link set veth0 up &>/dev/null
+	ip -netns $beta link set veth1 up &>/dev/null
+	ip -netns $beta link set lo up &>/dev/null
+	ip -netns $beta route del 2001:db8:2::/64
+	ip -netns $beta route add 2001:db8:2::/64 dev veth1
+	ip netns exec $beta \
+		sysctl -wq net.ipv6.conf.all.forwarding=1 &>/dev/null
+
+	ip -netns $gamma addr add 2001:db8:2::2/64 dev veth0 &>/dev/null
+	ip -netns $gamma link set veth0 up &>/dev/null
+	ip -netns $gamma link set lo up &>/dev/null
+	ip -netns $gamma route add 2001:db8:1::/64 \
+		via 2001:db8:2::1 dev veth0 &>/dev/null
+
+	sleep 1
+
+	ip netns exec $alpha ping6 -c 5 -W 1 2001:db8:2::2 &>/dev/null
+	if [ $? != 0 ]; then
+		echo "SKIP: Setup failed."
+		exit $ksft_skip
+	fi
+
+	sleep 1
+}
+
+cleanup()
+{
+	cleanup_ns $alpha $beta $gamma
+	[ $ila_lsmod != 0 ] && modprobe -r ila &>/dev/null
+}
+
+run_ila()
+{
+	if [ $skip_ila != 0 ]; then
+		echo "SKIP: ila (output)"
+		return
+	fi
+
+	ip -netns $beta route del 2001:db8:2::/64
+	ip -netns $beta route add 2001:db8:2:0:0:0:0:2/128 \
+		encap ila 2001:db8:2:0 csum-mode no-action ident-type luid \
+			hook-type output \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: ila (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	ip -netns $beta route del 2001:db8:2:0:0:0:0:2/128
+	ip -netns $beta route add 2001:db8:2::/64 dev veth1
+	sleep 1
+}
+
+run_ioam6()
+{
+	if [ $skip_ioam6 != 0 ]; then
+		echo "SKIP: ioam6 (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap ioam6 trace prealloc type 0x800000 ns 1 size 4 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: ioam6 (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run_rpl()
+{
+	if [ $skip_rpl != 0 ]; then
+		echo "SKIP: rpl (input)"
+		echo "SKIP: rpl (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap rpl segs 2001:db8:2::2 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: rpl (input)"
+	ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	echo "TEST: rpl (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run_seg6()
+{
+	if [ $skip_seg6 != 0 ]; then
+		echo "SKIP: seg6 (input)"
+		echo "SKIP: seg6 (output)"
+		return
+	fi
+
+	ip -netns $beta route change 2001:db8:2::/64 \
+		encap seg6 mode inline segs 2001:db8:2::2 \
+		dev veth1 &>/dev/null
+	sleep 1
+
+	echo "TEST: seg6 (input)"
+	ip netns exec $alpha ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+
+	echo "TEST: seg6 (output)"
+	ip netns exec $beta ping6 -c 2 -W 1 2001:db8:2::2 &>/dev/null
+	sleep 1
+}
+
+run()
+{
+	run_ila
+	run_ioam6
+	run_rpl
+	run_seg6
+}
+
+if [ "$(id -u)" -ne 0 ]; then
+	echo "SKIP: Need root privileges."
+	exit $ksft_skip
+fi
+
+if [ ! -x "$(command -v ip)" ]; then
+	echo "SKIP: Could not run test without ip tool."
+	exit $ksft_skip
+fi
+
+check_compatibility
+
+trap cleanup EXIT
+
+setup
+run
+
+exit $ksft_pass

From 2c1f97a52cb827a5f2768e67a9dddffae1ed47ab Mon Sep 17 00:00:00 2001
From: Arthur Mongodin <amongodin@randorisec.fr>
Date: Fri, 14 Mar 2025 21:11:31 +0100
Subject: [PATCH 2388/2753] mptcp: Fix data stream corruption in the address
 announcement

Because of the size restriction in the TCP options space, the MPTCP
ADD_ADDR option is exclusive and cannot be sent with other MPTCP ones.
For this reason, in the linked mptcp_out_options structure, group of
fields linked to different options are part of the same union.

There is a case where the mptcp_pm_add_addr_signal() function can modify
opts->addr, but not ended up sending an ADD_ADDR. Later on, back in
mptcp_established_options, other options will be sent, but with
unexpected data written in other fields due to the union, e.g. in
opts->ext_copy. This could lead to a data stream corruption in the next
packet.

Using an intermediate variable, prevents from corrupting previously
established DSS option. The assignment of the ADD_ADDR option
parameters is now done once we are sure this ADD_ADDR option can be set
in the packet, e.g. after having dropped other suboptions.

Fixes: 1bff1e43a30e ("mptcp: optimize out option generation")
Cc: stable@vger.kernel.org
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Arthur Mongodin <amongodin@randorisec.fr>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
[ Matt: the commit message has been updated: long lines splits and some
  clarifications. ]
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250314-net-mptcp-fix-data-stream-corr-sockopt-v1-1-122dbb249db3@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/mptcp/options.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index fd2de185bc939..23949ae2a3a8d 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -651,6 +651,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
 	bool drop_other_suboptions = false;
 	unsigned int opt_size = *size;
+	struct mptcp_addr_info addr;
 	bool echo;
 	int len;
 
@@ -659,7 +660,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	 */
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
-	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr,
+	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &addr,
 		    &echo, &drop_other_suboptions))
 		return false;
 
@@ -672,7 +673,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	else if (opts->suboptions & OPTION_MPTCP_DSS)
 		return false;
 
-	len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
+	len = mptcp_add_addr_len(addr.family, echo, !!addr.port);
 	if (remaining < len)
 		return false;
 
@@ -689,6 +690,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 		opts->ahmac = 0;
 		*size -= opt_size;
 	}
+	opts->addr = addr;
 	opts->suboptions |= OPTION_MPTCP_ADD_ADDR;
 	if (!echo) {
 		MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX);

From 23b763302ce068d7c97441e75434dc9f903adc7d Mon Sep 17 00:00:00 2001
From: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Date: Fri, 14 Mar 2025 22:41:54 +0100
Subject: [PATCH 2389/2753] tools headers: Sync uapi/asm-generic/socket.h with
 the kernel sources

This also fixes a wrong definitions for SCM_TS_OPT_ID & SO_RCVPRIORITY.

Accidentally found while working on another patchset.

Cc: linux-kernel@vger.kernel.org
Cc: netdev@vger.kernel.org
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jason Xing <kerneljasonxing@gmail.com>
Cc: Anna Emese Nyiri <annaemesenyiri@gmail.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Fixes: a89568e9be75 ("selftests: txtimestamp: add SCM_TS_OPT_ID test")
Fixes: e45469e594b2 ("sock: Introduce SO_RCVPRIORITY socket option")
Link: https://lore.kernel.org/netdev/20250314195257.34854-1-kuniyu@amazon.com/
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Link: https://patch.msgid.link/20250314214155.16046-1-aleksandr.mikhalitsyn@canonical.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/include/uapi/asm-generic/socket.h | 21 +++++++++++++++++++--
 1 file changed, 19 insertions(+), 2 deletions(-)

diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h
index ffff554a52300..aa5016ff3d911 100644
--- a/tools/include/uapi/asm-generic/socket.h
+++ b/tools/include/uapi/asm-generic/socket.h
@@ -119,14 +119,31 @@
 
 #define SO_DETACH_REUSEPORT_BPF 68
 
+#define SO_PREFER_BUSY_POLL	69
+#define SO_BUSY_POLL_BUDGET	70
+
+#define SO_NETNS_COOKIE		71
+
+#define SO_BUF_LOCK		72
+
+#define SO_RESERVE_MEM		73
+
+#define SO_TXREHASH		74
+
 #define SO_RCVMARK		75
 
 #define SO_PASSPIDFD		76
 #define SO_PEERPIDFD		77
 
-#define SCM_TS_OPT_ID		78
+#define SO_DEVMEM_LINEAR	78
+#define SCM_DEVMEM_LINEAR	SO_DEVMEM_LINEAR
+#define SO_DEVMEM_DMABUF	79
+#define SCM_DEVMEM_DMABUF	SO_DEVMEM_DMABUF
+#define SO_DEVMEM_DONTNEED	80
+
+#define SCM_TS_OPT_ID		81
 
-#define SO_RCVPRIORITY		79
+#define SO_RCVPRIORITY		82
 
 #if !defined(__KERNEL__)
 

From 90a7138619a0c55e2aefaad27b12ffc2ddbeed78 Mon Sep 17 00:00:00 2001
From: Lin Ma <linma@zju.edu.cn>
Date: Sun, 16 Mar 2025 00:51:13 +0800
Subject: [PATCH 2390/2753] net/neighbor: add missing policy for
 NDTPA_QUEUE_LENBYTES

Previous commit 8b5c171bb3dc ("neigh: new unresolved queue limits")
introduces new netlink attribute NDTPA_QUEUE_LENBYTES to represent
approximative value for deprecated QUEUE_LEN. However, it forgot to add
the associated nla_policy in nl_ntbl_parm_policy array. Fix it with one
simple NLA_U32 type policy.

Fixes: 8b5c171bb3dc ("neigh: new unresolved queue limits")
Signed-off-by: Lin Ma <linma@zju.edu.cn>
Link: https://patch.msgid.link/20250315165113.37600-1-linma@zju.edu.cn
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/neighbour.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c
index bd0251bd74a1f..1a620f903c56e 100644
--- a/net/core/neighbour.c
+++ b/net/core/neighbour.c
@@ -2250,6 +2250,7 @@ static const struct nla_policy nl_neightbl_policy[NDTA_MAX+1] = {
 static const struct nla_policy nl_ntbl_parm_policy[NDTPA_MAX+1] = {
 	[NDTPA_IFINDEX]			= { .type = NLA_U32 },
 	[NDTPA_QUEUE_LEN]		= { .type = NLA_U32 },
+	[NDTPA_QUEUE_LENBYTES]		= { .type = NLA_U32 },
 	[NDTPA_PROXY_QLEN]		= { .type = NLA_U32 },
 	[NDTPA_APP_PROBES]		= { .type = NLA_U32 },
 	[NDTPA_UCAST_PROBES]		= { .type = NLA_U32 },

From 355d940f4d5ae56ed082a455ce2cc737c7e898e8 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 19 Mar 2025 22:26:45 +0100
Subject: [PATCH 2391/2753] Revert "selftests: Add IPv6 link-local address
 generation tests for GRE devices."

This reverts commit 6f50175ccad4278ed3a9394c00b797b75441bd6e.

Commit 183185a18ff9 ("gre: Fix IPv6 link-local address generation.") is
going to be reverted. So let's revert the corresponding kselftest
first.

Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/259a9e98f7f1be7ce02b53d0b4afb7c18a8ff747.1742418408.git.gnault@redhat.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 tools/testing/selftests/net/Makefile          |   1 -
 .../testing/selftests/net/gre_ipv6_lladdr.sh  | 177 ------------------
 2 files changed, 178 deletions(-)
 delete mode 100755 tools/testing/selftests/net/gre_ipv6_lladdr.sh

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 843ab747645d0..8f32b4f01aee1 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -31,7 +31,6 @@ TEST_PROGS += veth.sh
 TEST_PROGS += ioam6.sh
 TEST_PROGS += gro.sh
 TEST_PROGS += gre_gso.sh
-TEST_PROGS += gre_ipv6_lladdr.sh
 TEST_PROGS += cmsg_so_mark.sh
 TEST_PROGS += cmsg_so_priority.sh
 TEST_PROGS += cmsg_time.sh cmsg_ipv6.sh
diff --git a/tools/testing/selftests/net/gre_ipv6_lladdr.sh b/tools/testing/selftests/net/gre_ipv6_lladdr.sh
deleted file mode 100755
index 5b34f6e1f8314..0000000000000
--- a/tools/testing/selftests/net/gre_ipv6_lladdr.sh
+++ /dev/null
@@ -1,177 +0,0 @@
-#!/bin/bash
-# SPDX-License-Identifier: GPL-2.0
-
-source ./lib.sh
-
-PAUSE_ON_FAIL="no"
-
-# The trap function handler
-#
-exit_cleanup_all()
-{
-	cleanup_all_ns
-
-	exit "${EXIT_STATUS}"
-}
-
-# Add fake IPv4 and IPv6 networks on the loopback device, to be used as
-# underlay by future GRE devices.
-#
-setup_basenet()
-{
-	ip -netns "${NS0}" link set dev lo up
-	ip -netns "${NS0}" address add dev lo 192.0.2.10/24
-	ip -netns "${NS0}" address add dev lo 2001:db8::10/64 nodad
-}
-
-# Check if network device has an IPv6 link-local address assigned.
-#
-# Parameters:
-#
-#   * $1: The network device to test
-#   * $2: An extra regular expression that should be matched (to verify the
-#         presence of extra attributes)
-#   * $3: The expected return code from grep (to allow checking the absence of
-#         a link-local address)
-#   * $4: The user visible name for the scenario being tested
-#
-check_ipv6_ll_addr()
-{
-	local DEV="$1"
-	local EXTRA_MATCH="$2"
-	local XRET="$3"
-	local MSG="$4"
-
-	RET=0
-	set +e
-	ip -netns "${NS0}" -6 address show dev "${DEV}" scope link | grep "fe80::" | grep -q "${EXTRA_MATCH}"
-	check_err_fail "${XRET}" $? ""
-	log_test "${MSG}"
-	set -e
-}
-
-# Create a GRE device and verify that it gets an IPv6 link-local address as
-# expected.
-#
-# Parameters:
-#
-#   * $1: The device type (gre, ip6gre, gretap or ip6gretap)
-#   * $2: The local underlay IP address (can be an IPv4, an IPv6 or "any")
-#   * $3: The remote underlay IP address (can be an IPv4, an IPv6 or "any")
-#   * $4: The IPv6 interface identifier generation mode to use for the GRE
-#         device (eui64, none, stable-privacy or random).
-#
-test_gre_device()
-{
-	local GRE_TYPE="$1"
-	local LOCAL_IP="$2"
-	local REMOTE_IP="$3"
-	local MODE="$4"
-	local ADDR_GEN_MODE
-	local MATCH_REGEXP
-	local MSG
-
-	ip link add netns "${NS0}" name gretest type "${GRE_TYPE}" local "${LOCAL_IP}" remote "${REMOTE_IP}"
-
-	case "${MODE}" in
-	    "eui64")
-		ADDR_GEN_MODE=0
-		MATCH_REGEXP=""
-		MSG="${GRE_TYPE}, mode: 0 (EUI64), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		;;
-	    "none")
-		ADDR_GEN_MODE=1
-		MATCH_REGEXP=""
-		MSG="${GRE_TYPE}, mode: 1 (none), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=1 # No link-local address should be generated
-		;;
-	    "stable-privacy")
-		ADDR_GEN_MODE=2
-		MATCH_REGEXP="stable-privacy"
-		MSG="${GRE_TYPE}, mode: 2 (stable privacy), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		# Initialise stable_secret (required for stable-privacy mode)
-		ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.stable_secret="2001:db8::abcd"
-		;;
-	    "random")
-		ADDR_GEN_MODE=3
-		MATCH_REGEXP="stable-privacy"
-		MSG="${GRE_TYPE}, mode: 3 (random), ${LOCAL_IP} -> ${REMOTE_IP}"
-		XRET=0
-		;;
-	esac
-
-	# Check that IPv6 link-local address is generated when device goes up
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
-	ip -netns "${NS0}" link set dev gretest up
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "config: ${MSG}"
-
-	# Now disable link-local address generation
-	ip -netns "${NS0}" link set dev gretest down
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode=1
-	ip -netns "${NS0}" link set dev gretest up
-
-	# Check that link-local address generation works when re-enabled while
-	# the device is already up
-	ip netns exec "${NS0}" sysctl -qw net.ipv6.conf.gretest.addr_gen_mode="${ADDR_GEN_MODE}"
-	check_ipv6_ll_addr gretest "${MATCH_REGEXP}" "${XRET}" "update: ${MSG}"
-
-	ip -netns "${NS0}" link del dev gretest
-}
-
-test_gre4()
-{
-	local GRE_TYPE
-	local MODE
-
-	for GRE_TYPE in "gre" "gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
-
-		for MODE in "eui64" "none" "stable-privacy" "random"; do
-			test_gre_device "${GRE_TYPE}" 192.0.2.10 192.0.2.11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" any 192.0.2.11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" 192.0.2.10 any "${MODE}"
-		done
-	done
-}
-
-test_gre6()
-{
-	local GRE_TYPE
-	local MODE
-
-	for GRE_TYPE in "ip6gre" "ip6gretap"; do
-		printf "\n####\nTesting IPv6 link-local address generation on ${GRE_TYPE} devices\n####\n\n"
-
-		for MODE in "eui64" "none" "stable-privacy" "random"; do
-			test_gre_device "${GRE_TYPE}" 2001:db8::10 2001:db8::11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" any 2001:db8::11 "${MODE}"
-			test_gre_device "${GRE_TYPE}" 2001:db8::10 any "${MODE}"
-		done
-	done
-}
-
-usage()
-{
-	echo "Usage: $0 [-p]"
-	exit 1
-}
-
-while getopts :p o
-do
-	case $o in
-		p) PAUSE_ON_FAIL="yes";;
-		*) usage;;
-	esac
-done
-
-setup_ns NS0
-
-set -e
-trap exit_cleanup_all EXIT
-
-setup_basenet
-
-test_gre4
-test_gre6

From fc486c2d060f67d672ddad81724f7c8a4d329570 Mon Sep 17 00:00:00 2001
From: Guillaume Nault <gnault@redhat.com>
Date: Wed, 19 Mar 2025 22:26:50 +0100
Subject: [PATCH 2392/2753] Revert "gre: Fix IPv6 link-local address
 generation."

This reverts commit 183185a18ff96751db52a46ccf93fff3a1f42815.

This patch broke net/forwarding/ip6gre_custom_multipath_hash.sh in some
circumstances (https://lore.kernel.org/netdev/Z9RIyKZDNoka53EO@mini-arch/).
Let's revert it while the problem is being investigated.

Fixes: 183185a18ff9 ("gre: Fix IPv6 link-local address generation.")
Signed-off-by: Guillaume Nault <gnault@redhat.com>
Link: https://patch.msgid.link/8b1ce738eb15dd841aab9ef888640cab4f6ccfea.1742418408.git.gnault@redhat.com
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/addrconf.c | 15 ++++++---------
 1 file changed, 6 insertions(+), 9 deletions(-)

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 8b6258819dade..ac8cc10765360 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3209,13 +3209,16 @@ static void add_v4_addrs(struct inet6_dev *idev)
 	struct in6_addr addr;
 	struct net_device *dev;
 	struct net *net = dev_net(idev->dev);
-	int scope, plen;
+	int scope, plen, offset = 0;
 	u32 pflags = 0;
 
 	ASSERT_RTNL();
 
 	memset(&addr, 0, sizeof(struct in6_addr));
-	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr, 4);
+	/* in case of IP6GRE the dev_addr is an IPv6 and therefore we use only the last 4 bytes */
+	if (idev->dev->addr_len == sizeof(struct in6_addr))
+		offset = sizeof(struct in6_addr) - 4;
+	memcpy(&addr.s6_addr32[3], idev->dev->dev_addr + offset, 4);
 
 	if (!(idev->dev->flags & IFF_POINTOPOINT) && idev->dev->type == ARPHRD_SIT) {
 		scope = IPV6_ADDR_COMPATv4;
@@ -3526,13 +3529,7 @@ static void addrconf_gre_config(struct net_device *dev)
 		return;
 	}
 
-	/* Generate the IPv6 link-local address using addrconf_addr_gen(),
-	 * unless we have an IPv4 GRE device not bound to an IP address and
-	 * which is in EUI64 mode (as __ipv6_isatap_ifid() would fail in this
-	 * case). Such devices fall back to add_v4_addrs() instead.
-	 */
-	if (!(dev->type == ARPHRD_IPGRE && *(__be32 *)dev->dev_addr == 0 &&
-	      idev->cnf.addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64)) {
+	if (dev->type == ARPHRD_ETHER) {
 		addrconf_addr_gen(idev, true);
 		return;
 	}

From feaee98c6c505494e2188e5c644b881f5c81ee59 Mon Sep 17 00:00:00 2001
From: David Ahern <dsahern@kernel.org>
Date: Wed, 12 Mar 2025 10:22:12 +0100
Subject: [PATCH 2393/2753] MAINTAINERS: Add Andrea Mayer as a maintainer of
 SRv6

Andrea has made significant contributions to SRv6 support in Linux.
Acknowledge the work and on-going interest in Srv6 support with a
maintainers entry for these files so hopefully he is included
on patches going forward.

Signed-off-by: David Ahern <dsahern@kernel.org>
Acked-by: Andrea Mayer <andrea.mayer@uniroma2.it>
Link: https://patch.msgid.link/20250312092212.46299-1-dsahern@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 625f3758c8800..1ca95d95c4892 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16663,6 +16663,17 @@ F:	net/mptcp/
 F:	tools/testing/selftests/bpf/*/*mptcp*.[ch]
 F:	tools/testing/selftests/net/mptcp/
 
+NETWORKING [SRv6]
+M:	Andrea Mayer <andrea.mayer@uniroma2.it>
+L:	netdev@vger.kernel.org
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net.git
+F:	include/linux/seg6*
+F:	include/net/seg6*
+F:	include/uapi/linux/seg6*
+F:	net/ipv6/seg6*
+F:	tools/testing/selftests/net/srv6*
+
 NETWORKING [TCP]
 M:	Eric Dumazet <edumazet@google.com>
 M:	Neal Cardwell <ncardwell@google.com>

From 6673b360ad0ba9784b8e3f8b38e0872378f7cc88 Mon Sep 17 00:00:00 2001
From: Douglas Anderson <dianders@chromium.org>
Date: Wed, 15 Jan 2025 19:36:37 -0800
Subject: [PATCH 2394/2753] Bluetooth: btusb: mediatek: Add err code to btusb
 claim iso printout

Add the error code to the message "Failed to claim iso
interface". That allows us to know which error case
usb_driver_claim_interface() hit.

Signed-off-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index a0fc465458b2f..5b7dec28de8b9 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2688,7 +2688,7 @@ static void btusb_mtk_claim_iso_intf(struct btusb_data *data)
 	device_unlock(&btmtk_data->isopkt_intf->dev);
 	if (err < 0) {
 		btmtk_data->isopkt_intf = NULL;
-		bt_dev_err(data->hdev, "Failed to claim iso interface");
+		bt_dev_err(data->hdev, "Failed to claim iso interface: %d", err);
 		return;
 	}
 

From 9857c09a2a57c0b718223a0e701da702df17cfd4 Mon Sep 17 00:00:00 2001
From: Dorian Cruveiller <doriancruveiller@gmail.com>
Date: Thu, 16 Jan 2025 00:34:31 +0100
Subject: [PATCH 2395/2753] Bluetooth: btusb: Add new VID/PID for WCN785x

Add VID 0489 & PID e10d for Qualcomm WCN785x USB Bluetooth chip.

The information in /sys/kernel/debug/usb/devices about the Bluetooth
device is listed as the below.

T:  Bus=01 Lev=01 Prnt=01 Port=03 Cnt=03 Dev#=  4 Spd=12   MxCh= 0
D:  Ver= 1.10 Cls=e0(wlcon) Sub=01 Prot=01 MxPS=64 #Cfgs=  1
P:  Vendor=0489 ProdID=e10d Rev= 0.01
C:* #Ifs= 2 Cfg#= 1 Atr=e0 MxPwr=100mA
I:* If#= 0 Alt= 0 #EPs= 3 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=81(I) Atr=03(Int.) MxPS=  16 Ivl=1ms
E:  Ad=82(I) Atr=02(Bulk) MxPS=  64 Ivl=0ms
E:  Ad=02(O) Atr=02(Bulk) MxPS=  64 Ivl=0ms
I:* If#= 1 Alt= 0 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   0 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   0 Ivl=1ms
I:  If#= 1 Alt= 1 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=   9 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=   9 Ivl=1ms
I:  If#= 1 Alt= 2 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  17 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  17 Ivl=1ms
I:  If#= 1 Alt= 3 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  25 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  25 Ivl=1ms
I:  If#= 1 Alt= 4 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  33 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  33 Ivl=1ms
I:  If#= 1 Alt= 5 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  49 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  49 Ivl=1ms
I:  If#= 1 Alt= 6 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  63 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  63 Ivl=1ms
I:  If#= 1 Alt= 7 #EPs= 2 Cls=e0(wlcon) Sub=01 Prot=01 Driver=btusb
E:  Ad=83(I) Atr=01(Isoc) MxPS=  65 Ivl=1ms
E:  Ad=03(O) Atr=01(Isoc) MxPS=  65 Ivl=1ms

Signed-off-by: Dorian Cruveiller <doriancruveiller@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5b7dec28de8b9..53514708d4c9f 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -376,6 +376,8 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f3), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe10d), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3623), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x2c7c, 0x0130), .driver_info = BTUSB_QCA_WCN6855 |

From 550e79a990c0f2c95ab862215453ce941be414e1 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Thu, 16 Jan 2025 17:07:08 +0530
Subject: [PATCH 2396/2753] Bluetooth: btintel: Add support for Intel Scorpius
 Peak

Add support for Scorpious Peak core.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c      | 3 +++
 drivers/bluetooth/btintel_pcie.c | 1 +
 2 files changed, 4 insertions(+)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index d2540b28bc7ae..03bf96e2544f4 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -478,6 +478,7 @@ int btintel_version_info_tlv(struct hci_dev *hdev,
 	case 0x1c:	/* Gale Peak (GaP) */
 	case 0x1d:	/* BlazarU (BzrU) */
 	case 0x1e:	/* BlazarI (Bzr) */
+	case 0x1f:      /* Scorpious Peak */
 		break;
 	default:
 		bt_dev_err(hdev, "Unsupported Intel hardware variant (0x%x)",
@@ -2919,6 +2920,7 @@ void btintel_set_msft_opcode(struct hci_dev *hdev, u8 hw_variant)
 	case 0x1c:
 	case 0x1d:
 	case 0x1e:
+	case 0x1f:
 		hci_set_msft_opcode(hdev, 0xFC1E);
 		break;
 	default:
@@ -3258,6 +3260,7 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 	case 0x1b:
 	case 0x1d:
 	case 0x1e:
+	case 0x1f:
 		/* Display version information of TLV type */
 		btintel_version_info_tlv(hdev, &ver_tlv);
 
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 091ffe3e14954..18f31f252565f 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -1449,6 +1449,7 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 	 */
 	switch (INTEL_HW_VARIANT(ver_tlv.cnvi_bt)) {
 	case 0x1e:	/* BzrI */
+	case 0x1f:	/* ScP  */
 		/* Display version information of TLV type */
 		btintel_version_info_tlv(hdev, &ver_tlv);
 

From fe75593bc420760d21c87457f2a876d55dfb253c Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Thu, 16 Jan 2025 17:07:09 +0530
Subject: [PATCH 2397/2753] Bluetooth: btintel_pcie: Add device id of Whale
 Peak

Add device of Whale Peak.

Output of sudo lspci -v  -s 00:14.7:

00:14.7 Bluetooth: Intel Corporation Device e476
        Subsystem: Intel Corporation Device 0011
        Flags: bus master, fast devsel, latency 0, IRQ 16, IOMMU group 11
        Memory at 11011c30000 (64-bit, non-prefetchable) [size=16K]
        Capabilities: [c8] Power Management version 3
        Capabilities: [d0] MSI: Enable- Count=1/1 Maskable- 64bit+
        Capabilities: [40] Express Root Complex Integrated Endpoint, MSI 00
        Capabilities: [80] MSI-X: Enable+ Count=32 Masked-
        Capabilities: [100] Latency Tolerance Reporting
        Kernel driver in use: btintel_pcie
        Kernel modules: btintel_pcie

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 18f31f252565f..b8b241a92bf9a 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -36,6 +36,7 @@
 /* Intel Bluetooth PCIe device id table */
 static const struct pci_device_id btintel_pcie_table[] = {
 	{ BTINTEL_PCI_DEVICE(0xA876, PCI_ANY_ID) },
+	{ BTINTEL_PCI_DEVICE(0xE476, PCI_ANY_ID) },
 	{ 0 }
 };
 MODULE_DEVICE_TABLE(pci, btintel_pcie_table);

From 049fb541913d143903f713486cd9db1c52b73d6c Mon Sep 17 00:00:00 2001
From: Zijun Hu <quic_zijuhu@quicinc.com>
Date: Tue, 21 Jan 2025 19:46:42 -0800
Subject: [PATCH 2398/2753] Bluetooth: btusb: Add 13 USB device IDs for
 Qualcomm WCN785x

Add 13 USB device IDs for Qualcomm WCN785x, and these IDs are
extracted from Windows driver inf file for various types of
WoS (Windows on Snapdragon) laptop.

Signed-off-by: Zijun Hu <quic_zijuhu@quicinc.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 53514708d4c9f..5e5296a8d2144 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -376,12 +376,38 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe0f3), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe100), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe103), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe10a), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe10d), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11b), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11c), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe11f), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe141), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14a), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14b), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe14d), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x13d3, 0x3623), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x13d3, 0x3624), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x2c7c, 0x0130), .driver_info = BTUSB_QCA_WCN6855 |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x2c7c, 0x0131), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x2c7c, 0x0132), .driver_info = BTUSB_QCA_WCN6855 |
+						     BTUSB_WIDEBAND_SPEECH },
 
 	/* Broadcom BCM2035 */
 	{ USB_DEVICE(0x0a5c, 0x2009), .driver_info = BTUSB_BCM92035 },

From c895d5d02ae0ad6d70d6409c4b16848ac8d9dfbb Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 27 Jan 2025 21:37:15 +0000
Subject: [PATCH 2399/2753] Bluetooth: MGMT: Remove unused
 mgmt_pending_find_data

mgmt_pending_find_data() last use was removed in 2021 by
commit 5a7501374664 ("Bluetooth: hci_sync: Convert MGMT_OP_GET_CLOCK_INFO")

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt_util.c | 17 -----------------
 net/bluetooth/mgmt_util.h |  4 ----
 2 files changed, 21 deletions(-)

diff --git a/net/bluetooth/mgmt_util.c b/net/bluetooth/mgmt_util.c
index 17ab909a7c07f..e5ff65e424b5b 100644
--- a/net/bluetooth/mgmt_util.c
+++ b/net/bluetooth/mgmt_util.c
@@ -229,23 +229,6 @@ struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
 	return NULL;
 }
 
-struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel,
-						u16 opcode,
-						struct hci_dev *hdev,
-						const void *data)
-{
-	struct mgmt_pending_cmd *cmd;
-
-	list_for_each_entry(cmd, &hdev->mgmt_pending, list) {
-		if (cmd->user_data != data)
-			continue;
-		if (cmd->opcode == opcode)
-			return cmd;
-	}
-
-	return NULL;
-}
-
 void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
 			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
 			  void *data)
diff --git a/net/bluetooth/mgmt_util.h b/net/bluetooth/mgmt_util.h
index bdf978605d5a8..f2ba994ab1d84 100644
--- a/net/bluetooth/mgmt_util.h
+++ b/net/bluetooth/mgmt_util.h
@@ -54,10 +54,6 @@ int mgmt_cmd_complete(struct sock *sk, u16 index, u16 cmd, u8 status,
 
 struct mgmt_pending_cmd *mgmt_pending_find(unsigned short channel, u16 opcode,
 					   struct hci_dev *hdev);
-struct mgmt_pending_cmd *mgmt_pending_find_data(unsigned short channel,
-						u16 opcode,
-						struct hci_dev *hdev,
-						const void *data);
 void mgmt_pending_foreach(u16 opcode, struct hci_dev *hdev,
 			  void (*cb)(struct mgmt_pending_cmd *cmd, void *data),
 			  void *data);

From 4d9c66cd02edfd7d3668d12a8cb248ad1e4eefde Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 27 Jan 2025 21:37:16 +0000
Subject: [PATCH 2400/2753] Bluetooth: MGMT: Remove unused
 mgmt_*_discovery_complete

mgmt_start_discovery_complete() and mgmt_stop_discovery_complete() last
uses were removed in 2022 by
commit ec2904c259c5 ("Bluetooth: Remove dead code from hci_request.c")

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  2 --
 net/bluetooth/mgmt.c             | 40 --------------------------------
 2 files changed, 42 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 6281063cbd8e4..131ff1f4ebef5 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -2354,8 +2354,6 @@ void mgmt_auth_enable_complete(struct hci_dev *hdev, u8 status);
 void mgmt_set_class_of_dev_complete(struct hci_dev *hdev, u8 *dev_class,
 				    u8 status);
 void mgmt_set_local_name_complete(struct hci_dev *hdev, u8 *name, u8 status);
-void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status);
-void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status);
 void mgmt_device_found(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
 		       u8 addr_type, u8 *dev_class, s8 rssi, u32 flags,
 		       u8 *eir, u16 eir_len, u8 *scan_rsp, u8 scan_rsp_len,
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 621c555f639be..12835e5054bed 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -5743,29 +5743,6 @@ static int remove_remote_oob_data(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
-void mgmt_start_discovery_complete(struct hci_dev *hdev, u8 status)
-{
-	struct mgmt_pending_cmd *cmd;
-
-	bt_dev_dbg(hdev, "status %u", status);
-
-	hci_dev_lock(hdev);
-
-	cmd = pending_find(MGMT_OP_START_DISCOVERY, hdev);
-	if (!cmd)
-		cmd = pending_find(MGMT_OP_START_SERVICE_DISCOVERY, hdev);
-
-	if (!cmd)
-		cmd = pending_find(MGMT_OP_START_LIMITED_DISCOVERY, hdev);
-
-	if (cmd) {
-		cmd->cmd_complete(cmd, mgmt_status(status));
-		mgmt_pending_remove(cmd);
-	}
-
-	hci_dev_unlock(hdev);
-}
-
 static bool discovery_type_is_valid(struct hci_dev *hdev, uint8_t type,
 				    uint8_t *mgmt_status)
 {
@@ -6018,23 +5995,6 @@ static int start_service_discovery(struct sock *sk, struct hci_dev *hdev,
 	return err;
 }
 
-void mgmt_stop_discovery_complete(struct hci_dev *hdev, u8 status)
-{
-	struct mgmt_pending_cmd *cmd;
-
-	bt_dev_dbg(hdev, "status %u", status);
-
-	hci_dev_lock(hdev);
-
-	cmd = pending_find(MGMT_OP_STOP_DISCOVERY, hdev);
-	if (cmd) {
-		cmd->cmd_complete(cmd, mgmt_status(status));
-		mgmt_pending_remove(cmd);
-	}
-
-	hci_dev_unlock(hdev);
-}
-
 static void stop_discovery_complete(struct hci_dev *hdev, void *data, int err)
 {
 	struct mgmt_pending_cmd *cmd = data;

From f1397da279e14b9b9f65f61a8cd0686421cb5a41 Mon Sep 17 00:00:00 2001
From: Jeremy Clifton <deaner92@yahoo.com>
Date: Wed, 29 Jan 2025 13:33:30 +0100
Subject: [PATCH 2401/2753] Bluetooth: Fix code style warning

Output of checkpatch shows warning:
drivers/bluetooth/bfusb.c:368: WARNING: braces {} are not necessary
for single statement blocks

Remove braces for single line statement.

Signed-off-by: Jeremy Clifton <deaner92@yahoo.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/bfusb.c | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/bluetooth/bfusb.c b/drivers/bluetooth/bfusb.c
index cab93935cc7f1..0d6ad50da0466 100644
--- a/drivers/bluetooth/bfusb.c
+++ b/drivers/bluetooth/bfusb.c
@@ -365,9 +365,8 @@ static void bfusb_rx_complete(struct urb *urb)
 			buf   += 3;
 		}
 
-		if (count < len) {
+		if (count < len)
 			bt_dev_err(data->hdev, "block extends over URB buffer ranges");
-		}
 
 		if ((hdr & 0xe1) == 0xc1)
 			bfusb_recv_block(data, hdr, buf, len);

From 35b8239a58763d2996f98b3c37df00d79bd07fbf Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Wed, 29 Jan 2025 08:28:17 +0530
Subject: [PATCH 2402/2753] Bluetooth: btintel: Add DSBR support for ScP

Add DSBR support for Scorpious Peak cores.

Refer commit eb9e749c0182 ("Bluetooth: btintel: Allow configuring drive
strength of BRI") for details about DSBR.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 5 +++++
 drivers/bluetooth/btintel.h | 1 +
 2 files changed, 6 insertions(+)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 03bf96e2544f4..ec5e2c7a56ae3 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2757,6 +2757,7 @@ static int btintel_set_dsbr(struct hci_dev *hdev, struct intel_version_tlv *ver)
 	/* DSBR command needs to be sent for,
 	 * 1. BlazarI or BlazarIW + B0 step product in IML image.
 	 * 2. Gale Peak2 or BlazarU in OP image.
+	 * 3. Scorpious Peak in IML image.
 	 */
 
 	switch (cnvi) {
@@ -2772,6 +2773,10 @@ static int btintel_set_dsbr(struct hci_dev *hdev, struct intel_version_tlv *ver)
 		    hdev->bus == HCI_USB)
 			break;
 		return 0;
+	case BTINTEL_CNVI_SCP:
+		if (ver->img_type == BTINTEL_IMG_IML)
+			break;
+		return 0;
 	default:
 		return 0;
 	}
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index fa43eb1378218..19530ea14905d 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -56,6 +56,7 @@ struct intel_tlv {
 #define BTINTEL_CNVI_BLAZARIW		0x901
 #define BTINTEL_CNVI_GAP		0x910
 #define BTINTEL_CNVI_BLAZARU		0x930
+ #define BTINTEL_CNVI_SCP		0xA00
 
 #define BTINTEL_IMG_BOOTLOADER		0x01	/* Bootloader image */
 #define BTINTEL_IMG_IML			0x02	/* Intermediate image */

From dd84e1c71888eb5ca265466eb84bbb027f697768 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Thu, 30 Jan 2025 21:43:26 +0300
Subject: [PATCH 2403/2753] Bluetooth: hci_uart: fix race during initialization

'hci_register_dev()' calls power up function, which is executed by
kworker - 'hci_power_on()'. This function does access to bluetooth chip
using callbacks from 'hci_ldisc.c', for example 'hci_uart_send_frame()'.
Now 'hci_uart_send_frame()' checks 'HCI_UART_PROTO_READY' bit set, and
if not - it fails. Problem is that 'HCI_UART_PROTO_READY' is set after
'hci_register_dev()', and there is tiny chance that 'hci_power_on()' will
be executed before setting this bit. In that case HCI init logic fails.

Patch moves setting of 'HCI_UART_PROTO_READY' before calling function
'hci_uart_register_dev()'.

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_ldisc.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index d2d6ba8d2f8b1..b955dc96b483a 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -707,12 +707,13 @@ static int hci_uart_set_proto(struct hci_uart *hu, int id)
 
 	hu->proto = p;
 
+	set_bit(HCI_UART_PROTO_READY, &hu->flags);
+
 	err = hci_uart_register_dev(hu);
 	if (err) {
 		return err;
 	}
 
-	set_bit(HCI_UART_PROTO_READY, &hu->flags);
 	return 0;
 }
 

From 09b5c2a66560722d59c9ba1111d2030f32ac53b0 Mon Sep 17 00:00:00 2001
From: Arseniy Krasnov <avkrasnov@salutedevices.com>
Date: Wed, 12 Feb 2025 18:59:46 +0300
Subject: [PATCH 2404/2753] Bluetooth: hci_uart: Fix another race during
 initialization

Do not set 'HCI_UART_PROTO_READY' before call 'hci_uart_register_dev()'.
Possible race is when someone calls 'hci_tty_uart_close()' after this bit
is set, but 'hci_uart_register_dev()' wasn't done. This leads to access
to uninitialized fields. To fix it let's set this bit after device was
registered (as before patch c411c62cc133) and to fix previous problem let's
add one more bit in addition to 'HCI_UART_PROTO_READY' which allows to
perform power up without original bit set (pls see commit c411c62cc133).

Crash backtrace from syzbot report:

RIP: 0010:skb_queue_empty_lockless include/linux/skbuff.h:1887 [inline]
RIP: 0010:skb_queue_purge_reason+0x6d/0x140 net/core/skbuff.c:3936

Call Trace:
 <TASK>
 skb_queue_purge include/linux/skbuff.h:3364 [inline]
 mrvl_close+0x2f/0x90 drivers/bluetooth/hci_mrvl.c:100
 hci_uart_tty_close+0xb6/0x120 drivers/bluetooth/hci_ldisc.c:557
 tty_ldisc_close drivers/tty/tty_ldisc.c:455 [inline]
 tty_ldisc_kill+0x66/0xc0 drivers/tty/tty_ldisc.c:613
 tty_ldisc_release+0xc9/0x120 drivers/tty/tty_ldisc.c:781
 tty_release_struct+0x10/0x80 drivers/tty/tty_io.c:1690
 tty_release+0x4ef/0x640 drivers/tty/tty_io.c:1861
 __fput+0x86/0x2a0 fs/file_table.c:450
 task_work_run+0x82/0xb0 kernel/task_work.c:239
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
 exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
 __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
 syscall_exit_to_user_mode+0xa3/0x1b0 kernel/entry/common.c:218
 do_syscall_64+0x9a/0x190 arch/x86/entry/common.c:89
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Signed-off-by: Arseniy Krasnov <avkrasnov@salutedevices.com>
Reported-by: syzbot+683f8cb11b94b1824c77@syzkaller.appspotmail.com
Tested-by: syzbot+683f8cb11b94b1824c77@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-bluetooth/d159c57f-8490-4c26-79da-6ad3612c4a14@salutedevices.com/
Fixes: dd84e1c71888 ("Bluetooth: hci_uart: fix race during initialization")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_ldisc.c | 20 ++++++++++++++------
 drivers/bluetooth/hci_uart.h  |  1 +
 2 files changed, 15 insertions(+), 6 deletions(-)

diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index b955dc96b483a..acba83156de9a 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -102,7 +102,8 @@ static inline struct sk_buff *hci_uart_dequeue(struct hci_uart *hu)
 	if (!skb) {
 		percpu_down_read(&hu->proto_lock);
 
-		if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+		if (test_bit(HCI_UART_PROTO_READY, &hu->flags) ||
+		    test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 			skb = hu->proto->dequeue(hu);
 
 		percpu_up_read(&hu->proto_lock);
@@ -124,7 +125,8 @@ int hci_uart_tx_wakeup(struct hci_uart *hu)
 	if (!percpu_down_read_trylock(&hu->proto_lock))
 		return 0;
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags))
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 		goto no_schedule;
 
 	set_bit(HCI_UART_TX_WAKEUP, &hu->tx_state);
@@ -278,7 +280,8 @@ static int hci_uart_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 
 	percpu_down_read(&hu->proto_lock);
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags)) {
 		percpu_up_read(&hu->proto_lock);
 		return -EUNATCH;
 	}
@@ -585,7 +588,8 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty)
 	if (tty != hu->tty)
 		return;
 
-	if (test_bit(HCI_UART_PROTO_READY, &hu->flags))
+	if (test_bit(HCI_UART_PROTO_READY, &hu->flags) ||
+	    test_bit(HCI_UART_PROTO_INIT, &hu->flags))
 		hci_uart_tx_wakeup(hu);
 }
 
@@ -611,7 +615,8 @@ static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data,
 
 	percpu_down_read(&hu->proto_lock);
 
-	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags)) {
+	if (!test_bit(HCI_UART_PROTO_READY, &hu->flags) &&
+	    !test_bit(HCI_UART_PROTO_INIT, &hu->flags)) {
 		percpu_up_read(&hu->proto_lock);
 		return;
 	}
@@ -707,13 +712,16 @@ static int hci_uart_set_proto(struct hci_uart *hu, int id)
 
 	hu->proto = p;
 
-	set_bit(HCI_UART_PROTO_READY, &hu->flags);
+	set_bit(HCI_UART_PROTO_INIT, &hu->flags);
 
 	err = hci_uart_register_dev(hu);
 	if (err) {
 		return err;
 	}
 
+	set_bit(HCI_UART_PROTO_READY, &hu->flags);
+	clear_bit(HCI_UART_PROTO_INIT, &hu->flags);
+
 	return 0;
 }
 
diff --git a/drivers/bluetooth/hci_uart.h b/drivers/bluetooth/hci_uart.h
index fbf3079b92a53..5ea5dd80e297c 100644
--- a/drivers/bluetooth/hci_uart.h
+++ b/drivers/bluetooth/hci_uart.h
@@ -90,6 +90,7 @@ struct hci_uart {
 #define HCI_UART_REGISTERED		1
 #define HCI_UART_PROTO_READY		2
 #define HCI_UART_NO_SUSPEND_NOTIFIER	3
+#define HCI_UART_PROTO_INIT		4
 
 /* TX states  */
 #define HCI_UART_SENDING	1

From d636bff6306ded4dbe22d903c439ad892280d7a7 Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 19 Feb 2025 22:51:29 +0000
Subject: [PATCH 2405/2753] Bluetooth: hci_vhci: convert timeouts to
 secs_to_jiffies()

Commit b35108a51cf7 ("jiffies: Define secs_to_jiffies()") introduced
secs_to_jiffies().  As the value here is a multiple of 1000, use
secs_to_jiffies() instead of msecs_to_jiffies to avoid the multiplication.

This is converted using scripts/coccinelle/misc/secs_to_jiffies.cocci with
the following Coccinelle rules:

@depends on patch@
expression E;
@@

-msecs_to_jiffies(E * 1000)
+secs_to_jiffies(E)

-msecs_to_jiffies(E * MSEC_PER_SEC)
+secs_to_jiffies(E)

Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_vhci.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 7651321d351cc..963741490106a 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -316,7 +316,7 @@ static inline void force_devcd_timeout(struct hci_dev *hdev,
 				       unsigned int timeout)
 {
 #ifdef CONFIG_DEV_COREDUMP
-	hdev->dump.timeout = msecs_to_jiffies(timeout * 1000);
+	hdev->dump.timeout = secs_to_jiffies(timeout);
 #endif
 }
 
@@ -645,7 +645,7 @@ static int vhci_open(struct inode *inode, struct file *file)
 	file->private_data = data;
 	nonseekable_open(inode, file);
 
-	schedule_delayed_work(&data->open_timeout, msecs_to_jiffies(1000));
+	schedule_delayed_work(&data->open_timeout, secs_to_jiffies(1));
 
 	return 0;
 }

From dbb64d8f7320a7e831d8b2ab78b68d60c3ae2a05 Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 19 Feb 2025 22:51:30 +0000
Subject: [PATCH 2406/2753] Bluetooth: MGMT: convert timeouts to
 secs_to_jiffies()

Commit b35108a51cf7 ("jiffies: Define secs_to_jiffies()") introduced
secs_to_jiffies().  As the value here is a multiple of 1000, use
secs_to_jiffies() instead of msecs_to_jiffies to avoid the multiplication.

This is converted using scripts/coccinelle/misc/secs_to_jiffies.cocci with
the following Coccinelle rules:

@depends on patch@
expression E;
@@

-msecs_to_jiffies(E * 1000)
+secs_to_jiffies(E)

-msecs_to_jiffies(E * MSEC_PER_SEC)
+secs_to_jiffies(E)

Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_sync.c | 2 +-
 net/bluetooth/mgmt.c     | 6 +++---
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index dd770ef5ec368..a43749aebf76e 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -1910,7 +1910,7 @@ int hci_schedule_adv_instance_sync(struct hci_dev *hdev, u8 instance,
 		hdev->adv_instance_timeout = timeout;
 		queue_delayed_work(hdev->req_workqueue,
 				   &hdev->adv_instance_expire,
-				   msecs_to_jiffies(timeout * 1000));
+				   secs_to_jiffies(timeout));
 	}
 
 	/* If we're just re-scheduling the same instance again then do not
diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 12835e5054bed..4fd30ba243be5 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -1533,7 +1533,7 @@ static void mgmt_set_discoverable_complete(struct hci_dev *hdev, void *data,
 
 	if (hci_dev_test_flag(hdev, HCI_DISCOVERABLE) &&
 	    hdev->discov_timeout > 0) {
-		int to = msecs_to_jiffies(hdev->discov_timeout * 1000);
+		int to = secs_to_jiffies(hdev->discov_timeout);
 		queue_delayed_work(hdev->req_workqueue, &hdev->discov_off, to);
 	}
 
@@ -1641,7 +1641,7 @@ static int set_discoverable(struct sock *sk, struct hci_dev *hdev, void *data,
 		hdev->discov_timeout = timeout;
 
 		if (cp->val && hdev->discov_timeout > 0) {
-			int to = msecs_to_jiffies(hdev->discov_timeout * 1000);
+			int to = secs_to_jiffies(hdev->discov_timeout);
 			queue_delayed_work(hdev->req_workqueue,
 					   &hdev->discov_off, to);
 		}
@@ -2534,7 +2534,7 @@ static int send_hci_cmd_sync(struct hci_dev *hdev, void *data)
 	skb = __hci_cmd_sync_ev(hdev, le16_to_cpu(cp->opcode),
 				le16_to_cpu(cp->params_len), cp->params,
 				cp->event, cp->timeout ?
-				msecs_to_jiffies(cp->timeout * 1000) :
+				secs_to_jiffies(cp->timeout) :
 				HCI_CMD_TIMEOUT);
 	if (IS_ERR(skb)) {
 		mgmt_cmd_status(cmd->sk, hdev->id, MGMT_OP_HCI_CMD_SYNC,

From 7cd71a8d9837a4599f2fa31029d6c14fb2a6811e Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 19 Feb 2025 22:51:31 +0000
Subject: [PATCH 2407/2753] Bluetooth: SMP: convert timeouts to
 secs_to_jiffies()

Commit b35108a51cf7 ("jiffies: Define secs_to_jiffies()") introduced
secs_to_jiffies().  As the value here is a multiple of 1000, use
secs_to_jiffies() instead of msecs_to_jiffies() for readability.

Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/smp.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 8b9724fd752a1..a31c6acf1df2b 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -55,7 +55,7 @@
 /* Keys which are not distributed with Secure Connections */
 #define SMP_SC_NO_DIST (SMP_DIST_ENC_KEY | SMP_DIST_LINK_KEY)
 
-#define SMP_TIMEOUT	msecs_to_jiffies(30000)
+#define SMP_TIMEOUT	secs_to_jiffies(30)
 
 #define ID_ADDR_TIMEOUT	msecs_to_jiffies(200)
 

From 3b1f80b443338da9418595302020b1299fcbfc61 Mon Sep 17 00:00:00 2001
From: Easwar Hariharan <eahariha@linux.microsoft.com>
Date: Wed, 19 Feb 2025 22:51:32 +0000
Subject: [PATCH 2408/2753] Bluetooth: L2CAP: convert timeouts to
 secs_to_jiffies()

Commit b35108a51cf7 ("jiffies: Define secs_to_jiffies()") introduced
secs_to_jiffies().  As the value here is a multiple of 1000, use
secs_to_jiffies() instead of msecs_to_jiffies() for readability.

Signed-off-by: Easwar Hariharan <eahariha@linux.microsoft.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h | 4 ++--
 net/bluetooth/l2cap_core.c    | 4 ++--
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 9189354c568f4..0bf8cb17a6e86 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -38,8 +38,8 @@
 #define L2CAP_DEFAULT_TX_WINDOW		63
 #define L2CAP_DEFAULT_EXT_WINDOW	0x3FFF
 #define L2CAP_DEFAULT_MAX_TX		3
-#define L2CAP_DEFAULT_RETRANS_TO	2000    /* 2 seconds */
-#define L2CAP_DEFAULT_MONITOR_TO	12000   /* 12 seconds */
+#define L2CAP_DEFAULT_RETRANS_TO	2    /* seconds */
+#define L2CAP_DEFAULT_MONITOR_TO	12   /* seconds */
 #define L2CAP_DEFAULT_MAX_PDU_SIZE	1492    /* Sized for AMP packet */
 #define L2CAP_DEFAULT_ACK_TO		200
 #define L2CAP_DEFAULT_MAX_SDU_SIZE	0xFFFF
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index c27ea70f71e1e..7b4adab353cf2 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -282,7 +282,7 @@ static void __set_retrans_timer(struct l2cap_chan *chan)
 	if (!delayed_work_pending(&chan->monitor_timer) &&
 	    chan->retrans_timeout) {
 		l2cap_set_timer(chan, &chan->retrans_timer,
-				msecs_to_jiffies(chan->retrans_timeout));
+				secs_to_jiffies(chan->retrans_timeout));
 	}
 }
 
@@ -291,7 +291,7 @@ static void __set_monitor_timer(struct l2cap_chan *chan)
 	__clear_retrans_timer(chan);
 	if (chan->monitor_timeout) {
 		l2cap_set_timer(chan, &chan->monitor_timer,
-				msecs_to_jiffies(chan->monitor_timeout));
+				secs_to_jiffies(chan->monitor_timeout));
 	}
 }
 

From 6052d803ef5928f6cbbe16fb821610a1c9975848 Mon Sep 17 00:00:00 2001
From: Jiande Lu <jiande.lu@mediatek.com>
Date: Thu, 20 Feb 2025 10:01:28 +0800
Subject: [PATCH 2409/2753] Bluetooth: btusb: Add 2 HWIDs for MT7922

Add below HWIDs for MediaTek MT7922 USB Bluetooth chip.
VID 0x0489, PID 0xe152
VID 0x0489, PID 0xe153

Patch has been tested successfully and controller is recognized
device pair successfully.

MT7922 module bring up message as below.
Bluetooth: Core ver 2.22
Bluetooth: HCI device and connection manager initialized
Bluetooth: HCI socket layer initialized
Bluetooth: L2CAP socket layer initialized
Bluetooth: SCO socket layer initialized
Bluetooth: hci0: HW/SW Version: 0x008a008a, Build Time: 20241106163512
Bluetooth: hci0: Device setup in 2284925 usecs
Bluetooth: hci0: HCI Enhanced Setup Synchronous Connection command is advertised, but not supported.
Bluetooth: hci0: AOSP extensions version v1.00
Bluetooth: BNEP (Ethernet Emulation) ver 1.3
Bluetooth: BNEP filters: protocol multicast
Bluetooth: BNEP socket layer initialized
Bluetooth: MGMT ver 1.22
Bluetooth: RFCOMM TTY layer initialized
Bluetooth: RFCOMM socket layer initialized
Bluetooth: RFCOMM ver 1.11

Signed-off-by: Jiande Lu <jiande.lu@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 5e5296a8d2144..7080d02f610b1 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -668,6 +668,10 @@ static const struct usb_device_id quirks_table[] = {
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x0489, 0xe102), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe152), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
+	{ USB_DEVICE(0x0489, 0xe153), .driver_info = BTUSB_MEDIATEK |
+						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x3804), .driver_info = BTUSB_MEDIATEK |
 						     BTUSB_WIDEBAND_SPEECH },
 	{ USB_DEVICE(0x04ca, 0x38e4), .driver_info = BTUSB_MEDIATEK |

From c8756df4ee8447fe1a090110cfba6aa1ccc874ea Mon Sep 17 00:00:00 2001
From: Janaki Ramaiah Thota <quic_janathot@quicinc.com>
Date: Thu, 20 Feb 2025 16:59:45 +0530
Subject: [PATCH 2410/2753] Bluetooth: hci_qca: use the power sequencer for
 wcn6750

Older boards are having entry "enable-gpios" in dts, we can safely assume
latest boards which are supporting PMU node enrty will support power
sequencer.

Signed-off-by: Janaki Ramaiah Thota <quic_janathot@quicinc.com>
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_qca.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 0ac2168f1dc4f..d2fd08aceb179 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2359,6 +2359,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	switch (qcadev->btsoc_type) {
 	case QCA_WCN6855:
 	case QCA_WCN7850:
+	case QCA_WCN6750:
 		if (!device_property_present(&serdev->dev, "enable-gpios")) {
 			/*
 			 * Backward compatibility with old DT sources. If the
@@ -2378,7 +2379,6 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 	case QCA_WCN3990:
 	case QCA_WCN3991:
 	case QCA_WCN3998:
-	case QCA_WCN6750:
 		qcadev->bt_power->dev = &serdev->dev;
 		err = qca_init_regulators(qcadev->bt_power, data->vregs,
 					  data->num_vregs);

From 05055be48300e9e2cee921d90c6b5546731b6774 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Wed, 19 Feb 2025 10:15:11 +0100
Subject: [PATCH 2411/2753] bluetooth: btnxpuart: Support for controller wakeup
 gpio config

When using the out-of-band WAKE_IN and WAKE_OUT pins, we have to tell
the firmware which pins to use (from controller point of view). This
allows to report remote wakeup support when WAKE_OUT(c2h) is configured.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 32 ++++++++++++++++++++++++++++----
 1 file changed, 28 insertions(+), 4 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index aa5ec1d444a9d..4f2f429c9800b 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -447,8 +447,14 @@ static int ps_setup(struct hci_dev *hdev)
 		return PTR_ERR(psdata->h2c_ps_gpio);
 	}
 
-	if (!psdata->h2c_ps_gpio)
+	if (device_property_read_u8(&serdev->dev, "nxp,wakein-pin", &psdata->h2c_wakeup_gpio)) {
+		psdata->h2c_wakeup_gpio = 0xff; /* 0xff: use default pin/gpio */
+	} else if (!psdata->h2c_ps_gpio) {
+		bt_dev_warn(hdev, "nxp,wakein-pin property without device-wakeup GPIO");
 		psdata->h2c_wakeup_gpio = 0xff;
+	}
+
+	device_property_read_u8(&serdev->dev, "nxp,wakeout-pin", &psdata->c2h_wakeup_gpio);
 
 	psdata->hdev = hdev;
 	INIT_WORK(&psdata->work, ps_work_func);
@@ -540,9 +546,11 @@ static int send_wakeup_method_cmd(struct hci_dev *hdev, void *data)
 
 	pcmd.c2h_wakeupmode = psdata->c2h_wakeupmode;
 	pcmd.c2h_wakeup_gpio = psdata->c2h_wakeup_gpio;
+	pcmd.h2c_wakeup_gpio = 0xff;
 	switch (psdata->h2c_wakeupmode) {
 	case WAKEUP_METHOD_GPIO:
 		pcmd.h2c_wakeupmode = BT_CTRL_WAKEUP_METHOD_GPIO;
+		pcmd.h2c_wakeup_gpio = psdata->h2c_wakeup_gpio;
 		break;
 	case WAKEUP_METHOD_DTR:
 		pcmd.h2c_wakeupmode = BT_CTRL_WAKEUP_METHOD_DSR;
@@ -552,7 +560,6 @@ static int send_wakeup_method_cmd(struct hci_dev *hdev, void *data)
 		pcmd.h2c_wakeupmode = BT_CTRL_WAKEUP_METHOD_BREAK;
 		break;
 	}
-	pcmd.h2c_wakeup_gpio = 0xff;
 
 	skb = nxp_drv_send_cmd(hdev, HCI_NXP_WAKEUP_METHOD, sizeof(pcmd), &pcmd);
 	if (IS_ERR(skb)) {
@@ -586,8 +593,13 @@ static void ps_init(struct hci_dev *hdev)
 	usleep_range(5000, 10000);
 
 	psdata->ps_state = PS_STATE_AWAKE;
-	psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_NONE;
-	psdata->c2h_wakeup_gpio = 0xff;
+
+	if (psdata->c2h_wakeup_gpio) {
+		psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_GPIO;
+	} else {
+		psdata->c2h_wakeupmode = BT_HOST_WAKEUP_METHOD_NONE;
+		psdata->c2h_wakeup_gpio = 0xff;
+	}
 
 	psdata->cur_h2c_wakeupmode = WAKEUP_METHOD_INVALID;
 	if (psdata->h2c_ps_gpio)
@@ -1266,6 +1278,17 @@ static int nxp_shutdown(struct hci_dev *hdev)
 	return 0;
 }
 
+static bool nxp_wakeup(struct hci_dev *hdev)
+{
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+	struct ps_data *psdata = &nxpdev->psdata;
+
+	if (psdata->c2h_wakeupmode != BT_HOST_WAKEUP_METHOD_NONE)
+		return true;
+
+	return false;
+}
+
 static int btnxpuart_queue_skb(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
@@ -1546,6 +1569,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	hdev->send  = nxp_enqueue;
 	hdev->hw_error = nxp_hw_err;
 	hdev->shutdown = nxp_shutdown;
+	hdev->wakeup = nxp_wakeup;
 	SET_HCIDEV_DEV(hdev, &serdev->dev);
 
 	if (hci_register_dev(hdev) < 0) {

From 855c316041c3c2166be63a585a9a326eeccfd057 Mon Sep 17 00:00:00 2001
From: Loic Poulain <loic.poulain@linaro.org>
Date: Wed, 19 Feb 2025 10:15:12 +0100
Subject: [PATCH 2412/2753] dt-bindings: net: bluetooth: nxp: Add wakeup pin
 properties

NXP bluetooth controller may have GPIO pins used and routed for `WAKE_IN`
and `WAKE_OUT`, such pin info must be known so that the driver is can
configure the controller's firmware accordingly.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../bindings/net/bluetooth/nxp,88w8987-bt.yaml       | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
index 0a2d7baf5db32..04f55fac42ce8 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
@@ -40,6 +40,16 @@ properties:
       Host-To-Chip power save mechanism is driven by this GPIO
       connected to BT_WAKE_IN pin of the NXP chipset.
 
+  nxp,wakein-pin:
+    $ref: /schemas/types.yaml#/definitions/uint8
+    description:
+      The GPIO number of the NXP chipset used for BT_WAKE_IN.
+
+  nxp,wakeout-pin:
+    $ref: /schemas/types.yaml#/definitions/uint8
+    description:
+      The GPIO number of the NXP chipset used for BT_WAKE_OUT.
+
 required:
   - compatible
 
@@ -54,5 +64,7 @@ examples:
             fw-init-baudrate = <3000000>;
             firmware-name = "uartuart8987_bt_v0.bin";
             device-wakeup-gpios = <&gpio 11 GPIO_ACTIVE_HIGH>;
+            nxp,wakein-pin = /bits/ 8 <18>;
+            nxp,wakeout-pin = /bits/ 8 <19>;
         };
     };

From dc66930d2f036efe0d2041d8fa8956b91f33748d Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 7 Feb 2025 22:41:15 +0200
Subject: [PATCH 2413/2753] dt-bindings: net: bluetooth: qualcomm: document
 WCN3950

WCN3950 is another member of the WiFi/BT WCN39xx family of the chips. It
requires different firmware, so document it as a new compat string.

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml   | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
index a72152f7e29b4..6353a336f382e 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/qualcomm-bluetooth.yaml
@@ -19,6 +19,7 @@ properties:
       - qcom,qca2066-bt
       - qcom,qca6174-bt
       - qcom,qca9377-bt
+      - qcom,wcn3950-bt
       - qcom,wcn3988-bt
       - qcom,wcn3990-bt
       - qcom,wcn3991-bt
@@ -138,6 +139,7 @@ allOf:
         compatible:
           contains:
             enum:
+              - qcom,wcn3950-bt
               - qcom,wcn3988-bt
               - qcom,wcn3990-bt
               - qcom,wcn3991-bt

From 5954a9a1584478296e3f877e2967d89b3898fe02 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 7 Feb 2025 22:41:16 +0200
Subject: [PATCH 2414/2753] Bluetooth: qca: simplify WCN399x NVM loading

The WCN399x code has two separate cases for loading the NVM data. In
preparation to adding support for WCN3950, which also requires similar
quirk, split the "variant" to be specified explicitly and merge two
snprintfs into a single one.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index cdf09d9a9ad27..7d6b02fe2040f 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -785,6 +785,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		   const char *firmware_name, const char *rampatch_name)
 {
 	struct qca_fw_config config = {};
+	const char *variant = "";
 	int err;
 	u8 rom_ver = 0;
 	u32 soc_ver;
@@ -883,13 +884,11 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		case QCA_WCN3990:
 		case QCA_WCN3991:
 		case QCA_WCN3998:
-			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID) {
-				snprintf(config.fwname, sizeof(config.fwname),
-					 "qca/crnv%02xu.bin", rom_ver);
-			} else {
-				snprintf(config.fwname, sizeof(config.fwname),
-					 "qca/crnv%02x.bin", rom_ver);
-			}
+			if (le32_to_cpu(ver.soc_id) == QCA_WCN3991_SOC_ID)
+				variant = "u";
+
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/crnv%02x%s.bin", rom_ver, variant);
 			break;
 		case QCA_WCN3988:
 			snprintf(config.fwname, sizeof(config.fwname),

From 3b0e0839d9f2559e3d7c88cac33a0ab128aab393 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Date: Fri, 7 Feb 2025 22:41:17 +0200
Subject: [PATCH 2415/2753] Bluetooth: qca: add WCN3950 support

WCN3950 is another example of the WCN39xx BT/WiFI family of chips. It
requires different firmware files and has different current
requirements, so add it as a separate SoC type.

The firmware for these chips has been recently added to the
linux-firmware repository and will be a part of the upcoming release:
- qca/cmbtfw12.tlv
- qca/cmbtfw13.tlv
- qca/cmnv12.bin
- qca/cmnv13.bin
- qca/cmnv13s.bin
- qca/cmnv13t.bin

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btqca.c   | 14 ++++++++++++++
 drivers/bluetooth/btqca.h   |  4 ++++
 drivers/bluetooth/hci_qca.c | 25 +++++++++++++++++++++++++
 3 files changed, 43 insertions(+)

diff --git a/drivers/bluetooth/btqca.c b/drivers/bluetooth/btqca.c
index 7d6b02fe2040f..3d6778b95e005 100644
--- a/drivers/bluetooth/btqca.c
+++ b/drivers/bluetooth/btqca.c
@@ -816,6 +816,10 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		snprintf(config.fwname, sizeof(config.fwname), "qca/%s", rampatch_name);
 	} else {
 		switch (soc_type) {
+		case QCA_WCN3950:
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/cmbtfw%02x.tlv", rom_ver);
+			break;
 		case QCA_WCN3990:
 		case QCA_WCN3991:
 		case QCA_WCN3998:
@@ -881,6 +885,15 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 		}
 	} else {
 		switch (soc_type) {
+		case QCA_WCN3950:
+			if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_T)
+				variant = "t";
+			else if (le32_to_cpu(ver.soc_id) == QCA_WCN3950_SOC_ID_S)
+				variant = "u";
+
+			snprintf(config.fwname, sizeof(config.fwname),
+				 "qca/cmnv%02x%s.bin", rom_ver, variant);
+			break;
 		case QCA_WCN3990:
 		case QCA_WCN3991:
 		case QCA_WCN3998:
@@ -947,6 +960,7 @@ int qca_uart_setup(struct hci_dev *hdev, uint8_t baudrate,
 	 * VsMsftOpCode.
 	 */
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
diff --git a/drivers/bluetooth/btqca.h b/drivers/bluetooth/btqca.h
index 9d28c88002257..8f3c1b1c77b3d 100644
--- a/drivers/bluetooth/btqca.h
+++ b/drivers/bluetooth/btqca.h
@@ -41,6 +41,9 @@
 
 #define QCA_WCN3991_SOC_ID		0x40014320
 
+#define QCA_WCN3950_SOC_ID_T		0x40074130
+#define QCA_WCN3950_SOC_ID_S		0x40075130
+
 /* QCA chipset version can be decided by patch and SoC
  * version, combination with upper 2 bytes from SoC
  * and lower 2 bytes from patch will be used.
@@ -145,6 +148,7 @@ enum qca_btsoc_type {
 	QCA_INVALID = -1,
 	QCA_AR3002,
 	QCA_ROME,
+	QCA_WCN3950,
 	QCA_WCN3988,
 	QCA_WCN3990,
 	QCA_WCN3998,
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index d2fd08aceb179..f2558506a02c7 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -623,6 +623,7 @@ static int qca_open(struct hci_uart *hu)
 		qcadev = serdev_device_get_drvdata(hu->serdev);
 
 		switch (qcadev->btsoc_type) {
+		case QCA_WCN3950:
 		case QCA_WCN3988:
 		case QCA_WCN3990:
 		case QCA_WCN3991:
@@ -1366,6 +1367,7 @@ static int qca_set_baudrate(struct hci_dev *hdev, uint8_t baudrate)
 
 	/* Give the controller time to process the request */
 	switch (qca_soc_type(hu)) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1452,6 +1454,7 @@ static unsigned int qca_get_speed(struct hci_uart *hu,
 static int qca_check_speeds(struct hci_uart *hu)
 {
 	switch (qca_soc_type(hu)) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1494,6 +1497,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 		 * changing the baudrate of chip and host.
 		 */
 		switch (soc_type) {
+		case QCA_WCN3950:
 		case QCA_WCN3988:
 		case QCA_WCN3990:
 		case QCA_WCN3991:
@@ -1528,6 +1532,7 @@ static int qca_set_speed(struct hci_uart *hu, enum qca_speed_type speed_type)
 
 error:
 		switch (soc_type) {
+		case QCA_WCN3950:
 		case QCA_WCN3988:
 		case QCA_WCN3990:
 		case QCA_WCN3991:
@@ -1746,6 +1751,7 @@ static int qca_regulator_init(struct hci_uart *hu)
 	}
 
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1776,6 +1782,7 @@ static int qca_regulator_init(struct hci_uart *hu)
 	qca_set_speed(hu, QCA_INIT_SPEED);
 
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1807,6 +1814,7 @@ static int qca_power_on(struct hci_dev *hdev)
 		return 0;
 
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1891,6 +1899,7 @@ static int qca_setup(struct hci_uart *hu)
 		soc_name = "qca2066";
 		break;
 
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1925,6 +1934,7 @@ static int qca_setup(struct hci_uart *hu)
 	clear_bit(QCA_SSR_TRIGGERED, &qca->flags);
 
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -1958,6 +1968,7 @@ static int qca_setup(struct hci_uart *hu)
 	}
 
 	switch (soc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -2046,6 +2057,17 @@ static const struct hci_uart_proto qca_proto = {
 	.dequeue	= qca_dequeue,
 };
 
+static const struct qca_device_data qca_soc_data_wcn3950 __maybe_unused = {
+	.soc_type = QCA_WCN3950,
+	.vregs = (struct qca_vreg []) {
+		{ "vddio", 15000  },
+		{ "vddxo", 60000  },
+		{ "vddrf", 155000 },
+		{ "vddch0", 585000 },
+	},
+	.num_vregs = 4,
+};
+
 static const struct qca_device_data qca_soc_data_wcn3988 __maybe_unused = {
 	.soc_type = QCA_WCN3988,
 	.vregs = (struct qca_vreg []) {
@@ -2338,6 +2360,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 		qcadev->btsoc_type = QCA_ROME;
 
 	switch (qcadev->btsoc_type) {
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -2375,6 +2398,7 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			break;
 		}
 		fallthrough;
+	case QCA_WCN3950:
 	case QCA_WCN3988:
 	case QCA_WCN3990:
 	case QCA_WCN3991:
@@ -2683,6 +2707,7 @@ static const struct of_device_id qca_bluetooth_of_match[] = {
 	{ .compatible = "qcom,qca6174-bt" },
 	{ .compatible = "qcom,qca6390-bt", .data = &qca_soc_data_qca6390},
 	{ .compatible = "qcom,qca9377-bt" },
+	{ .compatible = "qcom,wcn3950-bt", .data = &qca_soc_data_wcn3950},
 	{ .compatible = "qcom,wcn3988-bt", .data = &qca_soc_data_wcn3988},
 	{ .compatible = "qcom,wcn3990-bt", .data = &qca_soc_data_wcn3990},
 	{ .compatible = "qcom,wcn3991-bt", .data = &qca_soc_data_wcn3991},

From 99dc18b50b9de80e58ff363721a9c0e216797b44 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 25 Feb 2025 17:13:10 +0530
Subject: [PATCH 2416/2753] Bluetooth: btintel_pcie: Setup buffers for firmware
 traces

This patch allocates the host memory which is used by controller to dump
the firmware traces. The memory needs to be shared with controller via
context information.

Co-developed-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
---
 drivers/bluetooth/btintel_pcie.c | 89 ++++++++++++++++++++++++++++++++
 drivers/bluetooth/btintel_pcie.h | 32 ++++++++++++
 2 files changed, 121 insertions(+)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index b8b241a92bf9a..0c8e4e2dd9451 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -49,6 +49,8 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 #define BTINTEL_PCIE_HCI_EVT_PKT	0x00000004
 #define BTINTEL_PCIE_HCI_ISO_PKT	0x00000005
 
+ #define BTINTEL_PCIE_MAGIC_NUM    0xA5A5A5A5
+
 /* Alive interrupt context */
 enum {
 	BTINTEL_PCIE_ROM,
@@ -60,6 +62,83 @@ enum {
 	BTINTEL_PCIE_D3
 };
 
+/* Structure for dbgc fragment buffer
+ * @buf_addr_lsb: LSB of the buffer's physical address
+ * @buf_addr_msb: MSB of the buffer's physical address
+ * @buf_size: Total size of the buffer
+ */
+struct btintel_pcie_dbgc_ctxt_buf {
+	u32	buf_addr_lsb;
+	u32	buf_addr_msb;
+	u32	buf_size;
+};
+
+/* Structure for dbgc fragment
+ * @magic_num: 0XA5A5A5A5
+ * @ver: For Driver-FW compatibility
+ * @total_size: Total size of the payload debug info
+ * @num_buf: Num of allocated debug bufs
+ * @bufs: All buffer's addresses and sizes
+ */
+struct btintel_pcie_dbgc_ctxt {
+	u32	magic_num;
+	u32     ver;
+	u32     total_size;
+	u32     num_buf;
+	struct btintel_pcie_dbgc_ctxt_buf bufs[BTINTEL_PCIE_DBGC_BUFFER_COUNT];
+};
+
+/* This function initializes the memory for DBGC buffers and formats the
+ * DBGC fragment which consists header info and DBGC buffer's LSB, MSB and
+ * size as the payload
+ */
+static int btintel_pcie_setup_dbgc(struct btintel_pcie_data *data)
+{
+	struct btintel_pcie_dbgc_ctxt db_frag;
+	struct data_buf *buf;
+	int i;
+
+	data->dbgc.count = BTINTEL_PCIE_DBGC_BUFFER_COUNT;
+	data->dbgc.bufs = devm_kcalloc(&data->pdev->dev, data->dbgc.count,
+				       sizeof(*buf), GFP_KERNEL);
+	if (!data->dbgc.bufs)
+		return -ENOMEM;
+
+	data->dbgc.buf_v_addr = dmam_alloc_coherent(&data->pdev->dev,
+						    data->dbgc.count *
+						    BTINTEL_PCIE_DBGC_BUFFER_SIZE,
+						    &data->dbgc.buf_p_addr,
+						    GFP_KERNEL | __GFP_NOWARN);
+	if (!data->dbgc.buf_v_addr)
+		return -ENOMEM;
+
+	data->dbgc.frag_v_addr = dmam_alloc_coherent(&data->pdev->dev,
+						     sizeof(struct btintel_pcie_dbgc_ctxt),
+						     &data->dbgc.frag_p_addr,
+						     GFP_KERNEL | __GFP_NOWARN);
+	if (!data->dbgc.frag_v_addr)
+		return -ENOMEM;
+
+	data->dbgc.frag_size = sizeof(struct btintel_pcie_dbgc_ctxt);
+
+	db_frag.magic_num = BTINTEL_PCIE_MAGIC_NUM;
+	db_frag.ver = BTINTEL_PCIE_DBGC_FRAG_VERSION;
+	db_frag.total_size = BTINTEL_PCIE_DBGC_FRAG_PAYLOAD_SIZE;
+	db_frag.num_buf = BTINTEL_PCIE_DBGC_FRAG_BUFFER_COUNT;
+
+	for (i = 0; i < data->dbgc.count; i++) {
+		buf = &data->dbgc.bufs[i];
+		buf->data_p_addr = data->dbgc.buf_p_addr + i * BTINTEL_PCIE_DBGC_BUFFER_SIZE;
+		buf->data = data->dbgc.buf_v_addr + i * BTINTEL_PCIE_DBGC_BUFFER_SIZE;
+		db_frag.bufs[i].buf_addr_lsb = lower_32_bits(buf->data_p_addr);
+		db_frag.bufs[i].buf_addr_msb = upper_32_bits(buf->data_p_addr);
+		db_frag.bufs[i].buf_size = BTINTEL_PCIE_DBGC_BUFFER_SIZE;
+	}
+
+	memcpy(data->dbgc.frag_v_addr, &db_frag, sizeof(db_frag));
+	return 0;
+}
+
 static inline void ipc_print_ia_ring(struct hci_dev *hdev, struct ia *ia,
 				     u16 queue_num)
 {
@@ -1008,6 +1087,11 @@ static void btintel_pcie_init_ci(struct btintel_pcie_data *data,
 	ci->addr_urbdq1 = data->rxq.urbd1s_p_addr;
 	ci->num_urbdq1 = data->rxq.count;
 	ci->urbdq_db_vec = BTINTEL_PCIE_RXQ_NUM;
+
+	ci->dbg_output_mode = 0x01;
+	ci->dbgc_addr = data->dbgc.frag_p_addr;
+	ci->dbgc_size = data->dbgc.frag_size;
+	ci->dbg_preset = 0x00;
 }
 
 static void btintel_pcie_free_txq_bufs(struct btintel_pcie_data *data,
@@ -1220,6 +1304,11 @@ static int btintel_pcie_alloc(struct btintel_pcie_data *data)
 	/* Setup Index Array */
 	btintel_pcie_setup_ia(data, p_addr, v_addr, &data->ia);
 
+	/* Setup data buffers for dbgc */
+	err = btintel_pcie_setup_dbgc(data);
+	if (err)
+		goto exit_error_txq;
+
 	/* Setup Context Information */
 	p_addr += sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4;
 	v_addr += sizeof(u16) * BTINTEL_PCIE_NUM_QUEUES * 4;
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index f9aada0543c48..b9d32393002b1 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -48,6 +48,21 @@
 #define BTINTEL_PCIE_CSR_MSIX_IVAR_BASE		(BTINTEL_PCIE_CSR_MSIX_BASE + 0x0880)
 #define BTINTEL_PCIE_CSR_MSIX_IVAR(cause)	(BTINTEL_PCIE_CSR_MSIX_IVAR_BASE + (cause))
 
+/* The DRAM buffer count, each buffer size, and
+ * fragment buffer size
+ */
+#define BTINTEL_PCIE_DBGC_BUFFER_COUNT		16
+#define BTINTEL_PCIE_DBGC_BUFFER_SIZE		(256 * 1024) /* 256 KB */
+
+#define BTINTEL_PCIE_DBGC_FRAG_VERSION		1
+#define BTINTEL_PCIE_DBGC_FRAG_BUFFER_COUNT	BTINTEL_PCIE_DBGC_BUFFER_COUNT
+
+/* Magic number(4), version(4), size of payload length(4) */
+#define BTINTEL_PCIE_DBGC_FRAG_HEADER_SIZE	12
+
+/* Num of alloc Dbg buff (4) + (LSB(4), MSB(4), Size(4)) for each buffer */
+#define BTINTEL_PCIE_DBGC_FRAG_PAYLOAD_SIZE	196
+
 /* Causes for the FH register interrupts */
 enum msix_fh_int_causes {
 	BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0	= BIT(0),	/* cause 0 */
@@ -325,6 +340,22 @@ struct rxq {
 	struct data_buf	*bufs;
 };
 
+/* Structure for DRAM Buffer
+ * @count: Number of descriptors
+ * @buf: Array of data_buf structure
+ */
+struct btintel_pcie_dbgc {
+	u16		count;
+
+	void		*frag_v_addr;
+	dma_addr_t	frag_p_addr;
+	u16		frag_size;
+
+	dma_addr_t	buf_p_addr;
+	void		*buf_v_addr;
+	struct data_buf *bufs;
+};
+
 /* struct btintel_pcie_data
  * @pdev: pci device
  * @hdev: hdev device
@@ -405,6 +436,7 @@ struct btintel_pcie_data {
 	struct txq	txq;
 	struct rxq	rxq;
 	u32	alive_intr_ctxt;
+	struct btintel_pcie_dbgc	dbgc;
 };
 
 static inline u32 btintel_pcie_rd_reg32(struct btintel_pcie_data *data,

From 7bc2b14ab6022ecaa1f6bfe3b3e3002073c67b45 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 25 Feb 2025 17:13:11 +0530
Subject: [PATCH 2417/2753] Bluetooth: btintel_pcie: Read hardware exception
 data

On hardware error, controller writes hardware error event and optional
vendor specific hci events in device memory in TLV format and raises
MSIX interrupt. Driver reads the device memory and passes the events to
the stack for further processing.

Co-developed-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.h      |   1 +
 drivers/bluetooth/btintel_pcie.c | 224 ++++++++++++++++++++++++++++++-
 drivers/bluetooth/btintel_pcie.h |  23 ++++
 3 files changed, 247 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 19530ea14905d..4c21e69887a37 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -190,6 +190,7 @@ enum {
 struct btintel_data {
 	DECLARE_BITMAP(flags, __INTEL_NUM_FLAGS);
 	int (*acpi_reset_method)(struct hci_dev *hdev);
+	u32	cnvi_top;
 };
 
 #define btintel_set_flag(hdev, nr)					\
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 0c8e4e2dd9451..e8307eeb971f9 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -51,6 +51,14 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 
  #define BTINTEL_PCIE_MAGIC_NUM    0xA5A5A5A5
 
+#define BTINTEL_PCIE_BLZR_HWEXP_SIZE		1024
+#define BTINTEL_PCIE_BLZR_HWEXP_DMP_ADDR	0xB00A7C00
+
+#define BTINTEL_PCIE_SCP_HWEXP_SIZE		4096
+#define BTINTEL_PCIE_SCP_HWEXP_DMP_ADDR		0xB030F800
+
+#define BTINTEL_PCIE_MAGIC_NUM	0xA5A5A5A5
+
 /* Alive interrupt context */
 enum {
 	BTINTEL_PCIE_ROM,
@@ -353,6 +361,64 @@ static int btintel_pcie_reset_bt(struct btintel_pcie_data *data)
 	return reg == 0 ? 0 : -ENODEV;
 }
 
+static void btintel_pcie_mac_init(struct btintel_pcie_data *data)
+{
+	u32 reg;
+
+	/* Set MAC_INIT bit to start primary bootloader */
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG);
+	reg &= ~(BTINTEL_PCIE_CSR_FUNC_CTRL_FUNC_INIT |
+			BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_DISCON |
+			BTINTEL_PCIE_CSR_FUNC_CTRL_SW_RESET);
+	reg |= (BTINTEL_PCIE_CSR_FUNC_CTRL_FUNC_ENA |
+			BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_INIT);
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg);
+}
+
+static int btintel_pcie_get_mac_access(struct btintel_pcie_data *data)
+{
+	u32 reg;
+	int retry = 15;
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG);
+
+	reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS;
+	reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ;
+	if ((reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS) == 0)
+		reg |= BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ;
+
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg);
+
+	do {
+		reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG);
+		if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS)
+			return 0;
+		/* Need delay here for Target Access harwdware to settle down*/
+		usleep_range(1000, 1200);
+
+	} while (--retry > 0);
+
+	return -ETIME;
+}
+
+static void btintel_pcie_release_mac_access(struct btintel_pcie_data *data)
+{
+	u32 reg;
+
+	reg = btintel_pcie_rd_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG);
+
+	if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ)
+		reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ;
+
+	if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS)
+		reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS;
+
+	if (reg & BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ)
+		reg &= ~BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ;
+
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg);
+}
+
 /* This function enables BT function by setting BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_INIT bit in
  * BTINTEL_PCIE_CSR_FUNC_CTRL_REG register and wait for MSI-X with
  * BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0.
@@ -473,6 +539,27 @@ static inline char *btintel_pcie_alivectxt_state2str(u32 alive_intr_ctxt)
 	}
 }
 
+static int btintel_pcie_read_device_mem(struct btintel_pcie_data *data,
+					void *buf, u32 dev_addr, int len)
+{
+	int err;
+	u32 *val = buf;
+
+	/* Get device mac access */
+	err = btintel_pcie_get_mac_access(data);
+	if (err) {
+		bt_dev_err(data->hdev, "Failed to get mac access %d", err);
+		return err;
+	}
+
+	for (; len > 0; len -= 4, dev_addr += 4, val++)
+		*val = btintel_pcie_rd_dev_mem(data, dev_addr);
+
+	btintel_pcie_release_mac_access(data);
+
+	return 0;
+}
+
 /* This function handles the MSI-X interrupt for gp0 cause (bit 0 in
  * BTINTEL_PCIE_CSR_MSIX_HW_INT_CAUSES) which is sent for boot stage and image response.
  */
@@ -794,6 +881,122 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 	return ret;
 }
 
+static void btintel_pcie_read_hwexp(struct btintel_pcie_data *data)
+{
+	struct btintel_data *intel_data = hci_get_priv(data->hdev);
+	int len, err, offset, pending;
+	struct sk_buff *skb;
+	u8 *buf, prefix[64];
+	u32 addr, val;
+	u16 pkt_len;
+
+	struct tlv {
+		u8	type;
+		__le16	len;
+		u8	val[];
+	} __packed;
+
+	struct tlv *tlv;
+
+	switch (intel_data->cnvi_top & 0xfff) {
+	case BTINTEL_CNVI_BLAZARI:
+	case BTINTEL_CNVI_BLAZARIW:
+		/* only from step B0 onwards */
+		if (INTEL_CNVX_TOP_STEP(intel_data->cnvi_top) != 0x01)
+			return;
+		len = BTINTEL_PCIE_BLZR_HWEXP_SIZE; /* exception data length */
+		addr = BTINTEL_PCIE_BLZR_HWEXP_DMP_ADDR;
+	break;
+	case BTINTEL_CNVI_SCP:
+		len = BTINTEL_PCIE_SCP_HWEXP_SIZE;
+		addr = BTINTEL_PCIE_SCP_HWEXP_DMP_ADDR;
+	break;
+	default:
+		bt_dev_err(data->hdev, "Unsupported cnvi 0x%8.8x", intel_data->cnvi_top);
+		return;
+	}
+
+	buf = kzalloc(len, GFP_KERNEL);
+	if (!buf)
+		goto exit_on_error;
+
+	btintel_pcie_mac_init(data);
+
+	err = btintel_pcie_read_device_mem(data, buf, addr, len);
+	if (err)
+		goto exit_on_error;
+
+	val = get_unaligned_le32(buf);
+	if (val != BTINTEL_PCIE_MAGIC_NUM) {
+		bt_dev_err(data->hdev, "Invalid exception dump signature: 0x%8.8x",
+			   val);
+		goto exit_on_error;
+	}
+
+	snprintf(prefix, sizeof(prefix), "Bluetooth: %s: ", bt_dev_name(data->hdev));
+
+	offset = 4;
+	do {
+		pending = len - offset;
+		if (pending < sizeof(*tlv))
+			break;
+		tlv = (struct tlv *)(buf + offset);
+
+		/* If type == 0, then there are no more TLVs to be parsed */
+		if (!tlv->type) {
+			bt_dev_dbg(data->hdev, "Invalid TLV type 0");
+			break;
+		}
+		pkt_len = le16_to_cpu(tlv->len);
+		offset += sizeof(*tlv);
+		pending = len - offset;
+		if (pkt_len > pending)
+			break;
+
+		offset += pkt_len;
+
+		 /* Only TLVs of type == 1 are HCI events, no need to process other
+		  * TLVs
+		  */
+		if (tlv->type != 1)
+			continue;
+
+		bt_dev_dbg(data->hdev, "TLV packet length: %u", pkt_len);
+		if (pkt_len > HCI_MAX_EVENT_SIZE)
+			break;
+		skb = bt_skb_alloc(pkt_len, GFP_KERNEL);
+		if (!skb)
+			goto exit_on_error;
+		hci_skb_pkt_type(skb) = HCI_EVENT_PKT;
+		skb_put_data(skb, tlv->val, pkt_len);
+
+		/* copy Intel specific pcie packet type */
+		val = BTINTEL_PCIE_HCI_EVT_PKT;
+		memcpy(skb_push(skb, BTINTEL_PCIE_HCI_TYPE_LEN), &val,
+		       BTINTEL_PCIE_HCI_TYPE_LEN);
+
+		print_hex_dump(KERN_DEBUG, prefix, DUMP_PREFIX_OFFSET, 16, 1,
+			       tlv->val, pkt_len, false);
+
+		btintel_pcie_recv_frame(data, skb);
+	} while (offset < len);
+
+exit_on_error:
+	kfree(buf);
+}
+
+static void btintel_pcie_msix_hw_exp_handler(struct btintel_pcie_data *data)
+{
+	bt_dev_err(data->hdev, "Received hw exception interrupt");
+
+	if (test_and_set_bit(BTINTEL_PCIE_CORE_HALTED, &data->flags))
+		return;
+
+	if (test_and_set_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags))
+		return;
+	queue_work(data->workqueue, &data->rx_work);
+}
+
 static void btintel_pcie_rx_work(struct work_struct *work)
 {
 	struct btintel_pcie_data *data = container_of(work,
@@ -802,6 +1005,18 @@ static void btintel_pcie_rx_work(struct work_struct *work)
 	int err;
 	struct hci_dev *hdev = data->hdev;
 
+	if (test_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags)) {
+		/* Unlike usb products, controller will not send hardware
+		 * exception event on exception. Instead controller writes the
+		 * hardware event to device memory along with optional debug
+		 * events, raises MSIX and halts. Driver shall read the
+		 * exception event from device memory and passes it stack for
+		 * further processing.
+		 */
+		btintel_pcie_read_hwexp(data);
+		clear_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags);
+	}
+
 	/* Process the sk_buf in queue and send to the HCI layer */
 	while ((skb = skb_dequeue(&data->rx_skb_q))) {
 		err = btintel_pcie_recv_frame(data, skb);
@@ -920,6 +1135,10 @@ static irqreturn_t btintel_pcie_irq_msix_handler(int irq, void *dev_id)
 		return IRQ_NONE;
 	}
 
+	/* This interrupt is raised when there is an hardware exception */
+	if (intr_hw & BTINTEL_PCIE_MSIX_HW_INT_CAUSES_HWEXP)
+		btintel_pcie_msix_hw_exp_handler(data);
+
 	/* This interrupt is triggered by the firmware after updating
 	 * boot_stage register and image_response register
 	 */
@@ -1000,7 +1219,8 @@ struct btintel_pcie_causes_list {
 static struct btintel_pcie_causes_list causes_list[] = {
 	{ BTINTEL_PCIE_MSIX_FH_INT_CAUSES_0,	BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK,	0x00 },
 	{ BTINTEL_PCIE_MSIX_FH_INT_CAUSES_1,	BTINTEL_PCIE_CSR_MSIX_FH_INT_MASK,	0x01 },
-	{ BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK,	0x20 },
+	{ BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0,	BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK,	0x20 },
+	{ BTINTEL_PCIE_MSIX_HW_INT_CAUSES_HWEXP, BTINTEL_PCIE_CSR_MSIX_HW_INT_MASK,	0x23 },
 };
 
 /* This function configures the interrupt masks for both HW_INT_CAUSES and
@@ -1482,6 +1702,7 @@ static void btintel_pcie_release_hdev(struct btintel_pcie_data *data)
 
 static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 {
+	struct btintel_data *data = hci_get_priv(hdev);
 	const u8 param[1] = { 0xFF };
 	struct intel_version_tlv ver_tlv;
 	struct sk_buff *skb;
@@ -1520,6 +1741,7 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 		goto exit_error;
 	}
 
+	data->cnvi_top = ver_tlv.cnvi_top;
 	switch (INTEL_HW_PLATFORM(ver_tlv.cnvi_bt)) {
 	case 0x37:
 		break;
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index b9d32393002b1..d17808ebe7251 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -16,6 +16,8 @@
 #define BTINTEL_PCIE_CSR_CI_ADDR_LSB_REG	(BTINTEL_PCIE_CSR_BASE + 0x118)
 #define BTINTEL_PCIE_CSR_CI_ADDR_MSB_REG	(BTINTEL_PCIE_CSR_BASE + 0x11C)
 #define BTINTEL_PCIE_CSR_IMG_RESPONSE_REG	(BTINTEL_PCIE_CSR_BASE + 0x12C)
+#define BTINTEL_PCIE_PRPH_DEV_ADDR_REG		(BTINTEL_PCIE_CSR_BASE + 0x440)
+#define BTINTEL_PCIE_PRPH_DEV_RD_REG		(BTINTEL_PCIE_CSR_BASE + 0x458)
 #define BTINTEL_PCIE_CSR_HBUS_TARG_WRPTR	(BTINTEL_PCIE_CSR_BASE + 0x460)
 
 /* BTINTEL_PCIE_CSR Function Control Register */
@@ -23,6 +25,12 @@
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_INIT		(BIT(6))
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_FUNC_INIT		(BIT(7))
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_STS	(BIT(20))
+
+#define BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_ACCESS_REQ	(BIT(21))
+/* Stop MAC Access disconnection request */
+#define BTINTEL_PCIE_CSR_FUNC_CTRL_STOP_MAC_ACCESS_DIS	(BIT(22))
+#define BTINTEL_PCIE_CSR_FUNC_CTRL_XTAL_CLK_REQ		(BIT(23))
+
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_STS	(BIT(28))
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_BUS_MASTER_DISCON	(BIT(29))
 #define BTINTEL_PCIE_CSR_FUNC_CTRL_SW_RESET		(BIT(31))
@@ -72,6 +80,7 @@ enum msix_fh_int_causes {
 /* Causes for the HW register interrupts */
 enum msix_hw_int_causes {
 	BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0	= BIT(0),	/* cause 32 */
+	BTINTEL_PCIE_MSIX_HW_INT_CAUSES_HWEXP	= BIT(3),	/* cause 35 */
 };
 
 /* PCIe device states
@@ -84,6 +93,12 @@ enum {
 	BTINTEL_PCIE_STATE_D3_HOT = 2,
 	BTINTEL_PCIE_STATE_D3_COLD = 3,
 };
+
+enum {
+	BTINTEL_PCIE_CORE_HALTED,
+	BTINTEL_PCIE_HWEXP_INPROGRESS,
+};
+
 #define BTINTEL_PCIE_MSIX_NON_AUTO_CLEAR_CAUSE	BIT(7)
 
 /* Minimum and Maximum number of MSI-X Vector
@@ -476,3 +491,11 @@ static inline void btintel_pcie_clr_reg_bits(struct btintel_pcie_data *data,
 	r &= ~bits;
 	iowrite32(r, data->base_addr + offset);
 }
+
+static inline u32 btintel_pcie_rd_dev_mem(struct btintel_pcie_data *data,
+					  u32 addr)
+{
+	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_PRPH_DEV_ADDR_REG, addr);
+	return btintel_pcie_rd_reg32(data, BTINTEL_PCIE_PRPH_DEV_RD_REG);
+}
+

From bf20a007de0ae712689b79cefc250f9b026228a0 Mon Sep 17 00:00:00 2001
From: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Date: Sat, 1 Mar 2025 03:22:58 -0300
Subject: [PATCH 2418/2753] Bluetooth: Add quirk for broken READ_VOICE_SETTING

Some fake controllers cannot be initialized because they return a smaller
report than expected for READ_VOICE_SETTING.

Signed-off-by: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h      | 8 ++++++++
 include/net/bluetooth/hci_core.h | 4 ++++
 net/bluetooth/hci_sync.c         | 3 +++
 3 files changed, 15 insertions(+)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 0d51970d809fd..6886962eca78a 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -354,6 +354,14 @@ enum {
 	 * during the hdev->setup vendor callback.
 	 */
 	HCI_QUIRK_FIXUP_LE_EXT_ADV_REPORT_PHY,
+
+	/* When this quirk is set, the HCI_OP_READ_VOICE_SETTING command is
+	 * skipped. This is required for a subset of the CSR controller clones
+	 * which erroneously claim to support it.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_BROKEN_READ_VOICE_SETTING,
 };
 
 /* HCI device flags */
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 131ff1f4ebef5..7966db4038cca 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1925,6 +1925,10 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 	((dev)->commands[20] & 0x10 && \
 	 !test_bit(HCI_QUIRK_BROKEN_READ_ENC_KEY_SIZE, &hdev->quirks))
 
+#define read_voice_setting_capable(dev) \
+	((dev)->commands[9] & 0x04 && \
+	 !test_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &(dev)->quirks))
+
 /* Use enhanced synchronous connection if command is supported and its quirk
  * has not been set.
  */
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index a43749aebf76e..fd07858387600 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3696,6 +3696,9 @@ static int hci_read_local_name_sync(struct hci_dev *hdev)
 /* Read Voice Setting */
 static int hci_read_voice_setting_sync(struct hci_dev *hdev)
 {
+	if (!read_voice_setting_capable(hdev))
+		return 0;
+
 	return __hci_cmd_sync_status(hdev, HCI_OP_READ_VOICE_SETTING,
 				     0, NULL, HCI_CMD_TIMEOUT);
 }

From 1959dab3354aff80d8383bd7ced191e532673c84 Mon Sep 17 00:00:00 2001
From: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Date: Sat, 1 Mar 2025 03:22:59 -0300
Subject: [PATCH 2419/2753] Bluetooth: Add quirk for broken READ_PAGE_SCAN_TYPE

Some fake controllers cannot be initialized because they return a smaller
report than expected for READ_PAGE_SCAN_TYPE.

Signed-off-by: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 8 ++++++++
 net/bluetooth/hci_sync.c    | 3 ++-
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6886962eca78a..b99818df8ee79 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -362,6 +362,14 @@ enum {
 	 * This quirk must be set before hci_register_dev is called.
 	 */
 	HCI_QUIRK_BROKEN_READ_VOICE_SETTING,
+
+	/* When this quirk is set, the HCI_OP_READ_PAGE_SCAN_TYPE command is
+	 * skipped. This is required for a subset of the CSR controller clones
+	 * which erroneously claim to support it.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE,
 };
 
 /* HCI device flags */
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index fd07858387600..c4c2cf51b219c 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -4132,7 +4132,8 @@ static int hci_read_page_scan_type_sync(struct hci_dev *hdev)
 	 * support the Read Page Scan Type command. Check support for
 	 * this command in the bit mask of supported commands.
 	 */
-	if (!(hdev->commands[13] & 0x01))
+	if (!(hdev->commands[13] & 0x01) ||
+	    test_bit(HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, &hdev->quirks))
 		return 0;
 
 	return __hci_cmd_sync_status(hdev, HCI_OP_READ_PAGE_SCAN_TYPE,

From dccf34a4f2b31924be2dafa4a92e1ed0447d52f8 Mon Sep 17 00:00:00 2001
From: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Date: Sat, 1 Mar 2025 03:23:00 -0300
Subject: [PATCH 2420/2753] Bluetooth: Disable SCO support if
 READ_VOICE_SETTING is unsupported/broken

A SCO connection without the proper voice_setting can cause
the controller to lock up.

Signed-off-by: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_event.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 903b0b52692aa..19e19c9f5e68a 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -930,6 +930,9 @@ static u8 hci_cc_read_buffer_size(struct hci_dev *hdev, void *data,
 		hdev->sco_pkts = 8;
 	}
 
+	if (!read_voice_setting_capable(hdev))
+		hdev->sco_pkts = 0;
+
 	hdev->acl_cnt = hdev->acl_pkts;
 	hdev->sco_cnt = hdev->sco_pkts;
 

From 06c2f64d162548f9c87880666a5fc97d2a248f3a Mon Sep 17 00:00:00 2001
From: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Date: Sat, 1 Mar 2025 03:23:01 -0300
Subject: [PATCH 2421/2753] Bluetooth: btusb: Fix regression in the
 initialization of fake Bluetooth controllers

Set HCI_READ_VOICE_SETTING and HCI_READ_PAGE_SCAN_TYPE as broken.

Once the min/max length of the commands began to be asserted, these fake
controllers can no longer be initialized because they return a smaller
report for these commands.

This affects various fake controllers reusing the 0A12:0001 VID/PID.

Fixes: c8992cffbe74 ("Bluetooth: hci_event: Use of a function table to handle Command Complete")
Signed-off-by: Pedro Nishiyama <nishiyama.pedro@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btusb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index 7080d02f610b1..5012b5ff92c8a 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -2509,6 +2509,8 @@ static int btusb_setup_csr(struct hci_dev *hdev)
 		set_bit(HCI_QUIRK_BROKEN_ERR_DATA_REPORTING, &hdev->quirks);
 		set_bit(HCI_QUIRK_BROKEN_FILTER_CLEAR_ALL, &hdev->quirks);
 		set_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks);
+		set_bit(HCI_QUIRK_BROKEN_READ_VOICE_SETTING, &hdev->quirks);
+		set_bit(HCI_QUIRK_BROKEN_READ_PAGE_SCAN_TYPE, &hdev->quirks);
 
 		/* Clear the reset quirk since this is not an actual
 		 * early Bluetooth 1.1 device from CSR.

From 73330cfd6149b7e012276cc38bd9182c7fa1ed49 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Mon, 3 Mar 2025 22:15:27 +0530
Subject: [PATCH 2422/2753] Bluetooth: btintel_pcie: Add support for device
 coredump

1. Driver registers device coredump callback
2. Dumps firmware traces as part of coredump

Co-developed-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.h      |   1 -
 drivers/bluetooth/btintel_pcie.c | 259 ++++++++++++++++++++++++++++++-
 drivers/bluetooth/btintel_pcie.h |  38 +++++
 3 files changed, 291 insertions(+), 7 deletions(-)

diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 4c21e69887a37..19530ea14905d 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -190,7 +190,6 @@ enum {
 struct btintel_data {
 	DECLARE_BITMAP(flags, __INTEL_NUM_FLAGS);
 	int (*acpi_reset_method)(struct hci_dev *hdev);
-	u32	cnvi_top;
 };
 
 #define btintel_set_flag(hdev, nr)					\
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index e8307eeb971f9..a499bad58b53f 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -59,6 +59,8 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 
 #define BTINTEL_PCIE_MAGIC_NUM	0xA5A5A5A5
 
+#define BTINTEL_PCIE_TRIGGER_REASON_USER_TRIGGER	0x17A2
+
 /* Alive interrupt context */
 enum {
 	BTINTEL_PCIE_ROM,
@@ -375,6 +377,25 @@ static void btintel_pcie_mac_init(struct btintel_pcie_data *data)
 	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg);
 }
 
+static int btintel_pcie_add_dmp_data(struct hci_dev *hdev, const void *data, int size)
+{
+	struct sk_buff *skb;
+	int err;
+
+	skb = alloc_skb(size, GFP_ATOMIC);
+	if (!skb)
+		return -ENOMEM;
+
+	skb_put_data(skb, data, size);
+	err = hci_devcd_append(hdev, skb);
+	if (err) {
+		bt_dev_err(hdev, "Failed to append data in the coredump");
+		return err;
+	}
+
+	return 0;
+}
+
 static int btintel_pcie_get_mac_access(struct btintel_pcie_data *data)
 {
 	u32 reg;
@@ -419,6 +440,194 @@ static void btintel_pcie_release_mac_access(struct btintel_pcie_data *data)
 	btintel_pcie_wr_reg32(data, BTINTEL_PCIE_CSR_FUNC_CTRL_REG, reg);
 }
 
+static void btintel_pcie_copy_tlv(struct sk_buff *skb, enum btintel_pcie_tlv_type type,
+				  void *data, int size)
+{
+	struct intel_tlv *tlv;
+
+	tlv = skb_put(skb, sizeof(*tlv) + size);
+	tlv->type = type;
+	tlv->len = size;
+	memcpy(tlv->val, data, tlv->len);
+}
+
+static int btintel_pcie_read_dram_buffers(struct btintel_pcie_data *data)
+{
+	u32 offset, prev_size, wr_ptr_status, dump_size, i;
+	struct btintel_pcie_dbgc *dbgc = &data->dbgc;
+	u8 buf_idx, dump_time_len, fw_build;
+	struct hci_dev *hdev = data->hdev;
+	struct intel_tlv *tlv;
+	struct timespec64 now;
+	struct sk_buff *skb;
+	struct tm tm_now;
+	char buf[256];
+	u16 hdr_len;
+	int ret;
+
+	wr_ptr_status = btintel_pcie_rd_dev_mem(data, BTINTEL_PCIE_DBGC_CUR_DBGBUFF_STATUS);
+	offset = wr_ptr_status & BTINTEL_PCIE_DBG_OFFSET_BIT_MASK;
+
+	buf_idx = BTINTEL_PCIE_DBGC_DBG_BUF_IDX(wr_ptr_status);
+	if (buf_idx > dbgc->count) {
+		bt_dev_warn(hdev, "Buffer index is invalid");
+		return -EINVAL;
+	}
+
+	prev_size = buf_idx * BTINTEL_PCIE_DBGC_BUFFER_SIZE;
+	if (prev_size + offset >= prev_size)
+		data->dmp_hdr.write_ptr = prev_size + offset;
+	else
+		return -EINVAL;
+
+	ktime_get_real_ts64(&now);
+	time64_to_tm(now.tv_sec, 0, &tm_now);
+	dump_time_len = snprintf(buf, sizeof(buf), "Dump Time: %02d-%02d-%04ld %02d:%02d:%02d",
+				 tm_now.tm_mday, tm_now.tm_mon + 1, tm_now.tm_year + 1900,
+				 tm_now.tm_hour, tm_now.tm_min, tm_now.tm_sec);
+
+	fw_build = snprintf(buf + dump_time_len, sizeof(buf) - dump_time_len,
+			    "Firmware Timestamp: Year %u WW %02u buildtype %u build %u",
+			    2000 + (data->dmp_hdr.fw_timestamp >> 8),
+			    data->dmp_hdr.fw_timestamp & 0xff, data->dmp_hdr.fw_build_type,
+			    data->dmp_hdr.fw_build_num);
+
+	hdr_len = sizeof(*tlv) + sizeof(data->dmp_hdr.cnvi_bt) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.write_ptr) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.wrap_ctr) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.trigger_reason) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.fw_git_sha1) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.cnvr_top) +
+		  sizeof(*tlv) + sizeof(data->dmp_hdr.cnvi_top) +
+		  sizeof(*tlv) + dump_time_len +
+		  sizeof(*tlv) + fw_build;
+
+	dump_size = hdr_len + sizeof(hdr_len);
+
+	skb = alloc_skb(dump_size, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	/* Add debug buffers data length to dump size */
+	dump_size += BTINTEL_PCIE_DBGC_BUFFER_SIZE * dbgc->count;
+
+	ret = hci_devcd_init(hdev, dump_size);
+	if (ret) {
+		bt_dev_err(hdev, "Failed to init devcoredump, err %d", ret);
+		kfree_skb(skb);
+		return ret;
+	}
+
+	skb_put_data(skb, &hdr_len, sizeof(hdr_len));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_CNVI_BT, &data->dmp_hdr.cnvi_bt,
+			      sizeof(data->dmp_hdr.cnvi_bt));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_WRITE_PTR, &data->dmp_hdr.write_ptr,
+			      sizeof(data->dmp_hdr.write_ptr));
+
+	data->dmp_hdr.wrap_ctr = btintel_pcie_rd_dev_mem(data,
+							 BTINTEL_PCIE_DBGC_DBGBUFF_WRAP_ARND);
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_WRAP_CTR, &data->dmp_hdr.wrap_ctr,
+			      sizeof(data->dmp_hdr.wrap_ctr));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_TRIGGER_REASON, &data->dmp_hdr.trigger_reason,
+			      sizeof(data->dmp_hdr.trigger_reason));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_FW_SHA, &data->dmp_hdr.fw_git_sha1,
+			      sizeof(data->dmp_hdr.fw_git_sha1));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_CNVR_TOP, &data->dmp_hdr.cnvr_top,
+			      sizeof(data->dmp_hdr.cnvr_top));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_CNVI_TOP, &data->dmp_hdr.cnvi_top,
+			      sizeof(data->dmp_hdr.cnvi_top));
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_DUMP_TIME, buf, dump_time_len);
+
+	btintel_pcie_copy_tlv(skb, BTINTEL_FW_BUILD, buf + dump_time_len, fw_build);
+
+	ret = hci_devcd_append(hdev, skb);
+	if (ret)
+		goto exit_err;
+
+	for (i = 0; i < dbgc->count; i++) {
+		ret = btintel_pcie_add_dmp_data(hdev, dbgc->bufs[i].data,
+						BTINTEL_PCIE_DBGC_BUFFER_SIZE);
+		if (ret)
+			break;
+	}
+
+exit_err:
+	hci_devcd_complete(hdev);
+	return ret;
+}
+
+static void btintel_pcie_dump_traces(struct hci_dev *hdev)
+{
+	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
+	int ret = 0;
+
+	ret = btintel_pcie_get_mac_access(data);
+	if (ret) {
+		bt_dev_err(hdev, "Failed to get mac access: (%d)", ret);
+		return;
+	}
+
+	ret = btintel_pcie_read_dram_buffers(data);
+
+	btintel_pcie_release_mac_access(data);
+
+	if (ret)
+		bt_dev_err(hdev, "Failed to dump traces: (%d)", ret);
+}
+
+static void btintel_pcie_dump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
+	u16 len = skb->len;
+	u16 *hdrlen_ptr;
+	char buf[80];
+
+	hdrlen_ptr = skb_put_zero(skb, sizeof(len));
+
+	snprintf(buf, sizeof(buf), "Controller Name: 0x%X\n",
+		 INTEL_HW_VARIANT(data->dmp_hdr.cnvi_bt));
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Firmware Build Number: %u\n",
+		 data->dmp_hdr.fw_build_num);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Driver: %s\n", data->dmp_hdr.driver_name);
+	skb_put_data(skb, buf, strlen(buf));
+
+	snprintf(buf, sizeof(buf), "Vendor: Intel\n");
+	skb_put_data(skb, buf, strlen(buf));
+
+	*hdrlen_ptr = skb->len - len;
+}
+
+static void btintel_pcie_dump_notify(struct hci_dev *hdev, int state)
+{
+	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
+
+	switch (state) {
+	case HCI_DEVCOREDUMP_IDLE:
+		data->dmp_hdr.state = HCI_DEVCOREDUMP_IDLE;
+		break;
+	case HCI_DEVCOREDUMP_ACTIVE:
+		data->dmp_hdr.state = HCI_DEVCOREDUMP_ACTIVE;
+		break;
+	case HCI_DEVCOREDUMP_TIMEOUT:
+	case HCI_DEVCOREDUMP_ABORT:
+	case HCI_DEVCOREDUMP_DONE:
+		data->dmp_hdr.state = HCI_DEVCOREDUMP_IDLE;
+		break;
+	}
+}
+
 /* This function enables BT function by setting BTINTEL_PCIE_CSR_FUNC_CTRL_MAC_INIT bit in
  * BTINTEL_PCIE_CSR_FUNC_CTRL_REG register and wait for MSI-X with
  * BTINTEL_PCIE_MSIX_HW_INT_CAUSES_GP0.
@@ -883,7 +1092,6 @@ static int btintel_pcie_recv_frame(struct btintel_pcie_data *data,
 
 static void btintel_pcie_read_hwexp(struct btintel_pcie_data *data)
 {
-	struct btintel_data *intel_data = hci_get_priv(data->hdev);
 	int len, err, offset, pending;
 	struct sk_buff *skb;
 	u8 *buf, prefix[64];
@@ -898,11 +1106,11 @@ static void btintel_pcie_read_hwexp(struct btintel_pcie_data *data)
 
 	struct tlv *tlv;
 
-	switch (intel_data->cnvi_top & 0xfff) {
+	switch (data->dmp_hdr.cnvi_top & 0xfff) {
 	case BTINTEL_CNVI_BLAZARI:
 	case BTINTEL_CNVI_BLAZARIW:
 		/* only from step B0 onwards */
-		if (INTEL_CNVX_TOP_STEP(intel_data->cnvi_top) != 0x01)
+		if (INTEL_CNVX_TOP_STEP(data->dmp_hdr.cnvi_top) != 0x01)
 			return;
 		len = BTINTEL_PCIE_BLZR_HWEXP_SIZE; /* exception data length */
 		addr = BTINTEL_PCIE_BLZR_HWEXP_DMP_ADDR;
@@ -912,7 +1120,7 @@ static void btintel_pcie_read_hwexp(struct btintel_pcie_data *data)
 		addr = BTINTEL_PCIE_SCP_HWEXP_DMP_ADDR;
 	break;
 	default:
-		bt_dev_err(data->hdev, "Unsupported cnvi 0x%8.8x", intel_data->cnvi_top);
+		bt_dev_err(data->hdev, "Unsupported cnvi 0x%8.8x", data->dmp_hdr.cnvi_top);
 		return;
 	}
 
@@ -1017,6 +1225,11 @@ static void btintel_pcie_rx_work(struct work_struct *work)
 		clear_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags);
 	}
 
+	if (test_bit(BTINTEL_PCIE_COREDUMP_INPROGRESS, &data->flags)) {
+		btintel_pcie_dump_traces(data->hdev);
+		clear_bit(BTINTEL_PCIE_COREDUMP_INPROGRESS, &data->flags);
+	}
+
 	/* Process the sk_buf in queue and send to the HCI layer */
 	while ((skb = skb_dequeue(&data->rx_skb_q))) {
 		err = btintel_pcie_recv_frame(data, skb);
@@ -1702,7 +1915,7 @@ static void btintel_pcie_release_hdev(struct btintel_pcie_data *data)
 
 static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 {
-	struct btintel_data *data = hci_get_priv(hdev);
+	struct btintel_pcie_data *data = hci_get_drvdata(hdev);
 	const u8 param[1] = { 0xFF };
 	struct intel_version_tlv ver_tlv;
 	struct sk_buff *skb;
@@ -1741,7 +1954,6 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 		goto exit_error;
 	}
 
-	data->cnvi_top = ver_tlv.cnvi_top;
 	switch (INTEL_HW_PLATFORM(ver_tlv.cnvi_bt)) {
 	case 0x37:
 		break;
@@ -1787,6 +1999,23 @@ static int btintel_pcie_setup_internal(struct hci_dev *hdev)
 		break;
 	}
 
+	data->dmp_hdr.cnvi_top = ver_tlv.cnvi_top;
+	data->dmp_hdr.cnvr_top = ver_tlv.cnvr_top;
+	data->dmp_hdr.fw_timestamp = ver_tlv.timestamp;
+	data->dmp_hdr.fw_build_type = ver_tlv.build_type;
+	data->dmp_hdr.fw_build_num = ver_tlv.build_num;
+	data->dmp_hdr.cnvi_bt = ver_tlv.cnvi_bt;
+
+	if (ver_tlv.img_type == 0x02 || ver_tlv.img_type == 0x03)
+		data->dmp_hdr.fw_git_sha1 = ver_tlv.git_sha1;
+
+	err = hci_devcd_register(hdev, btintel_pcie_dump_traces, btintel_pcie_dump_hdr,
+				 btintel_pcie_dump_notify);
+	if (err) {
+		bt_dev_err(hdev, "Failed to register coredump (%d)", err);
+		goto exit_error;
+	}
+
 	btintel_print_fseq_info(hdev);
 exit_error:
 	kfree_skb(skb);
@@ -1851,6 +2080,7 @@ static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data)
 		goto exit_error;
 	}
 
+	data->dmp_hdr.driver_name = KBUILD_MODNAME;
 	return 0;
 
 exit_error:
@@ -1963,11 +2193,28 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
 	pci_set_drvdata(pdev, NULL);
 }
 
+#ifdef CONFIG_DEV_COREDUMP
+static void btintel_pcie_coredump(struct device *dev)
+{
+	struct  pci_dev *pdev = to_pci_dev(dev);
+	struct btintel_pcie_data *data = pci_get_drvdata(pdev);
+
+	if (test_and_set_bit(BTINTEL_PCIE_COREDUMP_INPROGRESS, &data->flags))
+		return;
+
+	data->dmp_hdr.trigger_reason  = BTINTEL_PCIE_TRIGGER_REASON_USER_TRIGGER;
+	queue_work(data->workqueue, &data->rx_work);
+}
+#endif
+
 static struct pci_driver btintel_pcie_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = btintel_pcie_table,
 	.probe = btintel_pcie_probe,
 	.remove = btintel_pcie_remove,
+#ifdef CONFIG_DEV_COREDUMP
+	.driver.coredump = btintel_pcie_coredump
+#endif
 };
 module_pci_driver(btintel_pcie_driver);
 
diff --git a/drivers/bluetooth/btintel_pcie.h b/drivers/bluetooth/btintel_pcie.h
index d17808ebe7251..873178019cad0 100644
--- a/drivers/bluetooth/btintel_pcie.h
+++ b/drivers/bluetooth/btintel_pcie.h
@@ -56,6 +56,15 @@
 #define BTINTEL_PCIE_CSR_MSIX_IVAR_BASE		(BTINTEL_PCIE_CSR_MSIX_BASE + 0x0880)
 #define BTINTEL_PCIE_CSR_MSIX_IVAR(cause)	(BTINTEL_PCIE_CSR_MSIX_IVAR_BASE + (cause))
 
+/* IOSF Debug Register */
+#define BTINTEL_PCIE_DBGC_BASE_ADDR			(0xf3800300)
+#define BTINTEL_PCIE_DBGC_CUR_DBGBUFF_STATUS		(BTINTEL_PCIE_DBGC_BASE_ADDR + 0x1C)
+#define BTINTEL_PCIE_DBGC_DBGBUFF_WRAP_ARND		(BTINTEL_PCIE_DBGC_BASE_ADDR + 0x2C)
+
+#define BTINTEL_PCIE_DBG_IDX_BIT_MASK		0x0F
+#define BTINTEL_PCIE_DBGC_DBG_BUF_IDX(data)	(((data) >> 24) & BTINTEL_PCIE_DBG_IDX_BIT_MASK)
+#define BTINTEL_PCIE_DBG_OFFSET_BIT_MASK	0xFFFFFF
+
 /* The DRAM buffer count, each buffer size, and
  * fragment buffer size
  */
@@ -97,6 +106,19 @@ enum {
 enum {
 	BTINTEL_PCIE_CORE_HALTED,
 	BTINTEL_PCIE_HWEXP_INPROGRESS,
+	BTINTEL_PCIE_COREDUMP_INPROGRESS
+};
+
+enum btintel_pcie_tlv_type {
+	BTINTEL_CNVI_BT,
+	BTINTEL_WRITE_PTR,
+	BTINTEL_WRAP_CTR,
+	BTINTEL_TRIGGER_REASON,
+	BTINTEL_FW_SHA,
+	BTINTEL_CNVR_TOP,
+	BTINTEL_CNVI_TOP,
+	BTINTEL_DUMP_TIME,
+	BTINTEL_FW_BUILD,
 };
 
 #define BTINTEL_PCIE_MSIX_NON_AUTO_CLEAR_CAUSE	BIT(7)
@@ -371,6 +393,21 @@ struct btintel_pcie_dbgc {
 	struct data_buf *bufs;
 };
 
+struct btintel_pcie_dump_header {
+	const char	*driver_name;
+	u32		cnvi_top;
+	u32		cnvr_top;
+	u16		fw_timestamp;
+	u8		fw_build_type;
+	u32		fw_build_num;
+	u32		fw_git_sha1;
+	u32		cnvi_bt;
+	u32		write_ptr;
+	u32		wrap_ctr;
+	u16		trigger_reason;
+	int		state;
+};
+
 /* struct btintel_pcie_data
  * @pdev: pci device
  * @hdev: hdev device
@@ -452,6 +489,7 @@ struct btintel_pcie_data {
 	struct rxq	rxq;
 	u32	alive_intr_ctxt;
 	struct btintel_pcie_dbgc	dbgc;
+	struct btintel_pcie_dump_header dmp_hdr;
 };
 
 static inline u32 btintel_pcie_rd_reg32(struct btintel_pcie_data *data,

From ffe0eadcf11d98883258f1f4af18badf3e96970e Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Thu, 27 Feb 2025 23:56:19 +0530
Subject: [PATCH 2423/2753] Bluetooth: btnxpuart: Move vendor specific
 initialization to .post_init

This moves change baudrate and power save vendor commands from
nxp_setup() to nxp_post_init().

This also moves the baudrate restore logic from nxp_serdev_remove() to
nxp_shutdown() which ensure baudrate is restored even when HCI dev is
down, preventing baudrate mismatch between host and controller when
device is probed again next time.

In case of removal when the hdev is up and running, we have to call the
shutdown procedure explicitly before unregistering the hdev.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Co-developed-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 45 +++++++++++++++++++++--------------
 1 file changed, 27 insertions(+), 18 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 4f2f429c9800b..5f07a57532cb6 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -630,11 +630,6 @@ static void ps_init(struct hci_dev *hdev)
 
 	psdata->cur_psmode = PS_MODE_DISABLE;
 	psdata->target_ps_mode = DEFAULT_PS_MODE;
-
-	if (psdata->cur_h2c_wakeupmode != psdata->h2c_wakeupmode)
-		hci_cmd_sync_queue(hdev, send_wakeup_method_cmd, NULL, NULL);
-	if (psdata->cur_psmode != psdata->target_ps_mode)
-		hci_cmd_sync_queue(hdev, send_ps_cmd, NULL, NULL);
 }
 
 /* NXP Firmware Download Feature */
@@ -1228,11 +1223,6 @@ static int nxp_setup(struct hci_dev *hdev)
 	serdev_device_set_baudrate(nxpdev->serdev, nxpdev->fw_init_baudrate);
 	nxpdev->current_baudrate = nxpdev->fw_init_baudrate;
 
-	if (nxpdev->current_baudrate != HCI_NXP_SEC_BAUDRATE) {
-		nxpdev->new_baudrate = HCI_NXP_SEC_BAUDRATE;
-		hci_cmd_sync_queue(hdev, nxp_set_baudrate_cmd, NULL, NULL);
-	}
-
 	ps_init(hdev);
 
 	if (test_and_clear_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state))
@@ -1241,6 +1231,22 @@ static int nxp_setup(struct hci_dev *hdev)
 	return 0;
 }
 
+static int nxp_post_init(struct hci_dev *hdev)
+{
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+	struct ps_data *psdata = &nxpdev->psdata;
+
+	if (nxpdev->current_baudrate != HCI_NXP_SEC_BAUDRATE) {
+		nxpdev->new_baudrate = HCI_NXP_SEC_BAUDRATE;
+		nxp_set_baudrate_cmd(hdev, NULL);
+	}
+	if (psdata->cur_h2c_wakeupmode != psdata->h2c_wakeupmode)
+		send_wakeup_method_cmd(hdev, NULL);
+	if (psdata->cur_psmode != psdata->target_ps_mode)
+		send_ps_cmd(hdev, NULL);
+	return 0;
+}
+
 static void nxp_hw_err(struct hci_dev *hdev, u8 code)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
@@ -1273,6 +1279,9 @@ static int nxp_shutdown(struct hci_dev *hdev)
 			set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
 		}
 		kfree_skb(skb);
+	} else if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
+		nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
+		nxp_set_baudrate_cmd(hdev, NULL);
 	}
 
 	return 0;
@@ -1566,6 +1575,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	hdev->close = btnxpuart_close;
 	hdev->flush = btnxpuart_flush;
 	hdev->setup = nxp_setup;
+	hdev->post_init = nxp_post_init;
 	hdev->send  = nxp_enqueue;
 	hdev->hw_error = nxp_hw_err;
 	hdev->shutdown = nxp_shutdown;
@@ -1597,16 +1607,15 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
 		clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
 		wake_up_interruptible(&nxpdev->check_boot_sign_wait_q);
 		wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q);
-	} else {
-		/* Restore FW baudrate to fw_init_baudrate if changed.
-		 * This will ensure FW baudrate is in sync with
-		 * driver baudrate in case this driver is re-inserted.
+	}
+
+	if (test_bit(HCI_RUNNING, &hdev->flags)) {
+		/* Ensure shutdown callback is executed before unregistering, so
+		 * that baudrate is reset to initial value.
 		 */
-		if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
-			nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
-			nxp_set_baudrate_cmd(hdev, NULL);
-		}
+		nxp_shutdown(hdev);
 	}
+
 	ps_cleanup(nxpdev);
 	hci_unregister_dev(hdev);
 	hci_free_dev(hdev);

From ef3d76fd2bdff6f55423420d090167d99b709e83 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Thu, 27 Feb 2025 23:56:20 +0530
Subject: [PATCH 2424/2753] Bluetooth: btnxpuart: Add support for HCI coredump
 feature

This adds support for Bluetooth Coredump feature to BTNXPUART driver to
collect FW dumps on demand, or in case FW goes in a bad state.

To trigger manual FW dump, following command can be used:
echo 1 > /sys/class/bluetooth/hci0/device/coredump

Once FW dump is complete, it can be written to a file:
cat /sys/class/bluetooth/hci0/devcoredump/data > fw_dump

While FW dump is in progress, any HCI command will return -EBUSY.

After FW dump is complete, driver will give HCI_NXP_IND_RESET command
which soft-resets the chip, allowing FW re-download.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 147 ++++++++++++++++++++++++++++++----
 1 file changed, 132 insertions(+), 15 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 5f07a57532cb6..97c3d3ae2f72f 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -31,6 +31,7 @@
 #define BTNXPUART_SERDEV_OPEN		4
 #define BTNXPUART_IR_IN_PROGRESS	5
 #define BTNXPUART_FW_DOWNLOAD_ABORT	6
+#define BTNXPUART_FW_DUMP_IN_PROGRESS	7
 
 /* NXP HW err codes */
 #define BTNXPUART_IR_HW_ERR		0xb0
@@ -106,6 +107,8 @@
 #define HCI_NXP_SET_OPER_SPEED	0xfc09
 /* Bluetooth vendor command: Independent Reset */
 #define HCI_NXP_IND_RESET	0xfcfc
+/* Bluetooth vendor command: Trigger FW dump */
+#define HCI_NXP_TRIGGER_DUMP	0xfe91
 
 /* Bluetooth Power State : Vendor cmd params */
 #define BT_PS_ENABLE			0x02
@@ -310,6 +313,16 @@ union nxp_v3_rx_timeout_nak_u {
 	u8 buf[6];
 };
 
+/* FW dump */
+#define NXP_FW_DUMP_SIZE	(1024 * 1000)
+
+struct nxp_fw_dump_hdr {
+	__le16 seq_num;
+	__le16 reserved;
+	__le16 buf_type;
+	__le16 buf_len;
+};
+
 static u8 crc8_table[CRC8_TABLE_SIZE];
 
 /* Default configurations */
@@ -774,6 +787,16 @@ static bool is_fw_downloading(struct btnxpuart_dev *nxpdev)
 	return test_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
 }
 
+static bool ind_reset_in_progress(struct btnxpuart_dev *nxpdev)
+{
+	return test_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state);
+}
+
+static bool fw_dump_in_progress(struct btnxpuart_dev *nxpdev)
+{
+	return test_bit(BTNXPUART_FW_DUMP_IN_PROGRESS, &nxpdev->tx_state);
+}
+
 static bool process_boot_signature(struct btnxpuart_dev *nxpdev)
 {
 	if (test_bit(BTNXPUART_CHECK_BOOT_SIGNATURE, &nxpdev->tx_state)) {
@@ -1175,7 +1198,7 @@ static int nxp_set_baudrate_cmd(struct hci_dev *hdev, void *data)
 static int nxp_check_boot_sign(struct btnxpuart_dev *nxpdev)
 {
 	serdev_device_set_baudrate(nxpdev->serdev, HCI_NXP_PRI_BAUDRATE);
-	if (test_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state))
+	if (ind_reset_in_progress(nxpdev))
 		serdev_device_set_flow_control(nxpdev->serdev, false);
 	else
 		serdev_device_set_flow_control(nxpdev->serdev, true);
@@ -1204,6 +1227,73 @@ static int nxp_set_ind_reset(struct hci_dev *hdev, void *data)
 	return hci_recv_frame(hdev, skb);
 }
 
+/* Firmware dump */
+static void nxp_coredump(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	u8 pcmd = 2;
+
+	skb = nxp_drv_send_cmd(hdev, HCI_NXP_TRIGGER_DUMP, 1, &pcmd);
+	if (!IS_ERR(skb))
+		kfree_skb(skb);
+}
+
+static void nxp_coredump_hdr(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	/* Nothing to be added in FW dump header */
+}
+
+static int nxp_process_fw_dump(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	struct hci_acl_hdr *acl_hdr = (struct hci_acl_hdr *)skb_pull_data(skb,
+									  sizeof(*acl_hdr));
+	struct nxp_fw_dump_hdr *fw_dump_hdr = (struct nxp_fw_dump_hdr *)skb->data;
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+	__u16 seq_num = __le16_to_cpu(fw_dump_hdr->seq_num);
+	__u16 buf_len = __le16_to_cpu(fw_dump_hdr->buf_len);
+	int err;
+
+	if (seq_num == 0x0001) {
+		if (test_and_set_bit(BTNXPUART_FW_DUMP_IN_PROGRESS, &nxpdev->tx_state)) {
+			bt_dev_err(hdev, "FW dump already in progress");
+			goto free_skb;
+		}
+		bt_dev_warn(hdev, "==== Start FW dump ===");
+		err = hci_devcd_init(hdev, NXP_FW_DUMP_SIZE);
+		if (err < 0)
+			goto free_skb;
+
+		schedule_delayed_work(&hdev->dump.dump_timeout,
+				      msecs_to_jiffies(20000));
+	}
+
+	err = hci_devcd_append(hdev, skb_clone(skb, GFP_ATOMIC));
+	if (err < 0)
+		goto free_skb;
+
+	if (buf_len == 0) {
+		bt_dev_warn(hdev, "==== FW dump complete ===");
+		clear_bit(BTNXPUART_FW_DUMP_IN_PROGRESS, &nxpdev->tx_state);
+		hci_devcd_complete(hdev);
+		nxp_set_ind_reset(hdev, NULL);
+	}
+
+free_skb:
+	kfree_skb(skb);
+	return 0;
+}
+
+static int nxp_recv_acl_pkt(struct hci_dev *hdev, struct sk_buff *skb)
+{
+	__u16 handle = __le16_to_cpu(hci_acl_hdr(skb)->handle);
+
+	/* FW dump chunks are ACL packets with conn handle 0xfff */
+	if ((handle & 0x0FFF) == 0xFFF)
+		return nxp_process_fw_dump(hdev, skb);
+	else
+		return hci_recv_frame(hdev, skb);
+}
+
 /* NXP protocol */
 static int nxp_setup(struct hci_dev *hdev)
 {
@@ -1265,20 +1355,15 @@ static int nxp_shutdown(struct hci_dev *hdev)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	struct sk_buff *skb;
-	u8 *status;
 	u8 pcmd = 0;
 
-	if (test_bit(BTNXPUART_IR_IN_PROGRESS, &nxpdev->tx_state)) {
+	if (ind_reset_in_progress(nxpdev)) {
 		skb = nxp_drv_send_cmd(hdev, HCI_NXP_IND_RESET, 1, &pcmd);
-		if (IS_ERR(skb))
-			return PTR_ERR(skb);
-
-		status = skb_pull_data(skb, 1);
-		if (status) {
-			serdev_device_set_flow_control(nxpdev->serdev, false);
-			set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
-		}
-		kfree_skb(skb);
+		serdev_device_set_flow_control(nxpdev->serdev, false);
+		set_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
+		/* HCI_NXP_IND_RESET command may not returns any response */
+		if (!IS_ERR(skb))
+			kfree_skb(skb);
 	} else if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
 		nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
 		nxp_set_baudrate_cmd(hdev, NULL);
@@ -1298,6 +1383,16 @@ static bool nxp_wakeup(struct hci_dev *hdev)
 	return false;
 }
 
+static void nxp_reset(struct hci_dev *hdev)
+{
+	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+
+	if (!ind_reset_in_progress(nxpdev) && !fw_dump_in_progress(nxpdev)) {
+		bt_dev_dbg(hdev, "CMD Timeout detected. Resetting.");
+		nxp_set_ind_reset(hdev, NULL);
+	}
+}
+
 static int btnxpuart_queue_skb(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
@@ -1318,6 +1413,9 @@ static int nxp_enqueue(struct hci_dev *hdev, struct sk_buff *skb)
 	struct wakeup_cmd_payload wakeup_parm;
 	__le32 baudrate_parm;
 
+	if (fw_dump_in_progress(nxpdev))
+		return -EBUSY;
+
 	/* if vendor commands are received from user space (e.g. hcitool), update
 	 * driver flags accordingly and ask driver to re-send the command to FW.
 	 * In case the payload for any command does not match expected payload
@@ -1486,7 +1584,7 @@ static int btnxpuart_flush(struct hci_dev *hdev)
 }
 
 static const struct h4_recv_pkt nxp_recv_pkts[] = {
-	{ H4_RECV_ACL,          .recv = hci_recv_frame },
+	{ H4_RECV_ACL,          .recv = nxp_recv_acl_pkt },
 	{ H4_RECV_SCO,          .recv = hci_recv_frame },
 	{ H4_RECV_EVENT,        .recv = hci_recv_frame },
 	{ H4_RECV_ISO,		.recv = hci_recv_frame },
@@ -1508,11 +1606,13 @@ static size_t btnxpuart_receive_buf(struct serdev_device *serdev,
 	if (IS_ERR(nxpdev->rx_skb)) {
 		int err = PTR_ERR(nxpdev->rx_skb);
 		/* Safe to ignore out-of-sync bootloader signatures */
-		if (!is_fw_downloading(nxpdev))
+		if (!is_fw_downloading(nxpdev) &&
+		    !ind_reset_in_progress(nxpdev))
 			bt_dev_err(nxpdev->hdev, "Frame reassembly failed (%d)", err);
 		return count;
 	}
-	if (!is_fw_downloading(nxpdev))
+	if (!is_fw_downloading(nxpdev) &&
+	    !ind_reset_in_progress(nxpdev))
 		nxpdev->hdev->stat.byte_rx += count;
 	return count;
 }
@@ -1580,6 +1680,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	hdev->hw_error = nxp_hw_err;
 	hdev->shutdown = nxp_shutdown;
 	hdev->wakeup = nxp_wakeup;
+	hdev->reset = nxp_reset;
 	SET_HCIDEV_DEV(hdev, &serdev->dev);
 
 	if (hci_register_dev(hdev) < 0) {
@@ -1590,6 +1691,8 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	if (ps_setup(hdev))
 		goto probe_fail;
 
+	hci_devcd_register(hdev, nxp_coredump, nxp_coredump_hdr, NULL);
+
 	return 0;
 
 probe_fail:
@@ -1641,6 +1744,17 @@ static int nxp_serdev_resume(struct device *dev)
 }
 #endif
 
+#ifdef CONFIG_DEV_COREDUMP
+static void nxp_serdev_coredump(struct device *dev)
+{
+	struct btnxpuart_dev *nxpdev = dev_get_drvdata(dev);
+	struct hci_dev  *hdev = nxpdev->hdev;
+
+	if (hdev->dump.coredump)
+		hdev->dump.coredump(hdev);
+}
+#endif
+
 static struct btnxpuart_data w8987_data __maybe_unused = {
 	.helper_fw_name = NULL,
 	.fw_name = FIRMWARE_W8987,
@@ -1671,6 +1785,9 @@ static struct serdev_device_driver nxp_serdev_driver = {
 		.name = "btnxpuart",
 		.of_match_table = of_match_ptr(nxpuart_of_match_table),
 		.pm = &nxp_pm_ops,
+#ifdef CONFIG_DEV_COREDUMP
+		.coredump = nxp_serdev_coredump,
+#endif
 	},
 };
 

From 8e90147907c271dc5fe402c90db51e9d5976e2d8 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 3 Mar 2025 16:57:51 +0530
Subject: [PATCH 2425/2753] dt-bindings: net: bluetooth: nxp: Add support to
 set BD address

Allow user to set custom BD address for NXP chipsets.

Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 .../devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml   | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
index 04f55fac42ce8..d02e9dd847eff 100644
--- a/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
+++ b/Documentation/devicetree/bindings/net/bluetooth/nxp,88w8987-bt.yaml
@@ -17,6 +17,9 @@ description:
 maintainers:
   - Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
 
+allOf:
+  - $ref: bluetooth-controller.yaml#
+
 properties:
   compatible:
     enum:
@@ -53,7 +56,7 @@ properties:
 required:
   - compatible
 
-additionalProperties: false
+unevaluatedProperties: false
 
 examples:
   - |
@@ -66,5 +69,6 @@ examples:
             device-wakeup-gpios = <&gpio 11 GPIO_ACTIVE_HIGH>;
             nxp,wakein-pin = /bits/ 8 <18>;
             nxp,wakeout-pin = /bits/ 8 <19>;
+            local-bd-address = [66 55 44 33 22 11];
         };
     };

From 3cbf1e896c98a3b7eadfd43a4ff7b27634713070 Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 3 Mar 2025 16:57:52 +0530
Subject: [PATCH 2426/2753] Bluetooth: btnxpuart: Add support to set BD address

This adds support for setting BD address during hci registration. NXP
FW does not allow vendor commands unless it receives a reset command
after FW download and initialization done.

As a workaround, the .set_bdaddr callback function will first send the
HCI reset command, followed by the actual vendor command to set BD
address.

The driver checks for the local-bd-address property in device tree, and
if preset, it sets the HCI_QUIRK_USE_BDADDR_PROPERTY quirk.

With this quirk set, the driver's set_bdaddr callback function is called
after FW download is complete and before HCI initialization, which sends
the hci reset and 3f 22 commands. During initialization, kernel reads
the newly set BD address from the controller.

Signed-off-by: Loic Poulain <loic.poulain@linaro.org>
Signed-off-by: Johan Korsnes <johan.korsnes@remarkable.no>
Signed-off-by: Kristian Krohn <kristian.krohn@remarkable.no>
Tested-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 59 ++++++++++++++++++++++++++++++++---
 1 file changed, 54 insertions(+), 5 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 97c3d3ae2f72f..b440ba9292ec5 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 /*
  *  NXP Bluetooth driver
- *  Copyright 2023 NXP
+ *  Copyright 2023-2025 NXP
  */
 
 #include <linux/module.h>
@@ -99,13 +99,16 @@
 #define PS_STATE_AWAKE          0
 #define PS_STATE_SLEEP          1
 
-/* Bluetooth vendor command : Sleep mode */
+/* NXP Vendor Commands. Refer user manual UM11628 on nxp.com */
+/* Set custom BD Address */
+#define HCI_NXP_SET_BD_ADDR	0xfc22
+/* Set Auto-Sleep mode */
 #define HCI_NXP_AUTO_SLEEP_MODE	0xfc23
-/* Bluetooth vendor command : Wakeup method */
+/* Set Wakeup method */
 #define HCI_NXP_WAKEUP_METHOD	0xfc53
-/* Bluetooth vendor command : Set operational baudrate */
+/* Set operational baudrate */
 #define HCI_NXP_SET_OPER_SPEED	0xfc09
-/* Bluetooth vendor command: Independent Reset */
+/* Independent Reset (Soft Reset) */
 #define HCI_NXP_IND_RESET	0xfcfc
 /* Bluetooth vendor command: Trigger FW dump */
 #define HCI_NXP_TRIGGER_DUMP	0xfe91
@@ -323,6 +326,15 @@ struct nxp_fw_dump_hdr {
 	__le16 buf_len;
 };
 
+union nxp_set_bd_addr_payload {
+	struct {
+		u8 param_id;
+		u8 param_len;
+		u8 param[6];
+	} __packed data;
+	u8 buf[8];
+};
+
 static u8 crc8_table[CRC8_TABLE_SIZE];
 
 /* Default configurations */
@@ -1294,6 +1306,35 @@ static int nxp_recv_acl_pkt(struct hci_dev *hdev, struct sk_buff *skb)
 		return hci_recv_frame(hdev, skb);
 }
 
+static int nxp_set_bdaddr(struct hci_dev *hdev, const bdaddr_t *bdaddr)
+{
+	union nxp_set_bd_addr_payload pcmd;
+	int err;
+
+	pcmd.data.param_id = 0xfe;
+	pcmd.data.param_len = 6;
+	memcpy(pcmd.data.param, bdaddr, 6);
+
+	/* BD address can be assigned only after first reset command. */
+	err = __hci_cmd_sync_status(hdev, HCI_OP_RESET, 0, NULL,
+				    HCI_INIT_TIMEOUT);
+	if (err) {
+		bt_dev_err(hdev,
+			   "Reset before setting local-bd-addr failed (%d)",
+			   err);
+		return err;
+	}
+
+	err = __hci_cmd_sync_status(hdev, HCI_NXP_SET_BD_ADDR, sizeof(pcmd),
+			     pcmd.buf, HCI_CMD_TIMEOUT);
+	if (err) {
+		bt_dev_err(hdev, "Changing device address failed (%d)", err);
+		return err;
+	}
+
+	return 0;
+}
+
 /* NXP protocol */
 static int nxp_setup(struct hci_dev *hdev)
 {
@@ -1631,6 +1672,7 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 {
 	struct hci_dev *hdev;
 	struct btnxpuart_dev *nxpdev;
+	bdaddr_t ba = {0};
 
 	nxpdev = devm_kzalloc(&serdev->dev, sizeof(*nxpdev), GFP_KERNEL);
 	if (!nxpdev)
@@ -1681,8 +1723,15 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
 	hdev->shutdown = nxp_shutdown;
 	hdev->wakeup = nxp_wakeup;
 	hdev->reset = nxp_reset;
+	hdev->set_bdaddr = nxp_set_bdaddr;
 	SET_HCIDEV_DEV(hdev, &serdev->dev);
 
+	device_property_read_u8_array(&nxpdev->serdev->dev,
+				      "local-bd-address",
+				      (u8 *)&ba, sizeof(ba));
+	if (bacmp(&ba, BDADDR_ANY))
+		set_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks);
+
 	if (hci_register_dev(hdev) < 0) {
 		dev_err(&serdev->dev, "Can't register HCI device\n");
 		goto probe_fail;

From 84fd199714f498161713be4312d7f83efbf4de05 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Tue, 4 Mar 2025 21:51:35 +0530
Subject: [PATCH 2427/2753] Bluetooth: btintel_pcie: Trigger device coredump on
 hardware exception

Driver dumps device core dump on firmware exception.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index a499bad58b53f..f3ab5b41b0507 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -60,6 +60,7 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 #define BTINTEL_PCIE_MAGIC_NUM	0xA5A5A5A5
 
 #define BTINTEL_PCIE_TRIGGER_REASON_USER_TRIGGER	0x17A2
+#define BTINTEL_PCIE_TRIGGER_REASON_FW_ASSERT		0x1E61
 
 /* Alive interrupt context */
 enum {
@@ -1202,6 +1203,11 @@ static void btintel_pcie_msix_hw_exp_handler(struct btintel_pcie_data *data)
 
 	if (test_and_set_bit(BTINTEL_PCIE_HWEXP_INPROGRESS, &data->flags))
 		return;
+
+	/* Trigger device core dump when there is HW  exception */
+	if (!test_and_set_bit(BTINTEL_PCIE_COREDUMP_INPROGRESS, &data->flags))
+		data->dmp_hdr.trigger_reason = BTINTEL_PCIE_TRIGGER_REASON_FW_ASSERT;
+
 	queue_work(data->workqueue, &data->rx_work);
 }
 

From 981bc854b45a10a9d34afe13c75727acfb963ca9 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Thu, 6 Mar 2025 16:15:15 -0500
Subject: [PATCH 2428/2753] Bluetooth: btintel_pci: Fix build warning

This fixes the following warning:

drivers/bluetooth/btintel_pcie.c:695:20: warning: unused function 'btintel_pcie_in_rom' [-Wunused-function]
  695 | static inline bool btintel_pcie_in_rom(struct btintel_pcie_data *data)
      |                    ^~~~~~~~~~~~~~~~~~~

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel_pcie.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index f3ab5b41b0507..9114be1fc3cee 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -685,20 +685,6 @@ static int btintel_pcie_enable_bt(struct btintel_pcie_data *data)
 	return 0;
 }
 
-/* BIT(0) - ROM, BIT(1) - IML and BIT(3) - OP
- * Sometimes during firmware image switching from ROM to IML or IML to OP image,
- * the previous image bit is not cleared by firmware when alive interrupt is
- * received. Driver needs to take care of these sticky bits when deciding the
- * current image running on controller.
- * Ex: 0x10 and 0x11 - both represents that controller is running IML
- */
-static inline bool btintel_pcie_in_rom(struct btintel_pcie_data *data)
-{
-	return data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_ROM &&
-		!(data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_IML) &&
-		!(data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_OPFW);
-}
-
 static inline bool btintel_pcie_in_op(struct btintel_pcie_data *data)
 {
 	return data->boot_stage_cache & BTINTEL_PCIE_CSR_BOOT_STAGE_OPFW;

From 62c068a049c6f65a64eb4acd16f97f88603d33e7 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Mon, 10 Mar 2025 22:46:56 +0300
Subject: [PATCH 2429/2753] Bluetooth: Fix error code in chan_alloc_skb_cb()

The chan_alloc_skb_cb() function is supposed to return error pointers on
error.  Returning NULL will lead to a NULL dereference.

Fixes: 6b8d4a6a0314 ("Bluetooth: 6LoWPAN: Use connected oriented channel instead of fixed one")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/6lowpan.c | 7 ++++++-
 1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 1298c8685bad3..73530b8e1eaee 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -826,11 +826,16 @@ static struct sk_buff *chan_alloc_skb_cb(struct l2cap_chan *chan,
 					 unsigned long hdr_len,
 					 unsigned long len, int nb)
 {
+	struct sk_buff *skb;
+
 	/* Note that we must allocate using GFP_ATOMIC here as
 	 * this function is called originally from netdev hard xmit
 	 * function in atomic context.
 	 */
-	return bt_skb_alloc(hdr_len + len, GFP_ATOMIC);
+	skb = bt_skb_alloc(hdr_len + len, GFP_ATOMIC);
+	if (!skb)
+		return ERR_PTR(-ENOMEM);
+	return skb;
 }
 
 static void chan_suspend_cb(struct l2cap_chan *chan)

From d578422dab2e0f762c1e8352b061e570af38e8d1 Mon Sep 17 00:00:00 2001
From: Arkadiusz Bokowy <arkadiusz.bokowy@gmail.com>
Date: Wed, 12 Mar 2025 20:09:43 +0100
Subject: [PATCH 2430/2753] Bluetooth: hci_event: Fix connection regression
 between LE and non-LE adapters

Due to a typo during defining HCI errors it is not possible to connect
LE-capable device with BR/EDR only adapter. The connection is terminated
by the LE adapter because the invalid LL params error code is treated
as unsupported remote feature.

Fixes: 79c0868ad65a ("Bluetooth: hci_event: Use HCI error defines instead of magic values")
Signed-off-by: Arkadiusz Bokowy <arkadiusz.bokowy@gmail.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index b99818df8ee79..aa684d2b079fa 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -699,7 +699,7 @@ enum {
 #define HCI_ERROR_REMOTE_POWER_OFF	0x15
 #define HCI_ERROR_LOCAL_HOST_TERM	0x16
 #define HCI_ERROR_PAIRING_NOT_ALLOWED	0x18
-#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE	0x1e
+#define HCI_ERROR_UNSUPPORTED_REMOTE_FEATURE	0x1a
 #define HCI_ERROR_INVALID_LL_PARAMS	0x1e
 #define HCI_ERROR_UNSPECIFIED		0x1f
 #define HCI_ERROR_ADVERTISING_TIMEOUT	0x3c

From 7a829d7d385da98cc5693e17af3cd43c000cc427 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 12 Mar 2025 11:14:20 -0400
Subject: [PATCH 2431/2753] Bluetooth: hci_core: Enable buffer flow control for
 SCO/eSCO

This enables buffer flow control for SCO/eSCO
(see: Bluetooth Core 6.0 spec: 6.22. Synchronous Flow Control Enable),
recently this has caused the following problem and is actually a nice
addition for the likes of Socket TX complete:

< HCI Command: Read Buffer Size (0x04|0x0005) plen 0
> HCI Event: Command Complete (0x0e) plen 11
      Read Buffer Size (0x04|0x0005) ncmd 1
        Status: Success (0x00)
        ACL MTU: 1021 ACL max packet: 5
        SCO MTU: 240  SCO max packet: 8
...
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
< SCO Data TX: Handle 257 flags 0x00 dlen 120
> HCI Event: Hardware Error (0x10) plen 1
        Code: 0x0a

To fix the code will now attempt to enable buffer flow control when
HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED is set by the driver:

< HCI Command: Write Sync Fl.. (0x03|0x002f) plen 1
        Flow control: Enabled (0x01)
> HCI Event: Command Complete (0x0e) plen 4
      Write Sync Flow Control Enable (0x03|0x002f) ncmd 1
        Status: Success (0x00)

On success then HCI_SCO_FLOWCTL would be set which indicates sco_cnt
shall be used for flow contro.

Fixes: 7fedd3bb6b77 ("Bluetooth: Prioritize SCO traffic")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Tested-by: Pauli Virtanen <pav@iki.fi>
---
 include/net/bluetooth/hci.h      | 13 +++++++
 include/net/bluetooth/hci_core.h |  1 +
 net/bluetooth/hci_core.c         | 62 +++++++++++++++-----------------
 net/bluetooth/hci_event.c        |  2 ++
 net/bluetooth/hci_sync.c         | 24 +++++++++++++
 5 files changed, 68 insertions(+), 34 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index aa684d2b079fa..6da61c185c949 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -208,6 +208,13 @@ enum {
 	 */
 	HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 
+	/* When this quirk is set consider Sync Flow Control as supported by
+	 * the driver.
+	 *
+	 * This quirk must be set before hci_register_dev is called.
+	 */
+	HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED,
+
 	/* When this quirk is set, the LE states reported through the
 	 * HCI_LE_READ_SUPPORTED_STATES are invalid/broken.
 	 *
@@ -448,6 +455,7 @@ enum {
 	HCI_WIDEBAND_SPEECH_ENABLED,
 	HCI_EVENT_FILTER_CONFIGURED,
 	HCI_PA_SYNC,
+	HCI_SCO_FLOWCTL,
 
 	HCI_DUT_MODE,
 	HCI_VENDOR_DIAG,
@@ -1544,6 +1552,11 @@ struct hci_rp_read_tx_power {
 	__s8     tx_power;
 } __packed;
 
+#define HCI_OP_WRITE_SYNC_FLOWCTL	0x0c2f
+struct hci_cp_write_sync_flowctl {
+	__u8     enable;
+} __packed;
+
 #define HCI_OP_READ_PAGE_SCAN_TYPE	0x0c46
 struct hci_rp_read_page_scan_type {
 	__u8     status;
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 7966db4038cca..f78e4298e39ac 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -1858,6 +1858,7 @@ void hci_conn_del_sysfs(struct hci_conn *conn);
 #define lmp_hold_capable(dev)      ((dev)->features[0][0] & LMP_HOLD)
 #define lmp_sniff_capable(dev)     ((dev)->features[0][0] & LMP_SNIFF)
 #define lmp_park_capable(dev)      ((dev)->features[0][1] & LMP_PARK)
+#define lmp_sco_capable(dev)       ((dev)->features[0][1] & LMP_SCO)
 #define lmp_inq_rssi_capable(dev)  ((dev)->features[0][3] & LMP_RSSI_INQ)
 #define lmp_esco_capable(dev)      ((dev)->features[0][3] & LMP_ESCO)
 #define lmp_bredr_capable(dev)     (!((dev)->features[0][4] & LMP_NO_BREDR))
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 012fc107901a6..94d9147612daf 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3552,42 +3552,27 @@ static void __check_timeout(struct hci_dev *hdev, unsigned int cnt, u8 type)
 }
 
 /* Schedule SCO */
-static void hci_sched_sco(struct hci_dev *hdev)
+static void hci_sched_sco(struct hci_dev *hdev, __u8 type)
 {
 	struct hci_conn *conn;
 	struct sk_buff *skb;
-	int quote;
+	int quote, *cnt;
+	unsigned int pkts = hdev->sco_pkts;
 
-	BT_DBG("%s", hdev->name);
+	bt_dev_dbg(hdev, "type %u", type);
 
-	if (!hci_conn_num(hdev, SCO_LINK))
+	if (!hci_conn_num(hdev, type) || !pkts)
 		return;
 
-	while (hdev->sco_cnt && (conn = hci_low_sent(hdev, SCO_LINK, &quote))) {
-		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
-			BT_DBG("skb %p len %d", skb, skb->len);
-			hci_send_frame(hdev, skb);
-
-			conn->sent++;
-			if (conn->sent == ~0)
-				conn->sent = 0;
-		}
-	}
-}
-
-static void hci_sched_esco(struct hci_dev *hdev)
-{
-	struct hci_conn *conn;
-	struct sk_buff *skb;
-	int quote;
-
-	BT_DBG("%s", hdev->name);
-
-	if (!hci_conn_num(hdev, ESCO_LINK))
-		return;
+	/* Use sco_pkts if flow control has not been enabled which will limit
+	 * the amount of buffer sent in a row.
+	 */
+	if (!hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL))
+		cnt = &pkts;
+	else
+		cnt = &hdev->sco_cnt;
 
-	while (hdev->sco_cnt && (conn = hci_low_sent(hdev, ESCO_LINK,
-						     &quote))) {
+	while (*cnt && (conn = hci_low_sent(hdev, type, &quote))) {
 		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
 			BT_DBG("skb %p len %d", skb, skb->len);
 			hci_send_frame(hdev, skb);
@@ -3595,8 +3580,17 @@ static void hci_sched_esco(struct hci_dev *hdev)
 			conn->sent++;
 			if (conn->sent == ~0)
 				conn->sent = 0;
+			(*cnt)--;
 		}
 	}
+
+	/* Rescheduled if all packets were sent and flow control is not enabled
+	 * as there could be more packets queued that could not be sent and
+	 * since no HCI_EV_NUM_COMP_PKTS event will be generated the reschedule
+	 * needs to be forced.
+	 */
+	if (!pkts && !hci_dev_test_flag(hdev, HCI_SCO_FLOWCTL))
+		queue_work(hdev->workqueue, &hdev->tx_work);
 }
 
 static void hci_sched_acl_pkt(struct hci_dev *hdev)
@@ -3632,8 +3626,8 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev)
 			chan->conn->sent++;
 
 			/* Send pending SCO packets right away */
-			hci_sched_sco(hdev);
-			hci_sched_esco(hdev);
+			hci_sched_sco(hdev, SCO_LINK);
+			hci_sched_sco(hdev, ESCO_LINK);
 		}
 	}
 
@@ -3688,8 +3682,8 @@ static void hci_sched_le(struct hci_dev *hdev)
 			chan->conn->sent++;
 
 			/* Send pending SCO packets right away */
-			hci_sched_sco(hdev);
-			hci_sched_esco(hdev);
+			hci_sched_sco(hdev, SCO_LINK);
+			hci_sched_sco(hdev, ESCO_LINK);
 		}
 	}
 
@@ -3734,8 +3728,8 @@ static void hci_tx_work(struct work_struct *work)
 
 	if (!hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) {
 		/* Schedule queues and send stuff to HCI driver */
-		hci_sched_sco(hdev);
-		hci_sched_esco(hdev);
+		hci_sched_sco(hdev, SCO_LINK);
+		hci_sched_sco(hdev, ESCO_LINK);
 		hci_sched_iso(hdev);
 		hci_sched_acl(hdev);
 		hci_sched_le(hdev);
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 19e19c9f5e68a..6d0138b778aa2 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4445,9 +4445,11 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 			break;
 
 		case SCO_LINK:
+		case ESCO_LINK:
 			hdev->sco_cnt += count;
 			if (hdev->sco_cnt > hdev->sco_pkts)
 				hdev->sco_cnt = hdev->sco_pkts;
+
 			break;
 
 		case ISO_LINK:
diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
index c4c2cf51b219c..609b035e5c904 100644
--- a/net/bluetooth/hci_sync.c
+++ b/net/bluetooth/hci_sync.c
@@ -3769,6 +3769,28 @@ static int hci_write_ca_timeout_sync(struct hci_dev *hdev)
 				     sizeof(param), &param, HCI_CMD_TIMEOUT);
 }
 
+/* Enable SCO flow control if supported */
+static int hci_write_sync_flowctl_sync(struct hci_dev *hdev)
+{
+	struct hci_cp_write_sync_flowctl cp;
+	int err;
+
+	/* Check if the controller supports SCO and HCI_OP_WRITE_SYNC_FLOWCTL */
+	if (!lmp_sco_capable(hdev) || !(hdev->commands[10] & BIT(4)) ||
+	    !test_bit(HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED, &hdev->quirks))
+		return 0;
+
+	memset(&cp, 0, sizeof(cp));
+	cp.enable = 0x01;
+
+	err = __hci_cmd_sync_status(hdev, HCI_OP_WRITE_SYNC_FLOWCTL,
+				    sizeof(cp), &cp, HCI_CMD_TIMEOUT);
+	if (!err)
+		hci_dev_set_flag(hdev, HCI_SCO_FLOWCTL);
+
+	return err;
+}
+
 /* BR Controller init stage 2 command sequence */
 static const struct hci_init_stage br_init2[] = {
 	/* HCI_OP_READ_BUFFER_SIZE */
@@ -3787,6 +3809,8 @@ static const struct hci_init_stage br_init2[] = {
 	HCI_INIT(hci_clear_event_filter_sync),
 	/* HCI_OP_WRITE_CA_TIMEOUT */
 	HCI_INIT(hci_write_ca_timeout_sync),
+	/* HCI_OP_WRITE_SYNC_FLOWCTL */
+	HCI_INIT(hci_write_sync_flowctl_sync),
 	{}
 };
 

From 337721541e07a3081b7e084e02c533c7a3ebc087 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 12 Mar 2025 11:14:21 -0400
Subject: [PATCH 2432/2753] Bluetooth: hci_vhci: Mark Sync Flow Control as
 supported

This sets HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED which indicates that
controllers created by vhci driver support Sync Flow Control.

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/hci_vhci.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index 963741490106a..a51935d37e5d7 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -416,6 +416,7 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 	hdev->wakeup = vhci_wakeup;
 	hdev->setup = vhci_setup;
 	set_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks);
+	set_bit(HCI_QUIRK_SYNC_FLOWCTL_SUPPORTED, &hdev->quirks);
 
 	/* bit 6 is for external configuration */
 	if (opcode & 0x40)

From f3db7b21641c288fbdde7070783dfe1a105b0670 Mon Sep 17 00:00:00 2001
From: Wentao Guan <guanwentao@uniontech.com>
Date: Tue, 18 Mar 2025 02:50:34 +0800
Subject: [PATCH 2433/2753] Bluetooth: HCI: Add definition of
 hci_rp_remote_name_req_cancel

Return Parameters is not only status, also bdaddr:

BLUETOOTH CORE SPECIFICATION Version 5.4 | Vol 4, Part E
page 1870:
BLUETOOTH CORE SPECIFICATION Version 5.0 | Vol 2, Part E
page 802:

Return parameters:
  Status:
  Size: 1 octet
  BD_ADDR:
  Size: 6 octets

Note that it also fixes the warning:
"Bluetooth: hci0: unexpected cc 0x041a length: 7 > 1"

Fixes: c8992cffbe741 ("Bluetooth: hci_event: Use of a function table to handle Command Complete")
Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci.h | 5 +++++
 net/bluetooth/hci_event.c   | 6 +++---
 2 files changed, 8 insertions(+), 3 deletions(-)

diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index 6da61c185c949..a8586c3058c7c 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -879,6 +879,11 @@ struct hci_cp_remote_name_req_cancel {
 	bdaddr_t bdaddr;
 } __packed;
 
+struct hci_rp_remote_name_req_cancel {
+	__u8     status;
+	bdaddr_t bdaddr;
+} __packed;
+
 #define HCI_OP_READ_REMOTE_FEATURES	0x041b
 struct hci_cp_read_remote_features {
 	__le16   handle;
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 6d0138b778aa2..0df4a0e082c82 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -151,7 +151,7 @@ static u8 hci_cc_exit_periodic_inq(struct hci_dev *hdev, void *data,
 static u8 hci_cc_remote_name_req_cancel(struct hci_dev *hdev, void *data,
 					struct sk_buff *skb)
 {
-	struct hci_ev_status *rp = data;
+	struct hci_rp_remote_name_req_cancel *rp = data;
 
 	bt_dev_dbg(hdev, "status 0x%2.2x", rp->status);
 
@@ -4015,8 +4015,8 @@ static const struct hci_cc {
 	HCI_CC_STATUS(HCI_OP_INQUIRY_CANCEL, hci_cc_inquiry_cancel),
 	HCI_CC_STATUS(HCI_OP_PERIODIC_INQ, hci_cc_periodic_inq),
 	HCI_CC_STATUS(HCI_OP_EXIT_PERIODIC_INQ, hci_cc_exit_periodic_inq),
-	HCI_CC_STATUS(HCI_OP_REMOTE_NAME_REQ_CANCEL,
-		      hci_cc_remote_name_req_cancel),
+	HCI_CC(HCI_OP_REMOTE_NAME_REQ_CANCEL, hci_cc_remote_name_req_cancel,
+	       sizeof(struct hci_rp_remote_name_req_cancel)),
 	HCI_CC(HCI_OP_ROLE_DISCOVERY, hci_cc_role_discovery,
 	       sizeof(struct hci_rp_role_discovery)),
 	HCI_CC(HCI_OP_READ_LINK_POLICY, hci_cc_read_link_policy,

From 5b6c87cdb955441bd24e22f94c55434970d03afb Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 17 Mar 2025 16:35:16 -0400
Subject: [PATCH 2434/2753] HCI: coredump: Log devcd dumps into the monitor

This logs the devcd dumps with hci_recv_diag so they appear in the
monitor traces with proper timestamps which can then be used to relate
the HCI traffic that caused the dump:

= Vendor Diagnostic (len 174)
        42 6c 75 65 74 6f 6f 74 68 20 64 65 76 63 6f 72  Bluetooth devcor
        65 64 75 6d 70 0a 53 74 61 74 65 3a 20 32 0a 00  edump.State: 2..
        43 6f 6e 74 72 6f 6c 6c 65 72 20 4e 61 6d 65 3a  Controller Name:
        20 76 68 63 69 5f 63 74 72 6c 0a 46 69 72 6d 77   vhci_ctrl.Firmw
        61 72 65 20 56 65 72 73 69 6f 6e 3a 20 76 68 63  are Version: vhc
        69 5f 66 77 0a 44 72 69 76 65 72 3a 20 76 68 63  i_fw.Driver: vhc
        69 5f 64 72 76 0a 56 65 6e 64 6f 72 3a 20 76 68  i_drv.Vendor: vh
        63 69 0a 2d 2d 2d 20 53 74 61 72 74 20 64 75 6d  ci.--- Start dum
        70 20 2d 2d 2d 0a 74 65 73 74 20 64 61 74 61 00  p ---.test data.
        00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
        00 00 00 00 00 00 00 00 00 00 00 00 00 00        ..............

Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/coredump.c | 28 +++++++++++++++++++++++-----
 1 file changed, 23 insertions(+), 5 deletions(-)

diff --git a/net/bluetooth/coredump.c b/net/bluetooth/coredump.c
index c18df3a086075..819eacb387622 100644
--- a/net/bluetooth/coredump.c
+++ b/net/bluetooth/coredump.c
@@ -240,6 +240,26 @@ static void hci_devcd_handle_pkt_pattern(struct hci_dev *hdev,
 		bt_dev_dbg(hdev, "Failed to set pattern");
 }
 
+static void hci_devcd_dump(struct hci_dev *hdev)
+{
+	struct sk_buff *skb;
+	u32 size;
+
+	bt_dev_dbg(hdev, "state %d", hdev->dump.state);
+
+	size = hdev->dump.tail - hdev->dump.head;
+
+	/* Emit a devcoredump with the available data */
+	dev_coredumpv(&hdev->dev, hdev->dump.head, size, GFP_KERNEL);
+
+	/* Send a copy to monitor as a diagnostic packet */
+	skb = bt_skb_alloc(size, GFP_ATOMIC);
+	if (skb) {
+		skb_put_data(skb, hdev->dump.head, size);
+		hci_recv_diag(hdev, skb);
+	}
+}
+
 static void hci_devcd_handle_pkt_complete(struct hci_dev *hdev,
 					  struct sk_buff *skb)
 {
@@ -256,7 +276,7 @@ static void hci_devcd_handle_pkt_complete(struct hci_dev *hdev,
 	bt_dev_dbg(hdev, "complete with size %u (expect %zu)", dump_size,
 		   hdev->dump.alloc_size);
 
-	dev_coredumpv(&hdev->dev, hdev->dump.head, dump_size, GFP_KERNEL);
+	hci_devcd_dump(hdev);
 }
 
 static void hci_devcd_handle_pkt_abort(struct hci_dev *hdev,
@@ -275,8 +295,7 @@ static void hci_devcd_handle_pkt_abort(struct hci_dev *hdev,
 	bt_dev_dbg(hdev, "aborted with size %u (expect %zu)", dump_size,
 		   hdev->dump.alloc_size);
 
-	/* Emit a devcoredump with the available data */
-	dev_coredumpv(&hdev->dev, hdev->dump.head, dump_size, GFP_KERNEL);
+	hci_devcd_dump(hdev);
 }
 
 /* Bluetooth devcoredump state machine.
@@ -391,8 +410,7 @@ void hci_devcd_timeout(struct work_struct *work)
 	bt_dev_dbg(hdev, "timeout with size %u (expect %zu)", dump_size,
 		   hdev->dump.alloc_size);
 
-	/* Emit a devcoredump with the available data */
-	dev_coredumpv(&hdev->dev, hdev->dump.head, dump_size, GFP_KERNEL);
+	hci_devcd_dump(hdev);
 
 	hci_devcd_reset(hdev);
 

From c6c3dc495a6ce5b9dfed4df08c3220207e7103bd Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Tue, 18 Mar 2025 21:06:42 +0200
Subject: [PATCH 2435/2753] net-timestamp: COMPLETION timestamp on packet tx
 completion

Add SOF_TIMESTAMPING_TX_COMPLETION, for requesting a software timestamp
when hardware reports a packet completed.

Completion tstamp is useful for Bluetooth, as hardware timestamps do not
exist in the HCI specification except for ISO packets, and the hardware
has a queue where packets may wait.  In this case the software SND
timestamp only reflects the kernel-side part of the total latency
(usually small) and queue length (usually 0 unless HW buffers
congested), whereas the completion report time is more informative of
the true latency.

It may also be useful in other cases where HW TX timestamps cannot be
obtained and user wants to estimate an upper bound to when the TX
probably happened.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 Documentation/networking/timestamping.rst | 8 ++++++++
 include/linux/skbuff.h                    | 7 ++++---
 include/uapi/linux/errqueue.h             | 1 +
 include/uapi/linux/net_tstamp.h           | 6 ++++--
 net/core/skbuff.c                         | 2 ++
 net/ethtool/common.c                      | 1 +
 net/socket.c                              | 3 +++
 7 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/timestamping.rst b/Documentation/networking/timestamping.rst
index 61ef9da10e284..b8fef8101176d 100644
--- a/Documentation/networking/timestamping.rst
+++ b/Documentation/networking/timestamping.rst
@@ -140,6 +140,14 @@ SOF_TIMESTAMPING_TX_ACK:
   cumulative acknowledgment. The mechanism ignores SACK and FACK.
   This flag can be enabled via both socket options and control messages.
 
+SOF_TIMESTAMPING_TX_COMPLETION:
+  Request tx timestamps on packet tx completion.  The completion
+  timestamp is generated by the kernel when it receives packet a
+  completion report from the hardware. Hardware may report multiple
+  packets at once, and completion timestamps reflect the timing of the
+  report and not actual tx time. This flag can be enabled via both
+  socket options and control messages.
+
 
 1.3.2 Timestamp Reporting
 ^^^^^^^^^^^^^^^^^^^^^^^^^
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cd8294cdc2496..b974a277975a8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -478,8 +478,8 @@ enum {
 	/* device driver is going to provide hardware time stamp */
 	SKBTX_IN_PROGRESS = 1 << 2,
 
-	/* reserved */
-	SKBTX_RESERVED = 1 << 3,
+	/* generate software time stamp on packet tx completion */
+	SKBTX_COMPLETION_TSTAMP = 1 << 3,
 
 	/* generate wifi status information (where possible) */
 	SKBTX_WIFI_STATUS = 1 << 4,
@@ -498,7 +498,8 @@ enum {
 
 #define SKBTX_ANY_SW_TSTAMP	(SKBTX_SW_TSTAMP    | \
 				 SKBTX_SCHED_TSTAMP | \
-				 SKBTX_BPF)
+				 SKBTX_BPF          | \
+				 SKBTX_COMPLETION_TSTAMP)
 #define SKBTX_ANY_TSTAMP	(SKBTX_HW_TSTAMP | \
 				 SKBTX_ANY_SW_TSTAMP)
 
diff --git a/include/uapi/linux/errqueue.h b/include/uapi/linux/errqueue.h
index 3c70e8ac14b8d..1ea47309d7726 100644
--- a/include/uapi/linux/errqueue.h
+++ b/include/uapi/linux/errqueue.h
@@ -73,6 +73,7 @@ enum {
 	SCM_TSTAMP_SND,		/* driver passed skb to NIC, or HW */
 	SCM_TSTAMP_SCHED,	/* data entered the packet scheduler */
 	SCM_TSTAMP_ACK,		/* data acknowledged by peer */
+	SCM_TSTAMP_COMPLETION,	/* packet tx completion */
 };
 
 #endif /* _UAPI_LINUX_ERRQUEUE_H */
diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h
index 55b0ab51096c1..383213de612a8 100644
--- a/include/uapi/linux/net_tstamp.h
+++ b/include/uapi/linux/net_tstamp.h
@@ -44,8 +44,9 @@ enum {
 	SOF_TIMESTAMPING_BIND_PHC = (1 << 15),
 	SOF_TIMESTAMPING_OPT_ID_TCP = (1 << 16),
 	SOF_TIMESTAMPING_OPT_RX_FILTER = (1 << 17),
+	SOF_TIMESTAMPING_TX_COMPLETION = (1 << 18),
 
-	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_OPT_RX_FILTER,
+	SOF_TIMESTAMPING_LAST = SOF_TIMESTAMPING_TX_COMPLETION,
 	SOF_TIMESTAMPING_MASK = (SOF_TIMESTAMPING_LAST - 1) |
 				 SOF_TIMESTAMPING_LAST
 };
@@ -58,7 +59,8 @@ enum {
 #define SOF_TIMESTAMPING_TX_RECORD_MASK	(SOF_TIMESTAMPING_TX_HARDWARE | \
 					 SOF_TIMESTAMPING_TX_SOFTWARE | \
 					 SOF_TIMESTAMPING_TX_SCHED | \
-					 SOF_TIMESTAMPING_TX_ACK)
+					 SOF_TIMESTAMPING_TX_ACK | \
+					 SOF_TIMESTAMPING_TX_COMPLETION)
 
 /**
  * struct so_timestamping - SO_TIMESTAMPING parameter
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ab8acb737b932..6cbf77bc61fce 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -5523,6 +5523,8 @@ static bool skb_tstamp_tx_report_so_timestamping(struct sk_buff *skb,
 						    SKBTX_SW_TSTAMP);
 	case SCM_TSTAMP_ACK:
 		return TCP_SKB_CB(skb)->txstamp_ack & TSTAMP_ACK_SK;
+	case SCM_TSTAMP_COMPLETION:
+		return skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP;
 	}
 
 	return false;
diff --git a/net/ethtool/common.c b/net/ethtool/common.c
index 7e3c16856c1a8..0cb6da1f692a0 100644
--- a/net/ethtool/common.c
+++ b/net/ethtool/common.c
@@ -476,6 +476,7 @@ const char sof_timestamping_names[][ETH_GSTRING_LEN] = {
 	[const_ilog2(SOF_TIMESTAMPING_BIND_PHC)]     = "bind-phc",
 	[const_ilog2(SOF_TIMESTAMPING_OPT_ID_TCP)]   = "option-id-tcp",
 	[const_ilog2(SOF_TIMESTAMPING_OPT_RX_FILTER)] = "option-rx-filter",
+	[const_ilog2(SOF_TIMESTAMPING_TX_COMPLETION)] = "tx-completion",
 };
 static_assert(ARRAY_SIZE(sof_timestamping_names) == __SOF_TIMESTAMPING_CNT);
 
diff --git a/net/socket.c b/net/socket.c
index b64ecf2722e7b..e3d879b532781 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -689,6 +689,9 @@ void __sock_tx_timestamp(__u32 tsflags, __u8 *tx_flags)
 	if (tsflags & SOF_TIMESTAMPING_TX_SCHED)
 		flags |= SKBTX_SCHED_TSTAMP;
 
+	if (tsflags & SOF_TIMESTAMPING_TX_COMPLETION)
+		flags |= SKBTX_COMPLETION_TSTAMP;
+
 	*tx_flags = flags;
 }
 EXPORT_SYMBOL(__sock_tx_timestamp);

From 6fdcfd541ec802adb6631bdbf8d66fe4da25f1ef Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Tue, 18 Mar 2025 21:06:43 +0200
Subject: [PATCH 2436/2753] Bluetooth: add support for skb TX SND/COMPLETION
 timestamping

Support enabling TX timestamping for some skbs, and track them until
packet completion. Generate software SCM_TSTAMP_COMPLETION when getting
completion report from hardware.

Generate software SCM_TSTAMP_SND before sending to driver. Sending from
driver requires changes in the driver API, and drivers mostly are going
to send the skb immediately.

Make the default situation with no COMPLETION TX timestamping more
efficient by only counting packets in the queue when there is nothing to
track.  When there is something to track, we need to make clones, since
the driver may modify sent skbs.

The tx_q queue length is bounded by the hdev flow control, which will
not send new packets before it has got completion reports for old ones.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/hci_core.h |  20 +++++
 net/bluetooth/hci_conn.c         | 122 +++++++++++++++++++++++++++++++
 net/bluetooth/hci_core.c         |  15 +++-
 net/bluetooth/hci_event.c        |   4 +
 4 files changed, 157 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index f78e4298e39ac..5115da34f8812 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -261,6 +261,12 @@ struct adv_info {
 	struct delayed_work	rpa_expired_cb;
 };
 
+struct tx_queue {
+	struct sk_buff_head queue;
+	unsigned int extra;
+	unsigned int tracked;
+};
+
 #define HCI_MAX_ADV_INSTANCES		5
 #define HCI_DEFAULT_ADV_DURATION	2
 
@@ -733,6 +739,8 @@ struct hci_conn {
 	struct sk_buff_head data_q;
 	struct list_head chan_list;
 
+	struct tx_queue tx_q;
+
 	struct delayed_work disc_work;
 	struct delayed_work auto_accept_work;
 	struct delayed_work idle_work;
@@ -1572,6 +1580,18 @@ void hci_conn_enter_active_mode(struct hci_conn *conn, __u8 force_active);
 void hci_conn_failed(struct hci_conn *conn, u8 status);
 u8 hci_conn_set_handle(struct hci_conn *conn, u16 handle);
 
+void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb);
+void hci_conn_tx_dequeue(struct hci_conn *conn);
+void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
+			    const struct sockcm_cookie *sockc);
+
+static inline void hci_sockcm_init(struct sockcm_cookie *sockc, struct sock *sk)
+{
+	*sockc = (struct sockcm_cookie) {
+		.tsflags = READ_ONCE(sk->sk_tsflags),
+	};
+}
+
 /*
  * hci_conn_get() and hci_conn_put() are used to control the life-time of an
  * "hci_conn" object. They do not guarantee that the hci_conn object is running,
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
index d097e308a7554..95972fd4c7843 100644
--- a/net/bluetooth/hci_conn.c
+++ b/net/bluetooth/hci_conn.c
@@ -27,6 +27,7 @@
 
 #include <linux/export.h>
 #include <linux/debugfs.h>
+#include <linux/errqueue.h>
 
 #include <net/bluetooth/bluetooth.h>
 #include <net/bluetooth/hci_core.h>
@@ -1002,6 +1003,7 @@ static struct hci_conn *__hci_conn_add(struct hci_dev *hdev, int type, bdaddr_t
 	}
 
 	skb_queue_head_init(&conn->data_q);
+	skb_queue_head_init(&conn->tx_q.queue);
 
 	INIT_LIST_HEAD(&conn->chan_list);
 	INIT_LIST_HEAD(&conn->link_list);
@@ -1155,6 +1157,7 @@ void hci_conn_del(struct hci_conn *conn)
 	}
 
 	skb_queue_purge(&conn->data_q);
+	skb_queue_purge(&conn->tx_q.queue);
 
 	/* Remove the connection from the list and cleanup its remaining
 	 * state. This is a separate function since for some cases like
@@ -3064,3 +3067,122 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
 	 */
 	return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL);
 }
+
+void hci_setup_tx_timestamp(struct sk_buff *skb, size_t key_offset,
+			    const struct sockcm_cookie *sockc)
+{
+	struct sock *sk = skb ? skb->sk : NULL;
+
+	/* This shall be called on a single skb of those generated by user
+	 * sendmsg(), and only when the sendmsg() does not return error to
+	 * user. This is required for keeping the tskey that increments here in
+	 * sync with possible sendmsg() counting by user.
+	 *
+	 * Stream sockets shall set key_offset to sendmsg() length in bytes
+	 * and call with the last fragment, others to 1 and first fragment.
+	 */
+
+	if (!skb || !sockc || !sk || !key_offset)
+		return;
+
+	sock_tx_timestamp(sk, sockc, &skb_shinfo(skb)->tx_flags);
+
+	if (sockc->tsflags & SOF_TIMESTAMPING_OPT_ID &&
+	    sockc->tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) {
+		if (sockc->tsflags & SOCKCM_FLAG_TS_OPT_ID) {
+			skb_shinfo(skb)->tskey = sockc->ts_opt_id;
+		} else {
+			int key = atomic_add_return(key_offset, &sk->sk_tskey);
+
+			skb_shinfo(skb)->tskey = key - 1;
+		}
+	}
+}
+
+void hci_conn_tx_queue(struct hci_conn *conn, struct sk_buff *skb)
+{
+	struct tx_queue *comp = &conn->tx_q;
+	bool track = false;
+
+	/* Emit SND now, ie. just before sending to driver */
+	if (skb_shinfo(skb)->tx_flags & SKBTX_SW_TSTAMP)
+		__skb_tstamp_tx(skb, NULL, NULL, skb->sk, SCM_TSTAMP_SND);
+
+	/* COMPLETION tstamp is emitted for tracked skb later in Number of
+	 * Completed Packets event. Available only for flow controlled cases.
+	 *
+	 * TODO: SCO support without flowctl (needs to be done in drivers)
+	 */
+	switch (conn->type) {
+	case ISO_LINK:
+	case ACL_LINK:
+	case LE_LINK:
+		break;
+	case SCO_LINK:
+	case ESCO_LINK:
+		if (!hci_dev_test_flag(conn->hdev, HCI_SCO_FLOWCTL))
+			return;
+		break;
+	default:
+		return;
+	}
+
+	if (skb->sk && (skb_shinfo(skb)->tx_flags & SKBTX_COMPLETION_TSTAMP))
+		track = true;
+
+	/* If nothing is tracked, just count extra skbs at the queue head */
+	if (!track && !comp->tracked) {
+		comp->extra++;
+		return;
+	}
+
+	if (track) {
+		skb = skb_clone_sk(skb);
+		if (!skb)
+			goto count_only;
+
+		comp->tracked++;
+	} else {
+		skb = skb_clone(skb, GFP_KERNEL);
+		if (!skb)
+			goto count_only;
+	}
+
+	skb_queue_tail(&comp->queue, skb);
+	return;
+
+count_only:
+	/* Stop tracking skbs, and only count. This will not emit timestamps for
+	 * the packets, but if we get here something is more seriously wrong.
+	 */
+	comp->tracked = 0;
+	comp->extra += skb_queue_len(&comp->queue) + 1;
+	skb_queue_purge(&comp->queue);
+}
+
+void hci_conn_tx_dequeue(struct hci_conn *conn)
+{
+	struct tx_queue *comp = &conn->tx_q;
+	struct sk_buff *skb;
+
+	/* If there are tracked skbs, the counted extra go before dequeuing real
+	 * skbs, to keep ordering. When nothing is tracked, the ordering doesn't
+	 * matter so dequeue real skbs first to get rid of them ASAP.
+	 */
+	if (comp->extra && (comp->tracked || skb_queue_empty(&comp->queue))) {
+		comp->extra--;
+		return;
+	}
+
+	skb = skb_dequeue(&comp->queue);
+	if (!skb)
+		return;
+
+	if (skb->sk) {
+		comp->tracked--;
+		__skb_tstamp_tx(skb, NULL, NULL, skb->sk,
+				SCM_TSTAMP_COMPLETION);
+	}
+
+	kfree_skb(skb);
+}
diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 94d9147612daf..5eb0600bbd03c 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3029,6 +3029,13 @@ static int hci_send_frame(struct hci_dev *hdev, struct sk_buff *skb)
 	return 0;
 }
 
+static int hci_send_conn_frame(struct hci_dev *hdev, struct hci_conn *conn,
+			       struct sk_buff *skb)
+{
+	hci_conn_tx_queue(conn, skb);
+	return hci_send_frame(hdev, skb);
+}
+
 /* Send HCI command */
 int hci_send_cmd(struct hci_dev *hdev, __u16 opcode, __u32 plen,
 		 const void *param)
@@ -3575,7 +3582,7 @@ static void hci_sched_sco(struct hci_dev *hdev, __u8 type)
 	while (*cnt && (conn = hci_low_sent(hdev, type, &quote))) {
 		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
 			BT_DBG("skb %p len %d", skb, skb->len);
-			hci_send_frame(hdev, skb);
+			hci_send_conn_frame(hdev, conn, skb);
 
 			conn->sent++;
 			if (conn->sent == ~0)
@@ -3618,7 +3625,7 @@ static void hci_sched_acl_pkt(struct hci_dev *hdev)
 			hci_conn_enter_active_mode(chan->conn,
 						   bt_cb(skb)->force_active);
 
-			hci_send_frame(hdev, skb);
+			hci_send_conn_frame(hdev, chan->conn, skb);
 			hdev->acl_last_tx = jiffies;
 
 			hdev->acl_cnt--;
@@ -3674,7 +3681,7 @@ static void hci_sched_le(struct hci_dev *hdev)
 
 			skb = skb_dequeue(&chan->data_q);
 
-			hci_send_frame(hdev, skb);
+			hci_send_conn_frame(hdev, chan->conn, skb);
 			hdev->le_last_tx = jiffies;
 
 			(*cnt)--;
@@ -3708,7 +3715,7 @@ static void hci_sched_iso(struct hci_dev *hdev)
 	while (*cnt && (conn = hci_low_sent(hdev, ISO_LINK, &quote))) {
 		while (quote-- && (skb = skb_dequeue(&conn->data_q))) {
 			BT_DBG("skb %p len %d", skb, skb->len);
-			hci_send_frame(hdev, skb);
+			hci_send_conn_frame(hdev, conn, skb);
 
 			conn->sent++;
 			if (conn->sent == ~0)
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index 0df4a0e082c82..83990c975c1f6 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -4415,6 +4415,7 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 		struct hci_comp_pkts_info *info = &ev->handles[i];
 		struct hci_conn *conn;
 		__u16  handle, count;
+		unsigned int i;
 
 		handle = __le16_to_cpu(info->handle);
 		count  = __le16_to_cpu(info->count);
@@ -4425,6 +4426,9 @@ static void hci_num_comp_pkts_evt(struct hci_dev *hdev, void *data,
 
 		conn->sent -= count;
 
+		for (i = 0; i < count; ++i)
+			hci_conn_tx_dequeue(conn);
+
 		switch (conn->type) {
 		case ACL_LINK:
 			hdev->acl_cnt += count;

From 27152ad0bc6715d34f351ede3e1d9d8852a9ee08 Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Tue, 18 Mar 2025 21:06:44 +0200
Subject: [PATCH 2437/2753] Bluetooth: ISO: add TX timestamping

Add BT_SCM_ERROR socket CMSG type.

Support TX timestamping in ISO sockets.

Support MSG_ERRQUEUE in ISO recvmsg.

If a packet from sendmsg() is fragmented, only the first ACL fragment is
timestamped.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/bluetooth.h |  1 +
 net/bluetooth/iso.c               | 24 ++++++++++++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/include/net/bluetooth/bluetooth.h b/include/net/bluetooth/bluetooth.h
index 435250c72d568..bbefde319f95e 100644
--- a/include/net/bluetooth/bluetooth.h
+++ b/include/net/bluetooth/bluetooth.h
@@ -156,6 +156,7 @@ struct bt_voice {
 #define BT_PKT_STATUS           16
 
 #define BT_SCM_PKT_STATUS	0x03
+#define BT_SCM_ERROR		0x04
 
 #define BT_ISO_QOS		17
 
diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c
index 0cb52a3308bae..3501a991f1c64 100644
--- a/net/bluetooth/iso.c
+++ b/net/bluetooth/iso.c
@@ -518,7 +518,8 @@ static struct bt_iso_qos *iso_sock_get_qos(struct sock *sk)
 	return &iso_pi(sk)->qos;
 }
 
-static int iso_send_frame(struct sock *sk, struct sk_buff *skb)
+static int iso_send_frame(struct sock *sk, struct sk_buff *skb,
+			  const struct sockcm_cookie *sockc)
 {
 	struct iso_conn *conn = iso_pi(sk)->conn;
 	struct bt_iso_qos *qos = iso_sock_get_qos(sk);
@@ -538,10 +539,12 @@ static int iso_send_frame(struct sock *sk, struct sk_buff *skb)
 	hdr->slen = cpu_to_le16(hci_iso_data_len_pack(len,
 						      HCI_ISO_STATUS_VALID));
 
-	if (sk->sk_state == BT_CONNECTED)
+	if (sk->sk_state == BT_CONNECTED) {
+		hci_setup_tx_timestamp(skb, 1, sockc);
 		hci_send_iso(conn->hcon, skb);
-	else
+	} else {
 		len = -ENOTCONN;
+	}
 
 	return len;
 }
@@ -1348,6 +1351,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb, **frag;
+	struct sockcm_cookie sockc;
 	size_t mtu;
 	int err;
 
@@ -1360,6 +1364,14 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	hci_sockcm_init(&sockc, sk);
+
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (err)
+			return err;
+	}
+
 	lock_sock(sk);
 
 	if (sk->sk_state != BT_CONNECTED) {
@@ -1405,7 +1417,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	lock_sock(sk);
 
 	if (sk->sk_state == BT_CONNECTED)
-		err = iso_send_frame(sk, skb);
+		err = iso_send_frame(sk, skb, &sockc);
 	else
 		err = -ENOTCONN;
 
@@ -1474,6 +1486,10 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 
 	BT_DBG("sk %p", sk);
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH,
+					  BT_SCM_ERROR);
+
 	if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) {
 		sock_hold(sk);
 		lock_sock(sk);

From acb462e45e73c49c9c0cf49bc6e36866143f74dc Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Tue, 18 Mar 2025 21:06:45 +0200
Subject: [PATCH 2438/2753] Bluetooth: L2CAP: add TX timestamping

Support TX timestamping in L2CAP sockets.

Support MSG_ERRQUEUE recvmsg.

For other than SOCK_STREAM L2CAP sockets, if a packet from sendmsg() is
fragmented, only the first ACL fragment is timestamped.

For SOCK_STREAM L2CAP sockets, use the bytestream convention and
timestamp the last fragment and count bytes in tskey.

Timestamps are not generated in the Enhanced Retransmission mode, as
meaning of COMPLETION stamp is unclear if L2CAP layer retransmits.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 include/net/bluetooth/l2cap.h |  3 ++-
 net/bluetooth/6lowpan.c       |  2 +-
 net/bluetooth/l2cap_core.c    | 41 ++++++++++++++++++++++++++++++++---
 net/bluetooth/l2cap_sock.c    | 15 ++++++++++++-
 net/bluetooth/smp.c           |  2 +-
 5 files changed, 56 insertions(+), 7 deletions(-)

diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h
index 0bf8cb17a6e86..4bb0eaedda180 100644
--- a/include/net/bluetooth/l2cap.h
+++ b/include/net/bluetooth/l2cap.h
@@ -955,7 +955,8 @@ void l2cap_chan_close(struct l2cap_chan *chan, int reason);
 int l2cap_chan_connect(struct l2cap_chan *chan, __le16 psm, u16 cid,
 		       bdaddr_t *dst, u8 dst_type, u16 timeout);
 int l2cap_chan_reconfigure(struct l2cap_chan *chan, __u16 mtu);
-int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len);
+int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len,
+		    const struct sockcm_cookie *sockc);
 void l2cap_chan_busy(struct l2cap_chan *chan, int busy);
 void l2cap_chan_rx_avail(struct l2cap_chan *chan, ssize_t rx_avail);
 int l2cap_chan_check_security(struct l2cap_chan *chan, bool initiator);
diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c
index 73530b8e1eaee..f0c862091bff2 100644
--- a/net/bluetooth/6lowpan.c
+++ b/net/bluetooth/6lowpan.c
@@ -444,7 +444,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb,
 	memset(&msg, 0, sizeof(msg));
 	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &iv, 1, skb->len);
 
-	err = l2cap_chan_send(chan, &msg, skb->len);
+	err = l2cap_chan_send(chan, &msg, skb->len, NULL);
 	if (err > 0) {
 		netdev->stats.tx_bytes += err;
 		netdev->stats.tx_packets++;
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index 7b4adab353cf2..c7b66b2ea9f21 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -2515,7 +2515,33 @@ static void l2cap_le_flowctl_send(struct l2cap_chan *chan)
 	       skb_queue_len(&chan->tx_q));
 }
 
-int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
+static void l2cap_tx_timestamp(struct sk_buff *skb,
+			       const struct sockcm_cookie *sockc,
+			       size_t len)
+{
+	struct sock *sk = skb ? skb->sk : NULL;
+
+	if (sk && sk->sk_type == SOCK_STREAM)
+		hci_setup_tx_timestamp(skb, len, sockc);
+	else
+		hci_setup_tx_timestamp(skb, 1, sockc);
+}
+
+static void l2cap_tx_timestamp_seg(struct sk_buff_head *queue,
+				   const struct sockcm_cookie *sockc,
+				   size_t len)
+{
+	struct sk_buff *skb = skb_peek(queue);
+	struct sock *sk = skb ? skb->sk : NULL;
+
+	if (sk && sk->sk_type == SOCK_STREAM)
+		l2cap_tx_timestamp(skb_peek_tail(queue), sockc, len);
+	else
+		l2cap_tx_timestamp(skb, sockc, len);
+}
+
+int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len,
+		    const struct sockcm_cookie *sockc)
 {
 	struct sk_buff *skb;
 	int err;
@@ -2530,6 +2556,8 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 		if (IS_ERR(skb))
 			return PTR_ERR(skb);
 
+		l2cap_tx_timestamp(skb, sockc, len);
+
 		l2cap_do_send(chan, skb);
 		return len;
 	}
@@ -2553,6 +2581,8 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 		if (err)
 			return err;
 
+		l2cap_tx_timestamp_seg(&seg_queue, sockc, len);
+
 		skb_queue_splice_tail_init(&seg_queue, &chan->tx_q);
 
 		l2cap_le_flowctl_send(chan);
@@ -2574,6 +2604,8 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 		if (IS_ERR(skb))
 			return PTR_ERR(skb);
 
+		l2cap_tx_timestamp(skb, sockc, len);
+
 		l2cap_do_send(chan, skb);
 		err = len;
 		break;
@@ -2597,10 +2629,13 @@ int l2cap_chan_send(struct l2cap_chan *chan, struct msghdr *msg, size_t len)
 		if (err)
 			break;
 
-		if (chan->mode == L2CAP_MODE_ERTM)
+		if (chan->mode == L2CAP_MODE_ERTM) {
+			/* TODO: ERTM mode timestamping */
 			l2cap_tx(chan, NULL, &seg_queue, L2CAP_EV_DATA_REQUEST);
-		else
+		} else {
+			l2cap_tx_timestamp_seg(&seg_queue, sockc, len);
 			l2cap_streaming_send(chan, &seg_queue);
+		}
 
 		err = len;
 
diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c
index acd11b268b98a..5aa55fa695943 100644
--- a/net/bluetooth/l2cap_sock.c
+++ b/net/bluetooth/l2cap_sock.c
@@ -1106,6 +1106,7 @@ static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct l2cap_chan *chan = l2cap_pi(sk)->chan;
+	struct sockcm_cookie sockc;
 	int err;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
@@ -1120,6 +1121,14 @@ static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (sk->sk_state != BT_CONNECTED)
 		return -ENOTCONN;
 
+	hci_sockcm_init(&sockc, sk);
+
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (err)
+			return err;
+	}
+
 	lock_sock(sk);
 	err = bt_sock_wait_ready(sk, msg->msg_flags);
 	release_sock(sk);
@@ -1127,7 +1136,7 @@ static int l2cap_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 		return err;
 
 	l2cap_chan_lock(chan);
-	err = l2cap_chan_send(chan, msg, len);
+	err = l2cap_chan_send(chan, msg, len, &sockc);
 	l2cap_chan_unlock(chan);
 
 	return err;
@@ -1168,6 +1177,10 @@ static int l2cap_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct l2cap_pinfo *pi = l2cap_pi(sk);
 	int err;
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH,
+					  BT_SCM_ERROR);
+
 	lock_sock(sk);
 
 	if (sk->sk_state == BT_CONNECT2 && test_bit(BT_SK_DEFER_SETUP,
diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index a31c6acf1df2b..47f359f24d1fd 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -608,7 +608,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data)
 
 	iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, iv, 2, 1 + len);
 
-	l2cap_chan_send(chan, &msg, 1 + len);
+	l2cap_chan_send(chan, &msg, 1 + len, NULL);
 
 	if (!chan->data)
 		return;

From 987f20b8a2d887689283fb4746c3e533aa5a0e2e Mon Sep 17 00:00:00 2001
From: Pauli Virtanen <pav@iki.fi>
Date: Tue, 18 Mar 2025 21:06:46 +0200
Subject: [PATCH 2439/2753] Bluetooth: SCO: add TX timestamping

Support TX timestamping in SCO sockets.
Not available for hdevs without SCO_FLOWCTL.

Support MSG_ERRQUEUE in SCO recvmsg.

Signed-off-by: Pauli Virtanen <pav@iki.fi>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/sco.c | 19 +++++++++++++++++--
 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c
index 5d1bc0d6aee03..2945d27e75dce 100644
--- a/net/bluetooth/sco.c
+++ b/net/bluetooth/sco.c
@@ -378,7 +378,8 @@ static int sco_connect(struct sock *sk)
 	return err;
 }
 
-static int sco_send_frame(struct sock *sk, struct sk_buff *skb)
+static int sco_send_frame(struct sock *sk, struct sk_buff *skb,
+			  const struct sockcm_cookie *sockc)
 {
 	struct sco_conn *conn = sco_pi(sk)->conn;
 	int len = skb->len;
@@ -389,6 +390,7 @@ static int sco_send_frame(struct sock *sk, struct sk_buff *skb)
 
 	BT_DBG("sk %p len %d", sk, len);
 
+	hci_setup_tx_timestamp(skb, 1, sockc);
 	hci_send_sco(conn->hcon, skb);
 
 	return len;
@@ -784,6 +786,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 {
 	struct sock *sk = sock->sk;
 	struct sk_buff *skb;
+	struct sockcm_cookie sockc;
 	int err;
 
 	BT_DBG("sock %p, sk %p", sock, sk);
@@ -795,6 +798,14 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	if (msg->msg_flags & MSG_OOB)
 		return -EOPNOTSUPP;
 
+	hci_sockcm_init(&sockc, sk);
+
+	if (msg->msg_controllen) {
+		err = sock_cmsg_send(sk, msg, &sockc);
+		if (err)
+			return err;
+	}
+
 	skb = bt_skb_sendmsg(sk, msg, len, len, 0, 0);
 	if (IS_ERR(skb))
 		return PTR_ERR(skb);
@@ -802,7 +813,7 @@ static int sco_sock_sendmsg(struct socket *sock, struct msghdr *msg,
 	lock_sock(sk);
 
 	if (sk->sk_state == BT_CONNECTED)
-		err = sco_send_frame(sk, skb);
+		err = sco_send_frame(sk, skb, &sockc);
 	else
 		err = -ENOTCONN;
 
@@ -868,6 +879,10 @@ static int sco_sock_recvmsg(struct socket *sock, struct msghdr *msg,
 	struct sock *sk = sock->sk;
 	struct sco_pinfo *pi = sco_pi(sk);
 
+	if (unlikely(flags & MSG_ERRQUEUE))
+		return sock_recv_errqueue(sk, msg, len, SOL_BLUETOOTH,
+					  BT_SCM_ERROR);
+
 	lock_sock(sk);
 
 	if (sk->sk_state == BT_CONNECT2 &&

From 048a7d5b74d48eb526dcdaa49ea94a579c9a4c93 Mon Sep 17 00:00:00 2001
From: Hao Qin <hao.qin@mediatek.com>
Date: Sat, 15 Mar 2025 10:27:30 +0800
Subject: [PATCH 2440/2753] Bluetooth: btmtk: Remove the resetting step before
 downloading the fw

Remove the resetting step before downloading the fw, as it may cause
other usb devices to fail to initialise when connected during boot
on kernels 6.11 and newer.

Signed-off-by: Hao Qin <hao.qin@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtk.c | 10 ----------
 1 file changed, 10 deletions(-)

diff --git a/drivers/bluetooth/btmtk.c b/drivers/bluetooth/btmtk.c
index 68846c5bd4f79..4390fd571dbd1 100644
--- a/drivers/bluetooth/btmtk.c
+++ b/drivers/bluetooth/btmtk.c
@@ -1330,13 +1330,6 @@ int btmtk_usb_setup(struct hci_dev *hdev)
 		break;
 	case 0x7922:
 	case 0x7925:
-		/* Reset the device to ensure it's in the initial state before
-		 * downloading the firmware to ensure.
-		 */
-
-		if (!test_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags))
-			btmtk_usb_subsys_reset(hdev, dev_id);
-		fallthrough;
 	case 0x7961:
 		btmtk_fw_get_filename(fw_bin_name, sizeof(fw_bin_name), dev_id,
 				      fw_version, fw_flavor);
@@ -1345,12 +1338,9 @@ int btmtk_usb_setup(struct hci_dev *hdev)
 						btmtk_usb_hci_wmt_sync);
 		if (err < 0) {
 			bt_dev_err(hdev, "Failed to set up firmware (%d)", err);
-			clear_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags);
 			return err;
 		}
 
-		set_bit(BTMTK_FIRMWARE_LOADED, &btmtk_data->flags);
-
 		/* It's Device EndPoint Reset Option Register */
 		err = btmtk_usb_uhw_reg_write(hdev, MTK_EP_RST_OPT,
 					      MTK_EP_RST_IN_OUT_OPT);

From a7fe0d2b0892ea724316f5530f65c2610d990de1 Mon Sep 17 00:00:00 2001
From: Sean Wang <sean.wang@mediatek.com>
Date: Tue, 11 Mar 2025 18:25:22 -0700
Subject: [PATCH 2441/2753] Bluetooth: btmtksdio: Prevent enabling interrupts
 after IRQ handler removal

Ensure interrupts are not re-enabled when the IRQ handler has already been
removed. This prevents unexpected IRQ handler execution due to stale or
unhandled interrupts.

Modify btmtksdio_txrx_work to check if bdev->func->irq_handler exists
before calling sdio_writel to enable interrupts.

Co-developed-by: Pedro Tsai <pedro.tsai@mediatek.com>
Signed-off-by: Pedro Tsai <pedro.tsai@mediatek.com>
Co-developed-by: Felix Freimann <felix.freimann@mediatek.com>
Signed-off-by: Felix Freimann <felix.freimann@mediatek.com>
Signed-off-by: Sean Wang <sean.wang@mediatek.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btmtksdio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index bd5464bde174f..edd5eead1e93b 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -610,7 +610,8 @@ static void btmtksdio_txrx_work(struct work_struct *work)
 	} while (int_status || time_is_before_jiffies(txrx_timeout));
 
 	/* Enable interrupt */
-	sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL);
+	if (bdev->func->irq_handler)
+		sdio_writel(bdev->func, C_INT_EN_SET, MTK_REG_CHLPCR, NULL);
 
 	sdio_release_host(bdev->func);
 

From fd4d2400d08028c1f87939b5601d20b38e7b93be Mon Sep 17 00:00:00 2001
From: Vijay Satija <vijay.satija@intel.com>
Date: Fri, 7 Mar 2025 16:30:11 +0530
Subject: [PATCH 2442/2753] Bluetooth: btintel: Add support to configure TX
 power

BRDS - Bluetooth Regulatory Domain Specific absorption rate

Bluetooth has regulatory limitations which prohibit or allow usage of certain
bands or channels as well as limiting Tx power. The Tx power values can be
configured in ACPI table. This patch reads from ACPI entry configures the
controller accordingly.

Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Vijay Satija <vijay.satija@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c | 333 ++++++++++++++++++++++++++++++++++++
 drivers/bluetooth/btintel.h |  23 +++
 2 files changed, 356 insertions(+)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index ec5e2c7a56ae3..48e2f400957bc 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -35,6 +35,11 @@ enum {
 	DSM_SET_RESET_METHOD = 3,
 };
 
+#define BTINTEL_BT_DOMAIN		0x12
+#define BTINTEL_SAR_LEGACY		0
+#define BTINTEL_SAR_INC_PWR		1
+#define BTINTEL_SAR_INC_PWR_SUPPORTED	0
+
 #define CMD_WRITE_BOOT_PARAMS	0xfc0e
 struct cmd_write_boot_params {
 	__le32 boot_addr;
@@ -2806,6 +2811,331 @@ static int btintel_set_dsbr(struct hci_dev *hdev, struct intel_version_tlv *ver)
 	return 0;
 }
 
+#ifdef CONFIG_ACPI
+static acpi_status btintel_evaluate_acpi_method(struct hci_dev *hdev,
+						acpi_string method,
+						union acpi_object **ptr,
+						u8 pkg_size)
+{
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *p;
+	acpi_status status;
+	acpi_handle handle;
+
+	handle = ACPI_HANDLE(GET_HCIDEV_DEV(hdev));
+	if (!handle) {
+		bt_dev_dbg(hdev, "ACPI-BT: No ACPI support for Bluetooth device");
+		return AE_NOT_EXIST;
+	}
+
+	status = acpi_evaluate_object(handle, method, NULL, &buffer);
+
+	if (ACPI_FAILURE(status)) {
+		bt_dev_dbg(hdev, "ACPI-BT: ACPI Failure: %s method: %s",
+			   acpi_format_exception(status), method);
+		return status;
+	}
+
+	p = buffer.pointer;
+
+	if (p->type != ACPI_TYPE_PACKAGE || p->package.count < pkg_size) {
+		bt_dev_warn(hdev, "ACPI-BT: Invalid object type: %d or package count: %d",
+			    p->type, p->package.count);
+		kfree(buffer.pointer);
+		return AE_ERROR;
+	}
+
+	*ptr = buffer.pointer;
+	return 0;
+}
+
+static union acpi_object *btintel_acpi_get_bt_pkg(union acpi_object *buffer)
+{
+	union acpi_object *domain, *bt_pkg;
+	int i;
+
+	for (i = 1; i < buffer->package.count; i++) {
+		bt_pkg = &buffer->package.elements[i];
+		domain = &bt_pkg->package.elements[0];
+		if (domain->type == ACPI_TYPE_INTEGER &&
+		    domain->integer.value == BTINTEL_BT_DOMAIN)
+			return bt_pkg;
+	}
+	return ERR_PTR(-ENOENT);
+}
+
+static int btintel_send_sar_ddc(struct hci_dev *hdev, struct btintel_cp_ddc_write *data, u8 len)
+{
+	struct sk_buff *skb;
+
+	skb = __hci_cmd_sync(hdev, 0xfc8b, len, data, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_warn(hdev, "Failed to send sar ddc id:0x%4.4x (%ld)",
+			    le16_to_cpu(data->id), PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+	kfree_skb(skb);
+	return 0;
+}
+
+static int btintel_send_edr(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+			    int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 5;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = sar->br >> 3;
+	cmd->data[1] = sar->edr2 >> 3;
+	cmd->data[2] = sar->edr3 >> 3;
+	return btintel_send_sar_ddc(hdev, cmd, 6);
+}
+
+static int btintel_send_le(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+			   int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = min3(sar->le, sar->le_lr, sar->le_2mhz) >> 3;
+	return btintel_send_sar_ddc(hdev, cmd, 4);
+}
+
+static int btintel_send_br(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+			   int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = sar->br >> 3;
+	return btintel_send_sar_ddc(hdev, cmd, 4);
+}
+
+static int btintel_send_br_mutual(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+				  int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = sar->br;
+	return btintel_send_sar_ddc(hdev, cmd, 4);
+}
+
+static int btintel_send_edr2(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+			     int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = sar->edr2;
+	return btintel_send_sar_ddc(hdev, cmd, 4);
+}
+
+static int btintel_send_edr3(struct hci_dev *hdev, struct btintel_cp_ddc_write *cmd,
+			     int id, struct btintel_sar_inc_pwr *sar)
+{
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(id);
+	cmd->data[0] = sar->edr3;
+	return btintel_send_sar_ddc(hdev, cmd, 4);
+}
+
+static int btintel_set_legacy_sar(struct hci_dev *hdev, struct btintel_sar_inc_pwr *sar)
+{
+	struct btintel_cp_ddc_write *cmd;
+	u8 buffer[64];
+	int ret;
+
+	cmd = (void *)buffer;
+	ret = btintel_send_br(hdev, cmd, 0x0131, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_br(hdev, cmd, 0x0132, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_le(hdev, cmd, 0x0133, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr(hdev, cmd, 0x0137, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr(hdev, cmd, 0x0138, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr(hdev, cmd, 0x013b, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr(hdev, cmd, 0x013c, sar);
+
+	return ret;
+}
+
+static int btintel_set_mutual_sar(struct hci_dev *hdev, struct btintel_sar_inc_pwr *sar)
+{
+	struct btintel_cp_ddc_write *cmd;
+	struct sk_buff *skb;
+	u8 buffer[64];
+	bool enable;
+	int ret;
+
+	cmd = (void *)buffer;
+
+	cmd->len = 3;
+	cmd->id = cpu_to_le16(0x019e);
+
+	if (sar->revision == BTINTEL_SAR_INC_PWR &&
+	    sar->inc_power_mode == BTINTEL_SAR_INC_PWR_SUPPORTED)
+		cmd->data[0] = 0x01;
+	else
+		cmd->data[0] = 0x00;
+
+	ret = btintel_send_sar_ddc(hdev, cmd, 4);
+	if (ret)
+		return ret;
+
+	if (sar->revision == BTINTEL_SAR_INC_PWR &&
+	    sar->inc_power_mode == BTINTEL_SAR_INC_PWR_SUPPORTED) {
+		cmd->len = 3;
+		cmd->id = cpu_to_le16(0x019f);
+		cmd->data[0] = sar->sar_2400_chain_a;
+
+		ret = btintel_send_sar_ddc(hdev, cmd, 4);
+		if (ret)
+			return ret;
+	}
+
+	ret = btintel_send_br_mutual(hdev, cmd, 0x01a0, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr2(hdev, cmd, 0x01a1, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_edr3(hdev, cmd, 0x01a2, sar);
+	if (ret)
+		return ret;
+
+	ret = btintel_send_le(hdev, cmd, 0x01a3, sar);
+	if (ret)
+		return ret;
+
+	enable = true;
+	skb = __hci_cmd_sync(hdev, 0xfe25, 1, &enable, HCI_CMD_TIMEOUT);
+	if (IS_ERR(skb)) {
+		bt_dev_warn(hdev, "Failed to send Intel SAR Enable (%ld)", PTR_ERR(skb));
+		return PTR_ERR(skb);
+	}
+
+	kfree_skb(skb);
+	return 0;
+}
+
+static int btintel_sar_send_to_device(struct hci_dev *hdev, struct btintel_sar_inc_pwr *sar,
+				      struct intel_version_tlv *ver)
+{
+	u16 cnvi, cnvr;
+	int ret;
+
+	cnvi = ver->cnvi_top & 0xfff;
+	cnvr = ver->cnvr_top & 0xfff;
+
+	if (cnvi < BTINTEL_CNVI_BLAZARI && cnvr < BTINTEL_CNVR_FMP2) {
+		bt_dev_info(hdev, "Applying legacy Bluetooth SAR");
+		ret = btintel_set_legacy_sar(hdev, sar);
+	} else if (cnvi == BTINTEL_CNVI_GAP || cnvr == BTINTEL_CNVR_FMP2) {
+		bt_dev_info(hdev, "Applying mutual Bluetooth SAR");
+		ret = btintel_set_mutual_sar(hdev, sar);
+	} else {
+		ret = -EOPNOTSUPP;
+	}
+
+	return ret;
+}
+
+static int btintel_acpi_set_sar(struct hci_dev *hdev, struct intel_version_tlv *ver)
+{
+	union acpi_object *bt_pkg, *buffer = NULL;
+	struct btintel_sar_inc_pwr sar;
+	acpi_status status;
+	u8 revision;
+	int ret;
+
+	status = btintel_evaluate_acpi_method(hdev, "BRDS", &buffer, 2);
+	if (ACPI_FAILURE(status))
+		return -ENOENT;
+
+	bt_pkg = btintel_acpi_get_bt_pkg(buffer);
+
+	if (IS_ERR(bt_pkg)) {
+		ret = PTR_ERR(bt_pkg);
+		goto error;
+	}
+
+	if (!bt_pkg->package.count) {
+		ret = -EINVAL;
+		goto error;
+	}
+
+	revision = buffer->package.elements[0].integer.value;
+
+	if (revision > BTINTEL_SAR_INC_PWR) {
+		bt_dev_dbg(hdev, "BT_SAR: revision: 0x%2.2x not supported", revision);
+		ret = -EOPNOTSUPP;
+		goto error;
+	}
+
+	memset(&sar, 0, sizeof(sar));
+
+	if (revision == BTINTEL_SAR_LEGACY && bt_pkg->package.count == 8) {
+		sar.revision = revision;
+		sar.bt_sar_bios = bt_pkg->package.elements[1].integer.value;
+		sar.br = bt_pkg->package.elements[2].integer.value;
+		sar.edr2 = bt_pkg->package.elements[3].integer.value;
+		sar.edr3 = bt_pkg->package.elements[4].integer.value;
+		sar.le = bt_pkg->package.elements[5].integer.value;
+		sar.le_2mhz = bt_pkg->package.elements[6].integer.value;
+		sar.le_lr  = bt_pkg->package.elements[7].integer.value;
+
+	} else if (revision == BTINTEL_SAR_INC_PWR && bt_pkg->package.count == 10) {
+		sar.revision = revision;
+		sar.bt_sar_bios = bt_pkg->package.elements[1].integer.value;
+		sar.inc_power_mode = bt_pkg->package.elements[2].integer.value;
+		sar.sar_2400_chain_a = bt_pkg->package.elements[3].integer.value;
+		sar.br = bt_pkg->package.elements[4].integer.value;
+		sar.edr2 = bt_pkg->package.elements[5].integer.value;
+		sar.edr3 = bt_pkg->package.elements[6].integer.value;
+		sar.le = bt_pkg->package.elements[7].integer.value;
+		sar.le_2mhz = bt_pkg->package.elements[8].integer.value;
+		sar.le_lr  = bt_pkg->package.elements[9].integer.value;
+	} else {
+		ret = -EINVAL;
+		goto error;
+	}
+
+	/* Apply only if it is enabled in BIOS */
+	if (sar.bt_sar_bios != 1) {
+		bt_dev_dbg(hdev, "Bluetooth SAR is not enabled");
+		ret = -EOPNOTSUPP;
+		goto error;
+	}
+
+	ret = btintel_sar_send_to_device(hdev, &sar, ver);
+error:
+	kfree(buffer);
+	return ret;
+}
+#endif /* CONFIG_ACPI */
+
+static int btintel_set_specific_absorption_rate(struct hci_dev *hdev,
+						struct intel_version_tlv *ver)
+{
+#ifdef CONFIG_ACPI
+	return btintel_acpi_set_sar(hdev, ver);
+#endif
+	return 0;
+}
+
 int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 				 struct intel_version_tlv *ver)
 {
@@ -2883,6 +3213,9 @@ int btintel_bootloader_setup_tlv(struct hci_dev *hdev,
 
 	hci_dev_clear_flag(hdev, HCI_QUALITY_REPORT);
 
+	/* Send sar values to controller */
+	btintel_set_specific_absorption_rate(hdev, ver);
+
 	/* Set PPAG feature */
 	btintel_set_ppag(hdev, ver);
 
diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index 19530ea14905d..b2b5be28e8032 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -58,6 +58,9 @@ struct intel_tlv {
 #define BTINTEL_CNVI_BLAZARU		0x930
  #define BTINTEL_CNVI_SCP		0xA00
 
+/* CNVR */
+#define BTINTEL_CNVR_FMP2		0x910
+
 #define BTINTEL_IMG_BOOTLOADER		0x01	/* Bootloader image */
 #define BTINTEL_IMG_IML			0x02	/* Intermediate image */
 #define BTINTEL_IMG_OP			0x03	/* Operational image */
@@ -165,6 +168,26 @@ struct hci_ppag_enable_cmd {
 #define INTEL_TLV_DEBUG_EXCEPTION	0x02
 #define INTEL_TLV_TEST_EXCEPTION	0xDE
 
+struct btintel_cp_ddc_write {
+	u8	len;
+	__le16	id;
+	u8	data[];
+} __packed;
+
+/* Bluetooth SAR feature (BRDS), Revision 1 */
+struct btintel_sar_inc_pwr {
+	u8	revision;
+	u32	bt_sar_bios; /* Mode of SAR control to be used, 1:enabled in bios */
+	u32	inc_power_mode;  /* Increased power mode */
+	u8	sar_2400_chain_a; /* Sar power restriction LB */
+	u8	br;
+	u8	edr2;
+	u8	edr3;
+	u8	le;
+	u8	le_2mhz;
+	u8	le_lr;
+};
+
 #define INTEL_HW_PLATFORM(cnvx_bt)	((u8)(((cnvx_bt) & 0x0000ff00) >> 8))
 #define INTEL_HW_VARIANT(cnvx_bt)	((u8)(((cnvx_bt) & 0x003f0000) >> 16))
 #define INTEL_CNVX_TOP_TYPE(cnvx_top)	((cnvx_top) & 0x00000fff)

From 25ba50076a65328b5a195aeb019eb9824a37def1 Mon Sep 17 00:00:00 2001
From: Kiran K <kiran.k@intel.com>
Date: Fri, 7 Mar 2025 17:04:08 +0530
Subject: [PATCH 2443/2753] Bluetooth: btintel: Fix leading white space

Remove the unwanted leading whitespace.

Fixes: 00b3e258e1c0 ("Bluetooth: btintel_pcie: Setup buffers for firmware traces")
Fixes: f5d8a90511b7 ("Bluetooth: btintel: Add DSBR support for ScP")
Signed-off-by: Kiran K <kiran.k@intel.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.h      | 2 +-
 drivers/bluetooth/btintel_pcie.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btintel.h b/drivers/bluetooth/btintel.h
index b2b5be28e8032..2aece3effa4e9 100644
--- a/drivers/bluetooth/btintel.h
+++ b/drivers/bluetooth/btintel.h
@@ -56,7 +56,7 @@ struct intel_tlv {
 #define BTINTEL_CNVI_BLAZARIW		0x901
 #define BTINTEL_CNVI_GAP		0x910
 #define BTINTEL_CNVI_BLAZARU		0x930
- #define BTINTEL_CNVI_SCP		0xA00
+#define BTINTEL_CNVI_SCP		0xA00
 
 /* CNVR */
 #define BTINTEL_CNVR_FMP2		0x910
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 9114be1fc3cee..c1e69fcc9c4fa 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -49,7 +49,7 @@ MODULE_DEVICE_TABLE(pci, btintel_pcie_table);
 #define BTINTEL_PCIE_HCI_EVT_PKT	0x00000004
 #define BTINTEL_PCIE_HCI_ISO_PKT	0x00000005
 
- #define BTINTEL_PCIE_MAGIC_NUM    0xA5A5A5A5
+#define BTINTEL_PCIE_MAGIC_NUM    0xA5A5A5A5
 
 #define BTINTEL_PCIE_BLZR_HWEXP_SIZE		1024
 #define BTINTEL_PCIE_BLZR_HWEXP_DMP_ADDR	0xB00A7C00

From ec16a00d7eb32bae4232211b774abc95209f97ab Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 10 Mar 2025 17:32:29 +0530
Subject: [PATCH 2444/2753] Bluetooth: btnxpuart: Add correct bootloader error
 codes

This corrects the bootloader error codes for NXP chipsets.
Since we have a common handling for all error codes, there is no backward
compatibility issue.
Added error handling for CRC error code in V3 bootloader signature.

Fixes: 27489364299a ("Bluetooth: btnxpuart: Add handling for boot-signature timeout errors")
Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 57 +++++++++++++++++++++--------------
 1 file changed, 35 insertions(+), 22 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b440ba9292ec5..b9d2fe5e992da 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -210,10 +210,11 @@ struct btnxpuart_dev {
 #define NXP_NAK_V3		0x7b
 #define NXP_CRC_ERROR_V3	0x7c
 
-/* Bootloader signature error codes */
-#define NXP_ACK_RX_TIMEOUT	0x0002	/* ACK not received from host */
-#define NXP_HDR_RX_TIMEOUT	0x0003	/* FW Header chunk not received */
-#define NXP_DATA_RX_TIMEOUT	0x0004	/* FW Data chunk not received */
+/* Bootloader signature error codes: Refer AN12820 from nxp.com */
+#define NXP_CRC_RX_ERROR	BIT(0)	/* CRC error in previous packet */
+#define NXP_ACK_RX_TIMEOUT	BIT(2)	/* ACK not received from host */
+#define NXP_HDR_RX_TIMEOUT	BIT(3)	/* FW Header chunk not received */
+#define NXP_DATA_RX_TIMEOUT	BIT(4)	/* FW Data chunk not received */
 
 #define HDR_LEN			16
 
@@ -316,6 +317,16 @@ union nxp_v3_rx_timeout_nak_u {
 	u8 buf[6];
 };
 
+struct nxp_v3_crc_nak {
+	u8 nak;
+	u8 crc;
+} __packed;
+
+union nxp_v3_crc_nak_u {
+	struct nxp_v3_crc_nak pkt;
+	u8 buf[2];
+};
+
 /* FW dump */
 #define NXP_FW_DUMP_SIZE	(1024 * 1000)
 
@@ -1089,25 +1100,27 @@ static void nxp_handle_fw_download_error(struct hci_dev *hdev, struct v3_data_re
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	__u32 offset = __le32_to_cpu(req->offset);
 	__u16 err = __le16_to_cpu(req->error);
-	union nxp_v3_rx_timeout_nak_u nak_tx_buf;
-
-	switch (err) {
-	case NXP_ACK_RX_TIMEOUT:
-	case NXP_HDR_RX_TIMEOUT:
-	case NXP_DATA_RX_TIMEOUT:
-		nak_tx_buf.pkt.nak = NXP_NAK_V3;
-		nak_tx_buf.pkt.offset = __cpu_to_le32(offset);
-		nak_tx_buf.pkt.crc = crc8(crc8_table, nak_tx_buf.buf,
-				      sizeof(nak_tx_buf) - 1, 0xff);
-		serdev_device_write_buf(nxpdev->serdev, nak_tx_buf.buf,
-					sizeof(nak_tx_buf));
-		break;
-	default:
-		bt_dev_dbg(hdev, "Unknown bootloader error code: %d", err);
-		break;
-
+	union nxp_v3_rx_timeout_nak_u timeout_nak_buf;
+	union nxp_v3_crc_nak_u crc_nak_buf;
+
+	if (err & NXP_CRC_RX_ERROR) {
+		crc_nak_buf.pkt.nak = NXP_CRC_ERROR_V3;
+		crc_nak_buf.pkt.crc = crc8(crc8_table, crc_nak_buf.buf,
+					   sizeof(crc_nak_buf) - 1, 0xff);
+		serdev_device_write_buf(nxpdev->serdev, crc_nak_buf.buf,
+					sizeof(crc_nak_buf));
+	} else if (err & NXP_ACK_RX_TIMEOUT ||
+		   err & NXP_HDR_RX_TIMEOUT ||
+		   err & NXP_DATA_RX_TIMEOUT) {
+		timeout_nak_buf.pkt.nak = NXP_NAK_V3;
+		timeout_nak_buf.pkt.offset = __cpu_to_le32(offset);
+		timeout_nak_buf.pkt.crc = crc8(crc8_table, timeout_nak_buf.buf,
+					       sizeof(timeout_nak_buf) - 1, 0xff);
+		serdev_device_write_buf(nxpdev->serdev, timeout_nak_buf.buf,
+					sizeof(timeout_nak_buf));
+	} else {
+		bt_dev_err(hdev, "Unknown bootloader error code: %d", err);
 	}
-
 }
 
 static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)

From f13bd7def71d7733a36ff57a7c8ad4b4f454c1ed Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 10 Mar 2025 17:32:30 +0530
Subject: [PATCH 2445/2753] Bluetooth: btnxpuart: Handle bootloader error
 during cmd5 and cmd7

This handles the scenario where the driver receives an error code after
sending cmd5 or cmd7 in the bootloader signature during FW download.
The bootloader error code is handled by the driver and FW offset is
corrected accordingly, and the cmd5 or cmd7 is re-sent to the controller
in case of CRC error.

Fixes: 689ca16e5232 ("Bluetooth: NXP: Add protocol support for NXP Bluetooth chipsets")
Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 61 ++++++++++++++++++++++++-----------
 1 file changed, 43 insertions(+), 18 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index b9d2fe5e992da..5eae622990b86 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -168,6 +168,12 @@ struct btnxpuart_data {
 	const char *fw_name_old;
 };
 
+enum bootloader_param_change {
+	not_changed,
+	cmd_sent,
+	changed
+};
+
 struct btnxpuart_dev {
 	struct hci_dev *hdev;
 	struct serdev_device *serdev;
@@ -183,6 +189,7 @@ struct btnxpuart_dev {
 	u32 fw_v1_sent_bytes;
 	u32 fw_dnld_v3_offset;
 	u32 fw_v3_offset_correction;
+	u32 fw_v3_prev_sent;
 	u32 fw_v1_expected_len;
 	u32 boot_reg_offset;
 	wait_queue_head_t fw_dnld_done_wait_q;
@@ -191,8 +198,8 @@ struct btnxpuart_dev {
 	u32 new_baudrate;
 	u32 current_baudrate;
 	u32 fw_init_baudrate;
-	bool timeout_changed;
-	bool baudrate_changed;
+	enum bootloader_param_change timeout_changed;
+	enum bootloader_param_change baudrate_changed;
 	bool helper_downloaded;
 
 	struct ps_data psdata;
@@ -680,8 +687,8 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 	nxpdev->boot_reg_offset = 0;
 	nxpdev->fw_dnld_v3_offset = 0;
 	nxpdev->fw_v3_offset_correction = 0;
-	nxpdev->baudrate_changed = false;
-	nxpdev->timeout_changed = false;
+	nxpdev->baudrate_changed = not_changed;
+	nxpdev->timeout_changed = not_changed;
 	nxpdev->helper_downloaded = false;
 
 	serdev_device_set_baudrate(nxpdev->serdev, HCI_NXP_PRI_BAUDRATE);
@@ -913,15 +920,14 @@ static int nxp_recv_fw_req_v1(struct hci_dev *hdev, struct sk_buff *skb)
 	len = __le16_to_cpu(req->len);
 
 	if (!nxp_data->helper_fw_name) {
-		if (!nxpdev->timeout_changed) {
-			nxpdev->timeout_changed = nxp_fw_change_timeout(hdev,
-									len);
+		if (nxpdev->timeout_changed != changed) {
+			nxp_fw_change_timeout(hdev, len);
+			nxpdev->timeout_changed = changed;
 			goto free_skb;
 		}
-		if (!nxpdev->baudrate_changed) {
-			nxpdev->baudrate_changed = nxp_fw_change_baudrate(hdev,
-									  len);
-			if (nxpdev->baudrate_changed) {
+		if (nxpdev->baudrate_changed != changed) {
+			if (nxp_fw_change_baudrate(hdev, len)) {
+				nxpdev->baudrate_changed = changed;
 				serdev_device_set_baudrate(nxpdev->serdev,
 							   HCI_NXP_SEC_BAUDRATE);
 				serdev_device_set_flow_control(nxpdev->serdev, true);
@@ -1127,7 +1133,8 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
 {
 	struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
 	struct v3_data_req *req;
-	__u16 len;
+	__u16 len = 0;
+	__u16 err = 0;
 	__u32 offset;
 
 	if (!process_boot_signature(nxpdev))
@@ -1137,23 +1144,40 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
 	if (!req || !nxpdev->fw)
 		goto free_skb;
 
-	if (!req->error) {
+	err = __le16_to_cpu(req->error);
+
+	if (!err) {
 		nxp_send_ack(NXP_ACK_V3, hdev);
+		if (nxpdev->timeout_changed == cmd_sent)
+			nxpdev->timeout_changed = changed;
+		if (nxpdev->baudrate_changed == cmd_sent)
+			nxpdev->baudrate_changed = changed;
 	} else {
 		nxp_handle_fw_download_error(hdev, req);
+		if (nxpdev->timeout_changed == cmd_sent &&
+		    err == NXP_CRC_RX_ERROR) {
+			nxpdev->fw_v3_offset_correction -= nxpdev->fw_v3_prev_sent;
+			nxpdev->timeout_changed = not_changed;
+		}
+		if (nxpdev->baudrate_changed == cmd_sent &&
+		    err == NXP_CRC_RX_ERROR) {
+			nxpdev->fw_v3_offset_correction -= nxpdev->fw_v3_prev_sent;
+			nxpdev->baudrate_changed = not_changed;
+		}
 		goto free_skb;
 	}
 
 	len = __le16_to_cpu(req->len);
 
-	if (!nxpdev->timeout_changed) {
-		nxpdev->timeout_changed = nxp_fw_change_timeout(hdev, len);
+	if (nxpdev->timeout_changed != changed) {
+		nxp_fw_change_timeout(hdev, len);
+		nxpdev->timeout_changed = cmd_sent;
 		goto free_skb;
 	}
 
-	if (!nxpdev->baudrate_changed) {
-		nxpdev->baudrate_changed = nxp_fw_change_baudrate(hdev, len);
-		if (nxpdev->baudrate_changed) {
+	if (nxpdev->baudrate_changed != changed) {
+		if (nxp_fw_change_baudrate(hdev, len)) {
+			nxpdev->baudrate_changed = cmd_sent;
 			serdev_device_set_baudrate(nxpdev->serdev,
 						   HCI_NXP_SEC_BAUDRATE);
 			serdev_device_set_flow_control(nxpdev->serdev, true);
@@ -1185,6 +1209,7 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
 				nxpdev->fw_dnld_v3_offset, len);
 
 free_skb:
+	nxpdev->fw_v3_prev_sent = len;
 	kfree_skb(skb);
 	return 0;
 }

From 1a6e1539e97303c60d82e3d5e163973e771a9d7f Mon Sep 17 00:00:00 2001
From: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Date: Mon, 10 Mar 2025 17:32:31 +0530
Subject: [PATCH 2446/2753] Bluetooth: btnxpuart: Fix kernel panic during FW
 release

This fixes a kernel panic seen during release FW in a stress test
scenario where WLAN and BT FW download occurs simultaneously, and due to
a HW bug, chip sends out only 1 bootloader signatures.

When driver receives the bootloader signature, it enters FW download
mode, but since no consequtive bootloader signatures seen, FW file is
not requested.

After 60 seconds, when FW download times out, release_firmware causes a
kernel panic.

[ 2601.949184] Unable to handle kernel paging request at virtual address 0000312e6f006573
[ 2601.992076] user pgtable: 4k pages, 48-bit VAs, pgdp=0000000111802000
[ 2601.992080] [0000312e6f006573] pgd=0000000000000000, p4d=0000000000000000
[ 2601.992087] Internal error: Oops: 0000000096000021 [#1] PREEMPT SMP
[ 2601.992091] Modules linked in: algif_hash algif_skcipher af_alg btnxpuart(O) pciexxx(O) mlan(O) overlay fsl_jr_uio caam_jr caamkeyblob_desc caamhash_desc caamalg_desc crypto_engine authenc libdes crct10dif_ce polyval_ce snd_soc_fsl_easrc snd_soc_fsl_asoc_card imx8_media_dev(C) snd_soc_fsl_micfil polyval_generic snd_soc_fsl_xcvr snd_soc_fsl_sai snd_soc_imx_audmux snd_soc_fsl_asrc snd_soc_imx_card snd_soc_imx_hdmi snd_soc_fsl_aud2htx snd_soc_fsl_utils imx_pcm_dma dw_hdmi_cec flexcan can_dev
[ 2602.001825] CPU: 2 PID: 20060 Comm: hciconfig Tainted: G         C O       6.6.23-lts-next-06236-gb586a521770e #1
[ 2602.010182] Hardware name: NXP i.MX8MPlus EVK board (DT)
[ 2602.010185] pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 2602.010191] pc : _raw_spin_lock+0x34/0x68
[ 2602.010201] lr : free_fw_priv+0x20/0xfc
[ 2602.020561] sp : ffff800089363b30
[ 2602.020563] x29: ffff800089363b30 x28: ffff0000d0eb5880 x27: 0000000000000000
[ 2602.020570] x26: 0000000000000000 x25: ffff0000d728b330 x24: 0000000000000000
[ 2602.020577] x23: ffff0000dc856f38
[ 2602.033797] x22: ffff800089363b70 x21: ffff0000dc856000
[ 2602.033802] x20: ff00312e6f006573 x19: ffff0000d0d9ea80 x18: 0000000000000000
[ 2602.033809] x17: 0000000000000000 x16: 0000000000000000 x15: 0000aaaad80dd480
[ 2602.083320] x14: 0000000000000000 x13: 00000000000001b9 x12: 0000000000000002
[ 2602.083326] x11: 0000000000000000 x10: 0000000000000a60 x9 : ffff800089363a30
[ 2602.083333] x8 : ffff0001793d75c0 x7 : ffff0000d6dbc400 x6 : 0000000000000000
[ 2602.083339] x5 : 00000000410fd030 x4 : 0000000000000000 x3 : 0000000000000001
[ 2602.083346] x2 : 0000000000000000 x1 : 0000000000000001 x0 : ff00312e6f006573
[ 2602.083354] Call trace:
[ 2602.083356]  _raw_spin_lock+0x34/0x68
[ 2602.083364]  release_firmware+0x48/0x6c
[ 2602.083370]  nxp_setup+0x3c4/0x540 [btnxpuart]
[ 2602.083383]  hci_dev_open_sync+0xf0/0xa34
[ 2602.083391]  hci_dev_open+0xd8/0x178
[ 2602.083399]  hci_sock_ioctl+0x3b0/0x590
[ 2602.083405]  sock_do_ioctl+0x60/0x118
[ 2602.083413]  sock_ioctl+0x2f4/0x374
[ 2602.091430]  __arm64_sys_ioctl+0xac/0xf0
[ 2602.091437]  invoke_syscall+0x48/0x110
[ 2602.091445]  el0_svc_common.constprop.0+0xc0/0xe0
[ 2602.091452]  do_el0_svc+0x1c/0x28
[ 2602.091457]  el0_svc+0x40/0xe4
[ 2602.091465]  el0t_64_sync_handler+0x120/0x12c
[ 2602.091470]  el0t_64_sync+0x190/0x194

Fixes: e3c4891098c8 ("Bluetooth: btnxpuart: Handle FW Download Abort scenario")
Fixes: 689ca16e5232 ("Bluetooth: NXP: Add protocol support for NXP Bluetooth chipsets")
Signed-off-by: Neeraj Sanjay Kale <neeraj.sanjaykale@nxp.com>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btnxpuart.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index 5eae622990b86..5091dea762a07 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -701,8 +701,10 @@ static int nxp_download_firmware(struct hci_dev *hdev)
 							 &nxpdev->tx_state),
 					       msecs_to_jiffies(60000));
 
-	release_firmware(nxpdev->fw);
-	memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
+	if (nxpdev->fw && strlen(nxpdev->fw_name)) {
+		release_firmware(nxpdev->fw);
+		memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
+	}
 
 	if (err == 0) {
 		bt_dev_err(hdev, "FW Download Timeout. offset: %d",

From 007d762107e92eeace3a11d8a0d3d010dd8c6161 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 16:30:06 +0100
Subject: [PATCH 2447/2753] MAINTAINERS: Add dedicated entries for
 phy_link_topology

The infrastructure to handle multi-phy devices is fairly standalone.
Add myself as maintainer for that part as well as the netlink uAPI
that exposes it.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 5959513a7359f..b3a23aceeb641 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16504,6 +16504,13 @@ F:	net/ethtool/mm.c
 F:	tools/testing/selftests/drivers/net/hw/ethtool_mm.sh
 K:	ethtool_mm
 
+NETWORKING [ETHTOOL PHY TOPOLOGY]
+M:	Maxime Chevallier <maxime.chevallier@bootlin.com>
+F:	Documentation/networking/phy-link-topology.rst
+F:	drivers/net/phy/phy_link_topology.c
+F:	include/linux/phy_link_topology.h
+F:	net/ethtool/phy.c
+
 NETWORKING [GENERAL]
 M:	"David S. Miller" <davem@davemloft.net>
 M:	Eric Dumazet <edumazet@google.com>

From f6a069d9540a54a152735ad4f579fbc7d23f2440 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:40 +0100
Subject: [PATCH 2448/2753] net: ethtool: netlink: Allow per-netdevice DUMP
 operations

We have a number of netlink commands in the ethnl family that may have
multiple objects to dump even for a single net_device, including :

 - PLCA, PSE-PD, phy: one message per PHY device
 - tsinfo: one message per timestamp source (netdev + phys)
 - rss: One per RSS context

To get this behaviour, these netlink commands need to roll a custom
->dumpit().

To prepare making per-netdev DUMP more generic in ethnl, introduce a
member in the ethnl ops to indicate if a given command may allow
pernetdev DUMPs (also referred to as filtered DUMPs).

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/netlink.c | 45 +++++++++++++++++++++++++++++--------------
 net/ethtool/netlink.h |  2 ++
 2 files changed, 33 insertions(+), 14 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index a163d40c6431b..7adede5e4ff17 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -587,21 +587,38 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 	int ret = 0;
 
 	rcu_read_lock();
-	for_each_netdev_dump(net, dev, ctx->pos_ifindex) {
-		dev_hold(dev);
+	if (ctx->req_info->dev) {
+		dev = ctx->req_info->dev;
 		rcu_read_unlock();
+		/* Filtered DUMP request targeted to a single netdev. We already
+		 * hold a ref to the netdev from ->start()
+		 */
+		ret = ethnl_default_dump_one(skb, dev, ctx,
+					     genl_info_dump(cb));
+		rcu_read_lock();
+		netdev_put(ctx->req_info->dev, &ctx->req_info->dev_tracker);
 
-		ret = ethnl_default_dump_one(skb, dev, ctx, genl_info_dump(cb));
+		if (ret < 0 && ret != -EOPNOTSUPP && likely(skb->len))
+			ret = skb->len;
 
-		rcu_read_lock();
-		dev_put(dev);
+	} else {
+		for_each_netdev_dump(net, dev, ctx->pos_ifindex) {
+			dev_hold(dev);
+			rcu_read_unlock();
+
+			ret = ethnl_default_dump_one(skb, dev, ctx,
+						     genl_info_dump(cb));
+
+			rcu_read_lock();
+			dev_put(dev);
 
-		if (ret < 0 && ret != -EOPNOTSUPP) {
-			if (likely(skb->len))
-				ret = skb->len;
-			break;
+			if (ret < 0 && ret != -EOPNOTSUPP) {
+				if (likely(skb->len))
+					ret = skb->len;
+				break;
+			}
+			ret = 0;
 		}
-		ret = 0;
 	}
 	rcu_read_unlock();
 
@@ -635,10 +652,10 @@ static int ethnl_default_start(struct netlink_callback *cb)
 	}
 
 	ret = ethnl_default_parse(req_info, &info->info, ops, false);
-	if (req_info->dev) {
-		/* We ignore device specification in dump requests but as the
-		 * same parser as for non-dump (doit) requests is used, it
-		 * would take reference to the device if it finds one
+	if (req_info->dev && !ops->allow_pernetdev_dump) {
+		/* We ignore device specification in unfiltered dump requests
+		 * but as the same parser as for non-dump (doit) requests is
+		 * used, it would take reference to the device if it finds one
 		 */
 		netdev_put(req_info->dev, &req_info->dev_tracker);
 		req_info->dev = NULL;
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index ec6ab5443a6f2..4aaa73282d6a1 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -331,6 +331,7 @@ int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid,
  * @req_info_size:    size of request info
  * @reply_data_size:  size of reply data
  * @allow_nodev_do:   allow non-dump request with no device identification
+ * @allow_pernetdev_dump: allow filtering dump requests with ifname/ifindex
  * @set_ntf_cmd:      notification to generate on changes (SET)
  * @parse_request:
  *	Parse request except common header (struct ethnl_req_info). Common
@@ -388,6 +389,7 @@ struct ethnl_request_ops {
 	unsigned int		req_info_size;
 	unsigned int		reply_data_size;
 	bool			allow_nodev_do;
+	bool			allow_pernetdev_dump;
 	u8			set_ntf_cmd;
 
 	int (*parse_request)(struct ethnl_req_info *req_info,

From 12608eb20620182b7fb5d1afb530f4ceb5e2e284 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:41 +0100
Subject: [PATCH 2449/2753] net: ethtool: netlink: Rename
 ethnl_default_dump_one

As we work on getting more objects out of a per-netdev DUMP, rename
ethnl_default_dump_one() into ethnl_default_dump_one_dev(), making it
explicit that this dumps everything for one netdev.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/netlink.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 7adede5e4ff17..644c202d284d7 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -540,9 +540,9 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
-static int ethnl_default_dump_one(struct sk_buff *skb, struct net_device *dev,
-				  const struct ethnl_dump_ctx *ctx,
-				  const struct genl_info *info)
+static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
+				      const struct ethnl_dump_ctx *ctx,
+				      const struct genl_info *info)
 {
 	void *ehdr;
 	int ret;
@@ -593,8 +593,8 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 		/* Filtered DUMP request targeted to a single netdev. We already
 		 * hold a ref to the netdev from ->start()
 		 */
-		ret = ethnl_default_dump_one(skb, dev, ctx,
-					     genl_info_dump(cb));
+		ret = ethnl_default_dump_one_dev(skb, dev, ctx,
+						 genl_info_dump(cb));
 		rcu_read_lock();
 		netdev_put(ctx->req_info->dev, &ctx->req_info->dev_tracker);
 
@@ -606,8 +606,8 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 			dev_hold(dev);
 			rcu_read_unlock();
 
-			ret = ethnl_default_dump_one(skb, dev, ctx,
-						     genl_info_dump(cb));
+			ret = ethnl_default_dump_one_dev(skb, dev, ctx,
+							 genl_info_dump(cb));
 
 			rcu_read_lock();
 			dev_put(dev);

From 9d669e93c670a2523e8d6f91edbe9229493261d3 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:42 +0100
Subject: [PATCH 2450/2753] net: ethtool: netlink: Introduce command-specific
 dump_one_dev

Prepare more generic ethnl DUMP hanldling, by allowing netlink commands
to register their own dump_one_dev() callback. This avoids having to
roll with a fully custom genl ->dumpit callback, allowing the re-use
of some ethnl plumbing.

Fallback to the default dump_one_dev behaviour when no custom callback
is found.

The command dump context is maintained within the ethnl_dump_ctx, that
we move in netlink.h so that command handlers can access it.

This context can be allocated/freed in new ->dump_start() and
->dump_done() callbacks.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/netlink.c | 62 +++++++++++++++++++++++++------------------
 net/ethtool/netlink.h | 35 ++++++++++++++++++++++++
 2 files changed, 71 insertions(+), 26 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 644c202d284d7..2dc6086e1ab59 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -339,24 +339,6 @@ int ethnl_multicast(struct sk_buff *skb, struct net_device *dev)
 
 /* GET request helpers */
 
-/**
- * struct ethnl_dump_ctx - context structure for generic dumpit() callback
- * @ops:        request ops of currently processed message type
- * @req_info:   parsed request header of processed request
- * @reply_data: data needed to compose the reply
- * @pos_ifindex: saved iteration position - ifindex
- *
- * These parameters are kept in struct netlink_callback as context preserved
- * between iterations. They are initialized by ethnl_default_start() and used
- * in ethnl_default_dumpit() and ethnl_default_done().
- */
-struct ethnl_dump_ctx {
-	const struct ethnl_request_ops	*ops;
-	struct ethnl_req_info		*req_info;
-	struct ethnl_reply_data		*reply_data;
-	unsigned long			pos_ifindex;
-};
-
 static const struct ethnl_request_ops *
 ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_STRSET_GET]	= &ethnl_strset_request_ops,
@@ -540,9 +522,9 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
-static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
-				      const struct ethnl_dump_ctx *ctx,
-				      const struct genl_info *info)
+static int ethnl_default_dump_one(struct sk_buff *skb,
+				  const struct ethnl_dump_ctx *ctx,
+				  const struct genl_info *info)
 {
 	void *ehdr;
 	int ret;
@@ -553,15 +535,15 @@ static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *de
 	if (!ehdr)
 		return -EMSGSIZE;
 
-	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
 	rtnl_lock();
-	netdev_lock_ops(dev);
+	netdev_lock_ops(ctx->reply_data->dev);
 	ret = ctx->ops->prepare_data(ctx->req_info, ctx->reply_data, info);
-	netdev_unlock_ops(dev);
+	netdev_unlock_ops(ctx->reply_data->dev);
 	rtnl_unlock();
 	if (ret < 0)
 		goto out;
-	ret = ethnl_fill_reply_header(skb, dev, ctx->ops->hdr_attr);
+	ret = ethnl_fill_reply_header(skb, ctx->reply_data->dev,
+				      ctx->ops->hdr_attr);
 	if (ret < 0)
 		goto out;
 	ret = ctx->ops->fill_reply(skb, ctx->req_info, ctx->reply_data);
@@ -569,11 +551,29 @@ static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *de
 out:
 	if (ctx->ops->cleanup_data)
 		ctx->ops->cleanup_data(ctx->reply_data);
-	ctx->reply_data->dev = NULL;
+
 	if (ret < 0)
 		genlmsg_cancel(skb, ehdr);
 	else
 		genlmsg_end(skb, ehdr);
+
+	return ret;
+}
+
+static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
+				      struct ethnl_dump_ctx *ctx,
+				      const struct genl_info *info)
+{
+	int ret;
+
+	ethnl_init_reply_data(ctx->reply_data, ctx->ops, dev);
+
+	if (ctx->ops->dump_one_dev)
+		ret = ctx->ops->dump_one_dev(skb, ctx, info);
+	else
+		ret = ethnl_default_dump_one(skb, ctx, info);
+
+	ctx->reply_data->dev = NULL;
 	return ret;
 }
 
@@ -606,6 +606,7 @@ static int ethnl_default_dumpit(struct sk_buff *skb,
 			dev_hold(dev);
 			rcu_read_unlock();
 
+			ctx->req_info->dev = dev;
 			ret = ethnl_default_dump_one_dev(skb, dev, ctx,
 							 genl_info_dump(cb));
 
@@ -668,6 +669,12 @@ static int ethnl_default_start(struct netlink_callback *cb)
 	ctx->reply_data = reply_data;
 	ctx->pos_ifindex = 0;
 
+	if (ctx->ops->dump_start) {
+		ret = ctx->ops->dump_start(ctx);
+		if (ret)
+			goto free_reply_data;
+	}
+
 	return 0;
 
 free_reply_data:
@@ -683,6 +690,9 @@ static int ethnl_default_done(struct netlink_callback *cb)
 {
 	struct ethnl_dump_ctx *ctx = ethnl_dump_context(cb);
 
+	if (ctx->ops->dump_done)
+		ctx->ops->dump_done(ctx);
+
 	kfree(ctx->reply_data);
 	kfree(ctx->req_info);
 
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 4aaa73282d6a1..79fe98190c64e 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -307,6 +307,26 @@ struct ethnl_reply_data {
 	struct net_device		*dev;
 };
 
+/**
+ * struct ethnl_dump_ctx - context structure for generic dumpit() callback
+ * @ops:        request ops of currently processed message type
+ * @req_info:   parsed request header of processed request
+ * @reply_data: data needed to compose the reply
+ * @pos_ifindex: saved iteration position - ifindex
+ * @cmd_ctx: command-specific context to maintain across the dump.
+ *
+ * These parameters are kept in struct netlink_callback as context preserved
+ * between iterations. They are initialized by ethnl_default_start() and used
+ * in ethnl_default_dumpit() and ethnl_default_done().
+ */
+struct ethnl_dump_ctx {
+	const struct ethnl_request_ops	*ops;
+	struct ethnl_req_info		*req_info;
+	struct ethnl_reply_data		*reply_data;
+	unsigned long			pos_ifindex;
+	void				*cmd_ctx;
+};
+
 int ethnl_ops_begin(struct net_device *dev);
 void ethnl_ops_complete(struct net_device *dev);
 
@@ -373,6 +393,15 @@ int ethnl_sock_priv_set(struct sk_buff *skb, struct net_device *dev, u32 portid,
  *	 - 0 if no configuration has changed
  *	 - 1 if configuration changed and notification should be generated
  *	 - negative errno on errors
+ * @dump_start:
+ *	Optional callback to prepare a dump operation, should there be a need
+ *	to maintain some context across the dump.
+ * @dump_one_dev:
+ *	Optional callback to generate all messages for a given netdev. This
+ *	is relevant only when a request can produce different results for the
+ *	same netdev depending on command-specific attributes.
+ * @dump_done:
+ *	Optional callback to cleanup any context allocated in ->dump_start()
  *
  * Description of variable parts of GET request handling when using the
  * unified infrastructure. When used, a pointer to an instance of this
@@ -409,6 +438,12 @@ struct ethnl_request_ops {
 			    struct genl_info *info);
 	int (*set)(struct ethnl_req_info *req_info,
 		   struct genl_info *info);
+
+	int (*dump_start)(struct ethnl_dump_ctx *ctx);
+	int (*dump_one_dev)(struct sk_buff *skb,
+			    struct ethnl_dump_ctx *ctx,
+			    const struct genl_info *info);
+	void (*dump_done)(struct ethnl_dump_ctx *ctx);
 };
 
 /* request handlers */

From 03ef42429cb9b4687cd65644a196ed1e1917a279 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:43 +0100
Subject: [PATCH 2451/2753] net: ethtool: netlink: Introduce per-phy DUMP
 helpers

As there are multiple ethnl commands that report messages based on
phy_device information, let's introduce a set of ethnl generic dump
helpers to allow DUMP support for each PHY on a given netdev.

This logic iterates over the phy_link_topology of each netdev (or a
single netdev for filtered DUMP), and call ethnl_default_dump_one() with
the req_info populated with ifindex + phyindex.

This allows re-using all the existing infra for phy-targetting commands
that already use ethnl generic helpers.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/netlink.c | 78 +++++++++++++++++++++++++++++++++++++++++++
 net/ethtool/netlink.h |  6 ++++
 2 files changed, 84 insertions(+)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 2dc6086e1ab59..821bc8b99306e 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -560,6 +560,84 @@ static int ethnl_default_dump_one(struct sk_buff *skb,
 	return ret;
 }
 
+/* Specific context for phy-targeting command DUMP operatins. We keep in context
+ * the latest phy_index we dumped, in case of an interrupted DUMP.
+ */
+struct ethnl_dump_ctx_perphy {
+	unsigned long phy_index;
+};
+
+/**
+ * ethnl_dump_start_perphy() - Initialise a dump for PHY cmds
+ * @ctx: Generic ethnl dump context whose cmd_ctx will be initialized
+ *
+ * Initializes a dump context for ethnl commands that may return
+ * one message per PHY on a single netdev.
+ *
+ * Returns: 0 for success, a negative value for errors.
+ */
+int ethnl_dump_start_perphy(struct ethnl_dump_ctx *ctx)
+{
+	struct ethnl_dump_ctx_perphy *dump_ctx;
+
+	dump_ctx = kzalloc(sizeof(*dump_ctx), GFP_KERNEL);
+	if (!dump_ctx)
+		return -ENOMEM;
+
+	ctx->cmd_ctx = dump_ctx;
+
+	return 0;
+}
+
+/**
+ * ethnl_dump_done_perphy() - Releases the per-phy dump context
+ * @ctx: Generic ethnl dump context whose cmd_ctx will be released
+ */
+void ethnl_dump_done_perphy(struct ethnl_dump_ctx *ctx)
+{
+	kfree(ctx->cmd_ctx);
+}
+
+/**
+ * ethnl_dump_one_dev_perphy() - Dump all PHY-related messages for one netdev
+ * @skb: skb containing the DUMP result
+ * @ctx: Dump context. Will be kept across the DUMP operation.
+ * @info: Genl receive info
+ *
+ * Some commands are related to PHY devices attached to netdevs. As there may be
+ * multiple PHYs, this DUMP handler will populate the reply with one message per
+ * PHY on a single netdev.
+ *
+ * Returns: 0 for success or when nothing to do, a negative value otherwise.
+ */
+int ethnl_dump_one_dev_perphy(struct sk_buff *skb,
+			      struct ethnl_dump_ctx *ctx,
+			      const struct genl_info *info)
+{
+	struct ethnl_dump_ctx_perphy *dump_ctx = ctx->cmd_ctx;
+	struct net_device *dev = ctx->reply_data->dev;
+	struct phy_device_node *pdn;
+	int ret = 0;
+
+	if (!dev->link_topo)
+		return 0;
+
+	xa_for_each_start(&dev->link_topo->phys, dump_ctx->phy_index,
+			  pdn, dump_ctx->phy_index) {
+		ctx->req_info->phy_index = dump_ctx->phy_index;
+
+		/* We can re-use the original dump_one as ->prepare_data in
+		 * commands use ethnl_req_get_phydev(), which gets the PHY from
+		 * what's in req_info
+		 */
+		ret = ethnl_default_dump_one(skb, ctx, info);
+		if (ret)
+			break;
+	}
+
+	return ret;
+}
+
 static int ethnl_default_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
 				      struct ethnl_dump_ctx *ctx,
 				      const struct genl_info *info)
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 79fe98190c64e..530a9b5c8b392 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -327,6 +327,12 @@ struct ethnl_dump_ctx {
 	void				*cmd_ctx;
 };
 
+/* Generic callbacks to be used by PHY targeting commands */
+int ethnl_dump_start_perphy(struct ethnl_dump_ctx *ctx);
+int ethnl_dump_one_dev_perphy(struct sk_buff *skb, struct ethnl_dump_ctx *ctx,
+			      const struct genl_info *info);
+void ethnl_dump_done_perphy(struct ethnl_dump_ctx *ctx);
+
 int ethnl_ops_begin(struct net_device *dev);
 void ethnl_ops_complete(struct net_device *dev);
 

From ea20c0621385f2e2d1af7bff395138cfb37725d6 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:44 +0100
Subject: [PATCH 2452/2753] net: ethtool: phy: Convert the PHY_GET command to
 generic phy dump

Now that we have an infrastructure in ethnl for perphy DUMPs, we can get
rid of the custom ->doit and ->dumpit to deal with PHY listing commands.

As most of the code was custom, this basically means re-writing how we
deal with PHY listing.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/netlink.c |   9 +-
 net/ethtool/netlink.h |   4 -
 net/ethtool/phy.c     | 344 ++++++++++++------------------------------
 3 files changed, 105 insertions(+), 252 deletions(-)

diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 821bc8b99306e..b32ddfe7cf88a 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -382,6 +382,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_MM_SET]		= &ethnl_mm_request_ops,
 	[ETHTOOL_MSG_TSCONFIG_GET]	= &ethnl_tsconfig_request_ops,
 	[ETHTOOL_MSG_TSCONFIG_SET]	= &ethnl_tsconfig_request_ops,
+	[ETHTOOL_MSG_PHY_GET]		= &ethnl_phy_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -1374,10 +1375,10 @@ static const struct genl_ops ethtool_genl_ops[] = {
 	},
 	{
 		.cmd	= ETHTOOL_MSG_PHY_GET,
-		.doit	= ethnl_phy_doit,
-		.start	= ethnl_phy_start,
-		.dumpit	= ethnl_phy_dumpit,
-		.done	= ethnl_phy_done,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_default_start,
+		.dumpit	= ethnl_default_dumpit,
+		.done	= ethnl_default_done,
 		.policy = ethnl_phy_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_phy_get_policy) - 1,
 	},
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 530a9b5c8b392..60f16090640f8 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -542,10 +542,6 @@ int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_act_module_fw_flash(struct sk_buff *skb, struct genl_info *info);
 int ethnl_rss_dump_start(struct netlink_callback *cb);
 int ethnl_rss_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_start(struct netlink_callback *cb);
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info);
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
-int ethnl_phy_done(struct netlink_callback *cb);
 int ethnl_tsinfo_start(struct netlink_callback *cb);
 int ethnl_tsinfo_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
 int ethnl_tsinfo_done(struct netlink_callback *cb);
diff --git a/net/ethtool/phy.c b/net/ethtool/phy.c
index 1f590e8d75ed6..88343fed73666 100644
--- a/net/ethtool/phy.c
+++ b/net/ethtool/phy.c
@@ -12,304 +12,160 @@
 #include <net/netdev_lock.h>
 
 struct phy_req_info {
-	struct ethnl_req_info		base;
-	struct phy_device_node		*pdn;
+	struct ethnl_req_info base;
 };
 
-#define PHY_REQINFO(__req_base) \
-	container_of(__req_base, struct phy_req_info, base)
+struct phy_reply_data {
+	struct ethnl_reply_data	base;
+	u32 phyindex;
+	char *drvname;
+	char *name;
+	unsigned int upstream_type;
+	char *upstream_sfp_name;
+	unsigned int upstream_index;
+	char *downstream_sfp_name;
+};
+
+#define PHY_REPDATA(__reply_base) \
+	container_of(__reply_base, struct phy_reply_data, base)
 
 const struct nla_policy ethnl_phy_get_policy[ETHTOOL_A_PHY_HEADER + 1] = {
 	[ETHTOOL_A_PHY_HEADER] = NLA_POLICY_NESTED(ethnl_header_policy),
 };
 
-/* Caller holds rtnl */
-static ssize_t
-ethnl_phy_reply_size(const struct ethnl_req_info *req_base,
-		     struct netlink_ext_ack *extack)
+static int phy_reply_size(const struct ethnl_req_info *req_info,
+			  const struct ethnl_reply_data *reply_data)
 {
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn = req_info->pdn;
-	struct phy_device *phydev = pdn->phy;
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 	size_t size = 0;
 
-	ASSERT_RTNL();
-
 	/* ETHTOOL_A_PHY_INDEX */
 	size += nla_total_size(sizeof(u32));
 
 	/* ETHTOOL_A_DRVNAME */
-	if (phydev->drv)
-		size += nla_total_size(strlen(phydev->drv->name) + 1);
+	if (rep_data->drvname)
+		size += nla_total_size(strlen(rep_data->drvname) + 1);
 
 	/* ETHTOOL_A_NAME */
-	size += nla_total_size(strlen(dev_name(&phydev->mdio.dev)) + 1);
+	size += nla_total_size(strlen(rep_data->name) + 1);
 
 	/* ETHTOOL_A_PHY_UPSTREAM_TYPE */
 	size += nla_total_size(sizeof(u32));
 
-	if (phy_on_sfp(phydev)) {
-		const char *upstream_sfp_name = sfp_get_name(pdn->parent_sfp_bus);
-
-		/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
-		if (upstream_sfp_name)
-			size += nla_total_size(strlen(upstream_sfp_name) + 1);
+	/* ETHTOOL_A_PHY_UPSTREAM_SFP_NAME */
+	if (rep_data->upstream_sfp_name)
+		size += nla_total_size(strlen(rep_data->upstream_sfp_name) + 1);
 
-		/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+	/* ETHTOOL_A_PHY_UPSTREAM_INDEX */
+	if (rep_data->upstream_index)
 		size += nla_total_size(sizeof(u32));
-	}
 
 	/* ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME */
-	if (phydev->sfp_bus) {
-		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
-
-		if (sfp_name)
-			size += nla_total_size(strlen(sfp_name) + 1);
-	}
+	if (rep_data->downstream_sfp_name)
+		size += nla_total_size(strlen(rep_data->downstream_sfp_name) + 1);
 
 	return size;
 }
 
-static int
-ethnl_phy_fill_reply(const struct ethnl_req_info *req_base, struct sk_buff *skb)
+static int phy_prepare_data(const struct ethnl_req_info *req_info,
+			    struct ethnl_reply_data *reply_data,
+			    const struct genl_info *info)
 {
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device_node *pdn = req_info->pdn;
-	struct phy_device *phydev = pdn->phy;
-	enum phy_upstream ptype;
+	struct phy_link_topology *topo = reply_data->dev->link_topo;
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
+	struct nlattr **tb = info->attrs;
+	struct phy_device_node *pdn;
+	struct phy_device *phydev;
 
-	ptype = pdn->upstream_type;
+	/* RTNL is held by the caller */
+	phydev = ethnl_req_get_phydev(req_info, tb, ETHTOOL_A_PHY_HEADER,
+				      info->extack);
+	if (IS_ERR_OR_NULL(phydev))
+		return -EOPNOTSUPP;
 
-	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, phydev->phyindex) ||
-	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, dev_name(&phydev->mdio.dev)) ||
-	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, ptype))
-		return -EMSGSIZE;
+	pdn = xa_load(&topo->phys, phydev->phyindex);
+	if (!pdn)
+		return -EOPNOTSUPP;
 
-	if (phydev->drv &&
-	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, phydev->drv->name))
-		return -EMSGSIZE;
+	rep_data->phyindex = phydev->phyindex;
+	rep_data->name = kstrdup(dev_name(&phydev->mdio.dev), GFP_KERNEL);
+	rep_data->drvname = kstrdup(phydev->drv->name, GFP_KERNEL);
+	rep_data->upstream_type = pdn->upstream_type;
 
-	if (ptype == PHY_UPSTREAM_PHY) {
+	if (pdn->upstream_type == PHY_UPSTREAM_PHY) {
 		struct phy_device *upstream = pdn->upstream.phydev;
-		const char *sfp_upstream_name;
-
-		/* Parent index */
-		if (nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX, upstream->phyindex))
-			return -EMSGSIZE;
-
-		if (pdn->parent_sfp_bus) {
-			sfp_upstream_name = sfp_get_name(pdn->parent_sfp_bus);
-			if (sfp_upstream_name &&
-			    nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
-					   sfp_upstream_name))
-				return -EMSGSIZE;
-		}
+		rep_data->upstream_index = upstream->phyindex;
 	}
 
-	if (phydev->sfp_bus) {
-		const char *sfp_name = sfp_get_name(phydev->sfp_bus);
+	if (pdn->parent_sfp_bus)
+		rep_data->upstream_sfp_name = kstrdup(sfp_get_name(pdn->parent_sfp_bus),
+						      GFP_KERNEL);
 
-		if (sfp_name &&
-		    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
-				   sfp_name))
-			return -EMSGSIZE;
-	}
+	if (phydev->sfp_bus)
+		rep_data->downstream_sfp_name = kstrdup(sfp_get_name(phydev->sfp_bus),
+							GFP_KERNEL);
 
 	return 0;
 }
 
-static int ethnl_phy_parse_request(struct ethnl_req_info *req_base,
-				   struct nlattr **tb,
-				   struct netlink_ext_ack *extack)
+static int phy_fill_reply(struct sk_buff *skb,
+			  const struct ethnl_req_info *req_info,
+			  const struct ethnl_reply_data *reply_data)
 {
-	struct phy_link_topology *topo = req_base->dev->link_topo;
-	struct phy_req_info *req_info = PHY_REQINFO(req_base);
-	struct phy_device *phydev;
-
-	phydev = ethnl_req_get_phydev(req_base, tb, ETHTOOL_A_PHY_HEADER,
-				      extack);
-	if (!phydev)
-		return 0;
-
-	if (IS_ERR(phydev))
-		return PTR_ERR(phydev);
-
-	if (!topo)
-		return 0;
-
-	req_info->pdn = xa_load(&topo->phys, phydev->phyindex);
-
-	return 0;
-}
-
-int ethnl_phy_doit(struct sk_buff *skb, struct genl_info *info)
-{
-	struct phy_req_info req_info = {};
-	struct nlattr **tb = info->attrs;
-	struct sk_buff *rskb;
-	void *reply_payload;
-	int reply_len;
-	int ret;
-
-	ret = ethnl_parse_header_dev_get(&req_info.base,
-					 tb[ETHTOOL_A_PHY_HEADER],
-					 genl_info_net(info), info->extack,
-					 true);
-	if (ret < 0)
-		return ret;
-
-	rtnl_lock();
-	netdev_lock_ops(req_info.base.dev);
-
-	ret = ethnl_phy_parse_request(&req_info.base, tb, info->extack);
-	if (ret < 0)
-		goto err_unlock;
-
-	/* No PHY, return early */
-	if (!req_info.pdn)
-		goto err_unlock;
-
-	ret = ethnl_phy_reply_size(&req_info.base, info->extack);
-	if (ret < 0)
-		goto err_unlock;
-	reply_len = ret + ethnl_reply_header_size();
-
-	rskb = ethnl_reply_init(reply_len, req_info.base.dev,
-				ETHTOOL_MSG_PHY_GET_REPLY,
-				ETHTOOL_A_PHY_HEADER,
-				info, &reply_payload);
-	if (!rskb) {
-		ret = -ENOMEM;
-		goto err_unlock;
-	}
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 
-	ret = ethnl_phy_fill_reply(&req_info.base, rskb);
-	if (ret)
-		goto err_free_msg;
-
-	netdev_unlock_ops(req_info.base.dev);
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	genlmsg_end(rskb, reply_payload);
-
-	return genlmsg_reply(rskb, info);
-
-err_free_msg:
-	nlmsg_free(rskb);
-err_unlock:
-	netdev_unlock_ops(req_info.base.dev);
-	rtnl_unlock();
-	ethnl_parse_header_dev_put(&req_info.base);
-	return ret;
-}
-
-struct ethnl_phy_dump_ctx {
-	struct phy_req_info	*phy_req_info;
-	unsigned long ifindex;
-	unsigned long phy_index;
-};
-
-int ethnl_phy_start(struct netlink_callback *cb)
-{
-	const struct genl_info *info = genl_info_dump(cb);
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	int ret;
+	if (nla_put_u32(skb, ETHTOOL_A_PHY_INDEX, rep_data->phyindex) ||
+	    nla_put_string(skb, ETHTOOL_A_PHY_NAME, rep_data->name) ||
+	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_TYPE, rep_data->upstream_type))
+		return -EMSGSIZE;
 
-	BUILD_BUG_ON(sizeof(*ctx) > sizeof(cb->ctx));
+	if (rep_data->drvname &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_DRVNAME, rep_data->drvname))
+		return -EMSGSIZE;
 
-	ctx->phy_req_info = kzalloc(sizeof(*ctx->phy_req_info), GFP_KERNEL);
-	if (!ctx->phy_req_info)
-		return -ENOMEM;
+	if (rep_data->upstream_index &&
+	    nla_put_u32(skb, ETHTOOL_A_PHY_UPSTREAM_INDEX,
+			rep_data->upstream_index))
+		return -EMSGSIZE;
 
-	ret = ethnl_parse_header_dev_get(&ctx->phy_req_info->base,
-					 info->attrs[ETHTOOL_A_PHY_HEADER],
-					 sock_net(cb->skb->sk), cb->extack,
-					 false);
-	ctx->ifindex = 0;
-	ctx->phy_index = 0;
+	if (rep_data->upstream_sfp_name &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_UPSTREAM_SFP_NAME,
+			   rep_data->upstream_sfp_name))
+		return -EMSGSIZE;
 
-	if (ret)
-		kfree(ctx->phy_req_info);
+	if (rep_data->downstream_sfp_name &&
+	    nla_put_string(skb, ETHTOOL_A_PHY_DOWNSTREAM_SFP_NAME,
+			   rep_data->downstream_sfp_name))
+		return -EMSGSIZE;
 
-	return ret;
+	return 0;
 }
 
-int ethnl_phy_done(struct netlink_callback *cb)
+static void phy_cleanup_data(struct ethnl_reply_data *reply_data)
 {
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-
-	if (ctx->phy_req_info->base.dev)
-		ethnl_parse_header_dev_put(&ctx->phy_req_info->base);
-
-	kfree(ctx->phy_req_info);
+	struct phy_reply_data *rep_data = PHY_REPDATA(reply_data);
 
-	return 0;
+	kfree(rep_data->drvname);
+	kfree(rep_data->name);
+	kfree(rep_data->upstream_sfp_name);
+	kfree(rep_data->downstream_sfp_name);
 }
 
-static int ethnl_phy_dump_one_dev(struct sk_buff *skb, struct net_device *dev,
-				  struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct phy_req_info *pri = ctx->phy_req_info;
-	struct phy_device_node *pdn;
-	int ret = 0;
-	void *ehdr;
-
-	if (!dev->link_topo)
-		return 0;
-
-	xa_for_each_start(&dev->link_topo->phys, ctx->phy_index, pdn, ctx->phy_index) {
-		ehdr = ethnl_dump_put(skb, cb, ETHTOOL_MSG_PHY_GET_REPLY);
-		if (!ehdr) {
-			ret = -EMSGSIZE;
-			break;
-		}
-
-		ret = ethnl_fill_reply_header(skb, dev, ETHTOOL_A_PHY_HEADER);
-		if (ret < 0) {
-			genlmsg_cancel(skb, ehdr);
-			break;
-		}
-
-		pri->pdn = pdn;
-		ret = ethnl_phy_fill_reply(&pri->base, skb);
-		if (ret < 0) {
-			genlmsg_cancel(skb, ehdr);
-			break;
-		}
-
-		genlmsg_end(skb, ehdr);
-	}
+const struct ethnl_request_ops ethnl_phy_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_PHY_GET,
+	.reply_cmd		= ETHTOOL_MSG_PHY_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_PHY_HEADER,
+	.req_info_size		= sizeof(struct phy_req_info),
+	.reply_data_size	= sizeof(struct phy_reply_data),
 
-	return ret;
-}
+	.prepare_data		= phy_prepare_data,
+	.reply_size		= phy_reply_size,
+	.fill_reply		= phy_fill_reply,
+	.cleanup_data		= phy_cleanup_data,
 
-int ethnl_phy_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
-{
-	struct ethnl_phy_dump_ctx *ctx = (void *)cb->ctx;
-	struct net *net = sock_net(skb->sk);
-	struct net_device *dev;
-	int ret = 0;
-
-	rtnl_lock();
-
-	if (ctx->phy_req_info->base.dev) {
-		dev = ctx->phy_req_info->base.dev;
-		netdev_lock_ops(dev);
-		ret = ethnl_phy_dump_one_dev(skb, dev, cb);
-		netdev_unlock_ops(dev);
-	} else {
-		for_each_netdev_dump(net, dev, ctx->ifindex) {
-			netdev_lock_ops(dev);
-			ret = ethnl_phy_dump_one_dev(skb, dev, cb);
-			netdev_unlock_ops(dev);
-			if (ret)
-				break;
-
-			ctx->phy_index = 0;
-		}
-	}
-	rtnl_unlock();
+	.dump_start		= ethnl_dump_start_perphy,
+	.dump_one_dev		= ethnl_dump_one_dev_perphy,
+	.dump_done		= ethnl_dump_done_perphy,
 
-	return ret;
-}
+	.allow_pernetdev_dump	= true,
+};

From ff803d2dd531d0df6a57316c2bedefbdf674cd3b Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:45 +0100
Subject: [PATCH 2453/2753] net: ethtool: plca: Use per-PHY DUMP operations

Leverage the per-phy ethnl DUMP helpers in case we have more that one
PLCA-able PHY on the link.

This is done for both PLCA status and PLCA config.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/plca.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/net/ethtool/plca.c b/net/ethtool/plca.c
index e1f7820a6158f..2148ff6075617 100644
--- a/net/ethtool/plca.c
+++ b/net/ethtool/plca.c
@@ -191,6 +191,12 @@ const struct ethnl_request_ops ethnl_plca_cfg_request_ops = {
 
 	.set			= ethnl_set_plca,
 	.set_ntf_cmd		= ETHTOOL_MSG_PLCA_NTF,
+
+	.dump_start		= ethnl_dump_start_perphy,
+	.dump_one_dev		= ethnl_dump_one_dev_perphy,
+	.dump_done		= ethnl_dump_done_perphy,
+
+	.allow_pernetdev_dump	= true,
 };
 
 // PLCA get status message -------------------------------------------------- //
@@ -268,4 +274,10 @@ const struct ethnl_request_ops ethnl_plca_status_request_ops = {
 	.prepare_data		= plca_get_status_prepare_data,
 	.reply_size		= plca_get_status_reply_size,
 	.fill_reply		= plca_get_status_fill_reply,
+
+	.dump_start		= ethnl_dump_start_perphy,
+	.dump_one_dev		= ethnl_dump_one_dev_perphy,
+	.dump_done		= ethnl_dump_done_perphy,
+
+	.allow_pernetdev_dump	= true,
 };

From 36b255b78368fbe9467e49ef9269f844c826f7dd Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Thu, 13 Mar 2025 19:26:46 +0100
Subject: [PATCH 2454/2753] net: ethtool: pse-pd: Use per-PHY DUMP operations

Leverage the per-phy ethnl DUMP helpers in case we have more that one
PSE PHY on the link.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ethtool/pse-pd.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 4f6b99eab2a6c..f3d14be8bdd9b 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -314,4 +314,10 @@ const struct ethnl_request_ops ethnl_pse_request_ops = {
 
 	.set			= ethnl_set_pse,
 	/* PSE has no notification */
+
+	.dump_start		= ethnl_dump_start_perphy,
+	.dump_one_dev		= ethnl_dump_one_dev_perphy,
+	.dump_done		= ethnl_dump_done_perphy,
+
+	.allow_pernetdev_dump	= true,
 };

From 3ce6925f67540e661659993719de12872a25a776 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Mar 2025 20:44:25 +0100
Subject: [PATCH 2455/2753] net: phy: realtek: remove call to
 devm_hwmon_sanitize_name

Since c909e68f8127 ("hwmon: (core) Use device name as a fallback in
devm_hwmon_device_register_with_info") we can simply provide NULL
as name argument.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/realtek/realtek_hwmon.c | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_hwmon.c b/drivers/net/phy/realtek/realtek_hwmon.c
index 1ecb410bb9418..ac96e2d1ebe82 100644
--- a/drivers/net/phy/realtek/realtek_hwmon.c
+++ b/drivers/net/phy/realtek/realtek_hwmon.c
@@ -63,16 +63,11 @@ static const struct hwmon_chip_info rtl822x_hwmon_chip_info = {
 int rtl822x_hwmon_init(struct phy_device *phydev)
 {
 	struct device *hwdev, *dev = &phydev->mdio.dev;
-	const char *name;
 
 	/* Ensure over-temp alarm is reset. */
 	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND2, RTL822X_VND2_TSALRM, 3);
 
-	name = devm_hwmon_sanitize_name(dev, dev_name(dev));
-	if (IS_ERR(name))
-		return PTR_ERR(name);
-
-	hwdev = devm_hwmon_device_register_with_info(dev, name, phydev,
+	hwdev = devm_hwmon_device_register_with_info(dev, NULL, phydev,
 						     &rtl822x_hwmon_chip_info,
 						     NULL);
 	return PTR_ERR_OR_ZERO(hwdev);

From a16376444e7386df1b91db7756c884ef1b499b3a Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Mar 2025 20:45:06 +0100
Subject: [PATCH 2456/2753] net: phy: tja11xx: remove call to
 devm_hwmon_sanitize_name

Since c909e68f8127 ("hwmon: (core) Use device name as a fallback in
devm_hwmon_device_register_with_info") we can simply provide NULL
as name argument.

Note that neither priv->hwmon_name nor priv->hwmon_dev are used
outside tja11xx_hwmon_register.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/nxp-tja11xx.c | 19 +++++--------------
 1 file changed, 5 insertions(+), 14 deletions(-)

diff --git a/drivers/net/phy/nxp-tja11xx.c b/drivers/net/phy/nxp-tja11xx.c
index 601094fe24ca8..07e94a2478ac3 100644
--- a/drivers/net/phy/nxp-tja11xx.c
+++ b/drivers/net/phy/nxp-tja11xx.c
@@ -87,8 +87,6 @@
 #define TJA110X_RMII_MODE_REFCLK_IN       BIT(0)
 
 struct tja11xx_priv {
-	char		*hwmon_name;
-	struct device	*hwmon_dev;
 	struct phy_device *phydev;
 	struct work_struct phy_register_work;
 	u32 flags;
@@ -508,19 +506,12 @@ static const struct hwmon_chip_info tja11xx_hwmon_chip_info = {
 static int tja11xx_hwmon_register(struct phy_device *phydev,
 				  struct tja11xx_priv *priv)
 {
-	struct device *dev = &phydev->mdio.dev;
-
-	priv->hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev));
-	if (IS_ERR(priv->hwmon_name))
-		return PTR_ERR(priv->hwmon_name);
-
-	priv->hwmon_dev =
-		devm_hwmon_device_register_with_info(dev, priv->hwmon_name,
-						     phydev,
-						     &tja11xx_hwmon_chip_info,
-						     NULL);
+	struct device *hdev, *dev = &phydev->mdio.dev;
 
-	return PTR_ERR_OR_ZERO(priv->hwmon_dev);
+	hdev = devm_hwmon_device_register_with_info(dev, NULL, phydev,
+						    &tja11xx_hwmon_chip_info,
+						    NULL);
+	return PTR_ERR_OR_ZERO(hdev);
 }
 
 static int tja11xx_parse_dt(struct phy_device *phydev)

From 507c13019c55899f0b97fa815fd91ce348586c5d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Mar 2025 20:45:42 +0100
Subject: [PATCH 2457/2753] net: phy: mxl-gpy: remove call to
 devm_hwmon_sanitize_name

Since c909e68f8127 ("hwmon: (core) Use device name as a fallback in
devm_hwmon_device_register_with_info") we can simply provide NULL
as name argument.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/mxl-gpy.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/phy/mxl-gpy.c b/drivers/net/phy/mxl-gpy.c
index a6cca8d432536..0c8dc16ee7bde 100644
--- a/drivers/net/phy/mxl-gpy.c
+++ b/drivers/net/phy/mxl-gpy.c
@@ -225,14 +225,8 @@ static int gpy_hwmon_register(struct phy_device *phydev)
 {
 	struct device *dev = &phydev->mdio.dev;
 	struct device *hwmon_dev;
-	char *hwmon_name;
 
-	hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev));
-	if (IS_ERR(hwmon_name))
-		return PTR_ERR(hwmon_name);
-
-	hwmon_dev = devm_hwmon_device_register_with_info(dev, hwmon_name,
-							 phydev,
+	hwmon_dev = devm_hwmon_device_register_with_info(dev, NULL, phydev,
 							 &gpy_hwmon_chip_info,
 							 NULL);
 

From b0bde1b7f0d384e7e71e3bc92945020ab1432e61 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 13 Mar 2025 20:46:22 +0100
Subject: [PATCH 2458/2753] net: phy: marvell-88q2xxx: remove call to
 devm_hwmon_sanitize_name

Since c909e68f8127 ("hwmon: (core) Use device name as a fallback in
devm_hwmon_device_register_with_info") we can simply provide NULL
as name argument.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/marvell-88q2xxx.c | 8 +-------
 1 file changed, 1 insertion(+), 7 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 15c0f8adc2f53..23e1f0521f549 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -765,16 +765,10 @@ static int mv88q2xxx_hwmon_probe(struct phy_device *phydev)
 	struct mv88q2xxx_priv *priv = phydev->priv;
 	struct device *dev = &phydev->mdio.dev;
 	struct device *hwmon;
-	char *hwmon_name;
 
 	priv->enable_temp = true;
-	hwmon_name = devm_hwmon_sanitize_name(dev, dev_name(dev));
-	if (IS_ERR(hwmon_name))
-		return PTR_ERR(hwmon_name);
 
-	hwmon = devm_hwmon_device_register_with_info(dev,
-						     hwmon_name,
-						     phydev,
+	hwmon = devm_hwmon_device_register_with_info(dev, NULL, phydev,
 						     &mv88q2xxx_hwmon_chip_info,
 						     NULL);
 

From b6886363c6612489406dbbd58508d4e5752d25a2 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:54 +0800
Subject: [PATCH 2459/2753] net: libwx: Add mailbox api for wangxun pf drivers

Implements the mailbox interfaces for wangxun pf drivers
ngbe and txgbe.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/Makefile  |   2 +-
 drivers/net/ethernet/wangxun/libwx/wx_mbx.c  | 176 +++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_mbx.h  |  32 ++++
 drivers/net/ethernet/wangxun/libwx/wx_type.h |   8 +
 4 files changed, 217 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_mbx.c
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_mbx.h

diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile
index e9f0f1f2309bf..cd1675ef32531 100644
--- a/drivers/net/ethernet/wangxun/libwx/Makefile
+++ b/drivers/net/ethernet/wangxun/libwx/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_LIBWX) += libwx.o
 
-libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o
+libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.c b/drivers/net/ethernet/wangxun/libwx/wx_mbx.c
new file mode 100644
index 0000000000000..73af5f11c3bdc
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.c
@@ -0,0 +1,176 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/pci.h>
+#include "wx_type.h"
+#include "wx_mbx.h"
+
+/**
+ *  wx_obtain_mbx_lock_pf - obtain mailbox lock
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+static int wx_obtain_mbx_lock_pf(struct wx *wx, u16 vf)
+{
+	int count = 5;
+	u32 mailbox;
+
+	while (count--) {
+		/* Take ownership of the buffer */
+		wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_PFU);
+
+		/* reserve mailbox for vf use */
+		mailbox = rd32(wx, WX_PXMAILBOX(vf));
+		if (mailbox & WX_PXMAILBOX_PFU)
+			return 0;
+		else if (count)
+			udelay(10);
+	}
+	wx_err(wx, "Failed to obtain mailbox lock for PF%d", vf);
+
+	return -EBUSY;
+}
+
+static int wx_check_for_bit_pf(struct wx *wx, u32 mask, int index)
+{
+	u32 mbvficr = rd32(wx, WX_MBVFICR(index));
+
+	if (!(mbvficr & mask))
+		return -EBUSY;
+	wr32(wx, WX_MBVFICR(index), mask);
+
+	return 0;
+}
+
+/**
+ *  wx_check_for_ack_pf - checks to see if the VF has acked
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 if the VF has set the status bit or else -EBUSY
+ **/
+int wx_check_for_ack_pf(struct wx *wx, u16 vf)
+{
+	u32 index = vf / 16, vf_bit = vf % 16;
+
+	return wx_check_for_bit_pf(wx,
+				   FIELD_PREP(WX_MBVFICR_VFACK_MASK,
+					      BIT(vf_bit)),
+				   index);
+}
+
+/**
+ *  wx_check_for_msg_pf - checks to see if the VF has sent mail
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 if the VF has got req bit or else -EBUSY
+ **/
+int wx_check_for_msg_pf(struct wx *wx, u16 vf)
+{
+	u32 index = vf / 16, vf_bit = vf % 16;
+
+	return wx_check_for_bit_pf(wx,
+				   FIELD_PREP(WX_MBVFICR_VFREQ_MASK,
+					      BIT(vf_bit)),
+				   index);
+}
+
+/**
+ *  wx_write_mbx_pf - Places a message in the mailbox
+ *  @wx: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EINVAL/-EBUSY on failure
+ **/
+int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf)
+{
+	struct wx_mbx_info *mbx = &wx->mbx;
+	int ret, i;
+
+	/* mbx->size is up to 15 */
+	if (size > mbx->size) {
+		wx_err(wx, "Invalid mailbox message size %d", size);
+		return -EINVAL;
+	}
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret = wx_obtain_mbx_lock_pf(wx, vf);
+	if (ret)
+		return ret;
+
+	/* flush msg and acks as we are overwriting the message buffer */
+	wx_check_for_msg_pf(wx, vf);
+	wx_check_for_ack_pf(wx, vf);
+
+	/* copy the caller specified message to the mailbox memory buffer */
+	for (i = 0; i < size; i++)
+		wr32a(wx, WX_PXMBMEM(vf), i, msg[i]);
+
+	/* Interrupt VF to tell it a message has been sent and release buffer */
+	/* set mirrored mailbox flags */
+	wr32a(wx, WX_PXMBMEM(vf), WX_VXMAILBOX_SIZE, WX_PXMAILBOX_STS);
+	wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_STS);
+
+	return 0;
+}
+
+/**
+ *  wx_read_mbx_pf - Read a message from the mailbox
+ *  @wx: pointer to the HW structure
+ *  @msg: The message buffer
+ *  @size: Length of buffer
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+int wx_read_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf)
+{
+	struct wx_mbx_info *mbx = &wx->mbx;
+	int ret;
+	u16 i;
+
+	/* limit read to size of mailbox and mbx->size is up to 15 */
+	if (size > mbx->size)
+		size = mbx->size;
+
+	/* lock the mailbox to prevent pf/vf race condition */
+	ret = wx_obtain_mbx_lock_pf(wx, vf);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < size; i++)
+		msg[i] = rd32a(wx, WX_PXMBMEM(vf), i);
+
+	/* Acknowledge the message and release buffer */
+	/* set mirrored mailbox flags */
+	wr32a(wx, WX_PXMBMEM(vf), WX_VXMAILBOX_SIZE, WX_PXMAILBOX_ACK);
+	wr32(wx, WX_PXMAILBOX(vf), WX_PXMAILBOX_ACK);
+
+	return 0;
+}
+
+/**
+ *  wx_check_for_rst_pf - checks to see if the VF has reset
+ *  @wx: pointer to the HW structure
+ *  @vf: the VF index
+ *
+ *  Return: return 0 on success and -EBUSY on failure
+ **/
+int wx_check_for_rst_pf(struct wx *wx, u16 vf)
+{
+	u32 reg_offset = WX_VF_REG_OFFSET(vf);
+	u32 vf_shift = WX_VF_IND_SHIFT(vf);
+	u32 vflre = 0;
+
+	vflre = rd32(wx, WX_VFLRE(reg_offset));
+	if (!(vflre & BIT(vf_shift)))
+		return -EBUSY;
+	wr32(wx, WX_VFLREC(reg_offset), BIT(vf_shift));
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
new file mode 100644
index 0000000000000..c09b25f3e43d9
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+#ifndef _WX_MBX_H_
+#define _WX_MBX_H_
+
+#define WX_VXMAILBOX_SIZE    15
+
+/* PF Registers */
+#define WX_PXMAILBOX(i)      (0x600 + (4 * (i))) /* i=[0,63] */
+#define WX_PXMAILBOX_STS     BIT(0) /* Initiate message send to VF */
+#define WX_PXMAILBOX_ACK     BIT(1) /* Ack message recv'd from VF */
+#define WX_PXMAILBOX_PFU     BIT(3) /* PF owns the mailbox buffer */
+
+#define WX_PXMBMEM(i)        (0x5000 + (64 * (i))) /* i=[0,63] */
+
+#define WX_VFLRE(i)          (0x4A0 + (4 * (i))) /* i=[0,1] */
+#define WX_VFLREC(i)         (0x4A8 + (4 * (i))) /* i=[0,1] */
+
+/* SR-IOV specific macros */
+#define WX_MBVFICR(i)         (0x480 + (4 * (i))) /* i=[0,3] */
+#define WX_MBVFICR_VFREQ_MASK GENMASK(15, 0)
+#define WX_MBVFICR_VFACK_MASK GENMASK(31, 16)
+
+#define WX_VT_MSGINFO_MASK    GENMASK(23, 16)
+
+int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
+int wx_read_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
+int wx_check_for_rst_pf(struct wx *wx, u16 mbx_id);
+int wx_check_for_msg_pf(struct wx *wx, u16 mbx_id);
+int wx_check_for_ack_pf(struct wx *wx, u16 mbx_id);
+
+#endif /* _WX_MBX_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 5b230ecbbabb5..18287b0ee0401 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -22,6 +22,9 @@
 #define WX_PCI_LINK_STATUS                      0xB2
 
 /**************** Global Registers ****************************/
+#define WX_VF_REG_OFFSET(_v)         FIELD_GET(GENMASK(15, 5), (_v))
+#define WX_VF_IND_SHIFT(_v)          FIELD_GET(GENMASK(4, 0), (_v))
+
 /* chip control Registers */
 #define WX_MIS_PWR                   0x10000
 #define WX_MIS_RST                   0x1000C
@@ -779,6 +782,10 @@ struct wx_bus_info {
 	u16 device;
 };
 
+struct wx_mbx_info {
+	u16 size;
+};
+
 struct wx_thermal_sensor_data {
 	s16 temp;
 	s16 alarm_thresh;
@@ -1129,6 +1136,7 @@ struct wx {
 	struct pci_dev *pdev;
 	struct net_device *netdev;
 	struct wx_bus_info bus;
+	struct wx_mbx_info mbx;
 	struct wx_mac_info mac;
 	enum em_mac_type mac_type;
 	enum sp_media_type media_type;

From 04fef10480df98fae30cc866d79966be6fb06ec5 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:55 +0800
Subject: [PATCH 2460/2753] net: libwx: Add sriov api for wangxun nics

Implement sriov_configure interface for wangxun nics in libwx.
Enable VT mode and initialize vf control structure, when sriov
is enabled. Do not be allowed to disable sriov when vfs are
assigned.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/Makefile   |   2 +-
 drivers/net/ethernet/wangxun/libwx/wx_mbx.h   |   4 +
 drivers/net/ethernet/wangxun/libwx/wx_sriov.c | 201 ++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.h |  10 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  31 +++
 5 files changed, 247 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_sriov.c
 create mode 100644 drivers/net/ethernet/wangxun/libwx/wx_sriov.h

diff --git a/drivers/net/ethernet/wangxun/libwx/Makefile b/drivers/net/ethernet/wangxun/libwx/Makefile
index cd1675ef32531..9b78b604a94e4 100644
--- a/drivers/net/ethernet/wangxun/libwx/Makefile
+++ b/drivers/net/ethernet/wangxun/libwx/Makefile
@@ -4,4 +4,4 @@
 
 obj-$(CONFIG_LIBWX) += libwx.o
 
-libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o
+libwx-objs := wx_hw.o wx_lib.o wx_ethtool.o wx_ptp.o wx_mbx.o wx_sriov.o
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
index c09b25f3e43d9..172b46b9c14dc 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
@@ -23,6 +23,10 @@
 
 #define WX_VT_MSGINFO_MASK    GENMASK(23, 16)
 
+enum wxvf_xcast_modes {
+	WXVF_XCAST_MODE_NONE = 0,
+};
+
 int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
 int wx_read_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
 int wx_check_for_rst_pf(struct wx *wx, u16 mbx_id);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
new file mode 100644
index 0000000000000..2392df341ad1f
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -0,0 +1,201 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#include <linux/etherdevice.h>
+#include <linux/pci.h>
+
+#include "wx_type.h"
+#include "wx_mbx.h"
+#include "wx_sriov.h"
+
+static void wx_vf_configuration(struct pci_dev *pdev, int event_mask)
+{
+	unsigned int vfn = (event_mask & GENMASK(5, 0));
+	struct wx *wx = pci_get_drvdata(pdev);
+
+	bool enable = ((event_mask & BIT(31)) != 0);
+
+	if (enable)
+		eth_zero_addr(wx->vfinfo[vfn].vf_mac_addr);
+}
+
+static int wx_alloc_vf_macvlans(struct wx *wx, u8 num_vfs)
+{
+	struct vf_macvlans *mv_list;
+	int num_vf_macvlans, i;
+
+	/* Initialize list of VF macvlans */
+	INIT_LIST_HEAD(&wx->vf_mvs.mvlist);
+
+	num_vf_macvlans = wx->mac.num_rar_entries -
+			  (WX_MAX_PF_MACVLANS + 1 + num_vfs);
+	if (!num_vf_macvlans)
+		return -EINVAL;
+
+	mv_list = kcalloc(num_vf_macvlans, sizeof(struct vf_macvlans),
+			  GFP_KERNEL);
+	if (!mv_list)
+		return -ENOMEM;
+
+	for (i = 0; i < num_vf_macvlans; i++) {
+		mv_list[i].vf = -1;
+		mv_list[i].free = true;
+		list_add(&mv_list[i].mvlist, &wx->vf_mvs.mvlist);
+	}
+	wx->mv_list = mv_list;
+
+	return 0;
+}
+
+static void wx_sriov_clear_data(struct wx *wx)
+{
+	/* set num VFs to 0 to prevent access to vfinfo */
+	wx->num_vfs = 0;
+
+	/* free VF control structures */
+	kfree(wx->vfinfo);
+	wx->vfinfo = NULL;
+
+	/* free macvlan list */
+	kfree(wx->mv_list);
+	wx->mv_list = NULL;
+
+	/* set default pool back to 0 */
+	wr32m(wx, WX_PSR_VM_CTL, WX_PSR_VM_CTL_POOL_MASK, 0);
+	wx->ring_feature[RING_F_VMDQ].offset = 0;
+
+	clear_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
+	/* Disable VMDq flag so device will be set in NM mode */
+	if (wx->ring_feature[RING_F_VMDQ].limit == 1)
+		clear_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+}
+
+static int __wx_enable_sriov(struct wx *wx, u8 num_vfs)
+{
+	int i, ret = 0;
+	u32 value = 0;
+
+	set_bit(WX_FLAG_SRIOV_ENABLED, wx->flags);
+	wx_err(wx, "SR-IOV enabled with %d VFs\n", num_vfs);
+
+	/* Enable VMDq flag so device will be set in VM mode */
+	set_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+	if (!wx->ring_feature[RING_F_VMDQ].limit)
+		wx->ring_feature[RING_F_VMDQ].limit = 1;
+	wx->ring_feature[RING_F_VMDQ].offset = num_vfs;
+
+	wx->vfinfo = kcalloc(num_vfs, sizeof(struct vf_data_storage),
+			     GFP_KERNEL);
+	if (!wx->vfinfo)
+		return -ENOMEM;
+
+	ret = wx_alloc_vf_macvlans(wx, num_vfs);
+	if (ret)
+		return ret;
+
+	/* Initialize default switching mode VEB */
+	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_SW_EN, WX_PSR_CTL_SW_EN);
+
+	for (i = 0; i < num_vfs; i++) {
+		/* enable spoof checking for all VFs */
+		wx->vfinfo[i].spoofchk_enabled = true;
+		wx->vfinfo[i].link_enable = true;
+		/* untrust all VFs */
+		wx->vfinfo[i].trusted = false;
+		/* set the default xcast mode */
+		wx->vfinfo[i].xcast_mode = WXVF_XCAST_MODE_NONE;
+	}
+
+	if (wx->mac.type == wx_mac_sp) {
+		if (num_vfs < 32)
+			value = WX_CFG_PORT_CTL_NUM_VT_32;
+		else
+			value = WX_CFG_PORT_CTL_NUM_VT_64;
+	} else {
+		value = WX_CFG_PORT_CTL_NUM_VT_8;
+	}
+	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_NUM_VT_MASK,
+	      value);
+
+	return ret;
+}
+
+static void wx_sriov_reinit(struct wx *wx)
+{
+	rtnl_lock();
+	wx->setup_tc(wx->netdev, netdev_get_num_tc(wx->netdev));
+	rtnl_unlock();
+}
+
+void wx_disable_sriov(struct wx *wx)
+{
+	if (!pci_vfs_assigned(wx->pdev))
+		pci_disable_sriov(wx->pdev);
+	else
+		wx_err(wx, "Unloading driver while VFs are assigned.\n");
+
+	/* clear flags and free allloced data */
+	wx_sriov_clear_data(wx);
+}
+EXPORT_SYMBOL(wx_disable_sriov);
+
+static int wx_pci_sriov_enable(struct pci_dev *dev,
+			       int num_vfs)
+{
+	struct wx *wx = pci_get_drvdata(dev);
+	int err = 0, i;
+
+	err = __wx_enable_sriov(wx, num_vfs);
+	if (err)
+		return err;
+
+	wx->num_vfs = num_vfs;
+	for (i = 0; i < wx->num_vfs; i++)
+		wx_vf_configuration(dev, (i | BIT(31)));
+
+	/* reset before enabling SRIOV to avoid mailbox issues */
+	wx_sriov_reinit(wx);
+
+	err = pci_enable_sriov(dev, num_vfs);
+	if (err) {
+		wx_err(wx, "Failed to enable PCI sriov: %d\n", err);
+		goto err_out;
+	}
+
+	return num_vfs;
+err_out:
+	wx_sriov_clear_data(wx);
+	return err;
+}
+
+static void wx_pci_sriov_disable(struct pci_dev *dev)
+{
+	struct wx *wx = pci_get_drvdata(dev);
+
+	wx_disable_sriov(wx);
+	wx_sriov_reinit(wx);
+}
+
+int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
+{
+	struct wx *wx = pci_get_drvdata(pdev);
+	int err;
+
+	if (!num_vfs) {
+		if (!pci_vfs_assigned(pdev)) {
+			wx_pci_sriov_disable(pdev);
+			return 0;
+		}
+
+		wx_err(wx, "can't free VFs because some are assigned to VMs.\n");
+		return -EBUSY;
+	}
+
+	err = wx_pci_sriov_enable(pdev, num_vfs);
+	if (err)
+		return err;
+
+	return num_vfs;
+}
+EXPORT_SYMBOL(wx_pci_sriov_configure);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
new file mode 100644
index 0000000000000..a16877f893896
--- /dev/null
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2015 - 2025 Beijing WangXun Technology Co., Ltd. */
+
+#ifndef _WX_SRIOV_H_
+#define _WX_SRIOV_H_
+
+void wx_disable_sriov(struct wx *wx);
+int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs);
+
+#endif /* _WX_SRIOV_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 18287b0ee0401..26776dee64903 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -20,6 +20,7 @@
 /* MSI-X capability fields masks */
 #define WX_PCIE_MSIX_TBL_SZ_MASK                0x7FF
 #define WX_PCI_LINK_STATUS                      0xB2
+#define WX_MAX_PF_MACVLANS                      15
 
 /**************** Global Registers ****************************/
 #define WX_VF_REG_OFFSET(_v)         FIELD_GET(GENMASK(15, 5), (_v))
@@ -93,6 +94,9 @@
 #define WX_CFG_TAG_TPID(_i)          (0x14430 + ((_i) * 4))
 #define WX_CFG_PORT_CTL_NUM_VT_MASK  GENMASK(13, 12) /* number of TVs */
 
+#define WX_CFG_PORT_CTL_NUM_VT_8     FIELD_PREP(GENMASK(13, 12), 1)
+#define WX_CFG_PORT_CTL_NUM_VT_32    FIELD_PREP(GENMASK(13, 12), 2)
+#define WX_CFG_PORT_CTL_NUM_VT_64    FIELD_PREP(GENMASK(13, 12), 3)
 
 /* GPIO Registers */
 #define WX_GPIO_DR                   0x14800
@@ -168,6 +172,7 @@
 /******************************* PSR Registers *******************************/
 /* psr control */
 #define WX_PSR_CTL                   0x15000
+#define WX_PSR_VM_CTL                0x151B0
 /* Header split receive */
 #define WX_PSR_CTL_SW_EN             BIT(18)
 #define WX_PSR_CTL_RSC_ACK           BIT(17)
@@ -205,6 +210,7 @@
 /* mcasst/ucast overflow tbl */
 #define WX_PSR_MC_TBL(_i)            (0x15200  + ((_i) * 4))
 #define WX_PSR_UC_TBL(_i)            (0x15400 + ((_i) * 4))
+#define WX_PSR_VM_CTL_POOL_MASK      GENMASK(12, 7)
 
 /* VM L2 contorl */
 #define WX_PSR_VM_L2CTL(_i)          (0x15600 + ((_i) * 4))
@@ -1059,6 +1065,7 @@ struct wx_ring_feature {
 
 enum wx_ring_f_enum {
 	RING_F_NONE = 0,
+	RING_F_VMDQ,
 	RING_F_RSS,
 	RING_F_FDIR,
 	RING_F_ARRAY_SIZE  /* must be last in enum set */
@@ -1114,8 +1121,27 @@ enum wx_state {
 	WX_STATE_NBITS		/* must be last */
 };
 
+struct vf_data_storage {
+	struct pci_dev *vfdev;
+	unsigned char vf_mac_addr[ETH_ALEN];
+	bool spoofchk_enabled;
+	bool link_enable;
+	bool trusted;
+	int xcast_mode;
+};
+
+struct vf_macvlans {
+	struct list_head mvlist;
+	int vf;
+	bool free;
+	bool is_macvlan;
+	u8 vf_macvlan[ETH_ALEN];
+};
+
 enum wx_pf_flags {
 	WX_FLAG_SWFW_RING,
+	WX_FLAG_VMDQ_ENABLED,
+	WX_FLAG_SRIOV_ENABLED,
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
 	WX_FLAG_FDIR_PERFECT,
@@ -1220,10 +1246,15 @@ struct wx {
 	u64 hw_csum_rx_good;
 	u64 hw_csum_rx_error;
 	u64 alloc_rx_buff_failed;
+	unsigned int num_vfs;
+	struct vf_data_storage *vfinfo;
+	struct vf_macvlans vf_mvs;
+	struct vf_macvlans *mv_list;
 
 	u32 atr_sample_rate;
 	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);
 	void (*configure_fdir)(struct wx *wx);
+	int (*setup_tc)(struct net_device *netdev, u8 tc);
 	void (*do_reset)(struct net_device *netdev);
 	int (*ptp_setup_sdp)(struct wx *wx);
 

From 56e81ea2077f40ad32bcf93b0e02bdbfe4369df6 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:56 +0800
Subject: [PATCH 2461/2753] net: libwx: Redesign flow when sriov is enabled

Reallocate queue and int resources when sriov is enabled.
Redefine macro VMDQ to make it work in VT mode.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c   | 294 ++++++++++++++++++-
 drivers/net/ethernet/wangxun/libwx/wx_lib.c  | 128 +++++++-
 drivers/net/ethernet/wangxun/libwx/wx_type.h |  34 ++-
 3 files changed, 439 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index aed45abafb1b7..1953365827a07 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -10,6 +10,7 @@
 
 #include "wx_type.h"
 #include "wx_lib.h"
+#include "wx_sriov.h"
 #include "wx_hw.h"
 
 static int wx_phy_read_reg_mdi(struct mii_bus *bus, int phy_addr, int devnum, int regnum)
@@ -964,11 +965,28 @@ static void wx_sync_mac_table(struct wx *wx)
 	}
 }
 
+static void wx_full_sync_mac_table(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->mac.num_rar_entries; i++) {
+		if (wx->mac_table[i].state & WX_MAC_STATE_IN_USE) {
+			wx_set_rar(wx, i,
+				   wx->mac_table[i].addr,
+				   wx->mac_table[i].pools,
+				   WX_PSR_MAC_SWC_AD_H_AV);
+		} else {
+			wx_clear_rar(wx, i);
+		}
+		wx->mac_table[i].state &= ~(WX_MAC_STATE_MODIFIED);
+	}
+}
+
 /* this function destroys the first RAR entry */
 void wx_mac_set_default_filter(struct wx *wx, u8 *addr)
 {
 	memcpy(&wx->mac_table[0].addr, addr, ETH_ALEN);
-	wx->mac_table[0].pools = 1ULL;
+	wx->mac_table[0].pools = BIT(VMDQ_P(0));
 	wx->mac_table[0].state = (WX_MAC_STATE_DEFAULT | WX_MAC_STATE_IN_USE);
 	wx_set_rar(wx, 0, wx->mac_table[0].addr,
 		   wx->mac_table[0].pools,
@@ -1206,6 +1224,35 @@ static void wx_update_mc_addr_list(struct wx *wx, struct net_device *netdev)
 	wx_dbg(wx, "Update mc addr list Complete\n");
 }
 
+static void wx_restore_vf_multicasts(struct wx *wx)
+{
+	u32 i, j, vector_bit, vector_reg;
+	struct vf_data_storage *vfinfo;
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(i));
+
+		vfinfo = &wx->vfinfo[i];
+		for (j = 0; j < vfinfo->num_vf_mc_hashes; j++) {
+			wx->addr_ctrl.mta_in_use++;
+			vector_reg = WX_PSR_MC_TBL_REG(vfinfo->vf_mc_hashes[j]);
+			vector_bit = WX_PSR_MC_TBL_BIT(vfinfo->vf_mc_hashes[j]);
+			wr32m(wx, WX_PSR_MC_TBL(vector_reg),
+			      BIT(vector_bit), BIT(vector_bit));
+			/* errata 5: maintain a copy of the reg table conf */
+			wx->mac.mta_shadow[vector_reg] |= BIT(vector_bit);
+		}
+		if (vfinfo->num_vf_mc_hashes)
+			vmolr |= WX_PSR_VM_L2CTL_ROMPE;
+		else
+			vmolr &= ~WX_PSR_VM_L2CTL_ROMPE;
+		wr32(wx, WX_PSR_VM_L2CTL(i), vmolr);
+	}
+
+	/* Restore any VF macvlans */
+	wx_full_sync_mac_table(wx);
+}
+
 /**
  * wx_write_mc_addr_list - write multicast addresses to MTA
  * @netdev: network interface device structure
@@ -1223,6 +1270,9 @@ static int wx_write_mc_addr_list(struct net_device *netdev)
 
 	wx_update_mc_addr_list(wx, netdev);
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		wx_restore_vf_multicasts(wx);
+
 	return netdev_mc_count(netdev);
 }
 
@@ -1243,7 +1293,7 @@ int wx_set_mac(struct net_device *netdev, void *p)
 	if (retval)
 		return retval;
 
-	wx_del_mac_filter(wx, wx->mac.addr, 0);
+	wx_del_mac_filter(wx, wx->mac.addr, VMDQ_P(0));
 	eth_hw_addr_set(netdev, addr->sa_data);
 	memcpy(wx->mac.addr, addr->sa_data, netdev->addr_len);
 
@@ -1345,6 +1395,10 @@ static int wx_hpbthresh(struct wx *wx)
 	/* Calculate delay value for device */
 	dv_id = WX_DV(link, tc);
 
+	/* Loopback switch introduces additional latency */
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		dv_id += WX_B2BT(tc);
+
 	/* Delay value is calculated in bit times convert to KB */
 	kb = WX_BT2KB(dv_id);
 	rx_pba = rd32(wx, WX_RDB_PB_SZ(0)) >> WX_RDB_PB_SZ_SHIFT;
@@ -1400,12 +1454,107 @@ static void wx_pbthresh_setup(struct wx *wx)
 		wx->fc.low_water = 0;
 }
 
+static void wx_set_ethertype_anti_spoofing(struct wx *wx, bool enable, int vf)
+{
+	u32 pfvfspoof, reg_offset, vf_shift;
+
+	vf_shift = WX_VF_IND_SHIFT(vf);
+	reg_offset = WX_VF_REG_OFFSET(vf);
+
+	pfvfspoof = rd32(wx, WX_TDM_ETYPE_AS(reg_offset));
+	if (enable)
+		pfvfspoof |= BIT(vf_shift);
+	else
+		pfvfspoof &= ~BIT(vf_shift);
+	wr32(wx, WX_TDM_ETYPE_AS(reg_offset), pfvfspoof);
+}
+
+static int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	struct wx *wx = netdev_priv(netdev);
+	u32 regval;
+
+	if (vf >= wx->num_vfs)
+		return -EINVAL;
+
+	wx->vfinfo[vf].spoofchk_enabled = setting;
+
+	regval = (setting << vf_bit);
+	wr32m(wx, WX_TDM_MAC_AS(index), regval | BIT(vf_bit), regval);
+
+	if (wx->vfinfo[vf].vlan_count)
+		wr32m(wx, WX_TDM_VLAN_AS(index), regval | BIT(vf_bit), regval);
+
+	return 0;
+}
+
+static void wx_configure_virtualization(struct wx *wx)
+{
+	u16 pool = wx->num_rx_pools;
+	u32 reg_offset, vf_shift;
+	u32 i;
+
+	if (!test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+		return;
+
+	wr32m(wx, WX_PSR_VM_CTL,
+	      WX_PSR_VM_CTL_POOL_MASK | WX_PSR_VM_CTL_REPLEN,
+	      FIELD_PREP(WX_PSR_VM_CTL_POOL_MASK, VMDQ_P(0)) |
+	      WX_PSR_VM_CTL_REPLEN);
+	while (pool--)
+		wr32m(wx, WX_PSR_VM_L2CTL(pool),
+		      WX_PSR_VM_L2CTL_AUPE, WX_PSR_VM_L2CTL_AUPE);
+
+	if (wx->mac.type == wx_mac_sp) {
+		vf_shift = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_offset = WX_VF_REG_OFFSET(VMDQ_P(0));
+
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_RDM_VF_RE(reg_offset ^ 1), reg_offset - 1);
+		wr32(wx, WX_TDM_VF_TE(reg_offset), GENMASK(31, vf_shift));
+		wr32(wx, WX_TDM_VF_TE(reg_offset ^ 1), reg_offset - 1);
+	} else {
+		vf_shift = BIT(VMDQ_P(0));
+		/* Enable only the PF pools for Tx/Rx */
+		wr32(wx, WX_RDM_VF_RE(0), vf_shift);
+		wr32(wx, WX_TDM_VF_TE(0), vf_shift);
+	}
+
+	/* clear VLAN promisc flag so VFTA will be updated if necessary */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+
+	for (i = 0; i < wx->num_vfs; i++) {
+		if (!wx->vfinfo[i].spoofchk_enabled)
+			wx_set_vf_spoofchk(wx->netdev, i, false);
+		/* enable ethertype anti spoofing if hw supports it */
+		wx_set_ethertype_anti_spoofing(wx, true, i);
+	}
+}
+
 static void wx_configure_port(struct wx *wx)
 {
 	u32 value, i;
 
-	value = WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
+	if (wx->mac.type == wx_mac_em) {
+		value = (wx->num_vfs == 0) ?
+			WX_CFG_PORT_CTL_NUM_VT_NONE :
+			WX_CFG_PORT_CTL_NUM_VT_8;
+	} else {
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+			if (wx->ring_feature[RING_F_RSS].indices == 4)
+				value = WX_CFG_PORT_CTL_NUM_VT_32;
+			else
+				value = WX_CFG_PORT_CTL_NUM_VT_64;
+		} else {
+			value = 0;
+		}
+	}
+
+	value |= WX_CFG_PORT_CTL_D_VLAN | WX_CFG_PORT_CTL_QINQ;
 	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_NUM_VT_MASK |
 	      WX_CFG_PORT_CTL_D_VLAN |
 	      WX_CFG_PORT_CTL_QINQ,
 	      value);
@@ -1466,6 +1615,83 @@ static void wx_vlan_strip_control(struct wx *wx, bool enable)
 	}
 }
 
+static void wx_vlan_promisc_enable(struct wx *wx)
+{
+	u32 vlnctrl, i, vind, bits, reg_idx;
+
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags)) {
+		/* we need to keep the VLAN filter on in SRIOV */
+		vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	} else {
+		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+		return;
+	}
+	/* We are already in VLAN promisc, nothing to do */
+	if (test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	set_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	/* Add PF to all active pools */
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits |= BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* Set all bits in the VLAN filter table array */
+	for (i = 0; i < wx->mac.vft_size; i++)
+		wr32(wx, WX_PSR_VLAN_TBL(i), U32_MAX);
+}
+
+static void wx_scrub_vfta(struct wx *wx)
+{
+	u32 i, vid, bits, vfta, vind, vlvf, reg_idx;
+
+	for (i = WX_PSR_VLAN_SWC_ENTRIES; --i;) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, i);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC_IDX);
+		/* pull VLAN ID from VLVF */
+		vid = vlvf & ~WX_PSR_VLAN_SWC_VIEN;
+		if (vlvf & WX_PSR_VLAN_SWC_VIEN) {
+			/* if PF is part of this then continue */
+			if (test_bit(vid, wx->active_vlans))
+				continue;
+		}
+		/* remove PF from the pool */
+		vind = WX_VF_IND_SHIFT(VMDQ_P(0));
+		reg_idx = WX_VF_REG_OFFSET(VMDQ_P(0));
+		bits = rd32(wx, WX_PSR_VLAN_SWC_VM(reg_idx));
+		bits &= ~BIT(vind);
+		wr32(wx, WX_PSR_VLAN_SWC_VM(reg_idx), bits);
+	}
+	/* extract values from vft_shadow and write back to VFTA */
+	for (i = 0; i < wx->mac.vft_size; i++) {
+		vfta = wx->mac.vft_shadow[i];
+		wr32(wx, WX_PSR_VLAN_TBL(i), vfta);
+	}
+}
+
+static void wx_vlan_promisc_disable(struct wx *wx)
+{
+	u32 vlnctrl;
+
+	/* configure vlan filtering */
+	vlnctrl = rd32(wx, WX_PSR_VLAN_CTL);
+	vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
+	/* We are not in VLAN promisc, nothing to do */
+	if (!test_bit(WX_FLAG_VLAN_PROMISC, wx->flags))
+		return;
+	/* Set flag so we don't redo unnecessary work */
+	clear_bit(WX_FLAG_VLAN_PROMISC, wx->flags);
+	wx_scrub_vfta(wx);
+}
+
 void wx_set_rx_mode(struct net_device *netdev)
 {
 	struct wx *wx = netdev_priv(netdev);
@@ -1478,7 +1704,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	/* Check for Promiscuous and All Multicast modes */
 	fctrl = rd32(wx, WX_PSR_CTL);
 	fctrl &= ~(WX_PSR_CTL_UPE | WX_PSR_CTL_MPE);
-	vmolr = rd32(wx, WX_PSR_VM_L2CTL(0));
+	vmolr = rd32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)));
 	vmolr &= ~(WX_PSR_VM_L2CTL_UPE |
 		   WX_PSR_VM_L2CTL_MPE |
 		   WX_PSR_VM_L2CTL_ROPE |
@@ -1499,7 +1725,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 		fctrl |= WX_PSR_CTL_UPE | WX_PSR_CTL_MPE;
 		/* pf don't want packets routing to vf, so clear UPE */
 		vmolr |= WX_PSR_VM_L2CTL_MPE;
-		vlnctrl &= ~WX_PSR_VLAN_CTL_VFE;
+		if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags) &&
+		    test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags))
+			vlnctrl |= WX_PSR_VLAN_CTL_VFE;
+		features &= ~NETIF_F_HW_VLAN_CTAG_FILTER;
 	}
 
 	if (netdev->flags & IFF_ALLMULTI) {
@@ -1522,7 +1751,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 	 * sufficient space to store all the addresses then enable
 	 * unicast promiscuous mode
 	 */
-	count = wx_write_uc_addr_list(netdev, 0);
+	count = wx_write_uc_addr_list(netdev, VMDQ_P(0));
 	if (count < 0) {
 		vmolr &= ~WX_PSR_VM_L2CTL_ROPE;
 		vmolr |= WX_PSR_VM_L2CTL_UPE;
@@ -1540,7 +1769,7 @@ void wx_set_rx_mode(struct net_device *netdev)
 
 	wr32(wx, WX_PSR_VLAN_CTL, vlnctrl);
 	wr32(wx, WX_PSR_CTL, fctrl);
-	wr32(wx, WX_PSR_VM_L2CTL(0), vmolr);
+	wr32(wx, WX_PSR_VM_L2CTL(VMDQ_P(0)), vmolr);
 
 	if ((features & NETIF_F_HW_VLAN_CTAG_RX) &&
 	    (features & NETIF_F_HW_VLAN_STAG_RX))
@@ -1548,6 +1777,10 @@ void wx_set_rx_mode(struct net_device *netdev)
 	else
 		wx_vlan_strip_control(wx, false);
 
+	if (features & NETIF_F_HW_VLAN_CTAG_FILTER)
+		wx_vlan_promisc_disable(wx);
+	else
+		wx_vlan_promisc_enable(wx);
 }
 EXPORT_SYMBOL(wx_set_rx_mode);
 
@@ -1797,6 +2030,13 @@ static void wx_setup_reta(struct wx *wx)
 	u32 random_key_size = WX_RSS_KEY_SIZE / 4;
 	u32 i, j;
 
+	if (test_bit(WX_FLAG_SRIOV_ENABLED, wx->flags)) {
+		if (wx->mac.type == wx_mac_sp)
+			rss_i = rss_i < 4 ? 4 : rss_i;
+		else if (wx->mac.type == wx_mac_em)
+			rss_i = 1;
+	}
+
 	/* Fill out hash function seeds */
 	for (i = 0; i < random_key_size; i++)
 		wr32(wx, WX_RDB_RSSRK(i), wx->rss_key[i]);
@@ -1814,10 +2054,40 @@ static void wx_setup_reta(struct wx *wx)
 	wx_store_reta(wx);
 }
 
+static void wx_setup_psrtype(struct wx *wx)
+{
+	int rss_i = wx->ring_feature[RING_F_RSS].indices;
+	u32 psrtype;
+	int pool;
+
+	psrtype = WX_RDB_PL_CFG_L4HDR |
+		  WX_RDB_PL_CFG_L3HDR |
+		  WX_RDB_PL_CFG_L2HDR |
+		  WX_RDB_PL_CFG_TUN_OUTL2HDR |
+		  WX_RDB_PL_CFG_TUN_TUNHDR;
+
+	if (wx->mac.type == wx_mac_sp) {
+		if (rss_i > 3)
+			psrtype |= FIELD_PREP(GENMASK(31, 29), 2);
+		else if (rss_i > 1)
+			psrtype |= FIELD_PREP(GENMASK(31, 29), 1);
+
+		for_each_set_bit(pool, &wx->fwd_bitmask, 32)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	} else {
+		for_each_set_bit(pool, &wx->fwd_bitmask, 8)
+			wr32(wx, WX_RDB_PL_CFG(VMDQ_P(pool)), psrtype);
+	}
+}
+
 static void wx_setup_mrqc(struct wx *wx)
 {
 	u32 rss_field = 0;
 
+	/* VT, and RSS do not coexist at the same time */
+	if (test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return;
+
 	/* Disable indicating checksum in descriptor, enables RSS hash */
 	wr32m(wx, WX_PSR_CTL, WX_PSR_CTL_PCSD, WX_PSR_CTL_PCSD);
 
@@ -1847,16 +2117,11 @@ static void wx_setup_mrqc(struct wx *wx)
  **/
 void wx_configure_rx(struct wx *wx)
 {
-	u32 psrtype, i;
 	int ret;
+	u32 i;
 
 	wx_disable_rx(wx);
-
-	psrtype = WX_RDB_PL_CFG_L4HDR |
-		  WX_RDB_PL_CFG_L3HDR |
-		  WX_RDB_PL_CFG_L2HDR |
-		  WX_RDB_PL_CFG_TUN_TUNHDR;
-	wr32(wx, WX_RDB_PL_CFG(0), psrtype);
+	wx_setup_psrtype(wx);
 
 	/* enable hw crc stripping */
 	wr32m(wx, WX_RSC_CTL, WX_RSC_CTL_CRC_STRIP, WX_RSC_CTL_CRC_STRIP);
@@ -1904,6 +2169,7 @@ void wx_configure(struct wx *wx)
 {
 	wx_set_rxpba(wx);
 	wx_pbthresh_setup(wx);
+	wx_configure_virtualization(wx);
 	wx_configure_port(wx);
 
 	wx_set_rx_mode(wx->netdev);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_lib.c b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
index 895f3c96a678f..60daae94acaac 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_lib.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_lib.c
@@ -1603,6 +1603,65 @@ void wx_napi_disable_all(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_napi_disable_all);
 
+static bool wx_set_vmdq_queues(struct wx *wx)
+{
+	u16 vmdq_i = wx->ring_feature[RING_F_VMDQ].limit;
+	u16 rss_i = wx->ring_feature[RING_F_RSS].limit;
+	u16 rss_m = WX_RSS_DISABLED_MASK;
+	u16 vmdq_m = 0;
+
+	/* only proceed if VMDq is enabled */
+	if (!test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return false;
+	/* Add starting offset to total pool count */
+	vmdq_i += wx->ring_feature[RING_F_VMDQ].offset;
+
+	if (wx->mac.type == wx_mac_sp) {
+		/* double check we are limited to maximum pools */
+		vmdq_i = min_t(u16, 64, vmdq_i);
+
+		/* 64 pool mode with 2 queues per pool, or
+		 * 16/32/64 pool mode with 1 queue per pool
+		 */
+		if (vmdq_i > 32 || rss_i < 4) {
+			vmdq_m = WX_VMDQ_2Q_MASK;
+			rss_m = WX_RSS_2Q_MASK;
+			rss_i = min_t(u16, rss_i, 2);
+		/* 32 pool mode with 4 queues per pool */
+		} else {
+			vmdq_m = WX_VMDQ_4Q_MASK;
+			rss_m = WX_RSS_4Q_MASK;
+			rss_i = 4;
+		}
+	} else {
+		/* double check we are limited to maximum pools */
+		vmdq_i = min_t(u16, 8, vmdq_i);
+
+		/* when VMDQ on, disable RSS */
+		rss_i = 1;
+	}
+
+	/* remove the starting offset from the pool count */
+	vmdq_i -= wx->ring_feature[RING_F_VMDQ].offset;
+
+	/* save features for later use */
+	wx->ring_feature[RING_F_VMDQ].indices = vmdq_i;
+	wx->ring_feature[RING_F_VMDQ].mask = vmdq_m;
+
+	/* limit RSS based on user input and save for later use */
+	wx->ring_feature[RING_F_RSS].indices = rss_i;
+	wx->ring_feature[RING_F_RSS].mask = rss_m;
+
+	wx->queues_per_pool = rss_i;/*maybe same to num_rx_queues_per_pool*/
+	wx->num_rx_pools = vmdq_i;
+	wx->num_rx_queues_per_pool = rss_i;
+
+	wx->num_rx_queues = vmdq_i * rss_i;
+	wx->num_tx_queues = vmdq_i * rss_i;
+
+	return true;
+}
+
 /**
  * wx_set_rss_queues: Allocate queues for RSS
  * @wx: board private structure to initialize
@@ -1617,6 +1676,10 @@ static void wx_set_rss_queues(struct wx *wx)
 
 	/* set mask for 16 queue limit of RSS */
 	f = &wx->ring_feature[RING_F_RSS];
+	if (wx->mac.type == wx_mac_sp)
+		f->mask = WX_RSS_64Q_MASK;
+	else
+		f->mask = WX_RSS_8Q_MASK;
 	f->indices = f->limit;
 
 	if (!(test_bit(WX_FLAG_FDIR_CAPABLE, wx->flags)))
@@ -1649,6 +1712,9 @@ static void wx_set_num_queues(struct wx *wx)
 	wx->num_tx_queues = 1;
 	wx->queues_per_pool = 1;
 
+	if (wx_set_vmdq_queues(wx))
+		return;
+
 	wx_set_rss_queues(wx);
 }
 
@@ -1729,6 +1795,10 @@ static int wx_set_interrupt_capability(struct wx *wx)
 	if (ret == 0 || (ret == -ENOMEM))
 		return ret;
 
+	/* Disable VMDq support */
+	dev_warn(&wx->pdev->dev, "Disabling VMQQ support\n");
+	clear_bit(WX_FLAG_VMDQ_ENABLED, wx->flags);
+
 	/* Disable RSS */
 	dev_warn(&wx->pdev->dev, "Disabling RSS support\n");
 	wx->ring_feature[RING_F_RSS].limit = 1;
@@ -1755,6 +1825,49 @@ static int wx_set_interrupt_capability(struct wx *wx)
 	return 0;
 }
 
+static bool wx_cache_ring_vmdq(struct wx *wx)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	struct wx_ring_feature *rss = &wx->ring_feature[RING_F_RSS];
+	u16 reg_idx;
+	int i;
+
+	/* only proceed if VMDq is enabled */
+	if (!test_bit(WX_FLAG_VMDQ_ENABLED, wx->flags))
+		return false;
+
+	if (wx->mac.type == wx_mac_sp) {
+		/* start at VMDq register offset for SR-IOV enabled setups */
+		reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
+		for (i = 0; i < wx->num_rx_queues; i++, reg_idx++) {
+			/* If we are greater than indices move to next pool */
+			if ((reg_idx & ~vmdq->mask) >= rss->indices)
+				reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+			wx->rx_ring[i]->reg_idx = reg_idx;
+		}
+		reg_idx = vmdq->offset * __ALIGN_MASK(1, ~vmdq->mask);
+		for (i = 0; i < wx->num_tx_queues; i++, reg_idx++) {
+			/* If we are greater than indices move to next pool */
+			if ((reg_idx & rss->mask) >= rss->indices)
+				reg_idx = __ALIGN_MASK(reg_idx, ~vmdq->mask);
+			wx->tx_ring[i]->reg_idx = reg_idx;
+		}
+	} else {
+		/* start at VMDq register offset for SR-IOV enabled setups */
+		reg_idx = vmdq->offset;
+		for (i = 0; i < wx->num_rx_queues; i++)
+			/* If we are greater than indices move to next pool */
+			wx->rx_ring[i]->reg_idx = reg_idx + i;
+
+		reg_idx = vmdq->offset;
+		for (i = 0; i < wx->num_tx_queues; i++)
+			/* If we are greater than indices move to next pool */
+			wx->tx_ring[i]->reg_idx = reg_idx + i;
+	}
+
+	return true;
+}
+
 /**
  * wx_cache_ring_rss - Descriptor ring to register mapping for RSS
  * @wx: board private structure to initialize
@@ -1766,6 +1879,9 @@ static void wx_cache_ring_rss(struct wx *wx)
 {
 	u16 i;
 
+	if (wx_cache_ring_vmdq(wx))
+		return;
+
 	for (i = 0; i < wx->num_rx_queues; i++)
 		wx->rx_ring[i]->reg_idx = i;
 
@@ -2164,7 +2280,8 @@ static void wx_set_ivar(struct wx *wx, s8 direction,
 		wr32(wx, WX_PX_MISC_IVAR, ivar);
 	} else {
 		/* tx or rx causes */
-		msix_vector += 1; /* offset for queue vectors */
+		if (!(wx->mac.type == wx_mac_em && wx->num_vfs == 7))
+			msix_vector += 1; /* offset for queue vectors */
 		msix_vector |= WX_PX_IVAR_ALLOC_VAL;
 		index = ((16 * (queue & 1)) + (8 * direction));
 		ivar = rd32(wx, WX_PX_IVAR(queue >> 1));
@@ -2216,10 +2333,17 @@ void wx_configure_vectors(struct wx *wx)
 {
 	struct pci_dev *pdev = wx->pdev;
 	u32 eitrsel = 0;
-	u16 v_idx;
+	u16 v_idx, i;
 
 	if (pdev->msix_enabled) {
 		/* Populate MSIX to EITR Select */
+		if (wx->mac.type == wx_mac_sp) {
+			if (wx->num_vfs >= 32)
+				eitrsel = BIT(wx->num_vfs % 32) - 1;
+		} else if (wx->mac.type == wx_mac_em) {
+			for (i = 0; i < wx->num_vfs; i++)
+				eitrsel |= BIT(i);
+		}
 		wr32(wx, WX_PX_ITRSEL, eitrsel);
 		/* use EIAM to auto-mask when MSI-X interrupt is asserted
 		 * this saves a register write for every interrupt
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 26776dee64903..be9463f8b4087 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -21,6 +21,7 @@
 #define WX_PCIE_MSIX_TBL_SZ_MASK                0x7FF
 #define WX_PCI_LINK_STATUS                      0xB2
 #define WX_MAX_PF_MACVLANS                      15
+#define WX_MAX_VF_MC_ENTRIES                    30
 
 /**************** Global Registers ****************************/
 #define WX_VF_REG_OFFSET(_v)         FIELD_GET(GENMASK(15, 5), (_v))
@@ -80,6 +81,7 @@
 #define WX_MAC_LXONOFFRXC            0x11E0C
 
 /*********************** Receive DMA registers **************************/
+#define WX_RDM_VF_RE(_i)             (0x12004 + ((_i) * 4))
 #define WX_RDM_DRP_PKT               0x12500
 #define WX_RDM_PKT_CNT               0x12504
 #define WX_RDM_BYTE_CNT_LSB          0x12508
@@ -94,6 +96,7 @@
 #define WX_CFG_TAG_TPID(_i)          (0x14430 + ((_i) * 4))
 #define WX_CFG_PORT_CTL_NUM_VT_MASK  GENMASK(13, 12) /* number of TVs */
 
+#define WX_CFG_PORT_CTL_NUM_VT_NONE  0
 #define WX_CFG_PORT_CTL_NUM_VT_8     FIELD_PREP(GENMASK(13, 12), 1)
 #define WX_CFG_PORT_CTL_NUM_VT_32    FIELD_PREP(GENMASK(13, 12), 2)
 #define WX_CFG_PORT_CTL_NUM_VT_64    FIELD_PREP(GENMASK(13, 12), 3)
@@ -119,6 +122,10 @@
 /*********************** Transmit DMA registers **************************/
 /* transmit global control */
 #define WX_TDM_CTL                   0x18000
+#define WX_TDM_VF_TE(_i)             (0x18004 + ((_i) * 4))
+#define WX_TDM_MAC_AS(_i)            (0x18060 + ((_i) * 4))
+#define WX_TDM_VLAN_AS(_i)           (0x18070 + ((_i) * 4))
+
 /* TDM CTL BIT */
 #define WX_TDM_CTL_TE                BIT(0) /* Transmit Enable */
 #define WX_TDM_PB_THRE(_i)           (0x18020 + ((_i) * 4))
@@ -209,7 +216,10 @@
 #define WX_PSR_1588_CTL_VALID           BIT(0)
 /* mcasst/ucast overflow tbl */
 #define WX_PSR_MC_TBL(_i)            (0x15200  + ((_i) * 4))
+#define WX_PSR_MC_TBL_REG(_i)        FIELD_GET(GENMASK(11, 5), (_i))
+#define WX_PSR_MC_TBL_BIT(_i)        FIELD_GET(GENMASK(4, 0), (_i))
 #define WX_PSR_UC_TBL(_i)            (0x15400 + ((_i) * 4))
+#define WX_PSR_VM_CTL_REPLEN         BIT(30) /* replication enabled */
 #define WX_PSR_VM_CTL_POOL_MASK      GENMASK(12, 7)
 
 /* VM L2 contorl */
@@ -254,6 +264,7 @@
 #define WX_PSR_VLAN_SWC              0x16220
 #define WX_PSR_VLAN_SWC_VM_L         0x16224
 #define WX_PSR_VLAN_SWC_VM_H         0x16228
+#define WX_PSR_VLAN_SWC_VM(_i)       (0x16224 + ((_i) * 4))
 #define WX_PSR_VLAN_SWC_IDX          0x16230         /* 64 vlan entries */
 /* VLAN pool filtering masks */
 #define WX_PSR_VLAN_SWC_VIEN         BIT(31)  /* filter is valid */
@@ -268,6 +279,10 @@
 #define WX_RSC_ST                    0x17004
 #define WX_RSC_ST_RSEC_RDY           BIT(0)
 
+/*********************** Transmit DMA registers **************************/
+/* transmit global control */
+#define WX_TDM_ETYPE_AS(_i)          (0x18058 + ((_i) * 4))
+
 /****************************** TDB ******************************************/
 #define WX_TDB_PB_SZ(_i)             (0x1CC00 + ((_i) * 4))
 #define WX_TXPKT_SIZE_MAX            0xA /* Max Tx Packet size */
@@ -426,6 +441,15 @@ enum WX_MSCA_CMD_value {
 /* Number of 80 microseconds we wait for PCI Express master disable */
 #define WX_PCI_MASTER_DISABLE_TIMEOUT        80000
 
+#define WX_RSS_64Q_MASK              0x3F
+#define WX_RSS_8Q_MASK               0x7
+#define WX_RSS_4Q_MASK               0x3
+#define WX_RSS_2Q_MASK               0x1
+#define WX_RSS_DISABLED_MASK         0x0
+
+#define WX_VMDQ_4Q_MASK              0x7C
+#define WX_VMDQ_2Q_MASK              0x7E
+
 /****************** Manageablility Host Interface defines ********************/
 #define WX_HI_MAX_BLOCK_BYTE_LENGTH  256 /* Num of bytes in range */
 #define WX_HI_COMMAND_TIMEOUT        1000 /* Process HI command limit */
@@ -493,7 +517,7 @@ enum WX_MSCA_CMD_value {
 #define WX_REQ_TX_DESCRIPTOR_MULTIPLE   128
 
 #define WX_MAX_JUMBO_FRAME_SIZE      9432 /* max payload 9414 */
-#define VMDQ_P(p)                    p
+#define VMDQ_P(p)       ((p) + wx->ring_feature[RING_F_VMDQ].offset)
 
 /* Supported Rx Buffer Sizes */
 #define WX_RXBUFFER_256      256    /* Used for skb receive header */
@@ -1128,6 +1152,10 @@ struct vf_data_storage {
 	bool link_enable;
 	bool trusted;
 	int xcast_mode;
+
+	u16 vf_mc_hashes[WX_MAX_VF_MC_ENTRIES];
+	u16 num_vf_mc_hashes;
+	u16 vlan_count;
 };
 
 struct vf_macvlans {
@@ -1141,6 +1169,7 @@ struct vf_macvlans {
 enum wx_pf_flags {
 	WX_FLAG_SWFW_RING,
 	WX_FLAG_VMDQ_ENABLED,
+	WX_FLAG_VLAN_PROMISC,
 	WX_FLAG_SRIOV_ENABLED,
 	WX_FLAG_FDIR_CAPABLE,
 	WX_FLAG_FDIR_HASH,
@@ -1217,6 +1246,8 @@ struct wx {
 	struct wx_ring *tx_ring[64] ____cacheline_aligned_in_smp;
 	struct wx_ring *rx_ring[64];
 	struct wx_q_vector *q_vector[64];
+	int num_rx_pools;
+	int num_rx_queues_per_pool;
 
 	unsigned int queues_per_pool;
 	struct msix_entry *msix_q_entries;
@@ -1250,6 +1281,7 @@ struct wx {
 	struct vf_data_storage *vfinfo;
 	struct vf_macvlans vf_mvs;
 	struct vf_macvlans *mv_list;
+	unsigned long fwd_bitmask;
 
 	u32 atr_sample_rate;
 	void (*atr)(struct wx_ring *ring, struct wx_tx_buffer *first, u8 ptype);

From b64a5f8e87627094d749fa92716bae06aaf6e508 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:57 +0800
Subject: [PATCH 2462/2753] net: libwx: Add msg task func

Implement wx_msg_task which is used to process mailbox
messages sent by vf.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c    |   8 +-
 drivers/net/ethernet/wangxun/libwx/wx_hw.h    |   4 +
 drivers/net/ethernet/wangxun/libwx/wx_mbx.h   |  41 ++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.c | 636 ++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.h |   1 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  17 +
 6 files changed, 703 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 1953365827a07..6cdb89a6951c6 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -1011,7 +1011,7 @@ void wx_flush_sw_mac_table(struct wx *wx)
 }
 EXPORT_SYMBOL(wx_flush_sw_mac_table);
 
-static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -1042,7 +1042,7 @@ static int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 	return -ENOMEM;
 }
 
-static int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
+int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool)
 {
 	u32 i;
 
@@ -1469,7 +1469,7 @@ static void wx_set_ethertype_anti_spoofing(struct wx *wx, bool enable, int vf)
 	wr32(wx, WX_TDM_ETYPE_AS(reg_offset), pfvfspoof);
 }
 
-static int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
+int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting)
 {
 	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
 	struct wx *wx = netdev_priv(netdev);
@@ -2528,7 +2528,7 @@ static int wx_set_vlvf(struct wx *wx, u32 vlan, u32 vind, bool vlan_on,
  *
  *  Turn on/off specified VLAN in the VLAN filter table.
  **/
-static int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
+int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on)
 {
 	u32 bitindex, vfta, targetbit;
 	bool vfta_changed = false;
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.h b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
index b883342bb5767..91c1d6135045b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.h
@@ -26,9 +26,12 @@ void wx_init_eeprom_params(struct wx *wx);
 void wx_get_mac_addr(struct wx *wx, u8 *mac_addr);
 void wx_init_rx_addrs(struct wx *wx);
 void wx_mac_set_default_filter(struct wx *wx, u8 *addr);
+int wx_add_mac_filter(struct wx *wx, u8 *addr, u16 pool);
+int wx_del_mac_filter(struct wx *wx, u8 *addr, u16 pool);
 void wx_flush_sw_mac_table(struct wx *wx);
 int wx_set_mac(struct net_device *netdev, void *p);
 void wx_disable_rx(struct wx *wx);
+int wx_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting);
 int wx_disable_sec_rx_path(struct wx *wx);
 void wx_enable_sec_rx_path(struct wx *wx);
 void wx_set_rx_mode(struct net_device *netdev);
@@ -42,6 +45,7 @@ int wx_stop_adapter(struct wx *wx);
 void wx_reset_misc(struct wx *wx);
 int wx_get_pcie_msix_counts(struct wx *wx, u16 *msix_count, u16 max_msix_count);
 int wx_sw_init(struct wx *wx);
+int wx_set_vfta(struct wx *wx, u32 vlan, u32 vind, bool vlan_on);
 int wx_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int wx_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, u16 vid);
 int wx_fc_enable(struct wx *wx, bool tx_pause, bool rx_pause);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
index 172b46b9c14dc..05aae138dbc31 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_mbx.h
@@ -21,10 +21,51 @@
 #define WX_MBVFICR_VFREQ_MASK GENMASK(15, 0)
 #define WX_MBVFICR_VFACK_MASK GENMASK(31, 16)
 
+#define WX_VT_MSGTYPE_ACK     BIT(31)
+#define WX_VT_MSGTYPE_NACK    BIT(30)
+#define WX_VT_MSGTYPE_CTS     BIT(29)
+#define WX_VT_MSGINFO_SHIFT   16
 #define WX_VT_MSGINFO_MASK    GENMASK(23, 16)
 
+enum wx_pfvf_api_rev {
+	wx_mbox_api_null,
+	wx_mbox_api_13 = 4,      /* API version 1.3 */
+	wx_mbox_api_unknown, /* indicates that API version is not known */
+};
+
+/* mailbox API */
+#define WX_VF_RESET                  0x01 /* VF requests reset */
+#define WX_VF_SET_MAC_ADDR           0x02 /* VF requests PF to set MAC addr */
+#define WX_VF_SET_MULTICAST          0x03 /* VF requests PF to set MC addr */
+#define WX_VF_SET_VLAN               0x04 /* VF requests PF to set VLAN */
+#define WX_VF_SET_LPE                0x05 /* VF requests PF to set VMOLR.LPE */
+#define WX_VF_SET_MACVLAN            0x06 /* VF requests PF unicast filter */
+#define WX_VF_API_NEGOTIATE          0x08 /* negotiate API version */
+#define WX_VF_GET_QUEUES             0x09 /* get queue configuration */
+#define WX_VF_GET_RETA               0x0a /* VF request for RETA */
+#define WX_VF_GET_RSS_KEY            0x0b /* get RSS key */
+#define WX_VF_UPDATE_XCAST_MODE      0x0c
+#define WX_VF_GET_LINK_STATE         0x10 /* get vf link state */
+#define WX_VF_GET_FW_VERSION         0x11 /* get fw version */
+
+#define WX_VF_BACKUP                 0x8001 /* VF requests backup */
+
+#define WX_PF_CONTROL_MSG            BIT(8) /* PF control message */
+#define WX_PF_NOFITY_VF_LINK_STATUS  0x1
+#define WX_PF_NOFITY_VF_NET_NOT_RUNNING BIT(31)
+
+#define WX_VF_TX_QUEUES              1 /* number of Tx queues supported */
+#define WX_VF_RX_QUEUES              2 /* number of Rx queues supported */
+#define WX_VF_TRANS_VLAN             3 /* Indication of port vlan */
+#define WX_VF_DEF_QUEUE              4 /* Default queue offset */
+
+#define WX_VF_PERMADDR_MSG_LEN       4
+
 enum wxvf_xcast_modes {
 	WXVF_XCAST_MODE_NONE = 0,
+	WXVF_XCAST_MODE_MULTI,
+	WXVF_XCAST_MODE_ALLMULTI,
+	WXVF_XCAST_MODE_PROMISC,
 };
 
 int wx_write_mbx_pf(struct wx *wx, u32 *msg, u16 size, u16 vf);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
index 2392df341ad1f..a038611570724 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -5,6 +5,7 @@
 #include <linux/pci.h>
 
 #include "wx_type.h"
+#include "wx_hw.h"
 #include "wx_mbx.h"
 #include "wx_sriov.h"
 
@@ -199,3 +200,638 @@ int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs)
 	return num_vfs;
 }
 EXPORT_SYMBOL(wx_pci_sriov_configure);
+
+static int wx_set_vf_mac(struct wx *wx, u16 vf, const u8 *mac_addr)
+{
+	u8 hw_addr[ETH_ALEN];
+	int ret = 0;
+
+	ether_addr_copy(hw_addr, mac_addr);
+	wx_del_mac_filter(wx, wx->vfinfo[vf].vf_mac_addr, vf);
+	ret = wx_add_mac_filter(wx, hw_addr, vf);
+	if (ret >= 0)
+		ether_addr_copy(wx->vfinfo[vf].vf_mac_addr, mac_addr);
+	else
+		eth_zero_addr(wx->vfinfo[vf].vf_mac_addr);
+
+	return ret;
+}
+
+static void wx_set_vmolr(struct wx *wx, u16 vf, bool aupe)
+{
+	u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+
+	vmolr |=  WX_PSR_VM_L2CTL_BAM;
+	if (aupe)
+		vmolr |= WX_PSR_VM_L2CTL_AUPE;
+	else
+		vmolr &= ~WX_PSR_VM_L2CTL_AUPE;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+}
+
+static void wx_set_vmvir(struct wx *wx, u16 vid, u16 qos, u16 vf)
+{
+	u32 vmvir = vid | (qos << VLAN_PRIO_SHIFT) |
+		    WX_TDM_VLAN_INS_VLANA_DEFAULT;
+
+	wr32(wx, WX_TDM_VLAN_INS(vf), vmvir);
+}
+
+static int wx_set_vf_vlan(struct wx *wx, int add, int vid, u16 vf)
+{
+	if (!vid && !add)
+		return 0;
+
+	return wx_set_vfta(wx, vid, vf, (bool)add);
+}
+
+static void wx_set_vlan_anti_spoofing(struct wx *wx, bool enable, int vf)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	u32 pfvfspoof;
+
+	pfvfspoof = rd32(wx, WX_TDM_VLAN_AS(index));
+	if (enable)
+		pfvfspoof |= BIT(vf_bit);
+	else
+		pfvfspoof &= ~BIT(vf_bit);
+	wr32(wx, WX_TDM_VLAN_AS(index), pfvfspoof);
+}
+
+static void wx_write_qde(struct wx *wx, u32 vf, u32 qde)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	u32 q_per_pool = __ALIGN_MASK(1, ~vmdq->mask);
+	u32 reg = 0, n = vf * q_per_pool / 32;
+	u32 i = vf * q_per_pool;
+
+	reg = rd32(wx, WX_RDM_PF_QDE(n));
+	for (i = (vf * q_per_pool - n * 32);
+	     i < ((vf + 1) * q_per_pool - n * 32);
+	     i++) {
+		if (qde == 1)
+			reg |= qde << i;
+		else
+			reg &= qde << i;
+	}
+
+	wr32(wx, WX_RDM_PF_QDE(n), reg);
+}
+
+static void wx_clear_vmvir(struct wx *wx, u32 vf)
+{
+	wr32(wx, WX_TDM_VLAN_INS(vf), 0);
+}
+
+static void wx_set_vf_rx_tx(struct wx *wx, int vf)
+{
+	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
+	u32 reg_cur_tx, reg_cur_rx, reg_req_tx, reg_req_rx;
+
+	reg_cur_tx = rd32(wx, WX_TDM_VF_TE(index));
+	reg_cur_rx = rd32(wx, WX_RDM_VF_RE(index));
+
+	if (wx->vfinfo[vf].link_enable) {
+		reg_req_tx = reg_cur_tx | BIT(vf_bit);
+		reg_req_rx = reg_cur_rx | BIT(vf_bit);
+		/* Enable particular VF */
+		if (reg_cur_tx != reg_req_tx)
+			wr32(wx, WX_TDM_VF_TE(index), reg_req_tx);
+		if (reg_cur_rx != reg_req_rx)
+			wr32(wx, WX_RDM_VF_RE(index), reg_req_rx);
+	} else {
+		reg_req_tx = BIT(vf_bit);
+		reg_req_rx = BIT(vf_bit);
+		/* Disable particular VF */
+		if (reg_cur_tx & reg_req_tx)
+			wr32(wx, WX_TDM_VFTE_CLR(index), reg_req_tx);
+		if (reg_cur_rx & reg_req_rx)
+			wr32(wx, WX_RDM_VFRE_CLR(index), reg_req_rx);
+	}
+}
+
+static int wx_get_vf_queues(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	struct wx_ring_feature *vmdq = &wx->ring_feature[RING_F_VMDQ];
+	unsigned int default_tc = 0;
+
+	msgbuf[WX_VF_TX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask);
+	msgbuf[WX_VF_RX_QUEUES] = __ALIGN_MASK(1, ~vmdq->mask);
+
+	if (wx->vfinfo[vf].pf_vlan || wx->vfinfo[vf].pf_qos)
+		msgbuf[WX_VF_TRANS_VLAN] = 1;
+	else
+		msgbuf[WX_VF_TRANS_VLAN] = 0;
+
+	/* notify VF of default queue */
+	msgbuf[WX_VF_DEF_QUEUE] = default_tc;
+
+	return 0;
+}
+
+static void wx_vf_reset_event(struct wx *wx, u16 vf)
+{
+	struct vf_data_storage *vfinfo = &wx->vfinfo[vf];
+	u8 num_tcs = netdev_get_num_tc(wx->netdev);
+
+	/* add PF assigned VLAN */
+	wx_set_vf_vlan(wx, true, vfinfo->pf_vlan, vf);
+
+	/* reset offloads to defaults */
+	wx_set_vmolr(wx, vf, !vfinfo->pf_vlan);
+
+	/* set outgoing tags for VFs */
+	if (!vfinfo->pf_vlan && !vfinfo->pf_qos && !num_tcs) {
+		wx_clear_vmvir(wx, vf);
+	} else {
+		if (vfinfo->pf_qos || !num_tcs)
+			wx_set_vmvir(wx, vfinfo->pf_vlan,
+				     vfinfo->pf_qos, vf);
+		else
+			wx_set_vmvir(wx, vfinfo->pf_vlan,
+				     wx->default_up, vf);
+	}
+
+	/* reset multicast table array for vf */
+	wx->vfinfo[vf].num_vf_mc_hashes = 0;
+
+	/* Flush and reset the mta with the new values */
+	wx_set_rx_mode(wx->netdev);
+
+	wx_del_mac_filter(wx, wx->vfinfo[vf].vf_mac_addr, vf);
+	/* reset VF api back to unknown */
+	wx->vfinfo[vf].vf_api = wx_mbox_api_null;
+}
+
+static void wx_vf_reset_msg(struct wx *wx, u16 vf)
+{
+	const u8 *vf_mac = wx->vfinfo[vf].vf_mac_addr;
+	struct net_device *dev = wx->netdev;
+	u32 msgbuf[5] = {0, 0, 0, 0, 0};
+	u8 *addr = (u8 *)(&msgbuf[1]);
+	u32 reg = 0, index, vf_bit;
+	int pf_max_frame;
+
+	/* reset the filters for the device */
+	wx_vf_reset_event(wx, vf);
+
+	/* set vf mac address */
+	if (!is_zero_ether_addr(vf_mac))
+		wx_set_vf_mac(wx, vf, vf_mac);
+
+	index = WX_VF_REG_OFFSET(vf);
+	vf_bit = WX_VF_IND_SHIFT(vf);
+
+	/* force drop enable for all VF Rx queues */
+	wx_write_qde(wx, vf, 1);
+
+	/* set transmit and receive for vf */
+	wx_set_vf_rx_tx(wx, vf);
+
+	pf_max_frame = dev->mtu + ETH_HLEN;
+
+	if (pf_max_frame > ETH_FRAME_LEN)
+		reg = BIT(vf_bit);
+	wr32(wx, WX_RDM_VFRE_CLR(index), reg);
+
+	/* enable VF mailbox for further messages */
+	wx->vfinfo[vf].clear_to_send = true;
+
+	/* reply to reset with ack and vf mac address */
+	msgbuf[0] = WX_VF_RESET;
+	if (!is_zero_ether_addr(vf_mac)) {
+		msgbuf[0] |= WX_VT_MSGTYPE_ACK;
+		memcpy(addr, vf_mac, ETH_ALEN);
+	} else {
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+		wx_err(wx, "VF %d has no MAC address assigned", vf);
+	}
+
+	msgbuf[3] = wx->mac.mc_filter_type;
+	wx_write_mbx_pf(wx, msgbuf, WX_VF_PERMADDR_MSG_LEN, vf);
+}
+
+static int wx_set_vf_mac_addr(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	const u8 *new_mac = ((u8 *)(&msgbuf[1]));
+	int ret;
+
+	if (!is_valid_ether_addr(new_mac)) {
+		wx_err(wx, "VF %d attempted to set invalid mac\n", vf);
+		return -EINVAL;
+	}
+
+	if (wx->vfinfo[vf].pf_set_mac &&
+	    memcmp(wx->vfinfo[vf].vf_mac_addr, new_mac, ETH_ALEN)) {
+		wx_err(wx,
+		       "VF %d attempt to set a MAC but it already had a MAC.",
+		       vf);
+		return -EBUSY;
+	}
+
+	ret = wx_set_vf_mac(wx, vf, new_mac);
+	if (ret < 0)
+		return ret;
+
+	return 0;
+}
+
+static void wx_set_vf_multicasts(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	struct vf_data_storage *vfinfo = &wx->vfinfo[vf];
+	u16 entries = (msgbuf[0] & WX_VT_MSGINFO_MASK)
+		      >> WX_VT_MSGINFO_SHIFT;
+	u32 vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+	u32 vector_bit, vector_reg, mta_reg, i;
+	u16 *hash_list = (u16 *)&msgbuf[1];
+
+	/* only so many hash values supported */
+	entries = min_t(u16, entries, WX_MAX_VF_MC_ENTRIES);
+	vfinfo->num_vf_mc_hashes = entries;
+
+	for (i = 0; i < entries; i++)
+		vfinfo->vf_mc_hashes[i] = hash_list[i];
+
+	for (i = 0; i < vfinfo->num_vf_mc_hashes; i++) {
+		vector_reg = WX_PSR_MC_TBL_REG(vfinfo->vf_mc_hashes[i]);
+		vector_bit = WX_PSR_MC_TBL_BIT(vfinfo->vf_mc_hashes[i]);
+		mta_reg = wx->mac.mta_shadow[vector_reg];
+		mta_reg |= BIT(vector_bit);
+		wx->mac.mta_shadow[vector_reg] = mta_reg;
+		wr32(wx, WX_PSR_MC_TBL(vector_reg), mta_reg);
+	}
+	vmolr |= WX_PSR_VM_L2CTL_ROMPE;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+}
+
+static void wx_set_vf_lpe(struct wx *wx, u32 max_frame, u32 vf)
+{
+	u32 index, vf_bit, vfre;
+	u32 max_frs, reg_val;
+
+	/* determine VF receive enable location */
+	index = WX_VF_REG_OFFSET(vf);
+	vf_bit = WX_VF_IND_SHIFT(vf);
+
+	vfre = rd32(wx, WX_RDM_VF_RE(index));
+	vfre |= BIT(vf_bit);
+	wr32(wx, WX_RDM_VF_RE(index), vfre);
+
+	/* pull current max frame size from hardware */
+	max_frs = DIV_ROUND_UP(max_frame, 1024);
+	reg_val = rd32(wx, WX_MAC_WDG_TIMEOUT) & WX_MAC_WDG_TIMEOUT_WTO_MASK;
+	if (max_frs > (reg_val + WX_MAC_WDG_TIMEOUT_WTO_DELTA))
+		wr32(wx, WX_MAC_WDG_TIMEOUT,
+		     max_frs - WX_MAC_WDG_TIMEOUT_WTO_DELTA);
+}
+
+static int wx_find_vlvf_entry(struct wx *wx, u32 vlan)
+{
+	int regindex;
+	u32 vlvf;
+
+	/* short cut the special case */
+	if (vlan == 0)
+		return 0;
+
+	/* Search for the vlan id in the VLVF entries */
+	for (regindex = 1; regindex < WX_PSR_VLAN_SWC_ENTRIES; regindex++) {
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, regindex);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC);
+		if ((vlvf & VLAN_VID_MASK) == vlan)
+			break;
+	}
+
+	/* Return a negative value if not found */
+	if (regindex >= WX_PSR_VLAN_SWC_ENTRIES)
+		regindex = -EINVAL;
+
+	return regindex;
+}
+
+static int wx_set_vf_macvlan(struct wx *wx,
+			     u16 vf, int index, unsigned char *mac_addr)
+{
+	struct vf_macvlans *entry;
+	struct list_head *pos;
+	int retval = 0;
+
+	if (index <= 1) {
+		list_for_each(pos, &wx->vf_mvs.mvlist) {
+			entry = list_entry(pos, struct vf_macvlans, mvlist);
+			if (entry->vf == vf) {
+				entry->vf = -1;
+				entry->free = true;
+				entry->is_macvlan = false;
+				wx_del_mac_filter(wx, entry->vf_macvlan, vf);
+			}
+		}
+	}
+
+	if (!index)
+		return 0;
+
+	entry = NULL;
+	list_for_each(pos, &wx->vf_mvs.mvlist) {
+		entry = list_entry(pos, struct vf_macvlans, mvlist);
+		if (entry->free)
+			break;
+	}
+
+	if (!entry || !entry->free)
+		return -ENOSPC;
+
+	retval = wx_add_mac_filter(wx, mac_addr, vf);
+	if (retval >= 0) {
+		entry->free = false;
+		entry->is_macvlan = true;
+		entry->vf = vf;
+		memcpy(entry->vf_macvlan, mac_addr, ETH_ALEN);
+	}
+
+	return retval;
+}
+
+static int wx_set_vf_vlan_msg(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	int add = (msgbuf[0] & WX_VT_MSGINFO_MASK) >> WX_VT_MSGINFO_SHIFT;
+	int vid = (msgbuf[1] & WX_PSR_VLAN_SWC_VLANID_MASK);
+	int ret;
+
+	if (add)
+		wx->vfinfo[vf].vlan_count++;
+	else if (wx->vfinfo[vf].vlan_count)
+		wx->vfinfo[vf].vlan_count--;
+
+	/* in case of promiscuous mode any VLAN filter set for a VF must
+	 * also have the PF pool added to it.
+	 */
+	if (add && wx->netdev->flags & IFF_PROMISC)
+		wx_set_vf_vlan(wx, add, vid, VMDQ_P(0));
+
+	ret = wx_set_vf_vlan(wx, add, vid, vf);
+	if (!ret && wx->vfinfo[vf].spoofchk_enabled)
+		wx_set_vlan_anti_spoofing(wx, true, vf);
+
+	/* Go through all the checks to see if the VLAN filter should
+	 * be wiped completely.
+	 */
+	if (!add && wx->netdev->flags & IFF_PROMISC) {
+		u32 bits = 0, vlvf;
+		int reg_ndx;
+
+		reg_ndx = wx_find_vlvf_entry(wx, vid);
+		if (reg_ndx < 0)
+			return -ENOSPC;
+		wr32(wx, WX_PSR_VLAN_SWC_IDX, reg_ndx);
+		vlvf = rd32(wx, WX_PSR_VLAN_SWC);
+		/* See if any other pools are set for this VLAN filter
+		 * entry other than the PF.
+		 */
+		if (VMDQ_P(0) < 32) {
+			bits = rd32(wx, WX_PSR_VLAN_SWC_VM_L);
+			bits &= ~BIT(VMDQ_P(0));
+			if (wx->mac.type == wx_mac_sp)
+				bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_H);
+		} else {
+			if (wx->mac.type == wx_mac_sp)
+				bits = rd32(wx, WX_PSR_VLAN_SWC_VM_H);
+			bits &= ~BIT(VMDQ_P(0) % 32);
+			bits |= rd32(wx, WX_PSR_VLAN_SWC_VM_L);
+		}
+		/* If the filter was removed then ensure PF pool bit
+		 * is cleared if the PF only added itself to the pool
+		 * because the PF is in promiscuous mode.
+		 */
+		if ((vlvf & VLAN_VID_MASK) == vid && !bits)
+			wx_set_vf_vlan(wx, add, vid, VMDQ_P(0));
+	}
+
+	return 0;
+}
+
+static int wx_set_vf_macvlan_msg(struct wx *wx, u32 *msgbuf, u16 vf)
+{
+	int index = (msgbuf[0] & WX_VT_MSGINFO_MASK) >>
+		    WX_VT_MSGINFO_SHIFT;
+	u8 *new_mac = ((u8 *)(&msgbuf[1]));
+	int err;
+
+	if (wx->vfinfo[vf].pf_set_mac && index > 0) {
+		wx_err(wx, "VF %d request MACVLAN filter but is denied\n", vf);
+		return -EINVAL;
+	}
+
+	/* An non-zero index indicates the VF is setting a filter */
+	if (index) {
+		if (!is_valid_ether_addr(new_mac)) {
+			wx_err(wx, "VF %d attempted to set invalid mac\n", vf);
+			return -EINVAL;
+		}
+		/* If the VF is allowed to set MAC filters then turn off
+		 * anti-spoofing to avoid false positives.
+		 */
+		if (wx->vfinfo[vf].spoofchk_enabled)
+			wx_set_vf_spoofchk(wx->netdev, vf, false);
+	}
+
+	err = wx_set_vf_macvlan(wx, vf, index, new_mac);
+	if (err == -ENOSPC)
+		wx_err(wx,
+		       "VF %d request MACVLAN filter but there is no space\n",
+		       vf);
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int wx_negotiate_vf_api(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	int api = msgbuf[1];
+
+	switch (api) {
+	case wx_mbox_api_13:
+		wx->vfinfo[vf].vf_api = api;
+		return 0;
+	default:
+		wx_err(wx, "VF %d requested invalid api version %u\n", vf, api);
+		return -EINVAL;
+	}
+}
+
+static int wx_get_vf_link_state(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	msgbuf[1] = wx->vfinfo[vf].link_enable;
+
+	return 0;
+}
+
+static int wx_get_fw_version(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	unsigned long fw_version = 0ULL;
+	int ret = 0;
+
+	ret = kstrtoul(wx->eeprom_id, 16, &fw_version);
+	if (ret)
+		return -EOPNOTSUPP;
+	msgbuf[1] = fw_version;
+
+	return 0;
+}
+
+static int wx_update_vf_xcast_mode(struct wx *wx, u32 *msgbuf, u32 vf)
+{
+	int xcast_mode = msgbuf[1];
+	u32 vmolr, disable, enable;
+
+	if (wx->vfinfo[vf].xcast_mode == xcast_mode)
+		return 0;
+
+	switch (xcast_mode) {
+	case WXVF_XCAST_MODE_NONE:
+		disable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			  WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			  WX_PSR_VM_L2CTL_VPE;
+		enable = 0;
+		break;
+	case WXVF_XCAST_MODE_MULTI:
+		disable = WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			  WX_PSR_VM_L2CTL_VPE;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE;
+		break;
+	case WXVF_XCAST_MODE_ALLMULTI:
+		disable = WX_PSR_VM_L2CTL_UPE | WX_PSR_VM_L2CTL_VPE;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			 WX_PSR_VM_L2CTL_MPE;
+		break;
+	case WXVF_XCAST_MODE_PROMISC:
+		disable = 0;
+		enable = WX_PSR_VM_L2CTL_BAM | WX_PSR_VM_L2CTL_ROMPE |
+			 WX_PSR_VM_L2CTL_MPE | WX_PSR_VM_L2CTL_UPE |
+			 WX_PSR_VM_L2CTL_VPE;
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	vmolr = rd32(wx, WX_PSR_VM_L2CTL(vf));
+	vmolr &= ~disable;
+	vmolr |= enable;
+	wr32(wx, WX_PSR_VM_L2CTL(vf), vmolr);
+
+	wx->vfinfo[vf].xcast_mode = xcast_mode;
+	msgbuf[1] = xcast_mode;
+
+	return 0;
+}
+
+static void wx_rcv_msg_from_vf(struct wx *wx, u16 vf)
+{
+	u16 mbx_size = WX_VXMAILBOX_SIZE;
+	u32 msgbuf[WX_VXMAILBOX_SIZE];
+	int retval;
+
+	retval = wx_read_mbx_pf(wx, msgbuf, mbx_size, vf);
+	if (retval) {
+		wx_err(wx, "Error receiving message from VF\n");
+		return;
+	}
+
+	/* this is a message we already processed, do nothing */
+	if (msgbuf[0] & (WX_VT_MSGTYPE_ACK | WX_VT_MSGTYPE_NACK))
+		return;
+
+	if (msgbuf[0] == WX_VF_RESET) {
+		wx_vf_reset_msg(wx, vf);
+		return;
+	}
+
+	/* until the vf completes a virtual function reset it should not be
+	 * allowed to start any configuration.
+	 */
+	if (!wx->vfinfo[vf].clear_to_send) {
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+		wx_write_mbx_pf(wx, msgbuf, 1, vf);
+		return;
+	}
+
+	switch ((msgbuf[0] & U16_MAX)) {
+	case WX_VF_SET_MAC_ADDR:
+		retval = wx_set_vf_mac_addr(wx, msgbuf, vf);
+		break;
+	case WX_VF_SET_MULTICAST:
+		wx_set_vf_multicasts(wx, msgbuf, vf);
+		retval = 0;
+		break;
+	case WX_VF_SET_VLAN:
+		retval = wx_set_vf_vlan_msg(wx, msgbuf, vf);
+		break;
+	case WX_VF_SET_LPE:
+		wx_set_vf_lpe(wx, msgbuf[1], vf);
+		retval = 0;
+		break;
+	case WX_VF_SET_MACVLAN:
+		retval = wx_set_vf_macvlan_msg(wx, msgbuf, vf);
+		break;
+	case WX_VF_API_NEGOTIATE:
+		retval = wx_negotiate_vf_api(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_QUEUES:
+		retval = wx_get_vf_queues(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_LINK_STATE:
+		retval = wx_get_vf_link_state(wx, msgbuf, vf);
+		break;
+	case WX_VF_GET_FW_VERSION:
+		retval = wx_get_fw_version(wx, msgbuf, vf);
+		break;
+	case WX_VF_UPDATE_XCAST_MODE:
+		retval = wx_update_vf_xcast_mode(wx, msgbuf, vf);
+		break;
+	case WX_VF_BACKUP:
+		break;
+	default:
+		wx_err(wx, "Unhandled Msg %8.8x\n", msgbuf[0]);
+		break;
+	}
+
+	/* notify the VF of the results of what it sent us */
+	if (retval)
+		msgbuf[0] |= WX_VT_MSGTYPE_NACK;
+	else
+		msgbuf[0] |= WX_VT_MSGTYPE_ACK;
+
+	msgbuf[0] |= WX_VT_MSGTYPE_CTS;
+
+	wx_write_mbx_pf(wx, msgbuf, mbx_size, vf);
+}
+
+static void wx_rcv_ack_from_vf(struct wx *wx, u16 vf)
+{
+	u32 msg = WX_VT_MSGTYPE_NACK;
+
+	/* if device isn't clear to send it shouldn't be reading either */
+	if (!wx->vfinfo[vf].clear_to_send)
+		wx_write_mbx_pf(wx, &msg, 1, vf);
+}
+
+void wx_msg_task(struct wx *wx)
+{
+	u16 vf;
+
+	for (vf = 0; vf < wx->num_vfs; vf++) {
+		/* process any reset requests */
+		if (!wx_check_for_rst_pf(wx, vf))
+			wx_vf_reset_event(wx, vf);
+
+		/* process any messages pending */
+		if (!wx_check_for_msg_pf(wx, vf))
+			wx_rcv_msg_from_vf(wx, vf);
+
+		/* process any acks */
+		if (!wx_check_for_ack_pf(wx, vf))
+			wx_rcv_ack_from_vf(wx, vf);
+	}
+}
+EXPORT_SYMBOL(wx_msg_task);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
index a16877f893896..5d1486f92deef 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
@@ -6,5 +6,6 @@
 
 void wx_disable_sriov(struct wx *wx);
 int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs);
+void wx_msg_task(struct wx *wx);
 
 #endif /* _WX_SRIOV_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index be9463f8b4087..a5ca2ca0aba79 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -82,6 +82,8 @@
 
 /*********************** Receive DMA registers **************************/
 #define WX_RDM_VF_RE(_i)             (0x12004 + ((_i) * 4))
+#define WX_RDM_PF_QDE(_i)            (0x12080 + ((_i) * 4))
+#define WX_RDM_VFRE_CLR(_i)          (0x120A0 + ((_i) * 4))
 #define WX_RDM_DRP_PKT               0x12500
 #define WX_RDM_PKT_CNT               0x12504
 #define WX_RDM_BYTE_CNT_LSB          0x12508
@@ -125,6 +127,7 @@
 #define WX_TDM_VF_TE(_i)             (0x18004 + ((_i) * 4))
 #define WX_TDM_MAC_AS(_i)            (0x18060 + ((_i) * 4))
 #define WX_TDM_VLAN_AS(_i)           (0x18070 + ((_i) * 4))
+#define WX_TDM_VFTE_CLR(_i)          (0x180A0 + ((_i) * 4))
 
 /* TDM CTL BIT */
 #define WX_TDM_CTL_TE                BIT(0) /* Transmit Enable */
@@ -226,6 +229,7 @@
 #define WX_PSR_VM_L2CTL(_i)          (0x15600 + ((_i) * 4))
 #define WX_PSR_VM_L2CTL_UPE          BIT(4) /* unicast promiscuous */
 #define WX_PSR_VM_L2CTL_VACC         BIT(6) /* accept nomatched vlan */
+#define WX_PSR_VM_L2CTL_VPE          BIT(7) /* vlan promiscuous mode */
 #define WX_PSR_VM_L2CTL_AUPE         BIT(8) /* accept untagged packets */
 #define WX_PSR_VM_L2CTL_ROMPE        BIT(9) /* accept packets in MTA tbl */
 #define WX_PSR_VM_L2CTL_ROPE         BIT(10) /* accept packets in UC tbl */
@@ -269,6 +273,7 @@
 /* VLAN pool filtering masks */
 #define WX_PSR_VLAN_SWC_VIEN         BIT(31)  /* filter is valid */
 #define WX_PSR_VLAN_SWC_ENTRIES      64
+#define WX_PSR_VLAN_SWC_VLANID_MASK  GENMASK(11, 0)
 
 /********************************* RSEC **************************************/
 /* general rsec */
@@ -282,6 +287,9 @@
 /*********************** Transmit DMA registers **************************/
 /* transmit global control */
 #define WX_TDM_ETYPE_AS(_i)          (0x18058 + ((_i) * 4))
+#define WX_TDM_VLAN_INS(_i)          (0x18100 + ((_i) * 4))
+/* Per VF Port VLAN insertion rules */
+#define WX_TDM_VLAN_INS_VLANA_DEFAULT BIT(30) /* Always use default VLAN*/
 
 /****************************** TDB ******************************************/
 #define WX_TDB_PB_SZ(_i)             (0x1CC00 + ((_i) * 4))
@@ -352,6 +360,9 @@
 #define WX_MAC_WDG_TIMEOUT           0x1100C
 #define WX_MAC_RX_FLOW_CTRL          0x11090
 #define WX_MAC_RX_FLOW_CTRL_RFE      BIT(0) /* receive fc enable */
+
+#define WX_MAC_WDG_TIMEOUT_WTO_MASK  GENMASK(3, 0)
+#define WX_MAC_WDG_TIMEOUT_WTO_DELTA 2
 /* MDIO Registers */
 #define WX_MSCA                      0x11200
 #define WX_MSCA_RA(v)                FIELD_PREP(U16_MAX, v)
@@ -1152,6 +1163,11 @@ struct vf_data_storage {
 	bool link_enable;
 	bool trusted;
 	int xcast_mode;
+	unsigned int vf_api;
+	bool clear_to_send;
+	u16 pf_vlan; /* When set, guest VLAN config not allowed. */
+	u16 pf_qos;
+	bool pf_set_mac;
 
 	u16 vf_mc_hashes[WX_MAX_VF_MC_ENTRIES];
 	u16 num_vf_mc_hashes;
@@ -1269,6 +1285,7 @@ struct wx {
 	u32 wol;
 
 	u16 bd_number;
+	bool default_up;
 
 	struct wx_hw_stats stats;
 	u64 tx_busy;

From d2172fd82864cf75c92229892aecfda8a8a0582a Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:58 +0800
Subject: [PATCH 2463/2753] net: ngbe: add sriov function support

Add sriov_configure for driver ops.
Add mailbox handler wx_msg_task for ngbe in
the interrupt handler.
Add the notification flow when the vfs exist.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/wx_sriov.c | 31 +++++++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.h |  2 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  2 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_main.c | 93 +++++++++++++++++--
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c |  5 +
 drivers/net/ethernet/wangxun/ngbe/ngbe_type.h |  3 +
 6 files changed, 127 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
index a038611570724..12d263890ad99 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -835,3 +835,34 @@ void wx_msg_task(struct wx *wx)
 	}
 }
 EXPORT_SYMBOL(wx_msg_task);
+
+void wx_disable_vf_rx_tx(struct wx *wx)
+{
+	wr32(wx, WX_TDM_VFTE_CLR(0), 0);
+	wr32(wx, WX_RDM_VFRE_CLR(0), 0);
+	if (wx->mac.type == wx_mac_sp) {
+		wr32(wx, WX_TDM_VFTE_CLR(1), 0);
+		wr32(wx, WX_RDM_VFRE_CLR(1), 0);
+	}
+}
+EXPORT_SYMBOL(wx_disable_vf_rx_tx);
+
+void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up)
+{
+	u32 msgbuf[2] = {0, 0};
+	u16 i;
+
+	if (!wx->num_vfs)
+		return;
+	msgbuf[0] = WX_PF_NOFITY_VF_LINK_STATUS | WX_PF_CONTROL_MSG;
+	if (link_up)
+		msgbuf[1] = (wx->speed << 1) | link_up;
+	if (wx->notify_down)
+		msgbuf[1] |= WX_PF_NOFITY_VF_NET_NOT_RUNNING;
+	for (i = 0; i < wx->num_vfs; i++) {
+		if (wx->vfinfo[i].clear_to_send)
+			msgbuf[0] |= WX_VT_MSGTYPE_CTS;
+		wx_write_mbx_pf(wx, msgbuf, 2, i);
+	}
+}
+EXPORT_SYMBOL(wx_ping_all_vfs_with_link_status);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
index 5d1486f92deef..3cbec7fb51bc0 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
@@ -7,5 +7,7 @@
 void wx_disable_sriov(struct wx *wx);
 int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs);
 void wx_msg_task(struct wx *wx);
+void wx_disable_vf_rx_tx(struct wx *wx);
+void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up);
 
 #endif /* _WX_SRIOV_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index a5ca2ca0aba79..9b9345290594f 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -92,6 +92,7 @@
 /************************* Port Registers ************************************/
 /* port cfg Registers */
 #define WX_CFG_PORT_CTL              0x14400
+#define WX_CFG_PORT_CTL_PFRSTD       BIT(14)
 #define WX_CFG_PORT_CTL_DRV_LOAD     BIT(3)
 #define WX_CFG_PORT_CTL_QINQ         BIT(2)
 #define WX_CFG_PORT_CTL_D_VLAN       BIT(0) /* double vlan*/
@@ -1231,6 +1232,7 @@ struct wx {
 	u8 swfw_index;
 
 	/* PHY stuff */
+	bool notify_down;
 	unsigned int link;
 	int speed;
 	int duplex;
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
index a6159214ec0a9..d321c7f23b0b1 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_main.c
@@ -15,6 +15,8 @@
 #include "../libwx/wx_hw.h"
 #include "../libwx/wx_lib.h"
 #include "../libwx/wx_ptp.h"
+#include "../libwx/wx_mbx.h"
+#include "../libwx/wx_sriov.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
 #include "ngbe_hw.h"
@@ -129,6 +131,10 @@ static int ngbe_sw_init(struct wx *wx)
 	wx->tx_work_limit = NGBE_DEFAULT_TX_WORK;
 	wx->rx_work_limit = NGBE_DEFAULT_RX_WORK;
 
+	wx->mbx.size = WX_VXMAILBOX_SIZE;
+	wx->setup_tc = ngbe_setup_tc;
+	set_bit(0, &wx->fwd_bitmask);
+
 	return 0;
 }
 
@@ -200,12 +206,10 @@ static irqreturn_t ngbe_intr(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
+static irqreturn_t ngbe_msix_common(struct wx *wx, u32 eicr)
 {
-	struct wx *wx = data;
-	u32 eicr;
-
-	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+	if (eicr & NGBE_PX_MISC_IC_VF_MBOX)
+		wx_msg_task(wx);
 
 	if (unlikely(eicr & NGBE_PX_MISC_IC_TIMESYNC))
 		wx_ptp_check_pps_event(wx);
@@ -217,6 +221,35 @@ static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static irqreturn_t ngbe_msix_other(int __always_unused irq, void *data)
+{
+	struct wx *wx = data;
+	u32 eicr;
+
+	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+
+	return ngbe_msix_common(wx, eicr);
+}
+
+static irqreturn_t ngbe_msic_and_queue(int __always_unused irq, void *data)
+{
+	struct wx_q_vector *q_vector;
+	struct wx *wx = data;
+	u32 eicr;
+
+	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+	if (!eicr) {
+		/* queue */
+		q_vector = wx->q_vector[0];
+		napi_schedule_irqoff(&q_vector->napi);
+		if (netif_running(wx->netdev))
+			ngbe_irq_enable(wx, true);
+		return IRQ_HANDLED;
+	}
+
+	return ngbe_msix_common(wx, eicr);
+}
+
 /**
  * ngbe_request_msix_irqs - Initialize MSI-X interrupts
  * @wx: board private structure
@@ -249,8 +282,16 @@ static int ngbe_request_msix_irqs(struct wx *wx)
 		}
 	}
 
-	err = request_irq(wx->msix_entry->vector,
-			  ngbe_msix_other, 0, netdev->name, wx);
+	/* Due to hardware design, when num_vfs < 7, pf can use 0 for misc and 1
+	 * for queue. But when num_vfs == 7, vector[1] is assigned to vf6.
+	 * Misc and queue should reuse interrupt vector[0].
+	 */
+	if (wx->num_vfs == 7)
+		err = request_irq(wx->msix_entry->vector,
+				  ngbe_msic_and_queue, 0, netdev->name, wx);
+	else
+		err = request_irq(wx->msix_entry->vector,
+				  ngbe_msix_other, 0, netdev->name, wx);
 
 	if (err) {
 		wx_err(wx, "request_irq for msix_other failed: %d\n", err);
@@ -302,6 +343,22 @@ static void ngbe_disable_device(struct wx *wx)
 	struct net_device *netdev = wx->netdev;
 	u32 i;
 
+	if (wx->num_vfs) {
+		/* Clear EITR Select mapping */
+		wr32(wx, WX_PX_ITRSEL, 0);
+
+		/* Mark all the VFs as inactive */
+		for (i = 0; i < wx->num_vfs; i++)
+			wx->vfinfo[i].clear_to_send = 0;
+		wx->notify_down = true;
+		/* ping all the active vfs to let them know we are going down */
+		wx_ping_all_vfs_with_link_status(wx, false);
+		wx->notify_down = false;
+
+		/* Disable all VFTE/VFRE TX/RX */
+		wx_disable_vf_rx_tx(wx);
+	}
+
 	/* disable all enabled rx queues */
 	for (i = 0; i < wx->num_rx_queues; i++)
 		/* this call also flushes the previous write */
@@ -324,12 +381,19 @@ static void ngbe_disable_device(struct wx *wx)
 	wx_update_stats(wx);
 }
 
+static void ngbe_reset(struct wx *wx)
+{
+	wx_flush_sw_mac_table(wx);
+	wx_mac_set_default_filter(wx, wx->mac.addr);
+	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
+		wx_ptp_reset(wx);
+}
+
 void ngbe_down(struct wx *wx)
 {
 	phylink_stop(wx->phylink);
 	ngbe_disable_device(wx);
-	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
-		wx_ptp_reset(wx);
+	ngbe_reset(wx);
 	wx_clean_all_tx_rings(wx);
 	wx_clean_all_rx_rings(wx);
 }
@@ -352,6 +416,11 @@ void ngbe_up(struct wx *wx)
 		ngbe_sfp_modules_txrx_powerctl(wx, true);
 
 	phylink_start(wx->phylink);
+	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
+	wr32m(wx, WX_CFG_PORT_CTL,
+	      WX_CFG_PORT_CTL_PFRSTD, WX_CFG_PORT_CTL_PFRSTD);
+	if (wx->num_vfs)
+		wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 /**
@@ -596,6 +665,10 @@ static int ngbe_probe(struct pci_dev *pdev,
 		goto err_pci_release_regions;
 	}
 
+	/* The emerald supports up to 8 VFs per pf, but physical
+	 * function also need one pool for basic networking.
+	 */
+	pci_sriov_set_totalvfs(pdev, NGBE_MAX_VFS_DRV_LIMIT);
 	wx->driver_name = ngbe_driver_name;
 	ngbe_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &ngbe_netdev_ops;
@@ -743,6 +816,7 @@ static void ngbe_remove(struct pci_dev *pdev)
 	struct net_device *netdev;
 
 	netdev = wx->netdev;
+	wx_disable_sriov(wx);
 	unregister_netdev(netdev);
 	phylink_destroy(wx->phylink);
 	pci_release_selected_regions(pdev,
@@ -802,6 +876,7 @@ static struct pci_driver ngbe_driver = {
 	.suspend  = ngbe_suspend,
 	.resume   = ngbe_resume,
 	.shutdown = ngbe_shutdown,
+	.sriov_configure = wx_pci_sriov_configure,
 };
 
 module_pci_driver(ngbe_driver);
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index ea1d7e9a91f3d..c63bb6e6f4056 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -9,6 +9,7 @@
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
 #include "ngbe_type.h"
 #include "ngbe_mdio.h"
 
@@ -70,6 +71,8 @@ static void ngbe_mac_link_down(struct phylink_config *config,
 	wx->speed = SPEED_UNKNOWN;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 static void ngbe_mac_link_up(struct phylink_config *config,
@@ -114,6 +117,8 @@ static void ngbe_mac_link_up(struct phylink_config *config,
 	wx->last_rx_ptp_check = jiffies;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
 }
 
 static const struct phylink_mac_ops ngbe_mac_ops = {
diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
index 992adbb98c7d1..bb74263f04985 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_type.h
@@ -73,12 +73,14 @@
 #define NGBE_PX_MISC_IEN_TIMESYNC		BIT(11)
 #define NGBE_PX_MISC_IEN_ETH_LK			BIT(18)
 #define NGBE_PX_MISC_IEN_INT_ERR		BIT(20)
+#define NGBE_PX_MISC_IC_VF_MBOX			BIT(23)
 #define NGBE_PX_MISC_IEN_GPIO			BIT(26)
 #define NGBE_PX_MISC_IEN_MASK ( \
 				NGBE_PX_MISC_IEN_DEV_RST | \
 				NGBE_PX_MISC_IEN_TIMESYNC | \
 				NGBE_PX_MISC_IEN_ETH_LK | \
 				NGBE_PX_MISC_IEN_INT_ERR | \
+				NGBE_PX_MISC_IC_VF_MBOX | \
 				NGBE_PX_MISC_IEN_GPIO)
 
 /* Extended Interrupt Cause Read */
@@ -134,6 +136,7 @@
 #define NGBE_MAX_RXD				8192
 #define NGBE_MIN_RXD				128
 
+#define NGBE_MAX_VFS_DRV_LIMIT			7
 extern char ngbe_driver_name[];
 
 void ngbe_down(struct wx *wx);

From 0ff5a8c54705312178e00981a149494f48b04416 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Fri, 14 Mar 2025 05:46:59 +0800
Subject: [PATCH 2464/2753] net: txgbe: add sriov function support

Add sriov_configure for driver ops.
Add mailbox handler wx_msg_task for txgbe.

Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/wangxun/libwx/wx_sriov.c | 42 +++++++++++++++++++
 drivers/net/ethernet/wangxun/libwx/wx_sriov.h |  1 +
 drivers/net/ethernet/wangxun/libwx/wx_type.h  |  1 +
 .../net/ethernet/wangxun/txgbe/txgbe_irq.c    | 21 ++++++++--
 .../net/ethernet/wangxun/txgbe/txgbe_main.c   | 27 ++++++++++++
 .../net/ethernet/wangxun/txgbe/txgbe_phy.c    |  6 +++
 .../net/ethernet/wangxun/txgbe/txgbe_type.h   |  7 +++-
 7 files changed, 101 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
index 12d263890ad99..bbc4da7f2482b 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.c
@@ -283,6 +283,15 @@ static void wx_clear_vmvir(struct wx *wx, u32 vf)
 	wr32(wx, WX_TDM_VLAN_INS(vf), 0);
 }
 
+static void wx_ping_vf(struct wx *wx, int vf)
+{
+	u32 ping = WX_PF_CONTROL_MSG;
+
+	if (wx->vfinfo[vf].clear_to_send)
+		ping |= WX_VT_MSGTYPE_CTS;
+	wx_write_mbx_pf(wx, &ping, 1, vf);
+}
+
 static void wx_set_vf_rx_tx(struct wx *wx, int vf)
 {
 	u32 index = WX_VF_REG_OFFSET(vf), vf_bit = WX_VF_IND_SHIFT(vf);
@@ -866,3 +875,36 @@ void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up)
 	}
 }
 EXPORT_SYMBOL(wx_ping_all_vfs_with_link_status);
+
+static void wx_set_vf_link_state(struct wx *wx, int vf, int state)
+{
+	wx->vfinfo[vf].link_state = state;
+	switch (state) {
+	case IFLA_VF_LINK_STATE_AUTO:
+		if (netif_running(wx->netdev))
+			wx->vfinfo[vf].link_enable = true;
+		else
+			wx->vfinfo[vf].link_enable = false;
+		break;
+	case IFLA_VF_LINK_STATE_ENABLE:
+		wx->vfinfo[vf].link_enable = true;
+		break;
+	case IFLA_VF_LINK_STATE_DISABLE:
+		wx->vfinfo[vf].link_enable = false;
+		break;
+	}
+	/* restart the VF */
+	wx->vfinfo[vf].clear_to_send = false;
+	wx_ping_vf(wx, vf);
+
+	wx_set_vf_rx_tx(wx, vf);
+}
+
+void wx_set_all_vfs(struct wx *wx)
+{
+	int i;
+
+	for (i = 0; i < wx->num_vfs; i++)
+		wx_set_vf_link_state(wx, i, wx->vfinfo[i].link_state);
+}
+EXPORT_SYMBOL(wx_set_all_vfs);
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
index 3cbec7fb51bc0..1eebaa3eb90e1 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_sriov.h
@@ -9,5 +9,6 @@ int wx_pci_sriov_configure(struct pci_dev *pdev, int num_vfs);
 void wx_msg_task(struct wx *wx);
 void wx_disable_vf_rx_tx(struct wx *wx);
 void wx_ping_all_vfs_with_link_status(struct wx *wx, bool link_up);
+void wx_set_all_vfs(struct wx *wx);
 
 #endif /* _WX_SRIOV_H_ */
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
index 9b9345290594f..e13172c9eeedd 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
+++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
@@ -1173,6 +1173,7 @@ struct vf_data_storage {
 	u16 vf_mc_hashes[WX_MAX_VF_MC_ENTRIES];
 	u16 num_vf_mc_hashes;
 	u16 vlan_count;
+	int link_state;
 };
 
 struct vf_macvlans {
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
index 8658a51ee8106..280c74a57f6e2 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_irq.c
@@ -7,6 +7,7 @@
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_sriov.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
 #include "txgbe_irq.h"
@@ -109,8 +110,17 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 	struct wx *wx = txgbe->wx;
 	u32 eicr;
 
-	if (wx->pdev->msix_enabled)
+	if (wx->pdev->msix_enabled) {
+		eicr = wx_misc_isb(wx, WX_ISB_MISC) & TXGBE_PX_MISC_IEN_MASK;
+		if (!eicr)
+			return IRQ_NONE;
+		txgbe->eicr = eicr;
+		if (eicr & TXGBE_PX_MISC_IC_VF_MBOX) {
+			wx_msg_task(txgbe->wx);
+			wx_intr_enable(wx, TXGBE_INTR_MISC);
+		}
 		return IRQ_WAKE_THREAD;
+	}
 
 	eicr = wx_misc_isb(wx, WX_ISB_VEC0);
 	if (!eicr) {
@@ -129,6 +139,11 @@ static irqreturn_t txgbe_misc_irq_handle(int irq, void *data)
 	q_vector = wx->q_vector[0];
 	napi_schedule_irqoff(&q_vector->napi);
 
+	eicr = wx_misc_isb(wx, WX_ISB_MISC) & TXGBE_PX_MISC_IEN_MASK;
+	if (!eicr)
+		return IRQ_NONE;
+	txgbe->eicr = eicr;
+
 	return IRQ_WAKE_THREAD;
 }
 
@@ -140,7 +155,7 @@ static irqreturn_t txgbe_misc_irq_thread_fn(int irq, void *data)
 	unsigned int sub_irq;
 	u32 eicr;
 
-	eicr = wx_misc_isb(wx, WX_ISB_MISC);
+	eicr = txgbe->eicr;
 	if (eicr & (TXGBE_PX_MISC_ETH_LK | TXGBE_PX_MISC_ETH_LKDN |
 		    TXGBE_PX_MISC_ETH_AN)) {
 		sub_irq = irq_find_mapping(txgbe->misc.domain, TXGBE_IRQ_LINK);
@@ -183,7 +198,7 @@ int txgbe_setup_misc_irq(struct txgbe *txgbe)
 	if (wx->mac.type == wx_mac_aml)
 		goto skip_sp_irq;
 
-	txgbe->misc.nirqs = 1;
+	txgbe->misc.nirqs = TXGBE_IRQ_MAX;
 	txgbe->misc.domain = irq_domain_add_simple(NULL, txgbe->misc.nirqs, 0,
 						   &txgbe_misc_irq_domain_ops, txgbe);
 	if (!txgbe->misc.domain)
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
index a2e245e3b0168..239270c28a899 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_main.c
@@ -15,6 +15,8 @@
 #include "../libwx/wx_lib.h"
 #include "../libwx/wx_ptp.h"
 #include "../libwx/wx_hw.h"
+#include "../libwx/wx_mbx.h"
+#include "../libwx/wx_sriov.h"
 #include "txgbe_type.h"
 #include "txgbe_hw.h"
 #include "txgbe_phy.h"
@@ -117,6 +119,12 @@ static void txgbe_up_complete(struct wx *wx)
 
 	/* enable transmits */
 	netif_tx_start_all_queues(netdev);
+
+	/* Set PF Reset Done bit so PF/VF Mail Ops can work */
+	wr32m(wx, WX_CFG_PORT_CTL, WX_CFG_PORT_CTL_PFRSTD,
+	      WX_CFG_PORT_CTL_PFRSTD);
+	/* update setting rx tx for all active vfs */
+	wx_set_all_vfs(wx);
 }
 
 static void txgbe_reset(struct wx *wx)
@@ -165,6 +173,16 @@ static void txgbe_disable_device(struct wx *wx)
 		wx_err(wx, "%s: invalid bus lan id %d\n",
 		       __func__, wx->bus.func);
 
+	if (wx->num_vfs) {
+		/* Clear EITR Select mapping */
+		wr32(wx, WX_PX_ITRSEL, 0);
+		/* Mark all the VFs as inactive */
+		for (i = 0 ; i < wx->num_vfs; i++)
+			wx->vfinfo[i].clear_to_send = 0;
+		/* update setting rx tx for all active vfs */
+		wx_set_all_vfs(wx);
+	}
+
 	if (!(((wx->subsystem_device_id & WX_NCSI_MASK) == WX_NCSI_SUP) ||
 	      ((wx->subsystem_device_id & WX_WOL_MASK) == WX_WOL_SUP))) {
 		/* disable mac transmiter */
@@ -307,12 +325,15 @@ static int txgbe_sw_init(struct wx *wx)
 	/* set default ring sizes */
 	wx->tx_ring_count = TXGBE_DEFAULT_TXD;
 	wx->rx_ring_count = TXGBE_DEFAULT_RXD;
+	wx->mbx.size = WX_VXMAILBOX_SIZE;
 
 	/* set default work limits */
 	wx->tx_work_limit = TXGBE_DEFAULT_TX_WORK;
 	wx->rx_work_limit = TXGBE_DEFAULT_RX_WORK;
 
+	wx->setup_tc = txgbe_setup_tc;
 	wx->do_reset = txgbe_do_reset;
+	set_bit(0, &wx->fwd_bitmask);
 
 	switch (wx->mac.type) {
 	case wx_mac_sp:
@@ -604,6 +625,10 @@ static int txgbe_probe(struct pci_dev *pdev,
 		goto err_pci_release_regions;
 	}
 
+	/* The sapphire supports up to 63 VFs per pf, but physical
+	 * function also need one pool for basic networking.
+	 */
+	pci_sriov_set_totalvfs(pdev, TXGBE_MAX_VFS_DRV_LIMIT);
 	wx->driver_name = txgbe_driver_name;
 	txgbe_set_ethtool_ops(netdev);
 	netdev->netdev_ops = &txgbe_netdev_ops;
@@ -794,6 +819,7 @@ static void txgbe_remove(struct pci_dev *pdev)
 	struct net_device *netdev;
 
 	netdev = wx->netdev;
+	wx_disable_sriov(wx);
 	unregister_netdev(netdev);
 
 	txgbe_remove_phy(txgbe);
@@ -816,6 +842,7 @@ static struct pci_driver txgbe_driver = {
 	.probe    = txgbe_probe,
 	.remove   = txgbe_remove,
 	.shutdown = txgbe_shutdown,
+	.sriov_configure = wx_pci_sriov_configure,
 };
 
 module_pci_driver(txgbe_driver);
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
index 85f022ceef4fe..1863cfd27ee79 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_phy.c
@@ -16,6 +16,8 @@
 #include "../libwx/wx_type.h"
 #include "../libwx/wx_lib.h"
 #include "../libwx/wx_ptp.h"
+#include "../libwx/wx_sriov.h"
+#include "../libwx/wx_mbx.h"
 #include "../libwx/wx_hw.h"
 #include "txgbe_type.h"
 #include "txgbe_phy.h"
@@ -184,6 +186,8 @@ static void txgbe_mac_link_down(struct phylink_config *config,
 	wx->speed = SPEED_UNKNOWN;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going down */
+	wx_ping_all_vfs_with_link_status(wx, false);
 }
 
 static void txgbe_mac_link_up(struct phylink_config *config,
@@ -225,6 +229,8 @@ static void txgbe_mac_link_up(struct phylink_config *config,
 	wx->last_rx_ptp_check = jiffies;
 	if (test_bit(WX_STATE_PTP_RUNNING, wx->state))
 		wx_ptp_reset_cyclecounter(wx);
+	/* ping all the active vfs to let them know we are going up */
+	wx_ping_all_vfs_with_link_status(wx, true);
 }
 
 static int txgbe_mac_prepare(struct phylink_config *config, unsigned int mode,
diff --git a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
index 9c1c26234cad9..5937cbc6bd057 100644
--- a/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
+++ b/drivers/net/ethernet/wangxun/txgbe/txgbe_type.h
@@ -77,11 +77,13 @@
 #define TXGBE_PX_MISC_ETH_LK                    BIT(18)
 #define TXGBE_PX_MISC_ETH_AN                    BIT(19)
 #define TXGBE_PX_MISC_INT_ERR                   BIT(20)
+#define TXGBE_PX_MISC_IC_VF_MBOX                BIT(23)
 #define TXGBE_PX_MISC_GPIO                      BIT(26)
 #define TXGBE_PX_MISC_IEN_MASK                            \
 	(TXGBE_PX_MISC_ETH_LKDN | TXGBE_PX_MISC_DEV_RST | \
 	 TXGBE_PX_MISC_ETH_EVENT | TXGBE_PX_MISC_ETH_LK | \
-	 TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR)
+	 TXGBE_PX_MISC_ETH_AN | TXGBE_PX_MISC_INT_ERR | \
+	 TXGBE_PX_MISC_IC_VF_MBOX)
 
 /* Port cfg registers */
 #define TXGBE_CFG_PORT_ST                       0x14404
@@ -174,6 +176,8 @@
 #define TXGBE_SP_RX_PB_SIZE     512
 #define TXGBE_SP_TDB_PB_SZ      (160 * 1024) /* 160KB Packet Buffer */
 
+#define TXGBE_MAX_VFS_DRV_LIMIT                 63
+
 #define TXGBE_DEFAULT_ATR_SAMPLE_RATE           20
 
 /* Software ATR hash keys */
@@ -348,6 +352,7 @@ struct txgbe {
 	struct clk *clk;
 	struct gpio_chip *gpio;
 	unsigned int link_irq;
+	u32 eicr;
 
 	/* flow director */
 	struct hlist_head fdir_filter_list;

From 2f76c62dd64a9a4f7a4541ffd7155a6f43eeb7fd Mon Sep 17 00:00:00 2001
From: Xiaomeng Zhang <zhangxiaomeng13@huawei.com>
Date: Fri, 14 Mar 2025 01:19:46 +0000
Subject: [PATCH 2465/2753] lockdep: Fix upper limit for LOCKDEP_BITS configs

The upper limit that was initially setup for LOCKDEP_BITS configs
is too high (24 bit shift), which causes the kernel image size to exceed
KERNEL_IMAGE_SIZE (1024MB) limit. When LOCKDEP_BITS is set to 24,
the kernel image size grows to 1562.19MB.

Adjust LOCKDEP_BITS to 22, which results in a kernel image size of
888.19MB, keeping it under the KERNEL_IMAGE_SIZE limit while still
maintaining adequate debug information capacity.

This change prevents the linker error:
  ld: kernel image bigger than KERNEL_IMAGE_SIZE

Fixes: e638072e6172 ("lockdep: Fix upper limit for LOCKDEP_*_BITS configs")
Signed-off-by: Xiaomeng Zhang <zhangxiaomeng13@huawei.com>
Signed-off-by: NipaLocal <nipa@local>
---
 lib/Kconfig.debug | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index fbd42f5b8e1e7..b63d0420f1f93 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1504,7 +1504,7 @@ config LOCKDEP_SMALL
 config LOCKDEP_BITS
 	int "Size for MAX_LOCKDEP_ENTRIES (as Nth power of 2)"
 	depends on LOCKDEP && !LOCKDEP_SMALL
-	range 10 24
+	range 10 22
 	default 15
 	help
 	  Try increasing this value if you hit "BUG: MAX_LOCKDEP_ENTRIES too low!" message.

From 90d11e3e033b68c3c7e61145933141a62538d378 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Fri, 14 Mar 2025 17:00:41 +0800
Subject: [PATCH 2466/2753] net: mctp: Remove unnecessary cast in mctp_cb

The void * cast in mctp_cb is unnecessary as it's already been done
at the start of the function.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: Jeremy Kerr <jk@codeconstruct.com.au>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/mctp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/mctp.h b/include/net/mctp.h
index 1ecbff7116f62..07d458990113d 100644
--- a/include/net/mctp.h
+++ b/include/net/mctp.h
@@ -212,7 +212,7 @@ static inline struct mctp_skb_cb *mctp_cb(struct sk_buff *skb)
 
 	BUILD_BUG_ON(sizeof(struct mctp_skb_cb) > sizeof(skb->cb));
 	WARN_ON(cb->magic != 0x4d435450);
-	return (void *)(skb->cb);
+	return cb;
 }
 
 /* If CONFIG_MCTP_FLOWS, we may add one of these as a SKB extension,

From daac44512abb82cd4ea9f045fdd4179994c4cab9 Mon Sep 17 00:00:00 2001
From: Luigi Leonardi <leonardi@redhat.com>
Date: Fri, 14 Mar 2025 10:27:33 +0100
Subject: [PATCH 2467/2753] vsock/test: Add test for null ptr deref when
 transport changes

Add a new test to ensure that when the transport changes a null pointer
dereference does not occur[1].

Note that this test does not fail, but it may hang on the client side if
it triggers a kernel oops.

This works by creating a socket, trying to connect to a server, and then
executing a second connect operation on the same socket but to a
different CID (0). This triggers a transport change. If the connect
operation is interrupted by a signal, this could cause a null-ptr-deref.

Since this bug is non-deterministic, we need to try several times. It
is safe to assume that the bug will show up within the timeout period.

If there is a G2H transport loaded in the system, the bug is not
triggered and this test will always pass.

[1]https://lore.kernel.org/netdev/Z2LvdTTQR7dBmPb5@v4bel-B760M-AORUS-ELITE-AX/

Suggested-by: Hyunwoo Kim <v4bel@theori.io>
Suggested-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: Luigi Leonardi <leonardi@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/vsock/Makefile     |   1 +
 tools/testing/vsock/vsock_test.c | 101 +++++++++++++++++++++++++++++++
 2 files changed, 102 insertions(+)

diff --git a/tools/testing/vsock/Makefile b/tools/testing/vsock/Makefile
index 6e0b4e95e2305..88211fd132d23 100644
--- a/tools/testing/vsock/Makefile
+++ b/tools/testing/vsock/Makefile
@@ -5,6 +5,7 @@ vsock_test: vsock_test.o vsock_test_zerocopy.o timeout.o control.o util.o msg_ze
 vsock_diag_test: vsock_diag_test.o timeout.o control.o util.o
 vsock_perf: vsock_perf.o msg_zerocopy_common.o
 
+vsock_test: LDLIBS = -lpthread
 vsock_uring_test: LDLIBS = -luring
 vsock_uring_test: control.o util.o vsock_uring_test.o timeout.o msg_zerocopy_common.o
 
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index d0f6d253ac72d..d2820a67403c9 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -23,6 +23,7 @@
 #include <sys/ioctl.h>
 #include <linux/sockios.h>
 #include <linux/time64.h>
+#include <pthread.h>
 
 #include "vsock_test_zerocopy.h"
 #include "timeout.h"
@@ -1788,6 +1789,101 @@ static void test_stream_connect_retry_server(const struct test_opts *opts)
 	close(fd);
 }
 
+static void *test_stream_transport_change_thread(void *vargp)
+{
+	pid_t *pid = (pid_t *)vargp;
+
+	/* We want this thread to terminate as soon as possible */
+	if (pthread_setcanceltype(PTHREAD_CANCEL_ASYNCHRONOUS, NULL)) {
+		perror("pthread_setcanceltype");
+		exit(EXIT_FAILURE);
+	}
+
+	while (true) {
+		if (kill(*pid, SIGUSR1) < 0) {
+			perror("kill");
+			exit(EXIT_FAILURE);
+		}
+	}
+	return NULL;
+}
+
+static void test_transport_change_signal_handler(int signal)
+{
+	/* We need a custom handler for SIGUSR1 as the default one terminates the process. */
+}
+
+static void test_stream_transport_change_client(const struct test_opts *opts)
+{
+	__sighandler_t old_handler;
+	pid_t pid = getpid();
+	pthread_t thread_id;
+	time_t tout;
+
+	old_handler = signal(SIGUSR1, test_transport_change_signal_handler);
+	if (old_handler == SIG_ERR) {
+		perror("signal");
+		exit(EXIT_FAILURE);
+	}
+
+	if (pthread_create(&thread_id, NULL, test_stream_transport_change_thread, &pid)) {
+		perror("pthread_create");
+		exit(EXIT_FAILURE);
+	}
+
+	tout = current_nsec() + TIMEOUT * NSEC_PER_SEC;
+	do {
+		struct sockaddr_vm sa = {
+			.svm_family = AF_VSOCK,
+			.svm_cid = opts->peer_cid,
+			.svm_port = opts->peer_port,
+		};
+		int s;
+
+		s = socket(AF_VSOCK, SOCK_STREAM, 0);
+		if (s < 0) {
+			perror("socket");
+			exit(EXIT_FAILURE);
+		}
+
+		connect(s, (struct sockaddr *)&sa, sizeof(sa));
+
+		/* Set CID to 0 cause a transport change. */
+		sa.svm_cid = 0;
+		connect(s, (struct sockaddr *)&sa, sizeof(sa));
+
+		close(s);
+	} while (current_nsec() < tout);
+
+	if (pthread_cancel(thread_id)) {
+		perror("pthread_cancel");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Wait for the thread to terminate */
+	if (pthread_join(thread_id, NULL)) {
+		perror("pthread_join");
+		exit(EXIT_FAILURE);
+	}
+
+	/* Restore the old handler */
+	if (signal(SIGUSR1, old_handler) == SIG_ERR) {
+		perror("signal");
+		exit(EXIT_FAILURE);
+	}
+}
+
+static void test_stream_transport_change_server(const struct test_opts *opts)
+{
+	time_t tout = current_nsec() + TIMEOUT * NSEC_PER_SEC;
+
+	do {
+		int s = vsock_stream_listen(VMADDR_CID_ANY, opts->peer_port);
+
+		close(s);
+	} while (current_nsec() < tout);
+}
+
 static void test_stream_linger_client(const struct test_opts *opts)
 {
 	struct linger optval = {
@@ -1984,6 +2080,11 @@ static struct test_case test_cases[] = {
 		.run_client = test_stream_linger_client,
 		.run_server = test_stream_linger_server,
 	},
+	{
+		.name = "SOCK_STREAM transport change null-ptr-deref",
+		.run_client = test_stream_transport_change_client,
+		.run_server = test_stream_transport_change_server,
+	},
 	{},
 };
 

From 881a66f00922f11f29ec24907b06e5d7b00d7c4a Mon Sep 17 00:00:00 2001
From: Justin Lai <justinlai0215@realtek.com>
Date: Fri, 14 Mar 2025 17:40:21 +0800
Subject: [PATCH 2468/2753] rtase: Add ndo_setup_tc support for CBS offload in
 traffic control setup

Add support for ndo_setup_tc to enable CBS offload functionality as
part of traffic control configuration for network devices.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/realtek/rtase/rtase.h    | 15 ++++++
 .../net/ethernet/realtek/rtase/rtase_main.c   | 49 +++++++++++++++++++
 2 files changed, 64 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase.h b/drivers/net/ethernet/realtek/rtase/rtase.h
index 2bbfcad613abb..498cfe4d0cac3 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase.h
+++ b/drivers/net/ethernet/realtek/rtase/rtase.h
@@ -170,6 +170,7 @@ enum rtase_registers {
 #define RTASE_TC_MODE_MASK GENMASK(11, 10)
 
 	RTASE_TOKSEL      = 0x2046,
+	RTASE_TXQCRDT_0   = 0x2500,
 	RTASE_RFIFONFULL  = 0x4406,
 	RTASE_INT_MITI_TX = 0x0A00,
 	RTASE_INT_MITI_RX = 0x0A80,
@@ -259,6 +260,12 @@ union rtase_rx_desc {
 #define RTASE_VLAN_TAG_MASK     GENMASK(15, 0)
 #define RTASE_RX_PKT_SIZE_MASK  GENMASK(13, 0)
 
+/* txqos hardware definitions */
+#define RTASE_1T_CLOCK            64
+#define RTASE_1T_POWER            10000000
+#define RTASE_IDLESLOPE_INT_SHIFT 25
+#define RTASE_IDLESLOPE_INT_MASK  GENMASK(31, 25)
+
 #define RTASE_IVEC_NAME_SIZE (IFNAMSIZ + 10)
 
 struct rtase_int_vector {
@@ -294,6 +301,13 @@ struct rtase_ring {
 	u64 alloc_fail;
 };
 
+struct rtase_txqos {
+	int hicredit;
+	int locredit;
+	int idleslope;
+	int sendslope;
+};
+
 struct rtase_stats {
 	u64 tx_dropped;
 	u64 rx_dropped;
@@ -313,6 +327,7 @@ struct rtase_private {
 
 	struct page_pool *page_pool;
 	struct rtase_ring tx_ring[RTASE_NUM_TX_QUEUE];
+	struct rtase_txqos tx_qos[RTASE_NUM_TX_QUEUE];
 	struct rtase_ring rx_ring[RTASE_NUM_RX_QUEUE];
 	struct rtase_counters *tally_vaddr;
 	dma_addr_t tally_paddr;
diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2aacc1996796d..2a61cd192026d 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1661,6 +1661,54 @@ static void rtase_get_stats64(struct net_device *dev,
 	stats->rx_length_errors = tp->stats.rx_length_errors;
 }
 
+static void rtase_set_hw_cbs(const struct rtase_private *tp, u32 queue)
+{
+	u32 idle = tp->tx_qos[queue].idleslope * RTASE_1T_CLOCK;
+	u32 val, i;
+
+	val = u32_encode_bits(idle / RTASE_1T_POWER, RTASE_IDLESLOPE_INT_MASK);
+	idle %= RTASE_1T_POWER;
+
+	for (i = 1; i <= RTASE_IDLESLOPE_INT_SHIFT; i++) {
+		idle *= 2;
+		if ((idle / RTASE_1T_POWER) == 1)
+			val |= BIT(RTASE_IDLESLOPE_INT_SHIFT - i);
+
+		idle %= RTASE_1T_POWER;
+	}
+
+	rtase_w32(tp, RTASE_TXQCRDT_0 + queue * 4, val);
+}
+
+static void rtase_setup_tc_cbs(struct rtase_private *tp,
+			       const struct tc_cbs_qopt_offload *qopt)
+{
+	u32 queue = qopt->queue;
+
+	tp->tx_qos[queue].hicredit = qopt->hicredit;
+	tp->tx_qos[queue].locredit = qopt->locredit;
+	tp->tx_qos[queue].idleslope = qopt->idleslope;
+	tp->tx_qos[queue].sendslope = qopt->sendslope;
+
+	rtase_set_hw_cbs(tp, queue);
+}
+
+static int rtase_setup_tc(struct net_device *dev, enum tc_setup_type type,
+			  void *type_data)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+
+	switch (type) {
+	case TC_SETUP_QDISC_CBS:
+		rtase_setup_tc_cbs(tp, type_data);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
 static netdev_features_t rtase_fix_features(struct net_device *dev,
 					    netdev_features_t features)
 {
@@ -1696,6 +1744,7 @@ static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_change_mtu = rtase_change_mtu,
 	.ndo_tx_timeout = rtase_tx_timeout,
 	.ndo_get_stats64 = rtase_get_stats64,
+	.ndo_setup_tc = rtase_setup_tc,
 	.ndo_fix_features = rtase_fix_features,
 	.ndo_set_features = rtase_set_features,
 };

From 04bc43a9d4439399188e5301b32310fd0f745df5 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 14 Mar 2025 12:06:31 +0200
Subject: [PATCH 2469/2753] MAINTAINERS: update bridge entry

Roopa has decided to withdraw as a bridge maintainer and Ido has agreed to
step up and co-maintain the bridge with me. He has been very helpful in
bridge patch reviews and has contributed a lot to the bridge over the
years. Add an entry for Roopa to CREDITS and also add bridge's headers
to its MAINTAINERS entry.

Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 CREDITS     | 4 ++++
 MAINTAINERS | 4 +++-
 2 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/CREDITS b/CREDITS
index 53d11a46fd698..d71d42c30044b 100644
--- a/CREDITS
+++ b/CREDITS
@@ -3233,6 +3233,10 @@ N: Rui Prior
 E: rprior@inescn.pt
 D: ATM device driver for NICStAR based cards
 
+N: Roopa Prabhu
+E: roopa@nvidia.com
+D: Bridge co-maintainer, vxlan and networking contributor
+
 N: Stefan Probst
 E: sp@caldera.de
 D: The Linux Support Team Erlangen, 1993-97
diff --git a/MAINTAINERS b/MAINTAINERS
index b3a23aceeb641..3594b6c6e6107 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8593,12 +8593,14 @@ F:	Documentation/networking/devlink/etas_es58x.rst
 F:	drivers/net/can/usb/etas_es58x/
 
 ETHERNET BRIDGE
-M:	Roopa Prabhu <roopa@nvidia.com>
 M:	Nikolay Aleksandrov <razor@blackwall.org>
+M:	Ido Schimmel <idosch@nvidia.com>
 L:	bridge@lists.linux.dev
 L:	netdev@vger.kernel.org
 S:	Maintained
 W:	http://www.linuxfoundation.org/en/Net:Bridge
+F:	include/linux/if_bridge.h
+F:	include/uapi/linux/if_bridge.h
 F:	include/linux/netfilter_bridge/
 F:	net/bridge/
 

From b83e6235c0c535d0da0077dfacea64b9d3be1e1a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 14 Mar 2025 11:10:19 +0100
Subject: [PATCH 2470/2753] page_pool: Move pp_magic check into helper
 functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Since we are about to stash some more information into the pp_magic
field, let's move the magic signature checks into a pair of helper
functions so it can be changed in one place.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c   |  4 ++--
 include/net/page_pool/types.h                  | 18 ++++++++++++++++++
 mm/page_alloc.c                                |  9 +++------
 net/core/netmem_priv.h                         |  5 +++++
 net/core/skbuff.c                              | 16 ++--------------
 net/core/xdp.c                                 |  4 ++--
 6 files changed, 32 insertions(+), 24 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 6f3094a479e1e..70c6f0b2abb92 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -706,8 +706,8 @@ static void mlx5e_free_xdpsq_desc(struct mlx5e_xdpsq *sq,
 				xdpi = mlx5e_xdpi_fifo_pop(xdpi_fifo);
 				page = xdpi.page.page;
 
-				/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-				 * as we know this is a page_pool page.
+				/* No need to check page_pool_page_is_pp() as we
+				 * know this is a page_pool page.
 				 */
 				page_pool_recycle_direct(page->pp, page);
 			} while (++n < num);
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 36eb57d73abc6..df0d3c1608929 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -54,6 +54,14 @@ struct pp_alloc_cache {
 	netmem_ref cache[PP_ALLOC_CACHE_SIZE];
 };
 
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page.
+ * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
+ * the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~0x3UL
+
 /**
  * struct page_pool_params - page pool parameters
  * @fast:	params accessed frequently on hotpath
@@ -264,6 +272,11 @@ void page_pool_destroy(struct page_pool *pool);
 void page_pool_use_xdp_mem(struct page_pool *pool, void (*disconnect)(void *),
 			   const struct xdp_mem_info *mem);
 void page_pool_put_netmem_bulk(netmem_ref *data, u32 count);
+
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
 #else
 static inline void page_pool_destroy(struct page_pool *pool)
 {
@@ -278,6 +291,11 @@ static inline void page_pool_use_xdp_mem(struct page_pool *pool,
 static inline void page_pool_put_netmem_bulk(netmem_ref *data, u32 count)
 {
 }
+
+static inline bool page_pool_page_is_pp(struct page *page)
+{
+	return false;
+}
 #endif
 
 void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 542d25f77be80..3535ee76afe94 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -55,6 +55,7 @@
 #include <linux/delayacct.h>
 #include <linux/cacheinfo.h>
 #include <linux/pgalloc_tag.h>
+#include <net/page_pool/types.h>
 #include <asm/div64.h>
 #include "internal.h"
 #include "shuffle.h"
@@ -872,9 +873,7 @@ static inline bool page_expected_state(struct page *page,
 #ifdef CONFIG_MEMCG
 			page->memcg_data |
 #endif
-#ifdef CONFIG_PAGE_POOL
-			((page->pp_magic & ~0x3UL) == PP_SIGNATURE) |
-#endif
+			page_pool_page_is_pp(page) |
 			(page->flags & check_flags)))
 		return false;
 
@@ -901,10 +900,8 @@ static const char *page_bad_reason(struct page *page, unsigned long flags)
 	if (unlikely(page->memcg_data))
 		bad_reason = "page still charged to cgroup";
 #endif
-#ifdef CONFIG_PAGE_POOL
-	if (unlikely((page->pp_magic & ~0x3UL) == PP_SIGNATURE))
+	if (unlikely(page_pool_page_is_pp(page)))
 		bad_reason = "page_pool leak";
-#endif
 	return bad_reason;
 }
 
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index 7eadb8393e002..f33162fd281c2 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -18,6 +18,11 @@ static inline void netmem_clear_pp_magic(netmem_ref netmem)
 	__netmem_clear_lsb(netmem)->pp_magic = 0;
 }
 
+static inline bool netmem_is_pp(netmem_ref netmem)
+{
+	return (netmem_get_pp_magic(netmem) & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+
 static inline void netmem_set_pp(netmem_ref netmem, struct page_pool *pool)
 {
 	__netmem_clear_lsb(netmem)->pp = pool;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ab8acb737b932..a64d777488e40 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -893,11 +893,6 @@ static void skb_clone_fraglist(struct sk_buff *skb)
 		skb_get(list);
 }
 
-static bool is_pp_netmem(netmem_ref netmem)
-{
-	return (netmem_get_pp_magic(netmem) & ~0x3UL) == PP_SIGNATURE;
-}
-
 int skb_pp_cow_data(struct page_pool *pool, struct sk_buff **pskb,
 		    unsigned int headroom)
 {
@@ -995,14 +990,7 @@ bool napi_pp_put_page(netmem_ref netmem)
 {
 	netmem = netmem_compound_head(netmem);
 
-	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
-	 * in order to preserve any existing bits, such as bit 0 for the
-	 * head page of compound page and bit 1 for pfmemalloc page, so
-	 * mask those bits for freeing side when doing below checking,
-	 * and page_is_pfmemalloc() is checked in __page_pool_put_page()
-	 * to avoid recycling the pfmemalloc page.
-	 */
-	if (unlikely(!is_pp_netmem(netmem)))
+	if (unlikely(!netmem_is_pp(netmem)))
 		return false;
 
 	page_pool_put_full_netmem(netmem_get_pp(netmem), netmem, false);
@@ -1042,7 +1030,7 @@ static int skb_pp_frag_ref(struct sk_buff *skb)
 
 	for (i = 0; i < shinfo->nr_frags; i++) {
 		head_netmem = netmem_compound_head(shinfo->frags[i].netmem);
-		if (likely(is_pp_netmem(head_netmem)))
+		if (likely(netmem_is_pp(head_netmem)))
 			page_pool_ref_netmem(head_netmem);
 		else
 			page_ref_inc(netmem_to_page(head_netmem));
diff --git a/net/core/xdp.c b/net/core/xdp.c
index f86eedad586a7..0ba73943c6eed 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -437,8 +437,8 @@ void __xdp_return(netmem_ref netmem, enum xdp_mem_type mem_type,
 		netmem = netmem_compound_head(netmem);
 		if (napi_direct && xdp_return_frame_no_direct())
 			napi_direct = false;
-		/* No need to check ((page->pp_magic & ~0x3UL) == PP_SIGNATURE)
-		 * as mem->type knows this a page_pool page
+		/* No need to check netmem_is_pp() as mem->type knows this a
+		 * page_pool page
 		 */
 		page_pool_put_full_netmem(netmem_get_pp(netmem), netmem,
 					  napi_direct);

From 51cddc7cf3fe9926cd2c1ac68112a39fc9e6e9df Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 14 Mar 2025 11:10:20 +0100
Subject: [PATCH 2471/2753] page_pool: Turn dma_sync and dma_sync_cpu fields
 into a bitmap
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Change the single-bit booleans for dma_sync into an unsigned long with
BIT() definitions so that a subsequent patch can write them both with a
singe WRITE_ONCE() on teardown. Also move the check for the sync_cpu
side into __page_pool_dma_sync_for_cpu() so it can be disabled for
non-netmem providers as well.

Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/page_pool/helpers.h | 6 +++---
 include/net/page_pool/types.h   | 8 ++++++--
 net/core/devmem.c               | 3 +--
 net/core/page_pool.c            | 9 +++++----
 4 files changed, 15 insertions(+), 11 deletions(-)

diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 582a3d00cbe23..7ed32bde4b894 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -443,6 +443,9 @@ static inline void __page_pool_dma_sync_for_cpu(const struct page_pool *pool,
 						const dma_addr_t dma_addr,
 						u32 offset, u32 dma_sync_size)
 {
+	if (!(READ_ONCE(pool->dma_sync) & PP_DMA_SYNC_CPU))
+		return;
+
 	dma_sync_single_range_for_cpu(pool->p.dev, dma_addr,
 				      offset + pool->p.offset, dma_sync_size,
 				      page_pool_get_dma_dir(pool));
@@ -473,9 +476,6 @@ page_pool_dma_sync_netmem_for_cpu(const struct page_pool *pool,
 				  const netmem_ref netmem, u32 offset,
 				  u32 dma_sync_size)
 {
-	if (!pool->dma_sync_for_cpu)
-		return;
-
 	__page_pool_dma_sync_for_cpu(pool,
 				     page_pool_get_dma_addr_netmem(netmem),
 				     offset, dma_sync_size);
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index df0d3c1608929..fbe34024b2006 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -33,6 +33,10 @@
 #define PP_FLAG_ALL		(PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV | \
 				 PP_FLAG_SYSTEM_POOL | PP_FLAG_ALLOW_UNREADABLE_NETMEM)
 
+/* bit values used in pp->dma_sync */
+#define PP_DMA_SYNC_DEV	BIT(0)
+#define PP_DMA_SYNC_CPU	BIT(1)
+
 /*
  * Fast allocation side cache array/stack
  *
@@ -175,12 +179,12 @@ struct page_pool {
 
 	bool has_init_callback:1;	/* slow::init_callback is set */
 	bool dma_map:1;			/* Perform DMA mapping */
-	bool dma_sync:1;		/* Perform DMA sync for device */
-	bool dma_sync_for_cpu:1;	/* Perform DMA sync for cpu */
 #ifdef CONFIG_PAGE_POOL_STATS
 	bool system:1;			/* This is a global percpu pool */
 #endif
 
+	unsigned long dma_sync;
+
 	__cacheline_group_begin_aligned(frag, PAGE_POOL_FRAG_GROUP_ALIGN);
 	long frag_users;
 	netmem_ref frag_page;
diff --git a/net/core/devmem.c b/net/core/devmem.c
index 6802e82a4d03b..955d392d707b1 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -340,8 +340,7 @@ int mp_dmabuf_devmem_init(struct page_pool *pool)
 	/* dma-buf dma addresses do not need and should not be used with
 	 * dma_sync_for_cpu/device. Force disable dma_sync.
 	 */
-	pool->dma_sync = false;
-	pool->dma_sync_for_cpu = false;
+	pool->dma_sync = 0;
 
 	if (pool->p.order != 0)
 		return -E2BIG;
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index acef1fcd8ddcf..d51ca4389dd62 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -203,7 +203,7 @@ static int page_pool_init(struct page_pool *pool,
 	memcpy(&pool->slow, &params->slow, sizeof(pool->slow));
 
 	pool->cpuid = cpuid;
-	pool->dma_sync_for_cpu = true;
+	pool->dma_sync = PP_DMA_SYNC_CPU;
 
 	/* Validate only known flags were used */
 	if (pool->slow.flags & ~PP_FLAG_ALL)
@@ -238,7 +238,7 @@ static int page_pool_init(struct page_pool *pool,
 		if (!pool->p.max_len)
 			return -EINVAL;
 
-		pool->dma_sync = true;
+		pool->dma_sync |= PP_DMA_SYNC_DEV;
 
 		/* pool->p.offset has to be set according to the address
 		 * offset used by the DMA engine to start copying rx data
@@ -291,7 +291,7 @@ static int page_pool_init(struct page_pool *pool,
 	}
 
 	if (pool->mp_ops) {
-		if (!pool->dma_map || !pool->dma_sync)
+		if (!pool->dma_map || !(pool->dma_sync & PP_DMA_SYNC_DEV))
 			return -EOPNOTSUPP;
 
 		if (WARN_ON(!is_kernel_rodata((unsigned long)pool->mp_ops))) {
@@ -466,7 +466,8 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 			      netmem_ref netmem,
 			      u32 dma_sync_size)
 {
-	if (pool->dma_sync && dma_dev_need_sync(pool->p.dev))
+	if ((READ_ONCE(pool->dma_sync) & PP_DMA_SYNC_DEV) &&
+	    dma_dev_need_sync(pool->p.dev))
 		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
 }
 

From a9301be52dae9b6bdb340c182d08d0565f605b96 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Toke=20H=C3=B8iland-J=C3=B8rgensen?= <toke@redhat.com>
Date: Fri, 14 Mar 2025 11:10:21 +0100
Subject: [PATCH 2472/2753] page_pool: Track DMA-mapped pages and unmap them
 when destroying the pool
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When enabling DMA mapping in page_pool, pages are kept DMA mapped until
they are released from the pool, to avoid the overhead of re-mapping the
pages every time they are used. This causes resource leaks and/or
crashes when there are pages still outstanding while the device is torn
down, because page_pool will attempt an unmap through a non-existent DMA
device on the subsequent page return.

To fix this, implement a simple tracking of outstanding DMA-mapped pages
in page pool using an xarray. This was first suggested by Mina[0], and
turns out to be fairly straight forward: We simply store pointers to
pages directly in the xarray with xa_alloc() when they are first DMA
mapped, and remove them from the array on unmap. Then, when a page pool
is torn down, it can simply walk the xarray and unmap all pages still
present there before returning, which also allows us to get rid of the
get/put_device() calls in page_pool. Using xa_cmpxchg(), no additional
synchronisation is needed, as a page will only ever be unmapped once.

To avoid having to walk the entire xarray on unmap to find the page
reference, we stash the ID assigned by xa_alloc() into the page
structure itself, using the upper bits of the pp_magic field. This
requires a couple of defines to avoid conflicting with the
POINTER_POISON_DELTA define, but this is all evaluated at compile-time,
so does not affect run-time performance. The bitmap calculations in this
patch gives the following number of bits for different architectures:

- 24 bits on 32-bit architectures
- 21 bits on PPC64 (because of the definition of ILLEGAL_POINTER_VALUE)
- 32 bits on other 64-bit architectures

Since all the tracking is performed on DMA map/unmap, no additional code
is needed in the fast path, meaning the performance overhead of this
tracking is negligible. A micro-benchmark shows that the total overhead
of using xarray for this purpose is about 400 ns (39 cycles(tsc) 395.218
ns; sum for both map and unmap[1]). Since this cost is only paid on DMA
map and unmap, it seems like an acceptable cost to fix the late unmap
issue. Further optimisation can narrow the cases where this cost is
paid (for instance by eliding the tracking when DMA map/unmap is a
no-op).

The extra memory needed to track the pages is neatly encapsulated inside
xarray, which uses the 'struct xa_node' structure to track items. This
structure is 576 bytes long, with slots for 64 items, meaning that a
full node occurs only 9 bytes of overhead per slot it tracks (in
practice, it probably won't be this efficient, but in any case it should
be an acceptable overhead).

[0] https://lore.kernel.org/all/CAHS8izPg7B5DwKfSuzz-iOop_YRbk3Sd6Y4rX7KBG9DcVJcyWg@mail.gmail.com/
[1] https://lore.kernel.org/r/ae07144c-9295-4c9d-a400-153bb689fe9e@huawei.com

Reported-by: Yonglong Liu <liuyonglong@huawei.com>
Closes: https://lore.kernel.org/r/8743264a-9700-4227-a556-5f931c720211@huawei.com
Fixes: ff7d6b27f894 ("page_pool: refurbish version of page_pool code")
Suggested-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Jesper Dangaard Brouer <hawk@kernel.org>
Tested-by: Jesper Dangaard Brouer <hawk@kernel.org>
Tested-by: Qiuling Ren <qren@redhat.com>
Tested-by: Yuying Ma <yuma@redhat.com>
Signed-off-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/page_pool/types.h | 36 ++++++++++++++++--
 net/core/netmem_priv.h        | 28 +++++++++++++-
 net/core/page_pool.c          | 72 ++++++++++++++++++++++++++++++-----
 3 files changed, 121 insertions(+), 15 deletions(-)

diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index fbe34024b2006..1e187489d3927 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -6,6 +6,7 @@
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
 #include <linux/types.h>
+#include <linux/xarray.h>
 #include <net/netmem.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
@@ -58,13 +59,38 @@ struct pp_alloc_cache {
 	netmem_ref cache[PP_ALLOC_CACHE_SIZE];
 };
 
+/*
+ * DMA mapping IDs
+ *
+ * When DMA-mapping a page, we allocate an ID (from an xarray) and stash this in
+ * the upper bits of page->pp_magic. The number of bits available here is
+ * constrained by the size of an unsigned long, and the definition of
+ * PP_SIGNATURE.
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#define _PP_DMA_INDEX_BITS MIN(32, BITS_PER_LONG - PP_DMA_INDEX_SHIFT - 1)
+
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#if POISON_POINTER_DELTA > 0
+#define PP_DMA_INDEX_BITS MIN(_PP_DMA_INDEX_BITS, \
+			      __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
+#else
+#define PP_DMA_INDEX_BITS _PP_DMA_INDEX_BITS
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+				  PP_DMA_INDEX_SHIFT)
+#define PP_DMA_INDEX_LIMIT XA_LIMIT(1, BIT(PP_DMA_INDEX_BITS) - 1)
+
 /* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
  * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
- * the head page of compound page and bit 1 for pfmemalloc page.
- * page_is_pfmemalloc() is checked in __page_pool_put_page() to avoid recycling
- * the pfmemalloc page.
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
  */
-#define PP_MAGIC_MASK ~0x3UL
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
 
 /**
  * struct page_pool_params - page pool parameters
@@ -233,6 +259,8 @@ struct page_pool {
 	void *mp_priv;
 	const struct memory_provider_ops *mp_ops;
 
+	struct xarray dma_mapped;
+
 #ifdef CONFIG_PAGE_POOL_STATS
 	/* recycle stats are per-cpu to avoid locking */
 	struct page_pool_recycle_stats __percpu *recycle_stats;
diff --git a/net/core/netmem_priv.h b/net/core/netmem_priv.h
index f33162fd281c2..cd95394399b40 100644
--- a/net/core/netmem_priv.h
+++ b/net/core/netmem_priv.h
@@ -5,7 +5,7 @@
 
 static inline unsigned long netmem_get_pp_magic(netmem_ref netmem)
 {
-	return __netmem_clear_lsb(netmem)->pp_magic;
+	return __netmem_clear_lsb(netmem)->pp_magic & ~PP_DMA_INDEX_MASK;
 }
 
 static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
@@ -15,6 +15,8 @@ static inline void netmem_or_pp_magic(netmem_ref netmem, unsigned long pp_magic)
 
 static inline void netmem_clear_pp_magic(netmem_ref netmem)
 {
+	WARN_ON_ONCE(__netmem_clear_lsb(netmem)->pp_magic & PP_DMA_INDEX_MASK);
+
 	__netmem_clear_lsb(netmem)->pp_magic = 0;
 }
 
@@ -33,4 +35,28 @@ static inline void netmem_set_dma_addr(netmem_ref netmem,
 {
 	__netmem_clear_lsb(netmem)->dma_addr = dma_addr;
 }
+
+static inline unsigned long netmem_get_dma_index(netmem_ref netmem)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return 0;
+
+	magic = __netmem_clear_lsb(netmem)->pp_magic;
+
+	return (magic & PP_DMA_INDEX_MASK) >> PP_DMA_INDEX_SHIFT;
+}
+
+static inline void netmem_set_dma_index(netmem_ref netmem,
+					unsigned long id)
+{
+	unsigned long magic;
+
+	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
+		return;
+
+	magic = netmem_get_pp_magic(netmem) | (id << PP_DMA_INDEX_SHIFT);
+	__netmem_clear_lsb(netmem)->pp_magic = magic;
+}
 #endif
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index d51ca4389dd62..5612d72d483ca 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -226,6 +226,8 @@ static int page_pool_init(struct page_pool *pool,
 			return -EINVAL;
 
 		pool->dma_map = true;
+
+		xa_init_flags(&pool->dma_mapped, XA_FLAGS_ALLOC1);
 	}
 
 	if (pool->slow.flags & PP_FLAG_DMA_SYNC_DEV) {
@@ -275,9 +277,6 @@ static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
-	if (pool->dma_map)
-		get_device(pool->p.dev);
-
 	if (pool->slow.flags & PP_FLAG_ALLOW_UNREADABLE_NETMEM) {
 		/* We rely on rtnl_lock()ing to make sure netdev_rx_queue
 		 * configuration doesn't change while we're initializing
@@ -325,7 +324,7 @@ static void page_pool_uninit(struct page_pool *pool)
 	ptr_ring_cleanup(&pool->ring, NULL);
 
 	if (pool->dma_map)
-		put_device(pool->p.dev);
+		xa_destroy(&pool->dma_mapped);
 
 #ifdef CONFIG_PAGE_POOL_STATS
 	if (!pool->system)
@@ -471,9 +470,11 @@ page_pool_dma_sync_for_device(const struct page_pool *pool,
 		__page_pool_dma_sync_for_device(pool, netmem, dma_sync_size);
 }
 
-static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
+static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem, gfp_t gfp)
 {
 	dma_addr_t dma;
+	int err;
+	u32 id;
 
 	/* Setup DMA mapping: use 'struct page' area for storing DMA-addr
 	 * since dma_addr_t can be either 32 or 64 bits and does not always fit
@@ -487,15 +488,28 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
 	if (dma_mapping_error(pool->p.dev, dma))
 		return false;
 
-	if (page_pool_set_dma_addr_netmem(netmem, dma))
+	if (in_softirq())
+		err = xa_alloc(&pool->dma_mapped, &id, netmem_to_page(netmem),
+			       PP_DMA_INDEX_LIMIT, gfp);
+	else
+		err = xa_alloc_bh(&pool->dma_mapped, &id, netmem_to_page(netmem),
+				  PP_DMA_INDEX_LIMIT, gfp);
+	if (err) {
+		WARN_ONCE(1, "couldn't track DMA mapping, please report to netdev@");
+		goto unmap_failed;
+	}
+
+	if (page_pool_set_dma_addr_netmem(netmem, dma)) {
+		WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 		goto unmap_failed;
+	}
 
+	netmem_set_dma_index(netmem, id);
 	page_pool_dma_sync_for_device(pool, netmem, pool->p.max_len);
 
 	return true;
 
 unmap_failed:
-	WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
 	dma_unmap_page_attrs(pool->p.dev, dma,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
@@ -512,7 +526,7 @@ static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
 	if (unlikely(!page))
 		return NULL;
 
-	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page)))) {
+	if (pool->dma_map && unlikely(!page_pool_dma_map(pool, page_to_netmem(page), gfp))) {
 		put_page(page);
 		return NULL;
 	}
@@ -558,7 +572,7 @@ static noinline netmem_ref __page_pool_alloc_pages_slow(struct page_pool *pool,
 	 */
 	for (i = 0; i < nr_pages; i++) {
 		netmem = pool->alloc.cache[i];
-		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem))) {
+		if (dma_map && unlikely(!page_pool_dma_map(pool, netmem, gfp))) {
 			put_page(netmem_to_page(netmem));
 			continue;
 		}
@@ -660,6 +674,8 @@ void page_pool_clear_pp_info(netmem_ref netmem)
 static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 							 netmem_ref netmem)
 {
+	struct page *old, *page = netmem_to_page(netmem);
+	unsigned long id;
 	dma_addr_t dma;
 
 	if (!pool->dma_map)
@@ -668,6 +684,17 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 		 */
 		return;
 
+	id = netmem_get_dma_index(netmem);
+	if (!id)
+		return;
+
+	if (in_softirq())
+		old = xa_cmpxchg(&pool->dma_mapped, id, page, NULL, 0);
+	else
+		old = xa_cmpxchg_bh(&pool->dma_mapped, id, page, NULL, 0);
+	if (old != page)
+		return;
+
 	dma = page_pool_get_dma_addr_netmem(netmem);
 
 	/* When page is unmapped, it cannot be returned to our pool */
@@ -675,6 +702,7 @@ static __always_inline void __page_pool_release_page_dma(struct page_pool *pool,
 			     PAGE_SIZE << pool->p.order, pool->p.dma_dir,
 			     DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
 	page_pool_set_dma_addr_netmem(netmem, 0);
+	netmem_set_dma_index(netmem, 0);
 }
 
 /* Disconnects a page (from a page_pool).  API users can have a need
@@ -1084,8 +1112,32 @@ static void page_pool_empty_alloc_cache_once(struct page_pool *pool)
 
 static void page_pool_scrub(struct page_pool *pool)
 {
+	unsigned long id;
+	void *ptr;
+
 	page_pool_empty_alloc_cache_once(pool);
-	pool->destroy_cnt++;
+	if (!pool->destroy_cnt++ && pool->dma_map) {
+		if (pool->dma_sync) {
+			/* paired with READ_ONCE in
+			 * page_pool_dma_sync_for_device() and
+			 * __page_pool_dma_sync_for_cpu()
+			 */
+			WRITE_ONCE(pool->dma_sync, false);
+
+			/* Make sure all concurrent returns that may see the old
+			 * value of dma_sync (and thus perform a sync) have
+			 * finished before doing the unmapping below. Skip the
+			 * wait if the device doesn't actually need syncing, or
+			 * if there are no outstanding mapped pages.
+			 */
+			if (dma_dev_need_sync(pool->p.dev) &&
+			    !xa_empty(&pool->dma_mapped))
+				synchronize_net();
+		}
+
+		xa_for_each(&pool->dma_mapped, id, ptr)
+			__page_pool_release_page_dma(pool, page_to_netmem(ptr));
+	}
 
 	/* No more consumers should exist, but producers could still
 	 * be in-flight.

From f56ed75d6c0c5eca8c51f2a171fc91243c7bf01d Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 14 Mar 2025 16:49:59 +0100
Subject: [PATCH 2473/2753] net: airoha: fix CONFIG_DEBUG_FS check

The #if check causes a build failure when CONFIG_DEBUG_FS is turned
off:

In file included from drivers/net/ethernet/airoha/airoha_eth.c:17:
drivers/net/ethernet/airoha/airoha_eth.h:543:5: error: "CONFIG_DEBUG_FS" is not defined, evaluates to 0 [-Werror=undef]
  543 | #if CONFIG_DEBUG_FS
      |     ^~~~~~~~~~~~~~~

Replace it with the correct #ifdef.

Fixes: 3fe15c640f38 ("net: airoha: Introduce PPE debugfs support")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/airoha/airoha_eth.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index f66b9b736b944..60690b685710c 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -540,7 +540,7 @@ void airoha_ppe_deinit(struct airoha_eth *eth);
 struct airoha_foe_entry *airoha_ppe_foe_get_entry(struct airoha_ppe *ppe,
 						  u32 hash);
 
-#if CONFIG_DEBUG_FS
+#ifdef CONFIG_DEBUG_FS
 int airoha_ppe_debugfs_init(struct airoha_ppe *ppe);
 #else
 static inline int airoha_ppe_debugfs_init(struct airoha_ppe *ppe)

From 4d2f1bbfbac949a02f91fa84d8537171d048f3d3 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 14 Mar 2025 17:23:17 +0100
Subject: [PATCH 2474/2753] net: phy: sfp: Add support for SMBus module access

The SFP module's eeprom and internals are accessible through an i2c bus.

It is possible that the SFP might be connected to an SMBus-only
controller, such as the one found in some PHY devices in the VSC85xx
family.

Introduce a set of sfp read/write ops that are going to be used if the
i2c bus is only capable of doing smbus byte accesses.

As Single-byte SMBus transaction go against SFF-8472 and breaks the
atomicity for diagnostics data access, hwmon is disabled in the case
of SMBus access.

Moreover, as this may cause other instabilities, print a warning at
probe time to indicate that the setup may be unreliable because of the
hardware design.

As hwmon may be disabled for both broken EEPROM and smbus, the warnings
are udpated accordingly.

Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/sfp.c | 82 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 74 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/sfp.c b/drivers/net/phy/sfp.c
index c88217af44a14..cd7624a26cd47 100644
--- a/drivers/net/phy/sfp.c
+++ b/drivers/net/phy/sfp.c
@@ -234,6 +234,7 @@ struct sfp {
 	enum mdio_i2c_proto mdio_protocol;
 	struct phy_device *mod_phy;
 	const struct sff_data *type;
+	size_t i2c_max_block_size;
 	size_t i2c_block_size;
 	u32 max_power_mW;
 
@@ -691,14 +692,71 @@ static int sfp_i2c_write(struct sfp *sfp, bool a2, u8 dev_addr, void *buf,
 	return ret == ARRAY_SIZE(msgs) ? len : 0;
 }
 
-static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c)
+static int sfp_smbus_byte_read(struct sfp *sfp, bool a2, u8 dev_addr,
+			       void *buf, size_t len)
 {
-	if (!i2c_check_functionality(i2c, I2C_FUNC_I2C))
-		return -EINVAL;
+	u8 bus_addr = a2 ? 0x51 : 0x50;
+	union i2c_smbus_data smbus_data;
+	u8 *data = buf;
+	int ret;
+
+	while (len) {
+		ret = i2c_smbus_xfer(sfp->i2c, bus_addr, 0,
+				     I2C_SMBUS_READ, dev_addr,
+				     I2C_SMBUS_BYTE_DATA, &smbus_data);
+		if (ret < 0)
+			return ret;
+
+		*data = smbus_data.byte;
+
+		len--;
+		data++;
+		dev_addr++;
+	}
+
+	return data - (u8 *)buf;
+}
+
+static int sfp_smbus_byte_write(struct sfp *sfp, bool a2, u8 dev_addr,
+				void *buf, size_t len)
+{
+	u8 bus_addr = a2 ? 0x51 : 0x50;
+	union i2c_smbus_data smbus_data;
+	u8 *data = buf;
+	int ret;
 
+	while (len) {
+		smbus_data.byte = *data;
+		ret = i2c_smbus_xfer(sfp->i2c, bus_addr, 0,
+				     I2C_SMBUS_WRITE, dev_addr,
+				     I2C_SMBUS_BYTE_DATA, &smbus_data);
+		if (ret)
+			return ret;
+
+		len--;
+		data++;
+		dev_addr++;
+	}
+
+	return 0;
+}
+
+static int sfp_i2c_configure(struct sfp *sfp, struct i2c_adapter *i2c)
+{
 	sfp->i2c = i2c;
-	sfp->read = sfp_i2c_read;
-	sfp->write = sfp_i2c_write;
+
+	if (i2c_check_functionality(i2c, I2C_FUNC_I2C)) {
+		sfp->read = sfp_i2c_read;
+		sfp->write = sfp_i2c_write;
+		sfp->i2c_max_block_size = SFP_EEPROM_BLOCK_SIZE;
+	} else if (i2c_check_functionality(i2c, I2C_FUNC_SMBUS_BYTE_DATA)) {
+		sfp->read = sfp_smbus_byte_read;
+		sfp->write = sfp_smbus_byte_write;
+		sfp->i2c_max_block_size = 1;
+	} else {
+		sfp->i2c = NULL;
+		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -1594,7 +1652,7 @@ static void sfp_hwmon_probe(struct work_struct *work)
 	 */
 	if (sfp->i2c_block_size < 2) {
 		dev_info(sfp->dev,
-			 "skipping hwmon device registration due to broken EEPROM\n");
+			 "skipping hwmon device registration\n");
 		dev_info(sfp->dev,
 			 "diagnostic EEPROM area cannot be read atomically to guarantee data coherency\n");
 		return;
@@ -2201,7 +2259,7 @@ static int sfp_sm_mod_probe(struct sfp *sfp, bool report)
 	u8 check;
 	int ret;
 
-	sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE;
+	sfp->i2c_block_size = sfp->i2c_max_block_size;
 
 	ret = sfp_read(sfp, false, 0, &id.base, sizeof(id.base));
 	if (ret < 0) {
@@ -2941,7 +2999,6 @@ static struct sfp *sfp_alloc(struct device *dev)
 		return ERR_PTR(-ENOMEM);
 
 	sfp->dev = dev;
-	sfp->i2c_block_size = SFP_EEPROM_BLOCK_SIZE;
 
 	mutex_init(&sfp->sm_mutex);
 	mutex_init(&sfp->st_mutex);
@@ -3115,6 +3172,15 @@ static int sfp_probe(struct platform_device *pdev)
 	if (!sfp->sfp_bus)
 		return -ENOMEM;
 
+	if (sfp->i2c_max_block_size < 2)
+		dev_warn(sfp->dev,
+			 "Please note:\n"
+			 "This SFP cage is accessed via an SMBus only capable of single byte\n"
+			 "transactions. Some features are disabled, other may be unreliable or\n"
+			 "sporadically fail. Use with caution. There is nothing that the kernel\n"
+			 "or community can do to fix it, the kernel will try best efforts. Please\n"
+			 "verify any problems on hardware that supports multi-byte I2C transactions.\n");
+
 	sfp_debugfs_init(sfp);
 
 	return 0;

From d02c0a92a9fe75f7f6664d7b3ae895423d8a7ff2 Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 14 Mar 2025 17:23:18 +0100
Subject: [PATCH 2475/2753] net: mdio: mdio-i2c: Add support for single-byte
 SMBus operations

PHYs that are within copper SFP modules have their MDIO bus accessible
through address 0x56 (usually) on the i2c bus. The MDIO-I2C bridge is
desgned for 16 bits accesses, but we can also perform 8bits accesses by
reading/writing the high and low bytes sequentially.

This commit adds support for this type of accesses, thus supporting
smbus controllers such as the one in the VSC8552.

This was only tested on Copper SFP modules that embed a Marvell 88e1111
PHY.

Tested-by: Sean Anderson <sean.anderson@linux.dev>
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/mdio/mdio-i2c.c | 79 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 78 insertions(+), 1 deletion(-)

diff --git a/drivers/net/mdio/mdio-i2c.c b/drivers/net/mdio/mdio-i2c.c
index da2001ea1f993..202f486e71f1a 100644
--- a/drivers/net/mdio/mdio-i2c.c
+++ b/drivers/net/mdio/mdio-i2c.c
@@ -106,6 +106,62 @@ static int i2c_mii_write_default_c22(struct mii_bus *bus, int phy_id, int reg,
 	return i2c_mii_write_default_c45(bus, phy_id, -1, reg, val);
 }
 
+static int smbus_byte_mii_read_default_c22(struct mii_bus *bus, int phy_id,
+					   int reg)
+{
+	struct i2c_adapter *i2c = bus->priv;
+	union i2c_smbus_data smbus_data;
+	int val = 0, ret;
+
+	if (!i2c_mii_valid_phy_id(phy_id))
+		return 0;
+
+	ret = i2c_smbus_xfer(i2c, i2c_mii_phy_addr(phy_id), 0,
+			     I2C_SMBUS_READ, reg,
+			     I2C_SMBUS_BYTE_DATA, &smbus_data);
+	if (ret < 0)
+		return ret;
+
+	val = ((smbus_data.byte & 0xff) << 8);
+
+	ret = i2c_smbus_xfer(i2c, i2c_mii_phy_addr(phy_id), 0,
+			     I2C_SMBUS_READ, reg,
+			     I2C_SMBUS_BYTE_DATA, &smbus_data);
+	if (ret < 0)
+		return ret;
+
+	val |= (smbus_data.byte & 0xff);
+
+	return val;
+}
+
+static int smbus_byte_mii_write_default_c22(struct mii_bus *bus, int phy_id,
+					    int reg, u16 val)
+{
+	struct i2c_adapter *i2c = bus->priv;
+	union i2c_smbus_data smbus_data;
+	int ret;
+
+	if (!i2c_mii_valid_phy_id(phy_id))
+		return 0;
+
+	smbus_data.byte = ((val & 0xff00) >> 8);
+
+	ret = i2c_smbus_xfer(i2c, i2c_mii_phy_addr(phy_id), 0,
+			     I2C_SMBUS_WRITE, reg,
+			     I2C_SMBUS_BYTE_DATA, &smbus_data);
+	if (ret < 0)
+		return ret;
+
+	smbus_data.byte = val & 0xff;
+
+	ret = i2c_smbus_xfer(i2c, i2c_mii_phy_addr(phy_id), 0,
+			     I2C_SMBUS_WRITE, reg,
+			     I2C_SMBUS_BYTE_DATA, &smbus_data);
+
+	return ret < 0 ? ret : 0;
+}
+
 /* RollBall SFPs do not access internal PHY via I2C address 0x56, but
  * instead via address 0x51, when SFP page is set to 0x03 and password to
  * 0xffffffff.
@@ -378,13 +434,26 @@ static int i2c_mii_init_rollball(struct i2c_adapter *i2c)
 		return 0;
 }
 
+static bool mdio_i2c_check_functionality(struct i2c_adapter *i2c,
+					 enum mdio_i2c_proto protocol)
+{
+	if (i2c_check_functionality(i2c, I2C_FUNC_I2C))
+		return true;
+
+	if (i2c_check_functionality(i2c, I2C_FUNC_SMBUS_BYTE_DATA) &&
+	    protocol == MDIO_I2C_MARVELL_C22)
+		return true;
+
+	return false;
+}
+
 struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c,
 			       enum mdio_i2c_proto protocol)
 {
 	struct mii_bus *mii;
 	int ret;
 
-	if (!i2c_check_functionality(i2c, I2C_FUNC_I2C))
+	if (!mdio_i2c_check_functionality(i2c, protocol))
 		return ERR_PTR(-EINVAL);
 
 	mii = mdiobus_alloc();
@@ -395,6 +464,14 @@ struct mii_bus *mdio_i2c_alloc(struct device *parent, struct i2c_adapter *i2c,
 	mii->parent = parent;
 	mii->priv = i2c;
 
+	/* Only use SMBus if we have no other choice */
+	if (i2c_check_functionality(i2c, I2C_FUNC_SMBUS_BYTE_DATA) &&
+	    !i2c_check_functionality(i2c, I2C_FUNC_I2C)) {
+		mii->read = smbus_byte_mii_read_default_c22;
+		mii->write = smbus_byte_mii_write_default_c22;
+		return mii;
+	}
+
 	switch (protocol) {
 	case MDIO_I2C_ROLLBALL:
 		ret = i2c_mii_init_rollball(i2c);

From 67258cdf3cfcbb7202a027db508e8d7b0bb75fe8 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:45 -0700
Subject: [PATCH 2476/2753] netconsole: introduce 'release' as a new sysdata
 field

This commit adds a new feature to the sysdata structure, allowing the
kernel release/version to be appended as part of sysdata. Additionally,
it updates the logic to count this new field as a used entry when
enabled.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/netconsole.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 43757b5c02169..4f1d9e864020d 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -106,6 +106,8 @@ enum sysdata_feature {
 	SYSDATA_CPU_NR = BIT(0),
 	/* Populate the task name (as in current->comm) in sysdata */
 	SYSDATA_TASKNAME = BIT(1),
+	/* Kernel release/version as part of sysdata */
+	SYSDATA_RELEASE = BIT(2),
 };
 
 /**
@@ -719,6 +721,8 @@ static size_t count_extradata_entries(struct netconsole_target *nt)
 		entries += 1;
 	if (nt->sysdata_fields & SYSDATA_TASKNAME)
 		entries += 1;
+	if (nt->sysdata_fields & SYSDATA_RELEASE)
+		entries += 1;
 
 	return entries;
 }

From 858aaf054cae45db1aa3b2f9385a92b61bc84aa5 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:46 -0700
Subject: [PATCH 2477/2753] netconsole: implement configfs for release_enabled

Implement the configfs helpers to show and set release_enabled configfs
directories under userdata.

When enabled, set the feature bit in netconsole_target->sysdata_fields.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/netconsole.c | 49 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 4f1d9e864020d..fe13e923a7d99 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -442,6 +442,19 @@ static ssize_t sysdata_taskname_enabled_show(struct config_item *item,
 	return sysfs_emit(buf, "%d\n", taskname_enabled);
 }
 
+static ssize_t sysdata_release_enabled_show(struct config_item *item,
+					    char *buf)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool release_enabled;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	release_enabled = !!(nt->sysdata_fields & SYSDATA_TASKNAME);
+	mutex_unlock(&dynamic_netconsole_mutex);
+
+	return sysfs_emit(buf, "%d\n", release_enabled);
+}
+
 /*
  * This one is special -- targets created through the configfs interface
  * are not enabled (and the corresponding netpoll activated) by default.
@@ -859,6 +872,40 @@ static void disable_sysdata_feature(struct netconsole_target *nt,
 	nt->extradata_complete[nt->userdata_length] = 0;
 }
 
+static ssize_t sysdata_release_enabled_store(struct config_item *item,
+					     const char *buf, size_t count)
+{
+	struct netconsole_target *nt = to_target(item->ci_parent);
+	bool release_enabled, curr;
+	ssize_t ret;
+
+	ret = kstrtobool(buf, &release_enabled);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dynamic_netconsole_mutex);
+	curr = !!(nt->sysdata_fields & SYSDATA_RELEASE);
+	if (release_enabled == curr)
+		goto unlock_ok;
+
+	if (release_enabled &&
+	    count_extradata_entries(nt) >= MAX_EXTRADATA_ITEMS) {
+		ret = -ENOSPC;
+		goto unlock;
+	}
+
+	if (release_enabled)
+		nt->sysdata_fields |= SYSDATA_RELEASE;
+	else
+		disable_sysdata_feature(nt, SYSDATA_RELEASE);
+
+unlock_ok:
+	ret = strnlen(buf, count);
+unlock:
+	mutex_unlock(&dynamic_netconsole_mutex);
+	return ret;
+}
+
 static ssize_t sysdata_taskname_enabled_store(struct config_item *item,
 					      const char *buf, size_t count)
 {
@@ -939,6 +986,7 @@ static ssize_t sysdata_cpu_nr_enabled_store(struct config_item *item,
 CONFIGFS_ATTR(userdatum_, value);
 CONFIGFS_ATTR(sysdata_, cpu_nr_enabled);
 CONFIGFS_ATTR(sysdata_, taskname_enabled);
+CONFIGFS_ATTR(sysdata_, release_enabled);
 
 static struct configfs_attribute *userdatum_attrs[] = {
 	&userdatum_attr_value,
@@ -1000,6 +1048,7 @@ static void userdatum_drop(struct config_group *group, struct config_item *item)
 static struct configfs_attribute *userdata_attrs[] = {
 	&sysdata_attr_cpu_nr_enabled,
 	&sysdata_attr_taskname_enabled,
+	&sysdata_attr_release_enabled,
 	NULL,
 };
 

From 8d20eedb5b7156a7072b26dc854d47128ab003ff Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:47 -0700
Subject: [PATCH 2478/2753] netconsole: add 'sysdata' suffix to related
 functions

This commit appends a common "sysdata" suffix to functions responsible
for appending data to sysdata.

This change enhances code clarity and prevents naming conflicts with
other "append" functions, particularly in anticipation of the upcoming
inclusion of the `release` field in the next patch.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/netconsole.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index fe13e923a7d99..93fbc7391f731 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1224,7 +1224,7 @@ static void populate_configfs_item(struct netconsole_target *nt,
 	init_target_config_group(nt, target_name);
 }
 
-static int append_cpu_nr(struct netconsole_target *nt, int offset)
+static int sysdata_append_cpu_nr(struct netconsole_target *nt, int offset)
 {
 	/* Append cpu=%d at extradata_complete after userdata str */
 	return scnprintf(&nt->extradata_complete[offset],
@@ -1232,7 +1232,7 @@ static int append_cpu_nr(struct netconsole_target *nt, int offset)
 			 raw_smp_processor_id());
 }
 
-static int append_taskname(struct netconsole_target *nt, int offset)
+static int sysdata_append_taskname(struct netconsole_target *nt, int offset)
 {
 	return scnprintf(&nt->extradata_complete[offset],
 			 MAX_EXTRADATA_ENTRY_LEN, " taskname=%s\n",
@@ -1256,9 +1256,9 @@ static int prepare_extradata(struct netconsole_target *nt)
 		goto out;
 
 	if (nt->sysdata_fields & SYSDATA_CPU_NR)
-		extradata_len += append_cpu_nr(nt, extradata_len);
+		extradata_len += sysdata_append_cpu_nr(nt, extradata_len);
 	if (nt->sysdata_fields & SYSDATA_TASKNAME)
-		extradata_len += append_taskname(nt, extradata_len);
+		extradata_len += sysdata_append_taskname(nt, extradata_len);
 
 	WARN_ON_ONCE(extradata_len >
 		     MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS);

From f0f581e38f67fed9405df6ee88dde728e53ba02a Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:48 -0700
Subject: [PATCH 2479/2753] netconsole: append release to sysdata

Append the init_utsname()->release to sysdata buffer before sending the
message in case the feature is set.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/netconsole.c | 10 ++++++++++
 1 file changed, 10 insertions(+)

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 93fbc7391f731..4289ccd3e41bf 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1238,6 +1238,14 @@ static int sysdata_append_taskname(struct netconsole_target *nt, int offset)
 			 MAX_EXTRADATA_ENTRY_LEN, " taskname=%s\n",
 			 current->comm);
 }
+
+static int sysdata_append_release(struct netconsole_target *nt, int offset)
+{
+	return scnprintf(&nt->extradata_complete[offset],
+			 MAX_EXTRADATA_ENTRY_LEN, " release=%s\n",
+			 init_utsname()->release);
+}
+
 /*
  * prepare_extradata - append sysdata at extradata_complete in runtime
  * @nt: target to send message to
@@ -1259,6 +1267,8 @@ static int prepare_extradata(struct netconsole_target *nt)
 		extradata_len += sysdata_append_cpu_nr(nt, extradata_len);
 	if (nt->sysdata_fields & SYSDATA_TASKNAME)
 		extradata_len += sysdata_append_taskname(nt, extradata_len);
+	if (nt->sysdata_fields & SYSDATA_RELEASE)
+		extradata_len += sysdata_append_release(nt, extradata_len);
 
 	WARN_ON_ONCE(extradata_len >
 		     MAX_EXTRADATA_ENTRY_LEN * MAX_EXTRADATA_ITEMS);

From 8a52d6f179ae9ec004346a1727944b992a23e52f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:49 -0700
Subject: [PATCH 2480/2753] selftests: netconsole: Add tests for 'release'
 feature in sysdata

Expands the self-tests to include the 'release' feature in
sysdata.

Verifies that enabling the 'release' feature appends the
correct data and ensures that disabling it functions as expected.

When enabled, the message should have an item similar to in the
userdata: `release=$(uname -r)`

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/drivers/net/netcons_sysdata.sh  | 44 +++++++++++++++++--
 1 file changed, 41 insertions(+), 3 deletions(-)

diff --git a/tools/testing/selftests/drivers/net/netcons_sysdata.sh b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
index f351206ed1bda..a737e377bf085 100755
--- a/tools/testing/selftests/drivers/net/netcons_sysdata.sh
+++ b/tools/testing/selftests/drivers/net/netcons_sysdata.sh
@@ -42,6 +42,17 @@ function set_taskname() {
 	echo 1 > "${NETCONS_PATH}/userdata/taskname_enabled"
 }
 
+# Enable the release to be appended to sysdata
+function set_release() {
+	if [[ ! -f "${NETCONS_PATH}/userdata/release_enabled" ]]
+	then
+		echo "Not able to enable release sysdata append. Configfs not available in ${NETCONS_PATH}/userdata/release_enabled" >&2
+		exit "${ksft_skip}"
+	fi
+
+	echo 1 > "${NETCONS_PATH}/userdata/release_enabled"
+}
+
 # Disable the sysdata cpu_nr feature
 function unset_cpu_nr() {
 	echo 0 > "${NETCONS_PATH}/userdata/cpu_nr_enabled"
@@ -52,6 +63,10 @@ function unset_taskname() {
 	echo 0 > "${NETCONS_PATH}/userdata/taskname_enabled"
 }
 
+function unset_release() {
+	echo 0 > "${NETCONS_PATH}/userdata/release_enabled"
+}
+
 # Test if MSG contains sysdata
 function validate_sysdata() {
 	# OUTPUT_FILE will contain something like:
@@ -93,6 +108,21 @@ function validate_sysdata() {
 	pkill_socat
 }
 
+function validate_release() {
+	RELEASE=$(uname -r)
+
+	if [ ! -f "$OUTPUT_FILE" ]; then
+		echo "FAIL: File was not generated." >&2
+		exit "${ksft_fail}"
+	fi
+
+	if ! grep -q "release=${RELEASE}" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'release=${RELEASE}' not found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+}
+
 # Test if MSG content exists in OUTPUT_FILE but no `cpu=` and `taskname=`
 # strings
 function validate_no_sysdata() {
@@ -119,6 +149,12 @@ function validate_no_sysdata() {
 		exit "${ksft_fail}"
 	fi
 
+	if grep -q "release=" "${OUTPUT_FILE}"; then
+		echo "FAIL: 'release=  found in ${OUTPUT_FILE}" >&2
+		cat "${OUTPUT_FILE}" >&2
+		exit "${ksft_fail}"
+	fi
+
 	rm "${OUTPUT_FILE}"
 }
 
@@ -169,9 +205,11 @@ MSG="Test #1 from CPU${CPU}"
 set_cpu_nr
 # Enable taskname to be appended to sysdata
 set_taskname
+set_release
 runtest
 # Make sure the message was received in the dst part
 # and exit
+validate_release
 validate_sysdata
 
 #====================================================
@@ -184,19 +222,19 @@ OUTPUT_FILE="/tmp/${TARGET}_2"
 MSG="Test #2 from CPU${CPU}"
 set_user_data
 runtest
+validate_release
 validate_sysdata
 
 # ===================================================
 # TEST #3
-# Unset cpu_nr, so, no CPU should be appended.
-# userdata is still set
+# Unset all sysdata, fail if any userdata is set
 # ===================================================
 CPU=$((RANDOM % $(nproc)))
 OUTPUT_FILE="/tmp/${TARGET}_3"
 MSG="Test #3 from CPU${CPU}"
-# Enable the auto population of cpu_nr
 unset_cpu_nr
 unset_taskname
+unset_release
 runtest
 # At this time, cpu= shouldn't be present in the msg
 validate_no_sysdata

From 0fe1cc4ec4f49f3fb4994872a048cd4720062f19 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 14 Mar 2025 10:58:50 -0700
Subject: [PATCH 2481/2753] docs: netconsole: document release feature

Add documentation explaining the kernel release auto-population feature
in netconsole.

This feature appends kernel version information to the userdata
dictionary in every message sent when enabled via the `release_enabled`
file in the configfs hierarchy.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/netconsole.rst | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/Documentation/networking/netconsole.rst b/Documentation/networking/netconsole.rst
index ec740ba127976..a0076b542e9c7 100644
--- a/Documentation/networking/netconsole.rst
+++ b/Documentation/networking/netconsole.rst
@@ -272,6 +272,31 @@ Example::
 In this example, the message was generated while "echo" was the current
 scheduled process.
 
+Kernel release auto population in userdata
+------------------------------------------
+
+Within the netconsole configfs hierarchy, there is a file named `release_enabled`
+located in the `userdata` directory. This file controls the kernel release
+(version) auto-population feature, which appends the kernel release information
+to userdata dictionary in every message sent.
+
+To enable the release auto-population::
+
+  echo 1 > /sys/kernel/config/netconsole/target1/userdata/release_enabled
+
+Example::
+
+  echo "This is a message" > /dev/kmsg
+  12,607,22085407756,-;This is a message
+   release=6.14.0-rc6-01219-g3c027fbd941d
+
+.. note::
+
+   This feature provides the same data as the "release prepend" feature.
+   However, in this case, the release information is appended to the userdata
+   dictionary rather than being included in the message header.
+
+
 CPU number auto population in userdata
 --------------------------------------
 

From b66569012617a9e0e6f066d74472fa47ba098306 Mon Sep 17 00:00:00 2001
From: XieLudan <xie.ludan@zte.com.cn>
Date: Sat, 15 Mar 2025 14:12:49 +0800
Subject: [PATCH 2482/2753] net: atm: use sysfs_emit() instead of scnprintf().

Follow the advice in Documentation/filesystems/sysfs.rst:
show() should only use sysfs_emit() or sysfs_emit_at() when formatting
the value to be returned to user space.

Signed-off-by: XieLudan <xie.ludan@zte.com.cn>
Signed-off-by: NipaLocal <nipa@local>
---
 net/atm/atm_sysfs.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/net/atm/atm_sysfs.c b/net/atm/atm_sysfs.c
index 54e7fb1a4ee50..0aab1c3c05def 100644
--- a/net/atm/atm_sysfs.c
+++ b/net/atm/atm_sysfs.c
@@ -16,7 +16,7 @@ static ssize_t type_show(struct device *cdev,
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
 
-	return scnprintf(buf, PAGE_SIZE, "%s\n", adev->type);
+	return sysfs_emit(buf, "%s\n", adev->type);
 }
 
 static ssize_t address_show(struct device *cdev,
@@ -24,7 +24,7 @@ static ssize_t address_show(struct device *cdev,
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
 
-	return scnprintf(buf, PAGE_SIZE, "%pM\n", adev->esi);
+	return sysfs_emit(buf, "%pM\n", adev->esi);
 }
 
 static ssize_t atmaddress_show(struct device *cdev,
@@ -37,7 +37,7 @@ static ssize_t atmaddress_show(struct device *cdev,
 
 	spin_lock_irqsave(&adev->lock, flags);
 	list_for_each_entry(aaddr, &adev->local, entry) {
-		count += scnprintf(buf + count, PAGE_SIZE - count,
+		count += sysfs_emit(buf + count,
 				   "%1phN.%2phN.%10phN.%6phN.%1phN\n",
 				   &aaddr->addr.sas_addr.prv[0],
 				   &aaddr->addr.sas_addr.prv[1],
@@ -55,7 +55,7 @@ static ssize_t atmindex_show(struct device *cdev,
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n", adev->number);
+	return sysfs_emit(buf, "%d\n", adev->number);
 }
 
 static ssize_t carrier_show(struct device *cdev,
@@ -63,7 +63,7 @@ static ssize_t carrier_show(struct device *cdev,
 {
 	struct atm_dev *adev = to_atm_dev(cdev);
 
-	return scnprintf(buf, PAGE_SIZE, "%d\n",
+	return sysfs_emit(buf, "%d\n",
 			 adev->signal == ATM_PHY_SIG_LOST ? 0 : 1);
 }
 
@@ -87,7 +87,7 @@ static ssize_t link_rate_show(struct device *cdev,
 	default:
 		link_rate = adev->link_rate * 8 * 53;
 	}
-	return scnprintf(buf, PAGE_SIZE, "%d\n", link_rate);
+	return sysfs_emit(buf, "%d\n", link_rate);
 }
 
 static DEVICE_ATTR_RO(address);

From ce5414387b051dd415e43c80b95ead58573b81cd Mon Sep 17 00:00:00 2001
From: I Hsin Cheng <richard120310@gmail.com>
Date: Sat, 15 Mar 2025 14:25:16 +0800
Subject: [PATCH 2483/2753] net/smc: Reduce size of smc_wr_tx_tasklet_fn

The variable "polled" in smc_wr_tx_tasklet_fn is a counter to determine
whether the loop has been executed for the first time. Refactor the type
of "polled" from "int" to "bool" can reduce the size of generated code
size by 12 bytes shown with the test below

$ ./scripts/bloat-o-meter vmlinux_old vmlinux_new
add/remove: 0/0 grow/shrink: 0/1 up/down: 0/-12 (-12)
Function                                     old     new   delta
smc_wr_tx_tasklet_fn                        1076    1064     -12
Total: Before=24795091, After=24795079, chg -0.00%

In some configuration, the compiler will complain this function for
exceeding 1024 bytes for function stack, this change can at least reduce
the size by 12 bytes within manner.

Signed-off-by: I Hsin Cheng <richard120310@gmail.com>
Reviewed-by: Dust Li <dust.li@linux.alibaba.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/smc/smc_wr.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c
index b04a21b8c5111..3cc435ed7fdea 100644
--- a/net/smc/smc_wr.c
+++ b/net/smc/smc_wr.c
@@ -138,14 +138,14 @@ static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t)
 	struct smc_ib_device *dev = from_tasklet(dev, t, send_tasklet);
 	struct ib_wc wc[SMC_WR_MAX_POLL_CQE];
 	int i = 0, rc;
-	int polled = 0;
+	bool polled = false;
 
 again:
-	polled++;
+	polled = !polled;
 	do {
 		memset(&wc, 0, sizeof(wc));
 		rc = ib_poll_cq(dev->roce_cq_send, SMC_WR_MAX_POLL_CQE, wc);
-		if (polled == 1) {
+		if (polled) {
 			ib_req_notify_cq(dev->roce_cq_send,
 					 IB_CQ_NEXT_COMP |
 					 IB_CQ_REPORT_MISSED_EVENTS);
@@ -155,7 +155,7 @@ static void smc_wr_tx_tasklet_fn(struct tasklet_struct *t)
 		for (i = 0; i < rc; i++)
 			smc_wr_tx_process_cqe(&wc[i]);
 	} while (rc > 0);
-	if (polled == 1)
+	if (polled)
 		goto again;
 }
 

From 80f24f9ad8de0af0a11ff5aaeb276d411bbc4d34 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Sat, 15 Mar 2025 13:04:20 +0100
Subject: [PATCH 2484/2753] net: airoha: Validate egress gdm port in
 airoha_ppe_foe_entry_prepare()

The system occasionally crashes dereferencing a NULL pointer when it is
forwarding constant, high load bidirectional traffic.

[ 2149.913414] Unable to handle kernel read from unreadable memory at virtual address 0000000000000000
[ 2149.925812] Mem abort info:
[ 2149.928713]   ESR = 0x0000000096000005
[ 2149.932762]   EC = 0x25: DABT (current EL), IL = 32 bits
[ 2149.938429]   SET = 0, FnV = 0
[ 2149.941814]   EA = 0, S1PTW = 0
[ 2149.945187]   FSC = 0x05: level 1 translation fault
[ 2149.950348] Data abort info:
[ 2149.953472]   ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000
[ 2149.959243]   CM = 0, WnR = 0, TnD = 0, TagAccess = 0
[ 2149.964593]   GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0
[ 2149.970243] user pgtable: 4k pages, 39-bit VAs, pgdp=000000008b507000
[ 2149.977068] [0000000000000000] pgd=0000000000000000, p4d=0000000000000000, pud=0000000000000000
[ 2149.986062] Internal error: Oops: 0000000096000005 [#1] SMP
[ 2150.082282]  arht_wrapper(O) i2c_core arht_hook(O) crc32_generic
[ 2150.177623] CPU: 0 PID: 38 Comm: kworker/u9:1 Tainted: G           O       6.6.73 #0
[ 2150.185362] Hardware name: Airoha AN7581 Evaluation Board (DT)
[ 2150.191189] Workqueue: nf_ft_offload_add nf_flow_rule_route_ipv6 [nf_flow_table]
[ 2150.198653] pstate: 00400005 (nzcv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 2150.205615] pc : airoha_ppe_flow_offload_replace.isra.0+0x6dc/0xc54
[ 2150.211882] lr : airoha_ppe_flow_offload_replace.isra.0+0x6cc/0xc54
[ 2150.218149] sp : ffffffc080e8ba10
[ 2150.221456] x29: ffffffc080e8bae0 x28: ffffff80080b0000 x27: 0000000000000000
[ 2150.228591] x26: ffffff8001c70020 x25: 0000000000000002 x24: 0000000000000000
[ 2150.235727] x23: 0000000061000000 x22: 00000000ffffffed x21: ffffffc080e8bbb0
[ 2150.242862] x20: ffffff8001c70000 x19: 0000000000000008 x18: 0000000000000000
[ 2150.249998] x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000
[ 2150.257133] x14: 0000000000000001 x13: 0000000000000008 x12: 0101010101010101
[ 2150.264268] x11: 7f7f7f7f7f7f7f7f x10: 0000000000000041 x9 : 0000000000000000
[ 2150.271404] x8 : ffffffc080e8bad8 x7 : 0000000000000000 x6 : 0000000000000015
[ 2150.278540] x5 : ffffffc080e8ba4e x4 : 0000000000000004 x3 : 0000000000000000
[ 2150.285675] x2 : 0000000000000008 x1 : 00000000080b0000 x0 : 0000000000000000
[ 2150.292811] Call trace:
[ 2150.295250]  airoha_ppe_flow_offload_replace.isra.0+0x6dc/0xc54
[ 2150.301171]  airoha_ppe_setup_tc_block_cb+0x7c/0x8b4
[ 2150.306135]  nf_flow_offload_ip_hook+0x710/0x874 [nf_flow_table]
[ 2150.312168]  nf_flow_rule_route_ipv6+0x53c/0x580 [nf_flow_table]
[ 2150.318200]  process_one_work+0x178/0x2f0
[ 2150.322211]  worker_thread+0x2e4/0x4cc
[ 2150.325953]  kthread+0xd8/0xdc
[ 2150.329008]  ret_from_fork+0x10/0x20
[ 2150.332589] Code: b9007bf7 b4001e9c f9448380 b9491381 (f9400000)
[ 2150.338681] ---[ end trace 0000000000000000 ]---
[ 2150.343298] Kernel panic - not syncing: Oops: Fatal exception
[ 2150.349035] SMP: stopping secondary CPUs
[ 2150.352954] Kernel Offset: disabled
[ 2150.356438] CPU features: 0x0,00000000,00000000,1000400b
[ 2150.361743] Memory Limit: none

Fix the issue validating egress gdm port in airoha_ppe_foe_entry_prepare
routine.

Fixes: 00a7678310fe ("net: airoha: Introduce flowtable offload support")
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/airoha/airoha_eth.c | 13 +++++++++++++
 drivers/net/ethernet/airoha/airoha_eth.h |  3 +++
 drivers/net/ethernet/airoha/airoha_ppe.c | 10 ++++++++--
 3 files changed, 24 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/airoha/airoha_eth.c b/drivers/net/ethernet/airoha/airoha_eth.c
index c0a642568ac11..bf9c882e9c8b0 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.c
+++ b/drivers/net/ethernet/airoha/airoha_eth.c
@@ -2454,6 +2454,19 @@ static void airoha_metadata_dst_free(struct airoha_gdm_port *port)
 	}
 }
 
+int airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			     struct airoha_gdm_port *port)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(eth->ports); i++) {
+		if (eth->ports[i] == port)
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
 static int airoha_alloc_gdm_port(struct airoha_eth *eth,
 				 struct device_node *np, int index)
 {
diff --git a/drivers/net/ethernet/airoha/airoha_eth.h b/drivers/net/ethernet/airoha/airoha_eth.h
index 60690b685710c..d199b8adffc0b 100644
--- a/drivers/net/ethernet/airoha/airoha_eth.h
+++ b/drivers/net/ethernet/airoha/airoha_eth.h
@@ -532,6 +532,9 @@ u32 airoha_rmw(void __iomem *base, u32 offset, u32 mask, u32 val);
 #define airoha_qdma_clear(qdma, offset, val)			\
 	airoha_rmw((qdma)->regs, (offset), (val), 0)
 
+int airoha_is_valid_gdm_port(struct airoha_eth *eth,
+			     struct airoha_gdm_port *port);
+
 void airoha_ppe_check_skb(struct airoha_ppe *ppe, u16 hash);
 int airoha_ppe_setup_tc_block_cb(enum tc_setup_type type, void *type_data,
 				 void *cb_priv);
diff --git a/drivers/net/ethernet/airoha/airoha_ppe.c b/drivers/net/ethernet/airoha/airoha_ppe.c
index 8b55e871352d3..65833e2058194 100644
--- a/drivers/net/ethernet/airoha/airoha_ppe.c
+++ b/drivers/net/ethernet/airoha/airoha_ppe.c
@@ -197,7 +197,8 @@ static int airoha_get_dsa_port(struct net_device **dev)
 #endif
 }
 
-static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe,
+static int airoha_ppe_foe_entry_prepare(struct airoha_eth *eth,
+					struct airoha_foe_entry *hwe,
 					struct net_device *dev, int type,
 					struct airoha_flow_data *data,
 					int l4proto)
@@ -224,6 +225,11 @@ static int airoha_ppe_foe_entry_prepare(struct airoha_foe_entry *hwe,
 	if (dev) {
 		struct airoha_gdm_port *port = netdev_priv(dev);
 		u8 pse_port;
+		int err;
+
+		err = airoha_is_valid_gdm_port(eth, port);
+		if (err)
+			return err;
 
 		if (dsa_port >= 0)
 			pse_port = port->id == 4 ? FE_PSE_PORT_GDM4 : port->id;
@@ -633,7 +639,7 @@ static int airoha_ppe_flow_offload_replace(struct airoha_gdm_port *port,
 	    !is_valid_ether_addr(data.eth.h_dest))
 		return -EINVAL;
 
-	err = airoha_ppe_foe_entry_prepare(&hwe, odev, offload_type,
+	err = airoha_ppe_foe_entry_prepare(eth, &hwe, odev, offload_type,
 					   &data, l4proto);
 	if (err)
 		return err;

From b8af0fbb30d386d6c4c8fc950fa1fe5bfafd9617 Mon Sep 17 00:00:00 2001
From: Eric Woudstra <ericwouds@gmail.com>
Date: Sat, 15 Mar 2025 20:59:08 +0100
Subject: [PATCH 2485/2753] net: pppoe: avoid zero-length arrays in struct
 pppoe_hdr

Jakub Kicinski suggested following patch:

W=1 C=1 GCC build gives us:

net/bridge/netfilter/nf_conntrack_bridge.c: note: in included file (through
../include/linux/if_pppox.h, ../include/uapi/linux/netfilter_bridge.h,
../include/linux/netfilter_bridge.h): include/uapi/linux/if_pppox.h:
153:29: warning: array of flexible structures

It doesn't like that hdr has a zero-length array which overlaps proto.
The kernel code doesn't currently need those arrays.

PPPoE connection is functional after applying this patch.

Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ppp/pppoe.c       | 2 +-
 include/uapi/linux/if_pppox.h | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
index 68e631718ab0b..17946af6a8cf6 100644
--- a/drivers/net/ppp/pppoe.c
+++ b/drivers/net/ppp/pppoe.c
@@ -882,7 +882,7 @@ static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
 	skb->protocol = cpu_to_be16(ETH_P_PPP_SES);
 
 	ph = skb_put(skb, total_len + sizeof(struct pppoe_hdr));
-	start = (char *)&ph->tag[0];
+	start = (char *)ph + sizeof(*ph);
 
 	error = memcpy_from_msg(start, m, total_len);
 	if (error < 0) {
diff --git a/include/uapi/linux/if_pppox.h b/include/uapi/linux/if_pppox.h
index 9abd80dcc46f9..29b804aa74745 100644
--- a/include/uapi/linux/if_pppox.h
+++ b/include/uapi/linux/if_pppox.h
@@ -122,7 +122,9 @@ struct sockaddr_pppol2tpv3in6 {
 struct pppoe_tag {
 	__be16 tag_type;
 	__be16 tag_len;
+#ifndef __KERNEL__
 	char tag_data[];
+#endif
 } __attribute__ ((packed));
 
 /* Tag identifiers */
@@ -150,7 +152,9 @@ struct pppoe_hdr {
 	__u8 code;
 	__be16 sid;
 	__be16 length;
+#ifndef __KERNEL__
 	struct pppoe_tag tag[];
+#endif
 } __packed;
 
 /* Length of entire PPPoE + PPP header */

From 231fb91d1c9d16c5528dd7f189443c241611724b Mon Sep 17 00:00:00 2001
From: Eric Woudstra <ericwouds@gmail.com>
Date: Sat, 15 Mar 2025 20:59:09 +0100
Subject: [PATCH 2486/2753] netfilter: nf_flow_table_offload: Add
 nf_flow_encap_push() for xmit direct

Loosely based on wenxu's patches:

"nf_flow_table_offload: offload the vlan/PPPoE encap in the flowtable".

Fixed double vlan and pppoe packets, almost entirely rewriting the patch.

After this patch, it is possible to transmit packets in the fastpath with
outgoing encaps, without using vlan- and/or pppoe-devices.

This makes it possible to use more different kinds of network setups.
For example, when bridge tagging is used to egress vlan tagged
packets using the forward fastpath. Another example is passing 802.1q
tagged packets through a bridge using the bridge fastpath.

This also makes the software fastpath process more similar to the
hardware offloaded fastpath process, where encaps are also pushed.

After applying this patch, always info->outdev = info->hw_outdev,
so the netfilter code can be further cleaned up by removing:
 * hw_outdev from struct nft_forward_info
 * out.hw_ifindex from struct nf_flow_route
 * out.hw_ifidx from struct flow_offload_tuple

Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/netfilter/nf_flow_table_ip.c | 96 +++++++++++++++++++++++++++++++-
 net/netfilter/nft_flow_offload.c |  6 +-
 2 files changed, 96 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index 8cd4cf7ae2112..d0c3c459c4d29 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -306,6 +306,92 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
 	return false;
 }
 
+static int nf_flow_vlan_inner_push(struct sk_buff *skb, __be16 proto, u16 id)
+{
+	struct vlan_hdr *vhdr;
+
+	if (skb_cow_head(skb, VLAN_HLEN))
+		return -1;
+
+	__skb_push(skb, VLAN_HLEN);
+	skb_reset_network_header(skb);
+
+	vhdr = (struct vlan_hdr *)(skb->data);
+	vhdr->h_vlan_TCI = htons(id);
+	vhdr->h_vlan_encapsulated_proto = skb->protocol;
+	skb->protocol = proto;
+
+	return 0;
+}
+
+static int nf_flow_ppoe_push(struct sk_buff *skb, u16 id)
+{
+	struct ppp_hdr {
+		struct pppoe_hdr hdr;
+		__be16 proto;
+	} *ph;
+	int data_len = skb->len + 2;
+	__be16 proto;
+
+	if (skb_cow_head(skb, PPPOE_SES_HLEN))
+		return -1;
+
+	if (skb->protocol == htons(ETH_P_IP))
+		proto = htons(PPP_IP);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		proto = htons(PPP_IPV6);
+	else
+		return -1;
+
+	__skb_push(skb, PPPOE_SES_HLEN);
+	skb_reset_network_header(skb);
+
+	ph = (struct ppp_hdr *)(skb->data);
+	ph->hdr.ver  = 1;
+	ph->hdr.type = 1;
+	ph->hdr.code = 0;
+	ph->hdr.sid  = htons(id);
+	ph->hdr.length = htons(data_len);
+	ph->proto = proto;
+	skb->protocol = htons(ETH_P_PPP_SES);
+
+	return 0;
+}
+
+static int nf_flow_encap_push(struct sk_buff *skb,
+			      struct flow_offload_tuple_rhash *tuplehash,
+			      unsigned short *type)
+{
+	int i = 0, ret = 0;
+
+	if (!tuplehash->tuple.encap_num)
+		return 0;
+
+	if (tuplehash->tuple.encap[i].proto == htons(ETH_P_8021Q) ||
+	    tuplehash->tuple.encap[i].proto == htons(ETH_P_8021AD)) {
+		__vlan_hwaccel_put_tag(skb, tuplehash->tuple.encap[i].proto,
+				       tuplehash->tuple.encap[i].id);
+		i++;
+		if (i >= tuplehash->tuple.encap_num)
+			return 0;
+	}
+
+	switch (tuplehash->tuple.encap[i].proto) {
+	case htons(ETH_P_8021Q):
+		*type = ETH_P_8021Q;
+		ret = nf_flow_vlan_inner_push(skb,
+					      tuplehash->tuple.encap[i].proto,
+					      tuplehash->tuple.encap[i].id);
+		break;
+	case htons(ETH_P_PPP_SES):
+		*type = ETH_P_PPP_SES;
+		ret = nf_flow_ppoe_push(skb,
+					tuplehash->tuple.encap[i].id);
+		break;
+	}
+	return ret;
+}
+
 static void nf_flow_encap_pop(struct sk_buff *skb,
 			      struct flow_offload_tuple_rhash *tuplehash)
 {
@@ -335,6 +421,7 @@ static void nf_flow_encap_pop(struct sk_buff *skb,
 
 static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
 				       const struct flow_offload_tuple_rhash *tuplehash,
+				       struct flow_offload_tuple_rhash *other_tuplehash,
 				       unsigned short type)
 {
 	struct net_device *outdev;
@@ -343,6 +430,9 @@ static unsigned int nf_flow_queue_xmit(struct net *net, struct sk_buff *skb,
 	if (!outdev)
 		return NF_DROP;
 
+	if (nf_flow_encap_push(skb, other_tuplehash, &type) < 0)
+		return NF_DROP;
+
 	skb->dev = outdev;
 	dev_hard_header(skb, skb->dev, type, tuplehash->tuple.out.h_dest,
 			tuplehash->tuple.out.h_source, skb->len);
@@ -462,7 +552,8 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb,
 		ret = NF_STOLEN;
 		break;
 	case FLOW_OFFLOAD_XMIT_DIRECT:
-		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IP);
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash,
+					 &flow->tuplehash[!dir], ETH_P_IP);
 		if (ret == NF_DROP)
 			flow_offload_teardown(flow);
 		break;
@@ -757,7 +848,8 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb,
 		ret = NF_STOLEN;
 		break;
 	case FLOW_OFFLOAD_XMIT_DIRECT:
-		ret = nf_flow_queue_xmit(state->net, skb, tuplehash, ETH_P_IPV6);
+		ret = nf_flow_queue_xmit(state->net, skb, tuplehash,
+					 &flow->tuplehash[!dir], ETH_P_IPV6);
 		if (ret == NF_DROP)
 			flow_offload_teardown(flow);
 		break;
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index 221d502230181..d320b7f5282e8 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -124,13 +124,12 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
 				info->indev = NULL;
 				break;
 			}
-			if (!info->outdev)
-				info->outdev = path->dev;
 			info->encap[info->num_encaps].id = path->encap.id;
 			info->encap[info->num_encaps].proto = path->encap.proto;
 			info->num_encaps++;
 			if (path->type == DEV_PATH_PPPOE)
 				memcpy(info->h_dest, path->encap.h_dest, ETH_ALEN);
+			info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT;
 			break;
 		case DEV_PATH_BRIDGE:
 			if (is_zero_ether_addr(info->h_source))
@@ -158,8 +157,7 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
 			break;
 		}
 	}
-	if (!info->outdev)
-		info->outdev = info->indev;
+	info->outdev = info->indev;
 
 	info->hw_outdev = info->indev;
 

From f0f1c2498b0c13fbd597d496a07cb4505aa8a1f3 Mon Sep 17 00:00:00 2001
From: Eric Woudstra <ericwouds@gmail.com>
Date: Sat, 15 Mar 2025 20:59:10 +0100
Subject: [PATCH 2487/2753] netfilter: flow: remove hw_outdev, out.hw_ifindex
 and out.hw_ifidx

Now always info->outdev == info->hw_outdev, so the netfilter code can be
further cleaned up by removing:
 * hw_outdev from struct nft_forward_info
 * out.hw_ifindex from struct nf_flow_route
 * out.hw_ifidx from struct flow_offload_tuple

Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: Eric Woudstra <ericwouds@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/netfilter/nf_flow_table.h | 2 --
 net/netfilter/nf_flow_table_core.c    | 1 -
 net/netfilter/nf_flow_table_offload.c | 2 +-
 net/netfilter/nft_flow_offload.c      | 4 ----
 4 files changed, 1 insertion(+), 8 deletions(-)

diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index d711642e78b57..4ab32fb61865b 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -145,7 +145,6 @@ struct flow_offload_tuple {
 		};
 		struct {
 			u32		ifidx;
-			u32		hw_ifidx;
 			u8		h_source[ETH_ALEN];
 			u8		h_dest[ETH_ALEN];
 		} out;
@@ -211,7 +210,6 @@ struct nf_flow_route {
 		} in;
 		struct {
 			u32			ifindex;
-			u32			hw_ifindex;
 			u8			h_source[ETH_ALEN];
 			u8			h_dest[ETH_ALEN];
 		} out;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 9d8361526f82a..1e5d3735c0286 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -127,7 +127,6 @@ static int flow_offload_fill_route(struct flow_offload *flow,
 		memcpy(flow_tuple->out.h_source, route->tuple[dir].out.h_source,
 		       ETH_ALEN);
 		flow_tuple->out.ifidx = route->tuple[dir].out.ifindex;
-		flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex;
 		dst_release(dst);
 		break;
 	case FLOW_OFFLOAD_XMIT_XFRM:
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index e06bc36f49fe7..d8f7bfd60ac66 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -555,7 +555,7 @@ static void flow_offload_redirect(struct net *net,
 	switch (this_tuple->xmit_type) {
 	case FLOW_OFFLOAD_XMIT_DIRECT:
 		this_tuple = &flow->tuplehash[dir].tuple;
-		ifindex = this_tuple->out.hw_ifidx;
+		ifindex = this_tuple->out.ifidx;
 		break;
 	case FLOW_OFFLOAD_XMIT_NEIGH:
 		other_tuple = &flow->tuplehash[!dir].tuple;
diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c
index d320b7f5282e8..acfdf523bd3ba 100644
--- a/net/netfilter/nft_flow_offload.c
+++ b/net/netfilter/nft_flow_offload.c
@@ -80,7 +80,6 @@ static int nft_dev_fill_forward_path(const struct nf_flow_route *route,
 struct nft_forward_info {
 	const struct net_device *indev;
 	const struct net_device *outdev;
-	const struct net_device *hw_outdev;
 	struct id {
 		__u16	id;
 		__be16	proto;
@@ -159,8 +158,6 @@ static void nft_dev_path_info(const struct net_device_path_stack *stack,
 	}
 	info->outdev = info->indev;
 
-	info->hw_outdev = info->indev;
-
 	if (nf_flowtable_hw_offload(flowtable) &&
 	    nft_is_valid_ether_device(info->indev))
 		info->xmit_type = FLOW_OFFLOAD_XMIT_DIRECT;
@@ -212,7 +209,6 @@ static void nft_dev_forward_path(struct nf_flow_route *route,
 		memcpy(route->tuple[dir].out.h_source, info.h_source, ETH_ALEN);
 		memcpy(route->tuple[dir].out.h_dest, info.h_dest, ETH_ALEN);
 		route->tuple[dir].out.ifindex = info.outdev->ifindex;
-		route->tuple[dir].out.hw_ifindex = info.hw_outdev->ifindex;
 		route->tuple[dir].xmit_type = info.xmit_type;
 	}
 }

From 01a2f15fbe82c141e3ca2a8c9e01b7881c14b28a Mon Sep 17 00:00:00 2001
From: Yael Chemla <ychemla@nvidia.com>
Date: Sun, 16 Mar 2025 10:14:33 +0200
Subject: [PATCH 2488/2753] net/mlx5e: Ensure each counter group uses its PCAM
 bit

The code was incorrectly relying on PCAM bit of ppcnt_statistical_group
for accessing per_lane_error_counters.
If ppcnt_statistical_group PCAM bit was not set, we would not read
per_lane_error_counters, even when its PCAM bit is set.
Given the existing device capabilities, it seems to cause no harm, so
this change primarily serves as cleanup.

Signed-off-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlx5/core/en_stats.c    | 24 ++++++++-----------
 1 file changed, 10 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 611ec4b6f3709..77d34037b92bb 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1272,11 +1272,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 
 	ethtool_puts(data, "link_down_events_phy");
 
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
-
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-		ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
+		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+			ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
@@ -1294,15 +1292,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 		data, MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
 			       counter_set.phys_layer_cntrs.link_down_events));
 
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
-
-	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-		mlx5e_ethtool_put_stat(
-			data,
-			MLX5E_READ_CTR64_BE(
-				&priv->stats.pport.phy_statistical_counters,
-				pport_phy_statistical_stats_desc, i));
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
+		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
+			mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR64_BE(
+					&priv->stats.pport.phy_statistical_counters,
+					pport_phy_statistical_stats_desc, i));
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)

From 5b0804442561226a8706bded9c05dbd4f5fc1ff9 Mon Sep 17 00:00:00 2001
From: Yael Chemla <ychemla@nvidia.com>
Date: Sun, 16 Mar 2025 10:14:34 +0200
Subject: [PATCH 2489/2753] net/mlx5e: Access PHY layer counter group as other
 counter groups

Adjust the way physical layer counters group is accessed to match the
generic method used for accessing other PPCNT counter groups.

Signed-off-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlx5/core/en_stats.c    | 25 +++++++++++++------
 1 file changed, 18 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 77d34037b92bb..0cf0c920532f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1227,6 +1227,13 @@ void mlx5e_stats_ts_get(struct mlx5e_priv *priv,
 	mutex_unlock(&priv->state_lock);
 }
 
+#define PPORT_PHY_LAYER_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, \
+		      counter_set.phys_layer_cntrs.c)
+static const struct counter_desc pport_phy_layer_cntrs_stats_desc[] = {
+	{ "link_down_events_phy", PPORT_PHY_LAYER_OFF(link_down_events) }
+};
+
 #define PPORT_PHY_STATISTICAL_OFF(c) \
 	MLX5_BYTE_OFF(ppcnt_reg, \
 		      counter_set.phys_layer_statistical_cntrs.c##_high)
@@ -1243,6 +1250,8 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 	{ "rx_err_lane_3_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits_lane3) },
 };
 
+#define NUM_PPORT_PHY_LAYER_COUNTERS \
+	ARRAY_SIZE(pport_phy_layer_cntrs_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
@@ -1253,8 +1262,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int num_stats;
 
-	/* "1" for link_down_events special counter */
-	num_stats = 1;
+	num_stats = NUM_PPORT_PHY_LAYER_COUNTERS;
 
 	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group) ?
 		     NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0;
@@ -1270,7 +1278,8 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	ethtool_puts(data, "link_down_events_phy");
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		ethtool_puts(data, pport_phy_layer_cntrs_stats_desc[i].format);
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
@@ -1287,10 +1296,12 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 	struct mlx5_core_dev *mdev = priv->mdev;
 	int i;
 
-	/* link_down_events_phy has special handling since it is not stored in __be64 format */
-	mlx5e_ethtool_put_stat(
-		data, MLX5_GET(ppcnt_reg, priv->stats.pport.phy_counters,
-			       counter_set.phys_layer_cntrs.link_down_events));
+	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
+		mlx5e_ethtool_put_stat(
+				data,
+				MLX5E_READ_CTR32_BE(&priv->stats.pport
+					.phy_counters,
+					pport_phy_layer_cntrs_stats_desc, i));
 
 	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
 		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)

From 057fcad53d0ce8d607f61995bba157fb823d89ae Mon Sep 17 00:00:00 2001
From: Yael Chemla <ychemla@nvidia.com>
Date: Sun, 16 Mar 2025 10:14:35 +0200
Subject: [PATCH 2490/2753] net/mlx5e: Get counter group size by FW capability

Retrieve the number of fields supported by each PPCNT counter group
based on the FW capability for this group.

Signed-off-by: Yael Chemla <ychemla@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlx5/core/en_stats.c    | 58 ++++++++++---------
 1 file changed, 31 insertions(+), 27 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index 0cf0c920532f5..a417962acfa9b 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1257,6 +1257,13 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_err_lanes_stats_desc)
 
+#define NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_statistical_group) ? \
+	NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0)
+#define NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, per_lane_error_counters) ? \
+	NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0)
+
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 {
 	struct mlx5_core_dev *mdev = priv->mdev;
@@ -1264,11 +1271,9 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 
 	num_stats = NUM_PPORT_PHY_LAYER_COUNTERS;
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group) ?
-		     NUM_PPORT_PHY_STATISTICAL_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev);
 
-	num_stats += MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters) ?
-		     NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0;
+	num_stats += NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
 
 	return num_stats;
 }
@@ -1281,14 +1286,15 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 	for (i = 0; i < NUM_PPORT_PHY_LAYER_COUNTERS; i++)
 		ethtool_puts(data, pport_phy_layer_cntrs_stats_desc[i].format);
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-			ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
+		ethtool_puts(data, pport_phy_statistical_stats_desc[i].format);
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			ethtool_puts(data,
-				     pport_phy_statistical_err_lanes_stats_desc[i].format);
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		ethtool_puts(data,
+			     pport_phy_statistical_err_lanes_stats_desc[i]
+			     .format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
@@ -1303,23 +1309,21 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 					.phy_counters,
 					pport_phy_layer_cntrs_stats_desc, i));
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_COUNTERS; i++)
-			mlx5e_ethtool_put_stat(
-				data,
-				MLX5E_READ_CTR64_BE(
-					&priv->stats.pport.phy_statistical_counters,
-					pport_phy_statistical_stats_desc, i));
+	for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(mdev); i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(
+				&priv->stats.pport.phy_statistical_counters,
+				pport_phy_statistical_stats_desc, i));
 
-	if (MLX5_CAP_PCAM_FEATURE(mdev, per_lane_error_counters))
-		for (i = 0; i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS; i++)
-			mlx5e_ethtool_put_stat(
-				data,
-				MLX5E_READ_CTR64_BE(
-					&priv->stats.pport
-						 .phy_statistical_counters,
-					pport_phy_statistical_err_lanes_stats_desc,
-					i));
+	for (i = 0;
+	     i < NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
+	     i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR64_BE(
+				&priv->stats.pport.phy_statistical_counters,
+				pport_phy_statistical_err_lanes_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)

From 6ec03fdaa109d99ea8b5e131f5966f93cb389476 Mon Sep 17 00:00:00 2001
From: Yael Chemla <ychemla@nvidia.com>
Date: Sun, 16 Mar 2025 10:14:36 +0200
Subject: [PATCH 2491/2753] net/mlx5e: Expose port reset cycle recovery counter
 via ethtool

Display recovery event of PPCNT recovery counters group. Counts (per
link) the number of total successful recovery events of any recovery
types during port reset cycle.

Signed-off-by: Yael Chemla <ychemla@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlx5/counters.rst       |  5 +++
 .../ethernet/mellanox/mlx5/core/en_stats.c    | 44 ++++++++++++++++---
 .../ethernet/mellanox/mlx5/core/en_stats.h    |  4 ++
 3 files changed, 48 insertions(+), 5 deletions(-)

diff --git a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
index 99d95be4d159f..43d72c8b713b1 100644
--- a/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
+++ b/Documentation/networking/device_drivers/ethernet/mellanox/mlx5/counters.rst
@@ -1082,6 +1082,11 @@ like flow control, FEC and more.
        need to replace the cable/transceiver.
      - Error
 
+   * - `total_success_recovery_phy`
+     - The number of total successful recovery events of any type during
+       ports reset cycle.
+     - Error
+
    * - `rx_out_of_buffer`
      - Number of times receive queue had no software buffers allocated for the
        adapter's incoming traffic.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index a417962acfa9b..acb00fd7efa4c 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -1250,12 +1250,22 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 	{ "rx_err_lane_3_phy", PPORT_PHY_STATISTICAL_OFF(phy_corrected_bits_lane3) },
 };
 
+#define PPORT_PHY_RECOVERY_OFF(c) \
+	MLX5_BYTE_OFF(ppcnt_reg, counter_set.phys_layer_recovery_cntrs.c)
+static const struct counter_desc
+pport_phy_recovery_cntrs_stats_desc[] = {
+	{ "total_success_recovery_phy",
+	  PPORT_PHY_RECOVERY_OFF(total_successful_recovery_events) }
+};
+
 #define NUM_PPORT_PHY_LAYER_COUNTERS \
 	ARRAY_SIZE(pport_phy_layer_cntrs_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_stats_desc)
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS \
 	ARRAY_SIZE(pport_phy_statistical_err_lanes_stats_desc)
+#define NUM_PPORT_PHY_RECOVERY_COUNTERS \
+	ARRAY_SIZE(pport_phy_recovery_cntrs_stats_desc)
 
 #define NUM_PPORT_PHY_STATISTICAL_LOOPBACK_COUNTERS(dev) \
 	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_statistical_group) ? \
@@ -1263,6 +1273,9 @@ pport_phy_statistical_err_lanes_stats_desc[] = {
 #define NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(dev) \
 	(MLX5_CAP_PCAM_FEATURE(dev, per_lane_error_counters) ? \
 	NUM_PPORT_PHY_STATISTICAL_PER_LANE_COUNTERS : 0)
+#define NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(dev) \
+	(MLX5_CAP_PCAM_FEATURE(dev, ppcnt_recovery_counters) ? \
+	NUM_PPORT_PHY_RECOVERY_COUNTERS : 0)
 
 static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 {
@@ -1275,6 +1288,7 @@ static MLX5E_DECLARE_STATS_GRP_OP_NUM_STATS(phy)
 
 	num_stats += NUM_PPORT_PHY_STATISTICAL_PER_LANE_LOOPBACK_COUNTERS(mdev);
 
+	num_stats += NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev);
 	return num_stats;
 }
 
@@ -1295,6 +1309,10 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STRS(phy)
 		ethtool_puts(data,
 			     pport_phy_statistical_err_lanes_stats_desc[i]
 			     .format);
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		ethtool_puts(data,
+			     pport_phy_recovery_cntrs_stats_desc[i].format);
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
@@ -1324,6 +1342,13 @@ static MLX5E_DECLARE_STATS_GRP_OP_FILL_STATS(phy)
 			MLX5E_READ_CTR64_BE(
 				&priv->stats.pport.phy_statistical_counters,
 				pport_phy_statistical_err_lanes_stats_desc, i));
+
+	for (i = 0; i < NUM_PPORT_PHY_RECOVERY_LOOPBACK_COUNTERS(mdev); i++)
+		mlx5e_ethtool_put_stat(
+			data,
+			MLX5E_READ_CTR32_BE(
+				&priv->stats.pport.phy_recovery_counters,
+				pport_phy_recovery_cntrs_stats_desc, i));
 }
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
@@ -1339,12 +1364,21 @@ static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(phy)
 	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_COUNTERS_GROUP);
 	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
 
-	if (!MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group))
-		return;
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_statistical_group)) {
+		out = pstats->phy_statistical_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 
-	out = pstats->phy_statistical_counters;
-	MLX5_SET(ppcnt_reg, in, grp, MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP);
-	mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0);
+	if (MLX5_CAP_PCAM_FEATURE(mdev, ppcnt_recovery_counters)) {
+		out = pstats->phy_recovery_counters;
+		MLX5_SET(ppcnt_reg, in, grp,
+			 MLX5_PHYSICAL_LAYER_RECOVERY_GROUP);
+		mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0,
+				     0);
+	}
 }
 
 void mlx5e_get_link_ext_stats(struct net_device *dev,
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 5961c569cfe01..0d87947e348df 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -309,6 +309,9 @@ struct mlx5e_vport_stats {
 #define PPORT_PHY_STATISTICAL_GET(pstats, c) \
 	MLX5_GET64(ppcnt_reg, (pstats)->phy_statistical_counters, \
 		   counter_set.phys_layer_statistical_cntrs.c##_high)
+#define PPORT_PHY_RECOVERY_GET(pstats, c) \
+	MLX5_GET64(ppcnt_reg, (pstats)->phy_recovery_counters, \
+		   counter_set.phys_layer_recovery_cntrs.c)
 #define PPORT_PER_PRIO_GET(pstats, prio, c) \
 	MLX5_GET64(ppcnt_reg, pstats->per_prio_counters[prio], \
 		   counter_set.eth_per_prio_grp_data_layout.c##_high)
@@ -324,6 +327,7 @@ struct mlx5e_pport_stats {
 	__be64 per_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 phy_statistical_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
+	__be64 phy_recovery_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];
 	__be64 per_tc_congest_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)];

From d72a6f6f8959da298bf4a9cfa3ea52faefb15891 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Niklas=20S=C3=B6derlund?=
 <niklas.soderlund+renesas@ragnatech.se>
Date: Sun, 16 Mar 2025 12:20:33 +0100
Subject: [PATCH 2492/2753] net: phy: marvell-88q2xxx: Enable temperature
 sensor for mv88q211x
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The temperature sensor enabled for mv88q222x devices also functions for
mv88q211x based devices. Unify the two devices probe functions to enable
the sensors for all devices supported by this driver.

The same oddity as for mv88q222x devices exists, the PHY must be up for
a correct temperature reading to be reported.

    # cat /sys/class/hwmon/hwmon9/temp1_input
    -75000

    # ifconfig end5 up

    # cat /sys/class/hwmon/hwmon9/temp1_input
    59000

Worth noting is that while the temperature register offsets and layout
are the same between mv88q211x and mv88q222x devices their names in the
datasheets are different. This change keeps the mv88q222x names for the
mv88q211x support.

Signed-off-by: Niklas Söderlund <niklas.soderlund+renesas@ragnatech.se>
Reviewed-by: Dimitri Fedrau <dima.fedrau@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/marvell-88q2xxx.c | 14 ++------------
 1 file changed, 2 insertions(+), 12 deletions(-)

diff --git a/drivers/net/phy/marvell-88q2xxx.c b/drivers/net/phy/marvell-88q2xxx.c
index 23e1f0521f549..5c687164b8e06 100644
--- a/drivers/net/phy/marvell-88q2xxx.c
+++ b/drivers/net/phy/marvell-88q2xxx.c
@@ -828,6 +828,7 @@ static int mv88q2xxx_leds_probe(struct phy_device *phydev)
 static int mv88q2xxx_probe(struct phy_device *phydev)
 {
 	struct mv88q2xxx_priv *priv;
+	int ret;
 
 	priv = devm_kzalloc(&phydev->mdio.dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
@@ -835,17 +836,6 @@ static int mv88q2xxx_probe(struct phy_device *phydev)
 
 	phydev->priv = priv;
 
-	return 0;
-}
-
-static int mv88q222x_probe(struct phy_device *phydev)
-{
-	int ret;
-
-	ret = mv88q2xxx_probe(phydev);
-	if (ret)
-		return ret;
-
 	ret = mv88q2xxx_leds_probe(phydev);
 	if (ret)
 		return ret;
@@ -1118,7 +1108,7 @@ static struct phy_driver mv88q2xxx_driver[] = {
 		.phy_id_mask		= MARVELL_PHY_ID_MASK,
 		.name			= "mv88q2220",
 		.flags			= PHY_POLL_CABLE_TEST,
-		.probe			= mv88q222x_probe,
+		.probe			= mv88q2xxx_probe,
 		.get_features		= mv88q2xxx_get_features,
 		.config_aneg		= mv88q2xxx_config_aneg,
 		.aneg_done		= genphy_c45_aneg_done,

From 0957f6f27c2f59afa416cf164fe57725c4751d17 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 16 Mar 2025 11:51:11 +0000
Subject: [PATCH 2493/2753] net: phy: fix genphy_c45_eee_is_active() for
 disabled EEE

Commit 809265fe96fe ("net: phy: c45: remove local advertisement
parameter from genphy_c45_eee_is_active") stopped reading the local
advertisement from the PHY earlier in this development cycle, which
broke "ethtool --set-eee ethX eee off".

When ethtool is used to set EEE off, genphy_c45_eee_is_active()
indicates that EEE was active if the link partner reported an
advertisement, which causes phylib to set phydev->enable_tx_lpi on
link up, despite our local advertisement in hardware being empty.
However, phydev->advertising_eee is preserved while EEE is turned off,
which leads to genphy_c45_eee_is_active() incorrectly reporting that
EEE is active.

Fix it by checking phydev->eee_cfg.eee_enabled, and if clear,
immediately indicate that EEE is not active.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/phy-c45.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index 8a0ffc3174ecf..bdd70d424491b 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1479,6 +1479,9 @@ int genphy_c45_eee_is_active(struct phy_device *phydev, unsigned long *lp)
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(common);
 	int ret;
 
+	if (!phydev->eee_cfg.eee_enabled)
+		return 0;
+
 	ret = genphy_c45_read_eee_lpa(phydev, tmp_lp);
 	if (ret)
 		return ret;

From a14b343f9930f2d5947dcbe38332a37d991971cf Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Sun, 16 Mar 2025 12:39:54 +0000
Subject: [PATCH 2494/2753] net: phy: realtek: disable PHY-mode EEE

Realtek RTL8211F has a "PHY-mode" EEE support which interferes with an
IEEE 802.3 compliant implementation. This mode defaults to enabled, and
results in the MAC receive path not seeing the link transition to LPI
state.

Fix this by disabling PHY-mode EEE.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/realtek/realtek_main.c | 11 +++++++++--
 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/phy/realtek/realtek_main.c b/drivers/net/phy/realtek/realtek_main.c
index 7a0b19d66acac..893c824796715 100644
--- a/drivers/net/phy/realtek/realtek_main.c
+++ b/drivers/net/phy/realtek/realtek_main.c
@@ -33,6 +33,9 @@
 
 #define RTL8211F_PHYCR1				0x18
 #define RTL8211F_PHYCR2				0x19
+#define RTL8211F_CLKOUT_EN			BIT(0)
+#define RTL8211F_PHYCR2_PHY_EEE_ENABLE		BIT(5)
+
 #define RTL8211F_INSR				0x1d
 
 #define RTL8211F_LEDCR				0x10
@@ -55,8 +58,6 @@
 #define RTL8211E_TX_DELAY			BIT(12)
 #define RTL8211E_RX_DELAY			BIT(11)
 
-#define RTL8211F_CLKOUT_EN			BIT(0)
-
 #define RTL8201F_ISR				0x1e
 #define RTL8201F_ISR_ANERR			BIT(15)
 #define RTL8201F_ISR_DUPLEX			BIT(13)
@@ -453,6 +454,12 @@ static int rtl8211f_config_init(struct phy_device *phydev)
 			str_enabled_disabled(val_rxdly));
 	}
 
+	/* Disable PHY-mode EEE so LPI is passed to the MAC */
+	ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2,
+			       RTL8211F_PHYCR2_PHY_EEE_ENABLE, 0);
+	if (ret)
+		return ret;
+
 	if (priv->has_phycr2) {
 		ret = phy_modify_paged(phydev, 0xa43, RTL8211F_PHYCR2,
 				       RTL8211F_CLKOUT_EN, priv->phycr2);

From 34d18583c2242d535f2beb7dc6219acc96f9b5a4 Mon Sep 17 00:00:00 2001
From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Date: Sun, 16 Mar 2025 16:27:15 +0100
Subject: [PATCH 2495/2753] Documentation: netlink: specs: tc: Add DualPI2
 specification

Describe the specification of tc qdisc DualPI2 stats and attributes,
which is the reference implementation of IETF RFC9332 DualQ Coupled AQM
(https://datatracker.ietf.org/doc/html/rfc9332) to provide two queues
called low latency and classic.

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/tc.yaml | 144 ++++++++++++++++++++++++++++
 1 file changed, 144 insertions(+)

diff --git a/Documentation/netlink/specs/tc.yaml b/Documentation/netlink/specs/tc.yaml
index aacccea5dfe42..0fb9719352857 100644
--- a/Documentation/netlink/specs/tc.yaml
+++ b/Documentation/netlink/specs/tc.yaml
@@ -816,6 +816,58 @@ definitions:
       -
         name: drop-overmemory
         type: u32
+  -
+    name: tc-dualpi2-xstats
+    type: struct
+    members:
+      -
+        name: prob
+        type: u32
+        doc: Current probability
+      -
+        name: delay_c
+        type: u32
+        doc: Current C-queue delay in microseconds
+      -
+        name: delay_l
+        type: u32
+        doc: Current L-queue delay in microseconds
+      -
+        name: pkts_in_c
+        type: u32
+        doc: Number of packets enqueued in the C-queue
+      -
+        name: pkts_in_l
+        type: u32
+        doc: Number of packets enqueued in the L-queue
+      -
+        name: maxq
+        type: u32
+        doc: Maximum number of packets seen by the DualPI2
+      -
+        name: ecn_mark
+        type: u32
+        doc: All packets marked with ecn
+      -
+        name: step_mark
+        type: u32
+        doc: Only packets marked with ecn due to L-queue step AQM
+      -
+        name: credit
+        type: s32
+        doc: Current credit value for WRR
+      -
+        name: memory_used
+        type: u32
+        doc: Memory used in bytes by the DualPI2
+      -
+        name: max_memory_used
+        type: u32
+        doc: Maximum memory used in bytes by the DualPI2
+      -
+        name: memory_limit
+        type: u32
+        doc: Memory limit in bytes
   -
     name: tc-fq-pie-xstats
     type: struct
@@ -2299,6 +2351,92 @@ attribute-sets:
       -
         name: quantum
         type: u32
+  -
+    name: tc-dualpi2-attrs
+    attributes:
+      -
+        name: limit
+        type: u32
+        doc: Limit of total number of packets in queue
+      -
+        name: memlimit
+        type: u32
+        doc: Memory limit of total number of packets in queue
+      -
+        name: target
+        type: u32
+        doc: Classic target delay in microseconds
+      -
+        name: tupdate
+        type: u32
+        doc: Drop probability update interval time in microseconds
+      -
+        name: alpha
+        type: u32
+        doc: Integral gain factor in Hz for PI controller
+      -
+        name: beta
+        type: u32
+        doc: Proportional gain factor in Hz for PI controller
+      -
+        name: step_thresh
+        type: u32
+        doc: L4S step marking threshold in microseconds or in packet (see step_packets)
+      -
+        name: step_packets
+        type: flags
+        doc: L4S Step marking threshold unit
+        entries:
+        - microseconds
+        - packets
+      -
+        name: min_qlen_step
+        type: u32
+        doc: Pacekts enqueued to the L-queue can apply the step threshold when the queue length of L-queue is larger than this value. (0 is recommended)
+      -
+        name: coupling_factor
+        type: u8
+        doc: Probability coupling factor between Classic and L4S (2 is recommended)
+      -
+        name: drop_overload
+        type: flags
+        doc: Control the overload strategy (drop to preserve latency or let the queue overflow)
+        entries:
+        - drop_on_overload
+        - overflow
+      -
+        name: drop_early
+        type: flags
+        doc: Decide where the Classic packets are PI-based dropped or marked
+        entries:
+        - drop_enqueue
+        - drop_dequeue
+      -
+        name: classic_protection
+        type: u8
+        doc:  Classic WRR weight in percentage (from 0 to 100)
+      -
+        name: ecn_mask
+        type: flags
+        doc: Configure the L-queue ECN classifier
+        entries:
+        - l4s_ect
+        - any_ect
+      -
+        name: gso_split
+        type: flags
+        doc: Split aggregated skb or not
+        entries:
+        - split_gso
+        - no_split_gso
+      -
+        name: max_rtt
+        type: u32
+        doc: The maximum expected RTT of the traffic that is controlled by DualPI2 in usec
+      -
+        name: typical_rtt
+        type: u32
+        doc: The typical base RTT of the traffic that is controlled by DualPI2 in usec
   -
     name: tc-ematch-attrs
     attributes:
@@ -3679,6 +3817,9 @@ sub-messages:
       -
         value: drr
         attribute-set: tc-drr-attrs
+      -
+        value: dualpi2
+        attribute-set: tc-dualpi2-attrs
       -
         value: etf
         attribute-set: tc-etf-attrs
@@ -3846,6 +3987,9 @@ sub-messages:
       -
         value: codel
         fixed-header: tc-codel-xstats
+      -
+        value: dualpi2
+        fixed-header: tc-dualpi2-xstats
       -
         value: fq
         fixed-header: tc-fq-qd-stats

From 5f9a8b76c8878a2e7e2cd9d2e02145e69bc9157f Mon Sep 17 00:00:00 2001
From: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Date: Sun, 16 Mar 2025 16:27:16 +0100
Subject: [PATCH 2496/2753] selftests/tc-testing: Add selftests for qdisc
 DualPI2

Update configuration and preload DualPI2 module for self-tests, and
add the folloiwng self-tests for DualPI2:

  Test a4c7: Create DualPI2 with default setting
  Test 2130: Create DualPI2 with typical_rtt and max_rtt
  Test 90c1: Create DualPI2 with max_rtt
  Test 7b3c: Create DualPI2 with any_ect option
  Test 49a3: Create DualPI2 with overflow option
  Test d0a1: Create DualPI2 with drop_enqueue option
  Test f051: Create DualPI2 with no_split_gso option

Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/tc-testing/config     |   1 +
 .../tc-testing/tc-tests/qdiscs/dualpi2.json   | 149 ++++++++++++++++++
 tools/testing/selftests/tc-testing/tdc.sh     |   1 +
 3 files changed, 151 insertions(+)
 create mode 100644 tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json

diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config
index db176fe7d0c3f..72b5f36f6731b 100644
--- a/tools/testing/selftests/tc-testing/config
+++ b/tools/testing/selftests/tc-testing/config
@@ -30,6 +30,7 @@ CONFIG_NET_SCH_CBS=m
 CONFIG_NET_SCH_CHOKE=m
 CONFIG_NET_SCH_CODEL=m
 CONFIG_NET_SCH_DRR=m
+CONFIG_NET_SCH_DUALPI2=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_FQ_CODEL=m
diff --git a/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json
new file mode 100644
index 0000000000000..1080074f2650e
--- /dev/null
+++ b/tools/testing/selftests/tc-testing/tc-tests/qdiscs/dualpi2.json
@@ -0,0 +1,149 @@
+[
+    {
+        "id": "a4c7",
+        "name": "Create DualPI2 with default setting",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* l4s_ect.* drop_on_overload.* drop_dequeue.* split_gso.*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "2130",
+        "name": "Create DualPI2 with typical_rtt and max_rtt",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 typical_rtt 20ms max_rtt 200ms",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 20ms tupdate 20ms alpha 0.042969 beta 1.496094",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "90c1",
+        "name": "Create DualPI2 with max_rtt",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 max_rtt 300ms",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* target 50ms tupdate 50ms alpha 0.050781 beta 0.996094",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "7b3c",
+        "name": "Create DualPI2 with any_ect option",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 any_ect",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* any_ect",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "49a3",
+        "name": "Create DualPI2 with overflow option",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 overflow",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p.* overflow",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "d0a1",
+        "name": "Create DualPI2 with drop_enqueue option",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 drop_enqueue",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* drop_enqueue",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    },
+    {
+        "id": "f051",
+        "name": "Create DualPI2 with no_split_gso option",
+        "category": [
+            "qdisc",
+            "dualpi2"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+        ],
+        "cmdUnderTest": "$TC qdisc add dev $DUMMY handle 1: root dualpi2 no_split_gso",
+        "expExitCode": "0",
+        "verifyCmd": "$TC qdisc show dev $DUMMY",
+        "matchPattern": "qdisc dualpi2 1: root refcnt [0-9]+ limit 10000p .* no_split_gso",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root"
+        ]
+    }
+]
diff --git a/tools/testing/selftests/tc-testing/tdc.sh b/tools/testing/selftests/tc-testing/tdc.sh
index cddff1772e104..e64e8acb77ae5 100755
--- a/tools/testing/selftests/tc-testing/tdc.sh
+++ b/tools/testing/selftests/tc-testing/tdc.sh
@@ -63,4 +63,5 @@ try_modprobe sch_hfsc
 try_modprobe sch_hhf
 try_modprobe sch_htb
 try_modprobe sch_teql
+try_modprobe sch_dualpi2
 ./tdc.py -J`nproc`

From 7fd51f8525129fc498a7fa82359ab5608db9be42 Mon Sep 17 00:00:00 2001
From: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Date: Sun, 16 Mar 2025 16:27:17 +0100
Subject: [PATCH 2497/2753] sched: Add dualpi2 qdisc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DualPI2 provides L4S-type low latency & loss to traffic that uses a
scalable congestion controller (e.g. TCP-Prague, DCTCP) without
degrading the performance of 'classic' traffic (e.g. Reno,
Cubic etc.). It is to be the reference implementation of IETF RFC9332
DualQ Coupled AQM (https://datatracker.ietf.org/doc/html/rfc9332).

Note that creating two independent queues cannot meet the goal of
DualPI2 mentioned in RFC9332: "...to preserve fairness between
ECN-capable and non-ECN-capable traffic." Further, it could even
lead to starvation of Classic traffic, which is also inconsistent
with the requirements in RFC9332: "...although priority MUST be
bounded in order not to starve Classic traffic." DualPI2 is
designed to maintain approximate per-flow fairness on L-queue and
C-queue by forming a single qdisc using the coupling factor and
scheduler between two queues.

The qdisc provides two queues called low latency and classic. It
classifies packets based on the ECN field in the IP headers. By
default it directs non-ECN and ECT(0) into the classic queue and
ECT(1) and CE into the low latency queue, as per the IETF spec.

Each queue runs its own AQM:
* The classic AQM is called PI2, which is similar to the PIE AQM but
  more responsive and simpler. Classic traffic requires a decent
  target queue (default 15ms for Internet deployment) to fully
  utilize the link and to avoid high drop rates.
* The low latency AQM is, by default, a very shallow ECN marking
  threshold (1ms) similar to that used for DCTCP.

The DualQ isolates the low queuing delay of the Low Latency queue
from the larger delay of the 'Classic' queue. However, from a
bandwidth perspective, flows in either queue will share out the link
capacity as if there was just a single queue. This bandwidth pooling
effect is achieved by coupling together the drop and ECN-marking
probabilities of the two AQMs.

The PI2 AQM has two main parameters in addition to its target delay.
The integral gain factor alpha is used to slowly correct any persistent
standing queue error from the target delay, while the proportional gain
factor beta is used to quickly compensate for queue changes (growth or
shrinkage). Either alpha and beta are given as a parameter, or they can
be calculated by tc from alternative typical and maximum RTT parameters.

Internally, the output of a linear Proportional Integral (PI)
controller is used for both queues. This output is squared to
calculate the drop or ECN-marking probability of the classic queue.
This counterbalances the square-root rate equation of Reno/Cubic,
which is the trick that balances flow rates across the queues. For
the ECN-marking probability of the low latency queue, the output of
the base AQM is multiplied by a coupling factor. This determines the
balance between the flow rates in each queue. The default setting
makes the flow rates roughly equal, which should be generally
applicable.

If DUALPI2 AQM has detected overload (due to excessive non-responsive
traffic in either queue), it will switch to signaling congestion
solely using drop, irrespective of the ECN field. Alternatively, it
can be configured to limit the drop probability and let the queue
grow and eventually overflow (like tail-drop).

GSO splitting in DUALPI2 is configurable from userspace while the
default behavior is to split gso. When running DUALPI2 at unshaped
10gigE with 4 download streams test, splitting gso apart results in
halving the latency with no loss in throughput:

Summary of tcp_4down run 'no_split_gso':
                         avg         median      # data pts
 Ping (ms) ICMP   :       0.53      0.30 ms         350
 TCP download avg :    2326.86       N/A Mbits/s    350
 TCP download sum :    9307.42       N/A Mbits/s    350
 TCP download::1  :    2672.99   2568.73 Mbits/s    350
 TCP download::2  :    2586.96   2570.51 Mbits/s    350
 TCP download::3  :    1786.26   1798.82 Mbits/s    350
 TCP download::4  :    2261.21   2309.49 Mbits/s    350

Summart of tcp_4down run 'split_gso':
                         avg          median      # data pts
 Ping (ms) ICMP   :       0.22      0.23 ms         350
 TCP download avg :    2335.02       N/A Mbits/s    350
 TCP download sum :    9340.09       N/A Mbits/s    350
 TCP download::1  :    2335.30   2334.22 Mbits/s    350
 TCP download::2  :    2334.72   2334.20 Mbits/s    350
 TCP download::3  :    2335.28   2334.58 Mbits/s    350
 TCP download::4  :    2334.79   2334.39 Mbits/s    350

A similar result is observed when running DUALPI2 at unshaped 1gigE
with 1 download stream test:

Summary of tcp_1down run 'no_split_gso':
                         avg         median      # data pts
 Ping (ms) ICMP :         1.13      1.25 ms         350
 TCP download   :       941.41    941.46 Mbits/s    350

Summart of tcp_1down run 'split_gso':
                         avg         median      # data pts
 Ping (ms) ICMP :         0.51      0.55 ms         350
 TCP download   :       941.41    941.45 Mbits/s    350

Additional details can be found in the draft:
  https://datatracker.ietf.org/doc/html/rfc9332

Signed-off-by: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
Co-developed-by: Olga Albisser <olga@albisser.org>
Signed-off-by: Olga Albisser <olga@albisser.org>
Co-developed-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Signed-off-by: Olivier Tilmans <olivier.tilmans@nokia.com>
Co-developed-by: Henrik Steen <henrist@henrist.net>
Signed-off-by: Henrik Steen <henrist@henrist.net>
Signed-off-by: Bob Briscoe <research@bobbriscoe.net>
Signed-off-by: Ilpo Järvinen <ij@kernel.org>
Co-developed-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Signed-off-by: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
Acked-by: Dave Taht <dave.taht@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/netdevice.h      |    1 +
 include/uapi/linux/pkt_sched.h |   39 ++
 net/sched/Kconfig              |   12 +
 net/sched/Makefile             |    1 +
 net/sched/sch_dualpi2.c        | 1090 ++++++++++++++++++++++++++++++++
 5 files changed, 1143 insertions(+)
 create mode 100644 net/sched/sch_dualpi2.c

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 0c5b1f7f8f3af..b1d92e12a6ae1 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -30,6 +30,7 @@
 #include <asm/byteorder.h>
 #include <asm/local.h>
 
+#include <linux/netdev_features.h>
 #include <linux/percpu.h>
 #include <linux/rculist.h>
 #include <linux/workqueue.h>
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 25a9a47001cdd..62fec34c10050 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1210,4 +1210,43 @@ enum {
 
 #define TCA_ETS_MAX (__TCA_ETS_MAX - 1)
 
+/* DUALPI2 */
+enum {
+	TCA_DUALPI2_UNSPEC,
+	TCA_DUALPI2_LIMIT,		/* Packets */
+	TCA_DUALPI2_MEMORY_LIMIT,	/* Bytes */
+	TCA_DUALPI2_TARGET,		/* us */
+	TCA_DUALPI2_TUPDATE,		/* us */
+	TCA_DUALPI2_ALPHA,		/* Hz scaled up by 256 */
+	TCA_DUALPI2_BETA,		/* HZ scaled up by 256 */
+	TCA_DUALPI2_STEP_THRESH,	/* Packets or us */
+	TCA_DUALPI2_STEP_PACKETS,	/* Whether STEP_THRESH is in packets */
+	TCA_DUALPI2_MIN_QLEN_STEP,	/* Minimum qlen to apply STEP_THRESH */
+	TCA_DUALPI2_COUPLING,		/* Coupling factor between queues */
+	TCA_DUALPI2_DROP_OVERLOAD,	/* Whether to drop on overload */
+	TCA_DUALPI2_DROP_EARLY,		/* Whether to drop on enqueue */
+	TCA_DUALPI2_C_PROTECTION,	/* Percentage */
+	TCA_DUALPI2_ECN_MASK,		/* L4S queue classification mask */
+	TCA_DUALPI2_SPLIT_GSO,		/* Split GSO packets at enqueue */
+	TCA_DUALPI2_PAD,
+	__TCA_DUALPI2_MAX
+};
+
+#define TCA_DUALPI2_MAX   (__TCA_DUALPI2_MAX - 1)
+
+struct tc_dualpi2_xstats {
+	__u32 prob;		/* current probability */
+	__u32 delay_c;		/* current delay in C queue */
+	__u32 delay_l;		/* current delay in L queue */
+	__s32 credit;		/* current c_protection credit */
+	__u32 packets_in_c;	/* number of packets enqueued in C queue */
+	__u32 packets_in_l;	/* number of packets enqueued in L queue */
+	__u32 maxq;		/* maximum queue size */
+	__u32 ecn_mark;		/* packets marked with ecn*/
+	__u32 step_marks;	/* ECN marks due to the step AQM */
+	__u32 memory_used;	/* Meory used of both queues */
+	__u32 max_memory_used;	/* Maximum used memory */
+	__u32 memory_limit;	/* Memory limit of both queues */
+};
+
 #endif
diff --git a/net/sched/Kconfig b/net/sched/Kconfig
index 8180d0c12fcea..f00b5ad92ce23 100644
--- a/net/sched/Kconfig
+++ b/net/sched/Kconfig
@@ -403,6 +403,18 @@ config NET_SCH_ETS
 
 	  If unsure, say N.
 
+config NET_SCH_DUALPI2
+	tristate "Dual Queue PI Square (DUALPI2) scheduler"
+	help
+	  Say Y here if you want to use the Dual Queue Proportional Integral
+	  Controller Improved with a Square scheduling algorithm.
+	  For more information, please see https://tools.ietf.org/html/rfc9332
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called sch_dualpi2.
+
+	  If unsure, say N.
+
 menuconfig NET_SCH_DEFAULT
 	bool "Allow override default queue discipline"
 	help
diff --git a/net/sched/Makefile b/net/sched/Makefile
index 82c3f78ca486e..1abb06554057d 100644
--- a/net/sched/Makefile
+++ b/net/sched/Makefile
@@ -62,6 +62,7 @@ obj-$(CONFIG_NET_SCH_FQ_PIE)	+= sch_fq_pie.o
 obj-$(CONFIG_NET_SCH_CBS)	+= sch_cbs.o
 obj-$(CONFIG_NET_SCH_ETF)	+= sch_etf.o
 obj-$(CONFIG_NET_SCH_TAPRIO)	+= sch_taprio.o
+obj-$(CONFIG_NET_SCH_DUALPI2)	+= sch_dualpi2.o
 
 obj-$(CONFIG_NET_CLS_U32)	+= cls_u32.o
 obj-$(CONFIG_NET_CLS_ROUTE4)	+= cls_route.o
diff --git a/net/sched/sch_dualpi2.c b/net/sched/sch_dualpi2.c
new file mode 100644
index 0000000000000..73d0e65829a0d
--- /dev/null
+++ b/net/sched/sch_dualpi2.c
@@ -0,0 +1,1090 @@
+// SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+/* Copyright (C) 2024 Nokia
+ *
+ * Author: Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>
+ * Author: Olga Albisser <olga@albisser.org>
+ * Author: Henrik Steen <henrist@henrist.net>
+ * Author: Olivier Tilmans <olivier.tilmans@nokia.com>
+ * Author: Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>
+ *
+ * DualPI Improved with a Square (dualpi2):
+ * - Supports congestion controls that comply with the Prague requirements
+ *   in RFC9331 (e.g. TCP-Prague)
+ * - Supports coupled dual-queue with PI2 as defined in RFC9332
+ * - Supports ECN L4S-identifier (IP.ECN==0b*1)
+ *
+ * note: Although DCTCP and BBRv3 can use shallow-threshold ECN marks,
+ *   they do not meet the 'Prague L4S Requirements' listed in RFC 9331
+ *   Section 4, so they can only be used with DualPI2 in a datacenter
+ *   context.
+ *
+ * References:
+ * - RFC9332: https://datatracker.ietf.org/doc/html/rfc9332
+ * - De Schepper, Koen, et al. "PI 2: A linearized AQM for both classic and
+ *   scalable TCP."  in proc. ACM CoNEXT'16, 2016.
+ */
+
+#include <linux/errno.h>
+#include <linux/hrtimer.h>
+#include <linux/if_vlan.h>
+#include <linux/kernel.h>
+#include <linux/limits.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+
+#include <net/gso.h>
+#include <net/inet_ecn.h>
+#include <net/pkt_cls.h>
+#include <net/pkt_sched.h>
+
+/* 32b enable to support flows with windows up to ~8.6 * 1e9 packets
+ * i.e., twice the maximal snd_cwnd.
+ * MAX_PROB must be consistent with the RNG in dualpi2_roll().
+ */
+#define MAX_PROB U32_MAX
+
+/* alpha/beta values exchanged over netlink are in units of 256ns */
+#define ALPHA_BETA_SHIFT 8
+
+/* Scaled values of alpha/beta must fit in 32b to avoid overflow in later
+ * computations. Consequently (see and dualpi2_scale_alpha_beta()), their
+ * netlink-provided values can use at most 31b, i.e. be at most (2^23)-1
+ * (~4MHz) as those are given in 1/256th. This enable to tune alpha/beta to
+ * control flows whose maximal RTTs can be in usec up to few secs.
+ */
+#define ALPHA_BETA_MAX ((1U << 31) - 1)
+
+/* Internal alpha/beta are in units of 64ns.
+ * This enables to use all alpha/beta values in the allowed range without loss
+ * of precision due to rounding when scaling them internally, e.g.,
+ * scale_alpha_beta(1) will not round down to 0.
+ */
+#define ALPHA_BETA_GRANULARITY 6
+
+#define ALPHA_BETA_SCALING (ALPHA_BETA_SHIFT - ALPHA_BETA_GRANULARITY)
+
+/* We express the weights (wc, wl) in %, i.e., wc + wl = 100 */
+#define MAX_WC 100
+
+struct dualpi2_sched_data {
+	struct Qdisc *l_queue;	/* The L4S Low latency queue (L-queue) */
+	struct Qdisc *sch;	/* The Classic queue (C-queue) */
+
+	/* Registered tc filters */
+	struct {
+		struct tcf_proto __rcu *filters;
+		struct tcf_block *block;
+	} tcf;
+
+	struct { /* PI2 parameters */
+		u64	target;	/* Target delay in nanoseconds */
+		u32	tupdate;/* Timer frequency in nanoseconds */
+		u32	prob;	/* Base PI probability */
+		u32	alpha;	/* Gain factor for the integral rate response */
+		u32	beta;	/* Gain factor for the proportional response */
+		struct hrtimer timer; /* prob update timer */
+	} pi2;
+
+	struct { /* Step AQM (L-queue only) parameters */
+		u32 thresh;	/* Step threshold */
+		bool in_packets;/* Whether the step is in packets or time */
+	} step;
+
+	struct { /* C-queue starvation protection */
+		s32	credit; /* Credit (sign indicates which queue) */
+		s32	init;	/* Reset value of the credit */
+		u8	wc;	/* C-queue weight (between 0 and MAX_WC) */
+		u8	wl;	/* L-queue weight (MAX_WC - wc) */
+	} c_protection;
+
+	/* General dualQ parameters */
+	u32	memory_limit;	/* Memory limit of both queues */
+	u8	coupling_factor;/* Coupling factor (k) between both queues */
+	u8	ecn_mask;	/* Mask to match packets into L-queue */
+	u32	min_qlen_step;	/* Minimum queue length to apply step thresh */
+	bool	drop_early;	/* Drop at enqueue instead of dequeue if true */
+	bool	drop_overload;	/* Drop (1) on overload, or overflow (0) */
+	bool	split_gso;	/* Split aggregated skb (1) or leave as is */
+
+	/* Statistics */
+	u64	c_head_ts;	/* Enqueue timestamp of the C-queue head */
+	u64	l_head_ts;	/* Enqueue timestamp of the L-queue head */
+	u64	last_qdelay;	/* Q delay val at the last probability update */
+	u32	packets_in_c;	/* Enqueue packet counter of the C-queue */
+	u32	packets_in_l;	/* Enqueue packet counter of the L-queue */
+	u32	maxq;		/* Maximum queue size of the C-queue */
+	u32	ecn_mark;	/* ECN mark pkt counter due to PI probability */
+	u32	step_marks;	/* ECN mark pkt counter due to step AQM */
+	u32	memory_used;	/* Memory used of both queues */
+	u32	max_memory_used;/* Maximum used memory */
+
+	struct { /* Deferred drop statistics */
+		u32 cnt;	/* Packets dropped */
+		u32 len;	/* Bytes dropped */
+	} deferred_drops;
+};
+
+struct dualpi2_skb_cb {
+	u64 ts;			/* Timestamp at enqueue */
+	u8 apply_step:1,	/* Can we apply the step threshold */
+	   classified:2,	/* Packet classification results */
+	   ect:2;		/* Packet ECT codepoint */
+};
+
+enum dualpi2_classification_results {
+	DUALPI2_C_CLASSIC	= 0,	/* C-queue */
+	DUALPI2_C_L4S		= 1,	/* L-queue (scale mark/classic drop) */
+	DUALPI2_C_LLLL		= 2,	/* L-queue (no drops/marks) */
+	__DUALPI2_C_MAX			/* Keep last*/
+};
+
+static struct dualpi2_skb_cb *dualpi2_skb_cb(struct sk_buff *skb)
+{
+	qdisc_cb_private_validate(skb, sizeof(struct dualpi2_skb_cb));
+	return (struct dualpi2_skb_cb *)qdisc_skb_cb(skb)->data;
+}
+
+static u64 dualpi2_sojourn_time(struct sk_buff *skb, u64 reference)
+{
+	return reference - dualpi2_skb_cb(skb)->ts;
+}
+
+static u64 head_enqueue_time(struct Qdisc *q)
+{
+	struct sk_buff *skb = qdisc_peek_head(q);
+
+	return skb ? dualpi2_skb_cb(skb)->ts : 0;
+}
+
+static u32 dualpi2_scale_alpha_beta(u32 param)
+{
+	u64 tmp = ((u64)param * MAX_PROB >> ALPHA_BETA_SCALING);
+
+	do_div(tmp, NSEC_PER_SEC);
+	return tmp;
+}
+
+static u32 dualpi2_unscale_alpha_beta(u32 param)
+{
+	u64 tmp = ((u64)param * NSEC_PER_SEC << ALPHA_BETA_SCALING);
+
+	do_div(tmp, MAX_PROB);
+	return tmp;
+}
+
+static ktime_t next_pi2_timeout(struct dualpi2_sched_data *q)
+{
+	return ktime_add_ns(ktime_get_ns(), q->pi2.tupdate);
+}
+
+static bool skb_is_l4s(struct sk_buff *skb)
+{
+	return dualpi2_skb_cb(skb)->classified == DUALPI2_C_L4S;
+}
+
+static bool skb_in_l_queue(struct sk_buff *skb)
+{
+	return dualpi2_skb_cb(skb)->classified != DUALPI2_C_CLASSIC;
+}
+
+static bool dualpi2_mark(struct dualpi2_sched_data *q, struct sk_buff *skb)
+{
+	if (INET_ECN_set_ce(skb)) {
+		q->ecn_mark++;
+		return true;
+	}
+	return false;
+}
+
+static void dualpi2_reset_c_protection(struct dualpi2_sched_data *q)
+{
+	q->c_protection.credit = q->c_protection.init;
+}
+
+/* This computes the initial credit value and WRR weight for the L queue (wl)
+ * from the weight of the C queue (wc).
+ * If wl > wc, the scheduler will start with the L queue when reset.
+ */
+static void dualpi2_calculate_c_protection(struct Qdisc *sch,
+					   struct dualpi2_sched_data *q, u32 wc)
+{
+	q->c_protection.wc = wc;
+	q->c_protection.wl = MAX_WC - wc;
+	q->c_protection.init = (s32)psched_mtu(qdisc_dev(sch)) *
+		((int)q->c_protection.wc - (int)q->c_protection.wl);
+	dualpi2_reset_c_protection(q);
+}
+
+static bool dualpi2_roll(u32 prob)
+{
+	return get_random_u32() <= prob;
+}
+
+/* Packets in the C-queue are subject to a marking probability pC, which is the
+ * square of the internal PI probability (i.e., have an overall lower mark/drop
+ * probability). If the qdisc is overloaded, ignore ECT values and only drop.
+ *
+ * Note that this marking scheme is also applied to L4S packets during overload.
+ * Return true if packet dropping is required in C queue
+ */
+static bool dualpi2_classic_marking(struct dualpi2_sched_data *q,
+				    struct sk_buff *skb, u32 prob,
+				    bool overload)
+{
+	if (dualpi2_roll(prob) && dualpi2_roll(prob)) {
+		if (overload || dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT)
+			return true;
+		dualpi2_mark(q, skb);
+	}
+	return false;
+}
+
+/* Packets in the L-queue are subject to a marking probability pL given by the
+ * internal PI probability scaled by the coupling factor.
+ *
+ * On overload (i.e., @local_l_prob is >= 100%):
+ * - if the qdisc is configured to trade losses to preserve latency (i.e.,
+ *   @q->drop_overload), apply classic drops first before marking.
+ * - otherwise, preserve the "no loss" property of ECN at the cost of queueing
+ *   delay, eventually resulting in taildrop behavior once sch->limit is
+ *   reached.
+ * Return true if packet dropping is required in L queue
+ */
+static bool dualpi2_scalable_marking(struct dualpi2_sched_data *q,
+				     struct sk_buff *skb,
+				     u64 local_l_prob, u32 prob,
+				     bool overload)
+{
+	if (overload) {
+		/* Apply classic drop */
+		if (!q->drop_overload ||
+		    !(dualpi2_roll(prob) && dualpi2_roll(prob)))
+			goto mark;
+		return true;
+	}
+
+	/* We can safely cut the upper 32b as overload==false */
+	if (dualpi2_roll(local_l_prob)) {
+		/* Non-ECT packets could have classified as L4S by filters. */
+		if (dualpi2_skb_cb(skb)->ect == INET_ECN_NOT_ECT)
+			return true;
+mark:
+		dualpi2_mark(q, skb);
+	}
+	return false;
+}
+
+/* Decide whether a given packet must be dropped (or marked if ECT), according
+ * to the PI2 probability.
+ *
+ * Never mark/drop if we have a standing queue of less than 2 MTUs.
+ */
+static bool must_drop(struct Qdisc *sch, struct dualpi2_sched_data *q,
+		      struct sk_buff *skb)
+{
+	u64 local_l_prob;
+	u32 prob;
+	bool overload;
+
+	if (sch->qstats.backlog < 2 * psched_mtu(qdisc_dev(sch)))
+		return false;
+
+	prob = READ_ONCE(q->pi2.prob);
+	local_l_prob = (u64)prob * q->coupling_factor;
+	overload = local_l_prob > MAX_PROB;
+
+	switch (dualpi2_skb_cb(skb)->classified) {
+	case DUALPI2_C_CLASSIC:
+		return dualpi2_classic_marking(q, skb, prob, overload);
+	case DUALPI2_C_L4S:
+		return dualpi2_scalable_marking(q, skb, local_l_prob, prob,
+						overload);
+	default: /* DUALPI2_C_LLLL */
+		return false;
+	}
+}
+
+static void dualpi2_read_ect(struct sk_buff *skb)
+{
+	struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb);
+	int wlen = skb_network_offset(skb);
+
+	switch (skb_protocol(skb, true)) {
+	case htons(ETH_P_IP):
+		wlen += sizeof(struct iphdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			goto not_ecn;
+
+		cb->ect = ipv4_get_dsfield(ip_hdr(skb)) & INET_ECN_MASK;
+		break;
+	case htons(ETH_P_IPV6):
+		wlen += sizeof(struct ipv6hdr);
+		if (!pskb_may_pull(skb, wlen) ||
+		    skb_try_make_writable(skb, wlen))
+			goto not_ecn;
+
+		cb->ect = ipv6_get_dsfield(ipv6_hdr(skb)) & INET_ECN_MASK;
+		break;
+	default:
+		goto not_ecn;
+	}
+	return;
+
+not_ecn:
+	/* Non pullable/writable packets can only be dropped hence are
+	 * classified as not ECT.
+	 */
+	cb->ect = INET_ECN_NOT_ECT;
+}
+
+static int dualpi2_skb_classify(struct dualpi2_sched_data *q,
+				struct sk_buff *skb)
+{
+	struct dualpi2_skb_cb *cb = dualpi2_skb_cb(skb);
+	struct tcf_result res;
+	struct tcf_proto *fl;
+	int result;
+
+	dualpi2_read_ect(skb);
+	if (cb->ect & q->ecn_mask) {
+		cb->classified = DUALPI2_C_L4S;
+		return NET_XMIT_SUCCESS;
+	}
+
+	if (TC_H_MAJ(skb->priority) == q->sch->handle &&
+	    TC_H_MIN(skb->priority) < __DUALPI2_C_MAX) {
+		cb->classified = TC_H_MIN(skb->priority);
+		return NET_XMIT_SUCCESS;
+	}
+
+	fl = rcu_dereference_bh(q->tcf.filters);
+	if (!fl) {
+		cb->classified = DUALPI2_C_CLASSIC;
+		return NET_XMIT_SUCCESS;
+	}
+
+	result = tcf_classify(skb, NULL, fl, &res, false);
+	if (result >= 0) {
+#ifdef CONFIG_NET_CLS_ACT
+		switch (result) {
+		case TC_ACT_STOLEN:
+		case TC_ACT_QUEUED:
+		case TC_ACT_TRAP:
+			return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN;
+		case TC_ACT_SHOT:
+			return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+		}
+#endif
+		cb->classified = TC_H_MIN(res.classid) < __DUALPI2_C_MAX ?
+			TC_H_MIN(res.classid) : DUALPI2_C_CLASSIC;
+	}
+	return NET_XMIT_SUCCESS;
+}
+
+static int dualpi2_enqueue_skb(struct sk_buff *skb, struct Qdisc *sch,
+			       struct sk_buff **to_free)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	struct dualpi2_skb_cb *cb;
+
+	if (unlikely(qdisc_qlen(sch) >= sch->limit) ||
+	    unlikely((u64)q->memory_used + skb->truesize > q->memory_limit)) {
+		qdisc_qstats_overlimit(sch);
+		if (skb_in_l_queue(skb))
+			qdisc_qstats_overlimit(q->l_queue);
+		return qdisc_drop(skb, sch, to_free);
+	}
+
+	if (q->drop_early && must_drop(sch, q, skb)) {
+		qdisc_drop(skb, sch, to_free);
+		return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS;
+	}
+
+	cb = dualpi2_skb_cb(skb);
+	cb->ts = ktime_get_ns();
+	q->memory_used += skb->truesize;
+	if (q->memory_used > q->max_memory_used)
+		q->max_memory_used = q->memory_used;
+
+	if (qdisc_qlen(sch) > q->maxq)
+		q->maxq = qdisc_qlen(sch);
+
+	if (skb_in_l_queue(skb)) {
+		/* Only apply the step if a queue is building up */
+		dualpi2_skb_cb(skb)->apply_step = skb_is_l4s(skb) &&
+			qdisc_qlen(q->l_queue) >= q->min_qlen_step;
+		/* Keep the overall qdisc stats consistent */
+		++sch->q.qlen;
+		qdisc_qstats_backlog_inc(sch, skb);
+		++q->packets_in_l;
+		if (!q->l_head_ts)
+			q->l_head_ts = cb->ts;
+		return qdisc_enqueue_tail(skb, q->l_queue);
+	}
+	++q->packets_in_c;
+	if (!q->c_head_ts)
+		q->c_head_ts = cb->ts;
+	return qdisc_enqueue_tail(skb, sch);
+}
+
+/* By default, dualpi2 will split GSO skbs into independent skbs and enqueue
+ * each of those individually. This yields the following benefits, at the
+ * expense of CPU usage:
+ * - Finer-grained AQM actions as the sub-packets of a burst no longer share the
+ *   same fate (e.g., the random mark/drop probability is applied individually)
+ * - Improved precision of the starvation protection/WRR scheduler at dequeue,
+ *   as the size of the dequeued packets will be smaller.
+ */
+static int dualpi2_qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+				 struct sk_buff **to_free)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	int err;
+
+	err = dualpi2_skb_classify(q, skb);
+	if (err != NET_XMIT_SUCCESS) {
+		if (err & __NET_XMIT_BYPASS)
+			qdisc_qstats_drop(sch);
+		__qdisc_drop(skb, to_free);
+		return err;
+	}
+
+	if (q->split_gso && skb_is_gso(skb)) {
+		netdev_features_t features;
+		struct sk_buff *nskb, *next;
+		int cnt, byte_len, orig_len;
+		int err;
+
+		features = netif_skb_features(skb);
+		nskb = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+		if (IS_ERR_OR_NULL(nskb))
+			return qdisc_drop(skb, sch, to_free);
+
+		cnt = 1;
+		byte_len = 0;
+		orig_len = qdisc_pkt_len(skb);
+		skb_list_walk_safe(nskb, nskb, next) {
+			skb_mark_not_on_list(nskb);
+			qdisc_skb_cb(nskb)->pkt_len = nskb->len;
+			dualpi2_skb_cb(nskb)->classified =
+				dualpi2_skb_cb(skb)->classified;
+			dualpi2_skb_cb(nskb)->ect = dualpi2_skb_cb(skb)->ect;
+			err = dualpi2_enqueue_skb(nskb, sch, to_free);
+			if (err == NET_XMIT_SUCCESS) {
+				/* Compute the backlog adjustment that needs
+				 * to be propagated in the qdisc tree to reflect
+				 * all new skbs successfully enqueued.
+				 */
+				++cnt;
+				byte_len += nskb->len;
+			}
+		}
+		if (err == NET_XMIT_SUCCESS) {
+			/* The caller will add the original skb stats to its
+			 * backlog, compensate this.
+			 */
+			--cnt;
+			byte_len -= orig_len;
+		}
+		qdisc_tree_reduce_backlog(sch, -cnt, -byte_len);
+		consume_skb(skb);
+		return err;
+	}
+	return dualpi2_enqueue_skb(skb, sch, to_free);
+}
+
+/* Select the queue from which the next packet can be dequeued, ensuring that
+ * neither queue can starve the other with a WRR scheduler.
+ *
+ * The sign of the WRR credit determines the next queue, while the size of
+ * the dequeued packet determines the magnitude of the WRR credit change. If
+ * either queue is empty, the WRR credit is kept unchanged.
+ *
+ * As the dequeued packet can be dropped later, the caller has to perform the
+ * qdisc_bstats_update() calls.
+ */
+static struct sk_buff *dequeue_packet(struct Qdisc *sch,
+				      struct dualpi2_sched_data *q,
+				      int *credit_change,
+				      u64 now)
+{
+	struct sk_buff *skb = NULL;
+	int c_len;
+
+	*credit_change = 0;
+	c_len = qdisc_qlen(sch) - qdisc_qlen(q->l_queue);
+	if (qdisc_qlen(q->l_queue) && (!c_len || q->c_protection.credit <= 0)) {
+		skb = __qdisc_dequeue_head(&q->l_queue->q);
+		WRITE_ONCE(q->l_head_ts, head_enqueue_time(q->l_queue));
+		if (c_len)
+			*credit_change = q->c_protection.wc;
+		qdisc_qstats_backlog_dec(q->l_queue, skb);
+		/* Keep the global queue size consistent */
+		--sch->q.qlen;
+		q->memory_used -= skb->truesize;
+	} else if (c_len) {
+		skb = __qdisc_dequeue_head(&sch->q);
+		WRITE_ONCE(q->c_head_ts, head_enqueue_time(sch));
+		if (qdisc_qlen(q->l_queue))
+			*credit_change = ~((s32)q->c_protection.wl) + 1;
+		q->memory_used -= skb->truesize;
+	} else {
+		dualpi2_reset_c_protection(q);
+		return NULL;
+	}
+	*credit_change *= qdisc_pkt_len(skb);
+	qdisc_qstats_backlog_dec(sch, skb);
+	return skb;
+}
+
+static int do_step_aqm(struct dualpi2_sched_data *q, struct sk_buff *skb,
+		       u64 now)
+{
+	u64 qdelay = 0;
+
+	if (q->step.in_packets)
+		qdelay = qdisc_qlen(q->l_queue);
+	else
+		qdelay = dualpi2_sojourn_time(skb, now);
+
+	if (dualpi2_skb_cb(skb)->apply_step && qdelay > q->step.thresh) {
+		if (!dualpi2_skb_cb(skb)->ect)
+			/* Drop this non-ECT packet */
+			return 1;
+		if (dualpi2_mark(q, skb))
+			++q->step_marks;
+	}
+	qdisc_bstats_update(q->l_queue, skb);
+	return 0;
+}
+
+static void drop_and_retry(struct dualpi2_sched_data *q, struct sk_buff *skb,
+			   struct Qdisc *sch)
+{
+	++q->deferred_drops.cnt;
+	q->deferred_drops.len += qdisc_pkt_len(skb);
+	consume_skb(skb);
+	qdisc_qstats_drop(sch);
+}
+
+static struct sk_buff *dualpi2_qdisc_dequeue(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *skb;
+	int credit_change;
+	u64 now;
+
+	now = ktime_get_ns();
+
+	while ((skb = dequeue_packet(sch, q, &credit_change, now))) {
+		if (!q->drop_early && must_drop(sch, q, skb)) {
+			drop_and_retry(q, skb, sch);
+			continue;
+		}
+
+		if (skb_in_l_queue(skb) && do_step_aqm(q, skb, now)) {
+			qdisc_qstats_drop(q->l_queue);
+			drop_and_retry(q, skb, sch);
+			continue;
+		}
+
+		q->c_protection.credit += credit_change;
+		qdisc_bstats_update(sch, skb);
+		break;
+	}
+
+	/* We cannot call qdisc_tree_reduce_backlog() if our qlen is 0,
+	 * or HTB crashes.
+	 */
+	if (q->deferred_drops.cnt && qdisc_qlen(sch)) {
+		qdisc_tree_reduce_backlog(sch, q->deferred_drops.cnt,
+					  q->deferred_drops.len);
+		q->deferred_drops.cnt = 0;
+		q->deferred_drops.len = 0;
+	}
+	return skb;
+}
+
+static s64 __scale_delta(u64 diff)
+{
+	do_div(diff, 1 << ALPHA_BETA_GRANULARITY);
+	return diff;
+}
+
+static void get_queue_delays(struct dualpi2_sched_data *q, u64 *qdelay_c,
+			     u64 *qdelay_l)
+{
+	u64 now, qc, ql;
+
+	now = ktime_get_ns();
+	qc = READ_ONCE(q->c_head_ts);
+	ql = READ_ONCE(q->l_head_ts);
+
+	*qdelay_c = qc ? now - qc : 0;
+	*qdelay_l = ql ? now - ql : 0;
+}
+
+static u32 calculate_probability(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	u32 new_prob;
+	u64 qdelay_c;
+	u64 qdelay_l;
+	u64 qdelay;
+	s64 delta;
+
+	get_queue_delays(q, &qdelay_c, &qdelay_l);
+	qdelay = max(qdelay_l, qdelay_c);
+	/* Alpha and beta take at most 32b, i.e, the delay difference would
+	 * overflow for queuing delay differences > ~4.2sec.
+	 */
+	delta = ((s64)qdelay - q->pi2.target) * q->pi2.alpha;
+	delta += ((s64)qdelay - q->last_qdelay) * q->pi2.beta;
+	if (delta > 0) {
+		new_prob = __scale_delta(delta) + q->pi2.prob;
+		if (new_prob < q->pi2.prob)
+			new_prob = MAX_PROB;
+	} else {
+		new_prob = q->pi2.prob - __scale_delta(~delta + 1);
+		if (new_prob > q->pi2.prob)
+			new_prob = 0;
+	}
+	q->last_qdelay = qdelay;
+	/* If we do not drop on overload, ensure we cap the L4S probability to
+	 * 100% to keep window fairness when overflowing.
+	 */
+	if (!q->drop_overload)
+		return min_t(u32, new_prob, MAX_PROB / q->coupling_factor);
+	return new_prob;
+}
+
+static enum hrtimer_restart dualpi2_timer(struct hrtimer *timer)
+{
+	struct dualpi2_sched_data *q = from_timer(q, timer, pi2.timer);
+
+	WRITE_ONCE(q->pi2.prob, calculate_probability(q->sch));
+
+	hrtimer_set_expires(&q->pi2.timer, next_pi2_timeout(q));
+	return HRTIMER_RESTART;
+}
+
+static struct netlink_range_validation dualpi2_alpha_beta_range = {
+	.min = 1,
+	.max = ALPHA_BETA_MAX,
+};
+
+static struct netlink_range_validation dualpi2_wc_range = {
+	.min = 0,
+	.max = MAX_WC,
+};
+
+static const struct nla_policy dualpi2_policy[TCA_DUALPI2_MAX + 1] = {
+	[TCA_DUALPI2_LIMIT]		= NLA_POLICY_MIN(NLA_U32, 1),
+	[TCA_DUALPI2_MEMORY_LIMIT]	= NLA_POLICY_MIN(NLA_U32, 1),
+	[TCA_DUALPI2_TARGET]		= {.type = NLA_U32},
+	[TCA_DUALPI2_TUPDATE]		= NLA_POLICY_MIN(NLA_U32, 1),
+	[TCA_DUALPI2_ALPHA]		=
+		NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range),
+	[TCA_DUALPI2_BETA]		=
+		NLA_POLICY_FULL_RANGE(NLA_U32, &dualpi2_alpha_beta_range),
+	[TCA_DUALPI2_STEP_THRESH]	= {.type = NLA_U32},
+	[TCA_DUALPI2_STEP_PACKETS]	= {.type = NLA_U8},
+	[TCA_DUALPI2_MIN_QLEN_STEP]	= {.type = NLA_U32},
+	[TCA_DUALPI2_COUPLING]		= NLA_POLICY_MIN(NLA_U8, 1),
+	[TCA_DUALPI2_DROP_OVERLOAD]	= {.type = NLA_U8},
+	[TCA_DUALPI2_DROP_EARLY]	= {.type = NLA_U8},
+	[TCA_DUALPI2_C_PROTECTION]	=
+		NLA_POLICY_FULL_RANGE(NLA_U8, &dualpi2_wc_range),
+	[TCA_DUALPI2_ECN_MASK]		= {.type = NLA_U8},
+	[TCA_DUALPI2_SPLIT_GSO]		= {.type = NLA_U8},
+};
+
+static int dualpi2_change(struct Qdisc *sch, struct nlattr *opt,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[TCA_DUALPI2_MAX + 1];
+	struct dualpi2_sched_data *q;
+	int old_backlog;
+	int old_qlen;
+	int err;
+
+	if (!opt)
+		return -EINVAL;
+	err = nla_parse_nested(tb, TCA_DUALPI2_MAX, opt, dualpi2_policy,
+			       extack);
+	if (err < 0)
+		return err;
+
+	q = qdisc_priv(sch);
+	sch_tree_lock(sch);
+
+	if (tb[TCA_DUALPI2_LIMIT]) {
+		u32 limit = nla_get_u32(tb[TCA_DUALPI2_LIMIT]);
+
+		WRITE_ONCE(sch->limit, limit);
+		WRITE_ONCE(q->memory_limit, limit * psched_mtu(qdisc_dev(sch)));
+	}
+
+	if (tb[TCA_DUALPI2_MEMORY_LIMIT])
+		WRITE_ONCE(q->memory_limit,
+			   nla_get_u32(tb[TCA_DUALPI2_MEMORY_LIMIT]));
+
+	if (tb[TCA_DUALPI2_TARGET]) {
+		u64 target = nla_get_u32(tb[TCA_DUALPI2_TARGET]);
+
+		WRITE_ONCE(q->pi2.target, target * NSEC_PER_USEC);
+	}
+
+	if (tb[TCA_DUALPI2_TUPDATE]) {
+		u64 tupdate = nla_get_u32(tb[TCA_DUALPI2_TUPDATE]);
+
+		WRITE_ONCE(q->pi2.tupdate, tupdate * NSEC_PER_USEC);
+	}
+
+	if (tb[TCA_DUALPI2_ALPHA]) {
+		u32 alpha = nla_get_u32(tb[TCA_DUALPI2_ALPHA]);
+
+		WRITE_ONCE(q->pi2.alpha, dualpi2_scale_alpha_beta(alpha));
+	}
+
+	if (tb[TCA_DUALPI2_BETA]) {
+		u32 beta = nla_get_u32(tb[TCA_DUALPI2_BETA]);
+
+		WRITE_ONCE(q->pi2.beta, dualpi2_scale_alpha_beta(beta));
+	}
+
+	if (tb[TCA_DUALPI2_STEP_PACKETS]) {
+		bool step_pkt = !!nla_get_u8(tb[TCA_DUALPI2_STEP_PACKETS]);
+		u32 step_th = READ_ONCE(q->step.thresh);
+
+		WRITE_ONCE(q->step.in_packets, step_pkt);
+		WRITE_ONCE(q->step.thresh,
+			   step_pkt ? step_th : (step_th * NSEC_PER_USEC));
+	}
+
+	if (tb[TCA_DUALPI2_STEP_THRESH]) {
+		u32 step_th = nla_get_u32(tb[TCA_DUALPI2_STEP_THRESH]);
+		bool step_pkt = READ_ONCE(q->step.in_packets);
+
+		WRITE_ONCE(q->step.thresh,
+			   step_pkt ? step_th : (step_th * NSEC_PER_USEC));
+	}
+
+	if (tb[TCA_DUALPI2_MIN_QLEN_STEP])
+		WRITE_ONCE(q->min_qlen_step,
+			   nla_get_u32(tb[TCA_DUALPI2_MIN_QLEN_STEP]));
+
+	if (tb[TCA_DUALPI2_COUPLING]) {
+		u8 coupling = nla_get_u8(tb[TCA_DUALPI2_COUPLING]);
+
+		WRITE_ONCE(q->coupling_factor, coupling);
+	}
+
+	if (tb[TCA_DUALPI2_DROP_OVERLOAD])
+		WRITE_ONCE(q->drop_overload,
+			   !!nla_get_u8(tb[TCA_DUALPI2_DROP_OVERLOAD]));
+
+	if (tb[TCA_DUALPI2_DROP_EARLY])
+		WRITE_ONCE(q->drop_early,
+			   !!nla_get_u8(tb[TCA_DUALPI2_DROP_EARLY]));
+
+	if (tb[TCA_DUALPI2_C_PROTECTION]) {
+		u8 wc = nla_get_u8(tb[TCA_DUALPI2_C_PROTECTION]);
+
+		dualpi2_calculate_c_protection(sch, q, wc);
+	}
+
+	if (tb[TCA_DUALPI2_ECN_MASK])
+		WRITE_ONCE(q->ecn_mask,
+			   nla_get_u8(tb[TCA_DUALPI2_ECN_MASK]));
+
+	if (tb[TCA_DUALPI2_SPLIT_GSO])
+		WRITE_ONCE(q->split_gso,
+			   !!nla_get_u8(tb[TCA_DUALPI2_SPLIT_GSO]));
+
+	old_qlen = qdisc_qlen(sch);
+	old_backlog = sch->qstats.backlog;
+	while (qdisc_qlen(sch) > sch->limit ||
+	       q->memory_used > q->memory_limit) {
+		struct sk_buff *skb = __qdisc_dequeue_head(&sch->q);
+
+		q->memory_used -= skb->truesize;
+		qdisc_qstats_backlog_dec(sch, skb);
+		rtnl_qdisc_drop(skb, sch);
+	}
+	qdisc_tree_reduce_backlog(sch, old_qlen - qdisc_qlen(sch),
+				  old_backlog - sch->qstats.backlog);
+
+	sch_tree_unlock(sch);
+	return 0;
+}
+
+/* Default alpha/beta values give a 10dB stability margin with max_rtt=100ms. */
+static void dualpi2_reset_default(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+
+	q->sch->limit = 10000;				/* Max 125ms at 1Gbps */
+	q->memory_limit = q->sch->limit * psched_mtu(qdisc_dev(sch));
+
+	q->pi2.target = 15 * NSEC_PER_MSEC;
+	q->pi2.tupdate = 16 * NSEC_PER_MSEC;
+	q->pi2.alpha = dualpi2_scale_alpha_beta(41);	/* ~0.16 Hz * 256 */
+	q->pi2.beta = dualpi2_scale_alpha_beta(819);	/* ~3.20 Hz * 256 */
+
+	q->step.thresh = 1 * NSEC_PER_MSEC;
+	q->step.in_packets = false;
+
+	dualpi2_calculate_c_protection(q->sch, q, 10);	/* wc=10%, wl=90% */
+
+	q->ecn_mask = INET_ECN_ECT_1;
+	q->min_qlen_step = 0;
+	q->coupling_factor = 2;		/* window fairness for equal RTTs */
+	q->drop_overload = true;	/* Preserve latency by dropping */
+	q->drop_early = false;		/* PI2 drops on dequeue */
+	q->split_gso = true;
+}
+
+static int dualpi2_init(struct Qdisc *sch, struct nlattr *opt,
+			struct netlink_ext_ack *extack)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	int err;
+
+	q->l_queue = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
+				       TC_H_MAKE(sch->handle, 1), extack);
+	if (!q->l_queue)
+		return -ENOMEM;
+
+	err = tcf_block_get(&q->tcf.block, &q->tcf.filters, sch, extack);
+	if (err)
+		return err;
+
+	q->sch = sch;
+	dualpi2_reset_default(sch);
+	hrtimer_init(&q->pi2.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED);
+	q->pi2.timer.function = dualpi2_timer;
+
+	if (opt) {
+		err = dualpi2_change(sch, opt, extack);
+
+		if (err)
+			return err;
+	}
+
+	hrtimer_start(&q->pi2.timer, next_pi2_timeout(q),
+		      HRTIMER_MODE_ABS_PINNED);
+	return 0;
+}
+
+static u32 convert_ns_to_usec(u64 ns)
+{
+	do_div(ns, NSEC_PER_USEC);
+	return ns;
+}
+
+static int dualpi2_dump(struct Qdisc *sch, struct sk_buff *skb)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	struct nlattr *opts;
+
+	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
+	if (!opts)
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, TCA_DUALPI2_LIMIT, READ_ONCE(sch->limit)) ||
+	    nla_put_u32(skb, TCA_DUALPI2_MEMORY_LIMIT,
+			READ_ONCE(q->memory_limit)) ||
+	    nla_put_u32(skb, TCA_DUALPI2_TARGET,
+			convert_ns_to_usec(READ_ONCE(q->pi2.target))) ||
+	    nla_put_u32(skb, TCA_DUALPI2_TUPDATE,
+			convert_ns_to_usec(READ_ONCE(q->pi2.tupdate))) ||
+	    nla_put_u32(skb, TCA_DUALPI2_ALPHA,
+			dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2.alpha))) ||
+	    nla_put_u32(skb, TCA_DUALPI2_BETA,
+			dualpi2_unscale_alpha_beta(READ_ONCE(q->pi2.beta))) ||
+	    nla_put_u32(skb, TCA_DUALPI2_STEP_THRESH,
+			READ_ONCE(q->step.in_packets) ?
+			READ_ONCE(q->step.thresh) :
+			convert_ns_to_usec(READ_ONCE(q->step.thresh))) ||
+	    nla_put_u32(skb, TCA_DUALPI2_MIN_QLEN_STEP,
+			READ_ONCE(q->min_qlen_step)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_COUPLING,
+		       READ_ONCE(q->coupling_factor)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_DROP_OVERLOAD,
+		       READ_ONCE(q->drop_overload)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_STEP_PACKETS,
+		       READ_ONCE(q->step.in_packets)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_DROP_EARLY,
+		       READ_ONCE(q->drop_early)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_C_PROTECTION,
+		       READ_ONCE(q->c_protection.wc)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_ECN_MASK, READ_ONCE(q->ecn_mask)) ||
+	    nla_put_u8(skb, TCA_DUALPI2_SPLIT_GSO, READ_ONCE(q->split_gso)))
+		goto nla_put_failure;
+
+	return nla_nest_end(skb, opts);
+
+nla_put_failure:
+	nla_nest_cancel(skb, opts);
+	return -1;
+}
+
+static int dualpi2_dump_stats(struct Qdisc *sch, struct gnet_dump *d)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+	struct tc_dualpi2_xstats st = {
+		.prob			= READ_ONCE(q->pi2.prob),
+		.packets_in_c		= q->packets_in_c,
+		.packets_in_l		= q->packets_in_l,
+		.maxq			= q->maxq,
+		.ecn_mark		= q->ecn_mark,
+		.credit			= q->c_protection.credit,
+		.step_marks		= q->step_marks,
+		.memory_used		= q->memory_used,
+		.max_memory_used	= q->max_memory_used,
+		.memory_limit		= q->memory_limit,
+	};
+	u64 qc, ql;
+
+	get_queue_delays(q, &qc, &ql);
+	st.delay_l = convert_ns_to_usec(ql);
+	st.delay_c = convert_ns_to_usec(qc);
+	return gnet_stats_copy_app(d, &st, sizeof(st));
+}
+
+/* Reset both L-queue and C-queue, internal packet counters, PI probability,
+ * C-queue protection credit, and timestamps, while preserving current
+ * configuration of DUALPI2.
+ */
+static void dualpi2_reset(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+
+	qdisc_reset_queue(sch);
+	qdisc_reset_queue(q->l_queue);
+	q->c_head_ts = 0;
+	q->l_head_ts = 0;
+	q->pi2.prob = 0;
+	q->packets_in_c = 0;
+	q->packets_in_l = 0;
+	q->maxq = 0;
+	q->ecn_mark = 0;
+	q->step_marks = 0;
+	q->memory_used = 0;
+	q->max_memory_used = 0;
+	dualpi2_reset_c_protection(q);
+}
+
+static void dualpi2_destroy(struct Qdisc *sch)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+
+	q->pi2.tupdate = 0;
+	hrtimer_cancel(&q->pi2.timer);
+	if (q->l_queue)
+		qdisc_put(q->l_queue);
+	tcf_block_put(q->tcf.block);
+}
+
+static struct Qdisc *dualpi2_leaf(struct Qdisc *sch, unsigned long arg)
+{
+	return NULL;
+}
+
+static unsigned long dualpi2_find(struct Qdisc *sch, u32 classid)
+{
+	return 0;
+}
+
+static unsigned long dualpi2_bind(struct Qdisc *sch, unsigned long parent,
+				  u32 classid)
+{
+	return 0;
+}
+
+static void dualpi2_unbind(struct Qdisc *q, unsigned long cl)
+{
+}
+
+static struct tcf_block *dualpi2_tcf_block(struct Qdisc *sch, unsigned long cl,
+					   struct netlink_ext_ack *extack)
+{
+	struct dualpi2_sched_data *q = qdisc_priv(sch);
+
+	if (cl)
+		return NULL;
+	return q->tcf.block;
+}
+
+static void dualpi2_walk(struct Qdisc *sch, struct qdisc_walker *arg)
+{
+	unsigned int i;
+
+	if (arg->stop)
+		return;
+
+	/* We statically define only 2 queues */
+	for (i = 0; i < 2; i++) {
+		if (arg->count < arg->skip) {
+			arg->count++;
+			continue;
+		}
+		if (arg->fn(sch, i + 1, arg) < 0) {
+			arg->stop = 1;
+			break;
+		}
+		arg->count++;
+	}
+}
+
+/* Minimal class support to handler tc filters */
+static const struct Qdisc_class_ops dualpi2_class_ops = {
+	.leaf		= dualpi2_leaf,
+	.find		= dualpi2_find,
+	.tcf_block	= dualpi2_tcf_block,
+	.bind_tcf	= dualpi2_bind,
+	.unbind_tcf	= dualpi2_unbind,
+	.walk		= dualpi2_walk,
+};
+
+static struct Qdisc_ops dualpi2_qdisc_ops __read_mostly = {
+	.id		= "dualpi2",
+	.cl_ops		= &dualpi2_class_ops,
+	.priv_size	= sizeof(struct dualpi2_sched_data),
+	.enqueue	= dualpi2_qdisc_enqueue,
+	.dequeue	= dualpi2_qdisc_dequeue,
+	.peek		= qdisc_peek_dequeued,
+	.init		= dualpi2_init,
+	.destroy	= dualpi2_destroy,
+	.reset		= dualpi2_reset,
+	.change		= dualpi2_change,
+	.dump		= dualpi2_dump,
+	.dump_stats	= dualpi2_dump_stats,
+	.owner		= THIS_MODULE,
+};
+
+static int __init dualpi2_module_init(void)
+{
+	return register_qdisc(&dualpi2_qdisc_ops);
+}
+
+static void __exit dualpi2_module_exit(void)
+{
+	unregister_qdisc(&dualpi2_qdisc_ops);
+}
+
+module_init(dualpi2_module_init);
+module_exit(dualpi2_module_exit);
+
+MODULE_DESCRIPTION("Dual Queue with Proportional Integral controller Improved with a Square (dualpi2) scheduler");
+MODULE_AUTHOR("Koen De Schepper <koen.de_schepper@nokia-bell-labs.com>");
+MODULE_AUTHOR("Olga Albisser <olga@albisser.org>");
+MODULE_AUTHOR("Henrik Steen <henrist@henrist.net>");
+MODULE_AUTHOR("Olivier Tilmans <olivier.tilmans@nokia.com>");
+MODULE_AUTHOR("Chia-Yu Chang <chia-yu.chang@nokia-bell-labs.com>");
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION("1.0");

From 94e459524518744f850c8328859d3f77aa506709 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Sun, 16 Mar 2025 12:28:37 -0700
Subject: [PATCH 2498/2753] net: Remove RTNL dance for SIOCBRADDIF and
 SIOCBRDELIF.

SIOCBRDELIF is passed to dev_ioctl() first and later forwarded to
br_ioctl_call(), which causes unnecessary RTNL dance and the splat
below [0] under RTNL pressure.

Let's say Thread A is trying to detach a device from a bridge and
Thread B is trying to remove the bridge.

In dev_ioctl(), Thread A bumps the bridge device's refcnt by
netdev_hold() and releases RTNL because the following br_ioctl_call()
also re-acquires RTNL.

In the race window, Thread B could acquire RTNL and try to remove
the bridge device.  Then, rtnl_unlock() by Thread B will release RTNL
and wait for netdev_put() by Thread A.

Thread A, however, must hold RTNL after the unlock in dev_ifsioc(),
which may take long under RTNL pressure, resulting in the splat by
Thread B.

  Thread A (SIOCBRDELIF)           Thread B (SIOCBRDELBR)
  ----------------------           ----------------------
  sock_ioctl                       sock_ioctl
  `- sock_do_ioctl                 `- br_ioctl_call
     `- dev_ioctl                     `- br_ioctl_stub
        |- rtnl_lock                     |
        |- dev_ifsioc                    '
        '  |- dev = __dev_get_by_name(...)
           |- netdev_hold(dev, ...)      .
       /   |- rtnl_unlock  ------.       |
       |   |- br_ioctl_call       `--->  |- rtnl_lock
  Race |   |  `- br_ioctl_stub           |- br_del_bridge
  Window   |     |                       |  |- dev = __dev_get_by_name(...)
       |   |     |  May take long        |  `- br_dev_delete(dev, ...)
       |   |     |  under RTNL pressure  |     `- unregister_netdevice_queue(dev, ...)
       |   |     |               |       `- rtnl_unlock
       \   |     |- rtnl_lock  <-'          `- netdev_run_todo
           |     |- ...                        `- netdev_run_todo
           |     `- rtnl_unlock                   |- __rtnl_unlock
           |                                      |- netdev_wait_allrefs_any
           |- netdev_put(dev, ...)  <----------------'
                                                Wait refcnt decrement
                                                and log splat below

To avoid blocking SIOCBRDELBR unnecessarily, let's not call
dev_ioctl() for SIOCBRADDIF and SIOCBRDELIF.

In the dev_ioctl() path, we do the following:

  1. Copy struct ifreq by get_user_ifreq in sock_do_ioctl()
  2. Check CAP_NET_ADMIN in dev_ioctl()
  3. Call dev_load() in dev_ioctl()
  4. Fetch the master dev from ifr.ifr_name in dev_ifsioc()

3. can be done by request_module() in br_ioctl_call(), so we move
1., 2., and 4. to br_ioctl_stub().

Note that 2. is also checked later in add_del_if(), but it's better
performed before RTNL.

SIOCBRADDIF and SIOCBRDELIF have been processed in dev_ioctl() since
the pre-git era, and there seems to be no specific reason to process
them there.

[0]:
unregister_netdevice: waiting for wpan3 to become free. Usage count = 2
ref_tracker: wpan3@ffff8880662d8608 has 1/1 users at
     __netdev_tracker_alloc include/linux/netdevice.h:4282 [inline]
     netdev_hold include/linux/netdevice.h:4311 [inline]
     dev_ifsioc+0xc6a/0x1160 net/core/dev_ioctl.c:624
     dev_ioctl+0x255/0x10c0 net/core/dev_ioctl.c:826
     sock_do_ioctl+0x1ca/0x260 net/socket.c:1213
     sock_ioctl+0x23a/0x6c0 net/socket.c:1318
     vfs_ioctl fs/ioctl.c:51 [inline]
     __do_sys_ioctl fs/ioctl.c:906 [inline]
     __se_sys_ioctl fs/ioctl.c:892 [inline]
     __x64_sys_ioctl+0x1a4/0x210 fs/ioctl.c:892
     do_syscall_x64 arch/x86/entry/common.c:52 [inline]
     do_syscall_64+0xcb/0x250 arch/x86/entry/common.c:83
     entry_SYSCALL_64_after_hwframe+0x77/0x7f

Fixes: 893b19587534 ("net: bridge: fix ioctl locking")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Reported-by: yan kang <kangyan91@outlook.com>
Reported-by: yue sun <samsun1006219@gmail.com>
Closes: https://lore.kernel.org/netdev/SY8P300MB0421225D54EB92762AE8F0F2A1D32@SY8P300MB0421.AUSP300.PROD.OUTLOOK.COM/
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Acked-by: Nikolay Aleksandrov <razor@blackwall.org>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/if_bridge.h |  6 ++----
 net/bridge/br_ioctl.c     | 36 +++++++++++++++++++++++++++++++++---
 net/bridge/br_private.h   |  3 +--
 net/core/dev_ioctl.c      | 19 -------------------
 net/socket.c              | 19 +++++++++----------
 5 files changed, 45 insertions(+), 38 deletions(-)

diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3ff96ae31bf6d..c5fe3b2a53e82 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -65,11 +65,9 @@ struct br_ip_list {
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 struct net_bridge;
-void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
-			     unsigned int cmd, struct ifreq *ifr,
+void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
 			     void __user *uarg));
-int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg);
+int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg);
 
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
diff --git a/net/bridge/br_ioctl.c b/net/bridge/br_ioctl.c
index f213ed1083618..6bc0a11f2ed3e 100644
--- a/net/bridge/br_ioctl.c
+++ b/net/bridge/br_ioctl.c
@@ -394,10 +394,26 @@ static int old_deviceless(struct net *net, void __user *data)
 	return -EOPNOTSUPP;
 }
 
-int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg)
+int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg)
 {
 	int ret = -EOPNOTSUPP;
+	struct ifreq ifr;
+
+	if (cmd == SIOCBRADDIF || cmd == SIOCBRDELIF) {
+		void __user *data;
+		char *colon;
+
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+
+		if (get_user_ifreq(&ifr, &data, uarg))
+			return -EFAULT;
+
+		ifr.ifr_name[IFNAMSIZ - 1] = 0;
+		colon = strchr(ifr.ifr_name, ':');
+		if (colon)
+			*colon = 0;
+	}
 
 	rtnl_lock();
 
@@ -430,7 +446,21 @@ int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
 		break;
 	case SIOCBRADDIF:
 	case SIOCBRDELIF:
-		ret = add_del_if(br, ifr->ifr_ifindex, cmd == SIOCBRADDIF);
+	{
+		struct net_device *dev;
+
+		dev = __dev_get_by_name(net, ifr.ifr_name);
+		if (!dev || !netif_device_present(dev)) {
+			ret = -ENODEV;
+			break;
+		}
+		if (!netif_is_bridge_master(dev)) {
+			ret = -EOPNOTSUPP;
+			break;
+		}
+
+		ret = add_del_if(netdev_priv(dev), ifr.ifr_ifindex, cmd == SIOCBRADDIF);
+	}
 		break;
 	}
 
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 1054b8a88edc4..d5b3c5936a79e 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -949,8 +949,7 @@ br_port_get_check_rtnl(const struct net_device *dev)
 /* br_ioctl.c */
 int br_dev_siocdevprivate(struct net_device *dev, struct ifreq *rq,
 			  void __user *data, int cmd);
-int br_ioctl_stub(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg);
+int br_ioctl_stub(struct net *net, unsigned int cmd, void __user *uarg);
 
 /* br_multicast.c */
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index eb8b41ec5523c..fff13a8b48f18 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -554,7 +554,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	int err;
 	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
 	const struct net_device_ops *ops;
-	netdevice_tracker dev_tracker;
 
 	if (!dev)
 		return -ENODEV;
@@ -628,22 +627,6 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, void __user *data,
 	case SIOCWANDEV:
 		return dev_siocwandev(dev, &ifr->ifr_settings);
 
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
-		if (!netif_device_present(dev))
-			return -ENODEV;
-		if (!netif_is_bridge_master(dev))
-			return -EOPNOTSUPP;
-
-		netdev_hold(dev, &dev_tracker, GFP_KERNEL);
-		rtnl_net_unlock(net);
-
-		err = br_ioctl_call(net, netdev_priv(dev), cmd, ifr, NULL);
-
-		netdev_put(dev, &dev_tracker);
-		rtnl_net_lock(net);
-		return err;
-
 	case SIOCDEVPRIVATE ... SIOCDEVPRIVATE + 15:
 		return dev_siocdevprivate(dev, ifr, data, cmd);
 
@@ -826,8 +809,6 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 	case SIOCBONDRELEASE:
 	case SIOCBONDSETHWADDR:
 	case SIOCBONDCHANGEACTIVE:
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
 	case SIOCSHWTSTAMP:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
diff --git a/net/socket.c b/net/socket.c
index b64ecf2722e7b..17fc00ef17fea 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1136,12 +1136,10 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from)
  */
 
 static DEFINE_MUTEX(br_ioctl_mutex);
-static int (*br_ioctl_hook)(struct net *net, struct net_bridge *br,
-			    unsigned int cmd, struct ifreq *ifr,
+static int (*br_ioctl_hook)(struct net *net, unsigned int cmd,
 			    void __user *uarg);
 
-void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
-			     unsigned int cmd, struct ifreq *ifr,
+void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
 			     void __user *uarg))
 {
 	mutex_lock(&br_ioctl_mutex);
@@ -1150,8 +1148,7 @@ void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
 }
 EXPORT_SYMBOL(brioctl_set);
 
-int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg)
+int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg)
 {
 	int err = -ENOPKG;
 
@@ -1160,7 +1157,7 @@ int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
 
 	mutex_lock(&br_ioctl_mutex);
 	if (br_ioctl_hook)
-		err = br_ioctl_hook(net, br, cmd, ifr, uarg);
+		err = br_ioctl_hook(net, cmd, uarg);
 	mutex_unlock(&br_ioctl_mutex);
 
 	return err;
@@ -1260,7 +1257,9 @@ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		case SIOCSIFBR:
 		case SIOCBRADDBR:
 		case SIOCBRDELBR:
-			err = br_ioctl_call(net, NULL, cmd, NULL, argp);
+		case SIOCBRADDIF:
+		case SIOCBRDELIF:
+			err = br_ioctl_call(net, cmd, argp);
 			break;
 		case SIOCGIFVLAN:
 		case SIOCSIFVLAN:
@@ -3420,6 +3419,8 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGPGRP:
 	case SIOCBRADDBR:
 	case SIOCBRDELBR:
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
 	case SIOCGIFVLAN:
 	case SIOCSIFVLAN:
 	case SIOCGSKNS:
@@ -3459,8 +3460,6 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock,
 	case SIOCGIFPFLAGS:
 	case SIOCGIFTXQLEN:
 	case SIOCSIFTXQLEN:
-	case SIOCBRADDIF:
-	case SIOCBRDELIF:
 	case SIOCGIFNAME:
 	case SIOCSIFNAME:
 	case SIOCGMIIPHY:

From c21cadaa80bdc58639a3ba1ee303ac02202316f5 Mon Sep 17 00:00:00 2001
From: Jim Liu <jim.t90615@gmail.com>
Date: Mon, 17 Mar 2025 14:34:52 +0800
Subject: [PATCH 2499/2753] net: phy: broadcom: Correct BCM5221 PHY model
 detection failure

Use "BRCM_PHY_MODEL" can be applied to the entire 5221 family of PHYs.

Fixes: 3abbd0699b67 ("net: phy: broadcom: add support for BCM5221 phy")
Signed-off-by: Jim Liu <jim.t90615@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/broadcom.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 13e43fee1906e..d5e863904e890 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -859,7 +859,7 @@ static int brcm_fet_config_init(struct phy_device *phydev)
 		return reg;
 
 	/* Unmask events we are interested in and mask interrupts globally. */
-	if (phydev->phy_id == PHY_ID_BCM5221)
+	if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM5221)
 		reg = MII_BRCM_FET_IR_ENABLE |
 		      MII_BRCM_FET_IR_MASK;
 	else
@@ -888,7 +888,7 @@ static int brcm_fet_config_init(struct phy_device *phydev)
 		return err;
 	}
 
-	if (phydev->phy_id != PHY_ID_BCM5221) {
+	if (BRCM_PHY_MODEL(phydev) != PHY_ID_BCM5221) {
 		/* Set the LED mode */
 		reg = __phy_read(phydev, MII_BRCM_FET_SHDW_AUXMODE4);
 		if (reg < 0) {
@@ -1009,7 +1009,7 @@ static int brcm_fet_suspend(struct phy_device *phydev)
 		return err;
 	}
 
-	if (phydev->phy_id == PHY_ID_BCM5221)
+	if (BRCM_PHY_MODEL(phydev) == PHY_ID_BCM5221)
 		/* Force Low Power Mode with clock enabled */
 		reg = BCM5221_SHDW_AM4_EN_CLK_LPM | BCM5221_SHDW_AM4_FORCE_LPM;
 	else

From ed74432e596acef5a8e1433f3f643860dce59413 Mon Sep 17 00:00:00 2001
From: David Arinzon <darinzon@amazon.com>
Date: Mon, 17 Mar 2025 09:11:47 +0200
Subject: [PATCH 2500/2753] net: ena: resolve WARN_ON when freeing IRQs

When IRQs are freed, a WARN_ON is triggered as the
affinity notifier is not released.
This results in the below stack trace:

[  484.544586]  ? __warn+0x84/0x130
[  484.544843]  ? free_irq+0x5c/0x70
[  484.545105]  ? report_bug+0x18a/0x1a0
[  484.545390]  ? handle_bug+0x53/0x90
[  484.545664]  ? exc_invalid_op+0x14/0x70
[  484.545959]  ? asm_exc_invalid_op+0x16/0x20
[  484.546279]  ? free_irq+0x5c/0x70
[  484.546545]  ? free_irq+0x10/0x70
[  484.546807]  ena_free_io_irq+0x5f/0x70 [ena]
[  484.547138]  ena_down+0x250/0x3e0 [ena]
[  484.547435]  ena_destroy_device+0x118/0x150 [ena]
[  484.547796]  __ena_shutoff+0x5a/0xe0 [ena]
[  484.548110]  pci_device_remove+0x3b/0xb0
[  484.548412]  device_release_driver_internal+0x193/0x200
[  484.548804]  driver_detach+0x44/0x90
[  484.549084]  bus_remove_driver+0x69/0xf0
[  484.549386]  pci_unregister_driver+0x2a/0xb0
[  484.549717]  ena_cleanup+0xc/0x130 [ena]
[  484.550021]  __do_sys_delete_module.constprop.0+0x176/0x310
[  484.550438]  ? syscall_trace_enter+0xfb/0x1c0
[  484.550782]  do_syscall_64+0x5b/0x170
[  484.551067]  entry_SYSCALL_64_after_hwframe+0x76/0x7e

Adding a call to `netif_napi_set_irq` with -1 as the IRQ index,
which frees the notifier.

Fixes: de340d8206bf ("net: ena: use napi's aRFS rmap notifers")
Signed-off-by: David Arinzon <darinzon@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Ahmed Zaki <ahmed.zaki@intel.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c
index 6aab85a7c60a1..70fa3adb49342 100644
--- a/drivers/net/ethernet/amazon/ena/ena_netdev.c
+++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c
@@ -1716,8 +1716,12 @@ static void ena_free_io_irq(struct ena_adapter *adapter)
 	int i;
 
 	for (i = ENA_IO_IRQ_FIRST_IDX; i < ENA_MAX_MSIX_VEC(io_queue_count); i++) {
+		struct ena_napi *ena_napi;
+
 		irq = &adapter->irq_tbl[i];
 		irq_set_affinity_hint(irq->vector, NULL);
+		ena_napi = irq->data;
+		netif_napi_set_irq(&ena_napi->napi, -1);
 		free_irq(irq->vector, irq->data);
 	}
 }

From 5460d7173a7a51d5d83f9846512e52bc94e9f752 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Mon, 17 Mar 2025 08:48:34 +0100
Subject: [PATCH 2501/2753] net: phy: dp83822: fix transmit amplitude if
 CONFIG_OF_MDIO not defined

When CONFIG_OF_MDIO is not defined the index for selecting the transmit
amplitude voltage for 100BASE-TX is set to 0, but it should be -1, if there
is no need to modify the transmit amplitude voltage. Move initialization of
the index from dp83822_of_init to dp8382x_probe.

Fixes: 4f3735e82d8a ("net: phy: dp83822: Add support for changing the transmit amplitude voltage")
Reviewed-by: Gerhard Engleder <gerhard@engleder-embedded.com>
Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/dp83822.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 3662f3905d5ad..14f3615496384 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -833,7 +833,6 @@ static int dp83822_of_init(struct phy_device *phydev)
 		dp83822->set_gpio2_clk_out = true;
 	}
 
-	dp83822->tx_amplitude_100base_tx_index = -1;
 	ret = phy_get_tx_amplitude_gain(phydev, dev,
 					ETHTOOL_LINK_MODE_100baseT_Full_BIT,
 					&val);
@@ -931,6 +930,7 @@ static int dp8382x_probe(struct phy_device *phydev)
 	if (!dp83822)
 		return -ENOMEM;
 
+	dp83822->tx_amplitude_100base_tx_index = -1;
 	phydev->priv = dp83822;
 
 	return 0;

From f1c630061163ebc857f2fe7282a6dcdf6cb0409f Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Mon, 17 Mar 2025 10:52:23 +0100
Subject: [PATCH 2502/2753] vsock/bpf: Fix EINTR connect() racing sockmap
 update

Signal delivery during connect() may result in a disconnect of an already
TCP_ESTABLISHED socket. Problem is that such established socket might have
been placed in a sockmap before the connection was closed. We end up with a
SS_UNCONNECTED vsock in a sockmap. And this, combined with the ability to
reassign (unconnected) vsock's transport to NULL, breaks the sockmap
contract. As manifested by WARN_ON_ONCE.

connect
  / state = SS_CONNECTED /
                                sock_map_update_elem
  if signal_pending
    state = SS_UNCONNECTED

connect
  transport = NULL
                                vsock_bpf_recvmsg
                                  WARN_ON_ONCE(!vsk->transport)

Ensure the socket does not stay in sockmap.

WARNING: CPU: 8 PID: 1228 at net/vmw_vsock/vsock_bpf.c:97 vsock_bpf_recvmsg+0xb43/0xe00
CPU: 8 UID: 0 PID: 1228 Comm: a.out Not tainted 6.14.0-rc5+
RIP: 0010:vsock_bpf_recvmsg+0xb43/0xe00
 sock_recvmsg+0x1b2/0x220
 __sys_recvfrom+0x190/0x270
 __x64_sys_recvfrom+0xdc/0x1b0
 do_syscall_64+0x93/0x1b0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: 634f1a7110b4 ("vsock: support sockmap")
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: NipaLocal <nipa@local>
---
 net/vmw_vsock/af_vsock.c  | 10 +++++++++-
 net/vmw_vsock/vsock_bpf.c |  1 +
 2 files changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 7e3db87ae4333..81b1b8e9c946a 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -1579,7 +1579,15 @@ static int vsock_connect(struct socket *sock, struct sockaddr *addr,
 
 		if (signal_pending(current)) {
 			err = sock_intr_errno(timeout);
-			sk->sk_state = sk->sk_state == TCP_ESTABLISHED ? TCP_CLOSING : TCP_CLOSE;
+			if (sk->sk_state == TCP_ESTABLISHED) {
+				/* Might have raced with a sockmap update. */
+				if (sk->sk_prot->unhash)
+					sk->sk_prot->unhash(sk);
+
+				sk->sk_state = TCP_CLOSING;
+			} else {
+				sk->sk_state = TCP_CLOSE;
+			}
 			sock->state = SS_UNCONNECTED;
 			vsock_transport_cancel_pkt(vsk);
 			vsock_remove_connected(vsk);
diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
index 07b96d56f3a57..c68fdaf09046b 100644
--- a/net/vmw_vsock/vsock_bpf.c
+++ b/net/vmw_vsock/vsock_bpf.c
@@ -127,6 +127,7 @@ static void vsock_bpf_rebuild_protos(struct proto *prot, const struct proto *bas
 {
 	*prot        = *base;
 	prot->close  = sock_map_close;
+	prot->unhash = sock_map_unhash;
 	prot->recvmsg = vsock_bpf_recvmsg;
 	prot->sock_is_readable = sk_msg_is_readable;
 }

From 4ce637d354d1cab94a08f498185fdb9f3cdd278c Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Mon, 17 Mar 2025 10:52:24 +0100
Subject: [PATCH 2503/2753] selftest/bpf: Add test for AF_VSOCK connect()
 racing sockmap update

Racing signal-interrupted connect() and sockmap update may result in an
unconnected (and missing vsock transport) socket in a sockmap.

Test spends 2 seconds attempting to reach WARN_ON_ONCE().

connect
  / state = SS_CONNECTED /
                                sock_map_update_elem
  if signal_pending
    state = SS_UNCONNECTED

connect
  transport = NULL
                                vsock_bpf_recvmsg
                                  WARN_ON_ONCE(!vsk->transport)

Signed-off-by: Michal Luczaj <mhal@rbox.co>
Acked-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/bpf/prog_tests/sockmap_basic.c  | 99 +++++++++++++++++++
 1 file changed, 99 insertions(+)

diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
index 1e3e4392dcca0..2f8bba2786635 100644
--- a/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
+++ b/tools/testing/selftests/bpf/prog_tests/sockmap_basic.c
@@ -3,6 +3,7 @@
 #include <error.h>
 #include <netinet/tcp.h>
 #include <sys/epoll.h>
+#include <linux/time64.h>
 
 #include "test_progs.h"
 #include "test_skmsg_load_helpers.skel.h"
@@ -1042,6 +1043,102 @@ static void test_sockmap_vsock_unconnected(void)
 	xclose(map);
 }
 
+#define CONNECT_SIGNAL_RACE_TIMEOUT 2 /* seconds */
+
+static void sig_handler(int signum)
+{
+	/* nop */
+}
+
+static void connect_signal_racer_cleanup(void *map)
+{
+	xclose(*(int *)map);
+}
+
+static void *connect_signal_racer(void *arg)
+{
+	pid_t pid;
+	int map;
+
+	map = bpf_map_create(BPF_MAP_TYPE_SOCKMAP, NULL, sizeof(int),
+			     sizeof(int), 1, NULL);
+	if (!ASSERT_OK_FD(map, "bpf_map_create"))
+		return NULL;
+
+	pthread_cleanup_push(connect_signal_racer_cleanup, &map);
+	pid = getpid();
+
+	for (;;) {
+		int c = *(int *)arg;
+		int zero = 0;
+
+		(void)bpf_map_update_elem(map, &zero, &c, BPF_ANY);
+
+		if (kill(pid, SIGUSR1)) {
+			FAIL_ERRNO("kill");
+			break;
+		}
+
+		if ((recv(c, NULL, 0, MSG_DONTWAIT) < 0) && errno == ENODEV) {
+			FAIL_ERRNO("recv");
+			break;
+		}
+	}
+
+	pthread_cleanup_pop(1);
+
+	return NULL;
+}
+
+static void test_sockmap_vsock_connect_signal_race(void)
+{
+	struct sockaddr_vm addr, bad_addr;
+	socklen_t alen = sizeof(addr);
+	sighandler_t orig_handler;
+	pthread_t thread;
+	int s, c, p;
+	__u64 tout;
+
+	orig_handler = signal(SIGUSR1, sig_handler);
+	if (!ASSERT_NEQ(orig_handler, SIG_ERR, "signal handler setup"))
+		return;
+
+	s = socket_loopback(AF_VSOCK, SOCK_SEQPACKET | SOCK_NONBLOCK);
+	if (s < 0)
+		goto restore;
+
+	if (xgetsockname(s, (struct sockaddr *)&addr, &alen))
+		goto close;
+
+	bad_addr = addr;
+	bad_addr.svm_cid = 0x42424242; /* non-existing */
+
+	if (xpthread_create(&thread, 0, connect_signal_racer, &c))
+		goto close;
+
+	tout = get_time_ns() + CONNECT_SIGNAL_RACE_TIMEOUT * NSEC_PER_SEC;
+	do {
+		c = xsocket(AF_VSOCK, SOCK_SEQPACKET, 0);
+		if (c < 0)
+			break;
+
+		if (connect(c, (struct sockaddr *)&addr, alen) && errno == EINTR)
+			(void)connect(c, (struct sockaddr *)&bad_addr, alen);
+
+		xclose(c);
+		p = accept(s, NULL, NULL);
+		if (p >= 0)
+			xclose(p);
+	} while (get_time_ns() < tout);
+
+	ASSERT_OK(pthread_cancel(thread), "pthread_cancel");
+	xpthread_join(thread, NULL);
+close:
+	xclose(s);
+restore:
+	ASSERT_NEQ(signal(SIGUSR1, orig_handler), SIG_ERR, "handler restore");
+}
+
 void test_sockmap_basic(void)
 {
 	if (test__start_subtest("sockmap create_update_free"))
@@ -1108,4 +1205,6 @@ void test_sockmap_basic(void)
 		test_sockmap_skb_verdict_vsock_poll();
 	if (test__start_subtest("sockmap vsock unconnected"))
 		test_sockmap_vsock_unconnected();
+	if (test__start_subtest("sockmap vsock connect signal race"))
+		test_sockmap_vsock_connect_signal_race();
 }

From ac3e3ece5610c761120cdce67ed83e7d224176d2 Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Mon, 17 Mar 2025 10:52:25 +0100
Subject: [PATCH 2504/2753] vsock/bpf: Fix bpf recvmsg() racing transport
 reassignment

Signal delivery during connect() may lead to a disconnect of an already
established socket. That involves removing socket from any sockmap and
resetting state to SS_UNCONNECTED. While it correctly restores socket's
proto, a call to vsock_bpf_recvmsg() might have been already under way in
another thread. If the connect()ing thread reassigns the vsock transport to
NULL, the recvmsg()ing thread may trigger a WARN_ON_ONCE.

connect
  / state = SS_CONNECTED /
                                sock_map_update_elem
                                vsock_bpf_recvmsg
                                  psock = sk_psock_get()
  lock sk
  if signal_pending
    unhash
      sock_map_remove_links
    state = SS_UNCONNECTED
  release sk

connect
  transport = NULL
                                  lock sk
                                  WARN_ON_ONCE(!vsk->transport)

Protect recvmsg() from racing against transport reassignment. Enforce the
sockmap invariant that psock implies transport: lock socket before getting
psock.

WARNING: CPU: 9 PID: 1222 at net/vmw_vsock/vsock_bpf.c:92 vsock_bpf_recvmsg+0xb55/0xe00
CPU: 9 UID: 0 PID: 1222 Comm: a.out Not tainted 6.14.0-rc5+
RIP: 0010:vsock_bpf_recvmsg+0xb55/0xe00
 sock_recvmsg+0x1b2/0x220
 __sys_recvfrom+0x190/0x270
 __x64_sys_recvfrom+0xdc/0x1b0
 do_syscall_64+0x93/0x1b0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Fixes: 634f1a7110b4 ("vsock: support sockmap")
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Signed-off-by: NipaLocal <nipa@local>
---
 net/vmw_vsock/vsock_bpf.c | 23 +++++++++++++++--------
 1 file changed, 15 insertions(+), 8 deletions(-)

diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
index c68fdaf09046b..5138195d91fb2 100644
--- a/net/vmw_vsock/vsock_bpf.c
+++ b/net/vmw_vsock/vsock_bpf.c
@@ -73,28 +73,35 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int
 	return err;
 }
 
-static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
-			     size_t len, int flags, int *addr_len)
+static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			     int flags, int *addr_len)
 {
 	struct sk_psock *psock;
 	struct vsock_sock *vsk;
 	int copied;
 
+	/* Since signal delivery during connect() may reset the state of socket
+	 * that's already in a sockmap, take the lock before checking on psock.
+	 * This serializes a possible transport reassignment, protecting this
+	 * function from running with NULL transport.
+	 */
+	lock_sock(sk);
+
 	psock = sk_psock_get(sk);
-	if (unlikely(!psock))
+	if (unlikely(!psock)) {
+		release_sock(sk);
 		return __vsock_recvmsg(sk, msg, len, flags);
+	}
 
-	lock_sock(sk);
 	vsk = vsock_sk(sk);
-
 	if (WARN_ON_ONCE(!vsk->transport)) {
 		copied = -ENODEV;
 		goto out;
 	}
 
 	if (vsock_has_data(sk, psock) && sk_psock_queue_empty(psock)) {
-		release_sock(sk);
 		sk_psock_put(sk, psock);
+		release_sock(sk);
 		return __vsock_recvmsg(sk, msg, len, flags);
 	}
 
@@ -108,8 +115,8 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 		}
 
 		if (sk_psock_queue_empty(psock)) {
-			release_sock(sk);
 			sk_psock_put(sk, psock);
+			release_sock(sk);
 			return __vsock_recvmsg(sk, msg, len, flags);
 		}
 
@@ -117,8 +124,8 @@ static int vsock_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
 	}
 
 out:
-	release_sock(sk);
 	sk_psock_put(sk, psock);
+	release_sock(sk);
 
 	return copied;
 }

From 7398bd1e782d482bc0493f1a83baa84fec133a94 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Mon, 17 Mar 2025 08:53:13 +0000
Subject: [PATCH 2505/2753] tcp: move icsk_clean_acked to a better location

As a followup of my presentation in Zagreb for netdev 0x19:

icsk_clean_acked is only used by TCP when/if CONFIG_TLS_DEVICE
is enabled from tcp_ack().

Rename it to tcp_clean_acked, move it to tcp_sock structure
in the tcp_sock_read_rx for better cache locality in TCP
fast path.

Define this field only when CONFIG_TLS_DEVICE is enabled
saving 8 bytes on configs not using it.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/net_cachelines/tcp_sock.rst |  1 +
 include/linux/tcp.h                                  |  3 +++
 include/net/inet_connection_sock.h                   |  2 --
 include/net/tcp.h                                    |  4 ++--
 net/ipv4/tcp.c                                       |  5 +++++
 net/ipv4/tcp_input.c                                 | 12 ++++++------
 net/tls/tls_device.c                                 |  8 ++++----
 7 files changed, 21 insertions(+), 14 deletions(-)

diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index 1f79765072b10..bc9b2131bf7ac 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -27,6 +27,7 @@ u32                           dsack_dups
 u32                           snd_una                 read_mostly         read_write          tcp_wnd_end,tcp_urg_mode,tcp_minshall_check,tcp_cwnd_validate(tx);tcp_ack,tcp_may_update_window,tcp_clean_rtx_queue(write),tcp_ack_tstamp(rx)
 u32                           snd_sml                 read_write                              tcp_minshall_check,tcp_minshall_update
 u32                           rcv_tstamp                                  read_mostly         tcp_ack
+void *                        tcp_clean_acked                             read_mostly         tcp_ack
 u32                           lsndtime                read_write                              tcp_slow_start_after_idle_check,tcp_event_data_sent
 u32                           last_oow_ack_time
 u32                           compressed_ack_rcv_nxt
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 159b2c59eb627..1669d95bb0f9a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -244,6 +244,9 @@ struct tcp_sock {
 	struct  minmax rtt_min;
 	/* OOO segments go in this rbtree. Socket lock must be held. */
 	struct rb_root	out_of_order_queue;
+#if defined(CONFIG_TLS_DEVICE)
+	void (*tcp_clean_acked)(struct sock *sk, u32 acked_seq);
+#endif
 	u32	snd_ssthresh;	/* Slow start size threshold		*/
 	u8	recvmsg_inq : 1;/* Indicate # of bytes in queue upon recvmsg */
 	__cacheline_group_end(tcp_sock_read_rx);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index f736d3097e43d..e8ed52fc603f2 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -66,7 +66,6 @@ struct inet_connection_sock_af_ops {
  * @icsk_af_ops		   Operations which are AF_INET{4,6} specific
  * @icsk_ulp_ops	   Pluggable ULP control hook
  * @icsk_ulp_data	   ULP private data
- * @icsk_clean_acked	   Clean acked data hook
  * @icsk_ca_state:	   Congestion control state
  * @icsk_retransmits:	   Number of unrecovered [RTO] timeouts
  * @icsk_pending:	   Scheduled timer event
@@ -97,7 +96,6 @@ struct inet_connection_sock {
 	const struct inet_connection_sock_af_ops *icsk_af_ops;
 	const struct tcp_ulp_ops  *icsk_ulp_ops;
 	void __rcu		  *icsk_ulp_data;
-	void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
 	unsigned int		  (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
 	__u8			  icsk_ca_state:5,
 				  icsk_ca_initialized:1,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index d08fbf90495de..f8efe56bbccb1 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2815,9 +2815,9 @@ extern struct static_key_false tcp_have_smc;
 #endif
 
 #if IS_ENABLED(CONFIG_TLS_DEVICE)
-void clean_acked_data_enable(struct inet_connection_sock *icsk,
+void clean_acked_data_enable(struct tcp_sock *tp,
 			     void (*cad)(struct sock *sk, u32 ack_seq));
-void clean_acked_data_disable(struct inet_connection_sock *icsk);
+void clean_acked_data_disable(struct tcp_sock *tp);
 void clean_acked_data_flush(void);
 #endif
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 989c3c3d8e757..fde56d28f586d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5026,7 +5026,12 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, rtt_min);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, out_of_order_queue);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, snd_ssthresh);
+#if IS_ENABLED(CONFIG_TLS_DEVICE)
+	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_rx, tcp_clean_acked);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 77);
+#else
 	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_rx, 69);
+#endif
 
 	/* TX read-write hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_write_tx, segs_out);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 72382ee4456db..a35018e2d0ba2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -119,18 +119,18 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
 #if IS_ENABLED(CONFIG_TLS_DEVICE)
 static DEFINE_STATIC_KEY_DEFERRED_FALSE(clean_acked_data_enabled, HZ);
 
-void clean_acked_data_enable(struct inet_connection_sock *icsk,
+void clean_acked_data_enable(struct tcp_sock *tp,
 			     void (*cad)(struct sock *sk, u32 ack_seq))
 {
-	icsk->icsk_clean_acked = cad;
+	tp->tcp_clean_acked = cad;
 	static_branch_deferred_inc(&clean_acked_data_enabled);
 }
 EXPORT_SYMBOL_GPL(clean_acked_data_enable);
 
-void clean_acked_data_disable(struct inet_connection_sock *icsk)
+void clean_acked_data_disable(struct tcp_sock *tp)
 {
 	static_branch_slow_dec_deferred(&clean_acked_data_enabled);
-	icsk->icsk_clean_acked = NULL;
+	tp->tcp_clean_acked = NULL;
 }
 EXPORT_SYMBOL_GPL(clean_acked_data_disable);
 
@@ -3987,8 +3987,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
 
 #if IS_ENABLED(CONFIG_TLS_DEVICE)
 		if (static_branch_unlikely(&clean_acked_data_enabled.key))
-			if (icsk->icsk_clean_acked)
-				icsk->icsk_clean_acked(sk, ack);
+			if (tp->tcp_clean_acked)
+				tp->tcp_clean_acked(sk, ack);
 #endif
 	}
 
diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c
index e50b6e71df13b..f672a62a9a52f 100644
--- a/net/tls/tls_device.c
+++ b/net/tls/tls_device.c
@@ -157,7 +157,7 @@ static void delete_all_records(struct tls_offload_context_tx *offload_ctx)
 	offload_ctx->retransmit_hint = NULL;
 }
 
-static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq)
+static void tls_tcp_clean_acked(struct sock *sk, u32 acked_seq)
 {
 	struct tls_context *tls_ctx = tls_get_ctx(sk);
 	struct tls_record_info *info, *temp;
@@ -204,7 +204,7 @@ void tls_device_sk_destruct(struct sock *sk)
 			destroy_record(ctx->open_record);
 		delete_all_records(ctx);
 		crypto_free_aead(ctx->aead_send);
-		clean_acked_data_disable(inet_csk(sk));
+		clean_acked_data_disable(tcp_sk(sk));
 	}
 
 	tls_device_queue_ctx_destruction(tls_ctx);
@@ -1126,7 +1126,7 @@ int tls_set_device_offload(struct sock *sk)
 	start_marker_record->num_frags = 0;
 	list_add_tail(&start_marker_record->list, &offload_ctx->records_list);
 
-	clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked);
+	clean_acked_data_enable(tcp_sk(sk), &tls_tcp_clean_acked);
 	ctx->push_pending_record = tls_device_push_pending_record;
 
 	/* TLS offload is greatly simplified if we don't send
@@ -1172,7 +1172,7 @@ int tls_set_device_offload(struct sock *sk)
 
 release_lock:
 	up_read(&device_offload_lock);
-	clean_acked_data_disable(inet_csk(sk));
+	clean_acked_data_disable(tcp_sk(sk));
 	crypto_free_aead(offload_ctx->aead_send);
 free_offload_ctx:
 	kfree(offload_ctx);

From 752a9098d77ddb8ebefe6674b9cfc914018b632a Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Mon, 17 Mar 2025 10:04:00 +0100
Subject: [PATCH 2506/2753] net: pktgen: add strict buffer parsing index check

Add strict buffer parsing index check to avoid the following Smatch
warning:

  net/core/pktgen.c:877 get_imix_entries()
  warn: check that incremented offset 'i' is capped

Checking the buffer index i after every get_user/i++ step and returning
with error code immediately avoids the current indirect (but correct)
error handling.

Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/netdev/36cf3ee2-38b1-47e5-a42a-363efeb0ace3@stanley.mountain/
Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/pktgen.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index e850598db3e70..fe7fdefab994c 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -856,6 +856,9 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		if (pkt_dev->n_imix_entries >= MAX_IMIX_ENTRIES)
 			return -E2BIG;
 
+		if (i >= maxlen)
+			return -EINVAL;
+
 		max = min(10, maxlen - i);
 		len = num_arg(&buffer[i], max, &size);
 		if (len < 0)
@@ -869,6 +872,8 @@ static ssize_t get_imix_entries(const char __user *buffer,
 		if (c != ',')
 			return -EINVAL;
 		i++;
+		if (i >= maxlen)
+			return -EINVAL;
 
 		if (size < 14 + 20 + 8)
 			size = 14 + 20 + 8;
@@ -911,6 +916,9 @@ static ssize_t get_labels(const char __user *buffer,
 		if (n >= MAX_MPLS_LABELS)
 			return -E2BIG;
 
+		if (i >= maxlen)
+			return -EINVAL;
+
 		max = min(8, maxlen - i);
 		len = hex32_arg(&buffer[i], max, &tmp);
 		if (len < 0)

From 4d2626f1390227052e3ab3e76389c8a0f07ef2cf Mon Sep 17 00:00:00 2001
From: Peter Seiderer <ps.report@gmx.net>
Date: Mon, 17 Mar 2025 10:04:01 +0100
Subject: [PATCH 2507/2753] selftest: net: update proc_net_pktgen (add more
 imix_weights test cases)

Add more imix_weights test cases (for incomplete input).

Signed-off-by: Peter Seiderer <ps.report@gmx.net>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/proc_net_pktgen.c | 44 +++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/tools/testing/selftests/net/proc_net_pktgen.c b/tools/testing/selftests/net/proc_net_pktgen.c
index 462805ac16147..69444fb295778 100644
--- a/tools/testing/selftests/net/proc_net_pktgen.c
+++ b/tools/testing/selftests/net/proc_net_pktgen.c
@@ -39,6 +39,10 @@ static const char dev_cmd_pkt_size_0[] = "pkt_size 300";
 static const char dev_cmd_imix_weights_0[] = "imix_weights 0,7 576,4 1500,1";
 static const char dev_cmd_imix_weights_1[] = "imix_weights 101,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20";
 static const char dev_cmd_imix_weights_2[] = "imix_weights 100,1 102,2 103,3 104,4 105,5 106,6 107,7 108,8 109,9 110,10 111,11 112,12 113,13 114,14 115,15 116,16 117,17 118,18 119,19 120,20 121,21";
+static const char dev_cmd_imix_weights_3[] = "imix_weights";
+static const char dev_cmd_imix_weights_4[] = "imix_weights ";
+static const char dev_cmd_imix_weights_5[] = "imix_weights 0";
+static const char dev_cmd_imix_weights_6[] = "imix_weights 0,";
 static const char dev_cmd_debug_0[] = "debug 1";
 static const char dev_cmd_debug_1[] = "debug 0";
 static const char dev_cmd_frags_0[] = "frags 100";
@@ -284,6 +288,46 @@ TEST_F(proc_net_pktgen, dev_cmd_imix_weights) {
 	len = write(self->dev_fd, dev_cmd_imix_weights_2, sizeof(dev_cmd_imix_weights_2));
 	EXPECT_EQ(len, -1);
 	EXPECT_EQ(errno, E2BIG);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_3, sizeof(dev_cmd_imix_weights_3) - 1);
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_4, sizeof(dev_cmd_imix_weights_4) - 1);
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_5, sizeof(dev_cmd_imix_weights_5) - 1);
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* with trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6));
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
+
+	/* without trailing '\0' */
+	len = write(self->dev_fd, dev_cmd_imix_weights_6, sizeof(dev_cmd_imix_weights_6) - 1);
+	EXPECT_EQ(len, -1);
+	EXPECT_EQ(errno, EINVAL);
 }
 
 TEST_F(proc_net_pktgen, dev_cmd_debug) {

From 6b9302888b03f5d2e217385e29d1bd3341deb961 Mon Sep 17 00:00:00 2001
From: Fan Gong <gongfan1@huawei.com>
Date: Mon, 17 Mar 2025 11:40:39 +0200
Subject: [PATCH 2508/2753] hinic3: module initialization and tx/rx logic

This is [1/3] part of hinic3 Ethernet driver initial submission.
With this patch hinic3 is a valid kernel module but non-functional
driver.

The driver parts contained in this patch:
Module initialization.
PCI driver registration but with empty id_table.
Auxiliary driver registration.
Net device_ops registration but open/stop are empty stubs.
tx/rx logic.

All major data structures of the driver are fully introduced with the
code that uses them but without their initialization code that requires
management interface with the hw.

Co-developed-by: Xin Guo <guoxin09@huawei.com>
Signed-off-by: Xin Guo <guoxin09@huawei.com>
Signed-off-by: Fan Gong <gongfan1@huawei.com>
Co-developed-by: Gur Stavi <gur.stavi@huawei.com>
Signed-off-by: Gur Stavi <gur.stavi@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../device_drivers/ethernet/huawei/hinic3.rst | 137 ++++
 .../device_drivers/ethernet/index.rst         |   1 +
 MAINTAINERS                                   |   7 +
 drivers/net/ethernet/huawei/Kconfig           |   1 +
 drivers/net/ethernet/huawei/Makefile          |   1 +
 drivers/net/ethernet/huawei/hinic3/Kconfig    |  19 +
 drivers/net/ethernet/huawei/hinic3/Makefile   |  21 +
 .../ethernet/huawei/hinic3/hinic3_common.c    |  53 ++
 .../ethernet/huawei/hinic3/hinic3_common.h    |  27 +
 .../ethernet/huawei/hinic3/hinic3_hw_cfg.c    |  24 +
 .../ethernet/huawei/hinic3/hinic3_hw_cfg.h    |  53 ++
 .../ethernet/huawei/hinic3/hinic3_hw_comm.c   |  32 +
 .../ethernet/huawei/hinic3/hinic3_hw_comm.h   |  13 +
 .../ethernet/huawei/hinic3/hinic3_hw_intf.h   | 113 +++
 .../net/ethernet/huawei/hinic3/hinic3_hwdev.c |  24 +
 .../net/ethernet/huawei/hinic3/hinic3_hwdev.h |  81 ++
 .../net/ethernet/huawei/hinic3/hinic3_hwif.c  |  21 +
 .../net/ethernet/huawei/hinic3/hinic3_hwif.h  |  58 ++
 .../net/ethernet/huawei/hinic3/hinic3_irq.c   |  47 ++
 .../net/ethernet/huawei/hinic3/hinic3_lld.c   | 416 +++++++++++
 .../net/ethernet/huawei/hinic3/hinic3_lld.h   |  21 +
 .../net/ethernet/huawei/hinic3/hinic3_main.c  | 357 +++++++++
 .../net/ethernet/huawei/hinic3/hinic3_mbox.c  |  16 +
 .../net/ethernet/huawei/hinic3/hinic3_mbox.h  |  15 +
 .../net/ethernet/huawei/hinic3/hinic3_mgmt.h  |  13 +
 .../huawei/hinic3/hinic3_mgmt_interface.h     | 105 +++
 .../huawei/hinic3/hinic3_netdev_ops.c         |  77 ++
 .../ethernet/huawei/hinic3/hinic3_nic_cfg.c   | 230 ++++++
 .../ethernet/huawei/hinic3/hinic3_nic_cfg.h   |  39 +
 .../ethernet/huawei/hinic3/hinic3_nic_dev.h   |  91 +++
 .../ethernet/huawei/hinic3/hinic3_nic_io.c    |  21 +
 .../ethernet/huawei/hinic3/hinic3_nic_io.h    | 118 +++
 .../huawei/hinic3/hinic3_queue_common.c       |  67 ++
 .../huawei/hinic3/hinic3_queue_common.h       |  54 ++
 .../net/ethernet/huawei/hinic3/hinic3_rx.c    | 404 ++++++++++
 .../net/ethernet/huawei/hinic3/hinic3_rx.h    |  91 +++
 .../net/ethernet/huawei/hinic3/hinic3_tx.c    | 691 ++++++++++++++++++
 .../net/ethernet/huawei/hinic3/hinic3_tx.h    | 130 ++++
 .../net/ethernet/huawei/hinic3/hinic3_wq.c    |  29 +
 .../net/ethernet/huawei/hinic3/hinic3_wq.h    |  76 ++
 40 files changed, 3794 insertions(+)
 create mode 100644 Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
 create mode 100644 drivers/net/ethernet/huawei/hinic3/Kconfig
 create mode 100644 drivers/net/ethernet/huawei/hinic3/Makefile
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_common.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_common.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_main.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
 create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_wq.h

diff --git a/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst b/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
new file mode 100644
index 0000000000000..e3dfd083fa525
--- /dev/null
+++ b/Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
@@ -0,0 +1,137 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================================================
+Linux kernel driver for Huawei Ethernet Device Driver (hinic3) family
+=====================================================================
+
+Overview
+========
+
+The hinic3 is a network interface card (NIC) for Data Center. It supports
+a range of link-speed devices (10GE, 25GE, 100GE, etc.). The hinic3
+devices can have multiple physical forms: LOM (Lan on Motherboard) NIC,
+PCIe standard NIC, OCP (Open Compute Project) NIC, etc.
+
+The hinic3 driver supports the following features:
+- IPv4/IPv6 TCP/UDP checksum offload
+- TSO (TCP Segmentation Offload), LRO (Large Receive Offload)
+- RSS (Receive Side Scaling)
+- MSI-X interrupt aggregation configuration and interrupt adaptation.
+- SR-IOV (Single Root I/O Virtualization).
+
+Content
+=======
+
+- Supported PCI vendor ID/device IDs
+- Source Code Structure of Hinic3 Driver
+- Management Interface
+
+Supported PCI vendor ID/device IDs
+==================================
+
+19e5:0222 - hinic3 PF/PPF
+19e5:375F - hinic3 VF
+
+Prime Physical Function (PPF) is responsible for the management of the
+whole NIC card. For example, clock synchronization between the NIC and
+the host. Any PF may serve as a PPF. The PPF is selected dynamically.
+
+Source Code Structure of Hinic3 Driver
+======================================
+
+========================  ================================================
+hinic3_pci_id_tbl.h       Supported device IDs
+hinic3_hw_intf.h          Interface between HW and driver
+hinic3_queue_common.[ch]  Common structures and methods for NIC queues
+hinic3_common.[ch]        Encapsulation of memory operations in Linux
+hinic3_csr.h              Register definitions in the BAR
+hinic3_hwif.[ch]          Interface for BAR
+hinic3_eqs.[ch]           Interface for AEQs and CEQs
+hinic3_mbox.[ch]          Interface for mailbox
+hinic3_mgmt.[ch]          Management interface based on mailbox and AEQ
+hinic3_wq.[ch]            Work queue data structures and interface
+hinic3_cmdq.[ch]          Command queue is used to post command to HW
+hinic3_hwdev.[ch]         HW structures and methods abstractions
+hinic3_lld.[ch]           Auxiliary driver adaptation layer
+hinic3_hw_comm.[ch]       Interface for common HW operations
+hinic3_mgmt_interface.h   Interface between firmware and driver
+hinic3_hw_cfg.[ch]        Interface for HW configuration
+hinic3_irq.c              Interrupt request
+hinic3_netdev_ops.c       Operations registered to Linux kernel stack
+hinic3_nic_dev.h          NIC structures and methods abstractions
+hinic3_main.c             Main Linux kernel driver
+hinic3_nic_cfg.[ch]       NIC service configuration
+hinic3_nic_io.[ch]        Management plane interface for TX and RX
+hinic3_rss.[ch]           Interface for Receive Side Scaling (RSS)
+hinic3_rx.[ch]            Interface for transmit
+hinic3_tx.[ch]            Interface for receive
+hinic3_ethtool.c          Interface for ethtool operations (ops)
+hinic3_filter.c           Interface for MAC address
+========================  ================================================
+
+Management Interface
+====================
+
+Asynchronous Event Queue (AEQ)
+------------------------------
+
+AEQ receives high priority events from the HW over a descriptor queue.
+Every descriptor is a fixed size of 64 bytes. AEQ can receive solicited or
+unsolicited events. Every device, VF or PF, can have up to 4 AEQs.
+Every AEQ is associated to a dedicated IRQ. AEQ can receive multiple types
+of events, but in practice the hinic3 driver ignores all events except for
+2 mailbox related events.
+
+Mailbox
+-------
+
+Mailbox is a communication mechanism between the hinic3 driver and the HW.
+Each device has an independent mailbox. Driver can use the mailbox to send
+requests to management. Driver receives mailbox messages, such as responses
+to requests, over the AEQ (using event HINIC3_AEQ_FOR_MBOX). Due to the
+limited size of mailbox data register, mailbox messages are sent
+segment-by-segment.
+
+Every device can use its mailbox to post request to firmware. The mailbox
+can also be used to post requests and responses between the PF and its VFs.
+
+Completion Event Queue (CEQ)
+----------------------------
+
+The implementation of CEQ is the same as AEQ. It receives completion events
+from HW over a fixed size descriptor of 32 bits. Every device can have up
+to 32 CEQs. Every CEQ has a dedicated IRQ. CEQ only receives solicited
+events that are responses to requests from the driver. CEQ can receive
+multiple types of events, but in practice the hinic3 driver ignores all
+events except for HINIC3_CMDQ that represents completion of previously
+posted commands on a cmdq.
+
+Command Queue (cmdq)
+--------------------
+
+Every cmdq has a dedicated work queue on which commands are posted.
+Commands on the work queue are fixed size descriptor of size 64 bytes.
+Completion of a command will be indicated using ctrl bits in the
+descriptor that carried the command. Notification of command completions
+will also be provided via event on CEQ. Every device has 4 command queues
+that are initialized as a set (called cmdqs), each with its own type.
+Hinic3 driver only uses type HINIC3_CMDQ_SYNC.
+
+Work Queues(WQ)
+---------------
+
+Work queues are logical arrays of fixed size WQEs. The array may be spread
+over multiple non-contiguous pages using indirection table. Work queues are
+used by I/O queues and command queues.
+
+Global function ID
+------------------
+
+Every function, PF or VF, has a unique ordinal identification within the device.
+Many management commands (mbox or cmdq) contain this ID so HW can apply the
+command effect to the right function.
+
+PF is allowed to post management commands to a subordinate VF by specifying the
+VFs ID. A VF must provide its own ID. Anti-spoofing in the HW will cause
+command from a VF to fail if it contains the wrong ID.
+
diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst
index 6fc1961492b77..f0dd920be12f4 100644
--- a/Documentation/networking/device_drivers/ethernet/index.rst
+++ b/Documentation/networking/device_drivers/ethernet/index.rst
@@ -28,6 +28,7 @@ Contents:
    freescale/gianfar
    google/gve
    huawei/hinic
+   huawei/hinic3
    intel/e100
    intel/e1000
    intel/e1000e
diff --git a/MAINTAINERS b/MAINTAINERS
index 3594b6c6e6107..3cf5f4729fe66 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10700,6 +10700,13 @@ S:	Maintained
 F:	Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
 F:	drivers/net/ethernet/huawei/hinic/
 
+HUAWEI 3RD GEN ETHERNET DRIVER
+M:	Fan Gong <gongfan1@huawei.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	Documentation/networking/device_drivers/ethernet/huawei/hinic3.rst
+F:	drivers/net/ethernet/huawei/hinic3/
+
 HUGETLB SUBSYSTEM
 M:	Muchun Song <muchun.song@linux.dev>
 L:	linux-mm@kvack.org
diff --git a/drivers/net/ethernet/huawei/Kconfig b/drivers/net/ethernet/huawei/Kconfig
index c05fce15eb518..7d0feb1da158a 100644
--- a/drivers/net/ethernet/huawei/Kconfig
+++ b/drivers/net/ethernet/huawei/Kconfig
@@ -16,5 +16,6 @@ config NET_VENDOR_HUAWEI
 if NET_VENDOR_HUAWEI
 
 source "drivers/net/ethernet/huawei/hinic/Kconfig"
+source "drivers/net/ethernet/huawei/hinic3/Kconfig"
 
 endif # NET_VENDOR_HUAWEI
diff --git a/drivers/net/ethernet/huawei/Makefile b/drivers/net/ethernet/huawei/Makefile
index 2549ad5afe6d4..59865b8828792 100644
--- a/drivers/net/ethernet/huawei/Makefile
+++ b/drivers/net/ethernet/huawei/Makefile
@@ -4,3 +4,4 @@
 #
 
 obj-$(CONFIG_HINIC) += hinic/
+obj-$(CONFIG_HINIC3) += hinic3/
diff --git a/drivers/net/ethernet/huawei/hinic3/Kconfig b/drivers/net/ethernet/huawei/hinic3/Kconfig
new file mode 100644
index 0000000000000..70e30a2af6a5a
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Kconfig
@@ -0,0 +1,19 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Huawei driver configuration
+#
+
+config HINIC3
+	tristate "Huawei 3rd generation network adapters (HINIC3) support"
+	# Fields of HW and management structures are little endian and are
+	# currently not converted
+	depends on !CPU_BIG_ENDIAN
+	depends on X86 || ARM64 || COMPILE_TEST
+	depends on PCI_MSI && 64BIT
+	select AUXILIARY_BUS
+	help
+	  This driver supports HiNIC 3rd gen Network Adapter (HINIC3).
+	  The driver is supported on X86_64 and ARM64 little endian.
+
+	  To compile this driver as a module, choose M here.
+	  The module will be called hinic3.
diff --git a/drivers/net/ethernet/huawei/hinic3/Makefile b/drivers/net/ethernet/huawei/hinic3/Makefile
new file mode 100644
index 0000000000000..509dfbfb0e96e
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/Makefile
@@ -0,0 +1,21 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+obj-$(CONFIG_HINIC3) += hinic3.o
+
+hinic3-objs := hinic3_common.o \
+	       hinic3_hw_cfg.o \
+	       hinic3_hw_comm.o \
+	       hinic3_hwdev.o \
+	       hinic3_hwif.o \
+	       hinic3_irq.o \
+	       hinic3_lld.o \
+	       hinic3_main.o \
+	       hinic3_mbox.o \
+	       hinic3_netdev_ops.o \
+	       hinic3_nic_cfg.o \
+	       hinic3_nic_io.o \
+	       hinic3_queue_common.o \
+	       hinic3_rx.o \
+	       hinic3_tx.o \
+	       hinic3_wq.o
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
new file mode 100644
index 0000000000000..0aa42068728cd
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.c
@@ -0,0 +1,53 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align)
+{
+	dma_addr_t paddr, align_paddr;
+	void *vaddr, *align_vaddr;
+	u32 real_size = size;
+
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	if (align_paddr == paddr) {
+		align_vaddr = vaddr;
+		goto out;
+	}
+
+	dma_free_coherent(dev, real_size, vaddr, paddr);
+
+	/* realloc memory for align */
+	real_size = size + align;
+	vaddr = dma_alloc_coherent(dev, real_size, &paddr, flag);
+	if (!vaddr)
+		return -ENOMEM;
+
+	align_paddr = ALIGN(paddr, align);
+	align_vaddr = vaddr + (align_paddr - paddr);
+
+out:
+	mem_align->real_size = real_size;
+	mem_align->ori_vaddr = vaddr;
+	mem_align->ori_paddr = paddr;
+	mem_align->align_vaddr = align_vaddr;
+	mem_align->align_paddr = align_paddr;
+
+	return 0;
+}
+
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align)
+{
+	dma_free_coherent(dev, mem_align->real_size,
+			  mem_align->ori_vaddr, mem_align->ori_paddr);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
new file mode 100644
index 0000000000000..bb795dace04c2
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_common.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_COMMON_H_
+#define _HINIC3_COMMON_H_
+
+#include <linux/device.h>
+
+#define HINIC3_MIN_PAGE_SIZE  0x1000
+
+struct hinic3_dma_addr_align {
+	u32        real_size;
+
+	void       *ori_vaddr;
+	dma_addr_t ori_paddr;
+
+	void       *align_vaddr;
+	dma_addr_t align_paddr;
+};
+
+int hinic3_dma_zalloc_coherent_align(struct device *dev, u32 size, u32 align,
+				     gfp_t flag,
+				     struct hinic3_dma_addr_align *mem_align);
+void hinic3_dma_free_coherent_align(struct device *dev,
+				    struct hinic3_dma_addr_align *mem_align);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
new file mode 100644
index 0000000000000..221545c264049
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.supp_svcs_bitmap & BIT(HINIC3_SERVICE_T_NIC);
+}
+
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.nic_svc_cap.max_sqs;
+}
+
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->cfg_mgmt->cap.port_id;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
new file mode 100644
index 0000000000000..e017b1ae9f054
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_cfg.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_CFG_H_
+#define _HINIC3_HW_CFG_H_
+
+#include <linux/mutex.h>
+#include <linux/pci.h>
+
+struct hinic3_hwdev;
+
+struct hinic3_irq {
+	u32  irq_id;
+	u16  msix_entry_idx;
+	bool allocated;
+};
+
+struct hinic3_irq_info {
+	struct hinic3_irq *irq;
+	u16               num_irq;
+	/* device max irq number */
+	u16               num_irq_hw;
+	/* protect irq alloc and free */
+	struct mutex      irq_mutex;
+};
+
+struct hinic3_nic_service_cap {
+	u16 max_sqs;
+};
+
+/* Device capabilities */
+struct hinic3_dev_cap {
+	/* Bitmasks of services supported by device */
+	u16                           supp_svcs_bitmap;
+	/* Physical port */
+	u8                            port_id;
+	struct hinic3_nic_service_cap nic_svc_cap;
+};
+
+struct hinic3_cfg_mgmt_info {
+	struct hinic3_irq_info irq_info;
+	struct hinic3_dev_cap  cap;
+};
+
+int hinic3_alloc_irqs(struct hinic3_hwdev *hwdev, u16 num,
+		      struct msix_entry *alloc_arr, u16 *act_num);
+void hinic3_free_irq(struct hinic3_hwdev *hwdev, u32 irq_id);
+
+bool hinic3_support_nic(struct hinic3_hwdev *hwdev);
+u16 hinic3_func_max_qnum(struct hinic3_hwdev *hwdev);
+u8 hinic3_physical_port_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
new file mode 100644
index 0000000000000..434696ce7dc23
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag)
+{
+	struct comm_cmd_func_reset func_reset = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	func_reset.func_id = func_id;
+	func_reset.reset_flag = reset_flag;
+
+	mgmt_msg_params_init_default(&msg_params, &func_reset,
+				     sizeof(func_reset));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_COMM,
+				       COMM_CMD_FUNC_RESET, &msg_params);
+	if (err || func_reset.head.status) {
+		dev_err(hwdev->dev, "Failed to reset func resources, reset_flag 0x%llx, err: %d, status: 0x%x\n",
+			reset_flag, err, func_reset.head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
new file mode 100644
index 0000000000000..c33a1c77da9ce
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_comm.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_COMM_H_
+#define _HINIC3_HW_COMM_H_
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_hwdev;
+
+int hinic3_func_reset(struct hinic3_hwdev *hwdev, u16 func_id, u64 reset_flag);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
new file mode 100644
index 0000000000000..3edf2820fd3ab
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hw_intf.h
@@ -0,0 +1,113 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HW_INTF_H_
+#define _HINIC3_HW_INTF_H_
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+#define MGMT_MSG_CMD_OP_SET   1
+#define MGMT_MSG_CMD_OP_GET   0
+
+#define MGMT_STATUS_PF_SET_VF_ALREADY  0x4
+#define MGMT_STATUS_EXIST              0x6
+#define MGMT_STATUS_CMD_UNSUPPORTED    0xFF
+
+#define MGMT_MSG_POLLING_TIMEOUT 0
+
+struct mgmt_msg_head {
+	u8 status;
+	u8 version;
+	u8 rsvd0[6];
+};
+
+struct mgmt_msg_params {
+	const void  *buf_in;
+	u32         in_size;
+	void        *buf_out;
+	u32         expected_out_size;
+	u32         timeout_ms;
+};
+
+/* CMDQ MODULE_TYPE */
+enum mgmt_mod_type {
+	/* HW communication module */
+	MGMT_MOD_COMM   = 0,
+	/* L2NIC module */
+	MGMT_MOD_L2NIC  = 1,
+	/* Configuration module */
+	MGMT_MOD_CFGM   = 7,
+	MGMT_MOD_HILINK = 14,
+};
+
+static inline void mgmt_msg_params_init_default(struct mgmt_msg_params *msg_params,
+						void *inout_buff, u32 buff_size)
+{
+	msg_params->buf_in = inout_buff;
+	msg_params->buf_out = inout_buff;
+	msg_params->in_size = buff_size;
+	msg_params->expected_out_size = buff_size;
+	msg_params->timeout_ms = 0;
+}
+
+/* COMM Commands between Driver to fw */
+enum comm_cmd {
+	/* Commands for clearing FLR and resources */
+	COMM_CMD_FUNC_RESET              = 0,
+	COMM_CMD_FEATURE_NEGO            = 1,
+	COMM_CMD_FLUSH_DOORBELL          = 2,
+	COMM_CMD_START_FLUSH             = 3,
+	COMM_CMD_GET_GLOBAL_ATTR         = 5,
+	COMM_CMD_SET_FUNC_SVC_USED_STATE = 7,
+
+	/* Driver Configuration Commands */
+	COMM_CMD_SET_CMDQ_CTXT           = 20,
+	COMM_CMD_SET_VAT                 = 21,
+	COMM_CMD_CFG_PAGESIZE            = 22,
+	COMM_CMD_CFG_MSIX_CTRL_REG       = 23,
+	COMM_CMD_SET_CEQ_CTRL_REG        = 24,
+	COMM_CMD_SET_DMA_ATTR            = 25,
+};
+
+enum comm_func_reset_bits {
+	COMM_FUNC_RESET_BIT_FLUSH        = BIT(0),
+	COMM_FUNC_RESET_BIT_MQM          = BIT(1),
+	COMM_FUNC_RESET_BIT_SMF          = BIT(2),
+	COMM_FUNC_RESET_BIT_PF_BW_CFG    = BIT(3),
+
+	COMM_FUNC_RESET_BIT_COMM         = BIT(10),
+	/* clear mbox and aeq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_MGMT_CH = BIT(11),
+	/* clear cmdq and ceq, The COMM_FUNC_RESET_BIT_COMM bit must be set */
+	COMM_FUNC_RESET_BIT_COMM_CMD_CH  = BIT(12),
+	COMM_FUNC_RESET_BIT_NIC          = BIT(13),
+};
+
+struct comm_cmd_func_reset {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u16                  rsvd1[3];
+	u64                  reset_flag;
+};
+
+#define COMM_MAX_FEATURE_QWORD  4
+struct comm_cmd_feature_nego {
+	struct mgmt_msg_head head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[COMM_MAX_FEATURE_QWORD];
+};
+
+/* Services supported by HW. HW uses these values when delivering events.
+ * HW supports multiple services that are not yet supported by driver
+ * (e.g. RoCE).
+ */
+enum hinic3_service_type {
+	HINIC3_SERVICE_T_NIC = 0,
+	/* MAX is only used by SW for array sizes. */
+	HINIC3_SERVICE_T_MAX = 1,
+};
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
new file mode 100644
index 0000000000000..6e8788a649258
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.c
@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_mgmt.h"
+
+int hinic3_init_hwdev(struct pci_dev *pdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
new file mode 100644
index 0000000000000..718398f1ad7c7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwdev.h
@@ -0,0 +1,81 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWDEV_H_
+#define _HINIC3_HWDEV_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/pci.h>
+
+#include "hinic3_hw_intf.h"
+
+struct hinic3_cmdqs;
+struct hinic3_hwif;
+
+enum hinic3_event_service_type {
+	HINIC3_EVENT_SRV_COMM = 0,
+	HINIC3_EVENT_SRV_NIC  = 1
+};
+
+#define HINIC3_SRV_EVENT_TYPE(svc, type)    (((svc) << 16) | (type))
+
+/* driver-specific data of pci_dev */
+struct hinic3_pcidev {
+	struct pci_dev       *pdev;
+	struct hinic3_hwdev  *hwdev;
+	/* Auxiliary devices */
+	struct hinic3_adev   *hadev[HINIC3_SERVICE_T_MAX];
+
+	void __iomem         *cfg_reg_base;
+	void __iomem         *intr_reg_base;
+	void __iomem         *db_base;
+	u64                  db_dwqe_len;
+	u64                  db_base_phy;
+
+	/* lock for attach/detach uld */
+	struct mutex         pdev_mutex;
+	unsigned long        state;
+};
+
+struct hinic3_hwdev {
+	struct hinic3_pcidev        *adapter;
+	struct pci_dev              *pdev;
+	struct device               *dev;
+	int                         dev_id;
+	struct hinic3_hwif          *hwif;
+	struct hinic3_cfg_mgmt_info *cfg_mgmt;
+	struct hinic3_aeqs          *aeqs;
+	struct hinic3_ceqs          *ceqs;
+	struct hinic3_mbox          *mbox;
+	struct hinic3_cmdqs         *cmdqs;
+	struct workqueue_struct     *workq;
+	/* protect channel init and deinit */
+	spinlock_t                  channel_lock;
+	u64                         features[COMM_MAX_FEATURE_QWORD];
+	u32                         wq_page_size;
+	u8                          max_cmdq;
+	ulong                       func_state;
+};
+
+struct hinic3_event_info {
+	/* enum hinic3_event_service_type */
+	u16 service;
+	u16 type;
+	u8  event_data[104];
+};
+
+struct hinic3_adev {
+	struct auxiliary_device  adev;
+	struct hinic3_hwdev      *hwdev;
+	enum hinic3_service_type svc_type;
+
+	void (*event)(struct auxiliary_device *adev,
+		      struct hinic3_event_info *event);
+};
+
+int hinic3_init_hwdev(struct pci_dev *pdev);
+void hinic3_free_hwdev(struct hinic3_hwdev *hwdev);
+
+void hinic3_set_api_stop(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
new file mode 100644
index 0000000000000..0865453bf0e7c
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/bitfield.h>
+#include <linux/device.h>
+#include <linux/io.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev)
+{
+	return hwdev->hwif->attr.func_global_idx;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
new file mode 100644
index 0000000000000..513c9680e6b61
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_hwif.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_HWIF_H_
+#define _HINIC3_HWIF_H_
+
+#include <linux/build_bug.h>
+#include <linux/spinlock_types.h>
+
+struct hinic3_hwdev;
+
+enum hinic3_func_type {
+	HINIC3_FUNC_TYPE_VF = 1,
+};
+
+struct hinic3_db_area {
+	unsigned long *db_bitmap_array;
+	u32           db_max_areas;
+	/* protect doorbell area alloc and free */
+	spinlock_t    idx_lock;
+};
+
+struct hinic3_func_attr {
+	enum hinic3_func_type func_type;
+	u16                   func_global_idx;
+	u16                   global_vf_id_of_pf;
+	u16                   num_irqs;
+	u16                   num_sq;
+	u8                    port_to_port_idx;
+	u8                    pci_intf_idx;
+	u8                    ppf_idx;
+	u8                    num_aeqs;
+	u8                    num_ceqs;
+	u8                    msix_flex_en;
+};
+
+static_assert(sizeof(struct hinic3_func_attr) == 20);
+
+struct hinic3_hwif {
+	u8 __iomem              *cfg_regs_base;
+	u64                     db_base_phy;
+	u64                     db_dwqe_len;
+	u8 __iomem              *db_base;
+	struct hinic3_db_area   db_area;
+	struct hinic3_func_attr attr;
+};
+
+enum hinic3_msix_state {
+	HINIC3_MSIX_ENABLE,
+	HINIC3_MSIX_DISABLE,
+};
+
+void hinic3_set_msix_state(struct hinic3_hwdev *hwdev, u16 msix_idx,
+			   enum hinic3_msix_state flag);
+
+u16 hinic3_global_func_id(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
new file mode 100644
index 0000000000000..dcd971f31140b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_irq.c
@@ -0,0 +1,47 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_poll(struct napi_struct *napi, int budget)
+{
+	struct hinic3_irq_cfg *irq_cfg =
+		container_of(napi, struct hinic3_irq_cfg, napi);
+	struct hinic3_nic_dev *nic_dev;
+	int tx_pkts, rx_pkts;
+
+	nic_dev = netdev_priv(irq_cfg->netdev);
+	rx_pkts = hinic3_rx_poll(irq_cfg->rxq, budget);
+
+	tx_pkts = hinic3_tx_poll(irq_cfg->txq, budget);
+	if (tx_pkts >= budget || rx_pkts >= budget)
+		return budget;
+
+	napi_complete(napi);
+
+	hinic3_set_msix_state(nic_dev->hwdev, irq_cfg->msix_entry_idx,
+			      HINIC3_MSIX_ENABLE);
+
+	return max(tx_pkts, rx_pkts);
+}
+
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(irq_cfg->netdev);
+
+	netif_napi_add(nic_dev->netdev, &irq_cfg->napi, hinic3_poll);
+	napi_enable(&irq_cfg->napi);
+}
+
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg)
+{
+	napi_disable(&irq_cfg->napi);
+	netif_napi_del(&irq_cfg->napi);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
new file mode 100644
index 0000000000000..bd653898ceb0b
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.c
@@ -0,0 +1,416 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_lld.h"
+#include "hinic3_mgmt.h"
+
+#define HINIC3_VF_PCI_CFG_REG_BAR  0
+#define HINIC3_PCI_INTR_REG_BAR    2
+#define HINIC3_PCI_DB_BAR          4
+
+#define HINIC3_EVENT_POLL_SLEEP_US   1000
+#define HINIC3_EVENT_POLL_TIMEOUT_US 10000000
+
+static struct hinic3_adev_device {
+	const char *name;
+} hinic3_adev_devices[HINIC3_SERVICE_T_MAX] = {
+	[HINIC3_SERVICE_T_NIC] = {
+		.name = "nic",
+	},
+};
+
+static bool hinic3_adev_svc_supported(struct hinic3_hwdev *hwdev,
+				      enum hinic3_service_type svc_type)
+{
+	switch (svc_type) {
+	case HINIC3_SERVICE_T_NIC:
+		return hinic3_support_nic(hwdev);
+	default:
+		break;
+	}
+
+	return false;
+}
+
+static void hinic3_comm_adev_release(struct device *dev)
+{
+	struct hinic3_adev *hadev = container_of(dev, struct hinic3_adev, adev.dev);
+
+	kfree(hadev);
+}
+
+static struct hinic3_adev *hinic3_add_one_adev(struct hinic3_hwdev *hwdev,
+					       enum hinic3_service_type svc_type)
+{
+	struct hinic3_adev *hadev;
+	const char *svc_name;
+	int ret;
+
+	hadev = kzalloc(sizeof(*hadev), GFP_KERNEL);
+	if (!hadev)
+		return NULL;
+
+	svc_name = hinic3_adev_devices[svc_type].name;
+	hadev->adev.name = svc_name;
+	hadev->adev.id = hwdev->dev_id;
+	hadev->adev.dev.parent = hwdev->dev;
+	hadev->adev.dev.release = hinic3_comm_adev_release;
+	hadev->svc_type = svc_type;
+	hadev->hwdev = hwdev;
+
+	ret = auxiliary_device_init(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed init adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		kfree(hadev);
+		return NULL;
+	}
+
+	ret = auxiliary_device_add(&hadev->adev);
+	if (ret) {
+		dev_err(hwdev->dev, "failed to add adev %s %u\n",
+			svc_name, hwdev->dev_id);
+		auxiliary_device_uninit(&hadev->adev);
+		return NULL;
+	}
+
+	return hadev;
+}
+
+static void hinic3_del_one_adev(struct hinic3_hwdev *hwdev,
+				enum hinic3_service_type svc_type)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	struct hinic3_adev *hadev;
+	int timeout;
+	bool state;
+
+	timeout = read_poll_timeout(test_and_set_bit, state, !state,
+				    HINIC3_EVENT_POLL_SLEEP_US,
+				    HINIC3_EVENT_POLL_TIMEOUT_US,
+				    false, svc_type, &pci_adapter->state);
+
+	hadev = pci_adapter->hadev[svc_type];
+	auxiliary_device_delete(&hadev->adev);
+	auxiliary_device_uninit(&hadev->adev);
+	pci_adapter->hadev[svc_type] = NULL;
+	if (!timeout)
+		clear_bit(svc_type, &pci_adapter->state);
+}
+
+static int hinic3_attach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	enum hinic3_service_type svc_type;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+
+	for (svc_type = 0; svc_type < HINIC3_SERVICE_T_MAX; svc_type++) {
+		if (!hinic3_adev_svc_supported(hwdev, svc_type))
+			continue;
+
+		pci_adapter->hadev[svc_type] = hinic3_add_one_adev(hwdev, svc_type);
+		if (!pci_adapter->hadev[svc_type])
+			goto err_add_one_adev;
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return 0;
+
+err_add_one_adev:
+	while (svc_type > 0) {
+		svc_type--;
+		if (pci_adapter->hadev[svc_type]) {
+			hinic3_del_one_adev(hwdev, svc_type);
+			pci_adapter->hadev[svc_type] = NULL;
+		}
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+	return -ENOMEM;
+}
+
+static void hinic3_detach_aux_devices(struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_pcidev *pci_adapter = hwdev->adapter;
+	int i;
+
+	mutex_lock(&pci_adapter->pdev_mutex);
+	for (i = 0; i < ARRAY_SIZE(hinic3_adev_devices); i++) {
+		if (pci_adapter->hadev[i])
+			hinic3_del_one_adev(hwdev, i);
+	}
+	mutex_unlock(&pci_adapter->pdev_mutex);
+}
+
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	return hadev->hwdev;
+}
+
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event))
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = event_handler;
+}
+
+void hinic3_adev_event_unregister(struct auxiliary_device *adev)
+{
+	struct hinic3_adev *hadev;
+
+	hadev = container_of(adev, struct hinic3_adev, adev);
+	hadev->event = NULL;
+}
+
+static int hinic3_mapping_bar(struct pci_dev *pdev,
+			      struct hinic3_pcidev *pci_adapter)
+{
+	pci_adapter->cfg_reg_base = pci_ioremap_bar(pdev,
+						    HINIC3_VF_PCI_CFG_REG_BAR);
+	if (!pci_adapter->cfg_reg_base) {
+		dev_err(&pdev->dev, "Failed to map configuration regs\n");
+		return -ENOMEM;
+	}
+
+	pci_adapter->intr_reg_base = pci_ioremap_bar(pdev,
+						     HINIC3_PCI_INTR_REG_BAR);
+	if (!pci_adapter->intr_reg_base) {
+		dev_err(&pdev->dev, "Failed to map interrupt regs\n");
+		goto err_undo_reg_bar;
+	}
+
+	pci_adapter->db_base_phy = pci_resource_start(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_dwqe_len = pci_resource_len(pdev, HINIC3_PCI_DB_BAR);
+	pci_adapter->db_base = pci_ioremap_bar(pdev, HINIC3_PCI_DB_BAR);
+	if (!pci_adapter->db_base) {
+		dev_err(&pdev->dev, "Failed to map doorbell regs\n");
+		goto err_undo_intr_bar;
+	}
+
+	return 0;
+
+err_undo_intr_bar:
+	iounmap(pci_adapter->intr_reg_base);
+
+err_undo_reg_bar:
+	iounmap(pci_adapter->cfg_reg_base);
+
+	return -ENOMEM;
+}
+
+static void hinic3_unmapping_bar(struct hinic3_pcidev *pci_adapter)
+{
+	iounmap(pci_adapter->db_base);
+	iounmap(pci_adapter->intr_reg_base);
+	iounmap(pci_adapter->cfg_reg_base);
+}
+
+static int hinic3_pci_init(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	pci_adapter = kzalloc(sizeof(*pci_adapter), GFP_KERNEL);
+	if (!pci_adapter)
+		return -ENOMEM;
+
+	pci_adapter->pdev = pdev;
+	mutex_init(&pci_adapter->pdev_mutex);
+
+	pci_set_drvdata(pdev, pci_adapter);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to enable PCI device\n");
+		goto err_pci_enable;
+	}
+
+	err = pci_request_regions(pdev, HINIC3_NIC_DRV_NAME);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to request regions\n");
+		goto err_pci_regions;
+	}
+
+	pci_set_master(pdev);
+
+	err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(64));
+	if (err) {
+		dev_warn(&pdev->dev, "Couldn't set 64-bit DMA mask\n");
+		/* try 32 bit DMA mask if 64 bit fails */
+		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
+		if (err) {
+			dev_err(&pdev->dev, "Failed to set DMA mask\n");
+			goto err_dma_mask;
+		}
+	}
+
+	return 0;
+
+err_dma_mask:
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+
+err_pci_regions:
+	pci_disable_device(pdev);
+
+err_pci_enable:
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+
+	return err;
+}
+
+static void hinic3_pci_deinit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	pci_set_drvdata(pdev, NULL);
+	mutex_destroy(&pci_adapter->pdev_mutex);
+	kfree(pci_adapter);
+}
+
+static int hinic3_func_init(struct pci_dev *pdev, struct hinic3_pcidev *pci_adapter)
+{
+	int err;
+
+	err = hinic3_init_hwdev(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to initialize hardware device\n");
+		return -EFAULT;
+	}
+
+	err = hinic3_attach_aux_devices(pci_adapter->hwdev);
+	if (err)
+		goto err_attatch_aux_devices;
+
+	return 0;
+
+err_attatch_aux_devices:
+	hinic3_free_hwdev(pci_adapter->hwdev);
+
+	return err;
+}
+
+static void hinic3_func_deinit(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_detach_aux_devices(pci_adapter->hwdev);
+	hinic3_free_hwdev(pci_adapter->hwdev);
+}
+
+static int hinic3_probe_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+	int err;
+
+	err = hinic3_mapping_bar(pdev, pci_adapter);
+	if (err) {
+		dev_err(&pdev->dev, "Failed to map bar\n");
+		goto err_map_bar;
+	}
+
+	err = hinic3_func_init(pdev, pci_adapter);
+	if (err)
+		goto err_func_init;
+
+	return 0;
+
+err_func_init:
+	hinic3_unmapping_bar(pci_adapter);
+
+err_map_bar:
+	dev_err(&pdev->dev, "PCIe device probe function failed\n");
+	return err;
+}
+
+static void hinic3_remove_func(struct hinic3_pcidev *pci_adapter)
+{
+	struct pci_dev *pdev = pci_adapter->pdev;
+
+	hinic3_func_deinit(pdev);
+	hinic3_unmapping_bar(pci_adapter);
+}
+
+static int hinic3_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct hinic3_pcidev *pci_adapter;
+	int err;
+
+	err = hinic3_pci_init(pdev);
+	if (err)
+		goto out;
+
+	pci_adapter = pci_get_drvdata(pdev);
+	err = hinic3_probe_func(pci_adapter);
+	if (err)
+		goto err_hinic3_probe_func;
+
+	return 0;
+
+err_hinic3_probe_func:
+	hinic3_pci_deinit(pdev);
+
+out:
+	dev_err(&pdev->dev, "PCIe device probe failed\n");
+	return err;
+}
+
+static void hinic3_remove(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	hinic3_remove_func(pci_adapter);
+	hinic3_pci_deinit(pdev);
+}
+
+static const struct pci_device_id hinic3_pci_table[] = {
+	/* Completed by later submission due to LoC limit. */
+	{0, 0}
+
+};
+
+MODULE_DEVICE_TABLE(pci, hinic3_pci_table);
+
+static void hinic3_shutdown(struct pci_dev *pdev)
+{
+	struct hinic3_pcidev *pci_adapter = pci_get_drvdata(pdev);
+
+	pci_disable_device(pdev);
+
+	if (pci_adapter)
+		hinic3_set_api_stop(pci_adapter->hwdev);
+}
+
+static struct pci_driver hinic3_driver = {
+	.name            = HINIC3_NIC_DRV_NAME,
+	.id_table        = hinic3_pci_table,
+	.probe           = hinic3_probe,
+	.remove          = hinic3_remove,
+	.shutdown        = hinic3_shutdown,
+	.sriov_configure = pci_sriov_configure_simple
+};
+
+int hinic3_lld_init(void)
+{
+	return pci_register_driver(&hinic3_driver);
+}
+
+void hinic3_lld_exit(void)
+{
+	pci_unregister_driver(&hinic3_driver);
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
new file mode 100644
index 0000000000000..322b448034763
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_lld.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_LLD_H_
+#define _HINIC3_LLD_H_
+
+#include <linux/auxiliary_bus.h>
+
+struct hinic3_event_info;
+
+#define HINIC3_NIC_DRV_NAME "hinic3"
+
+int hinic3_lld_init(void);
+void hinic3_lld_exit(void);
+void hinic3_adev_event_register(struct auxiliary_device *adev,
+				void (*event_handler)(struct auxiliary_device *adev,
+						      struct hinic3_event_info *event));
+void hinic3_adev_event_unregister(struct auxiliary_device *adev);
+struct hinic3_hwdev *hinic3_adev_get_hwdev(struct auxiliary_device *adev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_main.c b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
new file mode 100644
index 0000000000000..b10def13d78c5
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_main.c
@@ -0,0 +1,357 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hw_comm.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_lld.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+#define HINIC3_NIC_DRV_DESC  "Intelligent Network Interface Card Driver"
+
+#define HINIC3_RX_BUFF_LEN           2048
+#define HINIC3_RX_BUFF_NUM_PER_PAGE  2
+#define HINIC3_LRO_REPLENISH_THLD    256
+#define HINIC3_NIC_DEV_WQ_NAME       "hinic3_nic_dev_wq"
+
+#define HINIC3_SQ_DEPTH              1024
+#define HINIC3_RQ_DEPTH              1024
+
+static int hinic3_alloc_txrxqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_alloc_txqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc txqs\n");
+		return err;
+	}
+
+	err = hinic3_alloc_rxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc rxqs\n");
+		goto err_alloc_rxqs;
+	}
+
+	return 0;
+
+err_alloc_rxqs:
+	hinic3_free_txqs(netdev);
+
+	return err;
+}
+
+static void hinic3_free_txrxqs(struct net_device *netdev)
+{
+	hinic3_free_rxqs(netdev);
+	hinic3_free_txqs(netdev);
+}
+
+static int hinic3_init_nic_dev(struct net_device *netdev,
+			       struct hinic3_hwdev *hwdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = hwdev->pdev;
+	u32 page_num;
+
+	nic_dev->netdev = netdev;
+	SET_NETDEV_DEV(netdev, &pdev->dev);
+	nic_dev->hwdev = hwdev;
+	nic_dev->pdev = pdev;
+
+	nic_dev->rx_buff_len = HINIC3_RX_BUFF_LEN;
+	nic_dev->dma_rx_buff_size = HINIC3_RX_BUFF_NUM_PER_PAGE * nic_dev->rx_buff_len;
+	page_num = nic_dev->dma_rx_buff_size / HINIC3_MIN_PAGE_SIZE;
+	nic_dev->page_order = page_num > 0 ? ilog2(page_num) : 0;
+	nic_dev->lro_replenish_thld = HINIC3_LRO_REPLENISH_THLD;
+	nic_dev->nic_svc_cap = hwdev->cfg_mgmt->cap.nic_svc_cap;
+
+	return 0;
+}
+
+static int hinic3_sw_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	nic_dev->q_params.sq_depth = HINIC3_SQ_DEPTH;
+	nic_dev->q_params.rq_depth = HINIC3_RQ_DEPTH;
+
+	/* VF driver always uses random MAC address. During VM migration to a
+	 * new device, the new device should learn the VMs old MAC rather than
+	 * provide its own MAC. The product design assumes that every VF is
+	 * suspectable to migration so the device avoids offering MAC address
+	 * to VFs.
+	 */
+	eth_hw_addr_random(netdev);
+	err = hinic3_set_mac(hwdev, netdev->dev_addr, 0,
+			     hinic3_global_func_id(hwdev));
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set default MAC\n");
+		return err;
+	}
+
+	err = hinic3_alloc_txrxqs(netdev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to alloc qps\n");
+		goto err_alloc_qps;
+	}
+
+	return 0;
+
+err_alloc_qps:
+	hinic3_del_mac(hwdev, netdev->dev_addr, 0, hinic3_global_func_id(hwdev));
+
+	return err;
+}
+
+static void hinic3_sw_deinit(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	hinic3_free_txrxqs(netdev);
+	hinic3_del_mac(nic_dev->hwdev, netdev->dev_addr, 0,
+		       hinic3_global_func_id(nic_dev->hwdev));
+}
+
+static void hinic3_assign_netdev_ops(struct net_device *netdev)
+{
+	hinic3_set_netdev_ops(netdev);
+}
+
+static void netdev_feature_init(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	netdev_features_t cso_fts = 0;
+	netdev_features_t tso_fts = 0;
+	netdev_features_t dft_fts;
+
+	dft_fts = NETIF_F_SG | NETIF_F_HIGHDMA;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_CSUM))
+		cso_fts |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_SCTP_CRC))
+		cso_fts |= NETIF_F_SCTP_CRC;
+	if (hinic3_test_support(nic_dev, HINIC3_NIC_F_TSO))
+		tso_fts |= NETIF_F_TSO | NETIF_F_TSO6;
+
+	netdev->features |= dft_fts | cso_fts | tso_fts;
+}
+
+static int hinic3_set_default_hw_feature(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	int err;
+
+	err = hinic3_set_nic_feature_to_hw(nic_dev);
+	if (err) {
+		dev_err(hwdev->dev, "Failed to set nic features\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void hinic3_link_status_change(struct net_device *netdev, bool link_status_up)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	if (!HINIC3_CHANNEL_RES_VALID(nic_dev))
+		return;
+
+	if (link_status_up) {
+		if (netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = true;
+		netif_carrier_on(netdev);
+		netdev_dbg(netdev, "Link is up\n");
+	} else {
+		if (!netif_carrier_ok(netdev))
+			return;
+
+		nic_dev->link_status_up = false;
+		netif_carrier_off(netdev);
+		netdev_dbg(netdev, "Link is down\n");
+	}
+}
+
+static void hinic3_nic_event(struct auxiliary_device *adev,
+			     struct hinic3_event_info *event)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	netdev = nic_dev->netdev;
+
+	switch (HINIC3_SRV_EVENT_TYPE(event->service, event->type)) {
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC, HINIC3_NIC_EVENT_LINK_UP):
+		hinic3_link_status_change(netdev, true);
+		break;
+	case HINIC3_SRV_EVENT_TYPE(HINIC3_EVENT_SRV_NIC, HINIC3_NIC_EVENT_LINK_DOWN):
+		hinic3_link_status_change(netdev, false);
+		break;
+	default:
+		break;
+	}
+}
+
+static int hinic3_nic_probe(struct auxiliary_device *adev,
+			    const struct auxiliary_device_id *id)
+{
+	struct hinic3_hwdev *hwdev = hinic3_adev_get_hwdev(adev);
+	struct pci_dev *pdev = hwdev->pdev;
+	struct hinic3_nic_dev *nic_dev;
+	struct net_device *netdev;
+	u16 max_qps, glb_func_id;
+	int err;
+
+	if (!hinic3_support_nic(hwdev)) {
+		dev_dbg(&adev->dev, "HW doesn't support nic\n");
+		return 0;
+	}
+
+	hinic3_adev_event_register(adev, hinic3_nic_event);
+
+	glb_func_id = hinic3_global_func_id(hwdev);
+	err = hinic3_func_reset(hwdev, glb_func_id, COMM_FUNC_RESET_BIT_NIC);
+	if (err) {
+		dev_err(&adev->dev, "Failed to reset function\n");
+		goto err_undo_event_register;
+	}
+
+	max_qps = hinic3_func_max_qnum(hwdev);
+	netdev = alloc_etherdev_mq(sizeof(*nic_dev), max_qps);
+	if (!netdev) {
+		dev_err(&adev->dev, "Failed to allocate netdev\n");
+		err = -ENOMEM;
+		goto err_undo_event_register;
+	}
+
+	nic_dev = netdev_priv(netdev);
+	dev_set_drvdata(&adev->dev, nic_dev);
+	err = hinic3_init_nic_dev(netdev, hwdev);
+	if (err)
+		goto err_undo_netdev_alloc;
+
+	err = hinic3_init_nic_io(nic_dev);
+	if (err)
+		goto err_undo_netdev_alloc;
+
+	err = hinic3_sw_init(netdev);
+	if (err)
+		goto err_sw_init;
+
+	hinic3_assign_netdev_ops(netdev);
+
+	netdev_feature_init(netdev);
+	err = hinic3_set_default_hw_feature(netdev);
+	if (err)
+		goto err_set_features;
+
+	err = register_netdev(netdev);
+	if (err)
+		goto err_register_netdev;
+
+	netif_carrier_off(netdev);
+	return 0;
+
+err_register_netdev:
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+
+err_set_features:
+	hinic3_sw_deinit(netdev);
+
+err_sw_init:
+	hinic3_free_nic_io(nic_dev);
+
+err_undo_netdev_alloc:
+	free_netdev(netdev);
+
+err_undo_event_register:
+	hinic3_adev_event_unregister(adev);
+	dev_err(&pdev->dev, "NIC service probe failed\n");
+
+	return err;
+}
+
+static void hinic3_nic_remove(struct auxiliary_device *adev)
+{
+	struct hinic3_nic_dev *nic_dev = dev_get_drvdata(&adev->dev);
+	struct net_device *netdev;
+
+	if (!hinic3_support_nic(nic_dev->hwdev))
+		return;
+
+	netdev = nic_dev->netdev;
+	unregister_netdev(netdev);
+
+	hinic3_update_nic_feature(nic_dev, 0);
+	hinic3_set_nic_feature_to_hw(nic_dev);
+	hinic3_sw_deinit(netdev);
+
+	hinic3_free_nic_io(nic_dev);
+
+	free_netdev(netdev);
+}
+
+static const struct auxiliary_device_id hinic3_nic_id_table[] = {
+	{
+		.name = HINIC3_NIC_DRV_NAME ".nic",
+	},
+	{},
+};
+
+static struct auxiliary_driver hinic3_nic_driver = {
+	.probe    = hinic3_nic_probe,
+	.remove   = hinic3_nic_remove,
+	.suspend  = NULL,
+	.resume   = NULL,
+	.name     = "nic",
+	.id_table = hinic3_nic_id_table,
+};
+
+static __init int hinic3_nic_lld_init(void)
+{
+	int err;
+
+	pr_info("%s: %s\n", HINIC3_NIC_DRV_NAME, HINIC3_NIC_DRV_DESC);
+
+	err = hinic3_lld_init();
+	if (err)
+		return err;
+
+	err = auxiliary_driver_register(&hinic3_nic_driver);
+	if (err) {
+		hinic3_lld_exit();
+		return err;
+	}
+
+	return 0;
+}
+
+static __exit void hinic3_nic_lld_exit(void)
+{
+	auxiliary_driver_unregister(&hinic3_nic_driver);
+
+	hinic3_lld_exit();
+}
+
+module_init(hinic3_nic_lld_init);
+module_exit(hinic3_nic_lld_exit);
+
+MODULE_AUTHOR("Huawei Technologies CO., Ltd");
+MODULE_DESCRIPTION(HINIC3_NIC_DRV_DESC);
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
new file mode 100644
index 0000000000000..e74d1eb097301
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_common.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
new file mode 100644
index 0000000000000..d7a6c37b7eff7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mbox.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MBOX_H_
+#define _HINIC3_MBOX_H_
+
+#include <linux/bitfield.h>
+#include <linux/mutex.h>
+
+struct hinic3_hwdev;
+
+int hinic3_send_mbox_to_mgmt(struct hinic3_hwdev *hwdev, u8 mod, u16 cmd,
+			     const struct mgmt_msg_params *msg_params);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
new file mode 100644
index 0000000000000..4edabeb321122
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_H_
+#define _HINIC3_MGMT_H_
+
+#include <linux/types.h>
+
+struct hinic3_hwdev;
+
+void hinic3_flush_mgmt_workq(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
new file mode 100644
index 0000000000000..c4434efdc7f77
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_MGMT_INTERFACE_H_
+#define _HINIC3_MGMT_INTERFACE_H_
+
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/if_ether.h>
+
+#include "hinic3_hw_intf.h"
+
+struct l2nic_cmd_feature_nego {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u8                   opcode;
+	u8                   rsvd;
+	u64                  s_feature[4];
+};
+
+enum l2nic_func_tbl_cfg_bitmap {
+	L2NIC_FUNC_TBL_CFG_INIT        = 0,
+	L2NIC_FUNC_TBL_CFG_RX_BUF_SIZE = 1,
+	L2NIC_FUNC_TBL_CFG_MTU         = 2,
+};
+
+struct l2nic_func_tbl_cfg {
+	u16 rx_wqe_buf_size;
+	u16 mtu;
+	u32 rsvd[9];
+};
+
+struct l2nic_cmd_set_func_tbl {
+	struct mgmt_msg_head      msg_head;
+	u16                       func_id;
+	u16                       rsvd;
+	u32                       cfg_bitmap;
+	struct l2nic_func_tbl_cfg tbl_cfg;
+};
+
+struct l2nic_cmd_set_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_update_mac {
+	struct mgmt_msg_head msg_head;
+	u16                  func_id;
+	u16                  vlan_id;
+	u16                  rsvd1;
+	u8                   old_mac[ETH_ALEN];
+	u16                  rsvd2;
+	u8                   new_mac[ETH_ALEN];
+};
+
+struct l2nic_cmd_force_pkt_drop {
+	struct mgmt_msg_head msg_head;
+	u8                   port;
+	u8                   rsvd1[3];
+};
+
+/* Commands between NIC to fw */
+enum l2nic_cmd {
+	/* FUNC CFG */
+	L2NIC_CMD_SET_FUNC_TBL        = 5,
+	L2NIC_CMD_SET_VPORT_ENABLE    = 6,
+	L2NIC_CMD_SET_SQ_CI_ATTR      = 8,
+	L2NIC_CMD_CLEAR_QP_RESOURCE   = 11,
+	L2NIC_CMD_FEATURE_NEGO        = 15,
+	L2NIC_CMD_SET_MAC             = 21,
+	L2NIC_CMD_DEL_MAC             = 22,
+	L2NIC_CMD_UPDATE_MAC          = 23,
+	L2NIC_CMD_CFG_RSS             = 60,
+	L2NIC_CMD_CFG_RSS_HASH_KEY    = 63,
+	L2NIC_CMD_CFG_RSS_HASH_ENGINE = 64,
+	L2NIC_CMD_SET_RSS_CTX_TBL     = 65,
+	L2NIC_CMD_QOS_DCB_STATE       = 110,
+	L2NIC_CMD_FORCE_PKT_DROP      = 113,
+	L2NIC_CMD_MAX                 = 256,
+};
+
+enum hinic3_nic_feature_cap {
+	HINIC3_NIC_F_CSUM           = BIT(0),
+	HINIC3_NIC_F_SCTP_CRC       = BIT(1),
+	HINIC3_NIC_F_TSO            = BIT(2),
+	HINIC3_NIC_F_LRO            = BIT(3),
+	HINIC3_NIC_F_UFO            = BIT(4),
+	HINIC3_NIC_F_RSS            = BIT(5),
+	HINIC3_NIC_F_RX_VLAN_FILTER = BIT(6),
+	HINIC3_NIC_F_RX_VLAN_STRIP  = BIT(7),
+	HINIC3_NIC_F_TX_VLAN_INSERT = BIT(8),
+	HINIC3_NIC_F_VXLAN_OFFLOAD  = BIT(9),
+	HINIC3_NIC_F_FDIR           = BIT(11),
+	HINIC3_NIC_F_PROMISC        = BIT(12),
+	HINIC3_NIC_F_ALLMULTI       = BIT(13),
+	HINIC3_NIC_F_RATE_LIMIT     = BIT(16),
+};
+
+#define HINIC3_NIC_F_ALL_MASK           0x33bff
+#define HINIC3_NIC_DRV_DEFAULT_FEATURE  0x3f03f
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
new file mode 100644
index 0000000000000..4a3243bc92b15
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/netdevice.h>
+
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+#include "hinic3_tx.h"
+
+static int hinic3_open(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_close(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+static int hinic3_change_mtu(struct net_device *netdev, int new_mtu)
+{
+	int err;
+
+	err = hinic3_set_port_mtu(netdev, new_mtu);
+	if (err) {
+		netdev_err(netdev, "Failed to change port mtu to %d\n", new_mtu);
+		return err;
+	}
+
+	netdev_dbg(netdev, "Change mtu from %u to %d\n", netdev->mtu, new_mtu);
+	WRITE_ONCE(netdev->mtu, new_mtu);
+
+	return 0;
+}
+
+static int hinic3_set_mac_addr(struct net_device *netdev, void *addr)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct sockaddr *saddr = addr;
+	int err;
+
+	if (!is_valid_ether_addr(saddr->sa_data))
+		return -EADDRNOTAVAIL;
+
+	if (ether_addr_equal(netdev->dev_addr, saddr->sa_data))
+		return 0;
+
+	err = hinic3_update_mac(nic_dev->hwdev, netdev->dev_addr,
+				saddr->sa_data, 0,
+				hinic3_global_func_id(nic_dev->hwdev));
+
+	if (err)
+		return err;
+
+	eth_hw_addr_set(netdev, saddr->sa_data);
+
+	return 0;
+}
+
+static const struct net_device_ops hinic3_netdev_ops = {
+	.ndo_open             = hinic3_open,
+	.ndo_stop             = hinic3_close,
+	.ndo_change_mtu       = hinic3_change_mtu,
+	.ndo_set_mac_address  = hinic3_set_mac_addr,
+	.ndo_start_xmit       = hinic3_xmit_frame,
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev)
+{
+	netdev->netdev_ops = &hinic3_netdev_ops;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
new file mode 100644
index 0000000000000..45fd6d0a0d3e7
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c
@@ -0,0 +1,230 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_mbox.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+static int hinic3_feature_nego(struct hinic3_hwdev *hwdev, u8 opcode,
+			       u64 *s_feature, u16 size)
+{
+	struct l2nic_cmd_feature_nego feature_nego = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	feature_nego.func_id = hinic3_global_func_id(hwdev);
+	feature_nego.opcode = opcode;
+	if (opcode == MGMT_MSG_CMD_OP_SET)
+		memcpy(feature_nego.s_feature, s_feature, size * sizeof(u64));
+
+	mgmt_msg_params_init_default(&msg_params, &feature_nego,
+				     sizeof(feature_nego));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FEATURE_NEGO, &msg_params);
+	if (err || feature_nego.msg_head.status) {
+		dev_err(hwdev->dev, "Failed to negotiate nic feature, err:%d, status: 0x%x\n",
+			err, feature_nego.msg_head.status);
+		return -EIO;
+	}
+
+	if (opcode == MGMT_MSG_CMD_OP_GET)
+		memcpy(s_feature, feature_nego.s_feature, size * sizeof(u64));
+
+	return 0;
+}
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev)
+{
+	return hinic3_feature_nego(nic_dev->hwdev, MGMT_MSG_CMD_OP_SET,
+				   &nic_dev->nic_io->feature_cap, 1);
+}
+
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits)
+{
+	return (nic_dev->nic_io->feature_cap & feature_bits) == feature_bits;
+}
+
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap)
+{
+	nic_dev->nic_io->feature_cap = feature_cap;
+}
+
+static int hinic3_set_function_table(struct hinic3_hwdev *hwdev, u32 cfg_bitmap,
+				     const struct l2nic_func_tbl_cfg *cfg)
+{
+	struct l2nic_cmd_set_func_tbl cmd_func_tbl = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	cmd_func_tbl.func_id = hinic3_global_func_id(hwdev);
+	cmd_func_tbl.cfg_bitmap = cfg_bitmap;
+	cmd_func_tbl.tbl_cfg = *cfg;
+
+	mgmt_msg_params_init_default(&msg_params, &cmd_func_tbl,
+				     sizeof(cmd_func_tbl));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_FUNC_TBL, &msg_params);
+	if (err || cmd_func_tbl.msg_head.status) {
+		dev_err(hwdev->dev,
+			"Failed to set func table, bitmap: 0x%x, err: %d, status: 0x%x\n",
+			cfg_bitmap, err, cmd_func_tbl.msg_head.status);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct l2nic_func_tbl_cfg func_tbl_cfg = {};
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+
+	func_tbl_cfg.mtu = new_mtu;
+	return hinic3_set_function_table(hwdev, BIT(L2NIC_FUNC_TBL_CFG_MTU),
+					 &func_tbl_cfg);
+}
+
+static int hinic3_check_mac_info(struct hinic3_hwdev *hwdev, u8 status, u16 vlan_id)
+{
+	if ((status && status != MGMT_STATUS_EXIST) ||
+	    ((vlan_id & BIT(15)) && status == MGMT_STATUS_EXIST)) {
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_SET_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_PF_SET_VF_ALREADY) {
+		dev_warn(hwdev->dev, "PF has already set VF mac, Ignore set operation\n");
+		return 0;
+	}
+
+	if (mac_info.msg_head.status == MGMT_STATUS_EXIST) {
+		dev_warn(hwdev->dev, "MAC is repeated. Ignore update operation\n");
+		return 0;
+	}
+
+	return 0;
+}
+
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_set_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.mac, mac_addr);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_DEL_MAC, &msg_params);
+	if (err) {
+		dev_err(hwdev->dev,
+			"Failed to delete MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac, u8 *new_mac,
+		      u16 vlan_id, u16 func_id)
+{
+	struct l2nic_cmd_update_mac mac_info = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	if ((vlan_id & HINIC3_VLAN_ID_MASK) >= VLAN_N_VID) {
+		dev_err(hwdev->dev, "Invalid VLAN number: %d\n",
+			(vlan_id & HINIC3_VLAN_ID_MASK));
+		return -EINVAL;
+	}
+
+	mac_info.func_id = func_id;
+	mac_info.vlan_id = vlan_id;
+	ether_addr_copy(mac_info.old_mac, old_mac);
+	ether_addr_copy(mac_info.new_mac, new_mac);
+
+	mgmt_msg_params_init_default(&msg_params, &mac_info, sizeof(mac_info));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_UPDATE_MAC, &msg_params);
+	if (err || hinic3_check_mac_info(hwdev, mac_info.msg_head.status,
+					 mac_info.vlan_id)) {
+		dev_err(hwdev->dev,
+			"Failed to update MAC, err: %d, status: 0x%x\n",
+			err, mac_info.msg_head.status);
+		return -EIO;
+	}
+	return 0;
+}
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev)
+{
+	struct l2nic_cmd_force_pkt_drop pkt_drop = {};
+	struct mgmt_msg_params msg_params = {};
+	int err;
+
+	pkt_drop.port = hinic3_physical_port_id(hwdev);
+
+	mgmt_msg_params_init_default(&msg_params, &pkt_drop, sizeof(pkt_drop));
+
+	err = hinic3_send_mbox_to_mgmt(hwdev, MGMT_MOD_L2NIC,
+				       L2NIC_CMD_FORCE_PKT_DROP, &msg_params);
+	if ((pkt_drop.msg_head.status != MGMT_STATUS_CMD_UNSUPPORTED &&
+	     pkt_drop.msg_head.status) || err) {
+		dev_err(hwdev->dev,
+			"Failed to set force tx packets drop, err: %d, status: 0x%x\n",
+			err, pkt_drop.msg_head.status);
+		return -EFAULT;
+	}
+
+	return pkt_drop.msg_head.status;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
new file mode 100644
index 0000000000000..b7ae0f631cf43
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_CFG_H_
+#define _HINIC3_NIC_CFG_H_
+
+#include <linux/types.h>
+
+#include "hinic3_hw_intf.h"
+#include "hinic3_mgmt_interface.h"
+
+struct hinic3_hwdev;
+struct hinic3_nic_dev;
+
+#define HINIC3_MIN_MTU_SIZE          256
+#define HINIC3_MAX_JUMBO_FRAME_SIZE  9600
+
+#define HINIC3_VLAN_ID_MASK          0x7FFF
+
+enum hinic3_nic_event_type {
+	HINIC3_NIC_EVENT_LINK_DOWN = 0,
+	HINIC3_NIC_EVENT_LINK_UP   = 1,
+};
+
+int hinic3_set_nic_feature_to_hw(struct hinic3_nic_dev *nic_dev);
+bool hinic3_test_support(struct hinic3_nic_dev *nic_dev,
+			 enum hinic3_nic_feature_cap feature_bits);
+void hinic3_update_nic_feature(struct hinic3_nic_dev *nic_dev, u64 feature_cap);
+
+int hinic3_set_port_mtu(struct net_device *netdev, u16 new_mtu);
+
+int hinic3_set_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id, u16 func_id);
+int hinic3_del_mac(struct hinic3_hwdev *hwdev, const u8 *mac_addr, u16 vlan_id, u16 func_id);
+int hinic3_update_mac(struct hinic3_hwdev *hwdev, const u8 *old_mac, u8 *new_mac, u16 vlan_id,
+		      u16 func_id);
+
+int hinic3_force_drop_tx_pkt(struct hinic3_hwdev *hwdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
new file mode 100644
index 0000000000000..64a8fb874097d
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_DEV_H_
+#define _HINIC3_NIC_DEV_H_
+
+#include <linux/netdevice.h>
+
+#include "hinic3_hw_cfg.h"
+#include "hinic3_mgmt_interface.h"
+
+enum hinic3_flags {
+	HINIC3_INTF_UP,
+	HINIC3_RSS_ENABLE,
+	HINIC3_CHANGE_RES_INVALID,
+	HINIC3_RSS_DEFAULT_INDIR,
+};
+
+#define HINIC3_CHANNEL_RES_VALID(nic_dev) \
+	(test_bit(HINIC3_INTF_UP, &(nic_dev)->flags) && \
+	 !test_bit(HINIC3_CHANGE_RES_INVALID, &(nic_dev)->flags))
+
+enum hinic3_rss_hash_type {
+	HINIC3_RSS_HASH_ENGINE_TYPE_XOR  = 0,
+	HINIC3_RSS_HASH_ENGINE_TYPE_TOEP = 1,
+};
+
+struct hinic3_rss_type {
+	u8 tcp_ipv6_ext;
+	u8 ipv6_ext;
+	u8 tcp_ipv6;
+	u8 ipv6;
+	u8 tcp_ipv4;
+	u8 ipv4;
+	u8 udp_ipv6;
+	u8 udp_ipv4;
+};
+
+struct hinic3_irq_cfg {
+	struct net_device  *netdev;
+	u16                msix_entry_idx;
+	/* provided by OS */
+	u32                irq_id;
+	char               irq_name[IFNAMSIZ + 16];
+	struct napi_struct napi;
+	cpumask_t          affinity_mask;
+	struct hinic3_txq  *txq;
+	struct hinic3_rxq  *rxq;
+};
+
+struct hinic3_dyna_txrxq_params {
+	u16                        num_qps;
+	u32                        sq_depth;
+	u32                        rq_depth;
+
+	struct hinic3_dyna_txq_res *txqs_res;
+	struct hinic3_dyna_rxq_res *rxqs_res;
+	struct hinic3_irq_cfg      *irq_cfg;
+};
+
+struct hinic3_nic_dev {
+	struct pci_dev                  *pdev;
+	struct net_device               *netdev;
+	struct hinic3_hwdev             *hwdev;
+	struct hinic3_nic_io            *nic_io;
+
+	u16                             max_qps;
+	u32                             dma_rx_buff_size;
+	u16                             rx_buff_len;
+	u32                             page_order;
+	u32                             lro_replenish_thld;
+	unsigned long                   flags;
+	struct hinic3_nic_service_cap   nic_svc_cap;
+
+	struct hinic3_dyna_txrxq_params q_params;
+	struct hinic3_txq               *txqs;
+	struct hinic3_rxq               *rxqs;
+
+	u16                             num_qp_irq;
+	struct msix_entry               *qps_msix_entries;
+
+	bool                            link_status_up;
+};
+
+void hinic3_set_netdev_ops(struct net_device *netdev);
+
+/* Temporary prototypes. Functions become static in later submission. */
+void qp_add_napi(struct hinic3_irq_cfg *irq_cfg);
+void qp_del_napi(struct hinic3_irq_cfg *irq_cfg);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
new file mode 100644
index 0000000000000..34a1f5bd5ac19
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include "hinic3_hw_comm.h"
+#include "hinic3_hw_intf.h"
+#include "hinic3_hwdev.h"
+#include "hinic3_hwif.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
new file mode 100644
index 0000000000000..72c0969d73dad
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h
@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_NIC_IO_H_
+#define _HINIC3_NIC_IO_H_
+
+#include <linux/bitfield.h>
+
+#include "hinic3_wq.h"
+
+struct hinic3_nic_dev;
+
+#define HINIC3_SQ_WQEBB_SHIFT      4
+#define HINIC3_RQ_WQEBB_SHIFT      3
+#define HINIC3_SQ_WQEBB_SIZE       BIT(HINIC3_SQ_WQEBB_SHIFT)
+
+/* ******************** RQ_CTRL ******************** */
+enum hinic3_rq_wqe_type {
+	HINIC3_NORMAL_RQ_WQE = 1,
+};
+
+/* ******************** SQ_CTRL ******************** */
+#define HINIC3_TX_MSS_DEFAULT  0x3E00
+#define HINIC3_TX_MSS_MIN      0x50
+#define HINIC3_MAX_SQ_SGE      18
+
+struct hinic3_io_queue {
+	struct hinic3_wq  wq;
+	u8                owner;
+	u16               q_id;
+	u16               msix_entry_idx;
+	u8 __iomem        *db_addr;
+	u16               *cons_idx_addr;
+} ____cacheline_aligned;
+
+static inline u16 hinic3_get_sq_local_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->cons_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_local_pi(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return wq->prod_idx & wq->idx_mask;
+}
+
+static inline u16 hinic3_get_sq_hw_ci(const struct hinic3_io_queue *sq)
+{
+	const struct hinic3_wq *wq = &sq->wq;
+
+	return READ_ONCE(*sq->cons_idx_addr) & wq->idx_mask;
+}
+
+/* ******************** DB INFO ******************** */
+#define DB_INFO_QID_MASK    GENMASK(12, 0)
+#define DB_INFO_CFLAG_MASK  BIT(23)
+#define DB_INFO_COS_MASK    GENMASK(26, 24)
+#define DB_INFO_TYPE_MASK   GENMASK(31, 27)
+#define DB_INFO_SET(val, member)  \
+	FIELD_PREP(DB_INFO_##member##_MASK, val)
+
+#define DB_PI_LOW_MASK   0xFFU
+#define DB_PI_HIGH_MASK  0xFFU
+#define DB_PI_HI_SHIFT   8
+#define DB_PI_LOW(pi)    ((pi) & DB_PI_LOW_MASK)
+#define DB_PI_HIGH(pi)   (((pi) >> DB_PI_HI_SHIFT) & DB_PI_HIGH_MASK)
+#define DB_ADDR(q, pi)   ((u64 __iomem *)((q)->db_addr) + DB_PI_LOW(pi))
+#define DB_SRC_TYPE      1
+
+/* CFLAG_DATA_PATH */
+#define DB_CFLAG_DP_SQ   0
+#define DB_CFLAG_DP_RQ   1
+
+struct hinic3_nic_db {
+	u32 db_info;
+	u32 pi_hi;
+};
+
+static inline void hinic3_write_db(struct hinic3_io_queue *queue, int cos,
+				   u8 cflag, u16 pi)
+{
+	struct hinic3_nic_db db;
+
+	db.db_info = DB_INFO_SET(DB_SRC_TYPE, TYPE) | DB_INFO_SET(cflag, CFLAG) |
+		     DB_INFO_SET(cos, COS) | DB_INFO_SET(queue->q_id, QID);
+	db.pi_hi = DB_PI_HIGH(pi);
+
+	writeq(*((u64 *)&db), DB_ADDR(queue, pi));
+}
+
+struct hinic3_nic_io {
+	struct hinic3_io_queue *sq;
+	struct hinic3_io_queue *rq;
+
+	u16                    num_qps;
+	u16                    max_qps;
+
+	/* Base address for consumer index of all tx queues. Each queue is
+	 * given a full cache line to hold its consumer index. HW updates
+	 * current consumer index as it consumes tx WQEs.
+	 */
+	void                   *ci_vaddr_base;
+	dma_addr_t             ci_dma_base;
+
+	u8 __iomem             *sqs_db_addr;
+	u8 __iomem             *rqs_db_addr;
+
+	u16                    rx_buff_len;
+	u64                    feature_cap;
+};
+
+int hinic3_init_nic_io(struct hinic3_nic_dev *nic_dev);
+void hinic3_free_nic_io(struct hinic3_nic_dev *nic_dev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
new file mode 100644
index 0000000000000..8535840d86de0
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/device.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_queue_common.h"
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size)
+{
+	u32 elem_per_page;
+
+	elem_per_page = min(page_size / elem_size, q_depth);
+
+	qpages->pages = NULL;
+	qpages->page_size = page_size;
+	qpages->num_pages = max(q_depth / elem_per_page, 1);
+	qpages->elem_size_shift = ilog2(elem_size);
+	qpages->elem_per_pg_shift = ilog2(elem_per_page);
+}
+
+static void __queue_pages_free(struct hinic3_hwdev *hwdev,
+			       struct hinic3_queue_pages *qpages, u32 pg_cnt)
+{
+	while (pg_cnt > 0) {
+		pg_cnt--;
+		hinic3_dma_free_coherent_align(hwdev->dev,
+					       qpages->pages + pg_cnt);
+	}
+	kfree(qpages->pages);
+	qpages->pages = NULL;
+}
+
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages)
+{
+	__queue_pages_free(hwdev, qpages, qpages->num_pages);
+}
+
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align)
+{
+	u32 pg_idx;
+	int err;
+
+	qpages->pages = kcalloc(qpages->num_pages, sizeof(qpages->pages[0]), GFP_KERNEL);
+	if (!qpages->pages)
+		return -ENOMEM;
+
+	if (align == 0)
+		align = qpages->page_size;
+
+	for (pg_idx = 0; pg_idx < qpages->num_pages; pg_idx++) {
+		err = hinic3_dma_zalloc_coherent_align(hwdev->dev,
+						       qpages->page_size,
+						       align,
+						       GFP_KERNEL,
+						       qpages->pages + pg_idx);
+		if (err) {
+			__queue_pages_free(hwdev, qpages, pg_idx);
+			return err;
+		}
+	}
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
new file mode 100644
index 0000000000000..799861cc0e9b8
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_queue_common.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_QUEUE_COMMON_H_
+#define _HINIC3_QUEUE_COMMON_H_
+
+#include <linux/types.h>
+
+#include "hinic3_common.h"
+
+struct hinic3_hwdev;
+
+struct hinic3_queue_pages {
+	/* Array of DMA-able pages that actually holds the queue entries. */
+	struct hinic3_dma_addr_align  *pages;
+	/* Page size in bytes. */
+	u32                           page_size;
+	/* Number of pages, must be power of 2. */
+	u16                           num_pages;
+	u8                            elem_size_shift;
+	u8                            elem_per_pg_shift;
+};
+
+void hinic3_queue_pages_init(struct hinic3_queue_pages *qpages, u32 q_depth,
+			     u32 page_size, u32 elem_size);
+int hinic3_queue_pages_alloc(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages, u32 align);
+void hinic3_queue_pages_free(struct hinic3_hwdev *hwdev,
+			     struct hinic3_queue_pages *qpages);
+
+/* Get pointer to queue entry at the specified index. Index does not have to be
+ * masked to queue depth, only least significant bits will be used. Also
+ * provides remaining elements in same page (including the first one) in case
+ * caller needs multiple entries.
+ */
+static inline void *get_q_element(const struct hinic3_queue_pages *qpages,
+				  u32 idx, u32 *remaining_in_page)
+{
+	const struct hinic3_dma_addr_align *page;
+	u32 page_idx, elem_idx, elem_per_pg, ofs;
+	u8 shift;
+
+	shift = qpages->elem_per_pg_shift;
+	page_idx = (idx >> shift) & (qpages->num_pages - 1);
+	elem_per_pg = 1U << shift;
+	elem_idx = idx & (elem_per_pg - 1);
+	if (remaining_in_page)
+		*remaining_in_page = elem_per_pg - elem_idx;
+	ofs = elem_idx << qpages->elem_size_shift;
+	page = qpages->pages + page_idx;
+	return (char *)page->align_vaddr + ofs;
+}
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
new file mode 100644
index 0000000000000..a3a670c6ce9ba
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.c
@@ -0,0 +1,404 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/etherdevice.h>
+#include <linux/if_vlan.h>
+#include <linux/netdevice.h>
+#include <net/gro.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_rx.h"
+
+#define HINIC3_RX_HDR_SIZE              256
+#define HINIC3_RX_BUFFER_WRITE          16
+
+#define HINIC3_RX_TCP_PKT               0x3
+#define HINIC3_RX_UDP_PKT               0x4
+#define HINIC3_RX_SCTP_PKT              0x7
+
+#define HINIC3_RX_IPV4_PKT              0
+#define HINIC3_RX_IPV6_PKT              1
+#define HINIC3_RX_INVALID_IP_TYPE       2
+
+#define HINIC3_RX_PKT_FORMAT_NON_TUNNEL 0
+#define HINIC3_RX_PKT_FORMAT_VXLAN      1
+
+#define HINIC3_LRO_PKT_HDR_LEN_IPV4     66
+#define HINIC3_LRO_PKT_HDR_LEN_IPV6     86
+#define HINIC3_LRO_PKT_HDR_LEN(cqe) \
+	(RQ_CQE_OFFOLAD_TYPE_GET((cqe)->offload_type, IP_TYPE) == \
+	 HINIC3_RX_IPV6_PKT ? HINIC3_LRO_PKT_HDR_LEN_IPV6 : \
+	 HINIC3_LRO_PKT_HDR_LEN_IPV4)
+
+int hinic3_alloc_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+	return -EFAULT;
+}
+
+void hinic3_free_rxqs(struct net_device *netdev)
+{
+	/* Completed by later submission due to LoC limit. */
+}
+
+static int rx_alloc_mapped_page(struct net_device *netdev, struct hinic3_rx_info *rx_info)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	dma_addr_t dma = rx_info->buf_dma_addr;
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct page *page = rx_info->page;
+
+	if (likely(dma))
+		return 0;
+
+	page = alloc_pages_node(NUMA_NO_NODE, GFP_ATOMIC | __GFP_COMP,
+				nic_dev->page_order);
+	if (unlikely(!page))
+		return -ENOMEM;
+
+	dma = dma_map_page(&pdev->dev, page, 0, nic_dev->dma_rx_buff_size,
+			   DMA_FROM_DEVICE);
+	if (unlikely(dma_mapping_error(&pdev->dev, dma))) {
+		__free_pages(page, nic_dev->page_order);
+		return -ENOMEM;
+	}
+
+	rx_info->page = page;
+	rx_info->buf_dma_addr = dma;
+	rx_info->page_offset = 0;
+
+	return 0;
+}
+
+static void rq_wqe_buff_set(struct hinic3_io_queue *rq, uint32_t wqe_idx,
+			    dma_addr_t dma_addr, u16 len)
+{
+	struct hinic3_rq_wqe *rq_wqe;
+
+	rq_wqe = get_q_element(&rq->wq.qpages, wqe_idx, NULL);
+	rq_wqe->buf_hi_addr = upper_32_bits(dma_addr);
+	rq_wqe->buf_lo_addr = lower_32_bits(dma_addr);
+}
+
+static u32 hinic3_rx_fill_buffers(struct hinic3_rxq *rxq)
+{
+	struct net_device *netdev = rxq->netdev;
+	u32 i, free_wqebbs = rxq->delta - 1;
+	struct hinic3_nic_dev *nic_dev;
+	struct hinic3_rx_info *rx_info;
+	dma_addr_t dma_addr;
+	int err;
+
+	nic_dev = netdev_priv(netdev);
+	for (i = 0; i < free_wqebbs; i++) {
+		rx_info = &rxq->rx_info[rxq->next_to_update];
+
+		err = rx_alloc_mapped_page(netdev, rx_info);
+		if (unlikely(err))
+			break;
+
+		dma_addr = rx_info->buf_dma_addr + rx_info->page_offset;
+		rq_wqe_buff_set(rxq->rq, rxq->next_to_update, dma_addr,
+				nic_dev->rx_buff_len);
+		rxq->next_to_update = (rxq->next_to_update + 1) & rxq->q_mask;
+	}
+
+	if (likely(i)) {
+		hinic3_write_db(rxq->rq, rxq->q_id & 3, DB_CFLAG_DP_RQ,
+				rxq->next_to_update << HINIC3_NORMAL_RQ_WQE);
+		rxq->delta -= i;
+		rxq->next_to_alloc = rxq->next_to_update;
+	}
+
+	return i;
+}
+
+static void hinic3_reuse_rx_page(struct hinic3_rxq *rxq,
+				 struct hinic3_rx_info *old_rx_info)
+{
+	struct hinic3_rx_info *new_rx_info;
+	u16 nta = rxq->next_to_alloc;
+
+	new_rx_info = &rxq->rx_info[nta];
+
+	/* update, and store next to alloc */
+	nta++;
+	rxq->next_to_alloc = (nta < rxq->q_depth) ? nta : 0;
+
+	new_rx_info->page = old_rx_info->page;
+	new_rx_info->page_offset = old_rx_info->page_offset;
+	new_rx_info->buf_dma_addr = old_rx_info->buf_dma_addr;
+
+	/* sync the buffer for use by the device */
+	dma_sync_single_range_for_device(rxq->dev, new_rx_info->buf_dma_addr,
+					 new_rx_info->page_offset,
+					 rxq->buf_len,
+					 DMA_FROM_DEVICE);
+}
+
+static void hinic3_add_rx_frag(struct hinic3_rxq *rxq,
+			       struct hinic3_rx_info *rx_info,
+			       struct sk_buff *skb, u32 size)
+{
+	struct page *page;
+	u8 *va;
+
+	page = rx_info->page;
+	va = (u8 *)page_address(page) + rx_info->page_offset;
+	net_prefetch(va);
+
+	dma_sync_single_range_for_cpu(rxq->dev,
+				      rx_info->buf_dma_addr,
+				      rx_info->page_offset,
+				      rxq->buf_len,
+				      DMA_FROM_DEVICE);
+
+	if (size <= HINIC3_RX_HDR_SIZE && !skb_is_nonlinear(skb)) {
+		memcpy(__skb_put(skb, size), va,
+		       ALIGN(size, sizeof(long)));
+
+		/* page is not reserved, we can reuse buffer as-is */
+		if (likely(page_to_nid(page) == numa_node_id()))
+			goto reuse_rx_page;
+
+		/* this page cannot be reused so discard it */
+		put_page(page);
+		goto err_reuse_buffer;
+	}
+
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
+			rx_info->page_offset, size, rxq->buf_len);
+
+	/* avoid re-using remote pages */
+	if (unlikely(page_to_nid(page) != numa_node_id()))
+		goto err_reuse_buffer;
+
+	/* if we are the only owner of the page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		goto err_reuse_buffer;
+
+	/* flip page offset to other buffer */
+	rx_info->page_offset ^= rxq->buf_len;
+	get_page(page);
+
+reuse_rx_page:
+	hinic3_reuse_rx_page(rxq, rx_info);
+	return;
+
+err_reuse_buffer:
+	/* we are not reusing the buffer so unmap it */
+	dma_unmap_page(rxq->dev, rx_info->buf_dma_addr, rxq->dma_rx_buff_size, DMA_FROM_DEVICE);
+}
+
+static void packaging_skb(struct hinic3_rxq *rxq, struct sk_buff *skb,
+			  u32 sge_num, u32 pkt_len)
+{
+	struct hinic3_rx_info *rx_info;
+	u32 temp_pkt_len = pkt_len;
+	u32 temp_sge_num = sge_num;
+	u32 sw_ci;
+	u32 size;
+
+	sw_ci = rxq->cons_idx & rxq->q_mask;
+	while (temp_sge_num) {
+		rx_info = &rxq->rx_info[sw_ci];
+		sw_ci = (sw_ci + 1) & rxq->q_mask;
+		if (unlikely(temp_pkt_len > rxq->buf_len)) {
+			size = rxq->buf_len;
+			temp_pkt_len -= rxq->buf_len;
+		} else {
+			size = temp_pkt_len;
+		}
+
+		hinic3_add_rx_frag(rxq, rx_info, skb, size);
+
+		/* clear contents of buffer_info */
+		rx_info->buf_dma_addr = 0;
+		rx_info->page = NULL;
+		temp_sge_num--;
+	}
+}
+
+static u32 hinic3_get_sge_num(struct hinic3_rxq *rxq, u32 pkt_len)
+{
+	u32 sge_num;
+
+	sge_num = pkt_len >> rxq->rx_buff_shift;
+	sge_num += (pkt_len & (rxq->buf_len - 1)) ? 1 : 0;
+
+	return sge_num;
+}
+
+static struct sk_buff *hinic3_fetch_rx_buffer(struct hinic3_rxq *rxq,
+					      u32 pkt_len)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct sk_buff *skb;
+	u32 sge_num;
+
+	skb = netdev_alloc_skb_ip_align(netdev, HINIC3_RX_HDR_SIZE);
+	if (unlikely(!skb))
+		return NULL;
+
+	sge_num = hinic3_get_sge_num(rxq, pkt_len);
+
+	net_prefetchw(skb->data);
+	packaging_skb(rxq, skb, sge_num, pkt_len);
+
+	rxq->cons_idx += sge_num;
+	rxq->delta += sge_num;
+
+	return skb;
+}
+
+static void hinic3_pull_tail(struct sk_buff *skb)
+{
+	skb_frag_t *frag = &skb_shinfo(skb)->frags[0];
+	unsigned int pull_len;
+	unsigned char *va;
+
+	va = skb_frag_address(frag);
+
+	/* we need the header to contain the greater of either ETH_HLEN or
+	 * 60 bytes if the skb->len is less than 60 for skb_pad.
+	 */
+	pull_len = eth_get_headlen(skb->dev, va, HINIC3_RX_HDR_SIZE);
+
+	/* align pull length to size of long to optimize memcpy performance */
+	skb_copy_to_linear_data(skb, va, ALIGN(pull_len, sizeof(long)));
+
+	/* update all of the pointers */
+	skb_frag_size_sub(frag, pull_len);
+	skb_frag_off_add(frag, pull_len);
+
+	skb->data_len -= pull_len;
+	skb->tail += pull_len;
+}
+
+static void hinic3_rx_csum(struct hinic3_rxq *rxq, u32 offload_type,
+			   u32 status, struct sk_buff *skb)
+{
+	u32 pkt_fmt = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, TUNNEL_PKT_FORMAT);
+	u32 pkt_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, PKT_TYPE);
+	u32 ip_type = RQ_CQE_OFFOLAD_TYPE_GET(offload_type, IP_TYPE);
+	u32 csum_err = RQ_CQE_STATUS_GET(status, CSUM_ERR);
+	struct net_device *netdev = rxq->netdev;
+
+	if (!(netdev->features & NETIF_F_RXCSUM))
+		return;
+
+	if (unlikely(csum_err)) {
+		/* pkt type is recognized by HW, and csum is wrong */
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	if (ip_type == HINIC3_RX_INVALID_IP_TYPE ||
+	    !(pkt_fmt == HINIC3_RX_PKT_FORMAT_NON_TUNNEL ||
+	      pkt_fmt == HINIC3_RX_PKT_FORMAT_VXLAN)) {
+		skb->ip_summed = CHECKSUM_NONE;
+		return;
+	}
+
+	switch (pkt_type) {
+	case HINIC3_RX_TCP_PKT:
+	case HINIC3_RX_UDP_PKT:
+	case HINIC3_RX_SCTP_PKT:
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		break;
+	default:
+		skb->ip_summed = CHECKSUM_NONE;
+		break;
+	}
+}
+
+static void hinic3_lro_set_gso_params(struct sk_buff *skb, u16 num_lro)
+{
+	struct ethhdr *eth = (struct ethhdr *)(skb->data);
+	__be16 proto;
+
+	proto = __vlan_get_protocol(skb, eth->h_proto, NULL);
+
+	skb_shinfo(skb)->gso_size = DIV_ROUND_UP(skb->len - skb_headlen(skb), num_lro);
+	skb_shinfo(skb)->gso_type = proto == htons(ETH_P_IP) ? SKB_GSO_TCPV4 : SKB_GSO_TCPV6;
+	skb_shinfo(skb)->gso_segs = num_lro;
+}
+
+static int recv_one_pkt(struct hinic3_rxq *rxq, struct hinic3_rq_cqe *rx_cqe,
+			u32 pkt_len, u32 vlan_len, u32 status)
+{
+	struct net_device *netdev = rxq->netdev;
+	struct sk_buff *skb;
+	u32 offload_type;
+	u16 num_lro;
+
+	skb = hinic3_fetch_rx_buffer(rxq, pkt_len);
+	if (unlikely(!skb))
+		return -ENOMEM;
+
+	/* place header in linear portion of buffer */
+	if (skb_is_nonlinear(skb))
+		hinic3_pull_tail(skb);
+
+	offload_type = rx_cqe->offload_type;
+	hinic3_rx_csum(rxq, offload_type, status, skb);
+
+	num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+	if (num_lro)
+		hinic3_lro_set_gso_params(skb, num_lro);
+
+	skb_record_rx_queue(skb, rxq->q_id);
+	skb->protocol = eth_type_trans(skb, netdev);
+
+	if (skb_has_frag_list(skb)) {
+		napi_gro_flush(&rxq->irq_cfg->napi, false);
+		netif_receive_skb(skb);
+	} else {
+		napi_gro_receive(&rxq->irq_cfg->napi, skb);
+	}
+
+	return 0;
+}
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(rxq->netdev);
+	u32 sw_ci, status, pkt_len, vlan_len;
+	struct hinic3_rq_cqe *rx_cqe;
+	u32 num_wqe = 0;
+	int nr_pkts = 0;
+	u16 num_lro;
+
+	while (likely(nr_pkts < budget)) {
+		sw_ci = rxq->cons_idx & rxq->q_mask;
+		rx_cqe = rxq->cqe_arr + sw_ci;
+		status = rx_cqe->status;
+		if (!RQ_CQE_STATUS_GET(status, RXDONE))
+			break;
+
+		/* make sure we read rx_done before packet length */
+		rmb();
+
+		vlan_len = rx_cqe->vlan_len;
+		pkt_len = RQ_CQE_SGE_GET(vlan_len, LEN);
+		if (recv_one_pkt(rxq, rx_cqe, pkt_len, vlan_len, status))
+			break;
+
+		nr_pkts++;
+		num_lro = RQ_CQE_STATUS_GET(status, NUM_LRO);
+		if (num_lro)
+			num_wqe += hinic3_get_sge_num(rxq, pkt_len);
+
+		rx_cqe->status = 0;
+
+		if (num_wqe >= nic_dev->lro_replenish_thld)
+			break;
+	}
+
+	if (rxq->delta >= HINIC3_RX_BUFFER_WRITE)
+		hinic3_rx_fill_buffers(rxq);
+
+	return nr_pkts;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
new file mode 100644
index 0000000000000..276b712815ec1
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_rx.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_RX_H_
+#define _HINIC3_RX_H_
+
+#include <linux/bitfield.h>
+#include <linux/netdevice.h>
+
+#define RQ_CQE_OFFOLAD_TYPE_PKT_TYPE_MASK           GENMASK(4, 0)
+#define RQ_CQE_OFFOLAD_TYPE_IP_TYPE_MASK            GENMASK(6, 5)
+#define RQ_CQE_OFFOLAD_TYPE_TUNNEL_PKT_FORMAT_MASK  GENMASK(11, 8)
+#define RQ_CQE_OFFOLAD_TYPE_VLAN_EN_MASK            BIT(21)
+#define RQ_CQE_OFFOLAD_TYPE_GET(val, member) \
+	FIELD_GET(RQ_CQE_OFFOLAD_TYPE_##member##_MASK, val)
+
+#define RQ_CQE_SGE_VLAN_MASK  GENMASK(15, 0)
+#define RQ_CQE_SGE_LEN_MASK   GENMASK(31, 16)
+#define RQ_CQE_SGE_GET(val, member) \
+	FIELD_GET(RQ_CQE_SGE_##member##_MASK, val)
+
+#define RQ_CQE_STATUS_CSUM_ERR_MASK  GENMASK(15, 0)
+#define RQ_CQE_STATUS_NUM_LRO_MASK   GENMASK(23, 16)
+#define RQ_CQE_STATUS_RXDONE_MASK    BIT(31)
+#define RQ_CQE_STATUS_GET(val, member) \
+	FIELD_GET(RQ_CQE_STATUS_##member##_MASK, val)
+
+/* RX Completion information that is provided by HW for a specific RX WQE */
+struct hinic3_rq_cqe {
+	u32 status;
+	u32 vlan_len;
+	u32 offload_type;
+	u32 rsvd3;
+	u32 rsvd4;
+	u32 rsvd5;
+	u32 rsvd6;
+	u32 pkt_info;
+};
+
+struct hinic3_rq_wqe {
+	u32 buf_hi_addr;
+	u32 buf_lo_addr;
+	u32 cqe_hi_addr;
+	u32 cqe_lo_addr;
+};
+
+struct hinic3_rx_info {
+	dma_addr_t  buf_dma_addr;
+	struct page *page;
+	u32         page_offset;
+};
+
+struct hinic3_rxq {
+	struct net_device       *netdev;
+
+	u16                     q_id;
+	u32                     q_depth;
+	u32                     q_mask;
+
+	u16                     buf_len;
+	u32                     rx_buff_shift;
+	u32                     dma_rx_buff_size;
+
+	u32                     cons_idx;
+	u32                     delta;
+
+	u32                     irq_id;
+	u16                     msix_entry_idx;
+
+	/* cqe_arr and rx_info are arrays of rq_depth elements. Each element is
+	 * statically associated (by index) to a specific rq_wqe.
+	 */
+	struct hinic3_rq_cqe   *cqe_arr;
+	struct hinic3_rx_info  *rx_info;
+
+	struct hinic3_io_queue *rq;
+
+	struct hinic3_irq_cfg  *irq_cfg;
+	u16                    next_to_alloc;
+	u16                    next_to_update;
+	struct device          *dev; /* device for DMA mapping */
+
+	dma_addr_t             cqe_start_paddr;
+} ____cacheline_aligned;
+
+int hinic3_alloc_rxqs(struct net_device *netdev);
+void hinic3_free_rxqs(struct net_device *netdev);
+
+int hinic3_rx_poll(struct hinic3_rxq *rxq, int budget);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
new file mode 100644
index 0000000000000..6a91305ac15d0
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.c
@@ -0,0 +1,691 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/if_vlan.h>
+#include <linux/iopoll.h>
+#include <net/ip6_checksum.h>
+#include <net/ipv6.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_nic_cfg.h"
+#include "hinic3_nic_dev.h"
+#include "hinic3_nic_io.h"
+#include "hinic3_tx.h"
+#include "hinic3_wq.h"
+
+#define MIN_SKB_LEN                32
+
+int hinic3_alloc_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_hwdev *hwdev = nic_dev->hwdev;
+	u16 q_id, num_txqs = nic_dev->max_qps;
+	struct pci_dev *pdev = nic_dev->pdev;
+	struct hinic3_txq *txq;
+	u64 txq_size;
+
+	txq_size = num_txqs * sizeof(*nic_dev->txqs);
+	if (!txq_size) {
+		dev_err(hwdev->dev, "Cannot allocate zero size txqs\n");
+		return -EINVAL;
+	}
+
+	nic_dev->txqs = kzalloc(txq_size, GFP_KERNEL);
+	if (!nic_dev->txqs)
+		return -ENOMEM;
+
+	for (q_id = 0; q_id < num_txqs; q_id++) {
+		txq = &nic_dev->txqs[q_id];
+		txq->netdev = netdev;
+		txq->q_id = q_id;
+		txq->q_depth = nic_dev->q_params.sq_depth;
+		txq->q_mask = nic_dev->q_params.sq_depth - 1;
+		txq->dev = &pdev->dev;
+	}
+
+	return 0;
+}
+
+void hinic3_free_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+
+	kfree(nic_dev->txqs);
+}
+
+static void hinic3_set_buf_desc(struct hinic3_sq_bufdesc *buf_descs,
+				dma_addr_t addr, u32 len)
+{
+	buf_descs->hi_addr = upper_32_bits(addr);
+	buf_descs->lo_addr = lower_32_bits(addr);
+	buf_descs->len  = len;
+}
+
+static int hinic3_tx_map_skb(struct net_device *netdev, struct sk_buff *skb,
+			     struct hinic3_txq *txq,
+			     struct hinic3_tx_info *tx_info,
+			     struct hinic3_sq_wqe_combo *wqe_combo)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+	struct hinic3_sq_bufdesc *buf_desc = wqe_combo->bds_head;
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct hinic3_dma_info *dma_info = tx_info->dma_info;
+	struct pci_dev *pdev = nic_dev->pdev;
+	skb_frag_t *frag;
+	u32 j, i;
+	int err;
+
+	dma_info[0].dma = dma_map_single(&pdev->dev, skb->data, skb_headlen(skb), DMA_TO_DEVICE);
+	if (dma_mapping_error(&pdev->dev, dma_info[0].dma))
+		return -EFAULT;
+
+	dma_info[0].len = skb_headlen(skb);
+
+	wqe_desc->hi_addr = upper_32_bits(dma_info[0].dma);
+	wqe_desc->lo_addr = lower_32_bits(dma_info[0].dma);
+
+	wqe_desc->ctrl_len = dma_info[0].len;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags;) {
+		frag = &(skb_shinfo(skb)->frags[i]);
+		if (unlikely(i == wqe_combo->first_bds_num))
+			buf_desc = wqe_combo->bds_sec2;
+
+		i++;
+		dma_info[i].dma = skb_frag_dma_map(&pdev->dev, frag, 0,
+						   skb_frag_size(frag),
+						   DMA_TO_DEVICE);
+		if (dma_mapping_error(&pdev->dev, dma_info[i].dma)) {
+			i--;
+			err = -EFAULT;
+			goto err_frag_map;
+		}
+		dma_info[i].len = skb_frag_size(frag);
+
+		hinic3_set_buf_desc(buf_desc, dma_info[i].dma,
+				    dma_info[i].len);
+		buf_desc++;
+	}
+
+	return 0;
+
+err_frag_map:
+	for (j = 0; j < i;) {
+		j++;
+		dma_unmap_page(&pdev->dev, dma_info[j].dma,
+			       dma_info[j].len, DMA_TO_DEVICE);
+	}
+	dma_unmap_single(&pdev->dev, dma_info[0].dma, dma_info[0].len,
+			 DMA_TO_DEVICE);
+	return err;
+}
+
+static void hinic3_tx_unmap_skb(struct net_device *netdev,
+				struct sk_buff *skb,
+				struct hinic3_dma_info *dma_info)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	struct pci_dev *pdev = nic_dev->pdev;
+	int i;
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags;) {
+		i++;
+		dma_unmap_page(&pdev->dev,
+			       dma_info[i].dma,
+			       dma_info[i].len, DMA_TO_DEVICE);
+	}
+
+	dma_unmap_single(&pdev->dev, dma_info[0].dma,
+			 dma_info[0].len, DMA_TO_DEVICE);
+}
+
+static void hinic3_tx_free_skb(struct net_device *netdev,
+			       struct hinic3_tx_info *tx_info)
+{
+	hinic3_tx_unmap_skb(netdev, tx_info->skb, tx_info->dma_info);
+	dev_kfree_skb_any(tx_info->skb);
+	tx_info->skb = NULL;
+}
+
+union hinic3_ip {
+	struct iphdr   *v4;
+	struct ipv6hdr *v6;
+	unsigned char  *hdr;
+};
+
+union hinic3_l4 {
+	struct tcphdr *tcp;
+	struct udphdr *udp;
+	unsigned char *hdr;
+};
+
+enum hinic3_l3_type {
+	HINIC3_L3_UNKNOWN         = 0,
+	HINIC3_L3_IP6_PKT         = 1,
+	HINIC3_L3_IP4_PKT_NO_CSUM = 2,
+	HINIC3_L3_IP4_PKT_CSUM    = 3,
+};
+
+enum hinic3_l4_offload_type {
+	HINIC3_L4_OFFLOAD_DISABLE = 0,
+	HINIC3_L4_OFFLOAD_TCP     = 1,
+	HINIC3_L4_OFFLOAD_STCP    = 2,
+	HINIC3_L4_OFFLOAD_UDP     = 3,
+};
+
+/* initialize l4 offset and offload */
+static void get_inner_l4_info(struct sk_buff *skb, union hinic3_l4 *l4,
+			      u8 l4_proto, u32 *offset,
+			      enum hinic3_l4_offload_type *l4_offload)
+{
+	switch (l4_proto) {
+	case IPPROTO_TCP:
+		*l4_offload = HINIC3_L4_OFFLOAD_TCP;
+		/* To be same with TSO, payload offset begins from payload */
+		*offset = (l4->tcp->doff << TCP_HDR_DATA_OFF_UNIT_SHIFT) +
+			   TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+
+	case IPPROTO_UDP:
+		*l4_offload = HINIC3_L4_OFFLOAD_UDP;
+		*offset = TRANSPORT_OFFSET(l4->hdr, skb);
+		break;
+	default:
+		*l4_offload = HINIC3_L4_OFFLOAD_DISABLE;
+		*offset = 0;
+	}
+}
+
+static int hinic3_tx_csum(struct hinic3_txq *txq, struct hinic3_sq_task *task,
+			  struct sk_buff *skb)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL)
+		return 0;
+
+	if (skb->encapsulation) {
+		union hinic3_ip ip;
+		u8 l4_proto;
+
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, TUNNEL_FLAG);
+
+		ip.hdr = skb_network_header(skb);
+		if (ip.v4->version == 4) {
+			l4_proto = ip.v4->protocol;
+		} else if (ip.v4->version == 6) {
+			union hinic3_l4 l4;
+			unsigned char *exthdr;
+			__be16 frag_off;
+
+			exthdr = ip.hdr + sizeof(*ip.v6);
+			l4_proto = ip.v6->nexthdr;
+			l4.hdr = skb_transport_header(skb);
+			if (l4.hdr != exthdr)
+				ipv6_skip_exthdr(skb, exthdr - skb->data,
+						 &l4_proto, &frag_off);
+		} else {
+			l4_proto = IPPROTO_RAW;
+		}
+
+		if (l4_proto != IPPROTO_UDP ||
+		    ((struct udphdr *)skb_transport_header(skb))->dest != VXLAN_OFFLOAD_PORT_LE) {
+			/* Unsupported tunnel packet, disable csum offload */
+			skb_checksum_help(skb);
+			return 0;
+		}
+	}
+
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, INNER_L4_EN);
+
+	return 1;
+}
+
+static void get_inner_l3_l4_type(struct sk_buff *skb, union hinic3_ip *ip,
+				 union hinic3_l4 *l4,
+				 enum hinic3_l3_type *l3_type, u8 *l4_proto)
+{
+	unsigned char *exthdr;
+	__be16 frag_off;
+
+	if (ip->v4->version == 4) {
+		*l3_type = HINIC3_L3_IP4_PKT_CSUM;
+		*l4_proto = ip->v4->protocol;
+	} else if (ip->v4->version == 6) {
+		*l3_type = HINIC3_L3_IP6_PKT;
+		exthdr = ip->hdr + sizeof(*ip->v6);
+		*l4_proto = ip->v6->nexthdr;
+		if (exthdr != l4->hdr) {
+			ipv6_skip_exthdr(skb, exthdr - skb->data,
+					 l4_proto, &frag_off);
+		}
+	} else {
+		*l3_type = HINIC3_L3_UNKNOWN;
+		*l4_proto = 0;
+	}
+}
+
+static void hinic3_set_tso_info(struct hinic3_sq_task *task, u32 *queue_info,
+				enum hinic3_l4_offload_type l4_offload,
+				u32 offset, u32 mss)
+{
+	if (l4_offload == HINIC3_L4_OFFLOAD_TCP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1U, TSO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, INNER_L4_EN);
+	} else if (l4_offload == HINIC3_L4_OFFLOAD_UDP) {
+		*queue_info |= SQ_CTRL_QUEUE_INFO_SET(1U, UFO);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, INNER_L4_EN);
+	}
+
+	/* enable L3 calculation */
+	task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, INNER_L3_EN);
+
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(offset >> 1, PLDOFF);
+
+	/* set MSS value */
+	*queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+	*queue_info |= SQ_CTRL_QUEUE_INFO_SET(mss, MSS);
+}
+
+static __sum16 csum_magic(union hinic3_ip *ip, unsigned short proto)
+{
+	return (ip->v4->version == 4) ?
+		csum_tcpudp_magic(ip->v4->saddr, ip->v4->daddr, 0, proto, 0) :
+		csum_ipv6_magic(&ip->v6->saddr, &ip->v6->daddr, 0, proto, 0);
+}
+
+static int hinic3_tso(struct hinic3_sq_task *task, u32 *queue_info,
+		      struct sk_buff *skb)
+{
+	enum hinic3_l4_offload_type l4_offload;
+	enum hinic3_l3_type l3_type;
+	union hinic3_ip ip;
+	union hinic3_l4 l4;
+	u8 l4_proto;
+	u32 offset;
+	int err;
+
+	if (!skb_is_gso(skb))
+		return 0;
+
+	err = skb_cow_head(skb, 0);
+	if (err < 0)
+		return err;
+
+	if (skb->encapsulation) {
+		u32 gso_type = skb_shinfo(skb)->gso_type;
+		/* L3 checksum is always enabled */
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, OUT_L3_EN);
+		task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, TUNNEL_FLAG);
+
+		l4.hdr = skb_transport_header(skb);
+		ip.hdr = skb_network_header(skb);
+
+		if (gso_type & SKB_GSO_UDP_TUNNEL_CSUM) {
+			l4.udp->check = ~csum_magic(&ip, IPPROTO_UDP);
+			task->pkt_info0 |= SQ_TASK_INFO0_SET(1U, OUT_L4_EN);
+		}
+
+		ip.hdr = skb_inner_network_header(skb);
+		l4.hdr = skb_inner_transport_header(skb);
+	} else {
+		ip.hdr = skb_network_header(skb);
+		l4.hdr = skb_transport_header(skb);
+	}
+
+	get_inner_l3_l4_type(skb, &ip, &l4, &l3_type, &l4_proto);
+
+	if (l4_proto == IPPROTO_TCP)
+		l4.tcp->check = ~csum_magic(&ip, IPPROTO_TCP);
+
+	get_inner_l4_info(skb, &l4, l4_proto, &offset, &l4_offload);
+
+	hinic3_set_tso_info(task, queue_info, l4_offload, offset,
+			    skb_shinfo(skb)->gso_size);
+
+	return 1;
+}
+
+static void hinic3_set_vlan_tx_offload(struct hinic3_sq_task *task,
+				       u16 vlan_tag, u8 vlan_tpid)
+{
+	/* vlan_tpid: 0=select TPID0 in IPSU, 1=select TPID1 in IPSU
+	 * 2=select TPID2 in IPSU, 3=select TPID3 in IPSU,
+	 * 4=select TPID4 in IPSU
+	 */
+	task->vlan_offload = SQ_TASK_INFO3_SET(vlan_tag, VLAN_TAG) |
+			     SQ_TASK_INFO3_SET(vlan_tpid, VLAN_TPID) |
+			     SQ_TASK_INFO3_SET(1U, VLAN_TAG_VALID);
+}
+
+static u32 hinic3_tx_offload(struct sk_buff *skb, struct hinic3_sq_task *task,
+			     u32 *queue_info, struct hinic3_txq *txq)
+{
+	u32 offload = 0;
+	int tso_cs_en;
+
+	task->pkt_info0 = 0;
+	task->ip_identify = 0;
+	task->rsvd = 0;
+	task->vlan_offload = 0;
+
+	tso_cs_en = hinic3_tso(task, queue_info, skb);
+	if (tso_cs_en < 0) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	} else if (tso_cs_en) {
+		offload |= HINIC3_TX_OFFLOAD_TSO;
+	} else {
+		tso_cs_en = hinic3_tx_csum(txq, task, skb);
+		if (tso_cs_en)
+			offload |= HINIC3_TX_OFFLOAD_CSUM;
+	}
+
+#define VLAN_INSERT_MODE_MAX 5
+	if (unlikely(skb_vlan_tag_present(skb))) {
+		/* select vlan insert mode by qid, default 802.1Q Tag type */
+		hinic3_set_vlan_tx_offload(task, skb_vlan_tag_get(skb),
+					   txq->q_id % VLAN_INSERT_MODE_MAX);
+		offload |= HINIC3_TX_OFFLOAD_VLAN;
+	}
+
+	if (unlikely(SQ_CTRL_QUEUE_INFO_GET(*queue_info, PLDOFF) >
+		     SQ_CTRL_MAX_PLDOFF)) {
+		offload = HINIC3_TX_OFFLOAD_INVALID;
+		return offload;
+	}
+
+	return offload;
+}
+
+static int hinic3_maybe_stop_tx(struct hinic3_txq *txq, u16 wqebb_cnt)
+{
+	if (likely(hinic3_wq_free_wqebbs(&txq->sq->wq) >= wqebb_cnt))
+		return 0;
+
+	/* We need to check again in a case another CPU has just
+	 * made room available.
+	 */
+	netif_stop_subqueue(txq->netdev, txq->q_id);
+
+	if (likely(hinic3_wq_free_wqebbs(&txq->sq->wq) < wqebb_cnt))
+		return -EBUSY;
+
+	netif_start_subqueue(txq->netdev, txq->q_id);
+
+	return 0;
+}
+
+static u16 hinic3_get_and_update_sq_owner(struct hinic3_io_queue *sq,
+					  u16 curr_pi, u16 wqebb_cnt)
+{
+	u16 owner = sq->owner;
+
+	if (unlikely(curr_pi + wqebb_cnt >= sq->wq.q_depth))
+		sq->owner = !sq->owner;
+
+	return owner;
+}
+
+static u16 hinic3_set_wqe_combo(struct hinic3_txq *txq,
+				struct hinic3_sq_wqe_combo *wqe_combo,
+				u32 offload, u16 num_sge, u16 *curr_pi)
+{
+	struct hinic3_sq_bufdesc *second_part_wqebbs_addr;
+	u16 first_part_wqebbs_num, tmp_pi;
+	struct hinic3_sq_bufdesc *wqe;
+
+	wqe_combo->ctrl_bd0 = hinic3_wq_get_one_wqebb(&txq->sq->wq, curr_pi);
+	if (!offload && num_sge == 1) {
+		wqe_combo->wqe_type = SQ_WQE_COMPACT_TYPE;
+		return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi, 1);
+	}
+
+	wqe_combo->wqe_type = SQ_WQE_EXTENDED_TYPE;
+
+	if (offload) {
+		wqe_combo->task = hinic3_wq_get_one_wqebb(&txq->sq->wq, &tmp_pi);
+		wqe_combo->task_type = SQ_WQE_TASKSECT_16BYTES;
+	} else {
+		wqe_combo->task_type = SQ_WQE_TASKSECT_46BITS;
+	}
+
+	if (num_sge > 1) {
+		/* first wqebb contain bd0, and bd size is equal to sq wqebb
+		 * size, so we use (num_sge - 1) as wanted weqbb_cnt
+		 */
+		hinic3_wq_get_multi_wqebbs(&txq->sq->wq, num_sge - 1, &tmp_pi,
+					   &wqe,
+					   &second_part_wqebbs_addr,
+					   &first_part_wqebbs_num);
+		wqe_combo->bds_head = wqe;
+		wqe_combo->bds_sec2 = second_part_wqebbs_addr;
+		wqe_combo->first_bds_num = first_part_wqebbs_num;
+	}
+
+	return hinic3_get_and_update_sq_owner(txq->sq, *curr_pi,
+					      num_sge + !!offload);
+}
+
+static void hinic3_prepare_sq_ctrl(struct hinic3_sq_wqe_combo *wqe_combo,
+				   u32 queue_info, int nr_descs, u16 owner)
+{
+	struct hinic3_sq_wqe_desc *wqe_desc = wqe_combo->ctrl_bd0;
+
+	if (wqe_combo->wqe_type == SQ_WQE_COMPACT_TYPE) {
+		wqe_desc->ctrl_len |=
+		    SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+		    SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+		    SQ_CTRL_SET(owner, OWNER);
+
+		/* compact wqe queue_info will transfer to chip */
+		wqe_desc->queue_info = 0;
+		return;
+	}
+
+	wqe_desc->ctrl_len |= SQ_CTRL_SET(nr_descs, BUFDESC_NUM) |
+			      SQ_CTRL_SET(wqe_combo->task_type, TASKSECT_LEN) |
+			      SQ_CTRL_SET(SQ_NORMAL_WQE, DATA_FORMAT) |
+			      SQ_CTRL_SET(wqe_combo->wqe_type, EXTENDED) |
+			      SQ_CTRL_SET(owner, OWNER);
+
+	wqe_desc->queue_info = queue_info;
+	wqe_desc->queue_info |= SQ_CTRL_QUEUE_INFO_SET(1U, UC);
+
+	if (!SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS)) {
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_DEFAULT, MSS);
+	} else if (SQ_CTRL_QUEUE_INFO_GET(wqe_desc->queue_info, MSS) <
+		   HINIC3_TX_MSS_MIN) {
+		/* mss should not be less than 80 */
+		wqe_desc->queue_info &= ~SQ_CTRL_QUEUE_INFO_MSS_MASK;
+		wqe_desc->queue_info |=
+		    SQ_CTRL_QUEUE_INFO_SET(HINIC3_TX_MSS_MIN, MSS);
+	}
+}
+
+static netdev_tx_t hinic3_send_one_skb(struct sk_buff *skb,
+				       struct net_device *netdev,
+				       struct hinic3_txq *txq)
+{
+	struct hinic3_sq_wqe_combo wqe_combo = {};
+	struct hinic3_tx_info *tx_info;
+	u32 offload, queue_info = 0;
+	struct hinic3_sq_task task;
+	u16 wqebb_cnt, num_sge;
+	u16 saved_wq_prod_idx;
+	u16 owner, pi = 0;
+	u8 saved_sq_owner;
+	int err;
+
+	if (unlikely(skb->len < MIN_SKB_LEN)) {
+		if (skb_pad(skb, MIN_SKB_LEN - skb->len))
+			goto err_tx_skb_pad;
+
+		skb->len = MIN_SKB_LEN;
+	}
+
+	num_sge = skb_shinfo(skb)->nr_frags + 1;
+	/* assume normal wqe format + 1 wqebb for task info */
+	wqebb_cnt = num_sge + 1;
+	if (unlikely(hinic3_maybe_stop_tx(txq, wqebb_cnt)))
+		return NETDEV_TX_BUSY;
+
+	offload = hinic3_tx_offload(skb, &task, &queue_info, txq);
+	if (unlikely(offload == HINIC3_TX_OFFLOAD_INVALID)) {
+		goto tx_drop_pkts;
+	} else if (!offload) {
+		wqebb_cnt -= 1;
+		if (unlikely(num_sge == 1 &&
+			     skb->len > HINIC3_COMPACT_WQEE_SKB_MAX_LEN))
+			goto tx_drop_pkts;
+	}
+
+	saved_wq_prod_idx = txq->sq->wq.prod_idx;
+	saved_sq_owner = txq->sq->owner;
+
+	owner = hinic3_set_wqe_combo(txq, &wqe_combo, offload, num_sge, &pi);
+	if (offload)
+		*wqe_combo.task = task;
+
+	tx_info = &txq->tx_info[pi];
+	tx_info->skb = skb;
+	tx_info->wqebb_cnt = wqebb_cnt;
+
+	err = hinic3_tx_map_skb(netdev, skb, txq, tx_info, &wqe_combo);
+	if (err) {
+		/* Rollback work queue to reclaim the wqebb we did not use */
+		txq->sq->wq.prod_idx = saved_wq_prod_idx;
+		txq->sq->owner = saved_sq_owner;
+		goto tx_drop_pkts;
+	}
+
+	hinic3_prepare_sq_ctrl(&wqe_combo, queue_info, num_sge, owner);
+	hinic3_write_db(txq->sq, 0, DB_CFLAG_DP_SQ,
+			hinic3_get_sq_local_pi(txq->sq));
+
+	return NETDEV_TX_OK;
+
+tx_drop_pkts:
+	dev_kfree_skb_any(skb);
+
+err_tx_skb_pad:
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 q_id = skb_get_queue_mapping(skb);
+	struct hinic3_txq *txq;
+
+	if (unlikely(!netif_carrier_ok(netdev))) {
+		dev_kfree_skb_any(skb);
+		return NETDEV_TX_OK;
+	}
+
+	if (unlikely(q_id >= nic_dev->q_params.num_qps)) {
+		txq = &nic_dev->txqs[0];
+		goto tx_drop_pkts;
+	}
+	txq = &nic_dev->txqs[q_id];
+
+	return hinic3_send_one_skb(skb, netdev, txq);
+
+tx_drop_pkts:
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+}
+
+static bool is_hw_complete_sq_process(struct hinic3_io_queue *sq)
+{
+	u16 sw_pi, hw_ci;
+
+	sw_pi = hinic3_get_sq_local_pi(sq);
+	hw_ci = hinic3_get_sq_hw_ci(sq);
+
+	return sw_pi == hw_ci;
+}
+
+#define HINIC3_FLUSH_QUEUE_POLL_SLEEP_US   10000
+#define HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US 10000000
+static int hinic3_stop_sq(struct hinic3_txq *txq)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(txq->netdev);
+	int err, rc;
+
+	err = read_poll_timeout(hinic3_force_drop_tx_pkt, rc,
+				is_hw_complete_sq_process(txq->sq) || rc,
+				HINIC3_FLUSH_QUEUE_POLL_SLEEP_US,
+				HINIC3_FLUSH_QUEUE_POLL_TIMEOUT_US,
+				true, nic_dev->hwdev);
+	if (rc)
+		return rc;
+	else
+		return err;
+}
+
+/* packet transmission should be stopped before calling this function */
+void hinic3_flush_txqs(struct net_device *netdev)
+{
+	struct hinic3_nic_dev *nic_dev = netdev_priv(netdev);
+	u16 qid;
+	int err;
+
+	for (qid = 0; qid < nic_dev->q_params.num_qps; qid++) {
+		err = hinic3_stop_sq(&nic_dev->txqs[qid]);
+		if (err)
+			netdev_err(netdev, "Failed to stop sq%u\n", qid);
+	}
+}
+
+#define HINIC3_BDS_PER_SQ_WQEBB \
+	(HINIC3_SQ_WQEBB_SIZE / sizeof(struct hinic3_sq_bufdesc))
+
+int hinic3_tx_poll(struct hinic3_txq *txq, int budget)
+{
+	struct net_device *netdev = txq->netdev;
+	u16 hw_ci, sw_ci, q_id = txq->sq->q_id;
+	struct hinic3_nic_dev *nic_dev;
+	struct hinic3_tx_info *tx_info;
+	u16 wqebb_cnt = 0;
+	int pkts = 0;
+
+	nic_dev = netdev_priv(netdev);
+	hw_ci = hinic3_get_sq_hw_ci(txq->sq);
+	dma_rmb();
+	sw_ci = hinic3_get_sq_local_ci(txq->sq);
+
+	do {
+		tx_info = &txq->tx_info[sw_ci];
+
+		/* Did all wqebb of this wqe complete? */
+		if (hw_ci == sw_ci ||
+		    ((hw_ci - sw_ci) & txq->q_mask) < tx_info->wqebb_cnt)
+			break;
+
+		sw_ci = (sw_ci + tx_info->wqebb_cnt) & txq->q_mask;
+		net_prefetch(&txq->tx_info[sw_ci]);
+
+		wqebb_cnt += tx_info->wqebb_cnt;
+		pkts++;
+
+		hinic3_tx_free_skb(netdev, tx_info);
+	} while (likely(pkts < budget));
+
+	hinic3_wq_put_wqebbs(&txq->sq->wq, wqebb_cnt);
+
+	if (unlikely(__netif_subqueue_stopped(netdev, q_id) &&
+		     hinic3_wq_free_wqebbs(&txq->sq->wq) >= 1 &&
+		     test_bit(HINIC3_INTF_UP, &nic_dev->flags))) {
+		struct netdev_queue *netdev_txq =
+				netdev_get_tx_queue(netdev, q_id);
+
+		__netif_tx_lock(netdev_txq, smp_processor_id());
+		/* avoid re-waking subqueue with xmit_frame */
+		if (__netif_subqueue_stopped(netdev, q_id))
+			netif_wake_subqueue(netdev, q_id);
+
+		__netif_tx_unlock(netdev_txq);
+	}
+
+	return pkts;
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
new file mode 100644
index 0000000000000..4f53bbfb20b7a
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_tx.h
@@ -0,0 +1,130 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_TX_H_
+#define _HINIC3_TX_H_
+
+#include <linux/bitops.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/netdevice.h>
+#include <net/checksum.h>
+
+#define VXLAN_OFFLOAD_PORT_LE            cpu_to_be16(4789)
+#define TCP_HDR_DATA_OFF_UNIT_SHIFT      2
+#define TRANSPORT_OFFSET(l4_hdr, skb)    ((l4_hdr) - (skb)->data)
+
+#define HINIC3_COMPACT_WQEE_SKB_MAX_LEN  16383
+
+enum sq_wqe_data_format {
+	SQ_NORMAL_WQE = 0,
+};
+
+enum sq_wqe_ec_type {
+	SQ_WQE_COMPACT_TYPE  = 0,
+	SQ_WQE_EXTENDED_TYPE = 1,
+};
+
+enum sq_wqe_tasksect_len_type {
+	SQ_WQE_TASKSECT_46BITS  = 0,
+	SQ_WQE_TASKSECT_16BYTES = 1,
+};
+
+enum hinic3_tx_offload_type {
+	HINIC3_TX_OFFLOAD_TSO     = BIT(0),
+	HINIC3_TX_OFFLOAD_CSUM    = BIT(1),
+	HINIC3_TX_OFFLOAD_VLAN    = BIT(2),
+	HINIC3_TX_OFFLOAD_INVALID = BIT(3),
+	HINIC3_TX_OFFLOAD_ESP     = BIT(4),
+};
+
+#define SQ_CTRL_BUFDESC_NUM_MASK   GENMASK(26, 19)
+#define SQ_CTRL_TASKSECT_LEN_MASK  BIT(27)
+#define SQ_CTRL_DATA_FORMAT_MASK   BIT(28)
+#define SQ_CTRL_EXTENDED_MASK      BIT(30)
+#define SQ_CTRL_OWNER_MASK         BIT(31)
+#define SQ_CTRL_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_##member##_MASK, val)
+
+#define SQ_CTRL_QUEUE_INFO_PLDOFF_MASK  GENMASK(9, 2)
+#define SQ_CTRL_QUEUE_INFO_UFO_MASK     BIT(10)
+#define SQ_CTRL_QUEUE_INFO_TSO_MASK     BIT(11)
+#define SQ_CTRL_QUEUE_INFO_MSS_MASK     GENMASK(26, 13)
+#define SQ_CTRL_QUEUE_INFO_UC_MASK      BIT(28)
+
+#define SQ_CTRL_QUEUE_INFO_SET(val, member) \
+	FIELD_PREP(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+#define SQ_CTRL_QUEUE_INFO_GET(val, member) \
+	FIELD_GET(SQ_CTRL_QUEUE_INFO_##member##_MASK, val)
+
+#define SQ_CTRL_MAX_PLDOFF  221
+
+#define SQ_TASK_INFO0_TUNNEL_FLAG_MASK  BIT(19)
+#define SQ_TASK_INFO0_INNER_L4_EN_MASK  BIT(24)
+#define SQ_TASK_INFO0_INNER_L3_EN_MASK  BIT(25)
+#define SQ_TASK_INFO0_OUT_L4_EN_MASK    BIT(27)
+#define SQ_TASK_INFO0_OUT_L3_EN_MASK    BIT(28)
+#define SQ_TASK_INFO0_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO0_##member##_MASK, val)
+
+#define SQ_TASK_INFO3_VLAN_TAG_MASK        GENMASK(15, 0)
+#define SQ_TASK_INFO3_VLAN_TPID_MASK       GENMASK(18, 16)
+#define SQ_TASK_INFO3_VLAN_TAG_VALID_MASK  BIT(19)
+#define SQ_TASK_INFO3_SET(val, member) \
+	FIELD_PREP(SQ_TASK_INFO3_##member##_MASK, val)
+
+struct hinic3_sq_wqe_desc {
+	u32 ctrl_len;
+	u32 queue_info;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+struct hinic3_sq_task {
+	u32 pkt_info0;
+	u32 ip_identify;
+	u32 rsvd;
+	u32 vlan_offload;
+};
+
+struct hinic3_sq_wqe_combo {
+	struct hinic3_sq_wqe_desc *ctrl_bd0;
+	struct hinic3_sq_task     *task;
+	struct hinic3_sq_bufdesc  *bds_head;
+	struct hinic3_sq_bufdesc  *bds_sec2;
+	u16                       first_bds_num;
+	u32                       wqe_type;
+	u32                       task_type;
+};
+
+struct hinic3_dma_info {
+	dma_addr_t dma;
+	u32        len;
+};
+
+struct hinic3_tx_info {
+	struct sk_buff         *skb;
+	u16                    wqebb_cnt;
+	struct hinic3_dma_info *dma_info;
+};
+
+struct hinic3_txq {
+	struct net_device       *netdev;
+	struct device           *dev;
+
+	u16                     q_id;
+	u32                     q_mask;
+	u32                     q_depth;
+
+	struct hinic3_tx_info   *tx_info;
+	struct hinic3_io_queue  *sq;
+} ____cacheline_aligned;
+
+int hinic3_alloc_txqs(struct net_device *netdev);
+void hinic3_free_txqs(struct net_device *netdev);
+
+netdev_tx_t hinic3_xmit_frame(struct sk_buff *skb, struct net_device *netdev);
+int hinic3_tx_poll(struct hinic3_txq *txq, int budget);
+void hinic3_flush_txqs(struct net_device *netdev);
+
+#endif
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
new file mode 100644
index 0000000000000..66516dad16c84
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.c
@@ -0,0 +1,29 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved.
+
+#include <linux/dma-mapping.h>
+
+#include "hinic3_hwdev.h"
+#include "hinic3_wq.h"
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_wqebb,
+				struct hinic3_sq_bufdesc **second_part_wqebbs_addr,
+				u16 *first_part_wqebbs_num)
+{
+	u32 idx, remaining;
+
+	idx = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx += num_wqebbs;
+	*prod_idx = idx;
+	*first_wqebb = get_q_element(&wq->qpages, idx, &remaining);
+	if (likely(remaining >= num_wqebbs)) {
+		*first_part_wqebbs_num = num_wqebbs;
+		*second_part_wqebbs_addr = NULL;
+	} else {
+		*first_part_wqebbs_num = remaining;
+		idx += remaining;
+		*second_part_wqebbs_addr = get_q_element(&wq->qpages, idx, NULL);
+	}
+}
diff --git a/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
new file mode 100644
index 0000000000000..d90097eb86924
--- /dev/null
+++ b/drivers/net/ethernet/huawei/hinic3/hinic3_wq.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) Huawei Technologies Co., Ltd. 2025. All rights reserved. */
+
+#ifndef _HINIC3_WQ_H_
+#define _HINIC3_WQ_H_
+
+#include <linux/io.h>
+
+#include "hinic3_queue_common.h"
+
+struct hinic3_sq_bufdesc {
+	/* 31-bits Length, L2NIC only uses length[17:0] */
+	u32 len;
+	u32 rsvd;
+	u32 hi_addr;
+	u32 lo_addr;
+};
+
+/* Work queue is used to submit elements (tx, rx, cmd) to hw.
+ * Driver is the producer that advances prod_idx. cons_idx is advanced when
+ * HW reports completions of previously submitted elements.
+ */
+struct hinic3_wq {
+	struct hinic3_queue_pages qpages;
+	/* Unmasked producer/consumer indices that are advanced to natural
+	 * integer overflow regardless of queue depth.
+	 */
+	u16                       cons_idx;
+	u16                       prod_idx;
+
+	u32                       q_depth;
+	u16                       idx_mask;
+
+	/* Work Queue (logical WQEBB array) is mapped to hw via Chip Logical
+	 * Address (CLA) using 1 of 2 levels:
+	 *     level 0 - direct mapping of single wq page
+	 *     level 1 - indirect mapping of multiple pages via additional page
+	 *               table.
+	 * When wq uses level 1, wq_block will hold the allocated indirection
+	 * table.
+	 */
+	dma_addr_t                wq_block_paddr;
+	__be64                    *wq_block_vaddr;
+} ____cacheline_aligned;
+
+/* Get number of elements in work queue that are in-use. */
+static inline u16 hinic3_wq_get_used(const struct hinic3_wq *wq)
+{
+	return wq->prod_idx - wq->cons_idx;
+}
+
+static inline u16 hinic3_wq_free_wqebbs(struct hinic3_wq *wq)
+{
+	/* Don't allow queue to become completely full, report (free - 1). */
+	return wq->q_depth - hinic3_wq_get_used(wq) - 1;
+}
+
+static inline void *hinic3_wq_get_one_wqebb(struct hinic3_wq *wq, u16 *pi)
+{
+	*pi = wq->prod_idx & wq->idx_mask;
+	wq->prod_idx++;
+	return get_q_element(&wq->qpages, *pi, NULL);
+}
+
+static inline void hinic3_wq_put_wqebbs(struct hinic3_wq *wq, u16 num_wqebbs)
+{
+	wq->cons_idx += num_wqebbs;
+}
+
+void hinic3_wq_get_multi_wqebbs(struct hinic3_wq *wq,
+				u16 num_wqebbs, u16 *prod_idx,
+				struct hinic3_sq_bufdesc **first_wqebb,
+				struct hinic3_sq_bufdesc **second_part_wqebbs_addr,
+				u16 *first_part_wqebbs_num);
+
+#endif

From efff3273f068e30074c87c495c64a8f3a0f11dd4 Mon Sep 17 00:00:00 2001
From: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Date: Mon, 17 Mar 2025 10:27:17 +0100
Subject: [PATCH 2509/2753] MAINTAINERS: adjust the file entry in INTEL PMC
 CORE DRIVER
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit 7e2f7e25f6ff ("arch: x86: add IPC mailbox accessor function and add
SoC register access") adds a new file entry referring to the non-existent
file linux/platform_data/x86/intel_pmc_ipc.h in section INTEL PMC CORE
DRIVER rather than referring to the file
include/linux/platform_data/x86/intel_pmc_ipc.h added with this commit.
Note that it was missing 'include' in the beginning.

Adjust the file reference to the intended file.

Signed-off-by: Lukas Bulwahn <lukas.bulwahn@redhat.com>
Acked-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 3cf5f4729fe66..176ae661812f8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11882,7 +11882,7 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	Documentation/ABI/testing/sysfs-platform-intel-pmc
 F:	drivers/platform/x86/intel/pmc/
-F:	linux/platform_data/x86/intel_pmc_ipc.h
+F:	include/linux/platform_data/x86/intel_pmc_ipc.h
 
 INTEL PMIC GPIO DRIVERS
 M:	Andy Shevchenko <andy@kernel.org>

From df7a405565c926e06fcfb87f081c163e612cadb5 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Mon, 17 Mar 2025 12:24:19 +0200
Subject: [PATCH 2510/2753] rtnetlink: Allocate vfinfo size for VF GUIDs when
 supported

Commit 30aad41721e0 ("net/core: Add support for getting VF GUIDs")
added support for getting VF port and node GUIDs in netlink ifinfo
messages, but their size was not taken into consideration in the
function that allocates the netlink message, causing the following
warning when a netlink message is filled with many VF port and node
GUIDs:
 # echo 64 > /sys/bus/pci/devices/0000\:08\:00.0/sriov_numvfs
 # ip link show dev ib0
 RTNETLINK answers: Message too long
 Cannot send link get request: Message too long

Kernel warning:

 ------------[ cut here ]------------
 WARNING: CPU: 2 PID: 1930 at net/core/rtnetlink.c:4151 rtnl_getlink+0x586/0x5a0
 Modules linked in: xt_conntrack xt_MASQUERADE nfnetlink xt_addrtype iptable_nat nf_nat br_netfilter overlay mlx5_ib macsec mlx5_core tls rpcrdma rdma_ucm ib_uverbs ib_iser libiscsi scsi_transport_iscsi ib_umad rdma_cm iw_cm ib_ipoib fuse ib_cm ib_core
 CPU: 2 UID: 0 PID: 1930 Comm: ip Not tainted 6.14.0-rc2+ #1
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.13.0-0-gf21b5a4aeb02-prebuilt.qemu.org 04/01/2014
 RIP: 0010:rtnl_getlink+0x586/0x5a0
 Code: cb 82 e8 3d af 0a 00 4d 85 ff 0f 84 08 ff ff ff 4c 89 ff 41 be ea ff ff ff e8 66 63 5b ff 49 c7 07 80 4f cb 82 e9 36 fc ff ff <0f> 0b e9 16 fe ff ff e8 de a0 56 00 66 66 2e 0f 1f 84 00 00 00 00
 RSP: 0018:ffff888113557348 EFLAGS: 00010246
 RAX: 00000000ffffffa6 RBX: ffff88817e87aa34 RCX: dffffc0000000000
 RDX: 0000000000000003 RSI: 0000000000000000 RDI: ffff88817e87afb8
 RBP: 0000000000000009 R08: ffffffff821f44aa R09: 0000000000000000
 R10: ffff8881260f79a8 R11: ffff88817e87af00 R12: ffff88817e87aa00
 R13: ffffffff8563d300 R14: 00000000ffffffa6 R15: 00000000ffffffff
 FS:  00007f63a5dbf280(0000) GS:ffff88881ee00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007f63a5ba4493 CR3: 00000001700fe002 CR4: 0000000000772eb0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  <TASK>
  ? __warn+0xa5/0x230
  ? rtnl_getlink+0x586/0x5a0
  ? report_bug+0x22d/0x240
  ? handle_bug+0x53/0xa0
  ? exc_invalid_op+0x14/0x50
  ? asm_exc_invalid_op+0x16/0x20
  ? skb_trim+0x6a/0x80
  ? rtnl_getlink+0x586/0x5a0
  ? __pfx_rtnl_getlink+0x10/0x10
  ? rtnetlink_rcv_msg+0x1e5/0x860
  ? __pfx___mutex_lock+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? __pfx_lock_acquire+0x10/0x10
  ? stack_trace_save+0x90/0xd0
  ? filter_irq_stacks+0x1d/0x70
  ? kasan_save_stack+0x30/0x40
  ? kasan_save_stack+0x20/0x40
  ? kasan_save_track+0x10/0x30
  rtnetlink_rcv_msg+0x21c/0x860
  ? entry_SYSCALL_64_after_hwframe+0x76/0x7e
  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
  ? arch_stack_walk+0x9e/0xf0
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd5/0x410
  ? rcu_is_watching+0x34/0x60
  netlink_rcv_skb+0xe0/0x210
  ? __pfx_rtnetlink_rcv_msg+0x10/0x10
  ? __pfx_netlink_rcv_skb+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? __pfx___netlink_lookup+0x10/0x10
  ? lock_release+0x62/0x200
  ? netlink_deliver_tap+0xfd/0x290
  ? rcu_is_watching+0x34/0x60
  ? lock_release+0x62/0x200
  ? netlink_deliver_tap+0x95/0x290
  netlink_unicast+0x31f/0x480
  ? __pfx_netlink_unicast+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? lock_acquire+0xd5/0x410
  netlink_sendmsg+0x369/0x660
  ? lock_release+0x62/0x200
  ? __pfx_netlink_sendmsg+0x10/0x10
  ? import_ubuf+0xb9/0xf0
  ? __import_iovec+0x254/0x2b0
  ? lock_release+0x62/0x200
  ? __pfx_netlink_sendmsg+0x10/0x10
  ____sys_sendmsg+0x559/0x5a0
  ? __pfx_____sys_sendmsg+0x10/0x10
  ? __pfx_copy_msghdr_from_user+0x10/0x10
  ? rcu_is_watching+0x34/0x60
  ? do_read_fault+0x213/0x4a0
  ? rcu_is_watching+0x34/0x60
  ___sys_sendmsg+0xe4/0x150
  ? __pfx____sys_sendmsg+0x10/0x10
  ? do_fault+0x2cc/0x6f0
  ? handle_pte_fault+0x2e3/0x3d0
  ? __pfx_handle_pte_fault+0x10/0x10
  ? preempt_count_sub+0x14/0xc0
  ? __down_read_trylock+0x150/0x270
  ? __handle_mm_fault+0x404/0x8e0
  ? __pfx___handle_mm_fault+0x10/0x10
  ? lock_release+0x62/0x200
  ? __rcu_read_unlock+0x65/0x90
  ? rcu_is_watching+0x34/0x60
  __sys_sendmsg+0xd5/0x150
  ? __pfx___sys_sendmsg+0x10/0x10
  ? __up_read+0x192/0x480
  ? lock_release+0x62/0x200
  ? __rcu_read_unlock+0x65/0x90
  ? rcu_is_watching+0x34/0x60
  do_syscall_64+0x6d/0x140
  entry_SYSCALL_64_after_hwframe+0x76/0x7e
 RIP: 0033:0x7f63a5b13367
 Code: 0e 00 f7 d8 64 89 02 48 c7 c0 ff ff ff ff eb b9 0f 1f 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 51 c3 48 83 ec 28 89 54 24 1c 48 89 74 24 10
 RSP: 002b:00007fff8c726bc8 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
 RAX: ffffffffffffffda RBX: 0000000067b687c2 RCX: 00007f63a5b13367
 RDX: 0000000000000000 RSI: 00007fff8c726c30 RDI: 0000000000000004
 RBP: 00007fff8c726cb8 R08: 0000000000000000 R09: 0000000000000034
 R10: 00007fff8c726c7c R11: 0000000000000246 R12: 0000000000000001
 R13: 0000000000000000 R14: 00007fff8c726cd0 R15: 00007fff8c726cd0
  </TASK>
 irq event stamp: 0
 hardirqs last  enabled at (0): [<0000000000000000>] 0x0
 hardirqs last disabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830
 softirqs last  enabled at (0): [<ffffffff813f9e58>] copy_process+0xd08/0x2830
 softirqs last disabled at (0): [<0000000000000000>] 0x0
 ---[ end trace 0000000000000000 ]---

Thus, when calculating ifinfo message size, take VF GUIDs sizes into
account when supported.

Fixes: 30aad41721e0 ("net/core: Add support for getting VF GUIDs")
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/rtnetlink.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 5a24a30dfc2d1..9d05943dbf38d 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1156,7 +1156,9 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev,
 			 nla_total_size(sizeof(struct ifla_vf_rate)) +
 			 nla_total_size(sizeof(struct ifla_vf_link_state)) +
 			 nla_total_size(sizeof(struct ifla_vf_rss_query_en)) +
-			 nla_total_size(sizeof(struct ifla_vf_trust)));
+			 nla_total_size(sizeof(struct ifla_vf_trust)) +
+			 (dev->netdev_ops->ndo_get_vf_guid ?
+			  nla_total_size(sizeof(struct ifla_vf_guid)) * 2 : 0));
 		if (~ext_filter_mask & RTEXT_FILTER_SKIP_STATS) {
 			size += num_vfs *
 				(nla_total_size(0) + /* nest IFLA_VF_STATS */

From e8638d20b8cfd23ec278fe3aac071b1dbbf5c38f Mon Sep 17 00:00:00 2001
From: Murad Masimov <m.masimov@mt-integration.ru>
Date: Mon, 17 Mar 2025 13:53:52 +0300
Subject: [PATCH 2511/2753] ax25: Remove broken autobind

Binding AX25 socket by using the autobind feature leads to memory leaks
in ax25_connect() and also refcount leaks in ax25_release(). Memory
leak was detected with kmemleak:

================================================================
unreferenced object 0xffff8880253cd680 (size 96):
backtrace:
__kmalloc_node_track_caller_noprof (./include/linux/kmemleak.h:43)
kmemdup_noprof (mm/util.c:136)
ax25_rt_autobind (net/ax25/ax25_route.c:428)
ax25_connect (net/ax25/af_ax25.c:1282)
__sys_connect_file (net/socket.c:2045)
__sys_connect (net/socket.c:2064)
__x64_sys_connect (net/socket.c:2067)
do_syscall_64 (arch/x86/entry/common.c:52 arch/x86/entry/common.c:83)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
================================================================

When socket is bound, refcounts must be incremented the way it is done
in ax25_bind() and ax25_setsockopt() (SO_BINDTODEVICE). In case of
autobind, the refcounts are not incremented.

This bug leads to the following issue reported by Syzkaller:

================================================================
ax25_connect(): syz-executor318 uses autobind, please contact jreuter@yaina.de
------------[ cut here ]------------
refcount_t: decrement hit 0; leaking memory.
WARNING: CPU: 0 PID: 5317 at lib/refcount.c:31 refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31
Modules linked in:
CPU: 0 UID: 0 PID: 5317 Comm: syz-executor318 Not tainted 6.14.0-rc4-syzkaller-00278-gece144f151ac #0
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2~bpo12+1 04/01/2014
RIP: 0010:refcount_warn_saturate+0xfa/0x1d0 lib/refcount.c:31
...
Call Trace:
 <TASK>
 __refcount_dec include/linux/refcount.h:336 [inline]
 refcount_dec include/linux/refcount.h:351 [inline]
 ref_tracker_free+0x6af/0x7e0 lib/ref_tracker.c:236
 netdev_tracker_free include/linux/netdevice.h:4302 [inline]
 netdev_put include/linux/netdevice.h:4319 [inline]
 ax25_release+0x368/0x960 net/ax25/af_ax25.c:1080
 __sock_release net/socket.c:647 [inline]
 sock_close+0xbc/0x240 net/socket.c:1398
 __fput+0x3e9/0x9f0 fs/file_table.c:464
 __do_sys_close fs/open.c:1580 [inline]
 __se_sys_close fs/open.c:1565 [inline]
 __x64_sys_close+0x7f/0x110 fs/open.c:1565
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
 ...
 </TASK>
================================================================

Considering the issues above and the comments left in the code that say:
"check if we can remove this feature. It is broken."; "autobinding in this
may or may not work"; - it is better to completely remove this feature than
to fix it because it is broken and leads to various kinds of memory bugs.

Now calling connect() without first binding socket will result in an
error (-EINVAL). Userspace software that relies on the autobind feature
might get broken. However, this feature does not seem widely used with
this specific driver as it was not reliable at any point of time, and it
is already broken anyway. E.g. ax25-tools and ax25-apps packages for
popular distributions do not use the autobind feature for AF_AX25.

Found by Linux Verification Center (linuxtesting.org) with Syzkaller.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: syzbot+33841dc6aa3e1d86b78a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=33841dc6aa3e1d86b78a
Signed-off-by: Murad Masimov <m.masimov@mt-integration.ru>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/ax25.h    |  1 -
 net/ax25/af_ax25.c    | 30 ++++++------------
 net/ax25/ax25_route.c | 74 -------------------------------------------
 3 files changed, 10 insertions(+), 95 deletions(-)

diff --git a/include/net/ax25.h b/include/net/ax25.h
index 4ee141aae0a29..a7bba42dde153 100644
--- a/include/net/ax25.h
+++ b/include/net/ax25.h
@@ -418,7 +418,6 @@ void ax25_rt_device_down(struct net_device *);
 int ax25_rt_ioctl(unsigned int, void __user *);
 extern const struct seq_operations ax25_rt_seqops;
 ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev);
-int ax25_rt_autobind(ax25_cb *, ax25_address *);
 struct sk_buff *ax25_rt_build_path(struct sk_buff *, ax25_address *,
 				   ax25_address *, ax25_digi *);
 void ax25_rt_free(void);
diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 9f3b8b682adb2..3ee7dba343100 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -1270,28 +1270,18 @@ static int __must_check ax25_connect(struct socket *sock,
 		}
 	}
 
-	/*
-	 *	Must bind first - autobinding in this may or may not work. If
-	 *	the socket is already bound, check to see if the device has
-	 *	been filled in, error if it hasn't.
-	 */
+	/* Must bind first - autobinding does not work. */
 	if (sock_flag(sk, SOCK_ZAPPED)) {
-		/* check if we can remove this feature. It is broken. */
-		printk(KERN_WARNING "ax25_connect(): %s uses autobind, please contact jreuter@yaina.de\n",
-			current->comm);
-		if ((err = ax25_rt_autobind(ax25, &fsa->fsa_ax25.sax25_call)) < 0) {
-			kfree(digi);
-			goto out_release;
-		}
+		kfree(digi);
+		err = -EINVAL;
+		goto out_release;
+	}
 
-		ax25_fillin_cb(ax25, ax25->ax25_dev);
-		ax25_cb_add(ax25);
-	} else {
-		if (ax25->ax25_dev == NULL) {
-			kfree(digi);
-			err = -EHOSTUNREACH;
-			goto out_release;
-		}
+	/* Check to see if the device has been filled in, error if it hasn't. */
+	if (ax25->ax25_dev == NULL) {
+		kfree(digi);
+		err = -EHOSTUNREACH;
+		goto out_release;
 	}
 
 	if (sk->sk_type == SOCK_SEQPACKET &&
diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c
index 69de75db0c9c2..10577434f40bf 100644
--- a/net/ax25/ax25_route.c
+++ b/net/ax25/ax25_route.c
@@ -373,80 +373,6 @@ ax25_route *ax25_get_route(ax25_address *addr, struct net_device *dev)
 	return ax25_rt;
 }
 
-/*
- *	Adjust path: If you specify a default route and want to connect
- *      a target on the digipeater path but w/o having a special route
- *	set before, the path has to be truncated from your target on.
- */
-static inline void ax25_adjust_path(ax25_address *addr, ax25_digi *digipeat)
-{
-	int k;
-
-	for (k = 0; k < digipeat->ndigi; k++) {
-		if (ax25cmp(addr, &digipeat->calls[k]) == 0)
-			break;
-	}
-
-	digipeat->ndigi = k;
-}
-
-
-/*
- *	Find which interface to use.
- */
-int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr)
-{
-	ax25_uid_assoc *user;
-	ax25_route *ax25_rt;
-	int err = 0;
-
-	ax25_route_lock_use();
-	ax25_rt = ax25_get_route(addr, NULL);
-	if (!ax25_rt) {
-		ax25_route_lock_unuse();
-		return -EHOSTUNREACH;
-	}
-	rcu_read_lock();
-	if ((ax25->ax25_dev = ax25_dev_ax25dev(ax25_rt->dev)) == NULL) {
-		err = -EHOSTUNREACH;
-		goto put;
-	}
-
-	user = ax25_findbyuid(current_euid());
-	if (user) {
-		ax25->source_addr = user->call;
-		ax25_uid_put(user);
-	} else {
-		if (ax25_uid_policy && !capable(CAP_NET_BIND_SERVICE)) {
-			err = -EPERM;
-			goto put;
-		}
-		ax25->source_addr = *(ax25_address *)ax25->ax25_dev->dev->dev_addr;
-	}
-
-	if (ax25_rt->digipeat != NULL) {
-		ax25->digipeat = kmemdup(ax25_rt->digipeat, sizeof(ax25_digi),
-					 GFP_ATOMIC);
-		if (ax25->digipeat == NULL) {
-			err = -ENOMEM;
-			goto put;
-		}
-		ax25_adjust_path(addr, ax25->digipeat);
-	}
-
-	if (ax25->sk != NULL) {
-		local_bh_disable();
-		bh_lock_sock(ax25->sk);
-		sock_reset_flag(ax25->sk, SOCK_ZAPPED);
-		bh_unlock_sock(ax25->sk);
-		local_bh_enable();
-	}
-
-put:
-	rcu_read_unlock();
-	ax25_route_lock_unuse();
-	return err;
-}
 
 struct sk_buff *ax25_rt_build_path(struct sk_buff *skb, ax25_address *src,
 	ax25_address *dest, ax25_digi *digi)

From 1ed2268f7f50687461391fd4184ea4c0351beedc Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:51 +0900
Subject: [PATCH 2512/2753] virtio_net: Add functions for hashing

They are useful to implement VIRTIO_NET_F_RSS and
VIRTIO_NET_F_HASH_REPORT.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/virtio_net.h | 188 +++++++++++++++++++++++++++++++++++++
 1 file changed, 188 insertions(+)

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 02a9f4dc594d0..426f33b4b8244 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -9,6 +9,194 @@
 #include <uapi/linux/tcp.h>
 #include <uapi/linux/virtio_net.h>
 
+struct virtio_net_hash {
+	u32 value;
+	u16 report;
+};
+
+struct virtio_net_toeplitz_state {
+	u32 hash;
+	const u32 *key;
+};
+
+#define VIRTIO_NET_SUPPORTED_HASH_TYPES (VIRTIO_NET_RSS_HASH_TYPE_IPv4 | \
+					 VIRTIO_NET_RSS_HASH_TYPE_TCPv4 | \
+					 VIRTIO_NET_RSS_HASH_TYPE_UDPv4 | \
+					 VIRTIO_NET_RSS_HASH_TYPE_IPv6 | \
+					 VIRTIO_NET_RSS_HASH_TYPE_TCPv6 | \
+					 VIRTIO_NET_RSS_HASH_TYPE_UDPv6)
+
+#define VIRTIO_NET_RSS_MAX_KEY_SIZE 40
+
+static inline void virtio_net_toeplitz_convert_key(u32 *input, size_t len)
+{
+	while (len >= sizeof(*input)) {
+		*input = be32_to_cpu((__force __be32)*input);
+		input++;
+		len -= sizeof(*input);
+	}
+}
+
+static inline void virtio_net_toeplitz_calc(struct virtio_net_toeplitz_state *state,
+					    const __be32 *input, size_t len)
+{
+	while (len >= sizeof(*input)) {
+		for (u32 map = be32_to_cpu(*input); map; map &= (map - 1)) {
+			u32 i = ffs(map);
+
+			state->hash ^= state->key[0] << (32 - i) |
+				       (u32)((u64)state->key[1] >> i);
+		}
+
+		state->key++;
+		input++;
+		len -= sizeof(*input);
+	}
+}
+
+static inline u8 virtio_net_hash_key_length(u32 types)
+{
+	size_t len = 0;
+
+	if (types & VIRTIO_NET_HASH_REPORT_IPv4)
+		len = max(len,
+			  sizeof(struct flow_dissector_key_ipv4_addrs));
+
+	if (types &
+	    (VIRTIO_NET_HASH_REPORT_TCPv4 | VIRTIO_NET_HASH_REPORT_UDPv4))
+		len = max(len,
+			  sizeof(struct flow_dissector_key_ipv4_addrs) +
+			  sizeof(struct flow_dissector_key_ports));
+
+	if (types & VIRTIO_NET_HASH_REPORT_IPv6)
+		len = max(len,
+			  sizeof(struct flow_dissector_key_ipv6_addrs));
+
+	if (types &
+	    (VIRTIO_NET_HASH_REPORT_TCPv6 | VIRTIO_NET_HASH_REPORT_UDPv6))
+		len = max(len,
+			  sizeof(struct flow_dissector_key_ipv6_addrs) +
+			  sizeof(struct flow_dissector_key_ports));
+
+	return len + sizeof(u32);
+}
+
+static inline u32 virtio_net_hash_report(u32 types,
+					 const struct flow_keys_basic *keys)
+{
+	switch (keys->basic.n_proto) {
+	case cpu_to_be16(ETH_P_IP):
+		if (!(keys->control.flags & FLOW_DIS_IS_FRAGMENT)) {
+			if (keys->basic.ip_proto == IPPROTO_TCP &&
+			    (types & VIRTIO_NET_RSS_HASH_TYPE_TCPv4))
+				return VIRTIO_NET_HASH_REPORT_TCPv4;
+
+			if (keys->basic.ip_proto == IPPROTO_UDP &&
+			    (types & VIRTIO_NET_RSS_HASH_TYPE_UDPv4))
+				return VIRTIO_NET_HASH_REPORT_UDPv4;
+		}
+
+		if (types & VIRTIO_NET_RSS_HASH_TYPE_IPv4)
+			return VIRTIO_NET_HASH_REPORT_IPv4;
+
+		return VIRTIO_NET_HASH_REPORT_NONE;
+
+	case cpu_to_be16(ETH_P_IPV6):
+		if (!(keys->control.flags & FLOW_DIS_IS_FRAGMENT)) {
+			if (keys->basic.ip_proto == IPPROTO_TCP &&
+			    (types & VIRTIO_NET_RSS_HASH_TYPE_TCPv6))
+				return VIRTIO_NET_HASH_REPORT_TCPv6;
+
+			if (keys->basic.ip_proto == IPPROTO_UDP &&
+			    (types & VIRTIO_NET_RSS_HASH_TYPE_UDPv6))
+				return VIRTIO_NET_HASH_REPORT_UDPv6;
+		}
+
+		if (types & VIRTIO_NET_RSS_HASH_TYPE_IPv6)
+			return VIRTIO_NET_HASH_REPORT_IPv6;
+
+		return VIRTIO_NET_HASH_REPORT_NONE;
+
+	default:
+		return VIRTIO_NET_HASH_REPORT_NONE;
+	}
+}
+
+static inline void virtio_net_hash_rss(const struct sk_buff *skb,
+				       u32 types, const u32 *key,
+				       struct virtio_net_hash *hash)
+{
+	struct virtio_net_toeplitz_state toeplitz_state = { .key = key };
+	struct flow_keys flow;
+	struct flow_keys_basic flow_basic;
+	u16 report;
+
+	if (!skb_flow_dissect_flow_keys(skb, &flow, 0)) {
+		hash->report = VIRTIO_NET_HASH_REPORT_NONE;
+		return;
+	}
+
+	flow_basic = (struct flow_keys_basic) {
+		.control = flow.control,
+		.basic = flow.basic
+	};
+
+	report = virtio_net_hash_report(types, &flow_basic);
+
+	switch (report) {
+	case VIRTIO_NET_HASH_REPORT_IPv4:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v4addrs,
+					 sizeof(flow.addrs.v4addrs));
+		break;
+
+	case VIRTIO_NET_HASH_REPORT_TCPv4:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v4addrs,
+					 sizeof(flow.addrs.v4addrs));
+		virtio_net_toeplitz_calc(&toeplitz_state, &flow.ports.ports,
+					 sizeof(flow.ports.ports));
+		break;
+
+	case VIRTIO_NET_HASH_REPORT_UDPv4:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v4addrs,
+					 sizeof(flow.addrs.v4addrs));
+		virtio_net_toeplitz_calc(&toeplitz_state, &flow.ports.ports,
+					 sizeof(flow.ports.ports));
+		break;
+
+	case VIRTIO_NET_HASH_REPORT_IPv6:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v6addrs,
+					 sizeof(flow.addrs.v6addrs));
+		break;
+
+	case VIRTIO_NET_HASH_REPORT_TCPv6:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v6addrs,
+					 sizeof(flow.addrs.v6addrs));
+		virtio_net_toeplitz_calc(&toeplitz_state, &flow.ports.ports,
+					 sizeof(flow.ports.ports));
+		break;
+
+	case VIRTIO_NET_HASH_REPORT_UDPv6:
+		virtio_net_toeplitz_calc(&toeplitz_state,
+					 (__be32 *)&flow.addrs.v6addrs,
+					 sizeof(flow.addrs.v6addrs));
+		virtio_net_toeplitz_calc(&toeplitz_state, &flow.ports.ports,
+					 sizeof(flow.ports.ports));
+		break;
+
+	default:
+		hash->report = VIRTIO_NET_HASH_REPORT_NONE;
+		return;
+	}
+
+	hash->value = toeplitz_state.hash;
+	hash->report = report;
+}
+
 static inline bool virtio_net_hdr_match_proto(__be16 protocol, __u8 gso_type)
 {
 	switch (gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {

From 839b75b90bd2261d6b964cc137fa74222839585a Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:52 +0900
Subject: [PATCH 2513/2753] net: flow_dissector: Export
 flow_keys_dissector_symmetric

flow_keys_dissector_symmetric is useful to derive a symmetric hash
and to know its source such as IPv4, IPv6, TCP, and UDP.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/flow_dissector.h | 1 +
 net/core/flow_dissector.c    | 3 ++-
 2 files changed, 3 insertions(+), 1 deletion(-)

diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h
index ced79dc8e8560..d01c1ec77b7d2 100644
--- a/include/net/flow_dissector.h
+++ b/include/net/flow_dissector.h
@@ -423,6 +423,7 @@ __be32 flow_get_u32_src(const struct flow_keys *flow);
 __be32 flow_get_u32_dst(const struct flow_keys *flow);
 
 extern struct flow_dissector flow_keys_dissector;
+extern struct flow_dissector flow_keys_dissector_symmetric;
 extern struct flow_dissector flow_keys_basic_dissector;
 
 /* struct flow_keys_digest:
diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
index 1b61bb25ba0e5..12a384f37b992 100644
--- a/net/core/flow_dissector.c
+++ b/net/core/flow_dissector.c
@@ -1862,7 +1862,8 @@ void make_flow_keys_digest(struct flow_keys_digest *digest,
 }
 EXPORT_SYMBOL(make_flow_keys_digest);
 
-static struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+struct flow_dissector flow_keys_dissector_symmetric __read_mostly;
+EXPORT_SYMBOL(flow_keys_dissector_symmetric);
 
 u32 __skb_get_hash_symmetric_net(const struct net *net, const struct sk_buff *skb)
 {

From 31469f8b3c0164972aa6b03a01a2b56e5485da60 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:53 +0900
Subject: [PATCH 2514/2753] tun: Allow steering eBPF program to fall back

This clarifies a steering eBPF program takes precedence over the other
steering algorithms.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/tuntap.rst |  7 +++++++
 drivers/net/tun.c                   | 28 +++++++++++++++++-----------
 include/uapi/linux/if_tun.h         |  9 +++++++++
 3 files changed, 33 insertions(+), 11 deletions(-)

diff --git a/Documentation/networking/tuntap.rst b/Documentation/networking/tuntap.rst
index 4d7087f727be5..86b4ae8caa8ad 100644
--- a/Documentation/networking/tuntap.rst
+++ b/Documentation/networking/tuntap.rst
@@ -206,6 +206,13 @@ enable is true we enable it, otherwise we disable it::
       return ioctl(fd, TUNSETQUEUE, (void *)&ifr);
   }
 
+3.4 Reference
+-------------
+
+``linux/if_tun.h`` defines the interface described below:
+
+.. kernel-doc:: include/uapi/linux/if_tun.h
+
 Universal TUN/TAP device driver Frequently Asked Question
 =========================================================
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f75f912a0225f..5407eff482eea 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -476,21 +476,29 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 	return txq;
 }
 
-static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb)
+static bool tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb,
+				  u16 *ret)
 {
 	struct tun_prog *prog;
 	u32 numqueues;
-	u16 ret = 0;
+	u32 prog_ret;
+
+	prog = rcu_dereference(tun->steering_prog);
+	if (!prog)
+		return false;
 
 	numqueues = READ_ONCE(tun->numqueues);
-	if (!numqueues)
-		return 0;
+	if (!numqueues) {
+		*ret = 0;
+		return true;
+	}
 
-	prog = rcu_dereference(tun->steering_prog);
-	if (prog)
-		ret = bpf_prog_run_clear_cb(prog->prog, skb);
+	prog_ret = bpf_prog_run_clear_cb(prog->prog, skb);
+	if (prog_ret == TUN_STEERINGEBPF_FALLBACK)
+		return false;
 
-	return ret % numqueues;
+	*ret = (u16)prog_ret % numqueues;
+	return true;
 }
 
 static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
@@ -500,9 +508,7 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
 	u16 ret;
 
 	rcu_read_lock();
-	if (rcu_dereference(tun->steering_prog))
-		ret = tun_ebpf_select_queue(tun, skb);
-	else
+	if (!tun_ebpf_select_queue(tun, skb, &ret))
 		ret = tun_automq_select_queue(tun, skb);
 	rcu_read_unlock();
 
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 287cdc81c9390..980de74724fc4 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -115,4 +115,13 @@ struct tun_filter {
 	__u8   addr[][ETH_ALEN];
 };
 
+/**
+ * define TUN_STEERINGEBPF_FALLBACK - A steering eBPF return value to fall back
+ *
+ * A steering eBPF program may return this value to fall back to the steering
+ * algorithm that should have been used if the program was not set. This allows
+ * selectively overriding the steering decision.
+ */
+#define TUN_STEERINGEBPF_FALLBACK -1
+
 #endif /* _UAPI__IF_TUN_H */

From 2500c9b8146152d0c1f1f82c420bf3a4e43acc8c Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:54 +0900
Subject: [PATCH 2515/2753] tun: Add common virtio-net hash feature code

Add common code required for the features being added to TUN and TAP.
They will be enabled for each of them in following patches.

Added Features
==============

Hash reporting
--------------

Allow the guest to reuse the hash value to make receive steering
consistent between the host and guest, and to save hash computation.

Receive Side Scaling (RSS)
--------------------------

RSS is a receive steering algorithm that can be negotiated to use with
virtio_net. Conventionally the hash calculation was done by the VMM.
However, computing the hash after the queue was chosen defeats the
purpose of RSS.

Another approach is to use eBPF steering program. This approach has
another downside: it cannot report the calculated hash due to the
restrictive nature of eBPF steering program.

Introduce the code to perform RSS to the kernel in order to overcome
thse challenges. An alternative solution is to extend the eBPF steering
program so that it will be able to report to the userspace, but I didn't
opt for it because extending the current mechanism of eBPF steering
program as is because it relies on legacy context rewriting, and
introducing kfunc-based eBPF will result in non-UAPI dependency while
the other relevant virtualization APIs such as KVM and vhost_net are
UAPIs.

Added ioctls
============

They are designed to make extensibility and VM migration compatible.
This change only adds the implementation and does not expose them to
the userspace.

TUNGETVNETHASHCAP
-----------------

This ioctl tells supported features and hash types. It is useful to
check if a VM can be migrated to the current host.

TUNSETVNETHASH
--------------

This ioctl allows setting features and hash types to be enabled. It
limits the features exposed to the guest to ensure proper migration. It
also sets RSS parameters, depending on the enabled features and hash
types.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/tap.c           |  10 ++-
 drivers/net/tun.c           |  12 ++-
 drivers/net/tun_vnet.h      | 155 +++++++++++++++++++++++++++++++++---
 include/uapi/linux/if_tun.h |  73 +++++++++++++++++
 4 files changed, 236 insertions(+), 14 deletions(-)

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index d4ece538f1b23..25c60ff2d3f28 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -179,6 +179,11 @@ static void tap_put_queue(struct tap_queue *q)
 	sock_put(&q->sk);
 }
 
+static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
+{
+	return NULL;
+}
+
 /*
  * Select a queue based on the rxq of the device on which this packet
  * arrived. If the incoming device is not mq, calculate a flow hash
@@ -711,11 +716,12 @@ static ssize_t tap_put_user(struct tap_queue *q,
 	int total;
 
 	if (q->flags & IFF_VNET_HDR) {
-		struct virtio_net_hdr vnet_hdr;
+		struct virtio_net_hdr_v1_hash vnet_hdr;
 
 		vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
 
-		ret = tun_vnet_hdr_from_skb(q->flags, NULL, skb, &vnet_hdr);
+		ret = tun_vnet_hdr_from_skb(vnet_hdr_len, q->flags, NULL, skb,
+					    tap_find_hash, &vnet_hdr);
 		if (ret)
 			return ret;
 
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 5407eff482eea..9906659765e93 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -451,6 +451,11 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
 		e->rps_rxhash = hash;
 }
 
+static const struct virtio_net_hash *tun_find_hash(const struct sk_buff *skb)
+{
+	return NULL;
+}
+
 /* We try to identify a flow through its rxhash. The reason that
  * we do not check rxq no. is because some cards(e.g 82599), chooses
  * the rxq based on the txq where the last packet of the flow comes. As
@@ -2003,7 +2008,7 @@ static ssize_t tun_put_user_xdp(struct tun_struct *tun,
 	ssize_t ret;
 
 	if (tun->flags & IFF_VNET_HDR) {
-		struct virtio_net_hdr gso = { 0 };
+		struct virtio_net_hdr_v1_hash gso = { 0 };
 
 		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
 		ret = tun_vnet_hdr_put(vnet_hdr_sz, iter, &gso);
@@ -2056,9 +2061,10 @@ static ssize_t tun_put_user(struct tun_struct *tun,
 	}
 
 	if (vnet_hdr_sz) {
-		struct virtio_net_hdr gso;
+		struct virtio_net_hdr_v1_hash gso;
 
-		ret = tun_vnet_hdr_from_skb(tun->flags, tun->dev, skb, &gso);
+		ret = tun_vnet_hdr_from_skb(vnet_hdr_sz, tun->flags, tun->dev,
+					    skb, tun_find_hash, &gso);
 		if (ret)
 			return ret;
 
diff --git a/drivers/net/tun_vnet.h b/drivers/net/tun_vnet.h
index 58b9ac7a5fc40..578adaac0671c 100644
--- a/drivers/net/tun_vnet.h
+++ b/drivers/net/tun_vnet.h
@@ -6,6 +6,16 @@
 #define TUN_VNET_LE     0x80000000
 #define TUN_VNET_BE     0x40000000
 
+typedef struct virtio_net_hash *(*tun_vnet_hash_add)(struct sk_buff *);
+typedef const struct virtio_net_hash *(*tun_vnet_hash_find)(const struct sk_buff *);
+
+struct tun_vnet_hash_container {
+	struct tun_vnet_hash common;
+	struct tun_vnet_hash_rss rss;
+	u32 rss_key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
+	u16 rss_indirection_table[];
+};
+
 static inline bool tun_vnet_legacy_is_little_endian(unsigned int flags)
 {
 	bool be = IS_ENABLED(CONFIG_TUN_VNET_CROSS_LE) &&
@@ -107,6 +117,119 @@ static inline long tun_vnet_ioctl(int *vnet_hdr_sz, unsigned int *flags,
 	}
 }
 
+static inline long tun_vnet_ioctl_gethashcap(void __user *argp)
+{
+	static const struct tun_vnet_hash cap = {
+		.flags = TUN_VNET_HASH_REPORT | TUN_VNET_HASH_RSS,
+		.types = VIRTIO_NET_SUPPORTED_HASH_TYPES
+	};
+
+	return copy_to_user(argp, &cap, sizeof(cap)) ? -EFAULT : 0;
+}
+
+static inline long tun_vnet_ioctl_sethash(struct tun_vnet_hash_container __rcu **hashp,
+					  void __user *argp)
+{
+	struct tun_vnet_hash hash_buf;
+	struct tun_vnet_hash_container *hash;
+
+	if (copy_from_user(&hash_buf, argp, sizeof(hash_buf)))
+		return -EFAULT;
+	argp = (struct tun_vnet_hash __user *)argp + 1;
+
+	if (hash_buf.flags & TUN_VNET_HASH_RSS) {
+		struct tun_vnet_hash_rss rss;
+		size_t indirection_table_size;
+		size_t key_size;
+		size_t size;
+
+		if (copy_from_user(&rss, argp, sizeof(rss)))
+			return -EFAULT;
+		argp = (struct tun_vnet_hash_rss __user *)argp + 1;
+
+		indirection_table_size = ((size_t)rss.indirection_table_mask + 1) * 2;
+		key_size = virtio_net_hash_key_length(hash_buf.types);
+		size = struct_size(hash, rss_indirection_table,
+				   (size_t)rss.indirection_table_mask + 1);
+
+		hash = kmalloc(size, GFP_KERNEL);
+		if (!hash)
+			return -ENOMEM;
+
+		if (copy_from_user(hash->rss_indirection_table,
+				   argp, indirection_table_size)) {
+			kfree(hash);
+			return -EFAULT;
+		}
+		argp = (u16 __user *)argp + rss.indirection_table_mask + 1;
+
+		if (copy_from_user(hash->rss_key, argp, key_size)) {
+			kfree(hash);
+			return -EFAULT;
+		}
+
+		virtio_net_toeplitz_convert_key(hash->rss_key, key_size);
+		hash->rss = rss;
+	} else {
+		hash = kmalloc(sizeof(hash->common), GFP_KERNEL);
+		if (!hash)
+			return -ENOMEM;
+	}
+
+	hash->common = hash_buf;
+	kfree_rcu_mightsleep(rcu_replace_pointer_rtnl(*hashp, hash));
+	return 0;
+}
+
+static inline void tun_vnet_hash_report(const struct tun_vnet_hash_container *hash,
+					struct sk_buff *skb,
+					const struct flow_keys_basic *keys,
+					u32 value,
+					tun_vnet_hash_add vnet_hash_add)
+{
+	struct virtio_net_hash *report;
+
+	if (!hash || !(hash->common.flags & TUN_VNET_HASH_REPORT))
+		return;
+
+	report = vnet_hash_add(skb);
+	if (!report)
+		return;
+
+	*report = (struct virtio_net_hash) {
+		.report = virtio_net_hash_report(hash->common.types, keys),
+		.value = value
+	};
+}
+
+static inline u16 tun_vnet_rss_select_queue(u32 numqueues,
+					    const struct tun_vnet_hash_container *hash,
+					    struct sk_buff *skb,
+					    tun_vnet_hash_add vnet_hash_add)
+{
+	struct virtio_net_hash *report;
+	struct virtio_net_hash ret;
+	u16 index;
+
+	if (!numqueues)
+		return 0;
+
+	virtio_net_hash_rss(skb, hash->common.types, hash->rss_key, &ret);
+
+	if (!ret.report)
+		return hash->rss.unclassified_queue % numqueues;
+
+	if (hash->common.flags & TUN_VNET_HASH_REPORT) {
+		report = vnet_hash_add(skb);
+		if (report)
+			*report = ret;
+	}
+
+	index = ret.value & hash->rss.indirection_table_mask;
+
+	return hash->rss_indirection_table[index] % numqueues;
+}
+
 static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
 				   struct iov_iter *from,
 				   struct virtio_net_hdr *hdr)
@@ -135,15 +258,17 @@ static inline int tun_vnet_hdr_get(int sz, unsigned int flags,
 }
 
 static inline int tun_vnet_hdr_put(int sz, struct iov_iter *iter,
-				   const struct virtio_net_hdr *hdr)
+				   const struct virtio_net_hdr_v1_hash *hdr)
 {
+	int content_sz = MIN(sizeof(*hdr), sz);
+
 	if (unlikely(iov_iter_count(iter) < sz))
 		return -EINVAL;
 
-	if (unlikely(copy_to_iter(hdr, sizeof(*hdr), iter) != sizeof(*hdr)))
+	if (unlikely(copy_to_iter(hdr, content_sz, iter) != content_sz))
 		return -EFAULT;
 
-	if (iov_iter_zero(sz - sizeof(*hdr), iter) != sz - sizeof(*hdr))
+	if (iov_iter_zero(sz - content_sz, iter) != sz - content_sz)
 		return -EFAULT;
 
 	return 0;
@@ -155,26 +280,38 @@ static inline int tun_vnet_hdr_to_skb(unsigned int flags, struct sk_buff *skb,
 	return virtio_net_hdr_to_skb(skb, hdr, tun_vnet_is_little_endian(flags));
 }
 
-static inline int tun_vnet_hdr_from_skb(unsigned int flags,
+static inline int tun_vnet_hdr_from_skb(int sz, unsigned int flags,
 					const struct net_device *dev,
 					const struct sk_buff *skb,
-					struct virtio_net_hdr *hdr)
+					tun_vnet_hash_find vnet_hash_find,
+					struct virtio_net_hdr_v1_hash *hdr)
 {
 	int vlan_hlen = skb_vlan_tag_present(skb) ? VLAN_HLEN : 0;
+	const struct virtio_net_hash *report = sz < sizeof(struct virtio_net_hdr_v1_hash) ?
+					       NULL : vnet_hash_find(skb);
+
+	*hdr = (struct virtio_net_hdr_v1_hash) {
+		.hash_report = VIRTIO_NET_HASH_REPORT_NONE
+	};
+
+	if (report) {
+		hdr->hash_value = cpu_to_le32(report->value);
+		hdr->hash_report = cpu_to_le16(report->report);
+	}
 
-	if (virtio_net_hdr_from_skb(skb, hdr,
+	if (virtio_net_hdr_from_skb(skb, (struct virtio_net_hdr *)hdr,
 				    tun_vnet_is_little_endian(flags), true,
 				    vlan_hlen)) {
 		struct skb_shared_info *sinfo = skb_shinfo(skb);
 
 		if (net_ratelimit()) {
 			netdev_err(dev, "unexpected GSO type: 0x%x, gso_size %d, hdr_len %d\n",
-				   sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->gso_size),
-				   tun_vnet16_to_cpu(flags, hdr->hdr_len));
+				   sinfo->gso_type, tun_vnet16_to_cpu(flags, hdr->hdr.gso_size),
+				   tun_vnet16_to_cpu(flags, hdr->hdr.hdr_len));
 			print_hex_dump(KERN_ERR, "tun: ",
 				       DUMP_PREFIX_NONE,
 				       16, 1, skb->head,
-				       min(tun_vnet16_to_cpu(flags, hdr->hdr_len), 64), true);
+				       min(tun_vnet16_to_cpu(flags, hdr->hdr.hdr_len), 64), true);
 		}
 		WARN_ON_ONCE(1);
 		return -EINVAL;
diff --git a/include/uapi/linux/if_tun.h b/include/uapi/linux/if_tun.h
index 980de74724fc4..b7b0fe69a6520 100644
--- a/include/uapi/linux/if_tun.h
+++ b/include/uapi/linux/if_tun.h
@@ -62,6 +62,42 @@
 #define TUNSETCARRIER _IOW('T', 226, int)
 #define TUNGETDEVNETNS _IO('T', 227)
 
+/**
+ * define TUNGETVNETHASHCAP - ioctl to get virtio_net hashing capability
+ *
+ * The argument is a pointer to &struct tun_vnet_hash which will store the
+ * maximal virtio_net hashing configuration.
+ */
+#define TUNGETVNETHASHCAP _IOR('T', 228, struct tun_vnet_hash)
+
+/**
+ * define TUNSETVNETHASH - ioctl to configure virtio_net hashing
+ *
+ * The argument is a pointer to &struct tun_vnet_hash.
+ *
+ * The argument is a pointer to the compound of the following in order if
+ * %TUN_VNET_HASH_RSS is set:
+ *
+ * 1. &struct tun_vnet_hash
+ * 2. &struct tun_vnet_hash_rss
+ * 3. Indirection table
+ * 4. Key
+ *
+ * The %TUN_VNET_HASH_REPORT flag set with this ioctl will be effective only
+ * after calling the %TUNSETVNETHDRSZ ioctl with a number greater than or equal
+ * to the size of &struct virtio_net_hdr_v1_hash.
+ *
+ * The members added to the legacy header by %TUN_VNET_HASH_REPORT flag will
+ * always be little-endian.
+ *
+ * This ioctl results in %EBADFD if the underlying device is deleted. It affects
+ * all queues attached to the same device.
+ *
+ * This ioctl currently has no effect on XDP packets and packets with
+ * queue_mapping set by TC.
+ */
+#define TUNSETVNETHASH _IOW('T', 229, struct tun_vnet_hash)
+
 /* TUNSETIFF ifr flags */
 #define IFF_TUN		0x0001
 #define IFF_TAP		0x0002
@@ -124,4 +160,41 @@ struct tun_filter {
  */
 #define TUN_STEERINGEBPF_FALLBACK -1
 
+/**
+ * define TUN_VNET_HASH_REPORT - Request virtio_net hash reporting for vhost
+ */
+#define TUN_VNET_HASH_REPORT	0x0001
+
+/**
+ * define TUN_VNET_HASH_RSS - Request virtio_net RSS
+ */
+#define TUN_VNET_HASH_RSS	0x0002
+
+/**
+ * struct tun_vnet_hash - virtio_net hashing configuration
+ * @flags:
+ *		Bitmask consists of %TUN_VNET_HASH_REPORT and %TUN_VNET_HASH_RSS
+ * @pad:
+ *		Should be filled with zero before passing to %TUNSETVNETHASH
+ * @types:
+ *		Bitmask of allowed hash types
+ */
+struct tun_vnet_hash {
+	__u16 flags;
+	__u8 pad[2];
+	__u32 types;
+};
+
+/**
+ * struct tun_vnet_hash_rss - virtio_net RSS configuration
+ * @indirection_table_mask:
+ *		Bitmask to be applied to the indirection table index
+ * @unclassified_queue:
+ *		The index of the queue to place unclassified packets in
+ */
+struct tun_vnet_hash_rss {
+	__u16 indirection_table_mask;
+	__u16 unclassified_queue;
+};
+
 #endif /* _UAPI__IF_TUN_H */

From bda55b9f14bc213ed0ee24636edd1c2ce5531fc4 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:55 +0900
Subject: [PATCH 2516/2753] tun: Introduce virtio-net hash feature

Add ioctls and storage required for the virtio-net hash feature to TUN.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/Kconfig    |  1 +
 drivers/net/tun.c      | 54 +++++++++++++++++++++++++++++++++++-------
 include/linux/skbuff.h |  3 +++
 net/core/skbuff.c      |  4 ++++
 4 files changed, 54 insertions(+), 8 deletions(-)

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 1fd5acdc73c6a..aecfd244dd835 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -395,6 +395,7 @@ config TUN
 	tristate "Universal TUN/TAP device driver support"
 	depends on INET
 	select CRC32
+	select SKB_EXTENSIONS
 	help
 	  TUN/TAP provides packet reception and transmission for user space
 	  programs.  It can be viewed as a simple Point-to-Point or Ethernet
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 9906659765e93..6db3a16c3964e 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -209,6 +209,7 @@ struct tun_struct {
 	struct bpf_prog __rcu *xdp_prog;
 	struct tun_prog __rcu *steering_prog;
 	struct tun_prog __rcu *filter_prog;
+	struct tun_vnet_hash_container __rcu *vnet_hash;
 	struct ethtool_link_ksettings link_ksettings;
 	/* init args */
 	struct file *file;
@@ -451,9 +452,14 @@ static inline void tun_flow_save_rps_rxhash(struct tun_flow_entry *e, u32 hash)
 		e->rps_rxhash = hash;
 }
 
+static struct virtio_net_hash *tun_add_hash(struct sk_buff *skb)
+{
+	return skb_ext_add(skb, SKB_EXT_TUN_VNET_HASH);
+}
+
 static const struct virtio_net_hash *tun_find_hash(const struct sk_buff *skb)
 {
-	return NULL;
+	return skb_ext_find(skb, SKB_EXT_TUN_VNET_HASH);
 }
 
 /* We try to identify a flow through its rxhash. The reason that
@@ -462,14 +468,21 @@ static const struct virtio_net_hash *tun_find_hash(const struct sk_buff *skb)
  * the userspace application move between processors, we may get a
  * different rxq no. here.
  */
-static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
+static u16 tun_automq_select_queue(struct tun_struct *tun,
+				   const struct tun_vnet_hash_container *vnet_hash,
+				   struct sk_buff *skb)
 {
+	struct flow_keys keys;
+	struct flow_keys_basic keys_basic;
 	struct tun_flow_entry *e;
 	u32 txq, numqueues;
 
 	numqueues = READ_ONCE(tun->numqueues);
 
-	txq = __skb_get_hash_symmetric(skb);
+	memset(&keys, 0, sizeof(keys));
+	skb_flow_dissect(skb, &flow_keys_dissector_symmetric, &keys, 0);
+
+	txq = flow_hash_from_keys(&keys);
 	e = tun_flow_find(&tun->flows[tun_hashfn(txq)], txq);
 	if (e) {
 		tun_flow_save_rps_rxhash(e, txq);
@@ -478,6 +491,13 @@ static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb)
 		txq = reciprocal_scale(txq, numqueues);
 	}
 
+	keys_basic = (struct flow_keys_basic) {
+		.control = keys.control,
+		.basic = keys.basic
+	};
+	tun_vnet_hash_report(vnet_hash, skb, &keys_basic, skb->l4_hash ? skb->hash : txq,
+			     tun_add_hash);
+
 	return txq;
 }
 
@@ -513,8 +533,15 @@ static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb,
 	u16 ret;
 
 	rcu_read_lock();
-	if (!tun_ebpf_select_queue(tun, skb, &ret))
-		ret = tun_automq_select_queue(tun, skb);
+	if (!tun_ebpf_select_queue(tun, skb, &ret)) {
+		struct tun_vnet_hash_container *vnet_hash = rcu_dereference(tun->vnet_hash);
+
+		if (vnet_hash && (vnet_hash->common.flags & TUN_VNET_HASH_RSS))
+			ret = tun_vnet_rss_select_queue(READ_ONCE(tun->numqueues), vnet_hash,
+							skb, tun_add_hash);
+		else
+			ret = tun_automq_select_queue(tun, vnet_hash, skb);
+	}
 	rcu_read_unlock();
 
 	return ret;
@@ -2245,6 +2272,7 @@ static void tun_free_netdev(struct net_device *dev)
 	security_tun_dev_free_security(tun->security);
 	__tun_set_ebpf(tun, &tun->steering_prog, NULL);
 	__tun_set_ebpf(tun, &tun->filter_prog, NULL);
+	kfree_rcu_mightsleep(rcu_access_pointer(tun->vnet_hash));
 }
 
 static void tun_setup(struct net_device *dev)
@@ -3032,16 +3060,22 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 	} else {
 		memset(&ifr, 0, sizeof(ifr));
 	}
-	if (cmd == TUNGETFEATURES) {
+	switch (cmd) {
+	case TUNGETFEATURES:
 		/* Currently this just means: "what IFF flags are valid?".
 		 * This is needed because we never checked for invalid flags on
 		 * TUNSETIFF.
 		 */
 		return put_user(IFF_TUN | IFF_TAP | IFF_NO_CARRIER |
 				TUN_FEATURES, (unsigned int __user*)argp);
-	} else if (cmd == TUNSETQUEUE) {
+
+	case TUNSETQUEUE:
 		return tun_set_queue(file, &ifr);
-	} else if (cmd == SIOCGSKNS) {
+
+	case TUNGETVNETHASHCAP:
+		return tun_vnet_ioctl_gethashcap(argp);
+
+	case SIOCGSKNS:
 		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 			return -EPERM;
 		return open_related_ns(&net->ns, get_net_ns);
@@ -3282,6 +3316,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 		ret = open_related_ns(&net->ns, get_net_ns);
 		break;
 
+	case TUNSETVNETHASH:
+		ret = tun_vnet_ioctl_sethash(&tun->vnet_hash, argp);
+		break;
+
 	default:
 		ret = tun_vnet_ioctl(&tun->vnet_hdr_sz, &tun->flags, cmd, argp);
 		break;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index cd8294cdc2496..65e7cefa2bc60 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4825,6 +4825,9 @@ enum skb_ext_id {
 #endif
 #if IS_ENABLED(CONFIG_MCTP_FLOWS)
 	SKB_EXT_MCTP,
+#endif
+#if IS_ENABLED(CONFIG_TUN)
+	SKB_EXT_TUN_VNET_HASH,
 #endif
 	SKB_EXT_NUM, /* must be last */
 };
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index a64d777488e40..71581e9f2941d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -64,6 +64,7 @@
 #include <linux/mpls.h>
 #include <linux/kcov.h>
 #include <linux/iov_iter.h>
+#include <linux/virtio_net.h>
 
 #include <net/protocol.h>
 #include <net/dst.h>
@@ -5019,6 +5020,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_MCTP_FLOWS)
 	[SKB_EXT_MCTP] = SKB_EXT_CHUNKSIZEOF(struct mctp_flow),
 #endif
+#if IS_ENABLED(CONFIG_TUN)
+	[SKB_EXT_TUN_VNET_HASH] = SKB_EXT_CHUNKSIZEOF(struct virtio_net_hash),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)

From e478d76cdef29f2f7ba4ebc417ca053b44436bf0 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:56 +0900
Subject: [PATCH 2517/2753] tap: Introduce virtio-net hash feature

Add ioctls and storage required for the virtio-net hash feature to TAP.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ipvlan/ipvtap.c |  2 +-
 drivers/net/macvtap.c       |  2 +-
 drivers/net/tap.c           | 70 +++++++++++++++++++++++++++++++++----
 include/linux/if_tap.h      |  4 ++-
 4 files changed, 69 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ipvlan/ipvtap.c b/drivers/net/ipvlan/ipvtap.c
index edd13916831a7..89f946d347390 100644
--- a/drivers/net/ipvlan/ipvtap.c
+++ b/drivers/net/ipvlan/ipvtap.c
@@ -114,7 +114,7 @@ static void ipvtap_dellink(struct net_device *dev,
 	struct ipvtap_dev *vlan = netdev_priv(dev);
 
 	netdev_rx_handler_unregister(dev);
-	tap_del_queues(&vlan->tap);
+	tap_del(&vlan->tap);
 	ipvlan_link_delete(dev, head);
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index b391a0f740a3f..d5d4fa6669278 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -122,7 +122,7 @@ static void macvtap_dellink(struct net_device *dev,
 	struct macvtap_dev *vlantap = netdev_priv(dev);
 
 	netdev_rx_handler_unregister(dev);
-	tap_del_queues(&vlantap->tap);
+	tap_del(&vlantap->tap);
 	macvlan_dellink(dev, head);
 }
 
diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index 25c60ff2d3f28..2213a2aa83a86 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -49,6 +49,10 @@ struct major_info {
 	struct list_head next;
 };
 
+struct tap_skb_cb {
+	struct virtio_net_hash hash;
+};
+
 #define GOODCOPY_LEN 128
 
 static const struct proto_ops tap_socket_ops;
@@ -179,9 +183,20 @@ static void tap_put_queue(struct tap_queue *q)
 	sock_put(&q->sk);
 }
 
+static struct tap_skb_cb *tap_skb_cb(const struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(skb->cb) < sizeof(struct tap_skb_cb));
+	return (struct tap_skb_cb *)skb->cb;
+}
+
+static struct virtio_net_hash *tap_add_hash(struct sk_buff *skb)
+{
+	return &tap_skb_cb(skb)->hash;
+}
+
 static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
 {
-	return NULL;
+	return &tap_skb_cb(skb)->hash;
 }
 
 /*
@@ -194,6 +209,7 @@ static const struct virtio_net_hash *tap_find_hash(const struct sk_buff *skb)
 static struct tap_queue *tap_get_queue(struct tap_dev *tap,
 				       struct sk_buff *skb)
 {
+	struct flow_keys_basic keys_basic;
 	struct tap_queue *queue = NULL;
 	/* Access to taps array is protected by rcu, but access to numvtaps
 	 * isn't. Below we use it to lookup a queue, but treat it as a hint
@@ -201,17 +217,47 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap,
 	 * racing against queue removal.
 	 */
 	int numvtaps = READ_ONCE(tap->numvtaps);
+	struct tun_vnet_hash_container *vnet_hash = rcu_dereference(tap->vnet_hash);
 	__u32 rxq;
 
+	*tap_skb_cb(skb) = (struct tap_skb_cb) {
+		.hash = { .report = VIRTIO_NET_HASH_REPORT_NONE }
+	};
+
 	if (!numvtaps)
 		goto out;
 
 	if (numvtaps == 1)
 		goto single;
 
+	if (vnet_hash) {
+		if ((vnet_hash->common.flags & TUN_VNET_HASH_RSS)) {
+			rxq = tun_vnet_rss_select_queue(numvtaps, vnet_hash, skb, tap_add_hash);
+			queue = rcu_dereference(tap->taps[rxq]);
+			goto out;
+		}
+
+		if (!skb->l4_hash && !skb->sw_hash) {
+			struct flow_keys keys;
+
+			skb_flow_dissect_flow_keys(skb, &keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+			rxq = flow_hash_from_keys(&keys);
+			keys_basic = (struct flow_keys_basic) {
+				.control = keys.control,
+				.basic = keys.basic
+			};
+		} else {
+			skb_flow_dissect_flow_keys_basic(NULL, skb, &keys_basic, NULL, 0, 0, 0,
+							 FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);
+			rxq = skb->hash;
+		}
+	} else {
+		rxq = skb_get_hash(skb);
+	}
+
 	/* Check if we can use flow to select a queue */
-	rxq = skb_get_hash(skb);
 	if (rxq) {
+		tun_vnet_hash_report(vnet_hash, skb, &keys_basic, rxq, tap_add_hash);
 		queue = rcu_dereference(tap->taps[rxq % numvtaps]);
 		goto out;
 	}
@@ -234,10 +280,10 @@ static struct tap_queue *tap_get_queue(struct tap_dev *tap,
 
 /*
  * The net_device is going away, give up the reference
- * that it holds on all queues and safely set the pointer
- * from the queues to NULL.
+ * that it holds on all queues, safely set the pointer
+ * from the queues to NULL, and free vnet_hash.
  */
-void tap_del_queues(struct tap_dev *tap)
+void tap_del(struct tap_dev *tap)
 {
 	struct tap_queue *q, *tmp;
 
@@ -254,8 +300,10 @@ void tap_del_queues(struct tap_dev *tap)
 	BUG_ON(tap->numqueues);
 	/* guarantee that any future tap_set_queue will fail */
 	tap->numvtaps = MAX_TAP_QUEUES;
+
+	kfree_rcu_mightsleep(rtnl_dereference(tap->vnet_hash));
 }
-EXPORT_SYMBOL_GPL(tap_del_queues);
+EXPORT_SYMBOL_GPL(tap_del);
 
 rx_handler_result_t tap_handle_frame(struct sk_buff **pskb)
 {
@@ -998,6 +1046,16 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 		rtnl_unlock();
 		return ret;
 
+	case TUNGETVNETHASHCAP:
+		return tun_vnet_ioctl_gethashcap(argp);
+
+	case TUNSETVNETHASH:
+		rtnl_lock();
+		tap = rtnl_dereference(q->tap);
+		ret = tap ? tun_vnet_ioctl_sethash(&tap->vnet_hash, argp) : -EBADFD;
+		rtnl_unlock();
+		return ret;
+
 	case SIOCGIFHWADDR:
 		rtnl_lock();
 		tap = tap_get_tap_dev(q);
diff --git a/include/linux/if_tap.h b/include/linux/if_tap.h
index 553552fa635c3..9e8e02822d9c6 100644
--- a/include/linux/if_tap.h
+++ b/include/linux/if_tap.h
@@ -31,6 +31,7 @@ static inline struct ptr_ring *tap_get_ptr_ring(struct file *f)
 #define MAX_TAP_QUEUES 256
 
 struct tap_queue;
+struct tun_vnet_hash_container;
 
 struct tap_dev {
 	struct net_device	*dev;
@@ -43,6 +44,7 @@ struct tap_dev {
 	int			numqueues;
 	netdev_features_t	tap_features;
 	int			minor;
+	struct tun_vnet_hash_container __rcu *vnet_hash;
 
 	void (*update_features)(struct tap_dev *tap, netdev_features_t features);
 	void (*count_tx_dropped)(struct tap_dev *tap);
@@ -74,7 +76,7 @@ struct tap_queue {
 };
 
 rx_handler_result_t tap_handle_frame(struct sk_buff **pskb);
-void tap_del_queues(struct tap_dev *tap);
+void tap_del(struct tap_dev *tap);
 int tap_get_minor(dev_t major, struct tap_dev *tap);
 void tap_free_minor(dev_t major, struct tap_dev *tap);
 int tap_queue_resize(struct tap_dev *tap);

From c1ae79a7c8fe9766becac441da194a2e702d93ea Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:57 +0900
Subject: [PATCH 2518/2753] selftest: tun: Test vnet ioctls without device

Ensure that vnet ioctls result in EBADFD when the underlying device is
deleted.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/tun.c | 38 +++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
index fa83918b62d1b..ad168c15c02d9 100644
--- a/tools/testing/selftests/net/tun.c
+++ b/tools/testing/selftests/net/tun.c
@@ -159,4 +159,42 @@ TEST_F(tun, reattach_close_delete) {
 	EXPECT_EQ(tun_delete(self->ifname), 0);
 }
 
+FIXTURE(tun_deleted)
+{
+	char ifname[IFNAMSIZ];
+	int fd;
+};
+
+FIXTURE_SETUP(tun_deleted)
+{
+	self->ifname[0] = 0;
+	self->fd = tun_alloc(self->ifname);
+	ASSERT_LE(0, self->fd);
+
+	ASSERT_EQ(0, tun_delete(self->ifname))
+		EXPECT_EQ(0, close(self->fd));
+}
+
+FIXTURE_TEARDOWN(tun_deleted)
+{
+	EXPECT_EQ(0, close(self->fd));
+}
+
+TEST_F(tun_deleted, getvnethdrsz)
+{
+	ASSERT_EQ(-1, ioctl(self->fd, TUNGETVNETHDRSZ));
+	EXPECT_EQ(EBADFD, errno);
+}
+
+TEST_F(tun_deleted, getvnethashcap)
+{
+	struct tun_vnet_hash cap;
+	int i = ioctl(self->fd, TUNGETVNETHASHCAP, &cap);
+
+	if (i == -1 && errno == EBADFD)
+		SKIP(return, "TUNGETVNETHASHCAP not supported");
+
+	EXPECT_EQ(0, i);
+}
+
 TEST_HARNESS_MAIN

From 619a10786eeef999600588f5144741bfd60464dc Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:58 +0900
Subject: [PATCH 2519/2753] selftest: tun: Add tests for virtio-net hashing

The added tests confirm tun can perform RSS for all supported hash types
to select the receive queue and report hash values.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/Makefile |   2 +-
 tools/testing/selftests/net/tun.c    | 455 ++++++++++++++++++++++++++-
 2 files changed, 447 insertions(+), 10 deletions(-)

diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 6d718b478ed83..d12763c86bd02 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -129,6 +129,6 @@ $(OUTPUT)/reuseport_bpf_numa: LDLIBS += -lnuma
 $(OUTPUT)/tcp_mmap: LDLIBS += -lpthread -lcrypto
 $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
-$(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
+$(OUTPUT)/io_uring_zerocopy_tx $(OUTPUT)/tun: CFLAGS += -I../../../include/
 
 include bpf.mk
diff --git a/tools/testing/selftests/net/tun.c b/tools/testing/selftests/net/tun.c
index ad168c15c02d9..dfb84da50d91d 100644
--- a/tools/testing/selftests/net/tun.c
+++ b/tools/testing/selftests/net/tun.c
@@ -2,21 +2,38 @@
 
 #define _GNU_SOURCE
 
+#include <endian.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <sched.h>
+#include <stddef.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
-#include <linux/if.h>
+#include <net/if.h>
+#include <netinet/ip.h>
+#include <sys/ioctl.h>
+#include <sys/socket.h>
+#include <linux/compiler.h>
+#include <linux/icmp.h>
+#include <linux/if_arp.h>
 #include <linux/if_tun.h>
+#include <linux/ipv6.h>
 #include <linux/netlink.h>
 #include <linux/rtnetlink.h>
-#include <sys/ioctl.h>
-#include <sys/socket.h>
+#include <linux/sockios.h>
+#include <linux/tcp.h>
+#include <linux/udp.h>
+#include <linux/virtio_net.h>
 
 #include "../kselftest_harness.h"
 
+#define TUN_HWADDR_SOURCE { 0x02, 0x00, 0x00, 0x00, 0x00, 0x00 }
+#define TUN_HWADDR_DEST { 0x02, 0x00, 0x00, 0x00, 0x00, 0x01 }
+#define TUN_IPADDR_SOURCE htonl((172 << 24) | (17 << 16) | 0)
+#define TUN_IPADDR_DEST htonl((172 << 24) | (17 << 16) | 1)
+
 static int tun_attach(int fd, char *dev)
 {
 	struct ifreq ifr;
@@ -39,7 +56,7 @@ static int tun_detach(int fd, char *dev)
 	return ioctl(fd, TUNSETQUEUE, (void *) &ifr);
 }
 
-static int tun_alloc(char *dev)
+static int tun_alloc(char *dev, short flags)
 {
 	struct ifreq ifr;
 	int fd, err;
@@ -52,7 +69,8 @@ static int tun_alloc(char *dev)
 
 	memset(&ifr, 0, sizeof(ifr));
 	strcpy(ifr.ifr_name, dev);
-	ifr.ifr_flags = IFF_TAP | IFF_NAPI | IFF_MULTI_QUEUE;
+	ifr.ifr_flags = flags | IFF_TAP | IFF_NAPI | IFF_NO_PI |
+			IFF_MULTI_QUEUE;
 
 	err = ioctl(fd, TUNSETIFF, (void *) &ifr);
 	if (err < 0) {
@@ -64,6 +82,20 @@ static int tun_alloc(char *dev)
 	return fd;
 }
 
+static bool tun_set_flags(int local_fd, const char *name, short flags)
+{
+	struct ifreq ifreq = { .ifr_flags = flags };
+
+	strcpy(ifreq.ifr_name, name);
+
+	if (ioctl(local_fd, SIOCSIFFLAGS, &ifreq)) {
+		perror("SIOCSIFFLAGS");
+		return false;
+	}
+
+	return true;
+}
+
 static int tun_delete(char *dev)
 {
 	struct {
@@ -102,6 +134,107 @@ static int tun_delete(char *dev)
 	return ret;
 }
 
+static uint32_t tun_sum(const void *buf, size_t len)
+{
+	const uint16_t *sbuf = buf;
+	uint32_t sum = 0;
+
+	while (len > 1) {
+		sum += *sbuf++;
+		len -= 2;
+	}
+
+	if (len)
+		sum += *(uint8_t *)sbuf;
+
+	return sum;
+}
+
+static uint16_t tun_build_ip_check(uint32_t sum)
+{
+	return ~((sum & 0xffff) + (sum >> 16));
+}
+
+static uint32_t tun_build_ip_pseudo_sum(const void *iphdr)
+{
+	uint16_t tot_len = ntohs(((struct iphdr *)iphdr)->tot_len);
+
+	return tun_sum((char *)iphdr + offsetof(struct iphdr, saddr), 8) +
+	       htons(((struct iphdr *)iphdr)->protocol) +
+	       htons(tot_len - sizeof(struct iphdr));
+}
+
+static uint32_t tun_build_ipv6_pseudo_sum(const void *ipv6hdr)
+{
+	return tun_sum((char *)ipv6hdr + offsetof(struct ipv6hdr, saddr), 32) +
+	       ((struct ipv6hdr *)ipv6hdr)->payload_len +
+	       htons(((struct ipv6hdr *)ipv6hdr)->nexthdr);
+}
+
+static void tun_build_iphdr(void *dest, uint16_t len, uint8_t protocol)
+{
+	struct iphdr iphdr = {
+		.ihl = sizeof(iphdr) / 4,
+		.version = 4,
+		.tot_len = htons(sizeof(iphdr) + len),
+		.ttl = 255,
+		.protocol = protocol,
+		.saddr = TUN_IPADDR_SOURCE,
+		.daddr = TUN_IPADDR_DEST
+	};
+
+	iphdr.check = tun_build_ip_check(tun_sum(&iphdr, sizeof(iphdr)));
+	memcpy(dest, &iphdr, sizeof(iphdr));
+}
+
+static void tun_build_ipv6hdr(void *dest, uint16_t len, uint8_t protocol)
+{
+	struct ipv6hdr ipv6hdr = {
+		.version = 6,
+		.payload_len = htons(len),
+		.nexthdr = protocol,
+		.saddr = {
+			.s6_addr32 = {
+				htonl(0xffff0000), 0, 0, TUN_IPADDR_SOURCE
+			}
+		},
+		.daddr = {
+			.s6_addr32 = {
+				htonl(0xffff0000), 0, 0, TUN_IPADDR_DEST
+			}
+		},
+	};
+
+	memcpy(dest, &ipv6hdr, sizeof(ipv6hdr));
+}
+
+static void tun_build_tcphdr(void *dest, uint32_t sum)
+{
+	struct tcphdr tcphdr = {
+		.source = htons(9),
+		.dest = htons(9),
+		.fin = 1,
+		.doff = sizeof(tcphdr) / 4,
+	};
+	uint32_t tcp_sum = tun_sum(&tcphdr, sizeof(tcphdr));
+
+	tcphdr.check = tun_build_ip_check(sum + tcp_sum);
+	memcpy(dest, &tcphdr, sizeof(tcphdr));
+}
+
+static void tun_build_udphdr(void *dest, uint32_t sum)
+{
+	struct udphdr udphdr = {
+		.source = htons(9),
+		.dest = htons(9),
+		.len = htons(sizeof(udphdr)),
+	};
+	uint32_t udp_sum = tun_sum(&udphdr, sizeof(udphdr));
+
+	udphdr.check = tun_build_ip_check(sum + udp_sum);
+	memcpy(dest, &udphdr, sizeof(udphdr));
+}
+
 FIXTURE(tun)
 {
 	char ifname[IFNAMSIZ];
@@ -112,10 +245,10 @@ FIXTURE_SETUP(tun)
 {
 	memset(self->ifname, 0, sizeof(self->ifname));
 
-	self->fd = tun_alloc(self->ifname);
+	self->fd = tun_alloc(self->ifname, 0);
 	ASSERT_GE(self->fd, 0);
 
-	self->fd2 = tun_alloc(self->ifname);
+	self->fd2 = tun_alloc(self->ifname, 0);
 	ASSERT_GE(self->fd2, 0);
 }
 
@@ -168,7 +301,7 @@ FIXTURE(tun_deleted)
 FIXTURE_SETUP(tun_deleted)
 {
 	self->ifname[0] = 0;
-	self->fd = tun_alloc(self->ifname);
+	self->fd = tun_alloc(self->ifname, 0);
 	ASSERT_LE(0, self->fd);
 
 	ASSERT_EQ(0, tun_delete(self->ifname))
@@ -197,4 +330,308 @@ TEST_F(tun_deleted, getvnethashcap)
 	EXPECT_EQ(0, i);
 }
 
-TEST_HARNESS_MAIN
+FIXTURE(tun_vnet_hash)
+{
+	int dest_fds[3];
+	unsigned int dest_ifindex;
+	int source_fd;
+	char buffer[sizeof(struct ipv6hdr) + sizeof(struct tcphdr)];
+	uint16_t len;
+};
+
+FIXTURE_VARIANT(tun_vnet_hash)
+{
+	uint16_t eth_p;
+	uint8_t ipproto;
+	uint8_t flags;
+	uint16_t hash_report;
+	uint32_t hash_value;
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, unclassified)
+{
+	.eth_p = ETH_P_LOOPBACK
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, ipv4)
+{
+	.eth_p = ETH_P_IP,
+	.ipproto = 253,
+	.hash_report = VIRTIO_NET_HASH_REPORT_IPv4,
+	.hash_value = 0x6e45d952
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, tcpv4)
+{
+	.eth_p = ETH_P_IP,
+	.ipproto = IPPROTO_TCP,
+	.hash_report = VIRTIO_NET_HASH_REPORT_TCPv4,
+	.hash_value = 0xfb63539a
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, udpv4)
+{
+	.eth_p = ETH_P_IP,
+	.ipproto = IPPROTO_UDP,
+	.hash_report = VIRTIO_NET_HASH_REPORT_UDPv4,
+	.hash_value = 0xfb63539a
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, ipv6)
+{
+	.eth_p = ETH_P_IPV6,
+	.ipproto = 253,
+	.hash_report = VIRTIO_NET_HASH_REPORT_IPv6,
+	.hash_value = 0xd6eb560f
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, tcpv6)
+{
+	.eth_p = ETH_P_IPV6,
+	.ipproto = IPPROTO_TCP,
+	.hash_report = VIRTIO_NET_HASH_REPORT_TCPv6,
+	.hash_value = 0xc2b9f251
+};
+
+FIXTURE_VARIANT_ADD(tun_vnet_hash, udpv6)
+{
+	.eth_p = ETH_P_IPV6,
+	.ipproto = IPPROTO_UDP,
+	.hash_report = VIRTIO_NET_HASH_REPORT_UDPv6,
+	.hash_value = 0xc2b9f251
+};
+
+FIXTURE_SETUP(tun_vnet_hash)
+{
+	static const struct {
+		struct tun_vnet_hash hdr;
+		struct tun_vnet_hash_rss rss;
+		uint16_t rss_indirection_table[2];
+		uint8_t rss_key[40];
+	} vnet_hash = {
+		.hdr = {
+			.flags = TUN_VNET_HASH_REPORT | TUN_VNET_HASH_RSS,
+			.types = VIRTIO_NET_RSS_HASH_TYPE_IPv4 |
+				VIRTIO_NET_RSS_HASH_TYPE_TCPv4 |
+				VIRTIO_NET_RSS_HASH_TYPE_UDPv4 |
+				VIRTIO_NET_RSS_HASH_TYPE_IPv6 |
+				VIRTIO_NET_RSS_HASH_TYPE_TCPv6 |
+				VIRTIO_NET_RSS_HASH_TYPE_UDPv6
+		},
+		.rss = { .indirection_table_mask = 1, .unclassified_queue = 5 },
+		.rss_indirection_table = { 3, 4 },
+		.rss_key = {
+			0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2,
+			0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0,
+			0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4,
+			0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c,
+			0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa
+		}
+	};
+
+	struct {
+		struct virtio_net_hdr_v1_hash vnet_hdr;
+		struct ethhdr ethhdr;
+		struct arphdr arphdr;
+		unsigned char sender_hwaddr[6];
+		uint32_t sender_ipaddr;
+		unsigned char target_hwaddr[6];
+		uint32_t target_ipaddr;
+	} __packed packet = {
+		.ethhdr = {
+			.h_source = TUN_HWADDR_SOURCE,
+			.h_dest = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff },
+			.h_proto = htons(ETH_P_ARP)
+		},
+		.arphdr = {
+			.ar_hrd = htons(ARPHRD_ETHER),
+			.ar_pro = htons(ETH_P_IP),
+			.ar_hln = ETH_ALEN,
+			.ar_pln = 4,
+			.ar_op = htons(ARPOP_REQUEST)
+		},
+		.sender_hwaddr = TUN_HWADDR_DEST,
+		.sender_ipaddr = TUN_IPADDR_DEST,
+		.target_ipaddr = TUN_IPADDR_DEST
+	};
+
+	struct tun_vnet_hash cap;
+	char dest_ifname[IFNAMSIZ] = "";
+	int i, local_fd;
+	uint16_t ip_payload_len;
+	uint32_t ip_sum;
+
+	self->dest_fds[0] = tun_alloc(dest_ifname, IFF_VNET_HDR);
+	ASSERT_LE(0, self->dest_fds[0]) {
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+	}
+
+	i = ioctl(self->dest_fds[0], TUNGETVNETHASHCAP, &cap);
+	if (i == -1 && errno == EINVAL) {
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+		SKIP(return, "TUNGETVNETHASHCAP not supported");
+	}
+
+	ASSERT_EQ(0, i)
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	if ((cap.flags & vnet_hash.hdr.flags) != vnet_hash.hdr.flags) {
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+		SKIP(return, "Lacks some hash flag support");
+	}
+
+	if ((cap.types & vnet_hash.hdr.types) != vnet_hash.hdr.types) {
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+		SKIP(return, "Lacks some hash type support");
+	}
+
+	self->dest_ifindex = if_nametoindex(dest_ifname);
+	ASSERT_TRUE(self->dest_ifindex)
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	i = sizeof(struct virtio_net_hdr_v1_hash);
+	ASSERT_EQ(0, ioctl(self->dest_fds[0], TUNSETVNETHDRSZ, &i))
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	i = 1;
+	ASSERT_EQ(0, ioctl(self->dest_fds[0], TUNSETVNETLE, &i))
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	local_fd = socket(AF_LOCAL, SOCK_STREAM, 0);
+	ASSERT_LE(0, local_fd)
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	i = tun_set_flags(local_fd, dest_ifname, IFF_UP);
+	EXPECT_EQ(0, close(local_fd));
+	ASSERT_TRUE(i)
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	ASSERT_EQ(sizeof(packet),
+		  write(self->dest_fds[0], &packet, sizeof(packet)))
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	ASSERT_EQ(0, ioctl(self->dest_fds[0], TUNSETVNETHASH, &vnet_hash))
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	self->source_fd = socket(AF_PACKET, SOCK_DGRAM, 0);
+	ASSERT_LE(0, self->source_fd)
+		EXPECT_EQ(0, close(self->dest_fds[0]));
+
+	for (i = 1; i < ARRAY_SIZE(self->dest_fds); i++) {
+		self->dest_fds[i] = tun_alloc(dest_ifname, IFF_VNET_HDR);
+		ASSERT_LE(0, self->dest_fds[i]) {
+			while (i) {
+				i--;
+				EXPECT_EQ(0, close(self->dest_fds[i]));
+			}
+		}
+	}
+
+	if (variant->eth_p == ETH_P_IP || variant->eth_p == ETH_P_IPV6) {
+		switch (variant->ipproto) {
+		case IPPROTO_TCP:
+			ip_payload_len = sizeof(struct tcphdr);
+			break;
+
+		case IPPROTO_UDP:
+			ip_payload_len = sizeof(struct udphdr);
+			break;
+
+		default:
+			ip_payload_len = 0;
+		}
+
+		switch (variant->eth_p) {
+		case ETH_P_IP:
+			tun_build_iphdr(self->buffer, ip_payload_len, variant->ipproto);
+			self->len = sizeof(struct iphdr);
+			ip_sum = tun_build_ip_pseudo_sum(self->buffer);
+			break;
+
+		case ETH_P_IPV6:
+			tun_build_ipv6hdr(self->buffer, ip_payload_len, variant->ipproto);
+			self->len = sizeof(struct ipv6hdr);
+			ip_sum = tun_build_ipv6_pseudo_sum(self->buffer);
+			break;
+		}
+
+		switch (variant->ipproto) {
+		case IPPROTO_TCP:
+			tun_build_tcphdr(self->buffer + self->len, ip_sum);
+			break;
+
+		case IPPROTO_UDP:
+			tun_build_udphdr(self->buffer + self->len, ip_sum);
+			break;
+		}
+
+		self->len += ip_payload_len;
+	}
+}
+
+FIXTURE_TEARDOWN(tun_vnet_hash)
+{
+	EXPECT_EQ(0, close(self->source_fd));
+
+	for (size_t i = 0; i < ARRAY_SIZE(self->dest_fds); i++)
+		EXPECT_EQ(0, close(self->dest_fds[i]));
+}
+
+TEST_F(tun_vnet_hash, rx)
+{
+	size_t len = sizeof(struct virtio_net_hdr_v1_hash) + ETH_HLEN + self->len;
+	struct {
+		struct virtio_net_hdr_v1_hash vnet_hdr;
+		struct ethhdr ethhdr;
+		char payload[sizeof(self->buffer)];
+	} buffer;
+	struct virtio_net_hdr_v1_hash hdr = {
+		.hdr = { .flags = variant->flags },
+		.hash_value = htole32(variant->hash_value),
+		.hash_report = htole16(variant->hash_report)
+	};
+	int txq = variant->hash_report ? variant->hash_value & 1 : 2;
+	struct sockaddr_ll ll = {
+		.sll_family = AF_PACKET,
+		.sll_addr = TUN_HWADDR_DEST,
+		.sll_halen = ETH_ALEN,
+		.sll_ifindex = self->dest_ifindex,
+		.sll_protocol = htons(variant->eth_p),
+	};
+
+	EXPECT_EQ(self->len,
+		  sendto(self->source_fd, self->buffer, self->len, 0,
+			 (struct sockaddr *)&ll, sizeof(ll)));
+	EXPECT_EQ(len, read(self->dest_fds[txq], &buffer, len));
+	ASSERT_FALSE(memcmp(&buffer, &hdr, sizeof(hdr)));
+	ASSERT_FALSE(memcmp(buffer.payload, self->buffer, self->len));
+}
+
+int main(int argc, char **argv)
+{
+	FILE *file;
+
+	if (unshare(CLONE_NEWNET)) {
+		perror("unshare");
+		return KSFT_FAIL;
+	}
+
+	/* Disable IPv6 to eliminate IPv6 Neighbor Discovery messages. */
+	file = fopen("/proc/sys/net/ipv6/conf/default/disable_ipv6", "w");
+	if (file) {
+		if (fputc('1', file) != '1') {
+			perror("fputc");
+			return KSFT_FAIL;
+		}
+
+		if (fclose(file)) {
+			perror("fclose");
+			return KSFT_FAIL;
+		}
+	} else if (errno != ENOENT) {
+		perror("fopen");
+		return KSFT_FAIL;
+	}
+
+	return test_harness_run(argc, argv);
+}

From dd7898a84048180fd0cdfeac947ec9bc84450ca2 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:57:59 +0900
Subject: [PATCH 2520/2753] selftest: tap: Add tests for virtio-net ioctls

They only test the ioctls are wired up to the implementation common with
tun as it is already tested for tun.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/tap.c | 97 ++++++++++++++++++++++++++++++-
 1 file changed, 95 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/net/tap.c b/tools/testing/selftests/net/tap.c
index 247c3b3ac1c97..fbd38b08fdfa4 100644
--- a/tools/testing/selftests/net/tap.c
+++ b/tools/testing/selftests/net/tap.c
@@ -363,6 +363,7 @@ size_t build_test_packet_crash_tap_invalid_eth_proto(uint8_t *buf,
 FIXTURE(tap)
 {
 	int fd;
+	bool deleted;
 };
 
 FIXTURE_SETUP(tap)
@@ -387,8 +388,10 @@ FIXTURE_TEARDOWN(tap)
 	if (self->fd != -1)
 		close(self->fd);
 
-	ret = dev_delete(param_dev_tap_name);
-	EXPECT_EQ(ret, 0);
+	if (!self->deleted) {
+		ret = dev_delete(param_dev_tap_name);
+		EXPECT_EQ(ret, 0);
+	}
 
 	ret = dev_delete(param_dev_dummy_name);
 	EXPECT_EQ(ret, 0);
@@ -431,4 +434,94 @@ TEST_F(tap, test_packet_crash_tap_invalid_eth_proto)
 	ASSERT_EQ(errno, EINVAL);
 }
 
+TEST_F(tap, test_vnethdrsz)
+{
+	int sz = sizeof(struct virtio_net_hdr_v1_hash);
+
+	ASSERT_FALSE(dev_delete(param_dev_tap_name));
+	self->deleted = true;
+
+	ASSERT_FALSE(ioctl(self->fd, TUNSETVNETHDRSZ, &sz));
+	sz = 0;
+	ASSERT_FALSE(ioctl(self->fd, TUNGETVNETHDRSZ, &sz));
+	EXPECT_EQ(sizeof(struct virtio_net_hdr_v1_hash), sz);
+}
+
+TEST_F(tap, test_vnetle)
+{
+	int le = 1;
+
+	ASSERT_FALSE(dev_delete(param_dev_tap_name));
+	self->deleted = true;
+
+	ASSERT_FALSE(ioctl(self->fd, TUNSETVNETLE, &le));
+	le = 0;
+	ASSERT_FALSE(ioctl(self->fd, TUNGETVNETLE, &le));
+	EXPECT_EQ(1, le);
+}
+
+TEST_F(tap, test_vnetbe)
+{
+	int be = 1;
+	int ret;
+
+	ASSERT_FALSE(dev_delete(param_dev_tap_name));
+	self->deleted = true;
+
+	ret = ioctl(self->fd, TUNSETVNETBE, &be);
+	if (ret == -1 && errno == EINVAL)
+		SKIP(return, "TUNSETVNETBE not supported");
+
+	ASSERT_FALSE(ret);
+	be = 0;
+	ASSERT_FALSE(ioctl(self->fd, TUNGETVNETBE, &be));
+	EXPECT_EQ(1, be);
+}
+
+TEST_F(tap, test_getvnethashcap)
+{
+	static const struct tun_vnet_hash expected = {
+		.flags = TUN_VNET_HASH_REPORT | TUN_VNET_HASH_RSS,
+		.types = VIRTIO_NET_RSS_HASH_TYPE_IPv4 |
+			 VIRTIO_NET_RSS_HASH_TYPE_TCPv4 |
+			 VIRTIO_NET_RSS_HASH_TYPE_UDPv4 |
+			 VIRTIO_NET_RSS_HASH_TYPE_IPv6 |
+			 VIRTIO_NET_RSS_HASH_TYPE_TCPv6 |
+			 VIRTIO_NET_RSS_HASH_TYPE_UDPv6
+	};
+	struct tun_vnet_hash seen;
+	int ret;
+
+	ASSERT_FALSE(dev_delete(param_dev_tap_name));
+	self->deleted = true;
+
+	ret = ioctl(self->fd, TUNGETVNETHASHCAP, &seen);
+
+	if (ret == -1 && errno == EINVAL)
+		SKIP(return, "TUNGETVNETHASHCAP not supported");
+
+	EXPECT_FALSE(ret);
+	EXPECT_FALSE(memcmp(&expected, &seen, sizeof(expected)));
+}
+
+TEST_F(tap, test_setvnethash_alive)
+{
+	struct tun_vnet_hash hash = { .flags = 0 };
+
+	EXPECT_FALSE(ioctl(self->fd, TUNSETVNETHASH, &hash));
+}
+
+TEST_F(tap, test_setvnethash_deleted)
+{
+	ASSERT_FALSE(dev_delete(param_dev_tap_name));
+	self->deleted = true;
+
+	ASSERT_EQ(-1, ioctl(self->fd, TUNSETVNETHASH));
+
+	if (errno == EINVAL)
+		SKIP(return, "TUNSETVNETHASH not supported");
+
+	EXPECT_EQ(EBADFD, errno);
+}
+
 TEST_HARNESS_MAIN

From d7b135fcf82515fc3dd8081ce0f36ca4498fc050 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Mon, 17 Mar 2025 19:58:00 +0900
Subject: [PATCH 2521/2753] vhost/net: Support VIRTIO_NET_F_HASH_REPORT

VIRTIO_NET_F_HASH_REPORT allows to report hash values calculated on the
host. When VHOST_NET_F_VIRTIO_NET_HDR is employed, it will report no
hash values (i.e., the hash_report member is always set to
VIRTIO_NET_HASH_REPORT_NONE). Otherwise, the values reported by the
underlying socket will be reported.

VIRTIO_NET_F_HASH_REPORT requires VIRTIO_F_VERSION_1.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/vhost/net.c | 68 +++++++++++++++++++++++----------------------
 1 file changed, 35 insertions(+), 33 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index b9b9e9d409518..fc5b43e43a06f 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -73,6 +73,7 @@ enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
 			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+			 (1ULL << VIRTIO_NET_F_HASH_REPORT) |
 			 (1ULL << VIRTIO_F_ACCESS_PLATFORM) |
 			 (1ULL << VIRTIO_F_RING_RESET)
 };
@@ -1097,10 +1098,6 @@ static void handle_rx(struct vhost_net *net)
 		.msg_controllen = 0,
 		.msg_flags = MSG_DONTWAIT,
 	};
-	struct virtio_net_hdr hdr = {
-		.flags = 0,
-		.gso_type = VIRTIO_NET_HDR_GSO_NONE
-	};
 	size_t total_len = 0;
 	int err, mergeable;
 	s16 headcount;
@@ -1174,11 +1171,15 @@ static void handle_rx(struct vhost_net *net)
 		/* We don't need to be notified again. */
 		iov_iter_init(&msg.msg_iter, ITER_DEST, vq->iov, in, vhost_len);
 		fixup = msg.msg_iter;
-		if (unlikely((vhost_hlen))) {
-			/* We will supply the header ourselves
-			 * TODO: support TSO.
-			 */
-			iov_iter_advance(&msg.msg_iter, vhost_hlen);
+		/*
+		 * Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR
+		 * TODO: support TSO.
+		 */
+		if (unlikely(vhost_hlen) &&
+		    iov_iter_zero(vhost_hlen, &msg.msg_iter) != vhost_hlen) {
+			vq_err(vq, "Unable to write vnet_hdr at addr %p\n",
+			       vq->iov->iov_base);
+			goto out;
 		}
 		err = sock->ops->recvmsg(sock, &msg,
 					 sock_len, MSG_DONTWAIT | MSG_TRUNC);
@@ -1191,30 +1192,24 @@ static void handle_rx(struct vhost_net *net)
 			vhost_discard_vq_desc(vq, headcount);
 			continue;
 		}
-		/* Supply virtio_net_hdr if VHOST_NET_F_VIRTIO_NET_HDR */
-		if (unlikely(vhost_hlen)) {
-			if (copy_to_iter(&hdr, sizeof(hdr),
-					 &fixup) != sizeof(hdr)) {
-				vq_err(vq, "Unable to write vnet_hdr "
-				       "at addr %p\n", vq->iov->iov_base);
-				goto out;
-			}
-		} else {
-			/* Header came from socket; we'll need to patch
-			 * ->num_buffers over if VIRTIO_NET_F_MRG_RXBUF
-			 */
-			iov_iter_advance(&fixup, sizeof(hdr));
-		}
 		/* TODO: Should check and handle checksum. */
 
+		/*
+		 * We'll need to patch ->num_buffers over if
+		 * VIRTIO_NET_F_MRG_RXBUF or VIRTIO_F_VERSION_1
+		 */
 		num_buffers = cpu_to_vhost16(vq, headcount);
-		if (likely(set_num_buffers) &&
-		    copy_to_iter(&num_buffers, sizeof num_buffers,
-				 &fixup) != sizeof num_buffers) {
-			vq_err(vq, "Failed num_buffers write");
-			vhost_discard_vq_desc(vq, headcount);
-			goto out;
+		if (likely(set_num_buffers)) {
+			iov_iter_advance(&fixup, offsetof(struct virtio_net_hdr_v1, num_buffers));
+
+			if (copy_to_iter(&num_buffers, sizeof(num_buffers),
+					 &fixup) != sizeof(num_buffers)) {
+				vq_err(vq, "Failed num_buffers write");
+				vhost_discard_vq_desc(vq, headcount);
+				goto out;
+			}
 		}
+
 		nvq->done_idx += headcount;
 		if (nvq->done_idx > VHOST_NET_BATCH)
 			vhost_net_signal_used(nvq);
@@ -1607,10 +1602,13 @@ static int vhost_net_set_features(struct vhost_net *n, u64 features)
 	size_t vhost_hlen, sock_hlen, hdr_len;
 	int i;
 
-	hdr_len = (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			       (1ULL << VIRTIO_F_VERSION_1))) ?
-			sizeof(struct virtio_net_hdr_mrg_rxbuf) :
-			sizeof(struct virtio_net_hdr);
+	if (features & (1ULL << VIRTIO_NET_F_HASH_REPORT))
+		hdr_len = sizeof(struct virtio_net_hdr_v1_hash);
+	else if (features & ((1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+			     (1ULL << VIRTIO_F_VERSION_1)))
+		hdr_len = sizeof(struct virtio_net_hdr_mrg_rxbuf);
+	else
+		hdr_len = sizeof(struct virtio_net_hdr);
 	if (features & (1 << VHOST_NET_F_VIRTIO_NET_HDR)) {
 		/* vhost provides vnet_hdr */
 		vhost_hlen = hdr_len;
@@ -1691,6 +1689,10 @@ static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
 			return -EFAULT;
 		if (features & ~VHOST_NET_FEATURES)
 			return -EOPNOTSUPP;
+		if ((features & ((1ULL << VIRTIO_F_VERSION_1) |
+				 (1ULL << VIRTIO_NET_F_HASH_REPORT))) ==
+		    (1ULL << VIRTIO_NET_F_HASH_REPORT))
+			return -EINVAL;
 		return vhost_net_set_features(n, features);
 	case VHOST_GET_BACKEND_FEATURES:
 		features = VHOST_NET_BACKEND_FEATURES;

From d065b2436ff8abca94ea29b18b4664ccf3903bd1 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Mon, 17 Mar 2025 20:03:13 +0800
Subject: [PATCH 2522/2753] tcp: support TCP_RTO_MIN_US for set/getsockopt use

Support adjusting/reading RTO MIN for socket level by using set/getsockopt().

This new option has the same effect as TCP_BPF_RTO_MIN, which means it
doesn't affect RTAX_RTO_MIN usage (by using ip route...). Considering that
bpf option was implemented before this patch, so we need to use a standalone
new option for pure tcp set/getsockopt() use.

When the socket is created, its icsk_rto_min is set to the default
value that is controlled by sysctl_tcp_rto_min_us. Then if application
calls setsockopt() with TCP_RTO_MIN_US flag to pass a valid value, then
icsk_rto_min will be overridden in jiffies unit.

This patch adds WRITE_ONCE/READ_ONCE to avoid data-race around
icsk_rto_min.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/ip-sysctl.rst |  4 ++--
 include/net/tcp.h                      |  2 +-
 include/uapi/linux/tcp.h               |  1 +
 net/ipv4/tcp.c                         | 13 ++++++++++++-
 4 files changed, 16 insertions(+), 4 deletions(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 054561f8dcae7..5c63ab928b97d 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1229,8 +1229,8 @@ tcp_pingpong_thresh - INTEGER
 tcp_rto_min_us - INTEGER
 	Minimal TCP retransmission timeout (in microseconds). Note that the
 	rto_min route option has the highest precedence for configuring this
-	setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
-	this tcp_rto_min_us sysctl.
+	setting, followed by the TCP_BPF_RTO_MIN and TCP_RTO_MIN_US socket
+	options, followed by this tcp_rto_min_us sysctl.
 
 	The recommended practice is to use a value less or equal to 200000
 	microseconds.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f8efe56bbccb1..4450c384ef178 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -844,7 +844,7 @@ u32 tcp_delack_max(const struct sock *sk);
 static inline u32 tcp_rto_min(const struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = inet_csk(sk)->icsk_rto_min;
+	u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
 
 	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
 		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 92a2e79222ea5..a126b3860e63c 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -140,6 +140,7 @@ enum {
 
 #define TCP_IS_MPTCP		43	/* Is MPTCP being used? */
 #define TCP_RTO_MAX_MS		44	/* max rto time in ms */
+#define TCP_RTO_MIN_US		45	/* min rto time in us */
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fde56d28f586d..a8a1370d642eb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3352,7 +3352,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_probes_out = 0;
 	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	icsk->icsk_rto_min = TCP_RTO_MIN;
+	WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
@@ -3833,6 +3833,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val));
 		return 0;
+	case TCP_RTO_MIN_US: {
+		int rto_min = usecs_to_jiffies(val);
+
+		if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN)
+			return -EINVAL;
+		WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
+		return 0;
+	}
 	}
 
 	sockopt_lock_sock(sk);
@@ -4672,6 +4680,9 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_RTO_MAX_MS:
 		val = jiffies_to_msecs(tcp_rto_max(sk));
 		break;
+	case TCP_RTO_MIN_US:
+		val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}

From c730fe27580e1dab8d7db0a253e2c934d89d08e3 Mon Sep 17 00:00:00 2001
From: Jason Xing <kerneljasonxing@gmail.com>
Date: Mon, 17 Mar 2025 20:03:14 +0800
Subject: [PATCH 2523/2753] tcp: support TCP_DELACK_MAX_US for set/getsockopt
 use

Support adjusting/reading delayed ack max for socket level by using
set/getsockopt().

This option aligns with TCP_BPF_DELACK_MAX usage. Considering that bpf
option was implemented before this patch, so we need to use a standalone
new option for pure tcp set/getsockopt() use.

Add WRITE_ONCE/READ_ONCE() to prevent data-race if setsockopt()
happens to write one value to icsk_delack_max while icsk_delack_max is
being read.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/uapi/linux/tcp.h |  1 +
 net/ipv4/tcp.c           | 13 ++++++++++++-
 net/ipv4/tcp_output.c    |  2 +-
 3 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index a126b3860e63c..dc8fdc80e16b0 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -141,6 +141,7 @@ enum {
 #define TCP_IS_MPTCP		43	/* Is MPTCP being used? */
 #define TCP_RTO_MAX_MS		44	/* max rto time in ms */
 #define TCP_RTO_MIN_US		45	/* min rto time in us */
+#define TCP_DELACK_MAX_US	46	/* max delayed ack time in us */
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a8a1370d642eb..6edc441b37023 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3353,7 +3353,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
 	WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
-	icsk->icsk_delack_max = TCP_DELACK_MAX;
+	WRITE_ONCE(icsk->icsk_delack_max, TCP_DELACK_MAX);
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
@@ -3841,6 +3841,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 		WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
 		return 0;
 	}
+	case TCP_DELACK_MAX_US: {
+		int delack_max = usecs_to_jiffies(val);
+
+		if (delack_max > TCP_DELACK_MAX || delack_max < TCP_TIMEOUT_MIN)
+			return -EINVAL;
+		WRITE_ONCE(inet_csk(sk)->icsk_delack_max, delack_max);
+		return 0;
+	}
 	}
 
 	sockopt_lock_sock(sk);
@@ -4683,6 +4691,9 @@ int do_tcp_getsockopt(struct sock *sk, int level,
 	case TCP_RTO_MIN_US:
 		val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
 		break;
+	case TCP_DELACK_MAX_US:
+		val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_delack_max));
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index e0a4e5432399a..9a60610171145 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -4179,7 +4179,7 @@ u32 tcp_delack_max(const struct sock *sk)
 {
 	u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1;
 
-	return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min);
+	return min(READ_ONCE(inet_csk(sk)->icsk_delack_max), delack_from_rto_min);
 }
 
 /* Send out a delayed ack, the caller does the policy checking

From 703653c1b99fddacad61a05ee635122bc0a5b243 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 17 Mar 2025 14:31:49 +0200
Subject: [PATCH 2524/2753] selftests: drv-net: rss_input_xfrm: Check test
 prerequisites before running

Ensure the following prerequisites before executing the test:
1. 'socat' is installed on the remote host.
2. Python version supports socket.SO_INCOMING_CPU (available since v3.11).

Skip the test if either prerequisite is not met.

Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../testing/selftests/drivers/net/hw/rss_input_xfrm.py | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
index 53bb08cc29ec3..58d74ba6c3431 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_input_xfrm.py
@@ -7,7 +7,7 @@
 from lib.py import NetDrvEpEnv
 from lib.py import EthtoolFamily, NetdevFamily
 from lib.py import KsftSkipEx, KsftFailEx
-from lib.py import rand_port
+from lib.py import rand_port, CmdExitFailure
 
 
 def traffic(cfg, local_port, remote_port, ipver):
@@ -32,6 +32,14 @@ def test_rss_input_xfrm(cfg, ipver):
     if multiprocessing.cpu_count() < 2:
         raise KsftSkipEx("Need at least two CPUs to test symmetric RSS hash")
 
+    try:
+        cmd("hash socat", host=cfg.remote)
+    except CmdExitFailure:
+        raise KsftSkipEx("socat not installed on remote")
+
+    if not hasattr(socket, "SO_INCOMING_CPU"):
+        raise KsftSkipEx("socket.SO_INCOMING_CPU was added in Python 3.11")
+
     input_xfrm = cfg.ethnl.rss_get(
         {'header': {'dev-name': cfg.ifname}}).get('input_xfrm')
 

From dc6705907bf06035f23161b55d8d706340d8a103 Mon Sep 17 00:00:00 2001
From: Lubomir Rintel <lkundrak@v3.sk>
Date: Mon, 17 Mar 2025 16:07:37 +0100
Subject: [PATCH 2525/2753] rndis_host: Flag RNDIS modems as WWAN devices

Set FLAG_WWAN instead of FLAG_ETHERNET for RNDIS interfaces on Mobile
Broadband Modems, as opposed to regular Ethernet adapters.

Otherwise NetworkManager gets confused, misjudges the device type,
and wouldn't know it should connect a modem to get the device to work.
What would be the result depends on ModemManager version -- older
ModemManager would end up disconnecting a device after an unsuccessful
probe attempt (if it connected without needing to unlock a SIM), while
a newer one might spawn a separate PPP connection over a tty interface
instead, resulting in a general confusion and no end of chaos.

The only way to get this work reliably is to fix the device type
and have good enough version ModemManager (or equivalent).

Signed-off-by: Lubomir Rintel <lkundrak@v3.sk>
Fixes: 475ddf05ce2d ("rndis_host: Flag RNDIS modems as WWAN devices")
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/rndis_host.c | 16 ++++++++++++++--
 1 file changed, 14 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/rndis_host.c b/drivers/net/usb/rndis_host.c
index 7b3739b29c8f7..bb0bf14158727 100644
--- a/drivers/net/usb/rndis_host.c
+++ b/drivers/net/usb/rndis_host.c
@@ -630,6 +630,16 @@ static const struct driver_info	zte_rndis_info = {
 	.tx_fixup =	rndis_tx_fixup,
 };
 
+static const struct driver_info	wwan_rndis_info = {
+	.description =	"Mobile Broadband RNDIS device",
+	.flags =	FLAG_WWAN | FLAG_POINTTOPOINT | FLAG_FRAMING_RN | FLAG_NO_SETINT,
+	.bind =		rndis_bind,
+	.unbind =	rndis_unbind,
+	.status =	rndis_status,
+	.rx_fixup =	rndis_rx_fixup,
+	.tx_fixup =	rndis_tx_fixup,
+};
+
 /*-------------------------------------------------------------------------*/
 
 static const struct usb_device_id	products [] = {
@@ -666,9 +676,11 @@ static const struct usb_device_id	products [] = {
 	USB_INTERFACE_INFO(USB_CLASS_WIRELESS_CONTROLLER, 1, 3),
 	.driver_info = (unsigned long) &rndis_info,
 }, {
-	/* Novatel Verizon USB730L */
+	/* Mobile Broadband Modem, seen in Novatel Verizon USB730L and
+	 * Telit FN990A (RNDIS)
+	 */
 	USB_INTERFACE_INFO(USB_CLASS_MISC, 4, 1),
-	.driver_info = (unsigned long) &rndis_info,
+	.driver_info = (unsigned long)&wwan_rndis_info,
 },
 	{ },		// END
 };

From fbdd285407b01f8dc381ca6a6c7659192607fd08 Mon Sep 17 00:00:00 2001
From: Colin Ian King <colin.i.king@gmail.com>
Date: Mon, 17 Mar 2025 17:20:24 +0000
Subject: [PATCH 2526/2753] ice: make const read-only array dflt_rules static

Don't populate the const read-only array dflt_rules on the stack at run
time, instead make it static.

Signed-off-by: Colin Ian King <colin.i.king@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
index 1d118171de378..aceec184e89b2 100644
--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
@@ -1605,7 +1605,7 @@ void ice_fdir_replay_fltrs(struct ice_pf *pf)
  */
 int ice_fdir_create_dflt_rules(struct ice_pf *pf)
 {
-	const enum ice_fltr_ptype dflt_rules[] = {
+	static const enum ice_fltr_ptype dflt_rules[] = {
 		ICE_FLTR_PTYPE_NONF_IPV4_TCP, ICE_FLTR_PTYPE_NONF_IPV4_UDP,
 		ICE_FLTR_PTYPE_NONF_IPV6_TCP, ICE_FLTR_PTYPE_NONF_IPV6_UDP,
 	};

From 1b8b4b22a70279b1cd0faa9ff4e2fbf657621ced Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:44 +0100
Subject: [PATCH 2527/2753] net: dsa: mv88e6xxx: fix VTU methods for 6320
 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The VTU registers of the 6320 family use the 6352 semantics, not 6185.
Fix it.

Fixes: b8fee9571063 ("net: dsa: mv88e6xxx: add VLAN Get Next support")
Signed-off-by: Marek Behún <kabel@kernel.org>
Cc: <stable@vger.kernel.org> # 5.15.x
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 5db96ca52505a..06b17c3b2205c 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -5169,8 +5169,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5217,8 +5217,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.hardware_reset_pre = mv88e6xxx_g2_eeprom_wait,
 	.hardware_reset_post = mv88e6xxx_g2_eeprom_wait,
 	.reset = mv88e6352_g1_reset,
-	.vtu_getnext = mv88e6185_g1_vtu_getnext,
-	.vtu_loadpurge = mv88e6185_g1_vtu_loadpurge,
+	.vtu_getnext = mv88e6352_g1_vtu_getnext,
+	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,

From 06b17414328ec827d239620ac54445e6c6ea1218 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:45 +0100
Subject: [PATCH 2528/2753] net: dsa: mv88e6xxx: fix atu_move_port_mask for
 6341 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The atu_move_port_mask for 6341 family (Topaz) is 0xf, not 0x1f. The
PortVec field is 8 bits wide, not 11 as in 6390 family. Fix this.

Fixes: e606ca36bbf2 ("net: dsa: mv88e6xxx: rework ATU Remove")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 06b17c3b2205c..b989123cdbeb0 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -5818,7 +5818,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
@@ -6296,7 +6296,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.global1_addr = 0x1b,
 		.global2_addr = 0x1c,
 		.age_time_coeff = 3750,
-		.atu_move_port_mask = 0x1f,
+		.atu_move_port_mask = 0xf,
 		.g1_irqs = 9,
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,

From b370e62ea1dca69209a04fac363203170e95ae68 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:46 +0100
Subject: [PATCH 2529/2753] net: dsa: mv88e6xxx: enable PVT for 6321 switch
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit f36456522168 ("net: dsa: mv88e6xxx: move PVT description in
info") did not enable PVT for 6321 switch. Fix it.

Fixes: f36456522168 ("net: dsa: mv88e6xxx: move PVT description in info")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index b989123cdbeb0..3cddc8f084b37 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -6274,6 +6274,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.g2_irqs = 10,
 		.stats_type = STATS_TYPE_BANK0 | STATS_TYPE_BANK1,
 		.atu_move_port_mask = 0xf,
+		.pvt = true,
 		.multi_chip = true,
 		.edsa_support = MV88E6XXX_EDSA_SUPPORTED,
 		.ptp_support = true,

From 8da3d7c8528aee6b9f6c9e45fff1fffc57b4ed5d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:47 +0100
Subject: [PATCH 2530/2753] net: dsa: mv88e6xxx: enable .port_set_policy() for
 6320 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy")
did not add the .port_set_policy() method for the 6320 family. Fix it.

Fixes: f3a2cd326e44 ("net: dsa: mv88e6xxx: introduce .port_set_policy")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 3cddc8f084b37..f886a69d7a3ce 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -5145,6 +5145,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,
@@ -5194,6 +5195,7 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.port_set_rgmii_delay = mv88e6320_port_set_rgmii_delay,
 	.port_set_speed_duplex = mv88e6185_port_set_speed_duplex,
 	.port_tag_remap = mv88e6095_port_tag_remap,
+	.port_set_policy = mv88e6352_port_set_policy,
 	.port_set_frame_mode = mv88e6351_port_set_frame_mode,
 	.port_set_ucast_flood = mv88e6352_port_set_ucast_flood,
 	.port_set_mcast_flood = mv88e6352_port_set_mcast_flood,

From 3542f5e726bdd9409d4fa9521117ffb0f85601b6 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:48 +0100
Subject: [PATCH 2531/2753] net: dsa: mv88e6xxx: enable STU methods for 6320
 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Commit c050f5e91b47 ("net: dsa: mv88e6xxx: Fill in STU support for all
supported chips") introduced STU methods, but did not add them to the
6320 family. Fix it.

Fixes: c050f5e91b47 ("net: dsa: mv88e6xxx: Fill in STU support for all supported chips")
Signed-off-by: Marek Behún <kabel@kernel.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index f886a69d7a3ce..74b8bae226e4b 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -5172,6 +5172,8 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -5221,6 +5223,8 @@ static const struct mv88e6xxx_ops mv88e6321_ops = {
 	.reset = mv88e6352_g1_reset,
 	.vtu_getnext = mv88e6352_g1_vtu_getnext,
 	.vtu_loadpurge = mv88e6352_g1_vtu_loadpurge,
+	.stu_getnext = mv88e6352_g1_stu_getnext,
+	.stu_loadpurge = mv88e6352_g1_stu_loadpurge,
 	.gpio_ops = &mv88e6352_gpio_ops,
 	.avb_ops = &mv88e6352_avb_ops,
 	.ptp_ops = &mv88e6352_ptp_ops,
@@ -6241,6 +6245,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,
@@ -6267,6 +6272,7 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_internal_phys = 5,
 		.num_gpio = 15,
 		.max_vid = 4095,
+		.max_sid = 63,
 		.port_base_addr = 0x10,
 		.phy_base_addr = 0x0,
 		.global1_addr = 0x1b,

From 0adda5c1157edd5975c998d815a45a6f0ba12c01 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:49 +0100
Subject: [PATCH 2532/2753] net: dsa: mv88e6xxx: fix internal PHYs for 6320
 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Fix internal PHYs definition for the 6320 family, which has only 2
internal PHYs (on ports 3 and 4).

Fixes: bc3931557d1d ("net: dsa: mv88e6xxx: Add number of internal PHYs")
Signed-off-by: Marek Behún <kabel@kernel.org>
Cc: <stable@vger.kernel.org> # 6.6.x
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 74b8bae226e4b..88f479dc328ce 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -6242,7 +6242,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_databases = 4096,
 		.num_macs = 8192,
 		.num_ports = 7,
-		.num_internal_phys = 5,
+		.num_internal_phys = 2,
+		.internal_phys_offset = 3,
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.max_sid = 63,
@@ -6269,7 +6270,8 @@ static const struct mv88e6xxx_info mv88e6xxx_table[] = {
 		.num_databases = 4096,
 		.num_macs = 8192,
 		.num_ports = 7,
-		.num_internal_phys = 5,
+		.num_internal_phys = 2,
+		.internal_phys_offset = 3,
 		.num_gpio = 15,
 		.max_vid = 4095,
 		.max_sid = 63,

From 61821295eb2539773fef263047f0ea08092fd386 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Marek=20Beh=C3=BAn?= <kabel@kernel.org>
Date: Mon, 17 Mar 2025 18:32:50 +0100
Subject: [PATCH 2533/2753] net: dsa: mv88e6xxx: workaround RGMII transmit
 delay erratum for 6320 family
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Implement the workaround for erratum
  3.3 RGMII timing may be out of spec when transmit delay is enabled
for the 6320 family, which says:

  When transmit delay is enabled via Port register 1 bit 14 = 1, duty
  cycle may be out of spec. Under very rare conditions this may cause
  the attached device receive CRC errors.

Signed-off-by: Marek Behún <kabel@kernel.org>
Cc: <stable@vger.kernel.org> # 5.4.x
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/mv88e6xxx/chip.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
index 88f479dc328ce..901929f96b380 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.c
+++ b/drivers/net/dsa/mv88e6xxx/chip.c
@@ -3674,6 +3674,21 @@ static int mv88e6xxx_stats_setup(struct mv88e6xxx_chip *chip)
 	return mv88e6xxx_g1_stats_clear(chip);
 }
 
+static int mv88e6320_setup_errata(struct mv88e6xxx_chip *chip)
+{
+	u16 dummy;
+	int err;
+
+	/* Workaround for erratum
+	 *   3.3 RGMII timing may be out of spec when transmit delay is enabled
+	 */
+	err = mv88e6xxx_port_hidden_write(chip, 0, 0xf, 0x7, 0xe000);
+	if (err)
+		return err;
+
+	return mv88e6xxx_port_hidden_read(chip, 0, 0xf, 0x7, &dummy);
+}
+
 /* Check if the errata has already been applied. */
 static bool mv88e6390_setup_errata_applied(struct mv88e6xxx_chip *chip)
 {
@@ -5130,6 +5145,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = {
 
 static const struct mv88e6xxx_ops mv88e6320_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,
@@ -5182,6 +5198,7 @@ static const struct mv88e6xxx_ops mv88e6320_ops = {
 
 static const struct mv88e6xxx_ops mv88e6321_ops = {
 	/* MV88E6XXX_FAMILY_6320 */
+	.setup_errata = mv88e6320_setup_errata,
 	.ieee_pri_map = mv88e6085_g1_ieee_pri_map,
 	.ip_pri_map = mv88e6085_g1_ip_pri_map,
 	.irl_init_all = mv88e6352_g2_irl_init_all,

From 412d22f886980fc7301de12a145946afeb2dfaac Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:26 +0100
Subject: [PATCH 2534/2753] mlxsw: Trap ARP packets at layer 2 instead of layer
 3

Next patch will set the same hardware domain for all bridge ports,
including VXLAN, to prevent packets from being forwarded by software when
they were already forwarded by hardware.

ARP packets are not flooded by hardware to VXLAN, so software should handle
such flooding. When hardware domain of VXLAN device will be changed, ARP
packets which are trapped and marked with offload_fwd_mark will not be
flooded to VXLAN also in software, which will break VXLAN traffic.

To prevent such breaking, trap ARP packets at layer 2 and don't mark them
as L2-forwarded in hardware, then flooding ARP packets will be done only
in software, and VXLAN will send ARP packets.

Remove NVE_ENCAP_ARP which is no longer needed, as now ARP packets are
trapped when they enter the device.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlxsw/spectrum.c      |  2 --
 drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c | 12 ++++++------
 drivers/net/ethernet/mellanox/mlxsw/trap.h          |  5 ++---
 3 files changed, 8 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index c7e6a32582448..2bc8a3dbc836c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -2409,8 +2409,6 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = {
 	/* Multicast Router Traps */
 	MLXSW_SP_RXL_MARK(ACL1, TRAP_TO_CPU, MULTICAST, false),
 	MLXSW_SP_RXL_L3_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false),
-	/* NVE traps */
-	MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, NEIGH_DISCOVERY, false),
 };
 
 static const struct mlxsw_listener mlxsw_sp1_listener[] = {
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
index 1f9c1c86839f1..b5c3f789c685c 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c
@@ -959,18 +959,18 @@ static const struct mlxsw_sp_trap_item mlxsw_sp_trap_items_arr[] = {
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_REQUEST, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPBC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPBC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
 		.trap = MLXSW_SP_TRAP_CONTROL(ARP_RESPONSE, NEIGH_DISCOVERY,
-					      MIRROR),
+					      TRAP),
 		.listeners_arr = {
-			MLXSW_SP_RXL_MARK(ROUTER_ARPUC, NEIGH_DISCOVERY,
-					  TRAP_TO_CPU, false),
+			MLXSW_SP_RXL_NO_MARK(ARPUC, NEIGH_DISCOVERY,
+					     TRAP_TO_CPU, false),
 		},
 	},
 	{
diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h
index 83477c8e6971b..80ee5c4825dc9 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/trap.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h
@@ -29,6 +29,8 @@ enum {
 	MLXSW_TRAP_ID_FDB_MISMATCH = 0x3B,
 	MLXSW_TRAP_ID_FID_MISS = 0x3D,
 	MLXSW_TRAP_ID_DECAP_ECN0 = 0x40,
+	MLXSW_TRAP_ID_ARPBC = 0x50,
+	MLXSW_TRAP_ID_ARPUC = 0x51,
 	MLXSW_TRAP_ID_MTUERROR = 0x52,
 	MLXSW_TRAP_ID_TTLERROR = 0x53,
 	MLXSW_TRAP_ID_LBERROR = 0x54,
@@ -66,13 +68,10 @@ enum {
 	MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92,
 	MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1,
 	MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8,
-	MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD,
 	MLXSW_TRAP_ID_IPV4_BFD = 0xD0,
 	MLXSW_TRAP_ID_IPV6_BFD = 0xD1,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6,
 	MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7,
-	MLXSW_TRAP_ID_ROUTER_ARPBC = 0xE0,
-	MLXSW_TRAP_ID_ROUTER_ARPUC = 0xE1,
 	MLXSW_TRAP_ID_DISCARD_NON_ROUTABLE = 0x11A,
 	MLXSW_TRAP_ID_DISCARD_ROUTER2 = 0x130,
 	MLXSW_TRAP_ID_DISCARD_ROUTER3 = 0x131,

From 9b5dd077b76a528be225b798292ca6774ab829b7 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:27 +0100
Subject: [PATCH 2535/2753] mlxsw: spectrum: Call mlxsw_sp_bridge_vxlan_{join,
 leave}() for VLAN-aware bridge

mlxsw_sp_bridge_vxlan_{join,leave}() are not called when a VXLAN device
joins or leaves a VLAN-aware bridge. As mentioned in the comment - when the
bridge is VLAN-aware, the VNI of the VXLAN device needs to be mapped to a
VLAN, but at this point no VLANs are configured on the VxLAN device. This
means that we can call the APIs, but there is no point to do that, as they
do not configure anything in such cases.

Next patch will extend mlxsw_sp_bridge_vxlan_{join,leave}() to set hardware
domain for VXLAN, this should be done also when a VXLAN device joins or
leaves a VLAN-aware bridge. Call the APIs, which for now do not do anything
in these flows.

Align the call to mlxsw_sp_bridge_vxlan_leave() to be called like
mlxsw_sp_bridge_vxlan_join(), only in case that the VXLAN device is up,
so move the check to be done before calling
mlxsw_sp_bridge_vxlan_{join,leave}(). This does not change the existing
behavior, as there is a similar check inside mlxsw_sp_bridge_vxlan_leave().

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.c    | 20 ++++---------------
 1 file changed, 4 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
index 2bc8a3dbc836c..3080ea032e7f3 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c
@@ -5230,25 +5230,13 @@ static int mlxsw_sp_netdevice_vxlan_event(struct mlxsw_sp *mlxsw_sp,
 			return 0;
 		if (!mlxsw_sp_bridge_vxlan_is_valid(upper_dev, extack))
 			return -EOPNOTSUPP;
-		if (cu_info->linking) {
-			if (!netif_running(dev))
-				return 0;
-			/* When the bridge is VLAN-aware, the VNI of the VxLAN
-			 * device needs to be mapped to a VLAN, but at this
-			 * point no VLANs are configured on the VxLAN device
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		if (!netif_running(dev))
+			return 0;
+		if (cu_info->linking)
 			return mlxsw_sp_bridge_vxlan_join(mlxsw_sp, upper_dev,
 							  dev, 0, extack);
-		} else {
-			/* VLANs were already flushed, which triggered the
-			 * necessary cleanup
-			 */
-			if (br_vlan_enabled(upper_dev))
-				return 0;
+		else
 			mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, dev);
-		}
 		break;
 	case NETDEV_PRE_UP:
 		upper_dev = netdev_master_upper_dev_get(dev);

From a8ad615d3613bc6554bdef2a5c84b2094a5f8725 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:28 +0100
Subject: [PATCH 2536/2753] mlxsw: spectrum_switchdev: Add an internal API for
 VXLAN leave

There is asymmetry in how the VXLAN join and leave functions are used.
The join function (mlxsw_sp_bridge_vxlan_join()) is only called in
response to netdev events (e.g., VXLAN device joining a bridge), but the
leave function is also called in response to switchdev events (e.g.,
VLAN configuration on top of the VXLAN device) in order to invalidate
VNI to FID mappings.

This asymmetry will cause problems when the functions will be later
extended to mark VXLAN bridge ports as offloaded or not.

Therefore, create an internal function (__mlxsw_sp_bridge_vxlan_leave())
that is used to invalidate VNI to FID mappings and call it from
mlxsw_sp_bridge_vxlan_leave() which will only be invoked in response to
netdev events, like mlxsw_sp_bridge_vxlan_join().

No functional changes intended.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlxsw/spectrum_switchdev.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 6397ff0dc951c..c95ef79eaf3d6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2944,8 +2944,8 @@ int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 					      extack);
 }
 
-void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev)
+static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+					  const struct net_device *vxlan_dev)
 {
 	struct vxlan_dev *vxlan = netdev_priv(vxlan_dev);
 	struct mlxsw_sp_fid *fid;
@@ -2963,6 +2963,12 @@ void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_fid_put(fid);
 }
 
+void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
+				 const struct net_device *vxlan_dev)
+{
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+}
+
 static void
 mlxsw_sp_switchdev_vxlan_addr_convert(const union vxlan_addr *vxlan_addr,
 				      enum mlxsw_sp_l3proto *proto,
@@ -3867,7 +3873,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 			mlxsw_sp_fid_put(fid);
 			return -EINVAL;
 		}
-		mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+		__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 		mlxsw_sp_fid_put(fid);
 		return 0;
 	}
@@ -3883,7 +3889,7 @@ mlxsw_sp_switchdev_vxlan_vlan_add(struct mlxsw_sp *mlxsw_sp,
 	/* Fourth case: Thew new VLAN is PVID, which means the VLAN currently
 	 * mapped to the VNI should be unmapped
 	 */
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 	mlxsw_sp_fid_put(fid);
 
 	/* Fifth case: The new VLAN is also egress untagged, which means the
@@ -3923,7 +3929,7 @@ mlxsw_sp_switchdev_vxlan_vlan_del(struct mlxsw_sp *mlxsw_sp,
 	if (mlxsw_sp_fid_8021q_vid(fid) != vid)
 		goto out;
 
-	mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 
 out:
 	mlxsw_sp_fid_put(fid);

From 79b74467ef515035c8f9eaf40b3e0211511f44c0 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:29 +0100
Subject: [PATCH 2537/2753] mlxsw: spectrum_switchdev: Move
 mlxsw_sp_bridge_vxlan_join()

Next patch will call __mlxsw_sp_bridge_vxlan_leave() from
mlxsw_sp_bridge_vxlan_join() as part of error flow, move the function to
be able to call the second one.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../mellanox/mlxsw/spectrum_switchdev.c       | 30 +++++++++----------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index c95ef79eaf3d6..13ad4e31d7012 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2929,21 +2929,6 @@ void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port,
 	mlxsw_sp_bridge_port_put(mlxsw_sp->bridge, bridge_port);
 }
 
-int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
-			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
-			       struct netlink_ext_ack *extack)
-{
-	struct mlxsw_sp_bridge_device *bridge_device;
-
-	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
-	if (WARN_ON(!bridge_device))
-		return -EINVAL;
-
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
-					      extack);
-}
-
 static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 					  const struct net_device *vxlan_dev)
 {
@@ -2963,6 +2948,21 @@ static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 	mlxsw_sp_fid_put(fid);
 }
 
+int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
+			       const struct net_device *br_dev,
+			       const struct net_device *vxlan_dev, u16 vid,
+			       struct netlink_ext_ack *extack)
+{
+	struct mlxsw_sp_bridge_device *bridge_device;
+
+	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
+	if (WARN_ON(!bridge_device))
+		return -EINVAL;
+
+	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					      extack);
+}
+
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 				 const struct net_device *vxlan_dev)
 {

From 884a785d033d50ed80d810f84b25555d138b97bf Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:30 +0100
Subject: [PATCH 2538/2753] mlxsw: Add VXLAN bridge ports to same hardware
 domain as physical bridge ports

When hardware floods packets to bridge ports, but flooding to VXLAN bridge
port fails during encapsulation to one of the remote VTEPs, the packets are
trapped to CPU. In such case, the packets are marked with
skb->offload_fwd_mark, which means that packet was L2-forwarded in
hardware. Software data path repeats flooding, but packets which are
marked with skb->offload_fwd_mark will not be flooded by the bridge to
bridge ports which are in the same hardware domain as the ingress port.

Currently, mlxsw does not add VXLAN bridge ports to the same hardware
domain as physical bridge ports despite the fact that the device is able
to forward packets to and from VXLAN tunnels in hardware. In some scenarios
(as mentioned above) this can result in remote VTEPs receiving duplicate
packets. The packets are first flooded by hardware and after an
encapsulation failure, they are flooded again to all remote VTEPs by
software.

Solve this by adding VXLAN bridge ports to the same hardware domain as
physical bridge ports, so then nbp_switchdev_allowed_egress() will return
false also for VXLAN, and packets will not be sent twice from VXLAN device.

switchdev_bridge_port_offload() should get vxlan_dev not as const, so
some changes are required. Call switchdev API from
mlxsw_sp_bridge_vxlan_{join,leave}() which handle offload configurations.

Reported-by: Vladimir Oltean <olteanv@gmail.com>
Closes: https://lore.kernel.org/all/20250210152246.4ajumdchwhvbarik@skbuf/
Reported-by: Vladyslav Mykhaliuk <vmykhaliuk@nvidia.com>
Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlxsw/spectrum.h    |  4 +--
 .../mellanox/mlxsw/spectrum_switchdev.c       | 28 ++++++++++++++++---
 2 files changed, 26 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
index fa7082ee51839..37cd1d002b3be 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h
@@ -661,10 +661,10 @@ bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp,
 					 const struct net_device *br_dev);
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
+			       struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack);
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev);
+				 struct net_device *vxlan_dev);
 extern struct notifier_block mlxsw_sp_switchdev_notifier;
 
 /* spectrum.c */
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
index 13ad4e31d7012..a48bf342084da 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c
@@ -2950,22 +2950,42 @@ static void __mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
 
 int mlxsw_sp_bridge_vxlan_join(struct mlxsw_sp *mlxsw_sp,
 			       const struct net_device *br_dev,
-			       const struct net_device *vxlan_dev, u16 vid,
+			       struct net_device *vxlan_dev, u16 vid,
 			       struct netlink_ext_ack *extack)
 {
 	struct mlxsw_sp_bridge_device *bridge_device;
+	struct mlxsw_sp_port *mlxsw_sp_port;
+	int err;
 
 	bridge_device = mlxsw_sp_bridge_device_find(mlxsw_sp->bridge, br_dev);
 	if (WARN_ON(!bridge_device))
 		return -EINVAL;
 
-	return bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
-					      extack);
+	mlxsw_sp_port = mlxsw_sp_port_dev_lower_find(bridge_device->dev);
+	if (!mlxsw_sp_port)
+		return -EINVAL;
+
+	err = bridge_device->ops->vxlan_join(bridge_device, vxlan_dev, vid,
+					     extack);
+	if (err)
+		return err;
+
+	err = switchdev_bridge_port_offload(vxlan_dev, mlxsw_sp_port->dev,
+					    NULL, NULL, NULL, false, extack);
+	if (err)
+		goto err_bridge_port_offload;
+
+	return 0;
+
+err_bridge_port_offload:
+	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
+	return err;
 }
 
 void mlxsw_sp_bridge_vxlan_leave(struct mlxsw_sp *mlxsw_sp,
-				 const struct net_device *vxlan_dev)
+				 struct net_device *vxlan_dev)
 {
+	switchdev_bridge_port_unoffload(vxlan_dev, NULL, NULL, NULL);
 	__mlxsw_sp_bridge_vxlan_leave(mlxsw_sp, vxlan_dev);
 }
 

From 4f21ee969231f4201fa29de687089b00cdf0f5b8 Mon Sep 17 00:00:00 2001
From: Amit Cohen <amcohen@nvidia.com>
Date: Mon, 17 Mar 2025 18:37:31 +0100
Subject: [PATCH 2539/2753] selftests: vxlan_bridge: Test flood with unresolved
 FDB entry

Extend flood test to configure FDB entry with unresolved destination IP,
check that packets are not sent twice.

Without the previous patch which handles such scenario in mlxsw, the
tests fail:

$ TESTS='test_flood' ./vxlan_bridge_1d.sh
Running tests with UDP port 4789
TEST: VXLAN: flood                                                  [ OK ]
TEST: VXLAN: flood, unresolved FDB entry                            [FAIL]
        vx2 ns2: Expected to capture 10 packets, got 20.

$ TESTS='test_flood' ./vxlan_bridge_1q.sh
INFO: Running tests with UDP port 4789
TEST: VXLAN: flood vlan 10                                          [ OK ]
TEST: VXLAN: flood vlan 20                                          [ OK ]
TEST: VXLAN: flood vlan 10, unresolved FDB entry                    [FAIL]
        vx10 ns2: Expected to capture 10 packets, got 20.
TEST: VXLAN: flood vlan 20, unresolved FDB entry                    [FAIL]
        vx20 ns2: Expected to capture 10 packets, got 20.

With the previous patch, the tests pass.

Signed-off-by: Amit Cohen <amcohen@nvidia.com>
Reviewed-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/forwarding/vxlan_bridge_1d.sh   |  8 ++++++++
 .../selftests/net/forwarding/vxlan_bridge_1q.sh   | 15 +++++++++++++++
 2 files changed, 23 insertions(+)

diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
index 180c5eca556fe..b43816dd998ca 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1d.sh
@@ -428,6 +428,14 @@ __test_flood()
 test_flood()
 {
 	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood"
+
+	# Add an entry with arbitrary destination IP. Verify that packets are
+	# not duplicated (this can happen if hardware floods the packets, and
+	# then traps them due to misconfiguration, so software data path repeats
+	# flooding and resends packets).
+	bridge fdb append dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self
+	__test_flood de:ad:be:ef:13:37 192.0.2.100 "flood, unresolved FDB entry"
+	bridge fdb del dev vx1 00:00:00:00:00:00 dst 198.51.100.1 self
 }
 
 vxlan_fdb_add_del()
diff --git a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
index fb9a34cb50c66..afc65647f6731 100755
--- a/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
+++ b/tools/testing/selftests/net/forwarding/vxlan_bridge_1q.sh
@@ -539,6 +539,21 @@ test_flood()
 		10 10 0 10 0
 	__test_flood ca:fe:be:ef:13:37 198.51.100.100 20 "flood vlan 20" \
 		10 0 10 0 10
+
+	# Add entries with arbitrary destination IP. Verify that packets are
+	# not duplicated (this can happen if hardware floods the packets, and
+	# then traps them due to misconfiguration, so software data path repeats
+	# flooding and resends packets).
+	bridge fdb append dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self
+	bridge fdb append dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self
+
+	__test_flood de:ad:be:ef:13:37 192.0.2.100 10 \
+		"flood vlan 10, unresolved FDB entry" 10 10 0 10 0
+	__test_flood ca:fe:be:ef:13:37 198.51.100.100 20 \
+		"flood vlan 20, unresolved FDB entry" 10 0 10 0 10
+
+	bridge fdb del dev vx20 00:00:00:00:00:00 dst 203.0.113.2 self
+	bridge fdb del dev vx10 00:00:00:00:00:00 dst 203.0.113.1 self
 }
 
 vxlan_fdb_add_del()

From 48ff423e34d60ff00f0c217411f27bc5fd41630d Mon Sep 17 00:00:00 2001
From: Harshitha Ramamurthy <hramamurthy@google.com>
Date: Mon, 17 Mar 2025 21:41:41 +0000
Subject: [PATCH 2540/2753] gve: unlink old napi only if page pool exists

Commit de70981f295e ("gve: unlink old napi when stopping a queue using
queue API") unlinks the old napi when stopping a queue. But this breaks
QPL mode of the driver which does not use page pool. Fix this by checking
that there's a page pool associated with the ring.

Cc: stable@vger.kernel.org
Fixes: de70981f295e ("gve: unlink old napi when stopping a queue using queue API")
Reviewed-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 856ade0c209f6..4367c3aac698e 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -114,7 +114,8 @@ void gve_rx_stop_ring_dqo(struct gve_priv *priv, int idx)
 	if (!gve_rx_was_added_to_block(priv, idx))
 		return;
 
-	page_pool_disable_direct_recycling(rx->dqo.page_pool);
+	if (rx->dqo.page_pool)
+		page_pool_disable_direct_recycling(rx->dqo.page_pool);
 	gve_remove_napi(priv, ntfy_idx);
 	gve_rx_remove_from_block(priv, idx);
 	gve_rx_reset_ring_dqo(priv, idx);

From b1b6a1ffb1df7c9b4a9378fccbc1613783051d55 Mon Sep 17 00:00:00 2001
From: Sandro Pischinger <kernel@sandropischinger.de>
Date: Mon, 17 Mar 2025 23:43:00 +0100
Subject: [PATCH 2541/2753] lo.disable_ipv6=1 allows ::1 dst packet to take a
 default route

Hello all,

I stumbled upon an issue when disabling ipv6 just for the loopback device.
Afer doing so, sending a packet with destination ::1 will follow an available
default route, if exists, e.g. "default via fe80::2 dev ens3". This seems
to contradict RFC4291 2.5.3, which states that loopback packets must never leave
the node.

Using mainline kernel v6.14-rc7, configured with
x86_64_defconfig and kvm_guest.config on archlinux (in qemu):

$ ip -6 r
fe80::/64 dev ens3 proto kernel metric 256 pref medium
fec0::/64 dev ens3 proto ra metric 1002 pref medium
multicast ff00::/8 dev ens3 proto kernel metric 256 pref medium
default via fe80::2 dev ens3 proto ra metric 1002 pref medium

$ ip -6 r get ::1
local ::1 dev lo proto kernel src ::1 metric 0 pref medium

$ sysctl -w net.ipv6.conf.lo.disable_ipv6=1
net.ipv6.conf.lo.disable_ipv6 = 1

$ ip -6 r get ::1
::1 via fe80::2 dev ens3 proto ra src fe80::c9cb:505e:82a2:8ca7 metric 1002 pref medium

When observing trace events `fib6_table_lookup` for ping ::1, then we see that the ens3 device is selected
for the case when ipv6 is disabled for lo:
== lo.disable_ipv6=0
            ping-356   [000] .....   292.199930: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] .....   292.199932: fib6_table_lookup:    table 254 oif 0 iif 1 proto 17 ::/56460 -> ::1/1025 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] .....   292.200176: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] .....   292.200176: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] ..s2.   292.200187: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] ..s2.   292.200187: fib6_table_lookup:    table 254 oif 1 iif 1 proto 58 ::1/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] .....   293.255592: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] .....   293.255594: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] ..s2.   293.255606: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] ..s2.   293.255606: fib6_table_lookup:    table 254 oif 1 iif 1 proto 58 ::1/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] .....   294.279429: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] .....   294.279430: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] ..s2.   294.279441: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] ..s2.   294.279441: fib6_table_lookup:    table 254 oif 1 iif 1 proto 58 ::1/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] .....   295.303440: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] .....   295.303442: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0
            ping-356   [000] ..s2.   295.303451: fib6_table_lookup:    (ffffffff84041fd4)
            ping-356   [000] ..s2.   295.303452: fib6_table_lookup:    table 254 oif 1 iif 1 proto 58 ::1/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev lo gw :: err 0

== lo.disable_ipv6=1
            ping-363   [000] .....   358.104211: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   358.104213: fib6_table_lookup:    table 254 oif 0 iif 1 proto 17 ::/37566 -> ::1/1025 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   358.104453: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   358.104453: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   359.111414: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   359.111415: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   360.135436: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   360.135437: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   361.159595: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   361.159597: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   362.183614: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   362.183616: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
            ping-363   [000] .....   363.207450: fib6_table_lookup:    (ffffffff84041fd4)
            ping-363   [000] .....   363.207452: fib6_table_lookup:    table 254 oif 0 iif 1 proto 58 ::/0 -> ::1/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw fe80::2 err 0
     ksoftirqd/0-16    [000] ..s..   363.527470: fib6_table_lookup:    (ffffffff84041fd4)
     ksoftirqd/0-16    [000] ..s..   363.527471: fib6_table_lookup:    table 254 oif 0 iif 2 proto 58 fe80::2/0 -> fe80::c9cb:505e:82a2:8ca7/0 flowlabel 0 tos 0 scope 0 flags 0 ==> dev ens3 gw :: err 0

Intuitively I would expect `ping ::1` to fail with `ping: connect: Network is unreachable`,
as it does if there's no default route configured. However if there is one,
then ping just continues trying to send packets via the matching default route.

$ ping ::1
PING ::1 (::1) 56 data bytes
^C
    ::1 ping statistics ---
11 packets transmitted, 0 received, 100% packet loss, time 10230ms

Searching through the netdev mailing list archive, I found a somewaht related discussion,
where special handling for ::1 was mentioned. In particular one comment by Stephen Hemminger was:
as found in
  https://lore.kernel.org/netdev/20101216132812.2d7fd885@nehalam/
  Message-ID: <20101216132812.2d7fd885@nehalam> :

> When loopback device is being brought down, then keep the route table
> entries because they are special. The entries in the local table for
> linklocal routes and ::1 address should not be purged.

I don't understand enough of kernel IPv6 networking in order to
known if this is (still) the case today.

Is this behavior intended? If not, here's my draft patch for this, though
I'm not familiar with the codebase and cannot foresee any side-effects.

Best regards,
Sandro Pischinger

Signed-off-by: Sandro Pischinger <kernel@sandropischinger.de>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv6/route.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index c3406a0d45bd9..3ac67e1c846c3 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2193,6 +2193,12 @@ int fib6_table_lookup(struct net *net, struct fib6_table *table, int oif,
 
 redo_rt6_select:
 	rt6_select(net, fn, oif, res, strict);
+	if (ipv6_addr_loopback(&fl6->daddr)) {
+		struct fib6_info *rt = res->f6i;
+
+		if (!rt || !(rt->fib6_flags & RTF_LOCAL))
+			res->f6i = net->ipv6.fib6_null_entry;
+	}
 	if (res->f6i == net->ipv6.fib6_null_entry) {
 		fn = fib6_backtrack(fn, &fl6->saddr);
 		if (fn)

From fe164730e7db87345f99f2342a5f52915690056b Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:36 +0100
Subject: [PATCH 2542/2753] net: introduce OpenVPN Data Channel Offload (ovpn)

OpenVPN is a userspace software existing since around 2005 that allows
users to create secure tunnels.

So far OpenVPN has implemented all operations in userspace, which
implies several back and forth between kernel and user land in order to
process packets (encapsulate/decapsulate, encrypt/decrypt, rerouting..).

With `ovpn` we intend to move the fast path (data channel) entirely
in kernel space and thus improve user measured throughput over the
tunnel.

`ovpn` is implemented as a simple virtual network device driver, that
can be manipulated by means of the standard RTNL APIs. A device of kind
`ovpn` allows only IPv4/6 traffic and can be of type:
* P2P (peer-to-peer): any packet sent over the interface will be
  encapsulated and transmitted to the other side (typical OpenVPN
  client or peer-to-peer behaviour);
* P2MP (point-to-multipoint): packets sent over the interface are
  transmitted to peers based on existing routes (typical OpenVPN
  server behaviour).

After the interface has been created, OpenVPN in userspace can
configure it using a new Netlink API. Specifically it is possible
to manage peers and their keys.

The OpenVPN control channel is multiplexed over the same transport
socket by means of OP codes. Anything that is not DATA_V2 (OpenVPN
OP code for data traffic) is sent to userspace and handled there.
This way the `ovpn` codebase is kept as compact as possible while
focusing on handling data traffic only (fast path).

Any OpenVPN control feature (like cipher negotiation, TLS handshake,
rekeying, etc.) is still fully handled by the userspace process.

When userspace establishes a new connection with a peer, it first
performs the handshake and then passes the socket to the `ovpn` kernel
module, which takes ownership. From this moment on `ovpn` will handle
data traffic for the new peer.
When control packets are received on the link, they are forwarded to
userspace through the same transport socket they were received on, as
userspace is still listening to them.

Some events (like peer deletion) are sent to a Netlink multicast group.

Although it wasn't easy to convince the community, `ovpn` implements
only a limited number of the data-channel features supported by the
userspace program.

Each feature that made it to `ovpn` was attentively vetted to
avoid carrying too much legacy along with us (and to give a clear cut to
old and probalby-not-so-useful features).

Notably, only encryption using AEAD ciphers (specifically
ChaCha20Poly1305 and AES-GCM) was implemented. Supporting any other
cipher out there was not deemed useful.

Both UDP and TCP sockets are supported.

As explained above, in case of P2MP mode, OpenVPN will use the main system
routing table to decide which packet goes to which peer. This implies
that no routing table was re-implemented in the `ovpn` kernel module.

This kernel module can be enabled by selecting the CONFIG_OVPN entry
in the networking drivers section.

NOTE: this first patch introduces the very basic framework only.
Features are then added patch by patch, however, although each patch
will compile and possibly not break at runtime, only after having
applied the full set it is expected to see the ovpn module fully working.

Cc: steffen.klassert@secunet.com
Cc: antony.antony@secunet.com
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS               |   8 +++
 drivers/net/Kconfig       |   8 +++
 drivers/net/Makefile      |   1 +
 drivers/net/ovpn/Makefile |  10 ++++
 drivers/net/ovpn/main.c   | 112 ++++++++++++++++++++++++++++++++++++++
 5 files changed, 139 insertions(+)
 create mode 100644 drivers/net/ovpn/Makefile
 create mode 100644 drivers/net/ovpn/main.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 176ae661812f8..81834b3a1801b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17804,6 +17804,14 @@ F:	arch/openrisc/
 F:	drivers/irqchip/irq-ompic.c
 F:	drivers/irqchip/irq-or1k-*
 
+OPENVPN DATA CHANNEL OFFLOAD
+M:	Antonio Quartulli <antonio@openvpn.net>
+L:	openvpn-devel@lists.sourceforge.net (subscribers-only)
+L:	netdev@vger.kernel.org
+S:	Supported
+T:	git https://github.com/OpenVPN/linux-kernel-ovpn.git
+F:	drivers/net/ovpn/
+
 OPENVSWITCH
 M:	Pravin B Shelar <pshelar@ovn.org>
 L:	netdev@vger.kernel.org
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index aecfd244dd835..11ebcbf56dd54 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -115,6 +115,14 @@ config WIREGUARD_DEBUG
 
 	  Say N here unless you know what you're doing.
 
+config OVPN
+	tristate "OpenVPN data channel offload"
+	depends on NET && INET
+	depends on IPV6 || !IPV6
+	help
+	  This module enhances the performance of the OpenVPN userspace software
+	  by offloading the data channel processing to kernelspace.
+
 config EQUALIZER
 	tristate "EQL (serial line load balancing) support"
 	help
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 13743d0e83b5f..5152b3330e28d 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -11,6 +11,7 @@ obj-$(CONFIG_IPVLAN) += ipvlan/
 obj-$(CONFIG_IPVTAP) += ipvlan/
 obj-$(CONFIG_DUMMY) += dummy.o
 obj-$(CONFIG_WIREGUARD) += wireguard/
+obj-$(CONFIG_OVPN) += ovpn/
 obj-$(CONFIG_EQUALIZER) += eql.o
 obj-$(CONFIG_IFB) += ifb.o
 obj-$(CONFIG_MACSEC) += macsec.o
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
new file mode 100644
index 0000000000000..876800ebaa21a
--- /dev/null
+++ b/drivers/net/ovpn/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# ovpn -- OpenVPN data channel offload in kernel space
+#
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+# Author:	Antonio Quartulli <antonio@openvpn.net>
+
+obj-$(CONFIG_OVPN) := ovpn.o
+ovpn-y += main.o
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
new file mode 100644
index 0000000000000..e816e8fbbfeff
--- /dev/null
+++ b/drivers/net/ovpn/main.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <net/rtnetlink.h>
+
+static const struct net_device_ops ovpn_netdev_ops = {
+};
+
+/**
+ * ovpn_dev_is_valid - check if the netdevice is of type 'ovpn'
+ * @dev: the interface to check
+ *
+ * Return: whether the netdevice is of type 'ovpn'
+ */
+static bool ovpn_dev_is_valid(const struct net_device *dev)
+{
+	return dev->netdev_ops == &ovpn_netdev_ops;
+}
+
+static int ovpn_newlink(struct net_device *dev,
+			struct rtnl_newlink_params *params,
+			struct netlink_ext_ack *extack)
+{
+	return -EOPNOTSUPP;
+}
+
+static struct rtnl_link_ops ovpn_link_ops = {
+	.kind = "ovpn",
+	.netns_refund = false,
+	.newlink = ovpn_newlink,
+	.dellink = unregister_netdevice_queue,
+};
+
+static int ovpn_netdev_notifier_call(struct notifier_block *nb,
+				     unsigned long state, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	if (!ovpn_dev_is_valid(dev))
+		return NOTIFY_DONE;
+
+	switch (state) {
+	case NETDEV_REGISTER:
+		/* add device to internal list for later destruction upon
+		 * unregistration
+		 */
+		break;
+	case NETDEV_UNREGISTER:
+		/* can be delivered multiple times, so check registered flag,
+		 * then destroy the interface
+		 */
+		break;
+	case NETDEV_POST_INIT:
+	case NETDEV_GOING_DOWN:
+	case NETDEV_DOWN:
+	case NETDEV_UP:
+	case NETDEV_PRE_UP:
+	default:
+		return NOTIFY_DONE;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block ovpn_netdev_notifier = {
+	.notifier_call = ovpn_netdev_notifier_call,
+};
+
+static int __init ovpn_init(void)
+{
+	int err = register_netdevice_notifier(&ovpn_netdev_notifier);
+
+	if (err) {
+		pr_err("ovpn: can't register netdevice notifier: %d\n", err);
+		return err;
+	}
+
+	err = rtnl_link_register(&ovpn_link_ops);
+	if (err) {
+		pr_err("ovpn: can't register rtnl link ops: %d\n", err);
+		goto unreg_netdev;
+	}
+
+	return 0;
+
+unreg_netdev:
+	unregister_netdevice_notifier(&ovpn_netdev_notifier);
+	return err;
+}
+
+static __exit void ovpn_cleanup(void)
+{
+	rtnl_link_unregister(&ovpn_link_ops);
+	unregister_netdevice_notifier(&ovpn_netdev_notifier);
+
+	rcu_barrier();
+}
+
+module_init(ovpn_init);
+module_exit(ovpn_cleanup);
+
+MODULE_DESCRIPTION("OpenVPN data channel offload (ovpn)");
+MODULE_AUTHOR("(C) 2020-2025 OpenVPN, Inc.");
+MODULE_LICENSE("GPL");

From c5b34525d977de1c7cdab9a3af86d24a3877e9df Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:37 +0100
Subject: [PATCH 2543/2753] ovpn: add basic netlink support

This commit introduces basic netlink support with family
registration/unregistration functionalities and stub pre/post-doit.

More importantly it introduces the YAML uAPI description along
with its auto-generated files:
- include/uapi/linux/ovpn.h
- drivers/net/ovpn/netlink-gen.c
- drivers/net/ovpn/netlink-gen.h

Reviewed-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/ovpn.yaml | 367 ++++++++++++++++++++++++++
 MAINTAINERS                           |   2 +
 drivers/net/ovpn/Makefile             |   2 +
 drivers/net/ovpn/main.c               |  17 +-
 drivers/net/ovpn/main.h               |  14 +
 drivers/net/ovpn/netlink-gen.c        | 213 +++++++++++++++
 drivers/net/ovpn/netlink-gen.h        |  41 +++
 drivers/net/ovpn/netlink.c            | 160 +++++++++++
 drivers/net/ovpn/netlink.h            |  15 ++
 drivers/net/ovpn/ovpnpriv.h           |  21 ++
 include/uapi/linux/ovpn.h             | 109 ++++++++
 11 files changed, 960 insertions(+), 1 deletion(-)
 create mode 100644 Documentation/netlink/specs/ovpn.yaml
 create mode 100644 drivers/net/ovpn/main.h
 create mode 100644 drivers/net/ovpn/netlink-gen.c
 create mode 100644 drivers/net/ovpn/netlink-gen.h
 create mode 100644 drivers/net/ovpn/netlink.c
 create mode 100644 drivers/net/ovpn/netlink.h
 create mode 100644 drivers/net/ovpn/ovpnpriv.h
 create mode 100644 include/uapi/linux/ovpn.h

diff --git a/Documentation/netlink/specs/ovpn.yaml b/Documentation/netlink/specs/ovpn.yaml
new file mode 100644
index 0000000000000..6f131bead88f8
--- /dev/null
+++ b/Documentation/netlink/specs/ovpn.yaml
@@ -0,0 +1,367 @@
+# SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+#
+# Author: Antonio Quartulli <antonio@openvpn.net>
+#
+# Copyright (c) 2024-2025, OpenVPN Inc.
+#
+
+name: ovpn
+
+protocol: genetlink
+
+doc: Netlink protocol to control OpenVPN network devices
+
+definitions:
+  -
+    type: const
+    name: nonce-tail-size
+    value: 8
+  -
+    type: enum
+    name: cipher-alg
+    entries: [ none, aes-gcm, chacha20-poly1305 ]
+  -
+    type: enum
+    name: del-peer-reason
+    entries:
+      - teardown
+      - userspace
+      - expired
+      - transport-error
+      - transport-disconnect
+  -
+    type: enum
+    name: key-slot
+    entries: [ primary, secondary ]
+
+attribute-sets:
+  -
+    name: peer
+    attributes:
+      -
+        name: id
+        type: u32
+        doc: >-
+          The unique ID of the peer in the device context. To be used to identify
+          peers during operations for a specific device
+        checks:
+          max: 0xFFFFFF
+      -
+        name: remote-ipv4
+        type: u32
+        doc: The remote IPv4 address of the peer
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: remote-ipv6
+        type: binary
+        doc: The remote IPv6 address of the peer
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: remote-ipv6-scope-id
+        type: u32
+        doc: The scope id of the remote IPv6 address of the peer (RFC2553)
+      -
+        name: remote-port
+        type: u16
+        doc: The remote port of the peer
+        byte-order: big-endian
+        checks:
+          min: 1
+      -
+        name: socket
+        type: u32
+        doc: The socket to be used to communicate with the peer
+      -
+        name: socket-netnsid
+        type: s32
+        doc: The ID of the netns the socket assigned to this peer lives in
+      -
+        name: vpn-ipv4
+        type: u32
+        doc: The IPv4 address assigned to the peer by the server
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: vpn-ipv6
+        type: binary
+        doc: The IPv6 address assigned to the peer by the server
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: local-ipv4
+        type: u32
+        doc: The local IPv4 to be used to send packets to the peer (UDP only)
+        byte-order: big-endian
+        display-hint: ipv4
+      -
+        name: local-ipv6
+        type: binary
+        doc: The local IPv6 to be used to send packets to the peer (UDP only)
+        display-hint: ipv6
+        checks:
+          exact-len: 16
+      -
+        name: local-port
+        type: u16
+        doc: The local port to be used to send packets to the peer (UDP only)
+        byte-order: big-endian
+        checks:
+          min: 1
+      -
+        name: keepalive-interval
+        type: u32
+        doc: >-
+          The number of seconds after which a keep alive message is sent to the
+          peer
+      -
+        name: keepalive-timeout
+        type: u32
+        doc: >-
+          The number of seconds from the last activity after which the peer is
+          assumed dead
+      -
+        name: del-reason
+        type: u32
+        doc: The reason why a peer was deleted
+        enum: del-peer-reason
+      -
+        name: vpn-rx-bytes
+        type: uint
+        doc: Number of bytes received over the tunnel
+      -
+        name: vpn-tx-bytes
+        type: uint
+        doc: Number of bytes transmitted over the tunnel
+      -
+        name: vpn-rx-packets
+        type: uint
+        doc: Number of packets received over the tunnel
+      -
+        name: vpn-tx-packets
+        type: uint
+        doc: Number of packets transmitted over the tunnel
+      -
+        name: link-rx-bytes
+        type: uint
+        doc: Number of bytes received at the transport level
+      -
+        name: link-tx-bytes
+        type: uint
+        doc: Number of bytes transmitted at the transport level
+      -
+        name: link-rx-packets
+        type: uint
+        doc: Number of packets received at the transport level
+      -
+        name: link-tx-packets
+        type: uint
+        doc: Number of packets transmitted at the transport level
+  -
+    name: keyconf
+    attributes:
+      -
+        name: peer-id
+        type: u32
+        doc: >-
+          The unique ID of the peer in the device context. To be used to
+          identify peers during key operations
+        checks:
+          max: 0xFFFFFF
+      -
+        name: slot
+        type: u32
+        doc: The slot where the key should be stored
+        enum: key-slot
+      -
+        name: key-id
+        doc: >-
+          The unique ID of the key in the peer context. Used to fetch the
+          correct key upon decryption
+        type: u32
+        checks:
+          max: 7
+      -
+        name: cipher-alg
+        type: u32
+        doc: The cipher to be used when communicating with the peer
+        enum: cipher-alg
+      -
+        name: encrypt-dir
+        type: nest
+        doc: Key material for encrypt direction
+        nested-attributes: keydir
+      -
+        name: decrypt-dir
+        type: nest
+        doc: Key material for decrypt direction
+        nested-attributes: keydir
+  -
+    name: keydir
+    attributes:
+      -
+        name: cipher-key
+        type: binary
+        doc: The actual key to be used by the cipher
+        checks:
+         max-len: 256
+      -
+        name: nonce-tail
+        type: binary
+        doc: >-
+          Random nonce to be concatenated to the packet ID, in order to
+          obtain the actual cipher IV
+        checks:
+         exact-len: nonce-tail-size
+  -
+    name: ovpn
+    attributes:
+      -
+        name: ifindex
+        type: u32
+        doc: Index of the ovpn interface to operate on
+      -
+        name: peer
+        type: nest
+        doc: >-
+          The peer object containing the attributed of interest for the specific
+          operation
+        nested-attributes: peer
+      -
+        name: keyconf
+        type: nest
+        doc: Peer specific cipher configuration
+        nested-attributes: keyconf
+
+operations:
+  list:
+    -
+      name: peer-new
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Add a remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-set
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: modify a remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-get
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Retrieve data about existing remote peers (or a specific one)
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+        reply:
+          attributes:
+            - peer
+      dump:
+        request:
+          attributes:
+            - ifindex
+        reply:
+          attributes:
+            - peer
+    -
+      name: peer-del
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Delete existing remote peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - peer
+    -
+      name: peer-del-ntf
+      doc: Notification about a peer being deleted
+      notify: peer-get
+      mcgrp: peers
+
+    -
+      name: key-new
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Add a cipher key for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+    -
+      name: key-get
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Retrieve non-sensitive data about peer key and cipher
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+        reply:
+          attributes:
+            - keyconf
+    -
+      name: key-swap
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Swap primary and secondary session keys for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+    -
+      name: key-swap-ntf
+      notify: key-get
+      doc: >-
+        Notification about key having exhausted its IV space and requiring
+        renegotiation
+      mcgrp: peers
+    -
+      name: key-del
+      attribute-set: ovpn
+      flags: [ admin-perm ]
+      doc: Delete cipher key for a specific peer
+      do:
+        pre: ovpn-nl-pre-doit
+        post: ovpn-nl-post-doit
+        request:
+          attributes:
+            - ifindex
+            - keyconf
+
+mcast-groups:
+  list:
+    -
+      name: peers
diff --git a/MAINTAINERS b/MAINTAINERS
index 81834b3a1801b..5d058e9b4628c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17810,7 +17810,9 @@ L:	openvpn-devel@lists.sourceforge.net (subscribers-only)
 L:	netdev@vger.kernel.org
 S:	Supported
 T:	git https://github.com/OpenVPN/linux-kernel-ovpn.git
+F:	Documentation/netlink/specs/ovpn.yaml
 F:	drivers/net/ovpn/
+F:	include/uapi/linux/ovpn.h
 
 OPENVSWITCH
 M:	Pravin B Shelar <pshelar@ovn.org>
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 876800ebaa21a..75ac62bba0293 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -8,3 +8,5 @@
 
 obj-$(CONFIG_OVPN) := ovpn.o
 ovpn-y += main.o
+ovpn-y += netlink.o
+ovpn-y += netlink-gen.o
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index e816e8fbbfeff..28133e7e15e74 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -7,9 +7,15 @@
  *		James Yonan <james@openvpn.net>
  */
 
+#include <linux/genetlink.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <net/rtnetlink.h>
+#include <uapi/linux/ovpn.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "netlink.h"
 
 static const struct net_device_ops ovpn_netdev_ops = {
 };
@@ -20,7 +26,7 @@ static const struct net_device_ops ovpn_netdev_ops = {
  *
  * Return: whether the netdevice is of type 'ovpn'
  */
-static bool ovpn_dev_is_valid(const struct net_device *dev)
+bool ovpn_dev_is_valid(const struct net_device *dev)
 {
 	return dev->netdev_ops == &ovpn_netdev_ops;
 }
@@ -89,8 +95,16 @@ static int __init ovpn_init(void)
 		goto unreg_netdev;
 	}
 
+	err = ovpn_nl_register();
+	if (err) {
+		pr_err("ovpn: can't register netlink family: %d\n", err);
+		goto unreg_rtnl;
+	}
+
 	return 0;
 
+unreg_rtnl:
+	rtnl_link_unregister(&ovpn_link_ops);
 unreg_netdev:
 	unregister_netdevice_notifier(&ovpn_netdev_notifier);
 	return err;
@@ -98,6 +112,7 @@ static int __init ovpn_init(void)
 
 static __exit void ovpn_cleanup(void)
 {
+	ovpn_nl_unregister();
 	rtnl_link_unregister(&ovpn_link_ops);
 	unregister_netdevice_notifier(&ovpn_netdev_notifier);
 
diff --git a/drivers/net/ovpn/main.h b/drivers/net/ovpn/main.h
new file mode 100644
index 0000000000000..017cd01007659
--- /dev/null
+++ b/drivers/net/ovpn/main.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_MAIN_H_
+#define _NET_OVPN_MAIN_H_
+
+bool ovpn_dev_is_valid(const struct net_device *dev);
+
+#endif /* _NET_OVPN_MAIN_H_ */
diff --git a/drivers/net/ovpn/netlink-gen.c b/drivers/net/ovpn/netlink-gen.c
new file mode 100644
index 0000000000000..58e1a4342378e
--- /dev/null
+++ b/drivers/net/ovpn/netlink-gen.c
@@ -0,0 +1,213 @@
+// SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause)
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netlink-gen.h"
+
+#include <uapi/linux/ovpn.h>
+
+/* Integer value ranges */
+static const struct netlink_range_validation ovpn_a_peer_id_range = {
+	.max	= 16777215ULL,
+};
+
+static const struct netlink_range_validation ovpn_a_keyconf_peer_id_range = {
+	.max	= 16777215ULL,
+};
+
+/* Common nested types */
+const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1] = {
+	[OVPN_A_KEYCONF_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_keyconf_peer_id_range),
+	[OVPN_A_KEYCONF_SLOT] = NLA_POLICY_MAX(NLA_U32, 1),
+	[OVPN_A_KEYCONF_KEY_ID] = NLA_POLICY_MAX(NLA_U32, 7),
+	[OVPN_A_KEYCONF_CIPHER_ALG] = NLA_POLICY_MAX(NLA_U32, 2),
+	[OVPN_A_KEYCONF_ENCRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy),
+	[OVPN_A_KEYCONF_DECRYPT_DIR] = NLA_POLICY_NESTED(ovpn_keydir_nl_policy),
+};
+
+const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1] = {
+	[OVPN_A_KEYDIR_CIPHER_KEY] = NLA_POLICY_MAX_LEN(256),
+	[OVPN_A_KEYDIR_NONCE_TAIL] = NLA_POLICY_EXACT_LEN(OVPN_NONCE_TAIL_SIZE),
+};
+
+const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1] = {
+	[OVPN_A_PEER_ID] = NLA_POLICY_FULL_RANGE(NLA_U32, &ovpn_a_peer_id_range),
+	[OVPN_A_PEER_REMOTE_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_REMOTE_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID] = { .type = NLA_U32, },
+	[OVPN_A_PEER_REMOTE_PORT] = NLA_POLICY_MIN(NLA_BE16, 1),
+	[OVPN_A_PEER_SOCKET] = { .type = NLA_U32, },
+	[OVPN_A_PEER_SOCKET_NETNSID] = { .type = NLA_S32, },
+	[OVPN_A_PEER_VPN_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_VPN_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_LOCAL_IPV4] = { .type = NLA_BE32, },
+	[OVPN_A_PEER_LOCAL_IPV6] = NLA_POLICY_EXACT_LEN(16),
+	[OVPN_A_PEER_LOCAL_PORT] = NLA_POLICY_MIN(NLA_BE16, 1),
+	[OVPN_A_PEER_KEEPALIVE_INTERVAL] = { .type = NLA_U32, },
+	[OVPN_A_PEER_KEEPALIVE_TIMEOUT] = { .type = NLA_U32, },
+	[OVPN_A_PEER_DEL_REASON] = NLA_POLICY_MAX(NLA_U32, 4),
+	[OVPN_A_PEER_VPN_RX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_TX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_RX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_VPN_TX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_RX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_TX_BYTES] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_RX_PACKETS] = { .type = NLA_UINT, },
+	[OVPN_A_PEER_LINK_TX_PACKETS] = { .type = NLA_UINT, },
+};
+
+/* OVPN_CMD_PEER_NEW - do */
+static const struct nla_policy ovpn_peer_new_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_SET - do */
+static const struct nla_policy ovpn_peer_set_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_GET - do */
+static const struct nla_policy ovpn_peer_get_do_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_PEER_GET - dump */
+static const struct nla_policy ovpn_peer_get_dump_nl_policy[OVPN_A_IFINDEX + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+};
+
+/* OVPN_CMD_PEER_DEL - do */
+static const struct nla_policy ovpn_peer_del_nl_policy[OVPN_A_PEER + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_PEER] = NLA_POLICY_NESTED(ovpn_peer_nl_policy),
+};
+
+/* OVPN_CMD_KEY_NEW - do */
+static const struct nla_policy ovpn_key_new_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_GET - do */
+static const struct nla_policy ovpn_key_get_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_SWAP - do */
+static const struct nla_policy ovpn_key_swap_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* OVPN_CMD_KEY_DEL - do */
+static const struct nla_policy ovpn_key_del_nl_policy[OVPN_A_KEYCONF + 1] = {
+	[OVPN_A_IFINDEX] = { .type = NLA_U32, },
+	[OVPN_A_KEYCONF] = NLA_POLICY_NESTED(ovpn_keyconf_nl_policy),
+};
+
+/* Ops table for ovpn */
+static const struct genl_split_ops ovpn_nl_ops[] = {
+	{
+		.cmd		= OVPN_CMD_PEER_NEW,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_new_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_new_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_SET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_set_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_set_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_GET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_get_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_get_do_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_GET,
+		.dumpit		= ovpn_nl_peer_get_dumpit,
+		.policy		= ovpn_peer_get_dump_nl_policy,
+		.maxattr	= OVPN_A_IFINDEX,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
+	},
+	{
+		.cmd		= OVPN_CMD_PEER_DEL,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_peer_del_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_peer_del_nl_policy,
+		.maxattr	= OVPN_A_PEER,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_NEW,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_new_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_new_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_GET,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_get_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_get_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_SWAP,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_swap_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_swap_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd		= OVPN_CMD_KEY_DEL,
+		.pre_doit	= ovpn_nl_pre_doit,
+		.doit		= ovpn_nl_key_del_doit,
+		.post_doit	= ovpn_nl_post_doit,
+		.policy		= ovpn_key_del_nl_policy,
+		.maxattr	= OVPN_A_KEYCONF,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
+};
+
+static const struct genl_multicast_group ovpn_nl_mcgrps[] = {
+	[OVPN_NLGRP_PEERS] = { "peers", },
+};
+
+struct genl_family ovpn_nl_family __ro_after_init = {
+	.name		= OVPN_FAMILY_NAME,
+	.version	= OVPN_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= ovpn_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(ovpn_nl_ops),
+	.mcgrps		= ovpn_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(ovpn_nl_mcgrps),
+};
diff --git a/drivers/net/ovpn/netlink-gen.h b/drivers/net/ovpn/netlink-gen.h
new file mode 100644
index 0000000000000..66a4e4a0a055b
--- /dev/null
+++ b/drivers/net/ovpn/netlink-gen.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_OVPN_GEN_H
+#define _LINUX_OVPN_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/ovpn.h>
+
+/* Common nested types */
+extern const struct nla_policy ovpn_keyconf_nl_policy[OVPN_A_KEYCONF_DECRYPT_DIR + 1];
+extern const struct nla_policy ovpn_keydir_nl_policy[OVPN_A_KEYDIR_NONCE_TAIL + 1];
+extern const struct nla_policy ovpn_peer_nl_policy[OVPN_A_PEER_LINK_TX_PACKETS + 1];
+
+int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info);
+void
+ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		  struct genl_info *info);
+
+int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info);
+int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info);
+
+enum {
+	OVPN_NLGRP_PEERS,
+};
+
+extern struct genl_family ovpn_nl_family;
+
+#endif /* _LINUX_OVPN_GEN_H */
diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
new file mode 100644
index 0000000000000..8d267d4c82283
--- /dev/null
+++ b/drivers/net/ovpn/netlink.c
@@ -0,0 +1,160 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <net/genetlink.h>
+
+#include <uapi/linux/ovpn.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "netlink.h"
+#include "netlink-gen.h"
+
+MODULE_ALIAS_GENL_FAMILY(OVPN_FAMILY_NAME);
+
+/**
+ * ovpn_get_dev_from_attrs - retrieve the ovpn private data from the netdevice
+ *			     a netlink message is targeting
+ * @net: network namespace where to look for the interface
+ * @info: generic netlink info from the user request
+ * @tracker: tracker object to be used for the netdev reference acquisition
+ *
+ * Return: the ovpn private data, if found, or an error otherwise
+ */
+static struct ovpn_priv *
+ovpn_get_dev_from_attrs(struct net *net, const struct genl_info *info,
+			netdevice_tracker *tracker)
+{
+	struct ovpn_priv *ovpn;
+	struct net_device *dev;
+	int ifindex;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_IFINDEX))
+		return ERR_PTR(-EINVAL);
+
+	ifindex = nla_get_u32(info->attrs[OVPN_A_IFINDEX]);
+
+	rcu_read_lock();
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (!dev) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "ifindex does not match any interface");
+		return ERR_PTR(-ENODEV);
+	}
+
+	if (!ovpn_dev_is_valid(dev)) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "specified interface is not ovpn");
+		NL_SET_BAD_ATTR(info->extack, info->attrs[OVPN_A_IFINDEX]);
+		return ERR_PTR(-EINVAL);
+	}
+
+	ovpn = netdev_priv(dev);
+	netdev_hold(dev, tracker, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return ovpn;
+}
+
+int ovpn_nl_pre_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		     struct genl_info *info)
+{
+	netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1];
+	struct ovpn_priv *ovpn = ovpn_get_dev_from_attrs(genl_info_net(info),
+							 info, tracker);
+
+	if (IS_ERR(ovpn))
+		return PTR_ERR(ovpn);
+
+	info->user_ptr[0] = ovpn;
+
+	return 0;
+}
+
+void ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
+		       struct genl_info *info)
+{
+	netdevice_tracker *tracker = (netdevice_tracker *)&info->user_ptr[1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+
+	if (ovpn)
+		netdev_put(ovpn->dev, tracker);
+}
+
+int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ovpn_nl_register - perform any needed registration in the NL subsustem
+ *
+ * Return: 0 on success, a negative error code otherwise
+ */
+int __init ovpn_nl_register(void)
+{
+	int ret = genl_register_family(&ovpn_nl_family);
+
+	if (ret) {
+		pr_err("ovpn: genl_register_family failed: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_unregister - undo any module wide netlink registration
+ */
+void ovpn_nl_unregister(void)
+{
+	genl_unregister_family(&ovpn_nl_family);
+}
diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h
new file mode 100644
index 0000000000000..0d6c34e17082c
--- /dev/null
+++ b/drivers/net/ovpn/netlink.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_NETLINK_H_
+#define _NET_OVPN_NETLINK_H_
+
+int ovpn_nl_register(void);
+void ovpn_nl_unregister(void);
+
+#endif /* _NET_OVPN_NETLINK_H_ */
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
new file mode 100644
index 0000000000000..f9322536b06d6
--- /dev/null
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNSTRUCT_H_
+#define _NET_OVPN_OVPNSTRUCT_H_
+
+/**
+ * struct ovpn_priv - per ovpn interface state
+ * @dev: the actual netdev representing the tunnel
+ */
+struct ovpn_priv {
+	struct net_device *dev;
+};
+
+#endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/include/uapi/linux/ovpn.h b/include/uapi/linux/ovpn.h
new file mode 100644
index 0000000000000..680d1522dc87c
--- /dev/null
+++ b/include/uapi/linux/ovpn.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/ovpn.yaml */
+/* YNL-GEN uapi header */
+
+#ifndef _UAPI_LINUX_OVPN_H
+#define _UAPI_LINUX_OVPN_H
+
+#define OVPN_FAMILY_NAME	"ovpn"
+#define OVPN_FAMILY_VERSION	1
+
+#define OVPN_NONCE_TAIL_SIZE	8
+
+enum ovpn_cipher_alg {
+	OVPN_CIPHER_ALG_NONE,
+	OVPN_CIPHER_ALG_AES_GCM,
+	OVPN_CIPHER_ALG_CHACHA20_POLY1305,
+};
+
+enum ovpn_del_peer_reason {
+	OVPN_DEL_PEER_REASON_TEARDOWN,
+	OVPN_DEL_PEER_REASON_USERSPACE,
+	OVPN_DEL_PEER_REASON_EXPIRED,
+	OVPN_DEL_PEER_REASON_TRANSPORT_ERROR,
+	OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT,
+};
+
+enum ovpn_key_slot {
+	OVPN_KEY_SLOT_PRIMARY,
+	OVPN_KEY_SLOT_SECONDARY,
+};
+
+enum {
+	OVPN_A_PEER_ID = 1,
+	OVPN_A_PEER_REMOTE_IPV4,
+	OVPN_A_PEER_REMOTE_IPV6,
+	OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+	OVPN_A_PEER_REMOTE_PORT,
+	OVPN_A_PEER_SOCKET,
+	OVPN_A_PEER_SOCKET_NETNSID,
+	OVPN_A_PEER_VPN_IPV4,
+	OVPN_A_PEER_VPN_IPV6,
+	OVPN_A_PEER_LOCAL_IPV4,
+	OVPN_A_PEER_LOCAL_IPV6,
+	OVPN_A_PEER_LOCAL_PORT,
+	OVPN_A_PEER_KEEPALIVE_INTERVAL,
+	OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+	OVPN_A_PEER_DEL_REASON,
+	OVPN_A_PEER_VPN_RX_BYTES,
+	OVPN_A_PEER_VPN_TX_BYTES,
+	OVPN_A_PEER_VPN_RX_PACKETS,
+	OVPN_A_PEER_VPN_TX_PACKETS,
+	OVPN_A_PEER_LINK_RX_BYTES,
+	OVPN_A_PEER_LINK_TX_BYTES,
+	OVPN_A_PEER_LINK_RX_PACKETS,
+	OVPN_A_PEER_LINK_TX_PACKETS,
+
+	__OVPN_A_PEER_MAX,
+	OVPN_A_PEER_MAX = (__OVPN_A_PEER_MAX - 1)
+};
+
+enum {
+	OVPN_A_KEYCONF_PEER_ID = 1,
+	OVPN_A_KEYCONF_SLOT,
+	OVPN_A_KEYCONF_KEY_ID,
+	OVPN_A_KEYCONF_CIPHER_ALG,
+	OVPN_A_KEYCONF_ENCRYPT_DIR,
+	OVPN_A_KEYCONF_DECRYPT_DIR,
+
+	__OVPN_A_KEYCONF_MAX,
+	OVPN_A_KEYCONF_MAX = (__OVPN_A_KEYCONF_MAX - 1)
+};
+
+enum {
+	OVPN_A_KEYDIR_CIPHER_KEY = 1,
+	OVPN_A_KEYDIR_NONCE_TAIL,
+
+	__OVPN_A_KEYDIR_MAX,
+	OVPN_A_KEYDIR_MAX = (__OVPN_A_KEYDIR_MAX - 1)
+};
+
+enum {
+	OVPN_A_IFINDEX = 1,
+	OVPN_A_PEER,
+	OVPN_A_KEYCONF,
+
+	__OVPN_A_MAX,
+	OVPN_A_MAX = (__OVPN_A_MAX - 1)
+};
+
+enum {
+	OVPN_CMD_PEER_NEW = 1,
+	OVPN_CMD_PEER_SET,
+	OVPN_CMD_PEER_GET,
+	OVPN_CMD_PEER_DEL,
+	OVPN_CMD_PEER_DEL_NTF,
+	OVPN_CMD_KEY_NEW,
+	OVPN_CMD_KEY_GET,
+	OVPN_CMD_KEY_SWAP,
+	OVPN_CMD_KEY_SWAP_NTF,
+	OVPN_CMD_KEY_DEL,
+
+	__OVPN_CMD_MAX,
+	OVPN_CMD_MAX = (__OVPN_CMD_MAX - 1)
+};
+
+#define OVPN_MCGRP_PEERS	"peers"
+
+#endif /* _UAPI_LINUX_OVPN_H */

From 93b40d2d7cd795b1d062adf4c6bde0654f8c357a Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:38 +0100
Subject: [PATCH 2544/2753] ovpn: add basic interface
 creation/destruction/management routines

Add basic infrastructure for handling ovpn interfaces.

Tested-by: Donald Hunter <donald.hunter@gmail.com>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/rt_link.yaml | 16 ++++
 drivers/net/ovpn/Makefile                |  1 +
 drivers/net/ovpn/io.c                    | 22 ++++++
 drivers/net/ovpn/io.h                    | 24 ++++++
 drivers/net/ovpn/main.c                  | 99 ++++++++++++++++++++++--
 drivers/net/ovpn/ovpnpriv.h              |  7 ++
 drivers/net/ovpn/proto.h                 | 38 +++++++++
 include/uapi/linux/if_link.h             | 15 ++++
 8 files changed, 217 insertions(+), 5 deletions(-)
 create mode 100644 drivers/net/ovpn/io.c
 create mode 100644 drivers/net/ovpn/io.h
 create mode 100644 drivers/net/ovpn/proto.h

diff --git a/Documentation/netlink/specs/rt_link.yaml b/Documentation/netlink/specs/rt_link.yaml
index 31238455f8e9d..a50d9d7d882e7 100644
--- a/Documentation/netlink/specs/rt_link.yaml
+++ b/Documentation/netlink/specs/rt_link.yaml
@@ -938,6 +938,12 @@ definitions:
     entries:
       - name: none
       - name: default
+  -
+    name: ovpn-mode
+    type: enum
+    entries:
+      - p2p
+      - mp
 
 attribute-sets:
   -
@@ -2272,6 +2278,13 @@ attribute-sets:
       -
         name: tailroom
         type: u16
+  -
+    name: linkinfo-ovpn-attrs
+    attributes:
+      -
+        name: mode
+        type: u8
+        enum: ovpn-mode
 
 sub-messages:
   -
@@ -2322,6 +2335,9 @@ sub-messages:
       -
         value: netkit
         attribute-set: linkinfo-netkit-attrs
+      -
+        value: ovpn
+        attribute-set: linkinfo-ovpn-attrs
   -
     name: linkinfo-member-data-msg
     formats:
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 75ac62bba0293..0e5f686672fb5 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -8,5 +8,6 @@
 
 obj-$(CONFIG_OVPN) := ovpn.o
 ovpn-y += main.o
+ovpn-y += io.o
 ovpn-y += netlink.o
 ovpn-y += netlink-gen.o
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
new file mode 100644
index 0000000000000..4b71c38165d7a
--- /dev/null
+++ b/drivers/net/ovpn/io.c
@@ -0,0 +1,22 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+
+#include "io.h"
+
+/* Send user data to the network
+ */
+netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	skb_tx_error(skb);
+	kfree_skb(skb);
+	return NET_XMIT_DROP;
+}
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
new file mode 100644
index 0000000000000..afea5f81f5628
--- /dev/null
+++ b/drivers/net/ovpn/io.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPN_H_
+#define _NET_OVPN_OVPN_H_
+
+/* DATA_V2 header size with AEAD encryption */
+#define OVPN_HEAD_ROOM (OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE +	   \
+			16 /* AEAD TAG length */ +			   \
+			max(sizeof(struct udphdr), sizeof(struct tcphdr)) +\
+			max(sizeof(struct ipv6hdr), sizeof(struct iphdr)))
+
+/* max padding required by encryption */
+#define OVPN_MAX_PADDING 16
+
+netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
+
+#endif /* _NET_OVPN_OVPN_H_ */
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 28133e7e15e74..b19f1406d87d5 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -10,14 +10,28 @@
 #include <linux/genetlink.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <net/ip.h>
 #include <net/rtnetlink.h>
-#include <uapi/linux/ovpn.h>
+#include <uapi/linux/if_arp.h>
 
 #include "ovpnpriv.h"
 #include "main.h"
 #include "netlink.h"
+#include "io.h"
+#include "proto.h"
 
 static const struct net_device_ops ovpn_netdev_ops = {
+	.ndo_start_xmit		= ovpn_net_xmit,
+};
+
+static const struct device_type ovpn_type = {
+	.name = OVPN_FAMILY_NAME,
+};
+
+static const struct nla_policy ovpn_policy[IFLA_OVPN_MAX + 1] = {
+	[IFLA_OVPN_MODE] = NLA_POLICY_RANGE(NLA_U8, OVPN_MODE_P2P,
+					    OVPN_MODE_MP),
 };
 
 /**
@@ -31,44 +45,119 @@ bool ovpn_dev_is_valid(const struct net_device *dev)
 	return dev->netdev_ops == &ovpn_netdev_ops;
 }
 
+static void ovpn_setup(struct net_device *dev)
+{
+	netdev_features_t feat = NETIF_F_SG | NETIF_F_GSO |
+				 NETIF_F_GSO_SOFTWARE | NETIF_F_HIGHDMA;
+
+	dev->needs_free_netdev = true;
+
+	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
+
+	dev->netdev_ops = &ovpn_netdev_ops;
+
+	dev->hard_header_len = 0;
+	dev->addr_len = 0;
+	dev->mtu = ETH_DATA_LEN - OVPN_HEAD_ROOM;
+	dev->min_mtu = IPV4_MIN_MTU;
+	dev->max_mtu = IP_MAX_MTU - OVPN_HEAD_ROOM;
+
+	dev->type = ARPHRD_NONE;
+	dev->flags = IFF_POINTOPOINT | IFF_NOARP;
+	dev->priv_flags |= IFF_NO_QUEUE;
+
+	dev->lltx = true;
+	dev->features |= feat;
+	dev->hw_features |= feat;
+	dev->hw_enc_features |= feat;
+
+	dev->needed_headroom = ALIGN(OVPN_HEAD_ROOM, 4);
+	dev->needed_tailroom = OVPN_MAX_PADDING;
+
+	SET_NETDEV_DEVTYPE(dev, &ovpn_type);
+}
+
 static int ovpn_newlink(struct net_device *dev,
 			struct rtnl_newlink_params *params,
 			struct netlink_ext_ack *extack)
 {
-	return -EOPNOTSUPP;
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+	struct nlattr **data = params->data;
+	enum ovpn_mode mode = OVPN_MODE_P2P;
+
+	if (data && data[IFLA_OVPN_MODE]) {
+		mode = nla_get_u8(data[IFLA_OVPN_MODE]);
+		netdev_dbg(dev, "setting device mode: %u\n", mode);
+	}
+
+	ovpn->dev = dev;
+	ovpn->mode = mode;
+
+	/* turn carrier explicitly off after registration, this way state is
+	 * clearly defined
+	 */
+	netif_carrier_off(dev);
+
+	return register_netdevice(dev);
+}
+
+static int ovpn_fill_info(struct sk_buff *skb, const struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	if (nla_put_u8(skb, IFLA_OVPN_MODE, ovpn->mode))
+		return -EMSGSIZE;
+
+	return 0;
 }
 
 static struct rtnl_link_ops ovpn_link_ops = {
 	.kind = "ovpn",
 	.netns_refund = false,
+	.priv_size = sizeof(struct ovpn_priv),
+	.setup = ovpn_setup,
+	.policy = ovpn_policy,
+	.maxtype = IFLA_OVPN_MAX,
 	.newlink = ovpn_newlink,
 	.dellink = unregister_netdevice_queue,
+	.fill_info = ovpn_fill_info,
 };
 
 static int ovpn_netdev_notifier_call(struct notifier_block *nb,
 				     unsigned long state, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct ovpn_priv *ovpn;
 
 	if (!ovpn_dev_is_valid(dev))
 		return NOTIFY_DONE;
 
+	ovpn = netdev_priv(dev);
+
 	switch (state) {
 	case NETDEV_REGISTER:
-		/* add device to internal list for later destruction upon
-		 * unregistration
-		 */
+		ovpn->registered = true;
 		break;
 	case NETDEV_UNREGISTER:
+		/* twiddle thumbs on netns device moves */
+		if (dev->reg_state != NETREG_UNREGISTERING)
+			break;
+
 		/* can be delivered multiple times, so check registered flag,
 		 * then destroy the interface
 		 */
+		if (!ovpn->registered)
+			return NOTIFY_DONE;
+
+		netif_carrier_off(dev);
+		ovpn->registered = false;
 		break;
 	case NETDEV_POST_INIT:
 	case NETDEV_GOING_DOWN:
 	case NETDEV_DOWN:
 	case NETDEV_UP:
 	case NETDEV_PRE_UP:
+		break;
 	default:
 		return NOTIFY_DONE;
 	}
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index f9322536b06d6..33c2a41edf9b3 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -10,12 +10,19 @@
 #ifndef _NET_OVPN_OVPNSTRUCT_H_
 #define _NET_OVPN_OVPNSTRUCT_H_
 
+#include <uapi/linux/if_link.h>
+#include <uapi/linux/ovpn.h>
+
 /**
  * struct ovpn_priv - per ovpn interface state
  * @dev: the actual netdev representing the tunnel
+ * @registered: whether dev is still registered with netdev or not
+ * @mode: device operation mode (i.e. p2p, mp, ..)
  */
 struct ovpn_priv {
 	struct net_device *dev;
+	bool registered;
+	enum ovpn_mode mode;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h
new file mode 100644
index 0000000000000..5f95a78bebd37
--- /dev/null
+++ b/drivers/net/ovpn/proto.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_PROTO_H_
+#define _NET_OVPN_PROTO_H_
+
+/* When the OpenVPN protocol is ran in AEAD mode, use
+ * the OpenVPN packet ID as the AEAD nonce:
+ *
+ *    00000005 521c3b01 4308c041
+ *    [seq # ] [  nonce_tail   ]
+ *    [     12-byte full IV    ] -> OVPN_NONCE_SIZE
+ *    [4-bytes                   -> OVPN_NONCE_WIRE_SIZE
+ *    on wire]
+ */
+
+/* nonce size (96bits) as required by AEAD ciphers */
+#define OVPN_NONCE_SIZE			12
+/* last 8 bytes of AEAD nonce: provided by userspace and usually derived
+ * from key material generated during TLS handshake
+ */
+#define OVPN_NONCE_TAIL_SIZE		8
+
+/* OpenVPN nonce size reduced by 8-byte nonce tail -- this is the
+ * size of the AEAD Associated Data (AD) sent over the wire
+ * and is normally the head of the IV
+ */
+#define OVPN_NONCE_WIRE_SIZE (OVPN_NONCE_SIZE - OVPN_NONCE_TAIL_SIZE)
+
+#define OVPN_OPCODE_SIZE		4 /* DATA_V2 opcode size */
+
+#endif /* _NET_OVPN_PROTO_H_ */
diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 318386cc5b0d1..3ad2d5d980347 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -1986,4 +1986,19 @@ enum {
 
 #define IFLA_DSA_MAX	(__IFLA_DSA_MAX - 1)
 
+/* OVPN section */
+
+enum ovpn_mode {
+	OVPN_MODE_P2P,
+	OVPN_MODE_MP,
+};
+
+enum {
+	IFLA_OVPN_UNSPEC,
+	IFLA_OVPN_MODE,
+	__IFLA_OVPN_MAX,
+};
+
+#define IFLA_OVPN_MAX	(__IFLA_OVPN_MAX - 1)
+
 #endif /* _UAPI_LINUX_IF_LINK_H */

From 47a6157ef300e22aaea63a3c46776d039b89f459 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:39 +0100
Subject: [PATCH 2545/2753] ovpn: keep carrier always on for MP interfaces

An ovpn interface configured in MP mode will keep carrier always
on and let the user decide when to bring it administratively up and
down.

This way a MP node (i.e. a server) will keep its interface always
up and running, even when no peer is connected.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/main.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index b19f1406d87d5..15802dfd26fcb 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -21,7 +21,22 @@
 #include "io.h"
 #include "proto.h"
 
+static int ovpn_net_open(struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	/* carrier for P2P interfaces is switched on and off when
+	 * the peer is added or deleted.
+	 *
+	 * in case of P2MP interfaces we just keep the carrier always on
+	 */
+	if (ovpn->mode == OVPN_MODE_MP)
+		netif_carrier_on(dev);
+	return 0;
+}
+
 static const struct net_device_ops ovpn_netdev_ops = {
+	.ndo_open		= ovpn_net_open,
 	.ndo_start_xmit		= ovpn_net_xmit,
 };
 

From b9bbf258103cb9b95dbb729610565923d36139fd Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:40 +0100
Subject: [PATCH 2546/2753] ovpn: introduce the ovpn_peer object

An ovpn_peer object holds the whole status of a remote peer
(regardless whether it is a server or a client).

This includes status for crypto, tx/rx buffers, napi, etc.

Only support for one peer is introduced (P2P mode).
Multi peer support is introduced with a later patch.

Along with the ovpn_peer, also the ovpn_bind object is introcued
as the two are strictly related.
An ovpn_bind object wraps a sockaddr representing the local
coordinates being used to talk to a specific peer.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/Kconfig         |   1 +
 drivers/net/ovpn/Makefile   |   2 +
 drivers/net/ovpn/bind.c     |  58 +++++
 drivers/net/ovpn/bind.h     | 101 +++++++++
 drivers/net/ovpn/main.c     |  12 ++
 drivers/net/ovpn/ovpnpriv.h |   4 +
 drivers/net/ovpn/peer.c     | 411 ++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/peer.h     |  80 +++++++
 8 files changed, 669 insertions(+)
 create mode 100644 drivers/net/ovpn/bind.c
 create mode 100644 drivers/net/ovpn/bind.h
 create mode 100644 drivers/net/ovpn/peer.c
 create mode 100644 drivers/net/ovpn/peer.h

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 11ebcbf56dd54..5e224c4541173 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -119,6 +119,7 @@ config OVPN
 	tristate "OpenVPN data channel offload"
 	depends on NET && INET
 	depends on IPV6 || !IPV6
+	select DST_CACHE
 	help
 	  This module enhances the performance of the OpenVPN userspace software
 	  by offloading the data channel processing to kernelspace.
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 0e5f686672fb5..618328ae33886 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -7,7 +7,9 @@
 # Author:	Antonio Quartulli <antonio@openvpn.net>
 
 obj-$(CONFIG_OVPN) := ovpn.o
+ovpn-y += bind.o
 ovpn-y += main.o
 ovpn-y += io.o
 ovpn-y += netlink.o
 ovpn-y += netlink-gen.o
+ovpn-y += peer.o
diff --git a/drivers/net/ovpn/bind.c b/drivers/net/ovpn/bind.c
new file mode 100644
index 0000000000000..d4a1aeed12c99
--- /dev/null
+++ b/drivers/net/ovpn/bind.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2012-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+
+#include "ovpnpriv.h"
+#include "bind.h"
+#include "peer.h"
+
+/**
+ * ovpn_bind_from_sockaddr - retrieve binding matching sockaddr
+ * @ss: the sockaddr to match
+ *
+ * Return: the bind matching the passed sockaddr if found, NULL otherwise
+ */
+struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *ss)
+{
+	struct ovpn_bind *bind;
+	size_t sa_len;
+
+	if (ss->ss_family == AF_INET)
+		sa_len = sizeof(struct sockaddr_in);
+	else if (ss->ss_family == AF_INET6)
+		sa_len = sizeof(struct sockaddr_in6);
+	else
+		return ERR_PTR(-EAFNOSUPPORT);
+
+	bind = kzalloc(sizeof(*bind), GFP_ATOMIC);
+	if (unlikely(!bind))
+		return ERR_PTR(-ENOMEM);
+
+	memcpy(&bind->remote, ss, sa_len);
+
+	return bind;
+}
+
+/**
+ * ovpn_bind_reset - assign new binding to peer
+ * @peer: the peer whose binding has to be replaced
+ * @new: the new bind to assign
+ */
+void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *new)
+{
+	struct ovpn_bind *old;
+
+	spin_lock_bh(&peer->lock);
+	old = rcu_replace_pointer(peer->bind, new, true);
+	spin_unlock_bh(&peer->lock);
+
+	kfree_rcu(old, rcu);
+}
diff --git a/drivers/net/ovpn/bind.h b/drivers/net/ovpn/bind.h
new file mode 100644
index 0000000000000..4e0b8398bfd9e
--- /dev/null
+++ b/drivers/net/ovpn/bind.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2012-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNBIND_H_
+#define _NET_OVPN_OVPNBIND_H_
+
+#include <net/ip.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/rcupdate.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+
+struct ovpn_peer;
+
+/**
+ * union ovpn_sockaddr - basic transport layer address
+ * @in4: IPv4 address
+ * @in6: IPv6 address
+ */
+union ovpn_sockaddr {
+	struct sockaddr_in in4;
+	struct sockaddr_in6 in6;
+};
+
+/**
+ * struct ovpn_bind - remote peer binding
+ * @remote: the remote peer sockaddress
+ * @local: local endpoint used to talk to the peer
+ * @local.ipv4: local IPv4 used to talk to the peer
+ * @local.ipv6: local IPv6 used to talk to the peer
+ * @rcu: used to schedule RCU cleanup job
+ */
+struct ovpn_bind {
+	union ovpn_sockaddr remote;  /* remote sockaddr */
+
+	union {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	} local;
+
+	struct rcu_head rcu;
+};
+
+/**
+ * ovpn_bind_skb_src_match - match packet source with binding
+ * @bind: the binding to match
+ * @skb: the packet to match
+ *
+ * Return: true if the packet source matches the remote peer sockaddr
+ * in the binding
+ */
+static inline bool ovpn_bind_skb_src_match(const struct ovpn_bind *bind,
+					   const struct sk_buff *skb)
+{
+	const union ovpn_sockaddr *remote;
+
+	if (unlikely(!bind))
+		return false;
+
+	remote = &bind->remote;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		if (unlikely(remote->in4.sin_family != AF_INET))
+			return false;
+
+		if (unlikely(remote->in4.sin_addr.s_addr != ip_hdr(skb)->saddr))
+			return false;
+
+		if (unlikely(remote->in4.sin_port != udp_hdr(skb)->source))
+			return false;
+		break;
+	case htons(ETH_P_IPV6):
+		if (unlikely(remote->in6.sin6_family != AF_INET6))
+			return false;
+
+		if (unlikely(!ipv6_addr_equal(&remote->in6.sin6_addr,
+					      &ipv6_hdr(skb)->saddr)))
+			return false;
+
+		if (unlikely(remote->in6.sin6_port != udp_hdr(skb)->source))
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *sa);
+void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *bind);
+
+#endif /* _NET_OVPN_OVPNBIND_H_ */
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 15802dfd26fcb..49e39ca11310e 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -19,8 +19,14 @@
 #include "main.h"
 #include "netlink.h"
 #include "io.h"
+#include "peer.h"
 #include "proto.h"
 
+static int ovpn_net_init(struct net_device *dev)
+{
+	return 0;
+}
+
 static int ovpn_net_open(struct net_device *dev)
 {
 	struct ovpn_priv *ovpn = netdev_priv(dev);
@@ -36,6 +42,7 @@ static int ovpn_net_open(struct net_device *dev)
 }
 
 static const struct net_device_ops ovpn_netdev_ops = {
+	.ndo_init		= ovpn_net_init,
 	.ndo_open		= ovpn_net_open,
 	.ndo_start_xmit		= ovpn_net_xmit,
 };
@@ -107,6 +114,7 @@ static int ovpn_newlink(struct net_device *dev,
 
 	ovpn->dev = dev;
 	ovpn->mode = mode;
+	spin_lock_init(&ovpn->lock);
 
 	/* turn carrier explicitly off after registration, this way state is
 	 * clearly defined
@@ -166,6 +174,10 @@ static int ovpn_netdev_notifier_call(struct notifier_block *nb,
 
 		netif_carrier_off(dev);
 		ovpn->registered = false;
+
+		if (ovpn->mode == OVPN_MODE_P2P)
+			ovpn_peer_release_p2p(ovpn,
+					      OVPN_DEL_PEER_REASON_TEARDOWN);
 		break;
 	case NETDEV_POST_INIT:
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index 33c2a41edf9b3..fae2682b424b0 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -18,11 +18,15 @@
  * @dev: the actual netdev representing the tunnel
  * @registered: whether dev is still registered with netdev or not
  * @mode: device operation mode (i.e. p2p, mp, ..)
+ * @lock: protect this object
+ * @peer: in P2P mode, this is the only remote peer
  */
 struct ovpn_priv {
 	struct net_device *dev;
 	bool registered;
 	enum ovpn_mode mode;
+	spinlock_t lock; /* protect writing to the ovpn_priv object */
+	struct ovpn_peer __rcu *peer;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
new file mode 100644
index 0000000000000..338069c99248f
--- /dev/null
+++ b/drivers/net/ovpn/peer.c
@@ -0,0 +1,411 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/skbuff.h>
+#include <linux/list.h>
+
+#include "ovpnpriv.h"
+#include "bind.h"
+#include "io.h"
+#include "main.h"
+#include "netlink.h"
+#include "peer.h"
+
+static void unlock_ovpn(struct ovpn_priv *ovpn,
+			struct llist_head *release_list)
+	__releases(&ovpn->lock)
+{
+	struct ovpn_peer *peer;
+
+	spin_unlock_bh(&ovpn->lock);
+
+	llist_for_each_entry(peer, release_list->first, release_entry)
+		ovpn_peer_put(peer);
+}
+
+/**
+ * ovpn_peer_new - allocate and initialize a new peer object
+ * @ovpn: the openvpn instance inside which the peer should be created
+ * @id: the ID assigned to this peer
+ *
+ * Return: a pointer to the new peer on success or an error code otherwise
+ */
+struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
+{
+	struct ovpn_peer *peer;
+	int ret;
+
+	/* alloc and init peer object */
+	peer = kzalloc(sizeof(*peer), GFP_KERNEL);
+	if (!peer)
+		return ERR_PTR(-ENOMEM);
+
+	peer->id = id;
+	peer->ovpn = ovpn;
+
+	peer->vpn_addrs.ipv4.s_addr = htonl(INADDR_ANY);
+	peer->vpn_addrs.ipv6 = in6addr_any;
+
+	RCU_INIT_POINTER(peer->bind, NULL);
+	spin_lock_init(&peer->lock);
+	kref_init(&peer->refcount);
+
+	ret = dst_cache_init(&peer->dst_cache, GFP_KERNEL);
+	if (ret < 0) {
+		netdev_err(ovpn->dev,
+			   "cannot initialize dst cache for peer %u\n",
+			   peer->id);
+		kfree(peer);
+		return ERR_PTR(ret);
+	}
+
+	netdev_hold(ovpn->dev, &peer->dev_tracker, GFP_KERNEL);
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_release_rcu - RCU callback performing last peer release steps
+ * @head: RCU member of the ovpn_peer
+ */
+static void ovpn_peer_release_rcu(struct rcu_head *head)
+{
+	struct ovpn_peer *peer = container_of(head, struct ovpn_peer, rcu);
+
+	/* this call will immediately free the dst_cache, therefore we
+	 * perform it in the RCU callback, when all contexts are done
+	 */
+	dst_cache_destroy(&peer->dst_cache);
+	kfree(peer);
+}
+
+/**
+ * ovpn_peer_release - release peer private members
+ * @peer: the peer to release
+ */
+static void ovpn_peer_release(struct ovpn_peer *peer)
+{
+	ovpn_bind_reset(peer, NULL);
+	call_rcu(&peer->rcu, ovpn_peer_release_rcu);
+	netdev_put(peer->ovpn->dev, &peer->dev_tracker);
+}
+
+/**
+ * ovpn_peer_release_kref - callback for kref_put
+ * @kref: the kref object belonging to the peer
+ */
+void ovpn_peer_release_kref(struct kref *kref)
+{
+	struct ovpn_peer *peer = container_of(kref, struct ovpn_peer, refcount);
+
+	ovpn_peer_release(peer);
+}
+
+/**
+ * ovpn_peer_skb_to_sockaddr - fill sockaddr with skb source address
+ * @skb: the packet to extract data from
+ * @ss: the sockaddr to fill
+ *
+ * Return: sockaddr length on success or -1 otherwise
+ */
+static int ovpn_peer_skb_to_sockaddr(struct sk_buff *skb,
+				     struct sockaddr_storage *ss)
+{
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		sa4 = (struct sockaddr_in *)ss;
+		sa4->sin_family = AF_INET;
+		sa4->sin_addr.s_addr = ip_hdr(skb)->saddr;
+		sa4->sin_port = udp_hdr(skb)->source;
+		return sizeof(*sa4);
+	case htons(ETH_P_IPV6):
+		sa6 = (struct sockaddr_in6 *)ss;
+		sa6->sin6_family = AF_INET6;
+		sa6->sin6_addr = ipv6_hdr(skb)->saddr;
+		sa6->sin6_port = udp_hdr(skb)->source;
+		return sizeof(*sa6);
+	}
+
+	return -1;
+}
+
+/**
+ * ovpn_peer_transp_match - check if sockaddr and peer binding match
+ * @peer: the peer to get the binding from
+ * @ss: the sockaddr to match
+ *
+ * Return: true if sockaddr and binding match or false otherwise
+ */
+static bool ovpn_peer_transp_match(const struct ovpn_peer *peer,
+				   const struct sockaddr_storage *ss)
+{
+	struct ovpn_bind *bind = rcu_dereference(peer->bind);
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+
+	if (unlikely(!bind))
+		return false;
+
+	if (ss->ss_family != bind->remote.in4.sin_family)
+		return false;
+
+	switch (ss->ss_family) {
+	case AF_INET:
+		sa4 = (struct sockaddr_in *)ss;
+		if (sa4->sin_addr.s_addr != bind->remote.in4.sin_addr.s_addr)
+			return false;
+		if (sa4->sin_port != bind->remote.in4.sin_port)
+			return false;
+		break;
+	case AF_INET6:
+		sa6 = (struct sockaddr_in6 *)ss;
+		if (!ipv6_addr_equal(&sa6->sin6_addr,
+				     &bind->remote.in6.sin6_addr))
+			return false;
+		if (sa6->sin6_port != bind->remote.in6.sin6_port)
+			return false;
+		break;
+	default:
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * ovpn_peer_get_by_transp_addr_p2p - get peer by transport address in a P2P
+ *                                    instance
+ * @ovpn: the openvpn instance to search
+ * @ss: the transport socket address
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *
+ovpn_peer_get_by_transp_addr_p2p(struct ovpn_priv *ovpn,
+				 struct sockaddr_storage *ss)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+
+	rcu_read_lock();
+	tmp = rcu_dereference(ovpn->peer);
+	if (likely(tmp && ovpn_peer_transp_match(tmp, ss) &&
+		   ovpn_peer_hold(tmp)))
+		peer = tmp;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_transp_addr - retrieve peer by transport address
+ * @ovpn: the openvpn instance to search
+ * @skb: the skb to retrieve the source transport address from
+ *
+ * Return: a pointer to the peer if found or NULL otherwise
+ */
+struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
+					       struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = NULL;
+	struct sockaddr_storage ss = { 0 };
+
+	if (unlikely(!ovpn_peer_skb_to_sockaddr(skb, &ss)))
+		return NULL;
+
+	if (ovpn->mode == OVPN_MODE_P2P)
+		peer = ovpn_peer_get_by_transp_addr_p2p(ovpn, &ss);
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_id_p2p - get peer by ID in a P2P instance
+ * @ovpn: the openvpn instance to search
+ * @peer_id: the ID of the peer to find
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_id_p2p(struct ovpn_priv *ovpn,
+						 u32 peer_id)
+{
+	struct ovpn_peer *tmp, *peer = NULL;
+
+	rcu_read_lock();
+	tmp = rcu_dereference(ovpn->peer);
+	if (likely(tmp && tmp->id == peer_id && ovpn_peer_hold(tmp)))
+		peer = tmp;
+	rcu_read_unlock();
+
+	return peer;
+}
+
+/**
+ * ovpn_peer_get_by_id - retrieve peer by ID
+ * @ovpn: the openvpn instance to search
+ * @peer_id: the unique peer identifier to match
+ *
+ * Return: a pointer to the peer if found or NULL otherwise
+ */
+struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id)
+{
+	struct ovpn_peer *peer = NULL;
+
+	if (ovpn->mode == OVPN_MODE_P2P)
+		peer = ovpn_peer_get_by_id_p2p(ovpn, peer_id);
+
+	return peer;
+}
+
+static void ovpn_peer_remove(struct ovpn_peer *peer,
+			     enum ovpn_del_peer_reason reason,
+			     struct llist_head *release_list)
+{
+	switch (peer->ovpn->mode) {
+	case OVPN_MODE_P2P:
+		/* prevent double remove */
+		if (peer != rcu_access_pointer(peer->ovpn->peer))
+			return;
+
+		RCU_INIT_POINTER(peer->ovpn->peer, NULL);
+		/* in P2P mode the carrier is switched off when the peer is
+		 * deleted so that third party protocols can react accordingly
+		 */
+		netif_carrier_off(peer->ovpn->dev);
+		break;
+	default:
+		return;
+	}
+
+	peer->delete_reason = reason;
+
+	/* append to provided list for later socket release and ref drop */
+	llist_add(&peer->release_entry, release_list);
+}
+
+/**
+ * ovpn_peer_add_p2p - add peer to related tables in a P2P instance
+ * @ovpn: the instance to add the peer to
+ * @peer: the peer to add
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *tmp;
+
+	spin_lock_bh(&ovpn->lock);
+	/* in p2p mode it is possible to have a single peer only, therefore the
+	 * old one is released and substituted by the new one
+	 */
+	tmp = rcu_dereference_protected(ovpn->peer,
+					lockdep_is_held(&ovpn->lock));
+	if (tmp)
+		ovpn_peer_remove(tmp, OVPN_DEL_PEER_REASON_TEARDOWN,
+				 &release_list);
+
+	rcu_assign_pointer(ovpn->peer, peer);
+	/* in P2P mode the carrier is switched on when the peer is added */
+	netif_carrier_on(ovpn->dev);
+	unlock_ovpn(ovpn, &release_list);
+
+	return 0;
+}
+
+/**
+ * ovpn_peer_add - add peer to the related tables
+ * @ovpn: the openvpn instance the peer belongs to
+ * @peer: the peer object to add
+ *
+ * Assume refcounter was increased by caller
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	switch (ovpn->mode) {
+	case OVPN_MODE_P2P:
+		return ovpn_peer_add_p2p(ovpn, peer);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/**
+ * ovpn_peer_del_p2p - delete peer from related tables in a P2P instance
+ * @peer: the peer to delete
+ * @reason: reason why the peer was deleted (sent to userspace)
+ * @release_list: list where delete peer should be appended
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_del_p2p(struct ovpn_peer *peer,
+			     enum ovpn_del_peer_reason reason,
+			     struct llist_head *release_list)
+{
+	struct ovpn_peer *tmp;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	tmp = rcu_dereference_protected(peer->ovpn->peer,
+					lockdep_is_held(&peer->ovpn->lock));
+	if (tmp != peer)
+		return -ENOENT;
+
+	ovpn_peer_remove(peer, reason, release_list);
+
+	return 0;
+}
+
+/**
+ * ovpn_peer_del - delete peer from related tables
+ * @peer: the peer object to delete
+ * @reason: reason for deleting peer (will be sent to userspace)
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason)
+{
+	LLIST_HEAD(release_list);
+	int ret = -EOPNOTSUPP;
+
+	spin_lock_bh(&peer->ovpn->lock);
+	switch (peer->ovpn->mode) {
+	case OVPN_MODE_P2P:
+		ret = ovpn_peer_del_p2p(peer, reason, &release_list);
+		break;
+	default:
+		break;
+	}
+	unlock_ovpn(peer->ovpn, &release_list);
+
+	return ret;
+}
+
+/**
+ * ovpn_peer_release_p2p - release peer upon P2P device teardown
+ * @ovpn: the instance being torn down
+ * @reason: the reason for releasing the peer
+ */
+void ovpn_peer_release_p2p(struct ovpn_priv *ovpn,
+			   enum ovpn_del_peer_reason reason)
+{
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *peer;
+
+	spin_lock_bh(&ovpn->lock);
+	peer = rcu_dereference_protected(ovpn->peer,
+					 lockdep_is_held(&ovpn->lock));
+	if (peer)
+		ovpn_peer_remove(peer, reason, &release_list);
+	unlock_ovpn(ovpn, &release_list);
+}
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
new file mode 100644
index 0000000000000..fd2e7625990a7
--- /dev/null
+++ b/drivers/net/ovpn/peer.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNPEER_H_
+#define _NET_OVPN_OVPNPEER_H_
+
+#include <net/dst_cache.h>
+
+/**
+ * struct ovpn_peer - the main remote peer object
+ * @ovpn: main openvpn instance this peer belongs to
+ * @dev_tracker: reference tracker for associated dev
+ * @id: unique identifier
+ * @vpn_addrs: IP addresses assigned over the tunnel
+ * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
+ * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
+ * @dst_cache: cache for dst_entry used to send to peer
+ * @bind: remote peer binding
+ * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
+ * @lock: protects binding to peer (bind)
+ * @refcount: reference counter
+ * @rcu: used to free peer in an RCU safe way
+ * @release_entry: entry for the socket release list
+ */
+struct ovpn_peer {
+	struct ovpn_priv *ovpn;
+	netdevice_tracker dev_tracker;
+	u32 id;
+	struct {
+		struct in_addr ipv4;
+		struct in6_addr ipv6;
+	} vpn_addrs;
+	struct dst_cache dst_cache;
+	struct ovpn_bind __rcu *bind;
+	enum ovpn_del_peer_reason delete_reason;
+	spinlock_t lock; /* protects bind */
+	struct kref refcount;
+	struct rcu_head rcu;
+	struct llist_node release_entry;
+};
+
+/**
+ * ovpn_peer_hold - increase reference counter
+ * @peer: the peer whose counter should be increased
+ *
+ * Return: true if the counter was increased or false if it was zero already
+ */
+static inline bool ovpn_peer_hold(struct ovpn_peer *peer)
+{
+	return kref_get_unless_zero(&peer->refcount);
+}
+
+void ovpn_peer_release_kref(struct kref *kref);
+
+/**
+ * ovpn_peer_put - decrease reference counter
+ * @peer: the peer whose counter should be decreased
+ */
+static inline void ovpn_peer_put(struct ovpn_peer *peer)
+{
+	kref_put(&peer->refcount, ovpn_peer_release_kref);
+}
+
+struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id);
+int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer);
+int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason);
+void ovpn_peer_release_p2p(struct ovpn_priv *ovpn,
+			   enum ovpn_del_peer_reason reason);
+
+struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
+					       struct sk_buff *skb);
+struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id);
+
+#endif /* _NET_OVPN_OVPNPEER_H_ */

From dcd11fbd6bc03d90a49c46324a99d678772400f3 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:41 +0100
Subject: [PATCH 2547/2753] ovpn: introduce the ovpn_socket object

This specific structure is used in the ovpn kernel module
to wrap and carry around a standard kernel socket.

ovpn takes ownership of passed sockets and therefore an ovpn
specific objects is attached to them for status tracking
purposes.

Initially only UDP support is introduced. TCP will come in a later
patch.

Cc: willemdebruijn.kernel@gmail.com
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/Makefile |   2 +
 drivers/net/ovpn/main.c   |   2 +-
 drivers/net/ovpn/peer.c   |  28 ++++-
 drivers/net/ovpn/peer.h   |   6 +-
 drivers/net/ovpn/socket.c | 208 ++++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/socket.h |  38 +++++++
 drivers/net/ovpn/udp.c    |  75 ++++++++++++++
 drivers/net/ovpn/udp.h    |  19 ++++
 include/uapi/linux/udp.h  |   1 +
 9 files changed, 372 insertions(+), 7 deletions(-)
 create mode 100644 drivers/net/ovpn/socket.c
 create mode 100644 drivers/net/ovpn/socket.h
 create mode 100644 drivers/net/ovpn/udp.c
 create mode 100644 drivers/net/ovpn/udp.h

diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 618328ae33886..164f2058ea8e6 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -13,3 +13,5 @@ ovpn-y += io.o
 ovpn-y += netlink.o
 ovpn-y += netlink-gen.o
 ovpn-y += peer.o
+ovpn-y += socket.o
+ovpn-y += udp.o
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 49e39ca11310e..6f3f649bdf2d8 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -176,7 +176,7 @@ static int ovpn_netdev_notifier_call(struct notifier_block *nb,
 		ovpn->registered = false;
 
 		if (ovpn->mode == OVPN_MODE_P2P)
-			ovpn_peer_release_p2p(ovpn,
+			ovpn_peer_release_p2p(ovpn, NULL,
 					      OVPN_DEL_PEER_REASON_TEARDOWN);
 		break;
 	case NETDEV_POST_INIT:
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 338069c99248f..0bb6c15171848 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -16,17 +16,20 @@
 #include "main.h"
 #include "netlink.h"
 #include "peer.h"
+#include "socket.h"
 
 static void unlock_ovpn(struct ovpn_priv *ovpn,
-			struct llist_head *release_list)
+			 struct llist_head *release_list)
 	__releases(&ovpn->lock)
 {
 	struct ovpn_peer *peer;
 
 	spin_unlock_bh(&ovpn->lock);
 
-	llist_for_each_entry(peer, release_list->first, release_entry)
+	llist_for_each_entry(peer, release_list->first, release_entry) {
+		ovpn_socket_release(peer);
 		ovpn_peer_put(peer);
+	}
 }
 
 /**
@@ -394,18 +397,33 @@ int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason)
 /**
  * ovpn_peer_release_p2p - release peer upon P2P device teardown
  * @ovpn: the instance being torn down
+ * @sk: if not NULL, release peer only if it's using this specific socket
  * @reason: the reason for releasing the peer
  */
-void ovpn_peer_release_p2p(struct ovpn_priv *ovpn,
+void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
 			   enum ovpn_del_peer_reason reason)
 {
+	struct ovpn_socket *ovpn_sock;
 	LLIST_HEAD(release_list);
 	struct ovpn_peer *peer;
 
 	spin_lock_bh(&ovpn->lock);
 	peer = rcu_dereference_protected(ovpn->peer,
 					 lockdep_is_held(&ovpn->lock));
-	if (peer)
-		ovpn_peer_remove(peer, reason, &release_list);
+	if (!peer) {
+		spin_unlock_bh(&ovpn->lock);
+		return;
+	}
+
+	if (sk) {
+		ovpn_sock = rcu_access_pointer(peer->sock);
+		if (!ovpn_sock || ovpn_sock->sock->sk != sk) {
+			spin_unlock_bh(&ovpn->lock);
+			ovpn_peer_put(peer);
+			return;
+		}
+	}
+
+	ovpn_peer_remove(peer, reason, &release_list);
 	unlock_ovpn(ovpn, &release_list);
 }
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index fd2e7625990a7..29c9065cedccb 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -12,6 +12,8 @@
 
 #include <net/dst_cache.h>
 
+#include "socket.h"
+
 /**
  * struct ovpn_peer - the main remote peer object
  * @ovpn: main openvpn instance this peer belongs to
@@ -20,6 +22,7 @@
  * @vpn_addrs: IP addresses assigned over the tunnel
  * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
  * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
+ * @sock: the socket being used to talk to this peer
  * @dst_cache: cache for dst_entry used to send to peer
  * @bind: remote peer binding
  * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
@@ -36,6 +39,7 @@ struct ovpn_peer {
 		struct in_addr ipv4;
 		struct in6_addr ipv6;
 	} vpn_addrs;
+	struct ovpn_socket __rcu *sock;
 	struct dst_cache dst_cache;
 	struct ovpn_bind __rcu *bind;
 	enum ovpn_del_peer_reason delete_reason;
@@ -70,7 +74,7 @@ static inline void ovpn_peer_put(struct ovpn_peer *peer)
 struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id);
 int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer);
 int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason);
-void ovpn_peer_release_p2p(struct ovpn_priv *ovpn,
+void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
 			   enum ovpn_del_peer_reason reason);
 
 struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
new file mode 100644
index 0000000000000..0a1ba3f75aa74
--- /dev/null
+++ b/drivers/net/ovpn/socket.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/udp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "peer.h"
+#include "socket.h"
+#include "udp.h"
+
+static void ovpn_socket_release_kref(struct kref *kref)
+{
+	struct ovpn_socket *sock = container_of(kref, struct ovpn_socket,
+						refcount);
+
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		ovpn_udp_socket_detach(sock);
+
+	kfree_rcu(sock, rcu);
+}
+
+/**
+ * ovpn_socket_put - decrease reference counter
+ * @peer: peer whose socket reference counter should be decreased
+ * @sock: the RCU protected peer socket
+ *
+ * This function is only used internally. Users willing to release
+ * references to the ovpn_socket should use ovpn_socket_release()
+ */
+static void ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
+{
+	kref_put(&sock->refcount, ovpn_socket_release_kref);
+}
+
+/**
+ * ovpn_socket_release - release resources owned by socket user
+ * @peer: peer whose socket should be released
+ *
+ * This function should be invoked when the user is shutting
+ * down and wants to drop its link to the socket.
+ *
+ * In case of UDP, the detach routine will drop a reference to the
+ * ovpn netdev, pointed by the ovpn_socket.
+ *
+ * In case of TCP, releasing the socket will cause dropping
+ * the refcounter for the peer it is linked to, thus allowing the peer
+ * disappear as well.
+ *
+ * This function is expected to be invoked exactly once per peer
+ *
+ * NOTE: this function may sleep
+ */
+void ovpn_socket_release(struct ovpn_peer *peer)
+{
+	struct ovpn_socket *sock;
+
+	might_sleep();
+
+	/* release may be invoked after socket was detached */
+	rcu_read_lock();
+	sock = rcu_dereference_protected(peer->sock, true);
+	if (!sock) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_assign_pointer(peer->sock, NULL);
+	rcu_read_unlock();
+
+	/* sanity check: we should not end up here if the socket
+	 * was already closed
+	 */
+	if (!sock->sock->sk) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return;
+	}
+
+	/* Drop the reference while holding the sock lock to avoid
+	 * concurrent ovpn_socket_new call to mess up with a partially
+	 * detached socket.
+	 *
+	 * Holding the lock ensures that a socket with refcnt 0 is fully
+	 * detached before it can be picked by a concurrent reader.
+	 */
+	lock_sock(sock->sock->sk);
+	ovpn_socket_put(peer, sock);
+	release_sock(sock->sock->sk);
+
+	/* align all readers with sk_user_data being NULL */
+	synchronize_rcu();
+}
+
+static bool ovpn_socket_hold(struct ovpn_socket *sock)
+{
+	return kref_get_unless_zero(&sock->refcount);
+}
+
+static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer)
+{
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		return ovpn_udp_socket_attach(sock, peer->ovpn);
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ovpn_socket_new - create a new socket and initialize it
+ * @sock: the kernel socket to embed
+ * @peer: the peer reachable via this socket
+ *
+ * Return: an openvpn socket on success or a negative error code otherwise
+ */
+struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
+{
+	struct ovpn_socket *ovpn_sock;
+	int ret;
+
+	lock_sock(sock->sk);
+
+	/* a TCP socket can only be owned by a single peer, therefore there
+	 * can't be any other user
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP && sock->sk->sk_user_data) {
+		ovpn_sock = ERR_PTR(-EBUSY);
+		goto sock_release;
+	}
+
+	/* a UDP socket can be shared across multiple peers, but we must make
+	 * sure it is not owned by something else
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_UDP) {
+		u8 type = READ_ONCE(udp_sk(sock->sk)->encap_type);
+
+		/* socket owned by other encapsulation module */
+		if (type && type != UDP_ENCAP_OVPNINUDP) {
+			ovpn_sock = ERR_PTR(-EBUSY);
+			goto sock_release;
+		}
+
+		rcu_read_lock();
+		ovpn_sock = rcu_dereference_sk_user_data(sock->sk);
+		if (ovpn_sock) {
+			/* socket owned by another ovpn instance, we can't use it */
+			if (ovpn_sock->ovpn != peer->ovpn) {
+				ovpn_sock = ERR_PTR(-EBUSY);
+				rcu_read_unlock();
+				goto sock_release;
+			}
+
+			/* this socket is already owned by this instance,
+			 * therefore we can increase the refcounter and
+			 * use it as expected
+			 */
+			if (WARN_ON(!ovpn_socket_hold(ovpn_sock))) {
+				/* this should never happen because setting
+				 * the refcnt to 0 and detaching the socket
+				 * is expected to be atomic
+				 */
+				ovpn_sock = ERR_PTR(-EAGAIN);
+				rcu_read_unlock();
+				goto sock_release;
+			}
+
+			/* caller is expected to increase the sock
+			 * refcounter before passing it to this
+			 * function. For this reason we drop it if
+			 * not needed, like when this socket is already
+			 * owned.
+			 */
+			rcu_read_unlock();
+			goto sock_release;
+		}
+		rcu_read_unlock();
+	}
+
+	/* socket is not owned: attach to this ovpn instance */
+
+	ovpn_sock = kzalloc(sizeof(*ovpn_sock), GFP_KERNEL);
+	if (!ovpn_sock) {
+		ovpn_sock = ERR_PTR(-ENOMEM);
+		goto sock_release;
+	}
+
+	ovpn_sock->ovpn = peer->ovpn;
+	ovpn_sock->sock = sock;
+	kref_init(&ovpn_sock->refcount);
+
+	ret = ovpn_socket_attach(ovpn_sock, peer);
+	if (ret < 0) {
+		kfree(ovpn_sock);
+		ovpn_sock = ERR_PTR(ret);
+		goto sock_release;
+	}
+
+	rcu_assign_sk_user_data(sock->sk, ovpn_sock);
+sock_release:
+	release_sock(sock->sk);
+	return ovpn_sock;
+}
diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h
new file mode 100644
index 0000000000000..ade8c94619d7b
--- /dev/null
+++ b/drivers/net/ovpn/socket.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_SOCK_H_
+#define _NET_OVPN_SOCK_H_
+
+#include <linux/net.h>
+#include <linux/kref.h>
+#include <net/sock.h>
+
+struct ovpn_priv;
+struct ovpn_peer;
+
+/**
+ * struct ovpn_socket - a kernel socket referenced in the ovpn code
+ * @ovpn: ovpn instance owning this socket (UDP only)
+ * @sock: the low level sock object
+ * @refcount: amount of contexts currently referencing this object
+ * @rcu: member used to schedule RCU destructor callback
+ */
+struct ovpn_socket {
+	struct ovpn_priv *ovpn;
+	struct socket *sock;
+	struct kref refcount;
+	struct rcu_head rcu;
+};
+
+struct ovpn_socket *ovpn_socket_new(struct socket *sock,
+				    struct ovpn_peer *peer);
+void ovpn_socket_release(struct ovpn_peer *peer);
+
+#endif /* _NET_OVPN_SOCK_H_ */
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
new file mode 100644
index 0000000000000..91970e66a4340
--- /dev/null
+++ b/drivers/net/ovpn/udp.c
@@ -0,0 +1,75 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/socket.h>
+#include <linux/udp.h>
+#include <net/udp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "socket.h"
+#include "udp.h"
+
+/**
+ * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn
+ * @ovpn_sock: socket to configure
+ * @ovpn: the openvp instance to link
+ *
+ * After invoking this function, the sock will be controlled by ovpn so that
+ * any incoming packet may be processed by ovpn first.
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_priv *ovpn)
+{
+	struct socket *sock = ovpn_sock->sock;
+	struct ovpn_socket *old_data;
+	int ret = 0;
+
+	/* make sure no pre-existing encapsulation handler exists */
+	rcu_read_lock();
+	old_data = rcu_dereference_sk_user_data(sock->sk);
+	if (!old_data) {
+		/* socket is currently unused - we can take it */
+		rcu_read_unlock();
+		return 0;
+	}
+
+	/* socket is in use. We need to understand if it's owned by this ovpn
+	 * instance or by something else.
+	 * In the former case, we can increase the refcounter and happily
+	 * use it, because the same UDP socket is expected to be shared among
+	 * different peers.
+	 *
+	 * Unlikely TCP, a single UDP socket can be used to talk to many remote
+	 * hosts and therefore openvpn instantiates one only for all its peers
+	 */
+	if ((READ_ONCE(udp_sk(sock->sk)->encap_type) == UDP_ENCAP_OVPNINUDP) &&
+	    old_data->ovpn == ovpn) {
+		netdev_dbg(ovpn->dev,
+			   "provided socket already owned by this interface\n");
+		ret = -EALREADY;
+	} else {
+		netdev_dbg(ovpn->dev,
+			   "provided socket already taken by other user\n");
+		ret = -EBUSY;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
+
+/**
+ * ovpn_udp_socket_detach - clean udp-tunnel status for this socket
+ * @ovpn_sock: the socket to clean
+ */
+void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock)
+{
+}
diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h
new file mode 100644
index 0000000000000..1c8fb6fe402dc
--- /dev/null
+++ b/drivers/net/ovpn/udp.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_UDP_H_
+#define _NET_OVPN_UDP_H_
+
+struct ovpn_priv;
+struct socket;
+
+int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_priv *ovpn);
+void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock);
+
+#endif /* _NET_OVPN_UDP_H_ */
diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h
index d85d671deed3c..edca3e430305a 100644
--- a/include/uapi/linux/udp.h
+++ b/include/uapi/linux/udp.h
@@ -43,5 +43,6 @@ struct udphdr {
 #define UDP_ENCAP_GTP1U		5 /* 3GPP TS 29.060 */
 #define UDP_ENCAP_RXRPC		6
 #define TCP_ENCAP_ESPINTCP	7 /* Yikes, this is really xfrm encap types. */
+#define UDP_ENCAP_OVPNINUDP	8 /* OpenVPN traffic */
 
 #endif /* _UAPI_LINUX_UDP_H */

From 107e2da2b359bff36b0b89a6c4c9c7c98e53531c Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:42 +0100
Subject: [PATCH 2548/2753] ovpn: implement basic TX path (UDP)

Packets sent over the ovpn interface are processed and transmitted to the
connected peer, if any.

Implementation is UDP only. TCP will be added by a later patch.

Note: no crypto/encapsulation exists yet. Packets are just captured and
sent.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/Kconfig       |   1 +
 drivers/net/ovpn/io.c     | 137 +++++++++++++++++++++-
 drivers/net/ovpn/peer.c   |  32 ++++++
 drivers/net/ovpn/peer.h   |   2 +
 drivers/net/ovpn/skb.h    |  55 +++++++++
 drivers/net/ovpn/socket.c |   3 +-
 drivers/net/ovpn/udp.c    | 236 +++++++++++++++++++++++++++++++++++++-
 drivers/net/ovpn/udp.h    |   6 +
 8 files changed, 468 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ovpn/skb.h

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 5e224c4541173..dd6953636574a 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -120,6 +120,7 @@ config OVPN
 	depends on NET && INET
 	depends on IPV6 || !IPV6
 	select DST_CACHE
+	select NET_UDP_TUNNEL
 	help
 	  This module enhances the performance of the OpenVPN userspace software
 	  by offloading the data channel processing to kernelspace.
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 4b71c38165d7a..94b466bf2ef70 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -9,14 +9,149 @@
 
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <net/gso.h>
 
 #include "io.h"
+#include "ovpnpriv.h"
+#include "peer.h"
+#include "udp.h"
+#include "skb.h"
+#include "socket.h"
+
+static void ovpn_encrypt_post(struct sk_buff *skb, int ret)
+{
+	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
+	struct ovpn_socket *sock;
+
+	if (unlikely(ret < 0))
+		goto err;
+
+	skb_mark_not_on_list(skb);
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (unlikely(!sock))
+		goto err_unlock;
+
+	switch (sock->sock->sk->sk_protocol) {
+	case IPPROTO_UDP:
+		ovpn_udp_send_skb(peer, sock->sock, skb);
+		break;
+	default:
+		/* no transport configured yet */
+		goto err_unlock;
+	}
+	/* skb passed down the stack - don't free it */
+	skb = NULL;
+err_unlock:
+	rcu_read_unlock();
+err:
+	if (unlikely(skb))
+		dev_core_stats_tx_dropped_inc(peer->ovpn->dev);
+	ovpn_peer_put(peer);
+	kfree_skb(skb);
+}
+
+static bool ovpn_encrypt_one(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	ovpn_skb_cb(skb)->peer = peer;
+
+	/* take a reference to the peer because the crypto code may run async.
+	 * ovpn_encrypt_post() will release it upon completion
+	 */
+	if (unlikely(!ovpn_peer_hold(peer))) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return false;
+	}
+
+	ovpn_encrypt_post(skb, 0);
+	return true;
+}
+
+/* send skb to connected peer, if any */
+static void ovpn_send(struct ovpn_priv *ovpn, struct sk_buff *skb,
+		      struct ovpn_peer *peer)
+{
+	struct sk_buff *curr, *next;
+
+	/* this might be a GSO-segmented skb list: process each skb
+	 * independently
+	 */
+	skb_list_walk_safe(skb, curr, next) {
+		if (unlikely(!ovpn_encrypt_one(peer, curr))) {
+			dev_core_stats_tx_dropped_inc(ovpn->dev);
+			kfree_skb(curr);
+		}
+	}
+
+	ovpn_peer_put(peer);
+}
 
 /* Send user data to the network
  */
 netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+	struct sk_buff *segments, *curr, *next;
+	struct sk_buff_head skb_list;
+	struct ovpn_peer *peer;
+	__be16 proto;
+	int ret;
+
+	/* reset netfilter state */
+	nf_reset_ct(skb);
+
+	/* verify IP header size in network packet */
+	proto = ovpn_ip_check_protocol(skb);
+	if (unlikely(!proto || skb->protocol != proto))
+		goto drop;
+
+	if (skb_is_gso(skb)) {
+		segments = skb_gso_segment(skb, 0);
+		if (IS_ERR(segments)) {
+			ret = PTR_ERR(segments);
+			net_err_ratelimited("%s: cannot segment payload packet: %d\n",
+					    netdev_name(dev), ret);
+			goto drop;
+		}
+
+		consume_skb(skb);
+		skb = segments;
+	}
+
+	/* from this moment on, "skb" might be a list */
+
+	__skb_queue_head_init(&skb_list);
+	skb_list_walk_safe(skb, curr, next) {
+		skb_mark_not_on_list(curr);
+
+		curr = skb_share_check(curr, GFP_ATOMIC);
+		if (unlikely(!curr)) {
+			net_err_ratelimited("%s: skb_share_check failed for payload packet\n",
+					    netdev_name(dev));
+			dev_core_stats_tx_dropped_inc(ovpn->dev);
+			continue;
+		}
+
+		__skb_queue_tail(&skb_list, curr);
+	}
+	skb_list.prev->next = NULL;
+
+	/* retrieve peer serving the destination IP of this packet */
+	peer = ovpn_peer_get_by_dst(ovpn, skb);
+	if (unlikely(!peer)) {
+		net_dbg_ratelimited("%s: no peer to send data to\n",
+				    netdev_name(ovpn->dev));
+		goto drop;
+	}
+
+	ovpn_send(ovpn, skb_list.next, peer);
+
+	return NETDEV_TX_OK;
+
+drop:
+	dev_core_stats_tx_dropped_inc(ovpn->dev);
 	skb_tx_error(skb);
-	kfree_skb(skb);
+	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 0bb6c15171848..10eabd62ae723 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -294,6 +294,38 @@ static void ovpn_peer_remove(struct ovpn_peer *peer,
 	llist_add(&peer->release_entry, release_list);
 }
 
+/**
+ * ovpn_peer_get_by_dst - Lookup peer to send skb to
+ * @ovpn: the private data representing the current VPN session
+ * @skb: the skb to extract the destination address from
+ *
+ * This function takes a tunnel packet and looks up the peer to send it to
+ * after encapsulation. The skb is expected to be the in-tunnel packet, without
+ * any OpenVPN related header.
+ *
+ * Assume that the IP header is accessible in the skb data.
+ *
+ * Return: the peer if found or NULL otherwise.
+ */
+struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
+				       struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = NULL;
+
+	/* in P2P mode, no matter the destination, packets are always sent to
+	 * the single peer listening on the other side
+	 */
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		rcu_read_lock();
+		peer = rcu_dereference(ovpn->peer);
+		if (unlikely(peer && !ovpn_peer_hold(peer)))
+			peer = NULL;
+		rcu_read_unlock();
+	}
+
+	return peer;
+}
+
 /**
  * ovpn_peer_add_p2p - add peer to related tables in a P2P instance
  * @ovpn: the instance to add the peer to
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index 29c9065cedccb..fef04311c1593 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -80,5 +80,7 @@ void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
 struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
 					       struct sk_buff *skb);
 struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id);
+struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
+				       struct sk_buff *skb);
 
 #endif /* _NET_OVPN_OVPNPEER_H_ */
diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h
new file mode 100644
index 0000000000000..9db7a9adebdb4
--- /dev/null
+++ b/drivers/net/ovpn/skb.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_SKB_H_
+#define _NET_OVPN_SKB_H_
+
+#include <linux/in.h>
+#include <linux/in6.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/types.h>
+
+struct ovpn_cb {
+	struct ovpn_peer *peer;
+};
+
+static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb)
+{
+	BUILD_BUG_ON(sizeof(struct ovpn_cb) > sizeof(skb->cb));
+	return (struct ovpn_cb *)skb->cb;
+}
+
+/* Return IP protocol version from skb header.
+ * Return 0 if protocol is not IPv4/IPv6 or cannot be read.
+ */
+static inline __be16 ovpn_ip_check_protocol(struct sk_buff *skb)
+{
+	__be16 proto = 0;
+
+	/* skb could be non-linear,
+	 * make sure IP header is in non-fragmented part
+	 */
+	if (!pskb_network_may_pull(skb, sizeof(struct iphdr)))
+		return 0;
+
+	if (ip_hdr(skb)->version == 4) {
+		proto = htons(ETH_P_IP);
+	} else if (ip_hdr(skb)->version == 6) {
+		if (!pskb_network_may_pull(skb, sizeof(struct ipv6hdr)))
+			return 0;
+		proto = htons(ETH_P_IPV6);
+	}
+
+	return proto;
+}
+
+#endif /* _NET_OVPN_SKB_H_ */
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index 0a1ba3f75aa74..a4a8686f2e299 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -190,9 +190,8 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 		goto sock_release;
 	}
 
-	ovpn_sock->ovpn = peer->ovpn;
-	ovpn_sock->sock = sock;
 	kref_init(&ovpn_sock->refcount);
+	ovpn_sock->sock = sock;
 
 	ret = ovpn_socket_attach(ovpn_sock, peer);
 	if (ret < 0) {
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
index 91970e66a4340..ae76ae6d372f5 100644
--- a/drivers/net/ovpn/udp.c
+++ b/drivers/net/ovpn/udp.c
@@ -7,15 +7,249 @@
  */
 
 #include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/skbuff.h>
 #include <linux/socket.h>
 #include <linux/udp.h>
+#include <net/addrconf.h>
+#include <net/dst_cache.h>
+#include <net/route.h>
+#include <net/ipv6_stubs.h>
 #include <net/udp.h>
+#include <net/udp_tunnel.h>
 
 #include "ovpnpriv.h"
 #include "main.h"
+#include "bind.h"
+#include "io.h"
+#include "peer.h"
 #include "socket.h"
 #include "udp.h"
 
+/**
+ * ovpn_udp4_output - send IPv4 packet over udp socket
+ * @peer: the destination peer
+ * @bind: the binding related to the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp4_output(struct ovpn_peer *peer, struct ovpn_bind *bind,
+			    struct dst_cache *cache, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct rtable *rt;
+	struct flowi4 fl = {
+		.saddr = bind->local.ipv4.s_addr,
+		.daddr = bind->remote.in4.sin_addr.s_addr,
+		.fl4_sport = inet_sk(sk)->inet_sport,
+		.fl4_dport = bind->remote.in4.sin_port,
+		.flowi4_proto = sk->sk_protocol,
+		.flowi4_mark = sk->sk_mark,
+	};
+	int ret;
+
+	local_bh_disable();
+	rt = dst_cache_get_ip4(cache, &fl.saddr);
+	if (rt)
+		goto transmit;
+
+	if (unlikely(!inet_confirm_addr(sock_net(sk), NULL, 0, fl.saddr,
+					RT_SCOPE_HOST))) {
+		/* we may end up here when the cached address is not usable
+		 * anymore. In this case we reset address/cache and perform a
+		 * new look up
+		 */
+		fl.saddr = 0;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv4.s_addr = 0;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+	}
+
+	rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+	if (IS_ERR(rt) && PTR_ERR(rt) == -EINVAL) {
+		fl.saddr = 0;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv4.s_addr = 0;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+
+		rt = ip_route_output_flow(sock_net(sk), &fl, sk);
+	}
+
+	if (IS_ERR(rt)) {
+		ret = PTR_ERR(rt);
+		net_dbg_ratelimited("%s: no route to host %pISpc: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    &bind->remote.in4,
+				    ret);
+		goto err;
+	}
+	dst_cache_set_ip4(cache, &rt->dst, fl.saddr);
+
+transmit:
+	udp_tunnel_xmit_skb(rt, sk, skb, fl.saddr, fl.daddr, 0,
+			    ip4_dst_hoplimit(&rt->dst), 0, fl.fl4_sport,
+			    fl.fl4_dport, false, sk->sk_no_check_tx);
+	ret = 0;
+err:
+	local_bh_enable();
+	return ret;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+/**
+ * ovpn_udp6_output - send IPv6 packet over udp socket
+ * @peer: the destination peer
+ * @bind: the binding related to the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp6_output(struct ovpn_peer *peer, struct ovpn_bind *bind,
+			    struct dst_cache *cache, struct sock *sk,
+			    struct sk_buff *skb)
+{
+	struct dst_entry *dst;
+	int ret;
+
+	struct flowi6 fl = {
+		.saddr = bind->local.ipv6,
+		.daddr = bind->remote.in6.sin6_addr,
+		.fl6_sport = inet_sk(sk)->inet_sport,
+		.fl6_dport = bind->remote.in6.sin6_port,
+		.flowi6_proto = sk->sk_protocol,
+		.flowi6_mark = sk->sk_mark,
+		.flowi6_oif = bind->remote.in6.sin6_scope_id,
+	};
+
+	local_bh_disable();
+	dst = dst_cache_get_ip6(cache, &fl.saddr);
+	if (dst)
+		goto transmit;
+
+	if (unlikely(!ipv6_chk_addr(sock_net(sk), &fl.saddr, NULL, 0))) {
+		/* we may end up here when the cached address is not usable
+		 * anymore. In this case we reset address/cache and perform a
+		 * new look up
+		 */
+		fl.saddr = in6addr_any;
+		spin_lock_bh(&peer->lock);
+		bind->local.ipv6 = in6addr_any;
+		spin_unlock_bh(&peer->lock);
+		dst_cache_reset(cache);
+	}
+
+	dst = ipv6_stub->ipv6_dst_lookup_flow(sock_net(sk), sk, &fl, NULL);
+	if (IS_ERR(dst)) {
+		ret = PTR_ERR(dst);
+		net_dbg_ratelimited("%s: no route to host %pISpc: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    &bind->remote.in6, ret);
+		goto err;
+	}
+	dst_cache_set_ip6(cache, dst, &fl.saddr);
+
+transmit:
+	udp_tunnel6_xmit_skb(dst, sk, skb, skb->dev, &fl.saddr, &fl.daddr, 0,
+			     ip6_dst_hoplimit(dst), 0, fl.fl6_sport,
+			     fl.fl6_dport, udp_get_no_check6_tx(sk));
+	ret = 0;
+err:
+	local_bh_enable();
+	return ret;
+}
+#endif
+
+/**
+ * ovpn_udp_output - transmit skb using udp-tunnel
+ * @peer: the destination peer
+ * @cache: dst cache
+ * @sk: the socket to send the packet over
+ * @skb: the packet to send
+ *
+ * rcu_read_lock should be held on entry.
+ * On return, the skb is consumed.
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_udp_output(struct ovpn_peer *peer, struct dst_cache *cache,
+			   struct sock *sk, struct sk_buff *skb)
+{
+	struct ovpn_bind *bind;
+	int ret;
+
+	/* set sk to null if skb is already orphaned */
+	if (!skb->destructor)
+		skb->sk = NULL;
+
+	/* always permit openvpn-created packets to be (outside) fragmented */
+	skb->ignore_df = 1;
+
+	rcu_read_lock();
+	bind = rcu_dereference(peer->bind);
+	if (unlikely(!bind)) {
+		net_warn_ratelimited("%s: no bind for remote peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		ret = -ENODEV;
+		goto out;
+	}
+
+	switch (bind->remote.in4.sin_family) {
+	case AF_INET:
+		ret = ovpn_udp4_output(peer, bind, cache, sk, skb);
+		break;
+#if IS_ENABLED(CONFIG_IPV6)
+	case AF_INET6:
+		ret = ovpn_udp6_output(peer, bind, cache, sk, skb);
+		break;
+#endif
+	default:
+		ret = -EAFNOSUPPORT;
+		break;
+	}
+
+out:
+	rcu_read_unlock();
+	return ret;
+}
+
+/**
+ * ovpn_udp_send_skb - prepare skb and send it over via UDP
+ * @peer: the destination peer
+ * @sock: the RCU protected peer socket
+ * @skb: the packet to send
+ */
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb)
+{
+	int ret = -1;
+
+	skb->dev = peer->ovpn->dev;
+	/* no checksum performed at this layer */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* get socket info */
+	if (unlikely(!sock)) {
+		net_warn_ratelimited("%s: no sock for remote peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto out;
+	}
+
+	/* crypto layer -> transport (UDP) */
+	ret = ovpn_udp_output(peer, &peer->dst_cache, sock->sk, skb);
+out:
+	if (unlikely(ret < 0)) {
+		kfree_skb(skb);
+		return;
+	}
+}
+
 /**
  * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn
  * @ovpn_sock: socket to configure
@@ -31,7 +265,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 {
 	struct socket *sock = ovpn_sock->sock;
 	struct ovpn_socket *old_data;
-	int ret = 0;
+	int ret;
 
 	/* make sure no pre-existing encapsulation handler exists */
 	rcu_read_lock();
diff --git a/drivers/net/ovpn/udp.h b/drivers/net/ovpn/udp.h
index 1c8fb6fe402dc..9994eb6e04283 100644
--- a/drivers/net/ovpn/udp.h
+++ b/drivers/net/ovpn/udp.h
@@ -9,6 +9,9 @@
 #ifndef _NET_OVPN_UDP_H_
 #define _NET_OVPN_UDP_H_
 
+#include <net/sock.h>
+
+struct ovpn_peer;
 struct ovpn_priv;
 struct socket;
 
@@ -16,4 +19,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 			   struct ovpn_priv *ovpn);
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock);
 
+void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb);
+
 #endif /* _NET_OVPN_UDP_H_ */

From ae54cebc6c1a36ff801375e202bd16255876d98e Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:43 +0100
Subject: [PATCH 2549/2753] ovpn: implement basic RX path (UDP)

Packets received over the socket are forwarded to the user device.

Implementation is UDP only. TCP will be added by a later patch.

Note: no decryption/decapsulation exists yet, packets are forwarded as
they arrive without much processing.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/io.c       |  64 ++++++++++++++++-
 drivers/net/ovpn/io.h       |   2 +
 drivers/net/ovpn/main.c     |  14 +++-
 drivers/net/ovpn/ovpnpriv.h |   3 +
 drivers/net/ovpn/proto.h    |  50 ++++++++++++-
 drivers/net/ovpn/socket.c   |  13 +++-
 drivers/net/ovpn/socket.h   |   9 ++-
 drivers/net/ovpn/udp.c      | 135 ++++++++++++++++++++++++++++++++++++
 net/ipv6/udp.c              |   1 +
 9 files changed, 286 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 94b466bf2ef70..46ad27e8eb842 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -9,15 +9,77 @@
 
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
+#include <net/gro_cells.h>
 #include <net/gso.h>
 
-#include "io.h"
 #include "ovpnpriv.h"
 #include "peer.h"
+#include "io.h"
+#include "netlink.h"
+#include "proto.h"
 #include "udp.h"
 #include "skb.h"
 #include "socket.h"
 
+/* Called after decrypt to write the IP packet to the device.
+ * This method is expected to manage/free the skb.
+ */
+static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	unsigned int pkt_len;
+	int ret;
+
+	/* we can't guarantee the packet wasn't corrupted before entering the
+	 * VPN, therefore we give other layers a chance to check that
+	 */
+	skb->ip_summed = CHECKSUM_NONE;
+
+	/* skb hash for transport packet no longer valid after decapsulation */
+	skb_clear_hash(skb);
+
+	/* post-decrypt scrub -- prepare to inject encapsulated packet onto the
+	 * interface, based on __skb_tunnel_rx() in dst.h
+	 */
+	skb->dev = peer->ovpn->dev;
+	skb_set_queue_mapping(skb, 0);
+	skb_scrub_packet(skb, true);
+
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_inner_headers(skb);
+
+	/* cause packet to be "received" by the interface */
+	pkt_len = skb->len;
+	ret = gro_cells_receive(&peer->ovpn->gro_cells, skb);
+	if (likely(ret == NET_RX_SUCCESS))
+		/* update RX stats with the size of decrypted packet */
+		dev_sw_netstats_rx_add(peer->ovpn->dev, pkt_len);
+}
+
+static void ovpn_decrypt_post(struct sk_buff *skb, int ret)
+{
+	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
+
+	if (unlikely(ret < 0))
+		goto drop;
+
+	ovpn_netdev_write(peer, skb);
+	/* skb is passed to upper layer - don't free it */
+	skb = NULL;
+drop:
+	if (unlikely(skb))
+		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+	ovpn_peer_put(peer);
+	kfree_skb(skb);
+}
+
+/* RX path entry point: decrypt packet and forward it to the device */
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_decrypt_post(skb, 0);
+}
+
 static void ovpn_encrypt_post(struct sk_buff *skb, int ret)
 {
 	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
index afea5f81f5628..1cfa66873a2d4 100644
--- a/drivers/net/ovpn/io.h
+++ b/drivers/net/ovpn/io.h
@@ -21,4 +21,6 @@
 
 netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
 
+void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
+
 #endif /* _NET_OVPN_OVPN_H_ */
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 6f3f649bdf2d8..f6219b05485f0 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -11,6 +11,7 @@
 #include <linux/module.h>
 #include <linux/netdevice.h>
 #include <linux/inetdevice.h>
+#include <net/gro_cells.h>
 #include <net/ip.h>
 #include <net/rtnetlink.h>
 #include <uapi/linux/if_arp.h>
@@ -21,10 +22,20 @@
 #include "io.h"
 #include "peer.h"
 #include "proto.h"
+#include "udp.h"
 
 static int ovpn_net_init(struct net_device *dev)
 {
-	return 0;
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	return gro_cells_init(&ovpn->gro_cells, dev);
+}
+
+static void ovpn_net_uninit(struct net_device *dev)
+{
+	struct ovpn_priv *ovpn = netdev_priv(dev);
+
+	gro_cells_destroy(&ovpn->gro_cells);
 }
 
 static int ovpn_net_open(struct net_device *dev)
@@ -43,6 +54,7 @@ static int ovpn_net_open(struct net_device *dev)
 
 static const struct net_device_ops ovpn_netdev_ops = {
 	.ndo_init		= ovpn_net_init,
+	.ndo_uninit		= ovpn_net_uninit,
 	.ndo_open		= ovpn_net_open,
 	.ndo_start_xmit		= ovpn_net_xmit,
 };
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index fae2682b424b0..9d0640e9c71e7 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -10,6 +10,7 @@
 #ifndef _NET_OVPN_OVPNSTRUCT_H_
 #define _NET_OVPN_OVPNSTRUCT_H_
 
+#include <net/gro_cells.h>
 #include <uapi/linux/if_link.h>
 #include <uapi/linux/ovpn.h>
 
@@ -20,6 +21,7 @@
  * @mode: device operation mode (i.e. p2p, mp, ..)
  * @lock: protect this object
  * @peer: in P2P mode, this is the only remote peer
+ * @gro_cells: pointer to the Generic Receive Offload cell
  */
 struct ovpn_priv {
 	struct net_device *dev;
@@ -27,6 +29,7 @@ struct ovpn_priv {
 	enum ovpn_mode mode;
 	spinlock_t lock; /* protect writing to the ovpn_priv object */
 	struct ovpn_peer __rcu *peer;
+	struct gro_cells gro_cells;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h
index 5f95a78bebd37..591b97a9925fd 100644
--- a/drivers/net/ovpn/proto.h
+++ b/drivers/net/ovpn/proto.h
@@ -10,6 +10,11 @@
 #ifndef _NET_OVPN_PROTO_H_
 #define _NET_OVPN_PROTO_H_
 
+#include "main.h"
+
+#include <linux/bitfield.h>
+#include <linux/skbuff.h>
+
 /* When the OpenVPN protocol is ran in AEAD mode, use
  * the OpenVPN packet ID as the AEAD nonce:
  *
@@ -34,5 +39,48 @@
 #define OVPN_NONCE_WIRE_SIZE (OVPN_NONCE_SIZE - OVPN_NONCE_TAIL_SIZE)
 
 #define OVPN_OPCODE_SIZE		4 /* DATA_V2 opcode size */
+#define OVPN_OPCODE_KEYID_MASK		0x07000000
+#define OVPN_OPCODE_PKTTYPE_MASK	0xF8000000
+#define OVPN_OPCODE_PEERID_MASK		0x00FFFFFF
+
+/* packet opcodes of interest to us */
+#define OVPN_DATA_V1			6 /* data channel v1 packet */
+#define OVPN_DATA_V2			9 /* data channel v2 packet */
+
+#define OVPN_PEER_ID_UNDEF		0x00FFFFFF
+
+/**
+ * ovpn_opcode_from_skb - extract OP code from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the OP code
+ */
+static inline u8 ovpn_opcode_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PKTTYPE_MASK, opcode);
+}
+
+/**
+ * ovpn_peer_id_from_skb - extract peer ID from skb at specified offset
+ * @skb: the packet to extract the OP code from
+ * @offset: the offset in the data buffer where the OP code is located
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first 4 bytes.
+ *
+ * Return: the peer ID
+ */
+static inline u32 ovpn_peer_id_from_skb(const struct sk_buff *skb, u16 offset)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)(skb->data + offset));
+
+	return FIELD_GET(OVPN_OPCODE_PEERID_MASK, opcode);
+}
 
-#endif /* _NET_OVPN_PROTO_H_ */
+#endif /* _NET_OVPN_OVPNPROTO_H_ */
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index a4a8686f2e299..6de1e8c85a3d3 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -23,8 +23,10 @@ static void ovpn_socket_release_kref(struct kref *kref)
 	struct ovpn_socket *sock = container_of(kref, struct ovpn_socket,
 						refcount);
 
-	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP) {
 		ovpn_udp_socket_detach(sock);
+		netdev_put(sock->ovpn->dev, &sock->dev_tracker);
+	}
 
 	kfree_rcu(sock, rcu);
 }
@@ -200,6 +202,15 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 		goto sock_release;
 	}
 
+	if (sock->sk->sk_protocol == IPPROTO_UDP) {
+		/* in UDP we only link the ovpn instance since the socket is
+		 * shared among multiple peers
+		 */
+		ovpn_sock->ovpn = peer->ovpn;
+		netdev_hold(peer->ovpn->dev, &ovpn_sock->dev_tracker,
+			    GFP_KERNEL);
+	}
+
 	rcu_assign_sk_user_data(sock->sk, ovpn_sock);
 sock_release:
 	release_sock(sock->sk);
diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h
index ade8c94619d7b..c1697f4616d47 100644
--- a/drivers/net/ovpn/socket.h
+++ b/drivers/net/ovpn/socket.h
@@ -20,12 +20,19 @@ struct ovpn_peer;
 /**
  * struct ovpn_socket - a kernel socket referenced in the ovpn code
  * @ovpn: ovpn instance owning this socket (UDP only)
+ * @dev_tracker: reference tracker for associated dev (UDP only)
  * @sock: the low level sock object
  * @refcount: amount of contexts currently referencing this object
  * @rcu: member used to schedule RCU destructor callback
  */
 struct ovpn_socket {
-	struct ovpn_priv *ovpn;
+	union {
+		struct {
+			struct ovpn_priv *ovpn;
+			netdevice_tracker dev_tracker;
+		};
+	};
+
 	struct socket *sock;
 	struct kref refcount;
 	struct rcu_head rcu;
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
index ae76ae6d372f5..6f4b51089033a 100644
--- a/drivers/net/ovpn/udp.c
+++ b/drivers/net/ovpn/udp.c
@@ -15,6 +15,7 @@
 #include <net/dst_cache.h>
 #include <net/route.h>
 #include <net/ipv6_stubs.h>
+#include <net/transp_v6.h>
 #include <net/udp.h>
 #include <net/udp_tunnel.h>
 
@@ -23,9 +24,114 @@
 #include "bind.h"
 #include "io.h"
 #include "peer.h"
+#include "proto.h"
 #include "socket.h"
 #include "udp.h"
 
+/* Retrieve the corresponding ovpn object from a UDP socket
+ * rcu_read_lock must be held on entry
+ */
+static struct ovpn_socket *ovpn_socket_from_udp_sock(struct sock *sk)
+{
+	struct ovpn_socket *ovpn_sock;
+
+	if (unlikely(READ_ONCE(udp_sk(sk)->encap_type) != UDP_ENCAP_OVPNINUDP))
+		return NULL;
+
+	ovpn_sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!ovpn_sock))
+		return NULL;
+
+	/* make sure that sk matches our stored transport socket */
+	if (unlikely(!ovpn_sock->sock || sk != ovpn_sock->sock->sk))
+		return NULL;
+
+	return ovpn_sock;
+}
+
+/**
+ * ovpn_udp_encap_recv - Start processing a received UDP packet.
+ * @sk: socket over which the packet was received
+ * @skb: the received packet
+ *
+ * If the first byte of the payload is:
+ * - DATA_V2 the packet is accepted for further processing,
+ * - DATA_V1 the packet is dropped as not supported,
+ * - anything else the packet is forwarded to the UDP stack for
+ *   delivery to user space.
+ *
+ * Return:
+ *  0 if skb was consumed or dropped
+ * >0 if skb should be passed up to userspace as UDP (packet not consumed)
+ * <0 if skb should be resubmitted as proto -N (packet not consumed)
+ */
+static int ovpn_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+{
+	struct ovpn_socket *ovpn_sock;
+	struct ovpn_priv *ovpn;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	u8 opcode;
+
+	ovpn_sock = ovpn_socket_from_udp_sock(sk);
+	if (unlikely(!ovpn_sock)) {
+		net_err_ratelimited("ovpn: %s invoked on non ovpn socket\n",
+				    __func__);
+		goto drop_noovpn;
+	}
+
+	ovpn = ovpn_sock->ovpn;
+	if (unlikely(!ovpn)) {
+		net_err_ratelimited("ovpn: cannot obtain ovpn object from UDP socket\n");
+		goto drop_noovpn;
+	}
+
+	/* Make sure the first 4 bytes of the skb data buffer after the UDP
+	 * header are accessible.
+	 * They are required to fetch the OP code, the key ID and the peer ID.
+	 */
+	if (unlikely(!pskb_may_pull(skb, sizeof(struct udphdr) +
+				    OVPN_OPCODE_SIZE))) {
+		net_dbg_ratelimited("%s: packet too small from UDP socket\n",
+				    netdev_name(ovpn->dev));
+		goto drop;
+	}
+
+	opcode = ovpn_opcode_from_skb(skb, sizeof(struct udphdr));
+	if (unlikely(opcode != OVPN_DATA_V2)) {
+		/* DATA_V1 is not supported */
+		if (opcode == OVPN_DATA_V1)
+			goto drop;
+
+		/* unknown or control packet: let it bubble up to userspace */
+		return 1;
+	}
+
+	peer_id = ovpn_peer_id_from_skb(skb, sizeof(struct udphdr));
+	/* some OpenVPN server implementations send data packets with the
+	 * peer-id set to UNDEF. In this case we skip the peer lookup by peer-id
+	 * and we try with the transport address
+	 */
+	if (peer_id == OVPN_PEER_ID_UNDEF)
+		peer = ovpn_peer_get_by_transp_addr(ovpn, skb);
+	else
+		peer = ovpn_peer_get_by_id(ovpn, peer_id);
+
+	if (unlikely(!peer))
+		goto drop;
+
+	/* pop off outer UDP header */
+	__skb_pull(skb, sizeof(struct udphdr));
+	ovpn_recv(peer, skb);
+	return 0;
+
+drop:
+	dev_core_stats_rx_dropped_inc(ovpn->dev);
+drop_noovpn:
+	kfree_skb(skb);
+	return 0;
+}
+
 /**
  * ovpn_udp4_output - send IPv4 packet over udp socket
  * @peer: the destination peer
@@ -250,6 +356,25 @@ void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
 	}
 }
 
+static void ovpn_udp_encap_destroy(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+	struct ovpn_priv *ovpn;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock || !sock->ovpn) {
+		rcu_read_unlock();
+		return;
+	}
+	ovpn = sock->ovpn;
+	rcu_read_unlock();
+
+	if (ovpn->mode == OVPN_MODE_P2P)
+		ovpn_peer_release_p2p(ovpn, sk,
+				      OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
+}
+
 /**
  * ovpn_udp_socket_attach - set udp-tunnel CBs on socket and link it to ovpn
  * @ovpn_sock: socket to configure
@@ -263,6 +388,11 @@ void ovpn_udp_send_skb(struct ovpn_peer *peer, struct socket *sock,
 int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 			   struct ovpn_priv *ovpn)
 {
+	struct udp_tunnel_sock_cfg cfg = {
+		.encap_type = UDP_ENCAP_OVPNINUDP,
+		.encap_rcv = ovpn_udp_encap_recv,
+		.encap_destroy = ovpn_udp_encap_destroy,
+	};
 	struct socket *sock = ovpn_sock->sock;
 	struct ovpn_socket *old_data;
 	int ret;
@@ -273,6 +403,7 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
 	if (!old_data) {
 		/* socket is currently unused - we can take it */
 		rcu_read_unlock();
+		setup_udp_tunnel_sock(sock_net(sock->sk), sock, &cfg);
 		return 0;
 	}
 
@@ -306,4 +437,8 @@ int ovpn_udp_socket_attach(struct ovpn_socket *ovpn_sock,
  */
 void ovpn_udp_socket_detach(struct ovpn_socket *ovpn_sock)
 {
+	struct udp_tunnel_sock_cfg cfg = { };
+
+	setup_udp_tunnel_sock(sock_net(ovpn_sock->sock->sk), ovpn_sock->sock,
+			      &cfg);
 }
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 7317f8e053f1c..02a8ec4fa5d35 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -1935,6 +1935,7 @@ struct proto udpv6_prot = {
 	.h.udp_table		= NULL,
 	.diag_destroy		= udp_abort,
 };
+EXPORT_SYMBOL_GPL(udpv6_prot);
 
 static struct inet_protosw udpv6_protosw = {
 	.type =      SOCK_DGRAM,

From 5f5ff4edcf7c0b41a75361b56a01e7fd5826e1b5 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:44 +0100
Subject: [PATCH 2550/2753] ovpn: implement packet processing

This change implements encryption/decryption and
encapsulation/decapsulation of OpenVPN packets.

Support for generic crypto state is added along with
a wrapper for the AEAD crypto kernel API.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/Kconfig            |   4 +
 drivers/net/ovpn/Makefile      |   3 +
 drivers/net/ovpn/bind.c        |   9 +-
 drivers/net/ovpn/crypto.c      | 152 +++++++++++++
 drivers/net/ovpn/crypto.h      | 139 ++++++++++++
 drivers/net/ovpn/crypto_aead.c | 392 +++++++++++++++++++++++++++++++++
 drivers/net/ovpn/crypto_aead.h |  27 +++
 drivers/net/ovpn/io.c          | 149 ++++++++++++-
 drivers/net/ovpn/io.h          |   3 +
 drivers/net/ovpn/peer.c        |  29 +++
 drivers/net/ovpn/peer.h        |   5 +
 drivers/net/ovpn/pktid.c       | 129 +++++++++++
 drivers/net/ovpn/pktid.h       |  87 ++++++++
 drivers/net/ovpn/proto.h       |  32 +++
 drivers/net/ovpn/skb.h         |   5 +
 15 files changed, 1148 insertions(+), 17 deletions(-)
 create mode 100644 drivers/net/ovpn/crypto.c
 create mode 100644 drivers/net/ovpn/crypto.h
 create mode 100644 drivers/net/ovpn/crypto_aead.c
 create mode 100644 drivers/net/ovpn/crypto_aead.h
 create mode 100644 drivers/net/ovpn/pktid.c
 create mode 100644 drivers/net/ovpn/pktid.h

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index dd6953636574a..2cc91b1348725 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -121,6 +121,10 @@ config OVPN
 	depends on IPV6 || !IPV6
 	select DST_CACHE
 	select NET_UDP_TUNNEL
+	select CRYPTO
+	select CRYPTO_AES
+	select CRYPTO_GCM
+	select CRYPTO_CHACHA20POLY1305
 	help
 	  This module enhances the performance of the OpenVPN userspace software
 	  by offloading the data channel processing to kernelspace.
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 164f2058ea8e6..38c9fdca0e2e8 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -8,10 +8,13 @@
 
 obj-$(CONFIG_OVPN) := ovpn.o
 ovpn-y += bind.o
+ovpn-y += crypto.o
+ovpn-y += crypto_aead.o
 ovpn-y += main.o
 ovpn-y += io.o
 ovpn-y += netlink.o
 ovpn-y += netlink-gen.o
 ovpn-y += peer.o
+ovpn-y += pktid.o
 ovpn-y += socket.o
 ovpn-y += udp.o
diff --git a/drivers/net/ovpn/bind.c b/drivers/net/ovpn/bind.c
index d4a1aeed12c99..24d2788a277e6 100644
--- a/drivers/net/ovpn/bind.c
+++ b/drivers/net/ovpn/bind.c
@@ -48,11 +48,8 @@ struct ovpn_bind *ovpn_bind_from_sockaddr(const struct sockaddr_storage *ss)
  */
 void ovpn_bind_reset(struct ovpn_peer *peer, struct ovpn_bind *new)
 {
-	struct ovpn_bind *old;
+	lockdep_assert_held(&peer->lock);
 
-	spin_lock_bh(&peer->lock);
-	old = rcu_replace_pointer(peer->bind, new, true);
-	spin_unlock_bh(&peer->lock);
-
-	kfree_rcu(old, rcu);
+	kfree_rcu(rcu_replace_pointer(peer->bind, new,
+				      lockdep_is_held(&peer->lock)), rcu);
 }
diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c
new file mode 100644
index 0000000000000..db243cb48142f
--- /dev/null
+++ b/drivers/net/ovpn/crypto.c
@@ -0,0 +1,152 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/types.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <uapi/linux/ovpn.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "pktid.h"
+#include "crypto_aead.h"
+#include "crypto.h"
+
+static void ovpn_ks_destroy_rcu(struct rcu_head *head)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = container_of(head, struct ovpn_crypto_key_slot, rcu);
+	ovpn_aead_crypto_key_slot_destroy(ks);
+}
+
+void ovpn_crypto_key_slot_release(struct kref *kref)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = container_of(kref, struct ovpn_crypto_key_slot, refcount);
+	call_rcu(&ks->rcu, ovpn_ks_destroy_rcu);
+}
+
+/* can only be invoked when all peer references have been dropped (i.e. RCU
+ * release routine)
+ */
+void ovpn_crypto_state_release(struct ovpn_crypto_state *cs)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	ks = rcu_access_pointer(cs->slots[0]);
+	if (ks) {
+		RCU_INIT_POINTER(cs->slots[0], NULL);
+		ovpn_crypto_key_slot_put(ks);
+	}
+
+	ks = rcu_access_pointer(cs->slots[1]);
+	if (ks) {
+		RCU_INIT_POINTER(cs->slots[1], NULL);
+		ovpn_crypto_key_slot_put(ks);
+	}
+}
+
+/* Reset the ovpn_crypto_state object in a way that is atomic
+ * to RCU readers.
+ */
+int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs,
+			    const struct ovpn_peer_key_reset *pkr)
+{
+	struct ovpn_crypto_key_slot *old = NULL, *new;
+	u8 idx;
+
+	if (pkr->slot != OVPN_KEY_SLOT_PRIMARY &&
+	    pkr->slot != OVPN_KEY_SLOT_SECONDARY)
+		return -EINVAL;
+
+	new = ovpn_aead_crypto_key_slot_new(&pkr->key);
+	if (IS_ERR(new))
+		return PTR_ERR(new);
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	switch (pkr->slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		old = rcu_replace_pointer(cs->slots[idx], new,
+					  lockdep_is_held(&cs->lock));
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		old = rcu_replace_pointer(cs->slots[!idx], new,
+					  lockdep_is_held(&cs->lock));
+		break;
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (old)
+		ovpn_crypto_key_slot_put(old);
+
+	return 0;
+}
+
+void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs,
+				 enum ovpn_key_slot slot)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+	u8 idx;
+
+	if (slot != OVPN_KEY_SLOT_PRIMARY &&
+	    slot != OVPN_KEY_SLOT_SECONDARY) {
+		pr_warn("Invalid slot to release: %u\n", slot);
+		return;
+	}
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	switch (slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		ks = rcu_replace_pointer(cs->slots[idx], NULL,
+					 lockdep_is_held(&cs->lock));
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		ks = rcu_replace_pointer(cs->slots[!idx], NULL,
+					 lockdep_is_held(&cs->lock));
+		break;
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (!ks) {
+		pr_debug("Key slot already released: %u\n", slot);
+		return;
+	}
+
+	pr_debug("deleting key slot %u, key_id=%u\n", slot, ks->key_id);
+	ovpn_crypto_key_slot_put(ks);
+}
+
+/* this swap is not atomic, but there will be a very short time frame where the
+ * old_secondary key won't be available. This should not be a big deal as most
+ * likely both peers are already using the new primary at this point.
+ */
+void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs)
+{
+	const struct ovpn_crypto_key_slot *old_primary, *old_secondary;
+	u8 idx;
+
+	spin_lock_bh(&cs->lock);
+	idx = cs->primary_idx;
+	old_primary = rcu_dereference_protected(cs->slots[idx],
+						lockdep_is_held(&cs->lock));
+	old_secondary = rcu_dereference_protected(cs->slots[!idx],
+						  lockdep_is_held(&cs->lock));
+	/* perform real swap by switching the index of the primary key */
+	WRITE_ONCE(cs->primary_idx, !cs->primary_idx);
+
+	pr_debug("key swapped: (old primary) %d <-> (new primary) %d\n",
+		 old_primary ? old_primary->key_id : -1,
+		 old_secondary ? old_secondary->key_id : -1);
+
+	spin_unlock_bh(&cs->lock);
+}
diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h
new file mode 100644
index 0000000000000..5155791b87df7
--- /dev/null
+++ b/drivers/net/ovpn/crypto.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNCRYPTO_H_
+#define _NET_OVPN_OVPNCRYPTO_H_
+
+#include "pktid.h"
+#include "proto.h"
+
+/* info needed for both encrypt and decrypt directions */
+struct ovpn_key_direction {
+	const u8 *cipher_key;
+	size_t cipher_key_size;
+	const u8 *nonce_tail; /* only needed for GCM modes */
+	size_t nonce_tail_size; /* only needed for GCM modes */
+};
+
+/* all info for a particular symmetric key (primary or secondary) */
+struct ovpn_key_config {
+	enum ovpn_cipher_alg cipher_alg;
+	u8 key_id;
+	struct ovpn_key_direction encrypt;
+	struct ovpn_key_direction decrypt;
+};
+
+/* used to pass settings from netlink to the crypto engine */
+struct ovpn_peer_key_reset {
+	enum ovpn_key_slot slot;
+	struct ovpn_key_config key;
+};
+
+struct ovpn_crypto_key_slot {
+	u8 key_id;
+
+	struct crypto_aead *encrypt;
+	struct crypto_aead *decrypt;
+	u8 nonce_tail_xmit[OVPN_NONCE_TAIL_SIZE];
+	u8 nonce_tail_recv[OVPN_NONCE_TAIL_SIZE];
+
+	struct ovpn_pktid_recv pid_recv ____cacheline_aligned_in_smp;
+	struct ovpn_pktid_xmit pid_xmit ____cacheline_aligned_in_smp;
+	struct kref refcount;
+	struct rcu_head rcu;
+};
+
+struct ovpn_crypto_state {
+	struct ovpn_crypto_key_slot __rcu *slots[2];
+	u8 primary_idx;
+
+	/* protects primary and secondary slots */
+	spinlock_t lock;
+};
+
+static inline bool ovpn_crypto_key_slot_hold(struct ovpn_crypto_key_slot *ks)
+{
+	return kref_get_unless_zero(&ks->refcount);
+}
+
+static inline void ovpn_crypto_state_init(struct ovpn_crypto_state *cs)
+{
+	RCU_INIT_POINTER(cs->slots[0], NULL);
+	RCU_INIT_POINTER(cs->slots[1], NULL);
+	cs->primary_idx = 0;
+	spin_lock_init(&cs->lock);
+}
+
+static inline struct ovpn_crypto_key_slot *
+ovpn_crypto_key_id_to_slot(const struct ovpn_crypto_state *cs, u8 key_id)
+{
+	struct ovpn_crypto_key_slot *ks;
+	u8 idx;
+
+	if (unlikely(!cs))
+		return NULL;
+
+	rcu_read_lock();
+	idx = READ_ONCE(cs->primary_idx);
+	ks = rcu_dereference(cs->slots[idx]);
+	if (ks && ks->key_id == key_id) {
+		if (unlikely(!ovpn_crypto_key_slot_hold(ks)))
+			ks = NULL;
+		goto out;
+	}
+
+	ks = rcu_dereference(cs->slots[!idx]);
+	if (ks && ks->key_id == key_id) {
+		if (unlikely(!ovpn_crypto_key_slot_hold(ks)))
+			ks = NULL;
+		goto out;
+	}
+
+	/* when both key slots are occupied but no matching key ID is found, ks
+	 * has to be reset to NULL to avoid carrying a stale pointer
+	 */
+	ks = NULL;
+out:
+	rcu_read_unlock();
+
+	return ks;
+}
+
+static inline struct ovpn_crypto_key_slot *
+ovpn_crypto_key_slot_primary(const struct ovpn_crypto_state *cs)
+{
+	struct ovpn_crypto_key_slot *ks;
+
+	rcu_read_lock();
+	ks = rcu_dereference(cs->slots[cs->primary_idx]);
+	if (unlikely(ks && !ovpn_crypto_key_slot_hold(ks)))
+		ks = NULL;
+	rcu_read_unlock();
+
+	return ks;
+}
+
+void ovpn_crypto_key_slot_release(struct kref *kref);
+
+static inline void ovpn_crypto_key_slot_put(struct ovpn_crypto_key_slot *ks)
+{
+	kref_put(&ks->refcount, ovpn_crypto_key_slot_release);
+}
+
+int ovpn_crypto_state_reset(struct ovpn_crypto_state *cs,
+			    const struct ovpn_peer_key_reset *pkr);
+
+void ovpn_crypto_key_slot_delete(struct ovpn_crypto_state *cs,
+				 enum ovpn_key_slot slot);
+
+void ovpn_crypto_state_release(struct ovpn_crypto_state *cs);
+
+void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs);
+
+#endif /* _NET_OVPN_OVPNCRYPTO_H_ */
diff --git a/drivers/net/ovpn/crypto_aead.c b/drivers/net/ovpn/crypto_aead.c
new file mode 100644
index 0000000000000..e87e33f49c308
--- /dev/null
+++ b/drivers/net/ovpn/crypto_aead.c
@@ -0,0 +1,392 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <crypto/aead.h>
+#include <linux/skbuff.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/udp.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "pktid.h"
+#include "crypto_aead.h"
+#include "crypto.h"
+#include "peer.h"
+#include "proto.h"
+#include "skb.h"
+
+#define OVPN_AUTH_TAG_SIZE	16
+#define OVPN_AAD_SIZE		(OVPN_OPCODE_SIZE + OVPN_NONCE_WIRE_SIZE)
+
+#define ALG_NAME_AES		"gcm(aes)"
+#define ALG_NAME_CHACHAPOLY	"rfc7539(chacha20,poly1305)"
+
+static int ovpn_aead_encap_overhead(const struct ovpn_crypto_key_slot *ks)
+{
+	return  OVPN_OPCODE_SIZE +			/* OP header size */
+		sizeof(u32) +				/* Packet ID */
+		crypto_aead_authsize(ks->encrypt);	/* Auth Tag */
+}
+
+int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb)
+{
+	const unsigned int tag_size = crypto_aead_authsize(ks->encrypt);
+	struct aead_request *req;
+	struct sk_buff *trailer;
+	struct scatterlist *sg;
+	int nfrags, ret;
+	u32 pktid, op;
+	u8 *iv;
+
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_skb_cb(skb)->ks = ks;
+
+	/* Sample AEAD header format:
+	 * 48000001 00000005 7e7046bd 444a7e28 cc6387b1 64a4d6c1 380275a...
+	 * [ OP32 ] [seq # ] [             auth tag            ] [ payload ... ]
+	 *          [4-byte
+	 *          IV head]
+	 */
+
+	/* check that there's enough headroom in the skb for packet
+	 * encapsulation
+	 */
+	if (unlikely(skb_cow_head(skb, OVPN_HEAD_ROOM)))
+		return -ENOBUFS;
+
+	/* get number of skb frags and ensure that packet data is writable */
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(nfrags < 0))
+		return nfrags;
+
+	if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2)))
+		return -ENOSPC;
+
+	/* sg may be required by async crypto */
+	ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) *
+				       (nfrags + 2), GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->sg))
+		return -ENOMEM;
+
+	sg = ovpn_skb_cb(skb)->sg;
+
+	/* sg table:
+	 * 0: op, wire nonce (AD, len=OVPN_OP_SIZE_V2+OVPN_NONCE_WIRE_SIZE),
+	 * 1, 2, 3, ..., n: payload,
+	 * n+1: auth_tag (len=tag_size)
+	 */
+	sg_init_table(sg, nfrags + 2);
+
+	/* build scatterlist to encrypt packet payload */
+	ret = skb_to_sgvec_nomark(skb, sg + 1, 0, skb->len);
+	if (unlikely(nfrags != ret)) {
+		ret = -EINVAL;
+		goto free_sg;
+	}
+
+	/* append auth_tag onto scatterlist */
+	__skb_push(skb, tag_size);
+	sg_set_buf(sg + nfrags + 1, skb->data, tag_size);
+
+	/* obtain packet ID, which is used both as a first
+	 * 4 bytes of nonce and last 4 bytes of associated data.
+	 */
+	ret = ovpn_pktid_xmit_next(&ks->pid_xmit, &pktid);
+	if (unlikely(ret < 0))
+		goto free_sg;
+
+	/* iv may be required by async crypto */
+	ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->iv)) {
+		ret = -ENOMEM;
+		goto free_sg;
+	}
+
+	iv = ovpn_skb_cb(skb)->iv;
+
+	/* concat 4 bytes packet id and 8 bytes nonce tail into 12 bytes
+	 * nonce
+	 */
+	ovpn_pktid_aead_write(pktid, ks->nonce_tail_xmit, iv);
+
+	/* make space for packet id and push it to the front */
+	__skb_push(skb, OVPN_NONCE_WIRE_SIZE);
+	memcpy(skb->data, iv, OVPN_NONCE_WIRE_SIZE);
+
+	/* add packet op as head of additional data */
+	op = ovpn_opcode_compose(OVPN_DATA_V2, ks->key_id, peer->id);
+	__skb_push(skb, OVPN_OPCODE_SIZE);
+	BUILD_BUG_ON(sizeof(op) != OVPN_OPCODE_SIZE);
+	*((__force __be32 *)skb->data) = htonl(op);
+
+	/* AEAD Additional data */
+	sg_set_buf(sg, skb->data, OVPN_AAD_SIZE);
+
+	req = aead_request_alloc(ks->encrypt, GFP_ATOMIC);
+	if (unlikely(!req)) {
+		ret = -ENOMEM;
+		goto free_iv;
+	}
+
+	ovpn_skb_cb(skb)->req = req;
+
+	/* setup async crypto operation */
+	aead_request_set_tfm(req, ks->encrypt);
+	aead_request_set_callback(req, 0, ovpn_encrypt_post, skb);
+	aead_request_set_crypt(req, sg, sg,
+			       skb->len - ovpn_aead_encap_overhead(ks), iv);
+	aead_request_set_ad(req, OVPN_AAD_SIZE);
+
+	/* encrypt it */
+	return crypto_aead_encrypt(req);
+free_iv:
+	kfree(ovpn_skb_cb(skb)->iv);
+	ovpn_skb_cb(skb)->iv = NULL;
+free_sg:
+	kfree(ovpn_skb_cb(skb)->sg);
+	ovpn_skb_cb(skb)->sg = NULL;
+	return ret;
+}
+
+int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb)
+{
+	const unsigned int tag_size = crypto_aead_authsize(ks->decrypt);
+	int ret, payload_len, nfrags;
+	unsigned int payload_offset;
+	struct aead_request *req;
+	struct sk_buff *trailer;
+	struct scatterlist *sg;
+	u8 *iv;
+
+	payload_offset = OVPN_AAD_SIZE + tag_size;
+	payload_len = skb->len - payload_offset;
+
+	ovpn_skb_cb(skb)->payload_offset = payload_offset;
+	ovpn_skb_cb(skb)->peer = peer;
+	ovpn_skb_cb(skb)->ks = ks;
+
+	/* sanity check on packet size, payload size must be >= 0 */
+	if (unlikely(payload_len < 0))
+		return -EINVAL;
+
+	/* Prepare the skb data buffer to be accessed up until the auth tag.
+	 * This is required because this area is directly mapped into the sg
+	 * list.
+	 */
+	if (unlikely(!pskb_may_pull(skb, payload_offset)))
+		return -ENODATA;
+
+	/* get number of skb frags and ensure that packet data is writable */
+	nfrags = skb_cow_data(skb, 0, &trailer);
+	if (unlikely(nfrags < 0))
+		return nfrags;
+
+	if (unlikely(nfrags + 2 > (MAX_SKB_FRAGS + 2)))
+		return -ENOSPC;
+
+	/* sg may be required by async crypto */
+	ovpn_skb_cb(skb)->sg = kmalloc(sizeof(*ovpn_skb_cb(skb)->sg) *
+				       (nfrags + 2), GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->sg))
+		return -ENOMEM;
+
+	sg = ovpn_skb_cb(skb)->sg;
+
+	/* sg table:
+	 * 0: op, wire nonce (AD, len=OVPN_OPCODE_SIZE+OVPN_NONCE_WIRE_SIZE),
+	 * 1, 2, 3, ..., n: payload,
+	 * n+1: auth_tag (len=tag_size)
+	 */
+	sg_init_table(sg, nfrags + 2);
+
+	/* packet op is head of additional data */
+	sg_set_buf(sg, skb->data, OVPN_AAD_SIZE);
+
+	/* build scatterlist to decrypt packet payload */
+	ret = skb_to_sgvec_nomark(skb, sg + 1, payload_offset, payload_len);
+	if (unlikely(nfrags != ret)) {
+		ret = -EINVAL;
+		goto free_sg;
+	}
+
+	/* append auth_tag onto scatterlist */
+	sg_set_buf(sg + nfrags + 1, skb->data + OVPN_AAD_SIZE, tag_size);
+
+	/* iv may be required by async crypto */
+	ovpn_skb_cb(skb)->iv = kmalloc(OVPN_NONCE_SIZE, GFP_ATOMIC);
+	if (unlikely(!ovpn_skb_cb(skb)->iv)) {
+		ret = -ENOMEM;
+		goto free_sg;
+	}
+
+	iv = ovpn_skb_cb(skb)->iv;
+
+	/* copy nonce into IV buffer */
+	memcpy(iv, skb->data + OVPN_OPCODE_SIZE, OVPN_NONCE_WIRE_SIZE);
+	memcpy(iv + OVPN_NONCE_WIRE_SIZE, ks->nonce_tail_recv,
+	       OVPN_NONCE_TAIL_SIZE);
+
+	req = aead_request_alloc(ks->decrypt, GFP_ATOMIC);
+	if (unlikely(!req)) {
+		ret = -ENOMEM;
+		goto free_iv;
+	}
+
+	ovpn_skb_cb(skb)->req = req;
+
+	/* setup async crypto operation */
+	aead_request_set_tfm(req, ks->decrypt);
+	aead_request_set_callback(req, 0, ovpn_decrypt_post, skb);
+	aead_request_set_crypt(req, sg, sg, payload_len + tag_size, iv);
+
+	aead_request_set_ad(req, OVPN_AAD_SIZE);
+
+	/* decrypt it */
+	return crypto_aead_decrypt(req);
+free_iv:
+	kfree(ovpn_skb_cb(skb)->iv);
+	ovpn_skb_cb(skb)->iv = NULL;
+free_sg:
+	kfree(ovpn_skb_cb(skb)->sg);
+	ovpn_skb_cb(skb)->sg = NULL;
+	return ret;
+}
+
+/* Initialize a struct crypto_aead object */
+static struct crypto_aead *ovpn_aead_init(const char *title,
+					  const char *alg_name,
+					  const unsigned char *key,
+					  unsigned int keylen)
+{
+	struct crypto_aead *aead;
+	int ret;
+
+	aead = crypto_alloc_aead(alg_name, 0, 0);
+	if (IS_ERR(aead)) {
+		ret = PTR_ERR(aead);
+		pr_err("%s crypto_alloc_aead failed, err=%d\n", title, ret);
+		aead = NULL;
+		goto error;
+	}
+
+	ret = crypto_aead_setkey(aead, key, keylen);
+	if (ret) {
+		pr_err("%s crypto_aead_setkey size=%u failed, err=%d\n", title,
+		       keylen, ret);
+		goto error;
+	}
+
+	ret = crypto_aead_setauthsize(aead, OVPN_AUTH_TAG_SIZE);
+	if (ret) {
+		pr_err("%s crypto_aead_setauthsize failed, err=%d\n", title,
+		       ret);
+		goto error;
+	}
+
+	/* basic AEAD assumption */
+	if (crypto_aead_ivsize(aead) != OVPN_NONCE_SIZE) {
+		pr_err("%s IV size must be %d\n", title, OVPN_NONCE_SIZE);
+		ret = -EINVAL;
+		goto error;
+	}
+
+	pr_debug("********* Cipher %s (%s)\n", alg_name, title);
+	pr_debug("*** IV size=%u\n", crypto_aead_ivsize(aead));
+	pr_debug("*** req size=%u\n", crypto_aead_reqsize(aead));
+	pr_debug("*** block size=%u\n", crypto_aead_blocksize(aead));
+	pr_debug("*** auth size=%u\n", crypto_aead_authsize(aead));
+	pr_debug("*** alignmask=0x%x\n", crypto_aead_alignmask(aead));
+
+	return aead;
+
+error:
+	crypto_free_aead(aead);
+	return ERR_PTR(ret);
+}
+
+void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks)
+{
+	if (!ks)
+		return;
+
+	crypto_free_aead(ks->encrypt);
+	crypto_free_aead(ks->decrypt);
+	kfree(ks);
+}
+
+struct ovpn_crypto_key_slot *
+ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+	const char *alg_name;
+	int ret;
+
+	/* validate crypto alg */
+	switch (kc->cipher_alg) {
+	case OVPN_CIPHER_ALG_AES_GCM:
+		alg_name = ALG_NAME_AES;
+		break;
+	case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+		alg_name = ALG_NAME_CHACHAPOLY;
+		break;
+	default:
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
+	if (kc->encrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE ||
+	    kc->decrypt.nonce_tail_size != OVPN_NONCE_TAIL_SIZE)
+		return ERR_PTR(-EINVAL);
+
+	/* build the key slot */
+	ks = kmalloc(sizeof(*ks), GFP_KERNEL);
+	if (!ks)
+		return ERR_PTR(-ENOMEM);
+
+	ks->encrypt = NULL;
+	ks->decrypt = NULL;
+	kref_init(&ks->refcount);
+	ks->key_id = kc->key_id;
+
+	ks->encrypt = ovpn_aead_init("encrypt", alg_name,
+				     kc->encrypt.cipher_key,
+				     kc->encrypt.cipher_key_size);
+	if (IS_ERR(ks->encrypt)) {
+		ret = PTR_ERR(ks->encrypt);
+		ks->encrypt = NULL;
+		goto destroy_ks;
+	}
+
+	ks->decrypt = ovpn_aead_init("decrypt", alg_name,
+				     kc->decrypt.cipher_key,
+				     kc->decrypt.cipher_key_size);
+	if (IS_ERR(ks->decrypt)) {
+		ret = PTR_ERR(ks->decrypt);
+		ks->decrypt = NULL;
+		goto destroy_ks;
+	}
+
+	memcpy(ks->nonce_tail_xmit, kc->encrypt.nonce_tail,
+	       OVPN_NONCE_TAIL_SIZE);
+	memcpy(ks->nonce_tail_recv, kc->decrypt.nonce_tail,
+	       OVPN_NONCE_TAIL_SIZE);
+
+	/* init packet ID generation/validation */
+	ovpn_pktid_xmit_init(&ks->pid_xmit);
+	ovpn_pktid_recv_init(&ks->pid_recv);
+
+	return ks;
+
+destroy_ks:
+	ovpn_aead_crypto_key_slot_destroy(ks);
+	return ERR_PTR(ret);
+}
diff --git a/drivers/net/ovpn/crypto_aead.h b/drivers/net/ovpn/crypto_aead.h
new file mode 100644
index 0000000000000..40c056558add3
--- /dev/null
+++ b/drivers/net/ovpn/crypto_aead.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNAEAD_H_
+#define _NET_OVPN_OVPNAEAD_H_
+
+#include "crypto.h"
+
+#include <asm/types.h>
+#include <linux/skbuff.h>
+
+int ovpn_aead_encrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb);
+int ovpn_aead_decrypt(struct ovpn_peer *peer, struct ovpn_crypto_key_slot *ks,
+		      struct sk_buff *skb);
+
+struct ovpn_crypto_key_slot *
+ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc);
+void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks);
+
+#endif /* _NET_OVPN_OVPNAEAD_H_ */
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 46ad27e8eb842..f8113f160148c 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -7,6 +7,7 @@
  *		Antonio Quartulli <antonio@openvpn.net>
  */
 
+#include <crypto/aead.h>
 #include <linux/netdevice.h>
 #include <linux/skbuff.h>
 #include <net/gro_cells.h>
@@ -15,6 +16,9 @@
 #include "ovpnpriv.h"
 #include "peer.h"
 #include "io.h"
+#include "bind.h"
+#include "crypto.h"
+#include "crypto_aead.h"
 #include "netlink.h"
 #include "proto.h"
 #include "udp.h"
@@ -44,7 +48,7 @@ static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
 	skb_set_queue_mapping(skb, 0);
 	skb_scrub_packet(skb, true);
 
-	skb_reset_network_header(skb);
+	/* network header reset in ovpn_decrypt_post() */
 	skb_reset_transport_header(skb);
 	skb_reset_inner_headers(skb);
 
@@ -56,34 +60,147 @@ static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
 		dev_sw_netstats_rx_add(peer->ovpn->dev, pkt_len);
 }
 
-static void ovpn_decrypt_post(struct sk_buff *skb, int ret)
+void ovpn_decrypt_post(void *data, int ret)
 {
-	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
+	struct ovpn_crypto_key_slot *ks;
+	unsigned int payload_offset = 0;
+	struct sk_buff *skb = data;
+	struct ovpn_peer *peer;
+	__be16 proto;
+	__be32 *pid;
+
+	/* crypto is happening asynchronously. this function will be called
+	 * again later by the crypto callback with a proper return code
+	 */
+	if (unlikely(ret == -EINPROGRESS))
+		return;
+
+	payload_offset = ovpn_skb_cb(skb)->payload_offset;
+	ks = ovpn_skb_cb(skb)->ks;
+	peer = ovpn_skb_cb(skb)->peer;
+
+	/* crypto is done, cleanup skb CB and its members */
+
+	if (likely(ovpn_skb_cb(skb)->iv))
+		kfree(ovpn_skb_cb(skb)->iv);
+
+	if (likely(ovpn_skb_cb(skb)->sg))
+		kfree(ovpn_skb_cb(skb)->sg);
+
+	if (likely(ovpn_skb_cb(skb)->req))
+		aead_request_free(ovpn_skb_cb(skb)->req);
 
 	if (unlikely(ret < 0))
 		goto drop;
 
+	/* PID sits after the op */
+	pid = (__force __be32 *)(skb->data + OVPN_OPCODE_SIZE);
+	ret = ovpn_pktid_recv(&ks->pid_recv, ntohl(*pid), 0);
+	if (unlikely(ret < 0)) {
+		net_err_ratelimited("%s: PKT ID RX error for peer %u: %d\n",
+				    netdev_name(peer->ovpn->dev), peer->id,
+				    ret);
+		goto drop;
+	}
+
+	/* point to encapsulated IP packet */
+	__skb_pull(skb, payload_offset);
+
+	/* check if this is a valid datapacket that has to be delivered to the
+	 * ovpn interface
+	 */
+	skb_reset_network_header(skb);
+	proto = ovpn_ip_check_protocol(skb);
+	if (unlikely(!proto)) {
+		/* check if null packet */
+		if (unlikely(!pskb_may_pull(skb, 1))) {
+			net_info_ratelimited("%s: NULL packet received from peer %u\n",
+					     netdev_name(peer->ovpn->dev),
+					     peer->id);
+			goto drop;
+		}
+
+		net_info_ratelimited("%s: unsupported protocol received from peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto drop;
+	}
+	skb->protocol = proto;
+
+	/* perform Reverse Path Filtering (RPF) */
+	if (unlikely(!ovpn_peer_check_by_src(peer->ovpn, skb, peer))) {
+		if (skb->protocol == htons(ETH_P_IPV6))
+			net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI6c\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &ipv6_hdr(skb)->saddr);
+		else
+			net_dbg_ratelimited("%s: RPF dropped packet from peer %u, src: %pI4\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &ip_hdr(skb)->saddr);
+		goto drop;
+	}
+
 	ovpn_netdev_write(peer, skb);
 	/* skb is passed to upper layer - don't free it */
 	skb = NULL;
 drop:
 	if (unlikely(skb))
 		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
-	ovpn_peer_put(peer);
+	if (likely(peer))
+		ovpn_peer_put(peer);
+	if (likely(ks))
+		ovpn_crypto_key_slot_put(ks);
 	kfree_skb(skb);
 }
 
 /* RX path entry point: decrypt packet and forward it to the device */
 void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb)
 {
-	ovpn_skb_cb(skb)->peer = peer;
-	ovpn_decrypt_post(skb, 0);
+	struct ovpn_crypto_key_slot *ks;
+	u8 key_id;
+
+	/* get the key slot matching the key ID in the received packet */
+	key_id = ovpn_key_id_from_skb(skb);
+	ks = ovpn_crypto_key_id_to_slot(&peer->crypto, key_id);
+	if (unlikely(!ks)) {
+		net_info_ratelimited("%s: no available key for peer %u, key-id: %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id,
+				     key_id);
+		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+		kfree_skb(skb);
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb));
+	ovpn_decrypt_post(skb, ovpn_aead_decrypt(peer, ks, skb));
 }
 
-static void ovpn_encrypt_post(struct sk_buff *skb, int ret)
+void ovpn_encrypt_post(void *data, int ret)
 {
-	struct ovpn_peer *peer = ovpn_skb_cb(skb)->peer;
+	struct ovpn_crypto_key_slot *ks;
+	struct sk_buff *skb = data;
 	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+
+	/* encryption is happening asynchronously. This function will be
+	 * called later by the crypto callback with a proper return value
+	 */
+	if (unlikely(ret == -EINPROGRESS))
+		return;
+
+	ks = ovpn_skb_cb(skb)->ks;
+	peer = ovpn_skb_cb(skb)->peer;
+
+	/* crypto is done, cleanup skb CB and its members */
+
+	if (likely(ovpn_skb_cb(skb)->iv))
+		kfree(ovpn_skb_cb(skb)->iv);
+
+	if (likely(ovpn_skb_cb(skb)->sg))
+		kfree(ovpn_skb_cb(skb)->sg);
+
+	if (likely(ovpn_skb_cb(skb)->req))
+		aead_request_free(ovpn_skb_cb(skb)->req);
 
 	if (unlikely(ret < 0))
 		goto err;
@@ -110,23 +227,33 @@ static void ovpn_encrypt_post(struct sk_buff *skb, int ret)
 err:
 	if (unlikely(skb))
 		dev_core_stats_tx_dropped_inc(peer->ovpn->dev);
-	ovpn_peer_put(peer);
+	if (likely(peer))
+		ovpn_peer_put(peer);
+	if (likely(ks))
+		ovpn_crypto_key_slot_put(ks);
 	kfree_skb(skb);
 }
 
 static bool ovpn_encrypt_one(struct ovpn_peer *peer, struct sk_buff *skb)
 {
-	ovpn_skb_cb(skb)->peer = peer;
+	struct ovpn_crypto_key_slot *ks;
+
+	/* get primary key to be used for encrypting data */
+	ks = ovpn_crypto_key_slot_primary(&peer->crypto);
+	if (unlikely(!ks))
+		return false;
 
 	/* take a reference to the peer because the crypto code may run async.
 	 * ovpn_encrypt_post() will release it upon completion
 	 */
 	if (unlikely(!ovpn_peer_hold(peer))) {
 		DEBUG_NET_WARN_ON_ONCE(1);
+		ovpn_crypto_key_slot_put(ks);
 		return false;
 	}
 
-	ovpn_encrypt_post(skb, 0);
+	memset(ovpn_skb_cb(skb), 0, sizeof(struct ovpn_cb));
+	ovpn_encrypt_post(skb, ovpn_aead_encrypt(peer, ks, skb));
 	return true;
 }
 
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
index 1cfa66873a2d4..5143104b2c4b8 100644
--- a/drivers/net/ovpn/io.h
+++ b/drivers/net/ovpn/io.h
@@ -23,4 +23,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
 
 void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
 
+void ovpn_encrypt_post(void *data, int ret);
+void ovpn_decrypt_post(void *data, int ret);
+
 #endif /* _NET_OVPN_OVPN_H_ */
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 10eabd62ae723..23eaab1b465b8 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -12,6 +12,8 @@
 
 #include "ovpnpriv.h"
 #include "bind.h"
+#include "pktid.h"
+#include "crypto.h"
 #include "io.h"
 #include "main.h"
 #include "netlink.h"
@@ -56,6 +58,7 @@ struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
 	peer->vpn_addrs.ipv6 = in6addr_any;
 
 	RCU_INIT_POINTER(peer->bind, NULL);
+	ovpn_crypto_state_init(&peer->crypto);
 	spin_lock_init(&peer->lock);
 	kref_init(&peer->refcount);
 
@@ -94,7 +97,10 @@ static void ovpn_peer_release_rcu(struct rcu_head *head)
  */
 static void ovpn_peer_release(struct ovpn_peer *peer)
 {
+	ovpn_crypto_state_release(&peer->crypto);
+	spin_lock_bh(&peer->lock);
 	ovpn_bind_reset(peer, NULL);
+	spin_unlock_bh(&peer->lock);
 	call_rcu(&peer->rcu, ovpn_peer_release_rcu);
 	netdev_put(peer->ovpn->dev, &peer->dev_tracker);
 }
@@ -326,6 +332,29 @@ struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 	return peer;
 }
 
+/**
+ * ovpn_peer_check_by_src - check that skb source is routed via peer
+ * @ovpn: the openvpn instance to search
+ * @skb: the packet to extract source address from
+ * @peer: the peer to check against the source address
+ *
+ * Return: true if the peer is matching or false otherwise
+ */
+bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
+			    struct ovpn_peer *peer)
+{
+	bool match = false;
+
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		/* in P2P mode, no matter the destination, packets are always
+		 * sent to the single peer listening on the other side
+		 */
+		match = (peer == rcu_access_pointer(ovpn->peer));
+	}
+
+	return match;
+}
+
 /**
  * ovpn_peer_add_p2p - add peer to related tables in a P2P instance
  * @ovpn: the instance to add the peer to
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index fef04311c1593..a9113a969f94d 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -12,6 +12,7 @@
 
 #include <net/dst_cache.h>
 
+#include "crypto.h"
 #include "socket.h"
 
 /**
@@ -23,6 +24,7 @@
  * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
  * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
  * @sock: the socket being used to talk to this peer
+ * @crypto: the crypto configuration (ciphers, keys, etc..)
  * @dst_cache: cache for dst_entry used to send to peer
  * @bind: remote peer binding
  * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
@@ -40,6 +42,7 @@ struct ovpn_peer {
 		struct in6_addr ipv6;
 	} vpn_addrs;
 	struct ovpn_socket __rcu *sock;
+	struct ovpn_crypto_state crypto;
 	struct dst_cache dst_cache;
 	struct ovpn_bind __rcu *bind;
 	enum ovpn_del_peer_reason delete_reason;
@@ -82,5 +85,7 @@ struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
 struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id);
 struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 				       struct sk_buff *skb);
+bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
+			    struct ovpn_peer *peer);
 
 #endif /* _NET_OVPN_OVPNPEER_H_ */
diff --git a/drivers/net/ovpn/pktid.c b/drivers/net/ovpn/pktid.c
new file mode 100644
index 0000000000000..2e73d1c1ec8b6
--- /dev/null
+++ b/drivers/net/ovpn/pktid.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#include <linux/atomic.h>
+#include <linux/jiffies.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
+#include <linux/types.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "pktid.h"
+
+void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid)
+{
+	atomic64_set(&pid->seq_num, 1);
+}
+
+void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr)
+{
+	memset(pr, 0, sizeof(*pr));
+	spin_lock_init(&pr->lock);
+}
+
+/* Packet replay detection.
+ * Allows ID backtrack of up to REPLAY_WINDOW_SIZE - 1.
+ */
+int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time)
+{
+	const unsigned long now = jiffies;
+	int ret;
+
+	/* ID must not be zero */
+	if (unlikely(pkt_id == 0))
+		return -EINVAL;
+
+	spin_lock_bh(&pr->lock);
+
+	/* expire backtracks at or below pr->id after PKTID_RECV_EXPIRE time */
+	if (unlikely(time_after_eq(now, pr->expire)))
+		pr->id_floor = pr->id;
+
+	/* time changed? */
+	if (unlikely(pkt_time != pr->time)) {
+		if (pkt_time > pr->time) {
+			/* time moved forward, accept */
+			pr->base = 0;
+			pr->extent = 0;
+			pr->id = 0;
+			pr->time = pkt_time;
+			pr->id_floor = 0;
+		} else {
+			/* time moved backward, reject */
+			ret = -ETIME;
+			goto out;
+		}
+	}
+
+	if (likely(pkt_id == pr->id + 1)) {
+		/* well-formed ID sequence (incremented by 1) */
+		pr->base = REPLAY_INDEX(pr->base, -1);
+		pr->history[pr->base / 8] |= (1 << (pr->base % 8));
+		if (pr->extent < REPLAY_WINDOW_SIZE)
+			++pr->extent;
+		pr->id = pkt_id;
+	} else if (pkt_id > pr->id) {
+		/* ID jumped forward by more than one */
+		const unsigned int delta = pkt_id - pr->id;
+
+		if (delta < REPLAY_WINDOW_SIZE) {
+			unsigned int i;
+
+			pr->base = REPLAY_INDEX(pr->base, -delta);
+			pr->history[pr->base / 8] |= (1 << (pr->base % 8));
+			pr->extent += delta;
+			if (pr->extent > REPLAY_WINDOW_SIZE)
+				pr->extent = REPLAY_WINDOW_SIZE;
+			for (i = 1; i < delta; ++i) {
+				unsigned int newb = REPLAY_INDEX(pr->base, i);
+
+				pr->history[newb / 8] &= ~BIT(newb % 8);
+			}
+		} else {
+			pr->base = 0;
+			pr->extent = REPLAY_WINDOW_SIZE;
+			memset(pr->history, 0, sizeof(pr->history));
+			pr->history[0] = 1;
+		}
+		pr->id = pkt_id;
+	} else {
+		/* ID backtrack */
+		const unsigned int delta = pr->id - pkt_id;
+
+		if (delta > pr->max_backtrack)
+			pr->max_backtrack = delta;
+		if (delta < pr->extent) {
+			if (pkt_id > pr->id_floor) {
+				const unsigned int ri = REPLAY_INDEX(pr->base,
+								     delta);
+				u8 *p = &pr->history[ri / 8];
+				const u8 mask = (1 << (ri % 8));
+
+				if (*p & mask) {
+					ret = -EINVAL;
+					goto out;
+				}
+				*p |= mask;
+			} else {
+				ret = -EINVAL;
+				goto out;
+			}
+		} else {
+			ret = -EINVAL;
+			goto out;
+		}
+	}
+
+	pr->expire = now + PKTID_RECV_EXPIRE;
+	ret = 0;
+out:
+	spin_unlock_bh(&pr->lock);
+	return ret;
+}
diff --git a/drivers/net/ovpn/pktid.h b/drivers/net/ovpn/pktid.h
new file mode 100644
index 0000000000000..0e5fd91d48835
--- /dev/null
+++ b/drivers/net/ovpn/pktid.h
@@ -0,0 +1,87 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ *		James Yonan <james@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNPKTID_H_
+#define _NET_OVPN_OVPNPKTID_H_
+
+#include "proto.h"
+
+/* If no packets received for this length of time, set a backtrack floor
+ * at highest received packet ID thus far.
+ */
+#define PKTID_RECV_EXPIRE (30 * HZ)
+
+/* Packet-ID state for transmitter */
+struct ovpn_pktid_xmit {
+	atomic64_t seq_num;
+};
+
+/* replay window sizing in bytes = 2^REPLAY_WINDOW_ORDER */
+#define REPLAY_WINDOW_ORDER 8
+
+#define REPLAY_WINDOW_BYTES BIT(REPLAY_WINDOW_ORDER)
+#define REPLAY_WINDOW_SIZE  (REPLAY_WINDOW_BYTES * 8)
+#define REPLAY_INDEX(base, i) (((base) + (i)) & (REPLAY_WINDOW_SIZE - 1))
+
+/* Packet-ID state for receiver.
+ * Other than lock member, can be zeroed to initialize.
+ */
+struct ovpn_pktid_recv {
+	/* "sliding window" bitmask of recent packet IDs received */
+	u8 history[REPLAY_WINDOW_BYTES];
+	/* bit position of deque base in history */
+	unsigned int base;
+	/* extent (in bits) of deque in history */
+	unsigned int extent;
+	/* expiration of history in jiffies */
+	unsigned long expire;
+	/* highest sequence number received */
+	u32 id;
+	/* highest time stamp received */
+	u32 time;
+	/* we will only accept backtrack IDs > id_floor */
+	u32 id_floor;
+	unsigned int max_backtrack;
+	/* protects entire pktd ID state */
+	spinlock_t lock;
+};
+
+/* Get the next packet ID for xmit */
+static inline int ovpn_pktid_xmit_next(struct ovpn_pktid_xmit *pid, u32 *pktid)
+{
+	const s64 seq_num = atomic64_fetch_add_unless(&pid->seq_num, 1,
+						      0x100000000LL);
+	/* when the 32bit space is over, we return an error because the packet
+	 * ID is used to create the cipher IV and we do not want to reuse the
+	 * same value more than once
+	 */
+	if (unlikely(seq_num == 0x100000000LL))
+		return -ERANGE;
+
+	*pktid = (u32)seq_num;
+
+	return 0;
+}
+
+/* Write 12-byte AEAD IV to dest */
+static inline void ovpn_pktid_aead_write(const u32 pktid,
+					 const u8 nt[],
+					 unsigned char *dest)
+{
+	*(__force __be32 *)(dest) = htonl(pktid);
+	BUILD_BUG_ON(4 + OVPN_NONCE_TAIL_SIZE != OVPN_NONCE_SIZE);
+	memcpy(dest + 4, nt, OVPN_NONCE_TAIL_SIZE);
+}
+
+void ovpn_pktid_xmit_init(struct ovpn_pktid_xmit *pid);
+void ovpn_pktid_recv_init(struct ovpn_pktid_recv *pr);
+
+int ovpn_pktid_recv(struct ovpn_pktid_recv *pr, u32 pkt_id, u32 pkt_time);
+
+#endif /* _NET_OVPN_OVPNPKTID_H_ */
diff --git a/drivers/net/ovpn/proto.h b/drivers/net/ovpn/proto.h
index 591b97a9925fd..b7322c7c515e5 100644
--- a/drivers/net/ovpn/proto.h
+++ b/drivers/net/ovpn/proto.h
@@ -83,4 +83,36 @@ static inline u32 ovpn_peer_id_from_skb(const struct sk_buff *skb, u16 offset)
 	return FIELD_GET(OVPN_OPCODE_PEERID_MASK, opcode);
 }
 
+/**
+ * ovpn_key_id_from_skb - extract key ID from the skb head
+ * @skb: the packet to extract the key ID code from
+ *
+ * Note: this function assumes that the skb head was pulled enough
+ * to access the first byte.
+ *
+ * Return: the key ID
+ */
+static inline u8 ovpn_key_id_from_skb(const struct sk_buff *skb)
+{
+	u32 opcode = be32_to_cpu(*(__be32 *)skb->data);
+
+	return FIELD_GET(OVPN_OPCODE_KEYID_MASK, opcode);
+}
+
+/**
+ * ovpn_opcode_compose - combine OP code, key ID and peer ID to wire format
+ * @opcode: the OP code
+ * @key_id: the key ID
+ * @peer_id: the peer ID
+ *
+ * Return: a 4 bytes integer obtained combining all input values following the
+ * OpenVPN wire format. This integer can then be written to the packet header.
+ */
+static inline u32 ovpn_opcode_compose(u8 opcode, u8 key_id, u32 peer_id)
+{
+	return FIELD_PREP(OVPN_OPCODE_PKTTYPE_MASK, opcode) |
+	       FIELD_PREP(OVPN_OPCODE_KEYID_MASK, key_id) |
+	       FIELD_PREP(OVPN_OPCODE_PEERID_MASK, peer_id);
+}
+
 #endif /* _NET_OVPN_OVPNPROTO_H_ */
diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h
index 9db7a9adebdb4..bd3cbcfc770d2 100644
--- a/drivers/net/ovpn/skb.h
+++ b/drivers/net/ovpn/skb.h
@@ -20,6 +20,11 @@
 
 struct ovpn_cb {
 	struct ovpn_peer *peer;
+	struct ovpn_crypto_key_slot *ks;
+	struct aead_request *req;
+	struct scatterlist *sg;
+	u8 *iv;
+	unsigned int payload_offset;
 };
 
 static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb)

From 419a608de27ac1aee2bb0d4929215b4473d12e2b Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:45 +0100
Subject: [PATCH 2551/2753] ovpn: store tunnel and transport statistics

Byte/packet counters for in-tunnel and transport streams
are now initialized and updated as needed.

To be exported via netlink.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/Makefile |  1 +
 drivers/net/ovpn/io.c     | 12 +++++++++-
 drivers/net/ovpn/peer.c   |  2 ++
 drivers/net/ovpn/peer.h   |  5 +++++
 drivers/net/ovpn/stats.c  | 21 +++++++++++++++++
 drivers/net/ovpn/stats.h  | 47 +++++++++++++++++++++++++++++++++++++++
 6 files changed, 87 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ovpn/stats.c
 create mode 100644 drivers/net/ovpn/stats.h

diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 38c9fdca0e2e8..04c3345807c5d 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -17,4 +17,5 @@ ovpn-y += netlink-gen.o
 ovpn-y += peer.o
 ovpn-y += pktid.o
 ovpn-y += socket.o
+ovpn-y += stats.o
 ovpn-y += udp.o
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index f8113f160148c..a5bd21fb824f6 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -12,6 +12,7 @@
 #include <linux/skbuff.h>
 #include <net/gro_cells.h>
 #include <net/gso.h>
+#include <net/ip.h>
 
 #include "ovpnpriv.h"
 #include "peer.h"
@@ -55,9 +56,11 @@ static void ovpn_netdev_write(struct ovpn_peer *peer, struct sk_buff *skb)
 	/* cause packet to be "received" by the interface */
 	pkt_len = skb->len;
 	ret = gro_cells_receive(&peer->ovpn->gro_cells, skb);
-	if (likely(ret == NET_RX_SUCCESS))
+	if (likely(ret == NET_RX_SUCCESS)) {
 		/* update RX stats with the size of decrypted packet */
+		ovpn_peer_stats_increment_rx(&peer->vpn_stats, pkt_len);
 		dev_sw_netstats_rx_add(peer->ovpn->dev, pkt_len);
+	}
 }
 
 void ovpn_decrypt_post(void *data, int ret)
@@ -158,6 +161,8 @@ void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb)
 	struct ovpn_crypto_key_slot *ks;
 	u8 key_id;
 
+	ovpn_peer_stats_increment_rx(&peer->link_stats, skb->len);
+
 	/* get the key slot matching the key ID in the received packet */
 	key_id = ovpn_key_id_from_skb(skb);
 	ks = ovpn_crypto_key_id_to_slot(&peer->crypto, key_id);
@@ -181,6 +186,7 @@ void ovpn_encrypt_post(void *data, int ret)
 	struct sk_buff *skb = data;
 	struct ovpn_socket *sock;
 	struct ovpn_peer *peer;
+	unsigned int orig_len;
 
 	/* encryption is happening asynchronously. This function will be
 	 * called later by the crypto callback with a proper return value
@@ -206,6 +212,7 @@ void ovpn_encrypt_post(void *data, int ret)
 		goto err;
 
 	skb_mark_not_on_list(skb);
+	orig_len = skb->len;
 
 	rcu_read_lock();
 	sock = rcu_dereference(peer->sock);
@@ -220,6 +227,8 @@ void ovpn_encrypt_post(void *data, int ret)
 		/* no transport configured yet */
 		goto err_unlock;
 	}
+
+	ovpn_peer_stats_increment_tx(&peer->link_stats, orig_len);
 	/* skb passed down the stack - don't free it */
 	skb = NULL;
 err_unlock:
@@ -334,6 +343,7 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev)
 		goto drop;
 	}
 
+	ovpn_peer_stats_increment_tx(&peer->vpn_stats, skb->len);
 	ovpn_send(ovpn, skb_list.next, peer);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 23eaab1b465b8..0fe5333c6b810 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -61,6 +61,8 @@ struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
 	ovpn_crypto_state_init(&peer->crypto);
 	spin_lock_init(&peer->lock);
 	kref_init(&peer->refcount);
+	ovpn_peer_stats_init(&peer->vpn_stats);
+	ovpn_peer_stats_init(&peer->link_stats);
 
 	ret = dst_cache_init(&peer->dst_cache, GFP_KERNEL);
 	if (ret < 0) {
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index a9113a969f94d..2453d39ce327c 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -14,6 +14,7 @@
 
 #include "crypto.h"
 #include "socket.h"
+#include "stats.h"
 
 /**
  * struct ovpn_peer - the main remote peer object
@@ -27,6 +28,8 @@
  * @crypto: the crypto configuration (ciphers, keys, etc..)
  * @dst_cache: cache for dst_entry used to send to peer
  * @bind: remote peer binding
+ * @vpn_stats: per-peer in-VPN TX/RX stats
+ * @link_stats: per-peer link/transport TX/RX stats
  * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
  * @lock: protects binding to peer (bind)
  * @refcount: reference counter
@@ -45,6 +48,8 @@ struct ovpn_peer {
 	struct ovpn_crypto_state crypto;
 	struct dst_cache dst_cache;
 	struct ovpn_bind __rcu *bind;
+	struct ovpn_peer_stats vpn_stats;
+	struct ovpn_peer_stats link_stats;
 	enum ovpn_del_peer_reason delete_reason;
 	spinlock_t lock; /* protects bind */
 	struct kref refcount;
diff --git a/drivers/net/ovpn/stats.c b/drivers/net/ovpn/stats.c
new file mode 100644
index 0000000000000..d637143473bb9
--- /dev/null
+++ b/drivers/net/ovpn/stats.c
@@ -0,0 +1,21 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/atomic.h>
+
+#include "stats.h"
+
+void ovpn_peer_stats_init(struct ovpn_peer_stats *ps)
+{
+	atomic64_set(&ps->rx.bytes, 0);
+	atomic64_set(&ps->rx.packets, 0);
+
+	atomic64_set(&ps->tx.bytes, 0);
+	atomic64_set(&ps->tx.packets, 0);
+}
diff --git a/drivers/net/ovpn/stats.h b/drivers/net/ovpn/stats.h
new file mode 100644
index 0000000000000..53433d8b6c331
--- /dev/null
+++ b/drivers/net/ovpn/stats.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	James Yonan <james@openvpn.net>
+ *		Antonio Quartulli <antonio@openvpn.net>
+ *		Lev Stipakov <lev@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_OVPNSTATS_H_
+#define _NET_OVPN_OVPNSTATS_H_
+
+/* one stat */
+struct ovpn_peer_stat {
+	atomic64_t bytes;
+	atomic64_t packets;
+};
+
+/* rx and tx stats combined */
+struct ovpn_peer_stats {
+	struct ovpn_peer_stat rx;
+	struct ovpn_peer_stat tx;
+};
+
+void ovpn_peer_stats_init(struct ovpn_peer_stats *ps);
+
+static inline void ovpn_peer_stats_increment(struct ovpn_peer_stat *stat,
+					     const unsigned int n)
+{
+	atomic64_add(n, &stat->bytes);
+	atomic64_inc(&stat->packets);
+}
+
+static inline void ovpn_peer_stats_increment_rx(struct ovpn_peer_stats *stats,
+						const unsigned int n)
+{
+	ovpn_peer_stats_increment(&stats->rx, n);
+}
+
+static inline void ovpn_peer_stats_increment_tx(struct ovpn_peer_stats *stats,
+						const unsigned int n)
+{
+	ovpn_peer_stats_increment(&stats->tx, n);
+}
+
+#endif /* _NET_OVPN_OVPNSTATS_H_ */

From 7fb565852dd3439eb33e4cc594d5087dd91874c0 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:46 +0100
Subject: [PATCH 2552/2753] ovpn: implement TCP transport

With this change ovpn is allowed to communicate to peers also via TCP.
Parsing of incoming messages is implemented through the strparser API.

Note that ovpn redefines sk_prot and sk_socket->ops for the TCP socket
used to communicate with the peer.
For this reason it needs to access inet6_stream_ops, which is declared
as extern in the IPv6 module, but it is not fully exported.

Therefore this patch is also adding EXPORT_SYMBOL_GPL(inet6_stream_ops)
to net/ipv6/af_inet6.c.

Moreover export tcp_release_cb by means of EXPORT_SYMBOL instead of
EXPORT_IPV6_MOD, so that other modules can use it, even if IPV6 is
not compiled in.

Cc: David Ahern <dsahern@kernel.org>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/Kconfig         |   1 +
 drivers/net/ovpn/Makefile   |   1 +
 drivers/net/ovpn/io.c       |   4 +
 drivers/net/ovpn/main.c     |   3 +
 drivers/net/ovpn/ovpnpriv.h |   1 +
 drivers/net/ovpn/peer.h     |  35 +++
 drivers/net/ovpn/socket.c   |  44 ++-
 drivers/net/ovpn/socket.h   |   8 +-
 drivers/net/ovpn/tcp.c      | 588 ++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/tcp.h      |  36 +++
 net/ipv6/af_inet6.c         |   1 +
 11 files changed, 711 insertions(+), 11 deletions(-)
 create mode 100644 drivers/net/ovpn/tcp.c
 create mode 100644 drivers/net/ovpn/tcp.h

diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 2cc91b1348725..c5ba841046f1f 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -125,6 +125,7 @@ config OVPN
 	select CRYPTO_AES
 	select CRYPTO_GCM
 	select CRYPTO_CHACHA20POLY1305
+	select STREAM_PARSER
 	help
 	  This module enhances the performance of the OpenVPN userspace software
 	  by offloading the data channel processing to kernelspace.
diff --git a/drivers/net/ovpn/Makefile b/drivers/net/ovpn/Makefile
index 04c3345807c5d..229be66167e1f 100644
--- a/drivers/net/ovpn/Makefile
+++ b/drivers/net/ovpn/Makefile
@@ -18,4 +18,5 @@ ovpn-y += peer.o
 ovpn-y += pktid.o
 ovpn-y += socket.o
 ovpn-y += stats.o
+ovpn-y += tcp.o
 ovpn-y += udp.o
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index a5bd21fb824f6..801cdbff40952 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -22,6 +22,7 @@
 #include "crypto_aead.h"
 #include "netlink.h"
 #include "proto.h"
+#include "tcp.h"
 #include "udp.h"
 #include "skb.h"
 #include "socket.h"
@@ -223,6 +224,9 @@ void ovpn_encrypt_post(void *data, int ret)
 	case IPPROTO_UDP:
 		ovpn_udp_send_skb(peer, sock->sock, skb);
 		break;
+	case IPPROTO_TCP:
+		ovpn_tcp_send_skb(peer, sock->sock, skb);
+		break;
 	default:
 		/* no transport configured yet */
 		goto err_unlock;
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index f6219b05485f0..948c36129914c 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -22,6 +22,7 @@
 #include "io.h"
 #include "peer.h"
 #include "proto.h"
+#include "tcp.h"
 #include "udp.h"
 
 static int ovpn_net_init(struct net_device *dev)
@@ -229,6 +230,8 @@ static int __init ovpn_init(void)
 		goto unreg_rtnl;
 	}
 
+	ovpn_tcp_init();
+
 	return 0;
 
 unreg_rtnl:
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index 9d0640e9c71e7..2e3f4baf305f0 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -10,6 +10,7 @@
 #ifndef _NET_OVPN_OVPNSTRUCT_H_
 #define _NET_OVPN_OVPNSTRUCT_H_
 
+#include <linux/workqueue.h>
 #include <net/gro_cells.h>
 #include <uapi/linux/if_link.h>
 #include <uapi/linux/ovpn.h>
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index 2453d39ce327c..5ef00ba6523d7 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -11,6 +11,7 @@
 #define _NET_OVPN_OVPNPEER_H_
 
 #include <net/dst_cache.h>
+#include <net/strparser.h>
 
 #include "crypto.h"
 #include "socket.h"
@@ -25,6 +26,18 @@
  * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
  * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
  * @sock: the socket being used to talk to this peer
+ * @tcp: keeps track of TCP specific state
+ * @tcp.strp: stream parser context (TCP only)
+ * @tcp.user_queue: received packets that have to go to userspace (TCP only)
+ * @tcp.out_queue: packets on hold while socket is taken by user (TCP only)
+ * @tcp.tx_in_progress: true if TX is already ongoing (TCP only)
+ * @tcp.out_msg.skb: packet scheduled for sending (TCP only)
+ * @tcp.out_msg.offset: offset where next send should start (TCP only)
+ * @tcp.out_msg.len: remaining data to send within packet (TCP only)
+ * @tcp.sk_cb.sk_data_ready: pointer to original cb (TCP only)
+ * @tcp.sk_cb.sk_write_space: pointer to original cb (TCP only)
+ * @tcp.sk_cb.prot: pointer to original prot object (TCP only)
+ * @tcp.sk_cb.ops: pointer to the original prot_ops object (TCP only)
  * @crypto: the crypto configuration (ciphers, keys, etc..)
  * @dst_cache: cache for dst_entry used to send to peer
  * @bind: remote peer binding
@@ -45,6 +58,28 @@ struct ovpn_peer {
 		struct in6_addr ipv6;
 	} vpn_addrs;
 	struct ovpn_socket __rcu *sock;
+
+	struct {
+		struct strparser strp;
+		struct sk_buff_head user_queue;
+		struct sk_buff_head out_queue;
+		bool tx_in_progress;
+
+		struct {
+			struct sk_buff *skb;
+			int offset;
+			int len;
+		} out_msg;
+
+		struct {
+			void (*sk_data_ready)(struct sock *sk);
+			void (*sk_write_space)(struct sock *sk);
+			struct proto *prot;
+			const struct proto_ops *ops;
+		} sk_cb;
+
+		struct work_struct defer_del_work;
+	} tcp;
 	struct ovpn_crypto_state crypto;
 	struct dst_cache dst_cache;
 	struct ovpn_bind __rcu *bind;
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index 6de1e8c85a3d3..be20c500f373f 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -16,6 +16,7 @@
 #include "io.h"
 #include "peer.h"
 #include "socket.h"
+#include "tcp.h"
 #include "udp.h"
 
 static void ovpn_socket_release_kref(struct kref *kref)
@@ -23,12 +24,10 @@ static void ovpn_socket_release_kref(struct kref *kref)
 	struct ovpn_socket *sock = container_of(kref, struct ovpn_socket,
 						refcount);
 
-	if (sock->sock->sk->sk_protocol == IPPROTO_UDP) {
+	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
 		ovpn_udp_socket_detach(sock);
-		netdev_put(sock->ovpn->dev, &sock->dev_tracker);
-	}
-
-	kfree_rcu(sock, rcu);
+	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
+		ovpn_tcp_socket_detach(sock);
 }
 
 /**
@@ -38,10 +37,12 @@ static void ovpn_socket_release_kref(struct kref *kref)
  *
  * This function is only used internally. Users willing to release
  * references to the ovpn_socket should use ovpn_socket_release()
+ *
+ * Return: true if the socket was released, false otherwise
  */
-static void ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
+static bool ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
 {
-	kref_put(&sock->refcount, ovpn_socket_release_kref);
+	return kref_put(&sock->refcount, ovpn_socket_release_kref);
 }
 
 /**
@@ -65,6 +66,7 @@ static void ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
 void ovpn_socket_release(struct ovpn_peer *peer)
 {
 	struct ovpn_socket *sock;
+	bool released;
 
 	might_sleep();
 
@@ -94,11 +96,26 @@ void ovpn_socket_release(struct ovpn_peer *peer)
 	 * detached before it can be picked by a concurrent reader.
 	 */
 	lock_sock(sock->sock->sk);
-	ovpn_socket_put(peer, sock);
+	released = ovpn_socket_put(peer, sock);
 	release_sock(sock->sock->sk);
 
 	/* align all readers with sk_user_data being NULL */
 	synchronize_rcu();
+
+	/* following cleanup should happen with lock released */
+	if (released) {
+		if (sock->sock->sk->sk_protocol == IPPROTO_UDP) {
+			netdev_put(sock->ovpn->dev, &sock->dev_tracker);
+		} else if (sock->sock->sk->sk_protocol == IPPROTO_TCP) {
+			/* wait for TCP jobs to terminate */
+			ovpn_tcp_socket_wait_finish(sock);
+			ovpn_peer_put(sock->peer);
+		}
+		/* we can call plain kfree() because we already waited one RCU
+		 * period due to synchronize_rcu()
+		 */
+		kfree(sock);
+	}
 }
 
 static bool ovpn_socket_hold(struct ovpn_socket *sock)
@@ -110,6 +127,8 @@ static int ovpn_socket_attach(struct ovpn_socket *sock, struct ovpn_peer *peer)
 {
 	if (sock->sock->sk->sk_protocol == IPPROTO_UDP)
 		return ovpn_udp_socket_attach(sock, peer->ovpn);
+	else if (sock->sock->sk->sk_protocol == IPPROTO_TCP)
+		return ovpn_tcp_socket_attach(sock, peer);
 
 	return -EOPNOTSUPP;
 }
@@ -202,7 +221,14 @@ struct ovpn_socket *ovpn_socket_new(struct socket *sock, struct ovpn_peer *peer)
 		goto sock_release;
 	}
 
-	if (sock->sk->sk_protocol == IPPROTO_UDP) {
+	/* TCP sockets are per-peer, therefore they are linked to their unique
+	 * peer
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP) {
+		INIT_WORK(&ovpn_sock->tcp_tx_work, ovpn_tcp_tx_work);
+		ovpn_sock->peer = peer;
+		ovpn_peer_hold(peer);
+	} else if (sock->sk->sk_protocol == IPPROTO_UDP) {
 		/* in UDP we only link the ovpn instance since the socket is
 		 * shared among multiple peers
 		 */
diff --git a/drivers/net/ovpn/socket.h b/drivers/net/ovpn/socket.h
index c1697f4616d47..00d856b1a5d88 100644
--- a/drivers/net/ovpn/socket.h
+++ b/drivers/net/ovpn/socket.h
@@ -21,9 +21,11 @@ struct ovpn_peer;
  * struct ovpn_socket - a kernel socket referenced in the ovpn code
  * @ovpn: ovpn instance owning this socket (UDP only)
  * @dev_tracker: reference tracker for associated dev (UDP only)
+ * @peer: unique peer transmitting over this socket (TCP only)
  * @sock: the low level sock object
  * @refcount: amount of contexts currently referencing this object
- * @rcu: member used to schedule RCU destructor callback
+ * @work: member used to schedule release routine (it may block)
+ * @tcp_tx_work: work for deferring outgoing packet processing (TCP only)
  */
 struct ovpn_socket {
 	union {
@@ -31,11 +33,13 @@ struct ovpn_socket {
 			struct ovpn_priv *ovpn;
 			netdevice_tracker dev_tracker;
 		};
+		struct ovpn_peer *peer;
 	};
 
 	struct socket *sock;
 	struct kref refcount;
-	struct rcu_head rcu;
+	struct work_struct work;
+	struct work_struct tcp_tx_work;
 };
 
 struct ovpn_socket *ovpn_socket_new(struct socket *sock,
diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
new file mode 100644
index 0000000000000..a5bfd06bc9499
--- /dev/null
+++ b/drivers/net/ovpn/tcp.c
@@ -0,0 +1,588 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <linux/skbuff.h>
+#include <net/hotdata.h>
+#include <net/inet_common.h>
+#include <net/ipv6.h>
+#include <net/tcp.h>
+#include <net/transp_v6.h>
+#include <net/route.h>
+#include <trace/events/sock.h>
+
+#include "ovpnpriv.h"
+#include "main.h"
+#include "io.h"
+#include "peer.h"
+#include "proto.h"
+#include "skb.h"
+#include "tcp.h"
+
+#define OVPN_TCP_DEPTH_NESTING	2
+#if OVPN_TCP_DEPTH_NESTING == SINGLE_DEPTH_NESTING
+#error "OVPN TCP requires its own lockdep subclass"
+#endif
+
+static struct proto ovpn_tcp_prot __ro_after_init;
+static struct proto_ops ovpn_tcp_ops __ro_after_init;
+static struct proto ovpn_tcp6_prot __ro_after_init;
+static struct proto_ops ovpn_tcp6_ops __ro_after_init;
+
+static int ovpn_tcp_parse(struct strparser *strp, struct sk_buff *skb)
+{
+	struct strp_msg *rxm = strp_msg(skb);
+	__be16 blen;
+	u16 len;
+	int err;
+
+	/* when packets are written to the TCP stream, they are prepended with
+	 * two bytes indicating the actual packet size.
+	 * Parse accordingly and return the actual size (including the size
+	 * header)
+	 */
+
+	if (skb->len < rxm->offset + 2)
+		return 0;
+
+	err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen));
+	if (err < 0)
+		return err;
+
+	len = be16_to_cpu(blen);
+	if (len < 2)
+		return -EINVAL;
+
+	return len + 2;
+}
+
+/* queue skb for sending to userspace via recvmsg on the socket */
+static void ovpn_tcp_to_userspace(struct ovpn_peer *peer, struct sock *sk,
+				  struct sk_buff *skb)
+{
+	skb_set_owner_r(skb, sk);
+	memset(skb->cb, 0, sizeof(skb->cb));
+	skb_queue_tail(&peer->tcp.user_queue, skb);
+	peer->tcp.sk_cb.sk_data_ready(sk);
+}
+
+static void ovpn_tcp_rcv(struct strparser *strp, struct sk_buff *skb)
+{
+	struct ovpn_peer *peer = container_of(strp, struct ovpn_peer, tcp.strp);
+	struct strp_msg *msg = strp_msg(skb);
+	size_t pkt_len = msg->full_len - 2;
+	size_t off = msg->offset + 2;
+	u8 opcode;
+
+	/* ensure skb->data points to the beginning of the openvpn packet */
+	if (!pskb_pull(skb, off)) {
+		net_warn_ratelimited("%s: packet too small for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* strparser does not trim the skb for us, therefore we do it now */
+	if (pskb_trim(skb, pkt_len) != 0) {
+		net_warn_ratelimited("%s: trimming skb failed for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* we need the first byte of data to be accessible
+	 * to extract the opcode and the key ID later on
+	 */
+	if (!pskb_may_pull(skb, OVPN_OPCODE_SIZE)) {
+		net_warn_ratelimited("%s: packet too small to fetch opcode for peer %u\n",
+				     netdev_name(peer->ovpn->dev), peer->id);
+		goto err;
+	}
+
+	/* DATA_V2 packets are handled in kernel, the rest goes to user space */
+	opcode = ovpn_opcode_from_skb(skb, 0);
+	if (unlikely(opcode != OVPN_DATA_V2)) {
+		if (opcode == OVPN_DATA_V1) {
+			net_warn_ratelimited("%s: DATA_V1 detected on the TCP stream\n",
+					     netdev_name(peer->ovpn->dev));
+			goto err;
+		}
+
+		/* The packet size header must be there when sending the packet
+		 * to userspace, therefore we put it back
+		 */
+		skb_push(skb, 2);
+		ovpn_tcp_to_userspace(peer, strp->sk, skb);
+		return;
+	}
+
+	/* hold reference to peer as required by ovpn_recv().
+	 *
+	 * NOTE: in this context we should already be holding a reference to
+	 * this peer, therefore ovpn_peer_hold() is not expected to fail
+	 */
+	if (WARN_ON(!ovpn_peer_hold(peer)))
+		goto err;
+
+	ovpn_recv(peer, skb);
+	return;
+err:
+	dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+	kfree_skb(skb);
+	ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR);
+}
+
+static int ovpn_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+			    int flags, int *addr_len)
+{
+	int err = 0, off, copied = 0, ret;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) {
+		rcu_read_unlock();
+		return -EBADF;
+	}
+	peer = sock->peer;
+	rcu_read_unlock();
+
+	skb = __skb_recv_datagram(sk, &peer->tcp.user_queue, flags, &off, &err);
+	if (!skb) {
+		if (err == -EAGAIN && sk->sk_shutdown & RCV_SHUTDOWN) {
+			ret = 0;
+			goto out;
+		}
+		ret = err;
+		goto out;
+	}
+
+	copied = len;
+	if (copied > skb->len)
+		copied = skb->len;
+	else if (copied < skb->len)
+		msg->msg_flags |= MSG_TRUNC;
+
+	err = skb_copy_datagram_msg(skb, 0, msg, copied);
+	if (unlikely(err)) {
+		kfree_skb(skb);
+		ret = err;
+		goto out;
+	}
+
+	if (flags & MSG_TRUNC)
+		copied = skb->len;
+	kfree_skb(skb);
+	ret = copied;
+out:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock)
+{
+	struct ovpn_peer *peer = ovpn_sock->peer;
+	struct socket *sock = ovpn_sock->sock;
+
+	strp_stop(&peer->tcp.strp);
+	skb_queue_purge(&peer->tcp.user_queue);
+
+	/* restore CBs that were saved in ovpn_sock_set_tcp_cb() */
+	sock->sk->sk_data_ready = peer->tcp.sk_cb.sk_data_ready;
+	sock->sk->sk_write_space = peer->tcp.sk_cb.sk_write_space;
+	sock->sk->sk_prot = peer->tcp.sk_cb.prot;
+	sock->sk->sk_socket->ops = peer->tcp.sk_cb.ops;
+
+	rcu_assign_sk_user_data(sock->sk, NULL);
+}
+
+void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock)
+{
+	struct ovpn_peer *peer = sock->peer;
+
+	/* NOTE: we don't wait for peer->tcp.defer_del_work to finish:
+	 * either the worker is not running or this function
+	 * was invoked by that worker.
+	 */
+
+	cancel_work_sync(&sock->tcp_tx_work);
+	strp_done(&peer->tcp.strp);
+
+	skb_queue_purge(&peer->tcp.out_queue);
+	kfree_skb(peer->tcp.out_msg.skb);
+	peer->tcp.out_msg.skb = NULL;
+}
+
+static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk)
+{
+	struct sk_buff *skb = peer->tcp.out_msg.skb;
+
+	if (!skb)
+		return;
+
+	if (peer->tcp.tx_in_progress)
+		return;
+
+	peer->tcp.tx_in_progress = true;
+
+	do {
+		int ret = skb_send_sock_locked(sk, skb,
+					       peer->tcp.out_msg.offset,
+					       peer->tcp.out_msg.len);
+		if (unlikely(ret < 0)) {
+			if (ret == -EAGAIN)
+				goto out;
+
+			net_warn_ratelimited("%s: TCP error to peer %u: %d\n",
+					     netdev_name(peer->ovpn->dev),
+					     peer->id, ret);
+
+			/* in case of TCP error we can't recover the VPN
+			 * stream therefore we abort the connection
+			 */
+			ovpn_peer_hold(peer);
+			schedule_work(&peer->tcp.defer_del_work);
+
+			/* we bail out immediately and keep tx_in_progress set
+			 * to true. This way we prevent more TX attempts
+			 * which would lead to more invocations of
+			 * schedule_work()
+			 */
+			return;
+		}
+
+		peer->tcp.out_msg.len -= ret;
+		peer->tcp.out_msg.offset += ret;
+	} while (peer->tcp.out_msg.len > 0);
+
+	if (!peer->tcp.out_msg.len) {
+		preempt_disable();
+		dev_sw_netstats_tx_add(peer->ovpn->dev, 1, skb->len);
+		preempt_enable();
+	}
+
+	kfree_skb(peer->tcp.out_msg.skb);
+	peer->tcp.out_msg.skb = NULL;
+	peer->tcp.out_msg.len = 0;
+	peer->tcp.out_msg.offset = 0;
+
+out:
+	peer->tcp.tx_in_progress = false;
+}
+
+void ovpn_tcp_tx_work(struct work_struct *work)
+{
+	struct ovpn_socket *sock;
+
+	sock = container_of(work, struct ovpn_socket, tcp_tx_work);
+
+	lock_sock(sock->sock->sk);
+	if (sock->peer)
+		ovpn_tcp_send_sock(sock->peer, sock->sock->sk);
+	release_sock(sock->sock->sk);
+}
+
+static void ovpn_tcp_send_sock_skb(struct ovpn_peer *peer, struct sock *sk,
+				   struct sk_buff *skb)
+{
+	if (peer->tcp.out_msg.skb)
+		ovpn_tcp_send_sock(peer, sk);
+
+	if (peer->tcp.out_msg.skb) {
+		dev_core_stats_tx_dropped_inc(peer->ovpn->dev);
+		kfree_skb(skb);
+		return;
+	}
+
+	peer->tcp.out_msg.skb = skb;
+	peer->tcp.out_msg.len = skb->len;
+	peer->tcp.out_msg.offset = 0;
+	ovpn_tcp_send_sock(peer, sk);
+}
+
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock,
+		       struct sk_buff *skb)
+{
+	u16 len = skb->len;
+
+	*(__be16 *)__skb_push(skb, sizeof(u16)) = htons(len);
+
+	spin_lock_nested(&sock->sk->sk_lock.slock, OVPN_TCP_DEPTH_NESTING);
+	if (sock_owned_by_user(sock->sk)) {
+		if (skb_queue_len(&peer->tcp.out_queue) >=
+		    READ_ONCE(net_hotdata.max_backlog)) {
+			dev_core_stats_tx_dropped_inc(peer->ovpn->dev);
+			kfree_skb(skb);
+			goto unlock;
+		}
+		__skb_queue_tail(&peer->tcp.out_queue, skb);
+	} else {
+		ovpn_tcp_send_sock_skb(peer, sock->sk, skb);
+	}
+unlock:
+	spin_unlock(&sock->sk->sk_lock.slock);
+}
+
+static void ovpn_tcp_release(struct sock *sk)
+{
+	struct sk_buff_head queue;
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock) {
+		rcu_read_unlock();
+		return;
+	}
+
+	peer = sock->peer;
+
+	/* during initialization this function is called before
+	 * assigning sock->peer
+	 */
+	if (unlikely(!peer || !ovpn_peer_hold(peer))) {
+		rcu_read_unlock();
+		return;
+	}
+	rcu_read_unlock();
+
+	__skb_queue_head_init(&queue);
+	skb_queue_splice_init(&peer->tcp.out_queue, &queue);
+
+	while ((skb = __skb_dequeue(&queue)))
+		ovpn_tcp_send_sock_skb(peer, sk, skb);
+
+	peer->tcp.sk_cb.prot->release_cb(sk);
+	ovpn_peer_put(peer);
+}
+
+static int ovpn_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+{
+	struct ovpn_socket *sock;
+	int ret, linear = PAGE_SIZE;
+	struct ovpn_peer *peer;
+	struct sk_buff *skb;
+
+	lock_sock(sk);
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (unlikely(!sock || !sock->peer || !ovpn_peer_hold(sock->peer))) {
+		rcu_read_unlock();
+		release_sock(sk);
+		return -EIO;
+	}
+	rcu_read_unlock();
+	peer = sock->peer;
+
+	if (msg->msg_flags & ~MSG_DONTWAIT) {
+		ret = -EOPNOTSUPP;
+		goto peer_free;
+	}
+
+	if (peer->tcp.out_msg.skb) {
+		ret = -EAGAIN;
+		goto peer_free;
+	}
+
+	if (size < linear)
+		linear = size;
+
+	skb = sock_alloc_send_pskb(sk, linear, size - linear,
+				   msg->msg_flags & MSG_DONTWAIT, &ret, 0);
+	if (!skb) {
+		net_err_ratelimited("%s: skb alloc failed: %d\n",
+				    netdev_name(peer->ovpn->dev), ret);
+		goto peer_free;
+	}
+
+	skb_put(skb, linear);
+	skb->len = size;
+	skb->data_len = size - linear;
+
+	ret = skb_copy_datagram_from_iter(skb, 0, &msg->msg_iter, size);
+	if (ret) {
+		kfree_skb(skb);
+		net_err_ratelimited("%s: skb copy from iter failed: %d\n",
+				    netdev_name(peer->ovpn->dev), ret);
+		goto peer_free;
+	}
+
+	ovpn_tcp_send_sock_skb(peer, sk, skb);
+	ret = size;
+peer_free:
+	release_sock(sk);
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+static void ovpn_tcp_data_ready(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+
+	trace_sk_data_ready(sk);
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (likely(sock && sock->peer))
+		strp_data_ready(&sock->peer->tcp.strp);
+	rcu_read_unlock();
+}
+
+static void ovpn_tcp_write_space(struct sock *sk)
+{
+	struct ovpn_socket *sock;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (likely(sock && sock->peer)) {
+		schedule_work(&sock->tcp_tx_work);
+		sock->peer->tcp.sk_cb.sk_write_space(sk);
+	}
+	rcu_read_unlock();
+}
+
+static void ovpn_tcp_build_protos(struct proto *new_prot,
+				  struct proto_ops *new_ops,
+				  const struct proto *orig_prot,
+				  const struct proto_ops *orig_ops);
+
+static void ovpn_tcp_peer_del_work(struct work_struct *work)
+{
+	struct ovpn_peer *peer = container_of(work, struct ovpn_peer,
+					      tcp.defer_del_work);
+
+	ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_TRANSPORT_ERROR);
+	ovpn_peer_put(peer);
+}
+
+/* Set TCP encapsulation callbacks */
+int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_peer *peer)
+{
+	struct socket *sock = ovpn_sock->sock;
+	struct strp_callbacks cb = {
+		.rcv_msg = ovpn_tcp_rcv,
+		.parse_msg = ovpn_tcp_parse,
+	};
+	int ret;
+
+	/* make sure no pre-existing encapsulation handler exists */
+	if (sock->sk->sk_user_data)
+		return -EBUSY;
+
+	/* only a fully connected socket is expected. Connection should be
+	 * handled in userspace
+	 */
+	if (sock->sk->sk_state != TCP_ESTABLISHED) {
+		net_err_ratelimited("%s: provided TCP socket is not in ESTABLISHED state: %d\n",
+				    netdev_name(peer->ovpn->dev),
+				    sock->sk->sk_state);
+		return -EINVAL;
+	}
+
+	ret = strp_init(&peer->tcp.strp, sock->sk, &cb);
+	if (ret < 0) {
+		DEBUG_NET_WARN_ON_ONCE(1);
+		return ret;
+	}
+
+	INIT_WORK(&peer->tcp.defer_del_work, ovpn_tcp_peer_del_work);
+
+	__sk_dst_reset(sock->sk);
+	skb_queue_head_init(&peer->tcp.user_queue);
+	skb_queue_head_init(&peer->tcp.out_queue);
+
+	/* save current CBs so that they can be restored upon socket release */
+	peer->tcp.sk_cb.sk_data_ready = sock->sk->sk_data_ready;
+	peer->tcp.sk_cb.sk_write_space = sock->sk->sk_write_space;
+	peer->tcp.sk_cb.prot = sock->sk->sk_prot;
+	peer->tcp.sk_cb.ops = sock->sk->sk_socket->ops;
+
+	/* assign our static CBs and prot/ops */
+	sock->sk->sk_data_ready = ovpn_tcp_data_ready;
+	sock->sk->sk_write_space = ovpn_tcp_write_space;
+
+	if (sock->sk->sk_family == AF_INET) {
+		sock->sk->sk_prot = &ovpn_tcp_prot;
+		sock->sk->sk_socket->ops = &ovpn_tcp_ops;
+	} else {
+		sock->sk->sk_prot = &ovpn_tcp6_prot;
+		sock->sk->sk_socket->ops = &ovpn_tcp6_ops;
+	}
+
+	/* avoid using task_frag */
+	sock->sk->sk_allocation = GFP_ATOMIC;
+	sock->sk->sk_use_task_frag = false;
+
+	/* enqueue the RX worker */
+	strp_check_rcv(&peer->tcp.strp);
+
+	return 0;
+}
+
+static void ovpn_tcp_close(struct sock *sk, long timeout)
+{
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+
+	rcu_read_lock();
+	sock = rcu_dereference_sk_user_data(sk);
+	if (!sock || !sock->peer || !ovpn_peer_hold(sock->peer)) {
+		rcu_read_unlock();
+		return;
+	}
+	peer = sock->peer;
+	rcu_read_unlock();
+
+	ovpn_peer_del(sock->peer, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
+	peer->tcp.sk_cb.prot->close(sk, timeout);
+	ovpn_peer_put(peer);
+}
+
+static __poll_t ovpn_tcp_poll(struct file *file, struct socket *sock,
+			      poll_table *wait)
+{
+	__poll_t mask = datagram_poll(file, sock, wait);
+	struct ovpn_socket *ovpn_sock;
+
+	rcu_read_lock();
+	ovpn_sock = rcu_dereference_sk_user_data(sock->sk);
+	if (ovpn_sock && ovpn_sock->peer &&
+	    !skb_queue_empty(&ovpn_sock->peer->tcp.user_queue))
+		mask |= EPOLLIN | EPOLLRDNORM;
+	rcu_read_unlock();
+
+	return mask;
+}
+
+static void ovpn_tcp_build_protos(struct proto *new_prot,
+				  struct proto_ops *new_ops,
+				  const struct proto *orig_prot,
+				  const struct proto_ops *orig_ops)
+{
+	memcpy(new_prot, orig_prot, sizeof(*new_prot));
+	memcpy(new_ops, orig_ops, sizeof(*new_ops));
+	new_prot->recvmsg = ovpn_tcp_recvmsg;
+	new_prot->sendmsg = ovpn_tcp_sendmsg;
+	new_prot->close = ovpn_tcp_close;
+	new_prot->release_cb = ovpn_tcp_release;
+	new_ops->poll = ovpn_tcp_poll;
+}
+
+/* Initialize TCP static objects */
+void __init ovpn_tcp_init(void)
+{
+	ovpn_tcp_build_protos(&ovpn_tcp_prot, &ovpn_tcp_ops, &tcp_prot,
+			      &inet_stream_ops);
+
+#if IS_ENABLED(CONFIG_IPV6)
+	ovpn_tcp_build_protos(&ovpn_tcp6_prot, &ovpn_tcp6_ops, &tcpv6_prot,
+			      &inet6_stream_ops);
+#endif
+}
diff --git a/drivers/net/ovpn/tcp.h b/drivers/net/ovpn/tcp.h
new file mode 100644
index 0000000000000..10aefa834cf35
--- /dev/null
+++ b/drivers/net/ovpn/tcp.h
@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*  OpenVPN data channel offload
+ *
+ *  Copyright (C) 2019-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#ifndef _NET_OVPN_TCP_H_
+#define _NET_OVPN_TCP_H_
+
+#include <linux/net.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+
+#include "peer.h"
+#include "skb.h"
+#include "socket.h"
+
+void __init ovpn_tcp_init(void);
+
+int ovpn_tcp_socket_attach(struct ovpn_socket *ovpn_sock,
+			   struct ovpn_peer *peer);
+void ovpn_tcp_socket_detach(struct ovpn_socket *ovpn_sock);
+void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock);
+
+/* Prepare skb and enqueue it for sending to peer.
+ *
+ * Preparation consist in prepending the skb payload with its size.
+ * Required by the OpenVPN protocol in order to extract packets from
+ * the TCP stream on the receiver side.
+ */
+void ovpn_tcp_send_skb(struct ovpn_peer *peer, struct socket *sock, struct sk_buff *skb);
+void ovpn_tcp_tx_work(struct work_struct *work);
+
+#endif /* _NET_OVPN_TCP_H_ */
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index f60ec8b0f8ea4..3e812187e125c 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -715,6 +715,7 @@ const struct proto_ops inet6_stream_ops = {
 #endif
 	.set_rcvlowat	   = tcp_set_rcvlowat,
 };
+EXPORT_SYMBOL_GPL(inet6_stream_ops);
 
 const struct proto_ops inet6_dgram_ops = {
 	.family		   = PF_INET6,

From 56bd5cc69655d8dd4423bf0c11ec228f36ce74d5 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:47 +0100
Subject: [PATCH 2553/2753] skb: implement skb_send_sock_locked_with_flags()

When sending an skb over a socket using skb_send_sock_locked(),
it is currently not possible to specify any flag to be set in
msghdr->msg_flags.

However, we may want to pass flags the user may have specified,
like MSG_NOSIGNAL.

Extend __skb_send_sock() with a new argument 'flags' and add a
new interface named skb_send_sock_locked_with_flags().

Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Simon Horman <horms@kernel.org>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/skbuff.h |  2 ++
 net/core/skbuff.c      | 18 +++++++++++++-----
 2 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 65e7cefa2bc60..e42c956a7dbee 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -4145,6 +4145,8 @@ int skb_splice_bits(struct sk_buff *skb, struct sock *sk, unsigned int offset,
 		    unsigned int flags);
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len);
+int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb,
+				    int offset, int len, int flags);
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len);
 void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to);
 unsigned int skb_zerocopy_headlen(const struct sk_buff *from);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 71581e9f2941d..61dc11850d8af 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -3228,7 +3228,7 @@ static int sendmsg_unlocked(struct sock *sk, struct msghdr *msg)
 
 typedef int (*sendmsg_func)(struct sock *sk, struct msghdr *msg);
 static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
-			   int len, sendmsg_func sendmsg)
+			   int len, sendmsg_func sendmsg, int flags)
 {
 	unsigned int orig_len = len;
 	struct sk_buff *head = skb;
@@ -3246,7 +3246,7 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 		kv.iov_base = skb->data + offset;
 		kv.iov_len = slen;
 		memset(&msg, 0, sizeof(msg));
-		msg.msg_flags = MSG_DONTWAIT;
+		msg.msg_flags = MSG_DONTWAIT | flags;
 
 		iov_iter_kvec(&msg.msg_iter, ITER_SOURCE, &kv, 1, slen);
 		ret = INDIRECT_CALL_2(sendmsg, sendmsg_locked,
@@ -3283,7 +3283,8 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 		while (slen) {
 			struct bio_vec bvec;
 			struct msghdr msg = {
-				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT,
+				.msg_flags = MSG_SPLICE_PAGES | MSG_DONTWAIT |
+					     flags,
 			};
 
 			bvec_set_page(&bvec, skb_frag_page(frag), slen,
@@ -3329,14 +3330,21 @@ static int __skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset,
 int skb_send_sock_locked(struct sock *sk, struct sk_buff *skb, int offset,
 			 int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, 0);
 }
 EXPORT_SYMBOL_GPL(skb_send_sock_locked);
 
+int skb_send_sock_locked_with_flags(struct sock *sk, struct sk_buff *skb,
+				    int offset, int len, int flags)
+{
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_locked, flags);
+}
+EXPORT_SYMBOL_GPL(skb_send_sock_locked_with_flags);
+
 /* Send skb data on a socket. Socket must be unlocked. */
 int skb_send_sock(struct sock *sk, struct sk_buff *skb, int offset, int len)
 {
-	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked);
+	return __skb_send_sock(sk, skb, offset, len, sendmsg_unlocked, 0);
 }
 
 /**

From f6ebae4a790134e8f93557ca7a60b12a59ee5ae9 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:48 +0100
Subject: [PATCH 2554/2753] ovpn: add support for MSG_NOSIGNAL in tcp_sendmsg

Userspace may want to pass the MSG_NOSIGNAL flag to
tcp_sendmsg() in order to avoid generating a SIGPIPE.

To pass this flag down the TCP stack a new skb sending API
accepting a flags argument is introduced.

Cc: Eric Dumazet <edumazet@google.com>
Cc: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/skb.h |  1 +
 drivers/net/ovpn/tcp.c | 12 ++++++++----
 2 files changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ovpn/skb.h b/drivers/net/ovpn/skb.h
index bd3cbcfc770d2..64430880f1dae 100644
--- a/drivers/net/ovpn/skb.h
+++ b/drivers/net/ovpn/skb.h
@@ -25,6 +25,7 @@ struct ovpn_cb {
 	struct scatterlist *sg;
 	u8 *iv;
 	unsigned int payload_offset;
+	bool nosignal;
 };
 
 static inline struct ovpn_cb *ovpn_skb_cb(struct sk_buff *skb)
diff --git a/drivers/net/ovpn/tcp.c b/drivers/net/ovpn/tcp.c
index a5bfd06bc9499..e05c9ba0e0f5f 100644
--- a/drivers/net/ovpn/tcp.c
+++ b/drivers/net/ovpn/tcp.c
@@ -220,6 +220,7 @@ void ovpn_tcp_socket_wait_finish(struct ovpn_socket *sock)
 static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk)
 {
 	struct sk_buff *skb = peer->tcp.out_msg.skb;
+	int ret, flags;
 
 	if (!skb)
 		return;
@@ -230,9 +231,11 @@ static void ovpn_tcp_send_sock(struct ovpn_peer *peer, struct sock *sk)
 	peer->tcp.tx_in_progress = true;
 
 	do {
-		int ret = skb_send_sock_locked(sk, skb,
-					       peer->tcp.out_msg.offset,
-					       peer->tcp.out_msg.len);
+		flags = ovpn_skb_cb(skb)->nosignal ? MSG_NOSIGNAL : 0;
+		ret = skb_send_sock_locked_with_flags(sk, skb,
+						      peer->tcp.out_msg.offset,
+						      peer->tcp.out_msg.len,
+						      flags);
 		if (unlikely(ret < 0)) {
 			if (ret == -EAGAIN)
 				goto out;
@@ -380,7 +383,7 @@ static int ovpn_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 	rcu_read_unlock();
 	peer = sock->peer;
 
-	if (msg->msg_flags & ~MSG_DONTWAIT) {
+	if (msg->msg_flags & ~(MSG_DONTWAIT | MSG_NOSIGNAL)) {
 		ret = -EOPNOTSUPP;
 		goto peer_free;
 	}
@@ -413,6 +416,7 @@ static int ovpn_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
 		goto peer_free;
 	}
 
+	ovpn_skb_cb(skb)->nosignal = msg->msg_flags & MSG_NOSIGNAL;
 	ovpn_tcp_send_sock_skb(peer, sk, skb);
 	ret = size;
 peer_free:

From 84322fb4d911898149b1331f1ebc9d77e107d17c Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:49 +0100
Subject: [PATCH 2555/2753] ovpn: implement multi-peer support

With this change an ovpn instance will be able to stay connected to
multiple remote endpoints.

This functionality is strictly required when running ovpn on an
OpenVPN server.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/main.c     |  64 +++++++++++-
 drivers/net/ovpn/ovpnpriv.h |  19 ++++
 drivers/net/ovpn/peer.c     | 189 ++++++++++++++++++++++++++++++++++--
 drivers/net/ovpn/peer.h     |  12 ++-
 drivers/net/ovpn/udp.c      |   4 +-
 5 files changed, 272 insertions(+), 16 deletions(-)

diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 948c36129914c..1b3d5b6c83999 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -25,11 +25,66 @@
 #include "tcp.h"
 #include "udp.h"
 
+static void ovpn_priv_free(struct net_device *net)
+{
+	struct ovpn_priv *ovpn = netdev_priv(net);
+
+	kfree(ovpn->peers);
+}
+
+static int ovpn_mp_alloc(struct ovpn_priv *ovpn)
+{
+	struct in_device *dev_v4;
+	int i;
+
+	if (ovpn->mode != OVPN_MODE_MP)
+		return 0;
+
+	dev_v4 = __in_dev_get_rtnl(ovpn->dev);
+	if (dev_v4) {
+		/* disable redirects as Linux gets confused by ovpn
+		 * handling same-LAN routing.
+		 * This happens because a multipeer interface is used as
+		 * relay point between hosts in the same subnet, while
+		 * in a classic LAN this would not be needed because the
+		 * two hosts would be able to talk directly.
+		 */
+		IN_DEV_CONF_SET(dev_v4, SEND_REDIRECTS, false);
+		IPV4_DEVCONF_ALL(dev_net(ovpn->dev), SEND_REDIRECTS) = false;
+	}
+
+	/* the peer container is fairly large, therefore we allocate it only in
+	 * MP mode
+	 */
+	ovpn->peers = kzalloc(sizeof(*ovpn->peers), GFP_KERNEL);
+	if (!ovpn->peers)
+		return -ENOMEM;
+
+	for (i = 0; i < ARRAY_SIZE(ovpn->peers->by_id); i++) {
+		INIT_HLIST_HEAD(&ovpn->peers->by_id[i]);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr4[i], i);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_vpn_addr6[i], i);
+		INIT_HLIST_NULLS_HEAD(&ovpn->peers->by_transp_addr[i], i);
+	}
+
+	return 0;
+}
+
 static int ovpn_net_init(struct net_device *dev)
 {
 	struct ovpn_priv *ovpn = netdev_priv(dev);
+	int err = gro_cells_init(&ovpn->gro_cells, dev);
 
-	return gro_cells_init(&ovpn->gro_cells, dev);
+	if (err < 0)
+		return err;
+
+	err = ovpn_mp_alloc(ovpn);
+	if (err < 0) {
+		gro_cells_destroy(&ovpn->gro_cells);
+		return err;
+	}
+
+	return 0;
 }
 
 static void ovpn_net_uninit(struct net_device *dev)
@@ -91,6 +146,8 @@ static void ovpn_setup(struct net_device *dev)
 
 	dev->netdev_ops = &ovpn_netdev_ops;
 
+	dev->priv_destructor = ovpn_priv_free;
+
 	dev->hard_header_len = 0;
 	dev->addr_len = 0;
 	dev->mtu = ETH_DATA_LEN - OVPN_HEAD_ROOM;
@@ -187,10 +244,7 @@ static int ovpn_netdev_notifier_call(struct notifier_block *nb,
 
 		netif_carrier_off(dev);
 		ovpn->registered = false;
-
-		if (ovpn->mode == OVPN_MODE_P2P)
-			ovpn_peer_release_p2p(ovpn, NULL,
-					      OVPN_DEL_PEER_REASON_TEARDOWN);
+		ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN);
 		break;
 	case NETDEV_POST_INIT:
 	case NETDEV_GOING_DOWN:
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index 2e3f4baf305f0..b26ad97215a3d 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -15,12 +15,30 @@
 #include <uapi/linux/if_link.h>
 #include <uapi/linux/ovpn.h>
 
+/**
+ * struct ovpn_peer_collection - container of peers for MultiPeer mode
+ * @by_id: table of peers index by ID
+ * @by_vpn_addr4: table of peers indexed by VPN IPv4 address (items can be
+ *		  rehashed on the fly due to peer IP change)
+ * @by_vpn_addr6: table of peers indexed by VPN IPv6 address (items can be
+ *		  rehashed on the fly due to peer IP change)
+ * @by_transp_addr: table of peers indexed by transport address (items can be
+ *		    rehashed on the fly due to peer IP change)
+ */
+struct ovpn_peer_collection {
+	DECLARE_HASHTABLE(by_id, 12);
+	struct hlist_nulls_head by_vpn_addr4[1 << 12];
+	struct hlist_nulls_head by_vpn_addr6[1 << 12];
+	struct hlist_nulls_head by_transp_addr[1 << 12];
+};
+
 /**
  * struct ovpn_priv - per ovpn interface state
  * @dev: the actual netdev representing the tunnel
  * @registered: whether dev is still registered with netdev or not
  * @mode: device operation mode (i.e. p2p, mp, ..)
  * @lock: protect this object
+ * @peers: data structures holding multi-peer references
  * @peer: in P2P mode, this is the only remote peer
  * @gro_cells: pointer to the Generic Receive Offload cell
  */
@@ -29,6 +47,7 @@ struct ovpn_priv {
 	bool registered;
 	enum ovpn_mode mode;
 	spinlock_t lock; /* protect writing to the ovpn_priv object */
+	struct ovpn_peer_collection *peers;
 	struct ovpn_peer __rcu *peer;
 	struct gro_cells gro_cells;
 };
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 0fe5333c6b810..bed2e591c000c 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -9,6 +9,7 @@
 
 #include <linux/skbuff.h>
 #include <linux/list.h>
+#include <linux/hashtable.h>
 
 #include "ovpnpriv.h"
 #include "bind.h"
@@ -280,7 +281,19 @@ static void ovpn_peer_remove(struct ovpn_peer *peer,
 			     enum ovpn_del_peer_reason reason,
 			     struct llist_head *release_list)
 {
+	lockdep_assert_held(&peer->ovpn->lock);
+
 	switch (peer->ovpn->mode) {
+	case OVPN_MODE_MP:
+		/* prevent double remove */
+		if (hlist_unhashed(&peer->hash_entry_id))
+			return;
+
+		hlist_del_init_rcu(&peer->hash_entry_id);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr4);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr6);
+		hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr);
+		break;
 	case OVPN_MODE_P2P:
 		/* prevent double remove */
 		if (peer != rcu_access_pointer(peer->ovpn->peer))
@@ -292,8 +305,6 @@ static void ovpn_peer_remove(struct ovpn_peer *peer,
 		 */
 		netif_carrier_off(peer->ovpn->dev);
 		break;
-	default:
-		return;
 	}
 
 	peer->delete_reason = reason;
@@ -357,6 +368,89 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 	return match;
 }
 
+#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
+	typeof(_tbl) *__tbl = &(_tbl);				\
+	(&(*__tbl)[jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl)]); }) \
+
+/**
+ * ovpn_peer_add_mp - add peer to related tables in a MP instance
+ * @ovpn: the instance to add the peer to
+ * @peer: the peer to add
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_add_mp(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
+{
+	struct sockaddr_storage sa = { 0 };
+	struct hlist_nulls_head *nhead;
+	struct sockaddr_in6 *sa6;
+	struct sockaddr_in *sa4;
+	struct ovpn_bind *bind;
+	struct ovpn_peer *tmp;
+	size_t salen;
+	int ret = 0;
+
+	spin_lock_bh(&ovpn->lock);
+	/* do not add duplicates */
+	tmp = ovpn_peer_get_by_id(ovpn, peer->id);
+	if (tmp) {
+		ovpn_peer_put(tmp);
+		ret = -EEXIST;
+		goto out;
+	}
+
+	bind = rcu_dereference_protected(peer->bind, true);
+	/* peers connected via TCP have bind == NULL */
+	if (bind) {
+		switch (bind->remote.in4.sin_family) {
+		case AF_INET:
+			sa4 = (struct sockaddr_in *)&sa;
+
+			sa4->sin_family = AF_INET;
+			sa4->sin_addr.s_addr = bind->remote.in4.sin_addr.s_addr;
+			sa4->sin_port = bind->remote.in4.sin_port;
+			salen = sizeof(*sa4);
+			break;
+		case AF_INET6:
+			sa6 = (struct sockaddr_in6 *)&sa;
+
+			sa6->sin6_family = AF_INET6;
+			sa6->sin6_addr = bind->remote.in6.sin6_addr;
+			sa6->sin6_port = bind->remote.in6.sin6_port;
+			salen = sizeof(*sa6);
+			break;
+		default:
+			ret = -EPROTONOSUPPORT;
+			goto out;
+		}
+
+		nhead = ovpn_get_hash_head(ovpn->peers->by_transp_addr, &sa,
+					   salen);
+		hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead);
+	}
+
+	hlist_add_head_rcu(&peer->hash_entry_id,
+			   ovpn_get_hash_head(ovpn->peers->by_id, &peer->id,
+					      sizeof(peer->id)));
+
+	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) {
+		nhead = ovpn_get_hash_head(ovpn->peers->by_vpn_addr4,
+					   &peer->vpn_addrs.ipv4,
+					   sizeof(peer->vpn_addrs.ipv4));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr4, nhead);
+	}
+
+	if (!ipv6_addr_any(&peer->vpn_addrs.ipv6)) {
+		nhead = ovpn_get_hash_head(ovpn->peers->by_vpn_addr6,
+					   &peer->vpn_addrs.ipv6,
+					   sizeof(peer->vpn_addrs.ipv6));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr6, nhead);
+	}
+out:
+	spin_unlock_bh(&ovpn->lock);
+	return ret;
+}
+
 /**
  * ovpn_peer_add_p2p - add peer to related tables in a P2P instance
  * @ovpn: the instance to add the peer to
@@ -399,11 +493,42 @@ static int ovpn_peer_add_p2p(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
 int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
 {
 	switch (ovpn->mode) {
+	case OVPN_MODE_MP:
+		return ovpn_peer_add_mp(ovpn, peer);
 	case OVPN_MODE_P2P:
 		return ovpn_peer_add_p2p(ovpn, peer);
-	default:
-		return -EOPNOTSUPP;
 	}
+
+	return -EOPNOTSUPP;
+}
+
+/**
+ * ovpn_peer_del_mp - delete peer from related tables in a MP instance
+ * @peer: the peer to delete
+ * @reason: reason why the peer was deleted (sent to userspace)
+ * @release_list: list where delete peer should be appended
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_del_mp(struct ovpn_peer *peer,
+			    enum ovpn_del_peer_reason reason,
+			    struct llist_head *release_list)
+{
+	struct ovpn_peer *tmp;
+	int ret = -ENOENT;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	tmp = ovpn_peer_get_by_id(peer->ovpn, peer->id);
+	if (tmp == peer) {
+		ovpn_peer_remove(peer, reason, release_list);
+		ret = 0;
+	}
+
+	if (tmp)
+		ovpn_peer_put(tmp);
+
+	return ret;
 }
 
 /**
@@ -446,6 +571,9 @@ int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason)
 
 	spin_lock_bh(&peer->ovpn->lock);
 	switch (peer->ovpn->mode) {
+	case OVPN_MODE_MP:
+		ret = ovpn_peer_del_mp(peer, reason, &release_list);
+		break;
 	case OVPN_MODE_P2P:
 		ret = ovpn_peer_del_p2p(peer, reason, &release_list);
 		break;
@@ -463,8 +591,8 @@ int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason)
  * @sk: if not NULL, release peer only if it's using this specific socket
  * @reason: the reason for releasing the peer
  */
-void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
-			   enum ovpn_del_peer_reason reason)
+static void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
+				  enum ovpn_del_peer_reason reason)
 {
 	struct ovpn_socket *ovpn_sock;
 	LLIST_HEAD(release_list);
@@ -490,3 +618,52 @@ void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
 	ovpn_peer_remove(peer, reason, &release_list);
 	unlock_ovpn(ovpn, &release_list);
 }
+
+static void ovpn_peers_release_mp(struct ovpn_priv *ovpn, struct sock *sk,
+				  enum ovpn_del_peer_reason reason)
+{
+	struct ovpn_socket *ovpn_sock;
+	LLIST_HEAD(release_list);
+	struct ovpn_peer *peer;
+	struct hlist_node *tmp;
+	int bkt;
+
+	spin_lock_bh(&ovpn->lock);
+	hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) {
+		bool remove = true;
+
+		/* if a socket was passed as argument, skip all peers except
+		 * those using it
+		 */
+		if (sk) {
+			rcu_read_lock();
+			ovpn_sock = rcu_dereference(peer->sock);
+			remove = ovpn_sock && ovpn_sock->sock->sk == sk;
+			rcu_read_unlock();
+		}
+
+		if (remove)
+			ovpn_peer_remove(peer, reason, &release_list);
+	}
+	unlock_ovpn(ovpn, &release_list);
+}
+
+/**
+ * ovpn_peers_free - free all peers in the instance
+ * @ovpn: the instance whose peers should be released
+ * @sk: if not NULL, only peers using this socket are removed and the socket
+ *      is released immediately
+ * @reason: the reason for releasing all peers
+ */
+void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sk,
+		     enum ovpn_del_peer_reason reason)
+{
+	switch (ovpn->mode) {
+	case OVPN_MODE_P2P:
+		ovpn_peer_release_p2p(ovpn, sk, reason);
+		break;
+	case OVPN_MODE_MP:
+		ovpn_peers_release_mp(ovpn, sk, reason);
+		break;
+	}
+}
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index 5ef00ba6523d7..2a3b1031f58dd 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -25,6 +25,10 @@
  * @vpn_addrs: IP addresses assigned over the tunnel
  * @vpn_addrs.ipv4: IPv4 assigned to peer on the tunnel
  * @vpn_addrs.ipv6: IPv6 assigned to peer on the tunnel
+ * @hash_entry_id: entry in the peer ID hashtable
+ * @hash_entry_addr4: entry in the peer IPv4 hashtable
+ * @hash_entry_addr6: entry in the peer IPv6 hashtable
+ * @hash_entry_transp_addr: entry in the peer transport address hashtable
  * @sock: the socket being used to talk to this peer
  * @tcp: keeps track of TCP specific state
  * @tcp.strp: stream parser context (TCP only)
@@ -57,6 +61,10 @@ struct ovpn_peer {
 		struct in_addr ipv4;
 		struct in6_addr ipv6;
 	} vpn_addrs;
+	struct hlist_node hash_entry_id;
+	struct hlist_nulls_node hash_entry_addr4;
+	struct hlist_nulls_node hash_entry_addr6;
+	struct hlist_nulls_node hash_entry_transp_addr;
 	struct ovpn_socket __rcu *sock;
 
 	struct {
@@ -117,8 +125,8 @@ static inline void ovpn_peer_put(struct ovpn_peer *peer)
 struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id);
 int ovpn_peer_add(struct ovpn_priv *ovpn, struct ovpn_peer *peer);
 int ovpn_peer_del(struct ovpn_peer *peer, enum ovpn_del_peer_reason reason);
-void ovpn_peer_release_p2p(struct ovpn_priv *ovpn, struct sock *sk,
-			   enum ovpn_del_peer_reason reason);
+void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sock,
+		     enum ovpn_del_peer_reason reason);
 
 struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
 					       struct sk_buff *skb);
diff --git a/drivers/net/ovpn/udp.c b/drivers/net/ovpn/udp.c
index 6f4b51089033a..3367feb5cf725 100644
--- a/drivers/net/ovpn/udp.c
+++ b/drivers/net/ovpn/udp.c
@@ -370,9 +370,7 @@ static void ovpn_udp_encap_destroy(struct sock *sk)
 	ovpn = sock->ovpn;
 	rcu_read_unlock();
 
-	if (ovpn->mode == OVPN_MODE_P2P)
-		ovpn_peer_release_p2p(ovpn, sk,
-				      OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
+	ovpn_peers_free(ovpn, sk, OVPN_DEL_PEER_REASON_TRANSPORT_DISCONNECT);
 }
 
 /**

From 283d931ce0d8fbbecececc2e7399d423305d3699 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:50 +0100
Subject: [PATCH 2556/2753] ovpn: implement peer lookup logic

In a multi-peer scenario there are a number of situations when a
specific peer needs to be looked up.

We may want to lookup a peer by:
1. its ID
2. its VPN destination IP
3. its transport IP/port couple

For each of the above, there is a specific routing table referencing all
peers for fast look up.

Case 2. is a bit special in the sense that an outgoing packet may not be
sent to the peer VPN IP directly, but rather to a network behind it. For
this reason we first perform a nexthop lookup in the system routing
table and then we use the retrieved nexthop as peer search key.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/peer.c | 301 ++++++++++++++++++++++++++++++++++++++--
 1 file changed, 291 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index bed2e591c000c..2d6cecc28c5d1 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -10,6 +10,7 @@
 #include <linux/skbuff.h>
 #include <linux/list.h>
 #include <linux/hashtable.h>
+#include <net/ip6_route.h>
 
 #include "ovpnpriv.h"
 #include "bind.h"
@@ -150,6 +151,121 @@ static int ovpn_peer_skb_to_sockaddr(struct sk_buff *skb,
 	return -1;
 }
 
+/**
+ * ovpn_nexthop_from_skb4 - retrieve IPv4 nexthop for outgoing skb
+ * @skb: the outgoing packet
+ *
+ * Return: the IPv4 of the nexthop
+ */
+static __be32 ovpn_nexthop_from_skb4(struct sk_buff *skb)
+{
+	const struct rtable *rt = skb_rtable(skb);
+
+	if (rt && rt->rt_uses_gateway)
+		return rt->rt_gw4;
+
+	return ip_hdr(skb)->daddr;
+}
+
+/**
+ * ovpn_nexthop_from_skb6 - retrieve IPv6 nexthop for outgoing skb
+ * @skb: the outgoing packet
+ *
+ * Return: the IPv6 of the nexthop
+ */
+static struct in6_addr ovpn_nexthop_from_skb6(struct sk_buff *skb)
+{
+	const struct rt6_info *rt = skb_rt6_info(skb);
+
+	if (!rt || !(rt->rt6i_flags & RTF_GATEWAY))
+		return ipv6_hdr(skb)->daddr;
+
+	return rt->rt6i_gateway;
+}
+
+/* variable name __tbl2 needs to be different from __tbl1
+ * in the macro below to avoid confusing clang
+ */
+#define ovpn_get_hash_slot(_tbl, _key, _key_len) ({	\
+	typeof(_tbl) *__tbl2 = &(_tbl);			\
+	jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl2);	\
+})
+
+#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
+	typeof(_tbl) *__tbl1 = &(_tbl);				\
+	&(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\
+})
+
+/**
+ * ovpn_peer_get_by_vpn_addr4 - retrieve peer by its VPN IPv4 address
+ * @ovpn: the openvpn instance to search
+ * @addr: VPN IPv4 to use as search key
+ *
+ * Refcounter is not increased for the returned peer.
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_vpn_addr4(struct ovpn_priv *ovpn,
+						    __be32 addr)
+{
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	struct ovpn_peer *tmp;
+	unsigned int slot;
+
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr4, &addr,
+				  sizeof(addr));
+	nhead = &ovpn->peers->by_vpn_addr4[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr4)
+		if (addr == tmp->vpn_addrs.ipv4.s_addr)
+			return tmp;
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (get_nulls_value(ntmp) != slot)
+		goto begin;
+
+	return NULL;
+}
+
+/**
+ * ovpn_peer_get_by_vpn_addr6 - retrieve peer by its VPN IPv6 address
+ * @ovpn: the openvpn instance to search
+ * @addr: VPN IPv6 to use as search key
+ *
+ * Refcounter is not increased for the returned peer.
+ *
+ * Return: the peer if found or NULL otherwise
+ */
+static struct ovpn_peer *ovpn_peer_get_by_vpn_addr6(struct ovpn_priv *ovpn,
+						    struct in6_addr *addr)
+{
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	struct ovpn_peer *tmp;
+	unsigned int slot;
+
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_vpn_addr6, addr,
+				  sizeof(*addr));
+	nhead = &ovpn->peers->by_vpn_addr6[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead, hash_entry_addr6)
+		if (ipv6_addr_equal(addr, &tmp->vpn_addrs.ipv6))
+			return tmp;
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (get_nulls_value(ntmp) != slot)
+		goto begin;
+
+	return NULL;
+}
+
 /**
  * ovpn_peer_transp_match - check if sockaddr and peer binding match
  * @peer: the peer to get the binding from
@@ -227,14 +343,43 @@ ovpn_peer_get_by_transp_addr_p2p(struct ovpn_priv *ovpn,
 struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
 					       struct sk_buff *skb)
 {
-	struct ovpn_peer *peer = NULL;
+	struct ovpn_peer *tmp, *peer = NULL;
 	struct sockaddr_storage ss = { 0 };
+	struct hlist_nulls_head *nhead;
+	struct hlist_nulls_node *ntmp;
+	unsigned int slot;
+	ssize_t sa_len;
 
-	if (unlikely(!ovpn_peer_skb_to_sockaddr(skb, &ss)))
+	sa_len = ovpn_peer_skb_to_sockaddr(skb, &ss);
+	if (unlikely(sa_len < 0))
 		return NULL;
 
 	if (ovpn->mode == OVPN_MODE_P2P)
-		peer = ovpn_peer_get_by_transp_addr_p2p(ovpn, &ss);
+		return ovpn_peer_get_by_transp_addr_p2p(ovpn, &ss);
+
+	rcu_read_lock();
+begin:
+	slot = ovpn_get_hash_slot(ovpn->peers->by_transp_addr, &ss, sa_len);
+	nhead = &ovpn->peers->by_transp_addr[slot];
+
+	hlist_nulls_for_each_entry_rcu(tmp, ntmp, nhead,
+				       hash_entry_transp_addr) {
+		if (!ovpn_peer_transp_match(tmp, &ss))
+			continue;
+
+		if (!ovpn_peer_hold(tmp))
+			continue;
+
+		peer = tmp;
+		break;
+	}
+
+	/* item may have moved during lookup - check nulls and restart
+	 * if that's the case
+	 */
+	if (!peer && get_nulls_value(ntmp) != slot)
+		goto begin;
+	rcu_read_unlock();
 
 	return peer;
 }
@@ -269,10 +414,27 @@ static struct ovpn_peer *ovpn_peer_get_by_id_p2p(struct ovpn_priv *ovpn,
  */
 struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id)
 {
-	struct ovpn_peer *peer = NULL;
+	struct ovpn_peer *tmp, *peer = NULL;
+	struct hlist_head *head;
 
 	if (ovpn->mode == OVPN_MODE_P2P)
-		peer = ovpn_peer_get_by_id_p2p(ovpn, peer_id);
+		return ovpn_peer_get_by_id_p2p(ovpn, peer_id);
+
+	head = ovpn_get_hash_head(ovpn->peers->by_id, &peer_id,
+				  sizeof(peer_id));
+
+	rcu_read_lock();
+	hlist_for_each_entry_rcu(tmp, head, hash_entry_id) {
+		if (tmp->id != peer_id)
+			continue;
+
+		if (!ovpn_peer_hold(tmp))
+			continue;
+
+		peer = tmp;
+		break;
+	}
+	rcu_read_unlock();
 
 	return peer;
 }
@@ -330,6 +492,8 @@ struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 				       struct sk_buff *skb)
 {
 	struct ovpn_peer *peer = NULL;
+	struct in6_addr addr6;
+	__be32 addr4;
 
 	/* in P2P mode, no matter the destination, packets are always sent to
 	 * the single peer listening on the other side
@@ -340,11 +504,109 @@ struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 		if (unlikely(peer && !ovpn_peer_hold(peer)))
 			peer = NULL;
 		rcu_read_unlock();
+		return peer;
 	}
 
+	rcu_read_lock();
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		addr4 = ovpn_nexthop_from_skb4(skb);
+		peer = ovpn_peer_get_by_vpn_addr4(ovpn, addr4);
+		break;
+	case htons(ETH_P_IPV6):
+		addr6 = ovpn_nexthop_from_skb6(skb);
+		peer = ovpn_peer_get_by_vpn_addr6(ovpn, &addr6);
+		break;
+	}
+
+	if (unlikely(peer && !ovpn_peer_hold(peer)))
+		peer = NULL;
+	rcu_read_unlock();
+
 	return peer;
 }
 
+/**
+ * ovpn_nexthop_from_rt4 - look up the IPv4 nexthop for the given destination
+ * @ovpn: the private data representing the current VPN session
+ * @dest: the destination to be looked up
+ *
+ * Looks up in the IPv4 system routing table the IP of the nexthop to be used
+ * to reach the destination passed as argument. If no nexthop can be found, the
+ * destination itself is returned as it probably has to be used as nexthop.
+ *
+ * Return: the IP of the next hop if found or dest itself otherwise
+ */
+static __be32 ovpn_nexthop_from_rt4(struct ovpn_priv *ovpn, __be32 dest)
+{
+	struct rtable *rt;
+	struct flowi4 fl = {
+		.daddr = dest
+	};
+
+	rt = ip_route_output_flow(dev_net(ovpn->dev), &fl, NULL);
+	if (IS_ERR(rt)) {
+		net_dbg_ratelimited("%s: no route to host %pI4\n",
+				    netdev_name(ovpn->dev), &dest);
+		/* if we end up here this packet is probably going to be
+		 * thrown away later
+		 */
+		return dest;
+	}
+
+	if (!rt->rt_uses_gateway)
+		goto out;
+
+	dest = rt->rt_gw4;
+out:
+	ip_rt_put(rt);
+	return dest;
+}
+
+/**
+ * ovpn_nexthop_from_rt6 - look up the IPv6 nexthop for the given destination
+ * @ovpn: the private data representing the current VPN session
+ * @dest: the destination to be looked up
+ *
+ * Looks up in the IPv6 system routing table the IP of the nexthop to be used
+ * to reach the destination passed as argument. If no nexthop can be found, the
+ * destination itself is returned as it probably has to be used as nexthop.
+ *
+ * Return: the IP of the next hop if found or dest itself otherwise
+ */
+static struct in6_addr ovpn_nexthop_from_rt6(struct ovpn_priv *ovpn,
+					     struct in6_addr dest)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct dst_entry *entry;
+	struct rt6_info *rt;
+	struct flowi6 fl = {
+		.daddr = dest,
+	};
+
+	entry = ipv6_stub->ipv6_dst_lookup_flow(dev_net(ovpn->dev), NULL, &fl,
+						NULL);
+	if (IS_ERR(entry)) {
+		net_dbg_ratelimited("%s: no route to host %pI6c\n",
+				    netdev_name(ovpn->dev), &dest);
+		/* if we end up here this packet is probably going to be
+		 * thrown away later
+		 */
+		return dest;
+	}
+
+	rt = dst_rt6_info(entry);
+
+	if (!(rt->rt6i_flags & RTF_GATEWAY))
+		goto out;
+
+	dest = rt->rt6i_gateway;
+out:
+	dst_release((struct dst_entry *)rt);
+#endif
+	return dest;
+}
+
 /**
  * ovpn_peer_check_by_src - check that skb source is routed via peer
  * @ovpn: the openvpn instance to search
@@ -357,21 +619,40 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 			    struct ovpn_peer *peer)
 {
 	bool match = false;
+	struct in6_addr addr6;
+	__be32 addr4;
 
 	if (ovpn->mode == OVPN_MODE_P2P) {
 		/* in P2P mode, no matter the destination, packets are always
 		 * sent to the single peer listening on the other side
 		 */
-		match = (peer == rcu_access_pointer(ovpn->peer));
+		return peer == rcu_access_pointer(ovpn->peer);
+	}
+
+	/* This function performs a reverse path check, therefore we now
+	 * lookup the nexthop we would use if we wanted to route a packet
+	 * to the source IP. If the nexthop matches the sender we know the
+	 * latter is valid and we allow the packet to come in
+	 */
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		addr4 = ovpn_nexthop_from_rt4(ovpn, ip_hdr(skb)->saddr);
+		rcu_read_lock();
+		match = (peer == ovpn_peer_get_by_vpn_addr4(ovpn, addr4));
+		rcu_read_unlock();
+		break;
+	case htons(ETH_P_IPV6):
+		addr6 = ovpn_nexthop_from_rt6(ovpn, ipv6_hdr(skb)->saddr);
+		rcu_read_lock();
+		match = (peer == ovpn_peer_get_by_vpn_addr6(ovpn, &addr6));
+		rcu_read_unlock();
+		break;
 	}
 
 	return match;
 }
 
-#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
-	typeof(_tbl) *__tbl = &(_tbl);				\
-	(&(*__tbl)[jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl)]); }) \
-
 /**
  * ovpn_peer_add_mp - add peer to related tables in a MP instance
  * @ovpn: the instance to add the peer to

From 030029d245e3f449c02d844b514bfd6c8f5fa7fb Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:51 +0100
Subject: [PATCH 2557/2753] ovpn: implement keepalive mechanism

OpenVPN supports configuring a periodic keepalive packet.
message to allow the remote endpoint detect link failures.

This change implements the keepalive sending and timer expiring logic.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/io.c       |  74 +++++++++++++
 drivers/net/ovpn/io.h       |   5 +
 drivers/net/ovpn/main.c     |   3 +
 drivers/net/ovpn/ovpnpriv.h |   2 +
 drivers/net/ovpn/peer.c     | 205 ++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/peer.h     |  21 +++-
 6 files changed, 308 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 801cdbff40952..fcba094ed4120 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -27,6 +27,33 @@
 #include "skb.h"
 #include "socket.h"
 
+const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE] = {
+	0x2a, 0x18, 0x7b, 0xf3, 0x64, 0x1e, 0xb4, 0xcb,
+	0x07, 0xed, 0x2d, 0x0a, 0x98, 0x1f, 0xc7, 0x48
+};
+
+/**
+ * ovpn_is_keepalive - check if skb contains a keepalive message
+ * @skb: packet to check
+ *
+ * Assumes that the first byte of skb->data is defined.
+ *
+ * Return: true if skb contains a keepalive or false otherwise
+ */
+static bool ovpn_is_keepalive(struct sk_buff *skb)
+{
+	if (*skb->data != ovpn_keepalive_message[0])
+		return false;
+
+	if (skb->len != OVPN_KEEPALIVE_SIZE)
+		return false;
+
+	if (!pskb_may_pull(skb, OVPN_KEEPALIVE_SIZE))
+		return false;
+
+	return !memcmp(skb->data, ovpn_keepalive_message, OVPN_KEEPALIVE_SIZE);
+}
+
 /* Called after decrypt to write the IP packet to the device.
  * This method is expected to manage/free the skb.
  */
@@ -107,6 +134,9 @@ void ovpn_decrypt_post(void *data, int ret)
 		goto drop;
 	}
 
+	/* keep track of last received authenticated packet for keepalive */
+	WRITE_ONCE(peer->last_recv, ktime_get_real_seconds());
+
 	/* point to encapsulated IP packet */
 	__skb_pull(skb, payload_offset);
 
@@ -124,6 +154,13 @@ void ovpn_decrypt_post(void *data, int ret)
 			goto drop;
 		}
 
+		if (ovpn_is_keepalive(skb)) {
+			net_dbg_ratelimited("%s: ping received from peer %u\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id);
+			goto drop_nocount;
+		}
+
 		net_info_ratelimited("%s: unsupported protocol received from peer %u\n",
 				     netdev_name(peer->ovpn->dev), peer->id);
 		goto drop;
@@ -149,6 +186,7 @@ void ovpn_decrypt_post(void *data, int ret)
 drop:
 	if (unlikely(skb))
 		dev_core_stats_rx_dropped_inc(peer->ovpn->dev);
+drop_nocount:
 	if (likely(peer))
 		ovpn_peer_put(peer);
 	if (likely(ks))
@@ -233,6 +271,8 @@ void ovpn_encrypt_post(void *data, int ret)
 	}
 
 	ovpn_peer_stats_increment_tx(&peer->link_stats, orig_len);
+	/* keep track of last sent packet for keepalive */
+	WRITE_ONCE(peer->last_sent, ktime_get_real_seconds());
 	/* skb passed down the stack - don't free it */
 	skb = NULL;
 err_unlock:
@@ -358,3 +398,37 @@ netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	kfree_skb_list(skb);
 	return NET_XMIT_DROP;
 }
+
+/**
+ * ovpn_xmit_special - encrypt and transmit an out-of-band message to peer
+ * @peer: peer to send the message to
+ * @data: message content
+ * @len: message length
+ *
+ * Assumes that caller holds a reference to peer, which will be
+ * passed to ovpn_send()
+ */
+void ovpn_xmit_special(struct ovpn_peer *peer, const void *data,
+		       const unsigned int len)
+{
+	struct ovpn_priv *ovpn;
+	struct sk_buff *skb;
+
+	ovpn = peer->ovpn;
+	if (unlikely(!ovpn)) {
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	skb = alloc_skb(256 + len, GFP_ATOMIC);
+	if (unlikely(!skb)) {
+		ovpn_peer_put(peer);
+		return;
+	}
+
+	skb_reserve(skb, 128);
+	skb->priority = TC_PRIO_BESTEFFORT;
+	__skb_put_data(skb, data, len);
+
+	ovpn_send(ovpn, skb, peer);
+}
diff --git a/drivers/net/ovpn/io.h b/drivers/net/ovpn/io.h
index 5143104b2c4b8..db9e10f9077c4 100644
--- a/drivers/net/ovpn/io.h
+++ b/drivers/net/ovpn/io.h
@@ -19,9 +19,14 @@
 /* max padding required by encryption */
 #define OVPN_MAX_PADDING 16
 
+#define OVPN_KEEPALIVE_SIZE 16
+extern const unsigned char ovpn_keepalive_message[OVPN_KEEPALIVE_SIZE];
+
 netdev_tx_t ovpn_net_xmit(struct sk_buff *skb, struct net_device *dev);
 
 void ovpn_recv(struct ovpn_peer *peer, struct sk_buff *skb);
+void ovpn_xmit_special(struct ovpn_peer *peer, const void *data,
+		       const unsigned int len);
 
 void ovpn_encrypt_post(void *data, int ret);
 void ovpn_decrypt_post(void *data, int ret);
diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 1b3d5b6c83999..0e016d39c95e5 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -185,6 +185,7 @@ static int ovpn_newlink(struct net_device *dev,
 	ovpn->dev = dev;
 	ovpn->mode = mode;
 	spin_lock_init(&ovpn->lock);
+	INIT_DELAYED_WORK(&ovpn->keepalive_work, ovpn_peer_keepalive_work);
 
 	/* turn carrier explicitly off after registration, this way state is
 	 * clearly defined
@@ -244,6 +245,8 @@ static int ovpn_netdev_notifier_call(struct notifier_block *nb,
 
 		netif_carrier_off(dev);
 		ovpn->registered = false;
+
+		cancel_delayed_work_sync(&ovpn->keepalive_work);
 		ovpn_peers_free(ovpn, NULL, OVPN_DEL_PEER_REASON_TEARDOWN);
 		break;
 	case NETDEV_POST_INIT:
diff --git a/drivers/net/ovpn/ovpnpriv.h b/drivers/net/ovpn/ovpnpriv.h
index b26ad97215a3d..5403cdc99a67c 100644
--- a/drivers/net/ovpn/ovpnpriv.h
+++ b/drivers/net/ovpn/ovpnpriv.h
@@ -41,6 +41,7 @@ struct ovpn_peer_collection {
  * @peers: data structures holding multi-peer references
  * @peer: in P2P mode, this is the only remote peer
  * @gro_cells: pointer to the Generic Receive Offload cell
+ * @keepalive_work: struct used to schedule keepalive periodic job
  */
 struct ovpn_priv {
 	struct net_device *dev;
@@ -50,6 +51,7 @@ struct ovpn_priv {
 	struct ovpn_peer_collection *peers;
 	struct ovpn_peer __rcu *peer;
 	struct gro_cells gro_cells;
+	struct delayed_work keepalive_work;
 };
 
 #endif /* _NET_OVPN_OVPNSTRUCT_H_ */
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 2d6cecc28c5d1..45e87ac155b55 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -36,6 +36,52 @@ static void unlock_ovpn(struct ovpn_priv *ovpn,
 	}
 }
 
+/**
+ * ovpn_peer_keepalive_set - configure keepalive values for peer
+ * @peer: the peer to configure
+ * @interval: outgoing keepalive interval
+ * @timeout: incoming keepalive timeout
+ */
+void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout)
+{
+	time64_t now = ktime_get_real_seconds();
+
+	netdev_dbg(peer->ovpn->dev,
+		   "scheduling keepalive for peer %u: interval=%u timeout=%u\n",
+		   peer->id, interval, timeout);
+
+	peer->keepalive_interval = interval;
+	WRITE_ONCE(peer->last_sent, now);
+	peer->keepalive_xmit_exp = now + interval;
+
+	peer->keepalive_timeout = timeout;
+	WRITE_ONCE(peer->last_recv, now);
+	peer->keepalive_recv_exp = now + timeout;
+
+	/* now that interval and timeout have been changed, kick
+	 * off the worker so that the next delay can be recomputed
+	 */
+	mod_delayed_work(system_wq, &peer->ovpn->keepalive_work, 0);
+}
+
+/**
+ * ovpn_peer_keepalive_send - periodic worker sending keepalive packets
+ * @work: pointer to the work member of the related peer object
+ *
+ * NOTE: the reference to peer is not dropped because it gets inherited
+ * by ovpn_xmit_special()
+ */
+static void ovpn_peer_keepalive_send(struct work_struct *work)
+{
+	struct ovpn_peer *peer = container_of(work, struct ovpn_peer,
+					      keepalive_work);
+
+	local_bh_disable();
+	ovpn_xmit_special(peer, ovpn_keepalive_message,
+			  sizeof(ovpn_keepalive_message));
+	local_bh_enable();
+}
+
 /**
  * ovpn_peer_new - allocate and initialize a new peer object
  * @ovpn: the openvpn instance inside which the peer should be created
@@ -65,6 +111,7 @@ struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
 	kref_init(&peer->refcount);
 	ovpn_peer_stats_init(&peer->vpn_stats);
 	ovpn_peer_stats_init(&peer->link_stats);
+	INIT_WORK(&peer->keepalive_work, ovpn_peer_keepalive_send);
 
 	ret = dst_cache_init(&peer->dst_cache, GFP_KERNEL);
 	if (ret < 0) {
@@ -948,3 +995,161 @@ void ovpn_peers_free(struct ovpn_priv *ovpn, struct sock *sk,
 		break;
 	}
 }
+
+static time64_t ovpn_peer_keepalive_work_single(struct ovpn_peer *peer,
+						time64_t now,
+						struct llist_head *release_list)
+{
+	time64_t last_recv, last_sent, next_run1, next_run2;
+	unsigned long timeout, interval;
+	bool expired;
+
+	spin_lock_bh(&peer->lock);
+	/* we expect both timers to be configured at the same time,
+	 * therefore bail out if either is not set
+	 */
+	if (!peer->keepalive_timeout || !peer->keepalive_interval) {
+		spin_unlock_bh(&peer->lock);
+		return 0;
+	}
+
+	/* check for peer timeout */
+	expired = false;
+	timeout = peer->keepalive_timeout;
+	last_recv = READ_ONCE(peer->last_recv);
+	if (now < last_recv + timeout) {
+		peer->keepalive_recv_exp = last_recv + timeout;
+		next_run1 = peer->keepalive_recv_exp;
+	} else if (peer->keepalive_recv_exp > now) {
+		next_run1 = peer->keepalive_recv_exp;
+	} else {
+		expired = true;
+	}
+
+	if (expired) {
+		/* peer is dead -> kill it and move on */
+		spin_unlock_bh(&peer->lock);
+		netdev_dbg(peer->ovpn->dev, "peer %u expired\n",
+			   peer->id);
+		ovpn_peer_remove(peer, OVPN_DEL_PEER_REASON_EXPIRED,
+				 release_list);
+		return 0;
+	}
+
+	/* check for peer keepalive */
+	expired = false;
+	interval = peer->keepalive_interval;
+	last_sent = READ_ONCE(peer->last_sent);
+	if (now < last_sent + interval) {
+		peer->keepalive_xmit_exp = last_sent + interval;
+		next_run2 = peer->keepalive_xmit_exp;
+	} else if (peer->keepalive_xmit_exp > now) {
+		next_run2 = peer->keepalive_xmit_exp;
+	} else {
+		expired = true;
+		next_run2 = now + interval;
+	}
+	spin_unlock_bh(&peer->lock);
+
+	if (expired) {
+		/* a keepalive packet is required */
+		netdev_dbg(peer->ovpn->dev,
+			   "sending keepalive to peer %u\n",
+			   peer->id);
+		if (schedule_work(&peer->keepalive_work))
+			ovpn_peer_hold(peer);
+	}
+
+	if (next_run1 < next_run2)
+		return next_run1;
+
+	return next_run2;
+}
+
+static time64_t ovpn_peer_keepalive_work_mp(struct ovpn_priv *ovpn,
+					    time64_t now,
+					    struct llist_head *release_list)
+{
+	time64_t tmp_next_run, next_run = 0;
+	struct hlist_node *tmp;
+	struct ovpn_peer *peer;
+	int bkt;
+
+	lockdep_assert_held(&ovpn->lock);
+
+	hash_for_each_safe(ovpn->peers->by_id, bkt, tmp, peer, hash_entry_id) {
+		tmp_next_run = ovpn_peer_keepalive_work_single(peer, now,
+							       release_list);
+		if (!tmp_next_run)
+			continue;
+
+		/* the next worker run will be scheduled based on the shortest
+		 * required interval across all peers
+		 */
+		if (!next_run || tmp_next_run < next_run)
+			next_run = tmp_next_run;
+	}
+
+	return next_run;
+}
+
+static time64_t ovpn_peer_keepalive_work_p2p(struct ovpn_priv *ovpn,
+					     time64_t now,
+					     struct llist_head *release_list)
+{
+	struct ovpn_peer *peer;
+	time64_t next_run = 0;
+
+	lockdep_assert_held(&ovpn->lock);
+
+	peer = rcu_dereference_protected(ovpn->peer,
+					 lockdep_is_held(&ovpn->lock));
+	if (peer)
+		next_run = ovpn_peer_keepalive_work_single(peer, now,
+							   release_list);
+
+	return next_run;
+}
+
+/**
+ * ovpn_peer_keepalive_work - run keepalive logic on each known peer
+ * @work: pointer to the work member of the related ovpn object
+ *
+ * Each peer has two timers (if configured):
+ * 1. peer timeout: when no data is received for a certain interval,
+ *    the peer is considered dead and it gets killed.
+ * 2. peer keepalive: when no data is sent to a certain peer for a
+ *    certain interval, a special 'keepalive' packet is explicitly sent.
+ *
+ * This function iterates across the whole peer collection while
+ * checking the timers described above.
+ */
+void ovpn_peer_keepalive_work(struct work_struct *work)
+{
+	struct ovpn_priv *ovpn = container_of(work, struct ovpn_priv,
+					      keepalive_work.work);
+	time64_t next_run = 0, now = ktime_get_real_seconds();
+	LLIST_HEAD(release_list);
+
+	spin_lock_bh(&ovpn->lock);
+	switch (ovpn->mode) {
+	case OVPN_MODE_MP:
+		next_run = ovpn_peer_keepalive_work_mp(ovpn, now,
+						       &release_list);
+		break;
+	case OVPN_MODE_P2P:
+		next_run = ovpn_peer_keepalive_work_p2p(ovpn, now,
+							&release_list);
+		break;
+	}
+
+	/* prevent rearming if the interface is being destroyed */
+	if (next_run > 0 && ovpn->registered) {
+		netdev_dbg(ovpn->dev,
+			   "scheduling keepalive work: now=%llu next_run=%llu delta=%llu\n",
+			   next_run, now, next_run - now);
+		schedule_delayed_work(&ovpn->keepalive_work,
+				      (next_run - now) * HZ);
+	}
+	unlock_ovpn(ovpn, &release_list);
+}
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index 2a3b1031f58dd..e747c4b210642 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -45,13 +45,20 @@
  * @crypto: the crypto configuration (ciphers, keys, etc..)
  * @dst_cache: cache for dst_entry used to send to peer
  * @bind: remote peer binding
+ * @keepalive_interval: seconds after which a new keepalive should be sent
+ * @keepalive_xmit_exp: future timestamp when next keepalive should be sent
+ * @last_sent: timestamp of the last successfully sent packet
+ * @keepalive_timeout: seconds after which an inactive peer is considered dead
+ * @keepalive_recv_exp: future timestamp when the peer should expire
+ * @last_recv: timestamp of the last authenticated received packet
  * @vpn_stats: per-peer in-VPN TX/RX stats
  * @link_stats: per-peer link/transport TX/RX stats
  * @delete_reason: why peer was deleted (i.e. timeout, transport error, ..)
- * @lock: protects binding to peer (bind)
+ * @lock: protects binding to peer (bind) and keepalive* fields
  * @refcount: reference counter
  * @rcu: used to free peer in an RCU safe way
  * @release_entry: entry for the socket release list
+ * @keepalive_work: used to schedule keepalive sending
  */
 struct ovpn_peer {
 	struct ovpn_priv *ovpn;
@@ -91,13 +98,20 @@ struct ovpn_peer {
 	struct ovpn_crypto_state crypto;
 	struct dst_cache dst_cache;
 	struct ovpn_bind __rcu *bind;
+	unsigned long keepalive_interval;
+	unsigned long keepalive_xmit_exp;
+	time64_t last_sent;
+	unsigned long keepalive_timeout;
+	unsigned long keepalive_recv_exp;
+	time64_t last_recv;
 	struct ovpn_peer_stats vpn_stats;
 	struct ovpn_peer_stats link_stats;
 	enum ovpn_del_peer_reason delete_reason;
-	spinlock_t lock; /* protects bind */
+	spinlock_t lock; /* protects bind  and keepalive* */
 	struct kref refcount;
 	struct rcu_head rcu;
 	struct llist_node release_entry;
+	struct work_struct keepalive_work;
 };
 
 /**
@@ -136,4 +150,7 @@ struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 			    struct ovpn_peer *peer);
 
+void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout);
+void ovpn_peer_keepalive_work(struct work_struct *work);
+
 #endif /* _NET_OVPN_OVPNPEER_H_ */

From f43088dc6cfa63cc1deb752364bafd67b2e55cc0 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:52 +0100
Subject: [PATCH 2558/2753] ovpn: add support for updating local or remote UDP
 endpoint

In case of UDP links, the local or remote endpoint used to communicate
with a given peer may change without a connection restart.

Add support for learning the new address in case of change.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/io.c   |   8 ++
 drivers/net/ovpn/peer.c | 213 +++++++++++++++++++++++++++++++++++++---
 drivers/net/ovpn/peer.h |   2 +
 3 files changed, 210 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index fcba094ed4120..49bb58868053e 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -96,6 +96,7 @@ void ovpn_decrypt_post(void *data, int ret)
 	struct ovpn_crypto_key_slot *ks;
 	unsigned int payload_offset = 0;
 	struct sk_buff *skb = data;
+	struct ovpn_socket *sock;
 	struct ovpn_peer *peer;
 	__be16 proto;
 	__be32 *pid;
@@ -137,6 +138,13 @@ void ovpn_decrypt_post(void *data, int ret)
 	/* keep track of last received authenticated packet for keepalive */
 	WRITE_ONCE(peer->last_recv, ktime_get_real_seconds());
 
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (sock && sock->sock->sk->sk_protocol == IPPROTO_UDP)
+		/* check if this peer changed local or remote endpoint */
+		ovpn_peer_endpoints_update(peer, skb);
+	rcu_read_unlock();
+
 	/* point to encapsulated IP packet */
 	__skb_pull(skb, payload_offset);
 
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 45e87ac155b55..0d8b12fd5de4c 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -127,6 +127,206 @@ struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
 	return peer;
 }
 
+/**
+ * ovpn_peer_reset_sockaddr - recreate binding for peer
+ * @peer: peer to recreate the binding for
+ * @ss: sockaddr to use as remote endpoint for the binding
+ * @local_ip: local IP for the binding
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+static int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
+				    const struct sockaddr_storage *ss,
+				    const void *local_ip)
+{
+	struct ovpn_bind *bind;
+	size_t ip_len;
+
+	lockdep_assert_held(&peer->lock);
+
+	/* create new ovpn_bind object */
+	bind = ovpn_bind_from_sockaddr(ss);
+	if (IS_ERR(bind))
+		return PTR_ERR(bind);
+
+	if (ss->ss_family == AF_INET) {
+		ip_len = sizeof(struct in_addr);
+	} else if (ss->ss_family == AF_INET6) {
+		ip_len = sizeof(struct in6_addr);
+	} else {
+		net_dbg_ratelimited("%s: invalid family %u for remote endpoint for peer %u\n",
+				    netdev_name(peer->ovpn->dev),
+				    ss->ss_family, peer->id);
+		kfree(bind);
+		return -EINVAL;
+	}
+
+	memcpy(&bind->local, local_ip, ip_len);
+
+	/* set binding */
+	ovpn_bind_reset(peer, bind);
+
+	return 0;
+}
+
+/* variable name __tbl2 needs to be different from __tbl1
+ * in the macro below to avoid confusing clang
+ */
+#define ovpn_get_hash_slot(_tbl, _key, _key_len) ({	\
+	typeof(_tbl) *__tbl2 = &(_tbl);			\
+	jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl2);	\
+})
+
+#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
+	typeof(_tbl) *__tbl1 = &(_tbl);				\
+	&(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\
+})
+
+/**
+ * ovpn_peer_endpoints_update - update remote or local endpoint for peer
+ * @peer: peer to update the remote endpoint for
+ * @skb: incoming packet to retrieve the source/destination address from
+ */
+void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb)
+{
+	struct hlist_nulls_head *nhead;
+	struct sockaddr_storage ss;
+	struct sockaddr_in6 *sa6;
+	bool reset_cache = false;
+	struct sockaddr_in *sa;
+	struct ovpn_bind *bind;
+	const void *local_ip;
+	size_t salen = 0;
+
+	spin_lock_bh(&peer->lock);
+	bind = rcu_dereference_protected(peer->bind,
+					 lockdep_is_held(&peer->lock));
+	if (unlikely(!bind))
+		goto unlock;
+
+	switch (skb->protocol) {
+	case htons(ETH_P_IP):
+		/* float check */
+		if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) {
+			/* unconditionally save local endpoint in case
+			 * of float, as it may have changed as well
+			 */
+			local_ip = &ip_hdr(skb)->daddr;
+			sa = (struct sockaddr_in *)&ss;
+			sa->sin_family = AF_INET;
+			sa->sin_addr.s_addr = ip_hdr(skb)->saddr;
+			sa->sin_port = udp_hdr(skb)->source;
+			salen = sizeof(*sa);
+			reset_cache = true;
+			break;
+		}
+
+		/* if no float happened, let's double check if the local endpoint
+		 * has changed
+		 */
+		if (unlikely(bind->local.ipv4.s_addr != ip_hdr(skb)->daddr)) {
+			net_dbg_ratelimited("%s: learning local IPv4 for peer %d (%pI4 -> %pI4)\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &bind->local.ipv4.s_addr,
+					    &ip_hdr(skb)->daddr);
+			bind->local.ipv4.s_addr = ip_hdr(skb)->daddr;
+			reset_cache = true;
+		}
+		break;
+	case htons(ETH_P_IPV6):
+		/* float check */
+		if (unlikely(!ovpn_bind_skb_src_match(bind, skb))) {
+			/* unconditionally save local endpoint in case
+			 * of float, as it may have changed as well
+			 */
+			local_ip = &ipv6_hdr(skb)->daddr;
+			sa6 = (struct sockaddr_in6 *)&ss;
+			sa6->sin6_family = AF_INET6;
+			sa6->sin6_addr = ipv6_hdr(skb)->saddr;
+			sa6->sin6_port = udp_hdr(skb)->source;
+			sa6->sin6_scope_id = ipv6_iface_scope_id(&ipv6_hdr(skb)->saddr,
+								 skb->skb_iif);
+			salen = sizeof(*sa6);
+			reset_cache = true;
+			break;
+		}
+
+		/* if no float happened, let's double check if the local endpoint
+		 * has changed
+		 */
+		if (unlikely(!ipv6_addr_equal(&bind->local.ipv6,
+					      &ipv6_hdr(skb)->daddr))) {
+			net_dbg_ratelimited("%s: learning local IPv6 for peer %d (%pI6c -> %pI6c\n",
+					    netdev_name(peer->ovpn->dev),
+					    peer->id, &bind->local.ipv6,
+					    &ipv6_hdr(skb)->daddr);
+			bind->local.ipv6 = ipv6_hdr(skb)->daddr;
+			reset_cache = true;
+		}
+		break;
+	default:
+		goto unlock;
+	}
+
+	if (unlikely(reset_cache))
+		dst_cache_reset(&peer->dst_cache);
+
+	/* if the peer did not float, we can bail out now */
+	if (likely(!salen))
+		goto unlock;
+
+	if (unlikely(ovpn_peer_reset_sockaddr(peer,
+					      (struct sockaddr_storage *)&ss,
+					      local_ip) < 0))
+		goto unlock;
+
+	net_dbg_ratelimited("%s: peer %d floated to %pIScp",
+			    netdev_name(peer->ovpn->dev), peer->id, &ss);
+
+	spin_unlock_bh(&peer->lock);
+
+	/* rehashing is required only in MP mode as P2P has one peer
+	 * only and thus there is no hashtable
+	 */
+	if (peer->ovpn->mode == OVPN_MODE_MP) {
+		spin_lock_bh(&peer->ovpn->lock);
+		spin_lock_bh(&peer->lock);
+		bind = rcu_dereference_protected(peer->bind,
+						 lockdep_is_held(&peer->lock));
+		if (unlikely(!bind)) {
+			spin_unlock_bh(&peer->lock);
+			spin_unlock_bh(&peer->ovpn->lock);
+			return;
+		}
+
+		/* This function may be invoked concurrently, therefore another
+		 * float may have happened in parallel: perform rehashing
+		 * using the peer->bind->remote directly as key
+		 */
+
+		switch (bind->remote.in4.sin_family) {
+		case AF_INET:
+			salen = sizeof(*sa);
+			break;
+		case AF_INET6:
+			salen = sizeof(*sa6);
+			break;
+		}
+
+		/* remove old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_transp_addr);
+		/* re-add with new transport address */
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_transp_addr,
+					   &bind->remote, salen);
+		hlist_nulls_add_head_rcu(&peer->hash_entry_transp_addr, nhead);
+		spin_unlock_bh(&peer->lock);
+		spin_unlock_bh(&peer->ovpn->lock);
+	}
+	return;
+unlock:
+	spin_unlock_bh(&peer->lock);
+}
+
 /**
  * ovpn_peer_release_rcu - RCU callback performing last peer release steps
  * @head: RCU member of the ovpn_peer
@@ -230,19 +430,6 @@ static struct in6_addr ovpn_nexthop_from_skb6(struct sk_buff *skb)
 	return rt->rt6i_gateway;
 }
 
-/* variable name __tbl2 needs to be different from __tbl1
- * in the macro below to avoid confusing clang
- */
-#define ovpn_get_hash_slot(_tbl, _key, _key_len) ({	\
-	typeof(_tbl) *__tbl2 = &(_tbl);			\
-	jhash(_key, _key_len, 0) % HASH_SIZE(*__tbl2);	\
-})
-
-#define ovpn_get_hash_head(_tbl, _key, _key_len) ({		\
-	typeof(_tbl) *__tbl1 = &(_tbl);				\
-	&(*__tbl1)[ovpn_get_hash_slot(*__tbl1, _key, _key_len)];\
-})
-
 /**
  * ovpn_peer_get_by_vpn_addr4 - retrieve peer by its VPN IPv4 address
  * @ovpn: the openvpn instance to search
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index e747c4b210642..f1288734ff100 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -153,4 +153,6 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout);
 void ovpn_peer_keepalive_work(struct work_struct *work);
 
+void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb);
+
 #endif /* _NET_OVPN_OVPNPEER_H_ */

From b3a3d472b6d86c818bf65154070298be403040db Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:53 +0100
Subject: [PATCH 2559/2753] ovpn: implement peer add/get/dump/delete via
 netlink

This change introduces the netlink command needed to add, delete and
retrieve/dump known peers. Userspace is expected to use these commands
to handle known peer lifecycles.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/netlink.c | 678 ++++++++++++++++++++++++++++++++++++-
 drivers/net/ovpn/peer.c    |  79 +++--
 drivers/net/ovpn/peer.h    |   5 +
 drivers/net/ovpn/socket.c  |   4 +-
 4 files changed, 730 insertions(+), 36 deletions(-)

diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
index 8d267d4c82283..873386aa217e7 100644
--- a/drivers/net/ovpn/netlink.c
+++ b/drivers/net/ovpn/netlink.c
@@ -7,6 +7,7 @@
  */
 
 #include <linux/netdevice.h>
+#include <linux/types.h>
 #include <net/genetlink.h>
 
 #include <uapi/linux/ovpn.h>
@@ -15,6 +16,9 @@
 #include "main.h"
 #include "netlink.h"
 #include "netlink-gen.h"
+#include "bind.h"
+#include "peer.h"
+#include "socket.h"
 
 MODULE_ALIAS_GENL_FAMILY(OVPN_FAMILY_NAME);
 
@@ -89,29 +93,693 @@ void ovpn_nl_post_doit(const struct genl_split_ops *ops, struct sk_buff *skb,
 		netdev_put(ovpn->dev, tracker);
 }
 
+static bool ovpn_nl_attr_sockaddr_remote(struct nlattr **attrs,
+					 struct sockaddr_storage *ss)
+{
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	struct in6_addr *in6;
+	__be16 port = 0;
+	__be32 *in;
+
+	ss->ss_family = AF_UNSPEC;
+
+	if (attrs[OVPN_A_PEER_REMOTE_PORT])
+		port = nla_get_be16(attrs[OVPN_A_PEER_REMOTE_PORT]);
+
+	if (attrs[OVPN_A_PEER_REMOTE_IPV4]) {
+		ss->ss_family = AF_INET;
+		in = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV4]);
+	} else if (attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		ss->ss_family = AF_INET6;
+		in6 = nla_data(attrs[OVPN_A_PEER_REMOTE_IPV6]);
+	} else {
+		return false;
+	}
+
+	switch (ss->ss_family) {
+	case AF_INET6:
+		/* If this is a regular IPv6 just break and move on,
+		 * otherwise switch to AF_INET and extract the IPv4 accordingly
+		 */
+		if (!ipv6_addr_v4mapped(in6)) {
+			sin6 = (struct sockaddr_in6 *)ss;
+			sin6->sin6_port = port;
+			memcpy(&sin6->sin6_addr, in6, sizeof(*in6));
+			break;
+		}
+
+		/* v4-mapped-v6 address */
+		ss->ss_family = AF_INET;
+		in = &in6->s6_addr32[3];
+		fallthrough;
+	case AF_INET:
+		sin = (struct sockaddr_in *)ss;
+		sin->sin_port = port;
+		sin->sin_addr.s_addr = *in;
+		break;
+	}
+
+	return true;
+}
+
+static u8 *ovpn_nl_attr_local_ip(struct nlattr **attrs)
+{
+	u8 *addr6;
+
+	if (!attrs[OVPN_A_PEER_LOCAL_IPV4] && !attrs[OVPN_A_PEER_LOCAL_IPV6])
+		return NULL;
+
+	if (attrs[OVPN_A_PEER_LOCAL_IPV4])
+		return nla_data(attrs[OVPN_A_PEER_LOCAL_IPV4]);
+
+	addr6 = nla_data(attrs[OVPN_A_PEER_LOCAL_IPV6]);
+	/* this is an IPv4-mapped IPv6 address, therefore extract the actual
+	 * v4 address from the last 4 bytes
+	 */
+	if (ipv6_addr_v4mapped((struct in6_addr *)addr6))
+		return addr6 + 12;
+
+	return addr6;
+}
+
+static sa_family_t ovpn_nl_family_get(struct nlattr *addr4,
+				      struct nlattr *addr6)
+{
+	if (addr4)
+		return AF_INET;
+
+	if (addr6) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)nla_data(addr6)))
+			return AF_INET;
+		return AF_INET6;
+	}
+
+	return AF_UNSPEC;
+}
+
+static int ovpn_nl_peer_precheck(struct ovpn_priv *ovpn,
+				 struct genl_info *info,
+				 struct nlattr **attrs)
+{
+	sa_family_t local_fam, remote_fam;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	if (attrs[OVPN_A_PEER_REMOTE_IPV4] && attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify both remote IPv4 or IPv6 address");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV6] && attrs[OVPN_A_PEER_REMOTE_PORT]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify remote port without IP address");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    attrs[OVPN_A_PEER_LOCAL_IPV4]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify local IPv4 address without remote");
+		return -EINVAL;
+	}
+
+	if (!attrs[OVPN_A_PEER_REMOTE_IPV6] &&
+	    attrs[OVPN_A_PEER_LOCAL_IPV6]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify local IPV6 address without remote");
+		return -EINVAL;
+	}
+
+	/* check that local and remote address families are the same even
+	 * after parsing v4mapped IPv6 addresses.
+	 * (if addresses are not provided, family will be AF_UNSPEC and
+	 * the check is skipped)
+	 */
+	local_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_LOCAL_IPV4],
+				       attrs[OVPN_A_PEER_LOCAL_IPV6]);
+	remote_fam = ovpn_nl_family_get(attrs[OVPN_A_PEER_REMOTE_IPV4],
+					attrs[OVPN_A_PEER_REMOTE_IPV6]);
+	if (local_fam != AF_UNSPEC && remote_fam != AF_UNSPEC &&
+	    local_fam != remote_fam) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "mismatching local and remote address families");
+		return -EINVAL;
+	}
+
+	if (remote_fam != AF_INET6 && attrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+		NL_SET_ERR_MSG_MOD(info->extack,
+				   "cannot specify scope id without remote IPv6 address");
+		return -EINVAL;
+	}
+
+	/* VPN IPs are needed only in MP mode for selecting the right peer */
+	if (ovpn->mode == OVPN_MODE_P2P && (attrs[OVPN_A_PEER_VPN_IPV4] ||
+					    attrs[OVPN_A_PEER_VPN_IPV6])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected VPN IP in P2P mode");
+		return -EINVAL;
+	}
+
+	if ((attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	     !attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) ||
+	    (!attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	     attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "keepalive interval and timeout are required together");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_peer_modify - modify the peer attributes according to the incoming msg
+ * @peer: the peer to modify
+ * @info: generic netlink info from the user request
+ * @attrs: the attributes from the user request
+ *
+ * Return: a negative error code in case of failure, 0 on success or 1 on
+ *	   success and the VPN IPs have been modified (requires rehashing in MP
+ *	   mode)
+ */
+static int ovpn_nl_peer_modify(struct ovpn_peer *peer, struct genl_info *info,
+			       struct nlattr **attrs)
+{
+	struct sockaddr_storage ss = {};
+	void *local_ip = NULL;
+	u32 interv, timeout;
+	bool rehash = false;
+	int ret;
+
+	spin_lock_bh(&peer->lock);
+
+	if (ovpn_nl_attr_sockaddr_remote(attrs, &ss)) {
+		/* we carry the local IP in a generic container.
+		 * ovpn_peer_reset_sockaddr() will properly interpret it
+		 * based on ss.ss_family
+		 */
+		local_ip = ovpn_nl_attr_local_ip(attrs);
+
+		/* set peer sockaddr */
+		ret = ovpn_peer_reset_sockaddr(peer, &ss, local_ip);
+		if (ret < 0) {
+			NL_SET_ERR_MSG_FMT_MOD(info->extack,
+					       "cannot set peer sockaddr: %d",
+					       ret);
+			goto err_unlock;
+		}
+		dst_cache_reset(&peer->dst_cache);
+	}
+
+	if (attrs[OVPN_A_PEER_VPN_IPV4]) {
+		rehash = true;
+		peer->vpn_addrs.ipv4.s_addr =
+			nla_get_in_addr(attrs[OVPN_A_PEER_VPN_IPV4]);
+	}
+
+	if (attrs[OVPN_A_PEER_VPN_IPV6]) {
+		rehash = true;
+		peer->vpn_addrs.ipv6 =
+			nla_get_in6_addr(attrs[OVPN_A_PEER_VPN_IPV6]);
+	}
+
+	/* when setting the keepalive, both parameters have to be configured */
+	if (attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL] &&
+	    attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]) {
+		interv = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]);
+		timeout = nla_get_u32(attrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]);
+		ovpn_peer_keepalive_set(peer, interv, timeout);
+	}
+
+	netdev_dbg(peer->ovpn->dev,
+		   "modify peer id=%u endpoint=%pIScp VPN-IPv4=%pI4 VPN-IPv6=%pI6c\n",
+		   peer->id, &ss,
+		   &peer->vpn_addrs.ipv4.s_addr, &peer->vpn_addrs.ipv6);
+
+	spin_unlock_bh(&peer->lock);
+
+	return rehash ? 1 : 0;
+err_unlock:
+	spin_unlock_bh(&peer->lock);
+	return ret;
+}
+
 int ovpn_nl_peer_new_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_socket *ovpn_sock;
+	struct socket *sock = NULL;
+	struct ovpn_peer *peer;
+	u32 sockfd, peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	ret = ovpn_nl_peer_precheck(ovpn, info, attrs);
+	if (ret < 0)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_SOCKET))
+		return -EINVAL;
+
+	/* in MP mode VPN IPs are required for selecting the right peer */
+	if (ovpn->mode == OVPN_MODE_MP && !attrs[OVPN_A_PEER_VPN_IPV4] &&
+	    !attrs[OVPN_A_PEER_VPN_IPV6]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "VPN IP must be provided in MP mode");
+		return -EINVAL;
+	}
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_new(ovpn, peer_id);
+	if (IS_ERR(peer)) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot create new peer object for peer %u: %ld",
+				       peer_id, PTR_ERR(peer));
+		return PTR_ERR(peer);
+	}
+
+	/* lookup the fd in the kernel table and extract the socket object */
+	sockfd = nla_get_u32(attrs[OVPN_A_PEER_SOCKET]);
+	/* sockfd_lookup() increases sock's refcounter */
+	sock = sockfd_lookup(sockfd, &ret);
+	if (!sock) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot lookup peer socket (fd=%u): %d",
+				       sockfd, ret);
+		ret = -ENOTSOCK;
+		goto peer_release;
+	}
+
+	/* Only when using UDP as transport protocol the remote endpoint
+	 * can be configured so that ovpn knows where to send packets to.
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_UDP &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV4] &&
+	    !attrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "missing remote IP address for UDP socket");
+		sockfd_put(sock);
+		ret = -EINVAL;
+		goto peer_release;
+	}
+
+	/* In case of TCP, the socket is connected to the peer and ovpn
+	 * will just send bytes over it, without the need to specify a
+	 * destination.
+	 */
+	if (sock->sk->sk_protocol == IPPROTO_TCP &&
+	    (attrs[OVPN_A_PEER_REMOTE_IPV4] ||
+	     attrs[OVPN_A_PEER_REMOTE_IPV6])) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected remote IP address with TCP socket");
+		sockfd_put(sock);
+		ret = -EINVAL;
+		goto peer_release;
+	}
+
+	ovpn_sock = ovpn_socket_new(sock, peer);
+	/* at this point we unconditionally drop the reference to the socket:
+	 * - in case of error, the socket has to be dropped
+	 * - if case of success, the socket is configured and let
+	 *   userspace own the reference, so that the latter can
+	 *   trigger the final close()
+	 */
+	sockfd_put(sock);
+	if (IS_ERR(ovpn_sock)) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot encapsulate socket: %ld",
+				       PTR_ERR(ovpn_sock));
+		ret = -ENOTSOCK;
+		goto peer_release;
+	}
+
+	rcu_assign_pointer(peer->sock, ovpn_sock);
+
+	ret = ovpn_nl_peer_modify(peer, info, attrs);
+	if (ret < 0)
+		goto sock_release;
+
+	ret = ovpn_peer_add(ovpn, peer);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot add new peer (id=%u) to hashtable: %d",
+				       peer->id, ret);
+		goto sock_release;
+	}
+
+	return 0;
+
+sock_release:
+	ovpn_socket_release(peer);
+peer_release:
+	/* release right away because peer was not yet hashed, thus it is not
+	 * used in any context
+	 */
+	ovpn_peer_release(peer);
+
+	return ret;
 }
 
 int ovpn_nl_peer_set_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_socket *sock;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	ret = ovpn_nl_peer_precheck(ovpn, info, attrs);
+	if (ret < 0)
+		return ret;
+
+	if (attrs[OVPN_A_PEER_SOCKET]) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "socket cannot be modified");
+		return -EINVAL;
+	}
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	/* when using a TCP socket the remote IP is not expected */
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (sock && sock->sock->sk->sk_protocol == IPPROTO_TCP &&
+	    (attrs[OVPN_A_PEER_REMOTE_IPV4] ||
+	     attrs[OVPN_A_PEER_REMOTE_IPV6])) {
+		rcu_read_unlock();
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "unexpected remote IP address with TCP socket");
+		ovpn_peer_put(peer);
+		return -EINVAL;
+	}
+	rcu_read_unlock();
+
+	spin_lock_bh(&ovpn->lock);
+	ret = ovpn_nl_peer_modify(peer, info, attrs);
+	if (ret < 0) {
+		spin_unlock_bh(&ovpn->lock);
+		ovpn_peer_put(peer);
+		return ret;
+	}
+
+	/* ret == 1 means that VPN IPv4/6 has been modified and rehashing
+	 * is required
+	 */
+	if (ret > 0)
+		ovpn_peer_hash_vpn_ip(peer);
+	spin_unlock_bh(&ovpn->lock);
+	ovpn_peer_put(peer);
+
+	return 0;
+}
+
+static int ovpn_nl_send_peer(struct sk_buff *skb, const struct genl_info *info,
+			     const struct ovpn_peer *peer, u32 portid, u32 seq,
+			     int flags)
+{
+	const struct ovpn_bind *bind;
+	struct ovpn_socket *sock;
+	int ret = -EMSGSIZE;
+	struct nlattr *attr;
+	__be16 local_port;
+	void *hdr;
+	int id;
+
+	hdr = genlmsg_put(skb, portid, seq, &ovpn_nl_family, flags,
+			  OVPN_CMD_PEER_GET);
+	if (!hdr)
+		return -ENOBUFS;
+
+	attr = nla_nest_start(skb, OVPN_A_PEER);
+	if (!attr)
+		goto err;
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+
+	if (!net_eq(genl_info_net(info), sock_net(sock->sock->sk))) {
+		id = peernet2id_alloc(genl_info_net(info),
+				      sock_net(sock->sock->sk),
+				      GFP_ATOMIC);
+		if (nla_put_s32(skb, OVPN_A_PEER_SOCKET_NETNSID, id))
+			goto err_unlock;
+	}
+	local_port = inet_sk(sock->sock->sk)->inet_sport;
+	rcu_read_unlock();
+
+	if (nla_put_u32(skb, OVPN_A_PEER_ID, peer->id))
+		goto err;
+
+	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY))
+		if (nla_put_in_addr(skb, OVPN_A_PEER_VPN_IPV4,
+				    peer->vpn_addrs.ipv4.s_addr))
+			goto err;
+
+	if (!ipv6_addr_equal(&peer->vpn_addrs.ipv6, &in6addr_any))
+		if (nla_put_in6_addr(skb, OVPN_A_PEER_VPN_IPV6,
+				     &peer->vpn_addrs.ipv6))
+			goto err;
+
+	if (nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+			peer->keepalive_interval) ||
+	    nla_put_u32(skb, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+			peer->keepalive_timeout))
+		goto err;
+
+	rcu_read_lock();
+	bind = rcu_dereference(peer->bind);
+	if (bind) {
+		if (bind->remote.in4.sin_family == AF_INET) {
+			if (nla_put_in_addr(skb, OVPN_A_PEER_REMOTE_IPV4,
+					    bind->remote.in4.sin_addr.s_addr) ||
+			    nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT,
+					  bind->remote.in4.sin_port) ||
+			    nla_put_in_addr(skb, OVPN_A_PEER_LOCAL_IPV4,
+					    bind->local.ipv4.s_addr))
+				goto err_unlock;
+		} else if (bind->remote.in4.sin_family == AF_INET6) {
+			if (nla_put_in6_addr(skb, OVPN_A_PEER_REMOTE_IPV6,
+					     &bind->remote.in6.sin6_addr) ||
+			    nla_put_u32(skb, OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+					bind->remote.in6.sin6_scope_id) ||
+			    nla_put_net16(skb, OVPN_A_PEER_REMOTE_PORT,
+					  bind->remote.in6.sin6_port) ||
+			    nla_put_in6_addr(skb, OVPN_A_PEER_LOCAL_IPV6,
+					     &bind->local.ipv6))
+				goto err_unlock;
+		}
+	}
+	rcu_read_unlock();
+
+	if (nla_put_net16(skb, OVPN_A_PEER_LOCAL_PORT, local_port) ||
+	    /* VPN RX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_RX_BYTES,
+			 atomic64_read(&peer->vpn_stats.rx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_RX_PACKETS,
+			 atomic64_read(&peer->vpn_stats.rx.packets)) ||
+	    /* VPN TX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_TX_BYTES,
+			 atomic64_read(&peer->vpn_stats.tx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_VPN_TX_PACKETS,
+			 atomic64_read(&peer->vpn_stats.tx.packets)) ||
+	    /* link RX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_RX_BYTES,
+			 atomic64_read(&peer->link_stats.rx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_RX_PACKETS,
+			 atomic64_read(&peer->link_stats.rx.packets)) ||
+	    /* link TX stats */
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_TX_BYTES,
+			 atomic64_read(&peer->link_stats.tx.bytes)) ||
+	    nla_put_uint(skb, OVPN_A_PEER_LINK_TX_PACKETS,
+			 atomic64_read(&peer->link_stats.tx.packets)))
+		goto err;
+
+	nla_nest_end(skb, attr);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err_unlock:
+	rcu_read_unlock();
+err:
+	genlmsg_cancel(skb, hdr);
+	return ret;
 }
 
 int ovpn_nl_peer_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer *peer;
+	struct sk_buff *msg;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = ovpn_nl_send_peer(msg, info, peer, info->snd_portid,
+				info->snd_seq, 0);
+	if (ret < 0) {
+		nlmsg_free(msg);
+		goto err;
+	}
+
+	ret = genlmsg_reply(msg, info);
+err:
+	ovpn_peer_put(peer);
+	return ret;
 }
 
 int ovpn_nl_peer_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
-	return -EOPNOTSUPP;
+	const struct genl_info *info = genl_info_dump(cb);
+	int bkt, last_idx = cb->args[1], dumped = 0;
+	netdevice_tracker tracker;
+	struct ovpn_priv *ovpn;
+	struct ovpn_peer *peer;
+
+	ovpn = ovpn_get_dev_from_attrs(sock_net(cb->skb->sk), info, &tracker);
+	if (IS_ERR(ovpn))
+		return PTR_ERR(ovpn);
+
+	if (ovpn->mode == OVPN_MODE_P2P) {
+		/* if we already dumped a peer it means we are done */
+		if (last_idx)
+			goto out;
+
+		rcu_read_lock();
+		peer = rcu_dereference(ovpn->peer);
+		if (peer) {
+			if (ovpn_nl_send_peer(skb, info, peer,
+					      NETLINK_CB(cb->skb).portid,
+					      cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI) == 0)
+				dumped++;
+		}
+		rcu_read_unlock();
+	} else {
+		rcu_read_lock();
+		hash_for_each_rcu(ovpn->peers->by_id, bkt, peer,
+				  hash_entry_id) {
+			/* skip already dumped peers that were dumped by
+			 * previous invocations
+			 */
+			if (last_idx > 0) {
+				last_idx--;
+				continue;
+			}
+
+			if (ovpn_nl_send_peer(skb, info, peer,
+					      NETLINK_CB(cb->skb).portid,
+					      cb->nlh->nlmsg_seq,
+					      NLM_F_MULTI) < 0)
+				break;
+
+			/* count peers being dumped during this invocation */
+			dumped++;
+		}
+		rcu_read_unlock();
+	}
+
+out:
+	netdev_put(ovpn->dev, &tracker);
+
+	/* sum up peers dumped in this message, so that at the next invocation
+	 * we can continue from where we left
+	 */
+	cb->args[1] += dumped;
+	return skb->len;
 }
 
 int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_PEER))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_PEER_MAX, info->attrs[OVPN_A_PEER],
+			       ovpn_peer_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_PEER], attrs,
+			      OVPN_A_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	netdev_dbg(ovpn->dev, "del peer %u\n", peer->id);
+	ret = ovpn_peer_del(peer, OVPN_DEL_PEER_REASON_USERSPACE);
+	ovpn_peer_put(peer);
+
+	return ret;
 }
 
 int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info)
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 0d8b12fd5de4c..3af4531393f66 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -135,9 +135,9 @@ struct ovpn_peer *ovpn_peer_new(struct ovpn_priv *ovpn, u32 id)
  *
  * Return: 0 on success or a negative error code otherwise
  */
-static int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
-				    const struct sockaddr_storage *ss,
-				    const void *local_ip)
+int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
+			     const struct sockaddr_storage *ss,
+			     const void *local_ip)
 {
 	struct ovpn_bind *bind;
 	size_t ip_len;
@@ -149,19 +149,21 @@ static int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
 	if (IS_ERR(bind))
 		return PTR_ERR(bind);
 
-	if (ss->ss_family == AF_INET) {
-		ip_len = sizeof(struct in_addr);
-	} else if (ss->ss_family == AF_INET6) {
-		ip_len = sizeof(struct in6_addr);
-	} else {
-		net_dbg_ratelimited("%s: invalid family %u for remote endpoint for peer %u\n",
-				    netdev_name(peer->ovpn->dev),
-				    ss->ss_family, peer->id);
-		kfree(bind);
-		return -EINVAL;
-	}
+	if (local_ip) {
+		if (ss->ss_family == AF_INET) {
+			ip_len = sizeof(struct in_addr);
+		} else if (ss->ss_family == AF_INET6) {
+			ip_len = sizeof(struct in6_addr);
+		} else {
+			net_dbg_ratelimited("%s: invalid family %u for remote endpoint for peer %u\n",
+					    netdev_name(peer->ovpn->dev),
+					    ss->ss_family, peer->id);
+			kfree(bind);
+			return -EINVAL;
+		}
 
-	memcpy(&bind->local, local_ip, ip_len);
+		memcpy(&bind->local, local_ip, ip_len);
+	}
 
 	/* set binding */
 	ovpn_bind_reset(peer, bind);
@@ -346,7 +348,7 @@ static void ovpn_peer_release_rcu(struct rcu_head *head)
  * ovpn_peer_release - release peer private members
  * @peer: the peer to release
  */
-static void ovpn_peer_release(struct ovpn_peer *peer)
+void ovpn_peer_release(struct ovpn_peer *peer)
 {
 	ovpn_crypto_state_release(&peer->crypto);
 	spin_lock_bh(&peer->lock);
@@ -887,6 +889,37 @@ bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 	return match;
 }
 
+void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer)
+{
+	struct hlist_nulls_head *nhead;
+
+	lockdep_assert_held(&peer->ovpn->lock);
+
+	/* rehashing makes sense only in multipeer mode */
+	if (peer->ovpn->mode != OVPN_MODE_MP)
+		return;
+
+	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) {
+		/* remove potential old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr4);
+
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr4,
+					   &peer->vpn_addrs.ipv4,
+					   sizeof(peer->vpn_addrs.ipv4));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr4, nhead);
+	}
+
+	if (!ipv6_addr_any(&peer->vpn_addrs.ipv6)) {
+		/* remove potential old hashing */
+		hlist_nulls_del_init_rcu(&peer->hash_entry_addr6);
+
+		nhead = ovpn_get_hash_head(peer->ovpn->peers->by_vpn_addr6,
+					   &peer->vpn_addrs.ipv6,
+					   sizeof(peer->vpn_addrs.ipv6));
+		hlist_nulls_add_head_rcu(&peer->hash_entry_addr6, nhead);
+	}
+}
+
 /**
  * ovpn_peer_add_mp - add peer to related tables in a MP instance
  * @ovpn: the instance to add the peer to
@@ -948,19 +981,7 @@ static int ovpn_peer_add_mp(struct ovpn_priv *ovpn, struct ovpn_peer *peer)
 			   ovpn_get_hash_head(ovpn->peers->by_id, &peer->id,
 					      sizeof(peer->id)));
 
-	if (peer->vpn_addrs.ipv4.s_addr != htonl(INADDR_ANY)) {
-		nhead = ovpn_get_hash_head(ovpn->peers->by_vpn_addr4,
-					   &peer->vpn_addrs.ipv4,
-					   sizeof(peer->vpn_addrs.ipv4));
-		hlist_nulls_add_head_rcu(&peer->hash_entry_addr4, nhead);
-	}
-
-	if (!ipv6_addr_any(&peer->vpn_addrs.ipv6)) {
-		nhead = ovpn_get_hash_head(ovpn->peers->by_vpn_addr6,
-					   &peer->vpn_addrs.ipv6,
-					   sizeof(peer->vpn_addrs.ipv6));
-		hlist_nulls_add_head_rcu(&peer->hash_entry_addr6, nhead);
-	}
+	ovpn_peer_hash_vpn_ip(peer);
 out:
 	spin_unlock_bh(&ovpn->lock);
 	return ret;
diff --git a/drivers/net/ovpn/peer.h b/drivers/net/ovpn/peer.h
index f1288734ff100..a1423f2b09e06 100644
--- a/drivers/net/ovpn/peer.h
+++ b/drivers/net/ovpn/peer.h
@@ -125,6 +125,7 @@ static inline bool ovpn_peer_hold(struct ovpn_peer *peer)
 	return kref_get_unless_zero(&peer->refcount);
 }
 
+void ovpn_peer_release(struct ovpn_peer *peer);
 void ovpn_peer_release_kref(struct kref *kref);
 
 /**
@@ -147,6 +148,7 @@ struct ovpn_peer *ovpn_peer_get_by_transp_addr(struct ovpn_priv *ovpn,
 struct ovpn_peer *ovpn_peer_get_by_id(struct ovpn_priv *ovpn, u32 peer_id);
 struct ovpn_peer *ovpn_peer_get_by_dst(struct ovpn_priv *ovpn,
 				       struct sk_buff *skb);
+void ovpn_peer_hash_vpn_ip(struct ovpn_peer *peer);
 bool ovpn_peer_check_by_src(struct ovpn_priv *ovpn, struct sk_buff *skb,
 			    struct ovpn_peer *peer);
 
@@ -154,5 +156,8 @@ void ovpn_peer_keepalive_set(struct ovpn_peer *peer, u32 interval, u32 timeout);
 void ovpn_peer_keepalive_work(struct work_struct *work);
 
 void ovpn_peer_endpoints_update(struct ovpn_peer *peer, struct sk_buff *skb);
+int ovpn_peer_reset_sockaddr(struct ovpn_peer *peer,
+			     const struct sockaddr_storage *ss,
+			     const void *local_ip);
 
 #endif /* _NET_OVPN_OVPNPEER_H_ */
diff --git a/drivers/net/ovpn/socket.c b/drivers/net/ovpn/socket.c
index be20c500f373f..6ecf40857651a 100644
--- a/drivers/net/ovpn/socket.c
+++ b/drivers/net/ovpn/socket.c
@@ -49,8 +49,8 @@ static bool ovpn_socket_put(struct ovpn_peer *peer, struct ovpn_socket *sock)
  * ovpn_socket_release - release resources owned by socket user
  * @peer: peer whose socket should be released
  *
- * This function should be invoked when the user is shutting
- * down and wants to drop its link to the socket.
+ * This function should be invoked when the peer is being removed
+ * and wants to drop its link to the socket.
  *
  * In case of UDP, the detach routine will drop a reference to the
  * ovpn netdev, pointed by the ovpn_socket.

From 38b216d071e1d0e40daa58664cf636f86cc8f5b9 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:54 +0100
Subject: [PATCH 2560/2753] ovpn: implement key add/get/del/swap via netlink

This change introduces the netlink commands needed to add, get, delete
and swap keys for a specific peer.

Userspace is expected to use these commands to create, inspect (non
sensitive data only), destroy and rotate session keys for a specific
peer.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/crypto.c      |  40 +++++
 drivers/net/ovpn/crypto.h      |   4 +
 drivers/net/ovpn/crypto_aead.c |  17 ++
 drivers/net/ovpn/crypto_aead.h |   2 +
 drivers/net/ovpn/netlink.c     | 301 ++++++++++++++++++++++++++++++++-
 5 files changed, 360 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c
index db243cb48142f..3c15d6d78f0f5 100644
--- a/drivers/net/ovpn/crypto.c
+++ b/drivers/net/ovpn/crypto.c
@@ -150,3 +150,43 @@ void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs)
 
 	spin_unlock_bh(&cs->lock);
 }
+
+/**
+ * ovpn_crypto_config_get - populate keyconf object with non-sensible key data
+ * @cs: the crypto state to extract the key data from
+ * @slot: the specific slot to inspect
+ * @keyconf: the output object to populate
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_crypto_config_get(struct ovpn_crypto_state *cs,
+			   enum ovpn_key_slot slot,
+			   struct ovpn_key_config *keyconf)
+{
+	struct ovpn_crypto_key_slot *ks;
+	int idx;
+
+	switch (slot) {
+	case OVPN_KEY_SLOT_PRIMARY:
+		idx = cs->primary_idx;
+		break;
+	case OVPN_KEY_SLOT_SECONDARY:
+		idx = !cs->primary_idx;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	rcu_read_lock();
+	ks = rcu_dereference(cs->slots[idx]);
+	if (!ks) {
+		rcu_read_unlock();
+		return -ENOENT;
+	}
+
+	keyconf->cipher_alg = ovpn_aead_crypto_alg(ks);
+	keyconf->key_id = ks->key_id;
+	rcu_read_unlock();
+
+	return 0;
+}
diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h
index 5155791b87df7..487d24a7d2663 100644
--- a/drivers/net/ovpn/crypto.h
+++ b/drivers/net/ovpn/crypto.h
@@ -136,4 +136,8 @@ void ovpn_crypto_state_release(struct ovpn_crypto_state *cs);
 
 void ovpn_crypto_key_slots_swap(struct ovpn_crypto_state *cs);
 
+int ovpn_crypto_config_get(struct ovpn_crypto_state *cs,
+			   enum ovpn_key_slot slot,
+			   struct ovpn_key_config *keyconf);
+
 #endif /* _NET_OVPN_OVPNCRYPTO_H_ */
diff --git a/drivers/net/ovpn/crypto_aead.c b/drivers/net/ovpn/crypto_aead.c
index e87e33f49c308..26efe72987f3c 100644
--- a/drivers/net/ovpn/crypto_aead.c
+++ b/drivers/net/ovpn/crypto_aead.c
@@ -390,3 +390,20 @@ ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc)
 	ovpn_aead_crypto_key_slot_destroy(ks);
 	return ERR_PTR(ret);
 }
+
+enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks)
+{
+	const char *alg_name;
+
+	if (!ks->encrypt)
+		return OVPN_CIPHER_ALG_NONE;
+
+	alg_name = crypto_tfm_alg_name(crypto_aead_tfm(ks->encrypt));
+
+	if (!strcmp(alg_name, ALG_NAME_AES))
+		return OVPN_CIPHER_ALG_AES_GCM;
+	else if (!strcmp(alg_name, ALG_NAME_CHACHAPOLY))
+		return OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+	else
+		return OVPN_CIPHER_ALG_NONE;
+}
diff --git a/drivers/net/ovpn/crypto_aead.h b/drivers/net/ovpn/crypto_aead.h
index 40c056558add3..65a2ff3078986 100644
--- a/drivers/net/ovpn/crypto_aead.h
+++ b/drivers/net/ovpn/crypto_aead.h
@@ -24,4 +24,6 @@ struct ovpn_crypto_key_slot *
 ovpn_aead_crypto_key_slot_new(const struct ovpn_key_config *kc);
 void ovpn_aead_crypto_key_slot_destroy(struct ovpn_crypto_key_slot *ks);
 
+enum ovpn_cipher_alg ovpn_aead_crypto_alg(struct ovpn_crypto_key_slot *ks);
+
 #endif /* _NET_OVPN_OVPNAEAD_H_ */
diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
index 873386aa217e7..21784b44a897a 100644
--- a/drivers/net/ovpn/netlink.c
+++ b/drivers/net/ovpn/netlink.c
@@ -17,6 +17,7 @@
 #include "netlink.h"
 #include "netlink-gen.h"
 #include "bind.h"
+#include "crypto.h"
 #include "peer.h"
 #include "socket.h"
 
@@ -782,24 +783,316 @@ int ovpn_nl_peer_del_doit(struct sk_buff *skb, struct genl_info *info)
 	return ret;
 }
 
+static int ovpn_nl_get_key_dir(struct genl_info *info, struct nlattr *key,
+			       enum ovpn_cipher_alg cipher,
+			       struct ovpn_key_direction *dir)
+{
+	struct nlattr *attrs[OVPN_A_KEYDIR_MAX + 1];
+	int ret;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYDIR_MAX, key,
+			       ovpn_keydir_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	switch (cipher) {
+	case OVPN_CIPHER_ALG_AES_GCM:
+	case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+		if (NL_REQ_ATTR_CHECK(info->extack, key, attrs,
+				      OVPN_A_KEYDIR_CIPHER_KEY) ||
+		    NL_REQ_ATTR_CHECK(info->extack, key, attrs,
+				      OVPN_A_KEYDIR_NONCE_TAIL))
+			return -EINVAL;
+
+		dir->cipher_key = nla_data(attrs[OVPN_A_KEYDIR_CIPHER_KEY]);
+		dir->cipher_key_size = nla_len(attrs[OVPN_A_KEYDIR_CIPHER_KEY]);
+
+		/* These algorithms require a 96bit nonce,
+		 * Construct it by combining 4-bytes packet id and
+		 * 8-bytes nonce-tail from userspace
+		 */
+		dir->nonce_tail = nla_data(attrs[OVPN_A_KEYDIR_NONCE_TAIL]);
+		dir->nonce_tail_size = nla_len(attrs[OVPN_A_KEYDIR_NONCE_TAIL]);
+		break;
+	default:
+		NL_SET_ERR_MSG_MOD(info->extack, "unsupported cipher");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/**
+ * ovpn_nl_key_new_doit - configure a new key for the specified peer
+ * @skb: incoming netlink message
+ * @info: genetlink metadata
+ *
+ * This function allows the user to install a new key in the peer crypto
+ * state.
+ * Each peer has two 'slots', namely 'primary' and 'secondary', where
+ * keys can be installed. The key in the 'primary' slot is used for
+ * encryption, while both keys can be used for decryption by matching the
+ * key ID carried in the incoming packet.
+ *
+ * The user is responsible for rotating keys when necessary. The user
+ * may fetch peer traffic statistics via netlink in order to better
+ * identify the right time to rotate keys.
+ * The renegotiation follows these steps:
+ * 1. a new key is computed by the user and is installed in the 'secondary'
+ *    slot
+ * 2. at user discretion (usually after a predetermined time) 'primary' and
+ *    'secondary' contents are swapped and the new key starts being used for
+ *    encryption, while the old key is kept around for decryption of late
+ *    packets.
+ *
+ * Return: 0 on success or a negative error code otherwise.
+ */
 int ovpn_nl_key_new_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_peer_key_reset pkr;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_KEY_ID) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_CIPHER_ALG) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_ENCRYPT_DIR) ||
+	    NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_DECRYPT_DIR))
+		return -EINVAL;
+
+	pkr.slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+	pkr.key.key_id = nla_get_u32(attrs[OVPN_A_KEYCONF_KEY_ID]);
+	pkr.key.cipher_alg = nla_get_u32(attrs[OVPN_A_KEYCONF_CIPHER_ALG]);
+
+	ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_ENCRYPT_DIR],
+				  pkr.key.cipher_alg, &pkr.key.encrypt);
+	if (ret < 0)
+		return ret;
+
+	ret = ovpn_nl_get_key_dir(info, attrs[OVPN_A_KEYCONF_DECRYPT_DIR],
+				  pkr.key.cipher_alg, &pkr.key.decrypt);
+	if (ret < 0)
+		return ret;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to set key for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ret = ovpn_crypto_state_reset(&peer->crypto, &pkr);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot install new key for peer %u",
+				       peer_id);
+		goto out;
+	}
+
+	netdev_dbg(ovpn->dev, "new key installed (id=%u) for peer %u\n",
+		   pkr.key.key_id, peer_id);
+out:
+	ovpn_peer_put(peer);
+	return ret;
+}
+
+static int ovpn_nl_send_key(struct sk_buff *skb, const struct genl_info *info,
+			    u32 peer_id, enum ovpn_key_slot slot,
+			    const struct ovpn_key_config *keyconf)
+{
+	struct nlattr *attr;
+	void *hdr;
+
+	hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, &ovpn_nl_family,
+			  0, OVPN_CMD_KEY_GET);
+	if (!hdr)
+		return -ENOBUFS;
+
+	attr = nla_nest_start(skb, OVPN_A_KEYCONF);
+	if (!attr)
+		goto err;
+
+	if (nla_put_u32(skb, OVPN_A_KEYCONF_PEER_ID, peer_id))
+		goto err;
+
+	if (nla_put_u32(skb, OVPN_A_KEYCONF_SLOT, slot) ||
+	    nla_put_u32(skb, OVPN_A_KEYCONF_KEY_ID, keyconf->key_id) ||
+	    nla_put_u32(skb, OVPN_A_KEYCONF_CIPHER_ALG, keyconf->cipher_alg))
+		goto err;
+
+	nla_nest_end(skb, attr);
+	genlmsg_end(skb, hdr);
+
+	return 0;
+err:
+	genlmsg_cancel(skb, hdr);
+	return -EMSGSIZE;
 }
 
 int ovpn_nl_key_get_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct ovpn_key_config keyconf = { 0 };
+	enum ovpn_key_slot slot;
+	struct ovpn_peer *peer;
+	struct sk_buff *msg;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot find peer with id %u", peer_id);
+		return -ENOENT;
+	}
+
+	slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+
+	ret = ovpn_crypto_config_get(&peer->crypto, slot, &keyconf);
+	if (ret < 0) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "cannot extract key from slot %u for peer %u",
+				       slot, peer_id);
+		goto err;
+	}
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	ret = ovpn_nl_send_key(msg, info, peer->id, slot, &keyconf);
+	if (ret < 0) {
+		nlmsg_free(msg);
+		goto err;
+	}
+
+	ret = genlmsg_reply(msg, info);
+err:
+	ovpn_peer_put(peer);
+	return ret;
 }
 
 int ovpn_nl_key_swap_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	struct nlattr *attrs[OVPN_A_PEER_MAX + 1];
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to swap keys for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ovpn_crypto_key_slots_swap(&peer->crypto);
+	ovpn_peer_put(peer);
+
+	return 0;
 }
 
 int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info)
 {
-	return -EOPNOTSUPP;
+	struct nlattr *attrs[OVPN_A_KEYCONF_MAX + 1];
+	struct ovpn_priv *ovpn = info->user_ptr[0];
+	enum ovpn_key_slot slot;
+	struct ovpn_peer *peer;
+	u32 peer_id;
+	int ret;
+
+	if (GENL_REQ_ATTR_CHECK(info, OVPN_A_KEYCONF))
+		return -EINVAL;
+
+	ret = nla_parse_nested(attrs, OVPN_A_KEYCONF_MAX,
+			       info->attrs[OVPN_A_KEYCONF],
+			       ovpn_keyconf_nl_policy, info->extack);
+	if (ret)
+		return ret;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_PEER_ID))
+		return -EINVAL;
+
+	if (NL_REQ_ATTR_CHECK(info->extack, info->attrs[OVPN_A_KEYCONF], attrs,
+			      OVPN_A_KEYCONF_SLOT))
+		return -EINVAL;
+
+	peer_id = nla_get_u32(attrs[OVPN_A_KEYCONF_PEER_ID]);
+	slot = nla_get_u32(attrs[OVPN_A_KEYCONF_SLOT]);
+
+	peer = ovpn_peer_get_by_id(ovpn, peer_id);
+	if (!peer) {
+		NL_SET_ERR_MSG_FMT_MOD(info->extack,
+				       "no peer with id %u to delete key for",
+				       peer_id);
+		return -ENOENT;
+	}
+
+	ovpn_crypto_key_slot_delete(&peer->crypto, slot);
+	ovpn_peer_put(peer);
+
+	return 0;
 }
 
 /**

From e592f785239e3281050d19c7ccf6e2f37d03717b Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:55 +0100
Subject: [PATCH 2561/2753] ovpn: kill key and notify userspace in case of IV
 exhaustion

IV wrap-around is cryptographically dangerous for a number of ciphers,
therefore kill the key and inform userspace (via netlink) should the
IV space go exhausted.

Userspace has two ways of deciding when the key has to be renewed before
exhausting the IV space:
1) time based approach:
   after X seconds/minutes userspace generates a new key and sends it
   to the kernel. This is based on guestimate and normally default
   timer value works well.

2) packet count based approach:
   after X packets/bytes userspace generates a new key and sends it to
   the kernel. Userspace keeps track of the amount of traffic by
   periodically polling GET_PEER and fetching the VPN/LINK stats.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/crypto.c  | 19 +++++++++++
 drivers/net/ovpn/crypto.h  |  2 ++
 drivers/net/ovpn/io.c      | 13 ++++++++
 drivers/net/ovpn/netlink.c | 64 ++++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/netlink.h |  2 ++
 5 files changed, 100 insertions(+)

diff --git a/drivers/net/ovpn/crypto.c b/drivers/net/ovpn/crypto.c
index 3c15d6d78f0f5..f6cb14c9ec4a8 100644
--- a/drivers/net/ovpn/crypto.c
+++ b/drivers/net/ovpn/crypto.c
@@ -54,6 +54,25 @@ void ovpn_crypto_state_release(struct ovpn_crypto_state *cs)
 	}
 }
 
+/* removes the key matching the specified id from the crypto context */
+void ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id)
+{
+	struct ovpn_crypto_key_slot *ks = NULL;
+
+	spin_lock_bh(&cs->lock);
+	if (rcu_access_pointer(cs->slots[0])->key_id == key_id) {
+		ks = rcu_replace_pointer(cs->slots[0], NULL,
+					 lockdep_is_held(&cs->lock));
+	} else if (rcu_access_pointer(cs->slots[1])->key_id == key_id) {
+		ks = rcu_replace_pointer(cs->slots[1], NULL,
+					 lockdep_is_held(&cs->lock));
+	}
+	spin_unlock_bh(&cs->lock);
+
+	if (ks)
+		ovpn_crypto_key_slot_put(ks);
+}
+
 /* Reset the ovpn_crypto_state object in a way that is atomic
  * to RCU readers.
  */
diff --git a/drivers/net/ovpn/crypto.h b/drivers/net/ovpn/crypto.h
index 487d24a7d2663..4397253893ff2 100644
--- a/drivers/net/ovpn/crypto.h
+++ b/drivers/net/ovpn/crypto.h
@@ -140,4 +140,6 @@ int ovpn_crypto_config_get(struct ovpn_crypto_state *cs,
 			   enum ovpn_key_slot slot,
 			   struct ovpn_key_config *keyconf);
 
+void ovpn_crypto_kill_key(struct ovpn_crypto_state *cs, u8 key_id);
+
 #endif /* _NET_OVPN_OVPNCRYPTO_H_ */
diff --git a/drivers/net/ovpn/io.c b/drivers/net/ovpn/io.c
index 49bb58868053e..c11ed75c62a25 100644
--- a/drivers/net/ovpn/io.c
+++ b/drivers/net/ovpn/io.c
@@ -255,6 +255,19 @@ void ovpn_encrypt_post(void *data, int ret)
 	if (likely(ovpn_skb_cb(skb)->req))
 		aead_request_free(ovpn_skb_cb(skb)->req);
 
+	if (unlikely(ret == -ERANGE)) {
+		/* we ran out of IVs and we must kill the key as it can't be
+		 * use anymore
+		 */
+		netdev_warn(peer->ovpn->dev,
+			    "killing key %u for peer %u\n", ks->key_id,
+			    peer->id);
+		ovpn_crypto_kill_key(&peer->crypto, ks->key_id);
+		/* let userspace know so that a new key must be negotiated */
+		ovpn_nl_key_swap_notify(peer, ks->key_id);
+		goto err;
+	}
+
 	if (unlikely(ret < 0))
 		goto err;
 
diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
index 21784b44a897a..9315273409894 100644
--- a/drivers/net/ovpn/netlink.c
+++ b/drivers/net/ovpn/netlink.c
@@ -1095,6 +1095,70 @@ int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+/**
+ * ovpn_nl_key_swap_notify - notify userspace peer's key must be renewed
+ * @peer: the peer whose key needs to be renewed
+ * @key_id: the ID of the key that needs to be renewed
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id)
+{
+	struct ovpn_socket *sock;
+	struct nlattr *k_attr;
+	struct sk_buff *msg;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	netdev_info(peer->ovpn->dev, "peer with id %u must rekey - primary key unusable.\n",
+		    peer->id);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_KEY_SWAP_NTF);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto err_free_msg;
+	}
+
+	if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex))
+		goto err_cancel_msg;
+
+	k_attr = nla_nest_start(msg, OVPN_A_KEYCONF);
+	if (!k_attr)
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_KEYCONF_PEER_ID, peer->id))
+		goto err_cancel_msg;
+
+	if (nla_put_u16(msg, OVPN_A_KEYCONF_KEY_ID, key_id))
+		goto err_cancel_msg;
+
+	nla_nest_end(msg, k_attr);
+	genlmsg_end(msg, hdr);
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
+				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return 0;
+err_unlock:
+	rcu_read_unlock();
+err_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+err_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
 /**
  * ovpn_nl_register - perform any needed registration in the NL subsustem
  *
diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h
index 0d6c34e17082c..5dc84c8e5e803 100644
--- a/drivers/net/ovpn/netlink.h
+++ b/drivers/net/ovpn/netlink.h
@@ -12,4 +12,6 @@
 int ovpn_nl_register(void);
 void ovpn_nl_unregister(void);
 
+int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id);
+
 #endif /* _NET_OVPN_NETLINK_H_ */

From 076894ca69a2a0fcc66953edc5e1632966edb1ae Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:56 +0100
Subject: [PATCH 2562/2753] ovpn: notify userspace when a peer is deleted

Whenever a peer is deleted, send a notification to userspace so that it
can react accordingly.

This is most important when a peer is deleted due to ping timeout,
because it all happens in kernelspace and thus userspace has no direct
way to learn about it.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/netlink.c | 65 ++++++++++++++++++++++++++++++++++++++
 drivers/net/ovpn/netlink.h |  1 +
 drivers/net/ovpn/peer.c    |  1 +
 3 files changed, 67 insertions(+)

diff --git a/drivers/net/ovpn/netlink.c b/drivers/net/ovpn/netlink.c
index 9315273409894..30f2a7896edd3 100644
--- a/drivers/net/ovpn/netlink.c
+++ b/drivers/net/ovpn/netlink.c
@@ -1095,6 +1095,71 @@ int ovpn_nl_key_del_doit(struct sk_buff *skb, struct genl_info *info)
 	return 0;
 }
 
+/**
+ * ovpn_nl_peer_del_notify - notify userspace about peer being deleted
+ * @peer: the peer being deleted
+ *
+ * Return: 0 on success or a negative error code otherwise
+ */
+int ovpn_nl_peer_del_notify(struct ovpn_peer *peer)
+{
+	struct ovpn_socket *sock;
+	struct sk_buff *msg;
+	struct nlattr *attr;
+	int ret = -EMSGSIZE;
+	void *hdr;
+
+	netdev_info(peer->ovpn->dev, "deleting peer with id %u, reason %d\n",
+		    peer->id, peer->delete_reason);
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_put(msg, 0, 0, &ovpn_nl_family, 0, OVPN_CMD_PEER_DEL_NTF);
+	if (!hdr) {
+		ret = -ENOBUFS;
+		goto err_free_msg;
+	}
+
+	if (nla_put_u32(msg, OVPN_A_IFINDEX, peer->ovpn->dev->ifindex))
+		goto err_cancel_msg;
+
+	attr = nla_nest_start(msg, OVPN_A_PEER);
+	if (!attr)
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_PEER_DEL_REASON, peer->delete_reason))
+		goto err_cancel_msg;
+
+	if (nla_put_u32(msg, OVPN_A_PEER_ID, peer->id))
+		goto err_cancel_msg;
+
+	nla_nest_end(msg, attr);
+
+	genlmsg_end(msg, hdr);
+
+	rcu_read_lock();
+	sock = rcu_dereference(peer->sock);
+	if (!sock) {
+		ret = -EINVAL;
+		goto err_unlock;
+	}
+	genlmsg_multicast_netns(&ovpn_nl_family, sock_net(sock->sock->sk),
+				msg, 0, OVPN_NLGRP_PEERS, GFP_ATOMIC);
+	rcu_read_unlock();
+
+	return 0;
+
+err_unlock:
+	rcu_read_unlock();
+err_cancel_msg:
+	genlmsg_cancel(msg, hdr);
+err_free_msg:
+	nlmsg_free(msg);
+	return ret;
+}
+
 /**
  * ovpn_nl_key_swap_notify - notify userspace peer's key must be renewed
  * @peer: the peer whose key needs to be renewed
diff --git a/drivers/net/ovpn/netlink.h b/drivers/net/ovpn/netlink.h
index 5dc84c8e5e803..8615dfc3c4720 100644
--- a/drivers/net/ovpn/netlink.h
+++ b/drivers/net/ovpn/netlink.h
@@ -12,6 +12,7 @@
 int ovpn_nl_register(void);
 void ovpn_nl_unregister(void);
 
+int ovpn_nl_peer_del_notify(struct ovpn_peer *peer);
 int ovpn_nl_key_swap_notify(struct ovpn_peer *peer, u8 key_id);
 
 #endif /* _NET_OVPN_NETLINK_H_ */
diff --git a/drivers/net/ovpn/peer.c b/drivers/net/ovpn/peer.c
index 3af4531393f66..0b1d26388dba9 100644
--- a/drivers/net/ovpn/peer.c
+++ b/drivers/net/ovpn/peer.c
@@ -706,6 +706,7 @@ static void ovpn_peer_remove(struct ovpn_peer *peer,
 	}
 
 	peer->delete_reason = reason;
+	ovpn_nl_peer_del_notify(peer);
 
 	/* append to provided list for later socket release and ref drop */
 	llist_add(&peer->release_entry, release_list);

From 78b9a9c15181dd44544ce26acaa1d7d7dd7610a2 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:57 +0100
Subject: [PATCH 2563/2753] ovpn: add basic ethtool support

Implement support for basic ethtool functionality.

Note that ovpn is a virtual device driver, therefore
various ethtool APIs are just not meaningful and thus
not implemented.

Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ovpn/main.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/drivers/net/ovpn/main.c b/drivers/net/ovpn/main.c
index 0e016d39c95e5..46abbbed384a4 100644
--- a/drivers/net/ovpn/main.c
+++ b/drivers/net/ovpn/main.c
@@ -7,6 +7,7 @@
  *		James Yonan <james@openvpn.net>
  */
 
+#include <linux/ethtool.h>
 #include <linux/genetlink.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -135,6 +136,19 @@ bool ovpn_dev_is_valid(const struct net_device *dev)
 	return dev->netdev_ops == &ovpn_netdev_ops;
 }
 
+static void ovpn_get_drvinfo(struct net_device *dev,
+			     struct ethtool_drvinfo *info)
+{
+	strscpy(info->driver, "ovpn", sizeof(info->driver));
+	strscpy(info->bus_info, "ovpn", sizeof(info->bus_info));
+}
+
+static const struct ethtool_ops ovpn_ethtool_ops = {
+	.get_drvinfo		= ovpn_get_drvinfo,
+	.get_link		= ethtool_op_get_link,
+	.get_ts_info		= ethtool_op_get_ts_info,
+};
+
 static void ovpn_setup(struct net_device *dev)
 {
 	netdev_features_t feat = NETIF_F_SG | NETIF_F_GSO |
@@ -144,6 +158,7 @@ static void ovpn_setup(struct net_device *dev)
 
 	dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS;
 
+	dev->ethtool_ops = &ovpn_ethtool_ops;
 	dev->netdev_ops = &ovpn_netdev_ops;
 
 	dev->priv_destructor = ovpn_priv_free;

From 487c2a60d88751edad0c8b68e55a1ac3d33ab533 Mon Sep 17 00:00:00 2001
From: Antonio Quartulli <antonio@openvpn.net>
Date: Tue, 18 Mar 2025 02:40:58 +0100
Subject: [PATCH 2564/2753] testing/selftests: add test tool and scripts for
 ovpn module

The ovpn-cli tool can be compiled and used as selftest for the ovpn
kernel module.

[NOTE: it depends on libmedtls for decoding base64-encoded keys]

ovpn-cli implements the netlink and RTNL APIs and can thus be integrated
in any script for more automated testing.

Along with the tool, a bunch of scripts are provided that perform basic
functionality tests by means of network namespaces.
These scripts take part to the kselftest automation.

The output of the scripts, which will appear in the kselftest
reports, is a list of steps performed by the scripts plus some
output coming from the execution of `ping`, `iperf` and `ovpn-cli`
itself.
In general it is useful only in case of failure, in order to
understand which step has failed and why.

Please note: since peer sockets are tied to the userspace
process that created them (i.e. exiting the process will result
in closing the socket), every run of ovpn-cli that created
one will go to background and enter pause(), waiting for the
signal which will allow it to terminate.
Termination is accomplished at the end of each script by
issuing a killall command.

Cc: linux-kselftest@vger.kernel.org
Cc: Shuah Khan <skhan@linuxfoundation.org>
Signed-off-by: Antonio Quartulli <antonio@openvpn.net>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS                                   |    1 +
 tools/testing/selftests/Makefile              |    1 +
 tools/testing/selftests/net/ovpn/.gitignore   |    2 +
 tools/testing/selftests/net/ovpn/Makefile     |   31 +
 tools/testing/selftests/net/ovpn/common.sh    |   92 +
 tools/testing/selftests/net/ovpn/config       |   10 +
 tools/testing/selftests/net/ovpn/data64.key   |    5 +
 tools/testing/selftests/net/ovpn/ovpn-cli.c   | 2395 +++++++++++++++++
 .../testing/selftests/net/ovpn/tcp_peers.txt  |    5 +
 .../selftests/net/ovpn/test-chachapoly.sh     |    9 +
 .../net/ovpn/test-close-socket-tcp.sh         |    9 +
 .../selftests/net/ovpn/test-close-socket.sh   |   45 +
 .../testing/selftests/net/ovpn/test-float.sh  |    9 +
 tools/testing/selftests/net/ovpn/test-tcp.sh  |    9 +
 tools/testing/selftests/net/ovpn/test.sh      |  113 +
 .../testing/selftests/net/ovpn/udp_peers.txt  |    5 +
 16 files changed, 2741 insertions(+)
 create mode 100644 tools/testing/selftests/net/ovpn/.gitignore
 create mode 100644 tools/testing/selftests/net/ovpn/Makefile
 create mode 100644 tools/testing/selftests/net/ovpn/common.sh
 create mode 100644 tools/testing/selftests/net/ovpn/config
 create mode 100644 tools/testing/selftests/net/ovpn/data64.key
 create mode 100644 tools/testing/selftests/net/ovpn/ovpn-cli.c
 create mode 100644 tools/testing/selftests/net/ovpn/tcp_peers.txt
 create mode 100755 tools/testing/selftests/net/ovpn/test-chachapoly.sh
 create mode 100755 tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
 create mode 100755 tools/testing/selftests/net/ovpn/test-close-socket.sh
 create mode 100755 tools/testing/selftests/net/ovpn/test-float.sh
 create mode 100755 tools/testing/selftests/net/ovpn/test-tcp.sh
 create mode 100755 tools/testing/selftests/net/ovpn/test.sh
 create mode 100644 tools/testing/selftests/net/ovpn/udp_peers.txt

diff --git a/MAINTAINERS b/MAINTAINERS
index 5d058e9b4628c..5255a8f251bf6 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17813,6 +17813,7 @@ T:	git https://github.com/OpenVPN/linux-kernel-ovpn.git
 F:	Documentation/netlink/specs/ovpn.yaml
 F:	drivers/net/ovpn/
 F:	include/uapi/linux/ovpn.h
+F:	tools/testing/selftests/net/ovpn/
 
 OPENVSWITCH
 M:	Pravin B Shelar <pshelar@ovn.org>
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 8daac70c2f9d2..042be9a42b2e2 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -69,6 +69,7 @@ TARGETS += net/hsr
 TARGETS += net/mptcp
 TARGETS += net/netfilter
 TARGETS += net/openvswitch
+TARGETS += net/ovpn
 TARGETS += net/packetdrill
 TARGETS += net/rds
 TARGETS += net/tcp_ao
diff --git a/tools/testing/selftests/net/ovpn/.gitignore b/tools/testing/selftests/net/ovpn/.gitignore
new file mode 100644
index 0000000000000..ee44c081ca7c0
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/.gitignore
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0+
+ovpn-cli
diff --git a/tools/testing/selftests/net/ovpn/Makefile b/tools/testing/selftests/net/ovpn/Makefile
new file mode 100644
index 0000000000000..2d102878cb6dd
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/Makefile
@@ -0,0 +1,31 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+CFLAGS = -pedantic -Wextra -Wall -Wl,--no-as-needed -g -O0 -ggdb $(KHDR_INCLUDES)
+VAR_CFLAGS = $(shell pkg-config --cflags libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_CFLAGS),)
+VAR_CFLAGS = -I/usr/include/libnl3
+endif
+CFLAGS += $(VAR_CFLAGS)
+
+
+LDLIBS = -lmbedtls -lmbedcrypto
+VAR_LDLIBS = $(shell pkg-config --libs libnl-3.0 libnl-genl-3.0 2>/dev/null)
+ifeq ($(VAR_LDLIBS),)
+VAR_LDLIBS = -lnl-genl-3 -lnl-3
+endif
+LDLIBS += $(VAR_LDLIBS)
+
+
+TEST_FILES = common.sh
+
+TEST_PROGS = test.sh \
+	test-chachapoly.sh \
+	test-tcp.sh \
+	test-float.sh \
+	test-close-socket.sh \
+	test-close-socket-tcp.sh
+
+TEST_GEN_FILES := ovpn-cli
+
+include ../../lib.mk
diff --git a/tools/testing/selftests/net/ovpn/common.sh b/tools/testing/selftests/net/ovpn/common.sh
new file mode 100644
index 0000000000000..7502292a1ee03
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/common.sh
@@ -0,0 +1,92 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+UDP_PEERS_FILE=${UDP_PEERS_FILE:-udp_peers.txt}
+TCP_PEERS_FILE=${TCP_PEERS_FILE:-tcp_peers.txt}
+OVPN_CLI=${OVPN_CLI:-./ovpn-cli}
+ALG=${ALG:-aes}
+PROTO=${PROTO:-UDP}
+FLOAT=${FLOAT:-0}
+
+create_ns() {
+	ip netns add peer${1}
+}
+
+setup_ns() {
+	MODE="P2P"
+
+	if [ ${1} -eq 0 ]; then
+		MODE="MP"
+		for p in $(seq 1 ${NUM_PEERS}); do
+			ip link add veth${p} netns peer0 type veth peer name veth${p} netns peer${p}
+
+			ip -n peer0 addr add 10.10.${p}.1/24 dev veth${p}
+			ip -n peer0 link set veth${p} up
+
+			ip -n peer${p} addr add 10.10.${p}.2/24 dev veth${p}
+			ip -n peer${p} link set veth${p} up
+		done
+	fi
+
+	ip netns exec peer${1} ${OVPN_CLI} new_iface tun${1} $MODE
+	ip -n peer${1} addr add ${2} dev tun${1}
+	ip -n peer${1} link set tun${1} up
+}
+
+add_peer() {
+	if [ "${PROTO}" == "UDP" ]; then
+		if [ ${1} -eq 0 ]; then
+			ip netns exec peer0 ${OVPN_CLI} new_multi_peer tun0 1 ${UDP_PEERS_FILE}
+
+			for p in $(seq 1 ${NUM_PEERS}); do
+				ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 ${ALG} 0 \
+					data64.key
+			done
+		else
+			ip netns exec peer${1} ${OVPN_CLI} new_peer tun${1} ${1} 1 10.10.${1}.1 1
+			ip netns exec peer${1} ${OVPN_CLI} new_key tun${1} ${1} 1 0 ${ALG} 1 \
+				data64.key
+		fi
+	else
+		if [ ${1} -eq 0 ]; then
+			(ip netns exec peer0 ${OVPN_CLI} listen tun0 1 ${TCP_PEERS_FILE} && {
+				for p in $(seq 1 ${NUM_PEERS}); do
+					ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 1 0 \
+						${ALG} 0 data64.key
+				done
+			}) &
+			sleep 5
+		else
+			ip netns exec peer${1} ${OVPN_CLI} connect tun${1} ${1} 10.10.${1}.1 1 \
+				data64.key
+		fi
+	fi
+}
+
+cleanup() {
+	# some ovpn-cli processes sleep in background so they need manual poking
+	killall $(basename ${OVPN_CLI}) 2>/dev/null || true
+
+	# netns peer0 is deleted without erasing ifaces first
+	for p in $(seq 1 10); do
+		ip -n peer${p} link set tun${p} down 2>/dev/null || true
+		ip netns exec peer${p} ${OVPN_CLI} del_iface tun${p} 2>/dev/null || true
+	done
+	for p in $(seq 1 10); do
+		ip -n peer0 link del veth${p} 2>/dev/null || true
+	done
+	for p in $(seq 0 10); do
+		ip netns del peer${p} 2>/dev/null || true
+	done
+}
+
+if [ "${PROTO}" == "UDP" ]; then
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${UDP_PEERS_FILE} | awk '{print $1}')}
+else
+	NUM_PEERS=${NUM_PEERS:-$(wc -l ${TCP_PEERS_FILE} | awk '{print $1}')}
+fi
+
+
diff --git a/tools/testing/selftests/net/ovpn/config b/tools/testing/selftests/net/ovpn/config
new file mode 100644
index 0000000000000..71946ba9fa175
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/config
@@ -0,0 +1,10 @@
+CONFIG_NET=y
+CONFIG_INET=y
+CONFIG_STREAM_PARSER=y
+CONFIG_NET_UDP_TUNNEL=y
+CONFIG_DST_CACHE=y
+CONFIG_CRYPTO=y
+CONFIG_CRYPTO_AES=y
+CONFIG_CRYPTO_GCM=y
+CONFIG_CRYPTO_CHACHA20POLY1305=y
+CONFIG_OVPN=m
diff --git a/tools/testing/selftests/net/ovpn/data64.key b/tools/testing/selftests/net/ovpn/data64.key
new file mode 100644
index 0000000000000..a99e88c4e290f
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/data64.key
@@ -0,0 +1,5 @@
+jRqMACN7d7/aFQNT8S7jkrBD8uwrgHbG5OQZP2eu4R1Y7tfpS2bf5RHv06Vi163CGoaIiTX99R3B
+ia9ycAH8Wz1+9PWv51dnBLur9jbShlgZ2QHLtUc4a/gfT7zZwULXuuxdLnvR21DDeMBaTbkgbai9
+uvAa7ne1liIgGFzbv+Bas4HDVrygxIxuAnP5Qgc3648IJkZ0QEXPF+O9f0n5+QIvGCxkAUVx+5K6
+KIs+SoeWXnAopELmoGSjUpFtJbagXK82HfdqpuUxT2Tnuef0/14SzVE/vNleBNu2ZbyrSAaah8tE
+BofkPJUBFY+YQcfZNM5Dgrw3i+Bpmpq/gpdg5w==
diff --git a/tools/testing/selftests/net/ovpn/ovpn-cli.c b/tools/testing/selftests/net/ovpn/ovpn-cli.c
new file mode 100644
index 0000000000000..b6948b23e6b7f
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/ovpn-cli.c
@@ -0,0 +1,2395 @@
+// SPDX-License-Identifier: GPL-2.0
+/*  OpenVPN data channel accelerator
+ *
+ *  Copyright (C) 2020-2025 OpenVPN, Inc.
+ *
+ *  Author:	Antonio Quartulli <antonio@openvpn.net>
+ */
+
+#include <stdio.h>
+#include <inttypes.h>
+#include <stdbool.h>
+#include <string.h>
+#include <errno.h>
+#include <unistd.h>
+#include <arpa/inet.h>
+#include <net/if.h>
+#include <netinet/in.h>
+#include <time.h>
+
+#include <linux/ovpn.h>
+#include <linux/types.h>
+#include <linux/netlink.h>
+
+#include <netlink/socket.h>
+#include <netlink/netlink.h>
+#include <netlink/genl/genl.h>
+#include <netlink/genl/family.h>
+#include <netlink/genl/ctrl.h>
+
+#include <mbedtls/base64.h>
+#include <mbedtls/error.h>
+
+#include <sys/socket.h>
+
+/* defines to make checkpatch happy */
+#define strscpy strncpy
+#define __always_unused __attribute__((__unused__))
+
+/* libnl < 3.5.0 does not set the NLA_F_NESTED on its own, therefore we
+ * have to explicitly do it to prevent the kernel from failing upon
+ * parsing of the message
+ */
+#define nla_nest_start(_msg, _type) \
+	nla_nest_start(_msg, (_type) | NLA_F_NESTED)
+
+/* libnl < 3.11.0 does not implement nla_get_uint() */
+uint64_t ovpn_nla_get_uint(struct nlattr *attr)
+{
+	if (nla_len(attr) == sizeof(uint32_t))
+		return nla_get_u32(attr);
+	else
+		return nla_get_u64(attr);
+}
+
+typedef int (*ovpn_nl_cb)(struct nl_msg *msg, void *arg);
+
+enum ovpn_key_direction {
+	KEY_DIR_IN = 0,
+	KEY_DIR_OUT,
+};
+
+#define KEY_LEN (256 / 8)
+#define NONCE_LEN 8
+
+#define PEER_ID_UNDEF 0x00FFFFFF
+#define MAX_PEERS 10
+
+struct nl_ctx {
+	struct nl_sock *nl_sock;
+	struct nl_msg *nl_msg;
+	struct nl_cb *nl_cb;
+
+	int ovpn_dco_id;
+};
+
+enum ovpn_cmd {
+	CMD_INVALID,
+	CMD_NEW_IFACE,
+	CMD_DEL_IFACE,
+	CMD_LISTEN,
+	CMD_CONNECT,
+	CMD_NEW_PEER,
+	CMD_NEW_MULTI_PEER,
+	CMD_SET_PEER,
+	CMD_DEL_PEER,
+	CMD_GET_PEER,
+	CMD_NEW_KEY,
+	CMD_DEL_KEY,
+	CMD_GET_KEY,
+	CMD_SWAP_KEYS,
+	CMD_LISTEN_MCAST,
+};
+
+struct ovpn_ctx {
+	enum ovpn_cmd cmd;
+
+	__u8 key_enc[KEY_LEN];
+	__u8 key_dec[KEY_LEN];
+	__u8 nonce[NONCE_LEN];
+
+	enum ovpn_cipher_alg cipher;
+
+	sa_family_t sa_family;
+
+	unsigned long peer_id;
+	unsigned long lport;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} remote;
+
+	union {
+		struct sockaddr_in in4;
+		struct sockaddr_in6 in6;
+	} peer_ip;
+
+	bool peer_ip_set;
+
+	unsigned int ifindex;
+	char ifname[IFNAMSIZ];
+	enum ovpn_mode mode;
+	bool mode_set;
+
+	int socket;
+	int cli_sockets[MAX_PEERS];
+
+	__u32 keepalive_interval;
+	__u32 keepalive_timeout;
+
+	enum ovpn_key_direction key_dir;
+	enum ovpn_key_slot key_slot;
+	int key_id;
+
+	const char *peers_file;
+};
+
+static int ovpn_nl_recvmsgs(struct nl_ctx *ctx)
+{
+	int ret;
+
+	ret = nl_recvmsgs(ctx->nl_sock, ctx->nl_cb);
+
+	switch (ret) {
+	case -NLE_INTR:
+		fprintf(stderr,
+			"netlink received interrupt due to signal - ignoring\n");
+		break;
+	case -NLE_NOMEM:
+		fprintf(stderr, "netlink out of memory error\n");
+		break;
+	case -NLE_AGAIN:
+		fprintf(stderr,
+			"netlink reports blocking read - aborting wait\n");
+		break;
+	default:
+		if (ret)
+			fprintf(stderr, "netlink reports error (%d): %s\n",
+				ret, nl_geterror(-ret));
+		break;
+	}
+
+	return ret;
+}
+
+static struct nl_ctx *nl_ctx_alloc_flags(struct ovpn_ctx *ovpn, int cmd,
+					 int flags)
+{
+	struct nl_ctx *ctx;
+	int err, ret;
+
+	ctx = calloc(1, sizeof(*ctx));
+	if (!ctx)
+		return NULL;
+
+	ctx->nl_sock = nl_socket_alloc();
+	if (!ctx->nl_sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(ctx->nl_sock, 8192, 8192);
+
+	ret = genl_connect(ctx->nl_sock);
+	if (ret) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_sock;
+	}
+
+	/* enable Extended ACK for detailed error reporting */
+	err = 1;
+	setsockopt(nl_socket_get_fd(ctx->nl_sock), SOL_NETLINK, NETLINK_EXT_ACK,
+		   &err, sizeof(err));
+
+	ctx->ovpn_dco_id = genl_ctrl_resolve(ctx->nl_sock, OVPN_FAMILY_NAME);
+	if (ctx->ovpn_dco_id < 0) {
+		fprintf(stderr, "cannot find ovpn_dco netlink component: %d\n",
+			ctx->ovpn_dco_id);
+		goto err_free;
+	}
+
+	ctx->nl_msg = nlmsg_alloc();
+	if (!ctx->nl_msg) {
+		fprintf(stderr, "cannot allocate netlink message\n");
+		goto err_sock;
+	}
+
+	ctx->nl_cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!ctx->nl_cb) {
+		fprintf(stderr, "failed to allocate netlink callback\n");
+		goto err_msg;
+	}
+
+	nl_socket_set_cb(ctx->nl_sock, ctx->nl_cb);
+
+	genlmsg_put(ctx->nl_msg, 0, 0, ctx->ovpn_dco_id, 0, flags, cmd, 0);
+
+	if (ovpn->ifindex > 0)
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_IFINDEX, ovpn->ifindex);
+
+	return ctx;
+nla_put_failure:
+err_msg:
+	nlmsg_free(ctx->nl_msg);
+err_sock:
+	nl_socket_free(ctx->nl_sock);
+err_free:
+	free(ctx);
+	return NULL;
+}
+
+static struct nl_ctx *nl_ctx_alloc(struct ovpn_ctx *ovpn, int cmd)
+{
+	return nl_ctx_alloc_flags(ovpn, cmd, 0);
+}
+
+static void nl_ctx_free(struct nl_ctx *ctx)
+{
+	if (!ctx)
+		return;
+
+	nl_socket_free(ctx->nl_sock);
+	nlmsg_free(ctx->nl_msg);
+	nl_cb_put(ctx->nl_cb);
+	free(ctx);
+}
+
+static int ovpn_nl_cb_error(struct sockaddr_nl (*nla)__always_unused,
+			    struct nlmsgerr *err, void *arg)
+{
+	struct nlmsghdr *nlh = (struct nlmsghdr *)err - 1;
+	struct nlattr *tb_msg[NLMSGERR_ATTR_MAX + 1];
+	int len = nlh->nlmsg_len;
+	struct nlattr *attrs;
+	int *ret = arg;
+	int ack_len = sizeof(*nlh) + sizeof(int) + sizeof(*nlh);
+
+	*ret = err->error;
+
+	if (!(nlh->nlmsg_flags & NLM_F_ACK_TLVS))
+		return NL_STOP;
+
+	if (!(nlh->nlmsg_flags & NLM_F_CAPPED))
+		ack_len += err->msg.nlmsg_len - sizeof(*nlh);
+
+	if (len <= ack_len)
+		return NL_STOP;
+
+	attrs = (void *)((uint8_t *)nlh + ack_len);
+	len -= ack_len;
+
+	nla_parse(tb_msg, NLMSGERR_ATTR_MAX, attrs, len, NULL);
+	if (tb_msg[NLMSGERR_ATTR_MSG]) {
+		len = strnlen((char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]),
+			      nla_len(tb_msg[NLMSGERR_ATTR_MSG]));
+		fprintf(stderr, "kernel error: %*s\n", len,
+			(char *)nla_data(tb_msg[NLMSGERR_ATTR_MSG]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_NEST]) {
+		fprintf(stderr, "missing required nesting type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_NEST]));
+	}
+
+	if (tb_msg[NLMSGERR_ATTR_MISS_TYPE]) {
+		fprintf(stderr, "missing required attribute type %u\n",
+			nla_get_u32(tb_msg[NLMSGERR_ATTR_MISS_TYPE]));
+	}
+
+	return NL_STOP;
+}
+
+static int ovpn_nl_cb_finish(struct nl_msg (*msg)__always_unused,
+			     void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_SKIP;
+}
+
+static int ovpn_nl_cb_ack(struct nl_msg (*msg)__always_unused,
+			  void *arg)
+{
+	int *status = arg;
+
+	*status = 0;
+	return NL_STOP;
+}
+
+static int ovpn_nl_msg_send(struct nl_ctx *ctx, ovpn_nl_cb cb)
+{
+	int status = 1;
+
+	nl_cb_err(ctx->nl_cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_FINISH, NL_CB_CUSTOM, ovpn_nl_cb_finish,
+		  &status);
+	nl_cb_set(ctx->nl_cb, NL_CB_ACK, NL_CB_CUSTOM, ovpn_nl_cb_ack, &status);
+
+	if (cb)
+		nl_cb_set(ctx->nl_cb, NL_CB_VALID, NL_CB_CUSTOM, cb, ctx);
+
+	nl_send_auto_complete(ctx->nl_sock, ctx->nl_msg);
+
+	while (status == 1)
+		ovpn_nl_recvmsgs(ctx);
+
+	if (status < 0)
+		fprintf(stderr, "failed to send netlink message: %s (%d)\n",
+			strerror(-status), status);
+
+	return status;
+}
+
+static int ovpn_parse_key(const char *file, struct ovpn_ctx *ctx)
+{
+	int idx_enc, idx_dec, ret = -1;
+	unsigned char *ckey = NULL;
+	__u8 *bkey = NULL;
+	size_t olen = 0;
+	long ckey_len;
+	FILE *fp;
+
+	fp = fopen(file, "r");
+	if (!fp) {
+		fprintf(stderr, "cannot open: %s\n", file);
+		return -1;
+	}
+
+	/* get file size */
+	fseek(fp, 0L, SEEK_END);
+	ckey_len = ftell(fp);
+	rewind(fp);
+
+	/* if the file is longer, let's just read a portion */
+	if (ckey_len > 256)
+		ckey_len = 256;
+
+	ckey = malloc(ckey_len);
+	if (!ckey)
+		goto err;
+
+	ret = fread(ckey, 1, ckey_len, fp);
+	if (ret != ckey_len) {
+		fprintf(stderr,
+			"couldn't read enough data from key file: %dbytes read\n",
+			ret);
+		goto err;
+	}
+
+	olen = 0;
+	ret = mbedtls_base64_decode(NULL, 0, &olen, ckey, ckey_len);
+	if (ret != MBEDTLS_ERR_BASE64_BUFFER_TOO_SMALL) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error1: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	bkey = malloc(olen);
+	if (!bkey) {
+		fprintf(stderr, "cannot allocate binary key buffer\n");
+		goto err;
+	}
+
+	ret = mbedtls_base64_decode(bkey, olen, &olen, ckey, ckey_len);
+	if (ret) {
+		char buf[256];
+
+		mbedtls_strerror(ret, buf, sizeof(buf));
+		fprintf(stderr, "unexpected base64 error2: %s (%d)\n", buf,
+			ret);
+
+		goto err;
+	}
+
+	if (olen < 2 * KEY_LEN + NONCE_LEN) {
+		fprintf(stderr,
+			"not enough data in key file, found %zdB but needs %dB\n",
+			olen, 2 * KEY_LEN + NONCE_LEN);
+		goto err;
+	}
+
+	switch (ctx->key_dir) {
+	case KEY_DIR_IN:
+		idx_enc = 0;
+		idx_dec = 1;
+		break;
+	case KEY_DIR_OUT:
+		idx_enc = 1;
+		idx_dec = 0;
+		break;
+	default:
+		goto err;
+	}
+
+	memcpy(ctx->key_enc, bkey + KEY_LEN * idx_enc, KEY_LEN);
+	memcpy(ctx->key_dec, bkey + KEY_LEN * idx_dec, KEY_LEN);
+	memcpy(ctx->nonce, bkey + 2 * KEY_LEN, NONCE_LEN);
+
+	ret = 0;
+
+err:
+	fclose(fp);
+	free(bkey);
+	free(ckey);
+
+	return ret;
+}
+
+static int ovpn_parse_cipher(const char *cipher, struct ovpn_ctx *ctx)
+{
+	if (strcmp(cipher, "aes") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_AES_GCM;
+	else if (strcmp(cipher, "chachapoly") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_CHACHA20_POLY1305;
+	else if (strcmp(cipher, "none") == 0)
+		ctx->cipher = OVPN_CIPHER_ALG_NONE;
+	else
+		return -ENOTSUP;
+
+	return 0;
+}
+
+static int ovpn_parse_key_direction(const char *dir, struct ovpn_ctx *ctx)
+{
+	int in_dir;
+
+	in_dir = strtoll(dir, NULL, 10);
+	switch (in_dir) {
+	case KEY_DIR_IN:
+	case KEY_DIR_OUT:
+		ctx->key_dir = in_dir;
+		break;
+	default:
+		fprintf(stderr,
+			"invalid key direction provided. Can be 0 or 1 only\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_socket(struct ovpn_ctx *ctx, sa_family_t family, int proto)
+{
+	struct sockaddr_storage local_sock = { 0 };
+	struct sockaddr_in6 *in6;
+	struct sockaddr_in *in;
+	int ret, s, sock_type;
+	size_t sock_len;
+
+	if (proto == IPPROTO_UDP)
+		sock_type = SOCK_DGRAM;
+	else if (proto == IPPROTO_TCP)
+		sock_type = SOCK_STREAM;
+	else
+		return -EINVAL;
+
+	s = socket(family, sock_type, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (family) {
+	case AF_INET:
+		in = (struct sockaddr_in *)&local_sock;
+		in->sin_family = family;
+		in->sin_port = htons(ctx->lport);
+		in->sin_addr.s_addr = htonl(INADDR_ANY);
+		sock_len = sizeof(*in);
+		break;
+	case AF_INET6:
+		in6 = (struct sockaddr_in6 *)&local_sock;
+		in6->sin6_family = family;
+		in6->sin6_port = htons(ctx->lport);
+		in6->sin6_addr = in6addr_any;
+		sock_len = sizeof(*in6);
+		break;
+	default:
+		return -1;
+	}
+
+	int opt = 1;
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEADDR, &opt, sizeof(opt));
+
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEADDR");
+		return ret;
+	}
+
+	ret = setsockopt(s, SOL_SOCKET, SO_REUSEPORT, &opt, sizeof(opt));
+	if (ret < 0) {
+		perror("setsockopt for SO_REUSEPORT");
+		return ret;
+	}
+
+	if (family == AF_INET6) {
+		opt = 0;
+		if (setsockopt(s, IPPROTO_IPV6, IPV6_V6ONLY, &opt,
+			       sizeof(opt))) {
+			perror("failed to set IPV6_V6ONLY");
+			return -1;
+		}
+	}
+
+	ret = bind(s, (struct sockaddr *)&local_sock, sock_len);
+	if (ret < 0) {
+		perror("cannot bind socket");
+		goto err_socket;
+	}
+
+	ctx->socket = s;
+	ctx->sa_family = family;
+	return 0;
+
+err_socket:
+	close(s);
+	return -1;
+}
+
+static int ovpn_udp_socket(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	return ovpn_socket(ctx, family, IPPROTO_UDP);
+}
+
+static int ovpn_listen(struct ovpn_ctx *ctx, sa_family_t family)
+{
+	int ret;
+
+	ret = ovpn_socket(ctx, family, IPPROTO_TCP);
+	if (ret < 0)
+		return ret;
+
+	ret = listen(ctx->socket, 10);
+	if (ret < 0) {
+		perror("listen");
+		close(ctx->socket);
+		return -1;
+	}
+
+	return 0;
+}
+
+static int ovpn_accept(struct ovpn_ctx *ctx)
+{
+	socklen_t socklen;
+	int ret;
+
+	socklen = sizeof(ctx->remote);
+	ret = accept(ctx->socket, (struct sockaddr *)&ctx->remote, &socklen);
+	if (ret < 0) {
+		perror("accept");
+		goto err;
+	}
+
+	fprintf(stderr, "Connection received!\n");
+
+	switch (socklen) {
+	case sizeof(struct sockaddr_in):
+	case sizeof(struct sockaddr_in6):
+		break;
+	default:
+		fprintf(stderr, "error: expecting IPv4 or IPv6 connection\n");
+		close(ret);
+		ret = -EINVAL;
+		goto err;
+	}
+
+	return ret;
+err:
+	close(ctx->socket);
+	return ret;
+}
+
+static int ovpn_connect(struct ovpn_ctx *ovpn)
+{
+	socklen_t socklen;
+	int s, ret;
+
+	s = socket(ovpn->remote.in4.sin_family, SOCK_STREAM, 0);
+	if (s < 0) {
+		perror("cannot create socket");
+		return -1;
+	}
+
+	switch (ovpn->remote.in4.sin_family) {
+	case AF_INET:
+		socklen = sizeof(struct sockaddr_in);
+		break;
+	case AF_INET6:
+		socklen = sizeof(struct sockaddr_in6);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	ret = connect(s, (struct sockaddr *)&ovpn->remote, socklen);
+	if (ret < 0) {
+		perror("connect");
+		goto err;
+	}
+
+	fprintf(stderr, "connected\n");
+
+	ovpn->socket = s;
+
+	return 0;
+err:
+	close(s);
+	return ret;
+}
+
+static int ovpn_new_peer(struct ovpn_ctx *ovpn, bool is_tcp)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_SOCKET, ovpn->socket);
+
+	if (!is_tcp) {
+		switch (ovpn->remote.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV4,
+				    ovpn->remote.in4.sin_addr.s_addr);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in4.sin_port);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_REMOTE_IPV6,
+				sizeof(ovpn->remote.in6.sin6_addr),
+				&ovpn->remote.in6.sin6_addr);
+			NLA_PUT_U32(ctx->nl_msg,
+				    OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID,
+				    ovpn->remote.in6.sin6_scope_id);
+			NLA_PUT_U16(ctx->nl_msg, OVPN_A_PEER_REMOTE_PORT,
+				    ovpn->remote.in6.sin6_port);
+			break;
+		default:
+			fprintf(stderr,
+				"Invalid family for remote socket address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	if (ovpn->peer_ip_set) {
+		switch (ovpn->peer_ip.in4.sin_family) {
+		case AF_INET:
+			NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_VPN_IPV4,
+				    ovpn->peer_ip.in4.sin_addr.s_addr);
+			break;
+		case AF_INET6:
+			NLA_PUT(ctx->nl_msg, OVPN_A_PEER_VPN_IPV6,
+				sizeof(struct in6_addr),
+				&ovpn->peer_ip.in6.sin6_addr);
+			break;
+		default:
+			fprintf(stderr, "Invalid family for peer address\n");
+			goto nla_put_failure;
+		}
+	}
+
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_set_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_SET);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_INTERVAL,
+		    ovpn->keepalive_interval);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_KEEPALIVE_TIMEOUT,
+		    ovpn->keepalive_timeout);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_peer(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_PEER_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, attr);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_peer(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *pattrs[OVPN_A_PEER_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	__u16 rport = 0, lport = 0;
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_PEER]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(pattrs, OVPN_A_PEER_MAX, nla_data(attrs[OVPN_A_PEER]),
+		  nla_len(attrs[OVPN_A_PEER]), NULL);
+
+	if (pattrs[OVPN_A_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_ID]));
+
+	if (pattrs[OVPN_A_PEER_SOCKET_NETNSID])
+		fprintf(stderr, "\tsocket NetNS ID: %d\n",
+			nla_get_s32(pattrs[OVPN_A_PEER_SOCKET_NETNSID]));
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV4]) {
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(pattrs[OVPN_A_PEER_VPN_IPV4]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv4: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_VPN_IPV6]) {
+		char buf[INET6_ADDRSTRLEN];
+
+		inet_ntop(AF_INET6, nla_data(pattrs[OVPN_A_PEER_VPN_IPV6]),
+			  buf, sizeof(buf));
+		fprintf(stderr, "\tVPN IPv6: %s\n", buf);
+	}
+
+	if (pattrs[OVPN_A_PEER_LOCAL_PORT])
+		lport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_LOCAL_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_PORT])
+		rport = ntohs(nla_get_u16(pattrs[OVPN_A_PEER_REMOTE_PORT]));
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV6]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV6];
+		char buf[INET6_ADDRSTRLEN];
+		int scope_id = -1;
+
+		if (pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID]) {
+			void *p = pattrs[OVPN_A_PEER_REMOTE_IPV6_SCOPE_ID];
+
+			scope_id = nla_get_u32(p);
+		}
+
+		inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu (scope-id: %u)\n", buf, rport,
+			scope_id);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV6]) {
+			void *ip = pattrs[OVPN_A_PEER_LOCAL_IPV6];
+
+			inet_ntop(AF_INET6, nla_data(ip), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_REMOTE_IPV4]) {
+		void *ip = pattrs[OVPN_A_PEER_REMOTE_IPV4];
+		char buf[INET_ADDRSTRLEN];
+
+		inet_ntop(AF_INET, nla_data(ip), buf, sizeof(buf));
+		fprintf(stderr, "\tRemote: %s:%hu\n", buf, rport);
+
+		if (pattrs[OVPN_A_PEER_LOCAL_IPV4]) {
+			void *p = pattrs[OVPN_A_PEER_LOCAL_IPV4];
+
+			inet_ntop(AF_INET, nla_data(p), buf, sizeof(buf));
+			fprintf(stderr, "\tLocal: %s:%hu\n", buf, lport);
+		}
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL]) {
+		void *p = pattrs[OVPN_A_PEER_KEEPALIVE_INTERVAL];
+
+		fprintf(stderr, "\tKeepalive interval: %u sec\n",
+			nla_get_u32(p));
+	}
+
+	if (pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT])
+		fprintf(stderr, "\tKeepalive timeout: %u sec\n",
+			nla_get_u32(pattrs[OVPN_A_PEER_KEEPALIVE_TIMEOUT]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_BYTES])
+		fprintf(stderr, "\tVPN RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_BYTES])
+		fprintf(stderr, "\tVPN TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_VPN_RX_PACKETS])
+		fprintf(stderr, "\tVPN RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_VPN_TX_PACKETS])
+		fprintf(stderr, "\tVPN TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_VPN_TX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_BYTES])
+		fprintf(stderr, "\tLINK RX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_BYTES])
+		fprintf(stderr, "\tLINK TX bytes: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_BYTES]));
+
+	if (pattrs[OVPN_A_PEER_LINK_RX_PACKETS])
+		fprintf(stderr, "\tLINK RX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_RX_PACKETS]));
+
+	if (pattrs[OVPN_A_PEER_LINK_TX_PACKETS])
+		fprintf(stderr, "\tLINK TX packets: %" PRIu64 "\n",
+			ovpn_nla_get_uint(pattrs[OVPN_A_PEER_LINK_TX_PACKETS]));
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_peer(struct ovpn_ctx *ovpn)
+{
+	int flags = 0, ret = -1;
+	struct nlattr *attr;
+	struct nl_ctx *ctx;
+
+	if (ovpn->peer_id == PEER_ID_UNDEF)
+		flags = NLM_F_DUMP;
+
+	ctx = nl_ctx_alloc_flags(ovpn, OVPN_CMD_PEER_GET, flags);
+	if (!ctx)
+		return -ENOMEM;
+
+	if (ovpn->peer_id != PEER_ID_UNDEF) {
+		attr = nla_nest_start(ctx->nl_msg, OVPN_A_PEER);
+		NLA_PUT_U32(ctx->nl_msg, OVPN_A_PEER_ID, ovpn->peer_id);
+		nla_nest_end(ctx->nl_msg, attr);
+	}
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_peer);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_new_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf, *key_dir;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_NEW);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_KEY_ID, ovpn->key_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_CIPHER_ALG, ovpn->cipher);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_ENCRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_enc);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	key_dir = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF_DECRYPT_DIR);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_CIPHER_KEY, KEY_LEN, ovpn->key_dec);
+	NLA_PUT(ctx->nl_msg, OVPN_A_KEYDIR_NONCE_TAIL, NONCE_LEN, ovpn->nonce);
+	nla_nest_end(ctx->nl_msg, key_dir);
+
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_del_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_DEL);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_handle_key(struct nl_msg *msg, void (*arg)__always_unused)
+{
+	struct nlattr *kattrs[OVPN_A_KEYCONF_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+
+	nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!attrs[OVPN_A_KEYCONF]) {
+		fprintf(stderr, "no packet content in netlink message\n");
+		return NL_SKIP;
+	}
+
+	nla_parse(kattrs, OVPN_A_KEYCONF_MAX, nla_data(attrs[OVPN_A_KEYCONF]),
+		  nla_len(attrs[OVPN_A_KEYCONF]), NULL);
+
+	if (kattrs[OVPN_A_KEYCONF_PEER_ID])
+		fprintf(stderr, "* Peer %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_PEER_ID]));
+	if (kattrs[OVPN_A_KEYCONF_SLOT]) {
+		fprintf(stderr, "\t- Slot: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT])) {
+		case OVPN_KEY_SLOT_PRIMARY:
+			fprintf(stderr, "primary\n");
+			break;
+		case OVPN_KEY_SLOT_SECONDARY:
+			fprintf(stderr, "secondary\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_SLOT]));
+			break;
+		}
+	}
+	if (kattrs[OVPN_A_KEYCONF_KEY_ID])
+		fprintf(stderr, "\t- Key ID: %u\n",
+			nla_get_u32(kattrs[OVPN_A_KEYCONF_KEY_ID]));
+	if (kattrs[OVPN_A_KEYCONF_CIPHER_ALG]) {
+		fprintf(stderr, "\t- Cipher: ");
+		switch (nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG])) {
+		case OVPN_CIPHER_ALG_NONE:
+			fprintf(stderr, "none\n");
+			break;
+		case OVPN_CIPHER_ALG_AES_GCM:
+			fprintf(stderr, "aes-gcm\n");
+			break;
+		case OVPN_CIPHER_ALG_CHACHA20_POLY1305:
+			fprintf(stderr, "chacha20poly1305\n");
+			break;
+		default:
+			fprintf(stderr, "invalid (%u)\n",
+				nla_get_u32(kattrs[OVPN_A_KEYCONF_CIPHER_ALG]));
+			break;
+		}
+	}
+
+	return NL_SKIP;
+}
+
+static int ovpn_get_key(struct ovpn_ctx *ovpn)
+{
+	struct nlattr *keyconf;
+	struct nl_ctx *ctx;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_GET);
+	if (!ctx)
+		return -ENOMEM;
+
+	keyconf = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_SLOT, ovpn->key_slot);
+	nla_nest_end(ctx->nl_msg, keyconf);
+
+	ret = ovpn_nl_msg_send(ctx, ovpn_handle_key);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+static int ovpn_swap_keys(struct ovpn_ctx *ovpn)
+{
+	struct nl_ctx *ctx;
+	struct nlattr *kc;
+	int ret = -1;
+
+	ctx = nl_ctx_alloc(ovpn, OVPN_CMD_KEY_SWAP);
+	if (!ctx)
+		return -ENOMEM;
+
+	kc = nla_nest_start(ctx->nl_msg, OVPN_A_KEYCONF);
+	NLA_PUT_U32(ctx->nl_msg, OVPN_A_KEYCONF_PEER_ID, ovpn->peer_id);
+	nla_nest_end(ctx->nl_msg, kc);
+
+	ret = ovpn_nl_msg_send(ctx, NULL);
+nla_put_failure:
+	nl_ctx_free(ctx);
+	return ret;
+}
+
+/* Helper function used to easily add attributes to a rtnl message */
+static int ovpn_addattr(struct nlmsghdr *n, int maxlen, int type,
+			const void *data, int alen)
+{
+	int len = RTA_LENGTH(alen);
+	struct rtattr *rta;
+
+	if ((int)(NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len)) > maxlen)	{
+		fprintf(stderr, "%s: rtnl: message exceeded bound of %d\n",
+			__func__, maxlen);
+		return -EMSGSIZE;
+	}
+
+	rta = nlmsg_tail(n);
+	rta->rta_type = type;
+	rta->rta_len = len;
+
+	if (!data)
+		memset(RTA_DATA(rta), 0, alen);
+	else
+		memcpy(RTA_DATA(rta), data, alen);
+
+	n->nlmsg_len = NLMSG_ALIGN(n->nlmsg_len) + RTA_ALIGN(len);
+
+	return 0;
+}
+
+static struct rtattr *ovpn_nest_start(struct nlmsghdr *msg, size_t max_size,
+				      int attr)
+{
+	struct rtattr *nest = nlmsg_tail(msg);
+
+	if (ovpn_addattr(msg, max_size, attr, NULL, 0) < 0)
+		return NULL;
+
+	return nest;
+}
+
+static void ovpn_nest_end(struct nlmsghdr *msg, struct rtattr *nest)
+{
+	nest->rta_len = (uint8_t *)nlmsg_tail(msg) - (uint8_t *)nest;
+}
+
+#define RT_SNDBUF_SIZE (1024 * 2)
+#define RT_RCVBUF_SIZE (1024 * 4)
+
+/* Open RTNL socket */
+static int ovpn_rt_socket(void)
+{
+	int sndbuf = RT_SNDBUF_SIZE, rcvbuf = RT_RCVBUF_SIZE, fd;
+
+	fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (fd < 0) {
+		fprintf(stderr, "%s: cannot open netlink socket\n", __func__);
+		return fd;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_SNDBUF, &sndbuf,
+		       sizeof(sndbuf)) < 0) {
+		fprintf(stderr, "%s: SO_SNDBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &rcvbuf,
+		       sizeof(rcvbuf)) < 0) {
+		fprintf(stderr, "%s: SO_RCVBUF\n", __func__);
+		close(fd);
+		return -1;
+	}
+
+	return fd;
+}
+
+/* Bind socket to Netlink subsystem */
+static int ovpn_rt_bind(int fd, uint32_t groups)
+{
+	struct sockaddr_nl local = { 0 };
+	socklen_t addr_len;
+
+	local.nl_family = AF_NETLINK;
+	local.nl_groups = groups;
+
+	if (bind(fd, (struct sockaddr *)&local, sizeof(local)) < 0) {
+		fprintf(stderr, "%s: cannot bind netlink socket: %d\n",
+			__func__, errno);
+		return -errno;
+	}
+
+	addr_len = sizeof(local);
+	if (getsockname(fd, (struct sockaddr *)&local, &addr_len) < 0) {
+		fprintf(stderr, "%s: cannot getsockname: %d\n", __func__,
+			errno);
+		return -errno;
+	}
+
+	if (addr_len != sizeof(local)) {
+		fprintf(stderr, "%s: wrong address length %d\n", __func__,
+			addr_len);
+		return -EINVAL;
+	}
+
+	if (local.nl_family != AF_NETLINK) {
+		fprintf(stderr, "%s: wrong address family %d\n", __func__,
+			local.nl_family);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+typedef int (*ovpn_parse_reply_cb)(struct nlmsghdr *msg, void *arg);
+
+/* Send Netlink message and run callback on reply (if specified) */
+static int ovpn_rt_send(struct nlmsghdr *payload, pid_t peer,
+			unsigned int groups, ovpn_parse_reply_cb cb,
+			void *arg_cb)
+{
+	int len, rem_len, fd, ret, rcv_len;
+	struct sockaddr_nl nladdr = { 0 };
+	struct nlmsgerr *err;
+	struct nlmsghdr *h;
+	char buf[1024 * 16];
+	struct iovec iov = {
+		.iov_base = payload,
+		.iov_len = payload->nlmsg_len,
+	};
+	struct msghdr nlmsg = {
+		.msg_name = &nladdr,
+		.msg_namelen = sizeof(nladdr),
+		.msg_iov = &iov,
+		.msg_iovlen = 1,
+	};
+
+	nladdr.nl_family = AF_NETLINK;
+	nladdr.nl_pid = peer;
+	nladdr.nl_groups = groups;
+
+	payload->nlmsg_seq = time(NULL);
+
+	/* no need to send reply */
+	if (!cb)
+		payload->nlmsg_flags |= NLM_F_ACK;
+
+	fd = ovpn_rt_socket();
+	if (fd < 0) {
+		fprintf(stderr, "%s: can't open rtnl socket\n", __func__);
+		return -errno;
+	}
+
+	ret = ovpn_rt_bind(fd, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: can't bind rtnl socket\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	ret = sendmsg(fd, &nlmsg, 0);
+	if (ret < 0) {
+		fprintf(stderr, "%s: rtnl: error on sendmsg()\n", __func__);
+		ret = -errno;
+		goto out;
+	}
+
+	/* prepare buffer to store RTNL replies */
+	memset(buf, 0, sizeof(buf));
+	iov.iov_base = buf;
+
+	while (1) {
+		/*
+		 * iov_len is modified by recvmsg(), therefore has to be initialized before
+		 * using it again
+		 */
+		iov.iov_len = sizeof(buf);
+		rcv_len = recvmsg(fd, &nlmsg, 0);
+		if (rcv_len < 0) {
+			if (errno == EINTR || errno == EAGAIN) {
+				fprintf(stderr, "%s: interrupted call\n",
+					__func__);
+				continue;
+			}
+			fprintf(stderr, "%s: rtnl: error on recvmsg()\n",
+				__func__);
+			ret = -errno;
+			goto out;
+		}
+
+		if (rcv_len == 0) {
+			fprintf(stderr,
+				"%s: rtnl: socket reached unexpected EOF\n",
+				__func__);
+			ret = -EIO;
+			goto out;
+		}
+
+		if (nlmsg.msg_namelen != sizeof(nladdr)) {
+			fprintf(stderr,
+				"%s: sender address length: %u (expected %zu)\n",
+				__func__, nlmsg.msg_namelen, sizeof(nladdr));
+			ret = -EIO;
+			goto out;
+		}
+
+		h = (struct nlmsghdr *)buf;
+		while (rcv_len >= (int)sizeof(*h)) {
+			len = h->nlmsg_len;
+			rem_len = len - sizeof(*h);
+
+			if (rem_len < 0 || len > rcv_len) {
+				if (nlmsg.msg_flags & MSG_TRUNC) {
+					fprintf(stderr, "%s: truncated message\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+				fprintf(stderr, "%s: malformed message: len=%d\n",
+					__func__, len);
+				ret = -EIO;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_DONE) {
+				ret = 0;
+				goto out;
+			}
+
+			if (h->nlmsg_type == NLMSG_ERROR) {
+				err = (struct nlmsgerr *)NLMSG_DATA(h);
+				if (rem_len < (int)sizeof(struct nlmsgerr)) {
+					fprintf(stderr, "%s: ERROR truncated\n",
+						__func__);
+					ret = -EIO;
+					goto out;
+				}
+
+				if (err->error) {
+					fprintf(stderr, "%s: (%d) %s\n",
+						__func__, err->error,
+						strerror(-err->error));
+					ret = err->error;
+					goto out;
+				}
+
+				ret = 0;
+				if (cb)	{
+					int r = cb(h, arg_cb);
+
+					if (r <= 0)
+						ret = r;
+				}
+				goto out;
+			}
+
+			if (cb) {
+				int r = cb(h, arg_cb);
+
+				if (r <= 0) {
+					ret = r;
+					goto out;
+				}
+			} else {
+				fprintf(stderr, "%s: RTNL: unexpected reply\n",
+					__func__);
+			}
+
+			rcv_len -= NLMSG_ALIGN(len);
+			h = (struct nlmsghdr *)((uint8_t *)h +
+						NLMSG_ALIGN(len));
+		}
+
+		if (nlmsg.msg_flags & MSG_TRUNC) {
+			fprintf(stderr, "%s: message truncated\n", __func__);
+			continue;
+		}
+
+		if (rcv_len) {
+			fprintf(stderr, "%s: rtnl: %d not parsed bytes\n",
+				__func__, rcv_len);
+			ret = -1;
+			goto out;
+		}
+	}
+out:
+	close(fd);
+
+	return ret;
+}
+
+struct ovpn_link_req {
+	struct nlmsghdr n;
+	struct ifinfomsg i;
+	char buf[256];
+};
+
+static int ovpn_new_iface(struct ovpn_ctx *ovpn)
+{
+	struct rtattr *linkinfo, *data;
+	struct ovpn_link_req req = { 0 };
+	int ret = -1;
+
+	fprintf(stdout, "Creating interface %s with mode %u\n", ovpn->ifname,
+		ovpn->mode);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE | NLM_F_EXCL;
+	req.n.nlmsg_type = RTM_NEWLINK;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_IFNAME, ovpn->ifname,
+			 strlen(ovpn->ifname) + 1) < 0)
+		goto err;
+
+	linkinfo = ovpn_nest_start(&req.n, sizeof(req), IFLA_LINKINFO);
+	if (!linkinfo)
+		goto err;
+
+	if (ovpn_addattr(&req.n, sizeof(req), IFLA_INFO_KIND, OVPN_FAMILY_NAME,
+			 strlen(OVPN_FAMILY_NAME) + 1) < 0)
+		goto err;
+
+	if (ovpn->mode_set) {
+		data = ovpn_nest_start(&req.n, sizeof(req), IFLA_INFO_DATA);
+		if (!data)
+			goto err;
+
+		if (ovpn_addattr(&req.n, sizeof(req), IFLA_OVPN_MODE,
+				 &ovpn->mode, sizeof(uint8_t)) < 0)
+			goto err;
+
+		ovpn_nest_end(&req.n, data);
+	}
+
+	ovpn_nest_end(&req.n, linkinfo);
+
+	req.i.ifi_family = AF_PACKET;
+
+	ret = ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+err:
+	return ret;
+}
+
+static int ovpn_del_iface(struct ovpn_ctx *ovpn)
+{
+	struct ovpn_link_req req = { 0 };
+
+	fprintf(stdout, "Deleting interface %s ifindex %u\n", ovpn->ifname,
+		ovpn->ifindex);
+
+	req.n.nlmsg_len = NLMSG_LENGTH(sizeof(req.i));
+	req.n.nlmsg_flags = NLM_F_REQUEST;
+	req.n.nlmsg_type = RTM_DELLINK;
+
+	req.i.ifi_family = AF_PACKET;
+	req.i.ifi_index = ovpn->ifindex;
+
+	return ovpn_rt_send(&req.n, 0, 0, NULL, NULL);
+}
+
+static int nl_seq_check(struct nl_msg (*msg)__always_unused,
+			void (*arg)__always_unused)
+{
+	return NL_OK;
+}
+
+struct mcast_handler_args {
+	const char *group;
+	int id;
+};
+
+static int mcast_family_handler(struct nl_msg *msg, void *arg)
+{
+	struct mcast_handler_args *grp = arg;
+	struct nlattr *tb[CTRL_ATTR_MAX + 1];
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *mcgrp;
+	int rem_mcgrp;
+
+	nla_parse(tb, CTRL_ATTR_MAX, genlmsg_attrdata(gnlh, 0),
+		  genlmsg_attrlen(gnlh, 0), NULL);
+
+	if (!tb[CTRL_ATTR_MCAST_GROUPS])
+		return NL_SKIP;
+
+	nla_for_each_nested(mcgrp, tb[CTRL_ATTR_MCAST_GROUPS], rem_mcgrp) {
+		struct nlattr *tb_mcgrp[CTRL_ATTR_MCAST_GRP_MAX + 1];
+
+		nla_parse(tb_mcgrp, CTRL_ATTR_MCAST_GRP_MAX,
+			  nla_data(mcgrp), nla_len(mcgrp), NULL);
+
+		if (!tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME] ||
+		    !tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID])
+			continue;
+		if (strncmp(nla_data(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME]),
+			    grp->group, nla_len(tb_mcgrp[CTRL_ATTR_MCAST_GRP_NAME])))
+			continue;
+		grp->id = nla_get_u32(tb_mcgrp[CTRL_ATTR_MCAST_GRP_ID]);
+		break;
+	}
+
+	return NL_SKIP;
+}
+
+static int mcast_error_handler(struct sockaddr_nl (*nla)__always_unused,
+			       struct nlmsgerr *err, void *arg)
+{
+	int *ret = arg;
+
+	*ret = err->error;
+	return NL_STOP;
+}
+
+static int mcast_ack_handler(struct nl_msg (*msg)__always_unused, void *arg)
+{
+	int *ret = arg;
+
+	*ret = 0;
+	return NL_STOP;
+}
+
+static int ovpn_handle_msg(struct nl_msg *msg, void *arg)
+{
+	struct genlmsghdr *gnlh = nlmsg_data(nlmsg_hdr(msg));
+	struct nlattr *attrs[OVPN_A_MAX + 1];
+	struct nlmsghdr *nlh = nlmsg_hdr(msg);
+	//enum ovpn_del_peer_reason reason;
+	char ifname[IF_NAMESIZE];
+	int *ret = arg;
+	__u32 ifindex;
+
+	fprintf(stderr, "received message from ovpn-dco\n");
+
+	*ret = -1;
+
+	if (!genlmsg_valid_hdr(nlh, 0)) {
+		fprintf(stderr, "invalid header\n");
+		return NL_STOP;
+	}
+
+	if (nla_parse(attrs, OVPN_A_MAX, genlmsg_attrdata(gnlh, 0),
+		      genlmsg_attrlen(gnlh, 0), NULL)) {
+		fprintf(stderr, "received bogus data from ovpn-dco\n");
+		return NL_STOP;
+	}
+
+	if (!attrs[OVPN_A_IFINDEX]) {
+		fprintf(stderr, "no ifindex in this message\n");
+		return NL_STOP;
+	}
+
+	ifindex = nla_get_u32(attrs[OVPN_A_IFINDEX]);
+	if (!if_indextoname(ifindex, ifname)) {
+		fprintf(stderr, "cannot resolve ifname for ifindex: %u\n",
+			ifindex);
+		return NL_STOP;
+	}
+
+	switch (gnlh->cmd) {
+	case OVPN_CMD_PEER_DEL_NTF:
+		/*if (!attrs[OVPN_A_DEL_PEER_REASON]) {
+		 *	fprintf(stderr, "no reason in DEL_PEER message\n");
+		 *	return NL_STOP;
+		 *}
+		 *
+		 *reason = nla_get_u8(attrs[OVPN_A_DEL_PEER_REASON]);
+		 *fprintf(stderr,
+		 *	"received CMD_DEL_PEER, ifname: %s reason: %d\n",
+		 *	ifname, reason);
+		 */
+		fprintf(stdout, "received CMD_PEER_DEL_NTF\n");
+		break;
+	case OVPN_CMD_KEY_SWAP_NTF:
+		fprintf(stdout, "received CMD_KEY_SWAP_NTF\n");
+		break;
+	default:
+		fprintf(stderr, "received unknown command: %d\n", gnlh->cmd);
+		return NL_STOP;
+	}
+
+	*ret = 0;
+	return NL_OK;
+}
+
+static int ovpn_get_mcast_id(struct nl_sock *sock, const char *family,
+			     const char *group)
+{
+	struct nl_msg *msg;
+	struct nl_cb *cb;
+	int ret, ctrlid;
+	struct mcast_handler_args grp = {
+		.group = group,
+		.id = -ENOENT,
+	};
+
+	msg = nlmsg_alloc();
+	if (!msg)
+		return -ENOMEM;
+
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	if (!cb) {
+		ret = -ENOMEM;
+		goto out_fail_cb;
+	}
+
+	ctrlid = genl_ctrl_resolve(sock, "nlctrl");
+
+	genlmsg_put(msg, 0, 0, ctrlid, 0, 0, CTRL_CMD_GETFAMILY, 0);
+
+	ret = -ENOBUFS;
+	NLA_PUT_STRING(msg, CTRL_ATTR_FAMILY_NAME, family);
+
+	ret = nl_send_auto_complete(sock, msg);
+	if (ret < 0)
+		goto nla_put_failure;
+
+	ret = 1;
+
+	nl_cb_err(cb, NL_CB_CUSTOM, mcast_error_handler, &ret);
+	nl_cb_set(cb, NL_CB_ACK, NL_CB_CUSTOM, mcast_ack_handler, &ret);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, mcast_family_handler, &grp);
+
+	while (ret > 0)
+		nl_recvmsgs(sock, cb);
+
+	if (ret == 0)
+		ret = grp.id;
+ nla_put_failure:
+	nl_cb_put(cb);
+ out_fail_cb:
+	nlmsg_free(msg);
+	return ret;
+}
+
+static int ovpn_listen_mcast(void)
+{
+	struct nl_sock *sock;
+	struct nl_cb *cb;
+	int mcid, ret;
+
+	sock = nl_socket_alloc();
+	if (!sock) {
+		fprintf(stderr, "cannot allocate netlink socket\n");
+		goto err_free;
+	}
+
+	nl_socket_set_buffer_size(sock, 8192, 8192);
+
+	ret = genl_connect(sock);
+	if (ret < 0) {
+		fprintf(stderr, "cannot connect to generic netlink: %s\n",
+			nl_geterror(ret));
+		goto err_free;
+	}
+
+	mcid = ovpn_get_mcast_id(sock, OVPN_FAMILY_NAME, OVPN_MCGRP_PEERS);
+	if (mcid < 0) {
+		fprintf(stderr, "cannot get mcast group: %s\n",
+			nl_geterror(mcid));
+		goto err_free;
+	}
+
+	ret = nl_socket_add_membership(sock, mcid);
+	if (ret) {
+		fprintf(stderr, "failed to join mcast group: %d\n", ret);
+		goto err_free;
+	}
+
+	ret = 1;
+	cb = nl_cb_alloc(NL_CB_DEFAULT);
+	nl_cb_set(cb, NL_CB_SEQ_CHECK, NL_CB_CUSTOM, nl_seq_check, NULL);
+	nl_cb_set(cb, NL_CB_VALID, NL_CB_CUSTOM, ovpn_handle_msg, &ret);
+	nl_cb_err(cb, NL_CB_CUSTOM, ovpn_nl_cb_error, &ret);
+
+	while (ret == 1) {
+		int err = nl_recvmsgs(sock, cb);
+
+		if (err < 0) {
+			fprintf(stderr,
+				"cannot receive netlink message: (%d) %s\n",
+				err, nl_geterror(-err));
+			ret = -1;
+			break;
+		}
+	}
+
+	nl_cb_put(cb);
+err_free:
+	nl_socket_free(sock);
+	return ret;
+}
+
+static void usage(const char *cmd)
+{
+	fprintf(stderr,
+		"Usage %s <command> <iface> [arguments..]\n",
+		cmd);
+	fprintf(stderr, "where <command> can be one of the following\n\n");
+
+	fprintf(stderr, "* new_iface <iface> [mode]: create new ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tmode:\n");
+	fprintf(stderr, "\t\t- P2P for peer-to-peer mode (i.e. client)\n");
+	fprintf(stderr, "\t\t- MP for multi-peer mode (i.e. server)\n");
+
+	fprintf(stderr, "* del_iface <iface>: delete ovpn interface\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+
+	fprintf(stderr,
+		"* listen <iface> <lport> <peers_file> [ipv6]: listen for incoming peer TCP connections\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: TCP port to listen to\n");
+	fprintf(stderr,
+		"\tpeers_file: file containing one peer per line: Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <vpnaddr>\n");
+	fprintf(stderr,
+		"\tipv6: whether the socket should listen to the IPv6 wildcard address\n");
+
+	fprintf(stderr,
+		"* connect <iface> <peer_id> <raddr> <rport> [key_file]: start connecting peer of TCP-based VPN session\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the connecting peer\n");
+	fprintf(stderr, "\traddr: peer IP address to connect to\n");
+	fprintf(stderr, "\trport: peer TCP port to connect to\n");
+	fprintf(stderr,
+		"\tkey_file: file containing the symmetric key for encryption\n");
+
+	fprintf(stderr,
+		"* new_peer <iface> <peer_id> <lport> <raddr> <rport> [vpnaddr]: add new peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID to be used in data packets to/from this peer\n");
+	fprintf(stderr, "\traddr: peer IP address\n");
+	fprintf(stderr, "\trport: peer UDP port\n");
+	fprintf(stderr, "\tvpnaddr: peer VPN IP\n");
+
+	fprintf(stderr,
+		"* new_multi_peer <iface> <lport> <peers_file>: add multiple peers as listed in the file\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tlport: local UDP port to bind to\n");
+	fprintf(stderr,
+		"\tpeers_file: text file containing one peer per line. Line format:\n");
+	fprintf(stderr, "\t\t<peer_id> <raddr> <rport> <vpnaddr>\n");
+
+	fprintf(stderr,
+		"* set_peer <iface> <peer_id> <keepalive_interval> <keepalive_timeout>: set peer attributes\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr,
+		"\tkeepalive_interval: interval for sending ping messages\n");
+	fprintf(stderr,
+		"\tkeepalive_timeout: time after which a peer is timed out\n");
+
+	fprintf(stderr, "* del_peer <iface> <peer_id>: delete peer\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to delete\n");
+
+	fprintf(stderr, "* get_peer <iface> [peer_id]: retrieve peer(s) status\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to query. All peers are returned if omitted\n");
+
+	fprintf(stderr,
+		"* new_key <iface> <peer_id> <slot> <key_id> <cipher> <key_dir> <key_file>: set data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr,
+		"\tpeer_id: peer ID of the peer to configure the key for\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+	fprintf(stderr, "\tkey_id: an ID from 0 to 7\n");
+	fprintf(stderr,
+		"\tcipher: cipher to use, supported: aes (AES-GCM), chachapoly (CHACHA20POLY1305)\n");
+	fprintf(stderr,
+		"\tkey_dir: key direction, must 0 on one host and 1 on the other\n");
+	fprintf(stderr, "\tkey_file: file containing the pre-shared key\n");
+
+	fprintf(stderr,
+		"* del_key <iface> <peer_id> [slot]: erase existing data channel key\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+	fprintf(stderr, "\tslot: slot to erase. PRIMARY if omitted\n");
+
+	fprintf(stderr,
+		"* get_key <iface> <peer_id> <slot>: retrieve non sensible key data\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to query\n");
+	fprintf(stderr, "\tslot: either 1 (primary) or 2 (secondary)\n");
+
+	fprintf(stderr,
+		"* swap_keys <iface> <peer_id>: swap content of primary and secondary key slots\n");
+	fprintf(stderr, "\tiface: ovpn interface name\n");
+	fprintf(stderr, "\tpeer_id: peer ID of the peer to modify\n");
+
+	fprintf(stderr,
+		"* listen_mcast: listen to ovpn netlink multicast messages\n");
+}
+
+static int ovpn_parse_remote(struct ovpn_ctx *ovpn, const char *host,
+			     const char *service, const char *vpnip)
+{
+	int ret;
+	struct addrinfo *result;
+	struct addrinfo hints = {
+		.ai_family = ovpn->sa_family,
+		.ai_socktype = SOCK_DGRAM,
+		.ai_protocol = IPPROTO_UDP
+	};
+
+	if (host) {
+		ret = getaddrinfo(host, service, &hints, &result);
+		if (ret == EAI_NONAME || ret == EAI_FAIL)
+			return -1;
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->remote, result->ai_addr, result->ai_addrlen);
+	}
+
+	if (vpnip) {
+		ret = getaddrinfo(vpnip, NULL, &hints, &result);
+		if (ret == EAI_NONAME || ret == EAI_FAIL)
+			return -1;
+
+		if (!(result->ai_family == AF_INET &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in)) &&
+		    !(result->ai_family == AF_INET6 &&
+		      result->ai_addrlen == sizeof(struct sockaddr_in6))) {
+			ret = -EINVAL;
+			goto out;
+		}
+
+		memcpy(&ovpn->peer_ip, result->ai_addr, result->ai_addrlen);
+		ovpn->sa_family = result->ai_family;
+
+		ovpn->peer_ip_set = true;
+	}
+
+	ret = 0;
+out:
+	freeaddrinfo(result);
+	return ret;
+}
+
+static int ovpn_parse_new_peer(struct ovpn_ctx *ovpn, const char *peer_id,
+			       const char *raddr, const char *rport,
+			       const char *vpnip)
+{
+	ovpn->peer_id = strtoul(peer_id, NULL, 10);
+	if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+		fprintf(stderr, "peer ID value out of range\n");
+		return -1;
+	}
+
+	return ovpn_parse_remote(ovpn, raddr, rport, vpnip);
+}
+
+static int ovpn_parse_key_slot(const char *arg, struct ovpn_ctx *ovpn)
+{
+	int slot = strtoul(arg, NULL, 10);
+
+	if (errno == ERANGE || slot < 1 || slot > 2) {
+		fprintf(stderr, "key slot out of range\n");
+		return -1;
+	}
+
+	switch (slot) {
+	case 1:
+		ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+		break;
+	case 2:
+		ovpn->key_slot = OVPN_KEY_SLOT_SECONDARY;
+		break;
+	}
+
+	return 0;
+}
+
+static int ovpn_send_tcp_data(int socket)
+{
+	uint16_t len = htons(1000);
+	uint8_t buf[1002];
+	int ret;
+
+	memcpy(buf, &len, sizeof(len));
+	memset(buf + sizeof(len), 0x86, sizeof(buf) - sizeof(len));
+
+	ret = send(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	fprintf(stdout, "Sent %u bytes over TCP socket\n", ret);
+
+	return ret > 0 ? 0 : ret;
+}
+
+static int ovpn_recv_tcp_data(int socket)
+{
+	uint8_t buf[1002];
+	uint16_t len;
+	int ret;
+
+	ret = recv(socket, buf, sizeof(buf), MSG_NOSIGNAL);
+
+	if (ret < 2) {
+		fprintf(stderr, ">>>> Error while reading TCP data: %d\n", ret);
+		return ret;
+	}
+
+	memcpy(&len, buf, sizeof(len));
+	len = ntohs(len);
+
+	fprintf(stdout, ">>>> Received %u bytes over TCP socket, header: %u\n",
+		ret, len);
+
+/*	int i;
+ *	for (i = 2; i < ret; i++) {
+ *		fprintf(stdout, "0x%.2x ", buf[i]);
+ *		if (i && !((i - 2) % 16))
+ *			fprintf(stdout, "\n");
+ *	}
+ *	fprintf(stdout, "\n");
+ */
+	return 0;
+}
+
+static enum ovpn_cmd ovpn_parse_cmd(const char *cmd)
+{
+	if (!strcmp(cmd, "new_iface"))
+		return CMD_NEW_IFACE;
+
+	if (!strcmp(cmd, "del_iface"))
+		return CMD_DEL_IFACE;
+
+	if (!strcmp(cmd, "listen"))
+		return CMD_LISTEN;
+
+	if (!strcmp(cmd, "connect"))
+		return CMD_CONNECT;
+
+	if (!strcmp(cmd, "new_peer"))
+		return CMD_NEW_PEER;
+
+	if (!strcmp(cmd, "new_multi_peer"))
+		return CMD_NEW_MULTI_PEER;
+
+	if (!strcmp(cmd, "set_peer"))
+		return CMD_SET_PEER;
+
+	if (!strcmp(cmd, "del_peer"))
+		return CMD_DEL_PEER;
+
+	if (!strcmp(cmd, "get_peer"))
+		return CMD_GET_PEER;
+
+	if (!strcmp(cmd, "new_key"))
+		return CMD_NEW_KEY;
+
+	if (!strcmp(cmd, "del_key"))
+		return CMD_DEL_KEY;
+
+	if (!strcmp(cmd, "get_key"))
+		return CMD_GET_KEY;
+
+	if (!strcmp(cmd, "swap_keys"))
+		return CMD_SWAP_KEYS;
+
+	if (!strcmp(cmd, "listen_mcast"))
+		return CMD_LISTEN_MCAST;
+
+	return CMD_INVALID;
+}
+
+/* Send process to background and waits for signal.
+ *
+ * This helper is called at the end of commands
+ * creating sockets, so that the latter stay alive
+ * along with the process that created them.
+ *
+ * A signal is expected to be delivered in order to
+ * terminate the waiting processes
+ */
+static void ovpn_waitbg(void)
+{
+	daemon(1, 1);
+	pause();
+}
+
+static int ovpn_run_cmd(struct ovpn_ctx *ovpn)
+{
+	char peer_id[10], vpnip[INET6_ADDRSTRLEN], raddr[128], rport[10];
+	int n, ret;
+	FILE *fp;
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		ret = ovpn_new_iface(ovpn);
+		break;
+	case CMD_DEL_IFACE:
+		ret = ovpn_del_iface(ovpn);
+		break;
+	case CMD_LISTEN:
+		ret = ovpn_listen(ovpn, ovpn->sa_family);
+		if (ret < 0) {
+			fprintf(stderr, "cannot listen on TCP socket\n");
+			return ret;
+		}
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		int num_peers = 0;
+
+		while ((n = fscanf(fp, "%s %s\n", peer_id, vpnip)) == 2) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			if (num_peers == MAX_PEERS) {
+				fprintf(stderr, "max peers reached!\n");
+				return -E2BIG;
+			}
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.sa_family = ovpn->sa_family;
+
+			peer_ctx.socket = ovpn_accept(ovpn);
+			if (peer_ctx.socket < 0) {
+				fprintf(stderr, "cannot accept connection!\n");
+				return -1;
+			}
+
+			/* store peer sockets to test TCP I/O */
+			ovpn->cli_sockets[num_peers] = peer_ctx.socket;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, NULL,
+						  NULL, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, true);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s\n",
+					peer_id, vpnip);
+				return ret;
+			}
+			num_peers++;
+		}
+
+		for (int i = 0; i < num_peers; i++) {
+			ret = ovpn_recv_tcp_data(ovpn->cli_sockets[i]);
+			if (ret < 0)
+				break;
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_CONNECT:
+		ret = ovpn_connect(ovpn);
+		if (ret < 0) {
+			fprintf(stderr, "cannot connect TCP socket\n");
+			return ret;
+		}
+
+		ret = ovpn_new_peer(ovpn, true);
+		if (ret < 0) {
+			fprintf(stderr, "cannot add peer to VPN\n");
+			close(ovpn->socket);
+			return ret;
+		}
+
+		if (ovpn->cipher != OVPN_CIPHER_ALG_NONE) {
+			ret = ovpn_new_key(ovpn);
+			if (ret < 0) {
+				fprintf(stderr, "cannot set key\n");
+				return ret;
+			}
+		}
+
+		ret = ovpn_send_tcp_data(ovpn->socket);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6); //ovpn->sa_family ?
+		if (ret < 0)
+			return ret;
+
+		ret = ovpn_new_peer(ovpn, false);
+		ovpn_waitbg();
+		break;
+	case CMD_NEW_MULTI_PEER:
+		ret = ovpn_udp_socket(ovpn, AF_INET6);
+		if (ret < 0)
+			return ret;
+
+		fp = fopen(ovpn->peers_file, "r");
+		if (!fp) {
+			fprintf(stderr, "cannot open file: %s\n",
+				ovpn->peers_file);
+			return -1;
+		}
+
+		while ((n = fscanf(fp, "%s %s %s %s\n", peer_id, raddr, rport,
+				   vpnip)) == 4) {
+			struct ovpn_ctx peer_ctx = { 0 };
+
+			peer_ctx.ifindex = ovpn->ifindex;
+			peer_ctx.socket = ovpn->socket;
+			peer_ctx.sa_family = AF_UNSPEC;
+
+			ret = ovpn_parse_new_peer(&peer_ctx, peer_id, raddr,
+						  rport, vpnip);
+			if (ret < 0) {
+				fprintf(stderr, "error while parsing line\n");
+				return -1;
+			}
+
+			ret = ovpn_new_peer(&peer_ctx, false);
+			if (ret < 0) {
+				fprintf(stderr,
+					"cannot add peer to VPN: %s %s %s %s\n",
+					peer_id, raddr, rport, vpnip);
+				return ret;
+			}
+		}
+		ovpn_waitbg();
+		break;
+	case CMD_SET_PEER:
+		ret = ovpn_set_peer(ovpn);
+		break;
+	case CMD_DEL_PEER:
+		ret = ovpn_del_peer(ovpn);
+		break;
+	case CMD_GET_PEER:
+		if (ovpn->peer_id == PEER_ID_UNDEF)
+			fprintf(stderr, "List of peers connected to: %s\n",
+				ovpn->ifname);
+
+		ret = ovpn_get_peer(ovpn);
+		break;
+	case CMD_NEW_KEY:
+		ret = ovpn_new_key(ovpn);
+		break;
+	case CMD_DEL_KEY:
+		ret = ovpn_del_key(ovpn);
+		break;
+	case CMD_GET_KEY:
+		ret = ovpn_get_key(ovpn);
+		break;
+	case CMD_SWAP_KEYS:
+		ret = ovpn_swap_keys(ovpn);
+		break;
+	case CMD_LISTEN_MCAST:
+		ret = ovpn_listen_mcast();
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return ret;
+}
+
+static int ovpn_parse_cmd_args(struct ovpn_ctx *ovpn, int argc, char *argv[])
+{
+	int ret;
+
+	/* no args required for LISTEN_MCAST */
+	if (ovpn->cmd == CMD_LISTEN_MCAST)
+		return 0;
+
+	/* all commands need an ifname */
+	if (argc < 3)
+		return -EINVAL;
+
+	strscpy(ovpn->ifname, argv[2], IFNAMSIZ - 1);
+	ovpn->ifname[IFNAMSIZ - 1] = '\0';
+
+	/* all commands, except NEW_IFNAME, needs an ifindex */
+	if (ovpn->cmd != CMD_NEW_IFACE) {
+		ovpn->ifindex = if_nametoindex(ovpn->ifname);
+		if (!ovpn->ifindex) {
+			fprintf(stderr, "cannot find interface: %s\n",
+				strerror(errno));
+			return -1;
+		}
+	}
+
+	switch (ovpn->cmd) {
+	case CMD_NEW_IFACE:
+		if (argc < 4)
+			break;
+
+		if (!strcmp(argv[3], "P2P")) {
+			ovpn->mode = OVPN_MODE_P2P;
+		} else if (!strcmp(argv[3], "MP")) {
+			ovpn->mode = OVPN_MODE_MP;
+		} else {
+			fprintf(stderr, "Cannot parse iface mode: %s\n",
+				argv[3]);
+			return -1;
+		}
+		ovpn->mode_set = true;
+		break;
+	case CMD_DEL_IFACE:
+		break;
+	case CMD_LISTEN:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+
+		if (argc > 5 && !strcmp(argv[5], "ipv6"))
+			ovpn->sa_family = AF_INET6;
+		break;
+	case CMD_CONNECT:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->sa_family = AF_INET;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[4], argv[5],
+					  NULL);
+		if (ret < 0) {
+			fprintf(stderr, "Cannot parse remote peer data\n");
+			return -1;
+		}
+
+		if (argc > 6) {
+			ovpn->key_slot = OVPN_KEY_SLOT_PRIMARY;
+			ovpn->key_id = 0;
+			ovpn->cipher = OVPN_CIPHER_ALG_AES_GCM;
+			ovpn->key_dir = KEY_DIR_OUT;
+
+			ret = ovpn_parse_key(argv[6], ovpn);
+			if (ret)
+				return -1;
+		}
+		break;
+	case CMD_NEW_PEER:
+		if (argc < 7)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		const char *vpnip = (argc > 7) ? argv[7] : NULL;
+
+		ret = ovpn_parse_new_peer(ovpn, argv[3], argv[5], argv[6],
+					  vpnip);
+		if (ret < 0)
+			return -1;
+		break;
+	case CMD_NEW_MULTI_PEER:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->lport = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->lport > 65535) {
+			fprintf(stderr, "lport value out of range\n");
+			return -1;
+		}
+
+		ovpn->peers_file = argv[4];
+		break;
+	case CMD_SET_PEER:
+		if (argc < 6)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_interval = strtoul(argv[4], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+
+		ovpn->keepalive_timeout = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr,
+				"keepalive interval value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_DEL_PEER:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_GET_PEER:
+		ovpn->peer_id = PEER_ID_UNDEF;
+		if (argc > 3) {
+			ovpn->peer_id = strtoul(argv[3], NULL, 10);
+			if (errno == ERANGE || ovpn->peer_id > PEER_ID_UNDEF) {
+				fprintf(stderr, "peer ID value out of range\n");
+				return -1;
+			}
+		}
+		break;
+	case CMD_NEW_KEY:
+		if (argc < 9)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return -1;
+
+		ovpn->key_id = strtoul(argv[5], NULL, 10);
+		if (errno == ERANGE || ovpn->key_id > 2) {
+			fprintf(stderr, "key ID out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_cipher(argv[6], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key_direction(argv[7], ovpn);
+		if (ret < 0)
+			return -1;
+
+		ret = ovpn_parse_key(argv[8], ovpn);
+		if (ret)
+			return -1;
+		break;
+	case CMD_DEL_KEY:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_GET_KEY:
+		if (argc < 5)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+
+		ret = ovpn_parse_key_slot(argv[4], ovpn);
+		if (ret)
+			return ret;
+		break;
+	case CMD_SWAP_KEYS:
+		if (argc < 4)
+			return -EINVAL;
+
+		ovpn->peer_id = strtoul(argv[3], NULL, 10);
+		if (errno == ERANGE) {
+			fprintf(stderr, "peer ID value out of range\n");
+			return -1;
+		}
+		break;
+	case CMD_LISTEN_MCAST:
+		break;
+	case CMD_INVALID:
+		break;
+	}
+
+	return 0;
+}
+
+int main(int argc, char *argv[])
+{
+	struct ovpn_ctx ovpn;
+	int ret;
+
+	if (argc < 2) {
+		usage(argv[0]);
+		return -1;
+	}
+
+	memset(&ovpn, 0, sizeof(ovpn));
+	ovpn.sa_family = AF_INET;
+	ovpn.cipher = OVPN_CIPHER_ALG_NONE;
+
+	ovpn.cmd = ovpn_parse_cmd(argv[1]);
+	if (ovpn.cmd == CMD_INVALID) {
+		fprintf(stderr, "Error: unknown command.\n\n");
+		usage(argv[0]);
+		return -1;
+	}
+
+	ret = ovpn_parse_cmd_args(&ovpn, argc, argv);
+	if (ret < 0) {
+		fprintf(stderr, "Error: invalid arguments.\n\n");
+		if (ret == -EINVAL)
+			usage(argv[0]);
+		return ret;
+	}
+
+	ret = ovpn_run_cmd(&ovpn);
+	if (ret)
+		fprintf(stderr, "Cannot execute command: %s (%d)\n",
+			strerror(-ret), ret);
+
+	return ret;
+}
diff --git a/tools/testing/selftests/net/ovpn/tcp_peers.txt b/tools/testing/selftests/net/ovpn/tcp_peers.txt
new file mode 100644
index 0000000000000..d753eebe8716e
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/tcp_peers.txt
@@ -0,0 +1,5 @@
+1 5.5.5.2
+2 5.5.5.3
+3 5.5.5.4
+4 5.5.5.5
+5 5.5.5.6
diff --git a/tools/testing/selftests/net/ovpn/test-chachapoly.sh b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
new file mode 100755
index 0000000000000..32504079a2b89
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-chachapoly.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+ALG="chachapoly"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
new file mode 100755
index 0000000000000..093d44772ffdf
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test-close-socket.sh
diff --git a/tools/testing/selftests/net/ovpn/test-close-socket.sh b/tools/testing/selftests/net/ovpn/test-close-socket.sh
new file mode 100755
index 0000000000000..5e48a8b679287
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-close-socket.sh
@@ -0,0 +1,45 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+done
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/test-float.sh b/tools/testing/selftests/net/ovpn/test-float.sh
new file mode 100755
index 0000000000000..ba5d725e18b07
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-float.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+FLOAT="1"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test-tcp.sh b/tools/testing/selftests/net/ovpn/test-tcp.sh
new file mode 100755
index 0000000000000..ba3f1f315a349
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test-tcp.sh
@@ -0,0 +1,9 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+PROTO="TCP"
+
+source test.sh
diff --git a/tools/testing/selftests/net/ovpn/test.sh b/tools/testing/selftests/net/ovpn/test.sh
new file mode 100755
index 0000000000000..7b62897b02408
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/test.sh
@@ -0,0 +1,113 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2020-2025 OpenVPN, Inc.
+#
+#  Author:	Antonio Quartulli <antonio@openvpn.net>
+
+#set -x
+set -e
+
+source ./common.sh
+
+cleanup
+
+modprobe -q ovpn || true
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	create_ns ${p}
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	setup_ns ${p} 5.5.5.$((${p} + 1))/24
+done
+
+for p in $(seq 0 ${NUM_PEERS}); do
+	add_peer ${p}
+done
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 60 120
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 60 120
+done
+
+sleep 1
+
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ping -qfc 500 -w 3 5.5.5.$((${p} + 1))
+done
+
+if [ "$FLOAT" == "1" ]; then
+	# make clients float..
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip -n peer${p} addr del 10.10.${p}.2/24 dev veth${p}
+		ip -n peer${p} addr add 10.10.${p}.3/24 dev veth${p}
+	done
+	for p in $(seq 1 ${NUM_PEERS}); do
+		ip netns exec peer${p} ping -qfc 500 -w 3 5.5.5.1
+	done
+fi
+
+ip netns exec peer0 iperf3 -1 -s &
+sleep 1
+ip netns exec peer1 iperf3 -Z -t 3 -c 5.5.5.1
+
+echo "Adding secondary key and then swap:"
+for p in $(seq 1 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} new_key tun0 ${p} 2 1 ${ALG} 0 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} new_key tun${p} ${p} 2 1 ${ALG} 1 data64.key
+	ip netns exec peer${p} ${OVPN_CLI} swap_keys tun${p} ${p}
+done
+
+sleep 1
+
+echo "Querying all peers:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0
+ip netns exec peer1 ${OVPN_CLI} get_peer tun1
+
+echo "Querying peer 1:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 1
+
+echo "Querying non-existent peer 10:"
+ip netns exec peer0 ${OVPN_CLI} get_peer tun0 10 || true
+
+echo "Deleting peer 1:"
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 1
+ip netns exec peer1 ${OVPN_CLI} del_peer tun1 1
+
+echo "Querying keys:"
+for p in $(seq 2 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} get_key tun${p} ${p} 2
+done
+
+echo "Deleting peer while sending traffic:"
+(ip netns exec peer2 ping -qf -w 4 5.5.5.1)&
+sleep 2
+ip netns exec peer0 ${OVPN_CLI} del_peer tun0 2
+# following command fails in TCP mode
+# (both ends get conn reset when one peer disconnects)
+ip netns exec peer2 ${OVPN_CLI} del_peer tun2 2 || true
+
+echo "Deleting keys:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 1
+	ip netns exec peer${p} ${OVPN_CLI} del_key tun${p} ${p} 2
+done
+
+echo "Setting timeout to 3s MP:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer0 ${OVPN_CLI} set_peer tun0 ${p} 3 3 || true
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 0 0
+done
+# wait for peers to timeout
+sleep 5
+
+echo "Setting timeout to 3s P2P:"
+for p in $(seq 3 ${NUM_PEERS}); do
+	ip netns exec peer${p} ${OVPN_CLI} set_peer tun${p} ${p} 3 3
+done
+sleep 5
+
+cleanup
+
+modprobe -r ovpn || true
diff --git a/tools/testing/selftests/net/ovpn/udp_peers.txt b/tools/testing/selftests/net/ovpn/udp_peers.txt
new file mode 100644
index 0000000000000..32f14bd9347a6
--- /dev/null
+++ b/tools/testing/selftests/net/ovpn/udp_peers.txt
@@ -0,0 +1,5 @@
+1 10.10.1.2 1 5.5.5.2
+2 10.10.2.2 1 5.5.5.3
+3 10.10.3.2 1 5.5.5.4
+4 10.10.4.2 1 5.5.5.5
+5 10.10.5.2 1 5.5.5.6

From d41e6854855a6835127cb3b3259a748767cd1bc2 Mon Sep 17 00:00:00 2001
From: Qingfang Deng <dqfext@gmail.com>
Date: Tue, 18 Mar 2025 11:24:23 +0800
Subject: [PATCH 2565/2753] net: stmmac: Fix accessing freed irq affinity_hint

The cpumask should not be a local variable, since its pointer is saved
to irq_desc and may be accessed from procfs.
To fix it, use the persistent mask cpumask_of(cpu#).

Cc: stable@vger.kernel.org
Fixes: 8deec94c6040 ("net: stmmac: set IRQ affinity hint for multi MSI vectors")
Signed-off-by: Qingfang Deng <dqfext@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_main.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index a6a533d8a45be..cd79e3257b3fc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3676,7 +3676,6 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 {
 	struct stmmac_priv *priv = netdev_priv(dev);
 	enum request_irq_err irq_err;
-	cpumask_t cpu_mask;
 	int irq_idx = 0;
 	char *int_name;
 	int ret;
@@ -3805,9 +3804,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->rx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->rx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	/* Request Tx MSI irq */
@@ -3830,9 +3828,8 @@ static int stmmac_request_irq_multi_msi(struct net_device *dev)
 			irq_idx = i;
 			goto irq_error;
 		}
-		cpumask_clear(&cpu_mask);
-		cpumask_set_cpu(i % num_online_cpus(), &cpu_mask);
-		irq_set_affinity_hint(priv->tx_irq[i], &cpu_mask);
+		irq_set_affinity_hint(priv->tx_irq[i],
+				      cpumask_of(i % num_online_cpus()));
 	}
 
 	return 0;

From df8e85f871e0cdd0f56aac885ce1cbf91345b1c2 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 17 Mar 2025 20:48:48 -0700
Subject: [PATCH 2566/2753] af_unix: Sort headers.

This is a prep patch to make the following changes cleaner.

No functional change intended.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/af_unix.h      |  4 +--
 net/unix/af_unix.c         | 62 +++++++++++++++++++-------------------
 net/unix/diag.c            | 15 ++++-----
 net/unix/garbage.c         | 17 +++++------
 net/unix/sysctl_net_unix.c |  1 -
 net/unix/unix_bpf.c        |  4 +--
 6 files changed, 51 insertions(+), 52 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 63129c79b8cbc..c8dfdb41916d9 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -2,10 +2,10 @@
 #ifndef __LINUX_NET_AFUNIX_H
 #define __LINUX_NET_AFUNIX_H
 
-#include <linux/socket.h>
-#include <linux/un.h>
 #include <linux/mutex.h>
 #include <linux/refcount.h>
+#include <linux/socket.h>
+#include <linux/un.h>
 #include <net/sock.h>
 
 #if IS_ENABLED(CONFIG_UNIX)
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 7f8f3859cdb3f..1ff0ac99f3f35 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -77,46 +77,46 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/signal.h>
-#include <linux/sched/signal.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/stat.h>
+#include <linux/bpf-cgroup.h>
+#include <linux/btf_ids.h>
 #include <linux/dcache.h>
-#include <linux/namei.h>
-#include <linux/socket.h>
-#include <linux/un.h>
+#include <linux/errno.h>
 #include <linux/fcntl.h>
+#include <linux/file.h>
 #include <linux/filter.h>
-#include <linux/termios.h>
-#include <linux/sockios.h>
-#include <linux/net.h>
-#include <linux/in.h>
+#include <linux/freezer.h>
 #include <linux/fs.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
-#include <linux/skbuff.h>
-#include <linux/netdevice.h>
-#include <net/net_namespace.h>
-#include <net/sock.h>
-#include <net/tcp_states.h>
-#include <net/af_unix.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <net/scm.h>
+#include <linux/in.h>
 #include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/net.h>
+#include <linux/netdevice.h>
 #include <linux/poll.h>
+#include <linux/proc_fs.h>
 #include <linux/rtnetlink.h>
-#include <linux/mount.h>
-#include <net/checksum.h>
+#include <linux/sched/signal.h>
 #include <linux/security.h>
+#include <linux/seq_file.h>
+#include <linux/signal.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
 #include <linux/splice.h>
-#include <linux/freezer.h>
-#include <linux/file.h>
-#include <linux/btf_ids.h>
-#include <linux/bpf-cgroup.h>
+#include <linux/stat.h>
+#include <linux/string.h>
+#include <linux/termios.h>
+#include <linux/uaccess.h>
+#include <linux/un.h>
+#include <net/af_unix.h>
+#include <net/checksum.h>
+#include <net/net_namespace.h>
+#include <net/scm.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
 
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 9138af8b465e0..ba715507556a3 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -1,15 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0-only
-#include <linux/types.h>
-#include <linux/spinlock.h>
-#include <linux/sock_diag.h>
-#include <linux/unix_diag.h>
-#include <linux/skbuff.h>
+
 #include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/sock_diag.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
 #include <linux/uidgid.h>
-#include <net/netlink.h>
+#include <linux/unix_diag.h>
 #include <net/af_unix.h>
-#include <net/tcp_states.h>
+#include <net/netlink.h>
 #include <net/sock.h>
+#include <net/tcp_states.h>
 
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 9848b7b787017..6a641d4b55421 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -63,22 +63,21 @@
  *		wrt receive and holding up unrelated socket operations.
  */
 
+#include <linux/file.h>
+#include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/string.h>
-#include <linux/socket.h>
-#include <linux/un.h>
+#include <linux/mutex.h>
 #include <linux/net.h>
-#include <linux/fs.h>
-#include <linux/skbuff.h>
 #include <linux/netdevice.h>
-#include <linux/file.h>
 #include <linux/proc_fs.h>
-#include <linux/mutex.h>
+#include <linux/skbuff.h>
+#include <linux/socket.h>
+#include <linux/string.h>
+#include <linux/un.h>
 #include <linux/wait.h>
-
-#include <net/sock.h>
 #include <net/af_unix.h>
 #include <net/scm.h>
+#include <net/sock.h>
 #include <net/tcp_states.h>
 
 struct unix_sock *unix_get_socket(struct file *filp)
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index 357b3e5f38472..55118ae897d61 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -8,7 +8,6 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sysctl.h>
-
 #include <net/af_unix.h>
 
 static struct ctl_table unix_table[] = {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index bca2d86ba97d8..86598a959eaab 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -1,10 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2021 Cong Wang <cong.wang@bytedance.com> */
 
-#include <linux/skmsg.h>
 #include <linux/bpf.h>
-#include <net/sock.h>
+#include <linux/skmsg.h>
 #include <net/af_unix.h>
+#include <net/sock.h>
 
 #define unix_sk_has_data(__sk, __psock)					\
 		({	!skb_queue_empty(&__sk->sk_receive_queue) ||	\

From 1de6e5c881aba2676dc40d4d98daf58d676fd9fe Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 17 Mar 2025 20:48:49 -0700
Subject: [PATCH 2567/2753] af_unix: Move internal definitions to net/unix/.

net/af_unix.h is included by core and some LSMs, but most definitions
need not be.

Let's move struct unix_{vertex,edge} to net/unix/garbage.c and other
definitions to net/unix/af_unix.h.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/af_unix.h      | 76 +-------------------------------------
 net/unix/af_unix.c         |  2 +
 net/unix/af_unix.h         | 75 +++++++++++++++++++++++++++++++++++++
 net/unix/diag.c            |  2 +
 net/unix/garbage.c         | 18 +++++++++
 net/unix/sysctl_net_unix.c |  2 +
 net/unix/unix_bpf.c        |  2 +
 7 files changed, 102 insertions(+), 75 deletions(-)
 create mode 100644 net/unix/af_unix.h

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index c8dfdb41916d9..b5d70baba52bc 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -17,61 +17,17 @@ static inline struct unix_sock *unix_get_socket(struct file *filp)
 }
 #endif
 
-extern unsigned int unix_tot_inflight;
-void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver);
-void unix_del_edges(struct scm_fp_list *fpl);
-void unix_update_edges(struct unix_sock *receiver);
-int unix_prepare_fpl(struct scm_fp_list *fpl);
-void unix_destroy_fpl(struct scm_fp_list *fpl);
-void unix_gc(void);
-void wait_for_unix_gc(struct scm_fp_list *fpl);
-
-struct unix_vertex {
-	struct list_head edges;
-	struct list_head entry;
-	struct list_head scc_entry;
-	unsigned long out_degree;
-	unsigned long index;
-	unsigned long scc_index;
-};
-
-struct unix_edge {
-	struct unix_sock *predecessor;
-	struct unix_sock *successor;
-	struct list_head vertex_entry;
-	struct list_head stack_entry;
-};
-
-struct sock *unix_peer_get(struct sock *sk);
-
-#define UNIX_HASH_MOD	(256 - 1)
-#define UNIX_HASH_SIZE	(256 * 2)
-#define UNIX_HASH_BITS	8
-
 struct unix_address {
 	refcount_t	refcnt;
 	int		len;
 	struct sockaddr_un name[];
 };
 
-struct unix_skb_parms {
-	struct pid		*pid;		/* Skb credentials	*/
-	kuid_t			uid;
-	kgid_t			gid;
-	struct scm_fp_list	*fp;		/* Passed files		*/
-#ifdef CONFIG_SECURITY_NETWORK
-	u32			secid;		/* Security ID		*/
-#endif
-	u32			consumed;
-} __randomize_layout;
-
 struct scm_stat {
 	atomic_t nr_fds;
 	unsigned long nr_unix_fds;
 };
 
-#define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
-
 /* The AF_UNIX socket */
 struct unix_sock {
 	/* WARNING: sk has to be the first member */
@@ -84,6 +40,7 @@ struct unix_sock {
 	struct unix_vertex	*vertex;
 	spinlock_t		lock;
 	struct socket_wq	peer_wq;
+#define peer_wait		peer_wq.wait
 	wait_queue_entry_t	peer_wake;
 	struct scm_stat		scm_stat;
 #if IS_ENABLED(CONFIG_AF_UNIX_OOB)
@@ -94,35 +51,4 @@ struct unix_sock {
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
 #define unix_peer(sk) (unix_sk(sk)->peer)
 
-#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
-#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-
-#define peer_wait peer_wq.wait
-
-long unix_inq_len(struct sock *sk);
-long unix_outq_len(struct sock *sk);
-
-int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
-			 int flags);
-int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size,
-			  int flags);
-#ifdef CONFIG_SYSCTL
-int unix_sysctl_register(struct net *net);
-void unix_sysctl_unregister(struct net *net);
-#else
-static inline int unix_sysctl_register(struct net *net) { return 0; }
-static inline void unix_sysctl_unregister(struct net *net) {}
-#endif
-
-#ifdef CONFIG_BPF_SYSCALL
-extern struct proto unix_dgram_proto;
-extern struct proto unix_stream_proto;
-
-int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
-int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
-void __init unix_bpf_build_proto(void);
-#else
-static inline void __init unix_bpf_build_proto(void)
-{}
-#endif
 #endif
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 1ff0ac99f3f35..6390e04fe9164 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -118,6 +118,8 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 
+#include "af_unix.h"
+
 static atomic_long_t unix_nr_socks;
 static struct hlist_head bsd_socket_buckets[UNIX_HASH_SIZE / 2];
 static spinlock_t bsd_socket_locks[UNIX_HASH_SIZE / 2];
diff --git a/net/unix/af_unix.h b/net/unix/af_unix.h
new file mode 100644
index 0000000000000..ed4aedc428139
--- /dev/null
+++ b/net/unix/af_unix.h
@@ -0,0 +1,75 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __AF_UNIX_H
+#define __AF_UNIX_H
+
+#include <linux/uidgid.h>
+
+#define UNIX_HASH_MOD	(256 - 1)
+#define UNIX_HASH_SIZE	(256 * 2)
+#define UNIX_HASH_BITS	8
+
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+
+struct sock *unix_peer_get(struct sock *sk);
+
+struct unix_skb_parms {
+	struct pid		*pid;		/* skb credentials	*/
+	kuid_t			uid;
+	kgid_t			gid;
+	struct scm_fp_list	*fp;		/* Passed files		*/
+#ifdef CONFIG_SECURITY_NETWORK
+	u32			secid;		/* Security ID		*/
+#endif
+	u32			consumed;
+} __randomize_layout;
+
+#define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
+
+/* GC for SCM_RIGHTS */
+extern unsigned int unix_tot_inflight;
+void unix_add_edges(struct scm_fp_list *fpl, struct unix_sock *receiver);
+void unix_del_edges(struct scm_fp_list *fpl);
+void unix_update_edges(struct unix_sock *receiver);
+int unix_prepare_fpl(struct scm_fp_list *fpl);
+void unix_destroy_fpl(struct scm_fp_list *fpl);
+void unix_gc(void);
+void wait_for_unix_gc(struct scm_fp_list *fpl);
+
+/* SOCK_DIAG */
+long unix_inq_len(struct sock *sk);
+long unix_outq_len(struct sock *sk);
+
+/* sysctl */
+#ifdef CONFIG_SYSCTL
+int unix_sysctl_register(struct net *net);
+void unix_sysctl_unregister(struct net *net);
+#else
+static inline int unix_sysctl_register(struct net *net)
+{
+	return 0;
+}
+
+static inline void unix_sysctl_unregister(struct net *net)
+{
+}
+#endif
+
+/* BPF SOCKMAP */
+int __unix_dgram_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, int flags);
+int __unix_stream_recvmsg(struct sock *sk, struct msghdr *msg, size_t size, int flags);
+
+#ifdef CONFIG_BPF_SYSCALL
+extern struct proto unix_dgram_proto;
+extern struct proto unix_stream_proto;
+
+int unix_dgram_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
+int unix_stream_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
+void __init unix_bpf_build_proto(void);
+#else
+static inline void __init unix_bpf_build_proto(void)
+{
+}
+#endif
+
+#endif
diff --git a/net/unix/diag.c b/net/unix/diag.c
index ba715507556a3..c7e8c7d008f67 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -12,6 +12,8 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 
+#include "af_unix.h"
+
 static int sk_diag_dump_name(struct sock *sk, struct sk_buff *nlskb)
 {
 	/* might or might not have a hash table lock */
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 6a641d4b55421..8c8c7360349d2 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -80,6 +80,24 @@
 #include <net/sock.h>
 #include <net/tcp_states.h>
 
+#include "af_unix.h"
+
+struct unix_vertex {
+	struct list_head edges;
+	struct list_head entry;
+	struct list_head scc_entry;
+	unsigned long out_degree;
+	unsigned long index;
+	unsigned long scc_index;
+};
+
+struct unix_edge {
+	struct unix_sock *predecessor;
+	struct unix_sock *successor;
+	struct list_head vertex_entry;
+	struct list_head stack_entry;
+};
+
 struct unix_sock *unix_get_socket(struct file *filp)
 {
 	struct inode *inode = file_inode(filp);
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index 55118ae897d61..236b7faa92546 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -10,6 +10,8 @@
 #include <linux/sysctl.h>
 #include <net/af_unix.h>
 
+#include "af_unix.h"
+
 static struct ctl_table unix_table[] = {
 	{
 		.procname	= "max_dgram_qlen",
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 86598a959eaab..979dd4c4261ae 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -6,6 +6,8 @@
 #include <net/af_unix.h>
 #include <net/sock.h>
 
+#include "af_unix.h"
+
 #define unix_sk_has_data(__sk, __psock)					\
 		({	!skb_queue_empty(&__sk->sk_receive_queue) ||	\
 			!skb_queue_empty(&__psock->ingress_skb) ||	\

From 81047d7029442c8e29f540ae44a41ba24a203854 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 17 Mar 2025 20:48:50 -0700
Subject: [PATCH 2568/2753] af_unix: Explicitly include headers for non-pointer
 struct fields.

include/net/af_unix.h indirectly includes some definitions for structs.

Let's include such headers explicitly.

  linux/atomic.h   : scm_stat.nr_fds
  linux/net.h      : unix_sock.peer_wq
  linux/path.h     : unix_sock.path
  linux/spinlock.h : unix_sock.lock
  linux/wait.h     : unix_sock.peer_wake
  uapi/linux/un.h  : unix_address.name[]

linux/socket.h is removed as the structs there are not used directly,
and linux/un.h is clarified with uapi as un.h only exists under
include/uapi.

While at it, duplicate headers are removed from .c files.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/af_unix.h | 8 ++++++--
 net/unix/af_unix.c    | 3 ---
 net/unix/diag.c       | 3 ---
 net/unix/garbage.c    | 5 -----
 net/unix/unix_bpf.c   | 1 -
 5 files changed, 6 insertions(+), 14 deletions(-)

diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index b5d70baba52bc..b588069ece7eb 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -2,11 +2,15 @@
 #ifndef __LINUX_NET_AFUNIX_H
 #define __LINUX_NET_AFUNIX_H
 
+#include <linux/atomic.h>
 #include <linux/mutex.h>
+#include <linux/net.h>
+#include <linux/path.h>
 #include <linux/refcount.h>
-#include <linux/socket.h>
-#include <linux/un.h>
+#include <linux/spinlock.h>
+#include <linux/wait.h>
 #include <net/sock.h>
+#include <uapi/linux/un.h>
 
 #if IS_ENABLED(CONFIG_UNIX)
 struct unix_sock *unix_get_socket(struct file *filp);
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 6390e04fe9164..c081440cf5769 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -92,7 +92,6 @@
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/net.h>
 #include <linux/netdevice.h>
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
@@ -110,12 +109,10 @@
 #include <linux/string.h>
 #include <linux/termios.h>
 #include <linux/uaccess.h>
-#include <linux/un.h>
 #include <net/af_unix.h>
 #include <net/checksum.h>
 #include <net/net_namespace.h>
 #include <net/scm.h>
-#include <net/sock.h>
 #include <net/tcp_states.h>
 
 #include "af_unix.h"
diff --git a/net/unix/diag.c b/net/unix/diag.c
index c7e8c7d008f67..8b2247e05596f 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -3,13 +3,10 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/sock_diag.h>
-#include <linux/spinlock.h>
 #include <linux/types.h>
-#include <linux/uidgid.h>
 #include <linux/unix_diag.h>
 #include <net/af_unix.h>
 #include <net/netlink.h>
-#include <net/sock.h>
 #include <net/tcp_states.h>
 
 #include "af_unix.h"
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index 8c8c7360349d2..cd75502c47f1f 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -66,18 +66,13 @@
 #include <linux/file.h>
 #include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/mutex.h>
-#include <linux/net.h>
 #include <linux/netdevice.h>
 #include <linux/proc_fs.h>
 #include <linux/skbuff.h>
 #include <linux/socket.h>
 #include <linux/string.h>
-#include <linux/un.h>
-#include <linux/wait.h>
 #include <net/af_unix.h>
 #include <net/scm.h>
-#include <net/sock.h>
 #include <net/tcp_states.h>
 
 #include "af_unix.h"
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 979dd4c4261ae..e0d30d6d22acb 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -4,7 +4,6 @@
 #include <linux/bpf.h>
 #include <linux/skmsg.h>
 #include <net/af_unix.h>
-#include <net/sock.h>
 
 #include "af_unix.h"
 

From 9ab14ab57b8dc472e6d73a1f5e4638848dc4c56d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 17 Mar 2025 20:48:51 -0700
Subject: [PATCH 2569/2753] af_unix: Clean up #include under net/unix/.

net/unix/*.c include many unnecessary header files (rtnetlink.h,
netdevice.h, etc).

Let's clean them up.

af_unix.c:

  +uapi/linux/sockios.h   : Only exist under include/uapi
  +uapi/linux/termios.h   : Only exist under include/uapi

  -linux/freezer.h        : No longer use freezable_schedule_timeout()
  -linux/in.h             : No ipv4_is_XXX() etc
  -linux/module.h         : No longer support CONFIG_UNIX=m
  -linux/netdevice.h      : No dev used
  -linux/rtnetlink.h      : Not part of rtnetlink API
  -linux/signal.h         : signal_pending() is defined in sched/signal.h
  -linux/stat.h           : No struct stat used
  -net/checksum.h         : CHECKSUM_UNNECESSARY is defined in skbuff.h

diag.c:

  +linux/dcache.h         : struct dentry in sk_diag_dump_vfs()
  +linux/user_namespace.h : struct user_namespace in sk_diag_dump_uid()
  +uapi/linux/unix_diag.h : Only exist under include/uapi/

garbage.c:

  +linux/list.h           : struct unix_{vertex,edge}, etc
  +linux/workqueue.h      : DECLARE_WORK(unix_gc_work, ...)

  -linux/file.h           : No fget() etc
  -linux/kernel.h         : No cond_resched() etc
  -linux/netdevice.h      : No dev used
  -linux/proc_fs.h        : No procfs provided
  -linux/string.h         : No memcpy(), kmemdup(), etc

sysctl_net_unix.c:

  +linux/string.h         : kmemdup()
  +net/net_namespace.h    : struct net, net_eq()

  -linux/mm.h             : slab.h is enough

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/unix/af_unix.c         | 12 ++----------
 net/unix/diag.c            |  4 +++-
 net/unix/garbage.c         |  7 ++-----
 net/unix/sysctl_net_unix.c |  3 ++-
 4 files changed, 9 insertions(+), 17 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c081440cf5769..f78a2492826f9 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -84,36 +84,28 @@
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/filter.h>
-#include <linux/freezer.h>
 #include <linux/fs.h>
-#include <linux/in.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/netdevice.h>
 #include <linux/poll.h>
 #include <linux/proc_fs.h>
-#include <linux/rtnetlink.h>
 #include <linux/sched/signal.h>
 #include <linux/security.h>
 #include <linux/seq_file.h>
-#include <linux/signal.h>
 #include <linux/skbuff.h>
 #include <linux/slab.h>
 #include <linux/socket.h>
-#include <linux/sockios.h>
 #include <linux/splice.h>
-#include <linux/stat.h>
 #include <linux/string.h>
-#include <linux/termios.h>
 #include <linux/uaccess.h>
 #include <net/af_unix.h>
-#include <net/checksum.h>
 #include <net/net_namespace.h>
 #include <net/scm.h>
 #include <net/tcp_states.h>
+#include <uapi/linux/sockios.h>
+#include <uapi/linux/termios.h>
 
 #include "af_unix.h"
 
diff --git a/net/unix/diag.c b/net/unix/diag.c
index 8b2247e05596f..79b182d0e62ae 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -1,13 +1,15 @@
 // SPDX-License-Identifier: GPL-2.0-only
 
+#include <linux/dcache.h>
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/sock_diag.h>
 #include <linux/types.h>
-#include <linux/unix_diag.h>
+#include <linux/user_namespace.h>
 #include <net/af_unix.h>
 #include <net/netlink.h>
 #include <net/tcp_states.h>
+#include <uapi/linux/unix_diag.h>
 
 #include "af_unix.h"
 
diff --git a/net/unix/garbage.c b/net/unix/garbage.c
index cd75502c47f1f..01e2b9452c75b 100644
--- a/net/unix/garbage.c
+++ b/net/unix/garbage.c
@@ -63,14 +63,11 @@
  *		wrt receive and holding up unrelated socket operations.
  */
 
-#include <linux/file.h>
 #include <linux/fs.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-#include <linux/proc_fs.h>
+#include <linux/list.h>
 #include <linux/skbuff.h>
 #include <linux/socket.h>
-#include <linux/string.h>
+#include <linux/workqueue.h>
 #include <net/af_unix.h>
 #include <net/scm.h>
 #include <net/tcp_states.h>
diff --git a/net/unix/sysctl_net_unix.c b/net/unix/sysctl_net_unix.c
index 236b7faa92546..e02ed6e3955c0 100644
--- a/net/unix/sysctl_net_unix.c
+++ b/net/unix/sysctl_net_unix.c
@@ -5,10 +5,11 @@
  * Authors:	Mike Shaver.
  */
 
-#include <linux/mm.h>
 #include <linux/slab.h>
+#include <linux/string.h>
 #include <linux/sysctl.h>
 #include <net/af_unix.h>
+#include <net/net_namespace.h>
 
 #include "af_unix.h"
 

From f001813df47474d4a2085ad6108c953b32a70e75 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 17 Mar 2025 23:01:07 -0700
Subject: [PATCH 2570/2753] tcp/dccp: Remove
 inet_connection_sock_af_ops.addr2sockaddr().

inet_connection_sock_af_ops.addr2sockaddr() hasn't been used at all
in the git era.

  $ git grep addr2sockaddr $(git rev-list HEAD | tail -n 1)

Let's remove it.

Note that there was a 4 bytes hole after sockaddr_len and now it's
6 bytes, so the binary layout is not changed.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/inet6_connection_sock.h |  2 --
 include/net/inet_connection_sock.h  |  4 ----
 net/dccp/ipv4.c                     |  2 --
 net/dccp/ipv6.c                     |  4 ----
 net/ipv4/inet_connection_sock.c     | 11 -----------
 net/ipv4/tcp_ipv4.c                 |  2 --
 net/ipv6/inet6_connection_sock.c    | 14 --------------
 net/ipv6/tcp_ipv6.c                 |  4 ----
 8 files changed, 43 deletions(-)

diff --git a/include/net/inet6_connection_sock.h b/include/net/inet6_connection_sock.h
index 025bd8d3c769a..745891d2e1137 100644
--- a/include/net/inet6_connection_sock.h
+++ b/include/net/inet6_connection_sock.h
@@ -21,8 +21,6 @@ struct sockaddr;
 struct dst_entry *inet6_csk_route_req(const struct sock *sk, struct flowi6 *fl6,
 				      const struct request_sock *req, u8 proto);
 
-void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
-
 int inet6_csk_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
 
 struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu);
diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index e8ed52fc603f2..09a9d333fa42a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -44,12 +44,10 @@ struct inet_connection_sock_af_ops {
 				      struct request_sock *req_unhash,
 				      bool *own_req);
 	u16	    net_header_len;
-	u16	    sockaddr_len;
 	int	    (*setsockopt)(struct sock *sk, int level, int optname,
 				  sockptr_t optval, unsigned int optlen);
 	int	    (*getsockopt)(struct sock *sk, int level, int optname,
 				  char __user *optval, int __user *optlen);
-	void	    (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
 	void	    (*mtu_reduced)(struct sock *sk);
 };
 
@@ -315,8 +313,6 @@ static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
 int inet_csk_listen_start(struct sock *sk);
 void inet_csk_listen_stop(struct sock *sk);
 
-void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
-
 /* update the fast reuse flag when adding a socket */
 void inet_csk_update_fastreuse(struct inet_bind_bucket *tb,
 			       struct sock *sk);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index bfa529a54acab..2045ddac0fe9f 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -934,8 +934,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv4_af_ops = {
 	.net_header_len	   = sizeof(struct iphdr),
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
-	.addr2sockaddr	   = inet_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in),
 };
 
 static int dccp_v4_init_sock(struct sock *sk)
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 39ae9d89d7d43..e24dbffabfc19 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -988,8 +988,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_af_ops = {
 	.net_header_len	   = sizeof(struct ipv6hdr),
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in6),
 };
 
 /*
@@ -1004,8 +1002,6 @@ static const struct inet_connection_sock_af_ops dccp_ipv6_mapped = {
 	.net_header_len	   = sizeof(struct iphdr),
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in6),
 };
 
 static void dccp_v6_sk_destruct(struct sock *sk)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index e93c660340770..dd5cf8914a28d 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -1553,17 +1553,6 @@ void inet_csk_listen_stop(struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
 
-void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
-{
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
-	const struct inet_sock *inet = inet_sk(sk);
-
-	sin->sin_family		= AF_INET;
-	sin->sin_addr.s_addr	= inet->inet_daddr;
-	sin->sin_port		= inet->inet_dport;
-}
-EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
-
 static struct dst_entry *inet_csk_rebuild_route(struct sock *sk, struct flowi *fl)
 {
 	const struct inet_sock *inet = inet_sk(sk);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4fa4fbb0ad12d..1cd0938d47e07 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2477,8 +2477,6 @@ const struct inet_connection_sock_af_ops ipv4_specific = {
 	.net_header_len	   = sizeof(struct iphdr),
 	.setsockopt	   = ip_setsockopt,
 	.getsockopt	   = ip_getsockopt,
-	.addr2sockaddr	   = inet_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in),
 	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 EXPORT_IPV6_MOD(ipv4_specific);
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 80043e46117c5..dbcf556a35bbc 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -56,20 +56,6 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk,
 }
 EXPORT_SYMBOL(inet6_csk_route_req);
 
-void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
-{
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) uaddr;
-
-	sin6->sin6_family = AF_INET6;
-	sin6->sin6_addr = sk->sk_v6_daddr;
-	sin6->sin6_port	= inet_sk(sk)->inet_dport;
-	/* We do not store received flowlabel for TCP */
-	sin6->sin6_flowinfo = 0;
-	sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
-						  sk->sk_bound_dev_if);
-}
-EXPORT_SYMBOL_GPL(inet6_csk_addr2sockaddr);
-
 static inline
 struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie)
 {
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index e182ee0a23304..c134cf1a603a0 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -2068,8 +2068,6 @@ const struct inet_connection_sock_af_ops ipv6_specific = {
 	.net_header_len	   = sizeof(struct ipv6hdr),
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in6),
 	.mtu_reduced	   = tcp_v6_mtu_reduced,
 };
 
@@ -2102,8 +2100,6 @@ static const struct inet_connection_sock_af_ops ipv6_mapped = {
 	.net_header_len	   = sizeof(struct iphdr),
 	.setsockopt	   = ipv6_setsockopt,
 	.getsockopt	   = ipv6_getsockopt,
-	.addr2sockaddr	   = inet6_csk_addr2sockaddr,
-	.sockaddr_len	   = sizeof(struct sockaddr_in6),
 	.mtu_reduced	   = tcp_v4_mtu_reduced,
 };
 

From 20707bf27c91e3350500eb13ed488a38bab7fbcf Mon Sep 17 00:00:00 2001
From: Yui Washizu <yui.washidu@gmail.com>
Date: Tue, 18 Mar 2025 15:12:41 +0900
Subject: [PATCH 2571/2753] docs: fix the path of example code and example
 commands for device memory TCP

This updates the old path and fixes the description of unavailable options.

Signed-off-by: Yui Washizu <yui.washidu@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/devmem.rst | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/Documentation/networking/devmem.rst b/Documentation/networking/devmem.rst
index d953636453314..eb678ca454968 100644
--- a/Documentation/networking/devmem.rst
+++ b/Documentation/networking/devmem.rst
@@ -256,7 +256,7 @@ Testing
 =======
 
 More realistic example code can be found in the kernel source under
-``tools/testing/selftests/net/ncdevmem.c``
+``tools/testing/selftests/drivers/net/hw/ncdevmem.c``
 
 ncdevmem is a devmem TCP netcat. It works very similarly to netcat, but
 receives data directly into a udmabuf.
@@ -268,8 +268,7 @@ ncdevmem has a validation mode as well that expects a repeating pattern of
 incoming data and validates it as such. For example, you can launch
 ncdevmem on the server by::
 
-	ncdevmem -s <server IP> -c <client IP> -f eth1 -d 3 -n 0000:06:00.0 -l \
-		 -p 5201 -v 7
+	ncdevmem -s <server IP> -c <client IP> -f <ifname> -l -p 5201 -v 7
 
 On client side, use regular netcat to send TX data to ncdevmem process
 on the server::

From b658953234f547a477cce262b116c113e0ca1e9d Mon Sep 17 00:00:00 2001
From: WangYuli <wangyuli@uniontech.com>
Date: Tue, 18 Mar 2025 15:46:56 +0800
Subject: [PATCH 2572/2753] docs: networking: strparser: Fix a typo

The context indicates that 'than' is the correct word instead of 'then',
as a comparison is being performed.

Given that 'then' is also a valid English word, checkpatch.pl wouldn't
have picked up on this spelling error.

This typo was caught by AI during code review.

Fixes: adcce4d5dd46 ("strparser: Documentation")
Reported-by: Sourcery AI <hello@sourcery.ai>
Suggested-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: WangYuli <wangyuli@uniontech.com>
Reviewed-by: Yanteng Si <si.yanteng@linux.dev>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/strparser.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/strparser.rst b/Documentation/networking/strparser.rst
index 7f623d1db72aa..8dc6bb04c710b 100644
--- a/Documentation/networking/strparser.rst
+++ b/Documentation/networking/strparser.rst
@@ -180,7 +180,7 @@ There are seven callbacks:
     struct contains two fields: offset and full_len. Offset is
     where the message starts in the skb, and full_len is the
     the length of the message. skb->len - offset may be greater
-    then full_len since strparser does not trim the skb.
+    than full_len since strparser does not trim the skb.
 
     ::
 

From e59b01214fc4121d8a69a59127cf6d00e68ec707 Mon Sep 17 00:00:00 2001
From: ChunHao Lin <hau@realtek.com>
Date: Tue, 18 Mar 2025 16:37:20 +0800
Subject: [PATCH 2573/2753] r8169: enable RTL8168H/RTL8168EP/RTL8168FP ASPM
 support

This patch will enable RTL8168H/RTL8168EP/RTL8168FP ASPM support on
the platforms that have tested with ASPM enabled.

Signed-off-by: ChunHao Lin <hau@realtek.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/realtek/r8169_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 53e541ddb439f..5c5e256fb9fae 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -5398,7 +5398,7 @@ static void rtl_init_mac_address(struct rtl8169_private *tp)
 /* register is set if system vendor successfully tested ASPM 1.2 */
 static bool rtl_aspm_is_safe(struct rtl8169_private *tp)
 {
-	if (tp->mac_version >= RTL_GIGA_MAC_VER_61 &&
+	if (tp->mac_version >= RTL_GIGA_MAC_VER_46 &&
 	    r8168_mac_ocp_read(tp, 0xc0b2) & 0xf)
 		return true;
 

From 81de8771ad396bdd9324c7d947176a9bd609fe1b Mon Sep 17 00:00:00 2001
From: ChunHao Lin <hau@realtek.com>
Date: Tue, 18 Mar 2025 16:37:21 +0800
Subject: [PATCH 2574/2753] r8169: disable RTL8126 ZRX-DC timeout

Disable it due to it dose not meet ZRX-DC specification. If it is enabled,
device will exit L1 substate every 100ms. Disable it for saving more power
in L1 substate.

Signed-off-by: ChunHao Lin <hau@realtek.com>
Reviewed-by: Heiner Kallweit <hkallweit1@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/realtek/r8169_main.c | 27 +++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index 5c5e256fb9fae..4eebd9cb40a37 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2852,6 +2852,32 @@ static u32 rtl_csi_read(struct rtl8169_private *tp, int addr)
 		RTL_R32(tp, CSIDR) : ~0;
 }
 
+static void rtl_disable_zrxdc_timeout(struct rtl8169_private *tp)
+{
+	struct pci_dev *pdev = tp->pci_dev;
+	u32 csi;
+	int rc;
+	u8 val;
+
+#define RTL_GEN3_RELATED_OFF	0x0890
+#define RTL_GEN3_ZRXDC_NONCOMPL	0x1
+	if (pdev->cfg_size > RTL_GEN3_RELATED_OFF) {
+		rc = pci_read_config_byte(pdev, RTL_GEN3_RELATED_OFF, &val);
+		if (rc == PCIBIOS_SUCCESSFUL) {
+			val &= ~RTL_GEN3_ZRXDC_NONCOMPL;
+			rc = pci_write_config_byte(pdev, RTL_GEN3_RELATED_OFF,
+						   val);
+			if (rc == PCIBIOS_SUCCESSFUL)
+				return;
+		}
+	}
+
+	netdev_notice_once(tp->dev,
+		"No native access to PCI extended config space, falling back to CSI\n");
+	csi = rtl_csi_read(tp, RTL_GEN3_RELATED_OFF);
+	rtl_csi_write(tp, RTL_GEN3_RELATED_OFF, csi & ~RTL_GEN3_ZRXDC_NONCOMPL);
+}
+
 static void rtl_set_aspm_entry_latency(struct rtl8169_private *tp, u8 val)
 {
 	struct pci_dev *pdev = tp->pci_dev;
@@ -3824,6 +3850,7 @@ static void rtl_hw_start_8125d(struct rtl8169_private *tp)
 
 static void rtl_hw_start_8126a(struct rtl8169_private *tp)
 {
+	rtl_disable_zrxdc_timeout(tp);
 	rtl_set_def_aspm_entry_latency(tp);
 	rtl_hw_start_8125_common(tp);
 }

From dc1952003e6ec4e2c06183346b1f3e881b696556 Mon Sep 17 00:00:00 2001
From: Ryohei Kinugawa <ryohei.kinugawa@gmail.com>
Date: Tue, 18 Mar 2025 09:51:52 +0000
Subject: [PATCH 2575/2753] docs/kcm: Fix typo "BFP"

'BFP' should be 'BPF'.

Signed-off-by: Ryohei Kinugawa <ryohei.kinugawa@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/networking/kcm.rst | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/Documentation/networking/kcm.rst b/Documentation/networking/kcm.rst
index db0f5560ac1c2..71f44d0beaa36 100644
--- a/Documentation/networking/kcm.rst
+++ b/Documentation/networking/kcm.rst
@@ -200,7 +200,7 @@ while. Example use::
 
   setsockopt(kcmfd, SOL_KCM, KCM_RECV_DISABLE, &val, sizeof(val))
 
-BFP programs for message delineation
+BPF programs for message delineation
 ------------------------------------
 
 BPF programs can be compiled using the BPF LLVM backend. For example,

From c310b8c3f28ebf1a55a35154ad38ae7bceb77981 Mon Sep 17 00:00:00 2001
From: WangYuli <wangyuli@uniontech.com>
Date: Tue, 18 Mar 2025 18:36:54 +0800
Subject: [PATCH 2576/2753] mlxsw: spectrum_acl_bloom_filter: Workaround for
 some LLVM versions

This is a workaround to mitigate a compiler anomaly.

During LLVM toolchain compilation of this driver on s390x architecture, an
unreasonable __write_overflow_field warning occurs.

Contextually, chunk_index is restricted to 0, 1 or 2. By expanding these
possibilities, the compile warning is suppressed.

Fix follow error with clang-19 when -Werror:
  In file included from drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c:5:
  In file included from ./include/linux/gfp.h:7:
  In file included from ./include/linux/mmzone.h:8:
  In file included from ./include/linux/spinlock.h:63:
  In file included from ./include/linux/lockdep.h:14:
  In file included from ./include/linux/smp.h:13:
  In file included from ./include/linux/cpumask.h:12:
  In file included from ./include/linux/bitmap.h:13:
  In file included from ./include/linux/string.h:392:
  ./include/linux/fortify-string.h:571:4: error: call to '__write_overflow_field' declared with 'warning' attribute: detected write beyond size of field (1st parameter); maybe use struct_group()? [-Werror,-Wattribute-warning]
    571 |                         __write_overflow_field(p_size_field, size);
        |                         ^
  1 error generated.

According to the testing, we can be fairly certain that this is a clang
compiler bug, impacting only clang-19 and below. Clang versions 20 and
21 do not exhibit this behavior.

Link: https://lore.kernel.org/all/484364B641C901CD+20250311141025.1624528-1-wangyuli@uniontech.com/
Fixes: 7585cacdb978 ("mlxsw: spectrum_acl: Add Bloom filter handling")
Co-developed-by: Zijian Chen <czj2441@163.com>
Signed-off-by: Zijian Chen <czj2441@163.com>
Co-developed-by: Wentao Guan <guanwentao@uniontech.com>
Signed-off-by: Wentao Guan <guanwentao@uniontech.com>
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Co-developed-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: WangYuli <wangyuli@uniontech.com>
Signed-off-by: WangYuli <wangyuli@uniontech.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../mlxsw/spectrum_acl_bloom_filter.c         | 27 +++++++++++++++----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
index a54eedb69a3f5..067f0055a55af 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
@@ -212,7 +212,22 @@ static const u8 mlxsw_sp4_acl_bf_crc6_tab[256] = {
  * This array defines key offsets for easy access when copying key blocks from
  * entry key to Bloom filter chunk.
  */
-static const u8 chunk_key_offsets[MLXSW_BLOOM_KEY_CHUNKS] = {2, 20, 38};
+static char *
+mlxsw_sp_acl_bf_enc_key_get(struct mlxsw_sp_acl_atcam_entry *aentry,
+			    u8 chunk_index)
+{
+	switch (chunk_index) {
+	case 0:
+		return &aentry->ht_key.enc_key[2];
+	case 1:
+		return &aentry->ht_key.enc_key[20];
+	case 2:
+		return &aentry->ht_key.enc_key[38];
+	default:
+		WARN_ON_ONCE(1);
+		return &aentry->ht_key.enc_key[0];
+	}
+}
 
 static u16 mlxsw_sp2_acl_bf_crc16_byte(u16 crc, u8 c)
 {
@@ -235,9 +250,10 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 			     u8 key_offset, u8 chunk_key_len, u8 chunk_len)
 {
 	struct mlxsw_afk_key_info *key_info = aregion->region->key_info;
-	u8 chunk_index, chunk_count, block_count;
+	u8 chunk_index, chunk_count;
 	char *chunk = output;
 	__be16 erp_region_id;
+	u32 block_count;
 
 	block_count = mlxsw_afk_key_info_blocks_count_get(key_info);
 	chunk_count = 1 + ((block_count - 1) >> 2);
@@ -245,12 +261,13 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
 				   (aregion->region->id << 4));
 	for (chunk_index = max_chunks - chunk_count; chunk_index < max_chunks;
 	     chunk_index++) {
+		char *enc_key;
+
 		memset(chunk, 0, pad_bytes);
 		memcpy(chunk + pad_bytes, &erp_region_id,
 		       sizeof(erp_region_id));
-		memcpy(chunk + key_offset,
-		       &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
-		       chunk_key_len);
+		enc_key = mlxsw_sp_acl_bf_enc_key_get(aentry, chunk_index);
+		memcpy(chunk + key_offset, enc_key, chunk_key_len);
 		chunk += chunk_len;
 	}
 	*len = chunk_count * chunk_len;

From 7d35dfa17842e5fbd5993f95ae015f831c400aef Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Tue, 18 Mar 2025 13:24:26 +0200
Subject: [PATCH 2577/2753] selftests: drv-net: rss_ctx: Don't assume
 indirection table is present

The test_rss_context_dump() test assumes the indirection table is always
supported, which is not true for all drivers, e.g., virtio_net when
VIRTIO_NET_F_RSS is disabled.

Skip the check if 'indir' is not present.

Reviewed-by: Nimrod Oren <noren@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/drivers/net/hw/rss_ctx.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/hw/rss_ctx.py b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
index d6e69d7d5e438..ca60ae325c22e 100755
--- a/tools/testing/selftests/drivers/net/hw/rss_ctx.py
+++ b/tools/testing/selftests/drivers/net/hw/rss_ctx.py
@@ -392,7 +392,7 @@ def test_rss_context_dump(cfg):
 
     # Sanity-check the results
     for data in ctxs:
-        ksft_ne(set(data['indir']), {0}, "indir table is all zero")
+        ksft_ne(set(data.get('indir', [1])), {0}, "indir table is all zero")
         ksft_ne(set(data.get('hkey', [1])), {0}, "key is all zero")
 
         # More specific checks

From 973fdffb99a0d9a32fb45b2c6fd57168e9b1cffe Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:05 +0100
Subject: [PATCH 2578/2753] net: mvneta: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in mvneta driver
mvneta sets xdp headroom to:

MVNETA_MH_SIZE + MVNETA_SKB_HEADROOM

where

MVNETA_MH_SIZE 2
MVNETA_SKB_HEADROOM max(NET_SKB_PAD, XDP_PACKET_HEADROOM)

so the headroom is large enough to contain xdp_frame and xdp metadata.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/marvell/mvneta.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index 44b18c5739092..147571fdada37 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -2342,7 +2342,7 @@ mvneta_swbm_rx_frame(struct mvneta_port *pp,
 	prefetch(data);
 	xdp_buff_clear_frags_flag(xdp);
 	xdp_prepare_buff(xdp, data, pp->rx_offset_correction + MVNETA_MH_SIZE,
-			 data_len, false);
+			 data_len, true);
 }
 
 static void
@@ -2396,6 +2396,7 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 		      struct xdp_buff *xdp, u32 desc_status)
 {
 	struct skb_shared_info *sinfo = xdp_get_shared_info_from_buff(xdp);
+	u32 metasize = xdp->data - xdp->data_meta;
 	struct sk_buff *skb;
 	u8 num_frags;
 
@@ -2410,6 +2411,8 @@ mvneta_swbm_build_skb(struct mvneta_port *pp, struct page_pool *pool,
 
 	skb_reserve(skb, xdp->data - xdp->data_hard_start);
 	skb_put(skb, xdp->data_end - xdp->data);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->ip_summed = mvneta_rx_csum(pp, desc_status);
 
 	if (unlikely(xdp_buff_has_frags(xdp)))

From 3508f27bfa04c2acb5a7dc6dca2671b2b98a9ea7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:06 +0100
Subject: [PATCH 2579/2753] net: mvpp2: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in mvpp2 driver
mvpp2 driver sets xdp headroom to:

MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM

where

MVPP2_MH_SIZE 2
MVPP2_SKB_HEADROOM min(max(XDP_PACKET_HEADROOM, NET_SKB_PAD), 224)

so the headroom is large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index f166dc4e65037..54a235366a01b 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -3915,13 +3915,13 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 	while (rx_done < rx_todo) {
 		struct mvpp2_rx_desc *rx_desc = mvpp2_rxq_next_desc_get(rxq);
+		u32 rx_status, timestamp, metasize = 0;
 		struct mvpp2_bm_pool *bm_pool;
 		struct page_pool *pp = NULL;
 		struct sk_buff *skb;
 		unsigned int frag_size;
 		dma_addr_t dma_addr;
 		phys_addr_t phys_addr;
-		u32 rx_status, timestamp;
 		int pool, rx_bytes, err, ret;
 		struct page *page;
 		void *data;
@@ -3983,7 +3983,7 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 			xdp_init_buff(&xdp, PAGE_SIZE, xdp_rxq);
 			xdp_prepare_buff(&xdp, data,
 					 MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM,
-					 rx_bytes, false);
+					 rx_bytes, true);
 
 			ret = mvpp2_run_xdp(port, xdp_prog, &xdp, pp, &ps);
 
@@ -3999,6 +3999,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 				ps.rx_bytes += rx_bytes;
 				continue;
 			}
+
+			metasize = xdp.data - xdp.data_meta;
 		}
 
 		if (frag_size)
@@ -4038,6 +4040,8 @@ static int mvpp2_rx(struct mvpp2_port *port, struct napi_struct *napi,
 
 		skb_reserve(skb, MVPP2_MH_SIZE + MVPP2_SKB_HEADROOM);
 		skb_put(skb, rx_bytes);
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		skb->ip_summed = mvpp2_rx_csum(port, rx_status);
 		skb->protocol = eth_type_trans(skb, dev);
 

From 03dce68d70fd6c72311982c0e82f91b3d9b00092 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:07 +0100
Subject: [PATCH 2580/2753] net: netsec: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in netsec driver.
netsec driver sets xdp headroom to NETSEC_RXBUF_HEADROOM:

NETSEC_RXBUF_HEADROOM max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN

so the headroom is large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Acked-by: Ilias Apalodimas <ilias.apalodimas@linaro.org>
Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/socionext/netsec.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c
index dc99821c6226f..ee890de69ffe7 100644
--- a/drivers/net/ethernet/socionext/netsec.c
+++ b/drivers/net/ethernet/socionext/netsec.c
@@ -970,7 +970,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		struct netsec_de *de = dring->vaddr + (DESC_SZ * idx);
 		struct netsec_desc *desc = &dring->desc[idx];
 		struct page *page = virt_to_page(desc->addr);
-		u32 xdp_result = NETSEC_XDP_PASS;
+		u32 metasize, xdp_result = NETSEC_XDP_PASS;
 		struct sk_buff *skb = NULL;
 		u16 pkt_len, desc_len;
 		dma_addr_t dma_handle;
@@ -1019,7 +1019,7 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 		prefetch(desc->addr);
 
 		xdp_prepare_buff(&xdp, desc->addr, NETSEC_RXBUF_HEADROOM,
-				 pkt_len, false);
+				 pkt_len, true);
 
 		if (xdp_prog) {
 			xdp_result = netsec_run_xdp(priv, xdp_prog, &xdp);
@@ -1048,6 +1048,9 @@ static int netsec_process_rx(struct netsec_priv *priv, int budget)
 
 		skb_reserve(skb, xdp.data - xdp.data_hard_start);
 		skb_put(skb, xdp.data_end - xdp.data);
+		metasize = xdp.data - xdp.data_meta;
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		skb->protocol = eth_type_trans(skb, priv->ndev);
 
 		if (priv->rx_cksum_offload_flag &&

From 84395345a3f225e8615f95bf947daf362080b369 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:08 +0100
Subject: [PATCH 2581/2753] net: octeontx2: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in octeontx2 driver.
octeontx2 driver sets xdp headroom to OTX2_HEAD_ROOM

OTX2_HEAD_ROOM	OTX2_ALIGN
OTX2_ALIGN	128

so the headroom is large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/marvell/octeontx2/nic/otx2_txrx.c  | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
index 6bc5ce5a9f61c..af8cabe828d05 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c
@@ -41,7 +41,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush);
+				     u32 *metasize, bool *need_xdp_flush);
 
 static void otx2_sq_set_sqe_base(struct otx2_snd_queue *sq,
 				 struct sk_buff *skb)
@@ -336,6 +336,7 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	struct nix_rx_sg_s *sg = &cqe->sg;
 	struct sk_buff *skb = NULL;
 	void *end, *start;
+	u32 metasize = 0;
 	u64 *seg_addr;
 	u16 *seg_size;
 	int seg;
@@ -346,7 +347,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 	}
 
 	if (pfvf->xdp_prog)
-		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq, need_xdp_flush))
+		if (otx2_xdp_rcv_pkt_handler(pfvf, pfvf->xdp_prog, cqe, cq,
+					     &metasize, need_xdp_flush))
 			return;
 
 	skb = napi_get_frags(napi);
@@ -378,6 +380,8 @@ static void otx2_rcv_pkt_handler(struct otx2_nic *pfvf,
 		skb->mark = parse->match_id;
 
 	skb_mark_for_recycle(skb);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 
 	napi_gro_frags(napi);
 }
@@ -1482,7 +1486,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct bpf_prog *prog,
 				     struct nix_cqe_rx_s *cqe,
 				     struct otx2_cq_queue *cq,
-				     bool *need_xdp_flush)
+				     u32 *metasize, bool *need_xdp_flush)
 {
 	struct xdp_buff xdp, *xsk_buff = NULL;
 	unsigned char *hard_start;
@@ -1514,13 +1518,14 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	hard_start = (unsigned char *)phys_to_virt(pa);
 	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
-			 cqe->sg.seg_size, false);
+			 cqe->sg.seg_size, true);
 
 	act = bpf_prog_run_xdp(prog, &xdp);
 
 handle_xdp_verdict:
 	switch (act) {
 	case XDP_PASS:
+		*metasize = xdp.data - xdp.data_meta;
 		break;
 	case XDP_TX:
 		qidx += pfvf->hw.tx_queues;

From 0b47eee7b89170e1a626696a06897a4f8581ba52 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:09 +0100
Subject: [PATCH 2582/2753] net: ethernet: mediatek: Add metadata support for
 xdp mode

Set metadata size building the skb from xdp_buff in mediatek driver.
mtk_eth_soc driver sets xdp headroom to XDP_PACKET_HEADROOM so the
headroom is large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 922330b3f4d70..43197b28b3e74 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -2122,7 +2122,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 		if (ring->page_pool) {
 			struct page *page = virt_to_head_page(data);
 			struct xdp_buff xdp;
-			u32 ret;
+			u32 ret, metasize;
 
 			new_data = mtk_page_pool_get_buff(ring->page_pool,
 							  &dma_addr,
@@ -2138,7 +2138,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			xdp_init_buff(&xdp, PAGE_SIZE, &ring->xdp_q);
 			xdp_prepare_buff(&xdp, data, MTK_PP_HEADROOM, pktlen,
-					 false);
+					 true);
 			xdp_buff_clear_frags_flag(&xdp);
 
 			ret = mtk_xdp_run(eth, ring, &xdp, netdev);
@@ -2158,6 +2158,9 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget,
 
 			skb_reserve(skb, xdp.data - xdp.data_hard_start);
 			skb_put(skb, xdp.data_end - xdp.data);
+			metasize = xdp.data - xdp.data_meta;
+			if (metasize)
+				skb_metadata_set(skb, metasize);
 			skb_mark_for_recycle(skb);
 		} else {
 			if (ring->frag_size <= PAGE_SIZE)

From a6d9e31ae9ed7a442aec6aa5689be5fd115116b6 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:10 +0100
Subject: [PATCH 2583/2753] net: mana: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in mana driver.
mana driver sets xdp headroom to XDP_PACKET_HEADROOM so the headroom is
large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/microsoft/mana/mana_bpf.c | 2 +-
 drivers/net/ethernet/microsoft/mana/mana_en.c  | 4 ++++
 2 files changed, 5 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_bpf.c b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
index 23b1521c0df96..d30721d4516fc 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_bpf.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_bpf.c
@@ -91,7 +91,7 @@ u32 mana_run_xdp(struct net_device *ndev, struct mana_rxq *rxq,
 		goto out;
 
 	xdp_init_buff(xdp, PAGE_SIZE, &rxq->xdp_rxq);
-	xdp_prepare_buff(xdp, buf_va, XDP_PACKET_HEADROOM, pkt_len, false);
+	xdp_prepare_buff(xdp, buf_va, XDP_PACKET_HEADROOM, pkt_len, true);
 
 	act = bpf_prog_run_xdp(prog, xdp);
 
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index 9a8171f099b63..e190d5ee51544 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1559,8 +1559,12 @@ static struct sk_buff *mana_build_skb(struct mana_rxq *rxq, void *buf_va,
 		return NULL;
 
 	if (xdp->data_hard_start) {
+		u32 metasize = xdp->data - xdp->data_meta;
+
 		skb_reserve(skb, xdp->data - xdp->data_hard_start);
 		skb_put(skb, xdp->data_end - xdp->data);
+		if (metasize)
+			skb_metadata_set(skb, metasize);
 		return skb;
 	}
 

From e7710d14791cb6766da85e88b6c54993ef6c87b7 Mon Sep 17 00:00:00 2001
From: Lorenzo Bianconi <lorenzo@kernel.org>
Date: Tue, 18 Mar 2025 12:46:11 +0100
Subject: [PATCH 2584/2753] net: ti: cpsw: Add metadata support for xdp mode

Set metadata size building the skb from xdp_buff in cpsw/cpsw_new
drivers. ti cpsw and cpsw_new drivers set xdp headroom at least to
CPSW_HEADROOM_NA:

CPSW_HEADROOM_NA max(XDP_PACKET_HEADROOM, NET_SKB_PAD) + NET_IP_ALIGN

so the headroom is large enough to contain xdp_frame and xdp metadata.
Please note this patch is just compiled tested.

Reviewed-by: Michal Kubiak <michal.kubiak@intel.com>
Signed-off-by: Lorenzo Bianconi <lorenzo@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/ti/cpsw.c     | 6 +++++-
 drivers/net/ethernet/ti/cpsw_new.c | 6 +++++-
 2 files changed, 10 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c
index 0cb6fa6e5b7d4..a984b7d84e5e5 100644
--- a/drivers/net/ethernet/ti/cpsw.c
+++ b/drivers/net/ethernet/ti/cpsw.c
@@ -351,6 +351,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	int			ret = 0, port, ch = xmeta->ch;
 	int			headroom = CPSW_HEADROOM_NA;
 	struct net_device	*ndev = xmeta->ndev;
+	u32			metasize = 0;
 	struct cpsw_priv	*priv;
 	struct page_pool	*pool;
 	struct sk_buff		*skb;
@@ -400,7 +401,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			size -= CPSW_RX_VLAN_ENCAP_HDR_SIZE;
 		}
 
-		xdp_prepare_buff(&xdp, pa, headroom, size, false);
+		xdp_prepare_buff(&xdp, pa, headroom, size, true);
 
 		port = priv->emac_port + cpsw->data.dual_emac;
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, port, &len);
@@ -408,6 +409,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			goto requeue;
 
 		headroom = xdp.data - xdp.data_hard_start;
+		metasize = xdp.data - xdp.data_meta;
 
 		/* XDP prog can modify vlan tag, so can't use encap header */
 		status &= ~CPDMA_RX_VLAN_ENCAP;
@@ -423,6 +425,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 
 	skb_reserve(skb, headroom);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->dev = ndev;
 	if (status & CPDMA_RX_VLAN_ENCAP)
 		cpsw_rx_vlan_encap(skb);
diff --git a/drivers/net/ethernet/ti/cpsw_new.c b/drivers/net/ethernet/ti/cpsw_new.c
index 3da1c131335df..5b5b52e4e7a75 100644
--- a/drivers/net/ethernet/ti/cpsw_new.c
+++ b/drivers/net/ethernet/ti/cpsw_new.c
@@ -293,6 +293,7 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	struct page_pool *pool;
 	struct sk_buff *skb;
 	struct xdp_buff xdp;
+	u32 metasize = 0;
 	int ret = 0;
 	dma_addr_t dma;
 
@@ -345,13 +346,14 @@ static void cpsw_rx_handler(void *token, int len, int status)
 			size -= CPSW_RX_VLAN_ENCAP_HDR_SIZE;
 		}
 
-		xdp_prepare_buff(&xdp, pa, headroom, size, false);
+		xdp_prepare_buff(&xdp, pa, headroom, size, true);
 
 		ret = cpsw_run_xdp(priv, ch, &xdp, page, priv->emac_port, &len);
 		if (ret != CPSW_XDP_PASS)
 			goto requeue;
 
 		headroom = xdp.data - xdp.data_hard_start;
+		metasize = xdp.data - xdp.data_meta;
 
 		/* XDP prog can modify vlan tag, so can't use encap header */
 		status &= ~CPDMA_RX_VLAN_ENCAP;
@@ -368,6 +370,8 @@ static void cpsw_rx_handler(void *token, int len, int status)
 	skb->offload_fwd_mark = priv->offload_fwd_mark;
 	skb_reserve(skb, headroom);
 	skb_put(skb, len);
+	if (metasize)
+		skb_metadata_set(skb, metasize);
 	skb->dev = ndev;
 	if (status & CPDMA_RX_VLAN_ENCAP)
 		cpsw_rx_vlan_encap(skb);

From 1d450a8de9b80e333449b662ed75d2e743f9d15f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 18 Mar 2025 13:57:14 +0200
Subject: [PATCH 2585/2753] net: dsa: sja1105: fix displaced ethtool statistics
 counters

Port counters with no name (aka
sja1105_port_counters[__SJA1105_COUNTER_UNUSED]) are skipped when
reporting sja1105_get_sset_count(), but are not skipped during
sja1105_get_strings() and sja1105_get_ethtool_stats().

As a consequence, the first reported counter has an empty name and a
bogus value (reads from area 0, aka MAC, from offset 0, bits start:end
0:0). Also, the last counter (N_NOT_REACH on E/T, N_RX_BCAST on P/Q/R/S)
gets pushed out of the statistics counters that get shown.

Skip __SJA1105_COUNTER_UNUSED consistently, so that the bogus counter
with an empty name disappears, and in its place appears a valid counter.

Fixes: 039b167d68a3 ("net: dsa: sja1105: don't use burst SPI reads for port statistics")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/sja1105/sja1105_ethtool.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_ethtool.c b/drivers/net/dsa/sja1105/sja1105_ethtool.c
index 2ea64b1d026d7..84d7d3f66bd03 100644
--- a/drivers/net/dsa/sja1105/sja1105_ethtool.c
+++ b/drivers/net/dsa/sja1105/sja1105_ethtool.c
@@ -571,6 +571,9 @@ void sja1105_get_ethtool_stats(struct dsa_switch *ds, int port, u64 *data)
 		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
 
 	for (i = 0; i < max_ctr; i++) {
+		if (!strlen(sja1105_port_counters[i].name))
+			continue;
+
 		rc = sja1105_port_counter_read(priv, port, i, &data[k++]);
 		if (rc) {
 			dev_err(ds->dev,
@@ -596,8 +599,12 @@ void sja1105_get_strings(struct dsa_switch *ds, int port,
 	else
 		max_ctr = __MAX_SJA1105PQRS_PORT_COUNTER;
 
-	for (i = 0; i < max_ctr; i++)
+	for (i = 0; i < max_ctr; i++) {
+		if (!strlen(sja1105_port_counters[i].name))
+			continue;
+
 		ethtool_puts(&data, sja1105_port_counters[i].name);
+	}
 }
 
 int sja1105_get_sset_count(struct dsa_switch *ds, int port, int sset)

From a38680fd8a4d512e95f673b289b2ca17613358da Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 18 Mar 2025 13:57:15 +0200
Subject: [PATCH 2586/2753] net: dsa: sja1105: reject other RX filters than
 HWTSTAMP_FILTER_PTP_V2_L2_EVENT

This is all that we can support timestamping, so we shouldn't accept
anything else. Also see sja1105_hwtstamp_get().

To avoid erroring out in an inconsistent state, operate on copies of
priv->hwts_rx_en and priv->hwts_tx_en, and write them back when nothing
else can fail anymore.

Fixes: a602afd200f5 ("net: dsa: sja1105: Expose PTP timestamping ioctls to userspace")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/sja1105/sja1105_ptp.c | 20 +++++++++++++++-----
 1 file changed, 15 insertions(+), 5 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_ptp.c b/drivers/net/dsa/sja1105/sja1105_ptp.c
index a1f4ca6ad888f..08b45fdd1d248 100644
--- a/drivers/net/dsa/sja1105/sja1105_ptp.c
+++ b/drivers/net/dsa/sja1105/sja1105_ptp.c
@@ -61,17 +61,21 @@ enum sja1105_ptp_clk_mode {
 int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
 {
 	struct sja1105_private *priv = ds->priv;
+	unsigned long hwts_tx_en, hwts_rx_en;
 	struct hwtstamp_config config;
 
 	if (copy_from_user(&config, ifr->ifr_data, sizeof(config)))
 		return -EFAULT;
 
+	hwts_tx_en = priv->hwts_tx_en;
+	hwts_rx_en = priv->hwts_rx_en;
+
 	switch (config.tx_type) {
 	case HWTSTAMP_TX_OFF:
-		priv->hwts_tx_en &= ~BIT(port);
+		hwts_tx_en &= ~BIT(port);
 		break;
 	case HWTSTAMP_TX_ON:
-		priv->hwts_tx_en |= BIT(port);
+		hwts_tx_en |= BIT(port);
 		break;
 	default:
 		return -ERANGE;
@@ -79,15 +83,21 @@ int sja1105_hwtstamp_set(struct dsa_switch *ds, int port, struct ifreq *ifr)
 
 	switch (config.rx_filter) {
 	case HWTSTAMP_FILTER_NONE:
-		priv->hwts_rx_en &= ~BIT(port);
+		hwts_rx_en &= ~BIT(port);
 		break;
-	default:
-		priv->hwts_rx_en |= BIT(port);
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+		hwts_rx_en |= BIT(port);
 		break;
+	default:
+		return -ERANGE;
 	}
 
 	if (copy_to_user(ifr->ifr_data, &config, sizeof(config)))
 		return -EFAULT;
+
+	priv->hwts_tx_en = hwts_tx_en;
+	priv->hwts_rx_en = hwts_rx_en;
+
 	return 0;
 }
 

From d5d1743047d846a3f9a3254eeaaf1500630fc89f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Tue, 18 Mar 2025 13:57:16 +0200
Subject: [PATCH 2587/2753] net: dsa: sja1105: fix kasan out-of-bounds warning
 in sja1105_table_delete_entry()

There are actually 2 problems:
- deleting the last element doesn't require the memmove of elements
  [i + 1, end) over it. Actually, element i+1 is out of bounds.
- The memmove itself should move size - i - 1 elements, because the last
  element is out of bounds.

The out-of-bounds element still remains out of bounds after being
accessed, so the problem is only that we touch it, not that it becomes
in active use. But I suppose it can lead to issues if the out-of-bounds
element is part of an unmapped page.

Fixes: 6666cebc5e30 ("net: dsa: sja1105: Add support for VLAN operations")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/sja1105/sja1105_static_config.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/dsa/sja1105/sja1105_static_config.c b/drivers/net/dsa/sja1105/sja1105_static_config.c
index 3d790f8c6f4da..ffece8a400a66 100644
--- a/drivers/net/dsa/sja1105/sja1105_static_config.c
+++ b/drivers/net/dsa/sja1105/sja1105_static_config.c
@@ -1917,8 +1917,10 @@ int sja1105_table_delete_entry(struct sja1105_table *table, int i)
 	if (i > table->entry_count)
 		return -ERANGE;
 
-	memmove(entries + i * entry_size, entries + (i + 1) * entry_size,
-		(table->entry_count - i) * entry_size);
+	if (i + 1 < table->entry_count) {
+		memmove(entries + i * entry_size, entries + (i + 1) * entry_size,
+			(table->entry_count - i - 1) * entry_size);
+	}
 
 	table->entry_count--;
 

From 51ad6e01c568bfe0c6660b3bc0847068b035c473 Mon Sep 17 00:00:00 2001
From: "Lucien.Jheng" <lucienx123@gmail.com>
Date: Tue, 18 Mar 2025 21:31:05 +0800
Subject: [PATCH 2588/2753] net: phy: air_en8811h: Add clk provider for CKO pin

EN8811H outputs 25MHz or 50MHz clocks on CKO, selected by GPIO3.
CKO clock operates continuously from power-up through md32 loading.
Implement clk provider driver so we can disable the clock output in case
it isn't needed, which also helps to reduce EMF noise

Signed-off-by: Lucien.Jheng <lucienX123@gmail.com>
Reviewed-by: Daniel Golle <daniel@makrotopia.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/air_en8811h.c | 95 +++++++++++++++++++++++++++++++++++
 1 file changed, 95 insertions(+)

diff --git a/drivers/net/phy/air_en8811h.c b/drivers/net/phy/air_en8811h.c
index e9fd24cb72709..47ace7fac1d39 100644
--- a/drivers/net/phy/air_en8811h.c
+++ b/drivers/net/phy/air_en8811h.c
@@ -16,6 +16,7 @@
 #include <linux/property.h>
 #include <linux/wordpart.h>
 #include <linux/unaligned.h>
+#include <linux/clk-provider.h>
 
 #define EN8811H_PHY_ID		0x03a2a411
 
@@ -112,6 +113,11 @@
 #define   EN8811H_POLARITY_TX_NORMAL		BIT(0)
 #define   EN8811H_POLARITY_RX_REVERSE		BIT(1)
 
+#define EN8811H_CLK_CGM     0xcf958
+#define EN8811H_CLK_CGM_CKO     BIT(26)
+#define EN8811H_HWTRAP1     0xcf914
+#define EN8811H_HWTRAP1_CKO     BIT(12)
+
 #define EN8811H_GPIO_OUTPUT		0xcf8b8
 #define   EN8811H_GPIO_OUTPUT_345		(BIT(3) | BIT(4) | BIT(5))
 
@@ -142,10 +148,15 @@ struct led {
 	unsigned long state;
 };
 
+#define clk_hw_to_en8811h_priv(_hw)			\
+	container_of(_hw, struct en8811h_priv, hw)
+
 struct en8811h_priv {
 	u32		firmware_version;
 	bool		mcu_needs_restart;
 	struct led	led[EN8811H_LED_COUNT];
+	struct clk_hw        hw;
+	struct phy_device *phydev;
 };
 
 enum {
@@ -806,6 +817,84 @@ static int en8811h_led_hw_is_supported(struct phy_device *phydev, u8 index,
 	return 0;
 };
 
+static unsigned long en8811h_clk_recalc_rate(struct clk_hw *hw, unsigned long parent)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+	u32 pbus_value;
+	int ret;
+
+	ret = air_buckpbus_reg_read(phydev, EN8811H_HWTRAP1, &pbus_value);
+	if (ret < 0)
+		return ret;
+
+	return (pbus_value & EN8811H_HWTRAP1_CKO) ? 50000000 : 25000000;
+}
+
+static int en8811h_clk_enable(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+
+	return air_buckpbus_reg_modify(phydev, EN8811H_CLK_CGM,
+				EN8811H_CLK_CGM_CKO, EN8811H_CLK_CGM_CKO);
+}
+
+static void en8811h_clk_disable(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+
+	air_buckpbus_reg_modify(phydev, EN8811H_CLK_CGM,
+				EN8811H_CLK_CGM_CKO, 0);
+}
+
+static int en8811h_clk_is_enabled(struct clk_hw *hw)
+{
+	struct en8811h_priv *priv = clk_hw_to_en8811h_priv(hw);
+	struct phy_device *phydev = priv->phydev;
+	int ret = 0;
+	u32 pbus_value;
+
+	ret = air_buckpbus_reg_read(phydev, EN8811H_CLK_CGM, &pbus_value);
+	if (ret < 0)
+		return ret;
+
+	return (pbus_value & EN8811H_CLK_CGM_CKO);
+}
+
+static const struct clk_ops en8811h_clk_ops = {
+	.recalc_rate = en8811h_clk_recalc_rate,
+	.enable = en8811h_clk_enable,
+	.disable = en8811h_clk_disable,
+	.is_enabled	= en8811h_clk_is_enabled,
+};
+
+static int en8811h_clk_provider_setup(struct device *dev, struct clk_hw *hw)
+{
+	struct clk_init_data init;
+	int ret;
+
+	if (!IS_ENABLED(CONFIG_COMMON_CLK))
+		return 0;
+
+	init.name =  devm_kasprintf(dev, GFP_KERNEL, "%s-cko",
+				    fwnode_get_name(dev_fwnode(dev)));
+	if (!init.name)
+		return -ENOMEM;
+
+	init.ops = &en8811h_clk_ops;
+	init.flags = 0;
+	init.num_parents = 0;
+	hw->init = &init;
+
+	ret = devm_clk_hw_register(dev, hw);
+	if (ret)
+		return ret;
+
+	return devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, hw);
+}
+
 static int en8811h_probe(struct phy_device *phydev)
 {
 	struct en8811h_priv *priv;
@@ -838,6 +927,12 @@ static int en8811h_probe(struct phy_device *phydev)
 		return ret;
 	}
 
+	priv->phydev = phydev;
+	/* Co-Clock Output */
+	ret = en8811h_clk_provider_setup(&phydev->mdio.dev, &priv->hw);
+	if (ret)
+		return ret;
+
 	/* Configure led gpio pins as output */
 	ret = air_buckpbus_reg_modify(phydev, EN8811H_GPIO_OUTPUT,
 				      EN8811H_GPIO_OUTPUT_345,

From 25996bafccbceac7ce195f55d4bb28fd29c5731e Mon Sep 17 00:00:00 2001
From: Pablo Martin Medrano <pablmart@redhat.com>
Date: Tue, 18 Mar 2025 14:42:50 +0100
Subject: [PATCH 2589/2753] selftests/net: big_tcp: return xfail on slow
 machines

After debugging the following output for big_tcp.sh on a board:

CLI GSO | GW GRO | GW GSO | SER GRO
on        on       on       on      : [PASS]
on        off      on       off     : [PASS]
off       on       on       on      : [FAIL_on_link1]
on        on       off      on      : [FAIL_on_link1]

Davide Caratti found that by default the test duration 1s is too short
in slow systems to reach the correct cwd size necessary for tcp/ip to
generate at least one packet bigger than 65536 (matching the iptables
match on length rule the test evaluates)

This skips (with xfail) the aforementioned failing combinations when
KSFT_MACHINE_SLOW is set. For that the test has been modified to use
facilities from net/lib.sh.

The new output for the test will look like this (example with a forced
XFAIL)

Testing for BIG TCP:
      CLI GSO | GW GRO | GW GSO | SER GRO
TEST: on        on       on       on                    [ OK ]
TEST: on        off      on       off                   [ OK ]
TEST: off       on       on       on                    [XFAIL]

Fixes: a19747c3b9bf ("selftests: net: let big_tcp test cope with slow env")
Suggested-by: Davide Caratti <dcaratti@redhat.com>
Suggested-by: Petr Machata <petrm@nvidia.com>
Signed-off-by: Pablo Martin Medrano <pablmart@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/big_tcp.sh | 23 +++++++++++------------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/big_tcp.sh b/tools/testing/selftests/net/big_tcp.sh
index 2db9d15cd45fe..52b9a76b1c194 100755
--- a/tools/testing/selftests/net/big_tcp.sh
+++ b/tools/testing/selftests/net/big_tcp.sh
@@ -21,8 +21,7 @@ CLIENT_GW6="2001:db8:1::2"
 MAX_SIZE=128000
 CHK_SIZE=65535
 
-# Kselftest framework requirement - SKIP code is 4.
-ksft_skip=4
+source lib.sh
 
 setup() {
 	ip netns add $CLIENT_NS
@@ -143,21 +142,20 @@ do_test() {
 	start_counter link3 $SERVER_NS
 	do_netperf $CLIENT_NS
 
-	if check_counter link1 $ROUTER_NS; then
-		check_counter link3 $SERVER_NS || ret="FAIL_on_link3"
-	else
-		ret="FAIL_on_link1"
-	fi
+	check_counter link1 $ROUTER_NS
+	check_err $? "fail on link1"
+	check_counter link3 $SERVER_NS
+	check_err $? "fail on link3"
 
 	stop_counter link1 $ROUTER_NS
 	stop_counter link3 $SERVER_NS
-	printf "%-9s %-8s %-8s %-8s: [%s]\n" \
-		$cli_tso $gw_gro $gw_tso $ser_gro $ret
-	test $ret = "PASS"
+	log_test "$(printf "%-9s %-8s %-8s %-8s" \
+			$cli_tso $gw_gro $gw_tso $ser_gro)"
+	test $RET -eq 0
 }
 
 testup() {
-	echo "CLI GSO | GW GRO | GW GSO | SER GRO" && \
+	echo "      CLI GSO | GW GRO | GW GSO | SER GRO" && \
 	do_test "on"  "on"  "on"  "on"  && \
 	do_test "on"  "off" "on"  "off" && \
 	do_test "off" "on"  "on"  "on"  && \
@@ -176,7 +174,8 @@ if ! ip link help 2>&1 | grep gso_ipv4_max_size &> /dev/null; then
 fi
 
 trap cleanup EXIT
+xfail_on_slow
 setup && echo "Testing for BIG TCP:" && \
 NF=4 testup && echo "***v4 Tests Done***" && \
 NF=6 testup && echo "***v6 Tests Done***"
-exit $?
+exit $EXIT_STATUS

From b4aca49457ce7d86947272946c1e092091c2507c Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Tue, 18 Mar 2025 13:53:34 +0000
Subject: [PATCH 2590/2753] net: tulip: avoid unused variable warning
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There is an effort to achieve W=1 kernel builds without warnings.
As part of that effort Helge Deller highlighted the following warnings
in the tulip driver when compiling with W=1 and CONFIG_TULIP_MWI=n:

  .../tulip_core.c: In function ‘tulip_init_one’:
  .../tulip_core.c:1309:22: warning: variable ‘force_csr0’ set but not used

This patch addresses that problem using IS_ENABLED(). This approach has
the added benefit of reducing conditionally compiled code. And thus
increasing compile coverage. E.g. for allmodconfig builds which enable
CONFIG_TULIP_MWI.

Compile tested only.
No run-time effect intended.

Acked-by: Helge Deller <deller@gmx.de>
Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/dec/tulip/tulip_core.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/dec/tulip/tulip_core.c b/drivers/net/ethernet/dec/tulip/tulip_core.c
index 27e01d780cd02..75eac18ff2466 100644
--- a/drivers/net/ethernet/dec/tulip/tulip_core.c
+++ b/drivers/net/ethernet/dec/tulip/tulip_core.c
@@ -1177,7 +1177,6 @@ static void set_rx_mode(struct net_device *dev)
 	iowrite32(csr6, ioaddr + CSR6);
 }
 
-#ifdef CONFIG_TULIP_MWI
 static void tulip_mwi_config(struct pci_dev *pdev, struct net_device *dev)
 {
 	struct tulip_private *tp = netdev_priv(dev);
@@ -1251,7 +1250,6 @@ static void tulip_mwi_config(struct pci_dev *pdev, struct net_device *dev)
 		netdev_dbg(dev, "MWI config cacheline=%d, csr0=%08x\n",
 			   cache, csr0);
 }
-#endif
 
 /*
  *	Chips that have the MRM/reserved bit quirk and the burst quirk. That
@@ -1463,10 +1461,9 @@ static int tulip_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 	INIT_WORK(&tp->media_work, tulip_tbl[tp->chip_id].media_task);
 
-#ifdef CONFIG_TULIP_MWI
-	if (!force_csr0 && (tp->flags & HAS_PCI_MWI))
+	if (IS_ENABLED(CONFIG_TULIP_MWI) && !force_csr0 &&
+	    (tp->flags & HAS_PCI_MWI))
 		tulip_mwi_config (pdev, dev);
-#endif
 
 	/* Stop the chip's Tx and Rx processes. */
 	tulip_stop_rxtx(tp);

From 4775cad5657eee1fda683f64816e3b438a19525c Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:14:50 +0800
Subject: [PATCH 2591/2753] xsc: Add xsc driver basic framework

1. Add yunsilicon xsc driver basic compile framework, including
xsc_pci driver and xsc_eth driver
2. Implemented PCI device initialization.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 MAINTAINERS                                   |   7 +
 drivers/net/ethernet/Kconfig                  |   1 +
 drivers/net/ethernet/Makefile                 |   1 +
 drivers/net/ethernet/yunsilicon/Kconfig       |  26 +++
 drivers/net/ethernet/yunsilicon/Makefile      |   7 +
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |  43 ++++
 .../net/ethernet/yunsilicon/xsc/net/Kconfig   |  17 ++
 .../net/ethernet/yunsilicon/xsc/net/Makefile  |   9 +
 .../net/ethernet/yunsilicon/xsc/pci/Kconfig   |  14 ++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   9 +
 .../net/ethernet/yunsilicon/xsc/pci/main.c    | 214 ++++++++++++++++++
 11 files changed, 348 insertions(+)
 create mode 100644 drivers/net/ethernet/yunsilicon/Kconfig
 create mode 100644 drivers/net/ethernet/yunsilicon/Makefile
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/Kconfig
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/Makefile
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/Kconfig
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/main.c

diff --git a/MAINTAINERS b/MAINTAINERS
index 5255a8f251bf6..db648902cd325 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -26237,6 +26237,13 @@ S:	Maintained
 F:	Documentation/input/devices/yealink.rst
 F:	drivers/input/misc/yealink.*
 
+YUNSILICON XSC DRIVERS
+M:	Honggang Wei <weihg@yunsilicon.com>
+M:	Xin Tian <tianx@yunsilicon.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ethernet/yunsilicon/xsc
+
 Z3FOLD COMPRESSED PAGE ALLOCATOR
 M:	Vitaly Wool <vitaly.wool@konsulko.com>
 R:	Miaohe Lin <linmiaohe@huawei.com>
diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig
index f86d4557d8d77..0dcc72d75311a 100644
--- a/drivers/net/ethernet/Kconfig
+++ b/drivers/net/ethernet/Kconfig
@@ -83,6 +83,7 @@ source "drivers/net/ethernet/i825xx/Kconfig"
 source "drivers/net/ethernet/ibm/Kconfig"
 source "drivers/net/ethernet/intel/Kconfig"
 source "drivers/net/ethernet/xscale/Kconfig"
+source "drivers/net/ethernet/yunsilicon/Kconfig"
 
 config JME
 	tristate "JMicron(R) PCI-Express Gigabit Ethernet support"
diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile
index 67182339469a0..1a1b54ce202c0 100644
--- a/drivers/net/ethernet/Makefile
+++ b/drivers/net/ethernet/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_NET_VENDOR_INTEL) += intel/
 obj-$(CONFIG_NET_VENDOR_I825XX) += i825xx/
 obj-$(CONFIG_NET_VENDOR_MICROSOFT) += microsoft/
 obj-$(CONFIG_NET_VENDOR_XSCALE) += xscale/
+obj-$(CONFIG_NET_VENDOR_YUNSILICON) += yunsilicon/
 obj-$(CONFIG_JME) += jme.o
 obj-$(CONFIG_KORINA) += korina.o
 obj-$(CONFIG_LANTIQ_ETOP) += lantiq_etop.o
diff --git a/drivers/net/ethernet/yunsilicon/Kconfig b/drivers/net/ethernet/yunsilicon/Kconfig
new file mode 100644
index 0000000000000..1bf5b7fcf1ba1
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/Kconfig
@@ -0,0 +1,26 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+# Yunsilicon driver configuration
+#
+
+config NET_VENDOR_YUNSILICON
+	bool "Yunsilicon devices"
+	default y
+	depends on PCI
+	depends on ARM64 || X86_64 || COMPILE_TEST
+	help
+	  If you have a network (Ethernet) device belonging to this class,
+	  say Y.
+
+	  Note that the answer to this question doesn't directly affect the
+	  kernel: saying N will just cause the configurator to skip all
+	  the questions about Yunsilicon cards. If you say Y, you will be asked
+	  for your specific card in the following questions.
+
+if NET_VENDOR_YUNSILICON
+
+source "drivers/net/ethernet/yunsilicon/xsc/net/Kconfig"
+source "drivers/net/ethernet/yunsilicon/xsc/pci/Kconfig"
+
+endif # NET_VENDOR_YUNSILICON
diff --git a/drivers/net/ethernet/yunsilicon/Makefile b/drivers/net/ethernet/yunsilicon/Makefile
new file mode 100644
index 0000000000000..05aa35c3c8e18
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/Makefile
@@ -0,0 +1,7 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+# Makefile for the Yunsilicon device drivers.
+#
+
+obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc/pci/
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
new file mode 100644
index 0000000000000..0673e34fe6ac6
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_CORE_H
+#define __XSC_CORE_H
+
+#include <linux/pci.h>
+
+#define XSC_PCI_VENDOR_ID		0x1f67
+
+#define XSC_MC_PF_DEV_ID		0x1011
+#define XSC_MC_VF_DEV_ID		0x1012
+#define XSC_MC_PF_DEV_ID_DIAMOND	0x1021
+
+#define XSC_MF_HOST_PF_DEV_ID		0x1051
+#define XSC_MF_HOST_VF_DEV_ID		0x1052
+#define XSC_MF_SOC_PF_DEV_ID		0x1053
+
+#define XSC_MS_PF_DEV_ID		0x1111
+#define XSC_MS_VF_DEV_ID		0x1112
+
+#define XSC_MV_HOST_PF_DEV_ID		0x1151
+#define XSC_MV_HOST_VF_DEV_ID		0x1152
+#define XSC_MV_SOC_PF_DEV_ID		0x1153
+
+struct xsc_dev_resource {
+	/* protect buffer allocation according to numa node */
+	struct mutex		alloc_mutex;
+};
+
+struct xsc_core_device {
+	struct pci_dev		*pdev;
+	struct device		*device;
+	struct xsc_dev_resource	*dev_res;
+	int			numa_node;
+
+	void __iomem		*bar;
+	int			bar_num;
+};
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Kconfig b/drivers/net/ethernet/yunsilicon/xsc/net/Kconfig
new file mode 100644
index 0000000000000..b2f95370fdaa3
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Kconfig
@@ -0,0 +1,17 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+# Yunsilicon driver configuration
+#
+
+config YUNSILICON_XSC_ETH
+	tristate "Yunsilicon XSC ethernet driver"
+	depends on YUNSILICON_XSC_PCI
+	depends on NET
+	select PAGE_POOL
+	help
+	  This driver provides ethernet support for
+	  Yunsilicon XSC devices.
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called xsc_eth.
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
new file mode 100644
index 0000000000000..53300be3c78e9
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+
+ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
+
+obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc_eth.o
+
+xsc_eth-y := main.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Kconfig b/drivers/net/ethernet/yunsilicon/xsc/pci/Kconfig
new file mode 100644
index 0000000000000..b707da28b0a9c
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Kconfig
@@ -0,0 +1,14 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+# Yunsilicon PCI configuration
+#
+
+config YUNSILICON_XSC_PCI
+	tristate "Yunsilicon XSC PCI driver"
+	help
+	  This driver is common for Yunsilicon XSC
+	  ethernet and RDMA drivers.
+
+	  To compile this driver as a module, choose M here. The module
+	  will be called xsc_pci.
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
new file mode 100644
index 0000000000000..709270df85a75
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -0,0 +1,9 @@
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+# All rights reserved.
+
+ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
+
+obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
+
+xsc_pci-y := main.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
new file mode 100644
index 0000000000000..b8fc256792d12
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -0,0 +1,214 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include "common/xsc_core.h"
+
+static const struct pci_device_id xsc_pci_id_table[] = {
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID_DIAMOND) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MF_HOST_PF_DEV_ID) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MF_SOC_PF_DEV_ID) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MS_PF_DEV_ID) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MV_HOST_PF_DEV_ID) },
+	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MV_SOC_PF_DEV_ID) },
+	{ 0 }
+};
+
+static int xsc_set_dma_caps(struct pci_dev *pdev)
+{
+	int err;
+
+	err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (!err)
+		dma_set_max_seg_size(&pdev->dev, SZ_2G);
+
+	return err;
+}
+
+static int xsc_pci_init(struct xsc_core_device *xdev,
+			const struct pci_device_id *id)
+{
+	struct pci_dev *pdev = xdev->pdev;
+	void __iomem *bar_base;
+	int bar_num = 0;
+	int err;
+
+	xdev->numa_node = dev_to_node(&pdev->dev);
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		pci_err(pdev, "failed to enable PCI device: err=%d\n", err);
+		goto err_out;
+	}
+
+	err = pci_request_region(pdev, bar_num, KBUILD_MODNAME);
+	if (err) {
+		pci_err(pdev, "failed to request %s pci_region=%d: err=%d\n",
+			KBUILD_MODNAME, bar_num, err);
+		goto err_disable;
+	}
+
+	pci_set_master(pdev);
+
+	err = xsc_set_dma_caps(pdev);
+	if (err) {
+		pci_err(pdev, "failed to set DMA capabilities mask: err=%d\n",
+			err);
+		goto err_clr_master;
+	}
+
+	bar_base = pci_ioremap_bar(pdev, bar_num);
+	if (!bar_base) {
+		pci_err(pdev, "failed to ioremap %s bar%d\n", KBUILD_MODNAME,
+			bar_num);
+		err = -ENOMEM;
+		goto err_clr_master;
+	}
+
+	err = pci_save_state(pdev);
+	if (err) {
+		pci_err(pdev, "pci_save_state failed: err=%d\n", err);
+		goto err_io_unmap;
+	}
+
+	xdev->bar_num = bar_num;
+	xdev->bar = bar_base;
+
+	return 0;
+
+err_io_unmap:
+	pci_iounmap(pdev, bar_base);
+err_clr_master:
+	pci_clear_master(pdev);
+	pci_release_region(pdev, bar_num);
+err_disable:
+	pci_disable_device(pdev);
+err_out:
+	return err;
+}
+
+static void xsc_pci_fini(struct xsc_core_device *xdev)
+{
+	struct pci_dev *pdev = xdev->pdev;
+
+	pci_iounmap(pdev, xdev->bar);
+	pci_clear_master(pdev);
+	pci_release_region(pdev, xdev->bar_num);
+	pci_disable_device(pdev);
+}
+
+static int xsc_dev_res_init(struct xsc_core_device *xdev)
+{
+	struct xsc_dev_resource *dev_res;
+
+	dev_res = kvzalloc(sizeof(*dev_res), GFP_KERNEL);
+	if (!dev_res)
+		return -ENOMEM;
+
+	xdev->dev_res = dev_res;
+	mutex_init(&dev_res->alloc_mutex);
+
+	return 0;
+}
+
+static void xsc_dev_res_cleanup(struct xsc_core_device *xdev)
+{
+	kfree(xdev->dev_res);
+}
+
+static int xsc_core_dev_init(struct xsc_core_device *xdev)
+{
+	int err;
+
+	err = xsc_dev_res_init(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc dev res init failed %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void xsc_core_dev_cleanup(struct xsc_core_device *xdev)
+{
+	xsc_dev_res_cleanup(xdev);
+}
+
+static int xsc_pci_probe(struct pci_dev *pci_dev,
+			 const struct pci_device_id *id)
+{
+	struct xsc_core_device *xdev;
+	int err;
+
+	xdev = kzalloc(sizeof(*xdev), GFP_KERNEL);
+	if (!xdev)
+		return -ENOMEM;
+
+	xdev->pdev = pci_dev;
+	xdev->device = &pci_dev->dev;
+
+	pci_set_drvdata(pci_dev, xdev);
+	err = xsc_pci_init(xdev, id);
+	if (err) {
+		pci_err(pci_dev, "xsc_pci_init failed %d\n", err);
+		goto err_unset_pci_drvdata;
+	}
+
+	err = xsc_core_dev_init(xdev);
+	if (err) {
+		pci_err(pci_dev, "xsc_core_dev_init failed %d\n", err);
+		goto err_pci_fini;
+	}
+
+	return 0;
+err_pci_fini:
+	xsc_pci_fini(xdev);
+err_unset_pci_drvdata:
+	pci_set_drvdata(pci_dev, NULL);
+	kfree(xdev);
+
+	return err;
+}
+
+static void xsc_pci_remove(struct pci_dev *pci_dev)
+{
+	struct xsc_core_device *xdev = pci_get_drvdata(pci_dev);
+
+	xsc_core_dev_cleanup(xdev);
+	xsc_pci_fini(xdev);
+	pci_set_drvdata(pci_dev, NULL);
+	kfree(xdev);
+}
+
+static struct pci_driver xsc_pci_driver = {
+	.name		= "xsc-pci",
+	.id_table	= xsc_pci_id_table,
+	.probe		= xsc_pci_probe,
+	.remove		= xsc_pci_remove,
+};
+
+static int __init xsc_init(void)
+{
+	int err;
+
+	err = pci_register_driver(&xsc_pci_driver);
+	if (err) {
+		pr_err("failed to register pci driver\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static void __exit xsc_fini(void)
+{
+	pci_unregister_driver(&xsc_pci_driver);
+}
+
+module_init(xsc_init);
+module_exit(xsc_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Yunsilicon XSC PCI driver");

From 3db26b37d464bc2a79b0c68d2adc61b860a172b0 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:14:53 +0800
Subject: [PATCH 2592/2753] xsc: Enable command queue

The command queue is a hardware channel for sending
commands between the driver and the firmware.
xsc_cmd.h defines the command protocol structures.
The logic for command allocation, sending,
completion handling, and error handling is implemented
in cmdq.c.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../yunsilicon/xsc/common/xsc_auto_hw.h       |   94 +
 .../ethernet/yunsilicon/xsc/common/xsc_cmd.h  |  630 +++++++
 .../ethernet/yunsilicon/xsc/common/xsc_cmdq.h |  234 +++
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |    7 +
 .../yunsilicon/xsc/common/xsc_driver.h        |   26 +
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |    2 +-
 .../net/ethernet/yunsilicon/xsc/pci/cmdq.c    | 1571 +++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |   56 +
 8 files changed, 2619 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_auto_hw.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmd.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmdq.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_driver.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/cmdq.c

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_auto_hw.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_auto_hw.h
new file mode 100644
index 0000000000000..d9d0419e315b8
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_auto_hw.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_HW_H
+#define __XSC_HW_H
+
+/* hif_irq_csr_defines.h */
+#define HIF_IRQ_TBL2IRQ_TBL_RD_DONE_INT_MSIX_REG_ADDR   0xa1100070
+
+/* hif_cpm_csr_defines.h */
+#define HIF_CPM_LOCK_GET_REG_ADDR   0xa0000104
+#define HIF_CPM_LOCK_PUT_REG_ADDR   0xa0000108
+#define HIF_CPM_LOCK_AVAIL_REG_ADDR   0xa000010c
+#define HIF_CPM_IDA_DATA_MEM_ADDR   0xa0000800
+#define HIF_CPM_IDA_CMD_REG_ADDR   0xa0000020
+#define HIF_CPM_IDA_ADDR_REG_ADDR   0xa0000080
+#define HIF_CPM_IDA_BUSY_REG_ADDR   0xa0000100
+#define HIF_CPM_IDA_CMD_REG_IDA_IDX_WIDTH 5
+#define HIF_CPM_IDA_CMD_REG_IDA_LEN_WIDTH 4
+#define HIF_CPM_IDA_CMD_REG_IDA_R0W1_WIDTH 1
+#define HIF_CPM_LOCK_GET_REG_LOCK_VLD_SHIFT 5
+#define HIF_CPM_LOCK_GET_REG_LOCK_IDX_MASK  0x1f
+#define HIF_CPM_IDA_ADDR_REG_STRIDE 0x4
+#define HIF_CPM_CHIP_VERSION_H_REG_ADDR   0xa0000010
+
+/* mmc_csr_defines.h */
+#define MMC_MPT_TBL_MEM_DEPTH  32768
+#define MMC_MTT_TBL_MEM_DEPTH  262144
+#define MMC_MPT_TBL_MEM_WIDTH  256
+#define MMC_MTT_TBL_MEM_WIDTH  64
+#define MMC_MPT_TBL_MEM_ADDR   0xa4100000
+#define MMC_MTT_TBL_MEM_ADDR   0xa4200000
+
+/* clsf_dma_csr_defines.h */
+#define CLSF_DMA_DMA_UL_BUSY_REG_ADDR   0xa6010048
+#define CLSF_DMA_DMA_DL_DONE_REG_ADDR   0xa60100d0
+#define CLSF_DMA_DMA_DL_SUCCESS_REG_ADDR   0xa60100c0
+#define CLSF_DMA_ERR_CODE_CLR_REG_ADDR   0xa60100d4
+#define CLSF_DMA_DMA_RD_TABLE_ID_REG_DMA_RD_TBL_ID_MASK  0x7f
+#define CLSF_DMA_DMA_RD_TABLE_ID_REG_ADDR   0xa6010020
+#define CLSF_DMA_DMA_RD_ADDR_REG_DMA_RD_BURST_NUM_SHIFT 16
+#define CLSF_DMA_DMA_RD_ADDR_REG_ADDR   0xa6010024
+#define CLSF_DMA_INDRW_RD_START_REG_ADDR   0xa6010028
+
+/* hif_tbl_csr_defines.h */
+#define HIF_TBL_TBL_DL_BUSY_REG_ADDR   0xa1060030
+#define HIF_TBL_TBL_DL_REQ_REG_TBL_DL_LEN_SHIFT 12
+#define HIF_TBL_TBL_DL_REQ_REG_TBL_DL_HOST_ID_SHIFT 11
+#define HIF_TBL_TBL_DL_REQ_REG_ADDR   0xa1060020
+#define HIF_TBL_TBL_DL_ADDR_L_REG_TBL_DL_ADDR_L_MASK  0xffffffff
+#define HIF_TBL_TBL_DL_ADDR_L_REG_ADDR   0xa1060024
+#define HIF_TBL_TBL_DL_ADDR_H_REG_TBL_DL_ADDR_H_MASK  0xffffffff
+#define HIF_TBL_TBL_DL_ADDR_H_REG_ADDR   0xa1060028
+#define HIF_TBL_TBL_DL_START_REG_ADDR   0xa106002c
+#define HIF_TBL_TBL_UL_REQ_REG_TBL_UL_HOST_ID_SHIFT 11
+#define HIF_TBL_TBL_UL_REQ_REG_ADDR   0xa106007c
+#define HIF_TBL_TBL_UL_ADDR_L_REG_TBL_UL_ADDR_L_MASK  0xffffffff
+#define HIF_TBL_TBL_UL_ADDR_L_REG_ADDR   0xa1060080
+#define HIF_TBL_TBL_UL_ADDR_H_REG_TBL_UL_ADDR_H_MASK  0xffffffff
+#define HIF_TBL_TBL_UL_ADDR_H_REG_ADDR   0xa1060084
+#define HIF_TBL_TBL_UL_START_REG_ADDR   0xa1060088
+#define HIF_TBL_MSG_RDY_REG_ADDR   0xa1060044
+
+/* hif_cmdqm_csr_defines.h */
+#define HIF_CMDQM_HOST_REQ_PID_MEM_ADDR   0xa1026000
+#define HIF_CMDQM_HOST_REQ_CID_MEM_ADDR   0xa1028000
+#define HIF_CMDQM_HOST_RSP_PID_MEM_ADDR   0xa102e000
+#define HIF_CMDQM_HOST_RSP_CID_MEM_ADDR   0xa1030000
+#define HIF_CMDQM_HOST_REQ_BUF_BASE_H_ADDR_MEM_ADDR   0xa1022000
+#define HIF_CMDQM_HOST_REQ_BUF_BASE_L_ADDR_MEM_ADDR   0xa1024000
+#define HIF_CMDQM_HOST_RSP_BUF_BASE_H_ADDR_MEM_ADDR   0xa102a000
+#define HIF_CMDQM_HOST_RSP_BUF_BASE_L_ADDR_MEM_ADDR   0xa102c000
+#define HIF_CMDQM_VECTOR_ID_MEM_ADDR   0xa1034000
+#define HIF_CMDQM_Q_ELEMENT_SZ_REG_ADDR   0xa1020020
+#define HIF_CMDQM_HOST_Q_DEPTH_REG_ADDR   0xa1020028
+#define HIF_CMDQM_HOST_VF_ERR_STS_MEM_ADDR   0xa1032000
+
+/* PSV use */
+/* hif_irq_csr_defines.h */
+#define HIF_IRQ_CONTROL_TBL_MEM_ADDR   0xa1102000
+#define HIF_IRQ_INT_DB_REG_ADDR   0xa11000b4
+#define HIF_IRQ_CFG_VECTOR_TABLE_BUSY_REG_ADDR   0xa1100114
+#define HIF_IRQ_CFG_VECTOR_TABLE_ADDR_REG_ADDR   0xa11000f0
+#define HIF_IRQ_CFG_VECTOR_TABLE_CMD_REG_ADDR   0xa11000ec
+#define HIF_IRQ_CFG_VECTOR_TABLE_MSG_LADDR_REG_ADDR   0xa11000f4
+#define HIF_IRQ_CFG_VECTOR_TABLE_MSG_UADDR_REG_ADDR   0xa11000f8
+#define HIF_IRQ_CFG_VECTOR_TABLE_MSG_DATA_REG_ADDR   0xa11000fc
+#define HIF_IRQ_CFG_VECTOR_TABLE_CTRL_REG_ADDR   0xa1100100
+#define HIF_IRQ_CFG_VECTOR_TABLE_START_REG_ADDR   0xa11000e8
+
+#endif /* __XSC_HW_H  */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmd.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmd.h
new file mode 100644
index 0000000000000..b830e2a633e0c
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmd.h
@@ -0,0 +1,630 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_CMD_H
+#define __XSC_CMD_H
+
+#define XSC_CMDQ_VERSION	0x32
+
+#define XSC_BOARD_SN_LEN	32
+
+enum {
+	XSC_CMD_STAT_OK				= 0x0,
+	XSC_CMD_STAT_INT_ERR			= 0x1,
+	XSC_CMD_STAT_BAD_OP_ERR			= 0x2,
+	XSC_CMD_STAT_BAD_PARAM_ERR		= 0x3,
+	XSC_CMD_STAT_BAD_SYS_STATE_ERR		= 0x4,
+	XSC_CMD_STAT_BAD_RES_ERR		= 0x5,
+	XSC_CMD_STAT_RES_BUSY			= 0x6,
+	XSC_CMD_STAT_LIM_ERR			= 0x8,
+	XSC_CMD_STAT_BAD_RES_STATE_ERR		= 0x9,
+	XSC_CMD_STAT_IX_ERR			= 0xa,
+	XSC_CMD_STAT_NO_RES_ERR			= 0xf,
+	XSC_CMD_STAT_BAD_QP_STATE_ERR		= 0x10,
+	XSC_CMD_STAT_BAD_PKT_ERR		= 0x30,
+	XSC_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR	= 0x40,
+	XSC_CMD_STAT_BAD_INP_LEN_ERR		= 0x50,
+	XSC_CMD_STAT_BAD_OUTP_LEN_ERR		= 0x51,
+};
+
+enum {
+	XSC_CMD_OP_QUERY_HCA_CAP		= 0x100,
+	XSC_CMD_OP_QUERY_CMDQ_VERSION		= 0x10a,
+	XSC_CMD_OP_FUNCTION_RESET		= 0x10c,
+	XSC_CMD_OP_DUMMY			= 0x10d,
+	XSC_CMD_OP_QUERY_GUID			= 0x113,
+	XSC_CMD_OP_ACTIVATE_HW_CONFIG		= 0x114,
+
+	XSC_CMD_OP_CREATE_EQ			= 0x301,
+	XSC_CMD_OP_DESTROY_EQ			= 0x302,
+
+	XSC_CMD_OP_CREATE_CQ			= 0x400,
+	XSC_CMD_OP_DESTROY_CQ			= 0x401,
+
+	XSC_CMD_OP_CREATE_QP			= 0x500,
+	XSC_CMD_OP_DESTROY_QP			= 0x501,
+	XSC_CMD_OP_RST2INIT_QP			= 0x502,
+	XSC_CMD_OP_INIT2RTR_QP			= 0x503,
+	XSC_CMD_OP_RTR2RTS_QP			= 0x504,
+	XSC_CMD_OP_RTS2RTS_QP			= 0x505,
+	XSC_CMD_OP_SQERR2RTS_QP			= 0x506,
+	XSC_CMD_OP_2ERR_QP			= 0x507,
+	XSC_CMD_OP_RTS2SQD_QP			= 0x508,
+	XSC_CMD_OP_SQD2RTS_QP			= 0x509,
+	XSC_CMD_OP_2RST_QP			= 0x50a,
+	XSC_CMD_OP_INIT2INIT_QP			= 0x50e,
+	XSC_CMD_OP_CREATE_MULTI_QP		= 0x515,
+
+	XSC_CMD_OP_MODIFY_RAW_QP		= 0x81f,
+
+	XSC_CMD_OP_ENABLE_NIC_HCA		= 0x810,
+	XSC_CMD_OP_DISABLE_NIC_HCA		= 0x811,
+
+	XSC_CMD_OP_QUERY_VPORT_STATE		= 0x822,
+	XSC_CMD_OP_QUERY_EVENT_TYPE		= 0x831,
+
+	XSC_CMD_OP_ENABLE_MSIX			= 0x850,
+
+	XSC_CMD_OP_SET_MTU			= 0x1100,
+	XSC_CMD_OP_QUERY_ETH_MAC		= 0X1101,
+
+	XSC_CMD_OP_SET_PORT_ADMIN_STATUS	= 0x1801,
+
+	XSC_CMD_OP_MAX
+};
+
+enum xsc_dma_direct {
+	XSC_DMA_DIR_TO_MAC,
+	XSC_DMA_DIR_READ,
+	XSC_DMA_DIR_WRITE,
+	XSC_DMA_DIR_LOOPBACK,
+	XSC_DMA_DIR_MAX
+};
+
+/* hw feature bitmap, 32bit */
+enum xsc_hw_feature_flag {
+	XSC_HW_RDMA_SUPPORT			= BIT(0),
+	XSC_HW_PFC_PRIO_STATISTIC_SUPPORT	= BIT(1),
+	XSC_HW_PFC_STALL_STATS_SUPPORT		= BIT(3),
+	XSC_HW_RDMA_CM_SUPPORT			= BIT(5),
+
+	XSC_HW_LAST_FEATURE			= BIT(31)
+};
+
+struct xsc_inbox_hdr {
+	__be16		opcode;
+	u8		rsvd[4];
+	__be16		ver; /* cmd version */
+};
+
+struct xsc_outbox_hdr {
+	u8		status;
+	u8		rsvd[5];
+	__be16		ver;
+};
+
+/*CQ mbox*/
+struct xsc_cq_context {
+	__be16		eqn; /* event queue number */
+	__be16		pa_num; /* physical address count in the ctx */
+	__be16		glb_func_id;
+	u8		log_cq_sz;
+	u8		cq_type;
+};
+
+struct xsc_create_cq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	struct xsc_cq_context	ctx;
+	__be64			pas[]; /* physical address list */
+};
+
+struct xsc_create_cq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			cqn; /* completion queue number */
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_cq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			cqn;
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_cq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+/*QP mbox*/
+struct xsc_create_qp_request {
+	__be16		input_qpn;
+	__be16		pa_num;
+	u8		qp_type;
+	u8		log_sq_sz;
+	u8		log_rq_sz;
+	u8		dma_direct;
+	__be32		pdn; /* protect domain number */
+	__be16		cqn_send;
+	__be16		cqn_recv;
+	__be16		glb_funcid;
+	/*rsvd, the old logic_port */
+	u8		rsvd[2];
+	__be64		pas[];
+};
+
+struct xsc_create_qp_mbox_in {
+	struct xsc_inbox_hdr		hdr;
+	struct xsc_create_qp_request	req;
+};
+
+struct xsc_create_qp_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			qpn; /* queue pair number */
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_qp_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			qpn;
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_qp_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_qp_context {
+	__be32		remote_qpn;
+	__be32		cqn_send;
+	__be32		cqn_recv;
+	__be32		next_send_psn;
+	__be32		next_recv_psn;
+	__be32		pdn;
+	__be16		src_udp_port;
+	__be16		path_id;
+	u8		mtu_mode;
+	u8		lag_sel;
+	u8		lag_sel_en;
+	u8		retry_cnt;
+	u8		rnr_retry;
+	u8		dscp;
+	u8		state;
+	u8		hop_limit;
+	u8		dmac[6];
+	u8		smac[6];
+	__be32		dip[4];
+	__be32		sip[4];
+	__be16		ip_type;
+	__be16		grp_id;
+	u8		vlan_valid;
+	u8		dci_cfi_prio_sl;
+	__be16		vlan_id;
+	u8		qp_out_port;
+	u8		pcie_no;
+	__be16		lag_id;
+	__be16		func_id;
+	__be16		rsvd;
+};
+
+struct xsc_modify_qp_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			qpn;
+	struct xsc_qp_context	ctx;
+	u8			no_need_wait;
+};
+
+struct xsc_modify_qp_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_create_multiqp_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			qp_num;
+	u8			qp_type;
+	u8			rsvd;
+	__be32			req_len;
+	u8			data[];
+};
+
+struct xsc_create_multiqp_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			qpn_base;
+};
+
+/* MSIX TABLE mbox */
+struct xsc_msix_table_info_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			index;
+	u8			rsvd[6];
+};
+
+struct xsc_msix_table_info_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			addr_lo;
+	__be32			addr_hi;
+	__be32			data;
+};
+
+/*EQ mbox*/
+struct xsc_eq_context {
+	__be16			vecidx;
+	__be16			pa_num;
+	u8			log_eq_sz;
+	__be16			glb_func_id;
+	u8			is_async_eq;
+	u8			rsvd;
+};
+
+struct xsc_create_eq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	struct xsc_eq_context	ctx;
+	__be64			pas[];
+};
+
+struct xsc_create_eq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			eqn;
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_eq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			eqn;
+	u8			rsvd[4];
+};
+
+struct xsc_destroy_eq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_query_eq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd0[3];
+	u8			eqn;
+	u8			rsvd1[4];
+};
+
+struct xsc_query_eq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+	struct xsc_eq_context	ctx;
+};
+
+struct xsc_query_cq_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			cqn;
+	u8			rsvd0[4];
+};
+
+struct xsc_query_cq_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd0[8];
+	struct xsc_cq_context	ctx;
+	u8			rsvd6[16];
+	__be64			pas[];
+};
+
+struct xsc_cmd_query_cmdq_ver_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_cmd_query_cmdq_ver_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be16			cmdq_ver;
+	u8			rsvd[6];
+};
+
+struct xsc_cmd_dummy_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_cmd_dummy_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_fw_version {
+	u8		fw_version_major;
+	u8		fw_version_minor;
+	__be16		fw_version_patch;
+	__be32		fw_version_tweak;
+	u8		fw_version_extra_flag;
+	u8		rsvd[7];
+};
+
+struct xsc_hca_cap {
+	u8		rsvd1[12];
+	u8		send_seg_num;
+	u8		send_wqe_shift;
+	u8		recv_seg_num;
+	u8		recv_wqe_shift;
+	u8		log_max_srq_sz;
+	u8		log_max_qp_sz;
+	u8		log_max_mtt;
+	u8		log_max_qp;
+	u8		log_max_strq_sz;
+	u8		log_max_srqs;
+	u8		rsvd4[2];
+	u8		log_max_tso;
+	u8		log_max_cq_sz;
+	u8		rsvd6;
+	u8		log_max_cq;
+	u8		log_max_eq_sz;
+	u8		log_max_mkey;
+	u8		log_max_msix;
+	u8		log_max_eq;
+	u8		max_indirection;
+	u8		log_max_mrw_sz;
+	u8		log_max_bsf_list_sz;
+	u8		log_max_klm_list_sz;
+	u8		rsvd_8_0;
+	u8		log_max_ra_req_dc;
+	u8		rsvd_8_1;
+	u8		log_max_ra_res_dc;
+	u8		rsvd9;
+	u8		log_max_ra_req_qp;
+	u8		log_max_qp_depth;
+	u8		log_max_ra_res_qp;
+	__be16		max_vfs;
+	__be16		raweth_qp_id_end;
+	__be16		raw_tpe_qp_num;
+	__be16		max_qp_count;
+	__be16		raweth_qp_id_base;
+	u8		rsvd13;
+	u8		local_ca_ack_delay;
+	u8		max_num_eqs;
+	u8		num_ports;
+	u8		log_max_msg;
+	u8		mac_port;
+	__be16		raweth_rss_qp_id_base;
+	__be16		stat_rate_support;
+	u8		rsvd16[2];
+	__be64		flags;
+	u8		rsvd17;
+	u8		uar_sz;
+	u8		rsvd18;
+	u8		log_pg_sz;
+	__be16		bf_log_bf_reg_size;
+	__be16		msix_base;
+	__be16		msix_num;
+	__be16		max_desc_sz_sq;
+	u8		rsvd20[2];
+	__be16		max_desc_sz_rq;
+	u8		rsvd21[2];
+	__be16		max_desc_sz_sq_dc;
+	u8		rsvd22[4];
+	__be16		max_qp_mcg;
+	u8		rsvd23;
+	u8		log_max_mcg;
+	u8		rsvd24;
+	u8		log_max_pd;
+	u8		rsvd25;
+	u8		log_max_xrcd;
+	u8		rsvd26[40];
+	__be32		uar_page_sz;
+	u8		rsvd27[8];
+	__be32		hw_feature_flag; /* enum xsc_hw_feature_flag */
+	__be16		pf0_vf_funcid_base;
+	__be16		pf0_vf_funcid_top;
+	__be16		pf1_vf_funcid_base;
+	__be16		pf1_vf_funcid_top;
+	__be16		pcie0_pf_funcid_base;
+	__be16		pcie0_pf_funcid_top;
+	__be16		pcie1_pf_funcid_base;
+	__be16		pcie1_pf_funcid_top;
+	u8		log_msx_atomic_size_qp;
+	u8		pcie_host;
+	u8		rsvd28;
+	u8		log_msx_atomic_size_dc;
+	u8		board_sn[XSC_BOARD_SN_LEN];
+	u8		max_tc;
+	u8		mac_bit;
+	__be16		funcid_to_logic_port;
+	u8		rsvd29[6];
+	u8		nif_port_num;
+	u8		reg_mr_via_cmdq;
+	__be32		hca_core_clock;
+	__be32		max_rwq_indirection_tables; /* rss_caps */
+	__be32		max_rwq_indirection_table_size; /* rss_caps */
+	__be32		chip_ver_h;
+	__be32		chip_ver_m;
+	__be32		chip_ver_l;
+	__be32		hotfix_num;
+	__be32		feature_flag;
+	__be32		rx_pkt_len_max;
+	__be32		glb_func_id;
+	__be64		tx_db;
+	__be64		rx_db;
+	__be64		complete_db;
+	__be64		complete_reg;
+	__be64		event_db;
+	__be32		qp_rate_limit_min;
+	__be32		qp_rate_limit_max;
+	struct xsc_fw_version	fw_ver;
+	u8		lag_logic_port_ofst;
+};
+
+struct xsc_cmd_query_hca_cap_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			cpu_num;
+	u8			rsvd[6];
+};
+
+struct xsc_cmd_query_hca_cap_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd0[8];
+	struct xsc_hca_cap	hca_cap;
+};
+
+struct xsc_query_vport_state_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			admin_state:4;
+	u8			state:4;
+};
+
+struct xsc_query_vport_state_in {
+	struct xsc_inbox_hdr	hdr;
+	__be32			data0;
+#define XSC_QUERY_VPORT_OTHER_VPORT	BIT(0)
+#define XSC_QUERY_VPORT_VPORT_NUM_MASK	GENMASK(16, 1)
+};
+
+enum {
+	XSC_CMD_EVENT_RESP_CHANGE_LINK		= BIT(0),
+	XSC_CMD_EVENT_RESP_TEMP_WARN		= BIT(1),
+	XSC_CMD_EVENT_RESP_OVER_TEMP_PROTECTION	= BIT(2),
+};
+
+struct xsc_event_resp {
+	u8			resp_cmd_type;
+};
+
+struct xsc_event_query_type_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd[2];
+};
+
+struct xsc_event_query_type_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	struct xsc_event_resp	ctx;
+};
+
+struct xsc_modify_raw_qp_request {
+	__be16		qpn;
+	__be16		lag_id;
+	__be16		func_id;
+	u8		dma_direct;
+	u8		prio;
+	u8		qp_out_port;
+	u8		rsvd[7];
+};
+
+struct xsc_modify_raw_qp_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			pcie_no;
+	u8			rsvd[7];
+	struct xsc_modify_raw_qp_request	req;
+};
+
+struct xsc_modify_raw_qp_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_set_mtu_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			mtu;
+	__be16			rx_buf_sz_min;
+	u8			mac_port;
+	u8			rsvd;
+};
+
+struct xsc_set_mtu_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+};
+
+struct xsc_query_eth_mac_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			index;
+};
+
+struct xsc_query_eth_mac_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			mac[ETH_ALEN];
+};
+
+enum {
+	XSC_TBM_CAP_HASH_PPH = 0,
+	XSC_TBM_CAP_RSS,
+	XSC_TBM_CAP_PP_BYPASS,
+	XSC_TBM_CAP_PCT_DROP_CONFIG,
+};
+
+struct xsc_nic_attr {
+	__be16	caps;
+	__be16	caps_mask;
+	u8	mac_addr[ETH_ALEN];
+};
+
+struct xsc_rss_attr {
+	u8	rss_en;
+	u8	hfunc;
+	__be16	rqn_base;
+	__be16	rqn_num;
+	__be32	hash_tmpl;
+};
+
+struct xsc_cmd_enable_nic_hca_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	struct xsc_nic_attr	nic;
+	struct xsc_rss_attr	rss;
+};
+
+struct xsc_cmd_enable_nic_hca_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd0[2];
+};
+
+struct xsc_nic_dis_attr {
+	__be16	caps;
+};
+
+struct xsc_cmd_disable_nic_hca_mbox_in {
+	struct xsc_inbox_hdr		hdr;
+	struct xsc_nic_dis_attr		nic;
+};
+
+struct xsc_cmd_disable_nic_hca_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd0[4];
+};
+
+struct xsc_function_reset_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			glb_func_id;
+	u8			rsvd[6];
+};
+
+struct xsc_function_reset_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_cmd_query_guid_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_cmd_query_guid_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be64			guid;
+};
+
+struct xsc_cmd_activate_hw_config_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_cmd_activate_hw_config_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct xsc_event_set_port_admin_status_mbox_in {
+	struct xsc_inbox_hdr	hdr;
+	__be16			status;
+};
+
+struct xsc_event_set_port_admin_status_mbox_out {
+	struct xsc_outbox_hdr	hdr;
+	__be32			status;
+};
+
+#endif /* __XSC_CMD_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmdq.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmdq.h
new file mode 100644
index 0000000000000..0b29fc2f7b667
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_cmdq.h
@@ -0,0 +1,234 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_CMDQ_H
+#define __XSC_CMDQ_H
+
+#include <linux/if_ether.h>
+
+#include "common/xsc_cmd.h"
+
+enum {
+	XSC_CMD_TIMEOUT_MSEC	= 10 * 1000,
+	XSC_CMD_WQ_MAX_NAME	= 32,
+};
+
+enum {
+	XSC_CMD_DATA, /* print command payload only */
+	XSC_CMD_TIME, /* print command execution time */
+};
+
+enum {
+	XSC_MAX_COMMANDS		= 32,
+	XSC_CMD_DATA_BLOCK_SIZE	= 512,
+	XSC_PCI_CMD_XPORT		= 7,
+};
+
+struct xsc_cmd_prot_block {
+	u8		data[XSC_CMD_DATA_BLOCK_SIZE];
+	u8		rsvd0[48];
+	__be64		next;
+	__be32		block_num;
+	/* init to 0, dma user should change this val to 1 */
+	u8		owner_status;
+	u8		token;
+	u8		ctrl_sig;
+	u8		sig;
+};
+
+struct cache_ent {
+	/* protect block chain allocations */
+	spinlock_t		lock;
+	struct list_head	head;
+};
+
+struct cmd_msg_cache {
+	struct cache_ent	large;
+	struct cache_ent	med;
+
+};
+
+#define CMD_FIRST_SIZE 8
+struct xsc_cmd_first {
+	__be32		data[CMD_FIRST_SIZE];
+};
+
+struct xsc_cmd_mailbox {
+	void			*buf;
+	dma_addr_t		dma;
+	struct xsc_cmd_mailbox *next;
+};
+
+struct xsc_cmd_msg {
+	struct list_head	list;
+	struct cache_ent	*cache;
+	u32			len;
+	struct xsc_cmd_first	first;
+	struct xsc_cmd_mailbox	*next;
+};
+
+#define RSP_FIRST_SIZE 14
+struct xsc_rsp_first {
+	/* can be larger, xsc_rsp_layout */
+	__be32		data[RSP_FIRST_SIZE];
+};
+
+struct xsc_rsp_msg {
+	struct list_head		list;
+	struct cache_ent		*cache;
+	u32				len;
+	struct xsc_rsp_first		first;
+	struct xsc_cmd_mailbox		*next;
+};
+
+typedef void (*xsc_cmd_cbk_t)(int status, void *context);
+
+/* hw will use this for some records(e.g. vf_id) */
+struct cmdq_rsv {
+	u16	vf_id;
+	u8	rsv[2];
+};
+
+/* related with hw, won't change */
+#define CMDQ_ENTRY_SIZE 64
+
+struct xsc_cmd_layout {
+	struct cmdq_rsv	rsv0;
+	__be32		inlen;
+	__be64		in_ptr;
+	__be32		in[CMD_FIRST_SIZE];
+	__be64		out_ptr;
+	__be32		outlen;
+	u8		token;
+	u8		sig;
+	u8		idx;
+	u8		type: 7;
+	/* rsv for hw, arm will check this bit to make sure mem written */
+	u8		owner_bit: 1;
+};
+
+struct xsc_rsp_layout {
+	struct cmdq_rsv	rsv0;
+	__be32		out[RSP_FIRST_SIZE];
+	u8		token;
+	u8		sig;
+	u8		idx;
+	u8		type: 7;
+	/* rsv for hw, driver will check this bit to make sure mem written */
+	u8		owner_bit: 1;
+};
+
+struct xsc_cmd_work_ent {
+	struct xsc_cmd_msg	*in;
+	struct xsc_rsp_msg	*out;
+	int			idx;
+	struct completion	done;
+	struct xsc_cmd		*cmd;
+	struct work_struct	work;
+	struct xsc_cmd_layout	*lay;
+	struct xsc_rsp_layout	*rsp_lay;
+	int			ret;
+	u8			status;
+	u8			token;
+	struct timespec64	ts1;
+	struct timespec64	ts2;
+};
+
+struct xsc_cmd_debug {
+	struct dentry		*dbg_root;
+	struct dentry		*dbg_in;
+	struct dentry		*dbg_out;
+	struct dentry		*dbg_outlen;
+	struct dentry		*dbg_status;
+	struct dentry		*dbg_run;
+	void			*in_msg;
+	void			*out_msg;
+	u8			status;
+	u16			inlen;
+	u16			outlen;
+};
+
+struct xsc_cmd_stats {
+	u64		sum;
+	u64		n;
+	struct dentry	*root;
+	struct dentry	*avg;
+	struct dentry	*count;
+	/* protect command average calculations */
+	spinlock_t	lock;
+};
+
+struct xsc_cmd_reg {
+	u32 req_pid_addr;
+	u32 req_cid_addr;
+	u32 rsp_pid_addr;
+	u32 rsp_cid_addr;
+	u32 req_buf_h_addr;
+	u32 req_buf_l_addr;
+	u32 rsp_buf_h_addr;
+	u32 rsp_buf_l_addr;
+	u32 msix_vec_addr;
+	u32 element_sz_addr;
+	u32 q_depth_addr;
+	u32 interrupt_stat_addr;
+};
+
+enum xsc_cmd_status {
+	XSC_CMD_STATUS_NORMAL,
+	XSC_CMD_STATUS_TIMEDOUT,
+};
+
+enum xsc_cmd_mode {
+	XSC_CMD_MODE_POLLING,
+	XSC_CMD_MODE_EVENTS,
+};
+
+struct xsc_cmd {
+	struct xsc_cmd_reg	reg;
+	void			*cmd_buf;
+	void			*cq_buf;
+	dma_addr_t		dma;
+	dma_addr_t		cq_dma;
+	u16			cmd_pid;
+	u16			cq_cid;
+	u8			owner_bit;
+	u8			cmdif_rev;
+	u8			log_sz;
+	u8			log_stride;
+	int			max_reg_cmds;
+	int			events;
+	u32 __iomem		*vector;
+
+	/* protect command queue allocations */
+	spinlock_t		alloc_lock;
+	/* protect token allocations */
+	spinlock_t		token_lock;
+	/* protect cmdq req pid doorbell */
+	spinlock_t		doorbell_lock;
+	u8			token;
+	unsigned long		cmd_entry_mask;
+	char			wq_name[XSC_CMD_WQ_MAX_NAME];
+	struct workqueue_struct	*wq;
+	struct task_struct	*cq_task;
+	/* The semaphore limits the number of working commands
+	 * to max_reg_cmds. Each exec_cmd call does a down
+	 * to acquire the semaphore before execution and an up
+	 * after completion, ensuring no more than max_reg_cmds
+	 * commands run at the same time.
+	 */
+	struct semaphore	sem;
+	enum xsc_cmd_mode	mode;
+	struct xsc_cmd_work_ent	*ent_arr[XSC_MAX_COMMANDS];
+	struct dma_pool		*pool;
+	struct xsc_cmd_debug	dbg;
+	struct cmd_msg_cache	cache;
+	int			checksum_disabled;
+	struct xsc_cmd_stats	stats[XSC_CMD_OP_MAX];
+	unsigned int		irqn;
+	u8			ownerbit_learned;
+	u8			cmd_status;
+};
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index 0673e34fe6ac6..c6077b8b3a9b3 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -8,6 +8,8 @@
 
 #include <linux/pci.h>
 
+#include "common/xsc_cmdq.h"
+
 #define XSC_PCI_VENDOR_ID		0x1f67
 
 #define XSC_MC_PF_DEV_ID		0x1011
@@ -25,6 +27,8 @@
 #define XSC_MV_HOST_VF_DEV_ID		0x1152
 #define XSC_MV_SOC_PF_DEV_ID		0x1153
 
+#define XSC_REG_ADDR(dev, offset)	(((dev)->bar) + ((offset) - 0xA0000000))
+
 struct xsc_dev_resource {
 	/* protect buffer allocation according to numa node */
 	struct mutex		alloc_mutex;
@@ -38,6 +42,9 @@ struct xsc_core_device {
 
 	void __iomem		*bar;
 	int			bar_num;
+
+	struct xsc_cmd		cmd;
+	u16			cmdq_ver;
 };
 
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_driver.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_driver.h
new file mode 100644
index 0000000000000..d8a945fcce3bc
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_driver.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_DRIVER_H
+#define __XSC_DRIVER_H
+
+#include "common/xsc_core.h"
+#include "common/xsc_cmd.h"
+
+int xsc_cmd_init(struct xsc_core_device *xdev);
+void xsc_cmd_cleanup(struct xsc_core_device *xdev);
+void xsc_cmd_use_events(struct xsc_core_device *xdev);
+void xsc_cmd_use_polling(struct xsc_core_device *xdev);
+int xsc_cmd_err_handler(struct xsc_core_device *xdev);
+void xsc_cmd_resp_handler(struct xsc_core_device *xdev);
+int xsc_cmd_status_to_err(struct xsc_outbox_hdr *hdr);
+int xsc_cmd_exec(struct xsc_core_device *xdev,
+		 void *in, unsigned int in_size,
+		 void *out, unsigned int out_size);
+int xsc_cmd_version_check(struct xsc_core_device *xdev);
+const char *xsc_command_str(int command);
+
+#endif
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index 709270df85a75..5e0f0a2051f05 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o
+xsc_pci-y := main.o cmdq.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/cmdq.c b/drivers/net/ethernet/yunsilicon/xsc/pci/cmdq.c
new file mode 100644
index 0000000000000..4d461f45aa291
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/cmdq.c
@@ -0,0 +1,1571 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ * Copyright (c) 2013-2016, Mellanox Technologies. All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/dma-mapping.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/random.h>
+#include <linux/kthread.h>
+#include <linux/io-mapping.h>
+
+#include "common/xsc_driver.h"
+#include "common/xsc_cmd.h"
+#include "common/xsc_auto_hw.h"
+#include "common/xsc_core.h"
+
+enum {
+	CMD_IF_REV = 3,
+};
+
+enum {
+	NUM_LONG_LISTS	  = 2,
+	NUM_MED_LISTS	  = 64,
+	LONG_LIST_SIZE	  = (2ULL * 1024 * 1024 * 1024 / PAGE_SIZE) * 8 + 16 +
+				XSC_CMD_DATA_BLOCK_SIZE,
+	MED_LIST_SIZE	  = 16 + XSC_CMD_DATA_BLOCK_SIZE,
+};
+
+enum {
+	XSC_CMD_DELIVERY_STAT_OK			= 0x0,
+	XSC_CMD_DELIVERY_STAT_SIGNAT_ERR		= 0x1,
+	XSC_CMD_DELIVERY_STAT_TOK_ERR			= 0x2,
+	XSC_CMD_DELIVERY_STAT_BAD_BLK_NUM_ERR		= 0x3,
+	XSC_CMD_DELIVERY_STAT_OUT_PTR_ALIGN_ERR		= 0x4,
+	XSC_CMD_DELIVERY_STAT_IN_PTR_ALIGN_ERR		= 0x5,
+	XSC_CMD_DELIVERY_STAT_FW_ERR			= 0x6,
+	XSC_CMD_DELIVERY_STAT_IN_LENGTH_ERR		= 0x7,
+	XSC_CMD_DELIVERY_STAT_OUT_LENGTH_ERR		= 0x8,
+	XSC_CMD_DELIVERY_STAT_RES_FLD_NOT_CLR_ERR	= 0x9,
+	XSC_CMD_DELIVERY_STAT_CMD_DESCR_ERR		= 0x10,
+};
+
+static struct xsc_cmd_work_ent *xsc_alloc_cmd(struct xsc_cmd *cmd,
+					      struct xsc_cmd_msg *in,
+					      struct xsc_rsp_msg *out)
+{
+	struct xsc_cmd_work_ent *ent;
+
+	ent = kzalloc(sizeof(*ent), GFP_KERNEL);
+	if (!ent)
+		return ERR_PTR(-ENOMEM);
+
+	ent->in		= in;
+	ent->out	= out;
+	ent->cmd	= cmd;
+
+	return ent;
+}
+
+static void xsc_free_cmd(struct xsc_cmd_work_ent *ent)
+{
+	kfree(ent);
+}
+
+static u8 xsc_alloc_token(struct xsc_cmd *cmd)
+{
+	u8 token;
+
+	spin_lock(&cmd->token_lock);
+	token = cmd->token++ % 255 + 1;
+	spin_unlock(&cmd->token_lock);
+
+	return token;
+}
+
+static int xsc_alloc_ent(struct xsc_cmd *cmd)
+{
+	unsigned long flags;
+	int ret;
+
+	spin_lock_irqsave(&cmd->alloc_lock, flags);
+	ret = find_first_bit(&cmd->cmd_entry_mask, cmd->max_reg_cmds);
+	if (ret < cmd->max_reg_cmds)
+		clear_bit(ret, &cmd->cmd_entry_mask);
+	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
+
+	return ret < cmd->max_reg_cmds ? ret : -ENOSPC;
+}
+
+static void xsc_free_ent(struct xsc_cmd *cmd, int idx)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&cmd->alloc_lock, flags);
+	set_bit(idx, &cmd->cmd_entry_mask);
+	spin_unlock_irqrestore(&cmd->alloc_lock, flags);
+}
+
+static struct xsc_cmd_layout *xsc_get_inst(struct xsc_cmd *cmd, int idx)
+{
+	return cmd->cmd_buf + (idx << cmd->log_stride);
+}
+
+static struct xsc_rsp_layout *xsc_get_cq_inst(struct xsc_cmd *cmd, int idx)
+{
+	return cmd->cq_buf + (idx << cmd->log_stride);
+}
+
+static u8 xsc_xor8_buf(void *buf, int len)
+{
+	u8 *ptr = buf;
+	u8 sum = 0;
+	int i;
+
+	for (i = 0; i < len; i++)
+		sum ^= ptr[i];
+
+	return sum;
+}
+
+static int xsc_verify_block_sig(struct xsc_cmd_prot_block *block)
+{
+	/* rsvd0 was set to 0xFF by fw */
+	if (xsc_xor8_buf(block->rsvd0,
+			 sizeof(*block) - sizeof(block->data) - 1) != 0xff)
+		return -EINVAL;
+
+	if (xsc_xor8_buf(block, sizeof(*block)) != 0xff)
+		return -EINVAL;
+
+	return 0;
+}
+
+static void xsc_calc_block_sig(struct xsc_cmd_prot_block *block, u8 token)
+{
+	block->token = token;
+	block->ctrl_sig = ~xsc_xor8_buf(block->rsvd0,
+				    sizeof(*block) - sizeof(block->data) - 2);
+	block->sig = ~xsc_xor8_buf(block, sizeof(*block) - 1);
+}
+
+static void xsc_calc_chain_sig(struct xsc_cmd_mailbox *head, u8 token)
+{
+	struct xsc_cmd_mailbox *next = head;
+
+	while (next) {
+		xsc_calc_block_sig(next->buf, token);
+		next = next->next;
+	}
+}
+
+static void xsc_set_signature(struct xsc_cmd_work_ent *ent)
+{
+	ent->lay->sig = ~xsc_xor8_buf(ent->lay, sizeof(*ent->lay));
+	xsc_calc_chain_sig(ent->in->next, ent->token);
+	xsc_calc_chain_sig(ent->out->next, ent->token);
+}
+
+static int xsc_verify_signature(struct xsc_cmd_work_ent *ent)
+{
+	struct xsc_cmd_mailbox *next = ent->out->next;
+	int err;
+	u8 sig;
+
+	sig = xsc_xor8_buf(ent->rsp_lay, sizeof(*ent->rsp_lay));
+	if (sig != 0xff)
+		return -EINVAL;
+
+	while (next) {
+		err = xsc_verify_block_sig(next->buf);
+		if (err)
+			return err;
+
+		next = next->next;
+	}
+
+	return 0;
+}
+
+const char *xsc_command_str(int command)
+{
+	switch (command) {
+	case XSC_CMD_OP_QUERY_HCA_CAP:
+		return "QUERY_HCA_CAP";
+
+	case XSC_CMD_OP_QUERY_CMDQ_VERSION:
+		return "QUERY_CMDQ_VERSION";
+
+	case XSC_CMD_OP_FUNCTION_RESET:
+		return "FUNCTION_RESET";
+
+	case XSC_CMD_OP_DUMMY:
+		return "DUMMY_CMD";
+
+	case XSC_CMD_OP_CREATE_EQ:
+		return "CREATE_EQ";
+
+	case XSC_CMD_OP_DESTROY_EQ:
+		return "DESTROY_EQ";
+
+	case XSC_CMD_OP_CREATE_CQ:
+		return "CREATE_CQ";
+
+	case XSC_CMD_OP_DESTROY_CQ:
+		return "DESTROY_CQ";
+
+	case XSC_CMD_OP_CREATE_QP:
+		return "CREATE_QP";
+
+	case XSC_CMD_OP_DESTROY_QP:
+		return "DESTROY_QP";
+
+	case XSC_CMD_OP_RST2INIT_QP:
+		return "RST2INIT_QP";
+
+	case XSC_CMD_OP_INIT2RTR_QP:
+		return "INIT2RTR_QP";
+
+	case XSC_CMD_OP_RTR2RTS_QP:
+		return "RTR2RTS_QP";
+
+	case XSC_CMD_OP_RTS2RTS_QP:
+		return "RTS2RTS_QP";
+
+	case XSC_CMD_OP_SQERR2RTS_QP:
+		return "SQERR2RTS_QP";
+
+	case XSC_CMD_OP_2ERR_QP:
+		return "2ERR_QP";
+
+	case XSC_CMD_OP_RTS2SQD_QP:
+		return "RTS2SQD_QP";
+
+	case XSC_CMD_OP_SQD2RTS_QP:
+		return "SQD2RTS_QP";
+
+	case XSC_CMD_OP_2RST_QP:
+		return "2RST_QP";
+
+	case XSC_CMD_OP_INIT2INIT_QP:
+		return "INIT2INIT_QP";
+
+	case XSC_CMD_OP_MODIFY_RAW_QP:
+		return "MODIFY_RAW_QP";
+
+	case XSC_CMD_OP_ENABLE_NIC_HCA:
+		return "ENABLE_NIC_HCA";
+
+	case XSC_CMD_OP_DISABLE_NIC_HCA:
+		return "DISABLE_NIC_HCA";
+
+	case XSC_CMD_OP_QUERY_VPORT_STATE:
+		return "QUERY_VPORT_STATE";
+
+	case XSC_CMD_OP_QUERY_EVENT_TYPE:
+		return "QUERY_EVENT_TYPE";
+
+	case XSC_CMD_OP_ENABLE_MSIX:
+		return "ENABLE_MSIX";
+
+	case XSC_CMD_OP_SET_MTU:
+		return "SET_MTU";
+
+	case XSC_CMD_OP_QUERY_ETH_MAC:
+		return "QUERY_ETH_MAC";
+
+	default: return "unknown command opcode";
+	}
+}
+
+static void cmd_work_handler(struct work_struct *work)
+{
+	struct xsc_cmd_work_ent *ent;
+	struct xsc_core_device *xdev;
+	struct xsc_cmd_layout *lay;
+	struct semaphore *sem;
+	struct xsc_cmd *cmd;
+	unsigned long flags;
+
+	ent = container_of(work, struct xsc_cmd_work_ent, work);
+	cmd = ent->cmd;
+	xdev = container_of(cmd, struct xsc_core_device, cmd);
+	sem = &cmd->sem;
+	down(sem);
+	ent->idx = xsc_alloc_ent(cmd);
+	if (ent->idx < 0) {
+		pci_err(xdev->pdev, "failed to allocate command entry\n");
+		up(sem);
+		return;
+	}
+
+	ent->token = xsc_alloc_token(cmd);
+	cmd->ent_arr[ent->idx] = ent;
+
+	spin_lock_irqsave(&cmd->doorbell_lock, flags);
+	lay = xsc_get_inst(cmd, cmd->cmd_pid);
+	ent->lay = lay;
+	memset(lay, 0, sizeof(*lay));
+	memcpy(lay->in, ent->in->first.data, sizeof(lay->in));
+	if (ent->in->next)
+		lay->in_ptr = cpu_to_be64(ent->in->next->dma);
+	lay->inlen = cpu_to_be32(ent->in->len);
+	if (ent->out->next)
+		lay->out_ptr = cpu_to_be64(ent->out->next->dma);
+	lay->outlen = cpu_to_be32(ent->out->len);
+	lay->type = XSC_PCI_CMD_XPORT;
+	lay->token = ent->token;
+	lay->idx = ent->idx;
+	if (!cmd->checksum_disabled)
+		xsc_set_signature(ent);
+	else
+		lay->sig = 0xff;
+
+	ktime_get_ts64(&ent->ts1);
+
+	/* ring doorbell after the descriptor is valid */
+	wmb();
+
+	cmd->cmd_pid = (cmd->cmd_pid + 1) % (1 << cmd->log_sz);
+	writel(cmd->cmd_pid, XSC_REG_ADDR(xdev, cmd->reg.req_pid_addr));
+	spin_unlock_irqrestore(&cmd->doorbell_lock, flags);
+}
+
+static const char *xsc_deliv_status_to_str(u8 status)
+{
+	switch (status) {
+	case XSC_CMD_DELIVERY_STAT_OK:
+		return "no errors";
+	case XSC_CMD_DELIVERY_STAT_SIGNAT_ERR:
+		return "signature error";
+	case XSC_CMD_DELIVERY_STAT_TOK_ERR:
+		return "token error";
+	case XSC_CMD_DELIVERY_STAT_BAD_BLK_NUM_ERR:
+		return "bad block number";
+	case XSC_CMD_DELIVERY_STAT_OUT_PTR_ALIGN_ERR:
+		return "output pointer not aligned to block size";
+	case XSC_CMD_DELIVERY_STAT_IN_PTR_ALIGN_ERR:
+		return "input pointer not aligned to block size";
+	case XSC_CMD_DELIVERY_STAT_FW_ERR:
+		return "firmware internal error";
+	case XSC_CMD_DELIVERY_STAT_IN_LENGTH_ERR:
+		return "command input length error";
+	case XSC_CMD_DELIVERY_STAT_OUT_LENGTH_ERR:
+		return "command output length error";
+	case XSC_CMD_DELIVERY_STAT_RES_FLD_NOT_CLR_ERR:
+		return "reserved fields not cleared";
+	case XSC_CMD_DELIVERY_STAT_CMD_DESCR_ERR:
+		return "bad command descriptor type";
+	default:
+		return "unknown status code";
+	}
+}
+
+static u16 xsc_msg_to_opcode(struct xsc_cmd_msg *in)
+{
+	struct xsc_inbox_hdr *hdr = (struct xsc_inbox_hdr *)(in->first.data);
+
+	return be16_to_cpu(hdr->opcode);
+}
+
+static int xsc_wait_func(struct xsc_core_device *xdev,
+			 struct xsc_cmd_work_ent *ent)
+{
+	unsigned long timeout = msecs_to_jiffies(XSC_CMD_TIMEOUT_MSEC);
+	struct xsc_cmd *cmd = &xdev->cmd;
+	int err;
+
+	if (!wait_for_completion_timeout(&ent->done, timeout))
+		err = -ETIMEDOUT;
+	else
+		err = ent->ret;
+
+	if (err == -ETIMEDOUT) {
+		cmd->cmd_status = XSC_CMD_STATUS_TIMEDOUT;
+		pci_err(xdev->pdev, "wait for %s(0x%x) response timeout!\n",
+			xsc_command_str(xsc_msg_to_opcode(ent->in)),
+			xsc_msg_to_opcode(ent->in));
+	} else if (err) {
+		pci_err(xdev->pdev, "err %d, delivery status %s(%d)\n", err,
+			xsc_deliv_status_to_str(ent->status), ent->status);
+	}
+
+	return err;
+}
+
+/*  Notes:
+ *    1. Callback functions may not sleep
+ *    2. page queue commands do not support asynchrous completion
+ */
+static int xsc_cmd_invoke(struct xsc_core_device *xdev, struct xsc_cmd_msg *in,
+			  struct xsc_rsp_msg *out, u8 *status)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_cmd_work_ent *ent;
+	struct xsc_cmd_stats *stats;
+	ktime_t t1, t2, delta;
+	struct semaphore *sem;
+	int err = 0;
+	s64 ds;
+	u16 op;
+
+	ent = xsc_alloc_cmd(cmd, in, out);
+	if (IS_ERR(ent))
+		return PTR_ERR(ent);
+
+	init_completion(&ent->done);
+	INIT_WORK(&ent->work, cmd_work_handler);
+	if (!queue_work(cmd->wq, &ent->work)) {
+		pci_err(xdev->pdev, "failed to queue work\n");
+		err = -ENOMEM;
+		goto err_free;
+	}
+
+	err = xsc_wait_func(xdev, ent);
+	if (err == -ETIMEDOUT)
+		goto err_sem_up;
+	t1 = timespec64_to_ktime(ent->ts1);
+	t2 = timespec64_to_ktime(ent->ts2);
+	delta = ktime_sub(t2, t1);
+	ds = ktime_to_ns(delta);
+	op = be16_to_cpu(((struct xsc_inbox_hdr *)in->first.data)->opcode);
+	if (op < ARRAY_SIZE(cmd->stats)) {
+		stats = &cmd->stats[op];
+		spin_lock(&stats->lock);
+		stats->sum += ds;
+		++stats->n;
+		spin_unlock(&stats->lock);
+	}
+	*status = ent->status;
+	xsc_free_cmd(ent);
+
+	return err;
+
+err_sem_up:
+	sem = &cmd->sem;
+	up(sem);
+err_free:
+	xsc_free_cmd(ent);
+	return err;
+}
+
+static int xsc_copy_to_cmd_msg(struct xsc_cmd_msg *to, void *from,
+			       unsigned int size)
+{
+	struct xsc_cmd_prot_block *block;
+	struct xsc_cmd_mailbox *next;
+	unsigned int copy;
+
+	if (!to || !from)
+		return -ENOMEM;
+
+	copy = min(size, sizeof(to->first.data));
+	memcpy(to->first.data, from, copy);
+	size -= copy;
+	from += copy;
+
+	next = to->next;
+	while (size) {
+		if (!next) {
+			WARN_ONCE(1, "Mail box not enough\n");
+			return -ENOMEM;
+		}
+
+		copy = min(size, XSC_CMD_DATA_BLOCK_SIZE);
+		block = next->buf;
+		memcpy(block->data, from, copy);
+		block->owner_status = 0;
+		from += copy;
+		size -= copy;
+		next = next->next;
+	}
+
+	return 0;
+}
+
+static int xsc_copy_from_rsp_msg(void *to, struct xsc_rsp_msg *from,
+				 unsigned int size)
+{
+	struct xsc_cmd_prot_block *block;
+	struct xsc_cmd_mailbox *next;
+	unsigned int copy;
+
+	if (!to || !from)
+		return -ENOMEM;
+
+	copy = min(size, sizeof(from->first.data));
+	memcpy(to, from->first.data, copy);
+	size -= copy;
+	to += copy;
+
+	next = from->next;
+	while (size) {
+		if (!next) {
+			WARN_ONCE(1, "Mail too short\n");
+			return -ENOMEM;
+		}
+
+		copy = min(size, XSC_CMD_DATA_BLOCK_SIZE);
+		block = next->buf;
+		if (!block->owner_status)
+			pr_err("block ownership check failed\n");
+
+		memcpy(to, block->data, copy);
+		to += copy;
+		size -= copy;
+		next = next->next;
+	}
+
+	return 0;
+}
+
+static struct xsc_cmd_mailbox *xsc_alloc_cmd_box(struct xsc_core_device *xdev,
+						 gfp_t flags)
+{
+	struct xsc_cmd_mailbox *mailbox;
+
+	mailbox = kmalloc(sizeof(*mailbox), flags);
+	if (!mailbox)
+		return ERR_PTR(-ENOMEM);
+
+	mailbox->buf = dma_pool_zalloc(xdev->cmd.pool, flags,
+				       &mailbox->dma);
+	if (!mailbox->buf) {
+		kfree(mailbox);
+		return ERR_PTR(-ENOMEM);
+	}
+	mailbox->next = NULL;
+
+	return mailbox;
+}
+
+static void xsc_free_cmd_box(struct xsc_core_device *xdev,
+			     struct xsc_cmd_mailbox *mailbox)
+{
+	dma_pool_free(xdev->cmd.pool, mailbox->buf, mailbox->dma);
+
+	kfree(mailbox);
+}
+
+static struct xsc_cmd_msg *xsc_alloc_cmd_msg(struct xsc_core_device *xdev,
+					     gfp_t flags, unsigned int size)
+{
+	struct xsc_cmd_mailbox *tmp, *head = NULL;
+	struct xsc_cmd_prot_block *block;
+	struct xsc_cmd_msg *msg;
+	int blen;
+	int err;
+	int n;
+	int i;
+
+	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+
+	blen = size - min(sizeof(msg->first.data), size);
+	n = (blen + XSC_CMD_DATA_BLOCK_SIZE - 1) / XSC_CMD_DATA_BLOCK_SIZE;
+
+	for (i = 0; i < n; i++) {
+		tmp = xsc_alloc_cmd_box(xdev, flags);
+		if (IS_ERR(tmp)) {
+			pci_err(xdev->pdev, "failed allocating block\n");
+			err = PTR_ERR(tmp);
+			goto err_free;
+		}
+
+		block = tmp->buf;
+		tmp->next = head;
+		block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
+		block->block_num = cpu_to_be32(n - i - 1);
+		head = tmp;
+	}
+	msg->next = head;
+	msg->len = size;
+	return msg;
+
+err_free:
+	while (head) {
+		tmp = head->next;
+		xsc_free_cmd_box(xdev, head);
+		head = tmp;
+	}
+	kfree(msg);
+
+	return ERR_PTR(err);
+}
+
+static void xsc_free_cmd_msg(struct xsc_core_device *xdev,
+			     struct xsc_cmd_msg *msg)
+{
+	struct xsc_cmd_mailbox *head = msg->next;
+	struct xsc_cmd_mailbox *next;
+
+	while (head) {
+		next = head->next;
+		xsc_free_cmd_box(xdev, head);
+		head = next;
+	}
+	kfree(msg);
+}
+
+static struct xsc_rsp_msg *xsc_alloc_rsp_msg(struct xsc_core_device *xdev,
+					     gfp_t flags, unsigned int size)
+{
+	struct xsc_cmd_mailbox *tmp, *head = NULL;
+	struct xsc_cmd_prot_block *block;
+	struct xsc_rsp_msg *msg;
+	int blen;
+	int err;
+	int n;
+	int i;
+
+	msg = kzalloc(sizeof(*msg), GFP_KERNEL);
+	if (!msg)
+		return ERR_PTR(-ENOMEM);
+
+	blen = size - min_t(int, sizeof(msg->first.data), size);
+	n = (blen + XSC_CMD_DATA_BLOCK_SIZE - 1) / XSC_CMD_DATA_BLOCK_SIZE;
+
+	for (i = 0; i < n; i++) {
+		tmp = xsc_alloc_cmd_box(xdev, flags);
+		if (IS_ERR(tmp)) {
+			pci_err(xdev->pdev, "failed allocating block\n");
+			err = PTR_ERR(tmp);
+			goto err_free;
+		}
+
+		block = tmp->buf;
+		tmp->next = head;
+		block->next = cpu_to_be64(tmp->next ? tmp->next->dma : 0);
+		block->block_num = cpu_to_be32(n - i - 1);
+		head = tmp;
+	}
+	msg->next = head;
+	msg->len = size;
+	return msg;
+
+err_free:
+	while (head) {
+		tmp = head->next;
+		xsc_free_cmd_box(xdev, head);
+		head = tmp;
+	}
+	kfree(msg);
+
+	return ERR_PTR(err);
+}
+
+static void xsc_free_rsp_msg(struct xsc_core_device *xdev,
+			     struct xsc_rsp_msg *msg)
+{
+	struct xsc_cmd_mailbox *head = msg->next;
+	struct xsc_cmd_mailbox *next;
+
+	while (head) {
+		next = head->next;
+		xsc_free_cmd_box(xdev, head);
+		head = next;
+	}
+	kfree(msg);
+}
+
+static void xsc_set_wqname(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+
+	snprintf(cmd->wq_name, sizeof(cmd->wq_name), "xsc_cmd_%s",
+		 dev_name(&xdev->pdev->dev));
+}
+
+void xsc_cmd_use_events(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		down(&cmd->sem);
+
+	flush_workqueue(cmd->wq);
+
+	cmd->mode = XSC_CMD_MODE_EVENTS;
+
+	while (cmd->cmd_pid != cmd->cq_cid)
+		msleep(20);
+	kthread_stop(cmd->cq_task);
+	cmd->cq_task = NULL;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
+static int xsc_cmd_cq_polling(void *data);
+void xsc_cmd_use_polling(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	int i;
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		down(&cmd->sem);
+
+	flush_workqueue(cmd->wq);
+	cmd->mode = XSC_CMD_MODE_POLLING;
+	cmd->cq_task = kthread_create(xsc_cmd_cq_polling,
+				      (void *)xdev,
+				      "xsc_cmd_cq_polling");
+	if (cmd->cq_task)
+		wake_up_process(cmd->cq_task);
+
+	for (i = 0; i < cmd->max_reg_cmds; i++)
+		up(&cmd->sem);
+}
+
+static int xsc_status_to_err(u8 status)
+{
+	return status ? -1 : 0;
+}
+
+static struct xsc_cmd_msg *xsc_alloc_msg(struct xsc_core_device *xdev,
+					 unsigned int in_size)
+{
+	struct xsc_cmd_msg *msg = ERR_PTR(-ENOMEM);
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct cache_ent *ent = NULL;
+
+	if (in_size > MED_LIST_SIZE && in_size <= LONG_LIST_SIZE)
+		ent = &cmd->cache.large;
+	else if (in_size > 16 && in_size <= MED_LIST_SIZE)
+		ent = &cmd->cache.med;
+
+	if (ent) {
+		spin_lock(&ent->lock);
+		if (!list_empty(&ent->head)) {
+			msg = list_entry(ent->head.next, typeof(*msg), list);
+			/* For cached lists, we must explicitly state what is
+			 * the real size
+			 */
+			msg->len = in_size;
+			list_del(&msg->list);
+		}
+		spin_unlock(&ent->lock);
+	}
+
+	if (IS_ERR(msg))
+		msg = xsc_alloc_cmd_msg(xdev, GFP_KERNEL, in_size);
+
+	return msg;
+}
+
+static void xsc_free_msg(struct xsc_core_device *xdev, struct xsc_cmd_msg *msg)
+{
+	if (msg->cache) {
+		spin_lock(&msg->cache->lock);
+		list_add_tail(&msg->list, &msg->cache->head);
+		spin_unlock(&msg->cache->lock);
+	} else {
+		xsc_free_cmd_msg(xdev, msg);
+	}
+}
+
+static int xsc_dummy_work(struct xsc_core_device *xdev,
+			  struct xsc_cmd_msg *in,
+			  struct xsc_rsp_msg *out,
+			  u16 dummy_cnt,
+			  u16 dummy_start_pid)
+{
+	struct xsc_cmd_work_ent **dummy_ent_arr;
+	struct xsc_cmd *cmd = &xdev->cmd;
+	u16 temp_pid = dummy_start_pid;
+	struct xsc_cmd_layout *lay;
+	struct semaphore *sem;
+	u16 free_cnt = 0;
+	int err = 0;
+	u16 i;
+
+	sem = &cmd->sem;
+
+	dummy_ent_arr = kcalloc(dummy_cnt, sizeof(struct xsc_cmd_work_ent *),
+				GFP_KERNEL);
+	if (!dummy_ent_arr) {
+		err = -ENOMEM;
+		goto err_out;
+	}
+
+	for (i = 0; i < dummy_cnt; i++) {
+		dummy_ent_arr[i] = xsc_alloc_cmd(cmd, in, out);
+		if (IS_ERR(dummy_ent_arr[i])) {
+			pci_err(xdev->pdev, "failed to alloc cmd buffer\n");
+			err = -ENOMEM;
+			free_cnt = i;
+			goto err_free;
+		}
+
+		down(sem);
+
+		dummy_ent_arr[i]->idx = xsc_alloc_ent(cmd);
+		if (dummy_ent_arr[i]->idx < 0) {
+			pci_err(xdev->pdev, "failed to allocate command entry\n");
+			err = -1;
+			free_cnt = i;
+			up(sem);
+			xsc_free_cmd(dummy_ent_arr[i]);
+			goto err_free;
+		}
+		dummy_ent_arr[i]->token = xsc_alloc_token(cmd);
+		cmd->ent_arr[dummy_ent_arr[i]->idx] = dummy_ent_arr[i];
+		init_completion(&dummy_ent_arr[i]->done);
+
+		lay = xsc_get_inst(cmd, temp_pid);
+		dummy_ent_arr[i]->lay = lay;
+		memset(lay, 0, sizeof(*lay));
+		memcpy(lay->in,
+		       dummy_ent_arr[i]->in->first.data,
+		       sizeof(dummy_ent_arr[i]->in));
+		lay->inlen = cpu_to_be32(dummy_ent_arr[i]->in->len);
+		lay->outlen = cpu_to_be32(dummy_ent_arr[i]->out->len);
+		lay->type = XSC_PCI_CMD_XPORT;
+		lay->token = dummy_ent_arr[i]->token;
+		lay->idx = dummy_ent_arr[i]->idx;
+		if (!cmd->checksum_disabled)
+			xsc_set_signature(dummy_ent_arr[i]);
+		else
+			lay->sig = 0xff;
+		temp_pid = (temp_pid + 1) % (1 << cmd->log_sz);
+	}
+
+	/* ring doorbell after the descriptor is valid */
+	wmb();
+	writel(cmd->cmd_pid, XSC_REG_ADDR(xdev, cmd->reg.req_pid_addr));
+	if (readl(XSC_REG_ADDR(xdev, cmd->reg.interrupt_stat_addr)) != 0)
+		writel(0xF, XSC_REG_ADDR(xdev, cmd->reg.interrupt_stat_addr));
+
+	if (wait_for_completion_timeout(&dummy_ent_arr[dummy_cnt - 1]->done,
+					msecs_to_jiffies(3000)) == 0) {
+		pci_err(xdev->pdev, "dummy_cmd %d ent timeout, cmdq fail\n",
+			dummy_cnt - 1);
+		err = -ETIMEDOUT;
+	}
+
+	for (i = 0; i < dummy_cnt; i++)
+		xsc_free_cmd(dummy_ent_arr[i]);
+
+	kfree(dummy_ent_arr);
+	return err;
+
+err_free:
+	for (i = 0; i < free_cnt; i++) {
+		xsc_free_ent(cmd, dummy_ent_arr[i]->idx);
+		up(sem);
+		xsc_free_cmd(dummy_ent_arr[i]);
+	}
+	kfree(dummy_ent_arr);
+err_out:
+	return err;
+}
+
+static int xsc_dummy_cmd_exec(struct xsc_core_device *xdev,
+			      void *in, unsigned int in_size,
+			      void *out, unsigned int out_size,
+			      u16 dmmy_cnt, u16 dummy_start)
+{
+	struct xsc_rsp_msg *outb;
+	struct xsc_cmd_msg *inb;
+	int err;
+
+	inb = xsc_alloc_msg(xdev, in_size);
+	if (IS_ERR(inb)) {
+		err = PTR_ERR(inb);
+		return err;
+	}
+
+	err = xsc_copy_to_cmd_msg(inb, in, in_size);
+	if (err) {
+		pci_err(xdev->pdev, "err %d\n", err);
+		goto err_free_msg;
+	}
+
+	outb = xsc_alloc_rsp_msg(xdev, GFP_KERNEL, out_size);
+	if (IS_ERR(outb)) {
+		err = PTR_ERR(outb);
+		goto err_free_msg;
+	}
+
+	err = xsc_dummy_work(xdev, inb, outb, dmmy_cnt, dummy_start);
+
+	if (err)
+		goto err_free_rsp;
+
+	err = xsc_copy_from_rsp_msg(out, outb, out_size);
+
+err_free_rsp:
+	xsc_free_rsp_msg(xdev, outb);
+
+err_free_msg:
+	xsc_free_msg(xdev, inb);
+	return err;
+}
+
+static int xsc_send_dummy_cmd(struct xsc_core_device *xdev,
+			      u16 gap, u16 dummy_start)
+{
+	struct xsc_cmd_dummy_mbox_out *out;
+	struct xsc_cmd_dummy_mbox_in in;
+	int err;
+
+	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(&in, 0, sizeof(in));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_DUMMY);
+
+	err = xsc_dummy_cmd_exec(xdev, &in, sizeof(in), out, sizeof(*out),
+				 gap, dummy_start);
+	if (err)
+		goto err_free;
+
+	if (out->hdr.status) {
+		err = xsc_cmd_status_to_err(&out->hdr);
+		goto err_free;
+	}
+
+err_free:
+	kfree(out);
+	return err;
+}
+
+static int xsc_request_pid_cid_mismatch_restore(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	u16 req_pid, req_cid;
+	u16 gap;
+
+	int err;
+
+	req_pid = readl(XSC_REG_ADDR(xdev, cmd->reg.req_pid_addr));
+	req_cid = readl(XSC_REG_ADDR(xdev, cmd->reg.req_cid_addr));
+	if (req_pid >= (1 << cmd->log_sz) || req_cid >= (1 << cmd->log_sz)) {
+		pci_err(xdev->pdev,
+			"req_pid %d, req_cid %d, out of normal range!!! max value is %d\n",
+			req_pid, req_cid, (1 << cmd->log_sz));
+		return -EFAULT;
+	}
+
+	if (req_pid == req_cid)
+		return 0;
+
+	gap = (req_pid > req_cid) ? (req_pid - req_cid)
+	      : ((1 << cmd->log_sz) + req_pid - req_cid);
+
+	err = xsc_send_dummy_cmd(xdev, gap, req_cid);
+	if (err) {
+		pci_err(xdev->pdev, "Send dummy cmd failed\n");
+		return err;
+	}
+
+	return 0;
+}
+
+static int _xsc_cmd_exec(struct xsc_core_device *xdev,
+			 void *in, unsigned int in_size,
+			 void *out, unsigned int out_size)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_rsp_msg *outb;
+	struct xsc_cmd_msg *inb;
+	u8 status = 0;
+	int err;
+
+	if (cmd->cmd_status == XSC_CMD_STATUS_TIMEDOUT)
+		return -ETIMEDOUT;
+
+	inb = xsc_alloc_msg(xdev, in_size);
+	if (IS_ERR(inb)) {
+		err = PTR_ERR(inb);
+		return err;
+	}
+
+	err = xsc_copy_to_cmd_msg(inb, in, in_size);
+	if (err) {
+		pci_err(xdev->pdev, "copy to cmd_msg err %d\n", err);
+		goto err_free_msg;
+	}
+
+	outb = xsc_alloc_rsp_msg(xdev, GFP_KERNEL, out_size);
+	if (IS_ERR(outb)) {
+		err = PTR_ERR(outb);
+		goto err_free_msg;
+	}
+
+	err = xsc_cmd_invoke(xdev, inb, outb, &status);
+	if (err)
+		goto err_free_rsp;
+
+	if (status) {
+		pci_err(xdev->pdev, "opcode:%#x, err %d, status %d\n",
+			xsc_msg_to_opcode(inb), err, status);
+		err = xsc_status_to_err(status);
+		goto err_free_rsp;
+	}
+
+	err = xsc_copy_from_rsp_msg(out, outb, out_size);
+
+err_free_rsp:
+	xsc_free_rsp_msg(xdev, outb);
+
+err_free_msg:
+	xsc_free_msg(xdev, inb);
+	return err;
+}
+
+int xsc_cmd_exec(struct xsc_core_device *xdev,
+		 void *in, unsigned int in_size,
+		 void *out, unsigned int out_size)
+{
+	struct xsc_inbox_hdr *hdr = (struct xsc_inbox_hdr *)in;
+
+	hdr->ver = 0;
+	if (hdr->ver != 0) {
+		pci_err(xdev->pdev, "recv an unexpected cmd ver = %d, opcode = %d\n",
+			be16_to_cpu(hdr->ver), be16_to_cpu(hdr->opcode));
+		WARN_ON(hdr->ver != 0);
+	}
+
+	return _xsc_cmd_exec(xdev, in, in_size, out, out_size);
+}
+EXPORT_SYMBOL(xsc_cmd_exec);
+
+static void xsc_destroy_msg_cache(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_cmd_msg *msg;
+	struct xsc_cmd_msg *n;
+
+	list_for_each_entry_safe(msg, n, &cmd->cache.large.head, list) {
+		list_del(&msg->list);
+		xsc_free_cmd_msg(xdev, msg);
+	}
+
+	list_for_each_entry_safe(msg, n, &cmd->cache.med.head, list) {
+		list_del(&msg->list);
+		xsc_free_cmd_msg(xdev, msg);
+	}
+}
+
+static int xsc_create_msg_cache(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_cmd_msg *msg;
+	int err;
+	int i;
+
+	spin_lock_init(&cmd->cache.large.lock);
+	INIT_LIST_HEAD(&cmd->cache.large.head);
+	spin_lock_init(&cmd->cache.med.lock);
+	INIT_LIST_HEAD(&cmd->cache.med.head);
+
+	for (i = 0; i < NUM_LONG_LISTS; i++) {
+		msg = xsc_alloc_cmd_msg(xdev, GFP_KERNEL, LONG_LIST_SIZE);
+		if (IS_ERR(msg)) {
+			err = PTR_ERR(msg);
+			goto err_destroy;
+		}
+		msg->cache = &cmd->cache.large;
+		list_add_tail(&msg->list, &cmd->cache.large.head);
+	}
+
+	for (i = 0; i < NUM_MED_LISTS; i++) {
+		msg = xsc_alloc_cmd_msg(xdev, GFP_KERNEL, MED_LIST_SIZE);
+		if (IS_ERR(msg)) {
+			err = PTR_ERR(msg);
+			goto err_destroy;
+		}
+		msg->cache = &cmd->cache.med;
+		list_add_tail(&msg->list, &cmd->cache.med.head);
+	}
+
+	return 0;
+
+err_destroy:
+	xsc_destroy_msg_cache(xdev);
+	return err;
+}
+
+static void xsc_cmd_comp_handler(struct xsc_core_device *xdev, u8 idx,
+				 struct xsc_rsp_layout *rsp)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_cmd_work_ent *ent;
+
+	if (idx > cmd->max_reg_cmds || (cmd->cmd_entry_mask & (1 << idx))) {
+		pci_err(xdev->pdev, "idx[%d] exceed max cmds, or has no relative request.\n",
+			idx);
+		return;
+	}
+	ent = cmd->ent_arr[idx];
+	ent->rsp_lay = rsp;
+	ktime_get_ts64(&ent->ts2);
+
+	memcpy(ent->out->first.data,
+	       ent->rsp_lay->out,
+	       sizeof(ent->rsp_lay->out));
+	if (!cmd->checksum_disabled)
+		ent->ret = xsc_verify_signature(ent);
+	else
+		ent->ret = 0;
+	ent->status = 0;
+
+	xsc_free_ent(cmd, ent->idx);
+	complete(&ent->done);
+	up(&cmd->sem);
+}
+
+static int xsc_cmd_cq_polling(void *data)
+{
+	struct xsc_core_device *xdev = data;
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_rsp_layout *rsp;
+	u32 cq_pid;
+
+	while (!kthread_should_stop()) {
+		if (need_resched())
+			schedule();
+		cq_pid = readl(XSC_REG_ADDR(xdev, cmd->reg.rsp_pid_addr));
+		if (cmd->cq_cid == cq_pid) {
+			mdelay(3);
+			continue;
+		}
+
+		rsp = xsc_get_cq_inst(cmd, cmd->cq_cid);
+		if (!cmd->ownerbit_learned) {
+			cmd->ownerbit_learned = 1;
+			cmd->owner_bit = rsp->owner_bit;
+		}
+		if (cmd->owner_bit != rsp->owner_bit) {
+			pci_err(xdev->pdev, "hw update cq doorbell but buf not ready %u %u\n",
+				cmd->cq_cid, cq_pid);
+			continue;
+		}
+
+		xsc_cmd_comp_handler(xdev, rsp->idx, rsp);
+
+		cmd->cq_cid = (cmd->cq_cid + 1) % (1 << cmd->log_sz);
+
+		writel(cmd->cq_cid, XSC_REG_ADDR(xdev, cmd->reg.rsp_cid_addr));
+		if (cmd->cq_cid == 0)
+			cmd->owner_bit = !cmd->owner_bit;
+	}
+
+	return 0;
+}
+
+int xsc_cmd_err_handler(struct xsc_core_device *xdev)
+{
+	union interrupt_stat {
+		struct {
+			u32	hw_read_req_err:1;
+			u32	hw_write_req_err:1;
+			u32	req_pid_err:1;
+			u32	rsp_cid_err:1;
+		};
+		u32	raw;
+	} stat;
+	int retry = 0;
+	int err = 0;
+
+	stat.raw = readl(XSC_REG_ADDR(xdev, xdev->cmd.reg.interrupt_stat_addr));
+	while (stat.raw != 0) {
+		err++;
+		if (stat.hw_read_req_err) {
+			retry = 1;
+			stat.hw_read_req_err = 0;
+			pci_err(xdev->pdev, "hw report read req from host failed!\n");
+		} else if (stat.hw_write_req_err) {
+			retry = 1;
+			stat.hw_write_req_err = 0;
+			pci_err(xdev->pdev, "hw report write req to fw failed!\n");
+		} else if (stat.req_pid_err) {
+			stat.req_pid_err = 0;
+			pci_err(xdev->pdev, "hw report unexpected req pid!\n");
+		} else if (stat.rsp_cid_err) {
+			stat.rsp_cid_err = 0;
+			pci_err(xdev->pdev, "hw report unexpected rsp cid!\n");
+		} else {
+			stat.raw = 0;
+			pci_err(xdev->pdev, "ignore unknown interrupt!\n");
+		}
+	}
+
+	if (retry)
+		writel(xdev->cmd.cmd_pid,
+		       XSC_REG_ADDR(xdev, xdev->cmd.reg.req_pid_addr));
+
+	if (err)
+		writel(0xf,
+		       XSC_REG_ADDR(xdev, xdev->cmd.reg.interrupt_stat_addr));
+
+	return err;
+}
+
+void xsc_cmd_resp_handler(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+	struct xsc_rsp_layout *rsp;
+	const int budget = 32;
+	int count = 0;
+	u32 cq_pid;
+
+	while (count < budget) {
+		cq_pid = readl(XSC_REG_ADDR(xdev, cmd->reg.rsp_pid_addr));
+		if (cq_pid == cmd->cq_cid)
+			return;
+
+		rsp = xsc_get_cq_inst(cmd, cmd->cq_cid);
+		if (!cmd->ownerbit_learned) {
+			cmd->ownerbit_learned = 1;
+			cmd->owner_bit = rsp->owner_bit;
+		}
+		if (cmd->owner_bit != rsp->owner_bit) {
+			pci_err(xdev->pdev, "hw update cq doorbell but buf not ready %u %u\n",
+				cmd->cq_cid, cq_pid);
+			return;
+		}
+
+		xsc_cmd_comp_handler(xdev, rsp->idx, rsp);
+
+		cmd->cq_cid = (cmd->cq_cid + 1) % (1 << cmd->log_sz);
+		writel(cmd->cq_cid, XSC_REG_ADDR(xdev, cmd->reg.rsp_cid_addr));
+		if (cmd->cq_cid == 0)
+			cmd->owner_bit = !cmd->owner_bit;
+
+		count++;
+	}
+}
+
+static void xsc_cmd_handle_rsp_before_reload
+(struct xsc_cmd *cmd, struct xsc_core_device *xdev)
+{
+	u32 rsp_pid, rsp_cid;
+
+	rsp_pid = readl(XSC_REG_ADDR(xdev, cmd->reg.rsp_pid_addr));
+	rsp_cid = readl(XSC_REG_ADDR(xdev, cmd->reg.rsp_cid_addr));
+	if (rsp_pid == rsp_cid)
+		return;
+
+	cmd->cq_cid = rsp_pid;
+
+	writel(cmd->cq_cid, XSC_REG_ADDR(xdev, cmd->reg.rsp_cid_addr));
+}
+
+int xsc_cmd_init(struct xsc_core_device *xdev)
+{
+	unsigned int size = sizeof(struct xsc_cmd_prot_block);
+	int align = roundup_pow_of_two(size);
+	struct xsc_cmd *cmd = &xdev->cmd;
+	u32 cmd_h, cmd_l;
+	u32 err_stat;
+	int err;
+	int i;
+
+	/* now there is 544 cmdq resource, soc using from id 514 */
+	cmd->reg.req_pid_addr = HIF_CMDQM_HOST_REQ_PID_MEM_ADDR;
+	cmd->reg.req_cid_addr = HIF_CMDQM_HOST_REQ_CID_MEM_ADDR;
+	cmd->reg.rsp_pid_addr = HIF_CMDQM_HOST_RSP_PID_MEM_ADDR;
+	cmd->reg.rsp_cid_addr = HIF_CMDQM_HOST_RSP_CID_MEM_ADDR;
+	cmd->reg.req_buf_h_addr = HIF_CMDQM_HOST_REQ_BUF_BASE_H_ADDR_MEM_ADDR;
+	cmd->reg.req_buf_l_addr = HIF_CMDQM_HOST_REQ_BUF_BASE_L_ADDR_MEM_ADDR;
+	cmd->reg.rsp_buf_h_addr = HIF_CMDQM_HOST_RSP_BUF_BASE_H_ADDR_MEM_ADDR;
+	cmd->reg.rsp_buf_l_addr = HIF_CMDQM_HOST_RSP_BUF_BASE_L_ADDR_MEM_ADDR;
+	cmd->reg.msix_vec_addr = HIF_CMDQM_VECTOR_ID_MEM_ADDR;
+	cmd->reg.element_sz_addr = HIF_CMDQM_Q_ELEMENT_SZ_REG_ADDR;
+	cmd->reg.q_depth_addr = HIF_CMDQM_HOST_Q_DEPTH_REG_ADDR;
+	cmd->reg.interrupt_stat_addr = HIF_CMDQM_HOST_VF_ERR_STS_MEM_ADDR;
+
+	cmd->pool = dma_pool_create("xsc_cmd",
+				    &xdev->pdev->dev,
+				    size, align, 0);
+	if (!cmd->pool)
+		return -ENOMEM;
+
+	cmd->cmd_buf = (void *)__get_free_pages(GFP_ATOMIC, 0);
+	if (!cmd->cmd_buf) {
+		err = -ENOMEM;
+		goto err_free_pool;
+	}
+	cmd->cq_buf = (void *)__get_free_pages(GFP_ATOMIC, 0);
+	if (!cmd->cq_buf) {
+		err = -ENOMEM;
+		goto err_free_cmd;
+	}
+
+	cmd->dma = dma_map_single(&xdev->pdev->dev, cmd->cmd_buf, PAGE_SIZE,
+				  DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&xdev->pdev->dev, cmd->dma)) {
+		err = -ENOMEM;
+		goto err_free_cq;
+	}
+
+	cmd->cq_dma = dma_map_single(&xdev->pdev->dev, cmd->cq_buf, PAGE_SIZE,
+				     DMA_BIDIRECTIONAL);
+	if (dma_mapping_error(&xdev->pdev->dev, cmd->cq_dma)) {
+		err = -ENOMEM;
+		goto err_unmap_cmd;
+	}
+
+	cmd->cmd_pid = readl(XSC_REG_ADDR(xdev, cmd->reg.req_pid_addr));
+	cmd->cq_cid = readl(XSC_REG_ADDR(xdev, cmd->reg.rsp_cid_addr));
+	cmd->ownerbit_learned = 0;
+
+	xsc_cmd_handle_rsp_before_reload(cmd, xdev);
+
+#define ELEMENT_SIZE_LOG	6 /* 64B */
+#define Q_DEPTH_LOG		5 /* 32 */
+
+	cmd->log_sz = Q_DEPTH_LOG;
+	cmd->log_stride = readl(XSC_REG_ADDR(xdev, cmd->reg.element_sz_addr));
+	writel(1 << cmd->log_sz, XSC_REG_ADDR(xdev, cmd->reg.q_depth_addr));
+	if (cmd->log_stride != ELEMENT_SIZE_LOG) {
+		dev_err(&xdev->pdev->dev, "firmware failed to init cmdq, log_stride=(%d, %d)\n",
+			cmd->log_stride, ELEMENT_SIZE_LOG);
+		err = -ENODEV;
+		goto err_unmap_cq;
+	}
+
+	if (1 << cmd->log_sz > XSC_MAX_COMMANDS) {
+		dev_err(&xdev->pdev->dev, "firmware reports too many outstanding commands %d\n",
+			1 << cmd->log_sz);
+		err = -EINVAL;
+		goto err_unmap_cq;
+	}
+
+	if (cmd->log_sz + cmd->log_stride > PAGE_SHIFT) {
+		dev_err(&xdev->pdev->dev, "command queue size overflow\n");
+		err = -EINVAL;
+		goto err_unmap_cq;
+	}
+
+	cmd->checksum_disabled = 1;
+	cmd->max_reg_cmds = (1 << cmd->log_sz) - 1;
+	cmd->cmd_entry_mask = (1 << cmd->max_reg_cmds) - 1;
+
+	spin_lock_init(&cmd->alloc_lock);
+	spin_lock_init(&cmd->token_lock);
+	spin_lock_init(&cmd->doorbell_lock);
+	for (i = 0; i < ARRAY_SIZE(cmd->stats); i++)
+		spin_lock_init(&cmd->stats[i].lock);
+
+	sema_init(&cmd->sem, cmd->max_reg_cmds);
+
+	cmd_h = upper_32_bits(cmd->dma);
+	cmd_l = lower_32_bits(cmd->dma);
+	if (cmd_l & 0xfff) {
+		dev_err(&xdev->pdev->dev, "invalid command queue address\n");
+		err = -ENOMEM;
+		goto err_unmap_cq;
+	}
+
+	writel(cmd_h, XSC_REG_ADDR(xdev, cmd->reg.req_buf_h_addr));
+	writel(cmd_l, XSC_REG_ADDR(xdev, cmd->reg.req_buf_l_addr));
+
+	cmd_h = upper_32_bits(cmd->cq_dma);
+	cmd_l = lower_32_bits(cmd->cq_dma);
+	if (cmd_l & 0xfff) {
+		dev_err(&xdev->pdev->dev, "invalid command queue address\n");
+		err = -ENOMEM;
+		goto err_unmap_cq;
+	}
+	writel(cmd_h, XSC_REG_ADDR(xdev, cmd->reg.rsp_buf_h_addr));
+	writel(cmd_l, XSC_REG_ADDR(xdev, cmd->reg.rsp_buf_l_addr));
+
+	/* Make sure firmware sees the complete address before we proceed */
+	wmb();
+
+	cmd->mode = XSC_CMD_MODE_POLLING;
+	cmd->cmd_status = XSC_CMD_STATUS_NORMAL;
+
+	err = xsc_create_msg_cache(xdev);
+	if (err) {
+		dev_err(&xdev->pdev->dev, "failed to create command cache\n");
+		goto err_unmap_cq;
+	}
+
+	xsc_set_wqname(xdev);
+	cmd->wq = create_singlethread_workqueue(cmd->wq_name);
+	if (!cmd->wq) {
+		dev_err(&xdev->pdev->dev, "failed to create command workqueue\n");
+		err = -ENOMEM;
+		goto err_destroy_cache;
+	}
+
+	cmd->cq_task = kthread_create(xsc_cmd_cq_polling,
+				      (void *)xdev,
+				      "xsc_cmd_cq_polling");
+	if (!cmd->cq_task) {
+		dev_err(&xdev->pdev->dev, "failed to create cq task\n");
+		err = -ENOMEM;
+		goto err_destroy_wq;
+	}
+	wake_up_process(cmd->cq_task);
+
+	err = xsc_request_pid_cid_mismatch_restore(xdev);
+	if (err) {
+		dev_err(&xdev->pdev->dev, "request pid,cid wrong, restore failed\n");
+		goto err_stop_cq_task;
+	}
+
+	/* clear abnormal state to avoid the impact of previous error */
+	err_stat = readl(XSC_REG_ADDR(xdev, xdev->cmd.reg.interrupt_stat_addr));
+	if (err_stat) {
+		pci_err(xdev->pdev, "err_stat 0x%x when init, clear it\n",
+			err_stat);
+		writel(0xf,
+		       XSC_REG_ADDR(xdev, xdev->cmd.reg.interrupt_stat_addr));
+	}
+
+	return 0;
+
+err_stop_cq_task:
+	kthread_stop(cmd->cq_task);
+
+err_destroy_wq:
+	destroy_workqueue(cmd->wq);
+
+err_destroy_cache:
+	xsc_destroy_msg_cache(xdev);
+
+err_unmap_cq:
+	dma_unmap_single(&xdev->pdev->dev, cmd->cq_dma, PAGE_SIZE,
+			 DMA_BIDIRECTIONAL);
+
+err_unmap_cmd:
+	dma_unmap_single(&xdev->pdev->dev, cmd->dma, PAGE_SIZE,
+			 DMA_BIDIRECTIONAL);
+err_free_cq:
+	free_pages((unsigned long)cmd->cq_buf, 0);
+
+err_free_cmd:
+	free_pages((unsigned long)cmd->cmd_buf, 0);
+
+err_free_pool:
+	dma_pool_destroy(cmd->pool);
+
+	return err;
+}
+
+void xsc_cmd_cleanup(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd *cmd = &xdev->cmd;
+
+	destroy_workqueue(cmd->wq);
+	if (cmd->cq_task)
+		kthread_stop(cmd->cq_task);
+	xsc_destroy_msg_cache(xdev);
+	dma_unmap_single(&xdev->pdev->dev, cmd->dma, PAGE_SIZE,
+			 DMA_BIDIRECTIONAL);
+	free_pages((unsigned long)cmd->cq_buf, 0);
+	dma_unmap_single(&xdev->pdev->dev, cmd->cq_dma, PAGE_SIZE,
+			 DMA_BIDIRECTIONAL);
+	free_pages((unsigned long)cmd->cmd_buf, 0);
+	dma_pool_destroy(cmd->pool);
+}
+
+int xsc_cmd_version_check(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd_query_cmdq_ver_mbox_out *out;
+	struct xsc_cmd_query_cmdq_ver_mbox_in in;
+
+	int err;
+
+	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(&in, 0, sizeof(in));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_CMDQ_VERSION);
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), out, sizeof(*out));
+	if (err)
+		goto err_free;
+
+	if (out->hdr.status) {
+		err = xsc_cmd_status_to_err(&out->hdr);
+		goto err_free;
+	}
+
+	if (be16_to_cpu(out->cmdq_ver) != XSC_CMDQ_VERSION) {
+		pci_err(xdev->pdev, "cmdq version check failed, expecting %d, actual %d\n",
+			XSC_CMDQ_VERSION, be16_to_cpu(out->cmdq_ver));
+		err = -EINVAL;
+		goto err_free;
+	}
+	xdev->cmdq_ver = XSC_CMDQ_VERSION;
+
+err_free:
+	kfree(out);
+	return err;
+}
+
+static const char *cmd_status_str(u8 status)
+{
+	switch (status) {
+	case XSC_CMD_STAT_OK:
+		return "OK";
+	case XSC_CMD_STAT_INT_ERR:
+		return "internal error";
+	case XSC_CMD_STAT_BAD_OP_ERR:
+		return "bad operation";
+	case XSC_CMD_STAT_BAD_PARAM_ERR:
+		return "bad parameter";
+	case XSC_CMD_STAT_BAD_SYS_STATE_ERR:
+		return "bad system state";
+	case XSC_CMD_STAT_BAD_RES_ERR:
+		return "bad resource";
+	case XSC_CMD_STAT_RES_BUSY:
+		return "resource busy";
+	case XSC_CMD_STAT_LIM_ERR:
+		return "limits exceeded";
+	case XSC_CMD_STAT_BAD_RES_STATE_ERR:
+		return "bad resource state";
+	case XSC_CMD_STAT_IX_ERR:
+		return "bad index";
+	case XSC_CMD_STAT_NO_RES_ERR:
+		return "no resources";
+	case XSC_CMD_STAT_BAD_INP_LEN_ERR:
+		return "bad input length";
+	case XSC_CMD_STAT_BAD_OUTP_LEN_ERR:
+		return "bad output length";
+	case XSC_CMD_STAT_BAD_QP_STATE_ERR:
+		return "bad QP state";
+	case XSC_CMD_STAT_BAD_PKT_ERR:
+		return "bad packet (discarded)";
+	case XSC_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR:
+		return "bad size too many outstanding CQEs";
+	default:
+		return "unknown status";
+	}
+}
+
+int xsc_cmd_status_to_err(struct xsc_outbox_hdr *hdr)
+{
+	if (!hdr->status)
+		return 0;
+
+	pr_warn("command failed, status %s(0x%x)\n",
+		cmd_status_str(hdr->status), hdr->status);
+
+	switch (hdr->status) {
+	case XSC_CMD_STAT_OK:				return 0;
+	case XSC_CMD_STAT_INT_ERR:			return -EIO;
+	case XSC_CMD_STAT_BAD_OP_ERR:			return -EOPNOTSUPP;
+	case XSC_CMD_STAT_BAD_PARAM_ERR:		return -EINVAL;
+	case XSC_CMD_STAT_BAD_SYS_STATE_ERR:		return -EIO;
+	case XSC_CMD_STAT_BAD_RES_ERR:			return -EINVAL;
+	case XSC_CMD_STAT_RES_BUSY:			return -EBUSY;
+	case XSC_CMD_STAT_LIM_ERR:			return -EINVAL;
+	case XSC_CMD_STAT_BAD_RES_STATE_ERR:		return -EINVAL;
+	case XSC_CMD_STAT_IX_ERR:			return -EINVAL;
+	case XSC_CMD_STAT_NO_RES_ERR:			return -EAGAIN;
+	case XSC_CMD_STAT_BAD_INP_LEN_ERR:		return -EIO;
+	case XSC_CMD_STAT_BAD_OUTP_LEN_ERR:		return -EIO;
+	case XSC_CMD_STAT_BAD_QP_STATE_ERR:		return -EINVAL;
+	case XSC_CMD_STAT_BAD_PKT_ERR:			return -EINVAL;
+	case XSC_CMD_STAT_BAD_SIZE_OUTS_CQES_ERR:	return -EINVAL;
+	default:					return -EIO;
+	}
+}
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index b8fc256792d12..3c717acbb7db8 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -4,6 +4,7 @@
  */
 
 #include "common/xsc_core.h"
+#include "common/xsc_driver.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -136,6 +137,52 @@ static void xsc_core_dev_cleanup(struct xsc_core_device *xdev)
 	xsc_dev_res_cleanup(xdev);
 }
 
+static int xsc_hw_setup(struct xsc_core_device *xdev)
+{
+	int err;
+
+	err = xsc_cmd_init(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "Failed initializing command interface, aborting\n");
+		goto err_out;
+	}
+
+	err = xsc_cmd_version_check(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "Failed to check cmdq version\n");
+		goto err_cmd_cleanup;
+	}
+
+	return 0;
+err_cmd_cleanup:
+	xsc_cmd_cleanup(xdev);
+err_out:
+	return err;
+}
+
+static void xsc_hw_cleanup(struct xsc_core_device *xdev)
+{
+	xsc_cmd_cleanup(xdev);
+}
+
+static int xsc_load(struct xsc_core_device *xdev)
+{
+	int err = 0;
+
+	err = xsc_hw_setup(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc_hw_setup failed %d\n", err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void xsc_unload(struct xsc_core_device *xdev)
+{
+	xsc_hw_cleanup(xdev);
+}
+
 static int xsc_pci_probe(struct pci_dev *pci_dev,
 			 const struct pci_device_id *id)
 {
@@ -162,7 +209,15 @@ static int xsc_pci_probe(struct pci_dev *pci_dev,
 		goto err_pci_fini;
 	}
 
+	err = xsc_load(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc_load failed %d\n", err);
+		goto err_core_dev_cleanup;
+	}
+
 	return 0;
+err_core_dev_cleanup:
+	xsc_core_dev_cleanup(xdev);
 err_pci_fini:
 	xsc_pci_fini(xdev);
 err_unset_pci_drvdata:
@@ -176,6 +231,7 @@ static void xsc_pci_remove(struct pci_dev *pci_dev)
 {
 	struct xsc_core_device *xdev = pci_get_drvdata(pci_dev);
 
+	xsc_unload(xdev);
 	xsc_core_dev_cleanup(xdev);
 	xsc_pci_fini(xdev);
 	pci_set_drvdata(pci_dev, NULL);

From a99e7a415c701fcc3221073669da9fed431b2ff3 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:14:55 +0800
Subject: [PATCH 2593/2753] xsc: Add hardware setup APIs

After CMDQ is initialized, the driver can retrieve hardware
information from the firmware. This patch provides APIs to
obtain the Hardware Component Adapter (HCA) capabilities,
the Globally Unique Identifier (GUID) of the board, activate
the hardware configuration, and reset function-specific
resources.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h | 158 ++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   2 +-
 drivers/net/ethernet/yunsilicon/xsc/pci/hw.c  | 282 ++++++++++++++++++
 drivers/net/ethernet/yunsilicon/xsc/pci/hw.h  |  18 ++
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |  27 ++
 5 files changed, 486 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/hw.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index c6077b8b3a9b3..270e3d30a7c1b 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -29,6 +29,145 @@
 
 #define XSC_REG_ADDR(dev, offset)	(((dev)->bar) + ((offset) - 0xA0000000))
 
+enum {
+	XSC_MAX_PORTS	= 2,
+};
+
+enum {
+	XSC_MAX_FW_PORTS	= 1,
+};
+
+enum {
+	XSC_BF_REGS_PER_PAGE	= 4,
+	XSC_MAX_UAR_PAGES	= 1 << 8,
+	XSC_MAX_UUARS		= XSC_MAX_UAR_PAGES * XSC_BF_REGS_PER_PAGE,
+};
+
+/* hw */
+struct xsc_reg_addr {
+	u64	tx_db;
+	u64	rx_db;
+	u64	complete_db;
+	u64	complete_reg;
+	u64	event_db;
+	u64	cpm_get_lock;
+	u64	cpm_put_lock;
+	u64	cpm_lock_avail;
+	u64	cpm_data_mem;
+	u64	cpm_cmd;
+	u64	cpm_addr;
+	u64	cpm_busy;
+};
+
+struct xsc_board_info {
+	u32			board_id;
+	char			board_sn[XSC_BOARD_SN_LEN];
+	__be64			guid;
+	u8			guid_valid;
+	u8			hw_config_activated;
+};
+
+struct xsc_port_caps {
+	int		gid_table_len;
+	int		pkey_table_len;
+};
+
+struct xsc_caps {
+	u8		log_max_eq;
+	u8		log_max_cq;
+	u8		log_max_qp;
+	u8		log_max_mkey;
+	u8		log_max_pd;
+	u8		log_max_srq;
+	u8		log_max_msix;
+	u32		max_cqes;
+	u32		max_wqes;
+	u32		max_sq_desc_sz;
+	u32		max_rq_desc_sz;
+	u64		flags;
+	u16		stat_rate_support;
+	u32		log_max_msg;
+	u32		num_ports;
+	u32		max_ra_res_qp;
+	u32		max_ra_req_qp;
+	u32		max_srq_wqes;
+	u32		bf_reg_size;
+	u32		bf_regs_per_page;
+	struct xsc_port_caps	port[XSC_MAX_PORTS];
+	u8		ext_port_cap[XSC_MAX_PORTS];
+	u32		reserved_lkey;
+	u8		local_ca_ack_delay;
+	u8		log_max_mcg;
+	u16		max_qp_mcg;
+	u32		min_page_sz;
+	u32		send_ds_num;
+	u32		send_wqe_shift;
+	u32		recv_ds_num;
+	u32		recv_wqe_shift;
+	u32		rx_pkt_len_max;
+
+	u32		msix_enable:1;
+	u32		port_type:1;
+	u32		embedded_cpu:1;
+	u32		eswitch_manager:1;
+	u32		ecpf_vport_exists:1;
+	u32		vport_group_manager:1;
+	u32		sf:1;
+	u32		wqe_inline_mode:3;
+	u32		raweth_qp_id_base:15;
+	u32		rsvd0:7;
+
+	u16		max_vfs;
+	u8		log_max_qp_depth;
+	u8		log_max_current_uc_list;
+	u8		log_max_current_mc_list;
+	u16		log_max_vlan_list;
+	u8		fdb_multi_path_to_table;
+	u8		log_esw_max_sched_depth;
+
+	u8		max_num_sf_partitions;
+	u8		log_max_esw_sf;
+	u16		sf_base_id;
+
+	u32		max_tc:8;
+	u32		ets:1;
+	u32		dcbx:1;
+	u32		dscp:1;
+	u32		sbcam_reg:1;
+	u32		qos:1;
+	u32		port_buf:1;
+	u32		rsvd1:2;
+	u32		raw_tpe_qp_num:16;
+	u32		max_num_eqs:8;
+	u32		mac_port:8;
+	u32		raweth_rss_qp_id_base:16;
+	u16		msix_base;
+	u16		msix_num;
+	u8		log_max_mtt;
+	u8		log_max_tso;
+	u32		hca_core_clock;
+	u32		max_rwq_indirection_tables; /* rss_caps */
+	u32		max_rwq_indirection_table_size; /* rss_caps */
+	u16		raweth_qp_id_end;
+	u32		qp_rate_limit_min;
+	u32		qp_rate_limit_max;
+	u32		hw_feature_flag;
+	u16		pf0_vf_funcid_base;
+	u16		pf0_vf_funcid_top;
+	u16		pf1_vf_funcid_base;
+	u16		pf1_vf_funcid_top;
+	u16		pcie0_pf_funcid_base;
+	u16		pcie0_pf_funcid_top;
+	u16		pcie1_pf_funcid_base;
+	u16		pcie1_pf_funcid_top;
+	u8		nif_port_num;
+	u8		pcie_host;
+	u8		mac_bit;
+	u16		funcid_to_logic_port;
+	u8		lag_logic_port_ofst;
+};
+
+/* xsc_core */
 struct xsc_dev_resource {
 	/* protect buffer allocation according to numa node */
 	struct mutex		alloc_mutex;
@@ -43,8 +182,27 @@ struct xsc_core_device {
 	void __iomem		*bar;
 	int			bar_num;
 
+	u8			mac_port;
+	u16			glb_func_id;
+
 	struct xsc_cmd		cmd;
 	u16			cmdq_ver;
+
+	struct xsc_caps		caps;
+	struct xsc_board_info	*board_info;
+
+	struct xsc_reg_addr	regs;
+	u32			chip_ver_h;
+	u32			chip_ver_m;
+	u32			chip_ver_l;
+	u32			hotfix_num;
+	u32			feature_flag;
+
+	u8			fw_version_major;
+	u8			fw_version_minor;
+	u16			fw_version_patch;
+	u32			fw_version_tweak;
+	u8			fw_version_extra_flag;
 };
 
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index 5e0f0a2051f05..fea625d54af32 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o
+xsc_pci-y := main.o cmdq.o hw.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
new file mode 100644
index 0000000000000..7d239ca177f96
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
@@ -0,0 +1,282 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/module.h>
+#include <linux/vmalloc.h>
+#include "common/xsc_driver.h"
+#include "hw.h"
+
+#define MAX_BOARD_NUM	32
+
+static struct xsc_board_info *board_info[MAX_BOARD_NUM];
+
+static struct xsc_board_info *xsc_get_board_info(char *board_sn)
+{
+	int i;
+
+	for (i = 0; i < MAX_BOARD_NUM; i++) {
+		if (!board_info[i])
+			continue;
+		if (!strncmp(board_info[i]->board_sn, board_sn,
+			     XSC_BOARD_SN_LEN))
+			return board_info[i];
+	}
+
+	return NULL;
+}
+
+static struct xsc_board_info *xsc_alloc_board_info(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_BOARD_NUM; i++) {
+		if (!board_info[i])
+			break;
+	}
+	if (i == MAX_BOARD_NUM)
+		return NULL;
+	board_info[i] = vzalloc(sizeof(*board_info[i]));
+	if (!board_info[i])
+		return NULL;
+	board_info[i]->board_id = i;
+	return board_info[i];
+}
+
+void xsc_free_board_info(void)
+{
+	int i;
+
+	for (i = 0; i < MAX_BOARD_NUM; i++)
+		vfree(board_info[i]);
+}
+
+int xsc_cmd_query_hca_cap(struct xsc_core_device *xdev,
+			  struct xsc_caps *caps)
+{
+	struct xsc_cmd_query_hca_cap_mbox_out *out;
+	struct xsc_cmd_query_hca_cap_mbox_in in;
+	struct xsc_board_info *board_info;
+	int err;
+	u16 t16;
+
+	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(&in, 0, sizeof(in));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_HCA_CAP);
+	in.cpu_num = cpu_to_be16(num_online_cpus());
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), out, sizeof(*out));
+	if (err)
+		goto err_free;
+
+	if (out->hdr.status) {
+		err = xsc_cmd_status_to_err(&out->hdr);
+		goto err_free;
+	}
+
+	xdev->glb_func_id = be32_to_cpu(out->hca_cap.glb_func_id);
+	caps->pcie0_pf_funcid_base =
+		be16_to_cpu(out->hca_cap.pcie0_pf_funcid_base);
+	caps->pcie0_pf_funcid_top =
+		be16_to_cpu(out->hca_cap.pcie0_pf_funcid_top);
+	caps->pcie1_pf_funcid_base =
+		be16_to_cpu(out->hca_cap.pcie1_pf_funcid_base);
+	caps->pcie1_pf_funcid_top =
+		be16_to_cpu(out->hca_cap.pcie1_pf_funcid_top);
+	caps->funcid_to_logic_port =
+		be16_to_cpu(out->hca_cap.funcid_to_logic_port);
+
+	caps->pcie_host = out->hca_cap.pcie_host;
+	caps->nif_port_num = out->hca_cap.nif_port_num;
+	caps->hw_feature_flag = be32_to_cpu(out->hca_cap.hw_feature_flag);
+
+	caps->raweth_qp_id_base = be16_to_cpu(out->hca_cap.raweth_qp_id_base);
+	caps->raweth_qp_id_end = be16_to_cpu(out->hca_cap.raweth_qp_id_end);
+	caps->raweth_rss_qp_id_base =
+		be16_to_cpu(out->hca_cap.raweth_rss_qp_id_base);
+	caps->raw_tpe_qp_num = be16_to_cpu(out->hca_cap.raw_tpe_qp_num);
+	caps->max_cqes = 1 << out->hca_cap.log_max_cq_sz;
+	caps->max_wqes = 1 << out->hca_cap.log_max_qp_sz;
+	caps->max_sq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_sq);
+	caps->max_rq_desc_sz = be16_to_cpu(out->hca_cap.max_desc_sz_rq);
+	caps->flags = be64_to_cpu(out->hca_cap.flags);
+	caps->stat_rate_support = be16_to_cpu(out->hca_cap.stat_rate_support);
+	caps->log_max_msg = out->hca_cap.log_max_msg & 0x1f;
+	caps->num_ports = out->hca_cap.num_ports & 0xf;
+	caps->log_max_cq = out->hca_cap.log_max_cq & 0x1f;
+	caps->log_max_eq = out->hca_cap.log_max_eq & 0xf;
+	caps->log_max_msix = out->hca_cap.log_max_msix & 0xf;
+	caps->mac_port = out->hca_cap.mac_port & 0xff;
+	xdev->mac_port = caps->mac_port;
+	if (caps->num_ports > XSC_MAX_FW_PORTS) {
+		pci_err(xdev->pdev, "device has %d ports while the driver supports max %d ports\n",
+			caps->num_ports, XSC_MAX_FW_PORTS);
+		err = -EINVAL;
+		goto err_free;
+	}
+	caps->send_ds_num = out->hca_cap.send_seg_num;
+	caps->send_wqe_shift = out->hca_cap.send_wqe_shift;
+	caps->recv_ds_num = out->hca_cap.recv_seg_num;
+	caps->recv_wqe_shift = out->hca_cap.recv_wqe_shift;
+
+	caps->embedded_cpu = 0;
+	caps->ecpf_vport_exists = 0;
+	caps->log_max_current_uc_list = 0;
+	caps->log_max_current_mc_list = 0;
+	caps->log_max_vlan_list = 8;
+	caps->log_max_qp = out->hca_cap.log_max_qp & 0x1f;
+	caps->log_max_mkey = out->hca_cap.log_max_mkey & 0x3f;
+	caps->log_max_pd = out->hca_cap.log_max_pd & 0x1f;
+	caps->log_max_srq = out->hca_cap.log_max_srqs & 0x1f;
+	caps->local_ca_ack_delay = out->hca_cap.local_ca_ack_delay & 0x1f;
+	caps->log_max_mcg = out->hca_cap.log_max_mcg;
+	caps->log_max_mtt = out->hca_cap.log_max_mtt;
+	caps->log_max_tso = out->hca_cap.log_max_tso;
+	caps->hca_core_clock = be32_to_cpu(out->hca_cap.hca_core_clock);
+	caps->max_rwq_indirection_tables =
+		be32_to_cpu(out->hca_cap.max_rwq_indirection_tables);
+	caps->max_rwq_indirection_table_size =
+		be32_to_cpu(out->hca_cap.max_rwq_indirection_table_size);
+	caps->max_qp_mcg = be16_to_cpu(out->hca_cap.max_qp_mcg);
+	caps->max_ra_res_qp = 1 << (out->hca_cap.log_max_ra_res_qp & 0x3f);
+	caps->max_ra_req_qp = 1 << (out->hca_cap.log_max_ra_req_qp & 0x3f);
+	caps->max_srq_wqes = 1 << out->hca_cap.log_max_srq_sz;
+	caps->rx_pkt_len_max = be32_to_cpu(out->hca_cap.rx_pkt_len_max);
+	caps->max_vfs = be16_to_cpu(out->hca_cap.max_vfs);
+	caps->qp_rate_limit_min = be32_to_cpu(out->hca_cap.qp_rate_limit_min);
+	caps->qp_rate_limit_max = be32_to_cpu(out->hca_cap.qp_rate_limit_max);
+
+	caps->msix_enable = 1;
+	caps->msix_base = be16_to_cpu(out->hca_cap.msix_base);
+	caps->msix_num = be16_to_cpu(out->hca_cap.msix_num);
+
+	t16 = be16_to_cpu(out->hca_cap.bf_log_bf_reg_size);
+	if (t16 & 0x8000) {
+		caps->bf_reg_size = 1 << (t16 & 0x1f);
+		caps->bf_regs_per_page = XSC_BF_REGS_PER_PAGE;
+	} else {
+		caps->bf_reg_size = 0;
+		caps->bf_regs_per_page = 0;
+	}
+	caps->min_page_sz = ~(u32)((1 << PAGE_SHIFT) - 1);
+
+	caps->dcbx = 1;
+	caps->qos = 1;
+	caps->ets = 1;
+	caps->dscp = 1;
+	caps->max_tc = out->hca_cap.max_tc;
+	caps->log_max_qp_depth = out->hca_cap.log_max_qp_depth & 0xff;
+	caps->mac_bit = out->hca_cap.mac_bit;
+	caps->lag_logic_port_ofst = out->hca_cap.lag_logic_port_ofst;
+
+	xdev->chip_ver_h = be32_to_cpu(out->hca_cap.chip_ver_h);
+	xdev->chip_ver_m = be32_to_cpu(out->hca_cap.chip_ver_m);
+	xdev->chip_ver_l = be32_to_cpu(out->hca_cap.chip_ver_l);
+	xdev->hotfix_num = be32_to_cpu(out->hca_cap.hotfix_num);
+	xdev->feature_flag = be32_to_cpu(out->hca_cap.feature_flag);
+
+	board_info = xsc_get_board_info(out->hca_cap.board_sn);
+	if (!board_info) {
+		board_info = xsc_alloc_board_info();
+		if (!board_info) {
+			err = -ENOMEM;
+			goto err_free;
+		}
+
+		memcpy(board_info->board_sn,
+		       out->hca_cap.board_sn,
+		       sizeof(out->hca_cap.board_sn));
+	}
+
+	xdev->board_info = board_info;
+
+	xdev->regs.tx_db = be64_to_cpu(out->hca_cap.tx_db);
+	xdev->regs.rx_db = be64_to_cpu(out->hca_cap.rx_db);
+	xdev->regs.complete_db = be64_to_cpu(out->hca_cap.complete_db);
+	xdev->regs.complete_reg = be64_to_cpu(out->hca_cap.complete_reg);
+	xdev->regs.event_db = be64_to_cpu(out->hca_cap.event_db);
+
+	xdev->fw_version_major = out->hca_cap.fw_ver.fw_version_major;
+	xdev->fw_version_minor = out->hca_cap.fw_ver.fw_version_minor;
+	xdev->fw_version_patch =
+		be16_to_cpu(out->hca_cap.fw_ver.fw_version_patch);
+	xdev->fw_version_tweak =
+		be32_to_cpu(out->hca_cap.fw_ver.fw_version_tweak);
+	xdev->fw_version_extra_flag = out->hca_cap.fw_ver.fw_version_extra_flag;
+
+	kfree(out);
+	return 0;
+err_free:
+	kfree(out);
+	return err;
+}
+
+static int xsc_cmd_query_guid(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd_query_guid_mbox_out out;
+	struct xsc_cmd_query_guid_mbox_in in;
+	int err;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_GUID);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return xsc_cmd_status_to_err(&out.hdr);
+	xdev->board_info->guid = out.guid;
+	xdev->board_info->guid_valid = 1;
+	return 0;
+}
+
+int xsc_query_guid(struct xsc_core_device *xdev)
+{
+	if (xdev->board_info->guid_valid)
+		return 0;
+
+	return xsc_cmd_query_guid(xdev);
+}
+
+static int xsc_cmd_activate_hw_config(struct xsc_core_device *xdev)
+{
+	struct xsc_cmd_activate_hw_config_mbox_out out;
+	struct xsc_cmd_activate_hw_config_mbox_in in;
+	int err = 0;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_ACTIVATE_HW_CONFIG);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+	if (out.hdr.status)
+		return xsc_cmd_status_to_err(&out.hdr);
+	xdev->board_info->hw_config_activated = 1;
+	return 0;
+}
+
+int xsc_activate_hw_config(struct xsc_core_device *xdev)
+{
+	if (xdev->board_info->hw_config_activated)
+		return 0;
+
+	return xsc_cmd_activate_hw_config(xdev);
+}
+
+int xsc_reset_function_resource(struct xsc_core_device *xdev)
+{
+	struct xsc_function_reset_mbox_out out;
+	struct xsc_function_reset_mbox_in in;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_FUNCTION_RESET);
+	in.glb_func_id = cpu_to_be16(xdev->glb_func_id);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status)
+		return -EINVAL;
+
+	return 0;
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/hw.h b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.h
new file mode 100644
index 0000000000000..d1030bfdec0d5
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __HW_H
+#define __HW_H
+
+#include "common/xsc_core.h"
+
+void xsc_free_board_info(void);
+int xsc_cmd_query_hca_cap(struct xsc_core_device *xdev,
+			  struct xsc_caps *caps);
+int xsc_query_guid(struct xsc_core_device *xdev);
+int xsc_activate_hw_config(struct xsc_core_device *xdev);
+int xsc_reset_function_resource(struct xsc_core_device *xdev);
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index 3c717acbb7db8..099feb6504833 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -5,6 +5,7 @@
 
 #include "common/xsc_core.h"
 #include "common/xsc_driver.h"
+#include "hw.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -153,6 +154,31 @@ static int xsc_hw_setup(struct xsc_core_device *xdev)
 		goto err_cmd_cleanup;
 	}
 
+	err = xsc_cmd_query_hca_cap(xdev, &xdev->caps);
+	if (err) {
+		pci_err(xdev->pdev, "Failed to query hca, err=%d\n", err);
+		goto err_cmd_cleanup;
+	}
+
+	err = xsc_query_guid(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to query guid, err=%d\n", err);
+		goto err_cmd_cleanup;
+	}
+
+	err = xsc_activate_hw_config(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to activate hw config, err=%d\n",
+			err);
+		goto err_cmd_cleanup;
+	}
+
+	err = xsc_reset_function_resource(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "Failed to reset function resource\n");
+		goto err_cmd_cleanup;
+	}
+
 	return 0;
 err_cmd_cleanup:
 	xsc_cmd_cleanup(xdev);
@@ -261,6 +287,7 @@ static int __init xsc_init(void)
 static void __exit xsc_fini(void)
 {
 	pci_unregister_driver(&xsc_pci_driver);
+	xsc_free_board_info();
 }
 
 module_init(xsc_init);

From 947083e6f3f528d1a20d3d84ae93f96ba1c89e78 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:14:58 +0800
Subject: [PATCH 2594/2753] xsc: Add qp and cq management

Our hardware uses queue pairs (QP) and completion queues (CQ)
for packet transmission and reception. In the PCI driver, all
QP and CQ resources used by all xsc drivers(ethernet and rdma)
are recorded witch radix tree.
This patch defines the QP and CQ structures and initializes
the QP and CQ resource management during PCI initialization.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h | 155 ++++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   3 +-
 drivers/net/ethernet/yunsilicon/xsc/pci/cq.c  |  39 +++++
 drivers/net/ethernet/yunsilicon/xsc/pci/cq.h  |  14 ++
 drivers/net/ethernet/yunsilicon/xsc/pci/hw.c  |   1 +
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |   5 +
 drivers/net/ethernet/yunsilicon/xsc/pci/qp.c  |  80 +++++++++
 drivers/net/ethernet/yunsilicon/xsc/pci/qp.h  |  14 ++
 8 files changed, 310 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/cq.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/qp.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index 270e3d30a7c1b..db4b75afaa519 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -29,6 +29,10 @@
 
 #define XSC_REG_ADDR(dev, offset)	(((dev)->bar) + ((offset) - 0xA0000000))
 
+enum {
+	XSC_MAX_EQ_NAME	= 20
+};
+
 enum {
 	XSC_MAX_PORTS	= 2,
 };
@@ -43,6 +47,141 @@ enum {
 	XSC_MAX_UUARS		= XSC_MAX_UAR_PAGES * XSC_BF_REGS_PER_PAGE,
 };
 
+/* alloc */
+struct xsc_buf_list {
+	void			*buf;
+	dma_addr_t		map;
+};
+
+struct xsc_buf {
+	struct xsc_buf_list	direct;
+	struct xsc_buf_list	*page_list;
+	unsigned long		nbufs;
+	unsigned long		npages;
+	unsigned long		page_shift;
+	unsigned long		size;
+};
+
+struct xsc_frag_buf {
+	struct xsc_buf_list	*frags;
+	unsigned long		npages;
+	unsigned long		size;
+	u8			page_shift;
+};
+
+struct xsc_frag_buf_ctrl {
+	struct xsc_buf_list	*frags;
+	u32			sz_m1;
+	u16			frag_sz_m1;
+	u16			strides_offset;
+	u8			log_sz;
+	u8			log_stride;
+	u8			log_frag_strides;
+};
+
+/* qp */
+struct xsc_send_wqe_ctrl_seg {
+	__le32		data0;
+#define XSC_WQE_CTRL_SEG_MSG_OPCODE_MASK	GENMASK(7, 0)
+#define XSC_WQE_CTRL_SEG_WITH_IMM		BIT(8)
+#define XSC_WQE_CTRL_SEG_CSUM_EN_MASK		GENMASK(10, 9)
+#define XSC_WQE_CTRL_SEG_DS_DATA_NUM_MASK	GENMASK(15, 11)
+#define XSC_WQE_CTRL_SEG_WQE_ID_MASK		GENMASK(31, 16)
+
+	__le32		msg_len;
+	__le32		data2;
+#define XSC_WQE_CTRL_SEG_HAS_PPH		BIT(0)
+#define XSC_WQE_CTRL_SEG_SO_TYPE		BIT(1)
+#define XSC_WQE_CTRL_SEG_SO_DATA_SIZE_MASK	GENMASK(15, 2)
+#define XSC_WQE_CTRL_SEG_SO_HDR_LEN_MASK	GENMASK(31, 24)
+
+	__le32		data3;
+#define XSC_WQE_CTRL_SEG_SE			BIT(0)
+#define XSC_WQE_CTRL_SEG_CE			BIT(1)
+};
+
+struct xsc_wqe_data_seg {
+	__le32		data0;
+#define XSC_WQE_DATA_SEG_SEG_LEN_MASK		GENMASK(31, 1)
+
+	__le32		mkey;
+	__le64		va;
+};
+
+struct xsc_core_qp {
+	void			(*event)(struct xsc_core_qp *qp, int type);
+	u32			qpn;
+	atomic_t		refcount;
+	struct completion	free;
+	int			pid;
+	u16			qp_type;
+	u16			eth_queue_type;
+	u16			qp_type_internal;
+	u16			grp_id;
+	u8			mac_id;
+};
+
+struct xsc_qp_table {
+	spinlock_t		lock; /* protect radix tree */
+	struct radix_tree_root	tree;
+};
+
+/* cq */
+enum xsc_event {
+	XSC_EVENT_TYPE_COMP			= 0x0,
+	/* mad */
+	XSC_EVENT_TYPE_COMM_EST			= 0x02,
+	XSC_EVENT_TYPE_CQ_ERROR			= 0x04,
+	XSC_EVENT_TYPE_WQ_CATAS_ERROR		= 0x05,
+	XSC_EVENT_TYPE_INTERNAL_ERROR		= 0x08,
+	/* IBV_EVENT_QP_REQ_ERR */
+	XSC_EVENT_TYPE_WQ_INVAL_REQ_ERROR	= 0x10,
+	/* IBV_EVENT_QP_ACCESS_ERR */
+	XSC_EVENT_TYPE_WQ_ACCESS_ERROR		= 0x11,
+};
+
+struct xsc_core_cq {
+	u32			cqn;
+	u32			cqe_sz;
+	u64			arm_db;
+	u64			ci_db;
+	struct xsc_core_device	*xdev;
+	atomic_t		refcount;
+	struct completion	free;
+	unsigned int		vector;
+	unsigned int		irqn;
+	void			(*comp)(struct xsc_core_cq *cq);
+	void			(*event)(struct xsc_core_cq *cq,
+					 enum xsc_event);
+	u32			cons_index;
+	unsigned int		arm_sn;
+	int			pid;
+	u32			reg_next_cid;
+	u32			reg_done_pid;
+	struct xsc_eq		*eq;
+};
+
+struct xsc_cq_table {
+	spinlock_t		lock; /* protect radix tree */
+	struct radix_tree_root	tree;
+};
+
+struct xsc_eq {
+	struct xsc_core_device	*dev;
+	struct xsc_cq_table	cq_table;
+	/* offset from bar0/2 space start */
+	u32			doorbell;
+	u32			cons_index;
+	struct xsc_buf		buf;
+	unsigned int		irqn;
+	u32			eqn;
+	u32			nent;
+	cpumask_var_t		mask;
+	char			name[XSC_MAX_EQ_NAME];
+	struct list_head	list;
+	u16			index;
+};
+
 /* hw */
 struct xsc_reg_addr {
 	u64	tx_db;
@@ -169,6 +308,8 @@ struct xsc_caps {
 
 /* xsc_core */
 struct xsc_dev_resource {
+	struct xsc_qp_table	qp_table;
+	struct xsc_cq_table	cq_table;
 	/* protect buffer allocation according to numa node */
 	struct mutex		alloc_mutex;
 };
@@ -205,4 +346,18 @@ struct xsc_core_device {
 	u8			fw_version_extra_flag;
 };
 
+int xsc_core_create_resource_common(struct xsc_core_device *xdev,
+				    struct xsc_core_qp *qp);
+void xsc_core_destroy_resource_common(struct xsc_core_device *xdev,
+				      struct xsc_core_qp *qp);
+
+static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
+{
+	if (likely(buf->nbufs == 1))
+		return buf->direct.buf + offset;
+	else
+		return buf->page_list[offset >> PAGE_SHIFT].buf +
+			(offset & (PAGE_SIZE - 1));
+}
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index fea625d54af32..9a4a6e02da088 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,4 +6,5 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o hw.o
+xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
new file mode 100644
index 0000000000000..5cff9025cfc79
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
@@ -0,0 +1,39 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include "common/xsc_core.h"
+#include "cq.h"
+
+void xsc_cq_event(struct xsc_core_device *xdev, u32 cqn, int event_type)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+	struct xsc_core_cq *cq;
+
+	spin_lock(&table->lock);
+
+	cq = radix_tree_lookup(&table->tree, cqn);
+	if (cq)
+		atomic_inc(&cq->refcount);
+
+	spin_unlock(&table->lock);
+
+	if (!cq) {
+		pci_err(xdev->pdev, "Async event for bogus CQ 0x%x\n", cqn);
+		return;
+	}
+
+	cq->event(cq, event_type);
+
+	if (atomic_dec_and_test(&cq->refcount))
+		complete(&cq->free);
+}
+
+void xsc_init_cq_table(struct xsc_core_device *xdev)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+
+	spin_lock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/cq.h b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.h
new file mode 100644
index 0000000000000..902a7f1f23700
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __CQ_H
+#define __CQ_H
+
+#include "common/xsc_core.h"
+
+void xsc_cq_event(struct xsc_core_device *xdev, u32 cqn, int event_type);
+void xsc_init_cq_table(struct xsc_core_device *xdev);
+
+#endif /* __CQ_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
index 7d239ca177f96..6c39aac56231f 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/hw.c
@@ -5,6 +5,7 @@
 
 #include <linux/module.h>
 #include <linux/vmalloc.h>
+
 #include "common/xsc_driver.h"
 #include "hw.h"
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index 099feb6504833..03e8f269b1137 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -6,6 +6,8 @@
 #include "common/xsc_core.h"
 #include "common/xsc_driver.h"
 #include "hw.h"
+#include "qp.h"
+#include "cq.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -179,6 +181,9 @@ static int xsc_hw_setup(struct xsc_core_device *xdev)
 		goto err_cmd_cleanup;
 	}
 
+	xsc_init_cq_table(xdev);
+	xsc_init_qp_table(xdev);
+
 	return 0;
 err_cmd_cleanup:
 	xsc_cmd_cleanup(xdev);
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
new file mode 100644
index 0000000000000..cc79eaf921ac1
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/gfp.h>
+#include <linux/time.h>
+#include <linux/export.h>
+#include <linux/kthread.h>
+
+#include "common/xsc_core.h"
+#include "qp.h"
+
+int xsc_core_create_resource_common(struct xsc_core_device *xdev,
+				    struct xsc_core_qp *qp)
+{
+	struct xsc_qp_table *table = &xdev->dev_res->qp_table;
+	int err;
+
+	spin_lock_irq(&table->lock);
+	err = radix_tree_insert(&table->tree, qp->qpn, qp);
+	spin_unlock_irq(&table->lock);
+	if (err)
+		return err;
+
+	atomic_set(&qp->refcount, 1);
+	init_completion(&qp->free);
+	qp->pid = current->pid;
+
+	return 0;
+}
+EXPORT_SYMBOL(xsc_core_create_resource_common);
+
+void xsc_core_destroy_resource_common(struct xsc_core_device *xdev,
+				      struct xsc_core_qp *qp)
+{
+	struct xsc_qp_table *table = &xdev->dev_res->qp_table;
+	unsigned long flags;
+
+	spin_lock_irqsave(&table->lock, flags);
+	radix_tree_delete(&table->tree, qp->qpn);
+	spin_unlock_irqrestore(&table->lock, flags);
+
+	if (atomic_dec_and_test(&qp->refcount))
+		complete(&qp->free);
+	wait_for_completion(&qp->free);
+}
+EXPORT_SYMBOL(xsc_core_destroy_resource_common);
+
+void xsc_qp_event(struct xsc_core_device *xdev, u32 qpn, int event_type)
+{
+	struct xsc_qp_table *table = &xdev->dev_res->qp_table;
+	struct xsc_core_qp *qp;
+
+	spin_lock(&table->lock);
+
+	qp = radix_tree_lookup(&table->tree, qpn);
+	if (qp)
+		atomic_inc(&qp->refcount);
+
+	spin_unlock(&table->lock);
+
+	if (!qp) {
+		pci_err(xdev->pdev, "Async event for bogus QP 0x%x\n", qpn);
+		return;
+	}
+
+	qp->event(qp, event_type);
+
+	if (atomic_dec_and_test(&qp->refcount))
+		complete(&qp->free);
+}
+
+void xsc_init_qp_table(struct xsc_core_device *xdev)
+{
+	struct xsc_qp_table *table = &xdev->dev_res->qp_table;
+
+	spin_lock_init(&table->lock);
+	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/qp.h b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.h
new file mode 100644
index 0000000000000..af081933e0923
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __QP_H
+#define __QP_H
+
+#include "common/xsc_core.h"
+
+void xsc_init_qp_table(struct xsc_core_device *xdev);
+void xsc_qp_event(struct xsc_core_device *xdev, u32 qpn, int event_type);
+
+#endif /* __QP_H */

From b4ff8b3625b2e83dbd9e9fb3cd2bd3ce228fb5b3 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:00 +0800
Subject: [PATCH 2595/2753] xsc: Add eq and alloc

Add eq management and buffer alloc apis

This patch, along with the next one, implements the event handling
mechanism. The hardware uses the event queue (EQ) for event
reporting, notifying the CPU through interrupts, which then
reads and processes events from the EQ.

1. This patch implements the EQ API, including the initialization
of the EQ table, and the creation/destroy, start/stop operations
of the EQ.

2. When creating an event queue, a large amount of DMA memory is
required to store the ring buffer, necessitating multiple DMA page
allocations and unified management. For this purpose, we define
struct xsc_buff and use xsc_buf_alloc/free to allocate and free
memory. The usage of QP and CQ will also rely on these in the future.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |  38 ++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   3 +-
 .../net/ethernet/yunsilicon/xsc/pci/alloc.c   | 130 +++++++
 .../net/ethernet/yunsilicon/xsc/pci/alloc.h   |  17 +
 drivers/net/ethernet/yunsilicon/xsc/pci/eq.c  | 340 ++++++++++++++++++
 drivers/net/ethernet/yunsilicon/xsc/pci/eq.h  |  46 +++
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |   2 +
 7 files changed, 574 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/alloc.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/eq.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/eq.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index db4b75afaa519..78a77c7088d4f 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -27,12 +27,20 @@
 #define XSC_MV_HOST_VF_DEV_ID		0x1152
 #define XSC_MV_SOC_PF_DEV_ID		0x1153
 
+#define PAGE_SHIFT_4K			12
+#define PAGE_SIZE_4K			(_AC(1, UL) << PAGE_SHIFT_4K)
+#define PAGE_MASK_4K			(~(PAGE_SIZE_4K - 1))
+
 #define XSC_REG_ADDR(dev, offset)	(((dev)->bar) + ((offset) - 0xA0000000))
 
 enum {
 	XSC_MAX_EQ_NAME	= 20
 };
 
+enum {
+	XSC_MAX_IRQ_NAME	= 32
+};
+
 enum {
 	XSC_MAX_PORTS	= 2,
 };
@@ -166,6 +174,7 @@ struct xsc_cq_table {
 	struct radix_tree_root	tree;
 };
 
+/* eq */
 struct xsc_eq {
 	struct xsc_core_device	*dev;
 	struct xsc_cq_table	cq_table;
@@ -182,6 +191,25 @@ struct xsc_eq {
 	u16			index;
 };
 
+struct xsc_eq_table {
+	void __iomem		*update_ci;
+	void __iomem		*update_arm_ci;
+	struct list_head	comp_eqs_list;
+	struct xsc_eq		pages_eq;
+	struct xsc_eq		async_eq;
+	struct xsc_eq		cmd_eq;
+	int			num_comp_vectors;
+	int			eq_vec_comp_base;
+	/* protect EQs list */
+	spinlock_t		lock;
+};
+
+/* irq */
+struct xsc_irq_info {
+	cpumask_var_t mask;
+	char name[XSC_MAX_IRQ_NAME];
+};
+
 /* hw */
 struct xsc_reg_addr {
 	u64	tx_db;
@@ -310,6 +338,8 @@ struct xsc_caps {
 struct xsc_dev_resource {
 	struct xsc_qp_table	qp_table;
 	struct xsc_cq_table	cq_table;
+	struct xsc_eq_table	eq_table;
+	struct xsc_irq_info	*irq_info;
 	/* protect buffer allocation according to numa node */
 	struct mutex		alloc_mutex;
 };
@@ -326,6 +356,8 @@ struct xsc_core_device {
 	u8			mac_port;
 	u16			glb_func_id;
 
+	u16			msix_vec_base;
+
 	struct xsc_cmd		cmd;
 	u16			cmdq_ver;
 
@@ -350,6 +382,7 @@ int xsc_core_create_resource_common(struct xsc_core_device *xdev,
 				    struct xsc_core_qp *qp);
 void xsc_core_destroy_resource_common(struct xsc_core_device *xdev,
 				      struct xsc_core_qp *qp);
+struct xsc_eq *xsc_core_eq_get(struct xsc_core_device *xdev, int i);
 
 static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
 {
@@ -360,4 +393,9 @@ static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
 			(offset & (PAGE_SIZE - 1));
 }
 
+static inline bool xsc_fw_is_available(struct xsc_core_device *xdev)
+{
+	return xdev->cmd.cmd_status == XSC_CMD_STATUS_NORMAL;
+}
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index 9a4a6e02da088..667319958a2ec 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,5 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o
-
+xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
new file mode 100644
index 0000000000000..4c561d9fa6b64
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
@@ -0,0 +1,130 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/errno.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <linux/bitmap.h>
+#include <linux/dma-mapping.h>
+#include <linux/vmalloc.h>
+
+#include "alloc.h"
+
+/* Handling for queue buffers -- we allocate a bunch of memory and
+ * register it in a memory region at HCA virtual address 0.  If the
+ * requested size is > max_direct, we split the allocation into
+ * multiple pages, so we don't require too much contiguous memory.
+ */
+int xsc_buf_alloc(struct xsc_core_device *xdev,
+		  unsigned long size,
+		  unsigned long max_direct,
+		  struct xsc_buf *buf)
+{
+	dma_addr_t t;
+
+	buf->size = size;
+	if (size <= max_direct) {
+		buf->nbufs        = 1;
+		buf->npages       = 1;
+		buf->page_shift   = get_order(size) + PAGE_SHIFT;
+		buf->direct.buf   = dma_alloc_coherent(&xdev->pdev->dev,
+						       size,
+						       &t,
+						       GFP_KERNEL | __GFP_ZERO);
+		if (!buf->direct.buf)
+			return -ENOMEM;
+
+		buf->direct.map = t;
+
+		while (t & GENMASK(buf->page_shift - 1, 0)) {
+			--buf->page_shift;
+			buf->npages *= 2;
+		}
+	} else {
+		struct page **pages;
+		int i;
+
+		buf->direct.buf  = NULL;
+		buf->nbufs       = DIV_ROUND_UP(size, PAGE_SIZE);
+		buf->npages      = buf->nbufs;
+		buf->page_shift  = PAGE_SHIFT;
+		buf->page_list   = kcalloc(buf->nbufs, sizeof(*buf->page_list),
+					   GFP_KERNEL);
+		if (!buf->page_list)
+			return -ENOMEM;
+
+		for (i = 0; i < buf->nbufs; i++) {
+			buf->page_list[i].buf =
+				dma_alloc_coherent(&xdev->pdev->dev, PAGE_SIZE,
+						   &t, GFP_KERNEL | __GFP_ZERO);
+			if (!buf->page_list[i].buf)
+				goto err_free;
+
+			buf->page_list[i].map = t;
+		}
+
+		pages = kmalloc_array(buf->nbufs, sizeof(*pages), GFP_KERNEL);
+		if (!pages)
+			goto err_free;
+		for (i = 0; i < buf->nbufs; i++) {
+			void *addr = buf->page_list[i].buf;
+
+			if (is_vmalloc_addr(addr))
+				pages[i] = vmalloc_to_page(addr);
+			else
+				pages[i] = virt_to_page(addr);
+		}
+		buf->direct.buf = vmap(pages, buf->nbufs, VM_MAP, PAGE_KERNEL);
+		kfree(pages);
+		if (!buf->direct.buf)
+			goto err_free;
+	}
+
+	return 0;
+
+err_free:
+	xsc_buf_free(xdev, buf);
+
+	return -ENOMEM;
+}
+
+void xsc_buf_free(struct xsc_core_device *xdev, struct xsc_buf *buf)
+{
+	int i;
+
+	if (buf->nbufs == 1) {
+		dma_free_coherent(&xdev->pdev->dev, buf->size, buf->direct.buf,
+				  buf->direct.map);
+	} else {
+		if (BITS_PER_LONG == 64 && buf->direct.buf)
+			vunmap(buf->direct.buf);
+
+		for (i = 0; i < buf->nbufs; i++)
+			if (buf->page_list[i].buf)
+				dma_free_coherent(&xdev->pdev->dev, PAGE_SIZE,
+						  buf->page_list[i].buf,
+						  buf->page_list[i].map);
+		kfree(buf->page_list);
+	}
+}
+
+void xsc_fill_page_array(struct xsc_buf *buf, __be64 *pas, unsigned int npages)
+{
+	unsigned int shift = PAGE_SHIFT - PAGE_SHIFT_4K;
+	unsigned int mask = (1 << shift) - 1;
+	u64 addr;
+	int i;
+
+	for (i = 0; i < npages; i++) {
+		if (buf->nbufs == 1)
+			addr = buf->direct.map + (i << PAGE_SHIFT_4K);
+		else
+			addr = buf->page_list[i >> shift].map +
+			       ((i & mask) << PAGE_SHIFT_4K);
+
+		pas[i] = cpu_to_be64(addr);
+	}
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.h b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.h
new file mode 100644
index 0000000000000..a1c4b92a5aa2a
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __ALLOC_H
+#define __ALLOC_H
+
+#include "common/xsc_core.h"
+
+int xsc_buf_alloc(struct xsc_core_device *xdev,
+		  unsigned long size,
+		  unsigned long max_direct,
+		  struct xsc_buf *buf);
+void xsc_buf_free(struct xsc_core_device *xdev, struct xsc_buf *buf);
+void xsc_fill_page_array(struct xsc_buf *buf, __be64 *pas, unsigned int npages);
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/eq.c b/drivers/net/ethernet/yunsilicon/xsc/pci/eq.c
new file mode 100644
index 0000000000000..aa2c0ba61cda8
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/eq.c
@@ -0,0 +1,340 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/mm.h>
+
+#include "common/xsc_driver.h"
+#include "common/xsc_core.h"
+#include "qp.h"
+#include "alloc.h"
+#include "eq.h"
+
+enum {
+	XSC_EQE_SIZE		= sizeof(struct xsc_eqe),
+};
+
+enum {
+	XSC_NUM_SPARE_EQE	= 0x80,
+	XSC_NUM_ASYNC_EQE	= 0x100,
+};
+
+static int xsc_cmd_destroy_eq(struct xsc_core_device *xdev, u32 eqn)
+{
+	struct xsc_destroy_eq_mbox_out out = {0};
+	struct xsc_destroy_eq_mbox_in in = {0};
+	int err;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_DESTROY_EQ);
+	in.eqn = cpu_to_be32(eqn);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (!err)
+		return 0;
+
+	if (out.hdr.status)
+		err = xsc_cmd_status_to_err(&out.hdr);
+
+	return err;
+}
+
+static struct xsc_eqe *get_eqe(struct xsc_eq *eq, u32 entry)
+{
+	return xsc_buf_offset(&eq->buf, entry * XSC_EQE_SIZE);
+}
+
+static struct xsc_eqe *next_eqe_sw(struct xsc_eq *eq)
+{
+	struct xsc_eqe *eqe = get_eqe(eq, eq->cons_index & (eq->nent - 1));
+
+	return ((eqe->owner_data & XSC_EQE_OWNER) ^
+		!!(eq->cons_index & eq->nent)) ? NULL : eqe;
+}
+
+static void eq_update_ci(struct xsc_eq *eq, int arm)
+{
+	u32 db_val = 0;
+
+	db_val = FIELD_PREP(XSC_EQ_DB_NEXT_CID_MASK, eq->cons_index) |
+		 FIELD_PREP(XSC_EQ_DB_EQ_ID_MASK, eq->eqn);
+	if (arm)
+		db_val |= XSC_EQ_DB_ARM;
+	/* make sure memory is written before device access */
+	wmb();
+	writel(db_val, XSC_REG_ADDR(eq->dev, eq->doorbell));
+}
+
+static void xsc_cq_completion(struct xsc_core_device *xdev, u32 cqn)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+	struct xsc_core_cq *cq;
+
+	rcu_read_lock();
+	cq = radix_tree_lookup(&table->tree, cqn);
+	if (likely(cq))
+		atomic_inc(&cq->refcount);
+	rcu_read_unlock();
+
+	if (!cq) {
+		pci_err(xdev->pdev, "Completion event for bogus CQ, cqn=%d\n",
+			cqn);
+		return;
+	}
+
+	++cq->arm_sn;
+
+	if (!cq->comp)
+		pci_err(xdev->pdev, "cq->comp is NULL\n");
+	else
+		cq->comp(cq);
+
+	if (atomic_dec_and_test(&cq->refcount))
+		complete(&cq->free);
+}
+
+static void xsc_eq_cq_event(struct xsc_core_device *xdev,
+			    u32 cqn, int event_type)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+	struct xsc_core_cq *cq;
+
+	spin_lock(&table->lock);
+	cq = radix_tree_lookup(&table->tree, cqn);
+	if (likely(cq))
+		atomic_inc(&cq->refcount);
+	spin_unlock(&table->lock);
+
+	if (unlikely(!cq)) {
+		pci_err(xdev->pdev, "Async event for bogus CQ, cqn=%d\n",
+			cqn);
+		return;
+	}
+
+	cq->event(cq, event_type);
+
+	if (atomic_dec_and_test(&cq->refcount))
+		complete(&cq->free);
+}
+
+static int xsc_eq_int(struct xsc_core_device *xdev, struct xsc_eq *eq)
+{
+	u32 cqn, qpn, queue_id;
+	struct xsc_eqe *eqe;
+	int eqes_found = 0;
+	int set_ci = 0;
+
+	while ((eqe = next_eqe_sw(eq))) {
+		/* Make sure we read EQ entry contents after we've
+		 * checked the ownership bit.
+		 */
+		rmb();
+		switch (eqe->type) {
+		case XSC_EVENT_TYPE_COMP:
+		case XSC_EVENT_TYPE_INTERNAL_ERROR:
+			/* eqe is changing */
+			queue_id = FIELD_GET(XSC_EQE_QUEUE_ID_MASK,
+					     le16_to_cpu(eqe->queue_id_data));
+			cqn = queue_id;
+			xsc_cq_completion(xdev, cqn);
+			break;
+
+		case XSC_EVENT_TYPE_CQ_ERROR:
+			queue_id = FIELD_GET(XSC_EQE_QUEUE_ID_MASK,
+					     le16_to_cpu(eqe->queue_id_data));
+			cqn = queue_id;
+			xsc_eq_cq_event(xdev, cqn, eqe->type);
+			break;
+		case XSC_EVENT_TYPE_WQ_CATAS_ERROR:
+		case XSC_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+		case XSC_EVENT_TYPE_WQ_ACCESS_ERROR:
+			queue_id = FIELD_GET(XSC_EQE_QUEUE_ID_MASK,
+					     le16_to_cpu(eqe->queue_id_data));
+			qpn = queue_id;
+			xsc_qp_event(xdev, qpn, eqe->type);
+			break;
+		default:
+			break;
+		}
+
+		++eq->cons_index;
+		eqes_found = 1;
+		++set_ci;
+
+		/* The HCA will think the queue has overflowed if we
+		 * don't tell it we've been processing events.  We
+		 * create our EQs with XSC_NUM_SPARE_EQE extra
+		 * entries, so we must update our consumer index at
+		 * least that often.
+		 */
+		if (unlikely(set_ci >= XSC_NUM_SPARE_EQE)) {
+			eq_update_ci(eq, 0);
+			set_ci = 0;
+		}
+	}
+
+	eq_update_ci(eq, 1);
+
+	return eqes_found;
+}
+
+static irqreturn_t xsc_msix_handler(int irq, void *eq_ptr)
+{
+	struct xsc_core_device *xdev;
+	struct xsc_eq *eq = eq_ptr;
+
+	xdev = eq->dev;
+	xsc_eq_int(xdev, eq);
+
+	/* MSI-X vectors always belong to us */
+	return IRQ_HANDLED;
+}
+
+static void init_eq_buf(struct xsc_eq *eq)
+{
+	struct xsc_eqe *eqe;
+	int i;
+
+	for (i = 0; i < eq->nent; i++) {
+		eqe = get_eqe(eq, i);
+		eqe->owner_data |= XSC_EQE_OWNER;
+	}
+}
+
+int xsc_create_map_eq(struct xsc_core_device *xdev,
+		      struct xsc_eq *eq, u16 vecidx,
+		      u32 nent, const char *name)
+{
+	u16 msix_vec_offset = xdev->msix_vec_base + vecidx;
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+	struct xsc_create_eq_mbox_out out;
+	struct xsc_create_eq_mbox_in *in;
+	unsigned int hw_npages;
+	u32 inlen;
+	int err;
+
+	eq->nent = roundup_pow_of_two(roundup(nent, XSC_NUM_SPARE_EQE));
+	err = xsc_buf_alloc(xdev, eq->nent * XSC_EQE_SIZE, PAGE_SIZE, &eq->buf);
+	if (err)
+		return err;
+
+	init_eq_buf(eq);
+
+	hw_npages = DIV_ROUND_UP(eq->nent * XSC_EQE_SIZE, PAGE_SIZE_4K);
+	inlen = sizeof(*in) + sizeof(in->pas[0]) * hw_npages;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		err = -ENOMEM;
+		goto err_free_eq_buf;
+	}
+	memset(&out, 0, sizeof(out));
+
+	xsc_fill_page_array(&eq->buf, in->pas, hw_npages);
+
+	in->hdr.opcode = cpu_to_be16(XSC_CMD_OP_CREATE_EQ);
+	in->ctx.log_eq_sz = ilog2(eq->nent);
+	in->ctx.vecidx = cpu_to_be16(msix_vec_offset);
+	in->ctx.pa_num = cpu_to_be16(hw_npages);
+	in->ctx.glb_func_id = cpu_to_be16(xdev->glb_func_id);
+	in->ctx.is_async_eq = (vecidx == XSC_EQ_VEC_ASYNC ? 1 : 0);
+
+	err = xsc_cmd_exec(xdev, in, inlen, &out, sizeof(out));
+	if (err)
+		goto err_free_in;
+
+	if (out.hdr.status) {
+		err = -ENOSPC;
+		goto err_free_in;
+	}
+
+	snprintf(dev_res->irq_info[vecidx].name, XSC_MAX_IRQ_NAME, "%s@pci:%s",
+		 name, pci_name(xdev->pdev));
+
+	eq->eqn = be32_to_cpu(out.eqn);
+	eq->irqn = pci_irq_vector(xdev->pdev, vecidx);
+	eq->dev = xdev;
+	eq->doorbell = xdev->regs.event_db;
+	eq->index = vecidx;
+
+	err = request_irq(eq->irqn, xsc_msix_handler, 0,
+			  dev_res->irq_info[vecidx].name, eq);
+	if (err)
+		goto err_destroy_eq;
+
+	/* EQs are created in ARMED state
+	 */
+	eq_update_ci(eq, 1);
+	kvfree(in);
+	return 0;
+
+err_destroy_eq:
+	xsc_cmd_destroy_eq(xdev, eq->eqn);
+
+err_free_in:
+	kvfree(in);
+
+err_free_eq_buf:
+	xsc_buf_free(xdev, &eq->buf);
+	return err;
+}
+
+int xsc_destroy_unmap_eq(struct xsc_core_device *xdev, struct xsc_eq *eq)
+{
+	int err;
+
+	if (!xsc_fw_is_available(xdev))
+		return 0;
+
+	free_irq(eq->irqn, eq);
+	err = xsc_cmd_destroy_eq(xdev, eq->eqn);
+	if (err)
+		pci_err(xdev->pdev, "failed to destroy a previously created eq: eqn %d\n",
+			eq->eqn);
+	xsc_buf_free(xdev, &eq->buf);
+
+	return err;
+}
+
+void xsc_eq_init(struct xsc_core_device *xdev)
+{
+	spin_lock_init(&xdev->dev_res->eq_table.lock);
+}
+
+int xsc_start_eqs(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	int err;
+
+	err = xsc_create_map_eq(xdev, &table->async_eq, XSC_EQ_VEC_ASYNC,
+				XSC_NUM_ASYNC_EQE, "xsc_async_eq");
+	if (err)
+		pci_err(xdev->pdev, "failed to create async EQ %d\n", err);
+
+	return err;
+}
+
+void xsc_stop_eqs(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+
+	xsc_destroy_unmap_eq(xdev, &table->async_eq);
+}
+
+struct xsc_eq *xsc_core_eq_get(struct xsc_core_device *xdev, int i)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	struct xsc_eq *eq_ret = NULL;
+	struct xsc_eq *eq, *n;
+
+	spin_lock(&table->lock);
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		if (eq->index == i) {
+			eq_ret = eq;
+			break;
+		}
+	}
+	spin_unlock(&table->lock);
+
+	return eq_ret;
+}
+EXPORT_SYMBOL(xsc_core_eq_get);
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/eq.h b/drivers/net/ethernet/yunsilicon/xsc/pci/eq.h
new file mode 100644
index 0000000000000..b863a459b01f7
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/eq.h
@@ -0,0 +1,46 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __EQ_H
+#define __EQ_H
+
+#include "common/xsc_core.h"
+
+enum {
+	XSC_EQ_VEC_ASYNC		= 0,
+	XSC_VEC_CMD			= 1,
+	XSC_VEC_CMD_EVENT		= 2,
+	XSC_DMA_READ_DONE_VEC		= 3,
+	XSC_EQ_VEC_COMP_BASE,
+};
+
+struct xsc_eqe {
+	u8 type;
+	u8 sub_type;
+	__le16 queue_id_data;
+#define XSC_EQE_QUEUE_ID_MASK	GENMASK(14, 0)
+
+	u8 err_code;
+	u8 rsvd[2];
+	u8 owner_data;
+#define XSC_EQE_OWNER		BIT(7)
+};
+
+/* eq doorbell bitfields */
+#define XSC_EQ_DB_NEXT_CID_SHIFT	0
+#define XSC_EQ_DB_NEXT_CID_MASK		GENMASK(10, 0)
+#define XSC_EQ_DB_EQ_ID_SHIFT		11
+#define XSC_EQ_DB_EQ_ID_MASK		GENMASK(21, 11)
+#define XSC_EQ_DB_ARM			BIT(22)
+
+int xsc_create_map_eq(struct xsc_core_device *xdev,
+		      struct xsc_eq *eq, u16 vecidx,
+		      u32 nent, const char *name);
+int xsc_destroy_unmap_eq(struct xsc_core_device *xdev, struct xsc_eq *eq);
+void xsc_eq_init(struct xsc_core_device *xdev);
+int xsc_start_eqs(struct xsc_core_device *xdev);
+void xsc_stop_eqs(struct xsc_core_device *xdev);
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index 03e8f269b1137..161af95e06690 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -8,6 +8,7 @@
 #include "hw.h"
 #include "qp.h"
 #include "cq.h"
+#include "eq.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -183,6 +184,7 @@ static int xsc_hw_setup(struct xsc_core_device *xdev)
 
 	xsc_init_cq_table(xdev);
 	xsc_init_qp_table(xdev);
+	xsc_eq_init(xdev);
 
 	return 0;
 err_cmd_cleanup:

From d30ba78756f3b1dae35e8c3d882d2ca6afa80f19 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:04 +0800
Subject: [PATCH 2596/2753] xsc: Init pci irq

This patch implements the initialization of PCI MSI-X interrupts.
It handles the allocation of MSI-X interrupt vectors, registration
of interrupt requests (IRQs), configuration of interrupt affinity
, and interrupt handlers for different event types, including:

- Completion events (handled via completion queues).
- Command queue (cmdq) events (via xsc_cmd_handler).
- Asynchronous events (via xsc_event_handler).

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |   6 +
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   2 +-
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |  14 +-
 .../net/ethernet/yunsilicon/xsc/pci/pci_irq.c | 426 ++++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/pci_irq.h |  14 +
 5 files changed, 460 insertions(+), 2 deletions(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index 78a77c7088d4f..60dde506e8e13 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -347,9 +347,12 @@ struct xsc_dev_resource {
 struct xsc_core_device {
 	struct pci_dev		*pdev;
 	struct device		*device;
+	void			*eth_priv;
 	struct xsc_dev_resource	*dev_res;
 	int			numa_node;
 
+	void (*event_handler)(void *adapter);
+
 	void __iomem		*bar;
 	int			bar_num;
 
@@ -376,6 +379,7 @@ struct xsc_core_device {
 	u16			fw_version_patch;
 	u32			fw_version_tweak;
 	u8			fw_version_extra_flag;
+	cpumask_var_t		xps_cpumask;
 };
 
 int xsc_core_create_resource_common(struct xsc_core_device *xdev,
@@ -383,6 +387,8 @@ int xsc_core_create_resource_common(struct xsc_core_device *xdev,
 void xsc_core_destroy_resource_common(struct xsc_core_device *xdev,
 				      struct xsc_core_qp *qp);
 struct xsc_eq *xsc_core_eq_get(struct xsc_core_device *xdev, int i);
+int xsc_core_vector2eqn(struct xsc_core_device *xdev, int vector, u32 *eqn,
+			unsigned int *irqn);
 
 static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
 {
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index 667319958a2ec..3525d1c742dfa 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o
+xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o pci_irq.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index 161af95e06690..69f508af5572d 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -9,6 +9,7 @@
 #include "qp.h"
 #include "cq.h"
 #include "eq.h"
+#include "pci_irq.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -205,14 +206,25 @@ static int xsc_load(struct xsc_core_device *xdev)
 	err = xsc_hw_setup(xdev);
 	if (err) {
 		pci_err(xdev->pdev, "xsc_hw_setup failed %d\n", err);
-		return err;
+		goto err_out;
+	}
+
+	err = xsc_irq_eq_create(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc_irq_eq_create failed %d\n", err);
+		goto err_hw_cleanup;
 	}
 
 	return 0;
+err_hw_cleanup:
+	xsc_hw_cleanup(xdev);
+err_out:
+	return err;
 }
 
 static void xsc_unload(struct xsc_core_device *xdev)
 {
+	xsc_irq_eq_destroy(xdev);
 	xsc_hw_cleanup(xdev);
 }
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.c b/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.c
new file mode 100644
index 0000000000000..e8b680cc26f06
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.c
@@ -0,0 +1,426 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/irqdomain.h>
+#include <linux/msi.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/module.h>
+#ifdef CONFIG_RFS_ACCEL
+#include <linux/cpu_rmap.h>
+#endif
+
+#include "common/xsc_driver.h"
+#include "common/xsc_core.h"
+#include "eq.h"
+#include "pci_irq.h"
+
+enum {
+	XSC_COMP_EQ_SIZE = 1024,
+};
+
+enum xsc_eq_type {
+	XSC_EQ_TYPE_COMP,
+	XSC_EQ_TYPE_ASYNC,
+};
+
+struct xsc_irq {
+	struct atomic_notifier_head nh;
+	cpumask_var_t mask;
+	char name[XSC_MAX_IRQ_NAME];
+};
+
+struct xsc_irq_table {
+	struct xsc_irq *irq;
+	int nvec;
+#ifdef CONFIG_RFS_ACCEL
+	struct cpu_rmap *rmap;
+#endif
+};
+
+static void xsc_free_irq(struct xsc_core_device *xdev, unsigned int vector)
+{
+	unsigned int irqn = 0;
+
+	irqn = pci_irq_vector(xdev->pdev, vector);
+	disable_irq(irqn);
+
+	if (xsc_fw_is_available(xdev))
+		free_irq(irqn, xdev);
+}
+
+static int set_comp_irq_affinity_hint(struct xsc_core_device *xdev, int i)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	struct xsc_eq *eq = xsc_core_eq_get(xdev, i);
+	int vecidx = table->eq_vec_comp_base + i;
+	unsigned int irqn;
+	int ret;
+
+	irqn = pci_irq_vector(xdev->pdev, vecidx);
+	if (!zalloc_cpumask_var(&eq->mask, GFP_KERNEL)) {
+		pci_err(xdev->pdev, "zalloc_cpumask_var rx cpumask failed");
+		return -ENOMEM;
+	}
+
+	if (!zalloc_cpumask_var(&xdev->xps_cpumask, GFP_KERNEL)) {
+		pci_err(xdev->pdev, "zalloc_cpumask_var tx cpumask failed");
+		return -ENOMEM;
+	}
+
+	cpumask_set_cpu(cpumask_local_spread(i, xdev->numa_node),
+			xdev->xps_cpumask);
+	ret = irq_set_affinity_hint(irqn, eq->mask);
+
+	return ret;
+}
+
+static void clear_comp_irq_affinity_hint(struct xsc_core_device *xdev, int i)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	struct xsc_eq *eq = xsc_core_eq_get(xdev, i);
+	int vecidx = table->eq_vec_comp_base + i;
+	int irqn;
+
+	irqn = pci_irq_vector(xdev->pdev, vecidx);
+	irq_set_affinity_hint(irqn, NULL);
+	free_cpumask_var(eq->mask);
+}
+
+static int set_comp_irq_affinity_hints(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	int nvec = table->num_comp_vectors;
+	int err;
+	int i;
+
+	for (i = 0; i < nvec; i++) {
+		err = set_comp_irq_affinity_hint(xdev, i);
+		if (err)
+			goto err_out;
+	}
+
+	return 0;
+
+err_out:
+	for (i--; i >= 0; i--)
+		clear_comp_irq_affinity_hint(xdev, i);
+	free_cpumask_var(xdev->xps_cpumask);
+
+	return err;
+}
+
+static void clear_comp_irq_affinity_hints(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	int nvec = table->num_comp_vectors;
+	int i;
+
+	for (i = 0; i < nvec; i++)
+		clear_comp_irq_affinity_hint(xdev, i);
+	free_cpumask_var(xdev->xps_cpumask);
+}
+
+static int xsc_alloc_irq_vectors(struct xsc_core_device *xdev)
+{
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+	struct xsc_eq_table *table = &dev_res->eq_table;
+	int nvec = xdev->caps.msix_num;
+	int nvec_base;
+	int err;
+
+	nvec_base = XSC_EQ_VEC_COMP_BASE;
+	if (nvec <= nvec_base) {
+		pci_err(xdev->pdev, "failed to alloc irq vector(%d)\n", nvec);
+		return -ENOMEM;
+	}
+
+	dev_res->irq_info = kcalloc(nvec, sizeof(*dev_res->irq_info),
+				    GFP_KERNEL);
+	if (!dev_res->irq_info)
+		return -ENOMEM;
+
+	nvec = pci_alloc_irq_vectors(xdev->pdev, nvec_base + 1, nvec,
+				     PCI_IRQ_MSIX);
+	if (nvec < 0) {
+		err = nvec;
+		goto err_free_irq_info;
+	}
+
+	table->eq_vec_comp_base = nvec_base;
+	table->num_comp_vectors = nvec - nvec_base;
+	xdev->msix_vec_base = xdev->caps.msix_base;
+
+	return 0;
+
+err_free_irq_info:
+	kfree(dev_res->irq_info);
+	return err;
+}
+
+static void xsc_free_irq_vectors(struct xsc_core_device *xdev)
+{
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+
+	if (!xsc_fw_is_available(xdev))
+		return;
+
+	pci_free_irq_vectors(xdev->pdev);
+	kfree(dev_res->irq_info);
+}
+
+int xsc_core_vector2eqn(struct xsc_core_device *xdev, int vector, u32 *eqn,
+			unsigned int *irqn)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	struct xsc_eq *eq, *n;
+	int err = -ENOENT;
+
+	if (!xdev->caps.msix_enable)
+		return 0;
+
+	spin_lock(&table->lock);
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		if (eq->index == vector) {
+			*eqn = eq->eqn;
+			*irqn = eq->irqn;
+			err = 0;
+			break;
+		}
+	}
+	spin_unlock(&table->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(xsc_core_vector2eqn);
+
+static void free_comp_eqs(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	struct xsc_eq *eq, *n;
+
+	spin_lock(&table->lock);
+	list_for_each_entry_safe(eq, n, &table->comp_eqs_list, list) {
+		list_del(&eq->list);
+		spin_unlock(&table->lock);
+		if (xsc_destroy_unmap_eq(xdev, eq))
+			pci_err(xdev->pdev, "failed to destroy EQ 0x%x\n",
+				eq->eqn);
+		kfree(eq);
+		spin_lock(&table->lock);
+	}
+	spin_unlock(&table->lock);
+}
+
+static int alloc_comp_eqs(struct xsc_core_device *xdev)
+{
+	struct xsc_eq_table *table = &xdev->dev_res->eq_table;
+	char name[XSC_MAX_IRQ_NAME];
+	struct xsc_eq *eq;
+	int ncomp_vec;
+	u32 nent;
+	int err;
+	int i;
+
+	INIT_LIST_HEAD(&table->comp_eqs_list);
+	ncomp_vec = table->num_comp_vectors;
+	nent = XSC_COMP_EQ_SIZE;
+
+	for (i = 0; i < ncomp_vec; i++) {
+		eq = kzalloc(sizeof(*eq), GFP_KERNEL);
+		if (!eq) {
+			err = -ENOMEM;
+			goto err_free;
+		}
+
+		snprintf(name, XSC_MAX_IRQ_NAME, "xsc_comp%d", i);
+		err = xsc_create_map_eq(xdev, eq,
+					i + table->eq_vec_comp_base,
+					nent, name);
+		if (err) {
+			kfree(eq);
+			goto err_free;
+		}
+
+		eq->index = i;
+		spin_lock(&table->lock);
+		list_add_tail(&eq->list, &table->comp_eqs_list);
+		spin_unlock(&table->lock);
+	}
+
+	return 0;
+
+err_free:
+	free_comp_eqs(xdev);
+	return err;
+}
+
+static irqreturn_t xsc_cmd_handler(int irq, void *arg)
+{
+	struct xsc_core_device *xdev = (struct xsc_core_device *)arg;
+	int err;
+
+	disable_irq_nosync(xdev->cmd.irqn);
+	err = xsc_cmd_err_handler(xdev);
+	if (!err)
+		xsc_cmd_resp_handler(xdev);
+	enable_irq(xdev->cmd.irqn);
+
+	return IRQ_HANDLED;
+}
+
+static int xsc_request_irq_for_cmdq(struct xsc_core_device *xdev, u8 vecidx)
+{
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+
+	writel(xdev->msix_vec_base + vecidx,
+	       XSC_REG_ADDR(xdev, xdev->cmd.reg.msix_vec_addr));
+
+	snprintf(dev_res->irq_info[vecidx].name, XSC_MAX_IRQ_NAME, "%s@pci:%s",
+		 "xsc_cmd", pci_name(xdev->pdev));
+	xdev->cmd.irqn = pci_irq_vector(xdev->pdev, vecidx);
+	return request_irq(xdev->cmd.irqn, xsc_cmd_handler, 0,
+		dev_res->irq_info[vecidx].name, xdev);
+}
+
+static void xsc_free_irq_for_cmdq(struct xsc_core_device *xdev)
+{
+	xsc_free_irq(xdev, XSC_VEC_CMD);
+}
+
+static irqreturn_t xsc_event_handler(int irq, void *arg)
+{
+	struct xsc_core_device *xdev = (struct xsc_core_device *)arg;
+
+	if (!xdev->eth_priv)
+		return IRQ_NONE;
+
+	if (!xdev->event_handler)
+		return IRQ_NONE;
+
+	xdev->event_handler(xdev->eth_priv);
+
+	return IRQ_HANDLED;
+}
+
+static int xsc_request_irq_for_event(struct xsc_core_device *xdev)
+{
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+
+	snprintf(dev_res->irq_info[XSC_VEC_CMD_EVENT].name,
+		 XSC_MAX_IRQ_NAME, "%s@pci:%s",
+		 "xsc_eth_event", pci_name(xdev->pdev));
+	return request_irq(pci_irq_vector(xdev->pdev, XSC_VEC_CMD_EVENT),
+			   xsc_event_handler, 0,
+			   dev_res->irq_info[XSC_VEC_CMD_EVENT].name, xdev);
+}
+
+static void xsc_free_irq_for_event(struct xsc_core_device *xdev)
+{
+	xsc_free_irq(xdev, XSC_VEC_CMD_EVENT);
+}
+
+static int xsc_cmd_enable_msix(struct xsc_core_device *xdev)
+{
+	struct xsc_msix_table_info_mbox_out out;
+	struct xsc_msix_table_info_mbox_in in;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_ENABLE_MSIX);
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err) {
+		pci_err(xdev->pdev, "xsc_cmd_exec enable msix failed %d\n",
+			err);
+		return err;
+	}
+
+	return 0;
+}
+
+int xsc_irq_eq_create(struct xsc_core_device *xdev)
+{
+	int err;
+
+	if (xdev->caps.msix_enable == 0)
+		return 0;
+
+	err = xsc_alloc_irq_vectors(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "enable msix failed, err=%d\n", err);
+		goto err_out;
+	}
+
+	err = xsc_start_eqs(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to start EQs, err=%d\n", err);
+		goto err_free_irq_vectors;
+	}
+
+	err = alloc_comp_eqs(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to alloc comp EQs, err=%d\n", err);
+		goto err_stop_eqs;
+	}
+
+	err = xsc_request_irq_for_cmdq(xdev, XSC_VEC_CMD);
+	if (err) {
+		pci_err(xdev->pdev, "failed to request irq for cmdq, err=%d\n",
+			err);
+		goto err_free_comp_eqs;
+	}
+
+	err = xsc_request_irq_for_event(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to request irq for event, err=%d\n",
+			err);
+		goto err_free_irq_cmdq;
+	}
+
+	err = set_comp_irq_affinity_hints(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "failed to alloc affinity hint cpumask, err=%d\n",
+			err);
+		goto err_free_irq_evnt;
+	}
+
+	xsc_cmd_use_events(xdev);
+	err = xsc_cmd_enable_msix(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc_cmd_enable_msix failed %d.\n", err);
+		xsc_cmd_use_polling(xdev);
+		goto err_free_irq_evnt;
+	}
+	return 0;
+
+err_free_irq_evnt:
+	xsc_free_irq_for_event(xdev);
+err_free_irq_cmdq:
+	xsc_free_irq_for_cmdq(xdev);
+err_free_comp_eqs:
+	free_comp_eqs(xdev);
+err_stop_eqs:
+	xsc_stop_eqs(xdev);
+err_free_irq_vectors:
+	xsc_free_irq_vectors(xdev);
+err_out:
+	return err;
+}
+
+void xsc_irq_eq_destroy(struct xsc_core_device *xdev)
+{
+	if (xdev->caps.msix_enable == 0)
+		return;
+
+	xsc_stop_eqs(xdev);
+	clear_comp_irq_affinity_hints(xdev);
+	free_comp_eqs(xdev);
+
+	xsc_free_irq_for_event(xdev);
+	xsc_free_irq_for_cmdq(xdev);
+	xsc_free_irq_vectors(xdev);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.h b/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.h
new file mode 100644
index 0000000000000..e85c97cbc9f0f
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/pci_irq.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __PCI_IRQ_H
+#define __PCI_IRQ_H
+
+#include "common/xsc_core.h"
+
+int xsc_irq_eq_create(struct xsc_core_device *xdev);
+void xsc_irq_eq_destroy(struct xsc_core_device *xdev);
+
+#endif

From bb6b91b100b8639ea2b2f4d1f742a2ce66a13c3f Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:07 +0800
Subject: [PATCH 2597/2753] xsc: Init auxiliary device

Our device supports both Ethernet and RDMA functionalities, and
leveraging the auxiliary bus perfectly addresses our needs for
managing these distinct features. This patch utilizes auxiliary
device to handle the Ethernet functionality, while defining
xsc_adev_list to reserve expansion space for future RDMA
capabilities.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |  14 +++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |   3 +-
 .../net/ethernet/yunsilicon/xsc/pci/adev.c    | 115 ++++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/adev.h    |  14 +++
 .../net/ethernet/yunsilicon/xsc/pci/main.c    |  10 ++
 5 files changed, 155 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/adev.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/adev.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index 60dde506e8e13..e6863cb087c96 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -7,6 +7,7 @@
 #define __XSC_CORE_H
 
 #include <linux/pci.h>
+#include <linux/auxiliary_bus.h>
 
 #include "common/xsc_cmdq.h"
 
@@ -210,6 +211,17 @@ struct xsc_irq_info {
 	char name[XSC_MAX_IRQ_NAME];
 };
 
+/* adev */
+#define XSC_PCI_DRV_NAME "xsc_pci"
+#define XSC_ETH_ADEV_NAME "eth"
+
+struct xsc_adev {
+	struct auxiliary_device	adev;
+	struct xsc_core_device	*xdev;
+
+	int			idx;
+};
+
 /* hw */
 struct xsc_reg_addr {
 	u64	tx_db;
@@ -347,6 +359,8 @@ struct xsc_dev_resource {
 struct xsc_core_device {
 	struct pci_dev		*pdev;
 	struct device		*device;
+	int			adev_id;
+	struct xsc_adev		**xsc_adev_list;
 	void			*eth_priv;
 	struct xsc_dev_resource	*dev_res;
 	int			numa_node;
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index 3525d1c742dfa..ad0ecc122a794 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,4 +6,5 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o pci_irq.o
+xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o pci_irq.o adev.o
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/adev.c b/drivers/net/ethernet/yunsilicon/xsc/pci/adev.c
new file mode 100644
index 0000000000000..c9c6328a4b0a6
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/adev.c
@@ -0,0 +1,115 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/idr.h>
+
+#include "adev.h"
+
+static DEFINE_IDA(xsc_adev_ida);
+
+enum xsc_adev_idx {
+	XSC_ADEV_IDX_ETH,
+};
+
+static const char * const xsc_adev_name[] = {
+	[XSC_ADEV_IDX_ETH] = XSC_ETH_ADEV_NAME,
+};
+
+static void xsc_release_adev(struct device *dev)
+{
+	struct xsc_adev *xsc_adev =
+		container_of(dev, struct xsc_adev, adev.dev);
+	struct xsc_core_device *xdev = xsc_adev->xdev;
+	int idx = xsc_adev->idx;
+
+	kfree(xsc_adev);
+	xdev->xsc_adev_list[idx] = NULL;
+}
+
+static int xsc_reg_adev(struct xsc_core_device *xdev, int idx)
+{
+	struct auxiliary_device	*adev;
+	struct xsc_adev *xsc_adev;
+	int ret;
+
+	xsc_adev = kzalloc(sizeof(*xsc_adev), GFP_KERNEL);
+	if (!xsc_adev)
+		return -ENOMEM;
+
+	adev = &xsc_adev->adev;
+	adev->name = xsc_adev_name[idx];
+	adev->id = xdev->adev_id;
+	adev->dev.parent = &xdev->pdev->dev;
+	adev->dev.release = xsc_release_adev;
+	xsc_adev->xdev = xdev;
+	xsc_adev->idx = idx;
+
+	ret = auxiliary_device_init(adev);
+	if (ret) {
+		kfree(xsc_adev);
+		return ret;
+	}
+
+	ret = auxiliary_device_add(adev);
+	if (ret) {
+		auxiliary_device_uninit(adev);
+		return ret;
+	}
+
+	xdev->xsc_adev_list[idx] = xsc_adev;
+
+	return 0;
+}
+
+static void xsc_unreg_adev(struct xsc_core_device *xdev, int idx)
+{
+	struct xsc_adev *xsc_adev = xdev->xsc_adev_list[idx];
+	struct auxiliary_device *adev = &xsc_adev->adev;
+
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+}
+
+int xsc_adev_init(struct xsc_core_device *xdev)
+{
+	struct xsc_adev **xsc_adev_list;
+	int adev_id;
+	int ret;
+
+	xsc_adev_list = kcalloc(ARRAY_SIZE(xsc_adev_name),
+				sizeof(struct xsc_adev *),
+				GFP_KERNEL);
+	if (!xsc_adev_list)
+		return -ENOMEM;
+	xdev->xsc_adev_list = xsc_adev_list;
+
+	adev_id = ida_alloc(&xsc_adev_ida, GFP_KERNEL);
+	if (adev_id < 0) {
+		ret = adev_id;
+		goto err_free_adev_list;
+	}
+	xdev->adev_id = adev_id;
+
+	ret = xsc_reg_adev(xdev, XSC_ADEV_IDX_ETH);
+	if (ret)
+		goto err_dalloc_adev_id;
+
+	return 0;
+err_dalloc_adev_id:
+	ida_free(&xsc_adev_ida, xdev->adev_id);
+err_free_adev_list:
+	kfree(xsc_adev_list);
+
+	return ret;
+}
+
+void xsc_adev_uninit(struct xsc_core_device *xdev)
+{
+	xsc_unreg_adev(xdev, XSC_ADEV_IDX_ETH);
+	ida_free(&xsc_adev_ida, xdev->adev_id);
+	kfree(xdev->xsc_adev_list);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/adev.h b/drivers/net/ethernet/yunsilicon/xsc/pci/adev.h
new file mode 100644
index 0000000000000..3de4dd26f27f5
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/adev.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __ADEV_H
+#define __ADEV_H
+
+#include "common/xsc_core.h"
+
+int xsc_adev_init(struct xsc_core_device *xdev);
+void xsc_adev_uninit(struct xsc_core_device *xdev);
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
index 69f508af5572d..e1a7fd148f27e 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/main.c
@@ -10,6 +10,7 @@
 #include "cq.h"
 #include "eq.h"
 #include "pci_irq.h"
+#include "adev.h"
 
 static const struct pci_device_id xsc_pci_id_table[] = {
 	{ PCI_DEVICE(XSC_PCI_VENDOR_ID, XSC_MC_PF_DEV_ID) },
@@ -215,7 +216,15 @@ static int xsc_load(struct xsc_core_device *xdev)
 		goto err_hw_cleanup;
 	}
 
+	err = xsc_adev_init(xdev);
+	if (err) {
+		pci_err(xdev->pdev, "xsc_adev_init failed %d\n", err);
+		goto err_irq_eq_destroy;
+	}
+
 	return 0;
+err_irq_eq_destroy:
+	xsc_irq_eq_destroy(xdev);
 err_hw_cleanup:
 	xsc_hw_cleanup(xdev);
 err_out:
@@ -224,6 +233,7 @@ static int xsc_load(struct xsc_core_device *xdev)
 
 static void xsc_unload(struct xsc_core_device *xdev)
 {
+	xsc_adev_uninit(xdev);
 	xsc_irq_eq_destroy(xdev);
 	xsc_hw_cleanup(xdev);
 }

From d38f3c230844f899309d35b8589d1283750ea50a Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:09 +0800
Subject: [PATCH 2598/2753] xsc: Add ethernet interface

Implement an auxiliary driver for ethernet and initialize the
netdevice simply.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/yunsilicon/Makefile      |  1 +
 .../net/ethernet/yunsilicon/xsc/net/main.c    | 98 +++++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/net/xsc_eth.h | 16 +++
 .../yunsilicon/xsc/net/xsc_eth_common.h       | 15 +++
 4 files changed, 130 insertions(+)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/main.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h

diff --git a/drivers/net/ethernet/yunsilicon/Makefile b/drivers/net/ethernet/yunsilicon/Makefile
index 05aa35c3c8e18..86e241b015f7c 100644
--- a/drivers/net/ethernet/yunsilicon/Makefile
+++ b/drivers/net/ethernet/yunsilicon/Makefile
@@ -4,4 +4,5 @@
 # Makefile for the Yunsilicon device drivers.
 #
 
+obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc/net/
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc/pci/
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/main.c b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
new file mode 100644
index 0000000000000..f5e247864d88e
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/auxiliary_bus.h>
+
+#include "common/xsc_core.h"
+#include "xsc_eth_common.h"
+#include "xsc_eth.h"
+
+static int xsc_get_max_num_channels(struct xsc_core_device *xdev)
+{
+	return min_t(int, xdev->dev_res->eq_table.num_comp_vectors,
+		     XSC_ETH_MAX_NUM_CHANNELS);
+}
+
+static int xsc_eth_probe(struct auxiliary_device *adev,
+			 const struct auxiliary_device_id *adev_id)
+{
+	struct xsc_adev *xsc_adev = container_of(adev, struct xsc_adev, adev);
+	struct xsc_core_device *xdev = xsc_adev->xdev;
+	struct xsc_adapter *adapter;
+	struct net_device *netdev;
+	int num_chl, num_tc;
+	int err;
+
+	num_chl = xsc_get_max_num_channels(xdev);
+	num_tc = xdev->caps.max_tc;
+
+	netdev = alloc_etherdev_mqs(sizeof(struct xsc_adapter),
+				    num_chl * num_tc, num_chl);
+	if (!netdev) {
+		pr_err("alloc_etherdev_mqs failed, txq=%d, rxq=%d\n",
+		       (num_chl * num_tc), num_chl);
+		return -ENOMEM;
+	}
+
+	netdev->dev.parent = &xdev->pdev->dev;
+	adapter = netdev_priv(netdev);
+	adapter->netdev = netdev;
+	adapter->pdev = xdev->pdev;
+	adapter->dev = &adapter->pdev->dev;
+	adapter->xdev = xdev;
+	xdev->eth_priv = adapter;
+
+	err = register_netdev(netdev);
+	if (err) {
+		netdev_err(netdev, "register_netdev failed, err=%d\n", err);
+		goto err_free_netdev;
+	}
+
+	return 0;
+
+err_free_netdev:
+	free_netdev(netdev);
+
+	return err;
+}
+
+static void xsc_eth_remove(struct auxiliary_device *adev)
+{
+	struct xsc_adev *xsc_adev = container_of(adev, struct xsc_adev, adev);
+	struct xsc_core_device *xdev = xsc_adev->xdev;
+	struct xsc_adapter *adapter;
+
+	if (!xdev)
+		return;
+
+	adapter = xdev->eth_priv;
+	if (!adapter)
+		return;
+
+	unregister_netdev(adapter->netdev);
+
+	free_netdev(adapter->netdev);
+
+	xdev->eth_priv = NULL;
+}
+
+static const struct auxiliary_device_id xsc_eth_id_table[] = {
+	{ .name = XSC_PCI_DRV_NAME "." XSC_ETH_ADEV_NAME },
+	{},
+};
+MODULE_DEVICE_TABLE(auxiliary, xsc_eth_id_table);
+
+static struct auxiliary_driver xsc_eth_driver = {
+	.name = "eth",
+	.probe = xsc_eth_probe,
+	.remove = xsc_eth_remove,
+	.id_table = xsc_eth_id_table,
+};
+module_auxiliary_driver(xsc_eth_driver);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Yunsilicon XSC ethernet driver");
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
new file mode 100644
index 0000000000000..0c70c0d5912dd
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_ETH_H
+#define __XSC_ETH_H
+
+struct xsc_adapter {
+	struct net_device	*netdev;
+	struct pci_dev		*pdev;
+	struct device		*dev;
+	struct xsc_core_device	*xdev;
+};
+
+#endif /* __XSC_ETH_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
new file mode 100644
index 0000000000000..b5640f05d8947
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_ETH_COMMON_H
+#define __XSC_ETH_COMMON_H
+
+#define XSC_LOG_INDIR_RQT_SIZE		0x8
+
+#define XSC_INDIR_RQT_SIZE		BIT(XSC_LOG_INDIR_RQT_SIZE)
+#define XSC_ETH_MIN_NUM_CHANNELS	2
+#define XSC_ETH_MAX_NUM_CHANNELS	XSC_INDIR_RQT_SIZE
+
+#endif

From 9f5c4f2c8194882f3086cd128008646ccd031644 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:11 +0800
Subject: [PATCH 2599/2753] xsc: Init net device

Initialize network device:
1. Prepare xsc_eth_params, set up the network parameters such as MTU,
number of channels, and RSS configuration
2. Configure netdev, Set the MTU, features
3. Set mac addr to hardware, and attach netif

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |   1 +
 .../yunsilicon/xsc/common/xsc_device.h        |  42 +++
 .../ethernet/yunsilicon/xsc/common/xsc_pp.h   |  38 ++
 .../net/ethernet/yunsilicon/xsc/net/main.c    | 341 +++++++++++++++++-
 .../net/ethernet/yunsilicon/xsc/net/xsc_eth.h |  28 ++
 .../yunsilicon/xsc/net/xsc_eth_common.h       |  31 ++
 .../net/ethernet/yunsilicon/xsc/net/xsc_pph.h | 180 +++++++++
 .../ethernet/yunsilicon/xsc/net/xsc_queue.h   |  49 +++
 8 files changed, 709 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/common/xsc_pp.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_pph.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index e6863cb087c96..f310ca810af1b 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -8,6 +8,7 @@
 
 #include <linux/pci.h>
 #include <linux/auxiliary_bus.h>
+#include <linux/if_vlan.h>
 
 #include "common/xsc_cmdq.h"
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
new file mode 100644
index 0000000000000..45ea8d2a0e934
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_DEVICE_H
+#define __XSC_DEVICE_H
+
+enum xsc_traffic_types {
+	XSC_TT_IPV4,
+	XSC_TT_IPV4_TCP,
+	XSC_TT_IPV4_UDP,
+	XSC_TT_IPV6,
+	XSC_TT_IPV6_TCP,
+	XSC_TT_IPV6_UDP,
+	XSC_TT_IPV4_IPSEC_AH,
+	XSC_TT_IPV6_IPSEC_AH,
+	XSC_TT_IPV4_IPSEC_ESP,
+	XSC_TT_IPV6_IPSEC_ESP,
+	XSC_TT_ANY,
+	XSC_NUM_TT,
+};
+
+#define XSC_NUM_INDIR_TIRS XSC_NUM_TT
+
+enum {
+	XSC_L3_PROT_TYPE_IPV4	= BIT(0),
+	XSC_L3_PROT_TYPE_IPV6	= BIT(1),
+};
+
+enum {
+	XSC_L4_PROT_TYPE_TCP	= BIT(0),
+	XSC_L4_PROT_TYPE_UDP	= BIT(1),
+};
+
+struct xsc_tirc_config {
+	u8 l3_prot_type;
+	u8 l4_prot_type;
+	u32 rx_hash_fields;
+};
+
+#endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_pp.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_pp.h
new file mode 100644
index 0000000000000..582f99d8ca939
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_pp.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_PP_H
+#define __XSC_PP_H
+
+enum {
+	XSC_HASH_FIELD_SEL_SRC_IP	= BIT(0),
+	XSC_HASH_FIELD_SEL_PROTO	= BIT(1),
+	XSC_HASH_FIELD_SEL_DST_IP	= BIT(2),
+	XSC_HASH_FIELD_SEL_SPORT	= BIT(3),
+	XSC_HASH_FIELD_SEL_DPORT	= BIT(4),
+	XSC_HASH_FIELD_SEL_SRC_IPV6	= BIT(5),
+	XSC_HASH_FIELD_SEL_DST_IPV6	= BIT(6),
+	XSC_HASH_FIELD_SEL_SPORT_V6	= BIT(7),
+	XSC_HASH_FIELD_SEL_DPORT_V6	= BIT(8),
+};
+
+#define XSC_HASH_IP		(XSC_HASH_FIELD_SEL_SRC_IP	|\
+				XSC_HASH_FIELD_SEL_DST_IP	|\
+				XSC_HASH_FIELD_SEL_PROTO)
+#define XSC_HASH_IP_PORTS	(XSC_HASH_FIELD_SEL_SRC_IP	|\
+				XSC_HASH_FIELD_SEL_DST_IP	|\
+				XSC_HASH_FIELD_SEL_SPORT	|\
+				XSC_HASH_FIELD_SEL_DPORT	|\
+				XSC_HASH_FIELD_SEL_PROTO)
+#define XSC_HASH_IP6		(XSC_HASH_FIELD_SEL_SRC_IPV6	|\
+				XSC_HASH_FIELD_SEL_DST_IPV6	|\
+				XSC_HASH_FIELD_SEL_PROTO)
+#define XSC_HASH_IP6_PORTS	(XSC_HASH_FIELD_SEL_SRC_IPV6	|\
+				XSC_HASH_FIELD_SEL_DST_IPV6	|\
+				XSC_HASH_FIELD_SEL_SPORT_V6	|\
+				XSC_HASH_FIELD_SEL_DPORT_V6	|\
+				XSC_HASH_FIELD_SEL_PROTO)
+
+#endif /* __XSC_PP_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/main.c b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
index f5e247864d88e..cc40628f9e1a7 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
@@ -6,17 +6,339 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/auxiliary_bus.h>
+#include <linux/ethtool.h>
 
 #include "common/xsc_core.h"
+#include "common/xsc_driver.h"
+#include "common/xsc_device.h"
+#include "common/xsc_pp.h"
 #include "xsc_eth_common.h"
 #include "xsc_eth.h"
 
+static const struct xsc_tirc_config tirc_default_config[XSC_NUM_INDIR_TIRS] = {
+	[XSC_TT_IPV4] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = 0,
+				.rx_hash_fields = XSC_HASH_IP,
+	},
+	[XSC_TT_IPV4_TCP] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = XSC_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = XSC_HASH_IP_PORTS,
+	},
+	[XSC_TT_IPV4_UDP] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV4,
+				.l4_prot_type = XSC_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = XSC_HASH_IP_PORTS,
+	},
+	[XSC_TT_IPV6] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = 0,
+				.rx_hash_fields = XSC_HASH_IP6,
+	},
+	[XSC_TT_IPV6_TCP] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = XSC_L4_PROT_TYPE_TCP,
+				.rx_hash_fields = XSC_HASH_IP6_PORTS,
+	},
+	[XSC_TT_IPV6_UDP] = {
+				.l3_prot_type = XSC_L3_PROT_TYPE_IPV6,
+				.l4_prot_type = XSC_L4_PROT_TYPE_UDP,
+				.rx_hash_fields = XSC_HASH_IP6_PORTS,
+	},
+};
+
 static int xsc_get_max_num_channels(struct xsc_core_device *xdev)
 {
 	return min_t(int, xdev->dev_res->eq_table.num_comp_vectors,
 		     XSC_ETH_MAX_NUM_CHANNELS);
 }
 
+static void xsc_build_default_indir_rqt(u32 *indirection_rqt, int len,
+					int num_channels)
+{
+	int i;
+
+	for (i = 0; i < len; i++)
+		indirection_rqt[i] = i % num_channels;
+}
+
+static void xsc_build_rss_param(struct xsc_rss_params *rss_param,
+				u16 num_channels)
+{
+	enum xsc_traffic_types tt;
+
+	rss_param->hfunc = ETH_RSS_HASH_TOP;
+	netdev_rss_key_fill(rss_param->toeplitz_hash_key,
+			    sizeof(rss_param->toeplitz_hash_key));
+
+	xsc_build_default_indir_rqt(rss_param->indirection_rqt,
+				    XSC_INDIR_RQT_SIZE, num_channels);
+
+	for (tt = 0; tt < XSC_NUM_INDIR_TIRS; tt++) {
+		rss_param->rx_hash_fields[tt] =
+			tirc_default_config[tt].rx_hash_fields;
+	}
+	rss_param->rss_hash_tmpl = XSC_HASH_IP_PORTS | XSC_HASH_IP6_PORTS;
+}
+
+static void xsc_eth_build_nic_params(struct xsc_adapter *adapter,
+				     u32 ch_num, u32 tc_num)
+{
+	struct xsc_eth_params *params = &adapter->nic_param;
+	struct xsc_core_device *xdev = adapter->xdev;
+
+	params->mtu = SW_DEFAULT_MTU;
+	params->num_tc = tc_num;
+
+	params->comp_vectors = xdev->dev_res->eq_table.num_comp_vectors;
+	params->max_num_ch = ch_num;
+	params->num_channels = ch_num;
+
+	params->rq_max_size = BIT(xdev->caps.log_max_qp_depth);
+	params->sq_max_size = BIT(xdev->caps.log_max_qp_depth);
+	xsc_build_rss_param(&adapter->rss_param,
+			    adapter->nic_param.num_channels);
+}
+
+static int xsc_eth_netdev_init(struct xsc_adapter *adapter)
+{
+	unsigned int node, tc, nch;
+
+	tc = adapter->nic_param.num_tc;
+	nch = adapter->nic_param.max_num_ch;
+	node = dev_to_node(adapter->dev);
+	adapter->txq2sq = kcalloc_node(nch * tc,
+				       sizeof(*adapter->txq2sq),
+				       GFP_KERNEL, node);
+	if (!adapter->txq2sq)
+		goto err_out;
+
+	adapter->workq = create_singlethread_workqueue("xsc_eth");
+	if (!adapter->workq)
+		goto err_free_priv;
+
+	netif_carrier_off(adapter->netdev);
+
+	return 0;
+
+err_free_priv:
+	kfree(adapter->txq2sq);
+err_out:
+	return -ENOMEM;
+}
+
+static int xsc_eth_close(struct net_device *netdev)
+{
+	return 0;
+}
+
+static int xsc_eth_set_hw_mtu(struct xsc_core_device *xdev,
+			      u16 mtu, u16 rx_buf_sz)
+{
+	struct xsc_set_mtu_mbox_out out;
+	struct xsc_set_mtu_mbox_in in;
+	int ret;
+
+	memset(&in, 0, sizeof(struct xsc_set_mtu_mbox_in));
+	memset(&out, 0, sizeof(struct xsc_set_mtu_mbox_out));
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_SET_MTU);
+	in.mtu = cpu_to_be16(mtu);
+	in.rx_buf_sz_min = cpu_to_be16(rx_buf_sz);
+	in.mac_port = xdev->mac_port;
+
+	ret = xsc_cmd_exec(xdev, &in, sizeof(struct xsc_set_mtu_mbox_in), &out,
+			   sizeof(struct xsc_set_mtu_mbox_out));
+	if (ret || out.hdr.status) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "failed to set hw_mtu=%u rx_buf_sz=%u, err=%d, status=%d\n",
+			   mtu, rx_buf_sz, ret, out.hdr.status);
+		ret = -ENOEXEC;
+	}
+
+	return ret;
+}
+
+static const struct net_device_ops xsc_netdev_ops = {
+	/* TBD */
+};
+
+static void xsc_eth_build_nic_netdev(struct xsc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+
+	/* Set up network device as normal. */
+	netdev->priv_flags |= IFF_UNICAST_FLT | IFF_LIVE_ADDR_CHANGE;
+	netdev->netdev_ops = &xsc_netdev_ops;
+
+	netdev->min_mtu = SW_MIN_MTU;
+	netdev->max_mtu = SW_MAX_MTU;
+	/*mtu - macheaderlen - ipheaderlen should be aligned in 8B*/
+	netdev->mtu = SW_DEFAULT_MTU;
+
+	netdev->vlan_features |= NETIF_F_SG;
+	netdev->vlan_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+	netdev->vlan_features |= NETIF_F_GRO;
+	netdev->vlan_features |= NETIF_F_TSO;
+	netdev->vlan_features |= NETIF_F_TSO6;
+
+	netdev->vlan_features |= NETIF_F_RXCSUM;
+	netdev->vlan_features |= NETIF_F_RXHASH;
+
+	netdev->hw_features = netdev->vlan_features;
+
+	netdev->hw_enc_features |= NETIF_F_IP_CSUM;
+	netdev->hw_enc_features |= NETIF_F_IPV6_CSUM;
+	netdev->hw_enc_features |= NETIF_F_TSO;
+	netdev->hw_enc_features |= NETIF_F_TSO6;
+	netdev->hw_enc_features |= NETIF_F_GSO_PARTIAL;
+
+	netdev->hw_features		|= NETIF_F_GSO_PARTIAL;
+	netdev->hw_features		|= NETIF_F_GSO_UDP_L4;
+	netdev->features		|= netdev->hw_features;
+	netdev->gso_partial_features	|= NETIF_F_GSO_UDP_L4;
+
+	netdev->features		|= NETIF_F_HIGHDMA;
+}
+
+static int xsc_eth_nic_init(struct xsc_adapter *adapter,
+			    void *rep_priv, u32 ch_num, u32 tc_num)
+{
+	int err;
+
+	xsc_eth_build_nic_params(adapter, ch_num, tc_num);
+
+	err = xsc_eth_netdev_init(adapter);
+	if (err)
+		return err;
+
+	xsc_eth_build_nic_netdev(adapter);
+
+	return 0;
+}
+
+static void xsc_eth_nic_cleanup(struct xsc_adapter *adapter)
+{
+	destroy_workqueue(adapter->workq);
+	kfree(adapter->txq2sq);
+}
+
+static int xsc_eth_get_mac(struct xsc_core_device *xdev, char *mac)
+{
+	struct xsc_query_eth_mac_mbox_out *out;
+	struct xsc_query_eth_mac_mbox_in in;
+	int err = 0;
+
+	out = kzalloc(sizeof(*out), GFP_KERNEL);
+	if (!out)
+		return -ENOMEM;
+
+	memset(&in, 0, sizeof(in));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_ETH_MAC);
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), out, sizeof(*out));
+	if (err || out->hdr.status) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "get mac failed! err=%d, out.status=%u\n",
+			   err, out->hdr.status);
+		err = -ENOEXEC;
+		goto err_free;
+	}
+
+	memcpy(mac, out->mac, 6);
+
+err_free:
+	kfree(out);
+	return err;
+}
+
+static void xsc_eth_l2_addr_init(struct xsc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	char mac[6] = {0};
+	int ret = 0;
+
+	ret = xsc_eth_get_mac(adapter->xdev, mac);
+	if (ret) {
+		netdev_err(netdev, "get mac failed %d, generate random mac...",
+			   ret);
+		eth_random_addr(mac);
+	}
+	dev_addr_mod(netdev, 0, mac, 6);
+
+	if (!is_valid_ether_addr(netdev->perm_addr))
+		memcpy(netdev->perm_addr, netdev->dev_addr, netdev->addr_len);
+}
+
+static int xsc_eth_nic_enable(struct xsc_adapter *adapter)
+{
+	struct xsc_core_device *xdev = adapter->xdev;
+
+	xsc_eth_l2_addr_init(adapter);
+
+	xsc_eth_set_hw_mtu(xdev, XSC_SW2HW_MTU(adapter->nic_param.mtu),
+			   XSC_SW2HW_RX_PKT_LEN(adapter->nic_param.mtu));
+
+	rtnl_lock();
+	netif_device_attach(adapter->netdev);
+	rtnl_unlock();
+
+	return 0;
+}
+
+static void xsc_eth_nic_disable(struct xsc_adapter *adapter)
+{
+	rtnl_lock();
+	if (netif_running(adapter->netdev))
+		xsc_eth_close(adapter->netdev);
+	netif_device_detach(adapter->netdev);
+	rtnl_unlock();
+}
+
+static int xsc_attach_netdev(struct xsc_adapter *adapter)
+{
+	int err = -1;
+
+	err = xsc_eth_nic_enable(adapter);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void xsc_detach_netdev(struct xsc_adapter *adapter)
+{
+	xsc_eth_nic_disable(adapter);
+
+	flush_workqueue(adapter->workq);
+	adapter->status = XSCALE_ETH_DRIVER_DETACH;
+}
+
+static int xsc_eth_attach(struct xsc_core_device *xdev,
+			  struct xsc_adapter *adapter)
+{
+	int err = -1;
+
+	if (netif_device_present(adapter->netdev))
+		return 0;
+
+	err = xsc_attach_netdev(adapter);
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static void xsc_eth_detach(struct xsc_core_device *xdev,
+			   struct xsc_adapter *adapter)
+{
+	if (!netif_device_present(adapter->netdev))
+		return;
+
+	xsc_detach_netdev(adapter);
+}
+
 static int xsc_eth_probe(struct auxiliary_device *adev,
 			 const struct auxiliary_device_id *adev_id)
 {
@@ -24,6 +346,7 @@ static int xsc_eth_probe(struct auxiliary_device *adev,
 	struct xsc_core_device *xdev = xsc_adev->xdev;
 	struct xsc_adapter *adapter;
 	struct net_device *netdev;
+	void *rep_priv = NULL;
 	int num_chl, num_tc;
 	int err;
 
@@ -46,14 +369,30 @@ static int xsc_eth_probe(struct auxiliary_device *adev,
 	adapter->xdev = xdev;
 	xdev->eth_priv = adapter;
 
+	err = xsc_eth_nic_init(adapter, rep_priv, num_chl, num_tc);
+	if (err) {
+		netdev_err(netdev, "xsc_eth_nic_init failed, err=%d\n", err);
+		goto err_free_netdev;
+	}
+
+	err = xsc_eth_attach(xdev, adapter);
+	if (err) {
+		netdev_err(netdev, "xsc_eth_attach failed, err=%d\n", err);
+		goto err_nic_cleanup;
+	}
+
 	err = register_netdev(netdev);
 	if (err) {
 		netdev_err(netdev, "register_netdev failed, err=%d\n", err);
-		goto err_free_netdev;
+		goto err_detach;
 	}
 
 	return 0;
 
+err_detach:
+	xsc_eth_detach(xdev, adapter);
+err_nic_cleanup:
+	xsc_eth_nic_cleanup(adapter);
 err_free_netdev:
 	free_netdev(netdev);
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
index 0c70c0d5912dd..f5c1e3ead5402 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
@@ -6,11 +6,39 @@
 #ifndef __XSC_ETH_H
 #define __XSC_ETH_H
 
+#include "common/xsc_device.h"
+#include "xsc_eth_common.h"
+
+enum {
+	XSCALE_ETH_DRIVER_INIT,
+	XSCALE_ETH_DRIVER_OK,
+	XSCALE_ETH_DRIVER_CLOSE,
+	XSCALE_ETH_DRIVER_DETACH,
+};
+
+struct xsc_rss_params {
+	u32	indirection_rqt[XSC_INDIR_RQT_SIZE];
+	u32	rx_hash_fields[XSC_NUM_INDIR_TIRS];
+	u8	toeplitz_hash_key[52];
+	u8	hfunc;
+	u32	rss_hash_tmpl;
+};
+
 struct xsc_adapter {
 	struct net_device	*netdev;
 	struct pci_dev		*pdev;
 	struct device		*dev;
 	struct xsc_core_device	*xdev;
+
+	struct xsc_eth_params	nic_param;
+	struct xsc_rss_params	rss_param;
+
+	struct workqueue_struct	*workq;
+
+	struct xsc_sq		**txq2sq;
+
+	u32			status;
+	struct mutex		status_lock; /*protect status */
 };
 
 #endif /* __XSC_ETH_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
index b5640f05d8947..da17c16ad92e3 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
@@ -6,10 +6,41 @@
 #ifndef __XSC_ETH_COMMON_H
 #define __XSC_ETH_COMMON_H
 
+#include "xsc_pph.h"
+
+#define SW_MIN_MTU		ETH_MIN_MTU
+#define SW_DEFAULT_MTU		ETH_DATA_LEN
+#define SW_MAX_MTU		9600
+
+#define XSC_ETH_HW_MTU_SEND	9800
+#define XSC_ETH_HW_MTU_RECV	9800
+#define XSC_ETH_HARD_MTU	(ETH_HLEN + VLAN_HLEN * 2 + ETH_FCS_LEN)
+#define XSC_SW2HW_MTU(mtu)	((mtu) + XSC_ETH_HARD_MTU)
+#define XSC_SW2HW_FRAG_SIZE(mtu)	((mtu) + XSC_ETH_HARD_MTU)
+#define XSC_ETH_RX_MAX_HEAD_ROOM	256
+#define XSC_SW2HW_RX_PKT_LEN(mtu)	\
+	((mtu) + ETH_HLEN + XSC_ETH_RX_MAX_HEAD_ROOM)
+
 #define XSC_LOG_INDIR_RQT_SIZE		0x8
 
 #define XSC_INDIR_RQT_SIZE		BIT(XSC_LOG_INDIR_RQT_SIZE)
 #define XSC_ETH_MIN_NUM_CHANNELS	2
 #define XSC_ETH_MAX_NUM_CHANNELS	XSC_INDIR_RQT_SIZE
 
+struct xsc_eth_params {
+	u16	num_channels;
+	u16	max_num_ch;
+	u8	num_tc;
+	u32	mtu;
+	u32	hard_mtu;
+	u32	comp_vectors;
+	u32	sq_size;
+	u32	sq_max_size;
+	u8	rq_wq_type;
+	u32	rq_size;
+	u32	rq_max_size;
+	u32	rq_frags_size;
+	u32	pflags;
+};
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_pph.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_pph.h
new file mode 100644
index 0000000000000..34f1200e8bb58
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_pph.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_PPH_H
+#define __XSC_PPH_H
+
+#define XSC_PPH_HEAD_LEN	64
+
+enum {
+	L4_PROTO_NONE	= 0,
+	L4_PROTO_TCP	= 1,
+	L4_PROTO_UDP	= 2,
+	L4_PROTO_ICMP	= 3,
+	L4_PROTO_GRE	= 4,
+};
+
+enum {
+	L3_PROTO_NONE	= 0,
+	L3_PROTO_IP	= 2,
+	L3_PROTO_IP6	= 3,
+};
+
+struct epp_pph {
+	u16 outer_eth_type;
+	u16 inner_eth_type;
+
+	u16 rsv1:1;
+	u16 outer_vlan_flag:2;
+	u16 outer_ip_type:2;
+	u16 outer_ip_ofst:5;
+	u16 outer_ip_len:6;
+
+	u16 rsv2:1;
+	u16 outer_tp_type:3;
+	u16 outer_tp_csum_flag:1;
+	u16 outer_tp_ofst:7;
+	u16 ext_tunnel_type:4;
+
+	u8 tunnel_ofst;
+	u8 inner_mac_ofst;
+
+	u32 rsv3:2;
+	u32 inner_mac_flag:1;
+	u32 inner_vlan_flag:2;
+	u32 inner_ip_type:2;
+	u32 inner_ip_ofst:8;
+	u32 inner_ip_len:6;
+	u32 inner_tp_type:2;
+	u32 inner_tp_csum_flag:1;
+	u32 inner_tp_ofst:8;
+
+	u16 rsv4:1;
+	u16 payload_type:4;
+	u16 payload_ofst:8;
+	u16 pkt_type:3;
+
+	u16 rsv5:2;
+	u16 pri:3;
+	u16 logical_in_port:11;
+	u16 vlan_info;
+	u8 error_bitmap:8;
+
+	u8 rsv6:7;
+	u8 recirc_id_vld:1;
+	u16 recirc_id;
+
+	u8 rsv7:7;
+	u8 recirc_data_vld:1;
+	u32 recirc_data;
+
+	u8 rsv8:6;
+	u8 mark_tag_vld:2;
+	u16 mark_tag;
+
+	u8 rsv9:4;
+	u8 upa_to_soc:1;
+	u8 upa_from_soc:1;
+	u8 upa_re_up_call:1;
+	u8 upa_pkt_drop:1;
+
+	u8 ucdv;
+	u16 rsv10:2;
+	u16 pkt_len:14;
+
+	u16 rsv11:2;
+	u16 pkt_hdr_ptr:14;
+
+	u64	 rsv12:5;
+	u64	 csum_ofst:8;
+	u64	 csum_val:29;
+	u64	 csum_plen:14;
+	u64	 rsv11_0:8;
+
+	u64	 rsv11_1;
+	u64	 rsv11_2;
+	u16 rsv11_3;
+};
+
+#define OUTER_L3_BIT	BIT(3)
+#define OUTER_L4_BIT	BIT(2)
+#define INNER_L3_BIT	BIT(1)
+#define INNER_L4_BIT	BIT(0)
+#define OUTER_BIT		(OUTER_L3_BIT | OUTER_L4_BIT)
+#define INNER_BIT		(INNER_L3_BIT | INNER_L4_BIT)
+#define OUTER_AND_INNER	(OUTER_BIT | INNER_BIT)
+
+#define PACKET_UNKNOWN	BIT(4)
+
+#define EPP2SOC_PPH_EXT_TUNNEL_TYPE_OFFSET (6UL)
+#define EPP2SOC_PPH_EXT_TUNNEL_TYPE_BIT_MASK (0XF00)
+#define EPP2SOC_PPH_EXT_TUNNEL_TYPE_BIT_OFFSET (8)
+
+#define EPP2SOC_PPH_EXT_ERROR_BITMAP_OFFSET (20UL)
+#define EPP2SOC_PPH_EXT_ERROR_BITMAP_BIT_MASK (0XFF)
+#define EPP2SOC_PPH_EXT_ERROR_BITMAP_BIT_OFFSET (0)
+
+#define XSC_GET_EPP2SOC_PPH_EXT_TUNNEL_TYPE(PPH_BASE_ADDR)	\
+	((*(u16 *)((u8 *)(PPH_BASE_ADDR) +	\
+	EPP2SOC_PPH_EXT_TUNNEL_TYPE_OFFSET) &	\
+	EPP2SOC_PPH_EXT_TUNNEL_TYPE_BIT_MASK) >>	\
+	EPP2SOC_PPH_EXT_TUNNEL_TYPE_BIT_OFFSET)
+
+#define XSC_GET_EPP2SOC_PPH_ERROR_BITMAP(PPH_BASE_ADDR)	\
+	((*(u8 *)((u8 *)(PPH_BASE_ADDR) +	\
+	EPP2SOC_PPH_EXT_ERROR_BITMAP_OFFSET) &	\
+	EPP2SOC_PPH_EXT_ERROR_BITMAP_BIT_MASK) >>	\
+	EPP2SOC_PPH_EXT_ERROR_BITMAP_BIT_OFFSET)
+
+#define PPH_OUTER_IP_TYPE_OFF		(4UL)
+#define PPH_OUTER_IP_TYPE_MASK		(0x3)
+#define PPH_OUTER_IP_TYPE_SHIFT		(11)
+#define PPH_OUTER_IP_TYPE(base)		\
+	((ntohs(*(u16 *)((u8 *)(base) + PPH_OUTER_IP_TYPE_OFF)) >>	\
+	PPH_OUTER_IP_TYPE_SHIFT) & PPH_OUTER_IP_TYPE_MASK)
+
+#define PPH_OUTER_IP_OFST_OFF		(4UL)
+#define PPH_OUTER_IP_OFST_MASK		(0x1f)
+#define PPH_OUTER_IP_OFST_SHIFT		(6)
+#define PPH_OUTER_IP_OFST(base)			\
+	((ntohs(*(u16 *)((u8 *)(base) + PPH_OUTER_IP_OFST_OFF)) >>	\
+	PPH_OUTER_IP_OFST_SHIFT) & PPH_OUTER_IP_OFST_MASK)
+
+#define PPH_OUTER_IP_LEN_OFF		(4UL)
+#define PPH_OUTER_IP_LEN_MASK		(0x3f)
+#define PPH_OUTER_IP_LEN_SHIFT		(0)
+#define PPH_OUTER_IP_LEN(base)		\
+	((ntohs(*(u16 *)((u8 *)(base) + PPH_OUTER_IP_LEN_OFF)) >>	\
+	PPH_OUTER_IP_LEN_SHIFT) & PPH_OUTER_IP_LEN_MASK)
+
+#define PPH_OUTER_TP_TYPE_OFF		(6UL)
+#define PPH_OUTER_TP_TYPE_MASK		(0x7)
+#define PPH_OUTER_TP_TYPE_SHIFT		(12)
+#define PPH_OUTER_TP_TYPE(base)		\
+	((ntohs(*(u16 *)((u8 *)(base) + PPH_OUTER_TP_TYPE_OFF)) >>	\
+	PPH_OUTER_TP_TYPE_SHIFT) & PPH_OUTER_TP_TYPE_MASK)
+
+#define PPH_PAYLOAD_OFST_OFF		(14UL)
+#define PPH_PAYLOAD_OFST_MASK		(0xff)
+#define PPH_PAYLOAD_OFST_SHIFT		(3)
+#define PPH_PAYLOAD_OFST(base)		\
+	((ntohs(*(u16 *)((u8 *)(base) + PPH_PAYLOAD_OFST_OFF)) >>	\
+	PPH_PAYLOAD_OFST_SHIFT) & PPH_PAYLOAD_OFST_MASK)
+
+#define PPH_CSUM_OFST_OFF		(38UL)
+#define PPH_CSUM_OFST_MASK		(0xff)
+#define PPH_CSUM_OFST_SHIFT		(51)
+#define PPH_CSUM_OFST(base)		\
+	((be64_to_cpu(*(u64 *)((u8 *)(base) + PPH_CSUM_OFST_OFF)) >>	\
+	PPH_CSUM_OFST_SHIFT) & PPH_CSUM_OFST_MASK)
+
+#define PPH_CSUM_VAL_OFF		(38UL)
+#define PPH_CSUM_VAL_MASK		(0xeffffff)
+#define PPH_CSUM_VAL_SHIFT		(22)
+#define PPH_CSUM_VAL(base)		\
+	((be64_to_cpu(*(u64 *)((u8 *)(base) + PPH_CSUM_VAL_OFF)) >>	\
+	PPH_CSUM_VAL_SHIFT) & PPH_CSUM_VAL_MASK)
+#endif /* __XSC_TBM_H */
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
new file mode 100644
index 0000000000000..223d4873dd169
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved.
+ */
+
+#ifndef __XSC_QUEUE_H
+#define __XSC_QUEUE_H
+
+#include "common/xsc_core.h"
+
+struct xsc_sq {
+	struct xsc_core_qp		cqp;
+	/* dirtied @completion */
+	u16                        cc;
+	u32                        dma_fifo_cc;
+
+	/* dirtied @xmit */
+	u16                        pc ____cacheline_aligned_in_smp;
+	u32                        dma_fifo_pc;
+
+	struct xsc_cq            cq;
+
+	/* read only */
+	struct xsc_wq_cyc         wq;
+	u32                        dma_fifo_mask;
+	struct {
+		struct xsc_sq_dma         *dma_fifo;
+		struct xsc_tx_wqe_info    *wqe_info;
+	} db;
+	void __iomem              *uar_map;
+	struct netdev_queue       *txq;
+	u32                        sqn;
+	u16                        stop_room;
+
+	__be32                     mkey_be;
+	unsigned long              state;
+	unsigned int               hw_mtu;
+
+	/* control path */
+	struct xsc_wq_ctrl        wq_ctrl;
+	struct xsc_channel         *channel;
+	int                        ch_ix;
+	int                        txq_ix;
+	struct work_struct         recover_work;
+} ____cacheline_aligned_in_smp;
+
+#endif /* __XSC_QUEUE_H */

From c788bc053f0d52d54fc9e557c4dec8b5587ade81 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:14 +0800
Subject: [PATCH 2600/2753] xsc: Add eth needed qp and cq apis

1. For Ethernet data transmission and reception, this patch adds
APIs for using QP and CQ. For QPs, it includes Create QP, Modify QP
Status, and Destroy QP. For CQs, it includes Create CQ and Destroy
CQ. Since these operations are common to both Ethernet and RDMA,
they are added to the xsc_pci driver. In the xsc_eth driver,
Ethernet-specific operations are added, including create RSS RQ and
modify QP.

2. Ethernet QP and CQ ring buffer allocation functions are added:
xsc_eth_cqwq_create for CQ and xsc_eth_wq_cyc_create for QP.
Corresponding DMA buffer allocation functions are also added
in alloc.c.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |  27 +++
 .../net/ethernet/yunsilicon/xsc/net/Makefile  |   2 +-
 .../ethernet/yunsilicon/xsc/net/xsc_eth_wq.c  |  80 ++++++++
 .../ethernet/yunsilicon/xsc/net/xsc_eth_wq.h  | 187 ++++++++++++++++++
 .../net/ethernet/yunsilicon/xsc/pci/alloc.c   | 104 ++++++++++
 drivers/net/ethernet/yunsilicon/xsc/pci/cq.c  | 116 +++++++++++
 drivers/net/ethernet/yunsilicon/xsc/pci/qp.c  | 114 +++++++++++
 7 files changed, 629 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index f310ca810af1b..f9534993f8fb9 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -401,9 +401,36 @@ int xsc_core_create_resource_common(struct xsc_core_device *xdev,
 				    struct xsc_core_qp *qp);
 void xsc_core_destroy_resource_common(struct xsc_core_device *xdev,
 				      struct xsc_core_qp *qp);
+int xsc_core_eth_create_qp(struct xsc_core_device *xdev,
+			   struct xsc_create_qp_mbox_in *in,
+			   int insize, u32 *p_qpn);
+int xsc_core_eth_modify_qp_status(struct xsc_core_device *xdev,
+				  u32 qpn, u16 status);
+int xsc_core_eth_destroy_qp(struct xsc_core_device *xdev, u32 qpn);
+int xsc_core_eth_create_rss_qp_rqs(struct xsc_core_device *xdev,
+				   struct xsc_create_multiqp_mbox_in *in,
+				   int insize,
+				   u32 *p_qpn_base);
+int xsc_core_eth_modify_raw_qp(struct xsc_core_device *xdev,
+			       struct xsc_modify_raw_qp_mbox_in *in);
+int xsc_core_eth_create_cq(struct xsc_core_device *xdev,
+			   struct xsc_core_cq *xcq,
+			   struct xsc_create_cq_mbox_in *in,
+			   int insize);
+int xsc_core_eth_destroy_cq(struct xsc_core_device *xdev,
+			    struct xsc_core_cq *xcq);
+
 struct xsc_eq *xsc_core_eq_get(struct xsc_core_device *xdev, int i);
 int xsc_core_vector2eqn(struct xsc_core_device *xdev, int vector, u32 *eqn,
 			unsigned int *irqn);
+void xsc_core_fill_page_frag_array(struct xsc_frag_buf *buf,
+				   __be64 *pas, unsigned int npages);
+int xsc_core_frag_buf_alloc_node(struct xsc_core_device *xdev,
+				 unsigned long size,
+				 struct xsc_frag_buf *buf,
+				 int node);
+void xsc_core_frag_buf_free(struct xsc_core_device *xdev,
+			    struct xsc_frag_buf *buf);
 
 static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
 {
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
index 53300be3c78e9..ccbc5a26d4395 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc_eth.o
 
-xsc_eth-y := main.o
+xsc_eth-y := main.o xsc_eth_wq.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.c
new file mode 100644
index 0000000000000..20895b3638ec8
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.c
@@ -0,0 +1,80 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd. All
+ * rights reserved.
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ */
+
+#include "xsc_eth_wq.h"
+#include "xsc_eth.h"
+
+u32 xsc_wq_cyc_get_size(struct xsc_wq_cyc *wq)
+{
+	return (u32)wq->fbc.sz_m1 + 1;
+}
+
+static u32 wq_get_byte_sz(u8 log_sz, u8 log_stride)
+{
+	return ((u32)1 << log_sz) << log_stride;
+}
+
+int xsc_eth_cqwq_create(struct xsc_core_device *xdev,
+			struct xsc_wq_param *param,
+			u8 q_log_size,
+			u8 ele_log_size,
+			struct xsc_cqwq *wq,
+			struct xsc_wq_ctrl *wq_ctrl)
+{
+	u8 log_wq_stride = ele_log_size;
+	u8 log_wq_sz     = q_log_size;
+	int err;
+
+	err = xsc_core_frag_buf_alloc_node(xdev,
+					   wq_get_byte_sz(log_wq_sz,
+							  log_wq_stride),
+					   &wq_ctrl->buf,
+					   param->buf_numa_node);
+	if (err) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "xsc_core_frag_buf_alloc_node failed, %d\n", err);
+		return err;
+	}
+
+	xsc_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, &wq->fbc);
+	wq_ctrl->xdev = xdev;
+	return 0;
+}
+
+int xsc_eth_wq_cyc_create(struct xsc_core_device *xdev,
+			  struct xsc_wq_param *param,
+			  u8 q_log_size,
+			  u8 ele_log_size,
+			  struct xsc_wq_cyc *wq,
+			  struct xsc_wq_ctrl *wq_ctrl)
+{
+	struct xsc_frag_buf_ctrl *fbc = &wq->fbc;
+	u8 log_wq_stride = ele_log_size;
+	u8 log_wq_sz = q_log_size;
+	int err;
+
+	err = xsc_core_frag_buf_alloc_node(xdev,
+					   wq_get_byte_sz(log_wq_sz,
+							  log_wq_stride),
+					   &wq_ctrl->buf,
+					   param->buf_numa_node);
+	if (err) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "xsc_core_frag_buf_alloc_node failed, %d\n", err);
+		return err;
+	}
+
+	xsc_init_fbc(wq_ctrl->buf.frags, log_wq_stride, log_wq_sz, fbc);
+	wq->sz = xsc_wq_cyc_get_size(wq);
+	wq_ctrl->xdev = xdev;
+	return 0;
+}
+
+void xsc_eth_wq_destroy(struct xsc_wq_ctrl *wq_ctrl)
+{
+	xsc_core_frag_buf_free(wq_ctrl->xdev, &wq_ctrl->buf);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.h
new file mode 100644
index 0000000000000..5abe155c09ba0
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_wq.h
@@ -0,0 +1,187 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd. All
+ * rights reserved.
+ * Copyright (c) 2013-2015, Mellanox Technologies, Ltd.  All rights reserved.
+ */
+
+#ifndef __XSC_WQ_H
+#define __XSC_WQ_H
+
+#include "common/xsc_core.h"
+
+struct xsc_wq_param {
+	int		buf_numa_node;
+	int		db_numa_node;
+};
+
+struct xsc_wq_ctrl {
+	struct xsc_core_device	*xdev;
+	struct xsc_frag_buf	buf;
+};
+
+struct xsc_wq_cyc {
+	struct xsc_frag_buf_ctrl fbc;
+	u16			sz;
+	u16			wqe_ctr;
+	u16			cur_sz;
+};
+
+struct xsc_cqwq {
+	struct xsc_frag_buf_ctrl fbc;
+	__be32			  *db;
+	u32			  cc; /* consumer counter */
+};
+
+enum xsc_res_type {
+	XSC_RES_UND	= 0,
+	XSC_RES_RQ,
+	XSC_RES_SQ,
+	XSC_RES_MAX,
+};
+
+u32 xsc_wq_cyc_get_size(struct xsc_wq_cyc *wq);
+
+/*api for eth driver*/
+int xsc_eth_cqwq_create(struct xsc_core_device *xdev,
+			struct xsc_wq_param *param,
+			u8 q_log_size,
+			u8 ele_log_size,
+			struct xsc_cqwq *wq,
+			struct xsc_wq_ctrl *wq_ctrl);
+
+int xsc_eth_wq_cyc_create(struct xsc_core_device *xdev,
+			  struct xsc_wq_param *param,
+			  u8 q_log_size,
+			  u8 ele_log_size,
+			  struct xsc_wq_cyc *wq,
+			  struct xsc_wq_ctrl *wq_ctrl);
+void xsc_eth_wq_destroy(struct xsc_wq_ctrl *wq_ctrl);
+
+static inline void xsc_init_fbc_offset(struct xsc_buf_list *frags,
+				       u8 log_stride, u8 log_sz,
+				       u16 strides_offset,
+				       struct xsc_frag_buf_ctrl *fbc)
+{
+	fbc->frags      = frags;
+	fbc->log_stride = log_stride;
+	fbc->log_sz     = log_sz;
+	fbc->sz_m1	= (1 << fbc->log_sz) - 1;
+	fbc->log_frag_strides = PAGE_SHIFT - fbc->log_stride;
+	fbc->frag_sz_m1	= (1 << fbc->log_frag_strides) - 1;
+	fbc->strides_offset = strides_offset;
+}
+
+static inline void xsc_init_fbc(struct xsc_buf_list *frags,
+				u8 log_stride, u8 log_sz,
+				struct xsc_frag_buf_ctrl *fbc)
+{
+	xsc_init_fbc_offset(frags, log_stride, log_sz, 0, fbc);
+}
+
+static inline void *xsc_frag_buf_get_wqe(struct xsc_frag_buf_ctrl *fbc,
+					 u32 ix)
+{
+	unsigned int frag;
+
+	ix  += fbc->strides_offset;
+	frag = ix >> fbc->log_frag_strides;
+
+	return fbc->frags[frag].buf +
+		((fbc->frag_sz_m1 & ix) << fbc->log_stride);
+}
+
+static inline u32
+xsc_frag_buf_get_idx_last_contig_stride(struct xsc_frag_buf_ctrl *fbc, u32 ix)
+{
+	u32 last_frag_stride_idx = (ix + fbc->strides_offset) | fbc->frag_sz_m1;
+
+	return min_t(u32, last_frag_stride_idx - fbc->strides_offset,
+		     fbc->sz_m1);
+}
+
+static inline int xsc_wq_cyc_missing(struct xsc_wq_cyc *wq)
+{
+	return wq->sz - wq->cur_sz;
+}
+
+static inline int xsc_wq_cyc_is_empty(struct xsc_wq_cyc *wq)
+{
+	return !wq->cur_sz;
+}
+
+static inline void xsc_wq_cyc_push(struct xsc_wq_cyc *wq)
+{
+	wq->wqe_ctr++;
+	wq->cur_sz++;
+}
+
+static inline void xsc_wq_cyc_push_n(struct xsc_wq_cyc *wq, u8 n)
+{
+	wq->wqe_ctr += n;
+	wq->cur_sz += n;
+}
+
+static inline void xsc_wq_cyc_pop(struct xsc_wq_cyc *wq)
+{
+	wq->cur_sz--;
+}
+
+static inline u16 xsc_wq_cyc_ctr2ix(struct xsc_wq_cyc *wq, u16 ctr)
+{
+	return ctr & wq->fbc.sz_m1;
+}
+
+static inline u16 xsc_wq_cyc_get_head(struct xsc_wq_cyc *wq)
+{
+	return xsc_wq_cyc_ctr2ix(wq, wq->wqe_ctr);
+}
+
+static inline u16 xsc_wq_cyc_get_tail(struct xsc_wq_cyc *wq)
+{
+	return xsc_wq_cyc_ctr2ix(wq, wq->wqe_ctr - wq->cur_sz);
+}
+
+static inline void *xsc_wq_cyc_get_wqe(struct xsc_wq_cyc *wq, u16 ix)
+{
+	return xsc_frag_buf_get_wqe(&wq->fbc, ix);
+}
+
+static inline u32 xsc_cqwq_ctr2ix(struct xsc_cqwq *wq, u32 ctr)
+{
+	return ctr & wq->fbc.sz_m1;
+}
+
+static inline u32 xsc_cqwq_get_ci(struct xsc_cqwq *wq)
+{
+	return xsc_cqwq_ctr2ix(wq, wq->cc);
+}
+
+static inline u32 xsc_cqwq_get_ctr_wrap_cnt(struct xsc_cqwq *wq, u32 ctr)
+{
+	return ctr >> wq->fbc.log_sz;
+}
+
+static inline u32 xsc_cqwq_get_wrap_cnt(struct xsc_cqwq *wq)
+{
+	return xsc_cqwq_get_ctr_wrap_cnt(wq, wq->cc);
+}
+
+static inline void xsc_cqwq_pop(struct xsc_cqwq *wq)
+{
+	wq->cc++;
+}
+
+static inline u32 xsc_cqwq_get_size(struct xsc_cqwq *wq)
+{
+	return wq->fbc.sz_m1 + 1;
+}
+
+static inline struct xsc_cqe *xsc_cqwq_get_wqe(struct xsc_cqwq *wq, u32 ix)
+{
+	struct xsc_cqe *cqe = xsc_frag_buf_get_wqe(&wq->fbc, ix);
+
+	return cqe;
+}
+
+#endif /* __XSC_WQ_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
index 4c561d9fa6b64..eeb6846541d16 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/alloc.c
@@ -128,3 +128,107 @@ void xsc_fill_page_array(struct xsc_buf *buf, __be64 *pas, unsigned int npages)
 		pas[i] = cpu_to_be64(addr);
 	}
 }
+
+void xsc_core_fill_page_frag_array(struct xsc_frag_buf *buf,
+				   __be64 *pas,
+				   unsigned int npages)
+{
+	int i;
+	dma_addr_t addr;
+	unsigned int shift = PAGE_SHIFT - PAGE_SHIFT_4K;
+	unsigned int mask = (1 << shift) - 1;
+
+	for (i = 0; i < npages; i++) {
+		addr = buf->frags[i >> shift].map +
+			((i & mask) << PAGE_SHIFT_4K);
+		pas[i] = cpu_to_be64(addr);
+	}
+}
+EXPORT_SYMBOL(xsc_core_fill_page_frag_array);
+
+static void *xsc_dma_zalloc_coherent_node(struct xsc_core_device *xdev,
+					  size_t size, dma_addr_t *dma_handle,
+					  int node)
+{
+	struct xsc_dev_resource *dev_res = xdev->dev_res;
+	struct device *device = &xdev->pdev->dev;
+	int original_node;
+	void *cpu_handle;
+
+	/* WA for kernels that don't use numa_mem_id in alloc_pages_node */
+	if (node == NUMA_NO_NODE)
+		node = numa_mem_id();
+
+	mutex_lock(&dev_res->alloc_mutex);
+	original_node = dev_to_node(device);
+	set_dev_node(device, node);
+	cpu_handle = dma_alloc_coherent(device, size, dma_handle,
+					GFP_KERNEL);
+	set_dev_node(device, original_node);
+	mutex_unlock(&dev_res->alloc_mutex);
+	return cpu_handle;
+}
+
+int xsc_core_frag_buf_alloc_node(struct xsc_core_device *xdev,
+				 unsigned long size,
+				 struct xsc_frag_buf *buf,
+				 int node)
+{
+	int i;
+
+	buf->size = size;
+	buf->npages = DIV_ROUND_UP(size, PAGE_SIZE);
+	buf->page_shift = PAGE_SHIFT;
+	buf->frags = kcalloc(buf->npages, sizeof(struct xsc_buf_list),
+			     GFP_KERNEL);
+	if (!buf->frags)
+		goto err_out;
+
+	for (i = 0; i < buf->npages; i++) {
+		unsigned long frag_sz = min_t(unsigned long, size, PAGE_SIZE);
+		struct xsc_buf_list *frag = &buf->frags[i];
+
+		frag->buf = xsc_dma_zalloc_coherent_node(xdev, frag_sz,
+							 &frag->map, node);
+		if (!frag->buf)
+			goto err_free_buf;
+		if (frag->map & ((1 << buf->page_shift) - 1)) {
+			dma_free_coherent(&xdev->pdev->dev, frag_sz,
+					  buf->frags[i].buf, buf->frags[i].map);
+			pci_err(xdev->pdev, "unexpected map alignment: %pad, page_shift=%d\n",
+				&frag->map, buf->page_shift);
+			goto err_free_buf;
+		}
+		size -= frag_sz;
+	}
+
+	return 0;
+
+err_free_buf:
+	while (i--)
+		dma_free_coherent(&xdev->pdev->dev,
+				  PAGE_SIZE,
+				  buf->frags[i].buf,
+				  buf->frags[i].map);
+	kfree(buf->frags);
+err_out:
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(xsc_core_frag_buf_alloc_node);
+
+void xsc_core_frag_buf_free(struct xsc_core_device *xdev,
+			    struct xsc_frag_buf *buf)
+{
+	unsigned long size = buf->size;
+	int i;
+
+	for (i = 0; i < buf->npages; i++) {
+		unsigned long frag_sz = min_t(unsigned long, size, PAGE_SIZE);
+
+		dma_free_coherent(&xdev->pdev->dev, frag_sz, buf->frags[i].buf,
+				  buf->frags[i].map);
+		size -= frag_sz;
+	}
+	kfree(buf->frags);
+}
+EXPORT_SYMBOL(xsc_core_frag_buf_free);
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
index 5cff9025cfc79..493d846cf8af5 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/cq.c
@@ -4,6 +4,7 @@
  */
 
 #include "common/xsc_core.h"
+#include "common/xsc_driver.h"
 #include "cq.h"
 
 void xsc_cq_event(struct xsc_core_device *xdev, u32 cqn, int event_type)
@@ -37,3 +38,118 @@ void xsc_init_cq_table(struct xsc_core_device *xdev)
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 }
+
+static int xsc_create_cq(struct xsc_core_device *xdev, u32 *p_cqn,
+			 struct xsc_create_cq_mbox_in *in, int insize)
+{
+	struct xsc_create_cq_mbox_out out;
+	int ret;
+
+	memset(&out, 0, sizeof(out));
+	in->hdr.opcode = cpu_to_be16(XSC_CMD_OP_CREATE_CQ);
+	ret = xsc_cmd_exec(xdev, in, insize, &out, sizeof(out));
+	if (ret || out.hdr.status) {
+		pci_err(xdev->pdev, "failed to create cq, err=%d out.status=%u\n",
+			ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	*p_cqn = be32_to_cpu(out.cqn) & 0xffffff;
+	return 0;
+}
+
+static int xsc_destroy_cq(struct xsc_core_device *xdev, u32 cqn)
+{
+	struct xsc_destroy_cq_mbox_out out;
+	struct xsc_destroy_cq_mbox_in in;
+	int ret;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_DESTROY_CQ);
+	in.cqn = cpu_to_be32(cqn);
+	ret = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (ret || out.hdr.status) {
+		pci_err(xdev->pdev, "failed to destroy cq, err=%d out.status=%u\n",
+			ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+
+int xsc_core_eth_create_cq(struct xsc_core_device *xdev,
+			   struct xsc_core_cq *xcq,
+			   struct xsc_create_cq_mbox_in *in,
+			   int insize)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+	u32 cqn;
+	int ret;
+	int err;
+
+	ret = xsc_create_cq(xdev, &cqn, in, insize);
+	if (ret) {
+		pci_err(xdev->pdev, "xsc_create_cq failed\n");
+		return -ENOEXEC;
+	}
+	xcq->cqn = cqn;
+	xcq->cons_index = 0;
+	xcq->arm_sn = 0;
+	atomic_set(&xcq->refcount, 1);
+	init_completion(&xcq->free);
+
+	spin_lock_irq(&table->lock);
+	ret = radix_tree_insert(&table->tree, xcq->cqn, xcq);
+	spin_unlock_irq(&table->lock);
+	if (ret)
+		goto err_insert_cq;
+	return 0;
+err_insert_cq:
+	err = xsc_destroy_cq(xdev, cqn);
+	if (err)
+		pci_err(xdev->pdev, "failed to destroy cqn=%d, err=%d\n",
+			xcq->cqn, err);
+	return ret;
+}
+EXPORT_SYMBOL(xsc_core_eth_create_cq);
+
+int xsc_core_eth_destroy_cq(struct xsc_core_device *xdev,
+			    struct xsc_core_cq *xcq)
+{
+	struct xsc_cq_table *table = &xdev->dev_res->cq_table;
+	struct xsc_core_cq *tmp;
+	int err;
+
+	spin_lock_irq(&table->lock);
+	tmp = radix_tree_delete(&table->tree, xcq->cqn);
+	spin_unlock_irq(&table->lock);
+	if (!tmp) {
+		err = -ENOENT;
+		goto err_delete_cq;
+	}
+
+	if (tmp != xcq) {
+		err = -EINVAL;
+		goto err_delete_cq;
+	}
+
+	err = xsc_destroy_cq(xdev, xcq->cqn);
+	if (err)
+		goto err_destroy_cq;
+
+	if (atomic_dec_and_test(&xcq->refcount))
+		complete(&xcq->free);
+	wait_for_completion(&xcq->free);
+	return 0;
+
+err_destroy_cq:
+	pci_err(xdev->pdev, "failed to destroy cqn=%d, err=%d\n",
+		xcq->cqn, err);
+	return err;
+err_delete_cq:
+	pci_err(xdev->pdev, "cqn=%d not found in tree, err=%d\n",
+		xcq->cqn, err);
+	return err;
+}
+EXPORT_SYMBOL(xsc_core_eth_destroy_cq);
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
index cc79eaf921ac1..61746e0579f79 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/qp.c
@@ -9,6 +9,7 @@
 #include <linux/kthread.h>
 
 #include "common/xsc_core.h"
+#include "common/xsc_driver.h"
 #include "qp.h"
 
 int xsc_core_create_resource_common(struct xsc_core_device *xdev,
@@ -78,3 +79,116 @@ void xsc_init_qp_table(struct xsc_core_device *xdev)
 	spin_lock_init(&table->lock);
 	INIT_RADIX_TREE(&table->tree, GFP_ATOMIC);
 }
+
+int xsc_core_eth_create_qp(struct xsc_core_device *xdev,
+			   struct xsc_create_qp_mbox_in *in,
+			   int insize, u32 *p_qpn)
+{
+	struct xsc_create_qp_mbox_out out;
+	int ret;
+
+	in->hdr.opcode = cpu_to_be16(XSC_CMD_OP_CREATE_QP);
+	ret = xsc_cmd_exec(xdev, in, insize, &out, sizeof(out));
+	if (ret || out.hdr.status) {
+		pci_err(xdev->pdev, "failed to create sq, err=%d out.status=%u\n",
+			ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	*p_qpn = be32_to_cpu(out.qpn) & 0xffffff;
+
+	return 0;
+}
+EXPORT_SYMBOL(xsc_core_eth_create_qp);
+
+int xsc_core_eth_modify_qp_status(struct xsc_core_device *xdev,
+				  u32 qpn, u16 status)
+{
+	struct xsc_modify_qp_mbox_out out;
+	struct xsc_modify_qp_mbox_in in;
+	int ret = 0;
+
+	in.hdr.opcode = cpu_to_be16(status);
+	in.qpn = cpu_to_be32(qpn);
+	in.no_need_wait = 1;
+
+	ret = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (ret || out.hdr.status != 0) {
+		pci_err(xdev->pdev, "failed to modify qp %u status=%u, err=%d out.status %u\n",
+			qpn, status, ret, out.hdr.status);
+		ret = -ENOEXEC;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(xsc_core_eth_modify_qp_status);
+
+int xsc_core_eth_destroy_qp(struct xsc_core_device *xdev, u32 qpn)
+{
+	struct xsc_destroy_qp_mbox_out out;
+	struct xsc_destroy_qp_mbox_in in;
+	int err;
+
+	err = xsc_core_eth_modify_qp_status(xdev, qpn, XSC_CMD_OP_2RST_QP);
+	if (err) {
+		pci_err(xdev->pdev, "failed to set sq%d status=rst, err=%d\n",
+			qpn, err);
+		return err;
+	}
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_DESTROY_QP);
+	in.qpn = cpu_to_be32(qpn);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status) {
+		pci_err(xdev->pdev, "failed to destroy sq%d, err=%d out.status=%u\n",
+			qpn, err, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(xsc_core_eth_destroy_qp);
+
+int xsc_core_eth_modify_raw_qp(struct xsc_core_device *xdev,
+			       struct xsc_modify_raw_qp_mbox_in *in)
+{
+	struct xsc_modify_raw_qp_mbox_out out;
+	int ret;
+
+	in->hdr.opcode = cpu_to_be16(XSC_CMD_OP_MODIFY_RAW_QP);
+
+	ret = xsc_cmd_exec(xdev, in, sizeof(struct xsc_modify_raw_qp_mbox_in),
+			   &out, sizeof(struct xsc_modify_raw_qp_mbox_out));
+	if (ret || out.hdr.status) {
+		pci_err(xdev->pdev, "failed to modify sq, err=%d out.status=%u\n",
+			ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(xsc_core_eth_modify_raw_qp);
+
+int xsc_core_eth_create_rss_qp_rqs(struct xsc_core_device *xdev,
+				   struct xsc_create_multiqp_mbox_in *in,
+				   int insize,
+				   u32 *p_qpn_base)
+{
+	struct xsc_create_multiqp_mbox_out out;
+	int ret;
+
+	in->hdr.opcode = cpu_to_be16(XSC_CMD_OP_CREATE_MULTI_QP);
+	ret = xsc_cmd_exec(xdev, in, insize, &out, sizeof(out));
+	if (ret || out.hdr.status) {
+		pci_err(xdev->pdev,
+			"failed to create rss rq, qp_num=%d, type=%d, err=%d out.status=%u\n",
+			in->qp_num, in->qp_type, ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	*p_qpn_base = be32_to_cpu(out.qpn_base) & 0xffffff;
+	return 0;
+}
+EXPORT_SYMBOL(xsc_core_eth_create_rss_qp_rqs);

From db638ae6467b74f8f9d5f255f040926daf2ac8cd Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:16 +0800
Subject: [PATCH 2601/2753] xsc: ndo_open and ndo_stop

This patch implements ndo_open and ndo_close. The main task is to
initialize the channel resources.

A channel is a data transmission path. Each CPU is bound to a
channel, and each channel is associated with an interrupt.

A channel consists of one RX queue and multiple TX queues, with
the number of TX queues corresponding to the number of traffic
classes. Each TX queue and RX queue is a separate queue pair (QP).
The TX queue is used only for transmission, while the RX queue
is used only for reception. Each queue pair is bound to a
completion queue (CQ).

Each channel also has its own NAPI context.

The patch also add event handling functionality. Added a
workqueue and event handler to process asynchronous events from
the hardware.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |   44 +
 .../yunsilicon/xsc/common/xsc_device.h        |   35 +
 .../net/ethernet/yunsilicon/xsc/net/Makefile  |    2 +-
 .../net/ethernet/yunsilicon/xsc/net/main.c    | 1534 ++++++++++++++++-
 .../net/ethernet/yunsilicon/xsc/net/xsc_eth.h |    6 +
 .../yunsilicon/xsc/net/xsc_eth_common.h       |  142 ++
 .../ethernet/yunsilicon/xsc/net/xsc_eth_rx.c  |   48 +
 .../yunsilicon/xsc/net/xsc_eth_txrx.c         |  100 ++
 .../yunsilicon/xsc/net/xsc_eth_txrx.h         |   26 +
 .../ethernet/yunsilicon/xsc/net/xsc_queue.h   |  148 ++
 .../net/ethernet/yunsilicon/xsc/pci/Makefile  |    2 +-
 .../net/ethernet/yunsilicon/xsc/pci/vport.c   |   32 +
 12 files changed, 2115 insertions(+), 4 deletions(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/pci/vport.c

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index f9534993f8fb9..0b54b2d8ac19a 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -150,6 +150,34 @@ enum xsc_event {
 	XSC_EVENT_TYPE_WQ_ACCESS_ERROR		= 0x11,
 };
 
+struct xsc_cqe {
+	__le32		data0;
+#define XSC_CQE_MSG_OPCD_MASK		GENMASK(7, 0)
+#define XSC_CQE_ERR_CODE_MASK		GENMASK(6, 0)
+#define XSC_CQE_IS_ERR			BIT(7)
+#define XSC_CQE_QP_ID_MASK		GENMASK(22, 8)
+#define XSC_CQE_SE			BIT(24)
+#define XSC_CQE_HAS_PPH			BIT(25)
+#define XSC_CQE_TYPE			BIT(26)
+#define XSC_CQE_WITH_IMM		BIT(27)
+#define XSC_CQE_CSUM_ERR_MASK		GENMASK(31, 28)
+
+	__le32		imm_data;
+	__le32		msg_len;
+	__le32		vni;
+	__le32		ts_l;
+	__le16		ts_h;
+	__le16		wqe_id;
+	__le32		rsv;
+	__le32		data1;
+#define XSC_CQE_OWNER			BIT(31)
+};
+
+/* cq doorbell bitfields */
+#define XSC_CQ_DB_NEXT_CID_MASK		GENMASK(15, 0)
+#define XSC_CQ_DB_CQ_ID_MASK		GENMASK(30, 16)
+#define XSC_CQ_DB_ARM			BIT(31)
+
 struct xsc_core_cq {
 	u32			cqn;
 	u32			cqe_sz;
@@ -372,6 +400,8 @@ struct xsc_core_device {
 	int			bar_num;
 
 	u8			mac_port;
+	u8			pcie_no;
+	u8			pf_id;
 	u16			glb_func_id;
 
 	u16			msix_vec_base;
@@ -395,6 +425,8 @@ struct xsc_core_device {
 	u32			fw_version_tweak;
 	u8			fw_version_extra_flag;
 	cpumask_var_t		xps_cpumask;
+
+	u8			user_mode;
 };
 
 int xsc_core_create_resource_common(struct xsc_core_device *xdev,
@@ -432,6 +464,8 @@ int xsc_core_frag_buf_alloc_node(struct xsc_core_device *xdev,
 void xsc_core_frag_buf_free(struct xsc_core_device *xdev,
 			    struct xsc_frag_buf *buf);
 
+u8 xsc_core_query_vport_state(struct xsc_core_device *xdev, u16 vport);
+
 static inline void *xsc_buf_offset(struct xsc_buf *buf, unsigned long offset)
 {
 	if (likely(buf->nbufs == 1))
@@ -446,4 +480,14 @@ static inline bool xsc_fw_is_available(struct xsc_core_device *xdev)
 	return xdev->cmd.cmd_status == XSC_CMD_STATUS_NORMAL;
 }
 
+static inline void xsc_set_user_mode(struct xsc_core_device *xdev, u8 mode)
+{
+	xdev->user_mode = mode;
+}
+
+static inline u8 xsc_get_user_mode(struct xsc_core_device *xdev)
+{
+	return xdev->user_mode;
+}
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
index 45ea8d2a0e934..154a4e0272070 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_device.h
@@ -6,6 +6,22 @@
 #ifndef __XSC_DEVICE_H
 #define __XSC_DEVICE_H
 
+#include <linux/types.h>
+#include <linux/ethtool.h>
+
+/* QP type */
+enum {
+	XSC_QUEUE_TYPE_RDMA_RC		= 0,
+	XSC_QUEUE_TYPE_RDMA_MAD		= 1,
+	XSC_QUEUE_TYPE_RAW		= 2,
+	XSC_QUEUE_TYPE_VIRTIO_NET	= 3,
+	XSC_QUEUE_TYPE_VIRTIO_BLK	= 4,
+	XSC_QUEUE_TYPE_RAW_TPE		= 5,
+	XSC_QUEUE_TYPE_RAW_TSO		= 6,
+	XSC_QUEUE_TYPE_RAW_TX		= 7,
+	XSC_QUEUE_TYPE_INVALID		= 0xFF,
+};
+
 enum xsc_traffic_types {
 	XSC_TT_IPV4,
 	XSC_TT_IPV4_TCP,
@@ -39,4 +55,23 @@ struct xsc_tirc_config {
 	u32 rx_hash_fields;
 };
 
+enum {
+	XSC_HASH_FUNC_XOR		= 0,
+	XSC_HASH_FUNC_TOP		= 1,
+	XSC_HASH_FUNC_TOP_SYM	= 2,
+	XSC_HASH_FUNC_RSV		= 3,
+};
+
+static inline u8 xsc_hash_func_type(u8 hash_func)
+{
+	switch (hash_func) {
+	case ETH_RSS_HASH_TOP:
+		return XSC_HASH_FUNC_TOP;
+	case ETH_RSS_HASH_XOR:
+		return XSC_HASH_FUNC_XOR;
+	default:
+		return XSC_HASH_FUNC_TOP;
+	}
+}
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
index ccbc5a26d4395..104ef5330849c 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc_eth.o
 
-xsc_eth-y := main.o xsc_eth_wq.o
+xsc_eth-y := main.o xsc_eth_wq.o xsc_eth_txrx.o xsc_eth_rx.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/main.c b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
index cc40628f9e1a7..67e68a6f6318e 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
@@ -7,6 +7,7 @@
 #include <linux/etherdevice.h>
 #include <linux/auxiliary_bus.h>
 #include <linux/ethtool.h>
+#include <linux/irq.h>
 
 #include "common/xsc_core.h"
 #include "common/xsc_driver.h"
@@ -14,6 +15,7 @@
 #include "common/xsc_pp.h"
 #include "xsc_eth_common.h"
 #include "xsc_eth.h"
+#include "xsc_eth_txrx.h"
 
 static const struct xsc_tirc_config tirc_default_config[XSC_NUM_INDIR_TIRS] = {
 	[XSC_TT_IPV4] = {
@@ -114,6 +116,8 @@ static int xsc_eth_netdev_init(struct xsc_adapter *adapter)
 	if (!adapter->txq2sq)
 		goto err_out;
 
+	mutex_init(&adapter->status_lock);
+
 	adapter->workq = create_singlethread_workqueue("xsc_eth");
 	if (!adapter->workq)
 		goto err_free_priv;
@@ -128,11 +132,1536 @@ static int xsc_eth_netdev_init(struct xsc_adapter *adapter)
 	return -ENOMEM;
 }
 
-static int xsc_eth_close(struct net_device *netdev)
+static void xsc_eth_build_queue_param(struct xsc_adapter *adapter,
+				      struct xsc_queue_attr *attr, u8 type)
+{
+	struct xsc_core_device *xdev = adapter->xdev;
+
+	if (adapter->nic_param.sq_size == 0)
+		adapter->nic_param.sq_size = BIT(xdev->caps.log_max_qp_depth);
+	if (adapter->nic_param.rq_size == 0)
+		adapter->nic_param.rq_size = BIT(xdev->caps.log_max_qp_depth);
+
+	if (type == XSC_QUEUE_TYPE_EQ) {
+		attr->q_type = XSC_QUEUE_TYPE_EQ;
+		attr->ele_num = XSC_EQ_ELE_NUM;
+		attr->ele_size = XSC_EQ_ELE_SZ;
+		attr->ele_log_size = order_base_2(XSC_EQ_ELE_SZ);
+		attr->q_log_size = order_base_2(XSC_EQ_ELE_NUM);
+	} else if (type == XSC_QUEUE_TYPE_RQCQ) {
+		attr->q_type = XSC_QUEUE_TYPE_RQCQ;
+		attr->ele_num = min_t(int, XSC_RQCQ_ELE_NUM,
+				      xdev->caps.max_cqes);
+		attr->ele_size = XSC_RQCQ_ELE_SZ;
+		attr->ele_log_size = order_base_2(XSC_RQCQ_ELE_SZ);
+		attr->q_log_size = order_base_2(attr->ele_num);
+	} else if (type == XSC_QUEUE_TYPE_SQCQ) {
+		attr->q_type = XSC_QUEUE_TYPE_SQCQ;
+		attr->ele_num = min_t(int, XSC_SQCQ_ELE_NUM,
+				      xdev->caps.max_cqes);
+		attr->ele_size = XSC_SQCQ_ELE_SZ;
+		attr->ele_log_size = order_base_2(XSC_SQCQ_ELE_SZ);
+		attr->q_log_size = order_base_2(attr->ele_num);
+	} else if (type == XSC_QUEUE_TYPE_RQ) {
+		attr->q_type = XSC_QUEUE_TYPE_RQ;
+		attr->ele_num = adapter->nic_param.rq_size;
+		attr->ele_size = xdev->caps.recv_ds_num * XSC_RECV_WQE_DS;
+		attr->ele_log_size = order_base_2(attr->ele_size);
+		attr->q_log_size = order_base_2(attr->ele_num);
+	} else if (type == XSC_QUEUE_TYPE_SQ) {
+		attr->q_type = XSC_QUEUE_TYPE_SQ;
+		attr->ele_num = adapter->nic_param.sq_size;
+		attr->ele_size = xdev->caps.send_ds_num * XSC_SEND_WQE_DS;
+		attr->ele_log_size = order_base_2(attr->ele_size);
+		attr->q_log_size = order_base_2(attr->ele_num);
+	}
+}
+
+static u32 xsc_rx_get_linear_frag_sz(u32 mtu)
+{
+	u32 byte_count = XSC_SW2HW_FRAG_SIZE(mtu);
+
+	return XSC_SKB_FRAG_SZ(byte_count);
+}
+
+static bool xsc_rx_is_linear_skb(u32 mtu)
+{
+	u32 linear_frag_sz = xsc_rx_get_linear_frag_sz(mtu);
+
+	return linear_frag_sz <= PAGE_SIZE;
+}
+
+static u32 xsc_get_rq_frag_info(struct xsc_rq_frags_info *frags_info, u32 mtu)
+{
+	u32 byte_count = XSC_SW2HW_FRAG_SIZE(mtu);
+	int frag_stride;
+	int i = 0;
+
+	if (xsc_rx_is_linear_skb(mtu)) {
+		frag_stride = xsc_rx_get_linear_frag_sz(mtu);
+		frag_stride = roundup_pow_of_two(frag_stride);
+
+		frags_info->arr[0].frag_size = byte_count;
+		frags_info->arr[0].frag_stride = frag_stride;
+		frags_info->num_frags = 1;
+		frags_info->wqe_bulk = PAGE_SIZE / frag_stride;
+		frags_info->wqe_bulk_min = frags_info->wqe_bulk;
+		goto out;
+	}
+
+	if (byte_count <= DEFAULT_FRAG_SIZE) {
+		frags_info->arr[0].frag_size = DEFAULT_FRAG_SIZE;
+		frags_info->arr[0].frag_stride = DEFAULT_FRAG_SIZE;
+		frags_info->num_frags = 1;
+	} else if (byte_count <= PAGE_SIZE_4K) {
+		frags_info->arr[0].frag_size = PAGE_SIZE_4K;
+		frags_info->arr[0].frag_stride = PAGE_SIZE_4K;
+		frags_info->num_frags = 1;
+	} else if (byte_count <= (PAGE_SIZE_4K + DEFAULT_FRAG_SIZE)) {
+		if (PAGE_SIZE < 2 * PAGE_SIZE_4K) {
+			frags_info->arr[0].frag_size = PAGE_SIZE_4K;
+			frags_info->arr[0].frag_stride = PAGE_SIZE_4K;
+			frags_info->arr[1].frag_size = PAGE_SIZE_4K;
+			frags_info->arr[1].frag_stride = PAGE_SIZE_4K;
+			frags_info->num_frags = 2;
+		} else {
+			frags_info->arr[0].frag_size = 2 * PAGE_SIZE_4K;
+			frags_info->arr[0].frag_stride = 2 * PAGE_SIZE_4K;
+			frags_info->num_frags = 1;
+		}
+	} else if (byte_count <= 2 * PAGE_SIZE_4K) {
+		if (PAGE_SIZE < 2 * PAGE_SIZE_4K) {
+			frags_info->arr[0].frag_size = PAGE_SIZE_4K;
+			frags_info->arr[0].frag_stride = PAGE_SIZE_4K;
+			frags_info->arr[1].frag_size = PAGE_SIZE_4K;
+			frags_info->arr[1].frag_stride = PAGE_SIZE_4K;
+			frags_info->num_frags = 2;
+		} else {
+			frags_info->arr[0].frag_size = 2 * PAGE_SIZE_4K;
+			frags_info->arr[0].frag_stride = 2 * PAGE_SIZE_4K;
+			frags_info->num_frags = 1;
+		}
+	} else {
+		if (PAGE_SIZE < 4 * PAGE_SIZE_4K) {
+			frags_info->num_frags =
+				roundup(byte_count,
+					PAGE_SIZE_4K) / PAGE_SIZE_4K;
+			for (i = 0; i < frags_info->num_frags; i++) {
+				frags_info->arr[i].frag_size = PAGE_SIZE_4K;
+				frags_info->arr[i].frag_stride = PAGE_SIZE_4K;
+			}
+		} else {
+			frags_info->arr[0].frag_size = 4 * PAGE_SIZE_4K;
+			frags_info->arr[0].frag_stride = 4 * PAGE_SIZE_4K;
+			frags_info->num_frags = 1;
+		}
+	}
+
+	if (PAGE_SIZE <= PAGE_SIZE_4K) {
+		frags_info->wqe_bulk_min = 4;
+		frags_info->wqe_bulk = max_t(u8, frags_info->wqe_bulk_min, 8);
+	} else if (PAGE_SIZE <= 2 * PAGE_SIZE_4K) {
+		frags_info->wqe_bulk = 2;
+		frags_info->wqe_bulk_min = frags_info->wqe_bulk;
+	} else {
+		frags_info->wqe_bulk =
+			PAGE_SIZE /
+			(frags_info->num_frags * frags_info->arr[0].frag_size);
+		frags_info->wqe_bulk_min = frags_info->wqe_bulk;
+	}
+
+out:
+	frags_info->log_num_frags = order_base_2(frags_info->num_frags);
+
+	return frags_info->num_frags * frags_info->arr[0].frag_size;
+}
+
+static void xsc_build_rq_frags_info(struct xsc_queue_attr *attr,
+				    struct xsc_rq_frags_info *frags_info,
+				    struct xsc_eth_params *params)
+{
+	params->rq_frags_size = xsc_get_rq_frag_info(frags_info, params->mtu);
+	frags_info->frags_max_num = attr->ele_size / XSC_RECV_WQE_DS;
+}
+
+static void xsc_eth_build_channel_param(struct xsc_adapter *adapter,
+					struct xsc_channel_param *chl_param)
+{
+	xsc_eth_build_queue_param(adapter, &chl_param->rqcq_param.cq_attr,
+				  XSC_QUEUE_TYPE_RQCQ);
+	chl_param->rqcq_param.wq.buf_numa_node = dev_to_node(adapter->dev);
+
+	xsc_eth_build_queue_param(adapter, &chl_param->sqcq_param.cq_attr,
+				  XSC_QUEUE_TYPE_SQCQ);
+	chl_param->sqcq_param.wq.buf_numa_node = dev_to_node(adapter->dev);
+
+	xsc_eth_build_queue_param(adapter, &chl_param->sq_param.sq_attr,
+				  XSC_QUEUE_TYPE_SQ);
+	chl_param->sq_param.wq.buf_numa_node = dev_to_node(adapter->dev);
+
+	xsc_eth_build_queue_param(adapter, &chl_param->rq_param.rq_attr,
+				  XSC_QUEUE_TYPE_RQ);
+	chl_param->rq_param.wq.buf_numa_node = dev_to_node(adapter->dev);
+
+	xsc_build_rq_frags_info(&chl_param->rq_param.rq_attr,
+				&chl_param->rq_param.frags_info,
+				&adapter->nic_param);
+}
+
+static void xsc_eth_cq_error_event(struct xsc_core_cq *xcq,
+				   enum xsc_event event)
+{
+	struct xsc_cq *xsc_cq = container_of(xcq, struct xsc_cq, xcq);
+	struct xsc_core_device *xdev = xsc_cq->xdev;
+
+	if (event != XSC_EVENT_TYPE_CQ_ERROR) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "Unexpected event type %d on CQ %06x\n",
+			   event, xcq->cqn);
+		return;
+	}
+
+	netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+		   "Eth catch CQ ERROR: %x, cqn: %d\n", event, xcq->cqn);
+}
+
+static void xsc_eth_completion_event(struct xsc_core_cq *xcq)
+{
+	struct xsc_cq *cq = container_of(xcq, struct xsc_cq, xcq);
+	struct xsc_core_device *xdev = cq->xdev;
+	struct xsc_rq *rq = NULL;
+
+	if (unlikely(!cq->channel)) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "cq%d->channel is null\n", xcq->cqn);
+		return;
+	}
+
+	rq = &cq->channel->qp.rq[0];
+
+	set_bit(XSC_CHANNEL_NAPI_SCHED, &cq->channel->flags);
+
+	if (!test_bit(XSC_ETH_RQ_STATE_ENABLED, &rq->state))
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "ch%d_cq%d, napi_flag=0x%lx\n",
+			   cq->channel->chl_idx, xcq->cqn,
+			   cq->napi->state);
+
+	napi_schedule(cq->napi);
+	cq->event_ctr++;
+}
+
+static int xsc_eth_alloc_cq(struct xsc_channel *c, struct xsc_cq *pcq,
+			    struct xsc_cq_param *pcq_param)
+{
+	u8 ele_log_size = pcq_param->cq_attr.ele_log_size;
+	struct xsc_core_device *xdev = c->adapter->xdev;
+	u8 q_log_size = pcq_param->cq_attr.q_log_size;
+	struct xsc_core_cq *core_cq = &pcq->xcq;
+	int ret;
+	u32 i;
+
+	pcq_param->wq.db_numa_node = cpu_to_node(c->cpu);
+	pcq_param->wq.buf_numa_node = cpu_to_node(c->cpu);
+
+	ret = xsc_eth_cqwq_create(xdev, &pcq_param->wq,
+				  q_log_size, ele_log_size, &pcq->wq,
+				  &pcq->wq_ctrl);
+	if (ret)
+		return ret;
+
+	core_cq->cqe_sz = pcq_param->cq_attr.ele_num;
+	core_cq->comp = xsc_eth_completion_event;
+	core_cq->event = xsc_eth_cq_error_event;
+	core_cq->vector = c->chl_idx;
+
+	for (i = 0; i < xsc_cqwq_get_size(&pcq->wq); i++) {
+		struct xsc_cqe *cqe = xsc_cqwq_get_wqe(&pcq->wq, i);
+
+		cqe->data1 |= cpu_to_le32(XSC_CQE_OWNER);
+	}
+	pcq->xdev = xdev;
+
+	return ret;
+}
+
+static int xsc_eth_set_cq(struct xsc_channel *c,
+			  struct xsc_cq *pcq,
+			  struct xsc_cq_param *pcq_param)
+{
+	struct xsc_core_device *xdev = c->adapter->xdev;
+	struct xsc_create_cq_mbox_in *in;
+	unsigned int hw_npages;
+	unsigned int irqn;
+	int inlen;
+	u32 eqn;
+	int ret;
+
+	hw_npages = DIV_ROUND_UP(pcq->wq_ctrl.buf.size, PAGE_SIZE_4K);
+	/*mbox size + pas size*/
+	inlen = sizeof(struct xsc_create_cq_mbox_in) +
+		sizeof(__be64) * hw_npages;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	/*construct param of in struct*/
+	ret = xsc_core_vector2eqn(xdev, c->chl_idx, &eqn, &irqn);
+	if (ret)
+		goto err_free;
+
+	in->ctx.eqn = cpu_to_be16(eqn);
+	in->ctx.log_cq_sz = pcq_param->cq_attr.q_log_size;
+	in->ctx.pa_num = cpu_to_be16(hw_npages);
+	in->ctx.glb_func_id = cpu_to_be16(xdev->glb_func_id);
+
+	xsc_core_fill_page_frag_array(&pcq->wq_ctrl.buf,
+				      &in->pas[0],
+				      hw_npages);
+
+	ret = xsc_core_eth_create_cq(c->adapter->xdev, &pcq->xcq, in, inlen);
+	if (ret)
+		goto err_free;
+	pcq->xcq.irqn = irqn;
+	pcq->xcq.eq = xsc_core_eq_get(xdev, pcq->xcq.vector);
+	return 0;
+
+err_free:
+	kvfree(in);
+	return ret;
+}
+
+static void xsc_eth_free_cq(struct xsc_cq *cq)
+{
+	xsc_eth_wq_destroy(&cq->wq_ctrl);
+}
+
+static int xsc_eth_open_cq(struct xsc_channel *c,
+			   struct xsc_cq *pcq,
+			   struct xsc_cq_param *pcq_param)
+{
+	int ret;
+
+	ret = xsc_eth_alloc_cq(c, pcq, pcq_param);
+	if (ret)
+		return ret;
+
+	ret = xsc_eth_set_cq(c, pcq, pcq_param);
+	if (ret)
+		goto err_free_cq;
+
+	xsc_cq_notify_hw_rearm(pcq);
+
+	pcq->napi = &c->napi;
+	pcq->channel = c;
+	pcq->rx = (pcq_param->cq_attr.q_type == XSC_QUEUE_TYPE_RQCQ) ? 1 : 0;
+
+	return 0;
+
+err_free_cq:
+	xsc_eth_free_cq(pcq);
+	return ret;
+}
+
+static int xsc_eth_close_cq(struct xsc_channel *c, struct xsc_cq *pcq)
+{
+	struct xsc_core_device *xdev = c->adapter->xdev;
+	int ret;
+
+	ret = xsc_core_eth_destroy_cq(xdev, &pcq->xcq);
+	if (ret) {
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev, "failed to close ch%d cq%d, ret=%d\n",
+			   c->chl_idx, pcq->xcq.cqn, ret);
+		return ret;
+	}
+
+	xsc_eth_free_cq(pcq);
+
+	return 0;
+}
+
+static void xsc_free_qp_sq_db(struct xsc_sq *sq)
+{
+	kvfree(sq->db.wqe_info);
+	kvfree(sq->db.dma_fifo);
+}
+
+static void xsc_free_qp_sq(struct xsc_sq *sq)
+{
+	xsc_free_qp_sq_db(sq);
+	xsc_eth_wq_destroy(&sq->wq_ctrl);
+}
+
+static int xsc_eth_alloc_qp_sq_db(struct xsc_sq *sq, int numa)
+{
+	struct xsc_core_device *xdev = sq->cq.xdev;
+	int wq_sz;
+	int df_sz;
+
+	wq_sz = xsc_wq_cyc_get_size(&sq->wq);
+	df_sz = wq_sz * xdev->caps.send_ds_num;
+	sq->db.dma_fifo = kvzalloc_node(array_size(df_sz,
+						   sizeof(*sq->db.dma_fifo)),
+					GFP_KERNEL,
+					numa);
+	sq->db.wqe_info = kvzalloc_node(array_size(wq_sz,
+						   sizeof(*sq->db.wqe_info)),
+					GFP_KERNEL,
+					numa);
+
+	if (!sq->db.dma_fifo || !sq->db.wqe_info) {
+		xsc_free_qp_sq_db(sq);
+		return -ENOMEM;
+	}
+
+	sq->dma_fifo_mask = df_sz - 1;
+
+	return 0;
+}
+
+static void xsc_eth_qp_event(struct xsc_core_qp *qp, int type)
+{
+	struct xsc_core_device *xdev;
+	struct xsc_rq *rq;
+	struct xsc_sq *sq;
+
+	if (qp->eth_queue_type == XSC_RES_RQ) {
+		rq = container_of(qp, struct xsc_rq, cqp);
+		xdev = rq->cq.xdev;
+	} else if (qp->eth_queue_type == XSC_RES_SQ) {
+		sq = container_of(qp, struct xsc_sq, cqp);
+		xdev = sq->cq.xdev;
+	} else {
+		pr_err("%s:Unknown eth qp type %d\n", __func__, type);
+		return;
+	}
+
+	switch (type) {
+	case XSC_EVENT_TYPE_WQ_CATAS_ERROR:
+	case XSC_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+	case XSC_EVENT_TYPE_WQ_ACCESS_ERROR:
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "%s:Async event %x on QP %d\n",
+			   __func__, type, qp->qpn);
+		break;
+	default:
+		netdev_err(((struct xsc_adapter *)xdev->eth_priv)->netdev,
+			   "%s: Unexpected event type %d on QP %d\n",
+			   __func__, type, qp->qpn);
+		return;
+	}
+}
+
+static int xsc_eth_open_qp_sq(struct xsc_channel *c,
+			      struct xsc_sq *psq,
+			      struct xsc_sq_param *psq_param,
+			      u32 sq_idx)
+{
+	u8 ele_log_size = psq_param->sq_attr.ele_log_size;
+	u8 q_log_size = psq_param->sq_attr.q_log_size;
+	struct xsc_modify_raw_qp_mbox_in *modify_in;
+	struct xsc_create_qp_mbox_in *in;
+	struct xsc_core_device *xdev;
+	struct xsc_adapter *adapter;
+	unsigned int hw_npages;
+	int inlen;
+	int ret;
+
+	adapter = c->adapter;
+	xdev  = adapter->xdev;
+	psq_param->wq.db_numa_node = cpu_to_node(c->cpu);
+
+	ret = xsc_eth_wq_cyc_create(xdev, &psq_param->wq,
+				    q_log_size, ele_log_size, &psq->wq,
+				    &psq->wq_ctrl);
+	if (ret)
+		return ret;
+
+	hw_npages = DIV_ROUND_UP(psq->wq_ctrl.buf.size, PAGE_SIZE_4K);
+	inlen = sizeof(struct xsc_create_qp_mbox_in) +
+		sizeof(__be64) * hw_npages;
+
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		ret = -ENOMEM;
+		goto err_sq_wq_destroy;
+	}
+	in->req.input_qpn = cpu_to_be16(XSC_QPN_SQN_STUB); /*no use for eth*/
+	in->req.qp_type = XSC_QUEUE_TYPE_RAW_TSO; /*default sq is tso qp*/
+	in->req.log_sq_sz = ilog2(xdev->caps.send_ds_num) + q_log_size;
+	in->req.pa_num = cpu_to_be16(hw_npages);
+	in->req.cqn_send = cpu_to_be16(psq->cq.xcq.cqn);
+	in->req.cqn_recv = in->req.cqn_send;
+	in->req.glb_funcid = cpu_to_be16(xdev->glb_func_id);
+
+	xsc_core_fill_page_frag_array(&psq->wq_ctrl.buf,
+				      &in->req.pas[0], hw_npages);
+
+	ret = xsc_core_eth_create_qp(xdev, in, inlen, &psq->sqn);
+	if (ret)
+		goto err_sq_in_destroy;
+
+	psq->cqp.qpn = psq->sqn;
+	psq->cqp.event = xsc_eth_qp_event;
+	psq->cqp.eth_queue_type = XSC_RES_SQ;
+
+	ret = xsc_core_create_resource_common(xdev, &psq->cqp);
+	if (ret) {
+		netdev_err(adapter->netdev, "%s:error qp:%d errno:%d\n",
+			   __func__, psq->sqn, ret);
+		goto err_sq_destroy;
+	}
+
+	psq->channel = c;
+	psq->ch_ix = c->chl_idx;
+	psq->txq_ix = psq->ch_ix + sq_idx * adapter->channels.num_chl;
+
+	/*need to querify from hardware*/
+	psq->hw_mtu = XSC_ETH_HW_MTU_SEND;
+	psq->stop_room = 1;
+
+	ret = xsc_eth_alloc_qp_sq_db(psq, psq_param->wq.db_numa_node);
+	if (ret)
+		goto err_sq_common_destroy;
+
+	inlen = sizeof(struct xsc_modify_raw_qp_mbox_in);
+	modify_in = kvzalloc(inlen, GFP_KERNEL);
+	if (!modify_in) {
+		ret = -ENOMEM;
+		goto err_sq_common_destroy;
+	}
+
+	modify_in->req.qp_out_port = xdev->pf_id;
+	modify_in->pcie_no = xdev->pcie_no;
+	modify_in->req.qpn = cpu_to_be16((u16)(psq->sqn));
+	modify_in->req.func_id = cpu_to_be16(xdev->glb_func_id);
+	modify_in->req.dma_direct = XSC_DMA_DIR_TO_MAC;
+	modify_in->req.prio = sq_idx;
+	ret = xsc_core_eth_modify_raw_qp(xdev, modify_in);
+	if (ret)
+		goto err_sq_modify_in_destroy;
+
+	kvfree(modify_in);
+	kvfree(in);
+
+	return 0;
+
+err_sq_modify_in_destroy:
+	kvfree(modify_in);
+
+err_sq_common_destroy:
+	xsc_core_destroy_resource_common(xdev, &psq->cqp);
+
+err_sq_destroy:
+	xsc_core_eth_destroy_qp(xdev, psq->cqp.qpn);
+
+err_sq_in_destroy:
+	kvfree(in);
+
+err_sq_wq_destroy:
+	xsc_eth_wq_destroy(&psq->wq_ctrl);
+	return ret;
+}
+
+static int xsc_eth_close_qp_sq(struct xsc_channel *c, struct xsc_sq *psq)
+{
+	struct xsc_core_device *xdev = c->adapter->xdev;
+	int ret;
+
+	xsc_core_destroy_resource_common(xdev, &psq->cqp);
+
+	ret = xsc_core_eth_destroy_qp(xdev, psq->cqp.qpn);
+	if (ret)
+		return ret;
+
+	xsc_free_qp_sq(psq);
+
+	return 0;
+}
+
+static int xsc_eth_open_channel(struct xsc_adapter *adapter,
+				int idx,
+				struct xsc_channel *c,
+				struct xsc_channel_param *chl_param)
+{
+	struct xsc_core_device *xdev = adapter->xdev;
+	struct net_device *netdev = adapter->netdev;
+	const struct cpumask *aff;
+	unsigned int irqn;
+	int i, j;
+	u32 eqn;
+	int ret;
+
+	c->adapter = adapter;
+	c->netdev = adapter->netdev;
+	c->chl_idx = idx;
+	c->num_tc = adapter->nic_param.num_tc;
+
+	/*1rq per channel, and may have multi sqs per channel*/
+	c->qp.rq_num = 1;
+	c->qp.sq_num = c->num_tc;
+
+	if (xdev->caps.msix_enable) {
+		ret = xsc_core_vector2eqn(xdev, c->chl_idx, &eqn, &irqn);
+		if (ret)
+			goto err_out;
+		aff = irq_get_affinity_mask(irqn);
+		c->aff_mask = aff;
+		c->cpu = cpumask_first(aff);
+	}
+
+	if (c->qp.sq_num > XSC_MAX_NUM_TC || c->qp.rq_num > XSC_MAX_NUM_TC) {
+		ret = -EINVAL;
+		goto err_out;
+	}
+
+	for (i = 0; i < c->qp.rq_num; i++) {
+		ret = xsc_eth_open_cq(c, &c->qp.rq[i].cq,
+				      &chl_param->rqcq_param);
+		if (ret) {
+			j = i - 1;
+			goto err_close_rq_cq;
+		}
+	}
+
+	for (i = 0; i < c->qp.sq_num; i++) {
+		ret = xsc_eth_open_cq(c, &c->qp.sq[i].cq,
+				      &chl_param->sqcq_param);
+		if (ret) {
+			j = i - 1;
+			goto err_close_sq_cq;
+		}
+	}
+
+	for (i = 0; i < c->qp.sq_num; i++) {
+		ret = xsc_eth_open_qp_sq(c, &c->qp.sq[i],
+					 &chl_param->sq_param, i);
+		if (ret) {
+			j = i - 1;
+			goto err_close_sq;
+		}
+	}
+	netif_napi_add(netdev, &c->napi, xsc_eth_napi_poll);
+
+	netdev_dbg(adapter->netdev, "open channel%d ok\n", idx);
+	return 0;
+
+err_close_sq:
+	for (; j >= 0; j--)
+		xsc_eth_close_qp_sq(c, &c->qp.sq[j]);
+	j = (c->qp.rq_num - 1);
+err_close_sq_cq:
+	for (; j >= 0; j--)
+		xsc_eth_close_cq(c, &c->qp.sq[j].cq);
+	j = (c->qp.rq_num - 1);
+err_close_rq_cq:
+	for (; j >= 0; j--)
+		xsc_eth_close_cq(c, &c->qp.rq[j].cq);
+err_out:
+	netdev_err(adapter->netdev,
+		   "failed to open channel: ch%d, sq_num=%d, rq_num=%d, err=%d\n",
+		   idx, c->qp.sq_num, c->qp.rq_num, ret);
+	return ret;
+}
+
+static int xsc_eth_modify_qps_channel(struct xsc_adapter *adapter,
+				      struct xsc_channel *c)
+{
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < c->qp.rq_num; i++) {
+		c->qp.rq[i].post_wqes(&c->qp.rq[i]);
+		ret = xsc_core_eth_modify_qp_status(adapter->xdev,
+						    c->qp.rq[i].rqn,
+						    XSC_CMD_OP_RTR2RTS_QP);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < c->qp.sq_num; i++) {
+		ret = xsc_core_eth_modify_qp_status(adapter->xdev,
+						    c->qp.sq[i].sqn,
+						    XSC_CMD_OP_RTR2RTS_QP);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int xsc_eth_modify_qps(struct xsc_adapter *adapter,
+			      struct xsc_eth_channels *chls)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < chls->num_chl; i++) {
+		struct xsc_channel *c = &chls->c[i];
+
+		ret = xsc_eth_modify_qps_channel(adapter, c);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static void xsc_eth_init_frags_partition(struct xsc_rq *rq)
+{
+	struct xsc_wqe_frag_info next_frag = {};
+	struct xsc_wqe_frag_info *prev;
+	int i;
+
+	next_frag.di = &rq->wqe.di[0];
+	next_frag.offset = 0;
+	prev = NULL;
+
+	for (i = 0; i < xsc_wq_cyc_get_size(&rq->wqe.wq); i++) {
+		struct xsc_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+		struct xsc_wqe_frag_info *frag =
+			&rq->wqe.frags[i << rq->wqe.info.log_num_frags];
+		int f;
+
+		for (f = 0; f < rq->wqe.info.num_frags; f++, frag++) {
+			if (next_frag.offset + frag_info[f].frag_stride >
+				XSC_RX_FRAG_SZ) {
+				next_frag.di++;
+				next_frag.offset = 0;
+				if (prev)
+					prev->last_in_page = 1;
+			}
+			*frag = next_frag;
+
+			/* prepare next */
+			next_frag.offset += frag_info[f].frag_stride;
+			prev = frag;
+		}
+	}
+
+	if (prev)
+		prev->last_in_page = 1;
+}
+
+static int xsc_eth_init_di_list(struct xsc_rq *rq, u32 wq_sz, int cpu)
+{
+	int len = wq_sz << rq->wqe.info.log_num_frags;
+
+	rq->wqe.di = kvzalloc_node(array_size(len, sizeof(*rq->wqe.di)),
+				   GFP_KERNEL, cpu_to_node(cpu));
+	if (!rq->wqe.di)
+		return -ENOMEM;
+
+	xsc_eth_init_frags_partition(rq);
+
+	return 0;
+}
+
+static void xsc_eth_free_di_list(struct xsc_rq *rq)
+{
+	kvfree(rq->wqe.di);
+}
+
+static int xsc_eth_alloc_rq(struct xsc_channel *c,
+			    struct xsc_rq *prq,
+			    struct xsc_rq_param *prq_param)
+{
+	u8 ele_log_size = prq_param->rq_attr.ele_log_size;
+	u8 q_log_size = prq_param->rq_attr.q_log_size;
+	struct page_pool_params pagepool_params = {0};
+	struct xsc_adapter *adapter = c->adapter;
+	u32 pool_size = 1 << q_log_size;
+	int ret = 0;
+	u32 wq_sz;
+	int i, f;
+
+	prq_param->wq.db_numa_node = cpu_to_node(c->cpu);
+
+	ret = xsc_eth_wq_cyc_create(c->adapter->xdev, &prq_param->wq,
+				    q_log_size, ele_log_size, &prq->wqe.wq,
+				    &prq->wq_ctrl);
+	if (ret)
+		return ret;
+
+	wq_sz = xsc_wq_cyc_get_size(&prq->wqe.wq);
+
+	prq->wqe.info = prq_param->frags_info;
+	prq->wqe.frags =
+		kvzalloc_node(array_size((wq_sz << prq->wqe.info.log_num_frags),
+					 sizeof(*prq->wqe.frags)),
+			      GFP_KERNEL,
+			      cpu_to_node(c->cpu));
+	if (!prq->wqe.frags) {
+		ret = -ENOMEM;
+		goto err_destroy_wq;
+	}
+
+	ret = xsc_eth_init_di_list(prq, wq_sz, c->cpu);
+	if (ret)
+		goto err_free_frags;
+
+	prq->buff.map_dir = DMA_FROM_DEVICE;
+
+	/* Create a page_pool and register it with rxq */
+	pool_size =  wq_sz << prq->wqe.info.log_num_frags;
+	pagepool_params.order		= XSC_RX_FRAG_SZ_ORDER;
+	/* No-internal DMA mapping in page_pool */
+	pagepool_params.flags		= 0;
+	pagepool_params.pool_size	= pool_size;
+	pagepool_params.nid		= cpu_to_node(c->cpu);
+	pagepool_params.dev		= c->adapter->dev;
+	pagepool_params.dma_dir	= prq->buff.map_dir;
+
+	prq->page_pool = page_pool_create(&pagepool_params);
+	if (IS_ERR(prq->page_pool)) {
+		ret = PTR_ERR(prq->page_pool);
+		prq->page_pool = NULL;
+		goto err_free_di_list;
+	}
+
+	if (c->chl_idx == 0)
+		netdev_dbg(adapter->netdev,
+			   "page pool: size=%d, cpu=%d, pool_numa=%d, mtu=%d, wqe_numa=%d\n",
+			   pool_size, c->cpu, pagepool_params.nid,
+			   adapter->nic_param.mtu,
+			   prq_param->wq.buf_numa_node);
+
+	for (i = 0; i < wq_sz; i++) {
+		struct xsc_eth_rx_wqe_cyc *wqe =
+			xsc_wq_cyc_get_wqe(&prq->wqe.wq, i);
+
+		for (f = 0; f < prq->wqe.info.num_frags; f++) {
+			u32 frag_size = prq->wqe.info.arr[f].frag_size;
+			u32 val = 0;
+
+			val |= FIELD_PREP(XSC_WQE_DATA_SEG_SEG_LEN_MASK,
+					  frag_size);
+			wqe->data[f].data0 = cpu_to_le32(val);
+			wqe->data[f].mkey = cpu_to_le32(XSC_INVALID_LKEY);
+		}
+
+		for (; f < prq->wqe.info.frags_max_num; f++) {
+			wqe->data[f].data0 = 0;
+			wqe->data[f].mkey = cpu_to_le32(XSC_INVALID_LKEY);
+			wqe->data[f].va = 0;
+		}
+	}
+
+	prq->post_wqes = xsc_eth_post_rx_wqes;
+	prq->handle_rx_cqe = xsc_eth_handle_rx_cqe;
+	prq->dealloc_wqe = xsc_eth_dealloc_rx_wqe;
+	prq->wqe.skb_from_cqe = xsc_rx_is_linear_skb(adapter->nic_param.mtu) ?
+					xsc_skb_from_cqe_linear :
+					xsc_skb_from_cqe_nonlinear;
+	prq->ix = c->chl_idx;
+	prq->frags_sz = adapter->nic_param.rq_frags_size;
+
+	return 0;
+
+err_free_di_list:
+	xsc_eth_free_di_list(prq);
+err_free_frags:
+	kvfree(prq->wqe.frags);
+err_destroy_wq:
+	xsc_eth_wq_destroy(&prq->wq_ctrl);
+	return ret;
+}
+
+static void xsc_free_qp_rq(struct xsc_rq *rq)
+{
+	kvfree(rq->wqe.frags);
+	kvfree(rq->wqe.di);
+
+	if (rq->page_pool)
+		page_pool_destroy(rq->page_pool);
+
+	xsc_eth_wq_destroy(&rq->wq_ctrl);
+}
+
+static int xsc_eth_open_rss_qp_rqs(struct xsc_adapter *adapter,
+				   struct xsc_rq_param *prq_param,
+				   struct xsc_eth_channels *chls,
+				   unsigned int num_chl)
+{
+	u8 q_log_size = prq_param->rq_attr.q_log_size;
+	struct xsc_create_multiqp_mbox_in *in;
+	struct xsc_create_qp_request *req;
+	unsigned int hw_npages;
+	struct xsc_channel *c;
+	int ret = 0, err = 0;
+	struct xsc_rq *prq;
+	int paslen = 0;
+	int entry_len;
+	u32 rqn_base;
+	int i, j, n;
+	int inlen;
+
+	for (i = 0; i < num_chl; i++) {
+		c = &chls->c[i];
+
+		for (j = 0; j < c->qp.rq_num; j++) {
+			prq = &c->qp.rq[j];
+			ret = xsc_eth_alloc_rq(c, prq, prq_param);
+			if (ret)
+				goto err_alloc_rqs;
+
+			hw_npages = DIV_ROUND_UP(prq->wq_ctrl.buf.size,
+						 PAGE_SIZE_4K);
+			/*support different npages number smoothly*/
+			entry_len = sizeof(struct xsc_create_qp_request) +
+				sizeof(__be64) * hw_npages;
+
+			paslen += entry_len;
+		}
+	}
+
+	inlen = sizeof(struct xsc_create_multiqp_mbox_in) + paslen;
+	in = kvzalloc(inlen, GFP_KERNEL);
+	if (!in) {
+		ret = -ENOMEM;
+		goto err_create_rss_rqs;
+	}
+
+	in->qp_num = cpu_to_be16(num_chl);
+	in->qp_type = XSC_QUEUE_TYPE_RAW;
+	in->req_len = cpu_to_be32(inlen);
+
+	req = (struct xsc_create_qp_request *)&in->data[0];
+	n = 0;
+	for (i = 0; i < num_chl; i++) {
+		c = &chls->c[i];
+		for (j = 0; j < c->qp.rq_num; j++) {
+			prq = &c->qp.rq[j];
+
+			hw_npages = DIV_ROUND_UP(prq->wq_ctrl.buf.size,
+						 PAGE_SIZE_4K);
+			/* no use for eth */
+			req->input_qpn = cpu_to_be16(0);
+			req->qp_type = XSC_QUEUE_TYPE_RAW;
+			req->log_rq_sz = ilog2(adapter->xdev->caps.recv_ds_num)
+						+ q_log_size;
+			req->pa_num = cpu_to_be16(hw_npages);
+			req->cqn_recv = cpu_to_be16(prq->cq.xcq.cqn);
+			req->cqn_send = req->cqn_recv;
+			req->glb_funcid =
+				cpu_to_be16(adapter->xdev->glb_func_id);
+
+			xsc_core_fill_page_frag_array(&prq->wq_ctrl.buf,
+						      &req->pas[0],
+						      hw_npages);
+			n++;
+			req = (struct xsc_create_qp_request *)
+				(&in->data[0] + entry_len * n);
+		}
+	}
+
+	ret = xsc_core_eth_create_rss_qp_rqs(adapter->xdev, in, inlen,
+					     &rqn_base);
+	kvfree(in);
+	if (ret)
+		goto err_create_rss_rqs;
+
+	n = 0;
+	for (i = 0; i < num_chl; i++) {
+		c = &chls->c[i];
+		for (j = 0; j < c->qp.rq_num; j++) {
+			prq = &c->qp.rq[j];
+			prq->rqn = rqn_base + n;
+			prq->cqp.qpn = prq->rqn;
+			prq->cqp.event = xsc_eth_qp_event;
+			prq->cqp.eth_queue_type = XSC_RES_RQ;
+			ret = xsc_core_create_resource_common(adapter->xdev,
+							      &prq->cqp);
+			if (ret) {
+				err = ret;
+				netdev_err(adapter->netdev,
+					   "create resource common error qp:%d errno:%d\n",
+					   prq->rqn, ret);
+				continue;
+			}
+
+			n++;
+		}
+	}
+	if (err)
+		return err;
+
+	adapter->channels.rqn_base = rqn_base;
+	return 0;
+
+err_create_rss_rqs:
+	i = num_chl;
+err_alloc_rqs:
+	for (--i; i >= 0; i--) {
+		c = &chls->c[i];
+		for (j = 0; j < c->qp.rq_num; j++) {
+			prq = &c->qp.rq[j];
+			xsc_free_qp_rq(prq);
+		}
+	}
+	return ret;
+}
+
+static void xsc_eth_free_rx_wqe(struct xsc_rq *rq)
+{
+	struct xsc_wq_cyc *wq = &rq->wqe.wq;
+	u16 wqe_ix;
+
+	while (!xsc_wq_cyc_is_empty(wq)) {
+		wqe_ix = xsc_wq_cyc_get_tail(wq);
+		rq->dealloc_wqe(rq, wqe_ix);
+		xsc_wq_cyc_pop(wq);
+	}
+}
+
+static int xsc_eth_close_qp_rq(struct xsc_channel *c, struct xsc_rq *prq)
+{
+	struct xsc_core_device *xdev = c->adapter->xdev;
+	int ret;
+
+	xsc_core_destroy_resource_common(xdev, &prq->cqp);
+
+	ret = xsc_core_eth_destroy_qp(xdev, prq->cqp.qpn);
+	if (ret)
+		return ret;
+
+	xsc_eth_free_rx_wqe(prq);
+	xsc_free_qp_rq(prq);
+
+	return 0;
+}
+
+static void xsc_eth_close_channel(struct xsc_channel *c, bool free_rq)
+{
+	int i;
+
+	for (i = 0; i < c->qp.rq_num; i++) {
+		if (free_rq)
+			xsc_eth_close_qp_rq(c, &c->qp.rq[i]);
+		xsc_eth_close_cq(c, &c->qp.rq[i].cq);
+		memset(&c->qp.rq[i], 0, sizeof(struct xsc_rq));
+	}
+
+	for (i = 0; i < c->qp.sq_num; i++) {
+		xsc_eth_close_qp_sq(c, &c->qp.sq[i]);
+		xsc_eth_close_cq(c, &c->qp.sq[i].cq);
+	}
+
+	netif_napi_del(&c->napi);
+}
+
+static int xsc_eth_open_channels(struct xsc_adapter *adapter)
+{
+	struct xsc_eth_channels *chls = &adapter->channels;
+	struct xsc_core_device *xdev = adapter->xdev;
+	struct xsc_channel_param *chl_param;
+	bool free_rq = false;
+	int ret = 0;
+	int i;
+
+	chls->num_chl = adapter->nic_param.num_channels;
+	chls->c = kcalloc_node(chls->num_chl, sizeof(struct xsc_channel),
+			       GFP_KERNEL, xdev->numa_node);
+	if (!chls->c) {
+		ret = -ENOMEM;
+		goto err_out;
+	}
+
+	chl_param = kvzalloc(sizeof(*chl_param), GFP_KERNEL);
+	if (!chl_param) {
+		ret = -ENOMEM;
+		goto err_free_ch;
+	}
+
+	xsc_eth_build_channel_param(adapter, chl_param);
+
+	for (i = 0; i < chls->num_chl; i++) {
+		ret = xsc_eth_open_channel(adapter, i, &chls->c[i], chl_param);
+		if (ret)
+			goto err_close_channel;
+	}
+
+	ret = xsc_eth_open_rss_qp_rqs(adapter,
+				      &chl_param->rq_param,
+				      chls,
+				      chls->num_chl);
+	if (ret)
+		goto err_close_channel;
+	free_rq = true;
+
+	for (i = 0; i < chls->num_chl; i++)
+		napi_enable(&chls->c[i].napi);
+
+	/* flush cache to memory before interrupt and napi_poll running */
+	smp_wmb();
+
+	ret = xsc_eth_modify_qps(adapter, chls);
+	if (ret)
+		goto err_close_channel;
+
+	kvfree(chl_param);
+	return 0;
+
+err_close_channel:
+	for (--i; i >= 0; i--)
+		xsc_eth_close_channel(&chls->c[i], free_rq);
+
+	kvfree(chl_param);
+err_free_ch:
+	kfree(chls->c);
+err_out:
+	chls->num_chl = 0;
+	netdev_err(adapter->netdev, "failed to open %d channels, err=%d\n",
+		   chls->num_chl, ret);
+	return ret;
+}
+
+static void xsc_eth_close_channels(struct xsc_adapter *adapter)
+{
+	struct xsc_channel *c;
+	int i;
+
+	for (i = 0; i < adapter->channels.num_chl; i++) {
+		c = &adapter->channels.c[i];
+
+		xsc_eth_close_channel(c, true);
+	}
+
+	kfree(adapter->channels.c);
+	adapter->channels.num_chl = 0;
+}
+
+static void xsc_netdev_set_tcs(struct xsc_adapter *priv, u16 nch, u8 ntc)
+{
+	int tc;
+
+	netdev_reset_tc(priv->netdev);
+
+	if (ntc == 1)
+		return;
+
+	netdev_set_num_tc(priv->netdev, ntc);
+
+	/* Map netdev TCs to offset 0
+	 * We have our own UP to TXQ mapping for QoS
+	 */
+	for (tc = 0; tc < ntc; tc++)
+		netdev_set_tc_queue(priv->netdev, tc, nch, 0);
+}
+
+static void xsc_eth_build_tx2sq_maps(struct xsc_adapter *adapter)
+{
+	struct xsc_channel *c;
+	struct xsc_sq *psq;
+	int i, tc;
+
+	for (i = 0; i < adapter->channels.num_chl; i++) {
+		c = &adapter->channels.c[i];
+		for (tc = 0; tc < c->num_tc; tc++) {
+			psq = &c->qp.sq[tc];
+			adapter->txq2sq[psq->txq_ix] = psq;
+		}
+	}
+}
+
+static void xsc_eth_activate_txqsq(struct xsc_channel *c)
+{
+	int tc = c->num_tc;
+	struct xsc_sq *psq;
+
+	for (tc = 0; tc < c->num_tc; tc++) {
+		psq = &c->qp.sq[tc];
+		psq->txq = netdev_get_tx_queue(psq->channel->netdev,
+					       psq->txq_ix);
+		set_bit(XSC_ETH_SQ_STATE_ENABLED, &psq->state);
+		netdev_tx_reset_queue(psq->txq);
+		netif_tx_start_queue(psq->txq);
+	}
+}
+
+static void xsc_eth_deactivate_txqsq(struct xsc_channel *c)
+{
+	int tc = c->num_tc;
+	struct xsc_sq *psq;
+
+	for (tc = 0; tc < c->num_tc; tc++) {
+		psq = &c->qp.sq[tc];
+		clear_bit(XSC_ETH_SQ_STATE_ENABLED, &psq->state);
+	}
+}
+
+static void xsc_activate_rq(struct xsc_channel *c)
+{
+	int i;
+
+	for (i = 0; i < c->qp.rq_num; i++)
+		set_bit(XSC_ETH_RQ_STATE_ENABLED, &c->qp.rq[i].state);
+}
+
+static void xsc_deactivate_rq(struct xsc_channel *c)
+{
+	int i;
+
+	for (i = 0; i < c->qp.rq_num; i++)
+		clear_bit(XSC_ETH_RQ_STATE_ENABLED, &c->qp.rq[i].state);
+}
+
+static void xsc_eth_activate_channel(struct xsc_channel *c)
+{
+	xsc_eth_activate_txqsq(c);
+	xsc_activate_rq(c);
+}
+
+static void xsc_eth_deactivate_channel(struct xsc_channel *c)
+{
+	xsc_deactivate_rq(c);
+	xsc_eth_deactivate_txqsq(c);
+}
+
+static void xsc_eth_activate_channels(struct xsc_eth_channels *chs)
+{
+	int i;
+
+	for (i = 0; i < chs->num_chl; i++)
+		xsc_eth_activate_channel(&chs->c[i]);
+}
+
+static void xsc_eth_deactivate_channels(struct xsc_eth_channels *chs)
+{
+	int i;
+
+	for (i = 0; i < chs->num_chl; i++)
+		xsc_eth_deactivate_channel(&chs->c[i]);
+
+	/* Sync with all NAPIs to wait until they stop using queues. */
+	synchronize_net();
+
+	for (i = 0; i < chs->num_chl; i++)
+		/* last doorbell out */
+		napi_disable(&chs->c[i].napi);
+}
+
+static void xsc_eth_activate_priv_channels(struct xsc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+	int num_txqs;
+
+	num_txqs = adapter->channels.num_chl * adapter->nic_param.num_tc;
+	xsc_netdev_set_tcs(adapter,
+			   adapter->channels.num_chl,
+			   adapter->nic_param.num_tc);
+	netif_set_real_num_tx_queues(netdev, num_txqs);
+	netif_set_real_num_rx_queues(netdev, adapter->channels.num_chl);
+
+	xsc_eth_build_tx2sq_maps(adapter);
+	xsc_eth_activate_channels(&adapter->channels);
+	netif_tx_start_all_queues(adapter->netdev);
+}
+
+static void xsc_eth_deactivate_priv_channels(struct xsc_adapter *adapter)
+{
+	netif_tx_disable(adapter->netdev);
+	xsc_eth_deactivate_channels(&adapter->channels);
+}
+
+static int xsc_eth_sw_init(struct xsc_adapter *adapter)
+{
+	int ret;
+
+	ret = xsc_eth_open_channels(adapter);
+	if (ret)
+		return ret;
+
+	xsc_eth_activate_priv_channels(adapter);
+
+	return 0;
+}
+
+static void xsc_eth_sw_deinit(struct xsc_adapter *adapter)
+{
+	xsc_eth_deactivate_priv_channels(adapter);
+
+	return xsc_eth_close_channels(adapter);
+}
+
+static bool xsc_eth_get_link_status(struct xsc_adapter *adapter)
+{
+	struct xsc_core_device *xdev = adapter->xdev;
+	u16 vport = 0;
+	bool link_up;
+
+	link_up = xsc_core_query_vport_state(xdev, vport);
+
+	return link_up ? true : false;
+}
+
+static int xsc_eth_change_link_status(struct xsc_adapter *adapter)
+{
+	bool link_up;
+
+	link_up = xsc_eth_get_link_status(adapter);
+
+	if (link_up && !netif_carrier_ok(adapter->netdev)) {
+		netdev_info(adapter->netdev, "Link up\n");
+		netif_carrier_on(adapter->netdev);
+	} else if (!link_up && netif_carrier_ok(adapter->netdev)) {
+		netdev_info(adapter->netdev, "Link down\n");
+		netif_carrier_off(adapter->netdev);
+	}
+
+	return 0;
+}
+
+static void xsc_eth_event_work(struct work_struct *work)
+{
+	struct xsc_adapter *adapter = container_of(work,
+						   struct xsc_adapter,
+						   event_work);
+	struct xsc_event_query_type_mbox_out out;
+	struct xsc_event_query_type_mbox_in in;
+	int err;
+
+	if (adapter->status != XSCALE_ETH_DRIVER_OK)
+		return;
+
+	/*query cmd_type cmd*/
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_EVENT_TYPE);
+
+	err = xsc_cmd_exec(adapter->xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status) {
+		netdev_err(adapter->netdev, "failed to query event type, err=%d, status=%d\n",
+			   err, out.hdr.status);
+		goto err_out;
+	}
+
+	switch (out.ctx.resp_cmd_type) {
+	case XSC_CMD_EVENT_RESP_CHANGE_LINK:
+		err = xsc_eth_change_link_status(adapter);
+		if (err) {
+			netdev_err(adapter->netdev, "failed to change linkstatus, err=%d\n",
+				   err);
+			goto err_out;
+		}
+		break;
+	case XSC_CMD_EVENT_RESP_TEMP_WARN:
+		netdev_err(adapter->netdev, "[Minor]nic chip temperature high warning\n");
+		break;
+	case XSC_CMD_EVENT_RESP_OVER_TEMP_PROTECTION:
+		netdev_err(adapter->netdev, "[Critical]nic chip was over-temperature\n");
+		break;
+	default:
+		break;
+	}
+
+err_out:
+	return;
+}
+
+static void xsc_eth_event_handler(void *arg)
+{
+	struct xsc_adapter *adapter = (struct xsc_adapter *)arg;
+
+	queue_work(adapter->workq, &adapter->event_work);
+}
+
+static bool xsc_get_pct_drop_config(struct xsc_core_device *xdev)
+{
+	return (xdev->pdev->device == XSC_MC_PF_DEV_ID) ||
+		(xdev->pdev->device == XSC_MF_SOC_PF_DEV_ID) ||
+		(xdev->pdev->device == XSC_MS_PF_DEV_ID) ||
+		(xdev->pdev->device == XSC_MV_SOC_PF_DEV_ID);
+}
+
+static int xsc_eth_enable_nic_hca(struct xsc_adapter *adapter)
+{
+	struct xsc_cmd_enable_nic_hca_mbox_out out = {};
+	struct xsc_cmd_enable_nic_hca_mbox_in in = {};
+	struct xsc_core_device *xdev = adapter->xdev;
+	struct net_device *netdev = adapter->netdev;
+	u16 caps_mask = 0;
+	u16 caps = 0;
+	int err;
+
+	if (xsc_get_user_mode(xdev))
+		return 0;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_ENABLE_NIC_HCA);
+
+	in.rss.rss_en = 1;
+	in.rss.rqn_base = cpu_to_be16(adapter->channels.rqn_base -
+				xdev->caps.raweth_rss_qp_id_base);
+	in.rss.rqn_num = cpu_to_be16(adapter->channels.num_chl);
+	in.rss.hash_tmpl = cpu_to_be32(adapter->rss_param.rss_hash_tmpl);
+	in.rss.hfunc = xsc_hash_func_type(adapter->rss_param.hfunc);
+	caps_mask |= BIT(XSC_TBM_CAP_RSS);
+
+	if (netdev->features & NETIF_F_RXCSUM)
+		caps |= BIT(XSC_TBM_CAP_HASH_PPH);
+	caps_mask |= BIT(XSC_TBM_CAP_HASH_PPH);
+
+	if (xsc_get_pct_drop_config(xdev) && !(netdev->flags & IFF_SLAVE))
+		caps |= BIT(XSC_TBM_CAP_PCT_DROP_CONFIG);
+	caps_mask |= BIT(XSC_TBM_CAP_PCT_DROP_CONFIG);
+
+	memcpy(in.nic.mac_addr, netdev->dev_addr, ETH_ALEN);
+
+	in.nic.caps = cpu_to_be16(caps);
+	in.nic.caps_mask = cpu_to_be16(caps_mask);
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status) {
+		netdev_err(netdev, "failed!! err=%d, status=%d\n",
+			   err, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	return 0;
+}
+
+static int xsc_eth_disable_nic_hca(struct xsc_adapter *adapter)
 {
+	struct xsc_cmd_disable_nic_hca_mbox_out out = {};
+	struct xsc_cmd_disable_nic_hca_mbox_in in = {};
+	struct xsc_core_device *xdev = adapter->xdev;
+	struct net_device *netdev = adapter->netdev;
+	u16 caps = 0;
+	int err;
+
+	if (xsc_get_user_mode(xdev))
+		return 0;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_DISABLE_NIC_HCA);
+
+	if (xsc_get_pct_drop_config(xdev) &&
+	    !(netdev->priv_flags & IFF_BONDING))
+		caps |= BIT(XSC_TBM_CAP_PCT_DROP_CONFIG);
+
+	in.nic.caps = cpu_to_be16(caps);
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status) {
+		netdev_err(netdev, "failed!! err=%d, status=%d\n",
+			   err, out.hdr.status);
+		return -ENOEXEC;
+	}
+
 	return 0;
 }
 
+static void xsc_set_default_xps_cpumasks(struct xsc_adapter *priv,
+					 struct xsc_eth_params *params)
+{
+	struct xsc_core_device *xdev = priv->xdev;
+	int num_comp_vectors, irq;
+
+	num_comp_vectors = priv->nic_param.comp_vectors;
+	cpumask_clear(xdev->xps_cpumask);
+
+	for (irq = 0; irq < num_comp_vectors; irq++) {
+		cpumask_set_cpu(cpumask_local_spread(irq, xdev->numa_node),
+				xdev->xps_cpumask);
+		netif_set_xps_queue(priv->netdev, xdev->xps_cpumask, irq);
+	}
+}
+
+static int xsc_set_port_admin_status(struct xsc_adapter *adapter,
+				     enum xsc_port_status status)
+{
+	struct xsc_event_set_port_admin_status_mbox_out out;
+	struct xsc_event_set_port_admin_status_mbox_in in;
+	int ret = 0;
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_SET_PORT_ADMIN_STATUS);
+	in.status = cpu_to_be16(status);
+
+	ret = xsc_cmd_exec(adapter->xdev, &in, sizeof(in), &out, sizeof(out));
+	if (ret || out.hdr.status) {
+		netdev_err(adapter->netdev, "failed to set port admin status, err=%d, status=%d\n",
+			   ret, out.hdr.status);
+		return -ENOEXEC;
+	}
+
+	return ret;
+}
+
+static int xsc_eth_open(struct net_device *netdev)
+{
+	struct xsc_adapter *adapter = netdev_priv(netdev);
+	struct xsc_core_device *xdev = adapter->xdev;
+	int ret = 0;
+
+	mutex_lock(&adapter->status_lock);
+	if (adapter->status == XSCALE_ETH_DRIVER_OK) {
+		netdev_err(adapter->netdev, "unnormal ndo_open when status=%d\n",
+			   adapter->status);
+		goto out;
+	}
+
+	ret = xsc_eth_sw_init(adapter);
+	if (ret)
+		goto out;
+
+	ret = xsc_eth_enable_nic_hca(adapter);
+	if (ret)
+		goto err_sw_deinit;
+
+	/*INIT_WORK*/
+	INIT_WORK(&adapter->event_work, xsc_eth_event_work);
+	xdev->event_handler = xsc_eth_event_handler;
+
+	if (xsc_eth_get_link_status(adapter))	{
+		netdev_info(netdev, "Link up\n");
+		netif_carrier_on(adapter->netdev);
+	} else {
+		netdev_info(netdev, "Link down\n");
+	}
+
+	adapter->status = XSCALE_ETH_DRIVER_OK;
+
+	xsc_set_default_xps_cpumasks(adapter, &adapter->nic_param);
+
+	xsc_set_port_admin_status(adapter, XSC_PORT_UP);
+
+err_sw_deinit:
+	xsc_eth_sw_deinit(adapter);
+out:
+	mutex_unlock(&adapter->status_lock);
+	return ret;
+}
+
+static int xsc_eth_close(struct net_device *netdev)
+{
+	struct xsc_adapter *adapter = netdev_priv(netdev);
+	int ret = 0;
+
+	mutex_lock(&adapter->status_lock);
+
+	if (!netif_device_present(netdev)) {
+		ret = -ENODEV;
+		goto out;
+	}
+
+	if (adapter->status != XSCALE_ETH_DRIVER_OK)
+		goto out;
+
+	adapter->status = XSCALE_ETH_DRIVER_CLOSE;
+
+	netif_carrier_off(adapter->netdev);
+
+	xsc_eth_sw_deinit(adapter);
+
+	ret = xsc_eth_disable_nic_hca(adapter);
+	if (ret)
+		netdev_err(adapter->netdev, "failed to disable nic hca, err=%d\n",
+			   ret);
+
+	xsc_set_port_admin_status(adapter, XSC_PORT_DOWN);
+
+out:
+	mutex_unlock(&adapter->status_lock);
+
+	return ret;
+}
+
 static int xsc_eth_set_hw_mtu(struct xsc_core_device *xdev,
 			      u16 mtu, u16 rx_buf_sz)
 {
@@ -161,7 +1690,8 @@ static int xsc_eth_set_hw_mtu(struct xsc_core_device *xdev,
 }
 
 static const struct net_device_ops xsc_netdev_ops = {
-	/* TBD */
+	.ndo_open		= xsc_eth_open,
+	.ndo_stop		= xsc_eth_close,
 };
 
 static void xsc_eth_build_nic_netdev(struct xsc_adapter *adapter)
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
index f5c1e3ead5402..d9316615b4f5c 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
@@ -9,6 +9,10 @@
 #include "common/xsc_device.h"
 #include "xsc_eth_common.h"
 
+#define XSC_INVALID_LKEY	0x100
+
+#define XSCALE_DRIVER_NAME "xsc_eth"
+
 enum {
 	XSCALE_ETH_DRIVER_INIT,
 	XSCALE_ETH_DRIVER_OK,
@@ -34,7 +38,9 @@ struct xsc_adapter {
 	struct xsc_rss_params	rss_param;
 
 	struct workqueue_struct	*workq;
+	struct work_struct	event_work;
 
+	struct xsc_eth_channels	channels;
 	struct xsc_sq		**txq2sq;
 
 	u32			status;
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
index da17c16ad92e3..e6204d0fa9ca1 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
@@ -6,6 +6,7 @@
 #ifndef __XSC_ETH_COMMON_H
 #define __XSC_ETH_COMMON_H
 
+#include "xsc_queue.h"
 #include "xsc_pph.h"
 
 #define SW_MIN_MTU		ETH_MIN_MTU
@@ -21,12 +22,129 @@
 #define XSC_SW2HW_RX_PKT_LEN(mtu)	\
 	((mtu) + ETH_HLEN + XSC_ETH_RX_MAX_HEAD_ROOM)
 
+#define XSC_QPN_SQN_STUB		1025
+#define XSC_QPN_RQN_STUB		1024
+
 #define XSC_LOG_INDIR_RQT_SIZE		0x8
 
 #define XSC_INDIR_RQT_SIZE		BIT(XSC_LOG_INDIR_RQT_SIZE)
 #define XSC_ETH_MIN_NUM_CHANNELS	2
 #define XSC_ETH_MAX_NUM_CHANNELS	XSC_INDIR_RQT_SIZE
 
+#define XSC_TX_NUM_TC			1
+#define XSC_MAX_NUM_TC			8
+#define XSC_ETH_MAX_TC_TOTAL	\
+	(XSC_ETH_MAX_NUM_CHANNELS * XSC_MAX_NUM_TC)
+#define XSC_ETH_MAX_QP_NUM_PER_CH	(XSC_MAX_NUM_TC + 1)
+
+#define XSC_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+#define XSC_RQCQ_ELE_SZ		32
+#define XSC_SQCQ_ELE_SZ		32
+#define XSC_RQ_ELE_SZ		XSC_RECV_WQE_BB
+#define XSC_SQ_ELE_SZ		XSC_SEND_WQE_BB
+#define XSC_EQ_ELE_SZ		8
+
+#define XSC_SKB_FRAG_SZ(len)	(SKB_DATA_ALIGN(len) +	\
+				SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+#define XSC_MIN_SKB_FRAG_SZ	(XSC_SKB_FRAG_SZ(XSC_RX_HEADROOM))
+#define XSC_LOG_MAX_RX_WQE_BULK	\
+	(ilog2(PAGE_SIZE / roundup_pow_of_two(XSC_MIN_SKB_FRAG_SZ)))
+
+#define XSC_MIN_LOG_RQ_SZ		(1 + XSC_LOG_MAX_RX_WQE_BULK)
+#define XSC_DEF_LOG_RQ_SZ		0xa
+#define XSC_MAX_LOG_RQ_SZ		0xd
+
+#define XSC_MIN_LOG_SQ_SZ		0x6
+#define XSC_DEF_LOG_SQ_SZ		0xa
+#define XSC_MAX_LOG_SQ_SZ		0xd
+
+/* DS num */
+#define XSC_SQ_ELE_NUM_DEF	BIT(XSC_DEF_LOG_SQ_SZ)
+#define XSC_RQ_ELE_NUM_DEF	BIT(XSC_DEF_LOG_RQ_SZ)
+
+#define XSC_LOG_RQCQ_SZ		0xb
+#define XSC_LOG_SQCQ_SZ		0xa
+
+#define XSC_RQCQ_ELE_NUM	BIT(XSC_LOG_RQCQ_SZ)
+#define XSC_SQCQ_ELE_NUM	BIT(XSC_LOG_SQCQ_SZ)
+#define XSC_RQ_ELE_NUM		XSC_RQ_ELE_NUM_DEF
+#define XSC_SQ_ELE_NUM		XSC_SQ_ELE_NUM_DEF
+#define XSC_EQ_ELE_NUM		XSC_SQ_ELE_NUM_DEF
+
+enum xsc_port_status {
+	XSC_PORT_DOWN      = 0,
+	XSC_PORT_UP        = 1,
+};
+
+enum xsc_queue_type {
+	XSC_QUEUE_TYPE_EQ = 0,
+	XSC_QUEUE_TYPE_RQCQ,
+	XSC_QUEUE_TYPE_SQCQ,
+	XSC_QUEUE_TYPE_RQ,
+	XSC_QUEUE_TYPE_SQ,
+	XSC_QUEUE_TYPE_MAX,
+};
+
+struct xsc_queue_attr {
+	u8  q_type;
+	u32 ele_num;
+	u32 ele_size;
+	u8  ele_log_size;
+	u8  q_log_size;
+};
+
+struct xsc_eth_rx_wqe_cyc {
+	DECLARE_FLEX_ARRAY(struct xsc_wqe_data_seg, data);
+};
+
+struct xsc_eq_param {
+	struct xsc_queue_attr eq_attr;
+};
+
+struct xsc_cq_param {
+	struct xsc_wq_param wq;
+	struct cq_cmd {
+		u8 abc[16];
+	} cqc;
+	struct xsc_queue_attr cq_attr;
+};
+
+struct xsc_rq_param {
+	struct xsc_wq_param wq;
+	struct xsc_queue_attr rq_attr;
+	struct xsc_rq_frags_info frags_info;
+};
+
+struct xsc_sq_param {
+	struct xsc_wq_param wq;
+	struct xsc_queue_attr sq_attr;
+};
+
+struct xsc_qp_param {
+	struct xsc_queue_attr qp_attr;
+};
+
+struct xsc_channel_param {
+	struct xsc_cq_param rqcq_param;
+	struct xsc_cq_param sqcq_param;
+	struct xsc_rq_param rq_param;
+	struct xsc_sq_param sq_param;
+	struct xsc_qp_param qp_param;
+};
+
+struct xsc_eth_qp {
+	u16 rq_num;
+	u16 sq_num;
+	struct xsc_rq rq[XSC_MAX_NUM_TC]; /*may be use one only*/
+	struct xsc_sq sq[XSC_MAX_NUM_TC]; /*reserved to tc*/
+};
+
+enum channel_flags {
+	XSC_CHANNEL_NAPI_SCHED = 1,
+};
+
 struct xsc_eth_params {
 	u16	num_channels;
 	u16	max_num_ch;
@@ -43,4 +161,28 @@ struct xsc_eth_params {
 	u32	pflags;
 };
 
+struct xsc_channel {
+	/* data path */
+	struct xsc_eth_qp	qp;
+	struct napi_struct	napi;
+	u8			num_tc;
+	int			chl_idx;
+
+	/*relationship*/
+	struct xsc_adapter	*adapter;
+	struct net_device	*netdev;
+	int			cpu;
+	unsigned long		flags;
+
+	/* data path - accessed per napi poll */
+	const struct cpumask	*aff_mask;
+	struct irq_desc		*irq_desc;
+} ____cacheline_aligned_in_smp;
+
+struct xsc_eth_channels {
+	struct xsc_channel	*c;
+	unsigned int		num_chl;
+	u32			rqn_base;
+};
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
new file mode 100644
index 0000000000000..e8a22f32283b9
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd. All
+ * rights reserved.
+ * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved.
+ */
+
+#include "xsc_eth_txrx.h"
+
+struct sk_buff *xsc_skb_from_cqe_linear(struct xsc_rq *rq,
+					struct xsc_wqe_frag_info *wi,
+					u32 cqe_bcnt, u8 has_pph)
+{
+	/* TBD */
+	return NULL;
+}
+
+struct sk_buff *xsc_skb_from_cqe_nonlinear(struct xsc_rq *rq,
+					   struct xsc_wqe_frag_info *wi,
+					   u32 cqe_bcnt, u8 has_pph)
+{
+	/* TBD */
+	return NULL;
+}
+
+void xsc_eth_handle_rx_cqe(struct xsc_cqwq *cqwq,
+			   struct xsc_rq *rq, struct xsc_cqe *cqe)
+{
+	/* TBD */
+}
+
+int xsc_poll_rx_cq(struct xsc_cq *cq, int budget)
+{
+	/* TBD */
+	return 0;
+}
+
+void xsc_eth_dealloc_rx_wqe(struct xsc_rq *rq, u16 ix)
+{
+	/* TBD */
+}
+
+bool xsc_eth_post_rx_wqes(struct xsc_rq *rq)
+{
+	/* TBD */
+	return true;
+}
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
new file mode 100644
index 0000000000000..5d1fcb669ddd8
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
@@ -0,0 +1,100 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include "xsc_eth_common.h"
+#include "xsc_eth_txrx.h"
+
+void xsc_cq_notify_hw_rearm(struct xsc_cq *cq)
+{
+	u32 db_val = 0;
+
+	db_val |= FIELD_PREP(XSC_CQ_DB_NEXT_CID_MASK, cq->wq.cc) |
+		  FIELD_PREP(XSC_CQ_DB_CQ_ID_MASK, cq->xcq.cqn);
+
+	/* ensure doorbell record is visible to device
+	 * before ringing the doorbell
+	 */
+	wmb();
+	writel(db_val, XSC_REG_ADDR(cq->xdev, cq->xdev->regs.complete_db));
+}
+
+void xsc_cq_notify_hw(struct xsc_cq *cq)
+{
+	struct xsc_core_device *xdev  = cq->xdev;
+	u32 db_val = 0;
+
+	db_val |= FIELD_PREP(XSC_CQ_DB_NEXT_CID_MASK, cq->wq.cc) |
+		  FIELD_PREP(XSC_CQ_DB_CQ_ID_MASK, cq->xcq.cqn);
+
+	/* ensure doorbell record is visible to device
+	 * before ringing the doorbell
+	 */
+	wmb();
+	writel(db_val, XSC_REG_ADDR(xdev, xdev->regs.complete_reg));
+}
+
+static bool xsc_channel_no_affinity_change(struct xsc_channel *c)
+{
+	int current_cpu = smp_processor_id();
+
+	return cpumask_test_cpu(current_cpu, c->aff_mask);
+}
+
+static bool xsc_poll_tx_cq(struct xsc_cq *cq, int napi_budget)
+{
+	/* TBD */
+	return true;
+}
+
+int xsc_eth_napi_poll(struct napi_struct *napi, int budget)
+{
+	struct xsc_channel *c = container_of(napi, struct xsc_channel, napi);
+	struct xsc_eth_params *params = &c->adapter->nic_param;
+	struct xsc_rq *rq = &c->qp.rq[0];
+	struct xsc_sq *sq = NULL;
+	bool busy = false;
+	int work_done = 0;
+	int tx_budget = 0;
+	int i;
+
+	rcu_read_lock();
+
+	clear_bit(XSC_CHANNEL_NAPI_SCHED, &c->flags);
+
+	tx_budget = params->sq_size >> 2;
+	for (i = 0; i < c->num_tc; i++)
+		busy |= xsc_poll_tx_cq(&c->qp.sq[i].cq, tx_budget);
+
+	/* budget=0 means: don't poll rx rings */
+	if (likely(budget)) {
+		work_done = xsc_poll_rx_cq(&rq->cq, budget);
+		busy |= work_done == budget;
+	}
+
+	busy |= rq->post_wqes(rq);
+
+	if (busy) {
+		if (likely(xsc_channel_no_affinity_change(c))) {
+			rcu_read_unlock();
+			return budget;
+		}
+		if (budget && work_done == budget)
+			work_done--;
+	}
+
+	if (unlikely(!napi_complete_done(napi, work_done)))
+		goto err_out;
+
+	for (i = 0; i < c->num_tc; i++) {
+		sq = &c->qp.sq[i];
+		xsc_cq_notify_hw_rearm(&sq->cq);
+	}
+
+	xsc_cq_notify_hw_rearm(&rq->cq);
+err_out:
+	rcu_read_unlock();
+	return work_done;
+}
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
new file mode 100644
index 0000000000000..116019a9abbd8
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_RXTX_H
+#define __XSC_RXTX_H
+
+#include "xsc_eth.h"
+
+void xsc_cq_notify_hw_rearm(struct xsc_cq *cq);
+void xsc_cq_notify_hw(struct xsc_cq *cq);
+int xsc_eth_napi_poll(struct napi_struct *napi, int budget);
+bool xsc_eth_post_rx_wqes(struct xsc_rq *rq);
+void xsc_eth_handle_rx_cqe(struct xsc_cqwq *cqwq,
+			   struct xsc_rq *rq, struct xsc_cqe *cqe);
+void xsc_eth_dealloc_rx_wqe(struct xsc_rq *rq, u16 ix);
+struct sk_buff *xsc_skb_from_cqe_linear(struct xsc_rq *rq,
+					struct xsc_wqe_frag_info *wi,
+					u32 cqe_bcnt, u8 has_pph);
+struct sk_buff *xsc_skb_from_cqe_nonlinear(struct xsc_rq *rq,
+					   struct xsc_wqe_frag_info *wi,
+					   u32 cqe_bcnt, u8 has_pph);
+int xsc_poll_rx_cq(struct xsc_cq *cq, int budget);
+
+#endif /* XSC_RXTX_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
index 223d4873dd169..643b2c759c613 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
@@ -8,7 +8,155 @@
 #ifndef __XSC_QUEUE_H
 #define __XSC_QUEUE_H
 
+#include <net/page_pool/types.h>
+#include <net/page_pool/helpers.h>
+
 #include "common/xsc_core.h"
+#include "xsc_eth_wq.h"
+
+enum {
+	XSC_SEND_WQE_DS	= 16,
+	XSC_SEND_WQE_BB	= 64,
+};
+
+enum {
+	XSC_RECV_WQE_DS	= 16,
+	XSC_RECV_WQE_BB	= 16,
+};
+
+enum {
+	XSC_ETH_RQ_STATE_ENABLED,
+	XSC_ETH_RQ_STATE_AM,
+	XSC_ETH_RQ_STATE_CACHE_REDUCE_PENDING,
+};
+
+#define XSC_SEND_WQEBB_NUM_DS	        (XSC_SEND_WQE_BB / XSC_SEND_WQE_DS)
+#define XSC_LOG_SEND_WQEBB_NUM_DS	ilog2(XSC_SEND_WQEBB_NUM_DS)
+
+#define XSC_RECV_WQEBB_NUM_DS	        (XSC_RECV_WQE_BB / XSC_RECV_WQE_DS)
+#define XSC_LOG_RECV_WQEBB_NUM_DS	ilog2(XSC_RECV_WQEBB_NUM_DS)
+
+/* each ds holds one fragment in skb */
+#define XSC_MAX_RX_FRAGS        4
+#define XSC_RX_FRAG_SZ_ORDER    0
+#define XSC_RX_FRAG_SZ          (PAGE_SIZE << XSC_RX_FRAG_SZ_ORDER)
+#define DEFAULT_FRAG_SIZE       (2048)
+
+enum {
+	XSC_ETH_SQ_STATE_ENABLED,
+	XSC_ETH_SQ_STATE_AM,
+};
+
+struct xsc_dma_info {
+	struct page	*page;
+	dma_addr_t	addr;
+};
+
+struct xsc_page_cache {
+	struct xsc_dma_info	*page_cache;
+	u32	head;
+	u32	tail;
+	u32	sz;
+	u32	resv;
+};
+
+struct xsc_cq {
+	/* data path - accessed per cqe */
+	struct xsc_cqwq	wq;
+
+	/* data path - accessed per napi poll */
+	u16			event_ctr;
+	struct napi_struct	*napi;
+	struct xsc_core_cq	xcq;
+	struct xsc_channel	*channel;
+
+	/* control */
+	struct xsc_core_device	*xdev;
+	struct xsc_wq_ctrl	wq_ctrl;
+	u8			rx;
+} ____cacheline_aligned_in_smp;
+
+struct xsc_wqe_frag_info {
+	struct xsc_dma_info *di;
+	u32 offset;
+	u8 last_in_page;
+	u8 is_available;
+};
+
+struct xsc_rq_frag_info {
+	int frag_size;
+	int frag_stride;
+};
+
+struct xsc_rq_frags_info {
+	struct xsc_rq_frag_info arr[XSC_MAX_RX_FRAGS];
+	u8 num_frags;
+	u8 log_num_frags;
+	u8 wqe_bulk;
+	u8 wqe_bulk_min;
+	u8 frags_max_num;
+};
+
+struct xsc_rq;
+typedef void (*xsc_fp_handle_rx_cqe)(struct xsc_cqwq *cqwq, struct xsc_rq *rq,
+				     struct xsc_cqe *cqe);
+typedef bool (*xsc_fp_post_rx_wqes)(struct xsc_rq *rq);
+typedef void (*xsc_fp_dealloc_wqe)(struct xsc_rq *rq, u16 ix);
+typedef struct sk_buff * (*xsc_fp_skb_from_cqe)(struct xsc_rq *rq,
+						struct xsc_wqe_frag_info *wi,
+						u32 cqe_bcnt,
+						u8 has_pph);
+
+struct xsc_rq {
+	struct xsc_core_qp		cqp;
+	struct {
+		struct xsc_wq_cyc	wq;
+		struct xsc_wqe_frag_info	*frags;
+		struct xsc_dma_info	*di;
+		struct xsc_rq_frags_info	info;
+		xsc_fp_skb_from_cqe	skb_from_cqe;
+	} wqe;
+
+	struct {
+		u16	headroom;
+		u8	map_dir;	/* dma map direction */
+	} buff;
+
+	struct page_pool	*page_pool;
+	struct xsc_wq_ctrl	wq_ctrl;
+	struct xsc_cq		cq;
+	u32	rqn;
+	int	ix;
+
+	unsigned long	state;
+	struct work_struct  recover_work;
+
+	u32 hw_mtu;
+	u32 frags_sz;
+
+	xsc_fp_handle_rx_cqe	handle_rx_cqe;
+	xsc_fp_post_rx_wqes	post_wqes;
+	xsc_fp_dealloc_wqe	dealloc_wqe;
+	struct xsc_page_cache	page_cache;
+} ____cacheline_aligned_in_smp;
+
+enum xsc_dma_map_type {
+	XSC_DMA_MAP_SINGLE,
+	XSC_DMA_MAP_PAGE
+};
+
+struct xsc_sq_dma {
+	dma_addr_t	addr;
+	u32		size;
+	enum xsc_dma_map_type	type;
+};
+
+struct xsc_tx_wqe_info {
+	struct sk_buff *skb;
+	u32 num_bytes;
+	u8  num_wqebbs;
+	u8  num_dma;
+};
 
 struct xsc_sq {
 	struct xsc_core_qp		cqp;
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
index ad0ecc122a794..e8c13c6fda463 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/Makefile
@@ -6,5 +6,5 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_PCI) += xsc_pci.o
 
-xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o pci_irq.o adev.o
+xsc_pci-y := main.o cmdq.o hw.o qp.o cq.o alloc.o eq.o pci_irq.o adev.o vport.o
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/pci/vport.c b/drivers/net/ethernet/yunsilicon/xsc/pci/vport.c
new file mode 100644
index 0000000000000..edac8a6bd39e4
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/pci/vport.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021 - 2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include "common/xsc_core.h"
+#include "common/xsc_driver.h"
+
+u8 xsc_core_query_vport_state(struct xsc_core_device *xdev, u16 vport)
+{
+	struct xsc_query_vport_state_out out;
+	struct xsc_query_vport_state_in in;
+	u32 val = 0;
+	int err;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+
+	in.hdr.opcode = cpu_to_be16(XSC_CMD_OP_QUERY_VPORT_STATE);
+	val |= FIELD_PREP(XSC_QUERY_VPORT_VPORT_NUM_MASK, vport);
+	if (vport)
+		val |= XSC_QUERY_VPORT_OTHER_VPORT;
+	in.data0 = cpu_to_be32(val);
+
+	err = xsc_cmd_exec(xdev, &in, sizeof(in), &out, sizeof(out));
+	if (err || out.hdr.status)
+		pci_err(xdev->pdev, "failed to query vport state, err=%d, status=%d\n",
+			err, out.hdr.status);
+
+	return out.state;
+}
+EXPORT_SYMBOL(xsc_core_query_vport_state);

From 0ff604135f95956f1de67de445be6be989ffd3a8 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:19 +0800
Subject: [PATCH 2602/2753] xsc: Add ndo_start_xmit

This patch adds core data transmission functionality, focusing
on the ndo_start_xmit interface. The main steps are:

1. Transmission Entry
The entry point selects the appropriate transmit queue (SQ) and
verifies hardware readiness before calling xsc_eth_xmit_frame
for packet transmission.
2. Packet Processing
Supports TCP/UDP GSO, calculates MSS and IHS.
If necessary, performs SKB linearization and handles checksum
offload. Maps data for DMA using dma_map_single and
skb_frag_dma_map.
3. Descriptor Generation
Constructs control (cseg) and data (dseg) segments, including
setting operation codes, segment counts, and DMA addresses.
Hardware Notification & Queue Management:
4. Notifies hardware using a doorbell register and manages
queue flow to avoid overloading.
5. Combines small packets using netdev_xmit_more to reduce
doorbell writes and supports zero-copy transmission for efficiency.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/yunsilicon/xsc/net/Makefile  |   2 +-
 .../net/ethernet/yunsilicon/xsc/net/main.c    |   1 +
 .../net/ethernet/yunsilicon/xsc/net/xsc_eth.h |   2 +
 .../yunsilicon/xsc/net/xsc_eth_common.h       |   8 +
 .../ethernet/yunsilicon/xsc/net/xsc_eth_tx.c  | 316 ++++++++++++++++++
 .../yunsilicon/xsc/net/xsc_eth_txrx.h         |  37 ++
 .../ethernet/yunsilicon/xsc/net/xsc_queue.h   |   7 +
 7 files changed, 372 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c

diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
index 104ef5330849c..7cfc2aaa2637a 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc_eth.o
 
-xsc_eth-y := main.o xsc_eth_wq.o xsc_eth_txrx.o xsc_eth_rx.o
+xsc_eth-y := main.o xsc_eth_wq.o xsc_eth_txrx.o xsc_eth_tx.o xsc_eth_rx.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/main.c b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
index 67e68a6f6318e..8d6bcb87fe121 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
@@ -1692,6 +1692,7 @@ static int xsc_eth_set_hw_mtu(struct xsc_core_device *xdev,
 static const struct net_device_ops xsc_netdev_ops = {
 	.ndo_open		= xsc_eth_open,
 	.ndo_stop		= xsc_eth_close,
+	.ndo_start_xmit		= xsc_eth_xmit_start,
 };
 
 static void xsc_eth_build_nic_netdev(struct xsc_adapter *adapter)
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
index d9316615b4f5c..27fcfcda4f2a1 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
@@ -6,6 +6,8 @@
 #ifndef __XSC_ETH_H
 #define __XSC_ETH_H
 
+#include <linux/udp.h>
+
 #include "common/xsc_device.h"
 #include "xsc_eth_common.h"
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
index e6204d0fa9ca1..7ab311a47069f 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
@@ -185,4 +185,12 @@ struct xsc_eth_channels {
 	u32			rqn_base;
 };
 
+union xsc_send_doorbell {
+	struct{
+		s32  next_pid : 16;
+		u32 qp_num : 15;
+	};
+	u32 send_data;
+};
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c
new file mode 100644
index 0000000000000..1acc1db353579
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c
@@ -0,0 +1,316 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include <linux/tcp.h>
+
+#include "xsc_eth.h"
+#include "xsc_eth_txrx.h"
+
+#define XSC_OPCODE_RAW 7
+
+static void xsc_dma_push(struct xsc_sq *sq, dma_addr_t addr, u32 size,
+			 enum xsc_dma_map_type map_type)
+{
+	struct xsc_sq_dma *dma = xsc_dma_get(sq, sq->dma_fifo_pc++);
+
+	dma->addr = addr;
+	dma->size = size;
+	dma->type = map_type;
+}
+
+static void xsc_dma_unmap_wqe(struct xsc_sq *sq, u8 num_dma)
+{
+	struct xsc_adapter *adapter = sq->channel->adapter;
+	struct device *dev  = adapter->dev;
+	int i;
+
+	for (i = 0; i < num_dma; i++) {
+		struct xsc_sq_dma *last_pushed_dma;
+
+		last_pushed_dma = xsc_dma_get(sq, --sq->dma_fifo_pc);
+		xsc_tx_dma_unmap(dev, last_pushed_dma);
+	}
+}
+
+static void *xsc_sq_fetch_wqe(struct xsc_sq *sq, size_t size, u16 *pi)
+{
+	struct xsc_wq_cyc *wq = &sq->wq;
+	void *wqe;
+
+	/*caution, sp->pc is default to be zero*/
+	*pi  = xsc_wq_cyc_ctr2ix(wq, sq->pc);
+	wqe = xsc_wq_cyc_get_wqe(wq, *pi);
+	memset(wqe, 0, size);
+
+	return wqe;
+}
+
+static u16 xsc_tx_get_gso_ihs(struct xsc_sq *sq, struct sk_buff *skb)
+{
+	u16 ihs;
+
+	if (skb->encapsulation) {
+		ihs = skb_inner_transport_offset(skb) + inner_tcp_hdrlen(skb);
+	} else {
+		if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4)
+			ihs = skb_transport_offset(skb) + sizeof(struct udphdr);
+		else
+			ihs = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	}
+
+	return ihs;
+}
+
+static void xsc_txwqe_build_cseg_csum(struct xsc_sq *sq,
+				      struct sk_buff *skb,
+				      struct xsc_send_wqe_ctrl_seg *cseg)
+{
+	u32 val = le32_to_cpu(cseg->data0);
+
+	if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) {
+		if (skb->encapsulation)
+			val |= FIELD_PREP(XSC_WQE_CTRL_SEG_CSUM_EN_MASK,
+					  XSC_ETH_WQE_INNER_AND_OUTER_CSUM);
+		else
+			val |= FIELD_PREP(XSC_WQE_CTRL_SEG_CSUM_EN_MASK,
+					  XSC_ETH_WQE_OUTER_CSUM);
+	} else {
+		val |= FIELD_PREP(XSC_WQE_CTRL_SEG_CSUM_EN_MASK,
+				  XSC_ETH_WQE_NONE_CSUM);
+	}
+	cseg->data0 = cpu_to_le32(val);
+}
+
+static void xsc_txwqe_build_csegs(struct xsc_sq *sq, struct sk_buff *skb,
+				  u16 mss, u16 ihs, u16 headlen,
+				  u8 opcode, u16 ds_cnt, u32 num_bytes,
+				  struct xsc_send_wqe_ctrl_seg *cseg)
+{
+	struct xsc_core_device *xdev = sq->cq.xdev;
+	int send_wqe_ds_num_log;
+	u32 val = 0;
+
+	send_wqe_ds_num_log = ilog2(xdev->caps.send_ds_num);
+	xsc_txwqe_build_cseg_csum(sq, skb, cseg);
+
+	if (mss != 0) {
+		val |= XSC_WQE_CTRL_SEG_HAS_PPH |
+		       XSC_WQE_CTRL_SEG_SO_TYPE |
+		       FIELD_PREP(XSC_WQE_CTRL_SEG_SO_HDR_LEN_MASK, ihs) |
+		       FIELD_PREP(XSC_WQE_CTRL_SEG_SO_DATA_SIZE_MASK, mss);
+		cseg->data2 = cpu_to_le32(val);
+	}
+
+	val = le32_to_cpu(cseg->data0);
+	val |= FIELD_PREP(XSC_WQE_CTRL_SEG_MSG_OPCODE_MASK, opcode) |
+	       FIELD_PREP(XSC_WQE_CTRL_SEG_WQE_ID_MASK,
+			  sq->pc << send_wqe_ds_num_log) |
+	       FIELD_PREP(XSC_WQE_CTRL_SEG_DS_DATA_NUM_MASK,
+			  ds_cnt - XSC_SEND_WQEBB_CTRL_NUM_DS);
+	cseg->data0 = cpu_to_le32(val);
+	cseg->msg_len = cpu_to_le32(num_bytes);
+	cseg->data3 = cpu_to_le32(XSC_WQE_CTRL_SEG_CE);
+}
+
+static int xsc_txwqe_build_dsegs(struct xsc_sq *sq, struct sk_buff *skb,
+				 u16 ihs, u16 headlen,
+				 struct xsc_wqe_data_seg *dseg)
+{
+	struct xsc_adapter *adapter = sq->channel->adapter;
+	struct device *dev = adapter->dev;
+	dma_addr_t dma_addr = 0;
+	u8 num_dma = 0;
+	int i;
+
+	if (headlen) {
+		dma_addr = dma_map_single(dev,
+					  skb->data,
+					  headlen,
+					  DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(dev, dma_addr)))
+			goto err_dma_unmap_wqe;
+
+		dseg->va = cpu_to_le64(dma_addr);
+		dseg->mkey  = cpu_to_le32(be32_to_cpu(sq->mkey_be));
+		dseg->data0 |=
+			cpu_to_le32(FIELD_PREP(XSC_WQE_DATA_SEG_SEG_LEN_MASK,
+					       headlen));
+
+		xsc_dma_push(sq, dma_addr, headlen, XSC_DMA_MAP_SINGLE);
+		num_dma++;
+		dseg++;
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+		int fsz = skb_frag_size(frag);
+
+		dma_addr = skb_frag_dma_map(dev, frag, 0, fsz, DMA_TO_DEVICE);
+		if (unlikely(dma_mapping_error(dev, dma_addr)))
+			goto err_dma_unmap_wqe;
+
+		dseg->va = cpu_to_le64(dma_addr);
+		dseg->mkey = cpu_to_le32(be32_to_cpu(sq->mkey_be));
+		dseg->data0 |=
+			cpu_to_le32(FIELD_PREP(XSC_WQE_DATA_SEG_SEG_LEN_MASK,
+					       fsz));
+
+		xsc_dma_push(sq, dma_addr, fsz, XSC_DMA_MAP_PAGE);
+		num_dma++;
+		dseg++;
+	}
+
+	return num_dma;
+
+err_dma_unmap_wqe:
+	xsc_dma_unmap_wqe(sq, num_dma);
+	return -ENOMEM;
+}
+
+static void xsc_sq_notify_hw(struct xsc_wq_cyc *wq, u16 pc,
+			     struct xsc_sq *sq)
+{
+	struct xsc_adapter *adapter = sq->channel->adapter;
+	struct xsc_core_device *xdev  = adapter->xdev;
+	union xsc_send_doorbell doorbell_value;
+	int send_ds_num_log;
+
+	send_ds_num_log = ilog2(xdev->caps.send_ds_num);
+	/*reverse wqe index to ds index*/
+	doorbell_value.next_pid = pc << send_ds_num_log;
+	doorbell_value.qp_num = sq->sqn;
+
+	/* Make sure that descriptors are written before
+	 * updating doorbell record and ringing the doorbell
+	 */
+	wmb();
+	writel(doorbell_value.send_data, XSC_REG_ADDR(xdev, xdev->regs.tx_db));
+}
+
+static void xsc_txwqe_complete(struct xsc_sq *sq, struct sk_buff *skb,
+			       u8 opcode, u16 ds_cnt,
+			       u8 num_wqebbs, u32 num_bytes, u8 num_dma,
+			       struct xsc_tx_wqe_info *wi)
+{
+	struct xsc_wq_cyc *wq = &sq->wq;
+
+	wi->num_bytes = num_bytes;
+	wi->num_dma = num_dma;
+	wi->num_wqebbs = num_wqebbs;
+	wi->skb = skb;
+
+	netdev_tx_sent_queue(sq->txq, num_bytes);
+
+	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP))
+		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	sq->pc += wi->num_wqebbs;
+
+	if (unlikely(!xsc_wqc_has_room_for(wq, sq->cc, sq->pc, sq->stop_room)))
+		netif_tx_stop_queue(sq->txq);
+
+	if (!netdev_xmit_more() || netif_xmit_stopped(sq->txq))
+		xsc_sq_notify_hw(wq, sq->pc, sq);
+}
+
+static uint32_t xsc_eth_xmit_frame(struct sk_buff *skb,
+				   struct xsc_sq *sq,
+				   struct xsc_tx_wqe *wqe,
+				   u16 pi)
+{
+	struct xsc_core_device *xdev = sq->cq.xdev;
+	struct xsc_send_wqe_ctrl_seg *cseg;
+	struct xsc_wqe_data_seg *dseg;
+	struct xsc_tx_wqe_info *wi;
+	u16 mss, ihs, headlen;
+	u32 num_bytes;
+	u8 num_wqebbs;
+	int num_dma;
+	u16 ds_cnt;
+	u8 opcode;
+
+retry_send:
+	/* Calc ihs and ds cnt, no writes to wqe yet */
+	/*ctrl-ds, it would be reduce in ds_data_num*/
+	ds_cnt = XSC_SEND_WQEBB_CTRL_NUM_DS;
+
+	/*in andes inline is bonding with gso*/
+	if (skb_is_gso(skb)) {
+		opcode    = XSC_OPCODE_RAW;
+		mss       = skb_shinfo(skb)->gso_size;
+		ihs       = xsc_tx_get_gso_ihs(sq, skb);
+		num_bytes = skb->len;
+	} else {
+		opcode    = XSC_OPCODE_RAW;
+		mss       = 0;
+		ihs       = 0;
+		num_bytes = skb->len;
+	}
+
+	/*linear data in skb*/
+	headlen = skb->len - skb->data_len;
+	ds_cnt += !!headlen;
+	ds_cnt += skb_shinfo(skb)->nr_frags;
+
+	/* Check packet size. */
+	if (unlikely(mss == 0 && num_bytes > sq->hw_mtu))
+		goto err_drop;
+
+	num_wqebbs = DIV_ROUND_UP(ds_cnt, xdev->caps.send_ds_num);
+	/*if ds_cnt exceed one wqe, drop it*/
+	if (num_wqebbs != 1) {
+		if (skb_linearize(skb))
+			goto err_drop;
+		goto retry_send;
+	}
+
+	/* fill wqe */
+	wi   = (struct xsc_tx_wqe_info *)&sq->db.wqe_info[pi];
+	cseg = &wqe->ctrl;
+	dseg = &wqe->data[0];
+
+	if (unlikely(num_bytes == 0))
+		goto err_drop;
+
+	xsc_txwqe_build_csegs(sq, skb, mss, ihs, headlen,
+			      opcode, ds_cnt, num_bytes, cseg);
+
+	/*inline header is also use dma to transport*/
+	num_dma = xsc_txwqe_build_dsegs(sq, skb, ihs, headlen, dseg);
+	if (unlikely(num_dma < 0))
+		goto err_drop;
+
+	xsc_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
+			   num_dma, wi);
+
+	return NETDEV_TX_OK;
+
+err_drop:
+	dev_kfree_skb_any(skb);
+
+	return NETDEV_TX_OK;
+}
+
+netdev_tx_t xsc_eth_xmit_start(struct sk_buff *skb, struct net_device *netdev)
+{
+	struct xsc_adapter *adapter = netdev_priv(netdev);
+	int ds_num = adapter->xdev->caps.send_ds_num;
+	struct xsc_tx_wqe *wqe;
+	struct xsc_sq *sq;
+	u16 pi;
+
+	if (!adapter ||
+	    !adapter->xdev ||
+	    adapter->status != XSCALE_ETH_DRIVER_OK)
+		return NETDEV_TX_BUSY;
+
+	sq = adapter->txq2sq[skb_get_queue_mapping(skb)];
+	if (unlikely(!sq))
+		return NETDEV_TX_BUSY;
+
+	wqe = xsc_sq_fetch_wqe(sq, ds_num * XSC_SEND_WQE_DS, &pi);
+
+	return xsc_eth_xmit_frame(skb, sq, wqe, pi);
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
index 116019a9abbd8..68f3347e4e1f2 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
@@ -6,8 +6,18 @@
 #ifndef __XSC_RXTX_H
 #define __XSC_RXTX_H
 
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+
 #include "xsc_eth.h"
 
+enum {
+	XSC_ETH_WQE_NONE_CSUM,
+	XSC_ETH_WQE_INNER_CSUM,
+	XSC_ETH_WQE_OUTER_CSUM,
+	XSC_ETH_WQE_INNER_AND_OUTER_CSUM,
+};
+
 void xsc_cq_notify_hw_rearm(struct xsc_cq *cq);
 void xsc_cq_notify_hw(struct xsc_cq *cq);
 int xsc_eth_napi_poll(struct napi_struct *napi, int budget);
@@ -23,4 +33,31 @@ struct sk_buff *xsc_skb_from_cqe_nonlinear(struct xsc_rq *rq,
 					   u32 cqe_bcnt, u8 has_pph);
 int xsc_poll_rx_cq(struct xsc_cq *cq, int budget);
 
+netdev_tx_t xsc_eth_xmit_start(struct sk_buff *skb, struct net_device *netdev);
+
+static inline void xsc_tx_dma_unmap(struct device *dev, struct xsc_sq_dma *dma)
+{
+	switch (dma->type) {
+	case XSC_DMA_MAP_SINGLE:
+		dma_unmap_single(dev, dma->addr, dma->size, DMA_TO_DEVICE);
+		break;
+	case XSC_DMA_MAP_PAGE:
+		dma_unmap_page(dev, dma->addr, dma->size, DMA_TO_DEVICE);
+		break;
+	default:
+		break;
+	}
+}
+
+static inline struct xsc_sq_dma *xsc_dma_get(struct xsc_sq *sq, u32 i)
+{
+	return &sq->db.dma_fifo[i & sq->dma_fifo_mask];
+}
+
+static inline bool xsc_wqc_has_room_for(struct xsc_wq_cyc *wq,
+					u16 cc, u16 pc, u16 n)
+{
+	return (xsc_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
+}
+
 #endif /* XSC_RXTX_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
index 643b2c759c613..4c9f183fca9a6 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
@@ -36,6 +36,8 @@ enum {
 #define XSC_RECV_WQEBB_NUM_DS	        (XSC_RECV_WQE_BB / XSC_RECV_WQE_DS)
 #define XSC_LOG_RECV_WQEBB_NUM_DS	ilog2(XSC_RECV_WQEBB_NUM_DS)
 
+#define XSC_SEND_WQEBB_CTRL_NUM_DS	1
+
 /* each ds holds one fragment in skb */
 #define XSC_MAX_RX_FRAGS        4
 #define XSC_RX_FRAG_SZ_ORDER    0
@@ -158,6 +160,11 @@ struct xsc_tx_wqe_info {
 	u8  num_dma;
 };
 
+struct xsc_tx_wqe {
+	struct xsc_send_wqe_ctrl_seg ctrl;
+	struct xsc_wqe_data_seg data[];
+};
+
 struct xsc_sq {
 	struct xsc_core_qp		cqp;
 	/* dirtied @completion */

From e8c529b2ed394e308db088e75605c79ea9c46ba8 Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:21 +0800
Subject: [PATCH 2603/2753] xsc: Add eth reception data path

rx data path:
1. The hardware writes incoming packets into the RQ ring buffer and
generates a event queue entry
2. The event handler function(xsc_eth_completion_event in
xsc_eth_events.c) is triggered, invokes napi_schedule() to schedule
a softirq.
3. The kernel triggers the softirq handler net_rx_action, which calls
the driver's NAPI poll function (xsc_eth_napi_poll in xsc_eth_txrx.c).
The driver retrieves CQEs from the Completion Queue (CQ) via
xsc_poll_rx_cq.
4. xsc_eth_build_rx_skb constructs an sk_buff structure, and submits the
SKB to the kernel network stack via napi_gro_receive
5. The driver recycles the RX buffer and notifies the NIC via
xsc_eth_post_rx_wqes to prepare for new packets.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/yunsilicon/xsc/common/xsc_core.h |   5 +
 .../yunsilicon/xsc/net/xsc_eth_common.h       |  28 +
 .../ethernet/yunsilicon/xsc/net/xsc_eth_rx.c  | 569 +++++++++++++++++-
 .../yunsilicon/xsc/net/xsc_eth_txrx.c         |  92 ++-
 .../yunsilicon/xsc/net/xsc_eth_txrx.h         |  28 +
 5 files changed, 710 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
index 0b54b2d8ac19a..bc938292a5251 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/common/xsc_core.h
@@ -490,4 +490,9 @@ static inline u8 xsc_get_user_mode(struct xsc_core_device *xdev)
 	return xdev->user_mode;
 }
 
+static inline u8 get_cqe_opcode(struct xsc_cqe *cqe)
+{
+	return FIELD_GET(XSC_CQE_MSG_OPCD_MASK, le32_to_cpu(cqe->data0));
+}
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
index 7ab311a47069f..97bbf7e4fed1b 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_common.h
@@ -22,6 +22,8 @@
 #define XSC_SW2HW_RX_PKT_LEN(mtu)	\
 	((mtu) + ETH_HLEN + XSC_ETH_RX_MAX_HEAD_ROOM)
 
+#define XSC_RX_MAX_HEAD			(256)
+
 #define XSC_QPN_SQN_STUB		1025
 #define XSC_QPN_RQN_STUB		1024
 
@@ -145,6 +147,24 @@ enum channel_flags {
 	XSC_CHANNEL_NAPI_SCHED = 1,
 };
 
+enum xsc_eth_priv_flag {
+	XSC_PFLAG_RX_NO_CSUM_COMPLETE,
+	XSC_PFLAG_SNIFFER,
+	XSC_PFLAG_DROPLESS_RQ,
+	XSC_PFLAG_RX_COPY_BREAK,
+	XSC_NUM_PFLAGS, /* Keep last */
+};
+
+#define XSC_SET_PFLAG(params, pflag, enable)			\
+	do {							\
+		if (enable)					\
+			(params)->pflags |= BIT(pflag);		\
+		else						\
+			(params)->pflags &= ~(BIT(pflag));	\
+	} while (0)
+
+#define XSC_GET_PFLAG(params, pflag) (!!((params)->pflags & (BIT(pflag))))
+
 struct xsc_eth_params {
 	u16	num_channels;
 	u16	max_num_ch;
@@ -193,4 +213,12 @@ union xsc_send_doorbell {
 	u32 send_data;
 };
 
+union xsc_recv_doorbell {
+	struct{
+		s32  next_pid : 13;
+		u32 qp_num : 15;
+	};
+	u32 recv_data;
+};
+
 #endif
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
index e8a22f32283b9..e957c60a2e786 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
@@ -5,44 +5,593 @@
  * Copyright (c) 2015-2016, Mellanox Technologies. All rights reserved.
  */
 
+#include <linux/net_tstamp.h>
+#include <linux/device.h>
+
+#include "common/xsc_pp.h"
+#include "xsc_eth.h"
 #include "xsc_eth_txrx.h"
+#include "xsc_eth_common.h"
+#include "xsc_pph.h"
+
+#define PAGE_REF_ELEV  (U16_MAX)
+/* Upper bound on number of packets that share a single page */
+#define PAGE_REF_THRSD (PAGE_SIZE / 64)
+
+static void xsc_rq_notify_hw(struct xsc_rq *rq)
+{
+	struct xsc_core_device *xdev = rq->cq.xdev;
+	union xsc_recv_doorbell doorbell_value;
+	struct xsc_wq_cyc *wq = &rq->wqe.wq;
+	u64 rqwqe_id;
+
+	rqwqe_id = wq->wqe_ctr << (ilog2(xdev->caps.recv_ds_num));
+	/*reverse wqe index to ds index*/
+	doorbell_value.next_pid = rqwqe_id;
+	doorbell_value.qp_num = rq->rqn;
+
+	/* Make sure that descriptors are written before
+	 * updating doorbell record and ringing the doorbell
+	 */
+	wmb();
+	writel(doorbell_value.recv_data, XSC_REG_ADDR(xdev, xdev->regs.rx_db));
+}
+
+static void xsc_skb_set_hash(struct xsc_adapter *adapter,
+			     struct xsc_cqe *cqe,
+			     struct sk_buff *skb)
+{
+	struct xsc_rss_params *rss = &adapter->rss_param;
+	bool l3_hash = false;
+	bool l4_hash = false;
+	u32 hash_field;
+	int ht = 0;
+
+	if (adapter->netdev->features & NETIF_F_RXHASH) {
+		if (skb->protocol == htons(ETH_P_IP)) {
+			hash_field = rss->rx_hash_fields[XSC_TT_IPV4_TCP];
+			if (hash_field & XSC_HASH_FIELD_SEL_SRC_IP ||
+			    hash_field & XSC_HASH_FIELD_SEL_DST_IP)
+				l3_hash = true;
+
+			if (hash_field & XSC_HASH_FIELD_SEL_SPORT ||
+			    hash_field & XSC_HASH_FIELD_SEL_DPORT)
+				l4_hash = true;
+		} else if (skb->protocol == htons(ETH_P_IPV6)) {
+			hash_field = rss->rx_hash_fields[XSC_TT_IPV6_TCP];
+			if (hash_field & XSC_HASH_FIELD_SEL_SRC_IPV6 ||
+			    hash_field & XSC_HASH_FIELD_SEL_DST_IPV6)
+				l3_hash = true;
+
+			if (hash_field & XSC_HASH_FIELD_SEL_SPORT_V6 ||
+			    hash_field & XSC_HASH_FIELD_SEL_DPORT_V6)
+				l4_hash = true;
+		}
+
+		if (l3_hash && l4_hash)
+			ht = PKT_HASH_TYPE_L4;
+		else if (l3_hash)
+			ht = PKT_HASH_TYPE_L3;
+		if (ht)
+			skb_set_hash(skb, le32_to_cpu(cqe->vni), ht);
+	}
+}
+
+static void xsc_handle_csum(struct xsc_cqe *cqe, struct xsc_rq *rq,
+			    struct sk_buff *skb, struct xsc_wqe_frag_info *wi)
+{
+	struct xsc_dma_info *dma_info;
+	struct net_device *netdev;
+	struct epp_pph *hw_pph;
+	struct xsc_channel *c;
+	int offset_from;
+
+	c = rq->cq.channel;
+	netdev = c->adapter->netdev;
+	dma_info = wi->di;
+	offset_from = wi->offset;
+	hw_pph = page_address(dma_info->page) + offset_from;
+
+	if (unlikely((netdev->features & NETIF_F_RXCSUM) == 0))
+		goto csum_none;
+
+	if (unlikely(XSC_GET_EPP2SOC_PPH_ERROR_BITMAP(hw_pph) & PACKET_UNKNOWN))
+		goto csum_none;
+
+	if (XSC_GET_EPP2SOC_PPH_EXT_TUNNEL_TYPE(hw_pph) &&
+	    (!(FIELD_GET(XSC_CQE_CSUM_ERR_MASK, le32_to_cpu(cqe->data0)) &
+	       OUTER_AND_INNER))) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = 1;
+		skb->encapsulation = 1;
+	} else if (XSC_GET_EPP2SOC_PPH_EXT_TUNNEL_TYPE(hw_pph) &&
+		   (!(FIELD_GET(XSC_CQE_CSUM_ERR_MASK,
+				le32_to_cpu(cqe->data0)) &
+		      OUTER_BIT) &&
+		    (FIELD_GET(XSC_CQE_CSUM_ERR_MASK,
+			       le32_to_cpu(cqe->data0)) &
+		     INNER_BIT))) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		skb->csum_level = 0;
+		skb->encapsulation = 1;
+	} else if (!XSC_GET_EPP2SOC_PPH_EXT_TUNNEL_TYPE(hw_pph) &&
+		   (!(FIELD_GET(XSC_CQE_CSUM_ERR_MASK,
+				le32_to_cpu(cqe->data0)) &
+		      OUTER_BIT))) {
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+	}
+
+	goto out;
+
+csum_none:
+	skb->csum = 0;
+	skb->ip_summed = CHECKSUM_NONE;
+out:
+	return;
+}
+
+static void xsc_build_rx_skb(struct xsc_cqe *cqe,
+			     u32 cqe_bcnt,
+			     struct xsc_rq *rq,
+			     struct sk_buff *skb,
+			     struct xsc_wqe_frag_info *wi)
+{
+	struct xsc_adapter *adapter;
+	struct net_device *netdev;
+	struct xsc_channel *c;
+
+	c = rq->cq.channel;
+	adapter = c->adapter;
+	netdev = c->netdev;
+
+	skb->mac_len = ETH_HLEN;
+
+	skb_record_rx_queue(skb, rq->ix);
+	xsc_handle_csum(cqe, rq, skb, wi);
+
+	skb->protocol = eth_type_trans(skb, netdev);
+	xsc_skb_set_hash(adapter, cqe, skb);
+}
+
+static void xsc_complete_rx_cqe(struct xsc_rq *rq,
+				struct xsc_cqe *cqe,
+				u32 cqe_bcnt,
+				struct sk_buff *skb,
+				struct xsc_wqe_frag_info *wi)
+{
+	xsc_build_rx_skb(cqe, cqe_bcnt, rq, skb, wi);
+}
+
+static void xsc_add_skb_frag(struct xsc_rq *rq,
+			     struct sk_buff *skb,
+			     struct xsc_dma_info *di,
+			     u32 frag_offset, u32 len,
+			     unsigned int truesize)
+{
+	struct xsc_channel *c = rq->cq.channel;
+	struct device *dev = c->adapter->dev;
+
+	dma_sync_single_for_cpu(dev, di->addr + frag_offset,
+				len, DMA_FROM_DEVICE);
+	page_ref_inc(di->page);
+	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags,
+			di->page, frag_offset, len, truesize);
+}
+
+static void xsc_copy_skb_header(struct device *dev,
+				struct sk_buff *skb,
+				struct xsc_dma_info *dma_info,
+				int offset_from, u32 headlen)
+{
+	void *from = page_address(dma_info->page) + offset_from;
+	/* Aligning len to sizeof(long) optimizes memcpy performance */
+	unsigned int len = ALIGN(headlen, sizeof(long));
+
+	dma_sync_single_for_cpu(dev, dma_info->addr + offset_from, len,
+				DMA_FROM_DEVICE);
+	skb_copy_to_linear_data(skb, from, len);
+}
+
+static struct sk_buff *xsc_build_linear_skb(struct xsc_rq *rq, void *va,
+					    u32 frag_size, u16 headroom,
+					    u32 cqe_bcnt)
+{
+	struct sk_buff *skb = build_skb(va, frag_size);
+
+	if (unlikely(!skb))
+		return NULL;
+
+	skb_reserve(skb, headroom);
+	skb_put(skb, cqe_bcnt);
+
+	return skb;
+}
 
 struct sk_buff *xsc_skb_from_cqe_linear(struct xsc_rq *rq,
 					struct xsc_wqe_frag_info *wi,
 					u32 cqe_bcnt, u8 has_pph)
 {
-	/* TBD */
-	return NULL;
+	int pph_len = has_pph ? XSC_PPH_HEAD_LEN : 0;
+	u16 rx_headroom = rq->buff.headroom;
+	struct xsc_dma_info *di = wi->di;
+	struct sk_buff *skb;
+	void *va, *data;
+	u32 frag_size;
+
+	va = page_address(di->page) + wi->offset;
+	data = va + rx_headroom + pph_len;
+	frag_size = XSC_SKB_FRAG_SZ(rx_headroom + cqe_bcnt);
+
+	dma_sync_single_range_for_cpu(rq->cq.xdev->device, di->addr, wi->offset,
+				      frag_size, DMA_FROM_DEVICE);
+	net_prefetchw(va); /* xdp_frame data area */
+	net_prefetch(data);
+
+	skb = xsc_build_linear_skb(rq, va, frag_size, (rx_headroom + pph_len),
+				   (cqe_bcnt - pph_len));
+	if (unlikely(!skb))
+		return NULL;
+
+	/* queue up for recycling/reuse */
+	page_ref_inc(di->page);
+
+	return skb;
 }
 
 struct sk_buff *xsc_skb_from_cqe_nonlinear(struct xsc_rq *rq,
 					   struct xsc_wqe_frag_info *wi,
 					   u32 cqe_bcnt, u8 has_pph)
 {
-	/* TBD */
-	return NULL;
+	struct xsc_rq_frag_info *frag_info = &rq->wqe.info.arr[0];
+	u16 headlen  = min_t(u32, XSC_RX_MAX_HEAD, cqe_bcnt);
+	struct xsc_wqe_frag_info *head_wi = wi;
+	struct xsc_wqe_frag_info *rx_wi = wi;
+	u16 head_offset = head_wi->offset;
+	u16 byte_cnt = cqe_bcnt - headlen;
+	u16 frag_consumed_bytes = 0;
+	u16 frag_headlen = headlen;
+	struct net_device *netdev;
+	struct xsc_channel *c;
+	struct sk_buff *skb;
+	struct device *dev;
+	u8 fragcnt = 0;
+	int i = 0;
+
+	c = rq->cq.channel;
+	dev = c->adapter->dev;
+	netdev = c->adapter->netdev;
+
+	skb = napi_alloc_skb(rq->cq.napi, ALIGN(XSC_RX_MAX_HEAD, sizeof(long)));
+	if (unlikely(!skb))
+		return NULL;
+
+	net_prefetchw(skb->data);
+
+	if (likely(has_pph)) {
+		headlen = min_t(u32, XSC_RX_MAX_HEAD,
+				(cqe_bcnt - XSC_PPH_HEAD_LEN));
+		frag_headlen = headlen + XSC_PPH_HEAD_LEN;
+		byte_cnt = cqe_bcnt - headlen - XSC_PPH_HEAD_LEN;
+		head_offset += XSC_PPH_HEAD_LEN;
+	}
+
+	if (byte_cnt == 0 &&
+	    (XSC_GET_PFLAG(&c->adapter->nic_param, XSC_PFLAG_RX_COPY_BREAK))) {
+		for (i = 0; i < rq->wqe.info.num_frags; i++, wi++)
+			wi->is_available = 1;
+		goto out;
+	}
+
+	for (i = 0; i < rq->wqe.info.num_frags; i++, rx_wi++)
+		rx_wi->is_available = 0;
+
+	while (byte_cnt) {
+		/*figure out whether the first fragment can be a page ?*/
+		frag_consumed_bytes =
+			min_t(u16, frag_info->frag_size - frag_headlen,
+			      byte_cnt);
+
+		xsc_add_skb_frag(rq, skb, wi->di, wi->offset + frag_headlen,
+				 frag_consumed_bytes, frag_info->frag_stride);
+		byte_cnt -= frag_consumed_bytes;
+
+		/*to protect extend wqe read, drop exceed bytes*/
+		frag_headlen = 0;
+		fragcnt++;
+		if (fragcnt == rq->wqe.info.num_frags) {
+			if (byte_cnt) {
+				netdev_warn(netdev,
+					    "large packet reach the maximum rev-wqe num.\n");
+				netdev_warn(netdev,
+					    "%u bytes dropped: frag_num=%d, headlen=%d, cqe_cnt=%d, frag0_bytes=%d, frag_size=%d\n",
+					    byte_cnt, fragcnt,
+					    headlen, cqe_bcnt,
+					    frag_consumed_bytes,
+					    frag_info->frag_size);
+			}
+			break;
+		}
+
+		frag_info++;
+		wi++;
+	}
+
+out:
+	/* copy header */
+	xsc_copy_skb_header(dev, skb, head_wi->di, head_offset, headlen);
+
+	/* skb linear part was allocated with headlen and aligned to long */
+	skb->tail += headlen;
+	skb->len += headlen;
+
+	return skb;
+}
+
+static void xsc_page_dma_unmap(struct xsc_rq *rq, struct xsc_dma_info *dma_info)
+{
+	struct xsc_channel *c = rq->cq.channel;
+	struct device *dev = c->adapter->dev;
+
+	dma_unmap_page(dev, dma_info->addr, XSC_RX_FRAG_SZ, rq->buff.map_dir);
+}
+
+static void xsc_page_release_dynamic(struct xsc_rq *rq,
+				     struct xsc_dma_info *dma_info,
+				     bool recycle)
+{
+	xsc_page_dma_unmap(rq, dma_info);
+	page_pool_recycle_direct(rq->page_pool, dma_info->page);
+}
+
+static void xsc_put_rx_frag(struct xsc_rq *rq,
+			    struct xsc_wqe_frag_info *frag, bool recycle)
+{
+	if (frag->last_in_page)
+		xsc_page_release_dynamic(rq, frag->di, recycle);
+}
+
+static struct xsc_wqe_frag_info *get_frag(struct xsc_rq *rq, u16 ix)
+{
+	return &rq->wqe.frags[ix << rq->wqe.info.log_num_frags];
+}
+
+static void xsc_free_rx_wqe(struct xsc_rq *rq,
+			    struct xsc_wqe_frag_info *wi, bool recycle)
+{
+	int i;
+
+	for (i = 0; i < rq->wqe.info.num_frags; i++, wi++) {
+		if (wi->is_available && recycle)
+			continue;
+		xsc_put_rx_frag(rq, wi, recycle);
+	}
+}
+
+static void xsc_dump_error_rqcqe(struct xsc_rq *rq,
+				 struct xsc_cqe *cqe)
+{
+	struct net_device *netdev;
+	struct xsc_channel *c;
+	u32 ci;
+
+	c = rq->cq.channel;
+	netdev  = c->adapter->netdev;
+	ci = xsc_cqwq_get_ci(&rq->cq.wq);
+
+	net_err_ratelimited("Error cqe on dev=%s, cqn=%d, ci=%d, rqn=%d, qpn=%ld, error_code=0x%x\n",
+			    netdev->name, rq->cq.xcq.cqn, ci,
+			    rq->rqn,
+			    FIELD_GET(XSC_CQE_QP_ID_MASK,
+				      le32_to_cpu(cqe->data0)),
+			    get_cqe_opcode(cqe));
 }
 
 void xsc_eth_handle_rx_cqe(struct xsc_cqwq *cqwq,
 			   struct xsc_rq *rq, struct xsc_cqe *cqe)
 {
-	/* TBD */
+	struct xsc_channel *c = rq->cq.channel;
+	struct xsc_wq_cyc *wq = &rq->wqe.wq;
+	u8 cqe_opcode = get_cqe_opcode(cqe);
+	struct xsc_wqe_frag_info *wi;
+	struct sk_buff *skb;
+	u32 cqe_bcnt;
+	u16 ci;
+
+	ci = xsc_wq_cyc_ctr2ix(wq, cqwq->cc);
+	wi = get_frag(rq, ci);
+	if (unlikely(cqe_opcode & BIT(7))) {
+		xsc_dump_error_rqcqe(rq, cqe);
+		goto free_wqe;
+	}
+
+	cqe_bcnt = le32_to_cpu(cqe->msg_len);
+	if ((le32_to_cpu(cqe->data0) & XSC_CQE_HAS_PPH) &&
+	    cqe_bcnt <= XSC_PPH_HEAD_LEN)
+		goto free_wqe;
+
+	if (unlikely(cqe_bcnt > rq->frags_sz)) {
+		if (!XSC_GET_PFLAG(&c->adapter->nic_param,
+				   XSC_PFLAG_DROPLESS_RQ))
+			goto free_wqe;
+	}
+
+	cqe_bcnt = min_t(u32, cqe_bcnt, rq->frags_sz);
+	skb = rq->wqe.skb_from_cqe(rq, wi, cqe_bcnt,
+				   !!(le32_to_cpu(cqe->data0) &
+				      XSC_CQE_HAS_PPH));
+	if (!skb)
+		goto free_wqe;
+
+	xsc_complete_rx_cqe(rq, cqe,
+			    (le32_to_cpu(cqe->data0) & XSC_CQE_HAS_PPH) ?
+			    cqe_bcnt - XSC_PPH_HEAD_LEN : cqe_bcnt,
+			    skb, wi);
+
+	napi_gro_receive(rq->cq.napi, skb);
+
+free_wqe:
+	xsc_free_rx_wqe(rq, wi, true);
+	xsc_wq_cyc_pop(wq);
 }
 
 int xsc_poll_rx_cq(struct xsc_cq *cq, int budget)
 {
-	/* TBD */
+	struct xsc_rq *rq = container_of(cq, struct xsc_rq, cq);
+	struct xsc_cqwq *cqwq = &cq->wq;
+	struct xsc_cqe *cqe;
+	int work_done = 0;
+
+	if (!test_bit(XSC_ETH_RQ_STATE_ENABLED, &rq->state))
+		return 0;
+
+	while ((work_done < budget) && (cqe = xsc_cqwq_get_cqe(cqwq))) {
+		rq->handle_rx_cqe(cqwq, rq, cqe);
+		++work_done;
+
+		xsc_cqwq_pop(cqwq);
+	}
+
+	if (!work_done)
+		goto out;
+
+	xsc_cq_notify_hw(cq);
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+out:
+	return work_done;
+}
+
+static int xsc_page_alloc_mapped(struct xsc_rq *rq,
+				 struct xsc_dma_info *dma_info)
+{
+	struct xsc_channel *c = rq->cq.channel;
+	struct device *dev = c->adapter->dev;
+
+	dma_info->page = page_pool_dev_alloc_pages(rq->page_pool);
+	if (unlikely(!dma_info->page))
+		return -ENOMEM;
+
+	dma_info->addr = dma_map_page(dev, dma_info->page, 0,
+				      XSC_RX_FRAG_SZ, rq->buff.map_dir);
+	if (unlikely(dma_mapping_error(dev, dma_info->addr))) {
+		page_pool_recycle_direct(rq->page_pool, dma_info->page);
+		dma_info->page = NULL;
+		return -ENOMEM;
+	}
+
 	return 0;
 }
 
+static int xsc_get_rx_frag(struct xsc_rq *rq,
+			   struct xsc_wqe_frag_info *frag)
+{
+	int err = 0;
+
+	if (!frag->offset && !frag->is_available)
+		/* On first frag (offset == 0), replenish page (dma_info
+		 * actually). Other frags that point to the same dma_info
+		 * (with a different offset) should just use the new one
+		 * without replenishing again by themselves.
+		 */
+		err = xsc_page_alloc_mapped(rq, frag->di);
+
+	return err;
+}
+
+static int xsc_alloc_rx_wqe(struct xsc_rq *rq,
+			    struct xsc_eth_rx_wqe_cyc *wqe,
+			    u16 ix)
+{
+	struct xsc_wqe_frag_info *frag = get_frag(rq, ix);
+	u64 addr;
+	int err;
+	int i;
+
+	for (i = 0; i < rq->wqe.info.num_frags; i++, frag++) {
+		err = xsc_get_rx_frag(rq, frag);
+		if (unlikely(err))
+			goto err_free_frags;
+
+		addr = frag->di->addr + frag->offset + rq->buff.headroom;
+		wqe->data[i].va = cpu_to_le64(addr);
+	}
+
+	return 0;
+
+err_free_frags:
+	while (--i >= 0)
+		xsc_put_rx_frag(rq, --frag, true);
+
+	return err;
+}
+
 void xsc_eth_dealloc_rx_wqe(struct xsc_rq *rq, u16 ix)
 {
-	/* TBD */
+	struct xsc_wqe_frag_info *wi = get_frag(rq, ix);
+
+	xsc_free_rx_wqe(rq, wi, false);
 }
 
-bool xsc_eth_post_rx_wqes(struct xsc_rq *rq)
+static int xsc_alloc_rx_wqes(struct xsc_rq *rq, u16 ix, u8 wqe_bulk)
 {
-	/* TBD */
-	return true;
+	struct xsc_wq_cyc *wq = &rq->wqe.wq;
+	struct xsc_eth_rx_wqe_cyc *wqe;
+	int err;
+	int idx;
+	int i;
+
+	for (i = 0; i < wqe_bulk; i++) {
+		idx = xsc_wq_cyc_ctr2ix(wq, (ix + i));
+		wqe = xsc_wq_cyc_get_wqe(wq, idx);
+
+		err = xsc_alloc_rx_wqe(rq, wqe, idx);
+		if (unlikely(err))
+			goto err_free_wqes;
+	}
+
+	return 0;
+
+err_free_wqes:
+	while (--i >= 0)
+		xsc_eth_dealloc_rx_wqe(rq, ix + i);
+
+	return err;
 }
 
+bool xsc_eth_post_rx_wqes(struct xsc_rq *rq)
+{
+	struct xsc_wq_cyc *wq = &rq->wqe.wq;
+	u8 wqe_bulk, wqe_bulk_min;
+	int alloc;
+	u16 head;
+	int err;
+
+	wqe_bulk = rq->wqe.info.wqe_bulk;
+	wqe_bulk_min = rq->wqe.info.wqe_bulk_min;
+	if (xsc_wq_cyc_missing(wq) < wqe_bulk)
+		return false;
+
+	do {
+		head = xsc_wq_cyc_get_head(wq);
+
+		alloc = min_t(int, wqe_bulk, xsc_wq_cyc_missing(wq));
+		if (alloc < wqe_bulk && alloc >= wqe_bulk_min)
+			alloc = alloc & 0xfffffffe;
+
+		if (alloc > 0) {
+			err = xsc_alloc_rx_wqes(rq, head, alloc);
+			if (unlikely(err))
+				break;
+
+			xsc_wq_cyc_push_n(wq, alloc);
+		}
+	} while (xsc_wq_cyc_missing(wq) >= wqe_bulk_min);
+
+	dma_wmb();
+
+	/* ensure wqes are visible to device before updating doorbell record */
+	xsc_rq_notify_hw(rq);
+
+	return !!err;
+}
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
index 5d1fcb669ddd8..8140b66bb3020 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.c
@@ -42,10 +42,98 @@ static bool xsc_channel_no_affinity_change(struct xsc_channel *c)
 	return cpumask_test_cpu(current_cpu, c->aff_mask);
 }
 
+static void xsc_dump_error_sqcqe(struct xsc_sq *sq,
+				 struct xsc_cqe *cqe)
+{
+	struct net_device *netdev = sq->channel->netdev;
+	u32 ci = xsc_cqwq_get_ci(&sq->cq.wq);
+
+	net_err_ratelimited("Err cqe on dev %s cqn=0x%x ci=0x%x sqn=0x%x err_code=0x%x qpid=0x%lx\n",
+			    netdev->name, sq->cq.xcq.cqn, ci,
+			    sq->sqn, get_cqe_opcode(cqe),
+			    FIELD_GET(XSC_CQE_QP_ID_MASK,
+				      le32_to_cpu(cqe->data0)));
+}
+
 static bool xsc_poll_tx_cq(struct xsc_cq *cq, int napi_budget)
 {
-	/* TBD */
-	return true;
+	struct xsc_adapter *adapter;
+	struct xsc_cqe *cqe;
+	struct device *dev;
+	struct xsc_sq *sq;
+	u32 dma_fifo_cc;
+	u32 nbytes = 0;
+	u16 npkts = 0;
+	int i = 0;
+	u16 sqcc;
+
+	sq = container_of(cq, struct xsc_sq, cq);
+	if (!test_bit(XSC_ETH_SQ_STATE_ENABLED, &sq->state))
+		return false;
+
+	adapter = sq->channel->adapter;
+	dev = adapter->dev;
+
+	cqe = xsc_cqwq_get_cqe(&cq->wq);
+	if (!cqe)
+		goto out;
+
+	if (unlikely(get_cqe_opcode(cqe) & BIT(7))) {
+		xsc_dump_error_sqcqe(sq, cqe);
+		return false;
+	}
+
+	sqcc = sq->cc;
+
+	/* avoid dirtying sq cache line every cqe */
+	dma_fifo_cc = sq->dma_fifo_cc;
+	i = 0;
+	do {
+		struct xsc_tx_wqe_info *wi;
+		struct sk_buff *skb;
+		int j;
+		u16 ci;
+
+		xsc_cqwq_pop(&cq->wq);
+
+		ci = xsc_wq_cyc_ctr2ix(&sq->wq, sqcc);
+		wi = &sq->db.wqe_info[ci];
+		skb = wi->skb;
+
+		/*cqe may be overstanding in real test, not by nop in other*/
+		if (unlikely(!skb))
+			continue;
+
+		for (j = 0; j < wi->num_dma; j++) {
+			struct xsc_sq_dma *dma = xsc_dma_get(sq, dma_fifo_cc++);
+
+			xsc_tx_dma_unmap(dev, dma);
+		}
+
+		npkts++;
+		nbytes += wi->num_bytes;
+		sqcc += wi->num_wqebbs;
+		napi_consume_skb(skb, 0);
+
+	} while ((++i <= napi_budget) && (cqe = xsc_cqwq_get_cqe(&cq->wq)));
+
+	xsc_cq_notify_hw(cq);
+
+	/* ensure cq space is freed before enabling more cqes */
+	wmb();
+
+	sq->dma_fifo_cc = dma_fifo_cc;
+	sq->cc = sqcc;
+
+	netdev_tx_completed_queue(sq->txq, npkts, nbytes);
+
+	if (netif_tx_queue_stopped(sq->txq) &&
+	    xsc_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room)) {
+		netif_tx_wake_queue(sq->txq);
+	}
+
+out:
+	return (i == napi_budget);
 }
 
 int xsc_eth_napi_poll(struct napi_struct *napi, int budget)
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
index 68f3347e4e1f2..d0d303efaba4d 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_txrx.h
@@ -60,4 +60,32 @@ static inline bool xsc_wqc_has_room_for(struct xsc_wq_cyc *wq,
 	return (xsc_wq_cyc_ctr2ix(wq, cc - pc) >= n) || (cc == pc);
 }
 
+static inline struct xsc_cqe *xsc_cqwq_get_cqe_buff(struct xsc_cqwq *wq, u32 ix)
+{
+	struct xsc_cqe *cqe = xsc_frag_buf_get_wqe(&wq->fbc, ix);
+
+	return cqe;
+}
+
+static inline struct xsc_cqe *xsc_cqwq_get_cqe(struct xsc_cqwq *wq)
+{
+	u32 ci = xsc_cqwq_get_ci(wq);
+	u8 cqe_ownership_bit;
+	struct xsc_cqe *cqe;
+	u8 sw_ownership_val;
+
+	cqe = xsc_cqwq_get_cqe_buff(wq, ci);
+
+	cqe_ownership_bit = !!(le32_to_cpu(cqe->data1) & XSC_CQE_OWNER);
+	sw_ownership_val = xsc_cqwq_get_wrap_cnt(wq) & 1;
+
+	if (cqe_ownership_bit != sw_ownership_val)
+		return NULL;
+
+	/* ensure cqe content is read after cqe ownership bit */
+	dma_rmb();
+
+	return cqe;
+}
+
 #endif /* XSC_RXTX_H */

From c4d5ccd4bb756304061492d05b9f3c9c142429ef Mon Sep 17 00:00:00 2001
From: Xin Tian <tianx@yunsilicon.com>
Date: Tue, 18 Mar 2025 23:15:24 +0800
Subject: [PATCH 2604/2753] xsc: add ndo_get_stats64

Added basic network interface statistics.

Co-developed-by: Honggang Wei <weihg@yunsilicon.com>
Signed-off-by: Honggang Wei <weihg@yunsilicon.com>
Co-developed-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Lei Yan <jacky@yunsilicon.com>
Signed-off-by: Xin Tian <tianx@yunsilicon.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/yunsilicon/xsc/net/Makefile  |  2 +-
 .../net/ethernet/yunsilicon/xsc/net/main.c    | 29 +++++++++++-
 .../net/ethernet/yunsilicon/xsc/net/xsc_eth.h |  3 ++
 .../ethernet/yunsilicon/xsc/net/xsc_eth_rx.c  |  4 ++
 .../yunsilicon/xsc/net/xsc_eth_stats.c        | 46 +++++++++++++++++++
 .../yunsilicon/xsc/net/xsc_eth_stats.h        | 34 ++++++++++++++
 .../ethernet/yunsilicon/xsc/net/xsc_eth_tx.c  |  5 ++
 .../ethernet/yunsilicon/xsc/net/xsc_queue.h   |  2 +
 8 files changed, 122 insertions(+), 3 deletions(-)
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.c
 create mode 100644 drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.h

diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
index 7cfc2aaa2637a..e1cfa3cdf0fd0 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/Makefile
@@ -6,4 +6,4 @@ ccflags-y += -I$(srctree)/drivers/net/ethernet/yunsilicon/xsc
 
 obj-$(CONFIG_YUNSILICON_XSC_ETH) += xsc_eth.o
 
-xsc_eth-y := main.o xsc_eth_wq.o xsc_eth_txrx.o xsc_eth_tx.o xsc_eth_rx.o
+xsc_eth-y := main.o xsc_eth_wq.o xsc_eth_txrx.o xsc_eth_tx.o xsc_eth_rx.o xsc_eth_stats.o
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/main.c b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
index 8d6bcb87fe121..7cfad5ffebdad 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/main.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/main.c
@@ -561,15 +561,20 @@ static int xsc_eth_open_qp_sq(struct xsc_channel *c,
 	u8 ele_log_size = psq_param->sq_attr.ele_log_size;
 	u8 q_log_size = psq_param->sq_attr.q_log_size;
 	struct xsc_modify_raw_qp_mbox_in *modify_in;
+	struct xsc_channel_stats *channel_stats;
 	struct xsc_create_qp_mbox_in *in;
 	struct xsc_core_device *xdev;
 	struct xsc_adapter *adapter;
+	struct xsc_stats *stats;
 	unsigned int hw_npages;
 	int inlen;
 	int ret;
 
 	adapter = c->adapter;
 	xdev  = adapter->xdev;
+	stats = adapter->stats;
+	channel_stats = &stats->channel_stats[c->chl_idx];
+	psq->stats = &channel_stats->sq[sq_idx];
 	psq_param->wq.db_numa_node = cpu_to_node(c->cpu);
 
 	ret = xsc_eth_wq_cyc_create(xdev, &psq_param->wq,
@@ -870,11 +875,16 @@ static int xsc_eth_alloc_rq(struct xsc_channel *c,
 	u8 q_log_size = prq_param->rq_attr.q_log_size;
 	struct page_pool_params pagepool_params = {0};
 	struct xsc_adapter *adapter = c->adapter;
+	struct xsc_channel_stats *channel_stats;
 	u32 pool_size = 1 << q_log_size;
+	struct xsc_stats *stats;
 	int ret = 0;
 	u32 wq_sz;
 	int i, f;
 
+	stats = c->adapter->stats;
+	channel_stats = &stats->channel_stats[c->chl_idx];
+	prq->stats = &channel_stats->rq;
 	prq_param->wq.db_numa_node = cpu_to_node(c->cpu);
 
 	ret = xsc_eth_wq_cyc_create(c->adapter->xdev, &prq_param->wq,
@@ -1662,6 +1672,14 @@ static int xsc_eth_close(struct net_device *netdev)
 	return ret;
 }
 
+static void xsc_eth_get_stats(struct net_device *netdev,
+			      struct rtnl_link_stats64 *stats)
+{
+	struct xsc_adapter *adapter = netdev_priv(netdev);
+
+	xsc_eth_fold_sw_stats64(adapter, stats);
+}
+
 static int xsc_eth_set_hw_mtu(struct xsc_core_device *xdev,
 			      u16 mtu, u16 rx_buf_sz)
 {
@@ -1693,6 +1711,7 @@ static const struct net_device_ops xsc_netdev_ops = {
 	.ndo_open		= xsc_eth_open,
 	.ndo_stop		= xsc_eth_close,
 	.ndo_start_xmit		= xsc_eth_xmit_start,
+	.ndo_get_stats64	= xsc_eth_get_stats,
 };
 
 static void xsc_eth_build_nic_netdev(struct xsc_adapter *adapter)
@@ -1912,14 +1931,20 @@ static int xsc_eth_probe(struct auxiliary_device *adev,
 		goto err_nic_cleanup;
 	}
 
+	adapter->stats = kvzalloc(sizeof(*adapter->stats), GFP_KERNEL);
+	if (!adapter->stats)
+		goto err_detach;
+
 	err = register_netdev(netdev);
 	if (err) {
 		netdev_err(netdev, "register_netdev failed, err=%d\n", err);
-		goto err_detach;
+		goto err_free_stats;
 	}
 
 	return 0;
 
+err_free_stats:
+	kvfree(adapter->stats);
 err_detach:
 	xsc_eth_detach(xdev, adapter);
 err_nic_cleanup:
@@ -1944,7 +1969,7 @@ static void xsc_eth_remove(struct auxiliary_device *adev)
 		return;
 
 	unregister_netdev(adapter->netdev);
-
+	kvfree(adapter->stats);
 	free_netdev(adapter->netdev);
 
 	xdev->eth_priv = NULL;
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
index 27fcfcda4f2a1..eef2cca36d501 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth.h
@@ -10,6 +10,7 @@
 
 #include "common/xsc_device.h"
 #include "xsc_eth_common.h"
+#include "xsc_eth_stats.h"
 
 #define XSC_INVALID_LKEY	0x100
 
@@ -47,6 +48,8 @@ struct xsc_adapter {
 
 	u32			status;
 	struct mutex		status_lock; /*protect status */
+
+	struct xsc_stats	*stats;
 };
 
 #endif /* __XSC_ETH_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
index e957c60a2e786..1d4c5574c9f1c 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_rx.c
@@ -159,6 +159,10 @@ static void xsc_complete_rx_cqe(struct xsc_rq *rq,
 				struct sk_buff *skb,
 				struct xsc_wqe_frag_info *wi)
 {
+	struct xsc_rq_stats *stats = rq->stats;
+
+	stats->packets++;
+	stats->bytes += cqe_bcnt;
 	xsc_build_rx_skb(cqe, cqe_bcnt, rq, skb, wi);
 }
 
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.c
new file mode 100644
index 0000000000000..38bab39b999b1
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.c
@@ -0,0 +1,46 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#include "xsc_eth_stats.h"
+#include "xsc_eth.h"
+
+static int xsc_get_netdev_max_channels(struct xsc_adapter *adapter)
+{
+	struct net_device *netdev = adapter->netdev;
+
+	return min_t(unsigned int, netdev->num_rx_queues,
+		     netdev->num_tx_queues);
+}
+
+static int xsc_get_netdev_max_tc(struct xsc_adapter *adapter)
+{
+	return adapter->nic_param.num_tc;
+}
+
+void xsc_eth_fold_sw_stats64(struct xsc_adapter *adapter,
+			     struct rtnl_link_stats64 *s)
+{
+	int i, j;
+
+	for (i = 0; i < xsc_get_netdev_max_channels(adapter); i++) {
+		struct xsc_channel_stats *channel_stats;
+		struct xsc_rq_stats *rq_stats;
+
+		channel_stats = &adapter->stats->channel_stats[i];
+		rq_stats = &channel_stats->rq;
+
+		s->rx_packets   += rq_stats->packets;
+		s->rx_bytes     += rq_stats->bytes;
+
+		for (j = 0; j < xsc_get_netdev_max_tc(adapter); j++) {
+			struct xsc_sq_stats *sq_stats = &channel_stats->sq[j];
+
+			s->tx_packets    += sq_stats->packets;
+			s->tx_bytes      += sq_stats->bytes;
+			s->tx_dropped    += sq_stats->dropped;
+		}
+	}
+}
+
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.h
new file mode 100644
index 0000000000000..1828f4608d0c3
--- /dev/null
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_stats.h
@@ -0,0 +1,34 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Shanghai Yunsilicon Technology Co., Ltd.
+ * All rights reserved.
+ */
+
+#ifndef __XSC_EN_STATS_H
+#define __XSC_EN_STATS_H
+
+#include "xsc_eth_common.h"
+
+struct xsc_rq_stats {
+	u64 packets;
+	u64 bytes;
+};
+
+struct xsc_sq_stats {
+	u64 packets;
+	u64 bytes;
+	u64 dropped;
+};
+
+struct xsc_channel_stats {
+	struct xsc_sq_stats sq[XSC_MAX_NUM_TC];
+	struct xsc_rq_stats rq;
+} ____cacheline_aligned_in_smp;
+
+struct xsc_stats {
+	struct xsc_channel_stats channel_stats[XSC_ETH_MAX_NUM_CHANNELS];
+};
+
+void xsc_eth_fold_sw_stats64(struct xsc_adapter *adapter,
+			     struct rtnl_link_stats64 *s);
+
+#endif /* XSC_EN_STATS_H */
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c
index 1acc1db353579..044b5a0e46730 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_eth_tx.c
@@ -221,6 +221,7 @@ static uint32_t xsc_eth_xmit_frame(struct sk_buff *skb,
 				   u16 pi)
 {
 	struct xsc_core_device *xdev = sq->cq.xdev;
+	struct xsc_sq_stats *stats = sq->stats;
 	struct xsc_send_wqe_ctrl_seg *cseg;
 	struct xsc_wqe_data_seg *dseg;
 	struct xsc_tx_wqe_info *wi;
@@ -242,11 +243,13 @@ static uint32_t xsc_eth_xmit_frame(struct sk_buff *skb,
 		mss       = skb_shinfo(skb)->gso_size;
 		ihs       = xsc_tx_get_gso_ihs(sq, skb);
 		num_bytes = skb->len;
+		stats->packets += skb_shinfo(skb)->gso_segs;
 	} else {
 		opcode    = XSC_OPCODE_RAW;
 		mss       = 0;
 		ihs       = 0;
 		num_bytes = skb->len;
+		stats->packets++;
 	}
 
 	/*linear data in skb*/
@@ -284,10 +287,12 @@ static uint32_t xsc_eth_xmit_frame(struct sk_buff *skb,
 
 	xsc_txwqe_complete(sq, skb, opcode, ds_cnt, num_wqebbs, num_bytes,
 			   num_dma, wi);
+	stats->bytes     += num_bytes;
 
 	return NETDEV_TX_OK;
 
 err_drop:
+	stats->dropped++;
 	dev_kfree_skb_any(skb);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
index 4c9f183fca9a6..83fb13d8e380d 100644
--- a/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
+++ b/drivers/net/ethernet/yunsilicon/xsc/net/xsc_queue.h
@@ -132,6 +132,7 @@ struct xsc_rq {
 
 	unsigned long	state;
 	struct work_struct  recover_work;
+	struct xsc_rq_stats *stats;
 
 	u32 hw_mtu;
 	u32 frags_sz;
@@ -180,6 +181,7 @@ struct xsc_sq {
 	/* read only */
 	struct xsc_wq_cyc         wq;
 	u32                        dma_fifo_mask;
+	struct xsc_sq_stats     *stats;
 	struct {
 		struct xsc_sq_dma         *dma_fifo;
 		struct xsc_tx_wqe_info    *wqe_info;

From 2421c700ff1cfde07f018a2fd40b6b03caa30cb0 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:16 -0700
Subject: [PATCH 2605/2753] idpf: add initial PTP support

PTP feature is supported if the VIRTCHNL2_CAP_PTP is negotiated during the
capabilities recognition. Initial PTP support includes PTP initialization
and registration of the clock.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/Kconfig       |  1 +
 drivers/net/ethernet/intel/idpf/Makefile      |  1 +
 drivers/net/ethernet/intel/idpf/idpf.h        |  3 +
 drivers/net/ethernet/intel/idpf/idpf_main.c   |  4 +
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 90 +++++++++++++++++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    | 32 +++++++
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   | 10 ++-
 7 files changed, 140 insertions(+), 1 deletion(-)
 create mode 100644 drivers/net/ethernet/intel/idpf/idpf_ptp.c
 create mode 100644 drivers/net/ethernet/intel/idpf/idpf_ptp.h

diff --git a/drivers/net/ethernet/intel/idpf/Kconfig b/drivers/net/ethernet/intel/idpf/Kconfig
index 1addd663acad9..2c359a8551c7b 100644
--- a/drivers/net/ethernet/intel/idpf/Kconfig
+++ b/drivers/net/ethernet/intel/idpf/Kconfig
@@ -4,6 +4,7 @@
 config IDPF
 	tristate "Intel(R) Infrastructure Data Path Function Support"
 	depends on PCI_MSI
+	depends on PTP_1588_CLOCK_OPTIONAL
 	select DIMLIB
 	select LIBETH
 	help
diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 2ce01a0b58981..1f38a9d7125ca 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -17,3 +17,4 @@ idpf-y := \
 	idpf_vf_dev.o
 
 idpf-$(CONFIG_IDPF_SINGLEQ)	+= idpf_singleq_txrx.o
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_ptp.o
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 66544faab710a..2e8b14dd9d960 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -530,6 +530,7 @@ struct idpf_vc_xn_manager;
  * @vector_lock: Lock to protect vector distribution
  * @queue_lock: Lock to protect queue distribution
  * @vc_buf_lock: Lock to protect virtchnl buffer
+ * @ptp: Storage for PTP-related data
  */
 struct idpf_adapter {
 	struct pci_dev *pdev;
@@ -587,6 +588,8 @@ struct idpf_adapter {
 	struct mutex vector_lock;
 	struct mutex queue_lock;
 	struct mutex vc_buf_lock;
+
+	struct idpf_ptp *ptp;
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index b6c515d14cbf0..60bae30810353 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -163,6 +163,10 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_free;
 	}
 
+	err = pci_enable_ptm(pdev, NULL);
+	if (err)
+		pci_dbg(pdev, "PCIe PTM is not supported by PCIe bus/controller\n");
+
 	/* set up for high or low dma */
 	err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
 	if (err) {
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
new file mode 100644
index 0000000000000..71fc652b79e67
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -0,0 +1,90 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+
+/**
+ * idpf_ptp_create_clock - Create PTP clock device for userspace
+ * @adapter: Driver specific private structure
+ *
+ * This function creates a new PTP clock device.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock *clock;
+
+	/* Attempt to register the clock before enabling the hardware. */
+	clock = ptp_clock_register(&adapter->ptp->info,
+				   &adapter->pdev->dev);
+	if (IS_ERR(clock)) {
+		pci_err(adapter->pdev, "PTP clock creation failed: %pe\n",
+			clock);
+		return PTR_ERR(clock);
+	}
+
+	adapter->ptp->clock = clock;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_init - Initialize PTP hardware clock support
+ * @adapter: Driver specific private structure
+ *
+ * Set up the device for interacting with the PTP hardware clock for all
+ * functions. Function will allocate and register a ptp_clock with the
+ * PTP_1588_CLOCK infrastructure.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	int err;
+
+	if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) {
+		pci_dbg(adapter->pdev, "PTP capability is not detected\n");
+		return -EOPNOTSUPP;
+	}
+
+	adapter->ptp = kzalloc(sizeof(*adapter->ptp), GFP_KERNEL);
+	if (!adapter->ptp)
+		return -ENOMEM;
+
+	/* add a back pointer to adapter */
+	adapter->ptp->adapter = adapter;
+
+	err = idpf_ptp_create_clock(adapter);
+	if (err)
+		goto free_ptp;
+
+	pci_dbg(adapter->pdev, "PTP init successful\n");
+
+	return 0;
+
+free_ptp:
+	kfree(adapter->ptp);
+	adapter->ptp = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_ptp_release - Clear PTP hardware clock support
+ * @adapter: Driver specific private structure
+ */
+void idpf_ptp_release(struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	if (!ptp)
+		return;
+
+	if (ptp->clock)
+		ptp_clock_unregister(ptp->clock);
+
+	kfree(ptp);
+	adapter->ptp = NULL;
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
new file mode 100644
index 0000000000000..d009417bf9473
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef _IDPF_PTP_H
+#define _IDPF_PTP_H
+
+#include <linux/ptp_clock_kernel.h>
+
+/**
+ * struct idpf_ptp - PTP parameters
+ * @info: structure defining PTP hardware capabilities
+ * @clock: pointer to registered PTP clock device
+ * @adapter: back pointer to the adapter
+ */
+struct idpf_ptp {
+	struct ptp_clock_info info;
+	struct ptp_clock *clock;
+	struct idpf_adapter *adapter;
+};
+
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+int idpf_ptp_init(struct idpf_adapter *adapter);
+void idpf_ptp_release(struct idpf_adapter *adapter);
+#else /* CONFIG_PTP_1588_CLOCK */
+static inline int idpf_ptp_init(struct idpf_adapter *adapter)
+{
+	return 0;
+}
+
+static inline void idpf_ptp_release(struct idpf_adapter *adapter) { }
+#endif /* CONFIG_PTP_1588_CLOCK */
+#endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 3d2413b8684fc..1d42f8aee4aa6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -5,6 +5,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 #define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
 #define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
@@ -900,7 +901,8 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
-			    VIRTCHNL2_CAP_LOOPBACK);
+			    VIRTCHNL2_CAP_LOOPBACK		|
+			    VIRTCHNL2_CAP_PTP);
 
 	xn_params.vc_op = VIRTCHNL2_OP_GET_CAPS;
 	xn_params.send_buf.iov_base = &caps;
@@ -3029,6 +3031,11 @@ int idpf_vc_core_init(struct idpf_adapter *adapter)
 		goto err_intr_req;
 	}
 
+	err = idpf_ptp_init(adapter);
+	if (err)
+		pci_err(adapter->pdev, "PTP init failed, err=%pe\n",
+			ERR_PTR(err));
+
 	idpf_init_avail_queues(adapter);
 
 	/* Skew the delay for init tasks for each function based on fn number
@@ -3091,6 +3098,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 	if (!remove_in_prog)
 		idpf_vc_xn_shutdown(adapter->vcxn_mngr);
 
+	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
 	idpf_intr_rel(adapter);
 

From 76cdf907dc83827a699adac8d0715a8aeb83a552 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:17 -0700
Subject: [PATCH 2606/2753] virtchnl: add PTP virtchnl definitions

PTP capabilities are negotiated using virtchnl commands. There are two
available modes of the PTP support: direct and mailbox. When the direct
access to PTP resources is negotiated, virtchnl messages returns a set
of registers that allow read/write directly. When the mailbox access to
PTP resources is negotiated, virtchnl messages are used to access
PTP clock and to read the timestamp values.

Virtchnl API covers both modes and exposes a set of PTP capabilities.

Using virtchnl API, the driver recognizes also HW abilities - maximum
adjustment of the clock and the basic increment value.

Additionally, API allows to configure the secondary mailbox, dedicated
exclusively for PTP purposes.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/virtchnl2.h | 302 ++++++++++++++++++++
 1 file changed, 302 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 63deb120359cf..44a5ee84ed606 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -68,6 +68,16 @@ enum virtchnl2_op {
 	VIRTCHNL2_OP_ADD_MAC_ADDR		= 535,
 	VIRTCHNL2_OP_DEL_MAC_ADDR		= 536,
 	VIRTCHNL2_OP_CONFIG_PROMISCUOUS_MODE	= 537,
+
+	/* TimeSync opcodes */
+	VIRTCHNL2_OP_PTP_GET_CAPS			= 541,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP		= 542,
+	VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME		= 543,
+	VIRTCHNL2_OP_PTP_GET_CROSS_TIME			= 544,
+	VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME		= 545,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE		= 546,
+	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME		= 547,
+	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS	= 548,
 };
 
 /**
@@ -1270,4 +1280,296 @@ struct virtchnl2_promisc_info {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_promisc_info);
 
+/**
+ * enum virtchnl2_ptp_caps - PTP capabilities
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME: direct access to get the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB: mailbox access to get the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME: direct access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB: mailbox access to cross timestamp
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME: direct access to set the time of
+ *					   device clock
+ * @VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB: mailbox access to set the time of
+ *					      device clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK: direct access to adjust the time of device
+ *				      clock
+ * @VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB: mailbox access to adjust the time of
+ *					 device clock
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS: direct access to the Tx timestamping
+ * @VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB: mailbox access to the Tx timestamping
+ *
+ * PF/VF negotiates a set of supported PTP capabilities with the Control Plane.
+ * There are two access methods - mailbox (_MB) and direct.
+ * PTP capabilities enables Main Timer operations: get/set/adjust Main Timer,
+ * cross timestamping and the Tx timestamping.
+ */
+enum virtchnl2_ptp_caps {
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME		= BIT(0),
+	VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB	= BIT(1),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME		= BIT(2),
+	VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB		= BIT(3),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME		= BIT(4),
+	VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB	= BIT(5),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK		= BIT(6),
+	VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB		= BIT(7),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS			= BIT(8),
+	VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB			= BIT(9),
+};
+
+/**
+ * struct virtchnl2_ptp_clk_reg_offsets - Offsets of device and PHY clocks
+ *					  registers.
+ * @dev_clk_ns_l: Device clock low register offset
+ * @dev_clk_ns_h: Device clock high register offset
+ * @phy_clk_ns_l: PHY clock low register offset
+ * @phy_clk_ns_h: PHY clock high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_clk_reg_offsets {
+	__le32 dev_clk_ns_l;
+	__le32 dev_clk_ns_h;
+	__le32 phy_clk_ns_l;
+	__le32 phy_clk_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(24, virtchnl2_ptp_clk_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_cross_time_reg_offsets - Offsets of the device cross
+ *						 time registers.
+ * @sys_time_ns_l: System time low register offset
+ * @sys_time_ns_h: System time high register offset
+ * @cmd_sync_trigger: The command sync trigger register offset
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_cross_time_reg_offsets {
+	__le32 sys_time_ns_l;
+	__le32 sys_time_ns_h;
+	__le32 cmd_sync_trigger;
+	u8 pad[4];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_cross_time_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_clk_adj_reg_offsets - Offsets of device and PHY clocks
+ *					      adjustments registers.
+ * @dev_clk_cmd_type: Device clock command type register offset
+ * @dev_clk_incval_l: Device clock increment value low register offset
+ * @dev_clk_incval_h: Device clock increment value high registers offset
+ * @dev_clk_shadj_l: Device clock shadow adjust low register offset
+ * @dev_clk_shadj_h: Device clock shadow adjust high register offset
+ * @phy_clk_cmd_type: PHY timer command type register offset
+ * @phy_clk_incval_l: PHY timer increment value low register offset
+ * @phy_clk_incval_h: PHY timer increment value high register offset
+ * @phy_clk_shadj_l: PHY timer shadow adjust low register offset
+ * @phy_clk_shadj_h: PHY timer shadow adjust high register offset
+ */
+struct virtchnl2_ptp_clk_adj_reg_offsets {
+	__le32 dev_clk_cmd_type;
+	__le32 dev_clk_incval_l;
+	__le32 dev_clk_incval_h;
+	__le32 dev_clk_shadj_l;
+	__le32 dev_clk_shadj_h;
+	__le32 phy_clk_cmd_type;
+	__le32 phy_clk_incval_l;
+	__le32 phy_clk_incval_h;
+	__le32 phy_clk_shadj_l;
+	__le32 phy_clk_shadj_h;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(40, virtchnl2_ptp_clk_adj_reg_offsets);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch_caps - PTP Tx timestamp latch
+ *					       capabilities.
+ * @tx_latch_reg_offset_l: Tx timestamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx timestamp latch high register offset
+ * @index: Latch index provided to the Tx descriptor
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch_caps {
+	__le32 tx_latch_reg_offset_l;
+	__le32 tx_latch_reg_offset_h;
+	u8 index;
+	u8 pad[7];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch_caps);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_caps - Structure that defines Tx
+ *						   tstamp entries.
+ * @vport_id: Vport number
+ * @num_latches: Total number of latches
+ * @tstamp_ns_lo_bit: First bit for nanosecond part of the timestamp
+ * @tstamp_ns_hi_bit: Last bit for nanosecond part of the timestamp
+ * @pad: Padding for future tstamp granularity extensions
+ * @tstamp_latches: Capabilities of Tx timestamp entries
+ *
+ * PF/VF sends this message to negotiate the Tx timestamp latches for each
+ * Vport.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_caps {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 tstamp_ns_lo_bit;
+	u8 tstamp_ns_hi_bit;
+	u8 pad[8];
+
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tstamp_latches[]
+						  __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_caps);
+
+/**
+ * struct virtchnl2_ptp_get_caps - Get PTP capabilities
+ * @caps: PTP capability bitmap. See enum virtchnl2_ptp_caps
+ * @max_adj: The maximum possible frequency adjustment
+ * @base_incval: The default timer increment value
+ * @peer_mbx_q_id: ID of the PTP Device Control daemon queue
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @secondary_mbx: Indicates to the driver that it should create a secondary
+ *		   mailbox to inetract with control plane for PTP
+ * @pad: Padding for future extensions
+ * @clk_offsets: Main timer and PHY registers offsets
+ * @cross_time_offsets: Cross time registers offsets
+ * @clk_adj_offsets: Offsets needed to adjust the PHY and the main timer
+ *
+ * PF/VF sends this message to negotiate PTP capabilities. CP updates bitmap
+ * with supported features and fulfills appropriate structures.
+ * If HW uses primary MBX for PTP: secondary_mbx is set to false.
+ * If HW uses secondary MBX for PTP: secondary_mbx is set to true.
+ *	Control plane has 2 MBX and the driver has 1 MBX, send to peer
+ *	driver may be used to send a message using valid ptp_peer_mb_q_id and
+ *	ptp_peer_id.
+ * If HW does not use send to peer driver: secondary_mbx is no care field and
+ * peer_mbx_q_id holds invalid value (0xFFFF).
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_CAPS.
+ */
+struct virtchnl2_ptp_get_caps {
+	__le32 caps;
+	__le32 max_adj;
+	__le64 base_incval;
+	__le16 peer_mbx_q_id;
+	u8 peer_id;
+	u8 secondary_mbx;
+	u8 pad[4];
+
+	struct virtchnl2_ptp_clk_reg_offsets clk_offsets;
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_time_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(104, virtchnl2_ptp_get_caps);
+
+/**
+ * struct virtchnl2_ptp_tx_tstamp_latch - Structure that describes tx tstamp
+ *					  values, index and validity.
+ * @tstamp: Timestamp value
+ * @index: Timestamp index from which the value is read
+ * @valid: Timestamp validity
+ * @pad: Padding for future extensions
+ */
+struct virtchnl2_ptp_tx_tstamp_latch {
+	__le64 tstamp;
+	u8 index;
+	u8 valid;
+	u8 pad[6];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_tx_tstamp_latch);
+
+/**
+ * struct virtchnl2_ptp_get_vport_tx_tstamp_latches - Tx timestamp latches
+ *						      associated with the vport.
+ * @vport_id: Number of vport that requests the timestamp
+ * @num_latches: Number of latches
+ * @get_devtime_with_txtstmp: Flag to request device time along with Tx timestamp
+ * @pad: Padding for future extensions
+ * @device_time: device time if get_devtime_with_txtstmp was set in request
+ * @tstamp_latches: PTP TX timestamp latch
+ *
+ * PF/VF sends this message to receive a specified number of timestamps
+ * entries.
+ *
+ * Associated with VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP.
+ */
+struct virtchnl2_ptp_get_vport_tx_tstamp_latches {
+	__le32 vport_id;
+	__le16 num_latches;
+	u8 get_devtime_with_txtstmp;
+	u8 pad[1];
+	__le64 device_time;
+
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latches[]
+					     __counted_by_le(num_latches);
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_vport_tx_tstamp_latches);
+
+/**
+ * struct virtchnl2_ptp_get_dev_clk_time - Associated with message
+ *					   VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME.
+ * @dev_time_ns: Device clock time value in nanoseconds
+ *
+ * PF/VF sends this message to receive the time from the main timer.
+ */
+struct virtchnl2_ptp_get_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_get_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_get_cross_time: Associated with message
+ *					VIRTCHNL2_OP_PTP_GET_CROSS_TIME.
+ * @sys_time_ns: System counter value expressed in nanoseconds, read
+ *		 synchronously with device time
+ * @dev_time_ns: Device clock time value expressed in nanoseconds
+ *
+ * PF/VF sends this message to receive the cross time.
+ */
+struct virtchnl2_ptp_get_cross_time {
+	__le64 sys_time_ns;
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_ptp_get_cross_time);
+
+/**
+ * struct virtchnl2_ptp_set_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME.
+ * @dev_time_ns: Device time value expressed in nanoseconds to set
+ *
+ * PF/VF sends this message to set the time of the main timer.
+ */
+struct virtchnl2_ptp_set_dev_clk_time {
+	__le64 dev_time_ns;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_set_dev_clk_time);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_fine: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE.
+ * @incval: Source timer increment value per clock cycle
+ *
+ * PF/VF sends this message to adjust the frequency of the main timer by the
+ * indicated scaled ppm.
+ */
+struct virtchnl2_ptp_adj_dev_clk_fine {
+	__le64 incval;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_fine);
+
+/**
+ * struct virtchnl2_ptp_adj_dev_clk_time: Associated with message
+ *					  VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME.
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * PF/VF sends this message to adjust the time of the main timer by the delta.
+ */
+struct virtchnl2_ptp_adj_dev_clk_time {
+	__le64 delta;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time);
+
 #endif /* _VIRTCHNL_2_H_ */

From 6ae9a5c0beaa4451aea764fe56ff8051d24abca0 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:18 -0700
Subject: [PATCH 2607/2753] idpf: move virtchnl structures to the header file

Move virtchnl structures to the header file to expose them for the PTP
virtchnl file.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   | 86 +------------------
 .../net/ethernet/intel/idpf/idpf_virtchnl.h   | 84 ++++++++++++++++++
 2 files changed, 86 insertions(+), 84 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 1d42f8aee4aa6..e27f3f2777a26 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -7,88 +7,6 @@
 #include "idpf_virtchnl.h"
 #include "idpf_ptp.h"
 
-#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
-#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
-#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
-#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
-#define IDPF_VC_XN_RING_LEN		U8_MAX
-
-/**
- * enum idpf_vc_xn_state - Virtchnl transaction status
- * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
- * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
- * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received,
- *				  buffer updated
- * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
- *				 was an error, buffer not updated
- * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
- * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
- *		      return context; a callback may be provided to handle
- *		      return
- */
-enum idpf_vc_xn_state {
-	IDPF_VC_XN_IDLE = 1,
-	IDPF_VC_XN_WAITING,
-	IDPF_VC_XN_COMPLETED_SUCCESS,
-	IDPF_VC_XN_COMPLETED_FAILED,
-	IDPF_VC_XN_SHUTDOWN,
-	IDPF_VC_XN_ASYNC,
-};
-
-struct idpf_vc_xn;
-/* Callback for asynchronous messages */
-typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
-			    const struct idpf_ctlq_msg *);
-
-/**
- * struct idpf_vc_xn - Data structure representing virtchnl transactions
- * @completed: virtchnl event loop uses that to signal when a reply is
- *	       available, uses kernel completion API
- * @state: virtchnl event loop stores the data below, protected by the
- *	   completion's lock.
- * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
- *	      truncated on its way to the receiver thread according to
- *	      reply_buf.iov_len.
- * @reply: Reference to the buffer(s) where the reply data should be written
- *	   to. May be 0-length (then NULL address permitted) if the reply data
- *	   should be ignored.
- * @async_handler: if sent asynchronously, a callback can be provided to handle
- *		   the reply when it's received
- * @vc_op: corresponding opcode sent with this transaction
- * @idx: index used as retrieval on reply receive, used for cookie
- * @salt: changed every message to make unique, used for cookie
- */
-struct idpf_vc_xn {
-	struct completion completed;
-	enum idpf_vc_xn_state state;
-	size_t reply_sz;
-	struct kvec reply;
-	async_vc_cb async_handler;
-	u32 vc_op;
-	u8 idx;
-	u8 salt;
-};
-
-/**
- * struct idpf_vc_xn_params - Parameters for executing transaction
- * @send_buf: kvec for send buffer
- * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
- * @timeout_ms: timeout to wait for reply
- * @async: send message asynchronously, will not wait on completion
- * @async_handler: If sent asynchronously, optional callback handler. The user
- *		   must be careful when using async handlers as the memory for
- *		   the recv_buf _cannot_ be on stack if this is async.
- * @vc_op: virtchnl op to send
- */
-struct idpf_vc_xn_params {
-	struct kvec send_buf;
-	struct kvec recv_buf;
-	int timeout_ms;
-	bool async;
-	async_vc_cb async_handler;
-	u32 vc_op;
-};
-
 /**
  * struct idpf_vc_xn_manager - Manager for tracking transactions
  * @ring: backing and lookup for transactions
@@ -450,8 +368,8 @@ static void idpf_vc_xn_push_free(struct idpf_vc_xn_manager *vcxn_mngr,
  * >= @recv_buf.iov_len, but we never overflow @@recv_buf_iov_base). < 0 for
  * error.
  */
-static ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
-			       const struct idpf_vc_xn_params *params)
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params)
 {
 	const struct kvec *send_buf = &params->send_buf;
 	struct idpf_vc_xn *xn;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 83da5d8da56bf..3522c1238ea24 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -4,6 +4,88 @@
 #ifndef _IDPF_VIRTCHNL_H_
 #define _IDPF_VIRTCHNL_H_
 
+#define IDPF_VC_XN_MIN_TIMEOUT_MSEC	2000
+#define IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC	(60 * 1000)
+#define IDPF_VC_XN_IDX_M		GENMASK(7, 0)
+#define IDPF_VC_XN_SALT_M		GENMASK(15, 8)
+#define IDPF_VC_XN_RING_LEN		U8_MAX
+
+/**
+ * enum idpf_vc_xn_state - Virtchnl transaction status
+ * @IDPF_VC_XN_IDLE: not expecting a reply, ready to be used
+ * @IDPF_VC_XN_WAITING: expecting a reply, not yet received
+ * @IDPF_VC_XN_COMPLETED_SUCCESS: a reply was expected and received, buffer
+ *				  updated
+ * @IDPF_VC_XN_COMPLETED_FAILED: a reply was expected and received, but there
+ *				 was an error, buffer not updated
+ * @IDPF_VC_XN_SHUTDOWN: transaction object cannot be used, VC torn down
+ * @IDPF_VC_XN_ASYNC: transaction sent asynchronously and doesn't have the
+ *		      return context; a callback may be provided to handle
+ *		      return
+ */
+enum idpf_vc_xn_state {
+	IDPF_VC_XN_IDLE = 1,
+	IDPF_VC_XN_WAITING,
+	IDPF_VC_XN_COMPLETED_SUCCESS,
+	IDPF_VC_XN_COMPLETED_FAILED,
+	IDPF_VC_XN_SHUTDOWN,
+	IDPF_VC_XN_ASYNC,
+};
+
+struct idpf_vc_xn;
+/* Callback for asynchronous messages */
+typedef int (*async_vc_cb) (struct idpf_adapter *, struct idpf_vc_xn *,
+			    const struct idpf_ctlq_msg *);
+
+/**
+ * struct idpf_vc_xn - Data structure representing virtchnl transactions
+ * @completed: virtchnl event loop uses that to signal when a reply is
+ *	       available, uses kernel completion API
+ * @state: virtchnl event loop stores the data below, protected by the
+ *	   completion's lock.
+ * @reply_sz: Original size of reply, may be > reply_buf.iov_len; it will be
+ *	      truncated on its way to the receiver thread according to
+ *	      reply_buf.iov_len.
+ * @reply: Reference to the buffer(s) where the reply data should be written
+ *	   to. May be 0-length (then NULL address permitted) if the reply data
+ *	   should be ignored.
+ * @async_handler: if sent asynchronously, a callback can be provided to handle
+ *		   the reply when it's received
+ * @vc_op: corresponding opcode sent with this transaction
+ * @idx: index used as retrieval on reply receive, used for cookie
+ * @salt: changed every message to make unique, used for cookie
+ */
+struct idpf_vc_xn {
+	struct completion completed;
+	enum idpf_vc_xn_state state;
+	size_t reply_sz;
+	struct kvec reply;
+	async_vc_cb async_handler;
+	u32 vc_op;
+	u8 idx;
+	u8 salt;
+};
+
+/**
+ * struct idpf_vc_xn_params - Parameters for executing transaction
+ * @send_buf: kvec for send buffer
+ * @recv_buf: kvec for recv buffer, may be NULL, must then have zero length
+ * @timeout_ms: timeout to wait for reply
+ * @async: send message asynchronously, will not wait on completion
+ * @async_handler: If sent asynchronously, optional callback handler. The user
+ *		   must be careful when using async handlers as the memory for
+ *		   the recv_buf _cannot_ be on stack if this is async.
+ * @vc_op: virtchnl op to send
+ */
+struct idpf_vc_xn_params {
+	struct kvec send_buf;
+	struct kvec recv_buf;
+	int timeout_ms;
+	bool async;
+	async_vc_cb async_handler;
+	u32 vc_op;
+};
+
 struct idpf_adapter;
 struct idpf_netdev_priv;
 struct idpf_vec_regs;
@@ -11,6 +93,8 @@ struct idpf_vport;
 struct idpf_vport_max_q;
 struct idpf_vport_user_config_data;
 
+ssize_t idpf_vc_xn_exec(struct idpf_adapter *adapter,
+			const struct idpf_vc_xn_params *params);
 int idpf_init_dflt_mbx(struct idpf_adapter *adapter);
 void idpf_deinit_dflt_mbx(struct idpf_adapter *adapter);
 int idpf_vc_core_init(struct idpf_adapter *adapter);

From caeace08dfe5c1cf13335ef35725d12b209648d7 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:19 -0700
Subject: [PATCH 2608/2753] idpf: negotiate PTP capabilities and get PTP clock

PTP capabilities are negotiated using virtchnl command. Add get
capabilities function, direct access to read the PTP clock time and
direct access to read the cross timestamp - system time and PTP clock
time. Set initial PTP capabilities exposed to the stack.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Willem de Bruijn <willemb@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/Makefile      |   2 +
 drivers/net/ethernet/intel/idpf/idpf.h        |   2 +
 drivers/net/ethernet/intel/idpf/idpf_dev.c    |  14 +
 .../ethernet/intel/idpf/idpf_lan_pf_regs.h    |   4 +
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 263 ++++++++++++++++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    |  89 ++++++
 .../ethernet/intel/idpf/idpf_virtchnl_ptp.c   |  95 +++++++
 7 files changed, 469 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c

diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 1f38a9d7125ca..83ac5e2963822 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -17,4 +17,6 @@ idpf-y := \
 	idpf_vf_dev.o
 
 idpf-$(CONFIG_IDPF_SINGLEQ)	+= idpf_singleq_txrx.o
+
 idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_ptp.o
+idpf-$(CONFIG_PTP_1588_CLOCK)	+= idpf_virtchnl_ptp.o
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 2e8b14dd9d960..d5d5064d313bd 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -189,6 +189,7 @@ struct idpf_vport_max_q {
  * @mb_intr_reg_init: Mailbox interrupt register initialization
  * @reset_reg_init: Reset register initialization
  * @trigger_reset: Trigger a reset to occur
+ * @ptp_reg_init: PTP register initialization
  */
 struct idpf_reg_ops {
 	void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq);
@@ -197,6 +198,7 @@ struct idpf_reg_ops {
 	void (*reset_reg_init)(struct idpf_adapter *adapter);
 	void (*trigger_reset)(struct idpf_adapter *adapter,
 			      enum idpf_flags trig_cause);
+	void (*ptp_reg_init)(const struct idpf_adapter *adapter);
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 41e4bd49402a8..3fae81f1f9889 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -4,6 +4,7 @@
 #include "idpf.h"
 #include "idpf_lan_pf_regs.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 #define IDPF_PF_ITR_IDX_SPACING		0x4
 
@@ -148,6 +149,18 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter,
 	       idpf_get_reg_addr(adapter, PFGEN_CTRL));
 }
 
+/**
+ * idpf_ptp_reg_init - Initialize required registers
+ * @adapter: Driver specific private structure
+ *
+ * Set the bits required for enabling shtime and cmd execution
+ */
+static void idpf_ptp_reg_init(const struct idpf_adapter *adapter)
+{
+	adapter->ptp->cmd.shtime_enable_mask = PF_GLTSYN_CMD_SYNC_SHTIME_EN_M;
+	adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M;
+}
+
 /**
  * idpf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
@@ -159,6 +172,7 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 	adapter->dev_ops.reg_ops.mb_intr_reg_init = idpf_mb_intr_reg_init;
 	adapter->dev_ops.reg_ops.reset_reg_init = idpf_reset_reg_init;
 	adapter->dev_ops.reg_ops.trigger_reset = idpf_trigger_reset;
+	adapter->dev_ops.reg_ops.ptp_reg_init = idpf_ptp_reg_init;
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
index 24edb8a6ec2e6..cc9aa2b6a14aa 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_pf_regs.h
@@ -53,6 +53,10 @@
 #define PF_FW_ATQH_ATQH_M		GENMASK(9, 0)
 #define PF_FW_ATQT			(PF_FW_BASE + 0x24)
 
+/* Timesync registers */
+#define PF_GLTSYN_CMD_SYNC_EXEC_CMD_M	GENMASK(1, 0)
+#define PF_GLTSYN_CMD_SYNC_SHTIME_EN_M	BIT(2)
+
 /* Interrupts */
 #define PF_GLINT_BASE			0x08900000
 #define PF_GLINT_DYN_CTL(_INT)		(PF_GLINT_BASE + ((_INT) * 0x1000))
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 71fc652b79e67..34257fabd6a05 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -4,6 +4,258 @@
 #include "idpf.h"
 #include "idpf_ptp.h"
 
+/**
+ * idpf_ptp_get_access - Determine the access type of the PTP features
+ * @adapter: Driver specific private structure
+ * @direct: Capability that indicates the direct access
+ * @mailbox: Capability that indicates the mailbox access
+ *
+ * Return: the type of supported access for the PTP feature.
+ */
+static enum idpf_ptp_access
+idpf_ptp_get_access(const struct idpf_adapter *adapter, u32 direct, u32 mailbox)
+{
+	if (adapter->ptp->caps & direct)
+		return IDPF_PTP_DIRECT;
+	else if (adapter->ptp->caps & mailbox)
+		return IDPF_PTP_MAILBOX;
+	else
+		return IDPF_PTP_NONE;
+}
+
+/**
+ * idpf_ptp_get_features_access - Determine the access type of PTP features
+ * @adapter: Driver specific private structure
+ *
+ * Fulfill the adapter structure with type of the supported PTP features
+ * access.
+ */
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 direct, mailbox;
+
+	/* Get the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB;
+	ptp->get_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Get the cross timestamp */
+	direct = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB;
+	ptp->get_cross_tstamp_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+}
+
+/**
+ * idpf_ptp_enable_shtime - Enable shadow time and execute a command
+ * @adapter: Driver specific private structure
+ */
+static void idpf_ptp_enable_shtime(struct idpf_adapter *adapter)
+{
+	u32 shtime_enable, exec_cmd;
+
+	/* Get offsets */
+	shtime_enable = adapter->ptp->cmd.shtime_enable_mask;
+	exec_cmd = adapter->ptp->cmd.exec_cmd_mask;
+
+	/* Set the shtime en and the sync field */
+	writel(shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+	writel(exec_cmd | shtime_enable, adapter->ptp->dev_clk_regs.cmd_sync);
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg_direct - Read directly the main timer value
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ *
+ * Return: the device clock time on success, -errno otherwise.
+ */
+static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter,
+					    struct ptp_system_timestamp *sts)
+{
+	struct idpf_ptp *ptp = adapter->ptp;
+	u32 hi, lo;
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	idpf_ptp_enable_shtime(adapter);
+	lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	return ((u64)hi << 32) | lo;
+}
+
+/**
+ * idpf_ptp_read_src_clk_reg - Read the main timer value
+ * @adapter: Driver specific private structure
+ * @src_clk: Returned main timer value in nanoseconds unit
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock time on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk,
+				     struct ptp_system_timestamp *sts)
+{
+	switch (adapter->ptp->get_dev_clk_time_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_DIRECT:
+		*src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER) || IS_ENABLED(CONFIG_X86)
+/**
+ * idpf_ptp_get_sync_device_time_direct - Get the cross time stamp values
+ *					  directly
+ * @adapter: Driver specific private structure
+ * @dev_time: 64bit main timer value
+ * @sys_time: 64bit system time value
+ */
+static void idpf_ptp_get_sync_device_time_direct(struct idpf_adapter *adapter,
+						 u64 *dev_time, u64 *sys_time)
+{
+	u32 dev_time_lo, dev_time_hi, sys_time_lo, sys_time_hi;
+	struct idpf_ptp *ptp = adapter->ptp;
+
+	idpf_ptp_enable_shtime(adapter);
+
+	dev_time_lo = readl(ptp->dev_clk_regs.dev_clk_ns_l);
+	dev_time_hi = readl(ptp->dev_clk_regs.dev_clk_ns_h);
+
+	sys_time_lo = readl(ptp->dev_clk_regs.sys_time_ns_l);
+	sys_time_hi = readl(ptp->dev_clk_regs.sys_time_ns_h);
+
+	*dev_time = ((u64)dev_time_hi << 32) | dev_time_lo;
+	*sys_time = ((u64)sys_time_hi << 32) | sys_time_lo;
+}
+
+/**
+ * idpf_ptp_get_sync_device_time - Get the cross time stamp info
+ * @device: Current device time
+ * @system: System counter value read synchronously with device time
+ * @ctx: Context provided by timekeeping code
+ *
+ * Return: the device and the system clocks time read simultaneously on success,
+ * -errno otherwise.
+ */
+static int idpf_ptp_get_sync_device_time(ktime_t *device,
+					 struct system_counterval_t *system,
+					 void *ctx)
+{
+	struct idpf_adapter *adapter = ctx;
+	u64 ns_time_dev, ns_time_sys;
+
+	switch (adapter->ptp->get_cross_tstamp_access) {
+	case IDPF_PTP_NONE:
+		return -EOPNOTSUPP;
+	case IDPF_PTP_DIRECT:
+		idpf_ptp_get_sync_device_time_direct(adapter, &ns_time_dev,
+						     &ns_time_sys);
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
+	*device = ns_to_ktime(ns_time_dev);
+
+#if IS_ENABLED(CONFIG_X86)
+	system->cycles = ns_time_sys;
+	system->cs_id = CSID_X86_ART;
+#endif /* CONFIG_X86 */
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_crosststamp - Capture a device cross timestamp
+ * @info: the driver's PTP info structure
+ * @cts: The memory to fill the cross timestamp info
+ *
+ * Capture a cross timestamp between the system time and the device PTP hardware
+ * clock.
+ *
+ * Return: cross timestamp value on success, -errno on failure.
+ */
+static int idpf_ptp_get_crosststamp(struct ptp_clock_info *info,
+				    struct system_device_crosststamp *cts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	return get_device_system_crosststamp(idpf_ptp_get_sync_device_time,
+					     adapter, NULL, cts);
+}
+#endif /* CONFIG_ARM_ARCH_TIMER || CONFIG_X86 */
+
+/**
+ * idpf_ptp_gettimex64 - Get the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure to hold the current time value
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored if NULL is given.
+ *
+ * Return: the device clock value in ns, after converting it into a timespec
+ * struct on success, -errno otherwise.
+ */
+static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
+			       struct timespec64 *ts,
+			       struct ptp_system_timestamp *sts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	u64 time_ns;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &time_ns, sts);
+	if (err)
+		return -EACCES;
+
+	*ts = ns_to_timespec64(time_ns);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_caps - Set PTP capabilities
+ * @adapter: Driver specific private structure
+ *
+ * This function sets the PTP functions.
+ */
+static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
+{
+	struct ptp_clock_info *info = &adapter->ptp->info;
+
+	snprintf(info->name, sizeof(info->name), "%s-%s-clk",
+		 KBUILD_MODNAME, pci_name(adapter->pdev));
+
+	info->owner = THIS_MODULE;
+	info->gettimex64 = idpf_ptp_gettimex64;
+
+#if IS_ENABLED(CONFIG_ARM_ARCH_TIMER)
+	info->getcrosststamp = idpf_ptp_get_crosststamp;
+#elif IS_ENABLED(CONFIG_X86)
+	if (pcie_ptm_enabled(adapter->pdev) &&
+	    boot_cpu_has(X86_FEATURE_ART) &&
+	    boot_cpu_has(X86_FEATURE_TSC_KNOWN_FREQ))
+		info->getcrosststamp = idpf_ptp_get_crosststamp;
+#endif /* CONFIG_ARM_ARCH_TIMER */
+}
+
 /**
  * idpf_ptp_create_clock - Create PTP clock device for userspace
  * @adapter: Driver specific private structure
@@ -16,6 +268,8 @@ static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
 {
 	struct ptp_clock *clock;
 
+	idpf_ptp_set_caps(adapter);
+
 	/* Attempt to register the clock before enabling the hardware. */
 	clock = ptp_clock_register(&adapter->ptp->info,
 				   &adapter->pdev->dev);
@@ -56,6 +310,15 @@ int idpf_ptp_init(struct idpf_adapter *adapter)
 	/* add a back pointer to adapter */
 	adapter->ptp->adapter = adapter;
 
+	if (adapter->dev_ops.reg_ops.ptp_reg_init)
+		adapter->dev_ops.reg_ops.ptp_reg_init(adapter);
+
+	err = idpf_ptp_get_caps(adapter);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to get PTP caps err %d\n", err);
+		goto free_ptp;
+	}
+
 	err = idpf_ptp_create_clock(adapter);
 	if (err)
 		goto free_ptp;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index d009417bf9473..68aa7a0a05d0d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -6,21 +6,101 @@
 
 #include <linux/ptp_clock_kernel.h>
 
+/**
+ * struct idpf_ptp_cmd - PTP command masks
+ * @exec_cmd_mask: mask to trigger command execution
+ * @shtime_enable_mask: mask to enable shadow time
+ */
+struct idpf_ptp_cmd {
+	u32 exec_cmd_mask;
+	u32 shtime_enable_mask;
+};
+
+/* struct idpf_ptp_dev_clk_regs - PTP device registers
+ * @dev_clk_ns_l: low part of the device clock register
+ * @dev_clk_ns_h: high part of the device clock register
+ * @phy_clk_ns_l: low part of the PHY clock register
+ * @phy_clk_ns_h: high part of the PHY clock register
+ * @sys_time_ns_l: low part of the system time register
+ * @sys_time_ns_h: high part of the system time register
+ * @cmd: PTP command register
+ * @phy_cmd: PHY command register
+ * @cmd_sync: PTP command synchronization register
+ */
+struct idpf_ptp_dev_clk_regs {
+	/* Main clock */
+	void __iomem *dev_clk_ns_l;
+	void __iomem *dev_clk_ns_h;
+
+	/* PHY timer */
+	void __iomem *phy_clk_ns_l;
+	void __iomem *phy_clk_ns_h;
+
+	/* System time */
+	void __iomem *sys_time_ns_l;
+	void __iomem *sys_time_ns_h;
+
+	/* Command */
+	void __iomem *cmd;
+	void __iomem *phy_cmd;
+	void __iomem *cmd_sync;
+};
+
+/**
+ * enum idpf_ptp_access - the type of access to PTP operations
+ * @IDPF_PTP_NONE: no access
+ * @IDPF_PTP_DIRECT: direct access through BAR registers
+ * @IDPF_PTP_MAILBOX: access through mailbox messages
+ */
+enum idpf_ptp_access {
+	IDPF_PTP_NONE = 0,
+	IDPF_PTP_DIRECT,
+	IDPF_PTP_MAILBOX,
+};
+
 /**
  * struct idpf_ptp - PTP parameters
  * @info: structure defining PTP hardware capabilities
  * @clock: pointer to registered PTP clock device
  * @adapter: back pointer to the adapter
+ * @cmd: HW specific command masks
+ * @dev_clk_regs: the set of registers to access the device clock
+ * @caps: PTP capabilities negotiated with the Control Plane
+ * @get_dev_clk_time_access: access type for getting the device clock time
+ * @get_cross_tstamp_access: access type for the cross timestamping
+ * @rsv: reserved bits
  */
 struct idpf_ptp {
 	struct ptp_clock_info info;
 	struct ptp_clock *clock;
 	struct idpf_adapter *adapter;
+	struct idpf_ptp_cmd cmd;
+	struct idpf_ptp_dev_clk_regs dev_clk_regs;
+	u32 caps;
+	enum idpf_ptp_access get_dev_clk_time_access:2;
+	enum idpf_ptp_access get_cross_tstamp_access:2;
+	u32 rsv:28;
 };
 
+/**
+ * idpf_ptp_info_to_adapter - get driver adapter struct from ptp_clock_info
+ * @info: pointer to ptp_clock_info struct
+ *
+ * Return: pointer to the corresponding adapter struct
+ */
+static inline struct idpf_adapter *
+idpf_ptp_info_to_adapter(const struct ptp_clock_info *info)
+{
+	const struct idpf_ptp *ptp = container_of_const(info, struct idpf_ptp,
+							info);
+	return ptp->adapter;
+}
+
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int idpf_ptp_init(struct idpf_adapter *adapter);
 void idpf_ptp_release(struct idpf_adapter *adapter);
+int idpf_ptp_get_caps(struct idpf_adapter *adapter);
+void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
 #else /* CONFIG_PTP_1588_CLOCK */
 static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 {
@@ -28,5 +108,14 @@ static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 }
 
 static inline void idpf_ptp_release(struct idpf_adapter *adapter) { }
+
+static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
+
 #endif /* CONFIG_PTP_1588_CLOCK */
 #endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
new file mode 100644
index 0000000000000..123bc0008d43f
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -0,0 +1,95 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2024 Intel Corporation */
+
+#include "idpf.h"
+#include "idpf_ptp.h"
+#include "idpf_virtchnl.h"
+
+/**
+ * idpf_ptp_get_caps - Send virtchnl get ptp capabilities message
+ * @adapter: Driver specific private structure
+ *
+ * Send virtchnl get PTP capabilities message.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+int idpf_ptp_get_caps(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_ptp_get_caps *recv_ptp_caps_msg __free(kfree) = NULL;
+	struct virtchnl2_ptp_get_caps send_ptp_caps_msg = {
+		.caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME |
+				    VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB)
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
+		.send_buf.iov_base = &send_ptp_caps_msg,
+		.send_buf.iov_len = sizeof(send_ptp_caps_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	struct virtchnl2_ptp_cross_time_reg_offsets cross_tstamp_offsets;
+	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
+	struct idpf_ptp *ptp = adapter->ptp;
+	enum idpf_ptp_access access_type;
+	u32 temp_offset;
+	int reply_sz;
+
+	recv_ptp_caps_msg = kzalloc(sizeof(struct virtchnl2_ptp_get_caps),
+				    GFP_KERNEL);
+	if (!recv_ptp_caps_msg)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = recv_ptp_caps_msg;
+	xn_params.recv_buf.iov_len = sizeof(*recv_ptp_caps_msg);
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	else if (reply_sz != sizeof(*recv_ptp_caps_msg))
+		return -EIO;
+
+	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
+
+	/* Determine the access type for the PTP features */
+	idpf_ptp_get_features_access(adapter);
+
+	access_type = ptp->get_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		goto cross_tstamp;
+
+	clock_offsets = recv_ptp_caps_msg->clk_offsets;
+
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_l);
+	ptp->dev_clk_regs.dev_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.dev_clk_ns_h);
+	ptp->dev_clk_regs.dev_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_l);
+	ptp->dev_clk_regs.phy_clk_ns_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.phy_clk_ns_h);
+	ptp->dev_clk_regs.phy_clk_ns_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clock_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+cross_tstamp:
+	access_type = ptp->get_cross_tstamp_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		return 0;
+
+	cross_tstamp_offsets = recv_ptp_caps_msg->cross_time_offsets;
+
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_l);
+	ptp->dev_clk_regs.sys_time_ns_l = idpf_get_reg_addr(adapter,
+							    temp_offset);
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.sys_time_ns_h);
+	ptp->dev_clk_regs.sys_time_ns_h = idpf_get_reg_addr(adapter,
+							    temp_offset);
+	temp_offset = le32_to_cpu(cross_tstamp_offsets.cmd_sync_trigger);
+	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
+
+	return 0;
+}

From 56f37386de2292de9fc3683556506b9c771577a4 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:20 -0700
Subject: [PATCH 2609/2753] idpf: add mailbox access to read PTP clock time

When the access to read PTP clock is specified as mailbox, the driver
needs to send virtchnl message to perform PTP actions. Message is sent
using idpf_mbq_opc_send_msg_to_peer_drv mailbox opcode, with the parameters
received during PTP capabilities negotiation.

Add functions to recognize PTP messages, move them to dedicated secondary
mailbox, read the PTP clock time and cross timestamp using mailbox
messages.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/intel/idpf/idpf_controlq_api.h   |  3 +
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 66 +++++++++++++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    | 43 ++++++++++
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   | 47 +++++++++++
 .../ethernet/intel/idpf/idpf_virtchnl_ptp.c   | 83 +++++++++++++++++++
 5 files changed, 242 insertions(+)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
index e8e046ef2f0d7..9642494a67d88 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq_api.h
@@ -123,9 +123,12 @@ struct idpf_ctlq_info {
 /**
  * enum idpf_mbx_opc - PF/VF mailbox commands
  * @idpf_mbq_opc_send_msg_to_cp: used by PF or VF to send a message to its CP
+ * @idpf_mbq_opc_send_msg_to_peer_drv: used by PF or VF to send a message to
+ *				       any peer driver
  */
 enum idpf_mbx_opc {
 	idpf_mbq_opc_send_msg_to_cp		= 0x0801,
+	idpf_mbq_opc_send_msg_to_peer_drv	= 0x0804,
 };
 
 /* API supported for control queue management */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 34257fabd6a05..7d7d399a3de04 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -95,6 +95,37 @@ static u64 idpf_ptp_read_src_clk_reg_direct(struct idpf_adapter *adapter,
 	return ((u64)hi << 32) | lo;
 }
 
+/**
+ * idpf_ptp_read_src_clk_reg_mailbox - Read the main timer value through mailbox
+ * @adapter: Driver specific private structure
+ * @sts: Optional parameter for holding a pair of system timestamps from
+ *	 the system clock. Will be ignored when NULL is given.
+ * @src_clk: Returned main timer value in nanoseconds unit
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_read_src_clk_reg_mailbox(struct idpf_adapter *adapter,
+					     struct ptp_system_timestamp *sts,
+					     u64 *src_clk)
+{
+	struct idpf_ptp_dev_timers clk_time;
+	int err;
+
+	/* Read the system timestamp pre PHC read */
+	ptp_read_system_prets(sts);
+
+	err = idpf_ptp_get_dev_clk_time(adapter, &clk_time);
+	if (err)
+		return err;
+
+	/* Read the system timestamp post PHC read */
+	ptp_read_system_postts(sts);
+
+	*src_clk = clk_time.dev_clk_time_ns;
+
+	return 0;
+}
+
 /**
  * idpf_ptp_read_src_clk_reg - Read the main timer value
  * @adapter: Driver specific private structure
@@ -110,6 +141,8 @@ static int idpf_ptp_read_src_clk_reg(struct idpf_adapter *adapter, u64 *src_clk,
 	switch (adapter->ptp->get_dev_clk_time_access) {
 	case IDPF_PTP_NONE:
 		return -EOPNOTSUPP;
+	case IDPF_PTP_MAILBOX:
+		return idpf_ptp_read_src_clk_reg_mailbox(adapter, sts, src_clk);
 	case IDPF_PTP_DIRECT:
 		*src_clk = idpf_ptp_read_src_clk_reg_direct(adapter, sts);
 		break;
@@ -146,6 +179,31 @@ static void idpf_ptp_get_sync_device_time_direct(struct idpf_adapter *adapter,
 	*sys_time = ((u64)sys_time_hi << 32) | sys_time_lo;
 }
 
+/**
+ * idpf_ptp_get_sync_device_time_mailbox - Get the cross time stamp values
+ *					   through mailbox
+ * @adapter: Driver specific private structure
+ * @dev_time: 64bit main timer value expressed in nanoseconds
+ * @sys_time: 64bit system time value expressed in nanoseconds
+ *
+ * Return: a pair of cross timestamp values on success, -errno otherwise.
+ */
+static int idpf_ptp_get_sync_device_time_mailbox(struct idpf_adapter *adapter,
+						 u64 *dev_time, u64 *sys_time)
+{
+	struct idpf_ptp_dev_timers cross_time;
+	int err;
+
+	err = idpf_ptp_get_cross_time(adapter, &cross_time);
+	if (err)
+		return err;
+
+	*dev_time = cross_time.dev_clk_time_ns;
+	*sys_time = cross_time.sys_time_ns;
+
+	return err;
+}
+
 /**
  * idpf_ptp_get_sync_device_time - Get the cross time stamp info
  * @device: Current device time
@@ -161,10 +219,18 @@ static int idpf_ptp_get_sync_device_time(ktime_t *device,
 {
 	struct idpf_adapter *adapter = ctx;
 	u64 ns_time_dev, ns_time_sys;
+	int err;
 
 	switch (adapter->ptp->get_cross_tstamp_access) {
 	case IDPF_PTP_NONE:
 		return -EOPNOTSUPP;
+	case IDPF_PTP_MAILBOX:
+		err =  idpf_ptp_get_sync_device_time_mailbox(adapter,
+							     &ns_time_dev,
+							     &ns_time_sys);
+		if (err)
+			return err;
+		break;
 	case IDPF_PTP_DIRECT:
 		idpf_ptp_get_sync_device_time_direct(adapter, &ns_time_dev,
 						     &ns_time_sys);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index 68aa7a0a05d0d..572ee0e79ba26 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -58,6 +58,19 @@ enum idpf_ptp_access {
 	IDPF_PTP_MAILBOX,
 };
 
+/**
+ * struct idpf_ptp_secondary_mbx - PTP secondary mailbox
+ * @peer_mbx_q_id: PTP mailbox queue ID
+ * @peer_id: Peer ID for PTP Device Control daemon
+ * @valid: indicates whether secondary mailblox is supported by the Control
+ *	   Plane
+ */
+struct idpf_ptp_secondary_mbx {
+	u16 peer_mbx_q_id;
+	u16 peer_id;
+	bool valid:1;
+};
+
 /**
  * struct idpf_ptp - PTP parameters
  * @info: structure defining PTP hardware capabilities
@@ -69,6 +82,7 @@ enum idpf_ptp_access {
  * @get_dev_clk_time_access: access type for getting the device clock time
  * @get_cross_tstamp_access: access type for the cross timestamping
  * @rsv: reserved bits
+ * @secondary_mbx: parameters for using dedicated PTP mailbox
  */
 struct idpf_ptp {
 	struct ptp_clock_info info;
@@ -80,6 +94,7 @@ struct idpf_ptp {
 	enum idpf_ptp_access get_dev_clk_time_access:2;
 	enum idpf_ptp_access get_cross_tstamp_access:2;
 	u32 rsv:28;
+	struct idpf_ptp_secondary_mbx secondary_mbx;
 };
 
 /**
@@ -96,11 +111,25 @@ idpf_ptp_info_to_adapter(const struct ptp_clock_info *info)
 	return ptp->adapter;
 }
 
+/**
+ * struct idpf_ptp_dev_timers - System time and device time values
+ * @sys_time_ns: system time value expressed in nanoseconds
+ * @dev_clk_time_ns: device clock time value expressed in nanoseconds
+ */
+struct idpf_ptp_dev_timers {
+	u64 sys_time_ns;
+	u64 dev_clk_time_ns;
+};
+
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int idpf_ptp_init(struct idpf_adapter *adapter);
 void idpf_ptp_release(struct idpf_adapter *adapter);
 int idpf_ptp_get_caps(struct idpf_adapter *adapter);
 void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time);
+int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			    struct idpf_ptp_dev_timers *cross_time);
 #else /* CONFIG_PTP_1588_CLOCK */
 static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 {
@@ -117,5 +146,19 @@ static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 static inline void
 idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
 
+static inline int
+idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			  struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			struct idpf_ptp_dev_timers *cross_time)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_PTP_1588_CLOCK */
 #endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index e27f3f2777a26..0fc2be15b5395 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -154,6 +154,50 @@ static int idpf_mb_clean(struct idpf_adapter *adapter)
 	return err;
 }
 
+#if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
+/**
+ * idpf_ptp_is_mb_msg - Check if the message is PTP-related
+ * @op: virtchnl opcode
+ *
+ * Return: true if msg is PTP-related, false otherwise.
+ */
+static bool idpf_ptp_is_mb_msg(u32 op)
+{
+	switch (op) {
+	case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_CROSS_TIME:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * idpf_prepare_ptp_mb_msg - Prepare PTP related message
+ *
+ * @adapter: Driver specific private structure
+ * @op: virtchnl opcode
+ * @ctlq_msg: Corresponding control queue message
+ */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{
+	/* If the message is PTP-related and the secondary mailbox is available,
+	 * send the message through the secondary mailbox.
+	 */
+	if (!idpf_ptp_is_mb_msg(op) || !adapter->ptp->secondary_mbx.valid)
+		return;
+
+	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_peer_drv;
+	ctlq_msg->func_id = adapter->ptp->secondary_mbx.peer_mbx_q_id;
+	ctlq_msg->host_id = adapter->ptp->secondary_mbx.peer_id;
+}
+#else /* !CONFIG_PTP_1588_CLOCK */
+static void idpf_prepare_ptp_mb_msg(struct idpf_adapter *adapter, u32 op,
+				    struct idpf_ctlq_msg *ctlq_msg)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_send_mb_msg - Send message over mailbox
  * @adapter: Driver specific private structure
@@ -197,6 +241,9 @@ int idpf_send_mb_msg(struct idpf_adapter *adapter, u32 op,
 
 	ctlq_msg->opcode = idpf_mbq_opc_send_msg_to_cp;
 	ctlq_msg->func_id = 0;
+
+	idpf_prepare_ptp_mb_msg(adapter, op, ctlq_msg);
+
 	ctlq_msg->data_len = msg_size;
 	ctlq_msg->cookie.mbx.chnl_opcode = op;
 	ctlq_msg->cookie.mbx.chnl_retval = 0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
index 123bc0008d43f..e51fa16d13cd4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -30,6 +30,7 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 	};
 	struct virtchnl2_ptp_cross_time_reg_offsets cross_tstamp_offsets;
 	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
+	struct idpf_ptp_secondary_mbx *scnd_mbx;
 	struct idpf_ptp *ptp = adapter->ptp;
 	enum idpf_ptp_access access_type;
 	u32 temp_offset;
@@ -51,6 +52,16 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 
 	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
 
+	scnd_mbx = &ptp->secondary_mbx;
+	scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id);
+
+	/* if the ptp_mb_q_id holds invalid value (0xffff), the secondary
+	 * mailbox is not supported.
+	 */
+	scnd_mbx->valid = scnd_mbx->peer_mbx_q_id != 0xffff;
+	if (scnd_mbx->valid)
+		scnd_mbx->peer_id = recv_ptp_caps_msg->peer_id;
+
 	/* Determine the access type for the PTP features */
 	idpf_ptp_get_features_access(adapter);
 
@@ -93,3 +104,75 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 
 	return 0;
 }
+
+/**
+ * idpf_ptp_get_dev_clk_time - Send virtchnl get device clk time message
+ * @adapter: Driver specific private structure
+ * @dev_clk_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get time message to get the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
+			      struct idpf_ptp_dev_timers *dev_clk_time)
+{
+	struct virtchnl2_ptp_get_dev_clk_time get_dev_clk_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME,
+		.send_buf.iov_base = &get_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.recv_buf.iov_base = &get_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(get_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+	u64 dev_time;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(get_dev_clk_time_msg))
+		return -EIO;
+
+	dev_time = le64_to_cpu(get_dev_clk_time_msg.dev_time_ns);
+	dev_clk_time->dev_clk_time_ns = dev_time;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_cross_time - Send virtchnl get cross time message
+ * @adapter: Driver specific private structure
+ * @cross_time: Pointer to the device clock structure where the value is set
+ *
+ * Send virtchnl get cross time message to get the time of the clock and the
+ * system time.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
+			    struct idpf_ptp_dev_timers *cross_time)
+{
+	struct virtchnl2_ptp_get_cross_time cross_time_msg;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_CROSS_TIME,
+		.send_buf.iov_base = &cross_time_msg,
+		.send_buf.iov_len = sizeof(cross_time_msg),
+		.recv_buf.iov_base = &cross_time_msg,
+		.recv_buf.iov_len = sizeof(cross_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(cross_time_msg))
+		return -EIO;
+
+	cross_time->dev_clk_time_ns = le64_to_cpu(cross_time_msg.dev_time_ns);
+	cross_time->sys_time_ns = le64_to_cpu(cross_time_msg.sys_time_ns);
+
+	return 0;
+}

From 1185f7aa08cf28c5e8d33ba00e072ad3134efea7 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:21 -0700
Subject: [PATCH 2610/2753] idpf: add PTP clock configuration

PTP clock configuration operations - set time, adjust time and adjust
frequency are required to control the clock and maintain synchronization
process.

Extend get PTP capabilities function to request for the clock adjustments
and add functions to enable these actions using dedicated virtchnl
messages.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 194 ++++++++++++++++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    |  43 +++-
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   |   3 +
 .../ethernet/intel/idpf/idpf_virtchnl_ptp.c   | 142 ++++++++++++-
 4 files changed, 379 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 7d7d399a3de04..5aa00b9177b21 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -48,6 +48,20 @@ void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
 	ptp->get_cross_tstamp_access = idpf_ptp_get_access(adapter,
 							   direct,
 							   mailbox);
+
+	/* Set the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	mailbox = VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME;
+	ptp->set_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
+
+	/* Adjust the device clock time */
+	direct = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK;
+	mailbox = VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB;
+	ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter,
+							   direct,
+							   mailbox);
 }
 
 /**
@@ -296,6 +310,157 @@ static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
 	return 0;
 }
 
+/**
+ * idpf_ptp_settime64 - Set the time of the clock
+ * @info: the driver's PTP info structure
+ * @ts: timespec64 structure that holds the new time value
+ *
+ * Set the device clock to the user input value. The conversion from timespec
+ * to ns happens in the write function.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_settime64(struct ptp_clock_info *info,
+			      const struct timespec64 *ts)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+	u64 ns;
+
+	access = adapter->ptp->set_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	ns = timespec64_to_ns(ts);
+
+	err = idpf_ptp_set_dev_clk_time(adapter, ns);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to set the time, err: %pe\n",
+			ERR_PTR(err));
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjtime_nonatomic - Do a non-atomic clock adjustment
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime_nonatomic(struct ptp_clock_info *info, s64 delta)
+{
+	struct timespec64 now, then;
+	int err;
+
+	err = idpf_ptp_gettimex64(info, &now, NULL);
+	if (err)
+		return err;
+
+	then = ns_to_timespec64(delta);
+	now = timespec64_add(now, then);
+
+	return idpf_ptp_settime64(info, &now);
+}
+
+/**
+ * idpf_ptp_adjtime - Adjust the time of the clock by the indicated delta
+ * @info: the driver's PTP info structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	/* Hardware only supports atomic adjustments using signed 32-bit
+	 * integers. For any adjustment outside this range, perform
+	 * a non-atomic get->adjust->set flow.
+	 */
+	if (delta > S32_MAX || delta < S32_MIN)
+		return idpf_ptp_adjtime_nonatomic(info, delta);
+
+	err = idpf_ptp_adj_dev_clk_time(adapter, delta);
+	if (err) {
+		pci_err(adapter->pdev, "Failed to adjust the clock with delta %lld err: %pe\n",
+			delta, ERR_PTR(err));
+		return err;
+	}
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adjfine - Adjust clock increment rate
+ * @info: the driver's PTP info structure
+ * @scaled_ppm: Parts per million with 16-bit fractional field
+ *
+ * Adjust the frequency of the clock by the indicated scaled ppm from the
+ * base frequency.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_ptp_adjfine(struct ptp_clock_info *info, long scaled_ppm)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+	enum idpf_ptp_access access;
+	u64 incval, diff;
+	int err;
+
+	access = adapter->ptp->adj_dev_clk_time_access;
+	if (access != IDPF_PTP_MAILBOX)
+		return -EOPNOTSUPP;
+
+	incval = adapter->ptp->base_incval;
+
+	diff = adjust_by_scaled_ppm(incval, scaled_ppm);
+	err = idpf_ptp_adj_dev_clk_fine(adapter, diff);
+	if (err)
+		pci_err(adapter->pdev, "Failed to adjust clock increment rate for scaled ppm %ld %pe\n",
+			scaled_ppm, ERR_PTR(err));
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_verify_pin - Verify if pin supports requested pin function
+ * @info: the driver's PTP info structure
+ * @pin: Pin index
+ * @func: Assigned function
+ * @chan: Assigned channel
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_verify_pin(struct ptp_clock_info *info, unsigned int pin,
+			       enum ptp_pin_function func, unsigned int chan)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * idpf_ptp_gpio_enable - Enable/disable ancillary features of PHC
+ * @info: the driver's PTP info structure
+ * @rq: The requested feature to change
+ * @on: Enable/disable flag
+ *
+ * Return: EOPNOTSUPP as not supported yet.
+ */
+static int idpf_ptp_gpio_enable(struct ptp_clock_info *info,
+				struct ptp_clock_request *rq, int on)
+{
+	return -EOPNOTSUPP;
+}
+
 /**
  * idpf_ptp_set_caps - Set PTP capabilities
  * @adapter: Driver specific private structure
@@ -310,7 +475,13 @@ static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
 		 KBUILD_MODNAME, pci_name(adapter->pdev));
 
 	info->owner = THIS_MODULE;
+	info->max_adj = adapter->ptp->max_adj;
 	info->gettimex64 = idpf_ptp_gettimex64;
+	info->settime64 = idpf_ptp_settime64;
+	info->adjfine = idpf_ptp_adjfine;
+	info->adjtime = idpf_ptp_adjtime;
+	info->verify = idpf_ptp_verify_pin;
+	info->enable = idpf_ptp_gpio_enable;
 
 #if IS_ENABLED(CONFIG_ARM_ARCH_TIMER)
 	info->getcrosststamp = idpf_ptp_get_crosststamp;
@@ -362,6 +533,7 @@ static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
  */
 int idpf_ptp_init(struct idpf_adapter *adapter)
 {
+	struct timespec64 ts;
 	int err;
 
 	if (!idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP)) {
@@ -389,10 +561,32 @@ int idpf_ptp_init(struct idpf_adapter *adapter)
 	if (err)
 		goto free_ptp;
 
+	/* Write the default increment time value if the clock adjustments
+	 * are enabled.
+	 */
+	if (adapter->ptp->adj_dev_clk_time_access != IDPF_PTP_NONE) {
+		err = idpf_ptp_adj_dev_clk_fine(adapter,
+						adapter->ptp->base_incval);
+		if (err)
+			goto remove_clock;
+	}
+
+	/* Write the initial time value if the set time operation is enabled */
+	if (adapter->ptp->set_dev_clk_time_access != IDPF_PTP_NONE) {
+		ts = ktime_to_timespec64(ktime_get_real());
+		err = idpf_ptp_settime64(&adapter->ptp->info, &ts);
+		if (err)
+			goto remove_clock;
+	}
+
 	pci_dbg(adapter->pdev, "PTP init successful\n");
 
 	return 0;
 
+remove_clock:
+	ptp_clock_unregister(adapter->ptp->clock);
+	adapter->ptp->clock = NULL;
+
 free_ptp:
 	kfree(adapter->ptp);
 	adapter->ptp = NULL;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index 572ee0e79ba26..e7ccdcbdbd475 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -40,6 +40,18 @@ struct idpf_ptp_dev_clk_regs {
 	void __iomem *sys_time_ns_l;
 	void __iomem *sys_time_ns_h;
 
+	/* Main timer adjustments */
+	void __iomem *incval_l;
+	void __iomem *incval_h;
+	void __iomem *shadj_l;
+	void __iomem *shadj_h;
+
+	/* PHY timer adjustments */
+	void __iomem *phy_incval_l;
+	void __iomem *phy_incval_h;
+	void __iomem *phy_shadj_l;
+	void __iomem *phy_shadj_h;
+
 	/* Command */
 	void __iomem *cmd;
 	void __iomem *phy_cmd;
@@ -76,11 +88,15 @@ struct idpf_ptp_secondary_mbx {
  * @info: structure defining PTP hardware capabilities
  * @clock: pointer to registered PTP clock device
  * @adapter: back pointer to the adapter
+ * @base_incval: base increment value of the PTP clock
+ * @max_adj: maximum adjustment of the PTP clock
  * @cmd: HW specific command masks
  * @dev_clk_regs: the set of registers to access the device clock
  * @caps: PTP capabilities negotiated with the Control Plane
  * @get_dev_clk_time_access: access type for getting the device clock time
  * @get_cross_tstamp_access: access type for the cross timestamping
+ * @set_dev_clk_time_access: access type for setting the device clock time
+ * @adj_dev_clk_time_access: access type for the adjusting the device clock
  * @rsv: reserved bits
  * @secondary_mbx: parameters for using dedicated PTP mailbox
  */
@@ -88,12 +104,16 @@ struct idpf_ptp {
 	struct ptp_clock_info info;
 	struct ptp_clock *clock;
 	struct idpf_adapter *adapter;
+	u64 base_incval;
+	u64 max_adj;
 	struct idpf_ptp_cmd cmd;
 	struct idpf_ptp_dev_clk_regs dev_clk_regs;
 	u32 caps;
 	enum idpf_ptp_access get_dev_clk_time_access:2;
 	enum idpf_ptp_access get_cross_tstamp_access:2;
-	u32 rsv:28;
+	enum idpf_ptp_access set_dev_clk_time_access:2;
+	enum idpf_ptp_access adj_dev_clk_time_access:2;
+	u8 rsv;
 	struct idpf_ptp_secondary_mbx secondary_mbx;
 };
 
@@ -130,6 +150,9 @@ int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
 			      struct idpf_ptp_dev_timers *dev_clk_time);
 int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
 			    struct idpf_ptp_dev_timers *cross_time);
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
 #else /* CONFIG_PTP_1588_CLOCK */
 static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 {
@@ -160,5 +183,23 @@ idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
 	return -EOPNOTSUPP;
 }
 
+static inline int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter,
+					    u64 time)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter,
+					    u64 incval)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter,
+					    s64 delta)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_PTP_1588_CLOCK */
 #endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 0fc2be15b5395..5bd25dbc0e4c3 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -166,6 +166,9 @@ static bool idpf_ptp_is_mb_msg(u32 op)
 	switch (op) {
 	case VIRTCHNL2_OP_PTP_GET_DEV_CLK_TIME:
 	case VIRTCHNL2_OP_PTP_GET_CROSS_TIME:
+	case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE:
+	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME:
 		return true;
 	default:
 		return false;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
index e51fa16d13cd4..5de4bf94049ba 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -20,7 +20,9 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 		.caps = cpu_to_le32(VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME |
 				    VIRTCHNL2_CAP_PTP_GET_DEVICE_CLK_TIME_MB |
 				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
-				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB)
+				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB |
+				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB)
 	};
 	struct idpf_vc_xn_params xn_params = {
 		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
@@ -29,6 +31,7 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
 	};
 	struct virtchnl2_ptp_cross_time_reg_offsets cross_tstamp_offsets;
+	struct virtchnl2_ptp_clk_adj_reg_offsets clk_adj_offsets;
 	struct virtchnl2_ptp_clk_reg_offsets clock_offsets;
 	struct idpf_ptp_secondary_mbx *scnd_mbx;
 	struct idpf_ptp *ptp = adapter->ptp;
@@ -51,6 +54,8 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 		return -EIO;
 
 	ptp->caps = le32_to_cpu(recv_ptp_caps_msg->caps);
+	ptp->base_incval = le64_to_cpu(recv_ptp_caps_msg->base_incval);
+	ptp->max_adj = le32_to_cpu(recv_ptp_caps_msg->max_adj);
 
 	scnd_mbx = &ptp->secondary_mbx;
 	scnd_mbx->peer_mbx_q_id = le16_to_cpu(recv_ptp_caps_msg->peer_mbx_q_id);
@@ -89,7 +94,7 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 cross_tstamp:
 	access_type = ptp->get_cross_tstamp_access;
 	if (access_type != IDPF_PTP_DIRECT)
-		return 0;
+		goto discipline_clock;
 
 	cross_tstamp_offsets = recv_ptp_caps_msg->cross_time_offsets;
 
@@ -102,6 +107,39 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 	temp_offset = le32_to_cpu(cross_tstamp_offsets.cmd_sync_trigger);
 	ptp->dev_clk_regs.cmd_sync = idpf_get_reg_addr(adapter, temp_offset);
 
+discipline_clock:
+	access_type = ptp->adj_dev_clk_time_access;
+	if (access_type != IDPF_PTP_DIRECT)
+		return 0;
+
+	clk_adj_offsets = recv_ptp_caps_msg->clk_adj_offsets;
+
+	/* Device clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_cmd_type);
+	ptp->dev_clk_regs.cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_l);
+	ptp->dev_clk_regs.incval_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_incval_h);
+	ptp->dev_clk_regs.incval_h = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_l);
+	ptp->dev_clk_regs.shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.dev_clk_shadj_h);
+	ptp->dev_clk_regs.shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
+	/* PHY clock offsets */
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_cmd_type);
+	ptp->dev_clk_regs.phy_cmd = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_l);
+	ptp->dev_clk_regs.phy_incval_l = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_incval_h);
+	ptp->dev_clk_regs.phy_incval_h = idpf_get_reg_addr(adapter,
+							   temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_l);
+	ptp->dev_clk_regs.phy_shadj_l = idpf_get_reg_addr(adapter, temp_offset);
+	temp_offset = le32_to_cpu(clk_adj_offsets.phy_clk_shadj_h);
+	ptp->dev_clk_regs.phy_shadj_h = idpf_get_reg_addr(adapter, temp_offset);
+
 	return 0;
 }
 
@@ -176,3 +214,103 @@ int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
 
 	return 0;
 }
+
+/**
+ * idpf_ptp_set_dev_clk_time - Send virtchnl set device time message
+ * @adapter: Driver specific private structure
+ * @time: New time value
+ *
+ * Send virtchnl set time message to set the time of the clock.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time)
+{
+	struct virtchnl2_ptp_set_dev_clk_time set_dev_clk_time_msg = {
+		.dev_time_ns = cpu_to_le64(time),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME,
+		.send_buf.iov_base = &set_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.recv_buf.iov_base = &set_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(set_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(set_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_time - Send virtchnl adj device clock time message
+ * @adapter: Driver specific private structure
+ * @delta: Offset in nanoseconds to adjust the time by
+ *
+ * Send virtchnl adj time message to adjust the clock by the indicated delta.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta)
+{
+	struct virtchnl2_ptp_adj_dev_clk_time adj_dev_clk_time_msg = {
+		.delta = cpu_to_le64(delta),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME,
+		.send_buf.iov_base = &adj_dev_clk_time_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.recv_buf.iov_base = &adj_dev_clk_time_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_time_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_time_msg))
+		return -EIO;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_adj_dev_clk_fine - Send virtchnl adj time message
+ * @adapter: Driver specific private structure
+ * @incval: Source timer increment value per clock cycle
+ *
+ * Send virtchnl adj fine message to adjust the frequency of the clock by
+ * incval.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval)
+{
+	struct virtchnl2_ptp_adj_dev_clk_fine adj_dev_clk_fine_msg = {
+		.incval = cpu_to_le64(incval),
+	};
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE,
+		.send_buf.iov_base = &adj_dev_clk_fine_msg,
+		.send_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.recv_buf.iov_base = &adj_dev_clk_fine_msg,
+		.recv_buf.iov_len = sizeof(adj_dev_clk_fine_msg),
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int reply_sz;
+
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+	if (reply_sz != sizeof(adj_dev_clk_fine_msg))
+		return -EIO;
+
+	return 0;
+}

From 9c87c6781ce14fcfecb0e0ef5166446448bf67e6 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:22 -0700
Subject: [PATCH 2611/2753] idpf: add Tx timestamp capabilities negotiation

Tx timestamp capabilities are negotiated for the uplink Vport.
Driver receives information about the number of available Tx timestamp
latches, the size of Tx timestamp value and the set of indexes used
for Tx timestamping.

Add function to get the Tx timestamp capabilities and parse the uplink
vport flag.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Co-developed-by: Emil Tantilov <emil.s.tantilov@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Co-developed-by: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Signed-off-by: Pavan Kumar Linga <pavan.kumar.linga@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/idpf.h        |  10 ++
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    |  65 +++++++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    |  95 ++++++++++++-
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   |  11 ++
 .../ethernet/intel/idpf/idpf_virtchnl_ptp.c   | 128 +++++++++++++++++-
 drivers/net/ethernet/intel/idpf/virtchnl2.h   |  12 +-
 6 files changed, 317 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index d5d5064d313bd..fe4d8ad75b044 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -292,6 +292,7 @@ struct idpf_port_stats {
  * @port_stats: per port csum, header split, and other offload stats
  * @link_up: True if link is up
  * @sw_marker_wq: workqueue for marker packets
+ * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping
  */
 struct idpf_vport {
 	u16 num_txq;
@@ -336,6 +337,8 @@ struct idpf_vport {
 	bool link_up;
 
 	wait_queue_head_t sw_marker_wq;
+
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
 };
 
 /**
@@ -480,6 +483,13 @@ struct idpf_vport_config {
 
 struct idpf_vc_xn_manager;
 
+#define idpf_for_each_vport(adapter, iter) \
+	for (struct idpf_vport **__##iter = &(adapter)->vports[0], \
+	     *iter = (adapter)->max_vports ? *__##iter : NULL; \
+	     iter; \
+	     iter = (++__##iter) < &(adapter)->vports[(adapter)->max_vports] ? \
+	     *__##iter : NULL)
+
 /**
  * struct idpf_adapter - Device data struct generated on probe
  * @pdev: PCI device struct given on probe
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 5aa00b9177b21..d2c629a88cc58 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -62,6 +62,13 @@ void idpf_ptp_get_features_access(const struct idpf_adapter *adapter)
 	ptp->adj_dev_clk_time_access = idpf_ptp_get_access(adapter,
 							   direct,
 							   mailbox);
+
+	/* Tx timestamping */
+	direct = VIRTCHNL2_CAP_PTP_TX_TSTAMPS;
+	mailbox = VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB;
+	ptp->tx_tstamp_access = idpf_ptp_get_access(adapter,
+						    direct,
+						    mailbox);
 }
 
 /**
@@ -521,6 +528,61 @@ static int idpf_ptp_create_clock(const struct idpf_adapter *adapter)
 	return 0;
 }
 
+/**
+ * idpf_ptp_release_vport_tstamp - Release the Tx timestamps trakcers for a
+ *				   given vport.
+ * @vport: Virtual port structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries for a
+ * given vport.
+ */
+static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
+	struct list_head *head;
+
+	/* Remove list with free latches */
+	spin_lock(&vport->tx_tstamp_caps->lock_free);
+
+	head = &vport->tx_tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	spin_unlock(&vport->tx_tstamp_caps->lock_free);
+
+	/* Remove list with latches in use */
+	spin_lock(&vport->tx_tstamp_caps->lock_in_use);
+
+	head = &vport->tx_tstamp_caps->latches_in_use;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	spin_unlock(&vport->tx_tstamp_caps->lock_in_use);
+
+	kfree(vport->tx_tstamp_caps);
+	vport->tx_tstamp_caps = NULL;
+}
+
+/**
+ * idpf_ptp_release_tstamp - Release the Tx timestamps trackers
+ * @adapter: Driver specific private structure
+ *
+ * Remove the queues and delete lists that tracks Tx timestamp entries.
+ */
+static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter)
+{
+	idpf_for_each_vport(adapter, vport) {
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			continue;
+
+		idpf_ptp_release_vport_tstamp(vport);
+	}
+}
+
 /**
  * idpf_ptp_init - Initialize PTP hardware clock support
  * @adapter: Driver specific private structure
@@ -605,6 +667,9 @@ void idpf_ptp_release(struct idpf_adapter *adapter)
 	if (!ptp)
 		return;
 
+	if (ptp->tx_tstamp_access != IDPF_PTP_NONE)
+		idpf_ptp_release_tstamp(adapter);
+
 	if (ptp->clock)
 		ptp_clock_unregister(ptp->clock);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index e7ccdcbdbd475..3a9763bc32575 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -83,6 +83,70 @@ struct idpf_ptp_secondary_mbx {
 	bool valid:1;
 };
 
+/**
+ * enum idpf_ptp_tx_tstamp_state - Tx timestamp states
+ * @IDPF_PTP_FREE: Tx timestamp index free to use
+ * @IDPF_PTP_REQUEST: Tx timestamp index set to the Tx descriptor
+ * @IDPF_PTP_READ_VALUE: Tx timestamp value ready to be read
+ */
+enum idpf_ptp_tx_tstamp_state {
+	IDPF_PTP_FREE,
+	IDPF_PTP_REQUEST,
+	IDPF_PTP_READ_VALUE,
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp_status - Parameters to track Tx timestamp
+ * @skb: the pointer to the SKB that received the completion tag
+ * @state: the state of the Tx timestamp
+ */
+struct idpf_ptp_tx_tstamp_status {
+	struct sk_buff *skb;
+	enum idpf_ptp_tx_tstamp_state state;
+};
+
+/**
+ * struct idpf_ptp_tx_tstamp - Parameters for Tx timestamping
+ * @list_member: the list member structure
+ * @tx_latch_reg_offset_l: Tx tstamp latch low register offset
+ * @tx_latch_reg_offset_h: Tx tstamp latch high register offset
+ * @skb: the pointer to the SKB for this timestamp request
+ * @tstamp: the Tx tstamp value
+ * @idx: the index of the Tx tstamp
+ */
+struct idpf_ptp_tx_tstamp {
+	struct list_head list_member;
+	u32 tx_latch_reg_offset_l;
+	u32 tx_latch_reg_offset_h;
+	struct sk_buff *skb;
+	u64 tstamp;
+	u32 idx;
+};
+
+/**
+ * struct idpf_ptp_vport_tx_tstamp_caps - Tx timestamp capabilities
+ * @vport_id: the vport id
+ * @num_entries: the number of negotiated Tx timestamp entries
+ * @tstamp_ns_lo_bit: first bit for nanosecond part of the timestamp
+ * @lock_in_use: the lock to the used latches list
+ * @lock_free: the lock to free the latches list
+ * @lock_status: the lock to the status tracker
+ * @latches_free: the list of the free Tx timestamps latches
+ * @latches_in_use: the list of the used Tx timestamps latches
+ * @tx_tstamp_status: Tx tstamp status tracker
+ */
+struct idpf_ptp_vport_tx_tstamp_caps {
+	u32 vport_id;
+	u16 num_entries;
+	u16 tstamp_ns_lo_bit;
+	spinlock_t lock_in_use;
+	spinlock_t lock_free;
+	spinlock_t lock_status;
+	struct list_head latches_free;
+	struct list_head latches_in_use;
+	struct idpf_ptp_tx_tstamp_status tx_tstamp_status[];
+};
+
 /**
  * struct idpf_ptp - PTP parameters
  * @info: structure defining PTP hardware capabilities
@@ -97,6 +161,7 @@ struct idpf_ptp_secondary_mbx {
  * @get_cross_tstamp_access: access type for the cross timestamping
  * @set_dev_clk_time_access: access type for setting the device clock time
  * @adj_dev_clk_time_access: access type for the adjusting the device clock
+ * @tx_tstamp_access: access type for the Tx timestamp value read
  * @rsv: reserved bits
  * @secondary_mbx: parameters for using dedicated PTP mailbox
  */
@@ -113,7 +178,8 @@ struct idpf_ptp {
 	enum idpf_ptp_access get_cross_tstamp_access:2;
 	enum idpf_ptp_access set_dev_clk_time_access:2;
 	enum idpf_ptp_access adj_dev_clk_time_access:2;
-	u8 rsv;
+	enum idpf_ptp_access tx_tstamp_access:2;
+	u8 rsv:6;
 	struct idpf_ptp_secondary_mbx secondary_mbx;
 };
 
@@ -141,6 +207,27 @@ struct idpf_ptp_dev_timers {
 	u64 dev_clk_time_ns;
 };
 
+/**
+ * idpf_ptp_is_vport_tx_tstamp_ena - Verify the Tx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Tx timestamp capabilities are negotiated with the Control Plane only if the
+ * device clock value can be read, Tx timestamp access type is different than
+ * NONE, and the PTP clock for the adapter is created. When all those conditions
+ * are satisfied, Tx timestamp feature is enabled and tx_tstamp_caps is
+ * allocated and fulfilled.
+ *
+ * Return: true if the Tx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->tx_tstamp_caps)
+		return false;
+	else
+		return true;
+}
+
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int idpf_ptp_init(struct idpf_adapter *adapter);
 void idpf_ptp_release(struct idpf_adapter *adapter);
@@ -153,6 +240,7 @@ int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
 int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
 int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
 int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport);
 #else /* CONFIG_PTP_1588_CLOCK */
 static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 {
@@ -201,5 +289,10 @@ static inline int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter,
 	return -EOPNOTSUPP;
 }
 
+static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_PTP_1588_CLOCK */
 #endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 5bd25dbc0e4c3..be45d09e913e6 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -169,6 +169,8 @@ static bool idpf_ptp_is_mb_msg(u32 op)
 	case VIRTCHNL2_OP_PTP_SET_DEV_CLK_TIME:
 	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE:
 	case VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS:
+	case VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP:
 		return true;
 	default:
 		return false;
@@ -3134,6 +3136,7 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	u16 rx_itr[] = {2, 8, 32, 96, 128};
 	struct idpf_rss_data *rss_data;
 	u16 idx = vport->idx;
+	int err;
 
 	vport_config = adapter->vport_config[idx];
 	rss_data = &vport_config->user_config.rss_data;
@@ -3168,6 +3171,14 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 	idpf_vport_alloc_vec_indexes(vport);
 
 	vport->crc_enable = adapter->crc_enable;
+
+	if (!(vport_msg->vport_flags &
+	      cpu_to_le16(VIRTCHNL2_VPORT_UPLINK_PORT)))
+		return;
+
+	err = idpf_ptp_get_vport_tstamps_caps(vport);
+	if (err)
+		pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n");
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
index 5de4bf94049ba..12e776aedf631 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -22,7 +22,8 @@ int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME |
 				    VIRTCHNL2_CAP_PTP_GET_CROSS_TIME_MB |
 				    VIRTCHNL2_CAP_PTP_SET_DEVICE_CLK_TIME_MB |
-				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB)
+				    VIRTCHNL2_CAP_PTP_ADJ_DEVICE_CLK_MB |
+				    VIRTCHNL2_CAP_PTP_TX_TSTAMPS_MB)
 	};
 	struct idpf_vc_xn_params xn_params = {
 		.vc_op = VIRTCHNL2_OP_PTP_GET_CAPS,
@@ -314,3 +315,128 @@ int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval)
 
 	return 0;
 }
+
+/**
+ * idpf_ptp_get_vport_tstamps_caps - Send virtchnl to get tstamps caps for vport
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get vport tstamps caps message to receive the set of tstamp
+ * capabilities per vport.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps send_tx_tstamp_caps;
+	struct virtchnl2_ptp_get_vport_tx_tstamp_caps *rcv_tx_tstamp_caps;
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *ptp_tx_tstamps, *tmp;
+	struct virtchnl2_ptp_tx_tstamp_latch_caps tx_tstamp_latch_caps;
+	struct idpf_ptp_vport_tx_tstamp_caps *tstamp_caps;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS,
+		.send_buf.iov_base = &send_tx_tstamp_caps,
+		.send_buf.iov_len = sizeof(send_tx_tstamp_caps),
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	enum idpf_ptp_access tstamp_access, get_dev_clk_access;
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	struct list_head *head;
+	int err = 0, reply_sz;
+	u16 num_latches;
+	u32 size;
+
+	if (!ptp)
+		return -EOPNOTSUPP;
+
+	tstamp_access = ptp->tx_tstamp_access;
+	get_dev_clk_access = ptp->get_dev_clk_time_access;
+	if (tstamp_access == IDPF_PTP_NONE ||
+	    get_dev_clk_access == IDPF_PTP_NONE)
+		return -EOPNOTSUPP;
+
+	rcv_tx_tstamp_caps = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcv_tx_tstamp_caps)
+		return -ENOMEM;
+
+	send_tx_tstamp_caps.vport_id = cpu_to_le32(vport->vport_id);
+	xn_params.recv_buf.iov_base = rcv_tx_tstamp_caps;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	if (reply_sz < 0) {
+		err = reply_sz;
+		goto get_tstamp_caps_out;
+	}
+
+	num_latches = le16_to_cpu(rcv_tx_tstamp_caps->num_latches);
+	size = struct_size(rcv_tx_tstamp_caps, tstamp_latches, num_latches);
+	if (reply_sz != size) {
+		err = -EIO;
+		goto get_tstamp_caps_out;
+	}
+
+	size = struct_size(tstamp_caps, tx_tstamp_status, num_latches);
+	tstamp_caps = kzalloc(size, GFP_KERNEL);
+	if (!tstamp_caps) {
+		err = -ENOMEM;
+		goto get_tstamp_caps_out;
+	}
+
+	tstamp_caps->num_entries = num_latches;
+	INIT_LIST_HEAD(&tstamp_caps->latches_in_use);
+	INIT_LIST_HEAD(&tstamp_caps->latches_free);
+
+	spin_lock_init(&tstamp_caps->lock_free);
+	spin_lock_init(&tstamp_caps->lock_in_use);
+	spin_lock_init(&tstamp_caps->lock_status);
+
+	tstamp_caps->tstamp_ns_lo_bit = rcv_tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	ptp_tx_tstamps = kcalloc(tstamp_caps->num_entries,
+				 sizeof(*ptp_tx_tstamp), GFP_KERNEL);
+	if (!ptp_tx_tstamps) {
+		err = -ENOMEM;
+		goto err_free_ptp_tx_stamp_list;
+	}
+
+	for (u16 i = 0; i < tstamp_caps->num_entries; i++) {
+		__le32 offset_l, offset_h;
+
+		ptp_tx_tstamp = ptp_tx_tstamps + i;
+		tx_tstamp_latch_caps = rcv_tx_tstamp_caps->tstamp_latches[i];
+
+		if (tstamp_access != IDPF_PTP_DIRECT)
+			goto skip_offsets;
+
+		offset_l = tx_tstamp_latch_caps.tx_latch_reg_offset_l;
+		offset_h = tx_tstamp_latch_caps.tx_latch_reg_offset_h;
+		ptp_tx_tstamp->tx_latch_reg_offset_l = le32_to_cpu(offset_l);
+		ptp_tx_tstamp->tx_latch_reg_offset_h = le32_to_cpu(offset_h);
+
+skip_offsets:
+		ptp_tx_tstamp->idx = tx_tstamp_latch_caps.index;
+
+		list_add(&ptp_tx_tstamp->list_member,
+			 &tstamp_caps->latches_free);
+
+		tstamp_caps->tx_tstamp_status[i].state = IDPF_PTP_FREE;
+	}
+
+	vport->tx_tstamp_caps = tstamp_caps;
+	kfree(rcv_tx_tstamp_caps);
+
+	return 0;
+
+err_free_ptp_tx_stamp_list:
+	head = &tstamp_caps->latches_free;
+	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		list_del(&ptp_tx_tstamp->list_member);
+		kfree(ptp_tx_tstamp);
+	}
+
+	kfree(tstamp_caps);
+get_tstamp_caps_out:
+	kfree(rcv_tx_tstamp_caps);
+
+	return err;
+}
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index 44a5ee84ed606..07235f1b4c5cd 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -569,6 +569,14 @@ struct virtchnl2_queue_reg_chunks {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 
+/**
+ * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities.
+ * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports
+ */
+enum virtchnl2_vport_flags {
+	VIRTCHNL2_VPORT_UPLINK_PORT	= BIT(0),
+};
+
 /**
  * struct virtchnl2_create_vport - Create vport config info.
  * @vport_type: See enum virtchnl2_vport_type.
@@ -587,7 +595,7 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
  * @max_mtu: Max MTU. CP populates this field on response.
  * @vport_id: Vport id. CP populates this field on response.
  * @default_mac_addr: Default MAC address.
- * @pad: Padding.
+ * @vport_flags: See enum virtchnl2_vport_flags.
  * @rx_desc_ids: See VIRTCHNL2_RX_DESC_IDS definitions.
  * @tx_desc_ids: See VIRTCHNL2_TX_DESC_IDS definitions.
  * @pad1: Padding.
@@ -620,7 +628,7 @@ struct virtchnl2_create_vport {
 	__le16 max_mtu;
 	__le32 vport_id;
 	u8 default_mac_addr[ETH_ALEN];
-	__le16 pad;
+	__le16 vport_flags;
 	__le64 rx_desc_ids;
 	__le64 tx_desc_ids;
 	u8 pad1[72];

From ea7511b549632a248e1e75de22b16fff6d3e219a Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:23 -0700
Subject: [PATCH 2612/2753] idpf: add Tx timestamp flows

Add functions to request Tx timestamp for the PTP packets, read the Tx
timestamp when the completion tag for that packet is being received,
extend the Tx timestamp value and set the supported timestamping modes.

Tx timestamp is requested for the PTP packets by setting a TSYN bit and
index value in the Tx context descriptor. The driver assumption is that
the Tx timestamp value is ready to be read when the completion tag is
received. Then the driver schedules delayed work and the Tx timestamp
value read is requested through virtchnl message. At the end, the Tx
timestamp value is extended to 64-bit and provided back to the skb.

Co-developed-by: Josh Hay <joshua.a.hay@intel.com>
Signed-off-by: Josh Hay <joshua.a.hay@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/idpf.h        |  20 ++
 .../net/ethernet/intel/idpf/idpf_ethtool.c    |  74 +++++-
 .../net/ethernet/intel/idpf/idpf_lan_txrx.h   |  13 +-
 drivers/net/ethernet/intel/idpf/idpf_lib.c    |  55 ++++
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 239 +++++++++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    |  51 ++++
 drivers/net/ethernet/intel/idpf/idpf_txrx.c   | 141 ++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_txrx.h   |  11 +-
 .../net/ethernet/intel/idpf/idpf_virtchnl.c   |   6 +-
 .../ethernet/intel/idpf/idpf_virtchnl_ptp.c   | 235 +++++++++++++++++
 10 files changed, 830 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index fe4d8ad75b044..d7dbf7d9c7d31 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -246,9 +246,23 @@ struct idpf_port_stats {
 	u64_stats_t tx_busy;
 	u64_stats_t tx_drops;
 	u64_stats_t tx_dma_map_errs;
+	u64_stats_t tx_hwtstamp_skipped;
 	struct virtchnl2_vport_stats vport_stats;
 };
 
+/**
+ * struct idpf_tx_tstamp_stats - Tx timestamp statistics
+ * @tx_hwtstamp_lock: Lock to protect Tx tstamp stats
+ * @tx_hwtstamp_discarded: Number of Tx skbs discarded due to cached PHC time
+ *			   being too old to correctly extend timestamp
+ * @tx_hwtstamp_flushed: Number of Tx skbs flushed due to interface closed
+ */
+struct idpf_tx_tstamp_stats {
+	struct mutex tx_hwtstamp_lock;
+	u32 tx_hwtstamp_discarded;
+	u32 tx_hwtstamp_flushed;
+};
+
 /**
  * struct idpf_vport - Handle for netdevices and queue resources
  * @num_txq: Number of allocated TX queues
@@ -293,6 +307,9 @@ struct idpf_port_stats {
  * @link_up: True if link is up
  * @sw_marker_wq: workqueue for marker packets
  * @tx_tstamp_caps: Capabilities negotiated for Tx timestamping
+ * @tstamp_config: The Tx tstamp config
+ * @tstamp_task: Tx timestamping task
+ * @tstamp_stats: Tx timestamping statistics
  */
 struct idpf_vport {
 	u16 num_txq;
@@ -339,6 +356,9 @@ struct idpf_vport {
 	wait_queue_head_t sw_marker_wq;
 
 	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct kernel_hwtstamp_config tstamp_config;
+	struct work_struct tstamp_task;
+	struct idpf_tx_tstamp_stats tstamp_stats;
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index 59b1a1a099967..ec4183a609c4f 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -2,6 +2,7 @@
 /* Copyright (C) 2023 Intel Corporation */
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 
 /**
  * idpf_get_rxnfc - command to get RX flow classification rules
@@ -479,6 +480,9 @@ static const struct idpf_stats idpf_gstrings_port_stats[] = {
 	IDPF_PORT_STAT("tx-unicast_pkts", port_stats.vport_stats.tx_unicast),
 	IDPF_PORT_STAT("tx-multicast_pkts", port_stats.vport_stats.tx_multicast),
 	IDPF_PORT_STAT("tx-broadcast_pkts", port_stats.vport_stats.tx_broadcast),
+	IDPF_PORT_STAT("tx-hwtstamp_skipped", port_stats.tx_hwtstamp_skipped),
+	IDPF_PORT_STAT("tx-hwtstamp_flushed", tstamp_stats.tx_hwtstamp_flushed),
+	IDPF_PORT_STAT("tx-hwtstamp_discarded", tstamp_stats.tx_hwtstamp_discarded),
 };
 
 #define IDPF_PORT_STATS_LEN ARRAY_SIZE(idpf_gstrings_port_stats)
@@ -780,6 +784,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
 	u64_stats_set(&pstats->tx_busy, 0);
 	u64_stats_set(&pstats->tx_drops, 0);
 	u64_stats_set(&pstats->tx_dma_map_errs, 0);
+	u64_stats_set(&pstats->tx_hwtstamp_skipped, 0);
 	u64_stats_update_end(&pstats->stats_sync);
 
 	for (i = 0; i < vport->num_rxq_grp; i++) {
@@ -828,7 +833,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
 		struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
 
 		for (j = 0; j < txq_grp->num_txq; j++) {
-			u64 linearize, qbusy, skb_drops, dma_map_errs;
+			u64 linearize, qbusy, skb_drops, dma_map_errs, tstamp;
 			struct idpf_tx_queue *txq = txq_grp->txqs[j];
 			struct idpf_tx_queue_stats *stats;
 			unsigned int start;
@@ -844,6 +849,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
 				qbusy = u64_stats_read(&stats->q_busy);
 				skb_drops = u64_stats_read(&stats->skb_drops);
 				dma_map_errs = u64_stats_read(&stats->dma_map_errs);
+				tstamp = u64_stats_read(&stats->tstamp_skipped);
 			} while (u64_stats_fetch_retry(&txq->stats_sync, start));
 
 			u64_stats_update_begin(&pstats->stats_sync);
@@ -851,6 +857,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
 			u64_stats_add(&pstats->tx_busy, qbusy);
 			u64_stats_add(&pstats->tx_drops, skb_drops);
 			u64_stats_add(&pstats->tx_dma_map_errs, dma_map_errs);
+			u64_stats_add(&pstats->tx_hwtstamp_skipped, tstamp);
 			u64_stats_update_end(&pstats->stats_sync);
 		}
 	}
@@ -1312,6 +1319,70 @@ static int idpf_get_link_ksettings(struct net_device *netdev,
 	return 0;
 }
 
+/**
+ * idpf_get_timestamp_filters - Get the supported timestamping mode
+ * @vport: Virtual port structure
+ * @info: ethtool timestamping info structure
+ *
+ * Get the Tx/Rx timestamp filters.
+ */
+static void idpf_get_timestamp_filters(const struct idpf_vport *vport,
+				       struct kernel_ethtool_ts_info *info)
+{
+	info->so_timestamping = SOF_TIMESTAMPING_RX_HARDWARE |
+				SOF_TIMESTAMPING_RAW_HARDWARE;
+
+	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+
+	if (!vport->tx_tstamp_caps ||
+	    vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE)
+		return;
+
+	info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE |
+				 SOF_TIMESTAMPING_TX_HARDWARE;
+
+	info->tx_types |= BIT(HWTSTAMP_TX_ON);
+}
+
+/**
+ * idpf_get_ts_info - Get device PHC association
+ * @netdev: network interface device structure
+ * @info: ethtool timestamping info structure
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int idpf_get_ts_info(struct net_device *netdev,
+			    struct kernel_ethtool_ts_info *info)
+{
+	struct idpf_netdev_priv *np = netdev_priv(netdev);
+	struct idpf_vport *vport;
+	int err = 0;
+
+	if (!mutex_trylock(&np->adapter->vport_ctrl_lock))
+		return -EBUSY;
+
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->adapter->ptp) {
+		err = -EOPNOTSUPP;
+		goto unlock;
+	}
+
+	if (idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_PTP) &&
+	    vport->adapter->ptp->clock) {
+		info->phc_index = ptp_clock_index(vport->adapter->ptp->clock);
+		idpf_get_timestamp_filters(vport, info);
+	} else {
+		pci_dbg(vport->adapter->pdev, "PTP clock not detected\n");
+		err = ethtool_op_get_ts_info(netdev, info);
+	}
+
+unlock:
+	mutex_unlock(&np->adapter->vport_ctrl_lock);
+
+	return err;
+}
+
 static const struct ethtool_ops idpf_ethtool_ops = {
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_USE_ADAPTIVE,
@@ -1336,6 +1407,7 @@ static const struct ethtool_ops idpf_ethtool_ops = {
 	.get_ringparam		= idpf_get_ringparam,
 	.set_ringparam		= idpf_set_ringparam,
 	.get_link_ksettings	= idpf_get_link_ksettings,
+	.get_ts_info		= idpf_get_ts_info,
 };
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
index 8c7f8ef8f1a15..7492d17132431 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
@@ -282,7 +282,18 @@ struct idpf_flex_tx_tso_ctx_qw {
 	u8 flex;
 };
 
-struct idpf_flex_tx_ctx_desc {
+union idpf_flex_tx_ctx_desc {
+	/* DTYPE = IDPF_TX_DESC_DTYPE_CTX (0x01) */
+	struct {
+		__le64 qw0;
+#define IDPF_TX_CTX_L2TAG2_M	GENMASK_ULL(47, 32)
+		__le64 qw1;
+#define IDPF_TX_CTX_DTYPE_M	GENMASK_ULL(3, 0)
+#define IDPF_TX_CTX_CMD_M	GENMASK_ULL(15, 4)
+#define IDPF_TX_CTX_TSYN_REG_M	GENMASK_ULL(47, 30)
+#define IDPF_TX_CTX_MSS_M	GENMASK_ULL(50, 63)
+	} tsyn;
+
 	/* DTYPE = IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX (0x05) */
 	struct {
 		struct idpf_flex_tx_tso_ctx_qw qw0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index f3aea7bcdaa3b..b4752de5f0911 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -3,6 +3,7 @@
 
 #include "idpf.h"
 #include "idpf_virtchnl.h"
+#include "idpf_ptp.h"
 
 static const struct net_device_ops idpf_netdev_ops;
 
@@ -2345,6 +2346,58 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
 	mem->pa = 0;
 }
 
+static int idpf_hwtstamp_set(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config,
+			     struct netlink_ext_ack *extack)
+{
+	struct idpf_vport *vport;
+	int err;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EOPNOTSUPP;
+	}
+
+	err = idpf_ptp_set_timestamp_mode(vport, config);
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return err;
+}
+
+static int idpf_hwtstamp_get(struct net_device *netdev,
+			     struct kernel_hwtstamp_config *config)
+{
+	struct idpf_vport *vport;
+
+	idpf_vport_ctrl_lock(netdev);
+	vport = idpf_netdev_to_vport(netdev);
+
+	if (!vport->link_up) {
+		idpf_vport_ctrl_unlock(netdev);
+		return -EPERM;
+	}
+
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) {
+		idpf_vport_ctrl_unlock(netdev);
+		return 0;
+	}
+
+	*config = vport->tstamp_config;
+
+	idpf_vport_ctrl_unlock(netdev);
+
+	return 0;
+}
+
 static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_open = idpf_open,
 	.ndo_stop = idpf_stop,
@@ -2357,4 +2410,6 @@ static const struct net_device_ops idpf_netdev_ops = {
 	.ndo_get_stats64 = idpf_get_stats64,
 	.ndo_set_features = idpf_set_features,
 	.ndo_tx_timeout = idpf_tx_timeout,
+	.ndo_hwtstamp_get = idpf_hwtstamp_get,
+	.ndo_hwtstamp_set = idpf_hwtstamp_set,
 };
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index d2c629a88cc58..36bff5afa474e 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -317,6 +317,37 @@ static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
 	return 0;
 }
 
+/**
+ * idpf_ptp_update_cached_phctime - Update the cached PHC time values
+ * @adapter: Driver specific private structure
+ *
+ * This function updates the system time values which are cached in the adapter
+ * structure.
+ *
+ * This function must be called periodically to ensure that the cached value
+ * is never more than 2 seconds old.
+ *
+ * Return: 0 on success, negative otherwise.
+ */
+static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter)
+{
+	u64 systime;
+	int err;
+
+	err = idpf_ptp_read_src_clk_reg(adapter, &systime, NULL);
+	if (err)
+		return -EACCES;
+
+	/* Update the cached PHC time stored in the adapter structure.
+	 * These values are used to extend Tx timestamp values to 64 bit
+	 * expected by the stack.
+	 */
+	WRITE_ONCE(adapter->ptp->cached_phc_time, systime);
+	WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies);
+
+	return 0;
+}
+
 /**
  * idpf_ptp_settime64 - Set the time of the clock
  * @info: the driver's PTP info structure
@@ -348,6 +379,11 @@ static int idpf_ptp_settime64(struct ptp_clock_info *info,
 		return err;
 	}
 
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
 	return 0;
 }
 
@@ -404,6 +440,11 @@ static int idpf_ptp_adjtime(struct ptp_clock_info *info, s64 delta)
 		return err;
 	}
 
+	err = idpf_ptp_update_cached_phctime(adapter);
+	if (err)
+		pci_warn(adapter->pdev,
+			 "Unable to immediately update cached PHC time\n");
+
 	return 0;
 }
 
@@ -468,6 +509,160 @@ static int idpf_ptp_gpio_enable(struct ptp_clock_info *info,
 	return -EOPNOTSUPP;
 }
 
+/**
+ * idpf_ptp_tstamp_extend_32b_to_64b - Convert a 32b nanoseconds Tx or Rx
+ *				       timestamp value to 64b.
+ * @cached_phc_time: recently cached copy of PHC time
+ * @in_timestamp: Ingress/egress 32b nanoseconds timestamp value
+ *
+ * Hardware captures timestamps which contain only 32 bits of nominal
+ * nanoseconds, as opposed to the 64bit timestamps that the stack expects.
+ *
+ * Return: Tx timestamp value extended to 64 bits based on cached PHC time.
+ */
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp)
+{
+	s64 delta;
+
+	delta = in_timestamp - lower_32_bits(cached_phc_time);
+
+	return cached_phc_time + delta;
+}
+
+/**
+ * idpf_ptp_extend_ts - Convert a 40b timestamp to 64b nanoseconds
+ * @vport: Virtual port structure
+ * @in_tstamp: Ingress/egress timestamp value
+ *
+ * It is assumed that the caller verifies the timestamp is valid prior to
+ * calling this function.
+ *
+ * Extract the 32bit nominal nanoseconds and extend them. Use the cached PHC
+ * time stored in the device private PTP structure as the basis for timestamp
+ * extension.
+ *
+ * Return: Tx timestamp value extended to 64 bits.
+ */
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp)
+{
+	struct idpf_ptp *ptp = vport->adapter->ptp;
+	unsigned long discard_time;
+
+	discard_time = ptp->cached_phc_jiffies + 2 * HZ;
+
+	if (time_is_before_jiffies(discard_time)) {
+		mutex_lock(&vport->tstamp_stats.tx_hwtstamp_lock);
+		vport->tstamp_stats.tx_hwtstamp_discarded++;
+		mutex_unlock(&vport->tstamp_stats.tx_hwtstamp_lock);
+
+		return 0;
+	}
+
+	return idpf_ptp_tstamp_extend_32b_to_64b(ptp->cached_phc_time,
+						 lower_32_bits(in_tstamp));
+}
+
+/**
+ * idpf_ptp_request_ts - Request an available Tx timestamp index
+ * @tx_q: Transmit queue on which the Tx timestamp is requested
+ * @skb: The SKB to associate with this timestamp request
+ * @idx: Index of the Tx timestamp latch
+ *
+ * Request tx timestamp index negotiated during PTP init that will be set into
+ * Tx descriptor.
+ *
+ * Return: 0 and the index that can be provided to Tx descriptor on success,
+ * -errno otherwise.
+ */
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx)
+{
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	struct list_head *head;
+
+	/* Get the index from the free latches list */
+	spin_lock_bh(&tx_q->cached_tstamp_caps->lock_free);
+
+	head = &tx_q->cached_tstamp_caps->latches_free;
+	if (list_empty(head)) {
+		spin_unlock_bh(&tx_q->cached_tstamp_caps->lock_free);
+		return -ENOBUFS;
+	}
+
+	ptp_tx_tstamp = list_first_entry(head, struct idpf_ptp_tx_tstamp,
+					 list_member);
+	list_del(&ptp_tx_tstamp->list_member);
+	spin_unlock_bh(&tx_q->cached_tstamp_caps->lock_free);
+
+	ptp_tx_tstamp->skb = skb_get(skb);
+	skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
+
+	/* Move the element to the used latches list */
+	spin_lock_bh(&tx_q->cached_tstamp_caps->lock_in_use);
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_q->cached_tstamp_caps->latches_in_use);
+	spin_unlock_bh(&tx_q->cached_tstamp_caps->lock_in_use);
+
+	*idx = ptp_tx_tstamp->idx;
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
+ * @vport: Virtual port structure
+ * @config: Hwtstamp settings requested or saved
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config)
+{
+	switch (config->tx_type) {
+	case HWTSTAMP_TX_OFF:
+		break;
+	case HWTSTAMP_TX_ON:
+		if (!idpf_ptp_is_vport_tx_tstamp_ena(vport))
+			return -EINVAL;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	vport->tstamp_config.tx_type = config->tx_type;
+	*config = vport->tstamp_config;
+
+	return 0;
+}
+
+/**
+ * idpf_tstamp_task - Delayed task to handle Tx tstamps
+ * @work: work_struct handle
+ */
+void idpf_tstamp_task(struct work_struct *work)
+{
+	struct idpf_vport *vport;
+
+	vport = container_of(work, struct idpf_vport, tstamp_task);
+
+	idpf_ptp_get_tx_tstamp(vport);
+}
+
+/**
+ * idpf_ptp_do_aux_work - Do PTP periodic work
+ * @info: Driver's PTP info structure
+ *
+ * Return: Number of jiffies to periodic work.
+ */
+static long idpf_ptp_do_aux_work(struct ptp_clock_info *info)
+{
+	struct idpf_adapter *adapter = idpf_ptp_info_to_adapter(info);
+
+	idpf_ptp_update_cached_phctime(adapter);
+
+	return msecs_to_jiffies(500);
+}
+
 /**
  * idpf_ptp_set_caps - Set PTP capabilities
  * @adapter: Driver specific private structure
@@ -489,6 +684,7 @@ static void idpf_ptp_set_caps(const struct idpf_adapter *adapter)
 	info->adjtime = idpf_ptp_adjtime;
 	info->verify = idpf_ptp_verify_pin;
 	info->enable = idpf_ptp_gpio_enable;
+	info->do_aux_work = idpf_ptp_do_aux_work;
 
 #if IS_ENABLED(CONFIG_ARM_ARCH_TIMER)
 	info->getcrosststamp = idpf_ptp_get_crosststamp;
@@ -541,6 +737,8 @@ static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
 	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp, *tmp;
 	struct list_head *head;
 
+	cancel_work_sync(&vport->tstamp_task);
+
 	/* Remove list with free latches */
 	spin_lock(&vport->tx_tstamp_caps->lock_free);
 
@@ -553,16 +751,21 @@ static void idpf_ptp_release_vport_tstamp(struct idpf_vport *vport)
 	spin_unlock(&vport->tx_tstamp_caps->lock_free);
 
 	/* Remove list with latches in use */
+	mutex_lock(&vport->tstamp_stats.tx_hwtstamp_lock);
 	spin_lock(&vport->tx_tstamp_caps->lock_in_use);
 
 	head = &vport->tx_tstamp_caps->latches_in_use;
 	list_for_each_entry_safe(ptp_tx_tstamp, tmp, head, list_member) {
+		vport->tstamp_stats.tx_hwtstamp_flushed++;
 		list_del(&ptp_tx_tstamp->list_member);
 		kfree(ptp_tx_tstamp);
 	}
 
 	spin_unlock(&vport->tx_tstamp_caps->lock_in_use);
 
+	mutex_unlock(&vport->tstamp_stats.tx_hwtstamp_lock);
+	mutex_destroy(&vport->tstamp_stats.tx_hwtstamp_lock);
+
 	kfree(vport->tx_tstamp_caps);
 	vport->tx_tstamp_caps = NULL;
 }
@@ -583,6 +786,27 @@ static void idpf_ptp_release_tstamp(struct idpf_adapter *adapter)
 	}
 }
 
+/**
+ * idpf_ptp_get_txq_tstamp_capability - Verify the timestamping capability
+ *					for a given tx queue.
+ * @txq: Transmit queue
+ *
+ * Since performing timestamp flows requires reading the device clock value and
+ * the support in the Control Plane, the function checks both factors and
+ * summarizes the support for the timestamping.
+ *
+ * Return: true if the timestamping is supported, false otherwise.
+ */
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	if (!txq || !txq->cached_tstamp_caps)
+		return false;
+	else if (txq->cached_tstamp_caps->access)
+		return true;
+	else
+		return false;
+}
+
 /**
  * idpf_ptp_init - Initialize PTP hardware clock support
  * @adapter: Driver specific private structure
@@ -623,6 +847,9 @@ int idpf_ptp_init(struct idpf_adapter *adapter)
 	if (err)
 		goto free_ptp;
 
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_schedule_worker(adapter->ptp->clock, 0);
+
 	/* Write the default increment time value if the clock adjustments
 	 * are enabled.
 	 */
@@ -646,6 +873,9 @@ int idpf_ptp_init(struct idpf_adapter *adapter)
 	return 0;
 
 remove_clock:
+	if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+		ptp_cancel_worker_sync(adapter->ptp->clock);
+
 	ptp_clock_unregister(adapter->ptp->clock);
 	adapter->ptp->clock = NULL;
 
@@ -667,11 +897,16 @@ void idpf_ptp_release(struct idpf_adapter *adapter)
 	if (!ptp)
 		return;
 
-	if (ptp->tx_tstamp_access != IDPF_PTP_NONE)
+	if (ptp->tx_tstamp_access != IDPF_PTP_NONE &&
+	    ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
 		idpf_ptp_release_tstamp(adapter);
 
-	if (ptp->clock)
+	if (ptp->clock) {
+		if (adapter->ptp->get_dev_clk_time_access != IDPF_PTP_NONE)
+			ptp_cancel_worker_sync(adapter->ptp->clock);
+
 		ptp_clock_unregister(ptp->clock);
+	}
 
 	kfree(ptp);
 	adapter->ptp = NULL;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index 3a9763bc32575..5cb7b68085b60 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -131,6 +131,7 @@ struct idpf_ptp_tx_tstamp {
  * @lock_in_use: the lock to the used latches list
  * @lock_free: the lock to free the latches list
  * @lock_status: the lock to the status tracker
+ * @access: indicates an access to Tx timestamp
  * @latches_free: the list of the free Tx timestamps latches
  * @latches_in_use: the list of the used Tx timestamps latches
  * @tx_tstamp_status: Tx tstamp status tracker
@@ -142,6 +143,7 @@ struct idpf_ptp_vport_tx_tstamp_caps {
 	spinlock_t lock_in_use;
 	spinlock_t lock_free;
 	spinlock_t lock_status;
+	bool access:1;
 	struct list_head latches_free;
 	struct list_head latches_in_use;
 	struct idpf_ptp_tx_tstamp_status tx_tstamp_status[];
@@ -155,6 +157,8 @@ struct idpf_ptp_vport_tx_tstamp_caps {
  * @base_incval: base increment value of the PTP clock
  * @max_adj: maximum adjustment of the PTP clock
  * @cmd: HW specific command masks
+ * @cached_phc_time: a cached copy of the PHC time for timestamp extension
+ * @cached_phc_jiffies: jiffies when cached_phc_time was last updated
  * @dev_clk_regs: the set of registers to access the device clock
  * @caps: PTP capabilities negotiated with the Control Plane
  * @get_dev_clk_time_access: access type for getting the device clock time
@@ -172,6 +176,8 @@ struct idpf_ptp {
 	u64 base_incval;
 	u64 max_adj;
 	struct idpf_ptp_cmd cmd;
+	u64 cached_phc_time;
+	unsigned long cached_phc_jiffies;
 	struct idpf_ptp_dev_clk_regs dev_clk_regs;
 	u32 caps;
 	enum idpf_ptp_access get_dev_clk_time_access:2;
@@ -233,6 +239,7 @@ int idpf_ptp_init(struct idpf_adapter *adapter);
 void idpf_ptp_release(struct idpf_adapter *adapter);
 int idpf_ptp_get_caps(struct idpf_adapter *adapter);
 void idpf_ptp_get_features_access(const struct idpf_adapter *adapter);
+bool idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq);
 int idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
 			      struct idpf_ptp_dev_timers *dev_clk_time);
 int idpf_ptp_get_cross_time(struct idpf_adapter *adapter,
@@ -241,6 +248,14 @@ int idpf_ptp_set_dev_clk_time(struct idpf_adapter *adapter, u64 time);
 int idpf_ptp_adj_dev_clk_fine(struct idpf_adapter *adapter, u64 incval);
 int idpf_ptp_adj_dev_clk_time(struct idpf_adapter *adapter, s64 delta);
 int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport);
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport);
+int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+				struct kernel_hwtstamp_config *config);
+u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u64 in_tstamp);
+u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time, u32 in_timestamp);
+int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			u32 *idx);
+void idpf_tstamp_task(struct work_struct *work);
 #else /* CONFIG_PTP_1588_CLOCK */
 static inline int idpf_ptp_init(struct idpf_adapter *adapter)
 {
@@ -257,6 +272,12 @@ static inline int idpf_ptp_get_caps(struct idpf_adapter *adapter)
 static inline void
 idpf_ptp_get_features_access(const struct idpf_adapter *adapter) { }
 
+static inline bool
+idpf_ptp_get_txq_tstamp_capability(struct idpf_tx_queue *txq)
+{
+	return false;
+}
+
 static inline int
 idpf_ptp_get_dev_clk_time(struct idpf_adapter *adapter,
 			  struct idpf_ptp_dev_timers *dev_clk_time)
@@ -294,5 +315,35 @@ static inline int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
 	return -EOPNOTSUPP;
 }
 
+static inline int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int
+idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
+			    struct kernel_hwtstamp_config *config)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline u64 idpf_ptp_extend_ts(struct idpf_vport *vport, u32 in_tstamp)
+{
+	return 0;
+}
+
+static inline u64 idpf_ptp_tstamp_extend_32b_to_64b(u64 cached_phc_time,
+						    u32 in_timestamp)
+{
+	return 0;
+}
+
+static inline int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q,
+				      struct sk_buff *skb, u32 *idx)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void idpf_tstamp_task(struct work_struct *work) { }
 #endif /* CONFIG_PTP_1588_CLOCK */
 #endif /* _IDPF_PTP_H */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index bdf52cef3891b..0aa0680e57ad9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -5,6 +5,7 @@
 #include <net/libeth/tx.h>
 
 #include "idpf.h"
+#include "idpf_ptp.h"
 #include "idpf_virtchnl.h"
 
 struct idpf_tx_stash {
@@ -1107,6 +1108,8 @@ void idpf_vport_queues_rel(struct idpf_vport *vport)
  */
 static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 {
+	struct idpf_ptp_vport_tx_tstamp_caps *caps = vport->tx_tstamp_caps;
+	struct work_struct *tstamp_task = &vport->tstamp_task;
 	int i, j, k = 0;
 
 	vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs),
@@ -1121,6 +1124,12 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
 		for (j = 0; j < tx_grp->num_txq; j++, k++) {
 			vport->txqs[k] = tx_grp->txqs[j];
 			vport->txqs[k]->idx = k;
+
+			if (!caps)
+				continue;
+
+			vport->txqs[k]->cached_tstamp_caps = caps;
+			vport->txqs[k]->tstamp_task = tstamp_task;
 		}
 	}
 
@@ -1654,6 +1663,40 @@ static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
 	wake_up(&vport->sw_marker_wq);
 }
 
+/**
+ * idpf_tx_read_tstamp - schedule a work to read Tx timestamp value
+ * @txq: queue to read the timestamp from
+ * @skb: socket buffer to provide Tx timestamp value
+ *
+ * Schedule a work to read Tx timestamp value generated once the packet is
+ * transmitted.
+ */
+static void idpf_tx_read_tstamp(struct idpf_tx_queue *txq, struct sk_buff *skb)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_ptp_tx_tstamp_status *tx_tstamp_status;
+
+	tx_tstamp_caps = txq->cached_tstamp_caps;
+	spin_lock_bh(&tx_tstamp_caps->lock_status);
+
+	for (u32 i = 0; i < tx_tstamp_caps->num_entries; i++) {
+		tx_tstamp_status = &tx_tstamp_caps->tx_tstamp_status[i];
+		if (tx_tstamp_status->state != IDPF_PTP_FREE)
+			continue;
+
+		tx_tstamp_status->skb = skb;
+		tx_tstamp_status->state = IDPF_PTP_REQUEST;
+
+		/* Fetch timestamp from completion descriptor through
+		 * virtchnl msg to report to stack.
+		 */
+		queue_work(system_unbound_wq, txq->tstamp_task);
+		break;
+	}
+
+	spin_unlock_bh(&tx_tstamp_caps->lock_status);
+}
+
 /**
  * idpf_tx_clean_stashed_bufs - clean bufs that were stored for
  * out of order completions
@@ -1682,6 +1725,11 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
 			continue;
 
 		hash_del(&stash->hlist);
+
+		if (stash->buf.type == LIBETH_SQE_SKB &&
+		    (skb_shinfo(stash->buf.skb)->tx_flags & SKBTX_IN_PROGRESS))
+			idpf_tx_read_tstamp(txq, stash->buf.skb);
+
 		libeth_tx_complete(&stash->buf, &cp);
 
 		/* Push shadow buf back onto stack */
@@ -1876,8 +1924,12 @@ static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
 		     idpf_tx_buf_compl_tag(tx_buf) != compl_tag))
 		return false;
 
-	if (tx_buf->type == LIBETH_SQE_SKB)
+	if (tx_buf->type == LIBETH_SQE_SKB) {
+		if (skb_shinfo(tx_buf->skb)->tx_flags & SKBTX_IN_PROGRESS)
+			idpf_tx_read_tstamp(txq, tx_buf->skb);
+
 		libeth_tx_complete(tx_buf, &cp);
+	}
 
 	idpf_tx_clean_buf_ring_bump_ntc(txq, idx, tx_buf);
 
@@ -2127,7 +2179,7 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
 				    struct idpf_tx_splitq_params *params,
 				    u16 td_cmd, u16 size)
 {
-	desc->flow.qw1.cmd_dtype = (u16)params->dtype | td_cmd;
+	*(u32 *)&desc->flow.qw1.cmd_dtype = (u8)(params->dtype | td_cmd);
 	desc->flow.qw1.rxr_bufsize = cpu_to_le16((u16)size);
 	desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
 }
@@ -2296,7 +2348,7 @@ void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
 		 * descriptor. Reset that here.
 		 */
 		tx_desc = &txq->flex_tx[idx];
-		memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
+		memset(tx_desc, 0, sizeof(*tx_desc));
 		if (idx == 0)
 			idx = txq->desc_count;
 		idx--;
@@ -2699,10 +2751,10 @@ static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
  * Since the TX buffer rings mimics the descriptor ring, update the tx buffer
  * ring entry to reflect that this index is a context descriptor
  */
-static struct idpf_flex_tx_ctx_desc *
+static union idpf_flex_tx_ctx_desc *
 idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
 {
-	struct idpf_flex_tx_ctx_desc *desc;
+	union idpf_flex_tx_ctx_desc *desc;
 	int i = txq->next_to_use;
 
 	txq->tx_buf[i].type = LIBETH_SQE_CTX;
@@ -2732,6 +2784,73 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
 	return NETDEV_TX_OK;
 }
 
+#if (IS_ENABLED(CONFIG_PTP_1588_CLOCK))
+/**
+ * idpf_tx_tstamp - set up context descriptor for hardware timestamp
+ * @tx_q: queue to send buffer on
+ * @skb: pointer to the SKB we're sending
+ * @off: pointer to the offload struct
+ *
+ * Return: Positive index number on success, negative otherwise.
+ */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	int err, idx;
+
+	/* only timestamp the outbound packet if the user has requested it */
+	if (likely(!(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)))
+		return -1;
+
+	if (!idpf_ptp_get_txq_tstamp_capability(tx_q))
+		return -1;
+
+	/* Tx timestamps cannot be sampled when doing TSO */
+	if (off->tx_flags & IDPF_TX_FLAGS_TSO)
+		return -1;
+
+	/* Grab an open timestamp slot */
+	err = idpf_ptp_request_ts(tx_q, skb, &idx);
+	if (err) {
+		u64_stats_update_begin(&tx_q->stats_sync);
+		u64_stats_inc(&tx_q->q_stats.tstamp_skipped);
+		u64_stats_update_end(&tx_q->stats_sync);
+
+		return -1;
+	}
+
+	off->tx_flags |= IDPF_TX_FLAGS_TSYN;
+
+	return idx;
+}
+
+/**
+ * idpf_tx_set_tstamp_desc - Set the Tx descriptor fields needed to generate
+ *			     PHY Tx timestamp
+ * @ctx_desc: Context descriptor
+ * @idx: Index of the Tx timestamp latch
+ */
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{
+	ctx_desc->tsyn.qw1 = le64_encode_bits(IDPF_TX_DESC_DTYPE_CTX,
+					      IDPF_TX_CTX_DTYPE_M) |
+			     le64_encode_bits(IDPF_TX_CTX_DESC_TSYN,
+					      IDPF_TX_CTX_CMD_M) |
+			     le64_encode_bits(idx, IDPF_TX_CTX_TSYN_REG_M);
+}
+#else /* CONFIG_PTP_1588_CLOCK */
+static int idpf_tx_tstamp(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
+			  struct idpf_tx_offload_params *off)
+{
+	return -1;
+}
+
+static void idpf_tx_set_tstamp_desc(union idpf_flex_tx_ctx_desc *ctx_desc,
+				    u32 idx)
+{ }
+#endif /* CONFIG_PTP_1588_CLOCK */
+
 /**
  * idpf_tx_splitq_frame - Sends buffer on Tx ring using flex descriptors
  * @skb: send buffer
@@ -2743,9 +2862,10 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 					struct idpf_tx_queue *tx_q)
 {
 	struct idpf_tx_splitq_params tx_params = { };
+	union idpf_flex_tx_ctx_desc *ctx_desc;
 	struct idpf_tx_buf *first;
 	unsigned int count;
-	int tso;
+	int tso, idx;
 
 	count = idpf_tx_desc_count_required(tx_q, skb);
 	if (unlikely(!count))
@@ -2765,8 +2885,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 
 	if (tso) {
 		/* If tso is needed, set up context desc */
-		struct idpf_flex_tx_ctx_desc *ctx_desc =
-			idpf_tx_splitq_get_ctx_desc(tx_q);
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
 
 		ctx_desc->tso.qw1.cmd_dtype =
 				cpu_to_le16(IDPF_TX_DESC_DTYPE_FLEX_TSO_CTX |
@@ -2784,6 +2903,12 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
 		u64_stats_update_end(&tx_q->stats_sync);
 	}
 
+	idx = idpf_tx_tstamp(tx_q, skb, &tx_params.offload);
+	if (idx != -1) {
+		ctx_desc = idpf_tx_splitq_get_ctx_desc(tx_q);
+		idpf_tx_set_tstamp_desc(ctx_desc, idx);
+	}
+
 	/* record the location of the first descriptor for this packet */
 	first = &tx_q->tx_buf[tx_q->next_to_use];
 	first->skb = skb;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index b029f566e57cd..9b7aa72e1f32d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -142,6 +142,7 @@ do {								\
 #define IDPF_TX_FLAGS_IPV4		BIT(1)
 #define IDPF_TX_FLAGS_IPV6		BIT(2)
 #define IDPF_TX_FLAGS_TUNNEL		BIT(3)
+#define IDPF_TX_FLAGS_TSYN		BIT(4)
 
 union idpf_tx_flex_desc {
 	struct idpf_flex_tx_desc q; /* queue based scheduling */
@@ -443,6 +444,7 @@ struct idpf_tx_queue_stats {
 	u64_stats_t q_busy;
 	u64_stats_t skb_drops;
 	u64_stats_t dma_map_errs;
+	u64_stats_t tstamp_skipped;
 };
 
 #define IDPF_ITR_DYNAMIC	1
@@ -617,6 +619,8 @@ libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
  * @compl_tag_bufid_m: Completion tag buffer id mask
  * @compl_tag_cur_gen: Used to keep track of current completion tag generation
  * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+ * @cached_tstamp_caps: Tx timestamp capabilities negotiated with the CP
+ * @tstamp_task: Work that handles Tx timestamp read
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_tx_queue_stats
  * @q_id: Queue id
@@ -630,7 +634,7 @@ struct idpf_tx_queue {
 		struct idpf_base_tx_desc *base_tx;
 		struct idpf_base_tx_ctx_desc *base_ctx;
 		union idpf_tx_flex_desc *flex_tx;
-		struct idpf_flex_tx_ctx_desc *flex_ctx;
+		union idpf_flex_tx_ctx_desc *flex_ctx;
 
 		void *desc_ring;
 	};
@@ -666,6 +670,9 @@ struct idpf_tx_queue {
 	u16 compl_tag_cur_gen;
 	u16 compl_tag_gen_max;
 
+	struct idpf_ptp_vport_tx_tstamp_caps *cached_tstamp_caps;
+	struct work_struct *tstamp_task;
+
 	struct u64_stats_sync stats_sync;
 	struct idpf_tx_queue_stats q_stats;
 	__cacheline_group_end_aligned(read_write);
@@ -679,7 +686,7 @@ struct idpf_tx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_tx_queue, 64,
-			    88 + sizeof(struct u64_stats_sync),
+			    112 + sizeof(struct u64_stats_sync),
 			    24);
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index be45d09e913e6..07a9f5ae34fd9 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -3177,8 +3177,12 @@ void idpf_vport_init(struct idpf_vport *vport, struct idpf_vport_max_q *max_q)
 		return;
 
 	err = idpf_ptp_get_vport_tstamps_caps(vport);
-	if (err)
+	if (err) {
 		pci_dbg(vport->adapter->pdev, "Tx timestamping not supported\n");
+		return;
+	}
+
+	INIT_WORK(&vport->tstamp_task, idpf_tstamp_task);
 }
 
 /**
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
index 12e776aedf631..c582a9d34dd0b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl_ptp.c
@@ -382,7 +382,9 @@ int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
 		goto get_tstamp_caps_out;
 	}
 
+	tstamp_caps->access = true;
 	tstamp_caps->num_entries = num_latches;
+
 	INIT_LIST_HEAD(&tstamp_caps->latches_in_use);
 	INIT_LIST_HEAD(&tstamp_caps->latches_free);
 
@@ -425,6 +427,9 @@ int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
 	vport->tx_tstamp_caps = tstamp_caps;
 	kfree(rcv_tx_tstamp_caps);
 
+	/* Init mutex to protect tstamp statistics */
+	mutex_init(&vport->tstamp_stats.tx_hwtstamp_lock);
+
 	return 0;
 
 err_free_ptp_tx_stamp_list:
@@ -440,3 +445,233 @@ int idpf_ptp_get_vport_tstamps_caps(struct idpf_vport *vport)
 
 	return err;
 }
+
+/**
+ * idpf_ptp_update_tstamp_tracker - Update the Tx timestamp tracker based on
+ *				    the skb compatibility.
+ * @caps: Tx timestamp capabilities that monitor the latch status
+ * @skb: skb for which the tstamp value is returned through virtchnl message
+ * @current_state: Current state of the Tx timestamp latch
+ * @expected_state: Expected state of the Tx timestamp latch
+ *
+ * Find a proper skb tracker for which the Tx timestamp is received and change
+ * the state to expected value.
+ *
+ * Return: true if the tracker has been found and updated, false otherwise.
+ */
+static bool
+idpf_ptp_update_tstamp_tracker(struct idpf_ptp_vport_tx_tstamp_caps *caps,
+			       struct sk_buff *skb,
+			       enum idpf_ptp_tx_tstamp_state current_state,
+			       enum idpf_ptp_tx_tstamp_state expected_state)
+{
+	bool updated = false;
+
+	spin_lock(&caps->lock_status);
+	for (u16 i = 0; i < caps->num_entries; i++) {
+		struct idpf_ptp_tx_tstamp_status *status;
+
+		status = &caps->tx_tstamp_status[i];
+
+		if (skb == status->skb && status->state == current_state) {
+			status->state = expected_state;
+			updated = true;
+			break;
+		}
+	}
+	spin_unlock(&caps->lock_status);
+
+	return updated;
+}
+
+/**
+ * idpf_ptp_get_tstamp_value - Get the Tx timestamp value and provide it
+ *			       back to the skb.
+ * @vport: Virtual port structure
+ * @tstamp_latch: Tx timestamp latch structure fulfilled by the Control Plane
+ * @ptp_tx_tstamp: Tx timestamp latch to add to the free list
+ *
+ * Read the value of the Tx timestamp for a given latch received from the
+ * Control Plane, extend it to 64 bit and provide back to the skb.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tstamp_value(struct idpf_vport *vport,
+			  struct virtchnl2_ptp_tx_tstamp_latch *tstamp_latch,
+			  struct idpf_ptp_tx_tstamp *ptp_tx_tstamp)
+{
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct skb_shared_hwtstamps shhwtstamps;
+	bool state_upd = false;
+	u8 tstamp_ns_lo_bit;
+	u64 tstamp;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	tstamp_ns_lo_bit = tx_tstamp_caps->tstamp_ns_lo_bit;
+
+	ptp_tx_tstamp->tstamp = le64_to_cpu(tstamp_latch->tstamp);
+	ptp_tx_tstamp->tstamp >>= tstamp_ns_lo_bit;
+
+	state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+						   ptp_tx_tstamp->skb,
+						   IDPF_PTP_READ_VALUE,
+						   IDPF_PTP_FREE);
+	if (!state_upd)
+		return -EINVAL;
+
+	tstamp = idpf_ptp_extend_ts(vport, ptp_tx_tstamp->tstamp);
+	shhwtstamps.hwtstamp = ns_to_ktime(tstamp);
+	skb_tstamp_tx(ptp_tx_tstamp->skb, &shhwtstamps);
+	consume_skb(ptp_tx_tstamp->skb);
+
+	spin_lock(&tx_tstamp_caps->lock_free);
+	list_add(&ptp_tx_tstamp->list_member,
+		 &tx_tstamp_caps->latches_free);
+	spin_unlock(&tx_tstamp_caps->lock_free);
+
+	return 0;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp_async_handler - Async callback for getting Tx tstamps
+ * @adapter: Driver specific private structure
+ * @xn: transaction for message
+ * @ctlq_msg: received message
+ *
+ * Read the tstamps Tx tstamp values from a received message and put them
+ * directly to the skb. The number of timestamps to read is specified by
+ * the virtchnl message.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+static int
+idpf_ptp_get_tx_tstamp_async_handler(struct idpf_adapter *adapter,
+				     struct idpf_vc_xn *xn,
+				     const struct idpf_ctlq_msg *ctlq_msg)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *recv_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct virtchnl2_ptp_tx_tstamp_latch tstamp_latch;
+	struct idpf_ptp_tx_tstamp *tx_tstamp, *tmp;
+	struct idpf_vport *tstamp_vport = NULL;
+	struct list_head *head;
+	u16 num_latches;
+	u32 vport_id;
+	int err = 0;
+
+	recv_tx_tstamp_msg = ctlq_msg->ctx.indirect.payload->va;
+	vport_id = le32_to_cpu(recv_tx_tstamp_msg->vport_id);
+
+	idpf_for_each_vport(adapter, vport) {
+		if (!vport)
+			continue;
+
+		if (vport->vport_id == vport_id) {
+			tstamp_vport = vport;
+			break;
+		}
+	}
+
+	if (!tstamp_vport || !tstamp_vport->tx_tstamp_caps)
+		return -EINVAL;
+
+	tx_tstamp_caps = tstamp_vport->tx_tstamp_caps;
+	num_latches = le16_to_cpu(recv_tx_tstamp_msg->num_latches);
+
+	head = &tx_tstamp_caps->latches_in_use;
+	spin_lock(&tx_tstamp_caps->lock_in_use);
+
+	for (u16 i = 0; i < num_latches; i++) {
+		tstamp_latch = recv_tx_tstamp_msg->tstamp_latches[i];
+
+		if (!tstamp_latch.valid)
+			continue;
+
+		if (list_empty(head)) {
+			err = -ENOBUFS;
+			goto unlock;
+		}
+
+		list_for_each_entry_safe(tx_tstamp, tmp, head, list_member) {
+			if (tstamp_latch.index == tx_tstamp->idx) {
+				list_del(&tx_tstamp->list_member);
+				err = idpf_ptp_get_tstamp_value(tstamp_vport,
+								&tstamp_latch,
+								tx_tstamp);
+				if (err)
+					goto unlock;
+
+				break;
+			}
+		}
+	}
+
+unlock:
+	spin_unlock(&tx_tstamp_caps->lock_in_use);
+
+	return err;
+}
+
+/**
+ * idpf_ptp_get_tx_tstamp - Send virtchnl get Tx timestamp latches message
+ * @vport: Virtual port structure
+ *
+ * Send virtchnl get Tx tstamp message to read the value of the HW timestamp.
+ * The message contains a list of indexes set in the Tx descriptors.
+ *
+ * Return: 0 on success, -errno otherwise.
+ */
+int idpf_ptp_get_tx_tstamp(struct idpf_vport *vport)
+{
+	struct virtchnl2_ptp_get_vport_tx_tstamp_latches *send_tx_tstamp_msg;
+	struct idpf_ptp_vport_tx_tstamp_caps *tx_tstamp_caps;
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+		.async = true,
+		.async_handler = idpf_ptp_get_tx_tstamp_async_handler,
+	};
+	struct idpf_ptp_tx_tstamp *ptp_tx_tstamp;
+	int reply_sz, size, msg_size;
+	struct list_head *head;
+	bool state_upd;
+	u16 id = 0;
+
+	tx_tstamp_caps = vport->tx_tstamp_caps;
+	head = &tx_tstamp_caps->latches_in_use;
+
+	size = struct_size(send_tx_tstamp_msg, tstamp_latches,
+			   tx_tstamp_caps->num_entries);
+	send_tx_tstamp_msg = kzalloc(size, GFP_KERNEL);
+	if (!send_tx_tstamp_msg)
+		return -ENOMEM;
+
+	spin_lock(&tx_tstamp_caps->lock_in_use);
+	list_for_each_entry(ptp_tx_tstamp, head, list_member) {
+		u8 idx;
+
+		state_upd = idpf_ptp_update_tstamp_tracker(tx_tstamp_caps,
+							   ptp_tx_tstamp->skb,
+							   IDPF_PTP_REQUEST,
+							   IDPF_PTP_READ_VALUE);
+		if (!state_upd)
+			continue;
+
+		idx = ptp_tx_tstamp->idx;
+		send_tx_tstamp_msg->tstamp_latches[id].index = idx;
+		id++;
+	}
+	spin_unlock(&tx_tstamp_caps->lock_in_use);
+
+	msg_size = struct_size(send_tx_tstamp_msg, tstamp_latches, id);
+	send_tx_tstamp_msg->vport_id = cpu_to_le32(vport->vport_id);
+	send_tx_tstamp_msg->num_latches = cpu_to_le16(id);
+	xn_params.send_buf.iov_base = send_tx_tstamp_msg;
+	xn_params.send_buf.iov_len = msg_size;
+
+	reply_sz = idpf_vc_xn_exec(vport->adapter, &xn_params);
+	kfree(send_tx_tstamp_msg);
+
+	return min(reply_sz, 0);
+}

From 193a0c15f46913cee1e086c964b375db5554e4f3 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:24 -0700
Subject: [PATCH 2613/2753] idpf: add support for Rx timestamping

Add Rx timestamp function when the Rx timestamp value is read directly
from the Rx descriptor. In order to extend the Rx timestamp value to 64
bit in hot path, the PHC time is cached in the receive groups.
Add supported Rx timestamp modes.

Tested-by: YiFei Zhu <zhuyifei@google.com>
Tested-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/intel/idpf/idpf_ethtool.c    |  1 +
 drivers/net/ethernet/intel/idpf/idpf_lib.c    |  6 +-
 drivers/net/ethernet/intel/idpf/idpf_ptp.c    | 89 ++++++++++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_ptp.h    | 21 +++++
 drivers/net/ethernet/intel/idpf/idpf_txrx.c   | 30 +++++++
 drivers/net/ethernet/intel/idpf/idpf_txrx.h   |  7 +-
 6 files changed, 150 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
index ec4183a609c4f..7a4793749bc51 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
@@ -1333,6 +1333,7 @@ static void idpf_get_timestamp_filters(const struct idpf_vport *vport,
 				SOF_TIMESTAMPING_RAW_HARDWARE;
 
 	info->tx_types = BIT(HWTSTAMP_TX_OFF);
+	info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL);
 
 	if (!vport->tx_tstamp_caps ||
 	    vport->adapter->ptp->tx_tstamp_access == IDPF_PTP_NONE)
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b4752de5f0911..177bde44baa2c 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -2361,7 +2361,8 @@ static int idpf_hwtstamp_set(struct net_device *netdev,
 		return -EPERM;
 	}
 
-	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) {
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
 		idpf_vport_ctrl_unlock(netdev);
 		return -EOPNOTSUPP;
 	}
@@ -2386,7 +2387,8 @@ static int idpf_hwtstamp_get(struct net_device *netdev,
 		return -EPERM;
 	}
 
-	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport)) {
+	if (!idpf_ptp_is_vport_tx_tstamp_ena(vport) &&
+	    !idpf_ptp_is_vport_rx_tstamp_ena(vport)) {
 		idpf_vport_ctrl_unlock(netdev);
 		return 0;
 	}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.c b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
index 36bff5afa474e..85a9a25c44d6d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.c
@@ -317,12 +317,41 @@ static int idpf_ptp_gettimex64(struct ptp_clock_info *info,
 	return 0;
 }
 
+/**
+ * idpf_ptp_update_phctime_rxq_grp - Update the cached PHC time for a given Rx
+ *				     queue group.
+ * @grp: receive queue group in which Rx timestamp is enabled
+ * @split: Indicates whether the queue model is split or single queue
+ * @systime: Cached system time
+ */
+static void
+idpf_ptp_update_phctime_rxq_grp(const struct idpf_rxq_group *grp, bool split,
+				u64 systime)
+{
+	struct idpf_rx_queue *rxq;
+	u16 i;
+
+	if (!split) {
+		for (i = 0; i < grp->singleq.num_rxq; i++) {
+			rxq = grp->singleq.rxqs[i];
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	} else {
+		for (i = 0; i < grp->splitq.num_rxq_sets; i++) {
+			rxq = &grp->splitq.rxq_sets[i]->rxq;
+			if (rxq)
+				WRITE_ONCE(rxq->cached_phc_time, systime);
+		}
+	}
+}
+
 /**
  * idpf_ptp_update_cached_phctime - Update the cached PHC time values
  * @adapter: Driver specific private structure
  *
  * This function updates the system time values which are cached in the adapter
- * structure.
+ * structure and the Rx queues.
  *
  * This function must be called periodically to ensure that the cached value
  * is never more than 2 seconds old.
@@ -345,6 +374,21 @@ static int idpf_ptp_update_cached_phctime(struct idpf_adapter *adapter)
 	WRITE_ONCE(adapter->ptp->cached_phc_time, systime);
 	WRITE_ONCE(adapter->ptp->cached_phc_jiffies, jiffies);
 
+	idpf_for_each_vport(adapter, vport) {
+		bool split;
+
+		if (!vport || !vport->rxq_grps)
+			continue;
+
+		split = idpf_is_queue_model_split(vport->rxq_model);
+
+		for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+			struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+
+			idpf_ptp_update_phctime_rxq_grp(grp, split, systime);
+		}
+	}
+
 	return 0;
 }
 
@@ -608,6 +652,48 @@ int idpf_ptp_request_ts(struct idpf_tx_queue *tx_q, struct sk_buff *skb,
 	return 0;
 }
 
+/**
+ * idpf_ptp_set_rx_tstamp - Enable or disable Rx timestamping
+ * @vport: Virtual port structure
+ * @rx_filter: bool value for whether timestamps are enabled or disabled
+ */
+static void idpf_ptp_set_rx_tstamp(struct idpf_vport *vport, int rx_filter)
+{
+	bool enable = true, splitq;
+
+	splitq = idpf_is_queue_model_split(vport->rxq_model);
+
+	if (rx_filter == HWTSTAMP_FILTER_NONE) {
+		enable = false;
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_NONE;
+	} else {
+		vport->tstamp_config.rx_filter = HWTSTAMP_FILTER_ALL;
+	}
+
+	for (u16 i = 0; i < vport->num_rxq_grp; i++) {
+		struct idpf_rxq_group *grp = &vport->rxq_grps[i];
+		struct idpf_rx_queue *rx_queue;
+		u16 j, num_rxq;
+
+		if (splitq)
+			num_rxq = grp->splitq.num_rxq_sets;
+		else
+			num_rxq = grp->singleq.num_rxq;
+
+		for (j = 0; j < num_rxq; j++) {
+			if (splitq)
+				rx_queue = &grp->splitq.rxq_sets[j]->rxq;
+			else
+				rx_queue = grp->singleq.rxqs[j];
+
+			if (enable)
+				idpf_queue_set(PTP, rx_queue);
+			else
+				idpf_queue_clear(PTP, rx_queue);
+		}
+	}
+}
+
 /**
  * idpf_ptp_set_timestamp_mode - Setup driver for requested timestamp mode
  * @vport: Virtual port structure
@@ -630,6 +716,7 @@ int idpf_ptp_set_timestamp_mode(struct idpf_vport *vport,
 	}
 
 	vport->tstamp_config.tx_type = config->tx_type;
+	idpf_ptp_set_rx_tstamp(vport, config->rx_filter);
 	*config = vport->tstamp_config;
 
 	return 0;
diff --git a/drivers/net/ethernet/intel/idpf/idpf_ptp.h b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
index 5cb7b68085b60..c3ad2c5788682 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_ptp.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_ptp.h
@@ -234,6 +234,27 @@ static inline bool idpf_ptp_is_vport_tx_tstamp_ena(struct idpf_vport *vport)
 		return true;
 }
 
+/**
+ * idpf_ptp_is_vport_rx_tstamp_ena - Verify the Rx timestamping enablement for
+ *				     a given vport.
+ * @vport: Virtual port structure
+ *
+ * Rx timestamp feature is enabled if the PTP clock for the adapter is created
+ * and it is possible to read the value of the device clock. The second
+ * assumption comes from the need to extend the Rx timestamp value to 64 bit
+ * based on the current device clock time.
+ *
+ * Return: true if the Rx timestamping is enabled, false otherwise.
+ */
+static inline bool idpf_ptp_is_vport_rx_tstamp_ena(struct idpf_vport *vport)
+{
+	if (!vport->adapter->ptp ||
+	    vport->adapter->ptp->get_dev_clk_time_access == IDPF_PTP_NONE)
+		return false;
+	else
+		return true;
+}
+
 #if IS_ENABLED(CONFIG_PTP_1588_CLOCK)
 int idpf_ptp_init(struct idpf_adapter *adapter);
 void idpf_ptp_release(struct idpf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
index 0aa0680e57ad9..5137e9d15adb4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
@@ -3170,6 +3170,33 @@ static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	return 0;
 }
 
+/**
+ * idpf_rx_hwtstamp - check for an RX timestamp and pass up the stack
+ * @rxq: pointer to the rx queue that receives the timestamp
+ * @rx_desc: pointer to rx descriptor containing timestamp
+ * @skb: skb to put timestamp in
+ */
+static void
+idpf_rx_hwtstamp(const struct idpf_rx_queue *rxq,
+		 const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+		 struct sk_buff *skb)
+{
+	u64 cached_time, ts_ns;
+	u32 ts_high;
+
+	if (!(rx_desc->ts_low & VIRTCHNL2_RX_FLEX_TSTAMP_VALID))
+		return;
+
+	cached_time = READ_ONCE(rxq->cached_phc_time);
+
+	ts_high = le32_to_cpu(rx_desc->ts_high);
+	ts_ns = idpf_ptp_tstamp_extend_32b_to_64b(cached_time, ts_high);
+
+	*skb_hwtstamps(skb) = (struct skb_shared_hwtstamps) {
+		.hwtstamp = ns_to_ktime(ts_ns),
+	};
+}
+
 /**
  * idpf_rx_process_skb_fields - Populate skb header fields from Rx descriptor
  * @rxq: Rx descriptor ring packet is being transacted on
@@ -3195,6 +3222,9 @@ idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
 	/* process RSS/hash */
 	idpf_rx_hash(rxq, skb, rx_desc, decoded);
 
+	if (idpf_queue_has(PTP, rxq))
+		idpf_rx_hwtstamp(rxq, rx_desc, skb);
+
 	skb->protocol = eth_type_trans(skb, rxq->netdev);
 	skb_record_rx_queue(skb, rxq->idx);
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
index 9b7aa72e1f32d..c779fe71df999 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
@@ -290,6 +290,8 @@ struct idpf_ptype_state {
  * @__IDPF_Q_POLL_MODE: Enable poll mode
  * @__IDPF_Q_CRC_EN: enable CRC offload in singleq mode
  * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq)
+ * @__IDPF_Q_PTP: indicates whether the Rx timestamping is enabled for the
+ *		  queue
  * @__IDPF_Q_FLAGS_NBITS: Must be last
  */
 enum idpf_queue_flags_t {
@@ -300,6 +302,7 @@ enum idpf_queue_flags_t {
 	__IDPF_Q_POLL_MODE,
 	__IDPF_Q_CRC_EN,
 	__IDPF_Q_HSPLIT_EN,
+	__IDPF_Q_PTP,
 
 	__IDPF_Q_FLAGS_NBITS,
 };
@@ -496,6 +499,7 @@ struct idpf_txq_stash {
  * @next_to_alloc: RX buffer to allocate at
  * @skb: Pointer to the skb
  * @truesize: data buffer truesize in singleq
+ * @cached_phc_time: Cached PHC time for the Rx queue
  * @stats_sync: See struct u64_stats_sync
  * @q_stats: See union idpf_rx_queue_stats
  * @q_id: Queue id
@@ -543,6 +547,7 @@ struct idpf_rx_queue {
 
 	struct sk_buff *skb;
 	u32 truesize;
+	u64 cached_phc_time;
 
 	struct u64_stats_sync stats_sync;
 	struct idpf_rx_queue_stats q_stats;
@@ -562,7 +567,7 @@ struct idpf_rx_queue {
 	__cacheline_group_end_aligned(cold);
 };
 libeth_cacheline_set_assert(struct idpf_rx_queue, 64,
-			    80 + sizeof(struct u64_stats_sync),
+			    88 + sizeof(struct u64_stats_sync),
 			    32);
 
 /**

From ac00505ad01a9614eb4c550c118b37737135aa32 Mon Sep 17 00:00:00 2001
From: Milena Olech <milena.olech@intel.com>
Date: Tue, 18 Mar 2025 09:13:25 -0700
Subject: [PATCH 2614/2753] idpf: change the method for mailbox workqueue
 allocation

Since workqueues are created per CPU, the works scheduled to this
workqueues are run on the CPU they were assigned. It may result in
overloaded CPU that is not able to handle virtchnl messages in
relatively short time. Allocating workqueue with WQ_UNBOUND and
WQ_HIGHPRI flags allows scheduler to queue virtchl messages on less loaded
CPUs, what eliminates delays.

Reviewed-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Milena Olech <milena.olech@intel.com>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/idpf_main.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index 60bae30810353..022645f4fa9c1 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -198,9 +198,8 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto err_serv_wq_alloc;
 	}
 
-	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx",
-					  WQ_UNBOUND | WQ_MEM_RECLAIM, 0,
-					  dev_driver_string(dev),
+	adapter->mbx_wq = alloc_workqueue("%s-%s-mbx", WQ_UNBOUND | WQ_HIGHPRI,
+					  0, dev_driver_string(dev),
 					  dev_name(dev));
 	if (!adapter->mbx_wq) {
 		dev_err(dev, "Failed to allocate mailbox workqueue\n");

From c9c8ddb02899622e10a9e8554f16365819c8c73a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 18 Mar 2025 18:17:02 +0200
Subject: [PATCH 2615/2753] net: usb: asix: ax88772: Increase phy_name size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GCC compiler (Debian 14.2.0-17) is not happy about printing
into a short buffer (when build with `make W=1`):

 drivers/net/usb/ax88172a.c: In function ‘ax88172a_reset’:
 include/linux/phy.h:312:20: error: ‘%s’ directive output may be truncated writing up to 60 bytes into a region of size 20 [-Werror=format-truncation=]

Indeed, the buffer size is chosen based on some assumptions, while
in general the assigned name might not fit. Increase the buffer to
cover maximum length of the parameters. With that, change snprintf()
to use sizeof() instead of hard coded number.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/ax88172a.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/usb/ax88172a.c b/drivers/net/usb/ax88172a.c
index e47bb125048d4..7844eb02a4c78 100644
--- a/drivers/net/usb/ax88172a.c
+++ b/drivers/net/usb/ax88172a.c
@@ -18,7 +18,7 @@
 struct ax88172a_private {
 	struct mii_bus *mdio;
 	struct phy_device *phydev;
-	char phy_name[20];
+	char phy_name[MII_BUS_ID_SIZE + 5];
 	u16 phy_addr;
 	u16 oldmode;
 	int use_embdphy;
@@ -308,7 +308,7 @@ static int ax88172a_reset(struct usbnet *dev)
 		   rx_ctl);
 
 	/* Connect to PHY */
-	snprintf(priv->phy_name, 20, PHY_ID_FMT,
+	snprintf(priv->phy_name, sizeof(priv->phy_name), PHY_ID_FMT,
 		 priv->mdio->id, priv->phy_addr);
 
 	priv->phydev = phy_connect(dev->net, priv->phy_name,

From 8d53774a127bb6edb081ce8d5e132e68d32345d4 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 18 Mar 2025 19:55:19 +0100
Subject: [PATCH 2616/2753] netfilter: xtables: Use strscpy() instead of
 strscpy_pad()

kzalloc() already zero-initializes the destination buffer, making
strscpy() sufficient for safely copying the name. The additional NUL-
padding performed by strscpy_pad() is unnecessary.

The size parameter is optional, and strscpy() automatically determines
the size of the destination buffer using sizeof() if the argument is
omitted. This makes the explicit sizeof() call unnecessary; remove it.

No functional changes intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: NipaLocal <nipa@local>
---
 net/netfilter/xt_repldata.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/netfilter/xt_repldata.h b/net/netfilter/xt_repldata.h
index 5d1fb7018dbac..600060ca940af 100644
--- a/net/netfilter/xt_repldata.h
+++ b/net/netfilter/xt_repldata.h
@@ -29,7 +29,7 @@
 	if (tbl == NULL) \
 		return NULL; \
 	term = (struct type##_error *)&(((char *)tbl)[term_offset]); \
-	strscpy_pad(tbl->repl.name, info->name, sizeof(tbl->repl.name)); \
+	strscpy(tbl->repl.name, info->name); \
 	*term = (struct type##_error)typ2##_ERROR_INIT;  \
 	tbl->repl.valid_hooks = hook_mask; \
 	tbl->repl.num_entries = nhooks + 1; \

From ad549d80b88f3f80c8e84ff6992c24433a9fc21b Mon Sep 17 00:00:00 2001
From: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Date: Tue, 18 Mar 2025 13:04:45 -0700
Subject: [PATCH 2617/2753] ice: health.c: fix compilation on gcc 7.5

GCC 7 is not as good as GCC 8+ in telling what is a compile-time
const, and thus could be used for static storage.
Fortunately keeping strings as const arrays is enough to make old
gcc happy.

Excerpt from the report:
My GCC is: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0.

  CC [M]  drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.o
drivers/net/ethernet/intel/ice/devlink/health.c:35:3: error: initializer element is not constant
   ice_common_port_solutions, {ice_port_number_label}},
   ^~~~~~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/intel/ice/devlink/health.c:35:3: note: (near initialization for 'ice_health_status_lookup[0].solution')
drivers/net/ethernet/intel/ice/devlink/health.c:35:31: error: initializer element is not constant
   ice_common_port_solutions, {ice_port_number_label}},
                               ^~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/intel/ice/devlink/health.c:35:31: note: (near initialization for 'ice_health_status_lookup[0].data_label[0]')
drivers/net/ethernet/intel/ice/devlink/health.c:37:46: error: initializer element is not constant
   "Change or replace the module or cable.", {ice_port_number_label}},
                                              ^~~~~~~~~~~~~~~~~~~~~
drivers/net/ethernet/intel/ice/devlink/health.c:37:46: note: (near initialization for 'ice_health_status_lookup[1].data_label[0]')
drivers/net/ethernet/intel/ice/devlink/health.c:39:3: error: initializer element is not constant
   ice_common_port_solutions, {ice_port_number_label}},
   ^~~~~~~~~~~~~~~~~~~~~~~~~

Fixes: 85d6164ec56d ("ice: add fw and port health reporters")
Reported-by: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
Closes: https://lore.kernel.org/netdev/CY8PR11MB7134BF7A46D71E50D25FA7A989F72@CY8PR11MB7134.namprd11.prod.outlook.com
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Suggested-by: Simon Horman <horms@kernel.org>
Signed-off-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Sunitha Mekala <sunithax.d.mekala@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/devlink/health.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
index ea40f79412590..19c3d37aa768b 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.c
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -25,10 +25,10 @@ struct ice_health_status {
  * The below lookup requires to be sorted by code.
  */
 
-static const char *const ice_common_port_solutions =
+static const char ice_common_port_solutions[] =
 	"Check your cable connection. Change or replace the module or cable. Manually set speed and duplex.";
-static const char *const ice_port_number_label = "Port Number";
-static const char *const ice_update_nvm_solution = "Update to the latest NVM image.";
+static const char ice_port_number_label[] = "Port Number";
+static const char ice_update_nvm_solution[] = "Update to the latest NVM image.";
 
 static const struct ice_health_status ice_health_status_lookup[] = {
 	{ICE_AQC_HEALTH_STATUS_ERR_UNKNOWN_MOD_STRICT, "An unsupported module was detected.",

From a0ba61e6a2eba7f464255776c70119c943dc8e9a Mon Sep 17 00:00:00 2001
From: Karol Kolacinski <karol.kolacinski@intel.com>
Date: Tue, 18 Mar 2025 13:04:46 -0700
Subject: [PATCH 2618/2753] ice: ensure periodic output start time is in the
 future

On E800 series hardware, if the start time for a periodic output signal is
programmed into GLTSYN_TGT_H and GLTSYN_TGT_L registers, the hardware logic
locks up and the periodic output signal never starts. Any future attempt to
reprogram the clock function is futile as the hardware will not reset until
a power on.

The ice_ptp_cfg_perout function has logic to prevent this, as it checks if
the requested start time is in the past. If so, a new start time is
calculated by rounding up.

Since commit d755a7e129a5 ("ice: Cache perout/extts requests and check
flags"), the rounding is done to the nearest multiple of the clock period,
rather than to a full second. This is more accurate, since it ensures the
signal matches the user request precisely.

Unfortunately, there is a race condition with this rounding logic. If the
current time is close to the multiple of the period, we could calculate a
target time that is extremely soon. It takes time for the software to
program the registers, during which time this requested start time could
become a start time in the past. If that happens, the periodic output
signal will lock up.

For large enough periods, or for the logic prior to the mentioned commit,
this is unlikely. However, with the new logic rounding to the period and
with a small enough period, this becomes inevitable.

For example, attempting to enable a 10MHz signal requires a period of 100
nanoseconds. This means in the *best* case, we have 99 nanoseconds to
program the clock output. This is essentially impossible, and thus such a
small period practically guarantees that the clock output function will
lock up.

To fix this, add some slop to the clock time used to check if the start
time is in the past. Because it is not critical that output signals start
immediately, but it *is* critical that we do not brick the function, 0.5
seconds is selected. This does mean that any requested output will be
delayed by at least 0.5 seconds.

This slop is applied before rounding, so that we always round up to the
nearest multiple of the period that is at least 0.5 seconds in the future,
ensuring a minimum of 0.5 seconds to program the clock output registers.

Finally, to ensure that the hardware registers programming the clock output
complete in a timely manner, add a write flush to the end of
ice_ptp_write_perout. This ensures we don't risk any issue with PCIe
transaction batching.

Strictly speaking, this fixes a race condition all the way back at the
initial implementation of periodic output programming, as it is
theoretically possible to trigger this bug even on the old logic when
always rounding to a full second. However, the window is narrow, and the
code has been refactored heavily since then, making a direct backport not
apply cleanly.

Fixes: d755a7e129a5 ("ice: Cache perout/extts requests and check flags")
Signed-off-by: Karol Kolacinski <karol.kolacinski@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_ptp.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_ptp.c b/drivers/net/ethernet/intel/ice/ice_ptp.c
index 1bb0033347c76..1fd1ae03eb909 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp.c
@@ -1778,6 +1778,7 @@ static int ice_ptp_write_perout(struct ice_hw *hw, unsigned int chan,
 				  8 + chan + (tmr_idx * 4));
 
 	wr32(hw, GLGEN_GPIO_CTL(gpio_pin), val);
+	ice_flush(hw);
 
 	return 0;
 }
@@ -1838,9 +1839,10 @@ static int ice_ptp_cfg_perout(struct ice_pf *pf, struct ptp_perout_request *rq,
 		div64_u64_rem(start, period, &phase);
 
 	/* If we have only phase or start time is in the past, start the timer
-	 * at the next multiple of period, maintaining phase.
+	 * at the next multiple of period, maintaining phase at least 0.5 second
+	 * from now, so we have time to write it to HW.
 	 */
-	clk = ice_ptp_read_src_clk_reg(pf, NULL);
+	clk = ice_ptp_read_src_clk_reg(pf, NULL) + NSEC_PER_MSEC * 500;
 	if (rq->flags & PTP_PEROUT_PHASE || start <= clk - prop_delay_ns)
 		start = div64_u64(clk + period - 1, period) * period + phase;
 

From 7ebb0d49a24571cb7d86e8869271dacba1270906 Mon Sep 17 00:00:00 2001
From: Jesse Brandeburg <jbrandeburg@cloudflare.com>
Date: Tue, 18 Mar 2025 13:04:47 -0700
Subject: [PATCH 2619/2753] ice: fix reservation of resources for RDMA when
 disabled

If the CONFIG_INFINIBAND_IRDMA symbol is not enabled as a module or a
built-in, then don't let the driver reserve resources for RDMA. The result
of this change is a large savings in resources for older kernels, and a
cleaner driver configuration for the IRDMA=n case for old and new kernels.

Implement this by avoiding enabling the RDMA capability when scanning
hardware capabilities.

Note: Loading the out-of-tree irdma driver in connection to the in-kernel
ice driver, is not supported, and should not be attempted, especially when
disabling IRDMA in the kernel config.

Fixes: d25a0fc41c1f ("ice: Initialize RDMA support")
Signed-off-by: Jesse Brandeburg <jbrandeburg@cloudflare.com>
Acked-by: Dave Ertman <david.m.ertman@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_common.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index aaa592ffd2d82..59df31c2c83f7 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -2157,7 +2157,8 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 			  caps->nvm_unified_update);
 		break;
 	case ICE_AQC_CAPS_RDMA:
-		caps->rdma = (number == 1);
+		if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA))
+			caps->rdma = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma);
 		break;
 	case ICE_AQC_CAPS_MAX_MTU:

From f328864b9d5f210f380675475fb95406b1cd5ca6 Mon Sep 17 00:00:00 2001
From: Jan Glaza <jan.glaza@intel.com>
Date: Tue, 18 Mar 2025 13:04:48 -0700
Subject: [PATCH 2620/2753] virtchnl: make proto and filter action count
 unsigned

The count field in virtchnl_proto_hdrs and virtchnl_filter_action_set
should never be negative while still being valid. Changing it from
int to u32 ensures proper handling of values in virtchnl messages in
driverrs and prevents unintended behavior.
In its current signed form, a negative count does not trigger
an error in ice driver but instead results in it being treated as 0.
This can lead to unexpected outcomes when processing messages.
By using u32, any invalid values will correctly trigger -EINVAL,
making error detection more robust.

Fixes: 1f7ea1cd6a374 ("ice: Enable FDIR Configure for AVF")
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jan Glaza <jan.glaza@intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/avf/virtchnl.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 4811b9a146048..cf0afa60e4a7b 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -1343,7 +1343,7 @@ struct virtchnl_proto_hdrs {
 	 * 2 - from the second inner layer
 	 * ....
 	 **/
-	int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
+	u32 count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
 	union {
 		struct virtchnl_proto_hdr
 			proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
@@ -1395,7 +1395,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_filter_action);
 
 struct virtchnl_filter_action_set {
 	/* action number must be less then VIRTCHNL_MAX_NUM_ACTIONS */
-	int count;
+	u32 count;
 	struct virtchnl_filter_action actions[VIRTCHNL_MAX_NUM_ACTIONS];
 };
 

From 91d09bd8add732df7ff04389ae8a9f793d69380a Mon Sep 17 00:00:00 2001
From: Jan Glaza <jan.glaza@intel.com>
Date: Tue, 18 Mar 2025 13:04:49 -0700
Subject: [PATCH 2621/2753] ice: stop truncating queue ids when checking

Queue IDs can be up to 4096, fix invalid check to stop
truncating IDs to 8 bits.

Fixes: bf93bf791cec8 ("ice: introduce ice_virtchnl.c and ice_virtchnl.h")
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jan Glaza <jan.glaza@intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 674767781fe42..375949b3187db 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -565,7 +565,7 @@ bool ice_vc_isvalid_vsi_id(struct ice_vf *vf, u16 vsi_id)
  *
  * check for the valid queue ID
  */
-static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u8 qid)
+static bool ice_vc_isvalid_q_id(struct ice_vsi *vsi, u16 qid)
 {
 	/* allocated Tx and Rx queues should be always equal for VF VSI */
 	return qid < vsi->alloc_txq;

From 97560fdd26c474ea052828ad752f7c59f878015d Mon Sep 17 00:00:00 2001
From: Jan Glaza <jan.glaza@intel.com>
Date: Tue, 18 Mar 2025 13:04:50 -0700
Subject: [PATCH 2622/2753] ice: validate queue quanta parameters to prevent
 OOB access

Add queue wraparound prevention in quanta configuration.
Ensure end_qid does not overflow by validating start_qid and num_queues.

Fixes: 015307754a19 ("ice: Support VF queue rate limit and quanta size configuration")
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jan Glaza <jan.glaza@intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl.c | 13 +++++++++----
 1 file changed, 9 insertions(+), 4 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 375949b3187db..df0530344d42f 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -1903,13 +1903,21 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
  */
 static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 {
+	u16 quanta_prof_id, quanta_size, start_qid, num_queues, end_qid, i;
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	u16 quanta_prof_id, quanta_size, start_qid, end_qid, i;
 	struct virtchnl_quanta_cfg *qquanta =
 		(struct virtchnl_quanta_cfg *)msg;
 	struct ice_vsi *vsi;
 	int ret;
 
+	start_qid = qquanta->queue_select.start_queue_id;
+	num_queues = qquanta->queue_select.num_queues;
+
+	if (check_add_overflow(start_qid, num_queues, &end_qid)) {
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err;
+	}
+
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
 		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
 		goto err;
@@ -1921,8 +1929,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	end_qid = qquanta->queue_select.start_queue_id +
-		  qquanta->queue_select.num_queues;
 	if (end_qid > ICE_MAX_RSS_QS_PER_VF ||
 	    end_qid > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) {
 		dev_err(ice_pf_to_dev(vf->pf), "VF-%d trying to configure more than allocated number of queues: %d\n",
@@ -1951,7 +1957,6 @@ static int ice_vc_cfg_q_quanta(struct ice_vf *vf, u8 *msg)
 		goto err;
 	}
 
-	start_qid = qquanta->queue_select.start_queue_id;
 	for (i = start_qid; i < end_qid; i++)
 		vsi->tx_rings[i]->quanta_prof_id = quanta_prof_id;
 

From f6042912b23320f301fc36d85ba8bb2ab41049b2 Mon Sep 17 00:00:00 2001
From: Lukasz Czapnik <lukasz.czapnik@intel.com>
Date: Tue, 18 Mar 2025 13:04:51 -0700
Subject: [PATCH 2623/2753] ice: fix input validation for virtchnl BW

Add missing validation of tc and queue id values sent by a VF in
ice_vc_cfg_q_bw().
Additionally fixed logged value in the warning message,
where max_tx_rate was incorrectly referenced instead of min_tx_rate.
Also correct error handling in this function by properly exiting
when invalid configuration is detected.

Fixes: 015307754a19 ("ice: Support VF queue rate limit and quanta size configuration")
Reviewed-by: Jedrzej Jagielski <jedrzej.jagielski@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Lukasz Czapnik <lukasz.czapnik@intel.com>
Co-developed-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl.c | 24 ++++++++++++++++---
 1 file changed, 21 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index df0530344d42f..7c3006eb68dd0 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -1865,15 +1865,33 @@ static int ice_vc_cfg_q_bw(struct ice_vf *vf, u8 *msg)
 
 	for (i = 0; i < qbw->num_queues; i++) {
 		if (qbw->cfg[i].shaper.peak != 0 && vf->max_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.peak > vf->max_tx_rate)
+		    qbw->cfg[i].shaper.peak > vf->max_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The maximum queue %d rate limit configuration may not take effect because the maximum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
 				 vf->max_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 		if (qbw->cfg[i].shaper.committed != 0 && vf->min_tx_rate != 0 &&
-		    qbw->cfg[i].shaper.committed < vf->min_tx_rate)
+		    qbw->cfg[i].shaper.committed < vf->min_tx_rate) {
 			dev_warn(ice_pf_to_dev(vf->pf), "The minimum queue %d rate limit configuration may not take effect because the minimum TX rate for VF-%d is %d\n",
 				 qbw->cfg[i].queue_id, vf->vf_id,
-				 vf->max_tx_rate);
+				 vf->min_tx_rate);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].queue_id > vf->num_vf_qs) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure invalid queue_id\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
+		if (qbw->cfg[i].tc >= ICE_MAX_TRAFFIC_CLASS) {
+			dev_warn(ice_pf_to_dev(vf->pf), "VF-%d trying to configure a traffic class higher than allowed\n",
+				 vf->vf_id);
+			v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+			goto err;
+		}
 	}
 
 	for (i = 0; i < qbw->num_queues; i++) {

From 42192ed4a1960c21031626823dbeb07970bf6d2a Mon Sep 17 00:00:00 2001
From: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Date: Tue, 18 Mar 2025 13:04:52 -0700
Subject: [PATCH 2624/2753] ice: fix using untrusted value of pkt_len in
 ice_vc_fdir_parse_raw()

Fix using the untrusted value of proto->raw.pkt_len in function
ice_vc_fdir_parse_raw() by verifying if it does not exceed the
VIRTCHNL_MAX_SIZE_RAW_PACKET value.

Fixes: 99f419df8a5c ("ice: enable FDIR filters from raw binary patterns for VFs")
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Mateusz Polchlopek <mateusz.polchlopek@intel.com>
Signed-off-by: Martyna Szapar-Mudlaw <martyna.szapar-mudlaw@linux.intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/intel/ice/ice_virtchnl_fdir.c    | 24 ++++++++++++-------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 14e3f0f89c78d..9be4bd717512d 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -832,21 +832,27 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		      struct virtchnl_proto_hdrs *proto,
 		      struct virtchnl_fdir_fltr_conf *conf)
 {
-	u8 *pkt_buf, *msk_buf __free(kfree);
+	u8 *pkt_buf, *msk_buf __free(kfree) = NULL;
 	struct ice_parser_result rslt;
 	struct ice_pf *pf = vf->pf;
+	u16 pkt_len, udp_port = 0;
 	struct ice_parser *psr;
 	int status = -ENOMEM;
 	struct ice_hw *hw;
-	u16 udp_port = 0;
 
-	pkt_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
-	msk_buf = kzalloc(proto->raw.pkt_len, GFP_KERNEL);
+	pkt_len = proto->raw.pkt_len;
+
+	if (!pkt_len || pkt_len > VIRTCHNL_MAX_SIZE_RAW_PACKET)
+		return -EINVAL;
+
+	pkt_buf = kzalloc(pkt_len, GFP_KERNEL);
+	msk_buf = kzalloc(pkt_len, GFP_KERNEL);
+
 	if (!pkt_buf || !msk_buf)
 		goto err_mem_alloc;
 
-	memcpy(pkt_buf, proto->raw.spec, proto->raw.pkt_len);
-	memcpy(msk_buf, proto->raw.mask, proto->raw.pkt_len);
+	memcpy(pkt_buf, proto->raw.spec, pkt_len);
+	memcpy(msk_buf, proto->raw.mask, pkt_len);
 
 	hw = &pf->hw;
 
@@ -862,7 +868,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	if (ice_get_open_tunnel_port(hw, &udp_port, TNL_VXLAN))
 		ice_parser_vxlan_tunnel_set(psr, udp_port, true);
 
-	status = ice_parser_run(psr, pkt_buf, proto->raw.pkt_len, &rslt);
+	status = ice_parser_run(psr, pkt_buf, pkt_len, &rslt);
 	if (status)
 		goto err_parser_destroy;
 
@@ -876,7 +882,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 	}
 
 	status = ice_parser_profile_init(&rslt, pkt_buf, msk_buf,
-					 proto->raw.pkt_len, ICE_BLK_FD,
+					 pkt_len, ICE_BLK_FD,
 					 conf->prof);
 	if (status)
 		goto err_parser_profile_init;
@@ -885,7 +891,7 @@ ice_vc_fdir_parse_raw(struct ice_vf *vf,
 		ice_parser_profile_dump(hw, conf->prof);
 
 	/* Store raw flow info into @conf */
-	conf->pkt_len = proto->raw.pkt_len;
+	conf->pkt_len = pkt_len;
 	conf->pkt_buf = pkt_buf;
 	conf->parser_ena = true;
 

From 1975140eafe98fd2c7144df8f11e92f4ac1112b3 Mon Sep 17 00:00:00 2001
From: Emil Tantilov <emil.s.tantilov@intel.com>
Date: Tue, 18 Mar 2025 13:04:53 -0700
Subject: [PATCH 2625/2753] idpf: check error for register_netdev() on init

Current init logic ignores the error code from register_netdev(),
which will cause WARN_ON() on attempt to unregister it, if there was one,
and there is no info for the user that the creation of the netdev failed.

WARNING: CPU: 89 PID: 6902 at net/core/dev.c:11512 unregister_netdevice_many_notify+0x211/0x1a10
...
[ 3707.563641]  unregister_netdev+0x1c/0x30
[ 3707.563656]  idpf_vport_dealloc+0x5cf/0xce0 [idpf]
[ 3707.563684]  idpf_deinit_task+0xef/0x160 [idpf]
[ 3707.563712]  idpf_vc_core_deinit+0x84/0x320 [idpf]
[ 3707.563739]  idpf_remove+0xbf/0x780 [idpf]
[ 3707.563769]  pci_device_remove+0xab/0x1e0
[ 3707.563786]  device_release_driver_internal+0x371/0x530
[ 3707.563803]  driver_detach+0xbf/0x180
[ 3707.563816]  bus_remove_driver+0x11b/0x2a0
[ 3707.563829]  pci_unregister_driver+0x2a/0x250

Introduce an error check and log the vport number and error code.
On removal make sure to check VPORT_REG_NETDEV flag prior to calling
unregister and free on the netdev.

Add local variables for idx, vport_config and netdev for readability.

Fixes: 0fe45467a104 ("idpf: add create vport and netdev configuration")
Suggested-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: Emil Tantilov <emil.s.tantilov@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Tested-by: Samuel Salin <Samuel.salin@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/idpf/idpf_lib.c | 31 +++++++++++++++-------
 1 file changed, 22 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 177bde44baa2c..7e9a414dffa55 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -929,15 +929,19 @@ static int idpf_stop(struct net_device *netdev)
 static void idpf_decfg_netdev(struct idpf_vport *vport)
 {
 	struct idpf_adapter *adapter = vport->adapter;
+	u16 idx = vport->idx;
 
 	kfree(vport->rx_ptype_lkup);
 	vport->rx_ptype_lkup = NULL;
 
-	unregister_netdev(vport->netdev);
-	free_netdev(vport->netdev);
+	if (test_and_clear_bit(IDPF_VPORT_REG_NETDEV,
+			       adapter->vport_config[idx]->flags)) {
+		unregister_netdev(vport->netdev);
+		free_netdev(vport->netdev);
+	}
 	vport->netdev = NULL;
 
-	adapter->netdevs[vport->idx] = NULL;
+	adapter->netdevs[idx] = NULL;
 }
 
 /**
@@ -1538,13 +1542,22 @@ void idpf_init_task(struct work_struct *work)
 	}
 
 	for (index = 0; index < adapter->max_vports; index++) {
-		if (adapter->netdevs[index] &&
-		    !test_bit(IDPF_VPORT_REG_NETDEV,
-			      adapter->vport_config[index]->flags)) {
-			register_netdev(adapter->netdevs[index]);
-			set_bit(IDPF_VPORT_REG_NETDEV,
-				adapter->vport_config[index]->flags);
+		struct net_device *netdev = adapter->netdevs[index];
+		struct idpf_vport_config *vport_config;
+
+		vport_config = adapter->vport_config[index];
+
+		if (!netdev ||
+		    test_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags))
+			continue;
+
+		err = register_netdev(netdev);
+		if (err) {
+			dev_err(&pdev->dev, "failed to register netdev for vport %d: %pe\n",
+				index, ERR_PTR(err));
+			continue;
 		}
+		set_bit(IDPF_VPORT_REG_NETDEV, vport_config->flags);
 	}
 
 	/* As all the required vports are created, clear the reset flag

From 4c4692c1188b7e491672487f2d10178220366a62 Mon Sep 17 00:00:00 2001
From: Jacek Kowalski <jacek@jacekk.info>
Date: Tue, 18 Mar 2025 21:46:32 +0100
Subject: [PATCH 2626/2753] e1000e: add option not to verify NVM checksum

Many laptops and motherboards including I219-V network card have
invalid NVM checksum. While in most instances checksum is fixed by
e1000e module or by using bootutil, some setups are resistant to NVM
modifications. This result in the network card being completely
unusable.

It seems to be the case on Dell Latitude 5420 where UEFI firmware
corrupts (in this module's sense) checksums on each boot. No set of
BIOS options seems to help.

This commit adds e1000e module option called VerifyNVMChecksum
(defaults to 1) that allows advanced users to skip checkum verification
by setting it to 0.

Signed-off-by: Jacek Kowalski <Jacek@jacekk.info>
Cc: stable@vger.kernel.org
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/e1000e/e1000.h  |  1 +
 drivers/net/ethernet/intel/e1000e/netdev.c | 22 ++++++++--------
 drivers/net/ethernet/intel/e1000e/param.c  | 30 ++++++++++++++++++++++
 3 files changed, 43 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h
index ba9c19e6994c9..61dcc88dd2ff6 100644
--- a/drivers/net/ethernet/intel/e1000e/e1000.h
+++ b/drivers/net/ethernet/intel/e1000e/e1000.h
@@ -461,6 +461,7 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
 #define FLAG2_CHECK_RX_HWTSTAMP           BIT(13)
 #define FLAG2_CHECK_SYSTIM_OVERFLOW       BIT(14)
 #define FLAG2_ENABLE_S0IX_FLOWS           BIT(15)
+#define FLAG2_VERIFY_NVM_CHECKSUM         BIT(16)
 
 #define E1000_RX_DESC_PS(R, i)	    \
 	(&(((union e1000_rx_desc_packet_split *)((R).desc))[i]))
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 286155efcedf7..b99b22dcaba48 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -7567,16 +7567,18 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	 */
 	adapter->hw.mac.ops.reset_hw(&adapter->hw);
 
-	/* systems with ASPM and others may see the checksum fail on the first
-	 * attempt. Let's give it a few tries
-	 */
-	for (i = 0;; i++) {
-		if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
-			break;
-		if (i == 2) {
-			dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
-			err = -EIO;
-			goto err_eeprom;
+	if (adapter->flags2 & FLAG2_VERIFY_NVM_CHECKSUM) {
+		/* systems with ASPM and others may see the checksum fail on the first
+		* attempt. Let's give it a few tries
+		*/
+		for (i = 0;; i++) {
+			if (e1000_validate_nvm_checksum(&adapter->hw) >= 0)
+				break;
+			if (i == 2) {
+				dev_err(&pdev->dev, "The NVM Checksum Is Not Valid\n");
+				err = -EIO;
+				goto err_eeprom;
+			}
 		}
 	}
 
diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c
index 3132d8f2f207d..8711eb10dd119 100644
--- a/drivers/net/ethernet/intel/e1000e/param.c
+++ b/drivers/net/ethernet/intel/e1000e/param.c
@@ -127,6 +127,15 @@ E1000_PARAM(KumeranLockLoss, "Enable Kumeran lock loss workaround");
 E1000_PARAM(WriteProtectNVM,
 	    "Write-protect NVM [WARNING: disabling this can lead to corrupted NVM]");
 
+/* Verify NVM Checksum
+ *
+ * Valid Range: 0, 1
+ *
+ * Default Value: 1 (enabled)
+ */
+E1000_PARAM(VerifyNVMChecksum,
+	    "Verify NVM checksum [WARNING: disabling can cause invalid behavior]");
+
 /* Enable CRC Stripping
  *
  * Valid Range: 0, 1
@@ -524,4 +533,25 @@ void e1000e_check_options(struct e1000_adapter *adapter)
 			}
 		}
 	}
+	/* Verify NVM checksum */
+	{
+		static const struct e1000_option opt = {
+			.type = enable_option,
+			.name = "Verify NVM checksum",
+			.err  = "defaulting to Enabled",
+			.def  = OPTION_ENABLED
+		};
+
+		if (num_VerifyNVMChecksum > bd) {
+			unsigned int verify_nvm_checksum =
+				VerifyNVMChecksum[bd];
+			e1000_validate_option(&verify_nvm_checksum, &opt,
+						adapter);
+			if (verify_nvm_checksum)
+				adapter->flags2 |= FLAG2_VERIFY_NVM_CHECKSUM;
+		} else {
+			if (opt.def)
+				adapter->flags2 |= FLAG2_VERIFY_NVM_CHECKSUM;
+		}
+	}
 }

From d300e226d965f8f709b7855c72a1df25fee21792 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 18 Mar 2025 22:51:16 +0200
Subject: [PATCH 2627/2753] net/mlx5: LAG, reload representors on LAG creation
 failure

When LAG creation fails, the driver reloads the RDMA devices. If RDMA
representors are present, they should also be reloaded. This step was
missed in the cited commit.

Fixes: 598fe77df855 ("net/mlx5: Lag, Create shared FDB when in switchdev mode")
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index ed2ba272946b9..6c9737c537348 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -1052,6 +1052,10 @@ static void mlx5_do_bond(struct mlx5_lag *ldev)
 		if (err) {
 			if (shared_fdb || roce_lag)
 				mlx5_lag_add_devices(ldev);
+			if (shared_fdb) {
+				mlx5_ldev_for_each(i, 0, ldev)
+					mlx5_eswitch_reload_ib_reps(ldev->pf[i].dev->priv.eswitch);
+			}
 
 			return;
 		} else if (roce_lag) {

From 4c5943d6e7c33de80317c04b3b640551b7a08e78 Mon Sep 17 00:00:00 2001
From: Moshe Shemesh <moshe@nvidia.com>
Date: Tue, 18 Mar 2025 22:51:17 +0200
Subject: [PATCH 2628/2753] net/mlx5: Start health poll after enable hca

The health poll mechanism performs periodic checks to detect firmware
errors. One of the checks verifies the function is still enabled on
firmware side, but the function is enabled only after enable_hca command
completed. Start health poll after enable_hca command to avoid a race
between function enabled and first health polling.

Fixes: 9b98d395b85d ("net/mlx5: Start health poll at earlier stage of driver load")
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Reviewed-by: Shay Drori <shayd@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/main.c | 15 +++++++--------
 1 file changed, 7 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index 7e13c099e9fce..41e8660c819c0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1210,24 +1210,24 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 	dev->caps.embedded_cpu = mlx5_read_embedded_cpu(dev);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_UP);
 
-	mlx5_start_health_poll(dev);
-
 	err = mlx5_core_enable_hca(dev, 0);
 	if (err) {
 		mlx5_core_err(dev, "enable hca failed\n");
-		goto stop_health_poll;
+		goto err_cmd_cleanup;
 	}
 
+	mlx5_start_health_poll(dev);
+
 	err = mlx5_core_set_issi(dev);
 	if (err) {
 		mlx5_core_err(dev, "failed to set issi\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_satisfy_startup_pages(dev, 1);
 	if (err) {
 		mlx5_core_err(dev, "failed to allocate boot pages\n");
-		goto err_disable_hca;
+		goto stop_health_poll;
 	}
 
 	err = mlx5_tout_query_dtor(dev);
@@ -1240,10 +1240,9 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 
 reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
-err_disable_hca:
-	mlx5_core_disable_hca(dev, 0);
 stop_health_poll:
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 err_cmd_cleanup:
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
@@ -1254,8 +1253,8 @@ static int mlx5_function_enable(struct mlx5_core_dev *dev, bool boot, u64 timeou
 static void mlx5_function_disable(struct mlx5_core_dev *dev, bool boot)
 {
 	mlx5_reclaim_startup_pages(dev);
-	mlx5_core_disable_hca(dev, 0);
 	mlx5_stop_health_poll(dev, boot);
+	mlx5_core_disable_hca(dev, 0);
 	mlx5_cmd_set_state(dev, MLX5_CMDIF_STATE_DOWN);
 	mlx5_cmd_disable(dev);
 }

From 928d6fec425e71f359bfb944eb1d40fa88b18219 Mon Sep 17 00:00:00 2001
From: Joseph Huang <Joseph.Huang@garmin.com>
Date: Tue, 18 Mar 2025 18:42:46 -0400
Subject: [PATCH 2629/2753] net: bridge: mcast: Add offload failed mdb flag

Add MDB_FLAGS_OFFLOAD_FAILED and MDB_PG_FLAGS_OFFLOAD_FAILED to indicate
that an attempt to offload the MDB entry to switchdev has failed.

Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/uapi/linux/if_bridge.h |  9 +++++----
 net/bridge/br_mdb.c            |  2 ++
 net/bridge/br_private.h        | 11 ++++++-----
 net/bridge/br_switchdev.c      | 10 +++++-----
 4 files changed, 18 insertions(+), 14 deletions(-)

diff --git a/include/uapi/linux/if_bridge.h b/include/uapi/linux/if_bridge.h
index a5b743a2f7750..f2a6de424f3f9 100644
--- a/include/uapi/linux/if_bridge.h
+++ b/include/uapi/linux/if_bridge.h
@@ -699,10 +699,11 @@ struct br_mdb_entry {
 #define MDB_TEMPORARY 0
 #define MDB_PERMANENT 1
 	__u8 state;
-#define MDB_FLAGS_OFFLOAD	(1 << 0)
-#define MDB_FLAGS_FAST_LEAVE	(1 << 1)
-#define MDB_FLAGS_STAR_EXCL	(1 << 2)
-#define MDB_FLAGS_BLOCKED	(1 << 3)
+#define MDB_FLAGS_OFFLOAD		(1 << 0)
+#define MDB_FLAGS_FAST_LEAVE		(1 << 1)
+#define MDB_FLAGS_STAR_EXCL		(1 << 2)
+#define MDB_FLAGS_BLOCKED		(1 << 3)
+#define MDB_FLAGS_OFFLOAD_FAILED	(1 << 4)
 	__u8 flags;
 	__u16 vid;
 	struct {
diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 7e1ad229e1330..754bdf0fc1c03 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -144,6 +144,8 @@ static void __mdb_entry_fill_flags(struct br_mdb_entry *e, unsigned char flags)
 		e->flags |= MDB_FLAGS_STAR_EXCL;
 	if (flags & MDB_PG_FLAGS_BLOCKED)
 		e->flags |= MDB_FLAGS_BLOCKED;
+	if (flags & MDB_PG_FLAGS_OFFLOAD_FAILED)
+		e->flags |= MDB_FLAGS_OFFLOAD_FAILED;
 }
 
 static void __mdb_entry_to_br_ip(struct br_mdb_entry *entry, struct br_ip *ip,
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index d5b3c5936a79e..e09f9c344fa25 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -306,11 +306,12 @@ struct net_bridge_fdb_flush_desc {
 	u16				vlan_id;
 };
 
-#define MDB_PG_FLAGS_PERMANENT	BIT(0)
-#define MDB_PG_FLAGS_OFFLOAD	BIT(1)
-#define MDB_PG_FLAGS_FAST_LEAVE	BIT(2)
-#define MDB_PG_FLAGS_STAR_EXCL	BIT(3)
-#define MDB_PG_FLAGS_BLOCKED	BIT(4)
+#define MDB_PG_FLAGS_PERMANENT		BIT(0)
+#define MDB_PG_FLAGS_OFFLOAD		BIT(1)
+#define MDB_PG_FLAGS_FAST_LEAVE		BIT(2)
+#define MDB_PG_FLAGS_STAR_EXCL		BIT(3)
+#define MDB_PG_FLAGS_BLOCKED		BIT(4)
+#define MDB_PG_FLAGS_OFFLOAD_FAILED	BIT(5)
 
 #define PG_SRC_ENT_LIMIT	32
 
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 7b41ee8740cbb..68dccc2ff7b1b 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -505,9 +505,6 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	struct net_bridge_port *port = data->port;
 	struct net_bridge *br = port->br;
 
-	if (err)
-		goto err;
-
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &data->ip);
 	if (!mp)
@@ -516,11 +513,14 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	     pp = &p->next) {
 		if (p->key.port != port)
 			continue;
-		p->flags |= MDB_PG_FLAGS_OFFLOAD;
+
+		if (err)
+			p->flags |= MDB_PG_FLAGS_OFFLOAD_FAILED;
+		else
+			p->flags |= MDB_PG_FLAGS_OFFLOAD;
 	}
 out:
 	spin_unlock_bh(&br->multicast_lock);
-err:
 	kfree(priv);
 }
 

From 287485e8ab19872e09658a8c83732d680ae81299 Mon Sep 17 00:00:00 2001
From: Joseph Huang <Joseph.Huang@garmin.com>
Date: Tue, 18 Mar 2025 18:42:47 -0400
Subject: [PATCH 2630/2753] net: bridge: mcast: Notify on offload flag change

Notify user space on offload flag(s) change.

This behavior is controlled by the new knob mdb_notify_on_flag_change:

0 - the bridge will not notify user space about MDB flag change
1 - the bridge will notify user space about flag change if either
    MDB_PG_FLAGS_OFFLOAD or MDB_PG_FLAGS_OFFLOAD_FAILED has changed
2 - the bridge will notify user space about flag change only if
    MDB_PG_FLAGS_OFFLOAD_FAILED has changed

The default value is 0.

Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/bridge/br_mdb.c       | 28 +++++++++++++++++++++++-----
 net/bridge/br_multicast.c | 25 +++++++++++++++++++++++++
 net/bridge/br_private.h   | 15 +++++++++++++++
 net/bridge/br_switchdev.c | 25 +++++++++++++++++++++++--
 4 files changed, 86 insertions(+), 7 deletions(-)

diff --git a/net/bridge/br_mdb.c b/net/bridge/br_mdb.c
index 754bdf0fc1c03..bb5add19ad6a8 100644
--- a/net/bridge/br_mdb.c
+++ b/net/bridge/br_mdb.c
@@ -519,16 +519,17 @@ static size_t rtnl_mdb_nlmsg_size(const struct net_bridge_port_group *pg)
 	       rtnl_mdb_nlmsg_pg_size(pg);
 }
 
-void br_mdb_notify(struct net_device *dev,
-		   struct net_bridge_mdb_entry *mp,
-		   struct net_bridge_port_group *pg,
-		   int type)
+static void _br_mdb_notify(struct net_device *dev,
+			   struct net_bridge_mdb_entry *mp,
+			   struct net_bridge_port_group *pg,
+			   int type, bool notify_switchdev)
 {
 	struct net *net = dev_net(dev);
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	br_switchdev_mdb_notify(dev, mp, pg, type);
+	if (notify_switchdev)
+		br_switchdev_mdb_notify(dev, mp, pg, type);
 
 	skb = nlmsg_new(rtnl_mdb_nlmsg_size(pg), GFP_ATOMIC);
 	if (!skb)
@@ -546,6 +547,23 @@ void br_mdb_notify(struct net_device *dev,
 	rtnl_set_sk_err(net, RTNLGRP_MDB, err);
 }
 
+void br_mdb_notify(struct net_device *dev,
+		   struct net_bridge_mdb_entry *mp,
+		   struct net_bridge_port_group *pg,
+		   int type)
+{
+	_br_mdb_notify(dev, mp, pg, type, true);
+}
+
+#ifdef CONFIG_NET_SWITCHDEV
+void br_mdb_flag_change_notify(struct net_device *dev,
+			       struct net_bridge_mdb_entry *mp,
+			       struct net_bridge_port_group *pg)
+{
+	_br_mdb_notify(dev, mp, pg, RTM_NEWMDB, false);
+}
+#endif
+
 static int nlmsg_populate_rtr_fill(struct sk_buff *skb,
 				   struct net_device *dev,
 				   int ifindex, u16 vid, u32 pid,
diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
index b2ae0d2434d2e..8d583caecd40c 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -4051,6 +4051,10 @@ void br_multicast_ctx_init(struct net_bridge *br,
 	brmctx->ip6_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
 #endif
+#ifdef CONFIG_NET_SWITCHDEV
+	brmctx->multicast_mdb_notify_on_flag_change =
+		MDB_NOTIFY_ON_FLAG_CHANGE_DISABLE;
+#endif
 
 	timer_setup(&brmctx->ip4_mc_router_timer,
 		    br_ip4_multicast_local_router_expired, 0);
@@ -4708,6 +4712,27 @@ int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx,
 }
 #endif
 
+#ifdef CONFIG_NET_SWITCHDEV
+int br_multicast_set_mdb_notify_on_flag_change(struct net_bridge_mcast *brmctx,
+					       u8 val)
+{
+	switch (val) {
+	case MDB_NOTIFY_ON_FLAG_CHANGE_DISABLE:
+	case MDB_NOTIFY_ON_FLAG_CHANGE_BOTH:
+	case MDB_NOTIFY_ON_FLAG_CHANGE_FAIL_ONLY:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	spin_lock_bh(&brmctx->br->multicast_lock);
+	brmctx->multicast_mdb_notify_on_flag_change = val;
+	spin_unlock_bh(&brmctx->br->multicast_lock);
+
+	return 0;
+}
+#endif
+
 void br_multicast_set_query_intvl(struct net_bridge_mcast *brmctx,
 				  unsigned long val)
 {
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index e09f9c344fa25..6eb943695dfc8 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -132,6 +132,10 @@ struct net_bridge_mcast_port {
 #endif /* CONFIG_BRIDGE_IGMP_SNOOPING */
 };
 
+#define MDB_NOTIFY_ON_FLAG_CHANGE_DISABLE	0
+#define MDB_NOTIFY_ON_FLAG_CHANGE_BOTH		1
+#define MDB_NOTIFY_ON_FLAG_CHANGE_FAIL_ONLY	2
+
 /* net_bridge_mcast must be always defined due to forwarding stubs */
 struct net_bridge_mcast {
 #ifdef CONFIG_BRIDGE_IGMP_SNOOPING
@@ -146,6 +150,9 @@ struct net_bridge_mcast {
 	u8				multicast_router;
 #if IS_ENABLED(CONFIG_IPV6)
 	u8				multicast_mld_version;
+#endif
+#ifdef CONFIG_NET_SWITCHDEV
+	u8				multicast_mdb_notify_on_flag_change;
 #endif
 	unsigned long			multicast_last_member_interval;
 	unsigned long			multicast_membership_interval;
@@ -987,6 +994,10 @@ int br_multicast_set_igmp_version(struct net_bridge_mcast *brmctx,
 int br_multicast_set_mld_version(struct net_bridge_mcast *brmctx,
 				 unsigned long val);
 #endif
+#ifdef CONFIG_NET_SWITCHDEV
+int br_multicast_set_mdb_notify_on_flag_change(struct net_bridge_mcast *brmctx,
+					       u8 val);
+#endif
 struct net_bridge_mdb_entry *
 br_mdb_ip_get(struct net_bridge *br, struct br_ip *dst);
 struct net_bridge_mdb_entry *
@@ -1003,6 +1014,10 @@ int br_mdb_hash_init(struct net_bridge *br);
 void br_mdb_hash_fini(struct net_bridge *br);
 void br_mdb_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
 		   struct net_bridge_port_group *pg, int type);
+#ifdef CONFIG_NET_SWITCHDEV
+void br_mdb_flag_change_notify(struct net_device *dev, struct net_bridge_mdb_entry *mp,
+			       struct net_bridge_port_group *pg);
+#endif
 void br_rtr_notify(struct net_device *dev, struct net_bridge_mcast_port *pmctx,
 		   int type);
 void br_multicast_del_pg(struct net_bridge_mdb_entry *mp,
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 68dccc2ff7b1b..5b09cfcdf3f3b 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -504,20 +504,41 @@ static void br_switchdev_mdb_complete(struct net_device *dev, int err, void *pri
 	struct net_bridge_mdb_entry *mp;
 	struct net_bridge_port *port = data->port;
 	struct net_bridge *br = port->br;
+	bool offload_changed = false;
+	bool failed_changed = false;
+	u8 notify;
 
 	spin_lock_bh(&br->multicast_lock);
 	mp = br_mdb_ip_get(br, &data->ip);
 	if (!mp)
 		goto out;
+
+	notify = br->multicast_ctx.multicast_mdb_notify_on_flag_change;
+
 	for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL;
 	     pp = &p->next) {
 		if (p->key.port != port)
 			continue;
 
-		if (err)
+		if (err) {
+			if (!(p->flags & MDB_PG_FLAGS_OFFLOAD_FAILED))
+				failed_changed = true;
 			p->flags |= MDB_PG_FLAGS_OFFLOAD_FAILED;
-		else
+		} else {
+			if (!(p->flags & MDB_PG_FLAGS_OFFLOAD))
+				offload_changed = true;
 			p->flags |= MDB_PG_FLAGS_OFFLOAD;
+		}
+
+		if (notify == MDB_NOTIFY_ON_FLAG_CHANGE_DISABLE ||
+		    (!offload_changed && !failed_changed))
+			continue;
+
+		if (notify == MDB_NOTIFY_ON_FLAG_CHANGE_FAIL_ONLY &&
+		    !failed_changed)
+			continue;
+
+		br_mdb_flag_change_notify(br->dev, mp, p);
 	}
 out:
 	spin_unlock_bh(&br->multicast_lock);

From 7c19192797b868537b3454831987628252a5360e Mon Sep 17 00:00:00 2001
From: Joseph Huang <Joseph.Huang@garmin.com>
Date: Tue, 18 Mar 2025 18:42:48 -0400
Subject: [PATCH 2631/2753] net: bridge: Add notify on flag change netlink i/f

Add netlink interface to manipulate the mdb_notify_on_flag_change knob.

Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/uapi/linux/if_link.h | 14 ++++++++++++++
 net/bridge/br_netlink.c      | 21 +++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h
index 3ad2d5d980347..9cbe5d58bff14 100644
--- a/include/uapi/linux/if_link.h
+++ b/include/uapi/linux/if_link.h
@@ -742,6 +742,19 @@ enum in6_addr_gen_mode {
  * @IFLA_BR_FDB_MAX_LEARNED
  *   Set the number of max dynamically learned FDB entries for the current
  *   bridge.
+ *
+ * @IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE
+ *   Set how the bridge shall notify user space about MDB flag change via
+ *   RTM_NEWMDB netlink message.
+ *   The valid values are:
+ *
+ *     * 0 - the bridge will not notify user space about MDB flag change
+ *     * 1 - the bridge will notify user space about flag change if either
+ *           MDB_PG_FLAGS_OFFLOAD or MDB_PG_FLAGS_OFFLOAD_FAILED has changed
+ *     * 2 - the bridge will notify user space about flag change only if
+ *           MDB_PG_FLAGS_OFFLOAD_FAILED has changed
+ *
+ *   The default value is 0.
  */
 enum {
 	IFLA_BR_UNSPEC,
@@ -794,6 +807,7 @@ enum {
 	IFLA_BR_MCAST_QUERIER_STATE,
 	IFLA_BR_FDB_N_LEARNED,
 	IFLA_BR_FDB_MAX_LEARNED,
+	IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE,
 	__IFLA_BR_MAX,
 };
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 6e337937d0d7b..3ebdb7d3372d5 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -1270,6 +1270,7 @@ static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = {
 		NLA_POLICY_EXACT_LEN(sizeof(struct br_boolopt_multi)),
 	[IFLA_BR_FDB_N_LEARNED] = { .type = NLA_REJECT },
 	[IFLA_BR_FDB_MAX_LEARNED] = { .type = NLA_U32 },
+	[IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE] = { .type = NLA_U8 },
 };
 
 static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
@@ -1514,6 +1515,18 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[],
 			return err;
 	}
 #endif
+
+#ifdef CONFIG_NET_SWITCHDEV
+	if (data[IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE]) {
+		__u8 val;
+
+		val = nla_get_u8(data[IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE]);
+		err = br_multicast_set_mdb_notify_on_flag_change(&br->multicast_ctx,
+								 val);
+		if (err)
+			return err;
+	}
+#endif
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	if (data[IFLA_BR_NF_CALL_IPTABLES]) {
@@ -1627,6 +1640,9 @@ static size_t br_get_size(const struct net_device *brdev)
 	       nla_total_size(sizeof(u8)) +	/* IFLA_BR_MCAST_IGMP_VERSION */
 	       nla_total_size(sizeof(u8)) +	/* IFLA_BR_MCAST_MLD_VERSION */
 	       br_multicast_querier_state_size() + /* IFLA_BR_MCAST_QUERIER_STATE */
+#ifdef CONFIG_NET_SWITCHDEV
+	       nla_total_size(sizeof(u8)) +	/* IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE */
+#endif
 #endif
 #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
 	       nla_total_size(sizeof(u8)) +     /* IFLA_BR_NF_CALL_IPTABLES */
@@ -1724,6 +1740,11 @@ static int br_fill_info(struct sk_buff *skb, const struct net_device *brdev)
 	if (nla_put_u8(skb, IFLA_BR_MCAST_MLD_VERSION,
 		       br->multicast_ctx.multicast_mld_version))
 		return -EMSGSIZE;
+#endif
+#ifdef CONFIG_NET_SWITCHDEV
+	if (nla_put_u8(skb, IFLA_BR_MDB_NOTIFY_ON_FLAG_CHANGE,
+		       br->multicast_ctx.multicast_mdb_notify_on_flag_change))
+		return -EMSGSIZE;
 #endif
 	clockval = jiffies_to_clock_t(br->multicast_ctx.multicast_last_member_interval);
 	if (nla_put_u64_64bit(skb, IFLA_BR_MCAST_LAST_MEMBER_INTVL, clockval,

From f06ed1f98696a461ede5bae07812f4ffc7a500cc Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:34 +0000
Subject: [PATCH 2632/2753] selftests/net: Print TCP flags in more common
 format

Before:
># 13145[lib/ftrace-tcp.c:427] trace event filter tcp_ao_key_not_found [2001:db8:1::1:-1 => 2001:db8:254::1:7010, L3index 0, flags: !FS!R!P!., keyid: 100, rnext: 100, maclen: -1, sne: -1] = 1

After:
># 13487[lib/ftrace-tcp.c:427] trace event filter tcp_ao_key_not_found [2001:db8:1::1:-1 => 2001:db8:254::1:7010, L3index 0, flags: S, keyid: 100, rnext: 100, maclen: -1, sne: -1] = 1

For the history, I think the initial format was to emphasize the absence
of flags as well as their presence (!R meant no RST flag). But looking
again, it's just unreadable and hard to understand.
Make it the standard/expected one.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
index 24380c68fec6b..27403f8750547 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/ftrace-tcp.c
@@ -427,11 +427,8 @@ static void dump_trace_event(struct expected_trace_point *e)
 	test_print("trace event filter %s [%s:%d => %s:%d, L3index %d, flags: %s%s%s%s%s, keyid: %d, rnext: %d, maclen: %d, sne: %d] = %zu",
 		   trace_event_names[e->type],
 		   src, e->src_port, dst, e->dst_port, e->L3index,
-		   (e->fin > 0) ? "F" : (e->fin == 0) ? "!F" : "",
-		   (e->syn > 0) ? "S" : (e->syn == 0) ? "!S" : "",
-		   (e->rst > 0) ? "R" : (e->rst == 0) ? "!R" : "",
-		   (e->psh > 0) ? "P" : (e->psh == 0) ? "!P" : "",
-		   (e->ack > 0) ? "." : (e->ack == 0) ? "!." : "",
+		   e->fin ? "F" : "", e->syn ? "S" : "", e->rst ? "R" : "",
+		   e->psh ? "P" : "", e->ack ? "." : "",
 		   e->keyid, e->rnext, e->maclen, e->sne, e->matched);
 }
 

From e3867d0e65da148e8dbbf2e126b7ff2a66f40f50 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:35 +0000
Subject: [PATCH 2633/2753] selftests/net: Provide tcp-ao counters comparison
 helper

Rename __test_tcp_ao_counters_cmp() into test_assert_counters_ao() and
test_tcp_ao_key_counters_cmp() into test_assert_counters_key() as they
are asserts, rather than just compare functions.

Provide test_cmp_counters() helper, that's going to be used to compare
ao_info and netns counters as a stop condition for polling the sockets.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/tcp_ao/connect-deny.c       |  4 +-
 tools/testing/selftests/net/tcp_ao/connect.c  |  2 +-
 .../selftests/net/tcp_ao/icmps-discard.c      |  4 +-
 .../selftests/net/tcp_ao/key-management.c     |  8 +-
 .../testing/selftests/net/tcp_ao/lib/aolib.h  | 33 ++++++--
 tools/testing/selftests/net/tcp_ao/lib/sock.c | 83 +++++++++++--------
 tools/testing/selftests/net/tcp_ao/restore.c  |  4 +-
 tools/testing/selftests/net/tcp_ao/rst.c      |  6 +-
 .../selftests/net/tcp_ao/self-connect.c       |  2 +-
 tools/testing/selftests/net/tcp_ao/seq-ext.c  |  4 +-
 .../selftests/net/tcp_ao/unsigned-md5.c       |  2 +-
 11 files changed, 89 insertions(+), 63 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index d418162d335f4..42223a1a7a822 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -78,7 +78,7 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 	close(lsk);
 
 	if (pwd)
-		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
 	if (!cnt_name)
 		goto out;
@@ -204,7 +204,7 @@ static void try_connect(const char *tst_name, unsigned int port,
 	if (pwd && ret > 0) {
 		if (test_get_tcp_ao_counters(sk, &ao_cnt2))
 			test_error("test_get_tcp_ao_counters()");
-		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 	}
 out:
 	synchronize_threads(); /* close() */
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index f1d8d29e393f6..87647f38e7e6a 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -71,7 +71,7 @@ static void *client_fn(void *arg)
 				nr_packets, after_aogood, before_aogood);
 		return NULL;
 	}
-	if (test_tcp_ao_counters_cmp("connect", &ao1, &ao2, TEST_CNT_GOOD))
+	if (test_assert_counters("connect", &ao1, &ao2, TEST_CNT_GOOD))
 		return NULL;
 
 	test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu",
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index a1614f0d8c448..e2958a6a0e28e 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -91,9 +91,9 @@ static void serve_interfered(int sk)
 		return;
 	}
 #ifdef TEST_ICMPS_ACCEPT
-	test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD);
 #else
-	test_tcp_ao_counters_cmp(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
+	test_assert_counters(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
 #endif
 	if (icmp_ignored_a >= icmp_ignored_b) {
 		test_icmps_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index d4385b52c10b6..2c55c686285ac 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -633,7 +633,7 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 {
 	unsigned int i;
 
-	__test_tcp_ao_counters_cmp(tst_name, a, b, TEST_CNT_GOOD);
+	test_assert_counters_ao(tst_name, a, b, TEST_CNT_GOOD);
 
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
@@ -652,9 +652,9 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_tcp_ao_key_counters_cmp(tst_name, a, b,
-					     rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
-					     sndid, rcvid);
+		test_assert_counters_key(tst_name, a, b,
+					 rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
+					 sndid, rcvid);
 	}
 	test_tcp_ao_counters_free(a);
 	test_tcp_ao_counters_free(b);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index 5db2f65cddc4e..d6557940ef1fa 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -528,6 +528,22 @@ extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
 #define TEST_CNT_NS_DROPPED_ICMP	BIT(11)
 typedef uint16_t test_cnt;
 
+#define _for_each_counter(f)						\
+do {									\
+	/* per-netns */							\
+	f(netns_ao_good,		TEST_CNT_NS_GOOD);		\
+	f(netns_ao_bad,			TEST_CNT_NS_BAD);		\
+	f(netns_ao_key_not_found,	TEST_CNT_NS_KEY_NOT_FOUND);	\
+	f(netns_ao_required,		TEST_CNT_NS_AO_REQUIRED);	\
+	f(netns_ao_dropped_icmp,	TEST_CNT_NS_DROPPED_ICMP);	\
+	/* per-socket */						\
+	f(ao_info_pkt_good,		TEST_CNT_SOCK_GOOD);		\
+	f(ao_info_pkt_bad,		TEST_CNT_SOCK_BAD);		\
+	f(ao_info_pkt_key_not_found,	TEST_CNT_SOCK_KEY_NOT_FOUND);	\
+	f(ao_info_pkt_ao_required,	TEST_CNT_SOCK_AO_REQUIRED);	\
+	f(ao_info_pkt_dropped_icmp,	TEST_CNT_SOCK_DROPPED_ICMP);	\
+} while (0)
+
 #define TEST_CNT_AO_GOOD		(TEST_CNT_SOCK_GOOD | TEST_CNT_NS_GOOD)
 #define TEST_CNT_AO_BAD			(TEST_CNT_SOCK_BAD | TEST_CNT_NS_BAD)
 #define TEST_CNT_AO_KEY_NOT_FOUND	(TEST_CNT_SOCK_KEY_NOT_FOUND | \
@@ -539,10 +555,10 @@ typedef uint16_t test_cnt;
 #define TEST_CNT_GOOD			(TEST_CNT_KEY_GOOD | TEST_CNT_AO_GOOD)
 #define TEST_CNT_BAD			(TEST_CNT_KEY_BAD | TEST_CNT_AO_BAD)
 
-extern int __test_tcp_ao_counters_cmp(const char *tst_name,
+extern int test_assert_counters_ao(const char *tst_name,
 		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
 		test_cnt expected);
-extern int test_tcp_ao_key_counters_cmp(const char *tst_name,
+extern int test_assert_counters_key(const char *tst_name,
 		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
 		test_cnt expected, int sndid, int rcvid);
 extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts);
@@ -552,18 +568,17 @@ extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts);
  * to test_get_tcp_ao_counters(). Check key counters manually if they
  * may change.
  */
-static inline int test_tcp_ao_counters_cmp(const char *tst_name,
-					   struct tcp_ao_counters *before,
-					   struct tcp_ao_counters *after,
-					   test_cnt expected)
+static inline int test_assert_counters(const char *tst_name,
+				       struct tcp_ao_counters *before,
+				       struct tcp_ao_counters *after,
+				       test_cnt expected)
 {
 	int ret;
 
-	ret = __test_tcp_ao_counters_cmp(tst_name, before, after, expected);
+	ret = test_assert_counters_ao(tst_name, before, after, expected);
 	if (ret)
 		goto out;
-	ret = test_tcp_ao_key_counters_cmp(tst_name, before, after,
-					   expected, -1, -1);
+	ret = test_assert_counters_key(tst_name, before, after, expected, -1, -1);
 out:
 	test_tcp_ao_counters_free(before);
 	test_tcp_ao_counters_free(after);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 0ffda966c677b..2a2586b2ffa2b 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -403,55 +403,66 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
 	return 0;
 }
 
-int __test_tcp_ao_counters_cmp(const char *tst_name,
-			       struct tcp_ao_counters *before,
-			       struct tcp_ao_counters *after,
-			       test_cnt expected)
+int test_cmp_counters(struct tcp_ao_counters *before, struct tcp_ao_counters *after)
 {
-#define __cmp_ao(cnt, expecting_inc)					\
+#define __cmp(cnt, e_cnt)						\
+do {									\
+	if (before->cnt > after->cnt)					\
+		return -1;						\
+	if (before->cnt != after->cnt)					\
+		ret |= e_cnt;						\
+} while (0)
+
+	int ret = 0;
+	size_t i;
+
+	if (before->nr_keys != after->nr_keys)
+		return -1;
+
+	_for_each_counter(__cmp);
+
+	i = before->nr_keys;
+	while (i--) {
+		__cmp(key_cnts[i].pkt_good, TEST_CNT_KEY_GOOD);
+		__cmp(key_cnts[i].pkt_bad, TEST_CNT_KEY_BAD);
+	}
+#undef __cmp
+	return ret;
+}
+
+int test_assert_counters_ao(const char *tst_name,
+			    struct tcp_ao_counters *before,
+			    struct tcp_ao_counters *after,
+			    test_cnt expected)
+{
+#define __cmp_ao(cnt, e_cnt)						\
 do {									\
 	if (before->cnt > after->cnt) {					\
 		test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64, \
-			  tst_name ?: "", before->cnt, after->cnt);		\
+			  tst_name ?: "", before->cnt, after->cnt);	\
 		return -1;						\
 	}								\
-	if ((before->cnt != after->cnt) != (expecting_inc)) {		\
+	if ((before->cnt != after->cnt) != !!(expected & e_cnt)) {	\
 		test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64, \
-			  tst_name ?: "", (expecting_inc) ? "" : "not ",	\
+			  tst_name ?: "", (expected & e_cnt) ? "" : "not ",	\
 			  before->cnt, after->cnt);			\
 		return -1;						\
 	}								\
-} while(0)
+} while (0)
 
 	errno = 0;
-	/* per-netns */
-	__cmp_ao(netns_ao_good, !!(expected & TEST_CNT_NS_GOOD));
-	__cmp_ao(netns_ao_bad, !!(expected & TEST_CNT_NS_BAD));
-	__cmp_ao(netns_ao_key_not_found,
-		 !!(expected & TEST_CNT_NS_KEY_NOT_FOUND));
-	__cmp_ao(netns_ao_required, !!(expected & TEST_CNT_NS_AO_REQUIRED));
-	__cmp_ao(netns_ao_dropped_icmp,
-		 !!(expected & TEST_CNT_NS_DROPPED_ICMP));
-	/* per-socket */
-	__cmp_ao(ao_info_pkt_good, !!(expected & TEST_CNT_SOCK_GOOD));
-	__cmp_ao(ao_info_pkt_bad, !!(expected & TEST_CNT_SOCK_BAD));
-	__cmp_ao(ao_info_pkt_key_not_found,
-		 !!(expected & TEST_CNT_SOCK_KEY_NOT_FOUND));
-	__cmp_ao(ao_info_pkt_ao_required, !!(expected & TEST_CNT_SOCK_AO_REQUIRED));
-	__cmp_ao(ao_info_pkt_dropped_icmp,
-		 !!(expected & TEST_CNT_SOCK_DROPPED_ICMP));
+	_for_each_counter(__cmp_ao);
 	return 0;
 #undef __cmp_ao
 }
 
-int test_tcp_ao_key_counters_cmp(const char *tst_name,
-				 struct tcp_ao_counters *before,
-				 struct tcp_ao_counters *after,
-				 test_cnt expected,
-				 int sndid, int rcvid)
+int test_assert_counters_key(const char *tst_name,
+			     struct tcp_ao_counters *before,
+			     struct tcp_ao_counters *after,
+			     test_cnt expected, int sndid, int rcvid)
 {
 	size_t i;
-#define __cmp_ao(i, cnt, expecting_inc)					\
+#define __cmp_ao(i, cnt, e_cnt)					\
 do {									\
 	if (before->key_cnts[i].cnt > after->key_cnts[i].cnt) {		\
 		test_fail("%s: Decreased counter " __stringify(cnt) " %" PRIu64 " > %" PRIu64 " for key %u:%u", \
@@ -461,16 +472,16 @@ do {									\
 			  before->key_cnts[i].rcvid);			\
 		return -1;						\
 	}								\
-	if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != (expecting_inc)) {		\
+	if ((before->key_cnts[i].cnt != after->key_cnts[i].cnt) != !!(expected & e_cnt)) {		\
 		test_fail("%s: Counter " __stringify(cnt) " was %sexpected to increase %" PRIu64 " => %" PRIu64 " for key %u:%u", \
-			  tst_name ?: "", (expecting_inc) ? "" : "not ",\
+			  tst_name ?: "", (expected & e_cnt) ? "" : "not ",\
 			  before->key_cnts[i].cnt,			\
 			  after->key_cnts[i].cnt,			\
 			  before->key_cnts[i].sndid,			\
 			  before->key_cnts[i].rcvid);			\
 		return -1;						\
 	}								\
-} while(0)
+} while (0)
 
 	if (before->nr_keys != after->nr_keys) {
 		test_fail("%s: Keys changed on the socket %zu != %zu",
@@ -485,8 +496,8 @@ do {									\
 			continue;
 		if (rcvid >= 0 && before->key_cnts[i].rcvid != rcvid)
 			continue;
-		__cmp_ao(i, pkt_good, !!(expected & TEST_CNT_KEY_GOOD));
-		__cmp_ao(i, pkt_bad, !!(expected & TEST_CNT_KEY_BAD));
+		__cmp_ao(i, pkt_good, TEST_CNT_KEY_GOOD);
+		__cmp_ao(i, pkt_bad, TEST_CNT_KEY_BAD);
 	}
 	return 0;
 #undef __cmp_ao
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index ecc6f1e3a4141..ad8505f77023b 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -69,7 +69,7 @@ static void try_server_run(const char *tst_name, unsigned int port,
 		test_error("test_get_tcp_ao_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
-	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+	test_assert_counters(tst_name, &ao1, &ao2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
 		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -182,7 +182,7 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 		test_error("test_get_tcp_ao_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
-	test_tcp_ao_counters_cmp(tst_name, &ao1, &ao2, cnt_expected);
+	test_assert_counters(tst_name, &ao1, &ao2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
 		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index 6364facaa63ed..9cd257a995bb3 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -120,7 +120,7 @@ static void test_server_active_rst(unsigned int port)
 	synchronize_threads(); /* 5: closed active sk */
 
 	synchronize_threads(); /* 6: counters checks */
-	if (test_tcp_ao_counters_cmp("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD))
+	if (test_assert_counters("active RST server", &cnt1, &cnt2, TEST_CNT_GOOD))
 		test_fail("MKT counters (server) have not only good packets");
 	else
 		test_ok("MKT counters are good on server");
@@ -165,7 +165,7 @@ static void test_server_passive_rst(unsigned int port)
 	close(sk);
 
 	synchronize_threads(); /* 5: restore the socket, send more data */
-	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
 
 	synchronize_threads(); /* 6: server exits */
 }
@@ -431,7 +431,7 @@ static void test_client_passive_rst(unsigned int port)
 
 	synchronize_threads(); /* 6: server exits */
 	close(sk);
-	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
 }
 
 static void *client_fn(void *arg)
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 3ecd2b58de6a3..ebdf8e5d951f0 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -93,7 +93,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 		return;
 	}
 
-	if (test_tcp_ao_counters_cmp(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) {
+	if (test_assert_counters(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) {
 		close(sk);
 		return;
 	}
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index 8901a6785dc81..ea8a84edbd10f 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -140,7 +140,7 @@ static void *server_fn(void *arg)
 		test_error("test_get_tcp_ao_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
 
-	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &ao1, &ao2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
 		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -226,7 +226,7 @@ static void *client_fn(void *arg)
 		test_error("test_get_tcp_ao_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
 
-	test_tcp_ao_counters_cmp(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &ao1, &ao2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
 		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index f779e5892bc16..f403ca25bbe6e 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -108,7 +108,7 @@ static void try_accept(const char *tst_name, unsigned int port,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 	if (ao_addr)
-		test_tcp_ao_counters_cmp(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
 
 out:
 	synchronize_threads(); /* test_kill_sk() */

From 7c9b3a5198c19c4cc2ddd38d62e4669a600710b4 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:36 +0000
Subject: [PATCH 2634/2753] selftests/net: Fetch and check TCP-MD5 counters

There are related TCP-MD5 <=> TCP and TCP-MD5 <=> TCP-AO tests
that can benefit from checking the related counters, not only from
validating operations timeouts.

It also prepares the code for introduction of mixed select()+poll mode,
see the follow-up patches.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/tcp_ao/connect-deny.c       | 26 +++----
 tools/testing/selftests/net/tcp_ao/connect.c  | 18 ++---
 .../selftests/net/tcp_ao/icmps-discard.c      | 14 ++--
 .../selftests/net/tcp_ao/key-management.c     | 64 ++++++++---------
 .../testing/selftests/net/tcp_ao/lib/aolib.h  | 63 ++++++++++------
 tools/testing/selftests/net/tcp_ao/lib/sock.c | 72 ++++++++++---------
 tools/testing/selftests/net/tcp_ao/restore.c  | 56 +++++++--------
 tools/testing/selftests/net/tcp_ao/rst.c      | 34 ++++-----
 .../selftests/net/tcp_ao/self-connect.c       | 12 ++--
 tools/testing/selftests/net/tcp_ao/seq-ext.c  | 26 +++----
 .../selftests/net/tcp_ao/unsigned-md5.c       | 23 +++---
 11 files changed, 219 insertions(+), 189 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index 42223a1a7a822..919e8d2b91345 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -34,7 +34,7 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 		       const char *cnt_name, test_cnt cnt_expected,
 		       fault_t inj)
 {
-	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
 	int lsk, err, sk = 0;
 	time_t timeout;
@@ -46,8 +46,8 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 
 	if (cnt_name)
 		before_cnt = netstat_get_one(cnt_name, NULL);
-	if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt1))
-		test_error("test_get_tcp_ao_counters()");
+	if (pwd && test_get_tcp_counters(lsk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* preparations done */
 
@@ -72,13 +72,13 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 	}
 
 	synchronize_threads(); /* before counter checks */
-	if (pwd && test_get_tcp_ao_counters(lsk, &ao_cnt2))
-		test_error("test_get_tcp_ao_counters()");
+	if (pwd && test_get_tcp_counters(lsk, &cnt2))
+		test_error("test_get_tcp_counters()");
 
 	close(lsk);
 
 	if (pwd)
-		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
 
 	if (!cnt_name)
 		goto out;
@@ -163,7 +163,7 @@ static void try_connect(const char *tst_name, unsigned int port,
 			uint8_t sndid, uint8_t rcvid,
 			test_cnt cnt_expected, fault_t inj)
 {
-	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	struct tcp_counters cnt1, cnt2;
 	time_t timeout;
 	int sk, ret;
 
@@ -174,8 +174,8 @@ static void try_connect(const char *tst_name, unsigned int port,
 	if (pwd && test_add_key(sk, pwd, addr, prefix, sndid, rcvid))
 		test_error("setsockopt(TCP_AO_ADD_KEY)");
 
-	if (pwd && test_get_tcp_ao_counters(sk, &ao_cnt1))
-		test_error("test_get_tcp_ao_counters()");
+	if (pwd && test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* preparations done */
 
@@ -202,9 +202,11 @@ static void try_connect(const char *tst_name, unsigned int port,
 	else
 		test_ok("%s: connected", tst_name);
 	if (pwd && ret > 0) {
-		if (test_get_tcp_ao_counters(sk, &ao_cnt2))
-			test_error("test_get_tcp_ao_counters()");
-		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		if (test_get_tcp_counters(sk, &cnt2))
+			test_error("test_get_tcp_counters()");
+		test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
+	} else if (pwd) {
+		test_tcp_counters_free(&cnt1);
 	}
 out:
 	synchronize_threads(); /* close() */
diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index 87647f38e7e6a..45f2307483d3b 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -35,7 +35,7 @@ static void *client_fn(void *arg)
 	uint64_t before_aogood, after_aogood;
 	const size_t nr_packets = 20;
 	struct netstat *ns_before, *ns_after;
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters ao1, ao2;
 
 	if (sk < 0)
 		test_error("socket()");
@@ -50,8 +50,8 @@ static void *client_fn(void *arg)
 
 	ns_before = netstat_read();
 	before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
-	if (test_get_tcp_ao_counters(sk, &ao1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &ao1))
+		test_error("test_get_tcp_counters()");
 
 	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
 		test_fail("verify failed");
@@ -60,8 +60,8 @@ static void *client_fn(void *arg)
 
 	ns_after = netstat_read();
 	after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &ao2))
+		test_error("test_get_tcp_counters()");
 	netstat_print_diff(ns_before, ns_after);
 	netstat_free(ns_before);
 	netstat_free(ns_after);
@@ -75,10 +75,10 @@ static void *client_fn(void *arg)
 		return NULL;
 
 	test_ok("connect TCPAOGood %" PRIu64 "/%" PRIu64 "/%" PRIu64 " => %" PRIu64 "/%" PRIu64 "/%" PRIu64 ", sent %zu",
-			before_aogood, ao1.ao_info_pkt_good,
-			ao1.key_cnts[0].pkt_good,
-			after_aogood, ao2.ao_info_pkt_good,
-			ao2.key_cnts[0].pkt_good,
+			before_aogood, ao1.ao.ao_info_pkt_good,
+			ao1.ao.key_cnts[0].pkt_good,
+			after_aogood, ao2.ao.ao_info_pkt_good,
+			ao2.ao.key_cnts[0].pkt_good,
 			nr_packets);
 	return NULL;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index e2958a6a0e28e..61a5e8e2d7e0d 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -53,7 +53,7 @@ static void serve_interfered(int sk)
 	ssize_t test_quota = packet_size * packets_nr * 10;
 	uint64_t dest_unreach_a, dest_unreach_b;
 	uint64_t icmp_ignored_a, icmp_ignored_b;
-	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	struct tcp_counters cnt1, cnt2;
 	bool counter_not_found;
 	struct netstat *ns_after, *ns_before;
 	ssize_t bytes;
@@ -61,16 +61,16 @@ static void serve_interfered(int sk)
 	ns_before = netstat_read();
 	dest_unreach_a = netstat_get(ns_before, dst_unreach, NULL);
 	icmp_ignored_a = netstat_get(ns_before, tcpao_icmps, NULL);
-	if (test_get_tcp_ao_counters(sk, &ao_cnt1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 	bytes = test_server_run(sk, test_quota, 0);
 	ns_after = netstat_read();
 	netstat_print_diff(ns_before, ns_after);
 	dest_unreach_b = netstat_get(ns_after, dst_unreach, NULL);
 	icmp_ignored_b = netstat_get(ns_after, tcpao_icmps,
 					&counter_not_found);
-	if (test_get_tcp_ao_counters(sk, &ao_cnt2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 
 	netstat_free(ns_before);
 	netstat_free(ns_after);
@@ -91,9 +91,9 @@ static void serve_interfered(int sk)
 		return;
 	}
 #ifdef TEST_ICMPS_ACCEPT
-	test_assert_counters(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
 #else
-	test_assert_counters(NULL, &ao_cnt1, &ao_cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
+	test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD | TEST_CNT_AO_DROPPED_ICMP);
 #endif
 	if (icmp_ignored_a >= icmp_ignored_b) {
 		test_icmps_fail("%s counter didn't change: %" PRIu64 " >= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index 2c55c686285ac..c4087a15bdb3b 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -629,11 +629,11 @@ static int key_collection_socket(bool server, unsigned int port)
 }
 
 static void verify_counters(const char *tst_name, bool is_listen_sk, bool server,
-			    struct tcp_ao_counters *a, struct tcp_ao_counters *b)
+			    struct tcp_counters *a, struct tcp_counters *b)
 {
 	unsigned int i;
 
-	test_assert_counters_ao(tst_name, a, b, TEST_CNT_GOOD);
+	test_assert_counters_sk(tst_name, a, b, TEST_CNT_GOOD);
 
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
@@ -652,12 +652,12 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_assert_counters_key(tst_name, a, b,
+		test_assert_counters_key(tst_name, &a->ao, &b->ao,
 					 rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
 					 sndid, rcvid);
 	}
-	test_tcp_ao_counters_free(a);
-	test_tcp_ao_counters_free(b);
+	test_tcp_counters_free(a);
+	test_tcp_counters_free(b);
 	test_ok("%s: passed counters checks", tst_name);
 }
 
@@ -791,17 +791,17 @@ static void verify_keys(const char *tst_name, int sk,
 }
 
 static int start_server(const char *tst_name, unsigned int port, size_t quota,
-			struct tcp_ao_counters *begin,
+			struct tcp_counters *begin,
 			unsigned int current_index, unsigned int rnext_index)
 {
-	struct tcp_ao_counters lsk_c1, lsk_c2;
+	struct tcp_counters lsk_c1, lsk_c2;
 	ssize_t bytes;
 	int sk, lsk;
 
 	synchronize_threads(); /* 1: key collection initialized */
 	lsk = key_collection_socket(true, port);
-	if (test_get_tcp_ao_counters(lsk, &lsk_c1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(lsk, &lsk_c1))
+		test_error("test_get_tcp_counters()");
 	synchronize_threads(); /* 2: MKTs added => connect() */
 	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
 		test_error("test_wait_fd()");
@@ -809,12 +809,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota,
 	sk = accept(lsk, NULL, NULL);
 	if (sk < 0)
 		test_error("accept()");
-	if (test_get_tcp_ao_counters(sk, begin))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, begin))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* 3: accepted => send data */
-	if (test_get_tcp_ao_counters(lsk, &lsk_c2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(lsk, &lsk_c2))
+		test_error("test_get_tcp_counters()");
 	verify_keys(tst_name, lsk, true, true);
 	close(lsk);
 
@@ -830,12 +830,12 @@ static int start_server(const char *tst_name, unsigned int port, size_t quota,
 }
 
 static void end_server(const char *tst_name, int sk,
-		       struct tcp_ao_counters *begin)
+		       struct tcp_counters *begin)
 {
-	struct tcp_ao_counters end;
+	struct tcp_counters end;
 
-	if (test_get_tcp_ao_counters(sk, &end))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &end))
+		test_error("test_get_tcp_counters()");
 	verify_keys(tst_name, sk, false, true);
 
 	synchronize_threads(); /* 4: verified => closed */
@@ -848,7 +848,7 @@ static void end_server(const char *tst_name, int sk,
 static void try_server_run(const char *tst_name, unsigned int port, size_t quota,
 			   unsigned int current_index, unsigned int rnext_index)
 {
-	struct tcp_ao_counters tmp;
+	struct tcp_counters tmp;
 	int sk;
 
 	sk = start_server(tst_name, port, quota, &tmp,
@@ -860,7 +860,7 @@ static void server_rotations(const char *tst_name, unsigned int port,
 			     size_t quota, unsigned int rotations,
 			     unsigned int current_index, unsigned int rnext_index)
 {
-	struct tcp_ao_counters tmp;
+	struct tcp_counters tmp;
 	unsigned int i;
 	int sk;
 
@@ -886,7 +886,7 @@ static void server_rotations(const char *tst_name, unsigned int port,
 
 static int run_client(const char *tst_name, unsigned int port,
 		      unsigned int nr_keys, int current_index, int rnext_index,
-		      struct tcp_ao_counters *before,
+		      struct tcp_counters *before,
 		      const size_t msg_sz, const size_t msg_nr)
 {
 	int sk;
@@ -904,8 +904,8 @@ static int run_client(const char *tst_name, unsigned int port,
 		if (test_set_key(sk, sndid, rcvid))
 			test_error("failed to set current/rnext keys");
 	}
-	if (before && test_get_tcp_ao_counters(sk, before))
-		test_error("test_get_tcp_ao_counters()");
+	if (before && test_get_tcp_counters(sk, before))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* 2: MKTs added => connect() */
 	if (test_connect_socket(sk, this_ip_dest, port++) <= 0)
@@ -922,7 +922,7 @@ static int run_client(const char *tst_name, unsigned int port,
 		test_fail("verify failed");
 		close(sk);
 		if (before)
-			test_tcp_ao_counters_free(before);
+			test_tcp_counters_free(before);
 		return -1;
 	}
 
@@ -931,7 +931,7 @@ static int run_client(const char *tst_name, unsigned int port,
 
 static int start_client(const char *tst_name, unsigned int port,
 			unsigned int nr_keys, int current_index, int rnext_index,
-			struct tcp_ao_counters *before,
+			struct tcp_counters *before,
 			const size_t msg_sz, const size_t msg_nr)
 {
 	if (init_default_key_collection(nr_keys, true))
@@ -943,9 +943,9 @@ static int start_client(const char *tst_name, unsigned int port,
 
 static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
 		       int current_index, int rnext_index,
-		       struct tcp_ao_counters *start)
+		       struct tcp_counters *start)
 {
-	struct tcp_ao_counters end;
+	struct tcp_counters end;
 
 	/* Some application may become dependent on this kernel choice */
 	if (current_index < 0)
@@ -955,8 +955,8 @@ static void end_client(const char *tst_name, int sk, unsigned int nr_keys,
 	verify_current_rnext(tst_name, sk,
 			     collection.keys[current_index].client_keyid,
 			     collection.keys[rnext_index].server_keyid);
-	if (start && test_get_tcp_ao_counters(sk, &end))
-		test_error("test_get_tcp_ao_counters()");
+	if (start && test_get_tcp_counters(sk, &end))
+		test_error("test_get_tcp_counters()");
 	verify_keys(tst_name, sk, false, false);
 	synchronize_threads(); /* 4: verify => closed */
 	close(sk);
@@ -1048,7 +1048,7 @@ static void check_current_back(const char *tst_name, unsigned int port,
 			       unsigned int current_index, unsigned int rnext_index,
 			       unsigned int rotate_to_index)
 {
-	struct tcp_ao_counters tmp;
+	struct tcp_counters tmp;
 	int sk;
 
 	sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
@@ -1081,7 +1081,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 			   unsigned int nr_keys, unsigned int rotations,
 			   unsigned int current_index, unsigned int rnext_index)
 {
-	struct tcp_ao_counters tmp;
+	struct tcp_counters tmp;
 	unsigned int i;
 	int sk;
 
@@ -1102,7 +1102,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 		if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
 			test_fail("verify failed");
 			close(sk);
-			test_tcp_ao_counters_free(&tmp);
+			test_tcp_counters_free(&tmp);
 			return;
 		}
 		verify_current_rnext(tst_name, sk, -1,
@@ -1116,7 +1116,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 static void try_client_run(const char *tst_name, unsigned int port,
 			   unsigned int nr_keys, int current_index, int rnext_index)
 {
-	struct tcp_ao_counters tmp;
+	struct tcp_counters tmp;
 	int sk;
 
 	sk = start_client(tst_name, port, nr_keys, current_index, rnext_index,
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index d6557940ef1fa..b88d15df76886 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -512,7 +512,15 @@ struct tcp_ao_counters {
 	size_t nr_keys;
 	struct tcp_ao_key_counters *key_cnts;
 };
-extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
+
+struct tcp_counters {
+	struct tcp_ao_counters ao;
+	uint64_t netns_md5_notfound;
+	uint64_t netns_md5_unexpected;
+	uint64_t netns_md5_failure;
+};
+
+extern int test_get_tcp_counters(int sk, struct tcp_counters *out);
 
 #define TEST_CNT_KEY_GOOD		BIT(0)
 #define TEST_CNT_KEY_BAD		BIT(1)
@@ -526,22 +534,29 @@ extern int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out);
 #define TEST_CNT_NS_KEY_NOT_FOUND	BIT(9)
 #define TEST_CNT_NS_AO_REQUIRED		BIT(10)
 #define TEST_CNT_NS_DROPPED_ICMP	BIT(11)
+#define TEST_CNT_NS_MD5_NOT_FOUND	BIT(12)
+#define TEST_CNT_NS_MD5_UNEXPECTED	BIT(13)
+#define TEST_CNT_NS_MD5_FAILURE		BIT(14)
 typedef uint16_t test_cnt;
 
 #define _for_each_counter(f)						\
 do {									\
 	/* per-netns */							\
-	f(netns_ao_good,		TEST_CNT_NS_GOOD);		\
-	f(netns_ao_bad,			TEST_CNT_NS_BAD);		\
-	f(netns_ao_key_not_found,	TEST_CNT_NS_KEY_NOT_FOUND);	\
-	f(netns_ao_required,		TEST_CNT_NS_AO_REQUIRED);	\
-	f(netns_ao_dropped_icmp,	TEST_CNT_NS_DROPPED_ICMP);	\
+	f(ao.netns_ao_good,		TEST_CNT_NS_GOOD);		\
+	f(ao.netns_ao_bad,		TEST_CNT_NS_BAD);		\
+	f(ao.netns_ao_key_not_found,	TEST_CNT_NS_KEY_NOT_FOUND);	\
+	f(ao.netns_ao_required,		TEST_CNT_NS_AO_REQUIRED);	\
+	f(ao.netns_ao_dropped_icmp,	TEST_CNT_NS_DROPPED_ICMP);	\
 	/* per-socket */						\
-	f(ao_info_pkt_good,		TEST_CNT_SOCK_GOOD);		\
-	f(ao_info_pkt_bad,		TEST_CNT_SOCK_BAD);		\
-	f(ao_info_pkt_key_not_found,	TEST_CNT_SOCK_KEY_NOT_FOUND);	\
-	f(ao_info_pkt_ao_required,	TEST_CNT_SOCK_AO_REQUIRED);	\
-	f(ao_info_pkt_dropped_icmp,	TEST_CNT_SOCK_DROPPED_ICMP);	\
+	f(ao.ao_info_pkt_good,		TEST_CNT_SOCK_GOOD);		\
+	f(ao.ao_info_pkt_bad,		TEST_CNT_SOCK_BAD);		\
+	f(ao.ao_info_pkt_key_not_found,	TEST_CNT_SOCK_KEY_NOT_FOUND);	\
+	f(ao.ao_info_pkt_ao_required,	TEST_CNT_SOCK_AO_REQUIRED);	\
+	f(ao.ao_info_pkt_dropped_icmp,	TEST_CNT_SOCK_DROPPED_ICMP);	\
+	/* non-AO */							\
+	f(netns_md5_notfound,		TEST_CNT_NS_MD5_NOT_FOUND);	\
+	f(netns_md5_unexpected,		TEST_CNT_NS_MD5_UNEXPECTED);	\
+	f(netns_md5_failure,		TEST_CNT_NS_MD5_FAILURE);	\
 } while (0)
 
 #define TEST_CNT_AO_GOOD		(TEST_CNT_SOCK_GOOD | TEST_CNT_NS_GOOD)
@@ -555,33 +570,37 @@ do {									\
 #define TEST_CNT_GOOD			(TEST_CNT_KEY_GOOD | TEST_CNT_AO_GOOD)
 #define TEST_CNT_BAD			(TEST_CNT_KEY_BAD | TEST_CNT_AO_BAD)
 
-extern int test_assert_counters_ao(const char *tst_name,
-		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
+extern test_cnt test_cmp_counters(struct tcp_counters *before,
+				  struct tcp_counters *after);
+extern int test_assert_counters_sk(const char *tst_name,
+		struct tcp_counters *before, struct tcp_counters *after,
 		test_cnt expected);
 extern int test_assert_counters_key(const char *tst_name,
 		struct tcp_ao_counters *before, struct tcp_ao_counters *after,
 		test_cnt expected, int sndid, int rcvid);
-extern void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts);
+extern void test_tcp_counters_free(struct tcp_counters *cnts);
+
 /*
- * Frees buffers allocated in test_get_tcp_ao_counters().
+ * Frees buffers allocated in test_get_tcp_counters().
  * The function doesn't expect new keys or keys removed between calls
- * to test_get_tcp_ao_counters(). Check key counters manually if they
+ * to test_get_tcp_counters(). Check key counters manually if they
  * may change.
  */
 static inline int test_assert_counters(const char *tst_name,
-				       struct tcp_ao_counters *before,
-				       struct tcp_ao_counters *after,
+				       struct tcp_counters *before,
+				       struct tcp_counters *after,
 				       test_cnt expected)
 {
 	int ret;
 
-	ret = test_assert_counters_ao(tst_name, before, after, expected);
+	ret = test_assert_counters_sk(tst_name, before, after, expected);
 	if (ret)
 		goto out;
-	ret = test_assert_counters_key(tst_name, before, after, expected, -1, -1);
+	ret = test_assert_counters_key(tst_name, &before->ao, &after->ao,
+				       expected, -1, -1);
 out:
-	test_tcp_ao_counters_free(before);
-	test_tcp_ao_counters_free(after);
+	test_tcp_counters_free(before);
+	test_tcp_counters_free(after);
 	return ret;
 }
 
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 2a2586b2ffa2b..7ffde4dd79421 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -333,12 +333,12 @@ do {									\
 	return 0;
 }
 
-int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
+int test_get_tcp_counters(int sk, struct tcp_counters *out)
 {
 	struct tcp_ao_getsockopt *key_dump;
 	socklen_t key_dump_sz = sizeof(*key_dump);
 	struct tcp_ao_info_opt info = {};
-	bool c1, c2, c3, c4, c5;
+	bool c1, c2, c3, c4, c5, c6, c7, c8;
 	struct netstat *ns;
 	int err, nr_keys;
 
@@ -346,25 +346,30 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
 
 	/* per-netns */
 	ns = netstat_read();
-	out->netns_ao_good = netstat_get(ns, "TCPAOGood", &c1);
-	out->netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2);
-	out->netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3);
-	out->netns_ao_required = netstat_get(ns, "TCPAORequired", &c4);
-	out->netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5);
+	out->ao.netns_ao_good = netstat_get(ns, "TCPAOGood", &c1);
+	out->ao.netns_ao_bad = netstat_get(ns, "TCPAOBad", &c2);
+	out->ao.netns_ao_key_not_found = netstat_get(ns, "TCPAOKeyNotFound", &c3);
+	out->ao.netns_ao_required = netstat_get(ns, "TCPAORequired", &c4);
+	out->ao.netns_ao_dropped_icmp = netstat_get(ns, "TCPAODroppedIcmps", &c5);
+	out->netns_md5_notfound = netstat_get(ns, "TCPMD5NotFound", &c6);
+	out->netns_md5_unexpected = netstat_get(ns, "TCPMD5Unexpected", &c7);
+	out->netns_md5_failure = netstat_get(ns, "TCPMD5Failure", &c8);
 	netstat_free(ns);
-	if (c1 || c2 || c3 || c4 || c5)
+	if (c1 || c2 || c3 || c4 || c5 || c6 || c7 || c8)
 		return -EOPNOTSUPP;
 
 	err = test_get_ao_info(sk, &info);
+	if (err == -ENOENT)
+		return 0;
 	if (err)
 		return err;
 
 	/* per-socket */
-	out->ao_info_pkt_good		= info.pkt_good;
-	out->ao_info_pkt_bad		= info.pkt_bad;
-	out->ao_info_pkt_key_not_found	= info.pkt_key_not_found;
-	out->ao_info_pkt_ao_required	= info.pkt_ao_required;
-	out->ao_info_pkt_dropped_icmp	= info.pkt_dropped_icmp;
+	out->ao.ao_info_pkt_good = info.pkt_good;
+	out->ao.ao_info_pkt_bad = info.pkt_bad;
+	out->ao.ao_info_pkt_key_not_found = info.pkt_key_not_found;
+	out->ao.ao_info_pkt_ao_required = info.pkt_ao_required;
+	out->ao.ao_info_pkt_dropped_icmp = info.pkt_dropped_icmp;
 
 	/* per-key */
 	nr_keys = test_get_ao_keys_nr(sk);
@@ -372,7 +377,7 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
 		return nr_keys;
 	if (nr_keys == 0)
 		test_error("test_get_ao_keys_nr() == 0");
-	out->nr_keys = (size_t)nr_keys;
+	out->ao.nr_keys = (size_t)nr_keys;
 	key_dump = calloc(nr_keys, key_dump_sz);
 	if (!key_dump)
 		return -errno;
@@ -386,53 +391,54 @@ int test_get_tcp_ao_counters(int sk, struct tcp_ao_counters *out)
 		return -errno;
 	}
 
-	out->key_cnts = calloc(nr_keys, sizeof(out->key_cnts[0]));
-	if (!out->key_cnts) {
+	out->ao.key_cnts = calloc(nr_keys, sizeof(out->ao.key_cnts[0]));
+	if (!out->ao.key_cnts) {
 		free(key_dump);
 		return -errno;
 	}
 
 	while (nr_keys--) {
-		out->key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid;
-		out->key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid;
-		out->key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good;
-		out->key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad;
+		out->ao.key_cnts[nr_keys].sndid = key_dump[nr_keys].sndid;
+		out->ao.key_cnts[nr_keys].rcvid = key_dump[nr_keys].rcvid;
+		out->ao.key_cnts[nr_keys].pkt_good = key_dump[nr_keys].pkt_good;
+		out->ao.key_cnts[nr_keys].pkt_bad = key_dump[nr_keys].pkt_bad;
 	}
 	free(key_dump);
 
 	return 0;
 }
 
-int test_cmp_counters(struct tcp_ao_counters *before, struct tcp_ao_counters *after)
+test_cnt test_cmp_counters(struct tcp_counters *before,
+			   struct tcp_counters *after)
 {
 #define __cmp(cnt, e_cnt)						\
 do {									\
 	if (before->cnt > after->cnt)					\
-		return -1;						\
+		test_error("counter " __stringify(cnt) " decreased");	\
 	if (before->cnt != after->cnt)					\
 		ret |= e_cnt;						\
 } while (0)
 
-	int ret = 0;
+	test_cnt ret = 0;
 	size_t i;
 
-	if (before->nr_keys != after->nr_keys)
-		return -1;
+	if (before->ao.nr_keys != after->ao.nr_keys)
+		test_error("the number of keys has changed");
 
 	_for_each_counter(__cmp);
 
-	i = before->nr_keys;
+	i = before->ao.nr_keys;
 	while (i--) {
-		__cmp(key_cnts[i].pkt_good, TEST_CNT_KEY_GOOD);
-		__cmp(key_cnts[i].pkt_bad, TEST_CNT_KEY_BAD);
+		__cmp(ao.key_cnts[i].pkt_good, TEST_CNT_KEY_GOOD);
+		__cmp(ao.key_cnts[i].pkt_bad, TEST_CNT_KEY_BAD);
 	}
 #undef __cmp
 	return ret;
 }
 
-int test_assert_counters_ao(const char *tst_name,
-			    struct tcp_ao_counters *before,
-			    struct tcp_ao_counters *after,
+int test_assert_counters_sk(const char *tst_name,
+			    struct tcp_counters *before,
+			    struct tcp_counters *after,
 			    test_cnt expected)
 {
 #define __cmp_ao(cnt, e_cnt)						\
@@ -503,9 +509,9 @@ do {									\
 #undef __cmp_ao
 }
 
-void test_tcp_ao_counters_free(struct tcp_ao_counters *cnts)
+void test_tcp_counters_free(struct tcp_counters *cnts)
 {
-	free(cnts->key_cnts);
+	free(cnts->ao.key_cnts);
 }
 
 #define TEST_BUF_SIZE 4096
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index ad8505f77023b..4b98f06725ef9 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -17,7 +17,7 @@ static void try_server_run(const char *tst_name, unsigned int port,
 			   fault_t inj, test_cnt cnt_expected)
 {
 	const char *cnt_name = "TCPAOGood";
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt, after_cnt;
 	int sk, lsk;
 	time_t timeout;
@@ -48,8 +48,8 @@ static void try_server_run(const char *tst_name, unsigned int port,
 	}
 
 	before_cnt = netstat_get_one(cnt_name, NULL);
-	if (test_get_tcp_ao_counters(sk, &ao1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
 	bytes = test_server_run(sk, quota, timeout);
@@ -65,17 +65,17 @@ static void try_server_run(const char *tst_name, unsigned int port,
 			test_ok("%s: server alive", tst_name);
 	}
 	synchronize_threads(); /* 3: counters checks */
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
-	test_assert_counters(tst_name, &ao1, &ao2, cnt_expected);
+	test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
-		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
-				tst_name, cnt_name, after_cnt, before_cnt);
+		test_fail("%s(server): %s counter did not increase: %" PRIu64 " <= %" PRIu64,
+			  tst_name, cnt_name, after_cnt, before_cnt);
 	} else {
-		test_ok("%s: counter %s increased %" PRIu64 " => %" PRIu64,
+		test_ok("%s(server): counter %s increased %" PRIu64 " => %" PRIu64,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 
@@ -92,16 +92,16 @@ static void *server_fn(void *arg)
 {
 	unsigned int port = test_server_port;
 
-	try_server_run("TCP-AO migrate to another socket", port++,
+	try_server_run("TCP-AO migrate to another socket (server)", port++,
 		       0, TEST_CNT_GOOD);
-	try_server_run("TCP-AO with wrong send ISN", port++,
+	try_server_run("TCP-AO with wrong send ISN (server)", port++,
 		       FAULT_TIMEOUT, TEST_CNT_BAD);
-	try_server_run("TCP-AO with wrong receive ISN", port++,
+	try_server_run("TCP-AO with wrong receive ISN (server)", port++,
 		       FAULT_TIMEOUT, TEST_CNT_BAD);
-	try_server_run("TCP-AO with wrong send SEQ ext number", port++,
+	try_server_run("TCP-AO with wrong send SEQ ext number (server)", port++,
 		       FAULT_TIMEOUT, TEST_CNT_BAD);
-	try_server_run("TCP-AO with wrong receive SEQ ext number", port++,
-		       FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD);
+	try_server_run("TCP-AO with wrong receive SEQ ext number (server)",
+		       port++, FAULT_TIMEOUT, TEST_CNT_NS_BAD | TEST_CNT_GOOD);
 
 	synchronize_threads(); /* don't race to exit: client exits */
 	return NULL;
@@ -140,7 +140,7 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 			    fault_t inj, test_cnt cnt_expected)
 {
 	const char *cnt_name = "TCPAOGood";
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt, after_cnt;
 	time_t timeout;
 	int sk;
@@ -159,8 +159,8 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 		test_error("setsockopt(TCP_AO_ADD_KEY)");
 	test_ao_restore(sk, ao_img);
 
-	if (test_get_tcp_ao_counters(sk, &ao1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	test_disable_repair(sk);
 	test_sock_state_free(img);
@@ -178,11 +178,11 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 			test_ok("%s: post-migrate connection is alive", tst_name);
 	}
 	synchronize_threads(); /* 3: counters checks */
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	after_cnt = netstat_get_one(cnt_name, NULL);
 
-	test_assert_counters(tst_name, &ao1, &ao2, cnt_expected);
+	test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
 
 	if (after_cnt <= before_cnt) {
 		test_fail("%s: %s counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -203,7 +203,7 @@ static void *client_fn(void *arg)
 	sockaddr_af saddr;
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
-	test_sk_restore("TCP-AO migrate to another socket", port++,
+	test_sk_restore("TCP-AO migrate to another socket (client)", port++,
 			&saddr, &tcp_img, &ao_img, 0, TEST_CNT_GOOD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -212,7 +212,7 @@ static void *client_fn(void *arg)
 			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
 			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
-	test_sk_restore("TCP-AO with wrong send ISN", port++,
+	test_sk_restore("TCP-AO with wrong send ISN (client)", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -221,7 +221,7 @@ static void *client_fn(void *arg)
 			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
 			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
-	test_sk_restore("TCP-AO with wrong receive ISN", port++,
+	test_sk_restore("TCP-AO with wrong receive ISN (client)", port++,
 			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT, TEST_CNT_BAD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -229,8 +229,8 @@ static void *client_fn(void *arg)
 	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_addr, this_ip_dest,
 			      -1, port, 0, -1, -1, -1, -1, -1, 100, 100, -1);
 	/* not expecting server => client mismatches as only snd sne is broken */
-	test_sk_restore("TCP-AO with wrong send SEQ ext number", port++,
-			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+	test_sk_restore("TCP-AO with wrong send SEQ ext number (client)",
+			port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
 			TEST_CNT_NS_BAD | TEST_CNT_GOOD);
 
 	test_get_sk_checkpoint(port, &saddr, &tcp_img, &ao_img);
@@ -238,8 +238,8 @@ static void *client_fn(void *arg)
 	/* not expecting client => server mismatches as only rcv sne is broken */
 	trace_ao_event_expect(TCP_AO_MISMATCH, this_ip_dest, this_ip_addr,
 			      port, -1, 0, -1, -1, -1, -1, -1, 100, 100, -1);
-	test_sk_restore("TCP-AO with wrong receive SEQ ext number", port++,
-			&saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
+	test_sk_restore("TCP-AO with wrong receive SEQ ext number (client)",
+			port++, &saddr, &tcp_img, &ao_img, FAULT_TIMEOUT,
 			TEST_CNT_NS_GOOD | TEST_CNT_BAD);
 
 	return NULL;
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index 9cd257a995bb3..f752df511ba2e 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -84,15 +84,15 @@ static void close_forced(int sk)
 
 static void test_server_active_rst(unsigned int port)
 {
-	struct tcp_ao_counters cnt1, cnt2;
+	struct tcp_counters cnt1, cnt2;
 	ssize_t bytes;
 	int sk, lsk;
 
 	lsk = test_listen_socket(this_ip_addr, port, backlog);
 	if (test_add_key(lsk, DEFAULT_TEST_PASSWORD, this_ip_dest, -1, 100, 100))
 		test_error("setsockopt(TCP_AO_ADD_KEY)");
-	if (test_get_tcp_ao_counters(lsk, &cnt1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(lsk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* 1: MKT added */
 	if (test_wait_fd(lsk, TEST_TIMEOUT_SEC, 0))
@@ -103,8 +103,8 @@ static void test_server_active_rst(unsigned int port)
 		test_error("accept()");
 
 	synchronize_threads(); /* 2: connection accept()ed, another queued */
-	if (test_get_tcp_ao_counters(lsk, &cnt2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(lsk, &cnt2))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* 3: close listen socket */
 	close(lsk);
@@ -128,7 +128,7 @@ static void test_server_active_rst(unsigned int port)
 
 static void test_server_passive_rst(unsigned int port)
 {
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	int sk, lsk;
 	ssize_t bytes;
 
@@ -147,8 +147,8 @@ static void test_server_passive_rst(unsigned int port)
 
 	synchronize_threads(); /* 2: accepted => send data */
 	close(lsk);
-	if (test_get_tcp_ao_counters(sk, &ao1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	bytes = test_server_run(sk, quota, TEST_TIMEOUT_SEC);
 	if (bytes != quota) {
@@ -160,12 +160,12 @@ static void test_server_passive_rst(unsigned int port)
 
 	synchronize_threads(); /* 3: checkpoint the client */
 	synchronize_threads(); /* 4: close the server, creating twsk */
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	close(sk);
 
 	synchronize_threads(); /* 5: restore the socket, send more data */
-	test_assert_counters("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters("passive RST server", &cnt1, &cnt2, TEST_CNT_GOOD);
 
 	synchronize_threads(); /* 6: server exits */
 }
@@ -323,7 +323,7 @@ static void test_client_active_rst(unsigned int port)
 
 static void test_client_passive_rst(unsigned int port)
 {
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	struct tcp_ao_repair ao_img;
 	struct tcp_sock_state img;
 	sockaddr_af saddr;
@@ -397,8 +397,8 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("setsockopt(TCP_AO_ADD_KEY)");
 	test_ao_restore(sk, &ao_img);
 
-	if (test_get_tcp_ao_counters(sk, &ao1))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
@@ -426,12 +426,12 @@ static void test_client_passive_rst(unsigned int port)
 	else
 		test_fail("client sock is yet connected post-seq-adjust");
 
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* 6: server exits */
 	close(sk);
-	test_assert_counters("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters("client passive RST", &cnt1, &cnt2, TEST_CNT_GOOD);
 }
 
 static void *client_fn(void *arg)
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index ebdf8e5d951f0..93732732c60c0 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -30,7 +30,7 @@ static void setup_lo_intf(const char *lo_intf)
 static void tcp_self_connect(const char *tst, unsigned int port,
 			     bool different_keyids, bool check_restore)
 {
-	struct tcp_ao_counters before_ao, after_ao;
+	struct tcp_counters before, after;
 	uint64_t before_aogood, after_aogood;
 	struct netstat *ns_before, *ns_after;
 	const size_t nr_packets = 20;
@@ -60,8 +60,8 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 
 	ns_before = netstat_read();
 	before_aogood = netstat_get(ns_before, "TCPAOGood", NULL);
-	if (test_get_tcp_ao_counters(sk, &before_ao))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &before))
+		test_error("test_get_tcp_counters()");
 
 	if (__test_connect_socket(sk, "lo", (struct sockaddr *)&addr,
 				  sizeof(addr), TEST_TIMEOUT_SEC) < 0) {
@@ -78,8 +78,8 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 
 	ns_after = netstat_read();
 	after_aogood = netstat_get(ns_after, "TCPAOGood", NULL);
-	if (test_get_tcp_ao_counters(sk, &after_ao))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &after))
+		test_error("test_get_tcp_counters()");
 	if (!check_restore) {
 		/* to debug: netstat_print_diff(ns_before, ns_after); */
 		netstat_free(ns_before);
@@ -93,7 +93,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 		return;
 	}
 
-	if (test_assert_counters(tst, &before_ao, &after_ao, TEST_CNT_GOOD)) {
+	if (test_assert_counters(tst, &before, &after, TEST_CNT_GOOD)) {
 		close(sk);
 		return;
 	}
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index ea8a84edbd10f..ec2c93b6dc8e7 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -40,7 +40,7 @@ static void test_adjust_seqs(struct tcp_sock_state *img,
 static int test_sk_restore(struct tcp_sock_state *img,
 			   struct tcp_ao_repair *ao_img, sockaddr_af *saddr,
 			   const union tcp_addr daddr, unsigned int dport,
-			   struct tcp_ao_counters *cnt)
+			   struct tcp_counters *cnt)
 {
 	int sk;
 
@@ -54,8 +54,8 @@ static int test_sk_restore(struct tcp_sock_state *img,
 		test_error("setsockopt(TCP_AO_ADD_KEY)");
 	test_ao_restore(sk, ao_img);
 
-	if (test_get_tcp_ao_counters(sk, cnt))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, cnt))
+		test_error("test_get_tcp_counters()");
 
 	test_disable_repair(sk);
 	test_sock_state_free(img);
@@ -65,7 +65,7 @@ static int test_sk_restore(struct tcp_sock_state *img,
 static void *server_fn(void *arg)
 {
 	uint64_t before_good, after_good, after_bad;
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	struct tcp_sock_state img;
 	struct tcp_ao_repair ao_img;
 	sockaddr_af saddr;
@@ -114,7 +114,7 @@ static void *server_fn(void *arg)
 	test_adjust_seqs(&img, &ao_img, true);
 	synchronize_threads(); /* 4: dump finished */
 	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
-			     client_new_port, &ao1);
+			     client_new_port, &cnt1);
 
 	trace_ao_event_sne_expect(TCP_AO_SND_SNE_UPDATE, this_ip_addr,
 			this_ip_dest, test_server_port + 1, client_new_port, 1);
@@ -136,11 +136,11 @@ static void *server_fn(void *arg)
 	}
 
 	synchronize_threads(); /* 6: verify counters after SEQ-number rollover */
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
 
-	test_assert_counters(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
 		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
@@ -173,7 +173,7 @@ static void *server_fn(void *arg)
 static void *client_fn(void *arg)
 {
 	uint64_t before_good, after_good, after_bad;
-	struct tcp_ao_counters ao1, ao2;
+	struct tcp_counters cnt1, cnt2;
 	struct tcp_sock_state img;
 	struct tcp_ao_repair ao_img;
 	sockaddr_af saddr;
@@ -213,7 +213,7 @@ static void *client_fn(void *arg)
 	test_adjust_seqs(&img, &ao_img, false);
 	synchronize_threads(); /* 4: dump finished */
 	sk = test_sk_restore(&img, &ao_img, &saddr, this_ip_dest,
-			     test_server_port + 1, &ao1);
+			     test_server_port + 1, &cnt1);
 
 	synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
@@ -222,11 +222,11 @@ static void *client_fn(void *arg)
 		test_ok("post-migrate connection alive");
 
 	synchronize_threads(); /* 5: verify counters after SEQ-number rollover */
-	if (test_get_tcp_ao_counters(sk, &ao2))
-		test_error("test_get_tcp_ao_counters()");
+	if (test_get_tcp_counters(sk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	after_good = netstat_get_one("TCPAOGood", NULL);
 
-	test_assert_counters(NULL, &ao1, &ao2, TEST_CNT_GOOD);
+	test_assert_counters(NULL, &cnt1, &cnt2, TEST_CNT_GOOD);
 
 	if (after_good <= before_good) {
 		test_fail("TCPAOGood counter did not increase: %" PRIu64 " <= %" PRIu64,
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index f403ca25bbe6e..602dc04e3087b 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -41,7 +41,7 @@ static void try_accept(const char *tst_name, unsigned int port,
 		       const char *cnt_name, test_cnt cnt_expected,
 		       int needs_tcp_md5, fault_t inj)
 {
-	struct tcp_ao_counters ao_cnt1, ao_cnt2;
+	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
 	int lsk, err, sk = 0;
 	time_t timeout;
@@ -63,8 +63,8 @@ static void try_accept(const char *tst_name, unsigned int port,
 
 	if (cnt_name)
 		before_cnt = netstat_get_one(cnt_name, NULL);
-	if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt1))
-		test_error("test_get_tcp_ao_counters()");
+	if (ao_addr && test_get_tcp_counters(lsk, &cnt1))
+		test_error("test_get_tcp_counters()");
 
 	synchronize_threads(); /* preparations done */
 
@@ -89,8 +89,8 @@ static void try_accept(const char *tst_name, unsigned int port,
 		}
 	}
 
-	if (ao_addr && test_get_tcp_ao_counters(lsk, &ao_cnt2))
-		test_error("test_get_tcp_ao_counters()");
+	if (ao_addr && test_get_tcp_counters(lsk, &cnt2))
+		test_error("test_get_tcp_counters()");
 	close(lsk);
 
 	if (!cnt_name) {
@@ -108,7 +108,7 @@ static void try_accept(const char *tst_name, unsigned int port,
 			tst_name, cnt_name, before_cnt, after_cnt);
 	}
 	if (ao_addr)
-		test_assert_counters(tst_name, &ao_cnt1, &ao_cnt2, cnt_expected);
+		test_assert_counters(tst_name, &cnt1, &cnt2, cnt_expected);
 
 out:
 	synchronize_threads(); /* test_kill_sk() */
@@ -158,7 +158,7 @@ static void *server_fn(void *arg)
 		   TEST_CNT_GOOD, 0, 0);
 	try_accept("AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
 		   &addr_any, 0, 0, 100, 100, 0, "TCPMD5Unexpected",
-		   0, 1, FAULT_TIMEOUT);
+		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
 	try_accept("AO server (INADDR_ANY): no sign client", port++, NULL, 0,
 		   &addr_any, 0, 0, 100, 100, 0, "TCPAORequired",
 		   TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
@@ -204,10 +204,12 @@ static void *server_fn(void *arg)
 		   100, 100, 0, NULL, 0, 1, 0);
 	try_accept("AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
-		   100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
+		   100, 100, 0, "TCPMD5Unexpected",
+		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
 	try_accept("AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
-		   100, 100, 0, "TCPMD5Unexpected", 0, 1, FAULT_TIMEOUT);
+		   100, 100, 0, "TCPMD5Unexpected",
+		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
 	try_accept("AO+MD5 server: no sign client (unmatched)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "CurrEstab", 0, 1, 0);
@@ -217,7 +219,8 @@ static void *server_fn(void *arg)
 		   TEST_CNT_AO_REQUIRED, 1, FAULT_TIMEOUT);
 	try_accept("AO+MD5 server: no sign client (misconfig, matching MD5)",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
-		   100, 100, 0, "TCPMD5NotFound", 0, 1, FAULT_TIMEOUT);
+		   100, 100, 0, "TCPMD5NotFound",
+		   TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
 
 	try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,

From 28a4fa4298fd16cd7d46baf2f81fee431a30c46e Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:37 +0000
Subject: [PATCH 2635/2753] selftests/net: Add mixed select()+polling mode to
 TCP-AO tests

Currently, tcp_ao tests have two timeouts: TEST_RETRANSMIT_SEC and
TEST_TIMEOUT_SEC [by default 1 and 5 seconds]. The first one,
TEST_RETRANSMIT_SEC is used for operations that are expected to succeed
in order for a test to pass. It is usually not consumed and exists only
to avoid indefinite test run if the operation didn't complete.
The second one, TEST_RETRANSMIT_SEC exists for the tests that checking
operations, that are expected to fail/timeout. It is shorter as it is
fully consumed, with an expectation that if operation didn't succeed
during that period, it will timeout. And the related test that expects
the timeout is passing. The actual operation failure is then
cross-verified by other means like counters checks.

The issue with TEST_RETRANSMIT_SEC timeout is that 1 second is the exact
initial TCP timeout. So, in case the initial segment gets lost (quite
unlikely on local veth interface between two net namespaces, yet happens
in slow VMs), the retransmission never happens and as a result, the test
is not actually testing the functionality. Which in the end fails
counters checks.

As I want tcp_ao selftests to be fast and finishing in a reasonable
amount of time on manual run, I didn't consider increasing
TEST_RETRANSMIT_SEC.

Rather, initially, BPF_SOCK_OPS_TIMEOUT_INIT looked promising as a lever
to make the initial TCP timeout shorter. But as it's not a socket bpf
attached thing, but sock_ops (attaches to cgroups), the selftests would
have to use libbpf, which I wanted to avoid if not absolutely required.

Instead, use a mixed select() and counters polling mode with the longer
TEST_TIMEOUT_SEC timeout to detect running-away failed tests. It
actually not only allows losing segments and succeeding after
the previous TEST_RETRANSMIT_SEC timeout was consumed, but makes
the tests expecting timeout/failure pass faster.

The only test case taking longer (TEST_TIMEOUT_SEC) now is connect-deny
"wrong snd id", which checks for no key on SYN-ACK for which there is no
counter in the kernel (see tcp_make_synack()). Yet it can be speed up
by poking skpair from the trace event (see trace_tcp_ao_synack_no_key).

Fixes: ed9d09b309b1 ("selftests/net: Add a test for TCP-AO keys matching")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20241205070656.6ef344d7@kernel.org/
Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/tcp_ao/connect-deny.c       |  32 ++--
 .../testing/selftests/net/tcp_ao/lib/aolib.h  |  37 +++-
 tools/testing/selftests/net/tcp_ao/lib/sock.c | 162 ++++++++++++++++--
 tools/testing/selftests/net/tcp_ao/restore.c  |  17 +-
 .../selftests/net/tcp_ao/unsigned-md5.c       |  51 +++---
 5 files changed, 232 insertions(+), 67 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect-deny.c b/tools/testing/selftests/net/tcp_ao/connect-deny.c
index 919e8d2b91345..93b61e9a36f1f 100644
--- a/tools/testing/selftests/net/tcp_ao/connect-deny.c
+++ b/tools/testing/selftests/net/tcp_ao/connect-deny.c
@@ -4,6 +4,7 @@
 #include "aolib.h"
 
 #define fault(type)	(inj == FAULT_ ## type)
+static volatile int sk_pair;
 
 static inline int test_add_key_maclen(int sk, const char *key, uint8_t maclen,
 				      union tcp_addr in_addr, uint8_t prefix,
@@ -36,8 +37,8 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 {
 	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
+	test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
 	int lsk, err, sk = 0;
-	time_t timeout;
 
 	lsk = test_listen_socket(this_ip_addr, port, 1);
 
@@ -51,16 +52,19 @@ static void try_accept(const char *tst_name, unsigned int port, const char *pwd,
 
 	synchronize_threads(); /* preparations done */
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	err = test_wait_fd(lsk, timeout, 0);
+	err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair);
 	if (err == -ETIMEDOUT) {
+		sk_pair = err;
 		if (!fault(TIMEOUT))
-			test_fail("timed out for accept()");
+			test_fail("%s: timed out for accept()", tst_name);
+	} else if (err == -EKEYREJECTED) {
+		if (!fault(KEYREJECT))
+			test_fail("%s: key was rejected", tst_name);
 	} else if (err < 0) {
-		test_error("test_wait_fd()");
+		test_error("test_skpair_wait_poll()");
 	} else {
 		if (fault(TIMEOUT))
-			test_fail("ready to accept");
+			test_fail("%s: ready to accept", tst_name);
 
 		sk = accept(lsk, NULL, NULL);
 		if (sk < 0) {
@@ -109,7 +113,7 @@ static void *server_fn(void *arg)
 
 	try_accept("Non-AO server + AO client", port++, NULL,
 		   this_ip_dest, -1, 100, 100, 0,
-		   "TCPAOKeyNotFound", 0, FAULT_TIMEOUT);
+		   "TCPAOKeyNotFound", TEST_CNT_NS_KEY_NOT_FOUND, FAULT_TIMEOUT);
 
 	try_accept("AO server + Non-AO client", port++, DEFAULT_TEST_PASSWORD,
 		   this_ip_dest, -1, 100, 100, 0,
@@ -135,8 +139,9 @@ static void *server_fn(void *arg)
 		   wrong_addr, -1, 100, 100, 0,
 		   "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND, FAULT_TIMEOUT);
 
+	/* Key rejected by the other side, failing short through skpair */
 	try_accept("Client: Wrong addr", port++, NULL,
-		   this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_TIMEOUT);
+		   this_ip_dest, -1, 100, 100, 0, NULL, 0, FAULT_KEYREJECT);
 
 	try_accept("rcv id != snd id", port++, DEFAULT_TEST_PASSWORD,
 		   this_ip_dest, -1, 200, 100, 0,
@@ -164,7 +169,6 @@ static void try_connect(const char *tst_name, unsigned int port,
 			test_cnt cnt_expected, fault_t inj)
 {
 	struct tcp_counters cnt1, cnt2;
-	time_t timeout;
 	int sk, ret;
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
@@ -179,11 +183,10 @@ static void try_connect(const char *tst_name, unsigned int port,
 
 	synchronize_threads(); /* preparations done */
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
-
+	ret = test_skpair_connect_poll(sk, this_ip_dest, port, cnt_expected, &sk_pair);
 	synchronize_threads(); /* before counter checks */
 	if (ret < 0) {
+		sk_pair = ret;
 		if (fault(KEYREJECT) && ret == -EKEYREJECTED) {
 			test_ok("%s: connect() was prevented", tst_name);
 		} else if (ret == -ETIMEDOUT && fault(TIMEOUT)) {
@@ -243,6 +246,11 @@ static void *client_fn(void *arg)
 	try_connect("Wrong rcv id", port++, DEFAULT_TEST_PASSWORD,
 			this_ip_dest, -1, 100, 100, 0, FAULT_TIMEOUT);
 
+	/*
+	 * XXX: The test doesn't increase any counters, see tcp_make_synack().
+	 * Potentially, it can be speed up by setting sk_pair = -ETIMEDOUT
+	 * but the price would be increased complexity of the tracer thread.
+	 */
 	trace_ao_event_sk_expect(TCP_AO_SYNACK_NO_KEY, this_ip_dest, addr_any,
 				 port, 0, 100, 100);
 	try_connect("Wrong snd id", port++, DEFAULT_TEST_PASSWORD,
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index b88d15df76886..3c8c5ac2a878a 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -331,6 +331,7 @@ static inline int test_listen_socket(const union tcp_addr taddr,
  * If set to 0 - kernel will try to retransmit SYN number of times, set in
  * /proc/sys/net/ipv4/tcp_syn_retries
  * By default set to 1 to make tests pass faster on non-busy machine.
+ * [in process of removal, don't use in new tests]
  */
 #ifndef TEST_RETRANSMIT_SEC
 #define TEST_RETRANSMIT_SEC	1
@@ -483,8 +484,6 @@ static inline int test_set_ao_flags(int sk, bool ao_required, bool accept_icmps)
 }
 
 extern ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec);
-extern ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
-				const size_t msg_len, time_t timeout_sec);
 extern int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 			      time_t timeout_sec);
 
@@ -580,6 +579,40 @@ extern int test_assert_counters_key(const char *tst_name,
 		test_cnt expected, int sndid, int rcvid);
 extern void test_tcp_counters_free(struct tcp_counters *cnts);
 
+/*
+ * Polling for netns and socket counters during select()/connect() and also
+ * client/server messaging. Instead of constant timeout on underlying select(),
+ * check the counters and return early. This allows to pass the tests where
+ * timeout is expected without waiting for that fixing timeout (tests speed-up).
+ * Previously shorter timeouts were used for tests expecting to time out,
+ * but that leaded to sporadic false positives on counter checks failures,
+ * as one second timeouts aren't enough for TCP retransmit.
+ *
+ * Two sides of the socketpair (client/server) should synchronize failures
+ * using a shared variable *err, so that they can detect the other side's
+ * failure.
+ */
+extern int test_skpair_wait_poll(int sk, bool write, test_cnt cond,
+				 volatile int *err);
+extern int _test_skpair_connect_poll(int sk, const char *device,
+				     void *addr, size_t addr_sz,
+				     test_cnt cond, volatile int *err);
+static inline int test_skpair_connect_poll(int sk, const union tcp_addr taddr,
+					   unsigned int port,
+					   test_cnt cond, volatile int *err)
+{
+	sockaddr_af addr;
+
+	tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
+	return _test_skpair_connect_poll(sk, veth_name,
+					 (void *)&addr, sizeof(addr), cond, err);
+}
+
+extern int test_skpair_client(int sk, const size_t msg_len, const size_t nr,
+			      test_cnt cond, volatile int *err);
+extern int test_skpair_server(int sk, ssize_t quota,
+			      test_cnt cond, volatile int *err);
+
 /*
  * Frees buffers allocated in test_get_tcp_counters().
  * The function doesn't expect new keys or keys removed between calls
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 7ffde4dd79421..1befaf0aa98f9 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -34,10 +34,8 @@ int __test_listen_socket(int backlog, void *addr, size_t addr_sz)
 	return sk;
 }
 
-int test_wait_fd(int sk, time_t sec, bool write)
+static int __test_wait_fd(int sk, struct timeval *tv, bool write)
 {
-	struct timeval tv = { .tv_sec = sec };
-	struct timeval *ptv = NULL;
 	fd_set fds, efds;
 	int ret;
 	socklen_t slen = sizeof(ret);
@@ -47,14 +45,11 @@ int test_wait_fd(int sk, time_t sec, bool write)
 	FD_ZERO(&efds);
 	FD_SET(sk, &efds);
 
-	if (sec)
-		ptv = &tv;
-
 	errno = 0;
 	if (write)
-		ret = select(sk + 1, NULL, &fds, &efds, ptv);
+		ret = select(sk + 1, NULL, &fds, &efds, tv);
 	else
-		ret = select(sk + 1, &fds, NULL, &efds, ptv);
+		ret = select(sk + 1, &fds, NULL, &efds, tv);
 	if (ret < 0)
 		return -errno;
 	if (ret == 0) {
@@ -69,6 +64,52 @@ int test_wait_fd(int sk, time_t sec, bool write)
 	return 0;
 }
 
+int test_wait_fd(int sk, time_t sec, bool write)
+{
+	struct timeval tv = { .tv_sec = sec, };
+
+	return __test_wait_fd(sk, sec ? &tv : NULL, write);
+}
+
+static bool __skpair_poll_should_stop(int sk, struct tcp_counters *c,
+				      test_cnt condition)
+{
+	struct tcp_counters c2;
+	test_cnt diff;
+
+	if (test_get_tcp_counters(sk, &c2))
+		test_error("test_get_tcp_counters()");
+
+	diff = test_cmp_counters(c, &c2);
+	test_tcp_counters_free(&c2);
+	return (diff & condition) == condition;
+}
+
+/* How often wake up and check netns counters & paired (*err) */
+#define POLL_USEC	150
+static int __test_skpair_poll(int sk, bool write, uint64_t timeout,
+			      struct tcp_counters *c, test_cnt cond,
+			      volatile int *err)
+{
+	uint64_t t;
+
+	for (t = 0; t <= timeout * 1000000; t += POLL_USEC) {
+		struct timeval tv = { .tv_usec = POLL_USEC, };
+		int ret;
+
+		ret = __test_wait_fd(sk, &tv, write);
+		if (ret != -ETIMEDOUT)
+			return ret;
+		if (c && cond && __skpair_poll_should_stop(sk, c, cond))
+			break;
+		if (err && *err)
+			return *err;
+	}
+	if (err)
+		*err = -ETIMEDOUT;
+	return -ETIMEDOUT;
+}
+
 int __test_connect_socket(int sk, const char *device,
 			  void *addr, size_t addr_sz, time_t timeout)
 {
@@ -113,6 +154,43 @@ int __test_connect_socket(int sk, const char *device,
 	return err;
 }
 
+int test_skpair_wait_poll(int sk, bool write,
+			  test_cnt cond, volatile int *err)
+{
+	struct tcp_counters c;
+	int ret;
+
+	*err = 0;
+	if (test_get_tcp_counters(sk, &c))
+		test_error("test_get_tcp_counters()");
+	synchronize_threads(); /* 1: init skpair & read nscounters */
+
+	ret = __test_skpair_poll(sk, write, TEST_TIMEOUT_SEC, &c, cond, err);
+	test_tcp_counters_free(&c);
+	return ret;
+}
+
+int _test_skpair_connect_poll(int sk, const char *device,
+			      void *addr, size_t addr_sz,
+			      test_cnt condition, volatile int *err)
+{
+	struct tcp_counters c;
+	int ret;
+
+	*err = 0;
+	if (test_get_tcp_counters(sk, &c))
+		test_error("test_get_tcp_counters()");
+	synchronize_threads(); /* 1: init skpair & read nscounters */
+	ret = __test_connect_socket(sk, device, addr, addr_sz, -1);
+	if (ret < 0) {
+		test_tcp_counters_free(&c);
+		return (*err = ret);
+	}
+	ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, &c, condition, err);
+	test_tcp_counters_free(&c);
+	return ret;
+}
+
 int __test_set_md5(int sk, void *addr, size_t addr_sz, uint8_t prefix,
 		   int vrf, const char *password)
 {
@@ -515,7 +593,9 @@ void test_tcp_counters_free(struct tcp_counters *cnts)
 }
 
 #define TEST_BUF_SIZE 4096
-ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
+static ssize_t _test_server_run(int sk, ssize_t quota, struct tcp_counters *c,
+				test_cnt cond, volatile int *err,
+				time_t timeout_sec)
 {
 	ssize_t total = 0;
 
@@ -524,7 +604,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
 		ssize_t bytes, sent;
 		int ret;
 
-		ret = test_wait_fd(sk, timeout_sec, 0);
+		ret = __test_skpair_poll(sk, 0, timeout_sec, c, cond, err);
 		if (ret)
 			return ret;
 
@@ -535,7 +615,7 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
 		if (bytes == 0)
 			break;
 
-		ret = test_wait_fd(sk, timeout_sec, 1);
+		ret = __test_skpair_poll(sk, 1, timeout_sec, c, cond, err);
 		if (ret)
 			return ret;
 
@@ -550,13 +630,41 @@ ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
 	return total;
 }
 
-ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
-			 const size_t msg_len, time_t timeout_sec)
+ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec)
+{
+	return _test_server_run(sk, quota, NULL, 0, NULL,
+				timeout_sec ?: TEST_TIMEOUT_SEC);
+}
+
+int test_skpair_server(int sk, ssize_t quota, test_cnt cond, volatile int *err)
+{
+	struct tcp_counters c;
+	ssize_t ret;
+
+	*err = 0;
+	if (test_get_tcp_counters(sk, &c))
+		test_error("test_get_tcp_counters()");
+	synchronize_threads(); /* 1: init skpair & read nscounters */
+
+	ret = _test_server_run(sk, quota, &c, cond, err, TEST_TIMEOUT_SEC);
+	test_tcp_counters_free(&c);
+	return ret;
+}
+
+static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
+				struct tcp_counters *c, test_cnt cond,
+				volatile int *err, time_t timeout_sec)
 {
 	char msg[msg_len];
 	int nodelay = 1;
+	char *buf;
 	size_t i;
 
+	buf = alloca(buf_sz);
+	if (!buf)
+		return -ENOMEM;
+	randomize_buffer(buf, buf_sz);
+
 	if (setsockopt(sk, IPPROTO_TCP, TCP_NODELAY, &nodelay, sizeof(nodelay)))
 		test_error("setsockopt(TCP_NODELAY)");
 
@@ -564,7 +672,7 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
 		size_t sent, bytes = min(msg_len, buf_sz - i);
 		int ret;
 
-		ret = test_wait_fd(sk, timeout_sec, 1);
+		ret = __test_skpair_poll(sk, 1, timeout_sec, c, cond, err);
 		if (ret)
 			return ret;
 
@@ -578,7 +686,7 @@ ssize_t test_client_loop(int sk, char *buf, size_t buf_sz,
 		do {
 			ssize_t got;
 
-			ret = test_wait_fd(sk, timeout_sec, 0);
+			ret = __test_skpair_poll(sk, 0, timeout_sec, c, cond, err);
 			if (ret)
 				return ret;
 
@@ -601,11 +709,29 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 		       time_t timeout_sec)
 {
 	size_t buf_sz = msg_len * nr;
-	char *buf = alloca(buf_sz);
 	ssize_t ret;
 
-	randomize_buffer(buf, buf_sz);
-	ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
+	ret = test_client_loop(sk, buf_sz, msg_len, NULL, 0, NULL, timeout_sec);
+	if (ret < 0)
+		return (int)ret;
+	return ret != buf_sz ? -1 : 0;
+}
+
+int test_skpair_client(int sk, const size_t msg_len, const size_t nr,
+		       test_cnt cond, volatile int *err)
+{
+	struct tcp_counters c;
+	size_t buf_sz = msg_len * nr;
+	ssize_t ret;
+
+	*err = 0;
+	if (test_get_tcp_counters(sk, &c))
+		test_error("test_get_tcp_counters()");
+	synchronize_threads(); /* 1: init skpair & read nscounters */
+
+	ret = test_client_loop(sk, buf_sz, msg_len, &c, cond, err,
+			       TEST_TIMEOUT_SEC);
+	test_tcp_counters_free(&c);
 	if (ret < 0)
 		return (int)ret;
 	return ret != buf_sz ? -1 : 0;
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index 4b98f06725ef9..1c7264a5498a6 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -16,11 +16,11 @@ const size_t quota = nr_packets * msg_len;
 static void try_server_run(const char *tst_name, unsigned int port,
 			   fault_t inj, test_cnt cnt_expected)
 {
+	test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
 	const char *cnt_name = "TCPAOGood";
 	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt, after_cnt;
-	int sk, lsk;
-	time_t timeout;
+	int sk, lsk, dummy;
 	ssize_t bytes;
 
 	if (fault(TIMEOUT))
@@ -51,8 +51,7 @@ static void try_server_run(const char *tst_name, unsigned int port,
 	if (test_get_tcp_counters(sk, &cnt1))
 		test_error("test_get_tcp_counters()");
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	bytes = test_server_run(sk, quota, timeout);
+	bytes = test_skpair_server(sk, quota, poll_cnt, &dummy);
 	if (fault(TIMEOUT)) {
 		if (bytes > 0)
 			test_fail("%s: server served: %zd", tst_name, bytes);
@@ -139,11 +138,11 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 			    struct tcp_ao_repair *ao_img,
 			    fault_t inj, test_cnt cnt_expected)
 {
+	test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
 	const char *cnt_name = "TCPAOGood";
 	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt, after_cnt;
-	time_t timeout;
-	int sk;
+	int sk, dummy;
 
 	if (fault(TIMEOUT))
 		cnt_name = "TCPAOBad";
@@ -165,18 +164,18 @@ static void test_sk_restore(const char *tst_name, unsigned int server_port,
 	test_disable_repair(sk);
 	test_sock_state_free(img);
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	if (test_client_verify(sk, msg_len, nr_packets, timeout)) {
+	if (test_skpair_client(sk, msg_len, nr_packets, poll_cnt, &dummy)) {
 		if (fault(TIMEOUT))
 			test_ok("%s: post-migrate connection is broken", tst_name);
 		else
 			test_fail("%s: post-migrate connection is working", tst_name);
 	} else {
 		if (fault(TIMEOUT))
-			test_fail("%s: post-migrate connection still working", tst_name);
+			test_fail("%s: post-migrate connection is working", tst_name);
 		else
 			test_ok("%s: post-migrate connection is alive", tst_name);
 	}
+
 	synchronize_threads(); /* 3: counters checks */
 	if (test_get_tcp_counters(sk, &cnt2))
 		test_error("test_get_tcp_counters()");
diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index 602dc04e3087b..4cde2c9f7f49c 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -6,6 +6,7 @@
 #define fault(type)	(inj == FAULT_ ## type)
 static const char *md5_password = "Some evil genius, enemy to mankind, must have been the first contriver.";
 static const char *ao_password = DEFAULT_TEST_PASSWORD;
+static volatile int sk_pair;
 
 static union tcp_addr client2;
 static union tcp_addr client3;
@@ -43,8 +44,8 @@ static void try_accept(const char *tst_name, unsigned int port,
 {
 	struct tcp_counters cnt1, cnt2;
 	uint64_t before_cnt = 0, after_cnt = 0; /* silence GCC */
-	int lsk, err, sk = 0;
-	time_t timeout;
+	test_cnt poll_cnt = (cnt_expected == TEST_CNT_GOOD) ? 0 : cnt_expected;
+	int lsk, err, sk = -1;
 
 	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
 		return;
@@ -68,17 +69,20 @@ static void try_accept(const char *tst_name, unsigned int port,
 
 	synchronize_threads(); /* preparations done */
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	err = test_wait_fd(lsk, timeout, 0);
+	err = test_skpair_wait_poll(lsk, 0, poll_cnt, &sk_pair);
 	synchronize_threads(); /* connect()/accept() timeouts */
 	if (err == -ETIMEDOUT) {
+		sk_pair = err;
 		if (!fault(TIMEOUT))
-			test_fail("timed out for accept()");
+			test_fail("%s: timed out for accept()", tst_name);
+	} else if (err == -EKEYREJECTED) {
+		if (!fault(KEYREJECT))
+			test_fail("%s: key was rejected", tst_name);
 	} else if (err < 0) {
-		test_error("test_wait_fd()");
+		test_error("test_skpair_wait_poll()");
 	} else {
 		if (fault(TIMEOUT))
-			test_fail("ready to accept");
+			test_fail("%s: ready to accept", tst_name);
 
 		sk = accept(lsk, NULL, NULL);
 		if (sk < 0) {
@@ -112,7 +116,7 @@ static void try_accept(const char *tst_name, unsigned int port,
 
 out:
 	synchronize_threads(); /* test_kill_sk() */
-	if (sk > 0)
+	if (sk >= 0)
 		test_kill_sk(sk);
 }
 
@@ -172,19 +176,19 @@ static void *server_fn(void *arg)
 
 	try_accept("MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
-		   0, 1, FAULT_TIMEOUT);
+		   TEST_CNT_NS_KEY_NOT_FOUND, 1, FAULT_TIMEOUT);
 	try_accept("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
 		   NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0);
 	try_accept("MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
 		   0, NULL, 0, 0, 0, 0, 0, "TCPMD5NotFound",
-		   0, 1, FAULT_TIMEOUT);
+		   TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
 
 	try_accept("no sign server: AO client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
-		   TEST_CNT_AO_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
+		   TEST_CNT_NS_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
 	try_accept("no sign server: MD5 client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPMD5Unexpected",
-		   0, 1, FAULT_TIMEOUT);
+		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
 	try_accept("no sign server: no sign client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0);
 
@@ -222,12 +226,13 @@ static void *server_fn(void *arg)
 		   100, 100, 0, "TCPMD5NotFound",
 		   TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
 
+	/* Key rejected by the other side, failing short through skpair */
 	try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
-		   100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
+		   100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
 	try_accept("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
-		   100, 100, 0, NULL, 0, 1, FAULT_TIMEOUT);
+		   100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
 
 	server_add_fail_tests(&port);
 
@@ -262,7 +267,6 @@ static void try_connect(const char *tst_name, unsigned int port,
 		       uint8_t sndid, uint8_t rcvid, uint8_t vrf,
 		       fault_t inj, int needs_tcp_md5, union tcp_addr *bind_addr)
 {
-	time_t timeout;
 	int sk, ret;
 
 	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
@@ -284,11 +288,10 @@ static void try_connect(const char *tst_name, unsigned int port,
 
 	synchronize_threads(); /* preparations done */
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
-
+	ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair);
 	synchronize_threads(); /* connect()/accept() timeouts */
 	if (ret < 0) {
+		sk_pair = ret;
 		if (fault(KEYREJECT) && ret == -EKEYREJECTED)
 			test_ok("%s: connect() was prevented", tst_name);
 		else if (ret == -ETIMEDOUT && fault(TIMEOUT))
@@ -308,8 +311,7 @@ static void try_connect(const char *tst_name, unsigned int port,
 
 out:
 	synchronize_threads(); /* test_kill_sk() */
-	/* _test_connect_socket() cleans up on failure */
-	if (ret > 0)
+	if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */
 		test_kill_sk(sk);
 }
 
@@ -440,7 +442,6 @@ static void try_to_add(const char *tst_name, unsigned int port,
 		       int ao_vrf, uint8_t sndid, uint8_t rcvid,
 		       int needs_tcp_md5, fault_t inj)
 {
-	time_t timeout;
 	int sk, ret;
 
 	if (needs_tcp_md5 && should_skip_test(tst_name, KCONFIG_TCP_MD5))
@@ -453,11 +454,10 @@ static void try_to_add(const char *tst_name, unsigned int port,
 
 	synchronize_threads(); /* preparations done */
 
-	timeout = fault(TIMEOUT) ? TEST_RETRANSMIT_SEC : TEST_TIMEOUT_SEC;
-	ret = _test_connect_socket(sk, this_ip_dest, port, timeout);
+	ret = test_skpair_connect_poll(sk, this_ip_dest, port, 0, &sk_pair);
 
 	synchronize_threads(); /* connect()/accept() timeouts */
-	if (ret <= 0) {
+	if (ret < 0) {
 		test_error("%s: connect() returned %d", tst_name, ret);
 		goto out;
 	}
@@ -493,8 +493,7 @@ static void try_to_add(const char *tst_name, unsigned int port,
 
 out:
 	synchronize_threads(); /* test_kill_sk() */
-	/* _test_connect_socket() cleans up on failure */
-	if (ret > 0)
+	if (ret > 0) /* test_skpair_connect_poll() cleans up on failure */
 		test_kill_sk(sk);
 }
 

From 52031d4a14b57ae0f1f00a61a3f57eac25d8f48c Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:38 +0000
Subject: [PATCH 2636/2753] selftests/net: Print the testing side in
 unsigned-md5

As both client and server print the same test name on failure or pass,
add "[server]" so that it's more obvious from a log which side printed
"ok" or "not ok".

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/tcp_ao/unsigned-md5.c       | 44 +++++++++----------
 1 file changed, 22 insertions(+), 22 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
index 4cde2c9f7f49c..a1467b64390ad 100644
--- a/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
+++ b/tools/testing/selftests/net/tcp_ao/unsigned-md5.c
@@ -157,80 +157,80 @@ static void *server_fn(void *arg)
 
 	server_add_routes();
 
-	try_accept("AO server (INADDR_ANY): AO client", port++, NULL, 0,
+	try_accept("[server] AO server (INADDR_ANY): AO client", port++, NULL, 0,
 		   &addr_any, 0, 0, 100, 100, 0, "TCPAOGood",
 		   TEST_CNT_GOOD, 0, 0);
-	try_accept("AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
+	try_accept("[server] AO server (INADDR_ANY): MD5 client", port++, NULL, 0,
 		   &addr_any, 0, 0, 100, 100, 0, "TCPMD5Unexpected",
 		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
-	try_accept("AO server (INADDR_ANY): no sign client", port++, NULL, 0,
+	try_accept("[server] AO server (INADDR_ANY): no sign client", port++, NULL, 0,
 		   &addr_any, 0, 0, 100, 100, 0, "TCPAORequired",
 		   TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
-	try_accept("AO server (AO_REQUIRED): AO client", port++, NULL, 0,
+	try_accept("[server] AO server (AO_REQUIRED): AO client", port++, NULL, 0,
 		   &this_ip_dest, TEST_PREFIX, true,
 		   100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 0, 0);
-	try_accept("AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
+	try_accept("[server] AO server (AO_REQUIRED): unsigned client", port++, NULL, 0,
 		   &this_ip_dest, TEST_PREFIX, true,
 		   100, 100, 0, "TCPAORequired",
 		   TEST_CNT_AO_REQUIRED, 0, FAULT_TIMEOUT);
 
-	try_accept("MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
+	try_accept("[server] MD5 server (INADDR_ANY): AO client", port++, &addr_any, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
 		   TEST_CNT_NS_KEY_NOT_FOUND, 1, FAULT_TIMEOUT);
-	try_accept("MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
+	try_accept("[server] MD5 server (INADDR_ANY): MD5 client", port++, &addr_any, 0,
 		   NULL, 0, 0, 0, 0, 0, NULL, 0, 1, 0);
-	try_accept("MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
+	try_accept("[server] MD5 server (INADDR_ANY): no sign client", port++, &addr_any,
 		   0, NULL, 0, 0, 0, 0, 0, "TCPMD5NotFound",
 		   TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
 
-	try_accept("no sign server: AO client", port++, NULL, 0,
+	try_accept("[server] no sign server: AO client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPAOKeyNotFound",
 		   TEST_CNT_NS_KEY_NOT_FOUND, 0, FAULT_TIMEOUT);
-	try_accept("no sign server: MD5 client", port++, NULL, 0,
+	try_accept("[server] no sign server: MD5 client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "TCPMD5Unexpected",
 		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
-	try_accept("no sign server: no sign client", port++, NULL, 0,
+	try_accept("[server] no sign server: no sign client", port++, NULL, 0,
 		   NULL, 0, 0, 0, 0, 0, "CurrEstab", 0, 0, 0);
 
-	try_accept("AO+MD5 server: AO client (matching)", port++,
+	try_accept("[server] AO+MD5 server: AO client (matching)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPAOGood", TEST_CNT_GOOD, 1, 0);
-	try_accept("AO+MD5 server: AO client (misconfig, matching MD5)", port++,
+	try_accept("[server] AO+MD5 server: AO client (misconfig, matching MD5)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
 		   1, FAULT_TIMEOUT);
-	try_accept("AO+MD5 server: AO client (misconfig, non-matching)", port++,
+	try_accept("[server] AO+MD5 server: AO client (misconfig, non-matching)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPAOKeyNotFound", TEST_CNT_AO_KEY_NOT_FOUND,
 		   1, FAULT_TIMEOUT);
-	try_accept("AO+MD5 server: MD5 client (matching)", port++,
+	try_accept("[server] AO+MD5 server: MD5 client (matching)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, NULL, 0, 1, 0);
-	try_accept("AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
+	try_accept("[server] AO+MD5 server: MD5 client (misconfig, matching AO)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPMD5Unexpected",
 		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
-	try_accept("AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
+	try_accept("[server] AO+MD5 server: MD5 client (misconfig, non-matching)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPMD5Unexpected",
 		   TEST_CNT_NS_MD5_UNEXPECTED, 1, FAULT_TIMEOUT);
-	try_accept("AO+MD5 server: no sign client (unmatched)", port++,
+	try_accept("[server] AO+MD5 server: no sign client (unmatched)", port++,
 		   &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "CurrEstab", 0, 1, 0);
-	try_accept("AO+MD5 server: no sign client (misconfig, matching AO)",
+	try_accept("[server] AO+MD5 server: no sign client (misconfig, matching AO)",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPAORequired",
 		   TEST_CNT_AO_REQUIRED, 1, FAULT_TIMEOUT);
-	try_accept("AO+MD5 server: no sign client (misconfig, matching MD5)",
+	try_accept("[server] AO+MD5 server: no sign client (misconfig, matching MD5)",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, "TCPMD5NotFound",
 		   TEST_CNT_NS_MD5_NOT_FOUND, 1, FAULT_TIMEOUT);
 
 	/* Key rejected by the other side, failing short through skpair */
-	try_accept("AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
+	try_accept("[server] AO+MD5 server: client with both [TCP-MD5] and TCP-AO keys",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
-	try_accept("AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
+	try_accept("[server] AO+MD5 server: client with both TCP-MD5 and [TCP-AO] keys",
 		   port++, &this_ip_dest, TEST_PREFIX, &client2, TEST_PREFIX, 0,
 		   100, 100, 0, NULL, 0, 1, FAULT_KEYREJECT);
 

From d44e45722c6bc986e0306f86d49c54054aaa6a1e Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:39 +0000
Subject: [PATCH 2637/2753] selftests/net: Delete timeout from
 test_connect_socket()

Unused: it's always either the default timeout or asynchronous
connect().

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../testing/selftests/net/tcp_ao/lib/aolib.h  |  8 ++++----
 tools/testing/selftests/net/tcp_ao/lib/sock.c | 19 ++++++-------------
 tools/testing/selftests/net/tcp_ao/rst.c      |  5 ++---
 .../selftests/net/tcp_ao/self-connect.c       |  2 +-
 4 files changed, 13 insertions(+), 21 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index 3c8c5ac2a878a..e4d3d5016b619 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -289,7 +289,7 @@ extern int link_set_up(const char *intf);
 extern const unsigned int test_server_port;
 extern int test_wait_fd(int sk, time_t sec, bool write);
 extern int __test_connect_socket(int sk, const char *device,
-				 void *addr, size_t addr_sz, time_t timeout);
+				 void *addr, size_t addr_sz, bool async);
 extern int __test_listen_socket(int backlog, void *addr, size_t addr_sz);
 
 static inline int test_listen_socket(const union tcp_addr taddr,
@@ -338,19 +338,19 @@ static inline int test_listen_socket(const union tcp_addr taddr,
 #endif
 
 static inline int _test_connect_socket(int sk, const union tcp_addr taddr,
-				       unsigned int port, time_t timeout)
+				       unsigned int port, bool async)
 {
 	sockaddr_af addr;
 
 	tcp_addr_to_sockaddr_in(&addr, &taddr, htons(port));
 	return __test_connect_socket(sk, veth_name,
-				     (void *)&addr, sizeof(addr), timeout);
+				     (void *)&addr, sizeof(addr), async);
 }
 
 static inline int test_connect_socket(int sk, const union tcp_addr taddr,
 				      unsigned int port)
 {
-	return _test_connect_socket(sk, taddr, port, TEST_TIMEOUT_SEC);
+	return _test_connect_socket(sk, taddr, port, false);
 }
 
 extern int __test_set_md5(int sk, void *addr, size_t addr_sz,
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 1befaf0aa98f9..7863ebc36f3c6 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -111,7 +111,7 @@ static int __test_skpair_poll(int sk, bool write, uint64_t timeout,
 }
 
 int __test_connect_socket(int sk, const char *device,
-			  void *addr, size_t addr_sz, time_t timeout)
+			  void *addr, size_t addr_sz, bool async)
 {
 	long flags;
 	int err;
@@ -123,15 +123,6 @@ int __test_connect_socket(int sk, const char *device,
 			test_error("setsockopt(SO_BINDTODEVICE, %s)", device);
 	}
 
-	if (!timeout) {
-		err = connect(sk, addr, addr_sz);
-		if (err) {
-			err = -errno;
-			goto out;
-		}
-		return 0;
-	}
-
 	flags = fcntl(sk, F_GETFL);
 	if ((flags < 0) || (fcntl(sk, F_SETFL, flags | O_NONBLOCK) < 0))
 		test_error("fcntl()");
@@ -141,9 +132,9 @@ int __test_connect_socket(int sk, const char *device,
 			err = -errno;
 			goto out;
 		}
-		if (timeout < 0)
+		if (async)
 			return sk;
-		err = test_wait_fd(sk, timeout, 1);
+		err = test_wait_fd(sk, TEST_TIMEOUT_SEC, 1);
 		if (err)
 			goto out;
 	}
@@ -181,12 +172,14 @@ int _test_skpair_connect_poll(int sk, const char *device,
 	if (test_get_tcp_counters(sk, &c))
 		test_error("test_get_tcp_counters()");
 	synchronize_threads(); /* 1: init skpair & read nscounters */
-	ret = __test_connect_socket(sk, device, addr, addr_sz, -1);
+	ret = __test_connect_socket(sk, device, addr, addr_sz, true);
 	if (ret < 0) {
 		test_tcp_counters_free(&c);
 		return (*err = ret);
 	}
 	ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, &c, condition, err);
+	if (ret < 0)
+		close(sk);
 	test_tcp_counters_free(&c);
 	return ret;
 }
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index f752df511ba2e..e51be747e2b4f 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -271,8 +271,7 @@ static void test_client_active_rst(unsigned int port)
 
 	synchronize_threads(); /* 1: MKT added */
 	for (i = 0; i < last; i++) {
-		err = _test_connect_socket(sk[i], this_ip_dest, port,
-					       (i == 0) ? TEST_TIMEOUT_SEC : -1);
+		err = _test_connect_socket(sk[i], this_ip_dest, port, i != 0);
 		if (err < 0)
 			test_error("failed to connect()");
 	}
@@ -283,7 +282,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("test_wait_fds(): %d", err);
 
 	/* async connect() with third sk to get into request_sock_queue */
-	err = _test_connect_socket(sk[last], this_ip_dest, port, -1);
+	err = _test_connect_socket(sk[last], this_ip_dest, port, 1);
 	if (err < 0)
 		test_error("failed to connect()");
 
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 93732732c60c0..10927cfa23840 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -64,7 +64,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 		test_error("test_get_tcp_counters()");
 
 	if (__test_connect_socket(sk, "lo", (struct sockaddr *)&addr,
-				  sizeof(addr), TEST_TIMEOUT_SEC) < 0) {
+				  sizeof(addr), 0) < 0) {
 		ns_after = netstat_read();
 		netstat_print_diff(ns_before, ns_after);
 		test_error("failed to connect()");

From ceecb826bad71f34c7c6f70076b760685ef42882 Mon Sep 17 00:00:00 2001
From: Dmitry Safonov <0x7f454c46@gmail.com>
Date: Wed, 19 Mar 2025 03:13:40 +0000
Subject: [PATCH 2638/2753] selftests/net: Drop timeout argument from
 test_client_verify()

It's always TEST_TIMEOUT_SEC, with an unjustified exception in rst test,
that is more paranoia-long timeout rather than based on requirements.

Signed-off-by: Dmitry Safonov <0x7f454c46@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/tcp_ao/connect.c      |  2 +-
 .../testing/selftests/net/tcp_ao/icmps-discard.c  |  3 +--
 .../testing/selftests/net/tcp_ao/key-management.c |  8 ++++----
 tools/testing/selftests/net/tcp_ao/lib/aolib.h    |  3 +--
 tools/testing/selftests/net/tcp_ao/lib/sock.c     | 15 +++++++--------
 tools/testing/selftests/net/tcp_ao/restore.c      |  2 +-
 tools/testing/selftests/net/tcp_ao/rst.c          |  6 +++---
 tools/testing/selftests/net/tcp_ao/self-connect.c |  4 ++--
 tools/testing/selftests/net/tcp_ao/seq-ext.c      |  4 ++--
 9 files changed, 22 insertions(+), 25 deletions(-)

diff --git a/tools/testing/selftests/net/tcp_ao/connect.c b/tools/testing/selftests/net/tcp_ao/connect.c
index 45f2307483d3b..340f00e979eaf 100644
--- a/tools/testing/selftests/net/tcp_ao/connect.c
+++ b/tools/testing/selftests/net/tcp_ao/connect.c
@@ -53,7 +53,7 @@ static void *client_fn(void *arg)
 	if (test_get_tcp_counters(sk, &ao1))
 		test_error("test_get_tcp_counters()");
 
-	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+	if (test_client_verify(sk, 100, nr_packets)) {
 		test_fail("verify failed");
 		return NULL;
 	}
diff --git a/tools/testing/selftests/net/tcp_ao/icmps-discard.c b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
index 61a5e8e2d7e0d..85c1a1e958c68 100644
--- a/tools/testing/selftests/net/tcp_ao/icmps-discard.c
+++ b/tools/testing/selftests/net/tcp_ao/icmps-discard.c
@@ -395,7 +395,6 @@ static void icmp_interfere(const size_t nr, uint32_t rcv_nxt, void *src, void *d
 
 static void send_interfered(int sk)
 {
-	const unsigned int timeout = TEST_TIMEOUT_SEC;
 	struct sockaddr_in6 src, dst;
 	socklen_t addr_sz;
 
@@ -409,7 +408,7 @@ static void send_interfered(int sk)
 	while (1) {
 		uint32_t rcv_nxt;
 
-		if (test_client_verify(sk, packet_size, packets_nr, timeout)) {
+		if (test_client_verify(sk, packet_size, packets_nr)) {
 			test_fail("client: connection is broken");
 			return;
 		}
diff --git a/tools/testing/selftests/net/tcp_ao/key-management.c b/tools/testing/selftests/net/tcp_ao/key-management.c
index c4087a15bdb3b..69d9a7a05d5c1 100644
--- a/tools/testing/selftests/net/tcp_ao/key-management.c
+++ b/tools/testing/selftests/net/tcp_ao/key-management.c
@@ -918,7 +918,7 @@ static int run_client(const char *tst_name, unsigned int port,
 	collection.keys[rnext_index].used_on_server_tx = 1;
 
 	synchronize_threads(); /* 3: accepted => send data */
-	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
+	if (test_client_verify(sk, msg_sz, msg_nr)) {
 		test_fail("verify failed");
 		close(sk);
 		if (before)
@@ -1016,7 +1016,7 @@ static void try_unmatched_keys(int sk, int *rnext_index, unsigned int port)
 	trace_ao_event_expect(TCP_AO_RNEXT_REQUEST, this_ip_addr, this_ip_dest,
 			      -1, port, 0, -1, -1, -1, -1, -1,
 			      -1, key->server_keyid, -1);
-	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, msg_len, nr_packets))
 		test_fail("verify failed");
 	*rnext_index = i;
 }
@@ -1061,7 +1061,7 @@ static void check_current_back(const char *tst_name, unsigned int port,
 			      port, -1, 0, -1, -1, -1, -1, -1,
 			      collection.keys[rotate_to_index].client_keyid,
 			      collection.keys[current_index].client_keyid, -1);
-	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, msg_len, nr_packets))
 		test_fail("verify failed");
 	/* There is a race here: between setting the current_key with
 	 * setsockopt(TCP_AO_INFO) and starting to send some data - there
@@ -1099,7 +1099,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 				collection.keys[i].server_keyid, -1);
 		if (test_set_key(sk, -1, collection.keys[i].server_keyid))
 			test_error("Can't change the Rnext key");
-		if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+		if (test_client_verify(sk, msg_len, nr_packets)) {
 			test_fail("verify failed");
 			close(sk);
 			test_tcp_counters_free(&tmp);
diff --git a/tools/testing/selftests/net/tcp_ao/lib/aolib.h b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
index e4d3d5016b619..ebb2899c12fe0 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/aolib.h
+++ b/tools/testing/selftests/net/tcp_ao/lib/aolib.h
@@ -484,8 +484,7 @@ static inline int test_set_ao_flags(int sk, bool ao_required, bool accept_icmps)
 }
 
 extern ssize_t test_server_run(int sk, ssize_t quota, time_t timeout_sec);
-extern int test_client_verify(int sk, const size_t msg_len, const size_t nr,
-			      time_t timeout_sec);
+extern int test_client_verify(int sk, const size_t msg_len, const size_t nr);
 
 struct tcp_ao_key_counters {
 	uint8_t sndid;
diff --git a/tools/testing/selftests/net/tcp_ao/lib/sock.c b/tools/testing/selftests/net/tcp_ao/lib/sock.c
index 7863ebc36f3c6..ef8e9031d47a3 100644
--- a/tools/testing/selftests/net/tcp_ao/lib/sock.c
+++ b/tools/testing/selftests/net/tcp_ao/lib/sock.c
@@ -646,7 +646,7 @@ int test_skpair_server(int sk, ssize_t quota, test_cnt cond, volatile int *err)
 
 static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
 				struct tcp_counters *c, test_cnt cond,
-				volatile int *err, time_t timeout_sec)
+				volatile int *err)
 {
 	char msg[msg_len];
 	int nodelay = 1;
@@ -665,7 +665,7 @@ static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
 		size_t sent, bytes = min(msg_len, buf_sz - i);
 		int ret;
 
-		ret = __test_skpair_poll(sk, 1, timeout_sec, c, cond, err);
+		ret = __test_skpair_poll(sk, 1, TEST_TIMEOUT_SEC, c, cond, err);
 		if (ret)
 			return ret;
 
@@ -679,7 +679,8 @@ static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
 		do {
 			ssize_t got;
 
-			ret = __test_skpair_poll(sk, 0, timeout_sec, c, cond, err);
+			ret = __test_skpair_poll(sk, 0, TEST_TIMEOUT_SEC,
+						 c, cond, err);
 			if (ret)
 				return ret;
 
@@ -698,13 +699,12 @@ static ssize_t test_client_loop(int sk, size_t buf_sz, const size_t msg_len,
 	return i;
 }
 
-int test_client_verify(int sk, const size_t msg_len, const size_t nr,
-		       time_t timeout_sec)
+int test_client_verify(int sk, const size_t msg_len, const size_t nr)
 {
 	size_t buf_sz = msg_len * nr;
 	ssize_t ret;
 
-	ret = test_client_loop(sk, buf_sz, msg_len, NULL, 0, NULL, timeout_sec);
+	ret = test_client_loop(sk, buf_sz, msg_len, NULL, 0, NULL);
 	if (ret < 0)
 		return (int)ret;
 	return ret != buf_sz ? -1 : 0;
@@ -722,8 +722,7 @@ int test_skpair_client(int sk, const size_t msg_len, const size_t nr,
 		test_error("test_get_tcp_counters()");
 	synchronize_threads(); /* 1: init skpair & read nscounters */
 
-	ret = test_client_loop(sk, buf_sz, msg_len, &c, cond, err,
-			       TEST_TIMEOUT_SEC);
+	ret = test_client_loop(sk, buf_sz, msg_len, &c, cond, err);
 	test_tcp_counters_free(&c);
 	if (ret < 0)
 		return (int)ret;
diff --git a/tools/testing/selftests/net/tcp_ao/restore.c b/tools/testing/selftests/net/tcp_ao/restore.c
index 1c7264a5498a6..9a059b6c45231 100644
--- a/tools/testing/selftests/net/tcp_ao/restore.c
+++ b/tools/testing/selftests/net/tcp_ao/restore.c
@@ -124,7 +124,7 @@ static void test_get_sk_checkpoint(unsigned int server_port, sockaddr_af *saddr,
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, msg_len, nr_packets))
 		test_fail("pre-migrate verify failed");
 
 	test_enable_repair(sk);
diff --git a/tools/testing/selftests/net/tcp_ao/rst.c b/tools/testing/selftests/net/tcp_ao/rst.c
index e51be747e2b4f..883cddf377cff 100644
--- a/tools/testing/selftests/net/tcp_ao/rst.c
+++ b/tools/testing/selftests/net/tcp_ao/rst.c
@@ -287,7 +287,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 3: close listen socket */
-	if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk[0], packet_sz, quota / packet_sz))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -340,7 +340,7 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, packet_sz, quota / packet_sz))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -416,7 +416,7 @@ static void test_client_passive_rst(unsigned int port)
 	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
 	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
 	 */
-	err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+	err = test_client_verify(sk, packet_sz, quota / packet_sz);
 	/* Make sure that the connection was reset, not timeouted */
 	if (err && err == -ECONNRESET)
 		test_ok("client sock was passively reset post-seq-adjust");
diff --git a/tools/testing/selftests/net/tcp_ao/self-connect.c b/tools/testing/selftests/net/tcp_ao/self-connect.c
index 10927cfa23840..73b2f2276f3f5 100644
--- a/tools/testing/selftests/net/tcp_ao/self-connect.c
+++ b/tools/testing/selftests/net/tcp_ao/self-connect.c
@@ -70,7 +70,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 		test_error("failed to connect()");
 	}
 
-	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+	if (test_client_verify(sk, 100, nr_packets)) {
 		test_fail("%s: tcp connection verify failed", tst);
 		close(sk);
 		return;
@@ -136,7 +136,7 @@ static void tcp_self_connect(const char *tst, unsigned int port,
 	test_ao_restore(sk, &ao_img);
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
-	if (test_client_verify(sk, 100, nr_packets, TEST_TIMEOUT_SEC)) {
+	if (test_client_verify(sk, 100, nr_packets)) {
 		test_fail("%s: tcp connection verify failed", tst);
 		close(sk);
 		return;
diff --git a/tools/testing/selftests/net/tcp_ao/seq-ext.c b/tools/testing/selftests/net/tcp_ao/seq-ext.c
index ec2c93b6dc8e7..f00245263b20d 100644
--- a/tools/testing/selftests/net/tcp_ao/seq-ext.c
+++ b/tools/testing/selftests/net/tcp_ao/seq-ext.c
@@ -191,7 +191,7 @@ static void *client_fn(void *arg)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC)) {
+	if (test_client_verify(sk, msg_len, nr_packets)) {
 		test_fail("pre-migrate verify failed");
 		return NULL;
 	}
@@ -216,7 +216,7 @@ static void *client_fn(void *arg)
 			     test_server_port + 1, &cnt1);
 
 	synchronize_threads(); /* 5: verify the connection during SEQ-number rollover */
-	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, msg_len, nr_packets))
 		test_fail("post-migrate verify failed");
 	else
 		test_ok("post-migrate connection alive");

From 9c4a73a34aea1eefa8f48badf85e71774cfeb222 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Wed, 19 Mar 2025 08:09:47 +0000
Subject: [PATCH 2639/2753] bonding: use permanent address for MAC swapping if
 device address is same
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Similar with a951bc1e6ba5 ("bonding: correct the MAC address for "follow"
fail_over_mac policy"). The fail_over_mac follow mode requires the formerly
active slave to swap MAC addresses with the newly active slave during
failover. However, the slave's MAC address can be same under certain
conditions:

1) ip link set eth0 master bond0
   bond0 adopts eth0's MAC address (MAC0).

1) ip link set eth1 master bond0
   eth1 is added as a backup with its own MAC (MAC1).

3) ip link set eth0 nomaster
   eth0 is released and restores its MAC (MAC0).
   eth1 becomes the active slave, and bond0 assigns MAC0 to eth1.

4) ip link set eth0 master bond0
   eth0 is re-added to bond0, but both eth0 and eth1 now have MAC0,
   breaking the follow policy.

To resolve this issue, we need to swap the new active slave’s permanent
MAC address with the old one. The new active slave then uses the old
dev_addr, ensuring that it matches the bond address. After the fix:

5) ip link set bond0 type bond active_slave eth0
   dev_addr is the same, swap old active eth1's MAC (MAC0) with eth0.
   Swap new active eth0's permanent MAC (MAC0) to eth1.
   MAC addresses remain unchanged.

6) ip link set bond0 type bond active_slave eth1
   dev_addr is the same, swap the old active eth0's MAC (MAC0) with eth1.
   Swap new active eth1's permanent MAC (MAC1) to eth0.
   The MAC addresses are now correctly differentiated.

Fixes: 3915c1e8634a ("bonding: Add "follow" option to fail_over_mac")
Reported-by: Liang Li <liali@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/bonding/bond_main.c | 9 +++++++--
 include/net/bonding.h           | 8 ++++++++
 2 files changed, 15 insertions(+), 2 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 6c95f478ab805..b21456e759fdc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1104,8 +1104,13 @@ static void bond_do_fail_over_mac(struct bonding *bond,
 			old_active = bond_get_old_active(bond, new_active);
 
 		if (old_active) {
-			bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
-					  new_active->dev->addr_len);
+			if (bond_hw_addr_equal(old_active->dev->dev_addr, new_active->dev->dev_addr,
+					       new_active->dev->addr_len))
+				bond_hw_addr_copy(tmp_mac, new_active->perm_hwaddr,
+						  new_active->dev->addr_len);
+			else
+				bond_hw_addr_copy(tmp_mac, new_active->dev->dev_addr,
+						  new_active->dev->addr_len);
 			bond_hw_addr_copy(ss.__data,
 					  old_active->dev->dev_addr,
 					  old_active->dev->addr_len);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 8bb5f016969f1..de965c24dde0b 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -463,6 +463,14 @@ static inline void bond_hw_addr_copy(u8 *dst, const u8 *src, unsigned int len)
 	memcpy(dst, src, len);
 }
 
+static inline bool bond_hw_addr_equal(const u8 *dst, const u8 *src, unsigned int len)
+{
+	if (len == ETH_ALEN)
+		return ether_addr_equal(dst, src);
+	else
+		return (memcmp(dst, src, len) == 0);
+}
+
 #define BOND_PRI_RESELECT_ALWAYS	0
 #define BOND_PRI_RESELECT_BETTER	1
 #define BOND_PRI_RESELECT_FAILURE	2

From 202cfb3551ff5abd134bffdd331eeba9ac3103ea Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:47 +0100
Subject: [PATCH 2640/2753] net: usb: lan78xx: Improve error handling in PHY
 initialization

Ensure that return values from `lan78xx_write_reg()`,
`lan78xx_read_reg()`, and `phy_find_first()` are properly checked and
propagated. Use `ERR_PTR(ret)` for error reporting in
`lan7801_phy_init()` and replace `-EIO` with `-ENODEV` where appropriate
to provide more accurate error codes.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/lan78xx.c | 47 ++++++++++++++++++++++++++-------------
 1 file changed, 31 insertions(+), 16 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 137adf6d5b08a..13b5da18850ac 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -2510,14 +2510,13 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev)
 
 static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 {
-	u32 buf;
-	int ret;
 	struct fixed_phy_status fphy_status = {
 		.link = 1,
 		.speed = SPEED_1000,
 		.duplex = DUPLEX_FULL,
 	};
 	struct phy_device *phydev;
+	int ret;
 
 	phydev = phy_find_first(dev->mdiobus);
 	if (!phydev) {
@@ -2525,30 +2524,40 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
 		if (IS_ERR(phydev)) {
 			netdev_err(dev->net, "No PHY/fixed_PHY found\n");
-			return NULL;
+			return ERR_PTR(-ENODEV);
 		}
 		netdev_dbg(dev->net, "Registered FIXED PHY\n");
 		dev->interface = PHY_INTERFACE_MODE_RGMII;
 		ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
 					MAC_RGMII_ID_TXC_DELAY_EN_);
+		if (ret < 0)
+			return ERR_PTR(ret);
+
 		ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00);
-		ret = lan78xx_read_reg(dev, HW_CFG, &buf);
-		buf |= HW_CFG_CLK125_EN_;
-		buf |= HW_CFG_REFCLK25_EN_;
-		ret = lan78xx_write_reg(dev, HW_CFG, buf);
+		if (ret < 0)
+			return ERR_PTR(ret);
+
+		ret = lan78xx_update_reg(dev, HW_CFG, HW_CFG_CLK125_EN_ |
+					 HW_CFG_REFCLK25_EN_,
+					 HW_CFG_CLK125_EN_ | HW_CFG_REFCLK25_EN_);
+		if (ret < 0)
+			return ERR_PTR(ret);
 	} else {
 		if (!phydev->drv) {
 			netdev_err(dev->net, "no PHY driver found\n");
-			return NULL;
+			return ERR_PTR(-EINVAL);
 		}
 		dev->interface = PHY_INTERFACE_MODE_RGMII_ID;
 		/* The PHY driver is responsible to configure proper RGMII
 		 * interface delays. Disable RGMII delays on MAC side.
 		 */
-		lan78xx_write_reg(dev, MAC_RGMII_ID, 0);
+		ret = lan78xx_write_reg(dev, MAC_RGMII_ID, 0);
+		if (ret < 0)
+			return ERR_PTR(ret);
 
 		phydev->is_internal = false;
 	}
+
 	return phydev;
 }
 
@@ -2562,9 +2571,10 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 	switch (dev->chipid) {
 	case ID_REV_CHIP_ID_7801_:
 		phydev = lan7801_phy_init(dev);
-		if (!phydev) {
-			netdev_err(dev->net, "lan7801: PHY Init Failed");
-			return -EIO;
+		if (IS_ERR(phydev)) {
+			netdev_err(dev->net, "lan7801: failed to init PHY: %pe\n",
+				   phydev);
+			return PTR_ERR(phydev);
 		}
 		break;
 
@@ -2573,7 +2583,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 		phydev = phy_find_first(dev->mdiobus);
 		if (!phydev) {
 			netdev_err(dev->net, "no PHY found\n");
-			return -EIO;
+			return -ENODEV;
 		}
 		phydev->is_internal = true;
 		dev->interface = PHY_INTERFACE_MODE_GMII;
@@ -2581,7 +2591,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 
 	default:
 		netdev_err(dev->net, "Unknown CHIP ID found\n");
-		return -EIO;
+		return -ENODEV;
 	}
 
 	/* if phyirq is not set, use polling mode in phylib */
@@ -2633,7 +2643,10 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 						      sizeof(u32));
 		if (len >= 0) {
 			/* Ensure the appropriate LEDs are enabled */
-			lan78xx_read_reg(dev, HW_CFG, &reg);
+			ret = lan78xx_read_reg(dev, HW_CFG, &reg);
+			if (ret < 0)
+				return ret;
+
 			reg &= ~(HW_CFG_LED0_EN_ |
 				 HW_CFG_LED1_EN_ |
 				 HW_CFG_LED2_EN_ |
@@ -2642,7 +2655,9 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 				(len > 1) * HW_CFG_LED1_EN_ |
 				(len > 2) * HW_CFG_LED2_EN_ |
 				(len > 3) * HW_CFG_LED3_EN_;
-			lan78xx_write_reg(dev, HW_CFG, reg);
+			ret = lan78xx_write_reg(dev, HW_CFG, reg);
+			if (ret < 0)
+				return ret;
 		}
 	}
 

From 4b9a12fd5612fbefb790c178159901243fd57dca Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:48 +0100
Subject: [PATCH 2641/2753] net: usb: lan78xx: Convert to PHYlink for improved
 PHY and MAC management

Convert the LAN78xx driver to use the PHYlink framework for managing
PHY and MAC interactions.

Key changes include:
- Replace direct PHY operations with phylink equivalents (e.g.,
  phylink_start, phylink_stop).
- Introduce lan78xx_phylink_setup for phylink initialization and
  configuration.
- Add phylink MAC operations (lan78xx_mac_config,
  lan78xx_mac_link_down, lan78xx_mac_link_up) for managing link
  settings and flow control.
- Remove redundant and now phylink-managed functions like
  `lan78xx_link_status_change`.
- update lan78xx_get/set_pause to use phylink helpers

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/Kconfig   |   3 +-
 drivers/net/usb/lan78xx.c | 615 ++++++++++++++++++--------------------
 2 files changed, 298 insertions(+), 320 deletions(-)

diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig
index 3c360d4f06352..71168e47a9b1c 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -115,9 +115,8 @@ config USB_RTL8152
 config USB_LAN78XX
 	tristate "Microchip LAN78XX Based USB Ethernet Adapters"
 	select MII
-	select PHYLIB
+	select PHYLINK
 	select MICROCHIP_PHY
-	select FIXED_PHY
 	select CRC32
 	help
 	  This option adds support for Microchip LAN78XX based USB 2
diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 13b5da18850ac..fd6e80f9c35f7 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -6,6 +6,7 @@
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
 #include <linux/ethtool.h>
+#include <linux/phylink.h>
 #include <linux/usb.h>
 #include <linux/crc32.h>
 #include <linux/signal.h>
@@ -384,7 +385,7 @@ struct skb_data {		/* skb->cb is one of these */
 #define EVENT_RX_HALT			1
 #define EVENT_RX_MEMORY			2
 #define EVENT_STS_SPLIT			3
-#define EVENT_LINK_RESET		4
+#define EVENT_PHY_INT_ACK		4
 #define EVENT_RX_PAUSED			5
 #define EVENT_DEV_WAKING		6
 #define EVENT_DEV_ASLEEP		7
@@ -470,6 +471,9 @@ struct lan78xx_net {
 	struct statstage	stats;
 
 	struct irq_domain_data	domain_data;
+
+	struct phylink		*phylink;
+	struct phylink_config	phylink_config;
 };
 
 /* use ethtool to change the level for any given device */
@@ -1554,40 +1558,6 @@ static void lan78xx_set_multicast(struct net_device *netdev)
 	schedule_work(&pdata->set_multicast);
 }
 
-static int lan78xx_update_flowcontrol(struct lan78xx_net *dev, u8 duplex,
-				      u16 lcladv, u16 rmtadv)
-{
-	u32 flow = 0, fct_flow = 0;
-	u8 cap;
-
-	if (dev->fc_autoneg)
-		cap = mii_resolve_flowctrl_fdx(lcladv, rmtadv);
-	else
-		cap = dev->fc_request_control;
-
-	if (cap & FLOW_CTRL_TX)
-		flow |= (FLOW_CR_TX_FCEN_ | 0xFFFF);
-
-	if (cap & FLOW_CTRL_RX)
-		flow |= FLOW_CR_RX_FCEN_;
-
-	if (dev->udev->speed == USB_SPEED_SUPER)
-		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS);
-	else if (dev->udev->speed == USB_SPEED_HIGH)
-		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS);
-
-	netif_dbg(dev, link, dev->net, "rx pause %s, tx pause %s",
-		  (cap & FLOW_CTRL_RX ? "enabled" : "disabled"),
-		  (cap & FLOW_CTRL_TX ? "enabled" : "disabled"));
-
-	lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
-
-	/* threshold value should be set before enabling flow */
-	lan78xx_write_reg(dev, FLOW, flow);
-
-	return 0;
-}
-
 static void lan78xx_rx_urb_submit_all(struct lan78xx_net *dev);
 
 static int lan78xx_mac_reset(struct lan78xx_net *dev)
@@ -1636,99 +1606,10 @@ static int lan78xx_mac_reset(struct lan78xx_net *dev)
 	return ret;
 }
 
-static int lan78xx_link_reset(struct lan78xx_net *dev)
+static int lan78xx_phy_int_ack(struct lan78xx_net *dev)
 {
-	struct phy_device *phydev = dev->net->phydev;
-	struct ethtool_link_ksettings ecmd;
-	int ladv, radv, ret, link;
-	u32 buf;
-
 	/* clear LAN78xx interrupt status */
-	ret = lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
-	if (unlikely(ret < 0))
-		return ret;
-
-	mutex_lock(&phydev->lock);
-	phy_read_status(phydev);
-	link = phydev->link;
-	mutex_unlock(&phydev->lock);
-
-	if (!link && dev->link_on) {
-		dev->link_on = false;
-
-		/* reset MAC */
-		ret = lan78xx_mac_reset(dev);
-		if (ret < 0)
-			return ret;
-
-		del_timer(&dev->stat_monitor);
-	} else if (link && !dev->link_on) {
-		dev->link_on = true;
-
-		phy_ethtool_ksettings_get(phydev, &ecmd);
-
-		if (dev->udev->speed == USB_SPEED_SUPER) {
-			if (ecmd.base.speed == 1000) {
-				/* disable U2 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf &= ~USB_CFG1_DEV_U2_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-				/* enable U1 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf |= USB_CFG1_DEV_U1_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-			} else {
-				/* enable U1 & U2 */
-				ret = lan78xx_read_reg(dev, USB_CFG1, &buf);
-				if (ret < 0)
-					return ret;
-				buf |= USB_CFG1_DEV_U2_INIT_EN_;
-				buf |= USB_CFG1_DEV_U1_INIT_EN_;
-				ret = lan78xx_write_reg(dev, USB_CFG1, buf);
-				if (ret < 0)
-					return ret;
-			}
-		}
-
-		ladv = phy_read(phydev, MII_ADVERTISE);
-		if (ladv < 0)
-			return ladv;
-
-		radv = phy_read(phydev, MII_LPA);
-		if (radv < 0)
-			return radv;
-
-		netif_dbg(dev, link, dev->net,
-			  "speed: %u duplex: %d anadv: 0x%04x anlpa: 0x%04x",
-			  ecmd.base.speed, ecmd.base.duplex, ladv, radv);
-
-		ret = lan78xx_update_flowcontrol(dev, ecmd.base.duplex, ladv,
-						 radv);
-		if (ret < 0)
-			return ret;
-
-		if (!timer_pending(&dev->stat_monitor)) {
-			dev->delta = 1;
-			mod_timer(&dev->stat_monitor,
-				  jiffies + STAT_UPDATE_TIMER);
-		}
-
-		lan78xx_rx_urb_submit_all(dev);
-
-		local_bh_disable();
-		napi_schedule(&dev->napi);
-		local_bh_enable();
-	}
-
-	return 0;
+	return lan78xx_write_reg(dev, INT_STS, INT_STS_PHY_INT_);
 }
 
 /* some work can't be done in tasklets, so we use keventd
@@ -1757,7 +1638,7 @@ static void lan78xx_status(struct lan78xx_net *dev, struct urb *urb)
 
 	if (intdata & INT_ENP_PHY_INT) {
 		netif_dbg(dev, link, dev->net, "PHY INTR: 0x%08x\n", intdata);
-		lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
+		lan78xx_defer_kevent(dev, EVENT_PHY_INT_ACK);
 
 		if (dev->domain_data.phyirq > 0)
 			generic_handle_irq_safe(dev->domain_data.phyirq);
@@ -2039,63 +1920,16 @@ static void lan78xx_get_pause(struct net_device *net,
 			      struct ethtool_pauseparam *pause)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	struct ethtool_link_ksettings ecmd;
-
-	phy_ethtool_ksettings_get(phydev, &ecmd);
-
-	pause->autoneg = dev->fc_autoneg;
 
-	if (dev->fc_request_control & FLOW_CTRL_TX)
-		pause->tx_pause = 1;
-
-	if (dev->fc_request_control & FLOW_CTRL_RX)
-		pause->rx_pause = 1;
+	phylink_ethtool_get_pauseparam(dev->phylink, pause);
 }
 
 static int lan78xx_set_pause(struct net_device *net,
 			     struct ethtool_pauseparam *pause)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	struct ethtool_link_ksettings ecmd;
-	int ret;
-
-	phy_ethtool_ksettings_get(phydev, &ecmd);
-
-	if (pause->autoneg && !ecmd.base.autoneg) {
-		ret = -EINVAL;
-		goto exit;
-	}
-
-	dev->fc_request_control = 0;
-	if (pause->rx_pause)
-		dev->fc_request_control |= FLOW_CTRL_RX;
 
-	if (pause->tx_pause)
-		dev->fc_request_control |= FLOW_CTRL_TX;
-
-	if (ecmd.base.autoneg) {
-		__ETHTOOL_DECLARE_LINK_MODE_MASK(fc) = { 0, };
-		u32 mii_adv;
-
-		linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-				   ecmd.link_modes.advertising);
-		linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-				   ecmd.link_modes.advertising);
-		mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control);
-		mii_adv_to_linkmode_adv_t(fc, mii_adv);
-		linkmode_or(ecmd.link_modes.advertising, fc,
-			    ecmd.link_modes.advertising);
-
-		phy_ethtool_ksettings_set(phydev, &ecmd);
-	}
-
-	dev->fc_autoneg = pause->autoneg;
-
-	ret = 0;
-exit:
-	return ret;
+	return phylink_ethtool_set_pauseparam(dev->phylink, pause);
 }
 
 static int lan78xx_get_regs_len(struct net_device *netdev)
@@ -2356,26 +2190,6 @@ static void lan78xx_remove_mdio(struct lan78xx_net *dev)
 	mdiobus_free(dev->mdiobus);
 }
 
-static void lan78xx_link_status_change(struct net_device *net)
-{
-	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	u32 data;
-	int ret;
-
-	ret = lan78xx_read_reg(dev, MAC_CR, &data);
-	if (ret < 0)
-		return;
-
-	if (phydev->enable_tx_lpi)
-		data |=  MAC_CR_EEE_EN_;
-	else
-		data &= ~MAC_CR_EEE_EN_;
-	lan78xx_write_reg(dev, MAC_CR, data);
-
-	phy_print_status(phydev);
-}
-
 static int irq_map(struct irq_domain *d, unsigned int irq,
 		   irq_hw_number_t hwirq)
 {
@@ -2508,26 +2322,210 @@ static void lan78xx_remove_irq_domain(struct lan78xx_net *dev)
 	dev->domain_data.irqdomain = NULL;
 }
 
+static void lan78xx_mac_config(struct phylink_config *config, unsigned int mode,
+			       const struct phylink_link_state *state)
+{
+	struct net_device *net = to_net_dev(config->dev);
+	struct lan78xx_net *dev = netdev_priv(net);
+	u32 mac_cr = 0;
+	int ret;
+
+	/* Check if the mode is supported */
+	if (mode != MLO_AN_FIXED && mode != MLO_AN_PHY) {
+		netdev_err(net, "Unsupported negotiation mode: %u\n", mode);
+		return;
+	}
+
+	switch (state->interface) {
+	case PHY_INTERFACE_MODE_INTERNAL:
+	case PHY_INTERFACE_MODE_GMII:
+		mac_cr |= MAC_CR_GMII_EN_;
+		break;
+	case PHY_INTERFACE_MODE_RGMII:
+	case PHY_INTERFACE_MODE_RGMII_ID:
+	case PHY_INTERFACE_MODE_RGMII_TXID:
+	case PHY_INTERFACE_MODE_RGMII_RXID:
+		break;
+	default:
+		netdev_warn(net, "Unsupported interface mode: %d\n",
+			    state->interface);
+		return;
+	}
+
+	ret = lan78xx_update_reg(dev, MAC_CR, MAC_CR_GMII_EN_, mac_cr);
+	if (ret < 0)
+		netdev_err(net, "Failed to config MAC with error %pe\n",
+			   ERR_PTR(ret));
+}
+
+static void lan78xx_mac_link_down(struct phylink_config *config,
+				  unsigned int mode, phy_interface_t interface)
+{
+	struct net_device *net = to_net_dev(config->dev);
+	struct lan78xx_net *dev = netdev_priv(net);
+	int ret;
+
+	/* MAC reset will not de-assert TXEN/RXEN, we need to stop them
+	 * manually before reset. TX and RX should be disabled before running
+	 * link_up sequence.
+	 */
+	ret = lan78xx_stop_tx_path(dev);
+	if (ret < 0)
+		goto link_down_fail;
+
+	ret = lan78xx_stop_rx_path(dev);
+	if (ret < 0)
+		goto link_down_fail;
+
+	/* MAC reset seems to not affect MAC configuration, no idea if it is
+	 * really needed, but it was done in previous driver version. So, leave
+	 * it here.
+	 */
+	ret = lan78xx_mac_reset(dev);
+	if (ret < 0)
+		goto link_down_fail;
+
+	return;
+
+link_down_fail:
+	netdev_err(dev->net, "Failed to set MAC down with error %pe\n",
+		   ERR_PTR(ret));
+}
+
+static int lan78xx_configure_usb(struct lan78xx_net *dev, int speed)
+{
+	u32 mask, val;
+	int ret;
+
+	/* Return early if USB speed is not SuperSpeed */
+	if (dev->udev->speed != USB_SPEED_SUPER)
+		return 0;
+
+	/* Update U1 and U2 settings based on speed */
+	if (speed != SPEED_1000) {
+		mask = USB_CFG1_DEV_U2_INIT_EN_ | USB_CFG1_DEV_U1_INIT_EN_;
+		val = USB_CFG1_DEV_U2_INIT_EN_ | USB_CFG1_DEV_U1_INIT_EN_;
+		return lan78xx_update_reg(dev, USB_CFG1, mask, val);
+	}
+
+	/* For 1000 Mbps: disable U2 and enable U1 */
+	mask = USB_CFG1_DEV_U2_INIT_EN_;
+	val = 0;
+	ret = lan78xx_update_reg(dev, USB_CFG1, mask, val);
+	if (ret < 0)
+		return ret;
+
+	mask = USB_CFG1_DEV_U1_INIT_EN_;
+	val = USB_CFG1_DEV_U1_INIT_EN_;
+	return lan78xx_update_reg(dev, USB_CFG1, mask, val);
+}
+
+static int lan78xx_configure_flowcontrol(struct lan78xx_net *dev,
+					 bool tx_pause, bool rx_pause)
+{
+	u32 flow = 0, fct_flow = 0;
+	int ret;
+
+	if (tx_pause)
+		flow |= (FLOW_CR_TX_FCEN_ | 0xFFFF);
+
+	if (rx_pause)
+		flow |= FLOW_CR_RX_FCEN_;
+
+	if (dev->udev->speed == USB_SPEED_SUPER)
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_SS, FLOW_OFF_SS);
+	else if (dev->udev->speed == USB_SPEED_HIGH)
+		fct_flow = FLOW_CTRL_THRESHOLD(FLOW_ON_HS, FLOW_OFF_HS);
+
+	ret = lan78xx_write_reg(dev, FCT_FLOW, fct_flow);
+	if (ret < 0)
+		return ret;
+
+	/* threshold value should be set before enabling flow */
+	return lan78xx_write_reg(dev, FLOW, flow);
+}
+
+static void lan78xx_mac_link_up(struct phylink_config *config,
+				struct phy_device *phy,
+				unsigned int mode, phy_interface_t interface,
+				int speed, int duplex,
+				bool tx_pause, bool rx_pause)
+{
+	struct net_device *net = to_net_dev(config->dev);
+	struct lan78xx_net *dev = netdev_priv(net);
+	u32 mac_cr = 0;
+	int ret;
+
+	switch (speed) {
+	case SPEED_1000:
+		mac_cr |= MAC_CR_SPEED_1000_;
+		break;
+	case SPEED_100:
+		mac_cr |= MAC_CR_SPEED_100_;
+		break;
+	case SPEED_10:
+		mac_cr |= MAC_CR_SPEED_10_;
+		break;
+	default:
+		netdev_err(dev->net, "Unsupported speed %d\n", speed);
+		return;
+	}
+
+	if (duplex == DUPLEX_FULL)
+		mac_cr |= MAC_CR_FULL_DUPLEX_;
+
+	/* make sure TXEN and RXEN are disabled before reconfiguring MAC */
+	ret = lan78xx_update_reg(dev, MAC_CR, MAC_CR_SPEED_MASK_ |
+				 MAC_CR_FULL_DUPLEX_ | MAC_CR_EEE_EN_, mac_cr);
+	if (ret < 0)
+		goto link_up_fail;
+
+	ret = lan78xx_configure_flowcontrol(dev, tx_pause, rx_pause);
+	if (ret < 0)
+		goto link_up_fail;
+
+	ret = lan78xx_configure_usb(dev, speed);
+	if (ret < 0)
+		goto link_up_fail;
+
+	lan78xx_rx_urb_submit_all(dev);
+
+	ret = lan78xx_flush_rx_fifo(dev);
+	if (ret < 0)
+		goto link_up_fail;
+
+	ret = lan78xx_flush_tx_fifo(dev);
+	if (ret < 0)
+		goto link_up_fail;
+
+	ret = lan78xx_start_tx_path(dev);
+	if (ret < 0)
+		goto link_up_fail;
+
+	ret = lan78xx_start_rx_path(dev);
+	if (ret < 0)
+		goto link_up_fail;
+
+	return;
+link_up_fail:
+	netdev_err(dev->net, "Failed to set MAC up with error %pe\n",
+		   ERR_PTR(ret));
+}
+
+static const struct phylink_mac_ops lan78xx_phylink_mac_ops = {
+	.mac_config = lan78xx_mac_config,
+	.mac_link_down = lan78xx_mac_link_down,
+	.mac_link_up = lan78xx_mac_link_up,
+};
+
 static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 {
-	struct fixed_phy_status fphy_status = {
-		.link = 1,
-		.speed = SPEED_1000,
-		.duplex = DUPLEX_FULL,
-	};
 	struct phy_device *phydev;
 	int ret;
 
 	phydev = phy_find_first(dev->mdiobus);
 	if (!phydev) {
-		netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n");
-		phydev = fixed_phy_register(PHY_POLL, &fphy_status, NULL);
-		if (IS_ERR(phydev)) {
-			netdev_err(dev->net, "No PHY/fixed_PHY found\n");
-			return ERR_PTR(-ENODEV);
-		}
-		netdev_dbg(dev->net, "Registered FIXED PHY\n");
-		dev->interface = PHY_INTERFACE_MODE_RGMII;
+		netdev_dbg(dev->net, "PHY Not Found!! Forcing RGMII configuration\n");
 		ret = lan78xx_write_reg(dev, MAC_RGMII_ID,
 					MAC_RGMII_ID_TXC_DELAY_EN_);
 		if (ret < 0)
@@ -2547,7 +2545,7 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 			netdev_err(dev->net, "no PHY driver found\n");
 			return ERR_PTR(-EINVAL);
 		}
-		dev->interface = PHY_INTERFACE_MODE_RGMII_ID;
+		phydev->interface = PHY_INTERFACE_MODE_RGMII_ID;
 		/* The PHY driver is responsible to configure proper RGMII
 		 * interface delays. Disable RGMII delays on MAC side.
 		 */
@@ -2561,21 +2559,64 @@ static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
 	return phydev;
 }
 
+static int lan78xx_phylink_setup(struct lan78xx_net *dev)
+{
+	struct phylink_config *pc = &dev->phylink_config;
+	phy_interface_t link_interface;
+	struct phylink *phylink;
+
+	pc->dev = &dev->net->dev;
+	pc->type = PHYLINK_NETDEV;
+	pc->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10 |
+			       MAC_100 | MAC_1000FD;
+	pc->mac_managed_pm = true;
+
+	if (dev->chipid == ID_REV_CHIP_ID_7801_) {
+		phy_interface_set_rgmii(pc->supported_interfaces);
+		link_interface = PHY_INTERFACE_MODE_RGMII_ID;
+	} else {
+		__set_bit(PHY_INTERFACE_MODE_INTERNAL,
+			  pc->supported_interfaces);
+		link_interface = PHY_INTERFACE_MODE_INTERNAL;
+	}
+
+	phylink = phylink_create(pc, dev->net->dev.fwnode,
+				 link_interface, &lan78xx_phylink_mac_ops);
+	if (IS_ERR(phylink))
+		return PTR_ERR(phylink);
+
+	dev->phylink = phylink;
+
+	return 0;
+}
+
 static int lan78xx_phy_init(struct lan78xx_net *dev)
 {
-	__ETHTOOL_DECLARE_LINK_MODE_MASK(fc) = { 0, };
-	int ret;
-	u32 mii_adv;
 	struct phy_device *phydev;
+	int ret;
 
 	switch (dev->chipid) {
 	case ID_REV_CHIP_ID_7801_:
 		phydev = lan7801_phy_init(dev);
+		/* If no PHY found, set fixed link, probably there is no
+		 * device or some kind of different device like switch.
+		 * For example: EVB-KSZ9897-1 (KSZ9897 switch evaluation board
+		 * with LAN7801 & KSZ9031)
+		 */
 		if (IS_ERR(phydev)) {
-			netdev_err(dev->net, "lan7801: failed to init PHY: %pe\n",
-				   phydev);
-			return PTR_ERR(phydev);
+			struct phylink_link_state state = {
+				.speed = SPEED_1000,
+				.duplex = DUPLEX_FULL,
+				.interface = PHY_INTERFACE_MODE_RGMII,
+			};
+
+			ret = phylink_set_fixed_link(dev->phylink, &state);
+			if (ret)
+				netdev_err(dev->net, "Could not set fixed link\n");
+
+			return ret;
 		}
+
 		break;
 
 	case ID_REV_CHIP_ID_7800_:
@@ -2586,7 +2627,7 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 			return -ENODEV;
 		}
 		phydev->is_internal = true;
-		dev->interface = PHY_INTERFACE_MODE_GMII;
+		phydev->interface = PHY_INTERFACE_MODE_GMII;
 		break;
 
 	default:
@@ -2601,37 +2642,13 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 		phydev->irq = PHY_POLL;
 	netdev_dbg(dev->net, "phydev->irq = %d\n", phydev->irq);
 
-	/* set to AUTOMDIX */
-	phydev->mdix = ETH_TP_MDI_AUTO;
-
-	ret = phy_connect_direct(dev->net, phydev,
-				 lan78xx_link_status_change,
-				 dev->interface);
+	ret = phylink_connect_phy(dev->phylink, phydev);
 	if (ret) {
-		netdev_err(dev->net, "can't attach PHY to %s\n",
-			   dev->mdiobus->id);
-		if (dev->chipid == ID_REV_CHIP_ID_7801_) {
-			if (phy_is_pseudo_fixed_link(phydev)) {
-				fixed_phy_unregister(phydev);
-				phy_device_free(phydev);
-			}
-		}
-		return -EIO;
+		netdev_err(dev->net, "can't attach PHY to %s, error %pe\n",
+			   dev->mdiobus->id, ERR_PTR(ret));
+		return ret;
 	}
 
-	/* MAC doesn't support 1000T Half */
-	phy_remove_link_mode(phydev, ETHTOOL_LINK_MODE_1000baseT_Half_BIT);
-
-	/* support both flow controls */
-	dev->fc_request_control = (FLOW_CTRL_RX | FLOW_CTRL_TX);
-	linkmode_clear_bit(ETHTOOL_LINK_MODE_Pause_BIT,
-			   phydev->advertising);
-	linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
-			   phydev->advertising);
-	mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control);
-	mii_adv_to_linkmode_adv_t(fc, mii_adv);
-	linkmode_or(phydev->advertising, fc, phydev->advertising);
-
 	phy_support_eee(phydev);
 
 	if (phydev->mdio.dev.of_node) {
@@ -2661,10 +2678,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 		}
 	}
 
-	genphy_config_aneg(phydev);
-
-	dev->fc_autoneg = phydev->autoneg;
-
 	return 0;
 }
 
@@ -3004,7 +3017,6 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	unsigned long timeout;
 	int ret;
 	u32 buf;
-	u8 sig;
 
 	ret = lan78xx_read_reg(dev, HW_CFG, &buf);
 	if (ret < 0)
@@ -3161,22 +3173,12 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	if (ret < 0)
 		return ret;
 
+	buf &= ~(MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_);
+
 	/* LAN7801 only has RGMII mode */
-	if (dev->chipid == ID_REV_CHIP_ID_7801_) {
+	if (dev->chipid == ID_REV_CHIP_ID_7801_)
 		buf &= ~MAC_CR_GMII_EN_;
-		/* Enable Auto Duplex and Auto speed */
-		buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
-	}
 
-	if (dev->chipid == ID_REV_CHIP_ID_7800_ ||
-	    dev->chipid == ID_REV_CHIP_ID_7850_) {
-		ret = lan78xx_read_raw_eeprom(dev, 0, 1, &sig);
-		if (!ret && sig != EEPROM_INDICATOR) {
-			/* Implies there is no external eeprom. Set mac speed */
-			netdev_info(dev->net, "No External EEPROM. Setting MAC Speed\n");
-			buf |= MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_;
-		}
-	}
 	ret = lan78xx_write_reg(dev, MAC_CR, buf);
 	if (ret < 0)
 		return ret;
@@ -3226,9 +3228,11 @@ static int lan78xx_open(struct net_device *net)
 
 	mutex_lock(&dev->dev_mutex);
 
-	phy_start(net->phydev);
+	lan78xx_init_stats(dev);
+
+	napi_enable(&dev->napi);
 
-	netif_dbg(dev, ifup, dev->net, "phy initialised successfully");
+	set_bit(EVENT_DEV_OPEN, &dev->flags);
 
 	/* for Link Check */
 	if (dev->urb_intr) {
@@ -3240,31 +3244,9 @@ static int lan78xx_open(struct net_device *net)
 		}
 	}
 
-	ret = lan78xx_flush_rx_fifo(dev);
-	if (ret < 0)
-		goto done;
-	ret = lan78xx_flush_tx_fifo(dev);
-	if (ret < 0)
-		goto done;
-
-	ret = lan78xx_start_tx_path(dev);
-	if (ret < 0)
-		goto done;
-	ret = lan78xx_start_rx_path(dev);
-	if (ret < 0)
-		goto done;
-
-	lan78xx_init_stats(dev);
-
-	set_bit(EVENT_DEV_OPEN, &dev->flags);
+	phylink_start(dev->phylink);
 
 	netif_start_queue(net);
-
-	dev->link_on = false;
-
-	napi_enable(&dev->napi);
-
-	lan78xx_defer_kevent(dev, EVENT_LINK_RESET);
 done:
 	mutex_unlock(&dev->dev_mutex);
 
@@ -3332,12 +3314,7 @@ static int lan78xx_stop(struct net_device *net)
 		   net->stats.rx_packets, net->stats.tx_packets,
 		   net->stats.rx_errors, net->stats.tx_errors);
 
-	/* ignore errors that occur stopping the Tx and Rx data paths */
-	lan78xx_stop_tx_path(dev);
-	lan78xx_stop_rx_path(dev);
-
-	if (net->phydev)
-		phy_stop(net->phydev);
+	phylink_stop(dev->phylink);
 
 	usb_kill_urb(dev->urb_intr);
 
@@ -3347,7 +3324,7 @@ static int lan78xx_stop(struct net_device *net)
 	 */
 	clear_bit(EVENT_TX_HALT, &dev->flags);
 	clear_bit(EVENT_RX_HALT, &dev->flags);
-	clear_bit(EVENT_LINK_RESET, &dev->flags);
+	clear_bit(EVENT_PHY_INT_ACK, &dev->flags);
 	clear_bit(EVENT_STAT_UPDATE, &dev->flags);
 
 	cancel_delayed_work_sync(&dev->wq);
@@ -4271,14 +4248,14 @@ static void lan78xx_delayedwork(struct work_struct *work)
 		}
 	}
 
-	if (test_bit(EVENT_LINK_RESET, &dev->flags)) {
+	if (test_bit(EVENT_PHY_INT_ACK, &dev->flags)) {
 		int ret = 0;
 
-		clear_bit(EVENT_LINK_RESET, &dev->flags);
-		if (lan78xx_link_reset(dev) < 0) {
-			netdev_info(dev->net, "link reset failed (%d)\n",
-				    ret);
-		}
+		clear_bit(EVENT_PHY_INT_ACK, &dev->flags);
+		ret = lan78xx_phy_int_ack(dev);
+		if (ret)
+			netdev_info(dev->net, "PHY INT ack failed (%pe)\n",
+				    ERR_PTR(ret));
 	}
 
 	if (test_bit(EVENT_STAT_UPDATE, &dev->flags)) {
@@ -4352,32 +4329,29 @@ static void lan78xx_disconnect(struct usb_interface *intf)
 	struct lan78xx_net *dev;
 	struct usb_device *udev;
 	struct net_device *net;
-	struct phy_device *phydev;
 
 	dev = usb_get_intfdata(intf);
 	usb_set_intfdata(intf, NULL);
 	if (!dev)
 		return;
 
-	netif_napi_del(&dev->napi);
-
 	udev = interface_to_usbdev(intf);
 	net = dev->net;
 
+	rtnl_lock();
+	phylink_stop(dev->phylink);
+	phylink_disconnect_phy(dev->phylink);
+	rtnl_unlock();
+
+	netif_napi_del(&dev->napi);
+
 	unregister_netdev(net);
 
 	timer_shutdown_sync(&dev->stat_monitor);
 	set_bit(EVENT_DEV_DISCONNECT, &dev->flags);
 	cancel_delayed_work_sync(&dev->wq);
 
-	phydev = net->phydev;
-
-	phy_disconnect(net->phydev);
-
-	if (phy_is_pseudo_fixed_link(phydev)) {
-		fixed_phy_unregister(phydev);
-		phy_device_free(phydev);
-	}
+	phylink_destroy(dev->phylink);
 
 	usb_scuttle_anchored_urbs(&dev->deferred);
 
@@ -4461,7 +4435,6 @@ static int lan78xx_probe(struct usb_interface *intf,
 		goto out1;
 	}
 
-	/* netdev_printk() needs this */
 	SET_NETDEV_DEV(netdev, &intf->dev);
 
 	dev = netdev_priv(netdev);
@@ -4573,14 +4546,18 @@ static int lan78xx_probe(struct usb_interface *intf,
 	/* driver requires remote-wakeup capability during autosuspend. */
 	intf->needs_remote_wakeup = 1;
 
-	ret = lan78xx_phy_init(dev);
+	ret = lan78xx_phylink_setup(dev);
 	if (ret < 0)
 		goto free_urbs;
 
+	ret = lan78xx_phy_init(dev);
+	if (ret < 0)
+		goto destroy_phylink;
+
 	ret = register_netdev(netdev);
 	if (ret != 0) {
 		netif_err(dev, probe, netdev, "couldn't register the device\n");
-		goto out8;
+		goto disconnect_phy;
 	}
 
 	usb_set_intfdata(intf, dev);
@@ -4595,8 +4572,10 @@ static int lan78xx_probe(struct usb_interface *intf,
 
 	return 0;
 
-out8:
-	phy_disconnect(netdev->phydev);
+disconnect_phy:
+	phylink_disconnect_phy(dev->phylink);
+destroy_phylink:
+	phylink_destroy(dev->phylink);
 free_urbs:
 	usb_free_urb(dev->urb_intr);
 out5:
@@ -5158,7 +5137,7 @@ static int lan78xx_reset_resume(struct usb_interface *intf)
 	if (ret < 0)
 		return ret;
 
-	phy_start(dev->net->phydev);
+	phylink_start(dev->phylink);
 
 	ret = lan78xx_resume(intf);
 

From 617076a8caaf9a63841a3975eedbb932c2c3fb42 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:49 +0100
Subject: [PATCH 2642/2753] net: usb: lan78xx: Use ethtool_op_get_link to
 reflect current link status

Replace the custom lan78xx_get_link implementation with the standard
ethtool_op_get_link helper, which uses netif_carrier_ok to reflect
the current link status accurately.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/lan78xx.c | 14 +-------------
 1 file changed, 1 insertion(+), 13 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index fd6e80f9c35f7..6a6e965ec27fd 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1835,18 +1835,6 @@ static int lan78xx_set_eee(struct net_device *net, struct ethtool_keee *edata)
 	return ret;
 }
 
-static u32 lan78xx_get_link(struct net_device *net)
-{
-	u32 link;
-
-	mutex_lock(&net->phydev->lock);
-	phy_read_status(net->phydev);
-	link = net->phydev->link;
-	mutex_unlock(&net->phydev->lock);
-
-	return link;
-}
-
 static void lan78xx_get_drvinfo(struct net_device *net,
 				struct ethtool_drvinfo *info)
 {
@@ -1966,7 +1954,7 @@ lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs,
 }
 
 static const struct ethtool_ops lan78xx_ethtool_ops = {
-	.get_link	= lan78xx_get_link,
+	.get_link	= ethtool_op_get_link,
 	.nway_reset	= phy_ethtool_nway_reset,
 	.get_drvinfo	= lan78xx_get_drvinfo,
 	.get_msglevel	= lan78xx_get_msglevel,

From 940e73ff92d87e5afcd3bf1f95877defce6db6b2 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:50 +0100
Subject: [PATCH 2643/2753] net: usb: lan78xx: port link settings to phylink
 API

Refactor lan78xx_get_link_ksettings and lan78xx_set_link_ksettings to
use the phylink API (phylink_ethtool_ksettings_get and
phylink_ethtool_ksettings_set) instead of directly interfacing with the
PHY. This change simplifies the code and ensures better integration with
the phylink framework for link management.

Additionally, the explicit calls to usb_autopm_get_interface() and
usb_autopm_put_interface() have been removed. These were originally
needed to manage USB power management during register accesses. However,
lan78xx_mdiobus_read() and lan78xx_mdiobus_write() already handle USB
auto power management internally, ensuring that the interface remains
active when necessary. Since there are no other direct register accesses
in these functions that require explicit power management handling, the
extra calls have become redundant and are no longer needed.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/lan78xx.c | 34 ++--------------------------------
 1 file changed, 2 insertions(+), 32 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 6a6e965ec27fd..9ff8e7850e1e1 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1862,46 +1862,16 @@ static int lan78xx_get_link_ksettings(struct net_device *net,
 				      struct ethtool_link_ksettings *cmd)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	int ret;
-
-	ret = usb_autopm_get_interface(dev->intf);
-	if (ret < 0)
-		return ret;
 
-	phy_ethtool_ksettings_get(phydev, cmd);
-
-	usb_autopm_put_interface(dev->intf);
-
-	return ret;
+	return phylink_ethtool_ksettings_get(dev->phylink, cmd);
 }
 
 static int lan78xx_set_link_ksettings(struct net_device *net,
 				      const struct ethtool_link_ksettings *cmd)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	int ret = 0;
-	int temp;
-
-	ret = usb_autopm_get_interface(dev->intf);
-	if (ret < 0)
-		return ret;
-
-	/* change speed & duplex */
-	ret = phy_ethtool_ksettings_set(phydev, cmd);
 
-	if (!cmd->base.autoneg) {
-		/* force link down */
-		temp = phy_read(phydev, MII_BMCR);
-		phy_write(phydev, MII_BMCR, temp | BMCR_LOOPBACK);
-		mdelay(1);
-		phy_write(phydev, MII_BMCR, temp);
-	}
-
-	usb_autopm_put_interface(dev->intf);
-
-	return ret;
+	return phylink_ethtool_ksettings_set(dev->phylink, cmd);
 }
 
 static void lan78xx_get_pause(struct net_device *net,

From df8e53a08f4169dfd040eb1cb8b7aa65a77c3662 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:51 +0100
Subject: [PATCH 2644/2753] net: usb: lan78xx: Integrate EEE support with
 phylink LPI API

Refactor Energy-Efficient Ethernet (EEE) support in the LAN78xx driver to
fully integrate with the phylink Low Power Idle (LPI) API. This includes:

- Replacing direct calls to `phy_ethtool_get_eee` and `phy_ethtool_set_eee`
  with `phylink_ethtool_get_eee` and `phylink_ethtool_set_eee`.
- Implementing `.mac_enable_tx_lpi` and `.mac_disable_tx_lpi` to control
  LPI transitions via phylink.
- Configuring `lpi_timer_default` to align with recommended values from
  LAN7800 documentation.
- ensure EEE is disabled on controller reset

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/lan78xx.c | 111 +++++++++++++++++++++++---------------
 1 file changed, 67 insertions(+), 44 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 9ff8e7850e1e1..074ac4d1cbcbd 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -1785,54 +1785,15 @@ static int lan78xx_set_wol(struct net_device *netdev,
 static int lan78xx_get_eee(struct net_device *net, struct ethtool_keee *edata)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	struct phy_device *phydev = net->phydev;
-	int ret;
-	u32 buf;
-
-	ret = usb_autopm_get_interface(dev->intf);
-	if (ret < 0)
-		return ret;
-
-	ret = phy_ethtool_get_eee(phydev, edata);
-	if (ret < 0)
-		goto exit;
-
-	ret = lan78xx_read_reg(dev, MAC_CR, &buf);
-	if (buf & MAC_CR_EEE_EN_) {
-		/* EEE_TX_LPI_REQ_DLY & tx_lpi_timer are same uSec unit */
-		ret = lan78xx_read_reg(dev, EEE_TX_LPI_REQ_DLY, &buf);
-		edata->tx_lpi_timer = buf;
-	} else {
-		edata->tx_lpi_timer = 0;
-	}
-
-	ret = 0;
-exit:
-	usb_autopm_put_interface(dev->intf);
 
-	return ret;
+	return phylink_ethtool_get_eee(dev->phylink, edata);
 }
 
 static int lan78xx_set_eee(struct net_device *net, struct ethtool_keee *edata)
 {
 	struct lan78xx_net *dev = netdev_priv(net);
-	int ret;
-	u32 buf;
-
-	ret = usb_autopm_get_interface(dev->intf);
-	if (ret < 0)
-		return ret;
 
-	ret = phy_ethtool_set_eee(net->phydev, edata);
-	if (ret < 0)
-		goto out;
-
-	buf = (u32)edata->tx_lpi_timer;
-	ret = lan78xx_write_reg(dev, EEE_TX_LPI_REQ_DLY, buf);
-out:
-	usb_autopm_put_interface(dev->intf);
-
-	return ret;
+	return phylink_ethtool_set_eee(dev->phylink, edata);
 }
 
 static void lan78xx_get_drvinfo(struct net_device *net,
@@ -2470,10 +2431,50 @@ static void lan78xx_mac_link_up(struct phylink_config *config,
 		   ERR_PTR(ret));
 }
 
+static int lan78xx_mac_eee_enable(struct lan78xx_net *dev, bool enable)
+{
+	u32 mac_cr = 0;
+
+	if (enable)
+		mac_cr |= MAC_CR_EEE_EN_;
+
+	/* make sure TXEN and RXEN are disabled before reconfiguring MAC */
+	return lan78xx_update_reg(dev, MAC_CR, MAC_CR_EEE_EN_, mac_cr);
+}
+
+static void lan78xx_mac_disable_tx_lpi(struct phylink_config *config)
+{
+	struct net_device *net = to_net_dev(config->dev);
+	struct lan78xx_net *dev = netdev_priv(net);
+
+	lan78xx_mac_eee_enable(dev, false);
+}
+
+static int lan78xx_mac_enable_tx_lpi(struct phylink_config *config, u32 timer,
+				     bool tx_clk_stop)
+{
+	struct net_device *net = to_net_dev(config->dev);
+	struct lan78xx_net *dev = netdev_priv(net);
+	int ret;
+
+	/* Software should only change this field when Energy Efficient
+	 * Ethernet Enable (EEEEN) is cleared. We ensure that by clearing
+	 * EEEEN during probe, and phylink itself guarantees that
+	 * mac_disable_tx_lpi() will have been previously called.
+	 */
+	ret = lan78xx_write_reg(dev, EEE_TX_LPI_REQ_DLY, timer);
+	if (ret < 0)
+		return ret;
+
+	return lan78xx_mac_eee_enable(dev, true);
+}
+
 static const struct phylink_mac_ops lan78xx_phylink_mac_ops = {
 	.mac_config = lan78xx_mac_config,
 	.mac_link_down = lan78xx_mac_link_down,
 	.mac_link_up = lan78xx_mac_link_up,
+	.mac_disable_tx_lpi = lan78xx_mac_disable_tx_lpi,
+	.mac_enable_tx_lpi = lan78xx_mac_enable_tx_lpi,
 };
 
 static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev)
@@ -2528,6 +2529,26 @@ static int lan78xx_phylink_setup(struct lan78xx_net *dev)
 	pc->mac_capabilities = MAC_SYM_PAUSE | MAC_ASYM_PAUSE | MAC_10 |
 			       MAC_100 | MAC_1000FD;
 	pc->mac_managed_pm = true;
+	pc->lpi_capabilities = MAC_100FD | MAC_1000FD;
+	/*
+	 * Default TX LPI (Low Power Idle) request delay count is set to 50us.
+	 *
+	 * Source: LAN7800 Documentation, DS00001992H, Section 15.1.57, Page 204.
+	 *
+	 * Reasoning:
+	 * According to the application note in the LAN7800 documentation, a
+	 * zero delay may negatively impact the TX data path’s ability to
+	 * support Gigabit operation. A value of 50us is recommended as a
+	 * reasonable default when the part operates at Gigabit speeds,
+	 * balancing stability and power efficiency in EEE mode. This delay can
+	 * be increased based on performance testing, as EEE is designed for
+	 * scenarios with mostly idle links and occasional bursts of full
+	 * bandwidth transmission. The goal is to ensure reliable Gigabit
+	 * performance without overly aggressive power optimization during
+	 * inactive periods.
+	 */
+	pc->lpi_timer_default = 50;
+	pc->eee_enabled_default = true;
 
 	if (dev->chipid == ID_REV_CHIP_ID_7801_) {
 		phy_interface_set_rgmii(pc->supported_interfaces);
@@ -2538,6 +2559,10 @@ static int lan78xx_phylink_setup(struct lan78xx_net *dev)
 		link_interface = PHY_INTERFACE_MODE_INTERNAL;
 	}
 
+	memcpy(dev->phylink_config.lpi_interfaces,
+	       dev->phylink_config.supported_interfaces,
+	       sizeof(dev->phylink_config.lpi_interfaces));
+
 	phylink = phylink_create(pc, dev->net->dev.fwnode,
 				 link_interface, &lan78xx_phylink_mac_ops);
 	if (IS_ERR(phylink))
@@ -2607,8 +2632,6 @@ static int lan78xx_phy_init(struct lan78xx_net *dev)
 		return ret;
 	}
 
-	phy_support_eee(phydev);
-
 	if (phydev->mdio.dev.of_node) {
 		u32 reg;
 		int len;
@@ -3131,7 +3154,7 @@ static int lan78xx_reset(struct lan78xx_net *dev)
 	if (ret < 0)
 		return ret;
 
-	buf &= ~(MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_);
+	buf &= ~(MAC_CR_AUTO_DUPLEX_ | MAC_CR_AUTO_SPEED_ | MAC_CR_EEE_EN_);
 
 	/* LAN7801 only has RGMII mode */
 	if (dev->chipid == ID_REV_CHIP_ID_7801_)

From 037d410a979a9173db21862a9bab7100443aaa18 Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Wed, 19 Mar 2025 09:49:52 +0100
Subject: [PATCH 2645/2753] net: usb: lan78xx: remove unused struct members

Remove unused members from struct lan78xx_net, including:

    driver_priv
    suspend_count
    link_on
    mdix_ctrl
    interface
    fc_autoneg
    fc_request_control

These fields are no longer used in the driver and can be safely removed
as part of a cleanup.

Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/lan78xx.c | 9 ---------
 1 file changed, 9 deletions(-)

diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c
index 074ac4d1cbcbd..fc6517bb36715 100644
--- a/drivers/net/usb/lan78xx.c
+++ b/drivers/net/usb/lan78xx.c
@@ -414,7 +414,6 @@ struct lan78xx_net {
 	struct net_device	*net;
 	struct usb_device	*udev;
 	struct usb_interface	*intf;
-	void			*driver_priv;
 
 	unsigned int		tx_pend_data_len;
 	size_t			n_tx_urbs;
@@ -449,23 +448,15 @@ struct lan78xx_net {
 	unsigned long		flags;
 
 	wait_queue_head_t	*wait;
-	unsigned char		suspend_count;
 
 	unsigned int		maxpacket;
 	struct timer_list	stat_monitor;
 
 	unsigned long		data[5];
 
-	int			link_on;
-	u8			mdix_ctrl;
-
 	u32			chipid;
 	u32			chiprev;
 	struct mii_bus		*mdiobus;
-	phy_interface_t		interface;
-
-	int			fc_autoneg;
-	u8			fc_request_control;
 
 	int			delta;
 	struct statstage	stats;

From a0b657068a2eb050b2febcb19fc2599e040caede Mon Sep 17 00:00:00 2001
From: Jing Su <jingsusu@didiglobal.com>
Date: Wed, 19 Mar 2025 16:57:51 +0800
Subject: [PATCH 2646/2753] dql: Fix dql->limit value when reset.

Executing dql_reset after setting a non-zero value for limit_min can
lead to an unreasonable situation where dql->limit is less than
dql->limit_min.

For instance, after setting
/sys/class/net/eth*/queues/tx-0/byte_queue_limits/limit_min,
an ifconfig down/up operation might cause the ethernet driver to call
netdev_tx_reset_queue, which in turn invokes dql_reset.

In this case, dql->limit is reset to 0 while dql->limit_min remains
non-zero value, which is unexpected. The limit should always be
greater than or equal to limit_min.

Signed-off-by: Jing Su <jingsusu@didiglobal.com>
Signed-off-by: NipaLocal <nipa@local>
---
 lib/dynamic_queue_limits.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
index c1b7638a594ac..f97a752e900a0 100644
--- a/lib/dynamic_queue_limits.c
+++ b/lib/dynamic_queue_limits.c
@@ -190,7 +190,7 @@ EXPORT_SYMBOL(dql_completed);
 void dql_reset(struct dql *dql)
 {
 	/* Reset all dynamic values */
-	dql->limit = 0;
+	dql->limit = dql->min_limit;
 	dql->num_queued = 0;
 	dql->num_completed = 0;
 	dql->last_obj_cnt = 0;

From 0682dc17e114b75a2f24b9bf3f3830855fd6b6d1 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Wed, 19 Mar 2025 11:21:53 +0000
Subject: [PATCH 2647/2753] net: fix uninitialised access in mii_nway_restart()

In mii_nway_restart() during the line:

        bmcr = mii->mdio_read(mii->dev, mii->phy_id, MII_BMCR);

The code attempts to call mii->mdio_read which is ch9200_mdio_read().

ch9200_mdio_read() utilises a local buffer, which is initialised
with control_read():

        unsigned char buff[2];

However buff is conditionally initialised inside control_read():

        if (err == size) {
                memcpy(data, buf, size);
        }

If the condition of "err == size" is not met, then buff remains
uninitialised. Once this happens the uninitialised buff is accessed
and returned during ch9200_mdio_read():

        return (buff[0] | buff[1] << 8);

The problem stems from the fact that ch9200_mdio_read() ignores the
return value of control_read(), leading to uinit-access of buff.

To fix this we should check the return value of control_read()
and return early on error.

Reported-by: syzbot <syzbot+3361c2d6f78a3e0892f9@syzkaller.appspotmail.com>
Closes: https://syzkaller.appspot.com/bug?extid=3361c2d6f78a3e0892f9
Tested-by: syzbot <syzbot+3361c2d6f78a3e0892f9@syzkaller.appspotmail.com>
Fixes: 4a476bd6d1d9 ("usbnet: New driver for QinHeng CH9200 devices")
Cc: stable@vger.kernel.org
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/mii.c        | 2 ++
 drivers/net/usb/ch9200.c | 7 +++++--
 2 files changed, 7 insertions(+), 2 deletions(-)

diff --git a/drivers/net/mii.c b/drivers/net/mii.c
index 37bc3131d31a8..e305bf0f1d048 100644
--- a/drivers/net/mii.c
+++ b/drivers/net/mii.c
@@ -464,6 +464,8 @@ int mii_nway_restart (struct mii_if_info *mii)
 
 	/* if autoneg is off, it's an error */
 	bmcr = mii->mdio_read(mii->dev, mii->phy_id, MII_BMCR);
+	if (bmcr < 0)
+		return bmcr;
 
 	if (bmcr & BMCR_ANENABLE) {
 		bmcr |= BMCR_ANRESTART;
diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index f69d9b902da04..a206ffa76f1b9 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -178,6 +178,7 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 {
 	struct usbnet *dev = netdev_priv(netdev);
 	unsigned char buff[2];
+	int ret;
 
 	netdev_dbg(netdev, "%s phy_id:%02x loc:%02x\n",
 		   __func__, phy_id, loc);
@@ -185,8 +186,10 @@ static int ch9200_mdio_read(struct net_device *netdev, int phy_id, int loc)
 	if (phy_id != 0)
 		return -ENODEV;
 
-	control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
-		     CONTROL_TIMEOUT_MS);
+	ret = control_read(dev, REQUEST_READ, 0, loc * 2, buff, 0x02,
+			   CONTROL_TIMEOUT_MS);
+	if (ret < 0)
+		return ret;
 
 	return (buff[0] | buff[1] << 8);
 }

From 8ee762094a2103dfe58cd7bb18e56ec8b537e3cc Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Wed, 19 Mar 2025 11:21:54 +0000
Subject: [PATCH 2648/2753] net: ch9200: remove extraneous return in
 control_write() to propagate failures

The control_write() function sets err to -EINVAL however there
is an incorrectly placed 'return 0' statement after it which stops
the propogation of the error.

Fix this issue by removing the 'return 0'.

Fixes: 4a476bd6d1d9 ("usbnet: New driver for QinHeng CH9200 devices")
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/ch9200.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index a206ffa76f1b9..3a81e9e96fd33 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -168,8 +168,6 @@ static int control_write(struct usbnet *dev, unsigned char request,
 		err = -EINVAL;
 	kfree(buf);
 
-	return 0;
-
 err_out:
 	return err;
 }

From fa52f3c0a4f17f1f1bb83fff998d06fad333dda0 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Wed, 19 Mar 2025 11:21:55 +0000
Subject: [PATCH 2649/2753] net: ch9200: improve error handling in
 get_mac_address()

The get_mac_address() function has an issue where it does not
directly check the return value of each control_read(), instead
it sums up the return values and checks them all at the end
which means if any call to control_read() fails the function just
continues on.

Handle this by validating the return value of each call and fail fast
and early instead of continuing.

Fixes: 4a476bd6d1d9 ("usbnet: New driver for QinHeng CH9200 devices")
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/ch9200.c | 32 +++++++++++++++++++-------------
 1 file changed, 19 insertions(+), 13 deletions(-)

diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index 3a81e9e96fd33..6b674a39398da 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -304,24 +304,27 @@ static int ch9200_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
 
 static int get_mac_address(struct usbnet *dev, unsigned char *data)
 {
-	int err = 0;
 	unsigned char mac_addr[0x06];
-	int rd_mac_len = 0;
+	int rd_mac_len;
 
 	netdev_dbg(dev->net, "%s:\n\tusbnet VID:%0x PID:%0x\n", __func__,
 		   le16_to_cpu(dev->udev->descriptor.idVendor),
 		   le16_to_cpu(dev->udev->descriptor.idProduct));
 
-	memset(mac_addr, 0, sizeof(mac_addr));
-	rd_mac_len = control_read(dev, REQUEST_READ, 0,
-				  MAC_REG_STATION_L, mac_addr, 0x02,
-				  CONTROL_TIMEOUT_MS);
-	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_M,
-				   mac_addr + 2, 0x02, CONTROL_TIMEOUT_MS);
-	rd_mac_len += control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_H,
-				   mac_addr + 4, 0x02, CONTROL_TIMEOUT_MS);
-	if (rd_mac_len != ETH_ALEN)
-		err = -EINVAL;
+	rd_mac_len = control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_L,
+				  mac_addr, 0x02, CONTROL_TIMEOUT_MS);
+	if (rd_mac_len < 0)
+		return rd_mac_len;
+
+	rd_mac_len = control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_M,
+				  mac_addr + 2, 0x02, CONTROL_TIMEOUT_MS);
+	if (rd_mac_len < 0)
+		return rd_mac_len;
+
+	rd_mac_len = control_read(dev, REQUEST_READ, 0, MAC_REG_STATION_H,
+				  mac_addr + 4, 0x02, CONTROL_TIMEOUT_MS);
+	if (rd_mac_len < 0)
+		return rd_mac_len;
 
 	data[0] = mac_addr[5];
 	data[1] = mac_addr[4];
@@ -330,7 +333,7 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data)
 	data[4] = mac_addr[1];
 	data[5] = mac_addr[0];
 
-	return err;
+	return 0;
 }
 
 static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
@@ -386,6 +389,9 @@ static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
 			       CONTROL_TIMEOUT_MS);
 
 	retval = get_mac_address(dev, addr);
+	if (retval < 0)
+		return retval;
+
 	eth_hw_addr_set(dev->net, addr);
 
 	return retval;

From ee14cd0f2d94856d4877cac05022efe8a2539627 Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Wed, 19 Mar 2025 11:21:56 +0000
Subject: [PATCH 2650/2753] net: ch9200: add error handling in ch9200_bind()

The ch9200_bind() function has no error handling for any
control_write() calls.

Fix this by checking if any control_write() call fails and
propagate the error to the caller.

Fixes: 4a476bd6d1d9 ("usbnet: New driver for QinHeng CH9200 devices")
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/usb/ch9200.c | 18 +++++++++++++++---
 1 file changed, 15 insertions(+), 3 deletions(-)

diff --git a/drivers/net/usb/ch9200.c b/drivers/net/usb/ch9200.c
index 6b674a39398da..957d186e324af 100644
--- a/drivers/net/usb/ch9200.c
+++ b/drivers/net/usb/ch9200.c
@@ -338,12 +338,12 @@ static int get_mac_address(struct usbnet *dev, unsigned char *data)
 
 static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
 {
-	int retval = 0;
+	int retval;
 	unsigned char data[2];
 	u8 addr[ETH_ALEN];
 
 	retval = usbnet_get_endpoints(dev, intf);
-	if (retval)
+	if (retval < 0)
 		return retval;
 
 	dev->mii.dev = dev->net;
@@ -361,32 +361,44 @@ static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
 	data[1] = 0x0F;
 	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_THRESHOLD, data,
 			       0x02, CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	data[0] = 0xA0;
 	data[1] = 0x90;
 	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FIFO_DEPTH, data,
 			       0x02, CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	data[0] = 0x30;
 	data[1] = 0x00;
 	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_PAUSE, data,
 			       0x02, CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	data[0] = 0x17;
 	data[1] = 0xD8;
 	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_FLOW_CONTROL,
 			       data, 0x02, CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	/* Undocumented register */
 	data[0] = 0x01;
 	data[1] = 0x00;
 	retval = control_write(dev, REQUEST_WRITE, 0, 254, data, 0x02,
 			       CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	data[0] = 0x5F;
 	data[1] = 0x0D;
 	retval = control_write(dev, REQUEST_WRITE, 0, MAC_REG_CTRL, data, 0x02,
 			       CONTROL_TIMEOUT_MS);
+	if (retval < 0)
+		return retval;
 
 	retval = get_mac_address(dev, addr);
 	if (retval < 0)
@@ -394,7 +406,7 @@ static int ch9200_bind(struct usbnet *dev, struct usb_interface *intf)
 
 	eth_hw_addr_set(dev->net, addr);
 
-	return retval;
+	return 0;
 }
 
 static const struct driver_info ch9200_info = {

From 337c6307d30438badb0008ba16221ba0f030c2d9 Mon Sep 17 00:00:00 2001
From: Maxim Mikityanskiy <maxtram95@gmail.com>
Date: Wed, 19 Mar 2025 14:45:08 +0200
Subject: [PATCH 2651/2753] net/mlx5e: Fix ethtool -N flow-type ip4 to RSS
 context

There commands can be used to add an RSS context and steer some traffic
into it:

    # ethtool -X eth0 context new
    New RSS context is 1
    # ethtool -N eth0 flow-type ip4 dst-ip 1.1.1.1 context 1
    Added rule with ID 1023

However, the second command fails with EINVAL on mlx5e:

    # ethtool -N eth0 flow-type ip4 dst-ip 1.1.1.1 context 1
    rmgr: Cannot insert RX class rule: Invalid argument
    Cannot insert classification rule

It happens when flow_get_tirn calls flow_type_to_traffic_type with
flow_type = IP_USER_FLOW or IPV6_USER_FLOW. That function only handles
IPV4_FLOW and IPV6_FLOW cases, but unlike all other cases which are
common for hash and spec, IPv4 and IPv6 defines different contants for
hash and for spec:

    #define	TCP_V4_FLOW	0x01	/* hash or spec (tcp_ip4_spec) */
    #define	UDP_V4_FLOW	0x02	/* hash or spec (udp_ip4_spec) */
    ...
    #define	IPV4_USER_FLOW	0x0d	/* spec only (usr_ip4_spec) */
    #define	IP_USER_FLOW	IPV4_USER_FLOW
    #define	IPV6_USER_FLOW	0x0e	/* spec only (usr_ip6_spec; nfc only) */
    #define	IPV4_FLOW	0x10	/* hash only */
    #define	IPV6_FLOW	0x11	/* hash only */

Extend the switch in flow_type_to_traffic_type to support both, which
fixes the failing ethtool -N command with flow-type ip4 or ip6.

Fixes: 248d3b4c9a39 ("net/mlx5e: Support flow classification into RSS contexts")
Signed-off-by: Maxim Mikityanskiy <maxim@isovalent.com>
Tested-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
index 773624bb2c5d5..d68230a7b9f46 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
@@ -884,8 +884,10 @@ static int flow_type_to_traffic_type(u32 flow_type)
 	case ESP_V6_FLOW:
 		return MLX5_TT_IPV6_IPSEC_ESP;
 	case IPV4_FLOW:
+	case IP_USER_FLOW:
 		return MLX5_TT_IPV4;
 	case IPV6_FLOW:
+	case IPV6_USER_FLOW:
 		return MLX5_TT_IPV6;
 	default:
 		return -EINVAL;

From f6139faa8f7997376a30591257917f2d30e992bd Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 19 Mar 2025 15:42:26 +0200
Subject: [PATCH 2652/2753] net/mlx5e: TX, Utilize WQ fragments edge for
 multi-packet WQEs

For simplicity reasons, the driver avoids crossing work queue fragment
boundaries within the same TX WQE (Work-Queue Element). Until today, as
the number of packets in a TX MPWQE (Multi-Packet WQE) descriptor is not
known in advance, the driver pre-prepared contiguous memory for the
largest possible WQE. For this, when getting too close to the fragment
edge, having no room for the largest WQE possible, the driver was
filling the fragment remainder with NOP descriptors, aligning the next
descriptor to the beginning of the next fragment.

Generating and handling these NOPs wastes resources, like: CPU cycles,
work-queue entries fetched to the device, and PCI bandwidth.

In this patch, we replace this NOPs filling mechanism in the TX MPWQE
flow. Instead, we utilize the remaining entries of the fragment with a
TX MPWQE. If this room turns out to be too small, we simply open an
additional descriptor starting at the beginning of the next fragment.

Performance benchmark:
uperf test, single server against 3 clients.
TCP multi-stream, bidir, traffic profile "2x350B read, 1400B write".
Bottleneck is in inbound PCI bandwidth (device POV).

+---------------+------------+------------+--------+
|               | Before     | After      |        |
+---------------+------------+------------+--------+
| BW            | 117.4 Gbps | 121.1 Gbps | +3.1%  |
+---------------+------------+------------+--------+
| tx_packets    | 15 M/sec   | 15.5 M/sec | +3.3%  |
+---------------+------------+------------+--------+
| tx_nops       | 3  M/sec   | 0          | -100%  |
+---------------+------------+------------+--------+

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h    |  1 +
 .../net/ethernet/mellanox/mlx5/core/en/txrx.h   | 17 +++++++++++++++--
 .../net/ethernet/mellanox/mlx5/core/en/xdp.c    |  3 ++-
 .../net/ethernet/mellanox/mlx5/core/en/xdp.h    |  6 +++---
 drivers/net/ethernet/mellanox/mlx5/core/en_tx.c |  7 ++++---
 5 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index 8df185e2ef7fe..32ed4963b8ada 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -398,6 +398,7 @@ struct mlx5e_tx_mpwqe {
 	struct mlx5e_tx_wqe *wqe;
 	u32 bytes_count;
 	u8 ds_count;
+	u8 ds_count_max;
 	u8 pkt_count;
 	u8 inline_on;
 };
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 5ec468268d1aa..e837c21d3d213 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -214,6 +214,19 @@ static inline u16 mlx5e_txqsq_get_next_pi(struct mlx5e_txqsq *sq, u16 size)
 	return pi;
 }
 
+static inline u16 mlx5e_txqsq_get_next_pi_anysize(struct mlx5e_txqsq *sq,
+						  u16 *size)
+{
+	struct mlx5_wq_cyc *wq = &sq->wq;
+	u16 pi, contig_wqebbs;
+
+	pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc);
+	contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi);
+	*size = min_t(u16, contig_wqebbs, sq->max_sq_mpw_wqebbs);
+
+	return pi;
+}
+
 void mlx5e_txqsq_wake(struct mlx5e_txqsq *sq);
 
 static inline u16 mlx5e_shampo_get_cqe_header_index(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe)
@@ -358,9 +371,9 @@ mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma)
 
 void mlx5e_tx_mpwqe_ensure_complete(struct mlx5e_txqsq *sq);
 
-static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_tx_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
-	return session->ds_count == max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+	return session->ds_count == session->ds_count_max;
 }
 
 static inline void mlx5e_rqwq_reset(struct mlx5e_rq *rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
index 70c6f0b2abb92..5ce1b463b7a8d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c
@@ -390,6 +390,7 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq)
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = sq->max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = mlx5e_xdp_get_inline_state(sq, session->inline_on),
 	};
@@ -501,7 +502,7 @@ mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, struct mlx5e_xmit_data *xdptx
 
 	mlx5e_xdp_mpwqe_add_dseg(sq, p, stats);
 
-	if (unlikely(mlx5e_xdp_mpwqe_is_full(session, sq->max_sq_mpw_wqebbs)))
+	if (unlikely(mlx5e_xdp_mpwqe_is_full(session)))
 		mlx5e_xdp_mpwqe_complete(sq);
 
 	stats->xmit++;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
index e054db1e10f8a..446e492c6bb8e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h
@@ -182,13 +182,13 @@ static inline bool mlx5e_xdp_get_inline_state(struct mlx5e_xdpsq *sq, bool cur)
 	return cur;
 }
 
-static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session, u8 max_sq_mpw_wqebbs)
+static inline bool mlx5e_xdp_mpwqe_is_full(struct mlx5e_tx_mpwqe *session)
 {
 	if (session->inline_on)
 		return session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT >
-		       max_sq_mpw_wqebbs * MLX5_SEND_WQEBB_NUM_DS;
+		       session->ds_count_max;
 
-	return mlx5e_tx_mpwqe_is_full(session, max_sq_mpw_wqebbs);
+	return mlx5e_tx_mpwqe_is_full(session);
 }
 
 struct mlx5e_xdp_wqe_info {
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index f8c7912abe0e3..4fd853d19e313 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -525,9 +525,9 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 {
 	struct mlx5e_tx_mpwqe *session = &sq->mpwqe;
 	struct mlx5e_tx_wqe *wqe;
-	u16 pi;
+	u16 pi, num_wqebbs;
 
-	pi = mlx5e_txqsq_get_next_pi(sq, sq->max_sq_mpw_wqebbs);
+	pi = mlx5e_txqsq_get_next_pi_anysize(sq, &num_wqebbs);
 	wqe = MLX5E_TX_FETCH_WQE(sq, pi);
 	net_prefetchw(wqe->data);
 
@@ -535,6 +535,7 @@ static void mlx5e_tx_mpwqe_session_start(struct mlx5e_txqsq *sq,
 		.wqe = wqe,
 		.bytes_count = 0,
 		.ds_count = MLX5E_TX_WQE_EMPTY_DS_COUNT,
+		.ds_count_max = num_wqebbs * MLX5_SEND_WQEBB_NUM_DS,
 		.pkt_count = 0,
 		.inline_on = 0,
 	};
@@ -626,7 +627,7 @@ mlx5e_sq_xmit_mpwqe(struct mlx5e_txqsq *sq, struct sk_buff *skb,
 	mlx5e_tx_mpwqe_add_dseg(sq, &txd);
 	mlx5e_tx_skb_update_hwts_flags(skb);
 
-	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe, sq->max_sq_mpw_wqebbs))) {
+	if (unlikely(mlx5e_tx_mpwqe_is_full(&sq->mpwqe))) {
 		/* Might stop the queue and affect the retval of __netdev_tx_sent_queue. */
 		cseg = mlx5e_tx_mpwqe_session_complete(sq);
 

From d8129171e9ae0bc6b8ee051d891e06071c7c9963 Mon Sep 17 00:00:00 2001
From: Sudeep Holla <sudeep.holla@arm.com>
Date: Wed, 19 Mar 2025 13:52:09 +0000
Subject: [PATCH 2653/2753] net: phy: fixed_phy: transition to the faux device
 interface

The net fixed phy driver does not require the creation of a platform
device. Originally, this approach was chosen for simplicity when the
driver was first implemented.

With the introduction of the lightweight faux device interface, we now
have a more appropriate alternative. Migrate the device to utilize the
faux bus, given that the platform device it previously created was not
a real one anyway. This will get rid of the fake platform device.

Cc: Andrew Lunn <andrew@lunn.ch>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/fixed_phy.c | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/drivers/net/phy/fixed_phy.c b/drivers/net/phy/fixed_phy.c
index aef739c20ac4d..ee7831a9849b3 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -10,7 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/platform_device.h>
+#include <linux/device/faux.h>
 #include <linux/list.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
@@ -40,7 +40,7 @@ struct fixed_phy {
 	struct gpio_desc *link_gpiod;
 };
 
-static struct platform_device *pdev;
+static struct faux_device *fdev;
 static struct fixed_mdio_bus platform_fmb = {
 	.phys = LIST_HEAD_INIT(platform_fmb.phys),
 };
@@ -337,9 +337,9 @@ static int __init fixed_mdio_bus_init(void)
 	struct fixed_mdio_bus *fmb = &platform_fmb;
 	int ret;
 
-	pdev = platform_device_register_simple("Fixed MDIO bus", 0, NULL, 0);
-	if (IS_ERR(pdev))
-		return PTR_ERR(pdev);
+	fdev = faux_device_create("Fixed MDIO bus", NULL, NULL);
+	if (!fdev)
+		return -ENODEV;
 
 	fmb->mii_bus = mdiobus_alloc();
 	if (fmb->mii_bus == NULL) {
@@ -350,7 +350,7 @@ static int __init fixed_mdio_bus_init(void)
 	snprintf(fmb->mii_bus->id, MII_BUS_ID_SIZE, "fixed-0");
 	fmb->mii_bus->name = "Fixed MDIO Bus";
 	fmb->mii_bus->priv = fmb;
-	fmb->mii_bus->parent = &pdev->dev;
+	fmb->mii_bus->parent = &fdev->dev;
 	fmb->mii_bus->read = &fixed_mdio_read;
 	fmb->mii_bus->write = &fixed_mdio_write;
 	fmb->mii_bus->phy_mask = ~0;
@@ -364,7 +364,7 @@ static int __init fixed_mdio_bus_init(void)
 err_mdiobus_alloc:
 	mdiobus_free(fmb->mii_bus);
 err_mdiobus_reg:
-	platform_device_unregister(pdev);
+	faux_device_destroy(fdev);
 	return ret;
 }
 module_init(fixed_mdio_bus_init);
@@ -376,7 +376,7 @@ static void __exit fixed_mdio_bus_exit(void)
 
 	mdiobus_unregister(fmb->mii_bus);
 	mdiobus_free(fmb->mii_bus);
-	platform_device_unregister(pdev);
+	faux_device_destroy(fdev);
 
 	list_for_each_entry_safe(fp, tmp, &fmb->phys, node) {
 		list_del(&fp->node);

From cc7af88197418f84fc60925aef29f1d8053a0744 Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Wed, 19 Mar 2025 16:02:59 +0200
Subject: [PATCH 2654/2753] net/mlx5: Lag, use port selection tables when
 available

As queue affinity is being deprecated and will no longer be supported
in the future, Always check for the presence of the port selection
namespace. When available, leverage it to distribute traffic
across the physical ports via steering, ensuring compatibility with
future NICs.

Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Maor Gottlieb <maorg@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/lag/lag.c | 38 +++++--------------
 1 file changed, 9 insertions(+), 29 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 6c9737c537348..54642a8c2b35a 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -584,8 +584,9 @@ void mlx5_modify_lag(struct mlx5_lag *ldev,
 	}
 }
 
-static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
-					   unsigned long *flags)
+static int mlx5_lag_set_port_sel_mode(struct mlx5_lag *ldev,
+				      enum mlx5_lag_mode mode,
+				      unsigned long *flags)
 {
 	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
 	struct mlx5_core_dev *dev0;
@@ -593,7 +594,12 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	if (first_idx < 0)
 		return -EINVAL;
 
+	if (mode == MLX5_LAG_MODE_MPESW ||
+	    mode == MLX5_LAG_MODE_MULTIPATH)
+		return 0;
+
 	dev0 = ldev->pf[first_idx].dev;
+
 	if (!MLX5_CAP_PORT_SELECTION(dev0, port_select_flow_table)) {
 		if (ldev->ports > 2)
 			return -EINVAL;
@@ -608,32 +614,10 @@ static int mlx5_lag_set_port_sel_mode_roce(struct mlx5_lag *ldev,
 	return 0;
 }
 
-static void mlx5_lag_set_port_sel_mode_offloads(struct mlx5_lag *ldev,
-						struct lag_tracker *tracker,
-						enum mlx5_lag_mode mode,
-						unsigned long *flags)
-{
-	int first_idx = mlx5_lag_get_dev_index_by_seq(ldev, MLX5_LAG_P1);
-	struct lag_func *dev0;
-
-	if (first_idx < 0 || mode == MLX5_LAG_MODE_MPESW)
-		return;
-
-	dev0 = &ldev->pf[first_idx];
-	if (MLX5_CAP_PORT_SELECTION(dev0->dev, port_select_flow_table) &&
-	    tracker->tx_type == NETDEV_LAG_TX_TYPE_HASH) {
-		if (ldev->ports > 2)
-			ldev->buckets = MLX5_LAG_MAX_HASH_BUCKETS;
-		set_bit(MLX5_LAG_MODE_FLAG_HASH_BASED, flags);
-	}
-}
-
 static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 			      struct lag_tracker *tracker, bool shared_fdb,
 			      unsigned long *flags)
 {
-	bool roce_lag = mode == MLX5_LAG_MODE_ROCE;
-
 	*flags = 0;
 	if (shared_fdb) {
 		set_bit(MLX5_LAG_MODE_FLAG_SHARED_FDB, flags);
@@ -643,11 +627,7 @@ static int mlx5_lag_set_flags(struct mlx5_lag *ldev, enum mlx5_lag_mode mode,
 	if (mode == MLX5_LAG_MODE_MPESW)
 		set_bit(MLX5_LAG_MODE_FLAG_FDB_SEL_MODE_NATIVE, flags);
 
-	if (roce_lag)
-		return mlx5_lag_set_port_sel_mode_roce(ldev, flags);
-
-	mlx5_lag_set_port_sel_mode_offloads(ldev, tracker, mode, flags);
-	return 0;
+	return mlx5_lag_set_port_sel_mode(ldev, mode, flags);
 }
 
 char *mlx5_get_str_port_sel_mode(enum mlx5_lag_mode mode, unsigned long flags)

From bc5d041b2891b48710254fd622709c7b3c058eeb Mon Sep 17 00:00:00 2001
From: Amir Tzin <amirtz@nvidia.com>
Date: Wed, 19 Mar 2025 16:03:00 +0200
Subject: [PATCH 2655/2753] net/mlx5: fw reset, check bridge accessibility at
 earlier stage

Currently, mlx5_is_reset_now_capable() checks whether the pci bridge is
accessible only on bridge hot plug capability check.  If the pci bridge
is not accessible, reset now will fail regardless of bridge hotplug
capability. Move this check to function mlx5_is_reset_now_capable()
which, in such case, aborts the reset and does so in the request phase
instead of the reset now phase.

Signed-off-by: Aya Levin <ayal@nvidia.com>
Signed-off-by: Moshe Shemesh <moshe@nvidia.com>
Signed-off-by: Amir Tzin <amirtz@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/fw_reset.c    | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
index 566710d34a7b2..6830a49fe682e 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
@@ -345,15 +345,12 @@ static void mlx5_fw_live_patch_event(struct work_struct *work)
 }
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
-static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev)
+static int mlx5_check_hotplug_interrupt(struct mlx5_core_dev *dev,
+					struct pci_dev *bridge)
 {
-	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 reg16;
 	int err;
 
-	if (!bridge)
-		return -EOPNOTSUPP;
-
 	err = pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &reg16);
 	if (err)
 		return err;
@@ -416,9 +413,15 @@ static int mlx5_check_dev_ids(struct mlx5_core_dev *dev, u16 dev_id)
 static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 				      u8 reset_method)
 {
+	struct pci_dev *bridge = dev->pdev->bus->self;
 	u16 dev_id;
 	int err;
 
+	if (!bridge) {
+		mlx5_core_warn(dev, "PCI bus bridge is not accessible\n");
+		return false;
+	}
+
 	if (!MLX5_CAP_GEN(dev, fast_teardown)) {
 		mlx5_core_warn(dev, "fast teardown is not supported by firmware\n");
 		return false;
@@ -426,7 +429,7 @@ static bool mlx5_is_reset_now_capable(struct mlx5_core_dev *dev,
 
 #if IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)
 	if (reset_method != MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET) {
-		err = mlx5_check_hotplug_interrupt(dev);
+		err = mlx5_check_hotplug_interrupt(dev, bridge);
 		if (err)
 			return false;
 	}

From 35d629f0cc4a3ee4034d7dde02627b690f29f5ad Mon Sep 17 00:00:00 2001
From: Shay Drory <shayd@nvidia.com>
Date: Wed, 19 Mar 2025 16:03:01 +0200
Subject: [PATCH 2656/2753] net/mlx5: Update pfnum retrieval for devlink port
 attributes

Align mlx5 driver usage of 'pfnum' with the documentation clarification
introduced in commit bb70b0d48d8e ("devlink: Improve the port attributes
description").

Signed-off-by: Shay Drory <shayd@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c | 4 ++--
 drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c       | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
index 982fe37146834..b7102e14d23d3 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/devlink_port.c
@@ -32,7 +32,7 @@ static void mlx5_esw_offloads_pf_vf_devlink_port_attrs_set(struct mlx5_eswitch *
 	u16 pfnum;
 
 	mlx5_esw_get_port_parent_id(dev, &ppid);
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	external = mlx5_core_is_ecpf_esw_manager(dev);
 	if (external)
 		controller_num = dev->priv.eswitch->offloads.host_number + 1;
@@ -110,7 +110,7 @@ static void mlx5_esw_offloads_sf_devlink_port_attrs_set(struct mlx5_eswitch *esw
 	struct netdev_phys_item_id ppid = {};
 	u16 pfnum;
 
-	pfnum = mlx5_get_dev_index(dev);
+	pfnum = PCI_FUNC(dev->pdev->devfn);
 	mlx5_esw_get_port_parent_id(dev, &ppid);
 	memcpy(dl_port->attrs.switch_id.id, &ppid.id[0], ppid.id_len);
 	dl_port->attrs.switch_id.id_len = ppid.id_len;
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
index b96909fbeb12d..0864ba625c07d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/devlink.c
@@ -285,7 +285,7 @@ mlx5_sf_new_check_attr(struct mlx5_core_dev *dev, const struct devlink_port_new_
 		NL_SET_ERR_MSG_MOD(extack, "External controller is unsupported");
 		return -EOPNOTSUPP;
 	}
-	if (new_attr->pfnum != mlx5_get_dev_index(dev)) {
+	if (new_attr->pfnum != PCI_FUNC(dev->pdev->devfn)) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid pfnum supplied");
 		return -EOPNOTSUPP;
 	}

From a05ffc33ebbb7345372ea153510fe9e3b40d5a38 Mon Sep 17 00:00:00 2001
From: Paul Blakey <paulb@nvidia.com>
Date: Wed, 19 Mar 2025 16:03:02 +0200
Subject: [PATCH 2657/2753] net/mlx5e: CT: Filter legacy rules that are
 unrelated to nic

In nic mode CT setup where we do hairpin between the two
nics, both nics register to the same flow table (per zone),
and try to offload all rules on it.

Instead, filter the rules that originated from the relevant nic
(so only one side is offloaded for each nic).

Signed-off-by: Paul Blakey <paulb@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/mellanox/mlx5/core/en/tc_ct.c    | 29 +++++++++++++++++++
 1 file changed, 29 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
index a065e8fafb1d1..81332cd4a5824 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
@@ -1349,6 +1349,32 @@ mlx5_tc_ct_block_flow_offload_stats(struct mlx5_ct_ft *ft,
 	return 0;
 }
 
+static bool
+mlx5_tc_ct_filter_legacy_non_nic_flows(struct mlx5_ct_ft *ft,
+				       struct flow_cls_offload *flow)
+{
+	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
+	struct mlx5_tc_ct_priv *ct_priv = ft->ct_priv;
+	struct flow_match_meta match;
+	struct net_device *netdev;
+	bool same_dev = false;
+
+	if (!is_mdev_legacy_mode(ct_priv->dev) ||
+	    !flow_rule_match_key(rule, FLOW_DISSECTOR_KEY_META))
+		return true;
+
+	flow_rule_match_meta(rule, &match);
+
+	if (!(match.key->ingress_ifindex & match.mask->ingress_ifindex))
+		return true;
+
+	netdev = dev_get_by_index(&init_net, match.key->ingress_ifindex);
+	same_dev = ct_priv->netdev == netdev;
+	dev_put(netdev);
+
+	return same_dev;
+}
+
 static int
 mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 			      void *cb_priv)
@@ -1361,6 +1387,9 @@ mlx5_tc_ct_block_flow_offload(enum tc_setup_type type, void *type_data,
 
 	switch (f->command) {
 	case FLOW_CLS_REPLACE:
+		if (!mlx5_tc_ct_filter_legacy_non_nic_flows(ft, f))
+			return -EOPNOTSUPP;
+
 		return mlx5_tc_ct_block_flow_offload_add(ft, f);
 	case FLOW_CLS_DESTROY:
 		return mlx5_tc_ct_block_flow_offload_del(ft, f);

From 0979ceb8908bd3ee97f906cac8ef92fb8e227157 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Wed, 19 Mar 2025 16:03:03 +0200
Subject: [PATCH 2658/2753] net/mlx5e: TC, Don't offload CT commit if it's the
 last action

For CT action with commit argument, it's usually followed by the
forward action, either to the output netdev or next chain. The default
behavior for software is to drop by setting action attribute to
TC_ACT_SHOT instead of TC_ACT_PIPE if it's the last action. But driver
can't handle it, so block the offload for such case.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Roi Dayan <roid@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c    | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
index feeb41693c176..b6cabe829f198 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc/act/ct.c
@@ -5,6 +5,16 @@
 #include "en/tc_priv.h"
 #include "en/tc_ct.h"
 
+static bool
+tc_act_can_offload_ct(struct mlx5e_tc_act_parse_state *parse_state,
+		      const struct flow_action_entry *act,
+		      int act_index,
+		      struct mlx5_flow_attr *attr)
+{
+	return !((act->ct.action & TCA_CT_ACT_COMMIT) &&
+		 flow_action_is_last_entry(parse_state->flow_action, act));
+}
+
 static int
 tc_act_parse_ct(struct mlx5e_tc_act_parse_state *parse_state,
 		const struct flow_action_entry *act,
@@ -56,6 +66,7 @@ tc_act_is_missable_ct(const struct flow_action_entry *act)
 }
 
 struct mlx5e_tc_act mlx5e_tc_act_ct = {
+	.can_offload = tc_act_can_offload_ct,
 	.parse_action = tc_act_parse_ct,
 	.post_parse = tc_act_post_parse_ct,
 	.is_multi_table_act = tc_act_is_multi_table_act_ct,

From 05ae95e588797d8799b808982be9d0777455ab63 Mon Sep 17 00:00:00 2001
From: Zdenek Bouska <zdenek.bouska@siemens.com>
Date: Wed, 19 Mar 2025 15:18:48 +0100
Subject: [PATCH 2659/2753] igc: Fix TX drops in XDP ZC

Fixes TX frame drops in AF_XDP zero copy mode when budget < 4.
xsk_tx_peek_desc() consumed TX frame and it was ignored because of
low budget. Not even AF_XDP completion was done for dropped frames.

It can be reproduced on i226 by sending 100000x 60 B frames with
launch time set to minimal IPG (672 ns between starts of frames)
on 1Gbit/s. Always 1026 frames are not sent and are missing a
completion.

Fixes: 9acf59a752d4c ("igc: Enable TX via AF_XDP zero-copy")
Signed-off-by: Zdenek Bouska <zdenek.bouska@siemens.com>
Reviewed-by: Song Yoong Siang <yoong.siang.song@intel.com>
Reviewed-by: Florian Bezdeka <florian.bezdeka@siemens.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/igc/igc_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index 472f009630c98..f2e0a30a34973 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -3042,7 +3042,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	 * descriptors. Therefore, to be safe, we always ensure we have at least
 	 * 4 descriptors available.
 	 */
-	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget >= 4) {
+	while (budget >= 4 && xsk_tx_peek_desc(pool, &xdp_desc)) {
 		struct igc_metadata_request meta_req;
 		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;

From b4b8ce9d8cad34d196450dd873a47228e4d80ed3 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 19 Mar 2025 10:02:44 -0700
Subject: [PATCH 2660/2753] netpoll: Eliminate redundant assignment

The assignment of zero to udph->check is unnecessary as it is
immediately overwritten in the subsequent line. Remove the redundant
assignment.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Joe Damato <jdamato@fastly.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/netpoll.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 7bc75a4ef5d2a..4ddb7490df4b8 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -433,7 +433,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 	udph->len = htons(udp_len);
 
 	if (np->ipv6) {
-		udph->check = 0;
 		udph->check = csum_ipv6_magic(&np->local_ip.in6,
 					      &np->remote_ip.in6,
 					      udp_len, IPPROTO_UDP,

From 336f2694971a13862a6686fdb857e76645c1335d Mon Sep 17 00:00:00 2001
From: Nikhil Jha <njha@janestreet.com>
Date: Wed, 19 Mar 2025 13:02:39 -0400
Subject: [PATCH 2661/2753] sunrpc: implement rfc2203 rpcsec_gss seqnum cache

This implements a sequence number cache of the last three (right now
hardcoded) sent sequence numbers for a given XID, as suggested by the
RFC.

>From RFC2203 5.3.3.1:

"Note that the sequence number algorithm requires that the client
increment the sequence number even if it is retrying a request with
the same RPC transaction identifier.  It is not infrequent for
clients to get into a situation where they send two or more attempts
and a slow server sends the reply for the first attempt. With
RPCSEC_GSS, each request and reply will have a unique sequence
number. If the client wishes to improve turn around time on the RPC
call, it can cache the RPCSEC_GSS sequence number of each request it
sends. Then when it receives a response with a matching RPC
transaction identifier, it can compute the checksum of each sequence
number in the cache to try to match the checksum in the reply's
verifier."

Signed-off-by: Nikhil Jha <njha@janestreet.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/sunrpc/xprt.h    | 17 +++++++++-
 include/trace/events/rpcgss.h  |  4 +--
 include/trace/events/sunrpc.h  |  2 +-
 net/sunrpc/auth_gss/auth_gss.c | 59 +++++++++++++++++++++-------------
 net/sunrpc/xprt.c              |  3 +-
 5 files changed, 57 insertions(+), 28 deletions(-)

diff --git a/include/linux/sunrpc/xprt.h b/include/linux/sunrpc/xprt.h
index 81b952649d35e..f46d1fb8f71ae 100644
--- a/include/linux/sunrpc/xprt.h
+++ b/include/linux/sunrpc/xprt.h
@@ -30,6 +30,8 @@
 #define RPC_MAXCWND(xprt)	((xprt)->max_reqs << RPC_CWNDSHIFT)
 #define RPCXPRT_CONGESTED(xprt) ((xprt)->cong >= (xprt)->cwnd)
 
+#define RPC_GSS_SEQNO_ARRAY_SIZE 3U
+
 enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
@@ -66,7 +68,8 @@ struct rpc_rqst {
 	struct rpc_cred *	rq_cred;	/* Bound cred */
 	__be32			rq_xid;		/* request XID */
 	int			rq_cong;	/* has incremented xprt->cong */
-	u32			rq_seqno;	/* gss seq no. used on req. */
+	u32			rq_seqnos[RPC_GSS_SEQNO_ARRAY_SIZE];	/* past gss req seq nos. */
+	unsigned int		rq_seqno_count;	/* number of entries in rq_seqnos */
 	int			rq_enc_pages_num;
 	struct page		**rq_enc_pages;	/* scratch pages for use by
 						   gss privacy code */
@@ -119,6 +122,18 @@ struct rpc_rqst {
 #define rq_svec			rq_snd_buf.head
 #define rq_slen			rq_snd_buf.len
 
+static inline int xprt_rqst_add_seqno(struct rpc_rqst *req, u32 seqno)
+{
+	if (likely(req->rq_seqno_count < RPC_GSS_SEQNO_ARRAY_SIZE))
+		req->rq_seqno_count++;
+
+	/* Shift array to make room for the newest element at the beginning */
+	memmove(&req->rq_seqnos[1], &req->rq_seqnos[0],
+		(RPC_GSS_SEQNO_ARRAY_SIZE - 1) * sizeof(req->rq_seqnos[0]));
+	req->rq_seqnos[0] = seqno;
+	return 0;
+}
+
 /* RPC transport layer security policies */
 enum xprtsec_policies {
 	RPC_XPRTSEC_NONE = 0,
diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
index b0b6300a0cabd..8aeae06cf434d 100644
--- a/include/trace/events/rpcgss.h
+++ b/include/trace/events/rpcgss.h
@@ -409,7 +409,7 @@ TRACE_EVENT(rpcgss_seqno,
 		__entry->task_id = task->tk_pid;
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 	),
 
 	TP_printk(SUNRPC_TRACE_TASK_SPECIFIER " xid=0x%08x seqno=%u",
@@ -440,7 +440,7 @@ TRACE_EVENT(rpcgss_need_reencode,
 		__entry->client_id = task->tk_client->cl_clid;
 		__entry->xid = be32_to_cpu(task->tk_rqstp->rq_xid);
 		__entry->seq_xmit = seq_xmit;
-		__entry->seqno = task->tk_rqstp->rq_seqno;
+		__entry->seqno = *task->tk_rqstp->rq_seqnos;
 		__entry->ret = ret;
 	),
 
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index 851841336ee65..bb01a0ca93aa7 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1099,7 +1099,7 @@ TRACE_EVENT(xprt_transmit,
 		__entry->client_id = rqst->rq_task->tk_client ?
 			rqst->rq_task->tk_client->cl_clid : -1;
 		__entry->xid = be32_to_cpu(rqst->rq_xid);
-		__entry->seqno = rqst->rq_seqno;
+		__entry->seqno = *rqst->rq_seqnos;
 		__entry->status = status;
 	),
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 369310909fc98..0fa244f16876f 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -1545,6 +1545,7 @@ static int gss_marshal(struct rpc_task *task, struct xdr_stream *xdr)
 	struct kvec	iov;
 	struct xdr_buf	verf_buf;
 	int status;
+	u32 seqno;
 
 	/* Credential */
 
@@ -1556,15 +1557,16 @@ static int gss_marshal(struct rpc_task *task, struct xdr_stream *xdr)
 	cred_len = p++;
 
 	spin_lock(&ctx->gc_seq_lock);
-	req->rq_seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ;
+	seqno = (ctx->gc_seq < MAXSEQ) ? ctx->gc_seq++ : MAXSEQ;
+	xprt_rqst_add_seqno(req, seqno);
 	spin_unlock(&ctx->gc_seq_lock);
-	if (req->rq_seqno == MAXSEQ)
+	if (*req->rq_seqnos == MAXSEQ)
 		goto expired;
 	trace_rpcgss_seqno(task);
 
 	*p++ = cpu_to_be32(RPC_GSS_VERSION);
 	*p++ = cpu_to_be32(ctx->gc_proc);
-	*p++ = cpu_to_be32(req->rq_seqno);
+	*p++ = cpu_to_be32(*req->rq_seqnos);
 	*p++ = cpu_to_be32(gss_cred->gc_service);
 	p = xdr_encode_netobj(p, &ctx->gc_wire_ctx);
 	*cred_len = cpu_to_be32((p - (cred_len + 1)) << 2);
@@ -1678,17 +1680,31 @@ gss_refresh_null(struct rpc_task *task)
 	return 0;
 }
 
+static u32
+gss_validate_seqno_mic(struct gss_cl_ctx *ctx, u32 seqno, __be32 *seq, __be32 *p, u32 len)
+{
+	struct kvec iov;
+	struct xdr_buf verf_buf;
+	struct xdr_netobj mic;
+
+	*seq = cpu_to_be32(seqno);
+	iov.iov_base = seq;
+	iov.iov_len = 4;
+	xdr_buf_from_iov(&iov, &verf_buf);
+	mic.data = (u8 *)p;
+	mic.len = len;
+	return gss_verify_mic(ctx->gc_gss_ctx, &verf_buf, &mic);
+}
+
 static int
 gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
 {
 	struct rpc_cred *cred = task->tk_rqstp->rq_cred;
 	struct gss_cl_ctx *ctx = gss_cred_get_ctx(cred);
 	__be32		*p, *seq = NULL;
-	struct kvec	iov;
-	struct xdr_buf	verf_buf;
-	struct xdr_netobj mic;
 	u32		len, maj_stat;
 	int		status;
+	int		i = 1; /* don't recheck the first item */
 
 	p = xdr_inline_decode(xdr, 2 * sizeof(*p));
 	if (!p)
@@ -1705,13 +1721,10 @@ gss_validate(struct rpc_task *task, struct xdr_stream *xdr)
 	seq = kmalloc(4, GFP_KERNEL);
 	if (!seq)
 		goto validate_failed;
-	*seq = cpu_to_be32(task->tk_rqstp->rq_seqno);
-	iov.iov_base = seq;
-	iov.iov_len = 4;
-	xdr_buf_from_iov(&iov, &verf_buf);
-	mic.data = (u8 *)p;
-	mic.len = len;
-	maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &verf_buf, &mic);
+	maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[0], seq, p, len);
+	/* RFC 2203 5.3.3.1 - compute the checksum of each sequence number in the cache */
+	while (unlikely(maj_stat == GSS_S_BAD_SIG && i < task->tk_rqstp->rq_seqno_count))
+		maj_stat = gss_validate_seqno_mic(ctx, task->tk_rqstp->rq_seqnos[i], seq, p, len);
 	if (maj_stat == GSS_S_CONTEXT_EXPIRED)
 		clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags);
 	if (maj_stat)
@@ -1750,7 +1763,7 @@ gss_wrap_req_integ(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
 	if (!p)
 		goto wrap_failed;
 	integ_len = p++;
-	*p = cpu_to_be32(rqstp->rq_seqno);
+	*p = cpu_to_be32(*rqstp->rq_seqnos);
 
 	if (rpcauth_wrap_req_encode(task, xdr))
 		goto wrap_failed;
@@ -1847,7 +1860,7 @@ gss_wrap_req_priv(struct rpc_cred *cred, struct gss_cl_ctx *ctx,
 	if (!p)
 		goto wrap_failed;
 	opaque_len = p++;
-	*p = cpu_to_be32(rqstp->rq_seqno);
+	*p = cpu_to_be32(*rqstp->rq_seqnos);
 
 	if (rpcauth_wrap_req_encode(task, xdr))
 		goto wrap_failed;
@@ -2001,7 +2014,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
 	offset = rcv_buf->len - xdr_stream_remaining(xdr);
 	if (xdr_stream_decode_u32(xdr, &seqno))
 		goto unwrap_failed;
-	if (seqno != rqstp->rq_seqno)
+	if (seqno != *rqstp->rq_seqnos)
 		goto bad_seqno;
 	if (xdr_buf_subsegment(rcv_buf, &gss_data, offset, len))
 		goto unwrap_failed;
@@ -2045,7 +2058,7 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred,
 	trace_rpcgss_unwrap_failed(task);
 	goto out;
 bad_seqno:
-	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, seqno);
+	trace_rpcgss_bad_seqno(task, *rqstp->rq_seqnos, seqno);
 	goto out;
 bad_mic:
 	trace_rpcgss_verify_mic(task, maj_stat);
@@ -2077,7 +2090,7 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	if (maj_stat != GSS_S_COMPLETE)
 		goto bad_unwrap;
 	/* gss_unwrap decrypted the sequence number */
-	if (be32_to_cpup(p++) != rqstp->rq_seqno)
+	if (be32_to_cpup(p++) != *rqstp->rq_seqnos)
 		goto bad_seqno;
 
 	/* gss_unwrap redacts the opaque blob from the head iovec.
@@ -2093,7 +2106,7 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred,
 	trace_rpcgss_unwrap_failed(task);
 	return -EIO;
 bad_seqno:
-	trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, be32_to_cpup(--p));
+	trace_rpcgss_bad_seqno(task, *rqstp->rq_seqnos, be32_to_cpup(--p));
 	return -EIO;
 bad_unwrap:
 	trace_rpcgss_unwrap(task, maj_stat);
@@ -2118,14 +2131,14 @@ gss_xmit_need_reencode(struct rpc_task *task)
 	if (!ctx)
 		goto out;
 
-	if (gss_seq_is_newer(req->rq_seqno, READ_ONCE(ctx->gc_seq)))
+	if (gss_seq_is_newer(*req->rq_seqnos, READ_ONCE(ctx->gc_seq)))
 		goto out_ctx;
 
 	seq_xmit = READ_ONCE(ctx->gc_seq_xmit);
-	while (gss_seq_is_newer(req->rq_seqno, seq_xmit)) {
+	while (gss_seq_is_newer(*req->rq_seqnos, seq_xmit)) {
 		u32 tmp = seq_xmit;
 
-		seq_xmit = cmpxchg(&ctx->gc_seq_xmit, tmp, req->rq_seqno);
+		seq_xmit = cmpxchg(&ctx->gc_seq_xmit, tmp, *req->rq_seqnos);
 		if (seq_xmit == tmp) {
 			ret = false;
 			goto out_ctx;
@@ -2134,7 +2147,7 @@ gss_xmit_need_reencode(struct rpc_task *task)
 
 	win = ctx->gc_win;
 	if (win > 0)
-		ret = !gss_seq_is_newer(req->rq_seqno, seq_xmit - win);
+		ret = !gss_seq_is_newer(*req->rq_seqnos, seq_xmit - win);
 
 out_ctx:
 	gss_put_ctx(ctx);
diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c
index 09f245cda5262..395bdfdaf4313 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -1365,7 +1365,7 @@ xprt_request_enqueue_transmit(struct rpc_task *task)
 				INIT_LIST_HEAD(&req->rq_xmit2);
 				goto out;
 			}
-		} else if (!req->rq_seqno) {
+		} else if (req->rq_seqno_count == 0) {
 			list_for_each_entry(pos, &xprt->xmit_queue, rq_xmit) {
 				if (pos->rq_task->tk_owner != task->tk_owner)
 					continue;
@@ -1898,6 +1898,7 @@ xprt_request_init(struct rpc_task *task)
 	req->rq_snd_buf.bvec = NULL;
 	req->rq_rcv_buf.bvec = NULL;
 	req->rq_release_snd_buf = NULL;
+	req->rq_seqno_count = 0;
 	xprt_init_majortimeo(task, req, task->tk_client->cl_timeout);
 
 	trace_xprt_reserve(req);

From 869c5525a33f848812bddd36edf0e427691a851c Mon Sep 17 00:00:00 2001
From: Nikhil Jha <njha@janestreet.com>
Date: Wed, 19 Mar 2025 13:02:40 -0400
Subject: [PATCH 2662/2753] sunrpc: don't immediately retransmit on seqno miss

RFC2203 requires that retransmitted messages use a new gss sequence
number, but the same XID. This means that if the server is just slow
(e.x. overloaded), the client might receive a response using an older
seqno than the one it has recorded.

Currently, Linux's client immediately retransmits in this case. However,
this leads to a lot of wasted retransmits until the server eventually
responds faster than the client can resend.

Client -> SEQ 1 -> Server
Client -> SEQ 2 -> Server
Client <- SEQ 1 <- Server (misses, expecting seqno = 2)
Client -> SEQ 3 -> Server (immediate retransmission on miss)
Client <- SEQ 2 <- Server (misses, expecting seqno = 3)
Client -> SEQ 4 -> Server (immediate retransmission on miss)
... and so on ...

This commit makes it so that we ignore messages with bad checksums
due to seqnum mismatch, and rely on the usual timeout behavior for
retransmission instead of doing so immediately.

Signed-off-by: Nikhil Jha <njha@janestreet.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sunrpc/clnt.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 2fe88ea79a70c..98c0880ec18a8 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -2760,8 +2760,13 @@ rpc_decode_header(struct rpc_task *task, struct xdr_stream *xdr)
 	case -EPROTONOSUPPORT:
 		goto out_err;
 	case -EACCES:
-		/* Re-encode with a fresh cred */
-		fallthrough;
+		/* possible RPCSEC_GSS out-of-sequence event (RFC2203),
+		 * reset recv state and keep waiting, don't retransmit
+		 */
+		task->tk_rqstp->rq_reply_bytes_recvd = 0;
+		task->tk_status = xprt_request_enqueue_receive(task);
+		task->tk_action = call_transmit_status;
+		return -EBADMSG;
 	default:
 		goto out_garbage;
 	}

From 50206bc5b10553d38c4c580f58f0da1b9c758ad8 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Wed, 19 Mar 2025 10:46:25 -0700
Subject: [PATCH 2663/2753] net: phylink: Remove unused function pointer from
 phylink structure

From what I can tell the get_fixed_state pointer in the phylink structure
hasn't been used since commit <5c05c1dbb177> ("net: phylink, dsa: eliminate
phylink_fixed_state_cb()") . Since I can't find any users for it we might
as well just drop the pointer.

Fixes: 5c05c1dbb177 ("net: phylink, dsa: eliminate phylink_fixed_state_cb()")
Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/phylink.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 0f70a7f3dfccd..16a1f31f00911 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -72,8 +72,6 @@ struct phylink {
 	struct gpio_desc *link_gpio;
 	unsigned int link_irq;
 	struct timer_list link_poll;
-	void (*get_fixed_state)(struct net_device *dev,
-				struct phylink_link_state *s);
 
 	struct mutex state_mutex;
 	struct phylink_link_state phy_state;

From 374fe175f47e1873b646e8850c8c1820f9ea52e6 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Wed, 19 Mar 2025 21:23:17 +0200
Subject: [PATCH 2664/2753] net/mlx5: Remove NULL check before dev_{put, hold}

Fix coccinelle warnings:
WARNING: NULL check before dev_{put, hold} functions is not needed.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Jianbo Liu <jianbol@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c      | 9 +++------
 .../net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c    | 9 +++------
 drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c        | 3 +--
 3 files changed, 7 insertions(+), 14 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
index 721f35e597579..2162d776fe35d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c
@@ -31,8 +31,7 @@ static void mlx5e_tc_tun_route_attr_cleanup(struct mlx5e_tc_tun_route_attr *attr
 {
 	if (attr->n)
 		neigh_release(attr->n);
-	if (attr->route_dev)
-		dev_put(attr->route_dev);
+	dev_put(attr->route_dev);
 }
 
 struct mlx5e_tc_tunnel *mlx5e_get_tc_tun(struct net_device *tunnel_dev)
@@ -68,16 +67,14 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv,
 	 * while holding rcu read lock. Take the net_device for correctness
 	 * sake.
 	 */
-	if (uplink_upper)
-		dev_hold(uplink_upper);
+	dev_hold(uplink_upper);
 	rcu_read_unlock();
 
 	dst_is_lag_dev = (uplink_upper &&
 			  netif_is_lag_master(uplink_upper) &&
 			  real_dev == uplink_upper &&
 			  mlx5_lag_is_sriov(priv->mdev));
-	if (uplink_upper)
-		dev_put(uplink_upper);
+	dev_put(uplink_upper);
 
 	/* if the egress device isn't on the same HW e-switch or
 	 * it's a LAG device, use the uplink
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
index e7e01f3298efb..a0fc76a1bc082 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun_encap.c
@@ -42,8 +42,7 @@ static int mlx5e_set_int_port_tunnel(struct mlx5e_priv *priv,
 						&attr->action, out_index);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 
 	return err;
 }
@@ -753,8 +752,7 @@ static int mlx5e_set_vf_tunnel(struct mlx5_eswitch *esw,
 	}
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
@@ -788,8 +786,7 @@ static int mlx5e_update_vf_tunnel(struct mlx5_eswitch *esw,
 	mlx5e_tc_match_to_reg_mod_hdr_change(esw->dev, mod_hdr_acts, VPORT_TO_REG, act_id, data);
 
 out:
-	if (route_dev)
-		dev_put(route_dev);
+	dev_put(route_dev);
 	return err;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
index 54642a8c2b35a..d058cbb4a00c7 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
@@ -523,8 +523,7 @@ static struct net_device *mlx5_lag_active_backup_get_netdev(struct mlx5_core_dev
 		ndev = ldev->pf[last_idx].netdev;
 	}
 
-	if (ndev)
-		dev_hold(ndev);
+	dev_hold(ndev);
 
 unlock:
 	spin_unlock_irqrestore(&lag_lock, flags);

From 62c65b22ee2930fcc5c9391a3ff97cfcccb7e1d7 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Wed, 19 Mar 2025 21:23:18 +0200
Subject: [PATCH 2665/2753] net/mlx5e: Use right API to free bitmap memory

Use bitmap_free() to free memory allocated with bitmap_zalloc_node().
This fixes memtrack error:
  mtl rsc inconsistency: memtrack_free: .../drivers/net/ethernet/mellanox/mlx5/core/en_main.c::466: kfree for unknown address=0xFFFF0000CA3619E8, device=0x0

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Reviewed-by: Maher Sanalla <msanalla@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 2edc61328749e..3506024c24539 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -359,7 +359,7 @@ static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node)
 	return 0;
 
 err_nomem:
-	kvfree(shampo->bitmap);
+	bitmap_free(shampo->bitmap);
 	kvfree(shampo->pages);
 
 	return -ENOMEM;
@@ -367,7 +367,7 @@ static int mlx5e_rq_shampo_hd_info_alloc(struct mlx5e_rq *rq, int node)
 
 static void mlx5e_rq_shampo_hd_info_free(struct mlx5e_rq *rq)
 {
-	kvfree(rq->mpwqe.shampo->bitmap);
+	bitmap_free(rq->mpwqe.shampo->bitmap);
 	kvfree(rq->mpwqe.shampo->pages);
 }
 

From 0fab732b4b344ec7a22e1bd1d651c79b76b8bce2 Mon Sep 17 00:00:00 2001
From: Tariq Toukan <tariqt@nvidia.com>
Date: Wed, 19 Mar 2025 21:23:19 +0200
Subject: [PATCH 2666/2753] net/mlx5e: Always select CONFIG_PAGE_POOL_STATS

Always set PAGE_POOL_STATS in mlx5 Eth driver.
Cleanup the corresponding #ifdefs.

Page pool stats are essential to monitor and analyze RX performance.

Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Gal Pressman <gal@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/Kconfig    |  1 +
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.c | 14 --------------
 drivers/net/ethernet/mellanox/mlx5/core/en_stats.h |  4 ----
 3 files changed, 1 insertion(+), 18 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
index bf4015a12b410..6ec7d6e0181de 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig
@@ -31,6 +31,7 @@ config MLX5_CORE_EN
 	bool "Mellanox 5th generation network adapters (ConnectX series) Ethernet support"
 	depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE
 	select PAGE_POOL
+	select PAGE_POOL_STATS
 	select DIMLIB
 	help
 	  Ethernet support in Mellanox Technologies ConnectX-4 NIC.
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
index acb00fd7efa4c..1c121b435016d 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c
@@ -37,9 +37,7 @@
 #include "en/ptp.h"
 #include "en/port.h"
 
-#ifdef CONFIG_PAGE_POOL_STATS
 #include <net/page_pool/helpers.h>
-#endif
 
 void mlx5e_ethtool_put_stat(u64 **data, u64 val)
 {
@@ -196,7 +194,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) },
 #endif
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_fast) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_alloc_slow_high_order) },
@@ -208,7 +205,6 @@ static const struct counter_desc sw_stats_desc[] = {
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_packets) },
 	{ MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_tls_decrypted_bytes) },
@@ -377,7 +373,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_arfs_err                += rq_stats->arfs_err;
 #endif
 	s->rx_recover                 += rq_stats->recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	s->rx_pp_alloc_fast          += rq_stats->pp_alloc_fast;
 	s->rx_pp_alloc_slow          += rq_stats->pp_alloc_slow;
 	s->rx_pp_alloc_empty         += rq_stats->pp_alloc_empty;
@@ -389,7 +384,6 @@ static void mlx5e_stats_grp_sw_update_stats_rq_stats(struct mlx5e_sw_stats *s,
 	s->rx_pp_recycle_ring			+= rq_stats->pp_recycle_ring;
 	s->rx_pp_recycle_ring_full		+= rq_stats->pp_recycle_ring_full;
 	s->rx_pp_recycle_released_ref		+= rq_stats->pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	s->rx_tls_decrypted_packets   += rq_stats->tls_decrypted_packets;
 	s->rx_tls_decrypted_bytes     += rq_stats->tls_decrypted_bytes;
@@ -496,7 +490,6 @@ static void mlx5e_stats_grp_sw_update_stats_qos(struct mlx5e_priv *priv,
 	}
 }
 
-#ifdef CONFIG_PAGE_POOL_STATS
 static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 {
 	struct mlx5e_rq_stats *rq_stats = c->rq.stats;
@@ -519,11 +512,6 @@ static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
 	rq_stats->pp_recycle_ring_full = stats.recycle_stats.ring_full;
 	rq_stats->pp_recycle_released_ref = stats.recycle_stats.released_refcnt;
 }
-#else
-static void mlx5e_stats_update_stats_rq_page_pool(struct mlx5e_channel *c)
-{
-}
-#endif
 
 static MLX5E_DECLARE_STATS_GRP_OP_UPDATE_STATS(sw)
 {
@@ -2131,7 +2119,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) },
 #endif
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) },
-#ifdef CONFIG_PAGE_POOL_STATS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_fast) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_alloc_slow_high_order) },
@@ -2143,7 +2130,6 @@ static const struct counter_desc rq_stats_desc[] = {
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_ring_full) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, pp_recycle_released_ref) },
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_packets) },
 	{ MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, tls_decrypted_bytes) },
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
index 0d87947e348df..8de6fcbd3a033 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h
@@ -215,7 +215,6 @@ struct mlx5e_sw_stats {
 	u64 ch_aff_change;
 	u64 ch_force_irq;
 	u64 ch_eq_rearm;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 rx_pp_alloc_fast;
 	u64 rx_pp_alloc_slow;
 	u64 rx_pp_alloc_slow_high_order;
@@ -227,7 +226,6 @@ struct mlx5e_sw_stats {
 	u64 rx_pp_recycle_ring;
 	u64 rx_pp_recycle_ring_full;
 	u64 rx_pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tx_tls_encrypted_packets;
 	u64 tx_tls_encrypted_bytes;
@@ -385,7 +383,6 @@ struct mlx5e_rq_stats {
 	u64 arfs_err;
 #endif
 	u64 recover;
-#ifdef CONFIG_PAGE_POOL_STATS
 	u64 pp_alloc_fast;
 	u64 pp_alloc_slow;
 	u64 pp_alloc_slow_high_order;
@@ -397,7 +394,6 @@ struct mlx5e_rq_stats {
 	u64 pp_recycle_ring;
 	u64 pp_recycle_ring_full;
 	u64 pp_recycle_released_ref;
-#endif
 #ifdef CONFIG_MLX5_EN_TLS
 	u64 tls_decrypted_packets;
 	u64 tls_decrypted_bytes;

From eae22dae18f5ebfe5a824074900b82cbf04e9c97 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Wed, 19 Mar 2025 20:49:33 +0100
Subject: [PATCH 2667/2753] netfilter: x_tables: Remove unnecessary strscpy()
 size arguments

If the destination buffer has a fixed length, both strscpy_pad() and
strscpy() automatically determine its size using sizeof() when the
argument is omitted. This makes the explicit sizeof() calls unnecessary.
Remove them.

No functional changes intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: NipaLocal <nipa@local>
---
 net/netfilter/x_tables.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 709840612f0df..8607852dadec1 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -766,9 +766,9 @@ void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr,
 
 	msize += off;
 	m->u.user.match_size = msize;
-	strscpy(name, match->name, sizeof(name));
+	strscpy(name, match->name);
 	module_put(match->me);
-	strscpy_pad(m->u.user.name, name, sizeof(m->u.user.name));
+	strscpy_pad(m->u.user.name, name);
 
 	*size += off;
 	*dstptr += msize;
@@ -1147,9 +1147,9 @@ void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr,
 
 	tsize += off;
 	t->u.user.target_size = tsize;
-	strscpy(name, target->name, sizeof(name));
+	strscpy(name, target->name);
 	module_put(target->me);
-	strscpy_pad(t->u.user.name, name, sizeof(t->u.user.name));
+	strscpy_pad(t->u.user.name, name);
 
 	*size += off;
 	*dstptr += tsize;

From e0e9fa2cdab45f8143f40e72a56925bc6d517c49 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 19 Mar 2025 21:25:16 +0000
Subject: [PATCH 2668/2753] ipv6: fix _DEVADD() and _DEVUPD() macros

ip6_rcv_core() is using:

	__IP6_ADD_STATS(net, idev,
			IPSTATS_MIB_NOECTPKTS +
				(ipv6_get_dsfield(hdr) & INET_ECN_MASK),
			max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));

This is currently evaluating both expressions twice.

Fix _DEVADD() and _DEVUPD() macros to evaluate their arguments once.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/ipv6.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 9614006f483c9..2ccdf85f34f16 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -246,17 +246,20 @@ extern int sysctl_mld_qrv;
 #define _DEVADD(net, statname, mod, idev, field, val)			\
 ({									\
 	struct inet6_dev *_idev = (idev);				\
+	unsigned long _field = (field);					\
+	unsigned long _val = (val);					\
 	if (likely(_idev != NULL))					\
-		mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \
-	mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\
+		mod##SNMP_ADD_STATS((_idev)->stats.statname, _field,  _val); \
+	mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, _field, _val);\
 })
 
 #define _DEVUPD(net, statname, mod, idev, field, val)			\
 ({									\
 	struct inet6_dev *_idev = (idev);				\
+	unsigned long _val = (val);					\
 	if (likely(_idev != NULL))					\
-		mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \
-	mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\
+		mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, _val); \
+	mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, _val);\
 })
 
 /* MIBs */

From 2f8c40d4b78be144407d932f4d6b6186840000b6 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Wed, 19 Mar 2025 21:44:05 +0000
Subject: [PATCH 2669/2753] dt-bindings: net: rockchip-dwmac: Add compatible
 string for RK3528

Rockchip RK3528 has two Ethernet controllers based on Synopsys DWC
Ethernet QoS IP.

Add compatible string for the RK3528 variant.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../devicetree/bindings/net/rockchip-dwmac.yaml  | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
index 63ee0cc7a8f89..0ac7c4b47d6bf 100644
--- a/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
+++ b/Documentation/devicetree/bindings/net/rockchip-dwmac.yaml
@@ -24,6 +24,7 @@ select:
           - rockchip,rk3366-gmac
           - rockchip,rk3368-gmac
           - rockchip,rk3399-gmac
+          - rockchip,rk3528-gmac
           - rockchip,rk3568-gmac
           - rockchip,rk3576-gmac
           - rockchip,rk3588-gmac
@@ -49,6 +50,7 @@ properties:
               - rockchip,rv1108-gmac
       - items:
           - enum:
+              - rockchip,rk3528-gmac
               - rockchip,rk3568-gmac
               - rockchip,rk3576-gmac
               - rockchip,rk3588-gmac
@@ -66,7 +68,7 @@ properties:
       - const: eth_wake_irq
 
   clocks:
-    minItems: 5
+    minItems: 4
     maxItems: 8
 
   clock-names:
@@ -140,6 +142,18 @@ allOf:
       properties:
         rockchip,php-grf: false
 
+  - if:
+      not:
+        properties:
+          compatible:
+            contains:
+              enum:
+                - rockchip,rk3528-gmac
+    then:
+      properties:
+        clocks:
+          minItems: 5
+
 unevaluatedProperties: false
 
 examples:

From 18297f12fc599980283f9a95a3f59c2ba67ad31d Mon Sep 17 00:00:00 2001
From: David Wu <david.wu@rock-chips.com>
Date: Wed, 19 Mar 2025 21:44:06 +0000
Subject: [PATCH 2670/2753] net: stmmac: dwmac-rk: Add GMAC support for RK3528

Rockchip RK3528 has two Ethernet controllers based on Synopsys DWC
Ethernet QoS IP.

Add initial support for the RK3528 GMAC variant.

Signed-off-by: David Wu <david.wu@rock-chips.com>
Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 132 ++++++++++++++++++
 1 file changed, 132 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index c404017bc1da9..dfb4668db4ee3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -828,6 +828,137 @@ static const struct rk_gmac_ops rk3399_ops = {
 	.set_rmii_speed = rk3399_set_rmii_speed,
 };
 
+#define RK3528_VO_GRF_GMAC_CON		0x0018
+#define RK3528_VO_GRF_MACPHY_CON0	0x001c
+#define RK3528_VO_GRF_MACPHY_CON1	0x0020
+#define RK3528_VPU_GRF_GMAC_CON5	0x0018
+#define RK3528_VPU_GRF_GMAC_CON6	0x001c
+
+#define RK3528_GMAC_RXCLK_DLY_ENABLE	GRF_BIT(15)
+#define RK3528_GMAC_RXCLK_DLY_DISABLE	GRF_CLR_BIT(15)
+#define RK3528_GMAC_TXCLK_DLY_ENABLE	GRF_BIT(14)
+#define RK3528_GMAC_TXCLK_DLY_DISABLE	GRF_CLR_BIT(14)
+
+#define RK3528_GMAC_CLK_RX_DL_CFG(val)	HIWORD_UPDATE(val, 0xFF, 8)
+#define RK3528_GMAC_CLK_TX_DL_CFG(val)	HIWORD_UPDATE(val, 0xFF, 0)
+
+#define RK3528_GMAC0_PHY_INTF_SEL_RMII	GRF_BIT(1)
+#define RK3528_GMAC1_PHY_INTF_SEL_RGMII	GRF_CLR_BIT(8)
+#define RK3528_GMAC1_PHY_INTF_SEL_RMII	GRF_BIT(8)
+
+#define RK3528_GMAC1_CLK_SELECT_CRU	GRF_CLR_BIT(12)
+#define RK3528_GMAC1_CLK_SELECT_IO	GRF_BIT(12)
+
+#define RK3528_GMAC0_CLK_RMII_DIV2	GRF_BIT(3)
+#define RK3528_GMAC0_CLK_RMII_DIV20	GRF_CLR_BIT(3)
+#define RK3528_GMAC1_CLK_RMII_DIV2	GRF_BIT(10)
+#define RK3528_GMAC1_CLK_RMII_DIV20	GRF_CLR_BIT(10)
+
+#define RK3528_GMAC1_CLK_RGMII_DIV1	(GRF_CLR_BIT(11) | GRF_CLR_BIT(10))
+#define RK3528_GMAC1_CLK_RGMII_DIV5	(GRF_BIT(11) | GRF_BIT(10))
+#define RK3528_GMAC1_CLK_RGMII_DIV50	(GRF_BIT(11) | GRF_CLR_BIT(10))
+
+#define RK3528_GMAC0_CLK_RMII_GATE	GRF_BIT(2)
+#define RK3528_GMAC0_CLK_RMII_NOGATE	GRF_CLR_BIT(2)
+#define RK3528_GMAC1_CLK_RMII_GATE	GRF_BIT(9)
+#define RK3528_GMAC1_CLK_RMII_NOGATE	GRF_CLR_BIT(9)
+
+static void rk3528_set_to_rgmii(struct rk_priv_data *bsp_priv,
+				int tx_delay, int rx_delay)
+{
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+		     RK3528_GMAC1_PHY_INTF_SEL_RGMII);
+
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+		     DELAY_ENABLE(RK3528, tx_delay, rx_delay));
+
+	regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON6,
+		     RK3528_GMAC_CLK_RX_DL_CFG(rx_delay) |
+		     RK3528_GMAC_CLK_TX_DL_CFG(tx_delay));
+}
+
+static void rk3528_set_to_rmii(struct rk_priv_data *bsp_priv)
+{
+	if (bsp_priv->id == 1)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_PHY_INTF_SEL_RMII);
+	else
+		regmap_write(bsp_priv->grf, RK3528_VO_GRF_GMAC_CON,
+			     RK3528_GMAC0_PHY_INTF_SEL_RMII |
+			     RK3528_GMAC0_CLK_RMII_DIV2);
+}
+
+static void rk3528_set_rgmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+
+	if (speed == 10)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV50);
+	else if (speed == 100)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV5);
+	else if (speed == 1000)
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5,
+			     RK3528_GMAC1_CLK_RGMII_DIV1);
+	else
+		dev_err(dev, "unknown speed value for RGMII! speed=%d", speed);
+}
+
+static void rk3528_set_rmii_speed(struct rk_priv_data *bsp_priv, int speed)
+{
+	struct device *dev = &bsp_priv->pdev->dev;
+	unsigned int reg, val;
+
+	if (speed == 10)
+		val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV20 :
+					  RK3528_GMAC0_CLK_RMII_DIV20;
+	else if (speed == 100)
+		val = bsp_priv->id == 1 ? RK3528_GMAC1_CLK_RMII_DIV2 :
+					  RK3528_GMAC0_CLK_RMII_DIV2;
+	else {
+		dev_err(dev, "unknown speed value for RMII! speed=%d", speed);
+		return;
+	}
+
+	reg = bsp_priv->id == 1 ? RK3528_VPU_GRF_GMAC_CON5 :
+				  RK3528_VO_GRF_GMAC_CON;
+
+	regmap_write(bsp_priv->grf, reg, val);
+}
+
+static void rk3528_set_clock_selection(struct rk_priv_data *bsp_priv,
+				       bool input, bool enable)
+{
+	unsigned int val;
+
+	if (bsp_priv->id == 1) {
+		val = input ? RK3528_GMAC1_CLK_SELECT_IO :
+			      RK3528_GMAC1_CLK_SELECT_CRU;
+		val |= enable ? RK3528_GMAC1_CLK_RMII_NOGATE :
+				RK3528_GMAC1_CLK_RMII_GATE;
+		regmap_write(bsp_priv->grf, RK3528_VPU_GRF_GMAC_CON5, val);
+	} else {
+		val = enable ? RK3528_GMAC0_CLK_RMII_NOGATE :
+			       RK3528_GMAC0_CLK_RMII_GATE;
+		regmap_write(bsp_priv->grf, RK3528_VO_GRF_GMAC_CON, val);
+	}
+}
+
+static const struct rk_gmac_ops rk3528_ops = {
+	.set_to_rgmii = rk3528_set_to_rgmii,
+	.set_to_rmii = rk3528_set_to_rmii,
+	.set_rgmii_speed = rk3528_set_rgmii_speed,
+	.set_rmii_speed = rk3528_set_rmii_speed,
+	.set_clock_selection = rk3528_set_clock_selection,
+	.regs_valid = true,
+	.regs = {
+		0xffbd0000, /* gmac0 */
+		0xffbe0000, /* gmac1 */
+		0x0, /* sentinel */
+	},
+};
+
 #define RK3568_GRF_GMAC0_CON0		0x0380
 #define RK3568_GRF_GMAC0_CON1		0x0384
 #define RK3568_GRF_GMAC1_CON0		0x0388
@@ -1819,6 +1950,7 @@ static const struct of_device_id rk_gmac_dwmac_match[] = {
 	{ .compatible = "rockchip,rk3366-gmac", .data = &rk3366_ops },
 	{ .compatible = "rockchip,rk3368-gmac", .data = &rk3368_ops },
 	{ .compatible = "rockchip,rk3399-gmac", .data = &rk3399_ops },
+	{ .compatible = "rockchip,rk3528-gmac", .data = &rk3528_ops },
 	{ .compatible = "rockchip,rk3568-gmac", .data = &rk3568_ops },
 	{ .compatible = "rockchip,rk3576-gmac", .data = &rk3576_ops },
 	{ .compatible = "rockchip,rk3588-gmac", .data = &rk3588_ops },

From 1fcd7bbfa7386b0cb9e8e5753b850b73ed43e962 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Wed, 19 Mar 2025 21:44:07 +0000
Subject: [PATCH 2671/2753] net: stmmac: dwmac-rk: Move
 integrated_phy_powerup/down functions

Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these SoCs.

Move the rk_gmac_integrated_phy_powerup/down functions to top of the
file to prepare for them to be called directly by a GMAC variant
specific powerup/down operation.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 88 +++++++++----------
 1 file changed, 44 insertions(+), 44 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index dfb4668db4ee3..0321befed0d3b 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -92,6 +92,50 @@ struct rk_priv_data {
 	(((tx) ? soc##_GMAC_TXCLK_DLY_ENABLE : soc##_GMAC_TXCLK_DLY_DISABLE) | \
 	 ((rx) ? soc##_GMAC_RXCLK_DLY_ENABLE : soc##_GMAC_RXCLK_DLY_DISABLE))
 
+#define RK_GRF_MACPHY_CON0		0xb00
+#define RK_GRF_MACPHY_CON1		0xb04
+#define RK_GRF_MACPHY_CON2		0xb08
+#define RK_GRF_MACPHY_CON3		0xb0c
+
+#define RK_MACPHY_ENABLE		GRF_BIT(0)
+#define RK_MACPHY_DISABLE		GRF_CLR_BIT(0)
+#define RK_MACPHY_CFG_CLK_50M		GRF_BIT(14)
+#define RK_GMAC2PHY_RMII_MODE		(GRF_BIT(6) | GRF_CLR_BIT(7))
+#define RK_GRF_CON2_MACPHY_ID		HIWORD_UPDATE(0x1234, 0xffff, 0)
+#define RK_GRF_CON3_MACPHY_ID		HIWORD_UPDATE(0x35, 0x3f, 0)
+
+static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv)
+{
+	if (priv->ops->integrated_phy_powerup)
+		priv->ops->integrated_phy_powerup(priv);
+
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M);
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE);
+
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON2, RK_GRF_CON2_MACPHY_ID);
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON3, RK_GRF_CON3_MACPHY_ID);
+
+	if (priv->phy_reset) {
+		/* PHY needs to be disabled before trying to reset it */
+		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
+		if (priv->phy_reset)
+			reset_control_assert(priv->phy_reset);
+		usleep_range(10, 20);
+		if (priv->phy_reset)
+			reset_control_deassert(priv->phy_reset);
+		usleep_range(10, 20);
+		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_ENABLE);
+		msleep(30);
+	}
+}
+
+static void rk_gmac_integrated_phy_powerdown(struct rk_priv_data *priv)
+{
+	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
+	if (priv->phy_reset)
+		reset_control_assert(priv->phy_reset);
+}
+
 #define PX30_GRF_GMAC_CON1		0x0904
 
 /* PX30_GRF_GMAC_CON1 */
@@ -1463,50 +1507,6 @@ static const struct rk_gmac_ops rv1126_ops = {
 	.set_rmii_speed = rv1126_set_rmii_speed,
 };
 
-#define RK_GRF_MACPHY_CON0		0xb00
-#define RK_GRF_MACPHY_CON1		0xb04
-#define RK_GRF_MACPHY_CON2		0xb08
-#define RK_GRF_MACPHY_CON3		0xb0c
-
-#define RK_MACPHY_ENABLE		GRF_BIT(0)
-#define RK_MACPHY_DISABLE		GRF_CLR_BIT(0)
-#define RK_MACPHY_CFG_CLK_50M		GRF_BIT(14)
-#define RK_GMAC2PHY_RMII_MODE		(GRF_BIT(6) | GRF_CLR_BIT(7))
-#define RK_GRF_CON2_MACPHY_ID		HIWORD_UPDATE(0x1234, 0xffff, 0)
-#define RK_GRF_CON3_MACPHY_ID		HIWORD_UPDATE(0x35, 0x3f, 0)
-
-static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv)
-{
-	if (priv->ops->integrated_phy_powerup)
-		priv->ops->integrated_phy_powerup(priv);
-
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M);
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE);
-
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON2, RK_GRF_CON2_MACPHY_ID);
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON3, RK_GRF_CON3_MACPHY_ID);
-
-	if (priv->phy_reset) {
-		/* PHY needs to be disabled before trying to reset it */
-		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
-		if (priv->phy_reset)
-			reset_control_assert(priv->phy_reset);
-		usleep_range(10, 20);
-		if (priv->phy_reset)
-			reset_control_deassert(priv->phy_reset);
-		usleep_range(10, 20);
-		regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_ENABLE);
-		msleep(30);
-	}
-}
-
-static void rk_gmac_integrated_phy_powerdown(struct rk_priv_data *priv)
-{
-	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
-	if (priv->phy_reset)
-		reset_control_assert(priv->phy_reset);
-}
-
 static int rk_gmac_clk_init(struct plat_stmmacenet_data *plat)
 {
 	struct rk_priv_data *bsp_priv = plat->bsp_priv;

From fef467f3c7a78e5c72d45abfe43fb2ee06ff48c2 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Wed, 19 Mar 2025 21:44:08 +0000
Subject: [PATCH 2672/2753] net: stmmac: dwmac-rk: Add integrated_phy_powerdown
 operation

Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these newer SoCs.

Add a new integrated_phy_powerdown operation and change the call chain
for integrated_phy_powerup to prepare support for the integrated PHY
found in these newer SoCs.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 26 +++++++++++--------
 1 file changed, 15 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 0321befed0d3b..3673abd653020 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -33,6 +33,7 @@ struct rk_gmac_ops {
 	void (*set_clock_selection)(struct rk_priv_data *bsp_priv, bool input,
 				    bool enable);
 	void (*integrated_phy_powerup)(struct rk_priv_data *bsp_priv);
+	void (*integrated_phy_powerdown)(struct rk_priv_data *bsp_priv);
 	bool php_grf_required;
 	bool regs_valid;
 	u32 regs[];
@@ -104,11 +105,8 @@ struct rk_priv_data {
 #define RK_GRF_CON2_MACPHY_ID		HIWORD_UPDATE(0x1234, 0xffff, 0)
 #define RK_GRF_CON3_MACPHY_ID		HIWORD_UPDATE(0x35, 0x3f, 0)
 
-static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv)
+static void rk_gmac_integrated_ephy_powerup(struct rk_priv_data *priv)
 {
-	if (priv->ops->integrated_phy_powerup)
-		priv->ops->integrated_phy_powerup(priv);
-
 	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_CFG_CLK_50M);
 	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_GMAC2PHY_RMII_MODE);
 
@@ -129,7 +127,7 @@ static void rk_gmac_integrated_phy_powerup(struct rk_priv_data *priv)
 	}
 }
 
-static void rk_gmac_integrated_phy_powerdown(struct rk_priv_data *priv)
+static void rk_gmac_integrated_ephy_powerdown(struct rk_priv_data *priv)
 {
 	regmap_write(priv->grf, RK_GRF_MACPHY_CON0, RK_MACPHY_DISABLE);
 	if (priv->phy_reset)
@@ -368,6 +366,8 @@ static void rk3228_integrated_phy_powerup(struct rk_priv_data *priv)
 {
 	regmap_write(priv->grf, RK3228_GRF_CON_MUX,
 		     RK3228_GRF_CON_MUX_GMAC_INTEGRATED_PHY);
+
+	rk_gmac_integrated_ephy_powerup(priv);
 }
 
 static const struct rk_gmac_ops rk3228_ops = {
@@ -375,7 +375,8 @@ static const struct rk_gmac_ops rk3228_ops = {
 	.set_to_rmii = rk3228_set_to_rmii,
 	.set_rgmii_speed = rk3228_set_rgmii_speed,
 	.set_rmii_speed = rk3228_set_rmii_speed,
-	.integrated_phy_powerup =  rk3228_integrated_phy_powerup,
+	.integrated_phy_powerup = rk3228_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown,
 };
 
 #define RK3288_GRF_SOC_CON1	0x0248
@@ -601,6 +602,8 @@ static void rk3328_integrated_phy_powerup(struct rk_priv_data *priv)
 {
 	regmap_write(priv->grf, RK3328_GRF_MACPHY_CON1,
 		     RK3328_MACPHY_RMII_MODE);
+
+	rk_gmac_integrated_ephy_powerup(priv);
 }
 
 static const struct rk_gmac_ops rk3328_ops = {
@@ -608,7 +611,8 @@ static const struct rk_gmac_ops rk3328_ops = {
 	.set_to_rmii = rk3328_set_to_rmii,
 	.set_rgmii_speed = rk3328_set_rgmii_speed,
 	.set_rmii_speed = rk3328_set_rmii_speed,
-	.integrated_phy_powerup =  rk3328_integrated_phy_powerup,
+	.integrated_phy_powerup = rk3328_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk_gmac_integrated_ephy_powerdown,
 };
 
 #define RK3366_GRF_SOC_CON6	0x0418
@@ -1802,16 +1806,16 @@ static int rk_gmac_powerup(struct rk_priv_data *bsp_priv)
 
 	pm_runtime_get_sync(dev);
 
-	if (bsp_priv->integrated_phy)
-		rk_gmac_integrated_phy_powerup(bsp_priv);
+	if (bsp_priv->integrated_phy && bsp_priv->ops->integrated_phy_powerup)
+		bsp_priv->ops->integrated_phy_powerup(bsp_priv);
 
 	return 0;
 }
 
 static void rk_gmac_powerdown(struct rk_priv_data *gmac)
 {
-	if (gmac->integrated_phy)
-		rk_gmac_integrated_phy_powerdown(gmac);
+	if (gmac->integrated_phy && gmac->ops->integrated_phy_powerdown)
+		gmac->ops->integrated_phy_powerdown(gmac);
 
 	pm_runtime_put_sync(&gmac->pdev->dev);
 

From 30bfd67c9c4030ccc988702d6c43dee3a5b1c429 Mon Sep 17 00:00:00 2001
From: Jonas Karlman <jonas@kwiboo.se>
Date: Wed, 19 Mar 2025 21:44:09 +0000
Subject: [PATCH 2673/2753] net: stmmac: dwmac-rk: Add initial support for
 RK3528 integrated PHY

Rockchip RK3528 (and RV1106) has a different integrated PHY compared to
the integrated PHY on RK3228/RK3328. Current powerup/down operation is
not compatible with the integrated PHY found in these newer SoCs.

Add operations to powerup/down the integrated PHY found in RK3528.
Use helpers that can be used by other GMAC variants in the future.

Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/dwmac-rk.c    | 41 +++++++++++++++++++
 1 file changed, 41 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
index 3673abd653020..700858ff6f7c3 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-rk.c
@@ -134,6 +134,35 @@ static void rk_gmac_integrated_ephy_powerdown(struct rk_priv_data *priv)
 		reset_control_assert(priv->phy_reset);
 }
 
+#define RK_FEPHY_SHUTDOWN		GRF_BIT(1)
+#define RK_FEPHY_POWERUP		GRF_CLR_BIT(1)
+#define RK_FEPHY_INTERNAL_RMII_SEL	GRF_BIT(6)
+#define RK_FEPHY_24M_CLK_SEL		(GRF_BIT(8) | GRF_BIT(9))
+#define RK_FEPHY_PHY_ID			GRF_BIT(11)
+
+static void rk_gmac_integrated_fephy_powerup(struct rk_priv_data *priv,
+					     unsigned int reg)
+{
+	reset_control_assert(priv->phy_reset);
+	usleep_range(20, 30);
+
+	regmap_write(priv->grf, reg,
+		     RK_FEPHY_POWERUP |
+		     RK_FEPHY_INTERNAL_RMII_SEL |
+		     RK_FEPHY_24M_CLK_SEL |
+		     RK_FEPHY_PHY_ID);
+	usleep_range(10000, 12000);
+
+	reset_control_deassert(priv->phy_reset);
+	usleep_range(50000, 60000);
+}
+
+static void rk_gmac_integrated_fephy_powerdown(struct rk_priv_data *priv,
+					       unsigned int reg)
+{
+	regmap_write(priv->grf, reg, RK_FEPHY_SHUTDOWN);
+}
+
 #define PX30_GRF_GMAC_CON1		0x0904
 
 /* PX30_GRF_GMAC_CON1 */
@@ -993,12 +1022,24 @@ static void rk3528_set_clock_selection(struct rk_priv_data *bsp_priv,
 	}
 }
 
+static void rk3528_integrated_phy_powerup(struct rk_priv_data *bsp_priv)
+{
+	rk_gmac_integrated_fephy_powerup(bsp_priv, RK3528_VO_GRF_MACPHY_CON0);
+}
+
+static void rk3528_integrated_phy_powerdown(struct rk_priv_data *bsp_priv)
+{
+	rk_gmac_integrated_fephy_powerdown(bsp_priv, RK3528_VO_GRF_MACPHY_CON0);
+}
+
 static const struct rk_gmac_ops rk3528_ops = {
 	.set_to_rgmii = rk3528_set_to_rgmii,
 	.set_to_rmii = rk3528_set_to_rmii,
 	.set_rgmii_speed = rk3528_set_rgmii_speed,
 	.set_rmii_speed = rk3528_set_rmii_speed,
 	.set_clock_selection = rk3528_set_clock_selection,
+	.integrated_phy_powerup = rk3528_integrated_phy_powerup,
+	.integrated_phy_powerdown = rk3528_integrated_phy_powerdown,
 	.regs_valid = true,
 	.regs = {
 		0xffbd0000, /* gmac0 */

From 359379a162b8065f21c40e8ddd2fe3f57f0c3549 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:46 -0700
Subject: [PATCH 2674/2753] nexthop: Move nlmsg_parse() in rtm_to_nh_config()
 to rtm_new_nexthop().

We will split rtm_to_nh_config() into non-RTNL and RTNL parts,
and then the latter also needs tb.

As a prep, let's move nlmsg_parse() to rtm_new_nexthop().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 33 ++++++++++++++++++---------------
 1 file changed, 18 insertions(+), 15 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 01df7dd795f01..487933ecdb686 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3016,19 +3016,13 @@ static int rtm_to_nh_config_grp_res(struct nlattr *res, struct nh_config *cfg,
 }
 
 static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
-			    struct nlmsghdr *nlh, struct nh_config *cfg,
+			    struct nlmsghdr *nlh, struct nlattr **tb,
+			    struct nh_config *cfg,
 			    struct netlink_ext_ack *extack)
 {
 	struct nhmsg *nhm = nlmsg_data(nlh);
-	struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)];
 	int err;
 
-	err = nlmsg_parse(nlh, sizeof(*nhm), tb,
-			  ARRAY_SIZE(rtm_nh_policy_new) - 1,
-			  rtm_nh_policy_new, extack);
-	if (err < 0)
-		return err;
-
 	err = -EINVAL;
 	if (nhm->resvd || nhm->nh_scope) {
 		NL_SET_ERR_MSG(extack, "Invalid values in ancillary header");
@@ -3093,7 +3087,8 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 			NL_SET_ERR_MSG(extack, "Invalid group type");
 			goto out;
 		}
-		err = nh_check_attr_group(net, tb, ARRAY_SIZE(tb),
+
+		err = nh_check_attr_group(net, tb, ARRAY_SIZE(rtm_nh_policy_new),
 					  cfg->nh_grp_type, extack);
 		if (err)
 			goto out;
@@ -3211,18 +3206,26 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 			   struct netlink_ext_ack *extack)
 {
+	struct nlattr *tb[ARRAY_SIZE(rtm_nh_policy_new)];
 	struct net *net = sock_net(skb->sk);
 	struct nh_config cfg;
 	struct nexthop *nh;
 	int err;
 
-	err = rtm_to_nh_config(net, skb, nlh, &cfg, extack);
-	if (!err) {
-		nh = nexthop_add(net, &cfg, extack);
-		if (IS_ERR(nh))
-			err = PTR_ERR(nh);
-	}
+	err = nlmsg_parse(nlh, sizeof(struct nhmsg), tb,
+			  ARRAY_SIZE(rtm_nh_policy_new) - 1,
+			  rtm_nh_policy_new, extack);
+	if (err < 0)
+		goto out;
 
+	err = rtm_to_nh_config(net, skb, nlh, tb, &cfg, extack);
+	if (err)
+		goto out;
+
+	nh = nexthop_add(net, &cfg, extack);
+	if (IS_ERR(nh))
+		err = PTR_ERR(nh);
+out:
 	return err;
 }
 

From c158b150da23b6d35d82a4fe0c8f008d2ed38c2c Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:47 -0700
Subject: [PATCH 2675/2753] nexthop: Split nh_check_attr_group().

We will push RTNL down to rtm_new_nexthop(), and then we
want to move non-RTNL operations out of the scope.

nh_check_attr_group() validates NHA_GROUP attributes, and
nexthop_find_by_id() and some validation requires RTNL.

Let's factorise such parts as nh_check_attr_group_rtnl()
and call it from rtm_to_nh_config_rtnl().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 68 ++++++++++++++++++++++++++++++++--------------
 1 file changed, 47 insertions(+), 21 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 487933ecdb686..d30edc14b039b 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1272,10 +1272,8 @@ static int nh_check_attr_group(struct net *net,
 			       u16 nh_grp_type, struct netlink_ext_ack *extack)
 {
 	unsigned int len = nla_len(tb[NHA_GROUP]);
-	u8 nh_family = AF_UNSPEC;
 	struct nexthop_grp *nhg;
 	unsigned int i, j;
-	u8 nhg_fdb = 0;
 
 	if (!len || len & (sizeof(struct nexthop_grp) - 1)) {
 		NL_SET_ERR_MSG(extack,
@@ -1307,10 +1305,41 @@ static int nh_check_attr_group(struct net *net,
 		}
 	}
 
-	if (tb[NHA_FDB])
-		nhg_fdb = 1;
 	nhg = nla_data(tb[NHA_GROUP]);
-	for (i = 0; i < len; ++i) {
+	for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) {
+		if (!tb[i])
+			continue;
+		switch (i) {
+		case NHA_HW_STATS_ENABLE:
+		case NHA_FDB:
+			continue;
+		case NHA_RES_GROUP:
+			if (nh_grp_type == NEXTHOP_GRP_TYPE_RES)
+				continue;
+			break;
+		}
+		NL_SET_ERR_MSG(extack,
+			       "No other attributes can be set in nexthop groups");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int nh_check_attr_group_rtnl(struct net *net, struct nlattr *tb[],
+				    struct netlink_ext_ack *extack)
+{
+	u8 nh_family = AF_UNSPEC;
+	struct nexthop_grp *nhg;
+	unsigned int len;
+	unsigned int i;
+	u8 nhg_fdb;
+
+	len = nla_len(tb[NHA_GROUP]) / sizeof(*nhg);
+	nhg = nla_data(tb[NHA_GROUP]);
+	nhg_fdb = !!tb[NHA_FDB];
+
+	for (i = 0; i < len; i++) {
 		struct nexthop *nh;
 		bool is_fdb_nh;
 
@@ -1330,22 +1359,6 @@ static int nh_check_attr_group(struct net *net,
 			return -EINVAL;
 		}
 	}
-	for (i = NHA_GROUP_TYPE + 1; i < tb_size; ++i) {
-		if (!tb[i])
-			continue;
-		switch (i) {
-		case NHA_HW_STATS_ENABLE:
-		case NHA_FDB:
-			continue;
-		case NHA_RES_GROUP:
-			if (nh_grp_type == NEXTHOP_GRP_TYPE_RES)
-				continue;
-			break;
-		}
-		NL_SET_ERR_MSG(extack,
-			       "No other attributes can be set in nexthop groups");
-		return -EINVAL;
-	}
 
 	return 0;
 }
@@ -3202,6 +3215,15 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 	return err;
 }
 
+static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb,
+				 struct netlink_ext_ack *extack)
+{
+	if (tb[NHA_GROUP])
+		return nh_check_attr_group_rtnl(net, tb, extack);
+
+	return 0;
+}
+
 /* rtnl */
 static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 			   struct netlink_ext_ack *extack)
@@ -3222,6 +3244,10 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto out;
 
+	err = rtm_to_nh_config_rtnl(net, tb, extack);
+	if (err)
+		goto out;
+
 	nh = nexthop_add(net, &cfg, extack);
 	if (IS_ERR(nh))
 		err = PTR_ERR(nh);

From e695aa1b7fbfa5c9c0f0f0941e5e0c5de99a92c3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:48 -0700
Subject: [PATCH 2676/2753] nexthop: Move NHA_OIF validation to
 rtm_to_nh_config_rtnl().

NHA_OIF needs to look up a device by __dev_get_by_index(),
which requires RTNL.

Let's move NHA_OIF validation to rtm_to_nh_config_rtnl().

Note that the proceeding checks made the original !cfg->nh_fdb
check redundant.

  NHA_FDB is set           -> NHA_OIF cannot be set
  NHA_FDB is set but false -> NHA_OIF must be set
  NHA_FDB is not set       -> NHA_OIF must be set

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 43 +++++++++++++++++++++++--------------------
 1 file changed, 23 insertions(+), 20 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index d30edc14b039b..426cdf301c6fa 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3134,25 +3134,6 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 		goto out;
 	}
 
-	if (!cfg->nh_fdb && tb[NHA_OIF]) {
-		cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]);
-		if (cfg->nh_ifindex)
-			cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex);
-
-		if (!cfg->dev) {
-			NL_SET_ERR_MSG(extack, "Invalid device index");
-			goto out;
-		} else if (!(cfg->dev->flags & IFF_UP)) {
-			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
-			err = -ENETDOWN;
-			goto out;
-		} else if (!netif_carrier_ok(cfg->dev)) {
-			NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down");
-			err = -ENETDOWN;
-			goto out;
-		}
-	}
-
 	err = -EINVAL;
 	if (tb[NHA_GATEWAY]) {
 		struct nlattr *gwa = tb[NHA_GATEWAY];
@@ -3216,11 +3197,33 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 }
 
 static int rtm_to_nh_config_rtnl(struct net *net, struct nlattr **tb,
+				 struct nh_config *cfg,
 				 struct netlink_ext_ack *extack)
 {
 	if (tb[NHA_GROUP])
 		return nh_check_attr_group_rtnl(net, tb, extack);
 
+	if (tb[NHA_OIF]) {
+		cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]);
+		if (cfg->nh_ifindex)
+			cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex);
+
+		if (!cfg->dev) {
+			NL_SET_ERR_MSG(extack, "Invalid device index");
+			return -EINVAL;
+		}
+
+		if (!(cfg->dev->flags & IFF_UP)) {
+			NL_SET_ERR_MSG(extack, "Nexthop device is not up");
+			return -ENETDOWN;
+		}
+
+		if (!netif_carrier_ok(cfg->dev)) {
+			NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down");
+			return -ENETDOWN;
+		}
+	}
+
 	return 0;
 }
 
@@ -3244,7 +3247,7 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto out;
 
-	err = rtm_to_nh_config_rtnl(net, tb, extack);
+	err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack);
 	if (err)
 		goto out;
 

From f27028d9fe697b411c8c4bc646ff638b989d734d Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:49 -0700
Subject: [PATCH 2677/2753] nexthop: Check NLM_F_REPLACE and NHA_ID in
 rtm_new_nexthop().

nexthop_add() checks if NLM_F_REPLACE is specified without
non-zero NHA_ID, which does not require RTNL.

Let's move the check to rtm_new_nexthop().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 426cdf301c6fa..fb129c8300406 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2928,11 +2928,6 @@ static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg,
 	struct nexthop *nh;
 	int err;
 
-	if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) {
-		NL_SET_ERR_MSG(extack, "Replace requires nexthop id");
-		return ERR_PTR(-EINVAL);
-	}
-
 	if (!cfg->nh_id) {
 		cfg->nh_id = nh_find_unused_id(net);
 		if (!cfg->nh_id) {
@@ -3247,6 +3242,12 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		goto out;
 
+	if (cfg.nlflags & NLM_F_REPLACE && !cfg.nh_id) {
+		NL_SET_ERR_MSG(extack, "Replace requires nexthop id");
+		err = -EINVAL;
+		goto out;
+	}
+
 	err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack);
 	if (err)
 		goto out;

From 1e0943b3eb3b46a2b9f576f122da36aca6c861d6 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:50 -0700
Subject: [PATCH 2678/2753] nexthop: Remove redundant group len check in
 nexthop_create_group().

The number of NHA_GROUP entries is guaranteed to be non-zero in
nh_check_attr_group().

Let's remove the redundant check in nexthop_create_group().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index fb129c8300406..c552bb46aa23c 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -2692,9 +2692,6 @@ static struct nexthop *nexthop_create_group(struct net *net,
 	int err;
 	int i;
 
-	if (WARN_ON(!num_nh))
-		return ERR_PTR(-EINVAL);
-
 	nh = nexthop_alloc();
 	if (!nh)
 		return ERR_PTR(-ENOMEM);

From d233e8bbf88b62034a1f920d035aab50befb352f Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:51 -0700
Subject: [PATCH 2679/2753] nexthop: Convert RTM_NEWNEXTHOP to per-netns RTNL.

If we pass false to the rtnl_held param of lwtunnel_valid_encap_type(),
we can move RTNL down before rtm_to_nh_config_rtnl().

Let's use rtnl_net_lock() in rtm_new_nexthop().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 16 +++++++++++-----
 1 file changed, 11 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index c552bb46aa23c..06d5467eadc1d 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3169,7 +3169,7 @@ static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
 
 		cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]);
 		err = lwtunnel_valid_encap_type(cfg->nh_encap_type,
-						extack, true);
+						extack, false);
 		if (err < 0)
 			goto out;
 
@@ -3245,13 +3245,18 @@ static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 	}
 
+	rtnl_net_lock(net);
+
 	err = rtm_to_nh_config_rtnl(net, tb, &cfg, extack);
 	if (err)
-		goto out;
+		goto unlock;
 
 	nh = nexthop_add(net, &cfg, extack);
 	if (IS_ERR(nh))
 		err = PTR_ERR(nh);
+
+unlock:
+	rtnl_net_unlock(net);
 out:
 	return err;
 }
@@ -4067,18 +4072,19 @@ static struct pernet_operations nexthop_net_ops = {
 };
 
 static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = {
-	{.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop},
+	{.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
 	{.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop},
 	{.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop,
 	 .dumpit = rtm_dump_nexthop},
 	{.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket,
 	 .dumpit = rtm_dump_nexthop_bucket},
 	{.protocol = PF_INET, .msgtype = RTM_NEWNEXTHOP,
-	 .doit = rtm_new_nexthop},
+	 .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET, .msgtype = RTM_GETNEXTHOP,
 	 .dumpit = rtm_dump_nexthop},
 	{.protocol = PF_INET6, .msgtype = RTM_NEWNEXTHOP,
-	 .doit = rtm_new_nexthop},
+	 .doit = rtm_new_nexthop, .flags = RTNL_FLAG_DOIT_PERNET},
 	{.protocol = PF_INET6, .msgtype = RTM_GETNEXTHOP,
 	 .dumpit = rtm_dump_nexthop},
 };

From e88e545f5bdbd60f7446d75d88e46854d4ecc6c5 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Wed, 19 Mar 2025 16:06:52 -0700
Subject: [PATCH 2680/2753] nexthop: Convert RTM_DELNEXTHOP to per-netns RTNL.

In rtm_del_nexthop(), only nexthop_find_by_id() and remove_nexthop()
require RTNL as they touch net->nexthop.rb_root.

Let's move RTNL down as rtnl_net_lock() before nexthop_find_by_id().

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/nexthop.c | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 06d5467eadc1d..467151517023d 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3314,13 +3314,17 @@ static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (err)
 		return err;
 
+	rtnl_net_lock(net);
+
 	nh = nexthop_find_by_id(net, id);
-	if (!nh)
-		return -ENOENT;
+	if (nh)
+		remove_nexthop(net, nh, &nlinfo);
+	else
+		err = -ENOENT;
 
-	remove_nexthop(net, nh, &nlinfo);
+	rtnl_net_unlock(net);
 
-	return 0;
+	return err;
 }
 
 /* rtnl */
@@ -4074,7 +4078,8 @@ static struct pernet_operations nexthop_net_ops = {
 static const struct rtnl_msg_handler nexthop_rtnl_msg_handlers[] __initconst = {
 	{.msgtype = RTM_NEWNEXTHOP, .doit = rtm_new_nexthop,
 	 .flags = RTNL_FLAG_DOIT_PERNET},
-	{.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop},
+	{.msgtype = RTM_DELNEXTHOP, .doit = rtm_del_nexthop,
+	 .flags = RTNL_FLAG_DOIT_PERNET},
 	{.msgtype = RTM_GETNEXTHOP, .doit = rtm_get_nexthop,
 	 .dumpit = rtm_dump_nexthop},
 	{.msgtype = RTM_GETNEXTHOPBUCKET, .doit = rtm_get_nexthop_bucket,

From fd8b89d0a11f6169c4db6ec697b32826ce3934c7 Mon Sep 17 00:00:00 2001
From: Peng Fan <peng.fan@nxp.com>
Date: Thu, 20 Mar 2025 11:15:24 +0800
Subject: [PATCH 2681/2753] net: ethernet: Drop unused of_gpio.h

of_gpio.h is deprecated. Since there is no of_gpio_x API, drop
unused of_gpio.h. While at here, drop gpio.h and gpio/consumer.h if
no user in driver.

Signed-off-by: Peng Fan <peng.fan@nxp.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/cadence/macb_main.c | 3 ---
 drivers/net/ethernet/freescale/fec_ptp.c | 1 -
 drivers/net/ethernet/micrel/ks8851_spi.c | 2 --
 drivers/net/ethernet/smsc/smsc911x.c     | 1 -
 4 files changed, 7 deletions(-)

diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c
index b5797c1ac0a41..1fe8ec37491b1 100644
--- a/drivers/net/ethernet/cadence/macb_main.c
+++ b/drivers/net/ethernet/cadence/macb_main.c
@@ -17,8 +17,6 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/io.h>
-#include <linux/gpio.h>
-#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/netdevice.h>
 #include <linux/etherdevice.h>
@@ -26,7 +24,6 @@
 #include <linux/platform_device.h>
 #include <linux/phylink.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_mdio.h>
 #include <linux/of_net.h>
 #include <linux/ip.h>
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 7f6b574320716..7e62a4529e6fa 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -30,7 +30,6 @@
 #include <linux/phy.h>
 #include <linux/fec.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 
 #include "fec.h"
diff --git a/drivers/net/ethernet/micrel/ks8851_spi.c b/drivers/net/ethernet/micrel/ks8851_spi.c
index 3062cc0f91992..c862b13b447a5 100644
--- a/drivers/net/ethernet/micrel/ks8851_spi.c
+++ b/drivers/net/ethernet/micrel/ks8851_spi.c
@@ -20,8 +20,6 @@
 #include <linux/regulator/consumer.h>
 
 #include <linux/spi/spi.h>
-#include <linux/gpio.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 
 #include "ks8851.h"
diff --git a/drivers/net/ethernet/smsc/smsc911x.c b/drivers/net/ethernet/smsc/smsc911x.c
index f539813878f53..2e11060979655 100644
--- a/drivers/net/ethernet/smsc/smsc911x.c
+++ b/drivers/net/ethernet/smsc/smsc911x.c
@@ -43,7 +43,6 @@
 #include <linux/smsc911x.h>
 #include <linux/device.h>
 #include <linux/of.h>
-#include <linux/of_gpio.h>
 #include <linux/of_net.h>
 #include <linux/acpi.h>
 #include <linux/pm_runtime.h>

From 3d8c101a3dd4b2cbd9a492a0a50d5f359376df21 Mon Sep 17 00:00:00 2001
From: Sankararaman Jayaraman <sankararaman.jayaraman@broadcom.com>
Date: Thu, 20 Mar 2025 10:25:22 +0530
Subject: [PATCH 2682/2753] vmxnet3: unregister xdp rxq info in the reset path

vmxnet3 does not unregister xdp rxq info in the
vmxnet3_reset_work() code path as vmxnet3_rq_destroy()
is not invoked in this code path. So, we get below message with a
backtrace.

Missing unregister, handled but fix driver
WARNING: CPU:48 PID: 500 at net/core/xdp.c:182
__xdp_rxq_info_reg+0x93/0xf0

This patch fixes the problem by moving the unregister
code of XDP from vmxnet3_rq_destroy() to vmxnet3_rq_cleanup().

Fixes: 54f00cce1178 ("vmxnet3: Add XDP support.")
Signed-off-by: Sankararaman Jayaraman <sankararaman.jayaraman@broadcom.com>
Signed-off-by: Ronak Doshi <ronak.doshi@broadcom.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/vmxnet3/vmxnet3_drv.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c
index 6793fa09f9d1a..3df6aabc7e339 100644
--- a/drivers/net/vmxnet3/vmxnet3_drv.c
+++ b/drivers/net/vmxnet3/vmxnet3_drv.c
@@ -2033,6 +2033,11 @@ vmxnet3_rq_cleanup(struct vmxnet3_rx_queue *rq,
 
 	rq->comp_ring.gen = VMXNET3_INIT_GEN;
 	rq->comp_ring.next2proc = 0;
+
+	if (xdp_rxq_info_is_reg(&rq->xdp_rxq))
+		xdp_rxq_info_unreg(&rq->xdp_rxq);
+	page_pool_destroy(rq->page_pool);
+	rq->page_pool = NULL;
 }
 
 
@@ -2073,11 +2078,6 @@ static void vmxnet3_rq_destroy(struct vmxnet3_rx_queue *rq,
 		}
 	}
 
-	if (xdp_rxq_info_is_reg(&rq->xdp_rxq))
-		xdp_rxq_info_unreg(&rq->xdp_rxq);
-	page_pool_destroy(rq->page_pool);
-	rq->page_pool = NULL;
-
 	if (rq->data_ring.base) {
 		dma_free_coherent(&adapter->pdev->dev,
 				  rq->rx_ring[0].size * rq->data_ring.desc_size,

From 539663429cf751118955252ae7fe04b7a30ffdc7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Mar 2025 10:14:34 +0000
Subject: [PATCH 2683/2753] net: reorganize IP MIB values (II)

Commit 14a196807482 ("net: reorganize IP MIB values") changed
MIB values to group hot fields together.

Since then 5 new fields have been added without caring about
data locality.

This patch moves IPSTATS_MIB_OUTPKTS, IPSTATS_MIB_NOECTPKTS,
IPSTATS_MIB_ECT1PKTS, IPSTATS_MIB_ECT0PKTS, IPSTATS_MIB_CEPKTS
to the hot portion of per-cpu data.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/uapi/linux/snmp.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index eb9fb776fdc3e..ec47f9b68a1bf 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -23,9 +23,14 @@ enum
 	IPSTATS_MIB_INPKTS,			/* InReceives */
 	IPSTATS_MIB_INOCTETS,			/* InOctets */
 	IPSTATS_MIB_INDELIVERS,			/* InDelivers */
-	IPSTATS_MIB_OUTFORWDATAGRAMS,		/* OutForwDatagrams */
+	IPSTATS_MIB_NOECTPKTS,			/* InNoECTPkts */
+	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
+	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
+	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
 	IPSTATS_MIB_OUTREQUESTS,		/* OutRequests */
+	IPSTATS_MIB_OUTPKTS,			/* OutTransmits */
 	IPSTATS_MIB_OUTOCTETS,			/* OutOctets */
+	IPSTATS_MIB_OUTFORWDATAGRAMS,		/* OutForwDatagrams */
 /* other fields */
 	IPSTATS_MIB_INHDRERRORS,		/* InHdrErrors */
 	IPSTATS_MIB_INTOOBIGERRORS,		/* InTooBigErrors */
@@ -52,12 +57,7 @@ enum
 	IPSTATS_MIB_INBCASTOCTETS,		/* InBcastOctets */
 	IPSTATS_MIB_OUTBCASTOCTETS,		/* OutBcastOctets */
 	IPSTATS_MIB_CSUMERRORS,			/* InCsumErrors */
-	IPSTATS_MIB_NOECTPKTS,			/* InNoECTPkts */
-	IPSTATS_MIB_ECT1PKTS,			/* InECT1Pkts */
-	IPSTATS_MIB_ECT0PKTS,			/* InECT0Pkts */
-	IPSTATS_MIB_CEPKTS,			/* InCEPkts */
 	IPSTATS_MIB_REASM_OVERLAPS,		/* ReasmOverlaps */
-	IPSTATS_MIB_OUTPKTS,			/* OutTransmits */
 	__IPSTATS_MIB_MAX
 };
 

From debdca76a85ee51e323f4a5f7537addd70e0c404 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 20 Mar 2025 09:59:44 +0100
Subject: [PATCH 2684/2753] ynl: devlink: add missing board-serial-number

Add a missing attribute of board serial number.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/devlink.yaml | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index 09fbb4c03fc8d..bd9726269b4fa 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -1868,6 +1868,7 @@ operations:
             - info-version-fixed
             - info-version-running
             - info-version-stored
+            - info-board-serial-number
       dump:
         reply: *info-get-reply
 

From 208201efe619880117c5171749e92a47fd633ed1 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 20 Mar 2025 09:59:45 +0100
Subject: [PATCH 2685/2753] net/mlx5: Expose serial numbers in devlink info

Devlink info allows to expose serial number and board serial number
Get the values from PCI VPD and expose it.

$ devlink dev info
pci/0000:08:00.0:
  driver mlx5_core
  serial_number e4397f872caeed218000846daa7d2f49
  board.serial_number MT2314XZ00YA
  versions:
      fixed:
        fw.psid MT_0000000894
      running:
        fw.version 28.41.1000
        fw 28.41.1000
      stored:
        fw.version 28.41.1000
        fw 28.41.1000
auxiliary/mlx5_core.eth.0:
  driver mlx5_core.eth
pci/0000:08:00.1:
  driver mlx5_core
  serial_number e4397f872caeed218000846daa7d2f49
  board.serial_number MT2314XZ00YA
  versions:
      fixed:
        fw.psid MT_0000000894
      running:
        fw.version 28.41.1000
        fw 28.41.1000
      stored:
        fw.version 28.41.1000
        fw 28.41.1000
auxiliary/mlx5_core.eth.1:
  driver mlx5_core.eth

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/mellanox/mlx5/core/devlink.c | 49 +++++++++++++++++++
 1 file changed, 49 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index 73cd746443788..ebe48f4053795 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -35,6 +35,51 @@ static u16 mlx5_fw_ver_subminor(u32 version)
 	return version & 0xffff;
 }
 
+static int mlx5_devlink_serial_numbers_put(struct mlx5_core_dev *dev,
+					   struct devlink_info_req *req,
+					   struct netlink_ext_ack *extack)
+{
+	struct pci_dev *pdev = dev->pdev;
+	unsigned int vpd_size, kw_len;
+	char *str, *end;
+	u8 *vpd_data;
+	int err = 0;
+	int start;
+
+	vpd_data = pci_vpd_alloc(pdev, &vpd_size);
+	if (IS_ERR(vpd_data))
+		return 0;
+
+	start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size,
+					     PCI_VPD_RO_KEYWORD_SERIALNO, &kw_len);
+	if (start >= 0) {
+		str = kstrndup(vpd_data + start, kw_len, GFP_KERNEL);
+		if (!str) {
+			err = -ENOMEM;
+			goto end;
+		}
+		end = strchrnul(str, ' ');
+		*end = '\0';
+		err = devlink_info_board_serial_number_put(req, str);
+		kfree(str);
+	}
+
+	start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size, "V3", &kw_len);
+	if (start >= 0) {
+		str = kstrndup(vpd_data + start, kw_len, GFP_KERNEL);
+		if (!str) {
+			err = -ENOMEM;
+			goto end;
+		}
+		err = devlink_info_serial_number_put(req, str);
+		kfree(str);
+	}
+
+end:
+	kfree(vpd_data);
+	return err;
+}
+
 #define DEVLINK_FW_STRING_LEN 32
 
 static int
@@ -49,6 +94,10 @@ mlx5_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req,
 	if (!mlx5_core_is_pf(dev))
 		return 0;
 
+	err = mlx5_devlink_serial_numbers_put(dev, req, extack);
+	if (err)
+		return err;
+
 	err = devlink_info_version_fixed_put(req, "fw.psid", dev->board_id);
 	if (err)
 		return err;

From 2e16279de6171851b2d31e7fe9ff9a1eada6c849 Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 20 Mar 2025 09:59:46 +0100
Subject: [PATCH 2686/2753] devlink: add function unique identifier to devlink
 dev info

Presently, for multi-PF NIC each PF reports the same serial_number and
board.serial_number.

To universally identify a function, add function unique identifier (uid)
to be obtained from the driver as a string of arbitrary length.

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/devlink.yaml          | 4 ++++
 Documentation/networking/devlink/devlink-info.rst | 5 +++++
 include/net/devlink.h                             | 2 ++
 include/uapi/linux/devlink.h                      | 2 ++
 net/devlink/dev.c                                 | 9 +++++++++
 5 files changed, 22 insertions(+)

diff --git a/Documentation/netlink/specs/devlink.yaml b/Documentation/netlink/specs/devlink.yaml
index bd9726269b4fa..5d39eb68aefb1 100644
--- a/Documentation/netlink/specs/devlink.yaml
+++ b/Documentation/netlink/specs/devlink.yaml
@@ -820,6 +820,9 @@ attribute-sets:
       -
         name: region-direct
         type: flag
+      -
+        name: info-function-uid
+        type: string
 
   -
     name: dl-dev-stats
@@ -1869,6 +1872,7 @@ operations:
             - info-version-running
             - info-version-stored
             - info-board-serial-number
+            - info-function-uid
       dump:
         reply: *info-get-reply
 
diff --git a/Documentation/networking/devlink/devlink-info.rst b/Documentation/networking/devlink/devlink-info.rst
index 23073bc219d8e..04afceee0c03a 100644
--- a/Documentation/networking/devlink/devlink-info.rst
+++ b/Documentation/networking/devlink/devlink-info.rst
@@ -50,6 +50,11 @@ versions is generally discouraged - here, and via any other Linux API.
        This is usually the serial number of the board, often available in
        PCI *Vital Product Data*.
 
+   * - ``function.uid``
+     - Function uniqueue identifier.
+
+       Vendor defined uniqueue identifier of a function.
+
    * - ``fixed``
      - Group for hardware identifiers, and versions of components
        which are not field-updatable.
diff --git a/include/net/devlink.h b/include/net/devlink.h
index b8783126c1ed2..a0b84efd4740a 100644
--- a/include/net/devlink.h
+++ b/include/net/devlink.h
@@ -1846,6 +1846,8 @@ int devlink_info_serial_number_put(struct devlink_info_req *req,
 				   const char *sn);
 int devlink_info_board_serial_number_put(struct devlink_info_req *req,
 					 const char *bsn);
+int devlink_info_function_uid_put(struct devlink_info_req *req,
+				  const char *fuid);
 
 enum devlink_info_version_type {
 	DEVLINK_INFO_VERSION_TYPE_NONE,
diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h
index 9401aa3436733..816339790409c 100644
--- a/include/uapi/linux/devlink.h
+++ b/include/uapi/linux/devlink.h
@@ -614,6 +614,8 @@ enum devlink_attr {
 
 	DEVLINK_ATTR_REGION_DIRECT,		/* flag */
 
+	DEVLINK_ATTR_INFO_FUNCTION_UID,		/* string */
+
 	/* Add new attributes above here, update the spec in
 	 * Documentation/netlink/specs/devlink.yaml and re-generate
 	 * net/devlink/netlink_gen.c.
diff --git a/net/devlink/dev.c b/net/devlink/dev.c
index d6e3db300acbe..6c442549722c7 100644
--- a/net/devlink/dev.c
+++ b/net/devlink/dev.c
@@ -763,6 +763,15 @@ int devlink_info_board_serial_number_put(struct devlink_info_req *req,
 }
 EXPORT_SYMBOL_GPL(devlink_info_board_serial_number_put);
 
+int devlink_info_function_uid_put(struct devlink_info_req *req,
+				  const char *fuid)
+{
+	if (!req->msg)
+		return 0;
+	return nla_put_string(req->msg, DEVLINK_ATTR_INFO_FUNCTION_UID, fuid);
+}
+EXPORT_SYMBOL_GPL(devlink_info_function_uid_put);
+
 static int devlink_info_version_put(struct devlink_info_req *req, int attr,
 				    const char *version_name,
 				    const char *version_value,

From cef2d962db93c5995e9cfe05980cf8d4ffea867d Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Thu, 20 Mar 2025 09:59:47 +0100
Subject: [PATCH 2687/2753] net/mlx5: Expose function UID in devlink info

Devlink info allows to expose function UID.
Get the value from PCI VPD and expose it.

$ devlink dev info
pci/0000:08:00.0:
  driver mlx5_core
  serial_number e4397f872caeed218000846daa7d2f49
  board.serial_number MT2314XZ00YA
  function.uid MT2314XZ00YAMLNXS0D0F0
  versions:
      fixed:
        fw.psid MT_0000000894
      running:
        fw.version 28.41.1000
        fw 28.41.1000
      stored:
        fw.version 28.41.1000
        fw 28.41.1000
auxiliary/mlx5_core.eth.0:
  driver mlx5_core.eth
pci/0000:08:00.1:
  driver mlx5_core
  serial_number e4397f872caeed218000846daa7d2f49
  board.serial_number MT2314XZ00YA
  function.uid MT2314XZ00YAMLNXS0D0F1
  versions:
      fixed:
        fw.psid MT_0000000894
      running:
        fw.version 28.41.1000
        fw 28.41.1000
      stored:
        fw.version 28.41.1000
        fw 28.41.1000
auxiliary/mlx5_core.eth.1:
  driver mlx5_core.eth

Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/mellanox/mlx5/core/devlink.c | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
index ebe48f4053795..97bde76af3991 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c
@@ -75,6 +75,19 @@ static int mlx5_devlink_serial_numbers_put(struct mlx5_core_dev *dev,
 		kfree(str);
 	}
 
+	start = pci_vpd_find_ro_info_keyword(vpd_data, vpd_size, "VU", &kw_len);
+	if (start >= 0) {
+		str = kstrndup(vpd_data + start, kw_len, GFP_KERNEL);
+		if (!str) {
+			err = -ENOMEM;
+			goto end;
+		}
+		end = strchrnul(str, ' ');
+		*end = '\0';
+		err = devlink_info_function_uid_put(req, str);
+		kfree(str);
+	}
+
 end:
 	kfree(vpd_data);
 	return err;

From a7b2f660e1bd846bb7cbe39c4434c99eb8ca24ce Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 20 Mar 2025 11:19:20 +0000
Subject: [PATCH 2688/2753] tty: caif: removed unused function debugfs_tx()

Remove debugfs_tx() which was added when the caif driver was added in
commit 9b27105b4a44 ("net-caif-driver: add CAIF serial driver (ldisc)")
but it has never been used.

Flagged by LLVM 19.1.7 W=1 builds.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/caif/caif_serial.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index ed3a589def6b1..90ea3dc0fb109 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -126,15 +126,6 @@ static inline void debugfs_rx(struct ser_device *ser, const u8 *data, int size)
 	ser->rx_blob.data = ser->rx_data;
 	ser->rx_blob.size = size;
 }
-
-static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
-{
-	if (size > sizeof(ser->tx_data))
-		size = sizeof(ser->tx_data);
-	memcpy(ser->tx_data, data, size);
-	ser->tx_blob.data = ser->tx_data;
-	ser->tx_blob.size = size;
-}
 #else
 static inline void debugfs_init(struct ser_device *ser, struct tty_struct *tty)
 {
@@ -151,11 +142,6 @@ static inline void update_tty_status(struct ser_device *ser)
 static inline void debugfs_rx(struct ser_device *ser, const u8 *data, int size)
 {
 }
-
-static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
-{
-}
-
 #endif
 
 static void ldisc_receive(struct tty_struct *tty, const u8 *data,

From 3d136b1b4bb8f809d90d62aa24aa554117a01cde Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Thu, 20 Mar 2025 12:16:04 +0000
Subject: [PATCH 2689/2753] tcp: avoid atomic operations on sk->sk_rmem_alloc

TCP uses generic skb_set_owner_r() and sock_rfree()
for received packets, with socket lock being owned.

Switch to private versions, avoiding two atomic operations
per packet.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/tcp.h       | 15 +++++++++++++++
 net/ipv4/tcp.c          | 18 ++++++++++++++++--
 net/ipv4/tcp_fastopen.c |  2 +-
 net/ipv4/tcp_input.c    |  6 +++---
 4 files changed, 35 insertions(+), 6 deletions(-)

diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4450c384ef178..df04dc09c519d 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -779,6 +779,7 @@ static inline int tcp_bound_to_half_wnd(struct tcp_sock *tp, int pktsize)
 
 /* tcp.c */
 void tcp_get_info(struct sock *, struct tcp_info *);
+void tcp_sock_rfree(struct sk_buff *skb);
 
 /* Read 'sendfile()'-style from a TCP socket */
 int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
@@ -2898,4 +2899,18 @@ enum skb_drop_reason tcp_inbound_hash(struct sock *sk,
 		const void *saddr, const void *daddr,
 		int family, int dif, int sdif);
 
+/* version of skb_set_owner_r() avoiding one atomic_add() */
+static inline void tcp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
+{
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = tcp_sock_rfree;
+
+	sock_owned_by_me(sk);
+	atomic_set(&sk->sk_rmem_alloc,
+		   atomic_read(&sk->sk_rmem_alloc) + skb->truesize);
+
+	sk_forward_alloc_add(sk, -skb->truesize);
+}
+
 #endif	/* _TCP_H */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 6edc441b37023..ea8de00f669d0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1525,11 +1525,25 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 	__tcp_cleanup_rbuf(sk, copied);
 }
 
+/* private version of sock_rfree() avoiding one atomic_sub() */
+void tcp_sock_rfree(struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	unsigned int len = skb->truesize;
+
+	sock_owned_by_me(sk);
+	atomic_set(&sk->sk_rmem_alloc,
+		   atomic_read(&sk->sk_rmem_alloc) - len);
+
+	sk_forward_alloc_add(sk, len);
+	sk_mem_reclaim(sk);
+}
+
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
-	if (likely(skb->destructor == sock_rfree)) {
-		sock_rfree(skb);
+	if (likely(skb->destructor == tcp_sock_rfree)) {
+		tcp_sock_rfree(skb);
 		skb->destructor = NULL;
 		skb->sk = NULL;
 		return skb_attempt_defer_free(skb);
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 1a6b1bc542451..ca40665145c69 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -189,7 +189,7 @@ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb)
 	tcp_segs_in(tp, skb);
 	__skb_pull(skb, tcp_hdrlen(skb));
 	sk_forced_mem_schedule(sk, skb->truesize);
-	skb_set_owner_r(skb, sk);
+	tcp_skb_set_owner_r(skb, sk);
 
 	TCP_SKB_CB(skb)->seq++;
 	TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index a35018e2d0ba2..e1f952fbac48d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5171,7 +5171,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb)
 		if (tcp_is_sack(tp))
 			tcp_grow_window(sk, skb, false);
 		skb_condense(skb);
-		skb_set_owner_r(skb, sk);
+		tcp_skb_set_owner_r(skb, sk);
 	}
 }
 
@@ -5187,7 +5187,7 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,
 	tcp_rcv_nxt_update(tcp_sk(sk), TCP_SKB_CB(skb)->end_seq);
 	if (!eaten) {
 		tcp_add_receive_queue(sk, skb);
-		skb_set_owner_r(skb, sk);
+		tcp_skb_set_owner_r(skb, sk);
 	}
 	return eaten;
 }
@@ -5504,7 +5504,7 @@ tcp_collapse(struct sock *sk, struct sk_buff_head *list, struct rb_root *root,
 			__skb_queue_before(list, skb, nskb);
 		else
 			__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
-		skb_set_owner_r(nskb, sk);
+		tcp_skb_set_owner_r(nskb, sk);
 		mptcp_skb_ext_move(nskb, skb);
 
 		/* Copy data, releasing collapsed skbs. */

From 8adac3c013eea64f2bb0d414030834963d67b245 Mon Sep 17 00:00:00 2001
From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Date: Thu, 20 Mar 2025 05:22:19 -0700
Subject: [PATCH 2690/2753] net: mana: Add speed support in
 mana_get_link_ksettings

Add support for speed in mana ethtool get_link_ksettings
operation. This feature is not supported by all hardware.

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 42 +++++++++++++++++++
 .../ethernet/microsoft/mana/mana_ethtool.c    |  6 +++
 include/net/mana/mana.h                       | 17 ++++++++
 3 files changed, 65 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index e190d5ee51544..b9ca11e205974 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1170,6 +1170,48 @@ static int mana_cfg_vport_steering(struct mana_port_context *apc,
 	return err;
 }
 
+int mana_query_link_cfg(struct mana_port_context *apc)
+{
+	struct net_device *ndev = apc->ndev;
+	struct mana_query_link_config_req req = {};
+	struct mana_query_link_config_resp resp = {};
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_QUERY_LINK_CONFIG,
+			     sizeof(req), sizeof(resp));
+
+	req.vport = apc->port_handle;
+
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+
+	if (err) {
+		netdev_err(ndev, "Failed to query link config: %d\n", err);
+		goto out;
+	}
+
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_QUERY_LINK_CONFIG,
+				   sizeof(resp));
+
+	if (err || resp.hdr.status) {
+		netdev_err(ndev, "Failed to query link config: %d, 0x%x\n", err,
+			   resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+		goto out;
+	}
+
+	if (resp.qos_unconfigured) {
+		err = -EINVAL;
+		goto out;
+	}
+	apc->speed = resp.link_speed;
+	return 0;
+
+out:
+	return err;
+}
+
 int mana_create_wq_obj(struct mana_port_context *apc,
 		       mana_handle_t vport,
 		       u32 wq_type, struct mana_obj_spec *wq_spec,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index c419626073f5f..48234a738d265 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -427,6 +427,12 @@ static int mana_set_ringparam(struct net_device *ndev,
 static int mana_get_link_ksettings(struct net_device *ndev,
 				   struct ethtool_link_ksettings *cmd)
 {
+	struct mana_port_context *apc = netdev_priv(ndev);
+	int err;
+
+	err = mana_query_link_cfg(apc);
+
+	cmd->base.speed = (err) ? SPEED_UNKNOWN : apc->speed;
 	cmd->base.duplex = DUPLEX_FULL;
 	cmd->base.port = PORT_OTHER;
 
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 0d00b24eacafd..5f039ce99adeb 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -468,6 +468,8 @@ struct mana_port_context {
 
 	u16 port_idx;
 
+	u32 speed;
+
 	bool port_is_up;
 	bool port_st_save; /* Saved port state */
 
@@ -497,6 +499,7 @@ struct bpf_prog *mana_xdp_get(struct mana_port_context *apc);
 void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 void mana_query_gf_stats(struct mana_port_context *apc);
+int mana_query_link_cfg(struct mana_port_context *apc);
 int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
 void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
 
@@ -523,6 +526,7 @@ enum mana_command_code {
 	MANA_FENCE_RQ		= 0x20006,
 	MANA_CONFIG_VPORT_RX	= 0x20007,
 	MANA_QUERY_VPORT_CONFIG	= 0x20008,
+	MANA_QUERY_LINK_CONFIG	= 0x2000A,
 
 	/* Privileged commands for the PF mode */
 	MANA_REGISTER_FILTER	= 0x28000,
@@ -531,6 +535,19 @@ enum mana_command_code {
 	MANA_DEREGISTER_HW_PORT	= 0x28004,
 };
 
+/* Query Link Configuration*/
+struct mana_query_link_config_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+}; /* HW DATA */
+
+struct mana_query_link_config_resp {
+	struct gdma_resp_hdr hdr;
+	u32 link_speed;
+	bool qos_unconfigured;
+	u8 reserved[3];
+}; /* HW DATA */
+
 /* Query Device Configuration */
 struct mana_query_device_cfg_req {
 	struct gdma_req_hdr hdr;

From 289f9c4efc2982c5754724b30825518ddfe095f2 Mon Sep 17 00:00:00 2001
From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Date: Thu, 20 Mar 2025 05:22:20 -0700
Subject: [PATCH 2691/2753] net: mana: Implement set_link_ksettings in ethtool
 for speed

Add support for ethtool_set_link_ksettings for mana.
Set speed information of the port using ethtool. This
feature is not supported by all hardware.

Before the change:
$ethtool -s enP30832s1 speed 100
>netlink error: Operation not supported
$ethtool enP30832s1
>Settings for enP30832s1:
        Supported ports: [  ]
        Supported link modes:   Not reported
        Supported pause frame use: No
        Supports auto-negotiation: No
        Supported FEC modes: Not reported
        Advertised link modes:  Not reported
        Advertised pause frame use: No
        Advertised auto-negotiation: No
        Advertised FEC modes: Not reported
        Speed: Unknown!
        Duplex: Full
        Auto-negotiation: off
        Port: Other
        PHYAD: 0
        Transceiver: internal
        Link detected: yes

After the change:
$ethtool -s enP30832s1 speed 100
$ethtool enP30832s1
>Settings for enP30832s1:
        Supported ports: [  ]
        Supported link modes:   Not reported
        Supported pause frame use: No
        Supports auto-negotiation: No
        Supported FEC modes: Not reported
        Advertised link modes:  Not reported
        Advertised pause frame use: No
        Advertised auto-negotiation: No
        Advertised FEC modes: Not reported
        Speed: 100Mb/s
        Duplex: Full
        Auto-negotiation: off
        Port: Other
        PHYAD: 0
        Transceiver: internal
        Link detected: yes

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/microsoft/mana/mana_en.c | 39 +++++++++++++++++++
 .../ethernet/microsoft/mana/mana_ethtool.c    | 13 +++++++
 include/net/mana/mana.h                       | 16 ++++++++
 3 files changed, 68 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index b9ca11e205974..f7e7e53528c36 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -1212,6 +1212,45 @@ int mana_query_link_cfg(struct mana_port_context *apc)
 	return err;
 }
 
+int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed)
+{
+	struct mana_set_bw_clamp_req req = {};
+	struct mana_set_bw_clamp_resp resp = {};
+	struct net_device *ndev = apc->ndev;
+	int err;
+
+	mana_gd_init_req_hdr(&req.hdr, MANA_SET_BW_CLAMP,
+			     sizeof(req), sizeof(resp));
+	req.vport = apc->port_handle;
+	req.link_speed = speed;
+	req.enable_clamping = TRI_STATE_TRUE;
+
+	err = mana_send_request(apc->ac, &req, sizeof(req), &resp,
+				sizeof(resp));
+
+	if (err) {
+		netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
+			   speed, err);
+		return err;
+	}
+
+	err = mana_verify_resp_hdr(&resp.hdr, MANA_SET_BW_CLAMP,
+				   sizeof(resp));
+
+	if (err || resp.hdr.status) {
+		netdev_err(ndev, "Failed to set bandwidth clamp: %d, 0x%x\n", err,
+			   resp.hdr.status);
+		if (!err)
+			err = -EPROTO;
+		return err;
+	}
+
+	if (resp.qos_unconfigured)
+		netdev_info(ndev, "QoS is unconfigured\n");
+
+	return 0;
+}
+
 int mana_create_wq_obj(struct mana_port_context *apc,
 		       mana_handle_t vport,
 		       u32 wq_type, struct mana_obj_spec *wq_spec,
diff --git a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
index 48234a738d265..b29d0fe0a2014 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_ethtool.c
@@ -439,6 +439,18 @@ static int mana_get_link_ksettings(struct net_device *ndev,
 	return 0;
 }
 
+static int mana_set_link_ksettings(struct net_device *ndev,
+				   const struct ethtool_link_ksettings *cmd)
+{
+	struct mana_port_context *apc = netdev_priv(ndev);
+	int err;
+
+	err = mana_set_bw_clamp(apc, cmd->base.speed);
+
+	apc->speed = (err) ? apc->speed : cmd->base.speed;
+	return 0;
+}
+
 const struct ethtool_ops mana_ethtool_ops = {
 	.get_ethtool_stats	= mana_get_ethtool_stats,
 	.get_sset_count		= mana_get_sset_count,
@@ -453,5 +465,6 @@ const struct ethtool_ops mana_ethtool_ops = {
 	.get_ringparam          = mana_get_ringparam,
 	.set_ringparam          = mana_set_ringparam,
 	.get_link_ksettings	= mana_get_link_ksettings,
+	.set_link_ksettings	= mana_set_link_ksettings,
 	.get_link		= ethtool_op_get_link,
 };
diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
index 5f039ce99adeb..b4c66ce9ee3aa 100644
--- a/include/net/mana/mana.h
+++ b/include/net/mana/mana.h
@@ -500,6 +500,7 @@ void mana_chn_setxdp(struct mana_port_context *apc, struct bpf_prog *prog);
 int mana_bpf(struct net_device *ndev, struct netdev_bpf *bpf);
 void mana_query_gf_stats(struct mana_port_context *apc);
 int mana_query_link_cfg(struct mana_port_context *apc);
+int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed);
 int mana_pre_alloc_rxbufs(struct mana_port_context *apc, int mtu, int num_queues);
 void mana_pre_dealloc_rxbufs(struct mana_port_context *apc);
 
@@ -527,6 +528,7 @@ enum mana_command_code {
 	MANA_CONFIG_VPORT_RX	= 0x20007,
 	MANA_QUERY_VPORT_CONFIG	= 0x20008,
 	MANA_QUERY_LINK_CONFIG	= 0x2000A,
+	MANA_SET_BW_CLAMP	= 0x2000B,
 
 	/* Privileged commands for the PF mode */
 	MANA_REGISTER_FILTER	= 0x28000,
@@ -548,6 +550,20 @@ struct mana_query_link_config_resp {
 	u8 reserved[3];
 }; /* HW DATA */
 
+/* Set Bandwidth Clamp*/
+struct mana_set_bw_clamp_req {
+	struct gdma_req_hdr hdr;
+	mana_handle_t vport;
+	enum TRI_STATE enable_clamping;
+	u32 link_speed;
+}; /* HW DATA */
+
+struct mana_set_bw_clamp_resp {
+	struct gdma_resp_hdr hdr;
+	bool qos_unconfigured;
+	u8 reserved[7];
+}; /* HW DATA */
+
 /* Query Device Configuration */
 struct mana_query_device_cfg_req {
 	struct gdma_req_hdr hdr;

From e1305d285d4aea6ce8ffa02ad81dc86b8136bbb5 Mon Sep 17 00:00:00 2001
From: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Date: Thu, 20 Mar 2025 05:22:21 -0700
Subject: [PATCH 2692/2753] net: mana: Handle unsupported HWC commands

If any of the HWC commands are not recognized by the
underlying hardware, the hardware returns the response
header status of -1. Log the information using
netdev_info_once to avoid multiple error logs in dmesg.

Signed-off-by: Erni Sri Satya Vennela <ernis@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/microsoft/mana/hw_channel.c |  4 ++++
 drivers/net/ethernet/microsoft/mana/mana_en.c    | 11 +++++++++++
 2 files changed, 15 insertions(+)

diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
index 1ba49602089bb..58cfd247d8c5a 100644
--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
+++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
@@ -871,6 +871,10 @@ int mana_hwc_send_request(struct hw_channel_context *hwc, u32 req_len,
 	}
 
 	if (ctx->status_code && ctx->status_code != GDMA_STATUS_MORE_ENTRIES) {
+		if (ctx->status_code == -1) {
+			err = -EOPNOTSUPP;
+			goto out;
+		}
 		dev_err(hwc->dev, "HWC: Failed hw_channel req: 0x%x\n",
 			ctx->status_code);
 		err = -EPROTO;
diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
index f7e7e53528c36..3cc17991d925c 100644
--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
+++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
@@ -788,6 +788,9 @@ static int mana_send_request(struct mana_context *ac, void *in_buf,
 	err = mana_gd_send_request(gc, in_len, in_buf, out_len,
 				   out_buf);
 	if (err || resp->status) {
+		if (err == -EOPNOTSUPP)
+			return err;
+
 		dev_err(dev, "Failed to send mana message: %d, 0x%x\n",
 			err, resp->status);
 		return err ? err : -EPROTO;
@@ -1186,6 +1189,10 @@ int mana_query_link_cfg(struct mana_port_context *apc)
 				sizeof(resp));
 
 	if (err) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_QUERY_LINK_CONFIG not supported\n");
+			goto out;
+		}
 		netdev_err(ndev, "Failed to query link config: %d\n", err);
 		goto out;
 	}
@@ -1229,6 +1236,10 @@ int mana_set_bw_clamp(struct mana_port_context *apc, u32 speed)
 				sizeof(resp));
 
 	if (err) {
+		if (err == -EOPNOTSUPP) {
+			netdev_info_once(ndev, "MANA_SET_BW_CLAMP not supported\n");
+			return err;
+		}
 		netdev_err(ndev, "Failed to set bandwidth clamp for speed %u, err = %d",
 			   speed, err);
 		return err;

From 53a56504e239891166f045e58a3347a47604ddfd Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Thu, 20 Mar 2025 13:44:51 +0100
Subject: [PATCH 2693/2753] xfrm: Remove unnecessary strscpy_pad() size
 arguments

If the destination buffer has a fixed length, strscpy_pad()
automatically determines its size using sizeof() when the argument is
omitted. This makes the explicit sizeof() calls unnecessary - remove
them.

No functional changes intended.

Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Signed-off-by: NipaLocal <nipa@local>
---
 net/xfrm/xfrm_user.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
index 08c6d6f0179fb..a4d92ea43e3d3 100644
--- a/net/xfrm/xfrm_user.c
+++ b/net/xfrm/xfrm_user.c
@@ -1161,7 +1161,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	algo = nla_data(nla);
-	strscpy_pad(algo->alg_name, auth->alg_name, sizeof(algo->alg_name));
+	strscpy_pad(algo->alg_name, auth->alg_name);
 
 	if (redact_secret && auth->alg_key_len)
 		memset(algo->alg_key, 0, (auth->alg_key_len + 7) / 8);
@@ -1174,7 +1174,7 @@ static int copy_to_user_auth(struct xfrm_algo_auth *auth, struct sk_buff *skb)
 	if (!nla)
 		return -EMSGSIZE;
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, auth->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, auth->alg_name);
 	ap->alg_key_len = auth->alg_key_len;
 	ap->alg_trunc_len = auth->alg_trunc_len;
 	if (redact_secret && auth->alg_key_len)
@@ -1195,7 +1195,7 @@ static int copy_to_user_aead(struct xfrm_algo_aead *aead, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, aead->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, aead->alg_name);
 	ap->alg_key_len = aead->alg_key_len;
 	ap->alg_icv_len = aead->alg_icv_len;
 
@@ -1217,7 +1217,7 @@ static int copy_to_user_ealg(struct xfrm_algo *ealg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, ealg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, ealg->alg_name);
 	ap->alg_key_len = ealg->alg_key_len;
 
 	if (redact_secret && ealg->alg_key_len)
@@ -1238,7 +1238,7 @@ static int copy_to_user_calg(struct xfrm_algo *calg, struct sk_buff *skb)
 		return -EMSGSIZE;
 
 	ap = nla_data(nla);
-	strscpy_pad(ap->alg_name, calg->alg_name, sizeof(ap->alg_name));
+	strscpy_pad(ap->alg_name, calg->alg_name);
 	ap->alg_key_len = 0;
 
 	return 0;

From 7930dfd4700235fee4c11520a09ab04ddefcf45e Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 20 Mar 2025 09:51:03 -0700
Subject: [PATCH 2694/2753] net: hold netdev reference during qdisc_create
 request_module

Eric reports that by the time we call netdev_lock_ops after
rtnl_unlock/rtnl_lock, the dev might point to an invalid device.
Add extra dev_hold/dev_put to make sure the device pointer
is still valid after rtnl_unlock.

Fixes: a0527ee2df3f ("net: hold netdev instance lock during qdisc ndo_setup_tc")
Reported-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/netdev/20250305163732.2766420-1-sdf@fomichev.me/T/#me8dfd778ea4c4463acab55644e3f9836bc608771
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_api.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index aef39f6dc6a8a..85ddb811780cf 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -1280,11 +1280,13 @@ static struct Qdisc *qdisc_create(struct net_device *dev,
 			 * We replay the request because the device may
 			 * go away in the mean time.
 			 */
+			dev_hold(dev);
 			netdev_unlock_ops(dev);
 			rtnl_unlock();
 			request_module(NET_SCH_ALIAS_PREFIX "%s", name);
 			rtnl_lock();
 			netdev_lock_ops(dev);
+			dev_put(dev);
 			ops = qdisc_lookup_ops(kind);
 			if (ops != NULL) {
 				/* We will try again qdisc_lookup_ops,

From 37cc168a892c907650d46082b75a2809b5a3bf6f Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Thu, 20 Mar 2025 17:57:10 +0000
Subject: [PATCH 2695/2753] sfc: rip out MDIO support

Unlike Siena, no EF10 board ever had an external PHY, and consequently
 MDIO handling isn't even built into the firmware.  Since Siena has
 been split out into its own driver, the MDIO code can be deleted from
 the sfc driver.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/sfc/ef100_netdev.c     |  1 -
 drivers/net/ethernet/sfc/efx.c              | 24 ---------
 drivers/net/ethernet/sfc/mcdi_port.c        | 59 +--------------------
 drivers/net/ethernet/sfc/mcdi_port_common.c | 11 ----
 drivers/net/ethernet/sfc/net_driver.h       |  6 +--
 5 files changed, 2 insertions(+), 99 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef100_netdev.c b/drivers/net/ethernet/sfc/ef100_netdev.c
index 7f7d560cb2b4c..d941f073f1ebf 100644
--- a/drivers/net/ethernet/sfc/ef100_netdev.c
+++ b/drivers/net/ethernet/sfc/ef100_netdev.c
@@ -452,7 +452,6 @@ int ef100_probe_netdev(struct efx_probe_data *probe_data)
 				  NETIF_F_HIGHDMA | NETIF_F_ALL_TSO;
 	netif_set_tso_max_segs(net_dev,
 			       ESE_EF100_DP_GZ_TSO_MAX_HDR_NUM_SEGS_DEFAULT);
-	efx->mdio.dev = net_dev;
 
 	rc = efx_ef100_init_datapath_caps(efx);
 	if (rc < 0)
diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c
index 650136dfc642f..112e55b98ed3b 100644
--- a/drivers/net/ethernet/sfc/efx.c
+++ b/drivers/net/ethernet/sfc/efx.c
@@ -474,28 +474,6 @@ void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs,
 	}
 }
 
-/**************************************************************************
- *
- * ioctls
- *
- *************************************************************************/
-
-/* Net device ioctl
- * Context: process, rtnl_lock() held.
- */
-static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	struct mii_ioctl_data *data = if_mii(ifr);
-
-	/* Convert phy_id from older PRTAD/DEVAD format */
-	if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) &&
-	    (data->phy_id & 0xfc00) == 0x0400)
-		data->phy_id ^= MDIO_PHY_ID_C45 | 0x0400;
-
-	return mdio_mii_ioctl(&efx->mdio, data, cmd);
-}
-
 /**************************************************************************
  *
  * Kernel net device interface
@@ -593,7 +571,6 @@ static const struct net_device_ops efx_netdev_ops = {
 	.ndo_tx_timeout		= efx_watchdog,
 	.ndo_start_xmit		= efx_hard_start_xmit,
 	.ndo_validate_addr	= eth_validate_addr,
-	.ndo_eth_ioctl		= efx_ioctl,
 	.ndo_change_mtu		= efx_change_mtu,
 	.ndo_set_mac_address	= efx_set_mac_address,
 	.ndo_set_rx_mode	= efx_set_rx_mode,
@@ -1201,7 +1178,6 @@ static int efx_pci_probe(struct pci_dev *pci_dev,
 	rc = efx_init_struct(efx, pci_dev);
 	if (rc)
 		goto fail1;
-	efx->mdio.dev = net_dev;
 
 	pci_info(pci_dev, "Solarflare NIC detected\n");
 
diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c
index ad4694fa3ddae..7b236d291d8c2 100644
--- a/drivers/net/ethernet/sfc/mcdi_port.c
+++ b/drivers/net/ethernet/sfc/mcdi_port.c
@@ -17,58 +17,6 @@
 #include "selftest.h"
 #include "mcdi_port_common.h"
 
-static int efx_mcdi_mdio_read(struct net_device *net_dev,
-			      int prtad, int devad, u16 addr)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_READ_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_READ_OUT_LEN);
-	size_t outlen;
-	int rc;
-
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_BUS, efx->mdio_bus);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_PRTAD, prtad);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_DEVAD, devad);
-	MCDI_SET_DWORD(inbuf, MDIO_READ_IN_ADDR, addr);
-
-	rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_READ, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
-		return rc;
-
-	if (MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS) !=
-	    MC_CMD_MDIO_STATUS_GOOD)
-		return -EIO;
-
-	return (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE);
-}
-
-static int efx_mcdi_mdio_write(struct net_device *net_dev,
-			       int prtad, int devad, u16 addr, u16 value)
-{
-	struct efx_nic *efx = efx_netdev_priv(net_dev);
-	MCDI_DECLARE_BUF(inbuf, MC_CMD_MDIO_WRITE_IN_LEN);
-	MCDI_DECLARE_BUF(outbuf, MC_CMD_MDIO_WRITE_OUT_LEN);
-	size_t outlen;
-	int rc;
-
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_BUS, efx->mdio_bus);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_PRTAD, prtad);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_DEVAD, devad);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_ADDR, addr);
-	MCDI_SET_DWORD(inbuf, MDIO_WRITE_IN_VALUE, value);
-
-	rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_WRITE, inbuf, sizeof(inbuf),
-			  outbuf, sizeof(outbuf), &outlen);
-	if (rc)
-		return rc;
-
-	if (MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS) !=
-	    MC_CMD_MDIO_STATUS_GOOD)
-		return -EIO;
-
-	return 0;
-}
 
 u32 efx_mcdi_phy_get_caps(struct efx_nic *efx)
 {
@@ -97,12 +45,7 @@ int efx_mcdi_port_probe(struct efx_nic *efx)
 {
 	int rc;
 
-	/* Set up MDIO structure for PHY */
-	efx->mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
-	efx->mdio.mdio_read = efx_mcdi_mdio_read;
-	efx->mdio.mdio_write = efx_mcdi_mdio_write;
-
-	/* Fill out MDIO structure, loopback modes, and initial link state */
+	/* Fill out loopback modes and initial link state */
 	rc = efx_mcdi_phy_probe(efx);
 	if (rc != 0)
 		return rc;
diff --git a/drivers/net/ethernet/sfc/mcdi_port_common.c b/drivers/net/ethernet/sfc/mcdi_port_common.c
index 76ea26722ca46..dae684194ac8c 100644
--- a/drivers/net/ethernet/sfc/mcdi_port_common.c
+++ b/drivers/net/ethernet/sfc/mcdi_port_common.c
@@ -448,15 +448,6 @@ int efx_mcdi_phy_probe(struct efx_nic *efx)
 	efx->phy_data = phy_data;
 	efx->phy_type = phy_data->type;
 
-	efx->mdio_bus = phy_data->channel;
-	efx->mdio.prtad = phy_data->port;
-	efx->mdio.mmds = phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22);
-	efx->mdio.mode_support = 0;
-	if (phy_data->mmd_mask & (1 << MC_CMD_MMD_CLAUSE22))
-		efx->mdio.mode_support |= MDIO_SUPPORTS_C22;
-	if (phy_data->mmd_mask & ~(1 << MC_CMD_MMD_CLAUSE22))
-		efx->mdio.mode_support |= MDIO_SUPPORTS_C45 | MDIO_EMULATE_C22;
-
 	caps = MCDI_DWORD(outbuf, GET_LINK_OUT_CAP);
 	if (caps & (1 << MC_CMD_PHY_CAP_AN_LBN))
 		mcdi_to_ethtool_linkset(phy_data->media, caps,
@@ -546,8 +537,6 @@ void efx_mcdi_phy_get_link_ksettings(struct efx_nic *efx, struct ethtool_link_ks
 	cmd->base.port = mcdi_to_ethtool_media(phy_cfg->media);
 	cmd->base.phy_address = phy_cfg->port;
 	cmd->base.autoneg = !!(efx->link_advertising[0] & ADVERTISED_Autoneg);
-	cmd->base.mdio_support = (efx->mdio.mode_support &
-			      (MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22));
 
 	mcdi_to_ethtool_linkset(phy_cfg->media, phy_cfg->supported_cap,
 				cmd->link_modes.supported);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 8b0689f749b53..6912661b5a3dd 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -15,7 +15,7 @@
 #include <linux/ethtool.h>
 #include <linux/if_vlan.h>
 #include <linux/timer.h>
-#include <linux/mdio.h>
+#include <linux/mii.h>
 #include <linux/list.h>
 #include <linux/pci.h>
 #include <linux/device.h>
@@ -956,8 +956,6 @@ struct efx_mae;
  * @stats_buffer: DMA buffer for statistics
  * @phy_type: PHY type
  * @phy_data: PHY private data (including PHY-specific stats)
- * @mdio: PHY MDIO interface
- * @mdio_bus: PHY MDIO bus ID (only used by Siena)
  * @phy_mode: PHY operating mode. Serialised by @mac_lock.
  * @link_advertising: Autonegotiation advertising flags
  * @fec_config: Forward Error Correction configuration flags.  For bit positions
@@ -1132,8 +1130,6 @@ struct efx_nic {
 
 	unsigned int phy_type;
 	void *phy_data;
-	struct mdio_if_info mdio;
-	unsigned int mdio_bus;
 	enum efx_phy_mode phy_mode;
 
 	__ETHTOOL_DECLARE_LINK_MODE_MASK(link_advertising);

From 3edff3cba5004a111e1c5ea3c63e79ef3b6116ce Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Thu, 20 Mar 2025 17:57:11 +0000
Subject: [PATCH 2696/2753] sfc: update MCDI protocol headers

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/sfc/mcdi_pcol.h | 20158 ++++++++++---------------
 1 file changed, 8186 insertions(+), 11972 deletions(-)

diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h
index cd297e19cddcc..9cb339c461fba 100644
--- a/drivers/net/ethernet/sfc/mcdi_pcol.h
+++ b/drivers/net/ethernet/sfc/mcdi_pcol.h
@@ -72,19 +72,19 @@
  *               |                      \------- Error
  *               \------------------------------ Resync (always set)
  *
- * The client writes it's request into MC shared memory, and rings the
- * doorbell. Each request is completed by either by the MC writing
+ * The client writes its request into MC shared memory, and rings the
+ * doorbell. Each request is completed either by the MC writing
  * back into shared memory, or by writing out an event.
  *
  * All MCDI commands support completion by shared memory response. Each
  * request may also contain additional data (accounted for by HEADER.LEN),
- * and some response's may also contain additional data (again, accounted
+ * and some responses may also contain additional data (again, accounted
  * for by HEADER.LEN).
  *
  * Some MCDI commands support completion by event, in which any associated
  * response data is included in the event.
  *
- * The protocol requires one response to be delivered for every request, a
+ * The protocol requires one response to be delivered for every request; a
  * request should not be sent unless the response for the previous request
  * has been received (either by polling shared memory, or by receiving
  * an event).
@@ -165,6 +165,7 @@
 #define FSE_AZ_EV_CODE_MCDI_EVRESPONSE 0xc
 
 
+
 #define MC_CMD_ERR_CODE_OFST 0
 #define MC_CMD_ERR_PROXY_PENDING_HANDLE_OFST 4
 
@@ -321,7 +322,7 @@
 /* enum: The requesting client is not a function */
 #define          MC_CMD_ERR_CLIENT_NOT_FN 0x100c
 /* enum: The requested operation might require the command to be passed between
- * MCs, and thetransport doesn't support that. Should only ever been seen over
+ * MCs, and the transport doesn't support that. Should only ever been seen over
  * the UART.
  */
 #define          MC_CMD_ERR_TRANSPORT_NOPROXY 0x100d
@@ -358,7 +359,7 @@
  * sub-variant switching.
  */
 #define          MC_CMD_ERR_FILTERS_PRESENT 0x1014
-/* enum: The clock whose frequency you've attempted to set set doesn't exist on
+/* enum: The clock whose frequency you've attempted to set doesn't exist on
  * this NIC
  */
 #define          MC_CMD_ERR_NO_CLOCK 0x1015
@@ -387,25 +388,6 @@
  */
 #define          MC_CMD_ERR_PIOBUFS_PRESENT 0x101b
 
-/* MC_CMD_RESOURCE_SPECIFIER enum */
-/* enum: Any */
-#define          MC_CMD_RESOURCE_INSTANCE_ANY 0xffffffff
-#define          MC_CMD_RESOURCE_INSTANCE_NONE 0xfffffffe /* enum */
-
-/* MC_CMD_FPGA_FLASH_INDEX enum */
-#define          MC_CMD_FPGA_FLASH_PRIMARY 0x0 /* enum */
-#define          MC_CMD_FPGA_FLASH_SECONDARY 0x1 /* enum */
-
-/* MC_CMD_EXTERNAL_MAE_LINK_MODE enum */
-/* enum: Legacy mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_LEGACY 0x0
-/* enum: Switchdev mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_SWITCHDEV 0x1
-/* enum: Bootstrap mode as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_BOOTSTRAP 0x2
-/* enum: Link-mode change is in-progress as described in XN-200039-TC. */
-#define          MC_CMD_EXTERNAL_MAE_LINK_MODE_PENDING 0xf
-
 /* PCIE_INTERFACE enum: From EF100 onwards, SFC products can have multiple PCIe
  * interfaces. There is a need to refer to interfaces explicitly from drivers
  * (for example, a management driver on one interface administering a function
@@ -424,6 +406,14 @@
  * an on-NIC ARM module is expected to be connected.
  */
 #define          PCIE_INTERFACE_NIC_EMBEDDED 0x1
+/* enum: The PCIe logical interface 0. It is an alias for HOST_PRIMARY. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_0 0x0
+/* enum: The PCIe logical interface 1. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_1 0x2
+/* enum: The PCIe logical interface 2. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_2 0x3
+/* enum: The PCIe logical interface 3. */
+#define          PCIE_INTERFACE_PCIE_HOST_INTF_3 0x4
 /* enum: For MCDI commands issued over a PCIe interface, this value is
  * translated into the interface over which the command was issued. Not
  * meaningful for other MCDI transports.
@@ -640,7 +630,11 @@
  * be allocated by different counter blocks, so e.g. AR counter 42 is different
  * from CT counter 42. Generation counts are also type-specific. This value is
  * also present in the header of streaming counter packets, in the IDENTIFIER
- * field (see packetiser packet format definitions).
+ * field (see packetiser packet format definitions). Also note that LACP
+ * counter IDs are not allocated individually, instead the counter IDs are
+ * directly tied to the LACP balance table indices. These in turn are allocated
+ * in large contiguous blocks as a LAG config. Calling MAE_COUNTER_ALLOC/FREE
+ * with an LACP counter type will return EPERM.
  */
 /* enum: Action Rule counters - can be referenced in AR response. */
 #define          MAE_COUNTER_TYPE_AR 0x0
@@ -648,6 +642,14 @@
 #define          MAE_COUNTER_TYPE_CT 0x1
 /* enum: Outer Rule counters - can be referenced in OR response. */
 #define          MAE_COUNTER_TYPE_OR 0x2
+/* enum: LACP counters - linked to LACP balance table entries. */
+#define          MAE_COUNTER_TYPE_LACP 0x3
+
+/* MAE_COUNTER_ID enum: ID of allocated counter or counter list. */
+/* enum: A counter ID that is guaranteed never to represent a real counter or
+ * counter list.
+ */
+#define          MAE_COUNTER_ID_NULL 0xffffffff
 
 /* TABLE_ID enum: Unique IDs for tables. The 32-bit ID values have been
  * structured with bits [31:24] reserved (0), [23:16] indicating which major
@@ -656,7 +658,9 @@
  * variations of the same table. (All of the tables currently defined within
  * the streaming engines are listed here, but this does not imply that they are
  * all supported - MC_CMD_TABLE_LIST returns the list of actually supported
- * tables.)
+ * tables.) The DPU offload engines' enumerators follow a deliberate pattern:
+ * 0x01010000 + is_dpu_net * 0x10000 + is_wr_or_tx * 0x8000 + is_lite_pipe *
+ * 0x1000 + oe_engine_type * 0x100 + oe_instance_within_pipe * 0x10
  */
 /* enum: Outer_Rule_Table in the MAE - refer to SF-123102-TC. */
 #define          TABLE_ID_OUTER_RULE_TABLE 0x10000
@@ -694,45 +698,70 @@
 #define          TABLE_ID_RSS_CONTEXT_TABLE 0x20200
 /* enum: Indirection_Table in VNIC Rx - refer to SF-123102-TC. */
 #define          TABLE_ID_INDIRECTION_TABLE 0x20300
-
-/* TABLE_COMPRESSED_VLAN enum: Compressed VLAN TPID as used by some field
- * types; can be calculated by (((ether_type_msb >> 2) & 0x4) ^ 0x4) |
- * (ether_type_msb & 0x3);
- */
-#define          TABLE_COMPRESSED_VLAN_TPID_8100 0x5 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_88A8 0x4 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9100 0x1 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9200 0x2 /* enum */
-#define          TABLE_COMPRESSED_VLAN_TPID_9300 0x3 /* enum */
-
-/* TABLE_NAT_DIR enum: NAT direction. */
-#define          TABLE_NAT_DIR_SOURCE 0x0 /* enum */
-#define          TABLE_NAT_DIR_DEST 0x1 /* enum */
-
-/* TABLE_RSS_KEY_MODE enum: Defines how the value for Toeplitz hashing for RSS
- * is constructed as a concatenation (indicated here by "++") of packet header
- * fields.
- */
-/* enum: IP src addr ++ IP dst addr */
-#define          TABLE_RSS_KEY_MODE_SA_DA 0x0
-/* enum: IP src addr ++ IP dst addr ++ TCP/UDP src port ++ TCP/UDP dst port */
-#define          TABLE_RSS_KEY_MODE_SA_DA_SP_DP 0x1
-/* enum: IP src addr */
-#define          TABLE_RSS_KEY_MODE_SA 0x2
-/* enum: IP dst addr */
-#define          TABLE_RSS_KEY_MODE_DA 0x3
-/* enum: IP src addr ++ TCP/UDP src port */
-#define          TABLE_RSS_KEY_MODE_SA_SP 0x4
-/* enum: IP dest addr ++ TCP dest port */
-#define          TABLE_RSS_KEY_MODE_DA_DP 0x5
-/* enum: Nothing (produces input of 0, resulting in output hash of 0) */
-#define          TABLE_RSS_KEY_MODE_NONE 0x7
-
-/* TABLE_RSS_SPREAD_MODE enum: RSS spreading mode. */
-/* enum: RSS uses Indirection_Table lookup. */
-#define          TABLE_RSS_SPREAD_MODE_INDIRECTION 0x0
-/* enum: RSS uses even spreading calculation. */
-#define          TABLE_RSS_SPREAD_MODE_EVEN 0x1
+/* enum: DPU.host read pipe first CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_RD_CRC0_OE_PROFILE 0x1010000
+/* enum: DPU.host read pipe second CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_RD_CRC1_OE_PROFILE 0x1010010
+/* enum: DPU.host write pipe first CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_WR_CRC0_OE_PROFILE 0x1018000
+/* enum: DPU.host write pipe second CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_HOST_WR_CRC1_OE_PROFILE 0x1018010
+/* enum: DPU.net 'full' receive pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CRC0_OE_PROFILE 0x1020000
+/* enum: DPU.net 'full' receive pipe first checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CSUM0_OE_PROFILE 0x1020100
+/* enum: DPU.net 'full' receive pipe second checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_CSUM1_OE_PROFILE 0x1020110
+/* enum: DPU.net 'full' receive pipe AES-GCM offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RX_AES_GCM0_OE_PROFILE 0x1020200
+/* enum: DPU.net 'lite' receive pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RXLITE_CRC0_OE_PROFILE 0x1021000
+/* enum: DPU.net 'lite' receive pipe checksum offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_RXLITE_CSUM0_OE_PROFILE 0x1021100
+/* enum: DPU.net 'full' transmit pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CRC0_OE_PROFILE 0x1028000
+/* enum: DPU.net 'full' transmit pipe first checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CSUM0_OE_PROFILE 0x1028100
+/* enum: DPU.net 'full' transmit pipe second checksum offload engine profiles -
+ * refer to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_CSUM1_OE_PROFILE 0x1028110
+/* enum: DPU.net 'full' transmit pipe AES-GCM offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TX_AES_GCM0_OE_PROFILE 0x1028200
+/* enum: DPU.net 'lite' transmit pipe CRC offload engine profiles - refer to
+ * XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TXLITE_CRC0_OE_PROFILE 0x1029000
+/* enum: DPU.net 'lite' transmit pipe checksum offload engine profiles - refer
+ * to XN-200147-AN.
+ */
+#define          TABLE_ID_DPU_NET_TXLITE_CSUM0_OE_PROFILE 0x1029100
 
 /* TABLE_FIELD_ID enum: Unique IDs for fields. Related concepts have been
  * loosely grouped together into blocks with gaps for expansion, but the values
@@ -1026,6 +1055,16 @@
 #define          TABLE_FIELD_ID_BAL_TBL_BASE_DIV64 0xde
 /* enum: Length of balance table region: 0=>64, 1=>128, 2=>256. */
 #define          TABLE_FIELD_ID_BAL_TBL_LEN_ID 0xdf
+/* enum: LACP LAG ID (i.e. the low 3 bits of LACP LAG mport ID), indexing
+ * LACP_LAG_Config_Table. Refer to SF-123102-TC.
+ */
+#define          TABLE_FIELD_ID_LACP_LAG_ID 0xe0
+/* enum: Address in LACP_Balance_Table. The balance table is partitioned
+ * between LAGs according to the settings in LACP_LAG_Config_Table and then
+ * indexed by the LACP hash, providing the mapping to destination mports. Refer
+ * to SF-123102-TC.
+ */
+#define          TABLE_FIELD_ID_BAL_TBL_ADDR 0xe1
 /* enum: UDP port to match for UDP-based encapsulations; required to be 0 for
  * other encapsulation types.
  */
@@ -1082,6 +1121,55 @@
 #define          TABLE_FIELD_ID_INDIR_TBL_LEN_ID 0x105
 /* enum: An offset to be applied to the base destination queue ID. */
 #define          TABLE_FIELD_ID_INDIR_OFFSET 0x106
+/* enum: DPU offload engine profile ID to address. */
+#define          TABLE_FIELD_ID_OE_PROFILE 0x3e8
+/* enum: Width of the CRC to calculate - see CRC_VARIANT enum. */
+#define          TABLE_FIELD_ID_CRC_VARIANT 0x3f2
+/* enum: If set, reflect the bits of each input byte, bit 7 is LSB, bit 0 is
+ * MSB. If clear, bit 7 is MSB, bit 0 is LSB.
+ */
+#define          TABLE_FIELD_ID_CRC_REFIN 0x3f3
+/* enum: If set, reflect the bits of each output byte, bit 7 is LSB, bit 0 is
+ * MSB. If clear, bit 7 is MSB, bit 0 is LSB.
+ */
+#define          TABLE_FIELD_ID_CRC_REFOUT 0x3f4
+/* enum: If set, invert every bit of the output value. */
+#define          TABLE_FIELD_ID_CRC_INVOUT 0x3f5
+/* enum: The CRC polynomial to use for checksumming, in normal form. */
+#define          TABLE_FIELD_ID_CRC_POLY 0x3f6
+/* enum: Operation for the checksum engine to perform - see DPU_CSUM_OP enum.
+ */
+#define          TABLE_FIELD_ID_CSUM_OP 0x410
+/* enum: Byte offset of checksum relative to region_start (for VALIDATE_*
+ * operations only).
+ */
+#define          TABLE_FIELD_ID_CSUM_OFFSET 0x411
+/* enum: Indicates there is additional data on OPR bus that needs to be
+ * incorporated into the payload checksum.
+ */
+#define          TABLE_FIELD_ID_CSUM_OPR_ADDITIONAL_DATA 0x412
+/* enum: Log2 data size of additional data on OPR bus. */
+#define          TABLE_FIELD_ID_CSUM_OPR_DATA_SIZE_LOG2 0x413
+/* enum: 4 byte offset of where to find the additional data on the OPR bus. */
+#define          TABLE_FIELD_ID_CSUM_OPR_4B_OFF 0x414
+/* enum: Operation type for the AES-GCM core - see GCM_OP_CODE enum. */
+#define          TABLE_FIELD_ID_GCM_OP_CODE 0x41a
+/* enum: Key length - AES_KEY_LEN enum. */
+#define          TABLE_FIELD_ID_GCM_KEY_LEN 0x41b
+/* enum: OPR 4 byte offset for ICV or GHASH output (only in BULK_* mode) or
+ * IPSEC descrypt output.
+ */
+#define          TABLE_FIELD_ID_GCM_OPR_4B_OFFSET 0x41c
+/* enum: If OP_CODE is BULK_*, indicates Emit GHASH (Fragment mode). Else,
+ * indicates IPSEC-ESN mode.
+ */
+#define          TABLE_FIELD_ID_GCM_EMIT_GHASH_ISESN 0x41d
+/* enum: Replay Protection Enable. */
+#define          TABLE_FIELD_ID_GCM_REPLAY_PROTECT_EN 0x41e
+/* enum: IPSEC Encrypt ESP trailer NEXT_HEADER byte. */
+#define          TABLE_FIELD_ID_GCM_NEXT_HDR 0x41f
+/* enum: Replay Window Size. */
+#define          TABLE_FIELD_ID_GCM_REPLAY_WIN_SIZE 0x420
 
 /* MCDI_EVENT structuredef: The structure of an MCDI_EVENT on Siena/EF10/EF100
  * platforms
@@ -1138,6 +1226,24 @@
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_OFST 0
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_LBN 24
 #define        MCDI_EVENT_LINKCHANGE_LINK_FLAGS_WIDTH 8
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_LBN 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_PORT_HANDLE_WIDTH 24
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_LBN 24
+#define        MCDI_EVENT_PORT_LINKCHANGE_SEQ_NUM_WIDTH 7
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_OFST 0
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_LBN 31
+#define        MCDI_EVENT_PORT_LINKCHANGE_LINK_UP_WIDTH 1
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_LBN 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_PORT_HANDLE_WIDTH 24
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_LBN 24
+#define        MCDI_EVENT_PORT_MODULECHANGE_SEQ_NUM_WIDTH 7
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_OFST 0
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_LBN 31
+#define        MCDI_EVENT_PORT_MODULECHANGE_MDI_CONNECTED_WIDTH 1
 #define        MCDI_EVENT_SENSOREVT_MONITOR_OFST 0
 #define        MCDI_EVENT_SENSOREVT_MONITOR_LBN 0
 #define        MCDI_EVENT_SENSOREVT_MONITOR_WIDTH 8
@@ -1237,7 +1343,7 @@
 #define          MCDI_EVENT_AOE_FPGA_LOAD_FAILED 0xe
 /* enum: Notify that invalid flash type detected */
 #define          MCDI_EVENT_AOE_INVALID_FPGA_FLASH_TYPE 0xf
-/* enum: Notify that the attempt to run FPGA Controller firmware timedout */
+/* enum: Notify that the attempt to run FPGA Controller firmware timed out */
 #define          MCDI_EVENT_AOE_FC_RUN_TIMEDOUT 0x10
 /* enum: Failure to probe one or more FPGA boot flash chips */
 #define          MCDI_EVENT_AOE_FPGA_BOOT_FLASH_INVALID 0x11
@@ -1255,7 +1361,7 @@
 #define        MCDI_EVENT_AOE_ERR_FC_ASSERT_INFO_WIDTH 8
 /* enum: FC Assert happened, but the register information is not available */
 #define          MCDI_EVENT_AOE_ERR_FC_ASSERT_SEEN 0x0
-/* enum: The register information for FC Assert is ready for readinng by driver
+/* enum: The register information for FC Assert is ready for reading by driver
  */
 #define          MCDI_EVENT_AOE_ERR_FC_ASSERT_DATA_READY 0x1
 #define        MCDI_EVENT_AOE_ERR_CODE_FPGA_HEADER_VERIFY_FAILED_OFST 0
@@ -1364,6 +1470,12 @@
 #define        MCDI_EVENT_MODULECHANGE_SEQ_OFST 0
 #define        MCDI_EVENT_MODULECHANGE_SEQ_LBN 30
 #define        MCDI_EVENT_MODULECHANGE_SEQ_WIDTH 2
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_OFST 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_LBN 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_VI_ID_WIDTH 16
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_OFST 0
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_LBN 16
+#define        MCDI_EVENT_DESC_PROXY_VIRTQ_ID_WIDTH 16
 #define       MCDI_EVENT_DATA_LBN 0
 #define       MCDI_EVENT_DATA_WIDTH 32
 /* Alias for PTP_DATA. */
@@ -1500,6 +1612,31 @@
  * change to the journal.
  */
 #define          MCDI_EVENT_CODE_MPORT_JOURNAL_CHANGE 0x27
+/* enum: Notification that a source queue is enabled and attached to its proxy
+ * sink queue. SRC field contains the handle of the affected descriptor proxy
+ * function. DATA field contains the relative source queue number and absolute
+ * VI ID.
+ */
+#define          MCDI_EVENT_CODE_DESC_PROXY_FUNC_QUEUE_START 0x28
+/* enum: Notification of a change in link state and/or link speed of a network
+ * port link. This event applies to a network port identified by a handle,
+ * PORT_HANDLE, which is discovered by the driver using the MC_CMD_ENUM_PORTS
+ * command.
+ */
+#define          MCDI_EVENT_CODE_PORT_LINKCHANGE 0x29
+/* enum: Notification of a change in the state of an MDI (external connector)
+ * of a network port. This typically corresponds to module plug/unplug for
+ * modular interfaces (e.g., SFP/QSFP and similar) or cable connect/disconnect.
+ * This event applies to a network port identified by a handle, PORT_HANDLE,
+ * which is discovered by the driver using the MC_CMD_ENUM_PORTS command.
+ */
+#define          MCDI_EVENT_CODE_PORT_MODULECHANGE 0x2a
+/* enum: Notification that the port enumeration journal has changed since it
+ * was last read and updates can be read using the MC_CMD_ENUM_PORTS command.
+ * The firmware may moderate the events so that an event is not sent for every
+ * change to the journal.
+ */
+#define          MCDI_EVENT_CODE_ENUM_PORTS_CHANGE 0x2b
 /* enum: Artificial event generated by host and posted via MC for test
  * purposes.
  */
@@ -1512,6 +1649,14 @@
 #define       MCDI_EVENT_LINKCHANGE_DATA_LEN 4
 #define       MCDI_EVENT_LINKCHANGE_DATA_LBN 0
 #define       MCDI_EVENT_LINKCHANGE_DATA_WIDTH 32
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_OFST 0
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_LEN 4
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_LBN 0
+#define       MCDI_EVENT_PORT_LINKCHANGE_DATA_WIDTH 32
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_OFST 0
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_LEN 4
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_LBN 0
+#define       MCDI_EVENT_PORT_MODULECHANGE_DATA_WIDTH 32
 #define       MCDI_EVENT_SENSOREVT_DATA_OFST 0
 #define       MCDI_EVENT_SENSOREVT_DATA_LEN 4
 #define       MCDI_EVENT_SENSOREVT_DATA_LBN 0
@@ -1668,247 +1813,6 @@
 #define       MCDI_EVENT_DESC_PROXY_VIRTIO_FEATURES_LBN 0
 #define       MCDI_EVENT_DESC_PROXY_VIRTIO_FEATURES_WIDTH 32
 
-/* FCDI_EVENT structuredef */
-#define    FCDI_EVENT_LEN 8
-#define       FCDI_EVENT_CONT_LBN 32
-#define       FCDI_EVENT_CONT_WIDTH 1
-#define       FCDI_EVENT_LEVEL_LBN 33
-#define       FCDI_EVENT_LEVEL_WIDTH 3
-/* enum: Info. */
-#define          FCDI_EVENT_LEVEL_INFO 0x0
-/* enum: Warning. */
-#define          FCDI_EVENT_LEVEL_WARN 0x1
-/* enum: Error. */
-#define          FCDI_EVENT_LEVEL_ERR 0x2
-/* enum: Fatal. */
-#define          FCDI_EVENT_LEVEL_FATAL 0x3
-#define       FCDI_EVENT_DATA_OFST 0
-#define       FCDI_EVENT_DATA_LEN 4
-#define        FCDI_EVENT_LINK_STATE_STATUS_OFST 0
-#define        FCDI_EVENT_LINK_STATE_STATUS_LBN 0
-#define        FCDI_EVENT_LINK_STATE_STATUS_WIDTH 1
-#define          FCDI_EVENT_LINK_DOWN 0x0 /* enum */
-#define          FCDI_EVENT_LINK_UP 0x1 /* enum */
-#define       FCDI_EVENT_DATA_LBN 0
-#define       FCDI_EVENT_DATA_WIDTH 32
-#define       FCDI_EVENT_SRC_LBN 36
-#define       FCDI_EVENT_SRC_WIDTH 8
-#define       FCDI_EVENT_EV_CODE_LBN 60
-#define       FCDI_EVENT_EV_CODE_WIDTH 4
-#define       FCDI_EVENT_CODE_LBN 44
-#define       FCDI_EVENT_CODE_WIDTH 8
-/* enum: The FC was rebooted. */
-#define          FCDI_EVENT_CODE_REBOOT 0x1
-/* enum: Bad assert. */
-#define          FCDI_EVENT_CODE_ASSERT 0x2
-/* enum: DDR3 test result. */
-#define          FCDI_EVENT_CODE_DDR_TEST_RESULT 0x3
-/* enum: Link status. */
-#define          FCDI_EVENT_CODE_LINK_STATE 0x4
-/* enum: A timed read is ready to be serviced. */
-#define          FCDI_EVENT_CODE_TIMED_READ 0x5
-/* enum: One or more PPS IN events */
-#define          FCDI_EVENT_CODE_PPS_IN 0x6
-/* enum: Tick event from PTP clock */
-#define          FCDI_EVENT_CODE_PTP_TICK 0x7
-/* enum: ECC error counters */
-#define          FCDI_EVENT_CODE_DDR_ECC_STATUS 0x8
-/* enum: Current status of PTP */
-#define          FCDI_EVENT_CODE_PTP_STATUS 0x9
-/* enum: Port id config to map MC-FC port idx */
-#define          FCDI_EVENT_CODE_PORT_CONFIG 0xa
-/* enum: Boot result or error code */
-#define          FCDI_EVENT_CODE_BOOT_RESULT 0xb
-#define       FCDI_EVENT_REBOOT_SRC_LBN 36
-#define       FCDI_EVENT_REBOOT_SRC_WIDTH 8
-#define          FCDI_EVENT_REBOOT_FC_FW 0x0 /* enum */
-#define          FCDI_EVENT_REBOOT_FC_BOOTLOADER 0x1 /* enum */
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LEN 4
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0
-#define       FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32
-#define       FCDI_EVENT_ASSERT_TYPE_LBN 36
-#define       FCDI_EVENT_ASSERT_TYPE_WIDTH 8
-#define       FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_LBN 36
-#define       FCDI_EVENT_DDR_TEST_RESULT_STATUS_CODE_WIDTH 8
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_OFST 0
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_LEN 4
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_LBN 0
-#define       FCDI_EVENT_DDR_TEST_RESULT_RESULT_WIDTH 32
-#define       FCDI_EVENT_LINK_STATE_DATA_OFST 0
-#define       FCDI_EVENT_LINK_STATE_DATA_LEN 4
-#define       FCDI_EVENT_LINK_STATE_DATA_LBN 0
-#define       FCDI_EVENT_LINK_STATE_DATA_WIDTH 32
-#define       FCDI_EVENT_PTP_STATE_OFST 0
-#define       FCDI_EVENT_PTP_STATE_LEN 4
-#define          FCDI_EVENT_PTP_UNDEFINED 0x0 /* enum */
-#define          FCDI_EVENT_PTP_SETUP_FAILED 0x1 /* enum */
-#define          FCDI_EVENT_PTP_OPERATIONAL 0x2 /* enum */
-#define       FCDI_EVENT_PTP_STATE_LBN 0
-#define       FCDI_EVENT_PTP_STATE_WIDTH 32
-#define       FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_LBN 36
-#define       FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_WIDTH 8
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_OFST 0
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_LEN 4
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_LBN 0
-#define       FCDI_EVENT_DDR_ECC_STATUS_STATUS_WIDTH 32
-/* Index of MC port being referred to */
-#define       FCDI_EVENT_PORT_CONFIG_SRC_LBN 36
-#define       FCDI_EVENT_PORT_CONFIG_SRC_WIDTH 8
-/* FC Port index that matches the MC port index in SRC */
-#define       FCDI_EVENT_PORT_CONFIG_DATA_OFST 0
-#define       FCDI_EVENT_PORT_CONFIG_DATA_LEN 4
-#define       FCDI_EVENT_PORT_CONFIG_DATA_LBN 0
-#define       FCDI_EVENT_PORT_CONFIG_DATA_WIDTH 32
-#define       FCDI_EVENT_BOOT_RESULT_OFST 0
-#define       FCDI_EVENT_BOOT_RESULT_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_AOE/MC_CMD_AOE_OUT_INFO/FC_BOOT_RESULT */
-#define       FCDI_EVENT_BOOT_RESULT_LBN 0
-#define       FCDI_EVENT_BOOT_RESULT_WIDTH 32
-
-/* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events
- * to the MC. Note that this structure | is overlayed over a normal FCDI event
- * such that bits 32-63 containing | event code, level, source etc remain the
- * same. In this case the data | field of the header is defined to be the
- * number of timestamps
- */
-#define    FCDI_EXTENDED_EVENT_PPS_LENMIN 16
-#define    FCDI_EXTENDED_EVENT_PPS_LENMAX 248
-#define    FCDI_EXTENDED_EVENT_PPS_LENMAX_MCDI2 1016
-#define    FCDI_EXTENDED_EVENT_PPS_LEN(num) (8+8*(num))
-#define    FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_NUM(len) (((len)-8)/8)
-/* Number of timestamps following */
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_OFST 0
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_LBN 0
-#define       FCDI_EXTENDED_EVENT_PPS_COUNT_WIDTH 32
-/* Seconds field of a timestamp record */
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_SECONDS_WIDTH 32
-/* Nanoseconds field of a timestamp record */
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_OFST 12
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LBN 96
-#define       FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_WIDTH 32
-/* Timestamp records comprising the event */
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LEN 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_OFST 8
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_WIDTH 32
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_OFST 12
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_LEN 4
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_LBN 96
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_WIDTH 32
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MINNUM 1
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM 30
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM_MCDI2 126
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LBN 64
-#define       FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_WIDTH 64
-
-/* MUM_EVENT structuredef */
-#define    MUM_EVENT_LEN 8
-#define       MUM_EVENT_CONT_LBN 32
-#define       MUM_EVENT_CONT_WIDTH 1
-#define       MUM_EVENT_LEVEL_LBN 33
-#define       MUM_EVENT_LEVEL_WIDTH 3
-/* enum: Info. */
-#define          MUM_EVENT_LEVEL_INFO 0x0
-/* enum: Warning. */
-#define          MUM_EVENT_LEVEL_WARN 0x1
-/* enum: Error. */
-#define          MUM_EVENT_LEVEL_ERR 0x2
-/* enum: Fatal. */
-#define          MUM_EVENT_LEVEL_FATAL 0x3
-#define       MUM_EVENT_DATA_OFST 0
-#define       MUM_EVENT_DATA_LEN 4
-#define        MUM_EVENT_SENSOR_ID_OFST 0
-#define        MUM_EVENT_SENSOR_ID_LBN 0
-#define        MUM_EVENT_SENSOR_ID_WIDTH 8
-/*             Enum values, see field(s): */
-/*                MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
-#define        MUM_EVENT_SENSOR_STATE_OFST 0
-#define        MUM_EVENT_SENSOR_STATE_LBN 8
-#define        MUM_EVENT_SENSOR_STATE_WIDTH 8
-#define        MUM_EVENT_PORT_PHY_READY_OFST 0
-#define        MUM_EVENT_PORT_PHY_READY_LBN 0
-#define        MUM_EVENT_PORT_PHY_READY_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_LINK_UP_OFST 0
-#define        MUM_EVENT_PORT_PHY_LINK_UP_LBN 1
-#define        MUM_EVENT_PORT_PHY_LINK_UP_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_LOL_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_LOL_LBN 2
-#define        MUM_EVENT_PORT_PHY_TX_LOL_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_RX_LOL_OFST 0
-#define        MUM_EVENT_PORT_PHY_RX_LOL_LBN 3
-#define        MUM_EVENT_PORT_PHY_RX_LOL_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_LOS_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_LOS_LBN 4
-#define        MUM_EVENT_PORT_PHY_TX_LOS_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_RX_LOS_OFST 0
-#define        MUM_EVENT_PORT_PHY_RX_LOS_LBN 5
-#define        MUM_EVENT_PORT_PHY_RX_LOS_WIDTH 1
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_OFST 0
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_LBN 6
-#define        MUM_EVENT_PORT_PHY_TX_FAULT_WIDTH 1
-#define       MUM_EVENT_DATA_LBN 0
-#define       MUM_EVENT_DATA_WIDTH 32
-#define       MUM_EVENT_SRC_LBN 36
-#define       MUM_EVENT_SRC_WIDTH 8
-#define       MUM_EVENT_EV_CODE_LBN 60
-#define       MUM_EVENT_EV_CODE_WIDTH 4
-#define       MUM_EVENT_CODE_LBN 44
-#define       MUM_EVENT_CODE_WIDTH 8
-/* enum: The MUM was rebooted. */
-#define          MUM_EVENT_CODE_REBOOT 0x1
-/* enum: Bad assert. */
-#define          MUM_EVENT_CODE_ASSERT 0x2
-/* enum: Sensor failure. */
-#define          MUM_EVENT_CODE_SENSOR 0x3
-/* enum: Link fault has been asserted, or has cleared. */
-#define          MUM_EVENT_CODE_QSFP_LASI_INTERRUPT 0x4
-#define       MUM_EVENT_SENSOR_DATA_OFST 0
-#define       MUM_EVENT_SENSOR_DATA_LEN 4
-#define       MUM_EVENT_SENSOR_DATA_LBN 0
-#define       MUM_EVENT_SENSOR_DATA_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_FLAGS_OFST 0
-#define       MUM_EVENT_PORT_PHY_FLAGS_LEN 4
-#define       MUM_EVENT_PORT_PHY_FLAGS_LBN 0
-#define       MUM_EVENT_PORT_PHY_FLAGS_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_OFST 0
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_LEN 4
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_LBN 0
-#define       MUM_EVENT_PORT_PHY_COPPER_LEN_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_CAPS_OFST 0
-#define       MUM_EVENT_PORT_PHY_CAPS_LEN 4
-#define       MUM_EVENT_PORT_PHY_CAPS_LBN 0
-#define       MUM_EVENT_PORT_PHY_CAPS_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_TECH_OFST 0
-#define       MUM_EVENT_PORT_PHY_TECH_LEN 4
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_UNKNOWN 0x0 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_OPTICAL 0x1 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE 0x2 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_PASSIVE_EQUALIZED 0x3 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LIMITING 0x4 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_COPPER_ACTIVE_LINEAR 0x5 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_BASE_T 0x6 /* enum */
-#define          MUM_EVENT_PORT_PHY_STATE_QSFP_MODULE_TECH_LOOPBACK_PASSIVE 0x7 /* enum */
-#define       MUM_EVENT_PORT_PHY_TECH_LBN 0
-#define       MUM_EVENT_PORT_PHY_TECH_WIDTH 32
-#define       MUM_EVENT_PORT_PHY_SRC_DATA_ID_LBN 36
-#define       MUM_EVENT_PORT_PHY_SRC_DATA_ID_WIDTH 4
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_FLAGS 0x0 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_COPPER_LEN 0x1 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_CAPS 0x2 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_TECH 0x3 /* enum */
-#define          MUM_EVENT_PORT_PHY_SRC_DATA_ID_MAX 0x4 /* enum */
-#define       MUM_EVENT_PORT_PHY_SRC_PORT_NO_LBN 40
-#define       MUM_EVENT_PORT_PHY_SRC_PORT_NO_WIDTH 4
-
 
 /***********************************/
 /* MC_CMD_READ32
@@ -1968,90 +1872,6 @@
 #define    MC_CMD_WRITE32_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_COPYCODE
- * Copy MC code between two locations and jump. Note - this command really
- * belongs to INSECURE category but is required by shmboot. The command handler
- * has additional checks to reject insecure calls.
- */
-#define MC_CMD_COPYCODE 0x3
-#undef MC_CMD_0x3_PRIVILEGE_CTG
-
-#define MC_CMD_0x3_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_COPYCODE_IN msgrequest */
-#define    MC_CMD_COPYCODE_IN_LEN 16
-/* Source address
- *
- * The main image should be entered via a copy of a single word from and to a
- * magic address, which controls various aspects of the boot. The magic address
- * is a bitfield, with each bit as documented below.
- */
-#define       MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0
-#define       MC_CMD_COPYCODE_IN_SRC_ADDR_LEN 4
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT (see below) */
-#define          MC_CMD_COPYCODE_HUNT_NO_MAGIC_ADDR 0x10000
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT and
- * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED (see below)
- */
-#define          MC_CMD_COPYCODE_HUNT_NO_DATAPATH_MAGIC_ADDR 0x1d0d0
-/* enum: Deprecated; equivalent to setting BOOT_MAGIC_PRESENT,
- * BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED and BOOT_MAGIC_IGNORE_CONFIG (see
- * below)
- */
-#define          MC_CMD_COPYCODE_HUNT_IGNORE_CONFIG_MAGIC_ADDR 0x1badc
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_LBN 17
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_PRESENT_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_LBN 2
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SATELLITE_CPUS_NOT_LOADED_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_LBN 3
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_IGNORE_CONFIG_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_LBN 4
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_SKIP_BOOT_ICORE_SYNC_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_LBN 5
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_FORCE_STANDALONE_WIDTH 1
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_OFST 0
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_LBN 6
-#define        MC_CMD_COPYCODE_IN_BOOT_MAGIC_DISABLE_XIP_WIDTH 1
-/* Destination address */
-#define       MC_CMD_COPYCODE_IN_DEST_ADDR_OFST 4
-#define       MC_CMD_COPYCODE_IN_DEST_ADDR_LEN 4
-#define       MC_CMD_COPYCODE_IN_NUMWORDS_OFST 8
-#define       MC_CMD_COPYCODE_IN_NUMWORDS_LEN 4
-/* Address of where to jump after copy. */
-#define       MC_CMD_COPYCODE_IN_JUMP_OFST 12
-#define       MC_CMD_COPYCODE_IN_JUMP_LEN 4
-/* enum: Control should return to the caller rather than jumping */
-#define          MC_CMD_COPYCODE_JUMP_NONE 0x1
-
-/* MC_CMD_COPYCODE_OUT msgresponse */
-#define    MC_CMD_COPYCODE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SET_FUNC
- * Select function for function-specific commands.
- */
-#define MC_CMD_SET_FUNC 0x4
-#undef MC_CMD_0x4_PRIVILEGE_CTG
-
-#define MC_CMD_0x4_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_FUNC_IN msgrequest */
-#define    MC_CMD_SET_FUNC_IN_LEN 4
-/* Set function */
-#define       MC_CMD_SET_FUNC_IN_FUNC_OFST 0
-#define       MC_CMD_SET_FUNC_IN_FUNC_LEN 4
-
-/* MC_CMD_SET_FUNC_OUT msgresponse */
-#define    MC_CMD_SET_FUNC_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_GET_BOOT_STATUS
  * Get the instruction address from which the MC booted.
@@ -2259,6 +2079,7 @@
 /* Log destination */
 #define       MC_CMD_LOG_CTRL_IN_LOG_DEST_OFST 0
 #define       MC_CMD_LOG_CTRL_IN_LOG_DEST_LEN 4
+/* enum property: bitmask */
 /* enum: UART. */
 #define          MC_CMD_LOG_CTRL_IN_LOG_DEST_UART 0x1
 /* enum: Event queue. */
@@ -2304,6 +2125,9 @@
 
 /* MC_CMD_GET_VERSION_OUT msgresponse */
 #define    MC_CMD_GET_VERSION_OUT_LEN 32
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2326,6 +2150,9 @@
 
 /* MC_CMD_GET_VERSION_EXT_OUT msgresponse */
 #define    MC_CMD_GET_VERSION_EXT_OUT_LEN 48
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2356,6 +2183,9 @@
  * (depending on which components exist on a particular adapter)
  */
 #define    MC_CMD_GET_VERSION_V2_OUT_LEN 304
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2495,6 +2325,9 @@
  * (depending on which components exist on a particular adapter)
  */
 #define    MC_CMD_GET_VERSION_V3_OUT_LEN 328
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2641,6 +2474,9 @@
  * version information
  */
 #define    MC_CMD_GET_VERSION_V4_OUT_LEN 392
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -2803,6 +2639,9 @@
  * and board version information
  */
 #define    MC_CMD_GET_VERSION_V5_OUT_LEN 424
+/* This is normally the UTC build time in seconds since epoch or one of the
+ * special values listed
+ */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_OFST 0 */
 /*            MC_CMD_GET_VERSION_OUT_FIRMWARE_LEN 4 */
 /*            Enum values, see field(s): */
@@ -3065,8 +2904,18 @@
  * subscribers.
  */
 #define          MC_CMD_PTP_OP_SET_SYNC_STATUS 0x1b
-/* enum: Above this for future use. */
-#define          MC_CMD_PTP_OP_MAX 0x1c
+/* enum: X4 and later adapters should use this instead of
+ * PTP_OP_TIME_EVENT_SUBSCRIBE. Subscribe to receive periodic time events
+ * indicating the current NIC time
+ */
+#define          MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE_V2 0x1c
+/* enum: For X4 and later NICs. Packet timestamps and time sync events have
+ * IS_SET and IN_SYNC flags, that indicates whether time is updated and if it
+ * is in sync with host. Once set, IN_SYNC flag is cleared by hardware after a
+ * software configurable time out. Host driver need to query what is set and
+ * what is maximum supported interval, this MCDI can be used to query these.
+ */
+#define          MC_CMD_PTP_OP_GET_SYNC_TIMEOUT 0x1d
 
 /* MC_CMD_PTP_IN_ENABLE msgrequest */
 #define    MC_CMD_PTP_IN_ENABLE_LEN 16
@@ -3507,6 +3356,22 @@
 #define       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_OFST 12
 #define       MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_LEN 4
 
+/* MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2 msgrequest */
+#define    MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_LEN 16
+/*            MC_CMD_PTP_IN_CMD_OFST 0 */
+/*            MC_CMD_PTP_IN_CMD_LEN 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_LEN 4 */
+/* Event queue ID */
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_QUEUE_ID_OFST 8
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_QUEUE_ID_LEN 4
+/* Space for flags. */
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_FLAGS_OFST 12
+#define       MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_FLAGS_LEN 4
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_OFST 12
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_LBN 31
+#define        MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_V2_REPORT_SYNC_STATUS_WIDTH 1
+
 /* MC_CMD_PTP_IN_MANFTEST_PPS msgrequest */
 #define    MC_CMD_PTP_IN_MANFTEST_PPS_LEN 12
 /*            MC_CMD_PTP_IN_CMD_OFST 0 */
@@ -3540,6 +3405,13 @@
 #define       MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED1_OFST 20
 #define       MC_CMD_PTP_IN_SET_SYNC_STATUS_RESERVED1_LEN 4
 
+/* MC_CMD_PTP_IN_GET_SYNC_TIMEOUT msgrequest */
+#define    MC_CMD_PTP_IN_GET_SYNC_TIMEOUT_LEN 8
+/*            MC_CMD_PTP_IN_CMD_OFST 0 */
+/*            MC_CMD_PTP_IN_CMD_LEN 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */
+/*            MC_CMD_PTP_IN_PERIPH_ID_LEN 4 */
+
 /* MC_CMD_PTP_OUT msgresponse */
 #define    MC_CMD_PTP_OUT_LEN 0
 
@@ -3939,416 +3811,14 @@
 /* MC_CMD_PTP_OUT_SET_SYNC_STATUS msgresponse */
 #define    MC_CMD_PTP_OUT_SET_SYNC_STATUS_LEN 0
 
-
-/***********************************/
-/* MC_CMD_CSR_READ32
- * Read 32bit words from the indirect memory map.
- */
-#define MC_CMD_CSR_READ32 0xc
-#undef MC_CMD_0xc_PRIVILEGE_CTG
-
-#define MC_CMD_0xc_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CSR_READ32_IN msgrequest */
-#define    MC_CMD_CSR_READ32_IN_LEN 12
-/* Address */
-#define       MC_CMD_CSR_READ32_IN_ADDR_OFST 0
-#define       MC_CMD_CSR_READ32_IN_ADDR_LEN 4
-#define       MC_CMD_CSR_READ32_IN_STEP_OFST 4
-#define       MC_CMD_CSR_READ32_IN_STEP_LEN 4
-#define       MC_CMD_CSR_READ32_IN_NUMWORDS_OFST 8
-#define       MC_CMD_CSR_READ32_IN_NUMWORDS_LEN 4
-
-/* MC_CMD_CSR_READ32_OUT msgresponse */
-#define    MC_CMD_CSR_READ32_OUT_LENMIN 4
-#define    MC_CMD_CSR_READ32_OUT_LENMAX 252
-#define    MC_CMD_CSR_READ32_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_CSR_READ32_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_CSR_READ32_OUT_BUFFER_NUM(len) (((len)-0)/4)
-/* The last dword is the status, not a value read */
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_OFST 0
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_LEN 4
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MAXNUM 63
-#define       MC_CMD_CSR_READ32_OUT_BUFFER_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_CSR_WRITE32
- * Write 32bit dwords to the indirect memory map.
- */
-#define MC_CMD_CSR_WRITE32 0xd
-#undef MC_CMD_0xd_PRIVILEGE_CTG
-
-#define MC_CMD_0xd_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CSR_WRITE32_IN msgrequest */
-#define    MC_CMD_CSR_WRITE32_IN_LENMIN 12
-#define    MC_CMD_CSR_WRITE32_IN_LENMAX 252
-#define    MC_CMD_CSR_WRITE32_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_CSR_WRITE32_IN_LEN(num) (8+4*(num))
-#define    MC_CMD_CSR_WRITE32_IN_BUFFER_NUM(len) (((len)-8)/4)
-/* Address */
-#define       MC_CMD_CSR_WRITE32_IN_ADDR_OFST 0
-#define       MC_CMD_CSR_WRITE32_IN_ADDR_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_STEP_OFST 4
-#define       MC_CMD_CSR_WRITE32_IN_STEP_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_OFST 8
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_LEN 4
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MINNUM 1
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MAXNUM 61
-#define       MC_CMD_CSR_WRITE32_IN_BUFFER_MAXNUM_MCDI2 253
-
-/* MC_CMD_CSR_WRITE32_OUT msgresponse */
-#define    MC_CMD_CSR_WRITE32_OUT_LEN 4
-#define       MC_CMD_CSR_WRITE32_OUT_STATUS_OFST 0
-#define       MC_CMD_CSR_WRITE32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_HP
- * These commands are used for HP related features. They are grouped under one
- * MCDI command to avoid creating too many MCDI commands.
- */
-#define MC_CMD_HP 0x54
-#undef MC_CMD_0x54_PRIVILEGE_CTG
-
-#define MC_CMD_0x54_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_HP_IN msgrequest */
-#define    MC_CMD_HP_IN_LEN 16
-/* HP OCSD sub-command. When address is not NULL, request activation of OCSD at
- * the specified address with the specified interval.When address is NULL,
- * INTERVAL is interpreted as a command: 0: stop OCSD / 1: Report OCSD current
- * state / 2: (debug) Show temperature reported by one of the supported
- * sensors.
- */
-#define       MC_CMD_HP_IN_SUBCMD_OFST 0
-#define       MC_CMD_HP_IN_SUBCMD_LEN 4
-/* enum: OCSD (Option Card Sensor Data) sub-command. */
-#define          MC_CMD_HP_IN_OCSD_SUBCMD 0x0
-/* enum: Last known valid HP sub-command. */
-#define          MC_CMD_HP_IN_LAST_SUBCMD 0x0
-/* The address to the array of sensor fields. (Or NULL to use a sub-command.)
- */
-#define       MC_CMD_HP_IN_OCSD_ADDR_OFST 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LEN 8
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_OFST 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_LEN 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_LBN 32
-#define       MC_CMD_HP_IN_OCSD_ADDR_LO_WIDTH 32
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_OFST 8
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_LEN 4
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_LBN 64
-#define       MC_CMD_HP_IN_OCSD_ADDR_HI_WIDTH 32
-/* The requested update interval, in seconds. (Or the sub-command if ADDR is
- * NULL.)
- */
-#define       MC_CMD_HP_IN_OCSD_INTERVAL_OFST 12
-#define       MC_CMD_HP_IN_OCSD_INTERVAL_LEN 4
-
-/* MC_CMD_HP_OUT msgresponse */
-#define    MC_CMD_HP_OUT_LEN 4
-#define       MC_CMD_HP_OUT_OCSD_STATUS_OFST 0
-#define       MC_CMD_HP_OUT_OCSD_STATUS_LEN 4
-/* enum: OCSD stopped for this card. */
-#define          MC_CMD_HP_OUT_OCSD_STOPPED 0x1
-/* enum: OCSD was successfully started with the address provided. */
-#define          MC_CMD_HP_OUT_OCSD_STARTED 0x2
-/* enum: OCSD was already started for this card. */
-#define          MC_CMD_HP_OUT_OCSD_ALREADY_STARTED 0x3
-
-
-/***********************************/
-/* MC_CMD_STACKINFO
- * Get stack information.
- */
-#define MC_CMD_STACKINFO 0xf
-#undef MC_CMD_0xf_PRIVILEGE_CTG
-
-#define MC_CMD_0xf_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_STACKINFO_IN msgrequest */
-#define    MC_CMD_STACKINFO_IN_LEN 0
-
-/* MC_CMD_STACKINFO_OUT msgresponse */
-#define    MC_CMD_STACKINFO_OUT_LENMIN 12
-#define    MC_CMD_STACKINFO_OUT_LENMAX 252
-#define    MC_CMD_STACKINFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_STACKINFO_OUT_LEN(num) (0+12*(num))
-#define    MC_CMD_STACKINFO_OUT_THREAD_INFO_NUM(len) (((len)-0)/12)
-/* (thread ptr, stack size, free space) for each thread in system */
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_OFST 0
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_LEN 12
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MINNUM 1
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MAXNUM 21
-#define       MC_CMD_STACKINFO_OUT_THREAD_INFO_MAXNUM_MCDI2 85
-
-
-/***********************************/
-/* MC_CMD_MDIO_READ
- * MDIO register read.
- */
-#define MC_CMD_MDIO_READ 0x10
-#undef MC_CMD_0x10_PRIVILEGE_CTG
-
-#define MC_CMD_0x10_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MDIO_READ_IN msgrequest */
-#define    MC_CMD_MDIO_READ_IN_LEN 16
-/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
- * external devices.
- */
-#define       MC_CMD_MDIO_READ_IN_BUS_OFST 0
-#define       MC_CMD_MDIO_READ_IN_BUS_LEN 4
-/* enum: Internal. */
-#define          MC_CMD_MDIO_BUS_INTERNAL 0x0
-/* enum: External. */
-#define          MC_CMD_MDIO_BUS_EXTERNAL 0x1
-/* Port address */
-#define       MC_CMD_MDIO_READ_IN_PRTAD_OFST 4
-#define       MC_CMD_MDIO_READ_IN_PRTAD_LEN 4
-/* Device Address or clause 22. */
-#define       MC_CMD_MDIO_READ_IN_DEVAD_OFST 8
-#define       MC_CMD_MDIO_READ_IN_DEVAD_LEN 4
-/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
- * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
- */
-#define          MC_CMD_MDIO_CLAUSE22 0x20
-/* Address */
-#define       MC_CMD_MDIO_READ_IN_ADDR_OFST 12
-#define       MC_CMD_MDIO_READ_IN_ADDR_LEN 4
-
-/* MC_CMD_MDIO_READ_OUT msgresponse */
-#define    MC_CMD_MDIO_READ_OUT_LEN 8
-/* Value */
-#define       MC_CMD_MDIO_READ_OUT_VALUE_OFST 0
-#define       MC_CMD_MDIO_READ_OUT_VALUE_LEN 4
-/* Status the MDIO commands return the raw status bits from the MDIO block. A
- * "good" transaction should have the DONE bit set and all other bits clear.
- */
-#define       MC_CMD_MDIO_READ_OUT_STATUS_OFST 4
-#define       MC_CMD_MDIO_READ_OUT_STATUS_LEN 4
-/* enum: Good. */
-#define          MC_CMD_MDIO_STATUS_GOOD 0x8
-
-
-/***********************************/
-/* MC_CMD_MDIO_WRITE
- * MDIO register write.
- */
-#define MC_CMD_MDIO_WRITE 0x11
-#undef MC_CMD_0x11_PRIVILEGE_CTG
-
-#define MC_CMD_0x11_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_MDIO_WRITE_IN msgrequest */
-#define    MC_CMD_MDIO_WRITE_IN_LEN 20
-/* Bus number; there are two MDIO buses: one for the internal PHY, and one for
- * external devices.
- */
-#define       MC_CMD_MDIO_WRITE_IN_BUS_OFST 0
-#define       MC_CMD_MDIO_WRITE_IN_BUS_LEN 4
-/* enum: Internal. */
-/*               MC_CMD_MDIO_BUS_INTERNAL 0x0 */
-/* enum: External. */
-/*               MC_CMD_MDIO_BUS_EXTERNAL 0x1 */
-/* Port address */
-#define       MC_CMD_MDIO_WRITE_IN_PRTAD_OFST 4
-#define       MC_CMD_MDIO_WRITE_IN_PRTAD_LEN 4
-/* Device Address or clause 22. */
-#define       MC_CMD_MDIO_WRITE_IN_DEVAD_OFST 8
-#define       MC_CMD_MDIO_WRITE_IN_DEVAD_LEN 4
-/* enum: By default all the MCDI MDIO operations perform clause45 mode. If you
- * want to use clause22 then set DEVAD = MC_CMD_MDIO_CLAUSE22.
- */
-/*               MC_CMD_MDIO_CLAUSE22 0x20 */
-/* Address */
-#define       MC_CMD_MDIO_WRITE_IN_ADDR_OFST 12
-#define       MC_CMD_MDIO_WRITE_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_MDIO_WRITE_IN_VALUE_OFST 16
-#define       MC_CMD_MDIO_WRITE_IN_VALUE_LEN 4
-
-/* MC_CMD_MDIO_WRITE_OUT msgresponse */
-#define    MC_CMD_MDIO_WRITE_OUT_LEN 4
-/* Status; the MDIO commands return the raw status bits from the MDIO block. A
- * "good" transaction should have the DONE bit set and all other bits clear.
- */
-#define       MC_CMD_MDIO_WRITE_OUT_STATUS_OFST 0
-#define       MC_CMD_MDIO_WRITE_OUT_STATUS_LEN 4
-/* enum: Good. */
-/*               MC_CMD_MDIO_STATUS_GOOD 0x8 */
-
-
-/***********************************/
-/* MC_CMD_DBI_WRITE
- * Write DBI register(s).
- */
-#define MC_CMD_DBI_WRITE 0x12
-#undef MC_CMD_0x12_PRIVILEGE_CTG
-
-#define MC_CMD_0x12_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DBI_WRITE_IN msgrequest */
-#define    MC_CMD_DBI_WRITE_IN_LENMIN 12
-#define    MC_CMD_DBI_WRITE_IN_LENMAX 252
-#define    MC_CMD_DBI_WRITE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_DBI_WRITE_IN_LEN(num) (0+12*(num))
-#define    MC_CMD_DBI_WRITE_IN_DBIWROP_NUM(len) (((len)-0)/12)
-/* Each write op consists of an address (offset 0), byte enable/VF/CS2 (offset
- * 32) and value (offset 64). See MC_CMD_DBIWROP_TYPEDEF.
- */
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_OFST 0
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_LEN 12
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MINNUM 1
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MAXNUM 21
-#define       MC_CMD_DBI_WRITE_IN_DBIWROP_MAXNUM_MCDI2 85
-
-/* MC_CMD_DBI_WRITE_OUT msgresponse */
-#define    MC_CMD_DBI_WRITE_OUT_LEN 0
-
-/* MC_CMD_DBIWROP_TYPEDEF structuredef */
-#define    MC_CMD_DBIWROP_TYPEDEF_LEN 12
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_OFST 0
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_LEN 4
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_LBN 0
-#define       MC_CMD_DBIWROP_TYPEDEF_ADDRESS_WIDTH 32
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_OFST 4
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_LEN 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_LBN 16
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_NUM_WIDTH 16
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_LBN 15
-#define        MC_CMD_DBIWROP_TYPEDEF_VF_ACTIVE_WIDTH 1
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_OFST 4
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_LBN 14
-#define        MC_CMD_DBIWROP_TYPEDEF_CS2_WIDTH 1
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_LBN 32
-#define       MC_CMD_DBIWROP_TYPEDEF_PARMS_WIDTH 32
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_OFST 8
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_LEN 4
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_LBN 64
-#define       MC_CMD_DBIWROP_TYPEDEF_VALUE_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_PORT_READ32
- * Read a 32-bit register from the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_READ32 0x14
-
-/* MC_CMD_PORT_READ32_IN msgrequest */
-#define    MC_CMD_PORT_READ32_IN_LEN 4
-/* Address */
-#define       MC_CMD_PORT_READ32_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_READ32_IN_ADDR_LEN 4
-
-/* MC_CMD_PORT_READ32_OUT msgresponse */
-#define    MC_CMD_PORT_READ32_OUT_LEN 8
-/* Value */
-#define       MC_CMD_PORT_READ32_OUT_VALUE_OFST 0
-#define       MC_CMD_PORT_READ32_OUT_VALUE_LEN 4
-/* Status */
-#define       MC_CMD_PORT_READ32_OUT_STATUS_OFST 4
-#define       MC_CMD_PORT_READ32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_WRITE32
- * Write a 32-bit register to the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_WRITE32 0x15
-
-/* MC_CMD_PORT_WRITE32_IN msgrequest */
-#define    MC_CMD_PORT_WRITE32_IN_LEN 8
-/* Address */
-#define       MC_CMD_PORT_WRITE32_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_WRITE32_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_PORT_WRITE32_IN_VALUE_OFST 4
-#define       MC_CMD_PORT_WRITE32_IN_VALUE_LEN 4
-
-/* MC_CMD_PORT_WRITE32_OUT msgresponse */
-#define    MC_CMD_PORT_WRITE32_OUT_LEN 4
-/* Status */
-#define       MC_CMD_PORT_WRITE32_OUT_STATUS_OFST 0
-#define       MC_CMD_PORT_WRITE32_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_READ128
- * Read a 128-bit register from the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_READ128 0x16
-
-/* MC_CMD_PORT_READ128_IN msgrequest */
-#define    MC_CMD_PORT_READ128_IN_LEN 4
-/* Address */
-#define       MC_CMD_PORT_READ128_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_READ128_IN_ADDR_LEN 4
-
-/* MC_CMD_PORT_READ128_OUT msgresponse */
-#define    MC_CMD_PORT_READ128_OUT_LEN 20
-/* Value */
-#define       MC_CMD_PORT_READ128_OUT_VALUE_OFST 0
-#define       MC_CMD_PORT_READ128_OUT_VALUE_LEN 16
-/* Status */
-#define       MC_CMD_PORT_READ128_OUT_STATUS_OFST 16
-#define       MC_CMD_PORT_READ128_OUT_STATUS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PORT_WRITE128
- * Write a 128-bit register to the indirect port register map. The port to
- * access is implied by the Shared memory channel used.
- */
-#define MC_CMD_PORT_WRITE128 0x17
-
-/* MC_CMD_PORT_WRITE128_IN msgrequest */
-#define    MC_CMD_PORT_WRITE128_IN_LEN 20
-/* Address */
-#define       MC_CMD_PORT_WRITE128_IN_ADDR_OFST 0
-#define       MC_CMD_PORT_WRITE128_IN_ADDR_LEN 4
-/* Value */
-#define       MC_CMD_PORT_WRITE128_IN_VALUE_OFST 4
-#define       MC_CMD_PORT_WRITE128_IN_VALUE_LEN 16
-
-/* MC_CMD_PORT_WRITE128_OUT msgresponse */
-#define    MC_CMD_PORT_WRITE128_OUT_LEN 4
-/* Status */
-#define       MC_CMD_PORT_WRITE128_OUT_STATUS_OFST 0
-#define       MC_CMD_PORT_WRITE128_OUT_STATUS_LEN 4
-
-/* MC_CMD_CAPABILITIES structuredef */
-#define    MC_CMD_CAPABILITIES_LEN 4
-/* Small buf table. */
-#define       MC_CMD_CAPABILITIES_SMALL_BUF_TBL_LBN 0
-#define       MC_CMD_CAPABILITIES_SMALL_BUF_TBL_WIDTH 1
-/* Turbo mode (for Maranello). */
-#define       MC_CMD_CAPABILITIES_TURBO_LBN 1
-#define       MC_CMD_CAPABILITIES_TURBO_WIDTH 1
-/* Turbo mode active (for Maranello). */
-#define       MC_CMD_CAPABILITIES_TURBO_ACTIVE_LBN 2
-#define       MC_CMD_CAPABILITIES_TURBO_ACTIVE_WIDTH 1
-/* PTP offload. */
-#define       MC_CMD_CAPABILITIES_PTP_LBN 3
-#define       MC_CMD_CAPABILITIES_PTP_WIDTH 1
-/* AOE mode. */
-#define       MC_CMD_CAPABILITIES_AOE_LBN 4
-#define       MC_CMD_CAPABILITIES_AOE_WIDTH 1
-/* AOE mode active. */
-#define       MC_CMD_CAPABILITIES_AOE_ACTIVE_LBN 5
-#define       MC_CMD_CAPABILITIES_AOE_ACTIVE_WIDTH 1
-/* AOE mode active. */
-#define       MC_CMD_CAPABILITIES_FC_ACTIVE_LBN 6
-#define       MC_CMD_CAPABILITIES_FC_ACTIVE_WIDTH 1
-#define       MC_CMD_CAPABILITIES_RESERVED_LBN 7
-#define       MC_CMD_CAPABILITIES_RESERVED_WIDTH 25
+/* MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT msgresponse */
+#define    MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_LEN 8
+/* Current value set in NIC, in seconds */
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_CURRENT_OFST 0
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_CURRENT_LEN 4
+/* Maximum supported by NIC, in seconds */
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_MAXIMUM_OFST 4
+#define       MC_CMD_PTP_OUT_GET_SYNC_TIMEOUT_MAXIMUM_LEN 4
 
 
 /***********************************/
@@ -4426,112 +3896,6 @@
 #define       MC_CMD_GET_BOARD_CFG_OUT_FW_SUBTYPE_LIST_MAXNUM_MCDI2 32
 
 
-/***********************************/
-/* MC_CMD_DBI_READX
- * Read DBI register(s) -- extended functionality
- */
-#define MC_CMD_DBI_READX 0x19
-#undef MC_CMD_0x19_PRIVILEGE_CTG
-
-#define MC_CMD_0x19_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DBI_READX_IN msgrequest */
-#define    MC_CMD_DBI_READX_IN_LENMIN 8
-#define    MC_CMD_DBI_READX_IN_LENMAX 248
-#define    MC_CMD_DBI_READX_IN_LENMAX_MCDI2 1016
-#define    MC_CMD_DBI_READX_IN_LEN(num) (0+8*(num))
-#define    MC_CMD_DBI_READX_IN_DBIRDOP_NUM(len) (((len)-0)/8)
-/* Each Read op consists of an address (offset 0), VF/CS2) */
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_OFST 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LEN 8
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_OFST 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_LEN 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_LBN 0
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_LO_WIDTH 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_OFST 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_LEN 4
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_LBN 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_HI_WIDTH 32
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MINNUM 1
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MAXNUM 31
-#define       MC_CMD_DBI_READX_IN_DBIRDOP_MAXNUM_MCDI2 127
-
-/* MC_CMD_DBI_READX_OUT msgresponse */
-#define    MC_CMD_DBI_READX_OUT_LENMIN 4
-#define    MC_CMD_DBI_READX_OUT_LENMAX 252
-#define    MC_CMD_DBI_READX_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DBI_READX_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_DBI_READX_OUT_VALUE_NUM(len) (((len)-0)/4)
-/* Value */
-#define       MC_CMD_DBI_READX_OUT_VALUE_OFST 0
-#define       MC_CMD_DBI_READX_OUT_VALUE_LEN 4
-#define       MC_CMD_DBI_READX_OUT_VALUE_MINNUM 1
-#define       MC_CMD_DBI_READX_OUT_VALUE_MAXNUM 63
-#define       MC_CMD_DBI_READX_OUT_VALUE_MAXNUM_MCDI2 255
-
-/* MC_CMD_DBIRDOP_TYPEDEF structuredef */
-#define    MC_CMD_DBIRDOP_TYPEDEF_LEN 8
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_OFST 0
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_LEN 4
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_LBN 0
-#define       MC_CMD_DBIRDOP_TYPEDEF_ADDRESS_WIDTH 32
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_OFST 4
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_LEN 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_LBN 16
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_NUM_WIDTH 16
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_LBN 15
-#define        MC_CMD_DBIRDOP_TYPEDEF_VF_ACTIVE_WIDTH 1
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_OFST 4
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_LBN 14
-#define        MC_CMD_DBIRDOP_TYPEDEF_CS2_WIDTH 1
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_LBN 32
-#define       MC_CMD_DBIRDOP_TYPEDEF_PARMS_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_SET_RAND_SEED
- * Set the 16byte seed for the MC pseudo-random generator.
- */
-#define MC_CMD_SET_RAND_SEED 0x1a
-#undef MC_CMD_0x1a_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_RAND_SEED_IN msgrequest */
-#define    MC_CMD_SET_RAND_SEED_IN_LEN 16
-/* Seed value. */
-#define       MC_CMD_SET_RAND_SEED_IN_SEED_OFST 0
-#define       MC_CMD_SET_RAND_SEED_IN_SEED_LEN 16
-
-/* MC_CMD_SET_RAND_SEED_OUT msgresponse */
-#define    MC_CMD_SET_RAND_SEED_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LTSSM_HIST
- * Retrieve the history of the LTSSM, if the build supports it.
- */
-#define MC_CMD_LTSSM_HIST 0x1b
-
-/* MC_CMD_LTSSM_HIST_IN msgrequest */
-#define    MC_CMD_LTSSM_HIST_IN_LEN 0
-
-/* MC_CMD_LTSSM_HIST_OUT msgresponse */
-#define    MC_CMD_LTSSM_HIST_OUT_LENMIN 0
-#define    MC_CMD_LTSSM_HIST_OUT_LENMAX 252
-#define    MC_CMD_LTSSM_HIST_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LTSSM_HIST_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_LTSSM_HIST_OUT_DATA_NUM(len) (((len)-0)/4)
-/* variable number of LTSSM values, as bytes. The history is read-to-clear. */
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_OFST 0
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_LEN 4
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MINNUM 0
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MAXNUM 63
-#define       MC_CMD_LTSSM_HIST_OUT_DATA_MAXNUM_MCDI2 255
-
-
 /***********************************/
 /* MC_CMD_DRV_ATTACH
  * Inform MCPU that this port is managed on the host (i.e. driver active). For
@@ -4705,6 +4069,7 @@
 /* Flags associated with this function */
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_OFST 4
 #define       MC_CMD_DRV_ATTACH_EXT_OUT_FUNC_FLAGS_LEN 4
+/* enum property: bitshift */
 /* enum: Labels the lowest-numbered function visible to the OS */
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY 0x0
 /* enum: The function can control the link state of the physical port it is
@@ -4731,22 +4096,6 @@
 #define          MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TX_ONLY_VI_SPREADING_ENABLED 0x5
 
 
-/***********************************/
-/* MC_CMD_SHMUART
- * Route UART output to circular buffer in shared memory instead.
- */
-#define MC_CMD_SHMUART 0x1f
-
-/* MC_CMD_SHMUART_IN msgrequest */
-#define    MC_CMD_SHMUART_IN_LEN 4
-/* ??? */
-#define       MC_CMD_SHMUART_IN_FLAG_OFST 0
-#define       MC_CMD_SHMUART_IN_FLAG_LEN 4
-
-/* MC_CMD_SHMUART_OUT msgresponse */
-#define    MC_CMD_SHMUART_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_PORT_RESET
  * Generic per-port reset. There is no equivalent for per-board reset. Locks
@@ -4789,100 +4138,6 @@
 #define    MC_CMD_ENTITY_RESET_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_PCIE_CREDITS
- * Read instantaneous and minimum flow control thresholds.
- */
-#define MC_CMD_PCIE_CREDITS 0x21
-
-/* MC_CMD_PCIE_CREDITS_IN msgrequest */
-#define    MC_CMD_PCIE_CREDITS_IN_LEN 8
-/* poll period. 0 is disabled */
-#define       MC_CMD_PCIE_CREDITS_IN_POLL_PERIOD_OFST 0
-#define       MC_CMD_PCIE_CREDITS_IN_POLL_PERIOD_LEN 4
-/* wipe statistics */
-#define       MC_CMD_PCIE_CREDITS_IN_WIPE_OFST 4
-#define       MC_CMD_PCIE_CREDITS_IN_WIPE_LEN 4
-
-/* MC_CMD_PCIE_CREDITS_OUT msgresponse */
-#define    MC_CMD_PCIE_CREDITS_OUT_LEN 16
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_OFST 0
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_OFST 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_P_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_OFST 4
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_OFST 6
-#define       MC_CMD_PCIE_CREDITS_OUT_CURRENT_NP_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_OFST 8
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_OFST 10
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_P_DATA_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_OFST 12
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_HDR_LEN 2
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_OFST 14
-#define       MC_CMD_PCIE_CREDITS_OUT_MINIMUM_NP_DATA_LEN 2
-
-
-/***********************************/
-/* MC_CMD_RXD_MONITOR
- * Get histogram of RX queue fill level.
- */
-#define MC_CMD_RXD_MONITOR 0x22
-
-/* MC_CMD_RXD_MONITOR_IN msgrequest */
-#define    MC_CMD_RXD_MONITOR_IN_LEN 12
-#define       MC_CMD_RXD_MONITOR_IN_QID_OFST 0
-#define       MC_CMD_RXD_MONITOR_IN_QID_LEN 4
-#define       MC_CMD_RXD_MONITOR_IN_POLL_PERIOD_OFST 4
-#define       MC_CMD_RXD_MONITOR_IN_POLL_PERIOD_LEN 4
-#define       MC_CMD_RXD_MONITOR_IN_WIPE_OFST 8
-#define       MC_CMD_RXD_MONITOR_IN_WIPE_LEN 4
-
-/* MC_CMD_RXD_MONITOR_OUT msgresponse */
-#define    MC_CMD_RXD_MONITOR_OUT_LEN 80
-#define       MC_CMD_RXD_MONITOR_OUT_QID_OFST 0
-#define       MC_CMD_RXD_MONITOR_OUT_QID_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_FILL_OFST 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_FILL_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_FILL_OFST 8
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_FILL_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_1_OFST 12
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_1_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_2_OFST 16
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_2_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_4_OFST 20
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_4_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_8_OFST 24
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_8_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_16_OFST 28
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_16_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_32_OFST 32
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_32_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_64_OFST 36
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_64_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_128_OFST 40
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_128_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_256_OFST 44
-#define       MC_CMD_RXD_MONITOR_OUT_RING_LT_256_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_RING_GE_256_OFST 48
-#define       MC_CMD_RXD_MONITOR_OUT_RING_GE_256_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_1_OFST 52
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_1_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_2_OFST 56
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_2_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_4_OFST 60
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_4_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_8_OFST 64
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_8_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_16_OFST 68
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_16_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_32_OFST 72
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_LT_32_LEN 4
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_GE_32_OFST 76
-#define       MC_CMD_RXD_MONITOR_OUT_CACHE_GE_32_LEN 4
-
-
 /***********************************/
 /* MC_CMD_PUTS
  * Copy the given ASCII string out onto UART and/or out of the network port.
@@ -4931,6 +4186,54 @@
 /* MC_CMD_GET_PHY_CFG_IN msgrequest */
 #define    MC_CMD_GET_PHY_CFG_IN_LEN 0
 
+/* MC_CMD_GET_PHY_CFG_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_CFG_IN_V2_LEN 8
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_PHY_CFG_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_CFG_OUT msgresponse */
 #define    MC_CMD_GET_PHY_CFG_OUT_LEN 72
 /* flags */
@@ -5026,6 +4329,9 @@
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_OFST 8
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_LBN 21
 #define        MC_CMD_PHY_CAP_25G_BASER_FEC_REQUESTED_WIDTH 1
+#define        MC_CMD_PHY_CAP_200000FDX_OFST 8
+#define        MC_CMD_PHY_CAP_200000FDX_LBN 22
+#define        MC_CMD_PHY_CAP_200000FDX_WIDTH 1
 /* ?? */
 #define       MC_CMD_GET_PHY_CFG_OUT_CHANNEL_OFST 12
 #define       MC_CMD_GET_PHY_CFG_OUT_CHANNEL_LEN 4
@@ -5059,6 +4365,7 @@
 #define          MC_CMD_MEDIA_DSFP 0x8
 #define       MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48
 #define       MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_LEN 4
+/* enum property: bitshift */
 /* enum: Native clause 22 */
 #define          MC_CMD_MMD_CLAUSE22 0x0
 #define          MC_CMD_MMD_CLAUSE45_PMAPMD 0x1 /* enum */
@@ -5084,7 +4391,7 @@
 #define MC_CMD_START_BIST 0x25
 #undef MC_CMD_0x25_PRIVILEGE_CTG
 
-#define MC_CMD_0x25_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x25_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_START_BIST_IN msgrequest */
 #define    MC_CMD_START_BIST_IN_LEN 4
@@ -5124,7 +4431,7 @@
 #define MC_CMD_POLL_BIST 0x26
 #undef MC_CMD_0x26_PRIVILEGE_CTG
 
-#define MC_CMD_0x26_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x26_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_POLL_BIST_IN msgrequest */
 #define    MC_CMD_POLL_BIST_IN_LEN 0
@@ -5281,33 +4588,6 @@
 #define       MC_CMD_POLL_BIST_OUT_MEM_ECC_FATAL_LEN 4
 
 
-/***********************************/
-/* MC_CMD_FLUSH_RX_QUEUES
- * Flush receive queue(s). If SRIOV is enabled (via MC_CMD_SRIOV), then RXQ
- * flushes should be initiated via this MCDI operation, rather than via
- * directly writing FLUSH_CMD.
- *
- * The flush is completed (either done/fail) asynchronously (after this command
- * returns). The driver must still wait for flush done/failure events as usual.
- */
-#define MC_CMD_FLUSH_RX_QUEUES 0x27
-
-/* MC_CMD_FLUSH_RX_QUEUES_IN msgrequest */
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMIN 4
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX 252
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_LEN(num) (0+4*(num))
-#define    MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_NUM(len) (((len)-0)/4)
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_OFST 0
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_LEN 4
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MINNUM 1
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM 63
-#define       MC_CMD_FLUSH_RX_QUEUES_IN_QID_OFST_MAXNUM_MCDI2 255
-
-/* MC_CMD_FLUSH_RX_QUEUES_OUT msgresponse */
-#define    MC_CMD_FLUSH_RX_QUEUES_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_GET_LOOPBACK_MODES
  * Returns a bitmask of loopback modes available at each speed.
@@ -5320,6 +4600,54 @@
 /* MC_CMD_GET_LOOPBACK_MODES_IN msgrequest */
 #define    MC_CMD_GET_LOOPBACK_MODES_IN_LEN 0
 
+/* MC_CMD_GET_LOOPBACK_MODES_IN_V2 msgrequest */
+#define    MC_CMD_GET_LOOPBACK_MODES_IN_V2_LEN 8
+/* Target port to request loopback modes for. Uses MAE_LINK_ENDPOINT_SELECTOR
+ * which identifies a real or virtual network port by MAE port and link end.
+ * See the structure definition for more details
+ */
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_LOOPBACK_MODES_OUT msgresponse */
 #define    MC_CMD_GET_LOOPBACK_MODES_OUT_LEN 40
 /* Supported loopbacks. */
@@ -5333,6 +4661,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_LBN 32
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_100M_HI_WIDTH 32
+/* enum property: bitshift */
 /* enum: None. */
 #define          MC_CMD_LOOPBACK_NONE 0x0
 /* enum: Data. */
@@ -5422,6 +4751,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_LBN 96
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_1G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5435,6 +4765,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_LBN 160
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_10G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5448,6 +4779,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_LBN 224
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5461,6 +4793,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_LBN 288
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_40G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 
@@ -5479,6 +4812,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_LBN 32
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100M_HI_WIDTH 32
+/* enum property: bitshift */
 /* enum: None. */
 /*               MC_CMD_LOOPBACK_NONE 0x0 */
 /* enum: Data. */
@@ -5568,6 +4902,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_LBN 96
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_1G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5581,6 +4916,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_LBN 160
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_10G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5594,6 +4930,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_LBN 224
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported loopbacks. */
@@ -5607,6 +4944,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_LBN 288
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_40G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 25G loopbacks. */
@@ -5620,6 +4958,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_LBN 352
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_25G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 50 loopbacks. */
@@ -5633,6 +4972,7 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_LBN 416
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_50G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 /* Supported 100G loopbacks. */
@@ -5646,142 +4986,1221 @@
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_LEN 4
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_LBN 480
 #define       MC_CMD_GET_LOOPBACK_MODES_OUT_V2_100G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
 /*               100M */
 
-/* AN_TYPE structuredef: Auto-negotiation types defined in IEEE802.3 */
-#define    AN_TYPE_LEN 4
-#define       AN_TYPE_TYPE_OFST 0
-#define       AN_TYPE_TYPE_LEN 4
-/* enum: None, AN disabled or not supported */
-#define          MC_CMD_AN_NONE 0x0
-/* enum: Clause 28 - BASE-T */
-#define          MC_CMD_AN_CLAUSE28 0x1
-/* enum: Clause 37 - BASE-X */
-#define          MC_CMD_AN_CLAUSE37 0x2
-/* enum: Clause 73 - BASE-R startup protocol for backplane and copper cable
- * assemblies. Includes Clause 72/Clause 92 link-training.
- */
-#define          MC_CMD_AN_CLAUSE73 0x3
-#define       AN_TYPE_TYPE_LBN 0
-#define       AN_TYPE_TYPE_WIDTH 32
-
-/* FEC_TYPE structuredef: Forward error correction types defined in IEEE802.3
- */
-#define    FEC_TYPE_LEN 4
-#define       FEC_TYPE_TYPE_OFST 0
-#define       FEC_TYPE_TYPE_LEN 4
-/* enum: No FEC */
-#define          MC_CMD_FEC_NONE 0x0
-/* enum: Clause 74 BASE-R FEC (a.k.a Firecode) */
-#define          MC_CMD_FEC_BASER 0x1
-/* enum: Clause 91/Clause 108 Reed-Solomon FEC */
-#define          MC_CMD_FEC_RS 0x2
-#define       FEC_TYPE_TYPE_LBN 0
-#define       FEC_TYPE_TYPE_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_GET_LINK
- * Read the unified MAC/PHY link state. Locks required: None Return code: 0,
- * ETIME.
- */
-#define MC_CMD_GET_LINK 0x29
-#undef MC_CMD_0x29_PRIVILEGE_CTG
-
-#define MC_CMD_0x29_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_LINK_IN msgrequest */
-#define    MC_CMD_GET_LINK_IN_LEN 0
-
-/* MC_CMD_GET_LINK_OUT msgresponse */
-#define    MC_CMD_GET_LINK_OUT_LEN 28
-/* Near-side advertised capabilities. Refer to
- * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
- */
-#define       MC_CMD_GET_LINK_OUT_CAP_OFST 0
-#define       MC_CMD_GET_LINK_OUT_CAP_LEN 4
-/* Link-partner advertised capabilities. Refer to
- * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
- */
-#define       MC_CMD_GET_LINK_OUT_LP_CAP_OFST 4
-#define       MC_CMD_GET_LINK_OUT_LP_CAP_LEN 4
-/* Autonegotiated speed in mbit/s. The link may still be down even if this
- * reads non-zero.
+/* MC_CMD_GET_LOOPBACK_MODES_OUT_V3 msgresponse: Supported loopback modes for
+ * newer NICs with 200G support
  */
-#define       MC_CMD_GET_LINK_OUT_LINK_SPEED_OFST 8
-#define       MC_CMD_GET_LINK_OUT_LINK_SPEED_LEN 4
-/* Current loopback setting. */
-#define       MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_OFST 12
-#define       MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
-#define       MC_CMD_GET_LINK_OUT_FLAGS_OFST 16
-#define       MC_CMD_GET_LINK_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_LINK_OUT_LINK_UP_OFST 16
-#define        MC_CMD_GET_LINK_OUT_LINK_UP_LBN 0
-#define        MC_CMD_GET_LINK_OUT_LINK_UP_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_OFST 16
-#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN 1
-#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_BPX_LINK_OFST 16
-#define        MC_CMD_GET_LINK_OUT_BPX_LINK_LBN 2
-#define        MC_CMD_GET_LINK_OUT_BPX_LINK_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_PHY_LINK_OFST 16
-#define        MC_CMD_GET_LINK_OUT_PHY_LINK_LBN 3
-#define        MC_CMD_GET_LINK_OUT_PHY_LINK_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_OFST 16
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_LBN 6
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_OFST 16
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_LBN 7
-#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_OFST 16
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_LBN 8
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_WIDTH 1
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_OFST 16
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_LBN 9
-#define        MC_CMD_GET_LINK_OUT_MODULE_UP_WIDTH 1
-/* This returns the negotiated flow control value. */
-#define       MC_CMD_GET_LINK_OUT_FCNTL_OFST 20
-#define       MC_CMD_GET_LINK_OUT_FCNTL_LEN 4
+#define    MC_CMD_GET_LOOPBACK_MODES_OUT_V3_LEN 72
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_OFST 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_LBN 0
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_OFST 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_LBN 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100M_HI_WIDTH 32
+/* enum property: bitshift */
+/* enum: None. */
+/*               MC_CMD_LOOPBACK_NONE 0x0 */
+/* enum: Data. */
+/*               MC_CMD_LOOPBACK_DATA 0x1 */
+/* enum: GMAC. */
+/*               MC_CMD_LOOPBACK_GMAC 0x2 */
+/* enum: XGMII. */
+/*               MC_CMD_LOOPBACK_XGMII 0x3 */
+/* enum: XGXS. */
+/*               MC_CMD_LOOPBACK_XGXS 0x4 */
+/* enum: XAUI. */
+/*               MC_CMD_LOOPBACK_XAUI 0x5 */
+/* enum: GMII. */
+/*               MC_CMD_LOOPBACK_GMII 0x6 */
+/* enum: SGMII. */
+/*               MC_CMD_LOOPBACK_SGMII 0x7 */
+/* enum: XGBR. */
+/*               MC_CMD_LOOPBACK_XGBR 0x8 */
+/* enum: XFI. */
+/*               MC_CMD_LOOPBACK_XFI 0x9 */
+/* enum: XAUI Far. */
+/*               MC_CMD_LOOPBACK_XAUI_FAR 0xa */
+/* enum: GMII Far. */
+/*               MC_CMD_LOOPBACK_GMII_FAR 0xb */
+/* enum: SGMII Far. */
+/*               MC_CMD_LOOPBACK_SGMII_FAR 0xc */
+/* enum: XFI Far. */
+/*               MC_CMD_LOOPBACK_XFI_FAR 0xd */
+/* enum: GPhy. */
+/*               MC_CMD_LOOPBACK_GPHY 0xe */
+/* enum: PhyXS. */
+/*               MC_CMD_LOOPBACK_PHYXS 0xf */
+/* enum: PCS. */
+/*               MC_CMD_LOOPBACK_PCS 0x10 */
+/* enum: PMA-PMD. */
+/*               MC_CMD_LOOPBACK_PMAPMD 0x11 */
+/* enum: Cross-Port. */
+/*               MC_CMD_LOOPBACK_XPORT 0x12 */
+/* enum: XGMII-Wireside. */
+/*               MC_CMD_LOOPBACK_XGMII_WS 0x13 */
+/* enum: XAUI Wireside. */
+/*               MC_CMD_LOOPBACK_XAUI_WS 0x14 */
+/* enum: XAUI Wireside Far. */
+/*               MC_CMD_LOOPBACK_XAUI_WS_FAR 0x15 */
+/* enum: XAUI Wireside near. */
+/*               MC_CMD_LOOPBACK_XAUI_WS_NEAR 0x16 */
+/* enum: GMII Wireside. */
+/*               MC_CMD_LOOPBACK_GMII_WS 0x17 */
+/* enum: XFI Wireside. */
+/*               MC_CMD_LOOPBACK_XFI_WS 0x18 */
+/* enum: XFI Wireside Far. */
+/*               MC_CMD_LOOPBACK_XFI_WS_FAR 0x19 */
+/* enum: PhyXS Wireside. */
+/*               MC_CMD_LOOPBACK_PHYXS_WS 0x1a */
+/* enum: PMA lanes MAC-Serdes. */
+/*               MC_CMD_LOOPBACK_PMA_INT 0x1b */
+/* enum: KR Serdes Parallel (Encoder). */
+/*               MC_CMD_LOOPBACK_SD_NEAR 0x1c */
+/* enum: KR Serdes Serial. */
+/*               MC_CMD_LOOPBACK_SD_FAR 0x1d */
+/* enum: PMA lanes MAC-Serdes Wireside. */
+/*               MC_CMD_LOOPBACK_PMA_INT_WS 0x1e */
+/* enum: KR Serdes Parallel Wireside (Full PCS). */
+/*               MC_CMD_LOOPBACK_SD_FEP2_WS 0x1f */
+/* enum: KR Serdes Parallel Wireside (Sym Aligner to TX). */
+/*               MC_CMD_LOOPBACK_SD_FEP1_5_WS 0x20 */
+/* enum: KR Serdes Parallel Wireside (Deserializer to Serializer). */
+/*               MC_CMD_LOOPBACK_SD_FEP_WS 0x21 */
+/* enum: KR Serdes Serial Wireside. */
+/*               MC_CMD_LOOPBACK_SD_FES_WS 0x22 */
+/* enum: Near side of AOE Siena side port */
+/*               MC_CMD_LOOPBACK_AOE_INT_NEAR 0x23 */
+/* enum: Medford Wireside datapath loopback */
+/*               MC_CMD_LOOPBACK_DATA_WS 0x24 */
+/* enum: Force link up without setting up any physical loopback (snapper use
+ * only)
+ */
+/*               MC_CMD_LOOPBACK_FORCE_EXT_LINK 0x25 */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_OFST 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_OFST 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_LBN 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_OFST 12
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_LBN 96
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_1G_HI_WIDTH 32
+/* enum property: bitshift */
 /*            Enum values, see field(s): */
-/*               MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */
-#define       MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24
-#define       MC_CMD_GET_LINK_OUT_MAC_FAULT_LEN 4
-#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_OFST 24
-#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0
-#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1
-#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_OFST 24
-#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_LBN 1
-#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_WIDTH 1
-#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_OFST 24
-#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_LBN 2
-#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_WIDTH 1
-#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_OFST 24
-#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_LBN 3
-#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_WIDTH 1
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_OFST 16
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_OFST 16
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_LBN 128
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_OFST 20
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_LBN 160
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_10G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_OFST 24
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_OFST 24
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_LBN 192
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_OFST 28
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_LBN 224
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_SUGGESTED_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_OFST 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_OFST 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_LBN 256
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_OFST 36
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_LBN 288
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_40G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 25G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_OFST 40
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_OFST 40
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_LBN 320
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_OFST 44
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_LBN 352
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_25G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 50 loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_OFST 48
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_OFST 48
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_LBN 384
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_OFST 52
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_LBN 416
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_50G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 100G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_OFST 56
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_OFST 56
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_LBN 448
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_OFST 60
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_LBN 480
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_100G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
+/* Supported 200G loopbacks. */
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_OFST 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LEN 8
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_OFST 64
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_LBN 512
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_LO_WIDTH 32
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_OFST 68
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_LEN 4
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_LBN 544
+#define       MC_CMD_GET_LOOPBACK_MODES_OUT_V3_200G_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               100M */
 
-/* MC_CMD_GET_LINK_OUT_V2 msgresponse: Extended link state information */
-#define    MC_CMD_GET_LINK_OUT_V2_LEN 44
+/* AN_TYPE structuredef: Auto-negotiation types defined in IEEE802.3 */
+#define    AN_TYPE_LEN 4
+#define       AN_TYPE_TYPE_OFST 0
+#define       AN_TYPE_TYPE_LEN 4
+/* enum: None, AN disabled or not supported */
+#define          MC_CMD_AN_NONE 0x0
+/* enum: Clause 28 - BASE-T */
+#define          MC_CMD_AN_CLAUSE28 0x1
+/* enum: Clause 37 - BASE-X */
+#define          MC_CMD_AN_CLAUSE37 0x2
+/* enum: Clause 73 - BASE-R startup protocol for backplane and copper cable
+ * assemblies. Includes Clause 72/Clause 92 link-training.
+ */
+#define          MC_CMD_AN_CLAUSE73 0x3
+#define       AN_TYPE_TYPE_LBN 0
+#define       AN_TYPE_TYPE_WIDTH 32
+
+/* FEC_TYPE structuredef: Forward error correction types defined in IEEE802.3
+ */
+#define    FEC_TYPE_LEN 4
+#define       FEC_TYPE_TYPE_OFST 0
+#define       FEC_TYPE_TYPE_LEN 4
+/* enum: No FEC */
+#define          MC_CMD_FEC_NONE 0x0
+/* enum: IEEE 802.3, Clause 74 BASE-R FEC (a.k.a Firecode) */
+#define          MC_CMD_FEC_BASER 0x1
+/* enum: IEEE 802.3, Clause 91/Clause 108 Reed-Solomon FEC */
+#define          MC_CMD_FEC_RS 0x2
+/* enum: IEEE 802.3, Clause 161, interleaved RS-FEC sublayer for 100GBASE-R
+ * PHYs
+ */
+#define          MC_CMD_FEC_IEEE_RS_INT 0x3
+/* enum: Ethernet Consortium, Low Latency RS-FEC. RS(272, 258). Replaces FEC
+ * specified in Clause 119 for 100/200G PHY. Replaces FEC specified in Clause
+ * 134 for 50G PHY.
+ */
+#define          MC_CMD_FEC_ETCS_RS_LL 0x4
+/* enum: FEC mode selected automatically */
+#define          MC_CMD_FEC_AUTO 0x5
+#define       FEC_TYPE_TYPE_LBN 0
+#define       FEC_TYPE_TYPE_WIDTH 32
+
+/* MC_CMD_ETH_TECH structuredef: Ethernet technology as defined by IEEE802.3,
+ * Ethernet Technology Consortium, proprietary technologies. The driver must
+ * not use technologies labelled NONE and AUTO.
+ */
+#define    MC_CMD_ETH_TECH_LEN 16
+/* The enums in this field can be used either as bitwise indices into a tech
+ * mask (e.g. see MC_CMD_ETH_AN_FIELDS/TECH_MASK for example) or as regular
+ * enums (e.g. see MC_CMD_LINK_CTRL_IN/ADVERTISED_TECH_ABILITIES_MASK). This
+ * structure must be updated to add new technologies when projects that need
+ * them arise. An incomplete list of possible expansion in the future include:
+ * 100GBASE_KP4, 800GBASE_CR8, 800GBASE_KR8, 800GBASE_DR8, 800GBASE_SR8
+ * 800GBASE_VR8
+ */
+#define       MC_CMD_ETH_TECH_TECH_OFST 0
+#define       MC_CMD_ETH_TECH_TECH_LEN 16
+/* enum: 1000BASE-KX - 1000BASE-X PCS/PMA over an electrical backplane PMD. See
+ * IEEE 802.3 Clause 70
+ */
+#define          MC_CMD_ETH_TECH_1000BASEKX 0x0
+/* enum: 10GBASE-R - PCS/PMA over an electrical backplane PMD. Refer to IEEE
+ * 802.3 Clause 72
+ */
+#define          MC_CMD_ETH_TECH_10GBASE_KR 0x1
+/* enum: 40GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 84.
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_KR4 0x2
+/* enum: 40GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 85
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_CR4 0x3
+/* enum: 40GBASE-R PCS/PMA over 4 lane multimode fiber PMD as specified in
+ * Clause 86
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_SR4 0x4
+/* enum: 40GBASE-R PCS/PMA over 4 WDM lane single mode fiber PMD with long
+ * reach. See IEEE 802.3 Clause 87
+ */
+#define          MC_CMD_ETH_TECH_40GBASE_LR4 0x5
+/* enum: 25GBASE-R PCS/PMA over shielded balanced copper cable PMD. See IEEE
+ * 802.3 Clause 110
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_CR 0x6
+/* enum: 25GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 111
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_KR 0x7
+/* enum: 25GBASE-R PCS/PMA over multimode fiber PMD. Refer to IEEE 802.3 Clause
+ * 112
+ */
+#define          MC_CMD_ETH_TECH_25GBASE_SR 0x8
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on twin-axial copper
+ * cable. Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_CR2 0x9
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on copper backplane.
+ * Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_KR2 0xa
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 93
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR4 0xb
+/* enum: 100GBASE-R PCS/PMA over 4 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 95
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR4 0xc
+/* enum: 100GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 92
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR4 0xd
+/* enum: 100GBASE-R PCS/PMA over 4 WDM lane single mode fiber PMD, with
+ * long/extended reach,. See IEEE 802.3 Clause 88
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_LR4_ER4 0xe
+/* enum: An Ethernet Physical layer operating at 50 Gb/s on short reach fiber.
+ * Refer to Ethernet Technology Consortium 25/50G Ethernet Spec.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_SR2 0xf
+/* enum: 1000BASEX PCS/PMA. See IEEE 802.3 Clause 36 over undefined PMD, duplex
+ * mode unknown
+ */
+#define          MC_CMD_ETH_TECH_1000BASEX 0x10
+/* enum: Non-standardised. 10G direct attach */
+#define          MC_CMD_ETH_TECH_10GBASE_CR 0x11
+/* enum: 10GBASE-SR fiber over 850nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_SR 0x12
+/* enum: 10GBASE-LR fiber over 1310nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_LR 0x13
+/* enum: 10GBASE-LRM fiber over 1310 nm optics. See IEEE 802.3 Clause 68 */
+#define          MC_CMD_ETH_TECH_10GBASE_LRM 0x14
+/* enum: 10GBASE-ER fiber over 1550nm optics. See IEEE 802.3 Clause 52 */
+#define          MC_CMD_ETH_TECH_10GBASE_ER 0x15
+/* enum: 50GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_KR 0x16
+/* enum: 50GBASE-SR PCS/PMA over multimode fiber PMD as specified in Clause 138
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_SR 0x17
+/* enum: 50GBASE-CR PCS/PMA over shielded copper balanced cable PMD. See IEEE
+ * 802.3 Clause 136
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_CR 0x18
+/* enum: 50GBASE-R PCS/PMA over single mode fiber PMD as specified in Clause
+ * 139.
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_LR_ER_FR 0x19
+/* enum: 100 Gb/s PHY using 100GBASE-R encoding over single-mode fiber with
+ * reach up to at least 500 m (see IEEE 802.3 Clause 140)
+ */
+#define          MC_CMD_ETH_TECH_50GBASE_DR 0x1a
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR2 0x1b
+/* enum: 100GBASE-R PCS/PMA over 2 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR2 0x1c
+/* enum: 100GBASE-R PCS/PMA over 2 lane shielded copper balanced cable PMD. See
+ * IEEE 802.3 Clause 136
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR2 0x1d
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_100GBASE_LR2_ER2_FR2 0x1e
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_100GBASE_DR2 0x1f
+/* enum: 200GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 137
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_KR4 0x20
+/* enum: 200GBASE-R PCS/PMA over 4 lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_SR4 0x21
+/* enum: 200GBASE-R PCS/PMA over 4 WDM lane single-mode fiber PMD as specified
+ * in Clause 122
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_LR4_ER4_FR4 0x22
+/* enum: 200GBASE-R PCS/PMA over 4-lane single-mode fiber PMD. See IEEE 802.3
+ * Clause 121
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_DR4 0x23
+/* enum: 200GBASE-R PCS/PMA over 4 lane shielded copper balanced cable PMD as
+ * specified in Clause 136
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_CR4 0x24
+/* enum: Ethernet Technology Consortium 400G AN Spec. 400GBASE-KR8 PMD uses
+ * 802.3 Clause 137, but the number PMD lanes is 8.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_KR8 0x25
+/* enum: 400GBASE-R PCS/PMA over 8-lane multimode fiber PMD. See IEEE 802.3
+ * Clause 138
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_SR8 0x26
+/* enum: 400GBASE-R PCS/PMA over 8 WDM lane single-mode fiber PMD. See IEEE
+ * 802.3 Clause 122
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_LR8_ER8_FR8 0x27
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_400GBASE_DR8 0x28
+/* enum: Ethernet Technology Consortium 400G AN Spec. 400GBASE-CR8 PMD uses
+ * IEEE 802.3 Clause 136, but the number PMD lanes is 8.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_CR8 0x29
+/* enum: 100GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3ck
+ * Clause 163.
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_KR 0x2a
+/* enum: IEEE 802.3ck. 100G PHY with PMD as specified in Clause 167 over short
+ * reach fiber
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_SR 0x2b
+/* enum: 100G PMD together with single-mode fiber medium. See IEEE 802.3 Clause
+ * 140
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_LR_ER_FR 0x2c
+/* enum: 100GBASE-R PCS/PMA over shielded balanced copper cable PMD. See IEEE
+ * 802.3 in Clause 162 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR 0x2d
+/* enum: 100G PMD together with single-mode fiber medium. See IEEE 802.3 Clause
+ * 140
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_DR 0x2e
+/* enum: 200GBASE-R PCS/PMA over an electrical backplane PMD as specified in
+ * Clause 163 IEEE 802.3ck
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_KR2 0x2f
+/* enum: 200G PHY with PMD as specified in Clause 167 over short reach fiber
+ * IEEE 802.3ck
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_SR2 0x30
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_200GBASE_LR2_ER2_FR2 0x31
+/* enum: Unknown source */
+#define          MC_CMD_ETH_TECH_200GBASE_DR2 0x32
+/* enum: 200GBASE-R PCS/PMA over 2 lane shielded balanced copper cable PMD as
+ * specified in Clause 162 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_200GBASE_CR2 0x33
+/* enum: 400GBASE-R PCS/PMA over an electrical backplane PMD. See IEEE 802.3
+ * Clause 163 IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_KR4 0x34
+/* enum: 400G PHY with PMD over short reach fiber. See Clause 167 of IEEE
+ * 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_SR4 0x35
+/* enum: 400GBASE-R PCS/PMA over 4 WDM lane single-mode fiber PMD. See IEEE
+ * 802.3 Clause 151
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_LR4_ER4_FR4 0x36
+/* enum: 400GBASE-R PCS/PMA over 4-lane single-mode fiber PMD as specified in
+ * Clause 124
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_DR4 0x37
+/* enum: 400GBASE-R PCS/PMA over 4 lane shielded balanced copper cable PMD as
+ * specified in Clause 162 of IEEE 802.3ck.
+ */
+#define          MC_CMD_ETH_TECH_400GBASE_CR4 0x38
+/* enum: Automatic tech mode. The driver must not use this. */
+#define          MC_CMD_ETH_TECH_AUTO 0x39
+/* enum: See IEEE 802.3cc-2017 Clause 114 */
+#define          MC_CMD_ETH_TECH_25GBASE_LR_ER 0x3a
+/* enum: Up to 7 m over twinaxial copper cable assembly (10 lanes, 10 Gbit/s
+ * each) See IEEE 802.3ba-2010 Clause 85
+ */
+#define          MC_CMD_ETH_TECH_100GBASE_CR10 0x3b
+/* enum: Invalid tech mode. The driver must not use this. */
+#define          MC_CMD_ETH_TECH_NONE 0x7f
+#define       MC_CMD_ETH_TECH_TECH_LBN 0
+#define       MC_CMD_ETH_TECH_TECH_WIDTH 128
+
+/* MC_CMD_LINK_STATUS_FLAGS structuredef */
+#define    MC_CMD_LINK_STATUS_FLAGS_LEN 8
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: bitshift */
+/* enum: Whether we have overall link up */
+#define          MC_CMD_LINK_STATUS_FLAGS_LINK_UP 0x0
+/* enum: If set, the PHY has no external RX link synchronisation */
+#define          MC_CMD_LINK_STATUS_FLAGS_NO_PHY_LINK 0x1
+/* enum: If set, PMD/MDI is not connected (e.g. cable disconnected, module cage
+ * empty)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_MDI_DISCONNECTED 0x2
+/* enum: Set on error while decoding module data (e.g. module EEPROM does not
+ * contain valid values, has checksum errors, etc.)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_BAD 0x3
+/* enum: Set when module unsupported (e.g. unsupported link rate or link
+ * technology)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_UNSUPPORTED 0x4
+/* enum: Set on error while communicating with the module (e.g. I2C errors
+ * while reading EEPROM)
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_COMMS_FAULT 0x5
+/* enum: Set on module overcurrent/overvoltage condition */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_POWER_FAULT 0x6
+/* enum: Set on module overtemperature condition */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_THERMAL_FAULT 0x7
+/* enum: If set, the module is indicating Loss of Signal */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMD_LOS 0x8
+/* enum: If set, PMA is indicating loss of CDR lock (clock sync) */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMA_NO_CDR_LOCK 0x9
+/* enum: If set, PMA is indicating loss of analog signal */
+#define          MC_CMD_LINK_STATUS_FLAGS_PMA_LOS 0xa
+/* enum: If set, PCS is indicating loss of block lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_BLOCK_LOCK 0xb
+/* enum: If set, PCS is indicating loss of alignment marker lock on one or more
+ * lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_AM_LOCK 0xc
+/* enum: If set, PCS is indicating loss of overall alignment lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_NO_ALIGN_LOCK 0xd
+/* enum: If set, PCS is indicating high bit error rate condition. */
+#define          MC_CMD_LINK_STATUS_FLAGS_PCS_HI_BER 0xe
+/* enum: If set, FEC is indicating loss of FEC lock */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_NO_LOCK 0xf
+/* enum: If set, indicates that the number of symbol errors in a 8192-codeword
+ * window has exceeded the threshold K (417).
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_HI_SER 0x10
+/* enum: If set, the receiver has detected the local FEC has degraded. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_LOCAL_DEGRADED 0x11
+/* enum: If set, the receiver has detected the remote FEC has degraded. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_RM_DEGRADED 0x12
+/* enum: If set, the number of symbol errors is over an internal threshold. */
+#define          MC_CMD_LINK_STATUS_FLAGS_FEC_DEGRADED_SER 0x13
+/* enum: If set, autonegotiation has detected an auto-negotiation capable link
+ * partner
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_ABLE 0x14
+/* enum: If set, autonegotiation base page exchange has failed */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_BP_FAILED 0x15
+/* enum: If set, autonegotiation next page exchange has failed */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_NP_FAILED 0x16
+/* enum: If set, autonegotiation has failed to negotiate a common set of
+ * capabilities
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_AN_NO_HCD 0x17
+/* enum: If set, local end link training has failed to establish link training
+ * frame lock on one or more lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_LOCAL_FRAME_LOCK 0x18
+/* enum: If set, remote end link training has failed to establish link training
+ * frame lock on one or more lanes
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_RM_FRAME_LOCK 0x19
+/* enum: If set, remote end has failed to assert Receiver Ready (link training
+ * success) within the designated timeout
+ */
+#define          MC_CMD_LINK_STATUS_FLAGS_LT_NO_RX_READY 0x1a
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_LBN 0
+#define       MC_CMD_LINK_STATUS_FLAGS_STATUS_FLAGS_WIDTH 64
+
+/* MC_CMD_PAUSE_MODE structuredef */
+#define    MC_CMD_PAUSE_MODE_LEN 1
+#define       MC_CMD_PAUSE_MODE_TYPE_OFST 0
+#define       MC_CMD_PAUSE_MODE_TYPE_LEN 1
+/* enum: See IEEE 802.3 Clause 73.6.6 */
+#define          MC_CMD_PAUSE_MODE_AN_PAUSE 0x0
+/* enum: See IEEE 802.3 Clause 73.6.6 */
+#define          MC_CMD_PAUSE_MODE_AN_ASYM_DIR 0x1
+#define       MC_CMD_PAUSE_MODE_TYPE_LBN 0
+#define       MC_CMD_PAUSE_MODE_TYPE_WIDTH 8
+
+/* MC_CMD_ETH_AN_FIELDS structuredef: Fields used for IEEE 802.3 Clause 73
+ * Auto-Negotiation. Warning - This is fixed size and cannot be extended. This
+ * structure is used to define autonegotiable abilities (advertised, link
+ * partner and supported abilities).
+ */
+#define    MC_CMD_ETH_AN_FIELDS_LEN 25
+/* Mask of Ethernet technologies. The bit indices in this mask are taken from
+ * the TECH field in the MC_CMD_ETH_TECH structure.
+ */
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_OFST 0
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_LBN 0
+#define       MC_CMD_ETH_AN_FIELDS_TECH_MASK_WIDTH 128
+/* Mask of supported FEC modes */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_OFST 16
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_LBN 128
+#define       MC_CMD_ETH_AN_FIELDS_FEC_MASK_WIDTH 32
+/* Mask of requested FEC modes */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_OFST 20
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_LBN 160
+#define       MC_CMD_ETH_AN_FIELDS_FEC_REQ_WIDTH 32
+/* Bitmask of negotiated pause modes */
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_OFST 24
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_LBN 192
+#define       MC_CMD_ETH_AN_FIELDS_PAUSE_MASK_WIDTH 8
+
+/* MC_CMD_LOOPBACK_V2 structuredef: Loopback modes for use with the new
+ * MC_CMD_LINK_CTRL and MC_CMD_LINK_STATE. These loopback modes are not
+ * supported in other getlink/setlink commands.
+ */
+#define    MC_CMD_LOOPBACK_V2_LEN 4
+#define       MC_CMD_LOOPBACK_V2_MODE_OFST 0
+#define       MC_CMD_LOOPBACK_V2_MODE_LEN 4
+/* enum: No loopback */
+#define          MC_CMD_LOOPBACK_V2_NONE 0x0
+/* enum: Let firmware choose a supported loopback mode */
+#define          MC_CMD_LOOPBACK_V2_AUTO 0x1
+/* enum: Loopback after the MAC */
+#define          MC_CMD_LOOPBACK_V2_POST_MAC 0x2
+/* enum: Loopback after the PCS */
+#define          MC_CMD_LOOPBACK_V2_POST_PCS 0x3
+/* enum: Loopback after the PMA */
+#define          MC_CMD_LOOPBACK_V2_POST_PMA 0x4
+/* enum: Loopback after the MDI Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_MDI_WS 0x5
+/* enum: Loopback after the PMA Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_PMA_WS 0x6
+/* enum: Loopback after the PCS Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_PCS_WS 0x7
+/* enum: Loopback after the MAC Wireside */
+#define          MC_CMD_LOOPBACK_V2_POST_MAC_WS 0x8
+/* enum: Loopback after the MAC FIFOs (before the MAC) */
+#define          MC_CMD_LOOPBACK_V2_PRE_MAC 0x9
+#define       MC_CMD_LOOPBACK_V2_MODE_LBN 0
+#define       MC_CMD_LOOPBACK_V2_MODE_WIDTH 32
+
+/* MC_CMD_FCNTL structuredef */
+#define    MC_CMD_FCNTL_LEN 4
+#define       MC_CMD_FCNTL_MASK_OFST 0
+#define       MC_CMD_FCNTL_MASK_LEN 4
+/* enum: Flow control is off. */
+#define          MC_CMD_FCNTL_OFF 0x0
+/* enum: Respond to flow control. */
+#define          MC_CMD_FCNTL_RESPOND 0x1
+/* enum: Respond to and Issue flow control. */
+#define          MC_CMD_FCNTL_BIDIR 0x2
+/* enum: Auto negotiate flow control. */
+#define          MC_CMD_FCNTL_AUTO 0x3
+/* enum: Priority flow control. This is only supported on KSB. */
+#define          MC_CMD_FCNTL_QBB 0x4
+/* enum: Issue flow control. */
+#define          MC_CMD_FCNTL_GENERATE 0x5
+#define       MC_CMD_FCNTL_MASK_LBN 0
+#define       MC_CMD_FCNTL_MASK_WIDTH 32
+
+/* MC_CMD_LINK_FLAGS structuredef */
+#define    MC_CMD_LINK_FLAGS_LEN 4
+/* The enums defined in this field are used as indices into the
+ * MC_CMD_LINK_FLAGS bitmask.
+ */
+#define       MC_CMD_LINK_FLAGS_MASK_OFST 0
+#define       MC_CMD_LINK_FLAGS_MASK_LEN 4
+/* enum property: bitshift */
+/* enum: Enable auto-negotiation. If AN is enabled, link technology and FEC
+ * mode are determined by advertised capabilities and requested FEC modes,
+ * combined with link partner capabilities. If AN is disabled, link technology
+ * is forced to LINK_TECHNOLOGY and FEC mode is forced to FEC_MODE. Not valid
+ * if loopback is enabled
+ */
+#define          MC_CMD_LINK_FLAGS_AUTONEG_EN 0x0
+/* enum: Enable parallel detect. In addition to AN, try to sense partner forced
+ * speed/FEC mode (when partner AN disabled). Only valid if AN is enabled.
+ */
+#define          MC_CMD_LINK_FLAGS_PARALLEL_DETECT_EN 0x1
+/* enum: Force link down, in electrical idle. */
+#define          MC_CMD_LINK_FLAGS_LINK_DISABLE 0x2
+/* enum: Ignore the sequence number and always apply. */
+#define          MC_CMD_LINK_FLAGS_IGNORE_MODULE_SEQ 0x3
+#define       MC_CMD_LINK_FLAGS_MASK_LBN 0
+#define       MC_CMD_LINK_FLAGS_MASK_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_LINK_CTRL
+ * Write the unified MAC/PHY link configuration. Locks required: None. Return
+ * code: 0, EINVAL, ETIME, EAGAIN
+ */
+#define MC_CMD_LINK_CTRL 0x6b
+#undef MC_CMD_0x6b_PRIVILEGE_CTG
+
+#define MC_CMD_0x6b_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_LINK_CTRL_IN msgrequest */
+#define    MC_CMD_LINK_CTRL_IN_LEN 40
+/* Handle to the port to set link state for. */
+#define       MC_CMD_LINK_CTRL_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_LINK_CTRL_IN_PORT_HANDLE_LEN 4
+/* Control flags */
+#define       MC_CMD_LINK_CTRL_IN_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_LINK_CTRL_IN_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Reserved for future expansion, and included to provide padding for alignment
+ * purposes.
+ */
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_OFST 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LEN 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_OFST 8
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_LEN 4
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_LBN 64
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_LO_WIDTH 32
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_OFST 12
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_LEN 4
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_LBN 96
+#define       MC_CMD_LINK_CTRL_IN_RESERVED_HI_WIDTH 32
+/* Technology abilities to advertise during auto-negotiation */
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_TECH_ABILITIES_MASK_OFST 16
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_TECH_ABILITIES_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Pause abilities to advertise during auto-negotiation. Valid when auto-
+ * negotation is enabled and MC_CMD_SET_MAC_IN/FCTL is set to
+ * MC_CMD_FCNTL_AUTO. If auto-negotiation is disabled the driver must
+ * explicitly configure pause mode with MC_CMD_SET_MAC.
+ */
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_PAUSE_ABILITIES_MASK_OFST 32
+#define       MC_CMD_LINK_CTRL_IN_ADVERTISED_PAUSE_ABILITIES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* When auto-negotiation is enabled, this is the FEC mode to request. Note that
+ * a weaker FEC mode may get negotiated, depending on what the link partner
+ * supports. The driver should subsequently use MC_CMD_GET_LINK to check the
+ * actual negotiated FEC mode. When auto-negotiation is disabled, this is the
+ * forced FEC mode.
+ */
+#define       MC_CMD_LINK_CTRL_IN_FEC_MODE_OFST 33
+#define       MC_CMD_LINK_CTRL_IN_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* This is only to be used when auto-negotiation is disabled (forced speed or
+ * loopback mode). If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_CTRL_IN_LINK_TECHNOLOGY_OFST 36
+#define       MC_CMD_LINK_CTRL_IN_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* The sequence number of the last MODULECHANGE event. If this doesn't match,
+ * fail with EAGAIN.
+ */
+#define       MC_CMD_LINK_CTRL_IN_MODULE_SEQ_OFST 38
+#define       MC_CMD_LINK_CTRL_IN_MODULE_SEQ_LEN 1
+/* Loopback Mode. Only valid when auto-negotiation is disabled. */
+#define       MC_CMD_LINK_CTRL_IN_LOOPBACK_OFST 39
+#define       MC_CMD_LINK_CTRL_IN_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+
+/* MC_CMD_LINK_CTRL_OUT msgresponse */
+#define    MC_CMD_LINK_CTRL_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_LINK_STATE
+ */
+#define MC_CMD_LINK_STATE 0x6c
+#undef MC_CMD_0x6c_PRIVILEGE_CTG
+
+#define MC_CMD_0x6c_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_LINK_STATE_IN msgrequest */
+#define    MC_CMD_LINK_STATE_IN_LEN 4
+/* Handle to the port to get link state for. */
+#define       MC_CMD_LINK_STATE_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_LINK_STATE_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_LINK_STATE_OUT msgresponse */
+#define    MC_CMD_LINK_STATE_OUT_LEN 114
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_LEN 32
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_TECH_MASK_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_MASK_OFST 32
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_REQ_OFST 36
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_PAUSE_MASK_OFST 40
+#define       MC_CMD_LINK_STATE_OUT_ADVERTISED_ABILITIES_PAUSE_MASK_LEN 1
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_LEN 32
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_TECH_MASK_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_MASK_OFST 64
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_REQ_OFST 68
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_PAUSE_MASK_OFST 72
+#define       MC_CMD_LINK_STATE_OUT_LINK_PARTNER_ABILITIES_PAUSE_MASK_LEN 1
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_LEN 28
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_TECH_MASK_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_MASK_OFST 96
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_REQ_OFST 100
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_PAUSE_MASK_OFST 104
+#define       MC_CMD_LINK_STATE_OUT_SUPPORTED_ABILITIES_PAUSE_MASK_LEN 1
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+
+/* MC_CMD_LINK_STATE_OUT_V2 msgresponse: Updated LINK_STATE_OUT with
+ * LOCAL_AN_SUPPORT
+ */
+#define    MC_CMD_LINK_STATE_OUT_V2_LEN 120
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_V2_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_V2_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_V2_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_V2_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_V2_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_V2_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_V2_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V2_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_V2_ADVERTISED_ABILITIES_LEN 32
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_V2_LINK_PARTNER_ABILITIES_LEN 32
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_V2_SUPPORTED_ABILITIES_LEN 28
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_V2_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_V2_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_V2_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+/* Reports the auto-negotiation supported by the local device. This depends on
+ * the port and module properties.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V2_LOCAL_AN_SUPPORT_OFST 116
+#define       MC_CMD_LINK_STATE_OUT_V2_LOCAL_AN_SUPPORT_LEN 4
+/*            Enum values, see field(s): */
+/*               AN_TYPE/TYPE */
+
+/* MC_CMD_LINK_STATE_OUT_V3 msgresponse: Updated LINK_STATE_OUT_V2 for explicit
+ * reporting of the link speed and duplex mode.
+ */
+#define    MC_CMD_LINK_STATE_OUT_V3_LEN 128
+/* Flags used to report the current configuration/state of the link. */
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LEN 8
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_OFST 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_LBN 0
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_LO_WIDTH 32
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_OFST 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_LBN 32
+#define       MC_CMD_LINK_STATE_OUT_V3_STATUS_FLAGS_HI_WIDTH 32
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_STATUS_FLAGS/STATUS_FLAGS */
+/* Configured technology. If the specified value does not align with the values
+ * defined in the enum MC_CMD_ETH_TECH/TECH, it is considered invalid.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_TECHNOLOGY_OFST 8
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_TECHNOLOGY_LEN 2
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Configured FEC mode */
+#define       MC_CMD_LINK_STATE_OUT_V3_FEC_MODE_OFST 10
+#define       MC_CMD_LINK_STATE_OUT_V3_FEC_MODE_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* Bitmask of auto-negotiated pause modes */
+#define       MC_CMD_LINK_STATE_OUT_V3_PAUSE_MASK_OFST 11
+#define       MC_CMD_LINK_STATE_OUT_V3_PAUSE_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_PAUSE_MODE/TYPE */
+/* Configured loopback mode */
+#define       MC_CMD_LINK_STATE_OUT_V3_LOOPBACK_OFST 12
+#define       MC_CMD_LINK_STATE_OUT_V3_LOOPBACK_LEN 1
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* Abilities requested by the driver to advertise during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V3_ADVERTISED_ABILITIES_OFST 16
+#define       MC_CMD_LINK_STATE_OUT_V3_ADVERTISED_ABILITIES_LEN 32
+/* Abilities advertised by the link partner during auto-negotiation */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_PARTNER_ABILITIES_OFST 48
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_PARTNER_ABILITIES_LEN 32
+/* Abilities supported by the local device (including cable abilities) For
+ * fixed local device capbilities see MC_CMD_GET_LOCAL_DEVICE_INFO
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_SUPPORTED_ABILITIES_OFST 80
+#define       MC_CMD_LINK_STATE_OUT_V3_SUPPORTED_ABILITIES_LEN 28
+/* Control flags */
+#define       MC_CMD_LINK_STATE_OUT_V3_CONTROL_FLAGS_OFST 108
+#define       MC_CMD_LINK_STATE_OUT_V3_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LINK_FLAGS/MASK */
+/* Sequence number to synchronize link change events */
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_LINKCHANGE_SEQ_NUM_OFST 112
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_LINKCHANGE_SEQ_NUM_LEN 1
+/* Sequence number to synchronize module change events */
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_MODULECHANGE_SEQ_NUM_OFST 113
+#define       MC_CMD_LINK_STATE_OUT_V3_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+/* Reports the auto-negotiation supported by the local device. This depends on
+ * the port and module properties.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LOCAL_AN_SUPPORT_OFST 116
+#define       MC_CMD_LINK_STATE_OUT_V3_LOCAL_AN_SUPPORT_LEN 4
+/*            Enum values, see field(s): */
+/*               AN_TYPE/TYPE */
+/* Autonegotiated speed in mbit/s. The link may still be down even if this
+ * reads non-zero. LINK_SPEED field is intended to be used by drivers without
+ * the most up-to-date MCDI definitions, unable to deduce the link speed from
+ * the reported LINK_TECHNOLOGY field.
+ */
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_SPEED_OFST 120
+#define       MC_CMD_LINK_STATE_OUT_V3_LINK_SPEED_LEN 4
+#define       MC_CMD_LINK_STATE_OUT_V3_FLAGS_OFST 124
+#define       MC_CMD_LINK_STATE_OUT_V3_FLAGS_LEN 4
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_OFST 124
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_LBN 0
+#define        MC_CMD_LINK_STATE_OUT_V3_FULL_DUPLEX_WIDTH 1
+
+
+/***********************************/
+/* MC_CMD_GET_LINK
+ * Read the unified MAC/PHY link state. Locks required: None Return code: 0,
+ * ETIME.
+ */
+#define MC_CMD_GET_LINK 0x29
+#undef MC_CMD_0x29_PRIVILEGE_CTG
+
+#define MC_CMD_0x29_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_LINK_IN msgrequest */
+#define    MC_CMD_GET_LINK_IN_LEN 0
+
+/* MC_CMD_GET_LINK_IN_V2 msgrequest */
+#define    MC_CMD_GET_LINK_IN_V2_LEN 8
+/* Target port to request link state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details.
+ */
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_LINK_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
+/* MC_CMD_GET_LINK_OUT msgresponse */
+#define    MC_CMD_GET_LINK_OUT_LEN 28
 /* Near-side advertised capabilities. Refer to
  * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
  */
-#define       MC_CMD_GET_LINK_OUT_V2_CAP_OFST 0
-#define       MC_CMD_GET_LINK_OUT_V2_CAP_LEN 4
+#define       MC_CMD_GET_LINK_OUT_CAP_OFST 0
+#define       MC_CMD_GET_LINK_OUT_CAP_LEN 4
 /* Link-partner advertised capabilities. Refer to
  * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
  */
-#define       MC_CMD_GET_LINK_OUT_V2_LP_CAP_OFST 4
-#define       MC_CMD_GET_LINK_OUT_V2_LP_CAP_LEN 4
+#define       MC_CMD_GET_LINK_OUT_LP_CAP_OFST 4
+#define       MC_CMD_GET_LINK_OUT_LP_CAP_LEN 4
 /* Autonegotiated speed in mbit/s. The link may still be down even if this
  * reads non-zero.
  */
-#define       MC_CMD_GET_LINK_OUT_V2_LINK_SPEED_OFST 8
-#define       MC_CMD_GET_LINK_OUT_V2_LINK_SPEED_LEN 4
+#define       MC_CMD_GET_LINK_OUT_LINK_SPEED_OFST 8
+#define       MC_CMD_GET_LINK_OUT_LINK_SPEED_LEN 4
 /* Current loopback setting. */
-#define       MC_CMD_GET_LINK_OUT_V2_LOOPBACK_MODE_OFST 12
-#define       MC_CMD_GET_LINK_OUT_V2_LOOPBACK_MODE_LEN 4
+#define       MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_OFST 12
+#define       MC_CMD_GET_LINK_OUT_LOOPBACK_MODE_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
+#define       MC_CMD_GET_LINK_OUT_FLAGS_OFST 16
+#define       MC_CMD_GET_LINK_OUT_FLAGS_LEN 4
+#define        MC_CMD_GET_LINK_OUT_LINK_UP_OFST 16
+#define        MC_CMD_GET_LINK_OUT_LINK_UP_LBN 0
+#define        MC_CMD_GET_LINK_OUT_LINK_UP_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_OFST 16
+#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_LBN 1
+#define        MC_CMD_GET_LINK_OUT_FULL_DUPLEX_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_BPX_LINK_OFST 16
+#define        MC_CMD_GET_LINK_OUT_BPX_LINK_LBN 2
+#define        MC_CMD_GET_LINK_OUT_BPX_LINK_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_PHY_LINK_OFST 16
+#define        MC_CMD_GET_LINK_OUT_PHY_LINK_LBN 3
+#define        MC_CMD_GET_LINK_OUT_PHY_LINK_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_OFST 16
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_LBN 6
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_OFST 16
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_LBN 7
+#define        MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_OFST 16
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_LBN 8
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_VALID_WIDTH 1
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_OFST 16
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_LBN 9
+#define        MC_CMD_GET_LINK_OUT_MODULE_UP_WIDTH 1
+/* This returns the negotiated flow control value. */
+#define       MC_CMD_GET_LINK_OUT_FCNTL_OFST 20
+#define       MC_CMD_GET_LINK_OUT_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */
+#define       MC_CMD_GET_LINK_OUT_MAC_FAULT_OFST 24
+#define       MC_CMD_GET_LINK_OUT_MAC_FAULT_LEN 4
+#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_OFST 24
+#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_LBN 0
+#define        MC_CMD_MAC_FAULT_XGMII_LOCAL_WIDTH 1
+#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_OFST 24
+#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_LBN 1
+#define        MC_CMD_MAC_FAULT_XGMII_REMOTE_WIDTH 1
+#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_OFST 24
+#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_LBN 2
+#define        MC_CMD_MAC_FAULT_SGMII_REMOTE_WIDTH 1
+#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_OFST 24
+#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_LBN 3
+#define        MC_CMD_MAC_FAULT_PENDING_RECONFIG_WIDTH 1
+
+/* MC_CMD_GET_LINK_OUT_V2 msgresponse: Extended link state information */
+#define    MC_CMD_GET_LINK_OUT_V2_LEN 44
+/* Near-side advertised capabilities. Refer to
+ * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
+ */
+#define       MC_CMD_GET_LINK_OUT_V2_CAP_OFST 0
+#define       MC_CMD_GET_LINK_OUT_V2_CAP_LEN 4
+/* Link-partner advertised capabilities. Refer to
+ * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
+ */
+#define       MC_CMD_GET_LINK_OUT_V2_LP_CAP_OFST 4
+#define       MC_CMD_GET_LINK_OUT_V2_LP_CAP_LEN 4
+/* Autonegotiated speed in mbit/s. The link may still be down even if this
+ * reads non-zero.
+ */
+#define       MC_CMD_GET_LINK_OUT_V2_LINK_SPEED_OFST 8
+#define       MC_CMD_GET_LINK_OUT_V2_LINK_SPEED_LEN 4
+/* Current loopback setting. */
+#define       MC_CMD_GET_LINK_OUT_V2_LOOPBACK_MODE_OFST 12
+#define       MC_CMD_GET_LINK_OUT_V2_LOOPBACK_MODE_LEN 4
 /*            Enum values, see field(s): */
 /*               MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
 #define       MC_CMD_GET_LINK_OUT_V2_FLAGS_OFST 16
@@ -5813,6 +6232,7 @@
 /* This returns the negotiated flow control value. */
 #define       MC_CMD_GET_LINK_OUT_V2_FCNTL_OFST 20
 #define       MC_CMD_GET_LINK_OUT_V2_FCNTL_LEN 4
+/* enum property: value */
 /*            Enum values, see field(s): */
 /*               MC_CMD_SET_MAC/MC_CMD_SET_MAC_IN/FCNTL */
 #define       MC_CMD_GET_LINK_OUT_V2_MAC_FAULT_OFST 24
@@ -5969,6 +6389,95 @@
 #define        MC_CMD_SET_LINK_IN_V2_MODULE_SEQ_IGNORE_LBN 7
 #define        MC_CMD_SET_LINK_IN_V2_MODULE_SEQ_IGNORE_WIDTH 1
 
+/* MC_CMD_SET_LINK_IN_V3 msgrequest */
+#define    MC_CMD_SET_LINK_IN_V3_LEN 28
+/* Near-side advertised capabilities. Refer to
+ * MC_CMD_GET_PHY_CFG_OUT/SUPPORTED_CAP for bit definitions.
+ */
+#define       MC_CMD_SET_LINK_IN_V3_CAP_OFST 0
+#define       MC_CMD_SET_LINK_IN_V3_CAP_LEN 4
+/* Flags */
+#define       MC_CMD_SET_LINK_IN_V3_FLAGS_OFST 4
+#define       MC_CMD_SET_LINK_IN_V3_FLAGS_LEN 4
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_LBN 0
+#define        MC_CMD_SET_LINK_IN_V3_LOWPOWER_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_LBN 1
+#define        MC_CMD_SET_LINK_IN_V3_POWEROFF_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_LBN 2
+#define        MC_CMD_SET_LINK_IN_V3_TXDIS_WIDTH 1
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_OFST 4
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_LBN 3
+#define        MC_CMD_SET_LINK_IN_V3_LINKDOWN_WIDTH 1
+/* Loopback mode. */
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_MODE_OFST 8
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_MODE_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_GET_LOOPBACK_MODES/MC_CMD_GET_LOOPBACK_MODES_OUT/100M */
+/* A loopback speed of "0" is supported, and means (choose any available
+ * speed).
+ */
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_SPEED_OFST 12
+#define       MC_CMD_SET_LINK_IN_V3_LOOPBACK_SPEED_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_OFST 16
+#define       MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_LEN 1
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_OFST 16
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_LBN 0
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_NUMBER_WIDTH 7
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_OFST 16
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_LBN 7
+#define        MC_CMD_SET_LINK_IN_V3_MODULE_SEQ_IGNORE_WIDTH 1
+/* Padding */
+#define       MC_CMD_SET_LINK_IN_V3_RESERVED_OFST 17
+#define       MC_CMD_SET_LINK_IN_V3_RESERVED_LEN 3
+/* Target port to set link state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LEN 8
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LO_WIDTH 32
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_LBN 192
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FLAT_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_TYPE_OFST 23
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 180
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 176
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 22
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LINK_END_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_LINK_END_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LEN 8
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_OFST 20
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_LBN 160
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_OFST 24
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_LBN 192
+#define       MC_CMD_SET_LINK_IN_V3_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_SET_LINK_OUT msgresponse */
 #define    MC_CMD_SET_LINK_OUT_LEN 0
 
@@ -6034,17 +6543,17 @@
 #define       MC_CMD_SET_MAC_IN_FCNTL_OFST 20
 #define       MC_CMD_SET_MAC_IN_FCNTL_LEN 4
 /* enum: Flow control is off. */
-#define          MC_CMD_FCNTL_OFF 0x0
+/*               MC_CMD_FCNTL_OFF 0x0 */
 /* enum: Respond to flow control. */
-#define          MC_CMD_FCNTL_RESPOND 0x1
+/*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
-#define          MC_CMD_FCNTL_BIDIR 0x2
-/* enum: Auto neg flow control. */
-#define          MC_CMD_FCNTL_AUTO 0x3
-/* enum: Priority flow control (eftest builds only). */
-#define          MC_CMD_FCNTL_QBB 0x4
+/*               MC_CMD_FCNTL_BIDIR 0x2 */
+/* enum: Auto negotiate flow control. */
+/*               MC_CMD_FCNTL_AUTO 0x3 */
+/* enum: Priority flow control. This is only supported on KSB. */
+/*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
-#define          MC_CMD_FCNTL_GENERATE 0x5
+/*               MC_CMD_FCNTL_GENERATE 0x5 */
 #define       MC_CMD_SET_MAC_IN_FLAGS_OFST 24
 #define       MC_CMD_SET_MAC_IN_FLAGS_LEN 4
 #define        MC_CMD_SET_MAC_IN_FLAG_INCLUDE_FCS_OFST 24
@@ -6086,9 +6595,9 @@
 /*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
 /*               MC_CMD_FCNTL_BIDIR 0x2 */
-/* enum: Auto neg flow control. */
+/* enum: Auto negotiate flow control. */
 /*               MC_CMD_FCNTL_AUTO 0x3 */
-/* enum: Priority flow control (eftest builds only). */
+/* enum: Priority flow control. This is only supported on KSB. */
 /*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
 /*               MC_CMD_FCNTL_GENERATE 0x5 */
@@ -6155,9 +6664,9 @@
 /*               MC_CMD_FCNTL_RESPOND 0x1 */
 /* enum: Respond to and Issue flow control. */
 /*               MC_CMD_FCNTL_BIDIR 0x2 */
-/* enum: Auto neg flow control. */
+/* enum: Auto negotiate flow control. */
 /*               MC_CMD_FCNTL_AUTO 0x3 */
-/* enum: Priority flow control (eftest builds only). */
+/* enum: Priority flow control. This is only supported on KSB. */
 /*               MC_CMD_FCNTL_QBB 0x4 */
 /* enum: Issue flow control. */
 /*               MC_CMD_FCNTL_GENERATE 0x5 */
@@ -6188,19 +6697,9 @@
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_OFST 28
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_LBN 4
 #define        MC_CMD_SET_MAC_V3_IN_CFG_FCS_WIDTH 1
-/* Identifies the MAC to update by the specifying the end of a logical MAE
- * link. Setting TARGET to MAE_LINK_ENDPOINT_COMPAT is equivalent to using the
- * previous version of the command (MC_CMD_SET_MAC_EXT). Not all possible
- * combinations of MPORT_END and MPORT_SELECTOR in TARGET will work in all
- * circumstances. 1. Some will always work (e.g. a VF can always address its
- * logical MAC using MPORT_SELECTOR=ASSIGNED,LINK_END=VNIC), 2. Some are not
- * meaningful and will always fail with EINVAL (e.g. attempting to address the
- * VNIC end of a link to a physical port), 3. Some are meaningful but require
- * the MCDI client to have the required permission and fail with EPERM
- * otherwise (e.g. trying to set the MAC on a VF the caller cannot administer),
- * and 4. Some could be implementation-specific and fail with ENOTSUP if not
- * available (no examples exist right now). See SF-123581-TC section 4.3 for
- * more details.
+/* Target port to set mac state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
  */
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_OFST 32
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_LEN 8
@@ -6212,6 +6711,7 @@
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_LEN 4
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_LBN 288
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_OFST 32
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_LEN 4
 #define       MC_CMD_SET_MAC_V3_IN_TARGET_MPORT_SELECTOR_FLAT_OFST 32
@@ -6405,6 +6905,98 @@
 #define       MC_CMD_MAC_STATS_IN_PORT_ID_OFST 16
 #define       MC_CMD_MAC_STATS_IN_PORT_ID_LEN 4
 
+/* MC_CMD_MAC_STATS_V2_IN msgrequest */
+#define    MC_CMD_MAC_STATS_V2_IN_LEN 28
+/* ??? */
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_OFST 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_OFST 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_LBN 0
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_OFST 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_LBN 32
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_ADDR_HI_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_CMD_OFST 8
+#define       MC_CMD_MAC_STATS_V2_IN_CMD_LEN 4
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_LBN 0
+#define        MC_CMD_MAC_STATS_V2_IN_DMA_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_LBN 1
+#define        MC_CMD_MAC_STATS_V2_IN_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_LBN 4
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_LBN 5
+#define        MC_CMD_MAC_STATS_V2_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_OFST 8
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_LBN 16
+#define        MC_CMD_MAC_STATS_V2_IN_PERIOD_MS_WIDTH 16
+/* DMA length. Should be set to MAC_STATS_NUM_STATS * sizeof(uint64_t), as
+ * returned by MC_CMD_GET_CAPABILITIES_V4_OUT. For legacy firmware not
+ * supporting MC_CMD_GET_CAPABILITIES_V4_OUT, DMA_LEN should be set to
+ * MC_CMD_MAC_NSTATS * sizeof(uint64_t)
+ */
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_LEN_OFST 12
+#define       MC_CMD_MAC_STATS_V2_IN_DMA_LEN_LEN 4
+/* port id so vadapter stats can be provided */
+#define       MC_CMD_MAC_STATS_V2_IN_PORT_ID_OFST 16
+#define       MC_CMD_MAC_STATS_V2_IN_PORT_ID_LEN 4
+/* Target port to request statistics for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_LBN 192
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FLAT_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_TYPE_OFST 23
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 180
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 176
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 22
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LINK_END_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_LINK_END_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LEN 8
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_OFST 20
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_LBN 160
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_OFST 24
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_LBN 192
+#define       MC_CMD_MAC_STATS_V2_IN_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_MAC_STATS_OUT_DMA msgresponse */
 #define    MC_CMD_MAC_STATS_OUT_DMA_LEN 0
 
@@ -6421,6 +7013,7 @@
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS
+/* enum property: index */
 #define          MC_CMD_MAC_GENERATION_START 0x0 /* enum */
 #define          MC_CMD_MAC_DMABUF_START 0x1 /* enum */
 #define          MC_CMD_MAC_TX_PKTS 0x1 /* enum */
@@ -6583,6 +7176,7 @@
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V2_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V2
+/* enum property: index */
 /* enum: Start of FEC stats buffer space, Medford2 and up */
 #define          MC_CMD_MAC_FEC_DMABUF_START 0x61
 /* enum: Number of uncorrected FEC codewords on link (RS-FEC only for Medford2)
@@ -6622,6 +7216,7 @@
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V3_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V3
+/* enum property: index */
 /* enum: Start of CTPIO stats buffer space, Medford2 and up */
 #define          MC_CMD_MAC_CTPIO_DMABUF_START 0x68
 /* enum: Number of CTPIO fallbacks because a DMA packet was in progress on the
@@ -6702,6 +7297,7 @@
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_HI_LBN 32
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
 #define       MC_CMD_MAC_STATS_V4_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V4
+/* enum property: index */
 /* enum: Start of V4 stats buffer space */
 #define          MC_CMD_MAC_V4_DMABUF_START 0x79
 /* enum: RXDP counter: Number of packets truncated because scattering was
@@ -6723,112 +7319,35 @@
 /*            Other enum values, see field(s): */
 /*               MC_CMD_MAC_STATS_V3_OUT_NO_DMA/STATISTICS */
 
-
-/***********************************/
-/* MC_CMD_SRIOV
- * to be documented
- */
-#define MC_CMD_SRIOV 0x30
-
-/* MC_CMD_SRIOV_IN msgrequest */
-#define    MC_CMD_SRIOV_IN_LEN 12
-#define       MC_CMD_SRIOV_IN_ENABLE_OFST 0
-#define       MC_CMD_SRIOV_IN_ENABLE_LEN 4
-#define       MC_CMD_SRIOV_IN_VI_BASE_OFST 4
-#define       MC_CMD_SRIOV_IN_VI_BASE_LEN 4
-#define       MC_CMD_SRIOV_IN_VF_COUNT_OFST 8
-#define       MC_CMD_SRIOV_IN_VF_COUNT_LEN 4
-
-/* MC_CMD_SRIOV_OUT msgresponse */
-#define    MC_CMD_SRIOV_OUT_LEN 8
-#define       MC_CMD_SRIOV_OUT_VI_SCALE_OFST 0
-#define       MC_CMD_SRIOV_OUT_VI_SCALE_LEN 4
-#define       MC_CMD_SRIOV_OUT_VF_TOTAL_OFST 4
-#define       MC_CMD_SRIOV_OUT_VF_TOTAL_LEN 4
-
-/* MC_CMD_MEMCPY_RECORD_TYPEDEF structuredef */
-#define    MC_CMD_MEMCPY_RECORD_TYPEDEF_LEN 32
-/* this is only used for the first record */
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_OFST 0
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_LBN 0
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_NUM_RECORDS_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_OFST 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_LBN 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_RID_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_OFST 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LEN 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_OFST 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_LBN 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LO_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_OFST 12
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_LBN 96
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_HI_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_LBN 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_TO_ADDR_WIDTH 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_OFST 16
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_LEN 4
-#define          MC_CMD_MEMCPY_RECORD_TYPEDEF_RID_INLINE 0x100 /* enum */
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_LBN 128
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_RID_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_OFST 20
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LEN 8
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_OFST 20
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_LBN 160
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LO_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_OFST 24
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_LBN 192
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_HI_WIDTH 32
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_LBN 160
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_FROM_ADDR_WIDTH 64
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_OFST 28
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_LEN 4
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_LBN 224
-#define       MC_CMD_MEMCPY_RECORD_TYPEDEF_LENGTH_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_MEMCPY
- * DMA write data into (Rid,Addr), either by dma reading (Rid,Addr), or by data
- * embedded directly in the command.
- *
- * A common pattern is for a client to use generation counts to signal a dma
- * update of a datastructure. To facilitate this, this MCDI operation can
- * contain multiple requests which are executed in strict order. Requests take
- * the form of duplicating the entire MCDI request continuously (including the
- * requests record, which is ignored in all but the first structure)
- *
- * The source data can either come from a DMA from the host, or it can be
- * embedded within the request directly, thereby eliminating a DMA read. To
- * indicate this, the client sets FROM_RID=%RID_INLINE, ADDR_HI=0, and
- * ADDR_LO=offset, and inserts the data at %offset from the start of the
- * payload. It's the callers responsibility to ensure that the embedded data
- * doesn't overlap the records.
- *
- * Returns: 0, EINVAL (invalid RID)
- */
-#define MC_CMD_MEMCPY 0x31
-
-/* MC_CMD_MEMCPY_IN msgrequest */
-#define    MC_CMD_MEMCPY_IN_LENMIN 32
-#define    MC_CMD_MEMCPY_IN_LENMAX 224
-#define    MC_CMD_MEMCPY_IN_LENMAX_MCDI2 992
-#define    MC_CMD_MEMCPY_IN_LEN(num) (0+32*(num))
-#define    MC_CMD_MEMCPY_IN_RECORD_NUM(len) (((len)-0)/32)
-/* see MC_CMD_MEMCPY_RECORD_TYPEDEF */
-#define       MC_CMD_MEMCPY_IN_RECORD_OFST 0
-#define       MC_CMD_MEMCPY_IN_RECORD_LEN 32
-#define       MC_CMD_MEMCPY_IN_RECORD_MINNUM 1
-#define       MC_CMD_MEMCPY_IN_RECORD_MAXNUM 7
-#define       MC_CMD_MEMCPY_IN_RECORD_MAXNUM_MCDI2 31
-
-/* MC_CMD_MEMCPY_OUT msgresponse */
-#define    MC_CMD_MEMCPY_OUT_LEN 0
+/* MC_CMD_MAC_STATS_V5_OUT_DMA msgresponse */
+#define    MC_CMD_MAC_STATS_V5_OUT_DMA_LEN 0
+
+/* MC_CMD_MAC_STATS_V5_OUT_NO_DMA msgresponse */
+#define    MC_CMD_MAC_STATS_V5_OUT_NO_DMA_LEN (((MC_CMD_MAC_NSTATS_V5*64))>>3)
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_OFST 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LEN 8
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_OFST 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_LEN 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_LBN 0
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_LO_WIDTH 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_OFST 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_LEN 4
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_LBN 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_HI_WIDTH 32
+#define       MC_CMD_MAC_STATS_V5_OUT_NO_DMA_STATISTICS_NUM MC_CMD_MAC_NSTATS_V5
+/* enum property: index */
+/* enum: Start of V5 stats buffer space */
+#define          MC_CMD_MAC_V5_DMABUF_START 0x7c
+/* enum: Link toggle counter: Number of times the link has toggled between
+ * up/down and down/up
+ */
+#define          MC_CMD_MAC_LINK_TOGGLES 0x7c
+/* enum: This includes the space at offset 125 which is the final
+ * GENERATION_END in a MAC_STATS_V5 response and otherwise unused.
+ */
+#define          MC_CMD_MAC_NSTATS_V5 0x7e
+/*            Other enum values, see field(s): */
+/*               MC_CMD_MAC_STATS_V4_OUT_NO_DMA/STATISTICS */
 
 
 /***********************************/
@@ -6984,6 +7503,7 @@
 #define    MC_CMD_WOL_FILTER_RESET_IN_LEN 4
 #define       MC_CMD_WOL_FILTER_RESET_IN_MASK_OFST 0
 #define       MC_CMD_WOL_FILTER_RESET_IN_MASK_LEN 4
+/* enum property: bitmask */
 #define          MC_CMD_WOL_FILTER_RESET_IN_WAKE_FILTERS 0x1 /* enum */
 #define          MC_CMD_WOL_FILTER_RESET_IN_LIGHTSOUT_OFFLOADS 0x2 /* enum */
 
@@ -6991,23 +7511,6 @@
 #define    MC_CMD_WOL_FILTER_RESET_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_SET_MCAST_HASH
- * Set the MCAST hash value without otherwise reconfiguring the MAC
- */
-#define MC_CMD_SET_MCAST_HASH 0x35
-
-/* MC_CMD_SET_MCAST_HASH_IN msgrequest */
-#define    MC_CMD_SET_MCAST_HASH_IN_LEN 32
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH0_OFST 0
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH0_LEN 16
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH1_OFST 16
-#define       MC_CMD_SET_MCAST_HASH_IN_HASH1_LEN 16
-
-/* MC_CMD_SET_MCAST_HASH_OUT msgresponse */
-#define    MC_CMD_SET_MCAST_HASH_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_NVRAM_TYPES
  * Return bitfield indicating available types of virtual NVRAM partitions.
@@ -7026,6 +7529,7 @@
 /* Bit mask of supported types. */
 #define       MC_CMD_NVRAM_TYPES_OUT_TYPES_OFST 0
 #define       MC_CMD_NVRAM_TYPES_OUT_TYPES_LEN 4
+/* enum property: bitshift */
 /* enum: Disabled callisto. */
 #define          MC_CMD_NVRAM_TYPE_DISABLED_CALLISTO 0x0
 /* enum: MC firmware. */
@@ -7152,6 +7656,12 @@
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_OFST 12
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_LBN 7
 #define        MC_CMD_NVRAM_INFO_V2_OUT_A_B_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_LBN 8
+#define        MC_CMD_NVRAM_INFO_V2_OUT_WRITE_ONLY_WIDTH 1
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_OFST 12
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_LBN 9
+#define        MC_CMD_NVRAM_INFO_V2_OUT_SEQUENTIAL_WRITE_WIDTH 1
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_OFST 16
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSDEV_LEN 4
 #define       MC_CMD_NVRAM_INFO_V2_OUT_PHYSADDR_OFST 20
@@ -7499,6 +8009,128 @@
 #define          MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_COPY_FAILED 0x19
 /* enum: The update operation is in-progress. */
 #define          MC_CMD_NVRAM_VERIFY_RC_PENDING 0x1a
+/* enum: The update was an invalid user configuration file. */
+#define          MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG 0x1b
+/* enum: The write was to the AUTO partition but the data was not recognised as
+ * a valid partition.
+ */
+#define          MC_CMD_NVRAM_VERIFY_RC_UNKNOWN_TYPE 0x1c
+
+/* MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT msgresponse */
+#define    MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_LEN 88
+/* Result of nvram update completion processing. Result codes that indicate an
+ * internal build failure and therefore not expected to be seen by customers in
+ * the field are marked with a prefix 'Internal-error'.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_RESULT_CODE_OFST 0
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_RESULT_CODE_LEN 4
+/* enum: Invalid return code; only non-zero values are defined. Defined as
+ * unknown for backwards compatibility with NVRAM_UPDATE_FINISH_OUT.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_UNKNOWN 0x0 */
+/* enum: Verify succeeded without any errors. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SUCCESS 0x1 */
+/* enum: CMS format verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_CMS_CHECK_FAILED 0x2 */
+/* enum: Invalid CMS format in image metadata. */
+/*               MC_CMD_NVRAM_VERIFY_RC_INVALID_CMS_FORMAT 0x3 */
+/* enum: Message digest verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_MESSAGE_DIGEST_CHECK_FAILED 0x4 */
+/* enum: Error in message digest calculated over the reflash-header, payload
+ * and reflash-trailer.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BAD_MESSAGE_DIGEST 0x5 */
+/* enum: Signature verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHECK_FAILED 0x6 */
+/* enum: There are no valid signatures in the image. */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_VALID_SIGNATURES 0x7 */
+/* enum: Trusted approvers verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_TRUSTED_APPROVERS_CHECK_FAILED 0x8 */
+/* enum: The Trusted approver's list is empty. */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_TRUSTED_APPROVERS 0x9 */
+/* enum: Signature chain verification failed due to an internal error. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SIGNATURE_CHAIN_CHECK_FAILED 0xa */
+/* enum: The signers of the signatures in the image are not listed in the
+ * Trusted approver's list.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_NO_SIGNATURE_MATCH 0xb */
+/* enum: The image contains a test-signed certificate, but the adapter accepts
+ * only production signed images.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_REJECT_TEST_SIGNED 0xc */
+/* enum: The image has a lower security level than the current firmware. */
+/*               MC_CMD_NVRAM_VERIFY_RC_SECURITY_LEVEL_DOWNGRADE 0xd */
+/* enum: Internal-error. The signed image is missing the 'contents' section,
+ * where the 'contents' section holds the actual image payload to be applied.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_CONTENT_NOT_FOUND 0xe */
+/* enum: Internal-error. The bundle header is invalid. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_CONTENT_HEADER_INVALID 0xf */
+/* enum: Internal-error. The bundle does not have a valid reflash image layout.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_REFLASH_IMAGE_INVALID 0x10 */
+/* enum: Internal-error. The bundle has an inconsistent layout of components or
+ * incorrect checksum.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_IMAGE_LAYOUT_INVALID 0x11 */
+/* enum: Internal-error. The bundle manifest is inconsistent with components in
+ * the bundle.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_INVALID 0x12 */
+/* enum: Internal-error. The number of components in a bundle do not match the
+ * number of components advertised by the bundle manifest.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_NUM_COMPONENTS_MISMATCH 0x13 */
+/* enum: Internal-error. The bundle contains too many components for the MC
+ * firmware to process
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_TOO_MANY_COMPONENTS 0x14 */
+/* enum: Internal-error. The bundle manifest has an invalid/inconsistent
+ * component.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_INVALID 0x15 */
+/* enum: Internal-error. The hash of a component does not match the hash stored
+ * in the bundle manifest.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_HASH_MISMATCH 0x16 */
+/* enum: Internal-error. Component hash calculation failed. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_MANIFEST_COMPONENT_HASH_FAILED 0x17 */
+/* enum: Internal-error. The component does not have a valid reflash image
+ * layout.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_REFLASH_IMAGE_INVALID 0x18 */
+/* enum: The bundle processing code failed to copy a component to its target
+ * partition.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_BUNDLE_COMPONENT_COPY_FAILED 0x19 */
+/* enum: The update operation is in-progress. */
+/*               MC_CMD_NVRAM_VERIFY_RC_PENDING 0x1a */
+/* enum: The update was an invalid user configuration file. */
+/*               MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG 0x1b */
+/* enum: The write was to the AUTO partition but the data was not recognised as
+ * a valid partition.
+ */
+/*               MC_CMD_NVRAM_VERIFY_RC_UNKNOWN_TYPE 0x1c */
+/* If the update was a user configuration, what action(s) the user must take to
+ * apply the new configuration.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ACTIONS_REQUIRED_OFST 4
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ACTIONS_REQUIRED_LEN 4
+/* enum: No action required. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_NONE 0x0
+/* enum: The MC firmware must be rebooted (eg with MC_CMD_REBOOT). */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_FIRMWARE_REBOOT 0x1
+/* enum: The host must be rebooted. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_HOST_REBOOT 0x2
+/* enum: The firmware and host must be rebooted (in either order). */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_FIRMWARE_AND_HOST_REBOOT 0x3
+/* enum: The host must be fully powered off. */
+#define          MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_HOST_POWERCYCLE 0x4
+/* If the update failed with MC_CMD_NVRAM_VERIFY_RC_BAD_CONFIG, a null-
+ * terminated US-ASCII string suitable for showing to the user.
+ */
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ERROR_STRING_OFST 8
+#define       MC_CMD_NVRAM_UPDATE_FINISH_V3_OUT_ERROR_STRING_LEN 80
 
 
 /***********************************/
@@ -7522,7 +8154,7 @@
 #define MC_CMD_REBOOT 0x3d
 #undef MC_CMD_0x3d_PRIVILEGE_CTG
 
-#define MC_CMD_0x3d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x3d_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_REBOOT_IN msgrequest */
 #define    MC_CMD_REBOOT_IN_LEN 4
@@ -7534,65 +8166,6 @@
 #define    MC_CMD_REBOOT_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_SCHEDINFO
- * Request scheduler info. Locks required: NONE. Returns: An array of
- * (timeslice,maximum overrun), one for each thread, in ascending order of
- * thread address.
- */
-#define MC_CMD_SCHEDINFO 0x3e
-#undef MC_CMD_0x3e_PRIVILEGE_CTG
-
-#define MC_CMD_0x3e_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SCHEDINFO_IN msgrequest */
-#define    MC_CMD_SCHEDINFO_IN_LEN 0
-
-/* MC_CMD_SCHEDINFO_OUT msgresponse */
-#define    MC_CMD_SCHEDINFO_OUT_LENMIN 4
-#define    MC_CMD_SCHEDINFO_OUT_LENMAX 252
-#define    MC_CMD_SCHEDINFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_SCHEDINFO_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_SCHEDINFO_OUT_DATA_NUM(len) (((len)-0)/4)
-#define       MC_CMD_SCHEDINFO_OUT_DATA_OFST 0
-#define       MC_CMD_SCHEDINFO_OUT_DATA_LEN 4
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MINNUM 1
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MAXNUM 63
-#define       MC_CMD_SCHEDINFO_OUT_DATA_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_REBOOT_MODE
- * Set the mode for the next MC reboot. Locks required: NONE. Sets the reboot
- * mode to the specified value. Returns the old mode.
- */
-#define MC_CMD_REBOOT_MODE 0x3f
-#undef MC_CMD_0x3f_PRIVILEGE_CTG
-
-#define MC_CMD_0x3f_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_REBOOT_MODE_IN msgrequest */
-#define    MC_CMD_REBOOT_MODE_IN_LEN 4
-#define       MC_CMD_REBOOT_MODE_IN_VALUE_OFST 0
-#define       MC_CMD_REBOOT_MODE_IN_VALUE_LEN 4
-/* enum: Normal. */
-#define          MC_CMD_REBOOT_MODE_NORMAL 0x0
-/* enum: Power-on Reset. */
-#define          MC_CMD_REBOOT_MODE_POR 0x2
-/* enum: Snapper. */
-#define          MC_CMD_REBOOT_MODE_SNAPPER 0x3
-/* enum: snapper fake POR */
-#define          MC_CMD_REBOOT_MODE_SNAPPER_POR 0x4
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_OFST 0
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_LBN 7
-#define        MC_CMD_REBOOT_MODE_IN_FAKE_WIDTH 1
-
-/* MC_CMD_REBOOT_MODE_OUT msgresponse */
-#define    MC_CMD_REBOOT_MODE_OUT_LEN 4
-#define       MC_CMD_REBOOT_MODE_OUT_VALUE_OFST 0
-#define       MC_CMD_REBOOT_MODE_OUT_VALUE_LEN 4
-
-
 /***********************************/
 /* MC_CMD_SENSOR_INFO
  * Returns information about every available sensor.
@@ -8061,6 +8634,54 @@
 /* MC_CMD_GET_PHY_STATE_IN msgrequest */
 #define    MC_CMD_GET_PHY_STATE_IN_LEN 0
 
+/* MC_CMD_GET_PHY_STATE_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_STATE_IN_V2_LEN 8
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details.
+ */
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_LBN 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 3
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 20
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 16
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 2
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LINK_END_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_OFST 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_LBN 0
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_OFST 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_LBN 32
+#define       MC_CMD_GET_PHY_STATE_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_STATE_OUT msgresponse */
 #define    MC_CMD_GET_PHY_STATE_OUT_LEN 4
 #define       MC_CMD_GET_PHY_STATE_OUT_STATE_OFST 0
@@ -8071,22 +8692,6 @@
 #define          MC_CMD_PHY_STATE_ZOMBIE 0x2
 
 
-/***********************************/
-/* MC_CMD_SETUP_8021QBB
- * 802.1Qbb control. 8 Tx queues that map to priorities 0 - 7. Use all 1s to
- * disable 802.Qbb for a given priority.
- */
-#define MC_CMD_SETUP_8021QBB 0x44
-
-/* MC_CMD_SETUP_8021QBB_IN msgrequest */
-#define    MC_CMD_SETUP_8021QBB_IN_LEN 32
-#define       MC_CMD_SETUP_8021QBB_IN_TXQS_OFST 0
-#define       MC_CMD_SETUP_8021QBB_IN_TXQS_LEN 32
-
-/* MC_CMD_SETUP_8021QBB_OUT msgresponse */
-#define    MC_CMD_SETUP_8021QBB_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_WOL_FILTER_GET
  * Retrieve ID of any WoL filters. Locks required: None. Returns: 0, ENOSYS
@@ -8105,133 +8710,6 @@
 #define       MC_CMD_WOL_FILTER_GET_OUT_FILTER_ID_LEN 4
 
 
-/***********************************/
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD
- * Add a protocol offload to NIC for lights-out state. Locks required: None.
- * Returns: 0, ENOSYS
- */
-#define MC_CMD_ADD_LIGHTSOUT_OFFLOAD 0x46
-#undef MC_CMD_0x46_PRIVILEGE_CTG
-
-#define MC_CMD_0x46_PRIVILEGE_CTG SRIOV_CTG_LINK
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMIN 8
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX 252
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_NUM(len) (((len)-4)/4)
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4
-#define          MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_ARP 0x1 /* enum */
-#define          MC_CMD_LIGHTSOUT_OFFLOAD_PROTOCOL_NS 0x2 /* enum */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_LEN 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MINNUM 1
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MAXNUM 62
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_DATA_MAXNUM_MCDI2 254
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_LEN 14
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4 */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_MAC_LEN 6
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_IP_OFST 10
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_ARP_IP_LEN 4
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS msgrequest */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_LEN 42
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0 */
-/*            MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4 */
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_OFST 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_MAC_LEN 6
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_OFST 10
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_SNIPV6_LEN 16
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_OFST 26
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_IN_NS_IPV6_LEN 16
-
-/* MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT msgresponse */
-#define    MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_LEN 4
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_OFST 0
-#define       MC_CMD_ADD_LIGHTSOUT_OFFLOAD_OUT_FILTER_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD
- * Remove a protocol offload from NIC for lights-out state. Locks required:
- * None. Returns: 0, ENOSYS
- */
-#define MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD 0x47
-#undef MC_CMD_0x47_PRIVILEGE_CTG
-
-#define MC_CMD_0x47_PRIVILEGE_CTG SRIOV_CTG_LINK
-
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN msgrequest */
-#define    MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_LEN 8
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_OFST 0
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_PROTOCOL_LEN 4
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_OFST 4
-#define       MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_IN_FILTER_ID_LEN 4
-
-/* MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT msgresponse */
-#define    MC_CMD_REMOVE_LIGHTSOUT_OFFLOAD_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_MAC_RESET_RESTORE
- * Restore MAC after block reset. Locks required: None. Returns: 0.
- */
-#define MC_CMD_MAC_RESET_RESTORE 0x48
-
-/* MC_CMD_MAC_RESET_RESTORE_IN msgrequest */
-#define    MC_CMD_MAC_RESET_RESTORE_IN_LEN 0
-
-/* MC_CMD_MAC_RESET_RESTORE_OUT msgresponse */
-#define    MC_CMD_MAC_RESET_RESTORE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TESTASSERT
- * Deliberately trigger an assert-detonation in the firmware for testing
- * purposes (i.e. to allow tests that the driver copes gracefully). Locks
- * required: None Returns: 0
- */
-#define MC_CMD_TESTASSERT 0x49
-#undef MC_CMD_0x49_PRIVILEGE_CTG
-
-#define MC_CMD_0x49_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_TESTASSERT_IN msgrequest */
-#define    MC_CMD_TESTASSERT_IN_LEN 0
-
-/* MC_CMD_TESTASSERT_OUT msgresponse */
-#define    MC_CMD_TESTASSERT_OUT_LEN 0
-
-/* MC_CMD_TESTASSERT_V2_IN msgrequest */
-#define    MC_CMD_TESTASSERT_V2_IN_LEN 4
-/* How to provoke the assertion */
-#define       MC_CMD_TESTASSERT_V2_IN_TYPE_OFST 0
-#define       MC_CMD_TESTASSERT_V2_IN_TYPE_LEN 4
-/* enum: Assert using the FAIL_ASSERTION_WITH_USEFUL_VALUES macro. Unless
- * you're testing firmware, this is what you want.
- */
-#define          MC_CMD_TESTASSERT_V2_IN_FAIL_ASSERTION_WITH_USEFUL_VALUES 0x0
-/* enum: Assert using assert(0); */
-#define          MC_CMD_TESTASSERT_V2_IN_ASSERT_FALSE 0x1
-/* enum: Deliberately trigger a watchdog */
-#define          MC_CMD_TESTASSERT_V2_IN_WATCHDOG 0x2
-/* enum: Deliberately trigger a trap by loading from an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_LOAD_TRAP 0x3
-/* enum: Deliberately trigger a trap by storing to an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_STORE_TRAP 0x4
-/* enum: Jump to an invalid address */
-#define          MC_CMD_TESTASSERT_V2_IN_JUMP_TRAP 0x5
-
-/* MC_CMD_TESTASSERT_V2_OUT msgresponse */
-#define    MC_CMD_TESTASSERT_V2_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_WORKAROUND
  * Enable/Disable a given workaround. The mcfw will return EINVAL if it doesn't
@@ -8324,6 +8802,62 @@
 #define        MC_CMD_GET_PHY_MEDIA_INFO_IN_DSFP_BANK_LBN 16
 #define        MC_CMD_GET_PHY_MEDIA_INFO_IN_DSFP_BANK_WIDTH 16
 
+/* MC_CMD_GET_PHY_MEDIA_INFO_IN_V2 msgrequest */
+#define    MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_LEN 12
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_PAGE_OFST 0
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_PAGE_LEN 4
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_OFST 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_LBN 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_PAGE_WIDTH 16
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_OFST 0
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_LBN 16
+#define        MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_DSFP_BANK_WIDTH 16
+/* Target port to request PHY state for. Uses MAE_LINK_ENDPOINT_SELECTOR which
+ * identifies a real or virtual network port by MAE port and link end. See the
+ * structure definition for more details
+ */
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LEN 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_LBN 64
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_HI_WIDTH 32
+/* See structuredef: MAE_LINK_ENDPOINT_SELECTOR */
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FLAT_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FLAT_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_TYPE_OFST 7
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_TYPE_LEN 1
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_MPORT_ID_LEN 3
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_PPORT_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_LBN 52
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_INTF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_LBN 48
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_MH_PF_ID_WIDTH 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_OFST 6
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_PF_ID_LEN 1
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_MPORT_SELECTOR_FUNC_VF_ID_LEN 2
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LINK_END_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_LINK_END_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LEN 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_OFST 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_LBN 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_LO_WIDTH 32
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_OFST 8
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_LEN 4
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_LBN 64
+#define       MC_CMD_GET_PHY_MEDIA_INFO_IN_V2_TARGET_FLAT_HI_WIDTH 32
+
 /* MC_CMD_GET_PHY_MEDIA_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMIN 5
 #define    MC_CMD_GET_PHY_MEDIA_INFO_OUT_LENMAX 252
@@ -8348,7 +8882,7 @@
 #define MC_CMD_NVRAM_TEST 0x4c
 #undef MC_CMD_0x4c_PRIVILEGE_CTG
 
-#define MC_CMD_0x4c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0x4c_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_NVRAM_TEST_IN msgrequest */
 #define    MC_CMD_NVRAM_TEST_IN_LEN 4
@@ -8369,103 +8903,6 @@
 #define          MC_CMD_NVRAM_TEST_NOTSUPP 0x2
 
 
-/***********************************/
-/* MC_CMD_MRSFP_TWEAK
- * Read status and/or set parameters for the 'mrsfp' driver in mr_rusty builds.
- * I2C I/O expander bits are always read; if equaliser parameters are supplied,
- * they are configured first. Locks required: None. Return code: 0, EINVAL.
- */
-#define MC_CMD_MRSFP_TWEAK 0x4d
-
-/* MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG msgrequest */
-#define    MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_LEN 16
-/* 0-6 low->high de-emph. */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_LEVEL_OFST 0
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_LEVEL_LEN 4
-/* 0-8 low->high ref.V */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_DT_CFG_OFST 4
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_TXEQ_DT_CFG_LEN 4
-/* 0-8 0-8 low->high boost */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_BOOST_OFST 8
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_BOOST_LEN 4
-/* 0-8 low->high ref.V */
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_DT_CFG_OFST 12
-#define       MC_CMD_MRSFP_TWEAK_IN_EQ_CONFIG_RXEQ_DT_CFG_LEN 4
-
-/* MC_CMD_MRSFP_TWEAK_IN_READ_ONLY msgrequest */
-#define    MC_CMD_MRSFP_TWEAK_IN_READ_ONLY_LEN 0
-
-/* MC_CMD_MRSFP_TWEAK_OUT msgresponse */
-#define    MC_CMD_MRSFP_TWEAK_OUT_LEN 12
-/* input bits */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_OFST 0
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_INPUTS_LEN 4
-/* output bits */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_OFST 4
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_OUTPUTS_LEN 4
-/* direction */
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OFST 8
-#define       MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_LEN 4
-/* enum: Out. */
-#define          MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_OUT 0x0
-/* enum: In. */
-#define          MC_CMD_MRSFP_TWEAK_OUT_IOEXP_DIRECTION_IN 0x1
-
-
-/***********************************/
-/* MC_CMD_SENSOR_SET_LIMS
- * Adjusts the sensor limits. This is a warranty-voiding operation. Returns:
- * ENOENT if the sensor specified does not exist, EINVAL if the limits are out
- * of range.
- */
-#define MC_CMD_SENSOR_SET_LIMS 0x4e
-#undef MC_CMD_0x4e_PRIVILEGE_CTG
-
-#define MC_CMD_0x4e_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SENSOR_SET_LIMS_IN msgrequest */
-#define    MC_CMD_SENSOR_SET_LIMS_IN_LEN 20
-#define       MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_OFST 0
-#define       MC_CMD_SENSOR_SET_LIMS_IN_SENSOR_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_SENSOR_INFO/MC_CMD_SENSOR_INFO_OUT/MASK */
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW0_OFST 4
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW0_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI0_OFST 8
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI0_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW1_OFST 12
-#define       MC_CMD_SENSOR_SET_LIMS_IN_LOW1_LEN 4
-/* interpretation is is sensor-specific. */
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI1_OFST 16
-#define       MC_CMD_SENSOR_SET_LIMS_IN_HI1_LEN 4
-
-/* MC_CMD_SENSOR_SET_LIMS_OUT msgresponse */
-#define    MC_CMD_SENSOR_SET_LIMS_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_RESOURCE_LIMITS
- */
-#define MC_CMD_GET_RESOURCE_LIMITS 0x4f
-
-/* MC_CMD_GET_RESOURCE_LIMITS_IN msgrequest */
-#define    MC_CMD_GET_RESOURCE_LIMITS_IN_LEN 0
-
-/* MC_CMD_GET_RESOURCE_LIMITS_OUT msgresponse */
-#define    MC_CMD_GET_RESOURCE_LIMITS_OUT_LEN 16
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_BUFTBL_OFST 0
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_BUFTBL_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_EVQ_OFST 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_EVQ_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_RXQ_OFST 8
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_RXQ_LEN 4
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_TXQ_OFST 12
-#define       MC_CMD_GET_RESOURCE_LIMITS_OUT_TXQ_LEN 4
-
-
 /***********************************/
 /* MC_CMD_NVRAM_PARTITIONS
  * Reads the list of available virtual NVRAM partition types. Locks required:
@@ -8582,806 +9019,6 @@
 #define       MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_OFST 12
 #define       MC_CMD_GET_MAC_ADDRESSES_OUT_MAC_STRIDE_LEN 4
 
-
-/***********************************/
-/* MC_CMD_CLP
- * Perform a CLP related operation, see SF-110495-PS for details of CLP
- * processing. This command has been extended to accomodate the requirements of
- * different manufacturers which are to be found in SF-119187-TC, SF-119186-TC,
- * SF-120509-TC and SF-117282-PS.
- */
-#define MC_CMD_CLP 0x56
-#undef MC_CMD_0x56_PRIVILEGE_CTG
-
-#define MC_CMD_0x56_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_CLP_IN msgrequest */
-#define    MC_CMD_CLP_IN_LEN 4
-/* Sub operation */
-#define       MC_CMD_CLP_IN_OP_OFST 0
-#define       MC_CMD_CLP_IN_OP_LEN 4
-/* enum: Return to factory default settings */
-#define          MC_CMD_CLP_OP_DEFAULT 0x1
-/* enum: Set MAC address */
-#define          MC_CMD_CLP_OP_SET_MAC 0x2
-/* enum: Get MAC address */
-#define          MC_CMD_CLP_OP_GET_MAC 0x3
-/* enum: Set UEFI/GPXE boot mode */
-#define          MC_CMD_CLP_OP_SET_BOOT 0x4
-/* enum: Get UEFI/GPXE boot mode */
-#define          MC_CMD_CLP_OP_GET_BOOT 0x5
-
-/* MC_CMD_CLP_OUT msgresponse */
-#define    MC_CMD_CLP_OUT_LEN 0
-
-/* MC_CMD_CLP_IN_DEFAULT msgrequest */
-#define    MC_CMD_CLP_IN_DEFAULT_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_OUT_DEFAULT msgresponse */
-#define    MC_CMD_CLP_OUT_DEFAULT_LEN 0
-
-/* MC_CMD_CLP_IN_SET_MAC msgrequest */
-#define    MC_CMD_CLP_IN_SET_MAC_LEN 12
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* The MAC address assigned to port. A zero MAC address of 00:00:00:00:00:00
- * restores the permanent (factory-programmed) MAC address associated with the
- * port. A non-zero MAC address persists until a PCIe reset or a power cycle.
- */
-#define       MC_CMD_CLP_IN_SET_MAC_ADDR_OFST 4
-#define       MC_CMD_CLP_IN_SET_MAC_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_IN_SET_MAC_RESERVED_OFST 10
-#define       MC_CMD_CLP_IN_SET_MAC_RESERVED_LEN 2
-
-/* MC_CMD_CLP_OUT_SET_MAC msgresponse */
-#define    MC_CMD_CLP_OUT_SET_MAC_LEN 0
-
-/* MC_CMD_CLP_IN_SET_MAC_V2 msgrequest */
-#define    MC_CMD_CLP_IN_SET_MAC_V2_LEN 16
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* The MAC address assigned to port. A zero MAC address of 00:00:00:00:00:00
- * restores the permanent (factory-programmed) MAC address associated with the
- * port. A non-zero MAC address persists until a PCIe reset or a power cycle.
- */
-#define       MC_CMD_CLP_IN_SET_MAC_V2_ADDR_OFST 4
-#define       MC_CMD_CLP_IN_SET_MAC_V2_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_IN_SET_MAC_V2_RESERVED_OFST 10
-#define       MC_CMD_CLP_IN_SET_MAC_V2_RESERVED_LEN 2
-#define       MC_CMD_CLP_IN_SET_MAC_V2_FLAGS_OFST 12
-#define       MC_CMD_CLP_IN_SET_MAC_V2_FLAGS_LEN 4
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_OFST 12
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_LBN 0
-#define        MC_CMD_CLP_IN_SET_MAC_V2_VIRTUAL_WIDTH 1
-
-/* MC_CMD_CLP_IN_GET_MAC msgrequest */
-#define    MC_CMD_CLP_IN_GET_MAC_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_IN_GET_MAC_V2 msgrequest */
-#define    MC_CMD_CLP_IN_GET_MAC_V2_LEN 8
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-#define       MC_CMD_CLP_IN_GET_MAC_V2_FLAGS_OFST 4
-#define       MC_CMD_CLP_IN_GET_MAC_V2_FLAGS_LEN 4
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_OFST 4
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_LBN 0
-#define        MC_CMD_CLP_IN_GET_MAC_V2_PERMANENT_WIDTH 1
-
-/* MC_CMD_CLP_OUT_GET_MAC msgresponse */
-#define    MC_CMD_CLP_OUT_GET_MAC_LEN 8
-/* MAC address assigned to port */
-#define       MC_CMD_CLP_OUT_GET_MAC_ADDR_OFST 0
-#define       MC_CMD_CLP_OUT_GET_MAC_ADDR_LEN 6
-/* Padding */
-#define       MC_CMD_CLP_OUT_GET_MAC_RESERVED_OFST 6
-#define       MC_CMD_CLP_OUT_GET_MAC_RESERVED_LEN 2
-
-/* MC_CMD_CLP_IN_SET_BOOT msgrequest */
-#define    MC_CMD_CLP_IN_SET_BOOT_LEN 5
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-/* Boot flag */
-#define       MC_CMD_CLP_IN_SET_BOOT_FLAG_OFST 4
-#define       MC_CMD_CLP_IN_SET_BOOT_FLAG_LEN 1
-
-/* MC_CMD_CLP_OUT_SET_BOOT msgresponse */
-#define    MC_CMD_CLP_OUT_SET_BOOT_LEN 0
-
-/* MC_CMD_CLP_IN_GET_BOOT msgrequest */
-#define    MC_CMD_CLP_IN_GET_BOOT_LEN 4
-/*            MC_CMD_CLP_IN_OP_OFST 0 */
-/*            MC_CMD_CLP_IN_OP_LEN 4 */
-
-/* MC_CMD_CLP_OUT_GET_BOOT msgresponse */
-#define    MC_CMD_CLP_OUT_GET_BOOT_LEN 4
-/* Boot flag */
-#define       MC_CMD_CLP_OUT_GET_BOOT_FLAG_OFST 0
-#define       MC_CMD_CLP_OUT_GET_BOOT_FLAG_LEN 1
-/* Padding */
-#define       MC_CMD_CLP_OUT_GET_BOOT_RESERVED_OFST 1
-#define       MC_CMD_CLP_OUT_GET_BOOT_RESERVED_LEN 3
-
-
-/***********************************/
-/* MC_CMD_MUM
- * Perform a MUM operation
- */
-#define MC_CMD_MUM 0x57
-#undef MC_CMD_0x57_PRIVILEGE_CTG
-
-#define MC_CMD_0x57_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_MUM_IN msgrequest */
-#define    MC_CMD_MUM_IN_LEN 4
-#define       MC_CMD_MUM_IN_OP_HDR_OFST 0
-#define       MC_CMD_MUM_IN_OP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_OP_OFST 0
-#define        MC_CMD_MUM_IN_OP_LBN 0
-#define        MC_CMD_MUM_IN_OP_WIDTH 8
-/* enum: NULL MCDI command to MUM */
-#define          MC_CMD_MUM_OP_NULL 0x1
-/* enum: Get MUM version */
-#define          MC_CMD_MUM_OP_GET_VERSION 0x2
-/* enum: Issue raw I2C command to MUM */
-#define          MC_CMD_MUM_OP_RAW_CMD 0x3
-/* enum: Read from registers on devices connected to MUM. */
-#define          MC_CMD_MUM_OP_READ 0x4
-/* enum: Write to registers on devices connected to MUM. */
-#define          MC_CMD_MUM_OP_WRITE 0x5
-/* enum: Control UART logging. */
-#define          MC_CMD_MUM_OP_LOG 0x6
-/* enum: Operations on MUM GPIO lines */
-#define          MC_CMD_MUM_OP_GPIO 0x7
-/* enum: Get sensor readings from MUM */
-#define          MC_CMD_MUM_OP_READ_SENSORS 0x8
-/* enum: Initiate clock programming on the MUM */
-#define          MC_CMD_MUM_OP_PROGRAM_CLOCKS 0x9
-/* enum: Initiate FPGA load from flash on the MUM */
-#define          MC_CMD_MUM_OP_FPGA_LOAD 0xa
-/* enum: Request sensor reading from MUM ADC resulting from earlier request via
- * MUM ATB
- */
-#define          MC_CMD_MUM_OP_READ_ATB_SENSOR 0xb
-/* enum: Send commands relating to the QSFP ports via the MUM for PHY
- * operations
- */
-#define          MC_CMD_MUM_OP_QSFP 0xc
-/* enum: Request discrete and SODIMM DDR info (type, size, speed grade, voltage
- * level) from MUM
- */
-#define          MC_CMD_MUM_OP_READ_DDR_INFO 0xd
-
-/* MC_CMD_MUM_IN_NULL msgrequest */
-#define    MC_CMD_MUM_IN_NULL_LEN 4
-/* MUM cmd header */
-#define       MC_CMD_MUM_IN_CMD_OFST 0
-#define       MC_CMD_MUM_IN_CMD_LEN 4
-
-/* MC_CMD_MUM_IN_GET_VERSION msgrequest */
-#define    MC_CMD_MUM_IN_GET_VERSION_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_IN_READ msgrequest */
-#define    MC_CMD_MUM_IN_READ_LEN 16
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* ID of (device connected to MUM) to read from registers of */
-#define       MC_CMD_MUM_IN_READ_DEVICE_OFST 4
-#define       MC_CMD_MUM_IN_READ_DEVICE_LEN 4
-/* enum: Hittite HMC1035 clock generator on Sorrento board */
-#define          MC_CMD_MUM_DEV_HITTITE 0x1
-/* enum: Hittite HMC1035 clock generator for NIC-side on Sorrento board */
-#define          MC_CMD_MUM_DEV_HITTITE_NIC 0x2
-/* 32-bit address to read from */
-#define       MC_CMD_MUM_IN_READ_ADDR_OFST 8
-#define       MC_CMD_MUM_IN_READ_ADDR_LEN 4
-/* Number of words to read. */
-#define       MC_CMD_MUM_IN_READ_NUMWORDS_OFST 12
-#define       MC_CMD_MUM_IN_READ_NUMWORDS_LEN 4
-
-/* MC_CMD_MUM_IN_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_WRITE_LENMIN 16
-#define    MC_CMD_MUM_IN_WRITE_LENMAX 252
-#define    MC_CMD_MUM_IN_WRITE_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_IN_WRITE_LEN(num) (12+4*(num))
-#define    MC_CMD_MUM_IN_WRITE_BUFFER_NUM(len) (((len)-12)/4)
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* ID of (device connected to MUM) to write to registers of */
-#define       MC_CMD_MUM_IN_WRITE_DEVICE_OFST 4
-#define       MC_CMD_MUM_IN_WRITE_DEVICE_LEN 4
-/* enum: Hittite HMC1035 clock generator on Sorrento board */
-/*               MC_CMD_MUM_DEV_HITTITE 0x1 */
-/* 32-bit address to write to */
-#define       MC_CMD_MUM_IN_WRITE_ADDR_OFST 8
-#define       MC_CMD_MUM_IN_WRITE_ADDR_LEN 4
-/* Words to write */
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_OFST 12
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_LEN 4
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MINNUM 1
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MAXNUM 60
-#define       MC_CMD_MUM_IN_WRITE_BUFFER_MAXNUM_MCDI2 252
-
-/* MC_CMD_MUM_IN_RAW_CMD msgrequest */
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMIN 17
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMAX 252
-#define    MC_CMD_MUM_IN_RAW_CMD_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_IN_RAW_CMD_LEN(num) (16+1*(num))
-#define    MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_NUM(len) (((len)-16)/1)
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* MUM I2C cmd code */
-#define       MC_CMD_MUM_IN_RAW_CMD_CMD_CODE_OFST 4
-#define       MC_CMD_MUM_IN_RAW_CMD_CMD_CODE_LEN 4
-/* Number of bytes to write */
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_WRITE_OFST 8
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_WRITE_LEN 4
-/* Number of bytes to read */
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_READ_OFST 12
-#define       MC_CMD_MUM_IN_RAW_CMD_NUM_READ_LEN 4
-/* Bytes to write */
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_OFST 16
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_LEN 1
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MINNUM 1
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MAXNUM 236
-#define       MC_CMD_MUM_IN_RAW_CMD_WRITE_DATA_MAXNUM_MCDI2 1004
-
-/* MC_CMD_MUM_IN_LOG msgrequest */
-#define    MC_CMD_MUM_IN_LOG_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_LOG_OP_OFST 4
-#define       MC_CMD_MUM_IN_LOG_OP_LEN 4
-#define          MC_CMD_MUM_IN_LOG_OP_UART 0x1 /* enum */
-
-/* MC_CMD_MUM_IN_LOG_OP_UART msgrequest */
-#define    MC_CMD_MUM_IN_LOG_OP_UART_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/*            MC_CMD_MUM_IN_LOG_OP_OFST 4 */
-/*            MC_CMD_MUM_IN_LOG_OP_LEN 4 */
-/* Enable/disable debug output to UART */
-#define       MC_CMD_MUM_IN_LOG_OP_UART_ENABLE_OFST 8
-#define       MC_CMD_MUM_IN_LOG_OP_UART_ENABLE_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_LBN 0
-#define        MC_CMD_MUM_IN_GPIO_OPCODE_WIDTH 8
-#define          MC_CMD_MUM_IN_GPIO_IN_READ 0x0 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_WRITE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_READ 0x2 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE 0x3 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ 0x4 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP 0x5 /* enum */
-
-/* MC_CMD_MUM_IN_GPIO_IN_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_IN_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_IN_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_IN_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_WRITE_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_HDR_LEN 4
-/* The first 32-bit word to be written to the GPIO OUT register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK1_OFST 8
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK1_LEN 4
-/* The second 32-bit word to be written to the GPIO OUT register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK2_OFST 12
-#define       MC_CMD_MUM_IN_GPIO_OUT_WRITE_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_HDR_LEN 4
-/* The first 32-bit word to be written to the GPIO OUT ENABLE register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK1_OFST 8
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK1_LEN 4
-/* The second 32-bit word to be written to the GPIO OUT ENABLE register. */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK2_OFST 12
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_WRITE_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OUT_ENABLE_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OP msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_LBN 8
-#define        MC_CMD_MUM_IN_GPIO_OP_BITWISE_OP_WIDTH 8
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_READ 0x0 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG 0x2 /* enum */
-#define          MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE 0x3 /* enum */
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_LBN 16
-#define        MC_CMD_MUM_IN_GPIO_OP_GPIO_NUMBER_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_READ msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_READ_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_READ_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_READ_HDR_LEN 4
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_WRITE_WRITEBIT_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_CONFIG_CFG_WIDTH 8
-
-/* MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE msgrequest */
-#define    MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_LEN 8
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_HDR_LEN 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_OFST 4
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_LBN 24
-#define        MC_CMD_MUM_IN_GPIO_OP_OUT_ENABLE_ENABLEBIT_WIDTH 8
-
-/* MC_CMD_MUM_IN_READ_SENSORS msgrequest */
-#define    MC_CMD_MUM_IN_READ_SENSORS_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_READ_SENSORS_PARAMS_OFST 4
-#define       MC_CMD_MUM_IN_READ_SENSORS_PARAMS_LEN 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_OFST 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_LBN 0
-#define        MC_CMD_MUM_IN_READ_SENSORS_SENSOR_ID_WIDTH 8
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_OFST 4
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_LBN 8
-#define        MC_CMD_MUM_IN_READ_SENSORS_NUM_SENSORS_WIDTH 8
-
-/* MC_CMD_MUM_IN_PROGRAM_CLOCKS msgrequest */
-#define    MC_CMD_MUM_IN_PROGRAM_CLOCKS_LEN 12
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* Bit-mask of clocks to be programmed */
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_MASK_OFST 4
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_MASK_LEN 4
-#define          MC_CMD_MUM_CLOCK_ID_FPGA 0x0 /* enum */
-#define          MC_CMD_MUM_CLOCK_ID_DDR 0x1 /* enum */
-#define          MC_CMD_MUM_CLOCK_ID_NIC 0x2 /* enum */
-/* Control flags for clock programming */
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_OFST 8
-#define       MC_CMD_MUM_IN_PROGRAM_CLOCKS_FLAGS_LEN 4
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_LBN 0
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_OVERCLOCK_110_WIDTH 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_LBN 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_NIC_FROM_FPGA_WIDTH 1
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_OFST 8
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_LBN 2
-#define        MC_CMD_MUM_IN_PROGRAM_CLOCKS_CLOCK_REF_FROM_XO_WIDTH 1
-
-/* MC_CMD_MUM_IN_FPGA_LOAD msgrequest */
-#define    MC_CMD_MUM_IN_FPGA_LOAD_LEN 8
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-/* Enable/Disable FPGA config from flash */
-#define       MC_CMD_MUM_IN_FPGA_LOAD_ENABLE_OFST 4
-#define       MC_CMD_MUM_IN_FPGA_LOAD_ENABLE_LEN 4
-
-/* MC_CMD_MUM_IN_READ_ATB_SENSOR msgrequest */
-#define    MC_CMD_MUM_IN_READ_ATB_SENSOR_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_IN_QSFP msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_LEN 12
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_HDR_LEN 4
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_OFST 4
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_LBN 0
-#define        MC_CMD_MUM_IN_QSFP_OPCODE_WIDTH 4
-#define          MC_CMD_MUM_IN_QSFP_INIT 0x0 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_RECONFIGURE 0x1 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP 0x2 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO 0x3 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_FILL_STATS 0x4 /* enum */
-#define          MC_CMD_MUM_IN_QSFP_POLL_BIST 0x5 /* enum */
-#define       MC_CMD_MUM_IN_QSFP_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_INIT msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_INIT_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_INIT_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_INIT_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_INIT_CAGE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_INIT_CAGE_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_RECONFIGURE msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_RECONFIGURE_LEN 24
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_TX_DISABLE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_TX_DISABLE_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LANES_OFST 16
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LANES_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LINK_SPEED_OFST 20
-#define       MC_CMD_MUM_IN_QSFP_RECONFIGURE_PORT_LINK_SPEED_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_GET_SUPPORTED_CAP_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_LEN 16
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_IDX_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_PAGE_OFST 12
-#define       MC_CMD_MUM_IN_QSFP_GET_MEDIA_INFO_PAGE_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_FILL_STATS msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_FILL_STATS_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_FILL_STATS_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_QSFP_POLL_BIST msgrequest */
-#define    MC_CMD_MUM_IN_QSFP_POLL_BIST_LEN 12
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_OFST 4
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_HDR_LEN 4
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_OFST 8
-#define       MC_CMD_MUM_IN_QSFP_POLL_BIST_IDX_LEN 4
-
-/* MC_CMD_MUM_IN_READ_DDR_INFO msgrequest */
-#define    MC_CMD_MUM_IN_READ_DDR_INFO_LEN 4
-/* MUM cmd header */
-/*            MC_CMD_MUM_IN_CMD_OFST 0 */
-/*            MC_CMD_MUM_IN_CMD_LEN 4 */
-
-/* MC_CMD_MUM_OUT msgresponse */
-#define    MC_CMD_MUM_OUT_LEN 0
-
-/* MC_CMD_MUM_OUT_NULL msgresponse */
-#define    MC_CMD_MUM_OUT_NULL_LEN 0
-
-/* MC_CMD_MUM_OUT_GET_VERSION msgresponse */
-#define    MC_CMD_MUM_OUT_GET_VERSION_LEN 12
-#define       MC_CMD_MUM_OUT_GET_VERSION_FIRMWARE_OFST 0
-#define       MC_CMD_MUM_OUT_GET_VERSION_FIRMWARE_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_OFST 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LEN 8
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_OFST 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_LBN 32
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_LO_WIDTH 32
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_OFST 8
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_LEN 4
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_LBN 64
-#define       MC_CMD_MUM_OUT_GET_VERSION_VERSION_HI_WIDTH 32
-
-/* MC_CMD_MUM_OUT_RAW_CMD msgresponse */
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMIN 1
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMAX 252
-#define    MC_CMD_MUM_OUT_RAW_CMD_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_RAW_CMD_LEN(num) (0+1*(num))
-#define    MC_CMD_MUM_OUT_RAW_CMD_DATA_NUM(len) (((len)-0)/1)
-/* returned data */
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_OFST 0
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_LEN 1
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MAXNUM 252
-#define       MC_CMD_MUM_OUT_RAW_CMD_DATA_MAXNUM_MCDI2 1020
-
-/* MC_CMD_MUM_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_READ_LENMIN 4
-#define    MC_CMD_MUM_OUT_READ_LENMAX 252
-#define    MC_CMD_MUM_OUT_READ_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_READ_LEN(num) (0+4*(num))
-#define    MC_CMD_MUM_OUT_READ_BUFFER_NUM(len) (((len)-0)/4)
-#define       MC_CMD_MUM_OUT_READ_BUFFER_OFST 0
-#define       MC_CMD_MUM_OUT_READ_BUFFER_LEN 4
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MINNUM 1
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MAXNUM 63
-#define       MC_CMD_MUM_OUT_READ_BUFFER_MAXNUM_MCDI2 255
-
-/* MC_CMD_MUM_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_LOG msgresponse */
-#define    MC_CMD_MUM_OUT_LOG_LEN 0
-
-/* MC_CMD_MUM_OUT_LOG_OP_UART msgresponse */
-#define    MC_CMD_MUM_OUT_LOG_OP_UART_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_IN_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_IN_READ_LEN 8
-/* The first 32-bit word read from the GPIO IN register. */
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK1_LEN 4
-/* The second 32-bit word read from the GPIO IN register. */
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_IN_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_READ_LEN 8
-/* The first 32-bit word read from the GPIO OUT register. */
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK1_LEN 4
-/* The second 32-bit word read from the GPIO OUT register. */
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_LEN 8
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK1_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK1_LEN 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK2_OFST 4
-#define       MC_CMD_MUM_OUT_GPIO_OUT_ENABLE_READ_GPIOMASK2_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_READ msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_LEN 4
-#define       MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_BIT_READ_OFST 0
-#define       MC_CMD_MUM_OUT_GPIO_OP_OUT_READ_BIT_READ_LEN 4
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_WRITE_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_CONFIG_LEN 0
-
-/* MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE msgresponse */
-#define    MC_CMD_MUM_OUT_GPIO_OP_OUT_ENABLE_LEN 0
-
-/* MC_CMD_MUM_OUT_READ_SENSORS msgresponse */
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMIN 4
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMAX 252
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_READ_SENSORS_LEN(num) (0+4*(num))
-#define    MC_CMD_MUM_OUT_READ_SENSORS_DATA_NUM(len) (((len)-0)/4)
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_OFST 0
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_LEN 4
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MAXNUM 63
-#define       MC_CMD_MUM_OUT_READ_SENSORS_DATA_MAXNUM_MCDI2 255
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_LBN 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_READING_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_LBN 16
-#define        MC_CMD_MUM_OUT_READ_SENSORS_STATE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_OFST 0
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_LBN 24
-#define        MC_CMD_MUM_OUT_READ_SENSORS_TYPE_WIDTH 8
-
-/* MC_CMD_MUM_OUT_PROGRAM_CLOCKS msgresponse */
-#define    MC_CMD_MUM_OUT_PROGRAM_CLOCKS_LEN 4
-#define       MC_CMD_MUM_OUT_PROGRAM_CLOCKS_OK_MASK_OFST 0
-#define       MC_CMD_MUM_OUT_PROGRAM_CLOCKS_OK_MASK_LEN 4
-
-/* MC_CMD_MUM_OUT_FPGA_LOAD msgresponse */
-#define    MC_CMD_MUM_OUT_FPGA_LOAD_LEN 0
-
-/* MC_CMD_MUM_OUT_READ_ATB_SENSOR msgresponse */
-#define    MC_CMD_MUM_OUT_READ_ATB_SENSOR_LEN 4
-#define       MC_CMD_MUM_OUT_READ_ATB_SENSOR_RESULT_OFST 0
-#define       MC_CMD_MUM_OUT_READ_ATB_SENSOR_RESULT_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_INIT msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_INIT_LEN 0
-
-/* MC_CMD_MUM_OUT_QSFP_RECONFIGURE msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_RECONFIGURE_LEN 8
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LP_CAP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LP_CAP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_FLAGS_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_FLAGS_LEN 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_OFST 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_LBN 0
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_READY_WIDTH 1
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_OFST 4
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_LBN 1
-#define        MC_CMD_MUM_OUT_QSFP_RECONFIGURE_PORT_PHY_LINK_UP_WIDTH 1
-
-/* MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_PORT_PHY_LP_CAP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_GET_SUPPORTED_CAP_PORT_PHY_LP_CAP_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMIN 5
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMAX 252
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LENMAX_MCDI2 1020
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_LEN(num) (4+1*(num))
-#define    MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_NUM(len) (((len)-4)/1)
-/* in bytes */
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATALEN_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATALEN_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_LEN 1
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MINNUM 1
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MAXNUM 248
-#define       MC_CMD_MUM_OUT_QSFP_GET_MEDIA_INFO_DATA_MAXNUM_MCDI2 1016
-
-/* MC_CMD_MUM_OUT_QSFP_FILL_STATS msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_FILL_STATS_LEN 8
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PMA_PMD_LINK_UP_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PMA_PMD_LINK_UP_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PCS_LINK_UP_OFST 4
-#define       MC_CMD_MUM_OUT_QSFP_FILL_STATS_PORT_PHY_STATS_PCS_LINK_UP_LEN 4
-
-/* MC_CMD_MUM_OUT_QSFP_POLL_BIST msgresponse */
-#define    MC_CMD_MUM_OUT_QSFP_POLL_BIST_LEN 4
-#define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_OFST 0
-#define       MC_CMD_MUM_OUT_QSFP_POLL_BIST_TEST_LEN 4
-
-/* MC_CMD_MUM_OUT_READ_DDR_INFO msgresponse */
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMIN 24
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX 248
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LENMAX_MCDI2 1016
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_LEN(num) (8+8*(num))
-#define    MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_NUM(len) (((len)-8)/8)
-/* Discrete (soldered) DDR resistor strap info */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_OFST 0
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_DISCRETE_DDR_INFO_LEN 4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_OFST 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_LBN 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VRATIO_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_OFST 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_LBN 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED1_WIDTH 16
-/* Number of SODIMM info records */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_OFST 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_RECORDS_LEN 4
-/* Array of SODIMM info records */
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_OFST 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LEN 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_OFST 8
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_LEN 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_LBN 64
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_LO_WIDTH 32
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_OFST 12
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_LEN 4
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_LBN 96
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_HI_WIDTH 32
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MINNUM 2
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM 30
-#define       MC_CMD_MUM_OUT_READ_DDR_INFO_SODIMM_INFO_RECORD_MAXNUM_MCDI2 126
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_LBN 0
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_BANK_ID_WIDTH 8
-/* enum: SODIMM bank 1 (Top SODIMM for Sorrento) */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK1 0x0
-/* enum: SODIMM bank 2 (Bottom SODDIMM for Sorrento) */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_BANK2 0x1
-/* enum: Total number of SODIMM banks */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NUM_BANKS 0x2
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_LBN 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_TYPE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_LBN 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RANK_WIDTH 4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_LBN 20
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_VOLTAGE_WIDTH 4
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_POWERED 0x0 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V25 0x1 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V35 0x2 /* enum */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V5 0x3 /* enum */
-/* enum: Values 5-15 are reserved for future usage */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_1V8 0x4
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_LBN 24
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SIZE_WIDTH 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_LBN 32
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_SPEED_WIDTH 16
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_LBN 48
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_STATE_WIDTH 4
-/* enum: No module present */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_ABSENT 0x0
-/* enum: Module present supported and powered on */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_POWERED 0x1
-/* enum: Module present but bad type */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_TYPE 0x2
-/* enum: Module present but incompatible voltage */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_VOLTAGE 0x3
-/* enum: Module present but unknown SPD */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SPD 0x4
-/* enum: Module present but slot cannot support it */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_PRESENT_BAD_SLOT 0x5
-/* enum: Modules may or may not be present, but cannot establish contact by I2C
- */
-#define          MC_CMD_MUM_OUT_READ_DDR_INFO_NOT_REACHABLE 0x6
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_OFST 8
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_LBN 52
-#define        MC_CMD_MUM_OUT_READ_DDR_INFO_RESERVED2_WIDTH 12
-
 /* MC_CMD_DYNAMIC_SENSORS_LIMITS structuredef: Set of sensor limits. This
  * should match the equivalent structure in the sensor_query SPHINX service.
  */
@@ -9500,27 +9137,22 @@
  * and a generation count for this version of the sensor table. On systems
  * advertising the DYNAMIC_SENSORS capability bit, this replaces the
  * MC_CMD_READ_SENSORS command. On multi-MC systems this may include sensors
- * added by the NMC.
- *
- * Sensor handles are persistent for the lifetime of the sensor and are used to
- * identify sensors in MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS and
- * MC_CMD_DYNAMIC_SENSORS_GET_VALUES.
- *
- * The generation count is maintained by the MC, is persistent across reboots
- * and will be incremented each time the sensor table is modified. When the
- * table is modified, a CODE_DYNAMIC_SENSORS_CHANGE event will be generated
- * containing the new generation count. The driver should compare this against
- * the current generation count, and if it is different, call
- * MC_CMD_DYNAMIC_SENSORS_LIST again to update it's copy of the sensor table.
- *
- * The sensor count is provided to allow a future path to supporting more than
+ * added by the NMC. Sensor handles are persistent for the lifetime of the
+ * sensor and are used to identify sensors in
+ * MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS and
+ * MC_CMD_DYNAMIC_SENSORS_GET_VALUES. The generation count is maintained by the
+ * MC, is persistent across reboots and will be incremented each time the
+ * sensor table is modified. When the table is modified, a
+ * CODE_DYNAMIC_SENSORS_CHANGE event will be generated containing the new
+ * generation count. The driver should compare this against the current
+ * generation count, and if it is different, call MC_CMD_DYNAMIC_SENSORS_LIST
+ * again to update it's copy of the sensor table. The sensor count is provided
+ * to allow a future path to supporting more than
  * MC_CMD_DYNAMIC_SENSORS_GET_READINGS_IN_HANDLES_MAXNUM_MCDI2 sensors, i.e.
  * the maximum number that will fit in a single response. As this is a fairly
  * large number (253) it is not anticipated that this will be needed in the
- * near future, so can currently be ignored.
- *
- * On Riverhead this command is implemented as a wrapper for `list` in the
- * sensor_query SPHINX service.
+ * near future, so can currently be ignored. On Riverhead this command is
+ * implemented as a wrapper for `list` in the sensor_query SPHINX service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_LIST 0x66
 #undef MC_CMD_0x66_PRIVILEGE_CTG
@@ -9557,15 +9189,13 @@
 /***********************************/
 /* MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS
  * Get descriptions for a set of sensors, specified as an array of sensor
- * handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST
- *
- * Any handles which do not correspond to a sensor currently managed by the MC
- * will be dropped from from the response. This may happen when a sensor table
- * update is in progress, and effectively means the set of usable sensors is
- * the intersection between the sets of sensors known to the driver and the MC.
- *
- * On Riverhead this command is implemented as a wrapper for
- * `get_descriptions` in the sensor_query SPHINX service.
+ * handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST. Any handles which do not
+ * correspond to a sensor currently managed by the MC will be dropped from from
+ * the response. This may happen when a sensor table update is in progress, and
+ * effectively means the set of usable sensors is the intersection between the
+ * sets of sensors known to the driver and the MC. On Riverhead this command is
+ * implemented as a wrapper for `get_descriptions` in the sensor_query SPHINX
+ * service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_GET_DESCRIPTIONS 0x67
 #undef MC_CMD_0x67_PRIVILEGE_CTG
@@ -9602,19 +9232,15 @@
 /***********************************/
 /* MC_CMD_DYNAMIC_SENSORS_GET_READINGS
  * Read the state and value for a set of sensors, specified as an array of
- * sensor handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST.
- *
- * In the case of a broken sensor, then the state of the response's
- * MC_CMD_DYNAMIC_SENSORS_VALUE entry will be set to BROKEN, and any value
- * provided should be treated as erroneous.
- *
- * Any handles which do not correspond to a sensor currently managed by the MC
- * will be dropped from from the response. This may happen when a sensor table
- * update is in progress, and effectively means the set of usable sensors is
- * the intersection between the sets of sensors known to the driver and the MC.
- *
- * On Riverhead this command is implemented as a wrapper for `get_readings`
- * in the sensor_query SPHINX service.
+ * sensor handles as returned by MC_CMD_DYNAMIC_SENSORS_LIST. In the case of a
+ * broken sensor, then the state of the response's MC_CMD_DYNAMIC_SENSORS_VALUE
+ * entry will be set to BROKEN, and any value provided should be treated as
+ * erroneous. Any handles which do not correspond to a sensor currently managed
+ * by the MC will be dropped from from the response. This may happen when a
+ * sensor table update is in progress, and effectively means the set of usable
+ * sensors is the intersection between the sets of sensors known to the driver
+ * and the MC. On Riverhead this command is implemented as a wrapper for
+ * `get_readings` in the sensor_query SPHINX service.
  */
 #define MC_CMD_DYNAMIC_SENSORS_GET_READINGS 0x68
 #undef MC_CMD_0x68_PRIVILEGE_CTG
@@ -9647,45 +9273,1286 @@
 #define       MC_CMD_DYNAMIC_SENSORS_GET_READINGS_OUT_VALUES_MAXNUM 21
 #define       MC_CMD_DYNAMIC_SENSORS_GET_READINGS_OUT_VALUES_MAXNUM_MCDI2 85
 
-
+/* MC_CMD_MAC_FLAGS structuredef */
+#define    MC_CMD_MAC_FLAGS_LEN 4
+/* The enums defined in this field are used as indices into the
+ * MC_CMD_MAC_FLAGS bitmask.
+ */
+#define       MC_CMD_MAC_FLAGS_MASK_OFST 0
+#define       MC_CMD_MAC_FLAGS_MASK_LEN 4
+/* enum property: bitshift */
+/* enum: Include the FCS in the packet data delivered to the host. Ignored if
+ * RX_INCLUDE_FCS not set in capabilities.
+ */
+#define          MC_CMD_MAC_FLAGS_FLAG_INCLUDE_FCS 0x0
+#define       MC_CMD_MAC_FLAGS_MASK_LBN 0
+#define       MC_CMD_MAC_FLAGS_MASK_WIDTH 32
+
+/* MC_CMD_TRANSMISSION_MODE structuredef */
+#define    MC_CMD_TRANSMISSION_MODE_LEN 4
+#define       MC_CMD_TRANSMISSION_MODE_MASK_OFST 0
+#define       MC_CMD_TRANSMISSION_MODE_MASK_LEN 4
+/* enum property: value */
+#define          MC_CMD_TRANSMISSION_MODE_PROMSC_MODE 0x0 /* enum */
+#define          MC_CMD_TRANSMISSION_MODE_UNCST_MODE 0x1 /* enum */
+#define          MC_CMD_TRANSMISSION_MODE_BRDCST_MODE 0x2 /* enum */
+#define       MC_CMD_TRANSMISSION_MODE_MASK_LBN 0
+#define       MC_CMD_TRANSMISSION_MODE_MASK_WIDTH 32
+
+/* MC_CMD_MAC_CONFIG_OPTIONS structuredef */
+#define    MC_CMD_MAC_CONFIG_OPTIONS_LEN 4
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_OFST 0
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_LEN 4
+/* enum property: bitmask */
+/* enum: Configure the MAC address. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_ADDR 0x0
+/* enum: Configure the maximum frame length. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_MAX_FRAME_LEN 0x1
+/* enum: Configure flow control. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_FCNTL 0x2
+/* enum: Configure the transmission mode. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_TRANSMISSION_MODE 0x3
+/* enum: Configure FCS. */
+#define          MC_CMD_MAC_CONFIG_OPTIONS_CFG_INCLUDE_FCS 0x4
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_LBN 0
+#define       MC_CMD_MAC_CONFIG_OPTIONS_MASK_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_MAC_CTRL
+ * Set MAC configuration. Return code: 0, EINVAL, ENOTSUP
+ */
+#define MC_CMD_MAC_CTRL 0x1df
+#undef MC_CMD_0x1df_PRIVILEGE_CTG
+
+#define MC_CMD_0x1df_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_MAC_CTRL_IN msgrequest */
+#define    MC_CMD_MAC_CTRL_IN_LEN 32
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_CTRL_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_CTRL_IN_PORT_HANDLE_LEN 4
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set.
+ */
+#define       MC_CMD_MAC_CTRL_IN_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_MAC_CTRL_IN_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_CTRL_IN_ADDR_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LEN 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_CTRL_IN_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_CTRL_IN_ADDR_HI_WIDTH 32
+/* Includes the ethernet header, optional VLAN tags, payload and FCS. */
+#define       MC_CMD_MAC_CTRL_IN_MAX_FRAME_LEN_OFST 16
+#define       MC_CMD_MAC_CTRL_IN_MAX_FRAME_LEN_LEN 4
+/* Settings for flow control. */
+#define       MC_CMD_MAC_CTRL_IN_FCNTL_OFST 20
+#define       MC_CMD_MAC_CTRL_IN_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* Configure the MAC to transmit in one of promiscuous, unicast or broadcast
+ * mode.
+ */
+#define       MC_CMD_MAC_CTRL_IN_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_CTRL_IN_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* Flags to control and expand the configuration of the MAC. */
+#define       MC_CMD_MAC_CTRL_IN_FLAGS_OFST 28
+#define       MC_CMD_MAC_CTRL_IN_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+
+/* MC_CMD_MAC_CTRL_IN_V2 msgrequest: Updated MAC_CTRL with QBB mask */
+#define    MC_CMD_MAC_CTRL_IN_V2_LEN 33
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_CTRL_IN_V2_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_CTRL_IN_V2_PORT_HANDLE_LEN 4
+/* Select which parameters to configure. A parameter will only be modified if
+ * the corresponding control flag is set.
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_CONTROL_FLAGS_OFST 4
+#define       MC_CMD_MAC_CTRL_IN_V2_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LEN 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_CTRL_IN_V2_ADDR_HI_WIDTH 32
+/* Includes the ethernet header, optional VLAN tags, payload and FCS. */
+#define       MC_CMD_MAC_CTRL_IN_V2_MAX_FRAME_LEN_OFST 16
+#define       MC_CMD_MAC_CTRL_IN_V2_MAX_FRAME_LEN_LEN 4
+/* Settings for flow control. */
+#define       MC_CMD_MAC_CTRL_IN_V2_FCNTL_OFST 20
+#define       MC_CMD_MAC_CTRL_IN_V2_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* Configure the MAC to transmit in one of promiscuous, unicast or broadcast
+ * mode.
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_CTRL_IN_V2_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* Flags to control and expand the configuration of the MAC. */
+#define       MC_CMD_MAC_CTRL_IN_V2_FLAGS_OFST 28
+#define       MC_CMD_MAC_CTRL_IN_V2_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+/* Priority-based flow control mask (QBB). PRIO7 corresponds to the highest
+ * priority, and PRIO0 to the lowest. This field is only used when CFG_FCNTL is
+ * set and FCNTL is QBB
+ */
+#define       MC_CMD_MAC_CTRL_IN_V2_PRIO_FCNTL_MASK_OFST 32
+#define       MC_CMD_MAC_CTRL_IN_V2_PRIO_FCNTL_MASK_LEN 1
+/* enum property: bitmask */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO0 0x0 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO1 0x1 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO2 0x2 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO3 0x3 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO4 0x4 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO5 0x5 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO6 0x6 /* enum */
+#define          MC_CMD_MAC_CTRL_IN_V2_QBB_PRIO7 0x7 /* enum */
+
+/* MC_CMD_MAC_CTRL_OUT msgresponse */
+#define    MC_CMD_MAC_CTRL_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_MAC_STATE
+ * Read the MAC state. Return code: 0, ETIME.
+ */
+#define MC_CMD_MAC_STATE 0x1e0
+#undef MC_CMD_0x1e0_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e0_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_MAC_STATE_IN msgrequest */
+#define    MC_CMD_MAC_STATE_IN_LEN 4
+/* Handle for selected network port. */
+#define       MC_CMD_MAC_STATE_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATE_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_MAC_STATE_OUT msgresponse */
+#define    MC_CMD_MAC_STATE_OUT_LEN 32
+/* The configured maximum frame length of the MAC. */
+#define       MC_CMD_MAC_STATE_OUT_MAX_FRAME_LEN_OFST 0
+#define       MC_CMD_MAC_STATE_OUT_MAX_FRAME_LEN_LEN 4
+/* This returns the negotiated flow control value. */
+#define       MC_CMD_MAC_STATE_OUT_FCNTL_OFST 4
+#define       MC_CMD_MAC_STATE_OUT_FCNTL_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_FCNTL/MASK */
+/* MAC address of the device. */
+#define       MC_CMD_MAC_STATE_OUT_ADDR_OFST 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LEN 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_STATE_OUT_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_STATE_OUT_ADDR_HI_WIDTH 32
+/* Flags indicating MAC faults. */
+#define       MC_CMD_MAC_STATE_OUT_MAC_FAULT_FLAGS_OFST 16
+#define       MC_CMD_MAC_STATE_OUT_MAC_FAULT_FLAGS_LEN 4
+/* enum property: bitshift */
+/* enum: Indicates a local MAC fault. */
+#define          MC_CMD_MAC_STATE_OUT_LOCAL 0x0
+/* enum: Indicates a remote MAC fault. */
+#define          MC_CMD_MAC_STATE_OUT_REMOTE 0x1
+/* enum: Indicates a pending reconfiguration of the MAC. */
+#define          MC_CMD_MAC_STATE_OUT_PENDING_RECONFIG 0x2
+/* The flags that were used to configure the MAC. This is a copy of the FLAGS
+ * field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_FLAGS_OFST 20
+#define       MC_CMD_MAC_STATE_OUT_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_FLAGS/MASK */
+/* The transmission mode that was used to configure the MAC. This is a copy of
+ * the TRANSMISSION_MODE field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_TRANSMISSION_MODE_OFST 24
+#define       MC_CMD_MAC_STATE_OUT_TRANSMISSION_MODE_LEN 4
+/* enum property: value */
+/*            Enum values, see field(s): */
+/*               MC_CMD_TRANSMISSION_MODE/MASK */
+/* The control flags that were used to configure the MAC. This is a copy of the
+ * CONTROL field in the MC_CMD_MAC_CTRL_IN command.
+ */
+#define       MC_CMD_MAC_STATE_OUT_CONTROL_FLAGS_OFST 28
+#define       MC_CMD_MAC_STATE_OUT_CONTROL_FLAGS_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_MAC_CONFIG_OPTIONS/MASK */
+
+
+/***********************************/
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE
+ * Obtain a handle that can be operated on to configure and query the status of
+ * the link. ENOENT is returned when no port is assigned to the client. Return
+ * code: 0, ENOENT
+ */
+#define MC_CMD_GET_ASSIGNED_PORT_HANDLE 0x1e2
+#undef MC_CMD_0x1e2_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE_IN msgrequest */
+#define    MC_CMD_GET_ASSIGNED_PORT_HANDLE_IN_LEN 0
+
+/* MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT msgresponse */
+#define    MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_LEN 4
+/* Handle for assigned port. */
+#define       MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_ASSIGNED_PORT_HANDLE_OUT_PORT_HANDLE_LEN 4
+
+/* MC_CMD_STAT_ID structuredef */
+#define    MC_CMD_STAT_ID_LEN 4
+#define       MC_CMD_STAT_ID_SOURCE_ID_OFST 0
+#define       MC_CMD_STAT_ID_SOURCE_ID_LEN 2
+/* enum property: index */
+/* enum: Internal markers (generation start and end markers) */
+#define          MC_CMD_STAT_ID_MARKER 0x1
+/* enum: Network port MAC statistics. */
+#define          MC_CMD_STAT_ID_MAC 0x2
+/* enum: Network port PHY statistics. */
+#define          MC_CMD_STAT_ID_PHY 0x3
+#define       MC_CMD_STAT_ID_SOURCE_ID_LBN 0
+#define       MC_CMD_STAT_ID_SOURCE_ID_WIDTH 16
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: This value is used to mark the start of a generation of statistics for
+ * DMA synchronization. It is incremented whenever a new set of statistics is
+ * transferred. Always the first entry in the DMA buffer.
+ */
+#define          MC_CMD_STAT_ID_GENERATION_START 0x1
+/* enum: This value is used to mark the end of a generation of statistics for
+ * DMA synchronizaion. Always the last entry in the DMA buffer and set to the
+ * same value as GENERATION_START. The host driver must compare the
+ * GENERATION_START and GENERATION_END values to verify that the DMA buffer is
+ * consistent upon copying the the DMA buffer. If they do not match, it means
+ * that new DMA transfer has started while the host driver was copying the DMA
+ * buffer. In this case, the host driver must repeat the copy operation.
+ */
+#define          MC_CMD_STAT_ID_GENERATION_END 0x2
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_MARKER_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: Total number of packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_PKTS 0x1
+/* enum: Pause frames transmitted. */
+#define          MC_CMD_STAT_ID_TX_PAUSE_PKTS 0x2
+/* enum: Control frames transmitted. */
+#define          MC_CMD_STAT_ID_TX_CONTROL_PKTS 0x3
+/* enum: Unicast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_UNICAST_PKTS 0x4
+/* enum: Multicast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_MULTICAST_PKTS 0x5
+/* enum: Broadcast packets transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_BROADCAST_PKTS 0x6
+/* enum: Bytes transmitted (includes pause frames). */
+#define          MC_CMD_STAT_ID_TX_BYTES 0x7
+/* enum: Bytes transmitted with bad CRC. */
+#define          MC_CMD_STAT_ID_TX_BAD_BYTES 0x8
+/* enum: Bytes transmitted with good CRC. */
+#define          MC_CMD_STAT_ID_TX_GOOD_BYTES 0x9
+/* enum: Packets transmitted with length less than 64 bytes. */
+#define          MC_CMD_STAT_ID_TX_LT64_PKTS 0xa
+/* enum: Packets transmitted with length equal to 64 bytes. */
+#define          MC_CMD_STAT_ID_TX_64_PKTS 0xb
+/* enum: Packets transmitted with length between 65 and 127 bytes. */
+#define          MC_CMD_STAT_ID_TX_65_TO_127_PKTS 0xc
+/* enum: Packets transmitted with length between 128 and 255 bytes. */
+#define          MC_CMD_STAT_ID_TX_128_TO_255_PKTS 0xd
+/* enum: Packets transmitted with length between 256 and 511 bytes. */
+#define          MC_CMD_STAT_ID_TX_256_TO_511_PKTS 0xe
+/* enum: Packets transmitted with length between 512 and 1023 bytes. */
+#define          MC_CMD_STAT_ID_TX_512_TO_1023_PKTS 0xf
+/* enum: Packets transmitted with length between 1024 and 1518 bytes. */
+#define          MC_CMD_STAT_ID_TX_1024_TO_15XX_PKTS 0x10
+/* enum: Packets transmitted with length between 1519 and 9216 bytes. */
+#define          MC_CMD_STAT_ID_TX_15XX_TO_JUMBO_PKTS 0x11
+/* enum: Packets transmitted with length greater than 9216 bytes. */
+#define          MC_CMD_STAT_ID_TX_GTJUMBO_PKTS 0x12
+/* enum: Packets transmitted with bad FCS. */
+#define          MC_CMD_STAT_ID_TX_BAD_FCS_PKTS 0x13
+/* enum: Packets transmitted with good FCS. */
+#define          MC_CMD_STAT_ID_TX_GOOD_FCS_PKTS 0x14
+/* enum: Packets received. */
+#define          MC_CMD_STAT_ID_RX_PKTS 0x15
+/* enum: Pause frames received. */
+#define          MC_CMD_STAT_ID_RX_PAUSE_PKTS 0x16
+/* enum: Total number of good packets received. */
+#define          MC_CMD_STAT_ID_RX_GOOD_PKTS 0x17
+/* enum: Total number of BAD packets received. */
+#define          MC_CMD_STAT_ID_RX_BAD_PKTS 0x18
+/* enum: Total number of control frames received. */
+#define          MC_CMD_STAT_ID_RX_CONTROL_PKTS 0x19
+/* enum: Total number of unicast packets received. */
+#define          MC_CMD_STAT_ID_RX_UNICAST_PKTS 0x1a
+/* enum: Total number of multicast packets received. */
+#define          MC_CMD_STAT_ID_RX_MULTICAST_PKTS 0x1b
+/* enum: Total number of broadcast packets received. */
+#define          MC_CMD_STAT_ID_RX_BROADCAST_PKTS 0x1c
+/* enum: Total number of bytes received. */
+#define          MC_CMD_STAT_ID_RX_BYTES 0x1d
+/* enum: Total number of bytes received with bad CRC. */
+#define          MC_CMD_STAT_ID_RX_BAD_BYTES 0x1e
+/* enum: Total number of bytes received with GOOD CRC. */
+#define          MC_CMD_STAT_ID_RX_GOOD_BYTES 0x1f
+/* enum: Packets received with length equal to 64 bytes. */
+#define          MC_CMD_STAT_ID_RX_64_PKTS 0x20
+/* enum: Packets received with length between 65 and 127 bytes. */
+#define          MC_CMD_STAT_ID_RX_65_TO_127_PKTS 0x21
+/* enum: Packets received with length between 128 and 255 bytes. */
+#define          MC_CMD_STAT_ID_RX_128_TO_255_PKTS 0x22
+/* enum: Packets received with length between 256 and 511 bytes. */
+#define          MC_CMD_STAT_ID_RX_256_TO_511_PKTS 0x23
+/* enum: Packets received with length between 512 and 1023 bytes. */
+#define          MC_CMD_STAT_ID_RX_512_TO_1023_PKTS 0x24
+/* enum: Packets received with length between 1024 and 1518 bytes. */
+#define          MC_CMD_STAT_ID_RX_1024_TO_15XX_PKTS 0x25
+/* enum: Packets received with length between 1519 and 9216 bytes. */
+#define          MC_CMD_STAT_ID_RX_15XX_TO_JUMBO_PKTS 0x26
+/* enum: Packets received with length greater than 9216 bytes. */
+#define          MC_CMD_STAT_ID_RX_GTJUMBO_PKTS 0x27
+/* enum: Packets received with length less than 64 bytes. */
+#define          MC_CMD_STAT_ID_RX_UNDERSIZE_PKTS 0x28
+/* enum: Packets received with bad FCS. */
+#define          MC_CMD_STAT_ID_RX_BAD_FCS_PKTS 0x29
+/* enum: Packets received with GOOD FCS. */
+#define          MC_CMD_STAT_ID_RX_GOOD_FCS_PKTS 0x2a
+/* enum: Packets received with overflow. */
+#define          MC_CMD_STAT_ID_RX_OVERFLOW_PKTS 0x2b
+/* enum: Packets received with symbol error. */
+#define          MC_CMD_STAT_ID_RX_SYMBOL_ERROR_PKTS 0x2c
+/* enum: Packets received with alignment error. */
+#define          MC_CMD_STAT_ID_RX_ALIGN_ERROR_PKTS 0x2d
+/* enum: Packets received with length error. */
+#define          MC_CMD_STAT_ID_RX_LENGTH_ERROR_PKTS 0x2e
+/* enum: Packets received with internal error. */
+#define          MC_CMD_STAT_ID_RX_INTERNAL_ERROR_PKTS 0x2f
+/* enum: Packets received with jabber. These packets are larger than the
+ * allowed maximum receive unit (MRU). This indicates that a packet either has
+ * a bad CRC or has an RX error.
+ */
+#define          MC_CMD_STAT_ID_RX_JABBER_PKTS 0x30
+/* enum: Packets dropped due to having no descriptor. This is a datapath stat
+ */
+#define          MC_CMD_STAT_ID_RX_NODESC_DROPS 0x31
+/* enum: Packets received with lanes 0 and 1 character error. */
+#define          MC_CMD_STAT_ID_RX_LANES01_CHAR_ERR 0x32
+/* enum: Packets received with lanes 2 and 3 character error. */
+#define          MC_CMD_STAT_ID_RX_LANES23_CHAR_ERR 0x33
+/* enum: Packets received with lanes 0 and 1 disparity error. */
+#define          MC_CMD_STAT_ID_RX_LANES01_DISP_ERR 0x34
+/* enum: Packets received with lanes 2 and 3 disparity error. */
+#define          MC_CMD_STAT_ID_RX_LANES23_DISP_ERR 0x35
+/* enum: Packets received with match fault. */
+#define          MC_CMD_STAT_ID_RX_MATCH_FAULT 0x36
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_MAC_STAT_ID_WIDTH 16
+/* Include FEC stats. */
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_OFST 2
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_LEN 2
+/* enum property: index */
+/* enum: Number of uncorrected FEC codewords on link (RS-FEC only from Medford2
+ * onwards)
+ */
+#define          MC_CMD_STAT_ID_FEC_UNCORRECTED_ERRORS 0x1
+/* enum: Number of corrected FEC codewords on link (RS-FEC only from Medford2
+ * onwards)
+ */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_ERRORS 0x2
+/* enum: Number of corrected 10-bit symbol errors, lane 0 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE0 0x3
+/* enum: Number of corrected 10-bit symbol errors, lane 1 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE1 0x4
+/* enum: Number of corrected 10-bit symbol errors, lane 2 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE2 0x5
+/* enum: Number of corrected 10-bit symbol errors, lane 3 (RS-FEC only) */
+#define          MC_CMD_STAT_ID_FEC_CORRECTED_SYMBOLS_LANE3 0x6
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_LBN 16
+#define       MC_CMD_STAT_ID_PHY_STAT_ID_WIDTH 16
+
+/* MC_CMD_STAT_DESC structuredef: Structure describing the layout and size of
+ * the stats DMA buffer descriptor.
+ */
+#define    MC_CMD_STAT_DESC_LEN 8
+/* Unique identifier of the statistic. Formatted as MC_CMD_STAT_ID */
+#define       MC_CMD_STAT_DESC_STAT_ID_OFST 0
+#define       MC_CMD_STAT_DESC_STAT_ID_LEN 4
+#define       MC_CMD_STAT_DESC_STAT_ID_LBN 0
+#define       MC_CMD_STAT_DESC_STAT_ID_WIDTH 32
+/* See structuredef: MC_CMD_STAT_ID */
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_OFST 0
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_LBN 0
+#define       MC_CMD_STAT_DESC_STAT_ID_SOURCE_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MARKER_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_MAC_STAT_ID_WIDTH 16
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_OFST 2
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_LBN 16
+#define       MC_CMD_STAT_DESC_STAT_ID_PHY_STAT_ID_WIDTH 16
+/* Index of the statistic in the DMA buffer. */
+#define       MC_CMD_STAT_DESC_STAT_INDEX_OFST 4
+#define       MC_CMD_STAT_DESC_STAT_INDEX_LEN 2
+#define       MC_CMD_STAT_DESC_STAT_INDEX_LBN 32
+#define       MC_CMD_STAT_DESC_STAT_INDEX_WIDTH 16
+/* Reserved for future extension (e.g. flags field) - currently always 0. */
+#define       MC_CMD_STAT_DESC_RESERVED_OFST 6
+#define       MC_CMD_STAT_DESC_RESERVED_LEN 2
+#define       MC_CMD_STAT_DESC_RESERVED_LBN 48
+#define       MC_CMD_STAT_DESC_RESERVED_WIDTH 16
+
+
+/***********************************/
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR
+ * Get a list of descriptors that describe the layout and size of the stats
+ * buffer required for retrieving statistics for a given port. Each entry in
+ * the list is formatted as MC_CMD_STAT_DESC and provides the ID of each stat
+ * and its location and size in the buffer. It also gives the overall minimum
+ * size of the DMA buffer required when DMA mode is used. Note that the first
+ * and last entries in the list are reserved for the generation start
+ * (MC_CMD_MARKER_STAT_GENERATION_START) and end
+ * (MC_CMD_MARKER_STAT_GENERATION_END) markers respectively, to be used for DMA
+ * synchronisation as described in the documentation for the relevant enum
+ * entries. The entries are present in the buffer even if DMA mode is not used.
+ * Provisions are made (but currently unused) for extending the size of the
+ * descriptors, extending the size of the list beyond the maximum MCDI response
+ * size, as well as the dynamic runtime updates of the list. Returns: 0 on
+ * success, ENOENT on non-existent port handle
+ */
+#define MC_CMD_MAC_STATISTICS_DESCRIPTOR 0x1e3
+#undef MC_CMD_0x1e3_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN msgrequest */
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_LEN 8
+/* Handle of port to get MAC statitstics descriptors for. */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_PORT_HANDLE_LEN 4
+/* Offset of the first entry to return, for cases where not all entries fit in
+ * the MCDI response. Should be set to 0 on initial request, and on subsequent
+ * requests updated by the number of entries already returned, as long as the
+ * MORE_ENTRIES flag is set.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_OFFSET_OFST 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_IN_OFFSET_LEN 4
+
+/* MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT msgresponse */
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMIN 28
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMAX 252
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_LEN(num) (20+8*(num))
+#define    MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_NUM(len) (((len)-20)/8)
+/* Generation number of the stats buffer. This is incremented each time the
+ * buffer is updated, and is used to verify the consistency of the buffer
+ * contents. Reserved for future extension (dynamic list updates). Currently
+ * always set to 0.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_GENERATION_OFST 0
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_GENERATION_LEN 4
+/* Minimum size of the DMA buffer required to retrieve all statistics for the
+ * port. This is the sum of the sizes of all the statistics, plus the size of
+ * the generation markers. Minimum buffer size in bytes required to fit all
+ * statistics. Drivers will typically round up this value to the granularity of
+ * the host DMA allocation units.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_DMA_BUFFER_SIZE_OFST 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_DMA_BUFFER_SIZE_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_FLAGS_OFST 8
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_FLAGS_LEN 4
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_OFST 8
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_LBN 0
+#define        MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_MORE_ENTRIES_WIDTH 1
+/* Size of the individual descriptor entry in the list. Determines the entry
+ * stride in the list. Currently always set to size of MC_CMD_STAT_DESC, larger
+ * values can be used in the future for extending the descriptor, by appending
+ * new data to the end of the existing structure.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_SIZE_OFST 12
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_SIZE_LEN 4
+/* Number of entries returned in the descriptor list. */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_COUNT_OFST 16
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRY_COUNT_LEN 4
+/* List of descriptors. Each entry is formatted as MC_CMD_STAT_DESC and
+ * provides the ID of each stat and its location and size in the buffer. The
+ * first and last entries are reserved for the generation start and end markers
+ * respectively.
+ */
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_OFST 20
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LEN 8
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_OFST 20
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_LBN 160
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_LO_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_OFST 24
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_LEN 4
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_LBN 192
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_HI_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MINNUM 1
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MAXNUM 29
+#define       MC_CMD_MAC_STATISTICS_DESCRIPTOR_OUT_ENTRIES_MAXNUM_MCDI2 125
+
+
+/***********************************/
+/* MC_CMD_MAC_STATISTICS
+ * Get generic MAC statistics. This call retrieves unified statistics managed
+ * by the MC. The MC will populate and provide all supported statistics in the
+ * format as returned by MC_CMD_MAC_STATISTICS_DESCRIPTOR. Refer to the
+ * aforementioned command for the format and contents of the stats DMA buffer.
+ * To ensure consistent and accurate results, it is essential for the driver to
+ * initialize the DMA buffer with zeros when DMA mode is used. Returns: 0 on
+ * success, ETIME if the DMA buffer is not ready, ENOENT on non-existent port
+ * handle, and EINVAL on invalid parameters (DMA buffer too small)
+ */
+#define MC_CMD_MAC_STATISTICS 0x1e4
+#undef MC_CMD_0x1e4_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_MAC_STATISTICS_IN msgrequest */
+#define    MC_CMD_MAC_STATISTICS_IN_LEN 20
+/* Handle of port to get MAC statistics for. */
+#define       MC_CMD_MAC_STATISTICS_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_MAC_STATISTICS_IN_PORT_HANDLE_LEN 4
+/* Contains options for querying the MAC statistics. */
+#define       MC_CMD_MAC_STATISTICS_IN_CMD_OFST 4
+#define       MC_CMD_MAC_STATISTICS_IN_CMD_LEN 4
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_LBN 0
+#define        MC_CMD_MAC_STATISTICS_IN_DMA_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_LBN 1
+#define        MC_CMD_MAC_STATISTICS_IN_CLEAR_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_LBN 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_OFST 4
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_LBN 16
+#define        MC_CMD_MAC_STATISTICS_IN_PERIOD_MS_WIDTH 16
+/* This is the address of the DMA buffer to use for transfer of the statistics.
+ * Only valid if the DMA flag is set to 1.
+ */
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_OFST 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_OFST 8
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_LBN 64
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_OFST 12
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_LBN 96
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_ADDR_HI_WIDTH 32
+/* This is the length of the DMA buffer to use for the transfer of the
+ * statistics. The buffer should be at least DMA_BUFFER_SIZE long, as returned
+ * by MC_CMD_MAC_STATISTICS_DESCRIPTOR. If the supplied buffer is too small,
+ * the command will fail with EINVAL. Only valid if the DMA flag is set to 1.
+ */
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_LEN_OFST 16
+#define       MC_CMD_MAC_STATISTICS_IN_DMA_LEN_LEN 4
+
+/* MC_CMD_MAC_STATISTICS_OUT msgresponse */
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMIN 5
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMAX 252
+#define    MC_CMD_MAC_STATISTICS_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_MAC_STATISTICS_OUT_LEN(num) (4+1*(num))
+#define    MC_CMD_MAC_STATISTICS_OUT_DATA_NUM(len) (((len)-4)/1)
+/* length of the data in bytes */
+#define       MC_CMD_MAC_STATISTICS_OUT_DATALEN_OFST 0
+#define       MC_CMD_MAC_STATISTICS_OUT_DATALEN_LEN 4
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_OFST 4
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_LEN 1
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MINNUM 1
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MAXNUM 248
+#define       MC_CMD_MAC_STATISTICS_OUT_DATA_MAXNUM_MCDI2 1016
+
+/* NET_PORT_HANDLE_DESC structuredef: Network port descriptor containing a port
+ * handle and attributes used, for example, in MC_CMD_ENUM_PORTS.
+ */
+#define    NET_PORT_HANDLE_DESC_LEN 53
+/* The handle to identify the port */
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_OFST 0
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_LBN 0
+#define       NET_PORT_HANDLE_DESC_PORT_HANDLE_WIDTH 32
+/* Includes the type of port e.g. physical, virtual or MAE MPORT and other
+ * properties relevant to the port.
+ */
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_OFST 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LEN 8
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_OFST 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_LBN 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LO_WIDTH 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_OFST 8
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_LEN 4
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_LBN 64
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_HI_WIDTH 32
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_OFST 4
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_LBN 0
+#define        NET_PORT_HANDLE_DESC_PORT_TYPE_WIDTH 3
+#define          NET_PORT_HANDLE_DESC_PHYSICAL 0x0 /* enum */
+#define          NET_PORT_HANDLE_DESC_VIRTUAL 0x1 /* enum */
+#define          NET_PORT_HANDLE_DESC_MPORT 0x2 /* enum */
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_OFST 4
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_LBN 8
+#define        NET_PORT_HANDLE_DESC_IS_ZOMBIE_WIDTH 1
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_LBN 32
+#define       NET_PORT_HANDLE_DESC_PORT_PROPERTIES_WIDTH 64
+/* The dynamic change that led to the port enumeration */
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_OFST 12
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_LEN 1
+/* enum: Indicates that the ENTRY_SRC field has not been initialized. */
+#define          NET_PORT_HANDLE_DESC_UNKNOWN 0x0
+/* enum: The port was enumerated at start of day. */
+#define          NET_PORT_HANDLE_DESC_PRESENT 0x1
+/* enum: The port was dynamically added. */
+#define          NET_PORT_HANDLE_DESC_ADDED 0x2
+/* enum: The port was dynamically deleted. */
+#define          NET_PORT_HANDLE_DESC_DELETED 0x3
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_LBN 96
+#define       NET_PORT_HANDLE_DESC_ENTRY_SRC_WIDTH 8
+/* This is an opaque 40 byte label exposed to users as a unique identifier of
+ * the port. It is represented as a zero-terminated ASCII string and assigned
+ * by the port administrator which is typically either the firmware for a
+ * physical port or the host software responsible for creating the virtual
+ * port. The label is conveyed to the driver after assignment, which, unlike
+ * the port administrator, does not need to know how to interpret the label.
+ */
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_OFST 13
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_LEN 40
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_LBN 104
+#define       NET_PORT_HANDLE_DESC_PORT_LABEL_WIDTH 320
+
+
+/***********************************/
+/* MC_CMD_ENUM_PORTS
+ * This command returns handles for all ports present in the system. The PCIe
+ * function type of each port (either physical or virtual) is also reported.
+ * After a start-of-day port enumeration, firmware keeps track of all available
+ * ports upon creation or deletion and updates the ports if there is a change.
+ * This command is cleared after a control interface reset (e.g. FLR,
+ * ENTITY_RESET), in which case it must be called again to reenumerate the
+ * ports. The command is also clear-on-read and repeated calls will drain the
+ * buffer.
+ */
+#define MC_CMD_ENUM_PORTS 0x1e5
+#undef MC_CMD_0x1e5_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e5_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_ENUM_PORTS_IN msgrequest */
+#define    MC_CMD_ENUM_PORTS_IN_LEN 0
+
+/* MC_CMD_ENUM_PORTS_OUT msgresponse */
+#define    MC_CMD_ENUM_PORTS_OUT_LENMIN 12
+#define    MC_CMD_ENUM_PORTS_OUT_LENMAX 252
+#define    MC_CMD_ENUM_PORTS_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_ENUM_PORTS_OUT_LEN(num) (12+1*(num))
+#define    MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_NUM(len) (((len)-12)/1)
+/* Any unused flags are reserved and must be ignored. */
+#define       MC_CMD_ENUM_PORTS_OUT_FLAGS_OFST 0
+#define       MC_CMD_ENUM_PORTS_OUT_FLAGS_LEN 4
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_OFST 0
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_LBN 0
+#define        MC_CMD_ENUM_PORTS_OUT_MORE_WIDTH 1
+/* The number of NET_PORT_HANDLE_DESC structures in PORT_HANDLES. */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_COUNT_OFST 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_COUNT_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_SIZEOF_NET_PORT_HANDLE_DESC_OFST 8
+#define       MC_CMD_ENUM_PORTS_OUT_SIZEOF_NET_PORT_HANDLE_DESC_LEN 4
+/* Array of NET_PORT_HANDLE_DESC structures. Callers must use must use the
+ * SIZEOF_NET_PORT_HANDLE_DESC field field as the array stride between entries.
+ * This may also allow for tail padding for alignment. Fields beyond
+ * SIZEOF_NET_PORT_HANDLE_DESC are not present.
+ */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_OFST 12
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_LEN 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MINNUM 0
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MAXNUM 240
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_MAXNUM_MCDI2 1008
+/* See structuredef: NET_PORT_HANDLE_DESC */
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_HANDLE_OFST 12
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_HANDLE_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_OFST 16
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LEN 8
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_OFST 16
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_LBN 128
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_LO_WIDTH 32
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_OFST 20
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_LEN 4
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_LBN 160
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_PROPERTIES_HI_WIDTH 32
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_TYPE_LBN 128
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_TYPE_WIDTH 3
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_IS_ZOMBIE_LBN 136
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_IS_ZOMBIE_WIDTH 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_ENTRY_SRC_OFST 24
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_ENTRY_SRC_LEN 1
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_LABEL_OFST 25
+#define       MC_CMD_ENUM_PORTS_OUT_PORT_HANDLES_PORT_LABEL_LEN 40
+
+
+/***********************************/
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES
+ * Read properties of the transceiver associated with the port. Can be either
+ * for a fixed onboard transceiver or an inserted module. The returned data is
+ * interpreted from the transceiver hardware and may be fixed up by the
+ * firmware. Use MC_CMD_GET_MODULE_DATA to get raw undecoded data.
+ */
+#define MC_CMD_GET_TRANSCEIVER_PROPERTIES 0x1e6
+#undef MC_CMD_0x1e6_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e6_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN msgrequest */
+#define    MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_LEN 4
+/* Handle to port to get transceiver properties from. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT msgresponse */
+#define    MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LEN 89
+/* Supported technology abilities. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_TECH_ABILITIES_MASK_OFST 0
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_TECH_ABILITIES_MASK_LEN 16
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_ETH_TECH/TECH */
+/* Reserved for future expansion to accommodate future Ethernet technology
+ * expansion.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_RESERVED_OFST 16
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_RESERVED_LEN 16
+/* Preferred FEC modes. This is a function of the cable type and length. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PREFERRED_FEC_MASK_OFST 32
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PREFERRED_FEC_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               FEC_TYPE/TYPE */
+/* SFF-8042 code reported by the module. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CODE_OFST 36
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CODE_LEN 2
+/* Medium. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIUM_OFST 38
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIUM_LEN 1
+/* enum property: value */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_UNKNOWN 0x0 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_COPPER 0x1 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_OPTICAL 0x2 /* enum */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BACKPLANE 0x3 /* enum */
+/* Identifies the tech */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIA_SUBTYPE_OFST 39
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_MEDIA_SUBTYPE_LEN 1
+/* enum property: value */
+/*               MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_UNKNOWN 0x0 */
+/* enum: Ethernet over twisted-pair copper cables for distances up to 100
+ * meters.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BASET 0x1
+/* enum: Ethernet over twin-axial, balanced copper cable. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_CR 0x2
+/* enum: Ethernet over backplane for connections on the same board. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KX 0x3
+/* enum: Ethernet over a single backplane lane for connections between
+ * different boards.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KR 0x4
+/* enum: Ethernet over copper backplane. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_KP 0x5
+/* enum: Ethernet over fiber optic. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_BASEX 0x6
+/* enum: Short range ethernet over multimode fiber optic (See IEEE 802.3 Clause
+ * 49 and 52).
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SR 0x7
+/* enum: Long range, extended range or far reach ethernet used with single mode
+ * fiber optics.
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LR_ER_FR 0x8
+/* enum: Long reach multimode ethernet over multimode optical fiber. */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_LRM 0x9
+/* enum: Very short reach PAM4 ethernet over multimode optical fiber (see IEEE
+ * 802.3db).
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VR 0xa
+/* enum: BASE-R encoding and PAM4 over single-mode fiber with reach up to at
+ * least 500 meters (803.2 Clause 121 and 124)
+ */
+#define          MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_DR 0xb
+/* String of the vendor name as intepreted by NMC firmware. NMC firmware
+ * applies workarounds for known buggy transceivers. The vendor name is
+ * presented as 16 bytes of ASCII characters padded with spaces. It can also be
+ * represented as 16 bytes of zeros if the field is unspecified for the
+ * connected module. See SFF-8472/CMIS specifications for details.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_OFST 40
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_NAME_NUM 16
+/* The vendor part number as intepreted by NMC firmware. The field is presented
+ * as 16 bytes of ASCII chars padded with spaces. It can also be 16 bytes of
+ * zeros if the field is unspecified for the connected module.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_OFST 56
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_VENDOR_PN_NUM 16
+/* Serial number of the module presented as 16 bytes of ASCII characters padded
+ * with spaces. It can also be 16 bytes of zeros if the field is unspecified
+ * for the connected module. See SFF-8472/CMIS specifications for details.
+ */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_OFST 72
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_LEN 1
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_SERIAL_NUMBER_NUM 16
+/* This reports the number of module changes detected by the NMC firmware. */
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PORT_MODULECHANGE_SEQ_NUM_OFST 88
+#define       MC_CMD_GET_TRANSCEIVER_PROPERTIES_OUT_PORT_MODULECHANGE_SEQ_NUM_LEN 1
+
+
+/***********************************/
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES
+ */
+#define MC_CMD_GET_FIXED_PORT_PROPERTIES 0x1e7
+#undef MC_CMD_0x1e7_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e7_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_IN msgrequest: In this context, the port
+ * consists of the MAC and the PHY, and excludes any modules inserted into the
+ * cage. This information is fixed for a given board but not for a given ASIC.
+ * This command reports properties for the port as it is currently configured,
+ * and not its hardware capabilities, which can be better than the current
+ * configuration.
+ */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_LEN 4
+/* Handle to the port to from which to retreive properties */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT msgresponse */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LEN 36
+/* Supported capabilities of the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_LEN 25
+/* See structuredef: MC_CMD_ETH_AN_FIELDS */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_TECH_MASK_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_TECH_MASK_LEN 16
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_MASK_OFST 16
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_MASK_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_REQ_OFST 20
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_FEC_REQ_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_PAUSE_MASK_OFST 24
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_ABILITIES_PAUSE_MASK_LEN 1
+/* Number of lanes supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_NUM_LANES_OFST 25
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_NUM_LANES_LEN 1
+/* Bitmask of supported loopback modes. Where the response to this command
+ * includes the LOOPBACK_MODES_MASK_V2 field, that field should be used in
+ * preference to ensure that all available loopback modes are seen.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LOOPBACK_MODES_MASK_OFST 26
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_LOOPBACK_MODES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* This field serves as a cage index that uniquely identifies the cage to which
+ * the module is connected. This is useful when splitter cables that have
+ * multiple ports on a single cage are used.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_INDEX_OFST 27
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_INDEX_LEN 1
+/* This bitmask is used to specify the lanes within the cage identified by
+ * MDI_INDEX that are allocated to the port.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_LANE_MASK_OFST 28
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MDI_LANE_MASK_LEN 1
+/* Maximum frame length supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MAX_FRAME_LEN_OFST 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_MAX_FRAME_LEN_LEN 4
+
+/* MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2 msgresponse */
+#define    MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LEN 48
+/* Supported capabilities of the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_ABILITIES_OFST 0
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_ABILITIES_LEN 25
+/* Number of lanes supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_NUM_LANES_OFST 25
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_NUM_LANES_LEN 1
+/* Bitmask of supported loopback modes. Where the response to this command
+ * includes the LOOPBACK_MODES_MASK_V2 field, that field should be used in
+ * preference to ensure that all available loopback modes are seen.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_OFST 26
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_LEN 1
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+/* This field serves as a cage index that uniquely identifies the cage to which
+ * the module is connected. This is useful when splitter cables that have
+ * multiple ports on a single cage are used.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_INDEX_OFST 27
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_INDEX_LEN 1
+/* This bitmask is used to specify the lanes within the cage identified by
+ * MDI_INDEX that are allocated to the port.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_LANE_MASK_OFST 28
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MDI_LANE_MASK_LEN 1
+/* Maximum frame length supported by the port in its current configuration. */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MAX_FRAME_LEN_OFST 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_MAX_FRAME_LEN_LEN 4
+/* Bitmask of supported loopback modes. This field replaces the
+ * LOOPBACK_MODES_MASK field which is defined under version 1 of this command.
+ */
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_OFST 40
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LEN 8
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_OFST 40
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_LBN 320
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_LO_WIDTH 32
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_OFST 44
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_LEN 4
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_LBN 352
+#define       MC_CMD_GET_FIXED_PORT_PROPERTIES_OUT_V2_LOOPBACK_MODES_MASK_V2_HI_WIDTH 32
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               MC_CMD_LOOPBACK_V2/MODE */
+
+
+/***********************************/
+/* MC_CMD_GET_MODULE_DATA
+ * Read media-specific data from the PHY (e.g. SFP/SFP+ module ID information
+ * for SFP+ PHYs). This command returns raw data from the module's EEPROM and
+ * it is not interpreted by the MC. Use MC_CMD_GET_TRANSCEIVER_PROPERTIES to
+ * get interpreted data. Return code: 0, ENOENT
+ */
+#define MC_CMD_GET_MODULE_DATA 0x1e8
+#undef MC_CMD_0x1e8_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e8_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_MODULE_DATA_IN msgrequest */
+#define    MC_CMD_GET_MODULE_DATA_IN_LEN 16
+/* Handle to identify the port from which to request module properties. */
+#define       MC_CMD_GET_MODULE_DATA_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_IN_PORT_HANDLE_LEN 4
+/* 7 bit I2C address of the device. DEPRECATED: This field is replaced by
+ * MODULE_ADDR in V2. Use V2 of this command for proper alignment and easier
+ * access.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_DEVADDR_LBN 32
+#define       MC_CMD_GET_MODULE_DATA_IN_DEVADDR_WIDTH 7
+/* 0 if the page does not support banked access, non-zero otherwise. Non-zero
+ * BANK is valid if OFFSET is in the range 80h - ffh, i.e. in the Upper Memory
+ * region.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_BANK_OFST 6
+#define       MC_CMD_GET_MODULE_DATA_IN_BANK_LEN 2
+/* 0 if paged access is not supported, non-zero otherwise. Non-zero PAGE is
+ * valid if OFFSET is in the range 80h - ffh.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_PAGE_OFST 8
+#define       MC_CMD_GET_MODULE_DATA_IN_PAGE_LEN 2
+/* Offset in the range 00h - 7fh to access lower memory. Offset in the range
+ * 80h - ffh to access upper memory
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_OFFSET_OFST 10
+#define       MC_CMD_GET_MODULE_DATA_IN_OFFSET_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_IN_LENGTH_OFST 12
+#define       MC_CMD_GET_MODULE_DATA_IN_LENGTH_LEN 4
+
+/* MC_CMD_GET_MODULE_DATA_IN_V2 msgrequest: Updated MC_CMD_GET_MODULE_DATA with
+ * 8-bit wide ADDRESSING field. This new field provides a correctly aligned
+ * container for the 7-bit DEVADDR field from V1, now renamed MODULE_ADDR, to
+ * ensure proper alignment.
+ */
+#define    MC_CMD_GET_MODULE_DATA_IN_V2_LEN 16
+/* Handle to identify the port from which to request module properties. */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PORT_HANDLE_LEN 4
+/* 7 bit I2C address of the device. DEPRECATED: This field is replaced by
+ * MODULE_ADDR in V2. Use V2 of this command for proper alignment and easier
+ * access.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_DEVADDR_LBN 32
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_DEVADDR_WIDTH 7
+/* 0 if the page does not support banked access, non-zero otherwise. Non-zero
+ * BANK is valid if OFFSET is in the range 80h - ffh, i.e. in the Upper Memory
+ * region.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_BANK_OFST 6
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_BANK_LEN 2
+/* 0 if paged access is not supported, non-zero otherwise. Non-zero PAGE is
+ * valid if OFFSET is in the range 80h - ffh.
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PAGE_OFST 8
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_PAGE_LEN 2
+/* Offset in the range 00h - 7fh to access lower memory. Offset in the range
+ * 80h - ffh to access upper memory
+ */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_OFFSET_OFST 10
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_OFFSET_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_LENGTH_OFST 12
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_LENGTH_LEN 4
+/* Container for 7 bit I2C addresses. */
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_ADDRESSING_OFST 4
+#define       MC_CMD_GET_MODULE_DATA_IN_V2_ADDRESSING_LEN 1
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_OFST 4
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_LBN 0
+#define        MC_CMD_GET_MODULE_DATA_IN_V2_MODULE_ADDR_WIDTH 7
+
+/* MC_CMD_GET_MODULE_DATA_OUT msgresponse */
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMIN 5
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMAX 252
+#define    MC_CMD_GET_MODULE_DATA_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_GET_MODULE_DATA_OUT_LEN(num) (4+1*(num))
+#define    MC_CMD_GET_MODULE_DATA_OUT_DATA_NUM(len) (((len)-4)/1)
+/* length of the data in bytes */
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATALEN_OFST 0
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATALEN_LEN 4
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_OFST 4
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_LEN 1
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MINNUM 1
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MAXNUM 248
+#define       MC_CMD_GET_MODULE_DATA_OUT_DATA_MAXNUM_MCDI2 1016
+
+/* EVENT_MASK structuredef */
+#define    EVENT_MASK_LEN 4
+#define       EVENT_MASK_TYPE_OFST 0
+#define       EVENT_MASK_TYPE_LEN 4
+/* enum: PORT_LINKCHANGE event is enabled */
+#define          EVENT_MASK_PORT_LINKCHANGE 0x0
+/* enum: PORT_MODULECHANGE event is enabled */
+#define          EVENT_MASK_PORT_MODULECHANGE 0x1
+#define       EVENT_MASK_TYPE_LBN 0
+#define       EVENT_MASK_TYPE_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_SET_NETPORT_EVENTS_MASK
+ */
+#define MC_CMD_SET_NETPORT_EVENTS_MASK 0x1e9
+#undef MC_CMD_0x1e9_PRIVILEGE_CTG
+
+#define MC_CMD_0x1e9_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_SET_NETPORT_EVENTS_MASK_IN msgrequest: Enable or disable delivery of
+ * specified network port events for a given port identified by PORT_HANDLE. At
+ * start of day, or after any control interface reset (FLR, ENTITY_RESET,
+ * etc.), all event delivery is disabled for all ports associated with the
+ * control interface.
+ */
+#define    MC_CMD_SET_NETPORT_EVENTS_MASK_IN_LEN 8
+/* Handle to port to set event delivery mask. */
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_LEN 4
+/* Bitmask of events to enable. Event delivery is enabled when corresponding
+ * bit is 1, disabled when 0.
+ */
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_EVENT_MASK_OFST 4
+#define       MC_CMD_SET_NETPORT_EVENTS_MASK_IN_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+/* MC_CMD_SET_NETPORT_EVENTS_MASK_OUT msgresponse */
+#define    MC_CMD_SET_NETPORT_EVENTS_MASK_OUT_LEN 0
+
+
+/***********************************/
+/* MC_CMD_GET_NETPORT_EVENTS_MASK
+ */
+#define MC_CMD_GET_NETPORT_EVENTS_MASK 0x1ea
+#undef MC_CMD_0x1ea_PRIVILEGE_CTG
+
+#define MC_CMD_0x1ea_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_NETPORT_EVENTS_MASK_IN msgrequest: Get event delivery mask a
+ * given port identified by PORT_HANDLE.
+ */
+#define    MC_CMD_GET_NETPORT_EVENTS_MASK_IN_LEN 4
+/* Handle to port to get event deliver mask for. */
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_IN_PORT_HANDLE_LEN 4
+
+/* MC_CMD_GET_NETPORT_EVENTS_MASK_OUT msgresponse */
+#define    MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_LEN 4
+/* Bitmask of events enabled. Event delivery is enabled when corresponding bit
+ * is 1, disabled when 0.
+ */
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_EVENT_MASK_OFST 0
+#define       MC_CMD_GET_NETPORT_EVENTS_MASK_OUT_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+
 /***********************************/
-/* MC_CMD_EVENT_CTRL
- * Configure which categories of unsolicited events the driver expects to
- * receive (Riverhead).
- */
-#define MC_CMD_EVENT_CTRL 0x69
-#undef MC_CMD_0x69_PRIVILEGE_CTG
-
-#define MC_CMD_0x69_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_EVENT_CTRL_IN msgrequest */
-#define    MC_CMD_EVENT_CTRL_IN_LENMIN 0
-#define    MC_CMD_EVENT_CTRL_IN_LENMAX 252
-#define    MC_CMD_EVENT_CTRL_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_EVENT_CTRL_IN_LEN(num) (0+4*(num))
-#define    MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_NUM(len) (((len)-0)/4)
-/* Array of event categories for which the driver wishes to receive events. */
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_OFST 0
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_LEN 4
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MINNUM 0
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MAXNUM 63
-#define       MC_CMD_EVENT_CTRL_IN_EVENT_TYPE_MAXNUM_MCDI2 255
-/* enum: Driver wishes to receive LINKCHANGE events. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_LINKCHANGE 0x0
-/* enum: Driver wishes to receive SENSOR_CHANGE and SENSOR_STATE_CHANGE events.
- */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_SENSOREVT 0x1
-/* enum: Driver wishes to receive receive errors. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_RX_ERR 0x2
-/* enum: Driver wishes to receive transmit errors. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_TX_ERR 0x3
-/* enum: Driver wishes to receive firmware alerts. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_FWALERT 0x4
-/* enum: Driver wishes to receive reboot events. */
-#define          MC_CMD_EVENT_CTRL_IN_MCDI_EVENT_CODE_MC_REBOOT 0x5
-
-/* MC_CMD_EVENT_CTRL_OUT msgrequest */
-#define    MC_CMD_EVENT_CTRL_OUT_LEN 0
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS
+ */
+#define MC_CMD_GET_SUPPORTED_NETPORT_EVENTS 0x1eb
+#undef MC_CMD_0x1eb_PRIVILEGE_CTG
+
+#define MC_CMD_0x1eb_PRIVILEGE_CTG SRIOV_CTG_LINK
+
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_IN msgrequest: Get network port events
+ * supported by the platform. Information returned is fixed for a given NIC
+ * platform.
+ */
+#define    MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_IN_LEN 0
+
+/* MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT msgresponse */
+#define    MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_LEN 4
+/* Bitmask of events enabled. Event delivery is enabled when corresponding bit
+ * is 1, disabled when 0.
+ */
+#define       MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_EVENT_MASK_OFST 0
+#define       MC_CMD_GET_SUPPORTED_NETPORT_EVENTS_OUT_EVENT_MASK_LEN 4
+/* enum property: bitshift */
+/*            Enum values, see field(s): */
+/*               EVENT_MASK/TYPE */
+
+
+/***********************************/
+/* MC_CMD_GET_NETPORT_STATISTICS
+ * Get generic MAC statistics. This call retrieves unified statistics managed
+ * by the MC. The MC will populate and provide all supported statistics in the
+ * format as returned by MC_CMD_MAC_STATISTICS_DESCRIPTOR. Refer to the
+ * aforementioned command for the format and contents of the stats DMA buffer.
+ * To ensure consistent and accurate results, it is essential for the driver to
+ * initialize the DMA buffer with zeros when DMA mode is used. Returns: 0 on
+ * success, ETIME if the DMA buffer is not ready, ENOENT on non-existent port
+ * handle, and EINVAL on invalid parameters (DMA buffer too small)
+ */
+#define MC_CMD_GET_NETPORT_STATISTICS 0x1fa
+#undef MC_CMD_0x1fa_PRIVILEGE_CTG
+
+#define MC_CMD_0x1fa_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_GET_NETPORT_STATISTICS_IN msgrequest */
+#define    MC_CMD_GET_NETPORT_STATISTICS_IN_LEN 20
+/* Handle of port to get MAC statistics for. */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_PORT_HANDLE_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_PORT_HANDLE_LEN 4
+/* Contains options for querying the MAC statistics. */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_CMD_OFST 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_CMD_LEN 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LBN 0
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_LBN 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_CLEAR_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_LBN 2
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_CHANGE_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_LBN 3
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_ENABLE_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_LBN 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIODIC_NOEVENT_WIDTH 1
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_OFST 4
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_LBN 15
+#define        MC_CMD_GET_NETPORT_STATISTICS_IN_PERIOD_MS_WIDTH 17
+/* Specifies the physical address of the DMA buffer to use for statistics
+ * transfer. This field must contain a valid address under either of these
+ * conditions: 1. DMA flag is set (immediate DMA requested) 2. Both
+ * PERIODIC_CHANGE and PERIODIC_ENABLE are set (periodic DMA configured)
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_OFST 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LEN 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_OFST 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_LBN 64
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_LO_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_OFST 12
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_LBN 96
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_ADDR_HI_WIDTH 32
+/* Specifies the length of the DMA buffer in bytes for statistics transfer. The
+ * buffer size must be at least DMA_BUFFER_SIZE bytes (as returned by
+ * MC_CMD_MAC_STATISTICS_DESCRIPTOR). Providing an insufficient buffer size
+ * will result in an EINVAL error. This field must contain a valid length under
+ * either of these conditions: 1. DMA flag is set (immediate DMA requested) 2.
+ * Both PERIODIC_CHANGE and PERIODIC_ENABLE are set (periodic DMA configured)
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LEN_OFST 16
+#define       MC_CMD_GET_NETPORT_STATISTICS_IN_DMA_LEN_LEN 4
+
+/* MC_CMD_GET_NETPORT_STATISTICS_OUT msgresponse */
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMIN 0
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMAX 248
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LENMAX_MCDI2 1016
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_LEN(num) (0+8*(num))
+#define    MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_NUM(len) (((len)-0)/8)
+/* Statistics buffer. Zero-length if DMA mode is used. The statistics buffer is
+ * an array of 8-byte counter values, containing the generation start marker,
+ * stats counters, and generation end marker. The index of each counter in the
+ * array is reported by the MAC_STATISTICS_DESCRIPTOR command. The same layout
+ * is used for the DMA buffer for DMA mode stats.
+ */
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LEN 8
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_OFST 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_LBN 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_LO_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_OFST 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_LEN 4
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_LBN 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_HI_WIDTH 32
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MINNUM 0
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MAXNUM 31
+#define       MC_CMD_GET_NETPORT_STATISTICS_OUT_STATS_MAXNUM_MCDI2 127
 
 /* EVB_PORT_ID structuredef */
 #define    EVB_PORT_ID_LEN 4
@@ -9706,44 +10573,6 @@
 #define       EVB_PORT_ID_PORT_ID_LBN 0
 #define       EVB_PORT_ID_PORT_ID_WIDTH 32
 
-/* EVB_VLAN_TAG structuredef */
-#define    EVB_VLAN_TAG_LEN 2
-/* The VLAN tag value */
-#define       EVB_VLAN_TAG_VLAN_ID_LBN 0
-#define       EVB_VLAN_TAG_VLAN_ID_WIDTH 12
-#define       EVB_VLAN_TAG_MODE_LBN 12
-#define       EVB_VLAN_TAG_MODE_WIDTH 4
-/* enum: Insert the VLAN. */
-#define          EVB_VLAN_TAG_INSERT 0x0
-/* enum: Replace the VLAN if already present. */
-#define          EVB_VLAN_TAG_REPLACE 0x1
-
-/* BUFTBL_ENTRY structuredef */
-#define    BUFTBL_ENTRY_LEN 12
-/* the owner ID */
-#define       BUFTBL_ENTRY_OID_OFST 0
-#define       BUFTBL_ENTRY_OID_LEN 2
-#define       BUFTBL_ENTRY_OID_LBN 0
-#define       BUFTBL_ENTRY_OID_WIDTH 16
-/* the page parameter as one of ESE_DZ_SMC_PAGE_SIZE_ */
-#define       BUFTBL_ENTRY_PGSZ_OFST 2
-#define       BUFTBL_ENTRY_PGSZ_LEN 2
-#define       BUFTBL_ENTRY_PGSZ_LBN 16
-#define       BUFTBL_ENTRY_PGSZ_WIDTH 16
-/* the raw 64-bit address field from the SMC, not adjusted for page size */
-#define       BUFTBL_ENTRY_RAWADDR_OFST 4
-#define       BUFTBL_ENTRY_RAWADDR_LEN 8
-#define       BUFTBL_ENTRY_RAWADDR_LO_OFST 4
-#define       BUFTBL_ENTRY_RAWADDR_LO_LEN 4
-#define       BUFTBL_ENTRY_RAWADDR_LO_LBN 32
-#define       BUFTBL_ENTRY_RAWADDR_LO_WIDTH 32
-#define       BUFTBL_ENTRY_RAWADDR_HI_OFST 8
-#define       BUFTBL_ENTRY_RAWADDR_HI_LEN 4
-#define       BUFTBL_ENTRY_RAWADDR_HI_LBN 64
-#define       BUFTBL_ENTRY_RAWADDR_HI_WIDTH 32
-#define       BUFTBL_ENTRY_RAWADDR_LBN 32
-#define       BUFTBL_ENTRY_RAWADDR_WIDTH 64
-
 /* NVRAM_PARTITION_TYPE structuredef */
 #define    NVRAM_PARTITION_TYPE_LEN 2
 #define       NVRAM_PARTITION_TYPE_ID_OFST 0
@@ -9787,6 +10616,8 @@
 #define          NVRAM_PARTITION_TYPE_NMC_LOG 0x700
 /* enum: Non-volatile log output of second core on dual-core device */
 #define          NVRAM_PARTITION_TYPE_LOG_SLAVE 0x701
+/* enum: RAM (volatile) log output partition */
+#define          NVRAM_PARTITION_TYPE_RAM_LOG 0x702
 /* enum: Device state dump output partition */
 #define          NVRAM_PARTITION_TYPE_DUMP 0x800
 /* enum: Crash log partition for NMC firmware */
@@ -9923,6 +10754,16 @@
 #define          NVRAM_PARTITION_TYPE_SUC_SOC_CONFIG 0x1f07
 /* enum: System-on-Chip update information. */
 #define          NVRAM_PARTITION_TYPE_SOC_UPDATE 0x2003
+/* enum: Virtual partition. Write-only. Writes will actually be sent to an
+ * appropriate partition (for instance BUNDLE if the data starts with the magic
+ * number for a bundle update), or discarded with an error if not recognised as
+ * a supported type.
+ */
+#define          NVRAM_PARTITION_TYPE_AUTO 0x2100
+/* enum: MC/NMC (first stage) bootloader firmware. (For X4, see XN-202072-PS
+ * and XN-202084-SW section 3.1).
+ */
+#define          NVRAM_PARTITION_TYPE_BOOTLOADER 0x2200
 /* enum: Start of reserved value range (firmware may use for any purpose) */
 #define          NVRAM_PARTITION_TYPE_RESERVED_VALUES_MIN 0xff00
 /* enum: End of reserved value range (firmware may use for any purpose) */
@@ -9981,116 +10822,6 @@
 #define       LICENSED_APP_ID_ID_LBN 0
 #define       LICENSED_APP_ID_ID_WIDTH 32
 
-/* LICENSED_FEATURES structuredef */
-#define    LICENSED_FEATURES_LEN 8
-/* Bitmask of licensed firmware features */
-#define       LICENSED_FEATURES_MASK_OFST 0
-#define       LICENSED_FEATURES_MASK_LEN 8
-#define       LICENSED_FEATURES_MASK_LO_OFST 0
-#define       LICENSED_FEATURES_MASK_LO_LEN 4
-#define       LICENSED_FEATURES_MASK_LO_LBN 0
-#define       LICENSED_FEATURES_MASK_LO_WIDTH 32
-#define       LICENSED_FEATURES_MASK_HI_OFST 4
-#define       LICENSED_FEATURES_MASK_HI_LEN 4
-#define       LICENSED_FEATURES_MASK_HI_LBN 32
-#define       LICENSED_FEATURES_MASK_HI_WIDTH 32
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_OFST 0
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_LBN 0
-#define        LICENSED_FEATURES_RX_CUT_THROUGH_WIDTH 1
-#define        LICENSED_FEATURES_PIO_OFST 0
-#define        LICENSED_FEATURES_PIO_LBN 1
-#define        LICENSED_FEATURES_PIO_WIDTH 1
-#define        LICENSED_FEATURES_EVQ_TIMER_OFST 0
-#define        LICENSED_FEATURES_EVQ_TIMER_LBN 2
-#define        LICENSED_FEATURES_EVQ_TIMER_WIDTH 1
-#define        LICENSED_FEATURES_CLOCK_OFST 0
-#define        LICENSED_FEATURES_CLOCK_LBN 3
-#define        LICENSED_FEATURES_CLOCK_WIDTH 1
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_OFST 0
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_LBN 4
-#define        LICENSED_FEATURES_RX_TIMESTAMPS_WIDTH 1
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_OFST 0
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_LBN 5
-#define        LICENSED_FEATURES_TX_TIMESTAMPS_WIDTH 1
-#define        LICENSED_FEATURES_RX_SNIFF_OFST 0
-#define        LICENSED_FEATURES_RX_SNIFF_LBN 6
-#define        LICENSED_FEATURES_RX_SNIFF_WIDTH 1
-#define        LICENSED_FEATURES_TX_SNIFF_OFST 0
-#define        LICENSED_FEATURES_TX_SNIFF_LBN 7
-#define        LICENSED_FEATURES_TX_SNIFF_WIDTH 1
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_OFST 0
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_LBN 8
-#define        LICENSED_FEATURES_PROXY_FILTER_OPS_WIDTH 1
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_OFST 0
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_LBN 9
-#define        LICENSED_FEATURES_EVENT_CUT_THROUGH_WIDTH 1
-#define       LICENSED_FEATURES_MASK_LBN 0
-#define       LICENSED_FEATURES_MASK_WIDTH 64
-
-/* LICENSED_V3_APPS structuredef */
-#define    LICENSED_V3_APPS_LEN 8
-/* Bitmask of licensed applications */
-#define       LICENSED_V3_APPS_MASK_OFST 0
-#define       LICENSED_V3_APPS_MASK_LEN 8
-#define       LICENSED_V3_APPS_MASK_LO_OFST 0
-#define       LICENSED_V3_APPS_MASK_LO_LEN 4
-#define       LICENSED_V3_APPS_MASK_LO_LBN 0
-#define       LICENSED_V3_APPS_MASK_LO_WIDTH 32
-#define       LICENSED_V3_APPS_MASK_HI_OFST 4
-#define       LICENSED_V3_APPS_MASK_HI_LEN 4
-#define       LICENSED_V3_APPS_MASK_HI_LBN 32
-#define       LICENSED_V3_APPS_MASK_HI_WIDTH 32
-#define        LICENSED_V3_APPS_ONLOAD_OFST 0
-#define        LICENSED_V3_APPS_ONLOAD_LBN 0
-#define        LICENSED_V3_APPS_ONLOAD_WIDTH 1
-#define        LICENSED_V3_APPS_PTP_OFST 0
-#define        LICENSED_V3_APPS_PTP_LBN 1
-#define        LICENSED_V3_APPS_PTP_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_LBN 2
-#define        LICENSED_V3_APPS_SOLARCAPTURE_PRO_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARSECURE_OFST 0
-#define        LICENSED_V3_APPS_SOLARSECURE_LBN 3
-#define        LICENSED_V3_APPS_SOLARSECURE_WIDTH 1
-#define        LICENSED_V3_APPS_PERF_MONITOR_OFST 0
-#define        LICENSED_V3_APPS_PERF_MONITOR_LBN 4
-#define        LICENSED_V3_APPS_PERF_MONITOR_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_LBN 5
-#define        LICENSED_V3_APPS_SOLARCAPTURE_LIVE_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_LBN 6
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_WIDTH 1
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_OFST 0
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_LBN 7
-#define        LICENSED_V3_APPS_NETWORK_ACCESS_CONTROL_WIDTH 1
-#define        LICENSED_V3_APPS_TCP_DIRECT_OFST 0
-#define        LICENSED_V3_APPS_TCP_DIRECT_LBN 8
-#define        LICENSED_V3_APPS_TCP_DIRECT_WIDTH 1
-#define        LICENSED_V3_APPS_LOW_LATENCY_OFST 0
-#define        LICENSED_V3_APPS_LOW_LATENCY_LBN 9
-#define        LICENSED_V3_APPS_LOW_LATENCY_WIDTH 1
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_OFST 0
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_LBN 10
-#define        LICENSED_V3_APPS_SOLARCAPTURE_TAP_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_LBN 11
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_40G_WIDTH 1
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_OFST 0
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_LBN 12
-#define        LICENSED_V3_APPS_CAPTURE_SOLARSYSTEM_1G_WIDTH 1
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_OFST 0
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_LBN 13
-#define        LICENSED_V3_APPS_SCALEOUT_ONLOAD_WIDTH 1
-#define        LICENSED_V3_APPS_DSHBRD_OFST 0
-#define        LICENSED_V3_APPS_DSHBRD_LBN 14
-#define        LICENSED_V3_APPS_DSHBRD_WIDTH 1
-#define        LICENSED_V3_APPS_SCATRD_OFST 0
-#define        LICENSED_V3_APPS_SCATRD_LBN 15
-#define        LICENSED_V3_APPS_SCATRD_WIDTH 1
-#define       LICENSED_V3_APPS_MASK_LBN 0
-#define       LICENSED_V3_APPS_MASK_WIDTH 64
-
 /* LICENSED_V3_FEATURES structuredef */
 #define    LICENSED_V3_FEATURES_LEN 8
 /* Bitmask of licensed firmware features */
@@ -10199,44 +10930,6 @@
 #define       RSS_MODE_HASH_SELECTOR_LBN 0
 #define       RSS_MODE_HASH_SELECTOR_WIDTH 8
 
-/* CTPIO_STATS_MAP structuredef */
-#define    CTPIO_STATS_MAP_LEN 4
-/* The (function relative) VI number */
-#define       CTPIO_STATS_MAP_VI_OFST 0
-#define       CTPIO_STATS_MAP_VI_LEN 2
-#define       CTPIO_STATS_MAP_VI_LBN 0
-#define       CTPIO_STATS_MAP_VI_WIDTH 16
-/* The target bucket for the VI */
-#define       CTPIO_STATS_MAP_BUCKET_OFST 2
-#define       CTPIO_STATS_MAP_BUCKET_LEN 2
-#define       CTPIO_STATS_MAP_BUCKET_LBN 16
-#define       CTPIO_STATS_MAP_BUCKET_WIDTH 16
-
-
-/***********************************/
-/* MC_CMD_READ_REGS
- * Get a dump of the MCPU registers
- */
-#define MC_CMD_READ_REGS 0x50
-#undef MC_CMD_0x50_PRIVILEGE_CTG
-
-#define MC_CMD_0x50_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_REGS_IN msgrequest */
-#define    MC_CMD_READ_REGS_IN_LEN 0
-
-/* MC_CMD_READ_REGS_OUT msgresponse */
-#define    MC_CMD_READ_REGS_OUT_LEN 308
-/* Whether the corresponding register entry contains a valid value */
-#define       MC_CMD_READ_REGS_OUT_MASK_OFST 0
-#define       MC_CMD_READ_REGS_OUT_MASK_LEN 16
-/* Same order as MIPS GDB (r0-r31, sr, lo, hi, bad, cause, 32 x float, fsr,
- * fir, fp)
- */
-#define       MC_CMD_READ_REGS_OUT_REGS_OFST 16
-#define       MC_CMD_READ_REGS_OUT_REGS_LEN 4
-#define       MC_CMD_READ_REGS_OUT_REGS_NUM 73
-
 
 /***********************************/
 /* MC_CMD_INIT_EVQ
@@ -10640,25 +11333,6 @@
 #define        MC_CMD_INIT_EVQ_V3_OUT_FLAG_RXQ_FORCE_EV_MERGING_LBN 3
 #define        MC_CMD_INIT_EVQ_V3_OUT_FLAG_RXQ_FORCE_EV_MERGING_WIDTH 1
 
-/* QUEUE_CRC_MODE structuredef */
-#define    QUEUE_CRC_MODE_LEN 1
-#define       QUEUE_CRC_MODE_MODE_LBN 0
-#define       QUEUE_CRC_MODE_MODE_WIDTH 4
-/* enum: No CRC. */
-#define          QUEUE_CRC_MODE_NONE 0x0
-/* enum: CRC Fiber channel over ethernet. */
-#define          QUEUE_CRC_MODE_FCOE 0x1
-/* enum: CRC (digest) iSCSI header only. */
-#define          QUEUE_CRC_MODE_ISCSI_HDR 0x2
-/* enum: CRC (digest) iSCSI header and payload. */
-#define          QUEUE_CRC_MODE_ISCSI 0x3
-/* enum: CRC Fiber channel over IP over ethernet. */
-#define          QUEUE_CRC_MODE_FCOIPOE 0x4
-/* enum: CRC MPA. */
-#define          QUEUE_CRC_MODE_MPA 0x5
-#define       QUEUE_CRC_MODE_SPARE_LBN 4
-#define       QUEUE_CRC_MODE_SPARE_WIDTH 4
-
 
 /***********************************/
 /* MC_CMD_INIT_RXQ
@@ -10827,6 +11501,9 @@
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_EXT_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_EXT_IN_OWNER_ID_LEN 4
@@ -10933,6 +11610,9 @@
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V3_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V3_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V3_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V3_IN_OWNER_ID_LEN 4
@@ -11068,6 +11748,9 @@
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V4_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V4_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V4_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V4_IN_OWNER_ID_LEN 4
@@ -11216,6 +11899,9 @@
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_OFST 16
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_LBN 20
 #define        MC_CMD_INIT_RXQ_V5_IN_FLAG_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_OFST 16
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_LBN 21
+#define        MC_CMD_INIT_RXQ_V5_IN_FLAG_SUPPRESS_RX_EVENTS_WIDTH 1
 /* Owner ID to use if in buffer mode (zero if physical) */
 #define       MC_CMD_INIT_RXQ_V5_IN_OWNER_ID_OFST 20
 #define       MC_CMD_INIT_RXQ_V5_IN_OWNER_ID_LEN 4
@@ -11610,320 +12296,6 @@
 /* MC_CMD_PROXY_CMD_OUT msgresponse */
 #define    MC_CMD_PROXY_CMD_OUT_LEN 0
 
-/* MC_PROXY_STATUS_BUFFER structuredef: Host memory status buffer used to
- * manage proxied requests
- */
-#define    MC_PROXY_STATUS_BUFFER_LEN 16
-/* Handle allocated by the firmware for this proxy transaction */
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_OFST 0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_LEN 4
-/* enum: An invalid handle. */
-#define          MC_PROXY_STATUS_BUFFER_HANDLE_INVALID 0x0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_LBN 0
-#define       MC_PROXY_STATUS_BUFFER_HANDLE_WIDTH 32
-/* The requesting physical function number */
-#define       MC_PROXY_STATUS_BUFFER_PF_OFST 4
-#define       MC_PROXY_STATUS_BUFFER_PF_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_PF_LBN 32
-#define       MC_PROXY_STATUS_BUFFER_PF_WIDTH 16
-/* The requesting virtual function number. Set to VF_NULL if the target is a
- * PF.
- */
-#define       MC_PROXY_STATUS_BUFFER_VF_OFST 6
-#define       MC_PROXY_STATUS_BUFFER_VF_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_VF_LBN 48
-#define       MC_PROXY_STATUS_BUFFER_VF_WIDTH 16
-/* The target function RID. */
-#define       MC_PROXY_STATUS_BUFFER_RID_OFST 8
-#define       MC_PROXY_STATUS_BUFFER_RID_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_RID_LBN 64
-#define       MC_PROXY_STATUS_BUFFER_RID_WIDTH 16
-/* The status of the proxy as described in MC_CMD_PROXY_COMPLETE. */
-#define       MC_PROXY_STATUS_BUFFER_STATUS_OFST 10
-#define       MC_PROXY_STATUS_BUFFER_STATUS_LEN 2
-#define       MC_PROXY_STATUS_BUFFER_STATUS_LBN 80
-#define       MC_PROXY_STATUS_BUFFER_STATUS_WIDTH 16
-/* If a request is authorized rather than carried out by the host, this is the
- * elevated privilege mask granted to the requesting function.
- */
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_OFST 12
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_LEN 4
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_LBN 96
-#define       MC_PROXY_STATUS_BUFFER_GRANTED_PRIVILEGES_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_PROXY_CONFIGURE
- * Enable/disable authorization of MCDI requests from unprivileged functions by
- * a designated admin function
- */
-#define MC_CMD_PROXY_CONFIGURE 0x58
-#undef MC_CMD_0x58_PRIVILEGE_CTG
-
-#define MC_CMD_0x58_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PROXY_CONFIGURE_IN msgrequest */
-#define    MC_CMD_PROXY_CONFIGURE_IN_LEN 108
-#define       MC_CMD_PROXY_CONFIGURE_IN_FLAGS_OFST 0
-#define       MC_CMD_PROXY_CONFIGURE_IN_FLAGS_LEN 4
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_OFST 0
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_LBN 0
-#define        MC_CMD_PROXY_CONFIGURE_IN_ENABLE_WIDTH 1
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REQUEST_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_LBN 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_OFST 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_LBN 64
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BLOCK_SIZE_OFST 12
-#define       MC_CMD_PROXY_CONFIGURE_IN_STATUS_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REPLY_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_LBN 128
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_OFST 20
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_LBN 160
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BLOCK_SIZE_OFST 24
-#define       MC_CMD_PROXY_CONFIGURE_IN_REQUEST_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
- * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
- */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_LBN 224
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_OFST 32
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_LBN 256
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2, or zero if this buffer is not provided */
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BLOCK_SIZE_OFST 36
-#define       MC_CMD_PROXY_CONFIGURE_IN_REPLY_BLOCK_SIZE_LEN 4
-/* Applies to all three buffers */
-#define       MC_CMD_PROXY_CONFIGURE_IN_NUM_BLOCKS_OFST 40
-#define       MC_CMD_PROXY_CONFIGURE_IN_NUM_BLOCKS_LEN 4
-/* A bit mask defining which MCDI operations may be proxied */
-#define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_OFST 44
-#define       MC_CMD_PROXY_CONFIGURE_IN_ALLOWED_MCDI_MASK_LEN 64
-
-/* MC_CMD_PROXY_CONFIGURE_EXT_IN msgrequest */
-#define    MC_CMD_PROXY_CONFIGURE_EXT_IN_LEN 112
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_OFST 0
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_FLAGS_LEN 4
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_OFST 0
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_LBN 0
-#define        MC_CMD_PROXY_CONFIGURE_EXT_IN_ENABLE_WIDTH 1
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REQUEST_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_OFST 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_LBN 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_OFST 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_LBN 64
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_OFST 12
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_STATUS_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size REPLY_BLOCK_SIZE.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_OFST 16
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_LBN 128
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_OFST 20
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_LBN 160
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2 */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_OFST 24
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REQUEST_BLOCK_SIZE_LEN 4
-/* Host provides a contiguous memory buffer that contains at least NUM_BLOCKS
- * of blocks, each of the size STATUS_BLOCK_SIZE. This buffer is only needed if
- * host intends to complete proxied operations by using MC_CMD_PROXY_CMD.
- */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LEN 8
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_OFST 28
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_LBN 224
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_LO_WIDTH 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_OFST 32
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_LEN 4
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_LBN 256
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BUFF_ADDR_HI_WIDTH 32
-/* Must be a power of 2, or zero if this buffer is not provided */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_OFST 36
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_REPLY_BLOCK_SIZE_LEN 4
-/* Applies to all three buffers */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_OFST 40
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_NUM_BLOCKS_LEN 4
-/* A bit mask defining which MCDI operations may be proxied */
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_OFST 44
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_ALLOWED_MCDI_MASK_LEN 64
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_OFST 108
-#define       MC_CMD_PROXY_CONFIGURE_EXT_IN_RESERVED_LEN 4
-
-/* MC_CMD_PROXY_CONFIGURE_OUT msgresponse */
-#define    MC_CMD_PROXY_CONFIGURE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PROXY_COMPLETE
- * Tells FW that a requested proxy operation has either been completed (by
- * using MC_CMD_PROXY_CMD) or authorized/declined. May only be sent by the
- * function that enabled proxying/authorization (by using
- * MC_CMD_PROXY_CONFIGURE).
- */
-#define MC_CMD_PROXY_COMPLETE 0x5f
-#undef MC_CMD_0x5f_PRIVILEGE_CTG
-
-#define MC_CMD_0x5f_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PROXY_COMPLETE_IN msgrequest */
-#define    MC_CMD_PROXY_COMPLETE_IN_LEN 12
-#define       MC_CMD_PROXY_COMPLETE_IN_BLOCK_INDEX_OFST 0
-#define       MC_CMD_PROXY_COMPLETE_IN_BLOCK_INDEX_LEN 4
-#define       MC_CMD_PROXY_COMPLETE_IN_STATUS_OFST 4
-#define       MC_CMD_PROXY_COMPLETE_IN_STATUS_LEN 4
-/* enum: The operation has been completed by using MC_CMD_PROXY_CMD, the reply
- * is stored in the REPLY_BUFF.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_COMPLETE 0x0
-/* enum: The operation has been authorized. The originating function may now
- * try again.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_AUTHORIZED 0x1
-/* enum: The operation has been declined. */
-#define          MC_CMD_PROXY_COMPLETE_IN_DECLINED 0x2
-/* enum: The authorization failed because the relevant application did not
- * respond in time.
- */
-#define          MC_CMD_PROXY_COMPLETE_IN_TIMEDOUT 0x3
-#define       MC_CMD_PROXY_COMPLETE_IN_HANDLE_OFST 8
-#define       MC_CMD_PROXY_COMPLETE_IN_HANDLE_LEN 4
-
-/* MC_CMD_PROXY_COMPLETE_OUT msgresponse */
-#define    MC_CMD_PROXY_COMPLETE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_ALLOC_BUFTBL_CHUNK
- * Allocate a set of buffer table entries using the specified owner ID. This
- * operation allocates the required buffer table entries (and fails if it
- * cannot do so). The buffer table entries will initially be zeroed.
- */
-#define MC_CMD_ALLOC_BUFTBL_CHUNK 0x87
-#undef MC_CMD_0x87_PRIVILEGE_CTG
-
-#define MC_CMD_0x87_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ALLOC_BUFTBL_CHUNK_IN msgrequest */
-#define    MC_CMD_ALLOC_BUFTBL_CHUNK_IN_LEN 8
-/* Owner ID to use */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_OWNER_OFST 0
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_OWNER_LEN 4
-/* Size of buffer table pages to use, in bytes (note that only a few values are
- * legal on any specific hardware).
- */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_PAGE_SIZE_OFST 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_IN_PAGE_SIZE_LEN 4
-
-/* MC_CMD_ALLOC_BUFTBL_CHUNK_OUT msgresponse */
-#define    MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_LEN 12
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_HANDLE_OFST 0
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_HANDLE_LEN 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_NUMENTRIES_OFST 4
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_NUMENTRIES_LEN 4
-/* Buffer table IDs for use in DMA descriptors. */
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_ID_OFST 8
-#define       MC_CMD_ALLOC_BUFTBL_CHUNK_OUT_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES
- * Reprogram a set of buffer table entries in the specified chunk.
- */
-#define MC_CMD_PROGRAM_BUFTBL_ENTRIES 0x88
-#undef MC_CMD_0x88_PRIVILEGE_CTG
-
-#define MC_CMD_0x88_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN msgrequest */
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMIN 20
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 268
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX_MCDI2 268
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LEN(num) (12+8*(num))
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_NUM(len) (((len)-12)/8)
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_OFST 0
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_LEN 4
-/* ID */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_FIRSTID_OFST 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_FIRSTID_LEN 4
-/* Num entries */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 8
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_NUMENTRIES_LEN 4
-/* Buffer table entry address */
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_OFST 12
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LEN 8
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_OFST 12
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_LEN 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_LBN 96
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_WIDTH 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_OFST 16
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_LEN 4
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_LBN 128
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_WIDTH 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MINNUM 1
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM 32
-#define       MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM_MCDI2 32
-
-/* MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT msgresponse */
-#define    MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_FREE_BUFTBL_CHUNK
- */
-#define MC_CMD_FREE_BUFTBL_CHUNK 0x89
-#undef MC_CMD_0x89_PRIVILEGE_CTG
-
-#define MC_CMD_0x89_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_FREE_BUFTBL_CHUNK_IN msgrequest */
-#define    MC_CMD_FREE_BUFTBL_CHUNK_IN_LEN 4
-#define       MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_OFST 0
-#define       MC_CMD_FREE_BUFTBL_CHUNK_IN_HANDLE_LEN 4
-
-/* MC_CMD_FREE_BUFTBL_CHUNK_OUT msgresponse */
-#define    MC_CMD_FREE_BUFTBL_CHUNK_OUT_LEN 0
-
 
 /***********************************/
 /* MC_CMD_FILTER_OP
@@ -12822,6 +13194,10 @@
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_VNIC_ENCAP_MATCHES 0x5
 /* enum: read the supported encapsulation types for the VNIC */
 #define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_VNIC_ENCAP_TYPES 0x6
+/* enum: read the supported RX filter matches for low-latency queues (as
+ * allocated by MC_CMD_ALLOC_LL_QUEUES)
+ */
+#define          MC_CMD_GET_PARSER_DISP_INFO_IN_OP_GET_SUPPORTED_LL_RX_MATCHES 0x7
 
 /* MC_CMD_GET_PARSER_DISP_INFO_OUT msgresponse */
 #define    MC_CMD_GET_PARSER_DISP_INFO_OUT_LENMIN 8
@@ -12860,6 +13236,48 @@
 #define        MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_LBN 0
 #define        MC_CMD_GET_PARSER_DISP_RESTRICTIONS_OUT_DST_IP_MCAST_ONLY_WIDTH 1
 
+/* MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT msgresponse:
+ * GET_PARSER_DISP_INFO response format for OP_GET_SECURITY_RULE_INFO.
+ * (Medford-only; for use by SolarSecure apps, not directly by drivers. See
+ * SF-114946-SW.) NOTE - this message definition is provisional. It has not yet
+ * been used in any released code and may change during development. This note
+ * will be removed once it is regarded as stable.
+ */
+#define    MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_LEN 36
+/* identifies the type of operation requested */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_OP_OFST 0
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_OP_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_GET_PARSER_DISP_INFO_IN/OP */
+/* a version number representing the set of rule lookups that are implemented
+ * by the currently running firmware
+ */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_OFST 4
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_LEN 4
+/* enum: implements lookup sequences described in SF-114946-SW draft C */
+#define          MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_RULES_VERSION_SF_114946_SW_C 0x0
+/* the number of nodes in the subnet map */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_NODES_OFST 8
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_NODES_LEN 4
+/* the number of entries in one subnet map node */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_ENTRIES_PER_NODE_OFST 12
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_MAP_NUM_ENTRIES_PER_NODE_LEN 4
+/* minimum valid value for a subnet ID in a subnet map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MIN_OFST 16
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MIN_LEN 4
+/* maximum valid value for a subnet ID in a subnet map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MAX_OFST 20
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_SUBNET_ID_MAX_LEN 4
+/* the number of entries in the local and remote port range maps */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_TREE_NUM_ENTRIES_OFST 24
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_TREE_NUM_ENTRIES_LEN 4
+/* minimum valid value for a portrange ID in a port range map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MIN_OFST 28
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MIN_LEN 4
+/* maximum valid value for a portrange ID in a port range map leaf */
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MAX_OFST 32
+#define       MC_CMD_GET_PARSER_DISP_SECURITY_RULE_INFO_OUT_PORTRANGE_ID_MAX_LEN 4
+
 /* MC_CMD_GET_PARSER_DISP_VNIC_ENCAP_MATCHES_OUT msgresponse: This response is
  * returned if a MC_CMD_GET_PARSER_DISP_INFO_IN request is sent with OP value
  * OP_GET_SUPPORTED_VNIC_ENCAP_MATCHES. It contains information about the
@@ -12913,136 +13331,6 @@
 #define        MC_CMD_GET_PARSER_DISP_SUPPORTED_VNIC_ENCAP_TYPES_OUT_ENCAP_TYPE_L2GRE_WIDTH 1
 
 
-/***********************************/
-/* MC_CMD_PARSER_DISP_RW
- * Direct read/write of parser-dispatcher state (DICPUs and LUE) for debugging.
- * Please note that this interface is only of use to debug tools which have
- * knowledge of firmware and hardware data structures; nothing here is intended
- * for use by normal driver code. Note that although this command is in the
- * Admin privilege group, in tamperproof adapters, only read operations are
- * permitted.
- */
-#define MC_CMD_PARSER_DISP_RW 0xe5
-#undef MC_CMD_0xe5_PRIVILEGE_CTG
-
-#define MC_CMD_0xe5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PARSER_DISP_RW_IN msgrequest */
-#define    MC_CMD_PARSER_DISP_RW_IN_LEN 32
-/* identifies the target of the operation */
-#define       MC_CMD_PARSER_DISP_RW_IN_TARGET_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_IN_TARGET_LEN 4
-/* enum: RX dispatcher CPU */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX_DICPU 0x0
-/* enum: TX dispatcher CPU */
-#define          MC_CMD_PARSER_DISP_RW_IN_TX_DICPU 0x1
-/* enum: Lookup engine (with original metadata format). Deprecated; used only
- * by cmdclient as a fallback for very old Huntington firmware, and not
- * supported in firmware beyond v6.4.0.1005. Use LUE_VERSIONED_METADATA
- * instead.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_LUE 0x2
-/* enum: Lookup engine (with requested metadata format) */
-#define          MC_CMD_PARSER_DISP_RW_IN_LUE_VERSIONED_METADATA 0x3
-/* enum: RX0 dispatcher CPU (alias for RX_DICPU; Medford has 2 RX DICPUs) */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX0_DICPU 0x0
-/* enum: RX1 dispatcher CPU (only valid for Medford) */
-#define          MC_CMD_PARSER_DISP_RW_IN_RX1_DICPU 0x4
-/* enum: Miscellaneous other state (only valid for Medford) */
-#define          MC_CMD_PARSER_DISP_RW_IN_MISC_STATE 0x5
-/* identifies the type of operation requested */
-#define       MC_CMD_PARSER_DISP_RW_IN_OP_OFST 4
-#define       MC_CMD_PARSER_DISP_RW_IN_OP_LEN 4
-/* enum: Read a word of DICPU DMEM or a LUE entry */
-#define          MC_CMD_PARSER_DISP_RW_IN_READ 0x0
-/* enum: Write a word of DICPU DMEM or a LUE entry. Not permitted on
- * tamperproof adapters.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_WRITE 0x1
-/* enum: Read-modify-write a word of DICPU DMEM (not valid for LUE). Not
- * permitted on tamperproof adapters.
- */
-#define          MC_CMD_PARSER_DISP_RW_IN_RMW 0x2
-/* data memory address (DICPU targets) or LUE index (LUE targets) */
-#define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_OFST 8
-#define       MC_CMD_PARSER_DISP_RW_IN_ADDRESS_LEN 4
-/* selector (for MISC_STATE target) */
-#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_OFST 8
-#define       MC_CMD_PARSER_DISP_RW_IN_SELECTOR_LEN 4
-/* enum: Port to datapath mapping */
-#define          MC_CMD_PARSER_DISP_RW_IN_PORT_DP_MAPPING 0x1
-/* value to write (for DMEM writes) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_WRITE_VALUE_LEN 4
-/* XOR value (for DMEM read-modify-writes: new = (old & mask) ^ value) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_XOR_VALUE_LEN 4
-/* AND mask (for DMEM read-modify-writes: new = (old & mask) ^ value) */
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_OFST 16
-#define       MC_CMD_PARSER_DISP_RW_IN_DMEM_RMW_AND_MASK_LEN 4
-/* metadata format (for LUE reads using LUE_VERSIONED_METADATA) */
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_READ_METADATA_VERSION_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_READ_METADATA_VERSION_LEN 4
-/* value to write (for LUE writes) */
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_OFST 12
-#define       MC_CMD_PARSER_DISP_RW_IN_LUE_WRITE_VALUE_LEN 20
-
-/* MC_CMD_PARSER_DISP_RW_OUT msgresponse */
-#define    MC_CMD_PARSER_DISP_RW_OUT_LEN 52
-/* value read (for DMEM reads) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_DMEM_READ_VALUE_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_DMEM_READ_VALUE_LEN 4
-/* value read (for LUE reads) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_READ_VALUE_LEN 20
-/* up to 8 32-bit words of additional soft state from the LUE manager (the
- * exact content is firmware-dependent and intended only for debug use)
- */
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_OFST 20
-#define       MC_CMD_PARSER_DISP_RW_OUT_LUE_MGR_STATE_LEN 32
-/* datapath(s) used for each port (for MISC_STATE PORT_DP_MAPPING selector) */
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_OFST 0
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_LEN 4
-#define       MC_CMD_PARSER_DISP_RW_OUT_PORT_DP_MAPPING_NUM 4
-#define          MC_CMD_PARSER_DISP_RW_OUT_DP0 0x1 /* enum */
-#define          MC_CMD_PARSER_DISP_RW_OUT_DP1 0x2 /* enum */
-
-
-/***********************************/
-/* MC_CMD_GET_PF_COUNT
- * Get number of PFs on the device.
- */
-#define MC_CMD_GET_PF_COUNT 0xb6
-#undef MC_CMD_0xb6_PRIVILEGE_CTG
-
-#define MC_CMD_0xb6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PF_COUNT_IN msgrequest */
-#define    MC_CMD_GET_PF_COUNT_IN_LEN 0
-
-/* MC_CMD_GET_PF_COUNT_OUT msgresponse */
-#define    MC_CMD_GET_PF_COUNT_OUT_LEN 1
-/* Identifies the number of PFs on the device. */
-#define       MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_OFST 0
-#define       MC_CMD_GET_PF_COUNT_OUT_PF_COUNT_LEN 1
-
-
-/***********************************/
-/* MC_CMD_SET_PF_COUNT
- * Set number of PFs on the device.
- */
-#define MC_CMD_SET_PF_COUNT 0xb7
-
-/* MC_CMD_SET_PF_COUNT_IN msgrequest */
-#define    MC_CMD_SET_PF_COUNT_IN_LEN 4
-/* New number of PFs on the device. */
-#define       MC_CMD_SET_PF_COUNT_IN_PF_COUNT_OFST 0
-#define       MC_CMD_SET_PF_COUNT_IN_PF_COUNT_LEN 4
-
-/* MC_CMD_SET_PF_COUNT_OUT msgresponse */
-#define    MC_CMD_SET_PF_COUNT_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_GET_PORT_ASSIGNMENT
  * Get port assignment for current PCI function.
@@ -13068,25 +13356,6 @@
 #define          MC_CMD_GET_PORT_ASSIGNMENT_OUT_NULL_PORT 0xffffffff
 
 
-/***********************************/
-/* MC_CMD_SET_PORT_ASSIGNMENT
- * Set port assignment for current PCI function.
- */
-#define MC_CMD_SET_PORT_ASSIGNMENT 0xb9
-#undef MC_CMD_0xb9_PRIVILEGE_CTG
-
-#define MC_CMD_0xb9_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_PORT_ASSIGNMENT_IN msgrequest */
-#define    MC_CMD_SET_PORT_ASSIGNMENT_IN_LEN 4
-/* Identifies the port assignment for this function. */
-#define       MC_CMD_SET_PORT_ASSIGNMENT_IN_PORT_OFST 0
-#define       MC_CMD_SET_PORT_ASSIGNMENT_IN_PORT_LEN 4
-
-/* MC_CMD_SET_PORT_ASSIGNMENT_OUT msgresponse */
-#define    MC_CMD_SET_PORT_ASSIGNMENT_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_ALLOC_VIS
  * Allocate VIs for current PCI function.
@@ -13183,263 +13452,6 @@
 #define       MC_CMD_GET_SRIOV_CFG_OUT_VF_STRIDE_LEN 4
 
 
-/***********************************/
-/* MC_CMD_SET_SRIOV_CFG
- * Set SRIOV config for this PF.
- */
-#define MC_CMD_SET_SRIOV_CFG 0xbb
-#undef MC_CMD_0xbb_PRIVILEGE_CTG
-
-#define MC_CMD_0xbb_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_SRIOV_CFG_IN msgrequest */
-#define    MC_CMD_SET_SRIOV_CFG_IN_LEN 20
-/* Number of VFs currently enabled. */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_CURRENT_OFST 0
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_CURRENT_LEN 4
-/* Max number of VFs before sriov stride and offset may need to be changed. */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_MAX_OFST 4
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_MAX_LEN 4
-#define       MC_CMD_SET_SRIOV_CFG_IN_FLAGS_OFST 8
-#define       MC_CMD_SET_SRIOV_CFG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_OFST 8
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_LBN 0
-#define        MC_CMD_SET_SRIOV_CFG_IN_VF_ENABLED_WIDTH 1
-/* RID offset of first VF from PF, or 0 for no change, or
- * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate an offset.
- */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_OFFSET_OFST 12
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_OFFSET_LEN 4
-/* RID offset of each subsequent VF from the previous, 0 for no change, or
- * MC_CMD_RESOURCE_INSTANCE_ANY to allow the system to allocate a stride.
- */
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_STRIDE_OFST 16
-#define       MC_CMD_SET_SRIOV_CFG_IN_VF_STRIDE_LEN 4
-
-/* MC_CMD_SET_SRIOV_CFG_OUT msgresponse */
-#define    MC_CMD_SET_SRIOV_CFG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_VI_ALLOC_INFO
- * Get information about number of VI's and base VI number allocated to this
- * function. This message is not available to dynamic clients created by
- * MC_CMD_CLIENT_ALLOC.
- */
-#define MC_CMD_GET_VI_ALLOC_INFO 0x8d
-#undef MC_CMD_0x8d_PRIVILEGE_CTG
-
-#define MC_CMD_0x8d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VI_ALLOC_INFO_IN msgrequest */
-#define    MC_CMD_GET_VI_ALLOC_INFO_IN_LEN 0
-
-/* MC_CMD_GET_VI_ALLOC_INFO_OUT msgresponse */
-#define    MC_CMD_GET_VI_ALLOC_INFO_OUT_LEN 12
-/* The number of VIs allocated on this function */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_OFST 0
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_COUNT_LEN 4
-/* The base absolute VI number allocated to this function. Required to
- * correctly interpret wakeup events.
- */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_OFST 4
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_BASE_LEN 4
-/* Function's port vi_shift value (always 0 on Huntington) */
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_SHIFT_OFST 8
-#define       MC_CMD_GET_VI_ALLOC_INFO_OUT_VI_SHIFT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DUMP_VI_STATE
- * For CmdClient use. Dump pertinent information on a specific absolute VI. The
- * VI must be owned by the calling client or one of its ancestors; usership of
- * the VI (as set by MC_CMD_SET_VI_USER) is not sufficient.
- */
-#define MC_CMD_DUMP_VI_STATE 0x8e
-#undef MC_CMD_0x8e_PRIVILEGE_CTG
-
-#define MC_CMD_0x8e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_DUMP_VI_STATE_IN msgrequest */
-#define    MC_CMD_DUMP_VI_STATE_IN_LEN 4
-/* The VI number to query. */
-#define       MC_CMD_DUMP_VI_STATE_IN_VI_NUMBER_OFST 0
-#define       MC_CMD_DUMP_VI_STATE_IN_VI_NUMBER_LEN 4
-
-/* MC_CMD_DUMP_VI_STATE_OUT msgresponse */
-#define    MC_CMD_DUMP_VI_STATE_OUT_LEN 100
-/* The PF part of the function owning this VI. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_OFST 0
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_PF_LEN 2
-/* The VF part of the function owning this VI. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_OFST 2
-#define       MC_CMD_DUMP_VI_STATE_OUT_OWNER_VF_LEN 2
-/* Base of VIs allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_OFST 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_BASE_LEN 2
-/* Count of VIs allocated to the owner function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_OFST 6
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VI_COUNT_LEN 2
-/* Base interrupt vector allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_OFST 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_BASE_LEN 2
-/* Number of interrupt vectors allocated to this function. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_OFST 10
-#define       MC_CMD_DUMP_VI_STATE_OUT_FUNC_VECTOR_COUNT_LEN 2
-/* Raw evq ptr table data. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_OFST 12
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_OFST 12
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_LBN 96
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_OFST 16
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_LBN 128
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EVQ_PTR_RAW_HI_WIDTH 32
-/* Raw evq timer table data. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_OFST 20
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_OFST 20
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_LBN 160
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_OFST 24
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_LBN 192
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_TIMER_RAW_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_OFST 28
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_LEN 4
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_OFST 28
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_EV_META_WKUP_REF_WIDTH 8
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_OFST 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_OFST 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_LBN 256
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_OFST 36
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_LBN 288
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_0_HI_WIDTH 32
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_OFST 40
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_OFST 40
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_LBN 320
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_OFST 44
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_LBN 352
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_1_HI_WIDTH 32
-/* TXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_OFST 48
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_OFST 48
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_LBN 384
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_OFST 52
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_LBN 416
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_RAW_TBL_2_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_OFST 56
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_OFST 56
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_LBN 448
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_OFST 60
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_LBN 480
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_HI_WIDTH 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_QSTATE_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_LBN 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_TX_META_WAITCOUNT_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_OFST 56
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_LBN 40
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_PADDING_WIDTH 24
-/* RXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_OFST 64
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_OFST 64
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_LBN 512
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_OFST 68
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_LBN 544
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_0_HI_WIDTH 32
-/* RXDPCPU raw table data for queue. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_OFST 72
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_OFST 72
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_LBN 576
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_OFST 76
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_LBN 608
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_1_HI_WIDTH 32
-/* Reserved, currently 0. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_OFST 80
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_OFST 80
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_LBN 640
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_OFST 84
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_LBN 672
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_RAW_TBL_2_HI_WIDTH 32
-/* Combined metadata field. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_OFST 88
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LEN 8
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_OFST 88
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_LBN 704
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_LO_WIDTH 32
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_OFST 92
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_LEN 4
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_LBN 736
-#define       MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_HI_WIDTH 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_LBN 0
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_BASE_WIDTH 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_LBN 16
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_BUFS_NPAGES_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_LBN 24
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_QSTATE_WIDTH 8
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_OFST 88
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_LBN 32
-#define        MC_CMD_DUMP_VI_STATE_OUT_VI_RX_META_WAITCOUNT_WIDTH 8
-/* Current user, as assigned by MC_CMD_SET_VI_USER. */
-#define       MC_CMD_DUMP_VI_STATE_OUT_USER_CLIENT_ID_OFST 96
-#define       MC_CMD_DUMP_VI_STATE_OUT_USER_CLIENT_ID_LEN 4
-
-
 /***********************************/
 /* MC_CMD_ALLOC_PIOBUF
  * Allocate a push I/O buffer for later use with a tx queue.
@@ -13491,354 +13503,102 @@
 
 /* MC_CMD_GET_VI_TLP_PROCESSING_IN msgrequest */
 #define    MC_CMD_GET_VI_TLP_PROCESSING_IN_LEN 4
-/* VI number to get information for. */
+/* Queue handle, encodes queue type and VI number to get information for. */
 #define       MC_CMD_GET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
 #define       MC_CMD_GET_VI_TLP_PROCESSING_IN_INSTANCE_LEN 4
 
-/* MC_CMD_GET_VI_TLP_PROCESSING_OUT msgresponse */
-#define    MC_CMD_GET_VI_TLP_PROCESSING_OUT_LEN 4
-/* Transaction processing steering hint 1 for use with the Rx Queue. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_OFST 0
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG1_RX_LEN 1
-/* Transaction processing steering hint 2 for use with the Ev Queue. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_OFST 1
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_TAG2_EV_LEN 1
-/* Use Relaxed ordering model for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_LBN 16
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_RELAXED_ORDERING_WIDTH 1
-/* Use ID based ordering for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_LBN 17
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_ID_BASED_ORDERING_WIDTH 1
-/* Set no snoop bit for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_LBN 18
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_NO_SNOOP_WIDTH 1
-/* Enable TPH for TLPs on this VI. */
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_LBN 19
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_TPH_ON_WIDTH 1
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_DATA_OFST 0
-#define       MC_CMD_GET_VI_TLP_PROCESSING_OUT_DATA_LEN 4
+/* MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT msgresponse: This message has the same
+ * layout as GET_VI_TLP_PROCESSING_OUT, but with corrected field ordering to
+ * simplify use in drivers
+ */
+#define    MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_LEN 4
+#define       MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_DATA_OFST 0
+#define       MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_DATA_LEN 4
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_LBN 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG1_RX_WIDTH 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_LBN 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_TAG2_EV_WIDTH 8
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_LBN 16
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_LBN 16
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_PACKET_DATA_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_LBN 17
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_ID_BASED_ORDERING_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_LBN 18
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_NO_SNOOP_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_LBN 19
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_TPH_ON_WIDTH 1
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_OFST 0
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_LBN 20
+#define        MC_CMD_GET_VI_TLP_PROCESSING_V2_OUT_RELAXED_ORDERING_SYNC_DATA_WIDTH 1
 
 
 /***********************************/
 /* MC_CMD_SET_VI_TLP_PROCESSING
  * Set TLP steering and ordering information for a VI. The caller must have the
  * GRP_FUNC_DMA privilege and must be the currently-assigned user of this VI or
- * an ancestor of the current user (see MC_CMD_SET_VI_USER).
+ * an ancestor of the current user (see MC_CMD_SET_VI_USER). Note that LL
+ * queues require this to be called after allocation but before initialisation
+ * of the queue. TLP options of a queue are fixed after queue is initialised,
+ * with the values set to current global value or they can be overriden using
+ * this command. At LL queue allocation, all overrides are cleared.
  */
 #define MC_CMD_SET_VI_TLP_PROCESSING 0xb1
 #undef MC_CMD_0xb1_PRIVILEGE_CTG
 
 #define MC_CMD_0xb1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
 
-/* MC_CMD_SET_VI_TLP_PROCESSING_IN msgrequest */
-#define    MC_CMD_SET_VI_TLP_PROCESSING_IN_LEN 8
-/* VI number to set information for. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_INSTANCE_OFST 0
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_INSTANCE_LEN 4
-/* Transaction processing steering hint 1 for use with the Rx Queue. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_OFST 4
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG1_RX_LEN 1
-/* Transaction processing steering hint 2 for use with the Ev Queue. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_OFST 5
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_TAG2_EV_LEN 1
-/* Use Relaxed ordering model for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_LBN 48
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_RELAXED_ORDERING_WIDTH 1
-/* Use ID based ordering for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_LBN 49
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_ID_BASED_ORDERING_WIDTH 1
-/* Set the no snoop bit for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_LBN 50
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_NO_SNOOP_WIDTH 1
-/* Enable TPH for TLPs on this VI. */
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_LBN 51
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_TPH_ON_WIDTH 1
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_DATA_OFST 4
-#define       MC_CMD_SET_VI_TLP_PROCESSING_IN_DATA_LEN 4
+/* MC_CMD_SET_VI_TLP_PROCESSING_V2_IN msgrequest: This message has the same
+ * layout as SET_VI_TLP_PROCESSING_OUT, but with corrected field ordering to
+ * simplify use in drivers.
+ */
+#define    MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_LEN 8
+/* Queue handle, encodes queue type and VI number to set information for. */
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_INSTANCE_OFST 0
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_INSTANCE_LEN 4
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_DATA_OFST 4
+#define       MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_DATA_LEN 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_LBN 0
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG1_RX_WIDTH 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_LBN 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_TAG2_EV_WIDTH 8
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_LBN 16
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_LBN 16
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_PACKET_DATA_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_LBN 17
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_ID_BASED_ORDERING_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_LBN 18
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_NO_SNOOP_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_LBN 19
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_TPH_ON_WIDTH 1
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_OFST 4
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_LBN 20
+#define        MC_CMD_SET_VI_TLP_PROCESSING_V2_IN_RELAXED_ORDERING_SYNC_DATA_WIDTH 1
 
 /* MC_CMD_SET_VI_TLP_PROCESSING_OUT msgresponse */
 #define    MC_CMD_SET_VI_TLP_PROCESSING_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS
- * Get global PCIe steering and transaction processing configuration.
- */
-#define MC_CMD_GET_TLP_PROCESSING_GLOBALS 0xbc
-#undef MC_CMD_0xbc_PRIVILEGE_CTG
-
-#define MC_CMD_0xbc_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN msgrequest */
-#define    MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_LEN 4
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_LEN 4
-/* enum: MISC. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_MISC 0x0
-/* enum: IDO. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_IDO 0x1
-/* enum: RO. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_RO 0x2
-/* enum: TPH Type. */
-#define          MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_TPH_TYPE 0x3
-
-/* MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
-#define    MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_LEN 8
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_GLOBAL_CATEGORY_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
-/* Amalgamated TLP info word. */
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_WORD_OFST 4
-#define       MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_WORD_LEN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_WTAG_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_MISC_SPARE_WIDTH 31
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_DL_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_TX_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_EV_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_LBN 3
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_RX_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_LBN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_IDO_SPARE_WIDTH 28
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_RXDMA_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_LBN 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_TXDMA_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_DL_EN_WIDTH 1
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_LBN 3
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_RO_SPARE_WIDTH 29
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_LBN 0
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_LBN 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_DL_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_LBN 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_TX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_LBN 6
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_EV_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_LBN 8
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TPH_TYPE_RX_WIDTH 2
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_OFST 4
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_LBN 9
-#define        MC_CMD_GET_TLP_PROCESSING_GLOBALS_OUT_TLP_INFO_TLP_TYPE_SPARE_WIDTH 23
-
-
-/***********************************/
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS
- * Set global PCIe steering and transaction processing configuration.
- */
-#define MC_CMD_SET_TLP_PROCESSING_GLOBALS 0xbd
-#undef MC_CMD_0xbd_PRIVILEGE_CTG
-
-#define MC_CMD_0xbd_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN msgrequest */
-#define    MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_LEN 8
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_OFST 0
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_GLOBAL_CATEGORY_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_GET_TLP_PROCESSING_GLOBALS/MC_CMD_GET_TLP_PROCESSING_GLOBALS_IN/TLP_GLOBAL_CATEGORY */
-/* Amalgamated TLP info word. */
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_WORD_OFST 4
-#define       MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_WORD_LEN 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_MISC_WTAG_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_DL_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_LBN 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_TX_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_EV_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_LBN 3
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_IDO_RX_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_RXDMA_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_LBN 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_TXDMA_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_RO_DL_EN_WIDTH 1
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_LBN 0
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_MSIX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_LBN 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_DL_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_LBN 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_TX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_LBN 6
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_EV_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_LBN 8
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_TPH_TYPE_RX_WIDTH 2
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_OFST 4
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_LBN 10
-#define        MC_CMD_SET_TLP_PROCESSING_GLOBALS_IN_TLP_INFO_SPARE_WIDTH 22
-
-/* MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT msgresponse */
-#define    MC_CMD_SET_TLP_PROCESSING_GLOBALS_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SATELLITE_DOWNLOAD
- * Download a new set of images to the satellite CPUs from the host.
- */
-#define MC_CMD_SATELLITE_DOWNLOAD 0x91
-#undef MC_CMD_0x91_PRIVILEGE_CTG
-
-#define MC_CMD_0x91_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SATELLITE_DOWNLOAD_IN msgrequest: The reset requirements for the CPUs
- * are subtle, and so downloads must proceed in a number of phases.
- *
- * 1) PHASE_RESET with a target of TARGET_ALL and chunk ID/length of 0.
- *
- * 2) PHASE_IMEMS for each of the IMEM targets (target IDs 0-11). Each download
- * may consist of multiple chunks. The final chunk (with CHUNK_ID_LAST) should
- * be a checksum (a simple 32-bit sum) of the transferred data. An individual
- * download may be aborted using CHUNK_ID_ABORT.
- *
- * 3) PHASE_VECTORS for each of the vector table targets (target IDs 12-15),
- * similar to PHASE_IMEMS.
- *
- * 4) PHASE_READY with a target of TARGET_ALL and chunk ID/length of 0.
- *
- * After any error (a requested abort is not considered to be an error) the
- * sequence must be restarted from PHASE_RESET.
- */
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMIN 20
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMAX 252
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_LEN(num) (16+4*(num))
-#define    MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_NUM(len) (((len)-16)/4)
-/* Download phase. (Note: the IDLE phase is used internally and is never valid
- * in a command from the host.)
- */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_OFST 0
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_LEN 4
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IDLE 0x0 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_RESET 0x1 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_IMEMS 0x2 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_VECTORS 0x3 /* enum */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_PHASE_READY 0x4 /* enum */
-/* Target for download. (These match the blob numbers defined in
- * mc_flash_layout.h.)
- */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_OFST 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_LEN 4
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_TEXT 0x0
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_TEXT 0x1
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDP_TEXT 0x2
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDP_TEXT 0x3
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT 0x4
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_LUT_CFG 0x5
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT 0x6
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_LUT_CFG 0x7
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_HR_PGM 0x8
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXHRSL_SL_PGM 0x9
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_HR_PGM 0xa
-/* enum: Valid in phase 2 (PHASE_IMEMS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXHRSL_SL_PGM 0xb
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL0 0xc
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL0 0xd
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_RXDI_VTBL1 0xe
-/* enum: Valid in phase 3 (PHASE_VECTORS) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_TXDI_VTBL1 0xf
-/* enum: Valid in phases 1 (PHASE_RESET) and 4 (PHASE_READY) only */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_TARGET_ALL 0xffffffff
-/* Chunk ID, or CHUNK_ID_LAST or CHUNK_ID_ABORT */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_OFST 8
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_LEN 4
-/* enum: Last chunk, containing checksum rather than data */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_LAST 0xffffffff
-/* enum: Abort download of this item */
-#define          MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_ID_ABORT 0xfffffffe
-/* Length of this chunk in bytes */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_LEN_OFST 12
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_LEN_LEN 4
-/* Data for this chunk */
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_OFST 16
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_LEN 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MINNUM 1
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MAXNUM 59
-#define       MC_CMD_SATELLITE_DOWNLOAD_IN_CHUNK_DATA_MAXNUM_MCDI2 251
-
-/* MC_CMD_SATELLITE_DOWNLOAD_OUT msgresponse */
-#define    MC_CMD_SATELLITE_DOWNLOAD_OUT_LEN 8
-/* Same as MC_CMD_ERR field, but included as 0 in success cases */
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_RESULT_OFST 0
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_RESULT_LEN 4
-/* Extra status information */
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_INFO_OFST 4
-#define       MC_CMD_SATELLITE_DOWNLOAD_OUT_INFO_LEN 4
-/* enum: Code download OK, completed. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_COMPLETE 0x0
-/* enum: Code download aborted as requested. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_ABORTED 0x1
-/* enum: Code download OK so far, send next chunk. */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_OK_NEXT_CHUNK 0x2
-/* enum: Download phases out of sequence */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_PHASE 0x100
-/* enum: Bad target for this phase */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_TARGET 0x101
-/* enum: Chunk ID out of sequence */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_ID 0x200
-/* enum: Chunk length zero or too large */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHUNK_LEN 0x201
-/* enum: Checksum was incorrect */
-#define          MC_CMD_SATELLITE_DOWNLOAD_OUT_ERR_BAD_CHECKSUM 0x300
-
-
 /***********************************/
 /* MC_CMD_GET_CAPABILITIES
- * Get device capabilities.
- *
- * This is supplementary to the MC_CMD_GET_BOARD_CFG command, and intended to
- * reference inherent device capabilities as opposed to current NVRAM config.
+ * Get device capabilities. This is supplementary to the MC_CMD_GET_BOARD_CFG
+ * command, and intended to reference inherent device capabilities as opposed
+ * to current NVRAM config.
  */
 #define MC_CMD_GET_CAPABILITIES 0xbe
 #undef MC_CMD_0xbe_PRIVILEGE_CTG
@@ -14194,2096 +13954,3092 @@
 #define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_LBN 31
 #define        MC_CMD_GET_CAPABILITIES_V2_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP 0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_LOW_LATENCY 0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_PACKED_STREAM 0x2
+/* enum: Rules engine RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_RULES_ENGINE 0x5
+/* enum: DPDK RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_DPDK 0x6
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_BIST 0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_BACKPRESSURE 0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+/* enum: RXDP Test firmware image 10 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_SLOW 0x10c
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP 0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_LOW_LATENCY 0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_HIGH_PACKET_RATE 0x3
+/* enum: Rules engine TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_RULES_ENGINE 0x5
+/* enum: DPDK TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_DPDK 0x6
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_BIST 0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC (when
+ * TX_TSO_V2 == 1). Not present on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED 0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT 0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_ASSIGNED 0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V2_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED 0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_LEN 2
+
+/* MC_CMD_GET_CAPABILITIES_V3_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V3_OUT_LEN 76
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DPCPU_FW_ID_LEN 2
+/* enum: Standard RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP 0x0
+/* enum: Low latency RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_LOW_LATENCY 0x1
+/* enum: Packed stream RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_PACKED_STREAM 0x2
+/* enum: Rules engine RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_RULES_ENGINE 0x5
+/* enum: DPDK RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_DPDK 0x6
+/* enum: BIST RXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_BIST 0x10a
+/* enum: RXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+/* enum: RXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+/* enum: RXDP Test firmware image 3 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+/* enum: RXDP Test firmware image 4 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+/* enum: RXDP Test firmware image 5 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_BACKPRESSURE 0x105
+/* enum: RXDP Test firmware image 6 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+/* enum: RXDP Test firmware image 7 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+/* enum: RXDP Test firmware image 8 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+/* enum: RXDP Test firmware image 9 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+/* enum: RXDP Test firmware image 10 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_SLOW 0x10c
+/* TxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DPCPU_FW_ID_LEN 2
+/* enum: Standard TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP 0x0
+/* enum: Low latency TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_LOW_LATENCY 0x1
+/* enum: High packet rate TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_HIGH_PACKET_RATE 0x3
+/* enum: Rules engine TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_RULES_ENGINE 0x5
+/* enum: DPDK TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_DPDK 0x6
+/* enum: BIST TXDP firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_BIST 0x12d
+/* enum: TXDP Test firmware image 1 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+/* enum: TXDP Test firmware image 2 */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+/* enum: TXDP CSR bus test firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial RX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: RX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant RX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+/* enum: Low latency RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+/* enum: Packed stream RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+/* enum: RX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK RX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* enum: RX PD firmware parsing but not filtering network overlay tunnel
+ * encapsulations (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+/* enum: reserved value - do not use (may indicate alternative interpretation
+ * of REV field in future)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+/* Number of FATSOv2 contexts per datapath supported by this NIC (when
+ * TX_TSO_V2 == 1). Not present on older firmware (check the length).
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+/* One byte per PF containing the number of the external port assigned to this
+ * PF, indexed by PF number. Special values indicate that a PF is either not
+ * present or not assigned.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_ACCESS_NOT_PERMITTED 0xff
+/* enum: PF does not exist. */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_PRESENT 0xfe
+/* enum: PF does exist but is not assigned to any external port. */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_ASSIGNED 0xfd
+/* enum: This value indicates that PF is assigned, but it cannot be expressed
+ * in this field. It is intended for a possible future situation where a more
+ * complex scheme of PFs to ports mapping is being used. The future driver
+ * should look for a new field supporting the new scheme. The current/old
+ * driver should treat this value as PF_NOT_ASSIGNED.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+/* One byte per PF containing the number of its VFs, indexed by PF number. A
+ * special value indicates that a PF is not present.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_NUM 16
+/* enum: The caller is not permitted to access information on this PF. */
+/*               MC_CMD_GET_CAPABILITIES_V3_OUT_ACCESS_NOT_PERMITTED 0xff */
+/* enum: PF does not exist. */
+/*               MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_NUM 4
+/* Size of RX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ RX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DESC_CACHE_SIZE_LEN 1
+/* Size of TX descriptor cache expressed as binary logarithm The actual size
+ * equals (2 ^ TX_DESC_CACHE_SIZE)
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DESC_CACHE_SIZE_LEN 1
+/* Total number of available PIO buffers */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_PIO_BUFFS_LEN 2
+/* Size of a single PIO buffer */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_SIZE_PIO_BUFF_LEN 2
+/* On chips later than Medford the amount of address space assigned to each VI
+ * is configurable. This is a global setting that the driver must query to
+ * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
+ * with 8k VI windows.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_LEN 1
+/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
+ * CTPIO is not mapped.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_8K 0x0
+/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_16K 0x1
+/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_64K 0x2
+/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+/* Number of buffers per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+
+/* MC_CMD_GET_CAPABILITIES_V4_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V4_OUT_LEN 78
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_WIDTH 1
+/* RxDPCPU firmware id. */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V2_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V2_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V2_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V4_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V2_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V2_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_SIZE_PIO_BUFF_LEN 2
+/* On chips later than Medford the amount of address space assigned to each VI
+ * is configurable. This is a global setting that the driver must query to
+ * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
+ * with 8k VI windows.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_LEN 1
+/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
+ * CTPIO is not mapped.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_8K 0x0
+/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_16K 0x1
+/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_64K 0x2
+/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+/* Number of buffers per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+/* Entry count in the MAC stats array, including the final GENERATION_END
+ * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
+ * hold at least this many 64-bit stats values, if they wish to receive all
+ * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
+ * stats array returned will be truncated.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS_LEN 2
 
-/* MC_CMD_GET_CAPABILITIES_V3_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V3_OUT_LEN 76
+/* MC_CMD_GET_CAPABILITIES_V5_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V5_OUT_LEN 84
 /* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V3_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V3_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V5_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V3_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
- */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_LEN 1
-/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
- * CTPIO is not mapped.
- */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_8K 0x0
-/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_16K 0x1
-/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V3_OUT_VI_WINDOW_MODE_64K 0x2
-/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
- * (SF-115995-SW) in the present configuration of firmware and port mode.
- */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
-/* Number of buffers per adapter that can be used for VFIFO Stuffing
- * (SF-115995-SW) in the present configuration of firmware and port mode.
- */
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V3_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
-
-/* MC_CMD_GET_CAPABILITIES_V4_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V4_OUT_LEN 78
-/* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VXLAN_NVGRE_WIDTH 1
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_LEN 1
+/* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
+ * CTPIO is not mapped.
+ */
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_8K 0x0
+/* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_16K 0x1
+/* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
+#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_64K 0x2
+/* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+/* Number of buffers per adapter that can be used for VFIFO Stuffing
+ * (SF-115995-SW) in the present configuration of firmware and port mode.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+/* Entry count in the MAC stats array, including the final GENERATION_END
+ * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
+ * hold at least this many 64-bit stats values, if they wish to receive all
+ * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
+ * stats array returned will be truncated.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_NUM_STATS_LEN 2
+/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
+ * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+
+/* MC_CMD_GET_CAPABILITIES_V6_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V6_OUT_LEN 148
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V4_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V4_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V6_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V4_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V4_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V4_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_NUM_STATS_LEN 2
+/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
+ * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
+ * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
+ * they create an RX queue. Due to hardware limitations, only a small number of
+ * different buffer sizes may be available concurrently. Nonzero entries in
+ * this array are the sizes of buffers which the system guarantees will be
+ * available for use. If the list is empty, there are no limitations on
+ * concurrent buffer sizes.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
 
-/* MC_CMD_GET_CAPABILITIES_V5_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V5_OUT_LEN 84
+/* MC_CMD_GET_CAPABILITIES_V7_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V7_OUT_LEN 152
 /* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_RESERVED 0x0
-/* enum: Trivial TX PD firmware for early Huntington development (Huntington
- * development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
-/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
-/* enum: TX PD firmware with approximately Siena-compatible behaviour
- * (Huntington development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
-/* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
-/* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_VSWITCH 0x3
-/* enum: siena_compat variant TX PD firmware using PM rather than MAC
- * (Huntington development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
-/* enum: TX PD firmware handling layer 2 only for high packet rate performance
- * tests (Medford development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
-/* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
-/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_L3XUDP 0x9
-/* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_DPDK 0xa
-/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
-/* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_HW_CAPABILITIES_LEN 4
-/* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_LICENSE_CAPABILITIES_LEN 4
-/* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V5_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_RESERVED 0x0
+/* enum: Trivial TX PD firmware for early Huntington development (Huntington
+ * development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V5_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V7_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V5_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V5_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_NUM_STATS_LEN 2
 /* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
  * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
  */
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V5_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
+ * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
+ * they create an RX queue. Due to hardware limitations, only a small number of
+ * different buffer sizes may be available concurrently. Nonzero entries in
+ * this array are the sizes of buffers which the system guarantees will be
+ * available for use. If the list is empty, there are no limitations on
+ * concurrent buffer sizes.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+/* Third word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 
-/* MC_CMD_GET_CAPABILITIES_V6_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V6_OUT_LEN 148
+/* MC_CMD_GET_CAPABILITIES_V8_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V8_OUT_LEN 160
 /* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V6_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V6_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V8_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V6_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V6_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_NUM_STATS_LEN 2
 /* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
  * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_MAX_LEN 4
 /* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
  * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
  * they create an RX queue. Due to hardware limitations, only a small number of
@@ -16292,457 +17048,531 @@
  * available for use. If the list is empty, there are no limitations on
  * concurrent buffer sizes.
  */
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V6_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
-
-/* MC_CMD_GET_CAPABILITIES_V7_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V7_OUT_LEN 152
-/* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+/* Third word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CXL_CONFIG_ENABLE_WIDTH 1
+/* These bits are reserved for communicating test-specific capabilities to
+ * host-side test software. All production drivers should treat this field as
+ * opaque.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_WIDTH 32
+
+/* MC_CMD_GET_CAPABILITIES_V9_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V9_OUT_LEN 184
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V7_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V9_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V7_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V7_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_NUM_STATS_LEN 2
 /* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
  * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_MAX_LEN 4
 /* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
  * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
  * they create an RX queue. Due to hardware limitations, only a small number of
@@ -16751,502 +17581,566 @@
  * available for use. If the list is empty, there are no limitations on
  * concurrent buffer sizes.
  */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
 /* Third word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS3_OFST 148
-#define       MC_CMD_GET_CAPABILITIES_V7_OUT_FLAGS3_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_WOL_ETHERWAKE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_EVEN_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_VDPA_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V7_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
-
-/* MC_CMD_GET_CAPABILITIES_V8_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V8_OUT_LEN 160
-/* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CXL_CONFIG_ENABLE_WIDTH 1
+/* These bits are reserved for communicating test-specific capabilities to
+ * host-side test software. All production drivers should treat this field as
+ * opaque.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_WIDTH 32
+/* The minimum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum number of queues that can be used by an RSS context in exclusive
+ * mode. In exclusive mode the context has a configurable indirection table and
+ * a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+/* The maximum number of queues that can be used by an RSS context in even-
+ * spreading mode. In even-spreading mode the context has no indirection table
+ * but it does have a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+/* The total number of RSS contexts supported. Note that the number of
+ * available contexts using indirection tables is also limited by the
+ * availability of indirection table space allocated from a common pool.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_NUM_CONTEXTS_LEN 4
+/* The total amount of indirection table space that can be shared between RSS
+ * contexts.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+
+/* MC_CMD_GET_CAPABILITIES_V10_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V10_OUT_LEN 192
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V8_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V10_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V8_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V8_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_NUM_STATS_LEN 2
 /* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
  * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_MAX_LEN 4
 /* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
  * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
  * they create an RX queue. Due to hardware limitations, only a small number of
@@ -17255,516 +18149,580 @@
  * available for use. If the list is empty, there are no limitations on
  * concurrent buffer sizes.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
 /* Third word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS3_OFST 148
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_FLAGS3_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_WOL_ETHERWAKE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_EVEN_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_VDPA_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V8_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
  */
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LEN 8
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_LBN 1216
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_LO_WIDTH 32
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_OFST 156
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_LBN 1248
-#define       MC_CMD_GET_CAPABILITIES_V8_OUT_TEST_RESERVED_HI_WIDTH 32
-
-/* MC_CMD_GET_CAPABILITIES_V9_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V9_OUT_LEN 184
-/* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_WIDTH 32
+/* The minimum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum size (in table entries) of indirection table to be allocated
+ * from the pool for an RSS context. Note that the table size used must be a
+ * power of 2.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+/* The maximum number of queues that can be used by an RSS context in exclusive
+ * mode. In exclusive mode the context has a configurable indirection table and
+ * a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+/* The maximum number of queues that can be used by an RSS context in even-
+ * spreading mode. In even-spreading mode the context has no indirection table
+ * but it does have a configurable RSS key.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+/* The total number of RSS contexts supported. Note that the number of
+ * available contexts using indirection tables is also limited by the
+ * availability of indirection table space allocated from a common pool.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_NUM_CONTEXTS_LEN 4
+/* The total amount of indirection table space that can be shared between RSS
+ * contexts.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+/* A bitmap of the queue sizes the device can provide, where bit N being set
+ * indicates that 2**N is a valid size. The device may be limited in the number
+ * of different queue sizes that can exist simultaneously, so a bit being set
+ * here does not guarantee that an attempt to create a queue of that size will
+ * succeed.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
+/* A bitmap of queue sizes that are always available, in the same format as
+ * SUPPORTED_QUEUE_SIZES. Attempting to create a queue with one of these sizes
+ * will never fail due to unavailability of the requested size.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
+#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+
+/* MC_CMD_GET_CAPABILITIES_V11_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V11_OUT_LEN 196
+/* First word of flags. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
-/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
-/* enum: TX PD firmware with approximately Siena-compatible behaviour
- * (Huntington development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
-/* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
-/* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_VSWITCH 0x3
-/* enum: siena_compat variant TX PD firmware using PM rather than MAC
- * (Huntington development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
-/* enum: TX PD firmware handling layer 2 only for high packet rate performance
- * tests (Medford development only)
- */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
-/* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
-/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_L3XUDP 0x9
-/* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_DPDK 0xa
-/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
-/* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_HW_CAPABILITIES_LEN 4
-/* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_LICENSE_CAPABILITIES_LEN 4
-/* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+/* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+/* enum: TX PD firmware with approximately Siena-compatible behaviour
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+/* enum: Full featured TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+/* enum: (deprecated original name for the FULL_FEATURED variant) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+/* enum: siena_compat variant TX PD firmware using PM rather than MAC
+ * (Huntington development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+/* enum: TX PD firmware handling layer 2 only for high packet rate performance
+ * tests (Medford development only)
+ */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+/* enum: Rules engine TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+/* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+/* enum: DPDK TX PD production firmware */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_DPDK 0xa
+/* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+/* Hardware capabilities of NIC */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_HW_CAPABILITIES_LEN 4
+/* Licensed capabilities */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_LICENSE_CAPABILITIES_LEN 4
+/* Second word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V9_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V11_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V9_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V11_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V9_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V11_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
  * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
  * hold at least this many 64-bit stats values, if they wish to receive all
  * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
  * stats array returned will be truncated.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_MAC_STATS_NUM_STATS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_MAC_STATS_NUM_STATS_LEN 2
 /* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
  * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FILTER_ACTION_MARK_MAX_LEN 4
 /* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
  * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
  * they create an RX queue. Due to hardware limitations, only a small number of
@@ -17773,670 +18731,723 @@
  * available for use. If the list is empty, there are no limitations on
  * concurrent buffer sizes.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
 /* Third word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS3_OFST 148
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_FLAGS3_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_WOL_ETHERWAKE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_EVEN_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_VDPA_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V9_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V11_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LEN 8
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_LBN 1216
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_LO_WIDTH 32
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_OFST 156
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_LBN 1248
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_TEST_RESERVED_HI_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_TEST_RESERVED_HI_WIDTH 32
 /* The minimum size (in table entries) of indirection table to be allocated
  * from the pool for an RSS context. Note that the table size used must be a
  * power of 2.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
 /* The maximum size (in table entries) of indirection table to be allocated
  * from the pool for an RSS context. Note that the table size used must be a
  * power of 2.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
 /* The maximum number of queues that can be used by an RSS context in exclusive
  * mode. In exclusive mode the context has a configurable indirection table and
  * a configurable RSS key.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
 /* The maximum number of queues that can be used by an RSS context in even-
  * spreading mode. In even-spreading mode the context has no indirection table
  * but it does have a configurable RSS key.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
 /* The total number of RSS contexts supported. Note that the number of
  * available contexts using indirection tables is also limited by the
  * availability of indirection table space allocated from a common pool.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_NUM_CONTEXTS_OFST 176
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_NUM_CONTEXTS_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_NUM_CONTEXTS_LEN 4
 /* The total amount of indirection table space that can be shared between RSS
  * contexts.
  */
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_TABLE_POOL_SIZE_OFST 180
-#define       MC_CMD_GET_CAPABILITIES_V9_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+/* A bitmap of the queue sizes the device can provide, where bit N being set
+ * indicates that 2**N is a valid size. The device may be limited in the number
+ * of different queue sizes that can exist simultaneously, so a bit being set
+ * here does not guarantee that an attempt to create a queue of that size will
+ * succeed.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
+/* A bitmap of queue sizes that are always available, in the same format as
+ * SUPPORTED_QUEUE_SIZES. Attempting to create a queue with one of these sizes
+ * will never fail due to unavailability of the requested size.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+/* Number of available indirect memory maps. */
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_INDIRECT_MAP_INDEX_COUNT_OFST 192
+#define       MC_CMD_GET_CAPABILITIES_V11_OUT_INDIRECT_MAP_INDEX_COUNT_LEN 4
 
-/* MC_CMD_GET_CAPABILITIES_V10_OUT msgresponse */
-#define    MC_CMD_GET_CAPABILITIES_V10_OUT_LEN 192
+/* MC_CMD_GET_CAPABILITIES_V12_OUT msgresponse */
+#define    MC_CMD_GET_CAPABILITIES_V12_OUT_LEN 204
 /* First word of flags. */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS1_OFST 0
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS1_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VPORT_RECONFIGURE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_STRIPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_QUERY_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SET_MAC_ENHANCED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_QBB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_RSS_LIMITED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_INCLUDE_FCS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VLAN_INSERTION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_0_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_PREFIX_LEN_14_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_BATCHING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCAST_FILTER_CHAINING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DISABLE_SCATTER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVB_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_OFST 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VXLAN_NVGRE_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS1_OFST 0
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS1_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VPORT_RECONFIGURE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_STRIPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_QUERY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_PORT_VLAN_RESTRICT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DRV_ATTACH_PREBOOT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_FORCE_EVENT_MERGING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SET_MAC_ENHANCED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNKNOWN_UCAST_DST_FILTER_ALWAYS_MULTI_RECIPIENT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VADAPTOR_PERMIT_SET_MAC_WHEN_FILTERS_INSTALLED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_SECURITY_FILTERING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ADDITIONAL_RSS_MODES_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_QBB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_VAR_BUFFERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_RSS_LIMITED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_INCLUDE_FCS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VLAN_INSERTION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_0_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_PREFIX_LEN_14_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_BATCHING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCAST_FILTER_CHAINING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DISABLE_SCATTER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MCAST_UDP_LOOPBACK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVB_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_OFST 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VXLAN_NVGRE_WIDTH 1
 /* RxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DPCPU_FW_ID_OFST 4
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DPCPU_FW_ID_OFST 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DPCPU_FW_ID_LEN 2
 /* enum: Standard RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP 0x0
 /* enum: Low latency RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_LOW_LATENCY 0x1
 /* enum: Packed stream RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_PACKED_STREAM 0x2
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_PACKED_STREAM 0x2
 /* enum: Rules engine RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_RULES_ENGINE 0x5
 /* enum: DPDK RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_DPDK 0x6
 /* enum: BIST RXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_BIST 0x10a
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_BIST 0x10a
 /* enum: RXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_CUT_THROUGH 0x101
 /* enum: RXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD 0x102
 /* enum: RXDP Test firmware image 3 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_TO_MC_STORE_FORWARD_FIRST 0x103
 /* enum: RXDP Test firmware image 4 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_EVERY_EVENT_BATCHABLE 0x104
 /* enum: RXDP Test firmware image 5 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_BACKPRESSURE 0x105
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_BACKPRESSURE 0x105
 /* enum: RXDP Test firmware image 6 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_PACKET_EDITS 0x106
 /* enum: RXDP Test firmware image 7 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_RX_HDR_SPLIT 0x107
 /* enum: RXDP Test firmware image 8 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_DISABLE_DL 0x108
 /* enum: RXDP Test firmware image 9 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_DOORBELL_DELAY 0x10b
 /* enum: RXDP Test firmware image 10 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_TEST_FW_SLOW 0x10c
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_TEST_FW_SLOW 0x10c
 /* TxDPCPU firmware id. */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DPCPU_FW_ID_OFST 6
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DPCPU_FW_ID_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DPCPU_FW_ID_OFST 6
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DPCPU_FW_ID_LEN 2
 /* enum: Standard TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP 0x0
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP 0x0
 /* enum: Low latency TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_LOW_LATENCY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_LOW_LATENCY 0x1
 /* enum: High packet rate TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_HIGH_PACKET_RATE 0x3
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_HIGH_PACKET_RATE 0x3
 /* enum: Rules engine TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_RULES_ENGINE 0x5
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_RULES_ENGINE 0x5
 /* enum: DPDK TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_DPDK 0x6
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_DPDK 0x6
 /* enum: BIST TXDP firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_BIST 0x12d
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_BIST 0x12d
 /* enum: TXDP Test firmware image 1 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_TSO_EDIT 0x101
 /* enum: TXDP Test firmware image 2 */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_PACKET_EDITS 0x102
 /* enum: TXDP CSR bus test firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXDP_TEST_FW_CSR 0x103
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_OFST 8
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_OFST 8
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXDP_TEST_FW_CSR 0x103
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_OFST 8
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_OFST 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial RX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: RX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: RX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant RX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
 /* enum: Low latency RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_LOW_LATENCY 0x5
 /* enum: Packed stream RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_PACKED_STREAM 0x6
 /* enum: RX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK RX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* enum: RX PD firmware parsing but not filtering network overlay tunnel
  * encapsulations (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_OFST 10
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_LEN 2
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_REV_WIDTH 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_OFST 10
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_RXPD_FW_TYPE_TESTFW_ENCAP_PARSING_ONLY 0xf
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_OFST 10
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_LEN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_REV_WIDTH 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_OFST 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_VERSION_TYPE_WIDTH 4
 /* enum: reserved value - do not use (may indicate alternative interpretation
  * of REV field in future)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_RESERVED 0x0
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_RESERVED 0x0
 /* enum: Trivial TX PD firmware for early Huntington development (Huntington
  * development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_FIRST_PKT 0x1
 /* enum: TX PD firmware for telemetry prototyping (Medford2 development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_TESTFW_TELEMETRY 0x1
 /* enum: TX PD firmware with approximately Siena-compatible behaviour
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_SIENA_COMPAT 0x2
 /* enum: Full featured TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_FULL_FEATURED 0x3
 /* enum: (deprecated original name for the FULL_FEATURED variant) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_VSWITCH 0x3
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_VSWITCH 0x3
 /* enum: siena_compat variant TX PD firmware using PM rather than MAC
  * (Huntington development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_SIENA_COMPAT_PM 0x4
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_LOW_LATENCY 0x5 /* enum */
 /* enum: TX PD firmware handling layer 2 only for high packet rate performance
  * tests (Medford development only)
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_LAYER2_PERF 0x7
 /* enum: Rules engine TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_RULES_ENGINE 0x8
 /* enum: Custom firmware variant (see SF-119495-PD and bug69716) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_L3XUDP 0x9
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_L3XUDP 0x9
 /* enum: DPDK TX PD production firmware */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_DPDK 0xa
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_DPDK 0xa
 /* enum: RX PD firmware for GUE parsing prototype (Medford development only) */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_TXPD_FW_TYPE_TESTFW_GUE_PROTOTYPE 0xe
 /* Hardware capabilities of NIC */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_HW_CAPABILITIES_OFST 12
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_HW_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_HW_CAPABILITIES_OFST 12
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_HW_CAPABILITIES_LEN 4
 /* Licensed capabilities */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_LICENSE_CAPABILITIES_OFST 16
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_LICENSE_CAPABILITIES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_LICENSE_CAPABILITIES_OFST 16
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_LICENSE_CAPABILITIES_LEN 4
 /* Second word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS2_OFST 20
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS2_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_ENCAP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVQ_TIMER_CTRL_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EVENT_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_CUT_THROUGH_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_EVQ_V2_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TIMESTAMP_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_SNIFF_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_LBN 13
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_BACKGROUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MCDI_DB_RETURN_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_LBN 15
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_CTPIO_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_LBN 16
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_LBN 17
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TSA_BOUND_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_LBN 19
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_FLAG_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_LBN 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_LBN 22
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_L3XUDP_SUPPORT_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_LBN 24
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VI_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_LBN 25
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RXDP_HLB_IDLE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_LBN 28
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_BUNDLE_UPDATE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_LBN 29
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V3_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_LBN 30
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_SENSORS_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS2_OFST 20
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS2_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_ENCAP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVQ_TIMER_CTRL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EVENT_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_CUT_THROUGH_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_VFIFO_ULL_MODE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_40G_TX_SIZE_BINS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_TYPE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_EVQ_V2_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_MAC_TIMESTAMPING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TIMESTAMP_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_SNIFF_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_REPORT_VERIFY_RESULT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_BACKGROUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MCDI_DB_RETURN_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CTPIO_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TSA_BOUND_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_LBN 18
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_SF_ADAPTER_AUTHENTICATION_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_LBN 19
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_FLAG_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_LBN 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_SUPER_BUFFER_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_LBN 21
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EQUAL_STRIDE_PACKED_STREAM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_LBN 22
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_L3XUDP_SUPPORT_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_LBN 23
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_FW_SUBVARIANT_NO_TX_CSUM_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_LBN 24
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VI_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_LBN 25
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RXDP_HLB_IDLE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_LBN 26
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_NO_CONT_EV_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_LBN 27
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_INIT_RXQ_WITH_BUFFER_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_LBN 28
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_BUNDLE_UPDATE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_LBN 29
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V3_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_LBN 30
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_SENSORS_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_OFST 20
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_LBN 31
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_POLL_VERIFY_RESULT_WIDTH 1
 /* Number of FATSOv2 contexts per datapath supported by this NIC (when
  * TX_TSO_V2 == 1). Not present on older firmware (check the length).
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_N_CONTEXTS_OFST 24
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_TSO_V2_N_CONTEXTS_LEN 2
 /* One byte per PF containing the number of the external port assigned to this
  * PF, indexed by PF number. Special values indicate that a PF is either not
  * present or not assigned.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_OFST 26
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_PFS_TO_PORTS_ASSIGNMENT_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_ACCESS_NOT_PERMITTED 0xff
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_ACCESS_NOT_PERMITTED 0xff
 /* enum: PF does not exist. */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_PRESENT 0xfe
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_PRESENT 0xfe
 /* enum: PF does exist but is not assigned to any external port. */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_ASSIGNED 0xfd
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_ASSIGNED 0xfd
 /* enum: This value indicates that PF is assigned, but it cannot be expressed
  * in this field. It is intended for a possible future situation where a more
  * complex scheme of PFs to ports mapping is being used. The future driver
  * should look for a new field supporting the new scheme. The current/old
  * driver should treat this value as PF_NOT_ASSIGNED.
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_INCOMPATIBLE_ASSIGNMENT 0xfc
 /* One byte per PF containing the number of its VFs, indexed by PF number. A
  * special value indicates that a PF is not present.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_OFST 42
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_LEN 1
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VFS_PER_PF_NUM 16
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_OFST 42
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VFS_PER_PF_NUM 16
 /* enum: The caller is not permitted to access information on this PF. */
-/*               MC_CMD_GET_CAPABILITIES_V10_OUT_ACCESS_NOT_PERMITTED 0xff */
+/*               MC_CMD_GET_CAPABILITIES_V12_OUT_ACCESS_NOT_PERMITTED 0xff */
 /* enum: PF does not exist. */
-/*               MC_CMD_GET_CAPABILITIES_V10_OUT_PF_NOT_PRESENT 0xfe */
-/* Number of VIs available for each external port */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_OFST 58
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_LEN 2
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_VIS_PER_PORT_NUM 4
+/*               MC_CMD_GET_CAPABILITIES_V12_OUT_PF_NOT_PRESENT 0xfe */
+/* Number of VIs available for external ports 0-3. For devices with more than
+ * four ports, the remainder are in NUM_VIS_PER_PORT2 in
+ * GET_CAPABILITIES_V12_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_OFST 58
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT_NUM 4
 /* Size of RX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ RX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DESC_CACHE_SIZE_OFST 66
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DESC_CACHE_SIZE_OFST 66
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RX_DESC_CACHE_SIZE_LEN 1
 /* Size of TX descriptor cache expressed as binary logarithm The actual size
  * equals (2 ^ TX_DESC_CACHE_SIZE)
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DESC_CACHE_SIZE_OFST 67
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TX_DESC_CACHE_SIZE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DESC_CACHE_SIZE_OFST 67
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TX_DESC_CACHE_SIZE_LEN 1
 /* Total number of available PIO buffers */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_PIO_BUFFS_OFST 68
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_NUM_PIO_BUFFS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_PIO_BUFFS_OFST 68
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_PIO_BUFFS_LEN 2
 /* Size of a single PIO buffer */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SIZE_PIO_BUFF_OFST 70
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SIZE_PIO_BUFF_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SIZE_PIO_BUFF_OFST 70
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SIZE_PIO_BUFF_LEN 2
 /* On chips later than Medford the amount of address space assigned to each VI
  * is configurable. This is a global setting that the driver must query to
  * discover the VI to address mapping. Cut-through PIO (CTPIO) is not available
  * with 8k VI windows.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_OFST 72
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_OFST 72
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_LEN 1
 /* enum: Each VI occupies 8k as on Huntington and Medford. PIO is at offset 4k.
  * CTPIO is not mapped.
  */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_8K 0x0
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_8K 0x0
 /* enum: Each VI occupies 16k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_16K 0x1
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_16K 0x1
 /* enum: Each VI occupies 64k. PIO is at offset 4k. CTPIO is at offset 12k. */
-#define          MC_CMD_GET_CAPABILITIES_V10_OUT_VI_WINDOW_MODE_64K 0x2
+#define          MC_CMD_GET_CAPABILITIES_V12_OUT_VI_WINDOW_MODE_64K 0x2
 /* Number of vFIFOs per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_VFIFOS_OFST 73
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_VFIFOS_LEN 1
 /* Number of buffers per adapter that can be used for VFIFO Stuffing
  * (SF-115995-SW) in the present configuration of firmware and port mode.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_OFST 74
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_VFIFO_STUFFING_NUM_CP_BUFFERS_LEN 2
 /* Entry count in the MAC stats array, including the final GENERATION_END
- * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
- * hold at least this many 64-bit stats values, if they wish to receive all
- * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
- * stats array returned will be truncated.
- */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_NUM_STATS_OFST 76
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_MAC_STATS_NUM_STATS_LEN 2
-/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
- * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
- */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_MAX_OFST 80
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FILTER_ACTION_MARK_MAX_LEN 4
-/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
- * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
- * they create an RX queue. Due to hardware limitations, only a small number of
- * different buffer sizes may be available concurrently. Nonzero entries in
- * this array are the sizes of buffers which the system guarantees will be
- * available for use. If the list is empty, there are no limitations on
- * concurrent buffer sizes.
- */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
-/* Third word of flags. Not present on older firmware (check the length). */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS3_OFST 148
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_FLAGS3_LEN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_LBN 0
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_WOL_ETHERWAKE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_LBN 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_EVEN_SPREADING_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_LBN 3
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_LBN 4
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_VDPA_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
-#define        MC_CMD_GET_CAPABILITIES_V10_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+ * entry. For MAC stats DMA, drivers should allocate a buffer large enough to
+ * hold at least this many 64-bit stats values, if they wish to receive all
+ * available stats. If the buffer is shorter than MAC_STATS_NUM_STATS * 8, the
+ * stats array returned will be truncated.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_NUM_STATS_OFST 76
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_MAC_STATS_NUM_STATS_LEN 2
+/* Maximum supported value for MC_CMD_FILTER_OP_V3/MATCH_MARK_VALUE. This field
+ * will only be non-zero if MC_CMD_GET_CAPABILITIES/FILTER_ACTION_MARK is set.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_MAX_OFST 80
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FILTER_ACTION_MARK_MAX_LEN 4
+/* On devices where the INIT_RXQ_WITH_BUFFER_SIZE flag (in
+ * GET_CAPABILITIES_OUT_V2) is set, drivers have to specify a buffer size when
+ * they create an RX queue. Due to hardware limitations, only a small number of
+ * different buffer sizes may be available concurrently. Nonzero entries in
+ * this array are the sizes of buffers which the system guarantees will be
+ * available for use. If the list is empty, there are no limitations on
+ * concurrent buffer sizes.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_OFST 84
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_RX_BUFFER_SIZES_NUM 16
+/* Third word of flags. Not present on older firmware (check the length). */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS3_OFST 148
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_FLAGS3_LEN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_LBN 0
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_WOL_ETHERWAKE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_LBN 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_EVEN_SPREADING_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_LBN 2
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_SELECTABLE_TABLE_SIZE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_LBN 3
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_LBN 4
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_VDPA_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_LBN 5
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RX_VLAN_STRIPPING_PER_ENCAP_RULE_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_LBN 6
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTENDED_WIDTH_EVQS_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_LBN 7
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_UNSOL_EV_CREDIT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_LBN 8
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_ENCAPSULATED_MCDI_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_LBN 9
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_EXTERNAL_MAE_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_LBN 10
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_NVRAM_UPDATE_ABORT_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_LBN 11
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V2_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_LBN 12
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_STEER_ON_OUTER_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_LBN 13
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_MAE_ACTION_SET_ALLOC_V3_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_LBN 14
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_DYNAMIC_MPORT_JOURNAL_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_LBN 15
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CLIENT_CMD_VF_PROXY_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_LBN 16
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_LL_RX_EVENT_SUPPRESSION_SUPPORTED_WIDTH 1
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_OFST 148
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_LBN 17
+#define        MC_CMD_GET_CAPABILITIES_V12_OUT_CXL_CONFIG_ENABLE_WIDTH 1
 /* These bits are reserved for communicating test-specific capabilities to
  * host-side test software. All production drivers should treat this field as
  * opaque.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LEN 8
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_OFST 152
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_LBN 1216
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_LO_WIDTH 32
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_OFST 156
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_LEN 4
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_LBN 1248
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_TEST_RESERVED_HI_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LEN 8
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_OFST 152
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_LBN 1216
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_LO_WIDTH 32
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_OFST 156
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_LBN 1248
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_TEST_RESERVED_HI_WIDTH 32
 /* The minimum size (in table entries) of indirection table to be allocated
  * from the pool for an RSS context. Note that the table size used must be a
  * power of 2.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_OFST 160
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MIN_INDIRECTION_TABLE_SIZE_LEN 4
 /* The maximum size (in table entries) of indirection table to be allocated
  * from the pool for an RSS context. Note that the table size used must be a
  * power of 2.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_OFST 164
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_TABLE_SIZE_LEN 4
 /* The maximum number of queues that can be used by an RSS context in exclusive
  * mode. In exclusive mode the context has a configurable indirection table and
  * a configurable RSS key.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_QUEUES_OFST 168
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_INDIRECTION_QUEUES_LEN 4
 /* The maximum number of queues that can be used by an RSS context in even-
  * spreading mode. In even-spreading mode the context has no indirection table
  * but it does have a configurable RSS key.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_OFST 172
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_MAX_EVEN_SPREADING_QUEUES_LEN 4
 /* The total number of RSS contexts supported. Note that the number of
  * available contexts using indirection tables is also limited by the
  * availability of indirection table space allocated from a common pool.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_NUM_CONTEXTS_OFST 176
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_NUM_CONTEXTS_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_NUM_CONTEXTS_OFST 176
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_NUM_CONTEXTS_LEN 4
 /* The total amount of indirection table space that can be shared between RSS
  * contexts.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_TABLE_POOL_SIZE_OFST 180
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_RSS_TABLE_POOL_SIZE_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_TABLE_POOL_SIZE_OFST 180
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_RSS_TABLE_POOL_SIZE_LEN 4
 /* A bitmap of the queue sizes the device can provide, where bit N being set
  * indicates that 2**N is a valid size. The device may be limited in the number
  * of different queue sizes that can exist simultaneously, so a bit being set
  * here does not guarantee that an attempt to create a queue of that size will
  * succeed.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SUPPORTED_QUEUE_SIZES_OFST 184
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_SUPPORTED_QUEUE_SIZES_LEN 4
 /* A bitmap of queue sizes that are always available, in the same format as
  * SUPPORTED_QUEUE_SIZES. Attempting to create a queue with one of these sizes
  * will never fail due to unavailability of the requested size.
  */
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
-#define       MC_CMD_GET_CAPABILITIES_V10_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_QUEUE_SIZES_OFST 188
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_GUARANTEED_QUEUE_SIZES_LEN 4
+/* Number of available indirect memory maps. */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_INDIRECT_MAP_INDEX_COUNT_OFST 192
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_INDIRECT_MAP_INDEX_COUNT_LEN 4
+/* Number of VIs available for external ports 4-7. Information for ports 0-3 is
+ * in NUM_VIS_PER_PORT in GET_CAPABILITIES_V2_OUT.
+ */
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_OFST 196
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_LEN 2
+#define       MC_CMD_GET_CAPABILITIES_V12_OUT_NUM_VIS_PER_PORT2_NUM 4
 
 
 /***********************************/
@@ -18468,168 +19479,13 @@
  * are not defined.
  */
 #define          MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_TSA 0x1
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_ALLOC
- * Allocate a pacer bucket (for qau rp or a snapper test)
- */
-#define MC_CMD_TCM_BUCKET_ALLOC 0xb2
-#undef MC_CMD_0xb2_PRIVILEGE_CTG
-
-#define MC_CMD_0xb2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_ALLOC_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_ALLOC_IN_LEN 0
-
-/* MC_CMD_TCM_BUCKET_ALLOC_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_ALLOC_OUT_LEN 4
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_ALLOC_OUT_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_ALLOC_OUT_BUCKET_LEN 4
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_FREE
- * Free a pacer bucket
+/* enum: MCDI command used for platform management. Typically, these commands
+ * are used for low-level operations directed at the platform as a whole (e.g.
+ * MMIO device enumeration) rather than individual functions and use a
+ * dedicated comms channel (e.g. RPmsg/IPI). May be handled by the same or
+ * different CPU as MCDI_MESSAGE_TYPE_MC.
  */
-#define MC_CMD_TCM_BUCKET_FREE 0xb3
-#undef MC_CMD_0xb3_PRIVILEGE_CTG
-
-#define MC_CMD_0xb3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_FREE_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_FREE_IN_LEN 4
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_FREE_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_FREE_IN_BUCKET_LEN 4
-
-/* MC_CMD_TCM_BUCKET_FREE_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TCM_BUCKET_INIT
- * Initialise pacer bucket with a given rate
- */
-#define MC_CMD_TCM_BUCKET_INIT 0xb4
-#undef MC_CMD_0xb4_PRIVILEGE_CTG
-
-#define MC_CMD_0xb4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_BUCKET_INIT_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_INIT_IN_LEN 8
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_INIT_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_INIT_IN_BUCKET_LEN 4
-/* the rate in mbps */
-#define       MC_CMD_TCM_BUCKET_INIT_IN_RATE_OFST 4
-#define       MC_CMD_TCM_BUCKET_INIT_IN_RATE_LEN 4
-
-/* MC_CMD_TCM_BUCKET_INIT_EXT_IN msgrequest */
-#define    MC_CMD_TCM_BUCKET_INIT_EXT_IN_LEN 12
-/* the bucket id */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_BUCKET_OFST 0
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_BUCKET_LEN 4
-/* the rate in mbps */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_RATE_OFST 4
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_RATE_LEN 4
-/* the desired maximum fill level */
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_MAX_FILL_OFST 8
-#define       MC_CMD_TCM_BUCKET_INIT_EXT_IN_MAX_FILL_LEN 4
-
-/* MC_CMD_TCM_BUCKET_INIT_OUT msgresponse */
-#define    MC_CMD_TCM_BUCKET_INIT_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_TCM_TXQ_INIT
- * Initialise txq in pacer with given options or set options
- */
-#define MC_CMD_TCM_TXQ_INIT 0xb5
-#undef MC_CMD_0xb5_PRIVILEGE_CTG
-
-#define MC_CMD_0xb5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TCM_TXQ_INIT_IN msgrequest */
-#define    MC_CMD_TCM_TXQ_INIT_IN_LEN 28
-/* the txq id */
-#define       MC_CMD_TCM_TXQ_INIT_IN_QID_OFST 0
-#define       MC_CMD_TCM_TXQ_INIT_IN_QID_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_IN_LABEL_OFST 4
-#define       MC_CMD_TCM_TXQ_INIT_IN_LABEL_LEN 4
-/* bitmask of the priority queues this txq is inserted into when inserted. */
-#define       MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_OFST 8
-#define       MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAGS_LEN 4
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_LBN 0
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_GUARANTEED_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_LBN 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_NORMAL_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_LBN 2
-#define        MC_CMD_TCM_TXQ_INIT_IN_PQ_FLAG_LOW_WIDTH 1
-/* the reaction point (RP) bucket */
-#define       MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_OFST 12
-#define       MC_CMD_TCM_TXQ_INIT_IN_RP_BKT_LEN 4
-/* an already reserved bucket (typically set to bucket associated with outer
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT1_OFST 16
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT1_LEN 4
-/* an already reserved bucket (typically set to bucket associated with inner
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT2_OFST 20
-#define       MC_CMD_TCM_TXQ_INIT_IN_MAX_BKT2_LEN 4
-/* the min bucket (typically for ETS/minimum bandwidth) */
-#define       MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_OFST 24
-#define       MC_CMD_TCM_TXQ_INIT_IN_MIN_BKT_LEN 4
-
-/* MC_CMD_TCM_TXQ_INIT_EXT_IN msgrequest */
-#define    MC_CMD_TCM_TXQ_INIT_EXT_IN_LEN 32
-/* the txq id */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_QID_OFST 0
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_QID_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_NORMAL_OFST 4
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_NORMAL_LEN 4
-/* bitmask of the priority queues this txq is inserted into when inserted. */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAGS_OFST 8
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAGS_LEN 4
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_LBN 0
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_GUARANTEED_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_LBN 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_NORMAL_WIDTH 1
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_OFST 8
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_LBN 2
-#define        MC_CMD_TCM_TXQ_INIT_EXT_IN_PQ_FLAG_LOW_WIDTH 1
-/* the reaction point (RP) bucket */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_RP_BKT_OFST 12
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_RP_BKT_LEN 4
-/* an already reserved bucket (typically set to bucket associated with outer
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT1_OFST 16
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT1_LEN 4
-/* an already reserved bucket (typically set to bucket associated with inner
- * vswitch)
- */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT2_OFST 20
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MAX_BKT2_LEN 4
-/* the min bucket (typically for ETS/minimum bandwidth) */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MIN_BKT_OFST 24
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_MIN_BKT_LEN 4
-/* the static priority associated with the txq */
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_GUARANTEED_OFST 28
-#define       MC_CMD_TCM_TXQ_INIT_EXT_IN_LABEL_GUARANTEED_LEN 4
-
-/* MC_CMD_TCM_TXQ_INIT_OUT msgresponse */
-#define    MC_CMD_TCM_TXQ_INIT_OUT_LEN 0
+#define          MC_CMD_V2_EXTN_IN_MCDI_MESSAGE_TYPE_PLATFORM 0x2
 
 
 /***********************************/
@@ -18739,27 +19595,6 @@
 #define    MC_CMD_VSWITCH_FREE_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_VSWITCH_QUERY
- * read some config of v-switch. For now this command is an empty placeholder.
- * It may be used to check if a v-switch is connected to a given EVB port (if
- * not, then the command returns ENOENT).
- */
-#define MC_CMD_VSWITCH_QUERY 0x63
-#undef MC_CMD_0x63_PRIVILEGE_CTG
-
-#define MC_CMD_0x63_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VSWITCH_QUERY_IN msgrequest */
-#define    MC_CMD_VSWITCH_QUERY_IN_LEN 4
-/* The port to which the v-switch is connected. */
-#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_VSWITCH_QUERY_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_VSWITCH_QUERY_OUT msgresponse */
-#define    MC_CMD_VSWITCH_QUERY_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_VPORT_ALLOC
  * allocate a v-port.
@@ -18935,28 +19770,6 @@
 #define    MC_CMD_VADAPTOR_SET_MAC_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_VADAPTOR_GET_MAC
- * read the MAC address assigned to a v-adaptor.
- */
-#define MC_CMD_VADAPTOR_GET_MAC 0x5e
-#undef MC_CMD_0x5e_PRIVILEGE_CTG
-
-#define MC_CMD_0x5e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VADAPTOR_GET_MAC_IN msgrequest */
-#define    MC_CMD_VADAPTOR_GET_MAC_IN_LEN 4
-/* The port to which the v-adaptor is connected. */
-#define       MC_CMD_VADAPTOR_GET_MAC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_VADAPTOR_GET_MAC_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_VADAPTOR_GET_MAC_OUT msgresponse */
-#define    MC_CMD_VADAPTOR_GET_MAC_OUT_LEN 6
-/* The MAC address assigned to this v-adaptor */
-#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_OFST 0
-#define       MC_CMD_VADAPTOR_GET_MAC_OUT_MACADDR_LEN 6
-
-
 /***********************************/
 /* MC_CMD_VADAPTOR_QUERY
  * read some config of v-adaptor.
@@ -19013,86 +19826,6 @@
 #define    MC_CMD_EVB_PORT_ASSIGN_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_RDWR_A64_REGIONS
- * Assign the 64 bit region addresses.
- */
-#define MC_CMD_RDWR_A64_REGIONS 0x9b
-#undef MC_CMD_0x9b_PRIVILEGE_CTG
-
-#define MC_CMD_0x9b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_RDWR_A64_REGIONS_IN msgrequest */
-#define    MC_CMD_RDWR_A64_REGIONS_IN_LEN 17
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION0_OFST 0
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION0_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION1_OFST 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION1_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION2_OFST 8
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION2_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION3_OFST 12
-#define       MC_CMD_RDWR_A64_REGIONS_IN_REGION3_LEN 4
-/* Write enable bits 0-3, set to write, clear to read. */
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_LBN 128
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_WIDTH 4
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_OFST 16
-#define       MC_CMD_RDWR_A64_REGIONS_IN_WRITE_MASK_BYTE_LEN 1
-
-/* MC_CMD_RDWR_A64_REGIONS_OUT msgresponse: This data always included
- * regardless of state of write bits in the request.
- */
-#define    MC_CMD_RDWR_A64_REGIONS_OUT_LEN 16
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION0_OFST 0
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION0_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION1_OFST 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION1_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION2_OFST 8
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION2_LEN 4
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION3_OFST 12
-#define       MC_CMD_RDWR_A64_REGIONS_OUT_REGION3_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ONLOAD_STACK_ALLOC
- * Allocate an Onload stack ID.
- */
-#define MC_CMD_ONLOAD_STACK_ALLOC 0x9c
-#undef MC_CMD_0x9c_PRIVILEGE_CTG
-
-#define MC_CMD_0x9c_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ONLOAD_STACK_ALLOC_IN msgrequest */
-#define    MC_CMD_ONLOAD_STACK_ALLOC_IN_LEN 4
-/* The handle of the owning upstream port */
-#define       MC_CMD_ONLOAD_STACK_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_ALLOC_IN_UPSTREAM_PORT_ID_LEN 4
-
-/* MC_CMD_ONLOAD_STACK_ALLOC_OUT msgresponse */
-#define    MC_CMD_ONLOAD_STACK_ALLOC_OUT_LEN 4
-/* The handle of the new Onload stack */
-#define       MC_CMD_ONLOAD_STACK_ALLOC_OUT_ONLOAD_STACK_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_ALLOC_OUT_ONLOAD_STACK_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ONLOAD_STACK_FREE
- * Free an Onload stack ID.
- */
-#define MC_CMD_ONLOAD_STACK_FREE 0x9d
-#undef MC_CMD_0x9d_PRIVILEGE_CTG
-
-#define MC_CMD_0x9d_PRIVILEGE_CTG SRIOV_CTG_ONLOAD
-
-/* MC_CMD_ONLOAD_STACK_FREE_IN msgrequest */
-#define    MC_CMD_ONLOAD_STACK_FREE_IN_LEN 4
-/* The handle of the Onload stack */
-#define       MC_CMD_ONLOAD_STACK_FREE_IN_ONLOAD_STACK_ID_OFST 0
-#define       MC_CMD_ONLOAD_STACK_FREE_IN_ONLOAD_STACK_ID_LEN 4
-
-/* MC_CMD_ONLOAD_STACK_FREE_OUT msgresponse */
-#define    MC_CMD_ONLOAD_STACK_FREE_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_RSS_CONTEXT_ALLOC
  * Allocate an RSS context.
@@ -19304,93 +20037,6 @@
 #define       MC_CMD_RSS_CONTEXT_GET_TABLE_OUT_INDIRECTION_TABLE_LEN 128
 
 
-/***********************************/
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE
- * Write a portion of a selectable-size indirection table for an RSS context.
- * This command must be used instead of MC_CMD_RSS_CONTEXT_SET_TABLE if the
- * RSS_SELECTABLE_TABLE_SIZE bit is set in MC_CMD_GET_CAPABILITIES.
- */
-#define MC_CMD_RSS_CONTEXT_WRITE_TABLE 0x13e
-#undef MC_CMD_0x13e_PRIVILEGE_CTG
-
-#define MC_CMD_0x13e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN msgrequest */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMIN 8
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_NUM(len) (((len)-4)/4)
-/* The handle of the RSS context */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_RSS_CONTEXT_ID_OFST 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_RSS_CONTEXT_ID_LEN 4
-/* An array of index-value pairs to be written to the table. Structure is
- * MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY.
- */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_OFST 4
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_LEN 4
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MAXNUM 62
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_IN_ENTRIES_MAXNUM_MCDI2 254
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_OUT msgresponse */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_OUT_LEN 0
-
-/* MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY structuredef */
-#define    MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_LEN 4
-/* The index of the table entry to be written. */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_OFST 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_LEN 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_LBN 0
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_INDEX_WIDTH 16
-/* The value to write into the table entry. */
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_OFST 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_LEN 2
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_LBN 16
-#define       MC_CMD_RSS_CONTEXT_WRITE_TABLE_ENTRY_VALUE_WIDTH 16
-
-
-/***********************************/
-/* MC_CMD_RSS_CONTEXT_READ_TABLE
- * Read a portion of a selectable-size indirection table for an RSS context.
- * This command must be used instead of MC_CMD_RSS_CONTEXT_GET_TABLE if the
- * RSS_SELECTABLE_TABLE_SIZE bit is set in MC_CMD_GET_CAPABILITIES.
- */
-#define MC_CMD_RSS_CONTEXT_READ_TABLE 0x13f
-#undef MC_CMD_0x13f_PRIVILEGE_CTG
-
-#define MC_CMD_0x13f_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RSS_CONTEXT_READ_TABLE_IN msgrequest */
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMIN 6
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_LEN(num) (4+2*(num))
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_NUM(len) (((len)-4)/2)
-/* The handle of the RSS context */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_RSS_CONTEXT_ID_OFST 0
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_RSS_CONTEXT_ID_LEN 4
-/* An array containing the indices of the entries to be read. */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_OFST 4
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_LEN 2
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MAXNUM 124
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_IN_INDICES_MAXNUM_MCDI2 508
-
-/* MC_CMD_RSS_CONTEXT_READ_TABLE_OUT msgresponse */
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMIN 2
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMAX 252
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_LEN(num) (0+2*(num))
-#define    MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_NUM(len) (((len)-0)/2)
-/* A buffer containing the requested entries read from the table. */
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_OFST 0
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_LEN 2
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MINNUM 1
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MAXNUM 126
-#define       MC_CMD_RSS_CONTEXT_READ_TABLE_OUT_DATA_MAXNUM_MCDI2 510
-
-
 /***********************************/
 /* MC_CMD_RSS_CONTEXT_SET_FLAGS
  * Set various control flags for an RSS context.
@@ -19524,158 +20170,6 @@
 #define        MC_CMD_RSS_CONTEXT_GET_FLAGS_OUT_OTHER_IPV6_RSS_MODE_WIDTH 4
 
 
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_ALLOC
- * Allocate a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_ALLOC 0xa4
-#undef MC_CMD_0xa4_PRIVILEGE_CTG
-
-#define MC_CMD_0xa4_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_ALLOC_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_ALLOC_IN_LEN 8
-/* The handle of the owning upstream port */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_UPSTREAM_PORT_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_UPSTREAM_PORT_ID_LEN 4
-/* Number of queues spanned by this mapping, in the range 1-64; valid fixed
- * offsets in the mapping table will be in the range 0 to NUM_QUEUES-1, and
- * referenced RSS contexts must span no more than this number.
- */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_NUM_QUEUES_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_IN_NUM_QUEUES_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_ALLOC_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_ALLOC_OUT_LEN 4
-/* The handle of the new .1p mapping. This should be considered opaque to the
- * host, although a value of 0xFFFFFFFF is guaranteed never to be a valid
- * handle.
- */
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_LEN 4
-/* enum: guaranteed invalid .1p mapping handle value */
-#define          MC_CMD_DOT1P_MAPPING_ALLOC_OUT_DOT1P_MAPPING_ID_INVALID 0xffffffff
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_FREE
- * Free a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_FREE 0xa5
-#undef MC_CMD_0xa5_PRIVILEGE_CTG
-
-#define MC_CMD_0xa5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_FREE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_FREE_IN_LEN 4
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_FREE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_FREE_IN_DOT1P_MAPPING_ID_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_FREE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE
- * Set the mapping table for a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_SET_TABLE 0xa6
-#undef MC_CMD_0xa6_PRIVILEGE_CTG
-
-#define MC_CMD_0xa6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_LEN 36
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_DOT1P_MAPPING_ID_LEN 4
-/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
- * handle)
- */
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_SET_TABLE_IN_MAPPING_TABLE_LEN 32
-
-/* MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_SET_TABLE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE
- * Get the mapping table for a .1p mapping.
- */
-#define MC_CMD_DOT1P_MAPPING_GET_TABLE 0xa7
-#undef MC_CMD_0xa7_PRIVILEGE_CTG
-
-#define MC_CMD_0xa7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE_IN msgrequest */
-#define    MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_LEN 4
-/* The handle of the .1p mapping */
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_DOT1P_MAPPING_ID_OFST 0
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_IN_DOT1P_MAPPING_ID_LEN 4
-
-/* MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT msgresponse */
-#define    MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_LEN 36
-/* Per-priority mappings (1 32-bit word per entry - an offset or RSS context
- * handle)
- */
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_OFST 4
-#define       MC_CMD_DOT1P_MAPPING_GET_TABLE_OUT_MAPPING_TABLE_LEN 32
-
-
-/***********************************/
-/* MC_CMD_GET_VECTOR_CFG
- * Get Interrupt Vector config for this PF.
- */
-#define MC_CMD_GET_VECTOR_CFG 0xbf
-#undef MC_CMD_0xbf_PRIVILEGE_CTG
-
-#define MC_CMD_0xbf_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VECTOR_CFG_IN msgrequest */
-#define    MC_CMD_GET_VECTOR_CFG_IN_LEN 0
-
-/* MC_CMD_GET_VECTOR_CFG_OUT msgresponse */
-#define    MC_CMD_GET_VECTOR_CFG_OUT_LEN 12
-/* Base absolute interrupt vector number. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VEC_BASE_OFST 0
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VEC_BASE_LEN 4
-/* Number of interrupt vectors allocate to this PF. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_PF_OFST 4
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_PF_LEN 4
-/* Number of interrupt vectors to allocate per VF. */
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_VF_OFST 8
-#define       MC_CMD_GET_VECTOR_CFG_OUT_VECS_PER_VF_LEN 4
-
-
-/***********************************/
-/* MC_CMD_SET_VECTOR_CFG
- * Set Interrupt Vector config for this PF.
- */
-#define MC_CMD_SET_VECTOR_CFG 0xc0
-#undef MC_CMD_0xc0_PRIVILEGE_CTG
-
-#define MC_CMD_0xc0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SET_VECTOR_CFG_IN msgrequest */
-#define    MC_CMD_SET_VECTOR_CFG_IN_LEN 12
-/* Base absolute interrupt vector number, or MC_CMD_RESOURCE_INSTANCE_ANY to
- * let the system find a suitable base.
- */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VEC_BASE_OFST 0
-#define       MC_CMD_SET_VECTOR_CFG_IN_VEC_BASE_LEN 4
-/* Number of interrupt vectors allocate to this PF. */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_PF_OFST 4
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_PF_LEN 4
-/* Number of interrupt vectors to allocate per VF. */
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_VF_OFST 8
-#define       MC_CMD_SET_VECTOR_CFG_IN_VECS_PER_VF_LEN 4
-
-/* MC_CMD_SET_VECTOR_CFG_OUT msgresponse */
-#define    MC_CMD_SET_VECTOR_CFG_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_VPORT_ADD_MAC_ADDRESS
  * Add a MAC address to a v-port
@@ -19809,124 +20303,6 @@
 #define        MC_CMD_VPORT_RECONFIGURE_OUT_RESET_DONE_WIDTH 1
 
 
-/***********************************/
-/* MC_CMD_EVB_PORT_QUERY
- * read some config of v-port.
- */
-#define MC_CMD_EVB_PORT_QUERY 0x62
-#undef MC_CMD_0x62_PRIVILEGE_CTG
-
-#define MC_CMD_0x62_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_EVB_PORT_QUERY_IN msgrequest */
-#define    MC_CMD_EVB_PORT_QUERY_IN_LEN 4
-/* The handle of the v-port */
-#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_OFST 0
-#define       MC_CMD_EVB_PORT_QUERY_IN_PORT_ID_LEN 4
-
-/* MC_CMD_EVB_PORT_QUERY_OUT msgresponse */
-#define    MC_CMD_EVB_PORT_QUERY_OUT_LEN 8
-/* The EVB port flags as defined at MC_CMD_VPORT_ALLOC. */
-#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_OFST 0
-#define       MC_CMD_EVB_PORT_QUERY_OUT_PORT_FLAGS_LEN 4
-/* The number of VLAN tags that may be used on a v-adaptor connected to this
- * EVB port.
- */
-#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_OFST 4
-#define       MC_CMD_EVB_PORT_QUERY_OUT_NUM_AVAILABLE_VLAN_TAGS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DUMP_BUFTBL_ENTRIES
- * Dump buffer table entries, mainly for command client debug use. Dumps
- * absolute entries, and does not use chunk handles. All entries must be in
- * range, and used for q page mapping, Although the latter restriction may be
- * lifted in future.
- */
-#define MC_CMD_DUMP_BUFTBL_ENTRIES 0xab
-#undef MC_CMD_0xab_PRIVILEGE_CTG
-
-#define MC_CMD_0xab_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DUMP_BUFTBL_ENTRIES_IN msgrequest */
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_IN_LEN 8
-/* Index of the first buffer table entry. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_FIRSTID_OFST 0
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_FIRSTID_LEN 4
-/* Number of buffer table entries to dump. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_NUMENTRIES_OFST 4
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_IN_NUMENTRIES_LEN 4
-
-/* MC_CMD_DUMP_BUFTBL_ENTRIES_OUT msgresponse */
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMIN 12
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX 252
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_LEN(num) (0+12*(num))
-#define    MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_NUM(len) (((len)-0)/12)
-/* Raw buffer table entries, layed out as BUFTBL_ENTRY. */
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_OFST 0
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_LEN 12
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MINNUM 1
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MAXNUM 21
-#define       MC_CMD_DUMP_BUFTBL_ENTRIES_OUT_ENTRY_MAXNUM_MCDI2 85
-
-
-/***********************************/
-/* MC_CMD_SET_RXDP_CONFIG
- * Set global RXDP configuration settings
- */
-#define MC_CMD_SET_RXDP_CONFIG 0xc1
-#undef MC_CMD_0xc1_PRIVILEGE_CTG
-
-#define MC_CMD_0xc1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_RXDP_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_RXDP_CONFIG_IN_LEN 4
-#define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_OFST 0
-#define       MC_CMD_SET_RXDP_CONFIG_IN_DATA_LEN 4
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_OFST 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_LBN 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_DMA_WIDTH 1
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_OFST 0
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_LBN 1
-#define        MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_LEN_WIDTH 2
-/* enum: pad to 64 bytes */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_64 0x0
-/* enum: pad to 128 bytes (Medford only) */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_128 0x1
-/* enum: pad to 256 bytes (Medford only) */
-#define          MC_CMD_SET_RXDP_CONFIG_IN_PAD_HOST_256 0x2
-
-/* MC_CMD_SET_RXDP_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_RXDP_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_RXDP_CONFIG
- * Get global RXDP configuration settings
- */
-#define MC_CMD_GET_RXDP_CONFIG 0xc2
-#undef MC_CMD_0xc2_PRIVILEGE_CTG
-
-#define MC_CMD_0xc2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_RXDP_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_RXDP_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_RXDP_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_RXDP_CONFIG_OUT_LEN 4
-#define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_OFST 0
-#define       MC_CMD_GET_RXDP_CONFIG_OUT_DATA_LEN 4
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_OFST 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_LBN 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_DMA_WIDTH 1
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_OFST 0
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_LBN 1
-#define        MC_CMD_GET_RXDP_CONFIG_OUT_PAD_HOST_LEN_WIDTH 2
-/*             Enum values, see field(s): */
-/*                MC_CMD_SET_RXDP_CONFIG/MC_CMD_SET_RXDP_CONFIG_IN/PAD_HOST_LEN */
-
-
 /***********************************/
 /* MC_CMD_GET_CLOCK
  * Return the system and PDCPU clock frequencies.
@@ -19949,210 +20325,6 @@
 #define       MC_CMD_GET_CLOCK_OUT_DPCPU_FREQ_LEN 4
 
 
-/***********************************/
-/* MC_CMD_SET_CLOCK
- * Control the system and DPCPU clock frequencies. Changes are lost reboot.
- */
-#define MC_CMD_SET_CLOCK 0xad
-#undef MC_CMD_0xad_PRIVILEGE_CTG
-
-#define MC_CMD_0xad_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_CLOCK_IN msgrequest */
-#define    MC_CMD_SET_CLOCK_IN_LEN 28
-/* Requested frequency in MHz for system clock domain */
-#define       MC_CMD_SET_CLOCK_IN_SYS_FREQ_OFST 0
-#define       MC_CMD_SET_CLOCK_IN_SYS_FREQ_LEN 4
-/* enum: Leave the system clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_SYS_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for inter-core clock domain */
-#define       MC_CMD_SET_CLOCK_IN_ICORE_FREQ_OFST 4
-#define       MC_CMD_SET_CLOCK_IN_ICORE_FREQ_LEN 4
-/* enum: Leave the inter-core clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_ICORE_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for DPCPU clock domain */
-#define       MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_OFST 8
-#define       MC_CMD_SET_CLOCK_IN_DPCPU_FREQ_LEN 4
-/* enum: Leave the DPCPU clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_DPCPU_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for PCS clock domain */
-#define       MC_CMD_SET_CLOCK_IN_PCS_FREQ_OFST 12
-#define       MC_CMD_SET_CLOCK_IN_PCS_FREQ_LEN 4
-/* enum: Leave the PCS clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_PCS_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for MC clock domain */
-#define       MC_CMD_SET_CLOCK_IN_MC_FREQ_OFST 16
-#define       MC_CMD_SET_CLOCK_IN_MC_FREQ_LEN 4
-/* enum: Leave the MC clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_MC_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for rmon clock domain */
-#define       MC_CMD_SET_CLOCK_IN_RMON_FREQ_OFST 20
-#define       MC_CMD_SET_CLOCK_IN_RMON_FREQ_LEN 4
-/* enum: Leave the rmon clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_RMON_DOMAIN_DONT_CHANGE 0x0
-/* Requested frequency in MHz for vswitch clock domain */
-#define       MC_CMD_SET_CLOCK_IN_VSWITCH_FREQ_OFST 24
-#define       MC_CMD_SET_CLOCK_IN_VSWITCH_FREQ_LEN 4
-/* enum: Leave the vswitch clock domain frequency unchanged */
-#define          MC_CMD_SET_CLOCK_IN_VSWITCH_DOMAIN_DONT_CHANGE 0x0
-
-/* MC_CMD_SET_CLOCK_OUT msgresponse */
-#define    MC_CMD_SET_CLOCK_OUT_LEN 28
-/* Resulting system frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_SYS_FREQ_OFST 0
-#define       MC_CMD_SET_CLOCK_OUT_SYS_FREQ_LEN 4
-/* enum: The system clock domain doesn't exist */
-#define          MC_CMD_SET_CLOCK_OUT_SYS_DOMAIN_UNSUPPORTED 0x0
-/* Resulting inter-core frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_OFST 4
-#define       MC_CMD_SET_CLOCK_OUT_ICORE_FREQ_LEN 4
-/* enum: The inter-core clock domain doesn't exist / isn't used */
-#define          MC_CMD_SET_CLOCK_OUT_ICORE_DOMAIN_UNSUPPORTED 0x0
-/* Resulting DPCPU frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_OFST 8
-#define       MC_CMD_SET_CLOCK_OUT_DPCPU_FREQ_LEN 4
-/* enum: The dpcpu clock domain doesn't exist */
-#define          MC_CMD_SET_CLOCK_OUT_DPCPU_DOMAIN_UNSUPPORTED 0x0
-/* Resulting PCS frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_PCS_FREQ_OFST 12
-#define       MC_CMD_SET_CLOCK_OUT_PCS_FREQ_LEN 4
-/* enum: The PCS clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_PCS_DOMAIN_UNSUPPORTED 0x0
-/* Resulting MC frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_MC_FREQ_OFST 16
-#define       MC_CMD_SET_CLOCK_OUT_MC_FREQ_LEN 4
-/* enum: The MC clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_MC_DOMAIN_UNSUPPORTED 0x0
-/* Resulting rmon frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_RMON_FREQ_OFST 20
-#define       MC_CMD_SET_CLOCK_OUT_RMON_FREQ_LEN 4
-/* enum: The rmon clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_RMON_DOMAIN_UNSUPPORTED 0x0
-/* Resulting vswitch frequency in MHz */
-#define       MC_CMD_SET_CLOCK_OUT_VSWITCH_FREQ_OFST 24
-#define       MC_CMD_SET_CLOCK_OUT_VSWITCH_FREQ_LEN 4
-/* enum: The vswitch clock domain doesn't exist / isn't controlled */
-#define          MC_CMD_SET_CLOCK_OUT_VSWITCH_DOMAIN_UNSUPPORTED 0x0
-
-
-/***********************************/
-/* MC_CMD_DPCPU_RPC
- * Send an arbitrary DPCPU message.
- */
-#define MC_CMD_DPCPU_RPC 0xae
-#undef MC_CMD_0xae_PRIVILEGE_CTG
-
-#define MC_CMD_0xae_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_DPCPU_RPC_IN msgrequest */
-#define    MC_CMD_DPCPU_RPC_IN_LEN 36
-#define       MC_CMD_DPCPU_RPC_IN_CPU_OFST 0
-#define       MC_CMD_DPCPU_RPC_IN_CPU_LEN 4
-/* enum: RxDPCPU0 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX0 0x0
-/* enum: TxDPCPU0 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX0 0x1
-/* enum: TxDPCPU1 */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX1 0x2
-/* enum: RxDPCPU1 (Medford only) */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX1 0x3
-/* enum: RxDPCPU (will be for the calling function; for now, just an alias of
- * DPCPU_RX0)
- */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_RX 0x80
-/* enum: TxDPCPU (will be for the calling function; for now, just an alias of
- * DPCPU_TX0)
- */
-#define          MC_CMD_DPCPU_RPC_IN_DPCPU_TX 0x81
-/* First 8 bits [39:32] of DATA are consumed by MC-DPCPU protocol and must be
- * initialised to zero
- */
-#define       MC_CMD_DPCPU_RPC_IN_DATA_OFST 4
-#define       MC_CMD_DPCPU_RPC_IN_DATA_LEN 32
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_LBN 8
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_CMDNUM_WIDTH 8
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_READ 0x6 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_WRITE 0x7 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_SELF_TEST 0xc /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_TXDPCPU_CSR_ACCESS 0xe /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_READ 0x46 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_WRITE 0x47 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SELF_TEST 0x4a /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_CSR_ACCESS 0x4c /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CMDNUM_RXDPCPU_SET_MC_REPLAY_CNTXT 0x4d /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_OBJID_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_ADDR_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_LBN 48
-#define        MC_CMD_DPCPU_RPC_IN_HDR_CMD_REQ_COUNT_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_INFO_WIDTH 240
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_WIDTH 16
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_STOP_RETURN_RESULT 0x0 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_READ 0x1 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE 0x2 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_WRITE_READ 0x3 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_CMD_START_PIPELINED_READ 0x4 /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_LBN 48
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_START_DELAY_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_LBN 64
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_RPT_COUNT_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_LBN 80
-#define        MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_GAP_DELAY_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_LBN 16
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_WIDTH 16
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_CUT_THROUGH 0x1 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD 0x2 /* enum */
-#define          MC_CMD_DPCPU_RPC_IN_MC_REPLAY_MODE_STORE_FORWARD_FIRST 0x3 /* enum */
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_OFST 4
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_LBN 64
-#define        MC_CMD_DPCPU_RPC_IN_MC_REPLAY_CNTXT_WIDTH 16
-#define       MC_CMD_DPCPU_RPC_IN_WDATA_OFST 12
-#define       MC_CMD_DPCPU_RPC_IN_WDATA_LEN 24
-/* Register data to write. Only valid in write/write-read. */
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_DATA_OFST 16
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_DATA_LEN 4
-/* Register address. */
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_ADDRESS_OFST 20
-#define       MC_CMD_DPCPU_RPC_IN_CSR_ACCESS_ADDRESS_LEN 4
-
-/* MC_CMD_DPCPU_RPC_OUT msgresponse */
-#define    MC_CMD_DPCPU_RPC_OUT_LEN 36
-#define       MC_CMD_DPCPU_RPC_OUT_RC_OFST 0
-#define       MC_CMD_DPCPU_RPC_OUT_RC_LEN 4
-/* DATA */
-#define       MC_CMD_DPCPU_RPC_OUT_DATA_OFST 4
-#define       MC_CMD_DPCPU_RPC_OUT_DATA_LEN 32
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_OFST 4
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_LBN 32
-#define        MC_CMD_DPCPU_RPC_OUT_HDR_CMD_RESP_ERRCODE_WIDTH 16
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_OFST 4
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_LBN 48
-#define        MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_COUNT_WIDTH 16
-#define       MC_CMD_DPCPU_RPC_OUT_RDATA_OFST 12
-#define       MC_CMD_DPCPU_RPC_OUT_RDATA_LEN 24
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_1_OFST 12
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_1_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_2_OFST 16
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_2_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_3_OFST 20
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_3_LEN 4
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_4_OFST 24
-#define       MC_CMD_DPCPU_RPC_OUT_CSR_ACCESS_READ_VAL_4_LEN 4
-
-
 /***********************************/
 /* MC_CMD_TRIGGER_INTERRUPT
  * Trigger an interrupt by prodding the BIU.
@@ -20172,66 +20344,6 @@
 #define    MC_CMD_TRIGGER_INTERRUPT_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_SHMBOOT_OP
- * Special operations to support (for now) shmboot.
- */
-#define MC_CMD_SHMBOOT_OP 0xe6
-#undef MC_CMD_0xe6_PRIVILEGE_CTG
-
-#define MC_CMD_0xe6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SHMBOOT_OP_IN msgrequest */
-#define    MC_CMD_SHMBOOT_OP_IN_LEN 4
-/* Identifies the operation to perform */
-#define       MC_CMD_SHMBOOT_OP_IN_SHMBOOT_OP_OFST 0
-#define       MC_CMD_SHMBOOT_OP_IN_SHMBOOT_OP_LEN 4
-/* enum: Copy slave_data section to the slave core. (Greenport only) */
-#define          MC_CMD_SHMBOOT_OP_IN_PUSH_SLAVE_DATA 0x0
-
-/* MC_CMD_SHMBOOT_OP_OUT msgresponse */
-#define    MC_CMD_SHMBOOT_OP_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_CAP_BLK_READ
- * Read multiple 64bit words from capture block memory
- */
-#define MC_CMD_CAP_BLK_READ 0xe7
-#undef MC_CMD_0xe7_PRIVILEGE_CTG
-
-#define MC_CMD_0xe7_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_CAP_BLK_READ_IN msgrequest */
-#define    MC_CMD_CAP_BLK_READ_IN_LEN 12
-#define       MC_CMD_CAP_BLK_READ_IN_CAP_REG_OFST 0
-#define       MC_CMD_CAP_BLK_READ_IN_CAP_REG_LEN 4
-#define       MC_CMD_CAP_BLK_READ_IN_ADDR_OFST 4
-#define       MC_CMD_CAP_BLK_READ_IN_ADDR_LEN 4
-#define       MC_CMD_CAP_BLK_READ_IN_COUNT_OFST 8
-#define       MC_CMD_CAP_BLK_READ_IN_COUNT_LEN 4
-
-/* MC_CMD_CAP_BLK_READ_OUT msgresponse */
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMIN 8
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMAX 248
-#define    MC_CMD_CAP_BLK_READ_OUT_LENMAX_MCDI2 1016
-#define    MC_CMD_CAP_BLK_READ_OUT_LEN(num) (0+8*(num))
-#define    MC_CMD_CAP_BLK_READ_OUT_BUFFER_NUM(len) (((len)-0)/8)
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_OFST 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LEN 8
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_OFST 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_LEN 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_LBN 0
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_WIDTH 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_OFST 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_LEN 4
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_LBN 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_WIDTH 32
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MINNUM 1
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM 31
-#define       MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM_MCDI2 127
-
-
 /***********************************/
 /* MC_CMD_DUMP_DO
  * Take a dump of the DUT state
@@ -20379,34 +20491,6 @@
 #define       MC_CMD_DUMP_CONFIGURE_UNSOLICITED_IN_DUMPFILE_DST_CUSTOM_SIZE_LEN 4
 
 
-/***********************************/
-/* MC_CMD_SET_PSU
- * Adjusts power supply parameters. This is a warranty-voiding operation.
- * Returns: ENOENT if the parameter or rail specified does not exist, EINVAL if
- * the parameter is out of range.
- */
-#define MC_CMD_SET_PSU 0xea
-#undef MC_CMD_0xea_PRIVILEGE_CTG
-
-#define MC_CMD_0xea_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_SET_PSU_IN msgrequest */
-#define    MC_CMD_SET_PSU_IN_LEN 12
-#define       MC_CMD_SET_PSU_IN_PARAM_OFST 0
-#define       MC_CMD_SET_PSU_IN_PARAM_LEN 4
-#define          MC_CMD_SET_PSU_IN_PARAM_SUPPLY_VOLTAGE 0x0 /* enum */
-#define       MC_CMD_SET_PSU_IN_RAIL_OFST 4
-#define       MC_CMD_SET_PSU_IN_RAIL_LEN 4
-#define          MC_CMD_SET_PSU_IN_RAIL_0V9 0x0 /* enum */
-#define          MC_CMD_SET_PSU_IN_RAIL_1V2 0x1 /* enum */
-/* desired value, eg voltage in mV */
-#define       MC_CMD_SET_PSU_IN_VALUE_OFST 8
-#define       MC_CMD_SET_PSU_IN_VALUE_LEN 4
-
-/* MC_CMD_SET_PSU_OUT msgresponse */
-#define    MC_CMD_SET_PSU_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_GET_FUNCTION_INFO
  * Get function information. PF and VF number.
@@ -20448,7 +20532,7 @@
 #define MC_CMD_ENABLE_OFFLINE_BIST 0xed
 #undef MC_CMD_0xed_PRIVILEGE_CTG
 
-#define MC_CMD_0xed_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0xed_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_ENABLE_OFFLINE_BIST_IN msgrequest */
 #define    MC_CMD_ENABLE_OFFLINE_BIST_IN_LEN 0
@@ -20457,130 +20541,6 @@
 #define    MC_CMD_ENABLE_OFFLINE_BIST_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_UART_SEND_DATA
- * Send checksummed[sic] block of data over the uart. Response is a placeholder
- * should we wish to make this reliable; currently requests are fire-and-
- * forget.
- */
-#define MC_CMD_UART_SEND_DATA 0xee
-#undef MC_CMD_0xee_PRIVILEGE_CTG
-
-#define MC_CMD_0xee_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_UART_SEND_DATA_OUT msgrequest */
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMIN 16
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMAX 252
-#define    MC_CMD_UART_SEND_DATA_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_UART_SEND_DATA_OUT_LEN(num) (16+1*(num))
-#define    MC_CMD_UART_SEND_DATA_OUT_DATA_NUM(len) (((len)-16)/1)
-/* CRC32 over OFFSET, LENGTH, RESERVED, DATA */
-#define       MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_OFST 0
-#define       MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_LEN 4
-/* Offset at which to write the data */
-#define       MC_CMD_UART_SEND_DATA_OUT_OFFSET_OFST 4
-#define       MC_CMD_UART_SEND_DATA_OUT_OFFSET_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_SEND_DATA_OUT_LENGTH_OFST 8
-#define       MC_CMD_UART_SEND_DATA_OUT_LENGTH_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_SEND_DATA_OUT_RESERVED_OFST 12
-#define       MC_CMD_UART_SEND_DATA_OUT_RESERVED_LEN 4
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_OFST 16
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_LEN 1
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MINNUM 0
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM 236
-#define       MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM_MCDI2 1004
-
-/* MC_CMD_UART_SEND_DATA_IN msgresponse */
-#define    MC_CMD_UART_SEND_DATA_IN_LEN 0
-
-
-/***********************************/
-/* MC_CMD_UART_RECV_DATA
- * Request checksummed[sic] block of data over the uart. Only a placeholder,
- * subject to change and not currently implemented.
- */
-#define MC_CMD_UART_RECV_DATA 0xef
-#undef MC_CMD_0xef_PRIVILEGE_CTG
-
-#define MC_CMD_0xef_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_UART_RECV_DATA_OUT msgrequest */
-#define    MC_CMD_UART_RECV_DATA_OUT_LEN 16
-/* CRC32 over OFFSET, LENGTH, RESERVED */
-#define       MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_OFST 0
-#define       MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_LEN 4
-/* Offset from which to read the data */
-#define       MC_CMD_UART_RECV_DATA_OUT_OFFSET_OFST 4
-#define       MC_CMD_UART_RECV_DATA_OUT_OFFSET_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_RECV_DATA_OUT_LENGTH_OFST 8
-#define       MC_CMD_UART_RECV_DATA_OUT_LENGTH_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_RECV_DATA_OUT_RESERVED_OFST 12
-#define       MC_CMD_UART_RECV_DATA_OUT_RESERVED_LEN 4
-
-/* MC_CMD_UART_RECV_DATA_IN msgresponse */
-#define    MC_CMD_UART_RECV_DATA_IN_LENMIN 16
-#define    MC_CMD_UART_RECV_DATA_IN_LENMAX 252
-#define    MC_CMD_UART_RECV_DATA_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_UART_RECV_DATA_IN_LEN(num) (16+1*(num))
-#define    MC_CMD_UART_RECV_DATA_IN_DATA_NUM(len) (((len)-16)/1)
-/* CRC32 over RESERVED1, RESERVED2, RESERVED3, DATA */
-#define       MC_CMD_UART_RECV_DATA_IN_CHECKSUM_OFST 0
-#define       MC_CMD_UART_RECV_DATA_IN_CHECKSUM_LEN 4
-/* Offset at which to write the data */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED1_OFST 4
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED1_LEN 4
-/* Length of data */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED2_OFST 8
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED2_LEN 4
-/* Reserved for future use */
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED3_OFST 12
-#define       MC_CMD_UART_RECV_DATA_IN_RESERVED3_LEN 4
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_OFST 16
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_LEN 1
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MINNUM 0
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM 236
-#define       MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM_MCDI2 1004
-
-
-/***********************************/
-/* MC_CMD_READ_FUSES
- * Read data programmed into the device One-Time-Programmable (OTP) Fuses
- */
-#define MC_CMD_READ_FUSES 0xf0
-#undef MC_CMD_0xf0_PRIVILEGE_CTG
-
-#define MC_CMD_0xf0_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_FUSES_IN msgrequest */
-#define    MC_CMD_READ_FUSES_IN_LEN 8
-/* Offset in OTP to read */
-#define       MC_CMD_READ_FUSES_IN_OFFSET_OFST 0
-#define       MC_CMD_READ_FUSES_IN_OFFSET_LEN 4
-/* Length of data to read in bytes */
-#define       MC_CMD_READ_FUSES_IN_LENGTH_OFST 4
-#define       MC_CMD_READ_FUSES_IN_LENGTH_LEN 4
-
-/* MC_CMD_READ_FUSES_OUT msgresponse */
-#define    MC_CMD_READ_FUSES_OUT_LENMIN 4
-#define    MC_CMD_READ_FUSES_OUT_LENMAX 252
-#define    MC_CMD_READ_FUSES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_READ_FUSES_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_READ_FUSES_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Length of returned OTP data in bytes */
-#define       MC_CMD_READ_FUSES_OUT_LENGTH_OFST 0
-#define       MC_CMD_READ_FUSES_OUT_LENGTH_LEN 4
-/* Returned data */
-#define       MC_CMD_READ_FUSES_OUT_DATA_OFST 4
-#define       MC_CMD_READ_FUSES_OUT_DATA_LEN 1
-#define       MC_CMD_READ_FUSES_OUT_DATA_MINNUM 0
-#define       MC_CMD_READ_FUSES_OUT_DATA_MAXNUM 248
-#define       MC_CMD_READ_FUSES_OUT_DATA_MAXNUM_MCDI2 1016
-
-
 /***********************************/
 /* MC_CMD_KR_TUNE
  * Get or set KR Serdes RXEQ and TX Driver settings
@@ -20588,7 +20548,7 @@
 #define MC_CMD_KR_TUNE 0xf1
 #undef MC_CMD_0xf1_PRIVILEGE_CTG
 
-#define MC_CMD_0xf1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
+#define MC_CMD_0xf1_PRIVILEGE_CTG SRIOV_CTG_ADMIN_TSA_UNBOUND
 
 /* MC_CMD_KR_TUNE_IN msgrequest */
 #define    MC_CMD_KR_TUNE_IN_LENMIN 4
@@ -21123,274 +21083,18 @@
 /*               MC_CMD_KR_TUNE_LINK_TRAIN_CMD_IN/CM1 */
 /* C(+1) status */
 #define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_STATUS_OFST 8
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_STATUS_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_KR_TUNE_LINK_TRAIN_CMD_IN/CM1 */
-/* C(-1) value */
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CM1_VALUE_OFST 12
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CM1_VALUE_LEN 4
-/* C(0) value */
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_C0_VALUE_OFST 16
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_C0_VALUE_LEN 4
-/* C(+1) status */
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_VALUE_OFST 20
-#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_VALUE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PCIE_TUNE
- * Get or set PCIE Serdes RXEQ and TX Driver settings
- */
-#define MC_CMD_PCIE_TUNE 0xf2
-#undef MC_CMD_0xf2_PRIVILEGE_CTG
-
-#define MC_CMD_0xf2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PCIE_TUNE_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_IN_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_IN_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_NUM(len) (((len)-4)/4)
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_OP_LEN 1
-/* enum: Get current RXEQ settings */
-#define          MC_CMD_PCIE_TUNE_IN_RXEQ_GET 0x0
-/* enum: Override RXEQ settings */
-#define          MC_CMD_PCIE_TUNE_IN_RXEQ_SET 0x1
-/* enum: Get current TX Driver settings */
-#define          MC_CMD_PCIE_TUNE_IN_TXEQ_GET 0x2
-/* enum: Override TX Driver settings */
-#define          MC_CMD_PCIE_TUNE_IN_TXEQ_SET 0x3
-/* enum: Start PCIe Serdes Eye diagram plot on a given lane. */
-#define          MC_CMD_PCIE_TUNE_IN_START_EYE_PLOT 0x5
-/* enum: Poll PCIe Serdes Eye diagram plot. Returns one row of BER data. The
- * caller should call this command repeatedly after starting eye plot, until no
- * more data is returned.
- */
-#define          MC_CMD_PCIE_TUNE_IN_POLL_EYE_PLOT 0x6
-/* enum: Enable the SERDES BIST and set it to generate a 200MHz square wave */
-#define          MC_CMD_PCIE_TUNE_IN_BIST_SQUARE_WAVE 0x7
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_LEN 3
-/* Arguments specific to the operation */
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_OFST 4
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_LEN 4
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MINNUM 0
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MAXNUM 62
-#define       MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_ARGS_MAXNUM_MCDI2 254
-
-/* MC_CMD_PCIE_TUNE_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_RXEQ_GET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_RXEQ_GET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_NUM(len) (((len)-0)/4)
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM 63
-#define       MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_MAXNUM_MCDI2 255
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: Attenuation (0-15) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_ATT 0x0
-/* enum: CTLE Boost (0-15) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_BOOST 0x1
-/* enum: DFE Tap1 (0 - max negative, 64 - zero, 127 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP1 0x2
-/* enum: DFE Tap2 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP2 0x3
-/* enum: DFE Tap3 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP3 0x4
-/* enum: DFE Tap4 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP4 0x5
-/* enum: DFE Tap5 (0 - max negative, 32 - zero, 63 - max positive) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_TAP5 0x6
-/* enum: DFE DLev */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_DFE_DLEV 0x7
-/* enum: Figure of Merit */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_FOM 0x8
-/* enum: CTLE EQ Capacitor (HF Gain) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQC 0x9
-/* enum: CTLE EQ Resistor (DC Gain) */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_CTLE_EQRES 0xa
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_LANE_WIDTH 5
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_0 0x0 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_1 0x1 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_2 0x2 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_3 0x3 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_4 0x4 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_5 0x5 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_6 0x6 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_7 0x7 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_8 0x8 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_9 0x9 /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_10 0xa /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_11 0xb /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_12 0xc /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_13 0xd /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_14 0xe /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_15 0xf /* enum */
-#define          MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_LANE_ALL 0x10 /* enum */
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_LBN 13
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_AUTOCAL_WIDTH 1
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_LBN 14
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_RESERVED_WIDTH 10
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_OFST 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_LBN 24
-#define        MC_CMD_PCIE_TUNE_RXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_RXEQ_SET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMIN 8
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_LEN(num) (4+4*(num))
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_NUM(len) (((len)-4)/4)
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PCIE_TUNE_RSVD_LEN 3
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_OFST 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM 62
-#define       MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_MAXNUM_MCDI2 254
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_ID_WIDTH 8
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_ID */
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_LANE_WIDTH 5
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_LBN 13
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_AUTOCAL_WIDTH 1
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_LBN 14
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED_WIDTH 2
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_LBN 16
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_PARAM_INITIAL_WIDTH 8
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_OFST 4
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_LBN 24
-#define        MC_CMD_PCIE_TUNE_RXEQ_SET_IN_RESERVED2_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_RXEQ_SET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_RXEQ_SET_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_TXEQ_GET_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_TXEQ_GET_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMIN 4
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_NUM(len) (((len)-0)/4)
-/* RXEQ Parameter */
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_OFST 0
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LEN 4
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MINNUM 1
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63
-#define       MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM_MCDI2 255
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8
-/* enum: TxMargin (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXMARGIN 0x0
-/* enum: TxSwing (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_TXSWING 0x1
-/* enum: De-emphasis coefficient C(-1) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CM1 0x2
-/* enum: De-emphasis coefficient C(0) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_C0 0x3
-/* enum: De-emphasis coefficient C(+1) (PIPE) */
-#define          MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_CP1 0x4
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 4
-/*             Enum values, see field(s): */
-/*                MC_CMD_PCIE_TUNE_RXEQ_GET_OUT/PARAM_LANE */
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_LBN 12
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_RESERVED_WIDTH 12
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_OFST 0
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_LBN 24
-#define        MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8
-
-/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LEN 8
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_OFST 4
-#define       MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_LEN 4
-
-/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT_LEN 0
-
-/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_LEN 4
-/* Requested operation */
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1
-/* Align the arguments to 32 bits */
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3
-
-/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT msgresponse */
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num))
-#define    MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_NUM(len) (((len)-0)/2)
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126
-#define       MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM_MCDI2 510
-
-/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN msgrequest */
-#define    MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_IN_LEN 0
-
-/* MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT msgrequest */
-#define    MC_CMD_PCIE_TUNE_BIST_SQUARE_WAVE_OUT_LEN 0
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_STATUS_LEN 4
+/*            Enum values, see field(s): */
+/*               MC_CMD_KR_TUNE_LINK_TRAIN_CMD_IN/CM1 */
+/* C(-1) value */
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CM1_VALUE_OFST 12
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CM1_VALUE_LEN 4
+/* C(0) value */
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_C0_VALUE_OFST 16
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_C0_VALUE_LEN 4
+/* C(+1) status */
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_VALUE_OFST 20
+#define       MC_CMD_KR_TUNE_LINK_TRAIN_CMD_OUT_CP1_VALUE_LEN 4
 
 
 /***********************************/
@@ -21531,56 +21235,6 @@
 #define       MC_CMD_LICENSING_V3_OUT_RESERVED_1_LEN 24
 
 
-/***********************************/
-/* MC_CMD_LICENSING_GET_ID_V3
- * Get ID and type from the NVRAM_PARTITION_TYPE_LICENSE application license
- * partition - V3 licensing (Medford)
- */
-#define MC_CMD_LICENSING_GET_ID_V3 0xd1
-#undef MC_CMD_0xd1_PRIVILEGE_CTG
-
-#define MC_CMD_0xd1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSING_GET_ID_V3_IN msgrequest */
-#define    MC_CMD_LICENSING_GET_ID_V3_IN_LEN 0
-
-/* MC_CMD_LICENSING_GET_ID_V3_OUT msgresponse */
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMIN 8
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX 252
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LEN(num) (8+1*(num))
-#define    MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_NUM(len) (((len)-8)/1)
-/* type of license (eg 3) */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_OFST 0
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_TYPE_LEN 4
-/* length of the license ID (in bytes) */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_OFST 4
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LENGTH_LEN 4
-/* the unique license ID of the adapter */
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_OFST 8
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_LEN 1
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MINNUM 0
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM 244
-#define       MC_CMD_LICENSING_GET_ID_V3_OUT_LICENSE_ID_MAXNUM_MCDI2 1012
-
-
-/***********************************/
-/* MC_CMD_MC2MC_PROXY
- * Execute an arbitrary MCDI command on the slave MC of a dual-core device.
- * This will fail on a single-core system.
- */
-#define MC_CMD_MC2MC_PROXY 0xf4
-#undef MC_CMD_0xf4_PRIVILEGE_CTG
-
-#define MC_CMD_0xf4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MC2MC_PROXY_IN msgrequest */
-#define    MC_CMD_MC2MC_PROXY_IN_LEN 0
-
-/* MC_CMD_MC2MC_PROXY_OUT msgresponse */
-#define    MC_CMD_MC2MC_PROXY_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_GET_LICENSED_APP_STATE
  * Query the state of an individual licensed application. (Note that the actual
@@ -21609,424 +21263,6 @@
 #define          MC_CMD_GET_LICENSED_APP_STATE_OUT_LICENSED 0x1
 
 
-/***********************************/
-/* MC_CMD_GET_LICENSED_V3_APP_STATE
- * Query the state of an individual licensed application. (Note that the actual
- * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
- * operation or a reboot of the MC.) Used for V3 licensing (Medford)
- */
-#define MC_CMD_GET_LICENSED_V3_APP_STATE 0xd2
-#undef MC_CMD_0xd2_PRIVILEGE_CTG
-
-#define MC_CMD_0xd2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_LICENSED_V3_APP_STATE_IN msgrequest */
-#define    MC_CMD_GET_LICENSED_V3_APP_STATE_IN_LEN 8
-/* application ID to query (LICENSED_V3_APPS_xxx) expressed as a single bit
- * mask
- */
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_IN_APP_ID_HI_WIDTH 32
-
-/* MC_CMD_GET_LICENSED_V3_APP_STATE_OUT msgresponse */
-#define    MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LEN 4
-/* state of this application */
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_STATE_LEN 4
-/* enum: no (or invalid) license is present for the application */
-#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_NOT_LICENSED 0x0
-/* enum: a valid license is present for the application */
-#define          MC_CMD_GET_LICENSED_V3_APP_STATE_OUT_LICENSED 0x1
-
-
-/***********************************/
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES
- * Query the state of an one or more licensed features. (Note that the actual
- * state may be invalidated by the MC_CMD_LICENSING_V3 OP_UPDATE_LICENSE
- * operation or a reboot of the MC.) Used for V3 licensing (Medford)
- */
-#define MC_CMD_GET_LICENSED_V3_FEATURE_STATES 0xd3
-#undef MC_CMD_0xd3_PRIVILEGE_CTG
-
-#define MC_CMD_0xd3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN msgrequest */
-#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_LEN 8
-/* features to query (LICENSED_V3_FEATURES_xxx) expressed as a mask with one or
- * more bits set
- */
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_IN_FEATURES_HI_WIDTH 32
-
-/* MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT msgresponse */
-#define    MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_LEN 8
-/* states of these features - bit set for licensed, clear for not licensed */
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LEN 8
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_OFST 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_LBN 0
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_LO_WIDTH 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_OFST 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_LEN 4
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_LBN 32
-#define       MC_CMD_GET_LICENSED_V3_FEATURE_STATES_OUT_STATES_HI_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_LICENSED_APP_OP
- * Perform an action for an individual licensed application - not used for V3
- * licensing.
- */
-#define MC_CMD_LICENSED_APP_OP 0xf6
-#undef MC_CMD_0xf6_PRIVILEGE_CTG
-
-#define MC_CMD_0xf6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSED_APP_OP_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMIN 8
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMAX 252
-#define    MC_CMD_LICENSED_APP_OP_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSED_APP_OP_IN_LEN(num) (8+4*(num))
-#define    MC_CMD_LICENSED_APP_OP_IN_ARGS_NUM(len) (((len)-8)/4)
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_IN_OP_LEN 4
-/* enum: validate application */
-#define          MC_CMD_LICENSED_APP_OP_IN_OP_VALIDATE 0x0
-/* enum: mask application */
-#define          MC_CMD_LICENSED_APP_OP_IN_OP_MASK 0x1
-/* arguments specific to this particular operation */
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_LEN 4
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MINNUM 0
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM 61
-#define       MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM_MCDI2 253
-
-/* MC_CMD_LICENSED_APP_OP_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMIN 0
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMAX 252
-#define    MC_CMD_LICENSED_APP_OP_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_LICENSED_APP_OP_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_LICENSED_APP_OP_OUT_RESULT_NUM(len) (((len)-0)/4)
-/* result specific to this particular operation */
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_LEN 4
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MINNUM 0
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM 63
-#define       MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM_MCDI2 255
-
-/* MC_CMD_LICENSED_APP_OP_VALIDATE_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_VALIDATE_IN_LEN 72
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_LEN 4
-/* validation challenge */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_LEN 64
-
-/* MC_CMD_LICENSED_APP_OP_VALIDATE_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_LEN 68
-/* feature expiry (time_t) */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_LEN 4
-/* validation response */
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_LEN 64
-
-/* MC_CMD_LICENSED_APP_OP_MASK_IN msgrequest */
-#define    MC_CMD_LICENSED_APP_OP_MASK_IN_LEN 12
-/* application ID */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_APP_ID_OFST 0
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_APP_ID_LEN 4
-/* the type of operation requested */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_OP_OFST 4
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_OP_LEN 4
-/* flag */
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_FLAG_OFST 8
-#define       MC_CMD_LICENSED_APP_OP_MASK_IN_FLAG_LEN 4
-
-/* MC_CMD_LICENSED_APP_OP_MASK_OUT msgresponse */
-#define    MC_CMD_LICENSED_APP_OP_MASK_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LICENSED_V3_VALIDATE_APP
- * Perform validation for an individual licensed application - V3 licensing
- * (Medford)
- */
-#define MC_CMD_LICENSED_V3_VALIDATE_APP 0xd4
-#undef MC_CMD_0xd4_PRIVILEGE_CTG
-
-#define MC_CMD_0xd4_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_LICENSED_V3_VALIDATE_APP_IN msgrequest */
-#define    MC_CMD_LICENSED_V3_VALIDATE_APP_IN_LEN 56
-/* challenge for validation (384 bits) */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_OFST 0
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_CHALLENGE_LEN 48
-/* application ID expressed as a single bit mask */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_OFST 48
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LEN 8
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_OFST 48
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_LEN 4
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_LBN 384
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_LO_WIDTH 32
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_OFST 52
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_LEN 4
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_LBN 416
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_IN_APP_ID_HI_WIDTH 32
-
-/* MC_CMD_LICENSED_V3_VALIDATE_APP_OUT msgresponse */
-#define    MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_LEN 116
-/* validation response to challenge in the form of ECDSA signature consisting
- * of two 384-bit integers, r and s, in big-endian order. The signature signs a
- * SHA-384 digest of a message constructed from the concatenation of the input
- * message and the remaining fields of this output message, e.g. challenge[48
- * bytes] ... expiry_time[4 bytes] ...
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_OFST 0
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_RESPONSE_LEN 96
-/* application expiry time */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_OFST 96
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_TIME_LEN 4
-/* application expiry units */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_OFST 100
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNITS_LEN 4
-/* enum: expiry units are accounting units */
-#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_ACC 0x0
-/* enum: expiry units are calendar days */
-#define          MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_EXPIRY_UNIT_DAYS 0x1
-/* base MAC address of the NIC stored in NVRAM (note that this is a constant
- * value for a given NIC regardless which function is calling, effectively this
- * is PF0 base MAC address)
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_OFST 104
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_BASE_MACADDR_LEN 6
-/* MAC address of v-adaptor associated with the client. If no such v-adapator
- * exists, then the field is filled with 0xFF.
- */
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_OFST 110
-#define       MC_CMD_LICENSED_V3_VALIDATE_APP_OUT_VADAPTOR_MACADDR_LEN 6
-
-
-/***********************************/
-/* MC_CMD_LICENSED_V3_MASK_FEATURES
- * Mask features - V3 licensing (Medford)
- */
-#define MC_CMD_LICENSED_V3_MASK_FEATURES 0xd5
-#undef MC_CMD_0xd5_PRIVILEGE_CTG
-
-#define MC_CMD_0xd5_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_LICENSED_V3_MASK_FEATURES_IN msgrequest */
-#define    MC_CMD_LICENSED_V3_MASK_FEATURES_IN_LEN 12
-/* mask to be applied to features to be changed */
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_OFST 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LEN 8
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_OFST 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_LEN 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_LBN 0
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_LO_WIDTH 32
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_OFST 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_LEN 4
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_LBN 32
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_MASK_HI_WIDTH 32
-/* whether to turn on or turn off the masked features */
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_OFST 8
-#define       MC_CMD_LICENSED_V3_MASK_FEATURES_IN_FLAG_LEN 4
-/* enum: turn the features off */
-#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_OFF 0x0
-/* enum: turn the features back on */
-#define          MC_CMD_LICENSED_V3_MASK_FEATURES_IN_ON 0x1
-
-/* MC_CMD_LICENSED_V3_MASK_FEATURES_OUT msgresponse */
-#define    MC_CMD_LICENSED_V3_MASK_FEATURES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_LICENSING_V3_TEMPORARY
- * Perform operations to support installation of a single temporary license in
- * the adapter, in addition to those found in the licensing partition. See
- * SF-116124-SW for an overview of how this could be used. The license is
- * stored in MC persistent data and so will survive a MC reboot, but will be
- * erased when the adapter is power cycled
- */
-#define MC_CMD_LICENSING_V3_TEMPORARY 0xd6
-#undef MC_CMD_0xd6_PRIVILEGE_CTG
-
-#define MC_CMD_0xd6_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_LEN 4
-/* operation code */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_OP_LEN 4
-/* enum: install a new license, overwriting any existing temporary license.
- * This is an asynchronous operation owing to the time taken to validate an
- * ECDSA license
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_SET 0x0
-/* enum: clear the license immediately rather than waiting for the next power
- * cycle
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_CLEAR 0x1
-/* enum: get the status of the asynchronous MC_CMD_LICENSING_V3_TEMPORARY_SET
- * operation
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS 0x2
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_SET msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LEN 164
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_OP_LEN 4
-/* ECDSA license and signature */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_SET_LICENSE_LEN 160
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_CLEAR_OP_LEN 4
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS msgrequest */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_OP_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_IN_STATUS_OP_LEN 4
-
-/* MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS msgresponse */
-#define    MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LEN 12
-/* status code */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_STATUS_OFST 0
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_STATUS_LEN 4
-/* enum: finished validating and installing license */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_OK 0x0
-/* enum: license validation and installation in progress */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_IN_PROGRESS 0x1
-/* enum: licensing error. More specific error messages are not provided to
- * avoid exposing details of the licensing system to the client
- */
-#define          MC_CMD_LICENSING_V3_TEMPORARY_STATUS_ERROR 0x2
-/* bitmask of licensed features */
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LEN 8
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_OFST 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_LBN 32
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_LO_WIDTH 32
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_OFST 8
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_LEN 4
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_LBN 64
-#define       MC_CMD_LICENSING_V3_TEMPORARY_OUT_STATUS_LICENSED_FEATURES_HI_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_SET_PORT_SNIFF_CONFIG
- * Configure RX port sniffing for the physical port associated with the calling
- * function. Only a privileged function may change the port sniffing
- * configuration. A copy of all traffic delivered to the host (non-promiscuous
- * mode) or all traffic arriving at the port (promiscuous mode) may be
- * delivered to a specific queue, or a set of queues with RSS.
- */
-#define MC_CMD_SET_PORT_SNIFF_CONFIG 0xf7
-#undef MC_CMD_0xf7_PRIVILEGE_CTG
-
-#define MC_CMD_0xf7_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_PORT_SNIFF_CONFIG_IN_LEN 16
-/* configuration flags */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_OFST 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_OFST 0
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_LBN 1
-#define        MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_WIDTH 1
-/* receive queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_LEN 4
-/* enum: receive to just the specified queue */
-#define          MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0
-/* enum: receive to multiple queues using RSS context */
-#define          MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note
- * that these handles should be considered opaque to the host, although a value
- * of 0xFFFFFFFF is guaranteed never to be a valid handle.
- */
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12
-#define       MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_LEN 4
-
-/* MC_CMD_SET_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_PORT_SNIFF_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_PORT_SNIFF_CONFIG
- * Obtain the current RX port sniffing configuration for the physical port
- * associated with the calling function. Only a privileged function may read
- * the configuration.
- */
-#define MC_CMD_GET_PORT_SNIFF_CONFIG 0xf8
-#undef MC_CMD_0xf8_PRIVILEGE_CTG
-
-#define MC_CMD_0xf8_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_PORT_SNIFF_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_LEN 16
-/* configuration flags */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_OFST 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_OFST 0
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_LBN 1
-#define        MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_WIDTH 1
-/* receiving queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_LEN 4
-/* enum: receiving to just the specified queue */
-#define          MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0
-/* enum: receiving to multiple queues using RSS context */
-#define          MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) */
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12
-#define       MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_LEN 4
-
-
 /***********************************/
 /* MC_CMD_SET_PARSER_DISP_CONFIG
  * Change configuration related to the parser-dispatcher subsystem.
@@ -22072,305 +21308,6 @@
 #define    MC_CMD_SET_PARSER_DISP_CONFIG_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_GET_PARSER_DISP_CONFIG
- * Read configuration related to the parser-dispatcher subsystem.
- */
-#define MC_CMD_GET_PARSER_DISP_CONFIG 0xfa
-#undef MC_CMD_0xfa_PRIVILEGE_CTG
-
-#define MC_CMD_0xfa_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PARSER_DISP_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_IN_LEN 8
-/* the type of configuration setting to read */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_TYPE_OFST 0
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_SET_PARSER_DISP_CONFIG/MC_CMD_SET_PARSER_DISP_CONFIG_IN/TYPE */
-/* handle for the entity to query: queue handle, EVB port ID, etc. depending on
- * the type of configuration setting being read
- */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_ENTITY_OFST 4
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_IN_ENTITY_LEN 4
-
-/* MC_CMD_GET_PARSER_DISP_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMIN 4
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMAX 252
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_NUM(len) (((len)-0)/4)
-/* current value: the details depend on the type of configuration setting being
- * read
- */
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_OFST 0
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_LEN 4
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MINNUM 1
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MAXNUM 63
-#define       MC_CMD_GET_PARSER_DISP_CONFIG_OUT_VALUE_MAXNUM_MCDI2 255
-
-
-/***********************************/
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG
- * Configure TX port sniffing for the physical port associated with the calling
- * function. Only a privileged function may change the port sniffing
- * configuration. A copy of all traffic transmitted through the port may be
- * delivered to a specific queue, or a set of queues with RSS. Note that these
- * packets are delivered with transmit timestamps in the packet prefix, not
- * receive timestamps, so it is likely that the queue(s) will need to be
- * dedicated as TX sniff receivers.
- */
-#define MC_CMD_SET_TX_PORT_SNIFF_CONFIG 0xfb
-#undef MC_CMD_0xfb_PRIVILEGE_CTG
-
-#define MC_CMD_0xfb_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_LEN 16
-/* configuration flags */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_FLAGS_LEN 4
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_OFST 0
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0
-#define        MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1
-/* receive queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_LEN 4
-/* enum: receive to just the specified queue */
-#define          MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0
-/* enum: receive to multiple queues using RSS context */
-#define          MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note
- * that these handles should be considered opaque to the host, although a value
- * of 0xFFFFFFFF is guaranteed never to be a valid handle.
- */
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12
-#define       MC_CMD_SET_TX_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_LEN 4
-
-/* MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_SET_TX_PORT_SNIFF_CONFIG_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG
- * Obtain the current TX port sniffing configuration for the physical port
- * associated with the calling function. Only a privileged function may read
- * the configuration.
- */
-#define MC_CMD_GET_TX_PORT_SNIFF_CONFIG 0xfc
-#undef MC_CMD_0xfc_PRIVILEGE_CTG
-
-#define MC_CMD_0xfc_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN msgrequest */
-#define    MC_CMD_GET_TX_PORT_SNIFF_CONFIG_IN_LEN 0
-
-/* MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT msgresponse */
-#define    MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_LEN 16
-/* configuration flags */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_OFST 0
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0
-#define        MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1
-/* receiving queue handle (for RSS mode, this is the base queue) */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_LEN 4
-/* receive mode */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_LEN 4
-/* enum: receiving to just the specified queue */
-#define          MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0
-/* enum: receiving to multiple queues using RSS context */
-#define          MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1
-/* RSS context (for RX_MODE_RSS) */
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12
-#define       MC_CMD_GET_TX_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_RMON_STATS_RX_ERRORS
- * Per queue rx error stats.
- */
-#define MC_CMD_RMON_STATS_RX_ERRORS 0xfe
-#undef MC_CMD_0xfe_PRIVILEGE_CTG
-
-#define MC_CMD_0xfe_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_RMON_STATS_RX_ERRORS_IN msgrequest */
-#define    MC_CMD_RMON_STATS_RX_ERRORS_IN_LEN 8
-/* The rx queue to get stats for. */
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_RX_QUEUE_OFST 0
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_RX_QUEUE_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_FLAGS_OFST 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_IN_FLAGS_LEN 4
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_OFST 4
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_LBN 0
-#define        MC_CMD_RMON_STATS_RX_ERRORS_IN_RST_WIDTH 1
-
-/* MC_CMD_RMON_STATS_RX_ERRORS_OUT msgresponse */
-#define    MC_CMD_RMON_STATS_RX_ERRORS_OUT_LEN 16
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_CRC_ERRORS_OFST 0
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_CRC_ERRORS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_TRUNC_ERRORS_OFST 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_TRUNC_ERRORS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_NO_DESC_DROPS_OFST 8
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_NO_DESC_DROPS_LEN 4
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_ABORT_OFST 12
-#define       MC_CMD_RMON_STATS_RX_ERRORS_OUT_RX_ABORT_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_PCIE_RESOURCE_INFO
- * Find out about available PCIE resources
- */
-#define MC_CMD_GET_PCIE_RESOURCE_INFO 0xfd
-#undef MC_CMD_0xfd_PRIVILEGE_CTG
-
-#define MC_CMD_0xfd_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PCIE_RESOURCE_INFO_IN msgrequest */
-#define    MC_CMD_GET_PCIE_RESOURCE_INFO_IN_LEN 0
-
-/* MC_CMD_GET_PCIE_RESOURCE_INFO_OUT msgresponse */
-#define    MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_LEN 28
-/* The maximum number of PFs the device can expose */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PFS_OFST 0
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PFS_LEN 4
-/* The maximum number of VFs the device can expose in total */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VFS_OFST 4
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VFS_LEN 4
-/* The maximum number of MSI-X vectors the device can provide in total */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VECTORS_OFST 8
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VECTORS_LEN 4
-/* the number of MSI-X vectors the device will allocate by default to each PF
- */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_PF_VECTORS_OFST 12
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_PF_VECTORS_LEN 4
-/* the number of MSI-X vectors the device will allocate by default to each VF
- */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_VF_VECTORS_OFST 16
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_DEFAULT_VF_VECTORS_LEN 4
-/* the maximum number of MSI-X vectors the device can allocate to any one PF */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PF_VECTORS_OFST 20
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_PF_VECTORS_LEN 4
-/* the maximum number of MSI-X vectors the device can allocate to any one VF */
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VF_VECTORS_OFST 24
-#define       MC_CMD_GET_PCIE_RESOURCE_INFO_OUT_MAX_VF_VECTORS_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_PORT_MODES
- * Find out about available port modes
- */
-#define MC_CMD_GET_PORT_MODES 0xff
-#undef MC_CMD_0xff_PRIVILEGE_CTG
-
-#define MC_CMD_0xff_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_PORT_MODES_IN msgrequest */
-#define    MC_CMD_GET_PORT_MODES_IN_LEN 0
-
-/* MC_CMD_GET_PORT_MODES_OUT msgresponse */
-#define    MC_CMD_GET_PORT_MODES_OUT_LEN 12
-/* Bitmask of port modes available on the board (indexed by TLV_PORT_MODE_*)
- * that are supported for customer use in production firmware.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_MODES_OFST 0
-#define       MC_CMD_GET_PORT_MODES_OUT_MODES_LEN 4
-/* Default (canonical) board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_DEFAULT_MODE_OFST 4
-#define       MC_CMD_GET_PORT_MODES_OUT_DEFAULT_MODE_LEN 4
-/* Current board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_CURRENT_MODE_OFST 8
-#define       MC_CMD_GET_PORT_MODES_OUT_CURRENT_MODE_LEN 4
-
-/* MC_CMD_GET_PORT_MODES_OUT_V2 msgresponse */
-#define    MC_CMD_GET_PORT_MODES_OUT_V2_LEN 16
-/* Bitmask of port modes available on the board (indexed by TLV_PORT_MODE_*)
- * that are supported for customer use in production firmware.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_MODES_OFST 0
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_MODES_LEN 4
-/* Default (canonical) board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_DEFAULT_MODE_OFST 4
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_DEFAULT_MODE_LEN 4
-/* Current board mode */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_CURRENT_MODE_OFST 8
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_CURRENT_MODE_LEN 4
-/* Bitmask of engineering port modes available on the board (indexed by
- * TLV_PORT_MODE_*). A superset of MC_CMD_GET_PORT_MODES_OUT/MODES that
- * contains all modes implemented in firmware for a particular board. Modes
- * listed in MODES are considered production modes and should be exposed in
- * userland tools. Modes listed in ENGINEERING_MODES, but not in MODES
- * should be considered hidden (not to be exposed in userland tools) and for
- * engineering use only. There are no other semantic differences and any mode
- * listed in either MODES or ENGINEERING_MODES can be set on the board.
- */
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_ENGINEERING_MODES_OFST 12
-#define       MC_CMD_GET_PORT_MODES_OUT_V2_ENGINEERING_MODES_LEN 4
-
-
-/***********************************/
-/* MC_CMD_OVERRIDE_PORT_MODE
- * Override flash config port mode for subsequent MC reboot(s). Override data
- * is stored in the presistent data section of DMEM and activated on next MC
- * warm reboot. A cold reboot resets the override. It is assumed that a
- * sufficient number of PFs are available and that port mapping is valid for
- * the new port mode, as the override does not affect PF configuration.
- */
-#define MC_CMD_OVERRIDE_PORT_MODE 0x137
-#undef MC_CMD_0x137_PRIVILEGE_CTG
-
-#define MC_CMD_0x137_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_OVERRIDE_PORT_MODE_IN msgrequest */
-#define    MC_CMD_OVERRIDE_PORT_MODE_IN_LEN 8
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_FLAGS_OFST 0
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_FLAGS_LEN 4
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_OFST 0
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_LBN 0
-#define        MC_CMD_OVERRIDE_PORT_MODE_IN_ENABLE_WIDTH 1
-/* New mode (TLV_PORT_MODE_*) to set, if override enabled */
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_MODE_OFST 4
-#define       MC_CMD_OVERRIDE_PORT_MODE_IN_MODE_LEN 4
-
-/* MC_CMD_OVERRIDE_PORT_MODE_OUT msgresponse */
-#define    MC_CMD_OVERRIDE_PORT_MODE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_READ_ATB
- * Sample voltages on the ATB
- */
-#define MC_CMD_READ_ATB 0x100
-#undef MC_CMD_0x100_PRIVILEGE_CTG
-
-#define MC_CMD_0x100_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_READ_ATB_IN msgrequest */
-#define    MC_CMD_READ_ATB_IN_LEN 16
-#define       MC_CMD_READ_ATB_IN_SIGNAL_BUS_OFST 0
-#define       MC_CMD_READ_ATB_IN_SIGNAL_BUS_LEN 4
-#define          MC_CMD_READ_ATB_IN_BUS_CCOM 0x0 /* enum */
-#define          MC_CMD_READ_ATB_IN_BUS_CKR 0x1 /* enum */
-#define          MC_CMD_READ_ATB_IN_BUS_CPCIE 0x8 /* enum */
-#define       MC_CMD_READ_ATB_IN_SIGNAL_EN_BITNO_OFST 4
-#define       MC_CMD_READ_ATB_IN_SIGNAL_EN_BITNO_LEN 4
-#define       MC_CMD_READ_ATB_IN_SIGNAL_SEL_OFST 8
-#define       MC_CMD_READ_ATB_IN_SIGNAL_SEL_LEN 4
-#define       MC_CMD_READ_ATB_IN_SETTLING_TIME_US_OFST 12
-#define       MC_CMD_READ_ATB_IN_SETTLING_TIME_US_LEN 4
-
-/* MC_CMD_READ_ATB_OUT msgresponse */
-#define    MC_CMD_READ_ATB_OUT_LEN 4
-#define       MC_CMD_READ_ATB_OUT_SAMPLE_MV_OFST 0
-#define       MC_CMD_READ_ATB_OUT_SAMPLE_MV_LEN 4
-
-
 /***********************************/
 /* MC_CMD_GET_WORKAROUNDS
  * Read the list of all implemented and all currently enabled workarounds. The
@@ -22538,447 +21475,6 @@
 #define       MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_OFST 0
 #define       MC_CMD_LINK_STATE_MODE_OUT_OLD_MODE_LEN 4
 
-
-/***********************************/
-/* MC_CMD_GET_SNAPSHOT_LENGTH
- * Obtain the current range of allowable values for the SNAPSHOT_LENGTH
- * parameter to MC_CMD_INIT_RXQ.
- */
-#define MC_CMD_GET_SNAPSHOT_LENGTH 0x101
-#undef MC_CMD_0x101_PRIVILEGE_CTG
-
-#define MC_CMD_0x101_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_SNAPSHOT_LENGTH_IN msgrequest */
-#define    MC_CMD_GET_SNAPSHOT_LENGTH_IN_LEN 0
-
-/* MC_CMD_GET_SNAPSHOT_LENGTH_OUT msgresponse */
-#define    MC_CMD_GET_SNAPSHOT_LENGTH_OUT_LEN 8
-/* Minimum acceptable snapshot length. */
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MIN_OFST 0
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MIN_LEN 4
-/* Maximum acceptable snapshot length. */
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MAX_OFST 4
-#define       MC_CMD_GET_SNAPSHOT_LENGTH_OUT_RX_SNAPLEN_MAX_LEN 4
-
-
-/***********************************/
-/* MC_CMD_FUSE_DIAGS
- * Additional fuse diagnostics
- */
-#define MC_CMD_FUSE_DIAGS 0x102
-#undef MC_CMD_0x102_PRIVILEGE_CTG
-
-#define MC_CMD_0x102_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_FUSE_DIAGS_IN msgrequest */
-#define    MC_CMD_FUSE_DIAGS_IN_LEN 0
-
-/* MC_CMD_FUSE_DIAGS_OUT msgresponse */
-#define    MC_CMD_FUSE_DIAGS_OUT_LEN 48
-/* Total number of mismatched bits between pairs in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_MISMATCH_BITS_OFST 0
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_A_BAD_BITS_OFST 4
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_B_BAD_BITS_OFST 8
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 0 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_CHECKSUM_OFST 12
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA0_CHECKSUM_LEN 4
-/* Total number of mismatched bits between pairs in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_MISMATCH_BITS_OFST 16
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_A_BAD_BITS_OFST 20
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_B_BAD_BITS_OFST 24
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 1 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_CHECKSUM_OFST 28
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA1_CHECKSUM_LEN 4
-/* Total number of mismatched bits between pairs in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_MISMATCH_BITS_OFST 32
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_MISMATCH_BITS_LEN 4
-/* Total number of unexpectedly clear (set in B but not A) bits in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_A_BAD_BITS_OFST 36
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_A_BAD_BITS_LEN 4
-/* Total number of unexpectedly clear (set in A but not B) bits in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_B_BAD_BITS_OFST 40
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_PAIR_B_BAD_BITS_LEN 4
-/* Checksum of data after logical OR of pairs in area 2 */
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_CHECKSUM_OFST 44
-#define       MC_CMD_FUSE_DIAGS_OUT_AREA2_CHECKSUM_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PRIVILEGE_MODIFY
- * Modify the privileges of a set of PCIe functions. Note that this operation
- * only effects non-admin functions unless the admin privilege itself is
- * included in one of the masks provided.
- */
-#define MC_CMD_PRIVILEGE_MODIFY 0x60
-#undef MC_CMD_0x60_PRIVILEGE_CTG
-
-#define MC_CMD_0x60_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PRIVILEGE_MODIFY_IN msgrequest */
-#define    MC_CMD_PRIVILEGE_MODIFY_IN_LEN 16
-/* The groups of functions to have their privilege masks modified. */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FN_GROUP_OFST 0
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FN_GROUP_LEN 4
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_NONE 0x0 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_ALL 0x1 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_PFS_ONLY 0x2 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_VFS_ONLY 0x3 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_VFS_OF_PF 0x4 /* enum */
-#define          MC_CMD_PRIVILEGE_MODIFY_IN_ONE 0x5 /* enum */
-/* For VFS_OF_PF specify the PF, for ONE specify the target function */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_OFST 4
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_LEN 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_OFST 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_LBN 0
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_PF_WIDTH 16
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_OFST 4
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_LBN 16
-#define        MC_CMD_PRIVILEGE_MODIFY_IN_FUNCTION_VF_WIDTH 16
-/* Privileges to be added to the target functions. For privilege definitions
- * refer to the command MC_CMD_PRIVILEGE_MASK
- */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_ADD_MASK_OFST 8
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_ADD_MASK_LEN 4
-/* Privileges to be removed from the target functions. For privilege
- * definitions refer to the command MC_CMD_PRIVILEGE_MASK
- */
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_REMOVE_MASK_OFST 12
-#define       MC_CMD_PRIVILEGE_MODIFY_IN_REMOVE_MASK_LEN 4
-
-/* MC_CMD_PRIVILEGE_MODIFY_OUT msgresponse */
-#define    MC_CMD_PRIVILEGE_MODIFY_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_READ_BYTES
- * Read XPM memory
- */
-#define MC_CMD_XPM_READ_BYTES 0x103
-#undef MC_CMD_0x103_PRIVILEGE_CTG
-
-#define MC_CMD_0x103_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_XPM_READ_BYTES_IN msgrequest */
-#define    MC_CMD_XPM_READ_BYTES_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_READ_BYTES_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_READ_BYTES_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_READ_BYTES_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_READ_BYTES_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_READ_BYTES_OUT msgresponse */
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMIN 0
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMAX 252
-#define    MC_CMD_XPM_READ_BYTES_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_READ_BYTES_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_XPM_READ_BYTES_OUT_DATA_NUM(len) (((len)-0)/1)
-/* Data */
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_OFST 0
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_LEN 1
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MINNUM 0
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MAXNUM 252
-#define       MC_CMD_XPM_READ_BYTES_OUT_DATA_MAXNUM_MCDI2 1020
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_BYTES
- * Write XPM memory
- */
-#define MC_CMD_XPM_WRITE_BYTES 0x104
-#undef MC_CMD_0x104_PRIVILEGE_CTG
-
-#define MC_CMD_0x104_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_BYTES_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMIN 8
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMAX 252
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_WRITE_BYTES_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_XPM_WRITE_BYTES_IN_DATA_NUM(len) (((len)-8)/1)
-/* Start address (byte) */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_WRITE_BYTES_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_WRITE_BYTES_IN_COUNT_LEN 4
-/* Data */
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_OFST 8
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_LEN 1
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MINNUM 0
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MAXNUM 244
-#define       MC_CMD_XPM_WRITE_BYTES_IN_DATA_MAXNUM_MCDI2 1012
-
-/* MC_CMD_XPM_WRITE_BYTES_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_BYTES_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_READ_SECTOR
- * Read XPM sector
- */
-#define MC_CMD_XPM_READ_SECTOR 0x105
-#undef MC_CMD_0x105_PRIVILEGE_CTG
-
-#define MC_CMD_0x105_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_READ_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_READ_SECTOR_IN_LEN 8
-/* Sector index */
-#define       MC_CMD_XPM_READ_SECTOR_IN_INDEX_OFST 0
-#define       MC_CMD_XPM_READ_SECTOR_IN_INDEX_LEN 4
-/* Sector size */
-#define       MC_CMD_XPM_READ_SECTOR_IN_SIZE_OFST 4
-#define       MC_CMD_XPM_READ_SECTOR_IN_SIZE_LEN 4
-
-/* MC_CMD_XPM_READ_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMIN 4
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMAX 36
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LENMAX_MCDI2 36
-#define    MC_CMD_XPM_READ_SECTOR_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_XPM_READ_SECTOR_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Sector type */
-#define       MC_CMD_XPM_READ_SECTOR_OUT_TYPE_OFST 0
-#define       MC_CMD_XPM_READ_SECTOR_OUT_TYPE_LEN 4
-#define          MC_CMD_XPM_READ_SECTOR_OUT_BLANK 0x0 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_128 0x1 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_KEY_256 0x2 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_CRYPTO_DATA 0x3 /* enum */
-#define          MC_CMD_XPM_READ_SECTOR_OUT_INVALID 0xff /* enum */
-/* Sector data */
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_OFST 4
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_LEN 1
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MINNUM 0
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MAXNUM 32
-#define       MC_CMD_XPM_READ_SECTOR_OUT_DATA_MAXNUM_MCDI2 32
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_SECTOR
- * Write XPM sector
- */
-#define MC_CMD_XPM_WRITE_SECTOR 0x106
-#undef MC_CMD_0x106_PRIVILEGE_CTG
-
-#define MC_CMD_0x106_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMIN 12
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMAX 44
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LENMAX_MCDI2 44
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_LEN(num) (12+1*(num))
-#define    MC_CMD_XPM_WRITE_SECTOR_IN_DATA_NUM(len) (((len)-12)/1)
-/* If writing fails due to an uncorrectable error, try up to RETRIES following
- * sectors (or until no more space available). If 0, only one write attempt is
- * made. Note that uncorrectable errors are unlikely, thanks to XPM self-repair
- * mechanism.
- */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_OFST 0
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RETRIES_LEN 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_OFST 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_RESERVED_LEN 3
-/* Sector type */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_OFST 4
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_XPM_READ_SECTOR/MC_CMD_XPM_READ_SECTOR_OUT/TYPE */
-/* Sector size */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_OFST 8
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_SIZE_LEN 4
-/* Sector data */
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_OFST 12
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_LEN 1
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MINNUM 0
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MAXNUM 32
-#define       MC_CMD_XPM_WRITE_SECTOR_IN_DATA_MAXNUM_MCDI2 32
-
-/* MC_CMD_XPM_WRITE_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_SECTOR_OUT_LEN 4
-/* New sector index */
-#define       MC_CMD_XPM_WRITE_SECTOR_OUT_INDEX_OFST 0
-#define       MC_CMD_XPM_WRITE_SECTOR_OUT_INDEX_LEN 4
-
-
-/***********************************/
-/* MC_CMD_XPM_INVALIDATE_SECTOR
- * Invalidate XPM sector
- */
-#define MC_CMD_XPM_INVALIDATE_SECTOR 0x107
-#undef MC_CMD_0x107_PRIVILEGE_CTG
-
-#define MC_CMD_0x107_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_INVALIDATE_SECTOR_IN msgrequest */
-#define    MC_CMD_XPM_INVALIDATE_SECTOR_IN_LEN 4
-/* Sector index */
-#define       MC_CMD_XPM_INVALIDATE_SECTOR_IN_INDEX_OFST 0
-#define       MC_CMD_XPM_INVALIDATE_SECTOR_IN_INDEX_LEN 4
-
-/* MC_CMD_XPM_INVALIDATE_SECTOR_OUT msgresponse */
-#define    MC_CMD_XPM_INVALIDATE_SECTOR_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_BLANK_CHECK
- * Blank-check XPM memory and report bad locations
- */
-#define MC_CMD_XPM_BLANK_CHECK 0x108
-#undef MC_CMD_0x108_PRIVILEGE_CTG
-
-#define MC_CMD_0x108_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_BLANK_CHECK_IN msgrequest */
-#define    MC_CMD_XPM_BLANK_CHECK_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_BLANK_CHECK_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_BLANK_CHECK_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_BLANK_CHECK_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_BLANK_CHECK_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_BLANK_CHECK_OUT msgresponse */
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMIN 4
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMAX 252
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_LEN(num) (4+2*(num))
-#define    MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_NUM(len) (((len)-4)/2)
-/* Total number of bad (non-blank) locations */
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_COUNT_OFST 0
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_COUNT_LEN 4
-/* Addresses of bad locations (may be less than BAD_COUNT, if all cannot fit
- * into MCDI response)
- */
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_OFST 4
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_LEN 2
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MINNUM 0
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MAXNUM 124
-#define       MC_CMD_XPM_BLANK_CHECK_OUT_BAD_ADDR_MAXNUM_MCDI2 508
-
-
-/***********************************/
-/* MC_CMD_XPM_REPAIR
- * Blank-check and repair XPM memory
- */
-#define MC_CMD_XPM_REPAIR 0x109
-#undef MC_CMD_0x109_PRIVILEGE_CTG
-
-#define MC_CMD_0x109_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_REPAIR_IN msgrequest */
-#define    MC_CMD_XPM_REPAIR_IN_LEN 8
-/* Start address (byte) */
-#define       MC_CMD_XPM_REPAIR_IN_ADDR_OFST 0
-#define       MC_CMD_XPM_REPAIR_IN_ADDR_LEN 4
-/* Count (bytes) */
-#define       MC_CMD_XPM_REPAIR_IN_COUNT_OFST 4
-#define       MC_CMD_XPM_REPAIR_IN_COUNT_LEN 4
-
-/* MC_CMD_XPM_REPAIR_OUT msgresponse */
-#define    MC_CMD_XPM_REPAIR_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_DECODER_TEST
- * Test XPM memory address decoders for gross manufacturing defects. Can only
- * be performed on an unprogrammed part.
- */
-#define MC_CMD_XPM_DECODER_TEST 0x10a
-#undef MC_CMD_0x10a_PRIVILEGE_CTG
-
-#define MC_CMD_0x10a_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_DECODER_TEST_IN msgrequest */
-#define    MC_CMD_XPM_DECODER_TEST_IN_LEN 0
-
-/* MC_CMD_XPM_DECODER_TEST_OUT msgresponse */
-#define    MC_CMD_XPM_DECODER_TEST_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_WRITE_TEST
- * XPM memory write test. Test XPM write logic for gross manufacturing defects
- * by writing to a dedicated test row. There are 16 locations in the test row
- * and the test can only be performed on locations that have not been
- * previously used (i.e. can be run at most 16 times). The test will pick the
- * first available location to use, or fail with ENOSPC if none left.
- */
-#define MC_CMD_XPM_WRITE_TEST 0x10b
-#undef MC_CMD_0x10b_PRIVILEGE_CTG
-
-#define MC_CMD_0x10b_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_XPM_WRITE_TEST_IN msgrequest */
-#define    MC_CMD_XPM_WRITE_TEST_IN_LEN 0
-
-/* MC_CMD_XPM_WRITE_TEST_OUT msgresponse */
-#define    MC_CMD_XPM_WRITE_TEST_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_EXEC_SIGNED
- * Check the CMAC of the contents of IMEM and DMEM against the value supplied
- * and if correct begin execution from the start of IMEM. The caller supplies a
- * key ID, the length of IMEM and DMEM to validate and the expected CMAC. CMAC
- * computation runs from the start of IMEM, and from the start of DMEM + 16k,
- * to match flash booting. The command will respond with EINVAL if the CMAC
- * does match, otherwise it will respond with success before it jumps to IMEM.
- */
-#define MC_CMD_EXEC_SIGNED 0x10c
-#undef MC_CMD_0x10c_PRIVILEGE_CTG
-
-#define MC_CMD_0x10c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_EXEC_SIGNED_IN msgrequest */
-#define    MC_CMD_EXEC_SIGNED_IN_LEN 28
-/* the length of code to include in the CMAC */
-#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_OFST 0
-#define       MC_CMD_EXEC_SIGNED_IN_CODELEN_LEN 4
-/* the length of date to include in the CMAC */
-#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_OFST 4
-#define       MC_CMD_EXEC_SIGNED_IN_DATALEN_LEN 4
-/* the XPM sector containing the key to use */
-#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_OFST 8
-#define       MC_CMD_EXEC_SIGNED_IN_KEYSECTOR_LEN 4
-/* the expected CMAC value */
-#define       MC_CMD_EXEC_SIGNED_IN_CMAC_OFST 12
-#define       MC_CMD_EXEC_SIGNED_IN_CMAC_LEN 16
-
-/* MC_CMD_EXEC_SIGNED_OUT msgresponse */
-#define    MC_CMD_EXEC_SIGNED_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PREPARE_SIGNED
- * Prepare to upload a signed image. This will scrub the specified length of
- * the data region, which must be at least as large as the DATALEN supplied to
- * MC_CMD_EXEC_SIGNED.
- */
-#define MC_CMD_PREPARE_SIGNED 0x10d
-#undef MC_CMD_0x10d_PRIVILEGE_CTG
-
-#define MC_CMD_0x10d_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_PREPARE_SIGNED_IN msgrequest */
-#define    MC_CMD_PREPARE_SIGNED_IN_LEN 4
-/* the length of data area to clear */
-#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_OFST 0
-#define       MC_CMD_PREPARE_SIGNED_IN_DATALEN_LEN 4
-
-/* MC_CMD_PREPARE_SIGNED_OUT msgresponse */
-#define    MC_CMD_PREPARE_SIGNED_OUT_LEN 0
-
-
 /* TUNNEL_ENCAP_UDP_PORT_ENTRY structuredef */
 #define    TUNNEL_ENCAP_UDP_PORT_ENTRY_LEN 4
 /* UDP port (the standard ports are named below but any port may be used) */
@@ -23048,110 +21544,6 @@
 #define        MC_CMD_SET_TUNNEL_ENCAP_UDP_PORTS_OUT_RESETTING_WIDTH 1
 
 
-/***********************************/
-/* MC_CMD_RX_BALANCING
- * Configure a port upconverter to distribute the packets on both RX engines.
- * Packets are distributed based on a table with the destination vFIFO. The
- * index of the table is a hash of source and destination of IPV4 and VLAN
- * priority.
- */
-#define MC_CMD_RX_BALANCING 0x118
-#undef MC_CMD_0x118_PRIVILEGE_CTG
-
-#define MC_CMD_0x118_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_RX_BALANCING_IN msgrequest */
-#define    MC_CMD_RX_BALANCING_IN_LEN 16
-/* The RX port whose upconverter table will be modified */
-#define       MC_CMD_RX_BALANCING_IN_PORT_OFST 0
-#define       MC_CMD_RX_BALANCING_IN_PORT_LEN 4
-/* The VLAN priority associated to the table index and vFIFO */
-#define       MC_CMD_RX_BALANCING_IN_PRIORITY_OFST 4
-#define       MC_CMD_RX_BALANCING_IN_PRIORITY_LEN 4
-/* The resulting bit of SRC^DST for indexing the table */
-#define       MC_CMD_RX_BALANCING_IN_SRC_DST_OFST 8
-#define       MC_CMD_RX_BALANCING_IN_SRC_DST_LEN 4
-/* The RX engine to which the vFIFO in the table entry will point to */
-#define       MC_CMD_RX_BALANCING_IN_ENG_OFST 12
-#define       MC_CMD_RX_BALANCING_IN_ENG_LEN 4
-
-/* MC_CMD_RX_BALANCING_OUT msgresponse */
-#define    MC_CMD_RX_BALANCING_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_NVRAM_PRIVATE_APPEND
- * Append a single TLV to the MC_USAGE_TLV partition. Returns MC_CMD_ERR_EEXIST
- * if the tag is already present.
- */
-#define MC_CMD_NVRAM_PRIVATE_APPEND 0x11c
-#undef MC_CMD_0x11c_PRIVILEGE_CTG
-
-#define MC_CMD_0x11c_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_NVRAM_PRIVATE_APPEND_IN msgrequest */
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMIN 9
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMAX 252
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_NUM(len) (((len)-8)/1)
-/* The tag to be appended */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_TAG_OFST 0
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_TAG_LEN 4
-/* The length of the data */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENGTH_OFST 4
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_LENGTH_LEN 4
-/* The data to be contained in the TLV structure */
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_OFST 8
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_LEN 1
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MINNUM 1
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MAXNUM 244
-#define       MC_CMD_NVRAM_PRIVATE_APPEND_IN_DATA_BUFFER_MAXNUM_MCDI2 1012
-
-/* MC_CMD_NVRAM_PRIVATE_APPEND_OUT msgresponse */
-#define    MC_CMD_NVRAM_PRIVATE_APPEND_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_XPM_VERIFY_CONTENTS
- * Verify that the contents of the XPM memory is correct (Medford only). This
- * is used during manufacture to check that the XPM memory has been programmed
- * correctly at ATE.
- */
-#define MC_CMD_XPM_VERIFY_CONTENTS 0x11b
-#undef MC_CMD_0x11b_PRIVILEGE_CTG
-
-#define MC_CMD_0x11b_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_XPM_VERIFY_CONTENTS_IN msgrequest */
-#define    MC_CMD_XPM_VERIFY_CONTENTS_IN_LEN 4
-/* Data type to be checked */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_IN_DATA_TYPE_OFST 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_IN_DATA_TYPE_LEN 4
-
-/* MC_CMD_XPM_VERIFY_CONTENTS_OUT msgresponse */
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMIN 12
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMAX 252
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_LEN(num) (12+1*(num))
-#define    MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_NUM(len) (((len)-12)/1)
-/* Number of sectors found (test builds only) */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_SECTORS_OFST 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_SECTORS_LEN 4
-/* Number of bytes found (test builds only) */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_BYTES_OFST 4
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_NUM_BYTES_LEN 4
-/* Length of signature */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIG_LENGTH_OFST 8
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIG_LENGTH_LEN 4
-/* Signature */
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_OFST 12
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_LEN 1
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MINNUM 0
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MAXNUM 240
-#define       MC_CMD_XPM_VERIFY_CONTENTS_OUT_SIGNATURE_MAXNUM_MCDI2 1008
-
-
 /***********************************/
 /* MC_CMD_SET_EVQ_TMR
  * Update the timer load, timer reload and timer mode values for a given EVQ.
@@ -23242,595 +21634,25 @@
 #define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_MCDI_TMR_STEP_NS_LEN 4
 /* For timers updated using the bug35388 workaround, this is the time interval
  * (in nanoseconds) for each increment of the timer load/reload count. The
- * requested duration of a timer is this value multiplied by the timer
- * load/reload count. This field is only meaningful if the bug35388 workaround
- * is enabled.
- */
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT_OFST 24
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT_LEN 4
-/* For timers updated using the bug35388 workaround, this is the maximum value
- * allowed for timer load/reload counts. This field is only meaningful if the
- * bug35388 workaround is enabled.
- */
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT_OFST 28
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT_LEN 4
-/* For timers updated using the bug35388 workaround, timer load/reload counts
- * not a multiple of this step size will be rounded in an implementation
- * defined manner. This field is only meaningful if the bug35388 workaround is
- * enabled.
- */
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_OFST 32
-#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP
- * When we use the TX_vFIFO_ULL mode, we can allocate common pools using the
- * non used switch buffers.
- */
-#define MC_CMD_ALLOCATE_TX_VFIFO_CP 0x11d
-#undef MC_CMD_0x11d_PRIVILEGE_CTG
-
-#define MC_CMD_0x11d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP_IN msgrequest */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_LEN 20
-/* Desired instance. Must be set to a specific instance, which is a function
- * local queue index. The calling client must be the currently-assigned user of
- * this VI (see MC_CMD_SET_VI_USER).
- */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INSTANCE_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INSTANCE_LEN 4
-/* Will the common pool be used as TX_vFIFO_ULL (1) */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_MODE_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_MODE_LEN 4
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_ENABLED 0x1 /* enum */
-/* enum: Using this interface without TX_vFIFO_ULL is not supported for now */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_DISABLED 0x0
-/* Number of buffers to reserve for the common pool */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_SIZE_OFST 8
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_SIZE_LEN 4
-/* TX datapath to which the Common Pool is connected to. */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INGRESS_OFST 12
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_INGRESS_LEN 4
-/* enum: Extracts information from function */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1
-/* Network port or RX Engine to which the common pool connects. */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_EGRESS_OFST 16
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_EGRESS_LEN 4
-/* enum: Extracts information from function */
-/*               MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_USE_FUNCTION_VALUE -0x1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT0 0x0 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT1 0x1 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT2 0x2 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_PORT3 0x3 /* enum */
-/* enum: To enable Switch loopback with Rx engine 0 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE0 0x4
-/* enum: To enable Switch loopback with Rx engine 1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_CP_IN_RX_ENGINE1 0x5
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT msgresponse */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_LEN 4
-/* ID of the common pool allocated */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_CP_ID_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_CP_OUT_CP_ID_LEN 4
-
-
-/***********************************/
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO
- * When we use the TX_vFIFO_ULL mode, we can allocate vFIFOs using the
- * previously allocated common pools.
- */
-#define MC_CMD_ALLOCATE_TX_VFIFO_VFIFO 0x11e
-#undef MC_CMD_0x11e_PRIVILEGE_CTG
-
-#define MC_CMD_0x11e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN msgrequest */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LEN 20
-/* Common pool previously allocated to which the new vFIFO will be associated
- */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_CP_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_CP_LEN 4
-/* Port or RX engine to associate the vFIFO egress */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_EGRESS_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_EGRESS_LEN 4
-/* enum: Extracts information from common pool */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_USE_CP_VALUE -0x1
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT0 0x0 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT1 0x1 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT2 0x2 /* enum */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PORT3 0x3 /* enum */
-/* enum: To enable Switch loopback with Rx engine 0 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE0 0x4
-/* enum: To enable Switch loopback with Rx engine 1 */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_RX_ENGINE1 0x5
-/* Minimum number of buffers that the pool must have */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_SIZE_OFST 8
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_SIZE_LEN 4
-/* enum: Do not check the space available */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_NO_MINIMUM 0x0
-/* Will the vFIFO be used as TX_vFIFO_ULL */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_MODE_OFST 12
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_MODE_LEN 4
-/* Network priority of the vFIFO,if applicable */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PRIORITY_OFST 16
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_PRIORITY_LEN 4
-/* enum: Search for the lowest unused priority */
-#define          MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_IN_LOWEST_AVAILABLE -0x1
-
-/* MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT msgresponse */
-#define    MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_LEN 8
-/* Short vFIFO ID */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_VID_OFST 0
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_VID_LEN 4
-/* Network priority of the vFIFO */
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_PRIORITY_OFST 4
-#define       MC_CMD_ALLOCATE_TX_VFIFO_VFIFO_OUT_PRIORITY_LEN 4
-
-
-/***********************************/
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF
- * This interface clears the configuration of the given vFIFO and leaves it
- * ready to be re-used.
- */
-#define MC_CMD_TEARDOWN_TX_VFIFO_VF 0x11f
-#undef MC_CMD_0x11f_PRIVILEGE_CTG
-
-#define MC_CMD_0x11f_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF_IN msgrequest */
-#define    MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_LEN 4
-/* Short vFIFO ID */
-#define       MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_VFIFO_OFST 0
-#define       MC_CMD_TEARDOWN_TX_VFIFO_VF_IN_VFIFO_LEN 4
-
-/* MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT msgresponse */
-#define    MC_CMD_TEARDOWN_TX_VFIFO_VF_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP
- * This interface clears the configuration of the given common pool and leaves
- * it ready to be re-used.
- */
-#define MC_CMD_DEALLOCATE_TX_VFIFO_CP 0x121
-#undef MC_CMD_0x121_PRIVILEGE_CTG
-
-#define MC_CMD_0x121_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN msgrequest */
-#define    MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_LEN 4
-/* Common pool ID given when pool allocated */
-#define       MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_POOL_ID_OFST 0
-#define       MC_CMD_DEALLOCATE_TX_VFIFO_CP_IN_POOL_ID_LEN 4
-
-/* MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT msgresponse */
-#define    MC_CMD_DEALLOCATE_TX_VFIFO_CP_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS
- * This interface allows the host to find out how many common pool buffers are
- * not yet assigned.
- */
-#define MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS 0x124
-#undef MC_CMD_0x124_PRIVILEGE_CTG
-
-#define MC_CMD_0x124_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN msgrequest */
-#define    MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_IN_LEN 0
-
-/* MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT msgresponse */
-#define    MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_LEN 8
-/* Available buffers for the ENG to NET vFIFOs. */
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_NET_OFST 0
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_NET_LEN 4
-/* Available buffers for the ENG to ENG and NET to ENG vFIFOs. */
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_ENG_OFST 4
-#define       MC_CMD_SWITCH_GET_UNASSIGNED_BUFFERS_OUT_ENG_LEN 4
-
-
-/***********************************/
-/* MC_CMD_SUC_VERSION
- * Get the version of the SUC
- */
-#define MC_CMD_SUC_VERSION 0x134
-#undef MC_CMD_0x134_PRIVILEGE_CTG
-
-#define MC_CMD_0x134_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_SUC_VERSION_IN msgrequest */
-#define    MC_CMD_SUC_VERSION_IN_LEN 0
-
-/* MC_CMD_SUC_VERSION_OUT msgresponse */
-#define    MC_CMD_SUC_VERSION_OUT_LEN 24
-/* The SUC firmware version as four numbers - a.b.c.d */
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_OFST 0
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_LEN 4
-#define       MC_CMD_SUC_VERSION_OUT_VERSION_NUM 4
-/* The date, in seconds since the Unix epoch, when the firmware image was
- * built.
- */
-#define       MC_CMD_SUC_VERSION_OUT_BUILD_DATE_OFST 16
-#define       MC_CMD_SUC_VERSION_OUT_BUILD_DATE_LEN 4
-/* The ID of the SUC chip. This is specific to the platform but typically
- * indicates family, memory sizes etc. See SF-116728-SW for further details.
- */
-#define       MC_CMD_SUC_VERSION_OUT_CHIP_ID_OFST 20
-#define       MC_CMD_SUC_VERSION_OUT_CHIP_ID_LEN 4
-
-/* MC_CMD_SUC_BOOT_VERSION_IN msgrequest: Get the version of the SUC boot
- * loader.
- */
-#define    MC_CMD_SUC_BOOT_VERSION_IN_LEN 4
-#define       MC_CMD_SUC_BOOT_VERSION_IN_MAGIC_OFST 0
-#define       MC_CMD_SUC_BOOT_VERSION_IN_MAGIC_LEN 4
-/* enum: Requests the SUC boot version. */
-#define          MC_CMD_SUC_VERSION_GET_BOOT_VERSION 0xb007700b
-
-/* MC_CMD_SUC_BOOT_VERSION_OUT msgresponse */
-#define    MC_CMD_SUC_BOOT_VERSION_OUT_LEN 4
-/* The SUC boot version */
-#define       MC_CMD_SUC_BOOT_VERSION_OUT_VERSION_OFST 0
-#define       MC_CMD_SUC_BOOT_VERSION_OUT_VERSION_LEN 4
-
-
-/***********************************/
-/* MC_CMD_GET_RX_PREFIX_ID
- * This command is part of the mechanism for configuring the format of the RX
- * packet prefix. It takes as input a bitmask of the fields the host would like
- * to be in the prefix. If the hardware supports RX prefixes with that
- * combination of fields, then this command returns a list of prefix-ids,
- * opaque identifiers suitable for use in the RX_PREFIX_ID field of a
- * MC_CMD_INIT_RXQ_V5_IN message. If the combination of fields is not
- * supported, returns ENOTSUP. If the firmware can't create any new prefix-ids
- * due to resource constraints, returns ENOSPC.
- */
-#define MC_CMD_GET_RX_PREFIX_ID 0x13b
-#undef MC_CMD_0x13b_PRIVILEGE_CTG
-
-#define MC_CMD_0x13b_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_RX_PREFIX_ID_IN msgrequest */
-#define    MC_CMD_GET_RX_PREFIX_ID_IN_LEN 8
-/* Field bitmask. */
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LEN 8
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_LBN 0
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_LO_WIDTH 32
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_OFST 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_LBN 32
-#define       MC_CMD_GET_RX_PREFIX_ID_IN_FIELDS_HI_WIDTH 32
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_LBN 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_LENGTH_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_LBN 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_VALID_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_LBN 2
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_FLAG_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_LBN 3
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CLASS_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_LBN 4
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_PARTIAL_TSTAMP_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_LBN 5
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_RSS_HASH_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_LBN 6
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_USER_MARK_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_LBN 7
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_MPORT_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_LBN 7
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_INGRESS_VPORT_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_LBN 8
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_CSUM_FRAME_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_LBN 9
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIP_TCI_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_LBN 10
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VLAN_STRIPPED_WIDTH 1
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_OFST 0
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_LBN 11
-#define        MC_CMD_GET_RX_PREFIX_ID_IN_VSWITCH_STATUS_WIDTH 1
-
-/* MC_CMD_GET_RX_PREFIX_ID_OUT msgresponse */
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMIN 8
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMAX 252
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_LEN(num) (4+4*(num))
-#define    MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_NUM(len) (((len)-4)/4)
-/* Number of prefix-ids returned */
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_NUM_RX_PREFIX_IDS_OFST 0
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_NUM_RX_PREFIX_IDS_LEN 4
-/* Opaque prefix identifiers which can be passed into MC_CMD_INIT_RXQ_V5 or
- * MC_CMD_QUERY_PREFIX_ID
- */
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_OFST 4
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_LEN 4
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MINNUM 1
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MAXNUM 62
-#define       MC_CMD_GET_RX_PREFIX_ID_OUT_RX_PREFIX_ID_MAXNUM_MCDI2 254
-
-/* RX_PREFIX_FIELD_INFO structuredef: Information about a single RX prefix
- * field
- */
-#define    RX_PREFIX_FIELD_INFO_LEN 4
-/* The offset of the field from the start of the prefix, in bits */
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_OFST 0
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_LEN 2
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_LBN 0
-#define       RX_PREFIX_FIELD_INFO_OFFSET_BITS_WIDTH 16
-/* The width of the field, in bits */
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_OFST 2
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_LEN 1
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_LBN 16
-#define       RX_PREFIX_FIELD_INFO_WIDTH_BITS_WIDTH 8
-/* The type of the field. These enum values are in the same order as the fields
- * in the MC_CMD_GET_RX_PREFIX_ID_IN bitmask
- */
-#define       RX_PREFIX_FIELD_INFO_TYPE_OFST 3
-#define       RX_PREFIX_FIELD_INFO_TYPE_LEN 1
-#define          RX_PREFIX_FIELD_INFO_LENGTH 0x0 /* enum */
-#define          RX_PREFIX_FIELD_INFO_RSS_HASH_VALID 0x1 /* enum */
-#define          RX_PREFIX_FIELD_INFO_USER_FLAG 0x2 /* enum */
-#define          RX_PREFIX_FIELD_INFO_CLASS 0x3 /* enum */
-#define          RX_PREFIX_FIELD_INFO_PARTIAL_TSTAMP 0x4 /* enum */
-#define          RX_PREFIX_FIELD_INFO_RSS_HASH 0x5 /* enum */
-#define          RX_PREFIX_FIELD_INFO_USER_MARK 0x6 /* enum */
-#define          RX_PREFIX_FIELD_INFO_INGRESS_MPORT 0x7 /* enum */
-#define          RX_PREFIX_FIELD_INFO_INGRESS_VPORT 0x7 /* enum */
-#define          RX_PREFIX_FIELD_INFO_CSUM_FRAME 0x8 /* enum */
-#define          RX_PREFIX_FIELD_INFO_VLAN_STRIP_TCI 0x9 /* enum */
-#define          RX_PREFIX_FIELD_INFO_VLAN_STRIPPED 0xa /* enum */
-#define          RX_PREFIX_FIELD_INFO_VSWITCH_STATUS 0xb /* enum */
-#define       RX_PREFIX_FIELD_INFO_TYPE_LBN 24
-#define       RX_PREFIX_FIELD_INFO_TYPE_WIDTH 8
-
-/* RX_PREFIX_FIXED_RESPONSE structuredef: Information about an RX prefix in
- * which every field has a fixed offset and width
- */
-#define    RX_PREFIX_FIXED_RESPONSE_LENMIN 4
-#define    RX_PREFIX_FIXED_RESPONSE_LENMAX 252
-#define    RX_PREFIX_FIXED_RESPONSE_LENMAX_MCDI2 1020
-#define    RX_PREFIX_FIXED_RESPONSE_LEN(num) (4+4*(num))
-#define    RX_PREFIX_FIXED_RESPONSE_FIELDS_NUM(len) (((len)-4)/4)
-/* Length of the RX prefix in bytes */
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_OFST 0
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_LEN 1
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_LBN 0
-#define       RX_PREFIX_FIXED_RESPONSE_PREFIX_LENGTH_BYTES_WIDTH 8
-/* Number of fields present in the prefix */
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_OFST 1
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_LEN 1
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_LBN 8
-#define       RX_PREFIX_FIXED_RESPONSE_FIELD_COUNT_WIDTH 8
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_OFST 2
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_LEN 2
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_LBN 16
-#define       RX_PREFIX_FIXED_RESPONSE_RESERVED_WIDTH 16
-/* Array of RX_PREFIX_FIELD_INFO structures, of length FIELD_COUNT */
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_OFST 4
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_LEN 4
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MINNUM 0
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MAXNUM 62
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_MAXNUM_MCDI2 254
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_LBN 32
-#define       RX_PREFIX_FIXED_RESPONSE_FIELDS_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_QUERY_RX_PREFIX_ID
- * This command takes an RX prefix id (obtained from MC_CMD_GET_RX_PREFIX_ID)
- * and returns a description of the RX prefix of packets delievered to an RXQ
- * created with that prefix id
- */
-#define MC_CMD_QUERY_RX_PREFIX_ID 0x13c
-#undef MC_CMD_0x13c_PRIVILEGE_CTG
-
-#define MC_CMD_0x13c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_QUERY_RX_PREFIX_ID_IN msgrequest */
-#define    MC_CMD_QUERY_RX_PREFIX_ID_IN_LEN 4
-/* Prefix id to query */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_IN_RX_PREFIX_ID_OFST 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_IN_RX_PREFIX_ID_LEN 4
-
-/* MC_CMD_QUERY_RX_PREFIX_ID_OUT msgresponse */
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMIN 4
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMAX 252
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_NUM(len) (((len)-4)/1)
-/* An enum describing the structure of this response. */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_OFST 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_LEN 1
-/* enum: The response is of format RX_PREFIX_FIXED_RESPONSE */
-#define          MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_TYPE_FIXED 0x0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESERVED_OFST 1
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESERVED_LEN 3
-/* The response. Its format is as defined by the RESPONSE_TYPE value */
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_OFST 4
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_LEN 1
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MINNUM 0
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MAXNUM 248
-#define       MC_CMD_QUERY_RX_PREFIX_ID_OUT_RESPONSE_MAXNUM_MCDI2 1016
-
-
-/***********************************/
-/* MC_CMD_BUNDLE
- * A command to perform various bundle-related operations on insecure cards.
- */
-#define MC_CMD_BUNDLE 0x13d
-#undef MC_CMD_0x13d_PRIVILEGE_CTG
-
-#define MC_CMD_0x13d_PRIVILEGE_CTG SRIOV_CTG_INSECURE
-
-/* MC_CMD_BUNDLE_IN msgrequest */
-#define    MC_CMD_BUNDLE_IN_LEN 4
-/* Sub-command code */
-#define       MC_CMD_BUNDLE_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_IN_OP_LEN 4
-/* enum: Get the current host access mode set on component partitions. */
-#define          MC_CMD_BUNDLE_IN_OP_COMPONENT_ACCESS_GET 0x0
-/* enum: Set the host access mode set on component partitions. */
-#define          MC_CMD_BUNDLE_IN_OP_COMPONENT_ACCESS_SET 0x1
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN msgrequest: Retrieve the current
- * access mode on component partitions such as MC_FIRMWARE, SUC_FIRMWARE and
- * EXPANSION_UEFI. This command only works on engineering (insecure) cards. On
- * secure adapters, this command returns MC_CMD_ERR_EPERM.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_LEN 4
-/* Sub-command code. Must be OP_COMPONENT_ACCESS_GET. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_IN_OP_LEN 4
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT msgresponse: Returns the access
- * control mode.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_LEN 4
-/* Access mode of component partitions. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_ACCESS_MODE_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT_ACCESS_MODE_LEN 4
-/* enum: Component partitions are read-only from the host. */
-#define          MC_CMD_BUNDLE_COMPONENTS_READ_ONLY 0x0
-/* enum: Component partitions can read read-from written-to by the host. */
-#define          MC_CMD_BUNDLE_COMPONENTS_READ_WRITE 0x1
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN msgrequest: The component
- * partitions such as MC_FIRMWARE, SUC_FIRMWARE, EXPANSION_UEFI are set as
- * read-only on firmware built with bundle support. This command marks these
- * partitions as read/writeable. The access status set by this command does not
- * persist across MC reboots. This command only works on engineering (insecure)
- * cards. On secure adapters, this command returns MC_CMD_ERR_EPERM.
- */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_LEN 8
-/* Sub-command code. Must be OP_COMPONENT_ACCESS_SET. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_OP_OFST 0
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_OP_LEN 4
-/* Access mode of component partitions. */
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_ACCESS_MODE_OFST 4
-#define       MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_IN_ACCESS_MODE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_GET_OUT/ACCESS_MODE */
-
-/* MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_OUT msgresponse */
-#define    MC_CMD_BUNDLE_OP_COMPONENT_ACCESS_SET_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_GET_VPD
- * Read all VPD starting from a given address
+ * requested duration of a timer is this value multiplied by the timer
+ * load/reload count. This field is only meaningful if the bug35388 workaround
+ * is enabled.
  */
-#define MC_CMD_GET_VPD 0x165
-#undef MC_CMD_0x165_PRIVILEGE_CTG
-
-#define MC_CMD_0x165_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_VPD_IN msgresponse */
-#define    MC_CMD_GET_VPD_IN_LEN 4
-/* VPD address to start from. In case VPD is longer than MCDI buffer
- * (unlikely), user can make multiple calls with different starting addresses.
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT_OFST 24
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_NS_PER_COUNT_LEN 4
+/* For timers updated using the bug35388 workaround, this is the maximum value
+ * allowed for timer load/reload counts. This field is only meaningful if the
+ * bug35388 workaround is enabled.
  */
-#define       MC_CMD_GET_VPD_IN_ADDR_OFST 0
-#define       MC_CMD_GET_VPD_IN_ADDR_LEN 4
-
-/* MC_CMD_GET_VPD_OUT msgresponse */
-#define    MC_CMD_GET_VPD_OUT_LENMIN 0
-#define    MC_CMD_GET_VPD_OUT_LENMAX 252
-#define    MC_CMD_GET_VPD_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_GET_VPD_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_GET_VPD_OUT_DATA_NUM(len) (((len)-0)/1)
-/* VPD data returned. */
-#define       MC_CMD_GET_VPD_OUT_DATA_OFST 0
-#define       MC_CMD_GET_VPD_OUT_DATA_LEN 1
-#define       MC_CMD_GET_VPD_OUT_DATA_MINNUM 0
-#define       MC_CMD_GET_VPD_OUT_DATA_MAXNUM 252
-#define       MC_CMD_GET_VPD_OUT_DATA_MAXNUM_MCDI2 1020
-
-
-/***********************************/
-/* MC_CMD_GET_NCSI_INFO
- * Provide information about the NC-SI stack
- */
-#define MC_CMD_GET_NCSI_INFO 0x167
-#undef MC_CMD_0x167_PRIVILEGE_CTG
-
-#define MC_CMD_0x167_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_NCSI_INFO_IN msgrequest */
-#define    MC_CMD_GET_NCSI_INFO_IN_LEN 8
-/* Operation to be performed */
-#define       MC_CMD_GET_NCSI_INFO_IN_OP_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_IN_OP_LEN 4
-/* enum: Information on the link settings. */
-#define          MC_CMD_GET_NCSI_INFO_IN_OP_LINK 0x0
-/* enum: Statistics associated with the channel */
-#define          MC_CMD_GET_NCSI_INFO_IN_OP_STATISTICS 0x1
-/* The NC-SI channel on which the operation is to be performed */
-#define       MC_CMD_GET_NCSI_INFO_IN_CHANNEL_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_IN_CHANNEL_LEN 4
-
-/* MC_CMD_GET_NCSI_INFO_LINK_OUT msgresponse */
-#define    MC_CMD_GET_NCSI_INFO_LINK_OUT_LEN 12
-/* Settings as received from BMC. */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_SETTINGS_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_SETTINGS_LEN 4
-/* Advertised capabilities applied to channel. */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_ADV_CAP_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_ADV_CAP_LEN 4
-/* General status */
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_STATUS_OFST 8
-#define       MC_CMD_GET_NCSI_INFO_LINK_OUT_STATUS_LEN 4
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_LBN 0
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_STATE_WIDTH 2
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_LBN 2
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ENABLE_WIDTH 1
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_LBN 3
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_NETWORK_TX_WIDTH 1
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_OFST 8
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_LBN 4
-#define        MC_CMD_GET_NCSI_INFO_LINK_OUT_ATTACHED_WIDTH 1
-
-/* MC_CMD_GET_NCSI_INFO_STATISTICS_OUT msgresponse */
-#define    MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_LEN 28
-/* The number of NC-SI commands received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMDS_RX_OFST 0
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMDS_RX_LEN 4
-/* The number of NC-SI commands dropped. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_PKTS_DROPPED_OFST 4
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_PKTS_DROPPED_LEN 4
-/* The number of invalid NC-SI commands received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_TYPE_ERRS_OFST 8
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_TYPE_ERRS_LEN 4
-/* The number of checksum errors seen. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_CSUM_ERRS_OFST 12
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_CMD_CSUM_ERRS_LEN 4
-/* The number of NC-SI requests received. */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_RX_PKTS_OFST 16
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_RX_PKTS_LEN 4
-/* The number of NC-SI responses sent (includes AENs) */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_TX_PKTS_OFST 20
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_NCSI_TX_PKTS_LEN 4
-/* The number of NC-SI AENs sent */
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_AENS_SENT_OFST 24
-#define       MC_CMD_GET_NCSI_INFO_STATISTICS_OUT_AENS_SENT_LEN 4
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT_OFST 28
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_MAX_COUNT_LEN 4
+/* For timers updated using the bug35388 workaround, timer load/reload counts
+ * not a multiple of this step size will be rounded in an implementation
+ * defined manner. This field is only meaningful if the bug35388 workaround is
+ * enabled.
+ */
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_OFST 32
+#define       MC_CMD_GET_EVQ_TMR_PROPERTIES_OUT_BUG35388_TMR_STEP_LEN 4
 
 /* CLIENT_HANDLE structuredef: A client is an abstract entity that can make
  * requests of the device and that can own resources managed by the device.
@@ -23848,59 +21670,10 @@
 #define       CLIENT_HANDLE_OPAQUE_LBN 0
 #define       CLIENT_HANDLE_OPAQUE_WIDTH 32
 
-/* CLOCK_INFO structuredef: Information about a single hardware clock */
-#define    CLOCK_INFO_LEN 28
-/* Enumeration that uniquely identifies the clock */
-#define       CLOCK_INFO_CLOCK_ID_OFST 0
-#define       CLOCK_INFO_CLOCK_ID_LEN 2
-/* enum: The Riverhead CMC (card MC) */
-#define          CLOCK_INFO_CLOCK_CMC 0x0
-/* enum: The Riverhead NMC (network MC) */
-#define          CLOCK_INFO_CLOCK_NMC 0x1
-/* enum: The Riverhead SDNET slice main logic */
-#define          CLOCK_INFO_CLOCK_SDNET 0x2
-/* enum: The Riverhead SDNET LUT */
-#define          CLOCK_INFO_CLOCK_SDNET_LUT 0x3
-/* enum: The Riverhead SDNET control logic */
-#define          CLOCK_INFO_CLOCK_SDNET_CTRL 0x4
-/* enum: The Riverhead Streaming SubSystem */
-#define          CLOCK_INFO_CLOCK_SSS 0x5
-/* enum: The Riverhead network MAC and associated CSR registers */
-#define          CLOCK_INFO_CLOCK_MAC 0x6
-#define       CLOCK_INFO_CLOCK_ID_LBN 0
-#define       CLOCK_INFO_CLOCK_ID_WIDTH 16
-/* Assorted flags */
-#define       CLOCK_INFO_FLAGS_OFST 2
-#define       CLOCK_INFO_FLAGS_LEN 2
-#define        CLOCK_INFO_SETTABLE_OFST 2
-#define        CLOCK_INFO_SETTABLE_LBN 0
-#define        CLOCK_INFO_SETTABLE_WIDTH 1
-#define       CLOCK_INFO_FLAGS_LBN 16
-#define       CLOCK_INFO_FLAGS_WIDTH 16
-/* The frequency in HZ */
-#define       CLOCK_INFO_FREQUENCY_OFST 4
-#define       CLOCK_INFO_FREQUENCY_LEN 8
-#define       CLOCK_INFO_FREQUENCY_LO_OFST 4
-#define       CLOCK_INFO_FREQUENCY_LO_LEN 4
-#define       CLOCK_INFO_FREQUENCY_LO_LBN 32
-#define       CLOCK_INFO_FREQUENCY_LO_WIDTH 32
-#define       CLOCK_INFO_FREQUENCY_HI_OFST 8
-#define       CLOCK_INFO_FREQUENCY_HI_LEN 4
-#define       CLOCK_INFO_FREQUENCY_HI_LBN 64
-#define       CLOCK_INFO_FREQUENCY_HI_WIDTH 32
-#define       CLOCK_INFO_FREQUENCY_LBN 32
-#define       CLOCK_INFO_FREQUENCY_WIDTH 64
-/* Human-readable ASCII name for clock, with NUL termination */
-#define       CLOCK_INFO_NAME_OFST 12
-#define       CLOCK_INFO_NAME_LEN 1
-#define       CLOCK_INFO_NAME_NUM 16
-#define       CLOCK_INFO_NAME_LBN 96
-#define       CLOCK_INFO_NAME_WIDTH 8
-
 /* SCHED_CREDIT_CHECK_RESULT structuredef */
 #define    SCHED_CREDIT_CHECK_RESULT_LEN 16
-/* The instance of the scheduler. Refer to XN-200389-AW for the location of
- * these schedulers in the hardware.
+/* The instance of the scheduler. Refer to XN-200389-AW (snic/hnic) and
+ * XN-200425-TC (cdx) for the location of these schedulers in the hardware.
  */
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_OFST 0
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_LEN 1
@@ -23914,6 +21687,16 @@
 #define          SCHED_CREDIT_CHECK_RESULT_DMAC_H2C 0x7 /* enum */
 #define          SCHED_CREDIT_CHECK_RESULT_HUB_NET_B 0x8 /* enum */
 #define          SCHED_CREDIT_CHECK_RESULT_HUB_NET_REPLAY 0x9 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_ADAPTER_C2H_C 0xa /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A2_H2C_C 0xb /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A3_SOFT_ADAPTOR_C 0xc /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A4_DPU_WRITE_C 0xd /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_JRC_RRU 0xe /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_CDM_SINK 0xf /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_PCIE_SINK 0x10 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_UPORT_SINK 0x11 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_PSX_SINK 0x12 /* enum */
+#define          SCHED_CREDIT_CHECK_RESULT_A5_DPU_READ_C 0x13 /* enum */
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_LBN 0
 #define       SCHED_CREDIT_CHECK_RESULT_SCHED_INSTANCE_WIDTH 8
 /* The type of node that this result refers to. */
@@ -23923,6 +21706,10 @@
 #define          SCHED_CREDIT_CHECK_RESULT_DEST 0x0
 /* enum: Source node */
 #define          SCHED_CREDIT_CHECK_RESULT_SOURCE 0x1
+/* enum: Destination node credit type 1 (new to the Keystone schedulers, see
+ * SF-120268-TC)
+ */
+#define          SCHED_CREDIT_CHECK_RESULT_DEST_CREDIT1 0x2
 #define       SCHED_CREDIT_CHECK_RESULT_NODE_TYPE_LBN 8
 #define       SCHED_CREDIT_CHECK_RESULT_NODE_TYPE_WIDTH 8
 /* Level of node in scheduler hierarchy (level 0 is the bottom of the
@@ -23949,592 +21736,6 @@
 #define       SCHED_CREDIT_CHECK_RESULT_ACTUAL_CREDITS_WIDTH 32
 
 
-/***********************************/
-/* MC_CMD_GET_CLOCKS_INFO
- * Get information about the device clocks
- */
-#define MC_CMD_GET_CLOCKS_INFO 0x166
-#undef MC_CMD_0x166_PRIVILEGE_CTG
-
-#define MC_CMD_0x166_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_CLOCKS_INFO_IN msgrequest */
-#define    MC_CMD_GET_CLOCKS_INFO_IN_LEN 0
-
-/* MC_CMD_GET_CLOCKS_INFO_OUT msgresponse */
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMIN 0
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMAX 252
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LENMAX_MCDI2 1008
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_LEN(num) (0+28*(num))
-#define    MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_NUM(len) (((len)-0)/28)
-/* An array of CLOCK_INFO structures. */
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_OFST 0
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_LEN 28
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MINNUM 0
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MAXNUM 9
-#define       MC_CMD_GET_CLOCKS_INFO_OUT_INFOS_MAXNUM_MCDI2 36
-
-
-/***********************************/
-/* MC_CMD_VNIC_ENCAP_RULE_ADD
- * Add a rule for detecting encapsulations in the VNIC stage. Currently this
- * only affects checksum validation in VNIC RX - on TX the send descriptor
- * explicitly specifies encapsulation. These rules are per-VNIC, i.e. only
- * apply to the current driver. If a rule matches, then the packet is
- * considered to have the corresponding encapsulation type, and the inner
- * packet is parsed. It is up to the driver to ensure that overlapping rules
- * are not inserted. (If a packet would match multiple rules, a random one of
- * them will be used.) A rule with the exact same match criteria may not be
- * inserted twice (EALREADY). Only a limited number MATCH_FLAGS values are
- * supported, use MC_CMD_GET_PARSER_DISP_INFO with OP
- * OP_GET_SUPPORTED_VNIC_ENCAP_RULE_MATCHES to get a list of supported
- * combinations. Each driver may only have a limited set of active rules -
- * returns ENOSPC if the caller's table is full.
- */
-#define MC_CMD_VNIC_ENCAP_RULE_ADD 0x16d
-#undef MC_CMD_0x16d_PRIVILEGE_CTG
-
-#define MC_CMD_0x16d_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VNIC_ENCAP_RULE_ADD_IN msgrequest */
-#define    MC_CMD_VNIC_ENCAP_RULE_ADD_IN_LEN 36
-/* Set to MAE_MPORT_SELECTOR_ASSIGNED. In the future this may be relaxed. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MPORT_SELECTOR_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MPORT_SELECTOR_LEN 4
-/* Any non-zero bits other than the ones named below or an unsupported
- * combination will cause the NIC to return EOPNOTSUPP. In the future more
- * flags may be added.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_FLAGS_OFST 4
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_FLAGS_LEN 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_ETHER_TYPE_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_LBN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_OUTER_VLAN_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_LBN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_IP_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_LBN 3
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_IP_PROTO_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_OFST 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_LBN 4
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_MATCH_DST_PORT_WIDTH 1
-/* Only if MATCH_ETHER_TYPE is set. Ethertype value as bytes in network order.
- * Currently only IPv4 (0x0800) and IPv6 (0x86DD) ethertypes may be used.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ETHER_TYPE_OFST 8
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ETHER_TYPE_LEN 2
-/* Only if MATCH_OUTER_VLAN is set. VID value as bytes in network order.
- * (Deprecated)
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_LBN 80
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WIDTH 12
-/* Only if MATCH_OUTER_VLAN is set. Aligned wrapper for OUTER_VLAN_VID. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WORD_OFST 10
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_WORD_LEN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_OFST 10
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_OUTER_VLAN_VID_WIDTH 12
-/* Only if MATCH_DST_IP is set. IP address as bytes in network order. In the
- * case of IPv4, the IP should be in the first 4 bytes and all other bytes
- * should be zero.
- */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_IP_OFST 12
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_IP_LEN 16
-/* Only if MATCH_IP_PROTO is set. Currently only UDP proto (17) may be used. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_IP_PROTO_OFST 28
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_IP_PROTO_LEN 1
-/* Actions that should be applied to packets match the rule. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ACTION_FLAGS_OFST 29
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ACTION_FLAGS_LEN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_LBN 0
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STRIP_OUTER_VLAN_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_LBN 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_RSS_ON_OUTER_WIDTH 1
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_OFST 29
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_LBN 2
-#define        MC_CMD_VNIC_ENCAP_RULE_ADD_IN_STEER_ON_OUTER_WIDTH 1
-/* Only if MATCH_DST_PORT is set. Port number as bytes in network order. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_PORT_OFST 30
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_DST_PORT_LEN 2
-/* Resulting encapsulation type, as per MAE_MCDI_ENCAP_TYPE enumeration. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ENCAP_TYPE_OFST 32
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_IN_ENCAP_TYPE_LEN 4
-
-/* MC_CMD_VNIC_ENCAP_RULE_ADD_OUT msgresponse */
-#define    MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_LEN 4
-/* Handle to inserted rule. Used for removing the rule. */
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_HANDLE_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_ADD_OUT_HANDLE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE
- * Remove a VNIC encapsulation rule. Packets which would have previously
- * matched the rule will then be considered as unencapsulated. Returns EALREADY
- * if the input HANDLE doesn't correspond to an existing rule.
- */
-#define MC_CMD_VNIC_ENCAP_RULE_REMOVE 0x16e
-#undef MC_CMD_0x16e_PRIVILEGE_CTG
-
-#define MC_CMD_0x16e_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN msgrequest */
-#define    MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_LEN 4
-/* Handle which was returned by MC_CMD_VNIC_ENCAP_RULE_ADD. */
-#define       MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_HANDLE_OFST 0
-#define       MC_CMD_VNIC_ENCAP_RULE_REMOVE_IN_HANDLE_LEN 4
-
-/* MC_CMD_VNIC_ENCAP_RULE_REMOVE_OUT msgresponse */
-#define    MC_CMD_VNIC_ENCAP_RULE_REMOVE_OUT_LEN 0
-
-/* UUID structuredef: An RFC4122 standard UUID. The values here are stored in
- * the endianness specified by the RFC; users should ignore the broken-out
- * fields and instead do straight memory copies to ensure correct ordering.
- */
-#define    UUID_LEN 16
-#define       UUID_TIME_LOW_OFST 0
-#define       UUID_TIME_LOW_LEN 4
-#define       UUID_TIME_LOW_LBN 0
-#define       UUID_TIME_LOW_WIDTH 32
-#define       UUID_TIME_MID_OFST 4
-#define       UUID_TIME_MID_LEN 2
-#define       UUID_TIME_MID_LBN 32
-#define       UUID_TIME_MID_WIDTH 16
-#define       UUID_TIME_HI_LBN 52
-#define       UUID_TIME_HI_WIDTH 12
-#define       UUID_VERSION_LBN 48
-#define       UUID_VERSION_WIDTH 4
-#define       UUID_RESERVED_LBN 64
-#define       UUID_RESERVED_WIDTH 2
-#define       UUID_CLK_SEQ_LBN 66
-#define       UUID_CLK_SEQ_WIDTH 14
-#define       UUID_NODE_OFST 10
-#define       UUID_NODE_LEN 6
-#define       UUID_NODE_LBN 80
-#define       UUID_NODE_WIDTH 48
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_ALLOC
- * Create a handle to a datapath plugin's extension. This involves finding a
- * currently-loaded plugin offering the given functionality (as identified by
- * the UUID) and allocating a handle to track the usage of it. Plugin
- * functionality is identified by 'extension' rather than any other identifier
- * so that a single plugin bitfile may offer more than one piece of independent
- * functionality. If two bitfiles are loaded which both offer the same
- * extension, then the metadata is interrogated further to determine which is
- * the newest and that is the one opened. See SF-123625-SW for architectural
- * detail on datapath plugins.
- */
-#define MC_CMD_PLUGIN_ALLOC 0x1ad
-#undef MC_CMD_0x1ad_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ad_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_ALLOC_IN msgrequest */
-#define    MC_CMD_PLUGIN_ALLOC_IN_LEN 24
-/* The functionality requested of the plugin, as a UUID structure */
-#define       MC_CMD_PLUGIN_ALLOC_IN_UUID_OFST 0
-#define       MC_CMD_PLUGIN_ALLOC_IN_UUID_LEN 16
-/* Additional options for opening the handle */
-#define       MC_CMD_PLUGIN_ALLOC_IN_FLAGS_OFST 16
-#define       MC_CMD_PLUGIN_ALLOC_IN_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_OFST 16
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_LBN 0
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_INFO_ONLY_WIDTH 1
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_OFST 16
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_LBN 1
-#define        MC_CMD_PLUGIN_ALLOC_IN_FLAG_ALLOW_DISABLED_WIDTH 1
-/* Load the extension only if it is in the specified administrative group.
- * Specify ANY to load the extension wherever it is found (if there are
- * multiple choices then the extension with the highest MINOR_VER/PATCH_VER
- * will be loaded). See MC_CMD_PLUGIN_GET_META_GLOBAL for a description of
- * administrative groups.
- */
-#define       MC_CMD_PLUGIN_ALLOC_IN_ADMIN_GROUP_OFST 20
-#define       MC_CMD_PLUGIN_ALLOC_IN_ADMIN_GROUP_LEN 2
-/* enum: Load the extension from any ADMIN_GROUP. */
-#define          MC_CMD_PLUGIN_ALLOC_IN_ANY 0xffff
-/* Reserved */
-#define       MC_CMD_PLUGIN_ALLOC_IN_RESERVED_OFST 22
-#define       MC_CMD_PLUGIN_ALLOC_IN_RESERVED_LEN 2
-
-/* MC_CMD_PLUGIN_ALLOC_OUT msgresponse */
-#define    MC_CMD_PLUGIN_ALLOC_OUT_LEN 4
-/* Unique identifier of this usage */
-#define       MC_CMD_PLUGIN_ALLOC_OUT_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_ALLOC_OUT_HANDLE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_FREE
- * Delete a handle to a plugin's extension.
- */
-#define MC_CMD_PLUGIN_FREE 0x1ae
-#undef MC_CMD_0x1ae_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ae_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_FREE_IN msgrequest */
-#define    MC_CMD_PLUGIN_FREE_IN_LEN 4
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_FREE_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_FREE_IN_HANDLE_LEN 4
-
-/* MC_CMD_PLUGIN_FREE_OUT msgresponse */
-#define    MC_CMD_PLUGIN_FREE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_GLOBAL
- * Returns the global metadata applying to the whole plugin extension. See the
- * other metadata calls for subtypes of data.
- */
-#define MC_CMD_PLUGIN_GET_META_GLOBAL 0x1af
-#undef MC_CMD_0x1af_PRIVILEGE_CTG
-
-#define MC_CMD_0x1af_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_GLOBAL_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_GLOBAL_IN_LEN 4
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_IN_HANDLE_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_GLOBAL_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_LEN 36
-/* Unique identifier of this plugin extension. This is identical to the value
- * which was requested when the handle was allocated.
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_UUID_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_UUID_LEN 16
-/* semver sub-version of this plugin extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MINOR_VER_OFST 16
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MINOR_VER_LEN 2
-/* semver micro-version of this plugin extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PATCH_VER_OFST 18
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PATCH_VER_LEN 2
-/* Number of different messages which can be sent to this extension */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_NUM_MSGS_OFST 20
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_NUM_MSGS_LEN 4
-/* Byte offset within the VI window of the plugin's mapped CSR window. */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_OFFSET_OFST 24
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_OFFSET_LEN 2
-/* Number of bytes mapped through to the plugin's CSRs. 0 if that feature was
- * not requested by the plugin (in which case MAPPED_CSR_OFFSET and
- * MAPPED_CSR_FLAGS are ignored).
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_SIZE_OFST 26
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_SIZE_LEN 2
-/* Flags indicating how to perform the CSR window mapping. */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAGS_OFST 28
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_OFST 28
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_LBN 0
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_READ_WIDTH 1
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_OFST 28
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_LBN 1
-#define        MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_MAPPED_CSR_FLAG_WRITE_WIDTH 1
-/* Identifier of the set of extensions which all change state together.
- * Extensions having the same ADMIN_GROUP will always load and unload at the
- * same time. ADMIN_GROUP values themselves are arbitrary (but they contain a
- * generation number as an implementation detail to ensure that they're not
- * reused rapidly).
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_ADMIN_GROUP_OFST 32
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_ADMIN_GROUP_LEN 1
-/* Bitshift in MC_CMD_DEVEL_CLIENT_PRIVILEGE_MODIFY's MASK parameters
- * corresponding to this extension, i.e. set the bit 1<<PRIVILEGE_BIT to permit
- * access to this extension.
- */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PRIVILEGE_BIT_OFST 33
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_PRIVILEGE_BIT_LEN 1
-/* Reserved */
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_RESERVED_OFST 34
-#define       MC_CMD_PLUGIN_GET_META_GLOBAL_OUT_RESERVED_LEN 2
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER
- * Returns metadata supplied by the plugin author which describes this
- * extension in a human-readable way. Contrast with
- * MC_CMD_PLUGIN_GET_META_GLOBAL, which returns information needed for software
- * to operate.
- */
-#define MC_CMD_PLUGIN_GET_META_PUBLISHER 0x1b0
-#undef MC_CMD_0x1b0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b0_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_LEN 12
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_HANDLE_LEN 4
-/* Category of data to return */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_SUBTYPE_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_SUBTYPE_LEN 4
-/* enum: Top-level information about the extension. The returned data is an
- * array of key/value pairs using the keys in RFC5013 (Dublin Core) to describe
- * the extension. The data is a back-to-back list of zero-terminated strings;
- * the even-numbered fields (0,2,4,...) are keys and their following odd-
- * numbered fields are the corresponding values. Both keys and values are
- * nominally UTF-8. Per RFC5013, the same key may be repeated any number of
- * times. Note that all information (including the key/value structure itself
- * and the UTF-8 encoding) may have been provided by the plugin author, so
- * callers must be cautious about parsing it. Callers should parse only the
- * top-level structure to separate out the keys and values; the contents of the
- * values is not expected to be machine-readable.
- */
-#define          MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_EXTENSION_KVS 0x0
-/* Byte position of the data to be returned within the full data block of the
- * given SUBTYPE.
- */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_OFFSET_OFST 8
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_IN_OFFSET_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMIN 4
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMAX 252
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_LEN(num) (4+1*(num))
-#define    MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_NUM(len) (((len)-4)/1)
-/* Full length of the data block of the requested SUBTYPE, in bytes. */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_TOTAL_SIZE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_TOTAL_SIZE_LEN 4
-/* The information requested by SUBTYPE. */
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_LEN 1
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MAXNUM 248
-#define       MC_CMD_PLUGIN_GET_META_PUBLISHER_OUT_DATA_MAXNUM_MCDI2 1016
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_META_MSG
- * Returns the simple metadata for a specific plugin request message. This
- * supplies information necessary for the host to know how to build an
- * MC_CMD_PLUGIN_REQ request.
- */
-#define MC_CMD_PLUGIN_GET_META_MSG 0x1b1
-#undef MC_CMD_0x1b1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b1_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_META_MSG_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_META_MSG_IN_LEN 8
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_HANDLE_LEN 4
-/* Unique message ID to obtain */
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_ID_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_MSG_IN_ID_LEN 4
-
-/* MC_CMD_PLUGIN_GET_META_MSG_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_META_MSG_OUT_LEN 44
-/* Unique message ID. This is the same value as the input parameter; it exists
- * to allow future MCDI extensions which enumerate all messages.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_ID_OFST 0
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_ID_LEN 4
-/* Packed index number of this message, assigned by the MC to give each message
- * a unique ID in an array to allow for more efficient storage/management.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_INDEX_OFST 4
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_INDEX_LEN 4
-/* Short human-readable codename for this message. This is conventionally
- * formatted as a C identifier in the basic ASCII character set with any spare
- * bytes at the end set to 0, however this convention is not enforced by the MC
- * so consumers must check for all potential malformations before using it for
- * a trusted purpose.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_NAME_OFST 8
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_NAME_LEN 32
-/* Number of bytes of data which must be passed from the host kernel to the MC
- * for this message's payload, and which are passed back again in the response.
- * The MC's plugin metadata loader will have validated that the number of bytes
- * specified here will fit in to MC_CMD_PLUGIN_REQ_IN_DATA in a single MCDI
- * message.
- */
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_DATA_SIZE_OFST 40
-#define       MC_CMD_PLUGIN_GET_META_MSG_OUT_DATA_SIZE_LEN 4
-
-/* PLUGIN_EXTENSION structuredef: Used within MC_CMD_PLUGIN_GET_ALL to describe
- * an individual extension.
- */
-#define    PLUGIN_EXTENSION_LEN 20
-#define       PLUGIN_EXTENSION_UUID_OFST 0
-#define       PLUGIN_EXTENSION_UUID_LEN 16
-#define       PLUGIN_EXTENSION_UUID_LBN 0
-#define       PLUGIN_EXTENSION_UUID_WIDTH 128
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_OFST 16
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_LEN 1
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_LBN 128
-#define       PLUGIN_EXTENSION_ADMIN_GROUP_WIDTH 8
-#define       PLUGIN_EXTENSION_FLAG_ENABLED_LBN 136
-#define       PLUGIN_EXTENSION_FLAG_ENABLED_WIDTH 1
-#define       PLUGIN_EXTENSION_RESERVED_LBN 137
-#define       PLUGIN_EXTENSION_RESERVED_WIDTH 23
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_GET_ALL
- * Returns a list of all plugin extensions currently loaded and available. The
- * UUIDs returned can be passed to MC_CMD_PLUGIN_ALLOC in order to obtain more
- * detailed metadata via the MC_CMD_PLUGIN_GET_META_* family of requests. The
- * ADMIN_GROUP field collects how extensions are grouped in to units which are
- * loaded/unloaded together; extensions with the same value are in the same
- * group.
- */
-#define MC_CMD_PLUGIN_GET_ALL 0x1b2
-#undef MC_CMD_0x1b2_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b2_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_GET_ALL_IN msgrequest */
-#define    MC_CMD_PLUGIN_GET_ALL_IN_LEN 4
-/* Additional options for querying. Note that if neither FLAG_INCLUDE_ENABLED
- * nor FLAG_INCLUDE_DISABLED are specified then the result set will be empty.
- */
-#define       MC_CMD_PLUGIN_GET_ALL_IN_FLAGS_OFST 0
-#define       MC_CMD_PLUGIN_GET_ALL_IN_FLAGS_LEN 4
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_OFST 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_LBN 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_ENABLED_WIDTH 1
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_OFST 0
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_LBN 1
-#define        MC_CMD_PLUGIN_GET_ALL_IN_FLAG_INCLUDE_DISABLED_WIDTH 1
-
-/* MC_CMD_PLUGIN_GET_ALL_OUT msgresponse */
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMIN 0
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMAX 240
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_LEN(num) (0+20*(num))
-#define    MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_NUM(len) (((len)-0)/20)
-/* The list of available plugin extensions, as an array of PLUGIN_EXTENSION
- * structs.
- */
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_OFST 0
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_LEN 20
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MINNUM 0
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MAXNUM 12
-#define       MC_CMD_PLUGIN_GET_ALL_OUT_EXTENSIONS_MAXNUM_MCDI2 51
-
-
-/***********************************/
-/* MC_CMD_PLUGIN_REQ
- * Send a command to a plugin. A plugin may define an arbitrary number of
- * 'messages' which it allows applications on the host system to send, each
- * identified by a 32-bit ID.
- */
-#define MC_CMD_PLUGIN_REQ 0x1b3
-#undef MC_CMD_0x1b3_PRIVILEGE_CTG
-
-#define MC_CMD_0x1b3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_PLUGIN_REQ_IN msgrequest */
-#define    MC_CMD_PLUGIN_REQ_IN_LENMIN 8
-#define    MC_CMD_PLUGIN_REQ_IN_LENMAX 252
-#define    MC_CMD_PLUGIN_REQ_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_REQ_IN_LEN(num) (8+1*(num))
-#define    MC_CMD_PLUGIN_REQ_IN_DATA_NUM(len) (((len)-8)/1)
-/* Handle returned by MC_CMD_PLUGIN_ALLOC_OUT */
-#define       MC_CMD_PLUGIN_REQ_IN_HANDLE_OFST 0
-#define       MC_CMD_PLUGIN_REQ_IN_HANDLE_LEN 4
-/* Message ID defined by the plugin author */
-#define       MC_CMD_PLUGIN_REQ_IN_ID_OFST 4
-#define       MC_CMD_PLUGIN_REQ_IN_ID_LEN 4
-/* Data blob being the parameter to the message. This must be of the length
- * specified by MC_CMD_PLUGIN_GET_META_MSG_IN_MCDI_PARAM_SIZE.
- */
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_OFST 8
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_LEN 1
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MAXNUM 244
-#define       MC_CMD_PLUGIN_REQ_IN_DATA_MAXNUM_MCDI2 1012
-
-/* MC_CMD_PLUGIN_REQ_OUT msgresponse */
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMIN 0
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMAX 252
-#define    MC_CMD_PLUGIN_REQ_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_PLUGIN_REQ_OUT_LEN(num) (0+1*(num))
-#define    MC_CMD_PLUGIN_REQ_OUT_DATA_NUM(len) (((len)-0)/1)
-/* The input data, as transformed and/or updated by the plugin's eBPF. Will be
- * the same size as the input DATA parameter.
- */
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_OFST 0
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_LEN 1
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MINNUM 0
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MAXNUM 252
-#define       MC_CMD_PLUGIN_REQ_OUT_DATA_MAXNUM_MCDI2 1020
-
-/* DESC_ADDR_REGION structuredef: Describes a contiguous region of DESC_ADDR
- * space that maps to a contiguous region of TRGT_ADDR space. Addresses
- * DESC_ADDR in the range [DESC_ADDR_BASE:DESC_ADDR_BASE + 1 <<
- * WINDOW_SIZE_LOG2) map to TRGT_ADDR = DESC_ADDR - DESC_ADDR_BASE +
- * TRGT_ADDR_BASE.
- */
-#define    DESC_ADDR_REGION_LEN 32
-/* The start of the region in DESC_ADDR space. */
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_OFST 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LEN 8
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_OFST 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_LEN 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_LBN 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LO_WIDTH 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_OFST 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_LEN 4
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_LBN 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_HI_WIDTH 32
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_LBN 0
-#define       DESC_ADDR_REGION_DESC_ADDR_BASE_WIDTH 64
-/* The start of the region in TRGT_ADDR space. Drivers can set this via
- * MC_CMD_SET_DESC_ADDR_REGIONS.
- */
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_OFST 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LEN 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_OFST 8
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_LBN 64
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LO_WIDTH 32
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_OFST 12
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_LBN 96
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_HI_WIDTH 32
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_LBN 64
-#define       DESC_ADDR_REGION_TRGT_ADDR_BASE_WIDTH 64
-/* The size of the region. */
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_OFST 16
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_LEN 4
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_LBN 128
-#define       DESC_ADDR_REGION_WINDOW_SIZE_LOG2_WIDTH 32
-/* The alignment restriction on TRGT_ADDR. TRGT_ADDR values set by the driver
- * must be a multiple of 1 << TRGT_ADDR_ALIGN_LOG2.
- */
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_OFST 20
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_LEN 4
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_LBN 160
-#define       DESC_ADDR_REGION_TRGT_ADDR_ALIGN_LOG2_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_OFST 24
-#define       DESC_ADDR_REGION_RSVD_LEN 8
-#define       DESC_ADDR_REGION_RSVD_LO_OFST 24
-#define       DESC_ADDR_REGION_RSVD_LO_LEN 4
-#define       DESC_ADDR_REGION_RSVD_LO_LBN 192
-#define       DESC_ADDR_REGION_RSVD_LO_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_HI_OFST 28
-#define       DESC_ADDR_REGION_RSVD_HI_LEN 4
-#define       DESC_ADDR_REGION_RSVD_HI_LBN 224
-#define       DESC_ADDR_REGION_RSVD_HI_WIDTH 32
-#define       DESC_ADDR_REGION_RSVD_LBN 192
-#define       DESC_ADDR_REGION_RSVD_WIDTH 64
-
-
 /***********************************/
 /* MC_CMD_GET_DESC_ADDR_INFO
  * Returns a description of the mapping from DESC_ADDR to TRGT_ADDR for the calling function's address space.
@@ -24835,122 +22036,6 @@
 #define    MC_CMD_SET_CLIENT_MAC_ADDRESSES_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_GET_BOARD_ATTR
- * Retrieve physical build-level board attributes as configured at
- * manufacturing stage. Fields originate from EEPROM and per-platform constants
- * in firmware. Fields are used in development to identify/ differentiate
- * boards based on build levels/parameters, and also in manufacturing to cross
- * check "what was programmed in manufacturing" is same as "what firmware
- * thinks has been programmed" as there are two layers to translation within
- * firmware before the attributes reach this MCDI handler. Some parameters are
- * retrieved as part of other commands and therefore not replicated here. See
- * GET_VERSION_OUT.
- */
-#define MC_CMD_GET_BOARD_ATTR 0x1c6
-#undef MC_CMD_0x1c6_PRIVILEGE_CTG
-
-#define MC_CMD_0x1c6_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_BOARD_ATTR_IN msgrequest */
-#define    MC_CMD_GET_BOARD_ATTR_IN_LEN 0
-
-/* MC_CMD_GET_BOARD_ATTR_OUT msgresponse */
-#define    MC_CMD_GET_BOARD_ATTR_OUT_LEN 16
-/* Defines board capabilities and validity of attributes returned in this
- * response-message.
- */
-#define       MC_CMD_GET_BOARD_ATTR_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_BOARD_ATTR_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_LBN 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_FAN_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_LBN 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_SOC_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_OFST 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_LBN 2
-#define        MC_CMD_GET_BOARD_ATTR_OUT_HAS_AUX_POWER_WIDTH 1
-#define       MC_CMD_GET_BOARD_ATTR_OUT_ATTRIBUTES_OFST 4
-#define       MC_CMD_GET_BOARD_ATTR_OUT_ATTRIBUTES_LEN 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_LBN 0
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SOC_EE_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_LBN 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_SUC_EE_WIDTH 1
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_LBN 16
-#define        MC_CMD_GET_BOARD_ATTR_OUT_FPGA_VOLTAGES_SUPPORTED_WIDTH 8
-/* enum: The FPGA voltage on the adapter can be set to low */
-#define          MC_CMD_FPGA_VOLTAGE_LOW 0x0
-/* enum: The FPGA voltage on the adapter can be set to regular */
-#define          MC_CMD_FPGA_VOLTAGE_REG 0x1
-/* enum: The FPGA voltage on the adapter can be set to high */
-#define          MC_CMD_FPGA_VOLTAGE_HIGH 0x2
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_OFST 4
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_LBN 24
-#define        MC_CMD_GET_BOARD_ATTR_OUT_CAGE_COUNT_WIDTH 8
-/* An array of cage types on the board */
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_OFST 8
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_LEN 1
-#define       MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_NUM 8
-/* enum: The cages are not known */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_UNKNOWN 0x0
-/* enum: The cages are SFP/SFP+ */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_SFP 0x1
-/* enum: The cages are QSFP/QSFP+ */
-#define          MC_CMD_GET_BOARD_ATTR_OUT_CAGE_TYPE_QSFP 0x2
-
-
-/***********************************/
-/* MC_CMD_GET_SOC_STATE
- * Retrieve current state of the System-on-Chip. This command is valid when
- * MC_CMD_GET_BOARD_ATTR:HAS_SOC is set.
- */
-#define MC_CMD_GET_SOC_STATE 0x1c7
-#undef MC_CMD_0x1c7_PRIVILEGE_CTG
-
-#define MC_CMD_0x1c7_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_GET_SOC_STATE_IN msgrequest */
-#define    MC_CMD_GET_SOC_STATE_IN_LEN 0
-
-/* MC_CMD_GET_SOC_STATE_OUT msgresponse */
-#define    MC_CMD_GET_SOC_STATE_OUT_LEN 12
-/* Status flags for the SoC */
-#define       MC_CMD_GET_SOC_STATE_OUT_FLAGS_OFST 0
-#define       MC_CMD_GET_SOC_STATE_OUT_FLAGS_LEN 4
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_LBN 0
-#define        MC_CMD_GET_SOC_STATE_OUT_SHOULD_THROTTLE_WIDTH 1
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_LBN 1
-#define        MC_CMD_GET_SOC_STATE_OUT_OS_RECOVERY_REQUIRED_WIDTH 1
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_OFST 0
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_LBN 2
-#define        MC_CMD_GET_SOC_STATE_OUT_WDT_FIRED_WIDTH 1
-/* Status fields for the SoC */
-#define       MC_CMD_GET_SOC_STATE_OUT_ATTRIBUTES_OFST 4
-#define       MC_CMD_GET_SOC_STATE_OUT_ATTRIBUTES_LEN 4
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_OFST 4
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_LBN 0
-#define        MC_CMD_GET_SOC_STATE_OUT_RUN_STATE_WIDTH 8
-/* enum: Power on (set by SUC on power up) */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_BOOT 0x0
-/* enum: Running bootloader */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_BOOTLOADER 0x1
-/* enum: Bootloader has started OS. OS is booting */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_START 0x2
-/* enum: OS is running */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_RUNNING 0x3
-/* enum: Maintenance OS is running */
-#define          MC_CMD_GET_SOC_STATE_OUT_SOC_OS_MAINTENANCE 0x4
-/* Number of SoC resets since power on */
-#define       MC_CMD_GET_SOC_STATE_OUT_RESET_COUNT_OFST 8
-#define       MC_CMD_GET_SOC_STATE_OUT_RESET_COUNT_LEN 4
-
-
 /***********************************/
 /* MC_CMD_CHECK_SCHEDULER_CREDITS
  * For debugging purposes. For each source and destination node in the hardware
@@ -25009,76 +22094,6 @@
 #define       MC_CMD_CHECK_SCHEDULER_CREDITS_OUT_RESULTS_MAXNUM_MCDI2 62
 
 
-/***********************************/
-/* MC_CMD_TXQ_STATS
- * Query per-TXQ statistics.
- */
-#define MC_CMD_TXQ_STATS 0x1d5
-#undef MC_CMD_0x1d5_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d5_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TXQ_STATS_IN msgrequest */
-#define    MC_CMD_TXQ_STATS_IN_LEN 8
-/* Instance of TXQ to retrieve statistics for */
-#define       MC_CMD_TXQ_STATS_IN_INSTANCE_OFST 0
-#define       MC_CMD_TXQ_STATS_IN_INSTANCE_LEN 4
-/* Flags for the request */
-#define       MC_CMD_TXQ_STATS_IN_FLAGS_OFST 4
-#define       MC_CMD_TXQ_STATS_IN_FLAGS_LEN 4
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_OFST 4
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_LBN 0
-#define        MC_CMD_TXQ_STATS_IN_CLEAR_WIDTH 1
-
-/* MC_CMD_TXQ_STATS_OUT msgresponse */
-#define    MC_CMD_TXQ_STATS_OUT_LENMIN 0
-#define    MC_CMD_TXQ_STATS_OUT_LENMAX 248
-#define    MC_CMD_TXQ_STATS_OUT_LENMAX_MCDI2 1016
-#define    MC_CMD_TXQ_STATS_OUT_LEN(num) (0+8*(num))
-#define    MC_CMD_TXQ_STATS_OUT_STATISTICS_NUM(len) (((len)-0)/8)
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_OFST 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LEN 8
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_OFST 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_LEN 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_LBN 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_LO_WIDTH 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_OFST 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_LEN 4
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_LBN 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_HI_WIDTH 32
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MINNUM 0
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MAXNUM 31
-#define       MC_CMD_TXQ_STATS_OUT_STATISTICS_MAXNUM_MCDI2 127
-#define          MC_CMD_TXQ_STATS_CTPIO_MAX_FILL 0x0 /* enum */
-
-/* FUNCTION_PERSONALITY structuredef: The meanings of the personalities are
- * defined in SF-120734-TC with more information in SF-122717-TC.
- */
-#define    FUNCTION_PERSONALITY_LEN 4
-#define       FUNCTION_PERSONALITY_ID_OFST 0
-#define       FUNCTION_PERSONALITY_ID_LEN 4
-/* enum: Function has no assigned personality */
-#define          FUNCTION_PERSONALITY_NULL 0x0
-/* enum: Function has an EF100-style function control window and VI windows
- * with both EF100 and vDPA doorbells.
- */
-#define          FUNCTION_PERSONALITY_EF100 0x1
-/* enum: Function has virtio net device configuration registers and doorbells
- * for virtio queue pairs.
- */
-#define          FUNCTION_PERSONALITY_VIRTIO_NET 0x2
-/* enum: Function has virtio block device configuration registers and a
- * doorbell for a single virtqueue.
- */
-#define          FUNCTION_PERSONALITY_VIRTIO_BLK 0x3
-/* enum: Function is a Xilinx acceleration device - management function */
-#define          FUNCTION_PERSONALITY_ACCEL_MGMT 0x4
-/* enum: Function is a Xilinx acceleration device - user function */
-#define          FUNCTION_PERSONALITY_ACCEL_USR 0x5
-#define       FUNCTION_PERSONALITY_ID_LBN 0
-#define       FUNCTION_PERSONALITY_ID_WIDTH 32
-
-
 /***********************************/
 /* MC_CMD_VIRTIO_GET_FEATURES
  * Get a list of the virtio features supported by the device.
@@ -25161,37 +22176,6 @@
 #define    MC_CMD_VIRTIO_TEST_FEATURES_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_VIRTIO_GET_CAPABILITIES
- * Get virtio capabilities supported by the device. Returns general virtio
- * capabilities and limitations of the hardware / firmware implementation
- * (hardware device as a whole), rather than that of individual configured
- * virtio devices. At present, only the absolute maximum number of queues
- * allowed on multi-queue devices is returned. Response is expected to be
- * extended as necessary in the future.
- */
-#define MC_CMD_VIRTIO_GET_CAPABILITIES 0x1d3
-#undef MC_CMD_0x1d3_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d3_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_VIRTIO_GET_CAPABILITIES_IN msgrequest */
-#define    MC_CMD_VIRTIO_GET_CAPABILITIES_IN_LEN 4
-/* Type of device to get capabilities for. Matches the device id as defined by
- * the virtio spec.
- */
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_IN_DEVICE_ID_OFST 0
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_IN_DEVICE_ID_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_VIRTIO_GET_FEATURES/MC_CMD_VIRTIO_GET_FEATURES_IN/DEVICE_ID */
-
-/* MC_CMD_VIRTIO_GET_CAPABILITIES_OUT msgresponse */
-#define    MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_LEN 4
-/* Maximum number of queues supported for a single device instance */
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_MAX_QUEUES_OFST 0
-#define       MC_CMD_VIRTIO_GET_CAPABILITIES_OUT_MAX_QUEUES_LEN 4
-
-
 /***********************************/
 /* MC_CMD_VIRTIO_INIT_QUEUE
  * Create a virtio virtqueue. Fails with EALREADY if the queue already exists.
@@ -25474,866 +22458,6 @@
 #define       PCIE_FUNCTION_INTF_LBN 32
 #define       PCIE_FUNCTION_INTF_WIDTH 32
 
-/* QUEUE_ID structuredef: Structure representing an absolute queue identifier
- * (absolute VI number + VI relative queue number). On Keystone, a VI can
- * contain multiple queues (at present, up to 2), each with separate controls
- * for direction. This structure is required to uniquely identify the absolute
- * source queue for descriptor proxy functions.
- */
-#define    QUEUE_ID_LEN 4
-/* Absolute VI number */
-#define       QUEUE_ID_ABS_VI_OFST 0
-#define       QUEUE_ID_ABS_VI_LEN 2
-#define       QUEUE_ID_ABS_VI_LBN 0
-#define       QUEUE_ID_ABS_VI_WIDTH 16
-/* Relative queue number within the VI */
-#define       QUEUE_ID_REL_QUEUE_LBN 16
-#define       QUEUE_ID_REL_QUEUE_WIDTH 1
-#define       QUEUE_ID_RESERVED_LBN 17
-#define       QUEUE_ID_RESERVED_WIDTH 15
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CREATE
- * Descriptor proxy functions are abstract devices that forward all request
- * submitted to the host PCIe function (descriptors submitted to Virtio or
- * EF100 queues) to be handled on another function (most commonly on the
- * embedded Application Processor), via EF100 descriptor proxy, memory-to-
- * memory and descriptor-to-completion mechanisms. Primary user is Virtio-blk
- * subsystem, see SF-122927-TC. This function allocates a new descriptor proxy
- * function on the host and assigns a user-defined label. The actual function
- * configuration is not persisted until the caller configures it with
- * MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN and commits with
- * MC_CMD_DESC_PROXY_FUNC_COMMIT_IN.
- */
-#define MC_CMD_DESC_PROXY_FUNC_CREATE 0x172
-#undef MC_CMD_0x172_PRIVILEGE_CTG
-
-#define MC_CMD_0x172_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CREATE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LEN 52
-/* PCIe Function ID to allocate (as struct PCIE_FUNCTION). Set to
- * {PF_ANY,VF_ANY,interface} for "any available function" Set to
- * {PF_ANY,VF_NULL,interface} for "any available PF"
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_LBN 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_PF_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_VF_OFST 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_INTF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_FUNC_INTF_LEN 4
-/* The personality to set. The meanings of the personalities are defined in
- * SF-120734-TC with more information in SF-122717-TC. At present, we only
- * support proxying for VIRTIO_BLK
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_PERSONALITY_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LABEL_OFST 12
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_IN_LABEL_LEN 40
-
-/* MC_CMD_DESC_PROXY_FUNC_CREATE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_LEN 12
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_HANDLE_LEN 4
-/* Allocated function ID (as struct PCIE_FUNCTION) */
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_LBN 64
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_PF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_VF_OFST 6
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_INTF_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_CREATE_OUT_FUNC_INTF_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY
- * Remove an existing descriptor proxy function. Underlying function
- * personality and configuration reverts back to factory default. Function
- * configuration is committed immediately to specified store and any function
- * ownership is released.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DESTROY 0x173
-#undef MC_CMD_0x173_PRIVILEGE_CTG
-
-#define MC_CMD_0x173_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LEN 44
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LABEL_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_LABEL_LEN 40
-/* Store from which to remove function configuration */
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_STORE_OFST 40
-#define       MC_CMD_DESC_PROXY_FUNC_DESTROY_IN_STORE_LEN 4
-/*            Enum values, see field(s): */
-/*               MC_CMD_DESC_PROXY_FUNC_COMMIT/MC_CMD_DESC_PROXY_FUNC_COMMIT_IN/STORE */
-
-/* MC_CMD_DESC_PROXY_FUNC_DESTROY_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DESTROY_OUT_LEN 0
-
-/* VIRTIO_BLK_CONFIG structuredef: Virtio block device configuration. See
- * Virtio specification v1.1, Sections 5.2.3 and 6 for definition of feature
- * bits. See Virtio specification v1.1, Section 5.2.4 (struct
- * virtio_blk_config) for definition of remaining configuration fields
- */
-#define    VIRTIO_BLK_CONFIG_LEN 68
-/* Virtio block device features to advertise, per Virtio 1.1, 5.2.3 and 6 */
-#define       VIRTIO_BLK_CONFIG_FEATURES_OFST 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LEN 8
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_OFST 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_LEN 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_LBN 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_LO_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_OFST 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_LEN 4
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_LBN 32
-#define       VIRTIO_BLK_CONFIG_FEATURES_HI_WIDTH 32
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_LBN 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BARRIER_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_LBN 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SIZE_MAX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_LBN 2
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SEG_MAX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_LBN 4
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_GEOMETRY_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_LBN 5
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_RO_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_LBN 6
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_BLK_SIZE_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_LBN 7
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_SCSI_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_LBN 9
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_FLUSH_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_LBN 10
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_TOPOLOGY_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_LBN 11
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_CONFIG_WCE_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_LBN 12
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_MQ_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_LBN 13
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_DISCARD_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_LBN 14
-#define        VIRTIO_BLK_CONFIG_VIRTIO_BLK_F_WRITE_ZEROES_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_LBN 28
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_INDIRECT_DESC_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_LBN 29
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_EVENT_IDX_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_LBN 32
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_VERSION_1_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_LBN 33
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ACCESS_PLATFORM_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_LBN 34
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_RING_PACKED_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_LBN 35
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_IN_ORDER_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_LBN 36
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_ORDER_PLATFORM_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_LBN 37
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_SR_IOV_WIDTH 1
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_OFST 0
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_LBN 38
-#define        VIRTIO_BLK_CONFIG_VIRTIO_F_NOTIFICATION_DATA_WIDTH 1
-#define       VIRTIO_BLK_CONFIG_FEATURES_LBN 0
-#define       VIRTIO_BLK_CONFIG_FEATURES_WIDTH 64
-/* The capacity of the device (expressed in 512-byte sectors) */
-#define       VIRTIO_BLK_CONFIG_CAPACITY_OFST 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LEN 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_OFST 8
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_LEN 4
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_LBN 64
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LO_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_OFST 12
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_LEN 4
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_LBN 96
-#define       VIRTIO_BLK_CONFIG_CAPACITY_HI_WIDTH 32
-#define       VIRTIO_BLK_CONFIG_CAPACITY_LBN 64
-#define       VIRTIO_BLK_CONFIG_CAPACITY_WIDTH 64
-/* Maximum size of any single segment. Only valid when VIRTIO_BLK_F_SIZE_MAX is
- * set.
- */
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_OFST 16
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_LEN 4
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_LBN 128
-#define       VIRTIO_BLK_CONFIG_SIZE_MAX_WIDTH 32
-/* Maximum number of segments in a request. Only valid when
- * VIRTIO_BLK_F_SEG_MAX is set.
- */
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_OFST 20
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_LEN 4
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_LBN 160
-#define       VIRTIO_BLK_CONFIG_SEG_MAX_WIDTH 32
-/* Disk-style geometry - cylinders. Only valid when VIRTIO_BLK_F_GEOMETRY is
- * set.
- */
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_OFST 24
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_LEN 2
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_LBN 192
-#define       VIRTIO_BLK_CONFIG_CYLINDERS_WIDTH 16
-/* Disk-style geometry - heads. Only valid when VIRTIO_BLK_F_GEOMETRY is set.
- */
-#define       VIRTIO_BLK_CONFIG_HEADS_OFST 26
-#define       VIRTIO_BLK_CONFIG_HEADS_LEN 1
-#define       VIRTIO_BLK_CONFIG_HEADS_LBN 208
-#define       VIRTIO_BLK_CONFIG_HEADS_WIDTH 8
-/* Disk-style geometry - sectors. Only valid when VIRTIO_BLK_F_GEOMETRY is set.
- */
-#define       VIRTIO_BLK_CONFIG_SECTORS_OFST 27
-#define       VIRTIO_BLK_CONFIG_SECTORS_LEN 1
-#define       VIRTIO_BLK_CONFIG_SECTORS_LBN 216
-#define       VIRTIO_BLK_CONFIG_SECTORS_WIDTH 8
-/* Block size of disk. Only valid when VIRTIO_BLK_F_BLK_SIZE is set. */
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_OFST 28
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_LEN 4
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_LBN 224
-#define       VIRTIO_BLK_CONFIG_BLK_SIZE_WIDTH 32
-/* Block topology - number of logical blocks per physical block (log2). Only
- * valid when VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_OFST 32
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_LEN 1
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_LBN 256
-#define       VIRTIO_BLK_CONFIG_PHYSICAL_BLOCK_EXP_WIDTH 8
-/* Block topology - offset of first aligned logical block. Only valid when
- * VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_OFST 33
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_LEN 1
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_LBN 264
-#define       VIRTIO_BLK_CONFIG_ALIGNMENT_OFFSET_WIDTH 8
-/* Block topology - suggested minimum I/O size in blocks. Only valid when
- * VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_OFST 34
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_LEN 2
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_LBN 272
-#define       VIRTIO_BLK_CONFIG_MIN_IO_SIZE_WIDTH 16
-/* Block topology - optimal (suggested maximum) I/O size in blocks. Only valid
- * when VIRTIO_BLK_F_TOPOLOGY is set.
- */
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_OFST 36
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_LEN 4
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_LBN 288
-#define       VIRTIO_BLK_CONFIG_OPT_IO_SIZE_WIDTH 32
-/* Unused, set to zero. Note that virtio_blk_config.writeback is volatile and
- * not carried in config data.
- */
-#define       VIRTIO_BLK_CONFIG_UNUSED0_OFST 40
-#define       VIRTIO_BLK_CONFIG_UNUSED0_LEN 2
-#define       VIRTIO_BLK_CONFIG_UNUSED0_LBN 320
-#define       VIRTIO_BLK_CONFIG_UNUSED0_WIDTH 16
-/* Number of queues. Only valid if the VIRTIO_BLK_F_MQ feature is negotiated.
- */
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_OFST 42
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_LEN 2
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_LBN 336
-#define       VIRTIO_BLK_CONFIG_NUM_QUEUES_WIDTH 16
-/* Maximum discard sectors size, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_OFST 44
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_LBN 352
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SECTORS_WIDTH 32
-/* Maximum discard segment number. Only valid if VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_OFST 48
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_LBN 384
-#define       VIRTIO_BLK_CONFIG_MAX_DISCARD_SEG_WIDTH 32
-/* Discard sector alignment, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_DISCARD is set.
- */
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_OFST 52
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_LEN 4
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_LBN 416
-#define       VIRTIO_BLK_CONFIG_DISCARD_SECTOR_ALIGNMENT_WIDTH 32
-/* Maximum write zeroes sectors size, in 512-byte units. Only valid if
- * VIRTIO_BLK_F_WRITE_ZEROES is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_OFST 56
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_LBN 448
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SECTORS_WIDTH 32
-/* Maximum write zeroes segment number. Only valid if VIRTIO_BLK_F_WRITE_ZEROES
- * is set.
- */
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_OFST 60
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_LEN 4
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_LBN 480
-#define       VIRTIO_BLK_CONFIG_MAX_WRITE_ZEROES_SEG_WIDTH 32
-/* Write zeroes request can result in deallocating one or more sectors. Only
- * valid if VIRTIO_BLK_F_WRITE_ZEROES is set.
- */
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_OFST 64
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_LEN 1
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_LBN 512
-#define       VIRTIO_BLK_CONFIG_WRITE_ZEROES_MAY_UNMAP_WIDTH 8
-/* Unused, set to zero. */
-#define       VIRTIO_BLK_CONFIG_UNUSED1_OFST 65
-#define       VIRTIO_BLK_CONFIG_UNUSED1_LEN 3
-#define       VIRTIO_BLK_CONFIG_UNUSED1_LBN 520
-#define       VIRTIO_BLK_CONFIG_UNUSED1_WIDTH 24
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET
- * Set configuration for an existing descriptor proxy function. Configuration
- * data must match function personality. The actual function configuration is
- * not persisted until the caller commits with MC_CMD_DESC_PROXY_FUNC_COMMIT_IN
- */
-#define MC_CMD_DESC_PROXY_FUNC_CONFIG_SET 0x174
-#undef MC_CMD_0x174_PRIVILEGE_CTG
-
-#define MC_CMD_0x174_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMIN 20
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_LEN(num) (20+1*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_NUM(len) (((len)-20)/1)
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_HANDLE_LEN 4
-/* Reserved for future extension, set to zero. */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_RESERVED_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_RESERVED_LEN 16
-/* Configuration data. Format of configuration data is determined implicitly
- * from function personality referred to by HANDLE. Currently, only supported
- * format is VIRTIO_BLK_CONFIG.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_OFST 20
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_LEN 1
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MAXNUM 232
-#define       MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_IN_CONFIG_MAXNUM_MCDI2 1000
-
-/* MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CONFIG_SET_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT
- * Commit function configuration to non-volatile or volatile store. Once
- * configuration is applied to hardware (which may happen immediately or on
- * next function/device reset) a DESC_PROXY_FUNC_CONFIG_SET MCDI event will be
- * delivered to callers MCDI event queue.
- */
-#define MC_CMD_DESC_PROXY_FUNC_COMMIT 0x175
-#undef MC_CMD_0x175_PRIVILEGE_CTG
-
-#define MC_CMD_0x175_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_HANDLE_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_STORE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_STORE_LEN 4
-/* enum: Store into non-volatile (dynamic) config */
-#define          MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_NON_VOLATILE 0x0
-/* enum: Store into volatile (ephemeral) config */
-#define          MC_CMD_DESC_PROXY_FUNC_COMMIT_IN_VOLATILE 0x1
-
-/* MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_LEN 4
-/* Generation count to be delivered in an event once configuration becomes live
- */
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_CONFIG_GENERATION_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_COMMIT_OUT_CONFIG_GENERATION_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_OPEN
- * Retrieve a handle for an existing descriptor proxy function. Returns an
- * integer handle, valid until function is deallocated, MC rebooted or power-
- * cycle. Returns ENODEV if no function with given label exists.
- */
-#define MC_CMD_DESC_PROXY_FUNC_OPEN 0x176
-#undef MC_CMD_0x176_PRIVILEGE_CTG
-
-#define MC_CMD_0x176_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_OPEN_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LEN 40
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LABEL_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_IN_LABEL_LEN 40
-
-/* MC_CMD_DESC_PROXY_FUNC_OPEN_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMIN 40
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LEN(num) (40+1*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_NUM(len) (((len)-40)/1)
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_HANDLE_LEN 4
-/* PCIe Function ID (as struct PCIE_FUNCTION) */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LEN 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_LBN 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_LO_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_LBN 64
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_HI_WIDTH 32
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_PF_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_PF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_VF_OFST 6
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_VF_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_INTF_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_FUNC_INTF_LEN 4
-/* Function personality */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PERSONALITY_OFST 12
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-/* Function configuration state */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_STATUS_OFST 16
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_STATUS_LEN 4
-/* enum: Function configuration is visible to the host (live) */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_LIVE 0x0
-/* enum: Function configuration is pending reset */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_PENDING 0x1
-/* enum: Function configuration is missing (created, but no configuration
- * committed)
- */
-#define          MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_UNCONFIGURED 0x2
-/* Generation count to be delivered in an event once the configuration becomes
- * live (if status is "pending")
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_GENERATION_OFST 20
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_GENERATION_LEN 4
-/* Reserved for future extension, set to zero. */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_RESERVED_OFST 24
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_RESERVED_LEN 16
-/* Configuration data corresponding to function personality. Currently, only
- * supported format is VIRTIO_BLK_CONFIG. Not valid if status is UNCONFIGURED.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_OFST 40
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_LEN 1
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MAXNUM 212
-#define       MC_CMD_DESC_PROXY_FUNC_OPEN_OUT_CONFIG_MAXNUM_MCDI2 980
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE
- * Releases a handle for an open descriptor proxy function. If proxying was
- * enabled on the device, the caller is expected to gracefully stop it using
- * MC_CMD_DESC_PROXY_FUNC_DISABLE prior to calling this function. Closing an
- * active device without disabling proxying will result in forced close, which
- * will put the device into a failed state and signal the host driver of the
- * error (for virtio, DEVICE_NEEDS_RESET flag would be set on the host side)
- */
-#define MC_CMD_DESC_PROXY_FUNC_CLOSE 0x1a1
-#undef MC_CMD_0x1a1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_LEN 4
-/* Handle to the descriptor proxy function */
-#define       MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_CLOSE_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_CLOSE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_CLOSE_OUT_LEN 0
-
-/* DESC_PROXY_FUNC_MAP structuredef */
-#define    DESC_PROXY_FUNC_MAP_LEN 52
-/* PCIe function ID (as struct PCIE_FUNCTION) */
-#define       DESC_PROXY_FUNC_MAP_FUNC_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LEN 8
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_LO_WIDTH 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_OFST 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_LBN 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_HI_WIDTH 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_WIDTH 64
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_OFST 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_LEN 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_LBN 0
-#define       DESC_PROXY_FUNC_MAP_FUNC_PF_WIDTH 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_OFST 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_LEN 2
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_LBN 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_VF_WIDTH 16
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_OFST 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_LEN 4
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_LBN 32
-#define       DESC_PROXY_FUNC_MAP_FUNC_INTF_WIDTH 32
-/* Function personality */
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_OFST 8
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_LEN 4
-/*            Enum values, see field(s): */
-/*               FUNCTION_PERSONALITY/ID */
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_LBN 64
-#define       DESC_PROXY_FUNC_MAP_PERSONALITY_WIDTH 32
-/* User-defined label (zero-terminated ASCII string) to uniquely identify the
- * function
- */
-#define       DESC_PROXY_FUNC_MAP_LABEL_OFST 12
-#define       DESC_PROXY_FUNC_MAP_LABEL_LEN 40
-#define       DESC_PROXY_FUNC_MAP_LABEL_LBN 96
-#define       DESC_PROXY_FUNC_MAP_LABEL_WIDTH 320
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENUM
- * Enumerate existing descriptor proxy functions
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENUM 0x177
-#undef MC_CMD_0x177_PRIVILEGE_CTG
-
-#define MC_CMD_0x177_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENUM_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_IN_LEN 4
-/* Starting index, set to 0 on first request. See
- * MC_CMD_DESC_PROXY_FUNC_ENUM_OUT/FLAGS.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_IN_START_IDX_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_IN_START_IDX_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENUM_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMIN 4
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMAX 212
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LENMAX_MCDI2 992
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_LEN(num) (4+52*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_NUM(len) (((len)-4)/52)
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FLAGS_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FLAGS_LEN 4
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_OFST 0
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_LBN 0
-#define        MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_MORE_DATA_WIDTH 1
-/* Function map, as array of DESC_PROXY_FUNC_MAP */
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_LEN 52
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MAXNUM 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENUM_OUT_FUNC_MAP_MAXNUM_MCDI2 19
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE
- * Enable descriptor proxying for function into target event queue. Returns VI
- * allocation info for the proxy source function, so that the caller can map
- * absolute VI IDs from descriptor proxy events back to the originating
- * function. This is a legacy function that only supports single queue proxy
- * devices. It is also limited in that it can only be called after host driver
- * attach (once VI allocation is known) and will return MC_CMD_ERR_ENOTCONN
- * otherwise. For new code, see MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE which
- * supports multi-queue devices and has no dependency on host driver attach.
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENABLE 0x178
-#undef MC_CMD_0x178_PRIVILEGE_CTG
-
-#define MC_CMD_0x178_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_HANDLE_LEN 4
-/* Descriptor proxy sink queue (caller function relative). Must be extended
- * width event queue
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_TARGET_EVQ_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_IN_TARGET_EVQ_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_LEN 8
-/* The number of VIs allocated on the function */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_COUNT_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_COUNT_LEN 4
-/* The base absolute VI number allocated to the function. */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_BASE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_OUT_VI_BASE_LEN 4
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE
- * Enable descriptor proxying for a source queue on a host function into target
- * event queue. Source queue number is a relative virtqueue number on the
- * source function (0 to max_virtqueues-1). For a multi-queue device, the
- * caller must enable all source queues individually. To retrieve absolute VI
- * information for the source function (so that VI IDs from descriptor proxy
- * events can be mapped back to source function / queue) see
- * MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO
- */
-#define MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE 0x1d0
-#undef MC_CMD_0x1d0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d0_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_LEN 12
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_HANDLE_LEN 4
-/* Source relative queue number to enable proxying on */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_SOURCE_QUEUE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_SOURCE_QUEUE_LEN 4
-/* Descriptor proxy sink queue (caller function relative). Must be extended
- * width event queue
- */
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_TARGET_EVQ_OFST 8
-#define       MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_IN_TARGET_EVQ_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_ENABLE_QUEUE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE
- * Disable descriptor proxying for function. For multi-queue functions,
- * disables all queues.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DISABLE 0x179
-#undef MC_CMD_0x179_PRIVILEGE_CTG
-
-#define MC_CMD_0x179_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_LEN 4
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE
- * Disable descriptor proxying for a specific source queue on a function.
- */
-#define MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE 0x1d1
-#undef MC_CMD_0x1d1_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d1_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_LEN 8
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_HANDLE_LEN 4
-/* Source relative queue number to disable proxying on */
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_SOURCE_QUEUE_OFST 4
-#define       MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_IN_SOURCE_QUEUE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_DISABLE_QUEUE_OUT_LEN 0
-
-
-/***********************************/
-/* MC_CMD_DESC_PROXY_GET_VI_INFO
- * Returns absolute VI allocation information for the descriptor proxy source
- * function referenced by HANDLE, so that the caller can map absolute VI IDs
- * from descriptor proxy events back to the originating function and queue. The
- * call is only valid after the host driver for the source function has
- * attached (after receiving a driver attach event for the descriptor proxy
- * function) and will fail with ENOTCONN otherwise.
- */
-#define MC_CMD_DESC_PROXY_GET_VI_INFO 0x1d2
-#undef MC_CMD_0x1d2_PRIVILEGE_CTG
-
-#define MC_CMD_0x1d2_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_DESC_PROXY_GET_VI_INFO_IN msgrequest */
-#define    MC_CMD_DESC_PROXY_GET_VI_INFO_IN_LEN 4
-/* Handle to descriptor proxy function (as returned by
- * MC_CMD_DESC_PROXY_FUNC_OPEN)
- */
-#define       MC_CMD_DESC_PROXY_GET_VI_INFO_IN_HANDLE_OFST 0
-#define       MC_CMD_DESC_PROXY_GET_VI_INFO_IN_HANDLE_LEN 4
-
-/* MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT msgresponse */
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMIN 0
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMAX 252
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_LEN(num) (0+4*(num))
-#define    MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_NUM(len) (((len)-0)/4)
-/* VI information (VI ID + VI relative queue number) for each of the source
- * queues (in order from 0 to max_virtqueues-1), as array of QUEUE_ID
- * structures.
- */
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_LEN 4
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MINNUM 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MAXNUM 63
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_MAXNUM_MCDI2 255
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_ABS_VI_OFST 0
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_ABS_VI_LEN 2
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_REL_QUEUE_LBN 16
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_REL_QUEUE_WIDTH 1
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_RESERVED_LBN 17
-#define       MC_CMD_DESC_PROXY_FUNC_GET_VI_INFO_OUT_VI_MAP_RESERVED_WIDTH 15
-
-
-/***********************************/
-/* MC_CMD_GET_ADDR_SPC_ID
- * Get Address space identifier for use in mem2mem descriptors for a given
- * target. See SF-120734-TC for details on ADDR_SPC_IDs and mem2mem
- * descriptors.
- */
-#define MC_CMD_GET_ADDR_SPC_ID 0x1a0
-#undef MC_CMD_0x1a0_PRIVILEGE_CTG
-
-#define MC_CMD_0x1a0_PRIVILEGE_CTG SRIOV_CTG_ADMIN
-
-/* MC_CMD_GET_ADDR_SPC_ID_IN msgrequest */
-#define    MC_CMD_GET_ADDR_SPC_ID_IN_LEN 16
-/* Resource type to get ADDR_SPC_ID for */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_TYPE_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_TYPE_LEN 4
-/* enum: Address space ID for host/AP memory DMA over the same interface this
- * MCDI was called on
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_SELF 0x0
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_PCI_FUNC 0x1
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC with PASID value specified by PASID
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_PCI_FUNC_PASID 0x2
-/* enum: Address space ID for host/AP memory DMA via PCI interface and function
- * specified by FUNC with PASID value of relative VI specified by VI
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_REL_VI 0x3
-/* enum: Address space ID for host/AP memory DMA via PCI interface, function
- * and PASID value of absolute VI specified by VI
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_ABS_VI 0x4
-/* enum: Address space ID for host memory DMA via PCI interface and function of
- * descriptor proxy function specified by HANDLE
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_DESC_PROXY_HANDLE 0x5
-/* enum: Address space ID for DMA to/from MC memory */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_MC_MEM 0x6
-/* enum: Address space ID for DMA to/from other SmartNIC memory (on-chip, DDR)
- */
-#define          MC_CMD_GET_ADDR_SPC_ID_IN_NIC_MEM 0x7
-/* PCIe Function ID (as struct PCIE_FUNCTION). Only valid if TYPE is PCI_FUNC,
- * PCI_FUNC_PASID or REL_VI.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LEN 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_LBN 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_LO_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_OFST 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_LBN 64
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_HI_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_PF_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_PF_LEN 2
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_VF_OFST 6
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_VF_LEN 2
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_INTF_OFST 8
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_FUNC_INTF_LEN 4
-/* PASID value. Only valid if TYPE is PCI_FUNC_PASID. */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_PASID_OFST 12
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_PASID_LEN 4
-/* Relative or absolute VI number. Only valid if TYPE is REL_VI or ABS_VI */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_VI_OFST 12
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_VI_LEN 4
-/* Descriptor proxy function handle. Only valid if TYPE is DESC_PROXY_HANDLE.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_HANDLE_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_IN_HANDLE_LEN 4
-
-/* MC_CMD_GET_ADDR_SPC_ID_OUT msgresponse */
-#define    MC_CMD_GET_ADDR_SPC_ID_OUT_LEN 8
-/* Address Space ID for the requested target. Only the lower 36 bits are valid
- * in the current SmartNIC implementation.
- */
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LEN 8
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_OFST 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_LBN 0
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_LO_WIDTH 32
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_OFST 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_LEN 4
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_LBN 32
-#define       MC_CMD_GET_ADDR_SPC_ID_OUT_ADDR_SPC_ID_HI_WIDTH 32
-
 
 /***********************************/
 /* MC_CMD_GET_CLIENT_HANDLE
@@ -26359,7 +22483,8 @@
  * INTF=CALLER, PF=PF_NULL, VF=... to refer to a VF child of the calling PF or
  * a sibling VF of the calling VF. - INTF=CALLER, PF=..., VF=VF_NULL to refer
  * to a PF on the calling interface - INTF=CALLER, PF=..., VF=... to refer to a
- * VF on the calling interface - INTF=..., PF=..., VF=VF_NULL to refer to a PF
+ * VF on the calling interface - INTF=..., PF=PF_NULL, VF=VF_NULL to refer to
+ * the named interface itself - INTF=..., PF=..., VF=VF_NULL to refer to a PF
  * on a named interface - INTF=..., PF=..., VF=... to refer to a VF on a named
  * interface where ... refers to a small integer for the VF/PF fields, and to
  * values from the PCIE_INTERFACE enum for for the INTF field. It's only
@@ -26380,6 +22505,7 @@
  * backwards compatibility only, callers should use PCIE_INTERFACE_CALLER.
  */
 #define          MC_CMD_GET_CLIENT_HANDLE_IN_PCIE_FUNCTION_INTF_NULL 0xffffffff
+/* See structuredef: PCIE_FUNCTION */
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_PF_OFST 4
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_PF_LEN 2
 #define       MC_CMD_GET_CLIENT_HANDLE_IN_FUNC_VF_OFST 6
@@ -27350,7 +23476,7 @@
 /* MAE_MPORT_SELECTOR structuredef: MPORTS are identified by an opaque unsigned
  * integer value (mport_id) that is guaranteed to be representable within
  * 32-bits or within any NIC interface field that needs store the value
- * (whichever is narrowers). This selector structure provides a stable way to
+ * (whichever is narrower). This selector structure provides a stable way to
  * refer to m-ports.
  */
 #define    MAE_MPORT_SELECTOR_LEN 4
@@ -27425,10 +23551,22 @@
 #define       MAE_MPORT_SELECTOR_FLAT_WIDTH 32
 
 /* MAE_LINK_ENDPOINT_SELECTOR structuredef: Structure that identifies a real or
- * virtual network port by MAE port and link end
+ * virtual network port by MAE port and link end. Intended to be used by
+ * network port MCDI commands. Setting FLAT to MAE_LINK_ENDPOINT_COMPAT is
+ * equivalent to using the previous version of the command. Not all possible
+ * combinations of MPORT_END and MPORT_SELECTOR in MAE_LINK_ENDPOINT_SELECTOR
+ * will work in all circumstances. 1. Some will always work (e.g. a VF can
+ * always address its logical MAC using MPORT_SELECTOR=ASSIGNED,LINK_END=VNIC),
+ * 2. Some are not meaningful and will always fail with EINVAL (e.g. attempting
+ * to address the VNIC end of a link to a physical port), 3. Some are
+ * meaningful but require the MCDI client to have the required permission and
+ * fail with EPERM otherwise (e.g. trying to set the MAC on a VF the caller
+ * cannot administer), and 4. Some could be implementation-specific and fail
+ * with ENOTSUP if not available (no examples exist right now). See
+ * SF-123581-TC section 4.3 for more details.
  */
 #define    MAE_LINK_ENDPOINT_SELECTOR_LEN 8
-/* The MAE MPORT of interest */
+/* Identifier for the MAE MPORT of interest */
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_OFST 0
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_LEN 4
 #define       MAE_LINK_ENDPOINT_SELECTOR_MPORT_SELECTOR_LBN 0
@@ -27829,6 +23967,8 @@
 #define       MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_MAXNUM_MCDI2 253
 /* enum: A counter ID that is guaranteed never to represent a real counter */
 #define          MC_CMD_MAE_COUNTER_ALLOC_OUT_COUNTER_ID_NULL 0xffffffff
+/*            Other enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 
 
 /***********************************/
@@ -28266,6 +24406,24 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_OFST 0
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_LBN 14
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_IN_LACP_INC_L4_WIDTH 1
 /* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_VLAN0_TCI_BE_OFST 4
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_VLAN0_TCI_BE_LEN 2
@@ -28291,19 +24449,23 @@
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_DELIVER_OFST 20
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_DELIVER_LEN 4
 /* Allows an action set to trigger several counter updates. Set to
- * COUNTER_LIST_ID_NULL to request no counter action.
+ * MAE_COUNTER_ID_NULL to request no counter action.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_LIST_ID_OFST 24
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 /* If a driver only wished to update one counter within this action set, then
  * it can supply a COUNTER_ID instead of allocating a single-element counter
  * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
- * should be set to COUNTER_ID_NULL if this behaviour is not required. It is
- * not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
  * COUNTER_ID.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_ID_OFST 28
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_MARK_VALUE_OFST 32
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_IN_MARK_VALUE_LEN 4
 /* Set to MAC_ID_NULL to request no source MAC replacement. */
@@ -28347,6 +24509,24 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_OFST 0
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_LBN 14
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_LACP_INC_L4_WIDTH 1
 /* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_VLAN0_TCI_BE_OFST 4
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_VLAN0_TCI_BE_LEN 2
@@ -28372,19 +24552,23 @@
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DELIVER_OFST 20
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_DELIVER_LEN 4
 /* Allows an action set to trigger several counter updates. Set to
- * COUNTER_LIST_ID_NULL to request no counter action.
+ * MAE_COUNTER_ID_NULL to request no counter action.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_LIST_ID_OFST 24
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 /* If a driver only wished to update one counter within this action set, then
  * it can supply a COUNTER_ID instead of allocating a single-element counter
  * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
- * should be set to COUNTER_ID_NULL if this behaviour is not required. It is
- * not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
  * COUNTER_ID.
  */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_ID_OFST 28
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_MARK_VALUE_OFST 32
 #define       MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_MARK_VALUE_LEN 4
 /* Set to MAC_ID_NULL to request no source MAC replacement. */
@@ -28437,6 +24621,172 @@
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_ECN_ECT_1_TO_CE_LBN 6
 #define        MC_CMD_MAE_ACTION_SET_ALLOC_V2_IN_ECN_ECT_1_TO_CE_WIDTH 1
 
+/* MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN msgrequest: Only supported if
+ * MAE_ACTION_SET_ALLOC_V3_SUPPORTED is advertised in
+ * MC_CMD_GET_CAPABILITIES_V10_OUT.
+ */
+#define    MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LEN 53
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAGS_OFST 0
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAGS_LEN 4
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_PUSH_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_LBN 4
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN_POP_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_LBN 8
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DECAP_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_LBN 9
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_LBN 10
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_FLAG_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_LBN 11
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_NAT_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_LBN 12
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DECR_IP_TTL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_LBN 13
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_SRC_MPORT_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_LBN 14
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SUPPRESS_SELF_DELIVERY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_LBN 15
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_LBN 16
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_LBN 17
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_RDP_OUT_HOST_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_LBN 18
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_SET_NET_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_LBN 19
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_PLUGIN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_OFST 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_LBN 20
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_LACP_INC_L4_WIDTH 1
+/* If VLAN_PUSH >= 1, TCI value to be inserted as outermost VLAN. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_TCI_BE_OFST 4
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_TCI_BE_LEN 2
+/* If VLAN_PUSH >= 1, TPID value to be inserted as outermost VLAN. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_PROTO_BE_OFST 6
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN0_PROTO_BE_LEN 2
+/* If VLAN_PUSH == 2, inner TCI value to be inserted. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_TCI_BE_OFST 8
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_TCI_BE_LEN 2
+/* If VLAN_PUSH == 2, inner TPID value to be inserted. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_PROTO_BE_OFST 10
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_VLAN1_PROTO_BE_LEN 2
+/* Reserved. Ignored by firmware. Should be set to zero or 0xffffffff. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RSVD_OFST 12
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RSVD_LEN 4
+/* Set to ENCAP_HEADER_ID_NULL to request no encap action */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ENCAP_HEADER_ID_OFST 16
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ENCAP_HEADER_ID_LEN 4
+/* An m-port selector identifying the m-port that the modified packet should be
+ * delivered to. Set to MPORT_SELECTOR_NULL to request no delivery of the
+ * packet.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DELIVER_OFST 20
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DELIVER_LEN 4
+/* Allows an action set to trigger several counter updates. Set to
+ * MAE_COUNTER_ID_NULL to request no counter action.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_LIST_ID_OFST 24
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_LIST_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
+/* If a driver only wished to update one counter within this action set, then
+ * it can supply a COUNTER_ID instead of allocating a single-element counter
+ * list. The ID must have been allocated with COUNTER_TYPE=AR. This field
+ * should be set to MAE_COUNTER_ID_NULL if this behaviour is not required. It
+ * is not valid to supply a non-NULL value for both COUNTER_LIST_ID and
+ * COUNTER_ID.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_ID_OFST 28
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_COUNTER_ID_LEN 4
+/*            Enum values, see field(s): */
+/*               MAE_COUNTER_ID */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_VALUE_OFST 32
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_MARK_VALUE_LEN 4
+/* Set to MAC_ID_NULL to request no source MAC replacement. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SRC_MAC_ID_OFST 36
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_SRC_MAC_ID_LEN 4
+/* Set to MAC_ID_NULL to request no destination MAC replacement. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DST_MAC_ID_OFST 40
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DST_MAC_ID_LEN 4
+/* Source m-port ID to be reported for DO_SET_SRC_MPORT action. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_REPORTED_SRC_MPORT_OFST 44
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_REPORTED_SRC_MPORT_LEN 4
+/* Actions for modifying the Differentiated Services Code-Point (DSCP) bits
+ * within IPv4 and IPv6 headers.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_CONTROL_OFST 48
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_CONTROL_LEN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_ENCAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_DSCP_DECAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_DSCP_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_OFST 48
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DSCP_VALUE_WIDTH 6
+/* Actions for modifying the Explicit Congestion Notification (ECN) bits within
+ * IPv4 and IPv6 headers.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_CONTROL_OFST 50
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_CONTROL_LEN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_ENCAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_ECN_DECAP_COPY_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_DO_REPLACE_ECN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_VALUE_WIDTH 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_LBN 5
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_0_TO_CE_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_OFST 50
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_LBN 6
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_ECN_ECT_1_TO_CE_WIDTH 1
+/* Actions for overwriting CH_ROUTE subfields. */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OVERWRITE_OFST 51
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OVERWRITE_LEN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_LBN 0
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_C_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_LBN 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_D_PL_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_LBN 2
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_PL_CHAN_WIDTH 1
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_OFST 51
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_LBN 3
+#define        MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_RDP_OUT_HOST_CHAN_WIDTH 1
+/* Override outgoing CH_VC to network port for DO_SET_NET_CHAN action. Cannot
+ * be used in conjunction with DO_SET_SRC_MPORT action.
+ */
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_NET_CHAN_OFST 52
+#define       MC_CMD_MAE_ACTION_SET_ALLOC_V3_IN_NET_CHAN_LEN 1
+
 /* MC_CMD_MAE_ACTION_SET_ALLOC_OUT msgresponse */
 #define    MC_CMD_MAE_ACTION_SET_ALLOC_OUT_LEN 4
 /* The MSB of the AS_ID is guaranteed to be clear if the ID is not
@@ -28680,58 +25030,6 @@
 #define       MC_CMD_MAE_OUTER_RULE_REMOVE_OUT_REMOVED_OR_ID_MAXNUM 32
 #define       MC_CMD_MAE_OUTER_RULE_REMOVE_OUT_REMOVED_OR_ID_MAXNUM_MCDI2 32
 
-
-/***********************************/
-/* MC_CMD_MAE_OUTER_RULE_UPDATE
- * Atomically change the response of an Outer Rule.
- */
-#define MC_CMD_MAE_OUTER_RULE_UPDATE 0x17d
-#undef MC_CMD_0x17d_PRIVILEGE_CTG
-
-#define MC_CMD_0x17d_PRIVILEGE_CTG SRIOV_CTG_MAE
-
-/* MC_CMD_MAE_OUTER_RULE_UPDATE_IN msgrequest */
-#define    MC_CMD_MAE_OUTER_RULE_UPDATE_IN_LEN 16
-/* ID of outer rule to update */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_OR_ID_OFST 0
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_OR_ID_LEN 4
-/* Packets matching the rule will be parsed with this encapsulation. */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ENCAP_TYPE_OFST 4
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ENCAP_TYPE_LEN 4
-/*            Enum values, see field(s): */
-/*               MAE_MCDI_ENCAP_TYPE */
-/* This field controls the actions that are performed when a rule is hit. */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ACTION_CONTROL_OFST 8
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_ACTION_CONTROL_LEN 4
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_LBN 0
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_CT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_LBN 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_VNI_MODE_WIDTH 2
-/*             Enum values, see field(s): */
-/*                MAE_CT_VNI_MODE */
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_LBN 3
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_DO_COUNT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_LBN 4
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_TCP_FLAGS_INHIBIT_WIDTH 1
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_LBN 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_RECIRC_ID_WIDTH 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_OFST 8
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_LBN 16
-#define        MC_CMD_MAE_OUTER_RULE_UPDATE_IN_CT_DOMAIN_WIDTH 16
-/* ID of counter to increment when the rule is hit. Only used if the DO_COUNT
- * flag is set. The ID must have been allocated with COUNTER_TYPE=OR.
- */
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_COUNTER_ID_OFST 12
-#define       MC_CMD_MAE_OUTER_RULE_UPDATE_IN_COUNTER_ID_LEN 4
-
-/* MC_CMD_MAE_OUTER_RULE_UPDATE_OUT msgresponse */
-#define    MC_CMD_MAE_OUTER_RULE_UPDATE_OUT_LEN 0
-
 /* MAE_ACTION_RULE_RESPONSE structuredef */
 #define    MAE_ACTION_RULE_RESPONSE_LEN 16
 #define       MAE_ACTION_RULE_RESPONSE_ASL_ID_OFST 0
@@ -29122,142 +25420,6 @@
 #define       MAE_MPORT_DESC_VNIC_PLUGIN_TBD_LBN 352
 #define       MAE_MPORT_DESC_VNIC_PLUGIN_TBD_WIDTH 32
 
-/* MAE_MPORT_DESC_V2 structuredef */
-#define    MAE_MPORT_DESC_V2_LEN 56
-#define       MAE_MPORT_DESC_V2_MPORT_ID_OFST 0
-#define       MAE_MPORT_DESC_V2_MPORT_ID_LEN 4
-#define       MAE_MPORT_DESC_V2_MPORT_ID_LBN 0
-#define       MAE_MPORT_DESC_V2_MPORT_ID_WIDTH 32
-/* Reserved for future purposes, contains information independent of caller */
-#define       MAE_MPORT_DESC_V2_FLAGS_OFST 4
-#define       MAE_MPORT_DESC_V2_FLAGS_LEN 4
-#define       MAE_MPORT_DESC_V2_FLAGS_LBN 32
-#define       MAE_MPORT_DESC_V2_FLAGS_WIDTH 32
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_OFST 8
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_LEN 4
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_LBN 0
-#define        MAE_MPORT_DESC_V2_CAN_RECEIVE_ON_WIDTH 1
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_LBN 1
-#define        MAE_MPORT_DESC_V2_CAN_DELIVER_TO_WIDTH 1
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_OFST 8
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_LBN 2
-#define        MAE_MPORT_DESC_V2_CAN_DELETE_WIDTH 1
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_OFST 8
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_LBN 3
-#define        MAE_MPORT_DESC_V2_IS_ZOMBIE_WIDTH 1
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_LBN 64
-#define       MAE_MPORT_DESC_V2_CALLER_FLAGS_WIDTH 32
-/* Not the ideal name; it's really the type of thing connected to the m-port */
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_OFST 12
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_LEN 4
-/* enum: Connected to a MAC... */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_NET_PORT 0x0
-/* enum: Adds metadata and delivers to another m-port */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_ALIAS 0x1
-/* enum: Connected to a VNIC. */
-#define          MAE_MPORT_DESC_V2_MPORT_TYPE_VNIC 0x2
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_LBN 96
-#define       MAE_MPORT_DESC_V2_MPORT_TYPE_WIDTH 32
-/* 128-bit value available to drivers for m-port identification. */
-#define       MAE_MPORT_DESC_V2_UUID_OFST 16
-#define       MAE_MPORT_DESC_V2_UUID_LEN 16
-#define       MAE_MPORT_DESC_V2_UUID_LBN 128
-#define       MAE_MPORT_DESC_V2_UUID_WIDTH 128
-/* Big wadge of space reserved for other common properties */
-#define       MAE_MPORT_DESC_V2_RESERVED_OFST 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LEN 8
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_OFST 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_LEN 4
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_LBN 256
-#define       MAE_MPORT_DESC_V2_RESERVED_LO_WIDTH 32
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_OFST 36
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_LEN 4
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_LBN 288
-#define       MAE_MPORT_DESC_V2_RESERVED_HI_WIDTH 32
-#define       MAE_MPORT_DESC_V2_RESERVED_LBN 256
-#define       MAE_MPORT_DESC_V2_RESERVED_WIDTH 64
-/* Logical port index. Only valid when type NET Port. */
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_OFST 40
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_LEN 4
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_LBN 320
-#define       MAE_MPORT_DESC_V2_NET_PORT_IDX_WIDTH 32
-/* The m-port delivered to */
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_OFST 40
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_LEN 4
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_LBN 320
-#define       MAE_MPORT_DESC_V2_ALIAS_DELIVER_MPORT_ID_WIDTH 32
-/* The type of thing that owns the VNIC */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_OFST 40
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_LEN 4
-#define          MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_FUNCTION 0x1 /* enum */
-#define          MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_PLUGIN 0x2 /* enum */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_LBN 320
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_TYPE_WIDTH 32
-/* The PCIe interface on which the function lives. CJK: We need an enumeration
- * of interfaces that we extend as new interface (types) appear. This belongs
- * elsewhere and should be referenced from here
- */
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_OFST 44
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_LBN 352
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_INTERFACE_WIDTH 32
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_OFST 48
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_LEN 2
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_LBN 384
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_PF_IDX_WIDTH 16
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_OFST 50
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_LEN 2
-/* enum: Indicates that the function is a PF */
-#define          MAE_MPORT_DESC_V2_VF_IDX_NULL 0xffff
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_LBN 400
-#define       MAE_MPORT_DESC_V2_VNIC_FUNCTION_VF_IDX_WIDTH 16
-/* Reserved. Should be ignored for now. */
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_OFST 44
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_LBN 352
-#define       MAE_MPORT_DESC_V2_VNIC_PLUGIN_TBD_WIDTH 32
-/* A client handle for the VNIC's owner. Only valid for type VNIC. */
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_OFST 52
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_LEN 4
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_LBN 416
-#define       MAE_MPORT_DESC_V2_VNIC_CLIENT_HANDLE_WIDTH 32
-
-
-/***********************************/
-/* MC_CMD_MAE_MPORT_ENUMERATE
- * Deprecated in favour of MAE_MPORT_READ_JOURNAL. Support for this command
- * will be removed at some future point.
- */
-#define MC_CMD_MAE_MPORT_ENUMERATE 0x17c
-#undef MC_CMD_0x17c_PRIVILEGE_CTG
-
-#define MC_CMD_0x17c_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_MAE_MPORT_ENUMERATE_IN msgrequest */
-#define    MC_CMD_MAE_MPORT_ENUMERATE_IN_LEN 0
-
-/* MC_CMD_MAE_MPORT_ENUMERATE_OUT msgresponse */
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMIN 8
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMAX 252
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LENMAX_MCDI2 1020
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_LEN(num) (8+1*(num))
-#define    MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_NUM(len) (((len)-8)/1)
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_COUNT_OFST 0
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_COUNT_LEN 4
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_SIZEOF_MPORT_DESC_OFST 4
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_SIZEOF_MPORT_DESC_LEN 4
-/* Any array of MAE_MPORT_DESC structures. The MAE_MPORT_DESC structure may
- * grow in future version of this command. Drivers should use a stride of
- * SIZEOF_MPORT_DESC. Fields beyond SIZEOF_MPORT_DESC are not present.
- */
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_OFST 8
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_LEN 1
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MINNUM 0
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MAXNUM 244
-#define       MC_CMD_MAE_MPORT_ENUMERATE_OUT_MPORT_DESC_DATA_MAXNUM_MCDI2 1012
-
 
 /***********************************/
 /* MC_CMD_MAE_MPORT_READ_JOURNAL
@@ -29569,73 +25731,6 @@
 #define    MC_CMD_TABLE_INSERT_OUT_LEN 0
 
 
-/***********************************/
-/* MC_CMD_TABLE_UPDATE
- * Update an existing entry in a table with a new response value. May return
- * EINVAL for unknown table ID or other bad request parameters, ENOENT if the
- * entry does not already exist, or EPERM if the operation is not permitted. In
- * case of an error, the additional MCDI error argument field returns the raw
- * error code from the underlying CAM driver.
- */
-#define MC_CMD_TABLE_UPDATE 0x1ce
-#undef MC_CMD_0x1ce_PRIVILEGE_CTG
-
-#define MC_CMD_0x1ce_PRIVILEGE_CTG SRIOV_CTG_GENERAL
-
-/* MC_CMD_TABLE_UPDATE_IN msgrequest */
-#define    MC_CMD_TABLE_UPDATE_IN_LENMIN 16
-#define    MC_CMD_TABLE_UPDATE_IN_LENMAX 252
-#define    MC_CMD_TABLE_UPDATE_IN_LENMAX_MCDI2 1020
-#define    MC_CMD_TABLE_UPDATE_IN_LEN(num) (12+4*(num))
-#define    MC_CMD_TABLE_UPDATE_IN_DATA_NUM(len) (((len)-12)/4)
-/* Table identifier. */
-#define       MC_CMD_TABLE_UPDATE_IN_TABLE_ID_OFST 0
-#define       MC_CMD_TABLE_UPDATE_IN_TABLE_ID_LEN 4
-/*            Enum values, see field(s): */
-/*               TABLE_ID */
-/* Width in bits of supplied key data (must match table properties). */
-#define       MC_CMD_TABLE_UPDATE_IN_KEY_WIDTH_OFST 4
-#define       MC_CMD_TABLE_UPDATE_IN_KEY_WIDTH_LEN 2
-/* Width in bits of supplied mask data (0 for direct/BCAM tables, or for STCAM
- * when allocated MASK_ID is used instead).
- */
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_WIDTH_OFST 6
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_WIDTH_LEN 2
-/* Width in bits of supplied response data (for INSERT and UPDATE operations
- * this must match the table properties; for DELETE operations, no response
- * data is required and this must be 0).
- */
-#define       MC_CMD_TABLE_UPDATE_IN_RESP_WIDTH_OFST 8
-#define       MC_CMD_TABLE_UPDATE_IN_RESP_WIDTH_LEN 2
-/* Mask ID for STCAM table - used instead of mask data if the table descriptor
- * reports ALLOC_MASKS==1. Otherwise set to 0.
- */
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_ID_OFST 6
-#define       MC_CMD_TABLE_UPDATE_IN_MASK_ID_LEN 2
-/* Priority for TCAM or STCAM, in range 0..N_PRIORITIES-1, otherwise 0. */
-#define       MC_CMD_TABLE_UPDATE_IN_PRIORITY_OFST 8
-#define       MC_CMD_TABLE_UPDATE_IN_PRIORITY_LEN 2
-/* (32-bit alignment padding - set to 0) */
-#define       MC_CMD_TABLE_UPDATE_IN_RESERVED_OFST 10
-#define       MC_CMD_TABLE_UPDATE_IN_RESERVED_LEN 2
-/* Sequence of key, mask (if MASK_WIDTH > 0), and response (if RESP_WIDTH > 0)
- * data values. Each of these items is logically treated as a single wide N-bit
- * value, in which the individual fields have been placed within that value per
- * the LBN and WIDTH information from the table field descriptors. The wide
- * N-bit value is padded with 0 bits at the MSB end if necessary to make a
- * multiple of 32 bits. The value is then packed into this command as a
- * sequence of 32-bit words, bits [31:0] first, then bits [63:32], etc.
- */
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_OFST 12
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_LEN 4
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MINNUM 1
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MAXNUM 60
-#define       MC_CMD_TABLE_UPDATE_IN_DATA_MAXNUM_MCDI2 252
-
-/* MC_CMD_TABLE_UPDATE_OUT msgresponse */
-#define    MC_CMD_TABLE_UPDATE_OUT_LEN 0
-
-
 /***********************************/
 /* MC_CMD_TABLE_DELETE
  * Delete an existing entry in a table. May return EINVAL for unknown table ID
@@ -29702,5 +25797,124 @@
 /* MC_CMD_TABLE_DELETE_OUT msgresponse */
 #define    MC_CMD_TABLE_DELETE_OUT_LEN 0
 
+/* MC_CMD_QUEUE_HANDLE structuredef: On X4, to distinguish between full-
+ * featured (X2-style) VIs and low-latency (X3-style) queues, we use the top
+ * bits of the queue handle to specify the queue type in all MCDI calls which
+ * refer to VIs/queues. These bits should be masked off when indexing into a
+ * queue in the BAR.
+ */
+#define    MC_CMD_QUEUE_HANDLE_LEN 4
+/* Combined queue number and type. This is the ID returned by and passed into
+ * MCDI calls that use queues.
+ */
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_OFST 0
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_LEN 4
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_OFST 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_LBN 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_NUM_WIDTH 24
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_OFST 0
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LBN 24
+#define        MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_WIDTH 8
+/* enum: Indicates that the queue instance is a full-featured VI */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_FF_VI 0x0
+/* enum: Indicates that the queue instance is a LL TXQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_TXQ 0x1
+/* enum: Indicates that the queue instance is a LL RXQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_RXQ 0x2
+/* enum: Indicates that the queue instance is a LL EVQ */
+#define          MC_CMD_QUEUE_HANDLE_QUEUE_TYPE_LL_EVQ 0x3
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_LBN 0
+#define       MC_CMD_QUEUE_HANDLE_QUEUE_HANDLE_WIDTH 32
+
+
+/***********************************/
+/* MC_CMD_ALLOC_LL_QUEUES
+ * Allocate low latency (X3-style) queues for current PCI function. Can be
+ * called more than once if desired to allocate more queues.
+ */
+#define MC_CMD_ALLOC_LL_QUEUES 0x1dd
+#undef MC_CMD_0x1dd_PRIVILEGE_CTG
+
+#define MC_CMD_0x1dd_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_ALLOC_LL_QUEUES_IN msgrequest */
+#define    MC_CMD_ALLOC_LL_QUEUES_IN_LEN 24
+/* The minimum number of TXQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_TXQ_COUNT_OFST 0
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_TXQ_COUNT_LEN 4
+/* The maximum number of TXQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_TXQ_COUNT_OFST 4
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_TXQ_COUNT_LEN 4
+/* The minimum number of RXQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_RXQ_COUNT_OFST 8
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_RXQ_COUNT_LEN 4
+/* The maximum number of RXQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_RXQ_COUNT_OFST 12
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_RXQ_COUNT_LEN 4
+/* The minimum number of EVQs that is acceptable */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_EVQ_COUNT_OFST 16
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MIN_EVQ_COUNT_LEN 4
+/* The maximum number of EVQs that would be useful */
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_EVQ_COUNT_OFST 20
+#define       MC_CMD_ALLOC_LL_QUEUES_IN_MAX_EVQ_COUNT_LEN 4
+
+/* MC_CMD_ALLOC_LL_QUEUES_OUT msgresponse */
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMIN 16
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMAX 252
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LENMAX_MCDI2 1020
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_LEN(num) (12+4*(num))
+#define    MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_NUM(len) (((len)-12)/4)
+/* The number of TXQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_TXQ_COUNT_OFST 0
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_TXQ_COUNT_LEN 4
+/* The number of RXQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_RXQ_COUNT_OFST 4
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_RXQ_COUNT_LEN 4
+/* The number of EVQs allocated in this request */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_EVQ_COUNT_OFST 8
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_EVQ_COUNT_LEN 4
+/* A list of allocated queues, returned as MC_CMD_QUEUE_HANDLEs, not
+ * necessarily contiguous. TXQs are first in the list, followed by RXQs then
+ * EVQs. The type of each queue is indicated by the top bits (see the
+ * QUEUE_TYPE enum)
+ */
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_OFST 12
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_LEN 4
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MINNUM 1
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MAXNUM 60
+#define       MC_CMD_ALLOC_LL_QUEUES_OUT_QUEUES_MAXNUM_MCDI2 252
+
+
+/***********************************/
+/* MC_CMD_FREE_LL_QUEUES
+ * Free low latency (X3-style) queues for current PCI function.
+ */
+#define MC_CMD_FREE_LL_QUEUES 0x1de
+#undef MC_CMD_0x1de_PRIVILEGE_CTG
+
+#define MC_CMD_0x1de_PRIVILEGE_CTG SRIOV_CTG_GENERAL
+
+/* MC_CMD_FREE_LL_QUEUES_IN msgrequest */
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMIN 8
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMAX 252
+#define    MC_CMD_FREE_LL_QUEUES_IN_LENMAX_MCDI2 1020
+#define    MC_CMD_FREE_LL_QUEUES_IN_LEN(num) (4+4*(num))
+#define    MC_CMD_FREE_LL_QUEUES_IN_QUEUES_NUM(len) (((len)-4)/4)
+/* The number of queues to free. */
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUE_COUNT_OFST 0
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUE_COUNT_LEN 4
+/* A list of queues to free, as a list of MC_CMD_QUEUE_HANDLEs. They must have
+ * all been previously allocated by MC_CMD_ALLOC_LL_QUEUES. The type of each
+ * queue should be indicated by the top bits.
+ */
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_OFST 4
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_LEN 4
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MINNUM 1
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MAXNUM 62
+#define       MC_CMD_FREE_LL_QUEUES_IN_QUEUES_MAXNUM_MCDI2 254
+
+/* MC_CMD_FREE_LL_QUEUES_OUT msgresponse */
+#define    MC_CMD_FREE_LL_QUEUES_OUT_LEN 0
+
 
 #endif /* MCDI_PCOL_H */

From 43c3d6b4890da2acbd3015b864dc3e1f94ddc0d8 Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree.xilinx@gmail.com>
Date: Thu, 20 Mar 2025 17:57:12 +0000
Subject: [PATCH 2697/2753] sfc: support X4 devlink flash

Unlike X2 and EF100, we do not attempt to parse the firmware file to
 find an image within it; we simply hand the entire file to the MC,
 which is responsible for understanding any container formats we might
 use and validating that the firmware file is applicable to this NIC.

Signed-off-by: Edward Cree <ecree.xilinx@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/sfc/ef10.c        |  1 +
 drivers/net/ethernet/sfc/efx_reflash.c | 52 +++++++++++++++-----------
 drivers/net/ethernet/sfc/net_driver.h  |  3 ++
 3 files changed, 34 insertions(+), 22 deletions(-)

diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c
index 47d78abecf30d..47349c148c0c0 100644
--- a/drivers/net/ethernet/sfc/ef10.c
+++ b/drivers/net/ethernet/sfc/ef10.c
@@ -4419,6 +4419,7 @@ const struct efx_nic_type efx_x4_nic_type = {
 	.can_rx_scatter = true,
 	.always_rx_scatter = true,
 	.option_descriptors = true,
+	.flash_auto_partition = true,
 	.min_interrupt_mode = EFX_INT_MODE_MSIX,
 	.timer_period_max = 1 << ERF_DD_EVQ_IND_TIMER_VAL_WIDTH,
 	.offload_features = EF10_OFFLOAD_FEATURES,
diff --git a/drivers/net/ethernet/sfc/efx_reflash.c b/drivers/net/ethernet/sfc/efx_reflash.c
index ddc53740f0986..b12e95f1c80a5 100644
--- a/drivers/net/ethernet/sfc/efx_reflash.c
+++ b/drivers/net/ethernet/sfc/efx_reflash.c
@@ -407,31 +407,40 @@ int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
 		return -EOPNOTSUPP;
 	}
 
-	devlink_flash_update_status_notify(devlink, "Checking update", NULL, 0, 0);
+	mutex_lock(&efx->reflash_mutex);
 
-	rc = efx_reflash_parse_firmware_data(fw, &type, &data_subtype, &data,
-					     &data_size);
-	if (rc) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Firmware image validation check failed");
-		goto out;
-	}
+	devlink_flash_update_status_notify(devlink, "Checking update", NULL, 0, 0);
 
-	mutex_lock(&efx->reflash_mutex);
+	if (efx->type->flash_auto_partition) {
+		/* NIC wants entire FW file including headers;
+		 * FW will validate 'subtype' if there is one
+		 */
+		type = NVRAM_PARTITION_TYPE_AUTO;
+		data = fw->data;
+		data_size = fw->size;
+	} else {
+		rc = efx_reflash_parse_firmware_data(fw, &type, &data_subtype, &data,
+						     &data_size);
+		if (rc) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Firmware image validation check failed");
+			goto out_unlock;
+		}
 
-	rc = efx_mcdi_nvram_metadata(efx, type, &subtype, NULL, NULL, 0);
-	if (rc) {
-		NL_SET_ERR_MSG_FMT_MOD(extack,
-				       "Metadata query for NVRAM partition %#x failed",
-				       type);
-		goto out_unlock;
-	}
+		rc = efx_mcdi_nvram_metadata(efx, type, &subtype, NULL, NULL, 0);
+		if (rc) {
+			NL_SET_ERR_MSG_FMT_MOD(extack,
+					       "Metadata query for NVRAM partition %#x failed",
+					       type);
+			goto out_unlock;
+		}
 
-	if (subtype != data_subtype) {
-		NL_SET_ERR_MSG_MOD(extack,
-				   "Firmware image is not appropriate for this adapter");
-		rc = -EINVAL;
-		goto out_unlock;
+		if (subtype != data_subtype) {
+			NL_SET_ERR_MSG_MOD(extack,
+					   "Firmware image is not appropriate for this adapter");
+			rc = -EINVAL;
+			goto out_unlock;
+		}
 	}
 
 	rc = efx_mcdi_nvram_info(efx, type, &size, &erase_align, &write_align,
@@ -506,7 +515,6 @@ int efx_reflash_flash_firmware(struct efx_nic *efx, const struct firmware *fw,
 		rc = efx_mcdi_nvram_update_finish_polled(efx, type);
 out_unlock:
 	mutex_unlock(&efx->reflash_mutex);
-out:
 	devlink_flash_update_status_notify(devlink, rc ? "Update failed" :
 							 "Update complete",
 					   NULL, 0, 0);
diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h
index 6912661b5a3dd..5c0f306fb019a 100644
--- a/drivers/net/ethernet/sfc/net_driver.h
+++ b/drivers/net/ethernet/sfc/net_driver.h
@@ -1381,6 +1381,8 @@ struct efx_udp_tunnel {
  * @can_rx_scatter: NIC is able to scatter packets to multiple buffers
  * @always_rx_scatter: NIC will always scatter packets to multiple buffers
  * @option_descriptors: NIC supports TX option descriptors
+ * @flash_auto_partition: firmware flash uses AUTO partition, driver does
+ *	not need to perform image parsing
  * @min_interrupt_mode: Lowest capability interrupt mode supported
  *	from &enum efx_int_mode.
  * @timer_period_max: Maximum period of interrupt timer (in ticks)
@@ -1557,6 +1559,7 @@ struct efx_nic_type {
 	bool can_rx_scatter;
 	bool always_rx_scatter;
 	bool option_descriptors;
+	bool flash_auto_partition;
 	unsigned int min_interrupt_mode;
 	unsigned int timer_period_max;
 	netdev_features_t offload_features;

From 5a4d5e79b747a478aab7a196828b5efd425fdcf4 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Thu, 20 Mar 2025 19:22:38 +0100
Subject: [PATCH 2698/2753] net: introduce per netns packet chains

Currently network taps unbound to any interface are linked in the
global ptype_all list, affecting the performance in all the network
namespaces.

Add per netns ptypes chains, so that in the mentioned case only
the netns owning the packet socket(s) is affected.

While at that drop the global ptype_all list: no in kernel user
registers a tap on "any" type without specifying either the target
device or the target namespace (and IMHO doing that would not make
any sense).

Note that this adds a conditional in the fast path (to check for
per netns ptype_specific list) and increases the dataset size by
a cacheline (owing the per netns lists).

Reviewed-by: Sabrina Dubroca <sd@queasysnail.net>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/linux/netdevice.h   | 12 ++++++++-
 include/net/hotdata.h       |  1 -
 include/net/net_namespace.h |  3 +++
 net/core/dev.c              | 53 ++++++++++++++++++++++++++++---------
 net/core/hotdata.c          |  1 -
 net/core/net-procfs.c       | 28 +++++++++++++++-----
 net/core/net_namespace.c    |  2 ++
 7 files changed, 78 insertions(+), 22 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b1d92e12a6ae1..1a11b7a1f05c4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4279,7 +4279,17 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 	return 0;
 }
 
-bool dev_nit_active(struct net_device *dev);
+bool dev_nit_active_rcu(const struct net_device *dev);
+static inline bool dev_nit_active(const struct net_device *dev)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = dev_nit_active_rcu(dev);
+	rcu_read_unlock();
+	return ret;
+}
+
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 
 static inline void __dev_put(struct net_device *dev)
diff --git a/include/net/hotdata.h b/include/net/hotdata.h
index 30e9570beb2af..fda94b2647ffa 100644
--- a/include/net/hotdata.h
+++ b/include/net/hotdata.h
@@ -23,7 +23,6 @@ struct net_hotdata {
 	struct net_offload	udpv6_offload;
 #endif
 	struct list_head	offload_base;
-	struct list_head	ptype_all;
 	struct kmem_cache	*skbuff_cache;
 	struct kmem_cache	*skbuff_fclone_cache;
 	struct kmem_cache	*skb_small_head_cache;
diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
index f467a66abc6b1..bd57d8fb54f14 100644
--- a/include/net/net_namespace.h
+++ b/include/net/net_namespace.h
@@ -83,6 +83,9 @@ struct net {
 	struct llist_node	defer_free_list;
 	struct llist_node	cleanup_list;	/* namespaces on death row */
 
+	struct list_head ptype_all;
+	struct list_head ptype_specific;
+
 #ifdef CONFIG_KEYS
 	struct key_tag		*key_domain;	/* Key domain of operation tag */
 #endif
diff --git a/net/core/dev.c b/net/core/dev.c
index 2355603417650..bcf81c3ff6a32 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -572,10 +572,18 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev)
 
 static inline struct list_head *ptype_head(const struct packet_type *pt)
 {
-	if (pt->type == htons(ETH_P_ALL))
-		return pt->dev ? &pt->dev->ptype_all : &net_hotdata.ptype_all;
-	else
-		return pt->dev ? &pt->dev->ptype_specific :
+	if (pt->type == htons(ETH_P_ALL)) {
+		if (!pt->af_packet_net && !pt->dev)
+			return NULL;
+
+		return pt->dev ? &pt->dev->ptype_all :
+				 &pt->af_packet_net->ptype_all;
+	}
+
+	if (pt->dev)
+		return &pt->dev->ptype_specific;
+
+	return pt->af_packet_net ? &pt->af_packet_net->ptype_specific :
 				 &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK];
 }
 
@@ -596,6 +604,9 @@ void dev_add_pack(struct packet_type *pt)
 {
 	struct list_head *head = ptype_head(pt);
 
+	if (WARN_ON_ONCE(!head))
+		return;
+
 	spin_lock(&ptype_lock);
 	list_add_rcu(&pt->list, head);
 	spin_unlock(&ptype_lock);
@@ -620,6 +631,9 @@ void __dev_remove_pack(struct packet_type *pt)
 	struct list_head *head = ptype_head(pt);
 	struct packet_type *pt1;
 
+	if (!head)
+		return;
+
 	spin_lock(&ptype_lock);
 
 	list_for_each_entry(pt1, head, list) {
@@ -2441,16 +2455,21 @@ static inline bool skb_loop_sk(struct packet_type *ptype, struct sk_buff *skb)
 }
 
 /**
- * dev_nit_active - return true if any network interface taps are in use
+ * dev_nit_active_rcu - return true if any network interface taps are in use
+ *
+ * The caller must hold the RCU lock
  *
  * @dev: network device to check for the presence of taps
  */
-bool dev_nit_active(struct net_device *dev)
+bool dev_nit_active_rcu(const struct net_device *dev)
 {
-	return !list_empty(&net_hotdata.ptype_all) ||
+	/* Callers may hold either RCU or RCU BH lock */
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+
+	return !list_empty(&dev_net(dev)->ptype_all) ||
 	       !list_empty(&dev->ptype_all);
 }
-EXPORT_SYMBOL_GPL(dev_nit_active);
+EXPORT_SYMBOL_GPL(dev_nit_active_rcu);
 
 /*
  *	Support routine. Sends outgoing frames to any network
@@ -2459,11 +2478,12 @@ EXPORT_SYMBOL_GPL(dev_nit_active);
 
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 {
-	struct list_head *ptype_list = &net_hotdata.ptype_all;
 	struct packet_type *ptype, *pt_prev = NULL;
+	struct list_head *ptype_list;
 	struct sk_buff *skb2 = NULL;
 
 	rcu_read_lock();
+	ptype_list = &dev_net_rcu(dev)->ptype_all;
 again:
 	list_for_each_entry_rcu(ptype, ptype_list, list) {
 		if (READ_ONCE(ptype->ignore_outgoing))
@@ -2507,7 +2527,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev)
 		pt_prev = ptype;
 	}
 
-	if (ptype_list == &net_hotdata.ptype_all) {
+	if (ptype_list != &dev->ptype_all) {
 		ptype_list = &dev->ptype_all;
 		goto again;
 	}
@@ -3752,7 +3772,7 @@ static int xmit_one(struct sk_buff *skb, struct net_device *dev,
 	unsigned int len;
 	int rc;
 
-	if (dev_nit_active(dev))
+	if (dev_nit_active_rcu(dev))
 		dev_queue_xmit_nit(skb, dev);
 
 	len = skb->len;
@@ -5696,7 +5716,8 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 	if (pfmemalloc)
 		goto skip_taps;
 
-	list_for_each_entry_rcu(ptype, &net_hotdata.ptype_all, list) {
+	list_for_each_entry_rcu(ptype, &dev_net_rcu(skb->dev)->ptype_all,
+				list) {
 		if (pt_prev)
 			ret = deliver_skb(skb, pt_prev, orig_dev);
 		pt_prev = ptype;
@@ -5808,6 +5829,14 @@ static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
 				       &ptype_base[ntohs(type) &
 						   PTYPE_HASH_MASK]);
+
+		/* orig_dev and skb->dev could belong to different netns;
+		 * Even in such case we need to traverse only the list
+		 * coming from skb->dev, as the ptype owner (packet socket)
+		 * will use dev_net(skb->dev) to do namespace filtering.
+		 */
+		deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
+				       &dev_net_rcu(skb->dev)->ptype_specific);
 	}
 
 	deliver_ptype_list_skb(skb, &pt_prev, orig_dev, type,
diff --git a/net/core/hotdata.c b/net/core/hotdata.c
index d0aaaaa556f22..0bc893d5f07b0 100644
--- a/net/core/hotdata.c
+++ b/net/core/hotdata.c
@@ -7,7 +7,6 @@
 
 struct net_hotdata net_hotdata __cacheline_aligned = {
 	.offload_base = LIST_HEAD_INIT(net_hotdata.offload_base),
-	.ptype_all = LIST_HEAD_INIT(net_hotdata.ptype_all),
 	.gro_normal_batch = 8,
 
 	.netdev_budget = 300,
diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c
index fa6d3969734a6..3e92bf0f9060b 100644
--- a/net/core/net-procfs.c
+++ b/net/core/net-procfs.c
@@ -185,7 +185,13 @@ static void *ptype_get_idx(struct seq_file *seq, loff_t pos)
 		}
 	}
 
-	list_for_each_entry_rcu(pt, &net_hotdata.ptype_all, list) {
+	list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_all, list) {
+		if (i == pos)
+			return pt;
+		++i;
+	}
+
+	list_for_each_entry_rcu(pt, &seq_file_net(seq)->ptype_specific, list) {
 		if (i == pos)
 			return pt;
 		++i;
@@ -210,6 +216,7 @@ static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
 
 static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 {
+	struct net *net = seq_file_net(seq);
 	struct net_device *dev;
 	struct packet_type *pt;
 	struct list_head *nxt;
@@ -232,15 +239,22 @@ static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 				goto found;
 			}
 		}
-
-		nxt = net_hotdata.ptype_all.next;
-		goto ptype_all;
+		nxt = net->ptype_all.next;
+		goto net_ptype_all;
 	}
 
-	if (pt->type == htons(ETH_P_ALL)) {
-ptype_all:
-		if (nxt != &net_hotdata.ptype_all)
+	if (pt->af_packet_net) {
+net_ptype_all:
+		if (nxt != &net->ptype_all && nxt != &net->ptype_specific)
 			goto found;
+
+		if (nxt == &net->ptype_all) {
+			/* continue with ->ptype_specific if it's not empty */
+			nxt = net->ptype_specific.next;
+			if (nxt != &net->ptype_specific)
+				goto found;
+		}
+
 		hash = 0;
 		nxt = ptype_base[0].next;
 	} else
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 4303f2a492624..b0dfdf791ece5 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -340,6 +340,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
 	lock_set_cmp_fn(&net->rtnl_mutex, rtnl_net_lock_cmp_fn, NULL);
 #endif
 
+	INIT_LIST_HEAD(&net->ptype_all);
+	INIT_LIST_HEAD(&net->ptype_specific);
 	preinit_net_sysctl(net);
 }
 

From 7cc29541d7ade03b2d8ebf571593007be1db4c1c Mon Sep 17 00:00:00 2001
From: Nick Child <nnac123@linux.ibm.com>
Date: Thu, 20 Mar 2025 16:29:51 -0500
Subject: [PATCH 2699/2753] ibmvnic: Use kernel helpers for hex dumps

Previously, when the driver was printing hex dumps, the buffer was cast
to an 8 byte long and printed using string formatters. If the buffer
size was not a multiple of 8 then a read buffer overflow was possible.

Therefore, create a new ibmvnic function that loops over a buffer and
calls hex_dump_to_buffer instead.

This patch address KASAN reports like the one below:
  ibmvnic 30000003 env3: Login Buffer:
  ibmvnic 30000003 env3: 01000000af000000
  <...>
  ibmvnic 30000003 env3: 2e6d62692e736261
  ibmvnic 30000003 env3: 65050003006d6f63
  ==================================================================
  BUG: KASAN: slab-out-of-bounds in ibmvnic_login+0xacc/0xffc [ibmvnic]
  Read of size 8 at addr c0000001331a9aa8 by task ip/17681
  <...>
  Allocated by task 17681:
  <...>
  ibmvnic_login+0x2f0/0xffc [ibmvnic]
  ibmvnic_open+0x148/0x308 [ibmvnic]
  __dev_open+0x1ac/0x304
  <...>
  The buggy address is located 168 bytes inside of
                allocated 175-byte region [c0000001331a9a00, c0000001331a9aaf)
  <...>
  =================================================================
  ibmvnic 30000003 env3: 000000000033766e

Fixes: 032c5e82847a ("Driver for IBM System i/p VNIC protocol")
Signed-off-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Dave Marquardt <davemarq@linux.ibm.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/ibm/ibmvnic.c | 30 ++++++++++++++++++------------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 0676fc547b6f4..480606d1245ea 100644
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -4829,6 +4829,18 @@ static void vnic_add_client_data(struct ibmvnic_adapter *adapter,
 	strscpy(vlcd->name, adapter->netdev->name, len);
 }
 
+static void ibmvnic_print_hex_dump(struct net_device *dev, void *buf,
+				   size_t len)
+{
+	unsigned char hex_str[16 * 3];
+
+	for (size_t i = 0; i < len; i += 16) {
+		hex_dump_to_buffer((unsigned char *)buf + i, len - i, 16, 8,
+				   hex_str, sizeof(hex_str), false);
+		netdev_dbg(dev, "%s\n", hex_str);
+	}
+}
+
 static int send_login(struct ibmvnic_adapter *adapter)
 {
 	struct ibmvnic_login_rsp_buffer *login_rsp_buffer;
@@ -4939,10 +4951,8 @@ static int send_login(struct ibmvnic_adapter *adapter)
 	vnic_add_client_data(adapter, vlcd);
 
 	netdev_dbg(adapter->netdev, "Login Buffer:\n");
-	for (i = 0; i < (adapter->login_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(adapter->netdev, adapter->login_buf,
+			       adapter->login_buf_sz);
 
 	memset(&crq, 0, sizeof(crq));
 	crq.login.first = IBMVNIC_CRQ_CMD;
@@ -5319,15 +5329,13 @@ static void handle_query_ip_offload_rsp(struct ibmvnic_adapter *adapter)
 {
 	struct device *dev = &adapter->vdev->dev;
 	struct ibmvnic_query_ip_offload_buffer *buf = &adapter->ip_offload_buf;
-	int i;
 
 	dma_unmap_single(dev, adapter->ip_offload_tok,
 			 sizeof(adapter->ip_offload_buf), DMA_FROM_DEVICE);
 
 	netdev_dbg(adapter->netdev, "Query IP Offload Buffer:\n");
-	for (i = 0; i < (sizeof(adapter->ip_offload_buf) - 1) / 8 + 1; i++)
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(buf))[i]);
+	ibmvnic_print_hex_dump(adapter->netdev, buf,
+			       sizeof(adapter->ip_offload_buf));
 
 	netdev_dbg(adapter->netdev, "ipv4_chksum = %d\n", buf->ipv4_chksum);
 	netdev_dbg(adapter->netdev, "ipv6_chksum = %d\n", buf->ipv6_chksum);
@@ -5558,10 +5566,8 @@ static int handle_login_rsp(union ibmvnic_crq *login_rsp_crq,
 	netdev->mtu = adapter->req_mtu - ETH_HLEN;
 
 	netdev_dbg(adapter->netdev, "Login Response Buffer:\n");
-	for (i = 0; i < (adapter->login_rsp_buf_sz - 1) / 8 + 1; i++) {
-		netdev_dbg(adapter->netdev, "%016lx\n",
-			   ((unsigned long *)(adapter->login_rsp_buf))[i]);
-	}
+	ibmvnic_print_hex_dump(netdev, adapter->login_rsp_buf,
+			       adapter->login_rsp_buf_sz);
 
 	/* Sanity checks */
 	if (login->num_txcomp_subcrqs != login_rsp->num_txsubm_subcrqs ||

From 6029004af863ff2b48a00b56be711319e0403d5e Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Mar 2025 22:11:07 +0000
Subject: [PATCH 2700/2753] net: phylink: add phylink_prepare_resume()

When the system is suspended, the PHY may be placed in low-power mode
by setting the BMCR 0.11 Power down bit. IEEE 802.3 states that the
behaviour of the PHY in this state is implementation specific, and
the PHY is not required to meet the RX_CLK and TX_CLK requirements.
Essentially, this means that a PHY may stop the clocks that it is
generating while in power down state.

However, MACs exist which require the clocks from the PHY to be running
in order to properly resume. phylink_prepare_resume() provides them
with a way to clear the Power down bit early.

Note, however, that IEEE 802.3 gives PHYs up to 500ms grace before the
transmit and receive clocks meet the requirements after clearing the
power down bit.

Add a resume preparation function, which will ensure that the receive
clock from the PHY is appropriately configured while resuming.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/phylink.c | 25 +++++++++++++++++++++++++
 include/linux/phylink.h   |  1 +
 2 files changed, 26 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 16a1f31f00911..82860cf153aec 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -2479,6 +2479,31 @@ void phylink_suspend(struct phylink *pl, bool mac_wol)
 }
 EXPORT_SYMBOL_GPL(phylink_suspend);
 
+/**
+ * phylink_prepare_resume() - prepare to resume a network device
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ *
+ * Optional, but if called must be called prior to phylink_resume().
+ *
+ * Prepare to resume a network device, preparing the PHY as necessary.
+ */
+void phylink_prepare_resume(struct phylink *pl)
+{
+	struct phy_device *phydev = pl->phydev;
+
+	ASSERT_RTNL();
+
+	/* IEEE 802.3 22.2.4.1.5 allows PHYs to stop their receive clock
+	 * when PDOWN is set. However, some MACs require RXC to be running
+	 * in order to resume. If the MAC requires RXC, and we have a PHY,
+	 * then resume the PHY. Note that 802.3 allows PHYs 500ms before
+	 * the clock meets requirements. We do not implement this delay.
+	 */
+	if (pl->config->mac_requires_rxc && phydev && phydev->suspended)
+		phy_resume(phydev);
+}
+EXPORT_SYMBOL_GPL(phylink_prepare_resume);
+
 /**
  * phylink_resume() - handle a network device resume event
  * @pl: a pointer to a &struct phylink returned from phylink_create()
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 79876c84ae814..06f1b649f1731 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -707,6 +707,7 @@ void phylink_start(struct phylink *);
 void phylink_stop(struct phylink *);
 
 void phylink_suspend(struct phylink *pl, bool mac_wol);
+void phylink_prepare_resume(struct phylink *pl);
 void phylink_resume(struct phylink *pl);
 
 void phylink_ethtool_get_wol(struct phylink *, struct ethtool_wolinfo *);

From 0513ef42f38048b820238b9d6b70ed26bfe21663 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Mar 2025 22:11:12 +0000
Subject: [PATCH 2701/2753] net: stmmac: address non-LPI resume failures
 properly

The Synopsys Designware GMAC core databook requires all clocks to be
active in order to complete software reset, which we perform during
resume.

However, IEEE 802.3 allows a PHY to stop its clocks when placed in
low-power mode, which happens when the system is suspended and WoL
is not enabled.

As an attempt to work around this, commit 36d18b5664ef ("net: stmmac:
start phylink instance before stmmac_hw_setup()") started phylink
early, but this has the side effect that the mac_link_up() method may
be called before or during the initialisation of GMAC hardware.

We also have the socfpga glue driver directly calling phy_resume()
also as an attempt to work around this.

In a previous commit, phylink_prepare_resume() has been introduced
to give MAC drivers a way to ensure that the PHY is resumed prior to
their initialisation of their MAC hardware. This commit adds the call,
and moves the phylink_resume() call back to where it should be before
the aforementioned commit.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index cd79e3257b3fc..ffb2ee4b48290 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -7933,12 +7933,12 @@ int stmmac_resume(struct device *dev)
 	}
 
 	rtnl_lock();
-	phylink_resume(priv->phylink);
-	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
-		phylink_speed_up(priv->phylink);
-	rtnl_unlock();
 
-	rtnl_lock();
+	/* Prepare the PHY to resume, ensuring that its clocks which are
+	 * necessary for the MAC DMA reset to complete are running
+	 */
+	phylink_prepare_resume(priv->phylink);
+
 	mutex_lock(&priv->lock);
 
 	stmmac_reset_queues_param(priv);
@@ -7956,6 +7956,15 @@ int stmmac_resume(struct device *dev)
 	stmmac_enable_all_dma_irq(priv);
 
 	mutex_unlock(&priv->lock);
+
+	/* phylink_resume() must be called after the hardware has been
+	 * initialised because it may bring the link up immediately in a
+	 * workqueue thread, which will race with initialisation.
+	 */
+	phylink_resume(priv->phylink);
+	if (device_may_wakeup(priv->device) && !priv->plat->pmt)
+		phylink_speed_up(priv->phylink);
+
 	rtnl_unlock();
 
 	netif_device_attach(ndev);

From b9ab325a842b195120d4779b4c367d2914b9dab4 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Mar 2025 22:11:17 +0000
Subject: [PATCH 2702/2753] net: stmmac: socfpga: remove phy_resume() call

As the previous commit addressed DWGMAC resuming with a PHY in
suspended state, there is now no need for socfpga to work around
this. Remove this code.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 .../ethernet/stmicro/stmmac/dwmac-socfpga.c    | 18 ------------------
 1 file changed, 18 deletions(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
index 6b78ae7304669..1168556585597 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
@@ -523,24 +523,6 @@ static int socfpga_dwmac_resume(struct device *dev)
 
 	dwmac_priv->ops->set_phy_mode(priv->plat->bsp_priv);
 
-	/* Before the enet controller is suspended, the phy is suspended.
-	 * This causes the phy clock to be gated. The enet controller is
-	 * resumed before the phy, so the clock is still gated "off" when
-	 * the enet controller is resumed. This code makes sure the phy
-	 * is "resumed" before reinitializing the enet controller since
-	 * the enet controller depends on an active phy clock to complete
-	 * a DMA reset. A DMA reset will "time out" if executed
-	 * with no phy clock input on the Synopsys enet controller.
-	 * Verified through Synopsys Case #8000711656.
-	 *
-	 * Note that the phy clock is also gated when the phy is isolated.
-	 * Phy "suspend" and "isolate" controls are located in phy basic
-	 * control register 0, and can be modified by the phy driver
-	 * framework.
-	 */
-	if (ndev->phydev)
-		phy_resume(ndev->phydev);
-
 	return stmmac_resume(dev);
 }
 #endif /* CONFIG_PM_SLEEP */

From ec26c6db625376ec3d6b3cdebb2e44fa7cb6a46d Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Mar 2025 22:11:22 +0000
Subject: [PATCH 2703/2753] net: phylink: add functions to block/unblock rx
 clock stop

Some MACs require the PHY receive clock to be running to complete setup
actions. This may fail if the PHY has negotiated EEE, the MAC supports
receive clock stop, and the link has entered LPI state. Provide a pair
of APIs that MAC drivers can use to temporarily block the PHY disabling
the receive clock.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/phy/phylink.c | 59 +++++++++++++++++++++++++++++++++++++++
 include/linux/phylink.h   |  3 ++
 2 files changed, 62 insertions(+)

diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 82860cf153aec..b870a450e2a0b 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -87,6 +87,7 @@ struct phylink {
 	bool mac_enable_tx_lpi;
 	bool mac_tx_clk_stop;
 	u32 mac_tx_lpi_timer;
+	u8 mac_rx_clk_stop_blocked;
 
 	struct sfp_bus *sfp_bus;
 	bool sfp_may_have_phy;
@@ -2435,6 +2436,64 @@ void phylink_stop(struct phylink *pl)
 }
 EXPORT_SYMBOL_GPL(phylink_stop);
 
+/**
+ * phylink_rx_clk_stop_block() - block PHY ability to stop receive clock in LPI
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ *
+ * Disable the PHY's ability to stop the receive clock while the receive path
+ * is in EEE LPI state, until the number of calls to phylink_rx_clk_stop_block()
+ * are balanced by calls to phylink_rx_clk_stop_unblock().
+ */
+void phylink_rx_clk_stop_block(struct phylink *pl)
+{
+	ASSERT_RTNL();
+
+	if (pl->mac_rx_clk_stop_blocked == U8_MAX) {
+		phylink_warn(pl, "%s called too many times - ignoring\n",
+			     __func__);
+		dump_stack();
+		return;
+	}
+
+	/* Disable PHY receive clock stop if this is the first time this
+	 * function has been called and clock-stop was previously enabled.
+	 */
+	if (pl->mac_rx_clk_stop_blocked++ == 0 &&
+	    pl->mac_supports_eee_ops && pl->phydev &&
+	    pl->config->eee_rx_clk_stop_enable)
+		phy_eee_rx_clock_stop(pl->phydev, false);
+}
+EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_block);
+
+/**
+ * phylink_rx_clk_stop_unblock() - unblock PHY ability to stop receive clock
+ * @pl: a pointer to a &struct phylink returned from phylink_create()
+ *
+ * All calls to phylink_rx_clk_stop_block() must be balanced with a
+ * corresponding call to phylink_rx_clk_stop_unblock() to restore the PHYs
+ * ability to stop the receive clock when the receive path is in EEE LPI mode.
+ */
+void phylink_rx_clk_stop_unblock(struct phylink *pl)
+{
+	ASSERT_RTNL();
+
+	if (pl->mac_rx_clk_stop_blocked == 0) {
+		phylink_warn(pl, "%s called too many times - ignoring\n",
+			     __func__);
+		dump_stack();
+		return;
+	}
+
+	/* Re-enable PHY receive clock stop if the number of unblocks matches
+	 * the number of calls to the block function above.
+	 */
+	if (--pl->mac_rx_clk_stop_blocked == 0 &&
+	    pl->mac_supports_eee_ops && pl->phydev &&
+	    pl->config->eee_rx_clk_stop_enable)
+		phy_eee_rx_clock_stop(pl->phydev, true);
+}
+EXPORT_SYMBOL_GPL(phylink_rx_clk_stop_unblock);
+
 /**
  * phylink_suspend() - handle a network device suspend event
  * @pl: a pointer to a &struct phylink returned from phylink_create()
diff --git a/include/linux/phylink.h b/include/linux/phylink.h
index 06f1b649f1731..1f5773ab56601 100644
--- a/include/linux/phylink.h
+++ b/include/linux/phylink.h
@@ -706,6 +706,9 @@ int phylink_pcs_pre_init(struct phylink *pl, struct phylink_pcs *pcs);
 void phylink_start(struct phylink *);
 void phylink_stop(struct phylink *);
 
+void phylink_rx_clk_stop_block(struct phylink *);
+void phylink_rx_clk_stop_unblock(struct phylink *);
+
 void phylink_suspend(struct phylink *pl, bool mac_wol);
 void phylink_prepare_resume(struct phylink *pl);
 void phylink_resume(struct phylink *pl);

From c9da718cbfac6540616c65851ac4be4bcabddd82 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 20 Mar 2025 22:11:27 +0000
Subject: [PATCH 2704/2753] net: stmmac: block PHY RXC clock-stop

The DesignWare core requires the receive clock to be running during
certain operations. Ensure that we block PHY RXC clock-stop during
these operations.

This is a best-efforts change - not everywhere can be covered by this
because of net's core locking, which means we can't access the MDIO
bus to configure the PHY to disable RXC clock-stop in certain areas.
These are marked with FIXME comments.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 .../net/ethernet/stmicro/stmmac/stmmac_main.c | 27 +++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
index ffb2ee4b48290..6c83ee2ad0743 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@ -3484,9 +3484,18 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	if (priv->hw->phylink_pcs)
 		phylink_pcs_pre_init(priv->phylink, priv->hw->phylink_pcs);
 
+	/* Note that clk_rx_i must be running for reset to complete. This
+	 * clock may also be required when setting the MAC address.
+	 *
+	 * Block the receive clock stop for LPI mode at the PHY in case
+	 * the link is established with EEE mode active.
+	 */
+	phylink_rx_clk_stop_block(priv->phylink);
+
 	/* DMA initialization and SW reset */
 	ret = stmmac_init_dma_engine(priv);
 	if (ret < 0) {
+		phylink_rx_clk_stop_unblock(priv->phylink);
 		netdev_err(priv->dev, "%s: DMA engine initialization failed\n",
 			   __func__);
 		return ret;
@@ -3494,6 +3503,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 
 	/* Copy the MAC addr into the HW  */
 	stmmac_set_umac_addr(priv, priv->hw, dev->dev_addr, 0);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	/* PS and related bits will be programmed according to the speed */
 	if (priv->hw->pcs) {
@@ -3604,7 +3614,9 @@ static int stmmac_hw_setup(struct net_device *dev, bool ptp_register)
 	/* Start the ball rolling... */
 	stmmac_start_all_dma(priv);
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	return 0;
 }
@@ -5885,6 +5897,9 @@ static void stmmac_tx_timeout(struct net_device *dev, unsigned int txqueue)
  *  whenever multicast addresses must be enabled/disabled.
  *  Return value:
  *  void.
+ *
+ *  FIXME: This may need RXC to be running, but it may be called with BH
+ *  disabled, which means we can't call phylink_rx_clk_stop*().
  */
 static void stmmac_set_rx_mode(struct net_device *dev)
 {
@@ -6017,7 +6032,9 @@ static int stmmac_set_features(struct net_device *netdev,
 	else
 		priv->hw->hw_vlan_en = false;
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_hw_vlan_mode(priv, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	return 0;
 }
@@ -6301,7 +6318,9 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr)
 	if (ret)
 		goto set_mac_error;
 
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 set_mac_error:
 	pm_runtime_put(priv->device);
@@ -6657,6 +6676,9 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
 	return stmmac_update_vlan_hash(priv, priv->hw, hash, pmatch, is_double);
 }
 
+/* FIXME: This may need RXC to be running, but it may be called with BH
+ * disabled, which means we can't call phylink_rx_clk_stop*().
+ */
 static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -6688,6 +6710,9 @@ static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid
 	return ret;
 }
 
+/* FIXME: This may need RXC to be running, but it may be called with BH
+ * disabled, which means we can't call phylink_rx_clk_stop*().
+ */
 static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid)
 {
 	struct stmmac_priv *priv = netdev_priv(ndev);
@@ -7948,9 +7973,11 @@ int stmmac_resume(struct device *dev)
 
 	stmmac_hw_setup(ndev, false);
 	stmmac_init_coalesce(priv);
+	phylink_rx_clk_stop_block(priv->phylink);
 	stmmac_set_rx_mode(ndev);
 
 	stmmac_restore_hw_vlan_rx_fltr(priv, ndev, priv->hw);
+	phylink_rx_clk_stop_unblock(priv->phylink);
 
 	stmmac_enable_all_queues(priv);
 	stmmac_enable_all_dma_irq(priv);

From 1cb74fc15d5746c5ec589e15393c78e85a7dad69 Mon Sep 17 00:00:00 2001
From: Ilya Maximets <i.maximets@ovn.org>
Date: Thu, 20 Mar 2025 23:42:07 +0100
Subject: [PATCH 2705/2753] net: openvswitch: fix kernel-doc warnings in
 internal headers

Some field descriptions were missing, some were not very accurate.
Not touching the uAPI header or .c files for now.

Formatting of those comments isn't great in general, but at least
they are not missing anything now.

Before:
  $ ./scripts/kernel-doc -none -Wall net/openvswitch/*.h 2>&1 | wc -l
  16

After:
  $ ./scripts/kernel-doc -none -Wall net/openvswitch/*.h 2>&1 | wc -l
  0

Signed-off-by: Ilya Maximets <i.maximets@ovn.org>
Acked-by: Eelco Chaudron <echaudro@redhat.com>
Reviewed-by: Aaron Conole <aconole@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/openvswitch/datapath.h | 20 ++++++++++++++------
 net/openvswitch/vport.h    |  9 +++++++++
 2 files changed, 23 insertions(+), 6 deletions(-)

diff --git a/net/openvswitch/datapath.h b/net/openvswitch/datapath.h
index 9ca6231ea6470..384ca77f4e794 100644
--- a/net/openvswitch/datapath.h
+++ b/net/openvswitch/datapath.h
@@ -29,8 +29,8 @@
  * datapath.
  * @n_hit: Number of received packets for which a matching flow was found in
  * the flow table.
- * @n_miss: Number of received packets that had no matching flow in the flow
- * table.  The sum of @n_hit and @n_miss is the number of packets that have
+ * @n_missed: Number of received packets that had no matching flow in the flow
+ * table.  The sum of @n_hit and @n_missed is the number of packets that have
  * been received by the datapath.
  * @n_lost: Number of received packets that had no matching flow in the flow
  * table that could not be sent to userspace (normally due to an overflow in
@@ -40,6 +40,7 @@
  *   up per packet.
  * @n_cache_hit: The number of received packets that had their mask found using
  * the mask cache.
+ * @syncp: Synchronization point for 64bit counters.
  */
 struct dp_stats_percpu {
 	u64 n_hit;
@@ -74,8 +75,10 @@ struct dp_nlsk_pids {
  * ovs_mutex and RCU.
  * @stats_percpu: Per-CPU datapath statistics.
  * @net: Reference to net namespace.
- * @max_headroom: the maximum headroom of all vports in this datapath; it will
+ * @user_features: Bitmap of enabled %OVS_DP_F_* features.
+ * @max_headroom: The maximum headroom of all vports in this datapath; it will
  * be used by all the internal vports in this dp.
+ * @meter_tbl: Meter table.
  * @upcall_portids: RCU protected 'struct dp_nlsk_pids'.
  *
  * Context: See the comment on locking at the top of datapath.c for additional
@@ -128,10 +131,13 @@ struct ovs_skb_cb {
 #define OVS_CB(skb) ((struct ovs_skb_cb *)(skb)->cb)
 
 /**
- * struct dp_upcall - metadata to include with a packet to send to userspace
+ * struct dp_upcall_info - metadata to include with a packet sent to userspace
  * @cmd: One of %OVS_PACKET_CMD_*.
  * @userdata: If nonnull, its variable-length value is passed to userspace as
  * %OVS_PACKET_ATTR_USERDATA.
+ * @actions: If nonnull, its variable-length value is passed to userspace as
+ * %OVS_PACKET_ATTR_ACTIONS.
+ * @actions_len: The length of the @actions.
  * @portid: Netlink portid to which packet should be sent.  If @portid is 0
  * then no packet is sent and the packet is accounted in the datapath's @n_lost
  * counter.
@@ -152,6 +158,10 @@ struct dp_upcall_info {
  * struct ovs_net - Per net-namespace data for ovs.
  * @dps: List of datapaths to enable dumping them all out.
  * Protected by genl_mutex.
+ * @dp_notify_work: A work notifier to handle port unregistering.
+ * @masks_rebalance: A work to periodically optimize flow table caches.
+ * @ct_limit_info: A hash table of conntrack zone connection limits.
+ * @xt_label: Whether connlables are configured for the network or not.
  */
 struct ovs_net {
 	struct list_head dps;
@@ -160,8 +170,6 @@ struct ovs_net {
 #if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
 	struct ovs_ct_limit_info *ct_limit_info;
 #endif
-
-	/* Module reference for configuring conntrack. */
 	bool xt_label;
 };
 
diff --git a/net/openvswitch/vport.h b/net/openvswitch/vport.h
index 3e71ca8ad8a78..9f67b9dd49f98 100644
--- a/net/openvswitch/vport.h
+++ b/net/openvswitch/vport.h
@@ -97,6 +97,8 @@ struct vport {
  * @desired_ifindex: New vport's ifindex.
  * @dp: New vport's datapath.
  * @port_no: New vport's port number.
+ * @upcall_portids: %OVS_VPORT_ATTR_UPCALL_PID attribute from Netlink message,
+ * %NULL if none was supplied.
  */
 struct vport_parms {
 	const char *name;
@@ -125,6 +127,8 @@ struct vport_parms {
  * have any configuration.
  * @send: Send a packet on the device.
  * zero for dropped packets or negative for error.
+ * @owner: Module that implements this vport type.
+ * @list: List entry in the global list of vport types.
  */
 struct vport_ops {
 	enum ovs_vport_type type;
@@ -144,6 +148,7 @@ struct vport_ops {
 /**
  * struct vport_upcall_stats_percpu - per-cpu packet upcall statistics for
  * a given vport.
+ * @syncp:     Synchronization point for 64bit counters.
  * @n_success: Number of packets that upcall to userspace succeed.
  * @n_fail:    Number of packets that upcall to userspace failed.
  */
@@ -164,6 +169,8 @@ void ovs_vport_free(struct vport *);
  *
  * @vport: vport to access
  *
+ * Returns: A void pointer to a private data allocated in the @vport.
+ *
  * If a nonzero size was passed in priv_size of vport_alloc() a private data
  * area was allocated on creation.  This allows that area to be accessed and
  * used for any purpose needed by the vport implementer.
@@ -178,6 +185,8 @@ static inline void *vport_priv(const struct vport *vport)
  *
  * @priv: Start of private data area.
  *
+ * Returns: A reference to a vport structure that contains @priv.
+ *
  * It is sometimes useful to translate from a pointer to the private data
  * area to the vport, such as in the case where the private data pointer is
  * the result of a hash table lookup.  @priv must point to the start of the

From 2fd367bdbb70968e1ccfe85a7095dc4c84b7c227 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:28 -0700
Subject: [PATCH 2706/2753] sch_htb: make htb_qlen_notify() idempotent

htb_qlen_notify() always deactivates the HTB class and in fact could
trigger a warning if it is already deactivated. Therefore, it is not
idempotent and not friendly to its callers, like fq_codel_dequeue().

Let's make it idempotent to ease qdisc_tree_reduce_backlog() callers'
life.

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_htb.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index c31bc5489bddc..4b9a639b642e1 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1485,6 +1485,8 @@ static void htb_qlen_notify(struct Qdisc *sch, unsigned long arg)
 {
 	struct htb_class *cl = (struct htb_class *)arg;
 
+	if (!cl->prio_activity)
+		return;
 	htb_deactivate(qdisc_priv(sch), cl);
 }
 

From b3f5137ed47c56dacbb57e7ffb57e49fd5c09882 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:29 -0700
Subject: [PATCH 2707/2753] sch_drr: make drr_qlen_notify() idempotent

drr_qlen_notify() always deletes the DRR class from its active list
with list_del(), therefore, it is not idempotent and not friendly
to its callers, like fq_codel_dequeue().

Let's make it idempotent to ease qdisc_tree_reduce_backlog() callers'
life. Also change other list_del()'s to list_del_init() just to be
extra safe.

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_drr.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index c69b999fae171..e0a81d313aa76 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -105,6 +105,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -ENOBUFS;
 
 	gnet_stats_basic_sync_init(&cl->bstats);
+	INIT_LIST_HEAD(&cl->alist);
 	cl->common.classid = classid;
 	cl->quantum	   = quantum;
 	cl->qdisc	   = qdisc_create_dflt(sch->dev_queue,
@@ -229,7 +230,7 @@ static void drr_qlen_notify(struct Qdisc *csh, unsigned long arg)
 {
 	struct drr_class *cl = (struct drr_class *)arg;
 
-	list_del(&cl->alist);
+	list_del_init(&cl->alist);
 }
 
 static int drr_dump_class(struct Qdisc *sch, unsigned long arg,
@@ -390,7 +391,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)
 			if (unlikely(skb == NULL))
 				goto out;
 			if (cl->qdisc->q.qlen == 0)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 
 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
@@ -431,7 +432,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
 	for (i = 0; i < q->clhash.hashsize; i++) {
 		hlist_for_each_entry(cl, &q->clhash.hash[i], common.hnode) {
 			if (cl->qdisc->q.qlen)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 			qdisc_reset(cl->qdisc);
 		}
 	}

From 7a60222455bdf90a2441532ac204e292013167b7 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:30 -0700
Subject: [PATCH 2708/2753] sch_hfsc: make hfsc_qlen_notify() idempotent

hfsc_qlen_notify() is not idempotent either and not friendly
to its callers, like fq_codel_dequeue(). Let's make it idempotent
to ease qdisc_tree_reduce_backlog() callers' life:

1. update_vf() decreases cl->cl_nactive, so we can check whether it is
non-zero before calling it.

2. eltree_remove() always removes RB node cl->el_node, but we can use
   RB_EMPTY_NODE() + RB_CLEAR_NODE() to make it safe.

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_hfsc.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index c287bf8423b47..ce5045eea0656 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -203,7 +203,10 @@ eltree_insert(struct hfsc_class *cl)
 static inline void
 eltree_remove(struct hfsc_class *cl)
 {
-	rb_erase(&cl->el_node, &cl->sched->eligible);
+	if (!RB_EMPTY_NODE(&cl->el_node)) {
+		rb_erase(&cl->el_node, &cl->sched->eligible);
+		RB_CLEAR_NODE(&cl->el_node);
+	}
 }
 
 static inline void
@@ -1220,7 +1223,8 @@ hfsc_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	/* vttree is now handled in update_vf() so that update_vf(cl, 0, 0)
 	 * needs to be called explicitly to remove a class from vttree.
 	 */
-	update_vf(cl, 0, 0);
+	if (cl->cl_nactive)
+		update_vf(cl, 0, 0);
 	if (cl->cl_flags & HFSC_RSC)
 		eltree_remove(cl);
 }

From e07638413022d343b3695a4dd03718d09922d470 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:31 -0700
Subject: [PATCH 2709/2753] sch_qfq: make qfq_qlen_notify() idempotent

qfq_qlen_notify() always deletes its class from its active list
with list_del_init() _and_ calls qfq_deactivate_agg() when the whole list
becomes empty.

To make it idempotent, just skip everything when it is not in the active
list.

Also change other list_del()'s to list_del_init() just to be extra safe.

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_qfq.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 2cfbc977fe6d0..687a932eb9b2f 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -347,7 +347,7 @@ static void qfq_deactivate_class(struct qfq_sched *q, struct qfq_class *cl)
 	struct qfq_aggregate *agg = cl->agg;
 
 
-	list_del(&cl->alist); /* remove from RR queue of the aggregate */
+	list_del_init(&cl->alist); /* remove from RR queue of the aggregate */
 	if (list_empty(&agg->active)) /* agg is now inactive */
 		qfq_deactivate_agg(q, agg);
 }
@@ -474,6 +474,7 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 	gnet_stats_basic_sync_init(&cl->bstats);
 	cl->common.classid = classid;
 	cl->deficit = lmax;
+	INIT_LIST_HEAD(&cl->alist);
 
 	cl->qdisc = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops,
 				      classid, NULL);
@@ -982,7 +983,7 @@ static struct sk_buff *agg_dequeue(struct qfq_aggregate *agg,
 	cl->deficit -= (int) len;
 
 	if (cl->qdisc->q.qlen == 0) /* no more packets, remove from list */
-		list_del(&cl->alist);
+		list_del_init(&cl->alist);
 	else if (cl->deficit < qdisc_pkt_len(cl->qdisc->ops->peek(cl->qdisc))) {
 		cl->deficit += agg->lmax;
 		list_move_tail(&cl->alist, &agg->active);
@@ -1415,6 +1416,8 @@ static void qfq_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	struct qfq_sched *q = qdisc_priv(sch);
 	struct qfq_class *cl = (struct qfq_class *)arg;
 
+	if (list_empty(&cl->alist))
+		return;
 	qfq_deactivate_class(q, cl);
 }
 

From 417ff45d5a8a54d9d35777dcb410f68510f719a8 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:32 -0700
Subject: [PATCH 2710/2753] sch_ets: make est_qlen_notify() idempotent

est_qlen_notify() deletes its class from its active list with
list_del() when qlen is 0, therefore, it is not idempotent and
not friendly to its callers, like fq_codel_dequeue().

Let's make it idempotent to ease qdisc_tree_reduce_backlog() callers'
life. Also change other list_del()'s to list_del_init() just to be
extra safe.

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_ets.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/sch_ets.c b/net/sched/sch_ets.c
index 516038a441638..c3bdeb14185be 100644
--- a/net/sched/sch_ets.c
+++ b/net/sched/sch_ets.c
@@ -293,7 +293,7 @@ static void ets_class_qlen_notify(struct Qdisc *sch, unsigned long arg)
 	 * to remove them.
 	 */
 	if (!ets_class_is_strict(q, cl) && sch->q.qlen)
-		list_del(&cl->alist);
+		list_del_init(&cl->alist);
 }
 
 static int ets_class_dump(struct Qdisc *sch, unsigned long arg,
@@ -488,7 +488,7 @@ static struct sk_buff *ets_qdisc_dequeue(struct Qdisc *sch)
 			if (unlikely(!skb))
 				goto out;
 			if (cl->qdisc->q.qlen == 0)
-				list_del(&cl->alist);
+				list_del_init(&cl->alist);
 			return ets_qdisc_dequeue_skb(sch, skb);
 		}
 
@@ -657,7 +657,7 @@ static int ets_qdisc_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 	for (i = q->nbands; i < oldbands; i++) {
 		if (i >= q->nstrict && q->classes[i].qdisc->q.qlen)
-			list_del(&q->classes[i].alist);
+			list_del_init(&q->classes[i].alist);
 		qdisc_tree_flush_backlog(q->classes[i].qdisc);
 	}
 	WRITE_ONCE(q->nstrict, nstrict);
@@ -713,7 +713,7 @@ static void ets_qdisc_reset(struct Qdisc *sch)
 
 	for (band = q->nstrict; band < q->nbands; band++) {
 		if (q->classes[band].qdisc->q.qlen)
-			list_del(&q->classes[band].alist);
+			list_del_init(&q->classes[band].alist);
 	}
 	for (band = 0; band < q->nbands; band++)
 		qdisc_reset(q->classes[band].qdisc);

From 88cc26497f188f45edfa532806209261a5c14f06 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:33 -0700
Subject: [PATCH 2711/2753] codel: remove sch->q.qlen check before
 qdisc_tree_reduce_backlog()

After making all ->qlen_notify() callbacks idempotent, now it is safe to
remove the check of qlen!=0 from both fq_codel_dequeue() and
codel_qdisc_dequeue().

Reported-by: Gerrard Tai <gerrard.tai@starlabs.sg>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/sched/sch_codel.c    | 5 +----
 net/sched/sch_fq_codel.c | 6 ++----
 2 files changed, 3 insertions(+), 8 deletions(-)

diff --git a/net/sched/sch_codel.c b/net/sched/sch_codel.c
index 81189d02fee76..12dd71139da39 100644
--- a/net/sched/sch_codel.c
+++ b/net/sched/sch_codel.c
@@ -65,10 +65,7 @@ static struct sk_buff *codel_qdisc_dequeue(struct Qdisc *sch)
 			    &q->stats, qdisc_pkt_len, codel_get_enqueue_time,
 			    drop_func, dequeue_func);
 
-	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
-	 * or HTB crashes. Defer it for next round.
-	 */
-	if (q->stats.drop_count && sch->q.qlen) {
+	if (q->stats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->stats.drop_count, q->stats.drop_len);
 		q->stats.drop_count = 0;
 		q->stats.drop_len = 0;
diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c
index 799f5397ad4c1..6c9029f71e88d 100644
--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -315,10 +315,8 @@ static struct sk_buff *fq_codel_dequeue(struct Qdisc *sch)
 	}
 	qdisc_bstats_update(sch, skb);
 	flow->deficit -= qdisc_pkt_len(skb);
-	/* We cant call qdisc_tree_reduce_backlog() if our qlen is 0,
-	 * or HTB crashes. Defer it for next round.
-	 */
-	if (q->cstats.drop_count && sch->q.qlen) {
+
+	if (q->cstats.drop_count) {
 		qdisc_tree_reduce_backlog(sch, q->cstats.drop_count,
 					  q->cstats.drop_len);
 		q->cstats.drop_count = 0;

From 1d3523ef9bf06e2a8d8601f989ec0f96a926bd06 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:34 -0700
Subject: [PATCH 2712/2753] selftests/tc-testing: Add a test case for FQ_CODEL
 with HTB parent

Add a test case for FQ_CODEL with HTB parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 33 ++++++++++++++++++-
 1 file changed, 32 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 9044ac0541672..06cb2c3c577ee 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -126,5 +126,36 @@
             "$TC qdisc del dev $DUMMY root handle 1: drr",
             "$IP addr del 10.10.10.10/24 dev $DUMMY"
         ]
-   }
+   },
+    {
+        "id": "a4bb",
+        "name": "Test FQ_CODEL with HTB parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "fq_codel",
+            "htb"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root htb default 10",
+            "$TC class add dev $DUMMY parent 1: classid 1:10 htb rate 1kbit",
+            "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+            "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.1"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
+    }
 ]

From 9fa7142bba767d2f09569af0326921a0f34115cc Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:35 -0700
Subject: [PATCH 2713/2753] selftests/tc-testing: Add a test case for CODEL
 with HTB parent

Add a test case for CODEL with HTB parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 06cb2c3c577ee..3ee3197ec7d93 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -157,5 +157,36 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4bd",
+        "name": "Test CODEL with HTB parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "codel",
+            "htb"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root htb default 10",
+            "$TC class add dev $DUMMY parent 1: classid 1:10 htb rate 1kbit ceil 1kbit burst 1 prio 1",
+            "$TC qdisc add dev $DUMMY parent 1:10 handle 10: codel limit 1 target 0.01ms interval 1ms noecn",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+            "ping -c 2 -i 0 -s 1400 -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.5"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

From 0b67bc267b3f7f807b43eda1f4ba4cbd8c920e42 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:36 -0700
Subject: [PATCH 2714/2753] selftests/tc-testing: Add a test case for FQ_CODEL
 with QFQ parent

Add a test case for FQ_CODEL with QFQ parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 3ee3197ec7d93..d69d2fde1c1cc 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -188,5 +188,36 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4be",
+        "name": "Test FQ_CODEL with QFQ parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "fq_codel",
+            "qfq"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root qfq",
+            "$TC class add dev $DUMMY parent 1: classid 1:10 qfq weight 1 maxpkt 1000",
+            "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+            "ping -c 10 -s 1000 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.1"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

From c41c78b2fa80b6503e98e68b518f0c2c820f6b16 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:37 -0700
Subject: [PATCH 2715/2753] selftests/tc-testing: Add a test case for FQ_CODEL
 with HFSC parent

Add a test case for FQ_CODEL with HFSC parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index d69d2fde1c1cc..4fda4007e520e 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -219,5 +219,36 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4bf",
+        "name": "Test FQ_CODEL with HFSC parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "fq_codel",
+            "hfsc"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root hfsc default 10",
+            "$TC class add dev $DUMMY parent 1: classid 1:10 hfsc sc rate 1kbit ul rate 1kbit",
+            "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+            "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.1"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

From bc4b189219474f0783e0e4b883f6484dd620ffbe Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:38 -0700
Subject: [PATCH 2716/2753] selftests/tc-testing: Add a test case for FQ_CODEL
 with DRR parent

Add a test case for FQ_CODEL with DRR parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index 4fda4007e520e..a6d6ca2459098 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -250,5 +250,36 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4c0",
+        "name": "Test FQ_CODEL with DRR parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "fq_codel",
+            "drr"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root drr",
+            "$TC class add dev $DUMMY parent 1: classid 1:10 drr quantum 1500",
+            "$TC qdisc add dev $DUMMY parent 1:10 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:10",
+            "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.1"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

From f29bf788a3221631f2148b2e65014323b7848aa1 Mon Sep 17 00:00:00 2001
From: Cong Wang <xiyou.wangcong@gmail.com>
Date: Thu, 20 Mar 2025 16:25:39 -0700
Subject: [PATCH 2717/2753] selftests/tc-testing: Add a test case for FQ_CODEL
 with ETS parent

Add a test case for FQ_CODEL with ETS parent to verify packet drop
behavior when the queue becomes empty. This helps ensure proper
notification mechanisms between qdiscs.

Note this is best-effort, it is hard to play with those parameters
perfectly to always trigger ->qlen_notify().

Cc: Pedro Tammela <pctammela@mojatatu.com>
Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 .../tc-testing/tc-tests/infra/qdiscs.json     | 31 +++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
index a6d6ca2459098..3e38f81f830cc 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/infra/qdiscs.json
@@ -281,5 +281,36 @@
             "$TC qdisc del dev $DUMMY handle 1: root",
             "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
         ]
+    },
+    {
+        "id": "a4c1",
+        "name": "Test FQ_CODEL with ETS parent - force packet drop with empty queue",
+        "category": [
+            "qdisc",
+            "fq_codel",
+            "ets"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1: root ets bands 2 strict 1",
+            "$TC class change dev $DUMMY parent 1: classid 1:1 ets",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 10: fq_codel memory_limit 1 flows 1 target 0.1ms interval 1ms",
+            "$TC filter add dev $DUMMY parent 1: protocol ip prio 1 u32 match ip protocol 1 0xff flowid 1:1",
+            "ping -c 5 -f -I $DUMMY 10.10.10.1 > /dev/null || true",
+            "sleep 0.1"
+        ],
+        "cmdUnderTest": "$TC -s qdisc show dev $DUMMY",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY | grep -A 5 'qdisc fq_codel'",
+        "matchPattern": "dropped [1-9][0-9]*",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1: root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
     }
 ]

From 563167a558d560c4e2a1dad0b4c3fa151819e71e Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:05 +0000
Subject: [PATCH 2718/2753] gve: remove xdp_xsk_done and xdp_xsk_wakeup
 statistics

These statistics pollute the hotpath and do not have any real-world use
or meaning.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve.h         | 2 --
 drivers/net/ethernet/google/gve/gve_ethtool.c | 8 +++-----
 drivers/net/ethernet/google/gve/gve_tx.c      | 8 ++------
 3 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 483c43bab3a99..2064e592dfdd3 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -613,8 +613,6 @@ struct gve_tx_ring {
 	dma_addr_t complq_bus_dqo; /* dma address of the dqo.compl_ring */
 	struct u64_stats_sync statss; /* sync stats for 32bit archs */
 	struct xsk_buff_pool *xsk_pool;
-	u32 xdp_xsk_wakeup;
-	u32 xdp_xsk_done;
 	u64 xdp_xsk_sent;
 	u64 xdp_xmit;
 	u64 xdp_xmit_errors;
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index a572f1e059342..bc59b5b4235a0 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -63,8 +63,8 @@ static const char gve_gstrings_rx_stats[][ETH_GSTRING_LEN] = {
 static const char gve_gstrings_tx_stats[][ETH_GSTRING_LEN] = {
 	"tx_posted_desc[%u]", "tx_completed_desc[%u]", "tx_consumed_desc[%u]", "tx_bytes[%u]",
 	"tx_wake[%u]", "tx_stop[%u]", "tx_event_counter[%u]",
-	"tx_dma_mapping_error[%u]", "tx_xsk_wakeup[%u]",
-	"tx_xsk_done[%u]", "tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
+	"tx_dma_mapping_error[%u]",
+	"tx_xsk_sent[%u]", "tx_xdp_xmit[%u]", "tx_xdp_xmit_errors[%u]"
 };
 
 static const char gve_gstrings_adminq_stats[][ETH_GSTRING_LEN] = {
@@ -417,9 +417,7 @@ gve_get_ethtool_stats(struct net_device *netdev,
 					data[i++] = value;
 				}
 			}
-			/* XDP xsk counters */
-			data[i++] = tx->xdp_xsk_wakeup;
-			data[i++] = tx->xdp_xsk_done;
+			/* XDP counters */
 			do {
 				start = u64_stats_fetch_begin(&priv->tx[ring].statss);
 				data[i] = tx->xdp_xsk_sent;
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index 4350ebd9c2bd9..c8c067e180598 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -959,14 +959,10 @@ static int gve_xsk_tx(struct gve_priv *priv, struct gve_tx_ring *tx,
 
 	spin_lock(&tx->xdp_lock);
 	while (sent < budget) {
-		if (!gve_can_tx(tx, GVE_TX_START_THRESH))
+		if (!gve_can_tx(tx, GVE_TX_START_THRESH) ||
+		    !xsk_tx_peek_desc(tx->xsk_pool, &desc))
 			goto out;
 
-		if (!xsk_tx_peek_desc(tx->xsk_pool, &desc)) {
-			tx->xdp_xsk_done = tx->xdp_xsk_wakeup;
-			goto out;
-		}
-
 		data = xsk_buff_raw_get_data(tx->xsk_pool, desc.addr);
 		nsegs = gve_tx_fill_xdp(priv, tx, data, desc.len, NULL, true);
 		tx->req += nsegs;

From cfc714017968271817f16faca594b3d3391a28d3 Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:06 +0000
Subject: [PATCH 2719/2753] gve: introduce config-based allocation for XDP

An earlier patch series[1] introduced RX/TX ring allocation configuration
structs which contained metadata used to allocate and configure new RX
and TX rings. This led to a much cleaner and safer allocation pattern
wherein queue resources were not deallocated until new queue resources
were successfully allocated.

Migrate the XDP allocation path to use the same pattern to allow for the
existence of a single allocation path instead of relying on XDP-specific
allocation methods. These extra allocation methods result in the
duplication of many existing behaviors while being prone to error when
configuration changes unrelated to XDP occur.

Link: https://lore.kernel.org/netdev/20240122182632.1102721-1-shailend@google.com/ [1]
Reviewed-by: Praveen Kaligineedi <pkaligineedi@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve.h         |  56 ++--
 drivers/net/ethernet/google/gve/gve_ethtool.c |  19 +-
 drivers/net/ethernet/google/gve/gve_main.c    | 261 ++++--------------
 drivers/net/ethernet/google/gve/gve_rx.c      |   6 +-
 drivers/net/ethernet/google/gve/gve_rx_dqo.c  |   6 +-
 drivers/net/ethernet/google/gve/gve_tx.c      |  33 +--
 drivers/net/ethernet/google/gve/gve_tx_dqo.c  |  31 +--
 7 files changed, 118 insertions(+), 294 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 2064e592dfdd3..e5cc3fada9c92 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -631,10 +631,17 @@ struct gve_notify_block {
 	u32 irq;
 };
 
-/* Tracks allowed and current queue settings */
-struct gve_queue_config {
+/* Tracks allowed and current rx queue settings */
+struct gve_rx_queue_config {
 	u16 max_queues;
-	u16 num_queues; /* current */
+	u16 num_queues;
+};
+
+/* Tracks allowed and current tx queue settings */
+struct gve_tx_queue_config {
+	u16 max_queues;
+	u16 num_queues; /* number of TX queues, excluding XDP queues */
+	u16 num_xdp_queues;
 };
 
 /* Tracks the available and used qpl IDs */
@@ -658,11 +665,11 @@ struct gve_ptype_lut {
 
 /* Parameters for allocating resources for tx queues */
 struct gve_tx_alloc_rings_cfg {
-	struct gve_queue_config *qcfg;
+	struct gve_tx_queue_config *qcfg;
+
+	u16 num_xdp_rings;
 
 	u16 ring_size;
-	u16 start_idx;
-	u16 num_rings;
 	bool raw_addressing;
 
 	/* Allocated resources are returned here */
@@ -672,8 +679,8 @@ struct gve_tx_alloc_rings_cfg {
 /* Parameters for allocating resources for rx queues */
 struct gve_rx_alloc_rings_cfg {
 	/* tx config is also needed to determine QPL ids */
-	struct gve_queue_config *qcfg;
-	struct gve_queue_config *qcfg_tx;
+	struct gve_rx_queue_config *qcfg_rx;
+	struct gve_tx_queue_config *qcfg_tx;
 
 	u16 ring_size;
 	u16 packet_buffer_size;
@@ -764,9 +771,8 @@ struct gve_priv {
 	u32 rx_copybreak; /* copy packets smaller than this */
 	u16 default_num_queues; /* default num queues to set up */
 
-	u16 num_xdp_queues;
-	struct gve_queue_config tx_cfg;
-	struct gve_queue_config rx_cfg;
+	struct gve_tx_queue_config tx_cfg;
+	struct gve_rx_queue_config rx_cfg;
 	u32 num_ntfy_blks; /* spilt between TX and RX so must be even */
 
 	struct gve_registers __iomem *reg_bar0; /* see gve_register.h */
@@ -1039,27 +1045,16 @@ static inline bool gve_is_qpl(struct gve_priv *priv)
 }
 
 /* Returns the number of tx queue page lists */
-static inline u32 gve_num_tx_qpls(const struct gve_queue_config *tx_cfg,
-				  int num_xdp_queues,
+static inline u32 gve_num_tx_qpls(const struct gve_tx_queue_config *tx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
 		return 0;
-	return tx_cfg->num_queues + num_xdp_queues;
-}
-
-/* Returns the number of XDP tx queue page lists
- */
-static inline u32 gve_num_xdp_qpls(struct gve_priv *priv)
-{
-	if (priv->queue_format != GVE_GQI_QPL_FORMAT)
-		return 0;
-
-	return priv->num_xdp_queues;
+	return tx_cfg->num_queues + tx_cfg->num_xdp_queues;
 }
 
 /* Returns the number of rx queue page lists */
-static inline u32 gve_num_rx_qpls(const struct gve_queue_config *rx_cfg,
+static inline u32 gve_num_rx_qpls(const struct gve_rx_queue_config *rx_cfg,
 				  bool is_qpl)
 {
 	if (!is_qpl)
@@ -1077,7 +1072,8 @@ static inline u32 gve_rx_qpl_id(struct gve_priv *priv, int rx_qid)
 	return priv->tx_cfg.max_queues + rx_qid;
 }
 
-static inline u32 gve_get_rx_qpl_id(const struct gve_queue_config *tx_cfg, int rx_qid)
+static inline u32 gve_get_rx_qpl_id(const struct gve_tx_queue_config *tx_cfg,
+				    int rx_qid)
 {
 	return tx_cfg->max_queues + rx_qid;
 }
@@ -1087,7 +1083,7 @@ static inline u32 gve_tx_start_qpl_id(struct gve_priv *priv)
 	return gve_tx_qpl_id(priv, 0);
 }
 
-static inline u32 gve_rx_start_qpl_id(const struct gve_queue_config *tx_cfg)
+static inline u32 gve_rx_start_qpl_id(const struct gve_tx_queue_config *tx_cfg)
 {
 	return gve_get_rx_qpl_id(tx_cfg, 0);
 }
@@ -1118,7 +1114,7 @@ static inline bool gve_is_gqi(struct gve_priv *priv)
 
 static inline u32 gve_num_tx_queues(struct gve_priv *priv)
 {
-	return priv->tx_cfg.num_queues + priv->num_xdp_queues;
+	return priv->tx_cfg.num_queues + priv->tx_cfg.num_xdp_queues;
 }
 
 static inline u32 gve_xdp_tx_queue_id(struct gve_priv *priv, u32 queue_id)
@@ -1234,8 +1230,8 @@ int gve_adjust_config(struct gve_priv *priv,
 		      struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 		      struct gve_rx_alloc_rings_cfg *rx_alloc_cfg);
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config,
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
 		      bool reset_rss);
 /* flow steering rule */
 int gve_get_flow_rule_entry(struct gve_priv *priv, struct ethtool_rxnfc *cmd);
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index bc59b5b4235a0..a862031ba5d16 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -475,8 +475,8 @@ static int gve_set_channels(struct net_device *netdev,
 			    struct ethtool_channels *cmd)
 {
 	struct gve_priv *priv = netdev_priv(netdev);
-	struct gve_queue_config new_tx_cfg = priv->tx_cfg;
-	struct gve_queue_config new_rx_cfg = priv->rx_cfg;
+	struct gve_tx_queue_config new_tx_cfg = priv->tx_cfg;
+	struct gve_rx_queue_config new_rx_cfg = priv->rx_cfg;
 	struct ethtool_channels old_settings;
 	int new_tx = cmd->tx_count;
 	int new_rx = cmd->rx_count;
@@ -491,10 +491,17 @@ static int gve_set_channels(struct net_device *netdev,
 	if (!new_rx || !new_tx)
 		return -EINVAL;
 
-	if (priv->num_xdp_queues &&
-	    (new_tx != new_rx || (2 * new_tx > priv->tx_cfg.max_queues))) {
-		dev_err(&priv->pdev->dev, "XDP load failed: The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues");
-		return -EINVAL;
+	if (priv->xdp_prog) {
+		if (new_tx != new_rx ||
+		    (2 * new_tx > priv->tx_cfg.max_queues)) {
+			dev_err(&priv->pdev->dev, "The number of configured RX queues should be equal to the number of configured TX queues and the number of configured RX/TX queues should be less than or equal to half the maximum number of RX/TX queues when XDP program is installed");
+			return -EINVAL;
+		}
+
+		/* One XDP TX queue per RX queue. */
+		new_tx_cfg.num_xdp_queues = new_rx;
+	} else {
+		new_tx_cfg.num_xdp_queues = 0;
 	}
 
 	if (new_rx != priv->rx_cfg.num_queues &&
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 6dcdcaf518f4c..354f526a92385 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -795,30 +795,13 @@ static struct gve_queue_page_list *gve_rx_get_qpl(struct gve_priv *priv, int idx
 		return rx->dqo.qpl;
 }
 
-static int gve_register_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_register_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean up */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_register_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -836,30 +819,13 @@ static int gve_register_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_unregister_xdp_qpls(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-	int i;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	for (i = start_id; i < start_id + gve_num_xdp_qpls(priv); i++) {
-		err = gve_unregister_qpl(priv, gve_tx_get_qpl(priv, i));
-		/* This failure will trigger a reset - no need to clean */
-		if (err)
-			return err;
-	}
-	return 0;
-}
-
 static int gve_unregister_qpls(struct gve_priv *priv)
 {
 	int num_tx_qpls, num_rx_qpls;
 	int err;
 	int i;
 
-	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_num_xdp_qpls(priv),
-				      gve_is_qpl(priv));
+	num_tx_qpls = gve_num_tx_qpls(&priv->tx_cfg, gve_is_qpl(priv));
 	num_rx_qpls = gve_num_rx_qpls(&priv->rx_cfg, gve_is_qpl(priv));
 
 	for (i = 0; i < num_tx_qpls; i++) {
@@ -878,27 +844,6 @@ static int gve_unregister_qpls(struct gve_priv *priv)
 	return 0;
 }
 
-static int gve_create_xdp_rings(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_adminq_create_tx_queues(priv,
-					  gve_xdp_tx_start_queue_id(priv),
-					  priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev, "failed to create %d XDP tx queues\n",
-			  priv->num_xdp_queues);
-		/* This failure will trigger a reset - no need to clean
-		 * up
-		 */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "created %d XDP tx queues\n",
-		  priv->num_xdp_queues);
-
-	return 0;
-}
-
 static int gve_create_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -954,7 +899,7 @@ static void init_xdp_sync_stats(struct gve_priv *priv)
 	int i;
 
 	/* Init stats */
-	for (i = start_id; i < start_id + priv->num_xdp_queues; i++) {
+	for (i = start_id; i < start_id + priv->tx_cfg.num_xdp_queues; i++) {
 		int ntfy_idx = gve_tx_idx_to_ntfy(priv, i);
 
 		u64_stats_init(&priv->tx[i].statss);
@@ -979,24 +924,21 @@ static void gve_init_sync_stats(struct gve_priv *priv)
 static void gve_tx_get_curr_alloc_cfg(struct gve_priv *priv,
 				      struct gve_tx_alloc_rings_cfg *cfg)
 {
-	int num_xdp_queues = priv->xdp_prog ? priv->rx_cfg.num_queues : 0;
-
 	cfg->qcfg = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->ring_size = priv->tx_desc_cnt;
-	cfg->start_idx = 0;
-	cfg->num_rings = priv->tx_cfg.num_queues + num_xdp_queues;
+	cfg->num_xdp_rings = cfg->qcfg->num_xdp_queues;
 	cfg->tx = priv->tx;
 }
 
-static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings)
+static void gve_tx_stop_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
 	if (!priv->tx)
 		return;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_stop_ring_gqi(priv, i);
 		else
@@ -1004,12 +946,11 @@ static void gve_tx_stop_rings(struct gve_priv *priv, int start_id, int num_rings
 	}
 }
 
-static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
-			       int num_rings)
+static void gve_tx_start_rings(struct gve_priv *priv, int num_rings)
 {
 	int i;
 
-	for (i = start_id; i < start_id + num_rings; i++) {
+	for (i = 0; i < num_rings; i++) {
 		if (gve_is_gqi(priv))
 			gve_tx_start_ring_gqi(priv, i);
 		else
@@ -1017,28 +958,6 @@ static void gve_tx_start_rings(struct gve_priv *priv, int start_id,
 	}
 }
 
-static int gve_alloc_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-	int err = 0;
-
-	if (!priv->num_xdp_queues)
-		return 0;
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	err = gve_tx_alloc_rings_gqi(priv, &cfg);
-	if (err)
-		return err;
-
-	gve_tx_start_rings(priv, cfg.start_idx, cfg.num_rings);
-	init_xdp_sync_stats(priv);
-
-	return 0;
-}
-
 static int gve_queues_mem_alloc(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_alloc_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_alloc_cfg)
@@ -1069,26 +988,6 @@ static int gve_queues_mem_alloc(struct gve_priv *priv,
 	return err;
 }
 
-static int gve_destroy_xdp_rings(struct gve_priv *priv)
-{
-	int start_id;
-	int err;
-
-	start_id = gve_xdp_tx_start_queue_id(priv);
-	err = gve_adminq_destroy_tx_queues(priv,
-					   start_id,
-					   priv->num_xdp_queues);
-	if (err) {
-		netif_err(priv, drv, priv->dev,
-			  "failed to destroy XDP queues\n");
-		/* This failure will trigger a reset - no need to clean up */
-		return err;
-	}
-	netif_dbg(priv, drv, priv->dev, "destroyed XDP queues\n");
-
-	return 0;
-}
-
 static int gve_destroy_rings(struct gve_priv *priv)
 {
 	int num_tx_queues = gve_num_tx_queues(priv);
@@ -1113,20 +1012,6 @@ static int gve_destroy_rings(struct gve_priv *priv)
 	return 0;
 }
 
-static void gve_free_xdp_rings(struct gve_priv *priv)
-{
-	struct gve_tx_alloc_rings_cfg cfg = {0};
-
-	gve_tx_get_curr_alloc_cfg(priv, &cfg);
-	cfg.start_idx = gve_xdp_tx_start_queue_id(priv);
-	cfg.num_rings = priv->num_xdp_queues;
-
-	if (priv->tx) {
-		gve_tx_stop_rings(priv, cfg.start_idx, cfg.num_rings);
-		gve_tx_free_rings_gqi(priv, &cfg);
-	}
-}
-
 static void gve_queues_mem_free(struct gve_priv *priv,
 				struct gve_tx_alloc_rings_cfg *tx_cfg,
 				struct gve_rx_alloc_rings_cfg *rx_cfg)
@@ -1253,7 +1138,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 	int i, j;
 	u32 tx_qid;
 
-	if (!priv->num_xdp_queues)
+	if (!priv->tx_cfg.num_xdp_queues)
 		return 0;
 
 	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
@@ -1283,7 +1168,7 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 		}
 	}
 
-	for (i = 0; i < priv->num_xdp_queues; i++) {
+	for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) {
 		tx_qid = gve_xdp_tx_queue_id(priv, i);
 		priv->tx[tx_qid].xsk_pool = xsk_get_pool_from_qid(dev, i);
 	}
@@ -1304,7 +1189,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv)
 {
 	int i, tx_qid;
 
-	if (!priv->num_xdp_queues)
+	if (!priv->tx_cfg.num_xdp_queues || !priv->rx || !priv->tx)
 		return;
 
 	for (i = 0; i < priv->rx_cfg.num_queues; i++) {
@@ -1317,7 +1202,7 @@ static void gve_unreg_xdp_info(struct gve_priv *priv)
 		}
 	}
 
-	for (i = 0; i < priv->num_xdp_queues; i++) {
+	for (i = 0; i < priv->tx_cfg.num_xdp_queues; i++) {
 		tx_qid = gve_xdp_tx_queue_id(priv, i);
 		priv->tx[tx_qid].xsk_pool = NULL;
 	}
@@ -1334,7 +1219,7 @@ static void gve_drain_page_cache(struct gve_priv *priv)
 static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 				      struct gve_rx_alloc_rings_cfg *cfg)
 {
-	cfg->qcfg = &priv->rx_cfg;
+	cfg->qcfg_rx = &priv->rx_cfg;
 	cfg->qcfg_tx = &priv->tx_cfg;
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->enable_header_split = priv->header_split_enabled;
@@ -1415,17 +1300,13 @@ static int gve_queues_start(struct gve_priv *priv,
 
 	/* Record new configs into priv */
 	priv->tx_cfg = *tx_alloc_cfg->qcfg;
-	priv->rx_cfg = *rx_alloc_cfg->qcfg;
+	priv->tx_cfg.num_xdp_queues = tx_alloc_cfg->num_xdp_rings;
+	priv->rx_cfg = *rx_alloc_cfg->qcfg_rx;
 	priv->tx_desc_cnt = tx_alloc_cfg->ring_size;
 	priv->rx_desc_cnt = rx_alloc_cfg->ring_size;
 
-	if (priv->xdp_prog)
-		priv->num_xdp_queues = priv->rx_cfg.num_queues;
-	else
-		priv->num_xdp_queues = 0;
-
-	gve_tx_start_rings(priv, 0, tx_alloc_cfg->num_rings);
-	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg->num_queues);
+	gve_tx_start_rings(priv, gve_num_tx_queues(priv));
+	gve_rx_start_rings(priv, rx_alloc_cfg->qcfg_rx->num_queues);
 	gve_init_sync_stats(priv);
 
 	err = netif_set_real_num_tx_queues(dev, priv->tx_cfg.num_queues);
@@ -1477,7 +1358,7 @@ static int gve_queues_start(struct gve_priv *priv,
 	/* return the original error */
 	return err;
 stop_and_free_rings:
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 	gve_queues_mem_remove(priv);
 	return err;
@@ -1526,7 +1407,7 @@ static int gve_queues_stop(struct gve_priv *priv)
 
 	gve_unreg_xdp_info(priv);
 
-	gve_tx_stop_rings(priv, 0, gve_num_tx_queues(priv));
+	gve_tx_stop_rings(priv, gve_num_tx_queues(priv));
 	gve_rx_stop_rings(priv, priv->rx_cfg.num_queues);
 
 	priv->interface_down_cnt++;
@@ -1556,56 +1437,6 @@ static int gve_close(struct net_device *dev)
 	return 0;
 }
 
-static int gve_remove_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	err = gve_destroy_xdp_rings(priv);
-	if (err)
-		return err;
-
-	err = gve_unregister_xdp_qpls(priv);
-	if (err)
-		return err;
-
-	gve_unreg_xdp_info(priv);
-	gve_free_xdp_rings(priv);
-
-	priv->num_xdp_queues = 0;
-	return 0;
-}
-
-static int gve_add_xdp_queues(struct gve_priv *priv)
-{
-	int err;
-
-	priv->num_xdp_queues = priv->rx_cfg.num_queues;
-
-	err = gve_alloc_xdp_rings(priv);
-	if (err)
-		goto err;
-
-	err = gve_reg_xdp_info(priv, priv->dev);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_register_xdp_qpls(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	err = gve_create_xdp_rings(priv);
-	if (err)
-		goto free_xdp_rings;
-
-	return 0;
-
-free_xdp_rings:
-	gve_free_xdp_rings(priv);
-err:
-	priv->num_xdp_queues = 0;
-	return err;
-}
-
 static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 {
 	if (!gve_get_napi_enabled(priv))
@@ -1623,6 +1454,18 @@ static void gve_handle_link_status(struct gve_priv *priv, bool link_status)
 	}
 }
 
+static int gve_configure_rings_xdp(struct gve_priv *priv,
+				   u16 num_xdp_rings)
+{
+	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
+	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
+
+	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+	tx_alloc_cfg.num_xdp_rings = num_xdp_rings;
+
+	return gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+}
+
 static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		       struct netlink_ext_ack *extack)
 {
@@ -1635,29 +1478,26 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
 		WRITE_ONCE(priv->xdp_prog, prog);
 		if (old_prog)
 			bpf_prog_put(old_prog);
+
+		/* Update priv XDP queue configuration */
+		priv->tx_cfg.num_xdp_queues = priv->xdp_prog ?
+			priv->rx_cfg.num_queues : 0;
 		return 0;
 	}
 
-	gve_turndown(priv);
-	if (!old_prog && prog) {
-		// Allocate XDP TX queues if an XDP program is
-		// being installed
-		err = gve_add_xdp_queues(priv);
-		if (err)
-			goto out;
-	} else if (old_prog && !prog) {
-		// Remove XDP TX queues if an XDP program is
-		// being uninstalled
-		err = gve_remove_xdp_queues(priv);
-		if (err)
-			goto out;
-	}
+	if (!old_prog && prog)
+		err = gve_configure_rings_xdp(priv, priv->rx_cfg.num_queues);
+	else if (old_prog && !prog)
+		err = gve_configure_rings_xdp(priv, 0);
+
+	if (err)
+		goto out;
+
 	WRITE_ONCE(priv->xdp_prog, prog);
 	if (old_prog)
 		bpf_prog_put(old_prog);
 
 out:
-	gve_turnup(priv);
 	status = ioread32be(&priv->reg_bar0->device_status);
 	gve_handle_link_status(priv, GVE_DEVICE_STATUS_LINK_STATUS_MASK & status);
 	return err;
@@ -1908,13 +1748,12 @@ int gve_adjust_config(struct gve_priv *priv,
 }
 
 int gve_adjust_queues(struct gve_priv *priv,
-		      struct gve_queue_config new_rx_config,
-		      struct gve_queue_config new_tx_config,
+		      struct gve_rx_queue_config new_rx_config,
+		      struct gve_tx_queue_config new_tx_config,
 		      bool reset_rss)
 {
 	struct gve_tx_alloc_rings_cfg tx_alloc_cfg = {0};
 	struct gve_rx_alloc_rings_cfg rx_alloc_cfg = {0};
-	int num_xdp_queues;
 	int err;
 
 	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
@@ -1922,13 +1761,8 @@ int gve_adjust_queues(struct gve_priv *priv,
 	/* Relay the new config from ethtool */
 	tx_alloc_cfg.qcfg = &new_tx_config;
 	rx_alloc_cfg.qcfg_tx = &new_tx_config;
-	rx_alloc_cfg.qcfg = &new_rx_config;
+	rx_alloc_cfg.qcfg_rx = &new_rx_config;
 	rx_alloc_cfg.reset_rss = reset_rss;
-	tx_alloc_cfg.num_rings = new_tx_config.num_queues;
-
-	/* Add dedicated XDP TX queues if enabled. */
-	num_xdp_queues = priv->xdp_prog ? new_rx_config.num_queues : 0;
-	tx_alloc_cfg.num_rings += num_xdp_queues;
 
 	if (netif_running(priv->dev)) {
 		err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
@@ -2056,7 +1890,7 @@ static void gve_turnup(struct gve_priv *priv)
 		napi_schedule(&block->napi);
 	}
 
-	if (priv->num_xdp_queues && gve_supports_xdp_xmit(priv))
+	if (priv->tx_cfg.num_xdp_queues && gve_supports_xdp_xmit(priv))
 		xdp_features_set_redirect_target(priv->dev, false);
 
 	gve_set_napi_enabled(priv);
@@ -2412,6 +2246,7 @@ static int gve_init_priv(struct gve_priv *priv, bool skip_describe_device)
 		priv->rx_cfg.num_queues = min_t(int, priv->default_num_queues,
 						priv->rx_cfg.num_queues);
 	}
+	priv->tx_cfg.num_xdp_queues = 0;
 
 	dev_info(&priv->pdev->dev, "TX queues %d, RX queues %d\n",
 		 priv->tx_cfg.num_queues, priv->rx_cfg.num_queues);
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index acb73d4d0de6b..7b774cc510cca 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -385,12 +385,12 @@ int gve_rx_alloc_rings_gqi(struct gve_priv *priv,
 	int err = 0;
 	int i, j;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_gqi(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -419,7 +419,7 @@ void gve_rx_free_rings_gqi(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_gqi(priv, &rx[i], cfg);
 
 	kvfree(rx);
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 4367c3aac698e..07bb30497edb0 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -300,12 +300,12 @@ int gve_rx_alloc_rings_dqo(struct gve_priv *priv,
 	int err;
 	int i;
 
-	rx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_rx_ring),
+	rx = kvcalloc(cfg->qcfg_rx->max_queues, sizeof(struct gve_rx_ring),
 		      GFP_KERNEL);
 	if (!rx)
 		return -ENOMEM;
 
-	for (i = 0; i < cfg->qcfg->num_queues; i++) {
+	for (i = 0; i < cfg->qcfg_rx->num_queues; i++) {
 		err = gve_rx_alloc_ring_dqo(priv, cfg, &rx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -334,7 +334,7 @@ void gve_rx_free_rings_dqo(struct gve_priv *priv,
 	if (!rx)
 		return;
 
-	for (i = 0; i < cfg->qcfg->num_queues;  i++)
+	for (i = 0; i < cfg->qcfg_rx->num_queues;  i++)
 		gve_rx_free_ring_dqo(priv, &rx[i], cfg);
 
 	kvfree(rx);
diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
index c8c067e180598..1b40bf0c811a3 100644
--- a/drivers/net/ethernet/google/gve/gve_tx.c
+++ b/drivers/net/ethernet/google/gve/gve_tx.c
@@ -334,27 +334,23 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_gqi(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -370,8 +366,7 @@ int gve_tx_alloc_rings_gqi(struct gve_priv *priv,
 cleanup:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_gqi(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -384,13 +379,11 @@ void gve_tx_free_rings_gqi(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_gqi(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* gve_tx_avail - Calculates the number of slots available in the ring
@@ -844,7 +837,7 @@ int gve_xdp_xmit(struct net_device *dev, int n, struct xdp_frame **frames,
 		return -ENETDOWN;
 
 	qid = gve_xdp_tx_queue_id(priv,
-				  smp_processor_id() % priv->num_xdp_queues);
+				  smp_processor_id() % priv->tx_cfg.num_xdp_queues);
 
 	tx = &priv->tx[qid];
 
diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
index 394debc62268a..2eba868d80370 100644
--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
@@ -379,27 +379,23 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 			   struct gve_tx_alloc_rings_cfg *cfg)
 {
 	struct gve_tx_ring *tx = cfg->tx;
+	int total_queues;
 	int err = 0;
 	int i, j;
 
-	if (cfg->start_idx + cfg->num_rings > cfg->qcfg->max_queues) {
+	total_queues = cfg->qcfg->num_queues + cfg->num_xdp_rings;
+	if (total_queues > cfg->qcfg->max_queues) {
 		netif_err(priv, drv, priv->dev,
 			  "Cannot alloc more than the max num of Tx rings\n");
 		return -EINVAL;
 	}
 
-	if (cfg->start_idx == 0) {
-		tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
-			      GFP_KERNEL);
-		if (!tx)
-			return -ENOMEM;
-	} else if (!tx) {
-		netif_err(priv, drv, priv->dev,
-			  "Cannot alloc tx rings from a nonzero start idx without tx array\n");
-		return -EINVAL;
-	}
+	tx = kvcalloc(cfg->qcfg->max_queues, sizeof(struct gve_tx_ring),
+		      GFP_KERNEL);
+	if (!tx)
+		return -ENOMEM;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++) {
+	for (i = 0; i < total_queues; i++) {
 		err = gve_tx_alloc_ring_dqo(priv, cfg, &tx[i], i);
 		if (err) {
 			netif_err(priv, drv, priv->dev,
@@ -415,8 +411,7 @@ int gve_tx_alloc_rings_dqo(struct gve_priv *priv,
 err:
 	for (j = 0; j < i; j++)
 		gve_tx_free_ring_dqo(priv, &tx[j], cfg);
-	if (cfg->start_idx == 0)
-		kvfree(tx);
+	kvfree(tx);
 	return err;
 }
 
@@ -429,13 +424,11 @@ void gve_tx_free_rings_dqo(struct gve_priv *priv,
 	if (!tx)
 		return;
 
-	for (i = cfg->start_idx; i < cfg->start_idx + cfg->num_rings; i++)
+	for (i = 0; i < cfg->qcfg->num_queues + cfg->qcfg->num_xdp_queues; i++)
 		gve_tx_free_ring_dqo(priv, &tx[i], cfg);
 
-	if (cfg->start_idx == 0) {
-		kvfree(tx);
-		cfg->tx = NULL;
-	}
+	kvfree(tx);
+	cfg->tx = NULL;
 }
 
 /* Returns the number of slots available in the ring */

From 4138728f90053f924440ad90ee80603950df1923 Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:07 +0000
Subject: [PATCH 2720/2753] gve: update GQ RX to use buf_size

Commit ebdfae0d377b ("gve: adopt page pool for DQ RDA mode") introduced
a buf_size field to the gve_rx_slot_page_info struct, which can be used
in the datapath to take the place of the packet_buffer_size field, as it
will already be hot in the cache due to its extensive use. Using the
buf_size field in the datapath frees up the packet_buffer_size field in
the GQ-specific RX cacheline to be generalized for GQ and DQ (in the
next patch), as there is currently no common packet buffer size field
between the two queue formats.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve_rx.c | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 7b774cc510cca..9d444e723fcd4 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -141,12 +141,15 @@ void gve_rx_free_ring_gqi(struct gve_priv *priv, struct gve_rx_ring *rx,
 	netif_dbg(priv, drv, priv->dev, "freed rx ring %d\n", idx);
 }
 
-static void gve_setup_rx_buffer(struct gve_rx_slot_page_info *page_info,
-			     dma_addr_t addr, struct page *page, __be64 *slot_addr)
+static void gve_setup_rx_buffer(struct gve_rx_ring *rx,
+				struct gve_rx_slot_page_info *page_info,
+				dma_addr_t addr, struct page *page,
+				__be64 *slot_addr)
 {
 	page_info->page = page;
 	page_info->page_offset = 0;
 	page_info->page_address = page_address(page);
+	page_info->buf_size = rx->packet_buffer_size;
 	*slot_addr = cpu_to_be64(addr);
 	/* The page already has 1 ref */
 	page_ref_add(page, INT_MAX - 1);
@@ -171,7 +174,7 @@ static int gve_rx_alloc_buffer(struct gve_priv *priv, struct device *dev,
 		return err;
 	}
 
-	gve_setup_rx_buffer(page_info, dma, page, &data_slot->addr);
+	gve_setup_rx_buffer(rx, page_info, dma, page, &data_slot->addr);
 	return 0;
 }
 
@@ -199,7 +202,8 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			struct page *page = rx->data.qpl->pages[i];
 			dma_addr_t addr = i * PAGE_SIZE;
 
-			gve_setup_rx_buffer(&rx->data.page_info[i], addr, page,
+			gve_setup_rx_buffer(rx, &rx->data.page_info[i], addr,
+					    page,
 					    &rx->data.data_ring[i].qpl_offset);
 			continue;
 		}
@@ -222,6 +226,7 @@ static int gve_rx_prefill_pages(struct gve_rx_ring *rx,
 			rx->qpl_copy_pool[j].page = page;
 			rx->qpl_copy_pool[j].page_offset = 0;
 			rx->qpl_copy_pool[j].page_address = page_address(page);
+			rx->qpl_copy_pool[j].buf_size = rx->packet_buffer_size;
 
 			/* The page already has 1 ref. */
 			page_ref_add(page, INT_MAX - 1);
@@ -283,6 +288,7 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 
 	rx->mask = slots - 1;
 	rx->data.raw_addressing = cfg->raw_addressing;
@@ -351,7 +357,6 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 	rx->db_threshold = slots / 2;
 	gve_rx_init_ring_state_gqi(rx);
 
-	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	gve_rx_ctx_clear(&rx->ctx);
 
 	return 0;
@@ -590,7 +595,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 	copy_page_info->pad = page_info->pad;
 
 	skb = gve_rx_add_frags(napi, copy_page_info,
-			       rx->packet_buffer_size, len, ctx);
+			       copy_page_info->buf_size, len, ctx);
 	if (unlikely(!skb))
 		return NULL;
 
@@ -630,7 +635,8 @@ gve_rx_qpl(struct device *dev, struct net_device *netdev,
 	 * device.
 	 */
 	if (page_info->can_flip) {
-		skb = gve_rx_add_frags(napi, page_info, rx->packet_buffer_size, len, ctx);
+		skb = gve_rx_add_frags(napi, page_info, page_info->buf_size,
+				       len, ctx);
 		/* No point in recycling if we didn't get the skb */
 		if (skb) {
 			/* Make sure that the page isn't freed. */
@@ -680,7 +686,7 @@ static struct sk_buff *gve_rx_skb(struct gve_priv *priv, struct gve_rx_ring *rx,
 			skb = gve_rx_raw_addressing(&priv->pdev->dev, netdev,
 						    page_info, len, napi,
 						    data_slot,
-						    rx->packet_buffer_size, ctx);
+						    page_info->buf_size, ctx);
 		} else {
 			skb = gve_rx_qpl(&priv->pdev->dev, netdev, rx,
 					 page_info, len, napi, data_slot);
@@ -855,7 +861,7 @@ static void gve_rx(struct gve_rx_ring *rx, netdev_features_t feat,
 		void *old_data;
 		int xdp_act;
 
-		xdp_init_buff(&xdp, rx->packet_buffer_size, &rx->xdp_rxq);
+		xdp_init_buff(&xdp, page_info->buf_size, &rx->xdp_rxq);
 		xdp_prepare_buff(&xdp, page_info->page_address +
 				 page_info->page_offset, GVE_RX_PAD,
 				 len, false);

From 55e03dd88918ae73646ba834a412ac2c6fb2c629 Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:08 +0000
Subject: [PATCH 2721/2753] gve: merge packet buffer size fields

The data_buffer_size_dqo field in gve_priv and the packet_buffer_size
field in gve_rx_ring theoretically have the same meaning, but they are
defined in two different places and used in two separate contexts. There
is no good reason for this, so this change merges those fields into the
packet_buffer_size field in the RX ring.

This change also introduces a packet_buffer_size field to struct
gve_rx_queue_config to account for cases where queues are not allocated,
such as when the interface is down.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve.h                 | 4 ++--
 drivers/net/ethernet/google/gve/gve_adminq.c          | 4 +---
 drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c | 7 +++----
 drivers/net/ethernet/google/gve/gve_ethtool.c         | 3 +--
 drivers/net/ethernet/google/gve/gve_main.c            | 8 +++-----
 drivers/net/ethernet/google/gve/gve_rx.c              | 2 +-
 drivers/net/ethernet/google/gve/gve_rx_dqo.c          | 1 +
 7 files changed, 12 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index e5cc3fada9c92..9895541eddaec 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -227,6 +227,7 @@ struct gve_rx_cnts {
 /* Contains datapath state used to represent an RX queue. */
 struct gve_rx_ring {
 	struct gve_priv *gve;
+	u16 packet_buffer_size;
 	union {
 		/* GQI fields */
 		struct {
@@ -235,7 +236,6 @@ struct gve_rx_ring {
 
 			/* threshold for posting new buffs and descs */
 			u32 db_threshold;
-			u16 packet_buffer_size;
 
 			u32 qpl_copy_pool_mask;
 			u32 qpl_copy_pool_head;
@@ -635,6 +635,7 @@ struct gve_notify_block {
 struct gve_rx_queue_config {
 	u16 max_queues;
 	u16 num_queues;
+	u16 packet_buffer_size;
 };
 
 /* Tracks allowed and current tx queue settings */
@@ -842,7 +843,6 @@ struct gve_priv {
 	struct gve_ptype_lut *ptype_lut_dqo;
 
 	/* Must be a power of two. */
-	u16 data_buffer_size_dqo;
 	u16 max_rx_buffer_size; /* device limit */
 
 	enum gve_queue_format queue_format;
diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
index be7a423e5ab97..3e8fc33cc11fd 100644
--- a/drivers/net/ethernet/google/gve/gve_adminq.c
+++ b/drivers/net/ethernet/google/gve/gve_adminq.c
@@ -731,6 +731,7 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 		.ntfy_id = cpu_to_be32(rx->ntfy_id),
 		.queue_resources_addr = cpu_to_be64(rx->q_resources_bus),
 		.rx_ring_size = cpu_to_be16(priv->rx_desc_cnt),
+		.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size),
 	};
 
 	if (gve_is_gqi(priv)) {
@@ -743,7 +744,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->data.data_bus);
 		cmd->create_rx_queue.index = cpu_to_be32(queue_index);
 		cmd->create_rx_queue.queue_page_list_id = cpu_to_be32(qpl_id);
-		cmd->create_rx_queue.packet_buffer_size = cpu_to_be16(rx->packet_buffer_size);
 	} else {
 		u32 qpl_id = 0;
 
@@ -756,8 +756,6 @@ static void gve_adminq_get_create_rx_queue_cmd(struct gve_priv *priv,
 			cpu_to_be64(rx->dqo.complq.bus);
 		cmd->create_rx_queue.rx_data_ring_addr =
 			cpu_to_be64(rx->dqo.bufq.bus);
-		cmd->create_rx_queue.packet_buffer_size =
-			cpu_to_be16(priv->data_buffer_size_dqo);
 		cmd->create_rx_queue.rx_buff_ring_size =
 			cpu_to_be16(priv->rx_desc_cnt);
 		cmd->create_rx_queue.enable_rsc =
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
index af84cb88f828c..f9824664d04c5 100644
--- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -139,7 +139,7 @@ int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
 	buf_state->page_info.page_offset = 0;
 	buf_state->page_info.page_address =
 		page_address(buf_state->page_info.page);
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	buf_state->page_info.buf_size = rx->packet_buffer_size;
 	buf_state->last_single_ref_offset = 0;
 
 	/* The page already has 1 ref. */
@@ -162,7 +162,7 @@ void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state)
 void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
 			 struct gve_rx_buf_state_dqo *buf_state)
 {
-	const u16 data_buffer_size = priv->data_buffer_size_dqo;
+	const u16 data_buffer_size = rx->packet_buffer_size;
 	int pagecount;
 
 	/* Can't reuse if we only fit one buffer per page */
@@ -217,10 +217,9 @@ void gve_free_to_page_pool(struct gve_rx_ring *rx,
 static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 				    struct gve_rx_buf_state_dqo *buf_state)
 {
-	struct gve_priv *priv = rx->gve;
 	netmem_ref netmem;
 
-	buf_state->page_info.buf_size = priv->data_buffer_size_dqo;
+	buf_state->page_info.buf_size = rx->packet_buffer_size;
 	netmem = page_pool_alloc_netmem(rx->dqo.page_pool,
 					&buf_state->page_info.page_offset,
 					&buf_state->page_info.buf_size,
diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
index a862031ba5d16..31a21ccf48634 100644
--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
+++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
@@ -647,8 +647,7 @@ static int gve_set_tunable(struct net_device *netdev,
 	switch (etuna->id) {
 	case ETHTOOL_RX_COPYBREAK:
 	{
-		u32 max_copybreak = gve_is_gqi(priv) ?
-			GVE_DEFAULT_RX_BUFFER_SIZE : priv->data_buffer_size_dqo;
+		u32 max_copybreak = priv->rx_cfg.packet_buffer_size;
 
 		len = *(u32 *)value;
 		if (len > max_copybreak)
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 354f526a92385..20aabbe0e5180 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1224,9 +1224,7 @@ static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->raw_addressing = !gve_is_qpl(priv);
 	cfg->enable_header_split = priv->header_split_enabled;
 	cfg->ring_size = priv->rx_desc_cnt;
-	cfg->packet_buffer_size = gve_is_gqi(priv) ?
-				  GVE_DEFAULT_RX_BUFFER_SIZE :
-				  priv->data_buffer_size_dqo;
+	cfg->packet_buffer_size = priv->rx_cfg.packet_buffer_size;
 	cfg->rx = priv->rx;
 }
 
@@ -1331,7 +1329,7 @@ static int gve_queues_start(struct gve_priv *priv,
 		goto reset;
 
 	priv->header_split_enabled = rx_alloc_cfg->enable_header_split;
-	priv->data_buffer_size_dqo = rx_alloc_cfg->packet_buffer_size;
+	priv->rx_cfg.packet_buffer_size = rx_alloc_cfg->packet_buffer_size;
 
 	err = gve_create_rings(priv);
 	if (err)
@@ -2627,7 +2625,7 @@ static int gve_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	priv->service_task_flags = 0x0;
 	priv->state_flags = 0x0;
 	priv->ethtool_flags = 0x0;
-	priv->data_buffer_size_dqo = GVE_DEFAULT_RX_BUFFER_SIZE;
+	priv->rx_cfg.packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 	priv->max_rx_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
 
 	gve_set_probe_in_progress(priv);
diff --git a/drivers/net/ethernet/google/gve/gve_rx.c b/drivers/net/ethernet/google/gve/gve_rx.c
index 9d444e723fcd4..90e875c1832f8 100644
--- a/drivers/net/ethernet/google/gve/gve_rx.c
+++ b/drivers/net/ethernet/google/gve/gve_rx.c
@@ -288,7 +288,7 @@ int gve_rx_alloc_ring_gqi(struct gve_priv *priv,
 
 	rx->gve = priv;
 	rx->q_num = idx;
-	rx->packet_buffer_size = GVE_DEFAULT_RX_BUFFER_SIZE;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
 
 	rx->mask = slots - 1;
 	rx->data.raw_addressing = cfg->raw_addressing;
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 07bb30497edb0..218948b80b4ec 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -224,6 +224,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	memset(rx, 0, sizeof(*rx));
 	rx->gve = priv;
 	rx->q_num = idx;
+	rx->packet_buffer_size = cfg->packet_buffer_size;
 
 	rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots :
 		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);

From d6241530936125a059641474ab9dda54a84e3ce9 Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:09 +0000
Subject: [PATCH 2722/2753] gve: update XDP allocation path support RX buffer
 posting

In order to support installing an XDP program on DQ, RX buffers need to
be reposted using 4K buffers, which is larger than the default packet
buffer size of 2K. This is needed to accommodate the extra head and tail
that accompanies the data portion of an XDP buffer. Continuing to use 2K
buffers would mean that the packet buffer size for the NIC would have to
be restricted to 2048 - 320 - 256 = 1472B. However, this is problematic
for two reasons: first, 1472 is not a packet buffer size accepted by
GVE; second, at least 1474B of buffer space is needed to accommodate an
MTU of 1460, which is the default on GCP. As such, we allocate 4K
buffers, and post a 2K section of those 4K buffers (offset relative to
the XDP headroom) to the NIC for DMA to avoid a potential extra copy.
Because the GQ-QPL datapath requires copies regardless, this change was
not needed to support XDP in that case.

To capture this subtlety, a new field, packet_buffer_truesize, has been
added to the rx ring struct to represent size of the allocated buffer,
while packet_buffer_size has been left to represent the portion of the
buffer posted to the NIC.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaligineedi <pkaligineedi@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy <hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve.h         | 12 ++++++++--
 .../ethernet/google/gve/gve_buffer_mgmt_dqo.c | 17 +++++++++-----
 drivers/net/ethernet/google/gve/gve_main.c    | 19 +++++++++++++---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c  | 22 ++++++++++++++-----
 4 files changed, 53 insertions(+), 17 deletions(-)

diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
index 9895541eddaec..2fab38c8ee78a 100644
--- a/drivers/net/ethernet/google/gve/gve.h
+++ b/drivers/net/ethernet/google/gve/gve.h
@@ -59,6 +59,8 @@
 
 #define GVE_MAX_RX_BUFFER_SIZE 4096
 
+#define GVE_XDP_RX_BUFFER_SIZE_DQO 4096
+
 #define GVE_DEFAULT_RX_BUFFER_OFFSET 2048
 
 #define GVE_PAGE_POOL_SIZE_MULTIPLIER 4
@@ -227,7 +229,11 @@ struct gve_rx_cnts {
 /* Contains datapath state used to represent an RX queue. */
 struct gve_rx_ring {
 	struct gve_priv *gve;
-	u16 packet_buffer_size;
+
+	u16 packet_buffer_size;		/* Size of buffer posted to NIC */
+	u16 packet_buffer_truesize;	/* Total size of RX buffer */
+	u16 rx_headroom;
+
 	union {
 		/* GQI fields */
 		struct {
@@ -688,6 +694,7 @@ struct gve_rx_alloc_rings_cfg {
 	bool raw_addressing;
 	bool enable_header_split;
 	bool reset_rss;
+	bool xdp;
 
 	/* Allocated resources are returned here */
 	struct gve_rx_ring *rx;
@@ -1218,7 +1225,8 @@ void gve_free_buffer(struct gve_rx_ring *rx,
 		     struct gve_rx_buf_state_dqo *buf_state);
 int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc);
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx);
+					  struct gve_rx_ring *rx,
+					  bool xdp);
 
 /* Reset */
 void gve_schedule_reset(struct gve_priv *priv);
diff --git a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
index f9824664d04c5..a71883e1d9202 100644
--- a/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_buffer_mgmt_dqo.c
@@ -139,7 +139,8 @@ int gve_alloc_qpl_page_dqo(struct gve_rx_ring *rx,
 	buf_state->page_info.page_offset = 0;
 	buf_state->page_info.page_address =
 		page_address(buf_state->page_info.page);
-	buf_state->page_info.buf_size = rx->packet_buffer_size;
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
+	buf_state->page_info.pad = rx->rx_headroom;
 	buf_state->last_single_ref_offset = 0;
 
 	/* The page already has 1 ref. */
@@ -162,7 +163,7 @@ void gve_free_qpl_page_dqo(struct gve_rx_buf_state_dqo *buf_state)
 void gve_try_recycle_buf(struct gve_priv *priv, struct gve_rx_ring *rx,
 			 struct gve_rx_buf_state_dqo *buf_state)
 {
-	const u16 data_buffer_size = rx->packet_buffer_size;
+	const u16 data_buffer_size = rx->packet_buffer_truesize;
 	int pagecount;
 
 	/* Can't reuse if we only fit one buffer per page */
@@ -219,7 +220,7 @@ static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 {
 	netmem_ref netmem;
 
-	buf_state->page_info.buf_size = rx->packet_buffer_size;
+	buf_state->page_info.buf_size = rx->packet_buffer_truesize;
 	netmem = page_pool_alloc_netmem(rx->dqo.page_pool,
 					&buf_state->page_info.page_offset,
 					&buf_state->page_info.buf_size,
@@ -231,12 +232,14 @@ static int gve_alloc_from_page_pool(struct gve_rx_ring *rx,
 	buf_state->page_info.netmem = netmem;
 	buf_state->page_info.page_address = netmem_address(netmem);
 	buf_state->addr = page_pool_get_dma_addr_netmem(netmem);
+	buf_state->page_info.pad = rx->dqo.page_pool->p.offset;
 
 	return 0;
 }
 
 struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
-					  struct gve_rx_ring *rx)
+					  struct gve_rx_ring *rx,
+					  bool xdp)
 {
 	u32 ntfy_id = gve_rx_idx_to_ntfy(priv, rx->q_num);
 	struct page_pool_params pp = {
@@ -247,7 +250,8 @@ struct page_pool *gve_rx_create_page_pool(struct gve_priv *priv,
 		.netdev = priv->dev,
 		.napi = &priv->ntfy_blocks[ntfy_id].napi,
 		.max_len = PAGE_SIZE,
-		.dma_dir = DMA_FROM_DEVICE,
+		.dma_dir = xdp ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE,
+		.offset = xdp ? XDP_PACKET_HEADROOM : 0,
 	};
 
 	return page_pool_create(&pp);
@@ -301,7 +305,8 @@ int gve_alloc_buffer(struct gve_rx_ring *rx, struct gve_rx_desc_dqo *desc)
 	}
 	desc->buf_id = cpu_to_le16(buf_state - rx->dqo.buf_states);
 	desc->buf_addr = cpu_to_le64(buf_state->addr +
-				     buf_state->page_info.page_offset);
+				     buf_state->page_info.page_offset +
+				     buf_state->page_info.pad);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
index 20aabbe0e5180..cb2f9978f45e2 100644
--- a/drivers/net/ethernet/google/gve/gve_main.c
+++ b/drivers/net/ethernet/google/gve/gve_main.c
@@ -1149,8 +1149,14 @@ static int gve_reg_xdp_info(struct gve_priv *priv, struct net_device *dev)
 				       napi->napi_id);
 		if (err)
 			goto err;
-		err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
-						 MEM_TYPE_PAGE_SHARED, NULL);
+		if (gve_is_qpl(priv))
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_SHARED,
+							 NULL);
+		else
+			err = xdp_rxq_info_reg_mem_model(&rx->xdp_rxq,
+							 MEM_TYPE_PAGE_POOL,
+							 rx->dqo.page_pool);
 		if (err)
 			goto err;
 		rx->xsk_pool = xsk_get_pool_from_qid(dev, i);
@@ -1226,6 +1232,7 @@ static void gve_rx_get_curr_alloc_cfg(struct gve_priv *priv,
 	cfg->ring_size = priv->rx_desc_cnt;
 	cfg->packet_buffer_size = priv->rx_cfg.packet_buffer_size;
 	cfg->rx = priv->rx;
+	cfg->xdp = !!cfg->qcfg_tx->num_xdp_queues;
 }
 
 void gve_get_curr_alloc_cfgs(struct gve_priv *priv,
@@ -1461,6 +1468,7 @@ static int gve_configure_rings_xdp(struct gve_priv *priv,
 	gve_get_curr_alloc_cfgs(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 	tx_alloc_cfg.num_xdp_rings = num_xdp_rings;
 
+	rx_alloc_cfg.xdp = !!num_xdp_rings;
 	return gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
 }
 
@@ -1629,6 +1637,7 @@ static int gve_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags)
 static int verify_xdp_configuration(struct net_device *dev)
 {
 	struct gve_priv *priv = netdev_priv(dev);
+	u16 max_xdp_mtu;
 
 	if (dev->features & NETIF_F_LRO) {
 		netdev_warn(dev, "XDP is not supported when LRO is on.\n");
@@ -1641,7 +1650,11 @@ static int verify_xdp_configuration(struct net_device *dev)
 		return -EOPNOTSUPP;
 	}
 
-	if (dev->mtu > GVE_DEFAULT_RX_BUFFER_SIZE - sizeof(struct ethhdr) - GVE_RX_PAD) {
+	max_xdp_mtu = priv->rx_cfg.packet_buffer_size - sizeof(struct ethhdr);
+	if (priv->queue_format == GVE_GQI_QPL_FORMAT)
+		max_xdp_mtu -= GVE_RX_PAD;
+
+	if (dev->mtu > max_xdp_mtu) {
 		netdev_warn(dev, "XDP is not supported for mtu %d.\n",
 			    dev->mtu);
 		return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 218948b80b4ec..719891ccdc8fc 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -226,6 +226,14 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 	rx->q_num = idx;
 	rx->packet_buffer_size = cfg->packet_buffer_size;
 
+	if (cfg->xdp) {
+		rx->packet_buffer_truesize = GVE_XDP_RX_BUFFER_SIZE_DQO;
+		rx->rx_headroom = XDP_PACKET_HEADROOM;
+	} else {
+		rx->packet_buffer_truesize = rx->packet_buffer_size;
+		rx->rx_headroom = 0;
+	}
+
 	rx->dqo.num_buf_states = cfg->raw_addressing ? buffer_queue_slots :
 		gve_get_rx_pages_per_qpl_dqo(cfg->ring_size);
 	rx->dqo.buf_states = kvcalloc(rx->dqo.num_buf_states,
@@ -255,7 +263,7 @@ int gve_rx_alloc_ring_dqo(struct gve_priv *priv,
 		goto err;
 
 	if (cfg->raw_addressing) {
-		pool = gve_rx_create_page_pool(priv, rx);
+		pool = gve_rx_create_page_pool(priv, rx, cfg->xdp);
 		if (IS_ERR(pool))
 			goto err;
 
@@ -485,14 +493,15 @@ static void gve_skb_add_rx_frag(struct gve_rx_ring *rx,
 	if (rx->dqo.page_pool) {
 		skb_add_rx_frag_netmem(rx->ctx.skb_tail, num_frags,
 				       buf_state->page_info.netmem,
-				       buf_state->page_info.page_offset,
-				       buf_len,
+				       buf_state->page_info.page_offset +
+				       buf_state->page_info.pad, buf_len,
 				       buf_state->page_info.buf_size);
 	} else {
 		skb_add_rx_frag(rx->ctx.skb_tail, num_frags,
 				buf_state->page_info.page,
-				buf_state->page_info.page_offset,
-				buf_len, buf_state->page_info.buf_size);
+				buf_state->page_info.page_offset +
+				buf_state->page_info.pad, buf_len,
+				buf_state->page_info.buf_size);
 	}
 }
 
@@ -612,7 +621,8 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 
 	/* Sync the portion of dma buffer for CPU to read. */
 	dma_sync_single_range_for_cpu(&priv->pdev->dev, buf_state->addr,
-				      buf_state->page_info.page_offset,
+				      buf_state->page_info.page_offset +
+				      buf_state->page_info.pad,
 				      buf_len, DMA_FROM_DEVICE);
 
 	/* Append to current skb if one exists. */

From 9fc670b1f72e65bfb28971ef10884b8ae98a3b47 Mon Sep 17 00:00:00 2001
From: Joshua Washington <joshwash@google.com>
Date: Fri, 21 Mar 2025 00:29:10 +0000
Subject: [PATCH 2723/2753] gve: add XDP DROP and PASS support for DQ

This patch adds support for running XDP programs on DQ, along with
rudimentary processing for XDP_DROP and XDP_PASS. These actions require
very limited driver functionality when it comes to processing an XDP
buffer, so currently if the XDP action is not XDP_PASS, the packet is
dropped and stats are updated.

Reviewed-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Praveen Kaliginedi <pkaligineedi@google.com>
Signed-off-by: Joshua Washington <joshwash@google.com>
Signed-off-by: Harshitha Ramamurthy<hramamurthy@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/google/gve/gve_rx_dqo.c | 52 ++++++++++++++++++++
 1 file changed, 52 insertions(+)

diff --git a/drivers/net/ethernet/google/gve/gve_rx_dqo.c b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
index 719891ccdc8fc..dcb0545baa50f 100644
--- a/drivers/net/ethernet/google/gve/gve_rx_dqo.c
+++ b/drivers/net/ethernet/google/gve/gve_rx_dqo.c
@@ -547,6 +547,29 @@ static int gve_rx_append_frags(struct napi_struct *napi,
 	return 0;
 }
 
+static void gve_xdp_done_dqo(struct gve_priv *priv, struct gve_rx_ring *rx,
+			     struct xdp_buff *xdp, struct bpf_prog *xprog,
+			     int xdp_act,
+			     struct gve_rx_buf_state_dqo *buf_state)
+{
+	u64_stats_update_begin(&rx->statss);
+	switch (xdp_act) {
+	case XDP_ABORTED:
+	case XDP_DROP:
+	default:
+		rx->xdp_actions[xdp_act]++;
+		break;
+	case XDP_TX:
+		rx->xdp_tx_errors++;
+		break;
+	case XDP_REDIRECT:
+		rx->xdp_redirect_errors++;
+		break;
+	}
+	u64_stats_update_end(&rx->statss);
+	gve_free_buffer(rx, buf_state);
+}
+
 /* Returns 0 if descriptor is completed successfully.
  * Returns -EINVAL if descriptor is invalid.
  * Returns -ENOMEM if data cannot be copied to skb.
@@ -561,6 +584,7 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 	const bool hsplit = compl_desc->split_header;
 	struct gve_rx_buf_state_dqo *buf_state;
 	struct gve_priv *priv = rx->gve;
+	struct bpf_prog *xprog;
 	u16 buf_len;
 	u16 hdr_len;
 
@@ -634,6 +658,34 @@ static int gve_rx_dqo(struct napi_struct *napi, struct gve_rx_ring *rx,
 		return 0;
 	}
 
+	xprog = READ_ONCE(priv->xdp_prog);
+	if (xprog) {
+		struct xdp_buff xdp;
+		void *old_data;
+		int xdp_act;
+
+		xdp_init_buff(&xdp, buf_state->page_info.buf_size,
+			      &rx->xdp_rxq);
+		xdp_prepare_buff(&xdp,
+				 buf_state->page_info.page_address +
+				 buf_state->page_info.page_offset,
+				 buf_state->page_info.pad,
+				 buf_len, false);
+		old_data = xdp.data;
+		xdp_act = bpf_prog_run_xdp(xprog, &xdp);
+		buf_state->page_info.pad += xdp.data - old_data;
+		buf_len = xdp.data_end - xdp.data;
+		if (xdp_act != XDP_PASS) {
+			gve_xdp_done_dqo(priv, rx, &xdp, xprog, xdp_act,
+					 buf_state);
+			return 0;
+		}
+
+		u64_stats_update_begin(&rx->statss);
+		rx->xdp_actions[XDP_PASS]++;
+		u64_stats_update_end(&rx->statss);
+	}
+
 	if (eop && buf_len <= priv->rx_copybreak) {
 		rx->ctx.skb_head = gve_rx_copy(priv->dev, napi,
 					       &buf_state->page_info, buf_len);

From 46373bff582d1d42e9d68499ec1591a59f2ad49a Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Fri, 21 Mar 2025 02:15:18 +0000
Subject: [PATCH 2724/2753] Add support to set napi threaded for individual
 napi

A net device has a threaded sysctl that can be used to enable threaded
napi polling on all of the NAPI contexts under that device. Allow
enabling threaded napi polling at individual napi level using netlink.

Extend the netlink operation `napi-set` and allow setting the threaded
attribute of a NAPI. This will enable the threaded polling on a napi
context.

Tested using following command in qemu/virtio-net:
./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml \
  --do napi-set       --json '{"id": 66, "threaded": 1}'

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/netlink/specs/netdev.yaml | 10 ++++++++
 Documentation/networking/napi.rst       | 13 ++++++++++-
 include/linux/netdevice.h               | 10 ++++++++
 include/uapi/linux/netdev.h             |  1 +
 net/core/dev.c                          | 31 +++++++++++++++++++++++++
 net/core/netdev-genl-gen.c              |  5 ++--
 net/core/netdev-genl.c                  |  9 +++++++
 tools/include/uapi/linux/netdev.h       |  1 +
 8 files changed, 77 insertions(+), 3 deletions(-)

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index f5e0750ab71db..92f98f2a6bd74 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -280,6 +280,14 @@ attribute-sets:
         doc: The timeout, in nanoseconds, of how long to suspend irq
              processing, if event polling finds events
         type: uint
+      -
+        name: threaded
+        doc: Whether the napi is configured to operate in threaded polling
+             mode. If this is set to `1` then the NAPI context operates
+             in threaded polling mode.
+        type: u32
+        checks:
+          max: 1
   -
     name: xsk-info
     attributes: []
@@ -691,6 +699,7 @@ operations:
             - defer-hard-irqs
             - gro-flush-timeout
             - irq-suspend-timeout
+            - threaded
       dump:
         request:
           attributes:
@@ -743,6 +752,7 @@ operations:
             - defer-hard-irqs
             - gro-flush-timeout
             - irq-suspend-timeout
+            - threaded
 
 kernel-family:
   headers: [ "net/netdev_netlink.h"]
diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index d0e3953cae6ab..63f98c05860f8 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -444,7 +444,18 @@ dependent). The NAPI instance IDs will be assigned in the opposite
 order than the process IDs of the kernel threads.
 
 Threaded NAPI is controlled by writing 0/1 to the ``threaded`` file in
-netdev's sysfs directory.
+netdev's sysfs directory. It can also be enabled for a specific napi using
+netlink interface.
+
+For example, using the script:
+
+.. code-block:: bash
+
+  $ kernel-source/tools/net/ynl/pyynl/cli.py \
+            --spec Documentation/netlink/specs/netdev.yaml \
+            --do napi-set \
+            --json='{"id": 66,
+                     "threaded": 1}'
 
 .. rubric:: Footnotes
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 1a11b7a1f05c4..b1bcda3270ffe 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -370,6 +370,7 @@ struct napi_config {
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	cpumask_t affinity_mask;
+	bool threaded;
 	unsigned int napi_id;
 };
 
@@ -591,6 +592,15 @@ static inline bool napi_complete(struct napi_struct *n)
 
 int dev_set_threaded(struct net_device *dev, bool threaded);
 
+/*
+ * napi_set_threaded - set napi threaded state
+ * @napi: NAPI context
+ * @threaded: whether this napi does threaded polling
+ *
+ * Return 0 on success and negative errno on failure.
+ */
+int napi_set_threaded(struct napi_struct *napi, bool threaded);
+
 void napi_disable(struct napi_struct *n);
 void napi_disable_locked(struct napi_struct *n);
 
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 7600bf62dbdf0..fac1b8ffeb55f 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -134,6 +134,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/net/core/dev.c b/net/core/dev.c
index bcf81c3ff6a32..a35ff2b46a70b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6835,6 +6835,30 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
+int napi_set_threaded(struct napi_struct *napi, bool threaded)
+{
+	if (napi->dev->threaded)
+		return -EINVAL;
+
+	if (threaded) {
+		if (!napi->thread) {
+			int err = napi_kthread_create(napi);
+
+			if (err)
+				return err;
+		}
+	}
+
+	if (napi->config)
+		napi->config->threaded = threaded;
+
+	/* Make sure kthread is created before THREADED bit is set. */
+	smp_mb__before_atomic();
+	assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+
+	return 0;
+}
+
 int dev_set_threaded(struct net_device *dev, bool threaded)
 {
 	struct napi_struct *napi;
@@ -6846,6 +6870,11 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 		return 0;
 
 	if (threaded) {
+		/* Check if threaded is set at napi level already */
+		list_for_each_entry(napi, &dev->napi_list, dev_list)
+			if (test_bit(NAPI_STATE_THREADED, &napi->state))
+				return -EINVAL;
+
 		list_for_each_entry(napi, &dev->napi_list, dev_list) {
 			if (!napi->thread) {
 				err = napi_kthread_create(napi);
@@ -7092,6 +7121,8 @@ static void napi_restore_config(struct napi_struct *n)
 		napi_hash_add(n);
 		n->config->napi_id = n->napi_id;
 	}
+
+	napi_set_threaded(n, n->config->threaded);
 }
 
 static void napi_save_config(struct napi_struct *n)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 739f7b6506a6a..c2e5cee857d29 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -92,11 +92,12 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1]
 };
 
 /* NETDEV_CMD_NAPI_SET - do */
-static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = {
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED + 1] = {
 	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 1),
 };
 
 /* Ops table for netdev */
@@ -187,7 +188,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.cmd		= NETDEV_CMD_NAPI_SET,
 		.doit		= netdev_nl_napi_set_doit,
 		.policy		= netdev_napi_set_nl_policy,
-		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+		.maxattr	= NETDEV_A_NAPI_THREADED,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 };
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index a186fea63c09e..057001c3bbbaa 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -186,6 +186,9 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
 		goto nla_put_failure;
 
+	if (nla_put_u32(rsp, NETDEV_A_NAPI_THREADED, !!napi->thread))
+		goto nla_put_failure;
+
 	if (napi->thread) {
 		pid = task_pid_nr(napi->thread);
 		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
@@ -324,8 +327,14 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 {
 	u64 irq_suspend_timeout = 0;
 	u64 gro_flush_timeout = 0;
+	u32 threaded = 0;
 	u32 defer = 0;
 
+	if (info->attrs[NETDEV_A_NAPI_THREADED]) {
+		threaded = nla_get_u32(info->attrs[NETDEV_A_NAPI_THREADED]);
+		napi_set_threaded(napi, !!threaded);
+	}
+
 	if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) {
 		defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]);
 		napi_set_defer_hard_irqs(napi, defer);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7600bf62dbdf0..fac1b8ffeb55f 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -134,6 +134,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)

From c96c500d4f9597f275cf34eb3795ab1012646e90 Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Fri, 21 Mar 2025 02:15:19 +0000
Subject: [PATCH 2725/2753] net: Create separate gro_flush helper function

Move multiple copies of same code snippet doing `gro_flush` and
`gro_normal_list` into a separate helper function.

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/core/dev.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/net/core/dev.c b/net/core/dev.c
index a35ff2b46a70b..2625819f45fa0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6545,6 +6545,13 @@ static void skb_defer_free_flush(struct softnet_data *sd)
 	}
 }
 
+static void __napi_gro_flush_helper(struct napi_struct *napi)
+{
+	/* Flush too old packets. If HZ < 1000, flush all packets */
+	gro_flush(&napi->gro, HZ >= 1000);
+	gro_normal_list(&napi->gro);
+}
+
 #if defined(CONFIG_NET_RX_BUSY_POLL)
 
 static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
@@ -6555,9 +6562,7 @@ static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
 		return;
 	}
 
-	/* Flush too old packets. If HZ < 1000, flush all packets */
-	gro_flush(&napi->gro, HZ >= 1000);
-	gro_normal_list(&napi->gro);
+	__napi_gro_flush_helper(napi);
 
 	clear_bit(NAPI_STATE_SCHED, &napi->state);
 }
@@ -7389,9 +7394,7 @@ static int __napi_poll(struct napi_struct *n, bool *repoll)
 		return work;
 	}
 
-	/* Flush too old packets. If HZ < 1000, flush all packets */
-	gro_flush(&n->gro, HZ >= 1000);
-	gro_normal_list(&n->gro);
+	__napi_gro_flush_helper(n);
 
 	/* Some drivers may have called napi_schedule
 	 * prior to exhausting their budget.

From 9f9f9fedbfbef352e8fbd9d7cd6a60088a8e0efe Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Fri, 21 Mar 2025 02:15:20 +0000
Subject: [PATCH 2726/2753] Extend napi threaded polling to allow kthread based
 busy polling

Add a new state to napi state enum:

- STATE_THREADED_BUSY_POLL
  Threaded busy poll is enabled/running for this napi.

Following changes are introduced in the napi scheduling and state logic:

- When threaded busy poll is enabled through sysfs it also enables
  NAPI_STATE_THREADED so a kthread is created per napi. It also sets
  NAPI_STATE_THREADED_BUSY_POLL bit on each napi to indicate that we are
  supposed to busy poll for each napi.

- When napi is scheduled with STATE_SCHED_THREADED and associated
  kthread is woken up, the kthread owns the context. If
  NAPI_STATE_THREADED_BUSY_POLL and NAPI_SCHED_THREADED both are set
  then it means that we can busy poll.

- To keep busy polling and to avoid scheduling of the interrupts, the
  napi_complete_done returns false when both SCHED_THREADED and
  THREADED_BUSY_POLL flags are set. Also napi_complete_done returns
  early to avoid the STATE_SCHED_THREADED being unset.

- If at any point STATE_THREADED_BUSY_POLL is unset, the
  napi_complete_done will run and unset the SCHED_THREADED bit also.
  This will make the associated kthread go to sleep as per existing
  logic.

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 Documentation/ABI/testing/sysfs-class-net     |  3 +-
 Documentation/netlink/specs/netdev.yaml       | 12 ++-
 Documentation/networking/napi.rst             | 67 ++++++++++++-
 .../net/ethernet/atheros/atl1c/atl1c_main.c   |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/pci.c     |  2 +-
 drivers/net/ethernet/renesas/ravb_main.c      |  2 +-
 drivers/net/wireless/ath/ath10k/snoc.c        |  2 +-
 include/linux/netdevice.h                     | 20 +++-
 include/uapi/linux/netdev.h                   |  6 ++
 net/core/dev.c                                | 93 ++++++++++++++++---
 net/core/net-sysfs.c                          |  2 +-
 net/core/netdev-genl-gen.c                    |  2 +-
 net/core/netdev-genl.c                        |  2 +-
 tools/include/uapi/linux/netdev.h             |  6 ++
 14 files changed, 188 insertions(+), 33 deletions(-)

diff --git a/Documentation/ABI/testing/sysfs-class-net b/Documentation/ABI/testing/sysfs-class-net
index ebf21beba846d..15d7d36a8294b 100644
--- a/Documentation/ABI/testing/sysfs-class-net
+++ b/Documentation/ABI/testing/sysfs-class-net
@@ -343,7 +343,7 @@ Date:		Jan 2021
 KernelVersion:	5.12
 Contact:	netdev@vger.kernel.org
 Description:
-		Boolean value to control the threaded mode per device. User could
+		Integer value to control the threaded mode per device. User could
 		set this value to enable/disable threaded mode for all napi
 		belonging to this device, without the need to do device up/down.
 
@@ -351,4 +351,5 @@ Description:
 		== ==================================
 		0  threaded mode disabled for this dev
 		1  threaded mode enabled for this dev
+		2  threaded mode enabled, and busy polling enabled.
 		== ==================================
diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 92f98f2a6bd74..6501795595585 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -82,6 +82,10 @@ definitions:
     name: qstats-scope
     type: flags
     entries: [ queue ]
+  -
+    name: napi-threaded
+    type: enum
+    entries: [ disable, enable, busy-poll-enable ]
 
 attribute-sets:
   -
@@ -283,11 +287,11 @@ attribute-sets:
       -
         name: threaded
         doc: Whether the napi is configured to operate in threaded polling
-             mode. If this is set to `1` then the NAPI context operates
-             in threaded polling mode.
+             mode. If this is set to `enable` then the NAPI context operates
+             in threaded polling mode. If this is set to `busy-poll-enable`
+             then the NAPI kthread also does busypolling.
         type: u32
-        checks:
-          max: 1
+        enum: napi-threaded
   -
     name: xsk-info
     attributes: []
diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index 63f98c05860f8..0f83142c624d6 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -263,7 +263,9 @@ are not well known).
 Busy polling is enabled by either setting ``SO_BUSY_POLL`` on
 selected sockets or using the global ``net.core.busy_poll`` and
 ``net.core.busy_read`` sysctls. An io_uring API for NAPI busy polling
-also exists.
+also exists. Threaded polling of NAPI also has a mode to busy poll for
+packets (:ref:`threaded busy polling<threaded_busy_poll>`) using the same
+thread that is used for NAPI processing.
 
 epoll-based busy polling
 ------------------------
@@ -426,6 +428,69 @@ Therefore, setting ``gro_flush_timeout`` and ``napi_defer_hard_irqs`` is
 the recommended usage, because otherwise setting ``irq-suspend-timeout``
 might not have any discernible effect.
 
+.. _threaded_busy_poll:
+
+Threaded NAPI busy polling
+--------------------------
+
+Threaded napi allows processing of packets from each NAPI in a kthread in
+kernel. Threaded napi busy polling extends this and adds support to do
+continuous busy polling of this napi. This can be used to enable busy polling
+independent of userspace application or the API (epoll, io_uring, raw sockets)
+being used in userspace to process the packets.
+
+It can be enabled for each NAPI using netlink interface or at device level using
+the threaded NAPI sysctl.
+
+For example, using following script:
+
+.. code-block:: bash
+
+  $ kernel-source/tools/net/ynl/pyynl/cli.py \
+            --spec Documentation/netlink/specs/netdev.yaml \
+            --do napi-set \
+            --json='{"id": 66,
+                     "threaded": "busy-poll-enable"}'
+
+
+Enabling it for each NAPI allows finer control to enable busy pollling for
+only a set of NIC queues which will get traffic with low latency requirements.
+
+Depending on application requirement, user might want to set affinity of the
+kthread that is busy polling each NAPI. User might also want to set priority
+and the scheduler of the thread depending on the latency requirements.
+
+For a hard low-latency application, user might want to dedicate the full core
+for the NAPI polling so the NIC queue descriptors are picked up from the queue
+as soon as they appear. For more relaxed low-latency requirement, user might
+want to share the core with other threads.
+
+Once threaded busy polling is enabled for a NAPI, PID of the kthread can be
+fetched using netlink interface so the affinity, priority and scheduler
+configuration can be done.
+
+For example, following script can be used to fetch the pid:
+
+.. code-block:: bash
+
+  $ kernel-source/tools/net/ynl/pyynl/cli.py \
+            --spec Documentation/netlink/specs/netdev.yaml \
+            --do napi-get \
+            --json='{"id": 66}'
+
+This will output something like following, the pid `258` is the PID of the
+kthread that is polling this NAPI.
+
+.. code-block:: bash
+
+  $ {'defer-hard-irqs': 0,
+     'gro-flush-timeout': 0,
+     'id': 66,
+     'ifindex': 2,
+     'irq-suspend-timeout': 0,
+     'pid': 258,
+     'threaded': 'enable'}
+
 .. _threaded:
 
 Threaded NAPI
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index c571614b1d501..5133284767709 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2688,7 +2688,7 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->mii.mdio_write = atl1c_mdio_write;
 	adapter->mii.phy_id_mask = 0x1f;
 	adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK;
-	dev_set_threaded(netdev, true);
+	dev_set_threaded(netdev, NETDEV_NAPI_THREADED_ENABLE);
 	for (i = 0; i < adapter->rx_queue_count; ++i)
 		netif_napi_add(netdev, &adapter->rrd_ring[i].napi,
 			       atl1c_clean_rx);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 058dcabfaa2e4..2ed3b9263be2b 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -156,7 +156,7 @@ static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci)
 	}
 	strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx",
 		sizeof(mlxsw_pci->napi_dev_rx->name));
-	dev_set_threaded(mlxsw_pci->napi_dev_rx, true);
+	dev_set_threaded(mlxsw_pci->napi_dev_rx, NETDEV_NAPI_THREADED_ENABLE);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c9f4976a35275..12e4f68c0c8f9 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -3075,7 +3075,7 @@ static int ravb_probe(struct platform_device *pdev)
 	if (info->coalesce_irqs) {
 		netdev_sw_irq_coalesce_default_on(ndev);
 		if (num_present_cpus() == 1)
-			dev_set_threaded(ndev, true);
+			dev_set_threaded(ndev, NETDEV_NAPI_THREADED_ENABLE);
 	}
 
 	/* Network device register */
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index d436a874cd5af..52e0de8c30696 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -935,7 +935,7 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
 
 	bitmap_clear(ar_snoc->pending_ce_irqs, 0, CE_COUNT_MAX);
 
-	dev_set_threaded(ar->napi_dev, true);
+	dev_set_threaded(ar->napi_dev, NETDEV_NAPI_THREADED_ENABLE);
 	ath10k_core_napi_enable(ar);
 	ath10k_snoc_irq_enable(ar);
 	ath10k_snoc_rx_post(ar);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b1bcda3270ffe..76740bfb2009e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -370,7 +370,7 @@ struct napi_config {
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	cpumask_t affinity_mask;
-	bool threaded;
+	u8 threaded;
 	unsigned int napi_id;
 };
 
@@ -428,6 +428,8 @@ enum {
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
 	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
 	NAPI_STATE_HAS_NOTIFIER,	/* Napi has an IRQ notifier */
+	NAPI_STATE_THREADED_BUSY_POLL,	/* The threaded napi poller will busy poll */
+	NAPI_STATE_SCHED_THREADED_BUSY_POLL,  /* The threaded napi poller is busy polling */
 };
 
 enum {
@@ -442,8 +444,14 @@ enum {
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
 	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
 	NAPIF_STATE_HAS_NOTIFIER	= BIT(NAPI_STATE_HAS_NOTIFIER),
+	NAPIF_STATE_THREADED_BUSY_POLL	= BIT(NAPI_STATE_THREADED_BUSY_POLL),
+	NAPIF_STATE_SCHED_THREADED_BUSY_POLL  =
+			BIT(NAPI_STATE_SCHED_THREADED_BUSY_POLL),
 };
 
+#define NAPIF_STATE_THREADED_BUSY_POLL_MASK \
+	(NAPIF_STATE_THREADED | NAPIF_STATE_THREADED_BUSY_POLL)
+
 enum gro_result {
 	GRO_MERGED,
 	GRO_MERGED_FREE,
@@ -590,16 +598,18 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded);
+int dev_set_threaded(struct net_device *dev,
+		     enum netdev_napi_threaded threaded);
 
 /*
  * napi_set_threaded - set napi threaded state
  * @napi: NAPI context
- * @threaded: whether this napi does threaded polling
+ * @threaded: threading mode
  *
  * Return 0 on success and negative errno on failure.
  */
-int napi_set_threaded(struct napi_struct *napi, bool threaded);
+int napi_set_threaded(struct napi_struct *napi,
+		      enum netdev_napi_threaded threaded);
 
 void napi_disable(struct napi_struct *n);
 void napi_disable_locked(struct napi_struct *n);
@@ -2433,7 +2443,7 @@ struct net_device {
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
-	bool			threaded;
+	u8			threaded;
 	bool			irq_affinity_auto;
 	bool			rx_cpu_rmap_auto;
 
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index fac1b8ffeb55f..b9b59d60957ff 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -77,6 +77,12 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLE,
+	NETDEV_NAPI_THREADED_ENABLE,
+	NETDEV_NAPI_THREADED_BUSY_POLL_ENABLE,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
diff --git a/net/core/dev.c b/net/core/dev.c
index 2625819f45fa0..3795a72b80df6 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -78,6 +78,7 @@
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/isolation.h>
+#include <linux/sched/types.h>
 #include <linux/sched/mm.h>
 #include <linux/smpboot.h>
 #include <linux/mutex.h>
@@ -6465,7 +6466,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 	 *    the guarantee we will be called later.
 	 */
 	if (unlikely(n->state & (NAPIF_STATE_NPSVC |
-				 NAPIF_STATE_IN_BUSY_POLL)))
+				 NAPIF_STATE_IN_BUSY_POLL |
+				 NAPIF_STATE_SCHED_THREADED_BUSY_POLL)))
 		return false;
 
 	if (work_done) {
@@ -6840,7 +6842,21 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-int napi_set_threaded(struct napi_struct *napi, bool threaded)
+static void napi_set_threaded_state(struct napi_struct *napi,
+				    enum netdev_napi_threaded threaded)
+{
+	unsigned long val;
+
+	val = 0;
+	if (threaded == NETDEV_NAPI_THREADED_BUSY_POLL_ENABLE)
+		val |= NAPIF_STATE_THREADED_BUSY_POLL;
+	if (threaded)
+		val |= NAPIF_STATE_THREADED;
+	set_mask_bits(&napi->state, NAPIF_STATE_THREADED_BUSY_POLL_MASK, val);
+}
+
+int napi_set_threaded(struct napi_struct *napi,
+		      enum netdev_napi_threaded threaded)
 {
 	if (napi->dev->threaded)
 		return -EINVAL;
@@ -6859,14 +6875,15 @@ int napi_set_threaded(struct napi_struct *napi, bool threaded)
 
 	/* Make sure kthread is created before THREADED bit is set. */
 	smp_mb__before_atomic();
-	assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	napi_set_threaded_state(napi, threaded);
 
 	return 0;
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded)
+int dev_set_threaded(struct net_device *dev, enum netdev_napi_threaded threaded)
 {
 	struct napi_struct *napi;
+	unsigned long val;
 	int err = 0;
 
 	netdev_assert_locked_or_invisible(dev);
@@ -6874,17 +6891,22 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 	if (dev->threaded == threaded)
 		return 0;
 
+	val = 0;
 	if (threaded) {
 		/* Check if threaded is set at napi level already */
 		list_for_each_entry(napi, &dev->napi_list, dev_list)
 			if (test_bit(NAPI_STATE_THREADED, &napi->state))
 				return -EINVAL;
 
+		val |= NAPIF_STATE_THREADED;
+		if (threaded == NETDEV_NAPI_THREADED_BUSY_POLL_ENABLE)
+			val |= NAPIF_STATE_THREADED_BUSY_POLL;
+
 		list_for_each_entry(napi, &dev->napi_list, dev_list) {
 			if (!napi->thread) {
 				err = napi_kthread_create(napi);
 				if (err) {
-					threaded = false;
+					threaded = NETDEV_NAPI_THREADED_DISABLE;
 					break;
 				}
 			}
@@ -6903,9 +6925,13 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 	 * polled. In this case, the switch between threaded mode and
 	 * softirq mode will happen in the next round of napi_schedule().
 	 * This should not cause hiccups/stalls to the live traffic.
+	 *
+	 * Switch to busy_poll threaded napi will occur after the threaded
+	 * napi is scheduled.
 	 */
 	list_for_each_entry(napi, &dev->napi_list, dev_list)
-		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+		set_mask_bits(&napi->state,
+			      NAPIF_STATE_THREADED_BUSY_POLL_MASK, val);
 
 	return err;
 }
@@ -7225,8 +7251,12 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	 * Clear dev->threaded if kthread creation failed so that
 	 * threaded mode will not be enabled in napi_enable().
 	 */
-	if (dev->threaded && napi_kthread_create(napi))
-		dev->threaded = false;
+	if (dev->threaded) {
+		if (napi_kthread_create(napi))
+			dev->threaded = false;
+		else
+			napi_set_threaded_state(napi, dev->threaded);
+	}
 	netif_napi_set_irq_locked(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight_locked);
@@ -7248,7 +7278,9 @@ void napi_disable_locked(struct napi_struct *n)
 		}
 
 		new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC;
-		new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL);
+		new &= ~(NAPIF_STATE_THREADED
+			 | NAPIF_STATE_THREADED_BUSY_POLL
+			 | NAPIF_STATE_PREFER_BUSY_POLL);
 	} while (!try_cmpxchg(&n->state, &val, new));
 
 	hrtimer_cancel(&n->timer);
@@ -7292,7 +7324,7 @@ void napi_enable_locked(struct napi_struct *n)
 
 		new = val & ~(NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC);
 		if (n->dev->threaded && n->thread)
-			new |= NAPIF_STATE_THREADED;
+			napi_set_threaded_state(n, n->dev->threaded);
 	} while (!try_cmpxchg(&n->state, &val, new));
 }
 EXPORT_SYMBOL(napi_enable_locked);
@@ -7454,7 +7486,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 	return -1;
 }
 
-static void napi_threaded_poll_loop(struct napi_struct *napi)
+static void napi_threaded_poll_loop(struct napi_struct *napi, bool busy_poll)
 {
 	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
@@ -7483,22 +7515,53 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 		}
 		skb_defer_free_flush(sd);
 		bpf_net_ctx_clear(bpf_net_ctx);
+
+		/* Push the skbs up the stack if busy polling. */
+		if (busy_poll)
+			__napi_gro_flush_helper(napi);
 		local_bh_enable();
 
-		if (!repoll)
+		/* If busy polling then do not break here because we need to
+		 * call cond_resched and rcu_softirq_qs_periodic to prevent
+		 * watchdog warnings.
+		 */
+		if (!repoll && !busy_poll)
 			break;
 
 		rcu_softirq_qs_periodic(last_qs);
 		cond_resched();
+
+		if (!repoll)
+			break;
 	}
 }
 
 static int napi_threaded_poll(void *data)
 {
 	struct napi_struct *napi = data;
+	bool busy_poll_sched;
+	unsigned long val;
+	bool busy_poll;
+
+	while (!napi_thread_wait(napi)) {
+		/* Once woken up, this means that we are scheduled as threaded
+		 * napi and this thread owns the napi context, if busy poll
+		 * state is set then we busy poll this napi.
+		 */
+		val = READ_ONCE(napi->state);
+		busy_poll = val & NAPIF_STATE_THREADED_BUSY_POLL;
+		busy_poll_sched = val & NAPIF_STATE_SCHED_THREADED_BUSY_POLL;
 
-	while (!napi_thread_wait(napi))
-		napi_threaded_poll_loop(napi);
+		/* Do not busy poll if napi is disabled. */
+		if (unlikely(val & NAPIF_STATE_DISABLE))
+			busy_poll = false;
+
+		if (busy_poll != busy_poll_sched)
+			assign_bit(NAPI_STATE_SCHED_THREADED_BUSY_POLL,
+				   &napi->state, busy_poll);
+
+		napi_threaded_poll_loop(napi, busy_poll);
+	}
 
 	return 0;
 }
@@ -12666,7 +12729,7 @@ static void run_backlog_napi(unsigned int cpu)
 {
 	struct softnet_data *sd = per_cpu_ptr(&softnet_data, cpu);
 
-	napi_threaded_poll_loop(&sd->backlog);
+	napi_threaded_poll_loop(&sd->backlog, false);
 }
 
 static void backlog_napi_setup(unsigned int cpu)
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index abaa1c919b984..d3ccd04960fb8 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -741,7 +741,7 @@ static int modify_napi_threaded(struct net_device *dev, unsigned long val)
 	if (list_empty(&dev->napi_list))
 		return -EOPNOTSUPP;
 
-	if (val != 0 && val != 1)
+	if (val > NETDEV_NAPI_THREADED_BUSY_POLL_ENABLE)
 		return -EOPNOTSUPP;
 
 	ret = dev_set_threaded(dev, val);
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index c2e5cee857d29..1dbe5f19a192b 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -97,7 +97,7 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
-	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 1),
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 2),
 };
 
 /* Ops table for netdev */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 057001c3bbbaa..e540475290ca3 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -332,7 +332,7 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 
 	if (info->attrs[NETDEV_A_NAPI_THREADED]) {
 		threaded = nla_get_u32(info->attrs[NETDEV_A_NAPI_THREADED]);
-		napi_set_threaded(napi, !!threaded);
+		napi_set_threaded(napi, threaded);
 	}
 
 	if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) {
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index fac1b8ffeb55f..b9b59d60957ff 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -77,6 +77,12 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLE,
+	NETDEV_NAPI_THREADED_ENABLE,
+	NETDEV_NAPI_THREADED_BUSY_POLL_ENABLE,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,

From 9397422b0344c70afd73207be630a6bd5451d490 Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Fri, 21 Mar 2025 02:15:21 +0000
Subject: [PATCH 2727/2753] selftests: Add napi threaded busy poll test in
 `busy_poller`

Add testcase to run busy poll test with threaded napi busy poll enabled.

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/busy_poll_test.sh | 25 ++++++++++++++++++-
 tools/testing/selftests/net/busy_poller.c     | 14 ++++++++---
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/busy_poll_test.sh b/tools/testing/selftests/net/busy_poll_test.sh
index 7db292ec4884a..aeca610dc9892 100755
--- a/tools/testing/selftests/net/busy_poll_test.sh
+++ b/tools/testing/selftests/net/busy_poll_test.sh
@@ -27,6 +27,9 @@ NAPI_DEFER_HARD_IRQS=100
 GRO_FLUSH_TIMEOUT=50000
 SUSPEND_TIMEOUT=20000000
 
+# NAPI threaded busy poll config
+NAPI_THREADED_POLL=2
+
 setup_ns()
 {
 	set -e
@@ -62,6 +65,9 @@ cleanup_ns()
 test_busypoll()
 {
 	suspend_value=${1:-0}
+	napi_threaded_value=${2:-0}
+	prefer_busy_poll_value=${3:-$PREFER_BUSY_POLL}
+
 	tmp_file=$(mktemp)
 	out_file=$(mktemp)
 
@@ -73,10 +79,11 @@ test_busypoll()
 					     -b${SERVER_IP}        \
 					     -m${MAX_EVENTS}       \
 					     -u${BUSY_POLL_USECS}  \
-					     -P${PREFER_BUSY_POLL} \
+					     -P${prefer_busy_poll_value} \
 					     -g${BUSY_POLL_BUDGET} \
 					     -i${NSIM_SV_IFIDX}    \
 					     -s${suspend_value}    \
+					     -t${napi_threaded_value} \
 					     -o${out_file}&
 
 	wait_local_port_listen nssv ${SERVER_PORT} tcp
@@ -109,6 +116,15 @@ test_busypoll_with_suspend()
 	return $?
 }
 
+test_busypoll_with_napi_threaded()
+{
+	# Only enable napi threaded poll. Set suspend timeout and prefer busy
+	# poll to 0.
+	test_busypoll 0 ${NAPI_THREADED_POLL} 0
+
+	return $?
+}
+
 ###
 ### Code start
 ###
@@ -154,6 +170,13 @@ if [ $? -ne 0 ]; then
 	exit 1
 fi
 
+test_busypoll_with_napi_threaded
+if [ $? -ne 0 ]; then
+	echo "test_busypoll_with_napi_threaded failed"
+	cleanup_ns
+	exit 1
+fi
+
 echo "$NSIM_SV_FD:$NSIM_SV_IFIDX" > $NSIM_DEV_SYS_UNLINK
 
 echo $NSIM_CL_ID > $NSIM_DEV_SYS_DEL
diff --git a/tools/testing/selftests/net/busy_poller.c b/tools/testing/selftests/net/busy_poller.c
index 04c7ff577bb89..f7407f09f635e 100644
--- a/tools/testing/selftests/net/busy_poller.c
+++ b/tools/testing/selftests/net/busy_poller.c
@@ -65,15 +65,16 @@ static uint32_t cfg_busy_poll_usecs;
 static uint16_t cfg_busy_poll_budget;
 static uint8_t cfg_prefer_busy_poll;
 
-/* IRQ params */
+/* NAPI params */
 static uint32_t cfg_defer_hard_irqs;
 static uint64_t cfg_gro_flush_timeout;
 static uint64_t cfg_irq_suspend_timeout;
+static enum netdev_napi_threaded cfg_napi_threaded_poll = NETDEV_NAPI_THREADED_DISABLE;
 
 static void usage(const char *filepath)
 {
 	error(1, 0,
-	      "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -i<ifindex>",
+	      "Usage: %s -p<port> -b<addr> -m<max_events> -u<busy_poll_usecs> -P<prefer_busy_poll> -g<busy_poll_budget> -o<outfile> -d<defer_hard_irqs> -r<gro_flush_timeout> -s<irq_suspend_timeout> -t<napi_threaded_poll> -i<ifindex>",
 	      filepath);
 }
 
@@ -86,7 +87,7 @@ static void parse_opts(int argc, char **argv)
 	if (argc <= 1)
 		usage(argv[0]);
 
-	while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:")) != -1) {
+	while ((c = getopt(argc, argv, "p:m:b:u:P:g:o:d:r:s:i:t:")) != -1) {
 		/* most options take integer values, except o and b, so reduce
 		 * code duplication a bit for the common case by calling
 		 * strtoull here and leave bounds checking and casting per
@@ -168,6 +169,12 @@ static void parse_opts(int argc, char **argv)
 
 			cfg_ifindex = (int)tmp;
 			break;
+		case 't':
+			if (tmp == ULLONG_MAX || tmp > 2)
+				error(1, ERANGE, "napi threaded poll value must be 0-2");
+
+			cfg_napi_threaded_poll = (enum netdev_napi_threaded)tmp;
+			break;
 		}
 	}
 
@@ -246,6 +253,7 @@ static void setup_queue(void)
 						  cfg_gro_flush_timeout);
 	netdev_napi_set_req_set_irq_suspend_timeout(set_req,
 						    cfg_irq_suspend_timeout);
+	netdev_napi_set_req_set_threaded(set_req, cfg_napi_threaded_poll);
 
 	if (netdev_napi_set(ys, set_req))
 		error(1, 0, "can't set NAPI params: %s\n", yerr.msg);

From ac3db750c21e36ead52bbbbce247a489c359c466 Mon Sep 17 00:00:00 2001
From: Danny Lin <danny@orbstack.dev>
Date: Thu, 20 Mar 2025 21:34:49 -0700
Subject: [PATCH 2728/2753] net: fully namespace
 net.core.{r,w}mem_{default,max} sysctls

This builds on commit 19249c0724f2 ("net: make net.core.{r,w}mem_{default,max} namespaced")
by adding support for writing the sysctls from within net namespaces,
rather than only reading the values that were set in init_net. These are
relatively commonly-used sysctls, so programs may try to set them without
knowing that they're in a container. It can be surprising for such attempts
to fail with EACCES.

Unlike other net sysctls that were converted to namespaced ones, many
systems have a sysctl.conf (or other configs) that globally write to
net.core.rmem_default on boot and expect the value to propagate to
containers, and programs running in containers may depend on the increased
buffer sizes in order to work properly. This means that namespacing the
sysctls and using the kernel default values in each new netns would break
existing workloads.

As a compromise, inherit the initial net.core.*mem_* values from the
current process' netns when creating a new netns. This is not standard
behavior for most netns sysctls, but it avoids breaking existing workloads.

Signed-off-by: Danny Lin <danny@orbstack.dev>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/netns/core.h                    |  5 +++++
 include/net/sock.h                          |  6 -----
 net/core/net_namespace.c                    | 21 +++++++++++++++++
 net/core/sock.c                             | 16 ++++---------
 net/core/sysctl_net_core.c                  | 25 ++++-----------------
 net/ipv4/ip_output.c                        |  2 +-
 net/ipv4/tcp_output.c                       |  2 +-
 net/netfilter/ipvs/ip_vs_sync.c             |  4 ++--
 tools/testing/selftests/net/netns-sysctl.sh | 24 ++++++++++++++------
 9 files changed, 55 insertions(+), 50 deletions(-)

diff --git a/include/net/netns/core.h b/include/net/netns/core.h
index 9b36f0ff0c200..0459523602cbd 100644
--- a/include/net/netns/core.h
+++ b/include/net/netns/core.h
@@ -17,6 +17,11 @@ struct netns_core {
 	u8	sysctl_txrehash;
 	u8	sysctl_tstamp_allow_data;
 
+	u32 sysctl_wmem_max;
+	u32 sysctl_rmem_max;
+	u32 sysctl_wmem_default;
+	u32 sysctl_rmem_default;
+
 #ifdef CONFIG_PROC_FS
 	struct prot_inuse __percpu *prot_inuse;
 #endif
diff --git a/include/net/sock.h b/include/net/sock.h
index 8daf1b3b12c60..7aeddba449197 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2849,12 +2849,6 @@ void sk_get_meminfo(const struct sock *sk, u32 *meminfo);
 #define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
 #define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
 
-extern __u32 sysctl_wmem_max;
-extern __u32 sysctl_rmem_max;
-
-extern __u32 sysctl_wmem_default;
-extern __u32 sysctl_rmem_default;
-
 #define SKB_FRAG_PAGE_ORDER	get_order(32768)
 DECLARE_STATIC_KEY_FALSE(net_high_order_alloc_disable_key);
 
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index b0dfdf791ece5..39fe16f1ab724 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -317,6 +317,27 @@ static __net_init void preinit_net_sysctl(struct net *net)
 	net->core.sysctl_optmem_max = 128 * 1024;
 	net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED;
 	net->core.sysctl_tstamp_allow_data = 1;
+
+	/*
+	 * net.core.{r,w}mem_{default,max} used to be non-namespaced.
+	 * For backward compatibility, inherit values from the current netns
+	 * when creating a new one, so that setting them in init_net
+	 * affects new namespaces like it used to. This avoids causing
+	 * surprising performance regressions for namespaced applications
+	 * relying on tuned rmem/wmem.
+	 */
+	if (net == &init_net) {
+		net->core.sysctl_wmem_max = SK_WMEM_MAX;
+		net->core.sysctl_rmem_max = SK_RMEM_MAX;
+		net->core.sysctl_wmem_default = SK_WMEM_MAX;
+		net->core.sysctl_rmem_default = SK_RMEM_MAX;
+	} else {
+		struct net *current_net = current->nsproxy->net_ns;
+		net->core.sysctl_wmem_max = current_net->core.sysctl_wmem_max;
+		net->core.sysctl_rmem_max = current_net->core.sysctl_rmem_max;
+		net->core.sysctl_wmem_default = current_net->core.sysctl_wmem_default;
+		net->core.sysctl_rmem_default = current_net->core.sysctl_rmem_default;
+	}
 }
 
 /* init code that must occur even if setup_net() is not called. */
diff --git a/net/core/sock.c b/net/core/sock.c
index 323892066def8..88694cd59abdf 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -278,14 +278,6 @@ static struct lock_class_key af_wlock_keys[AF_MAX];
 static struct lock_class_key af_elock_keys[AF_MAX];
 static struct lock_class_key af_kern_callback_keys[AF_MAX];
 
-/* Run time adjustable parameters. */
-__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
-EXPORT_SYMBOL(sysctl_wmem_max);
-__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
-EXPORT_SYMBOL(sysctl_rmem_max);
-__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
-__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
-
 DEFINE_STATIC_KEY_FALSE(memalloc_socks_key);
 EXPORT_SYMBOL_GPL(memalloc_socks_key);
 
@@ -1333,7 +1325,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		val = min_t(u32, val, READ_ONCE(sysctl_wmem_max));
+		val = min_t(u32, val, READ_ONCE(sock_net(sk)->core.sysctl_wmem_max));
 set_sndbuf:
 		/* Ensure val * 2 fits into an int, to prevent max_t()
 		 * from treating it as a negative value.
@@ -1365,7 +1357,7 @@ int sk_setsockopt(struct sock *sk, int level, int optname,
 		 * play 'guess the biggest size' games. RCVBUF/SNDBUF
 		 * are treated in BSD as hints
 		 */
-		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sysctl_rmem_max)));
+		__sock_set_rcvbuf(sk, min_t(u32, val, READ_ONCE(sock_net(sk)->core.sysctl_rmem_max)));
 		break;
 
 	case SO_RCVBUFFORCE:
@@ -3618,8 +3610,8 @@ void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid)
 	timer_setup(&sk->sk_timer, NULL, 0);
 
 	sk->sk_allocation	=	GFP_KERNEL;
-	sk->sk_rcvbuf		=	READ_ONCE(sysctl_rmem_default);
-	sk->sk_sndbuf		=	READ_ONCE(sysctl_wmem_default);
+	sk->sk_rcvbuf		=	READ_ONCE(sock_net(sk)->core.sysctl_rmem_default);
+	sk->sk_sndbuf		=	READ_ONCE(sock_net(sk)->core.sysctl_wmem_default);
 	sk->sk_state		=	TCP_CLOSE;
 	sk->sk_use_task_frag	=	true;
 	sk_set_socket(sk, sock);
diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c
index c7769ee0d9c55..aedc249bf0e23 100644
--- a/net/core/sysctl_net_core.c
+++ b/net/core/sysctl_net_core.c
@@ -676,21 +676,9 @@ static struct ctl_table netns_core_table[] = {
 		.extra2		= SYSCTL_ONE,
 		.proc_handler	= proc_dou8vec_minmax,
 	},
-	{
-		.procname	= "tstamp_allow_data",
-		.data		= &init_net.core.sysctl_tstamp_allow_data,
-		.maxlen		= sizeof(u8),
-		.mode		= 0644,
-		.proc_handler	= proc_dou8vec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE
-	},
-	/* sysctl_core_net_init() will set the values after this
-	 * to readonly in network namespaces
-	 */
 	{
 		.procname	= "wmem_max",
-		.data		= &sysctl_wmem_max,
+		.data		= &init_net.core.sysctl_wmem_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -698,7 +686,7 @@ static struct ctl_table netns_core_table[] = {
 	},
 	{
 		.procname	= "rmem_max",
-		.data		= &sysctl_rmem_max,
+		.data		= &init_net.core.sysctl_rmem_max,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -706,7 +694,7 @@ static struct ctl_table netns_core_table[] = {
 	},
 	{
 		.procname	= "wmem_default",
-		.data		= &sysctl_wmem_default,
+		.data		= &init_net.core.sysctl_wmem_default,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -714,7 +702,7 @@ static struct ctl_table netns_core_table[] = {
 	},
 	{
 		.procname	= "rmem_default",
-		.data		= &sysctl_rmem_default,
+		.data		= &init_net.core.sysctl_rmem_default,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -748,13 +736,8 @@ static __net_init int sysctl_core_net_init(struct net *net)
 			goto err_dup;
 
 		for (i = 0; i < table_size; ++i) {
-			if (tbl[i].data == &sysctl_wmem_max)
-				break;
-
 			tbl[i].data += (char *)net - (char *)&init_net;
 		}
-		for (; i < table_size; ++i)
-			tbl[i].mode &= ~0222;
 	}
 
 	net->core.sysctl_hdr = register_net_sysctl_sz(net, "net/core", tbl, table_size);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 6e18d7ec50624..7b7c5e4ea5d81 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1643,7 +1643,7 @@ void ip_send_unicast_reply(struct sock *sk, const struct sock *orig_sk,
 
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
+	sk->sk_sndbuf = READ_ONCE(net->core.sysctl_wmem_default);
 	ipc.sockc.mark = fl4.flowi4_mark;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9a60610171145..abc766b3936dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -241,7 +241,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss,
 	if (wscale_ok) {
 		/* Set window scaling on max possible window */
 		space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
-		space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
+		space = max_t(u32, space, READ_ONCE(sock_net(sk)->core.sysctl_rmem_max));
 		space = min_t(u32, space, window_clamp);
 		*rcv_wscale = clamp_t(int, ilog2(space) - 15,
 				      0, TCP_MAX_WSCALE);
diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 3402675bf5215..62f30d5c25c7e 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1280,12 +1280,12 @@ static void set_sock_size(struct sock *sk, int mode, int val)
 	lock_sock(sk);
 	if (mode) {
 		val = clamp_t(int, val, (SOCK_MIN_SNDBUF + 1) / 2,
-			      READ_ONCE(sysctl_wmem_max));
+			      READ_ONCE(sock_net(sk)->core.sysctl_wmem_max));
 		sk->sk_sndbuf = val * 2;
 		sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
 	} else {
 		val = clamp_t(int, val, (SOCK_MIN_RCVBUF + 1) / 2,
-			      READ_ONCE(sysctl_rmem_max));
+			      READ_ONCE(sock_net(sk)->core.sysctl_rmem_max));
 		sk->sk_rcvbuf = val * 2;
 		sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
 	}
diff --git a/tools/testing/selftests/net/netns-sysctl.sh b/tools/testing/selftests/net/netns-sysctl.sh
index 45c34a3b9aae3..bb6f173a28e25 100755
--- a/tools/testing/selftests/net/netns-sysctl.sh
+++ b/tools/testing/selftests/net/netns-sysctl.sh
@@ -20,21 +20,31 @@ fail() {
 setup_ns test_ns
 
 for sc in {r,w}mem_{default,max}; do
-	# check that this is writable in a netns
+	initial_value="$(sysctl -n "net.core.$sc")"
+
+	# check that this is writable in the init netns
 	[ -w "/proc/sys/net/core/$sc" ] ||
 		fail "$sc isn't writable in the init netns!"
 
-	# change the value in the host netns
+	# change the value in the init netns
 	sysctl -qw "net.core.$sc=300000" ||
 		fail "Can't write $sc in init netns!"
 
-	# check that the value is read from the init netns
-	[ "$(ip netns exec $test_ns sysctl -n "net.core.$sc")" -eq 300000 ] ||
+	# check that the value did not change in the test netns
+	[ "$(ip netns exec $test_ns sysctl -n "net.core.$sc")" -eq "$initial_value" ] ||
 		fail "Value for $sc mismatch!"
 
-	# check that this isn't writable in a netns
-	ip netns exec $test_ns [ -w "/proc/sys/net/core/$sc" ] &&
-		fail "$sc is writable in a netns!"
+	# check that this is also writable in the test netns
+	ip netns exec $test_ns [ -w "/proc/sys/net/core/$sc" ] ||
+		fail "$sc isn't writable in the test netns!"
+
+	# change the value in the test netns
+	ip netns exec $test_ns sysctl -qw "net.core.$sc=200000" ||
+		fail "Can't write $sc in test netns!"
+
+	# check that the value is read from the test netns
+	[ "$(ip netns exec $test_ns sysctl -n "net.core.$sc")" -eq 200000 ] ||
+		fail "Value for $sc mismatch!"
 done
 
 echo 'Test passed OK'

From df2333e6df8ab4f16b7cb116a63bdd4ac799ca06 Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Fri, 21 Mar 2025 12:48:52 +0800
Subject: [PATCH 2729/2753] bonding: check xdp prog when set bond mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Following operations can trigger a warning[1]:

    ip netns add ns1
    ip netns exec ns1 ip link add bond0 type bond mode balance-rr
    ip netns exec ns1 ip link set dev bond0 xdp obj af_xdp_kern.o sec xdp
    ip netns exec ns1 ip link set bond0 type bond mode broadcast
    ip netns del ns1

When delete the namespace, dev_xdp_uninstall() is called to remove xdp
program on bond dev, and bond_xdp_set() will check the bond mode. If bond
mode is changed after attaching xdp program, the warning may occur.

Some bond modes (broadcast, etc.) do not support native xdp. Set bond mode
with xdp program attached is not good. Add check for xdp program when set
bond mode.

    [1]
    ------------[ cut here ]------------
    WARNING: CPU: 0 PID: 11 at net/core/dev.c:9912 unregister_netdevice_many_notify+0x8d9/0x930
    Modules linked in:
    CPU: 0 UID: 0 PID: 11 Comm: kworker/u4:0 Not tainted 6.14.0-rc4 #107
    Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014
    Workqueue: netns cleanup_net
    RIP: 0010:unregister_netdevice_many_notify+0x8d9/0x930
    Code: 00 00 48 c7 c6 6f e3 a2 82 48 c7 c7 d0 b3 96 82 e8 9c 10 3e ...
    RSP: 0018:ffffc90000063d80 EFLAGS: 00000282
    RAX: 00000000ffffffa1 RBX: ffff888004959000 RCX: 00000000ffffdfff
    RDX: 0000000000000000 RSI: 00000000ffffffea RDI: ffffc90000063b48
    RBP: ffffc90000063e28 R08: ffffffff82d39b28 R09: 0000000000009ffb
    R10: 0000000000000175 R11: ffffffff82d09b40 R12: ffff8880049598e8
    R13: 0000000000000001 R14: dead000000000100 R15: ffffc90000045000
    FS:  0000000000000000(0000) GS:ffff888007a00000(0000) knlGS:0000000000000000
    CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
    CR2: 000000000d406b60 CR3: 000000000483e000 CR4: 00000000000006f0
    Call Trace:
     <TASK>
     ? __warn+0x83/0x130
     ? unregister_netdevice_many_notify+0x8d9/0x930
     ? report_bug+0x18e/0x1a0
     ? handle_bug+0x54/0x90
     ? exc_invalid_op+0x18/0x70
     ? asm_exc_invalid_op+0x1a/0x20
     ? unregister_netdevice_many_notify+0x8d9/0x930
     ? bond_net_exit_batch_rtnl+0x5c/0x90
     cleanup_net+0x237/0x3d0
     process_one_work+0x163/0x390
     worker_thread+0x293/0x3b0
     ? __pfx_worker_thread+0x10/0x10
     kthread+0xec/0x1e0
     ? __pfx_kthread+0x10/0x10
     ? __pfx_kthread+0x10/0x10
     ret_from_fork+0x2f/0x50
     ? __pfx_kthread+0x10/0x10
     ret_from_fork_asm+0x1a/0x30
     </TASK>
    ---[ end trace 0000000000000000 ]---

Fixes: 9e2ee5c7e7c3 ("net, bonding: Add XDP support to the bonding driver")
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Acked-by: Jussi Maki <joamaki@gmail.com>
Reviewed-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/bonding/bond_main.c    | 8 ++++----
 drivers/net/bonding/bond_options.c | 3 +++
 include/net/bonding.h              | 1 +
 3 files changed, 8 insertions(+), 4 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index b21456e759fdc..2449f5b65cdb9 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -323,9 +323,9 @@ static bool bond_sk_check(struct bonding *bond)
 	}
 }
 
-static bool bond_xdp_check(struct bonding *bond)
+bool bond_xdp_check(struct bonding *bond, int mode)
 {
-	switch (BOND_MODE(bond)) {
+	switch (mode) {
 	case BOND_MODE_ROUNDROBIN:
 	case BOND_MODE_ACTIVEBACKUP:
 		return true;
@@ -1939,7 +1939,7 @@ void bond_xdp_set_features(struct net_device *bond_dev)
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond) || !bond_has_slaves(bond)) {
+	if (!bond_xdp_check(bond, BOND_MODE(bond)) || !bond_has_slaves(bond)) {
 		xdp_clear_features_flag(bond_dev);
 		return;
 	}
@@ -5704,7 +5704,7 @@ static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 
 	ASSERT_RTNL();
 
-	if (!bond_xdp_check(bond)) {
+	if (!bond_xdp_check(bond, BOND_MODE(bond))) {
 		BOND_NL_ERR(dev, extack,
 			    "No native XDP support for the current bonding mode");
 		return -EOPNOTSUPP;
diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index d1b095af253bd..91893c29b8995 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -868,6 +868,9 @@ static bool bond_set_xfrm_features(struct bonding *bond)
 static int bond_option_mode_set(struct bonding *bond,
 				const struct bond_opt_value *newval)
 {
+	if (bond->xdp_prog && !bond_xdp_check(bond, newval->value))
+		return -EOPNOTSUPP;
+
 	if (!bond_mode_uses_arp(newval->value)) {
 		if (bond->params.arp_interval) {
 			netdev_dbg(bond->dev, "%s mode is incompatible with arp monitoring, start mii monitoring\n",
diff --git a/include/net/bonding.h b/include/net/bonding.h
index de965c24dde0b..d018a299bb88c 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -703,6 +703,7 @@ void bond_debug_register(struct bonding *bond);
 void bond_debug_unregister(struct bonding *bond);
 void bond_debug_reregister(struct bonding *bond);
 const char *bond_mode_name(int mode);
+bool bond_xdp_check(struct bonding *bond, int mode);
 void bond_setup(struct net_device *bond_dev);
 unsigned int bond_get_num_tx_queues(void);
 int bond_netlink_init(void);

From bdf632c1e06eb524d26c52b747a5065991bba08a Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 21 Mar 2025 15:48:32 +0900
Subject: [PATCH 2730/2753] virtio_net: Split struct virtio_net_rss_config

struct virtio_net_rss_config was less useful in actual code because of a
flexible array placed in the middle. Add new structures that split it
into two to avoid having a flexible array in the middle.

Suggested-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/uapi/linux/virtio_net.h | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index ac9174717ef13..963540deae66a 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -327,6 +327,19 @@ struct virtio_net_rss_config {
 	__u8 hash_key_data[/* hash_key_length */];
 };
 
+struct virtio_net_rss_config_hdr {
+	__le32 hash_types;
+	__le16 indirection_table_mask;
+	__le16 unclassified_queue;
+	__le16 indirection_table[/* 1 + indirection_table_mask */];
+};
+
+struct virtio_net_rss_config_trailer {
+	__le16 max_tx_vq;
+	__u8 hash_key_length;
+	__u8 hash_key_data[/* hash_key_length */];
+};
+
  #define VIRTIO_NET_CTRL_MQ_RSS_CONFIG          1
 
 /*

From 91df9d78b435b9affbafafeefba0493eb4bf9b53 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 21 Mar 2025 15:48:33 +0900
Subject: [PATCH 2731/2753] virtio_net: Fix endian with virtio_net_ctrl_rss

Mark the fields of struct virtio_net_ctrl_rss as little endian as
they are in struct virtio_net_rss_config, which it follows.

Fixes: c7114b1249fa ("drivers/net/virtio_net: Added basic RSS support.")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/virtio_net.c | 30 +++++++++++++++---------------
 1 file changed, 15 insertions(+), 15 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 34cec2b11b74f..65e1ef77a1a91 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -368,15 +368,15 @@ struct receive_queue {
  */
 #define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
 struct virtio_net_ctrl_rss {
-	u32 hash_types;
-	u16 indirection_table_mask;
-	u16 unclassified_queue;
-	u16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */
-	u16 max_tx_vq;
+	__le32 hash_types;
+	__le16 indirection_table_mask;
+	__le16 unclassified_queue;
+	__le16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */
+	__le16 max_tx_vq;
 	u8 hash_key_length;
 	u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
 
-	u16 *indirection_table;
+	__le16 *indirection_table;
 };
 
 /* Control VQ buffers: protected by the rtnl lock */
@@ -3638,9 +3638,9 @@ static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pair
 
 	for (; i < vi->rss_indir_table_size; ++i) {
 		indir_val = ethtool_rxfh_indir_default(i, queue_pairs);
-		vi->rss.indirection_table[i] = indir_val;
+		vi->rss.indirection_table[i] = cpu_to_le16(indir_val);
 	}
-	vi->rss.max_tx_vq = queue_pairs;
+	vi->rss.max_tx_vq = cpu_to_le16(queue_pairs);
 }
 
 static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
@@ -4159,10 +4159,10 @@ static bool virtnet_commit_rss_command(struct virtnet_info *vi)
 
 static void virtnet_init_default_rss(struct virtnet_info *vi)
 {
-	vi->rss.hash_types = vi->rss_hash_types_supported;
+	vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_supported);
 	vi->rss_hash_types_saved = vi->rss_hash_types_supported;
 	vi->rss.indirection_table_mask = vi->rss_indir_table_size
-						? vi->rss_indir_table_size - 1 : 0;
+						? cpu_to_le16(vi->rss_indir_table_size - 1) : 0;
 	vi->rss.unclassified_queue = 0;
 
 	virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs);
@@ -4280,7 +4280,7 @@ static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *
 
 	if (new_hashtypes != vi->rss_hash_types_saved) {
 		vi->rss_hash_types_saved = new_hashtypes;
-		vi->rss.hash_types = vi->rss_hash_types_saved;
+		vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		if (vi->dev->features & NETIF_F_RXHASH)
 			return virtnet_commit_rss_command(vi);
 	}
@@ -5460,7 +5460,7 @@ static int virtnet_get_rxfh(struct net_device *dev,
 
 	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			rxfh->indir[i] = vi->rss.indirection_table[i];
+			rxfh->indir[i] = le16_to_cpu(vi->rss.indirection_table[i]);
 	}
 
 	if (rxfh->key)
@@ -5488,7 +5488,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
 			return -EOPNOTSUPP;
 
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			vi->rss.indirection_table[i] = rxfh->indir[i];
+			vi->rss.indirection_table[i] = cpu_to_le16(rxfh->indir[i]);
 		update = true;
 	}
 
@@ -6109,9 +6109,9 @@ static int virtnet_set_features(struct net_device *dev,
 
 	if ((dev->features ^ features) & NETIF_F_RXHASH) {
 		if (features & NETIF_F_RXHASH)
-			vi->rss.hash_types = vi->rss_hash_types_saved;
+			vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		else
-			vi->rss.hash_types = VIRTIO_NET_HASH_REPORT_NONE;
+			vi->rss.hash_types = cpu_to_le32(VIRTIO_NET_HASH_REPORT_NONE);
 
 		if (!virtnet_commit_rss_command(vi))
 			return -EINVAL;

From 221ac0f9fa0c0b0bafebef759244d07419fb3d51 Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 21 Mar 2025 15:48:34 +0900
Subject: [PATCH 2732/2753] virtio_net: Use new RSS config structs

The new RSS configuration structures allow easily constructing data for
VIRTIO_NET_CTRL_MQ_RSS_CONFIG as they strictly follow the order of data
for the command.

Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/virtio_net.c | 117 ++++++++++++++-------------------------
 1 file changed, 43 insertions(+), 74 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 65e1ef77a1a91..e46241c6fdabd 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -360,24 +360,7 @@ struct receive_queue {
 	struct xdp_buff **xsk_buffs;
 };
 
-/* This structure can contain rss message with maximum settings for indirection table and keysize
- * Note, that default structure that describes RSS configuration virtio_net_rss_config
- * contains same info but can't handle table values.
- * In any case, structure would be passed to virtio hw through sg_buf split by parts
- * because table sizes may be differ according to the device configuration.
- */
 #define VIRTIO_NET_RSS_MAX_KEY_SIZE     40
-struct virtio_net_ctrl_rss {
-	__le32 hash_types;
-	__le16 indirection_table_mask;
-	__le16 unclassified_queue;
-	__le16 hash_cfg_reserved; /* for HASH_CONFIG (see virtio_net_hash_config for details) */
-	__le16 max_tx_vq;
-	u8 hash_key_length;
-	u8 key[VIRTIO_NET_RSS_MAX_KEY_SIZE];
-
-	__le16 *indirection_table;
-};
 
 /* Control VQ buffers: protected by the rtnl lock */
 struct control_buf {
@@ -421,7 +404,9 @@ struct virtnet_info {
 	u16 rss_indir_table_size;
 	u32 rss_hash_types_supported;
 	u32 rss_hash_types_saved;
-	struct virtio_net_ctrl_rss rss;
+	struct virtio_net_rss_config_hdr *rss_hdr;
+	struct virtio_net_rss_config_trailer rss_trailer;
+	u8 rss_hash_key_data[VIRTIO_NET_RSS_MAX_KEY_SIZE];
 
 	/* Has control virtqueue */
 	bool has_cvq;
@@ -523,23 +508,16 @@ enum virtnet_xmit_type {
 	VIRTNET_XMIT_TYPE_XSK,
 };
 
-static int rss_indirection_table_alloc(struct virtio_net_ctrl_rss *rss, u16 indir_table_size)
+static size_t virtnet_rss_hdr_size(const struct virtnet_info *vi)
 {
-	if (!indir_table_size) {
-		rss->indirection_table = NULL;
-		return 0;
-	}
+	u16 indir_table_size = vi->has_rss ? vi->rss_indir_table_size : 1;
 
-	rss->indirection_table = kmalloc_array(indir_table_size, sizeof(u16), GFP_KERNEL);
-	if (!rss->indirection_table)
-		return -ENOMEM;
-
-	return 0;
+	return struct_size(vi->rss_hdr, indirection_table, indir_table_size);
 }
 
-static void rss_indirection_table_free(struct virtio_net_ctrl_rss *rss)
+static size_t virtnet_rss_trailer_size(const struct virtnet_info *vi)
 {
-	kfree(rss->indirection_table);
+	return struct_size(&vi->rss_trailer, hash_key_data, vi->rss_key_size);
 }
 
 /* We use the last two bits of the pointer to distinguish the xmit type. */
@@ -3638,15 +3616,16 @@ static void virtnet_rss_update_by_qpairs(struct virtnet_info *vi, u16 queue_pair
 
 	for (; i < vi->rss_indir_table_size; ++i) {
 		indir_val = ethtool_rxfh_indir_default(i, queue_pairs);
-		vi->rss.indirection_table[i] = cpu_to_le16(indir_val);
+		vi->rss_hdr->indirection_table[i] = cpu_to_le16(indir_val);
 	}
-	vi->rss.max_tx_vq = cpu_to_le16(queue_pairs);
+	vi->rss_trailer.max_tx_vq = cpu_to_le16(queue_pairs);
 }
 
 static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 {
 	struct virtio_net_ctrl_mq *mq __free(kfree) = NULL;
-	struct virtio_net_ctrl_rss old_rss;
+	struct virtio_net_rss_config_hdr *old_rss_hdr;
+	struct virtio_net_rss_config_trailer old_rss_trailer;
 	struct net_device *dev = vi->dev;
 	struct scatterlist sg;
 
@@ -3661,24 +3640,28 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	 * update (VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET below) and return directly.
 	 */
 	if (vi->has_rss && !netif_is_rxfh_configured(dev)) {
-		memcpy(&old_rss, &vi->rss, sizeof(old_rss));
-		if (rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size)) {
-			vi->rss.indirection_table = old_rss.indirection_table;
+		old_rss_hdr = vi->rss_hdr;
+		old_rss_trailer = vi->rss_trailer;
+		vi->rss_hdr = kzalloc(virtnet_rss_hdr_size(vi), GFP_KERNEL);
+		if (!vi->rss_hdr) {
+			vi->rss_hdr = old_rss_hdr;
 			return -ENOMEM;
 		}
 
+		*vi->rss_hdr = *old_rss_hdr;
 		virtnet_rss_update_by_qpairs(vi, queue_pairs);
 
 		if (!virtnet_commit_rss_command(vi)) {
 			/* restore ctrl_rss if commit_rss_command failed */
-			rss_indirection_table_free(&vi->rss);
-			memcpy(&vi->rss, &old_rss, sizeof(old_rss));
+			kfree(vi->rss_hdr);
+			vi->rss_hdr = old_rss_hdr;
+			vi->rss_trailer = old_rss_trailer;
 
 			dev_warn(&dev->dev, "Fail to set num of queue pairs to %d, because committing RSS failed\n",
 				 queue_pairs);
 			return -EINVAL;
 		}
-		rss_indirection_table_free(&old_rss);
+		kfree(old_rss_hdr);
 		goto succ;
 	}
 
@@ -4121,28 +4104,12 @@ static int virtnet_set_ringparam(struct net_device *dev,
 static bool virtnet_commit_rss_command(struct virtnet_info *vi)
 {
 	struct net_device *dev = vi->dev;
-	struct scatterlist sgs[4];
-	unsigned int sg_buf_size;
+	struct scatterlist sgs[2];
 
 	/* prepare sgs */
-	sg_init_table(sgs, 4);
-
-	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, hash_cfg_reserved);
-	sg_set_buf(&sgs[0], &vi->rss, sg_buf_size);
-
-	if (vi->has_rss) {
-		sg_buf_size = sizeof(uint16_t) * vi->rss_indir_table_size;
-		sg_set_buf(&sgs[1], vi->rss.indirection_table, sg_buf_size);
-	} else {
-		sg_set_buf(&sgs[1], &vi->rss.hash_cfg_reserved, sizeof(uint16_t));
-	}
-
-	sg_buf_size = offsetof(struct virtio_net_ctrl_rss, key)
-			- offsetof(struct virtio_net_ctrl_rss, max_tx_vq);
-	sg_set_buf(&sgs[2], &vi->rss.max_tx_vq, sg_buf_size);
-
-	sg_buf_size = vi->rss_key_size;
-	sg_set_buf(&sgs[3], vi->rss.key, sg_buf_size);
+	sg_init_table(sgs, 2);
+	sg_set_buf(&sgs[0], vi->rss_hdr, virtnet_rss_hdr_size(vi));
+	sg_set_buf(&sgs[1], &vi->rss_trailer, virtnet_rss_trailer_size(vi));
 
 	if (!virtnet_send_command(vi, VIRTIO_NET_CTRL_MQ,
 				  vi->has_rss ? VIRTIO_NET_CTRL_MQ_RSS_CONFIG
@@ -4159,17 +4126,17 @@ static bool virtnet_commit_rss_command(struct virtnet_info *vi)
 
 static void virtnet_init_default_rss(struct virtnet_info *vi)
 {
-	vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_supported);
+	vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_supported);
 	vi->rss_hash_types_saved = vi->rss_hash_types_supported;
-	vi->rss.indirection_table_mask = vi->rss_indir_table_size
+	vi->rss_hdr->indirection_table_mask = vi->rss_indir_table_size
 						? cpu_to_le16(vi->rss_indir_table_size - 1) : 0;
-	vi->rss.unclassified_queue = 0;
+	vi->rss_hdr->unclassified_queue = 0;
 
 	virtnet_rss_update_by_qpairs(vi, vi->curr_queue_pairs);
 
-	vi->rss.hash_key_length = vi->rss_key_size;
+	vi->rss_trailer.hash_key_length = vi->rss_key_size;
 
-	netdev_rss_key_fill(vi->rss.key, vi->rss_key_size);
+	netdev_rss_key_fill(vi->rss_hash_key_data, vi->rss_key_size);
 }
 
 static void virtnet_get_hashflow(const struct virtnet_info *vi, struct ethtool_rxnfc *info)
@@ -4280,7 +4247,7 @@ static bool virtnet_set_hashflow(struct virtnet_info *vi, struct ethtool_rxnfc *
 
 	if (new_hashtypes != vi->rss_hash_types_saved) {
 		vi->rss_hash_types_saved = new_hashtypes;
-		vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_saved);
+		vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		if (vi->dev->features & NETIF_F_RXHASH)
 			return virtnet_commit_rss_command(vi);
 	}
@@ -5460,11 +5427,11 @@ static int virtnet_get_rxfh(struct net_device *dev,
 
 	if (rxfh->indir) {
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			rxfh->indir[i] = le16_to_cpu(vi->rss.indirection_table[i]);
+			rxfh->indir[i] = le16_to_cpu(vi->rss_hdr->indirection_table[i]);
 	}
 
 	if (rxfh->key)
-		memcpy(rxfh->key, vi->rss.key, vi->rss_key_size);
+		memcpy(rxfh->key, vi->rss_hash_key_data, vi->rss_key_size);
 
 	rxfh->hfunc = ETH_RSS_HASH_TOP;
 
@@ -5488,7 +5455,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
 			return -EOPNOTSUPP;
 
 		for (i = 0; i < vi->rss_indir_table_size; ++i)
-			vi->rss.indirection_table[i] = cpu_to_le16(rxfh->indir[i]);
+			vi->rss_hdr->indirection_table[i] = cpu_to_le16(rxfh->indir[i]);
 		update = true;
 	}
 
@@ -5500,7 +5467,7 @@ static int virtnet_set_rxfh(struct net_device *dev,
 		if (!vi->has_rss && !vi->has_rss_hash_report)
 			return -EOPNOTSUPP;
 
-		memcpy(vi->rss.key, rxfh->key, vi->rss_key_size);
+		memcpy(vi->rss_hash_key_data, rxfh->key, vi->rss_key_size);
 		update = true;
 	}
 
@@ -6109,9 +6076,9 @@ static int virtnet_set_features(struct net_device *dev,
 
 	if ((dev->features ^ features) & NETIF_F_RXHASH) {
 		if (features & NETIF_F_RXHASH)
-			vi->rss.hash_types = cpu_to_le32(vi->rss_hash_types_saved);
+			vi->rss_hdr->hash_types = cpu_to_le32(vi->rss_hash_types_saved);
 		else
-			vi->rss.hash_types = cpu_to_le32(VIRTIO_NET_HASH_REPORT_NONE);
+			vi->rss_hdr->hash_types = cpu_to_le32(VIRTIO_NET_HASH_REPORT_NONE);
 
 		if (!virtnet_commit_rss_command(vi))
 			return -EINVAL;
@@ -6801,9 +6768,11 @@ static int virtnet_probe(struct virtio_device *vdev)
 			virtio_cread16(vdev, offsetof(struct virtio_net_config,
 				rss_max_indirection_table_length));
 	}
-	err = rss_indirection_table_alloc(&vi->rss, vi->rss_indir_table_size);
-	if (err)
+	vi->rss_hdr = kzalloc(virtnet_rss_hdr_size(vi), GFP_KERNEL);
+	if (!vi->rss_hdr) {
+		err = -ENOMEM;
 		goto free;
+	}
 
 	if (vi->has_rss || vi->has_rss_hash_report) {
 		vi->rss_key_size =
@@ -7082,7 +7051,7 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
-	rss_indirection_table_free(&vi->rss);
+	kfree(vi->rss_hdr);
 
 	free_netdev(vi->dev);
 }

From 6ce537be99fd1f644181833857edcba382b7375f Mon Sep 17 00:00:00 2001
From: Akihiko Odaki <akihiko.odaki@daynix.com>
Date: Fri, 21 Mar 2025 15:48:35 +0900
Subject: [PATCH 2733/2753] virtio_net: Allocate rss_hdr with devres

virtnet_probe() lacks the code to free rss_hdr in its error path.
Allocate rss_hdr with devres so that it will be automatically freed.

Fixes: 86a48a00efdf ("virtio_net: Support dynamic rss indirection table size")
Signed-off-by: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/virtio_net.c | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index e46241c6fdabd..aac5a5184ba95 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -3642,7 +3642,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 	if (vi->has_rss && !netif_is_rxfh_configured(dev)) {
 		old_rss_hdr = vi->rss_hdr;
 		old_rss_trailer = vi->rss_trailer;
-		vi->rss_hdr = kzalloc(virtnet_rss_hdr_size(vi), GFP_KERNEL);
+		vi->rss_hdr = devm_kzalloc(&dev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL);
 		if (!vi->rss_hdr) {
 			vi->rss_hdr = old_rss_hdr;
 			return -ENOMEM;
@@ -3653,7 +3653,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 
 		if (!virtnet_commit_rss_command(vi)) {
 			/* restore ctrl_rss if commit_rss_command failed */
-			kfree(vi->rss_hdr);
+			devm_kfree(&dev->dev, vi->rss_hdr);
 			vi->rss_hdr = old_rss_hdr;
 			vi->rss_trailer = old_rss_trailer;
 
@@ -3661,7 +3661,7 @@ static int virtnet_set_queues(struct virtnet_info *vi, u16 queue_pairs)
 				 queue_pairs);
 			return -EINVAL;
 		}
-		kfree(old_rss_hdr);
+		devm_kfree(&dev->dev, old_rss_hdr);
 		goto succ;
 	}
 
@@ -6768,7 +6768,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 			virtio_cread16(vdev, offsetof(struct virtio_net_config,
 				rss_max_indirection_table_length));
 	}
-	vi->rss_hdr = kzalloc(virtnet_rss_hdr_size(vi), GFP_KERNEL);
+	vi->rss_hdr = devm_kzalloc(&vdev->dev, virtnet_rss_hdr_size(vi), GFP_KERNEL);
 	if (!vi->rss_hdr) {
 		err = -ENOMEM;
 		goto free;
@@ -7051,8 +7051,6 @@ static void virtnet_remove(struct virtio_device *vdev)
 
 	remove_vq_common(vi);
 
-	kfree(vi->rss_hdr);
-
 	free_netdev(vi->dev);
 }
 

From 5bf42c3f3623015e1f57086ac9ef545d191900b6 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Fri, 21 Mar 2025 13:43:11 +0530
Subject: [PATCH 2734/2753] net: ti: prueth: Fix kernel warning while bringing
 down network interface

During network interface initialization, the NIC driver needs to register
its Rx queue with the XDP, to ensure the incoming XDP buffer carries a
pointer reference to this info and is stored inside xdp_rxq_info.

While this struct isn't tied to XDP prog, if there are any changes in
Rx queue, the NIC driver needs to stop the Rx queue by unregistering
with XDP before purging and reallocating memory. Drop page_pool destroy
during Rx channel reset as this is already handled by XDP during
xdp_rxq_info_unreg (Rx queue unregister), failing to do will cause the
following warning:

warning logs: https://gist.github.com/MeghanaMalladiTI/eb627e5dc8de24e42d7d46572c13e576

Fixes: 46eeb90f03e0 ("net: ti: icssg-prueth: Use page_pool API for RX buffer allocation")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index df5da7a98abf0..afa01c22dee89 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -1216,9 +1216,6 @@ void prueth_reset_rx_chan(struct prueth_rx_chn *chn,
 					  prueth_rx_cleanup, !!i);
 	if (disable)
 		k3_udma_glue_disable_rx_chn(chn->rx_chn);
-
-	page_pool_destroy(chn->pg_pool);
-	chn->pg_pool = NULL;
 }
 EXPORT_SYMBOL_GPL(prueth_reset_rx_chan);
 

From 1b372836b9b78b2eb6cb9c0360951f6c64ddde84 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Fri, 21 Mar 2025 13:43:12 +0530
Subject: [PATCH 2735/2753] net: ti: prueth: Fix possible NULL pointer
 dereference inside emac_xmit_xdp_frame()

There is an error check inside emac_xmit_xdp_frame() function which
is called when the driver wants to transmit XDP frame, to check if
the allocated tx descriptor is NULL, if true to exit and return
ICSSG_XDP_CONSUMED implying failure in transmission.

In this case trying to free a descriptor which is NULL will result
in kernel crash due to NULL pointer dereference. Fix this error handling
and increase netdev tx_dropped stats in the caller of this function
if the function returns ICSSG_XDP_CONSUMED.

Fixes: 62aa3246f462 ("net: ti: icssg-prueth: Add XDP support")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index afa01c22dee89..f0224576b95fd 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -584,7 +584,7 @@ u32 emac_xmit_xdp_frame(struct prueth_emac *emac,
 	first_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
 	if (!first_desc) {
 		netdev_dbg(ndev, "xdp tx: failed to allocate descriptor\n");
-		goto drop_free_descs;	/* drop */
+		return ICSSG_XDP_CONSUMED;	/* drop */
 	}
 
 	if (page) { /* already DMA mapped by page_pool */
@@ -672,8 +672,10 @@ static u32 emac_run_xdp(struct prueth_emac *emac, struct xdp_buff *xdp,
 
 		q_idx = smp_processor_id() % emac->tx_ch_num;
 		result = emac_xmit_xdp_frame(emac, xdpf, page, q_idx);
-		if (result == ICSSG_XDP_CONSUMED)
+		if (result == ICSSG_XDP_CONSUMED) {
+			ndev->stats.tx_dropped++;
 			goto drop;
+		}
 
 		dev_sw_netstats_rx_add(ndev, xdpf->len);
 		return result;

From a51d94c4e61f8f60729bf9e4bd022a15de910de2 Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Fri, 21 Mar 2025 13:43:13 +0530
Subject: [PATCH 2736/2753] net: ti: icss-iep: Fix possible NULL pointer
 dereference for perout request

Whenever there is a perout request from the user application,
kernel receives req structure containing the configuration info
for that req. Add NULL pointer handling for perout request if
that req struct points to NULL.

Fixes: e5b456a14215 ("net: ti: icss-iep: Add pwidth configuration for perout signal")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index b4a34c57b7b48..aeebdc4c121e6 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -498,6 +498,10 @@ static int icss_iep_perout_enable(struct icss_iep *iep,
 {
 	int ret = 0;
 
+	/* Return error if the req is NULL */
+	if (!req)
+		return -EINVAL;
+
 	/* Reject requests with unsupported flags */
 	if (req->flags & ~(PTP_PEROUT_DUTY_CYCLE |
 			  PTP_PEROUT_PHASE))

From 979366cf9ba3b615086ea3faee6d65b6c428a4a1 Mon Sep 17 00:00:00 2001
From: Wang Liang <wangliang74@huawei.com>
Date: Fri, 21 Mar 2025 17:03:53 +0800
Subject: [PATCH 2737/2753] net: fix NULL pointer dereference in l3mdev_l3_rcv

When delete l3s ipvlan:

    ip link del link eth0 ipvlan1 type ipvlan mode l3s

This may cause a null pointer dereference:

    Call trace:
     ip_rcv_finish+0x48/0xd0
     ip_rcv+0x5c/0x100
     __netif_receive_skb_one_core+0x64/0xb0
     __netif_receive_skb+0x20/0x80
     process_backlog+0xb4/0x204
     napi_poll+0xe8/0x294
     net_rx_action+0xd8/0x22c
     __do_softirq+0x12c/0x354

This is because l3mdev_l3_rcv() visit dev->l3mdev_ops after
ipvlan_l3s_unregister() assign the dev->l3mdev_ops to NULL. The process
like this:

    (CPU1)                     | (CPU2)
    l3mdev_l3_rcv()            |
      check dev->priv_flags:   |
        master = skb->dev;     |
                               |
                               | ipvlan_l3s_unregister()
                               |   set dev->priv_flags
                               |   dev->l3mdev_ops = NULL;
                               |
      visit master->l3mdev_ops |

To avoid this by do not set dev->l3mdev_ops when unregister l3s ipvlan.

Suggested-by: David Ahern <dsahern@kernel.org>
Fixes: c675e06a98a4 ("ipvlan: decouple l3s mode dependencies from other modes")
Signed-off-by: Wang Liang <wangliang74@huawei.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ipvlan/ipvlan_l3s.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/ipvlan/ipvlan_l3s.c b/drivers/net/ipvlan/ipvlan_l3s.c
index b4ef386bdb1ba..7c017fe35522a 100644
--- a/drivers/net/ipvlan/ipvlan_l3s.c
+++ b/drivers/net/ipvlan/ipvlan_l3s.c
@@ -226,5 +226,4 @@ void ipvlan_l3s_unregister(struct ipvl_port *port)
 
 	dev->priv_flags &= ~IFF_L3MDEV_RX_HANDLER;
 	ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
-	dev->l3mdev_ops = NULL;
 }

From 9f378307e222cc1ae01d989134dc1d285dd933a0 Mon Sep 17 00:00:00 2001
From: Tobias Waldekranz <tobias@waldekranz.com>
Date: Fri, 21 Mar 2025 10:03:23 +0100
Subject: [PATCH 2738/2753] net: mvpp2: Prevent parser TCAM memory corruption

Protect the parser TCAM/SRAM memory, and the cached (shadow) SRAM
information, from concurrent modifications.

Both the TCAM and SRAM tables are indirectly accessed by configuring
an index register that selects the row to read or write to. This means
that operations must be atomic in order to, e.g., avoid spreading
writes across multiple rows. Since the shadow SRAM array is used to
find free rows in the hardware table, it must also be protected in
order to avoid TOCTOU errors where multiple cores allocate the same
row.

This issue was detected in a situation where `mvpp2_set_rx_mode()` ran
concurrently on two CPUs. In this particular case the
MVPP2_PE_MAC_UC_PROMISCUOUS entry was corrupted, causing the
classifier unit to drop all incoming unicast - indicated by the
`rx_classifier_drops` counter.

Fixes: 3f518509dedc ("ethernet: Add new driver for Marvell Armada 375 network unit")
Signed-off-by: Tobias Waldekranz <tobias@waldekranz.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/marvell/mvpp2/mvpp2.h    |   3 +
 .../net/ethernet/marvell/mvpp2/mvpp2_main.c   |   3 +-
 .../net/ethernet/marvell/mvpp2/mvpp2_prs.c    | 131 +++++++++++++-----
 3 files changed, 105 insertions(+), 32 deletions(-)

diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
index 44fe9b68d1c22..a804a256dd07d 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h
@@ -1113,6 +1113,9 @@ struct mvpp2 {
 
 	/* Spinlocks for CM3 shared memory configuration */
 	spinlock_t mss_spinlock;
+
+	/* Spinlock for shared parser memory */
+	spinlock_t prs_spinlock;
 };
 
 struct mvpp2_pcpu_stats {
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
index 54a235366a01b..2ee67283a877c 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
@@ -7724,8 +7724,9 @@ static int mvpp2_probe(struct platform_device *pdev)
 	if (mvpp2_read(priv, MVPP2_VER_ID_REG) == MVPP2_VER_PP23)
 		priv->hw_version = MVPP23;
 
-	/* Init mss lock */
+	/* Init locks for shared packet processor resources */
 	spin_lock_init(&priv->mss_spinlock);
+	spin_lock_init(&priv->prs_spinlock);
 
 	/* Initialize network controller */
 	err = mvpp2_init(pdev, priv);
diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
index 9af22f497a40f..b90b4f677ce79 100644
--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
+++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_prs.c
@@ -43,8 +43,8 @@ static int mvpp2_prs_hw_write(struct mvpp2 *priv, struct mvpp2_prs_entry *pe)
 }
 
 /* Initialize tcam entry from hw */
-int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
-			   int tid)
+static int mvpp2_prs_init_from_hw_unlocked(struct mvpp2 *priv,
+					   struct mvpp2_prs_entry *pe, int tid)
 {
 	int i;
 
@@ -73,6 +73,18 @@ int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
 	return 0;
 }
 
+int mvpp2_prs_init_from_hw(struct mvpp2 *priv, struct mvpp2_prs_entry *pe,
+			   int tid)
+{
+	int err;
+
+	spin_lock_bh(&priv->prs_spinlock);
+	err = mvpp2_prs_init_from_hw_unlocked(priv, pe, tid);
+	spin_unlock_bh(&priv->prs_spinlock);
+
+	return err;
+}
+
 /* Invalidate tcam hw entry */
 static void mvpp2_prs_hw_inv(struct mvpp2 *priv, int index)
 {
@@ -374,7 +386,7 @@ static int mvpp2_prs_flow_find(struct mvpp2 *priv, int flow)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_FLOWS)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 		bits = mvpp2_prs_sram_ai_get(&pe);
 
 		/* Sram store classification lookup ID in AI bits [5:0] */
@@ -441,7 +453,7 @@ static void mvpp2_prs_mac_drop_all_set(struct mvpp2 *priv, int port, bool add)
 
 	if (priv->prs_shadow[MVPP2_PE_DROP_ALL].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, MVPP2_PE_DROP_ALL);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, MVPP2_PE_DROP_ALL);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -477,6 +489,8 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 	unsigned int ri;
 	int tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	if (l2_cast == MVPP2_PRS_L2_UNI_CAST) {
 		cast_match = MVPP2_PRS_UCAST_VAL;
 		tid = MVPP2_PE_MAC_UC_PROMISCUOUS;
@@ -489,7 +503,7 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 
 	/* promiscuous mode - Accept unknown unicast or multicast packets */
 	if (priv->prs_shadow[tid].valid) {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	} else {
 		memset(&pe, 0, sizeof(pe));
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -520,6 +534,8 @@ void mvpp2_prs_mac_promisc_set(struct mvpp2 *priv, int port,
 	mvpp2_prs_tcam_port_set(&pe, port, add);
 
 	mvpp2_prs_hw_write(priv, &pe);
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Set entry for dsa packets */
@@ -539,7 +555,7 @@ static void mvpp2_prs_dsa_tag_set(struct mvpp2 *priv, int port, bool add,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -610,7 +626,7 @@ static void mvpp2_prs_dsa_tag_ethertype_set(struct mvpp2 *priv, int port,
 
 	if (priv->prs_shadow[tid].valid) {
 		/* Entry exist - update port only */
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	} else {
 		/* Entry doesn't exist - create new */
 		memset(&pe, 0, sizeof(pe));
@@ -673,7 +689,7 @@ static int mvpp2_prs_vlan_find(struct mvpp2 *priv, unsigned short tpid, int ai)
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid);
 		if (!match)
 			continue;
@@ -726,7 +742,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			if ((ri_bits & MVPP2_PRS_RI_VLAN_MASK) ==
 			    MVPP2_PRS_RI_VLAN_DOUBLE)
@@ -760,7 +776,7 @@ static int mvpp2_prs_vlan_add(struct mvpp2 *priv, unsigned short tpid, int ai,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	}
 	/* Update ports' mask */
 	mvpp2_prs_tcam_port_map_set(&pe, port_map);
@@ -800,7 +816,7 @@ static int mvpp2_prs_double_vlan_find(struct mvpp2 *priv, unsigned short tpid1,
 		    priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VLAN)
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 
 		match = mvpp2_prs_tcam_data_cmp(&pe, 0, tpid1) &&
 			mvpp2_prs_tcam_data_cmp(&pe, 4, tpid2);
@@ -849,7 +865,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 			    priv->prs_shadow[tid_aux].lu != MVPP2_PRS_LU_VLAN)
 				continue;
 
-			mvpp2_prs_init_from_hw(priv, &pe, tid_aux);
+			mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid_aux);
 			ri_bits = mvpp2_prs_sram_ri_get(&pe);
 			ri_bits &= MVPP2_PRS_RI_VLAN_MASK;
 			if (ri_bits == MVPP2_PRS_RI_VLAN_SINGLE ||
@@ -880,7 +896,7 @@ static int mvpp2_prs_double_vlan_add(struct mvpp2 *priv, unsigned short tpid1,
 
 		mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VLAN);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	}
 
 	/* Update ports' mask */
@@ -1941,7 +1957,7 @@ static int mvpp2_prs_vid_range_find(struct mvpp2_port *port, u16 vid, u16 mask)
 		    port->priv->prs_shadow[tid].lu != MVPP2_PRS_LU_VID)
 			continue;
 
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(port->priv, &pe, tid);
 
 		mvpp2_prs_tcam_data_byte_get(&pe, 2, &byte[0], &enable[0]);
 		mvpp2_prs_tcam_data_byte_get(&pe, 3, &byte[1], &enable[1]);
@@ -1970,6 +1986,8 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Scan TCAM and see if entry with this <vid,port> already exist */
 	tid = mvpp2_prs_vid_range_find(port, vid, mask);
 
@@ -1988,8 +2006,10 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 						MVPP2_PRS_VLAN_FILT_MAX_ENTRY);
 
 		/* There isn't room for a new VID filter */
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&priv->prs_spinlock);
 			return tid;
+		}
 
 		mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_VID);
 		pe.index = tid;
@@ -1997,7 +2017,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	}
 
 	/* Enable the current port */
@@ -2019,6 +2039,7 @@ int mvpp2_prs_vid_entry_add(struct mvpp2_port *port, u16 vid)
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2028,15 +2049,16 @@ void mvpp2_prs_vid_entry_remove(struct mvpp2_port *port, u16 vid)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
-	/* Scan TCAM and see if entry with this <vid,port> already exist */
-	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	spin_lock_bh(&priv->prs_spinlock);
 
-	/* No such entry */
-	if (tid < 0)
-		return;
+	/* Invalidate TCAM entry with this <vid,port>, if it exists */
+	tid = mvpp2_prs_vid_range_find(port, vid, 0xfff);
+	if (tid >= 0) {
+		mvpp2_prs_hw_inv(priv, tid);
+		priv->prs_shadow[tid].valid = false;
+	}
 
-	mvpp2_prs_hw_inv(priv, tid);
-	priv->prs_shadow[tid].valid = false;
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove all existing VID filters on this port */
@@ -2045,6 +2067,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 	struct mvpp2 *priv = port->priv;
 	int tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PRS_VID_PORT_FIRST(port->id);
 	     tid <= MVPP2_PRS_VID_PORT_LAST(port->id); tid++) {
 		if (priv->prs_shadow[tid].valid) {
@@ -2052,6 +2076,8 @@ void mvpp2_prs_vid_remove_all(struct mvpp2_port *port)
 			priv->prs_shadow[tid].valid = false;
 		}
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Remove VID filering entry for this port */
@@ -2060,10 +2086,14 @@ void mvpp2_prs_vid_disable_filtering(struct mvpp2_port *port)
 	unsigned int tid = MVPP2_PRS_VID_PORT_DFLT(port->id);
 	struct mvpp2 *priv = port->priv;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	/* Invalidate the guard entry */
 	mvpp2_prs_hw_inv(priv, tid);
 
 	priv->prs_shadow[tid].valid = false;
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Add guard entry that drops packets when no VID is matched on this port */
@@ -2079,6 +2109,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	pe.index = tid;
 
 	reg_val = mvpp2_read(priv, MVPP2_MH_REG(port->id));
@@ -2111,6 +2143,8 @@ void mvpp2_prs_vid_enable_filtering(struct mvpp2_port *port)
 	/* Update shadow table */
 	mvpp2_prs_shadow_set(priv, pe.index, MVPP2_PRS_LU_VID);
 	mvpp2_prs_hw_write(priv, &pe);
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 /* Parser default initialization */
@@ -2217,7 +2251,7 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 		    (priv->prs_shadow[tid].udf != udf_type))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 		entry_pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
 		if (mvpp2_prs_mac_range_equals(&pe, da, mask) &&
@@ -2229,7 +2263,8 @@ mvpp2_prs_mac_da_range_find(struct mvpp2 *priv, int pmap, const u8 *da,
 }
 
 /* Update parser's mac da entry */
-int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+static int mvpp2_prs_mac_da_accept_unlocked(struct mvpp2_port *port,
+					    const u8 *da, bool add)
 {
 	unsigned char mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
 	struct mvpp2 *priv = port->priv;
@@ -2261,7 +2296,7 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 		/* Mask all ports */
 		mvpp2_prs_tcam_port_map_set(&pe, 0);
 	} else {
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_MAC);
@@ -2317,6 +2352,17 @@ int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
 	return 0;
 }
 
+int mvpp2_prs_mac_da_accept(struct mvpp2_port *port, const u8 *da, bool add)
+{
+	int err;
+
+	spin_lock_bh(&port->priv->prs_spinlock);
+	err = mvpp2_prs_mac_da_accept_unlocked(port, da, add);
+	spin_unlock_bh(&port->priv->prs_spinlock);
+
+	return err;
+}
+
 int mvpp2_prs_update_mac_da(struct net_device *dev, const u8 *da)
 {
 	struct mvpp2_port *port = netdev_priv(dev);
@@ -2345,6 +2391,8 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 	unsigned long pmap;
 	int index, tid;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	for (tid = MVPP2_PE_MAC_RANGE_START;
 	     tid <= MVPP2_PE_MAC_RANGE_END; tid++) {
 		unsigned char da[ETH_ALEN], da_mask[ETH_ALEN];
@@ -2354,7 +2402,7 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 		    (priv->prs_shadow[tid].udf != MVPP2_PRS_UDF_MAC_DEF))
 			continue;
 
-		mvpp2_prs_init_from_hw(priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(priv, &pe, tid);
 
 		pmap = mvpp2_prs_tcam_port_map_get(&pe);
 
@@ -2375,14 +2423,17 @@ void mvpp2_prs_mac_del_all(struct mvpp2_port *port)
 			continue;
 
 		/* Remove entry from TCAM */
-		mvpp2_prs_mac_da_accept(port, da, false);
+		mvpp2_prs_mac_da_accept_unlocked(port, da, false);
 	}
+
+	spin_unlock_bh(&priv->prs_spinlock);
 }
 
 int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 {
 	switch (type) {
 	case MVPP2_TAG_TYPE_EDSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to EDSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
@@ -2393,9 +2444,11 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_DSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_DSA:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Add port to DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, true,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2406,10 +2459,12 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	case MVPP2_TAG_TYPE_MH:
 	case MVPP2_TAG_TYPE_NONE:
+		spin_lock_bh(&priv->prs_spinlock);
 		/* Remove port form EDSA and DSA entries */
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_DSA);
@@ -2419,6 +2474,7 @@ int mvpp2_prs_tag_mode_set(struct mvpp2 *priv, int port, int type)
 				      MVPP2_PRS_TAGGED, MVPP2_PRS_EDSA);
 		mvpp2_prs_dsa_tag_set(priv, port, false,
 				      MVPP2_PRS_UNTAGGED, MVPP2_PRS_EDSA);
+		spin_unlock_bh(&priv->prs_spinlock);
 		break;
 
 	default:
@@ -2437,11 +2493,15 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	tid = mvpp2_prs_tcam_first_free(priv,
 					MVPP2_PE_LAST_FREE_TID,
 					MVPP2_PE_FIRST_FREE_TID);
-	if (tid < 0)
+	if (tid < 0) {
+		spin_unlock_bh(&priv->prs_spinlock);
 		return tid;
+	}
 
 	pe.index = tid;
 
@@ -2461,6 +2521,7 @@ int mvpp2_prs_add_flow(struct mvpp2 *priv, int flow, u32 ri, u32 ri_mask)
 	mvpp2_prs_tcam_port_map_set(&pe, MVPP2_PRS_PORT_MASK);
 	mvpp2_prs_hw_write(priv, &pe);
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return 0;
 }
 
@@ -2472,6 +2533,8 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 
 	memset(&pe, 0, sizeof(pe));
 
+	spin_lock_bh(&port->priv->prs_spinlock);
+
 	tid = mvpp2_prs_flow_find(port->priv, port->id);
 
 	/* Such entry not exist */
@@ -2480,8 +2543,10 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		tid = mvpp2_prs_tcam_first_free(port->priv,
 						MVPP2_PE_LAST_FREE_TID,
 					       MVPP2_PE_FIRST_FREE_TID);
-		if (tid < 0)
+		if (tid < 0) {
+			spin_unlock_bh(&port->priv->prs_spinlock);
 			return tid;
+		}
 
 		pe.index = tid;
 
@@ -2492,13 +2557,14 @@ int mvpp2_prs_def_flow(struct mvpp2_port *port)
 		/* Update shadow table */
 		mvpp2_prs_shadow_set(port->priv, pe.index, MVPP2_PRS_LU_FLOWS);
 	} else {
-		mvpp2_prs_init_from_hw(port->priv, &pe, tid);
+		mvpp2_prs_init_from_hw_unlocked(port->priv, &pe, tid);
 	}
 
 	mvpp2_prs_tcam_lu_set(&pe, MVPP2_PRS_LU_FLOWS);
 	mvpp2_prs_tcam_port_map_set(&pe, (1 << port->id));
 	mvpp2_prs_hw_write(port->priv, &pe);
 
+	spin_unlock_bh(&port->priv->prs_spinlock);
 	return 0;
 }
 
@@ -2509,11 +2575,14 @@ int mvpp2_prs_hits(struct mvpp2 *priv, int index)
 	if (index > MVPP2_PRS_TCAM_SRAM_SIZE)
 		return -EINVAL;
 
+	spin_lock_bh(&priv->prs_spinlock);
+
 	mvpp2_write(priv, MVPP2_PRS_TCAM_HIT_IDX_REG, index);
 
 	val = mvpp2_read(priv, MVPP2_PRS_TCAM_HIT_CNT_REG);
 
 	val &= MVPP2_PRS_TCAM_HIT_CNT_MASK;
 
+	spin_unlock_bh(&priv->prs_spinlock);
 	return val;
 }

From 8a7b85e334b5917fca3f7462a1b399c63a7ab153 Mon Sep 17 00:00:00 2001
From: luoxuanqiang <luoxuanqiang@kylinos.cn>
Date: Fri, 21 Mar 2025 17:52:00 +0800
Subject: [PATCH 2739/2753] ice: Check VF VSI Pointer Value in
 ice_vc_add_fdir_fltr()

As mentioned in the commit baeb705fd6a7 ("ice: always check VF VSI
pointer values"), we need to perform a null pointer check on the return
value of ice_get_vf_vsi() before using it.

Fixes: 6ebbe97a4881 ("ice: Add a per-VF limit on number of FDIR filters")
Signed-off-by: luoxuanqiang <xuanqiang.luo@linux.dev>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
index 9be4bd717512d..6bd3682e984e2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
@@ -2098,6 +2098,12 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
 	dev = ice_pf_to_dev(pf);
 	vf_vsi = ice_get_vf_vsi(vf);
 
+	if (!vf_vsi) {
+		dev_err(dev, "Can not get FDIR vf_vsi for VF %u\n", vf->vf_id);
+		v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+		goto err_exit;
+	}
+
 #define ICE_VF_MAX_FDIR_FILTERS	128
 	if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
 	    vf->fdir.fdir_fltr_cnt_total >= ICE_VF_MAX_FDIR_FILTERS) {

From 6c4343500c31dfe51d941f483afe8cc23fab500d Mon Sep 17 00:00:00 2001
From: Maxime Chevallier <maxime.chevallier@bootlin.com>
Date: Fri, 21 Mar 2025 11:35:01 +0100
Subject: [PATCH 2740/2753] net: stmmac: Call xpcs_config_eee_mult_fact() only
 when xpcs is present

Some dwmac variants such as dwmac_socfpga don't use xpcs but lynx_pcs.

Don't call xpcs_config_eee_mult_fact() in this case, as this causes a
crash at init :

 Unable to handle kernel NULL pointer dereference at virtual address 00000039 when write

 [...]

 Call trace:
  xpcs_config_eee_mult_fact from stmmac_pcs_setup+0x40/0x10c
  stmmac_pcs_setup from stmmac_dvr_probe+0xc0c/0x1244
  stmmac_dvr_probe from socfpga_dwmac_probe+0x130/0x1bc
  socfpga_dwmac_probe from platform_probe+0x5c/0xb0

Fixes: 060fb27060e8 ("net: stmmac: call xpcs_config_eee_mult_fact()")
Signed-off-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
index 7c0a4046bbe35..836f2848dfeb8 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -524,7 +524,8 @@ int stmmac_pcs_setup(struct net_device *ndev)
 	if (ret)
 		return dev_err_probe(priv->device, ret, "No xPCS found\n");
 
-	xpcs_config_eee_mult_fact(xpcs, priv->plat->mult_fact_100ns);
+	if (xpcs)
+		xpcs_config_eee_mult_fact(xpcs, priv->plat->mult_fact_100ns);
 
 	priv->hw->xpcs = xpcs;
 

From 0a934d64b9b9a6a46ec59f00924a5c38bb503487 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Mar 2025 12:52:52 +0100
Subject: [PATCH 2741/2753] udp_tunnel: properly deal with xfrm gro encap.

The blamed commit below does not take in account that xfrm
can enable GRO over UDP encapsulation without going through
setup_udp_tunnel_sock().

At deletion time such socket will still go through
udp_tunnel_cleanup_gro(), and the failed GRO type lookup will
trigger the reported warning.

Add the GRO accounting for XFRM tunnel when GRO is enabled, and
adjust the known gro types accordingly.

Note that we can't use setup_udp_tunnel_sock() here, as the xfrm
tunnel setup can be "incremental" - e.g. the encapsulation is created
first and GRO is enabled later.

Also we can not allow GRO sk lookup optimization for XFRM tunnels, as
the socket could match the selection criteria at enable time, and
later on the user-space could disconnect/bind it breaking such
criteria.

Reported-by: syzbot+8c469a2260132cd095c1@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=8c469a2260132cd095c1
Fixes: 311b36574ceac ("udp_tunnel: use static call for GRO hooks when possible")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/udp.c         | 5 +++++
 net/ipv4/udp_offload.c | 4 +++-
 2 files changed, 8 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index db606f7e41638..79efbf465fb04 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2903,10 +2903,15 @@ static void set_xfrm_gro_udp_encap_rcv(__u16 encap_type, unsigned short family,
 {
 #ifdef CONFIG_XFRM
 	if (udp_test_bit(GRO_ENABLED, sk) && encap_type == UDP_ENCAP_ESPINUDP) {
+		bool old_enabled = !!udp_sk(sk)->gro_receive;
+
 		if (family == AF_INET)
 			WRITE_ONCE(udp_sk(sk)->gro_receive, xfrm4_gro_udp_encap_rcv);
 		else if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6)
 			WRITE_ONCE(udp_sk(sk)->gro_receive, ipv6_stub->xfrm6_gro_udp_encap_rcv);
+
+		if (!old_enabled && udp_sk(sk)->gro_receive)
+			udp_tunnel_update_gro_rcv(sk, true);
 	}
 #endif
 }
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 088aa8cb8ac0c..02365b818f1af 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -37,9 +37,11 @@ struct udp_tunnel_type_entry {
 	refcount_t count;
 };
 
+/* vxlan, fou and xfrm have 2 different gro_receive hooks each */
 #define UDP_MAX_TUNNEL_TYPES (IS_ENABLED(CONFIG_GENEVE) + \
 			      IS_ENABLED(CONFIG_VXLAN) * 2 + \
-			      IS_ENABLED(CONFIG_NET_FOU) * 2)
+			      IS_ENABLED(CONFIG_NET_FOU) * 2 + \
+			      IS_ENABLED(CONFIG_XFRM) * 2)
 
 DEFINE_STATIC_CALL(udp_tunnel_gro_rcv, dummy_gro_rcv);
 static DEFINE_STATIC_KEY_FALSE(udp_tunnel_static_call);

From 00b5bf23ae18da015a31de5ab4e7ca5a9ab7e017 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Mar 2025 12:52:53 +0100
Subject: [PATCH 2742/2753] udp_tunnel: fix compile warning

Nathan reported that the compiler is not happy to use a zero
size udp_tunnel_gro_types array:

  net/ipv4/udp_offload.c:130:8: warning: array index 0 is past the end of the array (that has type 'struct udp_tunnel_type_entry[0]') [-Warray-bounds]
    130 |                                    udp_tunnel_gro_types[0].gro_receive);
        |                                    ^                    ~
  include/linux/static_call.h:154:42: note: expanded from macro 'static_call_update'
    154 |         typeof(&STATIC_CALL_TRAMP(name)) __F = (func);                  \
        |                                                 ^~~~
  net/ipv4/udp_offload.c:47:1: note: array 'udp_tunnel_gro_types' declared here
     47 | static struct udp_tunnel_type_entry udp_tunnel_gro_types[UDP_MAX_TUNNEL_TYPES];
        | ^
  1 warning generated.

In such (unusual) configuration we should skip entirely the
static call optimization accounting.

Reported-by: syzbot+8c469a2260132cd095c1@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/cover.1741718157.git.pabeni@redhat.com/T/#m6e309a49f04330de81a618c3c166368252ba42e4
Fixes: 311b36574ceac ("udp_tunnel: use static call for GRO hooks when possible")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/udp_offload.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 02365b818f1af..fd2b8e3830beb 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -83,7 +83,7 @@ void udp_tunnel_update_gro_rcv(struct sock *sk, bool add)
 	struct udp_sock *up = udp_sk(sk);
 	int i, old_gro_type_nr;
 
-	if (!up->gro_receive)
+	if (!UDP_MAX_TUNNEL_TYPES || !up->gro_receive)
 		return;
 
 	mutex_lock(&udp_tunnel_gro_type_lock);

From 424e8647e7fd95bce6ffee363b874138d8d0cf3f Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Mar 2025 12:52:54 +0100
Subject: [PATCH 2743/2753] udp_tunnel: fix UaF in GRO accounting

Siyzkaller reported a race in UDP tunnel GRO accounting, leading to
UaF:

BUG: KASAN: slab-use-after-free in udp_tunnel_update_gro_lookup+0x23c/0x2c0 net/ipv4/udp_offload.c:65
Read of size 8 at addr ffff88801235ebe8 by task syz.2.655/7921

CPU: 1 UID: 0 PID: 7921 Comm: syz.2.655 Not tainted 6.14.0-rc6-syzkaller-01313-g23c9ff659140 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2025
Call Trace:
 <TASK>
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0x16e/0x5b0 mm/kasan/report.c:521
 kasan_report+0x143/0x180 mm/kasan/report.c:634
 udp_tunnel_update_gro_lookup+0x23c/0x2c0 net/ipv4/udp_offload.c:65
 sk_common_release+0x71/0x2e0 net/core/sock.c:3896
 inet_release+0x17d/0x200 net/ipv4/af_inet.c:435
 __sock_release net/socket.c:647 [inline]
 sock_release+0x82/0x150 net/socket.c:675
 sock_free drivers/net/wireguard/socket.c:339 [inline]
 wg_socket_reinit+0x215/0x380 drivers/net/wireguard/socket.c:435
 wg_stop+0x59f/0x600 drivers/net/wireguard/device.c:133
 __dev_close_many+0x3a6/0x700 net/core/dev.c:1717
 dev_close_many+0x24e/0x4c0 net/core/dev.c:1742
 unregister_netdevice_many_notify+0x629/0x24f0 net/core/dev.c:11923
 rtnl_delete_link net/core/rtnetlink.c:3512 [inline]
 rtnl_dellink+0x526/0x8c0 net/core/rtnetlink.c:3554
 rtnetlink_rcv_msg+0x791/0xcf0 net/core/rtnetlink.c:6945
 netlink_rcv_skb+0x206/0x480 net/netlink/af_netlink.c:2534
 netlink_unicast_kernel net/netlink/af_netlink.c:1313 [inline]
 netlink_unicast+0x7f6/0x990 net/netlink/af_netlink.c:1339
 netlink_sendmsg+0x8de/0xcb0 net/netlink/af_netlink.c:1883
 sock_sendmsg_nosec net/socket.c:709 [inline]
 __sock_sendmsg+0x221/0x270 net/socket.c:724
 ____sys_sendmsg+0x53a/0x860 net/socket.c:2564
 ___sys_sendmsg net/socket.c:2618 [inline]
 __sys_sendmsg+0x269/0x350 net/socket.c:2650
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f35ab38d169
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f35ac28f038 EFLAGS: 00000246 ORIG_RAX: 000000000000002e
RAX: ffffffffffffffda RBX: 00007f35ab5a6160 RCX: 00007f35ab38d169
RDX: 0000000000000000 RSI: 0000400000000000 RDI: 0000000000000004
RBP: 00007f35ab40e2a0 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000001 R14: 00007f35ab5a6160 R15: 00007ffdddd781b8
 </TASK>

Allocated by task 7770:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 unpoison_slab_object mm/kasan/common.c:319 [inline]
 __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:345
 kasan_slab_alloc include/linux/kasan.h:250 [inline]
 slab_post_alloc_hook mm/slub.c:4115 [inline]
 slab_alloc_node mm/slub.c:4164 [inline]
 kmem_cache_alloc_noprof+0x1d9/0x380 mm/slub.c:4171
 sk_prot_alloc+0x58/0x210 net/core/sock.c:2190
 sk_alloc+0x3e/0x370 net/core/sock.c:2249
 inet_create+0x648/0xea0 net/ipv4/af_inet.c:326
 __sock_create+0x4c0/0xa30 net/socket.c:1539
 sock_create net/socket.c:1597 [inline]
 __sys_socket_create net/socket.c:1634 [inline]
 __sys_socket+0x150/0x3c0 net/socket.c:1681
 __do_sys_socket net/socket.c:1695 [inline]
 __se_sys_socket net/socket.c:1693 [inline]
 __x64_sys_socket+0x7a/0x90 net/socket.c:1693
 do_syscall_x64 arch/x86/entry/common.c:52 [inline]
 do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 7768:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
 kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:576
 poison_slab_object mm/kasan/common.c:247 [inline]
 __kasan_slab_free+0x59/0x70 mm/kasan/common.c:264
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2353 [inline]
 slab_free mm/slub.c:4609 [inline]
 kmem_cache_free+0x195/0x410 mm/slub.c:4711
 sk_prot_free net/core/sock.c:2230 [inline]
 __sk_destruct+0x4fd/0x690 net/core/sock.c:2327
 inet_release+0x17d/0x200 net/ipv4/af_inet.c:435
 __sock_release net/socket.c:647 [inline]
 sock_close+0xbc/0x240 net/socket.c:1389
 __fput+0x3e9/0x9f0 fs/file_table.c:464
 task_work_run+0x24f/0x310 kernel/task_work.c:227
 resume_user_mode_work include/linux/resume_user_mode.h:50 [inline]
 exit_to_user_mode_loop kernel/entry/common.c:114 [inline]
 exit_to_user_mode_prepare include/linux/entry-common.h:329 [inline]
 __syscall_exit_to_user_mode_work kernel/entry/common.c:207 [inline]
 syscall_exit_to_user_mode+0x13f/0x340 kernel/entry/common.c:218
 do_syscall_64+0x100/0x230 arch/x86/entry/common.c:89
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

The buggy address belongs to the object at ffff88801235e4c0
 which belongs to the cache UDP of size 1856
The buggy address is located 1832 bytes inside of
 freed 1856-byte region [ffff88801235e4c0, ffff88801235ec00)

At disposal time, to avoid unconditionally acquiring a spin lock, UDP
tunnel sockets are conditionally removed from the known tunnels list
only if the socket is actually present in such a list.

Such check happens outside the socket lock scope: the current CPU
could observe an uninitialized list entry even if the tunnel has been
actually registered by a different core.

Address the issue moving the blamed check under the relevant list
spin lock.

Reported-by: syzbot+1fb3291cc1beeb3c315a@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=1fb3291cc1beeb3c315a
Fixes: 8d4880db37835 ("udp_tunnel: create a fastpath GRO lookup.")
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 include/net/udp_tunnel.h | 4 ----
 net/ipv4/udp_offload.c   | 3 ++-
 2 files changed, 2 insertions(+), 5 deletions(-)

diff --git a/include/net/udp_tunnel.h b/include/net/udp_tunnel.h
index a7b230867eb14..13b54e6856414 100644
--- a/include/net/udp_tunnel.h
+++ b/include/net/udp_tunnel.h
@@ -214,14 +214,10 @@ static inline void udp_tunnel_update_gro_rcv(struct sock *sk, bool add) {}
 
 static inline void udp_tunnel_cleanup_gro(struct sock *sk)
 {
-	struct udp_sock *up = udp_sk(sk);
 	struct net *net = sock_net(sk);
 
 	udp_tunnel_update_gro_rcv(sk, false);
 
-	if (!up->tunnel_list.pprev)
-		return;
-
 	udp_tunnel_update_gro_lookup(net, sk, false);
 }
 
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index fd2b8e3830beb..b124355a36aee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -57,10 +57,11 @@ void udp_tunnel_update_gro_lookup(struct net *net, struct sock *sk, bool add)
 	struct udp_tunnel_gro *udp_tunnel_gro;
 
 	spin_lock(&udp_tunnel_gro_lock);
+
 	udp_tunnel_gro = &net->ipv4.udp_tunnel_gro[is_ipv6];
 	if (add)
 		hlist_add_head(&up->tunnel_list, &udp_tunnel_gro->list);
-	else
+	else if (up->tunnel_list.pprev)
 		hlist_del_init(&up->tunnel_list);
 
 	if (udp_tunnel_gro->list.first &&

From ce68810713472bbdd0929d0749cd1f0f832a9dc2 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Mar 2025 12:52:55 +0100
Subject: [PATCH 2744/2753] udp_tunnel: avoid inconsistent local variables
 usage

In setup_udp_tunnel_sock() 'sk' and 'sock->sk' are alias. The code
I introduced there uses alternatively both variables, for no good
reasons.

Stick to 'sk' usage, to be consistent with the prior code.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/udp_tunnel_core.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index c49fceea83139..aa9016619c25a 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -90,10 +90,10 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_tunnel_encap_enable(sk);
 
-	udp_tunnel_update_gro_rcv(sock->sk, true);
+	udp_tunnel_update_gro_rcv(sk, true);
 
-	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sock->sk))
-		udp_tunnel_update_gro_lookup(net, sock->sk, true);
+	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk))
+		udp_tunnel_update_gro_lookup(net, sk, true);
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);
 

From b0d999d3ba89f25a6db6a531162d8057ee4c87ff Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 21 Mar 2025 12:52:56 +0100
Subject: [PATCH 2745/2753] udp_tunnel: prevent GRO lookup optimization for
 user-space sockets

UDP tunnel sockets owned by the kernel are never disconnected/rebound
after setup_udp_tunnel_sock(), but sockets owned by the user-space could
go through such changes after being matching the criteria to enable
the GRO lookup optimization, breaking them.

Explicitly prevent user-space owned sockets from leveraging such
optimization.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: NipaLocal <nipa@local>
---
 net/ipv4/udp_tunnel_core.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp_tunnel_core.c b/net/ipv4/udp_tunnel_core.c
index aa9016619c25a..2326548997d3f 100644
--- a/net/ipv4/udp_tunnel_core.c
+++ b/net/ipv4/udp_tunnel_core.c
@@ -92,7 +92,8 @@ void setup_udp_tunnel_sock(struct net *net, struct socket *sock,
 
 	udp_tunnel_update_gro_rcv(sk, true);
 
-	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk))
+	if (!sk->sk_dport && !sk->sk_bound_dev_if && sk_saddr_any(sk) &&
+	    sk->sk_kern_sock)
 		udp_tunnel_update_gro_lookup(net, sk, true);
 }
 EXPORT_SYMBOL_GPL(setup_udp_tunnel_sock);

From eda8e8ab5c3652ef74f2169df483167334c6c59b Mon Sep 17 00:00:00 2001
From: Qasim Ijaz <qasdev00@gmail.com>
Date: Fri, 21 Mar 2025 12:13:52 +0000
Subject: [PATCH 2746/2753] net: dl2k: fix potential null deref in
 receive_packet()

If the pkt_len is less than the copy_thresh the netdev_alloc_skb_ip_align()
is called to allocate an skbuff, on failure it can return NULL. Since
there is no NULL check a NULL deref can occur when setting
skb->protocol.

Fix this by introducing a NULL check to handle allocation failure.

Fixes: 89d71a66c40d ("net: Use netdev_alloc_skb_ip_align()")
Signed-off-by: Qasim Ijaz <qasdev00@gmail.com>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/ethernet/dlink/dl2k.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/net/ethernet/dlink/dl2k.c b/drivers/net/ethernet/dlink/dl2k.c
index d0ea926078706..0f3ce805b00da 100644
--- a/drivers/net/ethernet/dlink/dl2k.c
+++ b/drivers/net/ethernet/dlink/dl2k.c
@@ -968,6 +968,11 @@ receive_packet (struct net_device *dev)
 							   np->rx_buf_sz,
 							   DMA_FROM_DEVICE);
 			}
+
+			if (unlikely(!skb)) {
+				np->rx_ring[entry].fraginfo = 0;
+				break;
+			}
 			skb->protocol = eth_type_trans (skb, dev);
 #if 0
 			/* Checksum done by hw, but csum value unavailable. */

From 0163049ca6da8e5d193660e9bde42f9b2970ed7c Mon Sep 17 00:00:00 2001
From: Oleksij Rempel <o.rempel@pengutronix.de>
Date: Fri, 21 Mar 2025 15:10:44 +0100
Subject: [PATCH 2747/2753] net: dsa: microchip: fix DCB apptrust configuration
 on KSZ88x3

Remove KSZ88x3-specific priority and apptrust configuration logic that was
based on incorrect register access assumptions. Also fix the register
offset for KSZ8_REG_PORT_1_CTRL_0 to align with get_port_addr() logic.

The KSZ88x3 switch family uses a different register layout compared to
KSZ9477-compatible variants. Specifically, port control registers need
offset adjustment through get_port_addr(), and do not match the datasheet
values directly.

Commit a1ea57710c9d ("net: dsa: microchip: dcb: add special handling for
KSZ88X3 family") introduced quirks based on datasheet offsets, which do
not work with the driver's internal addressing model. As a result, these
quirks addressed the wrong ports and caused unstable behavior.

This patch removes all KSZ88x3-specific DCB quirks and corrects the port
control register offset, effectively restoring working and predictable
apptrust configuration.

Fixes: a1ea57710c9d ("net: dsa: microchip: dcb: add special handling for KSZ88X3 family")
Signed-off-by: Oleksij Rempel <o.rempel@pengutronix.de>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/net/dsa/microchip/ksz8.c    |  11 +-
 drivers/net/dsa/microchip/ksz_dcb.c | 231 +---------------------------
 2 files changed, 9 insertions(+), 233 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index da7110d675583..be433b4e2b1ca 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -1625,7 +1625,6 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	const u16 *regs = dev->info->regs;
 	struct dsa_switch *ds = dev->ds;
 	const u32 *masks;
-	int queues;
 	u8 member;
 
 	masks = dev->info->masks;
@@ -1633,15 +1632,7 @@ void ksz8_port_setup(struct ksz_device *dev, int port, bool cpu_port)
 	/* enable broadcast storm limit */
 	ksz_port_cfg(dev, port, P_BCAST_STORM_CTRL, PORT_BROADCAST_STORM, true);
 
-	/* For KSZ88x3 enable only one queue by default, otherwise we won't
-	 * be able to get rid of PCP prios on Port 2.
-	 */
-	if (ksz_is_ksz88x3(dev))
-		queues = 1;
-	else
-		queues = dev->info->num_tx_queues;
-
-	ksz8_port_queue_split(dev, port, queues);
+	ksz8_port_queue_split(dev, port, dev->info->num_tx_queues);
 
 	/* replace priority */
 	ksz_port_cfg(dev, port, P_802_1P_CTRL,
diff --git a/drivers/net/dsa/microchip/ksz_dcb.c b/drivers/net/dsa/microchip/ksz_dcb.c
index 30b4a6186e38f..c3b501997ac94 100644
--- a/drivers/net/dsa/microchip/ksz_dcb.c
+++ b/drivers/net/dsa/microchip/ksz_dcb.c
@@ -10,7 +10,12 @@
 #include "ksz_dcb.h"
 #include "ksz8.h"
 
-#define KSZ8_REG_PORT_1_CTRL_0			0x10
+/* Port X Control 0 register.
+ * The datasheet specifies: Port 1 - 0x10, Port 2 - 0x20, Port 3 - 0x30.
+ * However, the driver uses get_port_addr(), which maps Port 1 to offset 0.
+ * Therefore, we define the base offset as 0x00 here to align with that logic.
+ */
+#define KSZ8_REG_PORT_1_CTRL_0			0x00
 #define KSZ8_PORT_DIFFSERV_ENABLE		BIT(6)
 #define KSZ8_PORT_802_1P_ENABLE			BIT(5)
 #define KSZ8_PORT_BASED_PRIO_M			GENMASK(4, 3)
@@ -181,49 +186,6 @@ int ksz_port_get_default_prio(struct dsa_switch *ds, int port)
 	return (data & mask) >> shift;
 }
 
-/**
- * ksz88x3_port_set_default_prio_quirks - Quirks for default priority
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the default priority
- * @prio: Priority value to set
- *
- * This function implements quirks for setting the default priority on KSZ88x3
- * devices. On Port 2, no other priority providers are working
- * except of PCP. So, configuring default priority on Port 2 is not possible.
- * On Port 1, it is not possible to configure port priority if PCP
- * apptrust on Port 2 is disabled. Since we disable multiple queues on the
- * switch to disable PCP on Port 2, we need to ensure that the default priority
- * configuration on Port 1 is in agreement with the configuration on Port 2.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port_set_default_prio_quirks(struct ksz_device *dev, int port,
-						u8 prio)
-{
-	if (!prio)
-		return 0;
-
-	if (port == KSZ_PORT_2) {
-		dev_err(dev->dev, "Port priority configuration is not working on Port 2\n");
-		return -EINVAL;
-	} else if (port == KSZ_PORT_1) {
-		u8 port2_data;
-		int ret;
-
-		ret = ksz_pread8(dev, KSZ_PORT_2, KSZ8_REG_PORT_1_CTRL_0,
-				 &port2_data);
-		if (ret)
-			return ret;
-
-		if (!(port2_data & KSZ8_PORT_802_1P_ENABLE)) {
-			dev_err(dev->dev, "Not possible to configure port priority on Port 1 if PCP apptrust on Port 2 is disabled\n");
-			return -EINVAL;
-		}
-	}
-
-	return 0;
-}
-
 /**
  * ksz_port_set_default_prio - Sets the default priority for a port on a KSZ
  *			       switch
@@ -239,18 +201,12 @@ static int ksz88x3_port_set_default_prio_quirks(struct ksz_device *dev, int port
 int ksz_port_set_default_prio(struct dsa_switch *ds, int port, u8 prio)
 {
 	struct ksz_device *dev = ds->priv;
-	int reg, shift, ret;
+	int reg, shift;
 	u8 mask;
 
 	if (prio >= dev->info->num_ipms)
 		return -EINVAL;
 
-	if (ksz_is_ksz88x3(dev)) {
-		ret = ksz88x3_port_set_default_prio_quirks(dev, port, prio);
-		if (ret)
-			return ret;
-	}
-
 	ksz_get_default_port_prio_reg(dev, &reg, &mask, &shift);
 
 	return ksz_prmw8(dev, port, reg, mask, (prio << shift) & mask);
@@ -518,155 +474,6 @@ static int ksz_port_set_apptrust_validate(struct ksz_device *dev, int port,
 	return -EINVAL;
 }
 
-/**
- * ksz88x3_port1_apptrust_quirk - Quirk for apptrust configuration on Port 1
- *				  of KSZ88x3 devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @port1_data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on Port 1 of
- * KSZ88x3 devices. It ensures that apptrust configuration on Port 1 is not
- * possible if PCP apptrust on Port 2 is disabled. This is because the Port 2
- * seems to be permanently hardwired to PCP classification, so we need to
- * do Port 1 configuration always in agreement with Port 2 configuration.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port1_apptrust_quirk(struct ksz_device *dev, int port,
-					int reg, u8 port1_data)
-{
-	u8 port2_data;
-	int ret;
-
-	/* If no apptrust is requested for Port 1, no need to care about Port 2
-	 * configuration.
-	 */
-	if (!(port1_data & (KSZ8_PORT_802_1P_ENABLE | KSZ8_PORT_DIFFSERV_ENABLE)))
-		return 0;
-
-	/* We got request to enable any apptrust on Port 1. To make it possible,
-	 * we need to enable multiple queues on the switch. If we enable
-	 * multiqueue support, PCP classification on Port 2 will be
-	 * automatically activated by HW.
-	 */
-	ret = ksz_pread8(dev, KSZ_PORT_2, reg, &port2_data);
-	if (ret)
-		return ret;
-
-	/* If KSZ8_PORT_802_1P_ENABLE bit is set on Port 2, the driver showed
-	 * the interest in PCP classification on Port 2. In this case,
-	 * multiqueue support is enabled and we can enable any apptrust on
-	 * Port 1.
-	 * If KSZ8_PORT_802_1P_ENABLE bit is not set on Port 2, the PCP
-	 * classification on Port 2 is still active, but the driver disabled
-	 * multiqueue support and made frame prioritization inactive for
-	 * all ports. In this case, we can't enable any apptrust on Port 1.
-	 */
-	if (!(port2_data & KSZ8_PORT_802_1P_ENABLE)) {
-		dev_err(dev->dev, "Not possible to enable any apptrust on Port 1 if PCP apptrust on Port 2 is disabled\n");
-		return -EINVAL;
-	}
-
-	return 0;
-}
-
-/**
- * ksz88x3_port2_apptrust_quirk - Quirk for apptrust configuration on Port 2
- *				  of KSZ88x3 devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @port2_data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on Port 2 of
- * KSZ88x3 devices. It ensures that DSCP apptrust is not working on Port 2 and
- * that it is not possible to disable PCP on Port 2. The only way to disable PCP
- * on Port 2 is to disable multiple queues on the switch.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port2_apptrust_quirk(struct ksz_device *dev, int port,
-					int reg, u8 port2_data)
-{
-	struct dsa_switch *ds = dev->ds;
-	u8 port1_data;
-	int ret;
-
-	/* First validate Port 2 configuration. DiffServ/DSCP is not working
-	 * on this port.
-	 */
-	if (port2_data & KSZ8_PORT_DIFFSERV_ENABLE) {
-		dev_err(dev->dev, "DSCP apptrust is not working on Port 2\n");
-		return -EINVAL;
-	}
-
-	/* If PCP support is requested, we need to enable all queues on the
-	 * switch to make PCP priority working on Port 2.
-	 */
-	if (port2_data & KSZ8_PORT_802_1P_ENABLE)
-		return ksz8_all_queues_split(dev, dev->info->num_tx_queues);
-
-	/* We got request to disable PCP priority on Port 2.
-	 * Now, we need to compare Port 2 configuration with Port 1
-	 * configuration.
-	 */
-	ret = ksz_pread8(dev, KSZ_PORT_1, reg, &port1_data);
-	if (ret)
-		return ret;
-
-	/* If Port 1 has any apptrust enabled, we can't disable multiple queues
-	 * on the switch, so we can't disable PCP on Port 2.
-	 */
-	if (port1_data & (KSZ8_PORT_802_1P_ENABLE | KSZ8_PORT_DIFFSERV_ENABLE)) {
-		dev_err(dev->dev, "Not possible to disable PCP on Port 2 if any apptrust is enabled on Port 1\n");
-		return -EINVAL;
-	}
-
-	/* Now we need to ensure that default priority on Port 1 is set to 0
-	 * otherwise we can't disable multiqueue support on the switch.
-	 */
-	ret = ksz_port_get_default_prio(ds, KSZ_PORT_1);
-	if (ret < 0) {
-		return ret;
-	} else if (ret) {
-		dev_err(dev->dev, "Not possible to disable PCP on Port 2 if non zero default priority is set on Port 1\n");
-		return -EINVAL;
-	}
-
-	/* Port 1 has no apptrust or default priority set and we got request to
-	 * disable PCP on Port 2. We can disable multiqueue support to disable
-	 * PCP on Port 2.
-	 */
-	return ksz8_all_queues_split(dev, 1);
-}
-
-/**
- * ksz88x3_port_apptrust_quirk - Quirk for apptrust configuration on KSZ88x3
- *			       devices
- * @dev: Pointer to the KSZ switch device structure
- * @port: Port number for which to set the apptrust selectors
- * @reg: Register address for the apptrust configuration
- * @data: Data to set for the apptrust configuration
- *
- * This function implements a quirk for apptrust configuration on KSZ88x3
- * devices. It ensures that apptrust configuration on Port 1 and
- * Port 2 is done in agreement with each other.
- *
- * Return: 0 on success, or a negative error code on failure
- */
-static int ksz88x3_port_apptrust_quirk(struct ksz_device *dev, int port,
-				       int reg, u8 data)
-{
-	if (port == KSZ_PORT_1)
-		return ksz88x3_port1_apptrust_quirk(dev, port, reg, data);
-	else if (port == KSZ_PORT_2)
-		return ksz88x3_port2_apptrust_quirk(dev, port, reg, data);
-
-	return 0;
-}
-
 /**
  * ksz_port_set_apptrust - Sets the apptrust selectors for a port on a KSZ
  *			   switch
@@ -707,12 +514,6 @@ int ksz_port_set_apptrust(struct dsa_switch *ds, int port,
 		}
 	}
 
-	if (ksz_is_ksz88x3(dev)) {
-		ret = ksz88x3_port_apptrust_quirk(dev, port, reg, data);
-		if (ret)
-			return ret;
-	}
-
 	return ksz_prmw8(dev, port, reg, mask, data);
 }
 
@@ -799,21 +600,5 @@ int ksz_dcb_init_port(struct ksz_device *dev, int port)
  */
 int ksz_dcb_init(struct ksz_device *dev)
 {
-	int ret;
-
-	ret = ksz_init_global_dscp_map(dev);
-	if (ret)
-		return ret;
-
-	/* Enable 802.1p priority control on Port 2 during switch initialization.
-	 * This setup is critical for the apptrust functionality on Port 1, which
-	 * relies on the priority settings of Port 2. Note: Port 1 is naturally
-	 * configured before Port 2, necessitating this configuration order.
-	 */
-	if (ksz_is_ksz88x3(dev))
-		return ksz_prmw8(dev, KSZ_PORT_2, KSZ8_REG_PORT_1_CTRL_0,
-				 KSZ8_PORT_802_1P_ENABLE,
-				 KSZ8_PORT_802_1P_ENABLE);
-
-	return 0;
+	return ksz_init_global_dscp_map(dev);
 }

From 7811f980221a3cc373f45aa2fcda484116e77815 Mon Sep 17 00:00:00 2001
From: fedora Cloud User <fedora@ip-172-31-39-240.us-east-2.compute.internal>
Date: Thu, 1 Feb 2024 06:34:18 -0800
Subject: [PATCH 2748/2753] forwarding: set timeout to 3 hours

tc_actions.sh keeps hanging the forwarding tests.

sdf@: tdc & tdc-dbg started intermittenly failing around Sep 25th

Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/forwarding/settings | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/settings b/tools/testing/selftests/net/forwarding/settings
index e7b9417537fbc..ff3de4936a009 100644
--- a/tools/testing/selftests/net/forwarding/settings
+++ b/tools/testing/selftests/net/forwarding/settings
@@ -1 +1,2 @@
-timeout=0
+timeout=10800
+profile=1

From ab820eb93df262cb4fc16a6c362b0cab4828f8b4 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sat, 17 Aug 2024 10:53:12 -0700
Subject: [PATCH 2749/2753] profile patch

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/kselftest/prefix.pl | 8 ++++++++
 tools/testing/selftests/kselftest/runner.sh | 2 +-
 2 files changed, 9 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/kselftest/prefix.pl b/tools/testing/selftests/kselftest/prefix.pl
index 12a7f4ca2684d..b8e4d697e3b3a 100755
--- a/tools/testing/selftests/kselftest/prefix.pl
+++ b/tools/testing/selftests/kselftest/prefix.pl
@@ -4,12 +4,15 @@
 # to have unbuffering forced with "stdbuf -i0 -o0 -e0 $cmd".
 use strict;
 use IO::Handle;
+use Time::HiRes qw( time );
 
 binmode STDIN;
 binmode STDOUT;
 
 STDOUT->autoflush(1);
 
+my $start_time = time();
+my $prev_time = $start_time;
 my $needed = 1;
 while (1) {
 	my $char;
@@ -17,6 +20,11 @@
 	exit 0 if ($bytes == 0);
 	if ($needed) {
 		print "# ";
+		if ($ENV{kselftest_profile}) {
+			my $now = time();
+			printf("%.2f [+%.2f] ", $now - $start_time, $now - $prev_time);
+			$prev_time = $now;
+		}
 		$needed = 0;
 	}
 	print $char;
diff --git a/tools/testing/selftests/kselftest/runner.sh b/tools/testing/selftests/kselftest/runner.sh
index 2c3c58e65a419..e65bffb9981f8 100644
--- a/tools/testing/selftests/kselftest/runner.sh
+++ b/tools/testing/selftests/kselftest/runner.sh
@@ -89,7 +89,7 @@ run_one()
 			fi
 			field=$(echo "$line" | cut -d= -f1)
 			value=$(echo "$line" | cut -d= -f2-)
-			eval "kselftest_$field"="$value"
+			eval "export kselftest_$field"="$value"
 		done < "$settings"
 	fi
 

From fe2e5bf7e3408c30a2314cc15391828d9d2783ff Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Thu, 29 Aug 2024 19:57:39 -0700
Subject: [PATCH 2750/2753] tc_action dbg

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 .../selftests/net/forwarding/tc_actions.sh    | 26 ++++++++++++++-----
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh
index ea89e558672db..5823d94b19e9b 100755
--- a/tools/testing/selftests/net/forwarding/tc_actions.sh
+++ b/tools/testing/selftests/net/forwarding/tc_actions.sh
@@ -223,19 +223,32 @@ mirred_egress_to_ingress_tcp_test()
 		ip_proto icmp \
 			action drop
 
-	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 &
-	local rpid=$!
-	ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1
-	wait -n $rpid
-	cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2
-	check_err $? "server output check failed"
+	echo P2
 
 	$MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \
 		-t icmp "ping,id=42,seq=5" -q
+	echo P2.1
 	tc_check_packets "dev $h1 egress" 101 10
 	check_err $? "didn't mirred redirect ICMP"
+	echo P2.2
 	tc_check_packets "dev $h1 ingress" 102 10
 	check_err $? "didn't drop mirred ICMP"
+	echo P2.3
+
+	echo P1
+
+	ip vrf exec v$h1 ncat --recv-only -w10 -l -p 12345 -o $mirred_e2i_tf2 &
+	local rpid=$!
+	sleep 0.2
+	echo P1.1
+	ip vrf exec v$h1 ncat -w1 --send-only 192.0.2.2 12345 <$mirred_e2i_tf1
+	echo P1.2
+	sleep 0.2
+	wait -n $rpid
+	cmp -s $mirred_e2i_tf1 $mirred_e2i_tf2
+	check_err $? "server output check failed"
+
+	echo P3
 
 	tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower
 	tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower
@@ -359,4 +372,5 @@ else
 	tests_run
 fi
 
+dmesg
 exit $EXIT_STATUS

From 55165a59c5012103b91ef601e8d445a63c9aa623 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Sun, 3 Nov 2024 16:10:42 -0800
Subject: [PATCH 2751/2753] selftests: net: enable profiling

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/net/settings | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/settings b/tools/testing/selftests/net/settings
index ed8418e8217a0..a38764182822e 100644
--- a/tools/testing/selftests/net/settings
+++ b/tools/testing/selftests/net/settings
@@ -1 +1,2 @@
 timeout=3600
+profile=1

From 427ce098c52a701ee9a060b94d320d9445e3d4e3 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 3 Feb 2025 07:29:16 -0800
Subject: [PATCH 2752/2753] kunit: try to disable broken and unneccessary tests

Disable tests we don't care about, we use alltests in kunit.

Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: NipaLocal <nipa@local>
---
 drivers/firmware/cirrus/Kconfig              | 1 -
 lib/Kconfig.debug                            | 1 -
 tools/testing/kunit/configs/all_tests.config | 9 ---------
 3 files changed, 11 deletions(-)

diff --git a/drivers/firmware/cirrus/Kconfig b/drivers/firmware/cirrus/Kconfig
index 0a883091259a2..1fdf948535957 100644
--- a/drivers/firmware/cirrus/Kconfig
+++ b/drivers/firmware/cirrus/Kconfig
@@ -12,7 +12,6 @@ config FW_CS_DSP_KUNIT_TEST_UTILS
 config FW_CS_DSP_KUNIT_TEST
 	tristate "KUnit tests for Cirrus Logic cs_dsp" if !KUNIT_ALL_TESTS
 	depends on KUNIT && REGMAP
-	default KUNIT_ALL_TESTS
 	select FW_CS_DSP
 	select FW_CS_DSP_KUNIT_TEST_UTILS
 	help
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b63d0420f1f93..89b28b8ce095f 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2481,7 +2481,6 @@ config TEST_IDA
 config TEST_MISC_MINOR
 	tristate "Basic misc minor Kunit test" if !KUNIT_ALL_TESTS
 	depends on KUNIT
-	default KUNIT_ALL_TESTS
 	help
 	  Kunit test for the misc minor.
 	  It tests misc minor functions for dynamic and misc dynamic minor.
diff --git a/tools/testing/kunit/configs/all_tests.config b/tools/testing/kunit/configs/all_tests.config
index b0049be00c706..81f59d41202b8 100644
--- a/tools/testing/kunit/configs/all_tests.config
+++ b/tools/testing/kunit/configs/all_tests.config
@@ -35,17 +35,8 @@ CONFIG_MAC80211=y
 CONFIG_WLAN_VENDOR_INTEL=y
 CONFIG_IWLWIFI=y
 
-CONFIG_DAMON=y
-CONFIG_DAMON_VADDR=y
-CONFIG_DAMON_PADDR=y
-
 CONFIG_REGMAP_BUILD=y
 
 CONFIG_SECURITY=y
 CONFIG_SECURITY_APPARMOR=y
 CONFIG_SECURITY_LANDLOCK=y
-
-CONFIG_SOUND=y
-CONFIG_SND=y
-CONFIG_SND_SOC=y
-CONFIG_SND_SOC_TOPOLOGY_BUILD=y

From eccd0389eefe0a8e0d87f126cf8e05698f101b86 Mon Sep 17 00:00:00 2001
From: NipaLocal <nipa@local>
Date: Tue, 11 Mar 2025 22:49:47 -0700
Subject: [PATCH 2753/2753] drv: net: add timeout

Signed-off-by: NipaLocal <nipa@local>
---
 tools/testing/selftests/drivers/net/settings | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 tools/testing/selftests/drivers/net/settings

diff --git a/tools/testing/selftests/drivers/net/settings b/tools/testing/selftests/drivers/net/settings
new file mode 100644
index 0000000000000..a953c96aa16e1
--- /dev/null
+++ b/tools/testing/selftests/drivers/net/settings
@@ -0,0 +1 @@
+timeout=180